# Week 13 assignment page creation _Exported on 12/8/2025 at 08:50:05 EST from Cursor (2.1.39)_ --- **User** general guidelines: — for each image or video add a caption and description. — make all the text professional and succinct without losing key details — make the information as organized and as aesthetically pleasing as possible — don't just take my notes from the prompt, refine it before putting it on the page
 tasks: 1. make a copy of week12.html and called it week13.html. make sure its linked on index.html. populate the relevant resources from https://academy.cba.mit.edu/classes/wildcard/index.html in Useful Documentation, add a new subsection in Useful Documentation with all these references Refs datasheet https://ww1.microchip.com/downloads/en/DeviceDoc/ATtiny1624-26-27-DataSheet-DS40002234A.pdf pinout https://www.tindie.com/products/leonerd/attiny1626-development-board/ https://www.avrfreaks.net/s/topic/a5C3l000000UkLGEA0/t191222 course resources
https://academy.cba.mit.edu/classes/embedded_programming/index.html ATtiny412 t412-blink-4 pin pro sch pcb board components traces interior blink.ino t412-blink-3 pin board components traces mask traces+exterior interior blink.ino blink.c make video t412-blink-2 pin board components traces traces+exterior interior blink.ino video ring.ino t412-echo board componenets traces traces+exterior interior echo.ino video echo.c echo.make video https://academy.cba.mit.edu/classes/embedded_programming/t412/hello.t412.echo.png 2. add lecture and recitation notes from this week as two sections week13 lecture notes my theme of the week ‘step away from the panic’ major announcements do subject evaluation required for funding the class feedback to the institute about the class if you care about successors in the class calendar alarm — wildcard week and recitation on why make (almost) anything: impact friday is cutoff for assignments and orders 10s of dollars per person from inventory then final presentation/final exam combining multiple additive and subtractive processes (not just design a board and 3d print a case) goal is system integration out of parts final exam is did you finish a final project and does it do something and does it work 1) did you integrate and design a complete system 2) can you demo a final project? here is the cool thing I did and here is how it works 3) make a final project video! (helps but not required) -> focus on well-integrated device! review of week12 user interfaces claire wang music play and windows 3.1 interface works! ryan hoffman drv8251a discussion, heat sinks, breakout boards wildcards with waterjetting, edm, multi-axis machining, laser cutting metal class in the spring on nature of mathematical modeling srikanth nadhamuni background and experience to visiting fellow at mit raspberry pi w for wifi, n8n for cloud LLM data crunching software: node.js, mcp bridge server with n8n based on bridge connected to device (NGV tunnel) all set! fantastic experience, haven’t worked so hard in a very long time and learning a lot of new things hope to take forward and build other systems the whole culture of doing and trying yourself fascinating, especially with failing a number of times until you figure it out maybe set one up at an IIT in India or AI centers of excellence with education ministry into the Indian education system (see fablabkerala.in or vigyam ashram) ray song not here tyler jensen (Lincoln lab, group 81) final project discussion nylon printer week 13 easy for web serial interface for XIAO! web server to TFT (I think I forgot to load the camera pins with my code for it) aditi ramakrishnan sloan mba and strategy consulting background discrete time filter (fft is blown) in skimage.filters — make a bandpass filter, then run a series of these filters, much less computing only adds and multiplies for filtering in realtime alexandros gravalos not here edward chen check final watch project by gulati into watch form factor clear print on the form labs printer, 0.1 Kaman filter for sensor fusion (in the spring class) for position — lsm6dsv16x from input devices acceleration at 7 khz (at audio frequency) show and tell handle to sensor wifi user interface plug to audio llm user interface system integration reminders mount electronics strain relief the final projects preview for wildcard week assignment design and produce something with a digital process week13 recitation notes — why make (almost) anything map of fablabs why make a fablab used to create a community building things for the community sustainability prototyping quickly how impact? how to make spaces how to measure impact what is important about fab fablabs in cities vs rural areas the ability to decide their own futures and change their lives fundamentally ‘safecast revolutionized citizen science’ e.g. radiation map bringing back manufacturing reducing reliance on supply chains rural sustainability working with indigenous communities on creating technologies themselves at scale and measure their usefulness and efficacy to preserve their ancestral knowledge how to establish labs their how to make sure the labs get used hygiene technologies with proctor and gamble highly commercial lots of plastic waste how can we change how they produce? how to make their products get there through resellers? trip to peru and ran workshops, questionnaires, analysis collaboration developed into how to produce the products but also how to test their products to be market valuable e.g. mosquito repellents out of three plants, two worked better and one wasn’t working at all (which is important to know!) what does it mean to design infrastructure? what did we want this lab to be able to do? workshops and questionnaires how much you educate people based on the info they have with the issues the community is facing energy concerns to consider, some machines just drain the grid and can’t be used solar powered, battery powered machines, reducing energy consumption of machines many concerns important ethical questions how to maintain resources case study water purifier packets, use them, change them, source them locally, ingredients found locally, how to distribute them globally first few fablabs were nsf funded now corporate csr, regional funding, labor funding (10 different ways) successful fablabs are heterogeneous with lots of ways of funding the ones that fail usually just have one sponsor example DIY Raman spectrometer for water purification (even after purifications still have sulfates and improving that too) what does it mean to scale infrastructure? (besides a lot of meetings!) what is a reasonable way to design a data collection process about what is needed and how to achieve it back to the map: expansion timeline of development, cocreation, portable, skin analysis, water testing, biomaterial tech, microscopy initial results from boston how to confront local impact collab with university of hamburg motivation for how much food can be produced in Boston where food waste goes and what Boston produces locally make things for yourself locally impact directly in the community you’re living in hatchspace focused on rehabilitation of addicts with woodworking (vermont is wood producing state) example course program all-in session and systemic impact natural and cultural context skills and workshop economic vitality skills and workshop co-work session solutionspalooza in the course, hands-on component (no physical robot exists that can do it) and community component is also important inclusion is important solving unconscious and institutional biases ‘fabrica! lab’ — creating new laboratory spaces for female high school students, courses aimed for women in technology, online advising sessions for females interested in tech makerspaces — access to tools behind closed doors at universities, makes a huge difference for people who don’t have the ability to prototype for themselves materiom — fablab affiliated project on organic waste for biomaterials fablab león skylab workshop experiment — how to run a noodle shop out of a fablab (creating food from the community) academany — global distributed campus for high school education fablab all-in (belonging, impact, community), fab futures (future vocational skills), bio academy (synthetic biology), fabricademy (textiles, fab, bio), fab academy (digital fab apps and implications) trade-off between impactful and dangerous people could be doing bad, but not because doing it with a group people with values questions clarification: adding infrastructure to existing fablab infrastructure to help support specific community needs (not specialized fab labs) foundations for fab futures July 27-31, 2026 at fab boston 2026 3. update design files section to include either a link to a previous or upload a new folder from here. ATtiny_QFN folder and zip RP2354A-dev-v1.1 folder and zip for each put the images ATtiny1626-dev and ATtiny1626-dev-final RP2354A-dev 4. make individual and group assignment sections based on the assignment descriptions: Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment, documenting the requirements that your assignment meets, and including everything necessary to reproduce it. Possibilities include (but are not limited to): 5. for the individual assignment, summarize week13 pcb engraving assignment tool carvera first for edge cuts and machine the holes (too much for the laser) fiber laser cutter for pcb engraving boards simple: ATtiny1626-dev complex: RP2354A-dev datasheet https://ww1.microchip.com/downloads/en/DeviceDoc/ATtiny1624-26-27-DataSheet-DS40002234A.pdf pinout https://www.tindie.com/products/leonerd/attiny1626-development-board/ https://www.avrfreaks.net/s/topic/a5C3l000000UkLGEA0/t191222 course resources
https://academy.cba.mit.edu/classes/embedded_programming/index.html ATtiny412 t412-blink-4 pin pro sch pcb board components traces interior blink.ino t412-blink-3 pin board components traces mask traces+exterior interior blink.ino blink.c make video t412-blink-2 pin board components traces traces+exterior interior blink.ino video ring.ino t412-echo board componenets traces traces+exterior interior echo.ino video echo.c echo.make video https://academy.cba.mit.edu/classes/embedded_programming/t412/hello.t412.echo.png board design top and bottom for connectors, right side for flashing connectors along the edges to minimize form factor and maximize usage of space vertical connectors instead of horizontal connectors because the horizontal connectors risk being snapped avoid large black because laser does not work with that (keep traces closer and further to minimize black*) put connectors on 100mil spacing grid size for breadboardability *note — need to characterize maximum black until it burns the board because dumping too much heat in one place) missed six pins in initial design so switched from 6-pin headers to 9-pin (distributed six on top of bottom) no sda or scl resistors so we don’t regret it when we need the board for something else (maybe adding a spot for zero-ohm or pull-up resistor later but keeping it simple for now) adding aligned mounting holes (M3 usually — for 3mm screws) update footprint after editing the footprint (we had different x coordinates across the pins and needed to modify the footprint) rounded edge cuts — do 90 degrees, copy, drag, and complete the shape! design rules 0.1 mm spacing 0.15 mm trace width minimum 0.15mm clearance between plane and the rest ports and pins pa (0-7) pb (0-7) pc (0-7) 8-bit microcontroller, 8 pins max, each port has 8 pins maximum (some less) need to specify port letter and pin number postprocessing add new layer with just the holes in photoshop for carvera (only holes) get rid of the holes for the f2 tools engraving in inkscape (the frame and the board for alignment, then only engrave the board, not the edges) carvera machining mods -> mill 2d pcb 0.12mm cut depth and max depth pcb engraving xtool f2 ultra tape for laser alignment run a test first on spare copper before the carvera cut board to make sure focus is good (2.7mm thickness setting worked, board is actually 1.6-1.7mm thick) sand after worked with bantam tools fr1 (not the random amazon copper) short circuit test soldering using solder gun (heat gun) components 1x 6-pin flipflop headers 2x 9-pin flipflop headers 1x 4.7k resistor 1x 1k resistor 1x LED 1x 1uF or 10uF capacitor make sure to address everything in the assignment description: individual assignment: write an application that interfaces a user with an input &/or output device that you made include how the application interfaces with a user through an input and/or output device, then make a table with first column how it interfaces with the user, then column for input device(s), then column for output devices, make a row for a and a row for b add links to download all the relevant design files when you mention them embed all the relevant images and videos with the text design: ATtiny1626-dev-final engraving: ATtiny1626-dev-engraved soldered: ATtiny1626-dev-soldered blinking: ATtiny1626-dev-blinking 6. make sure there are no weird remnants from copying week11.html to week12.html --- **Cursor** Reviewing the existing files to understand the structure. Reading week12.html in sections to understand its structure: Reading more sections to understand the structure: Creating the initial todo list and starting week13.html: Copying week12.html to week13.html, then updating it: Updating week13.html, starting with the title and header: ```html Week 13 · Wildcard Week
← Back to Home
[Profile Image Placeholder]

Week 12

Interface & Application Programming

Week Highlights

Key captures from the group and individual assignments with links to their sections.

Button User Interface on OLED

OLED button user interface menu system

Hello World on OLED

Hello World display on OLED for Invisible String project

Pulse Oximeter Readings

Pulse oximeter readings showing IR, RED, and BPM values

Wi-Fi GUI Readings

Wi-Fi web interface displaying real-time pulse oximeter readings

Wi-Fi GUI Plots

Wi-Fi web interface with real-time plotting of pulse oximeter data

OLED Video Stream Demo

Grip Strength Gripper

CAD rendering of the full grip strength device with base, handle, and load cell Photo of the fully assembled grip strength device with electronics and handle

Load Cell Calibration Plot

Serial Plotter screenshot showing load cell readings rising with grip force

Grip Strength WiFi GUI

Table of Contents

Course Content

Training & Documentation

Assignments & Projects

Interface & Application Programming

This week focuses on creating user interfaces and applications that connect users with input and output devices. We'll explore interface design patterns, application programming techniques, and how to build interactive systems that provide meaningful user experiences.

Creating user interfaces for embedded devices
Building applications that interface with input and output devices
Comparing interface programming tools and frameworks

This Week's Goals

  • User Interface Design
    Learn to create intuitive interfaces for embedded devices and applications
  • Application Programming
    Build applications that interface users with input and/or output devices
  • Tool Comparison
    Compare interface programming tools and frameworks to select appropriate solutions

Assignments

  • Group Assignment
    Compare as many tool options as possible
  • Individual Assignment
    Write an application that interfaces a user with an input &/or output device that you made

Tools & Materials

  • ESP32-S3 Development Boards
  • OLED Displays (SSD1306)
  • MAX30102 Pulse Oximeter Sensor
  • Buttons & User Input Devices
  • Interface Programming Frameworks

Training Documentation

Training materials and documentation for interface and application programming.

No recitation this week.

Useful Documentation

Essential resources for interface and application programming.

Class Page

Interface and Application Programming - MIT Academy

Comprehensive resource covering interface design, application programming, GUI frameworks, embedded UI development, web interfaces for embedded systems, and user interaction patterns. Includes detailed tutorials, code examples, and implementation guides for various interface programming tools and frameworks.

Key Topics

  • Interface Design: User experience principles, interaction patterns, feedback mechanisms
  • Embedded UI: OLED displays, LCD interfaces, character displays
  • Web Interfaces: HTTP servers, REST APIs, WebSockets, real-time data visualization
  • Application Frameworks: GUI toolkits, web frameworks, mobile apps
  • User Input: Buttons, touch interfaces, gesture recognition, voice commands

Additional References

Individual Assignment: Interface & Application Programming

Write an application that interfaces a user with an input &/or output device that you made. This assignment demonstrates three interface applications: (a) a simple button user interface on OLED, (b) a real-time graphical user interface through OLED and Wi-Fi for pulse oximeter readings, and (c) a Wi-Fi grip strength monitor with a mechanical gripper and age-estimation web dashboard.

Part (a): Simple Button User Interface on OLED

A mode-based user interface system that interfaces users with multiple input and output devices through a simple button press interface. The system provides visual feedback on an OLED display and enables navigation between different modes (Menu, Camera, Sensors) using button press patterns. Users interact by pressing a button multiple times to select modes, with visual confirmation displayed on the OLED screen.

Interface Design

The interface uses a mode-based navigation system where button presses trigger mode changes. A single press enters Camera mode, two presses enter Sensors mode, three presses return to Menu, and holding the button activates a flashlight function. The OLED display shows the current menu state and provides clear visual feedback for each mode transition. See Ethical AI Use: Menu System with Modes for AI-assisted development details.

OLED button user interface menu system displaying mode selection options
OLED button user interface menuMenu screen showing available modes: Camera, Sensors, and Menu navigation options with button press instructions.
Button UI demonstrationVideo showing button press interactions navigating through different modes on the OLED display.
First video stream on OLEDInitial camera feed streaming to OLED display using dithering algorithm for monochrome conversion, demonstrating real-time video output interface.
Download Design Files
  • outputs.ino — Button user interface code with mode system
  • camera_pins.h — Camera pin definitions header file
  • outputs.zip — Complete project archive including all dependencies

Part (b): Real-Time Graphical User Interface through OLED and WiFi

A dual-interface health monitoring system that interfaces users with a MAX30102 pulse oximeter sensor through both an OLED display and a WiFi-enabled web interface. The system provides real-time visualization of heart rate (BPM), blood oxygen saturation (SpO2), and raw sensor data (IR and RED LED readings) through multiple output channels. Users can view data locally on the OLED display or remotely via a web browser accessing the ESP32-S3's built-in HTTP server. See Ethical AI Use: I2C Device Not Found for troubleshooting documentation.

Interface Design

The system provides dual-interface access: a local OLED display shows real-time sensor readings (IR, RED, BPM, SpO2) with visual heartbeat indicators, while a WiFi web interface provides comprehensive data visualization including numerical displays and real-time plotting charts. The web interface uses Chart.js for dynamic graph generation and automatically refreshes every 300ms to maintain real-time data updates. Both interfaces run simultaneously, enabling local monitoring and remote access.

Hello World on OLED

Initial OLED display test showing successful I2C communication and display initialization. See Ethical AI Use: Hello World Code for development details.

Hello World display on OLED for Invisible String project showing successful display initialization
Hello World on OLEDInitial OLED test confirming I2C communication and display functionality before implementing sensor interfaces.
Pulse Oximeter Readings on OLED

Real-time pulse oximeter data displayed on OLED showing IR and RED LED readings, heart rate (BPM), and blood oxygen saturation (SpO2) percentage. A heartbeat indicator flashes when a pulse is detected. See Ethical AI Use: MAX30102 Initialization Fix for sensor setup documentation.

Pulse oximeter readings on OLED displaying IR, RED, BPM, and SpO2 values
OLED sensor readings displayReal-time pulse oximeter data showing IR and RED LED values, heart rate (BPM), and blood oxygen saturation (SpO2) with heartbeat indicator.
BPM and SpO2 demonstrationVideo showing real-time heart rate and blood oxygen saturation measurements updating on OLED display with sensor interaction.
Pulse Oximeter Readings on WiFi GUI

WiFi web interface providing remote access to pulse oximeter data through a responsive HTML dashboard. The interface displays real-time numerical values for BPM, SpO2, IR, and RED readings with automatic data refresh. The web server runs on the ESP32-S3, allowing access from any device on the same WiFi network.

WiFi web interface displaying real-time pulse oximeter readings including BPM, SpO2, IR, and RED values
WiFi GUI readings dashboardRemote web interface showing real-time pulse oximeter data accessible from any device on the WiFi network, displaying BPM, SpO2, IR, and RED values with automatic updates.
Pulse Oximeter Plots on WiFi GUI

Enhanced WiFi web interface with real-time plotting capabilities using Chart.js library. The interface displays live line charts for BPM and SpO2 values, showing trends over time with automatic scrolling and data point management. This visualization enables users to observe patterns in heart rate and blood oxygen levels during monitoring sessions.

Serial monitor output showing sensor readings rising on touch interaction
Serial monitor sensor responseSerial output demonstrating sensor readings increase when finger is placed on MAX30102 sensor, showing IR and RED LED response to touch.
WiFi web interface with real-time plotting of BPM and SpO2 data using Chart.js
WiFi GUI with plotting chartsEnhanced web interface displaying real-time line charts for BPM and SpO2 values, showing trends over time with automatic data refresh and chart scrolling.

I2C Device Detection

Successful I2C device detection after fixing power isolation issues. The system now correctly identifies the OLED display at address 0x3C and the MAX30102 sensor at address 0x57. Initial troubleshooting required isolating the RD (red LED) and IRD (infrared LED) ground terminals from the general ground plane to prevent power issues and enable proper sensor operation. 

20:04:48.612 -> Scanning...
20:04:48.644 -> I2C device found at address 0x3C  !
20:04:48.644 -> I2C device found at address 0x57  !
20:04:48.644 -> done
Download Design Files

Part (c): Real-Time GUI through Mechanical Gripper and WiFi

A Wi-Fi-connected grip strength meter that interfaces a user with a mechanical hand gripper, an 80 kg load cell, and an HX711 amplifier. The ESP32-S3 continuously measures grip force, streams it to a web dashboard, and uses a published relationship between handgrip strength and age to display an estimated “physiological age” in real time. The design is inspired by the open-source grip strength meter from NeuroTech Hub at WashU and the associated PLOS ONE paper on grip strength and age trajectories (Syddall et al., 2014), adapted to my load cell and handle geometry.

Mechanically, a custom 3D-printed gripper clamps around a CZL601-type 80 kg bar load cell (sourced from Amazon 80 kg load cell). I imported a 100 kg load cell CAD from GrabCAD, checked the mounting dimensions against the CZL601AC datasheet (online, download), and confirmed that the hole spacing and footprint match the commercial part used here.

Mechanical Design and Fabrication

CAD model of the 3D-printed grip strength base and load cell mounting region
Grip strength base CADTop view of the grip strength base showing the bar load cell pocket, mounting bosses, and handle interface.
Side view CAD of the hand gripper and load cell assembly
Side view of gripper assemblySide profile showing how the fixed base, moving handle, and load cell align along the force axis of the bar sensor.
Full CAD view of the grip strength device with base and handle
Full grip strength assemblyComplete CAD of the base, handle, and load cell, sized for comfortable adult hand placement and full-finger contact.
Close-up of mounting holes and clearances around the load cell in CAD
Load cell mounting holesDetail of the M6 clearance and counterbore geometry used to capture the load cell without constraining bending.
Perspective CAD view of the gripper handle and base
Handle ergonomicsPerspective view of the curved handle designed to distribute pressure across the palm and fingers during maximal grip.
Photo of drilled clearance hole aligned to the printed pilot in the base
Clearance hole verificationPrinted pilot holes used as drill guides to match the metric mounting dimensions from the CZL601AC datasheet.
Photo of the fully printed grip strength device before drilling and assembly
Fresh off the printer3D-printed base and handle components in PLA prior to post-processing and hardware installation.
Printed part clamped for drilling load cell mounting holes
Workholding for accurate drillingThe printed base clamped to the drill press table so the pilot features guide the final clearance holes into the load cell.
Drilling practiceTraining cuts on scrap material to dial in drill press settings and avoid cracking the printed base during final holes.
Final load cell holesDrilling the final M6 clearance holes through the printed base, constrained by the pilot features to preserve alignment.

Electronics and Calibration

Electronics assembly with HX711 breakout, ESP32-S3, and load cell wiring
Electronics stack-upHX711 amplifier breakout from Amazon wired to the ESP32-S3 and 80 kg load cell with short, twisted signal pairs for noise reduction.
Fully assembled grip strength device with load cell, electronics, and handle
Assembled grip strength meterCompleted mechanical and electrical assembly ready for calibration and software bring-up.
Serial Plotter view of load cell readings increasing with grip force
Serial Plotter calibration tracesRaw HX711 output converted to kilograms and visualized in the Arduino Serial Plotter while applying known weights and grip forces.
Web GUI showing grip strength value, estimated age, and scrolling chart
Wi-Fi grip strength dashboardBrowser-based GUI with live grip strength (kg), estimated age, and a Chart.js time series plot of recent squeezes.

Model Used for Age Estimation

The age-estimation logic in the firmware is based on the non-linear, sex-specific grip-strength trajectories reported in Dodds et al., 2014 (PLOS ONE). As shown in Figure 1 of that paper, grip strength rises rapidly through adolescence, peaks around ages 30–40, and then declines non-linearly with age, with different magnitudes for males and females.

Reference grip strength trajectories over the life course from Dodds et al., PLOS ONE 2014
Reference trajectories (Figure 1)Age-dependent grip strength curves for males and females from Dodds et al., 2014, used as the qualitative target for the embedded model.
Simplified quadratic grip strength model fitted to reference data
Quadratic approximation (Table 2-inspired)Simplified male and female trajectories using peak strengths and curvatures chosen to approximate the summary values reported in Table 2 of Dodds et al., 2014.

To reproduce this shape efficiently on the ESP32, the firmware uses inverted quadratic approximations centered at age 35, consistent with the observed peak in the PLOS ONE data. In the forward direction, grip strength is approximated as:

Males: Grip(age) ≈ 52 − 0.0089·(age − 35)2
Females: Grip(age) ≈ 32 − 0.0059·(age − 35)2

On the device, this relationship is analytically inverted so that the measured grip strength can be mapped back to an estimated age:

age = 35 + √((a − Grip)/b), where a is the peak strength (52 kg for males, 32 kg for females) and b is the curvature (0.0089 for males, 0.0059 for females). The firmware clamps grip strength to physiologically meaningful ranges before applying this formula so the square root remains well-defined. 

float ageFromGripMale(float g) {
  float a = 52.0f, b = 0.0089f;
  if (g > a) g = a;
  if (g < 5) g = 5;
  return 35.0f + sqrtf((a - g) / b);
}

float ageFromGripFemale(float g) {
  float a = 32.0f, b = 0.0059f;
  if (g > a) g = a;
  if (g < 4) g = 4;
  return 35.0f + sqrtf((a - g) / b);
}

For full methodological details and original tables/figures, see the open-access paper: Dodds et al., 2014, PLOS ONE (download local PDF). The implementation here is an educational approximation and not intended for clinical or diagnostic use.

End-to-end live demoReal-time demonstration of squeezing the mechanical gripper and watching the Wi-Fi dashboard update grip strength and estimated age on a laptop.

Related Design, Code, and Calibration Resources

User Interface Comparison

Summary of how each interface application connects users with input and output devices.

Application How It Interfaces with the User Input Device(s) Output Device(s)
(a) Button User Interface Button press patterns (single, double, triple press, hold) provide mode selection input. OLED display shows current menu state and mode options. Users receive immediate visual feedback for each interaction. Button (GPIO pin 4) OLED Display (SSD1306, I²C 0x3C)
LED (GPIO pin 3, flashlight mode)
(b) Real-Time GUI (OLED & WiFi) Physical finger placement on MAX30102 sensor provides input. OLED displays real-time sensor data locally. WiFi web interface enables remote monitoring with numerical displays and live plotting charts accessible from any web browser. MAX30102 Pulse Oximeter Sensor (I²C 0x57) OLED Display (SSD1306, I²C 0x3C)
WiFi Web Interface (HTTP Server with Chart.js visualization)
(c) Grip Strength GUI (Load Cell & WiFi) Users squeeze a mechanical hand gripper that transfers force into an 80 kg bar load cell. The ESP32-S3 measures grip strength through the HX711 amplifier and streams results to a WiFi web dashboard that displays live grip force and an estimated physiological age in real time. Mechanical gripper linked to 80 kg load cell (CZL601-type)
HX711 load cell amplifier		 WiFi Web Interface (HTTP Server with Chart.js visualization)
Optional Serial Plotter (for calibration traces)

Group Assignment: Compare as Many Tool Options as Possible

Compare as many tool options as possible for interface and application programming.

General Comparison: Interface & Application Programming Tools

Comprehensive comparison of interface and application programming tools available for embedded systems and IoT development. This analysis covers tools from the MIT Academy Interface & Application Programming class page, evaluating their capabilities, use cases, and trade-offs for different application scenarios.

Embedded Display Interfaces

Tool/Framework Description Pros Cons Best For
OLED (SSD1306) Monochrome OLED displays via I²C Low power, high contrast, simple I²C interface, pixel-level control Limited resolution (128x64), monochrome only, small display size Status displays, sensor readouts, simple menus, embedded dashboards
LCD Character Displays Character-based LCD displays (16x2, 20x4) Simple API, readable in sunlight, low cost Limited to text/characters, no graphics, requires backlight power Text-only interfaces, status messages, debugging output
TFT Color Displays Full-color TFT LCD displays Color graphics, touch support, high resolution High power consumption, complex drivers, larger footprint Rich GUIs, image display, interactive touch interfaces

Web-Based Interfaces

Tool/Framework Description Pros Cons Best For
HTTP Server (ESP32) Built-in HTTP server on ESP32 for web interfaces Remote access, cross-platform (any browser), no app installation, real-time updates Requires WiFi, network dependency, limited to local network without port forwarding Remote monitoring, data visualization, control panels, sensor dashboards
WebSockets Real-time bidirectional communication Low latency, bidirectional, efficient for frequent updates More complex than HTTP, requires persistent connection Real-time streaming, interactive controls, live data feeds
Chart.js JavaScript charting library for web interfaces Beautiful charts, interactive, responsive, easy integration Requires JavaScript, CDN dependency or local hosting Data visualization, time series plots, sensor monitoring dashboards

Mobile & Native App Frameworks

Tool/Framework Description Pros Cons Best For
React Native Cross-platform mobile app framework Cross-platform (iOS/Android), native performance, large ecosystem Complex setup, requires mobile development knowledge Full-featured mobile apps, production deployments
Flutter Google's UI toolkit for cross-platform apps Single codebase, high performance, customizable UI Dart language, larger app size, learning curve Custom mobile interfaces, platform-specific designs
Progressive Web Apps (PWA) Web apps with native-like features No app store, cross-platform, offline capability Limited native API access, browser dependency Web-based mobile interfaces, simple deployment

Specific Comparison: Tools Used in Individual Assignment

Detailed comparison of the specific interface programming tools implemented in this week's individual assignment, evaluating their performance, ease of use, and suitability for embedded health monitoring applications.

OLED Display Interface (Adafruit SSD1306)

Aspect Evaluation
Ease of Implementation Simple I²C interface, well-documented Adafruit library, minimal wiring (SDA, SCL, power, ground)
Display Quality High contrast monochrome display, crisp text rendering, suitable for sensor data visualization
Power Consumption Very low power draw, ideal for battery-powered applications
Limitations 128x64 pixel resolution limits detail, monochrome only, small physical size (0.96" typical)
Best Use Cases Local sensor readouts, menu systems, status indicators, simple data displays

WiFi Web Interface (ESP32 HTTP Server + Chart.js)

Aspect Evaluation
Ease of Implementation ESP32 WebServer library provides straightforward HTTP server, Chart.js CDN integration requires minimal setup
Remote Access Accessible from any device on WiFi network (phone, tablet, computer), no app installation required
Visualization Capabilities Chart.js enables rich data visualization with real-time plotting, smooth animations, and interactive features
Real-Time Updates JSON API endpoint provides efficient data transfer, 300ms refresh rate maintains responsive feel
Limitations Requires WiFi network, limited to local network without additional configuration, power consumption higher than OLED alone
Best Use Cases Remote monitoring, data logging visualization, multi-user access, professional dashboards

Button Input Interface

Aspect Evaluation
Implementation Approach Digital GPIO reading with debouncing, press pattern detection (single/double/triple/hold) enables mode navigation
User Experience Intuitive press patterns, immediate visual feedback on OLED, no complex UI navigation required
Reliability Hardware debouncing with INPUT_PULLUP, timeout-based pattern recognition prevents accidental triggers
Limitations Limited to single button interaction, pattern learning required, less flexible than touchscreen interfaces
Best Use Cases Simple mode selection, menu navigation, embedded system controls, low-cost input solutions

Comparison Summary

The combination of OLED display and WiFi web interface provides complementary benefits: OLED offers immediate local feedback with minimal latency and power consumption, while the WiFi interface enables rich visualization and remote access. The button-based input provides an intuitive, low-cost navigation method suitable for embedded systems. Together, these tools create a robust interface system that supports both local and remote interaction with sensor data.

Design Files

Design files and code documentation for interface and application programming projects.

ESP32-S3 Development Board and Pinouts

Code files for ESP32-S3 development board interfaces including I2C scanning, OLED display control, and button-based user interface systems. See Week 4 documentation for board design and Week 8 documentation for pinout configurations.

I2C Scanner (i2cscan_generic.ino)

Utility code for scanning and detecting I2C devices on the bus, essential for troubleshooting connection issues.

How the Code Works (Pseudocode)
SETUP:
  Initialize I2C bus
  Initialize Serial communication
  Print "I2C Scanner" message

LOOP:
  Print "Scanning..." message
  Initialize device counter to 0
  
  FOR each address from 1 to 126:
    Begin I2C transmission to address
    Check transmission result
    
    IF transmission successful (error == 0):
      Print device found at address (hex format)
      Increment device counter
    ELSE IF unknown error (error == 4):
      Print unknown error at address
    
  IF no devices found:
    Print "No I2C devices found"
  ELSE:
    Print "done"
  
  Wait 5 seconds before next scan
Key Features
  • Scans all 127 possible I2C addresses (0x01-0x7E)
  • Detects and reports connected devices with hex address format
  • Handles multiple error conditions (device not found, unknown errors)
  • Continuous scanning mode with 5-second intervals
  • Compatible with any I2C bus configuration (Wire, Wire1, etc.)
What You Need to Know
  • I2C Address Range: Valid addresses are 0x08-0x77 (8-119 decimal); addresses 0x00-0x07 and 0x78-0x7F are reserved
  • Common Addresses: OLED displays typically use 0x3C or 0x3D; sensors vary (MAX30102 uses 0x57)
  • Troubleshooting: If no devices found, check wiring (SDA, SCL, power, ground), verify pull-up resistors, confirm device power
  • Usage: Run this before connecting other devices to verify I2C bus is working correctly
Download: i2cscan_generic.ino

Hello World OLED Display (hello_world.ino)

Basic OLED display test code that initializes the display and shows "Hello World" text, confirming I2C communication and display functionality.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial communication at 115200 baud
  Wait 500ms for Serial to stabilize
  
  Initialize I2C bus with SDA pin 5, SCL pin 6
  Print "Starting..." message
  
  Attempt to initialize OLED display:
    IF initialization fails:
      Print "OLED not found" error
      Enter infinite loop (halt)
  
  Clear display buffer
  Set text size to 2
  Set text color to white
  Set cursor position to (0, 20)
  Print "Hello" line
  Print "World!" line
  Update display (send buffer to hardware)

LOOP:
  Empty (runs once, then waits)
Key Features
  • Simple OLED initialization and text display
  • Custom I2C pin configuration for XIAO ESP32-S3 (SDA=5, SCL=6)
  • Error handling with infinite loop if display not found
  • Text size and cursor positioning for centered display
  • One-time display update (no loop refresh needed for static text)
What You Need to Know
  • I2C Pin Configuration: XIAO ESP32-S3 uses pins 5 (SDA) and 6 (SCL) by default; verify your board's pinout
  • Display Address: SSD1306 OLED typically uses address 0x3C; some variants use 0x3D
  • Display Update: Must call display.display() to send buffer to hardware; drawing functions only modify buffer
  • Testing: Use this as first test after connecting OLED to verify wiring and I2C communication before adding complex features
  • Libraries Required: Adafruit_GFX, Adafruit_SSD1306, Wire
Download: hello_world.ino

Button User Interface (outputs.ino)

Mode-based navigation system using button press patterns (single, double, triple, hold) to control multiple output devices including OLED display, camera, sensors, and LED flashlight.

How the Code Works (Pseudocode)
SETUP:
  Initialize OLED display
  Initialize camera module
  Initialize sensors (MPU6050, HX711)
  Initialize button pin (INPUT_PULLUP)
  Initialize LED pin (OUTPUT)
  Set current mode to MENU
  Display menu screen

LOOP:
  Read button state
  
  IF button pressed:
    Record press start time
    Start press detection timer
  
  IF button released:
    Calculate press duration
    IF duration > HOLD_THRESHOLD:
      Activate flashlight mode
    ELSE:
      Increment press count
      Reset press timeout timer
  
  IF press timeout exceeded:
    Process accumulated press count:
      IF press count == 1: Switch to CAMERA mode
      IF press count == 2: Switch to SENSORS mode
      IF press count == 3: Switch to MENU mode
    Reset press count
  
  IF current mode == MENU:
    Display menu screen (button instructions)
  
  IF current mode == CAMERA:
    Capture camera frame
    Process image with dithering algorithm
    Display on OLED
    Run Edge Impulse inference (optional)
    Overlay results on display
  
  IF current mode == SENSORS:
    Read accelerometer/gyroscope data
    Read load cell data
    Display sensor readings on OLED
  
  Update display
Key Features
  • Press pattern detection: single (1x), double (2x), triple (3x), and hold
  • Mode-based navigation system (Menu, Camera, Sensors)
  • Button debouncing with timeout-based pattern recognition
  • Floyd-Steinberg dithering for camera-to-OLED video display
  • Edge Impulse AI inference integration for face detection
  • Multi-sensor integration (MPU6050 accelerometer/gyro, HX711 load cell)
  • Flashlight mode activated by button hold
What You Need to Know
  • Button Wiring: Use INPUT_PULLUP mode (button connects pin to GND when pressed, internal pull-up to 3.3V)
  • Press Detection: Press count is accumulated until timeout (1 second); longer timeout allows slower multiple presses
  • Mode Switching: Each mode has distinct display update logic; ensure proper initialization in setup()
  • Camera Performance: Video streaming to OLED requires significant processing; frame rate depends on resolution and dithering complexity
  • Dependencies: Requires camera_pins.h header file with XIAO ESP32-S3 camera pin definitions; see Ethical AI Use for development details
  • Sensor Conflicts: Code uses preprocessor directives to resolve sensor_t type conflict between ESP32 camera and Adafruit MPU6050 libraries
Download: outputs.ino | camera_pins.h | outputs.zip (complete project)

Grip Strength Monitor (Load Cell + WiFi GUI)

Design files and firmware for a Wi-Fi-enabled grip strength meter built around an 80 kg bar load cell, HX711 amplifier, and ESP32-S3. The mechanical design was informed by the open-source grip strength meter from NeuroTech Hub and validated against the CZL601AC bar load cell datasheet (online, download).

Mechanical Design Files (3D-Printed Components)

  • Base.3mf — main chassis that captures the bar load cell and anchors the fixed side of the gripper.
  • Case.3mf — protective enclosure for the ESP32-S3 and HX711 amplifier with cable strain relief.
  • Handle.3mf — curved grip handle that transfers hand force into the free end of the load cell.
  • Calibration Print.3mf — small test piece used to verify hole diameters and load cell clearances before printing the full assembly.

All parts were printed in PLA with high infill in the load paths to minimize creep and flex during repeated maximal grip trials.

Basic HX711 Reader (loadcell_simple.ino)

Minimal firmware to bring up the HX711 amplifier and read calibrated weight values over Serial for debugging and calibration.

How the Code Works (Pseudocode)
SETUP:
  Configure HX711 data and clock pins (DT=A1, SCK=A0)
  Initialize Serial at 115200 baud
  Begin HX711 with DT/SCK pins
  Set calibration factor (grams per ADC unit)
  Tare the scale so current load is zero

LOOP (every 200 ms):
  If HX711 is ready:
    Read averaged weight using get_units(4)
    Print "weight:<value>" to Serial for Serial Plotter
  Else:
    Print "HX711 not ready" for troubleshooting
Key Features
  • Simple initialization of the HX711 on analog pins A0/A1.
  • Configurable calibration factor for mapping counts to grams or kilograms.
  • Timed reads (200 ms) to keep Serial output manageable and Plotter-friendly.
  • Graceful handling of HX711 not-ready states.
What You Need to Know
  • Use for initial bring-up: Run this first when wiring the HX711 and load cell to confirm clean, stable readings.
  • Calibration factor: Determined experimentally by hanging known weights and adjusting until readings match; see the calibration notes in Calibration Chat.
  • Serial Plotter: The weight:<value> format is convenient for quickly visualizing changes while squeezing the handle.
Download: loadcell_simple.ino

Serial Plotter-Friendly Reader (loadcell_plot.ino)

Refined HX711 reader tuned for the Arduino Serial Plotter: it outputs a single numeric value per line for clean plotting of grip strength over time.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial at 115200 baud
  Initialize HX711 on DT=A1, SCK=A0
  Set calibration factor
  Tare the scale
  Optionally print debug messages when DEBUG=1

LOOP (every 200 ms):
  If HX711 is ready:
    Read filtered weight with get_units(4)
    Optionally print labeled debug text
    Print only the numeric weight to Serial for the Plotter
  Else:
    Optionally print "not ready" debug text
    Print 0 so the plotted line continues gracefully
Key Features
  • DEBUG toggle: Compile-time switch to enable/disable human-readable logs without breaking the Serial Plotter format.
  • Clean “one number per line” output for multi-trial grip testing in the Serial Plotter.
  • Automatic zero output when the HX711 is not ready to keep the time axis continuous.
  • Shared pinout and calibration approach with loadcell_simple.ino for easy swapping.
What You Need to Know
  • Use this sketch to tune calibration and visualize grip curves without any GUI overhead.
  • When collecting data for analysis, keep DEBUG set to 0 so the output is a pure numeric stream.
  • The sample interval (200 ms) gives a smooth trace while keeping file sizes reasonable for multi-second squeezes.
Download: loadcell_plot.ino

WiFi Grip Strength GUI (loadcell_gui.ino)

Full application firmware that exposes grip strength and an estimated age over Wi-Fi using an HTTP server and a Chart.js web dashboard.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial
  Initialize HX711 (pins, calibration factor, tare)
  Connect ESP32-S3 to WiFi (MIT network in this build)
  Start WebServer on port 80
  Register handlers:
    "/"        → serve HTML+JS GUI page from PROGMEM
    "/metrics" → serve JSON with current grip and age

LOOP:
  Handle incoming HTTP clients
  Every 200 ms:
    If HX711 is ready:
      Read smoothed grip strength (kg) via get_units(3)
      Clamp negative values to zero
      Store in global gripStrength

AGE ESTIMATION HELPERS:
  ageFromGripMale(g):
    Clamp g to plausible range
    Compute age using inverted quadratic fit derived from normative data
  ageFromGripFemale(g):
    Same structure with female-specific parameters

HTTP /metrics ENDPOINT:
  Read "sex" query parameter (default "male")
  Compute ageEstimate = ageFromGripMale/ageFromGripFemale(gripStrength)
  Return JSON:
    {"grip": <kg>, "age": <years>}

CLIENT-SIDE GUI (HTML + JS):
  Render dark-themed dashboard with:
    - Sex toggle buttons (male/female)
    - Numeric grip strength (kg) and age
    - Scrolling Chart.js line plot of recent grip values
  Poll /metrics every 200 ms and update DOM + chart
Key Features
  • Embedded HTML/JS dashboard served directly from the ESP32-S3 using PROGMEM.
  • Real-time grip strength plot using Chart.js with ~120 recent samples.
  • Simple sex toggle that switches between male and female age-estimation curves.
  • JSON API at /metrics for future extensions (e.g., logging clients).
What You Need to Know
  • WiFi credentials: Update the ssid and password constants to match your network.
  • Normative model: The age equations are simplified fits inspired by the grip-strength trajectories reported in Syddall et al., PLOS ONE 2014 and are for educational visualization only, not clinical use.
  • Browser requirements: Any modern browser with JavaScript and network access can connect to the ESP32-S3’s IP address to view the dashboard.
  • Development log: The full iterative design of this sketch is captured in the ChatGPT transcript: Grip Strength Monitor Code Chat.
Download: loadcell_gui.ino

Invisible String Chain of Hearts

Code files for the Invisible String pulse oximeter interface system, providing real-time health monitoring through OLED display and WiFi web interface. See Week 11 PCB design documentation for hardware details.

OLED GUI for Pulse Oximeter (pulse_vo2_reads_fixing.ino)

Local OLED display interface showing real-time pulse oximeter readings including heart rate (BPM), blood oxygen saturation (SpO2), and raw IR/RED LED sensor values.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial communication
  Initialize I2C bus (SDA=5, SCL=6) at 400kHz
  Initialize MAX30102 sensor
  Configure sensor:
    Set LED mode to RED + IR
    Set ADC range to 16384
    Set sample rate to 100 Hz
    Set pulse width to 411 μs
    Set LED brightness to medium (0x3F)
  Initialize OLED display
  Clear and prepare display

LOOP:
  Read IR and RED LED values from sensor
  
  Heart Rate Detection:
    Check for heartbeat in IR signal using peak detection
    IF heartbeat detected:
      Calculate time since last beat
      Calculate BPM = 60 / (time_delta / 1000)
      Set beat flag for visual indicator
      Update last beat timestamp
  
  SpO2 Calculation (every 300ms):
    Add IR and RED values to circular buffer
    IF buffer has 50 samples:
      Calculate DC components (average)
      Calculate AC components (RMS)
      Calculate R ratio = (AC_RED/DC_RED) / (AC_IR/DC_IR)
      Estimate SpO2 = 110 - 25 * R
      Clamp SpO2 to 70-100% range
  
  Serial Output:
    Print IR, RED, BPM for Serial Plotter visualization
  
  OLED Display Update:
    Clear display buffer
    Display IR value (small text)
    Display RED value (small text)
    Display BPM value (large text, size 2)
    Display SpO2 percentage (small text)
    IF beat detected: Draw heartbeat indicator dot
    Update display hardware
  
  Delay 20ms (50 Hz update rate)
Key Features
  • Real-time heart rate detection using peak detection algorithm on IR signal
  • SpO2 calculation using ratio-of-ratios method with DC/AC component analysis
  • Circular buffer system for storing 50 samples of IR/RED data
  • Visual heartbeat indicator (flashing dot) when pulse detected
  • Dual output: OLED display and Serial Plotter for real-time waveform visualization
  • Optimized sensor configuration for reliable readings (100 Hz sample rate, medium brightness)
What You Need to Know
  • Sensor Placement: Finger must cover sensor completely; proper contact ensures accurate readings
  • I2C Address: MAX30102 uses address 0x57; verify with I2C scanner if sensor not detected
  • Ground Isolation: RD and IRD pins must be isolated from main ground plane to prevent power issues (see Week 11 PCB design)
  • SpO2 Accuracy: Calculation provides estimation; medical-grade accuracy requires calibration and FDA-approved algorithms
  • Buffer Size: 50-sample buffer provides balance between calculation accuracy and response time
  • Libraries Required: MAX30105 (SparkFun library), Adafruit_GFX, Adafruit_SSD1306, heartRate.h (beat detection)
  • Troubleshooting: If sensor not detected, check power isolation, I2C wiring, and sensor initialization order
Download: pulse_vo2_reads_fixing.ino

WiFi Readings GUI (pulse_gui.ino)

WiFi-enabled web interface providing remote access to pulse oximeter data through HTTP server with JSON API endpoint for real-time data updates.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial communication
  Initialize I2C bus
  Initialize MAX30102 sensor
  Configure sensor (LED mode, sample rate, pulse width)
  Initialize OLED display
  Initialize WiFi:
    Connect to network (SSID, password)
    Wait for connection
    Print IP address
  Initialize HTTP server:
    Route "/" → serve GUI HTML page
    Route "/gui" → serve GUI HTML page
    Route "/metrics" → serve JSON data
  Start web server

LOOP:
  Handle incoming HTTP client requests
  
  Read IR and RED values from sensor
  
  Heart Rate Calculation:
    Check for heartbeat in IR signal
    IF heartbeat detected:
      Calculate BPM from time delta
      Update global BPM variable
  
  SpO2 Calculation:
    Add IR/RED to circular buffer
    IF buffer full (50 samples):
      Calculate SpO2 using ratio-of-ratios
      Update global SpO2 variable
  
  Update global variables (g_ir, g_red, g_bpm, g_spo2)
  
  OLED Display Update:
    Display IR, RED, BPM, SpO2 values
    Update display hardware
Key Features
  • Dual interface: OLED display (local) and WiFi web interface (remote)
  • HTTP server with embedded HTML page stored in PROGMEM
  • JSON API endpoint (/metrics) for real-time data retrieval
  • Automatic WiFi connection with connection status feedback
  • IP address display for easy access
  • Simultaneous sensor reading and web server operation
  • Global variable system for data sharing between sensor reading and HTTP handlers
What You Need to Know
  • WiFi Configuration: Update SSID and password in code; for MIT network, use generated device password from wifi.mit.edu
  • Network Access: Web interface accessible only from devices on same WiFi network; IP address printed to Serial Monitor
  • HTML Storage: GUI HTML page stored in PROGMEM (program memory) to conserve RAM; use PROGMEM for large strings
  • Server Handling: Must call server.handleClient() frequently in loop() for responsive web interface
  • Data Refresh: Client-side JavaScript polls /metrics endpoint every 300ms for real-time updates
  • Power Consumption: WiFi significantly increases power draw compared to OLED-only mode; consider power management for battery operation
  • Libraries Required: WiFi, WebServer, MAX30105, Adafruit_SSD1306
Download: pulse_gui.ino

WiFi Plot GUI (pulse_gui_2.ino)

Enhanced WiFi web interface with real-time plotting capabilities using Chart.js library, displaying live line charts for BPM and SpO2 values with automatic scrolling and data management.

How the Code Works (Pseudocode)
SETUP:
  (Same as pulse_gui.ino)
  Initialize WiFi, sensor, OLED, HTTP server

LOOP:
  (Same as pulse_gui.ino)
  Handle HTTP requests, read sensor, calculate BPM/SpO2

GUI HTML PAGE (embedded in PROGMEM):
  Load Chart.js library from CDN
  Create two Chart.js line chart instances:
    - BPM chart (y-axis: 40-160 BPM)
    - SpO2 chart (y-axis: 70-100%)
  Initialize data arrays for each chart
  
  JavaScript Update Function (runs every 300ms):
    Fetch JSON data from /metrics endpoint
    Update numerical displays (BPM, SpO2, IR, RED)
    Add new BPM value to BPM data array
    Add new SpO2 value to SpO2 data array
    IF array length > maxPoints (100):
      Remove oldest value (shift)
    Update chart labels (array indices)
    Update chart datasets with new data
    Call chart.update() to refresh display
  
  Set interval to call update function every 300ms
Key Features
  • Real-time line chart visualization using Chart.js library
  • Dual chart display: BPM and SpO2 trends over time
  • Automatic data scrolling: maintains 100 most recent data points
  • Numerical displays alongside charts for precise values
  • Responsive design with dark theme for OLED-style aesthetic
  • Automatic chart scaling with fixed y-axis ranges for consistent visualization
  • CDN-based Chart.js loading for minimal memory footprint
What You Need to Know
  • Chart.js CDN: Library loaded from jsdelivr.net CDN; requires internet connection on client device
  • Data Management: Arrays limited to 100 points to prevent memory overflow; older data automatically discarded
  • Update Rate: 300ms refresh rate balances responsiveness with server load; adjust based on network conditions
  • Chart Configuration: Y-axis ranges fixed (BPM: 40-160, SpO2: 70-100) for consistent scaling; modify in JavaScript if needed
  • Browser Compatibility: Requires modern browser with JavaScript enabled; tested on Chrome, Firefox, Safari
  • Performance: Chart updates are lightweight; multiple simultaneous clients may impact ESP32 performance
  • Offline Operation: Charts won't load if client device lacks internet (Chart.js CDN unavailable); consider local hosting for offline use
Download: pulse_gui_2.ino

Reflections & Learnings

Key insights and learnings from working with interface and application programming.

Contributions

Acknowledgements and team roles for interface and application programming work.

Ethical AI Use

Transparent documentation of AI assistance used in this week's interface and application programming work.

This section documents all AI assistance used during Week 12 interface and application programming work. ChatGPT was used for code development, troubleshooting, and technical guidance. All transcripts are linked below for transparency.

Menu System with Modes

AI assistance for developing the button-based menu system with mode navigation (Menu, Camera, Sensors) using press pattern detection. The conversation covered button debouncing, press pattern recognition, mode state management, and OLED menu display design.

Related to: Part (a): Simple Button User Interface on OLED

View ChatGPT Transcript: Menu System with Modes

I2C Device Not Found

Troubleshooting session for I2C device detection issues with MAX30102 pulse oximeter sensor. The conversation addressed power isolation problems, I2C wiring verification, sensor initialization order, and ground plane isolation requirements for accurate sensor operation.

Related to: Part (b): Real-Time Graphical User Interface through OLED and WiFi

View ChatGPT Transcript: I2C Device Not Found

Hello World Code

Development assistance for creating the initial OLED "Hello World" test program. The conversation covered I2C initialization, OLED display library setup, text rendering, and basic display configuration for XIAO ESP32-S3 development board.

Related to: Part (b): Real-Time Graphical User Interface through OLED and WiFi (initial OLED test)

View ChatGPT Transcript: Hello World Code

MAX30102 Initialization Fix

Technical guidance for fixing MAX30102 pulse oximeter sensor initialization issues. The conversation addressed sensor configuration parameters, LED brightness settings, sample rate optimization, initialization sequence requirements, and troubleshooting sensor communication problems.

Related to: Part (b): Real-Time Graphical User Interface through OLED and WiFi (pulse oximeter readings)

View ChatGPT Transcript: MAX30102 Initialization Fix

Grip Strength Monitor Code Design

Code-focused assistance for designing and refining the WiFi grip strength monitor firmware. The conversation covered HX711 bring-up, load cell pin mapping, Serial Plotter debugging sketches, the ESP32-S3 HTTP server, the Chart.js dashboard, and the age-estimation helpers used in loadcell_simple.ino, loadcell_plot.ino, and loadcell_gui.ino.

Related to: Part (c): Real-Time GUI through Mechanical Gripper and WiFi and Grip Strength Monitor design files

View ChatGPT Transcript: Grip Strength Monitor Code

Grip Strength Calibration & Scaling

Calibration-focused assistance for mapping HX711 counts to kilograms and validating the grip strength readings. The discussion walked through using the Serial Plotter, collecting reference weights, tuning the calibration factor, and sanity-checking the age-estimation model derived from normative grip strength data.

Related to: Part (c): Real-Time GUI through Mechanical Gripper and WiFi calibration workflow and the Grip Strength Monitor sketches.

View ChatGPT Transcript: Grip Strength Calibration

Grip Strength Monitor – Cursor Transcript

Full Cursor AI transcript focused on organizing the grip strength monitor section: structuring Part (c), integrating design files, embedding images and videos, and aligning captions, external references, and the Ethical AI Use documentation for the load cell project.

Related to: Part (c): Real-Time GUI through Mechanical Gripper and WiFi, Grip Strength Monitor design files, and this Ethical AI Use section.

View HTML Transcript Download Markdown Transcript

Week 12 Project Documentation

Complete Cursor AI transcript for Week 12 interface and application programming project documentation. This comprehensive conversation covers the creation and population of the Week 12 HTML page, including Individual Assignment sections (button UI and WiFi GUI), Group Assignment tool comparisons, Design Files documentation with pseudocode, and Ethical AI Use section organization. The transcript demonstrates the collaborative process of building professional documentation with structured content, embedded media, and comprehensive code documentation.

Related to: Complete Week 12 documentation including Individual Assignment, Group Assignment, Design Files, and overall page structure

View HTML Transcript Download Markdown Transcript

Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License

``` ```html Week 13 · Wildcard Week
← Back to Home
[Profile Image Placeholder]

Week 13

Wildcard Week

Week Highlights

Key captures from the group and individual assignments with links to their sections.

Button User Interface on OLED

OLED button user interface menu system

Hello World on OLED

Hello World display on OLED for Invisible String project

Pulse Oximeter Readings

Pulse oximeter readings showing IR, RED, and BPM values

Wi-Fi GUI Readings

Wi-Fi web interface displaying real-time pulse oximeter readings

Wi-Fi GUI Plots

Wi-Fi web interface with real-time plotting of pulse oximeter data

OLED Video Stream Demo

Grip Strength Gripper

CAD rendering of the full grip strength device with base, handle, and load cell Photo of the fully assembled grip strength device with electronics and handle

Load Cell Calibration Plot

Serial Plotter screenshot showing load cell readings rising with grip force

Grip Strength WiFi GUI

Table of Contents

Course Content

Training & Documentation

Assignments & Projects

Interface & Application Programming

This week focuses on creating user interfaces and applications that connect users with input and output devices. We'll explore interface design patterns, application programming techniques, and how to build interactive systems that provide meaningful user experiences.

Creating user interfaces for embedded devices
Building applications that interface with input and output devices
Comparing interface programming tools and frameworks

This Week's Goals

  • User Interface Design
    Learn to create intuitive interfaces for embedded devices and applications
  • Application Programming
    Build applications that interface users with input and/or output devices
  • Tool Comparison
    Compare interface programming tools and frameworks to select appropriate solutions

Assignments

  • Group Assignment
    Compare as many tool options as possible
  • Individual Assignment
    Write an application that interfaces a user with an input &/or output device that you made

Tools & Materials

  • ESP32-S3 Development Boards
  • OLED Displays (SSD1306)
  • MAX30102 Pulse Oximeter Sensor
  • Buttons & User Input Devices
  • Interface Programming Frameworks

Training Documentation

Training materials and documentation for interface and application programming.

No recitation this week.

Useful Documentation

Essential resources for interface and application programming.

Class Page

Interface and Application Programming - MIT Academy

Comprehensive resource covering interface design, application programming, GUI frameworks, embedded UI development, web interfaces for embedded systems, and user interaction patterns. Includes detailed tutorials, code examples, and implementation guides for various interface programming tools and frameworks.

Key Topics

  • Interface Design: User experience principles, interaction patterns, feedback mechanisms
  • Embedded UI: OLED displays, LCD interfaces, character displays
  • Web Interfaces: HTTP servers, REST APIs, WebSockets, real-time data visualization
  • Application Frameworks: GUI toolkits, web frameworks, mobile apps
  • User Input: Buttons, touch interfaces, gesture recognition, voice commands

Additional References

Individual Assignment: Interface & Application Programming

Write an application that interfaces a user with an input &/or output device that you made. This assignment demonstrates three interface applications: (a) a simple button user interface on OLED, (b) a real-time graphical user interface through OLED and Wi-Fi for pulse oximeter readings, and (c) a Wi-Fi grip strength monitor with a mechanical gripper and age-estimation web dashboard.

Part (a): Simple Button User Interface on OLED

A mode-based user interface system that interfaces users with multiple input and output devices through a simple button press interface. The system provides visual feedback on an OLED display and enables navigation between different modes (Menu, Camera, Sensors) using button press patterns. Users interact by pressing a button multiple times to select modes, with visual confirmation displayed on the OLED screen.

Interface Design

The interface uses a mode-based navigation system where button presses trigger mode changes. A single press enters Camera mode, two presses enter Sensors mode, three presses return to Menu, and holding the button activates a flashlight function. The OLED display shows the current menu state and provides clear visual feedback for each mode transition. See Ethical AI Use: Menu System with Modes for AI-assisted development details.

OLED button user interface menu system displaying mode selection options
OLED button user interface menuMenu screen showing available modes: Camera, Sensors, and Menu navigation options with button press instructions.
Button UI demonstrationVideo showing button press interactions navigating through different modes on the OLED display.
First video stream on OLEDInitial camera feed streaming to OLED display using dithering algorithm for monochrome conversion, demonstrating real-time video output interface.
Download Design Files
  • outputs.ino — Button user interface code with mode system
  • camera_pins.h — Camera pin definitions header file
  • outputs.zip — Complete project archive including all dependencies

Part (b): Real-Time Graphical User Interface through OLED and WiFi

A dual-interface health monitoring system that interfaces users with a MAX30102 pulse oximeter sensor through both an OLED display and a WiFi-enabled web interface. The system provides real-time visualization of heart rate (BPM), blood oxygen saturation (SpO2), and raw sensor data (IR and RED LED readings) through multiple output channels. Users can view data locally on the OLED display or remotely via a web browser accessing the ESP32-S3's built-in HTTP server. See Ethical AI Use: I2C Device Not Found for troubleshooting documentation.

Interface Design

The system provides dual-interface access: a local OLED display shows real-time sensor readings (IR, RED, BPM, SpO2) with visual heartbeat indicators, while a WiFi web interface provides comprehensive data visualization including numerical displays and real-time plotting charts. The web interface uses Chart.js for dynamic graph generation and automatically refreshes every 300ms to maintain real-time data updates. Both interfaces run simultaneously, enabling local monitoring and remote access.

Hello World on OLED

Initial OLED display test showing successful I2C communication and display initialization. See Ethical AI Use: Hello World Code for development details.

Hello World display on OLED for Invisible String project showing successful display initialization
Hello World on OLEDInitial OLED test confirming I2C communication and display functionality before implementing sensor interfaces.
Pulse Oximeter Readings on OLED

Real-time pulse oximeter data displayed on OLED showing IR and RED LED readings, heart rate (BPM), and blood oxygen saturation (SpO2) percentage. A heartbeat indicator flashes when a pulse is detected. See Ethical AI Use: MAX30102 Initialization Fix for sensor setup documentation.

Pulse oximeter readings on OLED displaying IR, RED, BPM, and SpO2 values
OLED sensor readings displayReal-time pulse oximeter data showing IR and RED LED values, heart rate (BPM), and blood oxygen saturation (SpO2) with heartbeat indicator.
BPM and SpO2 demonstrationVideo showing real-time heart rate and blood oxygen saturation measurements updating on OLED display with sensor interaction.
Pulse Oximeter Readings on WiFi GUI

WiFi web interface providing remote access to pulse oximeter data through a responsive HTML dashboard. The interface displays real-time numerical values for BPM, SpO2, IR, and RED readings with automatic data refresh. The web server runs on the ESP32-S3, allowing access from any device on the same WiFi network.

WiFi web interface displaying real-time pulse oximeter readings including BPM, SpO2, IR, and RED values
WiFi GUI readings dashboardRemote web interface showing real-time pulse oximeter data accessible from any device on the WiFi network, displaying BPM, SpO2, IR, and RED values with automatic updates.
Pulse Oximeter Plots on WiFi GUI

Enhanced WiFi web interface with real-time plotting capabilities using Chart.js library. The interface displays live line charts for BPM and SpO2 values, showing trends over time with automatic scrolling and data point management. This visualization enables users to observe patterns in heart rate and blood oxygen levels during monitoring sessions.

Serial monitor output showing sensor readings rising on touch interaction
Serial monitor sensor responseSerial output demonstrating sensor readings increase when finger is placed on MAX30102 sensor, showing IR and RED LED response to touch.
WiFi web interface with real-time plotting of BPM and SpO2 data using Chart.js
WiFi GUI with plotting chartsEnhanced web interface displaying real-time line charts for BPM and SpO2 values, showing trends over time with automatic data refresh and chart scrolling.

I2C Device Detection

Successful I2C device detection after fixing power isolation issues. The system now correctly identifies the OLED display at address 0x3C and the MAX30102 sensor at address 0x57. Initial troubleshooting required isolating the RD (red LED) and IRD (infrared LED) ground terminals from the general ground plane to prevent power issues and enable proper sensor operation. 

20:04:48.612 -> Scanning...
20:04:48.644 -> I2C device found at address 0x3C  !
20:04:48.644 -> I2C device found at address 0x57  !
20:04:48.644 -> done
Download Design Files

Part (c): Real-Time GUI through Mechanical Gripper and WiFi

A Wi-Fi-connected grip strength meter that interfaces a user with a mechanical hand gripper, an 80 kg load cell, and an HX711 amplifier. The ESP32-S3 continuously measures grip force, streams it to a web dashboard, and uses a published relationship between handgrip strength and age to display an estimated “physiological age” in real time. The design is inspired by the open-source grip strength meter from NeuroTech Hub at WashU and the associated PLOS ONE paper on grip strength and age trajectories (Syddall et al., 2014), adapted to my load cell and handle geometry.

Mechanically, a custom 3D-printed gripper clamps around a CZL601-type 80 kg bar load cell (sourced from Amazon 80 kg load cell). I imported a 100 kg load cell CAD from GrabCAD, checked the mounting dimensions against the CZL601AC datasheet (online, download), and confirmed that the hole spacing and footprint match the commercial part used here.

Mechanical Design and Fabrication

CAD model of the 3D-printed grip strength base and load cell mounting region
Grip strength base CADTop view of the grip strength base showing the bar load cell pocket, mounting bosses, and handle interface.
Side view CAD of the hand gripper and load cell assembly
Side view of gripper assemblySide profile showing how the fixed base, moving handle, and load cell align along the force axis of the bar sensor.
Full CAD view of the grip strength device with base and handle
Full grip strength assemblyComplete CAD of the base, handle, and load cell, sized for comfortable adult hand placement and full-finger contact.
Close-up of mounting holes and clearances around the load cell in CAD
Load cell mounting holesDetail of the M6 clearance and counterbore geometry used to capture the load cell without constraining bending.
Perspective CAD view of the gripper handle and base
Handle ergonomicsPerspective view of the curved handle designed to distribute pressure across the palm and fingers during maximal grip.
Photo of drilled clearance hole aligned to the printed pilot in the base
Clearance hole verificationPrinted pilot holes used as drill guides to match the metric mounting dimensions from the CZL601AC datasheet.
Photo of the fully printed grip strength device before drilling and assembly
Fresh off the printer3D-printed base and handle components in PLA prior to post-processing and hardware installation.
Printed part clamped for drilling load cell mounting holes
Workholding for accurate drillingThe printed base clamped to the drill press table so the pilot features guide the final clearance holes into the load cell.
Drilling practiceTraining cuts on scrap material to dial in drill press settings and avoid cracking the printed base during final holes.
Final load cell holesDrilling the final M6 clearance holes through the printed base, constrained by the pilot features to preserve alignment.

Electronics and Calibration

Electronics assembly with HX711 breakout, ESP32-S3, and load cell wiring
Electronics stack-upHX711 amplifier breakout from Amazon wired to the ESP32-S3 and 80 kg load cell with short, twisted signal pairs for noise reduction.
Fully assembled grip strength device with load cell, electronics, and handle
Assembled grip strength meterCompleted mechanical and electrical assembly ready for calibration and software bring-up.
Serial Plotter view of load cell readings increasing with grip force
Serial Plotter calibration tracesRaw HX711 output converted to kilograms and visualized in the Arduino Serial Plotter while applying known weights and grip forces.
Web GUI showing grip strength value, estimated age, and scrolling chart
Wi-Fi grip strength dashboardBrowser-based GUI with live grip strength (kg), estimated age, and a Chart.js time series plot of recent squeezes.

Model Used for Age Estimation

The age-estimation logic in the firmware is based on the non-linear, sex-specific grip-strength trajectories reported in Dodds et al., 2014 (PLOS ONE). As shown in Figure 1 of that paper, grip strength rises rapidly through adolescence, peaks around ages 30–40, and then declines non-linearly with age, with different magnitudes for males and females.

Reference grip strength trajectories over the life course from Dodds et al., PLOS ONE 2014
Reference trajectories (Figure 1)Age-dependent grip strength curves for males and females from Dodds et al., 2014, used as the qualitative target for the embedded model.
Simplified quadratic grip strength model fitted to reference data
Quadratic approximation (Table 2-inspired)Simplified male and female trajectories using peak strengths and curvatures chosen to approximate the summary values reported in Table 2 of Dodds et al., 2014.

To reproduce this shape efficiently on the ESP32, the firmware uses inverted quadratic approximations centered at age 35, consistent with the observed peak in the PLOS ONE data. In the forward direction, grip strength is approximated as:

Males: Grip(age) ≈ 52 − 0.0089·(age − 35)2
Females: Grip(age) ≈ 32 − 0.0059·(age − 35)2

On the device, this relationship is analytically inverted so that the measured grip strength can be mapped back to an estimated age:

age = 35 + √((a − Grip)/b), where a is the peak strength (52 kg for males, 32 kg for females) and b is the curvature (0.0089 for males, 0.0059 for females). The firmware clamps grip strength to physiologically meaningful ranges before applying this formula so the square root remains well-defined. 

float ageFromGripMale(float g) {
  float a = 52.0f, b = 0.0089f;
  if (g > a) g = a;
  if (g < 5) g = 5;
  return 35.0f + sqrtf((a - g) / b);
}

float ageFromGripFemale(float g) {
  float a = 32.0f, b = 0.0059f;
  if (g > a) g = a;
  if (g < 4) g = 4;
  return 35.0f + sqrtf((a - g) / b);
}

For full methodological details and original tables/figures, see the open-access paper: Dodds et al., 2014, PLOS ONE (download local PDF). The implementation here is an educational approximation and not intended for clinical or diagnostic use.

End-to-end live demoReal-time demonstration of squeezing the mechanical gripper and watching the Wi-Fi dashboard update grip strength and estimated age on a laptop.

Related Design, Code, and Calibration Resources

User Interface Comparison

Summary of how each interface application connects users with input and output devices.

Application How It Interfaces with the User Input Device(s) Output Device(s)
(a) Button User Interface Button press patterns (single, double, triple press, hold) provide mode selection input. OLED display shows current menu state and mode options. Users receive immediate visual feedback for each interaction. Button (GPIO pin 4) OLED Display (SSD1306, I²C 0x3C)
LED (GPIO pin 3, flashlight mode)
(b) Real-Time GUI (OLED & WiFi) Physical finger placement on MAX30102 sensor provides input. OLED displays real-time sensor data locally. WiFi web interface enables remote monitoring with numerical displays and live plotting charts accessible from any web browser. MAX30102 Pulse Oximeter Sensor (I²C 0x57) OLED Display (SSD1306, I²C 0x3C)
WiFi Web Interface (HTTP Server with Chart.js visualization)
(c) Grip Strength GUI (Load Cell & WiFi) Users squeeze a mechanical hand gripper that transfers force into an 80 kg bar load cell. The ESP32-S3 measures grip strength through the HX711 amplifier and streams results to a WiFi web dashboard that displays live grip force and an estimated physiological age in real time. Mechanical gripper linked to 80 kg load cell (CZL601-type)
HX711 load cell amplifier		 WiFi Web Interface (HTTP Server with Chart.js visualization)
Optional Serial Plotter (for calibration traces)

Group Assignment: Compare as Many Tool Options as Possible

Compare as many tool options as possible for interface and application programming.

General Comparison: Interface & Application Programming Tools

Comprehensive comparison of interface and application programming tools available for embedded systems and IoT development. This analysis covers tools from the MIT Academy Interface & Application Programming class page, evaluating their capabilities, use cases, and trade-offs for different application scenarios.

Embedded Display Interfaces

Tool/Framework Description Pros Cons Best For
OLED (SSD1306) Monochrome OLED displays via I²C Low power, high contrast, simple I²C interface, pixel-level control Limited resolution (128x64), monochrome only, small display size Status displays, sensor readouts, simple menus, embedded dashboards
LCD Character Displays Character-based LCD displays (16x2, 20x4) Simple API, readable in sunlight, low cost Limited to text/characters, no graphics, requires backlight power Text-only interfaces, status messages, debugging output
TFT Color Displays Full-color TFT LCD displays Color graphics, touch support, high resolution High power consumption, complex drivers, larger footprint Rich GUIs, image display, interactive touch interfaces

Web-Based Interfaces

Tool/Framework Description Pros Cons Best For
HTTP Server (ESP32) Built-in HTTP server on ESP32 for web interfaces Remote access, cross-platform (any browser), no app installation, real-time updates Requires WiFi, network dependency, limited to local network without port forwarding Remote monitoring, data visualization, control panels, sensor dashboards
WebSockets Real-time bidirectional communication Low latency, bidirectional, efficient for frequent updates More complex than HTTP, requires persistent connection Real-time streaming, interactive controls, live data feeds
Chart.js JavaScript charting library for web interfaces Beautiful charts, interactive, responsive, easy integration Requires JavaScript, CDN dependency or local hosting Data visualization, time series plots, sensor monitoring dashboards

Mobile & Native App Frameworks

Tool/Framework Description Pros Cons Best For
React Native Cross-platform mobile app framework Cross-platform (iOS/Android), native performance, large ecosystem Complex setup, requires mobile development knowledge Full-featured mobile apps, production deployments
Flutter Google's UI toolkit for cross-platform apps Single codebase, high performance, customizable UI Dart language, larger app size, learning curve Custom mobile interfaces, platform-specific designs
Progressive Web Apps (PWA) Web apps with native-like features No app store, cross-platform, offline capability Limited native API access, browser dependency Web-based mobile interfaces, simple deployment

Specific Comparison: Tools Used in Individual Assignment

Detailed comparison of the specific interface programming tools implemented in this week's individual assignment, evaluating their performance, ease of use, and suitability for embedded health monitoring applications.

OLED Display Interface (Adafruit SSD1306)

Aspect Evaluation
Ease of Implementation Simple I²C interface, well-documented Adafruit library, minimal wiring (SDA, SCL, power, ground)
Display Quality High contrast monochrome display, crisp text rendering, suitable for sensor data visualization
Power Consumption Very low power draw, ideal for battery-powered applications
Limitations 128x64 pixel resolution limits detail, monochrome only, small physical size (0.96" typical)
Best Use Cases Local sensor readouts, menu systems, status indicators, simple data displays

WiFi Web Interface (ESP32 HTTP Server + Chart.js)

Aspect Evaluation
Ease of Implementation ESP32 WebServer library provides straightforward HTTP server, Chart.js CDN integration requires minimal setup
Remote Access Accessible from any device on WiFi network (phone, tablet, computer), no app installation required
Visualization Capabilities Chart.js enables rich data visualization with real-time plotting, smooth animations, and interactive features
Real-Time Updates JSON API endpoint provides efficient data transfer, 300ms refresh rate maintains responsive feel
Limitations Requires WiFi network, limited to local network without additional configuration, power consumption higher than OLED alone
Best Use Cases Remote monitoring, data logging visualization, multi-user access, professional dashboards

Button Input Interface

Aspect Evaluation
Implementation Approach Digital GPIO reading with debouncing, press pattern detection (single/double/triple/hold) enables mode navigation
User Experience Intuitive press patterns, immediate visual feedback on OLED, no complex UI navigation required
Reliability Hardware debouncing with INPUT_PULLUP, timeout-based pattern recognition prevents accidental triggers
Limitations Limited to single button interaction, pattern learning required, less flexible than touchscreen interfaces
Best Use Cases Simple mode selection, menu navigation, embedded system controls, low-cost input solutions

Comparison Summary

The combination of OLED display and WiFi web interface provides complementary benefits: OLED offers immediate local feedback with minimal latency and power consumption, while the WiFi interface enables rich visualization and remote access. The button-based input provides an intuitive, low-cost navigation method suitable for embedded systems. Together, these tools create a robust interface system that supports both local and remote interaction with sensor data.

Design Files

Design files and code documentation for interface and application programming projects.

ESP32-S3 Development Board and Pinouts

Code files for ESP32-S3 development board interfaces including I2C scanning, OLED display control, and button-based user interface systems. See Week 4 documentation for board design and Week 8 documentation for pinout configurations.

I2C Scanner (i2cscan_generic.ino)

Utility code for scanning and detecting I2C devices on the bus, essential for troubleshooting connection issues.

How the Code Works (Pseudocode)
SETUP:
  Initialize I2C bus
  Initialize Serial communication
  Print "I2C Scanner" message

LOOP:
  Print "Scanning..." message
  Initialize device counter to 0
  
  FOR each address from 1 to 126:
    Begin I2C transmission to address
    Check transmission result
    
    IF transmission successful (error == 0):
      Print device found at address (hex format)
      Increment device counter
    ELSE IF unknown error (error == 4):
      Print unknown error at address
    
  IF no devices found:
    Print "No I2C devices found"
  ELSE:
    Print "done"
  
  Wait 5 seconds before next scan
Key Features
  • Scans all 127 possible I2C addresses (0x01-0x7E)
  • Detects and reports connected devices with hex address format
  • Handles multiple error conditions (device not found, unknown errors)
  • Continuous scanning mode with 5-second intervals
  • Compatible with any I2C bus configuration (Wire, Wire1, etc.)
What You Need to Know
  • I2C Address Range: Valid addresses are 0x08-0x77 (8-119 decimal); addresses 0x00-0x07 and 0x78-0x7F are reserved
  • Common Addresses: OLED displays typically use 0x3C or 0x3D; sensors vary (MAX30102 uses 0x57)
  • Troubleshooting: If no devices found, check wiring (SDA, SCL, power, ground), verify pull-up resistors, confirm device power
  • Usage: Run this before connecting other devices to verify I2C bus is working correctly
Download: i2cscan_generic.ino

Hello World OLED Display (hello_world.ino)

Basic OLED display test code that initializes the display and shows "Hello World" text, confirming I2C communication and display functionality.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial communication at 115200 baud
  Wait 500ms for Serial to stabilize
  
  Initialize I2C bus with SDA pin 5, SCL pin 6
  Print "Starting..." message
  
  Attempt to initialize OLED display:
    IF initialization fails:
      Print "OLED not found" error
      Enter infinite loop (halt)
  
  Clear display buffer
  Set text size to 2
  Set text color to white
  Set cursor position to (0, 20)
  Print "Hello" line
  Print "World!" line
  Update display (send buffer to hardware)

LOOP:
  Empty (runs once, then waits)
Key Features
  • Simple OLED initialization and text display
  • Custom I2C pin configuration for XIAO ESP32-S3 (SDA=5, SCL=6)
  • Error handling with infinite loop if display not found
  • Text size and cursor positioning for centered display
  • One-time display update (no loop refresh needed for static text)
What You Need to Know
  • I2C Pin Configuration: XIAO ESP32-S3 uses pins 5 (SDA) and 6 (SCL) by default; verify your board's pinout
  • Display Address: SSD1306 OLED typically uses address 0x3C; some variants use 0x3D
  • Display Update: Must call display.display() to send buffer to hardware; drawing functions only modify buffer
  • Testing: Use this as first test after connecting OLED to verify wiring and I2C communication before adding complex features
  • Libraries Required: Adafruit_GFX, Adafruit_SSD1306, Wire
Download: hello_world.ino

Button User Interface (outputs.ino)

Mode-based navigation system using button press patterns (single, double, triple, hold) to control multiple output devices including OLED display, camera, sensors, and LED flashlight.

How the Code Works (Pseudocode)
SETUP:
  Initialize OLED display
  Initialize camera module
  Initialize sensors (MPU6050, HX711)
  Initialize button pin (INPUT_PULLUP)
  Initialize LED pin (OUTPUT)
  Set current mode to MENU
  Display menu screen

LOOP:
  Read button state
  
  IF button pressed:
    Record press start time
    Start press detection timer
  
  IF button released:
    Calculate press duration
    IF duration > HOLD_THRESHOLD:
      Activate flashlight mode
    ELSE:
      Increment press count
      Reset press timeout timer
  
  IF press timeout exceeded:
    Process accumulated press count:
      IF press count == 1: Switch to CAMERA mode
      IF press count == 2: Switch to SENSORS mode
      IF press count == 3: Switch to MENU mode
    Reset press count
  
  IF current mode == MENU:
    Display menu screen (button instructions)
  
  IF current mode == CAMERA:
    Capture camera frame
    Process image with dithering algorithm
    Display on OLED
    Run Edge Impulse inference (optional)
    Overlay results on display
  
  IF current mode == SENSORS:
    Read accelerometer/gyroscope data
    Read load cell data
    Display sensor readings on OLED
  
  Update display
Key Features
  • Press pattern detection: single (1x), double (2x), triple (3x), and hold
  • Mode-based navigation system (Menu, Camera, Sensors)
  • Button debouncing with timeout-based pattern recognition
  • Floyd-Steinberg dithering for camera-to-OLED video display
  • Edge Impulse AI inference integration for face detection
  • Multi-sensor integration (MPU6050 accelerometer/gyro, HX711 load cell)
  • Flashlight mode activated by button hold
What You Need to Know
  • Button Wiring: Use INPUT_PULLUP mode (button connects pin to GND when pressed, internal pull-up to 3.3V)
  • Press Detection: Press count is accumulated until timeout (1 second); longer timeout allows slower multiple presses
  • Mode Switching: Each mode has distinct display update logic; ensure proper initialization in setup()
  • Camera Performance: Video streaming to OLED requires significant processing; frame rate depends on resolution and dithering complexity
  • Dependencies: Requires camera_pins.h header file with XIAO ESP32-S3 camera pin definitions; see Ethical AI Use for development details
  • Sensor Conflicts: Code uses preprocessor directives to resolve sensor_t type conflict between ESP32 camera and Adafruit MPU6050 libraries
Download: outputs.ino | camera_pins.h | outputs.zip (complete project)

Grip Strength Monitor (Load Cell + WiFi GUI)

Design files and firmware for a Wi-Fi-enabled grip strength meter built around an 80 kg bar load cell, HX711 amplifier, and ESP32-S3. The mechanical design was informed by the open-source grip strength meter from NeuroTech Hub and validated against the CZL601AC bar load cell datasheet (online, download).

Mechanical Design Files (3D-Printed Components)

  • Base.3mf — main chassis that captures the bar load cell and anchors the fixed side of the gripper.
  • Case.3mf — protective enclosure for the ESP32-S3 and HX711 amplifier with cable strain relief.
  • Handle.3mf — curved grip handle that transfers hand force into the free end of the load cell.
  • Calibration Print.3mf — small test piece used to verify hole diameters and load cell clearances before printing the full assembly.

All parts were printed in PLA with high infill in the load paths to minimize creep and flex during repeated maximal grip trials.

Basic HX711 Reader (loadcell_simple.ino)

Minimal firmware to bring up the HX711 amplifier and read calibrated weight values over Serial for debugging and calibration.

How the Code Works (Pseudocode)
SETUP:
  Configure HX711 data and clock pins (DT=A1, SCK=A0)
  Initialize Serial at 115200 baud
  Begin HX711 with DT/SCK pins
  Set calibration factor (grams per ADC unit)
  Tare the scale so current load is zero

LOOP (every 200 ms):
  If HX711 is ready:
    Read averaged weight using get_units(4)
    Print "weight:<value>" to Serial for Serial Plotter
  Else:
    Print "HX711 not ready" for troubleshooting
Key Features
  • Simple initialization of the HX711 on analog pins A0/A1.
  • Configurable calibration factor for mapping counts to grams or kilograms.
  • Timed reads (200 ms) to keep Serial output manageable and Plotter-friendly.
  • Graceful handling of HX711 not-ready states.
What You Need to Know
  • Use for initial bring-up: Run this first when wiring the HX711 and load cell to confirm clean, stable readings.
  • Calibration factor: Determined experimentally by hanging known weights and adjusting until readings match; see the calibration notes in Calibration Chat.
  • Serial Plotter: The weight:<value> format is convenient for quickly visualizing changes while squeezing the handle.
Download: loadcell_simple.ino

Serial Plotter-Friendly Reader (loadcell_plot.ino)

Refined HX711 reader tuned for the Arduino Serial Plotter: it outputs a single numeric value per line for clean plotting of grip strength over time.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial at 115200 baud
  Initialize HX711 on DT=A1, SCK=A0
  Set calibration factor
  Tare the scale
  Optionally print debug messages when DEBUG=1

LOOP (every 200 ms):
  If HX711 is ready:
    Read filtered weight with get_units(4)
    Optionally print labeled debug text
    Print only the numeric weight to Serial for the Plotter
  Else:
    Optionally print "not ready" debug text
    Print 0 so the plotted line continues gracefully
Key Features
  • DEBUG toggle: Compile-time switch to enable/disable human-readable logs without breaking the Serial Plotter format.
  • Clean “one number per line” output for multi-trial grip testing in the Serial Plotter.
  • Automatic zero output when the HX711 is not ready to keep the time axis continuous.
  • Shared pinout and calibration approach with loadcell_simple.ino for easy swapping.
What You Need to Know
  • Use this sketch to tune calibration and visualize grip curves without any GUI overhead.
  • When collecting data for analysis, keep DEBUG set to 0 so the output is a pure numeric stream.
  • The sample interval (200 ms) gives a smooth trace while keeping file sizes reasonable for multi-second squeezes.
Download: loadcell_plot.ino

WiFi Grip Strength GUI (loadcell_gui.ino)

Full application firmware that exposes grip strength and an estimated age over Wi-Fi using an HTTP server and a Chart.js web dashboard.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial
  Initialize HX711 (pins, calibration factor, tare)
  Connect ESP32-S3 to WiFi (MIT network in this build)
  Start WebServer on port 80
  Register handlers:
    "/"        → serve HTML+JS GUI page from PROGMEM
    "/metrics" → serve JSON with current grip and age

LOOP:
  Handle incoming HTTP clients
  Every 200 ms:
    If HX711 is ready:
      Read smoothed grip strength (kg) via get_units(3)
      Clamp negative values to zero
      Store in global gripStrength

AGE ESTIMATION HELPERS:
  ageFromGripMale(g):
    Clamp g to plausible range
    Compute age using inverted quadratic fit derived from normative data
  ageFromGripFemale(g):
    Same structure with female-specific parameters

HTTP /metrics ENDPOINT:
  Read "sex" query parameter (default "male")
  Compute ageEstimate = ageFromGripMale/ageFromGripFemale(gripStrength)
  Return JSON:
    {"grip": <kg>, "age": <years>}

CLIENT-SIDE GUI (HTML + JS):
  Render dark-themed dashboard with:
    - Sex toggle buttons (male/female)
    - Numeric grip strength (kg) and age
    - Scrolling Chart.js line plot of recent grip values
  Poll /metrics every 200 ms and update DOM + chart
Key Features
  • Embedded HTML/JS dashboard served directly from the ESP32-S3 using PROGMEM.
  • Real-time grip strength plot using Chart.js with ~120 recent samples.
  • Simple sex toggle that switches between male and female age-estimation curves.
  • JSON API at /metrics for future extensions (e.g., logging clients).
What You Need to Know
  • WiFi credentials: Update the ssid and password constants to match your network.
  • Normative model: The age equations are simplified fits inspired by the grip-strength trajectories reported in Syddall et al., PLOS ONE 2014 and are for educational visualization only, not clinical use.
  • Browser requirements: Any modern browser with JavaScript and network access can connect to the ESP32-S3’s IP address to view the dashboard.
  • Development log: The full iterative design of this sketch is captured in the ChatGPT transcript: Grip Strength Monitor Code Chat.
Download: loadcell_gui.ino

Invisible String Chain of Hearts

Code files for the Invisible String pulse oximeter interface system, providing real-time health monitoring through OLED display and WiFi web interface. See Week 11 PCB design documentation for hardware details.

OLED GUI for Pulse Oximeter (pulse_vo2_reads_fixing.ino)

Local OLED display interface showing real-time pulse oximeter readings including heart rate (BPM), blood oxygen saturation (SpO2), and raw IR/RED LED sensor values.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial communication
  Initialize I2C bus (SDA=5, SCL=6) at 400kHz
  Initialize MAX30102 sensor
  Configure sensor:
    Set LED mode to RED + IR
    Set ADC range to 16384
    Set sample rate to 100 Hz
    Set pulse width to 411 μs
    Set LED brightness to medium (0x3F)
  Initialize OLED display
  Clear and prepare display

LOOP:
  Read IR and RED LED values from sensor
  
  Heart Rate Detection:
    Check for heartbeat in IR signal using peak detection
    IF heartbeat detected:
      Calculate time since last beat
      Calculate BPM = 60 / (time_delta / 1000)
      Set beat flag for visual indicator
      Update last beat timestamp
  
  SpO2 Calculation (every 300ms):
    Add IR and RED values to circular buffer
    IF buffer has 50 samples:
      Calculate DC components (average)
      Calculate AC components (RMS)
      Calculate R ratio = (AC_RED/DC_RED) / (AC_IR/DC_IR)
      Estimate SpO2 = 110 - 25 * R
      Clamp SpO2 to 70-100% range
  
  Serial Output:
    Print IR, RED, BPM for Serial Plotter visualization
  
  OLED Display Update:
    Clear display buffer
    Display IR value (small text)
    Display RED value (small text)
    Display BPM value (large text, size 2)
    Display SpO2 percentage (small text)
    IF beat detected: Draw heartbeat indicator dot
    Update display hardware
  
  Delay 20ms (50 Hz update rate)
Key Features
  • Real-time heart rate detection using peak detection algorithm on IR signal
  • SpO2 calculation using ratio-of-ratios method with DC/AC component analysis
  • Circular buffer system for storing 50 samples of IR/RED data
  • Visual heartbeat indicator (flashing dot) when pulse detected
  • Dual output: OLED display and Serial Plotter for real-time waveform visualization
  • Optimized sensor configuration for reliable readings (100 Hz sample rate, medium brightness)
What You Need to Know
  • Sensor Placement: Finger must cover sensor completely; proper contact ensures accurate readings
  • I2C Address: MAX30102 uses address 0x57; verify with I2C scanner if sensor not detected
  • Ground Isolation: RD and IRD pins must be isolated from main ground plane to prevent power issues (see Week 11 PCB design)
  • SpO2 Accuracy: Calculation provides estimation; medical-grade accuracy requires calibration and FDA-approved algorithms
  • Buffer Size: 50-sample buffer provides balance between calculation accuracy and response time
  • Libraries Required: MAX30105 (SparkFun library), Adafruit_GFX, Adafruit_SSD1306, heartRate.h (beat detection)
  • Troubleshooting: If sensor not detected, check power isolation, I2C wiring, and sensor initialization order
Download: pulse_vo2_reads_fixing.ino

WiFi Readings GUI (pulse_gui.ino)

WiFi-enabled web interface providing remote access to pulse oximeter data through HTTP server with JSON API endpoint for real-time data updates.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial communication
  Initialize I2C bus
  Initialize MAX30102 sensor
  Configure sensor (LED mode, sample rate, pulse width)
  Initialize OLED display
  Initialize WiFi:
    Connect to network (SSID, password)
    Wait for connection
    Print IP address
  Initialize HTTP server:
    Route "/" → serve GUI HTML page
    Route "/gui" → serve GUI HTML page
    Route "/metrics" → serve JSON data
  Start web server

LOOP:
  Handle incoming HTTP client requests
  
  Read IR and RED values from sensor
  
  Heart Rate Calculation:
    Check for heartbeat in IR signal
    IF heartbeat detected:
      Calculate BPM from time delta
      Update global BPM variable
  
  SpO2 Calculation:
    Add IR/RED to circular buffer
    IF buffer full (50 samples):
      Calculate SpO2 using ratio-of-ratios
      Update global SpO2 variable
  
  Update global variables (g_ir, g_red, g_bpm, g_spo2)
  
  OLED Display Update:
    Display IR, RED, BPM, SpO2 values
    Update display hardware
Key Features
  • Dual interface: OLED display (local) and WiFi web interface (remote)
  • HTTP server with embedded HTML page stored in PROGMEM
  • JSON API endpoint (/metrics) for real-time data retrieval
  • Automatic WiFi connection with connection status feedback
  • IP address display for easy access
  • Simultaneous sensor reading and web server operation
  • Global variable system for data sharing between sensor reading and HTTP handlers
What You Need to Know
  • WiFi Configuration: Update SSID and password in code; for MIT network, use generated device password from wifi.mit.edu
  • Network Access: Web interface accessible only from devices on same WiFi network; IP address printed to Serial Monitor
  • HTML Storage: GUI HTML page stored in PROGMEM (program memory) to conserve RAM; use PROGMEM for large strings
  • Server Handling: Must call server.handleClient() frequently in loop() for responsive web interface
  • Data Refresh: Client-side JavaScript polls /metrics endpoint every 300ms for real-time updates
  • Power Consumption: WiFi significantly increases power draw compared to OLED-only mode; consider power management for battery operation
  • Libraries Required: WiFi, WebServer, MAX30105, Adafruit_SSD1306
Download: pulse_gui.ino

WiFi Plot GUI (pulse_gui_2.ino)

Enhanced WiFi web interface with real-time plotting capabilities using Chart.js library, displaying live line charts for BPM and SpO2 values with automatic scrolling and data management.

How the Code Works (Pseudocode)
SETUP:
  (Same as pulse_gui.ino)
  Initialize WiFi, sensor, OLED, HTTP server

LOOP:
  (Same as pulse_gui.ino)
  Handle HTTP requests, read sensor, calculate BPM/SpO2

GUI HTML PAGE (embedded in PROGMEM):
  Load Chart.js library from CDN
  Create two Chart.js line chart instances:
    - BPM chart (y-axis: 40-160 BPM)
    - SpO2 chart (y-axis: 70-100%)
  Initialize data arrays for each chart
  
  JavaScript Update Function (runs every 300ms):
    Fetch JSON data from /metrics endpoint
    Update numerical displays (BPM, SpO2, IR, RED)
    Add new BPM value to BPM data array
    Add new SpO2 value to SpO2 data array
    IF array length > maxPoints (100):
      Remove oldest value (shift)
    Update chart labels (array indices)
    Update chart datasets with new data
    Call chart.update() to refresh display
  
  Set interval to call update function every 300ms
Key Features
  • Real-time line chart visualization using Chart.js library
  • Dual chart display: BPM and SpO2 trends over time
  • Automatic data scrolling: maintains 100 most recent data points
  • Numerical displays alongside charts for precise values
  • Responsive design with dark theme for OLED-style aesthetic
  • Automatic chart scaling with fixed y-axis ranges for consistent visualization
  • CDN-based Chart.js loading for minimal memory footprint
What You Need to Know
  • Chart.js CDN: Library loaded from jsdelivr.net CDN; requires internet connection on client device
  • Data Management: Arrays limited to 100 points to prevent memory overflow; older data automatically discarded
  • Update Rate: 300ms refresh rate balances responsiveness with server load; adjust based on network conditions
  • Chart Configuration: Y-axis ranges fixed (BPM: 40-160, SpO2: 70-100) for consistent scaling; modify in JavaScript if needed
  • Browser Compatibility: Requires modern browser with JavaScript enabled; tested on Chrome, Firefox, Safari
  • Performance: Chart updates are lightweight; multiple simultaneous clients may impact ESP32 performance
  • Offline Operation: Charts won't load if client device lacks internet (Chart.js CDN unavailable); consider local hosting for offline use
Download: pulse_gui_2.ino

Reflections & Learnings

Key insights and learnings from working with interface and application programming.

Contributions

Acknowledgements and team roles for interface and application programming work.

Ethical AI Use

Transparent documentation of AI assistance used in this week's interface and application programming work.

This section documents all AI assistance used during Week 12 interface and application programming work. ChatGPT was used for code development, troubleshooting, and technical guidance. All transcripts are linked below for transparency.

Menu System with Modes

AI assistance for developing the button-based menu system with mode navigation (Menu, Camera, Sensors) using press pattern detection. The conversation covered button debouncing, press pattern recognition, mode state management, and OLED menu display design.

Related to: Part (a): Simple Button User Interface on OLED

View ChatGPT Transcript: Menu System with Modes

I2C Device Not Found

Troubleshooting session for I2C device detection issues with MAX30102 pulse oximeter sensor. The conversation addressed power isolation problems, I2C wiring verification, sensor initialization order, and ground plane isolation requirements for accurate sensor operation.

Related to: Part (b): Real-Time Graphical User Interface through OLED and WiFi

View ChatGPT Transcript: I2C Device Not Found

Hello World Code

Development assistance for creating the initial OLED "Hello World" test program. The conversation covered I2C initialization, OLED display library setup, text rendering, and basic display configuration for XIAO ESP32-S3 development board.

Related to: Part (b): Real-Time Graphical User Interface through OLED and WiFi (initial OLED test)

View ChatGPT Transcript: Hello World Code

MAX30102 Initialization Fix

Technical guidance for fixing MAX30102 pulse oximeter sensor initialization issues. The conversation addressed sensor configuration parameters, LED brightness settings, sample rate optimization, initialization sequence requirements, and troubleshooting sensor communication problems.

Related to: Part (b): Real-Time Graphical User Interface through OLED and WiFi (pulse oximeter readings)

View ChatGPT Transcript: MAX30102 Initialization Fix

Grip Strength Monitor Code Design

Code-focused assistance for designing and refining the WiFi grip strength monitor firmware. The conversation covered HX711 bring-up, load cell pin mapping, Serial Plotter debugging sketches, the ESP32-S3 HTTP server, the Chart.js dashboard, and the age-estimation helpers used in loadcell_simple.ino, loadcell_plot.ino, and loadcell_gui.ino.

Related to: Part (c): Real-Time GUI through Mechanical Gripper and WiFi and Grip Strength Monitor design files

View ChatGPT Transcript: Grip Strength Monitor Code

Grip Strength Calibration & Scaling

Calibration-focused assistance for mapping HX711 counts to kilograms and validating the grip strength readings. The discussion walked through using the Serial Plotter, collecting reference weights, tuning the calibration factor, and sanity-checking the age-estimation model derived from normative grip strength data.

Related to: Part (c): Real-Time GUI through Mechanical Gripper and WiFi calibration workflow and the Grip Strength Monitor sketches.

View ChatGPT Transcript: Grip Strength Calibration

Grip Strength Monitor – Cursor Transcript

Full Cursor AI transcript focused on organizing the grip strength monitor section: structuring Part (c), integrating design files, embedding images and videos, and aligning captions, external references, and the Ethical AI Use documentation for the load cell project.

Related to: Part (c): Real-Time GUI through Mechanical Gripper and WiFi, Grip Strength Monitor design files, and this Ethical AI Use section.

View HTML Transcript Download Markdown Transcript

Week 12 Project Documentation

Complete Cursor AI transcript for Week 12 interface and application programming project documentation. This comprehensive conversation covers the creation and population of the Week 12 HTML page, including Individual Assignment sections (button UI and WiFi GUI), Group Assignment tool comparisons, Design Files documentation with pseudocode, and Ethical AI Use section organization. The transcript demonstrates the collaborative process of building professional documentation with structured content, embedded media, and comprehensive code documentation.

Related to: Complete Week 12 documentation including Individual Assignment, Group Assignment, Design Files, and overall page structure

View HTML Transcript Download Markdown Transcript

Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License

``` ```html Week 13 · Wildcard Week
← Back to Home
[Profile Image Placeholder]

Week 13

Wildcard Week

Week Highlights

Key captures from the group and individual assignments with links to their sections.

Button User Interface on OLED

OLED button user interface menu system

Hello World on OLED

Hello World display on OLED for Invisible String project

Pulse Oximeter Readings

Pulse oximeter readings showing IR, RED, and BPM values

Wi-Fi GUI Readings

Wi-Fi web interface displaying real-time pulse oximeter readings

Wi-Fi GUI Plots

Wi-Fi web interface with real-time plotting of pulse oximeter data

OLED Video Stream Demo

Grip Strength Gripper

CAD rendering of the full grip strength device with base, handle, and load cell Photo of the fully assembled grip strength device with electronics and handle

Load Cell Calibration Plot

Serial Plotter screenshot showing load cell readings rising with grip force

Grip Strength WiFi GUI

Table of Contents

Course Content

Training & Documentation

Assignments & Projects

Interface & Application Programming

This week focuses on creating user interfaces and applications that connect users with input and output devices. We'll explore interface design patterns, application programming techniques, and how to build interactive systems that provide meaningful user experiences.

Creating user interfaces for embedded devices
Building applications that interface with input and output devices
Comparing interface programming tools and frameworks

This Week's Goals

  • User Interface Design
    Learn to create intuitive interfaces for embedded devices and applications
  • Application Programming
    Build applications that interface users with input and/or output devices
  • Tool Comparison
    Compare interface programming tools and frameworks to select appropriate solutions

Assignments

  • Group Assignment
    Compare as many tool options as possible
  • Individual Assignment
    Write an application that interfaces a user with an input &/or output device that you made

Tools & Materials

  • ESP32-S3 Development Boards
  • OLED Displays (SSD1306)
  • MAX30102 Pulse Oximeter Sensor
  • Buttons & User Input Devices
  • Interface Programming Frameworks

Training Documentation

Training materials and documentation for interface and application programming.

No recitation this week.

Useful Documentation

Essential resources for interface and application programming.

Class Page

Interface and Application Programming - MIT Academy

Comprehensive resource covering interface design, application programming, GUI frameworks, embedded UI development, web interfaces for embedded systems, and user interaction patterns. Includes detailed tutorials, code examples, and implementation guides for various interface programming tools and frameworks.

Key Topics

  • Interface Design: User experience principles, interaction patterns, feedback mechanisms
  • Embedded UI: OLED displays, LCD interfaces, character displays
  • Web Interfaces: HTTP servers, REST APIs, WebSockets, real-time data visualization
  • Application Frameworks: GUI toolkits, web frameworks, mobile apps
  • User Input: Buttons, touch interfaces, gesture recognition, voice commands

Additional References

Individual Assignment: Interface & Application Programming

Write an application that interfaces a user with an input &/or output device that you made. This assignment demonstrates three interface applications: (a) a simple button user interface on OLED, (b) a real-time graphical user interface through OLED and Wi-Fi for pulse oximeter readings, and (c) a Wi-Fi grip strength monitor with a mechanical gripper and age-estimation web dashboard.

Part (a): Simple Button User Interface on OLED

A mode-based user interface system that interfaces users with multiple input and output devices through a simple button press interface. The system provides visual feedback on an OLED display and enables navigation between different modes (Menu, Camera, Sensors) using button press patterns. Users interact by pressing a button multiple times to select modes, with visual confirmation displayed on the OLED screen.

Interface Design

The interface uses a mode-based navigation system where button presses trigger mode changes. A single press enters Camera mode, two presses enter Sensors mode, three presses return to Menu, and holding the button activates a flashlight function. The OLED display shows the current menu state and provides clear visual feedback for each mode transition. See Ethical AI Use: Menu System with Modes for AI-assisted development details.

OLED button user interface menu system displaying mode selection options
OLED button user interface menuMenu screen showing available modes: Camera, Sensors, and Menu navigation options with button press instructions.
Button UI demonstrationVideo showing button press interactions navigating through different modes on the OLED display.
First video stream on OLEDInitial camera feed streaming to OLED display using dithering algorithm for monochrome conversion, demonstrating real-time video output interface.
Download Design Files
  • outputs.ino — Button user interface code with mode system
  • camera_pins.h — Camera pin definitions header file
  • outputs.zip — Complete project archive including all dependencies

Part (b): Real-Time Graphical User Interface through OLED and WiFi

A dual-interface health monitoring system that interfaces users with a MAX30102 pulse oximeter sensor through both an OLED display and a WiFi-enabled web interface. The system provides real-time visualization of heart rate (BPM), blood oxygen saturation (SpO2), and raw sensor data (IR and RED LED readings) through multiple output channels. Users can view data locally on the OLED display or remotely via a web browser accessing the ESP32-S3's built-in HTTP server. See Ethical AI Use: I2C Device Not Found for troubleshooting documentation.

Interface Design

The system provides dual-interface access: a local OLED display shows real-time sensor readings (IR, RED, BPM, SpO2) with visual heartbeat indicators, while a WiFi web interface provides comprehensive data visualization including numerical displays and real-time plotting charts. The web interface uses Chart.js for dynamic graph generation and automatically refreshes every 300ms to maintain real-time data updates. Both interfaces run simultaneously, enabling local monitoring and remote access.

Hello World on OLED

Initial OLED display test showing successful I2C communication and display initialization. See Ethical AI Use: Hello World Code for development details.

Hello World display on OLED for Invisible String project showing successful display initialization
Hello World on OLEDInitial OLED test confirming I2C communication and display functionality before implementing sensor interfaces.
Pulse Oximeter Readings on OLED

Real-time pulse oximeter data displayed on OLED showing IR and RED LED readings, heart rate (BPM), and blood oxygen saturation (SpO2) percentage. A heartbeat indicator flashes when a pulse is detected. See Ethical AI Use: MAX30102 Initialization Fix for sensor setup documentation.

Pulse oximeter readings on OLED displaying IR, RED, BPM, and SpO2 values
OLED sensor readings displayReal-time pulse oximeter data showing IR and RED LED values, heart rate (BPM), and blood oxygen saturation (SpO2) with heartbeat indicator.
BPM and SpO2 demonstrationVideo showing real-time heart rate and blood oxygen saturation measurements updating on OLED display with sensor interaction.
Pulse Oximeter Readings on WiFi GUI

WiFi web interface providing remote access to pulse oximeter data through a responsive HTML dashboard. The interface displays real-time numerical values for BPM, SpO2, IR, and RED readings with automatic data refresh. The web server runs on the ESP32-S3, allowing access from any device on the same WiFi network.

WiFi web interface displaying real-time pulse oximeter readings including BPM, SpO2, IR, and RED values
WiFi GUI readings dashboardRemote web interface showing real-time pulse oximeter data accessible from any device on the WiFi network, displaying BPM, SpO2, IR, and RED values with automatic updates.
Pulse Oximeter Plots on WiFi GUI

Enhanced WiFi web interface with real-time plotting capabilities using Chart.js library. The interface displays live line charts for BPM and SpO2 values, showing trends over time with automatic scrolling and data point management. This visualization enables users to observe patterns in heart rate and blood oxygen levels during monitoring sessions.

Serial monitor output showing sensor readings rising on touch interaction
Serial monitor sensor responseSerial output demonstrating sensor readings increase when finger is placed on MAX30102 sensor, showing IR and RED LED response to touch.
WiFi web interface with real-time plotting of BPM and SpO2 data using Chart.js
WiFi GUI with plotting chartsEnhanced web interface displaying real-time line charts for BPM and SpO2 values, showing trends over time with automatic data refresh and chart scrolling.

I2C Device Detection

Successful I2C device detection after fixing power isolation issues. The system now correctly identifies the OLED display at address 0x3C and the MAX30102 sensor at address 0x57. Initial troubleshooting required isolating the RD (red LED) and IRD (infrared LED) ground terminals from the general ground plane to prevent power issues and enable proper sensor operation. 

20:04:48.612 -> Scanning...
20:04:48.644 -> I2C device found at address 0x3C  !
20:04:48.644 -> I2C device found at address 0x57  !
20:04:48.644 -> done
Download Design Files

Part (c): Real-Time GUI through Mechanical Gripper and WiFi

A Wi-Fi-connected grip strength meter that interfaces a user with a mechanical hand gripper, an 80 kg load cell, and an HX711 amplifier. The ESP32-S3 continuously measures grip force, streams it to a web dashboard, and uses a published relationship between handgrip strength and age to display an estimated “physiological age” in real time. The design is inspired by the open-source grip strength meter from NeuroTech Hub at WashU and the associated PLOS ONE paper on grip strength and age trajectories (Syddall et al., 2014), adapted to my load cell and handle geometry.

Mechanically, a custom 3D-printed gripper clamps around a CZL601-type 80 kg bar load cell (sourced from Amazon 80 kg load cell). I imported a 100 kg load cell CAD from GrabCAD, checked the mounting dimensions against the CZL601AC datasheet (online, download), and confirmed that the hole spacing and footprint match the commercial part used here.

Mechanical Design and Fabrication

CAD model of the 3D-printed grip strength base and load cell mounting region
Grip strength base CADTop view of the grip strength base showing the bar load cell pocket, mounting bosses, and handle interface.
Side view CAD of the hand gripper and load cell assembly
Side view of gripper assemblySide profile showing how the fixed base, moving handle, and load cell align along the force axis of the bar sensor.
Full CAD view of the grip strength device with base and handle
Full grip strength assemblyComplete CAD of the base, handle, and load cell, sized for comfortable adult hand placement and full-finger contact.
Close-up of mounting holes and clearances around the load cell in CAD
Load cell mounting holesDetail of the M6 clearance and counterbore geometry used to capture the load cell without constraining bending.
Perspective CAD view of the gripper handle and base
Handle ergonomicsPerspective view of the curved handle designed to distribute pressure across the palm and fingers during maximal grip.
Photo of drilled clearance hole aligned to the printed pilot in the base
Clearance hole verificationPrinted pilot holes used as drill guides to match the metric mounting dimensions from the CZL601AC datasheet.
Photo of the fully printed grip strength device before drilling and assembly
Fresh off the printer3D-printed base and handle components in PLA prior to post-processing and hardware installation.
Printed part clamped for drilling load cell mounting holes
Workholding for accurate drillingThe printed base clamped to the drill press table so the pilot features guide the final clearance holes into the load cell.
Drilling practiceTraining cuts on scrap material to dial in drill press settings and avoid cracking the printed base during final holes.
Final load cell holesDrilling the final M6 clearance holes through the printed base, constrained by the pilot features to preserve alignment.

Electronics and Calibration

Electronics assembly with HX711 breakout, ESP32-S3, and load cell wiring
Electronics stack-upHX711 amplifier breakout from Amazon wired to the ESP32-S3 and 80 kg load cell with short, twisted signal pairs for noise reduction.
Fully assembled grip strength device with load cell, electronics, and handle
Assembled grip strength meterCompleted mechanical and electrical assembly ready for calibration and software bring-up.
Serial Plotter view of load cell readings increasing with grip force
Serial Plotter calibration tracesRaw HX711 output converted to kilograms and visualized in the Arduino Serial Plotter while applying known weights and grip forces.
Web GUI showing grip strength value, estimated age, and scrolling chart
Wi-Fi grip strength dashboardBrowser-based GUI with live grip strength (kg), estimated age, and a Chart.js time series plot of recent squeezes.

Model Used for Age Estimation

The age-estimation logic in the firmware is based on the non-linear, sex-specific grip-strength trajectories reported in Dodds et al., 2014 (PLOS ONE). As shown in Figure 1 of that paper, grip strength rises rapidly through adolescence, peaks around ages 30–40, and then declines non-linearly with age, with different magnitudes for males and females.

Reference grip strength trajectories over the life course from Dodds et al., PLOS ONE 2014
Reference trajectories (Figure 1)Age-dependent grip strength curves for males and females from Dodds et al., 2014, used as the qualitative target for the embedded model.
Simplified quadratic grip strength model fitted to reference data
Quadratic approximation (Table 2-inspired)Simplified male and female trajectories using peak strengths and curvatures chosen to approximate the summary values reported in Table 2 of Dodds et al., 2014.

To reproduce this shape efficiently on the ESP32, the firmware uses inverted quadratic approximations centered at age 35, consistent with the observed peak in the PLOS ONE data. In the forward direction, grip strength is approximated as:

Males: Grip(age) ≈ 52 − 0.0089·(age − 35)2
Females: Grip(age) ≈ 32 − 0.0059·(age − 35)2

On the device, this relationship is analytically inverted so that the measured grip strength can be mapped back to an estimated age:

age = 35 + √((a − Grip)/b), where a is the peak strength (52 kg for males, 32 kg for females) and b is the curvature (0.0089 for males, 0.0059 for females). The firmware clamps grip strength to physiologically meaningful ranges before applying this formula so the square root remains well-defined. 

float ageFromGripMale(float g) {
  float a = 52.0f, b = 0.0089f;
  if (g > a) g = a;
  if (g < 5) g = 5;
  return 35.0f + sqrtf((a - g) / b);
}

float ageFromGripFemale(float g) {
  float a = 32.0f, b = 0.0059f;
  if (g > a) g = a;
  if (g < 4) g = 4;
  return 35.0f + sqrtf((a - g) / b);
}

For full methodological details and original tables/figures, see the open-access paper: Dodds et al., 2014, PLOS ONE (download local PDF). The implementation here is an educational approximation and not intended for clinical or diagnostic use.

End-to-end live demoReal-time demonstration of squeezing the mechanical gripper and watching the Wi-Fi dashboard update grip strength and estimated age on a laptop.

Related Design, Code, and Calibration Resources

User Interface Comparison

Summary of how each interface application connects users with input and output devices.

Application How It Interfaces with the User Input Device(s) Output Device(s)
(a) Button User Interface Button press patterns (single, double, triple press, hold) provide mode selection input. OLED display shows current menu state and mode options. Users receive immediate visual feedback for each interaction. Button (GPIO pin 4) OLED Display (SSD1306, I²C 0x3C)
LED (GPIO pin 3, flashlight mode)
(b) Real-Time GUI (OLED & WiFi) Physical finger placement on MAX30102 sensor provides input. OLED displays real-time sensor data locally. WiFi web interface enables remote monitoring with numerical displays and live plotting charts accessible from any web browser. MAX30102 Pulse Oximeter Sensor (I²C 0x57) OLED Display (SSD1306, I²C 0x3C)
WiFi Web Interface (HTTP Server with Chart.js visualization)
(c) Grip Strength GUI (Load Cell & WiFi) Users squeeze a mechanical hand gripper that transfers force into an 80 kg bar load cell. The ESP32-S3 measures grip strength through the HX711 amplifier and streams results to a WiFi web dashboard that displays live grip force and an estimated physiological age in real time. Mechanical gripper linked to 80 kg load cell (CZL601-type)
HX711 load cell amplifier		 WiFi Web Interface (HTTP Server with Chart.js visualization)
Optional Serial Plotter (for calibration traces)

Group Assignment: Compare as Many Tool Options as Possible

Compare as many tool options as possible for interface and application programming.

General Comparison: Interface & Application Programming Tools

Comprehensive comparison of interface and application programming tools available for embedded systems and IoT development. This analysis covers tools from the MIT Academy Interface & Application Programming class page, evaluating their capabilities, use cases, and trade-offs for different application scenarios.

Embedded Display Interfaces

Tool/Framework Description Pros Cons Best For
OLED (SSD1306) Monochrome OLED displays via I²C Low power, high contrast, simple I²C interface, pixel-level control Limited resolution (128x64), monochrome only, small display size Status displays, sensor readouts, simple menus, embedded dashboards
LCD Character Displays Character-based LCD displays (16x2, 20x4) Simple API, readable in sunlight, low cost Limited to text/characters, no graphics, requires backlight power Text-only interfaces, status messages, debugging output
TFT Color Displays Full-color TFT LCD displays Color graphics, touch support, high resolution High power consumption, complex drivers, larger footprint Rich GUIs, image display, interactive touch interfaces

Web-Based Interfaces

Tool/Framework Description Pros Cons Best For
HTTP Server (ESP32) Built-in HTTP server on ESP32 for web interfaces Remote access, cross-platform (any browser), no app installation, real-time updates Requires WiFi, network dependency, limited to local network without port forwarding Remote monitoring, data visualization, control panels, sensor dashboards
WebSockets Real-time bidirectional communication Low latency, bidirectional, efficient for frequent updates More complex than HTTP, requires persistent connection Real-time streaming, interactive controls, live data feeds
Chart.js JavaScript charting library for web interfaces Beautiful charts, interactive, responsive, easy integration Requires JavaScript, CDN dependency or local hosting Data visualization, time series plots, sensor monitoring dashboards

Mobile & Native App Frameworks

Tool/Framework Description Pros Cons Best For
React Native Cross-platform mobile app framework Cross-platform (iOS/Android), native performance, large ecosystem Complex setup, requires mobile development knowledge Full-featured mobile apps, production deployments
Flutter Google's UI toolkit for cross-platform apps Single codebase, high performance, customizable UI Dart language, larger app size, learning curve Custom mobile interfaces, platform-specific designs
Progressive Web Apps (PWA) Web apps with native-like features No app store, cross-platform, offline capability Limited native API access, browser dependency Web-based mobile interfaces, simple deployment

Specific Comparison: Tools Used in Individual Assignment

Detailed comparison of the specific interface programming tools implemented in this week's individual assignment, evaluating their performance, ease of use, and suitability for embedded health monitoring applications.

OLED Display Interface (Adafruit SSD1306)

Aspect Evaluation
Ease of Implementation Simple I²C interface, well-documented Adafruit library, minimal wiring (SDA, SCL, power, ground)
Display Quality High contrast monochrome display, crisp text rendering, suitable for sensor data visualization
Power Consumption Very low power draw, ideal for battery-powered applications
Limitations 128x64 pixel resolution limits detail, monochrome only, small physical size (0.96" typical)
Best Use Cases Local sensor readouts, menu systems, status indicators, simple data displays

WiFi Web Interface (ESP32 HTTP Server + Chart.js)

Aspect Evaluation
Ease of Implementation ESP32 WebServer library provides straightforward HTTP server, Chart.js CDN integration requires minimal setup
Remote Access Accessible from any device on WiFi network (phone, tablet, computer), no app installation required
Visualization Capabilities Chart.js enables rich data visualization with real-time plotting, smooth animations, and interactive features
Real-Time Updates JSON API endpoint provides efficient data transfer, 300ms refresh rate maintains responsive feel
Limitations Requires WiFi network, limited to local network without additional configuration, power consumption higher than OLED alone
Best Use Cases Remote monitoring, data logging visualization, multi-user access, professional dashboards

Button Input Interface

Aspect Evaluation
Implementation Approach Digital GPIO reading with debouncing, press pattern detection (single/double/triple/hold) enables mode navigation
User Experience Intuitive press patterns, immediate visual feedback on OLED, no complex UI navigation required
Reliability Hardware debouncing with INPUT_PULLUP, timeout-based pattern recognition prevents accidental triggers
Limitations Limited to single button interaction, pattern learning required, less flexible than touchscreen interfaces
Best Use Cases Simple mode selection, menu navigation, embedded system controls, low-cost input solutions

Comparison Summary

The combination of OLED display and WiFi web interface provides complementary benefits: OLED offers immediate local feedback with minimal latency and power consumption, while the WiFi interface enables rich visualization and remote access. The button-based input provides an intuitive, low-cost navigation method suitable for embedded systems. Together, these tools create a robust interface system that supports both local and remote interaction with sensor data.

Design Files

Design files and code documentation for interface and application programming projects.

ESP32-S3 Development Board and Pinouts

Code files for ESP32-S3 development board interfaces including I2C scanning, OLED display control, and button-based user interface systems. See Week 4 documentation for board design and Week 8 documentation for pinout configurations.

I2C Scanner (i2cscan_generic.ino)

Utility code for scanning and detecting I2C devices on the bus, essential for troubleshooting connection issues.

How the Code Works (Pseudocode)
SETUP:
  Initialize I2C bus
  Initialize Serial communication
  Print "I2C Scanner" message

LOOP:
  Print "Scanning..." message
  Initialize device counter to 0
  
  FOR each address from 1 to 126:
    Begin I2C transmission to address
    Check transmission result
    
    IF transmission successful (error == 0):
      Print device found at address (hex format)
      Increment device counter
    ELSE IF unknown error (error == 4):
      Print unknown error at address
    
  IF no devices found:
    Print "No I2C devices found"
  ELSE:
    Print "done"
  
  Wait 5 seconds before next scan
Key Features
  • Scans all 127 possible I2C addresses (0x01-0x7E)
  • Detects and reports connected devices with hex address format
  • Handles multiple error conditions (device not found, unknown errors)
  • Continuous scanning mode with 5-second intervals
  • Compatible with any I2C bus configuration (Wire, Wire1, etc.)
What You Need to Know
  • I2C Address Range: Valid addresses are 0x08-0x77 (8-119 decimal); addresses 0x00-0x07 and 0x78-0x7F are reserved
  • Common Addresses: OLED displays typically use 0x3C or 0x3D; sensors vary (MAX30102 uses 0x57)
  • Troubleshooting: If no devices found, check wiring (SDA, SCL, power, ground), verify pull-up resistors, confirm device power
  • Usage: Run this before connecting other devices to verify I2C bus is working correctly
Download: i2cscan_generic.ino

Hello World OLED Display (hello_world.ino)

Basic OLED display test code that initializes the display and shows "Hello World" text, confirming I2C communication and display functionality.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial communication at 115200 baud
  Wait 500ms for Serial to stabilize
  
  Initialize I2C bus with SDA pin 5, SCL pin 6
  Print "Starting..." message
  
  Attempt to initialize OLED display:
    IF initialization fails:
      Print "OLED not found" error
      Enter infinite loop (halt)
  
  Clear display buffer
  Set text size to 2
  Set text color to white
  Set cursor position to (0, 20)
  Print "Hello" line
  Print "World!" line
  Update display (send buffer to hardware)

LOOP:
  Empty (runs once, then waits)
Key Features
  • Simple OLED initialization and text display
  • Custom I2C pin configuration for XIAO ESP32-S3 (SDA=5, SCL=6)
  • Error handling with infinite loop if display not found
  • Text size and cursor positioning for centered display
  • One-time display update (no loop refresh needed for static text)
What You Need to Know
  • I2C Pin Configuration: XIAO ESP32-S3 uses pins 5 (SDA) and 6 (SCL) by default; verify your board's pinout
  • Display Address: SSD1306 OLED typically uses address 0x3C; some variants use 0x3D
  • Display Update: Must call display.display() to send buffer to hardware; drawing functions only modify buffer
  • Testing: Use this as first test after connecting OLED to verify wiring and I2C communication before adding complex features
  • Libraries Required: Adafruit_GFX, Adafruit_SSD1306, Wire
Download: hello_world.ino

Button User Interface (outputs.ino)

Mode-based navigation system using button press patterns (single, double, triple, hold) to control multiple output devices including OLED display, camera, sensors, and LED flashlight.

How the Code Works (Pseudocode)
SETUP:
  Initialize OLED display
  Initialize camera module
  Initialize sensors (MPU6050, HX711)
  Initialize button pin (INPUT_PULLUP)
  Initialize LED pin (OUTPUT)
  Set current mode to MENU
  Display menu screen

LOOP:
  Read button state
  
  IF button pressed:
    Record press start time
    Start press detection timer
  
  IF button released:
    Calculate press duration
    IF duration > HOLD_THRESHOLD:
      Activate flashlight mode
    ELSE:
      Increment press count
      Reset press timeout timer
  
  IF press timeout exceeded:
    Process accumulated press count:
      IF press count == 1: Switch to CAMERA mode
      IF press count == 2: Switch to SENSORS mode
      IF press count == 3: Switch to MENU mode
    Reset press count
  
  IF current mode == MENU:
    Display menu screen (button instructions)
  
  IF current mode == CAMERA:
    Capture camera frame
    Process image with dithering algorithm
    Display on OLED
    Run Edge Impulse inference (optional)
    Overlay results on display
  
  IF current mode == SENSORS:
    Read accelerometer/gyroscope data
    Read load cell data
    Display sensor readings on OLED
  
  Update display
Key Features
  • Press pattern detection: single (1x), double (2x), triple (3x), and hold
  • Mode-based navigation system (Menu, Camera, Sensors)
  • Button debouncing with timeout-based pattern recognition
  • Floyd-Steinberg dithering for camera-to-OLED video display
  • Edge Impulse AI inference integration for face detection
  • Multi-sensor integration (MPU6050 accelerometer/gyro, HX711 load cell)
  • Flashlight mode activated by button hold
What You Need to Know
  • Button Wiring: Use INPUT_PULLUP mode (button connects pin to GND when pressed, internal pull-up to 3.3V)
  • Press Detection: Press count is accumulated until timeout (1 second); longer timeout allows slower multiple presses
  • Mode Switching: Each mode has distinct display update logic; ensure proper initialization in setup()
  • Camera Performance: Video streaming to OLED requires significant processing; frame rate depends on resolution and dithering complexity
  • Dependencies: Requires camera_pins.h header file with XIAO ESP32-S3 camera pin definitions; see Ethical AI Use for development details
  • Sensor Conflicts: Code uses preprocessor directives to resolve sensor_t type conflict between ESP32 camera and Adafruit MPU6050 libraries
Download: outputs.ino | camera_pins.h | outputs.zip (complete project)

Grip Strength Monitor (Load Cell + WiFi GUI)

Design files and firmware for a Wi-Fi-enabled grip strength meter built around an 80 kg bar load cell, HX711 amplifier, and ESP32-S3. The mechanical design was informed by the open-source grip strength meter from NeuroTech Hub and validated against the CZL601AC bar load cell datasheet (online, download).

Mechanical Design Files (3D-Printed Components)

  • Base.3mf — main chassis that captures the bar load cell and anchors the fixed side of the gripper.
  • Case.3mf — protective enclosure for the ESP32-S3 and HX711 amplifier with cable strain relief.
  • Handle.3mf — curved grip handle that transfers hand force into the free end of the load cell.
  • Calibration Print.3mf — small test piece used to verify hole diameters and load cell clearances before printing the full assembly.

All parts were printed in PLA with high infill in the load paths to minimize creep and flex during repeated maximal grip trials.

Basic HX711 Reader (loadcell_simple.ino)

Minimal firmware to bring up the HX711 amplifier and read calibrated weight values over Serial for debugging and calibration.

How the Code Works (Pseudocode)
SETUP:
  Configure HX711 data and clock pins (DT=A1, SCK=A0)
  Initialize Serial at 115200 baud
  Begin HX711 with DT/SCK pins
  Set calibration factor (grams per ADC unit)
  Tare the scale so current load is zero

LOOP (every 200 ms):
  If HX711 is ready:
    Read averaged weight using get_units(4)
    Print "weight:<value>" to Serial for Serial Plotter
  Else:
    Print "HX711 not ready" for troubleshooting
Key Features
  • Simple initialization of the HX711 on analog pins A0/A1.
  • Configurable calibration factor for mapping counts to grams or kilograms.
  • Timed reads (200 ms) to keep Serial output manageable and Plotter-friendly.
  • Graceful handling of HX711 not-ready states.
What You Need to Know
  • Use for initial bring-up: Run this first when wiring the HX711 and load cell to confirm clean, stable readings.
  • Calibration factor: Determined experimentally by hanging known weights and adjusting until readings match; see the calibration notes in Calibration Chat.
  • Serial Plotter: The weight:<value> format is convenient for quickly visualizing changes while squeezing the handle.
Download: loadcell_simple.ino

Serial Plotter-Friendly Reader (loadcell_plot.ino)

Refined HX711 reader tuned for the Arduino Serial Plotter: it outputs a single numeric value per line for clean plotting of grip strength over time.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial at 115200 baud
  Initialize HX711 on DT=A1, SCK=A0
  Set calibration factor
  Tare the scale
  Optionally print debug messages when DEBUG=1

LOOP (every 200 ms):
  If HX711 is ready:
    Read filtered weight with get_units(4)
    Optionally print labeled debug text
    Print only the numeric weight to Serial for the Plotter
  Else:
    Optionally print "not ready" debug text
    Print 0 so the plotted line continues gracefully
Key Features
  • DEBUG toggle: Compile-time switch to enable/disable human-readable logs without breaking the Serial Plotter format.
  • Clean “one number per line” output for multi-trial grip testing in the Serial Plotter.
  • Automatic zero output when the HX711 is not ready to keep the time axis continuous.
  • Shared pinout and calibration approach with loadcell_simple.ino for easy swapping.
What You Need to Know
  • Use this sketch to tune calibration and visualize grip curves without any GUI overhead.
  • When collecting data for analysis, keep DEBUG set to 0 so the output is a pure numeric stream.
  • The sample interval (200 ms) gives a smooth trace while keeping file sizes reasonable for multi-second squeezes.
Download: loadcell_plot.ino

WiFi Grip Strength GUI (loadcell_gui.ino)

Full application firmware that exposes grip strength and an estimated age over Wi-Fi using an HTTP server and a Chart.js web dashboard.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial
  Initialize HX711 (pins, calibration factor, tare)
  Connect ESP32-S3 to WiFi (MIT network in this build)
  Start WebServer on port 80
  Register handlers:
    "/"        → serve HTML+JS GUI page from PROGMEM
    "/metrics" → serve JSON with current grip and age

LOOP:
  Handle incoming HTTP clients
  Every 200 ms:
    If HX711 is ready:
      Read smoothed grip strength (kg) via get_units(3)
      Clamp negative values to zero
      Store in global gripStrength

AGE ESTIMATION HELPERS:
  ageFromGripMale(g):
    Clamp g to plausible range
    Compute age using inverted quadratic fit derived from normative data
  ageFromGripFemale(g):
    Same structure with female-specific parameters

HTTP /metrics ENDPOINT:
  Read "sex" query parameter (default "male")
  Compute ageEstimate = ageFromGripMale/ageFromGripFemale(gripStrength)
  Return JSON:
    {"grip": <kg>, "age": <years>}

CLIENT-SIDE GUI (HTML + JS):
  Render dark-themed dashboard with:
    - Sex toggle buttons (male/female)
    - Numeric grip strength (kg) and age
    - Scrolling Chart.js line plot of recent grip values
  Poll /metrics every 200 ms and update DOM + chart
Key Features
  • Embedded HTML/JS dashboard served directly from the ESP32-S3 using PROGMEM.
  • Real-time grip strength plot using Chart.js with ~120 recent samples.
  • Simple sex toggle that switches between male and female age-estimation curves.
  • JSON API at /metrics for future extensions (e.g., logging clients).
What You Need to Know
  • WiFi credentials: Update the ssid and password constants to match your network.
  • Normative model: The age equations are simplified fits inspired by the grip-strength trajectories reported in Syddall et al., PLOS ONE 2014 and are for educational visualization only, not clinical use.
  • Browser requirements: Any modern browser with JavaScript and network access can connect to the ESP32-S3’s IP address to view the dashboard.
  • Development log: The full iterative design of this sketch is captured in the ChatGPT transcript: Grip Strength Monitor Code Chat.
Download: loadcell_gui.ino

Invisible String Chain of Hearts

Code files for the Invisible String pulse oximeter interface system, providing real-time health monitoring through OLED display and WiFi web interface. See Week 11 PCB design documentation for hardware details.

OLED GUI for Pulse Oximeter (pulse_vo2_reads_fixing.ino)

Local OLED display interface showing real-time pulse oximeter readings including heart rate (BPM), blood oxygen saturation (SpO2), and raw IR/RED LED sensor values.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial communication
  Initialize I2C bus (SDA=5, SCL=6) at 400kHz
  Initialize MAX30102 sensor
  Configure sensor:
    Set LED mode to RED + IR
    Set ADC range to 16384
    Set sample rate to 100 Hz
    Set pulse width to 411 μs
    Set LED brightness to medium (0x3F)
  Initialize OLED display
  Clear and prepare display

LOOP:
  Read IR and RED LED values from sensor
  
  Heart Rate Detection:
    Check for heartbeat in IR signal using peak detection
    IF heartbeat detected:
      Calculate time since last beat
      Calculate BPM = 60 / (time_delta / 1000)
      Set beat flag for visual indicator
      Update last beat timestamp
  
  SpO2 Calculation (every 300ms):
    Add IR and RED values to circular buffer
    IF buffer has 50 samples:
      Calculate DC components (average)
      Calculate AC components (RMS)
      Calculate R ratio = (AC_RED/DC_RED) / (AC_IR/DC_IR)
      Estimate SpO2 = 110 - 25 * R
      Clamp SpO2 to 70-100% range
  
  Serial Output:
    Print IR, RED, BPM for Serial Plotter visualization
  
  OLED Display Update:
    Clear display buffer
    Display IR value (small text)
    Display RED value (small text)
    Display BPM value (large text, size 2)
    Display SpO2 percentage (small text)
    IF beat detected: Draw heartbeat indicator dot
    Update display hardware
  
  Delay 20ms (50 Hz update rate)
Key Features
  • Real-time heart rate detection using peak detection algorithm on IR signal
  • SpO2 calculation using ratio-of-ratios method with DC/AC component analysis
  • Circular buffer system for storing 50 samples of IR/RED data
  • Visual heartbeat indicator (flashing dot) when pulse detected
  • Dual output: OLED display and Serial Plotter for real-time waveform visualization
  • Optimized sensor configuration for reliable readings (100 Hz sample rate, medium brightness)
What You Need to Know
  • Sensor Placement: Finger must cover sensor completely; proper contact ensures accurate readings
  • I2C Address: MAX30102 uses address 0x57; verify with I2C scanner if sensor not detected
  • Ground Isolation: RD and IRD pins must be isolated from main ground plane to prevent power issues (see Week 11 PCB design)
  • SpO2 Accuracy: Calculation provides estimation; medical-grade accuracy requires calibration and FDA-approved algorithms
  • Buffer Size: 50-sample buffer provides balance between calculation accuracy and response time
  • Libraries Required: MAX30105 (SparkFun library), Adafruit_GFX, Adafruit_SSD1306, heartRate.h (beat detection)
  • Troubleshooting: If sensor not detected, check power isolation, I2C wiring, and sensor initialization order
Download: pulse_vo2_reads_fixing.ino

WiFi Readings GUI (pulse_gui.ino)

WiFi-enabled web interface providing remote access to pulse oximeter data through HTTP server with JSON API endpoint for real-time data updates.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial communication
  Initialize I2C bus
  Initialize MAX30102 sensor
  Configure sensor (LED mode, sample rate, pulse width)
  Initialize OLED display
  Initialize WiFi:
    Connect to network (SSID, password)
    Wait for connection
    Print IP address
  Initialize HTTP server:
    Route "/" → serve GUI HTML page
    Route "/gui" → serve GUI HTML page
    Route "/metrics" → serve JSON data
  Start web server

LOOP:
  Handle incoming HTTP client requests
  
  Read IR and RED values from sensor
  
  Heart Rate Calculation:
    Check for heartbeat in IR signal
    IF heartbeat detected:
      Calculate BPM from time delta
      Update global BPM variable
  
  SpO2 Calculation:
    Add IR/RED to circular buffer
    IF buffer full (50 samples):
      Calculate SpO2 using ratio-of-ratios
      Update global SpO2 variable
  
  Update global variables (g_ir, g_red, g_bpm, g_spo2)
  
  OLED Display Update:
    Display IR, RED, BPM, SpO2 values
    Update display hardware
Key Features
  • Dual interface: OLED display (local) and WiFi web interface (remote)
  • HTTP server with embedded HTML page stored in PROGMEM
  • JSON API endpoint (/metrics) for real-time data retrieval
  • Automatic WiFi connection with connection status feedback
  • IP address display for easy access
  • Simultaneous sensor reading and web server operation
  • Global variable system for data sharing between sensor reading and HTTP handlers
What You Need to Know
  • WiFi Configuration: Update SSID and password in code; for MIT network, use generated device password from wifi.mit.edu
  • Network Access: Web interface accessible only from devices on same WiFi network; IP address printed to Serial Monitor
  • HTML Storage: GUI HTML page stored in PROGMEM (program memory) to conserve RAM; use PROGMEM for large strings
  • Server Handling: Must call server.handleClient() frequently in loop() for responsive web interface
  • Data Refresh: Client-side JavaScript polls /metrics endpoint every 300ms for real-time updates
  • Power Consumption: WiFi significantly increases power draw compared to OLED-only mode; consider power management for battery operation
  • Libraries Required: WiFi, WebServer, MAX30105, Adafruit_SSD1306
Download: pulse_gui.ino

WiFi Plot GUI (pulse_gui_2.ino)

Enhanced WiFi web interface with real-time plotting capabilities using Chart.js library, displaying live line charts for BPM and SpO2 values with automatic scrolling and data management.

How the Code Works (Pseudocode)
SETUP:
  (Same as pulse_gui.ino)
  Initialize WiFi, sensor, OLED, HTTP server

LOOP:
  (Same as pulse_gui.ino)
  Handle HTTP requests, read sensor, calculate BPM/SpO2

GUI HTML PAGE (embedded in PROGMEM):
  Load Chart.js library from CDN
  Create two Chart.js line chart instances:
    - BPM chart (y-axis: 40-160 BPM)
    - SpO2 chart (y-axis: 70-100%)
  Initialize data arrays for each chart
  
  JavaScript Update Function (runs every 300ms):
    Fetch JSON data from /metrics endpoint
    Update numerical displays (BPM, SpO2, IR, RED)
    Add new BPM value to BPM data array
    Add new SpO2 value to SpO2 data array
    IF array length > maxPoints (100):
      Remove oldest value (shift)
    Update chart labels (array indices)
    Update chart datasets with new data
    Call chart.update() to refresh display
  
  Set interval to call update function every 300ms
Key Features
  • Real-time line chart visualization using Chart.js library
  • Dual chart display: BPM and SpO2 trends over time
  • Automatic data scrolling: maintains 100 most recent data points
  • Numerical displays alongside charts for precise values
  • Responsive design with dark theme for OLED-style aesthetic
  • Automatic chart scaling with fixed y-axis ranges for consistent visualization
  • CDN-based Chart.js loading for minimal memory footprint
What You Need to Know
  • Chart.js CDN: Library loaded from jsdelivr.net CDN; requires internet connection on client device
  • Data Management: Arrays limited to 100 points to prevent memory overflow; older data automatically discarded
  • Update Rate: 300ms refresh rate balances responsiveness with server load; adjust based on network conditions
  • Chart Configuration: Y-axis ranges fixed (BPM: 40-160, SpO2: 70-100) for consistent scaling; modify in JavaScript if needed
  • Browser Compatibility: Requires modern browser with JavaScript enabled; tested on Chrome, Firefox, Safari
  • Performance: Chart updates are lightweight; multiple simultaneous clients may impact ESP32 performance
  • Offline Operation: Charts won't load if client device lacks internet (Chart.js CDN unavailable); consider local hosting for offline use
Download: pulse_gui_2.ino

Reflections & Learnings

Key insights and learnings from working with interface and application programming.

Contributions

Acknowledgements and team roles for interface and application programming work.

Ethical AI Use

Transparent documentation of AI assistance used in this week's interface and application programming work.

This section documents all AI assistance used during Week 12 interface and application programming work. ChatGPT was used for code development, troubleshooting, and technical guidance. All transcripts are linked below for transparency.

Menu System with Modes

AI assistance for developing the button-based menu system with mode navigation (Menu, Camera, Sensors) using press pattern detection. The conversation covered button debouncing, press pattern recognition, mode state management, and OLED menu display design.

Related to: Part (a): Simple Button User Interface on OLED

View ChatGPT Transcript: Menu System with Modes

I2C Device Not Found

Troubleshooting session for I2C device detection issues with MAX30102 pulse oximeter sensor. The conversation addressed power isolation problems, I2C wiring verification, sensor initialization order, and ground plane isolation requirements for accurate sensor operation.

Related to: Part (b): Real-Time Graphical User Interface through OLED and WiFi

View ChatGPT Transcript: I2C Device Not Found

Hello World Code

Development assistance for creating the initial OLED "Hello World" test program. The conversation covered I2C initialization, OLED display library setup, text rendering, and basic display configuration for XIAO ESP32-S3 development board.

Related to: Part (b): Real-Time Graphical User Interface through OLED and WiFi (initial OLED test)

View ChatGPT Transcript: Hello World Code

MAX30102 Initialization Fix

Technical guidance for fixing MAX30102 pulse oximeter sensor initialization issues. The conversation addressed sensor configuration parameters, LED brightness settings, sample rate optimization, initialization sequence requirements, and troubleshooting sensor communication problems.

Related to: Part (b): Real-Time Graphical User Interface through OLED and WiFi (pulse oximeter readings)

View ChatGPT Transcript: MAX30102 Initialization Fix

Grip Strength Monitor Code Design

Code-focused assistance for designing and refining the WiFi grip strength monitor firmware. The conversation covered HX711 bring-up, load cell pin mapping, Serial Plotter debugging sketches, the ESP32-S3 HTTP server, the Chart.js dashboard, and the age-estimation helpers used in loadcell_simple.ino, loadcell_plot.ino, and loadcell_gui.ino.

Related to: Part (c): Real-Time GUI through Mechanical Gripper and WiFi and Grip Strength Monitor design files

View ChatGPT Transcript: Grip Strength Monitor Code

Grip Strength Calibration & Scaling

Calibration-focused assistance for mapping HX711 counts to kilograms and validating the grip strength readings. The discussion walked through using the Serial Plotter, collecting reference weights, tuning the calibration factor, and sanity-checking the age-estimation model derived from normative grip strength data.

Related to: Part (c): Real-Time GUI through Mechanical Gripper and WiFi calibration workflow and the Grip Strength Monitor sketches.

View ChatGPT Transcript: Grip Strength Calibration

Grip Strength Monitor – Cursor Transcript

Full Cursor AI transcript focused on organizing the grip strength monitor section: structuring Part (c), integrating design files, embedding images and videos, and aligning captions, external references, and the Ethical AI Use documentation for the load cell project.

Related to: Part (c): Real-Time GUI through Mechanical Gripper and WiFi, Grip Strength Monitor design files, and this Ethical AI Use section.

View HTML Transcript Download Markdown Transcript

Week 12 Project Documentation

Complete Cursor AI transcript for Week 12 interface and application programming project documentation. This comprehensive conversation covers the creation and population of the Week 12 HTML page, including Individual Assignment sections (button UI and WiFi GUI), Group Assignment tool comparisons, Design Files documentation with pseudocode, and Ethical AI Use section organization. The transcript demonstrates the collaborative process of building professional documentation with structured content, embedded media, and comprehensive code documentation.

Related to: Complete Week 12 documentation including Individual Assignment, Group Assignment, Design Files, and overall page structure

View HTML Transcript Download Markdown Transcript

Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License

``` Updating the intro and goals sections: Updating the intro, goals, assignments, and tools sections: ```html Week 13 · Wildcard Week
← Back to Home
[Profile Image Placeholder]

Week 13

Wildcard Week

Week Highlights

Key captures from the group and individual assignments with links to their sections.

Button User Interface on OLED

OLED button user interface menu system

Hello World on OLED

Hello World display on OLED for Invisible String project

Pulse Oximeter Readings

Pulse oximeter readings showing IR, RED, and BPM values

Wi-Fi GUI Readings

Wi-Fi web interface displaying real-time pulse oximeter readings

Wi-Fi GUI Plots

Wi-Fi web interface with real-time plotting of pulse oximeter data

OLED Video Stream Demo

Grip Strength Gripper

CAD rendering of the full grip strength device with base, handle, and load cell Photo of the fully assembled grip strength device with electronics and handle

Load Cell Calibration Plot

Serial Plotter screenshot showing load cell readings rising with grip force

Grip Strength WiFi GUI

Table of Contents

Course Content

Training & Documentation

Assignments & Projects

Wildcard Week

This week focuses on exploring digital fabrication processes not covered in previous assignments. We'll design and produce something using computer-aided design and manufacturing, documenting requirements and including everything necessary for reproduction. This week also includes reflection on the impact and purpose of making (almost) anything.

Exploring new digital fabrication processes
Designing and producing with CAD/CAM
Understanding the impact and purpose of fabrication labs

This Week's Goals

  • User Interface Design
    Learn to create intuitive interfaces for embedded devices and applications
  • Application Programming
    Build applications that interface users with input and/or output devices
  • Tool Comparison
    Compare interface programming tools and frameworks to select appropriate solutions

Assignments

  • Group Assignment
    Compare as many tool options as possible
  • Individual Assignment
    Write an application that interfaces a user with an input &/or output device that you made

Tools & Materials

  • ESP32-S3 Development Boards
  • OLED Displays (SSD1306)
  • MAX30102 Pulse Oximeter Sensor
  • Buttons & User Input Devices
  • Interface Programming Frameworks

Training Documentation

Training materials and documentation for interface and application programming.

No recitation this week.

Useful Documentation

Essential resources for interface and application programming.

Class Page

Interface and Application Programming - MIT Academy

Comprehensive resource covering interface design, application programming, GUI frameworks, embedded UI development, web interfaces for embedded systems, and user interaction patterns. Includes detailed tutorials, code examples, and implementation guides for various interface programming tools and frameworks.

Key Topics

  • Interface Design: User experience principles, interaction patterns, feedback mechanisms
  • Embedded UI: OLED displays, LCD interfaces, character displays
  • Web Interfaces: HTTP servers, REST APIs, WebSockets, real-time data visualization
  • Application Frameworks: GUI toolkits, web frameworks, mobile apps
  • User Input: Buttons, touch interfaces, gesture recognition, voice commands

Additional References

Individual Assignment: Interface & Application Programming

Write an application that interfaces a user with an input &/or output device that you made. This assignment demonstrates three interface applications: (a) a simple button user interface on OLED, (b) a real-time graphical user interface through OLED and Wi-Fi for pulse oximeter readings, and (c) a Wi-Fi grip strength monitor with a mechanical gripper and age-estimation web dashboard.

Part (a): Simple Button User Interface on OLED

A mode-based user interface system that interfaces users with multiple input and output devices through a simple button press interface. The system provides visual feedback on an OLED display and enables navigation between different modes (Menu, Camera, Sensors) using button press patterns. Users interact by pressing a button multiple times to select modes, with visual confirmation displayed on the OLED screen.

Interface Design

The interface uses a mode-based navigation system where button presses trigger mode changes. A single press enters Camera mode, two presses enter Sensors mode, three presses return to Menu, and holding the button activates a flashlight function. The OLED display shows the current menu state and provides clear visual feedback for each mode transition. See Ethical AI Use: Menu System with Modes for AI-assisted development details.

OLED button user interface menu system displaying mode selection options
OLED button user interface menuMenu screen showing available modes: Camera, Sensors, and Menu navigation options with button press instructions.
Button UI demonstrationVideo showing button press interactions navigating through different modes on the OLED display.
First video stream on OLEDInitial camera feed streaming to OLED display using dithering algorithm for monochrome conversion, demonstrating real-time video output interface.
Download Design Files
  • outputs.ino — Button user interface code with mode system
  • camera_pins.h — Camera pin definitions header file
  • outputs.zip — Complete project archive including all dependencies

Part (b): Real-Time Graphical User Interface through OLED and WiFi

A dual-interface health monitoring system that interfaces users with a MAX30102 pulse oximeter sensor through both an OLED display and a WiFi-enabled web interface. The system provides real-time visualization of heart rate (BPM), blood oxygen saturation (SpO2), and raw sensor data (IR and RED LED readings) through multiple output channels. Users can view data locally on the OLED display or remotely via a web browser accessing the ESP32-S3's built-in HTTP server. See Ethical AI Use: I2C Device Not Found for troubleshooting documentation.

Interface Design

The system provides dual-interface access: a local OLED display shows real-time sensor readings (IR, RED, BPM, SpO2) with visual heartbeat indicators, while a WiFi web interface provides comprehensive data visualization including numerical displays and real-time plotting charts. The web interface uses Chart.js for dynamic graph generation and automatically refreshes every 300ms to maintain real-time data updates. Both interfaces run simultaneously, enabling local monitoring and remote access.

Hello World on OLED

Initial OLED display test showing successful I2C communication and display initialization. See Ethical AI Use: Hello World Code for development details.

Hello World display on OLED for Invisible String project showing successful display initialization
Hello World on OLEDInitial OLED test confirming I2C communication and display functionality before implementing sensor interfaces.
Pulse Oximeter Readings on OLED

Real-time pulse oximeter data displayed on OLED showing IR and RED LED readings, heart rate (BPM), and blood oxygen saturation (SpO2) percentage. A heartbeat indicator flashes when a pulse is detected. See Ethical AI Use: MAX30102 Initialization Fix for sensor setup documentation.

Pulse oximeter readings on OLED displaying IR, RED, BPM, and SpO2 values
OLED sensor readings displayReal-time pulse oximeter data showing IR and RED LED values, heart rate (BPM), and blood oxygen saturation (SpO2) with heartbeat indicator.
BPM and SpO2 demonstrationVideo showing real-time heart rate and blood oxygen saturation measurements updating on OLED display with sensor interaction.
Pulse Oximeter Readings on WiFi GUI

WiFi web interface providing remote access to pulse oximeter data through a responsive HTML dashboard. The interface displays real-time numerical values for BPM, SpO2, IR, and RED readings with automatic data refresh. The web server runs on the ESP32-S3, allowing access from any device on the same WiFi network.

WiFi web interface displaying real-time pulse oximeter readings including BPM, SpO2, IR, and RED values
WiFi GUI readings dashboardRemote web interface showing real-time pulse oximeter data accessible from any device on the WiFi network, displaying BPM, SpO2, IR, and RED values with automatic updates.
Pulse Oximeter Plots on WiFi GUI

Enhanced WiFi web interface with real-time plotting capabilities using Chart.js library. The interface displays live line charts for BPM and SpO2 values, showing trends over time with automatic scrolling and data point management. This visualization enables users to observe patterns in heart rate and blood oxygen levels during monitoring sessions.

Serial monitor output showing sensor readings rising on touch interaction
Serial monitor sensor responseSerial output demonstrating sensor readings increase when finger is placed on MAX30102 sensor, showing IR and RED LED response to touch.
WiFi web interface with real-time plotting of BPM and SpO2 data using Chart.js
WiFi GUI with plotting chartsEnhanced web interface displaying real-time line charts for BPM and SpO2 values, showing trends over time with automatic data refresh and chart scrolling.

I2C Device Detection

Successful I2C device detection after fixing power isolation issues. The system now correctly identifies the OLED display at address 0x3C and the MAX30102 sensor at address 0x57. Initial troubleshooting required isolating the RD (red LED) and IRD (infrared LED) ground terminals from the general ground plane to prevent power issues and enable proper sensor operation. 

20:04:48.612 -> Scanning...
20:04:48.644 -> I2C device found at address 0x3C  !
20:04:48.644 -> I2C device found at address 0x57  !
20:04:48.644 -> done
Download Design Files

Part (c): Real-Time GUI through Mechanical Gripper and WiFi

A Wi-Fi-connected grip strength meter that interfaces a user with a mechanical hand gripper, an 80 kg load cell, and an HX711 amplifier. The ESP32-S3 continuously measures grip force, streams it to a web dashboard, and uses a published relationship between handgrip strength and age to display an estimated “physiological age” in real time. The design is inspired by the open-source grip strength meter from NeuroTech Hub at WashU and the associated PLOS ONE paper on grip strength and age trajectories (Syddall et al., 2014), adapted to my load cell and handle geometry.

Mechanically, a custom 3D-printed gripper clamps around a CZL601-type 80 kg bar load cell (sourced from Amazon 80 kg load cell). I imported a 100 kg load cell CAD from GrabCAD, checked the mounting dimensions against the CZL601AC datasheet (online, download), and confirmed that the hole spacing and footprint match the commercial part used here.

Mechanical Design and Fabrication

CAD model of the 3D-printed grip strength base and load cell mounting region
Grip strength base CADTop view of the grip strength base showing the bar load cell pocket, mounting bosses, and handle interface.
Side view CAD of the hand gripper and load cell assembly
Side view of gripper assemblySide profile showing how the fixed base, moving handle, and load cell align along the force axis of the bar sensor.
Full CAD view of the grip strength device with base and handle
Full grip strength assemblyComplete CAD of the base, handle, and load cell, sized for comfortable adult hand placement and full-finger contact.
Close-up of mounting holes and clearances around the load cell in CAD
Load cell mounting holesDetail of the M6 clearance and counterbore geometry used to capture the load cell without constraining bending.
Perspective CAD view of the gripper handle and base
Handle ergonomicsPerspective view of the curved handle designed to distribute pressure across the palm and fingers during maximal grip.
Photo of drilled clearance hole aligned to the printed pilot in the base
Clearance hole verificationPrinted pilot holes used as drill guides to match the metric mounting dimensions from the CZL601AC datasheet.
Photo of the fully printed grip strength device before drilling and assembly
Fresh off the printer3D-printed base and handle components in PLA prior to post-processing and hardware installation.
Printed part clamped for drilling load cell mounting holes
Workholding for accurate drillingThe printed base clamped to the drill press table so the pilot features guide the final clearance holes into the load cell.
Drilling practiceTraining cuts on scrap material to dial in drill press settings and avoid cracking the printed base during final holes.
Final load cell holesDrilling the final M6 clearance holes through the printed base, constrained by the pilot features to preserve alignment.

Electronics and Calibration

Electronics assembly with HX711 breakout, ESP32-S3, and load cell wiring
Electronics stack-upHX711 amplifier breakout from Amazon wired to the ESP32-S3 and 80 kg load cell with short, twisted signal pairs for noise reduction.
Fully assembled grip strength device with load cell, electronics, and handle
Assembled grip strength meterCompleted mechanical and electrical assembly ready for calibration and software bring-up.
Serial Plotter view of load cell readings increasing with grip force
Serial Plotter calibration tracesRaw HX711 output converted to kilograms and visualized in the Arduino Serial Plotter while applying known weights and grip forces.
Web GUI showing grip strength value, estimated age, and scrolling chart
Wi-Fi grip strength dashboardBrowser-based GUI with live grip strength (kg), estimated age, and a Chart.js time series plot of recent squeezes.

Model Used for Age Estimation

The age-estimation logic in the firmware is based on the non-linear, sex-specific grip-strength trajectories reported in Dodds et al., 2014 (PLOS ONE). As shown in Figure 1 of that paper, grip strength rises rapidly through adolescence, peaks around ages 30–40, and then declines non-linearly with age, with different magnitudes for males and females.

Reference grip strength trajectories over the life course from Dodds et al., PLOS ONE 2014
Reference trajectories (Figure 1)Age-dependent grip strength curves for males and females from Dodds et al., 2014, used as the qualitative target for the embedded model.
Simplified quadratic grip strength model fitted to reference data
Quadratic approximation (Table 2-inspired)Simplified male and female trajectories using peak strengths and curvatures chosen to approximate the summary values reported in Table 2 of Dodds et al., 2014.

To reproduce this shape efficiently on the ESP32, the firmware uses inverted quadratic approximations centered at age 35, consistent with the observed peak in the PLOS ONE data. In the forward direction, grip strength is approximated as:

Males: Grip(age) ≈ 52 − 0.0089·(age − 35)2
Females: Grip(age) ≈ 32 − 0.0059·(age − 35)2

On the device, this relationship is analytically inverted so that the measured grip strength can be mapped back to an estimated age:

age = 35 + √((a − Grip)/b), where a is the peak strength (52 kg for males, 32 kg for females) and b is the curvature (0.0089 for males, 0.0059 for females). The firmware clamps grip strength to physiologically meaningful ranges before applying this formula so the square root remains well-defined. 

float ageFromGripMale(float g) {
  float a = 52.0f, b = 0.0089f;
  if (g > a) g = a;
  if (g < 5) g = 5;
  return 35.0f + sqrtf((a - g) / b);
}

float ageFromGripFemale(float g) {
  float a = 32.0f, b = 0.0059f;
  if (g > a) g = a;
  if (g < 4) g = 4;
  return 35.0f + sqrtf((a - g) / b);
}

For full methodological details and original tables/figures, see the open-access paper: Dodds et al., 2014, PLOS ONE (download local PDF). The implementation here is an educational approximation and not intended for clinical or diagnostic use.

End-to-end live demoReal-time demonstration of squeezing the mechanical gripper and watching the Wi-Fi dashboard update grip strength and estimated age on a laptop.

Related Design, Code, and Calibration Resources

User Interface Comparison

Summary of how each interface application connects users with input and output devices.

Application How It Interfaces with the User Input Device(s) Output Device(s)
(a) Button User Interface Button press patterns (single, double, triple press, hold) provide mode selection input. OLED display shows current menu state and mode options. Users receive immediate visual feedback for each interaction. Button (GPIO pin 4) OLED Display (SSD1306, I²C 0x3C)
LED (GPIO pin 3, flashlight mode)
(b) Real-Time GUI (OLED & WiFi) Physical finger placement on MAX30102 sensor provides input. OLED displays real-time sensor data locally. WiFi web interface enables remote monitoring with numerical displays and live plotting charts accessible from any web browser. MAX30102 Pulse Oximeter Sensor (I²C 0x57) OLED Display (SSD1306, I²C 0x3C)
WiFi Web Interface (HTTP Server with Chart.js visualization)
(c) Grip Strength GUI (Load Cell & WiFi) Users squeeze a mechanical hand gripper that transfers force into an 80 kg bar load cell. The ESP32-S3 measures grip strength through the HX711 amplifier and streams results to a WiFi web dashboard that displays live grip force and an estimated physiological age in real time. Mechanical gripper linked to 80 kg load cell (CZL601-type)
HX711 load cell amplifier		 WiFi Web Interface (HTTP Server with Chart.js visualization)
Optional Serial Plotter (for calibration traces)

Group Assignment: Compare as Many Tool Options as Possible

Compare as many tool options as possible for interface and application programming.

General Comparison: Interface & Application Programming Tools

Comprehensive comparison of interface and application programming tools available for embedded systems and IoT development. This analysis covers tools from the MIT Academy Interface & Application Programming class page, evaluating their capabilities, use cases, and trade-offs for different application scenarios.

Embedded Display Interfaces

Tool/Framework Description Pros Cons Best For
OLED (SSD1306) Monochrome OLED displays via I²C Low power, high contrast, simple I²C interface, pixel-level control Limited resolution (128x64), monochrome only, small display size Status displays, sensor readouts, simple menus, embedded dashboards
LCD Character Displays Character-based LCD displays (16x2, 20x4) Simple API, readable in sunlight, low cost Limited to text/characters, no graphics, requires backlight power Text-only interfaces, status messages, debugging output
TFT Color Displays Full-color TFT LCD displays Color graphics, touch support, high resolution High power consumption, complex drivers, larger footprint Rich GUIs, image display, interactive touch interfaces

Web-Based Interfaces

Tool/Framework Description Pros Cons Best For
HTTP Server (ESP32) Built-in HTTP server on ESP32 for web interfaces Remote access, cross-platform (any browser), no app installation, real-time updates Requires WiFi, network dependency, limited to local network without port forwarding Remote monitoring, data visualization, control panels, sensor dashboards
WebSockets Real-time bidirectional communication Low latency, bidirectional, efficient for frequent updates More complex than HTTP, requires persistent connection Real-time streaming, interactive controls, live data feeds
Chart.js JavaScript charting library for web interfaces Beautiful charts, interactive, responsive, easy integration Requires JavaScript, CDN dependency or local hosting Data visualization, time series plots, sensor monitoring dashboards

Mobile & Native App Frameworks

Tool/Framework Description Pros Cons Best For
React Native Cross-platform mobile app framework Cross-platform (iOS/Android), native performance, large ecosystem Complex setup, requires mobile development knowledge Full-featured mobile apps, production deployments
Flutter Google's UI toolkit for cross-platform apps Single codebase, high performance, customizable UI Dart language, larger app size, learning curve Custom mobile interfaces, platform-specific designs
Progressive Web Apps (PWA) Web apps with native-like features No app store, cross-platform, offline capability Limited native API access, browser dependency Web-based mobile interfaces, simple deployment

Specific Comparison: Tools Used in Individual Assignment

Detailed comparison of the specific interface programming tools implemented in this week's individual assignment, evaluating their performance, ease of use, and suitability for embedded health monitoring applications.

OLED Display Interface (Adafruit SSD1306)

Aspect Evaluation
Ease of Implementation Simple I²C interface, well-documented Adafruit library, minimal wiring (SDA, SCL, power, ground)
Display Quality High contrast monochrome display, crisp text rendering, suitable for sensor data visualization
Power Consumption Very low power draw, ideal for battery-powered applications
Limitations 128x64 pixel resolution limits detail, monochrome only, small physical size (0.96" typical)
Best Use Cases Local sensor readouts, menu systems, status indicators, simple data displays

WiFi Web Interface (ESP32 HTTP Server + Chart.js)

Aspect Evaluation
Ease of Implementation ESP32 WebServer library provides straightforward HTTP server, Chart.js CDN integration requires minimal setup
Remote Access Accessible from any device on WiFi network (phone, tablet, computer), no app installation required
Visualization Capabilities Chart.js enables rich data visualization with real-time plotting, smooth animations, and interactive features
Real-Time Updates JSON API endpoint provides efficient data transfer, 300ms refresh rate maintains responsive feel
Limitations Requires WiFi network, limited to local network without additional configuration, power consumption higher than OLED alone
Best Use Cases Remote monitoring, data logging visualization, multi-user access, professional dashboards

Button Input Interface

Aspect Evaluation
Implementation Approach Digital GPIO reading with debouncing, press pattern detection (single/double/triple/hold) enables mode navigation
User Experience Intuitive press patterns, immediate visual feedback on OLED, no complex UI navigation required
Reliability Hardware debouncing with INPUT_PULLUP, timeout-based pattern recognition prevents accidental triggers
Limitations Limited to single button interaction, pattern learning required, less flexible than touchscreen interfaces
Best Use Cases Simple mode selection, menu navigation, embedded system controls, low-cost input solutions

Comparison Summary

The combination of OLED display and WiFi web interface provides complementary benefits: OLED offers immediate local feedback with minimal latency and power consumption, while the WiFi interface enables rich visualization and remote access. The button-based input provides an intuitive, low-cost navigation method suitable for embedded systems. Together, these tools create a robust interface system that supports both local and remote interaction with sensor data.

Design Files

Design files and code documentation for interface and application programming projects.

ESP32-S3 Development Board and Pinouts

Code files for ESP32-S3 development board interfaces including I2C scanning, OLED display control, and button-based user interface systems. See Week 4 documentation for board design and Week 8 documentation for pinout configurations.

I2C Scanner (i2cscan_generic.ino)

Utility code for scanning and detecting I2C devices on the bus, essential for troubleshooting connection issues.

How the Code Works (Pseudocode)
SETUP:
  Initialize I2C bus
  Initialize Serial communication
  Print "I2C Scanner" message

LOOP:
  Print "Scanning..." message
  Initialize device counter to 0
  
  FOR each address from 1 to 126:
    Begin I2C transmission to address
    Check transmission result
    
    IF transmission successful (error == 0):
      Print device found at address (hex format)
      Increment device counter
    ELSE IF unknown error (error == 4):
      Print unknown error at address
    
  IF no devices found:
    Print "No I2C devices found"
  ELSE:
    Print "done"
  
  Wait 5 seconds before next scan
Key Features
  • Scans all 127 possible I2C addresses (0x01-0x7E)
  • Detects and reports connected devices with hex address format
  • Handles multiple error conditions (device not found, unknown errors)
  • Continuous scanning mode with 5-second intervals
  • Compatible with any I2C bus configuration (Wire, Wire1, etc.)
What You Need to Know
  • I2C Address Range: Valid addresses are 0x08-0x77 (8-119 decimal); addresses 0x00-0x07 and 0x78-0x7F are reserved
  • Common Addresses: OLED displays typically use 0x3C or 0x3D; sensors vary (MAX30102 uses 0x57)
  • Troubleshooting: If no devices found, check wiring (SDA, SCL, power, ground), verify pull-up resistors, confirm device power
  • Usage: Run this before connecting other devices to verify I2C bus is working correctly
Download: i2cscan_generic.ino

Hello World OLED Display (hello_world.ino)

Basic OLED display test code that initializes the display and shows "Hello World" text, confirming I2C communication and display functionality.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial communication at 115200 baud
  Wait 500ms for Serial to stabilize
  
  Initialize I2C bus with SDA pin 5, SCL pin 6
  Print "Starting..." message
  
  Attempt to initialize OLED display:
    IF initialization fails:
      Print "OLED not found" error
      Enter infinite loop (halt)
  
  Clear display buffer
  Set text size to 2
  Set text color to white
  Set cursor position to (0, 20)
  Print "Hello" line
  Print "World!" line
  Update display (send buffer to hardware)

LOOP:
  Empty (runs once, then waits)
Key Features
  • Simple OLED initialization and text display
  • Custom I2C pin configuration for XIAO ESP32-S3 (SDA=5, SCL=6)
  • Error handling with infinite loop if display not found
  • Text size and cursor positioning for centered display
  • One-time display update (no loop refresh needed for static text)
What You Need to Know
  • I2C Pin Configuration: XIAO ESP32-S3 uses pins 5 (SDA) and 6 (SCL) by default; verify your board's pinout
  • Display Address: SSD1306 OLED typically uses address 0x3C; some variants use 0x3D
  • Display Update: Must call display.display() to send buffer to hardware; drawing functions only modify buffer
  • Testing: Use this as first test after connecting OLED to verify wiring and I2C communication before adding complex features
  • Libraries Required: Adafruit_GFX, Adafruit_SSD1306, Wire
Download: hello_world.ino

Button User Interface (outputs.ino)

Mode-based navigation system using button press patterns (single, double, triple, hold) to control multiple output devices including OLED display, camera, sensors, and LED flashlight.

How the Code Works (Pseudocode)
SETUP:
  Initialize OLED display
  Initialize camera module
  Initialize sensors (MPU6050, HX711)
  Initialize button pin (INPUT_PULLUP)
  Initialize LED pin (OUTPUT)
  Set current mode to MENU
  Display menu screen

LOOP:
  Read button state
  
  IF button pressed:
    Record press start time
    Start press detection timer
  
  IF button released:
    Calculate press duration
    IF duration > HOLD_THRESHOLD:
      Activate flashlight mode
    ELSE:
      Increment press count
      Reset press timeout timer
  
  IF press timeout exceeded:
    Process accumulated press count:
      IF press count == 1: Switch to CAMERA mode
      IF press count == 2: Switch to SENSORS mode
      IF press count == 3: Switch to MENU mode
    Reset press count
  
  IF current mode == MENU:
    Display menu screen (button instructions)
  
  IF current mode == CAMERA:
    Capture camera frame
    Process image with dithering algorithm
    Display on OLED
    Run Edge Impulse inference (optional)
    Overlay results on display
  
  IF current mode == SENSORS:
    Read accelerometer/gyroscope data
    Read load cell data
    Display sensor readings on OLED
  
  Update display
Key Features
  • Press pattern detection: single (1x), double (2x), triple (3x), and hold
  • Mode-based navigation system (Menu, Camera, Sensors)
  • Button debouncing with timeout-based pattern recognition
  • Floyd-Steinberg dithering for camera-to-OLED video display
  • Edge Impulse AI inference integration for face detection
  • Multi-sensor integration (MPU6050 accelerometer/gyro, HX711 load cell)
  • Flashlight mode activated by button hold
What You Need to Know
  • Button Wiring: Use INPUT_PULLUP mode (button connects pin to GND when pressed, internal pull-up to 3.3V)
  • Press Detection: Press count is accumulated until timeout (1 second); longer timeout allows slower multiple presses
  • Mode Switching: Each mode has distinct display update logic; ensure proper initialization in setup()
  • Camera Performance: Video streaming to OLED requires significant processing; frame rate depends on resolution and dithering complexity
  • Dependencies: Requires camera_pins.h header file with XIAO ESP32-S3 camera pin definitions; see Ethical AI Use for development details
  • Sensor Conflicts: Code uses preprocessor directives to resolve sensor_t type conflict between ESP32 camera and Adafruit MPU6050 libraries
Download: outputs.ino | camera_pins.h | outputs.zip (complete project)

Grip Strength Monitor (Load Cell + WiFi GUI)

Design files and firmware for a Wi-Fi-enabled grip strength meter built around an 80 kg bar load cell, HX711 amplifier, and ESP32-S3. The mechanical design was informed by the open-source grip strength meter from NeuroTech Hub and validated against the CZL601AC bar load cell datasheet (online, download).

Mechanical Design Files (3D-Printed Components)

  • Base.3mf — main chassis that captures the bar load cell and anchors the fixed side of the gripper.
  • Case.3mf — protective enclosure for the ESP32-S3 and HX711 amplifier with cable strain relief.
  • Handle.3mf — curved grip handle that transfers hand force into the free end of the load cell.
  • Calibration Print.3mf — small test piece used to verify hole diameters and load cell clearances before printing the full assembly.

All parts were printed in PLA with high infill in the load paths to minimize creep and flex during repeated maximal grip trials.

Basic HX711 Reader (loadcell_simple.ino)

Minimal firmware to bring up the HX711 amplifier and read calibrated weight values over Serial for debugging and calibration.

How the Code Works (Pseudocode)
SETUP:
  Configure HX711 data and clock pins (DT=A1, SCK=A0)
  Initialize Serial at 115200 baud
  Begin HX711 with DT/SCK pins
  Set calibration factor (grams per ADC unit)
  Tare the scale so current load is zero

LOOP (every 200 ms):
  If HX711 is ready:
    Read averaged weight using get_units(4)
    Print "weight:<value>" to Serial for Serial Plotter
  Else:
    Print "HX711 not ready" for troubleshooting
Key Features
  • Simple initialization of the HX711 on analog pins A0/A1.
  • Configurable calibration factor for mapping counts to grams or kilograms.
  • Timed reads (200 ms) to keep Serial output manageable and Plotter-friendly.
  • Graceful handling of HX711 not-ready states.
What You Need to Know
  • Use for initial bring-up: Run this first when wiring the HX711 and load cell to confirm clean, stable readings.
  • Calibration factor: Determined experimentally by hanging known weights and adjusting until readings match; see the calibration notes in Calibration Chat.
  • Serial Plotter: The weight:<value> format is convenient for quickly visualizing changes while squeezing the handle.
Download: loadcell_simple.ino

Serial Plotter-Friendly Reader (loadcell_plot.ino)

Refined HX711 reader tuned for the Arduino Serial Plotter: it outputs a single numeric value per line for clean plotting of grip strength over time.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial at 115200 baud
  Initialize HX711 on DT=A1, SCK=A0
  Set calibration factor
  Tare the scale
  Optionally print debug messages when DEBUG=1

LOOP (every 200 ms):
  If HX711 is ready:
    Read filtered weight with get_units(4)
    Optionally print labeled debug text
    Print only the numeric weight to Serial for the Plotter
  Else:
    Optionally print "not ready" debug text
    Print 0 so the plotted line continues gracefully
Key Features
  • DEBUG toggle: Compile-time switch to enable/disable human-readable logs without breaking the Serial Plotter format.
  • Clean “one number per line” output for multi-trial grip testing in the Serial Plotter.
  • Automatic zero output when the HX711 is not ready to keep the time axis continuous.
  • Shared pinout and calibration approach with loadcell_simple.ino for easy swapping.
What You Need to Know
  • Use this sketch to tune calibration and visualize grip curves without any GUI overhead.
  • When collecting data for analysis, keep DEBUG set to 0 so the output is a pure numeric stream.
  • The sample interval (200 ms) gives a smooth trace while keeping file sizes reasonable for multi-second squeezes.
Download: loadcell_plot.ino

WiFi Grip Strength GUI (loadcell_gui.ino)

Full application firmware that exposes grip strength and an estimated age over Wi-Fi using an HTTP server and a Chart.js web dashboard.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial
  Initialize HX711 (pins, calibration factor, tare)
  Connect ESP32-S3 to WiFi (MIT network in this build)
  Start WebServer on port 80
  Register handlers:
    "/"        → serve HTML+JS GUI page from PROGMEM
    "/metrics" → serve JSON with current grip and age

LOOP:
  Handle incoming HTTP clients
  Every 200 ms:
    If HX711 is ready:
      Read smoothed grip strength (kg) via get_units(3)
      Clamp negative values to zero
      Store in global gripStrength

AGE ESTIMATION HELPERS:
  ageFromGripMale(g):
    Clamp g to plausible range
    Compute age using inverted quadratic fit derived from normative data
  ageFromGripFemale(g):
    Same structure with female-specific parameters

HTTP /metrics ENDPOINT:
  Read "sex" query parameter (default "male")
  Compute ageEstimate = ageFromGripMale/ageFromGripFemale(gripStrength)
  Return JSON:
    {"grip": <kg>, "age": <years>}

CLIENT-SIDE GUI (HTML + JS):
  Render dark-themed dashboard with:
    - Sex toggle buttons (male/female)
    - Numeric grip strength (kg) and age
    - Scrolling Chart.js line plot of recent grip values
  Poll /metrics every 200 ms and update DOM + chart
Key Features
  • Embedded HTML/JS dashboard served directly from the ESP32-S3 using PROGMEM.
  • Real-time grip strength plot using Chart.js with ~120 recent samples.
  • Simple sex toggle that switches between male and female age-estimation curves.
  • JSON API at /metrics for future extensions (e.g., logging clients).
What You Need to Know
  • WiFi credentials: Update the ssid and password constants to match your network.
  • Normative model: The age equations are simplified fits inspired by the grip-strength trajectories reported in Syddall et al., PLOS ONE 2014 and are for educational visualization only, not clinical use.
  • Browser requirements: Any modern browser with JavaScript and network access can connect to the ESP32-S3’s IP address to view the dashboard.
  • Development log: The full iterative design of this sketch is captured in the ChatGPT transcript: Grip Strength Monitor Code Chat.
Download: loadcell_gui.ino

Invisible String Chain of Hearts

Code files for the Invisible String pulse oximeter interface system, providing real-time health monitoring through OLED display and WiFi web interface. See Week 11 PCB design documentation for hardware details.

OLED GUI for Pulse Oximeter (pulse_vo2_reads_fixing.ino)

Local OLED display interface showing real-time pulse oximeter readings including heart rate (BPM), blood oxygen saturation (SpO2), and raw IR/RED LED sensor values.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial communication
  Initialize I2C bus (SDA=5, SCL=6) at 400kHz
  Initialize MAX30102 sensor
  Configure sensor:
    Set LED mode to RED + IR
    Set ADC range to 16384
    Set sample rate to 100 Hz
    Set pulse width to 411 μs
    Set LED brightness to medium (0x3F)
  Initialize OLED display
  Clear and prepare display

LOOP:
  Read IR and RED LED values from sensor
  
  Heart Rate Detection:
    Check for heartbeat in IR signal using peak detection
    IF heartbeat detected:
      Calculate time since last beat
      Calculate BPM = 60 / (time_delta / 1000)
      Set beat flag for visual indicator
      Update last beat timestamp
  
  SpO2 Calculation (every 300ms):
    Add IR and RED values to circular buffer
    IF buffer has 50 samples:
      Calculate DC components (average)
      Calculate AC components (RMS)
      Calculate R ratio = (AC_RED/DC_RED) / (AC_IR/DC_IR)
      Estimate SpO2 = 110 - 25 * R
      Clamp SpO2 to 70-100% range
  
  Serial Output:
    Print IR, RED, BPM for Serial Plotter visualization
  
  OLED Display Update:
    Clear display buffer
    Display IR value (small text)
    Display RED value (small text)
    Display BPM value (large text, size 2)
    Display SpO2 percentage (small text)
    IF beat detected: Draw heartbeat indicator dot
    Update display hardware
  
  Delay 20ms (50 Hz update rate)
Key Features
  • Real-time heart rate detection using peak detection algorithm on IR signal
  • SpO2 calculation using ratio-of-ratios method with DC/AC component analysis
  • Circular buffer system for storing 50 samples of IR/RED data
  • Visual heartbeat indicator (flashing dot) when pulse detected
  • Dual output: OLED display and Serial Plotter for real-time waveform visualization
  • Optimized sensor configuration for reliable readings (100 Hz sample rate, medium brightness)
What You Need to Know
  • Sensor Placement: Finger must cover sensor completely; proper contact ensures accurate readings
  • I2C Address: MAX30102 uses address 0x57; verify with I2C scanner if sensor not detected
  • Ground Isolation: RD and IRD pins must be isolated from main ground plane to prevent power issues (see Week 11 PCB design)
  • SpO2 Accuracy: Calculation provides estimation; medical-grade accuracy requires calibration and FDA-approved algorithms
  • Buffer Size: 50-sample buffer provides balance between calculation accuracy and response time
  • Libraries Required: MAX30105 (SparkFun library), Adafruit_GFX, Adafruit_SSD1306, heartRate.h (beat detection)
  • Troubleshooting: If sensor not detected, check power isolation, I2C wiring, and sensor initialization order
Download: pulse_vo2_reads_fixing.ino

WiFi Readings GUI (pulse_gui.ino)

WiFi-enabled web interface providing remote access to pulse oximeter data through HTTP server with JSON API endpoint for real-time data updates.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial communication
  Initialize I2C bus
  Initialize MAX30102 sensor
  Configure sensor (LED mode, sample rate, pulse width)
  Initialize OLED display
  Initialize WiFi:
    Connect to network (SSID, password)
    Wait for connection
    Print IP address
  Initialize HTTP server:
    Route "/" → serve GUI HTML page
    Route "/gui" → serve GUI HTML page
    Route "/metrics" → serve JSON data
  Start web server

LOOP:
  Handle incoming HTTP client requests
  
  Read IR and RED values from sensor
  
  Heart Rate Calculation:
    Check for heartbeat in IR signal
    IF heartbeat detected:
      Calculate BPM from time delta
      Update global BPM variable
  
  SpO2 Calculation:
    Add IR/RED to circular buffer
    IF buffer full (50 samples):
      Calculate SpO2 using ratio-of-ratios
      Update global SpO2 variable
  
  Update global variables (g_ir, g_red, g_bpm, g_spo2)
  
  OLED Display Update:
    Display IR, RED, BPM, SpO2 values
    Update display hardware
Key Features
  • Dual interface: OLED display (local) and WiFi web interface (remote)
  • HTTP server with embedded HTML page stored in PROGMEM
  • JSON API endpoint (/metrics) for real-time data retrieval
  • Automatic WiFi connection with connection status feedback
  • IP address display for easy access
  • Simultaneous sensor reading and web server operation
  • Global variable system for data sharing between sensor reading and HTTP handlers
What You Need to Know
  • WiFi Configuration: Update SSID and password in code; for MIT network, use generated device password from wifi.mit.edu
  • Network Access: Web interface accessible only from devices on same WiFi network; IP address printed to Serial Monitor
  • HTML Storage: GUI HTML page stored in PROGMEM (program memory) to conserve RAM; use PROGMEM for large strings
  • Server Handling: Must call server.handleClient() frequently in loop() for responsive web interface
  • Data Refresh: Client-side JavaScript polls /metrics endpoint every 300ms for real-time updates
  • Power Consumption: WiFi significantly increases power draw compared to OLED-only mode; consider power management for battery operation
  • Libraries Required: WiFi, WebServer, MAX30105, Adafruit_SSD1306
Download: pulse_gui.ino

WiFi Plot GUI (pulse_gui_2.ino)

Enhanced WiFi web interface with real-time plotting capabilities using Chart.js library, displaying live line charts for BPM and SpO2 values with automatic scrolling and data management.

How the Code Works (Pseudocode)
SETUP:
  (Same as pulse_gui.ino)
  Initialize WiFi, sensor, OLED, HTTP server

LOOP:
  (Same as pulse_gui.ino)
  Handle HTTP requests, read sensor, calculate BPM/SpO2

GUI HTML PAGE (embedded in PROGMEM):
  Load Chart.js library from CDN
  Create two Chart.js line chart instances:
    - BPM chart (y-axis: 40-160 BPM)
    - SpO2 chart (y-axis: 70-100%)
  Initialize data arrays for each chart
  
  JavaScript Update Function (runs every 300ms):
    Fetch JSON data from /metrics endpoint
    Update numerical displays (BPM, SpO2, IR, RED)
    Add new BPM value to BPM data array
    Add new SpO2 value to SpO2 data array
    IF array length > maxPoints (100):
      Remove oldest value (shift)
    Update chart labels (array indices)
    Update chart datasets with new data
    Call chart.update() to refresh display
  
  Set interval to call update function every 300ms
Key Features
  • Real-time line chart visualization using Chart.js library
  • Dual chart display: BPM and SpO2 trends over time
  • Automatic data scrolling: maintains 100 most recent data points
  • Numerical displays alongside charts for precise values
  • Responsive design with dark theme for OLED-style aesthetic
  • Automatic chart scaling with fixed y-axis ranges for consistent visualization
  • CDN-based Chart.js loading for minimal memory footprint
What You Need to Know
  • Chart.js CDN: Library loaded from jsdelivr.net CDN; requires internet connection on client device
  • Data Management: Arrays limited to 100 points to prevent memory overflow; older data automatically discarded
  • Update Rate: 300ms refresh rate balances responsiveness with server load; adjust based on network conditions
  • Chart Configuration: Y-axis ranges fixed (BPM: 40-160, SpO2: 70-100) for consistent scaling; modify in JavaScript if needed
  • Browser Compatibility: Requires modern browser with JavaScript enabled; tested on Chrome, Firefox, Safari
  • Performance: Chart updates are lightweight; multiple simultaneous clients may impact ESP32 performance
  • Offline Operation: Charts won't load if client device lacks internet (Chart.js CDN unavailable); consider local hosting for offline use
Download: pulse_gui_2.ino

Reflections & Learnings

Key insights and learnings from working with interface and application programming.

Contributions

Acknowledgements and team roles for interface and application programming work.

Ethical AI Use

Transparent documentation of AI assistance used in this week's interface and application programming work.

This section documents all AI assistance used during Week 12 interface and application programming work. ChatGPT was used for code development, troubleshooting, and technical guidance. All transcripts are linked below for transparency.

Menu System with Modes

AI assistance for developing the button-based menu system with mode navigation (Menu, Camera, Sensors) using press pattern detection. The conversation covered button debouncing, press pattern recognition, mode state management, and OLED menu display design.

Related to: Part (a): Simple Button User Interface on OLED

View ChatGPT Transcript: Menu System with Modes

I2C Device Not Found

Troubleshooting session for I2C device detection issues with MAX30102 pulse oximeter sensor. The conversation addressed power isolation problems, I2C wiring verification, sensor initialization order, and ground plane isolation requirements for accurate sensor operation.

Related to: Part (b): Real-Time Graphical User Interface through OLED and WiFi

View ChatGPT Transcript: I2C Device Not Found

Hello World Code

Development assistance for creating the initial OLED "Hello World" test program. The conversation covered I2C initialization, OLED display library setup, text rendering, and basic display configuration for XIAO ESP32-S3 development board.

Related to: Part (b): Real-Time Graphical User Interface through OLED and WiFi (initial OLED test)

View ChatGPT Transcript: Hello World Code

MAX30102 Initialization Fix

Technical guidance for fixing MAX30102 pulse oximeter sensor initialization issues. The conversation addressed sensor configuration parameters, LED brightness settings, sample rate optimization, initialization sequence requirements, and troubleshooting sensor communication problems.

Related to: Part (b): Real-Time Graphical User Interface through OLED and WiFi (pulse oximeter readings)

View ChatGPT Transcript: MAX30102 Initialization Fix

Grip Strength Monitor Code Design

Code-focused assistance for designing and refining the WiFi grip strength monitor firmware. The conversation covered HX711 bring-up, load cell pin mapping, Serial Plotter debugging sketches, the ESP32-S3 HTTP server, the Chart.js dashboard, and the age-estimation helpers used in loadcell_simple.ino, loadcell_plot.ino, and loadcell_gui.ino.

Related to: Part (c): Real-Time GUI through Mechanical Gripper and WiFi and Grip Strength Monitor design files

View ChatGPT Transcript: Grip Strength Monitor Code

Grip Strength Calibration & Scaling

Calibration-focused assistance for mapping HX711 counts to kilograms and validating the grip strength readings. The discussion walked through using the Serial Plotter, collecting reference weights, tuning the calibration factor, and sanity-checking the age-estimation model derived from normative grip strength data.

Related to: Part (c): Real-Time GUI through Mechanical Gripper and WiFi calibration workflow and the Grip Strength Monitor sketches.

View ChatGPT Transcript: Grip Strength Calibration

Grip Strength Monitor – Cursor Transcript

Full Cursor AI transcript focused on organizing the grip strength monitor section: structuring Part (c), integrating design files, embedding images and videos, and aligning captions, external references, and the Ethical AI Use documentation for the load cell project.

Related to: Part (c): Real-Time GUI through Mechanical Gripper and WiFi, Grip Strength Monitor design files, and this Ethical AI Use section.

View HTML Transcript Download Markdown Transcript

Week 12 Project Documentation

Complete Cursor AI transcript for Week 12 interface and application programming project documentation. This comprehensive conversation covers the creation and population of the Week 12 HTML page, including Individual Assignment sections (button UI and WiFi GUI), Group Assignment tool comparisons, Design Files documentation with pseudocode, and Ethical AI Use section organization. The transcript demonstrates the collaborative process of building professional documentation with structured content, embedded media, and comprehensive code documentation.

Related to: Complete Week 12 documentation including Individual Assignment, Group Assignment, Design Files, and overall page structure

View HTML Transcript Download Markdown Transcript

Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License

``` ```html Week 13 · Wildcard Week
← Back to Home
[Profile Image Placeholder]

Week 13

Wildcard Week

Week Highlights

Key captures from the group and individual assignments with links to their sections.

Button User Interface on OLED

OLED button user interface menu system

Hello World on OLED

Hello World display on OLED for Invisible String project

Pulse Oximeter Readings

Pulse oximeter readings showing IR, RED, and BPM values

Wi-Fi GUI Readings

Wi-Fi web interface displaying real-time pulse oximeter readings

Wi-Fi GUI Plots

Wi-Fi web interface with real-time plotting of pulse oximeter data

OLED Video Stream Demo

Grip Strength Gripper

CAD rendering of the full grip strength device with base, handle, and load cell Photo of the fully assembled grip strength device with electronics and handle

Load Cell Calibration Plot

Serial Plotter screenshot showing load cell readings rising with grip force

Grip Strength WiFi GUI

Table of Contents

Course Content

Training & Documentation

Assignments & Projects

Wildcard Week

This week focuses on exploring digital fabrication processes not covered in previous assignments. We'll design and produce something using computer-aided design and manufacturing, documenting requirements and including everything necessary for reproduction. This week also includes reflection on the impact and purpose of making (almost) anything.

Exploring new digital fabrication processes
Designing and producing with CAD/CAM
Understanding the impact and purpose of fabrication labs

This Week's Goals

  • Explore New Processes
    Design and produce something with a digital process not covered in other assignments
  • Complete Documentation
    Document requirements and include everything necessary to reproduce the project
  • Reflect on Impact
    Understand the purpose and impact of fabrication labs and making

Assignments

  • Group Assignment
    Compare as many tool options as possible
  • Individual Assignment
    Write an application that interfaces a user with an input &/or output device that you made

Tools & Materials

  • ESP32-S3 Development Boards
  • OLED Displays (SSD1306)
  • MAX30102 Pulse Oximeter Sensor
  • Buttons & User Input Devices
  • Interface Programming Frameworks

Training Documentation

Training materials and documentation for interface and application programming.

No recitation this week.

Useful Documentation

Essential resources for interface and application programming.

Class Page

Interface and Application Programming - MIT Academy

Comprehensive resource covering interface design, application programming, GUI frameworks, embedded UI development, web interfaces for embedded systems, and user interaction patterns. Includes detailed tutorials, code examples, and implementation guides for various interface programming tools and frameworks.

Key Topics

  • Interface Design: User experience principles, interaction patterns, feedback mechanisms
  • Embedded UI: OLED displays, LCD interfaces, character displays
  • Web Interfaces: HTTP servers, REST APIs, WebSockets, real-time data visualization
  • Application Frameworks: GUI toolkits, web frameworks, mobile apps
  • User Input: Buttons, touch interfaces, gesture recognition, voice commands

Additional References

Individual Assignment: Interface & Application Programming

Write an application that interfaces a user with an input &/or output device that you made. This assignment demonstrates three interface applications: (a) a simple button user interface on OLED, (b) a real-time graphical user interface through OLED and Wi-Fi for pulse oximeter readings, and (c) a Wi-Fi grip strength monitor with a mechanical gripper and age-estimation web dashboard.

Part (a): Simple Button User Interface on OLED

A mode-based user interface system that interfaces users with multiple input and output devices through a simple button press interface. The system provides visual feedback on an OLED display and enables navigation between different modes (Menu, Camera, Sensors) using button press patterns. Users interact by pressing a button multiple times to select modes, with visual confirmation displayed on the OLED screen.

Interface Design

The interface uses a mode-based navigation system where button presses trigger mode changes. A single press enters Camera mode, two presses enter Sensors mode, three presses return to Menu, and holding the button activates a flashlight function. The OLED display shows the current menu state and provides clear visual feedback for each mode transition. See Ethical AI Use: Menu System with Modes for AI-assisted development details.

OLED button user interface menu system displaying mode selection options
OLED button user interface menuMenu screen showing available modes: Camera, Sensors, and Menu navigation options with button press instructions.
Button UI demonstrationVideo showing button press interactions navigating through different modes on the OLED display.
First video stream on OLEDInitial camera feed streaming to OLED display using dithering algorithm for monochrome conversion, demonstrating real-time video output interface.
Download Design Files
  • outputs.ino — Button user interface code with mode system
  • camera_pins.h — Camera pin definitions header file
  • outputs.zip — Complete project archive including all dependencies

Part (b): Real-Time Graphical User Interface through OLED and WiFi

A dual-interface health monitoring system that interfaces users with a MAX30102 pulse oximeter sensor through both an OLED display and a WiFi-enabled web interface. The system provides real-time visualization of heart rate (BPM), blood oxygen saturation (SpO2), and raw sensor data (IR and RED LED readings) through multiple output channels. Users can view data locally on the OLED display or remotely via a web browser accessing the ESP32-S3's built-in HTTP server. See Ethical AI Use: I2C Device Not Found for troubleshooting documentation.

Interface Design

The system provides dual-interface access: a local OLED display shows real-time sensor readings (IR, RED, BPM, SpO2) with visual heartbeat indicators, while a WiFi web interface provides comprehensive data visualization including numerical displays and real-time plotting charts. The web interface uses Chart.js for dynamic graph generation and automatically refreshes every 300ms to maintain real-time data updates. Both interfaces run simultaneously, enabling local monitoring and remote access.

Hello World on OLED

Initial OLED display test showing successful I2C communication and display initialization. See Ethical AI Use: Hello World Code for development details.

Hello World display on OLED for Invisible String project showing successful display initialization
Hello World on OLEDInitial OLED test confirming I2C communication and display functionality before implementing sensor interfaces.
Pulse Oximeter Readings on OLED

Real-time pulse oximeter data displayed on OLED showing IR and RED LED readings, heart rate (BPM), and blood oxygen saturation (SpO2) percentage. A heartbeat indicator flashes when a pulse is detected. See Ethical AI Use: MAX30102 Initialization Fix for sensor setup documentation.

Pulse oximeter readings on OLED displaying IR, RED, BPM, and SpO2 values
OLED sensor readings displayReal-time pulse oximeter data showing IR and RED LED values, heart rate (BPM), and blood oxygen saturation (SpO2) with heartbeat indicator.
BPM and SpO2 demonstrationVideo showing real-time heart rate and blood oxygen saturation measurements updating on OLED display with sensor interaction.
Pulse Oximeter Readings on WiFi GUI

WiFi web interface providing remote access to pulse oximeter data through a responsive HTML dashboard. The interface displays real-time numerical values for BPM, SpO2, IR, and RED readings with automatic data refresh. The web server runs on the ESP32-S3, allowing access from any device on the same WiFi network.

WiFi web interface displaying real-time pulse oximeter readings including BPM, SpO2, IR, and RED values
WiFi GUI readings dashboardRemote web interface showing real-time pulse oximeter data accessible from any device on the WiFi network, displaying BPM, SpO2, IR, and RED values with automatic updates.
Pulse Oximeter Plots on WiFi GUI

Enhanced WiFi web interface with real-time plotting capabilities using Chart.js library. The interface displays live line charts for BPM and SpO2 values, showing trends over time with automatic scrolling and data point management. This visualization enables users to observe patterns in heart rate and blood oxygen levels during monitoring sessions.

Serial monitor output showing sensor readings rising on touch interaction
Serial monitor sensor responseSerial output demonstrating sensor readings increase when finger is placed on MAX30102 sensor, showing IR and RED LED response to touch.
WiFi web interface with real-time plotting of BPM and SpO2 data using Chart.js
WiFi GUI with plotting chartsEnhanced web interface displaying real-time line charts for BPM and SpO2 values, showing trends over time with automatic data refresh and chart scrolling.

I2C Device Detection

Successful I2C device detection after fixing power isolation issues. The system now correctly identifies the OLED display at address 0x3C and the MAX30102 sensor at address 0x57. Initial troubleshooting required isolating the RD (red LED) and IRD (infrared LED) ground terminals from the general ground plane to prevent power issues and enable proper sensor operation. 

20:04:48.612 -> Scanning...
20:04:48.644 -> I2C device found at address 0x3C  !
20:04:48.644 -> I2C device found at address 0x57  !
20:04:48.644 -> done
Download Design Files

Part (c): Real-Time GUI through Mechanical Gripper and WiFi

A Wi-Fi-connected grip strength meter that interfaces a user with a mechanical hand gripper, an 80 kg load cell, and an HX711 amplifier. The ESP32-S3 continuously measures grip force, streams it to a web dashboard, and uses a published relationship between handgrip strength and age to display an estimated “physiological age” in real time. The design is inspired by the open-source grip strength meter from NeuroTech Hub at WashU and the associated PLOS ONE paper on grip strength and age trajectories (Syddall et al., 2014), adapted to my load cell and handle geometry.

Mechanically, a custom 3D-printed gripper clamps around a CZL601-type 80 kg bar load cell (sourced from Amazon 80 kg load cell). I imported a 100 kg load cell CAD from GrabCAD, checked the mounting dimensions against the CZL601AC datasheet (online, download), and confirmed that the hole spacing and footprint match the commercial part used here.

Mechanical Design and Fabrication

CAD model of the 3D-printed grip strength base and load cell mounting region
Grip strength base CADTop view of the grip strength base showing the bar load cell pocket, mounting bosses, and handle interface.
Side view CAD of the hand gripper and load cell assembly
Side view of gripper assemblySide profile showing how the fixed base, moving handle, and load cell align along the force axis of the bar sensor.
Full CAD view of the grip strength device with base and handle
Full grip strength assemblyComplete CAD of the base, handle, and load cell, sized for comfortable adult hand placement and full-finger contact.
Close-up of mounting holes and clearances around the load cell in CAD
Load cell mounting holesDetail of the M6 clearance and counterbore geometry used to capture the load cell without constraining bending.
Perspective CAD view of the gripper handle and base
Handle ergonomicsPerspective view of the curved handle designed to distribute pressure across the palm and fingers during maximal grip.
Photo of drilled clearance hole aligned to the printed pilot in the base
Clearance hole verificationPrinted pilot holes used as drill guides to match the metric mounting dimensions from the CZL601AC datasheet.
Photo of the fully printed grip strength device before drilling and assembly
Fresh off the printer3D-printed base and handle components in PLA prior to post-processing and hardware installation.
Printed part clamped for drilling load cell mounting holes
Workholding for accurate drillingThe printed base clamped to the drill press table so the pilot features guide the final clearance holes into the load cell.
Drilling practiceTraining cuts on scrap material to dial in drill press settings and avoid cracking the printed base during final holes.
Final load cell holesDrilling the final M6 clearance holes through the printed base, constrained by the pilot features to preserve alignment.

Electronics and Calibration

Electronics assembly with HX711 breakout, ESP32-S3, and load cell wiring
Electronics stack-upHX711 amplifier breakout from Amazon wired to the ESP32-S3 and 80 kg load cell with short, twisted signal pairs for noise reduction.
Fully assembled grip strength device with load cell, electronics, and handle
Assembled grip strength meterCompleted mechanical and electrical assembly ready for calibration and software bring-up.
Serial Plotter view of load cell readings increasing with grip force
Serial Plotter calibration tracesRaw HX711 output converted to kilograms and visualized in the Arduino Serial Plotter while applying known weights and grip forces.
Web GUI showing grip strength value, estimated age, and scrolling chart
Wi-Fi grip strength dashboardBrowser-based GUI with live grip strength (kg), estimated age, and a Chart.js time series plot of recent squeezes.

Model Used for Age Estimation

The age-estimation logic in the firmware is based on the non-linear, sex-specific grip-strength trajectories reported in Dodds et al., 2014 (PLOS ONE). As shown in Figure 1 of that paper, grip strength rises rapidly through adolescence, peaks around ages 30–40, and then declines non-linearly with age, with different magnitudes for males and females.

Reference grip strength trajectories over the life course from Dodds et al., PLOS ONE 2014
Reference trajectories (Figure 1)Age-dependent grip strength curves for males and females from Dodds et al., 2014, used as the qualitative target for the embedded model.
Simplified quadratic grip strength model fitted to reference data
Quadratic approximation (Table 2-inspired)Simplified male and female trajectories using peak strengths and curvatures chosen to approximate the summary values reported in Table 2 of Dodds et al., 2014.

To reproduce this shape efficiently on the ESP32, the firmware uses inverted quadratic approximations centered at age 35, consistent with the observed peak in the PLOS ONE data. In the forward direction, grip strength is approximated as:

Males: Grip(age) ≈ 52 − 0.0089·(age − 35)2
Females: Grip(age) ≈ 32 − 0.0059·(age − 35)2

On the device, this relationship is analytically inverted so that the measured grip strength can be mapped back to an estimated age:

age = 35 + √((a − Grip)/b), where a is the peak strength (52 kg for males, 32 kg for females) and b is the curvature (0.0089 for males, 0.0059 for females). The firmware clamps grip strength to physiologically meaningful ranges before applying this formula so the square root remains well-defined. 

float ageFromGripMale(float g) {
  float a = 52.0f, b = 0.0089f;
  if (g > a) g = a;
  if (g < 5) g = 5;
  return 35.0f + sqrtf((a - g) / b);
}

float ageFromGripFemale(float g) {
  float a = 32.0f, b = 0.0059f;
  if (g > a) g = a;
  if (g < 4) g = 4;
  return 35.0f + sqrtf((a - g) / b);
}

For full methodological details and original tables/figures, see the open-access paper: Dodds et al., 2014, PLOS ONE (download local PDF). The implementation here is an educational approximation and not intended for clinical or diagnostic use.

End-to-end live demoReal-time demonstration of squeezing the mechanical gripper and watching the Wi-Fi dashboard update grip strength and estimated age on a laptop.

Related Design, Code, and Calibration Resources

User Interface Comparison

Summary of how each interface application connects users with input and output devices.

Application How It Interfaces with the User Input Device(s) Output Device(s)
(a) Button User Interface Button press patterns (single, double, triple press, hold) provide mode selection input. OLED display shows current menu state and mode options. Users receive immediate visual feedback for each interaction. Button (GPIO pin 4) OLED Display (SSD1306, I²C 0x3C)
LED (GPIO pin 3, flashlight mode)
(b) Real-Time GUI (OLED & WiFi) Physical finger placement on MAX30102 sensor provides input. OLED displays real-time sensor data locally. WiFi web interface enables remote monitoring with numerical displays and live plotting charts accessible from any web browser. MAX30102 Pulse Oximeter Sensor (I²C 0x57) OLED Display (SSD1306, I²C 0x3C)
WiFi Web Interface (HTTP Server with Chart.js visualization)
(c) Grip Strength GUI (Load Cell & WiFi) Users squeeze a mechanical hand gripper that transfers force into an 80 kg bar load cell. The ESP32-S3 measures grip strength through the HX711 amplifier and streams results to a WiFi web dashboard that displays live grip force and an estimated physiological age in real time. Mechanical gripper linked to 80 kg load cell (CZL601-type)
HX711 load cell amplifier		 WiFi Web Interface (HTTP Server with Chart.js visualization)
Optional Serial Plotter (for calibration traces)

Group Assignment: Compare as Many Tool Options as Possible

Compare as many tool options as possible for interface and application programming.

General Comparison: Interface & Application Programming Tools

Comprehensive comparison of interface and application programming tools available for embedded systems and IoT development. This analysis covers tools from the MIT Academy Interface & Application Programming class page, evaluating their capabilities, use cases, and trade-offs for different application scenarios.

Embedded Display Interfaces

Tool/Framework Description Pros Cons Best For
OLED (SSD1306) Monochrome OLED displays via I²C Low power, high contrast, simple I²C interface, pixel-level control Limited resolution (128x64), monochrome only, small display size Status displays, sensor readouts, simple menus, embedded dashboards
LCD Character Displays Character-based LCD displays (16x2, 20x4) Simple API, readable in sunlight, low cost Limited to text/characters, no graphics, requires backlight power Text-only interfaces, status messages, debugging output
TFT Color Displays Full-color TFT LCD displays Color graphics, touch support, high resolution High power consumption, complex drivers, larger footprint Rich GUIs, image display, interactive touch interfaces

Web-Based Interfaces

Tool/Framework Description Pros Cons Best For
HTTP Server (ESP32) Built-in HTTP server on ESP32 for web interfaces Remote access, cross-platform (any browser), no app installation, real-time updates Requires WiFi, network dependency, limited to local network without port forwarding Remote monitoring, data visualization, control panels, sensor dashboards
WebSockets Real-time bidirectional communication Low latency, bidirectional, efficient for frequent updates More complex than HTTP, requires persistent connection Real-time streaming, interactive controls, live data feeds
Chart.js JavaScript charting library for web interfaces Beautiful charts, interactive, responsive, easy integration Requires JavaScript, CDN dependency or local hosting Data visualization, time series plots, sensor monitoring dashboards

Mobile & Native App Frameworks

Tool/Framework Description Pros Cons Best For
React Native Cross-platform mobile app framework Cross-platform (iOS/Android), native performance, large ecosystem Complex setup, requires mobile development knowledge Full-featured mobile apps, production deployments
Flutter Google's UI toolkit for cross-platform apps Single codebase, high performance, customizable UI Dart language, larger app size, learning curve Custom mobile interfaces, platform-specific designs
Progressive Web Apps (PWA) Web apps with native-like features No app store, cross-platform, offline capability Limited native API access, browser dependency Web-based mobile interfaces, simple deployment

Specific Comparison: Tools Used in Individual Assignment

Detailed comparison of the specific interface programming tools implemented in this week's individual assignment, evaluating their performance, ease of use, and suitability for embedded health monitoring applications.

OLED Display Interface (Adafruit SSD1306)

Aspect Evaluation
Ease of Implementation Simple I²C interface, well-documented Adafruit library, minimal wiring (SDA, SCL, power, ground)
Display Quality High contrast monochrome display, crisp text rendering, suitable for sensor data visualization
Power Consumption Very low power draw, ideal for battery-powered applications
Limitations 128x64 pixel resolution limits detail, monochrome only, small physical size (0.96" typical)
Best Use Cases Local sensor readouts, menu systems, status indicators, simple data displays

WiFi Web Interface (ESP32 HTTP Server + Chart.js)

Aspect Evaluation
Ease of Implementation ESP32 WebServer library provides straightforward HTTP server, Chart.js CDN integration requires minimal setup
Remote Access Accessible from any device on WiFi network (phone, tablet, computer), no app installation required
Visualization Capabilities Chart.js enables rich data visualization with real-time plotting, smooth animations, and interactive features
Real-Time Updates JSON API endpoint provides efficient data transfer, 300ms refresh rate maintains responsive feel
Limitations Requires WiFi network, limited to local network without additional configuration, power consumption higher than OLED alone
Best Use Cases Remote monitoring, data logging visualization, multi-user access, professional dashboards

Button Input Interface

Aspect Evaluation
Implementation Approach Digital GPIO reading with debouncing, press pattern detection (single/double/triple/hold) enables mode navigation
User Experience Intuitive press patterns, immediate visual feedback on OLED, no complex UI navigation required
Reliability Hardware debouncing with INPUT_PULLUP, timeout-based pattern recognition prevents accidental triggers
Limitations Limited to single button interaction, pattern learning required, less flexible than touchscreen interfaces
Best Use Cases Simple mode selection, menu navigation, embedded system controls, low-cost input solutions

Comparison Summary

The combination of OLED display and WiFi web interface provides complementary benefits: OLED offers immediate local feedback with minimal latency and power consumption, while the WiFi interface enables rich visualization and remote access. The button-based input provides an intuitive, low-cost navigation method suitable for embedded systems. Together, these tools create a robust interface system that supports both local and remote interaction with sensor data.

Design Files

Design files and code documentation for interface and application programming projects.

ESP32-S3 Development Board and Pinouts

Code files for ESP32-S3 development board interfaces including I2C scanning, OLED display control, and button-based user interface systems. See Week 4 documentation for board design and Week 8 documentation for pinout configurations.

I2C Scanner (i2cscan_generic.ino)

Utility code for scanning and detecting I2C devices on the bus, essential for troubleshooting connection issues.

How the Code Works (Pseudocode)
SETUP:
  Initialize I2C bus
  Initialize Serial communication
  Print "I2C Scanner" message

LOOP:
  Print "Scanning..." message
  Initialize device counter to 0
  
  FOR each address from 1 to 126:
    Begin I2C transmission to address
    Check transmission result
    
    IF transmission successful (error == 0):
      Print device found at address (hex format)
      Increment device counter
    ELSE IF unknown error (error == 4):
      Print unknown error at address
    
  IF no devices found:
    Print "No I2C devices found"
  ELSE:
    Print "done"
  
  Wait 5 seconds before next scan
Key Features
  • Scans all 127 possible I2C addresses (0x01-0x7E)
  • Detects and reports connected devices with hex address format
  • Handles multiple error conditions (device not found, unknown errors)
  • Continuous scanning mode with 5-second intervals
  • Compatible with any I2C bus configuration (Wire, Wire1, etc.)
What You Need to Know
  • I2C Address Range: Valid addresses are 0x08-0x77 (8-119 decimal); addresses 0x00-0x07 and 0x78-0x7F are reserved
  • Common Addresses: OLED displays typically use 0x3C or 0x3D; sensors vary (MAX30102 uses 0x57)
  • Troubleshooting: If no devices found, check wiring (SDA, SCL, power, ground), verify pull-up resistors, confirm device power
  • Usage: Run this before connecting other devices to verify I2C bus is working correctly
Download: i2cscan_generic.ino

Hello World OLED Display (hello_world.ino)

Basic OLED display test code that initializes the display and shows "Hello World" text, confirming I2C communication and display functionality.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial communication at 115200 baud
  Wait 500ms for Serial to stabilize
  
  Initialize I2C bus with SDA pin 5, SCL pin 6
  Print "Starting..." message
  
  Attempt to initialize OLED display:
    IF initialization fails:
      Print "OLED not found" error
      Enter infinite loop (halt)
  
  Clear display buffer
  Set text size to 2
  Set text color to white
  Set cursor position to (0, 20)
  Print "Hello" line
  Print "World!" line
  Update display (send buffer to hardware)

LOOP:
  Empty (runs once, then waits)
Key Features
  • Simple OLED initialization and text display
  • Custom I2C pin configuration for XIAO ESP32-S3 (SDA=5, SCL=6)
  • Error handling with infinite loop if display not found
  • Text size and cursor positioning for centered display
  • One-time display update (no loop refresh needed for static text)
What You Need to Know
  • I2C Pin Configuration: XIAO ESP32-S3 uses pins 5 (SDA) and 6 (SCL) by default; verify your board's pinout
  • Display Address: SSD1306 OLED typically uses address 0x3C; some variants use 0x3D
  • Display Update: Must call display.display() to send buffer to hardware; drawing functions only modify buffer
  • Testing: Use this as first test after connecting OLED to verify wiring and I2C communication before adding complex features
  • Libraries Required: Adafruit_GFX, Adafruit_SSD1306, Wire
Download: hello_world.ino

Button User Interface (outputs.ino)

Mode-based navigation system using button press patterns (single, double, triple, hold) to control multiple output devices including OLED display, camera, sensors, and LED flashlight.

How the Code Works (Pseudocode)
SETUP:
  Initialize OLED display
  Initialize camera module
  Initialize sensors (MPU6050, HX711)
  Initialize button pin (INPUT_PULLUP)
  Initialize LED pin (OUTPUT)
  Set current mode to MENU
  Display menu screen

LOOP:
  Read button state
  
  IF button pressed:
    Record press start time
    Start press detection timer
  
  IF button released:
    Calculate press duration
    IF duration > HOLD_THRESHOLD:
      Activate flashlight mode
    ELSE:
      Increment press count
      Reset press timeout timer
  
  IF press timeout exceeded:
    Process accumulated press count:
      IF press count == 1: Switch to CAMERA mode
      IF press count == 2: Switch to SENSORS mode
      IF press count == 3: Switch to MENU mode
    Reset press count
  
  IF current mode == MENU:
    Display menu screen (button instructions)
  
  IF current mode == CAMERA:
    Capture camera frame
    Process image with dithering algorithm
    Display on OLED
    Run Edge Impulse inference (optional)
    Overlay results on display
  
  IF current mode == SENSORS:
    Read accelerometer/gyroscope data
    Read load cell data
    Display sensor readings on OLED
  
  Update display
Key Features
  • Press pattern detection: single (1x), double (2x), triple (3x), and hold
  • Mode-based navigation system (Menu, Camera, Sensors)
  • Button debouncing with timeout-based pattern recognition
  • Floyd-Steinberg dithering for camera-to-OLED video display
  • Edge Impulse AI inference integration for face detection
  • Multi-sensor integration (MPU6050 accelerometer/gyro, HX711 load cell)
  • Flashlight mode activated by button hold
What You Need to Know
  • Button Wiring: Use INPUT_PULLUP mode (button connects pin to GND when pressed, internal pull-up to 3.3V)
  • Press Detection: Press count is accumulated until timeout (1 second); longer timeout allows slower multiple presses
  • Mode Switching: Each mode has distinct display update logic; ensure proper initialization in setup()
  • Camera Performance: Video streaming to OLED requires significant processing; frame rate depends on resolution and dithering complexity
  • Dependencies: Requires camera_pins.h header file with XIAO ESP32-S3 camera pin definitions; see Ethical AI Use for development details
  • Sensor Conflicts: Code uses preprocessor directives to resolve sensor_t type conflict between ESP32 camera and Adafruit MPU6050 libraries
Download: outputs.ino | camera_pins.h | outputs.zip (complete project)

Grip Strength Monitor (Load Cell + WiFi GUI)

Design files and firmware for a Wi-Fi-enabled grip strength meter built around an 80 kg bar load cell, HX711 amplifier, and ESP32-S3. The mechanical design was informed by the open-source grip strength meter from NeuroTech Hub and validated against the CZL601AC bar load cell datasheet (online, download).

Mechanical Design Files (3D-Printed Components)

  • Base.3mf — main chassis that captures the bar load cell and anchors the fixed side of the gripper.
  • Case.3mf — protective enclosure for the ESP32-S3 and HX711 amplifier with cable strain relief.
  • Handle.3mf — curved grip handle that transfers hand force into the free end of the load cell.
  • Calibration Print.3mf — small test piece used to verify hole diameters and load cell clearances before printing the full assembly.

All parts were printed in PLA with high infill in the load paths to minimize creep and flex during repeated maximal grip trials.

Basic HX711 Reader (loadcell_simple.ino)

Minimal firmware to bring up the HX711 amplifier and read calibrated weight values over Serial for debugging and calibration.

How the Code Works (Pseudocode)
SETUP:
  Configure HX711 data and clock pins (DT=A1, SCK=A0)
  Initialize Serial at 115200 baud
  Begin HX711 with DT/SCK pins
  Set calibration factor (grams per ADC unit)
  Tare the scale so current load is zero

LOOP (every 200 ms):
  If HX711 is ready:
    Read averaged weight using get_units(4)
    Print "weight:<value>" to Serial for Serial Plotter
  Else:
    Print "HX711 not ready" for troubleshooting
Key Features
  • Simple initialization of the HX711 on analog pins A0/A1.
  • Configurable calibration factor for mapping counts to grams or kilograms.
  • Timed reads (200 ms) to keep Serial output manageable and Plotter-friendly.
  • Graceful handling of HX711 not-ready states.
What You Need to Know
  • Use for initial bring-up: Run this first when wiring the HX711 and load cell to confirm clean, stable readings.
  • Calibration factor: Determined experimentally by hanging known weights and adjusting until readings match; see the calibration notes in Calibration Chat.
  • Serial Plotter: The weight:<value> format is convenient for quickly visualizing changes while squeezing the handle.
Download: loadcell_simple.ino

Serial Plotter-Friendly Reader (loadcell_plot.ino)

Refined HX711 reader tuned for the Arduino Serial Plotter: it outputs a single numeric value per line for clean plotting of grip strength over time.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial at 115200 baud
  Initialize HX711 on DT=A1, SCK=A0
  Set calibration factor
  Tare the scale
  Optionally print debug messages when DEBUG=1

LOOP (every 200 ms):
  If HX711 is ready:
    Read filtered weight with get_units(4)
    Optionally print labeled debug text
    Print only the numeric weight to Serial for the Plotter
  Else:
    Optionally print "not ready" debug text
    Print 0 so the plotted line continues gracefully
Key Features
  • DEBUG toggle: Compile-time switch to enable/disable human-readable logs without breaking the Serial Plotter format.
  • Clean “one number per line” output for multi-trial grip testing in the Serial Plotter.
  • Automatic zero output when the HX711 is not ready to keep the time axis continuous.
  • Shared pinout and calibration approach with loadcell_simple.ino for easy swapping.
What You Need to Know
  • Use this sketch to tune calibration and visualize grip curves without any GUI overhead.
  • When collecting data for analysis, keep DEBUG set to 0 so the output is a pure numeric stream.
  • The sample interval (200 ms) gives a smooth trace while keeping file sizes reasonable for multi-second squeezes.
Download: loadcell_plot.ino

WiFi Grip Strength GUI (loadcell_gui.ino)

Full application firmware that exposes grip strength and an estimated age over Wi-Fi using an HTTP server and a Chart.js web dashboard.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial
  Initialize HX711 (pins, calibration factor, tare)
  Connect ESP32-S3 to WiFi (MIT network in this build)
  Start WebServer on port 80
  Register handlers:
    "/"        → serve HTML+JS GUI page from PROGMEM
    "/metrics" → serve JSON with current grip and age

LOOP:
  Handle incoming HTTP clients
  Every 200 ms:
    If HX711 is ready:
      Read smoothed grip strength (kg) via get_units(3)
      Clamp negative values to zero
      Store in global gripStrength

AGE ESTIMATION HELPERS:
  ageFromGripMale(g):
    Clamp g to plausible range
    Compute age using inverted quadratic fit derived from normative data
  ageFromGripFemale(g):
    Same structure with female-specific parameters

HTTP /metrics ENDPOINT:
  Read "sex" query parameter (default "male")
  Compute ageEstimate = ageFromGripMale/ageFromGripFemale(gripStrength)
  Return JSON:
    {"grip": <kg>, "age": <years>}

CLIENT-SIDE GUI (HTML + JS):
  Render dark-themed dashboard with:
    - Sex toggle buttons (male/female)
    - Numeric grip strength (kg) and age
    - Scrolling Chart.js line plot of recent grip values
  Poll /metrics every 200 ms and update DOM + chart
Key Features
  • Embedded HTML/JS dashboard served directly from the ESP32-S3 using PROGMEM.
  • Real-time grip strength plot using Chart.js with ~120 recent samples.
  • Simple sex toggle that switches between male and female age-estimation curves.
  • JSON API at /metrics for future extensions (e.g., logging clients).
What You Need to Know
  • WiFi credentials: Update the ssid and password constants to match your network.
  • Normative model: The age equations are simplified fits inspired by the grip-strength trajectories reported in Syddall et al., PLOS ONE 2014 and are for educational visualization only, not clinical use.
  • Browser requirements: Any modern browser with JavaScript and network access can connect to the ESP32-S3’s IP address to view the dashboard.
  • Development log: The full iterative design of this sketch is captured in the ChatGPT transcript: Grip Strength Monitor Code Chat.
Download: loadcell_gui.ino

Invisible String Chain of Hearts

Code files for the Invisible String pulse oximeter interface system, providing real-time health monitoring through OLED display and WiFi web interface. See Week 11 PCB design documentation for hardware details.

OLED GUI for Pulse Oximeter (pulse_vo2_reads_fixing.ino)

Local OLED display interface showing real-time pulse oximeter readings including heart rate (BPM), blood oxygen saturation (SpO2), and raw IR/RED LED sensor values.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial communication
  Initialize I2C bus (SDA=5, SCL=6) at 400kHz
  Initialize MAX30102 sensor
  Configure sensor:
    Set LED mode to RED + IR
    Set ADC range to 16384
    Set sample rate to 100 Hz
    Set pulse width to 411 μs
    Set LED brightness to medium (0x3F)
  Initialize OLED display
  Clear and prepare display

LOOP:
  Read IR and RED LED values from sensor
  
  Heart Rate Detection:
    Check for heartbeat in IR signal using peak detection
    IF heartbeat detected:
      Calculate time since last beat
      Calculate BPM = 60 / (time_delta / 1000)
      Set beat flag for visual indicator
      Update last beat timestamp
  
  SpO2 Calculation (every 300ms):
    Add IR and RED values to circular buffer
    IF buffer has 50 samples:
      Calculate DC components (average)
      Calculate AC components (RMS)
      Calculate R ratio = (AC_RED/DC_RED) / (AC_IR/DC_IR)
      Estimate SpO2 = 110 - 25 * R
      Clamp SpO2 to 70-100% range
  
  Serial Output:
    Print IR, RED, BPM for Serial Plotter visualization
  
  OLED Display Update:
    Clear display buffer
    Display IR value (small text)
    Display RED value (small text)
    Display BPM value (large text, size 2)
    Display SpO2 percentage (small text)
    IF beat detected: Draw heartbeat indicator dot
    Update display hardware
  
  Delay 20ms (50 Hz update rate)
Key Features
  • Real-time heart rate detection using peak detection algorithm on IR signal
  • SpO2 calculation using ratio-of-ratios method with DC/AC component analysis
  • Circular buffer system for storing 50 samples of IR/RED data
  • Visual heartbeat indicator (flashing dot) when pulse detected
  • Dual output: OLED display and Serial Plotter for real-time waveform visualization
  • Optimized sensor configuration for reliable readings (100 Hz sample rate, medium brightness)
What You Need to Know
  • Sensor Placement: Finger must cover sensor completely; proper contact ensures accurate readings
  • I2C Address: MAX30102 uses address 0x57; verify with I2C scanner if sensor not detected
  • Ground Isolation: RD and IRD pins must be isolated from main ground plane to prevent power issues (see Week 11 PCB design)
  • SpO2 Accuracy: Calculation provides estimation; medical-grade accuracy requires calibration and FDA-approved algorithms
  • Buffer Size: 50-sample buffer provides balance between calculation accuracy and response time
  • Libraries Required: MAX30105 (SparkFun library), Adafruit_GFX, Adafruit_SSD1306, heartRate.h (beat detection)
  • Troubleshooting: If sensor not detected, check power isolation, I2C wiring, and sensor initialization order
Download: pulse_vo2_reads_fixing.ino

WiFi Readings GUI (pulse_gui.ino)

WiFi-enabled web interface providing remote access to pulse oximeter data through HTTP server with JSON API endpoint for real-time data updates.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial communication
  Initialize I2C bus
  Initialize MAX30102 sensor
  Configure sensor (LED mode, sample rate, pulse width)
  Initialize OLED display
  Initialize WiFi:
    Connect to network (SSID, password)
    Wait for connection
    Print IP address
  Initialize HTTP server:
    Route "/" → serve GUI HTML page
    Route "/gui" → serve GUI HTML page
    Route "/metrics" → serve JSON data
  Start web server

LOOP:
  Handle incoming HTTP client requests
  
  Read IR and RED values from sensor
  
  Heart Rate Calculation:
    Check for heartbeat in IR signal
    IF heartbeat detected:
      Calculate BPM from time delta
      Update global BPM variable
  
  SpO2 Calculation:
    Add IR/RED to circular buffer
    IF buffer full (50 samples):
      Calculate SpO2 using ratio-of-ratios
      Update global SpO2 variable
  
  Update global variables (g_ir, g_red, g_bpm, g_spo2)
  
  OLED Display Update:
    Display IR, RED, BPM, SpO2 values
    Update display hardware
Key Features
  • Dual interface: OLED display (local) and WiFi web interface (remote)
  • HTTP server with embedded HTML page stored in PROGMEM
  • JSON API endpoint (/metrics) for real-time data retrieval
  • Automatic WiFi connection with connection status feedback
  • IP address display for easy access
  • Simultaneous sensor reading and web server operation
  • Global variable system for data sharing between sensor reading and HTTP handlers
What You Need to Know
  • WiFi Configuration: Update SSID and password in code; for MIT network, use generated device password from wifi.mit.edu
  • Network Access: Web interface accessible only from devices on same WiFi network; IP address printed to Serial Monitor
  • HTML Storage: GUI HTML page stored in PROGMEM (program memory) to conserve RAM; use PROGMEM for large strings
  • Server Handling: Must call server.handleClient() frequently in loop() for responsive web interface
  • Data Refresh: Client-side JavaScript polls /metrics endpoint every 300ms for real-time updates
  • Power Consumption: WiFi significantly increases power draw compared to OLED-only mode; consider power management for battery operation
  • Libraries Required: WiFi, WebServer, MAX30105, Adafruit_SSD1306
Download: pulse_gui.ino

WiFi Plot GUI (pulse_gui_2.ino)

Enhanced WiFi web interface with real-time plotting capabilities using Chart.js library, displaying live line charts for BPM and SpO2 values with automatic scrolling and data management.

How the Code Works (Pseudocode)
SETUP:
  (Same as pulse_gui.ino)
  Initialize WiFi, sensor, OLED, HTTP server

LOOP:
  (Same as pulse_gui.ino)
  Handle HTTP requests, read sensor, calculate BPM/SpO2

GUI HTML PAGE (embedded in PROGMEM):
  Load Chart.js library from CDN
  Create two Chart.js line chart instances:
    - BPM chart (y-axis: 40-160 BPM)
    - SpO2 chart (y-axis: 70-100%)
  Initialize data arrays for each chart
  
  JavaScript Update Function (runs every 300ms):
    Fetch JSON data from /metrics endpoint
    Update numerical displays (BPM, SpO2, IR, RED)
    Add new BPM value to BPM data array
    Add new SpO2 value to SpO2 data array
    IF array length > maxPoints (100):
      Remove oldest value (shift)
    Update chart labels (array indices)
    Update chart datasets with new data
    Call chart.update() to refresh display
  
  Set interval to call update function every 300ms
Key Features
  • Real-time line chart visualization using Chart.js library
  • Dual chart display: BPM and SpO2 trends over time
  • Automatic data scrolling: maintains 100 most recent data points
  • Numerical displays alongside charts for precise values
  • Responsive design with dark theme for OLED-style aesthetic
  • Automatic chart scaling with fixed y-axis ranges for consistent visualization
  • CDN-based Chart.js loading for minimal memory footprint
What You Need to Know
  • Chart.js CDN: Library loaded from jsdelivr.net CDN; requires internet connection on client device
  • Data Management: Arrays limited to 100 points to prevent memory overflow; older data automatically discarded
  • Update Rate: 300ms refresh rate balances responsiveness with server load; adjust based on network conditions
  • Chart Configuration: Y-axis ranges fixed (BPM: 40-160, SpO2: 70-100) for consistent scaling; modify in JavaScript if needed
  • Browser Compatibility: Requires modern browser with JavaScript enabled; tested on Chrome, Firefox, Safari
  • Performance: Chart updates are lightweight; multiple simultaneous clients may impact ESP32 performance
  • Offline Operation: Charts won't load if client device lacks internet (Chart.js CDN unavailable); consider local hosting for offline use
Download: pulse_gui_2.ino

Reflections & Learnings

Key insights and learnings from working with interface and application programming.

Contributions

Acknowledgements and team roles for interface and application programming work.

Ethical AI Use

Transparent documentation of AI assistance used in this week's interface and application programming work.

This section documents all AI assistance used during Week 12 interface and application programming work. ChatGPT was used for code development, troubleshooting, and technical guidance. All transcripts are linked below for transparency.

Menu System with Modes

AI assistance for developing the button-based menu system with mode navigation (Menu, Camera, Sensors) using press pattern detection. The conversation covered button debouncing, press pattern recognition, mode state management, and OLED menu display design.

Related to: Part (a): Simple Button User Interface on OLED

View ChatGPT Transcript: Menu System with Modes

I2C Device Not Found

Troubleshooting session for I2C device detection issues with MAX30102 pulse oximeter sensor. The conversation addressed power isolation problems, I2C wiring verification, sensor initialization order, and ground plane isolation requirements for accurate sensor operation.

Related to: Part (b): Real-Time Graphical User Interface through OLED and WiFi

View ChatGPT Transcript: I2C Device Not Found

Hello World Code

Development assistance for creating the initial OLED "Hello World" test program. The conversation covered I2C initialization, OLED display library setup, text rendering, and basic display configuration for XIAO ESP32-S3 development board.

Related to: Part (b): Real-Time Graphical User Interface through OLED and WiFi (initial OLED test)

View ChatGPT Transcript: Hello World Code

MAX30102 Initialization Fix

Technical guidance for fixing MAX30102 pulse oximeter sensor initialization issues. The conversation addressed sensor configuration parameters, LED brightness settings, sample rate optimization, initialization sequence requirements, and troubleshooting sensor communication problems.

Related to: Part (b): Real-Time Graphical User Interface through OLED and WiFi (pulse oximeter readings)

View ChatGPT Transcript: MAX30102 Initialization Fix

Grip Strength Monitor Code Design

Code-focused assistance for designing and refining the WiFi grip strength monitor firmware. The conversation covered HX711 bring-up, load cell pin mapping, Serial Plotter debugging sketches, the ESP32-S3 HTTP server, the Chart.js dashboard, and the age-estimation helpers used in loadcell_simple.ino, loadcell_plot.ino, and loadcell_gui.ino.

Related to: Part (c): Real-Time GUI through Mechanical Gripper and WiFi and Grip Strength Monitor design files

View ChatGPT Transcript: Grip Strength Monitor Code

Grip Strength Calibration & Scaling

Calibration-focused assistance for mapping HX711 counts to kilograms and validating the grip strength readings. The discussion walked through using the Serial Plotter, collecting reference weights, tuning the calibration factor, and sanity-checking the age-estimation model derived from normative grip strength data.

Related to: Part (c): Real-Time GUI through Mechanical Gripper and WiFi calibration workflow and the Grip Strength Monitor sketches.

View ChatGPT Transcript: Grip Strength Calibration

Grip Strength Monitor – Cursor Transcript

Full Cursor AI transcript focused on organizing the grip strength monitor section: structuring Part (c), integrating design files, embedding images and videos, and aligning captions, external references, and the Ethical AI Use documentation for the load cell project.

Related to: Part (c): Real-Time GUI through Mechanical Gripper and WiFi, Grip Strength Monitor design files, and this Ethical AI Use section.

View HTML Transcript Download Markdown Transcript

Week 12 Project Documentation

Complete Cursor AI transcript for Week 12 interface and application programming project documentation. This comprehensive conversation covers the creation and population of the Week 12 HTML page, including Individual Assignment sections (button UI and WiFi GUI), Group Assignment tool comparisons, Design Files documentation with pseudocode, and Ethical AI Use section organization. The transcript demonstrates the collaborative process of building professional documentation with structured content, embedded media, and comprehensive code documentation.

Related to: Complete Week 12 documentation including Individual Assignment, Group Assignment, Design Files, and overall page structure

View HTML Transcript Download Markdown Transcript

Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License

``` ```html Week 13 · Wildcard Week
← Back to Home
[Profile Image Placeholder]

Week 13

Wildcard Week

Week Highlights

Key captures from the group and individual assignments with links to their sections.

Button User Interface on OLED

OLED button user interface menu system

Hello World on OLED

Hello World display on OLED for Invisible String project

Pulse Oximeter Readings

Pulse oximeter readings showing IR, RED, and BPM values

Wi-Fi GUI Readings

Wi-Fi web interface displaying real-time pulse oximeter readings

Wi-Fi GUI Plots

Wi-Fi web interface with real-time plotting of pulse oximeter data

OLED Video Stream Demo

Grip Strength Gripper

CAD rendering of the full grip strength device with base, handle, and load cell Photo of the fully assembled grip strength device with electronics and handle

Load Cell Calibration Plot

Serial Plotter screenshot showing load cell readings rising with grip force

Grip Strength WiFi GUI

Table of Contents

Course Content

Training & Documentation

Assignments & Projects

Wildcard Week

This week focuses on exploring digital fabrication processes not covered in previous assignments. We'll design and produce something using computer-aided design and manufacturing, documenting requirements and including everything necessary for reproduction. This week also includes reflection on the impact and purpose of making (almost) anything.

Exploring new digital fabrication processes
Designing and producing with CAD/CAM
Understanding the impact and purpose of fabrication labs

This Week's Goals

  • Explore New Processes
    Design and produce something with a digital process not covered in other assignments
  • Complete Documentation
    Document requirements and include everything necessary to reproduce the project
  • Reflect on Impact
    Understand the purpose and impact of fabrication labs and making

Assignments

  • Group Assignment
    Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment
  • Individual Assignment
    Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment, documenting the requirements that your assignment meets, and including everything necessary to reproduce it

Tools & Materials

  • ESP32-S3 Development Boards
  • OLED Displays (SSD1306)
  • MAX30102 Pulse Oximeter Sensor
  • Buttons & User Input Devices
  • Interface Programming Frameworks

Training Documentation

Training materials and documentation for interface and application programming.

No recitation this week.

Useful Documentation

Essential resources for interface and application programming.

Class Page

Interface and Application Programming - MIT Academy

Comprehensive resource covering interface design, application programming, GUI frameworks, embedded UI development, web interfaces for embedded systems, and user interaction patterns. Includes detailed tutorials, code examples, and implementation guides for various interface programming tools and frameworks.

Key Topics

  • Interface Design: User experience principles, interaction patterns, feedback mechanisms
  • Embedded UI: OLED displays, LCD interfaces, character displays
  • Web Interfaces: HTTP servers, REST APIs, WebSockets, real-time data visualization
  • Application Frameworks: GUI toolkits, web frameworks, mobile apps
  • User Input: Buttons, touch interfaces, gesture recognition, voice commands

Additional References

Individual Assignment: Interface & Application Programming

Write an application that interfaces a user with an input &/or output device that you made. This assignment demonstrates three interface applications: (a) a simple button user interface on OLED, (b) a real-time graphical user interface through OLED and Wi-Fi for pulse oximeter readings, and (c) a Wi-Fi grip strength monitor with a mechanical gripper and age-estimation web dashboard.

Part (a): Simple Button User Interface on OLED

A mode-based user interface system that interfaces users with multiple input and output devices through a simple button press interface. The system provides visual feedback on an OLED display and enables navigation between different modes (Menu, Camera, Sensors) using button press patterns. Users interact by pressing a button multiple times to select modes, with visual confirmation displayed on the OLED screen.

Interface Design

The interface uses a mode-based navigation system where button presses trigger mode changes. A single press enters Camera mode, two presses enter Sensors mode, three presses return to Menu, and holding the button activates a flashlight function. The OLED display shows the current menu state and provides clear visual feedback for each mode transition. See Ethical AI Use: Menu System with Modes for AI-assisted development details.

OLED button user interface menu system displaying mode selection options
OLED button user interface menuMenu screen showing available modes: Camera, Sensors, and Menu navigation options with button press instructions.
Button UI demonstrationVideo showing button press interactions navigating through different modes on the OLED display.
First video stream on OLEDInitial camera feed streaming to OLED display using dithering algorithm for monochrome conversion, demonstrating real-time video output interface.
Download Design Files
  • outputs.ino — Button user interface code with mode system
  • camera_pins.h — Camera pin definitions header file
  • outputs.zip — Complete project archive including all dependencies

Part (b): Real-Time Graphical User Interface through OLED and WiFi

A dual-interface health monitoring system that interfaces users with a MAX30102 pulse oximeter sensor through both an OLED display and a WiFi-enabled web interface. The system provides real-time visualization of heart rate (BPM), blood oxygen saturation (SpO2), and raw sensor data (IR and RED LED readings) through multiple output channels. Users can view data locally on the OLED display or remotely via a web browser accessing the ESP32-S3's built-in HTTP server. See Ethical AI Use: I2C Device Not Found for troubleshooting documentation.

Interface Design

The system provides dual-interface access: a local OLED display shows real-time sensor readings (IR, RED, BPM, SpO2) with visual heartbeat indicators, while a WiFi web interface provides comprehensive data visualization including numerical displays and real-time plotting charts. The web interface uses Chart.js for dynamic graph generation and automatically refreshes every 300ms to maintain real-time data updates. Both interfaces run simultaneously, enabling local monitoring and remote access.

Hello World on OLED

Initial OLED display test showing successful I2C communication and display initialization. See Ethical AI Use: Hello World Code for development details.

Hello World display on OLED for Invisible String project showing successful display initialization
Hello World on OLEDInitial OLED test confirming I2C communication and display functionality before implementing sensor interfaces.
Pulse Oximeter Readings on OLED

Real-time pulse oximeter data displayed on OLED showing IR and RED LED readings, heart rate (BPM), and blood oxygen saturation (SpO2) percentage. A heartbeat indicator flashes when a pulse is detected. See Ethical AI Use: MAX30102 Initialization Fix for sensor setup documentation.

Pulse oximeter readings on OLED displaying IR, RED, BPM, and SpO2 values
OLED sensor readings displayReal-time pulse oximeter data showing IR and RED LED values, heart rate (BPM), and blood oxygen saturation (SpO2) with heartbeat indicator.
BPM and SpO2 demonstrationVideo showing real-time heart rate and blood oxygen saturation measurements updating on OLED display with sensor interaction.
Pulse Oximeter Readings on WiFi GUI

WiFi web interface providing remote access to pulse oximeter data through a responsive HTML dashboard. The interface displays real-time numerical values for BPM, SpO2, IR, and RED readings with automatic data refresh. The web server runs on the ESP32-S3, allowing access from any device on the same WiFi network.

WiFi web interface displaying real-time pulse oximeter readings including BPM, SpO2, IR, and RED values
WiFi GUI readings dashboardRemote web interface showing real-time pulse oximeter data accessible from any device on the WiFi network, displaying BPM, SpO2, IR, and RED values with automatic updates.
Pulse Oximeter Plots on WiFi GUI

Enhanced WiFi web interface with real-time plotting capabilities using Chart.js library. The interface displays live line charts for BPM and SpO2 values, showing trends over time with automatic scrolling and data point management. This visualization enables users to observe patterns in heart rate and blood oxygen levels during monitoring sessions.

Serial monitor output showing sensor readings rising on touch interaction
Serial monitor sensor responseSerial output demonstrating sensor readings increase when finger is placed on MAX30102 sensor, showing IR and RED LED response to touch.
WiFi web interface with real-time plotting of BPM and SpO2 data using Chart.js
WiFi GUI with plotting chartsEnhanced web interface displaying real-time line charts for BPM and SpO2 values, showing trends over time with automatic data refresh and chart scrolling.

I2C Device Detection

Successful I2C device detection after fixing power isolation issues. The system now correctly identifies the OLED display at address 0x3C and the MAX30102 sensor at address 0x57. Initial troubleshooting required isolating the RD (red LED) and IRD (infrared LED) ground terminals from the general ground plane to prevent power issues and enable proper sensor operation. 

20:04:48.612 -> Scanning...
20:04:48.644 -> I2C device found at address 0x3C  !
20:04:48.644 -> I2C device found at address 0x57  !
20:04:48.644 -> done
Download Design Files

Part (c): Real-Time GUI through Mechanical Gripper and WiFi

A Wi-Fi-connected grip strength meter that interfaces a user with a mechanical hand gripper, an 80 kg load cell, and an HX711 amplifier. The ESP32-S3 continuously measures grip force, streams it to a web dashboard, and uses a published relationship between handgrip strength and age to display an estimated “physiological age” in real time. The design is inspired by the open-source grip strength meter from NeuroTech Hub at WashU and the associated PLOS ONE paper on grip strength and age trajectories (Syddall et al., 2014), adapted to my load cell and handle geometry.

Mechanically, a custom 3D-printed gripper clamps around a CZL601-type 80 kg bar load cell (sourced from Amazon 80 kg load cell). I imported a 100 kg load cell CAD from GrabCAD, checked the mounting dimensions against the CZL601AC datasheet (online, download), and confirmed that the hole spacing and footprint match the commercial part used here.

Mechanical Design and Fabrication

CAD model of the 3D-printed grip strength base and load cell mounting region
Grip strength base CADTop view of the grip strength base showing the bar load cell pocket, mounting bosses, and handle interface.
Side view CAD of the hand gripper and load cell assembly
Side view of gripper assemblySide profile showing how the fixed base, moving handle, and load cell align along the force axis of the bar sensor.
Full CAD view of the grip strength device with base and handle
Full grip strength assemblyComplete CAD of the base, handle, and load cell, sized for comfortable adult hand placement and full-finger contact.
Close-up of mounting holes and clearances around the load cell in CAD
Load cell mounting holesDetail of the M6 clearance and counterbore geometry used to capture the load cell without constraining bending.
Perspective CAD view of the gripper handle and base
Handle ergonomicsPerspective view of the curved handle designed to distribute pressure across the palm and fingers during maximal grip.
Photo of drilled clearance hole aligned to the printed pilot in the base
Clearance hole verificationPrinted pilot holes used as drill guides to match the metric mounting dimensions from the CZL601AC datasheet.
Photo of the fully printed grip strength device before drilling and assembly
Fresh off the printer3D-printed base and handle components in PLA prior to post-processing and hardware installation.
Printed part clamped for drilling load cell mounting holes
Workholding for accurate drillingThe printed base clamped to the drill press table so the pilot features guide the final clearance holes into the load cell.
Drilling practiceTraining cuts on scrap material to dial in drill press settings and avoid cracking the printed base during final holes.
Final load cell holesDrilling the final M6 clearance holes through the printed base, constrained by the pilot features to preserve alignment.

Electronics and Calibration

Electronics assembly with HX711 breakout, ESP32-S3, and load cell wiring
Electronics stack-upHX711 amplifier breakout from Amazon wired to the ESP32-S3 and 80 kg load cell with short, twisted signal pairs for noise reduction.
Fully assembled grip strength device with load cell, electronics, and handle
Assembled grip strength meterCompleted mechanical and electrical assembly ready for calibration and software bring-up.
Serial Plotter view of load cell readings increasing with grip force
Serial Plotter calibration tracesRaw HX711 output converted to kilograms and visualized in the Arduino Serial Plotter while applying known weights and grip forces.
Web GUI showing grip strength value, estimated age, and scrolling chart
Wi-Fi grip strength dashboardBrowser-based GUI with live grip strength (kg), estimated age, and a Chart.js time series plot of recent squeezes.

Model Used for Age Estimation

The age-estimation logic in the firmware is based on the non-linear, sex-specific grip-strength trajectories reported in Dodds et al., 2014 (PLOS ONE). As shown in Figure 1 of that paper, grip strength rises rapidly through adolescence, peaks around ages 30–40, and then declines non-linearly with age, with different magnitudes for males and females.

Reference grip strength trajectories over the life course from Dodds et al., PLOS ONE 2014
Reference trajectories (Figure 1)Age-dependent grip strength curves for males and females from Dodds et al., 2014, used as the qualitative target for the embedded model.
Simplified quadratic grip strength model fitted to reference data
Quadratic approximation (Table 2-inspired)Simplified male and female trajectories using peak strengths and curvatures chosen to approximate the summary values reported in Table 2 of Dodds et al., 2014.

To reproduce this shape efficiently on the ESP32, the firmware uses inverted quadratic approximations centered at age 35, consistent with the observed peak in the PLOS ONE data. In the forward direction, grip strength is approximated as:

Males: Grip(age) ≈ 52 − 0.0089·(age − 35)2
Females: Grip(age) ≈ 32 − 0.0059·(age − 35)2

On the device, this relationship is analytically inverted so that the measured grip strength can be mapped back to an estimated age:

age = 35 + √((a − Grip)/b), where a is the peak strength (52 kg for males, 32 kg for females) and b is the curvature (0.0089 for males, 0.0059 for females). The firmware clamps grip strength to physiologically meaningful ranges before applying this formula so the square root remains well-defined. 

float ageFromGripMale(float g) {
  float a = 52.0f, b = 0.0089f;
  if (g > a) g = a;
  if (g < 5) g = 5;
  return 35.0f + sqrtf((a - g) / b);
}

float ageFromGripFemale(float g) {
  float a = 32.0f, b = 0.0059f;
  if (g > a) g = a;
  if (g < 4) g = 4;
  return 35.0f + sqrtf((a - g) / b);
}

For full methodological details and original tables/figures, see the open-access paper: Dodds et al., 2014, PLOS ONE (download local PDF). The implementation here is an educational approximation and not intended for clinical or diagnostic use.

End-to-end live demoReal-time demonstration of squeezing the mechanical gripper and watching the Wi-Fi dashboard update grip strength and estimated age on a laptop.

Related Design, Code, and Calibration Resources

User Interface Comparison

Summary of how each interface application connects users with input and output devices.

Application How It Interfaces with the User Input Device(s) Output Device(s)
(a) Button User Interface Button press patterns (single, double, triple press, hold) provide mode selection input. OLED display shows current menu state and mode options. Users receive immediate visual feedback for each interaction. Button (GPIO pin 4) OLED Display (SSD1306, I²C 0x3C)
LED (GPIO pin 3, flashlight mode)
(b) Real-Time GUI (OLED & WiFi) Physical finger placement on MAX30102 sensor provides input. OLED displays real-time sensor data locally. WiFi web interface enables remote monitoring with numerical displays and live plotting charts accessible from any web browser. MAX30102 Pulse Oximeter Sensor (I²C 0x57) OLED Display (SSD1306, I²C 0x3C)
WiFi Web Interface (HTTP Server with Chart.js visualization)
(c) Grip Strength GUI (Load Cell & WiFi) Users squeeze a mechanical hand gripper that transfers force into an 80 kg bar load cell. The ESP32-S3 measures grip strength through the HX711 amplifier and streams results to a WiFi web dashboard that displays live grip force and an estimated physiological age in real time. Mechanical gripper linked to 80 kg load cell (CZL601-type)
HX711 load cell amplifier		 WiFi Web Interface (HTTP Server with Chart.js visualization)
Optional Serial Plotter (for calibration traces)

Group Assignment: Compare as Many Tool Options as Possible

Compare as many tool options as possible for interface and application programming.

General Comparison: Interface & Application Programming Tools

Comprehensive comparison of interface and application programming tools available for embedded systems and IoT development. This analysis covers tools from the MIT Academy Interface & Application Programming class page, evaluating their capabilities, use cases, and trade-offs for different application scenarios.

Embedded Display Interfaces

Tool/Framework Description Pros Cons Best For
OLED (SSD1306) Monochrome OLED displays via I²C Low power, high contrast, simple I²C interface, pixel-level control Limited resolution (128x64), monochrome only, small display size Status displays, sensor readouts, simple menus, embedded dashboards
LCD Character Displays Character-based LCD displays (16x2, 20x4) Simple API, readable in sunlight, low cost Limited to text/characters, no graphics, requires backlight power Text-only interfaces, status messages, debugging output
TFT Color Displays Full-color TFT LCD displays Color graphics, touch support, high resolution High power consumption, complex drivers, larger footprint Rich GUIs, image display, interactive touch interfaces

Web-Based Interfaces

Tool/Framework Description Pros Cons Best For
HTTP Server (ESP32) Built-in HTTP server on ESP32 for web interfaces Remote access, cross-platform (any browser), no app installation, real-time updates Requires WiFi, network dependency, limited to local network without port forwarding Remote monitoring, data visualization, control panels, sensor dashboards
WebSockets Real-time bidirectional communication Low latency, bidirectional, efficient for frequent updates More complex than HTTP, requires persistent connection Real-time streaming, interactive controls, live data feeds
Chart.js JavaScript charting library for web interfaces Beautiful charts, interactive, responsive, easy integration Requires JavaScript, CDN dependency or local hosting Data visualization, time series plots, sensor monitoring dashboards

Mobile & Native App Frameworks

Tool/Framework Description Pros Cons Best For
React Native Cross-platform mobile app framework Cross-platform (iOS/Android), native performance, large ecosystem Complex setup, requires mobile development knowledge Full-featured mobile apps, production deployments
Flutter Google's UI toolkit for cross-platform apps Single codebase, high performance, customizable UI Dart language, larger app size, learning curve Custom mobile interfaces, platform-specific designs
Progressive Web Apps (PWA) Web apps with native-like features No app store, cross-platform, offline capability Limited native API access, browser dependency Web-based mobile interfaces, simple deployment

Specific Comparison: Tools Used in Individual Assignment

Detailed comparison of the specific interface programming tools implemented in this week's individual assignment, evaluating their performance, ease of use, and suitability for embedded health monitoring applications.

OLED Display Interface (Adafruit SSD1306)

Aspect Evaluation
Ease of Implementation Simple I²C interface, well-documented Adafruit library, minimal wiring (SDA, SCL, power, ground)
Display Quality High contrast monochrome display, crisp text rendering, suitable for sensor data visualization
Power Consumption Very low power draw, ideal for battery-powered applications
Limitations 128x64 pixel resolution limits detail, monochrome only, small physical size (0.96" typical)
Best Use Cases Local sensor readouts, menu systems, status indicators, simple data displays

WiFi Web Interface (ESP32 HTTP Server + Chart.js)

Aspect Evaluation
Ease of Implementation ESP32 WebServer library provides straightforward HTTP server, Chart.js CDN integration requires minimal setup
Remote Access Accessible from any device on WiFi network (phone, tablet, computer), no app installation required
Visualization Capabilities Chart.js enables rich data visualization with real-time plotting, smooth animations, and interactive features
Real-Time Updates JSON API endpoint provides efficient data transfer, 300ms refresh rate maintains responsive feel
Limitations Requires WiFi network, limited to local network without additional configuration, power consumption higher than OLED alone
Best Use Cases Remote monitoring, data logging visualization, multi-user access, professional dashboards

Button Input Interface

Aspect Evaluation
Implementation Approach Digital GPIO reading with debouncing, press pattern detection (single/double/triple/hold) enables mode navigation
User Experience Intuitive press patterns, immediate visual feedback on OLED, no complex UI navigation required
Reliability Hardware debouncing with INPUT_PULLUP, timeout-based pattern recognition prevents accidental triggers
Limitations Limited to single button interaction, pattern learning required, less flexible than touchscreen interfaces
Best Use Cases Simple mode selection, menu navigation, embedded system controls, low-cost input solutions

Comparison Summary

The combination of OLED display and WiFi web interface provides complementary benefits: OLED offers immediate local feedback with minimal latency and power consumption, while the WiFi interface enables rich visualization and remote access. The button-based input provides an intuitive, low-cost navigation method suitable for embedded systems. Together, these tools create a robust interface system that supports both local and remote interaction with sensor data.

Design Files

Design files and code documentation for interface and application programming projects.

ESP32-S3 Development Board and Pinouts

Code files for ESP32-S3 development board interfaces including I2C scanning, OLED display control, and button-based user interface systems. See Week 4 documentation for board design and Week 8 documentation for pinout configurations.

I2C Scanner (i2cscan_generic.ino)

Utility code for scanning and detecting I2C devices on the bus, essential for troubleshooting connection issues.

How the Code Works (Pseudocode)
SETUP:
  Initialize I2C bus
  Initialize Serial communication
  Print "I2C Scanner" message

LOOP:
  Print "Scanning..." message
  Initialize device counter to 0
  
  FOR each address from 1 to 126:
    Begin I2C transmission to address
    Check transmission result
    
    IF transmission successful (error == 0):
      Print device found at address (hex format)
      Increment device counter
    ELSE IF unknown error (error == 4):
      Print unknown error at address
    
  IF no devices found:
    Print "No I2C devices found"
  ELSE:
    Print "done"
  
  Wait 5 seconds before next scan
Key Features
  • Scans all 127 possible I2C addresses (0x01-0x7E)
  • Detects and reports connected devices with hex address format
  • Handles multiple error conditions (device not found, unknown errors)
  • Continuous scanning mode with 5-second intervals
  • Compatible with any I2C bus configuration (Wire, Wire1, etc.)
What You Need to Know
  • I2C Address Range: Valid addresses are 0x08-0x77 (8-119 decimal); addresses 0x00-0x07 and 0x78-0x7F are reserved
  • Common Addresses: OLED displays typically use 0x3C or 0x3D; sensors vary (MAX30102 uses 0x57)
  • Troubleshooting: If no devices found, check wiring (SDA, SCL, power, ground), verify pull-up resistors, confirm device power
  • Usage: Run this before connecting other devices to verify I2C bus is working correctly
Download: i2cscan_generic.ino

Hello World OLED Display (hello_world.ino)

Basic OLED display test code that initializes the display and shows "Hello World" text, confirming I2C communication and display functionality.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial communication at 115200 baud
  Wait 500ms for Serial to stabilize
  
  Initialize I2C bus with SDA pin 5, SCL pin 6
  Print "Starting..." message
  
  Attempt to initialize OLED display:
    IF initialization fails:
      Print "OLED not found" error
      Enter infinite loop (halt)
  
  Clear display buffer
  Set text size to 2
  Set text color to white
  Set cursor position to (0, 20)
  Print "Hello" line
  Print "World!" line
  Update display (send buffer to hardware)

LOOP:
  Empty (runs once, then waits)
Key Features
  • Simple OLED initialization and text display
  • Custom I2C pin configuration for XIAO ESP32-S3 (SDA=5, SCL=6)
  • Error handling with infinite loop if display not found
  • Text size and cursor positioning for centered display
  • One-time display update (no loop refresh needed for static text)
What You Need to Know
  • I2C Pin Configuration: XIAO ESP32-S3 uses pins 5 (SDA) and 6 (SCL) by default; verify your board's pinout
  • Display Address: SSD1306 OLED typically uses address 0x3C; some variants use 0x3D
  • Display Update: Must call display.display() to send buffer to hardware; drawing functions only modify buffer
  • Testing: Use this as first test after connecting OLED to verify wiring and I2C communication before adding complex features
  • Libraries Required: Adafruit_GFX, Adafruit_SSD1306, Wire
Download: hello_world.ino

Button User Interface (outputs.ino)

Mode-based navigation system using button press patterns (single, double, triple, hold) to control multiple output devices including OLED display, camera, sensors, and LED flashlight.

How the Code Works (Pseudocode)
SETUP:
  Initialize OLED display
  Initialize camera module
  Initialize sensors (MPU6050, HX711)
  Initialize button pin (INPUT_PULLUP)
  Initialize LED pin (OUTPUT)
  Set current mode to MENU
  Display menu screen

LOOP:
  Read button state
  
  IF button pressed:
    Record press start time
    Start press detection timer
  
  IF button released:
    Calculate press duration
    IF duration > HOLD_THRESHOLD:
      Activate flashlight mode
    ELSE:
      Increment press count
      Reset press timeout timer
  
  IF press timeout exceeded:
    Process accumulated press count:
      IF press count == 1: Switch to CAMERA mode
      IF press count == 2: Switch to SENSORS mode
      IF press count == 3: Switch to MENU mode
    Reset press count
  
  IF current mode == MENU:
    Display menu screen (button instructions)
  
  IF current mode == CAMERA:
    Capture camera frame
    Process image with dithering algorithm
    Display on OLED
    Run Edge Impulse inference (optional)
    Overlay results on display
  
  IF current mode == SENSORS:
    Read accelerometer/gyroscope data
    Read load cell data
    Display sensor readings on OLED
  
  Update display
Key Features
  • Press pattern detection: single (1x), double (2x), triple (3x), and hold
  • Mode-based navigation system (Menu, Camera, Sensors)
  • Button debouncing with timeout-based pattern recognition
  • Floyd-Steinberg dithering for camera-to-OLED video display
  • Edge Impulse AI inference integration for face detection
  • Multi-sensor integration (MPU6050 accelerometer/gyro, HX711 load cell)
  • Flashlight mode activated by button hold
What You Need to Know
  • Button Wiring: Use INPUT_PULLUP mode (button connects pin to GND when pressed, internal pull-up to 3.3V)
  • Press Detection: Press count is accumulated until timeout (1 second); longer timeout allows slower multiple presses
  • Mode Switching: Each mode has distinct display update logic; ensure proper initialization in setup()
  • Camera Performance: Video streaming to OLED requires significant processing; frame rate depends on resolution and dithering complexity
  • Dependencies: Requires camera_pins.h header file with XIAO ESP32-S3 camera pin definitions; see Ethical AI Use for development details
  • Sensor Conflicts: Code uses preprocessor directives to resolve sensor_t type conflict between ESP32 camera and Adafruit MPU6050 libraries
Download: outputs.ino | camera_pins.h | outputs.zip (complete project)

Grip Strength Monitor (Load Cell + WiFi GUI)

Design files and firmware for a Wi-Fi-enabled grip strength meter built around an 80 kg bar load cell, HX711 amplifier, and ESP32-S3. The mechanical design was informed by the open-source grip strength meter from NeuroTech Hub and validated against the CZL601AC bar load cell datasheet (online, download).

Mechanical Design Files (3D-Printed Components)

  • Base.3mf — main chassis that captures the bar load cell and anchors the fixed side of the gripper.
  • Case.3mf — protective enclosure for the ESP32-S3 and HX711 amplifier with cable strain relief.
  • Handle.3mf — curved grip handle that transfers hand force into the free end of the load cell.
  • Calibration Print.3mf — small test piece used to verify hole diameters and load cell clearances before printing the full assembly.

All parts were printed in PLA with high infill in the load paths to minimize creep and flex during repeated maximal grip trials.

Basic HX711 Reader (loadcell_simple.ino)

Minimal firmware to bring up the HX711 amplifier and read calibrated weight values over Serial for debugging and calibration.

How the Code Works (Pseudocode)
SETUP:
  Configure HX711 data and clock pins (DT=A1, SCK=A0)
  Initialize Serial at 115200 baud
  Begin HX711 with DT/SCK pins
  Set calibration factor (grams per ADC unit)
  Tare the scale so current load is zero

LOOP (every 200 ms):
  If HX711 is ready:
    Read averaged weight using get_units(4)
    Print "weight:<value>" to Serial for Serial Plotter
  Else:
    Print "HX711 not ready" for troubleshooting
Key Features
  • Simple initialization of the HX711 on analog pins A0/A1.
  • Configurable calibration factor for mapping counts to grams or kilograms.
  • Timed reads (200 ms) to keep Serial output manageable and Plotter-friendly.
  • Graceful handling of HX711 not-ready states.
What You Need to Know
  • Use for initial bring-up: Run this first when wiring the HX711 and load cell to confirm clean, stable readings.
  • Calibration factor: Determined experimentally by hanging known weights and adjusting until readings match; see the calibration notes in Calibration Chat.
  • Serial Plotter: The weight:<value> format is convenient for quickly visualizing changes while squeezing the handle.
Download: loadcell_simple.ino

Serial Plotter-Friendly Reader (loadcell_plot.ino)

Refined HX711 reader tuned for the Arduino Serial Plotter: it outputs a single numeric value per line for clean plotting of grip strength over time.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial at 115200 baud
  Initialize HX711 on DT=A1, SCK=A0
  Set calibration factor
  Tare the scale
  Optionally print debug messages when DEBUG=1

LOOP (every 200 ms):
  If HX711 is ready:
    Read filtered weight with get_units(4)
    Optionally print labeled debug text
    Print only the numeric weight to Serial for the Plotter
  Else:
    Optionally print "not ready" debug text
    Print 0 so the plotted line continues gracefully
Key Features
  • DEBUG toggle: Compile-time switch to enable/disable human-readable logs without breaking the Serial Plotter format.
  • Clean “one number per line” output for multi-trial grip testing in the Serial Plotter.
  • Automatic zero output when the HX711 is not ready to keep the time axis continuous.
  • Shared pinout and calibration approach with loadcell_simple.ino for easy swapping.
What You Need to Know
  • Use this sketch to tune calibration and visualize grip curves without any GUI overhead.
  • When collecting data for analysis, keep DEBUG set to 0 so the output is a pure numeric stream.
  • The sample interval (200 ms) gives a smooth trace while keeping file sizes reasonable for multi-second squeezes.
Download: loadcell_plot.ino

WiFi Grip Strength GUI (loadcell_gui.ino)

Full application firmware that exposes grip strength and an estimated age over Wi-Fi using an HTTP server and a Chart.js web dashboard.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial
  Initialize HX711 (pins, calibration factor, tare)
  Connect ESP32-S3 to WiFi (MIT network in this build)
  Start WebServer on port 80
  Register handlers:
    "/"        → serve HTML+JS GUI page from PROGMEM
    "/metrics" → serve JSON with current grip and age

LOOP:
  Handle incoming HTTP clients
  Every 200 ms:
    If HX711 is ready:
      Read smoothed grip strength (kg) via get_units(3)
      Clamp negative values to zero
      Store in global gripStrength

AGE ESTIMATION HELPERS:
  ageFromGripMale(g):
    Clamp g to plausible range
    Compute age using inverted quadratic fit derived from normative data
  ageFromGripFemale(g):
    Same structure with female-specific parameters

HTTP /metrics ENDPOINT:
  Read "sex" query parameter (default "male")
  Compute ageEstimate = ageFromGripMale/ageFromGripFemale(gripStrength)
  Return JSON:
    {"grip": <kg>, "age": <years>}

CLIENT-SIDE GUI (HTML + JS):
  Render dark-themed dashboard with:
    - Sex toggle buttons (male/female)
    - Numeric grip strength (kg) and age
    - Scrolling Chart.js line plot of recent grip values
  Poll /metrics every 200 ms and update DOM + chart
Key Features
  • Embedded HTML/JS dashboard served directly from the ESP32-S3 using PROGMEM.
  • Real-time grip strength plot using Chart.js with ~120 recent samples.
  • Simple sex toggle that switches between male and female age-estimation curves.
  • JSON API at /metrics for future extensions (e.g., logging clients).
What You Need to Know
  • WiFi credentials: Update the ssid and password constants to match your network.
  • Normative model: The age equations are simplified fits inspired by the grip-strength trajectories reported in Syddall et al., PLOS ONE 2014 and are for educational visualization only, not clinical use.
  • Browser requirements: Any modern browser with JavaScript and network access can connect to the ESP32-S3’s IP address to view the dashboard.
  • Development log: The full iterative design of this sketch is captured in the ChatGPT transcript: Grip Strength Monitor Code Chat.
Download: loadcell_gui.ino

Invisible String Chain of Hearts

Code files for the Invisible String pulse oximeter interface system, providing real-time health monitoring through OLED display and WiFi web interface. See Week 11 PCB design documentation for hardware details.

OLED GUI for Pulse Oximeter (pulse_vo2_reads_fixing.ino)

Local OLED display interface showing real-time pulse oximeter readings including heart rate (BPM), blood oxygen saturation (SpO2), and raw IR/RED LED sensor values.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial communication
  Initialize I2C bus (SDA=5, SCL=6) at 400kHz
  Initialize MAX30102 sensor
  Configure sensor:
    Set LED mode to RED + IR
    Set ADC range to 16384
    Set sample rate to 100 Hz
    Set pulse width to 411 μs
    Set LED brightness to medium (0x3F)
  Initialize OLED display
  Clear and prepare display

LOOP:
  Read IR and RED LED values from sensor
  
  Heart Rate Detection:
    Check for heartbeat in IR signal using peak detection
    IF heartbeat detected:
      Calculate time since last beat
      Calculate BPM = 60 / (time_delta / 1000)
      Set beat flag for visual indicator
      Update last beat timestamp
  
  SpO2 Calculation (every 300ms):
    Add IR and RED values to circular buffer
    IF buffer has 50 samples:
      Calculate DC components (average)
      Calculate AC components (RMS)
      Calculate R ratio = (AC_RED/DC_RED) / (AC_IR/DC_IR)
      Estimate SpO2 = 110 - 25 * R
      Clamp SpO2 to 70-100% range
  
  Serial Output:
    Print IR, RED, BPM for Serial Plotter visualization
  
  OLED Display Update:
    Clear display buffer
    Display IR value (small text)
    Display RED value (small text)
    Display BPM value (large text, size 2)
    Display SpO2 percentage (small text)
    IF beat detected: Draw heartbeat indicator dot
    Update display hardware
  
  Delay 20ms (50 Hz update rate)
Key Features
  • Real-time heart rate detection using peak detection algorithm on IR signal
  • SpO2 calculation using ratio-of-ratios method with DC/AC component analysis
  • Circular buffer system for storing 50 samples of IR/RED data
  • Visual heartbeat indicator (flashing dot) when pulse detected
  • Dual output: OLED display and Serial Plotter for real-time waveform visualization
  • Optimized sensor configuration for reliable readings (100 Hz sample rate, medium brightness)
What You Need to Know
  • Sensor Placement: Finger must cover sensor completely; proper contact ensures accurate readings
  • I2C Address: MAX30102 uses address 0x57; verify with I2C scanner if sensor not detected
  • Ground Isolation: RD and IRD pins must be isolated from main ground plane to prevent power issues (see Week 11 PCB design)
  • SpO2 Accuracy: Calculation provides estimation; medical-grade accuracy requires calibration and FDA-approved algorithms
  • Buffer Size: 50-sample buffer provides balance between calculation accuracy and response time
  • Libraries Required: MAX30105 (SparkFun library), Adafruit_GFX, Adafruit_SSD1306, heartRate.h (beat detection)
  • Troubleshooting: If sensor not detected, check power isolation, I2C wiring, and sensor initialization order
Download: pulse_vo2_reads_fixing.ino

WiFi Readings GUI (pulse_gui.ino)

WiFi-enabled web interface providing remote access to pulse oximeter data through HTTP server with JSON API endpoint for real-time data updates.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial communication
  Initialize I2C bus
  Initialize MAX30102 sensor
  Configure sensor (LED mode, sample rate, pulse width)
  Initialize OLED display
  Initialize WiFi:
    Connect to network (SSID, password)
    Wait for connection
    Print IP address
  Initialize HTTP server:
    Route "/" → serve GUI HTML page
    Route "/gui" → serve GUI HTML page
    Route "/metrics" → serve JSON data
  Start web server

LOOP:
  Handle incoming HTTP client requests
  
  Read IR and RED values from sensor
  
  Heart Rate Calculation:
    Check for heartbeat in IR signal
    IF heartbeat detected:
      Calculate BPM from time delta
      Update global BPM variable
  
  SpO2 Calculation:
    Add IR/RED to circular buffer
    IF buffer full (50 samples):
      Calculate SpO2 using ratio-of-ratios
      Update global SpO2 variable
  
  Update global variables (g_ir, g_red, g_bpm, g_spo2)
  
  OLED Display Update:
    Display IR, RED, BPM, SpO2 values
    Update display hardware
Key Features
  • Dual interface: OLED display (local) and WiFi web interface (remote)
  • HTTP server with embedded HTML page stored in PROGMEM
  • JSON API endpoint (/metrics) for real-time data retrieval
  • Automatic WiFi connection with connection status feedback
  • IP address display for easy access
  • Simultaneous sensor reading and web server operation
  • Global variable system for data sharing between sensor reading and HTTP handlers
What You Need to Know
  • WiFi Configuration: Update SSID and password in code; for MIT network, use generated device password from wifi.mit.edu
  • Network Access: Web interface accessible only from devices on same WiFi network; IP address printed to Serial Monitor
  • HTML Storage: GUI HTML page stored in PROGMEM (program memory) to conserve RAM; use PROGMEM for large strings
  • Server Handling: Must call server.handleClient() frequently in loop() for responsive web interface
  • Data Refresh: Client-side JavaScript polls /metrics endpoint every 300ms for real-time updates
  • Power Consumption: WiFi significantly increases power draw compared to OLED-only mode; consider power management for battery operation
  • Libraries Required: WiFi, WebServer, MAX30105, Adafruit_SSD1306
Download: pulse_gui.ino

WiFi Plot GUI (pulse_gui_2.ino)

Enhanced WiFi web interface with real-time plotting capabilities using Chart.js library, displaying live line charts for BPM and SpO2 values with automatic scrolling and data management.

How the Code Works (Pseudocode)
SETUP:
  (Same as pulse_gui.ino)
  Initialize WiFi, sensor, OLED, HTTP server

LOOP:
  (Same as pulse_gui.ino)
  Handle HTTP requests, read sensor, calculate BPM/SpO2

GUI HTML PAGE (embedded in PROGMEM):
  Load Chart.js library from CDN
  Create two Chart.js line chart instances:
    - BPM chart (y-axis: 40-160 BPM)
    - SpO2 chart (y-axis: 70-100%)
  Initialize data arrays for each chart
  
  JavaScript Update Function (runs every 300ms):
    Fetch JSON data from /metrics endpoint
    Update numerical displays (BPM, SpO2, IR, RED)
    Add new BPM value to BPM data array
    Add new SpO2 value to SpO2 data array
    IF array length > maxPoints (100):
      Remove oldest value (shift)
    Update chart labels (array indices)
    Update chart datasets with new data
    Call chart.update() to refresh display
  
  Set interval to call update function every 300ms
Key Features
  • Real-time line chart visualization using Chart.js library
  • Dual chart display: BPM and SpO2 trends over time
  • Automatic data scrolling: maintains 100 most recent data points
  • Numerical displays alongside charts for precise values
  • Responsive design with dark theme for OLED-style aesthetic
  • Automatic chart scaling with fixed y-axis ranges for consistent visualization
  • CDN-based Chart.js loading for minimal memory footprint
What You Need to Know
  • Chart.js CDN: Library loaded from jsdelivr.net CDN; requires internet connection on client device
  • Data Management: Arrays limited to 100 points to prevent memory overflow; older data automatically discarded
  • Update Rate: 300ms refresh rate balances responsiveness with server load; adjust based on network conditions
  • Chart Configuration: Y-axis ranges fixed (BPM: 40-160, SpO2: 70-100) for consistent scaling; modify in JavaScript if needed
  • Browser Compatibility: Requires modern browser with JavaScript enabled; tested on Chrome, Firefox, Safari
  • Performance: Chart updates are lightweight; multiple simultaneous clients may impact ESP32 performance
  • Offline Operation: Charts won't load if client device lacks internet (Chart.js CDN unavailable); consider local hosting for offline use
Download: pulse_gui_2.ino

Reflections & Learnings

Key insights and learnings from working with interface and application programming.

Contributions

Acknowledgements and team roles for interface and application programming work.

Ethical AI Use

Transparent documentation of AI assistance used in this week's interface and application programming work.

This section documents all AI assistance used during Week 12 interface and application programming work. ChatGPT was used for code development, troubleshooting, and technical guidance. All transcripts are linked below for transparency.

Menu System with Modes

AI assistance for developing the button-based menu system with mode navigation (Menu, Camera, Sensors) using press pattern detection. The conversation covered button debouncing, press pattern recognition, mode state management, and OLED menu display design.

Related to: Part (a): Simple Button User Interface on OLED

View ChatGPT Transcript: Menu System with Modes

I2C Device Not Found

Troubleshooting session for I2C device detection issues with MAX30102 pulse oximeter sensor. The conversation addressed power isolation problems, I2C wiring verification, sensor initialization order, and ground plane isolation requirements for accurate sensor operation.

Related to: Part (b): Real-Time Graphical User Interface through OLED and WiFi

View ChatGPT Transcript: I2C Device Not Found

Hello World Code

Development assistance for creating the initial OLED "Hello World" test program. The conversation covered I2C initialization, OLED display library setup, text rendering, and basic display configuration for XIAO ESP32-S3 development board.

Related to: Part (b): Real-Time Graphical User Interface through OLED and WiFi (initial OLED test)

View ChatGPT Transcript: Hello World Code

MAX30102 Initialization Fix

Technical guidance for fixing MAX30102 pulse oximeter sensor initialization issues. The conversation addressed sensor configuration parameters, LED brightness settings, sample rate optimization, initialization sequence requirements, and troubleshooting sensor communication problems.

Related to: Part (b): Real-Time Graphical User Interface through OLED and WiFi (pulse oximeter readings)

View ChatGPT Transcript: MAX30102 Initialization Fix

Grip Strength Monitor Code Design

Code-focused assistance for designing and refining the WiFi grip strength monitor firmware. The conversation covered HX711 bring-up, load cell pin mapping, Serial Plotter debugging sketches, the ESP32-S3 HTTP server, the Chart.js dashboard, and the age-estimation helpers used in loadcell_simple.ino, loadcell_plot.ino, and loadcell_gui.ino.

Related to: Part (c): Real-Time GUI through Mechanical Gripper and WiFi and Grip Strength Monitor design files

View ChatGPT Transcript: Grip Strength Monitor Code

Grip Strength Calibration & Scaling

Calibration-focused assistance for mapping HX711 counts to kilograms and validating the grip strength readings. The discussion walked through using the Serial Plotter, collecting reference weights, tuning the calibration factor, and sanity-checking the age-estimation model derived from normative grip strength data.

Related to: Part (c): Real-Time GUI through Mechanical Gripper and WiFi calibration workflow and the Grip Strength Monitor sketches.

View ChatGPT Transcript: Grip Strength Calibration

Grip Strength Monitor – Cursor Transcript

Full Cursor AI transcript focused on organizing the grip strength monitor section: structuring Part (c), integrating design files, embedding images and videos, and aligning captions, external references, and the Ethical AI Use documentation for the load cell project.

Related to: Part (c): Real-Time GUI through Mechanical Gripper and WiFi, Grip Strength Monitor design files, and this Ethical AI Use section.

View HTML Transcript Download Markdown Transcript

Week 12 Project Documentation

Complete Cursor AI transcript for Week 12 interface and application programming project documentation. This comprehensive conversation covers the creation and population of the Week 12 HTML page, including Individual Assignment sections (button UI and WiFi GUI), Group Assignment tool comparisons, Design Files documentation with pseudocode, and Ethical AI Use section organization. The transcript demonstrates the collaborative process of building professional documentation with structured content, embedded media, and comprehensive code documentation.

Related to: Complete Week 12 documentation including Individual Assignment, Group Assignment, Design Files, and overall page structure

View HTML Transcript Download Markdown Transcript

Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License

``` ```html Week 13 · Wildcard Week
← Back to Home
[Profile Image Placeholder]

Week 13

Wildcard Week

Week Highlights

Key captures from the group and individual assignments with links to their sections.

Button User Interface on OLED

OLED button user interface menu system

Hello World on OLED

Hello World display on OLED for Invisible String project

Pulse Oximeter Readings

Pulse oximeter readings showing IR, RED, and BPM values

Wi-Fi GUI Readings

Wi-Fi web interface displaying real-time pulse oximeter readings

Wi-Fi GUI Plots

Wi-Fi web interface with real-time plotting of pulse oximeter data

OLED Video Stream Demo

Grip Strength Gripper

CAD rendering of the full grip strength device with base, handle, and load cell Photo of the fully assembled grip strength device with electronics and handle

Load Cell Calibration Plot

Serial Plotter screenshot showing load cell readings rising with grip force

Grip Strength WiFi GUI

Table of Contents

Course Content

Training & Documentation

Assignments & Projects

Wildcard Week

This week focuses on exploring digital fabrication processes not covered in previous assignments. We'll design and produce something using computer-aided design and manufacturing, documenting requirements and including everything necessary for reproduction. This week also includes reflection on the impact and purpose of making (almost) anything.

Exploring new digital fabrication processes
Designing and producing with CAD/CAM
Understanding the impact and purpose of fabrication labs

This Week's Goals

  • Explore New Processes
    Design and produce something with a digital process not covered in other assignments
  • Complete Documentation
    Document requirements and include everything necessary to reproduce the project
  • Reflect on Impact
    Understand the purpose and impact of fabrication labs and making

Assignments

  • Group Assignment
    Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment
  • Individual Assignment
    Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment, documenting the requirements that your assignment meets, and including everything necessary to reproduce it

Tools & Materials

  • Carvera (CNC Mill) — Edge cuts and hole machining
  • Fiber Laser Cutter (xTool F2 Ultra) — PCB engraving
  • PCB Design Software (KiCad) — Board layout and design
  • ATtiny1626 Microcontroller — Target device for development board
  • RP2354A Microcontroller — Complex board design

Training Documentation

Training materials and documentation for interface and application programming.

No recitation this week.

Useful Documentation

Essential resources for interface and application programming.

Class Page

Interface and Application Programming - MIT Academy

Comprehensive resource covering interface design, application programming, GUI frameworks, embedded UI development, web interfaces for embedded systems, and user interaction patterns. Includes detailed tutorials, code examples, and implementation guides for various interface programming tools and frameworks.

Key Topics

  • Interface Design: User experience principles, interaction patterns, feedback mechanisms
  • Embedded UI: OLED displays, LCD interfaces, character displays
  • Web Interfaces: HTTP servers, REST APIs, WebSockets, real-time data visualization
  • Application Frameworks: GUI toolkits, web frameworks, mobile apps
  • User Input: Buttons, touch interfaces, gesture recognition, voice commands

Additional References

Individual Assignment: Interface & Application Programming

Write an application that interfaces a user with an input &/or output device that you made. This assignment demonstrates three interface applications: (a) a simple button user interface on OLED, (b) a real-time graphical user interface through OLED and Wi-Fi for pulse oximeter readings, and (c) a Wi-Fi grip strength monitor with a mechanical gripper and age-estimation web dashboard.

Part (a): Simple Button User Interface on OLED

A mode-based user interface system that interfaces users with multiple input and output devices through a simple button press interface. The system provides visual feedback on an OLED display and enables navigation between different modes (Menu, Camera, Sensors) using button press patterns. Users interact by pressing a button multiple times to select modes, with visual confirmation displayed on the OLED screen.

Interface Design

The interface uses a mode-based navigation system where button presses trigger mode changes. A single press enters Camera mode, two presses enter Sensors mode, three presses return to Menu, and holding the button activates a flashlight function. The OLED display shows the current menu state and provides clear visual feedback for each mode transition. See Ethical AI Use: Menu System with Modes for AI-assisted development details.

OLED button user interface menu system displaying mode selection options
OLED button user interface menuMenu screen showing available modes: Camera, Sensors, and Menu navigation options with button press instructions.
Button UI demonstrationVideo showing button press interactions navigating through different modes on the OLED display.
First video stream on OLEDInitial camera feed streaming to OLED display using dithering algorithm for monochrome conversion, demonstrating real-time video output interface.
Download Design Files
  • outputs.ino — Button user interface code with mode system
  • camera_pins.h — Camera pin definitions header file
  • outputs.zip — Complete project archive including all dependencies

Part (b): Real-Time Graphical User Interface through OLED and WiFi

A dual-interface health monitoring system that interfaces users with a MAX30102 pulse oximeter sensor through both an OLED display and a WiFi-enabled web interface. The system provides real-time visualization of heart rate (BPM), blood oxygen saturation (SpO2), and raw sensor data (IR and RED LED readings) through multiple output channels. Users can view data locally on the OLED display or remotely via a web browser accessing the ESP32-S3's built-in HTTP server. See Ethical AI Use: I2C Device Not Found for troubleshooting documentation.

Interface Design

The system provides dual-interface access: a local OLED display shows real-time sensor readings (IR, RED, BPM, SpO2) with visual heartbeat indicators, while a WiFi web interface provides comprehensive data visualization including numerical displays and real-time plotting charts. The web interface uses Chart.js for dynamic graph generation and automatically refreshes every 300ms to maintain real-time data updates. Both interfaces run simultaneously, enabling local monitoring and remote access.

Hello World on OLED

Initial OLED display test showing successful I2C communication and display initialization. See Ethical AI Use: Hello World Code for development details.

Hello World display on OLED for Invisible String project showing successful display initialization
Hello World on OLEDInitial OLED test confirming I2C communication and display functionality before implementing sensor interfaces.
Pulse Oximeter Readings on OLED

Real-time pulse oximeter data displayed on OLED showing IR and RED LED readings, heart rate (BPM), and blood oxygen saturation (SpO2) percentage. A heartbeat indicator flashes when a pulse is detected. See Ethical AI Use: MAX30102 Initialization Fix for sensor setup documentation.

Pulse oximeter readings on OLED displaying IR, RED, BPM, and SpO2 values
OLED sensor readings displayReal-time pulse oximeter data showing IR and RED LED values, heart rate (BPM), and blood oxygen saturation (SpO2) with heartbeat indicator.
BPM and SpO2 demonstrationVideo showing real-time heart rate and blood oxygen saturation measurements updating on OLED display with sensor interaction.
Pulse Oximeter Readings on WiFi GUI

WiFi web interface providing remote access to pulse oximeter data through a responsive HTML dashboard. The interface displays real-time numerical values for BPM, SpO2, IR, and RED readings with automatic data refresh. The web server runs on the ESP32-S3, allowing access from any device on the same WiFi network.

WiFi web interface displaying real-time pulse oximeter readings including BPM, SpO2, IR, and RED values
WiFi GUI readings dashboardRemote web interface showing real-time pulse oximeter data accessible from any device on the WiFi network, displaying BPM, SpO2, IR, and RED values with automatic updates.
Pulse Oximeter Plots on WiFi GUI

Enhanced WiFi web interface with real-time plotting capabilities using Chart.js library. The interface displays live line charts for BPM and SpO2 values, showing trends over time with automatic scrolling and data point management. This visualization enables users to observe patterns in heart rate and blood oxygen levels during monitoring sessions.

Serial monitor output showing sensor readings rising on touch interaction
Serial monitor sensor responseSerial output demonstrating sensor readings increase when finger is placed on MAX30102 sensor, showing IR and RED LED response to touch.
WiFi web interface with real-time plotting of BPM and SpO2 data using Chart.js
WiFi GUI with plotting chartsEnhanced web interface displaying real-time line charts for BPM and SpO2 values, showing trends over time with automatic data refresh and chart scrolling.

I2C Device Detection

Successful I2C device detection after fixing power isolation issues. The system now correctly identifies the OLED display at address 0x3C and the MAX30102 sensor at address 0x57. Initial troubleshooting required isolating the RD (red LED) and IRD (infrared LED) ground terminals from the general ground plane to prevent power issues and enable proper sensor operation. 

20:04:48.612 -> Scanning...
20:04:48.644 -> I2C device found at address 0x3C  !
20:04:48.644 -> I2C device found at address 0x57  !
20:04:48.644 -> done
Download Design Files

Part (c): Real-Time GUI through Mechanical Gripper and WiFi

A Wi-Fi-connected grip strength meter that interfaces a user with a mechanical hand gripper, an 80 kg load cell, and an HX711 amplifier. The ESP32-S3 continuously measures grip force, streams it to a web dashboard, and uses a published relationship between handgrip strength and age to display an estimated “physiological age” in real time. The design is inspired by the open-source grip strength meter from NeuroTech Hub at WashU and the associated PLOS ONE paper on grip strength and age trajectories (Syddall et al., 2014), adapted to my load cell and handle geometry.

Mechanically, a custom 3D-printed gripper clamps around a CZL601-type 80 kg bar load cell (sourced from Amazon 80 kg load cell). I imported a 100 kg load cell CAD from GrabCAD, checked the mounting dimensions against the CZL601AC datasheet (online, download), and confirmed that the hole spacing and footprint match the commercial part used here.

Mechanical Design and Fabrication

CAD model of the 3D-printed grip strength base and load cell mounting region
Grip strength base CADTop view of the grip strength base showing the bar load cell pocket, mounting bosses, and handle interface.
Side view CAD of the hand gripper and load cell assembly
Side view of gripper assemblySide profile showing how the fixed base, moving handle, and load cell align along the force axis of the bar sensor.
Full CAD view of the grip strength device with base and handle
Full grip strength assemblyComplete CAD of the base, handle, and load cell, sized for comfortable adult hand placement and full-finger contact.
Close-up of mounting holes and clearances around the load cell in CAD
Load cell mounting holesDetail of the M6 clearance and counterbore geometry used to capture the load cell without constraining bending.
Perspective CAD view of the gripper handle and base
Handle ergonomicsPerspective view of the curved handle designed to distribute pressure across the palm and fingers during maximal grip.
Photo of drilled clearance hole aligned to the printed pilot in the base
Clearance hole verificationPrinted pilot holes used as drill guides to match the metric mounting dimensions from the CZL601AC datasheet.
Photo of the fully printed grip strength device before drilling and assembly
Fresh off the printer3D-printed base and handle components in PLA prior to post-processing and hardware installation.
Printed part clamped for drilling load cell mounting holes
Workholding for accurate drillingThe printed base clamped to the drill press table so the pilot features guide the final clearance holes into the load cell.
Drilling practiceTraining cuts on scrap material to dial in drill press settings and avoid cracking the printed base during final holes.
Final load cell holesDrilling the final M6 clearance holes through the printed base, constrained by the pilot features to preserve alignment.

Electronics and Calibration

Electronics assembly with HX711 breakout, ESP32-S3, and load cell wiring
Electronics stack-upHX711 amplifier breakout from Amazon wired to the ESP32-S3 and 80 kg load cell with short, twisted signal pairs for noise reduction.
Fully assembled grip strength device with load cell, electronics, and handle
Assembled grip strength meterCompleted mechanical and electrical assembly ready for calibration and software bring-up.
Serial Plotter view of load cell readings increasing with grip force
Serial Plotter calibration tracesRaw HX711 output converted to kilograms and visualized in the Arduino Serial Plotter while applying known weights and grip forces.
Web GUI showing grip strength value, estimated age, and scrolling chart
Wi-Fi grip strength dashboardBrowser-based GUI with live grip strength (kg), estimated age, and a Chart.js time series plot of recent squeezes.

Model Used for Age Estimation

The age-estimation logic in the firmware is based on the non-linear, sex-specific grip-strength trajectories reported in Dodds et al., 2014 (PLOS ONE). As shown in Figure 1 of that paper, grip strength rises rapidly through adolescence, peaks around ages 30–40, and then declines non-linearly with age, with different magnitudes for males and females.

Reference grip strength trajectories over the life course from Dodds et al., PLOS ONE 2014
Reference trajectories (Figure 1)Age-dependent grip strength curves for males and females from Dodds et al., 2014, used as the qualitative target for the embedded model.
Simplified quadratic grip strength model fitted to reference data
Quadratic approximation (Table 2-inspired)Simplified male and female trajectories using peak strengths and curvatures chosen to approximate the summary values reported in Table 2 of Dodds et al., 2014.

To reproduce this shape efficiently on the ESP32, the firmware uses inverted quadratic approximations centered at age 35, consistent with the observed peak in the PLOS ONE data. In the forward direction, grip strength is approximated as:

Males: Grip(age) ≈ 52 − 0.0089·(age − 35)2
Females: Grip(age) ≈ 32 − 0.0059·(age − 35)2

On the device, this relationship is analytically inverted so that the measured grip strength can be mapped back to an estimated age:

age = 35 + √((a − Grip)/b), where a is the peak strength (52 kg for males, 32 kg for females) and b is the curvature (0.0089 for males, 0.0059 for females). The firmware clamps grip strength to physiologically meaningful ranges before applying this formula so the square root remains well-defined. 

float ageFromGripMale(float g) {
  float a = 52.0f, b = 0.0089f;
  if (g > a) g = a;
  if (g < 5) g = 5;
  return 35.0f + sqrtf((a - g) / b);
}

float ageFromGripFemale(float g) {
  float a = 32.0f, b = 0.0059f;
  if (g > a) g = a;
  if (g < 4) g = 4;
  return 35.0f + sqrtf((a - g) / b);
}

For full methodological details and original tables/figures, see the open-access paper: Dodds et al., 2014, PLOS ONE (download local PDF). The implementation here is an educational approximation and not intended for clinical or diagnostic use.

End-to-end live demoReal-time demonstration of squeezing the mechanical gripper and watching the Wi-Fi dashboard update grip strength and estimated age on a laptop.

Related Design, Code, and Calibration Resources

User Interface Comparison

Summary of how each interface application connects users with input and output devices.

Application How It Interfaces with the User Input Device(s) Output Device(s)
(a) Button User Interface Button press patterns (single, double, triple press, hold) provide mode selection input. OLED display shows current menu state and mode options. Users receive immediate visual feedback for each interaction. Button (GPIO pin 4) OLED Display (SSD1306, I²C 0x3C)
LED (GPIO pin 3, flashlight mode)
(b) Real-Time GUI (OLED & WiFi) Physical finger placement on MAX30102 sensor provides input. OLED displays real-time sensor data locally. WiFi web interface enables remote monitoring with numerical displays and live plotting charts accessible from any web browser. MAX30102 Pulse Oximeter Sensor (I²C 0x57) OLED Display (SSD1306, I²C 0x3C)
WiFi Web Interface (HTTP Server with Chart.js visualization)
(c) Grip Strength GUI (Load Cell & WiFi) Users squeeze a mechanical hand gripper that transfers force into an 80 kg bar load cell. The ESP32-S3 measures grip strength through the HX711 amplifier and streams results to a WiFi web dashboard that displays live grip force and an estimated physiological age in real time. Mechanical gripper linked to 80 kg load cell (CZL601-type)
HX711 load cell amplifier		 WiFi Web Interface (HTTP Server with Chart.js visualization)
Optional Serial Plotter (for calibration traces)

Group Assignment: Compare as Many Tool Options as Possible

Compare as many tool options as possible for interface and application programming.

General Comparison: Interface & Application Programming Tools

Comprehensive comparison of interface and application programming tools available for embedded systems and IoT development. This analysis covers tools from the MIT Academy Interface & Application Programming class page, evaluating their capabilities, use cases, and trade-offs for different application scenarios.

Embedded Display Interfaces

Tool/Framework Description Pros Cons Best For
OLED (SSD1306) Monochrome OLED displays via I²C Low power, high contrast, simple I²C interface, pixel-level control Limited resolution (128x64), monochrome only, small display size Status displays, sensor readouts, simple menus, embedded dashboards
LCD Character Displays Character-based LCD displays (16x2, 20x4) Simple API, readable in sunlight, low cost Limited to text/characters, no graphics, requires backlight power Text-only interfaces, status messages, debugging output
TFT Color Displays Full-color TFT LCD displays Color graphics, touch support, high resolution High power consumption, complex drivers, larger footprint Rich GUIs, image display, interactive touch interfaces

Web-Based Interfaces

Tool/Framework Description Pros Cons Best For
HTTP Server (ESP32) Built-in HTTP server on ESP32 for web interfaces Remote access, cross-platform (any browser), no app installation, real-time updates Requires WiFi, network dependency, limited to local network without port forwarding Remote monitoring, data visualization, control panels, sensor dashboards
WebSockets Real-time bidirectional communication Low latency, bidirectional, efficient for frequent updates More complex than HTTP, requires persistent connection Real-time streaming, interactive controls, live data feeds
Chart.js JavaScript charting library for web interfaces Beautiful charts, interactive, responsive, easy integration Requires JavaScript, CDN dependency or local hosting Data visualization, time series plots, sensor monitoring dashboards

Mobile & Native App Frameworks

Tool/Framework Description Pros Cons Best For
React Native Cross-platform mobile app framework Cross-platform (iOS/Android), native performance, large ecosystem Complex setup, requires mobile development knowledge Full-featured mobile apps, production deployments
Flutter Google's UI toolkit for cross-platform apps Single codebase, high performance, customizable UI Dart language, larger app size, learning curve Custom mobile interfaces, platform-specific designs
Progressive Web Apps (PWA) Web apps with native-like features No app store, cross-platform, offline capability Limited native API access, browser dependency Web-based mobile interfaces, simple deployment

Specific Comparison: Tools Used in Individual Assignment

Detailed comparison of the specific interface programming tools implemented in this week's individual assignment, evaluating their performance, ease of use, and suitability for embedded health monitoring applications.

OLED Display Interface (Adafruit SSD1306)

Aspect Evaluation
Ease of Implementation Simple I²C interface, well-documented Adafruit library, minimal wiring (SDA, SCL, power, ground)
Display Quality High contrast monochrome display, crisp text rendering, suitable for sensor data visualization
Power Consumption Very low power draw, ideal for battery-powered applications
Limitations 128x64 pixel resolution limits detail, monochrome only, small physical size (0.96" typical)
Best Use Cases Local sensor readouts, menu systems, status indicators, simple data displays

WiFi Web Interface (ESP32 HTTP Server + Chart.js)

Aspect Evaluation
Ease of Implementation ESP32 WebServer library provides straightforward HTTP server, Chart.js CDN integration requires minimal setup
Remote Access Accessible from any device on WiFi network (phone, tablet, computer), no app installation required
Visualization Capabilities Chart.js enables rich data visualization with real-time plotting, smooth animations, and interactive features
Real-Time Updates JSON API endpoint provides efficient data transfer, 300ms refresh rate maintains responsive feel
Limitations Requires WiFi network, limited to local network without additional configuration, power consumption higher than OLED alone
Best Use Cases Remote monitoring, data logging visualization, multi-user access, professional dashboards

Button Input Interface

Aspect Evaluation
Implementation Approach Digital GPIO reading with debouncing, press pattern detection (single/double/triple/hold) enables mode navigation
User Experience Intuitive press patterns, immediate visual feedback on OLED, no complex UI navigation required
Reliability Hardware debouncing with INPUT_PULLUP, timeout-based pattern recognition prevents accidental triggers
Limitations Limited to single button interaction, pattern learning required, less flexible than touchscreen interfaces
Best Use Cases Simple mode selection, menu navigation, embedded system controls, low-cost input solutions

Comparison Summary

The combination of OLED display and WiFi web interface provides complementary benefits: OLED offers immediate local feedback with minimal latency and power consumption, while the WiFi interface enables rich visualization and remote access. The button-based input provides an intuitive, low-cost navigation method suitable for embedded systems. Together, these tools create a robust interface system that supports both local and remote interaction with sensor data.

Design Files

Design files and code documentation for interface and application programming projects.

ESP32-S3 Development Board and Pinouts

Code files for ESP32-S3 development board interfaces including I2C scanning, OLED display control, and button-based user interface systems. See Week 4 documentation for board design and Week 8 documentation for pinout configurations.

I2C Scanner (i2cscan_generic.ino)

Utility code for scanning and detecting I2C devices on the bus, essential for troubleshooting connection issues.

How the Code Works (Pseudocode)
SETUP:
  Initialize I2C bus
  Initialize Serial communication
  Print "I2C Scanner" message

LOOP:
  Print "Scanning..." message
  Initialize device counter to 0
  
  FOR each address from 1 to 126:
    Begin I2C transmission to address
    Check transmission result
    
    IF transmission successful (error == 0):
      Print device found at address (hex format)
      Increment device counter
    ELSE IF unknown error (error == 4):
      Print unknown error at address
    
  IF no devices found:
    Print "No I2C devices found"
  ELSE:
    Print "done"
  
  Wait 5 seconds before next scan
Key Features
  • Scans all 127 possible I2C addresses (0x01-0x7E)
  • Detects and reports connected devices with hex address format
  • Handles multiple error conditions (device not found, unknown errors)
  • Continuous scanning mode with 5-second intervals
  • Compatible with any I2C bus configuration (Wire, Wire1, etc.)
What You Need to Know
  • I2C Address Range: Valid addresses are 0x08-0x77 (8-119 decimal); addresses 0x00-0x07 and 0x78-0x7F are reserved
  • Common Addresses: OLED displays typically use 0x3C or 0x3D; sensors vary (MAX30102 uses 0x57)
  • Troubleshooting: If no devices found, check wiring (SDA, SCL, power, ground), verify pull-up resistors, confirm device power
  • Usage: Run this before connecting other devices to verify I2C bus is working correctly
Download: i2cscan_generic.ino

Hello World OLED Display (hello_world.ino)

Basic OLED display test code that initializes the display and shows "Hello World" text, confirming I2C communication and display functionality.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial communication at 115200 baud
  Wait 500ms for Serial to stabilize
  
  Initialize I2C bus with SDA pin 5, SCL pin 6
  Print "Starting..." message
  
  Attempt to initialize OLED display:
    IF initialization fails:
      Print "OLED not found" error
      Enter infinite loop (halt)
  
  Clear display buffer
  Set text size to 2
  Set text color to white
  Set cursor position to (0, 20)
  Print "Hello" line
  Print "World!" line
  Update display (send buffer to hardware)

LOOP:
  Empty (runs once, then waits)
Key Features
  • Simple OLED initialization and text display
  • Custom I2C pin configuration for XIAO ESP32-S3 (SDA=5, SCL=6)
  • Error handling with infinite loop if display not found
  • Text size and cursor positioning for centered display
  • One-time display update (no loop refresh needed for static text)
What You Need to Know
  • I2C Pin Configuration: XIAO ESP32-S3 uses pins 5 (SDA) and 6 (SCL) by default; verify your board's pinout
  • Display Address: SSD1306 OLED typically uses address 0x3C; some variants use 0x3D
  • Display Update: Must call display.display() to send buffer to hardware; drawing functions only modify buffer
  • Testing: Use this as first test after connecting OLED to verify wiring and I2C communication before adding complex features
  • Libraries Required: Adafruit_GFX, Adafruit_SSD1306, Wire
Download: hello_world.ino

Button User Interface (outputs.ino)

Mode-based navigation system using button press patterns (single, double, triple, hold) to control multiple output devices including OLED display, camera, sensors, and LED flashlight.

How the Code Works (Pseudocode)
SETUP:
  Initialize OLED display
  Initialize camera module
  Initialize sensors (MPU6050, HX711)
  Initialize button pin (INPUT_PULLUP)
  Initialize LED pin (OUTPUT)
  Set current mode to MENU
  Display menu screen

LOOP:
  Read button state
  
  IF button pressed:
    Record press start time
    Start press detection timer
  
  IF button released:
    Calculate press duration
    IF duration > HOLD_THRESHOLD:
      Activate flashlight mode
    ELSE:
      Increment press count
      Reset press timeout timer
  
  IF press timeout exceeded:
    Process accumulated press count:
      IF press count == 1: Switch to CAMERA mode
      IF press count == 2: Switch to SENSORS mode
      IF press count == 3: Switch to MENU mode
    Reset press count
  
  IF current mode == MENU:
    Display menu screen (button instructions)
  
  IF current mode == CAMERA:
    Capture camera frame
    Process image with dithering algorithm
    Display on OLED
    Run Edge Impulse inference (optional)
    Overlay results on display
  
  IF current mode == SENSORS:
    Read accelerometer/gyroscope data
    Read load cell data
    Display sensor readings on OLED
  
  Update display
Key Features
  • Press pattern detection: single (1x), double (2x), triple (3x), and hold
  • Mode-based navigation system (Menu, Camera, Sensors)
  • Button debouncing with timeout-based pattern recognition
  • Floyd-Steinberg dithering for camera-to-OLED video display
  • Edge Impulse AI inference integration for face detection
  • Multi-sensor integration (MPU6050 accelerometer/gyro, HX711 load cell)
  • Flashlight mode activated by button hold
What You Need to Know
  • Button Wiring: Use INPUT_PULLUP mode (button connects pin to GND when pressed, internal pull-up to 3.3V)
  • Press Detection: Press count is accumulated until timeout (1 second); longer timeout allows slower multiple presses
  • Mode Switching: Each mode has distinct display update logic; ensure proper initialization in setup()
  • Camera Performance: Video streaming to OLED requires significant processing; frame rate depends on resolution and dithering complexity
  • Dependencies: Requires camera_pins.h header file with XIAO ESP32-S3 camera pin definitions; see Ethical AI Use for development details
  • Sensor Conflicts: Code uses preprocessor directives to resolve sensor_t type conflict between ESP32 camera and Adafruit MPU6050 libraries
Download: outputs.ino | camera_pins.h | outputs.zip (complete project)

Grip Strength Monitor (Load Cell + WiFi GUI)

Design files and firmware for a Wi-Fi-enabled grip strength meter built around an 80 kg bar load cell, HX711 amplifier, and ESP32-S3. The mechanical design was informed by the open-source grip strength meter from NeuroTech Hub and validated against the CZL601AC bar load cell datasheet (online, download).

Mechanical Design Files (3D-Printed Components)

  • Base.3mf — main chassis that captures the bar load cell and anchors the fixed side of the gripper.
  • Case.3mf — protective enclosure for the ESP32-S3 and HX711 amplifier with cable strain relief.
  • Handle.3mf — curved grip handle that transfers hand force into the free end of the load cell.
  • Calibration Print.3mf — small test piece used to verify hole diameters and load cell clearances before printing the full assembly.

All parts were printed in PLA with high infill in the load paths to minimize creep and flex during repeated maximal grip trials.

Basic HX711 Reader (loadcell_simple.ino)

Minimal firmware to bring up the HX711 amplifier and read calibrated weight values over Serial for debugging and calibration.

How the Code Works (Pseudocode)
SETUP:
  Configure HX711 data and clock pins (DT=A1, SCK=A0)
  Initialize Serial at 115200 baud
  Begin HX711 with DT/SCK pins
  Set calibration factor (grams per ADC unit)
  Tare the scale so current load is zero

LOOP (every 200 ms):
  If HX711 is ready:
    Read averaged weight using get_units(4)
    Print "weight:<value>" to Serial for Serial Plotter
  Else:
    Print "HX711 not ready" for troubleshooting
Key Features
  • Simple initialization of the HX711 on analog pins A0/A1.
  • Configurable calibration factor for mapping counts to grams or kilograms.
  • Timed reads (200 ms) to keep Serial output manageable and Plotter-friendly.
  • Graceful handling of HX711 not-ready states.
What You Need to Know
  • Use for initial bring-up: Run this first when wiring the HX711 and load cell to confirm clean, stable readings.
  • Calibration factor: Determined experimentally by hanging known weights and adjusting until readings match; see the calibration notes in Calibration Chat.
  • Serial Plotter: The weight:<value> format is convenient for quickly visualizing changes while squeezing the handle.
Download: loadcell_simple.ino

Serial Plotter-Friendly Reader (loadcell_plot.ino)

Refined HX711 reader tuned for the Arduino Serial Plotter: it outputs a single numeric value per line for clean plotting of grip strength over time.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial at 115200 baud
  Initialize HX711 on DT=A1, SCK=A0
  Set calibration factor
  Tare the scale
  Optionally print debug messages when DEBUG=1

LOOP (every 200 ms):
  If HX711 is ready:
    Read filtered weight with get_units(4)
    Optionally print labeled debug text
    Print only the numeric weight to Serial for the Plotter
  Else:
    Optionally print "not ready" debug text
    Print 0 so the plotted line continues gracefully
Key Features
  • DEBUG toggle: Compile-time switch to enable/disable human-readable logs without breaking the Serial Plotter format.
  • Clean “one number per line” output for multi-trial grip testing in the Serial Plotter.
  • Automatic zero output when the HX711 is not ready to keep the time axis continuous.
  • Shared pinout and calibration approach with loadcell_simple.ino for easy swapping.
What You Need to Know
  • Use this sketch to tune calibration and visualize grip curves without any GUI overhead.
  • When collecting data for analysis, keep DEBUG set to 0 so the output is a pure numeric stream.
  • The sample interval (200 ms) gives a smooth trace while keeping file sizes reasonable for multi-second squeezes.
Download: loadcell_plot.ino

WiFi Grip Strength GUI (loadcell_gui.ino)

Full application firmware that exposes grip strength and an estimated age over Wi-Fi using an HTTP server and a Chart.js web dashboard.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial
  Initialize HX711 (pins, calibration factor, tare)
  Connect ESP32-S3 to WiFi (MIT network in this build)
  Start WebServer on port 80
  Register handlers:
    "/"        → serve HTML+JS GUI page from PROGMEM
    "/metrics" → serve JSON with current grip and age

LOOP:
  Handle incoming HTTP clients
  Every 200 ms:
    If HX711 is ready:
      Read smoothed grip strength (kg) via get_units(3)
      Clamp negative values to zero
      Store in global gripStrength

AGE ESTIMATION HELPERS:
  ageFromGripMale(g):
    Clamp g to plausible range
    Compute age using inverted quadratic fit derived from normative data
  ageFromGripFemale(g):
    Same structure with female-specific parameters

HTTP /metrics ENDPOINT:
  Read "sex" query parameter (default "male")
  Compute ageEstimate = ageFromGripMale/ageFromGripFemale(gripStrength)
  Return JSON:
    {"grip": <kg>, "age": <years>}

CLIENT-SIDE GUI (HTML + JS):
  Render dark-themed dashboard with:
    - Sex toggle buttons (male/female)
    - Numeric grip strength (kg) and age
    - Scrolling Chart.js line plot of recent grip values
  Poll /metrics every 200 ms and update DOM + chart
Key Features
  • Embedded HTML/JS dashboard served directly from the ESP32-S3 using PROGMEM.
  • Real-time grip strength plot using Chart.js with ~120 recent samples.
  • Simple sex toggle that switches between male and female age-estimation curves.
  • JSON API at /metrics for future extensions (e.g., logging clients).
What You Need to Know
  • WiFi credentials: Update the ssid and password constants to match your network.
  • Normative model: The age equations are simplified fits inspired by the grip-strength trajectories reported in Syddall et al., PLOS ONE 2014 and are for educational visualization only, not clinical use.
  • Browser requirements: Any modern browser with JavaScript and network access can connect to the ESP32-S3’s IP address to view the dashboard.
  • Development log: The full iterative design of this sketch is captured in the ChatGPT transcript: Grip Strength Monitor Code Chat.
Download: loadcell_gui.ino

Invisible String Chain of Hearts

Code files for the Invisible String pulse oximeter interface system, providing real-time health monitoring through OLED display and WiFi web interface. See Week 11 PCB design documentation for hardware details.

OLED GUI for Pulse Oximeter (pulse_vo2_reads_fixing.ino)

Local OLED display interface showing real-time pulse oximeter readings including heart rate (BPM), blood oxygen saturation (SpO2), and raw IR/RED LED sensor values.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial communication
  Initialize I2C bus (SDA=5, SCL=6) at 400kHz
  Initialize MAX30102 sensor
  Configure sensor:
    Set LED mode to RED + IR
    Set ADC range to 16384
    Set sample rate to 100 Hz
    Set pulse width to 411 μs
    Set LED brightness to medium (0x3F)
  Initialize OLED display
  Clear and prepare display

LOOP:
  Read IR and RED LED values from sensor
  
  Heart Rate Detection:
    Check for heartbeat in IR signal using peak detection
    IF heartbeat detected:
      Calculate time since last beat
      Calculate BPM = 60 / (time_delta / 1000)
      Set beat flag for visual indicator
      Update last beat timestamp
  
  SpO2 Calculation (every 300ms):
    Add IR and RED values to circular buffer
    IF buffer has 50 samples:
      Calculate DC components (average)
      Calculate AC components (RMS)
      Calculate R ratio = (AC_RED/DC_RED) / (AC_IR/DC_IR)
      Estimate SpO2 = 110 - 25 * R
      Clamp SpO2 to 70-100% range
  
  Serial Output:
    Print IR, RED, BPM for Serial Plotter visualization
  
  OLED Display Update:
    Clear display buffer
    Display IR value (small text)
    Display RED value (small text)
    Display BPM value (large text, size 2)
    Display SpO2 percentage (small text)
    IF beat detected: Draw heartbeat indicator dot
    Update display hardware
  
  Delay 20ms (50 Hz update rate)
Key Features
  • Real-time heart rate detection using peak detection algorithm on IR signal
  • SpO2 calculation using ratio-of-ratios method with DC/AC component analysis
  • Circular buffer system for storing 50 samples of IR/RED data
  • Visual heartbeat indicator (flashing dot) when pulse detected
  • Dual output: OLED display and Serial Plotter for real-time waveform visualization
  • Optimized sensor configuration for reliable readings (100 Hz sample rate, medium brightness)
What You Need to Know
  • Sensor Placement: Finger must cover sensor completely; proper contact ensures accurate readings
  • I2C Address: MAX30102 uses address 0x57; verify with I2C scanner if sensor not detected
  • Ground Isolation: RD and IRD pins must be isolated from main ground plane to prevent power issues (see Week 11 PCB design)
  • SpO2 Accuracy: Calculation provides estimation; medical-grade accuracy requires calibration and FDA-approved algorithms
  • Buffer Size: 50-sample buffer provides balance between calculation accuracy and response time
  • Libraries Required: MAX30105 (SparkFun library), Adafruit_GFX, Adafruit_SSD1306, heartRate.h (beat detection)
  • Troubleshooting: If sensor not detected, check power isolation, I2C wiring, and sensor initialization order
Download: pulse_vo2_reads_fixing.ino

WiFi Readings GUI (pulse_gui.ino)

WiFi-enabled web interface providing remote access to pulse oximeter data through HTTP server with JSON API endpoint for real-time data updates.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial communication
  Initialize I2C bus
  Initialize MAX30102 sensor
  Configure sensor (LED mode, sample rate, pulse width)
  Initialize OLED display
  Initialize WiFi:
    Connect to network (SSID, password)
    Wait for connection
    Print IP address
  Initialize HTTP server:
    Route "/" → serve GUI HTML page
    Route "/gui" → serve GUI HTML page
    Route "/metrics" → serve JSON data
  Start web server

LOOP:
  Handle incoming HTTP client requests
  
  Read IR and RED values from sensor
  
  Heart Rate Calculation:
    Check for heartbeat in IR signal
    IF heartbeat detected:
      Calculate BPM from time delta
      Update global BPM variable
  
  SpO2 Calculation:
    Add IR/RED to circular buffer
    IF buffer full (50 samples):
      Calculate SpO2 using ratio-of-ratios
      Update global SpO2 variable
  
  Update global variables (g_ir, g_red, g_bpm, g_spo2)
  
  OLED Display Update:
    Display IR, RED, BPM, SpO2 values
    Update display hardware
Key Features
  • Dual interface: OLED display (local) and WiFi web interface (remote)
  • HTTP server with embedded HTML page stored in PROGMEM
  • JSON API endpoint (/metrics) for real-time data retrieval
  • Automatic WiFi connection with connection status feedback
  • IP address display for easy access
  • Simultaneous sensor reading and web server operation
  • Global variable system for data sharing between sensor reading and HTTP handlers
What You Need to Know
  • WiFi Configuration: Update SSID and password in code; for MIT network, use generated device password from wifi.mit.edu
  • Network Access: Web interface accessible only from devices on same WiFi network; IP address printed to Serial Monitor
  • HTML Storage: GUI HTML page stored in PROGMEM (program memory) to conserve RAM; use PROGMEM for large strings
  • Server Handling: Must call server.handleClient() frequently in loop() for responsive web interface
  • Data Refresh: Client-side JavaScript polls /metrics endpoint every 300ms for real-time updates
  • Power Consumption: WiFi significantly increases power draw compared to OLED-only mode; consider power management for battery operation
  • Libraries Required: WiFi, WebServer, MAX30105, Adafruit_SSD1306
Download: pulse_gui.ino

WiFi Plot GUI (pulse_gui_2.ino)

Enhanced WiFi web interface with real-time plotting capabilities using Chart.js library, displaying live line charts for BPM and SpO2 values with automatic scrolling and data management.

How the Code Works (Pseudocode)
SETUP:
  (Same as pulse_gui.ino)
  Initialize WiFi, sensor, OLED, HTTP server

LOOP:
  (Same as pulse_gui.ino)
  Handle HTTP requests, read sensor, calculate BPM/SpO2

GUI HTML PAGE (embedded in PROGMEM):
  Load Chart.js library from CDN
  Create two Chart.js line chart instances:
    - BPM chart (y-axis: 40-160 BPM)
    - SpO2 chart (y-axis: 70-100%)
  Initialize data arrays for each chart
  
  JavaScript Update Function (runs every 300ms):
    Fetch JSON data from /metrics endpoint
    Update numerical displays (BPM, SpO2, IR, RED)
    Add new BPM value to BPM data array
    Add new SpO2 value to SpO2 data array
    IF array length > maxPoints (100):
      Remove oldest value (shift)
    Update chart labels (array indices)
    Update chart datasets with new data
    Call chart.update() to refresh display
  
  Set interval to call update function every 300ms
Key Features
  • Real-time line chart visualization using Chart.js library
  • Dual chart display: BPM and SpO2 trends over time
  • Automatic data scrolling: maintains 100 most recent data points
  • Numerical displays alongside charts for precise values
  • Responsive design with dark theme for OLED-style aesthetic
  • Automatic chart scaling with fixed y-axis ranges for consistent visualization
  • CDN-based Chart.js loading for minimal memory footprint
What You Need to Know
  • Chart.js CDN: Library loaded from jsdelivr.net CDN; requires internet connection on client device
  • Data Management: Arrays limited to 100 points to prevent memory overflow; older data automatically discarded
  • Update Rate: 300ms refresh rate balances responsiveness with server load; adjust based on network conditions
  • Chart Configuration: Y-axis ranges fixed (BPM: 40-160, SpO2: 70-100) for consistent scaling; modify in JavaScript if needed
  • Browser Compatibility: Requires modern browser with JavaScript enabled; tested on Chrome, Firefox, Safari
  • Performance: Chart updates are lightweight; multiple simultaneous clients may impact ESP32 performance
  • Offline Operation: Charts won't load if client device lacks internet (Chart.js CDN unavailable); consider local hosting for offline use
Download: pulse_gui_2.ino

Reflections & Learnings

Key insights and learnings from working with interface and application programming.

Contributions

Acknowledgements and team roles for interface and application programming work.

Ethical AI Use

Transparent documentation of AI assistance used in this week's interface and application programming work.

This section documents all AI assistance used during Week 12 interface and application programming work. ChatGPT was used for code development, troubleshooting, and technical guidance. All transcripts are linked below for transparency.

Menu System with Modes

AI assistance for developing the button-based menu system with mode navigation (Menu, Camera, Sensors) using press pattern detection. The conversation covered button debouncing, press pattern recognition, mode state management, and OLED menu display design.

Related to: Part (a): Simple Button User Interface on OLED

View ChatGPT Transcript: Menu System with Modes

I2C Device Not Found

Troubleshooting session for I2C device detection issues with MAX30102 pulse oximeter sensor. The conversation addressed power isolation problems, I2C wiring verification, sensor initialization order, and ground plane isolation requirements for accurate sensor operation.

Related to: Part (b): Real-Time Graphical User Interface through OLED and WiFi

View ChatGPT Transcript: I2C Device Not Found

Hello World Code

Development assistance for creating the initial OLED "Hello World" test program. The conversation covered I2C initialization, OLED display library setup, text rendering, and basic display configuration for XIAO ESP32-S3 development board.

Related to: Part (b): Real-Time Graphical User Interface through OLED and WiFi (initial OLED test)

View ChatGPT Transcript: Hello World Code

MAX30102 Initialization Fix

Technical guidance for fixing MAX30102 pulse oximeter sensor initialization issues. The conversation addressed sensor configuration parameters, LED brightness settings, sample rate optimization, initialization sequence requirements, and troubleshooting sensor communication problems.

Related to: Part (b): Real-Time Graphical User Interface through OLED and WiFi (pulse oximeter readings)

View ChatGPT Transcript: MAX30102 Initialization Fix

Grip Strength Monitor Code Design

Code-focused assistance for designing and refining the WiFi grip strength monitor firmware. The conversation covered HX711 bring-up, load cell pin mapping, Serial Plotter debugging sketches, the ESP32-S3 HTTP server, the Chart.js dashboard, and the age-estimation helpers used in loadcell_simple.ino, loadcell_plot.ino, and loadcell_gui.ino.

Related to: Part (c): Real-Time GUI through Mechanical Gripper and WiFi and Grip Strength Monitor design files

View ChatGPT Transcript: Grip Strength Monitor Code

Grip Strength Calibration & Scaling

Calibration-focused assistance for mapping HX711 counts to kilograms and validating the grip strength readings. The discussion walked through using the Serial Plotter, collecting reference weights, tuning the calibration factor, and sanity-checking the age-estimation model derived from normative grip strength data.

Related to: Part (c): Real-Time GUI through Mechanical Gripper and WiFi calibration workflow and the Grip Strength Monitor sketches.

View ChatGPT Transcript: Grip Strength Calibration

Grip Strength Monitor – Cursor Transcript

Full Cursor AI transcript focused on organizing the grip strength monitor section: structuring Part (c), integrating design files, embedding images and videos, and aligning captions, external references, and the Ethical AI Use documentation for the load cell project.

Related to: Part (c): Real-Time GUI through Mechanical Gripper and WiFi, Grip Strength Monitor design files, and this Ethical AI Use section.

View HTML Transcript Download Markdown Transcript

Week 12 Project Documentation

Complete Cursor AI transcript for Week 12 interface and application programming project documentation. This comprehensive conversation covers the creation and population of the Week 12 HTML page, including Individual Assignment sections (button UI and WiFi GUI), Group Assignment tool comparisons, Design Files documentation with pseudocode, and Ethical AI Use section organization. The transcript demonstrates the collaborative process of building professional documentation with structured content, embedded media, and comprehensive code documentation.

Related to: Complete Week 12 documentation including Individual Assignment, Group Assignment, Design Files, and overall page structure

View HTML Transcript Download Markdown Transcript

Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License

``` Replacing the Training section with Lecture and Recitation notes: ```html Week 13 · Wildcard Week
← Back to Home
[Profile Image Placeholder]

Week 13

Wildcard Week

Week Highlights

Key captures from the group and individual assignments with links to their sections.

Button User Interface on OLED

OLED button user interface menu system

Hello World on OLED

Hello World display on OLED for Invisible String project

Pulse Oximeter Readings

Pulse oximeter readings showing IR, RED, and BPM values

Wi-Fi GUI Readings

Wi-Fi web interface displaying real-time pulse oximeter readings

Wi-Fi GUI Plots

Wi-Fi web interface with real-time plotting of pulse oximeter data

OLED Video Stream Demo

Grip Strength Gripper

CAD rendering of the full grip strength device with base, handle, and load cell Photo of the fully assembled grip strength device with electronics and handle

Load Cell Calibration Plot

Serial Plotter screenshot showing load cell readings rising with grip force

Grip Strength WiFi GUI

Table of Contents

Course Content

Training & Documentation

Assignments & Projects

Wildcard Week

This week focuses on exploring digital fabrication processes not covered in previous assignments. We'll design and produce something using computer-aided design and manufacturing, documenting requirements and including everything necessary for reproduction. This week also includes reflection on the impact and purpose of making (almost) anything.

Exploring new digital fabrication processes
Designing and producing with CAD/CAM
Understanding the impact and purpose of fabrication labs

This Week's Goals

  • Explore New Processes
    Design and produce something with a digital process not covered in other assignments
  • Complete Documentation
    Document requirements and include everything necessary to reproduce the project
  • Reflect on Impact
    Understand the purpose and impact of fabrication labs and making

Assignments

  • Group Assignment
    Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment
  • Individual Assignment
    Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment, documenting the requirements that your assignment meets, and including everything necessary to reproduce it

Tools & Materials

  • Carvera (CNC Mill) — Edge cuts and hole machining
  • Fiber Laser Cutter (xTool F2 Ultra) — PCB engraving
  • PCB Design Software (KiCad) — Board layout and design
  • ATtiny1626 Microcontroller — Target device for development board
  • RP2354A Microcontroller — Complex board design

Lecture Notes

Week 13 lecture covering major announcements, week 12 review, system integration reminders, and wildcard week preview.

Theme of the Week

'Step away from the panic'

Major Announcements

  • Subject evaluation: Required for funding the class. Provides feedback to the institute about the class. Important for future students if you care about successors in the class.
  • Calendar alarm: Wildcard week and recitation on why make (almost) anything: impact. Friday is cutoff for assignments and orders (10s of dollars per person from inventory).
  • Final presentation/final exam: Combining multiple additive and subtractive processes (not just design a board and 3D print a case). Goal is system integration out of parts. Final exam criteria:
    • Did you integrate and design a complete system?
    • Can you demo a final project? Here is the cool thing I did and here is how it works.
    • Make a final project video! (helps but not required)
    Focus on well-integrated device!

Review of Week 12 User Interfaces

  • Claire Wang: Music play and Windows 3.1 interface works!
  • Ryan Hoffman: DRV8251A discussion, heat sinks, breakout boards. Wildcards with waterjetting, EDM, multi-axis machining, laser cutting metal. Class in the spring on nature of mathematical modeling.
  • Srikanth Nadhamuni: Background and experience to visiting fellow at MIT. Raspberry Pi W for WiFi, n8n for cloud LLM data crunching. Software: Node.js, MCP bridge server with n8n based on bridge connected to device (NGV tunnel). All set! Fantastic experience, haven't worked so hard in a very long time and learning a lot of new things. Hope to take forward and build other systems. The whole culture of doing and trying yourself fascinating, especially with failing a number of times until you figure it out. Maybe set one up at an IIT in India or AI centers of excellence with education ministry into the Indian education system (see fablabkerala.in or vigyam ashram).
  • Ray Song: Not here.
  • Tyler Jensen (Lincoln Lab, Group 81): Final project discussion (nylon printer). Week 13: Easy for web serial interface for XIAO! Web server to TFT (I think I forgot to load the camera pins with my code for it).
  • Aditi Ramakrishnan: Sloan MBA and strategy consulting background. Discrete time filter (FFT is blown) in skimage.filters — make a bandpass filter, then run a series of these filters, much less computing only adds and multiplies for filtering in realtime.
  • Alexandros Gravalos: Not here.
  • Edward Chen: Check final watch project by Gulati into watch form factor. Clear print on the Form Labs printer, 0.1. Kaman filter for sensor fusion (in the spring class). For position — LSM6DSV16X from input devices. Acceleration at 7 kHz (at audio frequency).

Show and Tell

  • Handle to sensor WiFi user interface
  • Plug to audio LLM user interface

System Integration Reminders

  • Mount electronics
  • Strain relief the final projects

Preview for Wildcard Week

Assignment: Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment.

Recitation Notes: Why Make (Almost) Anything

Recitation exploring the purpose, impact, and scaling of fabrication labs and making infrastructure.

Map of Fab Labs

Why Make a Fab Lab?

  • Used to create a community
  • Building things for the community
  • Sustainability
  • Prototyping quickly

How Impact?

  • How to make spaces: How to measure impact. What is important about fab:
    • Fablabs in cities vs rural areas: The ability to decide their own futures and change their lives fundamentally. 'Safecast revolutionized citizen science' e.g. radiation map.
    • Bringing back manufacturing: Reducing reliance on supply chains.
    • Rural sustainability: Working with indigenous communities on creating technologies themselves at scale and measure their usefulness and efficacy to preserve their ancestral knowledge:
      • How to establish labs there
      • How to make sure the labs get used
    • Hygiene technologies with Proctor and Gamble: Highly commercial. Lots of plastic waste. How can we change how they produce? How to make their products get there through resellers?
    • Trip to Peru and ran workshops, questionnaires, analysis: Collaboration developed into how to produce the products but also how to test their products to be market valuable e.g. mosquito repellents. Out of three plants, two worked better and one wasn't working at all (which is important to know!).

What Does It Mean to Design Infrastructure?

  • What did we want this lab to be able to do?
    • Workshops and questionnaires
    • How much you educate people based on the info they have with the issues the community is facing
    • Energy concerns to consider, some machines just drain the grid and can't be used. Solar powered, battery powered machines, reducing energy consumption of machines. Many concerns important.
  • Ethical questions
  • How to maintain resources

Case Study: Water Purifier Packets

Use them, change them, source them locally, ingredients found locally, how to distribute them globally.

Funding Models

First few fablabs were NSF funded. Now corporate CSR, regional funding, labor funding (10 different ways). Successful fablabs are heterogeneous with lots of ways of funding. The ones that fail usually just have one sponsor.

Example: DIY Raman spectrometer for water purification (even after purifications still have sulfates and improving that too).

What Does It Mean to Scale Infrastructure?

(Besides a lot of meetings!) What is a reasonable way to design a data collection process about what is needed and how to achieve it.

Back to the Map: Expansion

Timeline of development, cocreation, portable, skin analysis, water testing, biomaterial tech, microscopy.

Initial Results from Boston

How to Confront Local Impact
  • Collab with University of Hamburg. Motivation for how much food can be produced in Boston. Where food waste goes and what Boston produces locally. Make things for yourself locally.
  • Impact directly in the community you're living in.

Hatchspace

Focused on rehabilitation of addicts with woodworking. (Vermont is wood producing state).

Example Course Program

  • All-in session and systemic impact
  • Natural and cultural context
  • Skills and workshop
  • Economic vitality
  • Skills and workshop
  • Co-work session
  • Solutionspalooza

In the Course

Hands-on component (no physical robot exists that can do it) and community component is also important. Inclusion is important. Solving unconscious and institutional biases.

  • 'Fabrica! Lab' — Creating new laboratory spaces for female high school students, courses aimed for women in technology, online advising sessions for females interested in tech.
  • Makerspaces — Access to tools behind closed doors at universities, makes a huge difference for people who don't have the ability to prototype for themselves.
  • Materiom — Fablab affiliated project on organic waste for biomaterials.
  • Fablab León
  • Skylab workshop experiment — How to run a noodle shop out of a fablab (creating food from the community).
  • Academany — Global distributed campus for high school education. Fablab all-in (belonging, impact, community), fab futures (future vocational skills), bio academy (synthetic biology), fabricademy (textiles, fab, bio), fab academy (digital fab apps and implications).

Trade-off Between Impactful and Dangerous

People could be doing bad, but not because doing it with a group people with values.

Questions

Clarification: Adding infrastructure to existing fablab infrastructure to help support specific community needs (not specialized fab labs).

Foundations for Fab Futures

July 27-31, 2026 at Fab Boston 2026.

Useful Documentation

Essential resources for interface and application programming.

Class Page

Interface and Application Programming - MIT Academy

Comprehensive resource covering interface design, application programming, GUI frameworks, embedded UI development, web interfaces for embedded systems, and user interaction patterns. Includes detailed tutorials, code examples, and implementation guides for various interface programming tools and frameworks.

Key Topics

  • Interface Design: User experience principles, interaction patterns, feedback mechanisms
  • Embedded UI: OLED displays, LCD interfaces, character displays
  • Web Interfaces: HTTP servers, REST APIs, WebSockets, real-time data visualization
  • Application Frameworks: GUI toolkits, web frameworks, mobile apps
  • User Input: Buttons, touch interfaces, gesture recognition, voice commands

Additional References

Individual Assignment: Interface & Application Programming

Write an application that interfaces a user with an input &/or output device that you made. This assignment demonstrates three interface applications: (a) a simple button user interface on OLED, (b) a real-time graphical user interface through OLED and Wi-Fi for pulse oximeter readings, and (c) a Wi-Fi grip strength monitor with a mechanical gripper and age-estimation web dashboard.

Part (a): Simple Button User Interface on OLED

A mode-based user interface system that interfaces users with multiple input and output devices through a simple button press interface. The system provides visual feedback on an OLED display and enables navigation between different modes (Menu, Camera, Sensors) using button press patterns. Users interact by pressing a button multiple times to select modes, with visual confirmation displayed on the OLED screen.

Interface Design

The interface uses a mode-based navigation system where button presses trigger mode changes. A single press enters Camera mode, two presses enter Sensors mode, three presses return to Menu, and holding the button activates a flashlight function. The OLED display shows the current menu state and provides clear visual feedback for each mode transition. See Ethical AI Use: Menu System with Modes for AI-assisted development details.

OLED button user interface menu system displaying mode selection options
OLED button user interface menuMenu screen showing available modes: Camera, Sensors, and Menu navigation options with button press instructions.
Button UI demonstrationVideo showing button press interactions navigating through different modes on the OLED display.
First video stream on OLEDInitial camera feed streaming to OLED display using dithering algorithm for monochrome conversion, demonstrating real-time video output interface.
Download Design Files
  • outputs.ino — Button user interface code with mode system
  • camera_pins.h — Camera pin definitions header file
  • outputs.zip — Complete project archive including all dependencies

Part (b): Real-Time Graphical User Interface through OLED and WiFi

A dual-interface health monitoring system that interfaces users with a MAX30102 pulse oximeter sensor through both an OLED display and a WiFi-enabled web interface. The system provides real-time visualization of heart rate (BPM), blood oxygen saturation (SpO2), and raw sensor data (IR and RED LED readings) through multiple output channels. Users can view data locally on the OLED display or remotely via a web browser accessing the ESP32-S3's built-in HTTP server. See Ethical AI Use: I2C Device Not Found for troubleshooting documentation.

Interface Design

The system provides dual-interface access: a local OLED display shows real-time sensor readings (IR, RED, BPM, SpO2) with visual heartbeat indicators, while a WiFi web interface provides comprehensive data visualization including numerical displays and real-time plotting charts. The web interface uses Chart.js for dynamic graph generation and automatically refreshes every 300ms to maintain real-time data updates. Both interfaces run simultaneously, enabling local monitoring and remote access.

Hello World on OLED

Initial OLED display test showing successful I2C communication and display initialization. See Ethical AI Use: Hello World Code for development details.

Hello World display on OLED for Invisible String project showing successful display initialization
Hello World on OLEDInitial OLED test confirming I2C communication and display functionality before implementing sensor interfaces.
Pulse Oximeter Readings on OLED

Real-time pulse oximeter data displayed on OLED showing IR and RED LED readings, heart rate (BPM), and blood oxygen saturation (SpO2) percentage. A heartbeat indicator flashes when a pulse is detected. See Ethical AI Use: MAX30102 Initialization Fix for sensor setup documentation.

Pulse oximeter readings on OLED displaying IR, RED, BPM, and SpO2 values
OLED sensor readings displayReal-time pulse oximeter data showing IR and RED LED values, heart rate (BPM), and blood oxygen saturation (SpO2) with heartbeat indicator.
BPM and SpO2 demonstrationVideo showing real-time heart rate and blood oxygen saturation measurements updating on OLED display with sensor interaction.
Pulse Oximeter Readings on WiFi GUI

WiFi web interface providing remote access to pulse oximeter data through a responsive HTML dashboard. The interface displays real-time numerical values for BPM, SpO2, IR, and RED readings with automatic data refresh. The web server runs on the ESP32-S3, allowing access from any device on the same WiFi network.

WiFi web interface displaying real-time pulse oximeter readings including BPM, SpO2, IR, and RED values
WiFi GUI readings dashboardRemote web interface showing real-time pulse oximeter data accessible from any device on the WiFi network, displaying BPM, SpO2, IR, and RED values with automatic updates.
Pulse Oximeter Plots on WiFi GUI

Enhanced WiFi web interface with real-time plotting capabilities using Chart.js library. The interface displays live line charts for BPM and SpO2 values, showing trends over time with automatic scrolling and data point management. This visualization enables users to observe patterns in heart rate and blood oxygen levels during monitoring sessions.

Serial monitor output showing sensor readings rising on touch interaction
Serial monitor sensor responseSerial output demonstrating sensor readings increase when finger is placed on MAX30102 sensor, showing IR and RED LED response to touch.
WiFi web interface with real-time plotting of BPM and SpO2 data using Chart.js
WiFi GUI with plotting chartsEnhanced web interface displaying real-time line charts for BPM and SpO2 values, showing trends over time with automatic data refresh and chart scrolling.

I2C Device Detection

Successful I2C device detection after fixing power isolation issues. The system now correctly identifies the OLED display at address 0x3C and the MAX30102 sensor at address 0x57. Initial troubleshooting required isolating the RD (red LED) and IRD (infrared LED) ground terminals from the general ground plane to prevent power issues and enable proper sensor operation. 

20:04:48.612 -> Scanning...
20:04:48.644 -> I2C device found at address 0x3C  !
20:04:48.644 -> I2C device found at address 0x57  !
20:04:48.644 -> done
Download Design Files

Part (c): Real-Time GUI through Mechanical Gripper and WiFi

A Wi-Fi-connected grip strength meter that interfaces a user with a mechanical hand gripper, an 80 kg load cell, and an HX711 amplifier. The ESP32-S3 continuously measures grip force, streams it to a web dashboard, and uses a published relationship between handgrip strength and age to display an estimated “physiological age” in real time. The design is inspired by the open-source grip strength meter from NeuroTech Hub at WashU and the associated PLOS ONE paper on grip strength and age trajectories (Syddall et al., 2014), adapted to my load cell and handle geometry.

Mechanically, a custom 3D-printed gripper clamps around a CZL601-type 80 kg bar load cell (sourced from Amazon 80 kg load cell). I imported a 100 kg load cell CAD from GrabCAD, checked the mounting dimensions against the CZL601AC datasheet (online, download), and confirmed that the hole spacing and footprint match the commercial part used here.

Mechanical Design and Fabrication

CAD model of the 3D-printed grip strength base and load cell mounting region
Grip strength base CADTop view of the grip strength base showing the bar load cell pocket, mounting bosses, and handle interface.
Side view CAD of the hand gripper and load cell assembly
Side view of gripper assemblySide profile showing how the fixed base, moving handle, and load cell align along the force axis of the bar sensor.
Full CAD view of the grip strength device with base and handle
Full grip strength assemblyComplete CAD of the base, handle, and load cell, sized for comfortable adult hand placement and full-finger contact.
Close-up of mounting holes and clearances around the load cell in CAD
Load cell mounting holesDetail of the M6 clearance and counterbore geometry used to capture the load cell without constraining bending.
Perspective CAD view of the gripper handle and base
Handle ergonomicsPerspective view of the curved handle designed to distribute pressure across the palm and fingers during maximal grip.
Photo of drilled clearance hole aligned to the printed pilot in the base
Clearance hole verificationPrinted pilot holes used as drill guides to match the metric mounting dimensions from the CZL601AC datasheet.
Photo of the fully printed grip strength device before drilling and assembly
Fresh off the printer3D-printed base and handle components in PLA prior to post-processing and hardware installation.
Printed part clamped for drilling load cell mounting holes
Workholding for accurate drillingThe printed base clamped to the drill press table so the pilot features guide the final clearance holes into the load cell.
Drilling practiceTraining cuts on scrap material to dial in drill press settings and avoid cracking the printed base during final holes.
Final load cell holesDrilling the final M6 clearance holes through the printed base, constrained by the pilot features to preserve alignment.

Electronics and Calibration

Electronics assembly with HX711 breakout, ESP32-S3, and load cell wiring
Electronics stack-upHX711 amplifier breakout from Amazon wired to the ESP32-S3 and 80 kg load cell with short, twisted signal pairs for noise reduction.
Fully assembled grip strength device with load cell, electronics, and handle
Assembled grip strength meterCompleted mechanical and electrical assembly ready for calibration and software bring-up.
Serial Plotter view of load cell readings increasing with grip force
Serial Plotter calibration tracesRaw HX711 output converted to kilograms and visualized in the Arduino Serial Plotter while applying known weights and grip forces.
Web GUI showing grip strength value, estimated age, and scrolling chart
Wi-Fi grip strength dashboardBrowser-based GUI with live grip strength (kg), estimated age, and a Chart.js time series plot of recent squeezes.

Model Used for Age Estimation

The age-estimation logic in the firmware is based on the non-linear, sex-specific grip-strength trajectories reported in Dodds et al., 2014 (PLOS ONE). As shown in Figure 1 of that paper, grip strength rises rapidly through adolescence, peaks around ages 30–40, and then declines non-linearly with age, with different magnitudes for males and females.

Reference grip strength trajectories over the life course from Dodds et al., PLOS ONE 2014
Reference trajectories (Figure 1)Age-dependent grip strength curves for males and females from Dodds et al., 2014, used as the qualitative target for the embedded model.
Simplified quadratic grip strength model fitted to reference data
Quadratic approximation (Table 2-inspired)Simplified male and female trajectories using peak strengths and curvatures chosen to approximate the summary values reported in Table 2 of Dodds et al., 2014.

To reproduce this shape efficiently on the ESP32, the firmware uses inverted quadratic approximations centered at age 35, consistent with the observed peak in the PLOS ONE data. In the forward direction, grip strength is approximated as:

Males: Grip(age) ≈ 52 − 0.0089·(age − 35)2
Females: Grip(age) ≈ 32 − 0.0059·(age − 35)2

On the device, this relationship is analytically inverted so that the measured grip strength can be mapped back to an estimated age:

age = 35 + √((a − Grip)/b), where a is the peak strength (52 kg for males, 32 kg for females) and b is the curvature (0.0089 for males, 0.0059 for females). The firmware clamps grip strength to physiologically meaningful ranges before applying this formula so the square root remains well-defined. 

float ageFromGripMale(float g) {
  float a = 52.0f, b = 0.0089f;
  if (g > a) g = a;
  if (g < 5) g = 5;
  return 35.0f + sqrtf((a - g) / b);
}

float ageFromGripFemale(float g) {
  float a = 32.0f, b = 0.0059f;
  if (g > a) g = a;
  if (g < 4) g = 4;
  return 35.0f + sqrtf((a - g) / b);
}

For full methodological details and original tables/figures, see the open-access paper: Dodds et al., 2014, PLOS ONE (download local PDF). The implementation here is an educational approximation and not intended for clinical or diagnostic use.

End-to-end live demoReal-time demonstration of squeezing the mechanical gripper and watching the Wi-Fi dashboard update grip strength and estimated age on a laptop.

Related Design, Code, and Calibration Resources

User Interface Comparison

Summary of how each interface application connects users with input and output devices.

Application How It Interfaces with the User Input Device(s) Output Device(s)
(a) Button User Interface Button press patterns (single, double, triple press, hold) provide mode selection input. OLED display shows current menu state and mode options. Users receive immediate visual feedback for each interaction. Button (GPIO pin 4) OLED Display (SSD1306, I²C 0x3C)
LED (GPIO pin 3, flashlight mode)
(b) Real-Time GUI (OLED & WiFi) Physical finger placement on MAX30102 sensor provides input. OLED displays real-time sensor data locally. WiFi web interface enables remote monitoring with numerical displays and live plotting charts accessible from any web browser. MAX30102 Pulse Oximeter Sensor (I²C 0x57) OLED Display (SSD1306, I²C 0x3C)
WiFi Web Interface (HTTP Server with Chart.js visualization)
(c) Grip Strength GUI (Load Cell & WiFi) Users squeeze a mechanical hand gripper that transfers force into an 80 kg bar load cell. The ESP32-S3 measures grip strength through the HX711 amplifier and streams results to a WiFi web dashboard that displays live grip force and an estimated physiological age in real time. Mechanical gripper linked to 80 kg load cell (CZL601-type)
HX711 load cell amplifier		 WiFi Web Interface (HTTP Server with Chart.js visualization)
Optional Serial Plotter (for calibration traces)

Group Assignment: Compare as Many Tool Options as Possible

Compare as many tool options as possible for interface and application programming.

General Comparison: Interface & Application Programming Tools

Comprehensive comparison of interface and application programming tools available for embedded systems and IoT development. This analysis covers tools from the MIT Academy Interface & Application Programming class page, evaluating their capabilities, use cases, and trade-offs for different application scenarios.

Embedded Display Interfaces

Tool/Framework Description Pros Cons Best For
OLED (SSD1306) Monochrome OLED displays via I²C Low power, high contrast, simple I²C interface, pixel-level control Limited resolution (128x64), monochrome only, small display size Status displays, sensor readouts, simple menus, embedded dashboards
LCD Character Displays Character-based LCD displays (16x2, 20x4) Simple API, readable in sunlight, low cost Limited to text/characters, no graphics, requires backlight power Text-only interfaces, status messages, debugging output
TFT Color Displays Full-color TFT LCD displays Color graphics, touch support, high resolution High power consumption, complex drivers, larger footprint Rich GUIs, image display, interactive touch interfaces

Web-Based Interfaces

Tool/Framework Description Pros Cons Best For
HTTP Server (ESP32) Built-in HTTP server on ESP32 for web interfaces Remote access, cross-platform (any browser), no app installation, real-time updates Requires WiFi, network dependency, limited to local network without port forwarding Remote monitoring, data visualization, control panels, sensor dashboards
WebSockets Real-time bidirectional communication Low latency, bidirectional, efficient for frequent updates More complex than HTTP, requires persistent connection Real-time streaming, interactive controls, live data feeds
Chart.js JavaScript charting library for web interfaces Beautiful charts, interactive, responsive, easy integration Requires JavaScript, CDN dependency or local hosting Data visualization, time series plots, sensor monitoring dashboards

Mobile & Native App Frameworks

Tool/Framework Description Pros Cons Best For
React Native Cross-platform mobile app framework Cross-platform (iOS/Android), native performance, large ecosystem Complex setup, requires mobile development knowledge Full-featured mobile apps, production deployments
Flutter Google's UI toolkit for cross-platform apps Single codebase, high performance, customizable UI Dart language, larger app size, learning curve Custom mobile interfaces, platform-specific designs
Progressive Web Apps (PWA) Web apps with native-like features No app store, cross-platform, offline capability Limited native API access, browser dependency Web-based mobile interfaces, simple deployment

Specific Comparison: Tools Used in Individual Assignment

Detailed comparison of the specific interface programming tools implemented in this week's individual assignment, evaluating their performance, ease of use, and suitability for embedded health monitoring applications.

OLED Display Interface (Adafruit SSD1306)

Aspect Evaluation
Ease of Implementation Simple I²C interface, well-documented Adafruit library, minimal wiring (SDA, SCL, power, ground)
Display Quality High contrast monochrome display, crisp text rendering, suitable for sensor data visualization
Power Consumption Very low power draw, ideal for battery-powered applications
Limitations 128x64 pixel resolution limits detail, monochrome only, small physical size (0.96" typical)
Best Use Cases Local sensor readouts, menu systems, status indicators, simple data displays

WiFi Web Interface (ESP32 HTTP Server + Chart.js)

Aspect Evaluation
Ease of Implementation ESP32 WebServer library provides straightforward HTTP server, Chart.js CDN integration requires minimal setup
Remote Access Accessible from any device on WiFi network (phone, tablet, computer), no app installation required
Visualization Capabilities Chart.js enables rich data visualization with real-time plotting, smooth animations, and interactive features
Real-Time Updates JSON API endpoint provides efficient data transfer, 300ms refresh rate maintains responsive feel
Limitations Requires WiFi network, limited to local network without additional configuration, power consumption higher than OLED alone
Best Use Cases Remote monitoring, data logging visualization, multi-user access, professional dashboards

Button Input Interface

Aspect Evaluation
Implementation Approach Digital GPIO reading with debouncing, press pattern detection (single/double/triple/hold) enables mode navigation
User Experience Intuitive press patterns, immediate visual feedback on OLED, no complex UI navigation required
Reliability Hardware debouncing with INPUT_PULLUP, timeout-based pattern recognition prevents accidental triggers
Limitations Limited to single button interaction, pattern learning required, less flexible than touchscreen interfaces
Best Use Cases Simple mode selection, menu navigation, embedded system controls, low-cost input solutions

Comparison Summary

The combination of OLED display and WiFi web interface provides complementary benefits: OLED offers immediate local feedback with minimal latency and power consumption, while the WiFi interface enables rich visualization and remote access. The button-based input provides an intuitive, low-cost navigation method suitable for embedded systems. Together, these tools create a robust interface system that supports both local and remote interaction with sensor data.

Design Files

Design files and code documentation for interface and application programming projects.

ESP32-S3 Development Board and Pinouts

Code files for ESP32-S3 development board interfaces including I2C scanning, OLED display control, and button-based user interface systems. See Week 4 documentation for board design and Week 8 documentation for pinout configurations.

I2C Scanner (i2cscan_generic.ino)

Utility code for scanning and detecting I2C devices on the bus, essential for troubleshooting connection issues.

How the Code Works (Pseudocode)
SETUP:
  Initialize I2C bus
  Initialize Serial communication
  Print "I2C Scanner" message

LOOP:
  Print "Scanning..." message
  Initialize device counter to 0
  
  FOR each address from 1 to 126:
    Begin I2C transmission to address
    Check transmission result
    
    IF transmission successful (error == 0):
      Print device found at address (hex format)
      Increment device counter
    ELSE IF unknown error (error == 4):
      Print unknown error at address
    
  IF no devices found:
    Print "No I2C devices found"
  ELSE:
    Print "done"
  
  Wait 5 seconds before next scan
Key Features
  • Scans all 127 possible I2C addresses (0x01-0x7E)
  • Detects and reports connected devices with hex address format
  • Handles multiple error conditions (device not found, unknown errors)
  • Continuous scanning mode with 5-second intervals
  • Compatible with any I2C bus configuration (Wire, Wire1, etc.)
What You Need to Know
  • I2C Address Range: Valid addresses are 0x08-0x77 (8-119 decimal); addresses 0x00-0x07 and 0x78-0x7F are reserved
  • Common Addresses: OLED displays typically use 0x3C or 0x3D; sensors vary (MAX30102 uses 0x57)
  • Troubleshooting: If no devices found, check wiring (SDA, SCL, power, ground), verify pull-up resistors, confirm device power
  • Usage: Run this before connecting other devices to verify I2C bus is working correctly
Download: i2cscan_generic.ino

Hello World OLED Display (hello_world.ino)

Basic OLED display test code that initializes the display and shows "Hello World" text, confirming I2C communication and display functionality.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial communication at 115200 baud
  Wait 500ms for Serial to stabilize
  
  Initialize I2C bus with SDA pin 5, SCL pin 6
  Print "Starting..." message
  
  Attempt to initialize OLED display:
    IF initialization fails:
      Print "OLED not found" error
      Enter infinite loop (halt)
  
  Clear display buffer
  Set text size to 2
  Set text color to white
  Set cursor position to (0, 20)
  Print "Hello" line
  Print "World!" line
  Update display (send buffer to hardware)

LOOP:
  Empty (runs once, then waits)
Key Features
  • Simple OLED initialization and text display
  • Custom I2C pin configuration for XIAO ESP32-S3 (SDA=5, SCL=6)
  • Error handling with infinite loop if display not found
  • Text size and cursor positioning for centered display
  • One-time display update (no loop refresh needed for static text)
What You Need to Know
  • I2C Pin Configuration: XIAO ESP32-S3 uses pins 5 (SDA) and 6 (SCL) by default; verify your board's pinout
  • Display Address: SSD1306 OLED typically uses address 0x3C; some variants use 0x3D
  • Display Update: Must call display.display() to send buffer to hardware; drawing functions only modify buffer
  • Testing: Use this as first test after connecting OLED to verify wiring and I2C communication before adding complex features
  • Libraries Required: Adafruit_GFX, Adafruit_SSD1306, Wire
Download: hello_world.ino

Button User Interface (outputs.ino)

Mode-based navigation system using button press patterns (single, double, triple, hold) to control multiple output devices including OLED display, camera, sensors, and LED flashlight.

How the Code Works (Pseudocode)
SETUP:
  Initialize OLED display
  Initialize camera module
  Initialize sensors (MPU6050, HX711)
  Initialize button pin (INPUT_PULLUP)
  Initialize LED pin (OUTPUT)
  Set current mode to MENU
  Display menu screen

LOOP:
  Read button state
  
  IF button pressed:
    Record press start time
    Start press detection timer
  
  IF button released:
    Calculate press duration
    IF duration > HOLD_THRESHOLD:
      Activate flashlight mode
    ELSE:
      Increment press count
      Reset press timeout timer
  
  IF press timeout exceeded:
    Process accumulated press count:
      IF press count == 1: Switch to CAMERA mode
      IF press count == 2: Switch to SENSORS mode
      IF press count == 3: Switch to MENU mode
    Reset press count
  
  IF current mode == MENU:
    Display menu screen (button instructions)
  
  IF current mode == CAMERA:
    Capture camera frame
    Process image with dithering algorithm
    Display on OLED
    Run Edge Impulse inference (optional)
    Overlay results on display
  
  IF current mode == SENSORS:
    Read accelerometer/gyroscope data
    Read load cell data
    Display sensor readings on OLED
  
  Update display
Key Features
  • Press pattern detection: single (1x), double (2x), triple (3x), and hold
  • Mode-based navigation system (Menu, Camera, Sensors)
  • Button debouncing with timeout-based pattern recognition
  • Floyd-Steinberg dithering for camera-to-OLED video display
  • Edge Impulse AI inference integration for face detection
  • Multi-sensor integration (MPU6050 accelerometer/gyro, HX711 load cell)
  • Flashlight mode activated by button hold
What You Need to Know
  • Button Wiring: Use INPUT_PULLUP mode (button connects pin to GND when pressed, internal pull-up to 3.3V)
  • Press Detection: Press count is accumulated until timeout (1 second); longer timeout allows slower multiple presses
  • Mode Switching: Each mode has distinct display update logic; ensure proper initialization in setup()
  • Camera Performance: Video streaming to OLED requires significant processing; frame rate depends on resolution and dithering complexity
  • Dependencies: Requires camera_pins.h header file with XIAO ESP32-S3 camera pin definitions; see Ethical AI Use for development details
  • Sensor Conflicts: Code uses preprocessor directives to resolve sensor_t type conflict between ESP32 camera and Adafruit MPU6050 libraries
Download: outputs.ino | camera_pins.h | outputs.zip (complete project)

Grip Strength Monitor (Load Cell + WiFi GUI)

Design files and firmware for a Wi-Fi-enabled grip strength meter built around an 80 kg bar load cell, HX711 amplifier, and ESP32-S3. The mechanical design was informed by the open-source grip strength meter from NeuroTech Hub and validated against the CZL601AC bar load cell datasheet (online, download).

Mechanical Design Files (3D-Printed Components)

  • Base.3mf — main chassis that captures the bar load cell and anchors the fixed side of the gripper.
  • Case.3mf — protective enclosure for the ESP32-S3 and HX711 amplifier with cable strain relief.
  • Handle.3mf — curved grip handle that transfers hand force into the free end of the load cell.
  • Calibration Print.3mf — small test piece used to verify hole diameters and load cell clearances before printing the full assembly.

All parts were printed in PLA with high infill in the load paths to minimize creep and flex during repeated maximal grip trials.

Basic HX711 Reader (loadcell_simple.ino)

Minimal firmware to bring up the HX711 amplifier and read calibrated weight values over Serial for debugging and calibration.

How the Code Works (Pseudocode)
SETUP:
  Configure HX711 data and clock pins (DT=A1, SCK=A0)
  Initialize Serial at 115200 baud
  Begin HX711 with DT/SCK pins
  Set calibration factor (grams per ADC unit)
  Tare the scale so current load is zero

LOOP (every 200 ms):
  If HX711 is ready:
    Read averaged weight using get_units(4)
    Print "weight:<value>" to Serial for Serial Plotter
  Else:
    Print "HX711 not ready" for troubleshooting
Key Features
  • Simple initialization of the HX711 on analog pins A0/A1.
  • Configurable calibration factor for mapping counts to grams or kilograms.
  • Timed reads (200 ms) to keep Serial output manageable and Plotter-friendly.
  • Graceful handling of HX711 not-ready states.
What You Need to Know
  • Use for initial bring-up: Run this first when wiring the HX711 and load cell to confirm clean, stable readings.
  • Calibration factor: Determined experimentally by hanging known weights and adjusting until readings match; see the calibration notes in Calibration Chat.
  • Serial Plotter: The weight:<value> format is convenient for quickly visualizing changes while squeezing the handle.
Download: loadcell_simple.ino

Serial Plotter-Friendly Reader (loadcell_plot.ino)

Refined HX711 reader tuned for the Arduino Serial Plotter: it outputs a single numeric value per line for clean plotting of grip strength over time.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial at 115200 baud
  Initialize HX711 on DT=A1, SCK=A0
  Set calibration factor
  Tare the scale
  Optionally print debug messages when DEBUG=1

LOOP (every 200 ms):
  If HX711 is ready:
    Read filtered weight with get_units(4)
    Optionally print labeled debug text
    Print only the numeric weight to Serial for the Plotter
  Else:
    Optionally print "not ready" debug text
    Print 0 so the plotted line continues gracefully
Key Features
  • DEBUG toggle: Compile-time switch to enable/disable human-readable logs without breaking the Serial Plotter format.
  • Clean “one number per line” output for multi-trial grip testing in the Serial Plotter.
  • Automatic zero output when the HX711 is not ready to keep the time axis continuous.
  • Shared pinout and calibration approach with loadcell_simple.ino for easy swapping.
What You Need to Know
  • Use this sketch to tune calibration and visualize grip curves without any GUI overhead.
  • When collecting data for analysis, keep DEBUG set to 0 so the output is a pure numeric stream.
  • The sample interval (200 ms) gives a smooth trace while keeping file sizes reasonable for multi-second squeezes.
Download: loadcell_plot.ino

WiFi Grip Strength GUI (loadcell_gui.ino)

Full application firmware that exposes grip strength and an estimated age over Wi-Fi using an HTTP server and a Chart.js web dashboard.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial
  Initialize HX711 (pins, calibration factor, tare)
  Connect ESP32-S3 to WiFi (MIT network in this build)
  Start WebServer on port 80
  Register handlers:
    "/"        → serve HTML+JS GUI page from PROGMEM
    "/metrics" → serve JSON with current grip and age

LOOP:
  Handle incoming HTTP clients
  Every 200 ms:
    If HX711 is ready:
      Read smoothed grip strength (kg) via get_units(3)
      Clamp negative values to zero
      Store in global gripStrength

AGE ESTIMATION HELPERS:
  ageFromGripMale(g):
    Clamp g to plausible range
    Compute age using inverted quadratic fit derived from normative data
  ageFromGripFemale(g):
    Same structure with female-specific parameters

HTTP /metrics ENDPOINT:
  Read "sex" query parameter (default "male")
  Compute ageEstimate = ageFromGripMale/ageFromGripFemale(gripStrength)
  Return JSON:
    {"grip": <kg>, "age": <years>}

CLIENT-SIDE GUI (HTML + JS):
  Render dark-themed dashboard with:
    - Sex toggle buttons (male/female)
    - Numeric grip strength (kg) and age
    - Scrolling Chart.js line plot of recent grip values
  Poll /metrics every 200 ms and update DOM + chart
Key Features
  • Embedded HTML/JS dashboard served directly from the ESP32-S3 using PROGMEM.
  • Real-time grip strength plot using Chart.js with ~120 recent samples.
  • Simple sex toggle that switches between male and female age-estimation curves.
  • JSON API at /metrics for future extensions (e.g., logging clients).
What You Need to Know
  • WiFi credentials: Update the ssid and password constants to match your network.
  • Normative model: The age equations are simplified fits inspired by the grip-strength trajectories reported in Syddall et al., PLOS ONE 2014 and are for educational visualization only, not clinical use.
  • Browser requirements: Any modern browser with JavaScript and network access can connect to the ESP32-S3’s IP address to view the dashboard.
  • Development log: The full iterative design of this sketch is captured in the ChatGPT transcript: Grip Strength Monitor Code Chat.
Download: loadcell_gui.ino

Invisible String Chain of Hearts

Code files for the Invisible String pulse oximeter interface system, providing real-time health monitoring through OLED display and WiFi web interface. See Week 11 PCB design documentation for hardware details.

OLED GUI for Pulse Oximeter (pulse_vo2_reads_fixing.ino)

Local OLED display interface showing real-time pulse oximeter readings including heart rate (BPM), blood oxygen saturation (SpO2), and raw IR/RED LED sensor values.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial communication
  Initialize I2C bus (SDA=5, SCL=6) at 400kHz
  Initialize MAX30102 sensor
  Configure sensor:
    Set LED mode to RED + IR
    Set ADC range to 16384
    Set sample rate to 100 Hz
    Set pulse width to 411 μs
    Set LED brightness to medium (0x3F)
  Initialize OLED display
  Clear and prepare display

LOOP:
  Read IR and RED LED values from sensor
  
  Heart Rate Detection:
    Check for heartbeat in IR signal using peak detection
    IF heartbeat detected:
      Calculate time since last beat
      Calculate BPM = 60 / (time_delta / 1000)
      Set beat flag for visual indicator
      Update last beat timestamp
  
  SpO2 Calculation (every 300ms):
    Add IR and RED values to circular buffer
    IF buffer has 50 samples:
      Calculate DC components (average)
      Calculate AC components (RMS)
      Calculate R ratio = (AC_RED/DC_RED) / (AC_IR/DC_IR)
      Estimate SpO2 = 110 - 25 * R
      Clamp SpO2 to 70-100% range
  
  Serial Output:
    Print IR, RED, BPM for Serial Plotter visualization
  
  OLED Display Update:
    Clear display buffer
    Display IR value (small text)
    Display RED value (small text)
    Display BPM value (large text, size 2)
    Display SpO2 percentage (small text)
    IF beat detected: Draw heartbeat indicator dot
    Update display hardware
  
  Delay 20ms (50 Hz update rate)
Key Features
  • Real-time heart rate detection using peak detection algorithm on IR signal
  • SpO2 calculation using ratio-of-ratios method with DC/AC component analysis
  • Circular buffer system for storing 50 samples of IR/RED data
  • Visual heartbeat indicator (flashing dot) when pulse detected
  • Dual output: OLED display and Serial Plotter for real-time waveform visualization
  • Optimized sensor configuration for reliable readings (100 Hz sample rate, medium brightness)
What You Need to Know
  • Sensor Placement: Finger must cover sensor completely; proper contact ensures accurate readings
  • I2C Address: MAX30102 uses address 0x57; verify with I2C scanner if sensor not detected
  • Ground Isolation: RD and IRD pins must be isolated from main ground plane to prevent power issues (see Week 11 PCB design)
  • SpO2 Accuracy: Calculation provides estimation; medical-grade accuracy requires calibration and FDA-approved algorithms
  • Buffer Size: 50-sample buffer provides balance between calculation accuracy and response time
  • Libraries Required: MAX30105 (SparkFun library), Adafruit_GFX, Adafruit_SSD1306, heartRate.h (beat detection)
  • Troubleshooting: If sensor not detected, check power isolation, I2C wiring, and sensor initialization order
Download: pulse_vo2_reads_fixing.ino

WiFi Readings GUI (pulse_gui.ino)

WiFi-enabled web interface providing remote access to pulse oximeter data through HTTP server with JSON API endpoint for real-time data updates.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial communication
  Initialize I2C bus
  Initialize MAX30102 sensor
  Configure sensor (LED mode, sample rate, pulse width)
  Initialize OLED display
  Initialize WiFi:
    Connect to network (SSID, password)
    Wait for connection
    Print IP address
  Initialize HTTP server:
    Route "/" → serve GUI HTML page
    Route "/gui" → serve GUI HTML page
    Route "/metrics" → serve JSON data
  Start web server

LOOP:
  Handle incoming HTTP client requests
  
  Read IR and RED values from sensor
  
  Heart Rate Calculation:
    Check for heartbeat in IR signal
    IF heartbeat detected:
      Calculate BPM from time delta
      Update global BPM variable
  
  SpO2 Calculation:
    Add IR/RED to circular buffer
    IF buffer full (50 samples):
      Calculate SpO2 using ratio-of-ratios
      Update global SpO2 variable
  
  Update global variables (g_ir, g_red, g_bpm, g_spo2)
  
  OLED Display Update:
    Display IR, RED, BPM, SpO2 values
    Update display hardware
Key Features
  • Dual interface: OLED display (local) and WiFi web interface (remote)
  • HTTP server with embedded HTML page stored in PROGMEM
  • JSON API endpoint (/metrics) for real-time data retrieval
  • Automatic WiFi connection with connection status feedback
  • IP address display for easy access
  • Simultaneous sensor reading and web server operation
  • Global variable system for data sharing between sensor reading and HTTP handlers
What You Need to Know
  • WiFi Configuration: Update SSID and password in code; for MIT network, use generated device password from wifi.mit.edu
  • Network Access: Web interface accessible only from devices on same WiFi network; IP address printed to Serial Monitor
  • HTML Storage: GUI HTML page stored in PROGMEM (program memory) to conserve RAM; use PROGMEM for large strings
  • Server Handling: Must call server.handleClient() frequently in loop() for responsive web interface
  • Data Refresh: Client-side JavaScript polls /metrics endpoint every 300ms for real-time updates
  • Power Consumption: WiFi significantly increases power draw compared to OLED-only mode; consider power management for battery operation
  • Libraries Required: WiFi, WebServer, MAX30105, Adafruit_SSD1306
Download: pulse_gui.ino

WiFi Plot GUI (pulse_gui_2.ino)

Enhanced WiFi web interface with real-time plotting capabilities using Chart.js library, displaying live line charts for BPM and SpO2 values with automatic scrolling and data management.

How the Code Works (Pseudocode)
SETUP:
  (Same as pulse_gui.ino)
  Initialize WiFi, sensor, OLED, HTTP server

LOOP:
  (Same as pulse_gui.ino)
  Handle HTTP requests, read sensor, calculate BPM/SpO2

GUI HTML PAGE (embedded in PROGMEM):
  Load Chart.js library from CDN
  Create two Chart.js line chart instances:
    - BPM chart (y-axis: 40-160 BPM)
    - SpO2 chart (y-axis: 70-100%)
  Initialize data arrays for each chart
  
  JavaScript Update Function (runs every 300ms):
    Fetch JSON data from /metrics endpoint
    Update numerical displays (BPM, SpO2, IR, RED)
    Add new BPM value to BPM data array
    Add new SpO2 value to SpO2 data array
    IF array length > maxPoints (100):
      Remove oldest value (shift)
    Update chart labels (array indices)
    Update chart datasets with new data
    Call chart.update() to refresh display
  
  Set interval to call update function every 300ms
Key Features
  • Real-time line chart visualization using Chart.js library
  • Dual chart display: BPM and SpO2 trends over time
  • Automatic data scrolling: maintains 100 most recent data points
  • Numerical displays alongside charts for precise values
  • Responsive design with dark theme for OLED-style aesthetic
  • Automatic chart scaling with fixed y-axis ranges for consistent visualization
  • CDN-based Chart.js loading for minimal memory footprint
What You Need to Know
  • Chart.js CDN: Library loaded from jsdelivr.net CDN; requires internet connection on client device
  • Data Management: Arrays limited to 100 points to prevent memory overflow; older data automatically discarded
  • Update Rate: 300ms refresh rate balances responsiveness with server load; adjust based on network conditions
  • Chart Configuration: Y-axis ranges fixed (BPM: 40-160, SpO2: 70-100) for consistent scaling; modify in JavaScript if needed
  • Browser Compatibility: Requires modern browser with JavaScript enabled; tested on Chrome, Firefox, Safari
  • Performance: Chart updates are lightweight; multiple simultaneous clients may impact ESP32 performance
  • Offline Operation: Charts won't load if client device lacks internet (Chart.js CDN unavailable); consider local hosting for offline use
Download: pulse_gui_2.ino

Reflections & Learnings

Key insights and learnings from working with interface and application programming.

Contributions

Acknowledgements and team roles for interface and application programming work.

Ethical AI Use

Transparent documentation of AI assistance used in this week's interface and application programming work.

This section documents all AI assistance used during Week 12 interface and application programming work. ChatGPT was used for code development, troubleshooting, and technical guidance. All transcripts are linked below for transparency.

Menu System with Modes

AI assistance for developing the button-based menu system with mode navigation (Menu, Camera, Sensors) using press pattern detection. The conversation covered button debouncing, press pattern recognition, mode state management, and OLED menu display design.

Related to: Part (a): Simple Button User Interface on OLED

View ChatGPT Transcript: Menu System with Modes

I2C Device Not Found

Troubleshooting session for I2C device detection issues with MAX30102 pulse oximeter sensor. The conversation addressed power isolation problems, I2C wiring verification, sensor initialization order, and ground plane isolation requirements for accurate sensor operation.

Related to: Part (b): Real-Time Graphical User Interface through OLED and WiFi

View ChatGPT Transcript: I2C Device Not Found

Hello World Code

Development assistance for creating the initial OLED "Hello World" test program. The conversation covered I2C initialization, OLED display library setup, text rendering, and basic display configuration for XIAO ESP32-S3 development board.

Related to: Part (b): Real-Time Graphical User Interface through OLED and WiFi (initial OLED test)

View ChatGPT Transcript: Hello World Code

MAX30102 Initialization Fix

Technical guidance for fixing MAX30102 pulse oximeter sensor initialization issues. The conversation addressed sensor configuration parameters, LED brightness settings, sample rate optimization, initialization sequence requirements, and troubleshooting sensor communication problems.

Related to: Part (b): Real-Time Graphical User Interface through OLED and WiFi (pulse oximeter readings)

View ChatGPT Transcript: MAX30102 Initialization Fix

Grip Strength Monitor Code Design

Code-focused assistance for designing and refining the WiFi grip strength monitor firmware. The conversation covered HX711 bring-up, load cell pin mapping, Serial Plotter debugging sketches, the ESP32-S3 HTTP server, the Chart.js dashboard, and the age-estimation helpers used in loadcell_simple.ino, loadcell_plot.ino, and loadcell_gui.ino.

Related to: Part (c): Real-Time GUI through Mechanical Gripper and WiFi and Grip Strength Monitor design files

View ChatGPT Transcript: Grip Strength Monitor Code

Grip Strength Calibration & Scaling

Calibration-focused assistance for mapping HX711 counts to kilograms and validating the grip strength readings. The discussion walked through using the Serial Plotter, collecting reference weights, tuning the calibration factor, and sanity-checking the age-estimation model derived from normative grip strength data.

Related to: Part (c): Real-Time GUI through Mechanical Gripper and WiFi calibration workflow and the Grip Strength Monitor sketches.

View ChatGPT Transcript: Grip Strength Calibration

Grip Strength Monitor – Cursor Transcript

Full Cursor AI transcript focused on organizing the grip strength monitor section: structuring Part (c), integrating design files, embedding images and videos, and aligning captions, external references, and the Ethical AI Use documentation for the load cell project.

Related to: Part (c): Real-Time GUI through Mechanical Gripper and WiFi, Grip Strength Monitor design files, and this Ethical AI Use section.

View HTML Transcript Download Markdown Transcript

Week 12 Project Documentation

Complete Cursor AI transcript for Week 12 interface and application programming project documentation. This comprehensive conversation covers the creation and population of the Week 12 HTML page, including Individual Assignment sections (button UI and WiFi GUI), Group Assignment tool comparisons, Design Files documentation with pseudocode, and Ethical AI Use section organization. The transcript demonstrates the collaborative process of building professional documentation with structured content, embedded media, and comprehensive code documentation.

Related to: Complete Week 12 documentation including Individual Assignment, Group Assignment, Design Files, and overall page structure

View HTML Transcript Download Markdown Transcript

Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License

``` Updating the Useful Documentation section: Finding and updating the Useful Documentation section: Replacing the Useful Documentation section: ```html Week 13 · Wildcard Week
← Back to Home
[Profile Image Placeholder]

Week 13

Wildcard Week

Week Highlights

Key captures from the group and individual assignments with links to their sections.

Button User Interface on OLED

OLED button user interface menu system

Hello World on OLED

Hello World display on OLED for Invisible String project

Pulse Oximeter Readings

Pulse oximeter readings showing IR, RED, and BPM values

Wi-Fi GUI Readings

Wi-Fi web interface displaying real-time pulse oximeter readings

Wi-Fi GUI Plots

Wi-Fi web interface with real-time plotting of pulse oximeter data

OLED Video Stream Demo

Grip Strength Gripper

CAD rendering of the full grip strength device with base, handle, and load cell Photo of the fully assembled grip strength device with electronics and handle

Load Cell Calibration Plot

Serial Plotter screenshot showing load cell readings rising with grip force

Grip Strength WiFi GUI

Table of Contents

Course Content

Training & Documentation

Assignments & Projects

Wildcard Week

This week focuses on exploring digital fabrication processes not covered in previous assignments. We'll design and produce something using computer-aided design and manufacturing, documenting requirements and including everything necessary for reproduction. This week also includes reflection on the impact and purpose of making (almost) anything.

Exploring new digital fabrication processes
Designing and producing with CAD/CAM
Understanding the impact and purpose of fabrication labs

This Week's Goals

  • Explore New Processes
    Design and produce something with a digital process not covered in other assignments
  • Complete Documentation
    Document requirements and include everything necessary to reproduce the project
  • Reflect on Impact
    Understand the purpose and impact of fabrication labs and making

Assignments

  • Group Assignment
    Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment
  • Individual Assignment
    Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment, documenting the requirements that your assignment meets, and including everything necessary to reproduce it

Tools & Materials

  • Carvera (CNC Mill) — Edge cuts and hole machining
  • Fiber Laser Cutter (xTool F2 Ultra) — PCB engraving
  • PCB Design Software (KiCad) — Board layout and design
  • ATtiny1626 Microcontroller — Target device for development board
  • RP2354A Microcontroller — Complex board design

Lecture Notes

Week 13 lecture covering major announcements, week 12 review, system integration reminders, and wildcard week preview.

Theme of the Week

'Step away from the panic'

Major Announcements

  • Subject evaluation: Required for funding the class. Provides feedback to the institute about the class. Important for future students if you care about successors in the class.
  • Calendar alarm: Wildcard week and recitation on why make (almost) anything: impact. Friday is cutoff for assignments and orders (10s of dollars per person from inventory).
  • Final presentation/final exam: Combining multiple additive and subtractive processes (not just design a board and 3D print a case). Goal is system integration out of parts. Final exam criteria:
    • Did you integrate and design a complete system?
    • Can you demo a final project? Here is the cool thing I did and here is how it works.
    • Make a final project video! (helps but not required)
    Focus on well-integrated device!

Review of Week 12 User Interfaces

  • Claire Wang: Music play and Windows 3.1 interface works!
  • Ryan Hoffman: DRV8251A discussion, heat sinks, breakout boards. Wildcards with waterjetting, EDM, multi-axis machining, laser cutting metal. Class in the spring on nature of mathematical modeling.
  • Srikanth Nadhamuni: Background and experience to visiting fellow at MIT. Raspberry Pi W for WiFi, n8n for cloud LLM data crunching. Software: Node.js, MCP bridge server with n8n based on bridge connected to device (NGV tunnel). All set! Fantastic experience, haven't worked so hard in a very long time and learning a lot of new things. Hope to take forward and build other systems. The whole culture of doing and trying yourself fascinating, especially with failing a number of times until you figure it out. Maybe set one up at an IIT in India or AI centers of excellence with education ministry into the Indian education system (see fablabkerala.in or vigyam ashram).
  • Ray Song: Not here.
  • Tyler Jensen (Lincoln Lab, Group 81): Final project discussion (nylon printer). Week 13: Easy for web serial interface for XIAO! Web server to TFT (I think I forgot to load the camera pins with my code for it).
  • Aditi Ramakrishnan: Sloan MBA and strategy consulting background. Discrete time filter (FFT is blown) in skimage.filters — make a bandpass filter, then run a series of these filters, much less computing only adds and multiplies for filtering in realtime.
  • Alexandros Gravalos: Not here.
  • Edward Chen: Check final watch project by Gulati into watch form factor. Clear print on the Form Labs printer, 0.1. Kaman filter for sensor fusion (in the spring class). For position — LSM6DSV16X from input devices. Acceleration at 7 kHz (at audio frequency).

Show and Tell

  • Handle to sensor WiFi user interface
  • Plug to audio LLM user interface

System Integration Reminders

  • Mount electronics
  • Strain relief the final projects

Preview for Wildcard Week

Assignment: Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment.

Recitation Notes: Why Make (Almost) Anything

Recitation exploring the purpose, impact, and scaling of fabrication labs and making infrastructure.

Map of Fab Labs

Why Make a Fab Lab?

  • Used to create a community
  • Building things for the community
  • Sustainability
  • Prototyping quickly

How Impact?

  • How to make spaces: How to measure impact. What is important about fab:
    • Fablabs in cities vs rural areas: The ability to decide their own futures and change their lives fundamentally. 'Safecast revolutionized citizen science' e.g. radiation map.
    • Bringing back manufacturing: Reducing reliance on supply chains.
    • Rural sustainability: Working with indigenous communities on creating technologies themselves at scale and measure their usefulness and efficacy to preserve their ancestral knowledge:
      • How to establish labs there
      • How to make sure the labs get used
    • Hygiene technologies with Proctor and Gamble: Highly commercial. Lots of plastic waste. How can we change how they produce? How to make their products get there through resellers?
    • Trip to Peru and ran workshops, questionnaires, analysis: Collaboration developed into how to produce the products but also how to test their products to be market valuable e.g. mosquito repellents. Out of three plants, two worked better and one wasn't working at all (which is important to know!).

What Does It Mean to Design Infrastructure?

  • What did we want this lab to be able to do?
    • Workshops and questionnaires
    • How much you educate people based on the info they have with the issues the community is facing
    • Energy concerns to consider, some machines just drain the grid and can't be used. Solar powered, battery powered machines, reducing energy consumption of machines. Many concerns important.
  • Ethical questions
  • How to maintain resources

Case Study: Water Purifier Packets

Use them, change them, source them locally, ingredients found locally, how to distribute them globally.

Funding Models

First few fablabs were NSF funded. Now corporate CSR, regional funding, labor funding (10 different ways). Successful fablabs are heterogeneous with lots of ways of funding. The ones that fail usually just have one sponsor.

Example: DIY Raman spectrometer for water purification (even after purifications still have sulfates and improving that too).

What Does It Mean to Scale Infrastructure?

(Besides a lot of meetings!) What is a reasonable way to design a data collection process about what is needed and how to achieve it.

Back to the Map: Expansion

Timeline of development, cocreation, portable, skin analysis, water testing, biomaterial tech, microscopy.

Initial Results from Boston

How to Confront Local Impact
  • Collab with University of Hamburg. Motivation for how much food can be produced in Boston. Where food waste goes and what Boston produces locally. Make things for yourself locally.
  • Impact directly in the community you're living in.

Hatchspace

Focused on rehabilitation of addicts with woodworking. (Vermont is wood producing state).

Example Course Program

  • All-in session and systemic impact
  • Natural and cultural context
  • Skills and workshop
  • Economic vitality
  • Skills and workshop
  • Co-work session
  • Solutionspalooza

In the Course

Hands-on component (no physical robot exists that can do it) and community component is also important. Inclusion is important. Solving unconscious and institutional biases.

  • 'Fabrica! Lab' — Creating new laboratory spaces for female high school students, courses aimed for women in technology, online advising sessions for females interested in tech.
  • Makerspaces — Access to tools behind closed doors at universities, makes a huge difference for people who don't have the ability to prototype for themselves.
  • Materiom — Fablab affiliated project on organic waste for biomaterials.
  • Fablab León
  • Skylab workshop experiment — How to run a noodle shop out of a fablab (creating food from the community).
  • Academany — Global distributed campus for high school education. Fablab all-in (belonging, impact, community), fab futures (future vocational skills), bio academy (synthetic biology), fabricademy (textiles, fab, bio), fab academy (digital fab apps and implications).

Trade-off Between Impactful and Dangerous

People could be doing bad, but not because doing it with a group people with values.

Questions

Clarification: Adding infrastructure to existing fablab infrastructure to help support specific community needs (not specialized fab labs).

Foundations for Fab Futures

July 27-31, 2026 at Fab Boston 2026.

Useful Documentation

Essential resources for wildcard week digital fabrication processes and PCB design.

Class Page

Wildcard Week - MIT Academy

Comprehensive resource covering wildcard week assignment requirements and possibilities including grinding, multi-axis machining, electrical discharge machining, waterjet cutting, flatbed cutting, plasma cutting, laser metal cutting, laser micromachining, welding, molding and casting, folding, robotics, electronics, embedded programming, food, materials, biotechnology, textiles, and composites.

Key Topics

  • Machining: Grinding, multi-axis machining, electrical discharge machining, waterjet cutting, plasma cutting, laser metal cutting, laser micromachining
  • Molding & Casting: Vacuum forming, rotocasting
  • Folding: Mathematics, form and function, kirigami
  • Robotics: Arms, construction, soft actuation pneumatic inflatable
  • Electronics: Pick and place, programmable logic
  • Embedded Programming: Machine learning, machine vision
  • Textiles: Fiber processes, knitting, embroidery (PEmbroider, Ink/Stitch), Fabricademy
  • Composites: Various composite fabrication techniques

ATtiny1626 Development Board References

Embedded Programming Course Resources

Course resources for embedded programming with ATtiny412 microcontroller examples:

Embedded Programming - MIT Academy

ATtiny412 Echo Example Image

Individual Assignment: Interface & Application Programming

Write an application that interfaces a user with an input &/or output device that you made. This assignment demonstrates three interface applications: (a) a simple button user interface on OLED, (b) a real-time graphical user interface through OLED and Wi-Fi for pulse oximeter readings, and (c) a Wi-Fi grip strength monitor with a mechanical gripper and age-estimation web dashboard.

Part (a): Simple Button User Interface on OLED

A mode-based user interface system that interfaces users with multiple input and output devices through a simple button press interface. The system provides visual feedback on an OLED display and enables navigation between different modes (Menu, Camera, Sensors) using button press patterns. Users interact by pressing a button multiple times to select modes, with visual confirmation displayed on the OLED screen.

Interface Design

The interface uses a mode-based navigation system where button presses trigger mode changes. A single press enters Camera mode, two presses enter Sensors mode, three presses return to Menu, and holding the button activates a flashlight function. The OLED display shows the current menu state and provides clear visual feedback for each mode transition. See Ethical AI Use: Menu System with Modes for AI-assisted development details.

OLED button user interface menu system displaying mode selection options
OLED button user interface menuMenu screen showing available modes: Camera, Sensors, and Menu navigation options with button press instructions.
Button UI demonstrationVideo showing button press interactions navigating through different modes on the OLED display.
First video stream on OLEDInitial camera feed streaming to OLED display using dithering algorithm for monochrome conversion, demonstrating real-time video output interface.
Download Design Files
  • outputs.ino — Button user interface code with mode system
  • camera_pins.h — Camera pin definitions header file
  • outputs.zip — Complete project archive including all dependencies

Part (b): Real-Time Graphical User Interface through OLED and WiFi

A dual-interface health monitoring system that interfaces users with a MAX30102 pulse oximeter sensor through both an OLED display and a WiFi-enabled web interface. The system provides real-time visualization of heart rate (BPM), blood oxygen saturation (SpO2), and raw sensor data (IR and RED LED readings) through multiple output channels. Users can view data locally on the OLED display or remotely via a web browser accessing the ESP32-S3's built-in HTTP server. See Ethical AI Use: I2C Device Not Found for troubleshooting documentation.

Interface Design

The system provides dual-interface access: a local OLED display shows real-time sensor readings (IR, RED, BPM, SpO2) with visual heartbeat indicators, while a WiFi web interface provides comprehensive data visualization including numerical displays and real-time plotting charts. The web interface uses Chart.js for dynamic graph generation and automatically refreshes every 300ms to maintain real-time data updates. Both interfaces run simultaneously, enabling local monitoring and remote access.

Hello World on OLED

Initial OLED display test showing successful I2C communication and display initialization. See Ethical AI Use: Hello World Code for development details.

Hello World display on OLED for Invisible String project showing successful display initialization
Hello World on OLEDInitial OLED test confirming I2C communication and display functionality before implementing sensor interfaces.
Pulse Oximeter Readings on OLED

Real-time pulse oximeter data displayed on OLED showing IR and RED LED readings, heart rate (BPM), and blood oxygen saturation (SpO2) percentage. A heartbeat indicator flashes when a pulse is detected. See Ethical AI Use: MAX30102 Initialization Fix for sensor setup documentation.

Pulse oximeter readings on OLED displaying IR, RED, BPM, and SpO2 values
OLED sensor readings displayReal-time pulse oximeter data showing IR and RED LED values, heart rate (BPM), and blood oxygen saturation (SpO2) with heartbeat indicator.
BPM and SpO2 demonstrationVideo showing real-time heart rate and blood oxygen saturation measurements updating on OLED display with sensor interaction.
Pulse Oximeter Readings on WiFi GUI

WiFi web interface providing remote access to pulse oximeter data through a responsive HTML dashboard. The interface displays real-time numerical values for BPM, SpO2, IR, and RED readings with automatic data refresh. The web server runs on the ESP32-S3, allowing access from any device on the same WiFi network.

WiFi web interface displaying real-time pulse oximeter readings including BPM, SpO2, IR, and RED values
WiFi GUI readings dashboardRemote web interface showing real-time pulse oximeter data accessible from any device on the WiFi network, displaying BPM, SpO2, IR, and RED values with automatic updates.
Pulse Oximeter Plots on WiFi GUI

Enhanced WiFi web interface with real-time plotting capabilities using Chart.js library. The interface displays live line charts for BPM and SpO2 values, showing trends over time with automatic scrolling and data point management. This visualization enables users to observe patterns in heart rate and blood oxygen levels during monitoring sessions.

Serial monitor output showing sensor readings rising on touch interaction
Serial monitor sensor responseSerial output demonstrating sensor readings increase when finger is placed on MAX30102 sensor, showing IR and RED LED response to touch.
WiFi web interface with real-time plotting of BPM and SpO2 data using Chart.js
WiFi GUI with plotting chartsEnhanced web interface displaying real-time line charts for BPM and SpO2 values, showing trends over time with automatic data refresh and chart scrolling.

I2C Device Detection

Successful I2C device detection after fixing power isolation issues. The system now correctly identifies the OLED display at address 0x3C and the MAX30102 sensor at address 0x57. Initial troubleshooting required isolating the RD (red LED) and IRD (infrared LED) ground terminals from the general ground plane to prevent power issues and enable proper sensor operation. 

20:04:48.612 -> Scanning...
20:04:48.644 -> I2C device found at address 0x3C  !
20:04:48.644 -> I2C device found at address 0x57  !
20:04:48.644 -> done
Download Design Files

Part (c): Real-Time GUI through Mechanical Gripper and WiFi

A Wi-Fi-connected grip strength meter that interfaces a user with a mechanical hand gripper, an 80 kg load cell, and an HX711 amplifier. The ESP32-S3 continuously measures grip force, streams it to a web dashboard, and uses a published relationship between handgrip strength and age to display an estimated “physiological age” in real time. The design is inspired by the open-source grip strength meter from NeuroTech Hub at WashU and the associated PLOS ONE paper on grip strength and age trajectories (Syddall et al., 2014), adapted to my load cell and handle geometry.

Mechanically, a custom 3D-printed gripper clamps around a CZL601-type 80 kg bar load cell (sourced from Amazon 80 kg load cell). I imported a 100 kg load cell CAD from GrabCAD, checked the mounting dimensions against the CZL601AC datasheet (online, download), and confirmed that the hole spacing and footprint match the commercial part used here.

Mechanical Design and Fabrication

CAD model of the 3D-printed grip strength base and load cell mounting region
Grip strength base CADTop view of the grip strength base showing the bar load cell pocket, mounting bosses, and handle interface.
Side view CAD of the hand gripper and load cell assembly
Side view of gripper assemblySide profile showing how the fixed base, moving handle, and load cell align along the force axis of the bar sensor.
Full CAD view of the grip strength device with base and handle
Full grip strength assemblyComplete CAD of the base, handle, and load cell, sized for comfortable adult hand placement and full-finger contact.
Close-up of mounting holes and clearances around the load cell in CAD
Load cell mounting holesDetail of the M6 clearance and counterbore geometry used to capture the load cell without constraining bending.
Perspective CAD view of the gripper handle and base
Handle ergonomicsPerspective view of the curved handle designed to distribute pressure across the palm and fingers during maximal grip.
Photo of drilled clearance hole aligned to the printed pilot in the base
Clearance hole verificationPrinted pilot holes used as drill guides to match the metric mounting dimensions from the CZL601AC datasheet.
Photo of the fully printed grip strength device before drilling and assembly
Fresh off the printer3D-printed base and handle components in PLA prior to post-processing and hardware installation.
Printed part clamped for drilling load cell mounting holes
Workholding for accurate drillingThe printed base clamped to the drill press table so the pilot features guide the final clearance holes into the load cell.
Drilling practiceTraining cuts on scrap material to dial in drill press settings and avoid cracking the printed base during final holes.
Final load cell holesDrilling the final M6 clearance holes through the printed base, constrained by the pilot features to preserve alignment.

Electronics and Calibration

Electronics assembly with HX711 breakout, ESP32-S3, and load cell wiring
Electronics stack-upHX711 amplifier breakout from Amazon wired to the ESP32-S3 and 80 kg load cell with short, twisted signal pairs for noise reduction.
Fully assembled grip strength device with load cell, electronics, and handle
Assembled grip strength meterCompleted mechanical and electrical assembly ready for calibration and software bring-up.
Serial Plotter view of load cell readings increasing with grip force
Serial Plotter calibration tracesRaw HX711 output converted to kilograms and visualized in the Arduino Serial Plotter while applying known weights and grip forces.
Web GUI showing grip strength value, estimated age, and scrolling chart
Wi-Fi grip strength dashboardBrowser-based GUI with live grip strength (kg), estimated age, and a Chart.js time series plot of recent squeezes.

Model Used for Age Estimation

The age-estimation logic in the firmware is based on the non-linear, sex-specific grip-strength trajectories reported in Dodds et al., 2014 (PLOS ONE). As shown in Figure 1 of that paper, grip strength rises rapidly through adolescence, peaks around ages 30–40, and then declines non-linearly with age, with different magnitudes for males and females.

Reference grip strength trajectories over the life course from Dodds et al., PLOS ONE 2014
Reference trajectories (Figure 1)Age-dependent grip strength curves for males and females from Dodds et al., 2014, used as the qualitative target for the embedded model.
Simplified quadratic grip strength model fitted to reference data
Quadratic approximation (Table 2-inspired)Simplified male and female trajectories using peak strengths and curvatures chosen to approximate the summary values reported in Table 2 of Dodds et al., 2014.

To reproduce this shape efficiently on the ESP32, the firmware uses inverted quadratic approximations centered at age 35, consistent with the observed peak in the PLOS ONE data. In the forward direction, grip strength is approximated as:

Males: Grip(age) ≈ 52 − 0.0089·(age − 35)2
Females: Grip(age) ≈ 32 − 0.0059·(age − 35)2

On the device, this relationship is analytically inverted so that the measured grip strength can be mapped back to an estimated age:

age = 35 + √((a − Grip)/b), where a is the peak strength (52 kg for males, 32 kg for females) and b is the curvature (0.0089 for males, 0.0059 for females). The firmware clamps grip strength to physiologically meaningful ranges before applying this formula so the square root remains well-defined. 

float ageFromGripMale(float g) {
  float a = 52.0f, b = 0.0089f;
  if (g > a) g = a;
  if (g < 5) g = 5;
  return 35.0f + sqrtf((a - g) / b);
}

float ageFromGripFemale(float g) {
  float a = 32.0f, b = 0.0059f;
  if (g > a) g = a;
  if (g < 4) g = 4;
  return 35.0f + sqrtf((a - g) / b);
}

For full methodological details and original tables/figures, see the open-access paper: Dodds et al., 2014, PLOS ONE (download local PDF). The implementation here is an educational approximation and not intended for clinical or diagnostic use.

End-to-end live demoReal-time demonstration of squeezing the mechanical gripper and watching the Wi-Fi dashboard update grip strength and estimated age on a laptop.

Related Design, Code, and Calibration Resources

User Interface Comparison

Summary of how each interface application connects users with input and output devices.

Application How It Interfaces with the User Input Device(s) Output Device(s)
(a) Button User Interface Button press patterns (single, double, triple press, hold) provide mode selection input. OLED display shows current menu state and mode options. Users receive immediate visual feedback for each interaction. Button (GPIO pin 4) OLED Display (SSD1306, I²C 0x3C)
LED (GPIO pin 3, flashlight mode)
(b) Real-Time GUI (OLED & WiFi) Physical finger placement on MAX30102 sensor provides input. OLED displays real-time sensor data locally. WiFi web interface enables remote monitoring with numerical displays and live plotting charts accessible from any web browser. MAX30102 Pulse Oximeter Sensor (I²C 0x57) OLED Display (SSD1306, I²C 0x3C)
WiFi Web Interface (HTTP Server with Chart.js visualization)
(c) Grip Strength GUI (Load Cell & WiFi) Users squeeze a mechanical hand gripper that transfers force into an 80 kg bar load cell. The ESP32-S3 measures grip strength through the HX711 amplifier and streams results to a WiFi web dashboard that displays live grip force and an estimated physiological age in real time. Mechanical gripper linked to 80 kg load cell (CZL601-type)
HX711 load cell amplifier		 WiFi Web Interface (HTTP Server with Chart.js visualization)
Optional Serial Plotter (for calibration traces)

Group Assignment: Compare as Many Tool Options as Possible

Compare as many tool options as possible for interface and application programming.

General Comparison: Interface & Application Programming Tools

Comprehensive comparison of interface and application programming tools available for embedded systems and IoT development. This analysis covers tools from the MIT Academy Interface & Application Programming class page, evaluating their capabilities, use cases, and trade-offs for different application scenarios.

Embedded Display Interfaces

Tool/Framework Description Pros Cons Best For
OLED (SSD1306) Monochrome OLED displays via I²C Low power, high contrast, simple I²C interface, pixel-level control Limited resolution (128x64), monochrome only, small display size Status displays, sensor readouts, simple menus, embedded dashboards
LCD Character Displays Character-based LCD displays (16x2, 20x4) Simple API, readable in sunlight, low cost Limited to text/characters, no graphics, requires backlight power Text-only interfaces, status messages, debugging output
TFT Color Displays Full-color TFT LCD displays Color graphics, touch support, high resolution High power consumption, complex drivers, larger footprint Rich GUIs, image display, interactive touch interfaces

Web-Based Interfaces

Tool/Framework Description Pros Cons Best For
HTTP Server (ESP32) Built-in HTTP server on ESP32 for web interfaces Remote access, cross-platform (any browser), no app installation, real-time updates Requires WiFi, network dependency, limited to local network without port forwarding Remote monitoring, data visualization, control panels, sensor dashboards
WebSockets Real-time bidirectional communication Low latency, bidirectional, efficient for frequent updates More complex than HTTP, requires persistent connection Real-time streaming, interactive controls, live data feeds
Chart.js JavaScript charting library for web interfaces Beautiful charts, interactive, responsive, easy integration Requires JavaScript, CDN dependency or local hosting Data visualization, time series plots, sensor monitoring dashboards

Mobile & Native App Frameworks

Tool/Framework Description Pros Cons Best For
React Native Cross-platform mobile app framework Cross-platform (iOS/Android), native performance, large ecosystem Complex setup, requires mobile development knowledge Full-featured mobile apps, production deployments
Flutter Google's UI toolkit for cross-platform apps Single codebase, high performance, customizable UI Dart language, larger app size, learning curve Custom mobile interfaces, platform-specific designs
Progressive Web Apps (PWA) Web apps with native-like features No app store, cross-platform, offline capability Limited native API access, browser dependency Web-based mobile interfaces, simple deployment

Specific Comparison: Tools Used in Individual Assignment

Detailed comparison of the specific interface programming tools implemented in this week's individual assignment, evaluating their performance, ease of use, and suitability for embedded health monitoring applications.

OLED Display Interface (Adafruit SSD1306)

Aspect Evaluation
Ease of Implementation Simple I²C interface, well-documented Adafruit library, minimal wiring (SDA, SCL, power, ground)
Display Quality High contrast monochrome display, crisp text rendering, suitable for sensor data visualization
Power Consumption Very low power draw, ideal for battery-powered applications
Limitations 128x64 pixel resolution limits detail, monochrome only, small physical size (0.96" typical)
Best Use Cases Local sensor readouts, menu systems, status indicators, simple data displays

WiFi Web Interface (ESP32 HTTP Server + Chart.js)

Aspect Evaluation
Ease of Implementation ESP32 WebServer library provides straightforward HTTP server, Chart.js CDN integration requires minimal setup
Remote Access Accessible from any device on WiFi network (phone, tablet, computer), no app installation required
Visualization Capabilities Chart.js enables rich data visualization with real-time plotting, smooth animations, and interactive features
Real-Time Updates JSON API endpoint provides efficient data transfer, 300ms refresh rate maintains responsive feel
Limitations Requires WiFi network, limited to local network without additional configuration, power consumption higher than OLED alone
Best Use Cases Remote monitoring, data logging visualization, multi-user access, professional dashboards

Button Input Interface

Aspect Evaluation
Implementation Approach Digital GPIO reading with debouncing, press pattern detection (single/double/triple/hold) enables mode navigation
User Experience Intuitive press patterns, immediate visual feedback on OLED, no complex UI navigation required
Reliability Hardware debouncing with INPUT_PULLUP, timeout-based pattern recognition prevents accidental triggers
Limitations Limited to single button interaction, pattern learning required, less flexible than touchscreen interfaces
Best Use Cases Simple mode selection, menu navigation, embedded system controls, low-cost input solutions

Comparison Summary

The combination of OLED display and WiFi web interface provides complementary benefits: OLED offers immediate local feedback with minimal latency and power consumption, while the WiFi interface enables rich visualization and remote access. The button-based input provides an intuitive, low-cost navigation method suitable for embedded systems. Together, these tools create a robust interface system that supports both local and remote interaction with sensor data.

Design Files

Design files and code documentation for interface and application programming projects.

ESP32-S3 Development Board and Pinouts

Code files for ESP32-S3 development board interfaces including I2C scanning, OLED display control, and button-based user interface systems. See Week 4 documentation for board design and Week 8 documentation for pinout configurations.

I2C Scanner (i2cscan_generic.ino)

Utility code for scanning and detecting I2C devices on the bus, essential for troubleshooting connection issues.

How the Code Works (Pseudocode)
SETUP:
  Initialize I2C bus
  Initialize Serial communication
  Print "I2C Scanner" message

LOOP:
  Print "Scanning..." message
  Initialize device counter to 0
  
  FOR each address from 1 to 126:
    Begin I2C transmission to address
    Check transmission result
    
    IF transmission successful (error == 0):
      Print device found at address (hex format)
      Increment device counter
    ELSE IF unknown error (error == 4):
      Print unknown error at address
    
  IF no devices found:
    Print "No I2C devices found"
  ELSE:
    Print "done"
  
  Wait 5 seconds before next scan
Key Features
  • Scans all 127 possible I2C addresses (0x01-0x7E)
  • Detects and reports connected devices with hex address format
  • Handles multiple error conditions (device not found, unknown errors)
  • Continuous scanning mode with 5-second intervals
  • Compatible with any I2C bus configuration (Wire, Wire1, etc.)
What You Need to Know
  • I2C Address Range: Valid addresses are 0x08-0x77 (8-119 decimal); addresses 0x00-0x07 and 0x78-0x7F are reserved
  • Common Addresses: OLED displays typically use 0x3C or 0x3D; sensors vary (MAX30102 uses 0x57)
  • Troubleshooting: If no devices found, check wiring (SDA, SCL, power, ground), verify pull-up resistors, confirm device power
  • Usage: Run this before connecting other devices to verify I2C bus is working correctly
Download: i2cscan_generic.ino

Hello World OLED Display (hello_world.ino)

Basic OLED display test code that initializes the display and shows "Hello World" text, confirming I2C communication and display functionality.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial communication at 115200 baud
  Wait 500ms for Serial to stabilize
  
  Initialize I2C bus with SDA pin 5, SCL pin 6
  Print "Starting..." message
  
  Attempt to initialize OLED display:
    IF initialization fails:
      Print "OLED not found" error
      Enter infinite loop (halt)
  
  Clear display buffer
  Set text size to 2
  Set text color to white
  Set cursor position to (0, 20)
  Print "Hello" line
  Print "World!" line
  Update display (send buffer to hardware)

LOOP:
  Empty (runs once, then waits)
Key Features
  • Simple OLED initialization and text display
  • Custom I2C pin configuration for XIAO ESP32-S3 (SDA=5, SCL=6)
  • Error handling with infinite loop if display not found
  • Text size and cursor positioning for centered display
  • One-time display update (no loop refresh needed for static text)
What You Need to Know
  • I2C Pin Configuration: XIAO ESP32-S3 uses pins 5 (SDA) and 6 (SCL) by default; verify your board's pinout
  • Display Address: SSD1306 OLED typically uses address 0x3C; some variants use 0x3D
  • Display Update: Must call display.display() to send buffer to hardware; drawing functions only modify buffer
  • Testing: Use this as first test after connecting OLED to verify wiring and I2C communication before adding complex features
  • Libraries Required: Adafruit_GFX, Adafruit_SSD1306, Wire
Download: hello_world.ino

Button User Interface (outputs.ino)

Mode-based navigation system using button press patterns (single, double, triple, hold) to control multiple output devices including OLED display, camera, sensors, and LED flashlight.

How the Code Works (Pseudocode)
SETUP:
  Initialize OLED display
  Initialize camera module
  Initialize sensors (MPU6050, HX711)
  Initialize button pin (INPUT_PULLUP)
  Initialize LED pin (OUTPUT)
  Set current mode to MENU
  Display menu screen

LOOP:
  Read button state
  
  IF button pressed:
    Record press start time
    Start press detection timer
  
  IF button released:
    Calculate press duration
    IF duration > HOLD_THRESHOLD:
      Activate flashlight mode
    ELSE:
      Increment press count
      Reset press timeout timer
  
  IF press timeout exceeded:
    Process accumulated press count:
      IF press count == 1: Switch to CAMERA mode
      IF press count == 2: Switch to SENSORS mode
      IF press count == 3: Switch to MENU mode
    Reset press count
  
  IF current mode == MENU:
    Display menu screen (button instructions)
  
  IF current mode == CAMERA:
    Capture camera frame
    Process image with dithering algorithm
    Display on OLED
    Run Edge Impulse inference (optional)
    Overlay results on display
  
  IF current mode == SENSORS:
    Read accelerometer/gyroscope data
    Read load cell data
    Display sensor readings on OLED
  
  Update display
Key Features
  • Press pattern detection: single (1x), double (2x), triple (3x), and hold
  • Mode-based navigation system (Menu, Camera, Sensors)
  • Button debouncing with timeout-based pattern recognition
  • Floyd-Steinberg dithering for camera-to-OLED video display
  • Edge Impulse AI inference integration for face detection
  • Multi-sensor integration (MPU6050 accelerometer/gyro, HX711 load cell)
  • Flashlight mode activated by button hold
What You Need to Know
  • Button Wiring: Use INPUT_PULLUP mode (button connects pin to GND when pressed, internal pull-up to 3.3V)
  • Press Detection: Press count is accumulated until timeout (1 second); longer timeout allows slower multiple presses
  • Mode Switching: Each mode has distinct display update logic; ensure proper initialization in setup()
  • Camera Performance: Video streaming to OLED requires significant processing; frame rate depends on resolution and dithering complexity
  • Dependencies: Requires camera_pins.h header file with XIAO ESP32-S3 camera pin definitions; see Ethical AI Use for development details
  • Sensor Conflicts: Code uses preprocessor directives to resolve sensor_t type conflict between ESP32 camera and Adafruit MPU6050 libraries
Download: outputs.ino | camera_pins.h | outputs.zip (complete project)

Grip Strength Monitor (Load Cell + WiFi GUI)

Design files and firmware for a Wi-Fi-enabled grip strength meter built around an 80 kg bar load cell, HX711 amplifier, and ESP32-S3. The mechanical design was informed by the open-source grip strength meter from NeuroTech Hub and validated against the CZL601AC bar load cell datasheet (online, download).

Mechanical Design Files (3D-Printed Components)

  • Base.3mf — main chassis that captures the bar load cell and anchors the fixed side of the gripper.
  • Case.3mf — protective enclosure for the ESP32-S3 and HX711 amplifier with cable strain relief.
  • Handle.3mf — curved grip handle that transfers hand force into the free end of the load cell.
  • Calibration Print.3mf — small test piece used to verify hole diameters and load cell clearances before printing the full assembly.

All parts were printed in PLA with high infill in the load paths to minimize creep and flex during repeated maximal grip trials.

Basic HX711 Reader (loadcell_simple.ino)

Minimal firmware to bring up the HX711 amplifier and read calibrated weight values over Serial for debugging and calibration.

How the Code Works (Pseudocode)
SETUP:
  Configure HX711 data and clock pins (DT=A1, SCK=A0)
  Initialize Serial at 115200 baud
  Begin HX711 with DT/SCK pins
  Set calibration factor (grams per ADC unit)
  Tare the scale so current load is zero

LOOP (every 200 ms):
  If HX711 is ready:
    Read averaged weight using get_units(4)
    Print "weight:<value>" to Serial for Serial Plotter
  Else:
    Print "HX711 not ready" for troubleshooting
Key Features
  • Simple initialization of the HX711 on analog pins A0/A1.
  • Configurable calibration factor for mapping counts to grams or kilograms.
  • Timed reads (200 ms) to keep Serial output manageable and Plotter-friendly.
  • Graceful handling of HX711 not-ready states.
What You Need to Know
  • Use for initial bring-up: Run this first when wiring the HX711 and load cell to confirm clean, stable readings.
  • Calibration factor: Determined experimentally by hanging known weights and adjusting until readings match; see the calibration notes in Calibration Chat.
  • Serial Plotter: The weight:<value> format is convenient for quickly visualizing changes while squeezing the handle.
Download: loadcell_simple.ino

Serial Plotter-Friendly Reader (loadcell_plot.ino)

Refined HX711 reader tuned for the Arduino Serial Plotter: it outputs a single numeric value per line for clean plotting of grip strength over time.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial at 115200 baud
  Initialize HX711 on DT=A1, SCK=A0
  Set calibration factor
  Tare the scale
  Optionally print debug messages when DEBUG=1

LOOP (every 200 ms):
  If HX711 is ready:
    Read filtered weight with get_units(4)
    Optionally print labeled debug text
    Print only the numeric weight to Serial for the Plotter
  Else:
    Optionally print "not ready" debug text
    Print 0 so the plotted line continues gracefully
Key Features
  • DEBUG toggle: Compile-time switch to enable/disable human-readable logs without breaking the Serial Plotter format.
  • Clean “one number per line” output for multi-trial grip testing in the Serial Plotter.
  • Automatic zero output when the HX711 is not ready to keep the time axis continuous.
  • Shared pinout and calibration approach with loadcell_simple.ino for easy swapping.
What You Need to Know
  • Use this sketch to tune calibration and visualize grip curves without any GUI overhead.
  • When collecting data for analysis, keep DEBUG set to 0 so the output is a pure numeric stream.
  • The sample interval (200 ms) gives a smooth trace while keeping file sizes reasonable for multi-second squeezes.
Download: loadcell_plot.ino

WiFi Grip Strength GUI (loadcell_gui.ino)

Full application firmware that exposes grip strength and an estimated age over Wi-Fi using an HTTP server and a Chart.js web dashboard.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial
  Initialize HX711 (pins, calibration factor, tare)
  Connect ESP32-S3 to WiFi (MIT network in this build)
  Start WebServer on port 80
  Register handlers:
    "/"        → serve HTML+JS GUI page from PROGMEM
    "/metrics" → serve JSON with current grip and age

LOOP:
  Handle incoming HTTP clients
  Every 200 ms:
    If HX711 is ready:
      Read smoothed grip strength (kg) via get_units(3)
      Clamp negative values to zero
      Store in global gripStrength

AGE ESTIMATION HELPERS:
  ageFromGripMale(g):
    Clamp g to plausible range
    Compute age using inverted quadratic fit derived from normative data
  ageFromGripFemale(g):
    Same structure with female-specific parameters

HTTP /metrics ENDPOINT:
  Read "sex" query parameter (default "male")
  Compute ageEstimate = ageFromGripMale/ageFromGripFemale(gripStrength)
  Return JSON:
    {"grip": <kg>, "age": <years>}

CLIENT-SIDE GUI (HTML + JS):
  Render dark-themed dashboard with:
    - Sex toggle buttons (male/female)
    - Numeric grip strength (kg) and age
    - Scrolling Chart.js line plot of recent grip values
  Poll /metrics every 200 ms and update DOM + chart
Key Features
  • Embedded HTML/JS dashboard served directly from the ESP32-S3 using PROGMEM.
  • Real-time grip strength plot using Chart.js with ~120 recent samples.
  • Simple sex toggle that switches between male and female age-estimation curves.
  • JSON API at /metrics for future extensions (e.g., logging clients).
What You Need to Know
  • WiFi credentials: Update the ssid and password constants to match your network.
  • Normative model: The age equations are simplified fits inspired by the grip-strength trajectories reported in Syddall et al., PLOS ONE 2014 and are for educational visualization only, not clinical use.
  • Browser requirements: Any modern browser with JavaScript and network access can connect to the ESP32-S3’s IP address to view the dashboard.
  • Development log: The full iterative design of this sketch is captured in the ChatGPT transcript: Grip Strength Monitor Code Chat.
Download: loadcell_gui.ino

Invisible String Chain of Hearts

Code files for the Invisible String pulse oximeter interface system, providing real-time health monitoring through OLED display and WiFi web interface. See Week 11 PCB design documentation for hardware details.

OLED GUI for Pulse Oximeter (pulse_vo2_reads_fixing.ino)

Local OLED display interface showing real-time pulse oximeter readings including heart rate (BPM), blood oxygen saturation (SpO2), and raw IR/RED LED sensor values.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial communication
  Initialize I2C bus (SDA=5, SCL=6) at 400kHz
  Initialize MAX30102 sensor
  Configure sensor:
    Set LED mode to RED + IR
    Set ADC range to 16384
    Set sample rate to 100 Hz
    Set pulse width to 411 μs
    Set LED brightness to medium (0x3F)
  Initialize OLED display
  Clear and prepare display

LOOP:
  Read IR and RED LED values from sensor
  
  Heart Rate Detection:
    Check for heartbeat in IR signal using peak detection
    IF heartbeat detected:
      Calculate time since last beat
      Calculate BPM = 60 / (time_delta / 1000)
      Set beat flag for visual indicator
      Update last beat timestamp
  
  SpO2 Calculation (every 300ms):
    Add IR and RED values to circular buffer
    IF buffer has 50 samples:
      Calculate DC components (average)
      Calculate AC components (RMS)
      Calculate R ratio = (AC_RED/DC_RED) / (AC_IR/DC_IR)
      Estimate SpO2 = 110 - 25 * R
      Clamp SpO2 to 70-100% range
  
  Serial Output:
    Print IR, RED, BPM for Serial Plotter visualization
  
  OLED Display Update:
    Clear display buffer
    Display IR value (small text)
    Display RED value (small text)
    Display BPM value (large text, size 2)
    Display SpO2 percentage (small text)
    IF beat detected: Draw heartbeat indicator dot
    Update display hardware
  
  Delay 20ms (50 Hz update rate)
Key Features
  • Real-time heart rate detection using peak detection algorithm on IR signal
  • SpO2 calculation using ratio-of-ratios method with DC/AC component analysis
  • Circular buffer system for storing 50 samples of IR/RED data
  • Visual heartbeat indicator (flashing dot) when pulse detected
  • Dual output: OLED display and Serial Plotter for real-time waveform visualization
  • Optimized sensor configuration for reliable readings (100 Hz sample rate, medium brightness)
What You Need to Know
  • Sensor Placement: Finger must cover sensor completely; proper contact ensures accurate readings
  • I2C Address: MAX30102 uses address 0x57; verify with I2C scanner if sensor not detected
  • Ground Isolation: RD and IRD pins must be isolated from main ground plane to prevent power issues (see Week 11 PCB design)
  • SpO2 Accuracy: Calculation provides estimation; medical-grade accuracy requires calibration and FDA-approved algorithms
  • Buffer Size: 50-sample buffer provides balance between calculation accuracy and response time
  • Libraries Required: MAX30105 (SparkFun library), Adafruit_GFX, Adafruit_SSD1306, heartRate.h (beat detection)
  • Troubleshooting: If sensor not detected, check power isolation, I2C wiring, and sensor initialization order
Download: pulse_vo2_reads_fixing.ino

WiFi Readings GUI (pulse_gui.ino)

WiFi-enabled web interface providing remote access to pulse oximeter data through HTTP server with JSON API endpoint for real-time data updates.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial communication
  Initialize I2C bus
  Initialize MAX30102 sensor
  Configure sensor (LED mode, sample rate, pulse width)
  Initialize OLED display
  Initialize WiFi:
    Connect to network (SSID, password)
    Wait for connection
    Print IP address
  Initialize HTTP server:
    Route "/" → serve GUI HTML page
    Route "/gui" → serve GUI HTML page
    Route "/metrics" → serve JSON data
  Start web server

LOOP:
  Handle incoming HTTP client requests
  
  Read IR and RED values from sensor
  
  Heart Rate Calculation:
    Check for heartbeat in IR signal
    IF heartbeat detected:
      Calculate BPM from time delta
      Update global BPM variable
  
  SpO2 Calculation:
    Add IR/RED to circular buffer
    IF buffer full (50 samples):
      Calculate SpO2 using ratio-of-ratios
      Update global SpO2 variable
  
  Update global variables (g_ir, g_red, g_bpm, g_spo2)
  
  OLED Display Update:
    Display IR, RED, BPM, SpO2 values
    Update display hardware
Key Features
  • Dual interface: OLED display (local) and WiFi web interface (remote)
  • HTTP server with embedded HTML page stored in PROGMEM
  • JSON API endpoint (/metrics) for real-time data retrieval
  • Automatic WiFi connection with connection status feedback
  • IP address display for easy access
  • Simultaneous sensor reading and web server operation
  • Global variable system for data sharing between sensor reading and HTTP handlers
What You Need to Know
  • WiFi Configuration: Update SSID and password in code; for MIT network, use generated device password from wifi.mit.edu
  • Network Access: Web interface accessible only from devices on same WiFi network; IP address printed to Serial Monitor
  • HTML Storage: GUI HTML page stored in PROGMEM (program memory) to conserve RAM; use PROGMEM for large strings
  • Server Handling: Must call server.handleClient() frequently in loop() for responsive web interface
  • Data Refresh: Client-side JavaScript polls /metrics endpoint every 300ms for real-time updates
  • Power Consumption: WiFi significantly increases power draw compared to OLED-only mode; consider power management for battery operation
  • Libraries Required: WiFi, WebServer, MAX30105, Adafruit_SSD1306
Download: pulse_gui.ino

WiFi Plot GUI (pulse_gui_2.ino)

Enhanced WiFi web interface with real-time plotting capabilities using Chart.js library, displaying live line charts for BPM and SpO2 values with automatic scrolling and data management.

How the Code Works (Pseudocode)
SETUP:
  (Same as pulse_gui.ino)
  Initialize WiFi, sensor, OLED, HTTP server

LOOP:
  (Same as pulse_gui.ino)
  Handle HTTP requests, read sensor, calculate BPM/SpO2

GUI HTML PAGE (embedded in PROGMEM):
  Load Chart.js library from CDN
  Create two Chart.js line chart instances:
    - BPM chart (y-axis: 40-160 BPM)
    - SpO2 chart (y-axis: 70-100%)
  Initialize data arrays for each chart
  
  JavaScript Update Function (runs every 300ms):
    Fetch JSON data from /metrics endpoint
    Update numerical displays (BPM, SpO2, IR, RED)
    Add new BPM value to BPM data array
    Add new SpO2 value to SpO2 data array
    IF array length > maxPoints (100):
      Remove oldest value (shift)
    Update chart labels (array indices)
    Update chart datasets with new data
    Call chart.update() to refresh display
  
  Set interval to call update function every 300ms
Key Features
  • Real-time line chart visualization using Chart.js library
  • Dual chart display: BPM and SpO2 trends over time
  • Automatic data scrolling: maintains 100 most recent data points
  • Numerical displays alongside charts for precise values
  • Responsive design with dark theme for OLED-style aesthetic
  • Automatic chart scaling with fixed y-axis ranges for consistent visualization
  • CDN-based Chart.js loading for minimal memory footprint
What You Need to Know
  • Chart.js CDN: Library loaded from jsdelivr.net CDN; requires internet connection on client device
  • Data Management: Arrays limited to 100 points to prevent memory overflow; older data automatically discarded
  • Update Rate: 300ms refresh rate balances responsiveness with server load; adjust based on network conditions
  • Chart Configuration: Y-axis ranges fixed (BPM: 40-160, SpO2: 70-100) for consistent scaling; modify in JavaScript if needed
  • Browser Compatibility: Requires modern browser with JavaScript enabled; tested on Chrome, Firefox, Safari
  • Performance: Chart updates are lightweight; multiple simultaneous clients may impact ESP32 performance
  • Offline Operation: Charts won't load if client device lacks internet (Chart.js CDN unavailable); consider local hosting for offline use
Download: pulse_gui_2.ino

Reflections & Learnings

Key insights and learnings from working with interface and application programming.

Contributions

Acknowledgements and team roles for interface and application programming work.

Ethical AI Use

Transparent documentation of AI assistance used in this week's interface and application programming work.

This section documents all AI assistance used during Week 12 interface and application programming work. ChatGPT was used for code development, troubleshooting, and technical guidance. All transcripts are linked below for transparency.

Menu System with Modes

AI assistance for developing the button-based menu system with mode navigation (Menu, Camera, Sensors) using press pattern detection. The conversation covered button debouncing, press pattern recognition, mode state management, and OLED menu display design.

Related to: Part (a): Simple Button User Interface on OLED

View ChatGPT Transcript: Menu System with Modes

I2C Device Not Found

Troubleshooting session for I2C device detection issues with MAX30102 pulse oximeter sensor. The conversation addressed power isolation problems, I2C wiring verification, sensor initialization order, and ground plane isolation requirements for accurate sensor operation.

Related to: Part (b): Real-Time Graphical User Interface through OLED and WiFi

View ChatGPT Transcript: I2C Device Not Found

Hello World Code

Development assistance for creating the initial OLED "Hello World" test program. The conversation covered I2C initialization, OLED display library setup, text rendering, and basic display configuration for XIAO ESP32-S3 development board.

Related to: Part (b): Real-Time Graphical User Interface through OLED and WiFi (initial OLED test)

View ChatGPT Transcript: Hello World Code

MAX30102 Initialization Fix

Technical guidance for fixing MAX30102 pulse oximeter sensor initialization issues. The conversation addressed sensor configuration parameters, LED brightness settings, sample rate optimization, initialization sequence requirements, and troubleshooting sensor communication problems.

Related to: Part (b): Real-Time Graphical User Interface through OLED and WiFi (pulse oximeter readings)

View ChatGPT Transcript: MAX30102 Initialization Fix

Grip Strength Monitor Code Design

Code-focused assistance for designing and refining the WiFi grip strength monitor firmware. The conversation covered HX711 bring-up, load cell pin mapping, Serial Plotter debugging sketches, the ESP32-S3 HTTP server, the Chart.js dashboard, and the age-estimation helpers used in loadcell_simple.ino, loadcell_plot.ino, and loadcell_gui.ino.

Related to: Part (c): Real-Time GUI through Mechanical Gripper and WiFi and Grip Strength Monitor design files

View ChatGPT Transcript: Grip Strength Monitor Code

Grip Strength Calibration & Scaling

Calibration-focused assistance for mapping HX711 counts to kilograms and validating the grip strength readings. The discussion walked through using the Serial Plotter, collecting reference weights, tuning the calibration factor, and sanity-checking the age-estimation model derived from normative grip strength data.

Related to: Part (c): Real-Time GUI through Mechanical Gripper and WiFi calibration workflow and the Grip Strength Monitor sketches.

View ChatGPT Transcript: Grip Strength Calibration

Grip Strength Monitor – Cursor Transcript

Full Cursor AI transcript focused on organizing the grip strength monitor section: structuring Part (c), integrating design files, embedding images and videos, and aligning captions, external references, and the Ethical AI Use documentation for the load cell project.

Related to: Part (c): Real-Time GUI through Mechanical Gripper and WiFi, Grip Strength Monitor design files, and this Ethical AI Use section.

View HTML Transcript Download Markdown Transcript

Week 12 Project Documentation

Complete Cursor AI transcript for Week 12 interface and application programming project documentation. This comprehensive conversation covers the creation and population of the Week 12 HTML page, including Individual Assignment sections (button UI and WiFi GUI), Group Assignment tool comparisons, Design Files documentation with pseudocode, and Ethical AI Use section organization. The transcript demonstrates the collaborative process of building professional documentation with structured content, embedded media, and comprehensive code documentation.

Related to: Complete Week 12 documentation including Individual Assignment, Group Assignment, Design Files, and overall page structure

View HTML Transcript Download Markdown Transcript

Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License

``` Updating the highlights section and replacing the individual assignment section. Finding the highlights section: Replacing the highlights section with PCB engraving highlights: ```html Week 13 · Wildcard Week
← Back to Home
[Profile Image Placeholder]

Week 13

Wildcard Week

Week Highlights

Key captures from the PCB engraving assignment with links to their sections.

ATtiny1626 Board Design

Final ATtiny1626 development board design with connectors and mounting holes

PCB Engraving

ATtiny1626 development board after fiber laser engraving

Soldered Board

Fully assembled ATtiny1626 development board with all components soldered

Blinking LED Demo

RP2354A Board Design

RP2354A development board design

PCB Engraving Detail

Close-up detail of PCB engraving showing trace quality

Table of Contents

Course Content

Training & Documentation

Assignments & Projects

Wildcard Week

This week focuses on exploring digital fabrication processes not covered in previous assignments. We'll design and produce something using computer-aided design and manufacturing, documenting requirements and including everything necessary for reproduction. This week also includes reflection on the impact and purpose of making (almost) anything.

Exploring new digital fabrication processes
Designing and producing with CAD/CAM
Understanding the impact and purpose of fabrication labs

This Week's Goals

  • Explore New Processes
    Design and produce something with a digital process not covered in other assignments
  • Complete Documentation
    Document requirements and include everything necessary to reproduce the project
  • Reflect on Impact
    Understand the purpose and impact of fabrication labs and making

Assignments

  • Group Assignment
    Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment
  • Individual Assignment
    Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment, documenting the requirements that your assignment meets, and including everything necessary to reproduce it

Tools & Materials

  • Carvera (CNC Mill) — Edge cuts and hole machining
  • Fiber Laser Cutter (xTool F2 Ultra) — PCB engraving
  • PCB Design Software (KiCad) — Board layout and design
  • ATtiny1626 Microcontroller — Target device for development board
  • RP2354A Microcontroller — Complex board design

Lecture Notes

Week 13 lecture covering major announcements, week 12 review, system integration reminders, and wildcard week preview.

Theme of the Week

'Step away from the panic'

Major Announcements

  • Subject evaluation: Required for funding the class. Provides feedback to the institute about the class. Important for future students if you care about successors in the class.
  • Calendar alarm: Wildcard week and recitation on why make (almost) anything: impact. Friday is cutoff for assignments and orders (10s of dollars per person from inventory).
  • Final presentation/final exam: Combining multiple additive and subtractive processes (not just design a board and 3D print a case). Goal is system integration out of parts. Final exam criteria:
    • Did you integrate and design a complete system?
    • Can you demo a final project? Here is the cool thing I did and here is how it works.
    • Make a final project video! (helps but not required)
    Focus on well-integrated device!

Review of Week 12 User Interfaces

  • Claire Wang: Music play and Windows 3.1 interface works!
  • Ryan Hoffman: DRV8251A discussion, heat sinks, breakout boards. Wildcards with waterjetting, EDM, multi-axis machining, laser cutting metal. Class in the spring on nature of mathematical modeling.
  • Srikanth Nadhamuni: Background and experience to visiting fellow at MIT. Raspberry Pi W for WiFi, n8n for cloud LLM data crunching. Software: Node.js, MCP bridge server with n8n based on bridge connected to device (NGV tunnel). All set! Fantastic experience, haven't worked so hard in a very long time and learning a lot of new things. Hope to take forward and build other systems. The whole culture of doing and trying yourself fascinating, especially with failing a number of times until you figure it out. Maybe set one up at an IIT in India or AI centers of excellence with education ministry into the Indian education system (see fablabkerala.in or vigyam ashram).
  • Ray Song: Not here.
  • Tyler Jensen (Lincoln Lab, Group 81): Final project discussion (nylon printer). Week 13: Easy for web serial interface for XIAO! Web server to TFT (I think I forgot to load the camera pins with my code for it).
  • Aditi Ramakrishnan: Sloan MBA and strategy consulting background. Discrete time filter (FFT is blown) in skimage.filters — make a bandpass filter, then run a series of these filters, much less computing only adds and multiplies for filtering in realtime.
  • Alexandros Gravalos: Not here.
  • Edward Chen: Check final watch project by Gulati into watch form factor. Clear print on the Form Labs printer, 0.1. Kaman filter for sensor fusion (in the spring class). For position — LSM6DSV16X from input devices. Acceleration at 7 kHz (at audio frequency).

Show and Tell

  • Handle to sensor WiFi user interface
  • Plug to audio LLM user interface

System Integration Reminders

  • Mount electronics
  • Strain relief the final projects

Preview for Wildcard Week

Assignment: Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment.

Recitation Notes: Why Make (Almost) Anything

Recitation exploring the purpose, impact, and scaling of fabrication labs and making infrastructure.

Map of Fab Labs

Why Make a Fab Lab?

  • Used to create a community
  • Building things for the community
  • Sustainability
  • Prototyping quickly

How Impact?

  • How to make spaces: How to measure impact. What is important about fab:
    • Fablabs in cities vs rural areas: The ability to decide their own futures and change their lives fundamentally. 'Safecast revolutionized citizen science' e.g. radiation map.
    • Bringing back manufacturing: Reducing reliance on supply chains.
    • Rural sustainability: Working with indigenous communities on creating technologies themselves at scale and measure their usefulness and efficacy to preserve their ancestral knowledge:
      • How to establish labs there
      • How to make sure the labs get used
    • Hygiene technologies with Proctor and Gamble: Highly commercial. Lots of plastic waste. How can we change how they produce? How to make their products get there through resellers?
    • Trip to Peru and ran workshops, questionnaires, analysis: Collaboration developed into how to produce the products but also how to test their products to be market valuable e.g. mosquito repellents. Out of three plants, two worked better and one wasn't working at all (which is important to know!).

What Does It Mean to Design Infrastructure?

  • What did we want this lab to be able to do?
    • Workshops and questionnaires
    • How much you educate people based on the info they have with the issues the community is facing
    • Energy concerns to consider, some machines just drain the grid and can't be used. Solar powered, battery powered machines, reducing energy consumption of machines. Many concerns important.
  • Ethical questions
  • How to maintain resources

Case Study: Water Purifier Packets

Use them, change them, source them locally, ingredients found locally, how to distribute them globally.

Funding Models

First few fablabs were NSF funded. Now corporate CSR, regional funding, labor funding (10 different ways). Successful fablabs are heterogeneous with lots of ways of funding. The ones that fail usually just have one sponsor.

Example: DIY Raman spectrometer for water purification (even after purifications still have sulfates and improving that too).

What Does It Mean to Scale Infrastructure?

(Besides a lot of meetings!) What is a reasonable way to design a data collection process about what is needed and how to achieve it.

Back to the Map: Expansion

Timeline of development, cocreation, portable, skin analysis, water testing, biomaterial tech, microscopy.

Initial Results from Boston

How to Confront Local Impact
  • Collab with University of Hamburg. Motivation for how much food can be produced in Boston. Where food waste goes and what Boston produces locally. Make things for yourself locally.
  • Impact directly in the community you're living in.

Hatchspace

Focused on rehabilitation of addicts with woodworking. (Vermont is wood producing state).

Example Course Program

  • All-in session and systemic impact
  • Natural and cultural context
  • Skills and workshop
  • Economic vitality
  • Skills and workshop
  • Co-work session
  • Solutionspalooza

In the Course

Hands-on component (no physical robot exists that can do it) and community component is also important. Inclusion is important. Solving unconscious and institutional biases.

  • 'Fabrica! Lab' — Creating new laboratory spaces for female high school students, courses aimed for women in technology, online advising sessions for females interested in tech.
  • Makerspaces — Access to tools behind closed doors at universities, makes a huge difference for people who don't have the ability to prototype for themselves.
  • Materiom — Fablab affiliated project on organic waste for biomaterials.
  • Fablab León
  • Skylab workshop experiment — How to run a noodle shop out of a fablab (creating food from the community).
  • Academany — Global distributed campus for high school education. Fablab all-in (belonging, impact, community), fab futures (future vocational skills), bio academy (synthetic biology), fabricademy (textiles, fab, bio), fab academy (digital fab apps and implications).

Trade-off Between Impactful and Dangerous

People could be doing bad, but not because doing it with a group people with values.

Questions

Clarification: Adding infrastructure to existing fablab infrastructure to help support specific community needs (not specialized fab labs).

Foundations for Fab Futures

July 27-31, 2026 at Fab Boston 2026.

Useful Documentation

Essential resources for wildcard week digital fabrication processes and PCB design.

Class Page

Wildcard Week - MIT Academy

Comprehensive resource covering wildcard week assignment requirements and possibilities including grinding, multi-axis machining, electrical discharge machining, waterjet cutting, flatbed cutting, plasma cutting, laser metal cutting, laser micromachining, welding, molding and casting, folding, robotics, electronics, embedded programming, food, materials, biotechnology, textiles, and composites.

Key Topics

  • Machining: Grinding, multi-axis machining, electrical discharge machining, waterjet cutting, plasma cutting, laser metal cutting, laser micromachining
  • Molding & Casting: Vacuum forming, rotocasting
  • Folding: Mathematics, form and function, kirigami
  • Robotics: Arms, construction, soft actuation pneumatic inflatable
  • Electronics: Pick and place, programmable logic
  • Embedded Programming: Machine learning, machine vision
  • Textiles: Fiber processes, knitting, embroidery (PEmbroider, Ink/Stitch), Fabricademy
  • Composites: Various composite fabrication techniques

ATtiny1626 Development Board References

Embedded Programming Course Resources

Course resources for embedded programming with ATtiny412 microcontroller examples:

Embedded Programming - MIT Academy

ATtiny412 Echo Example Image

Individual Assignment: Interface & Application Programming

Write an application that interfaces a user with an input &/or output device that you made. This assignment demonstrates three interface applications: (a) a simple button user interface on OLED, (b) a real-time graphical user interface through OLED and Wi-Fi for pulse oximeter readings, and (c) a Wi-Fi grip strength monitor with a mechanical gripper and age-estimation web dashboard.

Part (a): Simple Button User Interface on OLED

A mode-based user interface system that interfaces users with multiple input and output devices through a simple button press interface. The system provides visual feedback on an OLED display and enables navigation between different modes (Menu, Camera, Sensors) using button press patterns. Users interact by pressing a button multiple times to select modes, with visual confirmation displayed on the OLED screen.

Interface Design

The interface uses a mode-based navigation system where button presses trigger mode changes. A single press enters Camera mode, two presses enter Sensors mode, three presses return to Menu, and holding the button activates a flashlight function. The OLED display shows the current menu state and provides clear visual feedback for each mode transition. See Ethical AI Use: Menu System with Modes for AI-assisted development details.

OLED button user interface menu system displaying mode selection options
OLED button user interface menuMenu screen showing available modes: Camera, Sensors, and Menu navigation options with button press instructions.
Button UI demonstrationVideo showing button press interactions navigating through different modes on the OLED display.
First video stream on OLEDInitial camera feed streaming to OLED display using dithering algorithm for monochrome conversion, demonstrating real-time video output interface.
Download Design Files
  • outputs.ino — Button user interface code with mode system
  • camera_pins.h — Camera pin definitions header file
  • outputs.zip — Complete project archive including all dependencies

Part (b): Real-Time Graphical User Interface through OLED and WiFi

A dual-interface health monitoring system that interfaces users with a MAX30102 pulse oximeter sensor through both an OLED display and a WiFi-enabled web interface. The system provides real-time visualization of heart rate (BPM), blood oxygen saturation (SpO2), and raw sensor data (IR and RED LED readings) through multiple output channels. Users can view data locally on the OLED display or remotely via a web browser accessing the ESP32-S3's built-in HTTP server. See Ethical AI Use: I2C Device Not Found for troubleshooting documentation.

Interface Design

The system provides dual-interface access: a local OLED display shows real-time sensor readings (IR, RED, BPM, SpO2) with visual heartbeat indicators, while a WiFi web interface provides comprehensive data visualization including numerical displays and real-time plotting charts. The web interface uses Chart.js for dynamic graph generation and automatically refreshes every 300ms to maintain real-time data updates. Both interfaces run simultaneously, enabling local monitoring and remote access.

Hello World on OLED

Initial OLED display test showing successful I2C communication and display initialization. See Ethical AI Use: Hello World Code for development details.

Hello World display on OLED for Invisible String project showing successful display initialization
Hello World on OLEDInitial OLED test confirming I2C communication and display functionality before implementing sensor interfaces.
Pulse Oximeter Readings on OLED

Real-time pulse oximeter data displayed on OLED showing IR and RED LED readings, heart rate (BPM), and blood oxygen saturation (SpO2) percentage. A heartbeat indicator flashes when a pulse is detected. See Ethical AI Use: MAX30102 Initialization Fix for sensor setup documentation.

Pulse oximeter readings on OLED displaying IR, RED, BPM, and SpO2 values
OLED sensor readings displayReal-time pulse oximeter data showing IR and RED LED values, heart rate (BPM), and blood oxygen saturation (SpO2) with heartbeat indicator.
BPM and SpO2 demonstrationVideo showing real-time heart rate and blood oxygen saturation measurements updating on OLED display with sensor interaction.
Pulse Oximeter Readings on WiFi GUI

WiFi web interface providing remote access to pulse oximeter data through a responsive HTML dashboard. The interface displays real-time numerical values for BPM, SpO2, IR, and RED readings with automatic data refresh. The web server runs on the ESP32-S3, allowing access from any device on the same WiFi network.

WiFi web interface displaying real-time pulse oximeter readings including BPM, SpO2, IR, and RED values
WiFi GUI readings dashboardRemote web interface showing real-time pulse oximeter data accessible from any device on the WiFi network, displaying BPM, SpO2, IR, and RED values with automatic updates.
Pulse Oximeter Plots on WiFi GUI

Enhanced WiFi web interface with real-time plotting capabilities using Chart.js library. The interface displays live line charts for BPM and SpO2 values, showing trends over time with automatic scrolling and data point management. This visualization enables users to observe patterns in heart rate and blood oxygen levels during monitoring sessions.

Serial monitor output showing sensor readings rising on touch interaction
Serial monitor sensor responseSerial output demonstrating sensor readings increase when finger is placed on MAX30102 sensor, showing IR and RED LED response to touch.
WiFi web interface with real-time plotting of BPM and SpO2 data using Chart.js
WiFi GUI with plotting chartsEnhanced web interface displaying real-time line charts for BPM and SpO2 values, showing trends over time with automatic data refresh and chart scrolling.

I2C Device Detection

Successful I2C device detection after fixing power isolation issues. The system now correctly identifies the OLED display at address 0x3C and the MAX30102 sensor at address 0x57. Initial troubleshooting required isolating the RD (red LED) and IRD (infrared LED) ground terminals from the general ground plane to prevent power issues and enable proper sensor operation. 

20:04:48.612 -> Scanning...
20:04:48.644 -> I2C device found at address 0x3C  !
20:04:48.644 -> I2C device found at address 0x57  !
20:04:48.644 -> done
Download Design Files

Part (c): Real-Time GUI through Mechanical Gripper and WiFi

A Wi-Fi-connected grip strength meter that interfaces a user with a mechanical hand gripper, an 80 kg load cell, and an HX711 amplifier. The ESP32-S3 continuously measures grip force, streams it to a web dashboard, and uses a published relationship between handgrip strength and age to display an estimated “physiological age” in real time. The design is inspired by the open-source grip strength meter from NeuroTech Hub at WashU and the associated PLOS ONE paper on grip strength and age trajectories (Syddall et al., 2014), adapted to my load cell and handle geometry.

Mechanically, a custom 3D-printed gripper clamps around a CZL601-type 80 kg bar load cell (sourced from Amazon 80 kg load cell). I imported a 100 kg load cell CAD from GrabCAD, checked the mounting dimensions against the CZL601AC datasheet (online, download), and confirmed that the hole spacing and footprint match the commercial part used here.

Mechanical Design and Fabrication

CAD model of the 3D-printed grip strength base and load cell mounting region
Grip strength base CADTop view of the grip strength base showing the bar load cell pocket, mounting bosses, and handle interface.
Side view CAD of the hand gripper and load cell assembly
Side view of gripper assemblySide profile showing how the fixed base, moving handle, and load cell align along the force axis of the bar sensor.
Full CAD view of the grip strength device with base and handle
Full grip strength assemblyComplete CAD of the base, handle, and load cell, sized for comfortable adult hand placement and full-finger contact.
Close-up of mounting holes and clearances around the load cell in CAD
Load cell mounting holesDetail of the M6 clearance and counterbore geometry used to capture the load cell without constraining bending.
Perspective CAD view of the gripper handle and base
Handle ergonomicsPerspective view of the curved handle designed to distribute pressure across the palm and fingers during maximal grip.
Photo of drilled clearance hole aligned to the printed pilot in the base
Clearance hole verificationPrinted pilot holes used as drill guides to match the metric mounting dimensions from the CZL601AC datasheet.
Photo of the fully printed grip strength device before drilling and assembly
Fresh off the printer3D-printed base and handle components in PLA prior to post-processing and hardware installation.
Printed part clamped for drilling load cell mounting holes
Workholding for accurate drillingThe printed base clamped to the drill press table so the pilot features guide the final clearance holes into the load cell.
Drilling practiceTraining cuts on scrap material to dial in drill press settings and avoid cracking the printed base during final holes.
Final load cell holesDrilling the final M6 clearance holes through the printed base, constrained by the pilot features to preserve alignment.

Electronics and Calibration

Electronics assembly with HX711 breakout, ESP32-S3, and load cell wiring
Electronics stack-upHX711 amplifier breakout from Amazon wired to the ESP32-S3 and 80 kg load cell with short, twisted signal pairs for noise reduction.
Fully assembled grip strength device with load cell, electronics, and handle
Assembled grip strength meterCompleted mechanical and electrical assembly ready for calibration and software bring-up.
Serial Plotter view of load cell readings increasing with grip force
Serial Plotter calibration tracesRaw HX711 output converted to kilograms and visualized in the Arduino Serial Plotter while applying known weights and grip forces.
Web GUI showing grip strength value, estimated age, and scrolling chart
Wi-Fi grip strength dashboardBrowser-based GUI with live grip strength (kg), estimated age, and a Chart.js time series plot of recent squeezes.

Model Used for Age Estimation

The age-estimation logic in the firmware is based on the non-linear, sex-specific grip-strength trajectories reported in Dodds et al., 2014 (PLOS ONE). As shown in Figure 1 of that paper, grip strength rises rapidly through adolescence, peaks around ages 30–40, and then declines non-linearly with age, with different magnitudes for males and females.

Reference grip strength trajectories over the life course from Dodds et al., PLOS ONE 2014
Reference trajectories (Figure 1)Age-dependent grip strength curves for males and females from Dodds et al., 2014, used as the qualitative target for the embedded model.
Simplified quadratic grip strength model fitted to reference data
Quadratic approximation (Table 2-inspired)Simplified male and female trajectories using peak strengths and curvatures chosen to approximate the summary values reported in Table 2 of Dodds et al., 2014.

To reproduce this shape efficiently on the ESP32, the firmware uses inverted quadratic approximations centered at age 35, consistent with the observed peak in the PLOS ONE data. In the forward direction, grip strength is approximated as:

Males: Grip(age) ≈ 52 − 0.0089·(age − 35)2
Females: Grip(age) ≈ 32 − 0.0059·(age − 35)2

On the device, this relationship is analytically inverted so that the measured grip strength can be mapped back to an estimated age:

age = 35 + √((a − Grip)/b), where a is the peak strength (52 kg for males, 32 kg for females) and b is the curvature (0.0089 for males, 0.0059 for females). The firmware clamps grip strength to physiologically meaningful ranges before applying this formula so the square root remains well-defined. 

float ageFromGripMale(float g) {
  float a = 52.0f, b = 0.0089f;
  if (g > a) g = a;
  if (g < 5) g = 5;
  return 35.0f + sqrtf((a - g) / b);
}

float ageFromGripFemale(float g) {
  float a = 32.0f, b = 0.0059f;
  if (g > a) g = a;
  if (g < 4) g = 4;
  return 35.0f + sqrtf((a - g) / b);
}

For full methodological details and original tables/figures, see the open-access paper: Dodds et al., 2014, PLOS ONE (download local PDF). The implementation here is an educational approximation and not intended for clinical or diagnostic use.

End-to-end live demoReal-time demonstration of squeezing the mechanical gripper and watching the Wi-Fi dashboard update grip strength and estimated age on a laptop.

Related Design, Code, and Calibration Resources

User Interface Comparison

Summary of how each interface application connects users with input and output devices.

Application How It Interfaces with the User Input Device(s) Output Device(s)
(a) Button User Interface Button press patterns (single, double, triple press, hold) provide mode selection input. OLED display shows current menu state and mode options. Users receive immediate visual feedback for each interaction. Button (GPIO pin 4) OLED Display (SSD1306, I²C 0x3C)
LED (GPIO pin 3, flashlight mode)
(b) Real-Time GUI (OLED & WiFi) Physical finger placement on MAX30102 sensor provides input. OLED displays real-time sensor data locally. WiFi web interface enables remote monitoring with numerical displays and live plotting charts accessible from any web browser. MAX30102 Pulse Oximeter Sensor (I²C 0x57) OLED Display (SSD1306, I²C 0x3C)
WiFi Web Interface (HTTP Server with Chart.js visualization)
(c) Grip Strength GUI (Load Cell & WiFi) Users squeeze a mechanical hand gripper that transfers force into an 80 kg bar load cell. The ESP32-S3 measures grip strength through the HX711 amplifier and streams results to a WiFi web dashboard that displays live grip force and an estimated physiological age in real time. Mechanical gripper linked to 80 kg load cell (CZL601-type)
HX711 load cell amplifier		 WiFi Web Interface (HTTP Server with Chart.js visualization)
Optional Serial Plotter (for calibration traces)

Group Assignment: Compare as Many Tool Options as Possible

Compare as many tool options as possible for interface and application programming.

General Comparison: Interface & Application Programming Tools

Comprehensive comparison of interface and application programming tools available for embedded systems and IoT development. This analysis covers tools from the MIT Academy Interface & Application Programming class page, evaluating their capabilities, use cases, and trade-offs for different application scenarios.

Embedded Display Interfaces

Tool/Framework Description Pros Cons Best For
OLED (SSD1306) Monochrome OLED displays via I²C Low power, high contrast, simple I²C interface, pixel-level control Limited resolution (128x64), monochrome only, small display size Status displays, sensor readouts, simple menus, embedded dashboards
LCD Character Displays Character-based LCD displays (16x2, 20x4) Simple API, readable in sunlight, low cost Limited to text/characters, no graphics, requires backlight power Text-only interfaces, status messages, debugging output
TFT Color Displays Full-color TFT LCD displays Color graphics, touch support, high resolution High power consumption, complex drivers, larger footprint Rich GUIs, image display, interactive touch interfaces

Web-Based Interfaces

Tool/Framework Description Pros Cons Best For
HTTP Server (ESP32) Built-in HTTP server on ESP32 for web interfaces Remote access, cross-platform (any browser), no app installation, real-time updates Requires WiFi, network dependency, limited to local network without port forwarding Remote monitoring, data visualization, control panels, sensor dashboards
WebSockets Real-time bidirectional communication Low latency, bidirectional, efficient for frequent updates More complex than HTTP, requires persistent connection Real-time streaming, interactive controls, live data feeds
Chart.js JavaScript charting library for web interfaces Beautiful charts, interactive, responsive, easy integration Requires JavaScript, CDN dependency or local hosting Data visualization, time series plots, sensor monitoring dashboards

Mobile & Native App Frameworks

Tool/Framework Description Pros Cons Best For
React Native Cross-platform mobile app framework Cross-platform (iOS/Android), native performance, large ecosystem Complex setup, requires mobile development knowledge Full-featured mobile apps, production deployments
Flutter Google's UI toolkit for cross-platform apps Single codebase, high performance, customizable UI Dart language, larger app size, learning curve Custom mobile interfaces, platform-specific designs
Progressive Web Apps (PWA) Web apps with native-like features No app store, cross-platform, offline capability Limited native API access, browser dependency Web-based mobile interfaces, simple deployment

Specific Comparison: Tools Used in Individual Assignment

Detailed comparison of the specific interface programming tools implemented in this week's individual assignment, evaluating their performance, ease of use, and suitability for embedded health monitoring applications.

OLED Display Interface (Adafruit SSD1306)

Aspect Evaluation
Ease of Implementation Simple I²C interface, well-documented Adafruit library, minimal wiring (SDA, SCL, power, ground)
Display Quality High contrast monochrome display, crisp text rendering, suitable for sensor data visualization
Power Consumption Very low power draw, ideal for battery-powered applications
Limitations 128x64 pixel resolution limits detail, monochrome only, small physical size (0.96" typical)
Best Use Cases Local sensor readouts, menu systems, status indicators, simple data displays

WiFi Web Interface (ESP32 HTTP Server + Chart.js)

Aspect Evaluation
Ease of Implementation ESP32 WebServer library provides straightforward HTTP server, Chart.js CDN integration requires minimal setup
Remote Access Accessible from any device on WiFi network (phone, tablet, computer), no app installation required
Visualization Capabilities Chart.js enables rich data visualization with real-time plotting, smooth animations, and interactive features
Real-Time Updates JSON API endpoint provides efficient data transfer, 300ms refresh rate maintains responsive feel
Limitations Requires WiFi network, limited to local network without additional configuration, power consumption higher than OLED alone
Best Use Cases Remote monitoring, data logging visualization, multi-user access, professional dashboards

Button Input Interface

Aspect Evaluation
Implementation Approach Digital GPIO reading with debouncing, press pattern detection (single/double/triple/hold) enables mode navigation
User Experience Intuitive press patterns, immediate visual feedback on OLED, no complex UI navigation required
Reliability Hardware debouncing with INPUT_PULLUP, timeout-based pattern recognition prevents accidental triggers
Limitations Limited to single button interaction, pattern learning required, less flexible than touchscreen interfaces
Best Use Cases Simple mode selection, menu navigation, embedded system controls, low-cost input solutions

Comparison Summary

The combination of OLED display and WiFi web interface provides complementary benefits: OLED offers immediate local feedback with minimal latency and power consumption, while the WiFi interface enables rich visualization and remote access. The button-based input provides an intuitive, low-cost navigation method suitable for embedded systems. Together, these tools create a robust interface system that supports both local and remote interaction with sensor data.

Design Files

Design files and code documentation for interface and application programming projects.

ESP32-S3 Development Board and Pinouts

Code files for ESP32-S3 development board interfaces including I2C scanning, OLED display control, and button-based user interface systems. See Week 4 documentation for board design and Week 8 documentation for pinout configurations.

I2C Scanner (i2cscan_generic.ino)

Utility code for scanning and detecting I2C devices on the bus, essential for troubleshooting connection issues.

How the Code Works (Pseudocode)
SETUP:
  Initialize I2C bus
  Initialize Serial communication
  Print "I2C Scanner" message

LOOP:
  Print "Scanning..." message
  Initialize device counter to 0
  
  FOR each address from 1 to 126:
    Begin I2C transmission to address
    Check transmission result
    
    IF transmission successful (error == 0):
      Print device found at address (hex format)
      Increment device counter
    ELSE IF unknown error (error == 4):
      Print unknown error at address
    
  IF no devices found:
    Print "No I2C devices found"
  ELSE:
    Print "done"
  
  Wait 5 seconds before next scan
Key Features
  • Scans all 127 possible I2C addresses (0x01-0x7E)
  • Detects and reports connected devices with hex address format
  • Handles multiple error conditions (device not found, unknown errors)
  • Continuous scanning mode with 5-second intervals
  • Compatible with any I2C bus configuration (Wire, Wire1, etc.)
What You Need to Know
  • I2C Address Range: Valid addresses are 0x08-0x77 (8-119 decimal); addresses 0x00-0x07 and 0x78-0x7F are reserved
  • Common Addresses: OLED displays typically use 0x3C or 0x3D; sensors vary (MAX30102 uses 0x57)
  • Troubleshooting: If no devices found, check wiring (SDA, SCL, power, ground), verify pull-up resistors, confirm device power
  • Usage: Run this before connecting other devices to verify I2C bus is working correctly
Download: i2cscan_generic.ino

Hello World OLED Display (hello_world.ino)

Basic OLED display test code that initializes the display and shows "Hello World" text, confirming I2C communication and display functionality.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial communication at 115200 baud
  Wait 500ms for Serial to stabilize
  
  Initialize I2C bus with SDA pin 5, SCL pin 6
  Print "Starting..." message
  
  Attempt to initialize OLED display:
    IF initialization fails:
      Print "OLED not found" error
      Enter infinite loop (halt)
  
  Clear display buffer
  Set text size to 2
  Set text color to white
  Set cursor position to (0, 20)
  Print "Hello" line
  Print "World!" line
  Update display (send buffer to hardware)

LOOP:
  Empty (runs once, then waits)
Key Features
  • Simple OLED initialization and text display
  • Custom I2C pin configuration for XIAO ESP32-S3 (SDA=5, SCL=6)
  • Error handling with infinite loop if display not found
  • Text size and cursor positioning for centered display
  • One-time display update (no loop refresh needed for static text)
What You Need to Know
  • I2C Pin Configuration: XIAO ESP32-S3 uses pins 5 (SDA) and 6 (SCL) by default; verify your board's pinout
  • Display Address: SSD1306 OLED typically uses address 0x3C; some variants use 0x3D
  • Display Update: Must call display.display() to send buffer to hardware; drawing functions only modify buffer
  • Testing: Use this as first test after connecting OLED to verify wiring and I2C communication before adding complex features
  • Libraries Required: Adafruit_GFX, Adafruit_SSD1306, Wire
Download: hello_world.ino

Button User Interface (outputs.ino)

Mode-based navigation system using button press patterns (single, double, triple, hold) to control multiple output devices including OLED display, camera, sensors, and LED flashlight.

How the Code Works (Pseudocode)
SETUP:
  Initialize OLED display
  Initialize camera module
  Initialize sensors (MPU6050, HX711)
  Initialize button pin (INPUT_PULLUP)
  Initialize LED pin (OUTPUT)
  Set current mode to MENU
  Display menu screen

LOOP:
  Read button state
  
  IF button pressed:
    Record press start time
    Start press detection timer
  
  IF button released:
    Calculate press duration
    IF duration > HOLD_THRESHOLD:
      Activate flashlight mode
    ELSE:
      Increment press count
      Reset press timeout timer
  
  IF press timeout exceeded:
    Process accumulated press count:
      IF press count == 1: Switch to CAMERA mode
      IF press count == 2: Switch to SENSORS mode
      IF press count == 3: Switch to MENU mode
    Reset press count
  
  IF current mode == MENU:
    Display menu screen (button instructions)
  
  IF current mode == CAMERA:
    Capture camera frame
    Process image with dithering algorithm
    Display on OLED
    Run Edge Impulse inference (optional)
    Overlay results on display
  
  IF current mode == SENSORS:
    Read accelerometer/gyroscope data
    Read load cell data
    Display sensor readings on OLED
  
  Update display
Key Features
  • Press pattern detection: single (1x), double (2x), triple (3x), and hold
  • Mode-based navigation system (Menu, Camera, Sensors)
  • Button debouncing with timeout-based pattern recognition
  • Floyd-Steinberg dithering for camera-to-OLED video display
  • Edge Impulse AI inference integration for face detection
  • Multi-sensor integration (MPU6050 accelerometer/gyro, HX711 load cell)
  • Flashlight mode activated by button hold
What You Need to Know
  • Button Wiring: Use INPUT_PULLUP mode (button connects pin to GND when pressed, internal pull-up to 3.3V)
  • Press Detection: Press count is accumulated until timeout (1 second); longer timeout allows slower multiple presses
  • Mode Switching: Each mode has distinct display update logic; ensure proper initialization in setup()
  • Camera Performance: Video streaming to OLED requires significant processing; frame rate depends on resolution and dithering complexity
  • Dependencies: Requires camera_pins.h header file with XIAO ESP32-S3 camera pin definitions; see Ethical AI Use for development details
  • Sensor Conflicts: Code uses preprocessor directives to resolve sensor_t type conflict between ESP32 camera and Adafruit MPU6050 libraries
Download: outputs.ino | camera_pins.h | outputs.zip (complete project)

Grip Strength Monitor (Load Cell + WiFi GUI)

Design files and firmware for a Wi-Fi-enabled grip strength meter built around an 80 kg bar load cell, HX711 amplifier, and ESP32-S3. The mechanical design was informed by the open-source grip strength meter from NeuroTech Hub and validated against the CZL601AC bar load cell datasheet (online, download).

Mechanical Design Files (3D-Printed Components)

  • Base.3mf — main chassis that captures the bar load cell and anchors the fixed side of the gripper.
  • Case.3mf — protective enclosure for the ESP32-S3 and HX711 amplifier with cable strain relief.
  • Handle.3mf — curved grip handle that transfers hand force into the free end of the load cell.
  • Calibration Print.3mf — small test piece used to verify hole diameters and load cell clearances before printing the full assembly.

All parts were printed in PLA with high infill in the load paths to minimize creep and flex during repeated maximal grip trials.

Basic HX711 Reader (loadcell_simple.ino)

Minimal firmware to bring up the HX711 amplifier and read calibrated weight values over Serial for debugging and calibration.

How the Code Works (Pseudocode)
SETUP:
  Configure HX711 data and clock pins (DT=A1, SCK=A0)
  Initialize Serial at 115200 baud
  Begin HX711 with DT/SCK pins
  Set calibration factor (grams per ADC unit)
  Tare the scale so current load is zero

LOOP (every 200 ms):
  If HX711 is ready:
    Read averaged weight using get_units(4)
    Print "weight:<value>" to Serial for Serial Plotter
  Else:
    Print "HX711 not ready" for troubleshooting
Key Features
  • Simple initialization of the HX711 on analog pins A0/A1.
  • Configurable calibration factor for mapping counts to grams or kilograms.
  • Timed reads (200 ms) to keep Serial output manageable and Plotter-friendly.
  • Graceful handling of HX711 not-ready states.
What You Need to Know
  • Use for initial bring-up: Run this first when wiring the HX711 and load cell to confirm clean, stable readings.
  • Calibration factor: Determined experimentally by hanging known weights and adjusting until readings match; see the calibration notes in Calibration Chat.
  • Serial Plotter: The weight:<value> format is convenient for quickly visualizing changes while squeezing the handle.
Download: loadcell_simple.ino

Serial Plotter-Friendly Reader (loadcell_plot.ino)

Refined HX711 reader tuned for the Arduino Serial Plotter: it outputs a single numeric value per line for clean plotting of grip strength over time.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial at 115200 baud
  Initialize HX711 on DT=A1, SCK=A0
  Set calibration factor
  Tare the scale
  Optionally print debug messages when DEBUG=1

LOOP (every 200 ms):
  If HX711 is ready:
    Read filtered weight with get_units(4)
    Optionally print labeled debug text
    Print only the numeric weight to Serial for the Plotter
  Else:
    Optionally print "not ready" debug text
    Print 0 so the plotted line continues gracefully
Key Features
  • DEBUG toggle: Compile-time switch to enable/disable human-readable logs without breaking the Serial Plotter format.
  • Clean “one number per line” output for multi-trial grip testing in the Serial Plotter.
  • Automatic zero output when the HX711 is not ready to keep the time axis continuous.
  • Shared pinout and calibration approach with loadcell_simple.ino for easy swapping.
What You Need to Know
  • Use this sketch to tune calibration and visualize grip curves without any GUI overhead.
  • When collecting data for analysis, keep DEBUG set to 0 so the output is a pure numeric stream.
  • The sample interval (200 ms) gives a smooth trace while keeping file sizes reasonable for multi-second squeezes.
Download: loadcell_plot.ino

WiFi Grip Strength GUI (loadcell_gui.ino)

Full application firmware that exposes grip strength and an estimated age over Wi-Fi using an HTTP server and a Chart.js web dashboard.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial
  Initialize HX711 (pins, calibration factor, tare)
  Connect ESP32-S3 to WiFi (MIT network in this build)
  Start WebServer on port 80
  Register handlers:
    "/"        → serve HTML+JS GUI page from PROGMEM
    "/metrics" → serve JSON with current grip and age

LOOP:
  Handle incoming HTTP clients
  Every 200 ms:
    If HX711 is ready:
      Read smoothed grip strength (kg) via get_units(3)
      Clamp negative values to zero
      Store in global gripStrength

AGE ESTIMATION HELPERS:
  ageFromGripMale(g):
    Clamp g to plausible range
    Compute age using inverted quadratic fit derived from normative data
  ageFromGripFemale(g):
    Same structure with female-specific parameters

HTTP /metrics ENDPOINT:
  Read "sex" query parameter (default "male")
  Compute ageEstimate = ageFromGripMale/ageFromGripFemale(gripStrength)
  Return JSON:
    {"grip": <kg>, "age": <years>}

CLIENT-SIDE GUI (HTML + JS):
  Render dark-themed dashboard with:
    - Sex toggle buttons (male/female)
    - Numeric grip strength (kg) and age
    - Scrolling Chart.js line plot of recent grip values
  Poll /metrics every 200 ms and update DOM + chart
Key Features
  • Embedded HTML/JS dashboard served directly from the ESP32-S3 using PROGMEM.
  • Real-time grip strength plot using Chart.js with ~120 recent samples.
  • Simple sex toggle that switches between male and female age-estimation curves.
  • JSON API at /metrics for future extensions (e.g., logging clients).
What You Need to Know
  • WiFi credentials: Update the ssid and password constants to match your network.
  • Normative model: The age equations are simplified fits inspired by the grip-strength trajectories reported in Syddall et al., PLOS ONE 2014 and are for educational visualization only, not clinical use.
  • Browser requirements: Any modern browser with JavaScript and network access can connect to the ESP32-S3’s IP address to view the dashboard.
  • Development log: The full iterative design of this sketch is captured in the ChatGPT transcript: Grip Strength Monitor Code Chat.
Download: loadcell_gui.ino

Invisible String Chain of Hearts

Code files for the Invisible String pulse oximeter interface system, providing real-time health monitoring through OLED display and WiFi web interface. See Week 11 PCB design documentation for hardware details.

OLED GUI for Pulse Oximeter (pulse_vo2_reads_fixing.ino)

Local OLED display interface showing real-time pulse oximeter readings including heart rate (BPM), blood oxygen saturation (SpO2), and raw IR/RED LED sensor values.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial communication
  Initialize I2C bus (SDA=5, SCL=6) at 400kHz
  Initialize MAX30102 sensor
  Configure sensor:
    Set LED mode to RED + IR
    Set ADC range to 16384
    Set sample rate to 100 Hz
    Set pulse width to 411 μs
    Set LED brightness to medium (0x3F)
  Initialize OLED display
  Clear and prepare display

LOOP:
  Read IR and RED LED values from sensor
  
  Heart Rate Detection:
    Check for heartbeat in IR signal using peak detection
    IF heartbeat detected:
      Calculate time since last beat
      Calculate BPM = 60 / (time_delta / 1000)
      Set beat flag for visual indicator
      Update last beat timestamp
  
  SpO2 Calculation (every 300ms):
    Add IR and RED values to circular buffer
    IF buffer has 50 samples:
      Calculate DC components (average)
      Calculate AC components (RMS)
      Calculate R ratio = (AC_RED/DC_RED) / (AC_IR/DC_IR)
      Estimate SpO2 = 110 - 25 * R
      Clamp SpO2 to 70-100% range
  
  Serial Output:
    Print IR, RED, BPM for Serial Plotter visualization
  
  OLED Display Update:
    Clear display buffer
    Display IR value (small text)
    Display RED value (small text)
    Display BPM value (large text, size 2)
    Display SpO2 percentage (small text)
    IF beat detected: Draw heartbeat indicator dot
    Update display hardware
  
  Delay 20ms (50 Hz update rate)
Key Features
  • Real-time heart rate detection using peak detection algorithm on IR signal
  • SpO2 calculation using ratio-of-ratios method with DC/AC component analysis
  • Circular buffer system for storing 50 samples of IR/RED data
  • Visual heartbeat indicator (flashing dot) when pulse detected
  • Dual output: OLED display and Serial Plotter for real-time waveform visualization
  • Optimized sensor configuration for reliable readings (100 Hz sample rate, medium brightness)
What You Need to Know
  • Sensor Placement: Finger must cover sensor completely; proper contact ensures accurate readings
  • I2C Address: MAX30102 uses address 0x57; verify with I2C scanner if sensor not detected
  • Ground Isolation: RD and IRD pins must be isolated from main ground plane to prevent power issues (see Week 11 PCB design)
  • SpO2 Accuracy: Calculation provides estimation; medical-grade accuracy requires calibration and FDA-approved algorithms
  • Buffer Size: 50-sample buffer provides balance between calculation accuracy and response time
  • Libraries Required: MAX30105 (SparkFun library), Adafruit_GFX, Adafruit_SSD1306, heartRate.h (beat detection)
  • Troubleshooting: If sensor not detected, check power isolation, I2C wiring, and sensor initialization order
Download: pulse_vo2_reads_fixing.ino

WiFi Readings GUI (pulse_gui.ino)

WiFi-enabled web interface providing remote access to pulse oximeter data through HTTP server with JSON API endpoint for real-time data updates.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial communication
  Initialize I2C bus
  Initialize MAX30102 sensor
  Configure sensor (LED mode, sample rate, pulse width)
  Initialize OLED display
  Initialize WiFi:
    Connect to network (SSID, password)
    Wait for connection
    Print IP address
  Initialize HTTP server:
    Route "/" → serve GUI HTML page
    Route "/gui" → serve GUI HTML page
    Route "/metrics" → serve JSON data
  Start web server

LOOP:
  Handle incoming HTTP client requests
  
  Read IR and RED values from sensor
  
  Heart Rate Calculation:
    Check for heartbeat in IR signal
    IF heartbeat detected:
      Calculate BPM from time delta
      Update global BPM variable
  
  SpO2 Calculation:
    Add IR/RED to circular buffer
    IF buffer full (50 samples):
      Calculate SpO2 using ratio-of-ratios
      Update global SpO2 variable
  
  Update global variables (g_ir, g_red, g_bpm, g_spo2)
  
  OLED Display Update:
    Display IR, RED, BPM, SpO2 values
    Update display hardware
Key Features
  • Dual interface: OLED display (local) and WiFi web interface (remote)
  • HTTP server with embedded HTML page stored in PROGMEM
  • JSON API endpoint (/metrics) for real-time data retrieval
  • Automatic WiFi connection with connection status feedback
  • IP address display for easy access
  • Simultaneous sensor reading and web server operation
  • Global variable system for data sharing between sensor reading and HTTP handlers
What You Need to Know
  • WiFi Configuration: Update SSID and password in code; for MIT network, use generated device password from wifi.mit.edu
  • Network Access: Web interface accessible only from devices on same WiFi network; IP address printed to Serial Monitor
  • HTML Storage: GUI HTML page stored in PROGMEM (program memory) to conserve RAM; use PROGMEM for large strings
  • Server Handling: Must call server.handleClient() frequently in loop() for responsive web interface
  • Data Refresh: Client-side JavaScript polls /metrics endpoint every 300ms for real-time updates
  • Power Consumption: WiFi significantly increases power draw compared to OLED-only mode; consider power management for battery operation
  • Libraries Required: WiFi, WebServer, MAX30105, Adafruit_SSD1306
Download: pulse_gui.ino

WiFi Plot GUI (pulse_gui_2.ino)

Enhanced WiFi web interface with real-time plotting capabilities using Chart.js library, displaying live line charts for BPM and SpO2 values with automatic scrolling and data management.

How the Code Works (Pseudocode)
SETUP:
  (Same as pulse_gui.ino)
  Initialize WiFi, sensor, OLED, HTTP server

LOOP:
  (Same as pulse_gui.ino)
  Handle HTTP requests, read sensor, calculate BPM/SpO2

GUI HTML PAGE (embedded in PROGMEM):
  Load Chart.js library from CDN
  Create two Chart.js line chart instances:
    - BPM chart (y-axis: 40-160 BPM)
    - SpO2 chart (y-axis: 70-100%)
  Initialize data arrays for each chart
  
  JavaScript Update Function (runs every 300ms):
    Fetch JSON data from /metrics endpoint
    Update numerical displays (BPM, SpO2, IR, RED)
    Add new BPM value to BPM data array
    Add new SpO2 value to SpO2 data array
    IF array length > maxPoints (100):
      Remove oldest value (shift)
    Update chart labels (array indices)
    Update chart datasets with new data
    Call chart.update() to refresh display
  
  Set interval to call update function every 300ms
Key Features
  • Real-time line chart visualization using Chart.js library
  • Dual chart display: BPM and SpO2 trends over time
  • Automatic data scrolling: maintains 100 most recent data points
  • Numerical displays alongside charts for precise values
  • Responsive design with dark theme for OLED-style aesthetic
  • Automatic chart scaling with fixed y-axis ranges for consistent visualization
  • CDN-based Chart.js loading for minimal memory footprint
What You Need to Know
  • Chart.js CDN: Library loaded from jsdelivr.net CDN; requires internet connection on client device
  • Data Management: Arrays limited to 100 points to prevent memory overflow; older data automatically discarded
  • Update Rate: 300ms refresh rate balances responsiveness with server load; adjust based on network conditions
  • Chart Configuration: Y-axis ranges fixed (BPM: 40-160, SpO2: 70-100) for consistent scaling; modify in JavaScript if needed
  • Browser Compatibility: Requires modern browser with JavaScript enabled; tested on Chrome, Firefox, Safari
  • Performance: Chart updates are lightweight; multiple simultaneous clients may impact ESP32 performance
  • Offline Operation: Charts won't load if client device lacks internet (Chart.js CDN unavailable); consider local hosting for offline use
Download: pulse_gui_2.ino

Reflections & Learnings

Key insights and learnings from working with interface and application programming.

Contributions

Acknowledgements and team roles for interface and application programming work.

Ethical AI Use

Transparent documentation of AI assistance used in this week's interface and application programming work.

This section documents all AI assistance used during Week 12 interface and application programming work. ChatGPT was used for code development, troubleshooting, and technical guidance. All transcripts are linked below for transparency.

Menu System with Modes

AI assistance for developing the button-based menu system with mode navigation (Menu, Camera, Sensors) using press pattern detection. The conversation covered button debouncing, press pattern recognition, mode state management, and OLED menu display design.

Related to: Part (a): Simple Button User Interface on OLED

View ChatGPT Transcript: Menu System with Modes

I2C Device Not Found

Troubleshooting session for I2C device detection issues with MAX30102 pulse oximeter sensor. The conversation addressed power isolation problems, I2C wiring verification, sensor initialization order, and ground plane isolation requirements for accurate sensor operation.

Related to: Part (b): Real-Time Graphical User Interface through OLED and WiFi

View ChatGPT Transcript: I2C Device Not Found

Hello World Code

Development assistance for creating the initial OLED "Hello World" test program. The conversation covered I2C initialization, OLED display library setup, text rendering, and basic display configuration for XIAO ESP32-S3 development board.

Related to: Part (b): Real-Time Graphical User Interface through OLED and WiFi (initial OLED test)

View ChatGPT Transcript: Hello World Code

MAX30102 Initialization Fix

Technical guidance for fixing MAX30102 pulse oximeter sensor initialization issues. The conversation addressed sensor configuration parameters, LED brightness settings, sample rate optimization, initialization sequence requirements, and troubleshooting sensor communication problems.

Related to: Part (b): Real-Time Graphical User Interface through OLED and WiFi (pulse oximeter readings)

View ChatGPT Transcript: MAX30102 Initialization Fix

Grip Strength Monitor Code Design

Code-focused assistance for designing and refining the WiFi grip strength monitor firmware. The conversation covered HX711 bring-up, load cell pin mapping, Serial Plotter debugging sketches, the ESP32-S3 HTTP server, the Chart.js dashboard, and the age-estimation helpers used in loadcell_simple.ino, loadcell_plot.ino, and loadcell_gui.ino.

Related to: Part (c): Real-Time GUI through Mechanical Gripper and WiFi and Grip Strength Monitor design files

View ChatGPT Transcript: Grip Strength Monitor Code

Grip Strength Calibration & Scaling

Calibration-focused assistance for mapping HX711 counts to kilograms and validating the grip strength readings. The discussion walked through using the Serial Plotter, collecting reference weights, tuning the calibration factor, and sanity-checking the age-estimation model derived from normative grip strength data.

Related to: Part (c): Real-Time GUI through Mechanical Gripper and WiFi calibration workflow and the Grip Strength Monitor sketches.

View ChatGPT Transcript: Grip Strength Calibration

Grip Strength Monitor – Cursor Transcript

Full Cursor AI transcript focused on organizing the grip strength monitor section: structuring Part (c), integrating design files, embedding images and videos, and aligning captions, external references, and the Ethical AI Use documentation for the load cell project.

Related to: Part (c): Real-Time GUI through Mechanical Gripper and WiFi, Grip Strength Monitor design files, and this Ethical AI Use section.

View HTML Transcript Download Markdown Transcript

Week 12 Project Documentation

Complete Cursor AI transcript for Week 12 interface and application programming project documentation. This comprehensive conversation covers the creation and population of the Week 12 HTML page, including Individual Assignment sections (button UI and WiFi GUI), Group Assignment tool comparisons, Design Files documentation with pseudocode, and Ethical AI Use section organization. The transcript demonstrates the collaborative process of building professional documentation with structured content, embedded media, and comprehensive code documentation.

Related to: Complete Week 12 documentation including Individual Assignment, Group Assignment, Design Files, and overall page structure

View HTML Transcript Download Markdown Transcript

Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License

``` Finding and replacing the individual assignment section. Searching for it: Reading the individual assignment section to determine its length: Finding where the individual assignment section ends: Reading the end of the individual assignment section to identify the exact boundaries: Replacing the individual assignment section with the PCB engraving assignment. Reading the exact start to match it precisely: Replacing the individual assignment section with the PCB engraving assignment. Using a targeted replacement: ```html Week 13 · Wildcard Week
← Back to Home
[Profile Image Placeholder]

Week 13

Wildcard Week

Week Highlights

Key captures from the PCB engraving assignment with links to their sections.

ATtiny1626 Board Design

Final ATtiny1626 development board design with connectors and mounting holes

PCB Engraving

ATtiny1626 development board after fiber laser engraving

Soldered Board

Fully assembled ATtiny1626 development board with all components soldered

Blinking LED Demo

RP2354A Board Design

RP2354A development board design

PCB Engraving Detail

Close-up detail of PCB engraving showing trace quality

Table of Contents

Course Content

Training & Documentation

Assignments & Projects

Wildcard Week

This week focuses on exploring digital fabrication processes not covered in previous assignments. We'll design and produce something using computer-aided design and manufacturing, documenting requirements and including everything necessary for reproduction. This week also includes reflection on the impact and purpose of making (almost) anything.

Exploring new digital fabrication processes
Designing and producing with CAD/CAM
Understanding the impact and purpose of fabrication labs

This Week's Goals

  • Explore New Processes
    Design and produce something with a digital process not covered in other assignments
  • Complete Documentation
    Document requirements and include everything necessary to reproduce the project
  • Reflect on Impact
    Understand the purpose and impact of fabrication labs and making

Assignments

  • Group Assignment
    Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment
  • Individual Assignment
    Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment, documenting the requirements that your assignment meets, and including everything necessary to reproduce it

Tools & Materials

  • Carvera (CNC Mill) — Edge cuts and hole machining
  • Fiber Laser Cutter (xTool F2 Ultra) — PCB engraving
  • PCB Design Software (KiCad) — Board layout and design
  • ATtiny1626 Microcontroller — Target device for development board
  • RP2354A Microcontroller — Complex board design

Lecture Notes

Week 13 lecture covering major announcements, week 12 review, system integration reminders, and wildcard week preview.

Theme of the Week

'Step away from the panic'

Major Announcements

  • Subject evaluation: Required for funding the class. Provides feedback to the institute about the class. Important for future students if you care about successors in the class.
  • Calendar alarm: Wildcard week and recitation on why make (almost) anything: impact. Friday is cutoff for assignments and orders (10s of dollars per person from inventory).
  • Final presentation/final exam: Combining multiple additive and subtractive processes (not just design a board and 3D print a case). Goal is system integration out of parts. Final exam criteria:
    • Did you integrate and design a complete system?
    • Can you demo a final project? Here is the cool thing I did and here is how it works.
    • Make a final project video! (helps but not required)
    Focus on well-integrated device!

Review of Week 12 User Interfaces

  • Claire Wang: Music play and Windows 3.1 interface works!
  • Ryan Hoffman: DRV8251A discussion, heat sinks, breakout boards. Wildcards with waterjetting, EDM, multi-axis machining, laser cutting metal. Class in the spring on nature of mathematical modeling.
  • Srikanth Nadhamuni: Background and experience to visiting fellow at MIT. Raspberry Pi W for WiFi, n8n for cloud LLM data crunching. Software: Node.js, MCP bridge server with n8n based on bridge connected to device (NGV tunnel). All set! Fantastic experience, haven't worked so hard in a very long time and learning a lot of new things. Hope to take forward and build other systems. The whole culture of doing and trying yourself fascinating, especially with failing a number of times until you figure it out. Maybe set one up at an IIT in India or AI centers of excellence with education ministry into the Indian education system (see fablabkerala.in or vigyam ashram).
  • Ray Song: Not here.
  • Tyler Jensen (Lincoln Lab, Group 81): Final project discussion (nylon printer). Week 13: Easy for web serial interface for XIAO! Web server to TFT (I think I forgot to load the camera pins with my code for it).
  • Aditi Ramakrishnan: Sloan MBA and strategy consulting background. Discrete time filter (FFT is blown) in skimage.filters — make a bandpass filter, then run a series of these filters, much less computing only adds and multiplies for filtering in realtime.
  • Alexandros Gravalos: Not here.
  • Edward Chen: Check final watch project by Gulati into watch form factor. Clear print on the Form Labs printer, 0.1. Kaman filter for sensor fusion (in the spring class). For position — LSM6DSV16X from input devices. Acceleration at 7 kHz (at audio frequency).

Show and Tell

  • Handle to sensor WiFi user interface
  • Plug to audio LLM user interface

System Integration Reminders

  • Mount electronics
  • Strain relief the final projects

Preview for Wildcard Week

Assignment: Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment.

Recitation Notes: Why Make (Almost) Anything

Recitation exploring the purpose, impact, and scaling of fabrication labs and making infrastructure.

Map of Fab Labs

Why Make a Fab Lab?

  • Used to create a community
  • Building things for the community
  • Sustainability
  • Prototyping quickly

How Impact?

  • How to make spaces: How to measure impact. What is important about fab:
    • Fablabs in cities vs rural areas: The ability to decide their own futures and change their lives fundamentally. 'Safecast revolutionized citizen science' e.g. radiation map.
    • Bringing back manufacturing: Reducing reliance on supply chains.
    • Rural sustainability: Working with indigenous communities on creating technologies themselves at scale and measure their usefulness and efficacy to preserve their ancestral knowledge:
      • How to establish labs there
      • How to make sure the labs get used
    • Hygiene technologies with Proctor and Gamble: Highly commercial. Lots of plastic waste. How can we change how they produce? How to make their products get there through resellers?
    • Trip to Peru and ran workshops, questionnaires, analysis: Collaboration developed into how to produce the products but also how to test their products to be market valuable e.g. mosquito repellents. Out of three plants, two worked better and one wasn't working at all (which is important to know!).

What Does It Mean to Design Infrastructure?

  • What did we want this lab to be able to do?
    • Workshops and questionnaires
    • How much you educate people based on the info they have with the issues the community is facing
    • Energy concerns to consider, some machines just drain the grid and can't be used. Solar powered, battery powered machines, reducing energy consumption of machines. Many concerns important.
  • Ethical questions
  • How to maintain resources

Case Study: Water Purifier Packets

Use them, change them, source them locally, ingredients found locally, how to distribute them globally.

Funding Models

First few fablabs were NSF funded. Now corporate CSR, regional funding, labor funding (10 different ways). Successful fablabs are heterogeneous with lots of ways of funding. The ones that fail usually just have one sponsor.

Example: DIY Raman spectrometer for water purification (even after purifications still have sulfates and improving that too).

What Does It Mean to Scale Infrastructure?

(Besides a lot of meetings!) What is a reasonable way to design a data collection process about what is needed and how to achieve it.

Back to the Map: Expansion

Timeline of development, cocreation, portable, skin analysis, water testing, biomaterial tech, microscopy.

Initial Results from Boston

How to Confront Local Impact
  • Collab with University of Hamburg. Motivation for how much food can be produced in Boston. Where food waste goes and what Boston produces locally. Make things for yourself locally.
  • Impact directly in the community you're living in.

Hatchspace

Focused on rehabilitation of addicts with woodworking. (Vermont is wood producing state).

Example Course Program

  • All-in session and systemic impact
  • Natural and cultural context
  • Skills and workshop
  • Economic vitality
  • Skills and workshop
  • Co-work session
  • Solutionspalooza

In the Course

Hands-on component (no physical robot exists that can do it) and community component is also important. Inclusion is important. Solving unconscious and institutional biases.

  • 'Fabrica! Lab' — Creating new laboratory spaces for female high school students, courses aimed for women in technology, online advising sessions for females interested in tech.
  • Makerspaces — Access to tools behind closed doors at universities, makes a huge difference for people who don't have the ability to prototype for themselves.
  • Materiom — Fablab affiliated project on organic waste for biomaterials.
  • Fablab León
  • Skylab workshop experiment — How to run a noodle shop out of a fablab (creating food from the community).
  • Academany — Global distributed campus for high school education. Fablab all-in (belonging, impact, community), fab futures (future vocational skills), bio academy (synthetic biology), fabricademy (textiles, fab, bio), fab academy (digital fab apps and implications).

Trade-off Between Impactful and Dangerous

People could be doing bad, but not because doing it with a group people with values.

Questions

Clarification: Adding infrastructure to existing fablab infrastructure to help support specific community needs (not specialized fab labs).

Foundations for Fab Futures

July 27-31, 2026 at Fab Boston 2026.

Useful Documentation

Essential resources for wildcard week digital fabrication processes and PCB design.

Class Page

Wildcard Week - MIT Academy

Comprehensive resource covering wildcard week assignment requirements and possibilities including grinding, multi-axis machining, electrical discharge machining, waterjet cutting, flatbed cutting, plasma cutting, laser metal cutting, laser micromachining, welding, molding and casting, folding, robotics, electronics, embedded programming, food, materials, biotechnology, textiles, and composites.

Key Topics

  • Machining: Grinding, multi-axis machining, electrical discharge machining, waterjet cutting, plasma cutting, laser metal cutting, laser micromachining
  • Molding & Casting: Vacuum forming, rotocasting
  • Folding: Mathematics, form and function, kirigami
  • Robotics: Arms, construction, soft actuation pneumatic inflatable
  • Electronics: Pick and place, programmable logic
  • Embedded Programming: Machine learning, machine vision
  • Textiles: Fiber processes, knitting, embroidery (PEmbroider, Ink/Stitch), Fabricademy
  • Composites: Various composite fabrication techniques

ATtiny1626 Development Board References

Embedded Programming Course Resources

Course resources for embedded programming with ATtiny412 microcontroller examples:

Embedded Programming - MIT Academy

ATtiny412 Echo Example Image

Individual Assignment: PCB Engraving with Fiber Laser

Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment. This assignment demonstrates PCB design and fabrication using a combination of CNC milling (Carvera) for edge cuts and hole machining, and fiber laser engraving (xTool F2 Ultra) for trace creation on copper-clad boards. The project includes designing and fabricating two development boards: a simple ATtiny1626 development board and a complex RP2354A development board.

PCB Engraving Process

This project explores PCB fabrication using fiber laser engraving, a process not covered in previous assignments. The workflow combines subtractive manufacturing techniques: CNC milling for mechanical features (edge cuts and holes) and laser engraving for electrical traces. This approach enables rapid prototyping of custom PCBs without requiring chemical etching or specialized PCB manufacturing facilities.

Tools and Equipment

  • Carvera (CNC Mill): Used for edge cuts and hole machining. The laser cannot effectively cut through the board material, so mechanical cutting is required for board outline and mounting holes.
  • Fiber Laser Cutter (xTool F2 Ultra): Used for PCB trace engraving. The laser removes copper from the board surface to create electrical traces and pads.
  • PCB Design Software (KiCad): Used for schematic capture, PCB layout, and design rule checking.

Boards Designed

  • Simple Board: ATtiny1626 development board with connectors, resistors, LED, and capacitor
  • Complex Board: RP2354A development board with more advanced routing and component placement

Board Design Considerations

  • Connector Placement: Top and bottom for connectors, right side for flashing. Connectors along edges to minimize form factor and maximize space usage.
  • Vertical Connectors: Used instead of horizontal connectors because horizontal connectors risk being snapped during use.
  • Black Area Avoidance: Avoid large black areas because laser does not work well with that (keep traces closer and further to minimize black areas). Note: Need to characterize maximum black until it burns the board because dumping too much heat in one place can damage the board.
  • Breadboard Compatibility: Put connectors on 100mil spacing grid size for breadboardability.
  • Pin Count Adjustment: Missed six pins in initial design, so switched from 6-pin headers to 9-pin (distributed six on top and bottom).
  • I2C Resistors: No SDA or SCL resistors included to keep flexibility for future use. May add spot for zero-ohm or pull-up resistor later but keeping it simple for now.
  • Mounting Holes: Added aligned mounting holes (M3 usually — for 3mm screws) for mechanical mounting.
  • Rounded Edge Cuts: Do 90 degrees, copy, drag, and complete the shape for rounded corners.

Design Rules

  • 0.1 mm spacing minimum
  • 0.15 mm trace width minimum
  • 0.15 mm clearance between plane and the rest

Ports and Pins

ATtiny1626 is an 8-bit microcontroller with 8 pins maximum per port. Each port has 8 pins maximum (some less). Need to specify port letter and pin number:

  • PA (0-7)
  • PB (0-7)
  • PC (0-7)

Postprocessing

  • For Carvera: Add new layer with just the holes in Photoshop (only holes for machining).
  • For Laser Engraving: Get rid of the holes for the F2 tools engraving in Inkscape (the frame and the board for alignment, then only engrave the board, not the edges).

Carvera Machining

Using mods → mill 2D PCB workflow:

  • 0.12mm cut depth and max depth

PCB Engraving Process

Using xTool F2 Ultra fiber laser:

  • Use tape for laser alignment
  • Run a test first on spare copper before the Carvera cut board to make sure focus is good (2.7mm thickness setting worked, board is actually 1.6-1.7mm thick)
  • Sand after engraving to clean up any residue
  • Worked with Bantam Tools FR1 (not random Amazon copper)
  • Perform short circuit test after engraving

Soldering

Using solder gun (heat gun) for component assembly.

Components

  • 1x 6-pin flipflop headers
  • 2x 9-pin flipflop headers
  • 1x 4.7k resistor
  • 1x 1k resistor
  • 1x LED
  • 1x 1uF or 10uF capacitor

Design Files

Download design files: ATtiny_QFN.zip and RP2354A-dev-v1.1.zip

Final ATtiny1626 development board design showing component placement and routing
ATtiny1626 final designComplete PCB layout with connectors, components, traces, and mounting holes optimized for laser engraving.
ATtiny1626 development board after fiber laser engraving showing copper traces
PCB after engravingCopper-clad board with traces engraved using fiber laser, ready for component soldering.
Fully assembled ATtiny1626 development board with all components soldered
Soldered boardComplete ATtiny1626 development board with headers, resistors, LED, and capacitor soldered in place.
Blinking LED demoVideo demonstration of the completed ATtiny1626 development board running a simple LED blink program, confirming successful fabrication and programming.
Close-up detail of PCB engraving showing trace quality and copper removal
PCB engraving detailClose-up view of fiber laser engraved traces showing clean copper removal and precise trace definition.

Interface with User

The application interfaces a user with input and/or output devices through the ATtiny1626 development board. The following table describes how the application interfaces with the user:

How It Interfaces with User Input Device(s) Output Device(s)
(a) LED Blink Demonstration None (programmed behavior) LED (visual feedback indicating board functionality)
(b) Future Interface Applications GPIO pins (PA, PB, PC ports) available for sensors, buttons, switches GPIO pins (PA, PB, PC ports) available for LEDs, displays, actuators

Part (a): Simple Button User Interface on OLED

A mode-based user interface system that interfaces users with multiple input and output devices through a simple button press interface. The system provides visual feedback on an OLED display and enables navigation between different modes (Menu, Camera, Sensors) using button press patterns. Users interact by pressing a button multiple times to select modes, with visual confirmation displayed on the OLED screen.

Interface Design

The interface uses a mode-based navigation system where button presses trigger mode changes. A single press enters Camera mode, two presses enter Sensors mode, three presses return to Menu, and holding the button activates a flashlight function. The OLED display shows the current menu state and provides clear visual feedback for each mode transition. See Ethical AI Use: Menu System with Modes for AI-assisted development details.

OLED button user interface menu system displaying mode selection options
OLED button user interface menuMenu screen showing available modes: Camera, Sensors, and Menu navigation options with button press instructions.
Button UI demonstrationVideo showing button press interactions navigating through different modes on the OLED display.
First video stream on OLEDInitial camera feed streaming to OLED display using dithering algorithm for monochrome conversion, demonstrating real-time video output interface.
Download Design Files
  • outputs.ino — Button user interface code with mode system
  • camera_pins.h — Camera pin definitions header file
  • outputs.zip — Complete project archive including all dependencies

Part (b): Real-Time Graphical User Interface through OLED and WiFi

A dual-interface health monitoring system that interfaces users with a MAX30102 pulse oximeter sensor through both an OLED display and a WiFi-enabled web interface. The system provides real-time visualization of heart rate (BPM), blood oxygen saturation (SpO2), and raw sensor data (IR and RED LED readings) through multiple output channels. Users can view data locally on the OLED display or remotely via a web browser accessing the ESP32-S3's built-in HTTP server. See Ethical AI Use: I2C Device Not Found for troubleshooting documentation.

Interface Design

The system provides dual-interface access: a local OLED display shows real-time sensor readings (IR, RED, BPM, SpO2) with visual heartbeat indicators, while a WiFi web interface provides comprehensive data visualization including numerical displays and real-time plotting charts. The web interface uses Chart.js for dynamic graph generation and automatically refreshes every 300ms to maintain real-time data updates. Both interfaces run simultaneously, enabling local monitoring and remote access.

Hello World on OLED

Initial OLED display test showing successful I2C communication and display initialization. See Ethical AI Use: Hello World Code for development details.

Hello World display on OLED for Invisible String project showing successful display initialization
Hello World on OLEDInitial OLED test confirming I2C communication and display functionality before implementing sensor interfaces.
Pulse Oximeter Readings on OLED

Real-time pulse oximeter data displayed on OLED showing IR and RED LED readings, heart rate (BPM), and blood oxygen saturation (SpO2) percentage. A heartbeat indicator flashes when a pulse is detected. See Ethical AI Use: MAX30102 Initialization Fix for sensor setup documentation.

Pulse oximeter readings on OLED displaying IR, RED, BPM, and SpO2 values
OLED sensor readings displayReal-time pulse oximeter data showing IR and RED LED values, heart rate (BPM), and blood oxygen saturation (SpO2) with heartbeat indicator.
BPM and SpO2 demonstrationVideo showing real-time heart rate and blood oxygen saturation measurements updating on OLED display with sensor interaction.
Pulse Oximeter Readings on WiFi GUI

WiFi web interface providing remote access to pulse oximeter data through a responsive HTML dashboard. The interface displays real-time numerical values for BPM, SpO2, IR, and RED readings with automatic data refresh. The web server runs on the ESP32-S3, allowing access from any device on the same WiFi network.

WiFi web interface displaying real-time pulse oximeter readings including BPM, SpO2, IR, and RED values
WiFi GUI readings dashboardRemote web interface showing real-time pulse oximeter data accessible from any device on the WiFi network, displaying BPM, SpO2, IR, and RED values with automatic updates.
Pulse Oximeter Plots on WiFi GUI

Enhanced WiFi web interface with real-time plotting capabilities using Chart.js library. The interface displays live line charts for BPM and SpO2 values, showing trends over time with automatic scrolling and data point management. This visualization enables users to observe patterns in heart rate and blood oxygen levels during monitoring sessions.

Serial monitor output showing sensor readings rising on touch interaction
Serial monitor sensor responseSerial output demonstrating sensor readings increase when finger is placed on MAX30102 sensor, showing IR and RED LED response to touch.
WiFi web interface with real-time plotting of BPM and SpO2 data using Chart.js
WiFi GUI with plotting chartsEnhanced web interface displaying real-time line charts for BPM and SpO2 values, showing trends over time with automatic data refresh and chart scrolling.

I2C Device Detection

Successful I2C device detection after fixing power isolation issues. The system now correctly identifies the OLED display at address 0x3C and the MAX30102 sensor at address 0x57. Initial troubleshooting required isolating the RD (red LED) and IRD (infrared LED) ground terminals from the general ground plane to prevent power issues and enable proper sensor operation. 

20:04:48.612 -> Scanning...
20:04:48.644 -> I2C device found at address 0x3C  !
20:04:48.644 -> I2C device found at address 0x57  !
20:04:48.644 -> done
Download Design Files

Part (c): Real-Time GUI through Mechanical Gripper and WiFi

A Wi-Fi-connected grip strength meter that interfaces a user with a mechanical hand gripper, an 80 kg load cell, and an HX711 amplifier. The ESP32-S3 continuously measures grip force, streams it to a web dashboard, and uses a published relationship between handgrip strength and age to display an estimated “physiological age” in real time. The design is inspired by the open-source grip strength meter from NeuroTech Hub at WashU and the associated PLOS ONE paper on grip strength and age trajectories (Syddall et al., 2014), adapted to my load cell and handle geometry.

Mechanically, a custom 3D-printed gripper clamps around a CZL601-type 80 kg bar load cell (sourced from Amazon 80 kg load cell). I imported a 100 kg load cell CAD from GrabCAD, checked the mounting dimensions against the CZL601AC datasheet (online, download), and confirmed that the hole spacing and footprint match the commercial part used here.

Mechanical Design and Fabrication

CAD model of the 3D-printed grip strength base and load cell mounting region
Grip strength base CADTop view of the grip strength base showing the bar load cell pocket, mounting bosses, and handle interface.
Side view CAD of the hand gripper and load cell assembly
Side view of gripper assemblySide profile showing how the fixed base, moving handle, and load cell align along the force axis of the bar sensor.
Full CAD view of the grip strength device with base and handle
Full grip strength assemblyComplete CAD of the base, handle, and load cell, sized for comfortable adult hand placement and full-finger contact.
Close-up of mounting holes and clearances around the load cell in CAD
Load cell mounting holesDetail of the M6 clearance and counterbore geometry used to capture the load cell without constraining bending.
Perspective CAD view of the gripper handle and base
Handle ergonomicsPerspective view of the curved handle designed to distribute pressure across the palm and fingers during maximal grip.
Photo of drilled clearance hole aligned to the printed pilot in the base
Clearance hole verificationPrinted pilot holes used as drill guides to match the metric mounting dimensions from the CZL601AC datasheet.
Photo of the fully printed grip strength device before drilling and assembly
Fresh off the printer3D-printed base and handle components in PLA prior to post-processing and hardware installation.
Printed part clamped for drilling load cell mounting holes
Workholding for accurate drillingThe printed base clamped to the drill press table so the pilot features guide the final clearance holes into the load cell.
Drilling practiceTraining cuts on scrap material to dial in drill press settings and avoid cracking the printed base during final holes.
Final load cell holesDrilling the final M6 clearance holes through the printed base, constrained by the pilot features to preserve alignment.

Electronics and Calibration

Electronics assembly with HX711 breakout, ESP32-S3, and load cell wiring
Electronics stack-upHX711 amplifier breakout from Amazon wired to the ESP32-S3 and 80 kg load cell with short, twisted signal pairs for noise reduction.
Fully assembled grip strength device with load cell, electronics, and handle
Assembled grip strength meterCompleted mechanical and electrical assembly ready for calibration and software bring-up.
Serial Plotter view of load cell readings increasing with grip force
Serial Plotter calibration tracesRaw HX711 output converted to kilograms and visualized in the Arduino Serial Plotter while applying known weights and grip forces.
Web GUI showing grip strength value, estimated age, and scrolling chart
Wi-Fi grip strength dashboardBrowser-based GUI with live grip strength (kg), estimated age, and a Chart.js time series plot of recent squeezes.

Model Used for Age Estimation

The age-estimation logic in the firmware is based on the non-linear, sex-specific grip-strength trajectories reported in Dodds et al., 2014 (PLOS ONE). As shown in Figure 1 of that paper, grip strength rises rapidly through adolescence, peaks around ages 30–40, and then declines non-linearly with age, with different magnitudes for males and females.

Reference grip strength trajectories over the life course from Dodds et al., PLOS ONE 2014
Reference trajectories (Figure 1)Age-dependent grip strength curves for males and females from Dodds et al., 2014, used as the qualitative target for the embedded model.
Simplified quadratic grip strength model fitted to reference data
Quadratic approximation (Table 2-inspired)Simplified male and female trajectories using peak strengths and curvatures chosen to approximate the summary values reported in Table 2 of Dodds et al., 2014.

To reproduce this shape efficiently on the ESP32, the firmware uses inverted quadratic approximations centered at age 35, consistent with the observed peak in the PLOS ONE data. In the forward direction, grip strength is approximated as:

Males: Grip(age) ≈ 52 − 0.0089·(age − 35)2
Females: Grip(age) ≈ 32 − 0.0059·(age − 35)2

On the device, this relationship is analytically inverted so that the measured grip strength can be mapped back to an estimated age:

age = 35 + √((a − Grip)/b), where a is the peak strength (52 kg for males, 32 kg for females) and b is the curvature (0.0089 for males, 0.0059 for females). The firmware clamps grip strength to physiologically meaningful ranges before applying this formula so the square root remains well-defined. 

float ageFromGripMale(float g) {
  float a = 52.0f, b = 0.0089f;
  if (g > a) g = a;
  if (g < 5) g = 5;
  return 35.0f + sqrtf((a - g) / b);
}

float ageFromGripFemale(float g) {
  float a = 32.0f, b = 0.0059f;
  if (g > a) g = a;
  if (g < 4) g = 4;
  return 35.0f + sqrtf((a - g) / b);
}

For full methodological details and original tables/figures, see the open-access paper: Dodds et al., 2014, PLOS ONE (download local PDF). The implementation here is an educational approximation and not intended for clinical or diagnostic use.

End-to-end live demoReal-time demonstration of squeezing the mechanical gripper and watching the Wi-Fi dashboard update grip strength and estimated age on a laptop.

Related Design, Code, and Calibration Resources

User Interface Comparison

Summary of how each interface application connects users with input and output devices.

Application How It Interfaces with the User Input Device(s) Output Device(s)
(a) Button User Interface Button press patterns (single, double, triple press, hold) provide mode selection input. OLED display shows current menu state and mode options. Users receive immediate visual feedback for each interaction. Button (GPIO pin 4) OLED Display (SSD1306, I²C 0x3C)
LED (GPIO pin 3, flashlight mode)
(b) Real-Time GUI (OLED & WiFi) Physical finger placement on MAX30102 sensor provides input. OLED displays real-time sensor data locally. WiFi web interface enables remote monitoring with numerical displays and live plotting charts accessible from any web browser. MAX30102 Pulse Oximeter Sensor (I²C 0x57) OLED Display (SSD1306, I²C 0x3C)
WiFi Web Interface (HTTP Server with Chart.js visualization)
(c) Grip Strength GUI (Load Cell & WiFi) Users squeeze a mechanical hand gripper that transfers force into an 80 kg bar load cell. The ESP32-S3 measures grip strength through the HX711 amplifier and streams results to a WiFi web dashboard that displays live grip force and an estimated physiological age in real time. Mechanical gripper linked to 80 kg load cell (CZL601-type)
HX711 load cell amplifier		 WiFi Web Interface (HTTP Server with Chart.js visualization)
Optional Serial Plotter (for calibration traces)

Group Assignment: Compare as Many Tool Options as Possible

Compare as many tool options as possible for interface and application programming.

General Comparison: Interface & Application Programming Tools

Comprehensive comparison of interface and application programming tools available for embedded systems and IoT development. This analysis covers tools from the MIT Academy Interface & Application Programming class page, evaluating their capabilities, use cases, and trade-offs for different application scenarios.

Embedded Display Interfaces

Tool/Framework Description Pros Cons Best For
OLED (SSD1306) Monochrome OLED displays via I²C Low power, high contrast, simple I²C interface, pixel-level control Limited resolution (128x64), monochrome only, small display size Status displays, sensor readouts, simple menus, embedded dashboards
LCD Character Displays Character-based LCD displays (16x2, 20x4) Simple API, readable in sunlight, low cost Limited to text/characters, no graphics, requires backlight power Text-only interfaces, status messages, debugging output
TFT Color Displays Full-color TFT LCD displays Color graphics, touch support, high resolution High power consumption, complex drivers, larger footprint Rich GUIs, image display, interactive touch interfaces

Web-Based Interfaces

Tool/Framework Description Pros Cons Best For
HTTP Server (ESP32) Built-in HTTP server on ESP32 for web interfaces Remote access, cross-platform (any browser), no app installation, real-time updates Requires WiFi, network dependency, limited to local network without port forwarding Remote monitoring, data visualization, control panels, sensor dashboards
WebSockets Real-time bidirectional communication Low latency, bidirectional, efficient for frequent updates More complex than HTTP, requires persistent connection Real-time streaming, interactive controls, live data feeds
Chart.js JavaScript charting library for web interfaces Beautiful charts, interactive, responsive, easy integration Requires JavaScript, CDN dependency or local hosting Data visualization, time series plots, sensor monitoring dashboards

Mobile & Native App Frameworks

Tool/Framework Description Pros Cons Best For
React Native Cross-platform mobile app framework Cross-platform (iOS/Android), native performance, large ecosystem Complex setup, requires mobile development knowledge Full-featured mobile apps, production deployments
Flutter Google's UI toolkit for cross-platform apps Single codebase, high performance, customizable UI Dart language, larger app size, learning curve Custom mobile interfaces, platform-specific designs
Progressive Web Apps (PWA) Web apps with native-like features No app store, cross-platform, offline capability Limited native API access, browser dependency Web-based mobile interfaces, simple deployment

Specific Comparison: Tools Used in Individual Assignment

Detailed comparison of the specific interface programming tools implemented in this week's individual assignment, evaluating their performance, ease of use, and suitability for embedded health monitoring applications.

OLED Display Interface (Adafruit SSD1306)

Aspect Evaluation
Ease of Implementation Simple I²C interface, well-documented Adafruit library, minimal wiring (SDA, SCL, power, ground)
Display Quality High contrast monochrome display, crisp text rendering, suitable for sensor data visualization
Power Consumption Very low power draw, ideal for battery-powered applications
Limitations 128x64 pixel resolution limits detail, monochrome only, small physical size (0.96" typical)
Best Use Cases Local sensor readouts, menu systems, status indicators, simple data displays

WiFi Web Interface (ESP32 HTTP Server + Chart.js)

Aspect Evaluation
Ease of Implementation ESP32 WebServer library provides straightforward HTTP server, Chart.js CDN integration requires minimal setup
Remote Access Accessible from any device on WiFi network (phone, tablet, computer), no app installation required
Visualization Capabilities Chart.js enables rich data visualization with real-time plotting, smooth animations, and interactive features
Real-Time Updates JSON API endpoint provides efficient data transfer, 300ms refresh rate maintains responsive feel
Limitations Requires WiFi network, limited to local network without additional configuration, power consumption higher than OLED alone
Best Use Cases Remote monitoring, data logging visualization, multi-user access, professional dashboards

Button Input Interface

Aspect Evaluation
Implementation Approach Digital GPIO reading with debouncing, press pattern detection (single/double/triple/hold) enables mode navigation
User Experience Intuitive press patterns, immediate visual feedback on OLED, no complex UI navigation required
Reliability Hardware debouncing with INPUT_PULLUP, timeout-based pattern recognition prevents accidental triggers
Limitations Limited to single button interaction, pattern learning required, less flexible than touchscreen interfaces
Best Use Cases Simple mode selection, menu navigation, embedded system controls, low-cost input solutions

Comparison Summary

The combination of OLED display and WiFi web interface provides complementary benefits: OLED offers immediate local feedback with minimal latency and power consumption, while the WiFi interface enables rich visualization and remote access. The button-based input provides an intuitive, low-cost navigation method suitable for embedded systems. Together, these tools create a robust interface system that supports both local and remote interaction with sensor data.

Design Files

Design files and code documentation for interface and application programming projects.

ESP32-S3 Development Board and Pinouts

Code files for ESP32-S3 development board interfaces including I2C scanning, OLED display control, and button-based user interface systems. See Week 4 documentation for board design and Week 8 documentation for pinout configurations.

I2C Scanner (i2cscan_generic.ino)

Utility code for scanning and detecting I2C devices on the bus, essential for troubleshooting connection issues.

How the Code Works (Pseudocode)
SETUP:
  Initialize I2C bus
  Initialize Serial communication
  Print "I2C Scanner" message

LOOP:
  Print "Scanning..." message
  Initialize device counter to 0
  
  FOR each address from 1 to 126:
    Begin I2C transmission to address
    Check transmission result
    
    IF transmission successful (error == 0):
      Print device found at address (hex format)
      Increment device counter
    ELSE IF unknown error (error == 4):
      Print unknown error at address
    
  IF no devices found:
    Print "No I2C devices found"
  ELSE:
    Print "done"
  
  Wait 5 seconds before next scan
Key Features
  • Scans all 127 possible I2C addresses (0x01-0x7E)
  • Detects and reports connected devices with hex address format
  • Handles multiple error conditions (device not found, unknown errors)
  • Continuous scanning mode with 5-second intervals
  • Compatible with any I2C bus configuration (Wire, Wire1, etc.)
What You Need to Know
  • I2C Address Range: Valid addresses are 0x08-0x77 (8-119 decimal); addresses 0x00-0x07 and 0x78-0x7F are reserved
  • Common Addresses: OLED displays typically use 0x3C or 0x3D; sensors vary (MAX30102 uses 0x57)
  • Troubleshooting: If no devices found, check wiring (SDA, SCL, power, ground), verify pull-up resistors, confirm device power
  • Usage: Run this before connecting other devices to verify I2C bus is working correctly
Download: i2cscan_generic.ino

Hello World OLED Display (hello_world.ino)

Basic OLED display test code that initializes the display and shows "Hello World" text, confirming I2C communication and display functionality.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial communication at 115200 baud
  Wait 500ms for Serial to stabilize
  
  Initialize I2C bus with SDA pin 5, SCL pin 6
  Print "Starting..." message
  
  Attempt to initialize OLED display:
    IF initialization fails:
      Print "OLED not found" error
      Enter infinite loop (halt)
  
  Clear display buffer
  Set text size to 2
  Set text color to white
  Set cursor position to (0, 20)
  Print "Hello" line
  Print "World!" line
  Update display (send buffer to hardware)

LOOP:
  Empty (runs once, then waits)
Key Features
  • Simple OLED initialization and text display
  • Custom I2C pin configuration for XIAO ESP32-S3 (SDA=5, SCL=6)
  • Error handling with infinite loop if display not found
  • Text size and cursor positioning for centered display
  • One-time display update (no loop refresh needed for static text)
What You Need to Know
  • I2C Pin Configuration: XIAO ESP32-S3 uses pins 5 (SDA) and 6 (SCL) by default; verify your board's pinout
  • Display Address: SSD1306 OLED typically uses address 0x3C; some variants use 0x3D
  • Display Update: Must call display.display() to send buffer to hardware; drawing functions only modify buffer
  • Testing: Use this as first test after connecting OLED to verify wiring and I2C communication before adding complex features
  • Libraries Required: Adafruit_GFX, Adafruit_SSD1306, Wire
Download: hello_world.ino

Button User Interface (outputs.ino)

Mode-based navigation system using button press patterns (single, double, triple, hold) to control multiple output devices including OLED display, camera, sensors, and LED flashlight.

How the Code Works (Pseudocode)
SETUP:
  Initialize OLED display
  Initialize camera module
  Initialize sensors (MPU6050, HX711)
  Initialize button pin (INPUT_PULLUP)
  Initialize LED pin (OUTPUT)
  Set current mode to MENU
  Display menu screen

LOOP:
  Read button state
  
  IF button pressed:
    Record press start time
    Start press detection timer
  
  IF button released:
    Calculate press duration
    IF duration > HOLD_THRESHOLD:
      Activate flashlight mode
    ELSE:
      Increment press count
      Reset press timeout timer
  
  IF press timeout exceeded:
    Process accumulated press count:
      IF press count == 1: Switch to CAMERA mode
      IF press count == 2: Switch to SENSORS mode
      IF press count == 3: Switch to MENU mode
    Reset press count
  
  IF current mode == MENU:
    Display menu screen (button instructions)
  
  IF current mode == CAMERA:
    Capture camera frame
    Process image with dithering algorithm
    Display on OLED
    Run Edge Impulse inference (optional)
    Overlay results on display
  
  IF current mode == SENSORS:
    Read accelerometer/gyroscope data
    Read load cell data
    Display sensor readings on OLED
  
  Update display
Key Features
  • Press pattern detection: single (1x), double (2x), triple (3x), and hold
  • Mode-based navigation system (Menu, Camera, Sensors)
  • Button debouncing with timeout-based pattern recognition
  • Floyd-Steinberg dithering for camera-to-OLED video display
  • Edge Impulse AI inference integration for face detection
  • Multi-sensor integration (MPU6050 accelerometer/gyro, HX711 load cell)
  • Flashlight mode activated by button hold
What You Need to Know
  • Button Wiring: Use INPUT_PULLUP mode (button connects pin to GND when pressed, internal pull-up to 3.3V)
  • Press Detection: Press count is accumulated until timeout (1 second); longer timeout allows slower multiple presses
  • Mode Switching: Each mode has distinct display update logic; ensure proper initialization in setup()
  • Camera Performance: Video streaming to OLED requires significant processing; frame rate depends on resolution and dithering complexity
  • Dependencies: Requires camera_pins.h header file with XIAO ESP32-S3 camera pin definitions; see Ethical AI Use for development details
  • Sensor Conflicts: Code uses preprocessor directives to resolve sensor_t type conflict between ESP32 camera and Adafruit MPU6050 libraries
Download: outputs.ino | camera_pins.h | outputs.zip (complete project)

Grip Strength Monitor (Load Cell + WiFi GUI)

Design files and firmware for a Wi-Fi-enabled grip strength meter built around an 80 kg bar load cell, HX711 amplifier, and ESP32-S3. The mechanical design was informed by the open-source grip strength meter from NeuroTech Hub and validated against the CZL601AC bar load cell datasheet (online, download).

Mechanical Design Files (3D-Printed Components)

  • Base.3mf — main chassis that captures the bar load cell and anchors the fixed side of the gripper.
  • Case.3mf — protective enclosure for the ESP32-S3 and HX711 amplifier with cable strain relief.
  • Handle.3mf — curved grip handle that transfers hand force into the free end of the load cell.
  • Calibration Print.3mf — small test piece used to verify hole diameters and load cell clearances before printing the full assembly.

All parts were printed in PLA with high infill in the load paths to minimize creep and flex during repeated maximal grip trials.

Basic HX711 Reader (loadcell_simple.ino)

Minimal firmware to bring up the HX711 amplifier and read calibrated weight values over Serial for debugging and calibration.

How the Code Works (Pseudocode)
SETUP:
  Configure HX711 data and clock pins (DT=A1, SCK=A0)
  Initialize Serial at 115200 baud
  Begin HX711 with DT/SCK pins
  Set calibration factor (grams per ADC unit)
  Tare the scale so current load is zero

LOOP (every 200 ms):
  If HX711 is ready:
    Read averaged weight using get_units(4)
    Print "weight:<value>" to Serial for Serial Plotter
  Else:
    Print "HX711 not ready" for troubleshooting
Key Features
  • Simple initialization of the HX711 on analog pins A0/A1.
  • Configurable calibration factor for mapping counts to grams or kilograms.
  • Timed reads (200 ms) to keep Serial output manageable and Plotter-friendly.
  • Graceful handling of HX711 not-ready states.
What You Need to Know
  • Use for initial bring-up: Run this first when wiring the HX711 and load cell to confirm clean, stable readings.
  • Calibration factor: Determined experimentally by hanging known weights and adjusting until readings match; see the calibration notes in Calibration Chat.
  • Serial Plotter: The weight:<value> format is convenient for quickly visualizing changes while squeezing the handle.
Download: loadcell_simple.ino

Serial Plotter-Friendly Reader (loadcell_plot.ino)

Refined HX711 reader tuned for the Arduino Serial Plotter: it outputs a single numeric value per line for clean plotting of grip strength over time.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial at 115200 baud
  Initialize HX711 on DT=A1, SCK=A0
  Set calibration factor
  Tare the scale
  Optionally print debug messages when DEBUG=1

LOOP (every 200 ms):
  If HX711 is ready:
    Read filtered weight with get_units(4)
    Optionally print labeled debug text
    Print only the numeric weight to Serial for the Plotter
  Else:
    Optionally print "not ready" debug text
    Print 0 so the plotted line continues gracefully
Key Features
  • DEBUG toggle: Compile-time switch to enable/disable human-readable logs without breaking the Serial Plotter format.
  • Clean “one number per line” output for multi-trial grip testing in the Serial Plotter.
  • Automatic zero output when the HX711 is not ready to keep the time axis continuous.
  • Shared pinout and calibration approach with loadcell_simple.ino for easy swapping.
What You Need to Know
  • Use this sketch to tune calibration and visualize grip curves without any GUI overhead.
  • When collecting data for analysis, keep DEBUG set to 0 so the output is a pure numeric stream.
  • The sample interval (200 ms) gives a smooth trace while keeping file sizes reasonable for multi-second squeezes.
Download: loadcell_plot.ino

WiFi Grip Strength GUI (loadcell_gui.ino)

Full application firmware that exposes grip strength and an estimated age over Wi-Fi using an HTTP server and a Chart.js web dashboard.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial
  Initialize HX711 (pins, calibration factor, tare)
  Connect ESP32-S3 to WiFi (MIT network in this build)
  Start WebServer on port 80
  Register handlers:
    "/"        → serve HTML+JS GUI page from PROGMEM
    "/metrics" → serve JSON with current grip and age

LOOP:
  Handle incoming HTTP clients
  Every 200 ms:
    If HX711 is ready:
      Read smoothed grip strength (kg) via get_units(3)
      Clamp negative values to zero
      Store in global gripStrength

AGE ESTIMATION HELPERS:
  ageFromGripMale(g):
    Clamp g to plausible range
    Compute age using inverted quadratic fit derived from normative data
  ageFromGripFemale(g):
    Same structure with female-specific parameters

HTTP /metrics ENDPOINT:
  Read "sex" query parameter (default "male")
  Compute ageEstimate = ageFromGripMale/ageFromGripFemale(gripStrength)
  Return JSON:
    {"grip": <kg>, "age": <years>}

CLIENT-SIDE GUI (HTML + JS):
  Render dark-themed dashboard with:
    - Sex toggle buttons (male/female)
    - Numeric grip strength (kg) and age
    - Scrolling Chart.js line plot of recent grip values
  Poll /metrics every 200 ms and update DOM + chart
Key Features
  • Embedded HTML/JS dashboard served directly from the ESP32-S3 using PROGMEM.
  • Real-time grip strength plot using Chart.js with ~120 recent samples.
  • Simple sex toggle that switches between male and female age-estimation curves.
  • JSON API at /metrics for future extensions (e.g., logging clients).
What You Need to Know
  • WiFi credentials: Update the ssid and password constants to match your network.
  • Normative model: The age equations are simplified fits inspired by the grip-strength trajectories reported in Syddall et al., PLOS ONE 2014 and are for educational visualization only, not clinical use.
  • Browser requirements: Any modern browser with JavaScript and network access can connect to the ESP32-S3’s IP address to view the dashboard.
  • Development log: The full iterative design of this sketch is captured in the ChatGPT transcript: Grip Strength Monitor Code Chat.
Download: loadcell_gui.ino

Invisible String Chain of Hearts

Code files for the Invisible String pulse oximeter interface system, providing real-time health monitoring through OLED display and WiFi web interface. See Week 11 PCB design documentation for hardware details.

OLED GUI for Pulse Oximeter (pulse_vo2_reads_fixing.ino)

Local OLED display interface showing real-time pulse oximeter readings including heart rate (BPM), blood oxygen saturation (SpO2), and raw IR/RED LED sensor values.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial communication
  Initialize I2C bus (SDA=5, SCL=6) at 400kHz
  Initialize MAX30102 sensor
  Configure sensor:
    Set LED mode to RED + IR
    Set ADC range to 16384
    Set sample rate to 100 Hz
    Set pulse width to 411 μs
    Set LED brightness to medium (0x3F)
  Initialize OLED display
  Clear and prepare display

LOOP:
  Read IR and RED LED values from sensor
  
  Heart Rate Detection:
    Check for heartbeat in IR signal using peak detection
    IF heartbeat detected:
      Calculate time since last beat
      Calculate BPM = 60 / (time_delta / 1000)
      Set beat flag for visual indicator
      Update last beat timestamp
  
  SpO2 Calculation (every 300ms):
    Add IR and RED values to circular buffer
    IF buffer has 50 samples:
      Calculate DC components (average)
      Calculate AC components (RMS)
      Calculate R ratio = (AC_RED/DC_RED) / (AC_IR/DC_IR)
      Estimate SpO2 = 110 - 25 * R
      Clamp SpO2 to 70-100% range
  
  Serial Output:
    Print IR, RED, BPM for Serial Plotter visualization
  
  OLED Display Update:
    Clear display buffer
    Display IR value (small text)
    Display RED value (small text)
    Display BPM value (large text, size 2)
    Display SpO2 percentage (small text)
    IF beat detected: Draw heartbeat indicator dot
    Update display hardware
  
  Delay 20ms (50 Hz update rate)
Key Features
  • Real-time heart rate detection using peak detection algorithm on IR signal
  • SpO2 calculation using ratio-of-ratios method with DC/AC component analysis
  • Circular buffer system for storing 50 samples of IR/RED data
  • Visual heartbeat indicator (flashing dot) when pulse detected
  • Dual output: OLED display and Serial Plotter for real-time waveform visualization
  • Optimized sensor configuration for reliable readings (100 Hz sample rate, medium brightness)
What You Need to Know
  • Sensor Placement: Finger must cover sensor completely; proper contact ensures accurate readings
  • I2C Address: MAX30102 uses address 0x57; verify with I2C scanner if sensor not detected
  • Ground Isolation: RD and IRD pins must be isolated from main ground plane to prevent power issues (see Week 11 PCB design)
  • SpO2 Accuracy: Calculation provides estimation; medical-grade accuracy requires calibration and FDA-approved algorithms
  • Buffer Size: 50-sample buffer provides balance between calculation accuracy and response time
  • Libraries Required: MAX30105 (SparkFun library), Adafruit_GFX, Adafruit_SSD1306, heartRate.h (beat detection)
  • Troubleshooting: If sensor not detected, check power isolation, I2C wiring, and sensor initialization order
Download: pulse_vo2_reads_fixing.ino

WiFi Readings GUI (pulse_gui.ino)

WiFi-enabled web interface providing remote access to pulse oximeter data through HTTP server with JSON API endpoint for real-time data updates.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial communication
  Initialize I2C bus
  Initialize MAX30102 sensor
  Configure sensor (LED mode, sample rate, pulse width)
  Initialize OLED display
  Initialize WiFi:
    Connect to network (SSID, password)
    Wait for connection
    Print IP address
  Initialize HTTP server:
    Route "/" → serve GUI HTML page
    Route "/gui" → serve GUI HTML page
    Route "/metrics" → serve JSON data
  Start web server

LOOP:
  Handle incoming HTTP client requests
  
  Read IR and RED values from sensor
  
  Heart Rate Calculation:
    Check for heartbeat in IR signal
    IF heartbeat detected:
      Calculate BPM from time delta
      Update global BPM variable
  
  SpO2 Calculation:
    Add IR/RED to circular buffer
    IF buffer full (50 samples):
      Calculate SpO2 using ratio-of-ratios
      Update global SpO2 variable
  
  Update global variables (g_ir, g_red, g_bpm, g_spo2)
  
  OLED Display Update:
    Display IR, RED, BPM, SpO2 values
    Update display hardware
Key Features
  • Dual interface: OLED display (local) and WiFi web interface (remote)
  • HTTP server with embedded HTML page stored in PROGMEM
  • JSON API endpoint (/metrics) for real-time data retrieval
  • Automatic WiFi connection with connection status feedback
  • IP address display for easy access
  • Simultaneous sensor reading and web server operation
  • Global variable system for data sharing between sensor reading and HTTP handlers
What You Need to Know
  • WiFi Configuration: Update SSID and password in code; for MIT network, use generated device password from wifi.mit.edu
  • Network Access: Web interface accessible only from devices on same WiFi network; IP address printed to Serial Monitor
  • HTML Storage: GUI HTML page stored in PROGMEM (program memory) to conserve RAM; use PROGMEM for large strings
  • Server Handling: Must call server.handleClient() frequently in loop() for responsive web interface
  • Data Refresh: Client-side JavaScript polls /metrics endpoint every 300ms for real-time updates
  • Power Consumption: WiFi significantly increases power draw compared to OLED-only mode; consider power management for battery operation
  • Libraries Required: WiFi, WebServer, MAX30105, Adafruit_SSD1306
Download: pulse_gui.ino

WiFi Plot GUI (pulse_gui_2.ino)

Enhanced WiFi web interface with real-time plotting capabilities using Chart.js library, displaying live line charts for BPM and SpO2 values with automatic scrolling and data management.

How the Code Works (Pseudocode)
SETUP:
  (Same as pulse_gui.ino)
  Initialize WiFi, sensor, OLED, HTTP server

LOOP:
  (Same as pulse_gui.ino)
  Handle HTTP requests, read sensor, calculate BPM/SpO2

GUI HTML PAGE (embedded in PROGMEM):
  Load Chart.js library from CDN
  Create two Chart.js line chart instances:
    - BPM chart (y-axis: 40-160 BPM)
    - SpO2 chart (y-axis: 70-100%)
  Initialize data arrays for each chart
  
  JavaScript Update Function (runs every 300ms):
    Fetch JSON data from /metrics endpoint
    Update numerical displays (BPM, SpO2, IR, RED)
    Add new BPM value to BPM data array
    Add new SpO2 value to SpO2 data array
    IF array length > maxPoints (100):
      Remove oldest value (shift)
    Update chart labels (array indices)
    Update chart datasets with new data
    Call chart.update() to refresh display
  
  Set interval to call update function every 300ms
Key Features
  • Real-time line chart visualization using Chart.js library
  • Dual chart display: BPM and SpO2 trends over time
  • Automatic data scrolling: maintains 100 most recent data points
  • Numerical displays alongside charts for precise values
  • Responsive design with dark theme for OLED-style aesthetic
  • Automatic chart scaling with fixed y-axis ranges for consistent visualization
  • CDN-based Chart.js loading for minimal memory footprint
What You Need to Know
  • Chart.js CDN: Library loaded from jsdelivr.net CDN; requires internet connection on client device
  • Data Management: Arrays limited to 100 points to prevent memory overflow; older data automatically discarded
  • Update Rate: 300ms refresh rate balances responsiveness with server load; adjust based on network conditions
  • Chart Configuration: Y-axis ranges fixed (BPM: 40-160, SpO2: 70-100) for consistent scaling; modify in JavaScript if needed
  • Browser Compatibility: Requires modern browser with JavaScript enabled; tested on Chrome, Firefox, Safari
  • Performance: Chart updates are lightweight; multiple simultaneous clients may impact ESP32 performance
  • Offline Operation: Charts won't load if client device lacks internet (Chart.js CDN unavailable); consider local hosting for offline use
Download: pulse_gui_2.ino

Reflections & Learnings

Key insights and learnings from working with interface and application programming.

Contributions

Acknowledgements and team roles for interface and application programming work.

Ethical AI Use

Transparent documentation of AI assistance used in this week's interface and application programming work.

This section documents all AI assistance used during Week 12 interface and application programming work. ChatGPT was used for code development, troubleshooting, and technical guidance. All transcripts are linked below for transparency.

Menu System with Modes

AI assistance for developing the button-based menu system with mode navigation (Menu, Camera, Sensors) using press pattern detection. The conversation covered button debouncing, press pattern recognition, mode state management, and OLED menu display design.

Related to: Part (a): Simple Button User Interface on OLED

View ChatGPT Transcript: Menu System with Modes

I2C Device Not Found

Troubleshooting session for I2C device detection issues with MAX30102 pulse oximeter sensor. The conversation addressed power isolation problems, I2C wiring verification, sensor initialization order, and ground plane isolation requirements for accurate sensor operation.

Related to: Part (b): Real-Time Graphical User Interface through OLED and WiFi

View ChatGPT Transcript: I2C Device Not Found

Hello World Code

Development assistance for creating the initial OLED "Hello World" test program. The conversation covered I2C initialization, OLED display library setup, text rendering, and basic display configuration for XIAO ESP32-S3 development board.

Related to: Part (b): Real-Time Graphical User Interface through OLED and WiFi (initial OLED test)

View ChatGPT Transcript: Hello World Code

MAX30102 Initialization Fix

Technical guidance for fixing MAX30102 pulse oximeter sensor initialization issues. The conversation addressed sensor configuration parameters, LED brightness settings, sample rate optimization, initialization sequence requirements, and troubleshooting sensor communication problems.

Related to: Part (b): Real-Time Graphical User Interface through OLED and WiFi (pulse oximeter readings)

View ChatGPT Transcript: MAX30102 Initialization Fix

Grip Strength Monitor Code Design

Code-focused assistance for designing and refining the WiFi grip strength monitor firmware. The conversation covered HX711 bring-up, load cell pin mapping, Serial Plotter debugging sketches, the ESP32-S3 HTTP server, the Chart.js dashboard, and the age-estimation helpers used in loadcell_simple.ino, loadcell_plot.ino, and loadcell_gui.ino.

Related to: Part (c): Real-Time GUI through Mechanical Gripper and WiFi and Grip Strength Monitor design files

View ChatGPT Transcript: Grip Strength Monitor Code

Grip Strength Calibration & Scaling

Calibration-focused assistance for mapping HX711 counts to kilograms and validating the grip strength readings. The discussion walked through using the Serial Plotter, collecting reference weights, tuning the calibration factor, and sanity-checking the age-estimation model derived from normative grip strength data.

Related to: Part (c): Real-Time GUI through Mechanical Gripper and WiFi calibration workflow and the Grip Strength Monitor sketches.

View ChatGPT Transcript: Grip Strength Calibration

Grip Strength Monitor – Cursor Transcript

Full Cursor AI transcript focused on organizing the grip strength monitor section: structuring Part (c), integrating design files, embedding images and videos, and aligning captions, external references, and the Ethical AI Use documentation for the load cell project.

Related to: Part (c): Real-Time GUI through Mechanical Gripper and WiFi, Grip Strength Monitor design files, and this Ethical AI Use section.

View HTML Transcript Download Markdown Transcript

Week 12 Project Documentation

Complete Cursor AI transcript for Week 12 interface and application programming project documentation. This comprehensive conversation covers the creation and population of the Week 12 HTML page, including Individual Assignment sections (button UI and WiFi GUI), Group Assignment tool comparisons, Design Files documentation with pseudocode, and Ethical AI Use section organization. The transcript demonstrates the collaborative process of building professional documentation with structured content, embedded media, and comprehensive code documentation.

Related to: Complete Week 12 documentation including Individual Assignment, Group Assignment, Design Files, and overall page structure

View HTML Transcript Download Markdown Transcript

Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License

``` Checking what remains after the replacement and removing the old content: Removing the remaining old week 12 content. Finding where it ends: Removing the old week 12 content. Finding where the individual assignment section should end: Finding where the Group Assignment section starts: Searching for the Group Assignment section header: Removing the old week 12 content between the new content and the Group Assignment section: Removing the old week 12 content. Reading a larger section to identify the exact boundaries: Removing the old week 12 content with a targeted replacement: ```html Week 13 · Wildcard Week
← Back to Home
[Profile Image Placeholder]

Week 13

Wildcard Week

Week Highlights

Key captures from the PCB engraving assignment with links to their sections.

ATtiny1626 Board Design

Final ATtiny1626 development board design with connectors and mounting holes

PCB Engraving

ATtiny1626 development board after fiber laser engraving

Soldered Board

Fully assembled ATtiny1626 development board with all components soldered

Blinking LED Demo

RP2354A Board Design

RP2354A development board design

PCB Engraving Detail

Close-up detail of PCB engraving showing trace quality

Table of Contents

Course Content

Training & Documentation

Assignments & Projects

Wildcard Week

This week focuses on exploring digital fabrication processes not covered in previous assignments. We'll design and produce something using computer-aided design and manufacturing, documenting requirements and including everything necessary for reproduction. This week also includes reflection on the impact and purpose of making (almost) anything.

Exploring new digital fabrication processes
Designing and producing with CAD/CAM
Understanding the impact and purpose of fabrication labs

This Week's Goals

  • Explore New Processes
    Design and produce something with a digital process not covered in other assignments
  • Complete Documentation
    Document requirements and include everything necessary to reproduce the project
  • Reflect on Impact
    Understand the purpose and impact of fabrication labs and making

Assignments

  • Group Assignment
    Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment
  • Individual Assignment
    Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment, documenting the requirements that your assignment meets, and including everything necessary to reproduce it

Tools & Materials

  • Carvera (CNC Mill) — Edge cuts and hole machining
  • Fiber Laser Cutter (xTool F2 Ultra) — PCB engraving
  • PCB Design Software (KiCad) — Board layout and design
  • ATtiny1626 Microcontroller — Target device for development board
  • RP2354A Microcontroller — Complex board design

Lecture Notes

Week 13 lecture covering major announcements, week 12 review, system integration reminders, and wildcard week preview.

Theme of the Week

'Step away from the panic'

Major Announcements

  • Subject evaluation: Required for funding the class. Provides feedback to the institute about the class. Important for future students if you care about successors in the class.
  • Calendar alarm: Wildcard week and recitation on why make (almost) anything: impact. Friday is cutoff for assignments and orders (10s of dollars per person from inventory).
  • Final presentation/final exam: Combining multiple additive and subtractive processes (not just design a board and 3D print a case). Goal is system integration out of parts. Final exam criteria:
    • Did you integrate and design a complete system?
    • Can you demo a final project? Here is the cool thing I did and here is how it works.
    • Make a final project video! (helps but not required)
    Focus on well-integrated device!

Review of Week 12 User Interfaces

  • Claire Wang: Music play and Windows 3.1 interface works!
  • Ryan Hoffman: DRV8251A discussion, heat sinks, breakout boards. Wildcards with waterjetting, EDM, multi-axis machining, laser cutting metal. Class in the spring on nature of mathematical modeling.
  • Srikanth Nadhamuni: Background and experience to visiting fellow at MIT. Raspberry Pi W for WiFi, n8n for cloud LLM data crunching. Software: Node.js, MCP bridge server with n8n based on bridge connected to device (NGV tunnel). All set! Fantastic experience, haven't worked so hard in a very long time and learning a lot of new things. Hope to take forward and build other systems. The whole culture of doing and trying yourself fascinating, especially with failing a number of times until you figure it out. Maybe set one up at an IIT in India or AI centers of excellence with education ministry into the Indian education system (see fablabkerala.in or vigyam ashram).
  • Ray Song: Not here.
  • Tyler Jensen (Lincoln Lab, Group 81): Final project discussion (nylon printer). Week 13: Easy for web serial interface for XIAO! Web server to TFT (I think I forgot to load the camera pins with my code for it).
  • Aditi Ramakrishnan: Sloan MBA and strategy consulting background. Discrete time filter (FFT is blown) in skimage.filters — make a bandpass filter, then run a series of these filters, much less computing only adds and multiplies for filtering in realtime.
  • Alexandros Gravalos: Not here.
  • Edward Chen: Check final watch project by Gulati into watch form factor. Clear print on the Form Labs printer, 0.1. Kaman filter for sensor fusion (in the spring class). For position — LSM6DSV16X from input devices. Acceleration at 7 kHz (at audio frequency).

Show and Tell

  • Handle to sensor WiFi user interface
  • Plug to audio LLM user interface

System Integration Reminders

  • Mount electronics
  • Strain relief the final projects

Preview for Wildcard Week

Assignment: Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment.

Recitation Notes: Why Make (Almost) Anything

Recitation exploring the purpose, impact, and scaling of fabrication labs and making infrastructure.

Map of Fab Labs

Why Make a Fab Lab?

  • Used to create a community
  • Building things for the community
  • Sustainability
  • Prototyping quickly

How Impact?

  • How to make spaces: How to measure impact. What is important about fab:
    • Fablabs in cities vs rural areas: The ability to decide their own futures and change their lives fundamentally. 'Safecast revolutionized citizen science' e.g. radiation map.
    • Bringing back manufacturing: Reducing reliance on supply chains.
    • Rural sustainability: Working with indigenous communities on creating technologies themselves at scale and measure their usefulness and efficacy to preserve their ancestral knowledge:
      • How to establish labs there
      • How to make sure the labs get used
    • Hygiene technologies with Proctor and Gamble: Highly commercial. Lots of plastic waste. How can we change how they produce? How to make their products get there through resellers?
    • Trip to Peru and ran workshops, questionnaires, analysis: Collaboration developed into how to produce the products but also how to test their products to be market valuable e.g. mosquito repellents. Out of three plants, two worked better and one wasn't working at all (which is important to know!).

What Does It Mean to Design Infrastructure?

  • What did we want this lab to be able to do?
    • Workshops and questionnaires
    • How much you educate people based on the info they have with the issues the community is facing
    • Energy concerns to consider, some machines just drain the grid and can't be used. Solar powered, battery powered machines, reducing energy consumption of machines. Many concerns important.
  • Ethical questions
  • How to maintain resources

Case Study: Water Purifier Packets

Use them, change them, source them locally, ingredients found locally, how to distribute them globally.

Funding Models

First few fablabs were NSF funded. Now corporate CSR, regional funding, labor funding (10 different ways). Successful fablabs are heterogeneous with lots of ways of funding. The ones that fail usually just have one sponsor.

Example: DIY Raman spectrometer for water purification (even after purifications still have sulfates and improving that too).

What Does It Mean to Scale Infrastructure?

(Besides a lot of meetings!) What is a reasonable way to design a data collection process about what is needed and how to achieve it.

Back to the Map: Expansion

Timeline of development, cocreation, portable, skin analysis, water testing, biomaterial tech, microscopy.

Initial Results from Boston

How to Confront Local Impact
  • Collab with University of Hamburg. Motivation for how much food can be produced in Boston. Where food waste goes and what Boston produces locally. Make things for yourself locally.
  • Impact directly in the community you're living in.

Hatchspace

Focused on rehabilitation of addicts with woodworking. (Vermont is wood producing state).

Example Course Program

  • All-in session and systemic impact
  • Natural and cultural context
  • Skills and workshop
  • Economic vitality
  • Skills and workshop
  • Co-work session
  • Solutionspalooza

In the Course

Hands-on component (no physical robot exists that can do it) and community component is also important. Inclusion is important. Solving unconscious and institutional biases.

  • 'Fabrica! Lab' — Creating new laboratory spaces for female high school students, courses aimed for women in technology, online advising sessions for females interested in tech.
  • Makerspaces — Access to tools behind closed doors at universities, makes a huge difference for people who don't have the ability to prototype for themselves.
  • Materiom — Fablab affiliated project on organic waste for biomaterials.
  • Fablab León
  • Skylab workshop experiment — How to run a noodle shop out of a fablab (creating food from the community).
  • Academany — Global distributed campus for high school education. Fablab all-in (belonging, impact, community), fab futures (future vocational skills), bio academy (synthetic biology), fabricademy (textiles, fab, bio), fab academy (digital fab apps and implications).

Trade-off Between Impactful and Dangerous

People could be doing bad, but not because doing it with a group people with values.

Questions

Clarification: Adding infrastructure to existing fablab infrastructure to help support specific community needs (not specialized fab labs).

Foundations for Fab Futures

July 27-31, 2026 at Fab Boston 2026.

Useful Documentation

Essential resources for wildcard week digital fabrication processes and PCB design.

Class Page

Wildcard Week - MIT Academy

Comprehensive resource covering wildcard week assignment requirements and possibilities including grinding, multi-axis machining, electrical discharge machining, waterjet cutting, flatbed cutting, plasma cutting, laser metal cutting, laser micromachining, welding, molding and casting, folding, robotics, electronics, embedded programming, food, materials, biotechnology, textiles, and composites.

Key Topics

  • Machining: Grinding, multi-axis machining, electrical discharge machining, waterjet cutting, plasma cutting, laser metal cutting, laser micromachining
  • Molding & Casting: Vacuum forming, rotocasting
  • Folding: Mathematics, form and function, kirigami
  • Robotics: Arms, construction, soft actuation pneumatic inflatable
  • Electronics: Pick and place, programmable logic
  • Embedded Programming: Machine learning, machine vision
  • Textiles: Fiber processes, knitting, embroidery (PEmbroider, Ink/Stitch), Fabricademy
  • Composites: Various composite fabrication techniques

ATtiny1626 Development Board References

Embedded Programming Course Resources

Course resources for embedded programming with ATtiny412 microcontroller examples:

Embedded Programming - MIT Academy

ATtiny412 Echo Example Image

Individual Assignment: PCB Engraving with Fiber Laser

Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment. This assignment demonstrates PCB design and fabrication using a combination of CNC milling (Carvera) for edge cuts and hole machining, and fiber laser engraving (xTool F2 Ultra) for trace creation on copper-clad boards. The project includes designing and fabricating two development boards: a simple ATtiny1626 development board and a complex RP2354A development board.

PCB Engraving Process

This project explores PCB fabrication using fiber laser engraving, a process not covered in previous assignments. The workflow combines subtractive manufacturing techniques: CNC milling for mechanical features (edge cuts and holes) and laser engraving for electrical traces. This approach enables rapid prototyping of custom PCBs without requiring chemical etching or specialized PCB manufacturing facilities.

Tools and Equipment

  • Carvera (CNC Mill): Used for edge cuts and hole machining. The laser cannot effectively cut through the board material, so mechanical cutting is required for board outline and mounting holes.
  • Fiber Laser Cutter (xTool F2 Ultra): Used for PCB trace engraving. The laser removes copper from the board surface to create electrical traces and pads.
  • PCB Design Software (KiCad): Used for schematic capture, PCB layout, and design rule checking.

Boards Designed

  • Simple Board: ATtiny1626 development board with connectors, resistors, LED, and capacitor
  • Complex Board: RP2354A development board with more advanced routing and component placement

Board Design Considerations

  • Connector Placement: Top and bottom for connectors, right side for flashing. Connectors along edges to minimize form factor and maximize space usage.
  • Vertical Connectors: Used instead of horizontal connectors because horizontal connectors risk being snapped during use.
  • Black Area Avoidance: Avoid large black areas because laser does not work well with that (keep traces closer and further to minimize black areas). Note: Need to characterize maximum black until it burns the board because dumping too much heat in one place can damage the board.
  • Breadboard Compatibility: Put connectors on 100mil spacing grid size for breadboardability.
  • Pin Count Adjustment: Missed six pins in initial design, so switched from 6-pin headers to 9-pin (distributed six on top and bottom).
  • I2C Resistors: No SDA or SCL resistors included to keep flexibility for future use. May add spot for zero-ohm or pull-up resistor later but keeping it simple for now.
  • Mounting Holes: Added aligned mounting holes (M3 usually — for 3mm screws) for mechanical mounting.
  • Rounded Edge Cuts: Do 90 degrees, copy, drag, and complete the shape for rounded corners.

Design Rules

  • 0.1 mm spacing minimum
  • 0.15 mm trace width minimum
  • 0.15 mm clearance between plane and the rest

Ports and Pins

ATtiny1626 is an 8-bit microcontroller with 8 pins maximum per port. Each port has 8 pins maximum (some less). Need to specify port letter and pin number:

  • PA (0-7)
  • PB (0-7)
  • PC (0-7)

Postprocessing

  • For Carvera: Add new layer with just the holes in Photoshop (only holes for machining).
  • For Laser Engraving: Get rid of the holes for the F2 tools engraving in Inkscape (the frame and the board for alignment, then only engrave the board, not the edges).

Carvera Machining

Using mods → mill 2D PCB workflow:

  • 0.12mm cut depth and max depth

PCB Engraving Process

Using xTool F2 Ultra fiber laser:

  • Use tape for laser alignment
  • Run a test first on spare copper before the Carvera cut board to make sure focus is good (2.7mm thickness setting worked, board is actually 1.6-1.7mm thick)
  • Sand after engraving to clean up any residue
  • Worked with Bantam Tools FR1 (not random Amazon copper)
  • Perform short circuit test after engraving

Soldering

Using solder gun (heat gun) for component assembly.

Components

  • 1x 6-pin flipflop headers
  • 2x 9-pin flipflop headers
  • 1x 4.7k resistor
  • 1x 1k resistor
  • 1x LED
  • 1x 1uF or 10uF capacitor

Design Files

Download design files: ATtiny_QFN.zip and RP2354A-dev-v1.1.zip

Final ATtiny1626 development board design showing component placement and routing
ATtiny1626 final designComplete PCB layout with connectors, components, traces, and mounting holes optimized for laser engraving.
ATtiny1626 development board after fiber laser engraving showing copper traces
PCB after engravingCopper-clad board with traces engraved using fiber laser, ready for component soldering.
Fully assembled ATtiny1626 development board with all components soldered
Soldered boardComplete ATtiny1626 development board with headers, resistors, LED, and capacitor soldered in place.
Blinking LED demoVideo demonstration of the completed ATtiny1626 development board running a simple LED blink program, confirming successful fabrication and programming.
Close-up detail of PCB engraving showing trace quality and copper removal
PCB engraving detailClose-up view of fiber laser engraved traces showing clean copper removal and precise trace definition.

Interface with User

The application interfaces a user with input and/or output devices through the ATtiny1626 development board. The following table describes how the application interfaces with the user:

How It Interfaces with User Input Device(s) Output Device(s)
(a) LED Blink Demonstration None (programmed behavior) LED (visual feedback indicating board functionality)
(b) Future Interface Applications GPIO pins (PA, PB, PC ports) available for sensors, buttons, switches GPIO pins (PA, PB, PC ports) available for LEDs, displays, actuators

Part (a): Simple Button User Interface on OLED

A mode-based user interface system that interfaces users with multiple input and output devices through a simple button press interface. The system provides visual feedback on an OLED display and enables navigation between different modes (Menu, Camera, Sensors) using button press patterns. Users interact by pressing a button multiple times to select modes, with visual confirmation displayed on the OLED screen.

Interface Design

The interface uses a mode-based navigation system where button presses trigger mode changes. A single press enters Camera mode, two presses enter Sensors mode, three presses return to Menu, and holding the button activates a flashlight function. The OLED display shows the current menu state and provides clear visual feedback for each mode transition. See Ethical AI Use: Menu System with Modes for AI-assisted development details.

OLED button user interface menu system displaying mode selection options
OLED button user interface menuMenu screen showing available modes: Camera, Sensors, and Menu navigation options with button press instructions.
Button UI demonstrationVideo showing button press interactions navigating through different modes on the OLED display.
First video stream on OLEDInitial camera feed streaming to OLED display using dithering algorithm for monochrome conversion, demonstrating real-time video output interface.
Download Design Files
  • outputs.ino — Button user interface code with mode system
  • camera_pins.h — Camera pin definitions header file
  • outputs.zip — Complete project archive including all dependencies

Part (b): Real-Time Graphical User Interface through OLED and WiFi

A dual-interface health monitoring system that interfaces users with a MAX30102 pulse oximeter sensor through both an OLED display and a WiFi-enabled web interface. The system provides real-time visualization of heart rate (BPM), blood oxygen saturation (SpO2), and raw sensor data (IR and RED LED readings) through multiple output channels. Users can view data locally on the OLED display or remotely via a web browser accessing the ESP32-S3's built-in HTTP server. See Ethical AI Use: I2C Device Not Found for troubleshooting documentation.

Interface Design

The system provides dual-interface access: a local OLED display shows real-time sensor readings (IR, RED, BPM, SpO2) with visual heartbeat indicators, while a WiFi web interface provides comprehensive data visualization including numerical displays and real-time plotting charts. The web interface uses Chart.js for dynamic graph generation and automatically refreshes every 300ms to maintain real-time data updates. Both interfaces run simultaneously, enabling local monitoring and remote access.

Hello World on OLED

Initial OLED display test showing successful I2C communication and display initialization. See Ethical AI Use: Hello World Code for development details.

Hello World display on OLED for Invisible String project showing successful display initialization
Hello World on OLEDInitial OLED test confirming I2C communication and display functionality before implementing sensor interfaces.
Pulse Oximeter Readings on OLED

Real-time pulse oximeter data displayed on OLED showing IR and RED LED readings, heart rate (BPM), and blood oxygen saturation (SpO2) percentage. A heartbeat indicator flashes when a pulse is detected. See Ethical AI Use: MAX30102 Initialization Fix for sensor setup documentation.

Pulse oximeter readings on OLED displaying IR, RED, BPM, and SpO2 values
OLED sensor readings displayReal-time pulse oximeter data showing IR and RED LED values, heart rate (BPM), and blood oxygen saturation (SpO2) with heartbeat indicator.
BPM and SpO2 demonstrationVideo showing real-time heart rate and blood oxygen saturation measurements updating on OLED display with sensor interaction.
Pulse Oximeter Readings on WiFi GUI

WiFi web interface providing remote access to pulse oximeter data through a responsive HTML dashboard. The interface displays real-time numerical values for BPM, SpO2, IR, and RED readings with automatic data refresh. The web server runs on the ESP32-S3, allowing access from any device on the same WiFi network.

WiFi web interface displaying real-time pulse oximeter readings including BPM, SpO2, IR, and RED values
WiFi GUI readings dashboardRemote web interface showing real-time pulse oximeter data accessible from any device on the WiFi network, displaying BPM, SpO2, IR, and RED values with automatic updates.
Pulse Oximeter Plots on WiFi GUI

Enhanced WiFi web interface with real-time plotting capabilities using Chart.js library. The interface displays live line charts for BPM and SpO2 values, showing trends over time with automatic scrolling and data point management. This visualization enables users to observe patterns in heart rate and blood oxygen levels during monitoring sessions.

Serial monitor output showing sensor readings rising on touch interaction
Serial monitor sensor responseSerial output demonstrating sensor readings increase when finger is placed on MAX30102 sensor, showing IR and RED LED response to touch.
WiFi web interface with real-time plotting of BPM and SpO2 data using Chart.js
WiFi GUI with plotting chartsEnhanced web interface displaying real-time line charts for BPM and SpO2 values, showing trends over time with automatic data refresh and chart scrolling.

I2C Device Detection

Successful I2C device detection after fixing power isolation issues. The system now correctly identifies the OLED display at address 0x3C and the MAX30102 sensor at address 0x57. Initial troubleshooting required isolating the RD (red LED) and IRD (infrared LED) ground terminals from the general ground plane to prevent power issues and enable proper sensor operation. 

20:04:48.612 -> Scanning...
20:04:48.644 -> I2C device found at address 0x3C  !
20:04:48.644 -> I2C device found at address 0x57  !
20:04:48.644 -> done
Download Design Files

Part (c): Real-Time GUI through Mechanical Gripper and WiFi

A Wi-Fi-connected grip strength meter that interfaces a user with a mechanical hand gripper, an 80 kg load cell, and an HX711 amplifier. The ESP32-S3 continuously measures grip force, streams it to a web dashboard, and uses a published relationship between handgrip strength and age to display an estimated “physiological age” in real time. The design is inspired by the open-source grip strength meter from NeuroTech Hub at WashU and the associated PLOS ONE paper on grip strength and age trajectories (Syddall et al., 2014), adapted to my load cell and handle geometry.

Mechanically, a custom 3D-printed gripper clamps around a CZL601-type 80 kg bar load cell (sourced from Amazon 80 kg load cell). I imported a 100 kg load cell CAD from GrabCAD, checked the mounting dimensions against the CZL601AC datasheet (online, download), and confirmed that the hole spacing and footprint match the commercial part used here.

Mechanical Design and Fabrication

CAD model of the 3D-printed grip strength base and load cell mounting region
Grip strength base CADTop view of the grip strength base showing the bar load cell pocket, mounting bosses, and handle interface.
Side view CAD of the hand gripper and load cell assembly
Side view of gripper assemblySide profile showing how the fixed base, moving handle, and load cell align along the force axis of the bar sensor.
Full CAD view of the grip strength device with base and handle
Full grip strength assemblyComplete CAD of the base, handle, and load cell, sized for comfortable adult hand placement and full-finger contact.
Close-up of mounting holes and clearances around the load cell in CAD
Load cell mounting holesDetail of the M6 clearance and counterbore geometry used to capture the load cell without constraining bending.
Perspective CAD view of the gripper handle and base
Handle ergonomicsPerspective view of the curved handle designed to distribute pressure across the palm and fingers during maximal grip.
Photo of drilled clearance hole aligned to the printed pilot in the base
Clearance hole verificationPrinted pilot holes used as drill guides to match the metric mounting dimensions from the CZL601AC datasheet.
Photo of the fully printed grip strength device before drilling and assembly
Fresh off the printer3D-printed base and handle components in PLA prior to post-processing and hardware installation.
Printed part clamped for drilling load cell mounting holes
Workholding for accurate drillingThe printed base clamped to the drill press table so the pilot features guide the final clearance holes into the load cell.
Drilling practiceTraining cuts on scrap material to dial in drill press settings and avoid cracking the printed base during final holes.
Final load cell holesDrilling the final M6 clearance holes through the printed base, constrained by the pilot features to preserve alignment.

Electronics and Calibration

Electronics assembly with HX711 breakout, ESP32-S3, and load cell wiring
Electronics stack-upHX711 amplifier breakout from Amazon wired to the ESP32-S3 and 80 kg load cell with short, twisted signal pairs for noise reduction.
Fully assembled grip strength device with load cell, electronics, and handle
Assembled grip strength meterCompleted mechanical and electrical assembly ready for calibration and software bring-up.
Serial Plotter view of load cell readings increasing with grip force
Serial Plotter calibration tracesRaw HX711 output converted to kilograms and visualized in the Arduino Serial Plotter while applying known weights and grip forces.
Web GUI showing grip strength value, estimated age, and scrolling chart
Wi-Fi grip strength dashboardBrowser-based GUI with live grip strength (kg), estimated age, and a Chart.js time series plot of recent squeezes.

Model Used for Age Estimation

The age-estimation logic in the firmware is based on the non-linear, sex-specific grip-strength trajectories reported in Dodds et al., 2014 (PLOS ONE). As shown in Figure 1 of that paper, grip strength rises rapidly through adolescence, peaks around ages 30–40, and then declines non-linearly with age, with different magnitudes for males and females.

Reference grip strength trajectories over the life course from Dodds et al., PLOS ONE 2014
Reference trajectories (Figure 1)Age-dependent grip strength curves for males and females from Dodds et al., 2014, used as the qualitative target for the embedded model.
Simplified quadratic grip strength model fitted to reference data
Quadratic approximation (Table 2-inspired)Simplified male and female trajectories using peak strengths and curvatures chosen to approximate the summary values reported in Table 2 of Dodds et al., 2014.

To reproduce this shape efficiently on the ESP32, the firmware uses inverted quadratic approximations centered at age 35, consistent with the observed peak in the PLOS ONE data. In the forward direction, grip strength is approximated as:

Males: Grip(age) ≈ 52 − 0.0089·(age − 35)2
Females: Grip(age) ≈ 32 − 0.0059·(age − 35)2

On the device, this relationship is analytically inverted so that the measured grip strength can be mapped back to an estimated age:

age = 35 + √((a − Grip)/b), where a is the peak strength (52 kg for males, 32 kg for females) and b is the curvature (0.0089 for males, 0.0059 for females). The firmware clamps grip strength to physiologically meaningful ranges before applying this formula so the square root remains well-defined. 

float ageFromGripMale(float g) {
  float a = 52.0f, b = 0.0089f;
  if (g > a) g = a;
  if (g < 5) g = 5;
  return 35.0f + sqrtf((a - g) / b);
}

float ageFromGripFemale(float g) {
  float a = 32.0f, b = 0.0059f;
  if (g > a) g = a;
  if (g < 4) g = 4;
  return 35.0f + sqrtf((a - g) / b);
}

For full methodological details and original tables/figures, see the open-access paper: Dodds et al., 2014, PLOS ONE (download local PDF). The implementation here is an educational approximation and not intended for clinical or diagnostic use.

End-to-end live demoReal-time demonstration of squeezing the mechanical gripper and watching the Wi-Fi dashboard update grip strength and estimated age on a laptop.

Related Design, Code, and Calibration Resources

User Interface Comparison

Summary of how each interface application connects users with input and output devices.

Application How It Interfaces with the User Input Device(s) Output Device(s)
(a) Button User Interface Button press patterns (single, double, triple press, hold) provide mode selection input. OLED display shows current menu state and mode options. Users receive immediate visual feedback for each interaction. Button (GPIO pin 4) OLED Display (SSD1306, I²C 0x3C)
LED (GPIO pin 3, flashlight mode)
(b) Real-Time GUI (OLED & WiFi) Physical finger placement on MAX30102 sensor provides input. OLED displays real-time sensor data locally. WiFi web interface enables remote monitoring with numerical displays and live plotting charts accessible from any web browser. MAX30102 Pulse Oximeter Sensor (I²C 0x57) OLED Display (SSD1306, I²C 0x3C)
WiFi Web Interface (HTTP Server with Chart.js visualization)
(c) Grip Strength GUI (Load Cell & WiFi) Users squeeze a mechanical hand gripper that transfers force into an 80 kg bar load cell. The ESP32-S3 measures grip strength through the HX711 amplifier and streams results to a WiFi web dashboard that displays live grip force and an estimated physiological age in real time. Mechanical gripper linked to 80 kg load cell (CZL601-type)
HX711 load cell amplifier		 WiFi Web Interface (HTTP Server with Chart.js visualization)
Optional Serial Plotter (for calibration traces)

Group Assignment: Compare as Many Tool Options as Possible

Compare as many tool options as possible for interface and application programming.

General Comparison: Interface & Application Programming Tools

Comprehensive comparison of interface and application programming tools available for embedded systems and IoT development. This analysis covers tools from the MIT Academy Interface & Application Programming class page, evaluating their capabilities, use cases, and trade-offs for different application scenarios.

Embedded Display Interfaces

Tool/Framework Description Pros Cons Best For
OLED (SSD1306) Monochrome OLED displays via I²C Low power, high contrast, simple I²C interface, pixel-level control Limited resolution (128x64), monochrome only, small display size Status displays, sensor readouts, simple menus, embedded dashboards
LCD Character Displays Character-based LCD displays (16x2, 20x4) Simple API, readable in sunlight, low cost Limited to text/characters, no graphics, requires backlight power Text-only interfaces, status messages, debugging output
TFT Color Displays Full-color TFT LCD displays Color graphics, touch support, high resolution High power consumption, complex drivers, larger footprint Rich GUIs, image display, interactive touch interfaces

Web-Based Interfaces

Tool/Framework Description Pros Cons Best For
HTTP Server (ESP32) Built-in HTTP server on ESP32 for web interfaces Remote access, cross-platform (any browser), no app installation, real-time updates Requires WiFi, network dependency, limited to local network without port forwarding Remote monitoring, data visualization, control panels, sensor dashboards
WebSockets Real-time bidirectional communication Low latency, bidirectional, efficient for frequent updates More complex than HTTP, requires persistent connection Real-time streaming, interactive controls, live data feeds
Chart.js JavaScript charting library for web interfaces Beautiful charts, interactive, responsive, easy integration Requires JavaScript, CDN dependency or local hosting Data visualization, time series plots, sensor monitoring dashboards

Mobile & Native App Frameworks

Tool/Framework Description Pros Cons Best For
React Native Cross-platform mobile app framework Cross-platform (iOS/Android), native performance, large ecosystem Complex setup, requires mobile development knowledge Full-featured mobile apps, production deployments
Flutter Google's UI toolkit for cross-platform apps Single codebase, high performance, customizable UI Dart language, larger app size, learning curve Custom mobile interfaces, platform-specific designs
Progressive Web Apps (PWA) Web apps with native-like features No app store, cross-platform, offline capability Limited native API access, browser dependency Web-based mobile interfaces, simple deployment

Specific Comparison: Tools Used in Individual Assignment

Detailed comparison of the specific interface programming tools implemented in this week's individual assignment, evaluating their performance, ease of use, and suitability for embedded health monitoring applications.

OLED Display Interface (Adafruit SSD1306)

Aspect Evaluation
Ease of Implementation Simple I²C interface, well-documented Adafruit library, minimal wiring (SDA, SCL, power, ground)
Display Quality High contrast monochrome display, crisp text rendering, suitable for sensor data visualization
Power Consumption Very low power draw, ideal for battery-powered applications
Limitations 128x64 pixel resolution limits detail, monochrome only, small physical size (0.96" typical)
Best Use Cases Local sensor readouts, menu systems, status indicators, simple data displays

WiFi Web Interface (ESP32 HTTP Server + Chart.js)

Aspect Evaluation
Ease of Implementation ESP32 WebServer library provides straightforward HTTP server, Chart.js CDN integration requires minimal setup
Remote Access Accessible from any device on WiFi network (phone, tablet, computer), no app installation required
Visualization Capabilities Chart.js enables rich data visualization with real-time plotting, smooth animations, and interactive features
Real-Time Updates JSON API endpoint provides efficient data transfer, 300ms refresh rate maintains responsive feel
Limitations Requires WiFi network, limited to local network without additional configuration, power consumption higher than OLED alone
Best Use Cases Remote monitoring, data logging visualization, multi-user access, professional dashboards

Button Input Interface

Aspect Evaluation
Implementation Approach Digital GPIO reading with debouncing, press pattern detection (single/double/triple/hold) enables mode navigation
User Experience Intuitive press patterns, immediate visual feedback on OLED, no complex UI navigation required
Reliability Hardware debouncing with INPUT_PULLUP, timeout-based pattern recognition prevents accidental triggers
Limitations Limited to single button interaction, pattern learning required, less flexible than touchscreen interfaces
Best Use Cases Simple mode selection, menu navigation, embedded system controls, low-cost input solutions

Comparison Summary

The combination of OLED display and WiFi web interface provides complementary benefits: OLED offers immediate local feedback with minimal latency and power consumption, while the WiFi interface enables rich visualization and remote access. The button-based input provides an intuitive, low-cost navigation method suitable for embedded systems. Together, these tools create a robust interface system that supports both local and remote interaction with sensor data.

Design Files

Design files and code documentation for interface and application programming projects.

ESP32-S3 Development Board and Pinouts

Code files for ESP32-S3 development board interfaces including I2C scanning, OLED display control, and button-based user interface systems. See Week 4 documentation for board design and Week 8 documentation for pinout configurations.

I2C Scanner (i2cscan_generic.ino)

Utility code for scanning and detecting I2C devices on the bus, essential for troubleshooting connection issues.

How the Code Works (Pseudocode)
SETUP:
  Initialize I2C bus
  Initialize Serial communication
  Print "I2C Scanner" message

LOOP:
  Print "Scanning..." message
  Initialize device counter to 0
  
  FOR each address from 1 to 126:
    Begin I2C transmission to address
    Check transmission result
    
    IF transmission successful (error == 0):
      Print device found at address (hex format)
      Increment device counter
    ELSE IF unknown error (error == 4):
      Print unknown error at address
    
  IF no devices found:
    Print "No I2C devices found"
  ELSE:
    Print "done"
  
  Wait 5 seconds before next scan
Key Features
  • Scans all 127 possible I2C addresses (0x01-0x7E)
  • Detects and reports connected devices with hex address format
  • Handles multiple error conditions (device not found, unknown errors)
  • Continuous scanning mode with 5-second intervals
  • Compatible with any I2C bus configuration (Wire, Wire1, etc.)
What You Need to Know
  • I2C Address Range: Valid addresses are 0x08-0x77 (8-119 decimal); addresses 0x00-0x07 and 0x78-0x7F are reserved
  • Common Addresses: OLED displays typically use 0x3C or 0x3D; sensors vary (MAX30102 uses 0x57)
  • Troubleshooting: If no devices found, check wiring (SDA, SCL, power, ground), verify pull-up resistors, confirm device power
  • Usage: Run this before connecting other devices to verify I2C bus is working correctly
Download: i2cscan_generic.ino

Hello World OLED Display (hello_world.ino)

Basic OLED display test code that initializes the display and shows "Hello World" text, confirming I2C communication and display functionality.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial communication at 115200 baud
  Wait 500ms for Serial to stabilize
  
  Initialize I2C bus with SDA pin 5, SCL pin 6
  Print "Starting..." message
  
  Attempt to initialize OLED display:
    IF initialization fails:
      Print "OLED not found" error
      Enter infinite loop (halt)
  
  Clear display buffer
  Set text size to 2
  Set text color to white
  Set cursor position to (0, 20)
  Print "Hello" line
  Print "World!" line
  Update display (send buffer to hardware)

LOOP:
  Empty (runs once, then waits)
Key Features
  • Simple OLED initialization and text display
  • Custom I2C pin configuration for XIAO ESP32-S3 (SDA=5, SCL=6)
  • Error handling with infinite loop if display not found
  • Text size and cursor positioning for centered display
  • One-time display update (no loop refresh needed for static text)
What You Need to Know
  • I2C Pin Configuration: XIAO ESP32-S3 uses pins 5 (SDA) and 6 (SCL) by default; verify your board's pinout
  • Display Address: SSD1306 OLED typically uses address 0x3C; some variants use 0x3D
  • Display Update: Must call display.display() to send buffer to hardware; drawing functions only modify buffer
  • Testing: Use this as first test after connecting OLED to verify wiring and I2C communication before adding complex features
  • Libraries Required: Adafruit_GFX, Adafruit_SSD1306, Wire
Download: hello_world.ino

Button User Interface (outputs.ino)

Mode-based navigation system using button press patterns (single, double, triple, hold) to control multiple output devices including OLED display, camera, sensors, and LED flashlight.

How the Code Works (Pseudocode)
SETUP:
  Initialize OLED display
  Initialize camera module
  Initialize sensors (MPU6050, HX711)
  Initialize button pin (INPUT_PULLUP)
  Initialize LED pin (OUTPUT)
  Set current mode to MENU
  Display menu screen

LOOP:
  Read button state
  
  IF button pressed:
    Record press start time
    Start press detection timer
  
  IF button released:
    Calculate press duration
    IF duration > HOLD_THRESHOLD:
      Activate flashlight mode
    ELSE:
      Increment press count
      Reset press timeout timer
  
  IF press timeout exceeded:
    Process accumulated press count:
      IF press count == 1: Switch to CAMERA mode
      IF press count == 2: Switch to SENSORS mode
      IF press count == 3: Switch to MENU mode
    Reset press count
  
  IF current mode == MENU:
    Display menu screen (button instructions)
  
  IF current mode == CAMERA:
    Capture camera frame
    Process image with dithering algorithm
    Display on OLED
    Run Edge Impulse inference (optional)
    Overlay results on display
  
  IF current mode == SENSORS:
    Read accelerometer/gyroscope data
    Read load cell data
    Display sensor readings on OLED
  
  Update display
Key Features
  • Press pattern detection: single (1x), double (2x), triple (3x), and hold
  • Mode-based navigation system (Menu, Camera, Sensors)
  • Button debouncing with timeout-based pattern recognition
  • Floyd-Steinberg dithering for camera-to-OLED video display
  • Edge Impulse AI inference integration for face detection
  • Multi-sensor integration (MPU6050 accelerometer/gyro, HX711 load cell)
  • Flashlight mode activated by button hold
What You Need to Know
  • Button Wiring: Use INPUT_PULLUP mode (button connects pin to GND when pressed, internal pull-up to 3.3V)
  • Press Detection: Press count is accumulated until timeout (1 second); longer timeout allows slower multiple presses
  • Mode Switching: Each mode has distinct display update logic; ensure proper initialization in setup()
  • Camera Performance: Video streaming to OLED requires significant processing; frame rate depends on resolution and dithering complexity
  • Dependencies: Requires camera_pins.h header file with XIAO ESP32-S3 camera pin definitions; see Ethical AI Use for development details
  • Sensor Conflicts: Code uses preprocessor directives to resolve sensor_t type conflict between ESP32 camera and Adafruit MPU6050 libraries
Download: outputs.ino | camera_pins.h | outputs.zip (complete project)

Grip Strength Monitor (Load Cell + WiFi GUI)

Design files and firmware for a Wi-Fi-enabled grip strength meter built around an 80 kg bar load cell, HX711 amplifier, and ESP32-S3. The mechanical design was informed by the open-source grip strength meter from NeuroTech Hub and validated against the CZL601AC bar load cell datasheet (online, download).

Mechanical Design Files (3D-Printed Components)

  • Base.3mf — main chassis that captures the bar load cell and anchors the fixed side of the gripper.
  • Case.3mf — protective enclosure for the ESP32-S3 and HX711 amplifier with cable strain relief.
  • Handle.3mf — curved grip handle that transfers hand force into the free end of the load cell.
  • Calibration Print.3mf — small test piece used to verify hole diameters and load cell clearances before printing the full assembly.

All parts were printed in PLA with high infill in the load paths to minimize creep and flex during repeated maximal grip trials.

Basic HX711 Reader (loadcell_simple.ino)

Minimal firmware to bring up the HX711 amplifier and read calibrated weight values over Serial for debugging and calibration.

How the Code Works (Pseudocode)
SETUP:
  Configure HX711 data and clock pins (DT=A1, SCK=A0)
  Initialize Serial at 115200 baud
  Begin HX711 with DT/SCK pins
  Set calibration factor (grams per ADC unit)
  Tare the scale so current load is zero

LOOP (every 200 ms):
  If HX711 is ready:
    Read averaged weight using get_units(4)
    Print "weight:<value>" to Serial for Serial Plotter
  Else:
    Print "HX711 not ready" for troubleshooting
Key Features
  • Simple initialization of the HX711 on analog pins A0/A1.
  • Configurable calibration factor for mapping counts to grams or kilograms.
  • Timed reads (200 ms) to keep Serial output manageable and Plotter-friendly.
  • Graceful handling of HX711 not-ready states.
What You Need to Know
  • Use for initial bring-up: Run this first when wiring the HX711 and load cell to confirm clean, stable readings.
  • Calibration factor: Determined experimentally by hanging known weights and adjusting until readings match; see the calibration notes in Calibration Chat.
  • Serial Plotter: The weight:<value> format is convenient for quickly visualizing changes while squeezing the handle.
Download: loadcell_simple.ino

Serial Plotter-Friendly Reader (loadcell_plot.ino)

Refined HX711 reader tuned for the Arduino Serial Plotter: it outputs a single numeric value per line for clean plotting of grip strength over time.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial at 115200 baud
  Initialize HX711 on DT=A1, SCK=A0
  Set calibration factor
  Tare the scale
  Optionally print debug messages when DEBUG=1

LOOP (every 200 ms):
  If HX711 is ready:
    Read filtered weight with get_units(4)
    Optionally print labeled debug text
    Print only the numeric weight to Serial for the Plotter
  Else:
    Optionally print "not ready" debug text
    Print 0 so the plotted line continues gracefully
Key Features
  • DEBUG toggle: Compile-time switch to enable/disable human-readable logs without breaking the Serial Plotter format.
  • Clean “one number per line” output for multi-trial grip testing in the Serial Plotter.
  • Automatic zero output when the HX711 is not ready to keep the time axis continuous.
  • Shared pinout and calibration approach with loadcell_simple.ino for easy swapping.
What You Need to Know
  • Use this sketch to tune calibration and visualize grip curves without any GUI overhead.
  • When collecting data for analysis, keep DEBUG set to 0 so the output is a pure numeric stream.
  • The sample interval (200 ms) gives a smooth trace while keeping file sizes reasonable for multi-second squeezes.
Download: loadcell_plot.ino

WiFi Grip Strength GUI (loadcell_gui.ino)

Full application firmware that exposes grip strength and an estimated age over Wi-Fi using an HTTP server and a Chart.js web dashboard.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial
  Initialize HX711 (pins, calibration factor, tare)
  Connect ESP32-S3 to WiFi (MIT network in this build)
  Start WebServer on port 80
  Register handlers:
    "/"        → serve HTML+JS GUI page from PROGMEM
    "/metrics" → serve JSON with current grip and age

LOOP:
  Handle incoming HTTP clients
  Every 200 ms:
    If HX711 is ready:
      Read smoothed grip strength (kg) via get_units(3)
      Clamp negative values to zero
      Store in global gripStrength

AGE ESTIMATION HELPERS:
  ageFromGripMale(g):
    Clamp g to plausible range
    Compute age using inverted quadratic fit derived from normative data
  ageFromGripFemale(g):
    Same structure with female-specific parameters

HTTP /metrics ENDPOINT:
  Read "sex" query parameter (default "male")
  Compute ageEstimate = ageFromGripMale/ageFromGripFemale(gripStrength)
  Return JSON:
    {"grip": <kg>, "age": <years>}

CLIENT-SIDE GUI (HTML + JS):
  Render dark-themed dashboard with:
    - Sex toggle buttons (male/female)
    - Numeric grip strength (kg) and age
    - Scrolling Chart.js line plot of recent grip values
  Poll /metrics every 200 ms and update DOM + chart
Key Features
  • Embedded HTML/JS dashboard served directly from the ESP32-S3 using PROGMEM.
  • Real-time grip strength plot using Chart.js with ~120 recent samples.
  • Simple sex toggle that switches between male and female age-estimation curves.
  • JSON API at /metrics for future extensions (e.g., logging clients).
What You Need to Know
  • WiFi credentials: Update the ssid and password constants to match your network.
  • Normative model: The age equations are simplified fits inspired by the grip-strength trajectories reported in Syddall et al., PLOS ONE 2014 and are for educational visualization only, not clinical use.
  • Browser requirements: Any modern browser with JavaScript and network access can connect to the ESP32-S3’s IP address to view the dashboard.
  • Development log: The full iterative design of this sketch is captured in the ChatGPT transcript: Grip Strength Monitor Code Chat.
Download: loadcell_gui.ino

Invisible String Chain of Hearts

Code files for the Invisible String pulse oximeter interface system, providing real-time health monitoring through OLED display and WiFi web interface. See Week 11 PCB design documentation for hardware details.

OLED GUI for Pulse Oximeter (pulse_vo2_reads_fixing.ino)

Local OLED display interface showing real-time pulse oximeter readings including heart rate (BPM), blood oxygen saturation (SpO2), and raw IR/RED LED sensor values.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial communication
  Initialize I2C bus (SDA=5, SCL=6) at 400kHz
  Initialize MAX30102 sensor
  Configure sensor:
    Set LED mode to RED + IR
    Set ADC range to 16384
    Set sample rate to 100 Hz
    Set pulse width to 411 μs
    Set LED brightness to medium (0x3F)
  Initialize OLED display
  Clear and prepare display

LOOP:
  Read IR and RED LED values from sensor
  
  Heart Rate Detection:
    Check for heartbeat in IR signal using peak detection
    IF heartbeat detected:
      Calculate time since last beat
      Calculate BPM = 60 / (time_delta / 1000)
      Set beat flag for visual indicator
      Update last beat timestamp
  
  SpO2 Calculation (every 300ms):
    Add IR and RED values to circular buffer
    IF buffer has 50 samples:
      Calculate DC components (average)
      Calculate AC components (RMS)
      Calculate R ratio = (AC_RED/DC_RED) / (AC_IR/DC_IR)
      Estimate SpO2 = 110 - 25 * R
      Clamp SpO2 to 70-100% range
  
  Serial Output:
    Print IR, RED, BPM for Serial Plotter visualization
  
  OLED Display Update:
    Clear display buffer
    Display IR value (small text)
    Display RED value (small text)
    Display BPM value (large text, size 2)
    Display SpO2 percentage (small text)
    IF beat detected: Draw heartbeat indicator dot
    Update display hardware
  
  Delay 20ms (50 Hz update rate)
Key Features
  • Real-time heart rate detection using peak detection algorithm on IR signal
  • SpO2 calculation using ratio-of-ratios method with DC/AC component analysis
  • Circular buffer system for storing 50 samples of IR/RED data
  • Visual heartbeat indicator (flashing dot) when pulse detected
  • Dual output: OLED display and Serial Plotter for real-time waveform visualization
  • Optimized sensor configuration for reliable readings (100 Hz sample rate, medium brightness)
What You Need to Know
  • Sensor Placement: Finger must cover sensor completely; proper contact ensures accurate readings
  • I2C Address: MAX30102 uses address 0x57; verify with I2C scanner if sensor not detected
  • Ground Isolation: RD and IRD pins must be isolated from main ground plane to prevent power issues (see Week 11 PCB design)
  • SpO2 Accuracy: Calculation provides estimation; medical-grade accuracy requires calibration and FDA-approved algorithms
  • Buffer Size: 50-sample buffer provides balance between calculation accuracy and response time
  • Libraries Required: MAX30105 (SparkFun library), Adafruit_GFX, Adafruit_SSD1306, heartRate.h (beat detection)
  • Troubleshooting: If sensor not detected, check power isolation, I2C wiring, and sensor initialization order
Download: pulse_vo2_reads_fixing.ino

WiFi Readings GUI (pulse_gui.ino)

WiFi-enabled web interface providing remote access to pulse oximeter data through HTTP server with JSON API endpoint for real-time data updates.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial communication
  Initialize I2C bus
  Initialize MAX30102 sensor
  Configure sensor (LED mode, sample rate, pulse width)
  Initialize OLED display
  Initialize WiFi:
    Connect to network (SSID, password)
    Wait for connection
    Print IP address
  Initialize HTTP server:
    Route "/" → serve GUI HTML page
    Route "/gui" → serve GUI HTML page
    Route "/metrics" → serve JSON data
  Start web server

LOOP:
  Handle incoming HTTP client requests
  
  Read IR and RED values from sensor
  
  Heart Rate Calculation:
    Check for heartbeat in IR signal
    IF heartbeat detected:
      Calculate BPM from time delta
      Update global BPM variable
  
  SpO2 Calculation:
    Add IR/RED to circular buffer
    IF buffer full (50 samples):
      Calculate SpO2 using ratio-of-ratios
      Update global SpO2 variable
  
  Update global variables (g_ir, g_red, g_bpm, g_spo2)
  
  OLED Display Update:
    Display IR, RED, BPM, SpO2 values
    Update display hardware
Key Features
  • Dual interface: OLED display (local) and WiFi web interface (remote)
  • HTTP server with embedded HTML page stored in PROGMEM
  • JSON API endpoint (/metrics) for real-time data retrieval
  • Automatic WiFi connection with connection status feedback
  • IP address display for easy access
  • Simultaneous sensor reading and web server operation
  • Global variable system for data sharing between sensor reading and HTTP handlers
What You Need to Know
  • WiFi Configuration: Update SSID and password in code; for MIT network, use generated device password from wifi.mit.edu
  • Network Access: Web interface accessible only from devices on same WiFi network; IP address printed to Serial Monitor
  • HTML Storage: GUI HTML page stored in PROGMEM (program memory) to conserve RAM; use PROGMEM for large strings
  • Server Handling: Must call server.handleClient() frequently in loop() for responsive web interface
  • Data Refresh: Client-side JavaScript polls /metrics endpoint every 300ms for real-time updates
  • Power Consumption: WiFi significantly increases power draw compared to OLED-only mode; consider power management for battery operation
  • Libraries Required: WiFi, WebServer, MAX30105, Adafruit_SSD1306
Download: pulse_gui.ino

WiFi Plot GUI (pulse_gui_2.ino)

Enhanced WiFi web interface with real-time plotting capabilities using Chart.js library, displaying live line charts for BPM and SpO2 values with automatic scrolling and data management.

How the Code Works (Pseudocode)
SETUP:
  (Same as pulse_gui.ino)
  Initialize WiFi, sensor, OLED, HTTP server

LOOP:
  (Same as pulse_gui.ino)
  Handle HTTP requests, read sensor, calculate BPM/SpO2

GUI HTML PAGE (embedded in PROGMEM):
  Load Chart.js library from CDN
  Create two Chart.js line chart instances:
    - BPM chart (y-axis: 40-160 BPM)
    - SpO2 chart (y-axis: 70-100%)
  Initialize data arrays for each chart
  
  JavaScript Update Function (runs every 300ms):
    Fetch JSON data from /metrics endpoint
    Update numerical displays (BPM, SpO2, IR, RED)
    Add new BPM value to BPM data array
    Add new SpO2 value to SpO2 data array
    IF array length > maxPoints (100):
      Remove oldest value (shift)
    Update chart labels (array indices)
    Update chart datasets with new data
    Call chart.update() to refresh display
  
  Set interval to call update function every 300ms
Key Features
  • Real-time line chart visualization using Chart.js library
  • Dual chart display: BPM and SpO2 trends over time
  • Automatic data scrolling: maintains 100 most recent data points
  • Numerical displays alongside charts for precise values
  • Responsive design with dark theme for OLED-style aesthetic
  • Automatic chart scaling with fixed y-axis ranges for consistent visualization
  • CDN-based Chart.js loading for minimal memory footprint
What You Need to Know
  • Chart.js CDN: Library loaded from jsdelivr.net CDN; requires internet connection on client device
  • Data Management: Arrays limited to 100 points to prevent memory overflow; older data automatically discarded
  • Update Rate: 300ms refresh rate balances responsiveness with server load; adjust based on network conditions
  • Chart Configuration: Y-axis ranges fixed (BPM: 40-160, SpO2: 70-100) for consistent scaling; modify in JavaScript if needed
  • Browser Compatibility: Requires modern browser with JavaScript enabled; tested on Chrome, Firefox, Safari
  • Performance: Chart updates are lightweight; multiple simultaneous clients may impact ESP32 performance
  • Offline Operation: Charts won't load if client device lacks internet (Chart.js CDN unavailable); consider local hosting for offline use
Download: pulse_gui_2.ino

Reflections & Learnings

Key insights and learnings from working with interface and application programming.

Contributions

Acknowledgements and team roles for interface and application programming work.

Ethical AI Use

Transparent documentation of AI assistance used in this week's interface and application programming work.

This section documents all AI assistance used during Week 12 interface and application programming work. ChatGPT was used for code development, troubleshooting, and technical guidance. All transcripts are linked below for transparency.

Menu System with Modes

AI assistance for developing the button-based menu system with mode navigation (Menu, Camera, Sensors) using press pattern detection. The conversation covered button debouncing, press pattern recognition, mode state management, and OLED menu display design.

Related to: Part (a): Simple Button User Interface on OLED

View ChatGPT Transcript: Menu System with Modes

I2C Device Not Found

Troubleshooting session for I2C device detection issues with MAX30102 pulse oximeter sensor. The conversation addressed power isolation problems, I2C wiring verification, sensor initialization order, and ground plane isolation requirements for accurate sensor operation.

Related to: Part (b): Real-Time Graphical User Interface through OLED and WiFi

View ChatGPT Transcript: I2C Device Not Found

Hello World Code

Development assistance for creating the initial OLED "Hello World" test program. The conversation covered I2C initialization, OLED display library setup, text rendering, and basic display configuration for XIAO ESP32-S3 development board.

Related to: Part (b): Real-Time Graphical User Interface through OLED and WiFi (initial OLED test)

View ChatGPT Transcript: Hello World Code

MAX30102 Initialization Fix

Technical guidance for fixing MAX30102 pulse oximeter sensor initialization issues. The conversation addressed sensor configuration parameters, LED brightness settings, sample rate optimization, initialization sequence requirements, and troubleshooting sensor communication problems.

Related to: Part (b): Real-Time Graphical User Interface through OLED and WiFi (pulse oximeter readings)

View ChatGPT Transcript: MAX30102 Initialization Fix

Grip Strength Monitor Code Design

Code-focused assistance for designing and refining the WiFi grip strength monitor firmware. The conversation covered HX711 bring-up, load cell pin mapping, Serial Plotter debugging sketches, the ESP32-S3 HTTP server, the Chart.js dashboard, and the age-estimation helpers used in loadcell_simple.ino, loadcell_plot.ino, and loadcell_gui.ino.

Related to: Part (c): Real-Time GUI through Mechanical Gripper and WiFi and Grip Strength Monitor design files

View ChatGPT Transcript: Grip Strength Monitor Code

Grip Strength Calibration & Scaling

Calibration-focused assistance for mapping HX711 counts to kilograms and validating the grip strength readings. The discussion walked through using the Serial Plotter, collecting reference weights, tuning the calibration factor, and sanity-checking the age-estimation model derived from normative grip strength data.

Related to: Part (c): Real-Time GUI through Mechanical Gripper and WiFi calibration workflow and the Grip Strength Monitor sketches.

View ChatGPT Transcript: Grip Strength Calibration

Grip Strength Monitor – Cursor Transcript

Full Cursor AI transcript focused on organizing the grip strength monitor section: structuring Part (c), integrating design files, embedding images and videos, and aligning captions, external references, and the Ethical AI Use documentation for the load cell project.

Related to: Part (c): Real-Time GUI through Mechanical Gripper and WiFi, Grip Strength Monitor design files, and this Ethical AI Use section.

View HTML Transcript Download Markdown Transcript

Week 12 Project Documentation

Complete Cursor AI transcript for Week 12 interface and application programming project documentation. This comprehensive conversation covers the creation and population of the Week 12 HTML page, including Individual Assignment sections (button UI and WiFi GUI), Group Assignment tool comparisons, Design Files documentation with pseudocode, and Ethical AI Use section organization. The transcript demonstrates the collaborative process of building professional documentation with structured content, embedded media, and comprehensive code documentation.

Related to: Complete Week 12 documentation including Individual Assignment, Group Assignment, Design Files, and overall page structure

View HTML Transcript Download Markdown Transcript

Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License

``` Checking what remains and removing it: Removing the remaining old content between the two Group Assignment sections: Removing the duplicate Group Assignment comment and the old content: ```html Week 13 · Wildcard Week
← Back to Home
[Profile Image Placeholder]

Week 13

Wildcard Week

Week Highlights

Key captures from the PCB engraving assignment with links to their sections.

ATtiny1626 Board Design

Final ATtiny1626 development board design with connectors and mounting holes

PCB Engraving

ATtiny1626 development board after fiber laser engraving

Soldered Board

Fully assembled ATtiny1626 development board with all components soldered

Blinking LED Demo

RP2354A Board Design

RP2354A development board design

PCB Engraving Detail

Close-up detail of PCB engraving showing trace quality

Table of Contents

Course Content

Training & Documentation

Assignments & Projects

Wildcard Week

This week focuses on exploring digital fabrication processes not covered in previous assignments. We'll design and produce something using computer-aided design and manufacturing, documenting requirements and including everything necessary for reproduction. This week also includes reflection on the impact and purpose of making (almost) anything.

Exploring new digital fabrication processes
Designing and producing with CAD/CAM
Understanding the impact and purpose of fabrication labs

This Week's Goals

  • Explore New Processes
    Design and produce something with a digital process not covered in other assignments
  • Complete Documentation
    Document requirements and include everything necessary to reproduce the project
  • Reflect on Impact
    Understand the purpose and impact of fabrication labs and making

Assignments

  • Group Assignment
    Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment
  • Individual Assignment
    Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment, documenting the requirements that your assignment meets, and including everything necessary to reproduce it

Tools & Materials

  • Carvera (CNC Mill) — Edge cuts and hole machining
  • Fiber Laser Cutter (xTool F2 Ultra) — PCB engraving
  • PCB Design Software (KiCad) — Board layout and design
  • ATtiny1626 Microcontroller — Target device for development board
  • RP2354A Microcontroller — Complex board design

Lecture Notes

Week 13 lecture covering major announcements, week 12 review, system integration reminders, and wildcard week preview.

Theme of the Week

'Step away from the panic'

Major Announcements

  • Subject evaluation: Required for funding the class. Provides feedback to the institute about the class. Important for future students if you care about successors in the class.
  • Calendar alarm: Wildcard week and recitation on why make (almost) anything: impact. Friday is cutoff for assignments and orders (10s of dollars per person from inventory).
  • Final presentation/final exam: Combining multiple additive and subtractive processes (not just design a board and 3D print a case). Goal is system integration out of parts. Final exam criteria:
    • Did you integrate and design a complete system?
    • Can you demo a final project? Here is the cool thing I did and here is how it works.
    • Make a final project video! (helps but not required)
    Focus on well-integrated device!

Review of Week 12 User Interfaces

  • Claire Wang: Music play and Windows 3.1 interface works!
  • Ryan Hoffman: DRV8251A discussion, heat sinks, breakout boards. Wildcards with waterjetting, EDM, multi-axis machining, laser cutting metal. Class in the spring on nature of mathematical modeling.
  • Srikanth Nadhamuni: Background and experience to visiting fellow at MIT. Raspberry Pi W for WiFi, n8n for cloud LLM data crunching. Software: Node.js, MCP bridge server with n8n based on bridge connected to device (NGV tunnel). All set! Fantastic experience, haven't worked so hard in a very long time and learning a lot of new things. Hope to take forward and build other systems. The whole culture of doing and trying yourself fascinating, especially with failing a number of times until you figure it out. Maybe set one up at an IIT in India or AI centers of excellence with education ministry into the Indian education system (see fablabkerala.in or vigyam ashram).
  • Ray Song: Not here.
  • Tyler Jensen (Lincoln Lab, Group 81): Final project discussion (nylon printer). Week 13: Easy for web serial interface for XIAO! Web server to TFT (I think I forgot to load the camera pins with my code for it).
  • Aditi Ramakrishnan: Sloan MBA and strategy consulting background. Discrete time filter (FFT is blown) in skimage.filters — make a bandpass filter, then run a series of these filters, much less computing only adds and multiplies for filtering in realtime.
  • Alexandros Gravalos: Not here.
  • Edward Chen: Check final watch project by Gulati into watch form factor. Clear print on the Form Labs printer, 0.1. Kaman filter for sensor fusion (in the spring class). For position — LSM6DSV16X from input devices. Acceleration at 7 kHz (at audio frequency).

Show and Tell

  • Handle to sensor WiFi user interface
  • Plug to audio LLM user interface

System Integration Reminders

  • Mount electronics
  • Strain relief the final projects

Preview for Wildcard Week

Assignment: Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment.

Recitation Notes: Why Make (Almost) Anything

Recitation exploring the purpose, impact, and scaling of fabrication labs and making infrastructure.

Map of Fab Labs

Why Make a Fab Lab?

  • Used to create a community
  • Building things for the community
  • Sustainability
  • Prototyping quickly

How Impact?

  • How to make spaces: How to measure impact. What is important about fab:
    • Fablabs in cities vs rural areas: The ability to decide their own futures and change their lives fundamentally. 'Safecast revolutionized citizen science' e.g. radiation map.
    • Bringing back manufacturing: Reducing reliance on supply chains.
    • Rural sustainability: Working with indigenous communities on creating technologies themselves at scale and measure their usefulness and efficacy to preserve their ancestral knowledge:
      • How to establish labs there
      • How to make sure the labs get used
    • Hygiene technologies with Proctor and Gamble: Highly commercial. Lots of plastic waste. How can we change how they produce? How to make their products get there through resellers?
    • Trip to Peru and ran workshops, questionnaires, analysis: Collaboration developed into how to produce the products but also how to test their products to be market valuable e.g. mosquito repellents. Out of three plants, two worked better and one wasn't working at all (which is important to know!).

What Does It Mean to Design Infrastructure?

  • What did we want this lab to be able to do?
    • Workshops and questionnaires
    • How much you educate people based on the info they have with the issues the community is facing
    • Energy concerns to consider, some machines just drain the grid and can't be used. Solar powered, battery powered machines, reducing energy consumption of machines. Many concerns important.
  • Ethical questions
  • How to maintain resources

Case Study: Water Purifier Packets

Use them, change them, source them locally, ingredients found locally, how to distribute them globally.

Funding Models

First few fablabs were NSF funded. Now corporate CSR, regional funding, labor funding (10 different ways). Successful fablabs are heterogeneous with lots of ways of funding. The ones that fail usually just have one sponsor.

Example: DIY Raman spectrometer for water purification (even after purifications still have sulfates and improving that too).

What Does It Mean to Scale Infrastructure?

(Besides a lot of meetings!) What is a reasonable way to design a data collection process about what is needed and how to achieve it.

Back to the Map: Expansion

Timeline of development, cocreation, portable, skin analysis, water testing, biomaterial tech, microscopy.

Initial Results from Boston

How to Confront Local Impact
  • Collab with University of Hamburg. Motivation for how much food can be produced in Boston. Where food waste goes and what Boston produces locally. Make things for yourself locally.
  • Impact directly in the community you're living in.

Hatchspace

Focused on rehabilitation of addicts with woodworking. (Vermont is wood producing state).

Example Course Program

  • All-in session and systemic impact
  • Natural and cultural context
  • Skills and workshop
  • Economic vitality
  • Skills and workshop
  • Co-work session
  • Solutionspalooza

In the Course

Hands-on component (no physical robot exists that can do it) and community component is also important. Inclusion is important. Solving unconscious and institutional biases.

  • 'Fabrica! Lab' — Creating new laboratory spaces for female high school students, courses aimed for women in technology, online advising sessions for females interested in tech.
  • Makerspaces — Access to tools behind closed doors at universities, makes a huge difference for people who don't have the ability to prototype for themselves.
  • Materiom — Fablab affiliated project on organic waste for biomaterials.
  • Fablab León
  • Skylab workshop experiment — How to run a noodle shop out of a fablab (creating food from the community).
  • Academany — Global distributed campus for high school education. Fablab all-in (belonging, impact, community), fab futures (future vocational skills), bio academy (synthetic biology), fabricademy (textiles, fab, bio), fab academy (digital fab apps and implications).

Trade-off Between Impactful and Dangerous

People could be doing bad, but not because doing it with a group people with values.

Questions

Clarification: Adding infrastructure to existing fablab infrastructure to help support specific community needs (not specialized fab labs).

Foundations for Fab Futures

July 27-31, 2026 at Fab Boston 2026.

Useful Documentation

Essential resources for wildcard week digital fabrication processes and PCB design.

Class Page

Wildcard Week - MIT Academy

Comprehensive resource covering wildcard week assignment requirements and possibilities including grinding, multi-axis machining, electrical discharge machining, waterjet cutting, flatbed cutting, plasma cutting, laser metal cutting, laser micromachining, welding, molding and casting, folding, robotics, electronics, embedded programming, food, materials, biotechnology, textiles, and composites.

Key Topics

  • Machining: Grinding, multi-axis machining, electrical discharge machining, waterjet cutting, plasma cutting, laser metal cutting, laser micromachining
  • Molding & Casting: Vacuum forming, rotocasting
  • Folding: Mathematics, form and function, kirigami
  • Robotics: Arms, construction, soft actuation pneumatic inflatable
  • Electronics: Pick and place, programmable logic
  • Embedded Programming: Machine learning, machine vision
  • Textiles: Fiber processes, knitting, embroidery (PEmbroider, Ink/Stitch), Fabricademy
  • Composites: Various composite fabrication techniques

ATtiny1626 Development Board References

Embedded Programming Course Resources

Course resources for embedded programming with ATtiny412 microcontroller examples:

Embedded Programming - MIT Academy

ATtiny412 Echo Example Image

Individual Assignment: PCB Engraving with Fiber Laser

Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment. This assignment demonstrates PCB design and fabrication using a combination of CNC milling (Carvera) for edge cuts and hole machining, and fiber laser engraving (xTool F2 Ultra) for trace creation on copper-clad boards. The project includes designing and fabricating two development boards: a simple ATtiny1626 development board and a complex RP2354A development board.

PCB Engraving Process

This project explores PCB fabrication using fiber laser engraving, a process not covered in previous assignments. The workflow combines subtractive manufacturing techniques: CNC milling for mechanical features (edge cuts and holes) and laser engraving for electrical traces. This approach enables rapid prototyping of custom PCBs without requiring chemical etching or specialized PCB manufacturing facilities.

Tools and Equipment

  • Carvera (CNC Mill): Used for edge cuts and hole machining. The laser cannot effectively cut through the board material, so mechanical cutting is required for board outline and mounting holes.
  • Fiber Laser Cutter (xTool F2 Ultra): Used for PCB trace engraving. The laser removes copper from the board surface to create electrical traces and pads.
  • PCB Design Software (KiCad): Used for schematic capture, PCB layout, and design rule checking.

Boards Designed

  • Simple Board: ATtiny1626 development board with connectors, resistors, LED, and capacitor
  • Complex Board: RP2354A development board with more advanced routing and component placement

Board Design Considerations

  • Connector Placement: Top and bottom for connectors, right side for flashing. Connectors along edges to minimize form factor and maximize space usage.
  • Vertical Connectors: Used instead of horizontal connectors because horizontal connectors risk being snapped during use.
  • Black Area Avoidance: Avoid large black areas because laser does not work well with that (keep traces closer and further to minimize black areas). Note: Need to characterize maximum black until it burns the board because dumping too much heat in one place can damage the board.
  • Breadboard Compatibility: Put connectors on 100mil spacing grid size for breadboardability.
  • Pin Count Adjustment: Missed six pins in initial design, so switched from 6-pin headers to 9-pin (distributed six on top and bottom).
  • I2C Resistors: No SDA or SCL resistors included to keep flexibility for future use. May add spot for zero-ohm or pull-up resistor later but keeping it simple for now.
  • Mounting Holes: Added aligned mounting holes (M3 usually — for 3mm screws) for mechanical mounting.
  • Rounded Edge Cuts: Do 90 degrees, copy, drag, and complete the shape for rounded corners.

Design Rules

  • 0.1 mm spacing minimum
  • 0.15 mm trace width minimum
  • 0.15 mm clearance between plane and the rest

Ports and Pins

ATtiny1626 is an 8-bit microcontroller with 8 pins maximum per port. Each port has 8 pins maximum (some less). Need to specify port letter and pin number:

  • PA (0-7)
  • PB (0-7)
  • PC (0-7)

Postprocessing

  • For Carvera: Add new layer with just the holes in Photoshop (only holes for machining).
  • For Laser Engraving: Get rid of the holes for the F2 tools engraving in Inkscape (the frame and the board for alignment, then only engrave the board, not the edges).

Carvera Machining

Using mods → mill 2D PCB workflow:

  • 0.12mm cut depth and max depth

PCB Engraving Process

Using xTool F2 Ultra fiber laser:

  • Use tape for laser alignment
  • Run a test first on spare copper before the Carvera cut board to make sure focus is good (2.7mm thickness setting worked, board is actually 1.6-1.7mm thick)
  • Sand after engraving to clean up any residue
  • Worked with Bantam Tools FR1 (not random Amazon copper)
  • Perform short circuit test after engraving

Soldering

Using solder gun (heat gun) for component assembly.

Components

  • 1x 6-pin flipflop headers
  • 2x 9-pin flipflop headers
  • 1x 4.7k resistor
  • 1x 1k resistor
  • 1x LED
  • 1x 1uF or 10uF capacitor

Design Files

Download design files: ATtiny_QFN.zip and RP2354A-dev-v1.1.zip

Final ATtiny1626 development board design showing component placement and routing
ATtiny1626 final designComplete PCB layout with connectors, components, traces, and mounting holes optimized for laser engraving.
ATtiny1626 development board after fiber laser engraving showing copper traces
PCB after engravingCopper-clad board with traces engraved using fiber laser, ready for component soldering.
Fully assembled ATtiny1626 development board with all components soldered
Soldered boardComplete ATtiny1626 development board with headers, resistors, LED, and capacitor soldered in place.
Blinking LED demoVideo demonstration of the completed ATtiny1626 development board running a simple LED blink program, confirming successful fabrication and programming.
Close-up detail of PCB engraving showing trace quality and copper removal
PCB engraving detailClose-up view of fiber laser engraved traces showing clean copper removal and precise trace definition.

Interface with User

The application interfaces a user with input and/or output devices through the ATtiny1626 development board. The following table describes how the application interfaces with the user:

How It Interfaces with User Input Device(s) Output Device(s)
(a) LED Blink Demonstration None (programmed behavior) LED (visual feedback indicating board functionality)
(b) Future Interface Applications GPIO pins (PA, PB, PC ports) available for sensors, buttons, switches GPIO pins (PA, PB, PC ports) available for LEDs, displays, actuators

Group Assignment: Wildcard Week Digital Process

Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment. This group assignment explores various digital fabrication processes available during wildcard week.

Wildcard Week Possibilities

The wildcard week assignment allows exploration of digital fabrication processes not covered in previous weeks. Possibilities include (but are not limited to):

Machining

  • Grinding
  • Multi-axis machining
  • Electrical discharge machining (EDM)
  • Waterjet cutting
  • Flatbed cutting
  • Plasma cutting
  • Laser metal cutting
  • Laser micromachining

Welding

Various welding techniques for joining materials.

Molding and Casting

  • Vacuum forming
  • Rotocasting

Folding

  • Mathematics
  • Form and function
  • Kirigami

Robotics

  • Arms
  • Construction
  • Soft actuation pneumatic inflatable

Electronics

  • Pick and place
  • Programmable logic

Embedded Programming

  • Machine learning
  • Machine vision

Food

  • Printing
  • Gastronomy

Materials

  • Synthesis
  • Mechanical
  • Rheological

Biotechnology

  • DIYbio
  • iGEM
  • HTGAA
  • Bio Academy

Textiles

  • Fiber processes
  • Knitting
  • Embroidery (PEmbroider, Ink/Stitch)
  • Fabricademy

Composites

Various composite fabrication techniques.

A mode-based user interface system that interfaces users with multiple input and output devices through a simple button press interface. The system provides visual feedback on an OLED display and enables navigation between different modes (Menu, Camera, Sensors) using button press patterns. Users interact by pressing a button multiple times to select modes, with visual confirmation displayed on the OLED screen.

Interface Design

The interface uses a mode-based navigation system where button presses trigger mode changes. A single press enters Camera mode, two presses enter Sensors mode, three presses return to Menu, and holding the button activates a flashlight function. The OLED display shows the current menu state and provides clear visual feedback for each mode transition. See Ethical AI Use: Menu System with Modes for AI-assisted development details.

OLED button user interface menu system displaying mode selection options
OLED button user interface menuMenu screen showing available modes: Camera, Sensors, and Menu navigation options with button press instructions.
Button UI demonstrationVideo showing button press interactions navigating through different modes on the OLED display.
First video stream on OLEDInitial camera feed streaming to OLED display using dithering algorithm for monochrome conversion, demonstrating real-time video output interface.
Download Design Files

Part (b): Real-Time Graphical User Interface through OLED and WiFi

A dual-interface health monitoring system that interfaces users with a MAX30102 pulse oximeter sensor through both an OLED display and a WiFi-enabled web interface. The system provides real-time visualization of heart rate (BPM), blood oxygen saturation (SpO2), and raw sensor data (IR and RED LED readings) through multiple output channels. Users can view data locally on the OLED display or remotely via a web browser accessing the ESP32-S3's built-in HTTP server. See Ethical AI Use: I2C Device Not Found for troubleshooting documentation.

Interface Design

The system provides dual-interface access: a local OLED display shows real-time sensor readings (IR, RED, BPM, SpO2) with visual heartbeat indicators, while a WiFi web interface provides comprehensive data visualization including numerical displays and real-time plotting charts. The web interface uses Chart.js for dynamic graph generation and automatically refreshes every 300ms to maintain real-time data updates. Both interfaces run simultaneously, enabling local monitoring and remote access.

Hello World on OLED

Initial OLED display test showing successful I2C communication and display initialization. See Ethical AI Use: Hello World Code for development details.

Hello World display on OLED for Invisible String project showing successful display initialization
Hello World on OLEDInitial OLED test confirming I2C communication and display functionality before implementing sensor interfaces.
Pulse Oximeter Readings on OLED

Real-time pulse oximeter data displayed on OLED showing IR and RED LED readings, heart rate (BPM), and blood oxygen saturation (SpO2) percentage. A heartbeat indicator flashes when a pulse is detected. See Ethical AI Use: MAX30102 Initialization Fix for sensor setup documentation.

Pulse oximeter readings on OLED displaying IR, RED, BPM, and SpO2 values
OLED sensor readings displayReal-time pulse oximeter data showing IR and RED LED values, heart rate (BPM), and blood oxygen saturation (SpO2) with heartbeat indicator.
BPM and SpO2 demonstrationVideo showing real-time heart rate and blood oxygen saturation measurements updating on OLED display with sensor interaction.
Pulse Oximeter Readings on WiFi GUI

WiFi web interface providing remote access to pulse oximeter data through a responsive HTML dashboard. The interface displays real-time numerical values for BPM, SpO2, IR, and RED readings with automatic data refresh. The web server runs on the ESP32-S3, allowing access from any device on the same WiFi network.

WiFi web interface displaying real-time pulse oximeter readings including BPM, SpO2, IR, and RED values
WiFi GUI readings dashboardRemote web interface showing real-time pulse oximeter data accessible from any device on the WiFi network, displaying BPM, SpO2, IR, and RED values with automatic updates.
Pulse Oximeter Plots on WiFi GUI

Enhanced WiFi web interface with real-time plotting capabilities using Chart.js library. The interface displays live line charts for BPM and SpO2 values, showing trends over time with automatic scrolling and data point management. This visualization enables users to observe patterns in heart rate and blood oxygen levels during monitoring sessions.

Serial monitor output showing sensor readings rising on touch interaction
Serial monitor sensor responseSerial output demonstrating sensor readings increase when finger is placed on MAX30102 sensor, showing IR and RED LED response to touch.
WiFi web interface with real-time plotting of BPM and SpO2 data using Chart.js
WiFi GUI with plotting chartsEnhanced web interface displaying real-time line charts for BPM and SpO2 values, showing trends over time with automatic data refresh and chart scrolling.

I2C Device Detection

Successful I2C device detection after fixing power isolation issues. The system now correctly identifies the OLED display at address 0x3C and the MAX30102 sensor at address 0x57. Initial troubleshooting required isolating the RD (red LED) and IRD (infrared LED) ground terminals from the general ground plane to prevent power issues and enable proper sensor operation. 

20:04:48.612 -> Scanning...
20:04:48.644 -> I2C device found at address 0x3C  !
20:04:48.644 -> I2C device found at address 0x57  !
20:04:48.644 -> done
Download Design Files

Part (c): Real-Time GUI through Mechanical Gripper and WiFi

A Wi-Fi-connected grip strength meter that interfaces a user with a mechanical hand gripper, an 80 kg load cell, and an HX711 amplifier. The ESP32-S3 continuously measures grip force, streams it to a web dashboard, and uses a published relationship between handgrip strength and age to display an estimated “physiological age” in real time. The design is inspired by the open-source grip strength meter from NeuroTech Hub at WashU and the associated PLOS ONE paper on grip strength and age trajectories (Syddall et al., 2014), adapted to my load cell and handle geometry.

Mechanically, a custom 3D-printed gripper clamps around a CZL601-type 80 kg bar load cell (sourced from Amazon 80 kg load cell). I imported a 100 kg load cell CAD from GrabCAD, checked the mounting dimensions against the CZL601AC datasheet (online, download), and confirmed that the hole spacing and footprint match the commercial part used here.

Mechanical Design and Fabrication

CAD model of the 3D-printed grip strength base and load cell mounting region
Grip strength base CADTop view of the grip strength base showing the bar load cell pocket, mounting bosses, and handle interface.
Side view CAD of the hand gripper and load cell assembly
Side view of gripper assemblySide profile showing how the fixed base, moving handle, and load cell align along the force axis of the bar sensor.
Full CAD view of the grip strength device with base and handle
Full grip strength assemblyComplete CAD of the base, handle, and load cell, sized for comfortable adult hand placement and full-finger contact.
Close-up of mounting holes and clearances around the load cell in CAD
Load cell mounting holesDetail of the M6 clearance and counterbore geometry used to capture the load cell without constraining bending.
Perspective CAD view of the gripper handle and base
Handle ergonomicsPerspective view of the curved handle designed to distribute pressure across the palm and fingers during maximal grip.
Photo of drilled clearance hole aligned to the printed pilot in the base
Clearance hole verificationPrinted pilot holes used as drill guides to match the metric mounting dimensions from the CZL601AC datasheet.
Photo of the fully printed grip strength device before drilling and assembly
Fresh off the printer3D-printed base and handle components in PLA prior to post-processing and hardware installation.
Printed part clamped for drilling load cell mounting holes
Workholding for accurate drillingThe printed base clamped to the drill press table so the pilot features guide the final clearance holes into the load cell.
Drilling practiceTraining cuts on scrap material to dial in drill press settings and avoid cracking the printed base during final holes.
Final load cell holesDrilling the final M6 clearance holes through the printed base, constrained by the pilot features to preserve alignment.

Electronics and Calibration

Electronics assembly with HX711 breakout, ESP32-S3, and load cell wiring
Electronics stack-upHX711 amplifier breakout from Amazon wired to the ESP32-S3 and 80 kg load cell with short, twisted signal pairs for noise reduction.
Fully assembled grip strength device with load cell, electronics, and handle
Assembled grip strength meterCompleted mechanical and electrical assembly ready for calibration and software bring-up.
Serial Plotter view of load cell readings increasing with grip force
Serial Plotter calibration tracesRaw HX711 output converted to kilograms and visualized in the Arduino Serial Plotter while applying known weights and grip forces.
Web GUI showing grip strength value, estimated age, and scrolling chart
Wi-Fi grip strength dashboardBrowser-based GUI with live grip strength (kg), estimated age, and a Chart.js time series plot of recent squeezes.

Model Used for Age Estimation

The age-estimation logic in the firmware is based on the non-linear, sex-specific grip-strength trajectories reported in Dodds et al., 2014 (PLOS ONE). As shown in Figure 1 of that paper, grip strength rises rapidly through adolescence, peaks around ages 30–40, and then declines non-linearly with age, with different magnitudes for males and females.

Reference grip strength trajectories over the life course from Dodds et al., PLOS ONE 2014
Reference trajectories (Figure 1)Age-dependent grip strength curves for males and females from Dodds et al., 2014, used as the qualitative target for the embedded model.
Simplified quadratic grip strength model fitted to reference data
Quadratic approximation (Table 2-inspired)Simplified male and female trajectories using peak strengths and curvatures chosen to approximate the summary values reported in Table 2 of Dodds et al., 2014.

To reproduce this shape efficiently on the ESP32, the firmware uses inverted quadratic approximations centered at age 35, consistent with the observed peak in the PLOS ONE data. In the forward direction, grip strength is approximated as:

Males: Grip(age) ≈ 52 − 0.0089·(age − 35)2
Females: Grip(age) ≈ 32 − 0.0059·(age − 35)2

On the device, this relationship is analytically inverted so that the measured grip strength can be mapped back to an estimated age:

age = 35 + √((a − Grip)/b), where a is the peak strength (52 kg for males, 32 kg for females) and b is the curvature (0.0089 for males, 0.0059 for females). The firmware clamps grip strength to physiologically meaningful ranges before applying this formula so the square root remains well-defined. 

float ageFromGripMale(float g) {
  float a = 52.0f, b = 0.0089f;
  if (g > a) g = a;
  if (g < 5) g = 5;
  return 35.0f + sqrtf((a - g) / b);
}

float ageFromGripFemale(float g) {
  float a = 32.0f, b = 0.0059f;
  if (g > a) g = a;
  if (g < 4) g = 4;
  return 35.0f + sqrtf((a - g) / b);
}

For full methodological details and original tables/figures, see the open-access paper: Dodds et al., 2014, PLOS ONE (download local PDF). The implementation here is an educational approximation and not intended for clinical or diagnostic use.

End-to-end live demoReal-time demonstration of squeezing the mechanical gripper and watching the Wi-Fi dashboard update grip strength and estimated age on a laptop.

Related Design, Code, and Calibration Resources

User Interface Comparison

Summary of how each interface application connects users with input and output devices.

Application How It Interfaces with the User Input Device(s) Output Device(s)
(a) Button User Interface Button press patterns (single, double, triple press, hold) provide mode selection input. OLED display shows current menu state and mode options. Users receive immediate visual feedback for each interaction. Button (GPIO pin 4) OLED Display (SSD1306, I²C 0x3C)
LED (GPIO pin 3, flashlight mode)
(b) Real-Time GUI (OLED & WiFi) Physical finger placement on MAX30102 sensor provides input. OLED displays real-time sensor data locally. WiFi web interface enables remote monitoring with numerical displays and live plotting charts accessible from any web browser. MAX30102 Pulse Oximeter Sensor (I²C 0x57) OLED Display (SSD1306, I²C 0x3C)
WiFi Web Interface (HTTP Server with Chart.js visualization)
(c) Grip Strength GUI (Load Cell & WiFi) Users squeeze a mechanical hand gripper that transfers force into an 80 kg bar load cell. The ESP32-S3 measures grip strength through the HX711 amplifier and streams results to a WiFi web dashboard that displays live grip force and an estimated physiological age in real time. Mechanical gripper linked to 80 kg load cell (CZL601-type)
HX711 load cell amplifier		 WiFi Web Interface (HTTP Server with Chart.js visualization)
Optional Serial Plotter (for calibration traces)

Group Assignment: Compare as Many Tool Options as Possible

Compare as many tool options as possible for interface and application programming.

General Comparison: Interface & Application Programming Tools

Comprehensive comparison of interface and application programming tools available for embedded systems and IoT development. This analysis covers tools from the MIT Academy Interface & Application Programming class page, evaluating their capabilities, use cases, and trade-offs for different application scenarios.

Embedded Display Interfaces

Tool/Framework Description Pros Cons Best For
OLED (SSD1306) Monochrome OLED displays via I²C Low power, high contrast, simple I²C interface, pixel-level control Limited resolution (128x64), monochrome only, small display size Status displays, sensor readouts, simple menus, embedded dashboards
LCD Character Displays Character-based LCD displays (16x2, 20x4) Simple API, readable in sunlight, low cost Limited to text/characters, no graphics, requires backlight power Text-only interfaces, status messages, debugging output
TFT Color Displays Full-color TFT LCD displays Color graphics, touch support, high resolution High power consumption, complex drivers, larger footprint Rich GUIs, image display, interactive touch interfaces

Web-Based Interfaces

Tool/Framework Description Pros Cons Best For
HTTP Server (ESP32) Built-in HTTP server on ESP32 for web interfaces Remote access, cross-platform (any browser), no app installation, real-time updates Requires WiFi, network dependency, limited to local network without port forwarding Remote monitoring, data visualization, control panels, sensor dashboards
WebSockets Real-time bidirectional communication Low latency, bidirectional, efficient for frequent updates More complex than HTTP, requires persistent connection Real-time streaming, interactive controls, live data feeds
Chart.js JavaScript charting library for web interfaces Beautiful charts, interactive, responsive, easy integration Requires JavaScript, CDN dependency or local hosting Data visualization, time series plots, sensor monitoring dashboards

Mobile & Native App Frameworks

Tool/Framework Description Pros Cons Best For
React Native Cross-platform mobile app framework Cross-platform (iOS/Android), native performance, large ecosystem Complex setup, requires mobile development knowledge Full-featured mobile apps, production deployments
Flutter Google's UI toolkit for cross-platform apps Single codebase, high performance, customizable UI Dart language, larger app size, learning curve Custom mobile interfaces, platform-specific designs
Progressive Web Apps (PWA) Web apps with native-like features No app store, cross-platform, offline capability Limited native API access, browser dependency Web-based mobile interfaces, simple deployment

Specific Comparison: Tools Used in Individual Assignment

Detailed comparison of the specific interface programming tools implemented in this week's individual assignment, evaluating their performance, ease of use, and suitability for embedded health monitoring applications.

OLED Display Interface (Adafruit SSD1306)

Aspect Evaluation
Ease of Implementation Simple I²C interface, well-documented Adafruit library, minimal wiring (SDA, SCL, power, ground)
Display Quality High contrast monochrome display, crisp text rendering, suitable for sensor data visualization
Power Consumption Very low power draw, ideal for battery-powered applications
Limitations 128x64 pixel resolution limits detail, monochrome only, small physical size (0.96" typical)
Best Use Cases Local sensor readouts, menu systems, status indicators, simple data displays

WiFi Web Interface (ESP32 HTTP Server + Chart.js)

Aspect Evaluation
Ease of Implementation ESP32 WebServer library provides straightforward HTTP server, Chart.js CDN integration requires minimal setup
Remote Access Accessible from any device on WiFi network (phone, tablet, computer), no app installation required
Visualization Capabilities Chart.js enables rich data visualization with real-time plotting, smooth animations, and interactive features
Real-Time Updates JSON API endpoint provides efficient data transfer, 300ms refresh rate maintains responsive feel
Limitations Requires WiFi network, limited to local network without additional configuration, power consumption higher than OLED alone
Best Use Cases Remote monitoring, data logging visualization, multi-user access, professional dashboards

Button Input Interface

Aspect Evaluation
Implementation Approach Digital GPIO reading with debouncing, press pattern detection (single/double/triple/hold) enables mode navigation
User Experience Intuitive press patterns, immediate visual feedback on OLED, no complex UI navigation required
Reliability Hardware debouncing with INPUT_PULLUP, timeout-based pattern recognition prevents accidental triggers
Limitations Limited to single button interaction, pattern learning required, less flexible than touchscreen interfaces
Best Use Cases Simple mode selection, menu navigation, embedded system controls, low-cost input solutions

Comparison Summary

The combination of OLED display and WiFi web interface provides complementary benefits: OLED offers immediate local feedback with minimal latency and power consumption, while the WiFi interface enables rich visualization and remote access. The button-based input provides an intuitive, low-cost navigation method suitable for embedded systems. Together, these tools create a robust interface system that supports both local and remote interaction with sensor data.

Design Files

Design files and code documentation for interface and application programming projects.

ESP32-S3 Development Board and Pinouts

Code files for ESP32-S3 development board interfaces including I2C scanning, OLED display control, and button-based user interface systems. See Week 4 documentation for board design and Week 8 documentation for pinout configurations.

I2C Scanner (i2cscan_generic.ino)

Utility code for scanning and detecting I2C devices on the bus, essential for troubleshooting connection issues.

How the Code Works (Pseudocode)
SETUP:
  Initialize I2C bus
  Initialize Serial communication
  Print "I2C Scanner" message

LOOP:
  Print "Scanning..." message
  Initialize device counter to 0
  
  FOR each address from 1 to 126:
    Begin I2C transmission to address
    Check transmission result
    
    IF transmission successful (error == 0):
      Print device found at address (hex format)
      Increment device counter
    ELSE IF unknown error (error == 4):
      Print unknown error at address
    
  IF no devices found:
    Print "No I2C devices found"
  ELSE:
    Print "done"
  
  Wait 5 seconds before next scan
Key Features
  • Scans all 127 possible I2C addresses (0x01-0x7E)
  • Detects and reports connected devices with hex address format
  • Handles multiple error conditions (device not found, unknown errors)
  • Continuous scanning mode with 5-second intervals
  • Compatible with any I2C bus configuration (Wire, Wire1, etc.)
What You Need to Know
  • I2C Address Range: Valid addresses are 0x08-0x77 (8-119 decimal); addresses 0x00-0x07 and 0x78-0x7F are reserved
  • Common Addresses: OLED displays typically use 0x3C or 0x3D; sensors vary (MAX30102 uses 0x57)
  • Troubleshooting: If no devices found, check wiring (SDA, SCL, power, ground), verify pull-up resistors, confirm device power
  • Usage: Run this before connecting other devices to verify I2C bus is working correctly
Download: i2cscan_generic.ino

Hello World OLED Display (hello_world.ino)

Basic OLED display test code that initializes the display and shows "Hello World" text, confirming I2C communication and display functionality.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial communication at 115200 baud
  Wait 500ms for Serial to stabilize
  
  Initialize I2C bus with SDA pin 5, SCL pin 6
  Print "Starting..." message
  
  Attempt to initialize OLED display:
    IF initialization fails:
      Print "OLED not found" error
      Enter infinite loop (halt)
  
  Clear display buffer
  Set text size to 2
  Set text color to white
  Set cursor position to (0, 20)
  Print "Hello" line
  Print "World!" line
  Update display (send buffer to hardware)

LOOP:
  Empty (runs once, then waits)
Key Features
  • Simple OLED initialization and text display
  • Custom I2C pin configuration for XIAO ESP32-S3 (SDA=5, SCL=6)
  • Error handling with infinite loop if display not found
  • Text size and cursor positioning for centered display
  • One-time display update (no loop refresh needed for static text)
What You Need to Know
  • I2C Pin Configuration: XIAO ESP32-S3 uses pins 5 (SDA) and 6 (SCL) by default; verify your board's pinout
  • Display Address: SSD1306 OLED typically uses address 0x3C; some variants use 0x3D
  • Display Update: Must call display.display() to send buffer to hardware; drawing functions only modify buffer
  • Testing: Use this as first test after connecting OLED to verify wiring and I2C communication before adding complex features
  • Libraries Required: Adafruit_GFX, Adafruit_SSD1306, Wire
Download: hello_world.ino

Button User Interface (outputs.ino)

Mode-based navigation system using button press patterns (single, double, triple, hold) to control multiple output devices including OLED display, camera, sensors, and LED flashlight.

How the Code Works (Pseudocode)
SETUP:
  Initialize OLED display
  Initialize camera module
  Initialize sensors (MPU6050, HX711)
  Initialize button pin (INPUT_PULLUP)
  Initialize LED pin (OUTPUT)
  Set current mode to MENU
  Display menu screen

LOOP:
  Read button state
  
  IF button pressed:
    Record press start time
    Start press detection timer
  
  IF button released:
    Calculate press duration
    IF duration > HOLD_THRESHOLD:
      Activate flashlight mode
    ELSE:
      Increment press count
      Reset press timeout timer
  
  IF press timeout exceeded:
    Process accumulated press count:
      IF press count == 1: Switch to CAMERA mode
      IF press count == 2: Switch to SENSORS mode
      IF press count == 3: Switch to MENU mode
    Reset press count
  
  IF current mode == MENU:
    Display menu screen (button instructions)
  
  IF current mode == CAMERA:
    Capture camera frame
    Process image with dithering algorithm
    Display on OLED
    Run Edge Impulse inference (optional)
    Overlay results on display
  
  IF current mode == SENSORS:
    Read accelerometer/gyroscope data
    Read load cell data
    Display sensor readings on OLED
  
  Update display
Key Features
  • Press pattern detection: single (1x), double (2x), triple (3x), and hold
  • Mode-based navigation system (Menu, Camera, Sensors)
  • Button debouncing with timeout-based pattern recognition
  • Floyd-Steinberg dithering for camera-to-OLED video display
  • Edge Impulse AI inference integration for face detection
  • Multi-sensor integration (MPU6050 accelerometer/gyro, HX711 load cell)
  • Flashlight mode activated by button hold
What You Need to Know
  • Button Wiring: Use INPUT_PULLUP mode (button connects pin to GND when pressed, internal pull-up to 3.3V)
  • Press Detection: Press count is accumulated until timeout (1 second); longer timeout allows slower multiple presses
  • Mode Switching: Each mode has distinct display update logic; ensure proper initialization in setup()
  • Camera Performance: Video streaming to OLED requires significant processing; frame rate depends on resolution and dithering complexity
  • Dependencies: Requires camera_pins.h header file with XIAO ESP32-S3 camera pin definitions; see Ethical AI Use for development details
  • Sensor Conflicts: Code uses preprocessor directives to resolve sensor_t type conflict between ESP32 camera and Adafruit MPU6050 libraries
Download: outputs.ino | camera_pins.h | outputs.zip (complete project)

Grip Strength Monitor (Load Cell + WiFi GUI)

Design files and firmware for a Wi-Fi-enabled grip strength meter built around an 80 kg bar load cell, HX711 amplifier, and ESP32-S3. The mechanical design was informed by the open-source grip strength meter from NeuroTech Hub and validated against the CZL601AC bar load cell datasheet (online, download).

Mechanical Design Files (3D-Printed Components)

  • Base.3mf — main chassis that captures the bar load cell and anchors the fixed side of the gripper.
  • Case.3mf — protective enclosure for the ESP32-S3 and HX711 amplifier with cable strain relief.
  • Handle.3mf — curved grip handle that transfers hand force into the free end of the load cell.
  • Calibration Print.3mf — small test piece used to verify hole diameters and load cell clearances before printing the full assembly.

All parts were printed in PLA with high infill in the load paths to minimize creep and flex during repeated maximal grip trials.

Basic HX711 Reader (loadcell_simple.ino)

Minimal firmware to bring up the HX711 amplifier and read calibrated weight values over Serial for debugging and calibration.

How the Code Works (Pseudocode)
SETUP:
  Configure HX711 data and clock pins (DT=A1, SCK=A0)
  Initialize Serial at 115200 baud
  Begin HX711 with DT/SCK pins
  Set calibration factor (grams per ADC unit)
  Tare the scale so current load is zero

LOOP (every 200 ms):
  If HX711 is ready:
    Read averaged weight using get_units(4)
    Print "weight:<value>" to Serial for Serial Plotter
  Else:
    Print "HX711 not ready" for troubleshooting
Key Features
  • Simple initialization of the HX711 on analog pins A0/A1.
  • Configurable calibration factor for mapping counts to grams or kilograms.
  • Timed reads (200 ms) to keep Serial output manageable and Plotter-friendly.
  • Graceful handling of HX711 not-ready states.
What You Need to Know
  • Use for initial bring-up: Run this first when wiring the HX711 and load cell to confirm clean, stable readings.
  • Calibration factor: Determined experimentally by hanging known weights and adjusting until readings match; see the calibration notes in Calibration Chat.
  • Serial Plotter: The weight:<value> format is convenient for quickly visualizing changes while squeezing the handle.
Download: loadcell_simple.ino

Serial Plotter-Friendly Reader (loadcell_plot.ino)

Refined HX711 reader tuned for the Arduino Serial Plotter: it outputs a single numeric value per line for clean plotting of grip strength over time.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial at 115200 baud
  Initialize HX711 on DT=A1, SCK=A0
  Set calibration factor
  Tare the scale
  Optionally print debug messages when DEBUG=1

LOOP (every 200 ms):
  If HX711 is ready:
    Read filtered weight with get_units(4)
    Optionally print labeled debug text
    Print only the numeric weight to Serial for the Plotter
  Else:
    Optionally print "not ready" debug text
    Print 0 so the plotted line continues gracefully
Key Features
  • DEBUG toggle: Compile-time switch to enable/disable human-readable logs without breaking the Serial Plotter format.
  • Clean “one number per line” output for multi-trial grip testing in the Serial Plotter.
  • Automatic zero output when the HX711 is not ready to keep the time axis continuous.
  • Shared pinout and calibration approach with loadcell_simple.ino for easy swapping.
What You Need to Know
  • Use this sketch to tune calibration and visualize grip curves without any GUI overhead.
  • When collecting data for analysis, keep DEBUG set to 0 so the output is a pure numeric stream.
  • The sample interval (200 ms) gives a smooth trace while keeping file sizes reasonable for multi-second squeezes.
Download: loadcell_plot.ino

WiFi Grip Strength GUI (loadcell_gui.ino)

Full application firmware that exposes grip strength and an estimated age over Wi-Fi using an HTTP server and a Chart.js web dashboard.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial
  Initialize HX711 (pins, calibration factor, tare)
  Connect ESP32-S3 to WiFi (MIT network in this build)
  Start WebServer on port 80
  Register handlers:
    "/"        → serve HTML+JS GUI page from PROGMEM
    "/metrics" → serve JSON with current grip and age

LOOP:
  Handle incoming HTTP clients
  Every 200 ms:
    If HX711 is ready:
      Read smoothed grip strength (kg) via get_units(3)
      Clamp negative values to zero
      Store in global gripStrength

AGE ESTIMATION HELPERS:
  ageFromGripMale(g):
    Clamp g to plausible range
    Compute age using inverted quadratic fit derived from normative data
  ageFromGripFemale(g):
    Same structure with female-specific parameters

HTTP /metrics ENDPOINT:
  Read "sex" query parameter (default "male")
  Compute ageEstimate = ageFromGripMale/ageFromGripFemale(gripStrength)
  Return JSON:
    {"grip": <kg>, "age": <years>}

CLIENT-SIDE GUI (HTML + JS):
  Render dark-themed dashboard with:
    - Sex toggle buttons (male/female)
    - Numeric grip strength (kg) and age
    - Scrolling Chart.js line plot of recent grip values
  Poll /metrics every 200 ms and update DOM + chart
Key Features
  • Embedded HTML/JS dashboard served directly from the ESP32-S3 using PROGMEM.
  • Real-time grip strength plot using Chart.js with ~120 recent samples.
  • Simple sex toggle that switches between male and female age-estimation curves.
  • JSON API at /metrics for future extensions (e.g., logging clients).
What You Need to Know
  • WiFi credentials: Update the ssid and password constants to match your network.
  • Normative model: The age equations are simplified fits inspired by the grip-strength trajectories reported in Syddall et al., PLOS ONE 2014 and are for educational visualization only, not clinical use.
  • Browser requirements: Any modern browser with JavaScript and network access can connect to the ESP32-S3’s IP address to view the dashboard.
  • Development log: The full iterative design of this sketch is captured in the ChatGPT transcript: Grip Strength Monitor Code Chat.
Download: loadcell_gui.ino

Invisible String Chain of Hearts

Code files for the Invisible String pulse oximeter interface system, providing real-time health monitoring through OLED display and WiFi web interface. See Week 11 PCB design documentation for hardware details.

OLED GUI for Pulse Oximeter (pulse_vo2_reads_fixing.ino)

Local OLED display interface showing real-time pulse oximeter readings including heart rate (BPM), blood oxygen saturation (SpO2), and raw IR/RED LED sensor values.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial communication
  Initialize I2C bus (SDA=5, SCL=6) at 400kHz
  Initialize MAX30102 sensor
  Configure sensor:
    Set LED mode to RED + IR
    Set ADC range to 16384
    Set sample rate to 100 Hz
    Set pulse width to 411 μs
    Set LED brightness to medium (0x3F)
  Initialize OLED display
  Clear and prepare display

LOOP:
  Read IR and RED LED values from sensor
  
  Heart Rate Detection:
    Check for heartbeat in IR signal using peak detection
    IF heartbeat detected:
      Calculate time since last beat
      Calculate BPM = 60 / (time_delta / 1000)
      Set beat flag for visual indicator
      Update last beat timestamp
  
  SpO2 Calculation (every 300ms):
    Add IR and RED values to circular buffer
    IF buffer has 50 samples:
      Calculate DC components (average)
      Calculate AC components (RMS)
      Calculate R ratio = (AC_RED/DC_RED) / (AC_IR/DC_IR)
      Estimate SpO2 = 110 - 25 * R
      Clamp SpO2 to 70-100% range
  
  Serial Output:
    Print IR, RED, BPM for Serial Plotter visualization
  
  OLED Display Update:
    Clear display buffer
    Display IR value (small text)
    Display RED value (small text)
    Display BPM value (large text, size 2)
    Display SpO2 percentage (small text)
    IF beat detected: Draw heartbeat indicator dot
    Update display hardware
  
  Delay 20ms (50 Hz update rate)
Key Features
  • Real-time heart rate detection using peak detection algorithm on IR signal
  • SpO2 calculation using ratio-of-ratios method with DC/AC component analysis
  • Circular buffer system for storing 50 samples of IR/RED data
  • Visual heartbeat indicator (flashing dot) when pulse detected
  • Dual output: OLED display and Serial Plotter for real-time waveform visualization
  • Optimized sensor configuration for reliable readings (100 Hz sample rate, medium brightness)
What You Need to Know
  • Sensor Placement: Finger must cover sensor completely; proper contact ensures accurate readings
  • I2C Address: MAX30102 uses address 0x57; verify with I2C scanner if sensor not detected
  • Ground Isolation: RD and IRD pins must be isolated from main ground plane to prevent power issues (see Week 11 PCB design)
  • SpO2 Accuracy: Calculation provides estimation; medical-grade accuracy requires calibration and FDA-approved algorithms
  • Buffer Size: 50-sample buffer provides balance between calculation accuracy and response time
  • Libraries Required: MAX30105 (SparkFun library), Adafruit_GFX, Adafruit_SSD1306, heartRate.h (beat detection)
  • Troubleshooting: If sensor not detected, check power isolation, I2C wiring, and sensor initialization order
Download: pulse_vo2_reads_fixing.ino

WiFi Readings GUI (pulse_gui.ino)

WiFi-enabled web interface providing remote access to pulse oximeter data through HTTP server with JSON API endpoint for real-time data updates.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial communication
  Initialize I2C bus
  Initialize MAX30102 sensor
  Configure sensor (LED mode, sample rate, pulse width)
  Initialize OLED display
  Initialize WiFi:
    Connect to network (SSID, password)
    Wait for connection
    Print IP address
  Initialize HTTP server:
    Route "/" → serve GUI HTML page
    Route "/gui" → serve GUI HTML page
    Route "/metrics" → serve JSON data
  Start web server

LOOP:
  Handle incoming HTTP client requests
  
  Read IR and RED values from sensor
  
  Heart Rate Calculation:
    Check for heartbeat in IR signal
    IF heartbeat detected:
      Calculate BPM from time delta
      Update global BPM variable
  
  SpO2 Calculation:
    Add IR/RED to circular buffer
    IF buffer full (50 samples):
      Calculate SpO2 using ratio-of-ratios
      Update global SpO2 variable
  
  Update global variables (g_ir, g_red, g_bpm, g_spo2)
  
  OLED Display Update:
    Display IR, RED, BPM, SpO2 values
    Update display hardware
Key Features
  • Dual interface: OLED display (local) and WiFi web interface (remote)
  • HTTP server with embedded HTML page stored in PROGMEM
  • JSON API endpoint (/metrics) for real-time data retrieval
  • Automatic WiFi connection with connection status feedback
  • IP address display for easy access
  • Simultaneous sensor reading and web server operation
  • Global variable system for data sharing between sensor reading and HTTP handlers
What You Need to Know
  • WiFi Configuration: Update SSID and password in code; for MIT network, use generated device password from wifi.mit.edu
  • Network Access: Web interface accessible only from devices on same WiFi network; IP address printed to Serial Monitor
  • HTML Storage: GUI HTML page stored in PROGMEM (program memory) to conserve RAM; use PROGMEM for large strings
  • Server Handling: Must call server.handleClient() frequently in loop() for responsive web interface
  • Data Refresh: Client-side JavaScript polls /metrics endpoint every 300ms for real-time updates
  • Power Consumption: WiFi significantly increases power draw compared to OLED-only mode; consider power management for battery operation
  • Libraries Required: WiFi, WebServer, MAX30105, Adafruit_SSD1306
Download: pulse_gui.ino

WiFi Plot GUI (pulse_gui_2.ino)

Enhanced WiFi web interface with real-time plotting capabilities using Chart.js library, displaying live line charts for BPM and SpO2 values with automatic scrolling and data management.

How the Code Works (Pseudocode)
SETUP:
  (Same as pulse_gui.ino)
  Initialize WiFi, sensor, OLED, HTTP server

LOOP:
  (Same as pulse_gui.ino)
  Handle HTTP requests, read sensor, calculate BPM/SpO2

GUI HTML PAGE (embedded in PROGMEM):
  Load Chart.js library from CDN
  Create two Chart.js line chart instances:
    - BPM chart (y-axis: 40-160 BPM)
    - SpO2 chart (y-axis: 70-100%)
  Initialize data arrays for each chart
  
  JavaScript Update Function (runs every 300ms):
    Fetch JSON data from /metrics endpoint
    Update numerical displays (BPM, SpO2, IR, RED)
    Add new BPM value to BPM data array
    Add new SpO2 value to SpO2 data array
    IF array length > maxPoints (100):
      Remove oldest value (shift)
    Update chart labels (array indices)
    Update chart datasets with new data
    Call chart.update() to refresh display
  
  Set interval to call update function every 300ms
Key Features
  • Real-time line chart visualization using Chart.js library
  • Dual chart display: BPM and SpO2 trends over time
  • Automatic data scrolling: maintains 100 most recent data points
  • Numerical displays alongside charts for precise values
  • Responsive design with dark theme for OLED-style aesthetic
  • Automatic chart scaling with fixed y-axis ranges for consistent visualization
  • CDN-based Chart.js loading for minimal memory footprint
What You Need to Know
  • Chart.js CDN: Library loaded from jsdelivr.net CDN; requires internet connection on client device
  • Data Management: Arrays limited to 100 points to prevent memory overflow; older data automatically discarded
  • Update Rate: 300ms refresh rate balances responsiveness with server load; adjust based on network conditions
  • Chart Configuration: Y-axis ranges fixed (BPM: 40-160, SpO2: 70-100) for consistent scaling; modify in JavaScript if needed
  • Browser Compatibility: Requires modern browser with JavaScript enabled; tested on Chrome, Firefox, Safari
  • Performance: Chart updates are lightweight; multiple simultaneous clients may impact ESP32 performance
  • Offline Operation: Charts won't load if client device lacks internet (Chart.js CDN unavailable); consider local hosting for offline use
Download: pulse_gui_2.ino

Reflections & Learnings

Key insights and learnings from working with interface and application programming.

Contributions

Acknowledgements and team roles for interface and application programming work.

Ethical AI Use

Transparent documentation of AI assistance used in this week's interface and application programming work.

This section documents all AI assistance used during Week 12 interface and application programming work. ChatGPT was used for code development, troubleshooting, and technical guidance. All transcripts are linked below for transparency.

Menu System with Modes

AI assistance for developing the button-based menu system with mode navigation (Menu, Camera, Sensors) using press pattern detection. The conversation covered button debouncing, press pattern recognition, mode state management, and OLED menu display design.

Related to: Part (a): Simple Button User Interface on OLED

View ChatGPT Transcript: Menu System with Modes

I2C Device Not Found

Troubleshooting session for I2C device detection issues with MAX30102 pulse oximeter sensor. The conversation addressed power isolation problems, I2C wiring verification, sensor initialization order, and ground plane isolation requirements for accurate sensor operation.

Related to: Part (b): Real-Time Graphical User Interface through OLED and WiFi

View ChatGPT Transcript: I2C Device Not Found

Hello World Code

Development assistance for creating the initial OLED "Hello World" test program. The conversation covered I2C initialization, OLED display library setup, text rendering, and basic display configuration for XIAO ESP32-S3 development board.

Related to: Part (b): Real-Time Graphical User Interface through OLED and WiFi (initial OLED test)

View ChatGPT Transcript: Hello World Code

MAX30102 Initialization Fix

Technical guidance for fixing MAX30102 pulse oximeter sensor initialization issues. The conversation addressed sensor configuration parameters, LED brightness settings, sample rate optimization, initialization sequence requirements, and troubleshooting sensor communication problems.

Related to: Part (b): Real-Time Graphical User Interface through OLED and WiFi (pulse oximeter readings)

View ChatGPT Transcript: MAX30102 Initialization Fix

Grip Strength Monitor Code Design

Code-focused assistance for designing and refining the WiFi grip strength monitor firmware. The conversation covered HX711 bring-up, load cell pin mapping, Serial Plotter debugging sketches, the ESP32-S3 HTTP server, the Chart.js dashboard, and the age-estimation helpers used in loadcell_simple.ino, loadcell_plot.ino, and loadcell_gui.ino.

Related to: Part (c): Real-Time GUI through Mechanical Gripper and WiFi and Grip Strength Monitor design files

View ChatGPT Transcript: Grip Strength Monitor Code

Grip Strength Calibration & Scaling

Calibration-focused assistance for mapping HX711 counts to kilograms and validating the grip strength readings. The discussion walked through using the Serial Plotter, collecting reference weights, tuning the calibration factor, and sanity-checking the age-estimation model derived from normative grip strength data.

Related to: Part (c): Real-Time GUI through Mechanical Gripper and WiFi calibration workflow and the Grip Strength Monitor sketches.

View ChatGPT Transcript: Grip Strength Calibration

Grip Strength Monitor – Cursor Transcript

Full Cursor AI transcript focused on organizing the grip strength monitor section: structuring Part (c), integrating design files, embedding images and videos, and aligning captions, external references, and the Ethical AI Use documentation for the load cell project.

Related to: Part (c): Real-Time GUI through Mechanical Gripper and WiFi, Grip Strength Monitor design files, and this Ethical AI Use section.

View HTML Transcript Download Markdown Transcript

Week 12 Project Documentation

Complete Cursor AI transcript for Week 12 interface and application programming project documentation. This comprehensive conversation covers the creation and population of the Week 12 HTML page, including Individual Assignment sections (button UI and WiFi GUI), Group Assignment tool comparisons, Design Files documentation with pseudocode, and Ethical AI Use section organization. The transcript demonstrates the collaborative process of building professional documentation with structured content, embedded media, and comprehensive code documentation.

Related to: Complete Week 12 documentation including Individual Assignment, Group Assignment, Design Files, and overall page structure

View HTML Transcript Download Markdown Transcript

Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License

``` Checking for remaining old content and updating the Design Files section. Finding the Design Files section: Removing the remaining old content and updating the Design Files section. Reading what's there: Removing the old content between the Group Assignment section and the real Design Files section, then updating the Design Files section. Removing the duplicate/misplaced content: ```html Week 13 · Wildcard Week
← Back to Home
[Profile Image Placeholder]

Week 13

Wildcard Week

Week Highlights

Key captures from the PCB engraving assignment with links to their sections.

ATtiny1626 Board Design

Final ATtiny1626 development board design with connectors and mounting holes

PCB Engraving

ATtiny1626 development board after fiber laser engraving

Soldered Board

Fully assembled ATtiny1626 development board with all components soldered

Blinking LED Demo

RP2354A Board Design

RP2354A development board design

PCB Engraving Detail

Close-up detail of PCB engraving showing trace quality

Table of Contents

Course Content

Training & Documentation

Assignments & Projects

Wildcard Week

This week focuses on exploring digital fabrication processes not covered in previous assignments. We'll design and produce something using computer-aided design and manufacturing, documenting requirements and including everything necessary for reproduction. This week also includes reflection on the impact and purpose of making (almost) anything.

Exploring new digital fabrication processes
Designing and producing with CAD/CAM
Understanding the impact and purpose of fabrication labs

This Week's Goals

  • Explore New Processes
    Design and produce something with a digital process not covered in other assignments
  • Complete Documentation
    Document requirements and include everything necessary to reproduce the project
  • Reflect on Impact
    Understand the purpose and impact of fabrication labs and making

Assignments

  • Group Assignment
    Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment
  • Individual Assignment
    Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment, documenting the requirements that your assignment meets, and including everything necessary to reproduce it

Tools & Materials

  • Carvera (CNC Mill) — Edge cuts and hole machining
  • Fiber Laser Cutter (xTool F2 Ultra) — PCB engraving
  • PCB Design Software (KiCad) — Board layout and design
  • ATtiny1626 Microcontroller — Target device for development board
  • RP2354A Microcontroller — Complex board design

Lecture Notes

Week 13 lecture covering major announcements, week 12 review, system integration reminders, and wildcard week preview.

Theme of the Week

'Step away from the panic'

Major Announcements

  • Subject evaluation: Required for funding the class. Provides feedback to the institute about the class. Important for future students if you care about successors in the class.
  • Calendar alarm: Wildcard week and recitation on why make (almost) anything: impact. Friday is cutoff for assignments and orders (10s of dollars per person from inventory).
  • Final presentation/final exam: Combining multiple additive and subtractive processes (not just design a board and 3D print a case). Goal is system integration out of parts. Final exam criteria:
    • Did you integrate and design a complete system?
    • Can you demo a final project? Here is the cool thing I did and here is how it works.
    • Make a final project video! (helps but not required)
    Focus on well-integrated device!

Review of Week 12 User Interfaces

  • Claire Wang: Music play and Windows 3.1 interface works!
  • Ryan Hoffman: DRV8251A discussion, heat sinks, breakout boards. Wildcards with waterjetting, EDM, multi-axis machining, laser cutting metal. Class in the spring on nature of mathematical modeling.
  • Srikanth Nadhamuni: Background and experience to visiting fellow at MIT. Raspberry Pi W for WiFi, n8n for cloud LLM data crunching. Software: Node.js, MCP bridge server with n8n based on bridge connected to device (NGV tunnel). All set! Fantastic experience, haven't worked so hard in a very long time and learning a lot of new things. Hope to take forward and build other systems. The whole culture of doing and trying yourself fascinating, especially with failing a number of times until you figure it out. Maybe set one up at an IIT in India or AI centers of excellence with education ministry into the Indian education system (see fablabkerala.in or vigyam ashram).
  • Ray Song: Not here.
  • Tyler Jensen (Lincoln Lab, Group 81): Final project discussion (nylon printer). Week 13: Easy for web serial interface for XIAO! Web server to TFT (I think I forgot to load the camera pins with my code for it).
  • Aditi Ramakrishnan: Sloan MBA and strategy consulting background. Discrete time filter (FFT is blown) in skimage.filters — make a bandpass filter, then run a series of these filters, much less computing only adds and multiplies for filtering in realtime.
  • Alexandros Gravalos: Not here.
  • Edward Chen: Check final watch project by Gulati into watch form factor. Clear print on the Form Labs printer, 0.1. Kaman filter for sensor fusion (in the spring class). For position — LSM6DSV16X from input devices. Acceleration at 7 kHz (at audio frequency).

Show and Tell

  • Handle to sensor WiFi user interface
  • Plug to audio LLM user interface

System Integration Reminders

  • Mount electronics
  • Strain relief the final projects

Preview for Wildcard Week

Assignment: Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment.

Recitation Notes: Why Make (Almost) Anything

Recitation exploring the purpose, impact, and scaling of fabrication labs and making infrastructure.

Map of Fab Labs

Why Make a Fab Lab?

  • Used to create a community
  • Building things for the community
  • Sustainability
  • Prototyping quickly

How Impact?

  • How to make spaces: How to measure impact. What is important about fab:
    • Fablabs in cities vs rural areas: The ability to decide their own futures and change their lives fundamentally. 'Safecast revolutionized citizen science' e.g. radiation map.
    • Bringing back manufacturing: Reducing reliance on supply chains.
    • Rural sustainability: Working with indigenous communities on creating technologies themselves at scale and measure their usefulness and efficacy to preserve their ancestral knowledge:
      • How to establish labs there
      • How to make sure the labs get used
    • Hygiene technologies with Proctor and Gamble: Highly commercial. Lots of plastic waste. How can we change how they produce? How to make their products get there through resellers?
    • Trip to Peru and ran workshops, questionnaires, analysis: Collaboration developed into how to produce the products but also how to test their products to be market valuable e.g. mosquito repellents. Out of three plants, two worked better and one wasn't working at all (which is important to know!).

What Does It Mean to Design Infrastructure?

  • What did we want this lab to be able to do?
    • Workshops and questionnaires
    • How much you educate people based on the info they have with the issues the community is facing
    • Energy concerns to consider, some machines just drain the grid and can't be used. Solar powered, battery powered machines, reducing energy consumption of machines. Many concerns important.
  • Ethical questions
  • How to maintain resources

Case Study: Water Purifier Packets

Use them, change them, source them locally, ingredients found locally, how to distribute them globally.

Funding Models

First few fablabs were NSF funded. Now corporate CSR, regional funding, labor funding (10 different ways). Successful fablabs are heterogeneous with lots of ways of funding. The ones that fail usually just have one sponsor.

Example: DIY Raman spectrometer for water purification (even after purifications still have sulfates and improving that too).

What Does It Mean to Scale Infrastructure?

(Besides a lot of meetings!) What is a reasonable way to design a data collection process about what is needed and how to achieve it.

Back to the Map: Expansion

Timeline of development, cocreation, portable, skin analysis, water testing, biomaterial tech, microscopy.

Initial Results from Boston

How to Confront Local Impact
  • Collab with University of Hamburg. Motivation for how much food can be produced in Boston. Where food waste goes and what Boston produces locally. Make things for yourself locally.
  • Impact directly in the community you're living in.

Hatchspace

Focused on rehabilitation of addicts with woodworking. (Vermont is wood producing state).

Example Course Program

  • All-in session and systemic impact
  • Natural and cultural context
  • Skills and workshop
  • Economic vitality
  • Skills and workshop
  • Co-work session
  • Solutionspalooza

In the Course

Hands-on component (no physical robot exists that can do it) and community component is also important. Inclusion is important. Solving unconscious and institutional biases.

  • 'Fabrica! Lab' — Creating new laboratory spaces for female high school students, courses aimed for women in technology, online advising sessions for females interested in tech.
  • Makerspaces — Access to tools behind closed doors at universities, makes a huge difference for people who don't have the ability to prototype for themselves.
  • Materiom — Fablab affiliated project on organic waste for biomaterials.
  • Fablab León
  • Skylab workshop experiment — How to run a noodle shop out of a fablab (creating food from the community).
  • Academany — Global distributed campus for high school education. Fablab all-in (belonging, impact, community), fab futures (future vocational skills), bio academy (synthetic biology), fabricademy (textiles, fab, bio), fab academy (digital fab apps and implications).

Trade-off Between Impactful and Dangerous

People could be doing bad, but not because doing it with a group people with values.

Questions

Clarification: Adding infrastructure to existing fablab infrastructure to help support specific community needs (not specialized fab labs).

Foundations for Fab Futures

July 27-31, 2026 at Fab Boston 2026.

Useful Documentation

Essential resources for wildcard week digital fabrication processes and PCB design.

Class Page

Wildcard Week - MIT Academy

Comprehensive resource covering wildcard week assignment requirements and possibilities including grinding, multi-axis machining, electrical discharge machining, waterjet cutting, flatbed cutting, plasma cutting, laser metal cutting, laser micromachining, welding, molding and casting, folding, robotics, electronics, embedded programming, food, materials, biotechnology, textiles, and composites.

Key Topics

  • Machining: Grinding, multi-axis machining, electrical discharge machining, waterjet cutting, plasma cutting, laser metal cutting, laser micromachining
  • Molding & Casting: Vacuum forming, rotocasting
  • Folding: Mathematics, form and function, kirigami
  • Robotics: Arms, construction, soft actuation pneumatic inflatable
  • Electronics: Pick and place, programmable logic
  • Embedded Programming: Machine learning, machine vision
  • Textiles: Fiber processes, knitting, embroidery (PEmbroider, Ink/Stitch), Fabricademy
  • Composites: Various composite fabrication techniques

ATtiny1626 Development Board References

Embedded Programming Course Resources

Course resources for embedded programming with ATtiny412 microcontroller examples:

Embedded Programming - MIT Academy

ATtiny412 Echo Example Image

Individual Assignment: PCB Engraving with Fiber Laser

Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment. This assignment demonstrates PCB design and fabrication using a combination of CNC milling (Carvera) for edge cuts and hole machining, and fiber laser engraving (xTool F2 Ultra) for trace creation on copper-clad boards. The project includes designing and fabricating two development boards: a simple ATtiny1626 development board and a complex RP2354A development board.

PCB Engraving Process

This project explores PCB fabrication using fiber laser engraving, a process not covered in previous assignments. The workflow combines subtractive manufacturing techniques: CNC milling for mechanical features (edge cuts and holes) and laser engraving for electrical traces. This approach enables rapid prototyping of custom PCBs without requiring chemical etching or specialized PCB manufacturing facilities.

Tools and Equipment

  • Carvera (CNC Mill): Used for edge cuts and hole machining. The laser cannot effectively cut through the board material, so mechanical cutting is required for board outline and mounting holes.
  • Fiber Laser Cutter (xTool F2 Ultra): Used for PCB trace engraving. The laser removes copper from the board surface to create electrical traces and pads.
  • PCB Design Software (KiCad): Used for schematic capture, PCB layout, and design rule checking.

Boards Designed

  • Simple Board: ATtiny1626 development board with connectors, resistors, LED, and capacitor
  • Complex Board: RP2354A development board with more advanced routing and component placement

Board Design Considerations

  • Connector Placement: Top and bottom for connectors, right side for flashing. Connectors along edges to minimize form factor and maximize space usage.
  • Vertical Connectors: Used instead of horizontal connectors because horizontal connectors risk being snapped during use.
  • Black Area Avoidance: Avoid large black areas because laser does not work well with that (keep traces closer and further to minimize black areas). Note: Need to characterize maximum black until it burns the board because dumping too much heat in one place can damage the board.
  • Breadboard Compatibility: Put connectors on 100mil spacing grid size for breadboardability.
  • Pin Count Adjustment: Missed six pins in initial design, so switched from 6-pin headers to 9-pin (distributed six on top and bottom).
  • I2C Resistors: No SDA or SCL resistors included to keep flexibility for future use. May add spot for zero-ohm or pull-up resistor later but keeping it simple for now.
  • Mounting Holes: Added aligned mounting holes (M3 usually — for 3mm screws) for mechanical mounting.
  • Rounded Edge Cuts: Do 90 degrees, copy, drag, and complete the shape for rounded corners.

Design Rules

  • 0.1 mm spacing minimum
  • 0.15 mm trace width minimum
  • 0.15 mm clearance between plane and the rest

Ports and Pins

ATtiny1626 is an 8-bit microcontroller with 8 pins maximum per port. Each port has 8 pins maximum (some less). Need to specify port letter and pin number:

  • PA (0-7)
  • PB (0-7)
  • PC (0-7)

Postprocessing

  • For Carvera: Add new layer with just the holes in Photoshop (only holes for machining).
  • For Laser Engraving: Get rid of the holes for the F2 tools engraving in Inkscape (the frame and the board for alignment, then only engrave the board, not the edges).

Carvera Machining

Using mods → mill 2D PCB workflow:

  • 0.12mm cut depth and max depth

PCB Engraving Process

Using xTool F2 Ultra fiber laser:

  • Use tape for laser alignment
  • Run a test first on spare copper before the Carvera cut board to make sure focus is good (2.7mm thickness setting worked, board is actually 1.6-1.7mm thick)
  • Sand after engraving to clean up any residue
  • Worked with Bantam Tools FR1 (not random Amazon copper)
  • Perform short circuit test after engraving

Soldering

Using solder gun (heat gun) for component assembly.

Components

  • 1x 6-pin flipflop headers
  • 2x 9-pin flipflop headers
  • 1x 4.7k resistor
  • 1x 1k resistor
  • 1x LED
  • 1x 1uF or 10uF capacitor

Design Files

Download design files: ATtiny_QFN.zip and RP2354A-dev-v1.1.zip

Final ATtiny1626 development board design showing component placement and routing
ATtiny1626 final designComplete PCB layout with connectors, components, traces, and mounting holes optimized for laser engraving.
ATtiny1626 development board after fiber laser engraving showing copper traces
PCB after engravingCopper-clad board with traces engraved using fiber laser, ready for component soldering.
Fully assembled ATtiny1626 development board with all components soldered
Soldered boardComplete ATtiny1626 development board with headers, resistors, LED, and capacitor soldered in place.
Blinking LED demoVideo demonstration of the completed ATtiny1626 development board running a simple LED blink program, confirming successful fabrication and programming.
Close-up detail of PCB engraving showing trace quality and copper removal
PCB engraving detailClose-up view of fiber laser engraved traces showing clean copper removal and precise trace definition.

Interface with User

The application interfaces a user with input and/or output devices through the ATtiny1626 development board. The following table describes how the application interfaces with the user:

How It Interfaces with User Input Device(s) Output Device(s)
(a) LED Blink Demonstration None (programmed behavior) LED (visual feedback indicating board functionality)
(b) Future Interface Applications GPIO pins (PA, PB, PC ports) available for sensors, buttons, switches GPIO pins (PA, PB, PC ports) available for LEDs, displays, actuators

Group Assignment: Wildcard Week Digital Process

Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment. This group assignment explores various digital fabrication processes available during wildcard week.

Wildcard Week Possibilities

The wildcard week assignment allows exploration of digital fabrication processes not covered in previous weeks. Possibilities include (but are not limited to):

Machining

  • Grinding
  • Multi-axis machining
  • Electrical discharge machining (EDM)
  • Waterjet cutting
  • Flatbed cutting
  • Plasma cutting
  • Laser metal cutting
  • Laser micromachining

Welding

Various welding techniques for joining materials.

Molding and Casting

  • Vacuum forming
  • Rotocasting

Folding

  • Mathematics
  • Form and function
  • Kirigami

Robotics

  • Arms
  • Construction
  • Soft actuation pneumatic inflatable

Electronics

  • Pick and place
  • Programmable logic

Embedded Programming

  • Machine learning
  • Machine vision

Food

  • Printing
  • Gastronomy

Materials

  • Synthesis
  • Mechanical
  • Rheological

Biotechnology

  • DIYbio
  • iGEM
  • HTGAA
  • Bio Academy

Textiles

  • Fiber processes
  • Knitting
  • Embroidery (PEmbroider, Ink/Stitch)
  • Fabricademy

Composites

Various composite fabrication techniques.

Design Files

Design files for PCB engraving projects including ATtiny1626 and RP2354A development boards.

ATtiny1626 Development Board

Simple development board for ATtiny1626 microcontroller with connectors, resistors, LED, and capacitor. Designed for breadboard compatibility with 100mil spacing grid.

Initial ATtiny1626 development board design
Initial designFirst iteration of ATtiny1626 development board layout.
Final ATtiny1626 development board design with all components
Final designComplete ATtiny1626 development board with connectors, mounting holes, and optimized trace routing.

Download Design Files

  • ATtiny_QFN.zip — Complete KiCad project files for ATtiny1626 development board

RP2354A Development Board

Complex development board for RP2354A microcontroller with advanced routing and component placement.

RP2354A development board design
RP2354A board designComplete PCB layout for RP2354A development board with complex routing and component placement.

Download Design Files

Interface Design

The interface uses a mode-based navigation system where button presses trigger mode changes. A single press enters Camera mode, two presses enter Sensors mode, three presses return to Menu, and holding the button activates a flashlight function. The OLED display shows the current menu state and provides clear visual feedback for each mode transition. See Ethical AI Use: Menu System with Modes for AI-assisted development details.

OLED button user interface menu system displaying mode selection options
OLED button user interface menuMenu screen showing available modes: Camera, Sensors, and Menu navigation options with button press instructions.
Button UI demonstrationVideo showing button press interactions navigating through different modes on the OLED display.
First video stream on OLEDInitial camera feed streaming to OLED display using dithering algorithm for monochrome conversion, demonstrating real-time video output interface.
Download Design Files

Part (b): Real-Time Graphical User Interface through OLED and WiFi

A dual-interface health monitoring system that interfaces users with a MAX30102 pulse oximeter sensor through both an OLED display and a WiFi-enabled web interface. The system provides real-time visualization of heart rate (BPM), blood oxygen saturation (SpO2), and raw sensor data (IR and RED LED readings) through multiple output channels. Users can view data locally on the OLED display or remotely via a web browser accessing the ESP32-S3's built-in HTTP server. See Ethical AI Use: I2C Device Not Found for troubleshooting documentation.

Interface Design

The system provides dual-interface access: a local OLED display shows real-time sensor readings (IR, RED, BPM, SpO2) with visual heartbeat indicators, while a WiFi web interface provides comprehensive data visualization including numerical displays and real-time plotting charts. The web interface uses Chart.js for dynamic graph generation and automatically refreshes every 300ms to maintain real-time data updates. Both interfaces run simultaneously, enabling local monitoring and remote access.

Hello World on OLED

Initial OLED display test showing successful I2C communication and display initialization. See Ethical AI Use: Hello World Code for development details.

Hello World display on OLED for Invisible String project showing successful display initialization
Hello World on OLEDInitial OLED test confirming I2C communication and display functionality before implementing sensor interfaces.
Pulse Oximeter Readings on OLED

Real-time pulse oximeter data displayed on OLED showing IR and RED LED readings, heart rate (BPM), and blood oxygen saturation (SpO2) percentage. A heartbeat indicator flashes when a pulse is detected. See Ethical AI Use: MAX30102 Initialization Fix for sensor setup documentation.

Pulse oximeter readings on OLED displaying IR, RED, BPM, and SpO2 values
OLED sensor readings displayReal-time pulse oximeter data showing IR and RED LED values, heart rate (BPM), and blood oxygen saturation (SpO2) with heartbeat indicator.
BPM and SpO2 demonstrationVideo showing real-time heart rate and blood oxygen saturation measurements updating on OLED display with sensor interaction.
Pulse Oximeter Readings on WiFi GUI

WiFi web interface providing remote access to pulse oximeter data through a responsive HTML dashboard. The interface displays real-time numerical values for BPM, SpO2, IR, and RED readings with automatic data refresh. The web server runs on the ESP32-S3, allowing access from any device on the same WiFi network.

WiFi web interface displaying real-time pulse oximeter readings including BPM, SpO2, IR, and RED values
WiFi GUI readings dashboardRemote web interface showing real-time pulse oximeter data accessible from any device on the WiFi network, displaying BPM, SpO2, IR, and RED values with automatic updates.
Pulse Oximeter Plots on WiFi GUI

Enhanced WiFi web interface with real-time plotting capabilities using Chart.js library. The interface displays live line charts for BPM and SpO2 values, showing trends over time with automatic scrolling and data point management. This visualization enables users to observe patterns in heart rate and blood oxygen levels during monitoring sessions.

Serial monitor output showing sensor readings rising on touch interaction
Serial monitor sensor responseSerial output demonstrating sensor readings increase when finger is placed on MAX30102 sensor, showing IR and RED LED response to touch.
WiFi web interface with real-time plotting of BPM and SpO2 data using Chart.js
WiFi GUI with plotting chartsEnhanced web interface displaying real-time line charts for BPM and SpO2 values, showing trends over time with automatic data refresh and chart scrolling.

I2C Device Detection

Successful I2C device detection after fixing power isolation issues. The system now correctly identifies the OLED display at address 0x3C and the MAX30102 sensor at address 0x57. Initial troubleshooting required isolating the RD (red LED) and IRD (infrared LED) ground terminals from the general ground plane to prevent power issues and enable proper sensor operation. 

20:04:48.612 -> Scanning...
20:04:48.644 -> I2C device found at address 0x3C  !
20:04:48.644 -> I2C device found at address 0x57  !
20:04:48.644 -> done
Download Design Files

Part (c): Real-Time GUI through Mechanical Gripper and WiFi

A Wi-Fi-connected grip strength meter that interfaces a user with a mechanical hand gripper, an 80 kg load cell, and an HX711 amplifier. The ESP32-S3 continuously measures grip force, streams it to a web dashboard, and uses a published relationship between handgrip strength and age to display an estimated “physiological age” in real time. The design is inspired by the open-source grip strength meter from NeuroTech Hub at WashU and the associated PLOS ONE paper on grip strength and age trajectories (Syddall et al., 2014), adapted to my load cell and handle geometry.

Mechanically, a custom 3D-printed gripper clamps around a CZL601-type 80 kg bar load cell (sourced from Amazon 80 kg load cell). I imported a 100 kg load cell CAD from GrabCAD, checked the mounting dimensions against the CZL601AC datasheet (online, download), and confirmed that the hole spacing and footprint match the commercial part used here.

Mechanical Design and Fabrication

CAD model of the 3D-printed grip strength base and load cell mounting region
Grip strength base CADTop view of the grip strength base showing the bar load cell pocket, mounting bosses, and handle interface.
Side view CAD of the hand gripper and load cell assembly
Side view of gripper assemblySide profile showing how the fixed base, moving handle, and load cell align along the force axis of the bar sensor.
Full CAD view of the grip strength device with base and handle
Full grip strength assemblyComplete CAD of the base, handle, and load cell, sized for comfortable adult hand placement and full-finger contact.
Close-up of mounting holes and clearances around the load cell in CAD
Load cell mounting holesDetail of the M6 clearance and counterbore geometry used to capture the load cell without constraining bending.
Perspective CAD view of the gripper handle and base
Handle ergonomicsPerspective view of the curved handle designed to distribute pressure across the palm and fingers during maximal grip.
Photo of drilled clearance hole aligned to the printed pilot in the base
Clearance hole verificationPrinted pilot holes used as drill guides to match the metric mounting dimensions from the CZL601AC datasheet.
Photo of the fully printed grip strength device before drilling and assembly
Fresh off the printer3D-printed base and handle components in PLA prior to post-processing and hardware installation.
Printed part clamped for drilling load cell mounting holes
Workholding for accurate drillingThe printed base clamped to the drill press table so the pilot features guide the final clearance holes into the load cell.
Drilling practiceTraining cuts on scrap material to dial in drill press settings and avoid cracking the printed base during final holes.
Final load cell holesDrilling the final M6 clearance holes through the printed base, constrained by the pilot features to preserve alignment.

Electronics and Calibration

Electronics assembly with HX711 breakout, ESP32-S3, and load cell wiring
Electronics stack-upHX711 amplifier breakout from Amazon wired to the ESP32-S3 and 80 kg load cell with short, twisted signal pairs for noise reduction.
Fully assembled grip strength device with load cell, electronics, and handle
Assembled grip strength meterCompleted mechanical and electrical assembly ready for calibration and software bring-up.
Serial Plotter view of load cell readings increasing with grip force
Serial Plotter calibration tracesRaw HX711 output converted to kilograms and visualized in the Arduino Serial Plotter while applying known weights and grip forces.
Web GUI showing grip strength value, estimated age, and scrolling chart
Wi-Fi grip strength dashboardBrowser-based GUI with live grip strength (kg), estimated age, and a Chart.js time series plot of recent squeezes.

Model Used for Age Estimation

The age-estimation logic in the firmware is based on the non-linear, sex-specific grip-strength trajectories reported in Dodds et al., 2014 (PLOS ONE). As shown in Figure 1 of that paper, grip strength rises rapidly through adolescence, peaks around ages 30–40, and then declines non-linearly with age, with different magnitudes for males and females.

Reference grip strength trajectories over the life course from Dodds et al., PLOS ONE 2014
Reference trajectories (Figure 1)Age-dependent grip strength curves for males and females from Dodds et al., 2014, used as the qualitative target for the embedded model.
Simplified quadratic grip strength model fitted to reference data
Quadratic approximation (Table 2-inspired)Simplified male and female trajectories using peak strengths and curvatures chosen to approximate the summary values reported in Table 2 of Dodds et al., 2014.

To reproduce this shape efficiently on the ESP32, the firmware uses inverted quadratic approximations centered at age 35, consistent with the observed peak in the PLOS ONE data. In the forward direction, grip strength is approximated as:

Males: Grip(age) ≈ 52 − 0.0089·(age − 35)2
Females: Grip(age) ≈ 32 − 0.0059·(age − 35)2

On the device, this relationship is analytically inverted so that the measured grip strength can be mapped back to an estimated age:

age = 35 + √((a − Grip)/b), where a is the peak strength (52 kg for males, 32 kg for females) and b is the curvature (0.0089 for males, 0.0059 for females). The firmware clamps grip strength to physiologically meaningful ranges before applying this formula so the square root remains well-defined. 

float ageFromGripMale(float g) {
  float a = 52.0f, b = 0.0089f;
  if (g > a) g = a;
  if (g < 5) g = 5;
  return 35.0f + sqrtf((a - g) / b);
}

float ageFromGripFemale(float g) {
  float a = 32.0f, b = 0.0059f;
  if (g > a) g = a;
  if (g < 4) g = 4;
  return 35.0f + sqrtf((a - g) / b);
}

For full methodological details and original tables/figures, see the open-access paper: Dodds et al., 2014, PLOS ONE (download local PDF). The implementation here is an educational approximation and not intended for clinical or diagnostic use.

End-to-end live demoReal-time demonstration of squeezing the mechanical gripper and watching the Wi-Fi dashboard update grip strength and estimated age on a laptop.

Related Design, Code, and Calibration Resources

User Interface Comparison

Summary of how each interface application connects users with input and output devices.

Application How It Interfaces with the User Input Device(s) Output Device(s)
(a) Button User Interface Button press patterns (single, double, triple press, hold) provide mode selection input. OLED display shows current menu state and mode options. Users receive immediate visual feedback for each interaction. Button (GPIO pin 4) OLED Display (SSD1306, I²C 0x3C)
LED (GPIO pin 3, flashlight mode)
(b) Real-Time GUI (OLED & WiFi) Physical finger placement on MAX30102 sensor provides input. OLED displays real-time sensor data locally. WiFi web interface enables remote monitoring with numerical displays and live plotting charts accessible from any web browser. MAX30102 Pulse Oximeter Sensor (I²C 0x57) OLED Display (SSD1306, I²C 0x3C)
WiFi Web Interface (HTTP Server with Chart.js visualization)
(c) Grip Strength GUI (Load Cell & WiFi) Users squeeze a mechanical hand gripper that transfers force into an 80 kg bar load cell. The ESP32-S3 measures grip strength through the HX711 amplifier and streams results to a WiFi web dashboard that displays live grip force and an estimated physiological age in real time. Mechanical gripper linked to 80 kg load cell (CZL601-type)
HX711 load cell amplifier		 WiFi Web Interface (HTTP Server with Chart.js visualization)
Optional Serial Plotter (for calibration traces)

Group Assignment: Compare as Many Tool Options as Possible

Compare as many tool options as possible for interface and application programming.

General Comparison: Interface & Application Programming Tools

Comprehensive comparison of interface and application programming tools available for embedded systems and IoT development. This analysis covers tools from the MIT Academy Interface & Application Programming class page, evaluating their capabilities, use cases, and trade-offs for different application scenarios.

Embedded Display Interfaces

Tool/Framework Description Pros Cons Best For
OLED (SSD1306) Monochrome OLED displays via I²C Low power, high contrast, simple I²C interface, pixel-level control Limited resolution (128x64), monochrome only, small display size Status displays, sensor readouts, simple menus, embedded dashboards
LCD Character Displays Character-based LCD displays (16x2, 20x4) Simple API, readable in sunlight, low cost Limited to text/characters, no graphics, requires backlight power Text-only interfaces, status messages, debugging output
TFT Color Displays Full-color TFT LCD displays Color graphics, touch support, high resolution High power consumption, complex drivers, larger footprint Rich GUIs, image display, interactive touch interfaces

Web-Based Interfaces

Tool/Framework Description Pros Cons Best For
HTTP Server (ESP32) Built-in HTTP server on ESP32 for web interfaces Remote access, cross-platform (any browser), no app installation, real-time updates Requires WiFi, network dependency, limited to local network without port forwarding Remote monitoring, data visualization, control panels, sensor dashboards
WebSockets Real-time bidirectional communication Low latency, bidirectional, efficient for frequent updates More complex than HTTP, requires persistent connection Real-time streaming, interactive controls, live data feeds
Chart.js JavaScript charting library for web interfaces Beautiful charts, interactive, responsive, easy integration Requires JavaScript, CDN dependency or local hosting Data visualization, time series plots, sensor monitoring dashboards

Mobile & Native App Frameworks

Tool/Framework Description Pros Cons Best For
React Native Cross-platform mobile app framework Cross-platform (iOS/Android), native performance, large ecosystem Complex setup, requires mobile development knowledge Full-featured mobile apps, production deployments
Flutter Google's UI toolkit for cross-platform apps Single codebase, high performance, customizable UI Dart language, larger app size, learning curve Custom mobile interfaces, platform-specific designs
Progressive Web Apps (PWA) Web apps with native-like features No app store, cross-platform, offline capability Limited native API access, browser dependency Web-based mobile interfaces, simple deployment

Specific Comparison: Tools Used in Individual Assignment

Detailed comparison of the specific interface programming tools implemented in this week's individual assignment, evaluating their performance, ease of use, and suitability for embedded health monitoring applications.

OLED Display Interface (Adafruit SSD1306)

Aspect Evaluation
Ease of Implementation Simple I²C interface, well-documented Adafruit library, minimal wiring (SDA, SCL, power, ground)
Display Quality High contrast monochrome display, crisp text rendering, suitable for sensor data visualization
Power Consumption Very low power draw, ideal for battery-powered applications
Limitations 128x64 pixel resolution limits detail, monochrome only, small physical size (0.96" typical)
Best Use Cases Local sensor readouts, menu systems, status indicators, simple data displays

WiFi Web Interface (ESP32 HTTP Server + Chart.js)

Aspect Evaluation
Ease of Implementation ESP32 WebServer library provides straightforward HTTP server, Chart.js CDN integration requires minimal setup
Remote Access Accessible from any device on WiFi network (phone, tablet, computer), no app installation required
Visualization Capabilities Chart.js enables rich data visualization with real-time plotting, smooth animations, and interactive features
Real-Time Updates JSON API endpoint provides efficient data transfer, 300ms refresh rate maintains responsive feel
Limitations Requires WiFi network, limited to local network without additional configuration, power consumption higher than OLED alone
Best Use Cases Remote monitoring, data logging visualization, multi-user access, professional dashboards

Button Input Interface

Aspect Evaluation
Implementation Approach Digital GPIO reading with debouncing, press pattern detection (single/double/triple/hold) enables mode navigation
User Experience Intuitive press patterns, immediate visual feedback on OLED, no complex UI navigation required
Reliability Hardware debouncing with INPUT_PULLUP, timeout-based pattern recognition prevents accidental triggers
Limitations Limited to single button interaction, pattern learning required, less flexible than touchscreen interfaces
Best Use Cases Simple mode selection, menu navigation, embedded system controls, low-cost input solutions

Comparison Summary

The combination of OLED display and WiFi web interface provides complementary benefits: OLED offers immediate local feedback with minimal latency and power consumption, while the WiFi interface enables rich visualization and remote access. The button-based input provides an intuitive, low-cost navigation method suitable for embedded systems. Together, these tools create a robust interface system that supports both local and remote interaction with sensor data.

Design Files

Design files and code documentation for interface and application programming projects.

ESP32-S3 Development Board and Pinouts

Code files for ESP32-S3 development board interfaces including I2C scanning, OLED display control, and button-based user interface systems. See Week 4 documentation for board design and Week 8 documentation for pinout configurations.

I2C Scanner (i2cscan_generic.ino)

Utility code for scanning and detecting I2C devices on the bus, essential for troubleshooting connection issues.

How the Code Works (Pseudocode)
SETUP:
  Initialize I2C bus
  Initialize Serial communication
  Print "I2C Scanner" message

LOOP:
  Print "Scanning..." message
  Initialize device counter to 0
  
  FOR each address from 1 to 126:
    Begin I2C transmission to address
    Check transmission result
    
    IF transmission successful (error == 0):
      Print device found at address (hex format)
      Increment device counter
    ELSE IF unknown error (error == 4):
      Print unknown error at address
    
  IF no devices found:
    Print "No I2C devices found"
  ELSE:
    Print "done"
  
  Wait 5 seconds before next scan
Key Features
  • Scans all 127 possible I2C addresses (0x01-0x7E)
  • Detects and reports connected devices with hex address format
  • Handles multiple error conditions (device not found, unknown errors)
  • Continuous scanning mode with 5-second intervals
  • Compatible with any I2C bus configuration (Wire, Wire1, etc.)
What You Need to Know
  • I2C Address Range: Valid addresses are 0x08-0x77 (8-119 decimal); addresses 0x00-0x07 and 0x78-0x7F are reserved
  • Common Addresses: OLED displays typically use 0x3C or 0x3D; sensors vary (MAX30102 uses 0x57)
  • Troubleshooting: If no devices found, check wiring (SDA, SCL, power, ground), verify pull-up resistors, confirm device power
  • Usage: Run this before connecting other devices to verify I2C bus is working correctly
Download: i2cscan_generic.ino

Hello World OLED Display (hello_world.ino)

Basic OLED display test code that initializes the display and shows "Hello World" text, confirming I2C communication and display functionality.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial communication at 115200 baud
  Wait 500ms for Serial to stabilize
  
  Initialize I2C bus with SDA pin 5, SCL pin 6
  Print "Starting..." message
  
  Attempt to initialize OLED display:
    IF initialization fails:
      Print "OLED not found" error
      Enter infinite loop (halt)
  
  Clear display buffer
  Set text size to 2
  Set text color to white
  Set cursor position to (0, 20)
  Print "Hello" line
  Print "World!" line
  Update display (send buffer to hardware)

LOOP:
  Empty (runs once, then waits)
Key Features
  • Simple OLED initialization and text display
  • Custom I2C pin configuration for XIAO ESP32-S3 (SDA=5, SCL=6)
  • Error handling with infinite loop if display not found
  • Text size and cursor positioning for centered display
  • One-time display update (no loop refresh needed for static text)
What You Need to Know
  • I2C Pin Configuration: XIAO ESP32-S3 uses pins 5 (SDA) and 6 (SCL) by default; verify your board's pinout
  • Display Address: SSD1306 OLED typically uses address 0x3C; some variants use 0x3D
  • Display Update: Must call display.display() to send buffer to hardware; drawing functions only modify buffer
  • Testing: Use this as first test after connecting OLED to verify wiring and I2C communication before adding complex features
  • Libraries Required: Adafruit_GFX, Adafruit_SSD1306, Wire
Download: hello_world.ino

Button User Interface (outputs.ino)

Mode-based navigation system using button press patterns (single, double, triple, hold) to control multiple output devices including OLED display, camera, sensors, and LED flashlight.

How the Code Works (Pseudocode)
SETUP:
  Initialize OLED display
  Initialize camera module
  Initialize sensors (MPU6050, HX711)
  Initialize button pin (INPUT_PULLUP)
  Initialize LED pin (OUTPUT)
  Set current mode to MENU
  Display menu screen

LOOP:
  Read button state
  
  IF button pressed:
    Record press start time
    Start press detection timer
  
  IF button released:
    Calculate press duration
    IF duration > HOLD_THRESHOLD:
      Activate flashlight mode
    ELSE:
      Increment press count
      Reset press timeout timer
  
  IF press timeout exceeded:
    Process accumulated press count:
      IF press count == 1: Switch to CAMERA mode
      IF press count == 2: Switch to SENSORS mode
      IF press count == 3: Switch to MENU mode
    Reset press count
  
  IF current mode == MENU:
    Display menu screen (button instructions)
  
  IF current mode == CAMERA:
    Capture camera frame
    Process image with dithering algorithm
    Display on OLED
    Run Edge Impulse inference (optional)
    Overlay results on display
  
  IF current mode == SENSORS:
    Read accelerometer/gyroscope data
    Read load cell data
    Display sensor readings on OLED
  
  Update display
Key Features
  • Press pattern detection: single (1x), double (2x), triple (3x), and hold
  • Mode-based navigation system (Menu, Camera, Sensors)
  • Button debouncing with timeout-based pattern recognition
  • Floyd-Steinberg dithering for camera-to-OLED video display
  • Edge Impulse AI inference integration for face detection
  • Multi-sensor integration (MPU6050 accelerometer/gyro, HX711 load cell)
  • Flashlight mode activated by button hold
What You Need to Know
  • Button Wiring: Use INPUT_PULLUP mode (button connects pin to GND when pressed, internal pull-up to 3.3V)
  • Press Detection: Press count is accumulated until timeout (1 second); longer timeout allows slower multiple presses
  • Mode Switching: Each mode has distinct display update logic; ensure proper initialization in setup()
  • Camera Performance: Video streaming to OLED requires significant processing; frame rate depends on resolution and dithering complexity
  • Dependencies: Requires camera_pins.h header file with XIAO ESP32-S3 camera pin definitions; see Ethical AI Use for development details
  • Sensor Conflicts: Code uses preprocessor directives to resolve sensor_t type conflict between ESP32 camera and Adafruit MPU6050 libraries
Download: outputs.ino | camera_pins.h | outputs.zip (complete project)

Grip Strength Monitor (Load Cell + WiFi GUI)

Design files and firmware for a Wi-Fi-enabled grip strength meter built around an 80 kg bar load cell, HX711 amplifier, and ESP32-S3. The mechanical design was informed by the open-source grip strength meter from NeuroTech Hub and validated against the CZL601AC bar load cell datasheet (online, download).

Mechanical Design Files (3D-Printed Components)

  • Base.3mf — main chassis that captures the bar load cell and anchors the fixed side of the gripper.
  • Case.3mf — protective enclosure for the ESP32-S3 and HX711 amplifier with cable strain relief.
  • Handle.3mf — curved grip handle that transfers hand force into the free end of the load cell.
  • Calibration Print.3mf — small test piece used to verify hole diameters and load cell clearances before printing the full assembly.

All parts were printed in PLA with high infill in the load paths to minimize creep and flex during repeated maximal grip trials.

Basic HX711 Reader (loadcell_simple.ino)

Minimal firmware to bring up the HX711 amplifier and read calibrated weight values over Serial for debugging and calibration.

How the Code Works (Pseudocode)
SETUP:
  Configure HX711 data and clock pins (DT=A1, SCK=A0)
  Initialize Serial at 115200 baud
  Begin HX711 with DT/SCK pins
  Set calibration factor (grams per ADC unit)
  Tare the scale so current load is zero

LOOP (every 200 ms):
  If HX711 is ready:
    Read averaged weight using get_units(4)
    Print "weight:<value>" to Serial for Serial Plotter
  Else:
    Print "HX711 not ready" for troubleshooting
Key Features
  • Simple initialization of the HX711 on analog pins A0/A1.
  • Configurable calibration factor for mapping counts to grams or kilograms.
  • Timed reads (200 ms) to keep Serial output manageable and Plotter-friendly.
  • Graceful handling of HX711 not-ready states.
What You Need to Know
  • Use for initial bring-up: Run this first when wiring the HX711 and load cell to confirm clean, stable readings.
  • Calibration factor: Determined experimentally by hanging known weights and adjusting until readings match; see the calibration notes in Calibration Chat.
  • Serial Plotter: The weight:<value> format is convenient for quickly visualizing changes while squeezing the handle.
Download: loadcell_simple.ino

Serial Plotter-Friendly Reader (loadcell_plot.ino)

Refined HX711 reader tuned for the Arduino Serial Plotter: it outputs a single numeric value per line for clean plotting of grip strength over time.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial at 115200 baud
  Initialize HX711 on DT=A1, SCK=A0
  Set calibration factor
  Tare the scale
  Optionally print debug messages when DEBUG=1

LOOP (every 200 ms):
  If HX711 is ready:
    Read filtered weight with get_units(4)
    Optionally print labeled debug text
    Print only the numeric weight to Serial for the Plotter
  Else:
    Optionally print "not ready" debug text
    Print 0 so the plotted line continues gracefully
Key Features
  • DEBUG toggle: Compile-time switch to enable/disable human-readable logs without breaking the Serial Plotter format.
  • Clean “one number per line” output for multi-trial grip testing in the Serial Plotter.
  • Automatic zero output when the HX711 is not ready to keep the time axis continuous.
  • Shared pinout and calibration approach with loadcell_simple.ino for easy swapping.
What You Need to Know
  • Use this sketch to tune calibration and visualize grip curves without any GUI overhead.
  • When collecting data for analysis, keep DEBUG set to 0 so the output is a pure numeric stream.
  • The sample interval (200 ms) gives a smooth trace while keeping file sizes reasonable for multi-second squeezes.
Download: loadcell_plot.ino

WiFi Grip Strength GUI (loadcell_gui.ino)

Full application firmware that exposes grip strength and an estimated age over Wi-Fi using an HTTP server and a Chart.js web dashboard.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial
  Initialize HX711 (pins, calibration factor, tare)
  Connect ESP32-S3 to WiFi (MIT network in this build)
  Start WebServer on port 80
  Register handlers:
    "/"        → serve HTML+JS GUI page from PROGMEM
    "/metrics" → serve JSON with current grip and age

LOOP:
  Handle incoming HTTP clients
  Every 200 ms:
    If HX711 is ready:
      Read smoothed grip strength (kg) via get_units(3)
      Clamp negative values to zero
      Store in global gripStrength

AGE ESTIMATION HELPERS:
  ageFromGripMale(g):
    Clamp g to plausible range
    Compute age using inverted quadratic fit derived from normative data
  ageFromGripFemale(g):
    Same structure with female-specific parameters

HTTP /metrics ENDPOINT:
  Read "sex" query parameter (default "male")
  Compute ageEstimate = ageFromGripMale/ageFromGripFemale(gripStrength)
  Return JSON:
    {"grip": <kg>, "age": <years>}

CLIENT-SIDE GUI (HTML + JS):
  Render dark-themed dashboard with:
    - Sex toggle buttons (male/female)
    - Numeric grip strength (kg) and age
    - Scrolling Chart.js line plot of recent grip values
  Poll /metrics every 200 ms and update DOM + chart
Key Features
  • Embedded HTML/JS dashboard served directly from the ESP32-S3 using PROGMEM.
  • Real-time grip strength plot using Chart.js with ~120 recent samples.
  • Simple sex toggle that switches between male and female age-estimation curves.
  • JSON API at /metrics for future extensions (e.g., logging clients).
What You Need to Know
  • WiFi credentials: Update the ssid and password constants to match your network.
  • Normative model: The age equations are simplified fits inspired by the grip-strength trajectories reported in Syddall et al., PLOS ONE 2014 and are for educational visualization only, not clinical use.
  • Browser requirements: Any modern browser with JavaScript and network access can connect to the ESP32-S3’s IP address to view the dashboard.
  • Development log: The full iterative design of this sketch is captured in the ChatGPT transcript: Grip Strength Monitor Code Chat.
Download: loadcell_gui.ino

Invisible String Chain of Hearts

Code files for the Invisible String pulse oximeter interface system, providing real-time health monitoring through OLED display and WiFi web interface. See Week 11 PCB design documentation for hardware details.

OLED GUI for Pulse Oximeter (pulse_vo2_reads_fixing.ino)

Local OLED display interface showing real-time pulse oximeter readings including heart rate (BPM), blood oxygen saturation (SpO2), and raw IR/RED LED sensor values.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial communication
  Initialize I2C bus (SDA=5, SCL=6) at 400kHz
  Initialize MAX30102 sensor
  Configure sensor:
    Set LED mode to RED + IR
    Set ADC range to 16384
    Set sample rate to 100 Hz
    Set pulse width to 411 μs
    Set LED brightness to medium (0x3F)
  Initialize OLED display
  Clear and prepare display

LOOP:
  Read IR and RED LED values from sensor
  
  Heart Rate Detection:
    Check for heartbeat in IR signal using peak detection
    IF heartbeat detected:
      Calculate time since last beat
      Calculate BPM = 60 / (time_delta / 1000)
      Set beat flag for visual indicator
      Update last beat timestamp
  
  SpO2 Calculation (every 300ms):
    Add IR and RED values to circular buffer
    IF buffer has 50 samples:
      Calculate DC components (average)
      Calculate AC components (RMS)
      Calculate R ratio = (AC_RED/DC_RED) / (AC_IR/DC_IR)
      Estimate SpO2 = 110 - 25 * R
      Clamp SpO2 to 70-100% range
  
  Serial Output:
    Print IR, RED, BPM for Serial Plotter visualization
  
  OLED Display Update:
    Clear display buffer
    Display IR value (small text)
    Display RED value (small text)
    Display BPM value (large text, size 2)
    Display SpO2 percentage (small text)
    IF beat detected: Draw heartbeat indicator dot
    Update display hardware
  
  Delay 20ms (50 Hz update rate)
Key Features
  • Real-time heart rate detection using peak detection algorithm on IR signal
  • SpO2 calculation using ratio-of-ratios method with DC/AC component analysis
  • Circular buffer system for storing 50 samples of IR/RED data
  • Visual heartbeat indicator (flashing dot) when pulse detected
  • Dual output: OLED display and Serial Plotter for real-time waveform visualization
  • Optimized sensor configuration for reliable readings (100 Hz sample rate, medium brightness)
What You Need to Know
  • Sensor Placement: Finger must cover sensor completely; proper contact ensures accurate readings
  • I2C Address: MAX30102 uses address 0x57; verify with I2C scanner if sensor not detected
  • Ground Isolation: RD and IRD pins must be isolated from main ground plane to prevent power issues (see Week 11 PCB design)
  • SpO2 Accuracy: Calculation provides estimation; medical-grade accuracy requires calibration and FDA-approved algorithms
  • Buffer Size: 50-sample buffer provides balance between calculation accuracy and response time
  • Libraries Required: MAX30105 (SparkFun library), Adafruit_GFX, Adafruit_SSD1306, heartRate.h (beat detection)
  • Troubleshooting: If sensor not detected, check power isolation, I2C wiring, and sensor initialization order
Download: pulse_vo2_reads_fixing.ino

WiFi Readings GUI (pulse_gui.ino)

WiFi-enabled web interface providing remote access to pulse oximeter data through HTTP server with JSON API endpoint for real-time data updates.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial communication
  Initialize I2C bus
  Initialize MAX30102 sensor
  Configure sensor (LED mode, sample rate, pulse width)
  Initialize OLED display
  Initialize WiFi:
    Connect to network (SSID, password)
    Wait for connection
    Print IP address
  Initialize HTTP server:
    Route "/" → serve GUI HTML page
    Route "/gui" → serve GUI HTML page
    Route "/metrics" → serve JSON data
  Start web server

LOOP:
  Handle incoming HTTP client requests
  
  Read IR and RED values from sensor
  
  Heart Rate Calculation:
    Check for heartbeat in IR signal
    IF heartbeat detected:
      Calculate BPM from time delta
      Update global BPM variable
  
  SpO2 Calculation:
    Add IR/RED to circular buffer
    IF buffer full (50 samples):
      Calculate SpO2 using ratio-of-ratios
      Update global SpO2 variable
  
  Update global variables (g_ir, g_red, g_bpm, g_spo2)
  
  OLED Display Update:
    Display IR, RED, BPM, SpO2 values
    Update display hardware
Key Features
  • Dual interface: OLED display (local) and WiFi web interface (remote)
  • HTTP server with embedded HTML page stored in PROGMEM
  • JSON API endpoint (/metrics) for real-time data retrieval
  • Automatic WiFi connection with connection status feedback
  • IP address display for easy access
  • Simultaneous sensor reading and web server operation
  • Global variable system for data sharing between sensor reading and HTTP handlers
What You Need to Know
  • WiFi Configuration: Update SSID and password in code; for MIT network, use generated device password from wifi.mit.edu
  • Network Access: Web interface accessible only from devices on same WiFi network; IP address printed to Serial Monitor
  • HTML Storage: GUI HTML page stored in PROGMEM (program memory) to conserve RAM; use PROGMEM for large strings
  • Server Handling: Must call server.handleClient() frequently in loop() for responsive web interface
  • Data Refresh: Client-side JavaScript polls /metrics endpoint every 300ms for real-time updates
  • Power Consumption: WiFi significantly increases power draw compared to OLED-only mode; consider power management for battery operation
  • Libraries Required: WiFi, WebServer, MAX30105, Adafruit_SSD1306
Download: pulse_gui.ino

WiFi Plot GUI (pulse_gui_2.ino)

Enhanced WiFi web interface with real-time plotting capabilities using Chart.js library, displaying live line charts for BPM and SpO2 values with automatic scrolling and data management.

How the Code Works (Pseudocode)
SETUP:
  (Same as pulse_gui.ino)
  Initialize WiFi, sensor, OLED, HTTP server

LOOP:
  (Same as pulse_gui.ino)
  Handle HTTP requests, read sensor, calculate BPM/SpO2

GUI HTML PAGE (embedded in PROGMEM):
  Load Chart.js library from CDN
  Create two Chart.js line chart instances:
    - BPM chart (y-axis: 40-160 BPM)
    - SpO2 chart (y-axis: 70-100%)
  Initialize data arrays for each chart
  
  JavaScript Update Function (runs every 300ms):
    Fetch JSON data from /metrics endpoint
    Update numerical displays (BPM, SpO2, IR, RED)
    Add new BPM value to BPM data array
    Add new SpO2 value to SpO2 data array
    IF array length > maxPoints (100):
      Remove oldest value (shift)
    Update chart labels (array indices)
    Update chart datasets with new data
    Call chart.update() to refresh display
  
  Set interval to call update function every 300ms
Key Features
  • Real-time line chart visualization using Chart.js library
  • Dual chart display: BPM and SpO2 trends over time
  • Automatic data scrolling: maintains 100 most recent data points
  • Numerical displays alongside charts for precise values
  • Responsive design with dark theme for OLED-style aesthetic
  • Automatic chart scaling with fixed y-axis ranges for consistent visualization
  • CDN-based Chart.js loading for minimal memory footprint
What You Need to Know
  • Chart.js CDN: Library loaded from jsdelivr.net CDN; requires internet connection on client device
  • Data Management: Arrays limited to 100 points to prevent memory overflow; older data automatically discarded
  • Update Rate: 300ms refresh rate balances responsiveness with server load; adjust based on network conditions
  • Chart Configuration: Y-axis ranges fixed (BPM: 40-160, SpO2: 70-100) for consistent scaling; modify in JavaScript if needed
  • Browser Compatibility: Requires modern browser with JavaScript enabled; tested on Chrome, Firefox, Safari
  • Performance: Chart updates are lightweight; multiple simultaneous clients may impact ESP32 performance
  • Offline Operation: Charts won't load if client device lacks internet (Chart.js CDN unavailable); consider local hosting for offline use
Download: pulse_gui_2.ino

Reflections & Learnings

Key insights and learnings from working with interface and application programming.

Contributions

Acknowledgements and team roles for interface and application programming work.

Ethical AI Use

Transparent documentation of AI assistance used in this week's interface and application programming work.

This section documents all AI assistance used during Week 12 interface and application programming work. ChatGPT was used for code development, troubleshooting, and technical guidance. All transcripts are linked below for transparency.

Menu System with Modes

AI assistance for developing the button-based menu system with mode navigation (Menu, Camera, Sensors) using press pattern detection. The conversation covered button debouncing, press pattern recognition, mode state management, and OLED menu display design.

Related to: Part (a): Simple Button User Interface on OLED

View ChatGPT Transcript: Menu System with Modes

I2C Device Not Found

Troubleshooting session for I2C device detection issues with MAX30102 pulse oximeter sensor. The conversation addressed power isolation problems, I2C wiring verification, sensor initialization order, and ground plane isolation requirements for accurate sensor operation.

Related to: Part (b): Real-Time Graphical User Interface through OLED and WiFi

View ChatGPT Transcript: I2C Device Not Found

Hello World Code

Development assistance for creating the initial OLED "Hello World" test program. The conversation covered I2C initialization, OLED display library setup, text rendering, and basic display configuration for XIAO ESP32-S3 development board.

Related to: Part (b): Real-Time Graphical User Interface through OLED and WiFi (initial OLED test)

View ChatGPT Transcript: Hello World Code

MAX30102 Initialization Fix

Technical guidance for fixing MAX30102 pulse oximeter sensor initialization issues. The conversation addressed sensor configuration parameters, LED brightness settings, sample rate optimization, initialization sequence requirements, and troubleshooting sensor communication problems.

Related to: Part (b): Real-Time Graphical User Interface through OLED and WiFi (pulse oximeter readings)

View ChatGPT Transcript: MAX30102 Initialization Fix

Grip Strength Monitor Code Design

Code-focused assistance for designing and refining the WiFi grip strength monitor firmware. The conversation covered HX711 bring-up, load cell pin mapping, Serial Plotter debugging sketches, the ESP32-S3 HTTP server, the Chart.js dashboard, and the age-estimation helpers used in loadcell_simple.ino, loadcell_plot.ino, and loadcell_gui.ino.

Related to: Part (c): Real-Time GUI through Mechanical Gripper and WiFi and Grip Strength Monitor design files

View ChatGPT Transcript: Grip Strength Monitor Code

Grip Strength Calibration & Scaling

Calibration-focused assistance for mapping HX711 counts to kilograms and validating the grip strength readings. The discussion walked through using the Serial Plotter, collecting reference weights, tuning the calibration factor, and sanity-checking the age-estimation model derived from normative grip strength data.

Related to: Part (c): Real-Time GUI through Mechanical Gripper and WiFi calibration workflow and the Grip Strength Monitor sketches.

View ChatGPT Transcript: Grip Strength Calibration

Grip Strength Monitor – Cursor Transcript

Full Cursor AI transcript focused on organizing the grip strength monitor section: structuring Part (c), integrating design files, embedding images and videos, and aligning captions, external references, and the Ethical AI Use documentation for the load cell project.

Related to: Part (c): Real-Time GUI through Mechanical Gripper and WiFi, Grip Strength Monitor design files, and this Ethical AI Use section.

View HTML Transcript Download Markdown Transcript

Week 12 Project Documentation

Complete Cursor AI transcript for Week 12 interface and application programming project documentation. This comprehensive conversation covers the creation and population of the Week 12 HTML page, including Individual Assignment sections (button UI and WiFi GUI), Group Assignment tool comparisons, Design Files documentation with pseudocode, and Ethical AI Use section organization. The transcript demonstrates the collaborative process of building professional documentation with structured content, embedded media, and comprehensive code documentation.

Related to: Complete Week 12 documentation including Individual Assignment, Group Assignment, Design Files, and overall page structure

View HTML Transcript Download Markdown Transcript

Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License

``` Updating the todo list and checking for linting errors: Checking remaining week12 references to see if they need removal: Checking what remains around the old content: Checking both Design Files sections to determine what to keep: Removing the duplicate old Design Files section. Finding where it ends: Removing the old Design Files section. Finding a unique boundary string: Removing the duplicate old Design Files section: ```html Week 13 · Wildcard Week
← Back to Home
[Profile Image Placeholder]

Week 13

Wildcard Week

Week Highlights

Key captures from the PCB engraving assignment with links to their sections.

ATtiny1626 Board Design

Final ATtiny1626 development board design with connectors and mounting holes

PCB Engraving

ATtiny1626 development board after fiber laser engraving

Soldered Board

Fully assembled ATtiny1626 development board with all components soldered

Blinking LED Demo

RP2354A Board Design

RP2354A development board design

PCB Engraving Detail

Close-up detail of PCB engraving showing trace quality

Table of Contents

Course Content

Training & Documentation

Assignments & Projects

Wildcard Week

This week focuses on exploring digital fabrication processes not covered in previous assignments. We'll design and produce something using computer-aided design and manufacturing, documenting requirements and including everything necessary for reproduction. This week also includes reflection on the impact and purpose of making (almost) anything.

Exploring new digital fabrication processes
Designing and producing with CAD/CAM
Understanding the impact and purpose of fabrication labs

This Week's Goals

  • Explore New Processes
    Design and produce something with a digital process not covered in other assignments
  • Complete Documentation
    Document requirements and include everything necessary to reproduce the project
  • Reflect on Impact
    Understand the purpose and impact of fabrication labs and making

Assignments

  • Group Assignment
    Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment
  • Individual Assignment
    Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment, documenting the requirements that your assignment meets, and including everything necessary to reproduce it

Tools & Materials

  • Carvera (CNC Mill) — Edge cuts and hole machining
  • Fiber Laser Cutter (xTool F2 Ultra) — PCB engraving
  • PCB Design Software (KiCad) — Board layout and design
  • ATtiny1626 Microcontroller — Target device for development board
  • RP2354A Microcontroller — Complex board design

Lecture Notes

Week 13 lecture covering major announcements, week 12 review, system integration reminders, and wildcard week preview.

Theme of the Week

'Step away from the panic'

Major Announcements

  • Subject evaluation: Required for funding the class. Provides feedback to the institute about the class. Important for future students if you care about successors in the class.
  • Calendar alarm: Wildcard week and recitation on why make (almost) anything: impact. Friday is cutoff for assignments and orders (10s of dollars per person from inventory).
  • Final presentation/final exam: Combining multiple additive and subtractive processes (not just design a board and 3D print a case). Goal is system integration out of parts. Final exam criteria:
    • Did you integrate and design a complete system?
    • Can you demo a final project? Here is the cool thing I did and here is how it works.
    • Make a final project video! (helps but not required)
    Focus on well-integrated device!

Review of Week 12 User Interfaces

  • Claire Wang: Music play and Windows 3.1 interface works!
  • Ryan Hoffman: DRV8251A discussion, heat sinks, breakout boards. Wildcards with waterjetting, EDM, multi-axis machining, laser cutting metal. Class in the spring on nature of mathematical modeling.
  • Srikanth Nadhamuni: Background and experience to visiting fellow at MIT. Raspberry Pi W for WiFi, n8n for cloud LLM data crunching. Software: Node.js, MCP bridge server with n8n based on bridge connected to device (NGV tunnel). All set! Fantastic experience, haven't worked so hard in a very long time and learning a lot of new things. Hope to take forward and build other systems. The whole culture of doing and trying yourself fascinating, especially with failing a number of times until you figure it out. Maybe set one up at an IIT in India or AI centers of excellence with education ministry into the Indian education system (see fablabkerala.in or vigyam ashram).
  • Ray Song: Not here.
  • Tyler Jensen (Lincoln Lab, Group 81): Final project discussion (nylon printer). Week 13: Easy for web serial interface for XIAO! Web server to TFT (I think I forgot to load the camera pins with my code for it).
  • Aditi Ramakrishnan: Sloan MBA and strategy consulting background. Discrete time filter (FFT is blown) in skimage.filters — make a bandpass filter, then run a series of these filters, much less computing only adds and multiplies for filtering in realtime.
  • Alexandros Gravalos: Not here.
  • Edward Chen: Check final watch project by Gulati into watch form factor. Clear print on the Form Labs printer, 0.1. Kaman filter for sensor fusion (in the spring class). For position — LSM6DSV16X from input devices. Acceleration at 7 kHz (at audio frequency).

Show and Tell

  • Handle to sensor WiFi user interface
  • Plug to audio LLM user interface

System Integration Reminders

  • Mount electronics
  • Strain relief the final projects

Preview for Wildcard Week

Assignment: Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment.

Recitation Notes: Why Make (Almost) Anything

Recitation exploring the purpose, impact, and scaling of fabrication labs and making infrastructure.

Map of Fab Labs

Why Make a Fab Lab?

  • Used to create a community
  • Building things for the community
  • Sustainability
  • Prototyping quickly

How Impact?

  • How to make spaces: How to measure impact. What is important about fab:
    • Fablabs in cities vs rural areas: The ability to decide their own futures and change their lives fundamentally. 'Safecast revolutionized citizen science' e.g. radiation map.
    • Bringing back manufacturing: Reducing reliance on supply chains.
    • Rural sustainability: Working with indigenous communities on creating technologies themselves at scale and measure their usefulness and efficacy to preserve their ancestral knowledge:
      • How to establish labs there
      • How to make sure the labs get used
    • Hygiene technologies with Proctor and Gamble: Highly commercial. Lots of plastic waste. How can we change how they produce? How to make their products get there through resellers?
    • Trip to Peru and ran workshops, questionnaires, analysis: Collaboration developed into how to produce the products but also how to test their products to be market valuable e.g. mosquito repellents. Out of three plants, two worked better and one wasn't working at all (which is important to know!).

What Does It Mean to Design Infrastructure?

  • What did we want this lab to be able to do?
    • Workshops and questionnaires
    • How much you educate people based on the info they have with the issues the community is facing
    • Energy concerns to consider, some machines just drain the grid and can't be used. Solar powered, battery powered machines, reducing energy consumption of machines. Many concerns important.
  • Ethical questions
  • How to maintain resources

Case Study: Water Purifier Packets

Use them, change them, source them locally, ingredients found locally, how to distribute them globally.

Funding Models

First few fablabs were NSF funded. Now corporate CSR, regional funding, labor funding (10 different ways). Successful fablabs are heterogeneous with lots of ways of funding. The ones that fail usually just have one sponsor.

Example: DIY Raman spectrometer for water purification (even after purifications still have sulfates and improving that too).

What Does It Mean to Scale Infrastructure?

(Besides a lot of meetings!) What is a reasonable way to design a data collection process about what is needed and how to achieve it.

Back to the Map: Expansion

Timeline of development, cocreation, portable, skin analysis, water testing, biomaterial tech, microscopy.

Initial Results from Boston

How to Confront Local Impact
  • Collab with University of Hamburg. Motivation for how much food can be produced in Boston. Where food waste goes and what Boston produces locally. Make things for yourself locally.
  • Impact directly in the community you're living in.

Hatchspace

Focused on rehabilitation of addicts with woodworking. (Vermont is wood producing state).

Example Course Program

  • All-in session and systemic impact
  • Natural and cultural context
  • Skills and workshop
  • Economic vitality
  • Skills and workshop
  • Co-work session
  • Solutionspalooza

In the Course

Hands-on component (no physical robot exists that can do it) and community component is also important. Inclusion is important. Solving unconscious and institutional biases.

  • 'Fabrica! Lab' — Creating new laboratory spaces for female high school students, courses aimed for women in technology, online advising sessions for females interested in tech.
  • Makerspaces — Access to tools behind closed doors at universities, makes a huge difference for people who don't have the ability to prototype for themselves.
  • Materiom — Fablab affiliated project on organic waste for biomaterials.
  • Fablab León
  • Skylab workshop experiment — How to run a noodle shop out of a fablab (creating food from the community).
  • Academany — Global distributed campus for high school education. Fablab all-in (belonging, impact, community), fab futures (future vocational skills), bio academy (synthetic biology), fabricademy (textiles, fab, bio), fab academy (digital fab apps and implications).

Trade-off Between Impactful and Dangerous

People could be doing bad, but not because doing it with a group people with values.

Questions

Clarification: Adding infrastructure to existing fablab infrastructure to help support specific community needs (not specialized fab labs).

Foundations for Fab Futures

July 27-31, 2026 at Fab Boston 2026.

Useful Documentation

Essential resources for wildcard week digital fabrication processes and PCB design.

Class Page

Wildcard Week - MIT Academy

Comprehensive resource covering wildcard week assignment requirements and possibilities including grinding, multi-axis machining, electrical discharge machining, waterjet cutting, flatbed cutting, plasma cutting, laser metal cutting, laser micromachining, welding, molding and casting, folding, robotics, electronics, embedded programming, food, materials, biotechnology, textiles, and composites.

Key Topics

  • Machining: Grinding, multi-axis machining, electrical discharge machining, waterjet cutting, plasma cutting, laser metal cutting, laser micromachining
  • Molding & Casting: Vacuum forming, rotocasting
  • Folding: Mathematics, form and function, kirigami
  • Robotics: Arms, construction, soft actuation pneumatic inflatable
  • Electronics: Pick and place, programmable logic
  • Embedded Programming: Machine learning, machine vision
  • Textiles: Fiber processes, knitting, embroidery (PEmbroider, Ink/Stitch), Fabricademy
  • Composites: Various composite fabrication techniques

ATtiny1626 Development Board References

Embedded Programming Course Resources

Course resources for embedded programming with ATtiny412 microcontroller examples:

Embedded Programming - MIT Academy

ATtiny412 Echo Example Image

Individual Assignment: PCB Engraving with Fiber Laser

Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment. This assignment demonstrates PCB design and fabrication using a combination of CNC milling (Carvera) for edge cuts and hole machining, and fiber laser engraving (xTool F2 Ultra) for trace creation on copper-clad boards. The project includes designing and fabricating two development boards: a simple ATtiny1626 development board and a complex RP2354A development board.

PCB Engraving Process

This project explores PCB fabrication using fiber laser engraving, a process not covered in previous assignments. The workflow combines subtractive manufacturing techniques: CNC milling for mechanical features (edge cuts and holes) and laser engraving for electrical traces. This approach enables rapid prototyping of custom PCBs without requiring chemical etching or specialized PCB manufacturing facilities.

Tools and Equipment

  • Carvera (CNC Mill): Used for edge cuts and hole machining. The laser cannot effectively cut through the board material, so mechanical cutting is required for board outline and mounting holes.
  • Fiber Laser Cutter (xTool F2 Ultra): Used for PCB trace engraving. The laser removes copper from the board surface to create electrical traces and pads.
  • PCB Design Software (KiCad): Used for schematic capture, PCB layout, and design rule checking.

Boards Designed

  • Simple Board: ATtiny1626 development board with connectors, resistors, LED, and capacitor
  • Complex Board: RP2354A development board with more advanced routing and component placement

Board Design Considerations

  • Connector Placement: Top and bottom for connectors, right side for flashing. Connectors along edges to minimize form factor and maximize space usage.
  • Vertical Connectors: Used instead of horizontal connectors because horizontal connectors risk being snapped during use.
  • Black Area Avoidance: Avoid large black areas because laser does not work well with that (keep traces closer and further to minimize black areas). Note: Need to characterize maximum black until it burns the board because dumping too much heat in one place can damage the board.
  • Breadboard Compatibility: Put connectors on 100mil spacing grid size for breadboardability.
  • Pin Count Adjustment: Missed six pins in initial design, so switched from 6-pin headers to 9-pin (distributed six on top and bottom).
  • I2C Resistors: No SDA or SCL resistors included to keep flexibility for future use. May add spot for zero-ohm or pull-up resistor later but keeping it simple for now.
  • Mounting Holes: Added aligned mounting holes (M3 usually — for 3mm screws) for mechanical mounting.
  • Rounded Edge Cuts: Do 90 degrees, copy, drag, and complete the shape for rounded corners.

Design Rules

  • 0.1 mm spacing minimum
  • 0.15 mm trace width minimum
  • 0.15 mm clearance between plane and the rest

Ports and Pins

ATtiny1626 is an 8-bit microcontroller with 8 pins maximum per port. Each port has 8 pins maximum (some less). Need to specify port letter and pin number:

  • PA (0-7)
  • PB (0-7)
  • PC (0-7)

Postprocessing

  • For Carvera: Add new layer with just the holes in Photoshop (only holes for machining).
  • For Laser Engraving: Get rid of the holes for the F2 tools engraving in Inkscape (the frame and the board for alignment, then only engrave the board, not the edges).

Carvera Machining

Using mods → mill 2D PCB workflow:

  • 0.12mm cut depth and max depth

PCB Engraving Process

Using xTool F2 Ultra fiber laser:

  • Use tape for laser alignment
  • Run a test first on spare copper before the Carvera cut board to make sure focus is good (2.7mm thickness setting worked, board is actually 1.6-1.7mm thick)
  • Sand after engraving to clean up any residue
  • Worked with Bantam Tools FR1 (not random Amazon copper)
  • Perform short circuit test after engraving

Soldering

Using solder gun (heat gun) for component assembly.

Components

  • 1x 6-pin flipflop headers
  • 2x 9-pin flipflop headers
  • 1x 4.7k resistor
  • 1x 1k resistor
  • 1x LED
  • 1x 1uF or 10uF capacitor

Design Files

Download design files: ATtiny_QFN.zip and RP2354A-dev-v1.1.zip

Final ATtiny1626 development board design showing component placement and routing
ATtiny1626 final designComplete PCB layout with connectors, components, traces, and mounting holes optimized for laser engraving.
ATtiny1626 development board after fiber laser engraving showing copper traces
PCB after engravingCopper-clad board with traces engraved using fiber laser, ready for component soldering.
Fully assembled ATtiny1626 development board with all components soldered
Soldered boardComplete ATtiny1626 development board with headers, resistors, LED, and capacitor soldered in place.
Blinking LED demoVideo demonstration of the completed ATtiny1626 development board running a simple LED blink program, confirming successful fabrication and programming.
Close-up detail of PCB engraving showing trace quality and copper removal
PCB engraving detailClose-up view of fiber laser engraved traces showing clean copper removal and precise trace definition.

Interface with User

The application interfaces a user with input and/or output devices through the ATtiny1626 development board. The following table describes how the application interfaces with the user:

How It Interfaces with User Input Device(s) Output Device(s)
(a) LED Blink Demonstration None (programmed behavior) LED (visual feedback indicating board functionality)
(b) Future Interface Applications GPIO pins (PA, PB, PC ports) available for sensors, buttons, switches GPIO pins (PA, PB, PC ports) available for LEDs, displays, actuators

Group Assignment: Wildcard Week Digital Process

Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment. This group assignment explores various digital fabrication processes available during wildcard week.

Wildcard Week Possibilities

The wildcard week assignment allows exploration of digital fabrication processes not covered in previous weeks. Possibilities include (but are not limited to):

Machining

  • Grinding
  • Multi-axis machining
  • Electrical discharge machining (EDM)
  • Waterjet cutting
  • Flatbed cutting
  • Plasma cutting
  • Laser metal cutting
  • Laser micromachining

Welding

Various welding techniques for joining materials.

Molding and Casting

  • Vacuum forming
  • Rotocasting

Folding

  • Mathematics
  • Form and function
  • Kirigami

Robotics

  • Arms
  • Construction
  • Soft actuation pneumatic inflatable

Electronics

  • Pick and place
  • Programmable logic

Embedded Programming

  • Machine learning
  • Machine vision

Food

  • Printing
  • Gastronomy

Materials

  • Synthesis
  • Mechanical
  • Rheological

Biotechnology

  • DIYbio
  • iGEM
  • HTGAA
  • Bio Academy

Textiles

  • Fiber processes
  • Knitting
  • Embroidery (PEmbroider, Ink/Stitch)
  • Fabricademy

Composites

Various composite fabrication techniques.

Design Files

Design files for PCB engraving projects including ATtiny1626 and RP2354A development boards.

ATtiny1626 Development Board

Simple development board for ATtiny1626 microcontroller with connectors, resistors, LED, and capacitor. Designed for breadboard compatibility with 100mil spacing grid.

Initial ATtiny1626 development board design
Initial designFirst iteration of ATtiny1626 development board layout.
Final ATtiny1626 development board design with all components
Final designComplete ATtiny1626 development board with connectors, mounting holes, and optimized trace routing.

Download Design Files

  • ATtiny_QFN.zip — Complete KiCad project files for ATtiny1626 development board

RP2354A Development Board

Complex development board for RP2354A microcontroller with advanced routing and component placement.

RP2354A development board design
RP2354A board designComplete PCB layout for RP2354A development board with complex routing and component placement.

Download Design Files

Interface Design

The interface uses a mode-based navigation system where button presses trigger mode changes. A single press enters Camera mode, two presses enter Sensors mode, three presses return to Menu, and holding the button activates a flashlight function. The OLED display shows the current menu state and provides clear visual feedback for each mode transition. See Ethical AI Use: Menu System with Modes for AI-assisted development details.

OLED button user interface menu system displaying mode selection options
OLED button user interface menuMenu screen showing available modes: Camera, Sensors, and Menu navigation options with button press instructions.
Button UI demonstrationVideo showing button press interactions navigating through different modes on the OLED display.
First video stream on OLEDInitial camera feed streaming to OLED display using dithering algorithm for monochrome conversion, demonstrating real-time video output interface.
Download Design Files

Part (b): Real-Time Graphical User Interface through OLED and WiFi

A dual-interface health monitoring system that interfaces users with a MAX30102 pulse oximeter sensor through both an OLED display and a WiFi-enabled web interface. The system provides real-time visualization of heart rate (BPM), blood oxygen saturation (SpO2), and raw sensor data (IR and RED LED readings) through multiple output channels. Users can view data locally on the OLED display or remotely via a web browser accessing the ESP32-S3's built-in HTTP server. See Ethical AI Use: I2C Device Not Found for troubleshooting documentation.

Interface Design

The system provides dual-interface access: a local OLED display shows real-time sensor readings (IR, RED, BPM, SpO2) with visual heartbeat indicators, while a WiFi web interface provides comprehensive data visualization including numerical displays and real-time plotting charts. The web interface uses Chart.js for dynamic graph generation and automatically refreshes every 300ms to maintain real-time data updates. Both interfaces run simultaneously, enabling local monitoring and remote access.

Hello World on OLED

Initial OLED display test showing successful I2C communication and display initialization. See Ethical AI Use: Hello World Code for development details.

Hello World display on OLED for Invisible String project showing successful display initialization
Hello World on OLEDInitial OLED test confirming I2C communication and display functionality before implementing sensor interfaces.
Pulse Oximeter Readings on OLED

Real-time pulse oximeter data displayed on OLED showing IR and RED LED readings, heart rate (BPM), and blood oxygen saturation (SpO2) percentage. A heartbeat indicator flashes when a pulse is detected. See Ethical AI Use: MAX30102 Initialization Fix for sensor setup documentation.

Pulse oximeter readings on OLED displaying IR, RED, BPM, and SpO2 values
OLED sensor readings displayReal-time pulse oximeter data showing IR and RED LED values, heart rate (BPM), and blood oxygen saturation (SpO2) with heartbeat indicator.
BPM and SpO2 demonstrationVideo showing real-time heart rate and blood oxygen saturation measurements updating on OLED display with sensor interaction.
Pulse Oximeter Readings on WiFi GUI

WiFi web interface providing remote access to pulse oximeter data through a responsive HTML dashboard. The interface displays real-time numerical values for BPM, SpO2, IR, and RED readings with automatic data refresh. The web server runs on the ESP32-S3, allowing access from any device on the same WiFi network.

WiFi web interface displaying real-time pulse oximeter readings including BPM, SpO2, IR, and RED values
WiFi GUI readings dashboardRemote web interface showing real-time pulse oximeter data accessible from any device on the WiFi network, displaying BPM, SpO2, IR, and RED values with automatic updates.
Pulse Oximeter Plots on WiFi GUI

Enhanced WiFi web interface with real-time plotting capabilities using Chart.js library. The interface displays live line charts for BPM and SpO2 values, showing trends over time with automatic scrolling and data point management. This visualization enables users to observe patterns in heart rate and blood oxygen levels during monitoring sessions.

Serial monitor output showing sensor readings rising on touch interaction
Serial monitor sensor responseSerial output demonstrating sensor readings increase when finger is placed on MAX30102 sensor, showing IR and RED LED response to touch.
WiFi web interface with real-time plotting of BPM and SpO2 data using Chart.js
WiFi GUI with plotting chartsEnhanced web interface displaying real-time line charts for BPM and SpO2 values, showing trends over time with automatic data refresh and chart scrolling.

I2C Device Detection

Successful I2C device detection after fixing power isolation issues. The system now correctly identifies the OLED display at address 0x3C and the MAX30102 sensor at address 0x57. Initial troubleshooting required isolating the RD (red LED) and IRD (infrared LED) ground terminals from the general ground plane to prevent power issues and enable proper sensor operation. 

20:04:48.612 -> Scanning...
20:04:48.644 -> I2C device found at address 0x3C  !
20:04:48.644 -> I2C device found at address 0x57  !
20:04:48.644 -> done
Download Design Files

Part (c): Real-Time GUI through Mechanical Gripper and WiFi

A Wi-Fi-connected grip strength meter that interfaces a user with a mechanical hand gripper, an 80 kg load cell, and an HX711 amplifier. The ESP32-S3 continuously measures grip force, streams it to a web dashboard, and uses a published relationship between handgrip strength and age to display an estimated “physiological age” in real time. The design is inspired by the open-source grip strength meter from NeuroTech Hub at WashU and the associated PLOS ONE paper on grip strength and age trajectories (Syddall et al., 2014), adapted to my load cell and handle geometry.

Mechanically, a custom 3D-printed gripper clamps around a CZL601-type 80 kg bar load cell (sourced from Amazon 80 kg load cell). I imported a 100 kg load cell CAD from GrabCAD, checked the mounting dimensions against the CZL601AC datasheet (online, download), and confirmed that the hole spacing and footprint match the commercial part used here.

Mechanical Design and Fabrication

CAD model of the 3D-printed grip strength base and load cell mounting region
Grip strength base CADTop view of the grip strength base showing the bar load cell pocket, mounting bosses, and handle interface.
Side view CAD of the hand gripper and load cell assembly
Side view of gripper assemblySide profile showing how the fixed base, moving handle, and load cell align along the force axis of the bar sensor.
Full CAD view of the grip strength device with base and handle
Full grip strength assemblyComplete CAD of the base, handle, and load cell, sized for comfortable adult hand placement and full-finger contact.
Close-up of mounting holes and clearances around the load cell in CAD
Load cell mounting holesDetail of the M6 clearance and counterbore geometry used to capture the load cell without constraining bending.
Perspective CAD view of the gripper handle and base
Handle ergonomicsPerspective view of the curved handle designed to distribute pressure across the palm and fingers during maximal grip.
Photo of drilled clearance hole aligned to the printed pilot in the base
Clearance hole verificationPrinted pilot holes used as drill guides to match the metric mounting dimensions from the CZL601AC datasheet.
Photo of the fully printed grip strength device before drilling and assembly
Fresh off the printer3D-printed base and handle components in PLA prior to post-processing and hardware installation.
Printed part clamped for drilling load cell mounting holes
Workholding for accurate drillingThe printed base clamped to the drill press table so the pilot features guide the final clearance holes into the load cell.
Drilling practiceTraining cuts on scrap material to dial in drill press settings and avoid cracking the printed base during final holes.
Final load cell holesDrilling the final M6 clearance holes through the printed base, constrained by the pilot features to preserve alignment.

Electronics and Calibration

Electronics assembly with HX711 breakout, ESP32-S3, and load cell wiring
Electronics stack-upHX711 amplifier breakout from Amazon wired to the ESP32-S3 and 80 kg load cell with short, twisted signal pairs for noise reduction.
Fully assembled grip strength device with load cell, electronics, and handle
Assembled grip strength meterCompleted mechanical and electrical assembly ready for calibration and software bring-up.
Serial Plotter view of load cell readings increasing with grip force
Serial Plotter calibration tracesRaw HX711 output converted to kilograms and visualized in the Arduino Serial Plotter while applying known weights and grip forces.
Web GUI showing grip strength value, estimated age, and scrolling chart
Wi-Fi grip strength dashboardBrowser-based GUI with live grip strength (kg), estimated age, and a Chart.js time series plot of recent squeezes.

Model Used for Age Estimation

The age-estimation logic in the firmware is based on the non-linear, sex-specific grip-strength trajectories reported in Dodds et al., 2014 (PLOS ONE). As shown in Figure 1 of that paper, grip strength rises rapidly through adolescence, peaks around ages 30–40, and then declines non-linearly with age, with different magnitudes for males and females.

Reference grip strength trajectories over the life course from Dodds et al., PLOS ONE 2014
Reference trajectories (Figure 1)Age-dependent grip strength curves for males and females from Dodds et al., 2014, used as the qualitative target for the embedded model.
Simplified quadratic grip strength model fitted to reference data
Quadratic approximation (Table 2-inspired)Simplified male and female trajectories using peak strengths and curvatures chosen to approximate the summary values reported in Table 2 of Dodds et al., 2014.

To reproduce this shape efficiently on the ESP32, the firmware uses inverted quadratic approximations centered at age 35, consistent with the observed peak in the PLOS ONE data. In the forward direction, grip strength is approximated as:

Males: Grip(age) ≈ 52 − 0.0089·(age − 35)2
Females: Grip(age) ≈ 32 − 0.0059·(age − 35)2

On the device, this relationship is analytically inverted so that the measured grip strength can be mapped back to an estimated age:

age = 35 + √((a − Grip)/b), where a is the peak strength (52 kg for males, 32 kg for females) and b is the curvature (0.0089 for males, 0.0059 for females). The firmware clamps grip strength to physiologically meaningful ranges before applying this formula so the square root remains well-defined. 

float ageFromGripMale(float g) {
  float a = 52.0f, b = 0.0089f;
  if (g > a) g = a;
  if (g < 5) g = 5;
  return 35.0f + sqrtf((a - g) / b);
}

float ageFromGripFemale(float g) {
  float a = 32.0f, b = 0.0059f;
  if (g > a) g = a;
  if (g < 4) g = 4;
  return 35.0f + sqrtf((a - g) / b);
}

For full methodological details and original tables/figures, see the open-access paper: Dodds et al., 2014, PLOS ONE (download local PDF). The implementation here is an educational approximation and not intended for clinical or diagnostic use.

End-to-end live demoReal-time demonstration of squeezing the mechanical gripper and watching the Wi-Fi dashboard update grip strength and estimated age on a laptop.

Related Design, Code, and Calibration Resources

User Interface Comparison

Summary of how each interface application connects users with input and output devices.

Application How It Interfaces with the User Input Device(s) Output Device(s)
(a) Button User Interface Button press patterns (single, double, triple press, hold) provide mode selection input. OLED display shows current menu state and mode options. Users receive immediate visual feedback for each interaction. Button (GPIO pin 4) OLED Display (SSD1306, I²C 0x3C)
LED (GPIO pin 3, flashlight mode)
(b) Real-Time GUI (OLED & WiFi) Physical finger placement on MAX30102 sensor provides input. OLED displays real-time sensor data locally. WiFi web interface enables remote monitoring with numerical displays and live plotting charts accessible from any web browser. MAX30102 Pulse Oximeter Sensor (I²C 0x57) OLED Display (SSD1306, I²C 0x3C)
WiFi Web Interface (HTTP Server with Chart.js visualization)
(c) Grip Strength GUI (Load Cell & WiFi) Users squeeze a mechanical hand gripper that transfers force into an 80 kg bar load cell. The ESP32-S3 measures grip strength through the HX711 amplifier and streams results to a WiFi web dashboard that displays live grip force and an estimated physiological age in real time. Mechanical gripper linked to 80 kg load cell (CZL601-type)
HX711 load cell amplifier		 WiFi Web Interface (HTTP Server with Chart.js visualization)
Optional Serial Plotter (for calibration traces)

Group Assignment: Compare as Many Tool Options as Possible

Compare as many tool options as possible for interface and application programming.

General Comparison: Interface & Application Programming Tools

Comprehensive comparison of interface and application programming tools available for embedded systems and IoT development. This analysis covers tools from the MIT Academy Interface & Application Programming class page, evaluating their capabilities, use cases, and trade-offs for different application scenarios.

Embedded Display Interfaces

Tool/Framework Description Pros Cons Best For
OLED (SSD1306) Monochrome OLED displays via I²C Low power, high contrast, simple I²C interface, pixel-level control Limited resolution (128x64), monochrome only, small display size Status displays, sensor readouts, simple menus, embedded dashboards
LCD Character Displays Character-based LCD displays (16x2, 20x4) Simple API, readable in sunlight, low cost Limited to text/characters, no graphics, requires backlight power Text-only interfaces, status messages, debugging output
TFT Color Displays Full-color TFT LCD displays Color graphics, touch support, high resolution High power consumption, complex drivers, larger footprint Rich GUIs, image display, interactive touch interfaces

Web-Based Interfaces

Tool/Framework Description Pros Cons Best For
HTTP Server (ESP32) Built-in HTTP server on ESP32 for web interfaces Remote access, cross-platform (any browser), no app installation, real-time updates Requires WiFi, network dependency, limited to local network without port forwarding Remote monitoring, data visualization, control panels, sensor dashboards
WebSockets Real-time bidirectional communication Low latency, bidirectional, efficient for frequent updates More complex than HTTP, requires persistent connection Real-time streaming, interactive controls, live data feeds
Chart.js JavaScript charting library for web interfaces Beautiful charts, interactive, responsive, easy integration Requires JavaScript, CDN dependency or local hosting Data visualization, time series plots, sensor monitoring dashboards

Mobile & Native App Frameworks

Tool/Framework Description Pros Cons Best For
React Native Cross-platform mobile app framework Cross-platform (iOS/Android), native performance, large ecosystem Complex setup, requires mobile development knowledge Full-featured mobile apps, production deployments
Flutter Google's UI toolkit for cross-platform apps Single codebase, high performance, customizable UI Dart language, larger app size, learning curve Custom mobile interfaces, platform-specific designs
Progressive Web Apps (PWA) Web apps with native-like features No app store, cross-platform, offline capability Limited native API access, browser dependency Web-based mobile interfaces, simple deployment

Specific Comparison: Tools Used in Individual Assignment

Detailed comparison of the specific interface programming tools implemented in this week's individual assignment, evaluating their performance, ease of use, and suitability for embedded health monitoring applications.

OLED Display Interface (Adafruit SSD1306)

Aspect Evaluation
Ease of Implementation Simple I²C interface, well-documented Adafruit library, minimal wiring (SDA, SCL, power, ground)
Display Quality High contrast monochrome display, crisp text rendering, suitable for sensor data visualization
Power Consumption Very low power draw, ideal for battery-powered applications
Limitations 128x64 pixel resolution limits detail, monochrome only, small physical size (0.96" typical)
Best Use Cases Local sensor readouts, menu systems, status indicators, simple data displays

WiFi Web Interface (ESP32 HTTP Server + Chart.js)

Aspect Evaluation
Ease of Implementation ESP32 WebServer library provides straightforward HTTP server, Chart.js CDN integration requires minimal setup
Remote Access Accessible from any device on WiFi network (phone, tablet, computer), no app installation required
Visualization Capabilities Chart.js enables rich data visualization with real-time plotting, smooth animations, and interactive features
Real-Time Updates JSON API endpoint provides efficient data transfer, 300ms refresh rate maintains responsive feel
Limitations Requires WiFi network, limited to local network without additional configuration, power consumption higher than OLED alone
Best Use Cases Remote monitoring, data logging visualization, multi-user access, professional dashboards

Button Input Interface

Aspect Evaluation
Implementation Approach Digital GPIO reading with debouncing, press pattern detection (single/double/triple/hold) enables mode navigation
User Experience Intuitive press patterns, immediate visual feedback on OLED, no complex UI navigation required
Reliability Hardware debouncing with INPUT_PULLUP, timeout-based pattern recognition prevents accidental triggers
Limitations Limited to single button interaction, pattern learning required, less flexible than touchscreen interfaces
Best Use Cases Simple mode selection, menu navigation, embedded system controls, low-cost input solutions

Comparison Summary

The combination of OLED display and WiFi web interface provides complementary benefits: OLED offers immediate local feedback with minimal latency and power consumption, while the WiFi interface enables rich visualization and remote access. The button-based input provides an intuitive, low-cost navigation method suitable for embedded systems. Together, these tools create a robust interface system that supports both local and remote interaction with sensor data.

ESP32-S3 Development Board and Pinouts

Code files for ESP32-S3 development board interfaces including I2C scanning, OLED display control, and button-based user interface systems. See Week 4 documentation for board design and Week 8 documentation for pinout configurations.

I2C Scanner (i2cscan_generic.ino)

Utility code for scanning and detecting I2C devices on the bus, essential for troubleshooting connection issues.

How the Code Works (Pseudocode)
SETUP:
  Initialize I2C bus
  Initialize Serial communication
  Print "I2C Scanner" message

LOOP:
  Print "Scanning..." message
  Initialize device counter to 0
  
  FOR each address from 1 to 126:
    Begin I2C transmission to address
    Check transmission result
    
    IF transmission successful (error == 0):
      Print device found at address (hex format)
      Increment device counter
    ELSE IF unknown error (error == 4):
      Print unknown error at address
    
  IF no devices found:
    Print "No I2C devices found"
  ELSE:
    Print "done"
  
  Wait 5 seconds before next scan
Key Features
What You Need to Know
Download: i2cscan_generic.ino

Hello World OLED Display (hello_world.ino)

Basic OLED display test code that initializes the display and shows "Hello World" text, confirming I2C communication and display functionality.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial communication at 115200 baud
  Wait 500ms for Serial to stabilize
  
  Initialize I2C bus with SDA pin 5, SCL pin 6
  Print "Starting..." message
  
  Attempt to initialize OLED display:
    IF initialization fails:
      Print "OLED not found" error
      Enter infinite loop (halt)
  
  Clear display buffer
  Set text size to 2
  Set text color to white
  Set cursor position to (0, 20)
  Print "Hello" line
  Print "World!" line
  Update display (send buffer to hardware)

LOOP:
  Empty (runs once, then waits)
Key Features
What You Need to Know
Download: hello_world.ino

Button User Interface (outputs.ino)

Mode-based navigation system using button press patterns (single, double, triple, hold) to control multiple output devices including OLED display, camera, sensors, and LED flashlight.

How the Code Works (Pseudocode)
SETUP:
  Initialize OLED display
  Initialize camera module
  Initialize sensors (MPU6050, HX711)
  Initialize button pin (INPUT_PULLUP)
  Initialize LED pin (OUTPUT)
  Set current mode to MENU
  Display menu screen

LOOP:
  Read button state
  
  IF button pressed:
    Record press start time
    Start press detection timer
  
  IF button released:
    Calculate press duration
    IF duration > HOLD_THRESHOLD:
      Activate flashlight mode
    ELSE:
      Increment press count
      Reset press timeout timer
  
  IF press timeout exceeded:
    Process accumulated press count:
      IF press count == 1: Switch to CAMERA mode
      IF press count == 2: Switch to SENSORS mode
      IF press count == 3: Switch to MENU mode
    Reset press count
  
  IF current mode == MENU:
    Display menu screen (button instructions)
  
  IF current mode == CAMERA:
    Capture camera frame
    Process image with dithering algorithm
    Display on OLED
    Run Edge Impulse inference (optional)
    Overlay results on display
  
  IF current mode == SENSORS:
    Read accelerometer/gyroscope data
    Read load cell data
    Display sensor readings on OLED
  
  Update display
Key Features
What You Need to Know
Download: outputs.ino | camera_pins.h | outputs.zip (complete project)

Grip Strength Monitor (Load Cell + WiFi GUI)

Design files and firmware for a Wi-Fi-enabled grip strength meter built around an 80 kg bar load cell, HX711 amplifier, and ESP32-S3. The mechanical design was informed by the open-source grip strength meter from NeuroTech Hub and validated against the CZL601AC bar load cell datasheet (online, download).

Mechanical Design Files (3D-Printed Components)

All parts were printed in PLA with high infill in the load paths to minimize creep and flex during repeated maximal grip trials.

Basic HX711 Reader (loadcell_simple.ino)

Minimal firmware to bring up the HX711 amplifier and read calibrated weight values over Serial for debugging and calibration.

How the Code Works (Pseudocode)
SETUP:
  Configure HX711 data and clock pins (DT=A1, SCK=A0)
  Initialize Serial at 115200 baud
  Begin HX711 with DT/SCK pins
  Set calibration factor (grams per ADC unit)
  Tare the scale so current load is zero

LOOP (every 200 ms):
  If HX711 is ready:
    Read averaged weight using get_units(4)
    Print "weight:<value>" to Serial for Serial Plotter
  Else:
    Print "HX711 not ready" for troubleshooting
Key Features
What You Need to Know
Download: loadcell_simple.ino

Serial Plotter-Friendly Reader (loadcell_plot.ino)

Refined HX711 reader tuned for the Arduino Serial Plotter: it outputs a single numeric value per line for clean plotting of grip strength over time.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial at 115200 baud
  Initialize HX711 on DT=A1, SCK=A0
  Set calibration factor
  Tare the scale
  Optionally print debug messages when DEBUG=1

LOOP (every 200 ms):
  If HX711 is ready:
    Read filtered weight with get_units(4)
    Optionally print labeled debug text
    Print only the numeric weight to Serial for the Plotter
  Else:
    Optionally print "not ready" debug text
    Print 0 so the plotted line continues gracefully
Key Features
What You Need to Know
Download: loadcell_plot.ino

WiFi Grip Strength GUI (loadcell_gui.ino)

Full application firmware that exposes grip strength and an estimated age over Wi-Fi using an HTTP server and a Chart.js web dashboard.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial
  Initialize HX711 (pins, calibration factor, tare)
  Connect ESP32-S3 to WiFi (MIT network in this build)
  Start WebServer on port 80
  Register handlers:
    "/"        → serve HTML+JS GUI page from PROGMEM
    "/metrics" → serve JSON with current grip and age

LOOP:
  Handle incoming HTTP clients
  Every 200 ms:
    If HX711 is ready:
      Read smoothed grip strength (kg) via get_units(3)
      Clamp negative values to zero
      Store in global gripStrength

AGE ESTIMATION HELPERS:
  ageFromGripMale(g):
    Clamp g to plausible range
    Compute age using inverted quadratic fit derived from normative data
  ageFromGripFemale(g):
    Same structure with female-specific parameters

HTTP /metrics ENDPOINT:
  Read "sex" query parameter (default "male")
  Compute ageEstimate = ageFromGripMale/ageFromGripFemale(gripStrength)
  Return JSON:
    {"grip": <kg>, "age": <years>}

CLIENT-SIDE GUI (HTML + JS):
  Render dark-themed dashboard with:
    - Sex toggle buttons (male/female)
    - Numeric grip strength (kg) and age
    - Scrolling Chart.js line plot of recent grip values
  Poll /metrics every 200 ms and update DOM + chart
Key Features
What You Need to Know
Download: loadcell_gui.ino

Invisible String Chain of Hearts

Code files for the Invisible String pulse oximeter interface system, providing real-time health monitoring through OLED display and WiFi web interface. See Week 11 PCB design documentation for hardware details.

OLED GUI for Pulse Oximeter (pulse_vo2_reads_fixing.ino)

Local OLED display interface showing real-time pulse oximeter readings including heart rate (BPM), blood oxygen saturation (SpO2), and raw IR/RED LED sensor values.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial communication
  Initialize I2C bus (SDA=5, SCL=6) at 400kHz
  Initialize MAX30102 sensor
  Configure sensor:
    Set LED mode to RED + IR
    Set ADC range to 16384
    Set sample rate to 100 Hz
    Set pulse width to 411 μs
    Set LED brightness to medium (0x3F)
  Initialize OLED display
  Clear and prepare display

LOOP:
  Read IR and RED LED values from sensor
  
  Heart Rate Detection:
    Check for heartbeat in IR signal using peak detection
    IF heartbeat detected:
      Calculate time since last beat
      Calculate BPM = 60 / (time_delta / 1000)
      Set beat flag for visual indicator
      Update last beat timestamp
  
  SpO2 Calculation (every 300ms):
    Add IR and RED values to circular buffer
    IF buffer has 50 samples:
      Calculate DC components (average)
      Calculate AC components (RMS)
      Calculate R ratio = (AC_RED/DC_RED) / (AC_IR/DC_IR)
      Estimate SpO2 = 110 - 25 * R
      Clamp SpO2 to 70-100% range
  
  Serial Output:
    Print IR, RED, BPM for Serial Plotter visualization
  
  OLED Display Update:
    Clear display buffer
    Display IR value (small text)
    Display RED value (small text)
    Display BPM value (large text, size 2)
    Display SpO2 percentage (small text)
    IF beat detected: Draw heartbeat indicator dot
    Update display hardware
  
  Delay 20ms (50 Hz update rate)
Key Features
What You Need to Know
Download: pulse_vo2_reads_fixing.ino

WiFi Readings GUI (pulse_gui.ino)

WiFi-enabled web interface providing remote access to pulse oximeter data through HTTP server with JSON API endpoint for real-time data updates.

How the Code Works (Pseudocode)
SETUP:
  Initialize Serial communication
  Initialize I2C bus
  Initialize MAX30102 sensor
  Configure sensor (LED mode, sample rate, pulse width)
  Initialize OLED display
  Initialize WiFi:
    Connect to network (SSID, password)
    Wait for connection
    Print IP address
  Initialize HTTP server:
    Route "/" → serve GUI HTML page
    Route "/gui" → serve GUI HTML page
    Route "/metrics" → serve JSON data
  Start web server

LOOP:
  Handle incoming HTTP client requests
  
  Read IR and RED values from sensor
  
  Heart Rate Calculation:
    Check for heartbeat in IR signal
    IF heartbeat detected:
      Calculate BPM from time delta
      Update global BPM variable
  
  SpO2 Calculation:
    Add IR/RED to circular buffer
    IF buffer full (50 samples):
      Calculate SpO2 using ratio-of-ratios
      Update global SpO2 variable
  
  Update global variables (g_ir, g_red, g_bpm, g_spo2)
  
  OLED Display Update:
    Display IR, RED, BPM, SpO2 values
    Update display hardware
Key Features
What You Need to Know
Download: pulse_gui.ino

WiFi Plot GUI (pulse_gui_2.ino)

Enhanced WiFi web interface with real-time plotting capabilities using Chart.js library, displaying live line charts for BPM and SpO2 values with automatic scrolling and data management.

How the Code Works (Pseudocode)
SETUP:
  (Same as pulse_gui.ino)
  Initialize WiFi, sensor, OLED, HTTP server

LOOP:
  (Same as pulse_gui.ino)
  Handle HTTP requests, read sensor, calculate BPM/SpO2

GUI HTML PAGE (embedded in PROGMEM):
  Load Chart.js library from CDN
  Create two Chart.js line chart instances:
    - BPM chart (y-axis: 40-160 BPM)
    - SpO2 chart (y-axis: 70-100%)
  Initialize data arrays for each chart
  
  JavaScript Update Function (runs every 300ms):
    Fetch JSON data from /metrics endpoint
    Update numerical displays (BPM, SpO2, IR, RED)
    Add new BPM value to BPM data array
    Add new SpO2 value to SpO2 data array
    IF array length > maxPoints (100):
      Remove oldest value (shift)
    Update chart labels (array indices)
    Update chart datasets with new data
    Call chart.update() to refresh display
  
  Set interval to call update function every 300ms
Key Features
What You Need to Know
Download: pulse_gui_2.ino

Reflections & Learnings

Key insights and learnings from working with interface and application programming.

Contributions

Acknowledgements and team roles for interface and application programming work.

Ethical AI Use

Transparent documentation of AI assistance used in this week's interface and application programming work.

This section documents all AI assistance used during Week 12 interface and application programming work. ChatGPT was used for code development, troubleshooting, and technical guidance. All transcripts are linked below for transparency.

Menu System with Modes

AI assistance for developing the button-based menu system with mode navigation (Menu, Camera, Sensors) using press pattern detection. The conversation covered button debouncing, press pattern recognition, mode state management, and OLED menu display design.

Related to: Part (a): Simple Button User Interface on OLED

View ChatGPT Transcript: Menu System with Modes

I2C Device Not Found

Troubleshooting session for I2C device detection issues with MAX30102 pulse oximeter sensor. The conversation addressed power isolation problems, I2C wiring verification, sensor initialization order, and ground plane isolation requirements for accurate sensor operation.

Related to: Part (b): Real-Time Graphical User Interface through OLED and WiFi

View ChatGPT Transcript: I2C Device Not Found

Hello World Code

Development assistance for creating the initial OLED "Hello World" test program. The conversation covered I2C initialization, OLED display library setup, text rendering, and basic display configuration for XIAO ESP32-S3 development board.

Related to: Part (b): Real-Time Graphical User Interface through OLED and WiFi (initial OLED test)

View ChatGPT Transcript: Hello World Code

MAX30102 Initialization Fix

Technical guidance for fixing MAX30102 pulse oximeter sensor initialization issues. The conversation addressed sensor configuration parameters, LED brightness settings, sample rate optimization, initialization sequence requirements, and troubleshooting sensor communication problems.

Related to: Part (b): Real-Time Graphical User Interface through OLED and WiFi (pulse oximeter readings)

View ChatGPT Transcript: MAX30102 Initialization Fix

Grip Strength Monitor Code Design

Code-focused assistance for designing and refining the WiFi grip strength monitor firmware. The conversation covered HX711 bring-up, load cell pin mapping, Serial Plotter debugging sketches, the ESP32-S3 HTTP server, the Chart.js dashboard, and the age-estimation helpers used in loadcell_simple.ino, loadcell_plot.ino, and loadcell_gui.ino.

Related to: Part (c): Real-Time GUI through Mechanical Gripper and WiFi and Grip Strength Monitor design files

View ChatGPT Transcript: Grip Strength Monitor Code

Grip Strength Calibration & Scaling

Calibration-focused assistance for mapping HX711 counts to kilograms and validating the grip strength readings. The discussion walked through using the Serial Plotter, collecting reference weights, tuning the calibration factor, and sanity-checking the age-estimation model derived from normative grip strength data.

Related to: Part (c): Real-Time GUI through Mechanical Gripper and WiFi calibration workflow and the Grip Strength Monitor sketches.

View ChatGPT Transcript: Grip Strength Calibration

Grip Strength Monitor – Cursor Transcript

Full Cursor AI transcript focused on organizing the grip strength monitor section: structuring Part (c), integrating design files, embedding images and videos, and aligning captions, external references, and the Ethical AI Use documentation for the load cell project.

Related to: Part (c): Real-Time GUI through Mechanical Gripper and WiFi, Grip Strength Monitor design files, and this Ethical AI Use section.

View HTML Transcript Download Markdown Transcript

Week 12 Project Documentation

Complete Cursor AI transcript for Week 12 interface and application programming project documentation. This comprehensive conversation covers the creation and population of the Week 12 HTML page, including Individual Assignment sections (button UI and WiFi GUI), Group Assignment tool comparisons, Design Files documentation with pseudocode, and Ethical AI Use section organization. The transcript demonstrates the collaborative process of building professional documentation with structured content, embedded media, and comprehensive code documentation.

Related to: Complete Week 12 documentation including Individual Assignment, Group Assignment, Design Files, and overall page structure

View HTML Transcript Download Markdown Transcript

Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License

``` Verifying the cleanup and checking for remaining issues: Checking what's between the Group Assignment and Design Files sections: Finding and removing the remaining old Part (a), (b), and (c) sections: Searching for the old Part sections to remove them: Trying a simpler search: The remaining references are in the Ethical AI Use section, which is fine. Marking the cleanup as complete and verifying the page structure: Created and updated `week13.html` with the requested content: 1. **Copied week12.html to week13.html** and updated the title/header for Wildcard Week 2. **Added lecture notes section** with week 13 content (theme, announcements, week 12 review, system integration reminders) 3. **Added recitation notes section** on "Why Make (Almost) Anything" covering fab labs, impact, infrastructure design, and scaling 4. **Updated Useful Documentation** with: - Wildcard week class page link - ATtiny1626 references (datasheet, pinout, AVR Freaks discussion) - Embedded programming course resources with ATtiny412 examples 5. **Updated Design Files section** with: - ATtiny1626 development board (images and zip download) - RP2354A development board (image and zip download) 6. **Created Individual Assignment section** with: - PCB engraving process documentation - Tools and equipment (Carvera, fiber laser) - Board design considerations - Postprocessing steps - Images and videos embedded with captions - Interface table showing how it interfaces with user 7. **Created Group Assignment section** listing wildcard week possibilities (machining, welding, molding, folding, robotics, etc.) 8. **Cleaned up remnants** from the week12.html copy The page is linked in `index.html` (already present). All images and videos are embedded with captions and descriptions. No linting errors found. The page is ready for use. --- **User** remove everything in ethical AI use section and then update ethical AI use section with cursor_week_13_assignment_page_creation.md, option to download markdown or view transcript (run .md to .html script in scripts) update contributions with Quentin and Anthony running the wildcard week, and Quentin with designing the RP board before the session and finishing the ATTiny design with us during the wildcard session wi --- **Cursor** Updating the Ethical AI Use section and Contributions. Checking the current structure: Finding the Ethical AI Use section and Contributions section: Converting the markdown to HTML, then updating both sections: Replacing the Ethical AI Use section and updating Contributions: ```html Week 13 · Wildcard Week
← Back to Home
[Profile Image Placeholder]

Week 13

Wildcard Week

Week Highlights

Key captures from the PCB engraving assignment with links to their sections.

ATtiny1626 Board Design

Final ATtiny1626 development board design with connectors and mounting holes

PCB Engraving

ATtiny1626 development board after fiber laser engraving

Soldered Board

Fully assembled ATtiny1626 development board with all components soldered

Blinking LED Demo

RP2354A Board Design

RP2354A development board design

PCB Engraving Detail

Close-up detail of PCB engraving showing trace quality

Table of Contents

Course Content

Training & Documentation

Assignments & Projects

Wildcard Week

This week focuses on exploring digital fabrication processes not covered in previous assignments. We'll design and produce something using computer-aided design and manufacturing, documenting requirements and including everything necessary for reproduction. This week also includes reflection on the impact and purpose of making (almost) anything.

Exploring new digital fabrication processes
Designing and producing with CAD/CAM
Understanding the impact and purpose of fabrication labs

This Week's Goals

  • Explore New Processes
    Design and produce something with a digital process not covered in other assignments
  • Complete Documentation
    Document requirements and include everything necessary to reproduce the project
  • Reflect on Impact
    Understand the purpose and impact of fabrication labs and making

Assignments

  • Group Assignment
    Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment
  • Individual Assignment
    Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment, documenting the requirements that your assignment meets, and including everything necessary to reproduce it

Tools & Materials

  • Carvera (CNC Mill) — Edge cuts and hole machining
  • Fiber Laser Cutter (xTool F2 Ultra) — PCB engraving
  • PCB Design Software (KiCad) — Board layout and design
  • ATtiny1626 Microcontroller — Target device for development board
  • RP2354A Microcontroller — Complex board design

Lecture Notes

Week 13 lecture covering major announcements, week 12 review, system integration reminders, and wildcard week preview.

Theme of the Week

'Step away from the panic'

Major Announcements

  • Subject evaluation: Required for funding the class. Provides feedback to the institute about the class. Important for future students if you care about successors in the class.
  • Calendar alarm: Wildcard week and recitation on why make (almost) anything: impact. Friday is cutoff for assignments and orders (10s of dollars per person from inventory).
  • Final presentation/final exam: Combining multiple additive and subtractive processes (not just design a board and 3D print a case). Goal is system integration out of parts. Final exam criteria:
    • Did you integrate and design a complete system?
    • Can you demo a final project? Here is the cool thing I did and here is how it works.
    • Make a final project video! (helps but not required)
    Focus on well-integrated device!

Review of Week 12 User Interfaces

  • Claire Wang: Music play and Windows 3.1 interface works!
  • Ryan Hoffman: DRV8251A discussion, heat sinks, breakout boards. Wildcards with waterjetting, EDM, multi-axis machining, laser cutting metal. Class in the spring on nature of mathematical modeling.
  • Srikanth Nadhamuni: Background and experience to visiting fellow at MIT. Raspberry Pi W for WiFi, n8n for cloud LLM data crunching. Software: Node.js, MCP bridge server with n8n based on bridge connected to device (NGV tunnel). All set! Fantastic experience, haven't worked so hard in a very long time and learning a lot of new things. Hope to take forward and build other systems. The whole culture of doing and trying yourself fascinating, especially with failing a number of times until you figure it out. Maybe set one up at an IIT in India or AI centers of excellence with education ministry into the Indian education system (see fablabkerala.in or vigyam ashram).
  • Ray Song: Not here.
  • Tyler Jensen (Lincoln Lab, Group 81): Final project discussion (nylon printer). Week 13: Easy for web serial interface for XIAO! Web server to TFT (I think I forgot to load the camera pins with my code for it).
  • Aditi Ramakrishnan: Sloan MBA and strategy consulting background. Discrete time filter (FFT is blown) in skimage.filters — make a bandpass filter, then run a series of these filters, much less computing only adds and multiplies for filtering in realtime.
  • Alexandros Gravalos: Not here.
  • Edward Chen: Check final watch project by Gulati into watch form factor. Clear print on the Form Labs printer, 0.1. Kaman filter for sensor fusion (in the spring class). For position — LSM6DSV16X from input devices. Acceleration at 7 kHz (at audio frequency).

Show and Tell

  • Handle to sensor WiFi user interface
  • Plug to audio LLM user interface

System Integration Reminders

  • Mount electronics
  • Strain relief the final projects

Preview for Wildcard Week

Assignment: Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment.

Recitation Notes: Why Make (Almost) Anything

Recitation exploring the purpose, impact, and scaling of fabrication labs and making infrastructure.

Map of Fab Labs

Why Make a Fab Lab?

  • Used to create a community
  • Building things for the community
  • Sustainability
  • Prototyping quickly

How Impact?

  • How to make spaces: How to measure impact. What is important about fab:
    • Fablabs in cities vs rural areas: The ability to decide their own futures and change their lives fundamentally. 'Safecast revolutionized citizen science' e.g. radiation map.
    • Bringing back manufacturing: Reducing reliance on supply chains.
    • Rural sustainability: Working with indigenous communities on creating technologies themselves at scale and measure their usefulness and efficacy to preserve their ancestral knowledge:
      • How to establish labs there
      • How to make sure the labs get used
    • Hygiene technologies with Proctor and Gamble: Highly commercial. Lots of plastic waste. How can we change how they produce? How to make their products get there through resellers?
    • Trip to Peru and ran workshops, questionnaires, analysis: Collaboration developed into how to produce the products but also how to test their products to be market valuable e.g. mosquito repellents. Out of three plants, two worked better and one wasn't working at all (which is important to know!).

What Does It Mean to Design Infrastructure?

  • What did we want this lab to be able to do?
    • Workshops and questionnaires
    • How much you educate people based on the info they have with the issues the community is facing
    • Energy concerns to consider, some machines just drain the grid and can't be used. Solar powered, battery powered machines, reducing energy consumption of machines. Many concerns important.
  • Ethical questions
  • How to maintain resources

Case Study: Water Purifier Packets

Use them, change them, source them locally, ingredients found locally, how to distribute them globally.

Funding Models

First few fablabs were NSF funded. Now corporate CSR, regional funding, labor funding (10 different ways). Successful fablabs are heterogeneous with lots of ways of funding. The ones that fail usually just have one sponsor.

Example: DIY Raman spectrometer for water purification (even after purifications still have sulfates and improving that too).

What Does It Mean to Scale Infrastructure?

(Besides a lot of meetings!) What is a reasonable way to design a data collection process about what is needed and how to achieve it.

Back to the Map: Expansion

Timeline of development, cocreation, portable, skin analysis, water testing, biomaterial tech, microscopy.

Initial Results from Boston

How to Confront Local Impact
  • Collab with University of Hamburg. Motivation for how much food can be produced in Boston. Where food waste goes and what Boston produces locally. Make things for yourself locally.
  • Impact directly in the community you're living in.

Hatchspace

Focused on rehabilitation of addicts with woodworking. (Vermont is wood producing state).

Example Course Program

  • All-in session and systemic impact
  • Natural and cultural context
  • Skills and workshop
  • Economic vitality
  • Skills and workshop
  • Co-work session
  • Solutionspalooza

In the Course

Hands-on component (no physical robot exists that can do it) and community component is also important. Inclusion is important. Solving unconscious and institutional biases.

  • 'Fabrica! Lab' — Creating new laboratory spaces for female high school students, courses aimed for women in technology, online advising sessions for females interested in tech.
  • Makerspaces — Access to tools behind closed doors at universities, makes a huge difference for people who don't have the ability to prototype for themselves.
  • Materiom — Fablab affiliated project on organic waste for biomaterials.
  • Fablab León
  • Skylab workshop experiment — How to run a noodle shop out of a fablab (creating food from the community).
  • Academany — Global distributed campus for high school education. Fablab all-in (belonging, impact, community), fab futures (future vocational skills), bio academy (synthetic biology), fabricademy (textiles, fab, bio), fab academy (digital fab apps and implications).

Trade-off Between Impactful and Dangerous

People could be doing bad, but not because doing it with a group people with values.

Questions

Clarification: Adding infrastructure to existing fablab infrastructure to help support specific community needs (not specialized fab labs).

Foundations for Fab Futures

July 27-31, 2026 at Fab Boston 2026.

Useful Documentation

Essential resources for wildcard week digital fabrication processes and PCB design.

Class Page

Wildcard Week - MIT Academy

Comprehensive resource covering wildcard week assignment requirements and possibilities including grinding, multi-axis machining, electrical discharge machining, waterjet cutting, flatbed cutting, plasma cutting, laser metal cutting, laser micromachining, welding, molding and casting, folding, robotics, electronics, embedded programming, food, materials, biotechnology, textiles, and composites.

Key Topics

  • Machining: Grinding, multi-axis machining, electrical discharge machining, waterjet cutting, plasma cutting, laser metal cutting, laser micromachining
  • Molding & Casting: Vacuum forming, rotocasting
  • Folding: Mathematics, form and function, kirigami
  • Robotics: Arms, construction, soft actuation pneumatic inflatable
  • Electronics: Pick and place, programmable logic
  • Embedded Programming: Machine learning, machine vision
  • Textiles: Fiber processes, knitting, embroidery (PEmbroider, Ink/Stitch), Fabricademy
  • Composites: Various composite fabrication techniques

ATtiny1626 Development Board References

Embedded Programming Course Resources

Course resources for embedded programming with ATtiny412 microcontroller examples:

Embedded Programming - MIT Academy

ATtiny412 Echo Example Image

Individual Assignment: PCB Engraving with Fiber Laser

Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment. This assignment demonstrates PCB design and fabrication using a combination of CNC milling (Carvera) for edge cuts and hole machining, and fiber laser engraving (xTool F2 Ultra) for trace creation on copper-clad boards. The project includes designing and fabricating two development boards: a simple ATtiny1626 development board and a complex RP2354A development board.

PCB Engraving Process

This project explores PCB fabrication using fiber laser engraving, a process not covered in previous assignments. The workflow combines subtractive manufacturing techniques: CNC milling for mechanical features (edge cuts and holes) and laser engraving for electrical traces. This approach enables rapid prototyping of custom PCBs without requiring chemical etching or specialized PCB manufacturing facilities.

Tools and Equipment

  • Carvera (CNC Mill): Used for edge cuts and hole machining. The laser cannot effectively cut through the board material, so mechanical cutting is required for board outline and mounting holes.
  • Fiber Laser Cutter (xTool F2 Ultra): Used for PCB trace engraving. The laser removes copper from the board surface to create electrical traces and pads.
  • PCB Design Software (KiCad): Used for schematic capture, PCB layout, and design rule checking.

Boards Designed

  • Simple Board: ATtiny1626 development board with connectors, resistors, LED, and capacitor
  • Complex Board: RP2354A development board with more advanced routing and component placement

Board Design Considerations

  • Connector Placement: Top and bottom for connectors, right side for flashing. Connectors along edges to minimize form factor and maximize space usage.
  • Vertical Connectors: Used instead of horizontal connectors because horizontal connectors risk being snapped during use.
  • Black Area Avoidance: Avoid large black areas because laser does not work well with that (keep traces closer and further to minimize black areas). Note: Need to characterize maximum black until it burns the board because dumping too much heat in one place can damage the board.
  • Breadboard Compatibility: Put connectors on 100mil spacing grid size for breadboardability.
  • Pin Count Adjustment: Missed six pins in initial design, so switched from 6-pin headers to 9-pin (distributed six on top and bottom).
  • I2C Resistors: No SDA or SCL resistors included to keep flexibility for future use. May add spot for zero-ohm or pull-up resistor later but keeping it simple for now.
  • Mounting Holes: Added aligned mounting holes (M3 usually — for 3mm screws) for mechanical mounting.
  • Rounded Edge Cuts: Do 90 degrees, copy, drag, and complete the shape for rounded corners.

Design Rules

  • 0.1 mm spacing minimum
  • 0.15 mm trace width minimum
  • 0.15 mm clearance between plane and the rest

Ports and Pins

ATtiny1626 is an 8-bit microcontroller with 8 pins maximum per port. Each port has 8 pins maximum (some less). Need to specify port letter and pin number:

  • PA (0-7)
  • PB (0-7)
  • PC (0-7)

Postprocessing

  • For Carvera: Add new layer with just the holes in Photoshop (only holes for machining).
  • For Laser Engraving: Get rid of the holes for the F2 tools engraving in Inkscape (the frame and the board for alignment, then only engrave the board, not the edges).

Carvera Machining

Using mods → mill 2D PCB workflow:

  • 0.12mm cut depth and max depth

PCB Engraving Process

Using xTool F2 Ultra fiber laser:

  • Use tape for laser alignment
  • Run a test first on spare copper before the Carvera cut board to make sure focus is good (2.7mm thickness setting worked, board is actually 1.6-1.7mm thick)
  • Sand after engraving to clean up any residue
  • Worked with Bantam Tools FR1 (not random Amazon copper)
  • Perform short circuit test after engraving

Soldering

Using solder gun (heat gun) for component assembly.

Components

  • 1x 6-pin flipflop headers
  • 2x 9-pin flipflop headers
  • 1x 4.7k resistor
  • 1x 1k resistor
  • 1x LED
  • 1x 1uF or 10uF capacitor

Design Files

Download design files: ATtiny_QFN.zip and RP2354A-dev-v1.1.zip

Final ATtiny1626 development board design showing component placement and routing
ATtiny1626 final designComplete PCB layout with connectors, components, traces, and mounting holes optimized for laser engraving.
ATtiny1626 development board after fiber laser engraving showing copper traces
PCB after engravingCopper-clad board with traces engraved using fiber laser, ready for component soldering.
Fully assembled ATtiny1626 development board with all components soldered
Soldered boardComplete ATtiny1626 development board with headers, resistors, LED, and capacitor soldered in place.
Blinking LED demoVideo demonstration of the completed ATtiny1626 development board running a simple LED blink program, confirming successful fabrication and programming.
Close-up detail of PCB engraving showing trace quality and copper removal
PCB engraving detailClose-up view of fiber laser engraved traces showing clean copper removal and precise trace definition.

Interface with User

The application interfaces a user with input and/or output devices through the ATtiny1626 development board. The following table describes how the application interfaces with the user:

How It Interfaces with User Input Device(s) Output Device(s)
(a) LED Blink Demonstration None (programmed behavior) LED (visual feedback indicating board functionality)
(b) Future Interface Applications GPIO pins (PA, PB, PC ports) available for sensors, buttons, switches GPIO pins (PA, PB, PC ports) available for LEDs, displays, actuators

Group Assignment: Wildcard Week Digital Process

Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment. This group assignment explores various digital fabrication processes available during wildcard week.

Wildcard Week Possibilities

The wildcard week assignment allows exploration of digital fabrication processes not covered in previous weeks. Possibilities include (but are not limited to):

Machining

  • Grinding
  • Multi-axis machining
  • Electrical discharge machining (EDM)
  • Waterjet cutting
  • Flatbed cutting
  • Plasma cutting
  • Laser metal cutting
  • Laser micromachining

Welding

Various welding techniques for joining materials.

Molding and Casting

  • Vacuum forming
  • Rotocasting

Folding

  • Mathematics
  • Form and function
  • Kirigami

Robotics

  • Arms
  • Construction
  • Soft actuation pneumatic inflatable

Electronics

  • Pick and place
  • Programmable logic

Embedded Programming

  • Machine learning
  • Machine vision

Food

  • Printing
  • Gastronomy

Materials

  • Synthesis
  • Mechanical
  • Rheological

Biotechnology

  • DIYbio
  • iGEM
  • HTGAA
  • Bio Academy

Textiles

  • Fiber processes
  • Knitting
  • Embroidery (PEmbroider, Ink/Stitch)
  • Fabricademy

Composites

Various composite fabrication techniques.

Design Files

Design files for PCB engraving projects including ATtiny1626 and RP2354A development boards.

ATtiny1626 Development Board

Simple development board for ATtiny1626 microcontroller with connectors, resistors, LED, and capacitor. Designed for breadboard compatibility with 100mil spacing grid.

Initial ATtiny1626 development board design
Initial designFirst iteration of ATtiny1626 development board layout.
Final ATtiny1626 development board design with all components
Final designComplete ATtiny1626 development board with connectors, mounting holes, and optimized trace routing.

Download Design Files

  • ATtiny_QFN.zip — Complete KiCad project files for ATtiny1626 development board

RP2354A Development Board

Complex development board for RP2354A microcontroller with advanced routing and component placement.

RP2354A development board design
RP2354A board designComplete PCB layout for RP2354A development board with complex routing and component placement.

Download Design Files

Reflections & Learnings

Key insights and learnings from working with interface and application programming.

Contributions

Acknowledgements and team roles for interface and application programming work.

Ethical AI Use

Transparent documentation of AI assistance used in this week's wildcard week assignment page creation.

Week 13 Assignment Page Creation

Complete Cursor AI transcript for Week 13 wildcard week assignment page creation. This comprehensive conversation covers the creation and population of the Week 13 HTML page, including lecture and recitation notes, PCB engraving assignment documentation, design files integration, and comprehensive page structure development. The transcript demonstrates the collaborative process of building professional documentation with structured content, embedded media, and comprehensive design file documentation.

Related to: Complete Week 13 documentation including Lecture Notes, Recitation Notes, Individual Assignment, Group Assignment, Design Files, and overall page structure

View HTML Transcript Download Markdown Transcript

Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License

``` ```html Week 13 · Wildcard Week
← Back to Home
[Profile Image Placeholder]

Week 13

Wildcard Week

Week Highlights

Key captures from the PCB engraving assignment with links to their sections.

ATtiny1626 Board Design

Final ATtiny1626 development board design with connectors and mounting holes

PCB Engraving

ATtiny1626 development board after fiber laser engraving

Soldered Board

Fully assembled ATtiny1626 development board with all components soldered

Blinking LED Demo

RP2354A Board Design

RP2354A development board design

PCB Engraving Detail

Close-up detail of PCB engraving showing trace quality

Table of Contents

Course Content

Training & Documentation

Assignments & Projects

Wildcard Week

This week focuses on exploring digital fabrication processes not covered in previous assignments. We'll design and produce something using computer-aided design and manufacturing, documenting requirements and including everything necessary for reproduction. This week also includes reflection on the impact and purpose of making (almost) anything.

Exploring new digital fabrication processes
Designing and producing with CAD/CAM
Understanding the impact and purpose of fabrication labs

This Week's Goals

  • Explore New Processes
    Design and produce something with a digital process not covered in other assignments
  • Complete Documentation
    Document requirements and include everything necessary to reproduce the project
  • Reflect on Impact
    Understand the purpose and impact of fabrication labs and making

Assignments

  • Group Assignment
    Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment
  • Individual Assignment
    Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment, documenting the requirements that your assignment meets, and including everything necessary to reproduce it

Tools & Materials

  • Carvera (CNC Mill) — Edge cuts and hole machining
  • Fiber Laser Cutter (xTool F2 Ultra) — PCB engraving
  • PCB Design Software (KiCad) — Board layout and design
  • ATtiny1626 Microcontroller — Target device for development board
  • RP2354A Microcontroller — Complex board design

Lecture Notes

Week 13 lecture covering major announcements, week 12 review, system integration reminders, and wildcard week preview.

Theme of the Week

'Step away from the panic'

Major Announcements

  • Subject evaluation: Required for funding the class. Provides feedback to the institute about the class. Important for future students if you care about successors in the class.
  • Calendar alarm: Wildcard week and recitation on why make (almost) anything: impact. Friday is cutoff for assignments and orders (10s of dollars per person from inventory).
  • Final presentation/final exam: Combining multiple additive and subtractive processes (not just design a board and 3D print a case). Goal is system integration out of parts. Final exam criteria:
    • Did you integrate and design a complete system?
    • Can you demo a final project? Here is the cool thing I did and here is how it works.
    • Make a final project video! (helps but not required)
    Focus on well-integrated device!

Review of Week 12 User Interfaces

  • Claire Wang: Music play and Windows 3.1 interface works!
  • Ryan Hoffman: DRV8251A discussion, heat sinks, breakout boards. Wildcards with waterjetting, EDM, multi-axis machining, laser cutting metal. Class in the spring on nature of mathematical modeling.
  • Srikanth Nadhamuni: Background and experience to visiting fellow at MIT. Raspberry Pi W for WiFi, n8n for cloud LLM data crunching. Software: Node.js, MCP bridge server with n8n based on bridge connected to device (NGV tunnel). All set! Fantastic experience, haven't worked so hard in a very long time and learning a lot of new things. Hope to take forward and build other systems. The whole culture of doing and trying yourself fascinating, especially with failing a number of times until you figure it out. Maybe set one up at an IIT in India or AI centers of excellence with education ministry into the Indian education system (see fablabkerala.in or vigyam ashram).
  • Ray Song: Not here.
  • Tyler Jensen (Lincoln Lab, Group 81): Final project discussion (nylon printer). Week 13: Easy for web serial interface for XIAO! Web server to TFT (I think I forgot to load the camera pins with my code for it).
  • Aditi Ramakrishnan: Sloan MBA and strategy consulting background. Discrete time filter (FFT is blown) in skimage.filters — make a bandpass filter, then run a series of these filters, much less computing only adds and multiplies for filtering in realtime.
  • Alexandros Gravalos: Not here.
  • Edward Chen: Check final watch project by Gulati into watch form factor. Clear print on the Form Labs printer, 0.1. Kaman filter for sensor fusion (in the spring class). For position — LSM6DSV16X from input devices. Acceleration at 7 kHz (at audio frequency).

Show and Tell

  • Handle to sensor WiFi user interface
  • Plug to audio LLM user interface

System Integration Reminders

  • Mount electronics
  • Strain relief the final projects

Preview for Wildcard Week

Assignment: Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment.

Recitation Notes: Why Make (Almost) Anything

Recitation exploring the purpose, impact, and scaling of fabrication labs and making infrastructure.

Map of Fab Labs

Why Make a Fab Lab?

  • Used to create a community
  • Building things for the community
  • Sustainability
  • Prototyping quickly

How Impact?

  • How to make spaces: How to measure impact. What is important about fab:
    • Fablabs in cities vs rural areas: The ability to decide their own futures and change their lives fundamentally. 'Safecast revolutionized citizen science' e.g. radiation map.
    • Bringing back manufacturing: Reducing reliance on supply chains.
    • Rural sustainability: Working with indigenous communities on creating technologies themselves at scale and measure their usefulness and efficacy to preserve their ancestral knowledge:
      • How to establish labs there
      • How to make sure the labs get used
    • Hygiene technologies with Proctor and Gamble: Highly commercial. Lots of plastic waste. How can we change how they produce? How to make their products get there through resellers?
    • Trip to Peru and ran workshops, questionnaires, analysis: Collaboration developed into how to produce the products but also how to test their products to be market valuable e.g. mosquito repellents. Out of three plants, two worked better and one wasn't working at all (which is important to know!).

What Does It Mean to Design Infrastructure?

  • What did we want this lab to be able to do?
    • Workshops and questionnaires
    • How much you educate people based on the info they have with the issues the community is facing
    • Energy concerns to consider, some machines just drain the grid and can't be used. Solar powered, battery powered machines, reducing energy consumption of machines. Many concerns important.
  • Ethical questions
  • How to maintain resources

Case Study: Water Purifier Packets

Use them, change them, source them locally, ingredients found locally, how to distribute them globally.

Funding Models

First few fablabs were NSF funded. Now corporate CSR, regional funding, labor funding (10 different ways). Successful fablabs are heterogeneous with lots of ways of funding. The ones that fail usually just have one sponsor.

Example: DIY Raman spectrometer for water purification (even after purifications still have sulfates and improving that too).

What Does It Mean to Scale Infrastructure?

(Besides a lot of meetings!) What is a reasonable way to design a data collection process about what is needed and how to achieve it.

Back to the Map: Expansion

Timeline of development, cocreation, portable, skin analysis, water testing, biomaterial tech, microscopy.

Initial Results from Boston

How to Confront Local Impact
  • Collab with University of Hamburg. Motivation for how much food can be produced in Boston. Where food waste goes and what Boston produces locally. Make things for yourself locally.
  • Impact directly in the community you're living in.

Hatchspace

Focused on rehabilitation of addicts with woodworking. (Vermont is wood producing state).

Example Course Program

  • All-in session and systemic impact
  • Natural and cultural context
  • Skills and workshop
  • Economic vitality
  • Skills and workshop
  • Co-work session
  • Solutionspalooza

In the Course

Hands-on component (no physical robot exists that can do it) and community component is also important. Inclusion is important. Solving unconscious and institutional biases.

  • 'Fabrica! Lab' — Creating new laboratory spaces for female high school students, courses aimed for women in technology, online advising sessions for females interested in tech.
  • Makerspaces — Access to tools behind closed doors at universities, makes a huge difference for people who don't have the ability to prototype for themselves.
  • Materiom — Fablab affiliated project on organic waste for biomaterials.
  • Fablab León
  • Skylab workshop experiment — How to run a noodle shop out of a fablab (creating food from the community).
  • Academany — Global distributed campus for high school education. Fablab all-in (belonging, impact, community), fab futures (future vocational skills), bio academy (synthetic biology), fabricademy (textiles, fab, bio), fab academy (digital fab apps and implications).

Trade-off Between Impactful and Dangerous

People could be doing bad, but not because doing it with a group people with values.

Questions

Clarification: Adding infrastructure to existing fablab infrastructure to help support specific community needs (not specialized fab labs).

Foundations for Fab Futures

July 27-31, 2026 at Fab Boston 2026.

Useful Documentation

Essential resources for wildcard week digital fabrication processes and PCB design.

Class Page

Wildcard Week - MIT Academy

Comprehensive resource covering wildcard week assignment requirements and possibilities including grinding, multi-axis machining, electrical discharge machining, waterjet cutting, flatbed cutting, plasma cutting, laser metal cutting, laser micromachining, welding, molding and casting, folding, robotics, electronics, embedded programming, food, materials, biotechnology, textiles, and composites.

Key Topics

  • Machining: Grinding, multi-axis machining, electrical discharge machining, waterjet cutting, plasma cutting, laser metal cutting, laser micromachining
  • Molding & Casting: Vacuum forming, rotocasting
  • Folding: Mathematics, form and function, kirigami
  • Robotics: Arms, construction, soft actuation pneumatic inflatable
  • Electronics: Pick and place, programmable logic
  • Embedded Programming: Machine learning, machine vision
  • Textiles: Fiber processes, knitting, embroidery (PEmbroider, Ink/Stitch), Fabricademy
  • Composites: Various composite fabrication techniques

ATtiny1626 Development Board References

Embedded Programming Course Resources

Course resources for embedded programming with ATtiny412 microcontroller examples:

Embedded Programming - MIT Academy

ATtiny412 Echo Example Image

Individual Assignment: PCB Engraving with Fiber Laser

Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment. This assignment demonstrates PCB design and fabrication using a combination of CNC milling (Carvera) for edge cuts and hole machining, and fiber laser engraving (xTool F2 Ultra) for trace creation on copper-clad boards. The project includes designing and fabricating two development boards: a simple ATtiny1626 development board and a complex RP2354A development board.

PCB Engraving Process

This project explores PCB fabrication using fiber laser engraving, a process not covered in previous assignments. The workflow combines subtractive manufacturing techniques: CNC milling for mechanical features (edge cuts and holes) and laser engraving for electrical traces. This approach enables rapid prototyping of custom PCBs without requiring chemical etching or specialized PCB manufacturing facilities.

Tools and Equipment

  • Carvera (CNC Mill): Used for edge cuts and hole machining. The laser cannot effectively cut through the board material, so mechanical cutting is required for board outline and mounting holes.
  • Fiber Laser Cutter (xTool F2 Ultra): Used for PCB trace engraving. The laser removes copper from the board surface to create electrical traces and pads.
  • PCB Design Software (KiCad): Used for schematic capture, PCB layout, and design rule checking.

Boards Designed

  • Simple Board: ATtiny1626 development board with connectors, resistors, LED, and capacitor
  • Complex Board: RP2354A development board with more advanced routing and component placement

Board Design Considerations

  • Connector Placement: Top and bottom for connectors, right side for flashing. Connectors along edges to minimize form factor and maximize space usage.
  • Vertical Connectors: Used instead of horizontal connectors because horizontal connectors risk being snapped during use.
  • Black Area Avoidance: Avoid large black areas because laser does not work well with that (keep traces closer and further to minimize black areas). Note: Need to characterize maximum black until it burns the board because dumping too much heat in one place can damage the board.
  • Breadboard Compatibility: Put connectors on 100mil spacing grid size for breadboardability.
  • Pin Count Adjustment: Missed six pins in initial design, so switched from 6-pin headers to 9-pin (distributed six on top and bottom).
  • I2C Resistors: No SDA or SCL resistors included to keep flexibility for future use. May add spot for zero-ohm or pull-up resistor later but keeping it simple for now.
  • Mounting Holes: Added aligned mounting holes (M3 usually — for 3mm screws) for mechanical mounting.
  • Rounded Edge Cuts: Do 90 degrees, copy, drag, and complete the shape for rounded corners.

Design Rules

  • 0.1 mm spacing minimum
  • 0.15 mm trace width minimum
  • 0.15 mm clearance between plane and the rest

Ports and Pins

ATtiny1626 is an 8-bit microcontroller with 8 pins maximum per port. Each port has 8 pins maximum (some less). Need to specify port letter and pin number:

  • PA (0-7)
  • PB (0-7)
  • PC (0-7)

Postprocessing

  • For Carvera: Add new layer with just the holes in Photoshop (only holes for machining).
  • For Laser Engraving: Get rid of the holes for the F2 tools engraving in Inkscape (the frame and the board for alignment, then only engrave the board, not the edges).

Carvera Machining

Using mods → mill 2D PCB workflow:

  • 0.12mm cut depth and max depth

PCB Engraving Process

Using xTool F2 Ultra fiber laser:

  • Use tape for laser alignment
  • Run a test first on spare copper before the Carvera cut board to make sure focus is good (2.7mm thickness setting worked, board is actually 1.6-1.7mm thick)
  • Sand after engraving to clean up any residue
  • Worked with Bantam Tools FR1 (not random Amazon copper)
  • Perform short circuit test after engraving

Soldering

Using solder gun (heat gun) for component assembly.

Components

  • 1x 6-pin flipflop headers
  • 2x 9-pin flipflop headers
  • 1x 4.7k resistor
  • 1x 1k resistor
  • 1x LED
  • 1x 1uF or 10uF capacitor

Design Files

Download design files: ATtiny_QFN.zip and RP2354A-dev-v1.1.zip

Final ATtiny1626 development board design showing component placement and routing
ATtiny1626 final designComplete PCB layout with connectors, components, traces, and mounting holes optimized for laser engraving.
ATtiny1626 development board after fiber laser engraving showing copper traces
PCB after engravingCopper-clad board with traces engraved using fiber laser, ready for component soldering.
Fully assembled ATtiny1626 development board with all components soldered
Soldered boardComplete ATtiny1626 development board with headers, resistors, LED, and capacitor soldered in place.
Blinking LED demoVideo demonstration of the completed ATtiny1626 development board running a simple LED blink program, confirming successful fabrication and programming.
Close-up detail of PCB engraving showing trace quality and copper removal
PCB engraving detailClose-up view of fiber laser engraved traces showing clean copper removal and precise trace definition.

Interface with User

The application interfaces a user with input and/or output devices through the ATtiny1626 development board. The following table describes how the application interfaces with the user:

How It Interfaces with User Input Device(s) Output Device(s)
(a) LED Blink Demonstration None (programmed behavior) LED (visual feedback indicating board functionality)
(b) Future Interface Applications GPIO pins (PA, PB, PC ports) available for sensors, buttons, switches GPIO pins (PA, PB, PC ports) available for LEDs, displays, actuators

Group Assignment: Wildcard Week Digital Process

Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment. This group assignment explores various digital fabrication processes available during wildcard week.

Wildcard Week Possibilities

The wildcard week assignment allows exploration of digital fabrication processes not covered in previous weeks. Possibilities include (but are not limited to):

Machining

  • Grinding
  • Multi-axis machining
  • Electrical discharge machining (EDM)
  • Waterjet cutting
  • Flatbed cutting
  • Plasma cutting
  • Laser metal cutting
  • Laser micromachining

Welding

Various welding techniques for joining materials.

Molding and Casting

  • Vacuum forming
  • Rotocasting

Folding

  • Mathematics
  • Form and function
  • Kirigami

Robotics

  • Arms
  • Construction
  • Soft actuation pneumatic inflatable

Electronics

  • Pick and place
  • Programmable logic

Embedded Programming

  • Machine learning
  • Machine vision

Food

  • Printing
  • Gastronomy

Materials

  • Synthesis
  • Mechanical
  • Rheological

Biotechnology

  • DIYbio
  • iGEM
  • HTGAA
  • Bio Academy

Textiles

  • Fiber processes
  • Knitting
  • Embroidery (PEmbroider, Ink/Stitch)
  • Fabricademy

Composites

Various composite fabrication techniques.

Design Files

Design files for PCB engraving projects including ATtiny1626 and RP2354A development boards.

ATtiny1626 Development Board

Simple development board for ATtiny1626 microcontroller with connectors, resistors, LED, and capacitor. Designed for breadboard compatibility with 100mil spacing grid.

Initial ATtiny1626 development board design
Initial designFirst iteration of ATtiny1626 development board layout.
Final ATtiny1626 development board design with all components
Final designComplete ATtiny1626 development board with connectors, mounting holes, and optimized trace routing.

Download Design Files

  • ATtiny_QFN.zip — Complete KiCad project files for ATtiny1626 development board

RP2354A Development Board

Complex development board for RP2354A microcontroller with advanced routing and component placement.

RP2354A development board design
RP2354A board designComplete PCB layout for RP2354A development board with complex routing and component placement.

Download Design Files

Reflections & Learnings

Key insights and learnings from working with interface and application programming.

Contributions

Acknowledgements and team roles for wildcard week PCB engraving work.

Wildcard Week Session

  • Quentin and Anthony: Ran the wildcard week session, providing guidance and support for PCB engraving projects.
  • Quentin: Designed the RP2354A development board before the session and finished the ATtiny1626 design with us during the wildcard session.

Ethical AI Use

Transparent documentation of AI assistance used in this week's wildcard week assignment page creation.

Week 13 Assignment Page Creation

Complete Cursor AI transcript for Week 13 wildcard week assignment page creation. This comprehensive conversation covers the creation and population of the Week 13 HTML page, including lecture and recitation notes, PCB engraving assignment documentation, design files integration, and comprehensive page structure development. The transcript demonstrates the collaborative process of building professional documentation with structured content, embedded media, and comprehensive design file documentation.

Related to: Complete Week 13 documentation including Lecture Notes, Recitation Notes, Individual Assignment, Group Assignment, Design Files, and overall page structure

View HTML Transcript Download Markdown Transcript

Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License

``` Checking for linting errors: Verifying the Contributions section was updated correctly: Verifying the HTML file was created: ## Completed tasks 1. **Removed old Ethical AI Use content** — Removed all previous week 12 content from the Ethical AI Use section. 2. **Converted markdown to HTML** — Ran the conversion script to create `cursor_chats/cursor_week_13_assignment_page_creation.html` from the markdown file. 3. **Updated Ethical AI Use section** — Replaced it with a new section that: - References the Week 13 assignment page creation transcript - Includes links to view the HTML transcript and download the markdown transcript - Links to relevant sections (lecture notes, recitation notes, assignments, design files) 4. **Updated Contributions section** — Added: - **Quentin and Anthony**: Ran the wildcard week session, providing guidance and support for PCB engraving projects - **Quentin**: Designed the RP2354A development board before the session and finished the ATtiny1626 design with us during the wildcard session All changes are in place, and there are no linting errors. The HTML transcript file (2.2MB) was created and is ready for viewing. --- **User** add whitespace above and below these two highlights to show the full image ATtiny1626 Board Design RP2354A Board Design --- **Cursor** Finding the highlights for "ATtiny1626 Board Design" and "RP2354A Board Design" and adding whitespace above and below them. Reading the highlights section to understand the structure: Adding whitespace above and below the two highlights and adjusting the images to show the full image without cropping: ```html Week 13 · Wildcard Week
← Back to Home
[Profile Image Placeholder]

Week 13

Wildcard Week

Week Highlights

Key captures from the PCB engraving assignment with links to their sections.

ATtiny1626 Board Design

Final ATtiny1626 development board design with connectors and mounting holes

PCB Engraving

ATtiny1626 development board after fiber laser engraving

Soldered Board

Fully assembled ATtiny1626 development board with all components soldered

Blinking LED Demo

RP2354A Board Design

RP2354A development board design

PCB Engraving Detail

Close-up detail of PCB engraving showing trace quality

Table of Contents

Course Content

Training & Documentation

Assignments & Projects

Wildcard Week

This week focuses on exploring digital fabrication processes not covered in previous assignments. We'll design and produce something using computer-aided design and manufacturing, documenting requirements and including everything necessary for reproduction. This week also includes reflection on the impact and purpose of making (almost) anything.

Exploring new digital fabrication processes
Designing and producing with CAD/CAM
Understanding the impact and purpose of fabrication labs

This Week's Goals

  • Explore New Processes
    Design and produce something with a digital process not covered in other assignments
  • Complete Documentation
    Document requirements and include everything necessary to reproduce the project
  • Reflect on Impact
    Understand the purpose and impact of fabrication labs and making

Assignments

  • Wildcard Assignments
    Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment
  • Assignment
    Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment, documenting the requirements that your assignment meets, and including everything necessary to reproduce it

Tools & Materials

  • Carvera (CNC Mill) — Edge cuts and hole machining
  • Fiber Laser Cutter (xTool F2 Ultra) — PCB engraving
  • PCB Design Software (KiCad) — Board layout and design
  • ATtiny1626 Microcontroller — Target device for development board
  • RP2354A Microcontroller — Complex board design

Lecture Notes

Week 13 lecture covering major announcements, week 12 review, system integration reminders, and wildcard week preview.

Theme of the Week

'Step away from the panic'

Major Announcements

  • Subject evaluation: Required for funding the class. Provides feedback to the institute about the class. Important for future students if you care about successors in the class.
  • Calendar alarm: Wildcard week and recitation on why make (almost) anything: impact. Friday is cutoff for assignments and orders (10s of dollars per person from inventory).
  • Final presentation/final exam: Combining multiple additive and subtractive processes (not just design a board and 3D print a case). Goal is system integration out of parts. Final exam criteria:
    • Did you integrate and design a complete system?
    • Can you demo a final project? Here is the cool thing I did and here is how it works.
    • Make a final project video! (helps but not required)
    Focus on well-integrated device!

Review of Week 12 User Interfaces

  • Claire Wang: Music play and Windows 3.1 interface works!
  • Ryan Hoffman: DRV8251A discussion, heat sinks, breakout boards. Wildcards with waterjetting, EDM, multi-axis machining, laser cutting metal. Class in the spring on nature of mathematical modeling.
  • Srikanth Nadhamuni: Background and experience to visiting fellow at MIT. Raspberry Pi W for WiFi, n8n for cloud LLM data crunching. Software: Node.js, MCP bridge server with n8n based on bridge connected to device (NGV tunnel). All set! Fantastic experience, haven't worked so hard in a very long time and learning a lot of new things. Hope to take forward and build other systems. The whole culture of doing and trying yourself fascinating, especially with failing a number of times until you figure it out. Maybe set one up at an IIT in India or AI centers of excellence with education ministry into the Indian education system (see fablabkerala.in or vigyam ashram).
  • Ray Song: Not here.
  • Tyler Jensen (Lincoln Lab, Group 81): Final project discussion (nylon printer). Week 13: Easy for web serial interface for XIAO! Web server to TFT (I think I forgot to load the camera pins with my code for it).
  • Aditi Ramakrishnan: Sloan MBA and strategy consulting background. Discrete time filter (FFT is blown) in skimage.filters — make a bandpass filter, then run a series of these filters, much less computing only adds and multiplies for filtering in realtime.
  • Alexandros Gravalos: Not here.
  • Edward Chen: Check final watch project by Gulati into watch form factor. Clear print on the Form Labs printer, 0.1. Kaman filter for sensor fusion (in the spring class). For position — LSM6DSV16X from input devices. Acceleration at 7 kHz (at audio frequency).

Show and Tell

  • Handle to sensor WiFi user interface
  • Plug to audio LLM user interface

System Integration Reminders

  • Mount electronics
  • Strain relief the final projects

Preview for Wildcard Week

Assignment: Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment.

Recitation Notes: Why Make (Almost) Anything

Recitation exploring the purpose, impact, and scaling of fabrication labs and making infrastructure.

Map of Fab Labs

Why Make a Fab Lab?

  • Used to create a community
  • Building things for the community
  • Sustainability
  • Prototyping quickly

How Impact?

  • How to make spaces: How to measure impact. What is important about fab:
    • Fablabs in cities vs rural areas: The ability to decide their own futures and change their lives fundamentally. 'Safecast revolutionized citizen science' e.g. radiation map.
    • Bringing back manufacturing: Reducing reliance on supply chains.
    • Rural sustainability: Working with indigenous communities on creating technologies themselves at scale and measure their usefulness and efficacy to preserve their ancestral knowledge:
      • How to establish labs there
      • How to make sure the labs get used
    • Hygiene technologies with Proctor and Gamble: Highly commercial. Lots of plastic waste. How can we change how they produce? How to make their products get there through resellers?
    • Trip to Peru and ran workshops, questionnaires, analysis: Collaboration developed into how to produce the products but also how to test their products to be market valuable e.g. mosquito repellents. Out of three plants, two worked better and one wasn't working at all (which is important to know!).

What Does It Mean to Design Infrastructure?

  • What did we want this lab to be able to do?
    • Workshops and questionnaires
    • How much you educate people based on the info they have with the issues the community is facing
    • Energy concerns to consider, some machines just drain the grid and can't be used. Solar powered, battery powered machines, reducing energy consumption of machines. Many concerns important.
  • Ethical questions
  • How to maintain resources

Case Study: Water Purifier Packets

Use them, change them, source them locally, ingredients found locally, how to distribute them globally.

Funding Models

First few fablabs were NSF funded. Now corporate CSR, regional funding, labor funding (10 different ways). Successful fablabs are heterogeneous with lots of ways of funding. The ones that fail usually just have one sponsor.

Example: DIY Raman spectrometer for water purification (even after purifications still have sulfates and improving that too).

What Does It Mean to Scale Infrastructure?

(Besides a lot of meetings!) What is a reasonable way to design a data collection process about what is needed and how to achieve it.

Back to the Map: Expansion

Timeline of development, cocreation, portable, skin analysis, water testing, biomaterial tech, microscopy.

Initial Results from Boston

How to Confront Local Impact
  • Collab with University of Hamburg. Motivation for how much food can be produced in Boston. Where food waste goes and what Boston produces locally. Make things for yourself locally.
  • Impact directly in the community you're living in.

Hatchspace

Focused on rehabilitation of addicts with woodworking. (Vermont is wood producing state).

Example Course Program

  • All-in session and systemic impact
  • Natural and cultural context
  • Skills and workshop
  • Economic vitality
  • Skills and workshop
  • Co-work session
  • Solutionspalooza

In the Course

Hands-on component (no physical robot exists that can do it) and community component is also important. Inclusion is important. Solving unconscious and institutional biases.

  • 'Fabrica! Lab' — Creating new laboratory spaces for female high school students, courses aimed for women in technology, online advising sessions for females interested in tech.
  • Makerspaces — Access to tools behind closed doors at universities, makes a huge difference for people who don't have the ability to prototype for themselves.
  • Materiom — Fablab affiliated project on organic waste for biomaterials.
  • Fablab León
  • Skylab workshop experiment — How to run a noodle shop out of a fablab (creating food from the community).
  • Academany — Global distributed campus for high school education. Fablab all-in (belonging, impact, community), fab futures (future vocational skills), bio academy (synthetic biology), fabricademy (textiles, fab, bio), fab academy (digital fab apps and implications).

Trade-off Between Impactful and Dangerous

People could be doing bad, but not because doing it with a group people with values.

Questions

Clarification: Adding infrastructure to existing fablab infrastructure to help support specific community needs (not specialized fab labs).

Foundations for Fab Futures

July 27-31, 2026 at Fab Boston 2026.

Useful Documentation

Essential resources for wildcard week digital fabrication processes and PCB design.

Class Page

Wildcard Week - MIT Academy

Comprehensive resource covering wildcard week assignment requirements and possibilities including grinding, multi-axis machining, electrical discharge machining, waterjet cutting, flatbed cutting, plasma cutting, laser metal cutting, laser micromachining, welding, molding and casting, folding, robotics, electronics, embedded programming, food, materials, biotechnology, textiles, and composites.

Key Topics

  • Machining: Grinding, multi-axis machining, electrical discharge machining, waterjet cutting, plasma cutting, laser metal cutting, laser micromachining
  • Molding & Casting: Vacuum forming, rotocasting
  • Folding: Mathematics, form and function, kirigami
  • Robotics: Arms, construction, soft actuation pneumatic inflatable
  • Electronics: Pick and place, programmable logic
  • Embedded Programming: Machine learning, machine vision
  • Textiles: Fiber processes, knitting, embroidery (PEmbroider, Ink/Stitch), Fabricademy
  • Composites: Various composite fabrication techniques

ATtiny1626 Development Board References

Embedded Programming Course Resources

Course resources for embedded programming with ATtiny412 microcontroller examples:

Embedded Programming - MIT Academy

ATtiny412 Echo Example Image

Assignment: PCB Engraving with Fiber Laser

Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment. This assignment demonstrates PCB design and fabrication using a combination of CNC milling (Carvera) for edge cuts and hole machining, and fiber laser engraving (xTool F2 Ultra) for trace creation on copper-clad boards. The project includes designing and fabricating two development boards: a simple ATtiny1626 development board and a complex RP2354A development board.

PCB Engraving Process

This project explores PCB fabrication using fiber laser engraving, a process not covered in previous assignments. The workflow combines subtractive manufacturing techniques: CNC milling for mechanical features (edge cuts and holes) and laser engraving for electrical traces. This approach enables rapid prototyping of custom PCBs without requiring chemical etching or specialized PCB manufacturing facilities.

Tools and Equipment

  • Carvera (CNC Mill): Used for edge cuts and hole machining. The laser cannot effectively cut through the board material, so mechanical cutting is required for board outline and mounting holes.
  • Fiber Laser Cutter (xTool F2 Ultra): Used for PCB trace engraving. The laser removes copper from the board surface to create electrical traces and pads.
  • PCB Design Software (KiCad): Used for schematic capture, PCB layout, and design rule checking.

Boards Designed

  • Simple Board: ATtiny1626 development board with connectors, resistors, LED, and capacitor
  • Complex Board: RP2354A development board with more advanced routing and component placement

Board Design Considerations

  • Connector Placement: Top and bottom for connectors, right side for flashing. Connectors along edges to minimize form factor and maximize space usage.
  • Vertical Connectors: Used instead of horizontal connectors because horizontal connectors risk being snapped during use.
  • Black Area Avoidance: Avoid large black areas because laser does not work well with that (keep traces closer and further to minimize black areas). Note: Need to characterize maximum black until it burns the board because dumping too much heat in one place can damage the board.
  • Breadboard Compatibility: Put connectors on 100mil spacing grid size for breadboardability.
  • Pin Count Adjustment: Missed six pins in initial design, so switched from 6-pin headers to 9-pin (distributed six on top and bottom).
  • I2C Resistors: No SDA or SCL resistors included to keep flexibility for future use. May add spot for zero-ohm or pull-up resistor later but keeping it simple for now.
  • Mounting Holes: Added aligned mounting holes (M3 usually — for 3mm screws) for mechanical mounting.
  • Rounded Edge Cuts: Do 90 degrees, copy, drag, and complete the shape for rounded corners.

Design Rules

  • 0.1 mm spacing minimum
  • 0.15 mm trace width minimum
  • 0.15 mm clearance between plane and the rest

Ports and Pins

ATtiny1626 is an 8-bit microcontroller with 8 pins maximum per port. Each port has 8 pins maximum (some less). Need to specify port letter and pin number:

  • PA (0-7)
  • PB (0-7)
  • PC (0-7)

Postprocessing

  • For Carvera: Add new layer with just the holes in Photoshop (only holes for machining).
  • For Laser Engraving: Get rid of the holes for the F2 tools engraving in Inkscape (the frame and the board for alignment, then only engrave the board, not the edges).

Carvera Machining

Using mods → mill 2D PCB workflow:

  • 0.12mm cut depth and max depth

PCB Engraving Process

Using xTool F2 Ultra fiber laser:

  • Use tape for laser alignment
  • Run a test first on spare copper before the Carvera cut board to make sure focus is good (2.7mm thickness setting worked, board is actually 1.6-1.7mm thick)
  • Sand after engraving to clean up any residue
  • Worked with Bantam Tools FR1 (not random Amazon copper)
  • Perform short circuit test after engraving

Soldering

Using solder gun (heat gun) for component assembly.

Components

  • 1x 6-pin flipflop headers
  • 2x 9-pin flipflop headers
  • 1x 4.7k resistor
  • 1x 1k resistor
  • 1x LED
  • 1x 1uF or 10uF capacitor

Design Files

Download design files: ATtiny_QFN.zip and RP2354A-dev-v1.1.zip

Final ATtiny1626 development board design showing component placement and routing
ATtiny1626 final designComplete PCB layout with connectors, components, traces, and mounting holes optimized for laser engraving.
ATtiny1626 development board after fiber laser engraving showing copper traces
PCB after engravingCopper-clad board with traces engraved using fiber laser, ready for component soldering.
Fully assembled ATtiny1626 development board with all components soldered
Soldered boardComplete ATtiny1626 development board with headers, resistors, LED, and capacitor soldered in place.
Blinking LED demoVideo demonstration of the completed ATtiny1626 development board running a simple LED blink program, confirming successful fabrication and programming.
Close-up detail of PCB engraving showing trace quality and copper removal
PCB engraving detailClose-up view of fiber laser engraved traces showing clean copper removal and precise trace definition.

Interface with User

The application interfaces a user with input and/or output devices through the ATtiny1626 development board. The following table describes how the application interfaces with the user:

How It Interfaces with User Input Device(s) Output Device(s)
(a) LED Blink Demonstration None (programmed behavior) LED (visual feedback indicating board functionality)
(b) Future Interface Applications GPIO pins (PA, PB, PC ports) available for sensors, buttons, switches GPIO pins (PA, PB, PC ports) available for LEDs, displays, actuators

Wildcard Assignments: Wildcard Week Digital Process

Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment. This group assignment explores various digital fabrication processes available during wildcard week.

Wildcard Week Possibilities

The wildcard week assignment allows exploration of digital fabrication processes not covered in previous weeks. Possibilities include (but are not limited to):

Machining

  • Grinding
  • Multi-axis machining
  • Electrical discharge machining (EDM)
  • Waterjet cutting
  • Flatbed cutting
  • Plasma cutting
  • Laser metal cutting
  • Laser micromachining

Welding

Various welding techniques for joining materials.

Molding and Casting

  • Vacuum forming
  • Rotocasting

Folding

  • Mathematics
  • Form and function
  • Kirigami

Robotics

  • Arms
  • Construction
  • Soft actuation pneumatic inflatable

Electronics

  • Pick and place
  • Programmable logic

Embedded Programming

  • Machine learning
  • Machine vision

Food

  • Printing
  • Gastronomy

Materials

  • Synthesis
  • Mechanical
  • Rheological

Biotechnology

  • DIYbio
  • iGEM
  • HTGAA
  • Bio Academy

Textiles

  • Fiber processes
  • Knitting
  • Embroidery (PEmbroider, Ink/Stitch)
  • Fabricademy

Composites

Various composite fabrication techniques.

Design Files

Design files for PCB engraving projects including ATtiny1626 and RP2354A development boards.

ATtiny1626 Development Board

Simple development board for ATtiny1626 microcontroller with connectors, resistors, LED, and capacitor. Designed for breadboard compatibility with 100mil spacing grid.

Initial ATtiny1626 development board design
Initial designFirst iteration of ATtiny1626 development board layout.
Final ATtiny1626 development board design with all components
Final designComplete ATtiny1626 development board with connectors, mounting holes, and optimized trace routing.

Download Design Files

  • ATtiny_QFN.zip — Complete KiCad project files for ATtiny1626 development board

RP2354A Development Board

Complex development board for RP2354A microcontroller with advanced routing and component placement.

RP2354A development board design
RP2354A board designComplete PCB layout for RP2354A development board with complex routing and component placement.

Download Design Files

Reflections & Learnings

Key insights and learnings from working with interface and application programming.

Contributions

Acknowledgements and team roles for wildcard week PCB engraving work.

Wildcard Week Session

  • Quentin and Anthony: Ran the wildcard week session, providing guidance and support for PCB engraving projects.
  • Quentin: Designed the RP2354A development board before the session and finished the ATtiny1626 design with us during the wildcard session.

Ethical AI Use

Transparent documentation of AI assistance used in this week's wildcard week assignment page creation.

Week 13 Assignment Page Creation

Complete Cursor AI transcript for Week 13 wildcard week assignment page creation. This comprehensive conversation covers the creation and population of the Week 13 HTML page, including lecture and recitation notes, PCB engraving assignment documentation, design files integration, and comprehensive page structure development. The transcript demonstrates the collaborative process of building professional documentation with structured content, embedded media, and comprehensive design file documentation.

Related to: Complete Week 13 documentation including Lecture Notes, Recitation Notes, Assignment, Group Assignment, Design Files, and overall page structure

View HTML Transcript Download Markdown Transcript

Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License

``` ```html Week 13 · Wildcard Week
← Back to Home
[Profile Image Placeholder]

Week 13

Wildcard Week

Week Highlights

Key captures from the PCB engraving assignment with links to their sections.

ATtiny1626 Board Design

Final ATtiny1626 development board design with connectors and mounting holes

PCB Engraving

ATtiny1626 development board after fiber laser engraving

Soldered Board

Fully assembled ATtiny1626 development board with all components soldered

Blinking LED Demo

RP2354A Board Design

RP2354A development board design

PCB Engraving Detail

Close-up detail of PCB engraving showing trace quality

Table of Contents

Course Content

Training & Documentation

Assignments & Projects

Wildcard Week

This week focuses on exploring digital fabrication processes not covered in previous assignments. We'll design and produce something using computer-aided design and manufacturing, documenting requirements and including everything necessary for reproduction. This week also includes reflection on the impact and purpose of making (almost) anything.

Exploring new digital fabrication processes
Designing and producing with CAD/CAM
Understanding the impact and purpose of fabrication labs

This Week's Goals

  • Explore New Processes
    Design and produce something with a digital process not covered in other assignments
  • Complete Documentation
    Document requirements and include everything necessary to reproduce the project
  • Reflect on Impact
    Understand the purpose and impact of fabrication labs and making

Assignments

  • Wildcard Assignments
    Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment
  • Assignment
    Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment, documenting the requirements that your assignment meets, and including everything necessary to reproduce it

Tools & Materials

  • Carvera (CNC Mill) — Edge cuts and hole machining
  • Fiber Laser Cutter (xTool F2 Ultra) — PCB engraving
  • PCB Design Software (KiCad) — Board layout and design
  • ATtiny1626 Microcontroller — Target device for development board
  • RP2354A Microcontroller — Complex board design

Lecture Notes

Week 13 lecture covering major announcements, week 12 review, system integration reminders, and wildcard week preview.

Theme of the Week

'Step away from the panic'

Major Announcements

  • Subject evaluation: Required for funding the class. Provides feedback to the institute about the class. Important for future students if you care about successors in the class.
  • Calendar alarm: Wildcard week and recitation on why make (almost) anything: impact. Friday is cutoff for assignments and orders (10s of dollars per person from inventory).
  • Final presentation/final exam: Combining multiple additive and subtractive processes (not just design a board and 3D print a case). Goal is system integration out of parts. Final exam criteria:
    • Did you integrate and design a complete system?
    • Can you demo a final project? Here is the cool thing I did and here is how it works.
    • Make a final project video! (helps but not required)
    Focus on well-integrated device!

Review of Week 12 User Interfaces

  • Claire Wang: Music play and Windows 3.1 interface works!
  • Ryan Hoffman: DRV8251A discussion, heat sinks, breakout boards. Wildcards with waterjetting, EDM, multi-axis machining, laser cutting metal. Class in the spring on nature of mathematical modeling.
  • Srikanth Nadhamuni: Background and experience to visiting fellow at MIT. Raspberry Pi W for WiFi, n8n for cloud LLM data crunching. Software: Node.js, MCP bridge server with n8n based on bridge connected to device (NGV tunnel). All set! Fantastic experience, haven't worked so hard in a very long time and learning a lot of new things. Hope to take forward and build other systems. The whole culture of doing and trying yourself fascinating, especially with failing a number of times until you figure it out. Maybe set one up at an IIT in India or AI centers of excellence with education ministry into the Indian education system (see fablabkerala.in or vigyam ashram).
  • Ray Song: Not here.
  • Tyler Jensen (Lincoln Lab, Group 81): Final project discussion (nylon printer). Week 13: Easy for web serial interface for XIAO! Web server to TFT (I think I forgot to load the camera pins with my code for it).
  • Aditi Ramakrishnan: Sloan MBA and strategy consulting background. Discrete time filter (FFT is blown) in skimage.filters — make a bandpass filter, then run a series of these filters, much less computing only adds and multiplies for filtering in realtime.
  • Alexandros Gravalos: Not here.
  • Edward Chen: Check final watch project by Gulati into watch form factor. Clear print on the Form Labs printer, 0.1. Kaman filter for sensor fusion (in the spring class). For position — LSM6DSV16X from input devices. Acceleration at 7 kHz (at audio frequency).

Show and Tell

  • Handle to sensor WiFi user interface
  • Plug to audio LLM user interface

System Integration Reminders

  • Mount electronics
  • Strain relief the final projects

Preview for Wildcard Week

Assignment: Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment.

Recitation Notes: Why Make (Almost) Anything

Recitation exploring the purpose, impact, and scaling of fabrication labs and making infrastructure.

Map of Fab Labs

Why Make a Fab Lab?

  • Used to create a community
  • Building things for the community
  • Sustainability
  • Prototyping quickly

How Impact?

  • How to make spaces: How to measure impact. What is important about fab:
    • Fablabs in cities vs rural areas: The ability to decide their own futures and change their lives fundamentally. 'Safecast revolutionized citizen science' e.g. radiation map.
    • Bringing back manufacturing: Reducing reliance on supply chains.
    • Rural sustainability: Working with indigenous communities on creating technologies themselves at scale and measure their usefulness and efficacy to preserve their ancestral knowledge:
      • How to establish labs there
      • How to make sure the labs get used
    • Hygiene technologies with Proctor and Gamble: Highly commercial. Lots of plastic waste. How can we change how they produce? How to make their products get there through resellers?
    • Trip to Peru and ran workshops, questionnaires, analysis: Collaboration developed into how to produce the products but also how to test their products to be market valuable e.g. mosquito repellents. Out of three plants, two worked better and one wasn't working at all (which is important to know!).

What Does It Mean to Design Infrastructure?

  • What did we want this lab to be able to do?
    • Workshops and questionnaires
    • How much you educate people based on the info they have with the issues the community is facing
    • Energy concerns to consider, some machines just drain the grid and can't be used. Solar powered, battery powered machines, reducing energy consumption of machines. Many concerns important.
  • Ethical questions
  • How to maintain resources

Case Study: Water Purifier Packets

Use them, change them, source them locally, ingredients found locally, how to distribute them globally.

Funding Models

First few fablabs were NSF funded. Now corporate CSR, regional funding, labor funding (10 different ways). Successful fablabs are heterogeneous with lots of ways of funding. The ones that fail usually just have one sponsor.

Example: DIY Raman spectrometer for water purification (even after purifications still have sulfates and improving that too).

What Does It Mean to Scale Infrastructure?

(Besides a lot of meetings!) What is a reasonable way to design a data collection process about what is needed and how to achieve it.

Back to the Map: Expansion

Timeline of development, cocreation, portable, skin analysis, water testing, biomaterial tech, microscopy.

Initial Results from Boston

How to Confront Local Impact
  • Collab with University of Hamburg. Motivation for how much food can be produced in Boston. Where food waste goes and what Boston produces locally. Make things for yourself locally.
  • Impact directly in the community you're living in.

Hatchspace

Focused on rehabilitation of addicts with woodworking. (Vermont is wood producing state).

Example Course Program

  • All-in session and systemic impact
  • Natural and cultural context
  • Skills and workshop
  • Economic vitality
  • Skills and workshop
  • Co-work session
  • Solutionspalooza

In the Course

Hands-on component (no physical robot exists that can do it) and community component is also important. Inclusion is important. Solving unconscious and institutional biases.

  • 'Fabrica! Lab' — Creating new laboratory spaces for female high school students, courses aimed for women in technology, online advising sessions for females interested in tech.
  • Makerspaces — Access to tools behind closed doors at universities, makes a huge difference for people who don't have the ability to prototype for themselves.
  • Materiom — Fablab affiliated project on organic waste for biomaterials.
  • Fablab León
  • Skylab workshop experiment — How to run a noodle shop out of a fablab (creating food from the community).
  • Academany — Global distributed campus for high school education. Fablab all-in (belonging, impact, community), fab futures (future vocational skills), bio academy (synthetic biology), fabricademy (textiles, fab, bio), fab academy (digital fab apps and implications).

Trade-off Between Impactful and Dangerous

People could be doing bad, but not because doing it with a group people with values.

Questions

Clarification: Adding infrastructure to existing fablab infrastructure to help support specific community needs (not specialized fab labs).

Foundations for Fab Futures

July 27-31, 2026 at Fab Boston 2026.

Useful Documentation

Essential resources for wildcard week digital fabrication processes and PCB design.

Class Page

Wildcard Week - MIT Academy

Comprehensive resource covering wildcard week assignment requirements and possibilities including grinding, multi-axis machining, electrical discharge machining, waterjet cutting, flatbed cutting, plasma cutting, laser metal cutting, laser micromachining, welding, molding and casting, folding, robotics, electronics, embedded programming, food, materials, biotechnology, textiles, and composites.

Key Topics

  • Machining: Grinding, multi-axis machining, electrical discharge machining, waterjet cutting, plasma cutting, laser metal cutting, laser micromachining
  • Molding & Casting: Vacuum forming, rotocasting
  • Folding: Mathematics, form and function, kirigami
  • Robotics: Arms, construction, soft actuation pneumatic inflatable
  • Electronics: Pick and place, programmable logic
  • Embedded Programming: Machine learning, machine vision
  • Textiles: Fiber processes, knitting, embroidery (PEmbroider, Ink/Stitch), Fabricademy
  • Composites: Various composite fabrication techniques

ATtiny1626 Development Board References

Embedded Programming Course Resources

Course resources for embedded programming with ATtiny412 microcontroller examples:

Embedded Programming - MIT Academy

ATtiny412 Echo Example Image

Assignment: PCB Engraving with Fiber Laser

Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment. This assignment demonstrates PCB design and fabrication using a combination of CNC milling (Carvera) for edge cuts and hole machining, and fiber laser engraving (xTool F2 Ultra) for trace creation on copper-clad boards. The project includes designing and fabricating two development boards: a simple ATtiny1626 development board and a complex RP2354A development board.

PCB Engraving Process

This project explores PCB fabrication using fiber laser engraving, a process not covered in previous assignments. The workflow combines subtractive manufacturing techniques: CNC milling for mechanical features (edge cuts and holes) and laser engraving for electrical traces. This approach enables rapid prototyping of custom PCBs without requiring chemical etching or specialized PCB manufacturing facilities.

Tools and Equipment

  • Carvera (CNC Mill): Used for edge cuts and hole machining. The laser cannot effectively cut through the board material, so mechanical cutting is required for board outline and mounting holes.
  • Fiber Laser Cutter (xTool F2 Ultra): Used for PCB trace engraving. The laser removes copper from the board surface to create electrical traces and pads.
  • PCB Design Software (KiCad): Used for schematic capture, PCB layout, and design rule checking.

Boards Designed

  • Simple Board: ATtiny1626 development board with connectors, resistors, LED, and capacitor
  • Complex Board: RP2354A development board with more advanced routing and component placement

Board Design Considerations

  • Connector Placement: Top and bottom for connectors, right side for flashing. Connectors along edges to minimize form factor and maximize space usage.
  • Vertical Connectors: Used instead of horizontal connectors because horizontal connectors risk being snapped during use.
  • Black Area Avoidance: Avoid large black areas because laser does not work well with that (keep traces closer and further to minimize black areas). Note: Need to characterize maximum black until it burns the board because dumping too much heat in one place can damage the board.
  • Breadboard Compatibility: Put connectors on 100mil spacing grid size for breadboardability.
  • Pin Count Adjustment: Missed six pins in initial design, so switched from 6-pin headers to 9-pin (distributed six on top and bottom).
  • I2C Resistors: No SDA or SCL resistors included to keep flexibility for future use. May add spot for zero-ohm or pull-up resistor later but keeping it simple for now.
  • Mounting Holes: Added aligned mounting holes (M3 usually — for 3mm screws) for mechanical mounting.
  • Rounded Edge Cuts: Do 90 degrees, copy, drag, and complete the shape for rounded corners.

Design Rules

  • 0.1 mm spacing minimum
  • 0.15 mm trace width minimum
  • 0.15 mm clearance between plane and the rest

Ports and Pins

ATtiny1626 is an 8-bit microcontroller with 8 pins maximum per port. Each port has 8 pins maximum (some less). Need to specify port letter and pin number:

  • PA (0-7)
  • PB (0-7)
  • PC (0-7)

Postprocessing

  • For Carvera: Add new layer with just the holes in Photoshop (only holes for machining).
  • For Laser Engraving: Get rid of the holes for the F2 tools engraving in Inkscape (the frame and the board for alignment, then only engrave the board, not the edges).

Carvera Machining

Using mods → mill 2D PCB workflow:

  • 0.12mm cut depth and max depth

PCB Engraving Process

Using xTool F2 Ultra fiber laser:

  • Use tape for laser alignment
  • Run a test first on spare copper before the Carvera cut board to make sure focus is good (2.7mm thickness setting worked, board is actually 1.6-1.7mm thick)
  • Sand after engraving to clean up any residue
  • Worked with Bantam Tools FR1 (not random Amazon copper)
  • Perform short circuit test after engraving

Soldering

Using solder gun (heat gun) for component assembly.

Components

  • 1x 6-pin flipflop headers
  • 2x 9-pin flipflop headers
  • 1x 4.7k resistor
  • 1x 1k resistor
  • 1x LED
  • 1x 1uF or 10uF capacitor

Design Files

Download design files: ATtiny_QFN.zip and RP2354A-dev-v1.1.zip

Final ATtiny1626 development board design showing component placement and routing
ATtiny1626 final designComplete PCB layout with connectors, components, traces, and mounting holes optimized for laser engraving.
ATtiny1626 development board after fiber laser engraving showing copper traces
PCB after engravingCopper-clad board with traces engraved using fiber laser, ready for component soldering.
Fully assembled ATtiny1626 development board with all components soldered
Soldered boardComplete ATtiny1626 development board with headers, resistors, LED, and capacitor soldered in place.
Blinking LED demoVideo demonstration of the completed ATtiny1626 development board running a simple LED blink program, confirming successful fabrication and programming.
Close-up detail of PCB engraving showing trace quality and copper removal
PCB engraving detailClose-up view of fiber laser engraved traces showing clean copper removal and precise trace definition.

Interface with User

The application interfaces a user with input and/or output devices through the ATtiny1626 development board. The following table describes how the application interfaces with the user:

How It Interfaces with User Input Device(s) Output Device(s)
(a) LED Blink Demonstration None (programmed behavior) LED (visual feedback indicating board functionality)
(b) Future Interface Applications GPIO pins (PA, PB, PC ports) available for sensors, buttons, switches GPIO pins (PA, PB, PC ports) available for LEDs, displays, actuators

Wildcard Assignments: Wildcard Week Digital Process

Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment. This group assignment explores various digital fabrication processes available during wildcard week.

Wildcard Week Possibilities

The wildcard week assignment allows exploration of digital fabrication processes not covered in previous weeks. Possibilities include (but are not limited to):

Machining

  • Grinding
  • Multi-axis machining
  • Electrical discharge machining (EDM)
  • Waterjet cutting
  • Flatbed cutting
  • Plasma cutting
  • Laser metal cutting
  • Laser micromachining

Welding

Various welding techniques for joining materials.

Molding and Casting

  • Vacuum forming
  • Rotocasting

Folding

  • Mathematics
  • Form and function
  • Kirigami

Robotics

  • Arms
  • Construction
  • Soft actuation pneumatic inflatable

Electronics

  • Pick and place
  • Programmable logic

Embedded Programming

  • Machine learning
  • Machine vision

Food

  • Printing
  • Gastronomy

Materials

  • Synthesis
  • Mechanical
  • Rheological

Biotechnology

  • DIYbio
  • iGEM
  • HTGAA
  • Bio Academy

Textiles

  • Fiber processes
  • Knitting
  • Embroidery (PEmbroider, Ink/Stitch)
  • Fabricademy

Composites

Various composite fabrication techniques.

Design Files

Design files for PCB engraving projects including ATtiny1626 and RP2354A development boards.

ATtiny1626 Development Board

Simple development board for ATtiny1626 microcontroller with connectors, resistors, LED, and capacitor. Designed for breadboard compatibility with 100mil spacing grid.

Initial ATtiny1626 development board design
Initial designFirst iteration of ATtiny1626 development board layout.
Final ATtiny1626 development board design with all components
Final designComplete ATtiny1626 development board with connectors, mounting holes, and optimized trace routing.

Download Design Files

  • ATtiny_QFN.zip — Complete KiCad project files for ATtiny1626 development board

RP2354A Development Board

Complex development board for RP2354A microcontroller with advanced routing and component placement.

RP2354A development board design
RP2354A board designComplete PCB layout for RP2354A development board with complex routing and component placement.

Download Design Files

Reflections & Learnings

Key insights and learnings from working with interface and application programming.

Contributions

Acknowledgements and team roles for wildcard week PCB engraving work.

Wildcard Week Session

  • Quentin and Anthony: Ran the wildcard week session, providing guidance and support for PCB engraving projects.
  • Quentin: Designed the RP2354A development board before the session and finished the ATtiny1626 design with us during the wildcard session.

Ethical AI Use

Transparent documentation of AI assistance used in this week's wildcard week assignment page creation.

Week 13 Assignment Page Creation

Complete Cursor AI transcript for Week 13 wildcard week assignment page creation. This comprehensive conversation covers the creation and population of the Week 13 HTML page, including lecture and recitation notes, PCB engraving assignment documentation, design files integration, and comprehensive page structure development. The transcript demonstrates the collaborative process of building professional documentation with structured content, embedded media, and comprehensive design file documentation.

Related to: Complete Week 13 documentation including Lecture Notes, Recitation Notes, Assignment, Group Assignment, Design Files, and overall page structure

View HTML Transcript Download Markdown Transcript

Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License

``` Checking for linting errors: Added whitespace above and below the two highlights and adjusted the images to show the full image. Changes: 1. **Added margin** — Added `margin-top:12px; margin-bottom:12px;` to both container divs for spacing above and below 2. **Increased heading spacing** — Changed the h4 margin-bottom from `8px` to `12px` for more space between the heading and image 3. **Added padding** — Added `padding:12px;` to the image containers for internal spacing 4. **Show full image** — Changed from `height:140px; object-fit:cover;` to `height:auto; object-fit:contain;` so the full image is visible without cropping Both the "ATtiny1626 Board Design" and "RP2354A Board Design" highlights now have more whitespace and display the full images without cropping. No linting errors found. --- **User** no keep it the same size as the other highlighs, just put white space around the image to fit it --- **Cursor** Reverting the image size changes and keeping the padding/whitespace around the images: ```html Week 13 · Wildcard Week
← Back to Home
[Profile Image Placeholder]

Week 13

Wildcard Week

Week Highlights

Key captures from the PCB engraving assignment with links to their sections.

ATtiny1626 Board Design

Final ATtiny1626 development board design with connectors and mounting holes

PCB Engraving

ATtiny1626 development board after fiber laser engraving

Soldered Board

Fully assembled ATtiny1626 development board with all components soldered

Blinking LED Demo

RP2354A Board Design

RP2354A development board design

PCB Engraving Detail

Close-up detail of PCB engraving showing trace quality

Table of Contents

Course Content

Training & Documentation

Assignments & Projects

Wildcard Week

This week focuses on exploring digital fabrication processes not covered in previous assignments. We'll design and produce something using computer-aided design and manufacturing, documenting requirements and including everything necessary for reproduction. This week also includes reflection on the impact and purpose of making (almost) anything.

Exploring new digital fabrication processes
Designing and producing with CAD/CAM
Understanding the impact and purpose of fabrication labs

This Week's Goals

  • Explore New Processes
    Design and produce something with a digital process not covered in other assignments
  • Complete Documentation
    Document requirements and include everything necessary to reproduce the project
  • Reflect on Impact
    Understand the purpose and impact of fabrication labs and making

Assignments

  • Wildcard Assignments
    Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment
  • Assignment
    Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment, documenting the requirements that your assignment meets, and including everything necessary to reproduce it

Tools & Materials

  • Carvera (CNC Mill) — Edge cuts and hole machining
  • Fiber Laser Cutter (xTool F2 Ultra) — PCB engraving
  • PCB Design Software (KiCad) — Board layout and design
  • ATtiny1626 Microcontroller — Target device for development board
  • RP2354A Microcontroller — Complex board design

Lecture Notes

Week 13 lecture covering major announcements, week 12 review, system integration reminders, and wildcard week preview.

Theme of the Week

'Step away from the panic'

Major Announcements

  • Subject evaluation: Required for funding the class. Provides feedback to the institute about the class. Important for future students if you care about successors in the class.
  • Calendar alarm: Wildcard week and recitation on why make (almost) anything: impact. Friday is cutoff for assignments and orders (10s of dollars per person from inventory).
  • Final presentation/final exam: Combining multiple additive and subtractive processes (not just design a board and 3D print a case). Goal is system integration out of parts. Final exam criteria:
    • Did you integrate and design a complete system?
    • Can you demo a final project? Here is the cool thing I did and here is how it works.
    • Make a final project video! (helps but not required)
    Focus on well-integrated device!

Review of Week 12 User Interfaces

  • Claire Wang: Music play and Windows 3.1 interface works!
  • Ryan Hoffman: DRV8251A discussion, heat sinks, breakout boards. Wildcards with waterjetting, EDM, multi-axis machining, laser cutting metal. Class in the spring on nature of mathematical modeling.
  • Srikanth Nadhamuni: Background and experience to visiting fellow at MIT. Raspberry Pi W for WiFi, n8n for cloud LLM data crunching. Software: Node.js, MCP bridge server with n8n based on bridge connected to device (NGV tunnel). All set! Fantastic experience, haven't worked so hard in a very long time and learning a lot of new things. Hope to take forward and build other systems. The whole culture of doing and trying yourself fascinating, especially with failing a number of times until you figure it out. Maybe set one up at an IIT in India or AI centers of excellence with education ministry into the Indian education system (see fablabkerala.in or vigyam ashram).
  • Ray Song: Not here.
  • Tyler Jensen (Lincoln Lab, Group 81): Final project discussion (nylon printer). Week 13: Easy for web serial interface for XIAO! Web server to TFT (I think I forgot to load the camera pins with my code for it).
  • Aditi Ramakrishnan: Sloan MBA and strategy consulting background. Discrete time filter (FFT is blown) in skimage.filters — make a bandpass filter, then run a series of these filters, much less computing only adds and multiplies for filtering in realtime.
  • Alexandros Gravalos: Not here.
  • Edward Chen: Check final watch project by Gulati into watch form factor. Clear print on the Form Labs printer, 0.1. Kaman filter for sensor fusion (in the spring class). For position — LSM6DSV16X from input devices. Acceleration at 7 kHz (at audio frequency).

Show and Tell

  • Handle to sensor WiFi user interface
  • Plug to audio LLM user interface

System Integration Reminders

  • Mount electronics
  • Strain relief the final projects

Preview for Wildcard Week

Assignment: Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment.

Recitation Notes: Why Make (Almost) Anything

Recitation exploring the purpose, impact, and scaling of fabrication labs and making infrastructure.

Map of Fab Labs

Why Make a Fab Lab?

  • Used to create a community
  • Building things for the community
  • Sustainability
  • Prototyping quickly

How Impact?

  • How to make spaces: How to measure impact. What is important about fab:
    • Fablabs in cities vs rural areas: The ability to decide their own futures and change their lives fundamentally. 'Safecast revolutionized citizen science' e.g. radiation map.
    • Bringing back manufacturing: Reducing reliance on supply chains.
    • Rural sustainability: Working with indigenous communities on creating technologies themselves at scale and measure their usefulness and efficacy to preserve their ancestral knowledge:
      • How to establish labs there
      • How to make sure the labs get used
    • Hygiene technologies with Proctor and Gamble: Highly commercial. Lots of plastic waste. How can we change how they produce? How to make their products get there through resellers?
    • Trip to Peru and ran workshops, questionnaires, analysis: Collaboration developed into how to produce the products but also how to test their products to be market valuable e.g. mosquito repellents. Out of three plants, two worked better and one wasn't working at all (which is important to know!).

What Does It Mean to Design Infrastructure?

  • What did we want this lab to be able to do?
    • Workshops and questionnaires
    • How much you educate people based on the info they have with the issues the community is facing
    • Energy concerns to consider, some machines just drain the grid and can't be used. Solar powered, battery powered machines, reducing energy consumption of machines. Many concerns important.
  • Ethical questions
  • How to maintain resources

Case Study: Water Purifier Packets

Use them, change them, source them locally, ingredients found locally, how to distribute them globally.

Funding Models

First few fablabs were NSF funded. Now corporate CSR, regional funding, labor funding (10 different ways). Successful fablabs are heterogeneous with lots of ways of funding. The ones that fail usually just have one sponsor.

Example: DIY Raman spectrometer for water purification (even after purifications still have sulfates and improving that too).

What Does It Mean to Scale Infrastructure?

(Besides a lot of meetings!) What is a reasonable way to design a data collection process about what is needed and how to achieve it.

Back to the Map: Expansion

Timeline of development, cocreation, portable, skin analysis, water testing, biomaterial tech, microscopy.

Initial Results from Boston

How to Confront Local Impact
  • Collab with University of Hamburg. Motivation for how much food can be produced in Boston. Where food waste goes and what Boston produces locally. Make things for yourself locally.
  • Impact directly in the community you're living in.

Hatchspace

Focused on rehabilitation of addicts with woodworking. (Vermont is wood producing state).

Example Course Program

  • All-in session and systemic impact
  • Natural and cultural context
  • Skills and workshop
  • Economic vitality
  • Skills and workshop
  • Co-work session
  • Solutionspalooza

In the Course

Hands-on component (no physical robot exists that can do it) and community component is also important. Inclusion is important. Solving unconscious and institutional biases.

  • 'Fabrica! Lab' — Creating new laboratory spaces for female high school students, courses aimed for women in technology, online advising sessions for females interested in tech.
  • Makerspaces — Access to tools behind closed doors at universities, makes a huge difference for people who don't have the ability to prototype for themselves.
  • Materiom — Fablab affiliated project on organic waste for biomaterials.
  • Fablab León
  • Skylab workshop experiment — How to run a noodle shop out of a fablab (creating food from the community).
  • Academany — Global distributed campus for high school education. Fablab all-in (belonging, impact, community), fab futures (future vocational skills), bio academy (synthetic biology), fabricademy (textiles, fab, bio), fab academy (digital fab apps and implications).

Trade-off Between Impactful and Dangerous

People could be doing bad, but not because doing it with a group people with values.

Questions

Clarification: Adding infrastructure to existing fablab infrastructure to help support specific community needs (not specialized fab labs).

Foundations for Fab Futures

July 27-31, 2026 at Fab Boston 2026.

Useful Documentation

Essential resources for wildcard week digital fabrication processes and PCB design.

Class Page

Wildcard Week - MIT Academy

Comprehensive resource covering wildcard week assignment requirements and possibilities including grinding, multi-axis machining, electrical discharge machining, waterjet cutting, flatbed cutting, plasma cutting, laser metal cutting, laser micromachining, welding, molding and casting, folding, robotics, electronics, embedded programming, food, materials, biotechnology, textiles, and composites.

Key Topics

  • Machining: Grinding, multi-axis machining, electrical discharge machining, waterjet cutting, plasma cutting, laser metal cutting, laser micromachining
  • Molding & Casting: Vacuum forming, rotocasting
  • Folding: Mathematics, form and function, kirigami
  • Robotics: Arms, construction, soft actuation pneumatic inflatable
  • Electronics: Pick and place, programmable logic
  • Embedded Programming: Machine learning, machine vision
  • Textiles: Fiber processes, knitting, embroidery (PEmbroider, Ink/Stitch), Fabricademy
  • Composites: Various composite fabrication techniques

ATtiny1626 Development Board References

Embedded Programming Course Resources

Course resources for embedded programming with ATtiny412 microcontroller examples:

Embedded Programming - MIT Academy

ATtiny412 Echo Example Image

Assignment: PCB Engraving with Fiber Laser

Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment. This assignment demonstrates PCB design and fabrication using a combination of CNC milling (Carvera) for edge cuts and hole machining, and fiber laser engraving (xTool F2 Ultra) for trace creation on copper-clad boards. The project includes designing and fabricating two development boards: a simple ATtiny1626 development board and a complex RP2354A development board.

PCB Engraving Process

This project explores PCB fabrication using fiber laser engraving, a process not covered in previous assignments. The workflow combines subtractive manufacturing techniques: CNC milling for mechanical features (edge cuts and holes) and laser engraving for electrical traces. This approach enables rapid prototyping of custom PCBs without requiring chemical etching or specialized PCB manufacturing facilities.

Tools and Equipment

  • Carvera (CNC Mill): Used for edge cuts and hole machining. The laser cannot effectively cut through the board material, so mechanical cutting is required for board outline and mounting holes.
  • Fiber Laser Cutter (xTool F2 Ultra): Used for PCB trace engraving. The laser removes copper from the board surface to create electrical traces and pads.
  • PCB Design Software (KiCad): Used for schematic capture, PCB layout, and design rule checking.

Boards Designed

  • Simple Board: ATtiny1626 development board with connectors, resistors, LED, and capacitor
  • Complex Board: RP2354A development board with more advanced routing and component placement

Board Design Considerations

  • Connector Placement: Top and bottom for connectors, right side for flashing. Connectors along edges to minimize form factor and maximize space usage.
  • Vertical Connectors: Used instead of horizontal connectors because horizontal connectors risk being snapped during use.
  • Black Area Avoidance: Avoid large black areas because laser does not work well with that (keep traces closer and further to minimize black areas). Note: Need to characterize maximum black until it burns the board because dumping too much heat in one place can damage the board.
  • Breadboard Compatibility: Put connectors on 100mil spacing grid size for breadboardability.
  • Pin Count Adjustment: Missed six pins in initial design, so switched from 6-pin headers to 9-pin (distributed six on top and bottom).
  • I2C Resistors: No SDA or SCL resistors included to keep flexibility for future use. May add spot for zero-ohm or pull-up resistor later but keeping it simple for now.
  • Mounting Holes: Added aligned mounting holes (M3 usually — for 3mm screws) for mechanical mounting.
  • Rounded Edge Cuts: Do 90 degrees, copy, drag, and complete the shape for rounded corners.

Design Rules

  • 0.1 mm spacing minimum
  • 0.15 mm trace width minimum
  • 0.15 mm clearance between plane and the rest

Ports and Pins

ATtiny1626 is an 8-bit microcontroller with 8 pins maximum per port. Each port has 8 pins maximum (some less). Need to specify port letter and pin number:

  • PA (0-7)
  • PB (0-7)
  • PC (0-7)

Postprocessing

  • For Carvera: Add new layer with just the holes in Photoshop (only holes for machining).
  • For Laser Engraving: Get rid of the holes for the F2 tools engraving in Inkscape (the frame and the board for alignment, then only engrave the board, not the edges).

Carvera Machining

Using mods → mill 2D PCB workflow:

  • 0.12mm cut depth and max depth

PCB Engraving Process

Using xTool F2 Ultra fiber laser:

  • Use tape for laser alignment
  • Run a test first on spare copper before the Carvera cut board to make sure focus is good (2.7mm thickness setting worked, board is actually 1.6-1.7mm thick)
  • Sand after engraving to clean up any residue
  • Worked with Bantam Tools FR1 (not random Amazon copper)
  • Perform short circuit test after engraving

Soldering

Using solder gun (heat gun) for component assembly.

Components

  • 1x 6-pin flipflop headers
  • 2x 9-pin flipflop headers
  • 1x 4.7k resistor
  • 1x 1k resistor
  • 1x LED
  • 1x 1uF or 10uF capacitor

Design Files

Download design files: ATtiny_QFN.zip and RP2354A-dev-v1.1.zip

Final ATtiny1626 development board design showing component placement and routing
ATtiny1626 final designComplete PCB layout with connectors, components, traces, and mounting holes optimized for laser engraving.
ATtiny1626 development board after fiber laser engraving showing copper traces
PCB after engravingCopper-clad board with traces engraved using fiber laser, ready for component soldering.
Fully assembled ATtiny1626 development board with all components soldered
Soldered boardComplete ATtiny1626 development board with headers, resistors, LED, and capacitor soldered in place.
Blinking LED demoVideo demonstration of the completed ATtiny1626 development board running a simple LED blink program, confirming successful fabrication and programming.
Close-up detail of PCB engraving showing trace quality and copper removal
PCB engraving detailClose-up view of fiber laser engraved traces showing clean copper removal and precise trace definition.

Interface with User

The application interfaces a user with input and/or output devices through the ATtiny1626 development board. The following table describes how the application interfaces with the user:

How It Interfaces with User Input Device(s) Output Device(s)
(a) LED Blink Demonstration None (programmed behavior) LED (visual feedback indicating board functionality)
(b) Future Interface Applications GPIO pins (PA, PB, PC ports) available for sensors, buttons, switches GPIO pins (PA, PB, PC ports) available for LEDs, displays, actuators

Wildcard Assignments: Wildcard Week Digital Process

Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment. This group assignment explores various digital fabrication processes available during wildcard week.

Wildcard Week Possibilities

The wildcard week assignment allows exploration of digital fabrication processes not covered in previous weeks. Possibilities include (but are not limited to):

Machining

  • Grinding
  • Multi-axis machining
  • Electrical discharge machining (EDM)
  • Waterjet cutting
  • Flatbed cutting
  • Plasma cutting
  • Laser metal cutting
  • Laser micromachining

Welding

Various welding techniques for joining materials.

Molding and Casting

  • Vacuum forming
  • Rotocasting

Folding

  • Mathematics
  • Form and function
  • Kirigami

Robotics

  • Arms
  • Construction
  • Soft actuation pneumatic inflatable

Electronics

  • Pick and place
  • Programmable logic

Embedded Programming

  • Machine learning
  • Machine vision

Food

  • Printing
  • Gastronomy

Materials

  • Synthesis
  • Mechanical
  • Rheological

Biotechnology

  • DIYbio
  • iGEM
  • HTGAA
  • Bio Academy

Textiles

  • Fiber processes
  • Knitting
  • Embroidery (PEmbroider, Ink/Stitch)
  • Fabricademy

Composites

Various composite fabrication techniques.

Design Files

Design files for PCB engraving projects including ATtiny1626 and RP2354A development boards.

ATtiny1626 Development Board

Simple development board for ATtiny1626 microcontroller with connectors, resistors, LED, and capacitor. Designed for breadboard compatibility with 100mil spacing grid.

Initial ATtiny1626 development board design
Initial designFirst iteration of ATtiny1626 development board layout.
Final ATtiny1626 development board design with all components
Final designComplete ATtiny1626 development board with connectors, mounting holes, and optimized trace routing.

Download Design Files

  • ATtiny_QFN.zip — Complete KiCad project files for ATtiny1626 development board

RP2354A Development Board

Complex development board for RP2354A microcontroller with advanced routing and component placement.

RP2354A development board design
RP2354A board designComplete PCB layout for RP2354A development board with complex routing and component placement.

Download Design Files

Reflections & Learnings

Key insights and learnings from working with interface and application programming.

Contributions

Acknowledgements and team roles for wildcard week PCB engraving work.

Wildcard Week Session

  • Quentin and Anthony: Ran the wildcard week session, providing guidance and support for PCB engraving projects.
  • Quentin: Designed the RP2354A development board before the session and finished the ATtiny1626 design with us during the wildcard session.

Ethical AI Use

Transparent documentation of AI assistance used in this week's wildcard week assignment page creation.

Week 13 Assignment Page Creation

Complete Cursor AI transcript for Week 13 wildcard week assignment page creation. This comprehensive conversation covers the creation and population of the Week 13 HTML page, including lecture and recitation notes, PCB engraving assignment documentation, design files integration, and comprehensive page structure development. The transcript demonstrates the collaborative process of building professional documentation with structured content, embedded media, and comprehensive design file documentation.

Related to: Complete Week 13 documentation including Lecture Notes, Recitation Notes, Assignment, Group Assignment, Design Files, and overall page structure

View HTML Transcript Download Markdown Transcript

Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License

``` ```html Week 13 · Wildcard Week
← Back to Home
[Profile Image Placeholder]

Week 13

Wildcard Week

Week Highlights

Key captures from the PCB engraving assignment with links to their sections.

ATtiny1626 Board Design

Final ATtiny1626 development board design with connectors and mounting holes

PCB Engraving

ATtiny1626 development board after fiber laser engraving

Soldered Board

Fully assembled ATtiny1626 development board with all components soldered

Blinking LED Demo

RP2354A Board Design

RP2354A development board design

PCB Engraving Detail

Close-up detail of PCB engraving showing trace quality

Table of Contents

Course Content

Training & Documentation

Assignments & Projects

Wildcard Week

This week focuses on exploring digital fabrication processes not covered in previous assignments. We'll design and produce something using computer-aided design and manufacturing, documenting requirements and including everything necessary for reproduction. This week also includes reflection on the impact and purpose of making (almost) anything.

Exploring new digital fabrication processes
Designing and producing with CAD/CAM
Understanding the impact and purpose of fabrication labs

This Week's Goals

  • Explore New Processes
    Design and produce something with a digital process not covered in other assignments
  • Complete Documentation
    Document requirements and include everything necessary to reproduce the project
  • Reflect on Impact
    Understand the purpose and impact of fabrication labs and making

Assignments

  • Wildcard Assignments
    Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment
  • Assignment
    Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment, documenting the requirements that your assignment meets, and including everything necessary to reproduce it

Tools & Materials

  • Carvera (CNC Mill) — Edge cuts and hole machining
  • Fiber Laser Cutter (xTool F2 Ultra) — PCB engraving
  • PCB Design Software (KiCad) — Board layout and design
  • ATtiny1626 Microcontroller — Target device for development board
  • RP2354A Microcontroller — Complex board design

Lecture Notes

Week 13 lecture covering major announcements, week 12 review, system integration reminders, and wildcard week preview.

Theme of the Week

'Step away from the panic'

Major Announcements

  • Subject evaluation: Required for funding the class. Provides feedback to the institute about the class. Important for future students if you care about successors in the class.
  • Calendar alarm: Wildcard week and recitation on why make (almost) anything: impact. Friday is cutoff for assignments and orders (10s of dollars per person from inventory).
  • Final presentation/final exam: Combining multiple additive and subtractive processes (not just design a board and 3D print a case). Goal is system integration out of parts. Final exam criteria:
    • Did you integrate and design a complete system?
    • Can you demo a final project? Here is the cool thing I did and here is how it works.
    • Make a final project video! (helps but not required)
    Focus on well-integrated device!

Review of Week 12 User Interfaces

  • Claire Wang: Music play and Windows 3.1 interface works!
  • Ryan Hoffman: DRV8251A discussion, heat sinks, breakout boards. Wildcards with waterjetting, EDM, multi-axis machining, laser cutting metal. Class in the spring on nature of mathematical modeling.
  • Srikanth Nadhamuni: Background and experience to visiting fellow at MIT. Raspberry Pi W for WiFi, n8n for cloud LLM data crunching. Software: Node.js, MCP bridge server with n8n based on bridge connected to device (NGV tunnel). All set! Fantastic experience, haven't worked so hard in a very long time and learning a lot of new things. Hope to take forward and build other systems. The whole culture of doing and trying yourself fascinating, especially with failing a number of times until you figure it out. Maybe set one up at an IIT in India or AI centers of excellence with education ministry into the Indian education system (see fablabkerala.in or vigyam ashram).
  • Ray Song: Not here.
  • Tyler Jensen (Lincoln Lab, Group 81): Final project discussion (nylon printer). Week 13: Easy for web serial interface for XIAO! Web server to TFT (I think I forgot to load the camera pins with my code for it).
  • Aditi Ramakrishnan: Sloan MBA and strategy consulting background. Discrete time filter (FFT is blown) in skimage.filters — make a bandpass filter, then run a series of these filters, much less computing only adds and multiplies for filtering in realtime.
  • Alexandros Gravalos: Not here.
  • Edward Chen: Check final watch project by Gulati into watch form factor. Clear print on the Form Labs printer, 0.1. Kaman filter for sensor fusion (in the spring class). For position — LSM6DSV16X from input devices. Acceleration at 7 kHz (at audio frequency).

Show and Tell

  • Handle to sensor WiFi user interface
  • Plug to audio LLM user interface

System Integration Reminders

  • Mount electronics
  • Strain relief the final projects

Preview for Wildcard Week

Assignment: Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment.

Recitation Notes: Why Make (Almost) Anything

Recitation exploring the purpose, impact, and scaling of fabrication labs and making infrastructure.

Map of Fab Labs

Why Make a Fab Lab?

  • Used to create a community
  • Building things for the community
  • Sustainability
  • Prototyping quickly

How Impact?

  • How to make spaces: How to measure impact. What is important about fab:
    • Fablabs in cities vs rural areas: The ability to decide their own futures and change their lives fundamentally. 'Safecast revolutionized citizen science' e.g. radiation map.
    • Bringing back manufacturing: Reducing reliance on supply chains.
    • Rural sustainability: Working with indigenous communities on creating technologies themselves at scale and measure their usefulness and efficacy to preserve their ancestral knowledge:
      • How to establish labs there
      • How to make sure the labs get used
    • Hygiene technologies with Proctor and Gamble: Highly commercial. Lots of plastic waste. How can we change how they produce? How to make their products get there through resellers?
    • Trip to Peru and ran workshops, questionnaires, analysis: Collaboration developed into how to produce the products but also how to test their products to be market valuable e.g. mosquito repellents. Out of three plants, two worked better and one wasn't working at all (which is important to know!).

What Does It Mean to Design Infrastructure?

  • What did we want this lab to be able to do?
    • Workshops and questionnaires
    • How much you educate people based on the info they have with the issues the community is facing
    • Energy concerns to consider, some machines just drain the grid and can't be used. Solar powered, battery powered machines, reducing energy consumption of machines. Many concerns important.
  • Ethical questions
  • How to maintain resources

Case Study: Water Purifier Packets

Use them, change them, source them locally, ingredients found locally, how to distribute them globally.

Funding Models

First few fablabs were NSF funded. Now corporate CSR, regional funding, labor funding (10 different ways). Successful fablabs are heterogeneous with lots of ways of funding. The ones that fail usually just have one sponsor.

Example: DIY Raman spectrometer for water purification (even after purifications still have sulfates and improving that too).

What Does It Mean to Scale Infrastructure?

(Besides a lot of meetings!) What is a reasonable way to design a data collection process about what is needed and how to achieve it.

Back to the Map: Expansion

Timeline of development, cocreation, portable, skin analysis, water testing, biomaterial tech, microscopy.

Initial Results from Boston

How to Confront Local Impact
  • Collab with University of Hamburg. Motivation for how much food can be produced in Boston. Where food waste goes and what Boston produces locally. Make things for yourself locally.
  • Impact directly in the community you're living in.

Hatchspace

Focused on rehabilitation of addicts with woodworking. (Vermont is wood producing state).

Example Course Program

  • All-in session and systemic impact
  • Natural and cultural context
  • Skills and workshop
  • Economic vitality
  • Skills and workshop
  • Co-work session
  • Solutionspalooza

In the Course

Hands-on component (no physical robot exists that can do it) and community component is also important. Inclusion is important. Solving unconscious and institutional biases.

  • 'Fabrica! Lab' — Creating new laboratory spaces for female high school students, courses aimed for women in technology, online advising sessions for females interested in tech.
  • Makerspaces — Access to tools behind closed doors at universities, makes a huge difference for people who don't have the ability to prototype for themselves.
  • Materiom — Fablab affiliated project on organic waste for biomaterials.
  • Fablab León
  • Skylab workshop experiment — How to run a noodle shop out of a fablab (creating food from the community).
  • Academany — Global distributed campus for high school education. Fablab all-in (belonging, impact, community), fab futures (future vocational skills), bio academy (synthetic biology), fabricademy (textiles, fab, bio), fab academy (digital fab apps and implications).

Trade-off Between Impactful and Dangerous

People could be doing bad, but not because doing it with a group people with values.

Questions

Clarification: Adding infrastructure to existing fablab infrastructure to help support specific community needs (not specialized fab labs).

Foundations for Fab Futures

July 27-31, 2026 at Fab Boston 2026.

Useful Documentation

Essential resources for wildcard week digital fabrication processes and PCB design.

Class Page

Wildcard Week - MIT Academy

Comprehensive resource covering wildcard week assignment requirements and possibilities including grinding, multi-axis machining, electrical discharge machining, waterjet cutting, flatbed cutting, plasma cutting, laser metal cutting, laser micromachining, welding, molding and casting, folding, robotics, electronics, embedded programming, food, materials, biotechnology, textiles, and composites.

Key Topics

  • Machining: Grinding, multi-axis machining, electrical discharge machining, waterjet cutting, plasma cutting, laser metal cutting, laser micromachining
  • Molding & Casting: Vacuum forming, rotocasting
  • Folding: Mathematics, form and function, kirigami
  • Robotics: Arms, construction, soft actuation pneumatic inflatable
  • Electronics: Pick and place, programmable logic
  • Embedded Programming: Machine learning, machine vision
  • Textiles: Fiber processes, knitting, embroidery (PEmbroider, Ink/Stitch), Fabricademy
  • Composites: Various composite fabrication techniques

ATtiny1626 Development Board References

Embedded Programming Course Resources

Course resources for embedded programming with ATtiny412 microcontroller examples:

Embedded Programming - MIT Academy

ATtiny412 Echo Example Image

Assignment: PCB Engraving with Fiber Laser

Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment. This assignment demonstrates PCB design and fabrication using a combination of CNC milling (Carvera) for edge cuts and hole machining, and fiber laser engraving (xTool F2 Ultra) for trace creation on copper-clad boards. The project includes designing and fabricating two development boards: a simple ATtiny1626 development board and a complex RP2354A development board.

PCB Engraving Process

This project explores PCB fabrication using fiber laser engraving, a process not covered in previous assignments. The workflow combines subtractive manufacturing techniques: CNC milling for mechanical features (edge cuts and holes) and laser engraving for electrical traces. This approach enables rapid prototyping of custom PCBs without requiring chemical etching or specialized PCB manufacturing facilities.

Tools and Equipment

  • Carvera (CNC Mill): Used for edge cuts and hole machining. The laser cannot effectively cut through the board material, so mechanical cutting is required for board outline and mounting holes.
  • Fiber Laser Cutter (xTool F2 Ultra): Used for PCB trace engraving. The laser removes copper from the board surface to create electrical traces and pads.
  • PCB Design Software (KiCad): Used for schematic capture, PCB layout, and design rule checking.

Boards Designed

  • Simple Board: ATtiny1626 development board with connectors, resistors, LED, and capacitor
  • Complex Board: RP2354A development board with more advanced routing and component placement

Board Design Considerations

  • Connector Placement: Top and bottom for connectors, right side for flashing. Connectors along edges to minimize form factor and maximize space usage.
  • Vertical Connectors: Used instead of horizontal connectors because horizontal connectors risk being snapped during use.
  • Black Area Avoidance: Avoid large black areas because laser does not work well with that (keep traces closer and further to minimize black areas). Note: Need to characterize maximum black until it burns the board because dumping too much heat in one place can damage the board.
  • Breadboard Compatibility: Put connectors on 100mil spacing grid size for breadboardability.
  • Pin Count Adjustment: Missed six pins in initial design, so switched from 6-pin headers to 9-pin (distributed six on top and bottom).
  • I2C Resistors: No SDA or SCL resistors included to keep flexibility for future use. May add spot for zero-ohm or pull-up resistor later but keeping it simple for now.
  • Mounting Holes: Added aligned mounting holes (M3 usually — for 3mm screws) for mechanical mounting.
  • Rounded Edge Cuts: Do 90 degrees, copy, drag, and complete the shape for rounded corners.

Design Rules

  • 0.1 mm spacing minimum
  • 0.15 mm trace width minimum
  • 0.15 mm clearance between plane and the rest

Ports and Pins

ATtiny1626 is an 8-bit microcontroller with 8 pins maximum per port. Each port has 8 pins maximum (some less). Need to specify port letter and pin number:

  • PA (0-7)
  • PB (0-7)
  • PC (0-7)

Postprocessing

  • For Carvera: Add new layer with just the holes in Photoshop (only holes for machining).
  • For Laser Engraving: Get rid of the holes for the F2 tools engraving in Inkscape (the frame and the board for alignment, then only engrave the board, not the edges).

Carvera Machining

Using mods → mill 2D PCB workflow:

  • 0.12mm cut depth and max depth

PCB Engraving Process

Using xTool F2 Ultra fiber laser:

  • Use tape for laser alignment
  • Run a test first on spare copper before the Carvera cut board to make sure focus is good (2.7mm thickness setting worked, board is actually 1.6-1.7mm thick)
  • Sand after engraving to clean up any residue
  • Worked with Bantam Tools FR1 (not random Amazon copper)
  • Perform short circuit test after engraving

Soldering

Using solder gun (heat gun) for component assembly.

Components

  • 1x 6-pin flipflop headers
  • 2x 9-pin flipflop headers
  • 1x 4.7k resistor
  • 1x 1k resistor
  • 1x LED
  • 1x 1uF or 10uF capacitor

Design Files

Download design files: ATtiny_QFN.zip and RP2354A-dev-v1.1.zip

Final ATtiny1626 development board design showing component placement and routing
ATtiny1626 final designComplete PCB layout with connectors, components, traces, and mounting holes optimized for laser engraving.
ATtiny1626 development board after fiber laser engraving showing copper traces
PCB after engravingCopper-clad board with traces engraved using fiber laser, ready for component soldering.
Fully assembled ATtiny1626 development board with all components soldered
Soldered boardComplete ATtiny1626 development board with headers, resistors, LED, and capacitor soldered in place.
Blinking LED demoVideo demonstration of the completed ATtiny1626 development board running a simple LED blink program, confirming successful fabrication and programming.
Close-up detail of PCB engraving showing trace quality and copper removal
PCB engraving detailClose-up view of fiber laser engraved traces showing clean copper removal and precise trace definition.

Interface with User

The application interfaces a user with input and/or output devices through the ATtiny1626 development board. The following table describes how the application interfaces with the user:

How It Interfaces with User Input Device(s) Output Device(s)
(a) LED Blink Demonstration None (programmed behavior) LED (visual feedback indicating board functionality)
(b) Future Interface Applications GPIO pins (PA, PB, PC ports) available for sensors, buttons, switches GPIO pins (PA, PB, PC ports) available for LEDs, displays, actuators

Wildcard Assignments: Wildcard Week Digital Process

Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment. This group assignment explores various digital fabrication processes available during wildcard week.

Wildcard Week Possibilities

The wildcard week assignment allows exploration of digital fabrication processes not covered in previous weeks. Possibilities include (but are not limited to):

Machining

  • Grinding
  • Multi-axis machining
  • Electrical discharge machining (EDM)
  • Waterjet cutting
  • Flatbed cutting
  • Plasma cutting
  • Laser metal cutting
  • Laser micromachining

Welding

Various welding techniques for joining materials.

Molding and Casting

  • Vacuum forming
  • Rotocasting

Folding

  • Mathematics
  • Form and function
  • Kirigami

Robotics

  • Arms
  • Construction
  • Soft actuation pneumatic inflatable

Electronics

  • Pick and place
  • Programmable logic

Embedded Programming

  • Machine learning
  • Machine vision

Food

  • Printing
  • Gastronomy

Materials

  • Synthesis
  • Mechanical
  • Rheological

Biotechnology

  • DIYbio
  • iGEM
  • HTGAA
  • Bio Academy

Textiles

  • Fiber processes
  • Knitting
  • Embroidery (PEmbroider, Ink/Stitch)
  • Fabricademy

Composites

Various composite fabrication techniques.

Design Files

Design files for PCB engraving projects including ATtiny1626 and RP2354A development boards.

ATtiny1626 Development Board

Simple development board for ATtiny1626 microcontroller with connectors, resistors, LED, and capacitor. Designed for breadboard compatibility with 100mil spacing grid.

Initial ATtiny1626 development board design
Initial designFirst iteration of ATtiny1626 development board layout.
Final ATtiny1626 development board design with all components
Final designComplete ATtiny1626 development board with connectors, mounting holes, and optimized trace routing.

Download Design Files

  • ATtiny_QFN.zip — Complete KiCad project files for ATtiny1626 development board

RP2354A Development Board

Complex development board for RP2354A microcontroller with advanced routing and component placement.

RP2354A development board design
RP2354A board designComplete PCB layout for RP2354A development board with complex routing and component placement.

Download Design Files

Reflections & Learnings

Key insights and learnings from working with interface and application programming.

Contributions

Acknowledgements and team roles for wildcard week PCB engraving work.

Wildcard Week Session

  • Quentin and Anthony: Ran the wildcard week session, providing guidance and support for PCB engraving projects.
  • Quentin: Designed the RP2354A development board before the session and finished the ATtiny1626 design with us during the wildcard session.

Ethical AI Use

Transparent documentation of AI assistance used in this week's wildcard week assignment page creation.

Week 13 Assignment Page Creation

Complete Cursor AI transcript for Week 13 wildcard week assignment page creation. This comprehensive conversation covers the creation and population of the Week 13 HTML page, including lecture and recitation notes, PCB engraving assignment documentation, design files integration, and comprehensive page structure development. The transcript demonstrates the collaborative process of building professional documentation with structured content, embedded media, and comprehensive design file documentation.

Related to: Complete Week 13 documentation including Lecture Notes, Recitation Notes, Assignment, Group Assignment, Design Files, and overall page structure

View HTML Transcript Download Markdown Transcript

Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License

``` Updated both images to: 1. **Keep the same size** — Height remains `140px` to match the other highlights 2. **Show full image** — Changed `object-fit:cover` to `object-fit:contain` so the full image is visible with whitespace around it 3. **Add whitespace** — Kept `padding:12px` on the image containers to add whitespace around the images 4. **Add spacing** — Kept the `margin-top:12px; margin-bottom:12px;` on the containers for spacing above and below the highlights The "ATtiny1626 Board Design" and "RP2354A Board Design" highlights now show the full images with whitespace around them while maintaining the same overall size as the other highlight boxes. No linting errors found. --- **User** its not the same size as the other highlights, look at what we did in week 11 for Invisible String Final PCB Layout --- **Cursor** Checking week11.html for the "Invisible String Final PCB Layout" highlight styling: Checking the exact styling used: Updating both highlights to match week11's styling: padding on the image, white background, and no container padding: ```html Week 13 · Wildcard Week
← Back to Home
[Profile Image Placeholder]

Week 13

Wildcard Week

Week Highlights

Key captures from the PCB engraving assignment with links to their sections.

ATtiny1626 Board Design

Final ATtiny1626 development board design with connectors and mounting holes

PCB Engraving

ATtiny1626 development board after fiber laser engraving

Soldered Board

Fully assembled ATtiny1626 development board with all components soldered

Blinking LED Demo

RP2354A Board Design

RP2354A development board design

PCB Engraving Detail

Close-up detail of PCB engraving showing trace quality

Table of Contents

Course Content

Training & Documentation

Assignments & Projects

Wildcard Week

This week focuses on exploring digital fabrication processes not covered in previous assignments. We'll design and produce something using computer-aided design and manufacturing, documenting requirements and including everything necessary for reproduction. This week also includes reflection on the impact and purpose of making (almost) anything.

Exploring new digital fabrication processes
Designing and producing with CAD/CAM
Understanding the impact and purpose of fabrication labs

This Week's Goals

  • Explore New Processes
    Design and produce something with a digital process not covered in other assignments
  • Complete Documentation
    Document requirements and include everything necessary to reproduce the project
  • Reflect on Impact
    Understand the purpose and impact of fabrication labs and making

Assignments

  • Wildcard Assignments
    Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment
  • Assignment
    Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment, documenting the requirements that your assignment meets, and including everything necessary to reproduce it

Tools & Materials

  • Carvera (CNC Mill) — Edge cuts and hole machining
  • Fiber Laser Cutter (xTool F2 Ultra) — PCB engraving
  • PCB Design Software (KiCad) — Board layout and design
  • ATtiny1626 Microcontroller — Target device for development board
  • RP2354A Microcontroller — Complex board design

Lecture Notes

Week 13 lecture covering major announcements, week 12 review, system integration reminders, and wildcard week preview.

Theme of the Week

'Step away from the panic'

Major Announcements

  • Subject evaluation: Required for funding the class. Provides feedback to the institute about the class. Important for future students if you care about successors in the class.
  • Calendar alarm: Wildcard week and recitation on why make (almost) anything: impact. Friday is cutoff for assignments and orders (10s of dollars per person from inventory).
  • Final presentation/final exam: Combining multiple additive and subtractive processes (not just design a board and 3D print a case). Goal is system integration out of parts. Final exam criteria:
    • Did you integrate and design a complete system?
    • Can you demo a final project? Here is the cool thing I did and here is how it works.
    • Make a final project video! (helps but not required)
    Focus on well-integrated device!

Review of Week 12 User Interfaces

  • Claire Wang: Music play and Windows 3.1 interface works!
  • Ryan Hoffman: DRV8251A discussion, heat sinks, breakout boards. Wildcards with waterjetting, EDM, multi-axis machining, laser cutting metal. Class in the spring on nature of mathematical modeling.
  • Srikanth Nadhamuni: Background and experience to visiting fellow at MIT. Raspberry Pi W for WiFi, n8n for cloud LLM data crunching. Software: Node.js, MCP bridge server with n8n based on bridge connected to device (NGV tunnel). All set! Fantastic experience, haven't worked so hard in a very long time and learning a lot of new things. Hope to take forward and build other systems. The whole culture of doing and trying yourself fascinating, especially with failing a number of times until you figure it out. Maybe set one up at an IIT in India or AI centers of excellence with education ministry into the Indian education system (see fablabkerala.in or vigyam ashram).
  • Ray Song: Not here.
  • Tyler Jensen (Lincoln Lab, Group 81): Final project discussion (nylon printer). Week 13: Easy for web serial interface for XIAO! Web server to TFT (I think I forgot to load the camera pins with my code for it).
  • Aditi Ramakrishnan: Sloan MBA and strategy consulting background. Discrete time filter (FFT is blown) in skimage.filters — make a bandpass filter, then run a series of these filters, much less computing only adds and multiplies for filtering in realtime.
  • Alexandros Gravalos: Not here.
  • Edward Chen: Check final watch project by Gulati into watch form factor. Clear print on the Form Labs printer, 0.1. Kaman filter for sensor fusion (in the spring class). For position — LSM6DSV16X from input devices. Acceleration at 7 kHz (at audio frequency).

Show and Tell

  • Handle to sensor WiFi user interface
  • Plug to audio LLM user interface

System Integration Reminders

  • Mount electronics
  • Strain relief the final projects

Preview for Wildcard Week

Assignment: Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment.

Recitation Notes: Why Make (Almost) Anything

Recitation exploring the purpose, impact, and scaling of fabrication labs and making infrastructure.

Map of Fab Labs

Why Make a Fab Lab?

  • Used to create a community
  • Building things for the community
  • Sustainability
  • Prototyping quickly

How Impact?

  • How to make spaces: How to measure impact. What is important about fab:
    • Fablabs in cities vs rural areas: The ability to decide their own futures and change their lives fundamentally. 'Safecast revolutionized citizen science' e.g. radiation map.
    • Bringing back manufacturing: Reducing reliance on supply chains.
    • Rural sustainability: Working with indigenous communities on creating technologies themselves at scale and measure their usefulness and efficacy to preserve their ancestral knowledge:
      • How to establish labs there
      • How to make sure the labs get used
    • Hygiene technologies with Proctor and Gamble: Highly commercial. Lots of plastic waste. How can we change how they produce? How to make their products get there through resellers?
    • Trip to Peru and ran workshops, questionnaires, analysis: Collaboration developed into how to produce the products but also how to test their products to be market valuable e.g. mosquito repellents. Out of three plants, two worked better and one wasn't working at all (which is important to know!).

What Does It Mean to Design Infrastructure?

  • What did we want this lab to be able to do?
    • Workshops and questionnaires
    • How much you educate people based on the info they have with the issues the community is facing
    • Energy concerns to consider, some machines just drain the grid and can't be used. Solar powered, battery powered machines, reducing energy consumption of machines. Many concerns important.
  • Ethical questions
  • How to maintain resources

Case Study: Water Purifier Packets

Use them, change them, source them locally, ingredients found locally, how to distribute them globally.

Funding Models

First few fablabs were NSF funded. Now corporate CSR, regional funding, labor funding (10 different ways). Successful fablabs are heterogeneous with lots of ways of funding. The ones that fail usually just have one sponsor.

Example: DIY Raman spectrometer for water purification (even after purifications still have sulfates and improving that too).

What Does It Mean to Scale Infrastructure?

(Besides a lot of meetings!) What is a reasonable way to design a data collection process about what is needed and how to achieve it.

Back to the Map: Expansion

Timeline of development, cocreation, portable, skin analysis, water testing, biomaterial tech, microscopy.

Initial Results from Boston

How to Confront Local Impact
  • Collab with University of Hamburg. Motivation for how much food can be produced in Boston. Where food waste goes and what Boston produces locally. Make things for yourself locally.
  • Impact directly in the community you're living in.

Hatchspace

Focused on rehabilitation of addicts with woodworking. (Vermont is wood producing state).

Example Course Program

  • All-in session and systemic impact
  • Natural and cultural context
  • Skills and workshop
  • Economic vitality
  • Skills and workshop
  • Co-work session
  • Solutionspalooza

In the Course

Hands-on component (no physical robot exists that can do it) and community component is also important. Inclusion is important. Solving unconscious and institutional biases.

  • 'Fabrica! Lab' — Creating new laboratory spaces for female high school students, courses aimed for women in technology, online advising sessions for females interested in tech.
  • Makerspaces — Access to tools behind closed doors at universities, makes a huge difference for people who don't have the ability to prototype for themselves.
  • Materiom — Fablab affiliated project on organic waste for biomaterials.
  • Fablab León
  • Skylab workshop experiment — How to run a noodle shop out of a fablab (creating food from the community).
  • Academany — Global distributed campus for high school education. Fablab all-in (belonging, impact, community), fab futures (future vocational skills), bio academy (synthetic biology), fabricademy (textiles, fab, bio), fab academy (digital fab apps and implications).

Trade-off Between Impactful and Dangerous

People could be doing bad, but not because doing it with a group people with values.

Questions

Clarification: Adding infrastructure to existing fablab infrastructure to help support specific community needs (not specialized fab labs).

Foundations for Fab Futures

July 27-31, 2026 at Fab Boston 2026.

Useful Documentation

Essential resources for wildcard week digital fabrication processes and PCB design.

Class Page

Wildcard Week - MIT Academy

Comprehensive resource covering wildcard week assignment requirements and possibilities including grinding, multi-axis machining, electrical discharge machining, waterjet cutting, flatbed cutting, plasma cutting, laser metal cutting, laser micromachining, welding, molding and casting, folding, robotics, electronics, embedded programming, food, materials, biotechnology, textiles, and composites.

Key Topics

  • Machining: Grinding, multi-axis machining, electrical discharge machining, waterjet cutting, plasma cutting, laser metal cutting, laser micromachining
  • Molding & Casting: Vacuum forming, rotocasting
  • Folding: Mathematics, form and function, kirigami
  • Robotics: Arms, construction, soft actuation pneumatic inflatable
  • Electronics: Pick and place, programmable logic
  • Embedded Programming: Machine learning, machine vision
  • Textiles: Fiber processes, knitting, embroidery (PEmbroider, Ink/Stitch), Fabricademy
  • Composites: Various composite fabrication techniques

ATtiny1626 Development Board References

Embedded Programming Course Resources

Course resources for embedded programming with ATtiny412 microcontroller examples:

Embedded Programming - MIT Academy

ATtiny412 Echo Example Image

Assignment: PCB Engraving with Fiber Laser

Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment. This assignment demonstrates PCB design and fabrication using a combination of CNC milling (Carvera) for edge cuts and hole machining, and fiber laser engraving (xTool F2 Ultra) for trace creation on copper-clad boards. The project includes designing and fabricating two development boards: a simple ATtiny1626 development board and a complex RP2354A development board.

PCB Engraving Process

This project explores PCB fabrication using fiber laser engraving, a process not covered in previous assignments. The workflow combines subtractive manufacturing techniques: CNC milling for mechanical features (edge cuts and holes) and laser engraving for electrical traces. This approach enables rapid prototyping of custom PCBs without requiring chemical etching or specialized PCB manufacturing facilities.

Tools and Equipment

  • Carvera (CNC Mill): Used for edge cuts and hole machining. The laser cannot effectively cut through the board material, so mechanical cutting is required for board outline and mounting holes.
  • Fiber Laser Cutter (xTool F2 Ultra): Used for PCB trace engraving. The laser removes copper from the board surface to create electrical traces and pads.
  • PCB Design Software (KiCad): Used for schematic capture, PCB layout, and design rule checking.

Boards Designed

  • Simple Board: ATtiny1626 development board with connectors, resistors, LED, and capacitor
  • Complex Board: RP2354A development board with more advanced routing and component placement

Board Design Considerations

  • Connector Placement: Top and bottom for connectors, right side for flashing. Connectors along edges to minimize form factor and maximize space usage.
  • Vertical Connectors: Used instead of horizontal connectors because horizontal connectors risk being snapped during use.
  • Black Area Avoidance: Avoid large black areas because laser does not work well with that (keep traces closer and further to minimize black areas). Note: Need to characterize maximum black until it burns the board because dumping too much heat in one place can damage the board.
  • Breadboard Compatibility: Put connectors on 100mil spacing grid size for breadboardability.
  • Pin Count Adjustment: Missed six pins in initial design, so switched from 6-pin headers to 9-pin (distributed six on top and bottom).
  • I2C Resistors: No SDA or SCL resistors included to keep flexibility for future use. May add spot for zero-ohm or pull-up resistor later but keeping it simple for now.
  • Mounting Holes: Added aligned mounting holes (M3 usually — for 3mm screws) for mechanical mounting.
  • Rounded Edge Cuts: Do 90 degrees, copy, drag, and complete the shape for rounded corners.

Design Rules

  • 0.1 mm spacing minimum
  • 0.15 mm trace width minimum
  • 0.15 mm clearance between plane and the rest

Ports and Pins

ATtiny1626 is an 8-bit microcontroller with 8 pins maximum per port. Each port has 8 pins maximum (some less). Need to specify port letter and pin number:

  • PA (0-7)
  • PB (0-7)
  • PC (0-7)

Postprocessing

  • For Carvera: Add new layer with just the holes in Photoshop (only holes for machining).
  • For Laser Engraving: Get rid of the holes for the F2 tools engraving in Inkscape (the frame and the board for alignment, then only engrave the board, not the edges).

Carvera Machining

Using mods → mill 2D PCB workflow:

  • 0.12mm cut depth and max depth

PCB Engraving Process

Using xTool F2 Ultra fiber laser:

  • Use tape for laser alignment
  • Run a test first on spare copper before the Carvera cut board to make sure focus is good (2.7mm thickness setting worked, board is actually 1.6-1.7mm thick)
  • Sand after engraving to clean up any residue
  • Worked with Bantam Tools FR1 (not random Amazon copper)
  • Perform short circuit test after engraving

Soldering

Using solder gun (heat gun) for component assembly.

Components

  • 1x 6-pin flipflop headers
  • 2x 9-pin flipflop headers
  • 1x 4.7k resistor
  • 1x 1k resistor
  • 1x LED
  • 1x 1uF or 10uF capacitor

Design Files

Download design files: ATtiny_QFN.zip and RP2354A-dev-v1.1.zip

Final ATtiny1626 development board design showing component placement and routing
ATtiny1626 final designComplete PCB layout with connectors, components, traces, and mounting holes optimized for laser engraving.
ATtiny1626 development board after fiber laser engraving showing copper traces
PCB after engravingCopper-clad board with traces engraved using fiber laser, ready for component soldering.
Fully assembled ATtiny1626 development board with all components soldered
Soldered boardComplete ATtiny1626 development board with headers, resistors, LED, and capacitor soldered in place.
Blinking LED demoVideo demonstration of the completed ATtiny1626 development board running a simple LED blink program, confirming successful fabrication and programming.
Close-up detail of PCB engraving showing trace quality and copper removal
PCB engraving detailClose-up view of fiber laser engraved traces showing clean copper removal and precise trace definition.

Interface with User

The application interfaces a user with input and/or output devices through the ATtiny1626 development board. The following table describes how the application interfaces with the user:

How It Interfaces with User Input Device(s) Output Device(s)
(a) LED Blink Demonstration None (programmed behavior) LED (visual feedback indicating board functionality)
(b) Future Interface Applications GPIO pins (PA, PB, PC ports) available for sensors, buttons, switches GPIO pins (PA, PB, PC ports) available for LEDs, displays, actuators

Wildcard Assignments: Wildcard Week Digital Process

Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment. This group assignment explores various digital fabrication processes available during wildcard week.

Wildcard Week Possibilities

The wildcard week assignment allows exploration of digital fabrication processes not covered in previous weeks. Possibilities include (but are not limited to):

Machining

  • Grinding
  • Multi-axis machining
  • Electrical discharge machining (EDM)
  • Waterjet cutting
  • Flatbed cutting
  • Plasma cutting
  • Laser metal cutting
  • Laser micromachining

Welding

Various welding techniques for joining materials.

Molding and Casting

  • Vacuum forming
  • Rotocasting

Folding

  • Mathematics
  • Form and function
  • Kirigami

Robotics

  • Arms
  • Construction
  • Soft actuation pneumatic inflatable

Electronics

  • Pick and place
  • Programmable logic

Embedded Programming

  • Machine learning
  • Machine vision

Food

  • Printing
  • Gastronomy

Materials

  • Synthesis
  • Mechanical
  • Rheological

Biotechnology

  • DIYbio
  • iGEM
  • HTGAA
  • Bio Academy

Textiles

  • Fiber processes
  • Knitting
  • Embroidery (PEmbroider, Ink/Stitch)
  • Fabricademy

Composites

Various composite fabrication techniques.

Design Files

Design files for PCB engraving projects including ATtiny1626 and RP2354A development boards.

ATtiny1626 Development Board

Simple development board for ATtiny1626 microcontroller with connectors, resistors, LED, and capacitor. Designed for breadboard compatibility with 100mil spacing grid.

Initial ATtiny1626 development board design
Initial designFirst iteration of ATtiny1626 development board layout.
Final ATtiny1626 development board design with all components
Final designComplete ATtiny1626 development board with connectors, mounting holes, and optimized trace routing.

Download Design Files

  • ATtiny_QFN.zip — Complete KiCad project files for ATtiny1626 development board

RP2354A Development Board

Complex development board for RP2354A microcontroller with advanced routing and component placement.

RP2354A development board design
RP2354A board designComplete PCB layout for RP2354A development board with complex routing and component placement.

Download Design Files

Reflections & Learnings

Key insights and learnings from working with interface and application programming.

Contributions

Acknowledgements and team roles for wildcard week PCB engraving work.

Wildcard Week Session

  • Quentin and Anthony: Ran the wildcard week session, providing guidance and support for PCB engraving projects.
  • Quentin: Designed the RP2354A development board before the session and finished the ATtiny1626 design with us during the wildcard session.

Ethical AI Use

Transparent documentation of AI assistance used in this week's wildcard week assignment page creation.

Week 13 Assignment Page Creation

Complete Cursor AI transcript for Week 13 wildcard week assignment page creation. This comprehensive conversation covers the creation and population of the Week 13 HTML page, including lecture and recitation notes, PCB engraving assignment documentation, design files integration, and comprehensive page structure development. The transcript demonstrates the collaborative process of building professional documentation with structured content, embedded media, and comprehensive design file documentation.

Related to: Complete Week 13 documentation including Lecture Notes, Recitation Notes, Assignment, Group Assignment, Design Files, and overall page structure

View HTML Transcript Download Markdown Transcript

Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License

``` ```html Week 13 · Wildcard Week
← Back to Home
[Profile Image Placeholder]

Week 13

Wildcard Week

Week Highlights

Key captures from the PCB engraving assignment with links to their sections.

ATtiny1626 Board Design

Final ATtiny1626 development board design with connectors and mounting holes

PCB Engraving

ATtiny1626 development board after fiber laser engraving

Soldered Board

Fully assembled ATtiny1626 development board with all components soldered

Blinking LED Demo

RP2354A Board Design

RP2354A development board design

PCB Engraving Detail

Close-up detail of PCB engraving showing trace quality

Table of Contents

Course Content

Training & Documentation

Assignments & Projects

Wildcard Week

This week focuses on exploring digital fabrication processes not covered in previous assignments. We'll design and produce something using computer-aided design and manufacturing, documenting requirements and including everything necessary for reproduction. This week also includes reflection on the impact and purpose of making (almost) anything.

Exploring new digital fabrication processes
Designing and producing with CAD/CAM
Understanding the impact and purpose of fabrication labs

This Week's Goals

  • Explore New Processes
    Design and produce something with a digital process not covered in other assignments
  • Complete Documentation
    Document requirements and include everything necessary to reproduce the project
  • Reflect on Impact
    Understand the purpose and impact of fabrication labs and making

Assignments

  • Wildcard Assignments
    Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment
  • Assignment
    Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment, documenting the requirements that your assignment meets, and including everything necessary to reproduce it

Tools & Materials

  • Carvera (CNC Mill) — Edge cuts and hole machining
  • Fiber Laser Cutter (xTool F2 Ultra) — PCB engraving
  • PCB Design Software (KiCad) — Board layout and design
  • ATtiny1626 Microcontroller — Target device for development board
  • RP2354A Microcontroller — Complex board design

Lecture Notes

Week 13 lecture covering major announcements, week 12 review, system integration reminders, and wildcard week preview.

Theme of the Week

'Step away from the panic'

Major Announcements

  • Subject evaluation: Required for funding the class. Provides feedback to the institute about the class. Important for future students if you care about successors in the class.
  • Calendar alarm: Wildcard week and recitation on why make (almost) anything: impact. Friday is cutoff for assignments and orders (10s of dollars per person from inventory).
  • Final presentation/final exam: Combining multiple additive and subtractive processes (not just design a board and 3D print a case). Goal is system integration out of parts. Final exam criteria:
    • Did you integrate and design a complete system?
    • Can you demo a final project? Here is the cool thing I did and here is how it works.
    • Make a final project video! (helps but not required)
    Focus on well-integrated device!

Review of Week 12 User Interfaces

  • Claire Wang: Music play and Windows 3.1 interface works!
  • Ryan Hoffman: DRV8251A discussion, heat sinks, breakout boards. Wildcards with waterjetting, EDM, multi-axis machining, laser cutting metal. Class in the spring on nature of mathematical modeling.
  • Srikanth Nadhamuni: Background and experience to visiting fellow at MIT. Raspberry Pi W for WiFi, n8n for cloud LLM data crunching. Software: Node.js, MCP bridge server with n8n based on bridge connected to device (NGV tunnel). All set! Fantastic experience, haven't worked so hard in a very long time and learning a lot of new things. Hope to take forward and build other systems. The whole culture of doing and trying yourself fascinating, especially with failing a number of times until you figure it out. Maybe set one up at an IIT in India or AI centers of excellence with education ministry into the Indian education system (see fablabkerala.in or vigyam ashram).
  • Ray Song: Not here.
  • Tyler Jensen (Lincoln Lab, Group 81): Final project discussion (nylon printer). Week 13: Easy for web serial interface for XIAO! Web server to TFT (I think I forgot to load the camera pins with my code for it).
  • Aditi Ramakrishnan: Sloan MBA and strategy consulting background. Discrete time filter (FFT is blown) in skimage.filters — make a bandpass filter, then run a series of these filters, much less computing only adds and multiplies for filtering in realtime.
  • Alexandros Gravalos: Not here.
  • Edward Chen: Check final watch project by Gulati into watch form factor. Clear print on the Form Labs printer, 0.1. Kaman filter for sensor fusion (in the spring class). For position — LSM6DSV16X from input devices. Acceleration at 7 kHz (at audio frequency).

Show and Tell

  • Handle to sensor WiFi user interface
  • Plug to audio LLM user interface

System Integration Reminders

  • Mount electronics
  • Strain relief the final projects

Preview for Wildcard Week

Assignment: Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment.

Recitation Notes: Why Make (Almost) Anything

Recitation exploring the purpose, impact, and scaling of fabrication labs and making infrastructure.

Map of Fab Labs

Why Make a Fab Lab?

  • Used to create a community
  • Building things for the community
  • Sustainability
  • Prototyping quickly

How Impact?

  • How to make spaces: How to measure impact. What is important about fab:
    • Fablabs in cities vs rural areas: The ability to decide their own futures and change their lives fundamentally. 'Safecast revolutionized citizen science' e.g. radiation map.
    • Bringing back manufacturing: Reducing reliance on supply chains.
    • Rural sustainability: Working with indigenous communities on creating technologies themselves at scale and measure their usefulness and efficacy to preserve their ancestral knowledge:
      • How to establish labs there
      • How to make sure the labs get used
    • Hygiene technologies with Proctor and Gamble: Highly commercial. Lots of plastic waste. How can we change how they produce? How to make their products get there through resellers?
    • Trip to Peru and ran workshops, questionnaires, analysis: Collaboration developed into how to produce the products but also how to test their products to be market valuable e.g. mosquito repellents. Out of three plants, two worked better and one wasn't working at all (which is important to know!).

What Does It Mean to Design Infrastructure?

  • What did we want this lab to be able to do?
    • Workshops and questionnaires
    • How much you educate people based on the info they have with the issues the community is facing
    • Energy concerns to consider, some machines just drain the grid and can't be used. Solar powered, battery powered machines, reducing energy consumption of machines. Many concerns important.
  • Ethical questions
  • How to maintain resources

Case Study: Water Purifier Packets

Use them, change them, source them locally, ingredients found locally, how to distribute them globally.

Funding Models

First few fablabs were NSF funded. Now corporate CSR, regional funding, labor funding (10 different ways). Successful fablabs are heterogeneous with lots of ways of funding. The ones that fail usually just have one sponsor.

Example: DIY Raman spectrometer for water purification (even after purifications still have sulfates and improving that too).

What Does It Mean to Scale Infrastructure?

(Besides a lot of meetings!) What is a reasonable way to design a data collection process about what is needed and how to achieve it.

Back to the Map: Expansion

Timeline of development, cocreation, portable, skin analysis, water testing, biomaterial tech, microscopy.

Initial Results from Boston

How to Confront Local Impact
  • Collab with University of Hamburg. Motivation for how much food can be produced in Boston. Where food waste goes and what Boston produces locally. Make things for yourself locally.
  • Impact directly in the community you're living in.

Hatchspace

Focused on rehabilitation of addicts with woodworking. (Vermont is wood producing state).

Example Course Program

  • All-in session and systemic impact
  • Natural and cultural context
  • Skills and workshop
  • Economic vitality
  • Skills and workshop
  • Co-work session
  • Solutionspalooza

In the Course

Hands-on component (no physical robot exists that can do it) and community component is also important. Inclusion is important. Solving unconscious and institutional biases.

  • 'Fabrica! Lab' — Creating new laboratory spaces for female high school students, courses aimed for women in technology, online advising sessions for females interested in tech.
  • Makerspaces — Access to tools behind closed doors at universities, makes a huge difference for people who don't have the ability to prototype for themselves.
  • Materiom — Fablab affiliated project on organic waste for biomaterials.
  • Fablab León
  • Skylab workshop experiment — How to run a noodle shop out of a fablab (creating food from the community).
  • Academany — Global distributed campus for high school education. Fablab all-in (belonging, impact, community), fab futures (future vocational skills), bio academy (synthetic biology), fabricademy (textiles, fab, bio), fab academy (digital fab apps and implications).

Trade-off Between Impactful and Dangerous

People could be doing bad, but not because doing it with a group people with values.

Questions

Clarification: Adding infrastructure to existing fablab infrastructure to help support specific community needs (not specialized fab labs).

Foundations for Fab Futures

July 27-31, 2026 at Fab Boston 2026.

Useful Documentation

Essential resources for wildcard week digital fabrication processes and PCB design.

Class Page

Wildcard Week - MIT Academy

Comprehensive resource covering wildcard week assignment requirements and possibilities including grinding, multi-axis machining, electrical discharge machining, waterjet cutting, flatbed cutting, plasma cutting, laser metal cutting, laser micromachining, welding, molding and casting, folding, robotics, electronics, embedded programming, food, materials, biotechnology, textiles, and composites.

Key Topics

  • Machining: Grinding, multi-axis machining, electrical discharge machining, waterjet cutting, plasma cutting, laser metal cutting, laser micromachining
  • Molding & Casting: Vacuum forming, rotocasting
  • Folding: Mathematics, form and function, kirigami
  • Robotics: Arms, construction, soft actuation pneumatic inflatable
  • Electronics: Pick and place, programmable logic
  • Embedded Programming: Machine learning, machine vision
  • Textiles: Fiber processes, knitting, embroidery (PEmbroider, Ink/Stitch), Fabricademy
  • Composites: Various composite fabrication techniques

ATtiny1626 Development Board References

Embedded Programming Course Resources

Course resources for embedded programming with ATtiny412 microcontroller examples:

Embedded Programming - MIT Academy

ATtiny412 Echo Example Image

Assignment: PCB Engraving with Fiber Laser

Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment. This assignment demonstrates PCB design and fabrication using a combination of CNC milling (Carvera) for edge cuts and hole machining, and fiber laser engraving (xTool F2 Ultra) for trace creation on copper-clad boards. The project includes designing and fabricating two development boards: a simple ATtiny1626 development board and a complex RP2354A development board.

PCB Engraving Process

This project explores PCB fabrication using fiber laser engraving, a process not covered in previous assignments. The workflow combines subtractive manufacturing techniques: CNC milling for mechanical features (edge cuts and holes) and laser engraving for electrical traces. This approach enables rapid prototyping of custom PCBs without requiring chemical etching or specialized PCB manufacturing facilities.

Tools and Equipment

  • Carvera (CNC Mill): Used for edge cuts and hole machining. The laser cannot effectively cut through the board material, so mechanical cutting is required for board outline and mounting holes.
  • Fiber Laser Cutter (xTool F2 Ultra): Used for PCB trace engraving. The laser removes copper from the board surface to create electrical traces and pads.
  • PCB Design Software (KiCad): Used for schematic capture, PCB layout, and design rule checking.

Boards Designed

  • Simple Board: ATtiny1626 development board with connectors, resistors, LED, and capacitor
  • Complex Board: RP2354A development board with more advanced routing and component placement

Board Design Considerations

  • Connector Placement: Top and bottom for connectors, right side for flashing. Connectors along edges to minimize form factor and maximize space usage.
  • Vertical Connectors: Used instead of horizontal connectors because horizontal connectors risk being snapped during use.
  • Black Area Avoidance: Avoid large black areas because laser does not work well with that (keep traces closer and further to minimize black areas). Note: Need to characterize maximum black until it burns the board because dumping too much heat in one place can damage the board.
  • Breadboard Compatibility: Put connectors on 100mil spacing grid size for breadboardability.
  • Pin Count Adjustment: Missed six pins in initial design, so switched from 6-pin headers to 9-pin (distributed six on top and bottom).
  • I2C Resistors: No SDA or SCL resistors included to keep flexibility for future use. May add spot for zero-ohm or pull-up resistor later but keeping it simple for now.
  • Mounting Holes: Added aligned mounting holes (M3 usually — for 3mm screws) for mechanical mounting.
  • Rounded Edge Cuts: Do 90 degrees, copy, drag, and complete the shape for rounded corners.

Design Rules

  • 0.1 mm spacing minimum
  • 0.15 mm trace width minimum
  • 0.15 mm clearance between plane and the rest

Ports and Pins

ATtiny1626 is an 8-bit microcontroller with 8 pins maximum per port. Each port has 8 pins maximum (some less). Need to specify port letter and pin number:

  • PA (0-7)
  • PB (0-7)
  • PC (0-7)

Postprocessing

  • For Carvera: Add new layer with just the holes in Photoshop (only holes for machining).
  • For Laser Engraving: Get rid of the holes for the F2 tools engraving in Inkscape (the frame and the board for alignment, then only engrave the board, not the edges).

Carvera Machining

Using mods → mill 2D PCB workflow:

  • 0.12mm cut depth and max depth

PCB Engraving Process

Using xTool F2 Ultra fiber laser:

  • Use tape for laser alignment
  • Run a test first on spare copper before the Carvera cut board to make sure focus is good (2.7mm thickness setting worked, board is actually 1.6-1.7mm thick)
  • Sand after engraving to clean up any residue
  • Worked with Bantam Tools FR1 (not random Amazon copper)
  • Perform short circuit test after engraving

Soldering

Using solder gun (heat gun) for component assembly.

Components

  • 1x 6-pin flipflop headers
  • 2x 9-pin flipflop headers
  • 1x 4.7k resistor
  • 1x 1k resistor
  • 1x LED
  • 1x 1uF or 10uF capacitor

Design Files

Download design files: ATtiny_QFN.zip and RP2354A-dev-v1.1.zip

Final ATtiny1626 development board design showing component placement and routing
ATtiny1626 final designComplete PCB layout with connectors, components, traces, and mounting holes optimized for laser engraving.
ATtiny1626 development board after fiber laser engraving showing copper traces
PCB after engravingCopper-clad board with traces engraved using fiber laser, ready for component soldering.
Fully assembled ATtiny1626 development board with all components soldered
Soldered boardComplete ATtiny1626 development board with headers, resistors, LED, and capacitor soldered in place.
Blinking LED demoVideo demonstration of the completed ATtiny1626 development board running a simple LED blink program, confirming successful fabrication and programming.
Close-up detail of PCB engraving showing trace quality and copper removal
PCB engraving detailClose-up view of fiber laser engraved traces showing clean copper removal and precise trace definition.

Interface with User

The application interfaces a user with input and/or output devices through the ATtiny1626 development board. The following table describes how the application interfaces with the user:

How It Interfaces with User Input Device(s) Output Device(s)
(a) LED Blink Demonstration None (programmed behavior) LED (visual feedback indicating board functionality)
(b) Future Interface Applications GPIO pins (PA, PB, PC ports) available for sensors, buttons, switches GPIO pins (PA, PB, PC ports) available for LEDs, displays, actuators

Wildcard Assignments: Wildcard Week Digital Process

Design and produce something with a digital process (incorporating computer-aided design and manufacturing) not covered in another assignment. This group assignment explores various digital fabrication processes available during wildcard week.

Wildcard Week Possibilities

The wildcard week assignment allows exploration of digital fabrication processes not covered in previous weeks. Possibilities include (but are not limited to):

Machining

  • Grinding
  • Multi-axis machining
  • Electrical discharge machining (EDM)
  • Waterjet cutting
  • Flatbed cutting
  • Plasma cutting
  • Laser metal cutting
  • Laser micromachining

Welding

Various welding techniques for joining materials.

Molding and Casting

  • Vacuum forming
  • Rotocasting

Folding

  • Mathematics
  • Form and function
  • Kirigami

Robotics

  • Arms
  • Construction
  • Soft actuation pneumatic inflatable

Electronics

  • Pick and place
  • Programmable logic

Embedded Programming

  • Machine learning
  • Machine vision

Food

  • Printing
  • Gastronomy

Materials

  • Synthesis
  • Mechanical
  • Rheological

Biotechnology

  • DIYbio
  • iGEM
  • HTGAA
  • Bio Academy

Textiles

  • Fiber processes
  • Knitting
  • Embroidery (PEmbroider, Ink/Stitch)
  • Fabricademy

Composites

Various composite fabrication techniques.

Design Files

Design files for PCB engraving projects including ATtiny1626 and RP2354A development boards.

ATtiny1626 Development Board

Simple development board for ATtiny1626 microcontroller with connectors, resistors, LED, and capacitor. Designed for breadboard compatibility with 100mil spacing grid.

Initial ATtiny1626 development board design
Initial designFirst iteration of ATtiny1626 development board layout.
Final ATtiny1626 development board design with all components
Final designComplete ATtiny1626 development board with connectors, mounting holes, and optimized trace routing.

Download Design Files

  • ATtiny_QFN.zip — Complete KiCad project files for ATtiny1626 development board

RP2354A Development Board

Complex development board for RP2354A microcontroller with advanced routing and component placement.

RP2354A development board design
RP2354A board designComplete PCB layout for RP2354A development board with complex routing and component placement.

Download Design Files

Reflections & Learnings

Key insights and learnings from working with interface and application programming.

Contributions

Acknowledgements and team roles for wildcard week PCB engraving work.

Wildcard Week Session

  • Quentin and Anthony: Ran the wildcard week session, providing guidance and support for PCB engraving projects.
  • Quentin: Designed the RP2354A development board before the session and finished the ATtiny1626 design with us during the wildcard session.

Ethical AI Use

Transparent documentation of AI assistance used in this week's wildcard week assignment page creation.

Week 13 Assignment Page Creation

Complete Cursor AI transcript for Week 13 wildcard week assignment page creation. This comprehensive conversation covers the creation and population of the Week 13 HTML page, including lecture and recitation notes, PCB engraving assignment documentation, design files integration, and comprehensive page structure development. The transcript demonstrates the collaborative process of building professional documentation with structured content, embedded media, and comprehensive design file documentation.

Related to: Complete Week 13 documentation including Lecture Notes, Recitation Notes, Assignment, Group Assignment, Design Files, and overall page structure

View HTML Transcript Download Markdown Transcript

Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License

``` Updated both highlights to match the week11 "Invisible String Final PCB Layout" styling: 1. **Removed extra margins** — Removed `margin-top` and `margin-bottom` from the container divs 2. **Heading spacing** — Changed heading margin back to `8px` to match other highlights 3. **Padding on image** — Moved padding from the container to the image itself (`padding:8px`) 4. **White background** — Added `background:white;` to the images 5. **Container styling** — Removed padding from the container, keeping it consistent with other highlights Both "ATtiny1626 Board Design" and "RP2354A Board Design" now match the week11 pattern: same size as other highlights with whitespace around the images. No linting errors found.