# Final project documentation updates
_Exported on 12/15/2025 at 21:18:07 EST from Cursor (2.1.39)_
---
**User**
General commands for cursor — 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
1. take a summary of my week 14 system integration on week14.html, and make a system integration section in finalproject.html somewhere (find the best place to put it), add each day as a subsection. and make sure system integration is in the table of contents. add a link to full details on finalproject.html that takes you to week14.html and add links along the summary in finalproject.html to important spots of system integration throughout the section.
2. add a final project masterpiece section on finalproject.html and embed the video from week14/highlights/finalprojectdemo.mp4 with a brief description. link it in week14.html and also link it on youtube: https://youtu.be/4mIPPKHv3AU?si=bMCngMzhDp3IjFNQ
3. update the final project highlights with new rows (keep the existing highlights as is), just add the same system integration highlights from week14.html as additional rows beneath them. make sure everything links you to where it is
---
**Cursor**
Reviewing the relevant files to understand the structure.
Searching for specific sections in these files:
Reading specific sections to understand the structure:
Searching for system integration highlights in week14.html:
Reading the day sections to create summaries:
Finding the best place in finalproject.html to add the system integration section:
Creating the system integration section and updating the necessary parts. Starting with a todo list:
Adding the system integration section after week13:
```html
Final Project · HTMAA 2025 · Saleem A. Al Dajani
Interactive selfie capture system with touch controls and real-time display
Vision Board
Conceptual visualization of the multimodal intrinsic capacity assessment system integrating grip strength, voice analysis, facial recognition, video motion capture, reaction time measurement, and wearable accelerometer data.
Intrinsic Capacity (IC) Coverage by Digital Biomarkers
Domain
Grip
Voice
Face
Video
Reaction Time
Wearable
Locomotor
✅
🔸
🔸
✅
🔸
✅
Cognition
❌
✅
🔸
🔸
✅
🔸
Vitality
✅
✅
✅
✅
🔸
✅
Sensory
❌
✅
✅
✅
✅
🔸
Psychological
❌
✅
✅
✅
🔸
✅
✅ Strong coverage |
🔸 Partial/indirect |
❌ Not covered |
View full table →
Multimodal IC Pipeline
Inputs: Grip Strength, Voice, Face, Video, Reaction Time, Wearable Accelerometer
Development Approach: Following the spiral model methodology, this final project will iterate through multiple development cycles, each building upon previous work while addressing new requirements and risks.
This snapshot covers the subsystems and documentation that will be shown during the midterm review. Links jump directly to the supporting sections with detailed evidence.
Featured Subsystems
Camera subsystem — Edge inference demos and selfie capture loop.
Instructor meeting hold — Thursday, Nov 12 at 10:00 AM ET reserved via the shared HTMAA midterm review sheet.
Execution Schedule (Timeline Snapshot)
Condensed from the Week 8–13 development timeline: each sprint builds toward final integration, mirroring the gantt chart below.
Week 8 · Output Devices: figuring out wiring for real-time display states.
Week 9 · Molding & Casting: learn how to cast custom housings and refine structural components.
Week 10 · Mechanical Design: figure out ergonomic enclosure and calibration fixtures.
Week 11 · Networking: program BLE/Wi-Fi telemetry and wearable data fusion.
Week 12 · Interface/App: create mobile UI, cloud bridge, and IC scoring pipeline.
Week 13 · Final Integration: run validation passes, document results, and prep deployment.
Instructor Review Logistics
Calendar hold sent for Thursday, Nov 12 at 10:00 AM ET (38-501 conference room) per the shared HTMAA scheduling sheet. Agenda covers subsystem demos, weekly documentation spot checks (Weeks 0–9), and next-sprint alignment. Meeting slot referenced in the midterm review schedule; awaiting final confirmation via class Slack.
System Architecture
Updated block diagram highlighting the multimodal sensing stack (grip, voice, face, motion, wearables), on-device inference layers, and real-time feedback channels that feed the intrinsic capacity score.
Development Timeline
Timeline aligns subsystem sprints with HTMAA milestones: output devices (Week 8), molding and casting (Week 9), mechanical design (Week 10), networking and communications (Week 11), app programming (Week 12), and final integration (Week 13).
Remaining Tasks (Snapshot)
Weeks 0–9 locked in the core subsystems—documentation workflow, cutting and molding for the housing, embedded prototypes for reaction timing, SenseCraft camera inference, and early grip/voice rigs. The checklist below captures what still needs to happen to converge on the integrated MirrorAge system.
Hardware Integration
Consolidate grip, voice, camera, reaction-time, and wearable sensor harnesses into the MirrorAge enclosure.
Finish molding/casting iterations for the ergonomic housing and align mounting features for PCBs and haptics.
Firmware & Edge AI
Stabilize onboard inference for SenseCraft vision models and voice-age pipelines on the XIAO ESP32S3.
Calibrate grip-force and reaction-time firmware for repeatable sampling; close the loop to haptic/display feedback.
Networking & Data Fusion
Bring up BLE/Wi-Fi data paths for wearable accelerometer streaming and cloud logging of intrinsic capacity scores.
Implement the fusion layer that combines per-domain scores into an overall IC metric with on-device storage.
Interface & UX
Finish mobile/web dashboard mockups for user onboarding, data review, and device calibration workflows.
Finalize real-time mirror feedback cues (display states, haptics, lighting) tied to sensor status and IC outcomes.
Validation & Documentation
Run end-to-end system tests (sensor capture → fusion → feedback) and document calibration procedures.
Record the one-minute video, finalize final presentation assets, and polish the bill of materials for review.
Week 14 System Integration Plan
Detailed day-by-day schedule for final system integration, covering design, fabrication, programming, testing, and documentation. This plan outlines the path to completing the MirrorAge system integration and preparing for final presentation. View on Week 14 page →
The act of bringing something to a conclusion or ending in a decisive manner. The ability to efficiently finish tasks and projects with a goal-oriented mindset.
Wednesday
Morning
Publish system integration plan on website
Update weekly assignment sections on final project page (weeks 10-13)
Link final project design files
Update reflections and learnings
Update picture of prism holder
Add final pictures to Slack canvases
Create schematic between boards (wired and wireless) — updated system diagram on PPT-like page
Start CAD model of system
Place final order
Afternoon & Evening
Design:
Boards: Combine OLED screen/accelerometer with pulse oximeter board in a new board (maybe upgrade to small TFT as minor)
Boards: Speaker board with realtime amplifier and TFT (on the load cell fixed board)
Band: Mold design
Cases: 3D print mountable cases for the boards
Integrate designs into final CAD
Document design
Finish CAD model of system
Thursday
Fabricate
Milling boards
Print mold and cast band
Print cases
Solder
Solder components on milled boards
Connect boards with wired (and wireless connection codes)
Finishing
Mirror on screen (easy way with the film)
Documentation
Document fabrication
Friday
Programming
Board level codes
Server level codes
Documentation
Document codes
Completion
Finish anything else
Saturday
Programming & Testing
Demo integrated system
Test integrated system
Documentation
Document testing and evaluation
Review and complete documentation (list of questions)
Make the video by collaging documentation
Sunday
Fill up any gaps
Prepare demo on tensegrity table
Finalize 1-slide
Work on minors
If done, work on if there's time
Monday Morning
Transport demo on tensegrity table
Fill up any gaps
Work on minors
Specific Tasks to Complete This Week
Major Tasks
CAD model of system
Speaker board with realtime amplifier
Combine screen/accelerometer with pulse oximeter board in a new board
Mold and cast band
Design and fabricate casing (print)
Schematic between boards (wired and wireless) — updated system diagram on PPT-like page
Serial connection between pulse oximeter and tiny blinking heart for BPM (BPM from IR, SpO2 from delta)
Combine multiple boards on the same WiFi (switching tabs is easy way, board hosting the webpage querying and update or Python-based server somewhere where everything posting data, Raspberry Pi)
Put+program everything together according to the above (with WiFi for now)
MirrorAge is a self-contained edge-AI mirror that captures grip strength, facial imagery, voice, motion, and reaction time to estimate intrinsic capacity in real time.
The platform fuses weekly prototypes—ReactionAge latency tests, 3D printed grip mechanics, SenseCraft camera inference, and molded structural elements—into a multimodal mortality risk profiler.
Subsystems in progress: reaction-time module, SenseCraft FaceTTD inference stack, VoiceAge microphone pipeline, wearable streaming via BLE, and molded structural packaging.
Clinical motivation: translate WHO intrinsic capacity domains into measurable digital biomarkers that flag functional decline earlier than chronological age alone.
Project Goals
Deliver multimodal IC scoring Fuse grip, face, voice, reaction-time, and wearable streams on-device to output an intrinsic capacity score plus domain deltas.
Fabricate modular, serviceable hardware Iterate laser-cut tensegrity mirror shells, 3D printed torsional grips, custom PCBs, and silicone cast fixtures that assemble without bespoke tooling.
Validate against ground truth Benchmark embedded inferences against published datasets (Blomkvist et al. 2017, Fuentealba et al. 2025) and lab-collected pilots to quantify accuracy, latency, and reliability.
Timeline & Milestones
Week 10 · Hardware convergence Integrate SenseCraft FaceTTD camera, ReactionAge latency module, and newly milled PCB into a single ESP32S3 backplane.
Week 12 · Midterm review build Finish molded mirror enclosure, bring up BLE wearable link, and demo live IC score during midterm critique.
Final week · Validation & documentation Execute pilot data collection, refine model weights, and release reproducible fabrication + firmware packages.
Documenting the final project masterpiece that integrates the range of units covered, addressing all required questions.
What does it do?
MirrorAge captures synchronized digital biomarkers—camera frames processed with on-device FaceTTD models, VoiceAge microphone samples, grip strength torque, wearable accelerometry, and ReactionAge latency—to estimate intrinsic capacity and time-to-death acceleration.
A XIAO ESP32S3 Sense orchestrates sensing, performs Edge Impulse inference, and displays a live mortality-risk score on the OLED while logging packets to a Python analytics notebook.
Who's done what beforehand?
The concept builds on WHO intrinsic capacity framing and recent mortality-risk studies: Niccoli & Partridge (2012) establish age as the dominant chronic-disease predictor; Fuentealba et al. (Nature Aging 2025) show blood-based IC clocks outperform chronological models;
Zhavoronkov & Bhullar (2015) and Lancet Healthy Longevity editorials motivate treating functional decline as the actionable signal.
This project translates those findings into an accessible, multimodal measurement mirror that can operate outside hospital labs.
What sources did you use?
Primary references include Nature Aging 2025 intrinsic capacity papers, the PLOS ONE ReactionAge dataset (Blomkvist et al. 2017), Edge Impulse SenseCraft documentation, Smooth‑On Mold Star technical bulletins, RotoMetals alloy certificates, MIT HTMAA recitations, and the open-source GRPR grip-strength meter.
Design inspiration and safety notes were consolidated from Anthony Pennes' HTMA guides and Fab Academy molding tutorials.
What did you design?
• Laser-cut cardboard origami mirror frame and tensegrity-inspired floating mount (Weeks 1 & 6)
• ReactionAge firmware + enclosure with statistical post-processing dashboards (Week 2)
• 3D printed torsional spring grip module tuned for ±40 kg ranges (Week 3)
• KiCad/Fusion carrier PCB for the ESP32S3 Sense with OLED, force, and BLE breakouts (Week 5)
• Edge Impulse deployment pipeline with grayscale dithering overlay and live inference UX (Weeks 7–8)
• CAM toolpaths, silicone molds, and Drystone casts for structural packaging (Week 9)
What materials and components were used?
Seeed XIAO ESP32S3 Sense module with OV2640 camera and PDM mic, SparkFun Qwiic button and force sensors, SSD1306 OLED, wearable IMU node (Bosch BHI260), laser-cut cardboard/birch sheets, PLA+/Onyx filament, Mold Star 30 silicone, Drystone gypsum, Roto281 fusible alloy, and embedded fasteners/heat-set inserts.
Where did they come from?
Electronics from Seeed Studio, SparkFun, Digi-Key, and Adafruit; molding supplies and silicones from Reynolds Advanced Materials; Drystone and Hydro-Stone from USG via the MIT CBA stockroom; fusible alloys from RotoMetals; structural lumber and plywood from MIT's shop inventory; filaments from Prusa Research and Markforged.
How much did they cost?
Current spend: $96.34 for ReactionAge components (Week 2 BOM) + $78.42 for SenseCraft camera stack (XIAO ESP32S3 Sense, OLED, cabling) + $42.10 for molding media (Mold Star 30 quart, Drystone, release agents) = $216.86 to date.
Remaining allocation (~$130) is earmarked for BLE wearable hardware and final enclosure finishes; detailed line items tracked in the Airtable budget and mirrored in each weekly BOM CSV.
What parts and systems were made?
Custom origami mirror frame, 3D printed torsional grip shell, machined floating base, silicone molds and Drystone casts for arrow-inspired structural ribs, bespoke ESP32S3 breakout PCB, laser-cut ReactionAge control panel, and assembled sensor tower linking camera, OLED, and wearable gateway.
What tools and processes were used?
Parametric CAD in Fusion 360, laser cutting (Epilog) for origami tiles, Prusa MK4 FDM printing, Formlabs SLA for detail inserts, ShopBot CNC and Bantam PCB milling, silicone mixing/casting under vacuum, Edge Impulse model training, PlatformIO firmware, and Python/NumPy validation notebooks.
What questions were answered?
• Can consumer-grade sensors reproduce published reaction-time age curves? (Yes—ReactionAge matched Blomkvist et al. regression within 4.6 ms RMSE.)
• Will SenseCraft FaceTTD run locally on ESP32S3 with acceptable latency? (Yes—~310 ms/inference at 30% baseline accuracy, highlighting dataset needs.)
• Does molded packaging improve sensor placement repeatability? (Yes—silicone nests held camera ±0.5 mm, reducing alignment drift seen in cardboard prototypes.)
What worked? What didn't?
✅ Floyd–Steinberg dithering produced clear OLED previews; ✅ ReactionAge firmware maintained ±1 ms jitter; ✅ Molded Drystone ribs stiffened mirror shell without excess weight.
⚠️ FaceTTD accuracy plateaued at 30% due to limited training diversity; ⚠️ VoiceAge requires more MFCC samples to sustain 0.64-year MAE; ⚠️ Grip spring fatigue highlighted need for fiber-reinforced print or machined aluminum insert.
How was it evaluated?
Bench tests compare embedded predictions to published curves and desktop baselines: ReactionAge latency vs. Wii Balance Board golden data; FaceTTD inferencing cross-validated against Edge Impulse cloud classifier; VoiceAge MFCC regression verified through train/holdout splits; mechanical fixtures inspected with feeler gauges and dial indicators for tolerance drift.
What are the implications?
A portable intrinsic capacity mirror supports proactive geriatric screening, telehealth coaching, and longitudinal studies that correlate functional decline with interventions.
By grounding hardware in open-source parts and HTMAA fabrication methods, the system can be replicated across labs and community clinics to accelerate validation of digital aging biomarkers and personalize longevity therapies.
Design
Your project should incorporate 2D and 3D design, multiple additive and subtractive fabrication processes, electronics design and production, embedded microcontroller design, interfacing, and programming, system integration and packaging.
2D Design
2D design work for the multimodal intrinsic capacity assessment system:
Cardboard origami tiling for circular mirror frame, optimized for kerf learned during Week 1 laser characterization.
Vinyl-cut ReactionAge control labels and MirrorAge fascia decals for rapid UI readability.
KiCad/Fusion schematics + polygon pours for ESP32S3 carrier, force sensing front-end, and OLED interposer.
2D shop drawings for CNC floating base, including registration dowels and silicone mold parting lines.
Figma wireframes outlining the midterm web dashboard and on-device OLED states.
Subtractive: Laser cutting, milling for precision parts
Electronics: PCB design and production
Programming: Embedded microcontroller development
Bill of Materials
Where possible, I fabricated parts rather than buying them. This table summarizes all unique components in the final MirrorAge system, their approximate costs, and where they are used.
A mirrored copy of this bill of materials also appears on the Week 14 system-integration page for cross-linking directly from the integration steps
(Week 14 BOM).
Grip-strength molds, band molds, structural ribs
(Week 9,
Week 14)
Fasteners
M2/M3 hardware, heat-set inserts, misc. screws
Assorted
~$0.10–$0.30 ea.
$20.00 (bundle)
All mechanical assemblies (watch, grip rig, camera mount, demo table)
Estimated Total Project Cost
Electronics ≈ $190 · Mechanical & materials ≈ $130 ·
Total ≈ $320 (excluding lab-provided consumables and reused stock).
Exact per-week line items remain in the weekly documentation tables (for example
ReactionAge BOM CSV in Week 2),
while this table captures the consolidated, unique parts that make up the final integrated MirrorAge system.
Fabrication Process
Week-by-week fabrication rolled forward subsystems toward the integrated mirror:
Week 1 laser-cut origami tiles for the circular bezel; Week 2 PCB milling + soldering for ReactionAge;
Week 3–4 torsional spring 3D prints and sanding jigs; Week 5 copper-clad milling and reflow of the ESP32S3 carrier;
Week 6 ShopBot machining of the floating base; Week 8 resin + FDM camera enclosure build; Week 9 wax machining, Mold Star casting, and Drystone ribs.
Each step captured feeds-and-speeds, toolpaths, and fixturing photos embedded in the weekly pages for replication.
Testing & Validation
Validation combined bench instrumentation and statistical analysis: oscilloscope timing to verify ReactionAge jitter, Edge Impulse confusion matrices for FaceTTD and VoiceAge,
Instron pull tests for the torsional grip cartridge, IR thermography while curing Mold Star molds, dial-indicator checks on CNC-machined bases, and adhesive shear testing on mirror mounts.
Data are logged to CSV via the ESP32S3 and compared against published baselines inside the midterm Jupyter notebook.
Individual Mastery and Independent Operation
Projects can be separate or joint, but need to show individual mastery of the skills, and be independently operable.
Individual Mastery
Demonstration of individual skills across all course units:
2D and 3D Design
Modeled the tensegrity floating mirror, torsional grip shells, and camera bezel in Fusion 360 and Onshape.
Drove design reviews with Anthony/Neil to lock tolerances, assembly order, and module interface specs.
Demonstrates mastery across cutting, 3D printing, machining, electronics, networking, and interface programming units.
Documentation cross-linked via weekly pages, GitHub repos, and BOM spreadsheets for traceability.
Group Assignments
Collaborative work and individual contributions:
Embedded programming group: authored workflow trade-off analysis and repo organization that seeded ReactionAge firmware patterns.
Molding & casting group: led SDS review, material trials, and mixing SOP that informed final mirror mold.
Shared camera dev sessions with peers to improve Edge Impulse dataset collection and SenseCraft deployment strategies.
Useful Documentation
Helpful resources, documentation, and design files for the multimodal intrinsic capacity assessment system.
Open Source Grip Strength Meter
A cost-effective $50 grip strength measurement system that can be further optimized for our multimodal assessment platform.
This open-source design provides an excellent foundation for integrating grip strength measurement into our intrinsic capacity assessment system,
with potential for cost reduction through signal multiplexing on a single processor.
Detailed technical pipeline for processing multiple digital biomarkers to generate intrinsic capacity scores.
Pipeline Architecture
Inputs
• Grip Strength
• Voice
• Face
• Video (motion/gait)
• Reaction Time
• Wearable Accelerometer
→
Feature Extraction
Strength metrics
Prosody features
Facial landmarks
Gait parameters
Response latency
Activity patterns
Embeddings
Features converted to vector representations for multimodal fusion
→
Fusion Layer
Combines multimodal features using attention mechanisms
Output
• Overall IC Score
• Domain sub-scores
→
Domain Scores
Locomotor
Cognition
Vitality
Sensory
Psychological
Weekly System Development Breakdown
How each week of HTMAA 2025 builds toward the complete multimodal intrinsic capacity assessment system.
Week 0: Project Ideation
Initial concept development and planning
Project planning and documentation structure
Research direction and concept sketches
Week 1: Precision Cutting
Laser and vinyl cutting techniques
Device housing components via laser cutting
Sensor mounting brackets and enclosures
Vinyl cutting for device labeling and UI elements
Week 2: Embedded Programming
Electronics basics and microcontroller programming
Microcontroller programming for data collection
Basic sensor interface circuits
Week 3: 3D Scanning & Printing
3D technologies for device components
3D scanning for custom component design
3D printing for device housings
Week 4: Electronics Design
EDA and schematic design
PCB design for grip strength measurement
Sensor interface circuits and signal conditioning
Power management and data storage systems
Week 5: Electronics Production
PCB fabrication and assembly
PCB fabrication and debugging
Component assembly and testing
Week 6: Computer-controlled Machining
CAM and precision milling
Precision components via milling
Custom mechanical parts
Week 7: Input Devices
Sensor integration for data collection
Force sensors for grip strength measurement
Microphones for voice analysis
Camera systems for facial expression analysis
Reaction time measurement circuits
Week 8: Output Devices
Actuators and system integration
Display systems for real-time feedback
Haptic feedback for user interaction
Week 9: Molding & Casting
Forming and resin techniques
3D printing and molding for custom components
Silicone casting for device components
Week 10: Mechanical & Machine Design
System integration and mechanical design
Mechanical design for ergonomic device housing
System integration and calibration protocols
Week 11: Networking & Communications
Connectivity and communication protocols
Bluetooth/Wi-Fi connectivity for data transmission
Wearable accelerometer integration and data fusion
Week 12: Interface & Application Programming
UI development and application programming
Mobile app development for user interface
Cloud integration for data storage and analysis
Machine learning pipeline for IC score calculation
Week 13: Wildcard & Final Integration
Final orders and complete system deployment
Final testing, validation, and documentation
System integration and deployment
Camera Subsystem
Advanced camera system implementation using XIAO ESP32S3 Sense with real-time image processing, EdgeAI integration, and interactive selfie capture functionality.
System Overview
The camera system successfully captures images, processes them into bitmaps, and displays them on an OLED screen using advanced Floyd-Steinberg dithering algorithms.
Video Demonstrations
Camera Bot Selfie
Demonstration of the interactive selfie capture system with touch controls
Picture of Picture
Meta demonstration showing the camera system capturing its own display
Code Implementation
60-Second Auto Capture System
Automated camera system that captures and displays images every 60 seconds using advanced image processing techniques.
1. Initialize camera with PSRAM frame buffers
2. Configure OLED display (128x64 pixels)
3. Set up 60-second capture interval timer
4. In main loop:
a. Check if 60 seconds have elapsed
b. Capture image from camera
c. Process image:
- Downsample to 128x64 via box averaging
- Apply contrast stretch (linear scaling)
- Perform Floyd-Steinberg dithering
d. Display processed bitmap on OLED
e. Release frame buffer
5. Repeat process
Touch-Controlled Capture System
Interactive camera system with touch controls allowing manual capture triggers in addition to automatic timing.
1. Initialize camera and OLED display
2. Set up touch pins (GPIO1 & GPIO2) with threshold detection
3. Configure 60-second auto-capture timer
4. In main loop:
a. Update touch sensor readings
b. Detect touch press events (justPressed)
c. Check for capture trigger:
- Touch press OR 60-second timer elapsed
d. If triggered:
- Capture image from camera
- Process image (same as auto version)
- Display on OLED
- Reset timer
5. Continue monitoring for next trigger
The system captures photos, converts them to bitmaps using advanced image processing algorithms, and displays them on the OLED screen.
I'm also exploring integration with ML models, either through online API calls or by embedding TinyML model parameters from Python to C++.
Future development includes live streaming real-time video with ML prediction updates based on variable observation times,
and exploring Edge Impulse models as an alternative to manual Python-to-C++ conversion for faster deployment.
EdgeAI/TinyML Integration
Edge AI can also be implemented using Edge Impulse models, which may be faster than manually converting Python models to C++.
The SenseCraft AI platform provides a streamlined approach to training and deploying ML models directly on the XIAO ESP32S3.
Deploy inference bundle to the SenseCraft board alongside the camera stack.
Benchmark latency and accuracy against baseline VoiceAge models and document calibration protocol.
Week 0 - Introduction & Design
Project ideation and initial concept development for bioprinting rejuvenated tissue and aging biomarker devices.
Project planningConcept sketchesResearch direction
System Integration Plans: Establish the foundational architecture for multimodal data collection by designing the overall system framework that will integrate all six digital biomarkers (grip strength, voice, face, video, reaction time, wearable accelerometer) into a cohesive intrinsic capacity assessment platform.
Mapped the MirrorAge subsystem architecture, assembled the intrinsic capacity literature stack, and kicked off BRR/IRB coordination so fabrication sprints stay aligned with clinical requirements.
Week 1 - Principles & Cutting
Version control, laser cutting, and vinyl cutting techniques applied to final project components.
Laser cuttingVinyl cuttingVersion control
System Integration Plans: Fabricate precision-cut housing components and mounting brackets for all sensor modules (force sensors, microphones, cameras, reaction time circuits) using laser cutting, while creating vinyl-cut labels and UI elements for device identification and user guidance.
Characterized laser kerf, produced the origami mirror frame tiles, and generated vinyl interface labels—locking in enclosure dimensions and user UI cues for the mirror shell.
Week 2 - Embedded Programming
Electronics basics and embedded programming for the aging biomarker device components.
MicrocontrollersProgrammingElectronics
System Integration Plans: Develop embedded programming protocols for real-time data collection from all six biomarker sensors, implementing initial signal processing algorithms and establishing the communication framework for multimodal data fusion.
Built the ReactionAge firmware + enclosure, published the first BOM, and validated timing pipelines that will feed the MirrorAge IC fusion engine.
Week 3 - 3D Scanning & Printing
3D scanning and printing techniques for bioprinting components and device housings.
3D scanning3D printingAI tools
System Integration Plans: Create custom 3D-printed components for camera mounting systems and facial recognition hardware, while developing 3D scanning protocols for ergonomic device design that accommodates all sensor modalities in a user-friendly form factor.
Modeled and printed the torsional grip spring, performed 3D scans for ergonomic fixtures, and captured training assets for face/gait datasets.
Week 4 - Electronics Design
EDA and schematic design for the aging biomarker device electronics.
EDA toolsSchematic designCircuit design
System Integration Plans: Design comprehensive PCB schematics that integrate force sensor circuits for grip strength measurement, microphone preamplifiers for voice analysis, camera interfaces for facial recognition, and timing circuits for reaction time assessment into a unified electronics platform.
Completed the Fusion 360/KiCad schematic/PCB layout for the ESP32S3 carrier tying together force, audio, camera, reaction, and wearable interfaces.
Week 5 - Electronics Production
PCB fabrication, debugging, and assembly for the biomarker device.
PCB fabricationDebuggingAssembly
System Integration Plans: Fabricate and assemble the integrated PCB containing all sensor interfaces, implementing power management systems for continuous operation and establishing data storage protocols for the multimodal biomarker data collection system.
Fabricated and assembled the carrier PCB, brought up power domains, and verified sensor buses—establishing the electronics backbone for integration.
Week 6 - Computer-controlled Machining
CAM and milling for precision components and device housings.
CAMMillingPrecision machining
System Integration Plans: Machine precision mechanical components for the integrated device housing using computer-controlled milling, ensuring proper alignment and mounting for all sensor modules while maintaining ergonomic design for user comfort during multimodal data collection.
Machined the floating mirror base and tensegrity nodes, refining fixturing that ensures repeatable camera and grip alignment in the final assembly.
Week 7 - Input Devices
Sensors and embedded architectures for data collection in the biomarker device.
SensorsInput devicesData collection
System Integration Plans: Integrate all six input sensor systems (force sensors for grip strength, microphones for voice analysis, cameras for facial recognition and gait analysis, reaction time circuits, and wearable accelerometer) into the unified data collection platform with real-time processing capabilities.
Integrated the force sensor, microphone, and ReactionAge modules on the carrier, logging synchronized packets that exercise the multimodal intake stack.
Week 8 - Output Devices
Actuators and system integration for the biomarker device outputs.
ActuatorsOutput devicesSystem integration
System Integration Plans: Implement output devices including display systems for real-time intrinsic capacity feedback and haptic feedback mechanisms for user interaction, creating an intuitive interface for the multimodal biomarker assessment system.
Deployed the SenseCraft FaceTTD pipeline on the XIAO ESP32S3, implemented OLED dithering previews, and confirmed end-to-end edge inference latency.
Week 9 - Molding & Casting
Forming and resin techniques for bioprinting molds and device components.
MoldingCastingResins
System Integration Plans: Create custom molded components for the bioprinting aspects of the project and develop specialized casings for sensor protection, ensuring the device can withstand continuous use during multimodal data collection sessions.
Machined wax molds, cast Mold Star silicone and Drystone ribs, and prototyped arrow-inspired shells that stabilize the mirror and protect embedded sensors.
Week 10 - Mechanical & Machine Design
Kits and mechanical design for the bioprinting and biomarker device systems.
Mechanical designMachine designSystem integration
System Integration Plans: Complete the mechanical design integration of all system components, implementing calibration protocols for sensor alignment and developing the complete mechanical framework that houses all six digital biomarker measurement systems.
Developed mechanical actuation systems including tapping and swiping mechanisms for phone interaction, integrated camera with Edge AI face detection and Wi-Fi livestreaming, designed and 3D-printed phone holder with amplifier, and prepared comprehensive midterm review documentation with system diagrams and timeline.
Week 11 - Networking & Communications
BLE, Wi-Fi, and communication protocols for the biomarker device connectivity.
BLEWi-FiCommunications
System Integration Plans: Implement wireless communication protocols (Bluetooth/Wi-Fi) for seamless data transmission from all six sensor modalities, enabling real-time data fusion and establishing connectivity for the wearable accelerometer integration into the multimodal assessment system.
Implemented Wi-Fi camera livestreaming for real-time video transmission, developed ESP-NOW networking protocols for device communication, designed and milled PCBs for networking components, and explored Meshtastic for long-range communication capabilities.
Week 12 - Interface & Application Programming
UI and application development for the biomarker device interface.
UI designApplicationsUser interface
System Integration Plans: Develop the complete user interface and application programming for the multimodal system, implementing the machine learning pipeline for intrinsic capacity score calculation and creating cloud integration for comprehensive data storage and analysis of all biomarker measurements.
Created Wi-Fi web interface for real-time pulse oximeter readings with live plotting, developed grip strength measurement device with load cell and integrated GUI, implemented OLED button user interface for device control, and established video streaming capabilities for sensor data visualization.
Week 13 - Wildcard & Final Orders
Final orders and wildcard week activities for project completion.
Final ordersWildcard activitiesProject completion
System Integration Plans: Complete final system integration, testing, and validation of the complete multimodal intrinsic capacity assessment platform, ensuring all six digital biomarkers work cohesively to provide accurate WHO-defined intrinsic capacity scores across all five domains (locomotor, cognition, vitality, sensory, psychological).
Designed and fabricated ATtiny1626 tiny development board with fiber laser PCB engraving, created glass engraving system with UV laser including blinking heart integration for visual feedback, milled mounting holes and completed board assembly, and prepared final board designs for system integration.
System Integration
Final integration week focused on bringing all subsystems together, completing hardware fabrication, firmware integration, and documentation for the MirrorAge system presentation. View full details →
Initial system integration work focused on subsystem validation, CAD model consolidation, and design backbone acquisition for band integration. Conducted comprehensive testing of all subsystems to ensure proper functionality, identified and resoldered defective joints, and exported CAD models of all PCBs into a unified assembly model.
Physical integration of subsystems into the complete demo table assembly, including mechanical component fabrication and electrical board consolidation. Integrated the complete demo table with precise placement of the MirrorAge handgrip subsystem and aging clock subsystem, providing a unified platform for system demonstration.
Continued fabrication work integrating all manufacturing processes. Focused on completing physical components and preparing subsystems for final assembly and testing.
Comprehensive subsystem integration combining 2D fabrication (laser cutting and vinyl cutting), 3D printing (rigid and flexible components), PCB milling (single and double-sided boards), and molding/casting to complete all physical components. Upgraded MirrorAge TFT board to v13 and aging clock TFT board to v16 with optimized component placement and routing. Established reliable I²C bus communication and validated all sensor addresses.
Final integration day focused on closing the watch subsystem, soldering and verifying all double-sided boards, refining molded bands, and assembling the complete MirrorAge demo with both the aging clock and grip-strength subsystems fully wired and tested. Completed rivet installation for plated through-holes, sensor bring-up (accelerometer, pulse oximeter, OLED/TFT displays), and full system integration on the tensegrity demo table. The integrated system successfully demonstrated synchronized sensor readouts and display behavior across all boards.
Final project presentation and demonstration of the complete MirrorAge system. Showcased the integrated aging clock and grip-strength subsystems working together on the demo table, demonstrating real-time sensor data collection and display synchronization. View final presentation demo →
Full Documentation: For complete details, design files, code, and comprehensive documentation of the system integration process, see Week 14: System Integration.
Design Files
Complete repository of all design files, CAD models, schematics, PCB layouts, firmware, and fabrication files from Week 0 through Week 14, organized by week and component type.
Note: Additional design files, firmware, and documentation can be found in the respective week pages. Some files are part of larger archives (ZIP files) that contain multiple related design files.
Reflections & Learnings
Comprehensive reflections on the MirrorAge Intrinsic Capacity Mirror project development journey.
Modular system design allows for incremental development and component-level testing throughout the semester
Integration of mechanical, electrical, and software subsystems requires careful planning and coordination
Iterative design and prototyping revealed the importance of early testing and validation
Documentation and knowledge transfer are critical for project continuity and future improvements
The project successfully demonstrates how digital fabrication and embedded systems can create meaningful health assessment tools
Contributions
Acknowledgements and contributions that made this project possible.
Gladyshev Lab and Collaborators
Special thanks to the Gladyshev Lab and collaborators for the fruitful discussions that led to this multimodal intrinsic capacity assessment idea,
which supplements my PhD research goals in aging and longevity. The conceptual framework for integrating multiple digital biomarkers
to assess intrinsic capacity domains emerged from collaborative research discussions on aging biomarkers and healthspan assessment.
Transparent documentation of AI assistance used in this final project work, following course guidelines for ethical AI usage.
📋 General Guidelines: See General Commands for Cursor on the homepage for standard guidelines and commands used consistently throughout documentation development.
Cursor · Project Plan & Weekly Schedule
Comprehensive Cursor AI assistance for outlining the project plan and weekly schedule, including documentation structure, content organization, systematic updates across all week pages and the final project page, media integration, and summary generation workflows.
Cursor AI aligned the midterm review plan with updated system diagram, timeline, and remaining-task summaries, then refreshed finalproject.html to remove legacy bioprinting language and re-point internal links. The full transcript and generated HTML are available for review.
Cursor AI assistance for adding a white background behind the photo in the Final Project Spiral Development Model section on finalproject.html. The image container was updated with white background, padding, and rounded corners for improved visual presentation.
Cursor AI distilled Week 0–9 documentation and the Oct 31 lab meeting deck into midterm-ready narrative, cost, and validation content, replacing every placeholder in finalproject.html.
Transcript archived in markdown and HTML (generated via scripts/md_to_html_converter.py) for transparency.
ChatGPT was used to research and develop the multimodal intrinsic capacity assessment framework, including the comprehensive coverage analysis table and technical pipeline design.
The AI assisted with structuring the WHO-defined intrinsic capacity domains, identifying appropriate digital biomarkers, and designing the fusion architecture for multimodal data processing.
Cursor AI assisted with developing the complete final project page structure, implementing the multimodal intrinsic capacity assessment framework, and creating comprehensive documentation.
The AI helped with HTML structure, responsive design, weekly system integration plans, and organizing the technical documentation for the complete biomarker assessment system.
Cursor AI assisted with finalizing the project presentation structure to ensure full compliance with MIT Academy project presentation requirements.
The AI helped implement all required sections including answering questions, design documentation, bill of materials, individual mastery requirements,
course presentation structure, and spiral model development approach visualization.
ChatGPT was used to discuss camera system implementation strategies, image processing algorithms, and EdgeAI integration approaches.
The AI assisted with understanding Floyd-Steinberg dithering implementation, touch sensor integration, and exploring TinyML deployment options for the XIAO ESP32S3 platform.
AI-Assisted Project Highlights and Camera Subsystem Development
Cursor AI assisted with adding the project highlights section featuring camera system achievements and creating a comprehensive camera subsystem section with detailed code implementations, video demonstrations, and EdgeAI integration documentation.
The AI helped with HTML structure, responsive design, image processing explanations, and organizing the technical documentation for the complete camera system showcase.
Interactive selfie capture system with touch controls and real-time display
Vision Board
Conceptual visualization of the multimodal intrinsic capacity assessment system integrating grip strength, voice analysis, facial recognition, video motion capture, reaction time measurement, and wearable accelerometer data.
Intrinsic Capacity (IC) Coverage by Digital Biomarkers
Domain
Grip
Voice
Face
Video
Reaction Time
Wearable
Locomotor
✅
🔸
🔸
✅
🔸
✅
Cognition
❌
✅
🔸
🔸
✅
🔸
Vitality
✅
✅
✅
✅
🔸
✅
Sensory
❌
✅
✅
✅
✅
🔸
Psychological
❌
✅
✅
✅
🔸
✅
✅ Strong coverage |
🔸 Partial/indirect |
❌ Not covered |
View full table →
Multimodal IC Pipeline
Inputs: Grip Strength, Voice, Face, Video, Reaction Time, Wearable Accelerometer
Development Approach: Following the spiral model methodology, this final project will iterate through multiple development cycles, each building upon previous work while addressing new requirements and risks.
This snapshot covers the subsystems and documentation that will be shown during the midterm review. Links jump directly to the supporting sections with detailed evidence.
Featured Subsystems
Camera subsystem — Edge inference demos and selfie capture loop.
Instructor meeting hold — Thursday, Nov 12 at 10:00 AM ET reserved via the shared HTMAA midterm review sheet.
Execution Schedule (Timeline Snapshot)
Condensed from the Week 8–13 development timeline: each sprint builds toward final integration, mirroring the gantt chart below.
Week 8 · Output Devices: figuring out wiring for real-time display states.
Week 9 · Molding & Casting: learn how to cast custom housings and refine structural components.
Week 10 · Mechanical Design: figure out ergonomic enclosure and calibration fixtures.
Week 11 · Networking: program BLE/Wi-Fi telemetry and wearable data fusion.
Week 12 · Interface/App: create mobile UI, cloud bridge, and IC scoring pipeline.
Week 13 · Final Integration: run validation passes, document results, and prep deployment.
Instructor Review Logistics
Calendar hold sent for Thursday, Nov 12 at 10:00 AM ET (38-501 conference room) per the shared HTMAA scheduling sheet. Agenda covers subsystem demos, weekly documentation spot checks (Weeks 0–9), and next-sprint alignment. Meeting slot referenced in the midterm review schedule; awaiting final confirmation via class Slack.
System Architecture
Updated block diagram highlighting the multimodal sensing stack (grip, voice, face, motion, wearables), on-device inference layers, and real-time feedback channels that feed the intrinsic capacity score.
Development Timeline
Timeline aligns subsystem sprints with HTMAA milestones: output devices (Week 8), molding and casting (Week 9), mechanical design (Week 10), networking and communications (Week 11), app programming (Week 12), and final integration (Week 13).
Remaining Tasks (Snapshot)
Weeks 0–9 locked in the core subsystems—documentation workflow, cutting and molding for the housing, embedded prototypes for reaction timing, SenseCraft camera inference, and early grip/voice rigs. The checklist below captures what still needs to happen to converge on the integrated MirrorAge system.
Hardware Integration
Consolidate grip, voice, camera, reaction-time, and wearable sensor harnesses into the MirrorAge enclosure.
Finish molding/casting iterations for the ergonomic housing and align mounting features for PCBs and haptics.
Firmware & Edge AI
Stabilize onboard inference for SenseCraft vision models and voice-age pipelines on the XIAO ESP32S3.
Calibrate grip-force and reaction-time firmware for repeatable sampling; close the loop to haptic/display feedback.
Networking & Data Fusion
Bring up BLE/Wi-Fi data paths for wearable accelerometer streaming and cloud logging of intrinsic capacity scores.
Implement the fusion layer that combines per-domain scores into an overall IC metric with on-device storage.
Interface & UX
Finish mobile/web dashboard mockups for user onboarding, data review, and device calibration workflows.
Finalize real-time mirror feedback cues (display states, haptics, lighting) tied to sensor status and IC outcomes.
Validation & Documentation
Run end-to-end system tests (sensor capture → fusion → feedback) and document calibration procedures.
Record the one-minute video, finalize final presentation assets, and polish the bill of materials for review.
Week 14 System Integration Plan
Detailed day-by-day schedule for final system integration, covering design, fabrication, programming, testing, and documentation. This plan outlines the path to completing the MirrorAge system integration and preparing for final presentation. View on Week 14 page →
The act of bringing something to a conclusion or ending in a decisive manner. The ability to efficiently finish tasks and projects with a goal-oriented mindset.
Wednesday
Morning
Publish system integration plan on website
Update weekly assignment sections on final project page (weeks 10-13)
Link final project design files
Update reflections and learnings
Update picture of prism holder
Add final pictures to Slack canvases
Create schematic between boards (wired and wireless) — updated system diagram on PPT-like page
Start CAD model of system
Place final order
Afternoon & Evening
Design:
Boards: Combine OLED screen/accelerometer with pulse oximeter board in a new board (maybe upgrade to small TFT as minor)
Boards: Speaker board with realtime amplifier and TFT (on the load cell fixed board)
Band: Mold design
Cases: 3D print mountable cases for the boards
Integrate designs into final CAD
Document design
Finish CAD model of system
Thursday
Fabricate
Milling boards
Print mold and cast band
Print cases
Solder
Solder components on milled boards
Connect boards with wired (and wireless connection codes)
Finishing
Mirror on screen (easy way with the film)
Documentation
Document fabrication
Friday
Programming
Board level codes
Server level codes
Documentation
Document codes
Completion
Finish anything else
Saturday
Programming & Testing
Demo integrated system
Test integrated system
Documentation
Document testing and evaluation
Review and complete documentation (list of questions)
Make the video by collaging documentation
Sunday
Fill up any gaps
Prepare demo on tensegrity table
Finalize 1-slide
Work on minors
If done, work on if there's time
Monday Morning
Transport demo on tensegrity table
Fill up any gaps
Work on minors
Specific Tasks to Complete This Week
Major Tasks
CAD model of system
Speaker board with realtime amplifier
Combine screen/accelerometer with pulse oximeter board in a new board
Mold and cast band
Design and fabricate casing (print)
Schematic between boards (wired and wireless) — updated system diagram on PPT-like page
Serial connection between pulse oximeter and tiny blinking heart for BPM (BPM from IR, SpO2 from delta)
Combine multiple boards on the same WiFi (switching tabs is easy way, board hosting the webpage querying and update or Python-based server somewhere where everything posting data, Raspberry Pi)
Put+program everything together according to the above (with WiFi for now)
MirrorAge is a self-contained edge-AI mirror that captures grip strength, facial imagery, voice, motion, and reaction time to estimate intrinsic capacity in real time.
The platform fuses weekly prototypes—ReactionAge latency tests, 3D printed grip mechanics, SenseCraft camera inference, and molded structural elements—into a multimodal mortality risk profiler.
Subsystems in progress: reaction-time module, SenseCraft FaceTTD inference stack, VoiceAge microphone pipeline, wearable streaming via BLE, and molded structural packaging.
Clinical motivation: translate WHO intrinsic capacity domains into measurable digital biomarkers that flag functional decline earlier than chronological age alone.
Project Goals
Deliver multimodal IC scoring Fuse grip, face, voice, reaction-time, and wearable streams on-device to output an intrinsic capacity score plus domain deltas.
Fabricate modular, serviceable hardware Iterate laser-cut tensegrity mirror shells, 3D printed torsional grips, custom PCBs, and silicone cast fixtures that assemble without bespoke tooling.
Validate against ground truth Benchmark embedded inferences against published datasets (Blomkvist et al. 2017, Fuentealba et al. 2025) and lab-collected pilots to quantify accuracy, latency, and reliability.
Timeline & Milestones
Week 10 · Hardware convergence Integrate SenseCraft FaceTTD camera, ReactionAge latency module, and newly milled PCB into a single ESP32S3 backplane.
Week 12 · Midterm review build Finish molded mirror enclosure, bring up BLE wearable link, and demo live IC score during midterm critique.
Final week · Validation & documentation Execute pilot data collection, refine model weights, and release reproducible fabrication + firmware packages.
Documenting the final project masterpiece that integrates the range of units covered, addressing all required questions.
What does it do?
MirrorAge captures synchronized digital biomarkers—camera frames processed with on-device FaceTTD models, VoiceAge microphone samples, grip strength torque, wearable accelerometry, and ReactionAge latency—to estimate intrinsic capacity and time-to-death acceleration.
A XIAO ESP32S3 Sense orchestrates sensing, performs Edge Impulse inference, and displays a live mortality-risk score on the OLED while logging packets to a Python analytics notebook.
Who's done what beforehand?
The concept builds on WHO intrinsic capacity framing and recent mortality-risk studies: Niccoli & Partridge (2012) establish age as the dominant chronic-disease predictor; Fuentealba et al. (Nature Aging 2025) show blood-based IC clocks outperform chronological models;
Zhavoronkov & Bhullar (2015) and Lancet Healthy Longevity editorials motivate treating functional decline as the actionable signal.
This project translates those findings into an accessible, multimodal measurement mirror that can operate outside hospital labs.
What sources did you use?
Primary references include Nature Aging 2025 intrinsic capacity papers, the PLOS ONE ReactionAge dataset (Blomkvist et al. 2017), Edge Impulse SenseCraft documentation, Smooth‑On Mold Star technical bulletins, RotoMetals alloy certificates, MIT HTMAA recitations, and the open-source GRPR grip-strength meter.
Design inspiration and safety notes were consolidated from Anthony Pennes' HTMA guides and Fab Academy molding tutorials.
What did you design?
• Laser-cut cardboard origami mirror frame and tensegrity-inspired floating mount (Weeks 1 & 6)
• ReactionAge firmware + enclosure with statistical post-processing dashboards (Week 2)
• 3D printed torsional spring grip module tuned for ±40 kg ranges (Week 3)
• KiCad/Fusion carrier PCB for the ESP32S3 Sense with OLED, force, and BLE breakouts (Week 5)
• Edge Impulse deployment pipeline with grayscale dithering overlay and live inference UX (Weeks 7–8)
• CAM toolpaths, silicone molds, and Drystone casts for structural packaging (Week 9)
What materials and components were used?
Seeed XIAO ESP32S3 Sense module with OV2640 camera and PDM mic, SparkFun Qwiic button and force sensors, SSD1306 OLED, wearable IMU node (Bosch BHI260), laser-cut cardboard/birch sheets, PLA+/Onyx filament, Mold Star 30 silicone, Drystone gypsum, Roto281 fusible alloy, and embedded fasteners/heat-set inserts.
Where did they come from?
Electronics from Seeed Studio, SparkFun, Digi-Key, and Adafruit; molding supplies and silicones from Reynolds Advanced Materials; Drystone and Hydro-Stone from USG via the MIT CBA stockroom; fusible alloys from RotoMetals; structural lumber and plywood from MIT's shop inventory; filaments from Prusa Research and Markforged.
How much did they cost?
Current spend: $96.34 for ReactionAge components (Week 2 BOM) + $78.42 for SenseCraft camera stack (XIAO ESP32S3 Sense, OLED, cabling) + $42.10 for molding media (Mold Star 30 quart, Drystone, release agents) = $216.86 to date.
Remaining allocation (~$130) is earmarked for BLE wearable hardware and final enclosure finishes; detailed line items tracked in the Airtable budget and mirrored in each weekly BOM CSV.
What parts and systems were made?
Custom origami mirror frame, 3D printed torsional grip shell, machined floating base, silicone molds and Drystone casts for arrow-inspired structural ribs, bespoke ESP32S3 breakout PCB, laser-cut ReactionAge control panel, and assembled sensor tower linking camera, OLED, and wearable gateway.
What tools and processes were used?
Parametric CAD in Fusion 360, laser cutting (Epilog) for origami tiles, Prusa MK4 FDM printing, Formlabs SLA for detail inserts, ShopBot CNC and Bantam PCB milling, silicone mixing/casting under vacuum, Edge Impulse model training, PlatformIO firmware, and Python/NumPy validation notebooks.
What questions were answered?
• Can consumer-grade sensors reproduce published reaction-time age curves? (Yes—ReactionAge matched Blomkvist et al. regression within 4.6 ms RMSE.)
• Will SenseCraft FaceTTD run locally on ESP32S3 with acceptable latency? (Yes—~310 ms/inference at 30% baseline accuracy, highlighting dataset needs.)
• Does molded packaging improve sensor placement repeatability? (Yes—silicone nests held camera ±0.5 mm, reducing alignment drift seen in cardboard prototypes.)
What worked? What didn't?
✅ Floyd–Steinberg dithering produced clear OLED previews; ✅ ReactionAge firmware maintained ±1 ms jitter; ✅ Molded Drystone ribs stiffened mirror shell without excess weight.
⚠️ FaceTTD accuracy plateaued at 30% due to limited training diversity; ⚠️ VoiceAge requires more MFCC samples to sustain 0.64-year MAE; ⚠️ Grip spring fatigue highlighted need for fiber-reinforced print or machined aluminum insert.
How was it evaluated?
Bench tests compare embedded predictions to published curves and desktop baselines: ReactionAge latency vs. Wii Balance Board golden data; FaceTTD inferencing cross-validated against Edge Impulse cloud classifier; VoiceAge MFCC regression verified through train/holdout splits; mechanical fixtures inspected with feeler gauges and dial indicators for tolerance drift.
What are the implications?
A portable intrinsic capacity mirror supports proactive geriatric screening, telehealth coaching, and longitudinal studies that correlate functional decline with interventions.
By grounding hardware in open-source parts and HTMAA fabrication methods, the system can be replicated across labs and community clinics to accelerate validation of digital aging biomarkers and personalize longevity therapies.
Design
Your project should incorporate 2D and 3D design, multiple additive and subtractive fabrication processes, electronics design and production, embedded microcontroller design, interfacing, and programming, system integration and packaging.
2D Design
2D design work for the multimodal intrinsic capacity assessment system:
Cardboard origami tiling for circular mirror frame, optimized for kerf learned during Week 1 laser characterization.
Vinyl-cut ReactionAge control labels and MirrorAge fascia decals for rapid UI readability.
KiCad/Fusion schematics + polygon pours for ESP32S3 carrier, force sensing front-end, and OLED interposer.
2D shop drawings for CNC floating base, including registration dowels and silicone mold parting lines.
Figma wireframes outlining the midterm web dashboard and on-device OLED states.
Subtractive: Laser cutting, milling for precision parts
Electronics: PCB design and production
Programming: Embedded microcontroller development
Bill of Materials
Where possible, I fabricated parts rather than buying them. This table summarizes all unique components in the final MirrorAge system, their approximate costs, and where they are used.
A mirrored copy of this bill of materials also appears on the Week 14 system-integration page for cross-linking directly from the integration steps
(Week 14 BOM).
Grip-strength molds, band molds, structural ribs
(Week 9,
Week 14)
Fasteners
M2/M3 hardware, heat-set inserts, misc. screws
Assorted
~$0.10–$0.30 ea.
$20.00 (bundle)
All mechanical assemblies (watch, grip rig, camera mount, demo table)
Estimated Total Project Cost
Electronics ≈ $190 · Mechanical & materials ≈ $130 ·
Total ≈ $320 (excluding lab-provided consumables and reused stock).
Exact per-week line items remain in the weekly documentation tables (for example
ReactionAge BOM CSV in Week 2),
while this table captures the consolidated, unique parts that make up the final integrated MirrorAge system.
Fabrication Process
Week-by-week fabrication rolled forward subsystems toward the integrated mirror:
Week 1 laser-cut origami tiles for the circular bezel; Week 2 PCB milling + soldering for ReactionAge;
Week 3–4 torsional spring 3D prints and sanding jigs; Week 5 copper-clad milling and reflow of the ESP32S3 carrier;
Week 6 ShopBot machining of the floating base; Week 8 resin + FDM camera enclosure build; Week 9 wax machining, Mold Star casting, and Drystone ribs.
Each step captured feeds-and-speeds, toolpaths, and fixturing photos embedded in the weekly pages for replication.
Testing & Validation
Validation combined bench instrumentation and statistical analysis: oscilloscope timing to verify ReactionAge jitter, Edge Impulse confusion matrices for FaceTTD and VoiceAge,
Instron pull tests for the torsional grip cartridge, IR thermography while curing Mold Star molds, dial-indicator checks on CNC-machined bases, and adhesive shear testing on mirror mounts.
Data are logged to CSV via the ESP32S3 and compared against published baselines inside the midterm Jupyter notebook.
Individual Mastery and Independent Operation
Projects can be separate or joint, but need to show individual mastery of the skills, and be independently operable.
Individual Mastery
Demonstration of individual skills across all course units:
2D and 3D Design
Modeled the tensegrity floating mirror, torsional grip shells, and camera bezel in Fusion 360 and Onshape.
Drove design reviews with Anthony/Neil to lock tolerances, assembly order, and module interface specs.
Demonstrates mastery across cutting, 3D printing, machining, electronics, networking, and interface programming units.
Documentation cross-linked via weekly pages, GitHub repos, and BOM spreadsheets for traceability.
Group Assignments
Collaborative work and individual contributions:
Embedded programming group: authored workflow trade-off analysis and repo organization that seeded ReactionAge firmware patterns.
Molding & casting group: led SDS review, material trials, and mixing SOP that informed final mirror mold.
Shared camera dev sessions with peers to improve Edge Impulse dataset collection and SenseCraft deployment strategies.
Useful Documentation
Helpful resources, documentation, and design files for the multimodal intrinsic capacity assessment system.
Open Source Grip Strength Meter
A cost-effective $50 grip strength measurement system that can be further optimized for our multimodal assessment platform.
This open-source design provides an excellent foundation for integrating grip strength measurement into our intrinsic capacity assessment system,
with potential for cost reduction through signal multiplexing on a single processor.
Detailed technical pipeline for processing multiple digital biomarkers to generate intrinsic capacity scores.
Pipeline Architecture
Inputs
• Grip Strength
• Voice
• Face
• Video (motion/gait)
• Reaction Time
• Wearable Accelerometer
→
Feature Extraction
Strength metrics
Prosody features
Facial landmarks
Gait parameters
Response latency
Activity patterns
Embeddings
Features converted to vector representations for multimodal fusion
→
Fusion Layer
Combines multimodal features using attention mechanisms
Output
• Overall IC Score
• Domain sub-scores
→
Domain Scores
Locomotor
Cognition
Vitality
Sensory
Psychological
Weekly System Development Breakdown
How each week of HTMAA 2025 builds toward the complete multimodal intrinsic capacity assessment system.
Week 0: Project Ideation
Initial concept development and planning
Project planning and documentation structure
Research direction and concept sketches
Week 1: Precision Cutting
Laser and vinyl cutting techniques
Device housing components via laser cutting
Sensor mounting brackets and enclosures
Vinyl cutting for device labeling and UI elements
Week 2: Embedded Programming
Electronics basics and microcontroller programming
Microcontroller programming for data collection
Basic sensor interface circuits
Week 3: 3D Scanning & Printing
3D technologies for device components
3D scanning for custom component design
3D printing for device housings
Week 4: Electronics Design
EDA and schematic design
PCB design for grip strength measurement
Sensor interface circuits and signal conditioning
Power management and data storage systems
Week 5: Electronics Production
PCB fabrication and assembly
PCB fabrication and debugging
Component assembly and testing
Week 6: Computer-controlled Machining
CAM and precision milling
Precision components via milling
Custom mechanical parts
Week 7: Input Devices
Sensor integration for data collection
Force sensors for grip strength measurement
Microphones for voice analysis
Camera systems for facial expression analysis
Reaction time measurement circuits
Week 8: Output Devices
Actuators and system integration
Display systems for real-time feedback
Haptic feedback for user interaction
Week 9: Molding & Casting
Forming and resin techniques
3D printing and molding for custom components
Silicone casting for device components
Week 10: Mechanical & Machine Design
System integration and mechanical design
Mechanical design for ergonomic device housing
System integration and calibration protocols
Week 11: Networking & Communications
Connectivity and communication protocols
Bluetooth/Wi-Fi connectivity for data transmission
Wearable accelerometer integration and data fusion
Week 12: Interface & Application Programming
UI development and application programming
Mobile app development for user interface
Cloud integration for data storage and analysis
Machine learning pipeline for IC score calculation
Week 13: Wildcard & Final Integration
Final orders and complete system deployment
Final testing, validation, and documentation
System integration and deployment
Camera Subsystem
Advanced camera system implementation using XIAO ESP32S3 Sense with real-time image processing, EdgeAI integration, and interactive selfie capture functionality.
System Overview
The camera system successfully captures images, processes them into bitmaps, and displays them on an OLED screen using advanced Floyd-Steinberg dithering algorithms.
Video Demonstrations
Camera Bot Selfie
Demonstration of the interactive selfie capture system with touch controls
Picture of Picture
Meta demonstration showing the camera system capturing its own display
Code Implementation
60-Second Auto Capture System
Automated camera system that captures and displays images every 60 seconds using advanced image processing techniques.
1. Initialize camera with PSRAM frame buffers
2. Configure OLED display (128x64 pixels)
3. Set up 60-second capture interval timer
4. In main loop:
a. Check if 60 seconds have elapsed
b. Capture image from camera
c. Process image:
- Downsample to 128x64 via box averaging
- Apply contrast stretch (linear scaling)
- Perform Floyd-Steinberg dithering
d. Display processed bitmap on OLED
e. Release frame buffer
5. Repeat process
Touch-Controlled Capture System
Interactive camera system with touch controls allowing manual capture triggers in addition to automatic timing.
1. Initialize camera and OLED display
2. Set up touch pins (GPIO1 & GPIO2) with threshold detection
3. Configure 60-second auto-capture timer
4. In main loop:
a. Update touch sensor readings
b. Detect touch press events (justPressed)
c. Check for capture trigger:
- Touch press OR 60-second timer elapsed
d. If triggered:
- Capture image from camera
- Process image (same as auto version)
- Display on OLED
- Reset timer
5. Continue monitoring for next trigger
The system captures photos, converts them to bitmaps using advanced image processing algorithms, and displays them on the OLED screen.
I'm also exploring integration with ML models, either through online API calls or by embedding TinyML model parameters from Python to C++.
Future development includes live streaming real-time video with ML prediction updates based on variable observation times,
and exploring Edge Impulse models as an alternative to manual Python-to-C++ conversion for faster deployment.
EdgeAI/TinyML Integration
Edge AI can also be implemented using Edge Impulse models, which may be faster than manually converting Python models to C++.
The SenseCraft AI platform provides a streamlined approach to training and deploying ML models directly on the XIAO ESP32S3.
Deploy inference bundle to the SenseCraft board alongside the camera stack.
Benchmark latency and accuracy against baseline VoiceAge models and document calibration protocol.
Week 0 - Introduction & Design
Project ideation and initial concept development for bioprinting rejuvenated tissue and aging biomarker devices.
Project planningConcept sketchesResearch direction
System Integration Plans: Establish the foundational architecture for multimodal data collection by designing the overall system framework that will integrate all six digital biomarkers (grip strength, voice, face, video, reaction time, wearable accelerometer) into a cohesive intrinsic capacity assessment platform.
Mapped the MirrorAge subsystem architecture, assembled the intrinsic capacity literature stack, and kicked off BRR/IRB coordination so fabrication sprints stay aligned with clinical requirements.
Week 1 - Principles & Cutting
Version control, laser cutting, and vinyl cutting techniques applied to final project components.
Laser cuttingVinyl cuttingVersion control
System Integration Plans: Fabricate precision-cut housing components and mounting brackets for all sensor modules (force sensors, microphones, cameras, reaction time circuits) using laser cutting, while creating vinyl-cut labels and UI elements for device identification and user guidance.
Characterized laser kerf, produced the origami mirror frame tiles, and generated vinyl interface labels—locking in enclosure dimensions and user UI cues for the mirror shell.
Week 2 - Embedded Programming
Electronics basics and embedded programming for the aging biomarker device components.
MicrocontrollersProgrammingElectronics
System Integration Plans: Develop embedded programming protocols for real-time data collection from all six biomarker sensors, implementing initial signal processing algorithms and establishing the communication framework for multimodal data fusion.
Built the ReactionAge firmware + enclosure, published the first BOM, and validated timing pipelines that will feed the MirrorAge IC fusion engine.
Week 3 - 3D Scanning & Printing
3D scanning and printing techniques for bioprinting components and device housings.
3D scanning3D printingAI tools
System Integration Plans: Create custom 3D-printed components for camera mounting systems and facial recognition hardware, while developing 3D scanning protocols for ergonomic device design that accommodates all sensor modalities in a user-friendly form factor.
Modeled and printed the torsional grip spring, performed 3D scans for ergonomic fixtures, and captured training assets for face/gait datasets.
Week 4 - Electronics Design
EDA and schematic design for the aging biomarker device electronics.
EDA toolsSchematic designCircuit design
System Integration Plans: Design comprehensive PCB schematics that integrate force sensor circuits for grip strength measurement, microphone preamplifiers for voice analysis, camera interfaces for facial recognition, and timing circuits for reaction time assessment into a unified electronics platform.
Completed the Fusion 360/KiCad schematic/PCB layout for the ESP32S3 carrier tying together force, audio, camera, reaction, and wearable interfaces.
Week 5 - Electronics Production
PCB fabrication, debugging, and assembly for the biomarker device.
PCB fabricationDebuggingAssembly
System Integration Plans: Fabricate and assemble the integrated PCB containing all sensor interfaces, implementing power management systems for continuous operation and establishing data storage protocols for the multimodal biomarker data collection system.
Fabricated and assembled the carrier PCB, brought up power domains, and verified sensor buses—establishing the electronics backbone for integration.
Week 6 - Computer-controlled Machining
CAM and milling for precision components and device housings.
CAMMillingPrecision machining
System Integration Plans: Machine precision mechanical components for the integrated device housing using computer-controlled milling, ensuring proper alignment and mounting for all sensor modules while maintaining ergonomic design for user comfort during multimodal data collection.
Machined the floating mirror base and tensegrity nodes, refining fixturing that ensures repeatable camera and grip alignment in the final assembly.
Week 7 - Input Devices
Sensors and embedded architectures for data collection in the biomarker device.
SensorsInput devicesData collection
System Integration Plans: Integrate all six input sensor systems (force sensors for grip strength, microphones for voice analysis, cameras for facial recognition and gait analysis, reaction time circuits, and wearable accelerometer) into the unified data collection platform with real-time processing capabilities.
Integrated the force sensor, microphone, and ReactionAge modules on the carrier, logging synchronized packets that exercise the multimodal intake stack.
Week 8 - Output Devices
Actuators and system integration for the biomarker device outputs.
ActuatorsOutput devicesSystem integration
System Integration Plans: Implement output devices including display systems for real-time intrinsic capacity feedback and haptic feedback mechanisms for user interaction, creating an intuitive interface for the multimodal biomarker assessment system.
Deployed the SenseCraft FaceTTD pipeline on the XIAO ESP32S3, implemented OLED dithering previews, and confirmed end-to-end edge inference latency.
Week 9 - Molding & Casting
Forming and resin techniques for bioprinting molds and device components.
MoldingCastingResins
System Integration Plans: Create custom molded components for the bioprinting aspects of the project and develop specialized casings for sensor protection, ensuring the device can withstand continuous use during multimodal data collection sessions.
Machined wax molds, cast Mold Star silicone and Drystone ribs, and prototyped arrow-inspired shells that stabilize the mirror and protect embedded sensors.
Week 10 - Mechanical & Machine Design
Kits and mechanical design for the bioprinting and biomarker device systems.
Mechanical designMachine designSystem integration
System Integration Plans: Complete the mechanical design integration of all system components, implementing calibration protocols for sensor alignment and developing the complete mechanical framework that houses all six digital biomarker measurement systems.
Developed mechanical actuation systems including tapping and swiping mechanisms for phone interaction, integrated camera with Edge AI face detection and Wi-Fi livestreaming, designed and 3D-printed phone holder with amplifier, and prepared comprehensive midterm review documentation with system diagrams and timeline.
Week 11 - Networking & Communications
BLE, Wi-Fi, and communication protocols for the biomarker device connectivity.
BLEWi-FiCommunications
System Integration Plans: Implement wireless communication protocols (Bluetooth/Wi-Fi) for seamless data transmission from all six sensor modalities, enabling real-time data fusion and establishing connectivity for the wearable accelerometer integration into the multimodal assessment system.
Implemented Wi-Fi camera livestreaming for real-time video transmission, developed ESP-NOW networking protocols for device communication, designed and milled PCBs for networking components, and explored Meshtastic for long-range communication capabilities.
Week 12 - Interface & Application Programming
UI and application development for the biomarker device interface.
UI designApplicationsUser interface
System Integration Plans: Develop the complete user interface and application programming for the multimodal system, implementing the machine learning pipeline for intrinsic capacity score calculation and creating cloud integration for comprehensive data storage and analysis of all biomarker measurements.
Created Wi-Fi web interface for real-time pulse oximeter readings with live plotting, developed grip strength measurement device with load cell and integrated GUI, implemented OLED button user interface for device control, and established video streaming capabilities for sensor data visualization.
Week 13 - Wildcard & Final Orders
Final orders and wildcard week activities for project completion.
Final ordersWildcard activitiesProject completion
System Integration Plans: Complete final system integration, testing, and validation of the complete multimodal intrinsic capacity assessment platform, ensuring all six digital biomarkers work cohesively to provide accurate WHO-defined intrinsic capacity scores across all five domains (locomotor, cognition, vitality, sensory, psychological).
Designed and fabricated ATtiny1626 tiny development board with fiber laser PCB engraving, created glass engraving system with UV laser including blinking heart integration for visual feedback, milled mounting holes and completed board assembly, and prepared final board designs for system integration.
System Integration
Final integration week focused on bringing all subsystems together, completing hardware fabrication, firmware integration, and documentation for the MirrorAge system presentation. View full details →
Initial system integration work focused on subsystem validation, CAD model consolidation, and design backbone acquisition for band integration. Conducted comprehensive testing of all subsystems to ensure proper functionality, identified and resoldered defective joints, and exported CAD models of all PCBs into a unified assembly model.
Physical integration of subsystems into the complete demo table assembly, including mechanical component fabrication and electrical board consolidation. Integrated the complete demo table with precise placement of the MirrorAge handgrip subsystem and aging clock subsystem, providing a unified platform for system demonstration.
Continued fabrication work integrating all manufacturing processes. Focused on completing physical components and preparing subsystems for final assembly and testing.
Comprehensive subsystem integration combining 2D fabrication (laser cutting and vinyl cutting), 3D printing (rigid and flexible components), PCB milling (single and double-sided boards), and molding/casting to complete all physical components. Upgraded MirrorAge TFT board to v13 and aging clock TFT board to v16 with optimized component placement and routing. Established reliable I²C bus communication and validated all sensor addresses.
Final integration day focused on closing the watch subsystem, soldering and verifying all double-sided boards, refining molded bands, and assembling the complete MirrorAge demo with both the aging clock and grip-strength subsystems fully wired and tested. Completed rivet installation for plated through-holes, sensor bring-up (accelerometer, pulse oximeter, OLED/TFT displays), and full system integration on the tensegrity demo table. The integrated system successfully demonstrated synchronized sensor readouts and display behavior across all boards.
Final project presentation and demonstration of the complete MirrorAge system. Showcased the integrated aging clock and grip-strength subsystems working together on the demo table, demonstrating real-time sensor data collection and display synchronization. View final presentation demo →
Full Documentation: For complete details, design files, code, and comprehensive documentation of the system integration process, see Week 14: System Integration.
Design Files
Complete repository of all design files, CAD models, schematics, PCB layouts, firmware, and fabrication files from Week 0 through Week 14, organized by week and component type.
Note: Additional design files, firmware, and documentation can be found in the respective week pages. Some files are part of larger archives (ZIP files) that contain multiple related design files.
Reflections & Learnings
Comprehensive reflections on the MirrorAge Intrinsic Capacity Mirror project development journey.
Modular system design allows for incremental development and component-level testing throughout the semester
Integration of mechanical, electrical, and software subsystems requires careful planning and coordination
Iterative design and prototyping revealed the importance of early testing and validation
Documentation and knowledge transfer are critical for project continuity and future improvements
The project successfully demonstrates how digital fabrication and embedded systems can create meaningful health assessment tools
Contributions
Acknowledgements and contributions that made this project possible.
Gladyshev Lab and Collaborators
Special thanks to the Gladyshev Lab and collaborators for the fruitful discussions that led to this multimodal intrinsic capacity assessment idea,
which supplements my PhD research goals in aging and longevity. The conceptual framework for integrating multiple digital biomarkers
to assess intrinsic capacity domains emerged from collaborative research discussions on aging biomarkers and healthspan assessment.
Transparent documentation of AI assistance used in this final project work, following course guidelines for ethical AI usage.
📋 General Guidelines: See General Commands for Cursor on the homepage for standard guidelines and commands used consistently throughout documentation development.
Cursor · Project Plan & Weekly Schedule
Comprehensive Cursor AI assistance for outlining the project plan and weekly schedule, including documentation structure, content organization, systematic updates across all week pages and the final project page, media integration, and summary generation workflows.
Cursor AI aligned the midterm review plan with updated system diagram, timeline, and remaining-task summaries, then refreshed finalproject.html to remove legacy bioprinting language and re-point internal links. The full transcript and generated HTML are available for review.
Cursor AI assistance for adding a white background behind the photo in the Final Project Spiral Development Model section on finalproject.html. The image container was updated with white background, padding, and rounded corners for improved visual presentation.
Cursor AI distilled Week 0–9 documentation and the Oct 31 lab meeting deck into midterm-ready narrative, cost, and validation content, replacing every placeholder in finalproject.html.
Transcript archived in markdown and HTML (generated via scripts/md_to_html_converter.py) for transparency.
ChatGPT was used to research and develop the multimodal intrinsic capacity assessment framework, including the comprehensive coverage analysis table and technical pipeline design.
The AI assisted with structuring the WHO-defined intrinsic capacity domains, identifying appropriate digital biomarkers, and designing the fusion architecture for multimodal data processing.
Cursor AI assisted with developing the complete final project page structure, implementing the multimodal intrinsic capacity assessment framework, and creating comprehensive documentation.
The AI helped with HTML structure, responsive design, weekly system integration plans, and organizing the technical documentation for the complete biomarker assessment system.
Cursor AI assisted with finalizing the project presentation structure to ensure full compliance with MIT Academy project presentation requirements.
The AI helped implement all required sections including answering questions, design documentation, bill of materials, individual mastery requirements,
course presentation structure, and spiral model development approach visualization.
ChatGPT was used to discuss camera system implementation strategies, image processing algorithms, and EdgeAI integration approaches.
The AI assisted with understanding Floyd-Steinberg dithering implementation, touch sensor integration, and exploring TinyML deployment options for the XIAO ESP32S3 platform.
AI-Assisted Project Highlights and Camera Subsystem Development
Cursor AI assisted with adding the project highlights section featuring camera system achievements and creating a comprehensive camera subsystem section with detailed code implementations, video demonstrations, and EdgeAI integration documentation.
The AI helped with HTML structure, responsive design, image processing explanations, and organizing the technical documentation for the complete camera system showcase.
Interactive selfie capture system with touch controls and real-time display
Vision Board
Conceptual visualization of the multimodal intrinsic capacity assessment system integrating grip strength, voice analysis, facial recognition, video motion capture, reaction time measurement, and wearable accelerometer data.
Intrinsic Capacity (IC) Coverage by Digital Biomarkers
Domain
Grip
Voice
Face
Video
Reaction Time
Wearable
Locomotor
✅
🔸
🔸
✅
🔸
✅
Cognition
❌
✅
🔸
🔸
✅
🔸
Vitality
✅
✅
✅
✅
🔸
✅
Sensory
❌
✅
✅
✅
✅
🔸
Psychological
❌
✅
✅
✅
🔸
✅
✅ Strong coverage |
🔸 Partial/indirect |
❌ Not covered |
View full table →
Multimodal IC Pipeline
Inputs: Grip Strength, Voice, Face, Video, Reaction Time, Wearable Accelerometer
Development Approach: Following the spiral model methodology, this final project will iterate through multiple development cycles, each building upon previous work while addressing new requirements and risks.
This snapshot covers the subsystems and documentation that will be shown during the midterm review. Links jump directly to the supporting sections with detailed evidence.
Featured Subsystems
Camera subsystem — Edge inference demos and selfie capture loop.
Instructor meeting hold — Thursday, Nov 12 at 10:00 AM ET reserved via the shared HTMAA midterm review sheet.
Execution Schedule (Timeline Snapshot)
Condensed from the Week 8–13 development timeline: each sprint builds toward final integration, mirroring the gantt chart below.
Week 8 · Output Devices: figuring out wiring for real-time display states.
Week 9 · Molding & Casting: learn how to cast custom housings and refine structural components.
Week 10 · Mechanical Design: figure out ergonomic enclosure and calibration fixtures.
Week 11 · Networking: program BLE/Wi-Fi telemetry and wearable data fusion.
Week 12 · Interface/App: create mobile UI, cloud bridge, and IC scoring pipeline.
Week 13 · Final Integration: run validation passes, document results, and prep deployment.
Instructor Review Logistics
Calendar hold sent for Thursday, Nov 12 at 10:00 AM ET (38-501 conference room) per the shared HTMAA scheduling sheet. Agenda covers subsystem demos, weekly documentation spot checks (Weeks 0–9), and next-sprint alignment. Meeting slot referenced in the midterm review schedule; awaiting final confirmation via class Slack.
System Architecture
Updated block diagram highlighting the multimodal sensing stack (grip, voice, face, motion, wearables), on-device inference layers, and real-time feedback channels that feed the intrinsic capacity score.
Development Timeline
Timeline aligns subsystem sprints with HTMAA milestones: output devices (Week 8), molding and casting (Week 9), mechanical design (Week 10), networking and communications (Week 11), app programming (Week 12), and final integration (Week 13).
Remaining Tasks (Snapshot)
Weeks 0–9 locked in the core subsystems—documentation workflow, cutting and molding for the housing, embedded prototypes for reaction timing, SenseCraft camera inference, and early grip/voice rigs. The checklist below captures what still needs to happen to converge on the integrated MirrorAge system.
Hardware Integration
Consolidate grip, voice, camera, reaction-time, and wearable sensor harnesses into the MirrorAge enclosure.
Finish molding/casting iterations for the ergonomic housing and align mounting features for PCBs and haptics.
Firmware & Edge AI
Stabilize onboard inference for SenseCraft vision models and voice-age pipelines on the XIAO ESP32S3.
Calibrate grip-force and reaction-time firmware for repeatable sampling; close the loop to haptic/display feedback.
Networking & Data Fusion
Bring up BLE/Wi-Fi data paths for wearable accelerometer streaming and cloud logging of intrinsic capacity scores.
Implement the fusion layer that combines per-domain scores into an overall IC metric with on-device storage.
Interface & UX
Finish mobile/web dashboard mockups for user onboarding, data review, and device calibration workflows.
Finalize real-time mirror feedback cues (display states, haptics, lighting) tied to sensor status and IC outcomes.
Validation & Documentation
Run end-to-end system tests (sensor capture → fusion → feedback) and document calibration procedures.
Record the one-minute video, finalize final presentation assets, and polish the bill of materials for review.
Week 14 System Integration Plan
Detailed day-by-day schedule for final system integration, covering design, fabrication, programming, testing, and documentation. This plan outlines the path to completing the MirrorAge system integration and preparing for final presentation. View on Week 14 page →
The act of bringing something to a conclusion or ending in a decisive manner. The ability to efficiently finish tasks and projects with a goal-oriented mindset.
Wednesday
Morning
Publish system integration plan on website
Update weekly assignment sections on final project page (weeks 10-13)
Link final project design files
Update reflections and learnings
Update picture of prism holder
Add final pictures to Slack canvases
Create schematic between boards (wired and wireless) — updated system diagram on PPT-like page
Start CAD model of system
Place final order
Afternoon & Evening
Design:
Boards: Combine OLED screen/accelerometer with pulse oximeter board in a new board (maybe upgrade to small TFT as minor)
Boards: Speaker board with realtime amplifier and TFT (on the load cell fixed board)
Band: Mold design
Cases: 3D print mountable cases for the boards
Integrate designs into final CAD
Document design
Finish CAD model of system
Thursday
Fabricate
Milling boards
Print mold and cast band
Print cases
Solder
Solder components on milled boards
Connect boards with wired (and wireless connection codes)
Finishing
Mirror on screen (easy way with the film)
Documentation
Document fabrication
Friday
Programming
Board level codes
Server level codes
Documentation
Document codes
Completion
Finish anything else
Saturday
Programming & Testing
Demo integrated system
Test integrated system
Documentation
Document testing and evaluation
Review and complete documentation (list of questions)
Make the video by collaging documentation
Sunday
Fill up any gaps
Prepare demo on tensegrity table
Finalize 1-slide
Work on minors
If done, work on if there's time
Monday Morning
Transport demo on tensegrity table
Fill up any gaps
Work on minors
Specific Tasks to Complete This Week
Major Tasks
CAD model of system
Speaker board with realtime amplifier
Combine screen/accelerometer with pulse oximeter board in a new board
Mold and cast band
Design and fabricate casing (print)
Schematic between boards (wired and wireless) — updated system diagram on PPT-like page
Serial connection between pulse oximeter and tiny blinking heart for BPM (BPM from IR, SpO2 from delta)
Combine multiple boards on the same WiFi (switching tabs is easy way, board hosting the webpage querying and update or Python-based server somewhere where everything posting data, Raspberry Pi)
Put+program everything together according to the above (with WiFi for now)
MirrorAge is a self-contained edge-AI mirror that captures grip strength, facial imagery, voice, motion, and reaction time to estimate intrinsic capacity in real time.
The platform fuses weekly prototypes—ReactionAge latency tests, 3D printed grip mechanics, SenseCraft camera inference, and molded structural elements—into a multimodal mortality risk profiler.
Subsystems in progress: reaction-time module, SenseCraft FaceTTD inference stack, VoiceAge microphone pipeline, wearable streaming via BLE, and molded structural packaging.
Clinical motivation: translate WHO intrinsic capacity domains into measurable digital biomarkers that flag functional decline earlier than chronological age alone.
Project Goals
Deliver multimodal IC scoring Fuse grip, face, voice, reaction-time, and wearable streams on-device to output an intrinsic capacity score plus domain deltas.
Fabricate modular, serviceable hardware Iterate laser-cut tensegrity mirror shells, 3D printed torsional grips, custom PCBs, and silicone cast fixtures that assemble without bespoke tooling.
Validate against ground truth Benchmark embedded inferences against published datasets (Blomkvist et al. 2017, Fuentealba et al. 2025) and lab-collected pilots to quantify accuracy, latency, and reliability.
Timeline & Milestones
Week 10 · Hardware convergence Integrate SenseCraft FaceTTD camera, ReactionAge latency module, and newly milled PCB into a single ESP32S3 backplane.
Week 12 · Midterm review build Finish molded mirror enclosure, bring up BLE wearable link, and demo live IC score during midterm critique.
Final week · Validation & documentation Execute pilot data collection, refine model weights, and release reproducible fabrication + firmware packages.
Documenting the final project masterpiece that integrates the range of units covered, addressing all required questions.
What does it do?
MirrorAge captures synchronized digital biomarkers—camera frames processed with on-device FaceTTD models, VoiceAge microphone samples, grip strength torque, wearable accelerometry, and ReactionAge latency—to estimate intrinsic capacity and time-to-death acceleration.
A XIAO ESP32S3 Sense orchestrates sensing, performs Edge Impulse inference, and displays a live mortality-risk score on the OLED while logging packets to a Python analytics notebook.
Who's done what beforehand?
The concept builds on WHO intrinsic capacity framing and recent mortality-risk studies: Niccoli & Partridge (2012) establish age as the dominant chronic-disease predictor; Fuentealba et al. (Nature Aging 2025) show blood-based IC clocks outperform chronological models;
Zhavoronkov & Bhullar (2015) and Lancet Healthy Longevity editorials motivate treating functional decline as the actionable signal.
This project translates those findings into an accessible, multimodal measurement mirror that can operate outside hospital labs.
What sources did you use?
Primary references include Nature Aging 2025 intrinsic capacity papers, the PLOS ONE ReactionAge dataset (Blomkvist et al. 2017), Edge Impulse SenseCraft documentation, Smooth‑On Mold Star technical bulletins, RotoMetals alloy certificates, MIT HTMAA recitations, and the open-source GRPR grip-strength meter.
Design inspiration and safety notes were consolidated from Anthony Pennes' HTMA guides and Fab Academy molding tutorials.
What did you design?
• Laser-cut cardboard origami mirror frame and tensegrity-inspired floating mount (Weeks 1 & 6)
• ReactionAge firmware + enclosure with statistical post-processing dashboards (Week 2)
• 3D printed torsional spring grip module tuned for ±40 kg ranges (Week 3)
• KiCad/Fusion carrier PCB for the ESP32S3 Sense with OLED, force, and BLE breakouts (Week 5)
• Edge Impulse deployment pipeline with grayscale dithering overlay and live inference UX (Weeks 7–8)
• CAM toolpaths, silicone molds, and Drystone casts for structural packaging (Week 9)
What materials and components were used?
Seeed XIAO ESP32S3 Sense module with OV2640 camera and PDM mic, SparkFun Qwiic button and force sensors, SSD1306 OLED, wearable IMU node (Bosch BHI260), laser-cut cardboard/birch sheets, PLA+/Onyx filament, Mold Star 30 silicone, Drystone gypsum, Roto281 fusible alloy, and embedded fasteners/heat-set inserts.
Where did they come from?
Electronics from Seeed Studio, SparkFun, Digi-Key, and Adafruit; molding supplies and silicones from Reynolds Advanced Materials; Drystone and Hydro-Stone from USG via the MIT CBA stockroom; fusible alloys from RotoMetals; structural lumber and plywood from MIT's shop inventory; filaments from Prusa Research and Markforged.
How much did they cost?
Current spend: $96.34 for ReactionAge components (Week 2 BOM) + $78.42 for SenseCraft camera stack (XIAO ESP32S3 Sense, OLED, cabling) + $42.10 for molding media (Mold Star 30 quart, Drystone, release agents) = $216.86 to date.
Remaining allocation (~$130) is earmarked for BLE wearable hardware and final enclosure finishes; detailed line items tracked in the Airtable budget and mirrored in each weekly BOM CSV.
What parts and systems were made?
Custom origami mirror frame, 3D printed torsional grip shell, machined floating base, silicone molds and Drystone casts for arrow-inspired structural ribs, bespoke ESP32S3 breakout PCB, laser-cut ReactionAge control panel, and assembled sensor tower linking camera, OLED, and wearable gateway.
What tools and processes were used?
Parametric CAD in Fusion 360, laser cutting (Epilog) for origami tiles, Prusa MK4 FDM printing, Formlabs SLA for detail inserts, ShopBot CNC and Bantam PCB milling, silicone mixing/casting under vacuum, Edge Impulse model training, PlatformIO firmware, and Python/NumPy validation notebooks.
What questions were answered?
• Can consumer-grade sensors reproduce published reaction-time age curves? (Yes—ReactionAge matched Blomkvist et al. regression within 4.6 ms RMSE.)
• Will SenseCraft FaceTTD run locally on ESP32S3 with acceptable latency? (Yes—~310 ms/inference at 30% baseline accuracy, highlighting dataset needs.)
• Does molded packaging improve sensor placement repeatability? (Yes—silicone nests held camera ±0.5 mm, reducing alignment drift seen in cardboard prototypes.)
What worked? What didn't?
✅ Floyd–Steinberg dithering produced clear OLED previews; ✅ ReactionAge firmware maintained ±1 ms jitter; ✅ Molded Drystone ribs stiffened mirror shell without excess weight.
⚠️ FaceTTD accuracy plateaued at 30% due to limited training diversity; ⚠️ VoiceAge requires more MFCC samples to sustain 0.64-year MAE; ⚠️ Grip spring fatigue highlighted need for fiber-reinforced print or machined aluminum insert.
How was it evaluated?
Bench tests compare embedded predictions to published curves and desktop baselines: ReactionAge latency vs. Wii Balance Board golden data; FaceTTD inferencing cross-validated against Edge Impulse cloud classifier; VoiceAge MFCC regression verified through train/holdout splits; mechanical fixtures inspected with feeler gauges and dial indicators for tolerance drift.
What are the implications?
A portable intrinsic capacity mirror supports proactive geriatric screening, telehealth coaching, and longitudinal studies that correlate functional decline with interventions.
By grounding hardware in open-source parts and HTMAA fabrication methods, the system can be replicated across labs and community clinics to accelerate validation of digital aging biomarkers and personalize longevity therapies.
Design
Your project should incorporate 2D and 3D design, multiple additive and subtractive fabrication processes, electronics design and production, embedded microcontroller design, interfacing, and programming, system integration and packaging.
2D Design
2D design work for the multimodal intrinsic capacity assessment system:
Cardboard origami tiling for circular mirror frame, optimized for kerf learned during Week 1 laser characterization.
Vinyl-cut ReactionAge control labels and MirrorAge fascia decals for rapid UI readability.
KiCad/Fusion schematics + polygon pours for ESP32S3 carrier, force sensing front-end, and OLED interposer.
2D shop drawings for CNC floating base, including registration dowels and silicone mold parting lines.
Figma wireframes outlining the midterm web dashboard and on-device OLED states.
Subtractive: Laser cutting, milling for precision parts
Electronics: PCB design and production
Programming: Embedded microcontroller development
Bill of Materials
Where possible, I fabricated parts rather than buying them. This table summarizes all unique components in the final MirrorAge system, their approximate costs, and where they are used.
A mirrored copy of this bill of materials also appears on the Week 14 system-integration page for cross-linking directly from the integration steps
(Week 14 BOM).
Grip-strength molds, band molds, structural ribs
(Week 9,
Week 14)
Fasteners
M2/M3 hardware, heat-set inserts, misc. screws
Assorted
~$0.10–$0.30 ea.
$20.00 (bundle)
All mechanical assemblies (watch, grip rig, camera mount, demo table)
Estimated Total Project Cost
Electronics ≈ $190 · Mechanical & materials ≈ $130 ·
Total ≈ $320 (excluding lab-provided consumables and reused stock).
Exact per-week line items remain in the weekly documentation tables (for example
ReactionAge BOM CSV in Week 2),
while this table captures the consolidated, unique parts that make up the final integrated MirrorAge system.
Fabrication Process
Week-by-week fabrication rolled forward subsystems toward the integrated mirror:
Week 1 laser-cut origami tiles for the circular bezel; Week 2 PCB milling + soldering for ReactionAge;
Week 3–4 torsional spring 3D prints and sanding jigs; Week 5 copper-clad milling and reflow of the ESP32S3 carrier;
Week 6 ShopBot machining of the floating base; Week 8 resin + FDM camera enclosure build; Week 9 wax machining, Mold Star casting, and Drystone ribs.
Each step captured feeds-and-speeds, toolpaths, and fixturing photos embedded in the weekly pages for replication.
Testing & Validation
Validation combined bench instrumentation and statistical analysis: oscilloscope timing to verify ReactionAge jitter, Edge Impulse confusion matrices for FaceTTD and VoiceAge,
Instron pull tests for the torsional grip cartridge, IR thermography while curing Mold Star molds, dial-indicator checks on CNC-machined bases, and adhesive shear testing on mirror mounts.
Data are logged to CSV via the ESP32S3 and compared against published baselines inside the midterm Jupyter notebook.
Individual Mastery and Independent Operation
Projects can be separate or joint, but need to show individual mastery of the skills, and be independently operable.
Individual Mastery
Demonstration of individual skills across all course units:
2D and 3D Design
Modeled the tensegrity floating mirror, torsional grip shells, and camera bezel in Fusion 360 and Onshape.
Drove design reviews with Anthony/Neil to lock tolerances, assembly order, and module interface specs.
Demonstrates mastery across cutting, 3D printing, machining, electronics, networking, and interface programming units.
Documentation cross-linked via weekly pages, GitHub repos, and BOM spreadsheets for traceability.
Group Assignments
Collaborative work and individual contributions:
Embedded programming group: authored workflow trade-off analysis and repo organization that seeded ReactionAge firmware patterns.
Molding & casting group: led SDS review, material trials, and mixing SOP that informed final mirror mold.
Shared camera dev sessions with peers to improve Edge Impulse dataset collection and SenseCraft deployment strategies.
Useful Documentation
Helpful resources, documentation, and design files for the multimodal intrinsic capacity assessment system.
Open Source Grip Strength Meter
A cost-effective $50 grip strength measurement system that can be further optimized for our multimodal assessment platform.
This open-source design provides an excellent foundation for integrating grip strength measurement into our intrinsic capacity assessment system,
with potential for cost reduction through signal multiplexing on a single processor.
Detailed technical pipeline for processing multiple digital biomarkers to generate intrinsic capacity scores.
Pipeline Architecture
Inputs
• Grip Strength
• Voice
• Face
• Video (motion/gait)
• Reaction Time
• Wearable Accelerometer
→
Feature Extraction
Strength metrics
Prosody features
Facial landmarks
Gait parameters
Response latency
Activity patterns
Embeddings
Features converted to vector representations for multimodal fusion
→
Fusion Layer
Combines multimodal features using attention mechanisms
Output
• Overall IC Score
• Domain sub-scores
→
Domain Scores
Locomotor
Cognition
Vitality
Sensory
Psychological
Weekly System Development Breakdown
How each week of HTMAA 2025 builds toward the complete multimodal intrinsic capacity assessment system.
Week 0: Project Ideation
Initial concept development and planning
Project planning and documentation structure
Research direction and concept sketches
Week 1: Precision Cutting
Laser and vinyl cutting techniques
Device housing components via laser cutting
Sensor mounting brackets and enclosures
Vinyl cutting for device labeling and UI elements
Week 2: Embedded Programming
Electronics basics and microcontroller programming
Microcontroller programming for data collection
Basic sensor interface circuits
Week 3: 3D Scanning & Printing
3D technologies for device components
3D scanning for custom component design
3D printing for device housings
Week 4: Electronics Design
EDA and schematic design
PCB design for grip strength measurement
Sensor interface circuits and signal conditioning
Power management and data storage systems
Week 5: Electronics Production
PCB fabrication and assembly
PCB fabrication and debugging
Component assembly and testing
Week 6: Computer-controlled Machining
CAM and precision milling
Precision components via milling
Custom mechanical parts
Week 7: Input Devices
Sensor integration for data collection
Force sensors for grip strength measurement
Microphones for voice analysis
Camera systems for facial expression analysis
Reaction time measurement circuits
Week 8: Output Devices
Actuators and system integration
Display systems for real-time feedback
Haptic feedback for user interaction
Week 9: Molding & Casting
Forming and resin techniques
3D printing and molding for custom components
Silicone casting for device components
Week 10: Mechanical & Machine Design
System integration and mechanical design
Mechanical design for ergonomic device housing
System integration and calibration protocols
Week 11: Networking & Communications
Connectivity and communication protocols
Bluetooth/Wi-Fi connectivity for data transmission
Wearable accelerometer integration and data fusion
Week 12: Interface & Application Programming
UI development and application programming
Mobile app development for user interface
Cloud integration for data storage and analysis
Machine learning pipeline for IC score calculation
Week 13: Wildcard & Final Integration
Final orders and complete system deployment
Final testing, validation, and documentation
System integration and deployment
Camera Subsystem
Advanced camera system implementation using XIAO ESP32S3 Sense with real-time image processing, EdgeAI integration, and interactive selfie capture functionality.
System Overview
The camera system successfully captures images, processes them into bitmaps, and displays them on an OLED screen using advanced Floyd-Steinberg dithering algorithms.
Video Demonstrations
Camera Bot Selfie
Demonstration of the interactive selfie capture system with touch controls
Picture of Picture
Meta demonstration showing the camera system capturing its own display
Code Implementation
60-Second Auto Capture System
Automated camera system that captures and displays images every 60 seconds using advanced image processing techniques.
1. Initialize camera with PSRAM frame buffers
2. Configure OLED display (128x64 pixels)
3. Set up 60-second capture interval timer
4. In main loop:
a. Check if 60 seconds have elapsed
b. Capture image from camera
c. Process image:
- Downsample to 128x64 via box averaging
- Apply contrast stretch (linear scaling)
- Perform Floyd-Steinberg dithering
d. Display processed bitmap on OLED
e. Release frame buffer
5. Repeat process
Touch-Controlled Capture System
Interactive camera system with touch controls allowing manual capture triggers in addition to automatic timing.
1. Initialize camera and OLED display
2. Set up touch pins (GPIO1 & GPIO2) with threshold detection
3. Configure 60-second auto-capture timer
4. In main loop:
a. Update touch sensor readings
b. Detect touch press events (justPressed)
c. Check for capture trigger:
- Touch press OR 60-second timer elapsed
d. If triggered:
- Capture image from camera
- Process image (same as auto version)
- Display on OLED
- Reset timer
5. Continue monitoring for next trigger
The system captures photos, converts them to bitmaps using advanced image processing algorithms, and displays them on the OLED screen.
I'm also exploring integration with ML models, either through online API calls or by embedding TinyML model parameters from Python to C++.
Future development includes live streaming real-time video with ML prediction updates based on variable observation times,
and exploring Edge Impulse models as an alternative to manual Python-to-C++ conversion for faster deployment.
EdgeAI/TinyML Integration
Edge AI can also be implemented using Edge Impulse models, which may be faster than manually converting Python models to C++.
The SenseCraft AI platform provides a streamlined approach to training and deploying ML models directly on the XIAO ESP32S3.
Deploy inference bundle to the SenseCraft board alongside the camera stack.
Benchmark latency and accuracy against baseline VoiceAge models and document calibration protocol.
Week 0 - Introduction & Design
Project ideation and initial concept development for bioprinting rejuvenated tissue and aging biomarker devices.
Project planningConcept sketchesResearch direction
System Integration Plans: Establish the foundational architecture for multimodal data collection by designing the overall system framework that will integrate all six digital biomarkers (grip strength, voice, face, video, reaction time, wearable accelerometer) into a cohesive intrinsic capacity assessment platform.
Mapped the MirrorAge subsystem architecture, assembled the intrinsic capacity literature stack, and kicked off BRR/IRB coordination so fabrication sprints stay aligned with clinical requirements.
Week 1 - Principles & Cutting
Version control, laser cutting, and vinyl cutting techniques applied to final project components.
Laser cuttingVinyl cuttingVersion control
System Integration Plans: Fabricate precision-cut housing components and mounting brackets for all sensor modules (force sensors, microphones, cameras, reaction time circuits) using laser cutting, while creating vinyl-cut labels and UI elements for device identification and user guidance.
Characterized laser kerf, produced the origami mirror frame tiles, and generated vinyl interface labels—locking in enclosure dimensions and user UI cues for the mirror shell.
Week 2 - Embedded Programming
Electronics basics and embedded programming for the aging biomarker device components.
MicrocontrollersProgrammingElectronics
System Integration Plans: Develop embedded programming protocols for real-time data collection from all six biomarker sensors, implementing initial signal processing algorithms and establishing the communication framework for multimodal data fusion.
Built the ReactionAge firmware + enclosure, published the first BOM, and validated timing pipelines that will feed the MirrorAge IC fusion engine.
Week 3 - 3D Scanning & Printing
3D scanning and printing techniques for bioprinting components and device housings.
3D scanning3D printingAI tools
System Integration Plans: Create custom 3D-printed components for camera mounting systems and facial recognition hardware, while developing 3D scanning protocols for ergonomic device design that accommodates all sensor modalities in a user-friendly form factor.
Modeled and printed the torsional grip spring, performed 3D scans for ergonomic fixtures, and captured training assets for face/gait datasets.
Week 4 - Electronics Design
EDA and schematic design for the aging biomarker device electronics.
EDA toolsSchematic designCircuit design
System Integration Plans: Design comprehensive PCB schematics that integrate force sensor circuits for grip strength measurement, microphone preamplifiers for voice analysis, camera interfaces for facial recognition, and timing circuits for reaction time assessment into a unified electronics platform.
Completed the Fusion 360/KiCad schematic/PCB layout for the ESP32S3 carrier tying together force, audio, camera, reaction, and wearable interfaces.
Week 5 - Electronics Production
PCB fabrication, debugging, and assembly for the biomarker device.
PCB fabricationDebuggingAssembly
System Integration Plans: Fabricate and assemble the integrated PCB containing all sensor interfaces, implementing power management systems for continuous operation and establishing data storage protocols for the multimodal biomarker data collection system.
Fabricated and assembled the carrier PCB, brought up power domains, and verified sensor buses—establishing the electronics backbone for integration.
Week 6 - Computer-controlled Machining
CAM and milling for precision components and device housings.
CAMMillingPrecision machining
System Integration Plans: Machine precision mechanical components for the integrated device housing using computer-controlled milling, ensuring proper alignment and mounting for all sensor modules while maintaining ergonomic design for user comfort during multimodal data collection.
Machined the floating mirror base and tensegrity nodes, refining fixturing that ensures repeatable camera and grip alignment in the final assembly.
Week 7 - Input Devices
Sensors and embedded architectures for data collection in the biomarker device.
SensorsInput devicesData collection
System Integration Plans: Integrate all six input sensor systems (force sensors for grip strength, microphones for voice analysis, cameras for facial recognition and gait analysis, reaction time circuits, and wearable accelerometer) into the unified data collection platform with real-time processing capabilities.
Integrated the force sensor, microphone, and ReactionAge modules on the carrier, logging synchronized packets that exercise the multimodal intake stack.
Week 8 - Output Devices
Actuators and system integration for the biomarker device outputs.
ActuatorsOutput devicesSystem integration
System Integration Plans: Implement output devices including display systems for real-time intrinsic capacity feedback and haptic feedback mechanisms for user interaction, creating an intuitive interface for the multimodal biomarker assessment system.
Deployed the SenseCraft FaceTTD pipeline on the XIAO ESP32S3, implemented OLED dithering previews, and confirmed end-to-end edge inference latency.
Week 9 - Molding & Casting
Forming and resin techniques for bioprinting molds and device components.
MoldingCastingResins
System Integration Plans: Create custom molded components for the bioprinting aspects of the project and develop specialized casings for sensor protection, ensuring the device can withstand continuous use during multimodal data collection sessions.
Machined wax molds, cast Mold Star silicone and Drystone ribs, and prototyped arrow-inspired shells that stabilize the mirror and protect embedded sensors.
Week 10 - Mechanical & Machine Design
Kits and mechanical design for the bioprinting and biomarker device systems.
Mechanical designMachine designSystem integration
System Integration Plans: Complete the mechanical design integration of all system components, implementing calibration protocols for sensor alignment and developing the complete mechanical framework that houses all six digital biomarker measurement systems.
Developed mechanical actuation systems including tapping and swiping mechanisms for phone interaction, integrated camera with Edge AI face detection and Wi-Fi livestreaming, designed and 3D-printed phone holder with amplifier, and prepared comprehensive midterm review documentation with system diagrams and timeline.
Week 11 - Networking & Communications
BLE, Wi-Fi, and communication protocols for the biomarker device connectivity.
BLEWi-FiCommunications
System Integration Plans: Implement wireless communication protocols (Bluetooth/Wi-Fi) for seamless data transmission from all six sensor modalities, enabling real-time data fusion and establishing connectivity for the wearable accelerometer integration into the multimodal assessment system.
Implemented Wi-Fi camera livestreaming for real-time video transmission, developed ESP-NOW networking protocols for device communication, designed and milled PCBs for networking components, and explored Meshtastic for long-range communication capabilities.
Week 12 - Interface & Application Programming
UI and application development for the biomarker device interface.
UI designApplicationsUser interface
System Integration Plans: Develop the complete user interface and application programming for the multimodal system, implementing the machine learning pipeline for intrinsic capacity score calculation and creating cloud integration for comprehensive data storage and analysis of all biomarker measurements.
Created Wi-Fi web interface for real-time pulse oximeter readings with live plotting, developed grip strength measurement device with load cell and integrated GUI, implemented OLED button user interface for device control, and established video streaming capabilities for sensor data visualization.
Week 13 - Wildcard & Final Orders
Final orders and wildcard week activities for project completion.
Final ordersWildcard activitiesProject completion
System Integration Plans: Complete final system integration, testing, and validation of the complete multimodal intrinsic capacity assessment platform, ensuring all six digital biomarkers work cohesively to provide accurate WHO-defined intrinsic capacity scores across all five domains (locomotor, cognition, vitality, sensory, psychological).
Designed and fabricated ATtiny1626 tiny development board with fiber laser PCB engraving, created glass engraving system with UV laser including blinking heart integration for visual feedback, milled mounting holes and completed board assembly, and prepared final board designs for system integration.
System Integration
Final integration week focused on bringing all subsystems together, completing hardware fabrication, firmware integration, and documentation for the MirrorAge system presentation. View full details →
Initial system integration work focused on subsystem validation, CAD model consolidation, and design backbone acquisition for band integration. Conducted comprehensive testing of all subsystems to ensure proper functionality, identified and resoldered defective joints, and exported CAD models of all PCBs into a unified assembly model.
Physical integration of subsystems into the complete demo table assembly, including mechanical component fabrication and electrical board consolidation. Integrated the complete demo table with precise placement of the MirrorAge handgrip subsystem and aging clock subsystem, providing a unified platform for system demonstration.
Continued fabrication work integrating all manufacturing processes. Focused on completing physical components and preparing subsystems for final assembly and testing.
Comprehensive subsystem integration combining 2D fabrication (laser cutting and vinyl cutting), 3D printing (rigid and flexible components), PCB milling (single and double-sided boards), and molding/casting to complete all physical components. Upgraded MirrorAge TFT board to v13 and aging clock TFT board to v16 with optimized component placement and routing. Established reliable I²C bus communication and validated all sensor addresses.
Final integration day focused on closing the watch subsystem, soldering and verifying all double-sided boards, refining molded bands, and assembling the complete MirrorAge demo with both the aging clock and grip-strength subsystems fully wired and tested. Completed rivet installation for plated through-holes, sensor bring-up (accelerometer, pulse oximeter, OLED/TFT displays), and full system integration on the tensegrity demo table. The integrated system successfully demonstrated synchronized sensor readouts and display behavior across all boards.
Final project presentation and demonstration of the complete MirrorAge system. Showcased the integrated aging clock and grip-strength subsystems working together on the demo table, demonstrating real-time sensor data collection and display synchronization. View final presentation demo →
Full Documentation: For complete details, design files, code, and comprehensive documentation of the system integration process, see Week 14: System Integration.
Final Project Masterpiece
Complete demonstration of the integrated MirrorAge system showcasing all subsystems working together in real-time.
Final Presentation Demo: Complete MirrorAge system demonstration showing the integrated aging clock and grip-strength subsystems operating together on the demo table, with synchronized sensor readouts and real-time display updates across all boards.
Complete repository of all design files, CAD models, schematics, PCB layouts, firmware, and fabrication files from Week 0 through Week 14, organized by week and component type.
Note: Additional design files, firmware, and documentation can be found in the respective week pages. Some files are part of larger archives (ZIP files) that contain multiple related design files.
Reflections & Learnings
Comprehensive reflections on the MirrorAge Intrinsic Capacity Mirror project development journey.
Modular system design allows for incremental development and component-level testing throughout the semester
Integration of mechanical, electrical, and software subsystems requires careful planning and coordination
Iterative design and prototyping revealed the importance of early testing and validation
Documentation and knowledge transfer are critical for project continuity and future improvements
The project successfully demonstrates how digital fabrication and embedded systems can create meaningful health assessment tools
Contributions
Acknowledgements and contributions that made this project possible.
Gladyshev Lab and Collaborators
Special thanks to the Gladyshev Lab and collaborators for the fruitful discussions that led to this multimodal intrinsic capacity assessment idea,
which supplements my PhD research goals in aging and longevity. The conceptual framework for integrating multiple digital biomarkers
to assess intrinsic capacity domains emerged from collaborative research discussions on aging biomarkers and healthspan assessment.
Transparent documentation of AI assistance used in this final project work, following course guidelines for ethical AI usage.
📋 General Guidelines: See General Commands for Cursor on the homepage for standard guidelines and commands used consistently throughout documentation development.
Cursor · Project Plan & Weekly Schedule
Comprehensive Cursor AI assistance for outlining the project plan and weekly schedule, including documentation structure, content organization, systematic updates across all week pages and the final project page, media integration, and summary generation workflows.
Cursor AI aligned the midterm review plan with updated system diagram, timeline, and remaining-task summaries, then refreshed finalproject.html to remove legacy bioprinting language and re-point internal links. The full transcript and generated HTML are available for review.
Cursor AI assistance for adding a white background behind the photo in the Final Project Spiral Development Model section on finalproject.html. The image container was updated with white background, padding, and rounded corners for improved visual presentation.
Cursor AI distilled Week 0–9 documentation and the Oct 31 lab meeting deck into midterm-ready narrative, cost, and validation content, replacing every placeholder in finalproject.html.
Transcript archived in markdown and HTML (generated via scripts/md_to_html_converter.py) for transparency.
ChatGPT was used to research and develop the multimodal intrinsic capacity assessment framework, including the comprehensive coverage analysis table and technical pipeline design.
The AI assisted with structuring the WHO-defined intrinsic capacity domains, identifying appropriate digital biomarkers, and designing the fusion architecture for multimodal data processing.
Cursor AI assisted with developing the complete final project page structure, implementing the multimodal intrinsic capacity assessment framework, and creating comprehensive documentation.
The AI helped with HTML structure, responsive design, weekly system integration plans, and organizing the technical documentation for the complete biomarker assessment system.
Cursor AI assisted with finalizing the project presentation structure to ensure full compliance with MIT Academy project presentation requirements.
The AI helped implement all required sections including answering questions, design documentation, bill of materials, individual mastery requirements,
course presentation structure, and spiral model development approach visualization.
ChatGPT was used to discuss camera system implementation strategies, image processing algorithms, and EdgeAI integration approaches.
The AI assisted with understanding Floyd-Steinberg dithering implementation, touch sensor integration, and exploring TinyML deployment options for the XIAO ESP32S3 platform.
AI-Assisted Project Highlights and Camera Subsystem Development
Cursor AI assisted with adding the project highlights section featuring camera system achievements and creating a comprehensive camera subsystem section with detailed code implementations, video demonstrations, and EdgeAI integration documentation.
The AI helped with HTML structure, responsive design, image processing explanations, and organizing the technical documentation for the complete camera system showcase.
```
Finding the exact location to add the system integration highlights:
Finding the end of the highlights section:
Finding the end of the highlights section:
Adding system integration highlights before the closing tag:
```html
Final Project · HTMAA 2025 · Saleem A. Al Dajani
Interactive selfie capture system with touch controls and real-time display
Vision Board
Conceptual visualization of the multimodal intrinsic capacity assessment system integrating grip strength, voice analysis, facial recognition, video motion capture, reaction time measurement, and wearable accelerometer data.
Intrinsic Capacity (IC) Coverage by Digital Biomarkers
Domain
Grip
Voice
Face
Video
Reaction Time
Wearable
Locomotor
✅
🔸
🔸
✅
🔸
✅
Cognition
❌
✅
🔸
🔸
✅
🔸
Vitality
✅
✅
✅
✅
🔸
✅
Sensory
❌
✅
✅
✅
✅
🔸
Psychological
❌
✅
✅
✅
🔸
✅
✅ Strong coverage |
🔸 Partial/indirect |
❌ Not covered |
View full table →
Multimodal IC Pipeline
Inputs: Grip Strength, Voice, Face, Video, Reaction Time, Wearable Accelerometer
Development Approach: Following the spiral model methodology, this final project will iterate through multiple development cycles, each building upon previous work while addressing new requirements and risks.
This snapshot covers the subsystems and documentation that will be shown during the midterm review. Links jump directly to the supporting sections with detailed evidence.
Featured Subsystems
Camera subsystem — Edge inference demos and selfie capture loop.
Instructor meeting hold — Thursday, Nov 12 at 10:00 AM ET reserved via the shared HTMAA midterm review sheet.
Execution Schedule (Timeline Snapshot)
Condensed from the Week 8–13 development timeline: each sprint builds toward final integration, mirroring the gantt chart below.
Week 8 · Output Devices: figuring out wiring for real-time display states.
Week 9 · Molding & Casting: learn how to cast custom housings and refine structural components.
Week 10 · Mechanical Design: figure out ergonomic enclosure and calibration fixtures.
Week 11 · Networking: program BLE/Wi-Fi telemetry and wearable data fusion.
Week 12 · Interface/App: create mobile UI, cloud bridge, and IC scoring pipeline.
Week 13 · Final Integration: run validation passes, document results, and prep deployment.
Instructor Review Logistics
Calendar hold sent for Thursday, Nov 12 at 10:00 AM ET (38-501 conference room) per the shared HTMAA scheduling sheet. Agenda covers subsystem demos, weekly documentation spot checks (Weeks 0–9), and next-sprint alignment. Meeting slot referenced in the midterm review schedule; awaiting final confirmation via class Slack.
System Architecture
Updated block diagram highlighting the multimodal sensing stack (grip, voice, face, motion, wearables), on-device inference layers, and real-time feedback channels that feed the intrinsic capacity score.
Development Timeline
Timeline aligns subsystem sprints with HTMAA milestones: output devices (Week 8), molding and casting (Week 9), mechanical design (Week 10), networking and communications (Week 11), app programming (Week 12), and final integration (Week 13).
Remaining Tasks (Snapshot)
Weeks 0–9 locked in the core subsystems—documentation workflow, cutting and molding for the housing, embedded prototypes for reaction timing, SenseCraft camera inference, and early grip/voice rigs. The checklist below captures what still needs to happen to converge on the integrated MirrorAge system.
Hardware Integration
Consolidate grip, voice, camera, reaction-time, and wearable sensor harnesses into the MirrorAge enclosure.
Finish molding/casting iterations for the ergonomic housing and align mounting features for PCBs and haptics.
Firmware & Edge AI
Stabilize onboard inference for SenseCraft vision models and voice-age pipelines on the XIAO ESP32S3.
Calibrate grip-force and reaction-time firmware for repeatable sampling; close the loop to haptic/display feedback.
Networking & Data Fusion
Bring up BLE/Wi-Fi data paths for wearable accelerometer streaming and cloud logging of intrinsic capacity scores.
Implement the fusion layer that combines per-domain scores into an overall IC metric with on-device storage.
Interface & UX
Finish mobile/web dashboard mockups for user onboarding, data review, and device calibration workflows.
Finalize real-time mirror feedback cues (display states, haptics, lighting) tied to sensor status and IC outcomes.
Validation & Documentation
Run end-to-end system tests (sensor capture → fusion → feedback) and document calibration procedures.
Record the one-minute video, finalize final presentation assets, and polish the bill of materials for review.
Week 14 System Integration Plan
Detailed day-by-day schedule for final system integration, covering design, fabrication, programming, testing, and documentation. This plan outlines the path to completing the MirrorAge system integration and preparing for final presentation. View on Week 14 page →
The act of bringing something to a conclusion or ending in a decisive manner. The ability to efficiently finish tasks and projects with a goal-oriented mindset.
Wednesday
Morning
Publish system integration plan on website
Update weekly assignment sections on final project page (weeks 10-13)
Link final project design files
Update reflections and learnings
Update picture of prism holder
Add final pictures to Slack canvases
Create schematic between boards (wired and wireless) — updated system diagram on PPT-like page
Start CAD model of system
Place final order
Afternoon & Evening
Design:
Boards: Combine OLED screen/accelerometer with pulse oximeter board in a new board (maybe upgrade to small TFT as minor)
Boards: Speaker board with realtime amplifier and TFT (on the load cell fixed board)
Band: Mold design
Cases: 3D print mountable cases for the boards
Integrate designs into final CAD
Document design
Finish CAD model of system
Thursday
Fabricate
Milling boards
Print mold and cast band
Print cases
Solder
Solder components on milled boards
Connect boards with wired (and wireless connection codes)
Finishing
Mirror on screen (easy way with the film)
Documentation
Document fabrication
Friday
Programming
Board level codes
Server level codes
Documentation
Document codes
Completion
Finish anything else
Saturday
Programming & Testing
Demo integrated system
Test integrated system
Documentation
Document testing and evaluation
Review and complete documentation (list of questions)
Make the video by collaging documentation
Sunday
Fill up any gaps
Prepare demo on tensegrity table
Finalize 1-slide
Work on minors
If done, work on if there's time
Monday Morning
Transport demo on tensegrity table
Fill up any gaps
Work on minors
Specific Tasks to Complete This Week
Major Tasks
CAD model of system
Speaker board with realtime amplifier
Combine screen/accelerometer with pulse oximeter board in a new board
Mold and cast band
Design and fabricate casing (print)
Schematic between boards (wired and wireless) — updated system diagram on PPT-like page
Serial connection between pulse oximeter and tiny blinking heart for BPM (BPM from IR, SpO2 from delta)
Combine multiple boards on the same WiFi (switching tabs is easy way, board hosting the webpage querying and update or Python-based server somewhere where everything posting data, Raspberry Pi)
Put+program everything together according to the above (with WiFi for now)
MirrorAge is a self-contained edge-AI mirror that captures grip strength, facial imagery, voice, motion, and reaction time to estimate intrinsic capacity in real time.
The platform fuses weekly prototypes—ReactionAge latency tests, 3D printed grip mechanics, SenseCraft camera inference, and molded structural elements—into a multimodal mortality risk profiler.
Subsystems in progress: reaction-time module, SenseCraft FaceTTD inference stack, VoiceAge microphone pipeline, wearable streaming via BLE, and molded structural packaging.
Clinical motivation: translate WHO intrinsic capacity domains into measurable digital biomarkers that flag functional decline earlier than chronological age alone.
Project Goals
Deliver multimodal IC scoring Fuse grip, face, voice, reaction-time, and wearable streams on-device to output an intrinsic capacity score plus domain deltas.
Fabricate modular, serviceable hardware Iterate laser-cut tensegrity mirror shells, 3D printed torsional grips, custom PCBs, and silicone cast fixtures that assemble without bespoke tooling.
Validate against ground truth Benchmark embedded inferences against published datasets (Blomkvist et al. 2017, Fuentealba et al. 2025) and lab-collected pilots to quantify accuracy, latency, and reliability.
Timeline & Milestones
Week 10 · Hardware convergence Integrate SenseCraft FaceTTD camera, ReactionAge latency module, and newly milled PCB into a single ESP32S3 backplane.
Week 12 · Midterm review build Finish molded mirror enclosure, bring up BLE wearable link, and demo live IC score during midterm critique.
Final week · Validation & documentation Execute pilot data collection, refine model weights, and release reproducible fabrication + firmware packages.
Documenting the final project masterpiece that integrates the range of units covered, addressing all required questions.
What does it do?
MirrorAge captures synchronized digital biomarkers—camera frames processed with on-device FaceTTD models, VoiceAge microphone samples, grip strength torque, wearable accelerometry, and ReactionAge latency—to estimate intrinsic capacity and time-to-death acceleration.
A XIAO ESP32S3 Sense orchestrates sensing, performs Edge Impulse inference, and displays a live mortality-risk score on the OLED while logging packets to a Python analytics notebook.
Who's done what beforehand?
The concept builds on WHO intrinsic capacity framing and recent mortality-risk studies: Niccoli & Partridge (2012) establish age as the dominant chronic-disease predictor; Fuentealba et al. (Nature Aging 2025) show blood-based IC clocks outperform chronological models;
Zhavoronkov & Bhullar (2015) and Lancet Healthy Longevity editorials motivate treating functional decline as the actionable signal.
This project translates those findings into an accessible, multimodal measurement mirror that can operate outside hospital labs.
What sources did you use?
Primary references include Nature Aging 2025 intrinsic capacity papers, the PLOS ONE ReactionAge dataset (Blomkvist et al. 2017), Edge Impulse SenseCraft documentation, Smooth‑On Mold Star technical bulletins, RotoMetals alloy certificates, MIT HTMAA recitations, and the open-source GRPR grip-strength meter.
Design inspiration and safety notes were consolidated from Anthony Pennes' HTMA guides and Fab Academy molding tutorials.
What did you design?
• Laser-cut cardboard origami mirror frame and tensegrity-inspired floating mount (Weeks 1 & 6)
• ReactionAge firmware + enclosure with statistical post-processing dashboards (Week 2)
• 3D printed torsional spring grip module tuned for ±40 kg ranges (Week 3)
• KiCad/Fusion carrier PCB for the ESP32S3 Sense with OLED, force, and BLE breakouts (Week 5)
• Edge Impulse deployment pipeline with grayscale dithering overlay and live inference UX (Weeks 7–8)
• CAM toolpaths, silicone molds, and Drystone casts for structural packaging (Week 9)
What materials and components were used?
Seeed XIAO ESP32S3 Sense module with OV2640 camera and PDM mic, SparkFun Qwiic button and force sensors, SSD1306 OLED, wearable IMU node (Bosch BHI260), laser-cut cardboard/birch sheets, PLA+/Onyx filament, Mold Star 30 silicone, Drystone gypsum, Roto281 fusible alloy, and embedded fasteners/heat-set inserts.
Where did they come from?
Electronics from Seeed Studio, SparkFun, Digi-Key, and Adafruit; molding supplies and silicones from Reynolds Advanced Materials; Drystone and Hydro-Stone from USG via the MIT CBA stockroom; fusible alloys from RotoMetals; structural lumber and plywood from MIT's shop inventory; filaments from Prusa Research and Markforged.
How much did they cost?
Current spend: $96.34 for ReactionAge components (Week 2 BOM) + $78.42 for SenseCraft camera stack (XIAO ESP32S3 Sense, OLED, cabling) + $42.10 for molding media (Mold Star 30 quart, Drystone, release agents) = $216.86 to date.
Remaining allocation (~$130) is earmarked for BLE wearable hardware and final enclosure finishes; detailed line items tracked in the Airtable budget and mirrored in each weekly BOM CSV.
What parts and systems were made?
Custom origami mirror frame, 3D printed torsional grip shell, machined floating base, silicone molds and Drystone casts for arrow-inspired structural ribs, bespoke ESP32S3 breakout PCB, laser-cut ReactionAge control panel, and assembled sensor tower linking camera, OLED, and wearable gateway.
What tools and processes were used?
Parametric CAD in Fusion 360, laser cutting (Epilog) for origami tiles, Prusa MK4 FDM printing, Formlabs SLA for detail inserts, ShopBot CNC and Bantam PCB milling, silicone mixing/casting under vacuum, Edge Impulse model training, PlatformIO firmware, and Python/NumPy validation notebooks.
What questions were answered?
• Can consumer-grade sensors reproduce published reaction-time age curves? (Yes—ReactionAge matched Blomkvist et al. regression within 4.6 ms RMSE.)
• Will SenseCraft FaceTTD run locally on ESP32S3 with acceptable latency? (Yes—~310 ms/inference at 30% baseline accuracy, highlighting dataset needs.)
• Does molded packaging improve sensor placement repeatability? (Yes—silicone nests held camera ±0.5 mm, reducing alignment drift seen in cardboard prototypes.)
What worked? What didn't?
✅ Floyd–Steinberg dithering produced clear OLED previews; ✅ ReactionAge firmware maintained ±1 ms jitter; ✅ Molded Drystone ribs stiffened mirror shell without excess weight.
⚠️ FaceTTD accuracy plateaued at 30% due to limited training diversity; ⚠️ VoiceAge requires more MFCC samples to sustain 0.64-year MAE; ⚠️ Grip spring fatigue highlighted need for fiber-reinforced print or machined aluminum insert.
How was it evaluated?
Bench tests compare embedded predictions to published curves and desktop baselines: ReactionAge latency vs. Wii Balance Board golden data; FaceTTD inferencing cross-validated against Edge Impulse cloud classifier; VoiceAge MFCC regression verified through train/holdout splits; mechanical fixtures inspected with feeler gauges and dial indicators for tolerance drift.
What are the implications?
A portable intrinsic capacity mirror supports proactive geriatric screening, telehealth coaching, and longitudinal studies that correlate functional decline with interventions.
By grounding hardware in open-source parts and HTMAA fabrication methods, the system can be replicated across labs and community clinics to accelerate validation of digital aging biomarkers and personalize longevity therapies.
Design
Your project should incorporate 2D and 3D design, multiple additive and subtractive fabrication processes, electronics design and production, embedded microcontroller design, interfacing, and programming, system integration and packaging.
2D Design
2D design work for the multimodal intrinsic capacity assessment system:
Cardboard origami tiling for circular mirror frame, optimized for kerf learned during Week 1 laser characterization.
Vinyl-cut ReactionAge control labels and MirrorAge fascia decals for rapid UI readability.
KiCad/Fusion schematics + polygon pours for ESP32S3 carrier, force sensing front-end, and OLED interposer.
2D shop drawings for CNC floating base, including registration dowels and silicone mold parting lines.
Figma wireframes outlining the midterm web dashboard and on-device OLED states.
Subtractive: Laser cutting, milling for precision parts
Electronics: PCB design and production
Programming: Embedded microcontroller development
Bill of Materials
Where possible, I fabricated parts rather than buying them. This table summarizes all unique components in the final MirrorAge system, their approximate costs, and where they are used.
A mirrored copy of this bill of materials also appears on the Week 14 system-integration page for cross-linking directly from the integration steps
(Week 14 BOM).
Grip-strength molds, band molds, structural ribs
(Week 9,
Week 14)
Fasteners
M2/M3 hardware, heat-set inserts, misc. screws
Assorted
~$0.10–$0.30 ea.
$20.00 (bundle)
All mechanical assemblies (watch, grip rig, camera mount, demo table)
Estimated Total Project Cost
Electronics ≈ $190 · Mechanical & materials ≈ $130 ·
Total ≈ $320 (excluding lab-provided consumables and reused stock).
Exact per-week line items remain in the weekly documentation tables (for example
ReactionAge BOM CSV in Week 2),
while this table captures the consolidated, unique parts that make up the final integrated MirrorAge system.
Fabrication Process
Week-by-week fabrication rolled forward subsystems toward the integrated mirror:
Week 1 laser-cut origami tiles for the circular bezel; Week 2 PCB milling + soldering for ReactionAge;
Week 3–4 torsional spring 3D prints and sanding jigs; Week 5 copper-clad milling and reflow of the ESP32S3 carrier;
Week 6 ShopBot machining of the floating base; Week 8 resin + FDM camera enclosure build; Week 9 wax machining, Mold Star casting, and Drystone ribs.
Each step captured feeds-and-speeds, toolpaths, and fixturing photos embedded in the weekly pages for replication.
Testing & Validation
Validation combined bench instrumentation and statistical analysis: oscilloscope timing to verify ReactionAge jitter, Edge Impulse confusion matrices for FaceTTD and VoiceAge,
Instron pull tests for the torsional grip cartridge, IR thermography while curing Mold Star molds, dial-indicator checks on CNC-machined bases, and adhesive shear testing on mirror mounts.
Data are logged to CSV via the ESP32S3 and compared against published baselines inside the midterm Jupyter notebook.
Individual Mastery and Independent Operation
Projects can be separate or joint, but need to show individual mastery of the skills, and be independently operable.
Individual Mastery
Demonstration of individual skills across all course units:
2D and 3D Design
Modeled the tensegrity floating mirror, torsional grip shells, and camera bezel in Fusion 360 and Onshape.
Drove design reviews with Anthony/Neil to lock tolerances, assembly order, and module interface specs.
Demonstrates mastery across cutting, 3D printing, machining, electronics, networking, and interface programming units.
Documentation cross-linked via weekly pages, GitHub repos, and BOM spreadsheets for traceability.
Group Assignments
Collaborative work and individual contributions:
Embedded programming group: authored workflow trade-off analysis and repo organization that seeded ReactionAge firmware patterns.
Molding & casting group: led SDS review, material trials, and mixing SOP that informed final mirror mold.
Shared camera dev sessions with peers to improve Edge Impulse dataset collection and SenseCraft deployment strategies.
Useful Documentation
Helpful resources, documentation, and design files for the multimodal intrinsic capacity assessment system.
Open Source Grip Strength Meter
A cost-effective $50 grip strength measurement system that can be further optimized for our multimodal assessment platform.
This open-source design provides an excellent foundation for integrating grip strength measurement into our intrinsic capacity assessment system,
with potential for cost reduction through signal multiplexing on a single processor.
Detailed technical pipeline for processing multiple digital biomarkers to generate intrinsic capacity scores.
Pipeline Architecture
Inputs
• Grip Strength
• Voice
• Face
• Video (motion/gait)
• Reaction Time
• Wearable Accelerometer
→
Feature Extraction
Strength metrics
Prosody features
Facial landmarks
Gait parameters
Response latency
Activity patterns
Embeddings
Features converted to vector representations for multimodal fusion
→
Fusion Layer
Combines multimodal features using attention mechanisms
Output
• Overall IC Score
• Domain sub-scores
→
Domain Scores
Locomotor
Cognition
Vitality
Sensory
Psychological
Weekly System Development Breakdown
How each week of HTMAA 2025 builds toward the complete multimodal intrinsic capacity assessment system.
Week 0: Project Ideation
Initial concept development and planning
Project planning and documentation structure
Research direction and concept sketches
Week 1: Precision Cutting
Laser and vinyl cutting techniques
Device housing components via laser cutting
Sensor mounting brackets and enclosures
Vinyl cutting for device labeling and UI elements
Week 2: Embedded Programming
Electronics basics and microcontroller programming
Microcontroller programming for data collection
Basic sensor interface circuits
Week 3: 3D Scanning & Printing
3D technologies for device components
3D scanning for custom component design
3D printing for device housings
Week 4: Electronics Design
EDA and schematic design
PCB design for grip strength measurement
Sensor interface circuits and signal conditioning
Power management and data storage systems
Week 5: Electronics Production
PCB fabrication and assembly
PCB fabrication and debugging
Component assembly and testing
Week 6: Computer-controlled Machining
CAM and precision milling
Precision components via milling
Custom mechanical parts
Week 7: Input Devices
Sensor integration for data collection
Force sensors for grip strength measurement
Microphones for voice analysis
Camera systems for facial expression analysis
Reaction time measurement circuits
Week 8: Output Devices
Actuators and system integration
Display systems for real-time feedback
Haptic feedback for user interaction
Week 9: Molding & Casting
Forming and resin techniques
3D printing and molding for custom components
Silicone casting for device components
Week 10: Mechanical & Machine Design
System integration and mechanical design
Mechanical design for ergonomic device housing
System integration and calibration protocols
Week 11: Networking & Communications
Connectivity and communication protocols
Bluetooth/Wi-Fi connectivity for data transmission
Wearable accelerometer integration and data fusion
Week 12: Interface & Application Programming
UI development and application programming
Mobile app development for user interface
Cloud integration for data storage and analysis
Machine learning pipeline for IC score calculation
Week 13: Wildcard & Final Integration
Final orders and complete system deployment
Final testing, validation, and documentation
System integration and deployment
Camera Subsystem
Advanced camera system implementation using XIAO ESP32S3 Sense with real-time image processing, EdgeAI integration, and interactive selfie capture functionality.
System Overview
The camera system successfully captures images, processes them into bitmaps, and displays them on an OLED screen using advanced Floyd-Steinberg dithering algorithms.
Video Demonstrations
Camera Bot Selfie
Demonstration of the interactive selfie capture system with touch controls
Picture of Picture
Meta demonstration showing the camera system capturing its own display
Code Implementation
60-Second Auto Capture System
Automated camera system that captures and displays images every 60 seconds using advanced image processing techniques.
1. Initialize camera with PSRAM frame buffers
2. Configure OLED display (128x64 pixels)
3. Set up 60-second capture interval timer
4. In main loop:
a. Check if 60 seconds have elapsed
b. Capture image from camera
c. Process image:
- Downsample to 128x64 via box averaging
- Apply contrast stretch (linear scaling)
- Perform Floyd-Steinberg dithering
d. Display processed bitmap on OLED
e. Release frame buffer
5. Repeat process
Touch-Controlled Capture System
Interactive camera system with touch controls allowing manual capture triggers in addition to automatic timing.
1. Initialize camera and OLED display
2. Set up touch pins (GPIO1 & GPIO2) with threshold detection
3. Configure 60-second auto-capture timer
4. In main loop:
a. Update touch sensor readings
b. Detect touch press events (justPressed)
c. Check for capture trigger:
- Touch press OR 60-second timer elapsed
d. If triggered:
- Capture image from camera
- Process image (same as auto version)
- Display on OLED
- Reset timer
5. Continue monitoring for next trigger
The system captures photos, converts them to bitmaps using advanced image processing algorithms, and displays them on the OLED screen.
I'm also exploring integration with ML models, either through online API calls or by embedding TinyML model parameters from Python to C++.
Future development includes live streaming real-time video with ML prediction updates based on variable observation times,
and exploring Edge Impulse models as an alternative to manual Python-to-C++ conversion for faster deployment.
EdgeAI/TinyML Integration
Edge AI can also be implemented using Edge Impulse models, which may be faster than manually converting Python models to C++.
The SenseCraft AI platform provides a streamlined approach to training and deploying ML models directly on the XIAO ESP32S3.
Deploy inference bundle to the SenseCraft board alongside the camera stack.
Benchmark latency and accuracy against baseline VoiceAge models and document calibration protocol.
Week 0 - Introduction & Design
Project ideation and initial concept development for bioprinting rejuvenated tissue and aging biomarker devices.
Project planningConcept sketchesResearch direction
System Integration Plans: Establish the foundational architecture for multimodal data collection by designing the overall system framework that will integrate all six digital biomarkers (grip strength, voice, face, video, reaction time, wearable accelerometer) into a cohesive intrinsic capacity assessment platform.
Mapped the MirrorAge subsystem architecture, assembled the intrinsic capacity literature stack, and kicked off BRR/IRB coordination so fabrication sprints stay aligned with clinical requirements.
Week 1 - Principles & Cutting
Version control, laser cutting, and vinyl cutting techniques applied to final project components.
Laser cuttingVinyl cuttingVersion control
System Integration Plans: Fabricate precision-cut housing components and mounting brackets for all sensor modules (force sensors, microphones, cameras, reaction time circuits) using laser cutting, while creating vinyl-cut labels and UI elements for device identification and user guidance.
Characterized laser kerf, produced the origami mirror frame tiles, and generated vinyl interface labels—locking in enclosure dimensions and user UI cues for the mirror shell.
Week 2 - Embedded Programming
Electronics basics and embedded programming for the aging biomarker device components.
MicrocontrollersProgrammingElectronics
System Integration Plans: Develop embedded programming protocols for real-time data collection from all six biomarker sensors, implementing initial signal processing algorithms and establishing the communication framework for multimodal data fusion.
Built the ReactionAge firmware + enclosure, published the first BOM, and validated timing pipelines that will feed the MirrorAge IC fusion engine.
Week 3 - 3D Scanning & Printing
3D scanning and printing techniques for bioprinting components and device housings.
3D scanning3D printingAI tools
System Integration Plans: Create custom 3D-printed components for camera mounting systems and facial recognition hardware, while developing 3D scanning protocols for ergonomic device design that accommodates all sensor modalities in a user-friendly form factor.
Modeled and printed the torsional grip spring, performed 3D scans for ergonomic fixtures, and captured training assets for face/gait datasets.
Week 4 - Electronics Design
EDA and schematic design for the aging biomarker device electronics.
EDA toolsSchematic designCircuit design
System Integration Plans: Design comprehensive PCB schematics that integrate force sensor circuits for grip strength measurement, microphone preamplifiers for voice analysis, camera interfaces for facial recognition, and timing circuits for reaction time assessment into a unified electronics platform.
Completed the Fusion 360/KiCad schematic/PCB layout for the ESP32S3 carrier tying together force, audio, camera, reaction, and wearable interfaces.
Week 5 - Electronics Production
PCB fabrication, debugging, and assembly for the biomarker device.
PCB fabricationDebuggingAssembly
System Integration Plans: Fabricate and assemble the integrated PCB containing all sensor interfaces, implementing power management systems for continuous operation and establishing data storage protocols for the multimodal biomarker data collection system.
Fabricated and assembled the carrier PCB, brought up power domains, and verified sensor buses—establishing the electronics backbone for integration.
Week 6 - Computer-controlled Machining
CAM and milling for precision components and device housings.
CAMMillingPrecision machining
System Integration Plans: Machine precision mechanical components for the integrated device housing using computer-controlled milling, ensuring proper alignment and mounting for all sensor modules while maintaining ergonomic design for user comfort during multimodal data collection.
Machined the floating mirror base and tensegrity nodes, refining fixturing that ensures repeatable camera and grip alignment in the final assembly.
Week 7 - Input Devices
Sensors and embedded architectures for data collection in the biomarker device.
SensorsInput devicesData collection
System Integration Plans: Integrate all six input sensor systems (force sensors for grip strength, microphones for voice analysis, cameras for facial recognition and gait analysis, reaction time circuits, and wearable accelerometer) into the unified data collection platform with real-time processing capabilities.
Integrated the force sensor, microphone, and ReactionAge modules on the carrier, logging synchronized packets that exercise the multimodal intake stack.
Week 8 - Output Devices
Actuators and system integration for the biomarker device outputs.
ActuatorsOutput devicesSystem integration
System Integration Plans: Implement output devices including display systems for real-time intrinsic capacity feedback and haptic feedback mechanisms for user interaction, creating an intuitive interface for the multimodal biomarker assessment system.
Deployed the SenseCraft FaceTTD pipeline on the XIAO ESP32S3, implemented OLED dithering previews, and confirmed end-to-end edge inference latency.
Week 9 - Molding & Casting
Forming and resin techniques for bioprinting molds and device components.
MoldingCastingResins
System Integration Plans: Create custom molded components for the bioprinting aspects of the project and develop specialized casings for sensor protection, ensuring the device can withstand continuous use during multimodal data collection sessions.
Machined wax molds, cast Mold Star silicone and Drystone ribs, and prototyped arrow-inspired shells that stabilize the mirror and protect embedded sensors.
Week 10 - Mechanical & Machine Design
Kits and mechanical design for the bioprinting and biomarker device systems.
Mechanical designMachine designSystem integration
System Integration Plans: Complete the mechanical design integration of all system components, implementing calibration protocols for sensor alignment and developing the complete mechanical framework that houses all six digital biomarker measurement systems.
Developed mechanical actuation systems including tapping and swiping mechanisms for phone interaction, integrated camera with Edge AI face detection and Wi-Fi livestreaming, designed and 3D-printed phone holder with amplifier, and prepared comprehensive midterm review documentation with system diagrams and timeline.
Week 11 - Networking & Communications
BLE, Wi-Fi, and communication protocols for the biomarker device connectivity.
BLEWi-FiCommunications
System Integration Plans: Implement wireless communication protocols (Bluetooth/Wi-Fi) for seamless data transmission from all six sensor modalities, enabling real-time data fusion and establishing connectivity for the wearable accelerometer integration into the multimodal assessment system.
Implemented Wi-Fi camera livestreaming for real-time video transmission, developed ESP-NOW networking protocols for device communication, designed and milled PCBs for networking components, and explored Meshtastic for long-range communication capabilities.
Week 12 - Interface & Application Programming
UI and application development for the biomarker device interface.
UI designApplicationsUser interface
System Integration Plans: Develop the complete user interface and application programming for the multimodal system, implementing the machine learning pipeline for intrinsic capacity score calculation and creating cloud integration for comprehensive data storage and analysis of all biomarker measurements.
Created Wi-Fi web interface for real-time pulse oximeter readings with live plotting, developed grip strength measurement device with load cell and integrated GUI, implemented OLED button user interface for device control, and established video streaming capabilities for sensor data visualization.
Week 13 - Wildcard & Final Orders
Final orders and wildcard week activities for project completion.
Final ordersWildcard activitiesProject completion
System Integration Plans: Complete final system integration, testing, and validation of the complete multimodal intrinsic capacity assessment platform, ensuring all six digital biomarkers work cohesively to provide accurate WHO-defined intrinsic capacity scores across all five domains (locomotor, cognition, vitality, sensory, psychological).
Designed and fabricated ATtiny1626 tiny development board with fiber laser PCB engraving, created glass engraving system with UV laser including blinking heart integration for visual feedback, milled mounting holes and completed board assembly, and prepared final board designs for system integration.
System Integration
Final integration week focused on bringing all subsystems together, completing hardware fabrication, firmware integration, and documentation for the MirrorAge system presentation. View full details →
Initial system integration work focused on subsystem validation, CAD model consolidation, and design backbone acquisition for band integration. Conducted comprehensive testing of all subsystems to ensure proper functionality, identified and resoldered defective joints, and exported CAD models of all PCBs into a unified assembly model.
Physical integration of subsystems into the complete demo table assembly, including mechanical component fabrication and electrical board consolidation. Integrated the complete demo table with precise placement of the MirrorAge handgrip subsystem and aging clock subsystem, providing a unified platform for system demonstration.
Continued fabrication work integrating all manufacturing processes. Focused on completing physical components and preparing subsystems for final assembly and testing.
Comprehensive subsystem integration combining 2D fabrication (laser cutting and vinyl cutting), 3D printing (rigid and flexible components), PCB milling (single and double-sided boards), and molding/casting to complete all physical components. Upgraded MirrorAge TFT board to v13 and aging clock TFT board to v16 with optimized component placement and routing. Established reliable I²C bus communication and validated all sensor addresses.
Final integration day focused on closing the watch subsystem, soldering and verifying all double-sided boards, refining molded bands, and assembling the complete MirrorAge demo with both the aging clock and grip-strength subsystems fully wired and tested. Completed rivet installation for plated through-holes, sensor bring-up (accelerometer, pulse oximeter, OLED/TFT displays), and full system integration on the tensegrity demo table. The integrated system successfully demonstrated synchronized sensor readouts and display behavior across all boards.
Final project presentation and demonstration of the complete MirrorAge system. Showcased the integrated aging clock and grip-strength subsystems working together on the demo table, demonstrating real-time sensor data collection and display synchronization. View final presentation demo →
Full Documentation: For complete details, design files, code, and comprehensive documentation of the system integration process, see Week 14: System Integration.
Final Project Masterpiece
Complete demonstration of the integrated MirrorAge system showcasing all subsystems working together in real-time.
Final Presentation Demo: Complete MirrorAge system demonstration showing the integrated aging clock and grip-strength subsystems operating together on the demo table, with synchronized sensor readouts and real-time display updates across all boards.
Complete repository of all design files, CAD models, schematics, PCB layouts, firmware, and fabrication files from Week 0 through Week 14, organized by week and component type.
Note: Additional design files, firmware, and documentation can be found in the respective week pages. Some files are part of larger archives (ZIP files) that contain multiple related design files.
Reflections & Learnings
Comprehensive reflections on the MirrorAge Intrinsic Capacity Mirror project development journey.
Modular system design allows for incremental development and component-level testing throughout the semester
Integration of mechanical, electrical, and software subsystems requires careful planning and coordination
Iterative design and prototyping revealed the importance of early testing and validation
Documentation and knowledge transfer are critical for project continuity and future improvements
The project successfully demonstrates how digital fabrication and embedded systems can create meaningful health assessment tools
Contributions
Acknowledgements and contributions that made this project possible.
Gladyshev Lab and Collaborators
Special thanks to the Gladyshev Lab and collaborators for the fruitful discussions that led to this multimodal intrinsic capacity assessment idea,
which supplements my PhD research goals in aging and longevity. The conceptual framework for integrating multiple digital biomarkers
to assess intrinsic capacity domains emerged from collaborative research discussions on aging biomarkers and healthspan assessment.
Transparent documentation of AI assistance used in this final project work, following course guidelines for ethical AI usage.
📋 General Guidelines: See General Commands for Cursor on the homepage for standard guidelines and commands used consistently throughout documentation development.
Cursor · Project Plan & Weekly Schedule
Comprehensive Cursor AI assistance for outlining the project plan and weekly schedule, including documentation structure, content organization, systematic updates across all week pages and the final project page, media integration, and summary generation workflows.
Cursor AI aligned the midterm review plan with updated system diagram, timeline, and remaining-task summaries, then refreshed finalproject.html to remove legacy bioprinting language and re-point internal links. The full transcript and generated HTML are available for review.
Cursor AI assistance for adding a white background behind the photo in the Final Project Spiral Development Model section on finalproject.html. The image container was updated with white background, padding, and rounded corners for improved visual presentation.
Cursor AI distilled Week 0–9 documentation and the Oct 31 lab meeting deck into midterm-ready narrative, cost, and validation content, replacing every placeholder in finalproject.html.
Transcript archived in markdown and HTML (generated via scripts/md_to_html_converter.py) for transparency.
ChatGPT was used to research and develop the multimodal intrinsic capacity assessment framework, including the comprehensive coverage analysis table and technical pipeline design.
The AI assisted with structuring the WHO-defined intrinsic capacity domains, identifying appropriate digital biomarkers, and designing the fusion architecture for multimodal data processing.
Cursor AI assisted with developing the complete final project page structure, implementing the multimodal intrinsic capacity assessment framework, and creating comprehensive documentation.
The AI helped with HTML structure, responsive design, weekly system integration plans, and organizing the technical documentation for the complete biomarker assessment system.
Cursor AI assisted with finalizing the project presentation structure to ensure full compliance with MIT Academy project presentation requirements.
The AI helped implement all required sections including answering questions, design documentation, bill of materials, individual mastery requirements,
course presentation structure, and spiral model development approach visualization.
ChatGPT was used to discuss camera system implementation strategies, image processing algorithms, and EdgeAI integration approaches.
The AI assisted with understanding Floyd-Steinberg dithering implementation, touch sensor integration, and exploring TinyML deployment options for the XIAO ESP32S3 platform.
AI-Assisted Project Highlights and Camera Subsystem Development
Cursor AI assisted with adding the project highlights section featuring camera system achievements and creating a comprehensive camera subsystem section with detailed code implementations, video demonstrations, and EdgeAI integration documentation.
The AI helped with HTML structure, responsive design, image processing explanations, and organizing the technical documentation for the complete camera system showcase.
```
Adding a link to the final project masterpiece in week14.html:
Adding a link to the final project masterpiece in the Day 6 section:
```html
Week 14 · Final Project
Final integration week focused on bringing all subsystems together, completing hardware fabrication, firmware integration, and documentation for the MirrorAge system presentation.
The act of bringing something to a conclusion or ending in a decisive manner. The ability to efficiently finish tasks and projects with a goal-oriented mindset.
Wednesday
Morning
Publish system integration plan on website
Update weekly assignment sections on final project page (weeks 10-13)
Link final project design files
Update reflections and learnings
Update picture of prism holder
Add final pictures to Slack canvases
Create schematic between boards (wired and wireless) — updated system diagram on PPT-like page
Start CAD model of system
Place final order
Afternoon & Evening
Design:
Boards: Combine OLED screen/accelerometer with pulse oximeter board in a new board (maybe upgrade to small TFT as minor)
Boards: Speaker board with realtime amplifier and TFT (on the load cell fixed board)
Band: Mold design
Cases: 3D print mountable cases for the boards
Integrate designs into final CAD
Document design
Finish CAD model of system
Thursday
Fabricate
Milling boards
Print mold and cast band
Print cases
Solder
Solder components on milled boards
Connect boards with wired (and wireless connection codes)
Finishing
Mirror on screen (easy way with the film)
Documentation
Document fabrication
Friday
Programming
Board level codes
Server level codes
Documentation
Document codes
Completion
Finish anything else
Saturday
Programming & Testing
Demo integrated system
Test integrated system
Documentation
Document testing and evaluation
Review and complete documentation (list of questions)
Make the video by collaging documentation
Sunday
Fill up any gaps
Prepare demo on tensegrity table
Finalize 1-slide
Work on minors
If done, work on if there's time
Monday Morning
Transport demo on tensegrity table
Fill up any gaps
Work on minors
Specific Tasks to Complete This Week
Major Tasks
CAD model of system
Speaker board with realtime amplifier
Combine screen/accelerometer with pulse oximeter board in a new board
Mold and cast band
Design and fabricate casing (print)
Schematic between boards (wired and wireless) — updated system diagram on PPT-like page
Serial connection between pulse oximeter and tiny blinking heart for BPM (BPM from IR, SpO2 from delta)
Combine multiple boards on the same WiFi (switching tabs is easy way, board hosting the webpage querying and update or Python-based server somewhere where everything posting data, Raspberry Pi)
Put+program everything together according to the above (with WiFi for now)
Summary slide and one-minute video for documentation
Conception
Construction
Operation
Minor Tasks
Program microphone/speaker
Fix reaction time delay code
Program LoRa connection
Fix OLED plus WiFi issue
Upgrade to TFT (SPI is very straightforward, design board with either SPI or OLED connection)
Fix heart engraving to center
Engrave K9 glass mirror if it arrives
RD and IRD isolation slit (maybe wick and then cut)
Do the calibration curve for the load cell
Finish cardboard laser cutter origami big mirror frame
If There's Time
Moving base of mirror
Orders
Raspberry Pi Zero (or server host, do some research)
Presentation
Aim for 2.5 minutes because Neil will ask questions
Generally no slides except for 1 open summary slide (have backup slides in case questions come up!)
Related: See the Development Timeline on the final project page for the overall project schedule.
Day 1: Design Integration
Initial system integration work focused on subsystem validation, CAD model consolidation, and design backbone acquisition for band integration.
Subsystem Validation
Conducted comprehensive testing of all subsystems to ensure proper functionality. Identified and resoldered any defective joints, verifying that each subsystem operates correctly before proceeding with full system integration.
CAD Model Consolidation
Exported CAD models of all PCBs in the final design and imported them into a unified CAD assembly. This consolidated model provides a complete view of the system's mechanical integration and spatial relationships.
Integrated CAD Model: Exploded isometric view of the complete system assembly, including all PCBs (pulse oximeter, OLED/accelerometer, speaker/amplifier), main housing with transparent enclosure, and wearable band components. The model shows the spatial relationships between electronic subsystems and mechanical structures, enabling precise integration planning.
Band Design Backbone
Acquired CAD design files for Apple Watch form factor integration, enabling compatibility with existing band designs and standardized watch components. This provides a proven mechanical foundation for the wearable subsystem.
Resuming the daily schedule tomorrow with parallel work streams prioritized according to the critical path. Tasks that cannot be completed during scheduled days will be shifted to buffer days on Saturday and Sunday to maintain project momentum.
Day 2: Electrical and Mechanical Integration
Physical integration of subsystems into the complete demo table assembly, including mechanical component fabrication and electrical board consolidation.
2.1 Mechanical Integration
Mechanical design integration now includes the complete demo table with precise placement of the MirrorAge handgrip subsystem and the aging clock subsystem. The integrated assembly provides a unified platform for system demonstration and testing.
Complete Demo Table Assembly: Integrated mechanical design showing precise placement of the MirrorAge handgrip subsystem and aging clock subsystem on the demo table. The assembly demonstrates the spatial relationships and mounting configurations for both subsystems within the unified demonstration platform.
3D Additive Manufacturing
All 3D additive mechanical components were printed for rapid iterative development. The fabrication process required specific print settings and support strategies for different components:
Printing Initiation: 3D printer starting the fabrication process for mechanical components
Casing Print: Casing component during 3D printing process
Print Configuration Requirements:
Casing: Required organic support structures for complex overhangs
Dock: Required brim adhesion to prevent warping during printing
Bands: Printed using TPU (Thermoplastic Polyurethane) material for flexibility (will spiral into molding and casting in future iterations)
Organic Support Configuration: Slicer settings showing organic support structures for the casing component
Brim Addition: Dock component with brim added to prevent warping during printing
Casing with Organic Support: Printed casing component showing organic support structures
TPU Bands: Flexible wearable band components printed using TPU material
Print Failures and Iteration
Failed Casing Print: Initial casing print failure requiring support structure adjustments
Failed Dock Print: Dock print failure due to warping, resolved with brim addition
Printing Failures: Documentation of various print failures encountered during iterative development
Printing Progress: Successful components showing iterative improvement in print quality
2D Subtractive Manufacturing
The first 2D subtractive mechanical component was debugged and fabricated. The display face component required exporting a DXF of the full face to laser cut an acrylic display that fits the casing precisely. The original display part face was too small because it was filleted, so the edges of the aging clock body were traced and exported for accurate laser cutting.
Laser Cutting Process 1: Initial laser cutting of acrylic display component
Laser Cutting Process 2: Continued laser cutting operation for display face
Acrylic Display Fit: Laser-cut acrylic display component precisely fitted into the casing, demonstrating successful integration of 2D subtractive and 3D additive manufacturing components.
2.2 Electrical Integration Methods in Spiral Development
Electrical design integration combines multiple subsystems into unified board designs, with progressive upgrades incorporating TFT displays for enhanced visual feedback. The integration follows a spiral development approach, starting with base designs and iteratively adding features like TFT displays as design constraints are validated.
Board Design Evolution
Initial Board Design: First integrated board design showing size constraints relative to casing dimensions
Board in Casing: Revised board design fitted within casing dimensional constraints
Final Integrated Board Design: Complete aging clock board design combining accelerometer/camera functionality with pulse oximeter sensors in a single unified PCB layout optimized for casing fit and component placement.
TFT Display Integration
Both the aging clock watch board and the MirrorAge load cell-speaker board have been upgraded to include TFT displays for enhanced visual feedback. The displays use SPI communication for straightforward integration with the ESP32-S3 XIAO microcontroller.
For future iterations incorporating touchscreen functionality, the ILI9341 TFT with integrated touch controller requires additional pin connections. The touch controller shares the SPI bus with the TFT display and uses a separate chip select pin.
Touchscreen Wiring Diagram: Schematic showing ILI9341 TFT with touch controller connections to ESP32-C3, adapted from Arduino Forum ESP32-C3 and ILI9341. The diagram includes backlight brightness control (transistors Q4, Q5, Q6) which can be simplified to a 100Ω resistor for basic operation.
Touchscreen Pin Mapping (ESP32 XIAO):
Touch Pin
ESP32 XIAO Pin
T_CLK
SCK (GPIO8/D8)
T_CS
GPIO21/D21
T_DIN
MOSI (GPIO10/D10)
T_DO
MISO (GPIO9/D9)
Important Notes:
The TFT reset pin can be pulled to 3V3 via a 10kΩ resistor (not 5V as sometimes shown in diagrams)
The touch controller uses the same SPI bus as the TFT display, requiring a modified XPT2046_Touchscreen library with reduced SPI clock speed
TFT Display Wiring: Pin connection diagram showing SPI interface connections between TFT displays and ESP32-S3 XIAO microcontroller for both watch and MirrorAge boards.
MirrorAge Amplifier Board Design
The MirrorAge amplifier board integrates a real-time audio amplifier with load cell interface and TFT display. The base design includes the amplifier circuit and HX711 load cell interface, with an upgraded version adding the 2.4" ILI9341 TFT display.
Base Amplifier Board: Initial design with real-time amplifier and HX711 load cell interface
Base Board Layout: PCB layout showing component placement for amplifier and load cell interface
TFT Display Component:
1.8" TFT LCD: ST7735 controller, 128×160 pixels. CAD model reference:
GrabCAD ST7735 Model
TFT-Integrated MirrorAge Board: Upgraded PCB design incorporating the 2.4" ILI9341 TFT display alongside the amplifier and load cell interface, enabling visual feedback for grip strength measurements.
Aging Clock Watch Board Design
The aging clock watch board combines pulse oximeter sensors, accelerometer, and camera functionality. The base design uses an OLED display, with an upgraded version incorporating a 1.8" ST7735 TFT display for enhanced visual feedback.
Base Aging Clock Board: Initial design integrating pulse oximeter, accelerometer, and camera with OLED display for wearable watch form factor.
Board Fabrication and Integration
The first version of the aging clock board was milled. The initial board did not fit the casing, requiring either casing adjustment and reprinting, or milling a new miniaturized board with shrunken electronics. Both approaches are being evaluated. The MirrorAge board design has been completed for both base and TFT-integrated versions, ready for milling and testing.
Milled Integrated Board: First version of the integrated aging clock board after PCB milling, showing component placement and routing
Board Fit Test: Milled board nearly fitting in casing, demonstrating the need for dimensional optimization
Board Deflection Fixing: Process of addressing board deflection and mechanical fit issues during integration testing, demonstrating iterative refinement of the electrical-mechanical interface.
Day 3: Fabrication Integration
Comprehensive fabrication integration work combining 2D laser cutting, 3D printing, and PCB milling to create fully integrated subsystems ready for assembly and testing.
2.1 2D Fabrication: Laser Cutting and Vinyl Cutting
The laser-cut acrylic display component was updated in Day 2 and successfully integrated into the watch assembly. The acrylic display provides a clear protective face for the aging clock watch, precisely fitted to the casing dimensions.
The integrated watch assembly demonstrates successful integration of 2D subtractive manufacturing with 3D printed components, creating a cohesive mechanical structure for the wearable subsystem.
2.2 3D Printing: Rigid and Flexible Components
All 3D printed components were fabricated using both rigid and flexible materials. The bands were printed using TPU (Thermoplastic Polyurethane) for flexibility, while rigid components used standard PLA/PETG materials. Additional print details and configuration requirements are documented in Day 2.
The case should also be printed from TPU to improve interlock part fit. The spring-loaded interlock mechanism enables secure band closure while maintaining flexibility for comfortable wear.
TPU Band Print 1: Flexible wearable band component printed using TPU material for comfort and durability
TPU Band Print 2: Flexible band component demonstrating material properties and print quality
Band Closure: Interlock mechanism enabling secure band closure for wearable integration
Rigid Dock: 3D printed dock component for secure board mounting and electrical connection
Assembled Rigid Dock: Complete dock assembly showing board integration and mechanical mounting
Spring-Loaded Interlock: Detailed view of the interlock mechanism enabling secure yet flexible band closure
Spring-Loaded Interlock Operation: Demonstration of the interlock mechanism in action, showing secure closure and release functionality for the wearable band system.
2.3 Milling: Single and Double-Sided Boards
Aging Clock Watch Board
The aging clock watch board was successfully milled. The base design with OLED display worked correctly, and the design has been upgraded to include a TFT display. The new TFT-integrated design will be milled and tested alongside the base OLED version to validate both display options.
Milling Process 1: Initial milling operation for aging clock watch board
Tool Probing: Z-axis calibration and tool location setup for precise milling depth control
Milling Process 2: Continued milling operation showing tool path execution
Milling Process 3: Final milling passes completing board fabrication
Completed Milling: Finished aging clock board after successful milling operation
Vacuuming Debris: Post-milling cleanup process removing copper and substrate debris
Board Removal: Completed aging clock watch board removed from milling machine, ready for component soldering and testing.
MirrorAge Amplifier Board
The base MirrorAge amplifier board milling initially failed due to polygon pour isolation settings. The default isolation distance was set to 0 mil, which caused routing issues. After changing the back-side polygon pour isolation to 32 mil, the milling operation succeeded. When the shop closed, the design was upgraded to include a TFT screen. Both the base design and TFT-integrated versions will be milled together and tested.
Milling Process 1: Initial MirrorAge board milling operation
Milling Process 2: Continued milling showing tool path execution
Failed Milling: Initial milling failure caused by polygon pour isolation set to 0 mil
Failed Milling Video: Demonstration of milling failure due to incorrect isolation settings
Second-Side Fixturing: Board secured for double-sided milling operation
Second-Side Milling: Back-side milling operation for double-sided board
Back-Side Milling: Completing double-sided board fabrication
Fixed Isolation Setting: Polygon pour isolation corrected to 32 mil for proper routing
Successful Milling with Fixed Settings: MirrorAge board milling operation completing successfully after correcting polygon pour isolation to 32 mil, demonstrating the importance of proper PCB design rule configuration.
2.4 Integrating Fabrication
Physical integration of fabricated components demonstrates successful coordination between mechanical and electrical subsystems. The watch board fits within the watch case, and the acrylic display integrates properly. Additional work remains for drilling mounting holes for electronics and routing power connections.
Aging Clock Integration: Watch board and case integration showing proper dimensional fit
Integrated Watch Board: Complete watch board assembly within case, demonstrating successful mechanical integration
Assembled Bands: Complete band assembly with clip mechanism for secure attachment
Interlock Mechanism: Spring-loaded interlock providing secure yet flexible band closure
Interlock Operation: Demonstration of spring-loaded interlock mechanism enabling secure band closure and release for comfortable wearable integration.
TFT Display Upgrades
Both board designs have been upgraded to include TFT displays, and integration testing confirms proper fit. The TFT watch board fits correctly with the TFT display, and both the base and TFT-integrated MirrorAge load cell-speaker boards fit within the gripper enclosure. Additional work is needed for drilling mounting holes and adding hooks for load cell wire routing to the HX711 mounted on the board, as well as routing power connections.
TFT MirrorAge Schematic: Electrical schematic showing TFT display integration with amplifier and load cell interface
Integrated Demo System: Complete system integration showing all subsystems in unified demonstration platform
Day 4: Subsystem Integration
Comprehensive subsystem integration work combining 2D fabrication, 3D printing, PCB milling, and molding/casting to complete all physical components for final assembly and testing.
2.0 Final Electrical Design Upgrades
With the milling machine unavailable, the time was used to upgrade board designs, requiring component rotations and layout optimizations to ensure all components fit properly. As Quentin noted, "you have to get used to rotating it in your head"—a valuable skill for PCB design where spatial reasoning is essential for component placement and routing.
"you have to get used to rotating it in your head" — Quentin
MirrorAge TFT Board Upgrades (v13)
The MirrorAge TFT board design was upgraded to version 13, with component rotations and layout optimizations to improve fit and routing efficiency.
MirrorAge TFT Front v13: Upgraded front-side layout with optimized component placement and routing
MirrorAge TFT Back v13: Upgraded back-side routing with improved trace layout and component positioning
Aging Clock TFT Board Upgrades (v16)
The aging clock TFT board design was upgraded to version 16, incorporating component rotations and layout refinements to ensure proper fit within the watch casing constraints.
Aging Clock TFT Front v16: Upgraded front-side design with rotated components for optimal fit
Aging Clock TFT Back v16: Upgraded back-side routing with improved component placement
2.6 I²C Bring-Up and Future Electrical Robustness
Subsystem integration also focused on making the shared I²C bus predictable and debuggable. During flashing, an intermittent serial exception from esptool indicated that the USB device was reporting readiness but returning no data—a classic symptom of a loose cable, port contention, or transient power issue rather than a firmware bug. After power-cycling the board, checking that only one serial monitor was attached, and reseating the USB cable, flashing succeeded reliably.
With stable flashing restored, an I²C scanner sketch confirmed that all devices were present on the bus: the MAX30102 pulse oximeter at address 0x57, the MPU6050 accelerometer at 0x68, and the OLED display at 0x3C once it was wired in. Multiple scans over time reproduced the same addresses, validating bus integrity and confirming that the SDA/SCL routing and pull-up strategy were correct after earlier trace and enclosure fit issues.
Key practices for future spirals:
Keep I²C traces short, avoid sharp mechanical pinch points near the enclosure, and leave clearance for solder thickness to prevent pads from lifting under pressure.
Standardize on known-good I²C addresses (MAX30102 0x57, MPU6050 0x68, SSD1306 OLED 0x3C) and document them close to the schematic and firmware.
Use a simple I²C scanner and a dedicated flashing machine to separate bus-debug issues from USB driver or multi-process serial conflicts.
2.1 2D Fabrication: Laser Cutting and Vinyl Cutting
Laser-cut thinner acrylic (1.35mm) was fabricated to improve the fit of the clear display cover for the aging clock subsystem. The thinner material provides better dimensional tolerance and improved integration with the watch casing.
Thin Acrylic Cutting: Laser cutting 1.35mm acrylic sheet for improved display cover fit
Successful Cut: Completed laser-cut acrylic display cover with precise dimensions
Laser Cutting Process: Laser cutting operation for thin acrylic display cover
Final Cut: Completion of laser cutting process for display cover component
2.2 3D Printing: Rigid and Flexible Components
Band clips were printed using TPU (Thermoplastic Polyurethane) material for improved fit and flexibility. The flexible material provides better mechanical compliance and secure attachment to the watch body.
TPU Band Clips: Flexible band clips printed from TPU material for improved fit
Integrated Clips: TPU clips providing secure and flexible band attachment
Fitted Clips: Band clips filed and inserted for optimal fit and secure attachment
Clip Assembly: Complete band clip assembly demonstrating successful integration
2.3 Milling: Single and Double-Sided Boards
The TFT aging clock board design was milled, requiring iterative refinement due to initial design issues. The first mill had traces that were too close together, and the rivets were positioned under the microcontroller, requiring manual fixes with an ultrasonic knife before remilling the corrected board.
First Milling Attempt
The initial milling process revealed design issues that required correction. The board was milled on both front and back sides, with careful tool location and fixturing procedures.
Front-Side Milling: Initial front-side milling operation for aging clock board
Tool Location: Tool location procedure for front-side milling setup
Front Milling Start: Beginning of front-side milling operation
Front Milling Progress: Front-side milling operation in progress
Back-Side Tool Location: Tool location for back-side milling setup
Back Milling Start: Beginning of back-side milling operation
Back Milling Progress: Back-side milling operation continuing
Back Milling Completion: Final stages of back-side milling
Board Unloading: Removing completed board from milling machine
Post-Milling Cleanup: Vacuuming debris after milling operation
Design Issues and Manual Fixes
After milling, inspection revealed traces that were too close together and rivets positioned under the microcontroller. These issues were corrected manually using a two-step cutting process: the ultrasonic knife was used to initiate precise cuts on both ends of each problematic trace, establishing the correct penetration direction. A utility knife was then used to cut a straight line between these initiation points, isolating the upper and lower wiring. The challenge with manual trace cutting lies in controlling the initial penetration with the utility knife—the ultrasonic knife's precision in establishing the cut direction made the subsequent utility knife cut smoother and easier to complete from end to end. After these manual corrections, the board design was updated and remilled with the fixed layout.
PCB Removal: Removing milled board for inspection and testing
First Side: Initial side of milled board showing trace routing
Missing Traces: Traces that were too close together causing milling issues
Trace Detail: Detailed view of trace spacing issues requiring correction
Multiple Trace Issues: Additional locations with trace spacing problems
Double-Sided Board: Complete double-sided board showing front and back
Ultrasonic Knife: Used to initiate precise cuts on both ends of problematic traces, establishing the correct penetration direction for subsequent utility knife cuts. This precision makes the utility knife cut smoother and easier to complete from end to end.
Utility Knife: Used to cut a straight line between the ultrasonic knife initiation points, isolating upper and lower wiring. The challenge lies in controlling the initial penetration, which is why the ultrasonic knife's precise initiation cuts are essential.
Trace Cut 1: First trace modification using ultrasonic knife
Completed Cut 1: First trace cut completed successfully
Trace Cut 2: Second trace modification in progress
Completed Cut 2: Second trace cut completed successfully
Corrected Board Design and Remilling
After manual corrections, the board design was updated to move rivets away from the microcontroller and improve trace spacing. The corrected board was successfully milled with proper trace clearances and component placement.
Corrected Front Side: Updated board design with improved trace spacing
Corrected Back Side: Back side of corrected board showing proper routing
TFT Fit Test: TFT display properly fitting on corrected board design
TFT Alignment: TFT display properly aligned with board connectors
Corrected Front Milling 1: Beginning of corrected board front-side milling
Corrected Front Milling 2: Front-side milling operation continuing
Tool Location: Tool location procedure for corrected board milling
Front Milling Start: Beginning corrected front-side milling operation
Tool Change: Tool change during front-side milling operation
Back Milling Setup: Setup for back-side milling of corrected board
Back Milling Start: Beginning back-side milling of corrected board
Back Milling Progress: Back-side milling operation continuing
Post-Milling Cleanup: Vacuuming debris after corrected board milling
Moved Rivets: Board design with rivets repositioned away from microcontroller
Improved Design: Corrected board showing proper rivet placement and trace routing
Rivet Holes: Detail view of properly positioned rivet holes
MirrorAge TFT Board Milling
The base amplifier board was remilled after fixing polygon pour isolation settings (changed from 0 to 32 mil). The upgraded MirrorAge board with TFT display was also successfully milled, ready for soldering and testing.
MirrorAge TFT Front: Front side of MirrorAge board before TFT display integration
MirrorAge TFT Back: Back side of MirrorAge board before TFT display integration showing routing
Front Milling: Front-side milling of MirrorAge TFT board
Front Milling Progress: Front-side milling operation continuing
Back Milling: Back-side milling of MirrorAge TFT board
Minor Trace Issue: Small trace spacing issue requiring attention
Milled Front Side: Completed front side of MirrorAge TFT board
Fixturing: Double-sided tape used for secure board mounting during milling
Successful Milling: MirrorAge TFT board successfully milled and ready for assembly
Back Side: Back side of successfully milled MirrorAge TFT board
Completed MirrorAge TFT Board: High-quality view of the back side showing proper trace routing and component placement for the TFT-integrated MirrorAge amplifier board.
2.4 Molding and Casting
Starting from Anthony's sketch in the midterm review, 3D-printable open molds were designed to cast watch bands out of MoldStar 30. The process involved printing PLA molds, waxing for release, mixing and pouring the mold material, leveling, curing under a heat lamp, and demolding. The center section of the printed molds required cutting with an ultrasonic knife before pouring to ensure part removability. A backup TPU band was also printed in case of casting failure.
Design Origin: Anthony's midterm review sketch providing the foundation for band mold design
Printed Molds: PLA molds 3D printed for watch band casting
Mold A: First half of the two-part mold system
Mold B: Second half of the two-part mold system
Mold Preparation
The molds required cutting out the center section with an ultrasonic knife before waxing and casting. Wax was melted, painted onto the mold surfaces for release, and thinned as needed for proper coverage.
Mold A Prepared: Mold A after center section removal with ultrasonic knife and wax application
Mold B Prepared: Mold B after center section removal with ultrasonic knife and wax application
Wax Melting: Melting wax for mold release agent application
Wax Melting Process: Continued wax melting for release agent preparation
Wax Application: Painting wax release agent onto mold surfaces
Wax Thinning: Thinning wax for proper coverage and release properties
Waxed Molds Ready: Both molds properly waxed and prepared for MoldStar 30 casting operation.
Mold Mixing and Pouring
MoldStar 30 was mixed according to specifications, poured into the prepared molds, and leveled to ensure proper distribution and surface quality.
Component Mixing: Preparing MoldStar 30 components A and B for mixing
Mixed Material: MoldStar 30 fully mixed and ready for pouring
Mixing Process: Thoroughly mixing MoldStar 30 components
Stirring: Final stirring of mixed mold material
Pouring: Pouring mixed MoldStar 30 into prepared molds
Filled Molds: Molds filled with MoldStar 30 ready for leveling
Leveling: Leveling poured material for even distribution
Leveling Process: Continued leveling to ensure proper surface quality
Leveled Molds: Molds properly leveled and ready for heat lamp curing process.
Curing and Demolding
The filled molds were moved under a heat lamp for curing, then demolded and tested to ensure proper fit between the two band halves.
Heat Lamp Curing: Molds positioned under heat lamp for MoldStar 30 curing
Curing Progress: MoldStar 30 curing under heat lamp
Demolding 1: Beginning the demolding process for cured band
Demolding 2: Continued demolding process
Tab Removal: Removing casting tabs from demolded band
Band Testing: Testing fit between the two cast band halves
2.5 Aging Clock Subsystem Fabrication
The TFT aging clock board was successfully assembled into the watch enclosure, demonstrating successful integration of all fabricated components including the milled PCB, TFT display, and watch casing.
Complete Assembly: TFT aging clock board successfully assembled into the watch enclosure, demonstrating proper fit and integration of all subsystem components including the milled PCB, TFT display, watch casing, and acrylic display cover.
Day 5: Full System Integration
Final integration day focused on closing the watch subsystem as far as mechanically feasible, soldering and verifying all double-sided boards, refining molded bands, and assembling the complete MirrorAge demo with both the aging clock and grip-strength subsystems fully wired and tested.
I attempted to fully close the aging clock watch subsystem using the laser-cut acrylic top plate and printed enclosure. In practice, finite solder height and stacked components meant the acrylic pressed directly on the SDA/SCL traces; under load, the pressure ripped the I²C traces off the board even after successful end-to-end testing. For the final demo, I kept the subsystem open for reliability and prepared a backup pulse oximeter module to rework the board after the full system presentation.
Future electrical spirals will set stricter keep-out zones under fasteners and enclosure pinch points, lower component stack-up height in CAD, and route critical buses away from mechanical interfaces. The current integration still validates the fit envelope and cable-routing strategy, and will be re-closed once replacement boards and sensors are available.
Initial Fit Check: Aging clock board and pulse oximeter aligned inside the enclosure before closing the acrylic face.
Final Mechanical Fit: Tight clearances confirm the CAD was accurate, but highlight the need to account for solder thickness and wiring bends.
Backup Sensor: Spare MAX30102 breakout from Mariam kept to re-populate the watch board after the final demo.
Broken I²C Traces: First failure showing how enclosure pressure delaminated the SDA/SCL pads after repeated testing.
Trace Delamination Detail: Second damaged region reinforcing the need to keep critical buses away from mechanical constraints.
Cable Routing: Final cable paths for power, I²C, and sensor leads kept for future closed-enclosure re-integration.
For future iterations, see the consolidated electrical design and integration notes on the final project fabrication section and the updated Bill of Materials for enclosure and sensor stack-up choices.
2.2 3D Printing: Rigid Clips and Flexible Bands
To mount the bands inside the watch clip, I drilled precise holes and inserted inward-facing bolts that clamp into printed TPU clips. TPU provides just enough flexibility and toughness for this fastening strategy, whereas a similar approach would easily tear a silicone band. In the next spiral, the mechanics of the clip will be redesigned so the silicone band experiences distributed compression instead of point loads from metal hardware.
The integrated system view below shows how the TPU band, watch body, and electronics stack come together around the wrist, and serves as the mechanical reference for a future fully cast silicone band with embedded reinforcement.
Integrated Watch Subsystem: TPU bands fastened into the watch clip with inward bolts, supporting the assembled aging clock electronics while leaving room for future silicone band integration.
2.3 Soldering and Testing Single and Double-Sided Boards
Both the aging clock and MirrorAge boards are double-sided with plated through-rivets. I followed a consistent, compact assembly order: (1) install and flare rivets, (2) solder the microcontroller, (3) place and solder passives, then (4) populate and test input/output devices. The media below document that workflow step by step.
Rivet Installation (Plated Through-Holes)
Place a rivet into each via from the front side of the board.
Flip the board carefully using tweezers so rivets stay seated.
Use the thin flaring tool and light hammer taps to open each rivet.
Follow with the thicker forming tool to fully set the rivet head.
Inspect every connection to confirm clean, symmetric flares with no wobble.
MirrorAge Rivets (Front): Large board variant with through-rivets installed.
MirrorAge Rivets (Back): Back-side confirmation of robust mechanical connections.
Compact MirrorAge Board (Front): Small-format board variant using the same rivet process.
Compact MirrorAge Board (Back): Double-sided connectivity established across all through-holes.
Placing Rivets: Using tweezers to drop rivets into each via before flipping the board.
Placing Rivets (Detail): Close-up sequence confirming consistent seating depth.
Flipping the Board: Using tweezers and slow motion to flip the riveted board without losing alignment.
Flipping (Alternate Angle): Second view confirming stable fixturing during the flip.
Thin Tool Flaring: First hammering pass to open each rivet with the thin mandrel.
Thin Tool Flaring (Detail): Close-up of controlled, low-force taps to avoid pad damage.
Thick Tool Forming: Second hammering pass with the thicker tool to fully seat and form the rivet heads.
Thick Tool Forming (Detail): Ensuring each rivet is fully expanded without deforming the board.
Rivet Quality Check: Visual and mechanical inspection of all rivets before continuing with assembly.
Component Placement and Compact Soldering
After through-connection, I placed the microcontroller and passives as flat as possible to preserve headroom inside the enclosure. Headers were soldered last, from both the top and side, to keep cable strain away from delicate pads.
Aging Clock Placement (Front): Microcontroller, MAX30102, and passives packed tightly while respecting keep-outs.
Aging Clock Placement (Back): Back-side routing and decoupling network tucked between rivets.
MirrorAge Placement (Front): Amplifier, HX711, and connectors arranged around the TFT footprint.
MirrorAge Placement (Back): Back-side passives and routing for clean separation of analog and digital paths.
Compact Double-Sided Soldering: Dense layout executed with controlled solder volume to preserve enclosure clearance.
Header Soldering: Low-profile headers added last to route power, I²C, and display signals.
Flat Soldering: Tacking components flat to the board before fully wicking solder for mechanical robustness.
Soldering Straight Headers: Step-by-step soldering of through-hole headers with even wetting on both sides.
Header Row Completion: Finishing the full header row while maintaining alignment for easy connector insertion.
Sideways Header Soldering: Right-angle headers soldered from the side to keep cable exits low-profile.
Sideways Header Reinforcement: Final pass adding solder fillets for mechanical strength.
Soldering Passives: Placing and soldering resistors, capacitors, and pull-ups around the microcontroller and sensors.
Passives (Detail): Close-up of tip control to avoid tombstoning small components.
Final Passive Sweep: Last inspection and touch-up of the passive network before functional testing.
Taped Microcontroller Soldering Technique
To keep the XIAO footprint perfectly flat over the rivets, I used Kapton tape as a temporary stencil: the tape masked exposed copper around the footprint so I could drag-solder the castellated edges without flooding nearby vias. Once the joints were complete, the tape peeled away cleanly, leaving the board ready for final inspection.
Taped Footprint (Before): Kapton masking applied to protect surrounding copper while soldering the XIAO module.
Taped Footprint (After): Clean pads and well-formed joints once the tape is peeled away.
Cutting the Mask: Trimming Kapton tape to expose only the castellated pads.
Flat Above Rivets: Castellated edges soldered flat over rivets without bridging.
Completed Aging Clock Board: All components soldered and ready for subsystem testing.
Power Routing Detail: Compact power distribution region that simplifies future wiring changes.
Soldered MirrorAge Board (Front): Front-side view with amplifier, connectors, and TFT interface populated.
Soldered MirrorAge Board (Back): Clean back-side routing with no visible shorts or bridges.
Serial Bring-Up: Sensor-by-Sensor Testing
After soldering, I brought each sensor up sequentially to isolate any issues. The accelerometer, pulse oximeter, OLED, and TFT were each verified individually over serial before enabling the full integrated sketch.
Accelerometer Bring-Up: First successful accelerometer readings confirmed on the aging clock board.
Accelerometer Stability: Repeat readings confirm stable I²C and orientation mapping.
Pulse Oximeter Bring-Up: MAX30102 readings verified after soldering and I²C debugging.
OLED Verification: Base OLED display tested before migrating to TFT-only operation.
Display Stack Bring-Up: OLED and TFT displays confirmed working simultaneously during integration testing.
All boards passed short-circuit checks and per-sensor serial validation. Remaining electrical risks are limited to load cell hardware quality and long-term connector strain, which are documented for post-demo spirals.
2.4 Molding and Casting
The cast bands are mechanically promising but still need finishing. The edges require additional trimming and sanding, and one edge showed an incomplete fill due to insufficient waxing of the mold. Compared to the TPU prints, the casting material has better compliance and skin feel, and will be the preferred long-term solution once the fastening geometry is iterated.
For this week, I used the printed TPU bands for reliability, while documenting the cast band behavior as a future spiral that aligns with the existing mold designs and material choices.
Band Integration Context: The current TPU bands provide a working reference geometry for the cast silicone bands that will follow the same routing and attachment points.
2.5 Aging Clock Subsystem Fabrication
The aging clock subsystem was finalized by cutting and aligning the pulse oximeter opening so the sensor makes direct skin contact while the watch is worn. That opening simultaneously sets the board position inside the enclosure, constraining the stack according to the system-integration CAD.
With the TFT watch board, sensors, and acrylic window all integrated, the subsystem mechanically mirrors the final form factor even though the top remains open for this demo to protect the repaired traces.
Skin Contact Opening: Precisely placed cutout ensures the pulse oximeter sits flush against the skin while anchoring the internal PCB stack.
2.6 MirrorAge Subsystem Integration
The grip-strength electronics from Week 12 were mounted on the calibrated working load cell and integrated with the new MirrorAge electronics. Wires from the load cell and amplifier are routed along the structure and strain relieved with a moderate amount of glue to balance robustness with serviceability. The boards sit in their dedicated pockets according to the system-integration CAD, keeping the mechanical and electrical reference frames aligned.
Integrated Grip-Strength Subsystem: Working load cell, amplifier, and electronics mounted and wired, ready to stream grip-force data into the final system.
2.7 Full System Integration and Demo Readiness
With both the aging clock and grip-strength subsystems assembled, I brought the entire MirrorAge demo together on the tensegrity table. The videos below show the system running after final debugging, including sensor readouts and synchronized display behavior across the boards.
Integrated System (Pass 1): First full run after fixing wiring and I²C issues, confirming both subsystems operate together.
Integrated System (Pass 2): Second trial demonstrating stable readings and display updates over time.
Integrated System (Pass 3): Longer run verifying that no intermittent faults appear under repeated use.
Legacy Integrated Run: Earlier integrated test preserved to show progress from initial to final wiring.
Integrated System (Earlier Trial 1): Additional integrated run with a slightly earlier firmware revision.
Integrated System (Earlier Trial 2): View of the system from a different angle showing board placement on the demo table.
Fully Integrated Working System: Final demo-ready configuration with both subsystems powered, calibrated, and running together.
Demo Transport: Final packed configuration for safely transporting the full integrated system to the tensegrity demo table.
Day 6: Final Project Masterpiece
Final presentation demonstration of the complete MirrorAge system, showcasing the integrated aging clock and grip-strength subsystems working together in real-time.
This final presentation video demonstrates the complete MirrorAge system in action, featuring both the aging clock watch subsystem and the grip-strength measurement subsystem operating together. The demo showcases real-time sensor readings, synchronized display updates, and the full integration of mechanical, electrical, and software components developed throughout the semester.
Final Presentation Demo: Complete MirrorAge system demonstration showing integrated aging clock and grip-strength subsystems operating together in real-time.
Watch on YouTube for full resolution.
Note: A compressed local version is also available below for offline viewing. For the highest quality and full resolution, please view the video on YouTube.
Compressed Local Version (24MB): Offline-accessible version of the final presentation demo.
Design Files
Comprehensive table of all design files used in the system integration, organized by category with descriptions and links to their usage locations.
📁 Fusion 360 Files: All Fusion 360 design files are available in the HTMA Fusion team directory under HTMA/2025/EECS/Saleem, organized by the same weeks as the website structure.
Consolidated bill of materials for the integrated MirrorAge system used in this Week 14 system-integration build. This table mirrors the final project
Bill of Materials
and is repeated here so readers can cross-reference parts directly from the integration workflows.
Grip-strength molds, band molds, structural ribs
(Week 9,
Week 14)
Fasteners
M2/M3 hardware, heat-set inserts, misc. screws
Assorted
~$0.10–$0.30 ea.
$20.00 (bundle)
All mechanical assemblies (watch, grip rig, camera mount, demo table)
Estimated Total Project Cost
Electronics ≈ $190 · Mechanical & materials ≈ $130 ·
Total ≈ $320 (excluding lab-provided consumables and reused stock).
For the narrative, project-wide context, see the
final project BOM
and the per-week line items in the weekly documentation (for example the
ReactionAge BOM CSV in Week 2).
Critical Path Analysis
Project management view of the integration schedule, showing task dependencies, critical milestones, and current progress status.
Critical Path Tasks
Phase 1: Design & DocumentationCOMPLETED
CAD model consolidation and system integration design ✓
PCB design: combine OLED/accelerometer with pulse oximeter ✓
Demo table integration design with subsystem placement ✓
PCB design: speaker board with realtime amplifier and TFT (MirrorAge board) ✓
PCB design: TFT-integrated aging clock board ✓
Band mold design ✓
3D printable cases for board mounting ✓
TFT display wiring documentation and integration methods ✓
System schematic documentation (wired and wireless) ✓
Website documentation updates (Day 1, Day 2, Day 3, Day 4) ✓
Physical integration refinements: extra mounting holes, final power-routing harnesses, mirror film application to screen ✓
Phase 3: Integration & ProgrammingCOMPLETED
Board-level firmware integration for aging clock and MirrorAge boards ✓
System wiring and I²C bring-up for integrated demo ✓
WiFi / MQTT network coordination between boards ✓
Server-level code development and data logging pipelines ✓
Phase 4: Testing & DocumentationCOMPLETED
Integrated system testing and validation on tensegrity demo table ✓
System evaluation and consolidated cost documentation (this page) ✓
Last documentation review and polishing ✓
Optional / Presentation ExtrasNICE TO HAVE
One-minute video production (conception, construction, operation)
Final summary slide refresh for demo day
Current Status
✓
Completed:
Subsystem testing and validation, CAD model consolidation, demo table integration design, aging clock PCB design (accelerometer/camera + pulse oximeter), TFT-integrated aging clock board design, MirrorAge board design (base and TFT versions), 3D printing of mechanical components (casing with organic support, dock with brim, TPU bands and clips), laser-cut acrylic display (1.35mm thin version), aging clock board milling (with corrections and remilling), MirrorAge board milling (base and TFT versions), band mold design and casting (MoldStar 30), TFT display wiring documentation with touchscreen integration methods, aging clock subsystem assembly, Day 4 fabrication integration documentation
→
In Progress:
Refining physical integration (extra mounting, mirror film), extending firmware from working demo to networked IC pipeline, and documenting data-integration methods (serial, WiFi, MQTT) for future spirals.
○
Upcoming:
WiFi/MQTT network setup, final IC scoring integration, one-minute video, and last presentation/documentation touches.
Buffer Days (Saturday & Sunday)
Tasks that cannot be completed during scheduled weekdays will be shifted to Saturday and Sunday buffer days. This ensures the critical path remains on schedule while allowing flexibility for unexpected delays or additional refinement work.
Data Integration Methods in Spiral Development
Progressive development approach for integrating sensor data streams from multiple subsystems, starting with simple serial communication and evolving to wireless network-based architectures.
Method 1: Serial Communication (Easiest)
Direct serial communication through USB cable from computer to microcontroller, using PySerial to stream data. This provides the simplest initial integration path for rapid prototyping and debugging.
Implementation:
USB cable connection from computer to ESP32-S3 microcontroller
PySerial library for Python-based data streaming
Arduino Serial functions for microcontroller-side communication
Configure all microcontrollers as WiFi clients that stream data to a flash web server. This enables wireless communication while maintaining a centralized data aggregation point.
Implementation:
All ESP32-S3 boards configured as WiFi clients on the same network
Central web server (initially laptop-hosted) receives data streams
WiFiClient::write() functions for data transmission
Message Queuing Telemetry Transport (MQTT) provides a lightweight, publish-subscribe messaging protocol ideal for IoT device communication. This approach enables decentralized data exchange between all MirrorAge subsystems, allowing each board to publish sensor data and subscribe to relevant topics for coordinated system behavior.
Server Hosting Strategy:
Initial development and testing will use a laptop-hosted MQTT broker. In a later development spiral, the server will be migrated to a dedicated Raspberry Pi Zero or Raspberry Pi 5 for standalone operation and improved system portability. Paho MQTT library has been successfully tested for ESP32-S3 implementation.
Week 14 System Integration Code
The core firmware used during Week 14 for the aging clock watch and grip-strength subsystem is available below as both .ino source files and downloadable .zip archives.
These sketches currently run over simple serial/I²C links and will be extended in future spirals to stream data over WiFi/MQTT to the multimodal IC pipeline. The XIAO boards and TFT displays
also include SD card support for local backup storage once that code path is integrated.
Aging Clock · Base Sketch
aging_clock.ino initializes the MAX30102 pulse oximeter and IMU on the I²C bus, reads heart-rate and motion data, and prints structured serial lines for debugging.
The main loop continuously:
checks for new sensor samples (IR, RED, BPM, acceleration)
updates rolling averages / thresholds for stability
writes comma-separated values to Serial for logging or GUI visualization
Additional sketches (e.g., WiFi/MQTT clients, SD-card logging for the XIAO ESP32S3 and TFT shields) will be integrated in a future spiral once the serial and WiFi baselines are fully stabilized.
Development will progress through these methods in order of complexity, starting with serial communication for rapid prototyping, then moving to WiFi client architecture for wireless operation, and finally implementing MQTT for advanced decentralized communication. Each subsystem board (pulse oximeter, OLED/accelerometer, speaker/amplifier, load cell) will be integrated progressively, enabling:
Incremental complexity management and early validation
Decoupled communication between subsystems
Real-time data streaming from multiple sensors
Scalable architecture for adding new sensor modules
Flexible server deployment (laptop → Raspberry Pi migration path)
Reflections & Learnings
Reflections and key learnings from the final project integration week.
Key Points
System integration only works when mechanical envelopes, electrical robustness, and firmware are designed together and validated in short spirals.
Day-by-day planning and a clearly tracked critical path made it possible to finish fabrication, integration, and documentation on time.
Modular PCB and enclosure design allowed me to remill, resolder, and swap boards (including backup pulse oximeter modules) without restarting the whole system.
Careful documentation of failures—like ripped SDA/SCL traces, noisy load cells, and serial upload errors—directly improved the final wiring, strain relief, and bring-up process.
Collaborators, late-night debugging, and AI-assisted writing were all part of getting from a set of subsystems to a fully integrated, demo-ready MirrorAge system.
Contributions
Acknowledgments for contributions and collaborations during the final project week.
Anthony Pennes — for helping at every step of the way, including patient late-night debugging
sessions and a major final-hour assist at around 2 a.m. that kept the integrated demo on track.
Quentin — for jumping in whenever he had time, suggesting the bolt-based fastening approach
for the bands, and providing steady encouragement throughout the integration week.
Mariam — for offering a replacement pulse oximeter in the final hour of debugging after my
backup was lost and the board broke during integration, with a replacement order already placed and arriving
by Tuesday of this week.
Ethical AI Use
Documentation of AI-assisted tasks and tools used during the final project integration week.
📋 General Guidelines: See General Commands for Cursor on the homepage for standard guidelines and commands used consistently throughout documentation development.
Cursor · Project Plan & Weekly Schedule (Day 0)
Comprehensive Cursor AI assistance for outlining the project plan and weekly schedule, including documentation structure, content organization, systematic updates across all week pages and the final project page, media integration, and summary generation workflows.
Cursor AI assistance for Week 14 Day 1 project integration updates, including design integration documentation and initial system integration planning.
Cursor AI assistance for Week 14 project integration updates, including Day 2 electrical and mechanical integration documentation, data integration methods refinement, and critical path analysis updates.
Cursor · Electrical Integration and Fabrication (Day 3)
Cursor AI assistance for Week 14 Day 3 electrical integration and fabrication documentation, including TFT display wiring documentation, board design updates, fabrication integration methods, and Day 3 content updates.
Cursor · Final Project Documentation and Integration (Day 5)
Cursor AI assistance for final MirrorAge documentation and system integration, including Day 5 full-system integration write-up, Bill of Materials synchronization between Week 14 and the final project page, critical path updates, and code documentation for the aging clock and load-cell subsystems.
ChatGPT assistance for firmware development and debugging of the aging clock and load cell subsystems, including sensor integration, display drivers, and data processing algorithms.
Aging Clock Code Development
ChatGPT assistance for developing the aging clock firmware, including MAX30102 pulse oximeter integration, MPU6050 accelerometer readings, TFT display drivers, and sensor data processing algorithms.
ChatGPT assistance for developing the load cell firmware, including HX711 amplifier integration, calibration routines, force measurement algorithms, and TFT display visualization for grip-strength data.
Final integration week focused on bringing all subsystems together, completing hardware fabrication, firmware integration, and documentation for the MirrorAge system presentation.
The act of bringing something to a conclusion or ending in a decisive manner. The ability to efficiently finish tasks and projects with a goal-oriented mindset.
Wednesday
Morning
Publish system integration plan on website
Update weekly assignment sections on final project page (weeks 10-13)
Link final project design files
Update reflections and learnings
Update picture of prism holder
Add final pictures to Slack canvases
Create schematic between boards (wired and wireless) — updated system diagram on PPT-like page
Start CAD model of system
Place final order
Afternoon & Evening
Design:
Boards: Combine OLED screen/accelerometer with pulse oximeter board in a new board (maybe upgrade to small TFT as minor)
Boards: Speaker board with realtime amplifier and TFT (on the load cell fixed board)
Band: Mold design
Cases: 3D print mountable cases for the boards
Integrate designs into final CAD
Document design
Finish CAD model of system
Thursday
Fabricate
Milling boards
Print mold and cast band
Print cases
Solder
Solder components on milled boards
Connect boards with wired (and wireless connection codes)
Finishing
Mirror on screen (easy way with the film)
Documentation
Document fabrication
Friday
Programming
Board level codes
Server level codes
Documentation
Document codes
Completion
Finish anything else
Saturday
Programming & Testing
Demo integrated system
Test integrated system
Documentation
Document testing and evaluation
Review and complete documentation (list of questions)
Make the video by collaging documentation
Sunday
Fill up any gaps
Prepare demo on tensegrity table
Finalize 1-slide
Work on minors
If done, work on if there's time
Monday Morning
Transport demo on tensegrity table
Fill up any gaps
Work on minors
Specific Tasks to Complete This Week
Major Tasks
CAD model of system
Speaker board with realtime amplifier
Combine screen/accelerometer with pulse oximeter board in a new board
Mold and cast band
Design and fabricate casing (print)
Schematic between boards (wired and wireless) — updated system diagram on PPT-like page
Serial connection between pulse oximeter and tiny blinking heart for BPM (BPM from IR, SpO2 from delta)
Combine multiple boards on the same WiFi (switching tabs is easy way, board hosting the webpage querying and update or Python-based server somewhere where everything posting data, Raspberry Pi)
Put+program everything together according to the above (with WiFi for now)
Summary slide and one-minute video for documentation
Conception
Construction
Operation
Minor Tasks
Program microphone/speaker
Fix reaction time delay code
Program LoRa connection
Fix OLED plus WiFi issue
Upgrade to TFT (SPI is very straightforward, design board with either SPI or OLED connection)
Fix heart engraving to center
Engrave K9 glass mirror if it arrives
RD and IRD isolation slit (maybe wick and then cut)
Do the calibration curve for the load cell
Finish cardboard laser cutter origami big mirror frame
If There's Time
Moving base of mirror
Orders
Raspberry Pi Zero (or server host, do some research)
Presentation
Aim for 2.5 minutes because Neil will ask questions
Generally no slides except for 1 open summary slide (have backup slides in case questions come up!)
Related: See the Development Timeline on the final project page for the overall project schedule.
Day 1: Design Integration
Initial system integration work focused on subsystem validation, CAD model consolidation, and design backbone acquisition for band integration.
Subsystem Validation
Conducted comprehensive testing of all subsystems to ensure proper functionality. Identified and resoldered any defective joints, verifying that each subsystem operates correctly before proceeding with full system integration.
CAD Model Consolidation
Exported CAD models of all PCBs in the final design and imported them into a unified CAD assembly. This consolidated model provides a complete view of the system's mechanical integration and spatial relationships.
Integrated CAD Model: Exploded isometric view of the complete system assembly, including all PCBs (pulse oximeter, OLED/accelerometer, speaker/amplifier), main housing with transparent enclosure, and wearable band components. The model shows the spatial relationships between electronic subsystems and mechanical structures, enabling precise integration planning.
Band Design Backbone
Acquired CAD design files for Apple Watch form factor integration, enabling compatibility with existing band designs and standardized watch components. This provides a proven mechanical foundation for the wearable subsystem.
Resuming the daily schedule tomorrow with parallel work streams prioritized according to the critical path. Tasks that cannot be completed during scheduled days will be shifted to buffer days on Saturday and Sunday to maintain project momentum.
Day 2: Electrical and Mechanical Integration
Physical integration of subsystems into the complete demo table assembly, including mechanical component fabrication and electrical board consolidation.
2.1 Mechanical Integration
Mechanical design integration now includes the complete demo table with precise placement of the MirrorAge handgrip subsystem and the aging clock subsystem. The integrated assembly provides a unified platform for system demonstration and testing.
Complete Demo Table Assembly: Integrated mechanical design showing precise placement of the MirrorAge handgrip subsystem and aging clock subsystem on the demo table. The assembly demonstrates the spatial relationships and mounting configurations for both subsystems within the unified demonstration platform.
3D Additive Manufacturing
All 3D additive mechanical components were printed for rapid iterative development. The fabrication process required specific print settings and support strategies for different components:
Printing Initiation: 3D printer starting the fabrication process for mechanical components
Casing Print: Casing component during 3D printing process
Print Configuration Requirements:
Casing: Required organic support structures for complex overhangs
Dock: Required brim adhesion to prevent warping during printing
Bands: Printed using TPU (Thermoplastic Polyurethane) material for flexibility (will spiral into molding and casting in future iterations)
Organic Support Configuration: Slicer settings showing organic support structures for the casing component
Brim Addition: Dock component with brim added to prevent warping during printing
Casing with Organic Support: Printed casing component showing organic support structures
TPU Bands: Flexible wearable band components printed using TPU material
Print Failures and Iteration
Failed Casing Print: Initial casing print failure requiring support structure adjustments
Failed Dock Print: Dock print failure due to warping, resolved with brim addition
Printing Failures: Documentation of various print failures encountered during iterative development
Printing Progress: Successful components showing iterative improvement in print quality
2D Subtractive Manufacturing
The first 2D subtractive mechanical component was debugged and fabricated. The display face component required exporting a DXF of the full face to laser cut an acrylic display that fits the casing precisely. The original display part face was too small because it was filleted, so the edges of the aging clock body were traced and exported for accurate laser cutting.
Laser Cutting Process 1: Initial laser cutting of acrylic display component
Laser Cutting Process 2: Continued laser cutting operation for display face
Acrylic Display Fit: Laser-cut acrylic display component precisely fitted into the casing, demonstrating successful integration of 2D subtractive and 3D additive manufacturing components.
2.2 Electrical Integration Methods in Spiral Development
Electrical design integration combines multiple subsystems into unified board designs, with progressive upgrades incorporating TFT displays for enhanced visual feedback. The integration follows a spiral development approach, starting with base designs and iteratively adding features like TFT displays as design constraints are validated.
Board Design Evolution
Initial Board Design: First integrated board design showing size constraints relative to casing dimensions
Board in Casing: Revised board design fitted within casing dimensional constraints
Final Integrated Board Design: Complete aging clock board design combining accelerometer/camera functionality with pulse oximeter sensors in a single unified PCB layout optimized for casing fit and component placement.
TFT Display Integration
Both the aging clock watch board and the MirrorAge load cell-speaker board have been upgraded to include TFT displays for enhanced visual feedback. The displays use SPI communication for straightforward integration with the ESP32-S3 XIAO microcontroller.
For future iterations incorporating touchscreen functionality, the ILI9341 TFT with integrated touch controller requires additional pin connections. The touch controller shares the SPI bus with the TFT display and uses a separate chip select pin.
Touchscreen Wiring Diagram: Schematic showing ILI9341 TFT with touch controller connections to ESP32-C3, adapted from Arduino Forum ESP32-C3 and ILI9341. The diagram includes backlight brightness control (transistors Q4, Q5, Q6) which can be simplified to a 100Ω resistor for basic operation.
Touchscreen Pin Mapping (ESP32 XIAO):
Touch Pin
ESP32 XIAO Pin
T_CLK
SCK (GPIO8/D8)
T_CS
GPIO21/D21
T_DIN
MOSI (GPIO10/D10)
T_DO
MISO (GPIO9/D9)
Important Notes:
The TFT reset pin can be pulled to 3V3 via a 10kΩ resistor (not 5V as sometimes shown in diagrams)
The touch controller uses the same SPI bus as the TFT display, requiring a modified XPT2046_Touchscreen library with reduced SPI clock speed
TFT Display Wiring: Pin connection diagram showing SPI interface connections between TFT displays and ESP32-S3 XIAO microcontroller for both watch and MirrorAge boards.
MirrorAge Amplifier Board Design
The MirrorAge amplifier board integrates a real-time audio amplifier with load cell interface and TFT display. The base design includes the amplifier circuit and HX711 load cell interface, with an upgraded version adding the 2.4" ILI9341 TFT display.
Base Amplifier Board: Initial design with real-time amplifier and HX711 load cell interface
Base Board Layout: PCB layout showing component placement for amplifier and load cell interface
TFT Display Component:
1.8" TFT LCD: ST7735 controller, 128×160 pixels. CAD model reference:
GrabCAD ST7735 Model
TFT-Integrated MirrorAge Board: Upgraded PCB design incorporating the 2.4" ILI9341 TFT display alongside the amplifier and load cell interface, enabling visual feedback for grip strength measurements.
Aging Clock Watch Board Design
The aging clock watch board combines pulse oximeter sensors, accelerometer, and camera functionality. The base design uses an OLED display, with an upgraded version incorporating a 1.8" ST7735 TFT display for enhanced visual feedback.
Base Aging Clock Board: Initial design integrating pulse oximeter, accelerometer, and camera with OLED display for wearable watch form factor.
Board Fabrication and Integration
The first version of the aging clock board was milled. The initial board did not fit the casing, requiring either casing adjustment and reprinting, or milling a new miniaturized board with shrunken electronics. Both approaches are being evaluated. The MirrorAge board design has been completed for both base and TFT-integrated versions, ready for milling and testing.
Milled Integrated Board: First version of the integrated aging clock board after PCB milling, showing component placement and routing
Board Fit Test: Milled board nearly fitting in casing, demonstrating the need for dimensional optimization
Board Deflection Fixing: Process of addressing board deflection and mechanical fit issues during integration testing, demonstrating iterative refinement of the electrical-mechanical interface.
Day 3: Fabrication Integration
Comprehensive fabrication integration work combining 2D laser cutting, 3D printing, and PCB milling to create fully integrated subsystems ready for assembly and testing.
2.1 2D Fabrication: Laser Cutting and Vinyl Cutting
The laser-cut acrylic display component was updated in Day 2 and successfully integrated into the watch assembly. The acrylic display provides a clear protective face for the aging clock watch, precisely fitted to the casing dimensions.
The integrated watch assembly demonstrates successful integration of 2D subtractive manufacturing with 3D printed components, creating a cohesive mechanical structure for the wearable subsystem.
2.2 3D Printing: Rigid and Flexible Components
All 3D printed components were fabricated using both rigid and flexible materials. The bands were printed using TPU (Thermoplastic Polyurethane) for flexibility, while rigid components used standard PLA/PETG materials. Additional print details and configuration requirements are documented in Day 2.
The case should also be printed from TPU to improve interlock part fit. The spring-loaded interlock mechanism enables secure band closure while maintaining flexibility for comfortable wear.
TPU Band Print 1: Flexible wearable band component printed using TPU material for comfort and durability
TPU Band Print 2: Flexible band component demonstrating material properties and print quality
Band Closure: Interlock mechanism enabling secure band closure for wearable integration
Rigid Dock: 3D printed dock component for secure board mounting and electrical connection
Assembled Rigid Dock: Complete dock assembly showing board integration and mechanical mounting
Spring-Loaded Interlock: Detailed view of the interlock mechanism enabling secure yet flexible band closure
Spring-Loaded Interlock Operation: Demonstration of the interlock mechanism in action, showing secure closure and release functionality for the wearable band system.
2.3 Milling: Single and Double-Sided Boards
Aging Clock Watch Board
The aging clock watch board was successfully milled. The base design with OLED display worked correctly, and the design has been upgraded to include a TFT display. The new TFT-integrated design will be milled and tested alongside the base OLED version to validate both display options.
Milling Process 1: Initial milling operation for aging clock watch board
Tool Probing: Z-axis calibration and tool location setup for precise milling depth control
Milling Process 2: Continued milling operation showing tool path execution
Milling Process 3: Final milling passes completing board fabrication
Completed Milling: Finished aging clock board after successful milling operation
Vacuuming Debris: Post-milling cleanup process removing copper and substrate debris
Board Removal: Completed aging clock watch board removed from milling machine, ready for component soldering and testing.
MirrorAge Amplifier Board
The base MirrorAge amplifier board milling initially failed due to polygon pour isolation settings. The default isolation distance was set to 0 mil, which caused routing issues. After changing the back-side polygon pour isolation to 32 mil, the milling operation succeeded. When the shop closed, the design was upgraded to include a TFT screen. Both the base design and TFT-integrated versions will be milled together and tested.
Milling Process 1: Initial MirrorAge board milling operation
Milling Process 2: Continued milling showing tool path execution
Failed Milling: Initial milling failure caused by polygon pour isolation set to 0 mil
Failed Milling Video: Demonstration of milling failure due to incorrect isolation settings
Second-Side Fixturing: Board secured for double-sided milling operation
Second-Side Milling: Back-side milling operation for double-sided board
Back-Side Milling: Completing double-sided board fabrication
Fixed Isolation Setting: Polygon pour isolation corrected to 32 mil for proper routing
Successful Milling with Fixed Settings: MirrorAge board milling operation completing successfully after correcting polygon pour isolation to 32 mil, demonstrating the importance of proper PCB design rule configuration.
2.4 Integrating Fabrication
Physical integration of fabricated components demonstrates successful coordination between mechanical and electrical subsystems. The watch board fits within the watch case, and the acrylic display integrates properly. Additional work remains for drilling mounting holes for electronics and routing power connections.
Aging Clock Integration: Watch board and case integration showing proper dimensional fit
Integrated Watch Board: Complete watch board assembly within case, demonstrating successful mechanical integration
Assembled Bands: Complete band assembly with clip mechanism for secure attachment
Interlock Mechanism: Spring-loaded interlock providing secure yet flexible band closure
Interlock Operation: Demonstration of spring-loaded interlock mechanism enabling secure band closure and release for comfortable wearable integration.
TFT Display Upgrades
Both board designs have been upgraded to include TFT displays, and integration testing confirms proper fit. The TFT watch board fits correctly with the TFT display, and both the base and TFT-integrated MirrorAge load cell-speaker boards fit within the gripper enclosure. Additional work is needed for drilling mounting holes and adding hooks for load cell wire routing to the HX711 mounted on the board, as well as routing power connections.
TFT MirrorAge Schematic: Electrical schematic showing TFT display integration with amplifier and load cell interface
Integrated Demo System: Complete system integration showing all subsystems in unified demonstration platform
Day 4: Subsystem Integration
Comprehensive subsystem integration work combining 2D fabrication, 3D printing, PCB milling, and molding/casting to complete all physical components for final assembly and testing.
2.0 Final Electrical Design Upgrades
With the milling machine unavailable, the time was used to upgrade board designs, requiring component rotations and layout optimizations to ensure all components fit properly. As Quentin noted, "you have to get used to rotating it in your head"—a valuable skill for PCB design where spatial reasoning is essential for component placement and routing.
"you have to get used to rotating it in your head" — Quentin
MirrorAge TFT Board Upgrades (v13)
The MirrorAge TFT board design was upgraded to version 13, with component rotations and layout optimizations to improve fit and routing efficiency.
MirrorAge TFT Front v13: Upgraded front-side layout with optimized component placement and routing
MirrorAge TFT Back v13: Upgraded back-side routing with improved trace layout and component positioning
Aging Clock TFT Board Upgrades (v16)
The aging clock TFT board design was upgraded to version 16, incorporating component rotations and layout refinements to ensure proper fit within the watch casing constraints.
Aging Clock TFT Front v16: Upgraded front-side design with rotated components for optimal fit
Aging Clock TFT Back v16: Upgraded back-side routing with improved component placement
2.6 I²C Bring-Up and Future Electrical Robustness
Subsystem integration also focused on making the shared I²C bus predictable and debuggable. During flashing, an intermittent serial exception from esptool indicated that the USB device was reporting readiness but returning no data—a classic symptom of a loose cable, port contention, or transient power issue rather than a firmware bug. After power-cycling the board, checking that only one serial monitor was attached, and reseating the USB cable, flashing succeeded reliably.
With stable flashing restored, an I²C scanner sketch confirmed that all devices were present on the bus: the MAX30102 pulse oximeter at address 0x57, the MPU6050 accelerometer at 0x68, and the OLED display at 0x3C once it was wired in. Multiple scans over time reproduced the same addresses, validating bus integrity and confirming that the SDA/SCL routing and pull-up strategy were correct after earlier trace and enclosure fit issues.
Key practices for future spirals:
Keep I²C traces short, avoid sharp mechanical pinch points near the enclosure, and leave clearance for solder thickness to prevent pads from lifting under pressure.
Standardize on known-good I²C addresses (MAX30102 0x57, MPU6050 0x68, SSD1306 OLED 0x3C) and document them close to the schematic and firmware.
Use a simple I²C scanner and a dedicated flashing machine to separate bus-debug issues from USB driver or multi-process serial conflicts.
2.1 2D Fabrication: Laser Cutting and Vinyl Cutting
Laser-cut thinner acrylic (1.35mm) was fabricated to improve the fit of the clear display cover for the aging clock subsystem. The thinner material provides better dimensional tolerance and improved integration with the watch casing.
Thin Acrylic Cutting: Laser cutting 1.35mm acrylic sheet for improved display cover fit
Successful Cut: Completed laser-cut acrylic display cover with precise dimensions
Laser Cutting Process: Laser cutting operation for thin acrylic display cover
Final Cut: Completion of laser cutting process for display cover component
2.2 3D Printing: Rigid and Flexible Components
Band clips were printed using TPU (Thermoplastic Polyurethane) material for improved fit and flexibility. The flexible material provides better mechanical compliance and secure attachment to the watch body.
TPU Band Clips: Flexible band clips printed from TPU material for improved fit
Integrated Clips: TPU clips providing secure and flexible band attachment
Fitted Clips: Band clips filed and inserted for optimal fit and secure attachment
Clip Assembly: Complete band clip assembly demonstrating successful integration
2.3 Milling: Single and Double-Sided Boards
The TFT aging clock board design was milled, requiring iterative refinement due to initial design issues. The first mill had traces that were too close together, and the rivets were positioned under the microcontroller, requiring manual fixes with an ultrasonic knife before remilling the corrected board.
First Milling Attempt
The initial milling process revealed design issues that required correction. The board was milled on both front and back sides, with careful tool location and fixturing procedures.
Front-Side Milling: Initial front-side milling operation for aging clock board
Tool Location: Tool location procedure for front-side milling setup
Front Milling Start: Beginning of front-side milling operation
Front Milling Progress: Front-side milling operation in progress
Back-Side Tool Location: Tool location for back-side milling setup
Back Milling Start: Beginning of back-side milling operation
Back Milling Progress: Back-side milling operation continuing
Back Milling Completion: Final stages of back-side milling
Board Unloading: Removing completed board from milling machine
Post-Milling Cleanup: Vacuuming debris after milling operation
Design Issues and Manual Fixes
After milling, inspection revealed traces that were too close together and rivets positioned under the microcontroller. These issues were corrected manually using a two-step cutting process: the ultrasonic knife was used to initiate precise cuts on both ends of each problematic trace, establishing the correct penetration direction. A utility knife was then used to cut a straight line between these initiation points, isolating the upper and lower wiring. The challenge with manual trace cutting lies in controlling the initial penetration with the utility knife—the ultrasonic knife's precision in establishing the cut direction made the subsequent utility knife cut smoother and easier to complete from end to end. After these manual corrections, the board design was updated and remilled with the fixed layout.
PCB Removal: Removing milled board for inspection and testing
First Side: Initial side of milled board showing trace routing
Missing Traces: Traces that were too close together causing milling issues
Trace Detail: Detailed view of trace spacing issues requiring correction
Multiple Trace Issues: Additional locations with trace spacing problems
Double-Sided Board: Complete double-sided board showing front and back
Ultrasonic Knife: Used to initiate precise cuts on both ends of problematic traces, establishing the correct penetration direction for subsequent utility knife cuts. This precision makes the utility knife cut smoother and easier to complete from end to end.
Utility Knife: Used to cut a straight line between the ultrasonic knife initiation points, isolating upper and lower wiring. The challenge lies in controlling the initial penetration, which is why the ultrasonic knife's precise initiation cuts are essential.
Trace Cut 1: First trace modification using ultrasonic knife
Completed Cut 1: First trace cut completed successfully
Trace Cut 2: Second trace modification in progress
Completed Cut 2: Second trace cut completed successfully
Corrected Board Design and Remilling
After manual corrections, the board design was updated to move rivets away from the microcontroller and improve trace spacing. The corrected board was successfully milled with proper trace clearances and component placement.
Corrected Front Side: Updated board design with improved trace spacing
Corrected Back Side: Back side of corrected board showing proper routing
TFT Fit Test: TFT display properly fitting on corrected board design
TFT Alignment: TFT display properly aligned with board connectors
Corrected Front Milling 1: Beginning of corrected board front-side milling
Corrected Front Milling 2: Front-side milling operation continuing
Tool Location: Tool location procedure for corrected board milling
Front Milling Start: Beginning corrected front-side milling operation
Tool Change: Tool change during front-side milling operation
Back Milling Setup: Setup for back-side milling of corrected board
Back Milling Start: Beginning back-side milling of corrected board
Back Milling Progress: Back-side milling operation continuing
Post-Milling Cleanup: Vacuuming debris after corrected board milling
Moved Rivets: Board design with rivets repositioned away from microcontroller
Improved Design: Corrected board showing proper rivet placement and trace routing
Rivet Holes: Detail view of properly positioned rivet holes
MirrorAge TFT Board Milling
The base amplifier board was remilled after fixing polygon pour isolation settings (changed from 0 to 32 mil). The upgraded MirrorAge board with TFT display was also successfully milled, ready for soldering and testing.
MirrorAge TFT Front: Front side of MirrorAge board before TFT display integration
MirrorAge TFT Back: Back side of MirrorAge board before TFT display integration showing routing
Front Milling: Front-side milling of MirrorAge TFT board
Front Milling Progress: Front-side milling operation continuing
Back Milling: Back-side milling of MirrorAge TFT board
Minor Trace Issue: Small trace spacing issue requiring attention
Milled Front Side: Completed front side of MirrorAge TFT board
Fixturing: Double-sided tape used for secure board mounting during milling
Successful Milling: MirrorAge TFT board successfully milled and ready for assembly
Back Side: Back side of successfully milled MirrorAge TFT board
Completed MirrorAge TFT Board: High-quality view of the back side showing proper trace routing and component placement for the TFT-integrated MirrorAge amplifier board.
2.4 Molding and Casting
Starting from Anthony's sketch in the midterm review, 3D-printable open molds were designed to cast watch bands out of MoldStar 30. The process involved printing PLA molds, waxing for release, mixing and pouring the mold material, leveling, curing under a heat lamp, and demolding. The center section of the printed molds required cutting with an ultrasonic knife before pouring to ensure part removability. A backup TPU band was also printed in case of casting failure.
Design Origin: Anthony's midterm review sketch providing the foundation for band mold design
Printed Molds: PLA molds 3D printed for watch band casting
Mold A: First half of the two-part mold system
Mold B: Second half of the two-part mold system
Mold Preparation
The molds required cutting out the center section with an ultrasonic knife before waxing and casting. Wax was melted, painted onto the mold surfaces for release, and thinned as needed for proper coverage.
Mold A Prepared: Mold A after center section removal with ultrasonic knife and wax application
Mold B Prepared: Mold B after center section removal with ultrasonic knife and wax application
Wax Melting: Melting wax for mold release agent application
Wax Melting Process: Continued wax melting for release agent preparation
Wax Application: Painting wax release agent onto mold surfaces
Wax Thinning: Thinning wax for proper coverage and release properties
Waxed Molds Ready: Both molds properly waxed and prepared for MoldStar 30 casting operation.
Mold Mixing and Pouring
MoldStar 30 was mixed according to specifications, poured into the prepared molds, and leveled to ensure proper distribution and surface quality.
Component Mixing: Preparing MoldStar 30 components A and B for mixing
Mixed Material: MoldStar 30 fully mixed and ready for pouring
Mixing Process: Thoroughly mixing MoldStar 30 components
Stirring: Final stirring of mixed mold material
Pouring: Pouring mixed MoldStar 30 into prepared molds
Filled Molds: Molds filled with MoldStar 30 ready for leveling
Leveling: Leveling poured material for even distribution
Leveling Process: Continued leveling to ensure proper surface quality
Leveled Molds: Molds properly leveled and ready for heat lamp curing process.
Curing and Demolding
The filled molds were moved under a heat lamp for curing, then demolded and tested to ensure proper fit between the two band halves.
Heat Lamp Curing: Molds positioned under heat lamp for MoldStar 30 curing
Curing Progress: MoldStar 30 curing under heat lamp
Demolding 1: Beginning the demolding process for cured band
Demolding 2: Continued demolding process
Tab Removal: Removing casting tabs from demolded band
Band Testing: Testing fit between the two cast band halves
2.5 Aging Clock Subsystem Fabrication
The TFT aging clock board was successfully assembled into the watch enclosure, demonstrating successful integration of all fabricated components including the milled PCB, TFT display, and watch casing.
Complete Assembly: TFT aging clock board successfully assembled into the watch enclosure, demonstrating proper fit and integration of all subsystem components including the milled PCB, TFT display, watch casing, and acrylic display cover.
Day 5: Full System Integration
Final integration day focused on closing the watch subsystem as far as mechanically feasible, soldering and verifying all double-sided boards, refining molded bands, and assembling the complete MirrorAge demo with both the aging clock and grip-strength subsystems fully wired and tested.
I attempted to fully close the aging clock watch subsystem using the laser-cut acrylic top plate and printed enclosure. In practice, finite solder height and stacked components meant the acrylic pressed directly on the SDA/SCL traces; under load, the pressure ripped the I²C traces off the board even after successful end-to-end testing. For the final demo, I kept the subsystem open for reliability and prepared a backup pulse oximeter module to rework the board after the full system presentation.
Future electrical spirals will set stricter keep-out zones under fasteners and enclosure pinch points, lower component stack-up height in CAD, and route critical buses away from mechanical interfaces. The current integration still validates the fit envelope and cable-routing strategy, and will be re-closed once replacement boards and sensors are available.
Initial Fit Check: Aging clock board and pulse oximeter aligned inside the enclosure before closing the acrylic face.
Final Mechanical Fit: Tight clearances confirm the CAD was accurate, but highlight the need to account for solder thickness and wiring bends.
Backup Sensor: Spare MAX30102 breakout from Mariam kept to re-populate the watch board after the final demo.
Broken I²C Traces: First failure showing how enclosure pressure delaminated the SDA/SCL pads after repeated testing.
Trace Delamination Detail: Second damaged region reinforcing the need to keep critical buses away from mechanical constraints.
Cable Routing: Final cable paths for power, I²C, and sensor leads kept for future closed-enclosure re-integration.
For future iterations, see the consolidated electrical design and integration notes on the final project fabrication section and the updated Bill of Materials for enclosure and sensor stack-up choices.
2.2 3D Printing: Rigid Clips and Flexible Bands
To mount the bands inside the watch clip, I drilled precise holes and inserted inward-facing bolts that clamp into printed TPU clips. TPU provides just enough flexibility and toughness for this fastening strategy, whereas a similar approach would easily tear a silicone band. In the next spiral, the mechanics of the clip will be redesigned so the silicone band experiences distributed compression instead of point loads from metal hardware.
The integrated system view below shows how the TPU band, watch body, and electronics stack come together around the wrist, and serves as the mechanical reference for a future fully cast silicone band with embedded reinforcement.
Integrated Watch Subsystem: TPU bands fastened into the watch clip with inward bolts, supporting the assembled aging clock electronics while leaving room for future silicone band integration.
2.3 Soldering and Testing Single and Double-Sided Boards
Both the aging clock and MirrorAge boards are double-sided with plated through-rivets. I followed a consistent, compact assembly order: (1) install and flare rivets, (2) solder the microcontroller, (3) place and solder passives, then (4) populate and test input/output devices. The media below document that workflow step by step.
Rivet Installation (Plated Through-Holes)
Place a rivet into each via from the front side of the board.
Flip the board carefully using tweezers so rivets stay seated.
Use the thin flaring tool and light hammer taps to open each rivet.
Follow with the thicker forming tool to fully set the rivet head.
Inspect every connection to confirm clean, symmetric flares with no wobble.
MirrorAge Rivets (Front): Large board variant with through-rivets installed.
MirrorAge Rivets (Back): Back-side confirmation of robust mechanical connections.
Compact MirrorAge Board (Front): Small-format board variant using the same rivet process.
Compact MirrorAge Board (Back): Double-sided connectivity established across all through-holes.
Placing Rivets: Using tweezers to drop rivets into each via before flipping the board.
Placing Rivets (Detail): Close-up sequence confirming consistent seating depth.
Flipping the Board: Using tweezers and slow motion to flip the riveted board without losing alignment.
Flipping (Alternate Angle): Second view confirming stable fixturing during the flip.
Thin Tool Flaring: First hammering pass to open each rivet with the thin mandrel.
Thin Tool Flaring (Detail): Close-up of controlled, low-force taps to avoid pad damage.
Thick Tool Forming: Second hammering pass with the thicker tool to fully seat and form the rivet heads.
Thick Tool Forming (Detail): Ensuring each rivet is fully expanded without deforming the board.
Rivet Quality Check: Visual and mechanical inspection of all rivets before continuing with assembly.
Component Placement and Compact Soldering
After through-connection, I placed the microcontroller and passives as flat as possible to preserve headroom inside the enclosure. Headers were soldered last, from both the top and side, to keep cable strain away from delicate pads.
Aging Clock Placement (Front): Microcontroller, MAX30102, and passives packed tightly while respecting keep-outs.
Aging Clock Placement (Back): Back-side routing and decoupling network tucked between rivets.
MirrorAge Placement (Front): Amplifier, HX711, and connectors arranged around the TFT footprint.
MirrorAge Placement (Back): Back-side passives and routing for clean separation of analog and digital paths.
Compact Double-Sided Soldering: Dense layout executed with controlled solder volume to preserve enclosure clearance.
Header Soldering: Low-profile headers added last to route power, I²C, and display signals.
Flat Soldering: Tacking components flat to the board before fully wicking solder for mechanical robustness.
Soldering Straight Headers: Step-by-step soldering of through-hole headers with even wetting on both sides.
Header Row Completion: Finishing the full header row while maintaining alignment for easy connector insertion.
Sideways Header Soldering: Right-angle headers soldered from the side to keep cable exits low-profile.
Sideways Header Reinforcement: Final pass adding solder fillets for mechanical strength.
Soldering Passives: Placing and soldering resistors, capacitors, and pull-ups around the microcontroller and sensors.
Passives (Detail): Close-up of tip control to avoid tombstoning small components.
Final Passive Sweep: Last inspection and touch-up of the passive network before functional testing.
Taped Microcontroller Soldering Technique
To keep the XIAO footprint perfectly flat over the rivets, I used Kapton tape as a temporary stencil: the tape masked exposed copper around the footprint so I could drag-solder the castellated edges without flooding nearby vias. Once the joints were complete, the tape peeled away cleanly, leaving the board ready for final inspection.
Taped Footprint (Before): Kapton masking applied to protect surrounding copper while soldering the XIAO module.
Taped Footprint (After): Clean pads and well-formed joints once the tape is peeled away.
Cutting the Mask: Trimming Kapton tape to expose only the castellated pads.
Flat Above Rivets: Castellated edges soldered flat over rivets without bridging.
Completed Aging Clock Board: All components soldered and ready for subsystem testing.
Power Routing Detail: Compact power distribution region that simplifies future wiring changes.
Soldered MirrorAge Board (Front): Front-side view with amplifier, connectors, and TFT interface populated.
Soldered MirrorAge Board (Back): Clean back-side routing with no visible shorts or bridges.
Serial Bring-Up: Sensor-by-Sensor Testing
After soldering, I brought each sensor up sequentially to isolate any issues. The accelerometer, pulse oximeter, OLED, and TFT were each verified individually over serial before enabling the full integrated sketch.
Accelerometer Bring-Up: First successful accelerometer readings confirmed on the aging clock board.
Accelerometer Stability: Repeat readings confirm stable I²C and orientation mapping.
Pulse Oximeter Bring-Up: MAX30102 readings verified after soldering and I²C debugging.
OLED Verification: Base OLED display tested before migrating to TFT-only operation.
Display Stack Bring-Up: OLED and TFT displays confirmed working simultaneously during integration testing.
All boards passed short-circuit checks and per-sensor serial validation. Remaining electrical risks are limited to load cell hardware quality and long-term connector strain, which are documented for post-demo spirals.
2.4 Molding and Casting
The cast bands are mechanically promising but still need finishing. The edges require additional trimming and sanding, and one edge showed an incomplete fill due to insufficient waxing of the mold. Compared to the TPU prints, the casting material has better compliance and skin feel, and will be the preferred long-term solution once the fastening geometry is iterated.
For this week, I used the printed TPU bands for reliability, while documenting the cast band behavior as a future spiral that aligns with the existing mold designs and material choices.
Band Integration Context: The current TPU bands provide a working reference geometry for the cast silicone bands that will follow the same routing and attachment points.
2.5 Aging Clock Subsystem Fabrication
The aging clock subsystem was finalized by cutting and aligning the pulse oximeter opening so the sensor makes direct skin contact while the watch is worn. That opening simultaneously sets the board position inside the enclosure, constraining the stack according to the system-integration CAD.
With the TFT watch board, sensors, and acrylic window all integrated, the subsystem mechanically mirrors the final form factor even though the top remains open for this demo to protect the repaired traces.
Skin Contact Opening: Precisely placed cutout ensures the pulse oximeter sits flush against the skin while anchoring the internal PCB stack.
2.6 MirrorAge Subsystem Integration
The grip-strength electronics from Week 12 were mounted on the calibrated working load cell and integrated with the new MirrorAge electronics. Wires from the load cell and amplifier are routed along the structure and strain relieved with a moderate amount of glue to balance robustness with serviceability. The boards sit in their dedicated pockets according to the system-integration CAD, keeping the mechanical and electrical reference frames aligned.
Integrated Grip-Strength Subsystem: Working load cell, amplifier, and electronics mounted and wired, ready to stream grip-force data into the final system.
2.7 Full System Integration and Demo Readiness
With both the aging clock and grip-strength subsystems assembled, I brought the entire MirrorAge demo together on the tensegrity table. The videos below show the system running after final debugging, including sensor readouts and synchronized display behavior across the boards.
Integrated System (Pass 1): First full run after fixing wiring and I²C issues, confirming both subsystems operate together.
Integrated System (Pass 2): Second trial demonstrating stable readings and display updates over time.
Integrated System (Pass 3): Longer run verifying that no intermittent faults appear under repeated use.
Legacy Integrated Run: Earlier integrated test preserved to show progress from initial to final wiring.
Integrated System (Earlier Trial 1): Additional integrated run with a slightly earlier firmware revision.
Integrated System (Earlier Trial 2): View of the system from a different angle showing board placement on the demo table.
Fully Integrated Working System: Final demo-ready configuration with both subsystems powered, calibrated, and running together.
Demo Transport: Final packed configuration for safely transporting the full integrated system to the tensegrity demo table.
Day 6: Final Project Masterpiece
Final presentation demonstration of the complete MirrorAge system, showcasing the integrated aging clock and grip-strength subsystems working together in real-time. View on final project page →
This final presentation video demonstrates the complete MirrorAge system in action, featuring both the aging clock watch subsystem and the grip-strength measurement subsystem operating together. The demo showcases real-time sensor readings, synchronized display updates, and the full integration of mechanical, electrical, and software components developed throughout the semester.
Final Presentation Demo: Complete MirrorAge system demonstration showing integrated aging clock and grip-strength subsystems operating together in real-time.
Watch on YouTube for full resolution.
Note: A compressed local version is also available below for offline viewing. For the highest quality and full resolution, please view the video on YouTube.
Compressed Local Version (24MB): Offline-accessible version of the final presentation demo.
Design Files
Comprehensive table of all design files used in the system integration, organized by category with descriptions and links to their usage locations.
📁 Fusion 360 Files: All Fusion 360 design files are available in the HTMA Fusion team directory under HTMA/2025/EECS/Saleem, organized by the same weeks as the website structure.
Consolidated bill of materials for the integrated MirrorAge system used in this Week 14 system-integration build. This table mirrors the final project
Bill of Materials
and is repeated here so readers can cross-reference parts directly from the integration workflows.
Grip-strength molds, band molds, structural ribs
(Week 9,
Week 14)
Fasteners
M2/M3 hardware, heat-set inserts, misc. screws
Assorted
~$0.10–$0.30 ea.
$20.00 (bundle)
All mechanical assemblies (watch, grip rig, camera mount, demo table)
Estimated Total Project Cost
Electronics ≈ $190 · Mechanical & materials ≈ $130 ·
Total ≈ $320 (excluding lab-provided consumables and reused stock).
For the narrative, project-wide context, see the
final project BOM
and the per-week line items in the weekly documentation (for example the
ReactionAge BOM CSV in Week 2).
Critical Path Analysis
Project management view of the integration schedule, showing task dependencies, critical milestones, and current progress status.
Critical Path Tasks
Phase 1: Design & DocumentationCOMPLETED
CAD model consolidation and system integration design ✓
PCB design: combine OLED/accelerometer with pulse oximeter ✓
Demo table integration design with subsystem placement ✓
PCB design: speaker board with realtime amplifier and TFT (MirrorAge board) ✓
PCB design: TFT-integrated aging clock board ✓
Band mold design ✓
3D printable cases for board mounting ✓
TFT display wiring documentation and integration methods ✓
System schematic documentation (wired and wireless) ✓
Website documentation updates (Day 1, Day 2, Day 3, Day 4) ✓
Physical integration refinements: extra mounting holes, final power-routing harnesses, mirror film application to screen ✓
Phase 3: Integration & ProgrammingCOMPLETED
Board-level firmware integration for aging clock and MirrorAge boards ✓
System wiring and I²C bring-up for integrated demo ✓
WiFi / MQTT network coordination between boards ✓
Server-level code development and data logging pipelines ✓
Phase 4: Testing & DocumentationCOMPLETED
Integrated system testing and validation on tensegrity demo table ✓
System evaluation and consolidated cost documentation (this page) ✓
Last documentation review and polishing ✓
Optional / Presentation ExtrasNICE TO HAVE
One-minute video production (conception, construction, operation)
Final summary slide refresh for demo day
Current Status
✓
Completed:
Subsystem testing and validation, CAD model consolidation, demo table integration design, aging clock PCB design (accelerometer/camera + pulse oximeter), TFT-integrated aging clock board design, MirrorAge board design (base and TFT versions), 3D printing of mechanical components (casing with organic support, dock with brim, TPU bands and clips), laser-cut acrylic display (1.35mm thin version), aging clock board milling (with corrections and remilling), MirrorAge board milling (base and TFT versions), band mold design and casting (MoldStar 30), TFT display wiring documentation with touchscreen integration methods, aging clock subsystem assembly, Day 4 fabrication integration documentation
→
In Progress:
Refining physical integration (extra mounting, mirror film), extending firmware from working demo to networked IC pipeline, and documenting data-integration methods (serial, WiFi, MQTT) for future spirals.
○
Upcoming:
WiFi/MQTT network setup, final IC scoring integration, one-minute video, and last presentation/documentation touches.
Buffer Days (Saturday & Sunday)
Tasks that cannot be completed during scheduled weekdays will be shifted to Saturday and Sunday buffer days. This ensures the critical path remains on schedule while allowing flexibility for unexpected delays or additional refinement work.
Data Integration Methods in Spiral Development
Progressive development approach for integrating sensor data streams from multiple subsystems, starting with simple serial communication and evolving to wireless network-based architectures.
Method 1: Serial Communication (Easiest)
Direct serial communication through USB cable from computer to microcontroller, using PySerial to stream data. This provides the simplest initial integration path for rapid prototyping and debugging.
Implementation:
USB cable connection from computer to ESP32-S3 microcontroller
PySerial library for Python-based data streaming
Arduino Serial functions for microcontroller-side communication
Configure all microcontrollers as WiFi clients that stream data to a flash web server. This enables wireless communication while maintaining a centralized data aggregation point.
Implementation:
All ESP32-S3 boards configured as WiFi clients on the same network
Central web server (initially laptop-hosted) receives data streams
WiFiClient::write() functions for data transmission
Message Queuing Telemetry Transport (MQTT) provides a lightweight, publish-subscribe messaging protocol ideal for IoT device communication. This approach enables decentralized data exchange between all MirrorAge subsystems, allowing each board to publish sensor data and subscribe to relevant topics for coordinated system behavior.
Server Hosting Strategy:
Initial development and testing will use a laptop-hosted MQTT broker. In a later development spiral, the server will be migrated to a dedicated Raspberry Pi Zero or Raspberry Pi 5 for standalone operation and improved system portability. Paho MQTT library has been successfully tested for ESP32-S3 implementation.
Week 14 System Integration Code
The core firmware used during Week 14 for the aging clock watch and grip-strength subsystem is available below as both .ino source files and downloadable .zip archives.
These sketches currently run over simple serial/I²C links and will be extended in future spirals to stream data over WiFi/MQTT to the multimodal IC pipeline. The XIAO boards and TFT displays
also include SD card support for local backup storage once that code path is integrated.
Aging Clock · Base Sketch
aging_clock.ino initializes the MAX30102 pulse oximeter and IMU on the I²C bus, reads heart-rate and motion data, and prints structured serial lines for debugging.
The main loop continuously:
checks for new sensor samples (IR, RED, BPM, acceleration)
updates rolling averages / thresholds for stability
writes comma-separated values to Serial for logging or GUI visualization
Additional sketches (e.g., WiFi/MQTT clients, SD-card logging for the XIAO ESP32S3 and TFT shields) will be integrated in a future spiral once the serial and WiFi baselines are fully stabilized.
Development will progress through these methods in order of complexity, starting with serial communication for rapid prototyping, then moving to WiFi client architecture for wireless operation, and finally implementing MQTT for advanced decentralized communication. Each subsystem board (pulse oximeter, OLED/accelerometer, speaker/amplifier, load cell) will be integrated progressively, enabling:
Incremental complexity management and early validation
Decoupled communication between subsystems
Real-time data streaming from multiple sensors
Scalable architecture for adding new sensor modules
Flexible server deployment (laptop → Raspberry Pi migration path)
Reflections & Learnings
Reflections and key learnings from the final project integration week.
Key Points
System integration only works when mechanical envelopes, electrical robustness, and firmware are designed together and validated in short spirals.
Day-by-day planning and a clearly tracked critical path made it possible to finish fabrication, integration, and documentation on time.
Modular PCB and enclosure design allowed me to remill, resolder, and swap boards (including backup pulse oximeter modules) without restarting the whole system.
Careful documentation of failures—like ripped SDA/SCL traces, noisy load cells, and serial upload errors—directly improved the final wiring, strain relief, and bring-up process.
Collaborators, late-night debugging, and AI-assisted writing were all part of getting from a set of subsystems to a fully integrated, demo-ready MirrorAge system.
Contributions
Acknowledgments for contributions and collaborations during the final project week.
Anthony Pennes — for helping at every step of the way, including patient late-night debugging
sessions and a major final-hour assist at around 2 a.m. that kept the integrated demo on track.
Quentin — for jumping in whenever he had time, suggesting the bolt-based fastening approach
for the bands, and providing steady encouragement throughout the integration week.
Mariam — for offering a replacement pulse oximeter in the final hour of debugging after my
backup was lost and the board broke during integration, with a replacement order already placed and arriving
by Tuesday of this week.
Ethical AI Use
Documentation of AI-assisted tasks and tools used during the final project integration week.
📋 General Guidelines: See General Commands for Cursor on the homepage for standard guidelines and commands used consistently throughout documentation development.
Cursor · Project Plan & Weekly Schedule (Day 0)
Comprehensive Cursor AI assistance for outlining the project plan and weekly schedule, including documentation structure, content organization, systematic updates across all week pages and the final project page, media integration, and summary generation workflows.
Cursor AI assistance for Week 14 Day 1 project integration updates, including design integration documentation and initial system integration planning.
Cursor AI assistance for Week 14 project integration updates, including Day 2 electrical and mechanical integration documentation, data integration methods refinement, and critical path analysis updates.
Cursor · Electrical Integration and Fabrication (Day 3)
Cursor AI assistance for Week 14 Day 3 electrical integration and fabrication documentation, including TFT display wiring documentation, board design updates, fabrication integration methods, and Day 3 content updates.
Cursor · Final Project Documentation and Integration (Day 5)
Cursor AI assistance for final MirrorAge documentation and system integration, including Day 5 full-system integration write-up, Bill of Materials synchronization between Week 14 and the final project page, critical path updates, and code documentation for the aging clock and load-cell subsystems.
ChatGPT assistance for firmware development and debugging of the aging clock and load cell subsystems, including sensor integration, display drivers, and data processing algorithms.
Aging Clock Code Development
ChatGPT assistance for developing the aging clock firmware, including MAX30102 pulse oximeter integration, MPU6050 accelerometer readings, TFT display drivers, and sensor data processing algorithms.
ChatGPT assistance for developing the load cell firmware, including HX711 amplifier integration, calibration routines, force measurement algorithms, and TFT display visualization for grip-strength data.
```
All tasks completed. Summary:
## Completed tasks
1. **System Integration Section** — Added to `finalproject.html` with summaries for each day (Day 1–6), including links to detailed sections in `week14.html`.
2. **Table of Contents** — Added "System Integration" and "Final Project Masterpiece" entries.
3. **Final Project Masterpiece Section** — Added with:
- Embedded video from `week14/highlights/finalpresentationdemo.mp4`
- YouTube link: https://youtu.be/4mIPPKHv3AU?si=bMCngMzhDp3IjFNQ
- Brief description of the demo
4. **Highlights Section** — Added system integration highlights from `week14.html` as three rows:
- Row 1: System Integration Design, Aging Clock TFT Board, MirrorAge TFT Board
- Row 2: Soldered MirrorAge Board, Enclosure Integration, Demo Transport
- Row 3: Integrated Aging Clock, Working Integrated System, Final Presentation Demo
- All items link to their respective sections
5. **Links in week14.html** — Updated the highlights section and Day 6 section to link to the final project masterpiece section.
All content is linked and organized. The system integration section includes summaries for each day with links to detailed sections in `week14.html`, and the final project masterpiece section is accessible from both pages.
Note: I used `finalpresentationdemo.mp4` since that file exists in the highlights folder. If you prefer a different file, let me know.
---
**User**
add key pictures and videos from week14.html in the summary in each section
---
**Cursor**
Adding key images and videos from week14.html to each day's summary in the system integration section. Reviewing each day's content to identify the most relevant media.
Checking Day 3 content, then updating each day's summary with key images and videos:
Updating each day's summary with key images and videos:
```html
Final Project · HTMAA 2025 · Saleem A. Al Dajani
Interactive selfie capture system with touch controls and real-time display
Vision Board
Conceptual visualization of the multimodal intrinsic capacity assessment system integrating grip strength, voice analysis, facial recognition, video motion capture, reaction time measurement, and wearable accelerometer data.
Intrinsic Capacity (IC) Coverage by Digital Biomarkers
Domain
Grip
Voice
Face
Video
Reaction Time
Wearable
Locomotor
✅
🔸
🔸
✅
🔸
✅
Cognition
❌
✅
🔸
🔸
✅
🔸
Vitality
✅
✅
✅
✅
🔸
✅
Sensory
❌
✅
✅
✅
✅
🔸
Psychological
❌
✅
✅
✅
🔸
✅
✅ Strong coverage |
🔸 Partial/indirect |
❌ Not covered |
View full table →
Multimodal IC Pipeline
Inputs: Grip Strength, Voice, Face, Video, Reaction Time, Wearable Accelerometer
Development Approach: Following the spiral model methodology, this final project will iterate through multiple development cycles, each building upon previous work while addressing new requirements and risks.
This snapshot covers the subsystems and documentation that will be shown during the midterm review. Links jump directly to the supporting sections with detailed evidence.
Featured Subsystems
Camera subsystem — Edge inference demos and selfie capture loop.
Instructor meeting hold — Thursday, Nov 12 at 10:00 AM ET reserved via the shared HTMAA midterm review sheet.
Execution Schedule (Timeline Snapshot)
Condensed from the Week 8–13 development timeline: each sprint builds toward final integration, mirroring the gantt chart below.
Week 8 · Output Devices: figuring out wiring for real-time display states.
Week 9 · Molding & Casting: learn how to cast custom housings and refine structural components.
Week 10 · Mechanical Design: figure out ergonomic enclosure and calibration fixtures.
Week 11 · Networking: program BLE/Wi-Fi telemetry and wearable data fusion.
Week 12 · Interface/App: create mobile UI, cloud bridge, and IC scoring pipeline.
Week 13 · Final Integration: run validation passes, document results, and prep deployment.
Instructor Review Logistics
Calendar hold sent for Thursday, Nov 12 at 10:00 AM ET (38-501 conference room) per the shared HTMAA scheduling sheet. Agenda covers subsystem demos, weekly documentation spot checks (Weeks 0–9), and next-sprint alignment. Meeting slot referenced in the midterm review schedule; awaiting final confirmation via class Slack.
System Architecture
Updated block diagram highlighting the multimodal sensing stack (grip, voice, face, motion, wearables), on-device inference layers, and real-time feedback channels that feed the intrinsic capacity score.
Development Timeline
Timeline aligns subsystem sprints with HTMAA milestones: output devices (Week 8), molding and casting (Week 9), mechanical design (Week 10), networking and communications (Week 11), app programming (Week 12), and final integration (Week 13).
Remaining Tasks (Snapshot)
Weeks 0–9 locked in the core subsystems—documentation workflow, cutting and molding for the housing, embedded prototypes for reaction timing, SenseCraft camera inference, and early grip/voice rigs. The checklist below captures what still needs to happen to converge on the integrated MirrorAge system.
Hardware Integration
Consolidate grip, voice, camera, reaction-time, and wearable sensor harnesses into the MirrorAge enclosure.
Finish molding/casting iterations for the ergonomic housing and align mounting features for PCBs and haptics.
Firmware & Edge AI
Stabilize onboard inference for SenseCraft vision models and voice-age pipelines on the XIAO ESP32S3.
Calibrate grip-force and reaction-time firmware for repeatable sampling; close the loop to haptic/display feedback.
Networking & Data Fusion
Bring up BLE/Wi-Fi data paths for wearable accelerometer streaming and cloud logging of intrinsic capacity scores.
Implement the fusion layer that combines per-domain scores into an overall IC metric with on-device storage.
Interface & UX
Finish mobile/web dashboard mockups for user onboarding, data review, and device calibration workflows.
Finalize real-time mirror feedback cues (display states, haptics, lighting) tied to sensor status and IC outcomes.
Validation & Documentation
Run end-to-end system tests (sensor capture → fusion → feedback) and document calibration procedures.
Record the one-minute video, finalize final presentation assets, and polish the bill of materials for review.
Week 14 System Integration Plan
Detailed day-by-day schedule for final system integration, covering design, fabrication, programming, testing, and documentation. This plan outlines the path to completing the MirrorAge system integration and preparing for final presentation. View on Week 14 page →
The act of bringing something to a conclusion or ending in a decisive manner. The ability to efficiently finish tasks and projects with a goal-oriented mindset.
Wednesday
Morning
Publish system integration plan on website
Update weekly assignment sections on final project page (weeks 10-13)
Link final project design files
Update reflections and learnings
Update picture of prism holder
Add final pictures to Slack canvases
Create schematic between boards (wired and wireless) — updated system diagram on PPT-like page
Start CAD model of system
Place final order
Afternoon & Evening
Design:
Boards: Combine OLED screen/accelerometer with pulse oximeter board in a new board (maybe upgrade to small TFT as minor)
Boards: Speaker board with realtime amplifier and TFT (on the load cell fixed board)
Band: Mold design
Cases: 3D print mountable cases for the boards
Integrate designs into final CAD
Document design
Finish CAD model of system
Thursday
Fabricate
Milling boards
Print mold and cast band
Print cases
Solder
Solder components on milled boards
Connect boards with wired (and wireless connection codes)
Finishing
Mirror on screen (easy way with the film)
Documentation
Document fabrication
Friday
Programming
Board level codes
Server level codes
Documentation
Document codes
Completion
Finish anything else
Saturday
Programming & Testing
Demo integrated system
Test integrated system
Documentation
Document testing and evaluation
Review and complete documentation (list of questions)
Make the video by collaging documentation
Sunday
Fill up any gaps
Prepare demo on tensegrity table
Finalize 1-slide
Work on minors
If done, work on if there's time
Monday Morning
Transport demo on tensegrity table
Fill up any gaps
Work on minors
Specific Tasks to Complete This Week
Major Tasks
CAD model of system
Speaker board with realtime amplifier
Combine screen/accelerometer with pulse oximeter board in a new board
Mold and cast band
Design and fabricate casing (print)
Schematic between boards (wired and wireless) — updated system diagram on PPT-like page
Serial connection between pulse oximeter and tiny blinking heart for BPM (BPM from IR, SpO2 from delta)
Combine multiple boards on the same WiFi (switching tabs is easy way, board hosting the webpage querying and update or Python-based server somewhere where everything posting data, Raspberry Pi)
Put+program everything together according to the above (with WiFi for now)
MirrorAge is a self-contained edge-AI mirror that captures grip strength, facial imagery, voice, motion, and reaction time to estimate intrinsic capacity in real time.
The platform fuses weekly prototypes—ReactionAge latency tests, 3D printed grip mechanics, SenseCraft camera inference, and molded structural elements—into a multimodal mortality risk profiler.
Subsystems in progress: reaction-time module, SenseCraft FaceTTD inference stack, VoiceAge microphone pipeline, wearable streaming via BLE, and molded structural packaging.
Clinical motivation: translate WHO intrinsic capacity domains into measurable digital biomarkers that flag functional decline earlier than chronological age alone.
Project Goals
Deliver multimodal IC scoring Fuse grip, face, voice, reaction-time, and wearable streams on-device to output an intrinsic capacity score plus domain deltas.
Fabricate modular, serviceable hardware Iterate laser-cut tensegrity mirror shells, 3D printed torsional grips, custom PCBs, and silicone cast fixtures that assemble without bespoke tooling.
Validate against ground truth Benchmark embedded inferences against published datasets (Blomkvist et al. 2017, Fuentealba et al. 2025) and lab-collected pilots to quantify accuracy, latency, and reliability.
Timeline & Milestones
Week 10 · Hardware convergence Integrate SenseCraft FaceTTD camera, ReactionAge latency module, and newly milled PCB into a single ESP32S3 backplane.
Week 12 · Midterm review build Finish molded mirror enclosure, bring up BLE wearable link, and demo live IC score during midterm critique.
Final week · Validation & documentation Execute pilot data collection, refine model weights, and release reproducible fabrication + firmware packages.
Documenting the final project masterpiece that integrates the range of units covered, addressing all required questions.
What does it do?
MirrorAge captures synchronized digital biomarkers—camera frames processed with on-device FaceTTD models, VoiceAge microphone samples, grip strength torque, wearable accelerometry, and ReactionAge latency—to estimate intrinsic capacity and time-to-death acceleration.
A XIAO ESP32S3 Sense orchestrates sensing, performs Edge Impulse inference, and displays a live mortality-risk score on the OLED while logging packets to a Python analytics notebook.
Who's done what beforehand?
The concept builds on WHO intrinsic capacity framing and recent mortality-risk studies: Niccoli & Partridge (2012) establish age as the dominant chronic-disease predictor; Fuentealba et al. (Nature Aging 2025) show blood-based IC clocks outperform chronological models;
Zhavoronkov & Bhullar (2015) and Lancet Healthy Longevity editorials motivate treating functional decline as the actionable signal.
This project translates those findings into an accessible, multimodal measurement mirror that can operate outside hospital labs.
What sources did you use?
Primary references include Nature Aging 2025 intrinsic capacity papers, the PLOS ONE ReactionAge dataset (Blomkvist et al. 2017), Edge Impulse SenseCraft documentation, Smooth‑On Mold Star technical bulletins, RotoMetals alloy certificates, MIT HTMAA recitations, and the open-source GRPR grip-strength meter.
Design inspiration and safety notes were consolidated from Anthony Pennes' HTMA guides and Fab Academy molding tutorials.
What did you design?
• Laser-cut cardboard origami mirror frame and tensegrity-inspired floating mount (Weeks 1 & 6)
• ReactionAge firmware + enclosure with statistical post-processing dashboards (Week 2)
• 3D printed torsional spring grip module tuned for ±40 kg ranges (Week 3)
• KiCad/Fusion carrier PCB for the ESP32S3 Sense with OLED, force, and BLE breakouts (Week 5)
• Edge Impulse deployment pipeline with grayscale dithering overlay and live inference UX (Weeks 7–8)
• CAM toolpaths, silicone molds, and Drystone casts for structural packaging (Week 9)
What materials and components were used?
Seeed XIAO ESP32S3 Sense module with OV2640 camera and PDM mic, SparkFun Qwiic button and force sensors, SSD1306 OLED, wearable IMU node (Bosch BHI260), laser-cut cardboard/birch sheets, PLA+/Onyx filament, Mold Star 30 silicone, Drystone gypsum, Roto281 fusible alloy, and embedded fasteners/heat-set inserts.
Where did they come from?
Electronics from Seeed Studio, SparkFun, Digi-Key, and Adafruit; molding supplies and silicones from Reynolds Advanced Materials; Drystone and Hydro-Stone from USG via the MIT CBA stockroom; fusible alloys from RotoMetals; structural lumber and plywood from MIT's shop inventory; filaments from Prusa Research and Markforged.
How much did they cost?
Current spend: $96.34 for ReactionAge components (Week 2 BOM) + $78.42 for SenseCraft camera stack (XIAO ESP32S3 Sense, OLED, cabling) + $42.10 for molding media (Mold Star 30 quart, Drystone, release agents) = $216.86 to date.
Remaining allocation (~$130) is earmarked for BLE wearable hardware and final enclosure finishes; detailed line items tracked in the Airtable budget and mirrored in each weekly BOM CSV.
What parts and systems were made?
Custom origami mirror frame, 3D printed torsional grip shell, machined floating base, silicone molds and Drystone casts for arrow-inspired structural ribs, bespoke ESP32S3 breakout PCB, laser-cut ReactionAge control panel, and assembled sensor tower linking camera, OLED, and wearable gateway.
What tools and processes were used?
Parametric CAD in Fusion 360, laser cutting (Epilog) for origami tiles, Prusa MK4 FDM printing, Formlabs SLA for detail inserts, ShopBot CNC and Bantam PCB milling, silicone mixing/casting under vacuum, Edge Impulse model training, PlatformIO firmware, and Python/NumPy validation notebooks.
What questions were answered?
• Can consumer-grade sensors reproduce published reaction-time age curves? (Yes—ReactionAge matched Blomkvist et al. regression within 4.6 ms RMSE.)
• Will SenseCraft FaceTTD run locally on ESP32S3 with acceptable latency? (Yes—~310 ms/inference at 30% baseline accuracy, highlighting dataset needs.)
• Does molded packaging improve sensor placement repeatability? (Yes—silicone nests held camera ±0.5 mm, reducing alignment drift seen in cardboard prototypes.)
What worked? What didn't?
✅ Floyd–Steinberg dithering produced clear OLED previews; ✅ ReactionAge firmware maintained ±1 ms jitter; ✅ Molded Drystone ribs stiffened mirror shell without excess weight.
⚠️ FaceTTD accuracy plateaued at 30% due to limited training diversity; ⚠️ VoiceAge requires more MFCC samples to sustain 0.64-year MAE; ⚠️ Grip spring fatigue highlighted need for fiber-reinforced print or machined aluminum insert.
How was it evaluated?
Bench tests compare embedded predictions to published curves and desktop baselines: ReactionAge latency vs. Wii Balance Board golden data; FaceTTD inferencing cross-validated against Edge Impulse cloud classifier; VoiceAge MFCC regression verified through train/holdout splits; mechanical fixtures inspected with feeler gauges and dial indicators for tolerance drift.
What are the implications?
A portable intrinsic capacity mirror supports proactive geriatric screening, telehealth coaching, and longitudinal studies that correlate functional decline with interventions.
By grounding hardware in open-source parts and HTMAA fabrication methods, the system can be replicated across labs and community clinics to accelerate validation of digital aging biomarkers and personalize longevity therapies.
Design
Your project should incorporate 2D and 3D design, multiple additive and subtractive fabrication processes, electronics design and production, embedded microcontroller design, interfacing, and programming, system integration and packaging.
2D Design
2D design work for the multimodal intrinsic capacity assessment system:
Cardboard origami tiling for circular mirror frame, optimized for kerf learned during Week 1 laser characterization.
Vinyl-cut ReactionAge control labels and MirrorAge fascia decals for rapid UI readability.
KiCad/Fusion schematics + polygon pours for ESP32S3 carrier, force sensing front-end, and OLED interposer.
2D shop drawings for CNC floating base, including registration dowels and silicone mold parting lines.
Figma wireframes outlining the midterm web dashboard and on-device OLED states.
Subtractive: Laser cutting, milling for precision parts
Electronics: PCB design and production
Programming: Embedded microcontroller development
Bill of Materials
Where possible, I fabricated parts rather than buying them. This table summarizes all unique components in the final MirrorAge system, their approximate costs, and where they are used.
A mirrored copy of this bill of materials also appears on the Week 14 system-integration page for cross-linking directly from the integration steps
(Week 14 BOM).
Grip-strength molds, band molds, structural ribs
(Week 9,
Week 14)
Fasteners
M2/M3 hardware, heat-set inserts, misc. screws
Assorted
~$0.10–$0.30 ea.
$20.00 (bundle)
All mechanical assemblies (watch, grip rig, camera mount, demo table)
Estimated Total Project Cost
Electronics ≈ $190 · Mechanical & materials ≈ $130 ·
Total ≈ $320 (excluding lab-provided consumables and reused stock).
Exact per-week line items remain in the weekly documentation tables (for example
ReactionAge BOM CSV in Week 2),
while this table captures the consolidated, unique parts that make up the final integrated MirrorAge system.
Fabrication Process
Week-by-week fabrication rolled forward subsystems toward the integrated mirror:
Week 1 laser-cut origami tiles for the circular bezel; Week 2 PCB milling + soldering for ReactionAge;
Week 3–4 torsional spring 3D prints and sanding jigs; Week 5 copper-clad milling and reflow of the ESP32S3 carrier;
Week 6 ShopBot machining of the floating base; Week 8 resin + FDM camera enclosure build; Week 9 wax machining, Mold Star casting, and Drystone ribs.
Each step captured feeds-and-speeds, toolpaths, and fixturing photos embedded in the weekly pages for replication.
Testing & Validation
Validation combined bench instrumentation and statistical analysis: oscilloscope timing to verify ReactionAge jitter, Edge Impulse confusion matrices for FaceTTD and VoiceAge,
Instron pull tests for the torsional grip cartridge, IR thermography while curing Mold Star molds, dial-indicator checks on CNC-machined bases, and adhesive shear testing on mirror mounts.
Data are logged to CSV via the ESP32S3 and compared against published baselines inside the midterm Jupyter notebook.
Individual Mastery and Independent Operation
Projects can be separate or joint, but need to show individual mastery of the skills, and be independently operable.
Individual Mastery
Demonstration of individual skills across all course units:
2D and 3D Design
Modeled the tensegrity floating mirror, torsional grip shells, and camera bezel in Fusion 360 and Onshape.
Drove design reviews with Anthony/Neil to lock tolerances, assembly order, and module interface specs.
Demonstrates mastery across cutting, 3D printing, machining, electronics, networking, and interface programming units.
Documentation cross-linked via weekly pages, GitHub repos, and BOM spreadsheets for traceability.
Group Assignments
Collaborative work and individual contributions:
Embedded programming group: authored workflow trade-off analysis and repo organization that seeded ReactionAge firmware patterns.
Molding & casting group: led SDS review, material trials, and mixing SOP that informed final mirror mold.
Shared camera dev sessions with peers to improve Edge Impulse dataset collection and SenseCraft deployment strategies.
Useful Documentation
Helpful resources, documentation, and design files for the multimodal intrinsic capacity assessment system.
Open Source Grip Strength Meter
A cost-effective $50 grip strength measurement system that can be further optimized for our multimodal assessment platform.
This open-source design provides an excellent foundation for integrating grip strength measurement into our intrinsic capacity assessment system,
with potential for cost reduction through signal multiplexing on a single processor.
Detailed technical pipeline for processing multiple digital biomarkers to generate intrinsic capacity scores.
Pipeline Architecture
Inputs
• Grip Strength
• Voice
• Face
• Video (motion/gait)
• Reaction Time
• Wearable Accelerometer
→
Feature Extraction
Strength metrics
Prosody features
Facial landmarks
Gait parameters
Response latency
Activity patterns
Embeddings
Features converted to vector representations for multimodal fusion
→
Fusion Layer
Combines multimodal features using attention mechanisms
Output
• Overall IC Score
• Domain sub-scores
→
Domain Scores
Locomotor
Cognition
Vitality
Sensory
Psychological
Weekly System Development Breakdown
How each week of HTMAA 2025 builds toward the complete multimodal intrinsic capacity assessment system.
Week 0: Project Ideation
Initial concept development and planning
Project planning and documentation structure
Research direction and concept sketches
Week 1: Precision Cutting
Laser and vinyl cutting techniques
Device housing components via laser cutting
Sensor mounting brackets and enclosures
Vinyl cutting for device labeling and UI elements
Week 2: Embedded Programming
Electronics basics and microcontroller programming
Microcontroller programming for data collection
Basic sensor interface circuits
Week 3: 3D Scanning & Printing
3D technologies for device components
3D scanning for custom component design
3D printing for device housings
Week 4: Electronics Design
EDA and schematic design
PCB design for grip strength measurement
Sensor interface circuits and signal conditioning
Power management and data storage systems
Week 5: Electronics Production
PCB fabrication and assembly
PCB fabrication and debugging
Component assembly and testing
Week 6: Computer-controlled Machining
CAM and precision milling
Precision components via milling
Custom mechanical parts
Week 7: Input Devices
Sensor integration for data collection
Force sensors for grip strength measurement
Microphones for voice analysis
Camera systems for facial expression analysis
Reaction time measurement circuits
Week 8: Output Devices
Actuators and system integration
Display systems for real-time feedback
Haptic feedback for user interaction
Week 9: Molding & Casting
Forming and resin techniques
3D printing and molding for custom components
Silicone casting for device components
Week 10: Mechanical & Machine Design
System integration and mechanical design
Mechanical design for ergonomic device housing
System integration and calibration protocols
Week 11: Networking & Communications
Connectivity and communication protocols
Bluetooth/Wi-Fi connectivity for data transmission
Wearable accelerometer integration and data fusion
Week 12: Interface & Application Programming
UI development and application programming
Mobile app development for user interface
Cloud integration for data storage and analysis
Machine learning pipeline for IC score calculation
Week 13: Wildcard & Final Integration
Final orders and complete system deployment
Final testing, validation, and documentation
System integration and deployment
Camera Subsystem
Advanced camera system implementation using XIAO ESP32S3 Sense with real-time image processing, EdgeAI integration, and interactive selfie capture functionality.
System Overview
The camera system successfully captures images, processes them into bitmaps, and displays them on an OLED screen using advanced Floyd-Steinberg dithering algorithms.
Video Demonstrations
Camera Bot Selfie
Demonstration of the interactive selfie capture system with touch controls
Picture of Picture
Meta demonstration showing the camera system capturing its own display
Code Implementation
60-Second Auto Capture System
Automated camera system that captures and displays images every 60 seconds using advanced image processing techniques.
1. Initialize camera with PSRAM frame buffers
2. Configure OLED display (128x64 pixels)
3. Set up 60-second capture interval timer
4. In main loop:
a. Check if 60 seconds have elapsed
b. Capture image from camera
c. Process image:
- Downsample to 128x64 via box averaging
- Apply contrast stretch (linear scaling)
- Perform Floyd-Steinberg dithering
d. Display processed bitmap on OLED
e. Release frame buffer
5. Repeat process
Touch-Controlled Capture System
Interactive camera system with touch controls allowing manual capture triggers in addition to automatic timing.
1. Initialize camera and OLED display
2. Set up touch pins (GPIO1 & GPIO2) with threshold detection
3. Configure 60-second auto-capture timer
4. In main loop:
a. Update touch sensor readings
b. Detect touch press events (justPressed)
c. Check for capture trigger:
- Touch press OR 60-second timer elapsed
d. If triggered:
- Capture image from camera
- Process image (same as auto version)
- Display on OLED
- Reset timer
5. Continue monitoring for next trigger
The system captures photos, converts them to bitmaps using advanced image processing algorithms, and displays them on the OLED screen.
I'm also exploring integration with ML models, either through online API calls or by embedding TinyML model parameters from Python to C++.
Future development includes live streaming real-time video with ML prediction updates based on variable observation times,
and exploring Edge Impulse models as an alternative to manual Python-to-C++ conversion for faster deployment.
EdgeAI/TinyML Integration
Edge AI can also be implemented using Edge Impulse models, which may be faster than manually converting Python models to C++.
The SenseCraft AI platform provides a streamlined approach to training and deploying ML models directly on the XIAO ESP32S3.
Deploy inference bundle to the SenseCraft board alongside the camera stack.
Benchmark latency and accuracy against baseline VoiceAge models and document calibration protocol.
Week 0 - Introduction & Design
Project ideation and initial concept development for bioprinting rejuvenated tissue and aging biomarker devices.
Project planningConcept sketchesResearch direction
System Integration Plans: Establish the foundational architecture for multimodal data collection by designing the overall system framework that will integrate all six digital biomarkers (grip strength, voice, face, video, reaction time, wearable accelerometer) into a cohesive intrinsic capacity assessment platform.
Mapped the MirrorAge subsystem architecture, assembled the intrinsic capacity literature stack, and kicked off BRR/IRB coordination so fabrication sprints stay aligned with clinical requirements.
Week 1 - Principles & Cutting
Version control, laser cutting, and vinyl cutting techniques applied to final project components.
Laser cuttingVinyl cuttingVersion control
System Integration Plans: Fabricate precision-cut housing components and mounting brackets for all sensor modules (force sensors, microphones, cameras, reaction time circuits) using laser cutting, while creating vinyl-cut labels and UI elements for device identification and user guidance.
Characterized laser kerf, produced the origami mirror frame tiles, and generated vinyl interface labels—locking in enclosure dimensions and user UI cues for the mirror shell.
Week 2 - Embedded Programming
Electronics basics and embedded programming for the aging biomarker device components.
MicrocontrollersProgrammingElectronics
System Integration Plans: Develop embedded programming protocols for real-time data collection from all six biomarker sensors, implementing initial signal processing algorithms and establishing the communication framework for multimodal data fusion.
Built the ReactionAge firmware + enclosure, published the first BOM, and validated timing pipelines that will feed the MirrorAge IC fusion engine.
Week 3 - 3D Scanning & Printing
3D scanning and printing techniques for bioprinting components and device housings.
3D scanning3D printingAI tools
System Integration Plans: Create custom 3D-printed components for camera mounting systems and facial recognition hardware, while developing 3D scanning protocols for ergonomic device design that accommodates all sensor modalities in a user-friendly form factor.
Modeled and printed the torsional grip spring, performed 3D scans for ergonomic fixtures, and captured training assets for face/gait datasets.
Week 4 - Electronics Design
EDA and schematic design for the aging biomarker device electronics.
EDA toolsSchematic designCircuit design
System Integration Plans: Design comprehensive PCB schematics that integrate force sensor circuits for grip strength measurement, microphone preamplifiers for voice analysis, camera interfaces for facial recognition, and timing circuits for reaction time assessment into a unified electronics platform.
Completed the Fusion 360/KiCad schematic/PCB layout for the ESP32S3 carrier tying together force, audio, camera, reaction, and wearable interfaces.
Week 5 - Electronics Production
PCB fabrication, debugging, and assembly for the biomarker device.
PCB fabricationDebuggingAssembly
System Integration Plans: Fabricate and assemble the integrated PCB containing all sensor interfaces, implementing power management systems for continuous operation and establishing data storage protocols for the multimodal biomarker data collection system.
Fabricated and assembled the carrier PCB, brought up power domains, and verified sensor buses—establishing the electronics backbone for integration.
Week 6 - Computer-controlled Machining
CAM and milling for precision components and device housings.
CAMMillingPrecision machining
System Integration Plans: Machine precision mechanical components for the integrated device housing using computer-controlled milling, ensuring proper alignment and mounting for all sensor modules while maintaining ergonomic design for user comfort during multimodal data collection.
Machined the floating mirror base and tensegrity nodes, refining fixturing that ensures repeatable camera and grip alignment in the final assembly.
Week 7 - Input Devices
Sensors and embedded architectures for data collection in the biomarker device.
SensorsInput devicesData collection
System Integration Plans: Integrate all six input sensor systems (force sensors for grip strength, microphones for voice analysis, cameras for facial recognition and gait analysis, reaction time circuits, and wearable accelerometer) into the unified data collection platform with real-time processing capabilities.
Integrated the force sensor, microphone, and ReactionAge modules on the carrier, logging synchronized packets that exercise the multimodal intake stack.
Week 8 - Output Devices
Actuators and system integration for the biomarker device outputs.
ActuatorsOutput devicesSystem integration
System Integration Plans: Implement output devices including display systems for real-time intrinsic capacity feedback and haptic feedback mechanisms for user interaction, creating an intuitive interface for the multimodal biomarker assessment system.
Deployed the SenseCraft FaceTTD pipeline on the XIAO ESP32S3, implemented OLED dithering previews, and confirmed end-to-end edge inference latency.
Week 9 - Molding & Casting
Forming and resin techniques for bioprinting molds and device components.
MoldingCastingResins
System Integration Plans: Create custom molded components for the bioprinting aspects of the project and develop specialized casings for sensor protection, ensuring the device can withstand continuous use during multimodal data collection sessions.
Machined wax molds, cast Mold Star silicone and Drystone ribs, and prototyped arrow-inspired shells that stabilize the mirror and protect embedded sensors.
Week 10 - Mechanical & Machine Design
Kits and mechanical design for the bioprinting and biomarker device systems.
Mechanical designMachine designSystem integration
System Integration Plans: Complete the mechanical design integration of all system components, implementing calibration protocols for sensor alignment and developing the complete mechanical framework that houses all six digital biomarker measurement systems.
Developed mechanical actuation systems including tapping and swiping mechanisms for phone interaction, integrated camera with Edge AI face detection and Wi-Fi livestreaming, designed and 3D-printed phone holder with amplifier, and prepared comprehensive midterm review documentation with system diagrams and timeline.
Week 11 - Networking & Communications
BLE, Wi-Fi, and communication protocols for the biomarker device connectivity.
BLEWi-FiCommunications
System Integration Plans: Implement wireless communication protocols (Bluetooth/Wi-Fi) for seamless data transmission from all six sensor modalities, enabling real-time data fusion and establishing connectivity for the wearable accelerometer integration into the multimodal assessment system.
Implemented Wi-Fi camera livestreaming for real-time video transmission, developed ESP-NOW networking protocols for device communication, designed and milled PCBs for networking components, and explored Meshtastic for long-range communication capabilities.
Week 12 - Interface & Application Programming
UI and application development for the biomarker device interface.
UI designApplicationsUser interface
System Integration Plans: Develop the complete user interface and application programming for the multimodal system, implementing the machine learning pipeline for intrinsic capacity score calculation and creating cloud integration for comprehensive data storage and analysis of all biomarker measurements.
Created Wi-Fi web interface for real-time pulse oximeter readings with live plotting, developed grip strength measurement device with load cell and integrated GUI, implemented OLED button user interface for device control, and established video streaming capabilities for sensor data visualization.
Week 13 - Wildcard & Final Orders
Final orders and wildcard week activities for project completion.
Final ordersWildcard activitiesProject completion
System Integration Plans: Complete final system integration, testing, and validation of the complete multimodal intrinsic capacity assessment platform, ensuring all six digital biomarkers work cohesively to provide accurate WHO-defined intrinsic capacity scores across all five domains (locomotor, cognition, vitality, sensory, psychological).
Designed and fabricated ATtiny1626 tiny development board with fiber laser PCB engraving, created glass engraving system with UV laser including blinking heart integration for visual feedback, milled mounting holes and completed board assembly, and prepared final board designs for system integration.
System Integration
Final integration week focused on bringing all subsystems together, completing hardware fabrication, firmware integration, and documentation for the MirrorAge system presentation. View full details →
Initial system integration work focused on subsystem validation, CAD model consolidation, and design backbone acquisition for band integration. Conducted comprehensive testing of all subsystems to ensure proper functionality, identified and resoldered defective joints, and exported CAD models of all PCBs into a unified assembly model.
Integrated CAD Model: Exploded isometric view of the complete system assembly, including all PCBs, main housing with transparent enclosure, and wearable band components.
Physical integration of subsystems into the complete demo table assembly, including mechanical component fabrication and electrical board consolidation. Integrated the complete demo table with precise placement of the MirrorAge handgrip subsystem and aging clock subsystem, providing a unified platform for system demonstration.
Continued fabrication work integrating all manufacturing processes. Focused on completing physical components and preparing subsystems for final assembly and testing.
Comprehensive subsystem integration combining 2D fabrication (laser cutting and vinyl cutting), 3D printing (rigid and flexible components), PCB milling (single and double-sided boards), and molding/casting to complete all physical components. Upgraded MirrorAge TFT board to v13 and aging clock TFT board to v16 with optimized component placement and routing. Established reliable I²C bus communication and validated all sensor addresses.
Final integration day focused on closing the watch subsystem, soldering and verifying all double-sided boards, refining molded bands, and assembling the complete MirrorAge demo with both the aging clock and grip-strength subsystems fully wired and tested. Completed rivet installation for plated through-holes, sensor bring-up (accelerometer, pulse oximeter, OLED/TFT displays), and full system integration on the tensegrity demo table. The integrated system successfully demonstrated synchronized sensor readouts and display behavior across all boards.
Final project presentation and demonstration of the complete MirrorAge system. Showcased the integrated aging clock and grip-strength subsystems working together on the demo table, demonstrating real-time sensor data collection and display synchronization. View final presentation demo →
Full Documentation: For complete details, design files, code, and comprehensive documentation of the system integration process, see Week 14: System Integration.
Final Project Masterpiece
Complete demonstration of the integrated MirrorAge system showcasing all subsystems working together in real-time.
Final Presentation Demo: Complete MirrorAge system demonstration showing the integrated aging clock and grip-strength subsystems operating together on the demo table, with synchronized sensor readouts and real-time display updates across all boards.
Complete repository of all design files, CAD models, schematics, PCB layouts, firmware, and fabrication files from Week 0 through Week 14, organized by week and component type.
Note: Additional design files, firmware, and documentation can be found in the respective week pages. Some files are part of larger archives (ZIP files) that contain multiple related design files.
Reflections & Learnings
Comprehensive reflections on the MirrorAge Intrinsic Capacity Mirror project development journey.
Modular system design allows for incremental development and component-level testing throughout the semester
Integration of mechanical, electrical, and software subsystems requires careful planning and coordination
Iterative design and prototyping revealed the importance of early testing and validation
Documentation and knowledge transfer are critical for project continuity and future improvements
The project successfully demonstrates how digital fabrication and embedded systems can create meaningful health assessment tools
Contributions
Acknowledgements and contributions that made this project possible.
Gladyshev Lab and Collaborators
Special thanks to the Gladyshev Lab and collaborators for the fruitful discussions that led to this multimodal intrinsic capacity assessment idea,
which supplements my PhD research goals in aging and longevity. The conceptual framework for integrating multiple digital biomarkers
to assess intrinsic capacity domains emerged from collaborative research discussions on aging biomarkers and healthspan assessment.
Transparent documentation of AI assistance used in this final project work, following course guidelines for ethical AI usage.
📋 General Guidelines: See General Commands for Cursor on the homepage for standard guidelines and commands used consistently throughout documentation development.
Cursor · Project Plan & Weekly Schedule
Comprehensive Cursor AI assistance for outlining the project plan and weekly schedule, including documentation structure, content organization, systematic updates across all week pages and the final project page, media integration, and summary generation workflows.
Cursor AI aligned the midterm review plan with updated system diagram, timeline, and remaining-task summaries, then refreshed finalproject.html to remove legacy bioprinting language and re-point internal links. The full transcript and generated HTML are available for review.
Cursor AI assistance for adding a white background behind the photo in the Final Project Spiral Development Model section on finalproject.html. The image container was updated with white background, padding, and rounded corners for improved visual presentation.
Cursor AI distilled Week 0–9 documentation and the Oct 31 lab meeting deck into midterm-ready narrative, cost, and validation content, replacing every placeholder in finalproject.html.
Transcript archived in markdown and HTML (generated via scripts/md_to_html_converter.py) for transparency.
ChatGPT was used to research and develop the multimodal intrinsic capacity assessment framework, including the comprehensive coverage analysis table and technical pipeline design.
The AI assisted with structuring the WHO-defined intrinsic capacity domains, identifying appropriate digital biomarkers, and designing the fusion architecture for multimodal data processing.
Cursor AI assisted with developing the complete final project page structure, implementing the multimodal intrinsic capacity assessment framework, and creating comprehensive documentation.
The AI helped with HTML structure, responsive design, weekly system integration plans, and organizing the technical documentation for the complete biomarker assessment system.
Cursor AI assisted with finalizing the project presentation structure to ensure full compliance with MIT Academy project presentation requirements.
The AI helped implement all required sections including answering questions, design documentation, bill of materials, individual mastery requirements,
course presentation structure, and spiral model development approach visualization.
ChatGPT was used to discuss camera system implementation strategies, image processing algorithms, and EdgeAI integration approaches.
The AI assisted with understanding Floyd-Steinberg dithering implementation, touch sensor integration, and exploring TinyML deployment options for the XIAO ESP32S3 platform.
AI-Assisted Project Highlights and Camera Subsystem Development
Cursor AI assisted with adding the project highlights section featuring camera system achievements and creating a comprehensive camera subsystem section with detailed code implementations, video demonstrations, and EdgeAI integration documentation.
The AI helped with HTML structure, responsive design, image processing explanations, and organizing the technical documentation for the complete camera system showcase.
Interactive selfie capture system with touch controls and real-time display
Vision Board
Conceptual visualization of the multimodal intrinsic capacity assessment system integrating grip strength, voice analysis, facial recognition, video motion capture, reaction time measurement, and wearable accelerometer data.
Intrinsic Capacity (IC) Coverage by Digital Biomarkers
Domain
Grip
Voice
Face
Video
Reaction Time
Wearable
Locomotor
✅
🔸
🔸
✅
🔸
✅
Cognition
❌
✅
🔸
🔸
✅
🔸
Vitality
✅
✅
✅
✅
🔸
✅
Sensory
❌
✅
✅
✅
✅
🔸
Psychological
❌
✅
✅
✅
🔸
✅
✅ Strong coverage |
🔸 Partial/indirect |
❌ Not covered |
View full table →
Multimodal IC Pipeline
Inputs: Grip Strength, Voice, Face, Video, Reaction Time, Wearable Accelerometer
Development Approach: Following the spiral model methodology, this final project will iterate through multiple development cycles, each building upon previous work while addressing new requirements and risks.
This snapshot covers the subsystems and documentation that will be shown during the midterm review. Links jump directly to the supporting sections with detailed evidence.
Featured Subsystems
Camera subsystem — Edge inference demos and selfie capture loop.
Instructor meeting hold — Thursday, Nov 12 at 10:00 AM ET reserved via the shared HTMAA midterm review sheet.
Execution Schedule (Timeline Snapshot)
Condensed from the Week 8–13 development timeline: each sprint builds toward final integration, mirroring the gantt chart below.
Week 8 · Output Devices: figuring out wiring for real-time display states.
Week 9 · Molding & Casting: learn how to cast custom housings and refine structural components.
Week 10 · Mechanical Design: figure out ergonomic enclosure and calibration fixtures.
Week 11 · Networking: program BLE/Wi-Fi telemetry and wearable data fusion.
Week 12 · Interface/App: create mobile UI, cloud bridge, and IC scoring pipeline.
Week 13 · Final Integration: run validation passes, document results, and prep deployment.
Instructor Review Logistics
Calendar hold sent for Thursday, Nov 12 at 10:00 AM ET (38-501 conference room) per the shared HTMAA scheduling sheet. Agenda covers subsystem demos, weekly documentation spot checks (Weeks 0–9), and next-sprint alignment. Meeting slot referenced in the midterm review schedule; awaiting final confirmation via class Slack.
System Architecture
Updated block diagram highlighting the multimodal sensing stack (grip, voice, face, motion, wearables), on-device inference layers, and real-time feedback channels that feed the intrinsic capacity score.
Development Timeline
Timeline aligns subsystem sprints with HTMAA milestones: output devices (Week 8), molding and casting (Week 9), mechanical design (Week 10), networking and communications (Week 11), app programming (Week 12), and final integration (Week 13).
Remaining Tasks (Snapshot)
Weeks 0–9 locked in the core subsystems—documentation workflow, cutting and molding for the housing, embedded prototypes for reaction timing, SenseCraft camera inference, and early grip/voice rigs. The checklist below captures what still needs to happen to converge on the integrated MirrorAge system.
Hardware Integration
Consolidate grip, voice, camera, reaction-time, and wearable sensor harnesses into the MirrorAge enclosure.
Finish molding/casting iterations for the ergonomic housing and align mounting features for PCBs and haptics.
Firmware & Edge AI
Stabilize onboard inference for SenseCraft vision models and voice-age pipelines on the XIAO ESP32S3.
Calibrate grip-force and reaction-time firmware for repeatable sampling; close the loop to haptic/display feedback.
Networking & Data Fusion
Bring up BLE/Wi-Fi data paths for wearable accelerometer streaming and cloud logging of intrinsic capacity scores.
Implement the fusion layer that combines per-domain scores into an overall IC metric with on-device storage.
Interface & UX
Finish mobile/web dashboard mockups for user onboarding, data review, and device calibration workflows.
Finalize real-time mirror feedback cues (display states, haptics, lighting) tied to sensor status and IC outcomes.
Validation & Documentation
Run end-to-end system tests (sensor capture → fusion → feedback) and document calibration procedures.
Record the one-minute video, finalize final presentation assets, and polish the bill of materials for review.
Week 14 System Integration Plan
Detailed day-by-day schedule for final system integration, covering design, fabrication, programming, testing, and documentation. This plan outlines the path to completing the MirrorAge system integration and preparing for final presentation. View on Week 14 page →
The act of bringing something to a conclusion or ending in a decisive manner. The ability to efficiently finish tasks and projects with a goal-oriented mindset.
Wednesday
Morning
Publish system integration plan on website
Update weekly assignment sections on final project page (weeks 10-13)
Link final project design files
Update reflections and learnings
Update picture of prism holder
Add final pictures to Slack canvases
Create schematic between boards (wired and wireless) — updated system diagram on PPT-like page
Start CAD model of system
Place final order
Afternoon & Evening
Design:
Boards: Combine OLED screen/accelerometer with pulse oximeter board in a new board (maybe upgrade to small TFT as minor)
Boards: Speaker board with realtime amplifier and TFT (on the load cell fixed board)
Band: Mold design
Cases: 3D print mountable cases for the boards
Integrate designs into final CAD
Document design
Finish CAD model of system
Thursday
Fabricate
Milling boards
Print mold and cast band
Print cases
Solder
Solder components on milled boards
Connect boards with wired (and wireless connection codes)
Finishing
Mirror on screen (easy way with the film)
Documentation
Document fabrication
Friday
Programming
Board level codes
Server level codes
Documentation
Document codes
Completion
Finish anything else
Saturday
Programming & Testing
Demo integrated system
Test integrated system
Documentation
Document testing and evaluation
Review and complete documentation (list of questions)
Make the video by collaging documentation
Sunday
Fill up any gaps
Prepare demo on tensegrity table
Finalize 1-slide
Work on minors
If done, work on if there's time
Monday Morning
Transport demo on tensegrity table
Fill up any gaps
Work on minors
Specific Tasks to Complete This Week
Major Tasks
CAD model of system
Speaker board with realtime amplifier
Combine screen/accelerometer with pulse oximeter board in a new board
Mold and cast band
Design and fabricate casing (print)
Schematic between boards (wired and wireless) — updated system diagram on PPT-like page
Serial connection between pulse oximeter and tiny blinking heart for BPM (BPM from IR, SpO2 from delta)
Combine multiple boards on the same WiFi (switching tabs is easy way, board hosting the webpage querying and update or Python-based server somewhere where everything posting data, Raspberry Pi)
Put+program everything together according to the above (with WiFi for now)
MirrorAge is a self-contained edge-AI mirror that captures grip strength, facial imagery, voice, motion, and reaction time to estimate intrinsic capacity in real time.
The platform fuses weekly prototypes—ReactionAge latency tests, 3D printed grip mechanics, SenseCraft camera inference, and molded structural elements—into a multimodal mortality risk profiler.
Subsystems in progress: reaction-time module, SenseCraft FaceTTD inference stack, VoiceAge microphone pipeline, wearable streaming via BLE, and molded structural packaging.
Clinical motivation: translate WHO intrinsic capacity domains into measurable digital biomarkers that flag functional decline earlier than chronological age alone.
Project Goals
Deliver multimodal IC scoring Fuse grip, face, voice, reaction-time, and wearable streams on-device to output an intrinsic capacity score plus domain deltas.
Fabricate modular, serviceable hardware Iterate laser-cut tensegrity mirror shells, 3D printed torsional grips, custom PCBs, and silicone cast fixtures that assemble without bespoke tooling.
Validate against ground truth Benchmark embedded inferences against published datasets (Blomkvist et al. 2017, Fuentealba et al. 2025) and lab-collected pilots to quantify accuracy, latency, and reliability.
Timeline & Milestones
Week 10 · Hardware convergence Integrate SenseCraft FaceTTD camera, ReactionAge latency module, and newly milled PCB into a single ESP32S3 backplane.
Week 12 · Midterm review build Finish molded mirror enclosure, bring up BLE wearable link, and demo live IC score during midterm critique.
Final week · Validation & documentation Execute pilot data collection, refine model weights, and release reproducible fabrication + firmware packages.
Documenting the final project masterpiece that integrates the range of units covered, addressing all required questions.
What does it do?
MirrorAge captures synchronized digital biomarkers—camera frames processed with on-device FaceTTD models, VoiceAge microphone samples, grip strength torque, wearable accelerometry, and ReactionAge latency—to estimate intrinsic capacity and time-to-death acceleration.
A XIAO ESP32S3 Sense orchestrates sensing, performs Edge Impulse inference, and displays a live mortality-risk score on the OLED while logging packets to a Python analytics notebook.
Who's done what beforehand?
The concept builds on WHO intrinsic capacity framing and recent mortality-risk studies: Niccoli & Partridge (2012) establish age as the dominant chronic-disease predictor; Fuentealba et al. (Nature Aging 2025) show blood-based IC clocks outperform chronological models;
Zhavoronkov & Bhullar (2015) and Lancet Healthy Longevity editorials motivate treating functional decline as the actionable signal.
This project translates those findings into an accessible, multimodal measurement mirror that can operate outside hospital labs.
What sources did you use?
Primary references include Nature Aging 2025 intrinsic capacity papers, the PLOS ONE ReactionAge dataset (Blomkvist et al. 2017), Edge Impulse SenseCraft documentation, Smooth‑On Mold Star technical bulletins, RotoMetals alloy certificates, MIT HTMAA recitations, and the open-source GRPR grip-strength meter.
Design inspiration and safety notes were consolidated from Anthony Pennes' HTMA guides and Fab Academy molding tutorials.
What did you design?
• Laser-cut cardboard origami mirror frame and tensegrity-inspired floating mount (Weeks 1 & 6)
• ReactionAge firmware + enclosure with statistical post-processing dashboards (Week 2)
• 3D printed torsional spring grip module tuned for ±40 kg ranges (Week 3)
• KiCad/Fusion carrier PCB for the ESP32S3 Sense with OLED, force, and BLE breakouts (Week 5)
• Edge Impulse deployment pipeline with grayscale dithering overlay and live inference UX (Weeks 7–8)
• CAM toolpaths, silicone molds, and Drystone casts for structural packaging (Week 9)
What materials and components were used?
Seeed XIAO ESP32S3 Sense module with OV2640 camera and PDM mic, SparkFun Qwiic button and force sensors, SSD1306 OLED, wearable IMU node (Bosch BHI260), laser-cut cardboard/birch sheets, PLA+/Onyx filament, Mold Star 30 silicone, Drystone gypsum, Roto281 fusible alloy, and embedded fasteners/heat-set inserts.
Where did they come from?
Electronics from Seeed Studio, SparkFun, Digi-Key, and Adafruit; molding supplies and silicones from Reynolds Advanced Materials; Drystone and Hydro-Stone from USG via the MIT CBA stockroom; fusible alloys from RotoMetals; structural lumber and plywood from MIT's shop inventory; filaments from Prusa Research and Markforged.
How much did they cost?
Current spend: $96.34 for ReactionAge components (Week 2 BOM) + $78.42 for SenseCraft camera stack (XIAO ESP32S3 Sense, OLED, cabling) + $42.10 for molding media (Mold Star 30 quart, Drystone, release agents) = $216.86 to date.
Remaining allocation (~$130) is earmarked for BLE wearable hardware and final enclosure finishes; detailed line items tracked in the Airtable budget and mirrored in each weekly BOM CSV.
What parts and systems were made?
Custom origami mirror frame, 3D printed torsional grip shell, machined floating base, silicone molds and Drystone casts for arrow-inspired structural ribs, bespoke ESP32S3 breakout PCB, laser-cut ReactionAge control panel, and assembled sensor tower linking camera, OLED, and wearable gateway.
What tools and processes were used?
Parametric CAD in Fusion 360, laser cutting (Epilog) for origami tiles, Prusa MK4 FDM printing, Formlabs SLA for detail inserts, ShopBot CNC and Bantam PCB milling, silicone mixing/casting under vacuum, Edge Impulse model training, PlatformIO firmware, and Python/NumPy validation notebooks.
What questions were answered?
• Can consumer-grade sensors reproduce published reaction-time age curves? (Yes—ReactionAge matched Blomkvist et al. regression within 4.6 ms RMSE.)
• Will SenseCraft FaceTTD run locally on ESP32S3 with acceptable latency? (Yes—~310 ms/inference at 30% baseline accuracy, highlighting dataset needs.)
• Does molded packaging improve sensor placement repeatability? (Yes—silicone nests held camera ±0.5 mm, reducing alignment drift seen in cardboard prototypes.)
What worked? What didn't?
✅ Floyd–Steinberg dithering produced clear OLED previews; ✅ ReactionAge firmware maintained ±1 ms jitter; ✅ Molded Drystone ribs stiffened mirror shell without excess weight.
⚠️ FaceTTD accuracy plateaued at 30% due to limited training diversity; ⚠️ VoiceAge requires more MFCC samples to sustain 0.64-year MAE; ⚠️ Grip spring fatigue highlighted need for fiber-reinforced print or machined aluminum insert.
How was it evaluated?
Bench tests compare embedded predictions to published curves and desktop baselines: ReactionAge latency vs. Wii Balance Board golden data; FaceTTD inferencing cross-validated against Edge Impulse cloud classifier; VoiceAge MFCC regression verified through train/holdout splits; mechanical fixtures inspected with feeler gauges and dial indicators for tolerance drift.
What are the implications?
A portable intrinsic capacity mirror supports proactive geriatric screening, telehealth coaching, and longitudinal studies that correlate functional decline with interventions.
By grounding hardware in open-source parts and HTMAA fabrication methods, the system can be replicated across labs and community clinics to accelerate validation of digital aging biomarkers and personalize longevity therapies.
Design
Your project should incorporate 2D and 3D design, multiple additive and subtractive fabrication processes, electronics design and production, embedded microcontroller design, interfacing, and programming, system integration and packaging.
2D Design
2D design work for the multimodal intrinsic capacity assessment system:
Cardboard origami tiling for circular mirror frame, optimized for kerf learned during Week 1 laser characterization.
Vinyl-cut ReactionAge control labels and MirrorAge fascia decals for rapid UI readability.
KiCad/Fusion schematics + polygon pours for ESP32S3 carrier, force sensing front-end, and OLED interposer.
2D shop drawings for CNC floating base, including registration dowels and silicone mold parting lines.
Figma wireframes outlining the midterm web dashboard and on-device OLED states.
Subtractive: Laser cutting, milling for precision parts
Electronics: PCB design and production
Programming: Embedded microcontroller development
Bill of Materials
Where possible, I fabricated parts rather than buying them. This table summarizes all unique components in the final MirrorAge system, their approximate costs, and where they are used.
A mirrored copy of this bill of materials also appears on the Week 14 system-integration page for cross-linking directly from the integration steps
(Week 14 BOM).
Grip-strength molds, band molds, structural ribs
(Week 9,
Week 14)
Fasteners
M2/M3 hardware, heat-set inserts, misc. screws
Assorted
~$0.10–$0.30 ea.
$20.00 (bundle)
All mechanical assemblies (watch, grip rig, camera mount, demo table)
Estimated Total Project Cost
Electronics ≈ $190 · Mechanical & materials ≈ $130 ·
Total ≈ $320 (excluding lab-provided consumables and reused stock).
Exact per-week line items remain in the weekly documentation tables (for example
ReactionAge BOM CSV in Week 2),
while this table captures the consolidated, unique parts that make up the final integrated MirrorAge system.
Fabrication Process
Week-by-week fabrication rolled forward subsystems toward the integrated mirror:
Week 1 laser-cut origami tiles for the circular bezel; Week 2 PCB milling + soldering for ReactionAge;
Week 3–4 torsional spring 3D prints and sanding jigs; Week 5 copper-clad milling and reflow of the ESP32S3 carrier;
Week 6 ShopBot machining of the floating base; Week 8 resin + FDM camera enclosure build; Week 9 wax machining, Mold Star casting, and Drystone ribs.
Each step captured feeds-and-speeds, toolpaths, and fixturing photos embedded in the weekly pages for replication.
Testing & Validation
Validation combined bench instrumentation and statistical analysis: oscilloscope timing to verify ReactionAge jitter, Edge Impulse confusion matrices for FaceTTD and VoiceAge,
Instron pull tests for the torsional grip cartridge, IR thermography while curing Mold Star molds, dial-indicator checks on CNC-machined bases, and adhesive shear testing on mirror mounts.
Data are logged to CSV via the ESP32S3 and compared against published baselines inside the midterm Jupyter notebook.
Individual Mastery and Independent Operation
Projects can be separate or joint, but need to show individual mastery of the skills, and be independently operable.
Individual Mastery
Demonstration of individual skills across all course units:
2D and 3D Design
Modeled the tensegrity floating mirror, torsional grip shells, and camera bezel in Fusion 360 and Onshape.
Drove design reviews with Anthony/Neil to lock tolerances, assembly order, and module interface specs.
Demonstrates mastery across cutting, 3D printing, machining, electronics, networking, and interface programming units.
Documentation cross-linked via weekly pages, GitHub repos, and BOM spreadsheets for traceability.
Group Assignments
Collaborative work and individual contributions:
Embedded programming group: authored workflow trade-off analysis and repo organization that seeded ReactionAge firmware patterns.
Molding & casting group: led SDS review, material trials, and mixing SOP that informed final mirror mold.
Shared camera dev sessions with peers to improve Edge Impulse dataset collection and SenseCraft deployment strategies.
Useful Documentation
Helpful resources, documentation, and design files for the multimodal intrinsic capacity assessment system.
Open Source Grip Strength Meter
A cost-effective $50 grip strength measurement system that can be further optimized for our multimodal assessment platform.
This open-source design provides an excellent foundation for integrating grip strength measurement into our intrinsic capacity assessment system,
with potential for cost reduction through signal multiplexing on a single processor.
Detailed technical pipeline for processing multiple digital biomarkers to generate intrinsic capacity scores.
Pipeline Architecture
Inputs
• Grip Strength
• Voice
• Face
• Video (motion/gait)
• Reaction Time
• Wearable Accelerometer
→
Feature Extraction
Strength metrics
Prosody features
Facial landmarks
Gait parameters
Response latency
Activity patterns
Embeddings
Features converted to vector representations for multimodal fusion
→
Fusion Layer
Combines multimodal features using attention mechanisms
Output
• Overall IC Score
• Domain sub-scores
→
Domain Scores
Locomotor
Cognition
Vitality
Sensory
Psychological
Weekly System Development Breakdown
How each week of HTMAA 2025 builds toward the complete multimodal intrinsic capacity assessment system.
Week 0: Project Ideation
Initial concept development and planning
Project planning and documentation structure
Research direction and concept sketches
Week 1: Precision Cutting
Laser and vinyl cutting techniques
Device housing components via laser cutting
Sensor mounting brackets and enclosures
Vinyl cutting for device labeling and UI elements
Week 2: Embedded Programming
Electronics basics and microcontroller programming
Microcontroller programming for data collection
Basic sensor interface circuits
Week 3: 3D Scanning & Printing
3D technologies for device components
3D scanning for custom component design
3D printing for device housings
Week 4: Electronics Design
EDA and schematic design
PCB design for grip strength measurement
Sensor interface circuits and signal conditioning
Power management and data storage systems
Week 5: Electronics Production
PCB fabrication and assembly
PCB fabrication and debugging
Component assembly and testing
Week 6: Computer-controlled Machining
CAM and precision milling
Precision components via milling
Custom mechanical parts
Week 7: Input Devices
Sensor integration for data collection
Force sensors for grip strength measurement
Microphones for voice analysis
Camera systems for facial expression analysis
Reaction time measurement circuits
Week 8: Output Devices
Actuators and system integration
Display systems for real-time feedback
Haptic feedback for user interaction
Week 9: Molding & Casting
Forming and resin techniques
3D printing and molding for custom components
Silicone casting for device components
Week 10: Mechanical & Machine Design
System integration and mechanical design
Mechanical design for ergonomic device housing
System integration and calibration protocols
Week 11: Networking & Communications
Connectivity and communication protocols
Bluetooth/Wi-Fi connectivity for data transmission
Wearable accelerometer integration and data fusion
Week 12: Interface & Application Programming
UI development and application programming
Mobile app development for user interface
Cloud integration for data storage and analysis
Machine learning pipeline for IC score calculation
Week 13: Wildcard & Final Integration
Final orders and complete system deployment
Final testing, validation, and documentation
System integration and deployment
Camera Subsystem
Advanced camera system implementation using XIAO ESP32S3 Sense with real-time image processing, EdgeAI integration, and interactive selfie capture functionality.
System Overview
The camera system successfully captures images, processes them into bitmaps, and displays them on an OLED screen using advanced Floyd-Steinberg dithering algorithms.
Video Demonstrations
Camera Bot Selfie
Demonstration of the interactive selfie capture system with touch controls
Picture of Picture
Meta demonstration showing the camera system capturing its own display
Code Implementation
60-Second Auto Capture System
Automated camera system that captures and displays images every 60 seconds using advanced image processing techniques.
1. Initialize camera with PSRAM frame buffers
2. Configure OLED display (128x64 pixels)
3. Set up 60-second capture interval timer
4. In main loop:
a. Check if 60 seconds have elapsed
b. Capture image from camera
c. Process image:
- Downsample to 128x64 via box averaging
- Apply contrast stretch (linear scaling)
- Perform Floyd-Steinberg dithering
d. Display processed bitmap on OLED
e. Release frame buffer
5. Repeat process
Touch-Controlled Capture System
Interactive camera system with touch controls allowing manual capture triggers in addition to automatic timing.
1. Initialize camera and OLED display
2. Set up touch pins (GPIO1 & GPIO2) with threshold detection
3. Configure 60-second auto-capture timer
4. In main loop:
a. Update touch sensor readings
b. Detect touch press events (justPressed)
c. Check for capture trigger:
- Touch press OR 60-second timer elapsed
d. If triggered:
- Capture image from camera
- Process image (same as auto version)
- Display on OLED
- Reset timer
5. Continue monitoring for next trigger
The system captures photos, converts them to bitmaps using advanced image processing algorithms, and displays them on the OLED screen.
I'm also exploring integration with ML models, either through online API calls or by embedding TinyML model parameters from Python to C++.
Future development includes live streaming real-time video with ML prediction updates based on variable observation times,
and exploring Edge Impulse models as an alternative to manual Python-to-C++ conversion for faster deployment.
EdgeAI/TinyML Integration
Edge AI can also be implemented using Edge Impulse models, which may be faster than manually converting Python models to C++.
The SenseCraft AI platform provides a streamlined approach to training and deploying ML models directly on the XIAO ESP32S3.
Deploy inference bundle to the SenseCraft board alongside the camera stack.
Benchmark latency and accuracy against baseline VoiceAge models and document calibration protocol.
Week 0 - Introduction & Design
Project ideation and initial concept development for bioprinting rejuvenated tissue and aging biomarker devices.
Project planningConcept sketchesResearch direction
System Integration Plans: Establish the foundational architecture for multimodal data collection by designing the overall system framework that will integrate all six digital biomarkers (grip strength, voice, face, video, reaction time, wearable accelerometer) into a cohesive intrinsic capacity assessment platform.
Mapped the MirrorAge subsystem architecture, assembled the intrinsic capacity literature stack, and kicked off BRR/IRB coordination so fabrication sprints stay aligned with clinical requirements.
Week 1 - Principles & Cutting
Version control, laser cutting, and vinyl cutting techniques applied to final project components.
Laser cuttingVinyl cuttingVersion control
System Integration Plans: Fabricate precision-cut housing components and mounting brackets for all sensor modules (force sensors, microphones, cameras, reaction time circuits) using laser cutting, while creating vinyl-cut labels and UI elements for device identification and user guidance.
Characterized laser kerf, produced the origami mirror frame tiles, and generated vinyl interface labels—locking in enclosure dimensions and user UI cues for the mirror shell.
Week 2 - Embedded Programming
Electronics basics and embedded programming for the aging biomarker device components.
MicrocontrollersProgrammingElectronics
System Integration Plans: Develop embedded programming protocols for real-time data collection from all six biomarker sensors, implementing initial signal processing algorithms and establishing the communication framework for multimodal data fusion.
Built the ReactionAge firmware + enclosure, published the first BOM, and validated timing pipelines that will feed the MirrorAge IC fusion engine.
Week 3 - 3D Scanning & Printing
3D scanning and printing techniques for bioprinting components and device housings.
3D scanning3D printingAI tools
System Integration Plans: Create custom 3D-printed components for camera mounting systems and facial recognition hardware, while developing 3D scanning protocols for ergonomic device design that accommodates all sensor modalities in a user-friendly form factor.
Modeled and printed the torsional grip spring, performed 3D scans for ergonomic fixtures, and captured training assets for face/gait datasets.
Week 4 - Electronics Design
EDA and schematic design for the aging biomarker device electronics.
EDA toolsSchematic designCircuit design
System Integration Plans: Design comprehensive PCB schematics that integrate force sensor circuits for grip strength measurement, microphone preamplifiers for voice analysis, camera interfaces for facial recognition, and timing circuits for reaction time assessment into a unified electronics platform.
Completed the Fusion 360/KiCad schematic/PCB layout for the ESP32S3 carrier tying together force, audio, camera, reaction, and wearable interfaces.
Week 5 - Electronics Production
PCB fabrication, debugging, and assembly for the biomarker device.
PCB fabricationDebuggingAssembly
System Integration Plans: Fabricate and assemble the integrated PCB containing all sensor interfaces, implementing power management systems for continuous operation and establishing data storage protocols for the multimodal biomarker data collection system.
Fabricated and assembled the carrier PCB, brought up power domains, and verified sensor buses—establishing the electronics backbone for integration.
Week 6 - Computer-controlled Machining
CAM and milling for precision components and device housings.
CAMMillingPrecision machining
System Integration Plans: Machine precision mechanical components for the integrated device housing using computer-controlled milling, ensuring proper alignment and mounting for all sensor modules while maintaining ergonomic design for user comfort during multimodal data collection.
Machined the floating mirror base and tensegrity nodes, refining fixturing that ensures repeatable camera and grip alignment in the final assembly.
Week 7 - Input Devices
Sensors and embedded architectures for data collection in the biomarker device.
SensorsInput devicesData collection
System Integration Plans: Integrate all six input sensor systems (force sensors for grip strength, microphones for voice analysis, cameras for facial recognition and gait analysis, reaction time circuits, and wearable accelerometer) into the unified data collection platform with real-time processing capabilities.
Integrated the force sensor, microphone, and ReactionAge modules on the carrier, logging synchronized packets that exercise the multimodal intake stack.
Week 8 - Output Devices
Actuators and system integration for the biomarker device outputs.
ActuatorsOutput devicesSystem integration
System Integration Plans: Implement output devices including display systems for real-time intrinsic capacity feedback and haptic feedback mechanisms for user interaction, creating an intuitive interface for the multimodal biomarker assessment system.
Deployed the SenseCraft FaceTTD pipeline on the XIAO ESP32S3, implemented OLED dithering previews, and confirmed end-to-end edge inference latency.
Week 9 - Molding & Casting
Forming and resin techniques for bioprinting molds and device components.
MoldingCastingResins
System Integration Plans: Create custom molded components for the bioprinting aspects of the project and develop specialized casings for sensor protection, ensuring the device can withstand continuous use during multimodal data collection sessions.
Machined wax molds, cast Mold Star silicone and Drystone ribs, and prototyped arrow-inspired shells that stabilize the mirror and protect embedded sensors.
Week 10 - Mechanical & Machine Design
Kits and mechanical design for the bioprinting and biomarker device systems.
Mechanical designMachine designSystem integration
System Integration Plans: Complete the mechanical design integration of all system components, implementing calibration protocols for sensor alignment and developing the complete mechanical framework that houses all six digital biomarker measurement systems.
Developed mechanical actuation systems including tapping and swiping mechanisms for phone interaction, integrated camera with Edge AI face detection and Wi-Fi livestreaming, designed and 3D-printed phone holder with amplifier, and prepared comprehensive midterm review documentation with system diagrams and timeline.
Week 11 - Networking & Communications
BLE, Wi-Fi, and communication protocols for the biomarker device connectivity.
BLEWi-FiCommunications
System Integration Plans: Implement wireless communication protocols (Bluetooth/Wi-Fi) for seamless data transmission from all six sensor modalities, enabling real-time data fusion and establishing connectivity for the wearable accelerometer integration into the multimodal assessment system.
Implemented Wi-Fi camera livestreaming for real-time video transmission, developed ESP-NOW networking protocols for device communication, designed and milled PCBs for networking components, and explored Meshtastic for long-range communication capabilities.
Week 12 - Interface & Application Programming
UI and application development for the biomarker device interface.
UI designApplicationsUser interface
System Integration Plans: Develop the complete user interface and application programming for the multimodal system, implementing the machine learning pipeline for intrinsic capacity score calculation and creating cloud integration for comprehensive data storage and analysis of all biomarker measurements.
Created Wi-Fi web interface for real-time pulse oximeter readings with live plotting, developed grip strength measurement device with load cell and integrated GUI, implemented OLED button user interface for device control, and established video streaming capabilities for sensor data visualization.
Week 13 - Wildcard & Final Orders
Final orders and wildcard week activities for project completion.
Final ordersWildcard activitiesProject completion
System Integration Plans: Complete final system integration, testing, and validation of the complete multimodal intrinsic capacity assessment platform, ensuring all six digital biomarkers work cohesively to provide accurate WHO-defined intrinsic capacity scores across all five domains (locomotor, cognition, vitality, sensory, psychological).
Designed and fabricated ATtiny1626 tiny development board with fiber laser PCB engraving, created glass engraving system with UV laser including blinking heart integration for visual feedback, milled mounting holes and completed board assembly, and prepared final board designs for system integration.
System Integration
Final integration week focused on bringing all subsystems together, completing hardware fabrication, firmware integration, and documentation for the MirrorAge system presentation. View full details →
Initial system integration work focused on subsystem validation, CAD model consolidation, and design backbone acquisition for band integration. Conducted comprehensive testing of all subsystems to ensure proper functionality, identified and resoldered defective joints, and exported CAD models of all PCBs into a unified assembly model.
Integrated CAD Model: Exploded isometric view of the complete system assembly, including all PCBs, main housing with transparent enclosure, and wearable band components.
Physical integration of subsystems into the complete demo table assembly, including mechanical component fabrication and electrical board consolidation. Integrated the complete demo table with precise placement of the MirrorAge handgrip subsystem and aging clock subsystem, providing a unified platform for system demonstration.
Complete Demo Table Assembly: Integrated mechanical design showing precise placement of the MirrorAge handgrip subsystem and aging clock subsystem on the demo table.
Continued fabrication work integrating all manufacturing processes. Focused on completing physical components and preparing subsystems for final assembly and testing.
Comprehensive subsystem integration combining 2D fabrication (laser cutting and vinyl cutting), 3D printing (rigid and flexible components), PCB milling (single and double-sided boards), and molding/casting to complete all physical components. Upgraded MirrorAge TFT board to v13 and aging clock TFT board to v16 with optimized component placement and routing. Established reliable I²C bus communication and validated all sensor addresses.
Final integration day focused on closing the watch subsystem, soldering and verifying all double-sided boards, refining molded bands, and assembling the complete MirrorAge demo with both the aging clock and grip-strength subsystems fully wired and tested. Completed rivet installation for plated through-holes, sensor bring-up (accelerometer, pulse oximeter, OLED/TFT displays), and full system integration on the tensegrity demo table. The integrated system successfully demonstrated synchronized sensor readouts and display behavior across all boards.
Final project presentation and demonstration of the complete MirrorAge system. Showcased the integrated aging clock and grip-strength subsystems working together on the demo table, demonstrating real-time sensor data collection and display synchronization. View final presentation demo →
Full Documentation: For complete details, design files, code, and comprehensive documentation of the system integration process, see Week 14: System Integration.
Final Project Masterpiece
Complete demonstration of the integrated MirrorAge system showcasing all subsystems working together in real-time.
Final Presentation Demo: Complete MirrorAge system demonstration showing the integrated aging clock and grip-strength subsystems operating together on the demo table, with synchronized sensor readouts and real-time display updates across all boards.
Complete repository of all design files, CAD models, schematics, PCB layouts, firmware, and fabrication files from Week 0 through Week 14, organized by week and component type.
Note: Additional design files, firmware, and documentation can be found in the respective week pages. Some files are part of larger archives (ZIP files) that contain multiple related design files.
Reflections & Learnings
Comprehensive reflections on the MirrorAge Intrinsic Capacity Mirror project development journey.
Modular system design allows for incremental development and component-level testing throughout the semester
Integration of mechanical, electrical, and software subsystems requires careful planning and coordination
Iterative design and prototyping revealed the importance of early testing and validation
Documentation and knowledge transfer are critical for project continuity and future improvements
The project successfully demonstrates how digital fabrication and embedded systems can create meaningful health assessment tools
Contributions
Acknowledgements and contributions that made this project possible.
Gladyshev Lab and Collaborators
Special thanks to the Gladyshev Lab and collaborators for the fruitful discussions that led to this multimodal intrinsic capacity assessment idea,
which supplements my PhD research goals in aging and longevity. The conceptual framework for integrating multiple digital biomarkers
to assess intrinsic capacity domains emerged from collaborative research discussions on aging biomarkers and healthspan assessment.
Transparent documentation of AI assistance used in this final project work, following course guidelines for ethical AI usage.
📋 General Guidelines: See General Commands for Cursor on the homepage for standard guidelines and commands used consistently throughout documentation development.
Cursor · Project Plan & Weekly Schedule
Comprehensive Cursor AI assistance for outlining the project plan and weekly schedule, including documentation structure, content organization, systematic updates across all week pages and the final project page, media integration, and summary generation workflows.
Cursor AI aligned the midterm review plan with updated system diagram, timeline, and remaining-task summaries, then refreshed finalproject.html to remove legacy bioprinting language and re-point internal links. The full transcript and generated HTML are available for review.
Cursor AI assistance for adding a white background behind the photo in the Final Project Spiral Development Model section on finalproject.html. The image container was updated with white background, padding, and rounded corners for improved visual presentation.
Cursor AI distilled Week 0–9 documentation and the Oct 31 lab meeting deck into midterm-ready narrative, cost, and validation content, replacing every placeholder in finalproject.html.
Transcript archived in markdown and HTML (generated via scripts/md_to_html_converter.py) for transparency.
ChatGPT was used to research and develop the multimodal intrinsic capacity assessment framework, including the comprehensive coverage analysis table and technical pipeline design.
The AI assisted with structuring the WHO-defined intrinsic capacity domains, identifying appropriate digital biomarkers, and designing the fusion architecture for multimodal data processing.
Cursor AI assisted with developing the complete final project page structure, implementing the multimodal intrinsic capacity assessment framework, and creating comprehensive documentation.
The AI helped with HTML structure, responsive design, weekly system integration plans, and organizing the technical documentation for the complete biomarker assessment system.
Cursor AI assisted with finalizing the project presentation structure to ensure full compliance with MIT Academy project presentation requirements.
The AI helped implement all required sections including answering questions, design documentation, bill of materials, individual mastery requirements,
course presentation structure, and spiral model development approach visualization.
ChatGPT was used to discuss camera system implementation strategies, image processing algorithms, and EdgeAI integration approaches.
The AI assisted with understanding Floyd-Steinberg dithering implementation, touch sensor integration, and exploring TinyML deployment options for the XIAO ESP32S3 platform.
AI-Assisted Project Highlights and Camera Subsystem Development
Cursor AI assisted with adding the project highlights section featuring camera system achievements and creating a comprehensive camera subsystem section with detailed code implementations, video demonstrations, and EdgeAI integration documentation.
The AI helped with HTML structure, responsive design, image processing explanations, and organizing the technical documentation for the complete camera system showcase.
Interactive selfie capture system with touch controls and real-time display
Vision Board
Conceptual visualization of the multimodal intrinsic capacity assessment system integrating grip strength, voice analysis, facial recognition, video motion capture, reaction time measurement, and wearable accelerometer data.
Intrinsic Capacity (IC) Coverage by Digital Biomarkers
Domain
Grip
Voice
Face
Video
Reaction Time
Wearable
Locomotor
✅
🔸
🔸
✅
🔸
✅
Cognition
❌
✅
🔸
🔸
✅
🔸
Vitality
✅
✅
✅
✅
🔸
✅
Sensory
❌
✅
✅
✅
✅
🔸
Psychological
❌
✅
✅
✅
🔸
✅
✅ Strong coverage |
🔸 Partial/indirect |
❌ Not covered |
View full table →
Multimodal IC Pipeline
Inputs: Grip Strength, Voice, Face, Video, Reaction Time, Wearable Accelerometer
Development Approach: Following the spiral model methodology, this final project will iterate through multiple development cycles, each building upon previous work while addressing new requirements and risks.
This snapshot covers the subsystems and documentation that will be shown during the midterm review. Links jump directly to the supporting sections with detailed evidence.
Featured Subsystems
Camera subsystem — Edge inference demos and selfie capture loop.
Instructor meeting hold — Thursday, Nov 12 at 10:00 AM ET reserved via the shared HTMAA midterm review sheet.
Execution Schedule (Timeline Snapshot)
Condensed from the Week 8–13 development timeline: each sprint builds toward final integration, mirroring the gantt chart below.
Week 8 · Output Devices: figuring out wiring for real-time display states.
Week 9 · Molding & Casting: learn how to cast custom housings and refine structural components.
Week 10 · Mechanical Design: figure out ergonomic enclosure and calibration fixtures.
Week 11 · Networking: program BLE/Wi-Fi telemetry and wearable data fusion.
Week 12 · Interface/App: create mobile UI, cloud bridge, and IC scoring pipeline.
Week 13 · Final Integration: run validation passes, document results, and prep deployment.
Instructor Review Logistics
Calendar hold sent for Thursday, Nov 12 at 10:00 AM ET (38-501 conference room) per the shared HTMAA scheduling sheet. Agenda covers subsystem demos, weekly documentation spot checks (Weeks 0–9), and next-sprint alignment. Meeting slot referenced in the midterm review schedule; awaiting final confirmation via class Slack.
System Architecture
Updated block diagram highlighting the multimodal sensing stack (grip, voice, face, motion, wearables), on-device inference layers, and real-time feedback channels that feed the intrinsic capacity score.
Development Timeline
Timeline aligns subsystem sprints with HTMAA milestones: output devices (Week 8), molding and casting (Week 9), mechanical design (Week 10), networking and communications (Week 11), app programming (Week 12), and final integration (Week 13).
Remaining Tasks (Snapshot)
Weeks 0–9 locked in the core subsystems—documentation workflow, cutting and molding for the housing, embedded prototypes for reaction timing, SenseCraft camera inference, and early grip/voice rigs. The checklist below captures what still needs to happen to converge on the integrated MirrorAge system.
Hardware Integration
Consolidate grip, voice, camera, reaction-time, and wearable sensor harnesses into the MirrorAge enclosure.
Finish molding/casting iterations for the ergonomic housing and align mounting features for PCBs and haptics.
Firmware & Edge AI
Stabilize onboard inference for SenseCraft vision models and voice-age pipelines on the XIAO ESP32S3.
Calibrate grip-force and reaction-time firmware for repeatable sampling; close the loop to haptic/display feedback.
Networking & Data Fusion
Bring up BLE/Wi-Fi data paths for wearable accelerometer streaming and cloud logging of intrinsic capacity scores.
Implement the fusion layer that combines per-domain scores into an overall IC metric with on-device storage.
Interface & UX
Finish mobile/web dashboard mockups for user onboarding, data review, and device calibration workflows.
Finalize real-time mirror feedback cues (display states, haptics, lighting) tied to sensor status and IC outcomes.
Validation & Documentation
Run end-to-end system tests (sensor capture → fusion → feedback) and document calibration procedures.
Record the one-minute video, finalize final presentation assets, and polish the bill of materials for review.
Week 14 System Integration Plan
Detailed day-by-day schedule for final system integration, covering design, fabrication, programming, testing, and documentation. This plan outlines the path to completing the MirrorAge system integration and preparing for final presentation. View on Week 14 page →
The act of bringing something to a conclusion or ending in a decisive manner. The ability to efficiently finish tasks and projects with a goal-oriented mindset.
Wednesday
Morning
Publish system integration plan on website
Update weekly assignment sections on final project page (weeks 10-13)
Link final project design files
Update reflections and learnings
Update picture of prism holder
Add final pictures to Slack canvases
Create schematic between boards (wired and wireless) — updated system diagram on PPT-like page
Start CAD model of system
Place final order
Afternoon & Evening
Design:
Boards: Combine OLED screen/accelerometer with pulse oximeter board in a new board (maybe upgrade to small TFT as minor)
Boards: Speaker board with realtime amplifier and TFT (on the load cell fixed board)
Band: Mold design
Cases: 3D print mountable cases for the boards
Integrate designs into final CAD
Document design
Finish CAD model of system
Thursday
Fabricate
Milling boards
Print mold and cast band
Print cases
Solder
Solder components on milled boards
Connect boards with wired (and wireless connection codes)
Finishing
Mirror on screen (easy way with the film)
Documentation
Document fabrication
Friday
Programming
Board level codes
Server level codes
Documentation
Document codes
Completion
Finish anything else
Saturday
Programming & Testing
Demo integrated system
Test integrated system
Documentation
Document testing and evaluation
Review and complete documentation (list of questions)
Make the video by collaging documentation
Sunday
Fill up any gaps
Prepare demo on tensegrity table
Finalize 1-slide
Work on minors
If done, work on if there's time
Monday Morning
Transport demo on tensegrity table
Fill up any gaps
Work on minors
Specific Tasks to Complete This Week
Major Tasks
CAD model of system
Speaker board with realtime amplifier
Combine screen/accelerometer with pulse oximeter board in a new board
Mold and cast band
Design and fabricate casing (print)
Schematic between boards (wired and wireless) — updated system diagram on PPT-like page
Serial connection between pulse oximeter and tiny blinking heart for BPM (BPM from IR, SpO2 from delta)
Combine multiple boards on the same WiFi (switching tabs is easy way, board hosting the webpage querying and update or Python-based server somewhere where everything posting data, Raspberry Pi)
Put+program everything together according to the above (with WiFi for now)
MirrorAge is a self-contained edge-AI mirror that captures grip strength, facial imagery, voice, motion, and reaction time to estimate intrinsic capacity in real time.
The platform fuses weekly prototypes—ReactionAge latency tests, 3D printed grip mechanics, SenseCraft camera inference, and molded structural elements—into a multimodal mortality risk profiler.
Subsystems in progress: reaction-time module, SenseCraft FaceTTD inference stack, VoiceAge microphone pipeline, wearable streaming via BLE, and molded structural packaging.
Clinical motivation: translate WHO intrinsic capacity domains into measurable digital biomarkers that flag functional decline earlier than chronological age alone.
Project Goals
Deliver multimodal IC scoring Fuse grip, face, voice, reaction-time, and wearable streams on-device to output an intrinsic capacity score plus domain deltas.
Fabricate modular, serviceable hardware Iterate laser-cut tensegrity mirror shells, 3D printed torsional grips, custom PCBs, and silicone cast fixtures that assemble without bespoke tooling.
Validate against ground truth Benchmark embedded inferences against published datasets (Blomkvist et al. 2017, Fuentealba et al. 2025) and lab-collected pilots to quantify accuracy, latency, and reliability.
Timeline & Milestones
Week 10 · Hardware convergence Integrate SenseCraft FaceTTD camera, ReactionAge latency module, and newly milled PCB into a single ESP32S3 backplane.
Week 12 · Midterm review build Finish molded mirror enclosure, bring up BLE wearable link, and demo live IC score during midterm critique.
Final week · Validation & documentation Execute pilot data collection, refine model weights, and release reproducible fabrication + firmware packages.
Documenting the final project masterpiece that integrates the range of units covered, addressing all required questions.
What does it do?
MirrorAge captures synchronized digital biomarkers—camera frames processed with on-device FaceTTD models, VoiceAge microphone samples, grip strength torque, wearable accelerometry, and ReactionAge latency—to estimate intrinsic capacity and time-to-death acceleration.
A XIAO ESP32S3 Sense orchestrates sensing, performs Edge Impulse inference, and displays a live mortality-risk score on the OLED while logging packets to a Python analytics notebook.
Who's done what beforehand?
The concept builds on WHO intrinsic capacity framing and recent mortality-risk studies: Niccoli & Partridge (2012) establish age as the dominant chronic-disease predictor; Fuentealba et al. (Nature Aging 2025) show blood-based IC clocks outperform chronological models;
Zhavoronkov & Bhullar (2015) and Lancet Healthy Longevity editorials motivate treating functional decline as the actionable signal.
This project translates those findings into an accessible, multimodal measurement mirror that can operate outside hospital labs.
What sources did you use?
Primary references include Nature Aging 2025 intrinsic capacity papers, the PLOS ONE ReactionAge dataset (Blomkvist et al. 2017), Edge Impulse SenseCraft documentation, Smooth‑On Mold Star technical bulletins, RotoMetals alloy certificates, MIT HTMAA recitations, and the open-source GRPR grip-strength meter.
Design inspiration and safety notes were consolidated from Anthony Pennes' HTMA guides and Fab Academy molding tutorials.
What did you design?
• Laser-cut cardboard origami mirror frame and tensegrity-inspired floating mount (Weeks 1 & 6)
• ReactionAge firmware + enclosure with statistical post-processing dashboards (Week 2)
• 3D printed torsional spring grip module tuned for ±40 kg ranges (Week 3)
• KiCad/Fusion carrier PCB for the ESP32S3 Sense with OLED, force, and BLE breakouts (Week 5)
• Edge Impulse deployment pipeline with grayscale dithering overlay and live inference UX (Weeks 7–8)
• CAM toolpaths, silicone molds, and Drystone casts for structural packaging (Week 9)
What materials and components were used?
Seeed XIAO ESP32S3 Sense module with OV2640 camera and PDM mic, SparkFun Qwiic button and force sensors, SSD1306 OLED, wearable IMU node (Bosch BHI260), laser-cut cardboard/birch sheets, PLA+/Onyx filament, Mold Star 30 silicone, Drystone gypsum, Roto281 fusible alloy, and embedded fasteners/heat-set inserts.
Where did they come from?
Electronics from Seeed Studio, SparkFun, Digi-Key, and Adafruit; molding supplies and silicones from Reynolds Advanced Materials; Drystone and Hydro-Stone from USG via the MIT CBA stockroom; fusible alloys from RotoMetals; structural lumber and plywood from MIT's shop inventory; filaments from Prusa Research and Markforged.
How much did they cost?
Current spend: $96.34 for ReactionAge components (Week 2 BOM) + $78.42 for SenseCraft camera stack (XIAO ESP32S3 Sense, OLED, cabling) + $42.10 for molding media (Mold Star 30 quart, Drystone, release agents) = $216.86 to date.
Remaining allocation (~$130) is earmarked for BLE wearable hardware and final enclosure finishes; detailed line items tracked in the Airtable budget and mirrored in each weekly BOM CSV.
What parts and systems were made?
Custom origami mirror frame, 3D printed torsional grip shell, machined floating base, silicone molds and Drystone casts for arrow-inspired structural ribs, bespoke ESP32S3 breakout PCB, laser-cut ReactionAge control panel, and assembled sensor tower linking camera, OLED, and wearable gateway.
What tools and processes were used?
Parametric CAD in Fusion 360, laser cutting (Epilog) for origami tiles, Prusa MK4 FDM printing, Formlabs SLA for detail inserts, ShopBot CNC and Bantam PCB milling, silicone mixing/casting under vacuum, Edge Impulse model training, PlatformIO firmware, and Python/NumPy validation notebooks.
What questions were answered?
• Can consumer-grade sensors reproduce published reaction-time age curves? (Yes—ReactionAge matched Blomkvist et al. regression within 4.6 ms RMSE.)
• Will SenseCraft FaceTTD run locally on ESP32S3 with acceptable latency? (Yes—~310 ms/inference at 30% baseline accuracy, highlighting dataset needs.)
• Does molded packaging improve sensor placement repeatability? (Yes—silicone nests held camera ±0.5 mm, reducing alignment drift seen in cardboard prototypes.)
What worked? What didn't?
✅ Floyd–Steinberg dithering produced clear OLED previews; ✅ ReactionAge firmware maintained ±1 ms jitter; ✅ Molded Drystone ribs stiffened mirror shell without excess weight.
⚠️ FaceTTD accuracy plateaued at 30% due to limited training diversity; ⚠️ VoiceAge requires more MFCC samples to sustain 0.64-year MAE; ⚠️ Grip spring fatigue highlighted need for fiber-reinforced print or machined aluminum insert.
How was it evaluated?
Bench tests compare embedded predictions to published curves and desktop baselines: ReactionAge latency vs. Wii Balance Board golden data; FaceTTD inferencing cross-validated against Edge Impulse cloud classifier; VoiceAge MFCC regression verified through train/holdout splits; mechanical fixtures inspected with feeler gauges and dial indicators for tolerance drift.
What are the implications?
A portable intrinsic capacity mirror supports proactive geriatric screening, telehealth coaching, and longitudinal studies that correlate functional decline with interventions.
By grounding hardware in open-source parts and HTMAA fabrication methods, the system can be replicated across labs and community clinics to accelerate validation of digital aging biomarkers and personalize longevity therapies.
Design
Your project should incorporate 2D and 3D design, multiple additive and subtractive fabrication processes, electronics design and production, embedded microcontroller design, interfacing, and programming, system integration and packaging.
2D Design
2D design work for the multimodal intrinsic capacity assessment system:
Cardboard origami tiling for circular mirror frame, optimized for kerf learned during Week 1 laser characterization.
Vinyl-cut ReactionAge control labels and MirrorAge fascia decals for rapid UI readability.
KiCad/Fusion schematics + polygon pours for ESP32S3 carrier, force sensing front-end, and OLED interposer.
2D shop drawings for CNC floating base, including registration dowels and silicone mold parting lines.
Figma wireframes outlining the midterm web dashboard and on-device OLED states.
Subtractive: Laser cutting, milling for precision parts
Electronics: PCB design and production
Programming: Embedded microcontroller development
Bill of Materials
Where possible, I fabricated parts rather than buying them. This table summarizes all unique components in the final MirrorAge system, their approximate costs, and where they are used.
A mirrored copy of this bill of materials also appears on the Week 14 system-integration page for cross-linking directly from the integration steps
(Week 14 BOM).
Grip-strength molds, band molds, structural ribs
(Week 9,
Week 14)
Fasteners
M2/M3 hardware, heat-set inserts, misc. screws
Assorted
~$0.10–$0.30 ea.
$20.00 (bundle)
All mechanical assemblies (watch, grip rig, camera mount, demo table)
Estimated Total Project Cost
Electronics ≈ $190 · Mechanical & materials ≈ $130 ·
Total ≈ $320 (excluding lab-provided consumables and reused stock).
Exact per-week line items remain in the weekly documentation tables (for example
ReactionAge BOM CSV in Week 2),
while this table captures the consolidated, unique parts that make up the final integrated MirrorAge system.
Fabrication Process
Week-by-week fabrication rolled forward subsystems toward the integrated mirror:
Week 1 laser-cut origami tiles for the circular bezel; Week 2 PCB milling + soldering for ReactionAge;
Week 3–4 torsional spring 3D prints and sanding jigs; Week 5 copper-clad milling and reflow of the ESP32S3 carrier;
Week 6 ShopBot machining of the floating base; Week 8 resin + FDM camera enclosure build; Week 9 wax machining, Mold Star casting, and Drystone ribs.
Each step captured feeds-and-speeds, toolpaths, and fixturing photos embedded in the weekly pages for replication.
Testing & Validation
Validation combined bench instrumentation and statistical analysis: oscilloscope timing to verify ReactionAge jitter, Edge Impulse confusion matrices for FaceTTD and VoiceAge,
Instron pull tests for the torsional grip cartridge, IR thermography while curing Mold Star molds, dial-indicator checks on CNC-machined bases, and adhesive shear testing on mirror mounts.
Data are logged to CSV via the ESP32S3 and compared against published baselines inside the midterm Jupyter notebook.
Individual Mastery and Independent Operation
Projects can be separate or joint, but need to show individual mastery of the skills, and be independently operable.
Individual Mastery
Demonstration of individual skills across all course units:
2D and 3D Design
Modeled the tensegrity floating mirror, torsional grip shells, and camera bezel in Fusion 360 and Onshape.
Drove design reviews with Anthony/Neil to lock tolerances, assembly order, and module interface specs.
Demonstrates mastery across cutting, 3D printing, machining, electronics, networking, and interface programming units.
Documentation cross-linked via weekly pages, GitHub repos, and BOM spreadsheets for traceability.
Group Assignments
Collaborative work and individual contributions:
Embedded programming group: authored workflow trade-off analysis and repo organization that seeded ReactionAge firmware patterns.
Molding & casting group: led SDS review, material trials, and mixing SOP that informed final mirror mold.
Shared camera dev sessions with peers to improve Edge Impulse dataset collection and SenseCraft deployment strategies.
Useful Documentation
Helpful resources, documentation, and design files for the multimodal intrinsic capacity assessment system.
Open Source Grip Strength Meter
A cost-effective $50 grip strength measurement system that can be further optimized for our multimodal assessment platform.
This open-source design provides an excellent foundation for integrating grip strength measurement into our intrinsic capacity assessment system,
with potential for cost reduction through signal multiplexing on a single processor.
Detailed technical pipeline for processing multiple digital biomarkers to generate intrinsic capacity scores.
Pipeline Architecture
Inputs
• Grip Strength
• Voice
• Face
• Video (motion/gait)
• Reaction Time
• Wearable Accelerometer
→
Feature Extraction
Strength metrics
Prosody features
Facial landmarks
Gait parameters
Response latency
Activity patterns
Embeddings
Features converted to vector representations for multimodal fusion
→
Fusion Layer
Combines multimodal features using attention mechanisms
Output
• Overall IC Score
• Domain sub-scores
→
Domain Scores
Locomotor
Cognition
Vitality
Sensory
Psychological
Weekly System Development Breakdown
How each week of HTMAA 2025 builds toward the complete multimodal intrinsic capacity assessment system.
Week 0: Project Ideation
Initial concept development and planning
Project planning and documentation structure
Research direction and concept sketches
Week 1: Precision Cutting
Laser and vinyl cutting techniques
Device housing components via laser cutting
Sensor mounting brackets and enclosures
Vinyl cutting for device labeling and UI elements
Week 2: Embedded Programming
Electronics basics and microcontroller programming
Microcontroller programming for data collection
Basic sensor interface circuits
Week 3: 3D Scanning & Printing
3D technologies for device components
3D scanning for custom component design
3D printing for device housings
Week 4: Electronics Design
EDA and schematic design
PCB design for grip strength measurement
Sensor interface circuits and signal conditioning
Power management and data storage systems
Week 5: Electronics Production
PCB fabrication and assembly
PCB fabrication and debugging
Component assembly and testing
Week 6: Computer-controlled Machining
CAM and precision milling
Precision components via milling
Custom mechanical parts
Week 7: Input Devices
Sensor integration for data collection
Force sensors for grip strength measurement
Microphones for voice analysis
Camera systems for facial expression analysis
Reaction time measurement circuits
Week 8: Output Devices
Actuators and system integration
Display systems for real-time feedback
Haptic feedback for user interaction
Week 9: Molding & Casting
Forming and resin techniques
3D printing and molding for custom components
Silicone casting for device components
Week 10: Mechanical & Machine Design
System integration and mechanical design
Mechanical design for ergonomic device housing
System integration and calibration protocols
Week 11: Networking & Communications
Connectivity and communication protocols
Bluetooth/Wi-Fi connectivity for data transmission
Wearable accelerometer integration and data fusion
Week 12: Interface & Application Programming
UI development and application programming
Mobile app development for user interface
Cloud integration for data storage and analysis
Machine learning pipeline for IC score calculation
Week 13: Wildcard & Final Integration
Final orders and complete system deployment
Final testing, validation, and documentation
System integration and deployment
Camera Subsystem
Advanced camera system implementation using XIAO ESP32S3 Sense with real-time image processing, EdgeAI integration, and interactive selfie capture functionality.
System Overview
The camera system successfully captures images, processes them into bitmaps, and displays them on an OLED screen using advanced Floyd-Steinberg dithering algorithms.
Video Demonstrations
Camera Bot Selfie
Demonstration of the interactive selfie capture system with touch controls
Picture of Picture
Meta demonstration showing the camera system capturing its own display
Code Implementation
60-Second Auto Capture System
Automated camera system that captures and displays images every 60 seconds using advanced image processing techniques.
1. Initialize camera with PSRAM frame buffers
2. Configure OLED display (128x64 pixels)
3. Set up 60-second capture interval timer
4. In main loop:
a. Check if 60 seconds have elapsed
b. Capture image from camera
c. Process image:
- Downsample to 128x64 via box averaging
- Apply contrast stretch (linear scaling)
- Perform Floyd-Steinberg dithering
d. Display processed bitmap on OLED
e. Release frame buffer
5. Repeat process
Touch-Controlled Capture System
Interactive camera system with touch controls allowing manual capture triggers in addition to automatic timing.
1. Initialize camera and OLED display
2. Set up touch pins (GPIO1 & GPIO2) with threshold detection
3. Configure 60-second auto-capture timer
4. In main loop:
a. Update touch sensor readings
b. Detect touch press events (justPressed)
c. Check for capture trigger:
- Touch press OR 60-second timer elapsed
d. If triggered:
- Capture image from camera
- Process image (same as auto version)
- Display on OLED
- Reset timer
5. Continue monitoring for next trigger
The system captures photos, converts them to bitmaps using advanced image processing algorithms, and displays them on the OLED screen.
I'm also exploring integration with ML models, either through online API calls or by embedding TinyML model parameters from Python to C++.
Future development includes live streaming real-time video with ML prediction updates based on variable observation times,
and exploring Edge Impulse models as an alternative to manual Python-to-C++ conversion for faster deployment.
EdgeAI/TinyML Integration
Edge AI can also be implemented using Edge Impulse models, which may be faster than manually converting Python models to C++.
The SenseCraft AI platform provides a streamlined approach to training and deploying ML models directly on the XIAO ESP32S3.
Deploy inference bundle to the SenseCraft board alongside the camera stack.
Benchmark latency and accuracy against baseline VoiceAge models and document calibration protocol.
Week 0 - Introduction & Design
Project ideation and initial concept development for bioprinting rejuvenated tissue and aging biomarker devices.
Project planningConcept sketchesResearch direction
System Integration Plans: Establish the foundational architecture for multimodal data collection by designing the overall system framework that will integrate all six digital biomarkers (grip strength, voice, face, video, reaction time, wearable accelerometer) into a cohesive intrinsic capacity assessment platform.
Mapped the MirrorAge subsystem architecture, assembled the intrinsic capacity literature stack, and kicked off BRR/IRB coordination so fabrication sprints stay aligned with clinical requirements.
Week 1 - Principles & Cutting
Version control, laser cutting, and vinyl cutting techniques applied to final project components.
Laser cuttingVinyl cuttingVersion control
System Integration Plans: Fabricate precision-cut housing components and mounting brackets for all sensor modules (force sensors, microphones, cameras, reaction time circuits) using laser cutting, while creating vinyl-cut labels and UI elements for device identification and user guidance.
Characterized laser kerf, produced the origami mirror frame tiles, and generated vinyl interface labels—locking in enclosure dimensions and user UI cues for the mirror shell.
Week 2 - Embedded Programming
Electronics basics and embedded programming for the aging biomarker device components.
MicrocontrollersProgrammingElectronics
System Integration Plans: Develop embedded programming protocols for real-time data collection from all six biomarker sensors, implementing initial signal processing algorithms and establishing the communication framework for multimodal data fusion.
Built the ReactionAge firmware + enclosure, published the first BOM, and validated timing pipelines that will feed the MirrorAge IC fusion engine.
Week 3 - 3D Scanning & Printing
3D scanning and printing techniques for bioprinting components and device housings.
3D scanning3D printingAI tools
System Integration Plans: Create custom 3D-printed components for camera mounting systems and facial recognition hardware, while developing 3D scanning protocols for ergonomic device design that accommodates all sensor modalities in a user-friendly form factor.
Modeled and printed the torsional grip spring, performed 3D scans for ergonomic fixtures, and captured training assets for face/gait datasets.
Week 4 - Electronics Design
EDA and schematic design for the aging biomarker device electronics.
EDA toolsSchematic designCircuit design
System Integration Plans: Design comprehensive PCB schematics that integrate force sensor circuits for grip strength measurement, microphone preamplifiers for voice analysis, camera interfaces for facial recognition, and timing circuits for reaction time assessment into a unified electronics platform.
Completed the Fusion 360/KiCad schematic/PCB layout for the ESP32S3 carrier tying together force, audio, camera, reaction, and wearable interfaces.
Week 5 - Electronics Production
PCB fabrication, debugging, and assembly for the biomarker device.
PCB fabricationDebuggingAssembly
System Integration Plans: Fabricate and assemble the integrated PCB containing all sensor interfaces, implementing power management systems for continuous operation and establishing data storage protocols for the multimodal biomarker data collection system.
Fabricated and assembled the carrier PCB, brought up power domains, and verified sensor buses—establishing the electronics backbone for integration.
Week 6 - Computer-controlled Machining
CAM and milling for precision components and device housings.
CAMMillingPrecision machining
System Integration Plans: Machine precision mechanical components for the integrated device housing using computer-controlled milling, ensuring proper alignment and mounting for all sensor modules while maintaining ergonomic design for user comfort during multimodal data collection.
Machined the floating mirror base and tensegrity nodes, refining fixturing that ensures repeatable camera and grip alignment in the final assembly.
Week 7 - Input Devices
Sensors and embedded architectures for data collection in the biomarker device.
SensorsInput devicesData collection
System Integration Plans: Integrate all six input sensor systems (force sensors for grip strength, microphones for voice analysis, cameras for facial recognition and gait analysis, reaction time circuits, and wearable accelerometer) into the unified data collection platform with real-time processing capabilities.
Integrated the force sensor, microphone, and ReactionAge modules on the carrier, logging synchronized packets that exercise the multimodal intake stack.
Week 8 - Output Devices
Actuators and system integration for the biomarker device outputs.
ActuatorsOutput devicesSystem integration
System Integration Plans: Implement output devices including display systems for real-time intrinsic capacity feedback and haptic feedback mechanisms for user interaction, creating an intuitive interface for the multimodal biomarker assessment system.
Deployed the SenseCraft FaceTTD pipeline on the XIAO ESP32S3, implemented OLED dithering previews, and confirmed end-to-end edge inference latency.
Week 9 - Molding & Casting
Forming and resin techniques for bioprinting molds and device components.
MoldingCastingResins
System Integration Plans: Create custom molded components for the bioprinting aspects of the project and develop specialized casings for sensor protection, ensuring the device can withstand continuous use during multimodal data collection sessions.
Machined wax molds, cast Mold Star silicone and Drystone ribs, and prototyped arrow-inspired shells that stabilize the mirror and protect embedded sensors.
Week 10 - Mechanical & Machine Design
Kits and mechanical design for the bioprinting and biomarker device systems.
Mechanical designMachine designSystem integration
System Integration Plans: Complete the mechanical design integration of all system components, implementing calibration protocols for sensor alignment and developing the complete mechanical framework that houses all six digital biomarker measurement systems.
Developed mechanical actuation systems including tapping and swiping mechanisms for phone interaction, integrated camera with Edge AI face detection and Wi-Fi livestreaming, designed and 3D-printed phone holder with amplifier, and prepared comprehensive midterm review documentation with system diagrams and timeline.
Week 11 - Networking & Communications
BLE, Wi-Fi, and communication protocols for the biomarker device connectivity.
BLEWi-FiCommunications
System Integration Plans: Implement wireless communication protocols (Bluetooth/Wi-Fi) for seamless data transmission from all six sensor modalities, enabling real-time data fusion and establishing connectivity for the wearable accelerometer integration into the multimodal assessment system.
Implemented Wi-Fi camera livestreaming for real-time video transmission, developed ESP-NOW networking protocols for device communication, designed and milled PCBs for networking components, and explored Meshtastic for long-range communication capabilities.
Week 12 - Interface & Application Programming
UI and application development for the biomarker device interface.
UI designApplicationsUser interface
System Integration Plans: Develop the complete user interface and application programming for the multimodal system, implementing the machine learning pipeline for intrinsic capacity score calculation and creating cloud integration for comprehensive data storage and analysis of all biomarker measurements.
Created Wi-Fi web interface for real-time pulse oximeter readings with live plotting, developed grip strength measurement device with load cell and integrated GUI, implemented OLED button user interface for device control, and established video streaming capabilities for sensor data visualization.
Week 13 - Wildcard & Final Orders
Final orders and wildcard week activities for project completion.
Final ordersWildcard activitiesProject completion
System Integration Plans: Complete final system integration, testing, and validation of the complete multimodal intrinsic capacity assessment platform, ensuring all six digital biomarkers work cohesively to provide accurate WHO-defined intrinsic capacity scores across all five domains (locomotor, cognition, vitality, sensory, psychological).
Designed and fabricated ATtiny1626 tiny development board with fiber laser PCB engraving, created glass engraving system with UV laser including blinking heart integration for visual feedback, milled mounting holes and completed board assembly, and prepared final board designs for system integration.
System Integration
Final integration week focused on bringing all subsystems together, completing hardware fabrication, firmware integration, and documentation for the MirrorAge system presentation. View full details →
Initial system integration work focused on subsystem validation, CAD model consolidation, and design backbone acquisition for band integration. Conducted comprehensive testing of all subsystems to ensure proper functionality, identified and resoldered defective joints, and exported CAD models of all PCBs into a unified assembly model.
Integrated CAD Model: Exploded isometric view of the complete system assembly, including all PCBs, main housing with transparent enclosure, and wearable band components.
Physical integration of subsystems into the complete demo table assembly, including mechanical component fabrication and electrical board consolidation. Integrated the complete demo table with precise placement of the MirrorAge handgrip subsystem and aging clock subsystem, providing a unified platform for system demonstration.
Complete Demo Table Assembly: Integrated mechanical design showing precise placement of the MirrorAge handgrip subsystem and aging clock subsystem on the demo table.
Continued fabrication work integrating all manufacturing processes. Focused on completing physical components including 2D laser cutting, 3D printing of rigid and flexible components, and PCB milling to prepare subsystems for final assembly and testing.
TPU Band Print: Flexible wearable band component printed using TPU material
Flexible Band: TPU band demonstrating material properties and print quality
Comprehensive subsystem integration combining 2D fabrication (laser cutting and vinyl cutting), 3D printing (rigid and flexible components), PCB milling (single and double-sided boards), and molding/casting to complete all physical components. Upgraded MirrorAge TFT board to v13 and aging clock TFT board to v16 with optimized component placement and routing. Established reliable I²C bus communication and validated all sensor addresses.
Final integration day focused on closing the watch subsystem, soldering and verifying all double-sided boards, refining molded bands, and assembling the complete MirrorAge demo with both the aging clock and grip-strength subsystems fully wired and tested. Completed rivet installation for plated through-holes, sensor bring-up (accelerometer, pulse oximeter, OLED/TFT displays), and full system integration on the tensegrity demo table. The integrated system successfully demonstrated synchronized sensor readouts and display behavior across all boards.
Final project presentation and demonstration of the complete MirrorAge system. Showcased the integrated aging clock and grip-strength subsystems working together on the demo table, demonstrating real-time sensor data collection and display synchronization. View final presentation demo →
Full Documentation: For complete details, design files, code, and comprehensive documentation of the system integration process, see Week 14: System Integration.
Final Project Masterpiece
Complete demonstration of the integrated MirrorAge system showcasing all subsystems working together in real-time.
Final Presentation Demo: Complete MirrorAge system demonstration showing the integrated aging clock and grip-strength subsystems operating together on the demo table, with synchronized sensor readouts and real-time display updates across all boards.
Complete repository of all design files, CAD models, schematics, PCB layouts, firmware, and fabrication files from Week 0 through Week 14, organized by week and component type.
Note: Additional design files, firmware, and documentation can be found in the respective week pages. Some files are part of larger archives (ZIP files) that contain multiple related design files.
Reflections & Learnings
Comprehensive reflections on the MirrorAge Intrinsic Capacity Mirror project development journey.
Modular system design allows for incremental development and component-level testing throughout the semester
Integration of mechanical, electrical, and software subsystems requires careful planning and coordination
Iterative design and prototyping revealed the importance of early testing and validation
Documentation and knowledge transfer are critical for project continuity and future improvements
The project successfully demonstrates how digital fabrication and embedded systems can create meaningful health assessment tools
Contributions
Acknowledgements and contributions that made this project possible.
Gladyshev Lab and Collaborators
Special thanks to the Gladyshev Lab and collaborators for the fruitful discussions that led to this multimodal intrinsic capacity assessment idea,
which supplements my PhD research goals in aging and longevity. The conceptual framework for integrating multiple digital biomarkers
to assess intrinsic capacity domains emerged from collaborative research discussions on aging biomarkers and healthspan assessment.
Transparent documentation of AI assistance used in this final project work, following course guidelines for ethical AI usage.
📋 General Guidelines: See General Commands for Cursor on the homepage for standard guidelines and commands used consistently throughout documentation development.
Cursor · Project Plan & Weekly Schedule
Comprehensive Cursor AI assistance for outlining the project plan and weekly schedule, including documentation structure, content organization, systematic updates across all week pages and the final project page, media integration, and summary generation workflows.
Cursor AI aligned the midterm review plan with updated system diagram, timeline, and remaining-task summaries, then refreshed finalproject.html to remove legacy bioprinting language and re-point internal links. The full transcript and generated HTML are available for review.
Cursor AI assistance for adding a white background behind the photo in the Final Project Spiral Development Model section on finalproject.html. The image container was updated with white background, padding, and rounded corners for improved visual presentation.
Cursor AI distilled Week 0–9 documentation and the Oct 31 lab meeting deck into midterm-ready narrative, cost, and validation content, replacing every placeholder in finalproject.html.
Transcript archived in markdown and HTML (generated via scripts/md_to_html_converter.py) for transparency.
ChatGPT was used to research and develop the multimodal intrinsic capacity assessment framework, including the comprehensive coverage analysis table and technical pipeline design.
The AI assisted with structuring the WHO-defined intrinsic capacity domains, identifying appropriate digital biomarkers, and designing the fusion architecture for multimodal data processing.
Cursor AI assisted with developing the complete final project page structure, implementing the multimodal intrinsic capacity assessment framework, and creating comprehensive documentation.
The AI helped with HTML structure, responsive design, weekly system integration plans, and organizing the technical documentation for the complete biomarker assessment system.
Cursor AI assisted with finalizing the project presentation structure to ensure full compliance with MIT Academy project presentation requirements.
The AI helped implement all required sections including answering questions, design documentation, bill of materials, individual mastery requirements,
course presentation structure, and spiral model development approach visualization.
ChatGPT was used to discuss camera system implementation strategies, image processing algorithms, and EdgeAI integration approaches.
The AI assisted with understanding Floyd-Steinberg dithering implementation, touch sensor integration, and exploring TinyML deployment options for the XIAO ESP32S3 platform.
AI-Assisted Project Highlights and Camera Subsystem Development
Cursor AI assisted with adding the project highlights section featuring camera system achievements and creating a comprehensive camera subsystem section with detailed code implementations, video demonstrations, and EdgeAI integration documentation.
The AI helped with HTML structure, responsive design, image processing explanations, and organizing the technical documentation for the complete camera system showcase.
Interactive selfie capture system with touch controls and real-time display
Vision Board
Conceptual visualization of the multimodal intrinsic capacity assessment system integrating grip strength, voice analysis, facial recognition, video motion capture, reaction time measurement, and wearable accelerometer data.
Intrinsic Capacity (IC) Coverage by Digital Biomarkers
Domain
Grip
Voice
Face
Video
Reaction Time
Wearable
Locomotor
✅
🔸
🔸
✅
🔸
✅
Cognition
❌
✅
🔸
🔸
✅
🔸
Vitality
✅
✅
✅
✅
🔸
✅
Sensory
❌
✅
✅
✅
✅
🔸
Psychological
❌
✅
✅
✅
🔸
✅
✅ Strong coverage |
🔸 Partial/indirect |
❌ Not covered |
View full table →
Multimodal IC Pipeline
Inputs: Grip Strength, Voice, Face, Video, Reaction Time, Wearable Accelerometer
Development Approach: Following the spiral model methodology, this final project will iterate through multiple development cycles, each building upon previous work while addressing new requirements and risks.
This snapshot covers the subsystems and documentation that will be shown during the midterm review. Links jump directly to the supporting sections with detailed evidence.
Featured Subsystems
Camera subsystem — Edge inference demos and selfie capture loop.
Instructor meeting hold — Thursday, Nov 12 at 10:00 AM ET reserved via the shared HTMAA midterm review sheet.
Execution Schedule (Timeline Snapshot)
Condensed from the Week 8–13 development timeline: each sprint builds toward final integration, mirroring the gantt chart below.
Week 8 · Output Devices: figuring out wiring for real-time display states.
Week 9 · Molding & Casting: learn how to cast custom housings and refine structural components.
Week 10 · Mechanical Design: figure out ergonomic enclosure and calibration fixtures.
Week 11 · Networking: program BLE/Wi-Fi telemetry and wearable data fusion.
Week 12 · Interface/App: create mobile UI, cloud bridge, and IC scoring pipeline.
Week 13 · Final Integration: run validation passes, document results, and prep deployment.
Instructor Review Logistics
Calendar hold sent for Thursday, Nov 12 at 10:00 AM ET (38-501 conference room) per the shared HTMAA scheduling sheet. Agenda covers subsystem demos, weekly documentation spot checks (Weeks 0–9), and next-sprint alignment. Meeting slot referenced in the midterm review schedule; awaiting final confirmation via class Slack.
System Architecture
Updated block diagram highlighting the multimodal sensing stack (grip, voice, face, motion, wearables), on-device inference layers, and real-time feedback channels that feed the intrinsic capacity score.
Development Timeline
Timeline aligns subsystem sprints with HTMAA milestones: output devices (Week 8), molding and casting (Week 9), mechanical design (Week 10), networking and communications (Week 11), app programming (Week 12), and final integration (Week 13).
Remaining Tasks (Snapshot)
Weeks 0–9 locked in the core subsystems—documentation workflow, cutting and molding for the housing, embedded prototypes for reaction timing, SenseCraft camera inference, and early grip/voice rigs. The checklist below captures what still needs to happen to converge on the integrated MirrorAge system.
Hardware Integration
Consolidate grip, voice, camera, reaction-time, and wearable sensor harnesses into the MirrorAge enclosure.
Finish molding/casting iterations for the ergonomic housing and align mounting features for PCBs and haptics.
Firmware & Edge AI
Stabilize onboard inference for SenseCraft vision models and voice-age pipelines on the XIAO ESP32S3.
Calibrate grip-force and reaction-time firmware for repeatable sampling; close the loop to haptic/display feedback.
Networking & Data Fusion
Bring up BLE/Wi-Fi data paths for wearable accelerometer streaming and cloud logging of intrinsic capacity scores.
Implement the fusion layer that combines per-domain scores into an overall IC metric with on-device storage.
Interface & UX
Finish mobile/web dashboard mockups for user onboarding, data review, and device calibration workflows.
Finalize real-time mirror feedback cues (display states, haptics, lighting) tied to sensor status and IC outcomes.
Validation & Documentation
Run end-to-end system tests (sensor capture → fusion → feedback) and document calibration procedures.
Record the one-minute video, finalize final presentation assets, and polish the bill of materials for review.
Week 14 System Integration Plan
Detailed day-by-day schedule for final system integration, covering design, fabrication, programming, testing, and documentation. This plan outlines the path to completing the MirrorAge system integration and preparing for final presentation. View on Week 14 page →
The act of bringing something to a conclusion or ending in a decisive manner. The ability to efficiently finish tasks and projects with a goal-oriented mindset.
Wednesday
Morning
Publish system integration plan on website
Update weekly assignment sections on final project page (weeks 10-13)
Link final project design files
Update reflections and learnings
Update picture of prism holder
Add final pictures to Slack canvases
Create schematic between boards (wired and wireless) — updated system diagram on PPT-like page
Start CAD model of system
Place final order
Afternoon & Evening
Design:
Boards: Combine OLED screen/accelerometer with pulse oximeter board in a new board (maybe upgrade to small TFT as minor)
Boards: Speaker board with realtime amplifier and TFT (on the load cell fixed board)
Band: Mold design
Cases: 3D print mountable cases for the boards
Integrate designs into final CAD
Document design
Finish CAD model of system
Thursday
Fabricate
Milling boards
Print mold and cast band
Print cases
Solder
Solder components on milled boards
Connect boards with wired (and wireless connection codes)
Finishing
Mirror on screen (easy way with the film)
Documentation
Document fabrication
Friday
Programming
Board level codes
Server level codes
Documentation
Document codes
Completion
Finish anything else
Saturday
Programming & Testing
Demo integrated system
Test integrated system
Documentation
Document testing and evaluation
Review and complete documentation (list of questions)
Make the video by collaging documentation
Sunday
Fill up any gaps
Prepare demo on tensegrity table
Finalize 1-slide
Work on minors
If done, work on if there's time
Monday Morning
Transport demo on tensegrity table
Fill up any gaps
Work on minors
Specific Tasks to Complete This Week
Major Tasks
CAD model of system
Speaker board with realtime amplifier
Combine screen/accelerometer with pulse oximeter board in a new board
Mold and cast band
Design and fabricate casing (print)
Schematic between boards (wired and wireless) — updated system diagram on PPT-like page
Serial connection between pulse oximeter and tiny blinking heart for BPM (BPM from IR, SpO2 from delta)
Combine multiple boards on the same WiFi (switching tabs is easy way, board hosting the webpage querying and update or Python-based server somewhere where everything posting data, Raspberry Pi)
Put+program everything together according to the above (with WiFi for now)
MirrorAge is a self-contained edge-AI mirror that captures grip strength, facial imagery, voice, motion, and reaction time to estimate intrinsic capacity in real time.
The platform fuses weekly prototypes—ReactionAge latency tests, 3D printed grip mechanics, SenseCraft camera inference, and molded structural elements—into a multimodal mortality risk profiler.
Subsystems in progress: reaction-time module, SenseCraft FaceTTD inference stack, VoiceAge microphone pipeline, wearable streaming via BLE, and molded structural packaging.
Clinical motivation: translate WHO intrinsic capacity domains into measurable digital biomarkers that flag functional decline earlier than chronological age alone.
Project Goals
Deliver multimodal IC scoring Fuse grip, face, voice, reaction-time, and wearable streams on-device to output an intrinsic capacity score plus domain deltas.
Fabricate modular, serviceable hardware Iterate laser-cut tensegrity mirror shells, 3D printed torsional grips, custom PCBs, and silicone cast fixtures that assemble without bespoke tooling.
Validate against ground truth Benchmark embedded inferences against published datasets (Blomkvist et al. 2017, Fuentealba et al. 2025) and lab-collected pilots to quantify accuracy, latency, and reliability.
Timeline & Milestones
Week 10 · Hardware convergence Integrate SenseCraft FaceTTD camera, ReactionAge latency module, and newly milled PCB into a single ESP32S3 backplane.
Week 12 · Midterm review build Finish molded mirror enclosure, bring up BLE wearable link, and demo live IC score during midterm critique.
Final week · Validation & documentation Execute pilot data collection, refine model weights, and release reproducible fabrication + firmware packages.
Documenting the final project masterpiece that integrates the range of units covered, addressing all required questions.
What does it do?
MirrorAge captures synchronized digital biomarkers—camera frames processed with on-device FaceTTD models, VoiceAge microphone samples, grip strength torque, wearable accelerometry, and ReactionAge latency—to estimate intrinsic capacity and time-to-death acceleration.
A XIAO ESP32S3 Sense orchestrates sensing, performs Edge Impulse inference, and displays a live mortality-risk score on the OLED while logging packets to a Python analytics notebook.
Who's done what beforehand?
The concept builds on WHO intrinsic capacity framing and recent mortality-risk studies: Niccoli & Partridge (2012) establish age as the dominant chronic-disease predictor; Fuentealba et al. (Nature Aging 2025) show blood-based IC clocks outperform chronological models;
Zhavoronkov & Bhullar (2015) and Lancet Healthy Longevity editorials motivate treating functional decline as the actionable signal.
This project translates those findings into an accessible, multimodal measurement mirror that can operate outside hospital labs.
What sources did you use?
Primary references include Nature Aging 2025 intrinsic capacity papers, the PLOS ONE ReactionAge dataset (Blomkvist et al. 2017), Edge Impulse SenseCraft documentation, Smooth‑On Mold Star technical bulletins, RotoMetals alloy certificates, MIT HTMAA recitations, and the open-source GRPR grip-strength meter.
Design inspiration and safety notes were consolidated from Anthony Pennes' HTMA guides and Fab Academy molding tutorials.
What did you design?
• Laser-cut cardboard origami mirror frame and tensegrity-inspired floating mount (Weeks 1 & 6)
• ReactionAge firmware + enclosure with statistical post-processing dashboards (Week 2)
• 3D printed torsional spring grip module tuned for ±40 kg ranges (Week 3)
• KiCad/Fusion carrier PCB for the ESP32S3 Sense with OLED, force, and BLE breakouts (Week 5)
• Edge Impulse deployment pipeline with grayscale dithering overlay and live inference UX (Weeks 7–8)
• CAM toolpaths, silicone molds, and Drystone casts for structural packaging (Week 9)
What materials and components were used?
Seeed XIAO ESP32S3 Sense module with OV2640 camera and PDM mic, SparkFun Qwiic button and force sensors, SSD1306 OLED, wearable IMU node (Bosch BHI260), laser-cut cardboard/birch sheets, PLA+/Onyx filament, Mold Star 30 silicone, Drystone gypsum, Roto281 fusible alloy, and embedded fasteners/heat-set inserts.
Where did they come from?
Electronics from Seeed Studio, SparkFun, Digi-Key, and Adafruit; molding supplies and silicones from Reynolds Advanced Materials; Drystone and Hydro-Stone from USG via the MIT CBA stockroom; fusible alloys from RotoMetals; structural lumber and plywood from MIT's shop inventory; filaments from Prusa Research and Markforged.
How much did they cost?
Current spend: $96.34 for ReactionAge components (Week 2 BOM) + $78.42 for SenseCraft camera stack (XIAO ESP32S3 Sense, OLED, cabling) + $42.10 for molding media (Mold Star 30 quart, Drystone, release agents) = $216.86 to date.
Remaining allocation (~$130) is earmarked for BLE wearable hardware and final enclosure finishes; detailed line items tracked in the Airtable budget and mirrored in each weekly BOM CSV.
What parts and systems were made?
Custom origami mirror frame, 3D printed torsional grip shell, machined floating base, silicone molds and Drystone casts for arrow-inspired structural ribs, bespoke ESP32S3 breakout PCB, laser-cut ReactionAge control panel, and assembled sensor tower linking camera, OLED, and wearable gateway.
What tools and processes were used?
Parametric CAD in Fusion 360, laser cutting (Epilog) for origami tiles, Prusa MK4 FDM printing, Formlabs SLA for detail inserts, ShopBot CNC and Bantam PCB milling, silicone mixing/casting under vacuum, Edge Impulse model training, PlatformIO firmware, and Python/NumPy validation notebooks.
What questions were answered?
• Can consumer-grade sensors reproduce published reaction-time age curves? (Yes—ReactionAge matched Blomkvist et al. regression within 4.6 ms RMSE.)
• Will SenseCraft FaceTTD run locally on ESP32S3 with acceptable latency? (Yes—~310 ms/inference at 30% baseline accuracy, highlighting dataset needs.)
• Does molded packaging improve sensor placement repeatability? (Yes—silicone nests held camera ±0.5 mm, reducing alignment drift seen in cardboard prototypes.)
What worked? What didn't?
✅ Floyd–Steinberg dithering produced clear OLED previews; ✅ ReactionAge firmware maintained ±1 ms jitter; ✅ Molded Drystone ribs stiffened mirror shell without excess weight.
⚠️ FaceTTD accuracy plateaued at 30% due to limited training diversity; ⚠️ VoiceAge requires more MFCC samples to sustain 0.64-year MAE; ⚠️ Grip spring fatigue highlighted need for fiber-reinforced print or machined aluminum insert.
How was it evaluated?
Bench tests compare embedded predictions to published curves and desktop baselines: ReactionAge latency vs. Wii Balance Board golden data; FaceTTD inferencing cross-validated against Edge Impulse cloud classifier; VoiceAge MFCC regression verified through train/holdout splits; mechanical fixtures inspected with feeler gauges and dial indicators for tolerance drift.
What are the implications?
A portable intrinsic capacity mirror supports proactive geriatric screening, telehealth coaching, and longitudinal studies that correlate functional decline with interventions.
By grounding hardware in open-source parts and HTMAA fabrication methods, the system can be replicated across labs and community clinics to accelerate validation of digital aging biomarkers and personalize longevity therapies.
Design
Your project should incorporate 2D and 3D design, multiple additive and subtractive fabrication processes, electronics design and production, embedded microcontroller design, interfacing, and programming, system integration and packaging.
2D Design
2D design work for the multimodal intrinsic capacity assessment system:
Cardboard origami tiling for circular mirror frame, optimized for kerf learned during Week 1 laser characterization.
Vinyl-cut ReactionAge control labels and MirrorAge fascia decals for rapid UI readability.
KiCad/Fusion schematics + polygon pours for ESP32S3 carrier, force sensing front-end, and OLED interposer.
2D shop drawings for CNC floating base, including registration dowels and silicone mold parting lines.
Figma wireframes outlining the midterm web dashboard and on-device OLED states.
Subtractive: Laser cutting, milling for precision parts
Electronics: PCB design and production
Programming: Embedded microcontroller development
Bill of Materials
Where possible, I fabricated parts rather than buying them. This table summarizes all unique components in the final MirrorAge system, their approximate costs, and where they are used.
A mirrored copy of this bill of materials also appears on the Week 14 system-integration page for cross-linking directly from the integration steps
(Week 14 BOM).
Grip-strength molds, band molds, structural ribs
(Week 9,
Week 14)
Fasteners
M2/M3 hardware, heat-set inserts, misc. screws
Assorted
~$0.10–$0.30 ea.
$20.00 (bundle)
All mechanical assemblies (watch, grip rig, camera mount, demo table)
Estimated Total Project Cost
Electronics ≈ $190 · Mechanical & materials ≈ $130 ·
Total ≈ $320 (excluding lab-provided consumables and reused stock).
Exact per-week line items remain in the weekly documentation tables (for example
ReactionAge BOM CSV in Week 2),
while this table captures the consolidated, unique parts that make up the final integrated MirrorAge system.
Fabrication Process
Week-by-week fabrication rolled forward subsystems toward the integrated mirror:
Week 1 laser-cut origami tiles for the circular bezel; Week 2 PCB milling + soldering for ReactionAge;
Week 3–4 torsional spring 3D prints and sanding jigs; Week 5 copper-clad milling and reflow of the ESP32S3 carrier;
Week 6 ShopBot machining of the floating base; Week 8 resin + FDM camera enclosure build; Week 9 wax machining, Mold Star casting, and Drystone ribs.
Each step captured feeds-and-speeds, toolpaths, and fixturing photos embedded in the weekly pages for replication.
Testing & Validation
Validation combined bench instrumentation and statistical analysis: oscilloscope timing to verify ReactionAge jitter, Edge Impulse confusion matrices for FaceTTD and VoiceAge,
Instron pull tests for the torsional grip cartridge, IR thermography while curing Mold Star molds, dial-indicator checks on CNC-machined bases, and adhesive shear testing on mirror mounts.
Data are logged to CSV via the ESP32S3 and compared against published baselines inside the midterm Jupyter notebook.
Individual Mastery and Independent Operation
Projects can be separate or joint, but need to show individual mastery of the skills, and be independently operable.
Individual Mastery
Demonstration of individual skills across all course units:
2D and 3D Design
Modeled the tensegrity floating mirror, torsional grip shells, and camera bezel in Fusion 360 and Onshape.
Drove design reviews with Anthony/Neil to lock tolerances, assembly order, and module interface specs.
Demonstrates mastery across cutting, 3D printing, machining, electronics, networking, and interface programming units.
Documentation cross-linked via weekly pages, GitHub repos, and BOM spreadsheets for traceability.
Group Assignments
Collaborative work and individual contributions:
Embedded programming group: authored workflow trade-off analysis and repo organization that seeded ReactionAge firmware patterns.
Molding & casting group: led SDS review, material trials, and mixing SOP that informed final mirror mold.
Shared camera dev sessions with peers to improve Edge Impulse dataset collection and SenseCraft deployment strategies.
Useful Documentation
Helpful resources, documentation, and design files for the multimodal intrinsic capacity assessment system.
Open Source Grip Strength Meter
A cost-effective $50 grip strength measurement system that can be further optimized for our multimodal assessment platform.
This open-source design provides an excellent foundation for integrating grip strength measurement into our intrinsic capacity assessment system,
with potential for cost reduction through signal multiplexing on a single processor.
Detailed technical pipeline for processing multiple digital biomarkers to generate intrinsic capacity scores.
Pipeline Architecture
Inputs
• Grip Strength
• Voice
• Face
• Video (motion/gait)
• Reaction Time
• Wearable Accelerometer
→
Feature Extraction
Strength metrics
Prosody features
Facial landmarks
Gait parameters
Response latency
Activity patterns
Embeddings
Features converted to vector representations for multimodal fusion
→
Fusion Layer
Combines multimodal features using attention mechanisms
Output
• Overall IC Score
• Domain sub-scores
→
Domain Scores
Locomotor
Cognition
Vitality
Sensory
Psychological
Weekly System Development Breakdown
How each week of HTMAA 2025 builds toward the complete multimodal intrinsic capacity assessment system.
Week 0: Project Ideation
Initial concept development and planning
Project planning and documentation structure
Research direction and concept sketches
Week 1: Precision Cutting
Laser and vinyl cutting techniques
Device housing components via laser cutting
Sensor mounting brackets and enclosures
Vinyl cutting for device labeling and UI elements
Week 2: Embedded Programming
Electronics basics and microcontroller programming
Microcontroller programming for data collection
Basic sensor interface circuits
Week 3: 3D Scanning & Printing
3D technologies for device components
3D scanning for custom component design
3D printing for device housings
Week 4: Electronics Design
EDA and schematic design
PCB design for grip strength measurement
Sensor interface circuits and signal conditioning
Power management and data storage systems
Week 5: Electronics Production
PCB fabrication and assembly
PCB fabrication and debugging
Component assembly and testing
Week 6: Computer-controlled Machining
CAM and precision milling
Precision components via milling
Custom mechanical parts
Week 7: Input Devices
Sensor integration for data collection
Force sensors for grip strength measurement
Microphones for voice analysis
Camera systems for facial expression analysis
Reaction time measurement circuits
Week 8: Output Devices
Actuators and system integration
Display systems for real-time feedback
Haptic feedback for user interaction
Week 9: Molding & Casting
Forming and resin techniques
3D printing and molding for custom components
Silicone casting for device components
Week 10: Mechanical & Machine Design
System integration and mechanical design
Mechanical design for ergonomic device housing
System integration and calibration protocols
Week 11: Networking & Communications
Connectivity and communication protocols
Bluetooth/Wi-Fi connectivity for data transmission
Wearable accelerometer integration and data fusion
Week 12: Interface & Application Programming
UI development and application programming
Mobile app development for user interface
Cloud integration for data storage and analysis
Machine learning pipeline for IC score calculation
Week 13: Wildcard & Final Integration
Final orders and complete system deployment
Final testing, validation, and documentation
System integration and deployment
Camera Subsystem
Advanced camera system implementation using XIAO ESP32S3 Sense with real-time image processing, EdgeAI integration, and interactive selfie capture functionality.
System Overview
The camera system successfully captures images, processes them into bitmaps, and displays them on an OLED screen using advanced Floyd-Steinberg dithering algorithms.
Video Demonstrations
Camera Bot Selfie
Demonstration of the interactive selfie capture system with touch controls
Picture of Picture
Meta demonstration showing the camera system capturing its own display
Code Implementation
60-Second Auto Capture System
Automated camera system that captures and displays images every 60 seconds using advanced image processing techniques.
1. Initialize camera with PSRAM frame buffers
2. Configure OLED display (128x64 pixels)
3. Set up 60-second capture interval timer
4. In main loop:
a. Check if 60 seconds have elapsed
b. Capture image from camera
c. Process image:
- Downsample to 128x64 via box averaging
- Apply contrast stretch (linear scaling)
- Perform Floyd-Steinberg dithering
d. Display processed bitmap on OLED
e. Release frame buffer
5. Repeat process
Touch-Controlled Capture System
Interactive camera system with touch controls allowing manual capture triggers in addition to automatic timing.
1. Initialize camera and OLED display
2. Set up touch pins (GPIO1 & GPIO2) with threshold detection
3. Configure 60-second auto-capture timer
4. In main loop:
a. Update touch sensor readings
b. Detect touch press events (justPressed)
c. Check for capture trigger:
- Touch press OR 60-second timer elapsed
d. If triggered:
- Capture image from camera
- Process image (same as auto version)
- Display on OLED
- Reset timer
5. Continue monitoring for next trigger
The system captures photos, converts them to bitmaps using advanced image processing algorithms, and displays them on the OLED screen.
I'm also exploring integration with ML models, either through online API calls or by embedding TinyML model parameters from Python to C++.
Future development includes live streaming real-time video with ML prediction updates based on variable observation times,
and exploring Edge Impulse models as an alternative to manual Python-to-C++ conversion for faster deployment.
EdgeAI/TinyML Integration
Edge AI can also be implemented using Edge Impulse models, which may be faster than manually converting Python models to C++.
The SenseCraft AI platform provides a streamlined approach to training and deploying ML models directly on the XIAO ESP32S3.
Deploy inference bundle to the SenseCraft board alongside the camera stack.
Benchmark latency and accuracy against baseline VoiceAge models and document calibration protocol.
Week 0 - Introduction & Design
Project ideation and initial concept development for bioprinting rejuvenated tissue and aging biomarker devices.
Project planningConcept sketchesResearch direction
System Integration Plans: Establish the foundational architecture for multimodal data collection by designing the overall system framework that will integrate all six digital biomarkers (grip strength, voice, face, video, reaction time, wearable accelerometer) into a cohesive intrinsic capacity assessment platform.
Mapped the MirrorAge subsystem architecture, assembled the intrinsic capacity literature stack, and kicked off BRR/IRB coordination so fabrication sprints stay aligned with clinical requirements.
Week 1 - Principles & Cutting
Version control, laser cutting, and vinyl cutting techniques applied to final project components.
Laser cuttingVinyl cuttingVersion control
System Integration Plans: Fabricate precision-cut housing components and mounting brackets for all sensor modules (force sensors, microphones, cameras, reaction time circuits) using laser cutting, while creating vinyl-cut labels and UI elements for device identification and user guidance.
Characterized laser kerf, produced the origami mirror frame tiles, and generated vinyl interface labels—locking in enclosure dimensions and user UI cues for the mirror shell.
Week 2 - Embedded Programming
Electronics basics and embedded programming for the aging biomarker device components.
MicrocontrollersProgrammingElectronics
System Integration Plans: Develop embedded programming protocols for real-time data collection from all six biomarker sensors, implementing initial signal processing algorithms and establishing the communication framework for multimodal data fusion.
Built the ReactionAge firmware + enclosure, published the first BOM, and validated timing pipelines that will feed the MirrorAge IC fusion engine.
Week 3 - 3D Scanning & Printing
3D scanning and printing techniques for bioprinting components and device housings.
3D scanning3D printingAI tools
System Integration Plans: Create custom 3D-printed components for camera mounting systems and facial recognition hardware, while developing 3D scanning protocols for ergonomic device design that accommodates all sensor modalities in a user-friendly form factor.
Modeled and printed the torsional grip spring, performed 3D scans for ergonomic fixtures, and captured training assets for face/gait datasets.
Week 4 - Electronics Design
EDA and schematic design for the aging biomarker device electronics.
EDA toolsSchematic designCircuit design
System Integration Plans: Design comprehensive PCB schematics that integrate force sensor circuits for grip strength measurement, microphone preamplifiers for voice analysis, camera interfaces for facial recognition, and timing circuits for reaction time assessment into a unified electronics platform.
Completed the Fusion 360/KiCad schematic/PCB layout for the ESP32S3 carrier tying together force, audio, camera, reaction, and wearable interfaces.
Week 5 - Electronics Production
PCB fabrication, debugging, and assembly for the biomarker device.
PCB fabricationDebuggingAssembly
System Integration Plans: Fabricate and assemble the integrated PCB containing all sensor interfaces, implementing power management systems for continuous operation and establishing data storage protocols for the multimodal biomarker data collection system.
Fabricated and assembled the carrier PCB, brought up power domains, and verified sensor buses—establishing the electronics backbone for integration.
Week 6 - Computer-controlled Machining
CAM and milling for precision components and device housings.
CAMMillingPrecision machining
System Integration Plans: Machine precision mechanical components for the integrated device housing using computer-controlled milling, ensuring proper alignment and mounting for all sensor modules while maintaining ergonomic design for user comfort during multimodal data collection.
Machined the floating mirror base and tensegrity nodes, refining fixturing that ensures repeatable camera and grip alignment in the final assembly.
Week 7 - Input Devices
Sensors and embedded architectures for data collection in the biomarker device.
SensorsInput devicesData collection
System Integration Plans: Integrate all six input sensor systems (force sensors for grip strength, microphones for voice analysis, cameras for facial recognition and gait analysis, reaction time circuits, and wearable accelerometer) into the unified data collection platform with real-time processing capabilities.
Integrated the force sensor, microphone, and ReactionAge modules on the carrier, logging synchronized packets that exercise the multimodal intake stack.
Week 8 - Output Devices
Actuators and system integration for the biomarker device outputs.
ActuatorsOutput devicesSystem integration
System Integration Plans: Implement output devices including display systems for real-time intrinsic capacity feedback and haptic feedback mechanisms for user interaction, creating an intuitive interface for the multimodal biomarker assessment system.
Deployed the SenseCraft FaceTTD pipeline on the XIAO ESP32S3, implemented OLED dithering previews, and confirmed end-to-end edge inference latency.
Week 9 - Molding & Casting
Forming and resin techniques for bioprinting molds and device components.
MoldingCastingResins
System Integration Plans: Create custom molded components for the bioprinting aspects of the project and develop specialized casings for sensor protection, ensuring the device can withstand continuous use during multimodal data collection sessions.
Machined wax molds, cast Mold Star silicone and Drystone ribs, and prototyped arrow-inspired shells that stabilize the mirror and protect embedded sensors.
Week 10 - Mechanical & Machine Design
Kits and mechanical design for the bioprinting and biomarker device systems.
Mechanical designMachine designSystem integration
System Integration Plans: Complete the mechanical design integration of all system components, implementing calibration protocols for sensor alignment and developing the complete mechanical framework that houses all six digital biomarker measurement systems.
Developed mechanical actuation systems including tapping and swiping mechanisms for phone interaction, integrated camera with Edge AI face detection and Wi-Fi livestreaming, designed and 3D-printed phone holder with amplifier, and prepared comprehensive midterm review documentation with system diagrams and timeline.
Week 11 - Networking & Communications
BLE, Wi-Fi, and communication protocols for the biomarker device connectivity.
BLEWi-FiCommunications
System Integration Plans: Implement wireless communication protocols (Bluetooth/Wi-Fi) for seamless data transmission from all six sensor modalities, enabling real-time data fusion and establishing connectivity for the wearable accelerometer integration into the multimodal assessment system.
Implemented Wi-Fi camera livestreaming for real-time video transmission, developed ESP-NOW networking protocols for device communication, designed and milled PCBs for networking components, and explored Meshtastic for long-range communication capabilities.
Week 12 - Interface & Application Programming
UI and application development for the biomarker device interface.
UI designApplicationsUser interface
System Integration Plans: Develop the complete user interface and application programming for the multimodal system, implementing the machine learning pipeline for intrinsic capacity score calculation and creating cloud integration for comprehensive data storage and analysis of all biomarker measurements.
Created Wi-Fi web interface for real-time pulse oximeter readings with live plotting, developed grip strength measurement device with load cell and integrated GUI, implemented OLED button user interface for device control, and established video streaming capabilities for sensor data visualization.
Week 13 - Wildcard & Final Orders
Final orders and wildcard week activities for project completion.
Final ordersWildcard activitiesProject completion
System Integration Plans: Complete final system integration, testing, and validation of the complete multimodal intrinsic capacity assessment platform, ensuring all six digital biomarkers work cohesively to provide accurate WHO-defined intrinsic capacity scores across all five domains (locomotor, cognition, vitality, sensory, psychological).
Designed and fabricated ATtiny1626 tiny development board with fiber laser PCB engraving, created glass engraving system with UV laser including blinking heart integration for visual feedback, milled mounting holes and completed board assembly, and prepared final board designs for system integration.
System Integration
Final integration week focused on bringing all subsystems together, completing hardware fabrication, firmware integration, and documentation for the MirrorAge system presentation. View full details →
Initial system integration work focused on subsystem validation, CAD model consolidation, and design backbone acquisition for band integration. Conducted comprehensive testing of all subsystems to ensure proper functionality, identified and resoldered defective joints, and exported CAD models of all PCBs into a unified assembly model.
Integrated CAD Model: Exploded isometric view of the complete system assembly, including all PCBs, main housing with transparent enclosure, and wearable band components.
Physical integration of subsystems into the complete demo table assembly, including mechanical component fabrication and electrical board consolidation. Integrated the complete demo table with precise placement of the MirrorAge handgrip subsystem and aging clock subsystem, providing a unified platform for system demonstration.
Complete Demo Table Assembly: Integrated mechanical design showing precise placement of the MirrorAge handgrip subsystem and aging clock subsystem on the demo table.
Continued fabrication work integrating all manufacturing processes. Focused on completing physical components including 2D laser cutting, 3D printing of rigid and flexible components, and PCB milling to prepare subsystems for final assembly and testing.
TPU Band Print: Flexible wearable band component printed using TPU material
Flexible Band: TPU band demonstrating material properties and print quality
Comprehensive subsystem integration combining 2D fabrication (laser cutting and vinyl cutting), 3D printing (rigid and flexible components), PCB milling (single and double-sided boards), and molding/casting to complete all physical components. Upgraded MirrorAge TFT board to v13 and aging clock TFT board to v16 with optimized component placement and routing. Established reliable I²C bus communication and validated all sensor addresses.
MirrorAge TFT v13: Upgraded front-side layout with optimized component placement
Aging Clock TFT v16: Upgraded front-side design with rotated components for optimal fit
Final integration day focused on closing the watch subsystem, soldering and verifying all double-sided boards, refining molded bands, and assembling the complete MirrorAge demo with both the aging clock and grip-strength subsystems fully wired and tested. Completed rivet installation for plated through-holes, sensor bring-up (accelerometer, pulse oximeter, OLED/TFT displays), and full system integration on the tensegrity demo table. The integrated system successfully demonstrated synchronized sensor readouts and display behavior across all boards.
Final project presentation and demonstration of the complete MirrorAge system. Showcased the integrated aging clock and grip-strength subsystems working together on the demo table, demonstrating real-time sensor data collection and display synchronization. View final presentation demo →
Full Documentation: For complete details, design files, code, and comprehensive documentation of the system integration process, see Week 14: System Integration.
Final Project Masterpiece
Complete demonstration of the integrated MirrorAge system showcasing all subsystems working together in real-time.
Final Presentation Demo: Complete MirrorAge system demonstration showing the integrated aging clock and grip-strength subsystems operating together on the demo table, with synchronized sensor readouts and real-time display updates across all boards.
Complete repository of all design files, CAD models, schematics, PCB layouts, firmware, and fabrication files from Week 0 through Week 14, organized by week and component type.
Note: Additional design files, firmware, and documentation can be found in the respective week pages. Some files are part of larger archives (ZIP files) that contain multiple related design files.
Reflections & Learnings
Comprehensive reflections on the MirrorAge Intrinsic Capacity Mirror project development journey.
Modular system design allows for incremental development and component-level testing throughout the semester
Integration of mechanical, electrical, and software subsystems requires careful planning and coordination
Iterative design and prototyping revealed the importance of early testing and validation
Documentation and knowledge transfer are critical for project continuity and future improvements
The project successfully demonstrates how digital fabrication and embedded systems can create meaningful health assessment tools
Contributions
Acknowledgements and contributions that made this project possible.
Gladyshev Lab and Collaborators
Special thanks to the Gladyshev Lab and collaborators for the fruitful discussions that led to this multimodal intrinsic capacity assessment idea,
which supplements my PhD research goals in aging and longevity. The conceptual framework for integrating multiple digital biomarkers
to assess intrinsic capacity domains emerged from collaborative research discussions on aging biomarkers and healthspan assessment.
Transparent documentation of AI assistance used in this final project work, following course guidelines for ethical AI usage.
📋 General Guidelines: See General Commands for Cursor on the homepage for standard guidelines and commands used consistently throughout documentation development.
Cursor · Project Plan & Weekly Schedule
Comprehensive Cursor AI assistance for outlining the project plan and weekly schedule, including documentation structure, content organization, systematic updates across all week pages and the final project page, media integration, and summary generation workflows.
Cursor AI aligned the midterm review plan with updated system diagram, timeline, and remaining-task summaries, then refreshed finalproject.html to remove legacy bioprinting language and re-point internal links. The full transcript and generated HTML are available for review.
Cursor AI assistance for adding a white background behind the photo in the Final Project Spiral Development Model section on finalproject.html. The image container was updated with white background, padding, and rounded corners for improved visual presentation.
Cursor AI distilled Week 0–9 documentation and the Oct 31 lab meeting deck into midterm-ready narrative, cost, and validation content, replacing every placeholder in finalproject.html.
Transcript archived in markdown and HTML (generated via scripts/md_to_html_converter.py) for transparency.
ChatGPT was used to research and develop the multimodal intrinsic capacity assessment framework, including the comprehensive coverage analysis table and technical pipeline design.
The AI assisted with structuring the WHO-defined intrinsic capacity domains, identifying appropriate digital biomarkers, and designing the fusion architecture for multimodal data processing.
Cursor AI assisted with developing the complete final project page structure, implementing the multimodal intrinsic capacity assessment framework, and creating comprehensive documentation.
The AI helped with HTML structure, responsive design, weekly system integration plans, and organizing the technical documentation for the complete biomarker assessment system.
Cursor AI assisted with finalizing the project presentation structure to ensure full compliance with MIT Academy project presentation requirements.
The AI helped implement all required sections including answering questions, design documentation, bill of materials, individual mastery requirements,
course presentation structure, and spiral model development approach visualization.
ChatGPT was used to discuss camera system implementation strategies, image processing algorithms, and EdgeAI integration approaches.
The AI assisted with understanding Floyd-Steinberg dithering implementation, touch sensor integration, and exploring TinyML deployment options for the XIAO ESP32S3 platform.
AI-Assisted Project Highlights and Camera Subsystem Development
Cursor AI assisted with adding the project highlights section featuring camera system achievements and creating a comprehensive camera subsystem section with detailed code implementations, video demonstrations, and EdgeAI integration documentation.
The AI helped with HTML structure, responsive design, image processing explanations, and organizing the technical documentation for the complete camera system showcase.
Interactive selfie capture system with touch controls and real-time display
Vision Board
Conceptual visualization of the multimodal intrinsic capacity assessment system integrating grip strength, voice analysis, facial recognition, video motion capture, reaction time measurement, and wearable accelerometer data.
Intrinsic Capacity (IC) Coverage by Digital Biomarkers
Domain
Grip
Voice
Face
Video
Reaction Time
Wearable
Locomotor
✅
🔸
🔸
✅
🔸
✅
Cognition
❌
✅
🔸
🔸
✅
🔸
Vitality
✅
✅
✅
✅
🔸
✅
Sensory
❌
✅
✅
✅
✅
🔸
Psychological
❌
✅
✅
✅
🔸
✅
✅ Strong coverage |
🔸 Partial/indirect |
❌ Not covered |
View full table →
Multimodal IC Pipeline
Inputs: Grip Strength, Voice, Face, Video, Reaction Time, Wearable Accelerometer
Development Approach: Following the spiral model methodology, this final project will iterate through multiple development cycles, each building upon previous work while addressing new requirements and risks.
This snapshot covers the subsystems and documentation that will be shown during the midterm review. Links jump directly to the supporting sections with detailed evidence.
Featured Subsystems
Camera subsystem — Edge inference demos and selfie capture loop.
Instructor meeting hold — Thursday, Nov 12 at 10:00 AM ET reserved via the shared HTMAA midterm review sheet.
Execution Schedule (Timeline Snapshot)
Condensed from the Week 8–13 development timeline: each sprint builds toward final integration, mirroring the gantt chart below.
Week 8 · Output Devices: figuring out wiring for real-time display states.
Week 9 · Molding & Casting: learn how to cast custom housings and refine structural components.
Week 10 · Mechanical Design: figure out ergonomic enclosure and calibration fixtures.
Week 11 · Networking: program BLE/Wi-Fi telemetry and wearable data fusion.
Week 12 · Interface/App: create mobile UI, cloud bridge, and IC scoring pipeline.
Week 13 · Final Integration: run validation passes, document results, and prep deployment.
Instructor Review Logistics
Calendar hold sent for Thursday, Nov 12 at 10:00 AM ET (38-501 conference room) per the shared HTMAA scheduling sheet. Agenda covers subsystem demos, weekly documentation spot checks (Weeks 0–9), and next-sprint alignment. Meeting slot referenced in the midterm review schedule; awaiting final confirmation via class Slack.
System Architecture
Updated block diagram highlighting the multimodal sensing stack (grip, voice, face, motion, wearables), on-device inference layers, and real-time feedback channels that feed the intrinsic capacity score.
Development Timeline
Timeline aligns subsystem sprints with HTMAA milestones: output devices (Week 8), molding and casting (Week 9), mechanical design (Week 10), networking and communications (Week 11), app programming (Week 12), and final integration (Week 13).
Remaining Tasks (Snapshot)
Weeks 0–9 locked in the core subsystems—documentation workflow, cutting and molding for the housing, embedded prototypes for reaction timing, SenseCraft camera inference, and early grip/voice rigs. The checklist below captures what still needs to happen to converge on the integrated MirrorAge system.
Hardware Integration
Consolidate grip, voice, camera, reaction-time, and wearable sensor harnesses into the MirrorAge enclosure.
Finish molding/casting iterations for the ergonomic housing and align mounting features for PCBs and haptics.
Firmware & Edge AI
Stabilize onboard inference for SenseCraft vision models and voice-age pipelines on the XIAO ESP32S3.
Calibrate grip-force and reaction-time firmware for repeatable sampling; close the loop to haptic/display feedback.
Networking & Data Fusion
Bring up BLE/Wi-Fi data paths for wearable accelerometer streaming and cloud logging of intrinsic capacity scores.
Implement the fusion layer that combines per-domain scores into an overall IC metric with on-device storage.
Interface & UX
Finish mobile/web dashboard mockups for user onboarding, data review, and device calibration workflows.
Finalize real-time mirror feedback cues (display states, haptics, lighting) tied to sensor status and IC outcomes.
Validation & Documentation
Run end-to-end system tests (sensor capture → fusion → feedback) and document calibration procedures.
Record the one-minute video, finalize final presentation assets, and polish the bill of materials for review.
Week 14 System Integration Plan
Detailed day-by-day schedule for final system integration, covering design, fabrication, programming, testing, and documentation. This plan outlines the path to completing the MirrorAge system integration and preparing for final presentation. View on Week 14 page →
The act of bringing something to a conclusion or ending in a decisive manner. The ability to efficiently finish tasks and projects with a goal-oriented mindset.
Wednesday
Morning
Publish system integration plan on website
Update weekly assignment sections on final project page (weeks 10-13)
Link final project design files
Update reflections and learnings
Update picture of prism holder
Add final pictures to Slack canvases
Create schematic between boards (wired and wireless) — updated system diagram on PPT-like page
Start CAD model of system
Place final order
Afternoon & Evening
Design:
Boards: Combine OLED screen/accelerometer with pulse oximeter board in a new board (maybe upgrade to small TFT as minor)
Boards: Speaker board with realtime amplifier and TFT (on the load cell fixed board)
Band: Mold design
Cases: 3D print mountable cases for the boards
Integrate designs into final CAD
Document design
Finish CAD model of system
Thursday
Fabricate
Milling boards
Print mold and cast band
Print cases
Solder
Solder components on milled boards
Connect boards with wired (and wireless connection codes)
Finishing
Mirror on screen (easy way with the film)
Documentation
Document fabrication
Friday
Programming
Board level codes
Server level codes
Documentation
Document codes
Completion
Finish anything else
Saturday
Programming & Testing
Demo integrated system
Test integrated system
Documentation
Document testing and evaluation
Review and complete documentation (list of questions)
Make the video by collaging documentation
Sunday
Fill up any gaps
Prepare demo on tensegrity table
Finalize 1-slide
Work on minors
If done, work on if there's time
Monday Morning
Transport demo on tensegrity table
Fill up any gaps
Work on minors
Specific Tasks to Complete This Week
Major Tasks
CAD model of system
Speaker board with realtime amplifier
Combine screen/accelerometer with pulse oximeter board in a new board
Mold and cast band
Design and fabricate casing (print)
Schematic between boards (wired and wireless) — updated system diagram on PPT-like page
Serial connection between pulse oximeter and tiny blinking heart for BPM (BPM from IR, SpO2 from delta)
Combine multiple boards on the same WiFi (switching tabs is easy way, board hosting the webpage querying and update or Python-based server somewhere where everything posting data, Raspberry Pi)
Put+program everything together according to the above (with WiFi for now)
MirrorAge is a self-contained edge-AI mirror that captures grip strength, facial imagery, voice, motion, and reaction time to estimate intrinsic capacity in real time.
The platform fuses weekly prototypes—ReactionAge latency tests, 3D printed grip mechanics, SenseCraft camera inference, and molded structural elements—into a multimodal mortality risk profiler.
Subsystems in progress: reaction-time module, SenseCraft FaceTTD inference stack, VoiceAge microphone pipeline, wearable streaming via BLE, and molded structural packaging.
Clinical motivation: translate WHO intrinsic capacity domains into measurable digital biomarkers that flag functional decline earlier than chronological age alone.
Project Goals
Deliver multimodal IC scoring Fuse grip, face, voice, reaction-time, and wearable streams on-device to output an intrinsic capacity score plus domain deltas.
Fabricate modular, serviceable hardware Iterate laser-cut tensegrity mirror shells, 3D printed torsional grips, custom PCBs, and silicone cast fixtures that assemble without bespoke tooling.
Validate against ground truth Benchmark embedded inferences against published datasets (Blomkvist et al. 2017, Fuentealba et al. 2025) and lab-collected pilots to quantify accuracy, latency, and reliability.
Timeline & Milestones
Week 10 · Hardware convergence Integrate SenseCraft FaceTTD camera, ReactionAge latency module, and newly milled PCB into a single ESP32S3 backplane.
Week 12 · Midterm review build Finish molded mirror enclosure, bring up BLE wearable link, and demo live IC score during midterm critique.
Final week · Validation & documentation Execute pilot data collection, refine model weights, and release reproducible fabrication + firmware packages.
Documenting the final project masterpiece that integrates the range of units covered, addressing all required questions.
What does it do?
MirrorAge captures synchronized digital biomarkers—camera frames processed with on-device FaceTTD models, VoiceAge microphone samples, grip strength torque, wearable accelerometry, and ReactionAge latency—to estimate intrinsic capacity and time-to-death acceleration.
A XIAO ESP32S3 Sense orchestrates sensing, performs Edge Impulse inference, and displays a live mortality-risk score on the OLED while logging packets to a Python analytics notebook.
Who's done what beforehand?
The concept builds on WHO intrinsic capacity framing and recent mortality-risk studies: Niccoli & Partridge (2012) establish age as the dominant chronic-disease predictor; Fuentealba et al. (Nature Aging 2025) show blood-based IC clocks outperform chronological models;
Zhavoronkov & Bhullar (2015) and Lancet Healthy Longevity editorials motivate treating functional decline as the actionable signal.
This project translates those findings into an accessible, multimodal measurement mirror that can operate outside hospital labs.
What sources did you use?
Primary references include Nature Aging 2025 intrinsic capacity papers, the PLOS ONE ReactionAge dataset (Blomkvist et al. 2017), Edge Impulse SenseCraft documentation, Smooth‑On Mold Star technical bulletins, RotoMetals alloy certificates, MIT HTMAA recitations, and the open-source GRPR grip-strength meter.
Design inspiration and safety notes were consolidated from Anthony Pennes' HTMA guides and Fab Academy molding tutorials.
What did you design?
• Laser-cut cardboard origami mirror frame and tensegrity-inspired floating mount (Weeks 1 & 6)
• ReactionAge firmware + enclosure with statistical post-processing dashboards (Week 2)
• 3D printed torsional spring grip module tuned for ±40 kg ranges (Week 3)
• KiCad/Fusion carrier PCB for the ESP32S3 Sense with OLED, force, and BLE breakouts (Week 5)
• Edge Impulse deployment pipeline with grayscale dithering overlay and live inference UX (Weeks 7–8)
• CAM toolpaths, silicone molds, and Drystone casts for structural packaging (Week 9)
What materials and components were used?
Seeed XIAO ESP32S3 Sense module with OV2640 camera and PDM mic, SparkFun Qwiic button and force sensors, SSD1306 OLED, wearable IMU node (Bosch BHI260), laser-cut cardboard/birch sheets, PLA+/Onyx filament, Mold Star 30 silicone, Drystone gypsum, Roto281 fusible alloy, and embedded fasteners/heat-set inserts.
Where did they come from?
Electronics from Seeed Studio, SparkFun, Digi-Key, and Adafruit; molding supplies and silicones from Reynolds Advanced Materials; Drystone and Hydro-Stone from USG via the MIT CBA stockroom; fusible alloys from RotoMetals; structural lumber and plywood from MIT's shop inventory; filaments from Prusa Research and Markforged.
How much did they cost?
Current spend: $96.34 for ReactionAge components (Week 2 BOM) + $78.42 for SenseCraft camera stack (XIAO ESP32S3 Sense, OLED, cabling) + $42.10 for molding media (Mold Star 30 quart, Drystone, release agents) = $216.86 to date.
Remaining allocation (~$130) is earmarked for BLE wearable hardware and final enclosure finishes; detailed line items tracked in the Airtable budget and mirrored in each weekly BOM CSV.
What parts and systems were made?
Custom origami mirror frame, 3D printed torsional grip shell, machined floating base, silicone molds and Drystone casts for arrow-inspired structural ribs, bespoke ESP32S3 breakout PCB, laser-cut ReactionAge control panel, and assembled sensor tower linking camera, OLED, and wearable gateway.
What tools and processes were used?
Parametric CAD in Fusion 360, laser cutting (Epilog) for origami tiles, Prusa MK4 FDM printing, Formlabs SLA for detail inserts, ShopBot CNC and Bantam PCB milling, silicone mixing/casting under vacuum, Edge Impulse model training, PlatformIO firmware, and Python/NumPy validation notebooks.
What questions were answered?
• Can consumer-grade sensors reproduce published reaction-time age curves? (Yes—ReactionAge matched Blomkvist et al. regression within 4.6 ms RMSE.)
• Will SenseCraft FaceTTD run locally on ESP32S3 with acceptable latency? (Yes—~310 ms/inference at 30% baseline accuracy, highlighting dataset needs.)
• Does molded packaging improve sensor placement repeatability? (Yes—silicone nests held camera ±0.5 mm, reducing alignment drift seen in cardboard prototypes.)
What worked? What didn't?
✅ Floyd–Steinberg dithering produced clear OLED previews; ✅ ReactionAge firmware maintained ±1 ms jitter; ✅ Molded Drystone ribs stiffened mirror shell without excess weight.
⚠️ FaceTTD accuracy plateaued at 30% due to limited training diversity; ⚠️ VoiceAge requires more MFCC samples to sustain 0.64-year MAE; ⚠️ Grip spring fatigue highlighted need for fiber-reinforced print or machined aluminum insert.
How was it evaluated?
Bench tests compare embedded predictions to published curves and desktop baselines: ReactionAge latency vs. Wii Balance Board golden data; FaceTTD inferencing cross-validated against Edge Impulse cloud classifier; VoiceAge MFCC regression verified through train/holdout splits; mechanical fixtures inspected with feeler gauges and dial indicators for tolerance drift.
What are the implications?
A portable intrinsic capacity mirror supports proactive geriatric screening, telehealth coaching, and longitudinal studies that correlate functional decline with interventions.
By grounding hardware in open-source parts and HTMAA fabrication methods, the system can be replicated across labs and community clinics to accelerate validation of digital aging biomarkers and personalize longevity therapies.
Design
Your project should incorporate 2D and 3D design, multiple additive and subtractive fabrication processes, electronics design and production, embedded microcontroller design, interfacing, and programming, system integration and packaging.
2D Design
2D design work for the multimodal intrinsic capacity assessment system:
Cardboard origami tiling for circular mirror frame, optimized for kerf learned during Week 1 laser characterization.
Vinyl-cut ReactionAge control labels and MirrorAge fascia decals for rapid UI readability.
KiCad/Fusion schematics + polygon pours for ESP32S3 carrier, force sensing front-end, and OLED interposer.
2D shop drawings for CNC floating base, including registration dowels and silicone mold parting lines.
Figma wireframes outlining the midterm web dashboard and on-device OLED states.
Subtractive: Laser cutting, milling for precision parts
Electronics: PCB design and production
Programming: Embedded microcontroller development
Bill of Materials
Where possible, I fabricated parts rather than buying them. This table summarizes all unique components in the final MirrorAge system, their approximate costs, and where they are used.
A mirrored copy of this bill of materials also appears on the Week 14 system-integration page for cross-linking directly from the integration steps
(Week 14 BOM).
Grip-strength molds, band molds, structural ribs
(Week 9,
Week 14)
Fasteners
M2/M3 hardware, heat-set inserts, misc. screws
Assorted
~$0.10–$0.30 ea.
$20.00 (bundle)
All mechanical assemblies (watch, grip rig, camera mount, demo table)
Estimated Total Project Cost
Electronics ≈ $190 · Mechanical & materials ≈ $130 ·
Total ≈ $320 (excluding lab-provided consumables and reused stock).
Exact per-week line items remain in the weekly documentation tables (for example
ReactionAge BOM CSV in Week 2),
while this table captures the consolidated, unique parts that make up the final integrated MirrorAge system.
Fabrication Process
Week-by-week fabrication rolled forward subsystems toward the integrated mirror:
Week 1 laser-cut origami tiles for the circular bezel; Week 2 PCB milling + soldering for ReactionAge;
Week 3–4 torsional spring 3D prints and sanding jigs; Week 5 copper-clad milling and reflow of the ESP32S3 carrier;
Week 6 ShopBot machining of the floating base; Week 8 resin + FDM camera enclosure build; Week 9 wax machining, Mold Star casting, and Drystone ribs.
Each step captured feeds-and-speeds, toolpaths, and fixturing photos embedded in the weekly pages for replication.
Testing & Validation
Validation combined bench instrumentation and statistical analysis: oscilloscope timing to verify ReactionAge jitter, Edge Impulse confusion matrices for FaceTTD and VoiceAge,
Instron pull tests for the torsional grip cartridge, IR thermography while curing Mold Star molds, dial-indicator checks on CNC-machined bases, and adhesive shear testing on mirror mounts.
Data are logged to CSV via the ESP32S3 and compared against published baselines inside the midterm Jupyter notebook.
Individual Mastery and Independent Operation
Projects can be separate or joint, but need to show individual mastery of the skills, and be independently operable.
Individual Mastery
Demonstration of individual skills across all course units:
2D and 3D Design
Modeled the tensegrity floating mirror, torsional grip shells, and camera bezel in Fusion 360 and Onshape.
Drove design reviews with Anthony/Neil to lock tolerances, assembly order, and module interface specs.
Demonstrates mastery across cutting, 3D printing, machining, electronics, networking, and interface programming units.
Documentation cross-linked via weekly pages, GitHub repos, and BOM spreadsheets for traceability.
Group Assignments
Collaborative work and individual contributions:
Embedded programming group: authored workflow trade-off analysis and repo organization that seeded ReactionAge firmware patterns.
Molding & casting group: led SDS review, material trials, and mixing SOP that informed final mirror mold.
Shared camera dev sessions with peers to improve Edge Impulse dataset collection and SenseCraft deployment strategies.
Useful Documentation
Helpful resources, documentation, and design files for the multimodal intrinsic capacity assessment system.
Open Source Grip Strength Meter
A cost-effective $50 grip strength measurement system that can be further optimized for our multimodal assessment platform.
This open-source design provides an excellent foundation for integrating grip strength measurement into our intrinsic capacity assessment system,
with potential for cost reduction through signal multiplexing on a single processor.
Detailed technical pipeline for processing multiple digital biomarkers to generate intrinsic capacity scores.
Pipeline Architecture
Inputs
• Grip Strength
• Voice
• Face
• Video (motion/gait)
• Reaction Time
• Wearable Accelerometer
→
Feature Extraction
Strength metrics
Prosody features
Facial landmarks
Gait parameters
Response latency
Activity patterns
Embeddings
Features converted to vector representations for multimodal fusion
→
Fusion Layer
Combines multimodal features using attention mechanisms
Output
• Overall IC Score
• Domain sub-scores
→
Domain Scores
Locomotor
Cognition
Vitality
Sensory
Psychological
Weekly System Development Breakdown
How each week of HTMAA 2025 builds toward the complete multimodal intrinsic capacity assessment system.
Week 0: Project Ideation
Initial concept development and planning
Project planning and documentation structure
Research direction and concept sketches
Week 1: Precision Cutting
Laser and vinyl cutting techniques
Device housing components via laser cutting
Sensor mounting brackets and enclosures
Vinyl cutting for device labeling and UI elements
Week 2: Embedded Programming
Electronics basics and microcontroller programming
Microcontroller programming for data collection
Basic sensor interface circuits
Week 3: 3D Scanning & Printing
3D technologies for device components
3D scanning for custom component design
3D printing for device housings
Week 4: Electronics Design
EDA and schematic design
PCB design for grip strength measurement
Sensor interface circuits and signal conditioning
Power management and data storage systems
Week 5: Electronics Production
PCB fabrication and assembly
PCB fabrication and debugging
Component assembly and testing
Week 6: Computer-controlled Machining
CAM and precision milling
Precision components via milling
Custom mechanical parts
Week 7: Input Devices
Sensor integration for data collection
Force sensors for grip strength measurement
Microphones for voice analysis
Camera systems for facial expression analysis
Reaction time measurement circuits
Week 8: Output Devices
Actuators and system integration
Display systems for real-time feedback
Haptic feedback for user interaction
Week 9: Molding & Casting
Forming and resin techniques
3D printing and molding for custom components
Silicone casting for device components
Week 10: Mechanical & Machine Design
System integration and mechanical design
Mechanical design for ergonomic device housing
System integration and calibration protocols
Week 11: Networking & Communications
Connectivity and communication protocols
Bluetooth/Wi-Fi connectivity for data transmission
Wearable accelerometer integration and data fusion
Week 12: Interface & Application Programming
UI development and application programming
Mobile app development for user interface
Cloud integration for data storage and analysis
Machine learning pipeline for IC score calculation
Week 13: Wildcard & Final Integration
Final orders and complete system deployment
Final testing, validation, and documentation
System integration and deployment
Camera Subsystem
Advanced camera system implementation using XIAO ESP32S3 Sense with real-time image processing, EdgeAI integration, and interactive selfie capture functionality.
System Overview
The camera system successfully captures images, processes them into bitmaps, and displays them on an OLED screen using advanced Floyd-Steinberg dithering algorithms.
Video Demonstrations
Camera Bot Selfie
Demonstration of the interactive selfie capture system with touch controls
Picture of Picture
Meta demonstration showing the camera system capturing its own display
Code Implementation
60-Second Auto Capture System
Automated camera system that captures and displays images every 60 seconds using advanced image processing techniques.
1. Initialize camera with PSRAM frame buffers
2. Configure OLED display (128x64 pixels)
3. Set up 60-second capture interval timer
4. In main loop:
a. Check if 60 seconds have elapsed
b. Capture image from camera
c. Process image:
- Downsample to 128x64 via box averaging
- Apply contrast stretch (linear scaling)
- Perform Floyd-Steinberg dithering
d. Display processed bitmap on OLED
e. Release frame buffer
5. Repeat process
Touch-Controlled Capture System
Interactive camera system with touch controls allowing manual capture triggers in addition to automatic timing.
1. Initialize camera and OLED display
2. Set up touch pins (GPIO1 & GPIO2) with threshold detection
3. Configure 60-second auto-capture timer
4. In main loop:
a. Update touch sensor readings
b. Detect touch press events (justPressed)
c. Check for capture trigger:
- Touch press OR 60-second timer elapsed
d. If triggered:
- Capture image from camera
- Process image (same as auto version)
- Display on OLED
- Reset timer
5. Continue monitoring for next trigger
The system captures photos, converts them to bitmaps using advanced image processing algorithms, and displays them on the OLED screen.
I'm also exploring integration with ML models, either through online API calls or by embedding TinyML model parameters from Python to C++.
Future development includes live streaming real-time video with ML prediction updates based on variable observation times,
and exploring Edge Impulse models as an alternative to manual Python-to-C++ conversion for faster deployment.
EdgeAI/TinyML Integration
Edge AI can also be implemented using Edge Impulse models, which may be faster than manually converting Python models to C++.
The SenseCraft AI platform provides a streamlined approach to training and deploying ML models directly on the XIAO ESP32S3.
Deploy inference bundle to the SenseCraft board alongside the camera stack.
Benchmark latency and accuracy against baseline VoiceAge models and document calibration protocol.
Week 0 - Introduction & Design
Project ideation and initial concept development for bioprinting rejuvenated tissue and aging biomarker devices.
Project planningConcept sketchesResearch direction
System Integration Plans: Establish the foundational architecture for multimodal data collection by designing the overall system framework that will integrate all six digital biomarkers (grip strength, voice, face, video, reaction time, wearable accelerometer) into a cohesive intrinsic capacity assessment platform.
Mapped the MirrorAge subsystem architecture, assembled the intrinsic capacity literature stack, and kicked off BRR/IRB coordination so fabrication sprints stay aligned with clinical requirements.
Week 1 - Principles & Cutting
Version control, laser cutting, and vinyl cutting techniques applied to final project components.
Laser cuttingVinyl cuttingVersion control
System Integration Plans: Fabricate precision-cut housing components and mounting brackets for all sensor modules (force sensors, microphones, cameras, reaction time circuits) using laser cutting, while creating vinyl-cut labels and UI elements for device identification and user guidance.
Characterized laser kerf, produced the origami mirror frame tiles, and generated vinyl interface labels—locking in enclosure dimensions and user UI cues for the mirror shell.
Week 2 - Embedded Programming
Electronics basics and embedded programming for the aging biomarker device components.
MicrocontrollersProgrammingElectronics
System Integration Plans: Develop embedded programming protocols for real-time data collection from all six biomarker sensors, implementing initial signal processing algorithms and establishing the communication framework for multimodal data fusion.
Built the ReactionAge firmware + enclosure, published the first BOM, and validated timing pipelines that will feed the MirrorAge IC fusion engine.
Week 3 - 3D Scanning & Printing
3D scanning and printing techniques for bioprinting components and device housings.
3D scanning3D printingAI tools
System Integration Plans: Create custom 3D-printed components for camera mounting systems and facial recognition hardware, while developing 3D scanning protocols for ergonomic device design that accommodates all sensor modalities in a user-friendly form factor.
Modeled and printed the torsional grip spring, performed 3D scans for ergonomic fixtures, and captured training assets for face/gait datasets.
Week 4 - Electronics Design
EDA and schematic design for the aging biomarker device electronics.
EDA toolsSchematic designCircuit design
System Integration Plans: Design comprehensive PCB schematics that integrate force sensor circuits for grip strength measurement, microphone preamplifiers for voice analysis, camera interfaces for facial recognition, and timing circuits for reaction time assessment into a unified electronics platform.
Completed the Fusion 360/KiCad schematic/PCB layout for the ESP32S3 carrier tying together force, audio, camera, reaction, and wearable interfaces.
Week 5 - Electronics Production
PCB fabrication, debugging, and assembly for the biomarker device.
PCB fabricationDebuggingAssembly
System Integration Plans: Fabricate and assemble the integrated PCB containing all sensor interfaces, implementing power management systems for continuous operation and establishing data storage protocols for the multimodal biomarker data collection system.
Fabricated and assembled the carrier PCB, brought up power domains, and verified sensor buses—establishing the electronics backbone for integration.
Week 6 - Computer-controlled Machining
CAM and milling for precision components and device housings.
CAMMillingPrecision machining
System Integration Plans: Machine precision mechanical components for the integrated device housing using computer-controlled milling, ensuring proper alignment and mounting for all sensor modules while maintaining ergonomic design for user comfort during multimodal data collection.
Machined the floating mirror base and tensegrity nodes, refining fixturing that ensures repeatable camera and grip alignment in the final assembly.
Week 7 - Input Devices
Sensors and embedded architectures for data collection in the biomarker device.
SensorsInput devicesData collection
System Integration Plans: Integrate all six input sensor systems (force sensors for grip strength, microphones for voice analysis, cameras for facial recognition and gait analysis, reaction time circuits, and wearable accelerometer) into the unified data collection platform with real-time processing capabilities.
Integrated the force sensor, microphone, and ReactionAge modules on the carrier, logging synchronized packets that exercise the multimodal intake stack.
Week 8 - Output Devices
Actuators and system integration for the biomarker device outputs.
ActuatorsOutput devicesSystem integration
System Integration Plans: Implement output devices including display systems for real-time intrinsic capacity feedback and haptic feedback mechanisms for user interaction, creating an intuitive interface for the multimodal biomarker assessment system.
Deployed the SenseCraft FaceTTD pipeline on the XIAO ESP32S3, implemented OLED dithering previews, and confirmed end-to-end edge inference latency.
Week 9 - Molding & Casting
Forming and resin techniques for bioprinting molds and device components.
MoldingCastingResins
System Integration Plans: Create custom molded components for the bioprinting aspects of the project and develop specialized casings for sensor protection, ensuring the device can withstand continuous use during multimodal data collection sessions.
Machined wax molds, cast Mold Star silicone and Drystone ribs, and prototyped arrow-inspired shells that stabilize the mirror and protect embedded sensors.
Week 10 - Mechanical & Machine Design
Kits and mechanical design for the bioprinting and biomarker device systems.
Mechanical designMachine designSystem integration
System Integration Plans: Complete the mechanical design integration of all system components, implementing calibration protocols for sensor alignment and developing the complete mechanical framework that houses all six digital biomarker measurement systems.
Developed mechanical actuation systems including tapping and swiping mechanisms for phone interaction, integrated camera with Edge AI face detection and Wi-Fi livestreaming, designed and 3D-printed phone holder with amplifier, and prepared comprehensive midterm review documentation with system diagrams and timeline.
Week 11 - Networking & Communications
BLE, Wi-Fi, and communication protocols for the biomarker device connectivity.
BLEWi-FiCommunications
System Integration Plans: Implement wireless communication protocols (Bluetooth/Wi-Fi) for seamless data transmission from all six sensor modalities, enabling real-time data fusion and establishing connectivity for the wearable accelerometer integration into the multimodal assessment system.
Implemented Wi-Fi camera livestreaming for real-time video transmission, developed ESP-NOW networking protocols for device communication, designed and milled PCBs for networking components, and explored Meshtastic for long-range communication capabilities.
Week 12 - Interface & Application Programming
UI and application development for the biomarker device interface.
UI designApplicationsUser interface
System Integration Plans: Develop the complete user interface and application programming for the multimodal system, implementing the machine learning pipeline for intrinsic capacity score calculation and creating cloud integration for comprehensive data storage and analysis of all biomarker measurements.
Created Wi-Fi web interface for real-time pulse oximeter readings with live plotting, developed grip strength measurement device with load cell and integrated GUI, implemented OLED button user interface for device control, and established video streaming capabilities for sensor data visualization.
Week 13 - Wildcard & Final Orders
Final orders and wildcard week activities for project completion.
Final ordersWildcard activitiesProject completion
System Integration Plans: Complete final system integration, testing, and validation of the complete multimodal intrinsic capacity assessment platform, ensuring all six digital biomarkers work cohesively to provide accurate WHO-defined intrinsic capacity scores across all five domains (locomotor, cognition, vitality, sensory, psychological).
Designed and fabricated ATtiny1626 tiny development board with fiber laser PCB engraving, created glass engraving system with UV laser including blinking heart integration for visual feedback, milled mounting holes and completed board assembly, and prepared final board designs for system integration.
System Integration
Final integration week focused on bringing all subsystems together, completing hardware fabrication, firmware integration, and documentation for the MirrorAge system presentation. View full details →
Initial system integration work focused on subsystem validation, CAD model consolidation, and design backbone acquisition for band integration. Conducted comprehensive testing of all subsystems to ensure proper functionality, identified and resoldered defective joints, and exported CAD models of all PCBs into a unified assembly model.
Integrated CAD Model: Exploded isometric view of the complete system assembly, including all PCBs, main housing with transparent enclosure, and wearable band components.
Physical integration of subsystems into the complete demo table assembly, including mechanical component fabrication and electrical board consolidation. Integrated the complete demo table with precise placement of the MirrorAge handgrip subsystem and aging clock subsystem, providing a unified platform for system demonstration.
Complete Demo Table Assembly: Integrated mechanical design showing precise placement of the MirrorAge handgrip subsystem and aging clock subsystem on the demo table.
Continued fabrication work integrating all manufacturing processes. Focused on completing physical components including 2D laser cutting, 3D printing of rigid and flexible components, and PCB milling to prepare subsystems for final assembly and testing.
TPU Band Print: Flexible wearable band component printed using TPU material
Flexible Band: TPU band demonstrating material properties and print quality
Comprehensive subsystem integration combining 2D fabrication (laser cutting and vinyl cutting), 3D printing (rigid and flexible components), PCB milling (single and double-sided boards), and molding/casting to complete all physical components. Upgraded MirrorAge TFT board to v13 and aging clock TFT board to v16 with optimized component placement and routing. Established reliable I²C bus communication and validated all sensor addresses.
MirrorAge TFT v13: Upgraded front-side layout with optimized component placement
Aging Clock TFT v16: Upgraded front-side design with rotated components for optimal fit
Final integration day focused on closing the watch subsystem, soldering and verifying all double-sided boards, refining molded bands, and assembling the complete MirrorAge demo with both the aging clock and grip-strength subsystems fully wired and tested. Completed rivet installation for plated through-holes, sensor bring-up (accelerometer, pulse oximeter, OLED/TFT displays), and full system integration on the tensegrity demo table. The integrated system successfully demonstrated synchronized sensor readouts and display behavior across all boards.
Soldered MirrorAge Board: Complete double-sided board with all components installed
Integrated Watch Subsystem: TPU bands fastened into the watch clip with assembled electronics
Working Integrated System: Complete MirrorAge system demonstrating synchronized sensor readouts and display behavior
Final project presentation and demonstration of the complete MirrorAge system. Showcased the integrated aging clock and grip-strength subsystems working together on the demo table, demonstrating real-time sensor data collection and display synchronization. View final presentation demo →
Full Documentation: For complete details, design files, code, and comprehensive documentation of the system integration process, see Week 14: System Integration.
Final Project Masterpiece
Complete demonstration of the integrated MirrorAge system showcasing all subsystems working together in real-time.
Final Presentation Demo: Complete MirrorAge system demonstration showing the integrated aging clock and grip-strength subsystems operating together on the demo table, with synchronized sensor readouts and real-time display updates across all boards.
Complete repository of all design files, CAD models, schematics, PCB layouts, firmware, and fabrication files from Week 0 through Week 14, organized by week and component type.
Note: Additional design files, firmware, and documentation can be found in the respective week pages. Some files are part of larger archives (ZIP files) that contain multiple related design files.
Reflections & Learnings
Comprehensive reflections on the MirrorAge Intrinsic Capacity Mirror project development journey.
Modular system design allows for incremental development and component-level testing throughout the semester
Integration of mechanical, electrical, and software subsystems requires careful planning and coordination
Iterative design and prototyping revealed the importance of early testing and validation
Documentation and knowledge transfer are critical for project continuity and future improvements
The project successfully demonstrates how digital fabrication and embedded systems can create meaningful health assessment tools
Contributions
Acknowledgements and contributions that made this project possible.
Gladyshev Lab and Collaborators
Special thanks to the Gladyshev Lab and collaborators for the fruitful discussions that led to this multimodal intrinsic capacity assessment idea,
which supplements my PhD research goals in aging and longevity. The conceptual framework for integrating multiple digital biomarkers
to assess intrinsic capacity domains emerged from collaborative research discussions on aging biomarkers and healthspan assessment.
Transparent documentation of AI assistance used in this final project work, following course guidelines for ethical AI usage.
📋 General Guidelines: See General Commands for Cursor on the homepage for standard guidelines and commands used consistently throughout documentation development.
Cursor · Project Plan & Weekly Schedule
Comprehensive Cursor AI assistance for outlining the project plan and weekly schedule, including documentation structure, content organization, systematic updates across all week pages and the final project page, media integration, and summary generation workflows.
Cursor AI aligned the midterm review plan with updated system diagram, timeline, and remaining-task summaries, then refreshed finalproject.html to remove legacy bioprinting language and re-point internal links. The full transcript and generated HTML are available for review.
Cursor AI assistance for adding a white background behind the photo in the Final Project Spiral Development Model section on finalproject.html. The image container was updated with white background, padding, and rounded corners for improved visual presentation.
Cursor AI distilled Week 0–9 documentation and the Oct 31 lab meeting deck into midterm-ready narrative, cost, and validation content, replacing every placeholder in finalproject.html.
Transcript archived in markdown and HTML (generated via scripts/md_to_html_converter.py) for transparency.
ChatGPT was used to research and develop the multimodal intrinsic capacity assessment framework, including the comprehensive coverage analysis table and technical pipeline design.
The AI assisted with structuring the WHO-defined intrinsic capacity domains, identifying appropriate digital biomarkers, and designing the fusion architecture for multimodal data processing.
Cursor AI assisted with developing the complete final project page structure, implementing the multimodal intrinsic capacity assessment framework, and creating comprehensive documentation.
The AI helped with HTML structure, responsive design, weekly system integration plans, and organizing the technical documentation for the complete biomarker assessment system.
Cursor AI assisted with finalizing the project presentation structure to ensure full compliance with MIT Academy project presentation requirements.
The AI helped implement all required sections including answering questions, design documentation, bill of materials, individual mastery requirements,
course presentation structure, and spiral model development approach visualization.
ChatGPT was used to discuss camera system implementation strategies, image processing algorithms, and EdgeAI integration approaches.
The AI assisted with understanding Floyd-Steinberg dithering implementation, touch sensor integration, and exploring TinyML deployment options for the XIAO ESP32S3 platform.
AI-Assisted Project Highlights and Camera Subsystem Development
Cursor AI assisted with adding the project highlights section featuring camera system achievements and creating a comprehensive camera subsystem section with detailed code implementations, video demonstrations, and EdgeAI integration documentation.
The AI helped with HTML structure, responsive design, image processing explanations, and organizing the technical documentation for the complete camera system showcase.
Interactive selfie capture system with touch controls and real-time display
Vision Board
Conceptual visualization of the multimodal intrinsic capacity assessment system integrating grip strength, voice analysis, facial recognition, video motion capture, reaction time measurement, and wearable accelerometer data.
Intrinsic Capacity (IC) Coverage by Digital Biomarkers
Domain
Grip
Voice
Face
Video
Reaction Time
Wearable
Locomotor
✅
🔸
🔸
✅
🔸
✅
Cognition
❌
✅
🔸
🔸
✅
🔸
Vitality
✅
✅
✅
✅
🔸
✅
Sensory
❌
✅
✅
✅
✅
🔸
Psychological
❌
✅
✅
✅
🔸
✅
✅ Strong coverage |
🔸 Partial/indirect |
❌ Not covered |
View full table →
Multimodal IC Pipeline
Inputs: Grip Strength, Voice, Face, Video, Reaction Time, Wearable Accelerometer
Development Approach: Following the spiral model methodology, this final project will iterate through multiple development cycles, each building upon previous work while addressing new requirements and risks.
This snapshot covers the subsystems and documentation that will be shown during the midterm review. Links jump directly to the supporting sections with detailed evidence.
Featured Subsystems
Camera subsystem — Edge inference demos and selfie capture loop.
Instructor meeting hold — Thursday, Nov 12 at 10:00 AM ET reserved via the shared HTMAA midterm review sheet.
Execution Schedule (Timeline Snapshot)
Condensed from the Week 8–13 development timeline: each sprint builds toward final integration, mirroring the gantt chart below.
Week 8 · Output Devices: figuring out wiring for real-time display states.
Week 9 · Molding & Casting: learn how to cast custom housings and refine structural components.
Week 10 · Mechanical Design: figure out ergonomic enclosure and calibration fixtures.
Week 11 · Networking: program BLE/Wi-Fi telemetry and wearable data fusion.
Week 12 · Interface/App: create mobile UI, cloud bridge, and IC scoring pipeline.
Week 13 · Final Integration: run validation passes, document results, and prep deployment.
Instructor Review Logistics
Calendar hold sent for Thursday, Nov 12 at 10:00 AM ET (38-501 conference room) per the shared HTMAA scheduling sheet. Agenda covers subsystem demos, weekly documentation spot checks (Weeks 0–9), and next-sprint alignment. Meeting slot referenced in the midterm review schedule; awaiting final confirmation via class Slack.
System Architecture
Updated block diagram highlighting the multimodal sensing stack (grip, voice, face, motion, wearables), on-device inference layers, and real-time feedback channels that feed the intrinsic capacity score.
Development Timeline
Timeline aligns subsystem sprints with HTMAA milestones: output devices (Week 8), molding and casting (Week 9), mechanical design (Week 10), networking and communications (Week 11), app programming (Week 12), and final integration (Week 13).
Remaining Tasks (Snapshot)
Weeks 0–9 locked in the core subsystems—documentation workflow, cutting and molding for the housing, embedded prototypes for reaction timing, SenseCraft camera inference, and early grip/voice rigs. The checklist below captures what still needs to happen to converge on the integrated MirrorAge system.
Hardware Integration
Consolidate grip, voice, camera, reaction-time, and wearable sensor harnesses into the MirrorAge enclosure.
Finish molding/casting iterations for the ergonomic housing and align mounting features for PCBs and haptics.
Firmware & Edge AI
Stabilize onboard inference for SenseCraft vision models and voice-age pipelines on the XIAO ESP32S3.
Calibrate grip-force and reaction-time firmware for repeatable sampling; close the loop to haptic/display feedback.
Networking & Data Fusion
Bring up BLE/Wi-Fi data paths for wearable accelerometer streaming and cloud logging of intrinsic capacity scores.
Implement the fusion layer that combines per-domain scores into an overall IC metric with on-device storage.
Interface & UX
Finish mobile/web dashboard mockups for user onboarding, data review, and device calibration workflows.
Finalize real-time mirror feedback cues (display states, haptics, lighting) tied to sensor status and IC outcomes.
Validation & Documentation
Run end-to-end system tests (sensor capture → fusion → feedback) and document calibration procedures.
Record the one-minute video, finalize final presentation assets, and polish the bill of materials for review.
Week 14 System Integration Plan
Detailed day-by-day schedule for final system integration, covering design, fabrication, programming, testing, and documentation. This plan outlines the path to completing the MirrorAge system integration and preparing for final presentation. View on Week 14 page →
The act of bringing something to a conclusion or ending in a decisive manner. The ability to efficiently finish tasks and projects with a goal-oriented mindset.
Wednesday
Morning
Publish system integration plan on website
Update weekly assignment sections on final project page (weeks 10-13)
Link final project design files
Update reflections and learnings
Update picture of prism holder
Add final pictures to Slack canvases
Create schematic between boards (wired and wireless) — updated system diagram on PPT-like page
Start CAD model of system
Place final order
Afternoon & Evening
Design:
Boards: Combine OLED screen/accelerometer with pulse oximeter board in a new board (maybe upgrade to small TFT as minor)
Boards: Speaker board with realtime amplifier and TFT (on the load cell fixed board)
Band: Mold design
Cases: 3D print mountable cases for the boards
Integrate designs into final CAD
Document design
Finish CAD model of system
Thursday
Fabricate
Milling boards
Print mold and cast band
Print cases
Solder
Solder components on milled boards
Connect boards with wired (and wireless connection codes)
Finishing
Mirror on screen (easy way with the film)
Documentation
Document fabrication
Friday
Programming
Board level codes
Server level codes
Documentation
Document codes
Completion
Finish anything else
Saturday
Programming & Testing
Demo integrated system
Test integrated system
Documentation
Document testing and evaluation
Review and complete documentation (list of questions)
Make the video by collaging documentation
Sunday
Fill up any gaps
Prepare demo on tensegrity table
Finalize 1-slide
Work on minors
If done, work on if there's time
Monday Morning
Transport demo on tensegrity table
Fill up any gaps
Work on minors
Specific Tasks to Complete This Week
Major Tasks
CAD model of system
Speaker board with realtime amplifier
Combine screen/accelerometer with pulse oximeter board in a new board
Mold and cast band
Design and fabricate casing (print)
Schematic between boards (wired and wireless) — updated system diagram on PPT-like page
Serial connection between pulse oximeter and tiny blinking heart for BPM (BPM from IR, SpO2 from delta)
Combine multiple boards on the same WiFi (switching tabs is easy way, board hosting the webpage querying and update or Python-based server somewhere where everything posting data, Raspberry Pi)
Put+program everything together according to the above (with WiFi for now)
MirrorAge is a self-contained edge-AI mirror that captures grip strength, facial imagery, voice, motion, and reaction time to estimate intrinsic capacity in real time.
The platform fuses weekly prototypes—ReactionAge latency tests, 3D printed grip mechanics, SenseCraft camera inference, and molded structural elements—into a multimodal mortality risk profiler.
Subsystems in progress: reaction-time module, SenseCraft FaceTTD inference stack, VoiceAge microphone pipeline, wearable streaming via BLE, and molded structural packaging.
Clinical motivation: translate WHO intrinsic capacity domains into measurable digital biomarkers that flag functional decline earlier than chronological age alone.
Project Goals
Deliver multimodal IC scoring Fuse grip, face, voice, reaction-time, and wearable streams on-device to output an intrinsic capacity score plus domain deltas.
Fabricate modular, serviceable hardware Iterate laser-cut tensegrity mirror shells, 3D printed torsional grips, custom PCBs, and silicone cast fixtures that assemble without bespoke tooling.
Validate against ground truth Benchmark embedded inferences against published datasets (Blomkvist et al. 2017, Fuentealba et al. 2025) and lab-collected pilots to quantify accuracy, latency, and reliability.
Timeline & Milestones
Week 10 · Hardware convergence Integrate SenseCraft FaceTTD camera, ReactionAge latency module, and newly milled PCB into a single ESP32S3 backplane.
Week 12 · Midterm review build Finish molded mirror enclosure, bring up BLE wearable link, and demo live IC score during midterm critique.
Final week · Validation & documentation Execute pilot data collection, refine model weights, and release reproducible fabrication + firmware packages.
Documenting the final project masterpiece that integrates the range of units covered, addressing all required questions.
What does it do?
MirrorAge captures synchronized digital biomarkers—camera frames processed with on-device FaceTTD models, VoiceAge microphone samples, grip strength torque, wearable accelerometry, and ReactionAge latency—to estimate intrinsic capacity and time-to-death acceleration.
A XIAO ESP32S3 Sense orchestrates sensing, performs Edge Impulse inference, and displays a live mortality-risk score on the OLED while logging packets to a Python analytics notebook.
Who's done what beforehand?
The concept builds on WHO intrinsic capacity framing and recent mortality-risk studies: Niccoli & Partridge (2012) establish age as the dominant chronic-disease predictor; Fuentealba et al. (Nature Aging 2025) show blood-based IC clocks outperform chronological models;
Zhavoronkov & Bhullar (2015) and Lancet Healthy Longevity editorials motivate treating functional decline as the actionable signal.
This project translates those findings into an accessible, multimodal measurement mirror that can operate outside hospital labs.
What sources did you use?
Primary references include Nature Aging 2025 intrinsic capacity papers, the PLOS ONE ReactionAge dataset (Blomkvist et al. 2017), Edge Impulse SenseCraft documentation, Smooth‑On Mold Star technical bulletins, RotoMetals alloy certificates, MIT HTMAA recitations, and the open-source GRPR grip-strength meter.
Design inspiration and safety notes were consolidated from Anthony Pennes' HTMA guides and Fab Academy molding tutorials.
What did you design?
• Laser-cut cardboard origami mirror frame and tensegrity-inspired floating mount (Weeks 1 & 6)
• ReactionAge firmware + enclosure with statistical post-processing dashboards (Week 2)
• 3D printed torsional spring grip module tuned for ±40 kg ranges (Week 3)
• KiCad/Fusion carrier PCB for the ESP32S3 Sense with OLED, force, and BLE breakouts (Week 5)
• Edge Impulse deployment pipeline with grayscale dithering overlay and live inference UX (Weeks 7–8)
• CAM toolpaths, silicone molds, and Drystone casts for structural packaging (Week 9)
What materials and components were used?
Seeed XIAO ESP32S3 Sense module with OV2640 camera and PDM mic, SparkFun Qwiic button and force sensors, SSD1306 OLED, wearable IMU node (Bosch BHI260), laser-cut cardboard/birch sheets, PLA+/Onyx filament, Mold Star 30 silicone, Drystone gypsum, Roto281 fusible alloy, and embedded fasteners/heat-set inserts.
Where did they come from?
Electronics from Seeed Studio, SparkFun, Digi-Key, and Adafruit; molding supplies and silicones from Reynolds Advanced Materials; Drystone and Hydro-Stone from USG via the MIT CBA stockroom; fusible alloys from RotoMetals; structural lumber and plywood from MIT's shop inventory; filaments from Prusa Research and Markforged.
How much did they cost?
Current spend: $96.34 for ReactionAge components (Week 2 BOM) + $78.42 for SenseCraft camera stack (XIAO ESP32S3 Sense, OLED, cabling) + $42.10 for molding media (Mold Star 30 quart, Drystone, release agents) = $216.86 to date.
Remaining allocation (~$130) is earmarked for BLE wearable hardware and final enclosure finishes; detailed line items tracked in the Airtable budget and mirrored in each weekly BOM CSV.
What parts and systems were made?
Custom origami mirror frame, 3D printed torsional grip shell, machined floating base, silicone molds and Drystone casts for arrow-inspired structural ribs, bespoke ESP32S3 breakout PCB, laser-cut ReactionAge control panel, and assembled sensor tower linking camera, OLED, and wearable gateway.
What tools and processes were used?
Parametric CAD in Fusion 360, laser cutting (Epilog) for origami tiles, Prusa MK4 FDM printing, Formlabs SLA for detail inserts, ShopBot CNC and Bantam PCB milling, silicone mixing/casting under vacuum, Edge Impulse model training, PlatformIO firmware, and Python/NumPy validation notebooks.
What questions were answered?
• Can consumer-grade sensors reproduce published reaction-time age curves? (Yes—ReactionAge matched Blomkvist et al. regression within 4.6 ms RMSE.)
• Will SenseCraft FaceTTD run locally on ESP32S3 with acceptable latency? (Yes—~310 ms/inference at 30% baseline accuracy, highlighting dataset needs.)
• Does molded packaging improve sensor placement repeatability? (Yes—silicone nests held camera ±0.5 mm, reducing alignment drift seen in cardboard prototypes.)
What worked? What didn't?
✅ Floyd–Steinberg dithering produced clear OLED previews; ✅ ReactionAge firmware maintained ±1 ms jitter; ✅ Molded Drystone ribs stiffened mirror shell without excess weight.
⚠️ FaceTTD accuracy plateaued at 30% due to limited training diversity; ⚠️ VoiceAge requires more MFCC samples to sustain 0.64-year MAE; ⚠️ Grip spring fatigue highlighted need for fiber-reinforced print or machined aluminum insert.
How was it evaluated?
Bench tests compare embedded predictions to published curves and desktop baselines: ReactionAge latency vs. Wii Balance Board golden data; FaceTTD inferencing cross-validated against Edge Impulse cloud classifier; VoiceAge MFCC regression verified through train/holdout splits; mechanical fixtures inspected with feeler gauges and dial indicators for tolerance drift.
What are the implications?
A portable intrinsic capacity mirror supports proactive geriatric screening, telehealth coaching, and longitudinal studies that correlate functional decline with interventions.
By grounding hardware in open-source parts and HTMAA fabrication methods, the system can be replicated across labs and community clinics to accelerate validation of digital aging biomarkers and personalize longevity therapies.
Design
Your project should incorporate 2D and 3D design, multiple additive and subtractive fabrication processes, electronics design and production, embedded microcontroller design, interfacing, and programming, system integration and packaging.
2D Design
2D design work for the multimodal intrinsic capacity assessment system:
Cardboard origami tiling for circular mirror frame, optimized for kerf learned during Week 1 laser characterization.
Vinyl-cut ReactionAge control labels and MirrorAge fascia decals for rapid UI readability.
KiCad/Fusion schematics + polygon pours for ESP32S3 carrier, force sensing front-end, and OLED interposer.
2D shop drawings for CNC floating base, including registration dowels and silicone mold parting lines.
Figma wireframes outlining the midterm web dashboard and on-device OLED states.
Subtractive: Laser cutting, milling for precision parts
Electronics: PCB design and production
Programming: Embedded microcontroller development
Bill of Materials
Where possible, I fabricated parts rather than buying them. This table summarizes all unique components in the final MirrorAge system, their approximate costs, and where they are used.
A mirrored copy of this bill of materials also appears on the Week 14 system-integration page for cross-linking directly from the integration steps
(Week 14 BOM).
Grip-strength molds, band molds, structural ribs
(Week 9,
Week 14)
Fasteners
M2/M3 hardware, heat-set inserts, misc. screws
Assorted
~$0.10–$0.30 ea.
$20.00 (bundle)
All mechanical assemblies (watch, grip rig, camera mount, demo table)
Estimated Total Project Cost
Electronics ≈ $190 · Mechanical & materials ≈ $130 ·
Total ≈ $320 (excluding lab-provided consumables and reused stock).
Exact per-week line items remain in the weekly documentation tables (for example
ReactionAge BOM CSV in Week 2),
while this table captures the consolidated, unique parts that make up the final integrated MirrorAge system.
Fabrication Process
Week-by-week fabrication rolled forward subsystems toward the integrated mirror:
Week 1 laser-cut origami tiles for the circular bezel; Week 2 PCB milling + soldering for ReactionAge;
Week 3–4 torsional spring 3D prints and sanding jigs; Week 5 copper-clad milling and reflow of the ESP32S3 carrier;
Week 6 ShopBot machining of the floating base; Week 8 resin + FDM camera enclosure build; Week 9 wax machining, Mold Star casting, and Drystone ribs.
Each step captured feeds-and-speeds, toolpaths, and fixturing photos embedded in the weekly pages for replication.
Testing & Validation
Validation combined bench instrumentation and statistical analysis: oscilloscope timing to verify ReactionAge jitter, Edge Impulse confusion matrices for FaceTTD and VoiceAge,
Instron pull tests for the torsional grip cartridge, IR thermography while curing Mold Star molds, dial-indicator checks on CNC-machined bases, and adhesive shear testing on mirror mounts.
Data are logged to CSV via the ESP32S3 and compared against published baselines inside the midterm Jupyter notebook.
Individual Mastery and Independent Operation
Projects can be separate or joint, but need to show individual mastery of the skills, and be independently operable.
Individual Mastery
Demonstration of individual skills across all course units:
2D and 3D Design
Modeled the tensegrity floating mirror, torsional grip shells, and camera bezel in Fusion 360 and Onshape.
Drove design reviews with Anthony/Neil to lock tolerances, assembly order, and module interface specs.
Demonstrates mastery across cutting, 3D printing, machining, electronics, networking, and interface programming units.
Documentation cross-linked via weekly pages, GitHub repos, and BOM spreadsheets for traceability.
Group Assignments
Collaborative work and individual contributions:
Embedded programming group: authored workflow trade-off analysis and repo organization that seeded ReactionAge firmware patterns.
Molding & casting group: led SDS review, material trials, and mixing SOP that informed final mirror mold.
Shared camera dev sessions with peers to improve Edge Impulse dataset collection and SenseCraft deployment strategies.
Useful Documentation
Helpful resources, documentation, and design files for the multimodal intrinsic capacity assessment system.
Open Source Grip Strength Meter
A cost-effective $50 grip strength measurement system that can be further optimized for our multimodal assessment platform.
This open-source design provides an excellent foundation for integrating grip strength measurement into our intrinsic capacity assessment system,
with potential for cost reduction through signal multiplexing on a single processor.
Detailed technical pipeline for processing multiple digital biomarkers to generate intrinsic capacity scores.
Pipeline Architecture
Inputs
• Grip Strength
• Voice
• Face
• Video (motion/gait)
• Reaction Time
• Wearable Accelerometer
→
Feature Extraction
Strength metrics
Prosody features
Facial landmarks
Gait parameters
Response latency
Activity patterns
Embeddings
Features converted to vector representations for multimodal fusion
→
Fusion Layer
Combines multimodal features using attention mechanisms
Output
• Overall IC Score
• Domain sub-scores
→
Domain Scores
Locomotor
Cognition
Vitality
Sensory
Psychological
Weekly System Development Breakdown
How each week of HTMAA 2025 builds toward the complete multimodal intrinsic capacity assessment system.
Week 0: Project Ideation
Initial concept development and planning
Project planning and documentation structure
Research direction and concept sketches
Week 1: Precision Cutting
Laser and vinyl cutting techniques
Device housing components via laser cutting
Sensor mounting brackets and enclosures
Vinyl cutting for device labeling and UI elements
Week 2: Embedded Programming
Electronics basics and microcontroller programming
Microcontroller programming for data collection
Basic sensor interface circuits
Week 3: 3D Scanning & Printing
3D technologies for device components
3D scanning for custom component design
3D printing for device housings
Week 4: Electronics Design
EDA and schematic design
PCB design for grip strength measurement
Sensor interface circuits and signal conditioning
Power management and data storage systems
Week 5: Electronics Production
PCB fabrication and assembly
PCB fabrication and debugging
Component assembly and testing
Week 6: Computer-controlled Machining
CAM and precision milling
Precision components via milling
Custom mechanical parts
Week 7: Input Devices
Sensor integration for data collection
Force sensors for grip strength measurement
Microphones for voice analysis
Camera systems for facial expression analysis
Reaction time measurement circuits
Week 8: Output Devices
Actuators and system integration
Display systems for real-time feedback
Haptic feedback for user interaction
Week 9: Molding & Casting
Forming and resin techniques
3D printing and molding for custom components
Silicone casting for device components
Week 10: Mechanical & Machine Design
System integration and mechanical design
Mechanical design for ergonomic device housing
System integration and calibration protocols
Week 11: Networking & Communications
Connectivity and communication protocols
Bluetooth/Wi-Fi connectivity for data transmission
Wearable accelerometer integration and data fusion
Week 12: Interface & Application Programming
UI development and application programming
Mobile app development for user interface
Cloud integration for data storage and analysis
Machine learning pipeline for IC score calculation
Week 13: Wildcard & Final Integration
Final orders and complete system deployment
Final testing, validation, and documentation
System integration and deployment
Camera Subsystem
Advanced camera system implementation using XIAO ESP32S3 Sense with real-time image processing, EdgeAI integration, and interactive selfie capture functionality.
System Overview
The camera system successfully captures images, processes them into bitmaps, and displays them on an OLED screen using advanced Floyd-Steinberg dithering algorithms.
Video Demonstrations
Camera Bot Selfie
Demonstration of the interactive selfie capture system with touch controls
Picture of Picture
Meta demonstration showing the camera system capturing its own display
Code Implementation
60-Second Auto Capture System
Automated camera system that captures and displays images every 60 seconds using advanced image processing techniques.
1. Initialize camera with PSRAM frame buffers
2. Configure OLED display (128x64 pixels)
3. Set up 60-second capture interval timer
4. In main loop:
a. Check if 60 seconds have elapsed
b. Capture image from camera
c. Process image:
- Downsample to 128x64 via box averaging
- Apply contrast stretch (linear scaling)
- Perform Floyd-Steinberg dithering
d. Display processed bitmap on OLED
e. Release frame buffer
5. Repeat process
Touch-Controlled Capture System
Interactive camera system with touch controls allowing manual capture triggers in addition to automatic timing.
1. Initialize camera and OLED display
2. Set up touch pins (GPIO1 & GPIO2) with threshold detection
3. Configure 60-second auto-capture timer
4. In main loop:
a. Update touch sensor readings
b. Detect touch press events (justPressed)
c. Check for capture trigger:
- Touch press OR 60-second timer elapsed
d. If triggered:
- Capture image from camera
- Process image (same as auto version)
- Display on OLED
- Reset timer
5. Continue monitoring for next trigger
The system captures photos, converts them to bitmaps using advanced image processing algorithms, and displays them on the OLED screen.
I'm also exploring integration with ML models, either through online API calls or by embedding TinyML model parameters from Python to C++.
Future development includes live streaming real-time video with ML prediction updates based on variable observation times,
and exploring Edge Impulse models as an alternative to manual Python-to-C++ conversion for faster deployment.
EdgeAI/TinyML Integration
Edge AI can also be implemented using Edge Impulse models, which may be faster than manually converting Python models to C++.
The SenseCraft AI platform provides a streamlined approach to training and deploying ML models directly on the XIAO ESP32S3.
Deploy inference bundle to the SenseCraft board alongside the camera stack.
Benchmark latency and accuracy against baseline VoiceAge models and document calibration protocol.
Week 0 - Introduction & Design
Project ideation and initial concept development for bioprinting rejuvenated tissue and aging biomarker devices.
Project planningConcept sketchesResearch direction
System Integration Plans: Establish the foundational architecture for multimodal data collection by designing the overall system framework that will integrate all six digital biomarkers (grip strength, voice, face, video, reaction time, wearable accelerometer) into a cohesive intrinsic capacity assessment platform.
Mapped the MirrorAge subsystem architecture, assembled the intrinsic capacity literature stack, and kicked off BRR/IRB coordination so fabrication sprints stay aligned with clinical requirements.
Week 1 - Principles & Cutting
Version control, laser cutting, and vinyl cutting techniques applied to final project components.
Laser cuttingVinyl cuttingVersion control
System Integration Plans: Fabricate precision-cut housing components and mounting brackets for all sensor modules (force sensors, microphones, cameras, reaction time circuits) using laser cutting, while creating vinyl-cut labels and UI elements for device identification and user guidance.
Characterized laser kerf, produced the origami mirror frame tiles, and generated vinyl interface labels—locking in enclosure dimensions and user UI cues for the mirror shell.
Week 2 - Embedded Programming
Electronics basics and embedded programming for the aging biomarker device components.
MicrocontrollersProgrammingElectronics
System Integration Plans: Develop embedded programming protocols for real-time data collection from all six biomarker sensors, implementing initial signal processing algorithms and establishing the communication framework for multimodal data fusion.
Built the ReactionAge firmware + enclosure, published the first BOM, and validated timing pipelines that will feed the MirrorAge IC fusion engine.
Week 3 - 3D Scanning & Printing
3D scanning and printing techniques for bioprinting components and device housings.
3D scanning3D printingAI tools
System Integration Plans: Create custom 3D-printed components for camera mounting systems and facial recognition hardware, while developing 3D scanning protocols for ergonomic device design that accommodates all sensor modalities in a user-friendly form factor.
Modeled and printed the torsional grip spring, performed 3D scans for ergonomic fixtures, and captured training assets for face/gait datasets.
Week 4 - Electronics Design
EDA and schematic design for the aging biomarker device electronics.
EDA toolsSchematic designCircuit design
System Integration Plans: Design comprehensive PCB schematics that integrate force sensor circuits for grip strength measurement, microphone preamplifiers for voice analysis, camera interfaces for facial recognition, and timing circuits for reaction time assessment into a unified electronics platform.
Completed the Fusion 360/KiCad schematic/PCB layout for the ESP32S3 carrier tying together force, audio, camera, reaction, and wearable interfaces.
Week 5 - Electronics Production
PCB fabrication, debugging, and assembly for the biomarker device.
PCB fabricationDebuggingAssembly
System Integration Plans: Fabricate and assemble the integrated PCB containing all sensor interfaces, implementing power management systems for continuous operation and establishing data storage protocols for the multimodal biomarker data collection system.
Fabricated and assembled the carrier PCB, brought up power domains, and verified sensor buses—establishing the electronics backbone for integration.
Week 6 - Computer-controlled Machining
CAM and milling for precision components and device housings.
CAMMillingPrecision machining
System Integration Plans: Machine precision mechanical components for the integrated device housing using computer-controlled milling, ensuring proper alignment and mounting for all sensor modules while maintaining ergonomic design for user comfort during multimodal data collection.
Machined the floating mirror base and tensegrity nodes, refining fixturing that ensures repeatable camera and grip alignment in the final assembly.
Week 7 - Input Devices
Sensors and embedded architectures for data collection in the biomarker device.
SensorsInput devicesData collection
System Integration Plans: Integrate all six input sensor systems (force sensors for grip strength, microphones for voice analysis, cameras for facial recognition and gait analysis, reaction time circuits, and wearable accelerometer) into the unified data collection platform with real-time processing capabilities.
Integrated the force sensor, microphone, and ReactionAge modules on the carrier, logging synchronized packets that exercise the multimodal intake stack.
Week 8 - Output Devices
Actuators and system integration for the biomarker device outputs.
ActuatorsOutput devicesSystem integration
System Integration Plans: Implement output devices including display systems for real-time intrinsic capacity feedback and haptic feedback mechanisms for user interaction, creating an intuitive interface for the multimodal biomarker assessment system.
Deployed the SenseCraft FaceTTD pipeline on the XIAO ESP32S3, implemented OLED dithering previews, and confirmed end-to-end edge inference latency.
Week 9 - Molding & Casting
Forming and resin techniques for bioprinting molds and device components.
MoldingCastingResins
System Integration Plans: Create custom molded components for the bioprinting aspects of the project and develop specialized casings for sensor protection, ensuring the device can withstand continuous use during multimodal data collection sessions.
Machined wax molds, cast Mold Star silicone and Drystone ribs, and prototyped arrow-inspired shells that stabilize the mirror and protect embedded sensors.
Week 10 - Mechanical & Machine Design
Kits and mechanical design for the bioprinting and biomarker device systems.
Mechanical designMachine designSystem integration
System Integration Plans: Complete the mechanical design integration of all system components, implementing calibration protocols for sensor alignment and developing the complete mechanical framework that houses all six digital biomarker measurement systems.
Developed mechanical actuation systems including tapping and swiping mechanisms for phone interaction, integrated camera with Edge AI face detection and Wi-Fi livestreaming, designed and 3D-printed phone holder with amplifier, and prepared comprehensive midterm review documentation with system diagrams and timeline.
Week 11 - Networking & Communications
BLE, Wi-Fi, and communication protocols for the biomarker device connectivity.
BLEWi-FiCommunications
System Integration Plans: Implement wireless communication protocols (Bluetooth/Wi-Fi) for seamless data transmission from all six sensor modalities, enabling real-time data fusion and establishing connectivity for the wearable accelerometer integration into the multimodal assessment system.
Implemented Wi-Fi camera livestreaming for real-time video transmission, developed ESP-NOW networking protocols for device communication, designed and milled PCBs for networking components, and explored Meshtastic for long-range communication capabilities.
Week 12 - Interface & Application Programming
UI and application development for the biomarker device interface.
UI designApplicationsUser interface
System Integration Plans: Develop the complete user interface and application programming for the multimodal system, implementing the machine learning pipeline for intrinsic capacity score calculation and creating cloud integration for comprehensive data storage and analysis of all biomarker measurements.
Created Wi-Fi web interface for real-time pulse oximeter readings with live plotting, developed grip strength measurement device with load cell and integrated GUI, implemented OLED button user interface for device control, and established video streaming capabilities for sensor data visualization.
Week 13 - Wildcard & Final Orders
Final orders and wildcard week activities for project completion.
Final ordersWildcard activitiesProject completion
System Integration Plans: Complete final system integration, testing, and validation of the complete multimodal intrinsic capacity assessment platform, ensuring all six digital biomarkers work cohesively to provide accurate WHO-defined intrinsic capacity scores across all five domains (locomotor, cognition, vitality, sensory, psychological).
Designed and fabricated ATtiny1626 tiny development board with fiber laser PCB engraving, created glass engraving system with UV laser including blinking heart integration for visual feedback, milled mounting holes and completed board assembly, and prepared final board designs for system integration.
System Integration
Final integration week focused on bringing all subsystems together, completing hardware fabrication, firmware integration, and documentation for the MirrorAge system presentation. View full details →
Initial system integration work focused on subsystem validation, CAD model consolidation, and design backbone acquisition for band integration. Conducted comprehensive testing of all subsystems to ensure proper functionality, identified and resoldered defective joints, and exported CAD models of all PCBs into a unified assembly model.
Integrated CAD Model: Exploded isometric view of the complete system assembly, including all PCBs, main housing with transparent enclosure, and wearable band components.
Physical integration of subsystems into the complete demo table assembly, including mechanical component fabrication and electrical board consolidation. Integrated the complete demo table with precise placement of the MirrorAge handgrip subsystem and aging clock subsystem, providing a unified platform for system demonstration.
Complete Demo Table Assembly: Integrated mechanical design showing precise placement of the MirrorAge handgrip subsystem and aging clock subsystem on the demo table.
Continued fabrication work integrating all manufacturing processes. Focused on completing physical components including 2D laser cutting, 3D printing of rigid and flexible components, and PCB milling to prepare subsystems for final assembly and testing.
TPU Band Print: Flexible wearable band component printed using TPU material
Flexible Band: TPU band demonstrating material properties and print quality
Comprehensive subsystem integration combining 2D fabrication (laser cutting and vinyl cutting), 3D printing (rigid and flexible components), PCB milling (single and double-sided boards), and molding/casting to complete all physical components. Upgraded MirrorAge TFT board to v13 and aging clock TFT board to v16 with optimized component placement and routing. Established reliable I²C bus communication and validated all sensor addresses.
MirrorAge TFT v13: Upgraded front-side layout with optimized component placement
Aging Clock TFT v16: Upgraded front-side design with rotated components for optimal fit
Final integration day focused on closing the watch subsystem, soldering and verifying all double-sided boards, refining molded bands, and assembling the complete MirrorAge demo with both the aging clock and grip-strength subsystems fully wired and tested. Completed rivet installation for plated through-holes, sensor bring-up (accelerometer, pulse oximeter, OLED/TFT displays), and full system integration on the tensegrity demo table. The integrated system successfully demonstrated synchronized sensor readouts and display behavior across all boards.
Soldered MirrorAge Board: Complete double-sided board with all components installed
Integrated Watch Subsystem: TPU bands fastened into the watch clip with assembled electronics
Working Integrated System: Complete MirrorAge system demonstrating synchronized sensor readouts and display behavior
Final project presentation and demonstration of the complete MirrorAge system. Showcased the integrated aging clock and grip-strength subsystems working together on the demo table, demonstrating real-time sensor data collection and display synchronization. View final presentation demo →
Final Presentation Demo: Complete MirrorAge system demonstration showing integrated aging clock and grip-strength subsystems operating together in real-time
Full Documentation: For complete details, design files, code, and comprehensive documentation of the system integration process, see Week 14: System Integration.
Final Project Masterpiece
Complete demonstration of the integrated MirrorAge system showcasing all subsystems working together in real-time.
Final Presentation Demo: Complete MirrorAge system demonstration showing the integrated aging clock and grip-strength subsystems operating together on the demo table, with synchronized sensor readouts and real-time display updates across all boards.
Complete repository of all design files, CAD models, schematics, PCB layouts, firmware, and fabrication files from Week 0 through Week 14, organized by week and component type.
Note: Additional design files, firmware, and documentation can be found in the respective week pages. Some files are part of larger archives (ZIP files) that contain multiple related design files.
Reflections & Learnings
Comprehensive reflections on the MirrorAge Intrinsic Capacity Mirror project development journey.
Modular system design allows for incremental development and component-level testing throughout the semester
Integration of mechanical, electrical, and software subsystems requires careful planning and coordination
Iterative design and prototyping revealed the importance of early testing and validation
Documentation and knowledge transfer are critical for project continuity and future improvements
The project successfully demonstrates how digital fabrication and embedded systems can create meaningful health assessment tools
Contributions
Acknowledgements and contributions that made this project possible.
Gladyshev Lab and Collaborators
Special thanks to the Gladyshev Lab and collaborators for the fruitful discussions that led to this multimodal intrinsic capacity assessment idea,
which supplements my PhD research goals in aging and longevity. The conceptual framework for integrating multiple digital biomarkers
to assess intrinsic capacity domains emerged from collaborative research discussions on aging biomarkers and healthspan assessment.
Transparent documentation of AI assistance used in this final project work, following course guidelines for ethical AI usage.
📋 General Guidelines: See General Commands for Cursor on the homepage for standard guidelines and commands used consistently throughout documentation development.
Cursor · Project Plan & Weekly Schedule
Comprehensive Cursor AI assistance for outlining the project plan and weekly schedule, including documentation structure, content organization, systematic updates across all week pages and the final project page, media integration, and summary generation workflows.
Cursor AI aligned the midterm review plan with updated system diagram, timeline, and remaining-task summaries, then refreshed finalproject.html to remove legacy bioprinting language and re-point internal links. The full transcript and generated HTML are available for review.
Cursor AI assistance for adding a white background behind the photo in the Final Project Spiral Development Model section on finalproject.html. The image container was updated with white background, padding, and rounded corners for improved visual presentation.
Cursor AI distilled Week 0–9 documentation and the Oct 31 lab meeting deck into midterm-ready narrative, cost, and validation content, replacing every placeholder in finalproject.html.
Transcript archived in markdown and HTML (generated via scripts/md_to_html_converter.py) for transparency.
ChatGPT was used to research and develop the multimodal intrinsic capacity assessment framework, including the comprehensive coverage analysis table and technical pipeline design.
The AI assisted with structuring the WHO-defined intrinsic capacity domains, identifying appropriate digital biomarkers, and designing the fusion architecture for multimodal data processing.
Cursor AI assisted with developing the complete final project page structure, implementing the multimodal intrinsic capacity assessment framework, and creating comprehensive documentation.
The AI helped with HTML structure, responsive design, weekly system integration plans, and organizing the technical documentation for the complete biomarker assessment system.
Cursor AI assisted with finalizing the project presentation structure to ensure full compliance with MIT Academy project presentation requirements.
The AI helped implement all required sections including answering questions, design documentation, bill of materials, individual mastery requirements,
course presentation structure, and spiral model development approach visualization.
ChatGPT was used to discuss camera system implementation strategies, image processing algorithms, and EdgeAI integration approaches.
The AI assisted with understanding Floyd-Steinberg dithering implementation, touch sensor integration, and exploring TinyML deployment options for the XIAO ESP32S3 platform.
AI-Assisted Project Highlights and Camera Subsystem Development
Cursor AI assisted with adding the project highlights section featuring camera system achievements and creating a comprehensive camera subsystem section with detailed code implementations, video demonstrations, and EdgeAI integration documentation.
The AI helped with HTML structure, responsive design, image processing explanations, and organizing the technical documentation for the complete camera system showcase.
```
Added key images and videos from week14.html to each day's summary in the system integration section:
## Added Media by Day:
**Day 1: Design Integration**
- Integrated CAD model image showing the complete system assembly
**Day 2: Electrical and Mechanical Integration**
- Demo table assembly image showing the integrated subsystems
**Day 3: Fabrication Integration**
- Two TPU band print images showing flexible wearable components
**Day 4: Subsystem Integration**
- MirrorAge TFT board v13 front image
- Aging Clock TFT board v16 front image
**Day 5: Full System Integration**
- Soldered MirrorAge board front image
- Integrated watch subsystem image
- Working integrated system video showing the complete system in action
**Day 6: Final Presentation**
- Final presentation demo video showing the complete MirrorAge system demonstration
All media includes captions and links to the detailed sections in week14.html. The summaries are concise and include the most relevant visuals for each day.
---
**User**
in the summary of week14.html get rid of vinyl cutting i didnt do any vinyl cutting, also add some more key images images/videos of the laser cutting, the milling, the soldering, the testing, etc. for each subsection
---
**Cursor**
Removing vinyl cutting from the Day 4 summary and adding more key images/videos for laser cutting, milling, soldering, and testing. Checking week14.html for relevant media:
Checking for soldering and testing media in Day 5:
Updating Day 4 and Day 5 summaries: removing vinyl cutting and adding more images/videos.
```html
Final Project · HTMAA 2025 · Saleem A. Al Dajani
Interactive selfie capture system with touch controls and real-time display
Vision Board
Conceptual visualization of the multimodal intrinsic capacity assessment system integrating grip strength, voice analysis, facial recognition, video motion capture, reaction time measurement, and wearable accelerometer data.
Intrinsic Capacity (IC) Coverage by Digital Biomarkers
Domain
Grip
Voice
Face
Video
Reaction Time
Wearable
Locomotor
✅
🔸
🔸
✅
🔸
✅
Cognition
❌
✅
🔸
🔸
✅
🔸
Vitality
✅
✅
✅
✅
🔸
✅
Sensory
❌
✅
✅
✅
✅
🔸
Psychological
❌
✅
✅
✅
🔸
✅
✅ Strong coverage |
🔸 Partial/indirect |
❌ Not covered |
View full table →
Multimodal IC Pipeline
Inputs: Grip Strength, Voice, Face, Video, Reaction Time, Wearable Accelerometer
Development Approach: Following the spiral model methodology, this final project will iterate through multiple development cycles, each building upon previous work while addressing new requirements and risks.
This snapshot covers the subsystems and documentation that will be shown during the midterm review. Links jump directly to the supporting sections with detailed evidence.
Featured Subsystems
Camera subsystem — Edge inference demos and selfie capture loop.
Instructor meeting hold — Thursday, Nov 12 at 10:00 AM ET reserved via the shared HTMAA midterm review sheet.
Execution Schedule (Timeline Snapshot)
Condensed from the Week 8–13 development timeline: each sprint builds toward final integration, mirroring the gantt chart below.
Week 8 · Output Devices: figuring out wiring for real-time display states.
Week 9 · Molding & Casting: learn how to cast custom housings and refine structural components.
Week 10 · Mechanical Design: figure out ergonomic enclosure and calibration fixtures.
Week 11 · Networking: program BLE/Wi-Fi telemetry and wearable data fusion.
Week 12 · Interface/App: create mobile UI, cloud bridge, and IC scoring pipeline.
Week 13 · Final Integration: run validation passes, document results, and prep deployment.
Instructor Review Logistics
Calendar hold sent for Thursday, Nov 12 at 10:00 AM ET (38-501 conference room) per the shared HTMAA scheduling sheet. Agenda covers subsystem demos, weekly documentation spot checks (Weeks 0–9), and next-sprint alignment. Meeting slot referenced in the midterm review schedule; awaiting final confirmation via class Slack.
System Architecture
Updated block diagram highlighting the multimodal sensing stack (grip, voice, face, motion, wearables), on-device inference layers, and real-time feedback channels that feed the intrinsic capacity score.
Development Timeline
Timeline aligns subsystem sprints with HTMAA milestones: output devices (Week 8), molding and casting (Week 9), mechanical design (Week 10), networking and communications (Week 11), app programming (Week 12), and final integration (Week 13).
Remaining Tasks (Snapshot)
Weeks 0–9 locked in the core subsystems—documentation workflow, cutting and molding for the housing, embedded prototypes for reaction timing, SenseCraft camera inference, and early grip/voice rigs. The checklist below captures what still needs to happen to converge on the integrated MirrorAge system.
Hardware Integration
Consolidate grip, voice, camera, reaction-time, and wearable sensor harnesses into the MirrorAge enclosure.
Finish molding/casting iterations for the ergonomic housing and align mounting features for PCBs and haptics.
Firmware & Edge AI
Stabilize onboard inference for SenseCraft vision models and voice-age pipelines on the XIAO ESP32S3.
Calibrate grip-force and reaction-time firmware for repeatable sampling; close the loop to haptic/display feedback.
Networking & Data Fusion
Bring up BLE/Wi-Fi data paths for wearable accelerometer streaming and cloud logging of intrinsic capacity scores.
Implement the fusion layer that combines per-domain scores into an overall IC metric with on-device storage.
Interface & UX
Finish mobile/web dashboard mockups for user onboarding, data review, and device calibration workflows.
Finalize real-time mirror feedback cues (display states, haptics, lighting) tied to sensor status and IC outcomes.
Validation & Documentation
Run end-to-end system tests (sensor capture → fusion → feedback) and document calibration procedures.
Record the one-minute video, finalize final presentation assets, and polish the bill of materials for review.
Week 14 System Integration Plan
Detailed day-by-day schedule for final system integration, covering design, fabrication, programming, testing, and documentation. This plan outlines the path to completing the MirrorAge system integration and preparing for final presentation. View on Week 14 page →
The act of bringing something to a conclusion or ending in a decisive manner. The ability to efficiently finish tasks and projects with a goal-oriented mindset.
Wednesday
Morning
Publish system integration plan on website
Update weekly assignment sections on final project page (weeks 10-13)
Link final project design files
Update reflections and learnings
Update picture of prism holder
Add final pictures to Slack canvases
Create schematic between boards (wired and wireless) — updated system diagram on PPT-like page
Start CAD model of system
Place final order
Afternoon & Evening
Design:
Boards: Combine OLED screen/accelerometer with pulse oximeter board in a new board (maybe upgrade to small TFT as minor)
Boards: Speaker board with realtime amplifier and TFT (on the load cell fixed board)
Band: Mold design
Cases: 3D print mountable cases for the boards
Integrate designs into final CAD
Document design
Finish CAD model of system
Thursday
Fabricate
Milling boards
Print mold and cast band
Print cases
Solder
Solder components on milled boards
Connect boards with wired (and wireless connection codes)
Finishing
Mirror on screen (easy way with the film)
Documentation
Document fabrication
Friday
Programming
Board level codes
Server level codes
Documentation
Document codes
Completion
Finish anything else
Saturday
Programming & Testing
Demo integrated system
Test integrated system
Documentation
Document testing and evaluation
Review and complete documentation (list of questions)
Make the video by collaging documentation
Sunday
Fill up any gaps
Prepare demo on tensegrity table
Finalize 1-slide
Work on minors
If done, work on if there's time
Monday Morning
Transport demo on tensegrity table
Fill up any gaps
Work on minors
Specific Tasks to Complete This Week
Major Tasks
CAD model of system
Speaker board with realtime amplifier
Combine screen/accelerometer with pulse oximeter board in a new board
Mold and cast band
Design and fabricate casing (print)
Schematic between boards (wired and wireless) — updated system diagram on PPT-like page
Serial connection between pulse oximeter and tiny blinking heart for BPM (BPM from IR, SpO2 from delta)
Combine multiple boards on the same WiFi (switching tabs is easy way, board hosting the webpage querying and update or Python-based server somewhere where everything posting data, Raspberry Pi)
Put+program everything together according to the above (with WiFi for now)
MirrorAge is a self-contained edge-AI mirror that captures grip strength, facial imagery, voice, motion, and reaction time to estimate intrinsic capacity in real time.
The platform fuses weekly prototypes—ReactionAge latency tests, 3D printed grip mechanics, SenseCraft camera inference, and molded structural elements—into a multimodal mortality risk profiler.
Subsystems in progress: reaction-time module, SenseCraft FaceTTD inference stack, VoiceAge microphone pipeline, wearable streaming via BLE, and molded structural packaging.
Clinical motivation: translate WHO intrinsic capacity domains into measurable digital biomarkers that flag functional decline earlier than chronological age alone.
Project Goals
Deliver multimodal IC scoring Fuse grip, face, voice, reaction-time, and wearable streams on-device to output an intrinsic capacity score plus domain deltas.
Fabricate modular, serviceable hardware Iterate laser-cut tensegrity mirror shells, 3D printed torsional grips, custom PCBs, and silicone cast fixtures that assemble without bespoke tooling.
Validate against ground truth Benchmark embedded inferences against published datasets (Blomkvist et al. 2017, Fuentealba et al. 2025) and lab-collected pilots to quantify accuracy, latency, and reliability.
Timeline & Milestones
Week 10 · Hardware convergence Integrate SenseCraft FaceTTD camera, ReactionAge latency module, and newly milled PCB into a single ESP32S3 backplane.
Week 12 · Midterm review build Finish molded mirror enclosure, bring up BLE wearable link, and demo live IC score during midterm critique.
Final week · Validation & documentation Execute pilot data collection, refine model weights, and release reproducible fabrication + firmware packages.
Documenting the final project masterpiece that integrates the range of units covered, addressing all required questions.
What does it do?
MirrorAge captures synchronized digital biomarkers—camera frames processed with on-device FaceTTD models, VoiceAge microphone samples, grip strength torque, wearable accelerometry, and ReactionAge latency—to estimate intrinsic capacity and time-to-death acceleration.
A XIAO ESP32S3 Sense orchestrates sensing, performs Edge Impulse inference, and displays a live mortality-risk score on the OLED while logging packets to a Python analytics notebook.
Who's done what beforehand?
The concept builds on WHO intrinsic capacity framing and recent mortality-risk studies: Niccoli & Partridge (2012) establish age as the dominant chronic-disease predictor; Fuentealba et al. (Nature Aging 2025) show blood-based IC clocks outperform chronological models;
Zhavoronkov & Bhullar (2015) and Lancet Healthy Longevity editorials motivate treating functional decline as the actionable signal.
This project translates those findings into an accessible, multimodal measurement mirror that can operate outside hospital labs.
What sources did you use?
Primary references include Nature Aging 2025 intrinsic capacity papers, the PLOS ONE ReactionAge dataset (Blomkvist et al. 2017), Edge Impulse SenseCraft documentation, Smooth‑On Mold Star technical bulletins, RotoMetals alloy certificates, MIT HTMAA recitations, and the open-source GRPR grip-strength meter.
Design inspiration and safety notes were consolidated from Anthony Pennes' HTMA guides and Fab Academy molding tutorials.
What did you design?
• Laser-cut cardboard origami mirror frame and tensegrity-inspired floating mount (Weeks 1 & 6)
• ReactionAge firmware + enclosure with statistical post-processing dashboards (Week 2)
• 3D printed torsional spring grip module tuned for ±40 kg ranges (Week 3)
• KiCad/Fusion carrier PCB for the ESP32S3 Sense with OLED, force, and BLE breakouts (Week 5)
• Edge Impulse deployment pipeline with grayscale dithering overlay and live inference UX (Weeks 7–8)
• CAM toolpaths, silicone molds, and Drystone casts for structural packaging (Week 9)
What materials and components were used?
Seeed XIAO ESP32S3 Sense module with OV2640 camera and PDM mic, SparkFun Qwiic button and force sensors, SSD1306 OLED, wearable IMU node (Bosch BHI260), laser-cut cardboard/birch sheets, PLA+/Onyx filament, Mold Star 30 silicone, Drystone gypsum, Roto281 fusible alloy, and embedded fasteners/heat-set inserts.
Where did they come from?
Electronics from Seeed Studio, SparkFun, Digi-Key, and Adafruit; molding supplies and silicones from Reynolds Advanced Materials; Drystone and Hydro-Stone from USG via the MIT CBA stockroom; fusible alloys from RotoMetals; structural lumber and plywood from MIT's shop inventory; filaments from Prusa Research and Markforged.
How much did they cost?
Current spend: $96.34 for ReactionAge components (Week 2 BOM) + $78.42 for SenseCraft camera stack (XIAO ESP32S3 Sense, OLED, cabling) + $42.10 for molding media (Mold Star 30 quart, Drystone, release agents) = $216.86 to date.
Remaining allocation (~$130) is earmarked for BLE wearable hardware and final enclosure finishes; detailed line items tracked in the Airtable budget and mirrored in each weekly BOM CSV.
What parts and systems were made?
Custom origami mirror frame, 3D printed torsional grip shell, machined floating base, silicone molds and Drystone casts for arrow-inspired structural ribs, bespoke ESP32S3 breakout PCB, laser-cut ReactionAge control panel, and assembled sensor tower linking camera, OLED, and wearable gateway.
What tools and processes were used?
Parametric CAD in Fusion 360, laser cutting (Epilog) for origami tiles, Prusa MK4 FDM printing, Formlabs SLA for detail inserts, ShopBot CNC and Bantam PCB milling, silicone mixing/casting under vacuum, Edge Impulse model training, PlatformIO firmware, and Python/NumPy validation notebooks.
What questions were answered?
• Can consumer-grade sensors reproduce published reaction-time age curves? (Yes—ReactionAge matched Blomkvist et al. regression within 4.6 ms RMSE.)
• Will SenseCraft FaceTTD run locally on ESP32S3 with acceptable latency? (Yes—~310 ms/inference at 30% baseline accuracy, highlighting dataset needs.)
• Does molded packaging improve sensor placement repeatability? (Yes—silicone nests held camera ±0.5 mm, reducing alignment drift seen in cardboard prototypes.)
What worked? What didn't?
✅ Floyd–Steinberg dithering produced clear OLED previews; ✅ ReactionAge firmware maintained ±1 ms jitter; ✅ Molded Drystone ribs stiffened mirror shell without excess weight.
⚠️ FaceTTD accuracy plateaued at 30% due to limited training diversity; ⚠️ VoiceAge requires more MFCC samples to sustain 0.64-year MAE; ⚠️ Grip spring fatigue highlighted need for fiber-reinforced print or machined aluminum insert.
How was it evaluated?
Bench tests compare embedded predictions to published curves and desktop baselines: ReactionAge latency vs. Wii Balance Board golden data; FaceTTD inferencing cross-validated against Edge Impulse cloud classifier; VoiceAge MFCC regression verified through train/holdout splits; mechanical fixtures inspected with feeler gauges and dial indicators for tolerance drift.
What are the implications?
A portable intrinsic capacity mirror supports proactive geriatric screening, telehealth coaching, and longitudinal studies that correlate functional decline with interventions.
By grounding hardware in open-source parts and HTMAA fabrication methods, the system can be replicated across labs and community clinics to accelerate validation of digital aging biomarkers and personalize longevity therapies.
Design
Your project should incorporate 2D and 3D design, multiple additive and subtractive fabrication processes, electronics design and production, embedded microcontroller design, interfacing, and programming, system integration and packaging.
2D Design
2D design work for the multimodal intrinsic capacity assessment system:
Cardboard origami tiling for circular mirror frame, optimized for kerf learned during Week 1 laser characterization.
Vinyl-cut ReactionAge control labels and MirrorAge fascia decals for rapid UI readability.
KiCad/Fusion schematics + polygon pours for ESP32S3 carrier, force sensing front-end, and OLED interposer.
2D shop drawings for CNC floating base, including registration dowels and silicone mold parting lines.
Figma wireframes outlining the midterm web dashboard and on-device OLED states.
Subtractive: Laser cutting, milling for precision parts
Electronics: PCB design and production
Programming: Embedded microcontroller development
Bill of Materials
Where possible, I fabricated parts rather than buying them. This table summarizes all unique components in the final MirrorAge system, their approximate costs, and where they are used.
A mirrored copy of this bill of materials also appears on the Week 14 system-integration page for cross-linking directly from the integration steps
(Week 14 BOM).
Grip-strength molds, band molds, structural ribs
(Week 9,
Week 14)
Fasteners
M2/M3 hardware, heat-set inserts, misc. screws
Assorted
~$0.10–$0.30 ea.
$20.00 (bundle)
All mechanical assemblies (watch, grip rig, camera mount, demo table)
Estimated Total Project Cost
Electronics ≈ $190 · Mechanical & materials ≈ $130 ·
Total ≈ $320 (excluding lab-provided consumables and reused stock).
Exact per-week line items remain in the weekly documentation tables (for example
ReactionAge BOM CSV in Week 2),
while this table captures the consolidated, unique parts that make up the final integrated MirrorAge system.
Fabrication Process
Week-by-week fabrication rolled forward subsystems toward the integrated mirror:
Week 1 laser-cut origami tiles for the circular bezel; Week 2 PCB milling + soldering for ReactionAge;
Week 3–4 torsional spring 3D prints and sanding jigs; Week 5 copper-clad milling and reflow of the ESP32S3 carrier;
Week 6 ShopBot machining of the floating base; Week 8 resin + FDM camera enclosure build; Week 9 wax machining, Mold Star casting, and Drystone ribs.
Each step captured feeds-and-speeds, toolpaths, and fixturing photos embedded in the weekly pages for replication.
Testing & Validation
Validation combined bench instrumentation and statistical analysis: oscilloscope timing to verify ReactionAge jitter, Edge Impulse confusion matrices for FaceTTD and VoiceAge,
Instron pull tests for the torsional grip cartridge, IR thermography while curing Mold Star molds, dial-indicator checks on CNC-machined bases, and adhesive shear testing on mirror mounts.
Data are logged to CSV via the ESP32S3 and compared against published baselines inside the midterm Jupyter notebook.
Individual Mastery and Independent Operation
Projects can be separate or joint, but need to show individual mastery of the skills, and be independently operable.
Individual Mastery
Demonstration of individual skills across all course units:
2D and 3D Design
Modeled the tensegrity floating mirror, torsional grip shells, and camera bezel in Fusion 360 and Onshape.
Drove design reviews with Anthony/Neil to lock tolerances, assembly order, and module interface specs.
Demonstrates mastery across cutting, 3D printing, machining, electronics, networking, and interface programming units.
Documentation cross-linked via weekly pages, GitHub repos, and BOM spreadsheets for traceability.
Group Assignments
Collaborative work and individual contributions:
Embedded programming group: authored workflow trade-off analysis and repo organization that seeded ReactionAge firmware patterns.
Molding & casting group: led SDS review, material trials, and mixing SOP that informed final mirror mold.
Shared camera dev sessions with peers to improve Edge Impulse dataset collection and SenseCraft deployment strategies.
Useful Documentation
Helpful resources, documentation, and design files for the multimodal intrinsic capacity assessment system.
Open Source Grip Strength Meter
A cost-effective $50 grip strength measurement system that can be further optimized for our multimodal assessment platform.
This open-source design provides an excellent foundation for integrating grip strength measurement into our intrinsic capacity assessment system,
with potential for cost reduction through signal multiplexing on a single processor.
Detailed technical pipeline for processing multiple digital biomarkers to generate intrinsic capacity scores.
Pipeline Architecture
Inputs
• Grip Strength
• Voice
• Face
• Video (motion/gait)
• Reaction Time
• Wearable Accelerometer
→
Feature Extraction
Strength metrics
Prosody features
Facial landmarks
Gait parameters
Response latency
Activity patterns
Embeddings
Features converted to vector representations for multimodal fusion
→
Fusion Layer
Combines multimodal features using attention mechanisms
Output
• Overall IC Score
• Domain sub-scores
→
Domain Scores
Locomotor
Cognition
Vitality
Sensory
Psychological
Weekly System Development Breakdown
How each week of HTMAA 2025 builds toward the complete multimodal intrinsic capacity assessment system.
Week 0: Project Ideation
Initial concept development and planning
Project planning and documentation structure
Research direction and concept sketches
Week 1: Precision Cutting
Laser and vinyl cutting techniques
Device housing components via laser cutting
Sensor mounting brackets and enclosures
Vinyl cutting for device labeling and UI elements
Week 2: Embedded Programming
Electronics basics and microcontroller programming
Microcontroller programming for data collection
Basic sensor interface circuits
Week 3: 3D Scanning & Printing
3D technologies for device components
3D scanning for custom component design
3D printing for device housings
Week 4: Electronics Design
EDA and schematic design
PCB design for grip strength measurement
Sensor interface circuits and signal conditioning
Power management and data storage systems
Week 5: Electronics Production
PCB fabrication and assembly
PCB fabrication and debugging
Component assembly and testing
Week 6: Computer-controlled Machining
CAM and precision milling
Precision components via milling
Custom mechanical parts
Week 7: Input Devices
Sensor integration for data collection
Force sensors for grip strength measurement
Microphones for voice analysis
Camera systems for facial expression analysis
Reaction time measurement circuits
Week 8: Output Devices
Actuators and system integration
Display systems for real-time feedback
Haptic feedback for user interaction
Week 9: Molding & Casting
Forming and resin techniques
3D printing and molding for custom components
Silicone casting for device components
Week 10: Mechanical & Machine Design
System integration and mechanical design
Mechanical design for ergonomic device housing
System integration and calibration protocols
Week 11: Networking & Communications
Connectivity and communication protocols
Bluetooth/Wi-Fi connectivity for data transmission
Wearable accelerometer integration and data fusion
Week 12: Interface & Application Programming
UI development and application programming
Mobile app development for user interface
Cloud integration for data storage and analysis
Machine learning pipeline for IC score calculation
Week 13: Wildcard & Final Integration
Final orders and complete system deployment
Final testing, validation, and documentation
System integration and deployment
Camera Subsystem
Advanced camera system implementation using XIAO ESP32S3 Sense with real-time image processing, EdgeAI integration, and interactive selfie capture functionality.
System Overview
The camera system successfully captures images, processes them into bitmaps, and displays them on an OLED screen using advanced Floyd-Steinberg dithering algorithms.
Video Demonstrations
Camera Bot Selfie
Demonstration of the interactive selfie capture system with touch controls
Picture of Picture
Meta demonstration showing the camera system capturing its own display
Code Implementation
60-Second Auto Capture System
Automated camera system that captures and displays images every 60 seconds using advanced image processing techniques.
1. Initialize camera with PSRAM frame buffers
2. Configure OLED display (128x64 pixels)
3. Set up 60-second capture interval timer
4. In main loop:
a. Check if 60 seconds have elapsed
b. Capture image from camera
c. Process image:
- Downsample to 128x64 via box averaging
- Apply contrast stretch (linear scaling)
- Perform Floyd-Steinberg dithering
d. Display processed bitmap on OLED
e. Release frame buffer
5. Repeat process
Touch-Controlled Capture System
Interactive camera system with touch controls allowing manual capture triggers in addition to automatic timing.
1. Initialize camera and OLED display
2. Set up touch pins (GPIO1 & GPIO2) with threshold detection
3. Configure 60-second auto-capture timer
4. In main loop:
a. Update touch sensor readings
b. Detect touch press events (justPressed)
c. Check for capture trigger:
- Touch press OR 60-second timer elapsed
d. If triggered:
- Capture image from camera
- Process image (same as auto version)
- Display on OLED
- Reset timer
5. Continue monitoring for next trigger
The system captures photos, converts them to bitmaps using advanced image processing algorithms, and displays them on the OLED screen.
I'm also exploring integration with ML models, either through online API calls or by embedding TinyML model parameters from Python to C++.
Future development includes live streaming real-time video with ML prediction updates based on variable observation times,
and exploring Edge Impulse models as an alternative to manual Python-to-C++ conversion for faster deployment.
EdgeAI/TinyML Integration
Edge AI can also be implemented using Edge Impulse models, which may be faster than manually converting Python models to C++.
The SenseCraft AI platform provides a streamlined approach to training and deploying ML models directly on the XIAO ESP32S3.
Deploy inference bundle to the SenseCraft board alongside the camera stack.
Benchmark latency and accuracy against baseline VoiceAge models and document calibration protocol.
Week 0 - Introduction & Design
Project ideation and initial concept development for bioprinting rejuvenated tissue and aging biomarker devices.
Project planningConcept sketchesResearch direction
System Integration Plans: Establish the foundational architecture for multimodal data collection by designing the overall system framework that will integrate all six digital biomarkers (grip strength, voice, face, video, reaction time, wearable accelerometer) into a cohesive intrinsic capacity assessment platform.
Mapped the MirrorAge subsystem architecture, assembled the intrinsic capacity literature stack, and kicked off BRR/IRB coordination so fabrication sprints stay aligned with clinical requirements.
Week 1 - Principles & Cutting
Version control, laser cutting, and vinyl cutting techniques applied to final project components.
Laser cuttingVinyl cuttingVersion control
System Integration Plans: Fabricate precision-cut housing components and mounting brackets for all sensor modules (force sensors, microphones, cameras, reaction time circuits) using laser cutting, while creating vinyl-cut labels and UI elements for device identification and user guidance.
Characterized laser kerf, produced the origami mirror frame tiles, and generated vinyl interface labels—locking in enclosure dimensions and user UI cues for the mirror shell.
Week 2 - Embedded Programming
Electronics basics and embedded programming for the aging biomarker device components.
MicrocontrollersProgrammingElectronics
System Integration Plans: Develop embedded programming protocols for real-time data collection from all six biomarker sensors, implementing initial signal processing algorithms and establishing the communication framework for multimodal data fusion.
Built the ReactionAge firmware + enclosure, published the first BOM, and validated timing pipelines that will feed the MirrorAge IC fusion engine.
Week 3 - 3D Scanning & Printing
3D scanning and printing techniques for bioprinting components and device housings.
3D scanning3D printingAI tools
System Integration Plans: Create custom 3D-printed components for camera mounting systems and facial recognition hardware, while developing 3D scanning protocols for ergonomic device design that accommodates all sensor modalities in a user-friendly form factor.
Modeled and printed the torsional grip spring, performed 3D scans for ergonomic fixtures, and captured training assets for face/gait datasets.
Week 4 - Electronics Design
EDA and schematic design for the aging biomarker device electronics.
EDA toolsSchematic designCircuit design
System Integration Plans: Design comprehensive PCB schematics that integrate force sensor circuits for grip strength measurement, microphone preamplifiers for voice analysis, camera interfaces for facial recognition, and timing circuits for reaction time assessment into a unified electronics platform.
Completed the Fusion 360/KiCad schematic/PCB layout for the ESP32S3 carrier tying together force, audio, camera, reaction, and wearable interfaces.
Week 5 - Electronics Production
PCB fabrication, debugging, and assembly for the biomarker device.
PCB fabricationDebuggingAssembly
System Integration Plans: Fabricate and assemble the integrated PCB containing all sensor interfaces, implementing power management systems for continuous operation and establishing data storage protocols for the multimodal biomarker data collection system.
Fabricated and assembled the carrier PCB, brought up power domains, and verified sensor buses—establishing the electronics backbone for integration.
Week 6 - Computer-controlled Machining
CAM and milling for precision components and device housings.
CAMMillingPrecision machining
System Integration Plans: Machine precision mechanical components for the integrated device housing using computer-controlled milling, ensuring proper alignment and mounting for all sensor modules while maintaining ergonomic design for user comfort during multimodal data collection.
Machined the floating mirror base and tensegrity nodes, refining fixturing that ensures repeatable camera and grip alignment in the final assembly.
Week 7 - Input Devices
Sensors and embedded architectures for data collection in the biomarker device.
SensorsInput devicesData collection
System Integration Plans: Integrate all six input sensor systems (force sensors for grip strength, microphones for voice analysis, cameras for facial recognition and gait analysis, reaction time circuits, and wearable accelerometer) into the unified data collection platform with real-time processing capabilities.
Integrated the force sensor, microphone, and ReactionAge modules on the carrier, logging synchronized packets that exercise the multimodal intake stack.
Week 8 - Output Devices
Actuators and system integration for the biomarker device outputs.
ActuatorsOutput devicesSystem integration
System Integration Plans: Implement output devices including display systems for real-time intrinsic capacity feedback and haptic feedback mechanisms for user interaction, creating an intuitive interface for the multimodal biomarker assessment system.
Deployed the SenseCraft FaceTTD pipeline on the XIAO ESP32S3, implemented OLED dithering previews, and confirmed end-to-end edge inference latency.
Week 9 - Molding & Casting
Forming and resin techniques for bioprinting molds and device components.
MoldingCastingResins
System Integration Plans: Create custom molded components for the bioprinting aspects of the project and develop specialized casings for sensor protection, ensuring the device can withstand continuous use during multimodal data collection sessions.
Machined wax molds, cast Mold Star silicone and Drystone ribs, and prototyped arrow-inspired shells that stabilize the mirror and protect embedded sensors.
Week 10 - Mechanical & Machine Design
Kits and mechanical design for the bioprinting and biomarker device systems.
Mechanical designMachine designSystem integration
System Integration Plans: Complete the mechanical design integration of all system components, implementing calibration protocols for sensor alignment and developing the complete mechanical framework that houses all six digital biomarker measurement systems.
Developed mechanical actuation systems including tapping and swiping mechanisms for phone interaction, integrated camera with Edge AI face detection and Wi-Fi livestreaming, designed and 3D-printed phone holder with amplifier, and prepared comprehensive midterm review documentation with system diagrams and timeline.
Week 11 - Networking & Communications
BLE, Wi-Fi, and communication protocols for the biomarker device connectivity.
BLEWi-FiCommunications
System Integration Plans: Implement wireless communication protocols (Bluetooth/Wi-Fi) for seamless data transmission from all six sensor modalities, enabling real-time data fusion and establishing connectivity for the wearable accelerometer integration into the multimodal assessment system.
Implemented Wi-Fi camera livestreaming for real-time video transmission, developed ESP-NOW networking protocols for device communication, designed and milled PCBs for networking components, and explored Meshtastic for long-range communication capabilities.
Week 12 - Interface & Application Programming
UI and application development for the biomarker device interface.
UI designApplicationsUser interface
System Integration Plans: Develop the complete user interface and application programming for the multimodal system, implementing the machine learning pipeline for intrinsic capacity score calculation and creating cloud integration for comprehensive data storage and analysis of all biomarker measurements.
Created Wi-Fi web interface for real-time pulse oximeter readings with live plotting, developed grip strength measurement device with load cell and integrated GUI, implemented OLED button user interface for device control, and established video streaming capabilities for sensor data visualization.
Week 13 - Wildcard & Final Orders
Final orders and wildcard week activities for project completion.
Final ordersWildcard activitiesProject completion
System Integration Plans: Complete final system integration, testing, and validation of the complete multimodal intrinsic capacity assessment platform, ensuring all six digital biomarkers work cohesively to provide accurate WHO-defined intrinsic capacity scores across all five domains (locomotor, cognition, vitality, sensory, psychological).
Designed and fabricated ATtiny1626 tiny development board with fiber laser PCB engraving, created glass engraving system with UV laser including blinking heart integration for visual feedback, milled mounting holes and completed board assembly, and prepared final board designs for system integration.
System Integration
Final integration week focused on bringing all subsystems together, completing hardware fabrication, firmware integration, and documentation for the MirrorAge system presentation. View full details →
Initial system integration work focused on subsystem validation, CAD model consolidation, and design backbone acquisition for band integration. Conducted comprehensive testing of all subsystems to ensure proper functionality, identified and resoldered defective joints, and exported CAD models of all PCBs into a unified assembly model.
Integrated CAD Model: Exploded isometric view of the complete system assembly, including all PCBs, main housing with transparent enclosure, and wearable band components.
Physical integration of subsystems into the complete demo table assembly, including mechanical component fabrication and electrical board consolidation. Integrated the complete demo table with precise placement of the MirrorAge handgrip subsystem and aging clock subsystem, providing a unified platform for system demonstration.
Complete Demo Table Assembly: Integrated mechanical design showing precise placement of the MirrorAge handgrip subsystem and aging clock subsystem on the demo table.
Continued fabrication work integrating all manufacturing processes. Focused on completing physical components including 2D laser cutting, 3D printing of rigid and flexible components, and PCB milling to prepare subsystems for final assembly and testing.
TPU Band Print: Flexible wearable band component printed using TPU material
Flexible Band: TPU band demonstrating material properties and print quality
Comprehensive subsystem integration combining 2D fabrication (laser cutting), 3D printing (rigid and flexible components), PCB milling (single and double-sided boards), and molding/casting to complete all physical components. Upgraded MirrorAge TFT board to v13 and aging clock TFT board to v16 with optimized component placement and routing. Established reliable I²C bus communication and validated all sensor addresses.
Laser Cutting
Thin Acrylic Cutting: Laser cutting 1.35mm acrylic sheet for improved display cover fit
Successful Cut: Completed laser-cut acrylic display cover with precise dimensions
Final integration day focused on closing the watch subsystem, soldering and verifying all double-sided boards, refining molded bands, and assembling the complete MirrorAge demo with both the aging clock and grip-strength subsystems fully wired and tested. Completed rivet installation for plated through-holes, sensor bring-up (accelerometer, pulse oximeter, OLED/TFT displays), and full system integration on the tensegrity demo table. The integrated system successfully demonstrated synchronized sensor readouts and display behavior across all boards.
Soldered MirrorAge Board: Complete double-sided board with all components installed
Integrated Watch Subsystem: TPU bands fastened into the watch clip with assembled electronics
Working Integrated System: Complete MirrorAge system demonstrating synchronized sensor readouts and display behavior
Final project presentation and demonstration of the complete MirrorAge system. Showcased the integrated aging clock and grip-strength subsystems working together on the demo table, demonstrating real-time sensor data collection and display synchronization. View final presentation demo →
Final Presentation Demo: Complete MirrorAge system demonstration showing integrated aging clock and grip-strength subsystems operating together in real-time
Full Documentation: For complete details, design files, code, and comprehensive documentation of the system integration process, see Week 14: System Integration.
Final Project Masterpiece
Complete demonstration of the integrated MirrorAge system showcasing all subsystems working together in real-time.
Final Presentation Demo: Complete MirrorAge system demonstration showing the integrated aging clock and grip-strength subsystems operating together on the demo table, with synchronized sensor readouts and real-time display updates across all boards.
Complete repository of all design files, CAD models, schematics, PCB layouts, firmware, and fabrication files from Week 0 through Week 14, organized by week and component type.
Note: Additional design files, firmware, and documentation can be found in the respective week pages. Some files are part of larger archives (ZIP files) that contain multiple related design files.
Reflections & Learnings
Comprehensive reflections on the MirrorAge Intrinsic Capacity Mirror project development journey.
Modular system design allows for incremental development and component-level testing throughout the semester
Integration of mechanical, electrical, and software subsystems requires careful planning and coordination
Iterative design and prototyping revealed the importance of early testing and validation
Documentation and knowledge transfer are critical for project continuity and future improvements
The project successfully demonstrates how digital fabrication and embedded systems can create meaningful health assessment tools
Contributions
Acknowledgements and contributions that made this project possible.
Gladyshev Lab and Collaborators
Special thanks to the Gladyshev Lab and collaborators for the fruitful discussions that led to this multimodal intrinsic capacity assessment idea,
which supplements my PhD research goals in aging and longevity. The conceptual framework for integrating multiple digital biomarkers
to assess intrinsic capacity domains emerged from collaborative research discussions on aging biomarkers and healthspan assessment.
Transparent documentation of AI assistance used in this final project work, following course guidelines for ethical AI usage.
📋 General Guidelines: See General Commands for Cursor on the homepage for standard guidelines and commands used consistently throughout documentation development.
Cursor · Project Plan & Weekly Schedule
Comprehensive Cursor AI assistance for outlining the project plan and weekly schedule, including documentation structure, content organization, systematic updates across all week pages and the final project page, media integration, and summary generation workflows.
Cursor AI aligned the midterm review plan with updated system diagram, timeline, and remaining-task summaries, then refreshed finalproject.html to remove legacy bioprinting language and re-point internal links. The full transcript and generated HTML are available for review.
Cursor AI assistance for adding a white background behind the photo in the Final Project Spiral Development Model section on finalproject.html. The image container was updated with white background, padding, and rounded corners for improved visual presentation.
Cursor AI distilled Week 0–9 documentation and the Oct 31 lab meeting deck into midterm-ready narrative, cost, and validation content, replacing every placeholder in finalproject.html.
Transcript archived in markdown and HTML (generated via scripts/md_to_html_converter.py) for transparency.
ChatGPT was used to research and develop the multimodal intrinsic capacity assessment framework, including the comprehensive coverage analysis table and technical pipeline design.
The AI assisted with structuring the WHO-defined intrinsic capacity domains, identifying appropriate digital biomarkers, and designing the fusion architecture for multimodal data processing.
Cursor AI assisted with developing the complete final project page structure, implementing the multimodal intrinsic capacity assessment framework, and creating comprehensive documentation.
The AI helped with HTML structure, responsive design, weekly system integration plans, and organizing the technical documentation for the complete biomarker assessment system.
Cursor AI assisted with finalizing the project presentation structure to ensure full compliance with MIT Academy project presentation requirements.
The AI helped implement all required sections including answering questions, design documentation, bill of materials, individual mastery requirements,
course presentation structure, and spiral model development approach visualization.
ChatGPT was used to discuss camera system implementation strategies, image processing algorithms, and EdgeAI integration approaches.
The AI assisted with understanding Floyd-Steinberg dithering implementation, touch sensor integration, and exploring TinyML deployment options for the XIAO ESP32S3 platform.
AI-Assisted Project Highlights and Camera Subsystem Development
Cursor AI assisted with adding the project highlights section featuring camera system achievements and creating a comprehensive camera subsystem section with detailed code implementations, video demonstrations, and EdgeAI integration documentation.
The AI helped with HTML structure, responsive design, image processing explanations, and organizing the technical documentation for the complete camera system showcase.
Interactive selfie capture system with touch controls and real-time display
Vision Board
Conceptual visualization of the multimodal intrinsic capacity assessment system integrating grip strength, voice analysis, facial recognition, video motion capture, reaction time measurement, and wearable accelerometer data.
Intrinsic Capacity (IC) Coverage by Digital Biomarkers
Domain
Grip
Voice
Face
Video
Reaction Time
Wearable
Locomotor
✅
🔸
🔸
✅
🔸
✅
Cognition
❌
✅
🔸
🔸
✅
🔸
Vitality
✅
✅
✅
✅
🔸
✅
Sensory
❌
✅
✅
✅
✅
🔸
Psychological
❌
✅
✅
✅
🔸
✅
✅ Strong coverage |
🔸 Partial/indirect |
❌ Not covered |
View full table →
Multimodal IC Pipeline
Inputs: Grip Strength, Voice, Face, Video, Reaction Time, Wearable Accelerometer
Development Approach: Following the spiral model methodology, this final project will iterate through multiple development cycles, each building upon previous work while addressing new requirements and risks.
This snapshot covers the subsystems and documentation that will be shown during the midterm review. Links jump directly to the supporting sections with detailed evidence.
Featured Subsystems
Camera subsystem — Edge inference demos and selfie capture loop.
Instructor meeting hold — Thursday, Nov 12 at 10:00 AM ET reserved via the shared HTMAA midterm review sheet.
Execution Schedule (Timeline Snapshot)
Condensed from the Week 8–13 development timeline: each sprint builds toward final integration, mirroring the gantt chart below.
Week 8 · Output Devices: figuring out wiring for real-time display states.
Week 9 · Molding & Casting: learn how to cast custom housings and refine structural components.
Week 10 · Mechanical Design: figure out ergonomic enclosure and calibration fixtures.
Week 11 · Networking: program BLE/Wi-Fi telemetry and wearable data fusion.
Week 12 · Interface/App: create mobile UI, cloud bridge, and IC scoring pipeline.
Week 13 · Final Integration: run validation passes, document results, and prep deployment.
Instructor Review Logistics
Calendar hold sent for Thursday, Nov 12 at 10:00 AM ET (38-501 conference room) per the shared HTMAA scheduling sheet. Agenda covers subsystem demos, weekly documentation spot checks (Weeks 0–9), and next-sprint alignment. Meeting slot referenced in the midterm review schedule; awaiting final confirmation via class Slack.
System Architecture
Updated block diagram highlighting the multimodal sensing stack (grip, voice, face, motion, wearables), on-device inference layers, and real-time feedback channels that feed the intrinsic capacity score.
Development Timeline
Timeline aligns subsystem sprints with HTMAA milestones: output devices (Week 8), molding and casting (Week 9), mechanical design (Week 10), networking and communications (Week 11), app programming (Week 12), and final integration (Week 13).
Remaining Tasks (Snapshot)
Weeks 0–9 locked in the core subsystems—documentation workflow, cutting and molding for the housing, embedded prototypes for reaction timing, SenseCraft camera inference, and early grip/voice rigs. The checklist below captures what still needs to happen to converge on the integrated MirrorAge system.
Hardware Integration
Consolidate grip, voice, camera, reaction-time, and wearable sensor harnesses into the MirrorAge enclosure.
Finish molding/casting iterations for the ergonomic housing and align mounting features for PCBs and haptics.
Firmware & Edge AI
Stabilize onboard inference for SenseCraft vision models and voice-age pipelines on the XIAO ESP32S3.
Calibrate grip-force and reaction-time firmware for repeatable sampling; close the loop to haptic/display feedback.
Networking & Data Fusion
Bring up BLE/Wi-Fi data paths for wearable accelerometer streaming and cloud logging of intrinsic capacity scores.
Implement the fusion layer that combines per-domain scores into an overall IC metric with on-device storage.
Interface & UX
Finish mobile/web dashboard mockups for user onboarding, data review, and device calibration workflows.
Finalize real-time mirror feedback cues (display states, haptics, lighting) tied to sensor status and IC outcomes.
Validation & Documentation
Run end-to-end system tests (sensor capture → fusion → feedback) and document calibration procedures.
Record the one-minute video, finalize final presentation assets, and polish the bill of materials for review.
Week 14 System Integration Plan
Detailed day-by-day schedule for final system integration, covering design, fabrication, programming, testing, and documentation. This plan outlines the path to completing the MirrorAge system integration and preparing for final presentation. View on Week 14 page →
The act of bringing something to a conclusion or ending in a decisive manner. The ability to efficiently finish tasks and projects with a goal-oriented mindset.
Wednesday
Morning
Publish system integration plan on website
Update weekly assignment sections on final project page (weeks 10-13)
Link final project design files
Update reflections and learnings
Update picture of prism holder
Add final pictures to Slack canvases
Create schematic between boards (wired and wireless) — updated system diagram on PPT-like page
Start CAD model of system
Place final order
Afternoon & Evening
Design:
Boards: Combine OLED screen/accelerometer with pulse oximeter board in a new board (maybe upgrade to small TFT as minor)
Boards: Speaker board with realtime amplifier and TFT (on the load cell fixed board)
Band: Mold design
Cases: 3D print mountable cases for the boards
Integrate designs into final CAD
Document design
Finish CAD model of system
Thursday
Fabricate
Milling boards
Print mold and cast band
Print cases
Solder
Solder components on milled boards
Connect boards with wired (and wireless connection codes)
Finishing
Mirror on screen (easy way with the film)
Documentation
Document fabrication
Friday
Programming
Board level codes
Server level codes
Documentation
Document codes
Completion
Finish anything else
Saturday
Programming & Testing
Demo integrated system
Test integrated system
Documentation
Document testing and evaluation
Review and complete documentation (list of questions)
Make the video by collaging documentation
Sunday
Fill up any gaps
Prepare demo on tensegrity table
Finalize 1-slide
Work on minors
If done, work on if there's time
Monday Morning
Transport demo on tensegrity table
Fill up any gaps
Work on minors
Specific Tasks to Complete This Week
Major Tasks
CAD model of system
Speaker board with realtime amplifier
Combine screen/accelerometer with pulse oximeter board in a new board
Mold and cast band
Design and fabricate casing (print)
Schematic between boards (wired and wireless) — updated system diagram on PPT-like page
Serial connection between pulse oximeter and tiny blinking heart for BPM (BPM from IR, SpO2 from delta)
Combine multiple boards on the same WiFi (switching tabs is easy way, board hosting the webpage querying and update or Python-based server somewhere where everything posting data, Raspberry Pi)
Put+program everything together according to the above (with WiFi for now)
MirrorAge is a self-contained edge-AI mirror that captures grip strength, facial imagery, voice, motion, and reaction time to estimate intrinsic capacity in real time.
The platform fuses weekly prototypes—ReactionAge latency tests, 3D printed grip mechanics, SenseCraft camera inference, and molded structural elements—into a multimodal mortality risk profiler.
Subsystems in progress: reaction-time module, SenseCraft FaceTTD inference stack, VoiceAge microphone pipeline, wearable streaming via BLE, and molded structural packaging.
Clinical motivation: translate WHO intrinsic capacity domains into measurable digital biomarkers that flag functional decline earlier than chronological age alone.
Project Goals
Deliver multimodal IC scoring Fuse grip, face, voice, reaction-time, and wearable streams on-device to output an intrinsic capacity score plus domain deltas.
Fabricate modular, serviceable hardware Iterate laser-cut tensegrity mirror shells, 3D printed torsional grips, custom PCBs, and silicone cast fixtures that assemble without bespoke tooling.
Validate against ground truth Benchmark embedded inferences against published datasets (Blomkvist et al. 2017, Fuentealba et al. 2025) and lab-collected pilots to quantify accuracy, latency, and reliability.
Timeline & Milestones
Week 10 · Hardware convergence Integrate SenseCraft FaceTTD camera, ReactionAge latency module, and newly milled PCB into a single ESP32S3 backplane.
Week 12 · Midterm review build Finish molded mirror enclosure, bring up BLE wearable link, and demo live IC score during midterm critique.
Final week · Validation & documentation Execute pilot data collection, refine model weights, and release reproducible fabrication + firmware packages.
Documenting the final project masterpiece that integrates the range of units covered, addressing all required questions.
What does it do?
MirrorAge captures synchronized digital biomarkers—camera frames processed with on-device FaceTTD models, VoiceAge microphone samples, grip strength torque, wearable accelerometry, and ReactionAge latency—to estimate intrinsic capacity and time-to-death acceleration.
A XIAO ESP32S3 Sense orchestrates sensing, performs Edge Impulse inference, and displays a live mortality-risk score on the OLED while logging packets to a Python analytics notebook.
Who's done what beforehand?
The concept builds on WHO intrinsic capacity framing and recent mortality-risk studies: Niccoli & Partridge (2012) establish age as the dominant chronic-disease predictor; Fuentealba et al. (Nature Aging 2025) show blood-based IC clocks outperform chronological models;
Zhavoronkov & Bhullar (2015) and Lancet Healthy Longevity editorials motivate treating functional decline as the actionable signal.
This project translates those findings into an accessible, multimodal measurement mirror that can operate outside hospital labs.
What sources did you use?
Primary references include Nature Aging 2025 intrinsic capacity papers, the PLOS ONE ReactionAge dataset (Blomkvist et al. 2017), Edge Impulse SenseCraft documentation, Smooth‑On Mold Star technical bulletins, RotoMetals alloy certificates, MIT HTMAA recitations, and the open-source GRPR grip-strength meter.
Design inspiration and safety notes were consolidated from Anthony Pennes' HTMA guides and Fab Academy molding tutorials.
What did you design?
• Laser-cut cardboard origami mirror frame and tensegrity-inspired floating mount (Weeks 1 & 6)
• ReactionAge firmware + enclosure with statistical post-processing dashboards (Week 2)
• 3D printed torsional spring grip module tuned for ±40 kg ranges (Week 3)
• KiCad/Fusion carrier PCB for the ESP32S3 Sense with OLED, force, and BLE breakouts (Week 5)
• Edge Impulse deployment pipeline with grayscale dithering overlay and live inference UX (Weeks 7–8)
• CAM toolpaths, silicone molds, and Drystone casts for structural packaging (Week 9)
What materials and components were used?
Seeed XIAO ESP32S3 Sense module with OV2640 camera and PDM mic, SparkFun Qwiic button and force sensors, SSD1306 OLED, wearable IMU node (Bosch BHI260), laser-cut cardboard/birch sheets, PLA+/Onyx filament, Mold Star 30 silicone, Drystone gypsum, Roto281 fusible alloy, and embedded fasteners/heat-set inserts.
Where did they come from?
Electronics from Seeed Studio, SparkFun, Digi-Key, and Adafruit; molding supplies and silicones from Reynolds Advanced Materials; Drystone and Hydro-Stone from USG via the MIT CBA stockroom; fusible alloys from RotoMetals; structural lumber and plywood from MIT's shop inventory; filaments from Prusa Research and Markforged.
How much did they cost?
Current spend: $96.34 for ReactionAge components (Week 2 BOM) + $78.42 for SenseCraft camera stack (XIAO ESP32S3 Sense, OLED, cabling) + $42.10 for molding media (Mold Star 30 quart, Drystone, release agents) = $216.86 to date.
Remaining allocation (~$130) is earmarked for BLE wearable hardware and final enclosure finishes; detailed line items tracked in the Airtable budget and mirrored in each weekly BOM CSV.
What parts and systems were made?
Custom origami mirror frame, 3D printed torsional grip shell, machined floating base, silicone molds and Drystone casts for arrow-inspired structural ribs, bespoke ESP32S3 breakout PCB, laser-cut ReactionAge control panel, and assembled sensor tower linking camera, OLED, and wearable gateway.
What tools and processes were used?
Parametric CAD in Fusion 360, laser cutting (Epilog) for origami tiles, Prusa MK4 FDM printing, Formlabs SLA for detail inserts, ShopBot CNC and Bantam PCB milling, silicone mixing/casting under vacuum, Edge Impulse model training, PlatformIO firmware, and Python/NumPy validation notebooks.
What questions were answered?
• Can consumer-grade sensors reproduce published reaction-time age curves? (Yes—ReactionAge matched Blomkvist et al. regression within 4.6 ms RMSE.)
• Will SenseCraft FaceTTD run locally on ESP32S3 with acceptable latency? (Yes—~310 ms/inference at 30% baseline accuracy, highlighting dataset needs.)
• Does molded packaging improve sensor placement repeatability? (Yes—silicone nests held camera ±0.5 mm, reducing alignment drift seen in cardboard prototypes.)
What worked? What didn't?
✅ Floyd–Steinberg dithering produced clear OLED previews; ✅ ReactionAge firmware maintained ±1 ms jitter; ✅ Molded Drystone ribs stiffened mirror shell without excess weight.
⚠️ FaceTTD accuracy plateaued at 30% due to limited training diversity; ⚠️ VoiceAge requires more MFCC samples to sustain 0.64-year MAE; ⚠️ Grip spring fatigue highlighted need for fiber-reinforced print or machined aluminum insert.
How was it evaluated?
Bench tests compare embedded predictions to published curves and desktop baselines: ReactionAge latency vs. Wii Balance Board golden data; FaceTTD inferencing cross-validated against Edge Impulse cloud classifier; VoiceAge MFCC regression verified through train/holdout splits; mechanical fixtures inspected with feeler gauges and dial indicators for tolerance drift.
What are the implications?
A portable intrinsic capacity mirror supports proactive geriatric screening, telehealth coaching, and longitudinal studies that correlate functional decline with interventions.
By grounding hardware in open-source parts and HTMAA fabrication methods, the system can be replicated across labs and community clinics to accelerate validation of digital aging biomarkers and personalize longevity therapies.
Design
Your project should incorporate 2D and 3D design, multiple additive and subtractive fabrication processes, electronics design and production, embedded microcontroller design, interfacing, and programming, system integration and packaging.
2D Design
2D design work for the multimodal intrinsic capacity assessment system:
Cardboard origami tiling for circular mirror frame, optimized for kerf learned during Week 1 laser characterization.
Vinyl-cut ReactionAge control labels and MirrorAge fascia decals for rapid UI readability.
KiCad/Fusion schematics + polygon pours for ESP32S3 carrier, force sensing front-end, and OLED interposer.
2D shop drawings for CNC floating base, including registration dowels and silicone mold parting lines.
Figma wireframes outlining the midterm web dashboard and on-device OLED states.
Subtractive: Laser cutting, milling for precision parts
Electronics: PCB design and production
Programming: Embedded microcontroller development
Bill of Materials
Where possible, I fabricated parts rather than buying them. This table summarizes all unique components in the final MirrorAge system, their approximate costs, and where they are used.
A mirrored copy of this bill of materials also appears on the Week 14 system-integration page for cross-linking directly from the integration steps
(Week 14 BOM).
Grip-strength molds, band molds, structural ribs
(Week 9,
Week 14)
Fasteners
M2/M3 hardware, heat-set inserts, misc. screws
Assorted
~$0.10–$0.30 ea.
$20.00 (bundle)
All mechanical assemblies (watch, grip rig, camera mount, demo table)
Estimated Total Project Cost
Electronics ≈ $190 · Mechanical & materials ≈ $130 ·
Total ≈ $320 (excluding lab-provided consumables and reused stock).
Exact per-week line items remain in the weekly documentation tables (for example
ReactionAge BOM CSV in Week 2),
while this table captures the consolidated, unique parts that make up the final integrated MirrorAge system.
Fabrication Process
Week-by-week fabrication rolled forward subsystems toward the integrated mirror:
Week 1 laser-cut origami tiles for the circular bezel; Week 2 PCB milling + soldering for ReactionAge;
Week 3–4 torsional spring 3D prints and sanding jigs; Week 5 copper-clad milling and reflow of the ESP32S3 carrier;
Week 6 ShopBot machining of the floating base; Week 8 resin + FDM camera enclosure build; Week 9 wax machining, Mold Star casting, and Drystone ribs.
Each step captured feeds-and-speeds, toolpaths, and fixturing photos embedded in the weekly pages for replication.
Testing & Validation
Validation combined bench instrumentation and statistical analysis: oscilloscope timing to verify ReactionAge jitter, Edge Impulse confusion matrices for FaceTTD and VoiceAge,
Instron pull tests for the torsional grip cartridge, IR thermography while curing Mold Star molds, dial-indicator checks on CNC-machined bases, and adhesive shear testing on mirror mounts.
Data are logged to CSV via the ESP32S3 and compared against published baselines inside the midterm Jupyter notebook.
Individual Mastery and Independent Operation
Projects can be separate or joint, but need to show individual mastery of the skills, and be independently operable.
Individual Mastery
Demonstration of individual skills across all course units:
2D and 3D Design
Modeled the tensegrity floating mirror, torsional grip shells, and camera bezel in Fusion 360 and Onshape.
Drove design reviews with Anthony/Neil to lock tolerances, assembly order, and module interface specs.
Demonstrates mastery across cutting, 3D printing, machining, electronics, networking, and interface programming units.
Documentation cross-linked via weekly pages, GitHub repos, and BOM spreadsheets for traceability.
Group Assignments
Collaborative work and individual contributions:
Embedded programming group: authored workflow trade-off analysis and repo organization that seeded ReactionAge firmware patterns.
Molding & casting group: led SDS review, material trials, and mixing SOP that informed final mirror mold.
Shared camera dev sessions with peers to improve Edge Impulse dataset collection and SenseCraft deployment strategies.
Useful Documentation
Helpful resources, documentation, and design files for the multimodal intrinsic capacity assessment system.
Open Source Grip Strength Meter
A cost-effective $50 grip strength measurement system that can be further optimized for our multimodal assessment platform.
This open-source design provides an excellent foundation for integrating grip strength measurement into our intrinsic capacity assessment system,
with potential for cost reduction through signal multiplexing on a single processor.
Detailed technical pipeline for processing multiple digital biomarkers to generate intrinsic capacity scores.
Pipeline Architecture
Inputs
• Grip Strength
• Voice
• Face
• Video (motion/gait)
• Reaction Time
• Wearable Accelerometer
→
Feature Extraction
Strength metrics
Prosody features
Facial landmarks
Gait parameters
Response latency
Activity patterns
Embeddings
Features converted to vector representations for multimodal fusion
→
Fusion Layer
Combines multimodal features using attention mechanisms
Output
• Overall IC Score
• Domain sub-scores
→
Domain Scores
Locomotor
Cognition
Vitality
Sensory
Psychological
Weekly System Development Breakdown
How each week of HTMAA 2025 builds toward the complete multimodal intrinsic capacity assessment system.
Week 0: Project Ideation
Initial concept development and planning
Project planning and documentation structure
Research direction and concept sketches
Week 1: Precision Cutting
Laser and vinyl cutting techniques
Device housing components via laser cutting
Sensor mounting brackets and enclosures
Vinyl cutting for device labeling and UI elements
Week 2: Embedded Programming
Electronics basics and microcontroller programming
Microcontroller programming for data collection
Basic sensor interface circuits
Week 3: 3D Scanning & Printing
3D technologies for device components
3D scanning for custom component design
3D printing for device housings
Week 4: Electronics Design
EDA and schematic design
PCB design for grip strength measurement
Sensor interface circuits and signal conditioning
Power management and data storage systems
Week 5: Electronics Production
PCB fabrication and assembly
PCB fabrication and debugging
Component assembly and testing
Week 6: Computer-controlled Machining
CAM and precision milling
Precision components via milling
Custom mechanical parts
Week 7: Input Devices
Sensor integration for data collection
Force sensors for grip strength measurement
Microphones for voice analysis
Camera systems for facial expression analysis
Reaction time measurement circuits
Week 8: Output Devices
Actuators and system integration
Display systems for real-time feedback
Haptic feedback for user interaction
Week 9: Molding & Casting
Forming and resin techniques
3D printing and molding for custom components
Silicone casting for device components
Week 10: Mechanical & Machine Design
System integration and mechanical design
Mechanical design for ergonomic device housing
System integration and calibration protocols
Week 11: Networking & Communications
Connectivity and communication protocols
Bluetooth/Wi-Fi connectivity for data transmission
Wearable accelerometer integration and data fusion
Week 12: Interface & Application Programming
UI development and application programming
Mobile app development for user interface
Cloud integration for data storage and analysis
Machine learning pipeline for IC score calculation
Week 13: Wildcard & Final Integration
Final orders and complete system deployment
Final testing, validation, and documentation
System integration and deployment
Camera Subsystem
Advanced camera system implementation using XIAO ESP32S3 Sense with real-time image processing, EdgeAI integration, and interactive selfie capture functionality.
System Overview
The camera system successfully captures images, processes them into bitmaps, and displays them on an OLED screen using advanced Floyd-Steinberg dithering algorithms.
Video Demonstrations
Camera Bot Selfie
Demonstration of the interactive selfie capture system with touch controls
Picture of Picture
Meta demonstration showing the camera system capturing its own display
Code Implementation
60-Second Auto Capture System
Automated camera system that captures and displays images every 60 seconds using advanced image processing techniques.
1. Initialize camera with PSRAM frame buffers
2. Configure OLED display (128x64 pixels)
3. Set up 60-second capture interval timer
4. In main loop:
a. Check if 60 seconds have elapsed
b. Capture image from camera
c. Process image:
- Downsample to 128x64 via box averaging
- Apply contrast stretch (linear scaling)
- Perform Floyd-Steinberg dithering
d. Display processed bitmap on OLED
e. Release frame buffer
5. Repeat process
Touch-Controlled Capture System
Interactive camera system with touch controls allowing manual capture triggers in addition to automatic timing.
1. Initialize camera and OLED display
2. Set up touch pins (GPIO1 & GPIO2) with threshold detection
3. Configure 60-second auto-capture timer
4. In main loop:
a. Update touch sensor readings
b. Detect touch press events (justPressed)
c. Check for capture trigger:
- Touch press OR 60-second timer elapsed
d. If triggered:
- Capture image from camera
- Process image (same as auto version)
- Display on OLED
- Reset timer
5. Continue monitoring for next trigger
The system captures photos, converts them to bitmaps using advanced image processing algorithms, and displays them on the OLED screen.
I'm also exploring integration with ML models, either through online API calls or by embedding TinyML model parameters from Python to C++.
Future development includes live streaming real-time video with ML prediction updates based on variable observation times,
and exploring Edge Impulse models as an alternative to manual Python-to-C++ conversion for faster deployment.
EdgeAI/TinyML Integration
Edge AI can also be implemented using Edge Impulse models, which may be faster than manually converting Python models to C++.
The SenseCraft AI platform provides a streamlined approach to training and deploying ML models directly on the XIAO ESP32S3.
Deploy inference bundle to the SenseCraft board alongside the camera stack.
Benchmark latency and accuracy against baseline VoiceAge models and document calibration protocol.
Week 0 - Introduction & Design
Project ideation and initial concept development for bioprinting rejuvenated tissue and aging biomarker devices.
Project planningConcept sketchesResearch direction
System Integration Plans: Establish the foundational architecture for multimodal data collection by designing the overall system framework that will integrate all six digital biomarkers (grip strength, voice, face, video, reaction time, wearable accelerometer) into a cohesive intrinsic capacity assessment platform.
Mapped the MirrorAge subsystem architecture, assembled the intrinsic capacity literature stack, and kicked off BRR/IRB coordination so fabrication sprints stay aligned with clinical requirements.
Week 1 - Principles & Cutting
Version control, laser cutting, and vinyl cutting techniques applied to final project components.
Laser cuttingVinyl cuttingVersion control
System Integration Plans: Fabricate precision-cut housing components and mounting brackets for all sensor modules (force sensors, microphones, cameras, reaction time circuits) using laser cutting, while creating vinyl-cut labels and UI elements for device identification and user guidance.
Characterized laser kerf, produced the origami mirror frame tiles, and generated vinyl interface labels—locking in enclosure dimensions and user UI cues for the mirror shell.
Week 2 - Embedded Programming
Electronics basics and embedded programming for the aging biomarker device components.
MicrocontrollersProgrammingElectronics
System Integration Plans: Develop embedded programming protocols for real-time data collection from all six biomarker sensors, implementing initial signal processing algorithms and establishing the communication framework for multimodal data fusion.
Built the ReactionAge firmware + enclosure, published the first BOM, and validated timing pipelines that will feed the MirrorAge IC fusion engine.
Week 3 - 3D Scanning & Printing
3D scanning and printing techniques for bioprinting components and device housings.
3D scanning3D printingAI tools
System Integration Plans: Create custom 3D-printed components for camera mounting systems and facial recognition hardware, while developing 3D scanning protocols for ergonomic device design that accommodates all sensor modalities in a user-friendly form factor.
Modeled and printed the torsional grip spring, performed 3D scans for ergonomic fixtures, and captured training assets for face/gait datasets.
Week 4 - Electronics Design
EDA and schematic design for the aging biomarker device electronics.
EDA toolsSchematic designCircuit design
System Integration Plans: Design comprehensive PCB schematics that integrate force sensor circuits for grip strength measurement, microphone preamplifiers for voice analysis, camera interfaces for facial recognition, and timing circuits for reaction time assessment into a unified electronics platform.
Completed the Fusion 360/KiCad schematic/PCB layout for the ESP32S3 carrier tying together force, audio, camera, reaction, and wearable interfaces.
Week 5 - Electronics Production
PCB fabrication, debugging, and assembly for the biomarker device.
PCB fabricationDebuggingAssembly
System Integration Plans: Fabricate and assemble the integrated PCB containing all sensor interfaces, implementing power management systems for continuous operation and establishing data storage protocols for the multimodal biomarker data collection system.
Fabricated and assembled the carrier PCB, brought up power domains, and verified sensor buses—establishing the electronics backbone for integration.
Week 6 - Computer-controlled Machining
CAM and milling for precision components and device housings.
CAMMillingPrecision machining
System Integration Plans: Machine precision mechanical components for the integrated device housing using computer-controlled milling, ensuring proper alignment and mounting for all sensor modules while maintaining ergonomic design for user comfort during multimodal data collection.
Machined the floating mirror base and tensegrity nodes, refining fixturing that ensures repeatable camera and grip alignment in the final assembly.
Week 7 - Input Devices
Sensors and embedded architectures for data collection in the biomarker device.
SensorsInput devicesData collection
System Integration Plans: Integrate all six input sensor systems (force sensors for grip strength, microphones for voice analysis, cameras for facial recognition and gait analysis, reaction time circuits, and wearable accelerometer) into the unified data collection platform with real-time processing capabilities.
Integrated the force sensor, microphone, and ReactionAge modules on the carrier, logging synchronized packets that exercise the multimodal intake stack.
Week 8 - Output Devices
Actuators and system integration for the biomarker device outputs.
ActuatorsOutput devicesSystem integration
System Integration Plans: Implement output devices including display systems for real-time intrinsic capacity feedback and haptic feedback mechanisms for user interaction, creating an intuitive interface for the multimodal biomarker assessment system.
Deployed the SenseCraft FaceTTD pipeline on the XIAO ESP32S3, implemented OLED dithering previews, and confirmed end-to-end edge inference latency.
Week 9 - Molding & Casting
Forming and resin techniques for bioprinting molds and device components.
MoldingCastingResins
System Integration Plans: Create custom molded components for the bioprinting aspects of the project and develop specialized casings for sensor protection, ensuring the device can withstand continuous use during multimodal data collection sessions.
Machined wax molds, cast Mold Star silicone and Drystone ribs, and prototyped arrow-inspired shells that stabilize the mirror and protect embedded sensors.
Week 10 - Mechanical & Machine Design
Kits and mechanical design for the bioprinting and biomarker device systems.
Mechanical designMachine designSystem integration
System Integration Plans: Complete the mechanical design integration of all system components, implementing calibration protocols for sensor alignment and developing the complete mechanical framework that houses all six digital biomarker measurement systems.
Developed mechanical actuation systems including tapping and swiping mechanisms for phone interaction, integrated camera with Edge AI face detection and Wi-Fi livestreaming, designed and 3D-printed phone holder with amplifier, and prepared comprehensive midterm review documentation with system diagrams and timeline.
Week 11 - Networking & Communications
BLE, Wi-Fi, and communication protocols for the biomarker device connectivity.
BLEWi-FiCommunications
System Integration Plans: Implement wireless communication protocols (Bluetooth/Wi-Fi) for seamless data transmission from all six sensor modalities, enabling real-time data fusion and establishing connectivity for the wearable accelerometer integration into the multimodal assessment system.
Implemented Wi-Fi camera livestreaming for real-time video transmission, developed ESP-NOW networking protocols for device communication, designed and milled PCBs for networking components, and explored Meshtastic for long-range communication capabilities.
Week 12 - Interface & Application Programming
UI and application development for the biomarker device interface.
UI designApplicationsUser interface
System Integration Plans: Develop the complete user interface and application programming for the multimodal system, implementing the machine learning pipeline for intrinsic capacity score calculation and creating cloud integration for comprehensive data storage and analysis of all biomarker measurements.
Created Wi-Fi web interface for real-time pulse oximeter readings with live plotting, developed grip strength measurement device with load cell and integrated GUI, implemented OLED button user interface for device control, and established video streaming capabilities for sensor data visualization.
Week 13 - Wildcard & Final Orders
Final orders and wildcard week activities for project completion.
Final ordersWildcard activitiesProject completion
System Integration Plans: Complete final system integration, testing, and validation of the complete multimodal intrinsic capacity assessment platform, ensuring all six digital biomarkers work cohesively to provide accurate WHO-defined intrinsic capacity scores across all five domains (locomotor, cognition, vitality, sensory, psychological).
Designed and fabricated ATtiny1626 tiny development board with fiber laser PCB engraving, created glass engraving system with UV laser including blinking heart integration for visual feedback, milled mounting holes and completed board assembly, and prepared final board designs for system integration.
System Integration
Final integration week focused on bringing all subsystems together, completing hardware fabrication, firmware integration, and documentation for the MirrorAge system presentation. View full details →
Initial system integration work focused on subsystem validation, CAD model consolidation, and design backbone acquisition for band integration. Conducted comprehensive testing of all subsystems to ensure proper functionality, identified and resoldered defective joints, and exported CAD models of all PCBs into a unified assembly model.
Integrated CAD Model: Exploded isometric view of the complete system assembly, including all PCBs, main housing with transparent enclosure, and wearable band components.
Physical integration of subsystems into the complete demo table assembly, including mechanical component fabrication and electrical board consolidation. Integrated the complete demo table with precise placement of the MirrorAge handgrip subsystem and aging clock subsystem, providing a unified platform for system demonstration.
Complete Demo Table Assembly: Integrated mechanical design showing precise placement of the MirrorAge handgrip subsystem and aging clock subsystem on the demo table.
Continued fabrication work integrating all manufacturing processes. Focused on completing physical components including 2D laser cutting, 3D printing of rigid and flexible components, and PCB milling to prepare subsystems for final assembly and testing.
TPU Band Print: Flexible wearable band component printed using TPU material
Flexible Band: TPU band demonstrating material properties and print quality
Comprehensive subsystem integration combining 2D fabrication (laser cutting), 3D printing (rigid and flexible components), PCB milling (single and double-sided boards), and molding/casting to complete all physical components. Upgraded MirrorAge TFT board to v13 and aging clock TFT board to v16 with optimized component placement and routing. Established reliable I²C bus communication and validated all sensor addresses.
Laser Cutting
Thin Acrylic Cutting: Laser cutting 1.35mm acrylic sheet for improved display cover fit
Successful Cut: Completed laser-cut acrylic display cover with precise dimensions
Final integration day focused on closing the watch subsystem, soldering and verifying all double-sided boards, refining molded bands, and assembling the complete MirrorAge demo with both the aging clock and grip-strength subsystems fully wired and tested. Completed rivet installation for plated through-holes, sensor bring-up (accelerometer, pulse oximeter, OLED/TFT displays), and full system integration on the tensegrity demo table. The integrated system successfully demonstrated synchronized sensor readouts and display behavior across all boards.
Rivet Installation & Soldering
Placing Rivets: Using tweezers to drop rivets into each via before flipping the board
Rivet Flaring: First hammering pass to open each rivet with the thin mandrel
Double-Sided Soldering: Dense layout executed with controlled solder volume to preserve enclosure clearance
Soldered MirrorAge Board: Complete double-sided board with all components installed
Soldering Passives: Close-up of tip control to avoid tombstoning small components
Sensor Testing & Bring-Up
Accelerometer Bring-Up: First successful accelerometer readings confirmed on the aging clock board
Pulse Oximeter Bring-Up: MAX30102 readings verified after soldering and I²C debugging
OLED Verification: Base OLED display tested before migrating to TFT-only operation
Display Stack: OLED and TFT displays confirmed working simultaneously during integration testing
System Integration
Integrated Watch Subsystem: TPU bands fastened into the watch clip with assembled electronics
Enclosure Fit: Final mechanical fit confirming CAD accuracy and proper clearances
Working Integrated System: Complete MirrorAge system demonstrating synchronized sensor readouts and display behavior
Final project presentation and demonstration of the complete MirrorAge system. Showcased the integrated aging clock and grip-strength subsystems working together on the demo table, demonstrating real-time sensor data collection and display synchronization. View final presentation demo →
Final Presentation Demo: Complete MirrorAge system demonstration showing integrated aging clock and grip-strength subsystems operating together in real-time
Full Documentation: For complete details, design files, code, and comprehensive documentation of the system integration process, see Week 14: System Integration.
Final Project Masterpiece
Complete demonstration of the integrated MirrorAge system showcasing all subsystems working together in real-time.
Final Presentation Demo: Complete MirrorAge system demonstration showing the integrated aging clock and grip-strength subsystems operating together on the demo table, with synchronized sensor readouts and real-time display updates across all boards.
Complete repository of all design files, CAD models, schematics, PCB layouts, firmware, and fabrication files from Week 0 through Week 14, organized by week and component type.
Note: Additional design files, firmware, and documentation can be found in the respective week pages. Some files are part of larger archives (ZIP files) that contain multiple related design files.
Reflections & Learnings
Comprehensive reflections on the MirrorAge Intrinsic Capacity Mirror project development journey.
Modular system design allows for incremental development and component-level testing throughout the semester
Integration of mechanical, electrical, and software subsystems requires careful planning and coordination
Iterative design and prototyping revealed the importance of early testing and validation
Documentation and knowledge transfer are critical for project continuity and future improvements
The project successfully demonstrates how digital fabrication and embedded systems can create meaningful health assessment tools
Contributions
Acknowledgements and contributions that made this project possible.
Gladyshev Lab and Collaborators
Special thanks to the Gladyshev Lab and collaborators for the fruitful discussions that led to this multimodal intrinsic capacity assessment idea,
which supplements my PhD research goals in aging and longevity. The conceptual framework for integrating multiple digital biomarkers
to assess intrinsic capacity domains emerged from collaborative research discussions on aging biomarkers and healthspan assessment.
Transparent documentation of AI assistance used in this final project work, following course guidelines for ethical AI usage.
📋 General Guidelines: See General Commands for Cursor on the homepage for standard guidelines and commands used consistently throughout documentation development.
Cursor · Project Plan & Weekly Schedule
Comprehensive Cursor AI assistance for outlining the project plan and weekly schedule, including documentation structure, content organization, systematic updates across all week pages and the final project page, media integration, and summary generation workflows.
Cursor AI aligned the midterm review plan with updated system diagram, timeline, and remaining-task summaries, then refreshed finalproject.html to remove legacy bioprinting language and re-point internal links. The full transcript and generated HTML are available for review.
Cursor AI assistance for adding a white background behind the photo in the Final Project Spiral Development Model section on finalproject.html. The image container was updated with white background, padding, and rounded corners for improved visual presentation.
Cursor AI distilled Week 0–9 documentation and the Oct 31 lab meeting deck into midterm-ready narrative, cost, and validation content, replacing every placeholder in finalproject.html.
Transcript archived in markdown and HTML (generated via scripts/md_to_html_converter.py) for transparency.
ChatGPT was used to research and develop the multimodal intrinsic capacity assessment framework, including the comprehensive coverage analysis table and technical pipeline design.
The AI assisted with structuring the WHO-defined intrinsic capacity domains, identifying appropriate digital biomarkers, and designing the fusion architecture for multimodal data processing.
Cursor AI assisted with developing the complete final project page structure, implementing the multimodal intrinsic capacity assessment framework, and creating comprehensive documentation.
The AI helped with HTML structure, responsive design, weekly system integration plans, and organizing the technical documentation for the complete biomarker assessment system.
Cursor AI assisted with finalizing the project presentation structure to ensure full compliance with MIT Academy project presentation requirements.
The AI helped implement all required sections including answering questions, design documentation, bill of materials, individual mastery requirements,
course presentation structure, and spiral model development approach visualization.
ChatGPT was used to discuss camera system implementation strategies, image processing algorithms, and EdgeAI integration approaches.
The AI assisted with understanding Floyd-Steinberg dithering implementation, touch sensor integration, and exploring TinyML deployment options for the XIAO ESP32S3 platform.
AI-Assisted Project Highlights and Camera Subsystem Development
Cursor AI assisted with adding the project highlights section featuring camera system achievements and creating a comprehensive camera subsystem section with detailed code implementations, video demonstrations, and EdgeAI integration documentation.
The AI helped with HTML structure, responsive design, image processing explanations, and organizing the technical documentation for the complete camera system showcase.
```
## Changes Made:
### Day 4: Subsystem Integration
- Removed "vinyl cutting" from the description
- Added Laser Cutting subsection with:
- 2 images showing the cutting process and results
- 1 video of the laser cutting operation
- Added PCB Milling subsection with:
- 2 videos showing front and back milling operations
- 2 images showing board removal and double-sided result
- Kept Board Design Upgrades subsection with TFT board images
### Day 5: Full System Integration
- Added Rivet Installation & Soldering subsection with:
- 2 videos showing rivet placement and flaring
- 2 images showing double-sided soldering and completed board
- 1 video showing passive component soldering technique
- Added Sensor Testing & Bring-Up subsection with:
- 4 images showing accelerometer, pulse oximeter, OLED, and TFT display testing
- Added System Integration subsection with:
- 2 images showing integrated watch subsystem and enclosure fit
- 1 video showing the working integrated system
The summaries now include organized media for each process, making the integration work clearer and easier to follow.
.png)
This work is licensed under a
Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License
