TinyML Step Counter Wristband Kit with ESP32 + LED
Build Your Own AI-Powered Step Counter Wristband with ESP32-S3 and TensorFlow Lite
Every part needed, pre-tested for compatibility, with an AI build companion trained on this exact project. Shipped from Bengaluru in 3-5 days.
With this kit, you won’t just assemble a circuit — you’ll train and deploy a real machine learning model that counts your steps and classifies walking or running activity on a wrist-worn device. The ADXL345 accelerometer feeds motion data into a TensorFlow Lite step detection model running on the ESP32-S3, and the OLED displays your real-time step count. It’s a compact introduction to embedded AI that feels like a genuine wearable prototype, perfect for fitness enthusiasts, CBSE science projects, or exploring on-device machine learning.
What You'll Build
A USB-powered step counter that uses a MEMS accelerometer to capture movement, runs a quantized TensorFlow Lite model to detect each step, and displays the count along with an activity class (walking, running, or idle) on a crisp 0.96‑inch OLED screen. The tactile button lets you reset the step count, and the breadboard layout keeps everything accessible so you can modify, extend, or repackage it in a 3D-printed wristband case.
What You'll Learn
- Collecting and pre‑processing accelerometer data for time‑series classification on a microcontroller
- Training a TensorFlow Lite model and converting it for edge deployment on ESP32‑S3
- Interfacing an I2C OLED display and ADXL345 sensor with ESP32‑S3
- Optimising memory and inference speed for real‑time on‑device AI workloads
Kit Contents
| Component | Quantity |
|---|---|
| ESP32-S3 Dev Board | 1 |
| ADXL345 Accel | 1 |
| 0.96in OLED | 1 |
| Tactile Button | 1 |
| 4.7kΩ Resistors | 5 |
| 100nF Caps | 5 |
| 400-pt Breadboard | 1 |
| M-M Wires | 20 |
| Micro USB Cable | 1 |
Why Buy This Kit Instead of Sourcing Parts Separately
| Factor | Sourcing Separately | Compoden Kit |
|---|---|---|
| Compatibility checks | You verify every part | Pre-tested as a system |
| Build support | Forums and scattered tutorials | AI companion trained on this exact project |
| Time to first working build | Days of debugging | Hours, with step-by-step guidance |
| Shipping coordination | Multiple sellers, multiple delays | One shipment from Bengaluru in 3-5 days |
Who This Kit Is For
This kit is designed for CBSE Class 11–12 students working on AI and electronics curriculum projects, and for B.Tech ECE/EEE undergraduates prototyping wearable health devices at institutions like VIT, BITS, or NITs. It’s also a strong fit for Smart India Hackathon teams building fitness trackers and for ATL Tinkering Labs that want a hands‑on introduction to machine learning on microcontrollers, without needing prior ML experience.
Built and Backed by Compoden
Every Compoden kit ships with an AI build companion trained on this exact project — accessible via a QR code on the box, with WhatsApp and email backup. We've spent 10 years building projects for makers, schools, and institutions across India. If a part fails because of a manufacturing defect, replace it free within 7 days.
What if I get stuck during the build?
Your AI companion provides real‑time debugging suggestions, and our team is available on WhatsApp for direct guidance — you'll never be left alone.
Do I need prior machine learning experience?
No. The companion walks you through training the step‑detection model using a free Google Colab notebook, so you learn the concepts while getting a working model without any coding overhead.
Can I wear this like a regular wristband?
The circuit is breadboarded for easy prototyping. You can transfer it to a 3D‑printed wristband case (not included) and power it with a Li‑Po battery connected to the ESP32‑S3’s battery header for a wearable form factor.
How is the step count accuracy compared to a phone?
The TensorFlow Lite model is trained on real walking and running data from the ADXL345. With proper placement on the wrist, it achieves step‑counting accuracy comparable to basic fitness bands, and you can retrain the model with your own data to improve it further.
ADXL345 feeds a TensorFlow Lite step detection model on ESP32-S3. OLED shows step count and activity class.
What's in this kit
Other projects you can build
Shipping Information
- Prepaid Orders: ₹75 for orders up to ₹999, FREE shipping above ₹999
- COD Orders: ₹125 shipping + ₹50 COD fee = ₹175 total
- Delivery Timeline: Dispatch in 1-2 days, delivery in 2-7 days depending on location
Returns & Warranty
- 7-Day Return: Manufacturing defects only (approval required)
- Warranty: 7 days from delivery
- Non-Returnable: Batteries, consumables, cut wires, clearance items