Explainable AI Feature Chart Kit with ESP32 + DHT22
Explainable AI on ESP32: Feature Importance Chart Kit with Sensors & TFLite
Every part needed, pre-tested for compatibility, with an AI build companion trained on this exact project. Shipped from Bengaluru in 3-5 days.
Imagine a compact device that not only classifies its surroundings but also shows exactly which sensor influenced its decision—temperature spike, a specific vibration pattern, or sudden motion. This kit turns a TensorFlow Lite classifier on an ESP32 into a transparent, LIME-style explanation engine. You’ll collect raw readings from DHT22, ADXL345, and MPU6050, run inference, and render a real-time bar chart of feature importance on the colour display. It’s the perfect way to demystify edge ML for research, hackathons, or final-year engineering projects.
What You'll Build
A fully functional edge AI system: the ESP32 reads multi-sensor data, runs a TensorFlow Lite classifier to determine the current state (e.g., idle, walking, hot room), and displays both the predicted class and the feature importance chart on the 2.4-inch TFT screen. You’ll have a self-contained, battery-powered instrument that proves how even tiny microcontrollers can deliver interpretable AI.
What You'll Learn
- Train and quantize a TensorFlow Lite classifier for microcontroller deployment
- Implement a LIME-like feature attribution method—generate importance scores by perturbing input features and observing output changes
- Design an embedded dashboard on ILI9341 TFT: real-time bar chart for feature importance and classification result
- Integrate DHT22, ADXL345, and MPU6050 via I2C to build a robust sensor pipeline
Kit Contents
| Component | Quantity |
|---|---|
| ESP32 Dev Board | 1 |
| ADXL345 Accel | 1 |
| DHT22 | 1 |
| MPU6050 | 1 |
| 2.4in TFT ILI9341 | 1 |
| 4.7kΩ Resistors | 5 |
| 100nF Capacitors | 5 |
| PCB Prototype Board | 2 |
| 5V 2A Power Supply | 1 |
| Enclosure Box | 1 |
| Soldering Iron | 1 |
| Solder Wire | 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
Ideal for B.Tech ECE, CSE, and AI students at NITs, VIT, BITS Pilani, and IITs who need a tangible project for their capstone, Smart India Hackathon, or IEEE paper. Self-taught embedded ML developers wanting to move beyond accuracy and explain model decisions will also find it invaluable.
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?
Scan the QR code to launch the AI companion, which walks you through each connection and code block. If you need a human touch, message us on WhatsApp—we typically reply in minutes.
Do I need prior experience with TensorFlow Lite?
Yes, basic familiarity is recommended. The companion code and the AI assistant will guide you through training a custom model and converting it, but you should be comfortable with Python and the ML workflow.
Can I collect my own dataset for a different classification task?
Absolutely. The kit includes scripts to record labelled sensor data via the ESP32’s serial out. The LIME-explanation pipeline adapts automatically, so you can train a classifier for any multi-sensor scenario and still get feature importance charts.
Is the AI companion a chatbot or an app?
It’s a web-based assistant that loads when you scan the QR code—no downloads required. It contains the full project map, wiring diagrams, and code snippets. WhatsApp backup is available whenever you are offline or prefer written conversation.
TFLite classifier on ESP32. LIME-style local explanation visualised as bar chart showing feature importance.
What's in this kit
Choose your assembly option:
- Soldering Kit — 25W soldering iron, 60/40 solder wire, flux, and small perfboard for permanent assembly.
- Breadboard Combo — 800-point full-size breadboard with 65-piece jumper wire pack for solderless prototyping.
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