HomeCoursesProjectsCorporate TrainingPricingBlog
Start Building →
Edge AI · Beginner

Sensor data pipeline on ESP32

Wire raw sensor readings into a clean preprocessing pipeline ready for model input — the first checkpoint of the Production Edge AI Pipeline course.

Start Building View Related Course
Project build preview
Project blueprint

What you'll build

This project takes a raw sensor feed and turns it into the exact tensor shape a trained model expects — the unglamorous but essential first step of any real edge AI pipeline.

You'll leave with a clean preprocessing pipeline you can reuse across sensors and models, and an understanding of why this layer is where most on-device failures actually originate.

⌁
Included build referenceWiring diagram — ESP32, sensor, and power setup
✦
Project overview

Understand the build here. Learn and access the assets in the LMS.

This page covers what the project does, what you need, and how the build comes together. The LMS contains the complete lessons, source code, circuit diagrams, and deployment materials.

Start Learning →
Before you start

Build requirements

01An ESP32 development board
02A sensor of your choice (DHT22 used in the course)
03Basic Python familiarity
From setup to working system

Build sequence

Follow the steps in order, verify each checkpoint, and finish with a working project you can explain and extend.

01

Wire the sensor to the ESP32

Connect the sensor and confirm raw readings over serial.

02

Build the preprocessing pipeline

Normalize, window, and shape readings into model-ready tensors.

03

Validate against training data

Confirm the on-device pipeline matches what the model was trained on.

04

Hand off to inference

Pipe the preprocessed tensor into the model input — ready for the next project.

Build the next checkpoint

Stop collecting tutorials. Ship a working build.

Use this project as a concrete piece of your embedded, IoT, or edge AI portfolio.

Start Building →