Riding Behavior Monitoring App

Real-time motorcycle monitoring system built on Raspberry Pi. Features LSTM-based riding behavior prediction and smart OBD-II diagnostics with alerts for battery and engine health.

Technologies Used

Python

TensorFlow/Keras

HTML/CSS/JS

Raspberry Pi

MPU6050

OBD-II

Key Features

LSTM-based riding behavior prediction
Live stream of MPU6050 sensor data
Real-time OBD-II engine diagnostics
Smart alerts for battery and coolant health
Dashboard with behavior trends
Touchscreen-optimized UI

Project Overview

This personal project monitors motorcycle diagnostics and riding behavior using real-time sensor data and machine learning.

I independently designed and developed the entire system from hardware integration and backend logic to training the LSTM model and building the frontend UI.

The app runs on a Raspberry Pi with a 7-inch touchscreen and combines MPU6050 motion data with OBD-II engine readings. It classifies riding patterns and triggers smart alerts for battery and coolant issues.