Neural Network KNN — Road Surface Condition Classification

Neural Network KNN is a machine learning project designed to determine road surface conditions based on accelerometer sensor data.
The model uses K-Nearest Neighbors (KNN) to classify road states by analyzing datasets obtained from the Z-axis accelerometer indicator.

This solution can be applied in vehicle telemetry, road quality monitoring, and intelligent transport systems.

How It Works

Sensor data collected from an accelerometer is processed and used as input for the KNN model.
By analyzing vibration patterns along the Z-axis, the algorithm identifies and classifies the current road surface condition.

The model is trained on prepared datasets and can be adapted to different vehicles or sensor configurations.

Key Features & Capabilities

Road Surface Classification
Detects and classifies road conditions based on accelerometer data.

KNN-Based Machine Learning Model
Simple, effective, and interpretable approach for sensor data classification.

Z-Axis Accelerometer Analysis
Focuses on vertical vibration data for accurate road condition detection.

Extensible Data Pipeline
Easily adaptable to new datasets or sensor inputs.

Tech Stack

Python

NumPy

Pandas

Scikit-learn

TensorFlow

OpenPyXL