ECG Heartbeat Classification

A machine learning project for classifying ECG heartbeats into normal and abnormal categories using signal preprocessing, feature extraction, and model training.
This repository contains a Jupyter Notebook with end-to-end workflow and a saved trained model file.

---

🧠 Project Overview

Electrocardiography (ECG) records the electrical activity of the heart and is widely used to diagnose cardiac conditions such as arrhythmias and other abnormalities. Automated ECG classification models help detect irregular heartbeats quickly and reliably, aiding in early diagnosis and monitoring.:contentReference[oaicite:1]{index=1}

This project explores building a machine learning model that:

• Loads ECG signal data
• Preprocesses and extracts meaningful features
• Trains and evaluates classifiers
• Saves a trained model for future inference

The trained model file ECG_ARRHYTHMIA_Classification.h5 and the notebook model.ipynb are included for reproducibility and extension.:contentReference[oaicite:2]{index=2}

---

📁 Repository Structure

ECG_Heartbeat_Classification/
├── ECG_ARRHYTHMIA_Classification.h5    # Trained classification model
├── model.ipynb                          # Notebook with preprocessing, training & evaluation
└── README.md                           # Project documentation

---

🛠 Installation & Setup

1. Clone the repository

   git clone https://github.com/abrarshahh/ECG_Heartbeat_Classification.git
   cd ECG_Heartbeat_Classification
   

2. Create and activate a Python virtual environment

   python3 -m venv venv
   source venv/bin/activate
   

3. Install dependencies

   pip install numpy pandas matplotlib scikit-learn tensorflow
   

---