Arrhythmia Classification using 1D CNN

This project uses a 1D Convolutional Neural Network (CNN) to classify arrhythmias in ECG data. The dataset used is the MIT-BIH Arrhythmia Database, which contains ECG recordings of various arrhythmia types. The project is implemented using TensorFlow, Keras, and other Python libraries.

Table of Contents

1. Requirements
2. Dataset
3. Usage
4. Project Structure
5. License

Requirements

To install the required Python packages, run the following command:

pip install biosppy tensorflow keras sklearn matplotlib numpy scipy pywt pandas

Dataset

The dataset can be downloaded from the MIT-BIH Arrhythmia Database. To download the dataset, navigate to the link and download the files in the "mitdb" folder. Save the files in a directory of your choice (e.g., "mitDB").

Usage

1. Download the dataset and save it in a directory.
2. Update the path variable in the Jupyter Notebook file with the directory where the dataset is saved.
3. Run the Jupyter Notebook cells to preprocess the data, train the 1D CNN model, and evaluate the model's performance.

path = "your_directory_path_here/mitDB/"

Project Structure

The Jupyter Notebook consists of the following sections:

• Importing required libraries
• Defining plot settings and functions
• Reading and processing the dataset
• Data preprocessing
• Training and testing the 1D CNN model
• Model evaluation and confusion matrix

By following the steps mentioned in the "Usage" section, you can train and evaluate the 1D CNN model for arrhythmia classification using the MIT-BIH Arrhythmia Database.

License

This project is licensed under the MIT License. See the LICENSE file for details.