ECG Anomaly Detection

Project Overview

• Dataset: Utilized ECG-5000
• Model Architectures: Trained Autoencoder with reconstruction loss
• Results: Achieved out-class MSE Of 0.07
• Threshold: Decided Anomaly Threshold based upon 94th Percentile of Reconstruction Error of Normal Samples
• Pipeline: Modelled a pipeline for ECG and its reconstruction plot along with Model's Prediction

Results:

Normal Samples

Anoamly Detection

Getting Started

To get started with the project, follow these steps:

Clone the repository:

git clone https://github.com/Ahmaddimran/Histopathological-Lung-and-Colon-Cancer-Detection.git

Install dependencies:

Dataset -> http://storage.googleapis.com/download.tensorflow.org/data/ecg.csv

Contributing

Any contribution is welcomed!

Liesence

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

Acknowledgements

BIDMC Congestive Heart Failure Database(chfdb) https://www.timeseriesclassification.com/description.php?Dataset=ECG5000