End-to-End Optimized Arrhythmia Detection Pipeline using Machine Learning for Ultra-Edge Devices

Description

This repository contains code for the implementation of the paper titled "End-to-End Optimized Arrhythmia Detection Pipeline using Machine Learning for Ultra-Edge Devices", that has been published at the 20^th IEEE International Conference on Machine Learning and Applications (ICMLA21), Pasadena, CA, USA. You can download all three datasets from PhysioNet.

1. MIT-BIH Atrial Fibrillation DataBase (AFDB)
2. AF Classification from a Short Single Lead ECG Recording - The PhysioNet Computing in Cardiology Challenge 2017 (2017/CHDB)
3. MIT-BIH Malignant Ventricular Ectopy Database (VFDB)

Architecture

Publication Link

Link: https://ieeexplore.ieee.org/document/9680091

Citation:

@INPROCEEDINGS{9680091,  
    author={Sideshwar, J B and Sachin Krishan, T and Nagarajan, Vishal and S, Shanthakumar and Vijayaraghavan, Vineeth},
    booktitle={2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA)},   
    title={End-to-End Optimized Arrhythmia Detection Pipeline using Machine Learning for Ultra-Edge Devices},   
    year={2021},  
    volume={},  
    number={},  
    pages={1501-1506},  
    doi={10.1109/ICMLA52953.2021.00242}}