A Light Weight Cardiac Monitoring System for On-Device ECG Analysis
Abstract
In this paper, we propose a demonstrable prototype of an on-device cardiac monitoring system comprising bio-sensor module and a low-powered microcontroller. Apart from measuring physiological vitals, the proposed system can classify abnormal heart rhythms on the microcontroller itself for low-cost 24 $\,\times \,$ × 7 unobtrusive monitoring. A Convolutional Neural network (CNN) is duly optimized to run on the constrained hardware platform for identification of normal, Atrial Fibrillation (AF) and other abnormal rhythms from single-lead electrocardiogram (ECG) signals. The system is successfully verified on offline dataset. It also reports promising accuracy when deployed for real-time health monitoring.
Cite
Text
Banerjee and Ghose. "A Light Weight Cardiac Monitoring System for On-Device ECG Analysis." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2022. doi:10.1007/978-3-031-26422-1_49Markdown
[Banerjee and Ghose. "A Light Weight Cardiac Monitoring System for On-Device ECG Analysis." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2022.](https://mlanthology.org/ecmlpkdd/2022/banerjee2022ecmlpkdd-light/) doi:10.1007/978-3-031-26422-1_49BibTeX
@inproceedings{banerjee2022ecmlpkdd-light,
title = {{A Light Weight Cardiac Monitoring System for On-Device ECG Analysis}},
author = {Banerjee, Rohan and Ghose, Avik},
booktitle = {European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases},
year = {2022},
pages = {649-653},
doi = {10.1007/978-3-031-26422-1_49},
url = {https://mlanthology.org/ecmlpkdd/2022/banerjee2022ecmlpkdd-light/}
}