LSTM-Based ECG Classification for Continuous Monitoring on Personal Wearable Devices

TLDR

A novel ECG classification algorithm is proposed for continuous cardiac monitoring on wearable devices with limited processing capacity. The algorithm uses a wavelet transform followed by multiple LSTM recurrent neural networks. Experimental results show the algorithm outperforms prior work, meets real‑time timing on various hardware, and remains lightweight. Source code is available online.

Abstract

Objective: A novel ECG classification algorithm is proposed for continuous cardiac monitoring on wearable devices with limited processing capacity. Methods: The proposed solution employs a novel architecture consisting of wavelet transform and multiple LSTM recurrent neural networks. Results: Experimental evaluations show superior ECG classification performance compared to previous works. Measurements on different hardware platforms show the proposed algorithm meets timing requirements for continuous and real-time execution on wearable devices. Conclusion: In contrast to many compute-intensive deep-learning based approaches, the proposed algorithm is lightweight, and therefore, brings continuous monitoring with accurate LSTM-based ECG classification to wearable devices. Significance: The proposed algorithm is both accurate and lightweight. The source code is available online [1].