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

## TL;DR

This paper introduces a lightweight LSTM-based ECG classification algorithm designed for continuous real-time cardiac monitoring on wearable devices with limited processing power, demonstrating superior performance and meeting timing constraints.

## Contribution

The paper presents a novel architecture combining wavelet transform and multiple LSTM networks optimized for wearable ECG monitoring, which is both accurate and computationally efficient.

## Key findings

- Superior ECG classification accuracy compared to previous methods
- Meets real-time processing requirements on wearable hardware
- Lightweight architecture suitable for continuous monitoring

## 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].