Multi-Feature Fusion and Compressed Bi-LSTM for Memory-Efficient Heartbeat Classification on Wearable Devices

TL;DR

This paper introduces a resource-efficient ECG heartbeat classification method using multi-feature fusion and compressed Bi-LSTM, achieving high accuracy on challenging classes with fewer parameters suitable for wearable devices.

Contribution

It proposes a novel multi-feature fusion approach combined with compressed Bi-LSTM for accurate, memory-efficient heartbeat classification on wearable devices.

Findings

Improved classification accuracy for RBBB and LBBB classes.

Achieved 28% reduction in network parameters with Bi-LSTM.

Developed multiple neural network models of varying sizes for high accuracy.

Abstract

In this article, we present a resource-efficient approach for electrocardiogram (ECG) based heartbeat classification using multi-feature fusion and bidirectional long short-term memory (Bi-LSTM). The dataset comprises five original classes from the MIT-BIH Arrhythmia Database: Normal (N), Left Bundle Branch Block (LBBB), Right Bundle Branch Block (RBBB), Premature Ventricular Contraction (PVC), and Paced Beat (PB). Preprocessing methods including the discrete wavelet transform and dual moving average windows are used to reduce noise and artifacts in the raw ECG signal, and extract the main points (PQRST) of the ECG waveform. Multi-feature fusion is achieved by utilizing time intervals and the proposed under-the-curve areas, which are inherently robust against noise, as input features. Simulations demonstrated that incorporating under-the-curve area features improved the classification accuracy for the challenging RBBB and LBBB classes from 31.4\% to 84.3\% for RBBB, and from 69.6\% to 87.0\% for LBBB. Using a Bi-LSTM network, rather than a conventional LSTM network, resulted in higher accuracy (33.8\% vs 21.8\%) with a 28\% reduction in required network parameters for the RBBB class. Multiple neural network models with varying parameter sizes, including tiny (84k), small (150k), medium (478k), and large (1.25M) models, are developed to achieve high accuracy \textit{across all classes}, a more crucial and challenging goal than overall classification accuracy.