ECG-TCN: Wearable Cardiac Arrhythmia Detection with a Temporal Convolutional Network

TL;DR

This paper introduces a novel temporal convolutional network (TCN) for wearable ECG-based arrhythmia detection, achieving high accuracy with significantly fewer parameters and lower energy consumption suitable for long-term wearable health monitoring.

Contribution

The paper presents a TCN model that maintains high accuracy while drastically reducing computational complexity and energy use, enabling real-time wearable ECG analysis.

Findings

Achieves 94.2% accuracy on ECG5000 dataset

Uses 27 times fewer parameters than state-of-the-art models

Consumes 23 times less energy on embedded platforms

Abstract

Personalized ubiquitous healthcare solutions require energy-efficient wearable platforms that provide an accurate classification of bio-signals while consuming low average power for long-term battery-operated use. Single lead electrocardiogram (ECG) signals provide the ability to detect, classify, and even predict cardiac arrhythmia. In this paper, we propose a novel temporal convolutional network (TCN) that achieves high accuracy while still being feasible for wearable platform use. Experimental results on the ECG5000 dataset show that the TCN has a similar accuracy (94.2%) score as the state-of-the-art (SoA) network while achieving an improvement of 16.5% in the balanced accuracy score. This accurate classification is done with 27 times fewer parameters and 37 times less multiply-accumulate operations. We test our implementation on two publicly available platforms, the STM32L475, which is based on ARM Cortex M4F, and the GreenWaves Technologies GAP8 on the GAPuino board, based on 1+8 RISC-V CV32E40P cores. Measurements show that the GAP8 implementation respects the real-time constraints while consuming 0.10 mJ per inference. With 9.91 GMAC/s/W, it is 23.0 times more energy-efficient and 46.85 times faster than an implementation on the ARM Cortex M4F (0.43 GMAC/s/W). Overall, we obtain 8.1% higher accuracy while consuming 19.6 times less energy and being 35.1 times faster compared to a previous SoA embedded implementation.