Lightweight Multi-task CNN for ECG Diagnosis with GRU-Diffusion

TL;DR

This paper introduces a lightweight multi-task CNN with GRU-Diffusion for ECG diagnosis, achieving high accuracy and efficiency suitable for edge devices, by sharing knowledge across tasks and generating synthetic signals for imbalanced data.

Contribution

The paper presents a novel multi-task framework with integrated GRU-augmented Diffusion for improved ECG classification on resource-constrained devices.

Findings

Achieves over 99.7% accuracy on MIT-BIH and PTB datasets.

Uses fewer parameters than traditional models.

Effective for real-time ECG diagnosis on wearable devices.

Abstract

With the increasing demand for real-time Electrocardiogram (ECG) classification on edge devices, existing models face challenges of high computational cost and limited accuracy on imbalanced datasets.This paper presents Multi-task DFNet, a lightweight multi-task framework for ECG classification across the MIT-BIH Arrhythmia Database and the PTB Diagnostic ECG Database, enabling efficient task collaboration by dynamically sharing knowledge across tasks, such as arrhythmia detection, myocardial infarction (MI) classification, and other cardiovascular abnormalities. The proposed method integrates GRU-augmented Diffusion, where the GRU is embedded within the diffusion model to capture temporal dependencies better and generate high-quality synthetic signals for imbalanced classes. The experimental results show that Multi-task DFNet achieves 99.72% and 99.89% accuracy on the MIT-BIH dataset and PTB dataset, respectively, with significantly fewer parameters compared to traditional models, making it suitable for deployment on wearable ECG monitors. This work offers a compact and efficient solution for multi-task ECG diagnosis, providing a promising potential for edge healthcare applications on resource-constrained devices.