Lightweight Multi-task CNN for ECG Diagnosis with GRU-Diffusion
Preprint
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.Keywords
All Related Versions
This publication has 18 references indexed in Scilit:
- A gated cross-domain collaborative network for underwater object detectionPattern Recognition, 2023
- Automated Atrial Fibrillation Detection using a Hybrid CNN-LSTM Network on Imbalanced ECG DatasetsBiomedical Signal Processing and Control, 2021
- Opportunities and challenges of deep learning methods for electrocardiogram data: A systematic reviewComputers in Biology and Medicine, 2020
- ML–ResNet: A novel network to detect and locate myocardial infarction using 12 leads ECGComputer Methods and Programs in Biomedicine, 2020
- Generalization of Convolutional Neural Networks for ECG Classification Using Generative Adversarial NetworksIEEE Access, 2020
- A Deep Bidirectional GRU Network Model for Biometric Electrocardiogram Classification Based on Recurrent Neural NetworksIEEE Access, 2019
- Automated Heartbeat Classification Exploiting Convolutional Neural Network With Channel-Wise AttentionIEEE Access, 2019
- A novel wavelet sequence based on deep bidirectional LSTM network model for ECG signal classificationComputers in Biology and Medicine, 2018
- Application of deep convolutional neural network for automated detection of myocardial infarction using ECG signalsInformation Sciences, 2017
- The impact of the MIT-BIH Arrhythmia DatabaseIEEE Engineering in Medicine and Biology Magazine, 2001