SEVGGNet-LSTM: a fused deep learning model for ECG classification

TL;DR

This paper introduces SEVGGNet-LSTM, a deep learning model combining CNN, LSTM, and attention mechanisms for robust ECG classification, validated across multiple datasets with promising results.

Contribution

It proposes a novel fused deep learning architecture integrating VGG, LSTM, and attention mechanisms for improved ECG classification accuracy.

Findings

Effective feature extraction with combined CNN and LSTM

Enhanced classification accuracy using attention mechanism

Robust performance across different datasets

Abstract

This paper presents a fused deep learning algorithm for ECG classification. It takes advantages of the combined convolutional and recurrent neural network for ECG classification, and the weight allocation capability of attention mechanism. The input ECG signals are firstly segmented and normalized, and then fed into the combined VGG and LSTM network for feature extraction and classification. An attention mechanism (SE block) is embedded into the core network for increasing the weight of important features. Two databases from different sources and devices are employed for performance validation, and the results well demonstrate the effectiveness and robustness of the proposed algorithm.