A fast ECG diagnosis using frequency-based compressive neural network

Abstract

Electrocardiogram (ECG) diagnosis is a widely-used clinical approach because it has been proven as an efficient way to diagnose cardiac disease. However, to get an accurate ECG diagnosis is a challenging task because it is a nonlinear problem. Therefore, many Neural Network (NN)-based ECG analysis approaches were proposed to analyzes ECG signal in time domain in recent years which can improve the ability of ECG analyzing. However, these methods suffer from long computing time because of complex preprocessing. To solve this problem, we propose a method that analyze ECG signal in frequency domain. Different from the time-domain analysis, frequency domain analysis requires less preprocessing, fewer parameters, and less complexity of analysis. The experimental result shows that the proposed method save 80% of ECG diagnosis time compared with the conventional ECG wavelet analysis with only 5% average accuracy loss.