A Comparison of 1-D and 2-D Deep Convolutional Neural Networks in ECG Classification

TL;DR

This paper compares 1D and 2D CNN approaches for ECG arrhythmia detection, demonstrating that 2D CNNs initialized with ImageNet weights outperform 1D methods in accuracy and robustness.

Contribution

It introduces a 2D CNN-based ECG classification method using image representations and shows improved performance over 1D methods with transfer learning.

Findings

2D CNN achieves 98% accuracy on MIT-BIH database

2D CNN with ImageNet initialization outperforms 1D signal method

High accuracy maintained across SNR range from 20 dB to 35 dB

Abstract

Effective detection of arrhythmia is an important task in the remote monitoring of electrocardiogram (ECG). The traditional ECG recognition depends on the judgment of the clinicians' experience, but the results suffer from the probability of human error due to the fatigue. To solve this problem, an ECG signal classification method based on the images is presented to classify ECG signals into normal and abnormal beats by using two-dimensional convolutional neural networks (2D-CNNs). First, we compare the accuracy and robustness between one-dimensional ECG signal input method and two-dimensional image input method in AlexNet network. Then, in order to alleviate the overfitting problem in two-dimensional network, we initialize AlexNet-like network with weights trained on ImageNet, to fit the training ECG images and fine-tune the model, and to further improve the accuracy and robustness of ECG classification. The performance evaluated on the MIT-BIH arrhythmia database demonstrates that the proposed method can achieve the accuracy of 98% and maintain high accuracy within SNR range from 20 dB to 35 dB. The experiment shows that the 2D-CNNs initialized with AlexNet weights performs better than one-dimensional signal method without a large-scale dataset.