Heartbeat Classification Using 1D Convolutional Neural Networks

Abstract

Electrocardiogram (ECG) is an essential source of information for heart diseases classification. Hence, it is used by the cardiologist to diagnose heart attacks and detect the abnormalities of the heart. The automatic classification of the ECG signals is playing a vital role in the clinical diagnosis of heart diseases. In this paper, an end-to-end classification method is proposed using 1D Convolution Neural Networks (CNN) to extract the important features from the input signals and classify it automatically. The main advantage of CNN compared to the related work methods is that it gets rid of the hand-crafted features by combining the feature extraction and the classification into a single learning method without any human supervision. The proposed solution consists of data filtering, dynamic heartbeat segmentation, and 1D-CNN consisting of 10 layers without the input and the output layers. Our experimental results on 14 classes of the public MIT-BIH arrhythmia dataset achieved a promising classification accuracy of 97.8% which outperforms several ECG classification methods.