Combination of Convolutional and Recurrent Neural Networks for Heartbeat Classification

Abstract

Electrocardiogram (ECG) plays an essential role in the medical field, it records the electrical activity of the heart over time and provides information about the heart condition. Hence, the cardiologist uses it to detect the abnormalities of the heart and to diagnose the heart diseases. Convolutional Neural Networks (CNNs) have proven their ability in extracting the most important features, Long Short-Term Memory (LSTM) has the capabilities of learning the temporal dependencies between the sequential data. In this paper, a novel method based on the combination of CNN and LSTM is proposed to classify 15 classes of the MIT-BIH dataset automatically without any hand-engineering feature extraction methods. The proposed method consists of data filtering, dynamic technique for heartbeat segmentation, and CNN-LSTM model consists of 12 layers.