Deep Convolutional Neural Networks for ECG Heartbeat Classification Using Two-Stage Hierarchical Method

Electrocardiogram (ECG) is widely used in computer-aided systems for arrhythmia detection because it provides essential information for the heart functionalities. The cardiologist uses it to diagnose and detect the abnormalities of the heart. Hence, automating the process of ECG heartbeat classification plays a vital role in the clinical diagnosis. In this paper, a two-stage hierarchical method is proposed using deep Convolution Neural Networks (CNN) to determine the category of the heartbeats in the first stage, and then classify the classes belonging to that category in the second stage. This work is based on 16 different classes from the public MIT-BIH arrhythmia dataset. But the MIT-BIH dataset is unbalanced, which degrades the classification accuracy of the deep learning models. This problem is solved by using an adaptive synthetic sampling technique to generate synthetic heartbeats to restore the balance of the dataset.