Arrhythmia Detection Algorithm Using 1D-CNN and Wavelet Soft Thresholding Methods

With the increasing aging of the population, cardiovascular diseases have become one of the most important causes of death. Arrhythmia is one of the common conditions of cardiovascular diseases, and electrocardiogram (ECG) can reflect information about the electrical activity of the heart, and an abnormal ECG can detect different kinds of arrhythmia. By visual inspection of ECG is not only time consuming but can lead to misdiagnosis which in turn affects the treatment of the disease. With the enhanced availability of wearable devices, home monitoring turns out to be a more preferred option for the elderly. In this paper, a lightweight automatic arrhythmia classification method based on wavelet soft threshold transform method and convolutional neural network (CNN) is proposed. Experiments were conducted using the MIT-BIH arrhythmia dataset for the training and validation of the model, and arrhythmias were categorized into five categories according to the Association for the Advancement of Medical Instrumentation (AAMI) criteria, and an accuracy of 99.47% was finally obtained.