Deep Neural Network Classification for ECG Arrhythmia Detection with Optimized Feature Autoencoder

Heart disease has become the leading cause of death today. Electrocardiogram (ECG) is a device used to detect the patient's heart condition. This ECG test is painless but can provide important information to diagnose the patient's heart condition. The ECG signal produced becomes a reference for health practitioners to detect heart disease. Arrhythmia refers to irregularities in the rhythm of the heartbeat. The classification of ECG signals has attracted many researchers to study in recent years. In this study, classification using deep learning has shown very good results in detecting arrhythmias. The preprocessing process is carried out using normalize bound and autoencoder. ECG signals are segmented into short signals before going into the classification section. The proposed classification method uses DNN (Deep Neural Network). Where the DNN classification method gets excellent results, namely accuracy reaches 99.8%, sensitivity 87.77%, specificity 99.81%.