Classification of cardiac arrhythmia stages using hybrid features extraction with K-nearest neighbour classifier of ECG signals

Abstract

The catastrophic heart diseases such as Myocardial Infarction (MI), Heart Failure (HF) and Ischemic Heart Disease (IHD) is a chain process leads to Coronary Artery Disease (CAD). The analysis of CAD from Electrocardiogram (ECG) signals by manual techniques are quite difficult. Therefore, there is need of techniques without human interaction for classifying the CAD should be improved. This work presented the recognition of five types of ECG beats by using a three-step system. In the first step, Pan-Tompkins algorithm (PTA) is used for detecting the peaks in ECG signals. The second step includes extraction of three interval features combined with ECG higher order statistics. In the third step for classifying ECG beats K-Nearest Neighbour (KNN) technique is employed. This approach analysed the heartbeats as normal or abnormal as accurately, and the experiments were conducted on MIT/BIH arrhythmia database for classifying the ECG signals. The results stated that the accuracy of the proposed approach is up to 98.40% for segregating the signals.