AUTOMATIC ARRHYTHMIA DETECTION USING SUPPORT VECTOR MACHINE BASED ON DISCRETE WAVELET TRANSFORM

Abstract

Arrhythmia is abnormal electrical activity that happens in the heart, causing less effective pumping; where an abnormally fast electrical signal causes two problems: first, the heart pumps too quickly and second, fills the ventricles with an inadequate amount of blood. Alternatively, the abnormal electrical signal makes it pump a sufficient amount of blood out to the body too slowly. It is classified by both its location of origin and rate. Some arrhythmias are life-threatening and can result in cardiac arrest. Arrhythmia can be a challenge to understand, but with automated detection, diagnosis is more simple. The purpose of this study is to introduce a robust implementation algorithm to discriminate between normal sinus rhythm and three types of arrhythmia (atrial fibrillation, ventricular fibrillation, and supra ventricular tachycardia that were collected from physionet database). This can be done by capturing the main features that contain both frequency and location information of the signal through discrete wavelet transform, followed by principal component analysis on each decomposed level