Arrhythmia discrimination using support vector machine

Abstract

In this paper support vector machine (SVM) classifier is developed for the classification of two types of arrhythmias i.e. premature ventricular contraction (PVC) and atrial premature contraction (APC). Discrete wavelet transform (DWT) is used for feature extraction of the ECG signal. For the classification purpose MIT-BIH arrhythmia database is used from the physionet.org. The aim of the work is to develop a technique which classifies the arrhythmia with higher accuracy. MATLAB 7.8.0(R2009a) is used for the simulation purpose.