Arrhythmia Detection Using Wigner-Ville Distribution Based Neural Network

Abstract

Different techniques have been used by the researchers in recent years to detect arrhythmias from electrocardiogram(ECG) signal. In this paper we have used Wigner-Ville time-frequency energy distribution(WVD) and neural network to classify four different ECG beats. These four beats are Normal(N), Left Bundle Branch Block(L), Right Bundle Branch Block(R) and Ventricular Premature Contraction(V). The 1-D wall slice from the WVD of ECG signal is considered as the features to train the Back propagation Neural network(BPNN) for arrhythmia beat classification. ECG signal samples from MIT-BIH arrhythmia database are used. Two different testing datasets are considered to evaluate the performance of the technique. The experimental results achieved a maximum and minimum accuracy of 99.77% and 87.50% respectively.