ECG classification using wavelet subband energy based features

Detection and classification of electrocardiogram (ECG) signals is critically linked to the diagnosis of cardiac abnormalities. In this paper, a novel approach for ECG classification is presented using features based on wavelet subband energy coefficients. The ECG signals are decomposed into time-frequency representation using wavelet transform and then wavelet coefficients are used to calculate some statistical parameters. Types of ECG beat considered for the classification are normal beat, paced beat, pre-ventricular contraction, left bundle branch block and right bundle branch block beat. The signals are obtained from the MIT-BIH Arrhythmia database. Multilayer Perceptron Neural Network is used for classification.