DOI: 10.5176/2251-2179_ATAI11
Authors: Thomas Sri Widodo
Abstract:
This paper discusses on the feature extraction and classification of electrocardiogram (ECG) using multi resolution wavelet transform and back propagation neural network. In this paper Sym8 wavelet is chosen for obtaining the approximation and details signals and their normalized energy features. Based on the data obtained from MIT-BIH Database, classification for the ECG of normal sinus rhythm, arrhythmia, and intracardiac atrial fibrillation can be done.
Keywords: Electrocardiogram, feature extraction, classification, wavelet transform, neural network.
