Cardiac beat classification based on wavelet analysis of empirical mode decomposed ECG signals

This paper presents a cardiac beat classification method based on wavelet analysis of decomposed ECG signals obtained via empirical mode decomposition (EMD). Instead of analyzing the given ECG signal directly, first the intrinsic mode functions (IMFs) are extracted by using the EMD and then the discrete wavelet packet decomposition (WPD) is performed only on the selected dominant IMFs. Both approximate and detail WPD coefficients of the dominant IMF are taken into consideration. It is found that some higher order statistics of these EMD-WPD coefficients corresponding to different beat classes exhibit distinguishing characteristics and these statistical parameters are chosen as the desired features. Finally, the obtained feature set is used as an input to k nearest neighbor (KNN) classifier, which is employed for the purpose of classification. Extensive simulations are carried out on ECG signals taken from widely used MIT-B1II arrhythmia database to classify five classes of cardiac beats. Simulation results show that the proposed EMD-Wavelet based feature can provide quite satisfactory classification performance with reduced feature dimension.