Cross Wavelet Transform based ECG Pattern Analysis and Classification

In this project, we use cross wavelet transform (XWT) for the analysis and classification of Electro Cardio Gram (ECG) signals. The cross correlation between two time domain signals gives a measure of similarity between two waveforms. The application of the continuous wavelet transform(CWT) to two time series and the cross examination of the two decompositions reveal localized similarities in time and frequencies. Application of the XWT to a pair of data yields wavelet cross spectrum (WCS) and wavelet coherence (WCOH). The proposed algorithm analyses ECG data utilizing XWT and explores the resulting spectral differences. A normal beat ensemble is selected as the absolute normal ECG pattern template and the coherence between various other normal and abnormal subject is computed. The WCS and WCOH of various ECG pattern show distinguishing characteristics. The simulated ECG data base and real ECG data base obtained from Physionet are used for evaluation of the methods. A heuristically determined mathematical formula extracts the features from WCS and WCOH. The features extracted from WCS are used as input to the nearest neighbor classifier for classifying normal and abnormal patterns. Finally the normal and abnormal signals are classified using k Nearest Neighbor classifier.