PROJECT TITLE :

Application Of Cross Wavelet Transform For Ecg Pattern Analysis And Classification - 2014

ABSTRACT:

In this paper, we tend to use cross wavelet remodel (XWT) for the analysis and classification of electrocardiogram (ECG) signals. The cross-correlation between 2 time-domain signals gives a live of similarity between 2 waveforms. The appliance of the continuous wavelet transform to 2 time series and therefore the cross examination of the two decompositions reveal localized similarities in time and frequency. Application of the XWT to a combine of data yields wavelet cross spectrum (WCS) and wavelet coherence (WCOH). The proposed algorithm analyzes ECG information utilizing XWT and explores the resulting spectral differences. A pathologically varying pattern from the normal pattern within the QT zone of the inferior leads shows the presence of inferior myocardial infarction. A normal beat ensemble is chosen as absolutely the traditional ECG pattern template, and the coherence between numerous other normal and abnormal subjects is computed. The WCS and WCOH of numerous ECG patterns show distinguishing characteristics over 2 specific regions R1 and R2, where R1 is that the QRS complicated area and R2 is that the T-wave region. The Physikalisch-Technische Bundesanstalt diagnostic ECG database is used for analysis of the strategies. A heuristically determined mathematical formula extracts the parameter(s) from the WCS and WCOH. Empirical tests establish that the parameter(s) are relevant for classification of traditional and abnormal cardiac patterns. The overall accuracy, sensitivity, and specificity when combining the three leads are obtained as ninety seven.sixpercent, 97.3%, and 98.8%, respectively.