The continuous wavelet transform using for natural ECG signal arrhythmias detection by statistical parameters

The electrocardiogram (ECG) is immensely beneficial for diagnosing the arrhythmias that may lead to serious complications in the heart health. In this paper, the continuous wavelet transform (CWT) was used for electrocardiogram arrhythmias detection. The natural arrhythmias were: Supra-ventricular arrhythmias (SV), atrioventricular (AV) and Normocardia (NC) were chosen for detection as well as for testing the proposed method The Natural signals were taken from MIT-BIH database to be used for testing. The continuous wavelet transform was connected to the standard deviation (SD) and Shannon entropy (SE) for feature extraction stage. For classification a safe threshold has been suggested to discriminate between the different arrhythmias. Several combinations of the CWT application were testing. The wavelet packet transform was used for comparison. All combinations have given reasonable results, but continuous wavelet transform with standard deviation taken for the third sub signal have given the superior results. The results of our study will open the door for choosing the continuous transform for detection that has been neglected by the researchers for this task.