Classification of Cardiac Signals with Automated R-Peak Detection Using Wavelet Transform Method

Heart rate is a vital sign that holds important information about cardiac signals. The measurement of heart rate is of particular interest since it reflects the dynamic changes of cardiac functions. Close examination of electrocardiogram (ECG) morphology is used to determine the specific value of heart rate as well as to distinguish between normal or abnormal heart functioning. Since ECG signal is contaminated by various noise components and artifacts like baseline wandering (BLW), power line interference (PLI), motion artifacts and electrode motion. Therefore, it is an immense task to separate the preferred signal from these noise contents and to measure physiological heart rate. Hence, this paper firstly presents wavelet transform based method to remove PLI and BLW noises, the major sources affecting recorded ECG. Furthermore for analyzing ECG signals and identifying characteristics features two methods have been proposed to calculate heart rate. They are: (i) temporal characteristics-based timing intervals between two consecutive R-peaks and (ii) local frequency-based ECG signal analysis used to identify number of R-peaks. At last according to the standard range of heart beats per minute, classification of normal and abnormal ECG is done and results obtained from both methods are compared. It includes simulation of 35 ECG records, out of which 24 are normal and 11 are abnormal, which are further classified in 4 fast heart beats and 7 slow heart beats called tachycardia and bradycardia respectively. The efficiency of proposed work is validated from MIT BIH arrhythmia database.

Automated summary

Heart rate is an important vital sign that reflects the dynamic changes of cardiac signals. This paper proposes a wavelet transform based method to remove noise and calculate physiological heart rate. Two methods, based on timing intervals and local frequency analysis, are used to analyze ECG signals and identify heart rate. The efficiency of the proposed work is validated using the MIT BIH arrhythmia database.