Algorithm for EMG noise level approximation in ECG signals

Abstract

Abstract In this paper, we introduce an approach for Electromyogram (EMG) noise level approximation in Electrocardiogram (ECG) signals. The stationary wavelet transform (SWT) is used to find efficient translation-invariant approximation of EMG noise. This is accomplished in the form of reference signal extracted as an estimation of the signal quality vs. EMG noise. The reference signal is built and then normalized after considering different heart rates and rhythms which increases its robustness and reliability to give accurate results regardless of input signal rhythm. Additionally, four applications of the extracted reference signal are suggested in this paper. For evaluation purposes both real EMG and artificial noises were used. The tested ECG signals are from MIT-BIH Arrhythmia Database Directory. The correlation coefficient between the added noise and the reference signal were computed for moving windows over the signal. Finally, the correlation between beats detection and reference signal was computed and presented. Reference signal gave high correlation with false positive values. Most false positives caused by EMG noise occur in intervals of greater amplitude reference signal and vice versa.