ECG Signal Denoising Based on Wavelet Transform and Genetic Algorithm

Abstract

ECG signal analysis is crucial for diagnosing heart abnormalities. The presence of noise can alter the ECG signal’s fundamental features. At the time of signal acquisition, Power Line Interference noise (PLI) strongly affects the ECG signal. In this paper, we propose an ECG signal denoising method based on a combination of Genetic Algorithm (GA) and Wavelet Transformation (WT) by putting the WT through a series of successive iterations in the search space in order to obtain the optimal decomposition level and the threshold value. The performance of our proposed method is tested and validated through a series of experiments on the widely known MIT-BIH database using an objective evaluation based on the Signal-to-Noise Ratio (SNR) and the Percentage Root mean square Difference (PRD). The results showed our method’s effectiveness in reducing the Power Line Interference noise and making the ECG signal less noisy and more suitable for further medical applications. For instance, at an input SNR of10 dB, we obtained an output SNR of 22.56 dB and a PRD of 7.46%.