Adaptive ECG denoising using genetic algorithm-based thresholding and ensemble empirical mode decomposition.

This paper proposes an adaptive denoising methodology for electrocardiogram (ECG) signals that employs ensemble empirical mode decomposition (EEMD) and a genetic algorithm (GA)-based thresholding technique. In this method, a noisy ECG signal is first decomposed by means of EEMD into a series of intrinsic mode functions (IMFs), which are then separated into signal- and noise-dominant groups using a similarity measure based on Kullback-Leibler divergence and a probability density function. A GA-based thresholding technique is then used adaptively to remove the noise inherent in noise-dominant IMFs. Finally, a denoised signal is reconstructed by combining the signal-dominant IMFs and the denoised noise-dominant IMFs. The performance of the proposed denoising methodology is evaluated in the present work by using the MIT-BIH arrhythmia ECG database, and results from the proposed method are compared with those of other conventional approaches in various noisy environments. Experimental results indicate that the proposed denoising method outperforms other denoising methodologies in terms of signal-to-noise ratio, mean square error, and percent root mean square difference. [ABSTRACT FROM AUTHOR]