Title: Optimised denoising scheme via opposition-based self-adaptive learning PSO algorithm for wavelet-based ECG signal noise reduction
Authors: Vinu Sundararaj
Addresses: Anna University, Sri Krishna College of Engineering & Technology, Coimbatore, India
Abstract: Electrocardiogram (ECG) signal is significant to diagnose cardiac arrhythmia among various biological signals. The accurate analysis of noisy electrocardiographic (ECG) signal is a very motivating challenge. According to this automated analysis, the noises present in electrocardiogram signal need to be removed for perfect diagnosis. Numerous investigators have been reported different techniques for denoising the electrocardiographic signal in recent years. In this paper, an efficient scheme for denoising electrocardiogram (ECG) signals is proposed based on a wavelet-based threshold mechanism. This scheme is based on an opposition-based self-adaptive learning particle swarm optimisation (OSLPSO) in dual tree complex wavelet packet scheme, in which the OSLPSO is utilised to for threshold optimisation. Different abnormal and normal electrocardiographic signals are tested to evaluate this approach from MIT/BIH arrhythmia database, by artificially adding white Gaussian noises with variation of 5 dB, 10 dB and 15 dB. Simulation results illustrate that the proposed system has good performance in various noise level and obtains better visual quality compared with other methods.
Keywords: electrocardiogram; denoising; self-adaptive learning; opposition learning; particle swarm optimisation; MIT/BIH arrhythmia; thresholding; DTCWPT.
International Journal of Biomedical Engineering and Technology, 2019 Vol.31 No.4, pp.325 - 345
Received: 12 Dec 2016
Accepted: 23 Mar 2017
Published online: 23 Oct 2019 *