Comparison analysis between rigrsure, sqtwolog, heursure and minimaxi techniques using hard and soft thresholding methods

Nowadays, wavelet transform (WT) is widely used in the realm of signal denoising, has proven a high effectiveness in terms of time and quality concerning denoising methods. Despite there are several achievements denoising through wavelet thresholding methods, these do not disclose an optimal configuration. In this paper, we proposed a comparative performance analysis of several thresholding methods using WT; biological signals are denoised to obtain performance metrics. The efficiency of particular thresholding methods: rigrsure, sqtwolog, heursure and minimaxi using hard and soft thresholding are compared in the presence of low Gaussian noise also the effect of wavelet decomposition levels is analyzed. For wavelet decomposition, Haar wavelet is used. Experimental results show that by increasing decomposition levels likewise there was a denoising improvement in terms of root mean square error (RMSE) and correlation coefficient, however, from the fifth decomposition level RMSE and correlation coefficient slowly tends to get worse, also the threshold method rigrsure on soft thresholding improved RMSE of 1.77 to 1.03 and correlation coefficient of 99.32% to 99.71% while others techniques on both, soft and hard thresholding did not improve more than 1.1 in RMSE and 99.67% in correlation coefficient.