Fetal phonocardiogram signals denoising using improved complete ensemble (EMD) with adaptive noise and optimal thresholding of wavelet coefficients

Abstract

Although fetal phonocardiogram (fPCG) signals have become a good indicator for discovered heart disease, they may be contaminated by various noises that reduce the signals quality and the final diagnosis decision. Moreover, the noise may cause the risk of the data to misunderstand the heart signal and to misinterpret it. The main objective of this paper is to effectively remove noise from the fPCG signal to make it clinically feasible. So, we proposed a novel noise reduction method based on Improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (ICEEMDAN), wavelet threshold and Crow Search Algorithm (CSA). This noise reduction method, named ICEEMDAN-DWT-CSA, has three major advantages. They were, (i) A better suppress of mode mixing and a minimized number of IMFs, (ii) A choice of wavelet corresponding to the study signal proven by the literature and (iii) Selection of the optimal threshold value. Firstly, the noisy fPCG signal is decomposed into Intrinsic Mode Functions (IMFs) by the (ICEEMDAN). Each noisy IMFs were decomposed by the Discrete Wavelet Transform (DWT). Then, the optimal threshold value using the (CSA) technique is selected and the thresholding function is carried out in the detail’s coefficients. Secondly, each denoised (IMFs) is reconstructed by applying the Inverse Discrete Wavelet Transform (IDWT). Finally, all these denoised (IMFs) are combined to get the denoised fPCG signal. The performance of the proposed method has been evaluated by Signal to Noise Ratio (SNR), Mean Square Error (MSE) and the Correlation Coefficient (COR). The experiment gave a better result than some standard methods.

Augmented detection of septal defects using advanced optical coherence tomography network-processed phonocardiogram

“…Prior to denoising the phonocardiogram, the segmentation process facilitated the removal of irrelevant noise and emphasized the fundamental heart sounds (S1 and S2). An adaptive, non-linear mid-threshold estimation method for wavelet-based denoising of phonocardiograms has been proposed to efficiently suppress various types of noises ( 29 , 30 ) and would be useful to implement in future studies. In addition to denoising, quick and accurate assessment of heart sounds can be achieved via wavelet transforms.…”

Partial discharge de-noising based on hybrid particle swarm optimization SWT adaptive threshold

“…From Equation (10), the threshold function with the second derivative is needed to apply adaptive iteration, based on the steepest descent method and the commonly used soft threshold function and hard threshold function of higher order cannot guide, unable to adaptive iteration, only to estimate of threshold value, is not optimal for the objective function based on the type of Sigmoid function as a threshold function [22]. The function is second order derivable, and when the wavelet coefficient is larger than the threshold value, the wavelet coefficient processed by the function has a high similarity with the wavelet coefficient obtained by the standard soft threshold method.…”

“…Empirical Mode decomposition (EMD) and its improved algorithms, such as ensemble EMD(EEMD), Complementary Ensemble EMD(CEEMD), etc, are very suitable for the decomposition of non-stationary and nonlinear signals, and have been widely used in signal denoising [9,10]. Tang et al [11] used EMD to decompose PD signals into several IMFs, then de-noised the noisy IMFs through ICA, and finally obtained de-noised signals by reconstructed the denoised IMFs .…”