EEG Signal denoising using hybrid approach of Variational Mode Decomposition and wavelets for depression

Background: Artifact contamination reduces the accuracy of various EEG based neuroengineering applications. With time, biomedical signal denoising has been the utmost protuberant research area. So, the noise-reducing algorithm should be carefully deployed since artifacts result in degraded performance. Motivation: Artifact reduction or denoising in degraded EEG signals requires a lot of improvement. The main aim of this paper is to present the investigation carried out to suppress the noise found in EEG signals of depression. Method: The focus is to compare the effectiveness of the physiological signal denoising approaches based on discrete wavelet transform (DWT) and wavelet packet transform (WPT) combined with VMD (variational mode decomposition), namely VMD-DWT and VMD-WPT, with other approaches. In these approaches, the detrended fluctuation analysis (DFA) will be used to define the mode selection criteria. First of all, VMD will decompose the signal into various components, then DWT and WPT will be used to denoise the artifactual components rather than completely rejecting these with DFA as the mode selection basis. Simulations have been carried out on artificially contaminated and real databases of depression to demonstrate the effectiveness of the proposed technique using the performance parameters such as SNR, PSNR, and MSE. Contribution: It can be said that sufficient removal of artifacts is gained by VMD- DFA-WPT and VMD-DFA-DWT though VMD-DFA-WPT outperforms VMD- DFA-DWT and others. Such an artifact removal system may offer an effective solution for clinicians as a crucial stage of pre-processing and may prevent delay in diagnosis for depression signals.

Automated summary

This study compares the effectiveness of physiological signal denoising methods based on DWT and WPT combined with VMD in removing artifact contamination in EEG signals of depression. The results show that VMD-DFA-WPT is the optimal approach, making a significant contribution to denoising research in the neuroengineering field.