Sub-band selection approach to artifact suppression from electroencephalography signal using hybrid wavelet transform

Sujan Ali,Khademul Islam Molla,Ekramul Hamid,Jannatul Ferdous

doi:10.1177/1729881421992269

Abstract

This article presents a hybrid wavelet-based algorithm to suppress the ocular artifacts from electroencephalography (EEG) signals. The hybrid wavelet transform (HWT) method is designed by the combination of discrete wavelet decomposition and wavelet packet transform. The artifact suppression is performed by the selection of sub-bands obtained by HWT. Fractional Gaussian noise (fGn) is used as the reference signal to select the sub-bands containing the artifacts. The multichannel EEG signal is decomposed HWT into a finite set of sub-bands. The energies of the sub-bands are compared to that of the fGn to the desired sub-band signals. The EEG signal is reconstructed by the selected sub-bands consisting of EEG. The experiments are conducted for both simulated and real EEG signals to study the performance of the proposed algorithm. The results are compared with recently developed algorithms of artifact suppression. It is found that the proposed method performs better than the methods compared in terms of performance metrics and computational cost.

Highlights

The electroencephalography (EEG) signals recorded from the scalp surface are usually contaminated by different physiological signals which are termed as artifacts
brain–computer interfaces (BCIs) experiment is conducted to test the cleaning performance followed by the BMI classification with EEG signal
Artifact suppression is essential for neurorobotics classification

Summary

Introduction

The electroencephalography (EEG) signals recorded from the scalp surface are usually contaminated by different physiological signals which are termed as artifacts. Electrooculography (EOG) makes a serious obstacle to many neuroscience experiments including the application for brain–computer interfaces (BCIs).[1] It has noticeable higher energy at a lower frequency compared to target EEG signals. The most popular blind source separation (BSS) technique of independent component analysis (ICA) is commonly employed to remove EOG artifacts. A number of research[2,3,4] have turned to ICA aiming to project the recorded raw EEG data into statistically independent components. It is not always guaranteed that the extracted

Methods

Results

Conclusion