A Machine Learning-Based Big EEG Data Artifact Detection and Wavelet-Based Removal: An Empirical Approach

Shalini Stalin,Anurag Jain,Vandana Roy,Mohammad Monirujjaman Khan,Prashant Kumar Shukla,Atef Zaguia,Piyush Kumar Shukla,A M Bastos Pereira

doi:10.1155/2021/2942808

Abstract

The electroencephalogram (EEG) signals are a big data which are frequently corrupted by motion artifacts. As human neural diseases, diagnosis and analysis need a robust neurological signal. Consequently, the EEG artifacts’ eradication is a vital step. In this research paper, the primary motion artifact is detected from a single-channel EEG signal using support vector machine (SVM) and preceded with further artifacts’ suppression. The signal features’ abstraction and further detection are done through ensemble empirical mode decomposition (EEMD) algorithm. Moreover, canonical correlation analysis (CCA) filtering approach is applied for motion artifact removal. Finally, leftover motion artifacts’ unpredictability is removed by applying wavelet transform (WT) algorithm. Finally, results are optimized by using Harris hawks optimization (HHO) algorithm. The results of the assessment confirm that the algorithm recommended is superior to the algorithms currently in use.

Highlights

An effective diagnosis and analysis of neurological diseases are possible when a vital neurological signal is acquired from the patient
E analysis is based on artifacts’ removal and signal distortion. e quantitative evaluations of some important matrices are shown in Table 2. ese evaluations are done for synthesized EEG signals generated with different Signal-to-noise ratio (SNR)
The signal channel signal is decomposed by using ensemble empirical mode decomposition (EEMD) algorithm. ese decomposed EEGs (IMFs) have been applied to support vector machine (SVM) classifier for detection of artifacts from input EEG signal

Summary

Introduction

An effective diagnosis and analysis of neurological diseases are possible when a vital neurological signal is acquired from the patient. A more accurate artifact removal method is developed in this research work and applied to remove motion artifacts, as this artifact is the most recurrent and distressing component in the EEG data. This GT signal only is not capable to relate the effectiveness of the artifact elimination procedure. The most suitable and efficient algorithms are applied in this recommended work to mitigate these artifacts effectively In this recommended work, ensemble empirical mode decomposition (EEMD) [9], blind source separation (BSS) [13], and wavelet transform (WT) [16] are applied in cascade for effective elimination of these motion artifacts.

Recommended System Model

Experiments

Performance Assessment Factors

Methodology

Evaluation parameters DSNR Lambda

Conclusion