EEG artifact removal using sub-space decomposition, nonlinear dynamics, stationary wavelet transform and machine learning algorithms

Morteza Zangeneh Soroush; Parisa Tahvilian; Mohammad Hossein Nasirpour; Keivan Maghooli; Khosro Sadeghniiat-Haghighi; Sepide Vahid Harandi; Zeinab Abdollahi; Ali Ghazizadeh; Nader Jafarnia Dabanloo

doi:10.3389/fphys.2022.910368

EEG artifact removal using sub-space decomposition, nonlinear dynamics, stationary wavelet transform and machine learning algorithms

Front Physiol. 2022 Aug 24:13:910368. doi: 10.3389/fphys.2022.910368. eCollection 2022.

Authors

Morteza Zangeneh Soroush^{1

2

3

4

5

6}, Parisa Tahvilian^{4

5}, Mohammad Hossein Nasirpour⁷, Keivan Maghooli^{4

5}, Khosro Sadeghniiat-Haghighi^{1

8}, Sepide Vahid Harandi⁹, Zeinab Abdollahi¹⁰, Ali Ghazizadeh^{2

3}, Nader Jafarnia Dabanloo^{4

5}

Affiliations

¹ Occupational Sleep Research Center, Baharloo Hospital, Tehran University of Medical Sciences, Tehran, Iran.
² School of Cognitive Sciences, Institute for Research in Fundamental Sciences, IPM, Tehran, Iran.
³ Bio-Intelligence Research Unit, Electrical Engineering Department, Sharif University of Technology, Tehran, Iran.
⁴ Department of Biomedical Engineering, Science and Research Branch, Islamic Azad University, Tehran, Iran.
⁵ Engineering Research Center in Medicine and Biology, Science and Research Branch, Islamic Azad University, Tehran, Iran.
⁶ Department of Clinical Neuroscience, Mahdiyeh Clinic, Tehran, Iran.
⁷ Department of Medical Genetics, Institute of Medical Biotechnology, National Institute of Genetic Engineering and Biotechnology (NIGEB), Tehran, Iran.
⁸ Sleep Breathing Disorders Research Center, Tehran University of Medical Sciences, Tehran, Iran.
⁹ Department of Psychology, Islamic Azad University, Najafabad Branch, Najafabad, Iran.
¹⁰ Department of Electrical and Computer Engineering, Islamic Azad University, Qazvin Branch, Qazvin, Iran.

Abstract

Blind source separation (BSS) methods have received a great deal of attention in electroencephalogram (EEG) artifact elimination as they are routine and standard signal processing tools to remove artifacts and reserve desired neural information. On the other hand, a classifier should follow BSS methods to automatically identify artifactual sources and remove them in the following steps. In addition, removing all detected artifactual components leads to loss of information since some desired information related to neural activity leaks to these sources. So, an approach should be employed to detect and suppress the artifacts and reserve neural activity. This study introduces a novel method based on EEG and Poincare planes in the phase space to detect artifactual components estimated by second-order blind identification (SOBI). Artifacts are detected using a mixture of well-known conventional classifiers and were removed employing stationary wavelet transform (SWT) to reserve neural information. The proposed method is a combination of signal processing techniques and machine learning algorithms, including multi-layer perceptron (MLP), K-nearest neighbor (KNN), naïve Bayes, and support vector machine (SVM) which have significant results while applying our proposed method to different scenarios. Simulated, semi-simulated, and real EEG signals are employed to evaluate the proposed method, and several evaluation criteria are calculated. We achieved acceptable results, for example, 98% average accuracy and 97% average sensitivity in artifactual EEG component detection or about 2% as mean square error in EEG reconstruction after artifact removal. Results showed that the proposed method is effective and can be used in future studies as we have considered different real-world scenarios to evaluate it.

Keywords: EEG artifact removal; noise reduction; phase space reconstruction; source separation; stationary wavelet transform; subspace decomposition.