Understanding the nonlinear behavior of EEG with advanced machine learning in artifact elimination

Md Samiul Haque Sunny; Shifat Hossain; Nashrah Afroze; Md Kamrul Hasan; Eklas Hossain; Mohammad H Rahman

doi:10.1088/2057-1976/ac3f17

Understanding the nonlinear behavior of EEG with advanced machine learning in artifact elimination

Biomed Phys Eng Express. 2021 Dec 9;8(1). doi: 10.1088/2057-1976/ac3f17.

Authors

Md Samiul Haque Sunny¹, Shifat Hossain², Nashrah Afroze³, Md Kamrul Hasan³, Eklas Hossain⁴, Mohammad H Rahman⁵

Affiliations

¹ Department of Computer Science, University of Wisconsin-Milwaukee, WI 53211-3029, United States of America.
² Department of Electronics Engineering, Kookmin University, Seoul, Republic of Korea.
³ Department of Electrical and Electronic Engineering, Khulna University of Engineering and Technology, Khulna-9203, Bangladesh.
⁴ Department of Electrical Engineering and Renewable Energy, Oregon Institute of Technology, Klamath Falls, OR-97601, United States of America.
⁵ Mechanical Engineering Department, University of Wisconsin-Milwaukee, WI 53211-3029, United States of America.

PMID: 34852330
DOI: 10.1088/2057-1976/ac3f17

Abstract

Steady-state Visually Evoked Potential (SSVEP) based Electroencephalogram (EEG) signal is utilized in brain-computer interface paradigms, diagnosis of brain diseases, and measurement of the cognitive status of the human brain. However, various artifacts such as the Electrocardiogram (ECG), Electrooculogram (EOG), and Electromyogram (EMG) are present in the raw EEG signal, which adversely affect the EEG-based appliances. In this research, Adaptive Neuro-fuzzy Interface Systems (ANFIS) and Hilbert-Huang Transform (HHT) are primarily employed to remove the artifacts from EEG signals. This work proposes Adaptive Noise Cancellation (ANC) and ANFIS based methods for canceling EEG artifacts. A mathematical model of EEG with the aforementioned artifacts is determined to accomplish the research goal, and then those artifacts are eliminated based on their mathematical characteristics. ANC, ANFIS, and HHT algorithms are simulated on the MATLAB platform, and their performances are also justified by various error estimation criteria using hardware implementation.

Keywords: EEG artifacts; Hilbert-Huang transform; adaptive neuro-fuzzy interface systems; artifact’s removal; electroencephalogram.

MeSH terms

Artifacts*
Brain-Computer Interfaces*
Electroencephalography / methods
Humans
Machine Learning
Signal Processing, Computer-Assisted