A novel method of motor imagery classification using eeg signal

Venkatachalam K; Devipriya A; Maniraj J; Sivaram M; Ambikapathy A; S Amiri Iraj

doi:10.1016/j.artmed.2019.101787

A novel method of motor imagery classification using eeg signal

Artif Intell Med. 2020 Mar:103:101787. doi: 10.1016/j.artmed.2019.101787. Epub 2019 Dec 31.

Authors

Venkatachalam K¹, Devipriya A², Maniraj J³, Sivaram M⁴, Ambikapathy A⁵, S Amiri Iraj⁶

Affiliations

¹ School of CSE, VIT Bhopal University, Bhopal, India. Electronic address: venkatme83@gmail.com.
² Department of IT, Sri Krishna College of Engineering and Technology, Coimbatore, India. Electronic address: itdevipriya@gmail.com.
³ Department of Mechanical Engineering, KIT, Coimbatore, India. Electronic address: maniraj_j@rediffmail.com.
⁴ Department of Computer Networking, Lebanese French University, Erbil, Kurdistan Region, Iraq. Electronic address: sivaram.murugan@lfu.edu.krd.
⁵ Department of EEE, Galgotias College of Engineering and Technology, Greater Noida, India. Electronic address: ami_ty21@yahoo.com.
⁶ Computational Optics Research Group, Advanced Institute of Materials Science, Ton Duc Thang University, Ho Chi Minh City, Viet Nam; Faculty of Applied Sciences, Ton Duc Thang University, Ho Chi Minh City, Viet Nam. Electronic address: irajsadeghamiri@tdtu.edu.vn.

PMID: 32143794
DOI: 10.1016/j.artmed.2019.101787

Abstract

A subject of extensive research interest in the Brain Computer Interfaces (BCIs) niche is motor imagery (MI), where users imagine limb movements to control the system. This interest is owed to the immense potential for its applicability in gaming, neuro-prosthetics and neuro-rehabilitation, where the user's thoughts of imagined movements need to be decoded. Electroencephalography (EEG) equipment is commonly used for keeping track of cerebrum movement in BCI systems. The EEG signals are recognized by feature extraction and classification. The current research proposes a Hybrid-KELM (Kernel Extreme Learning Machine) method based on PCA (Principal Component Analysis) and FLD (Fisher's Linear Discriminant) for MI BCI classification of EEG data. The performance and results of the method are demonstrated using BCI competition dataset III, and compared with those of contemporary methods. The proposed method generated an accuracy of 96.54%.

Keywords: BCI; ELM; Electroencephalogram; Fisher’s linear discriminant; Principal component analysis.

MeSH terms

Brain-Computer Interfaces*
Electroencephalography / methods*
Humans
Imagination
Machine Learning*
Principal Component Analysis
Signal Processing, Computer-Assisted*