Comparative analysis of features extracted from EEG spatial, spectral and temporal domains for binary and multiclass motor imagery classification

Seung Bo Lee, Hyun Ji Kim, Hakseung Kim, Ji Hoon Jeong, Seong Whan Lee, Dong-Joo Kim

Research output: Contribution to journalArticle

Abstract

The electroencephalogram (EEG) remains the predominant source of neurophysiological signals for motor imagery-based brain-computer interfaces (MI-BCIs). Various features can be derived from three distinctive domains (i.e., spatial, temporal and spectral); however, the efficacies of the existing feature extraction methods when discriminating complex multiclass MI tasks have yet to be reported. This study investigates the performances of EEG feature extraction techniques from varying domains against different levels of complex, multiclass MI tasks. Ten healthy volunteers underwent multiple complex MI tasks via a robotic arm (i.e., hand grasping and wrist twisting; grasp, spread, pronation and supination). The discrimination performances of various feature extraction (i.e., common spatial patterns (CSP), time domain parameters (TDP), and power spectral density (PSD)) and classification methods for EEG were tested to perform binary (hand grasping/wrist twisting), ternary ((A) grasp/spread/wrist twisting and (B) hand grasping/pronation/supination) and quaternary (grasp/spread/pronation/supination) discrimination. Based on the available data, the combination of shrinkage-regularized linear discriminant analysis (SRLDA) and TDP achieved the highest accuracy. The findings suggest that multiclass complex MI-BCI task discrimination could gain more benefit from analyzing simple and symbolic features such as TDP rather than more complex features such as CSP and PSD.

Original languageEnglish
Pages (from-to)190-200
Number of pages11
JournalInformation Sciences
Volume502
DOIs
Publication statusPublished - 2019 Oct 1

Fingerprint

Multi-class
Electroencephalography
Comparative Analysis
Feature extraction
Brain computer interface
Power spectral density
Grasping
Binary
Feature Extraction
Discrimination
Time Domain
Power Spectral Density
Spatial Pattern
Robotic arms
Discriminant analysis
End effectors
Shrinkage
Discriminant Analysis
Ternary
Efficacy

Keywords

  • Brain-computer interface
  • Electroencephalogram
  • Feature extraction
  • Motor imagery
  • Multiclass discrimination

ASJC Scopus subject areas

  • Software
  • Control and Systems Engineering
  • Theoretical Computer Science
  • Computer Science Applications
  • Information Systems and Management
  • Artificial Intelligence

Cite this

Comparative analysis of features extracted from EEG spatial, spectral and temporal domains for binary and multiclass motor imagery classification. / Lee, Seung Bo; Kim, Hyun Ji; Kim, Hakseung; Jeong, Ji Hoon; Lee, Seong Whan; Kim, Dong-Joo.

In: Information Sciences, Vol. 502, 01.10.2019, p. 190-200.

Research output: Contribution to journalArticle

@article{4469805daa484cccbe6d60a36d441749,
title = "Comparative analysis of features extracted from EEG spatial, spectral and temporal domains for binary and multiclass motor imagery classification",
abstract = "The electroencephalogram (EEG) remains the predominant source of neurophysiological signals for motor imagery-based brain-computer interfaces (MI-BCIs). Various features can be derived from three distinctive domains (i.e., spatial, temporal and spectral); however, the efficacies of the existing feature extraction methods when discriminating complex multiclass MI tasks have yet to be reported. This study investigates the performances of EEG feature extraction techniques from varying domains against different levels of complex, multiclass MI tasks. Ten healthy volunteers underwent multiple complex MI tasks via a robotic arm (i.e., hand grasping and wrist twisting; grasp, spread, pronation and supination). The discrimination performances of various feature extraction (i.e., common spatial patterns (CSP), time domain parameters (TDP), and power spectral density (PSD)) and classification methods for EEG were tested to perform binary (hand grasping/wrist twisting), ternary ((A) grasp/spread/wrist twisting and (B) hand grasping/pronation/supination) and quaternary (grasp/spread/pronation/supination) discrimination. Based on the available data, the combination of shrinkage-regularized linear discriminant analysis (SRLDA) and TDP achieved the highest accuracy. The findings suggest that multiclass complex MI-BCI task discrimination could gain more benefit from analyzing simple and symbolic features such as TDP rather than more complex features such as CSP and PSD.",
keywords = "Brain-computer interface, Electroencephalogram, Feature extraction, Motor imagery, Multiclass discrimination",
author = "Lee, {Seung Bo} and Kim, {Hyun Ji} and Hakseung Kim and Jeong, {Ji Hoon} and Lee, {Seong Whan} and Dong-Joo Kim",
year = "2019",
month = "10",
day = "1",
doi = "10.1016/j.ins.2019.06.008",
language = "English",
volume = "502",
pages = "190--200",
journal = "Information Sciences",
issn = "0020-0255",
publisher = "Elsevier Inc.",

}

TY - JOUR

T1 - Comparative analysis of features extracted from EEG spatial, spectral and temporal domains for binary and multiclass motor imagery classification

AU - Lee, Seung Bo

AU - Kim, Hyun Ji

AU - Kim, Hakseung

AU - Jeong, Ji Hoon

AU - Lee, Seong Whan

AU - Kim, Dong-Joo

PY - 2019/10/1

Y1 - 2019/10/1

N2 - The electroencephalogram (EEG) remains the predominant source of neurophysiological signals for motor imagery-based brain-computer interfaces (MI-BCIs). Various features can be derived from three distinctive domains (i.e., spatial, temporal and spectral); however, the efficacies of the existing feature extraction methods when discriminating complex multiclass MI tasks have yet to be reported. This study investigates the performances of EEG feature extraction techniques from varying domains against different levels of complex, multiclass MI tasks. Ten healthy volunteers underwent multiple complex MI tasks via a robotic arm (i.e., hand grasping and wrist twisting; grasp, spread, pronation and supination). The discrimination performances of various feature extraction (i.e., common spatial patterns (CSP), time domain parameters (TDP), and power spectral density (PSD)) and classification methods for EEG were tested to perform binary (hand grasping/wrist twisting), ternary ((A) grasp/spread/wrist twisting and (B) hand grasping/pronation/supination) and quaternary (grasp/spread/pronation/supination) discrimination. Based on the available data, the combination of shrinkage-regularized linear discriminant analysis (SRLDA) and TDP achieved the highest accuracy. The findings suggest that multiclass complex MI-BCI task discrimination could gain more benefit from analyzing simple and symbolic features such as TDP rather than more complex features such as CSP and PSD.

AB - The electroencephalogram (EEG) remains the predominant source of neurophysiological signals for motor imagery-based brain-computer interfaces (MI-BCIs). Various features can be derived from three distinctive domains (i.e., spatial, temporal and spectral); however, the efficacies of the existing feature extraction methods when discriminating complex multiclass MI tasks have yet to be reported. This study investigates the performances of EEG feature extraction techniques from varying domains against different levels of complex, multiclass MI tasks. Ten healthy volunteers underwent multiple complex MI tasks via a robotic arm (i.e., hand grasping and wrist twisting; grasp, spread, pronation and supination). The discrimination performances of various feature extraction (i.e., common spatial patterns (CSP), time domain parameters (TDP), and power spectral density (PSD)) and classification methods for EEG were tested to perform binary (hand grasping/wrist twisting), ternary ((A) grasp/spread/wrist twisting and (B) hand grasping/pronation/supination) and quaternary (grasp/spread/pronation/supination) discrimination. Based on the available data, the combination of shrinkage-regularized linear discriminant analysis (SRLDA) and TDP achieved the highest accuracy. The findings suggest that multiclass complex MI-BCI task discrimination could gain more benefit from analyzing simple and symbolic features such as TDP rather than more complex features such as CSP and PSD.

KW - Brain-computer interface

KW - Electroencephalogram

KW - Feature extraction

KW - Motor imagery

KW - Multiclass discrimination

UR - http://www.scopus.com/inward/record.url?scp=85067252628&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85067252628&partnerID=8YFLogxK

U2 - 10.1016/j.ins.2019.06.008

DO - 10.1016/j.ins.2019.06.008

M3 - Article

AN - SCOPUS:85067252628

VL - 502

SP - 190

EP - 200

JO - Information Sciences

JF - Information Sciences

SN - 0020-0255

ER -