Effects of Task Complexity on Motor Imagery Based Brain-Computer Interface

M. Ebrahim M. Mashat; Chin-Teng Lin; Dingguo Zhang

doi:10.1109/TNSRE.2019.2936987

Effects of Task Complexity on Motor Imagery Based Brain-Computer Interface

M. Ebrahim M. Mashat, Chin-Teng Lin , Dingguo Zhang

Shanghai Jiao Tong University

Research output: Contribution to journal › Article › peer-review

26 Citations (SciVal)

Abstract

The performance of electroencephalogram (EEG)-based brain-computer interfaces (BCIs) still needs improvements for real world applications. An improvement on BCIs could be achieved by enhancing brain signals from the source via subject intention-based modulation. In this work, we aim to investigate the effects of task complexity on performance of motor imagery (MI) based BCIs. In specific, we studied the effects of motor imagery of a complex task versus a simple task on discriminability of brain activation patterns using EEG. The results show an increase of up to 7.25% in BCI classification accuracy for motor imagery of the complex task in comparison to the simple task. Furthermore, spectral power analysis in low frequency bands, alpha and beta, shows a significant decrease in power value for the complex task. However, high frequency gamma band analysis unveils a significant increase for the complex task. These findings may lead to designing better BCIs with high performance.

Original language	English
Article number	8809824
Pages (from-to)	2178-2185
Number of pages	8
Journal	IEEE Transactions on Neural Systems and Rehabilitation Engineering
Volume	27
Issue number	10
Early online date	22 Aug 2019
DOIs	https://doi.org/10.1109/TNSRE.2019.2936987
Publication status	Published - 1 Oct 2019

Bibliographical note

Funding Information:
28 10.1109/TNSRE.2019.2936987 0b0000648971db4e Active orig-research F T F F F F F Publish 10 IEEE 1534-4320 © 2019 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. See http://www.ieee.org/publications_standards/publications/rights/index.html for more information. The performance of electroencephalogram (EEG)-based brain-computer interfaces (BCIs) still needs improvements for real world applications. An improvement on BCIs could be achieved by enhancing brain signals from the source via subject intention-based modulation. In this work, we aim to investigate the effects of task complexity on performance of motor imagery (MI) based BCIs. In specific, we studied the effects of motor imagery of a complex task versus a simple task on discriminability of brain activation patterns using EEG. The results show an increase of up to 7.25% in BCI classification accuracy for motor imagery of the complex task in comparison to the simple task. Furthermore, spectral power analysis in low frequency bands, alpha and beta, shows a significant decrease in power value for the complex task. However, high frequency gamma band analysis unveils a significant increase for the complex task. These findings may lead to designing better BCIs with high performance. 0 Mashat, M.E.M. M. Ebrahim M. Mashat M. Ebrahim M. M. Ebrahim M. Mashat Mashat State Key Laboratory of Mechanical Systems and Vibration, School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai, China Author 0 0000-0001-8371-8197 Lin, C. Chin-Teng Lin Chin-Teng Chin-Teng Lin Lin Centre for Artificial Intelligence, CIBCI Lab, Faculty of Engineering and Information Technology, University of Technology Sydney, Ultimo, NSW, Australia Author 0 0000-0003-4803-7489 Zhang, D. Dingguo Zhang Dingguo Dingguo Zhang Zhang Department of Electronic and Electrical Engineering, University of Bath, Bath, U.K. Author [email protected] 2019 Oct. 2019 8 21 2019 10 14 2085566 08809824.pdf 2178-2185 8809824 Task analysis Electroencephalography Writing Visualization Complexity theory Magnetic resonance imaging Grasping Brain-computer interface electroencephalography task complexity motor imagery event-related de-synchronization classification accuracy National Natural Science Foundation of China 10.13039/501100001809 61761166006 91848112 Foundation of Shanghai Municipal Commission of Health and Family Planning 10.13039/501100010032 2017ZZ01006

Publisher Copyright:
© 2001-2011 IEEE.

Keywords

Brain-computer interface
classification accuracy
electroencephalography
event-related de-synchronization
motor imagery
task complexity

ASJC Scopus subject areas

Internal Medicine
General Neuroscience
Biomedical Engineering

Access to Document

10.1109/TNSRE.2019.2936987

Cite this

@article{cf8c0dd626084cc6802f47a9e03db0f3,

title = "Effects of Task Complexity on Motor Imagery Based Brain-Computer Interface",

abstract = "The performance of electroencephalogram (EEG)-based brain-computer interfaces (BCIs) still needs improvements for real world applications. An improvement on BCIs could be achieved by enhancing brain signals from the source via subject intention-based modulation. In this work, we aim to investigate the effects of task complexity on performance of motor imagery (MI) based BCIs. In specific, we studied the effects of motor imagery of a complex task versus a simple task on discriminability of brain activation patterns using EEG. The results show an increase of up to 7.25% in BCI classification accuracy for motor imagery of the complex task in comparison to the simple task. Furthermore, spectral power analysis in low frequency bands, alpha and beta, shows a significant decrease in power value for the complex task. However, high frequency gamma band analysis unveils a significant increase for the complex task. These findings may lead to designing better BCIs with high performance.",

keywords = "Brain-computer interface, classification accuracy, electroencephalography, event-related de-synchronization, motor imagery, task complexity",

author = "Mashat, {M. Ebrahim M.} and Chin-Teng Lin and Dingguo Zhang",

note = "Funding Information: 28 10.1109/TNSRE.2019.2936987 0b0000648971db4e Active orig-research F T F F F F F Publish 10 IEEE 1534-4320 {\textcopyright} 2019 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. See http://www.ieee.org/publications_standards/publications/rights/index.html for more information. The performance of electroencephalogram (EEG)-based brain-computer interfaces (BCIs) still needs improvements for real world applications. An improvement on BCIs could be achieved by enhancing brain signals from the source via subject intention-based modulation. In this work, we aim to investigate the effects of task complexity on performance of motor imagery (MI) based BCIs. In specific, we studied the effects of motor imagery of a complex task versus a simple task on discriminability of brain activation patterns using EEG. The results show an increase of up to 7.25% in BCI classification accuracy for motor imagery of the complex task in comparison to the simple task. Furthermore, spectral power analysis in low frequency bands, alpha and beta, shows a significant decrease in power value for the complex task. However, high frequency gamma band analysis unveils a significant increase for the complex task. These findings may lead to designing better BCIs with high performance. 0 Mashat, M.E.M. M. Ebrahim M. Mashat M. Ebrahim M. M. Ebrahim M. Mashat Mashat State Key Laboratory of Mechanical Systems and Vibration, School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai, China Author 0 0000-0001-8371-8197 Lin, C. Chin-Teng Lin Chin-Teng Chin-Teng Lin Lin Centre for Artificial Intelligence, CIBCI Lab, Faculty of Engineering and Information Technology, University of Technology Sydney, Ultimo, NSW, Australia Author 0 0000-0003-4803-7489 Zhang, D. Dingguo Zhang Dingguo Dingguo Zhang Zhang Department of Electronic and Electrical Engineering, University of Bath, Bath, U.K. Author [email protected] 2019 Oct. 2019 8 21 2019 10 14 2085566 08809824.pdf 2178-2185 8809824 Task analysis Electroencephalography Writing Visualization Complexity theory Magnetic resonance imaging Grasping Brain-computer interface electroencephalography task complexity motor imagery event-related de-synchronization classification accuracy National Natural Science Foundation of China 10.13039/501100001809 61761166006 91848112 Foundation of Shanghai Municipal Commission of Health and Family Planning 10.13039/501100010032 2017ZZ01006 Publisher Copyright: {\textcopyright} 2001-2011 IEEE.",

year = "2019",

month = oct,

day = "1",

doi = "10.1109/TNSRE.2019.2936987",

language = "English",

volume = "27",

pages = "2178--2185",

journal = "IEEE Transactions on Neural Systems and Rehabilitation Engineering",

issn = "1534-4320",

publisher = "IEEE",

number = "10",

}

TY - JOUR

T1 - Effects of Task Complexity on Motor Imagery Based Brain-Computer Interface

AU - Mashat, M. Ebrahim M.

AU - Lin , Chin-Teng

AU - Zhang, Dingguo

N1 - Funding Information: 28 10.1109/TNSRE.2019.2936987 0b0000648971db4e Active orig-research F T F F F F F Publish 10 IEEE 1534-4320 © 2019 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. See http://www.ieee.org/publications_standards/publications/rights/index.html for more information. The performance of electroencephalogram (EEG)-based brain-computer interfaces (BCIs) still needs improvements for real world applications. An improvement on BCIs could be achieved by enhancing brain signals from the source via subject intention-based modulation. In this work, we aim to investigate the effects of task complexity on performance of motor imagery (MI) based BCIs. In specific, we studied the effects of motor imagery of a complex task versus a simple task on discriminability of brain activation patterns using EEG. The results show an increase of up to 7.25% in BCI classification accuracy for motor imagery of the complex task in comparison to the simple task. Furthermore, spectral power analysis in low frequency bands, alpha and beta, shows a significant decrease in power value for the complex task. However, high frequency gamma band analysis unveils a significant increase for the complex task. These findings may lead to designing better BCIs with high performance. 0 Mashat, M.E.M. M. Ebrahim M. Mashat M. Ebrahim M. M. Ebrahim M. Mashat Mashat State Key Laboratory of Mechanical Systems and Vibration, School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai, China Author 0 0000-0001-8371-8197 Lin, C. Chin-Teng Lin Chin-Teng Chin-Teng Lin Lin Centre for Artificial Intelligence, CIBCI Lab, Faculty of Engineering and Information Technology, University of Technology Sydney, Ultimo, NSW, Australia Author 0 0000-0003-4803-7489 Zhang, D. Dingguo Zhang Dingguo Dingguo Zhang Zhang Department of Electronic and Electrical Engineering, University of Bath, Bath, U.K. Author [email protected] 2019 Oct. 2019 8 21 2019 10 14 2085566 08809824.pdf 2178-2185 8809824 Task analysis Electroencephalography Writing Visualization Complexity theory Magnetic resonance imaging Grasping Brain-computer interface electroencephalography task complexity motor imagery event-related de-synchronization classification accuracy National Natural Science Foundation of China 10.13039/501100001809 61761166006 91848112 Foundation of Shanghai Municipal Commission of Health and Family Planning 10.13039/501100010032 2017ZZ01006 Publisher Copyright: © 2001-2011 IEEE.

PY - 2019/10/1

Y1 - 2019/10/1

N2 - The performance of electroencephalogram (EEG)-based brain-computer interfaces (BCIs) still needs improvements for real world applications. An improvement on BCIs could be achieved by enhancing brain signals from the source via subject intention-based modulation. In this work, we aim to investigate the effects of task complexity on performance of motor imagery (MI) based BCIs. In specific, we studied the effects of motor imagery of a complex task versus a simple task on discriminability of brain activation patterns using EEG. The results show an increase of up to 7.25% in BCI classification accuracy for motor imagery of the complex task in comparison to the simple task. Furthermore, spectral power analysis in low frequency bands, alpha and beta, shows a significant decrease in power value for the complex task. However, high frequency gamma band analysis unveils a significant increase for the complex task. These findings may lead to designing better BCIs with high performance.

AB - The performance of electroencephalogram (EEG)-based brain-computer interfaces (BCIs) still needs improvements for real world applications. An improvement on BCIs could be achieved by enhancing brain signals from the source via subject intention-based modulation. In this work, we aim to investigate the effects of task complexity on performance of motor imagery (MI) based BCIs. In specific, we studied the effects of motor imagery of a complex task versus a simple task on discriminability of brain activation patterns using EEG. The results show an increase of up to 7.25% in BCI classification accuracy for motor imagery of the complex task in comparison to the simple task. Furthermore, spectral power analysis in low frequency bands, alpha and beta, shows a significant decrease in power value for the complex task. However, high frequency gamma band analysis unveils a significant increase for the complex task. These findings may lead to designing better BCIs with high performance.

KW - Brain-computer interface

KW - classification accuracy

KW - electroencephalography

KW - event-related de-synchronization

KW - motor imagery

KW - task complexity

UR - http://www.scopus.com/inward/record.url?scp=85073664385&partnerID=8YFLogxK

U2 - 10.1109/TNSRE.2019.2936987

DO - 10.1109/TNSRE.2019.2936987

M3 - Article

SN - 1534-4320

VL - 27

SP - 2178

EP - 2185

JO - IEEE Transactions on Neural Systems and Rehabilitation Engineering

JF - IEEE Transactions on Neural Systems and Rehabilitation Engineering

IS - 10

M1 - 8809824

ER -

Effects of Task Complexity on Motor Imagery Based Brain-Computer Interface

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this