Effective user training for motor imagery based brain computer interface with object-directed 3D visual display

Shuang Liang; Kup Sze Choi; Jing Qin; Wai Man Pang; Pheng Ann Heng

doi:10.1109/BMEI.2014.7002788

Effective user training for motor imagery based brain computer interface with object-directed 3D visual display

Shuang Liang, Kup Sze Choi, Jing Qin, Wai Man Pang, Pheng Ann Heng

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

5 Citations (Scopus)

Abstract

Effective user training could help us to improve the discrimination performance of our intention in brain computer interface (BCI). This paper aims to differentiate users left or right hand motor imagery (MI) tasks with different scenarios in 3D virtual environment, as non-object-directed (NOD) scenario, static-object-directed (SOD) scenario and dynamic-object-directed (DOD) scenario respectively. The results have significant differences by applying these three scenarios. Both SOD and DOD scenarios provide better classification accuracy, shorten single-trial period, and need smaller training samples comparing with the NOD case. We conclude that improving visual display may facilitate learning to use a BCI. Further comparing these results between single-subject and multiple-subject paradigm of BCI, we verify better classification performance could also be achieved by the multiple-subject paradigm. We believe these findings have the potential to improve discrimination performance of users intention for EEG-based BCI applications.

Original language	English
Title of host publication	Proceedings - 2014 7th International Conference on BioMedical Engineering and Informatics, BMEI 2014
Publisher	IEEE
Pages	297-301
Number of pages	5
ISBN (Electronic)	9781479958382
DOIs	https://doi.org/10.1109/BMEI.2014.7002788
Publication status	Published - 1 Jan 2014
Event	2014 7th International Conference on BioMedical Engineering and Informatics, BMEI 2014 - Bayshore Hotel, Dalian, China Duration: 14 Oct 2014 → 16 Oct 2014

Conference

Conference	2014 7th International Conference on BioMedical Engineering and Informatics, BMEI 2014
Country/Territory	China
City	Dalian
Period	14/10/14 → 16/10/14

Keywords

Brain computer interface (BCI)
Electroencephalogram (EEG)
Motor imagery
Multiple-subject paradigm
Single-subject paradigm
User training
Visual display

ASJC Scopus subject areas

Signal Processing
Health Information Management
Information Systems
Biomedical Engineering
Health Informatics

More information

10.1109/BMEI.2014.7002788

Cite this

@inproceedings{1208ad8c4c1940edabb88bf0771592ea,

title = "Effective user training for motor imagery based brain computer interface with object-directed 3D visual display",

abstract = "Effective user training could help us to improve the discrimination performance of our intention in brain computer interface (BCI). This paper aims to differentiate users left or right hand motor imagery (MI) tasks with different scenarios in 3D virtual environment, as non-object-directed (NOD) scenario, static-object-directed (SOD) scenario and dynamic-object-directed (DOD) scenario respectively. The results have significant differences by applying these three scenarios. Both SOD and DOD scenarios provide better classification accuracy, shorten single-trial period, and need smaller training samples comparing with the NOD case. We conclude that improving visual display may facilitate learning to use a BCI. Further comparing these results between single-subject and multiple-subject paradigm of BCI, we verify better classification performance could also be achieved by the multiple-subject paradigm. We believe these findings have the potential to improve discrimination performance of users intention for EEG-based BCI applications.",

keywords = "Brain computer interface (BCI), Electroencephalogram (EEG), Motor imagery, Multiple-subject paradigm, Single-subject paradigm, User training, Visual display",

author = "Shuang Liang and Choi, {Kup Sze} and Jing Qin and Pang, {Wai Man} and Heng, {Pheng Ann}",

year = "2014",

month = jan,

day = "1",

doi = "10.1109/BMEI.2014.7002788",

language = "English",

pages = "297--301",

booktitle = "Proceedings - 2014 7th International Conference on BioMedical Engineering and Informatics, BMEI 2014",

publisher = "IEEE",

address = "United States",

note = "2014 7th International Conference on BioMedical Engineering and Informatics, BMEI 2014 ; Conference date: 14-10-2014 Through 16-10-2014",

}

Liang, S, Choi, KS, Qin, J, Pang, WM & Heng, PA 2014, Effective user training for motor imagery based brain computer interface with object-directed 3D visual display. in Proceedings - 2014 7th International Conference on BioMedical Engineering and Informatics, BMEI 2014., 7002788, IEEE, pp. 297-301, 2014 7th International Conference on BioMedical Engineering and Informatics, BMEI 2014, Dalian, China, 14/10/14. https://doi.org/10.1109/BMEI.2014.7002788

Effective user training for motor imagery based brain computer interface with object-directed 3D visual display. / Liang, Shuang; Choi, Kup Sze; Qin, Jing et al.
Proceedings - 2014 7th International Conference on BioMedical Engineering and Informatics, BMEI 2014. IEEE, 2014. p. 297-301 7002788.

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

TY - GEN

T1 - Effective user training for motor imagery based brain computer interface with object-directed 3D visual display

AU - Liang, Shuang

AU - Choi, Kup Sze

AU - Qin, Jing

AU - Pang, Wai Man

AU - Heng, Pheng Ann

PY - 2014/1/1

Y1 - 2014/1/1

N2 - Effective user training could help us to improve the discrimination performance of our intention in brain computer interface (BCI). This paper aims to differentiate users left or right hand motor imagery (MI) tasks with different scenarios in 3D virtual environment, as non-object-directed (NOD) scenario, static-object-directed (SOD) scenario and dynamic-object-directed (DOD) scenario respectively. The results have significant differences by applying these three scenarios. Both SOD and DOD scenarios provide better classification accuracy, shorten single-trial period, and need smaller training samples comparing with the NOD case. We conclude that improving visual display may facilitate learning to use a BCI. Further comparing these results between single-subject and multiple-subject paradigm of BCI, we verify better classification performance could also be achieved by the multiple-subject paradigm. We believe these findings have the potential to improve discrimination performance of users intention for EEG-based BCI applications.

AB - Effective user training could help us to improve the discrimination performance of our intention in brain computer interface (BCI). This paper aims to differentiate users left or right hand motor imagery (MI) tasks with different scenarios in 3D virtual environment, as non-object-directed (NOD) scenario, static-object-directed (SOD) scenario and dynamic-object-directed (DOD) scenario respectively. The results have significant differences by applying these three scenarios. Both SOD and DOD scenarios provide better classification accuracy, shorten single-trial period, and need smaller training samples comparing with the NOD case. We conclude that improving visual display may facilitate learning to use a BCI. Further comparing these results between single-subject and multiple-subject paradigm of BCI, we verify better classification performance could also be achieved by the multiple-subject paradigm. We believe these findings have the potential to improve discrimination performance of users intention for EEG-based BCI applications.

KW - Brain computer interface (BCI)

KW - Electroencephalogram (EEG)

KW - Motor imagery

KW - Multiple-subject paradigm

KW - Single-subject paradigm

KW - User training

KW - Visual display

UR - http://www.scopus.com/inward/record.url?scp=84942514614&partnerID=8YFLogxK

U2 - 10.1109/BMEI.2014.7002788

DO - 10.1109/BMEI.2014.7002788

M3 - Conference article published in proceeding or book

SP - 297

EP - 301

BT - Proceedings - 2014 7th International Conference on BioMedical Engineering and Informatics, BMEI 2014

PB - IEEE

T2 - 2014 7th International Conference on BioMedical Engineering and Informatics, BMEI 2014

Y2 - 14 October 2014 through 16 October 2014

ER -

Effective user training for motor imagery based brain computer interface with object-directed 3D visual display

Abstract

Conference

Keywords

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this