EEG-based discrimination of elbow/shoulder torques using brain computer interface algorithms

Implications for rehabilitation

J. Zhou*, Jun Yao, Jie Deng, Julius P A Dewald

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

10 Citations (Scopus)

Abstract

Brain computer interface (BCI) algorithms are used to predict the torque generation in the direction of shoulder abduction or elbow flexion using scalp EEG signals from 163 electrodes. Based on features extracted from both frequency and time domains, three classifiers are employed including support vector classifier, classification trees and K nearest neighbor. Support vector classifier achieves the highest recognition rate of 92.9% on two able-bodied subjects in average. The recognition rates we obtained on the able-bodied subjects are among the highest compared with previous reports on predicting motor intent using scalp EEG. This demonstrates the feasibility of separating the shoulder/elbow torques using scalp EEG as well as the potential of support vector classifier in applications of BCI. Preliminary experiments on two hemiparetic stroke subjects using support vector classifier reports an accuracy of 84.1% in average, which shows an increased difficulty in predicting intent presumably due to cortical reorganization resulting from the stroke.

Original languageEnglish (US)
Title of host publicationProceedings of the 2005 27th Annual International Conference of the Engineering in Medicine and Biology Society, IEEE-EMBS 2005
Pages4134-4137
Number of pages4
Volume7 VOLS
StatePublished - Dec 1 2005
Event2005 27th Annual International Conference of the Engineering in Medicine and Biology Society, IEEE-EMBS 2005 - Shanghai, China
Duration: Sep 1 2005Sep 4 2005

Other

Other2005 27th Annual International Conference of the Engineering in Medicine and Biology Society, IEEE-EMBS 2005
CountryChina
CityShanghai
Period9/1/059/4/05

Fingerprint

Brain-Computer Interfaces
Brain computer interface
Torque
Elbow
Electroencephalography
Scalp
Patient rehabilitation
Classifiers
Rehabilitation
Stroke
Electrodes
Bioelectric potentials
Experiments

Keywords

  • BCI
  • EEG
  • Elbow flexion
  • Shoulder abduction
  • Support vector classifier

ASJC Scopus subject areas

  • Signal Processing
  • Biomedical Engineering
  • Computer Vision and Pattern Recognition
  • Health Informatics

Cite this

Zhou, J., Yao, J., Deng, J., & Dewald, J. P. A. (2005). EEG-based discrimination of elbow/shoulder torques using brain computer interface algorithms: Implications for rehabilitation. In Proceedings of the 2005 27th Annual International Conference of the Engineering in Medicine and Biology Society, IEEE-EMBS 2005 (Vol. 7 VOLS, pp. 4134-4137). [1615373]
Zhou, J. ; Yao, Jun ; Deng, Jie ; Dewald, Julius P A. / EEG-based discrimination of elbow/shoulder torques using brain computer interface algorithms : Implications for rehabilitation. Proceedings of the 2005 27th Annual International Conference of the Engineering in Medicine and Biology Society, IEEE-EMBS 2005. Vol. 7 VOLS 2005. pp. 4134-4137
@inproceedings{68faa35c38ed4e19b8bb8f8735ad51dd,
title = "EEG-based discrimination of elbow/shoulder torques using brain computer interface algorithms: Implications for rehabilitation",
abstract = "Brain computer interface (BCI) algorithms are used to predict the torque generation in the direction of shoulder abduction or elbow flexion using scalp EEG signals from 163 electrodes. Based on features extracted from both frequency and time domains, three classifiers are employed including support vector classifier, classification trees and K nearest neighbor. Support vector classifier achieves the highest recognition rate of 92.9{\%} on two able-bodied subjects in average. The recognition rates we obtained on the able-bodied subjects are among the highest compared with previous reports on predicting motor intent using scalp EEG. This demonstrates the feasibility of separating the shoulder/elbow torques using scalp EEG as well as the potential of support vector classifier in applications of BCI. Preliminary experiments on two hemiparetic stroke subjects using support vector classifier reports an accuracy of 84.1{\%} in average, which shows an increased difficulty in predicting intent presumably due to cortical reorganization resulting from the stroke.",
keywords = "BCI, EEG, Elbow flexion, Shoulder abduction, Support vector classifier",
author = "J. Zhou and Jun Yao and Jie Deng and Dewald, {Julius P A}",
year = "2005",
month = "12",
day = "1",
language = "English (US)",
isbn = "0780387406",
volume = "7 VOLS",
pages = "4134--4137",
booktitle = "Proceedings of the 2005 27th Annual International Conference of the Engineering in Medicine and Biology Society, IEEE-EMBS 2005",

}

Zhou, J, Yao, J, Deng, J & Dewald, JPA 2005, EEG-based discrimination of elbow/shoulder torques using brain computer interface algorithms: Implications for rehabilitation. in Proceedings of the 2005 27th Annual International Conference of the Engineering in Medicine and Biology Society, IEEE-EMBS 2005. vol. 7 VOLS, 1615373, pp. 4134-4137, 2005 27th Annual International Conference of the Engineering in Medicine and Biology Society, IEEE-EMBS 2005, Shanghai, China, 9/1/05.

EEG-based discrimination of elbow/shoulder torques using brain computer interface algorithms : Implications for rehabilitation. / Zhou, J.; Yao, Jun; Deng, Jie; Dewald, Julius P A.

Proceedings of the 2005 27th Annual International Conference of the Engineering in Medicine and Biology Society, IEEE-EMBS 2005. Vol. 7 VOLS 2005. p. 4134-4137 1615373.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - EEG-based discrimination of elbow/shoulder torques using brain computer interface algorithms

T2 - Implications for rehabilitation

AU - Zhou, J.

AU - Yao, Jun

AU - Deng, Jie

AU - Dewald, Julius P A

PY - 2005/12/1

Y1 - 2005/12/1

N2 - Brain computer interface (BCI) algorithms are used to predict the torque generation in the direction of shoulder abduction or elbow flexion using scalp EEG signals from 163 electrodes. Based on features extracted from both frequency and time domains, three classifiers are employed including support vector classifier, classification trees and K nearest neighbor. Support vector classifier achieves the highest recognition rate of 92.9% on two able-bodied subjects in average. The recognition rates we obtained on the able-bodied subjects are among the highest compared with previous reports on predicting motor intent using scalp EEG. This demonstrates the feasibility of separating the shoulder/elbow torques using scalp EEG as well as the potential of support vector classifier in applications of BCI. Preliminary experiments on two hemiparetic stroke subjects using support vector classifier reports an accuracy of 84.1% in average, which shows an increased difficulty in predicting intent presumably due to cortical reorganization resulting from the stroke.

AB - Brain computer interface (BCI) algorithms are used to predict the torque generation in the direction of shoulder abduction or elbow flexion using scalp EEG signals from 163 electrodes. Based on features extracted from both frequency and time domains, three classifiers are employed including support vector classifier, classification trees and K nearest neighbor. Support vector classifier achieves the highest recognition rate of 92.9% on two able-bodied subjects in average. The recognition rates we obtained on the able-bodied subjects are among the highest compared with previous reports on predicting motor intent using scalp EEG. This demonstrates the feasibility of separating the shoulder/elbow torques using scalp EEG as well as the potential of support vector classifier in applications of BCI. Preliminary experiments on two hemiparetic stroke subjects using support vector classifier reports an accuracy of 84.1% in average, which shows an increased difficulty in predicting intent presumably due to cortical reorganization resulting from the stroke.

KW - BCI

KW - EEG

KW - Elbow flexion

KW - Shoulder abduction

KW - Support vector classifier

UR - http://www.scopus.com/inward/record.url?scp=33846914912&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33846914912&partnerID=8YFLogxK

M3 - Conference contribution

SN - 0780387406

SN - 9780780387409

VL - 7 VOLS

SP - 4134

EP - 4137

BT - Proceedings of the 2005 27th Annual International Conference of the Engineering in Medicine and Biology Society, IEEE-EMBS 2005

ER -

Zhou J, Yao J, Deng J, Dewald JPA. EEG-based discrimination of elbow/shoulder torques using brain computer interface algorithms: Implications for rehabilitation. In Proceedings of the 2005 27th Annual International Conference of the Engineering in Medicine and Biology Society, IEEE-EMBS 2005. Vol. 7 VOLS. 2005. p. 4134-4137. 1615373