Customized linear discriminant analysis for brain-computer interfaces

N. S. Dias, M. Kamrunnahar, P. M. Mendes, S. J. Schiff, J. H. Correia

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

5 Citations (Scopus)

Abstract

This study presents a procedure to customize mental task discrimination for a specific human subject. Three male subjects, between 20 and 30 years old, were submitted to 4-5 sessions. Each session was composed of 4 blocks of 20 trials. Two block types were implemented. One required that the subject perform feet and tongue movements. The other block required the subject to perform left and right arm movements. Subjects were instructed to perform motor imagery as well as actual movements. In order to avoid previous assumptions on preferable channel locations and frequency ranges, 105 (21 electrodesx5 frequency ranges) electroencephalogram (EEG) features were extracted from the sessions' data. A linear discriminant analysis (LDA) approach was applied to the feature set. The dimensionality of the multivariate data set was reduced through a discriminant stepwise procedure. Only the variables which best discriminated between groups, for a specific subject, were used. Those features predicted group membership during online feedback sessions with error lower than 12%, in each subject best performance. Classification errors for training data were very low and were neglected.

Original languageEnglish (US)
Title of host publicationProceedings of the 3rd International IEEE EMBS Conference on Neural Engineering
Pages430-433
Number of pages4
DOIs
StatePublished - Sep 25 2007
Event3rd International IEEE EMBS Conference on Neural Engineering - Kohala Coast, HI, United States
Duration: May 2 2007May 5 2007

Publication series

NameProceedings of the 3rd International IEEE EMBS Conference on Neural Engineering

Other

Other3rd International IEEE EMBS Conference on Neural Engineering
CountryUnited States
CityKohala Coast, HI
Period5/2/075/5/07

Fingerprint

Brain-Computer Interfaces
Brain computer interface
Discriminant Analysis
Discriminant analysis
Imagery (Psychotherapy)
Electroencephalography
Tongue
Foot
Arm
Feedback
Datasets

All Science Journal Classification (ASJC) codes

  • Biotechnology
  • Bioengineering
  • Neuroscience (miscellaneous)

Cite this

Dias, N. S., Kamrunnahar, M., Mendes, P. M., Schiff, S. J., & Correia, J. H. (2007). Customized linear discriminant analysis for brain-computer interfaces. In Proceedings of the 3rd International IEEE EMBS Conference on Neural Engineering (pp. 430-433). [4227306] (Proceedings of the 3rd International IEEE EMBS Conference on Neural Engineering). https://doi.org/10.1109/CNE.2007.369701
Dias, N. S. ; Kamrunnahar, M. ; Mendes, P. M. ; Schiff, S. J. ; Correia, J. H. / Customized linear discriminant analysis for brain-computer interfaces. Proceedings of the 3rd International IEEE EMBS Conference on Neural Engineering. 2007. pp. 430-433 (Proceedings of the 3rd International IEEE EMBS Conference on Neural Engineering).
@inproceedings{8b8b851577184eadb82718bc25ed1d03,
title = "Customized linear discriminant analysis for brain-computer interfaces",
abstract = "This study presents a procedure to customize mental task discrimination for a specific human subject. Three male subjects, between 20 and 30 years old, were submitted to 4-5 sessions. Each session was composed of 4 blocks of 20 trials. Two block types were implemented. One required that the subject perform feet and tongue movements. The other block required the subject to perform left and right arm movements. Subjects were instructed to perform motor imagery as well as actual movements. In order to avoid previous assumptions on preferable channel locations and frequency ranges, 105 (21 electrodesx5 frequency ranges) electroencephalogram (EEG) features were extracted from the sessions' data. A linear discriminant analysis (LDA) approach was applied to the feature set. The dimensionality of the multivariate data set was reduced through a discriminant stepwise procedure. Only the variables which best discriminated between groups, for a specific subject, were used. Those features predicted group membership during online feedback sessions with error lower than 12{\%}, in each subject best performance. Classification errors for training data were very low and were neglected.",
author = "Dias, {N. S.} and M. Kamrunnahar and Mendes, {P. M.} and Schiff, {S. J.} and Correia, {J. H.}",
year = "2007",
month = "9",
day = "25",
doi = "10.1109/CNE.2007.369701",
language = "English (US)",
isbn = "1424407923",
series = "Proceedings of the 3rd International IEEE EMBS Conference on Neural Engineering",
pages = "430--433",
booktitle = "Proceedings of the 3rd International IEEE EMBS Conference on Neural Engineering",

}

Dias, NS, Kamrunnahar, M, Mendes, PM, Schiff, SJ & Correia, JH 2007, Customized linear discriminant analysis for brain-computer interfaces. in Proceedings of the 3rd International IEEE EMBS Conference on Neural Engineering., 4227306, Proceedings of the 3rd International IEEE EMBS Conference on Neural Engineering, pp. 430-433, 3rd International IEEE EMBS Conference on Neural Engineering, Kohala Coast, HI, United States, 5/2/07. https://doi.org/10.1109/CNE.2007.369701

Customized linear discriminant analysis for brain-computer interfaces. / Dias, N. S.; Kamrunnahar, M.; Mendes, P. M.; Schiff, S. J.; Correia, J. H.

Proceedings of the 3rd International IEEE EMBS Conference on Neural Engineering. 2007. p. 430-433 4227306 (Proceedings of the 3rd International IEEE EMBS Conference on Neural Engineering).

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

TY - GEN

T1 - Customized linear discriminant analysis for brain-computer interfaces

AU - Dias, N. S.

AU - Kamrunnahar, M.

AU - Mendes, P. M.

AU - Schiff, S. J.

AU - Correia, J. H.

PY - 2007/9/25

Y1 - 2007/9/25

N2 - This study presents a procedure to customize mental task discrimination for a specific human subject. Three male subjects, between 20 and 30 years old, were submitted to 4-5 sessions. Each session was composed of 4 blocks of 20 trials. Two block types were implemented. One required that the subject perform feet and tongue movements. The other block required the subject to perform left and right arm movements. Subjects were instructed to perform motor imagery as well as actual movements. In order to avoid previous assumptions on preferable channel locations and frequency ranges, 105 (21 electrodesx5 frequency ranges) electroencephalogram (EEG) features were extracted from the sessions' data. A linear discriminant analysis (LDA) approach was applied to the feature set. The dimensionality of the multivariate data set was reduced through a discriminant stepwise procedure. Only the variables which best discriminated between groups, for a specific subject, were used. Those features predicted group membership during online feedback sessions with error lower than 12%, in each subject best performance. Classification errors for training data were very low and were neglected.

AB - This study presents a procedure to customize mental task discrimination for a specific human subject. Three male subjects, between 20 and 30 years old, were submitted to 4-5 sessions. Each session was composed of 4 blocks of 20 trials. Two block types were implemented. One required that the subject perform feet and tongue movements. The other block required the subject to perform left and right arm movements. Subjects were instructed to perform motor imagery as well as actual movements. In order to avoid previous assumptions on preferable channel locations and frequency ranges, 105 (21 electrodesx5 frequency ranges) electroencephalogram (EEG) features were extracted from the sessions' data. A linear discriminant analysis (LDA) approach was applied to the feature set. The dimensionality of the multivariate data set was reduced through a discriminant stepwise procedure. Only the variables which best discriminated between groups, for a specific subject, were used. Those features predicted group membership during online feedback sessions with error lower than 12%, in each subject best performance. Classification errors for training data were very low and were neglected.

UR - http://www.scopus.com/inward/record.url?scp=34548805472&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34548805472&partnerID=8YFLogxK

U2 - 10.1109/CNE.2007.369701

DO - 10.1109/CNE.2007.369701

M3 - Conference contribution

AN - SCOPUS:34548805472

SN - 1424407923

SN - 9781424407927

T3 - Proceedings of the 3rd International IEEE EMBS Conference on Neural Engineering

SP - 430

EP - 433

BT - Proceedings of the 3rd International IEEE EMBS Conference on Neural Engineering

ER -

Dias NS, Kamrunnahar M, Mendes PM, Schiff SJ, Correia JH. Customized linear discriminant analysis for brain-computer interfaces. In Proceedings of the 3rd International IEEE EMBS Conference on Neural Engineering. 2007. p. 430-433. 4227306. (Proceedings of the 3rd International IEEE EMBS Conference on Neural Engineering). https://doi.org/10.1109/CNE.2007.369701