Optimal-channel selection algorithms in mental tasks based brain-computer interface

Han Sun, Yu Zhang, Bruce Gluckman, Xuefei Zhong, Xiong Zhang

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

4 Citations (Scopus)

Abstract

Brain computer interface (BCI) for healthy people is a growing field. Minimizing the number of electroencephalography (EEG) channels is a key technological advantage for the application of BCI, which would make the system more mobile, easier to setup and long-time use in the real life. In this paper, to decrease the number of channels, multi-channel common spatial pattern (MCSP) algorithm is used to extract the features with two mental tasks (i.e., mental arithmetic and spatial imagery), and support vector machine (SVM) is used to classify the tasks performed. In detail, the separability value of each individual channel is computed based on between/within-group variance and a modified entropy criterion to evaluate its contribution to classification performance. The optimal channels are chosen based on the separability ranking. The performance of proposed methods is compared with recursive channel elimination and genetic algorithm. The results demonstrate that the EEG signals have different trends between the two mental tasks with highest brain activity in left central-parietal and parietal lobes, and the separability values allow reduction of number of electrodes from 15 to 4 and 10 while the classification accuracy reaches 80% and 90% respectively. Therefore, the optimal-channel algorithms can reduce the number of channels and improve the performance of the mental tasks based BCI.

Original languageEnglish (US)
Title of host publicationProceedings of the 2018 8th International Conference on Bioscience, Biochemistry and Bioinformatics, ICBBB 2018
PublisherAssociation for Computing Machinery
Pages118-123
Number of pages6
ISBN (Electronic)9781450353410
DOIs
StatePublished - Jan 18 2018
Event8th International Conference on Bioscience, Biochemistry and Bioinformatics, ICBBB 2018 - Tokyo, Japan
Duration: Jan 18 2018Jan 20 2018

Publication series

NameACM International Conference Proceeding Series

Other

Other8th International Conference on Bioscience, Biochemistry and Bioinformatics, ICBBB 2018
CountryJapan
CityTokyo
Period1/18/181/20/18

Fingerprint

Brain computer interface
Electroencephalography
Support vector machines
Brain
Entropy
Genetic algorithms
Electrodes

All Science Journal Classification (ASJC) codes

  • Software
  • Human-Computer Interaction
  • Computer Vision and Pattern Recognition
  • Computer Networks and Communications

Cite this

Sun, H., Zhang, Y., Gluckman, B., Zhong, X., & Zhang, X. (2018). Optimal-channel selection algorithms in mental tasks based brain-computer interface. In Proceedings of the 2018 8th International Conference on Bioscience, Biochemistry and Bioinformatics, ICBBB 2018 (pp. 118-123). (ACM International Conference Proceeding Series). Association for Computing Machinery. https://doi.org/10.1145/3180382.3180388
Sun, Han ; Zhang, Yu ; Gluckman, Bruce ; Zhong, Xuefei ; Zhang, Xiong. / Optimal-channel selection algorithms in mental tasks based brain-computer interface. Proceedings of the 2018 8th International Conference on Bioscience, Biochemistry and Bioinformatics, ICBBB 2018. Association for Computing Machinery, 2018. pp. 118-123 (ACM International Conference Proceeding Series).
@inproceedings{b139f115a7ed41558dfc27f9824c865c,
title = "Optimal-channel selection algorithms in mental tasks based brain-computer interface",
abstract = "Brain computer interface (BCI) for healthy people is a growing field. Minimizing the number of electroencephalography (EEG) channels is a key technological advantage for the application of BCI, which would make the system more mobile, easier to setup and long-time use in the real life. In this paper, to decrease the number of channels, multi-channel common spatial pattern (MCSP) algorithm is used to extract the features with two mental tasks (i.e., mental arithmetic and spatial imagery), and support vector machine (SVM) is used to classify the tasks performed. In detail, the separability value of each individual channel is computed based on between/within-group variance and a modified entropy criterion to evaluate its contribution to classification performance. The optimal channels are chosen based on the separability ranking. The performance of proposed methods is compared with recursive channel elimination and genetic algorithm. The results demonstrate that the EEG signals have different trends between the two mental tasks with highest brain activity in left central-parietal and parietal lobes, and the separability values allow reduction of number of electrodes from 15 to 4 and 10 while the classification accuracy reaches 80{\%} and 90{\%} respectively. Therefore, the optimal-channel algorithms can reduce the number of channels and improve the performance of the mental tasks based BCI.",
author = "Han Sun and Yu Zhang and Bruce Gluckman and Xuefei Zhong and Xiong Zhang",
year = "2018",
month = "1",
day = "18",
doi = "10.1145/3180382.3180388",
language = "English (US)",
series = "ACM International Conference Proceeding Series",
publisher = "Association for Computing Machinery",
pages = "118--123",
booktitle = "Proceedings of the 2018 8th International Conference on Bioscience, Biochemistry and Bioinformatics, ICBBB 2018",

}

Sun, H, Zhang, Y, Gluckman, B, Zhong, X & Zhang, X 2018, Optimal-channel selection algorithms in mental tasks based brain-computer interface. in Proceedings of the 2018 8th International Conference on Bioscience, Biochemistry and Bioinformatics, ICBBB 2018. ACM International Conference Proceeding Series, Association for Computing Machinery, pp. 118-123, 8th International Conference on Bioscience, Biochemistry and Bioinformatics, ICBBB 2018, Tokyo, Japan, 1/18/18. https://doi.org/10.1145/3180382.3180388

Optimal-channel selection algorithms in mental tasks based brain-computer interface. / Sun, Han; Zhang, Yu; Gluckman, Bruce; Zhong, Xuefei; Zhang, Xiong.

Proceedings of the 2018 8th International Conference on Bioscience, Biochemistry and Bioinformatics, ICBBB 2018. Association for Computing Machinery, 2018. p. 118-123 (ACM International Conference Proceeding Series).

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

TY - GEN

T1 - Optimal-channel selection algorithms in mental tasks based brain-computer interface

AU - Sun, Han

AU - Zhang, Yu

AU - Gluckman, Bruce

AU - Zhong, Xuefei

AU - Zhang, Xiong

PY - 2018/1/18

Y1 - 2018/1/18

N2 - Brain computer interface (BCI) for healthy people is a growing field. Minimizing the number of electroencephalography (EEG) channels is a key technological advantage for the application of BCI, which would make the system more mobile, easier to setup and long-time use in the real life. In this paper, to decrease the number of channels, multi-channel common spatial pattern (MCSP) algorithm is used to extract the features with two mental tasks (i.e., mental arithmetic and spatial imagery), and support vector machine (SVM) is used to classify the tasks performed. In detail, the separability value of each individual channel is computed based on between/within-group variance and a modified entropy criterion to evaluate its contribution to classification performance. The optimal channels are chosen based on the separability ranking. The performance of proposed methods is compared with recursive channel elimination and genetic algorithm. The results demonstrate that the EEG signals have different trends between the two mental tasks with highest brain activity in left central-parietal and parietal lobes, and the separability values allow reduction of number of electrodes from 15 to 4 and 10 while the classification accuracy reaches 80% and 90% respectively. Therefore, the optimal-channel algorithms can reduce the number of channels and improve the performance of the mental tasks based BCI.

AB - Brain computer interface (BCI) for healthy people is a growing field. Minimizing the number of electroencephalography (EEG) channels is a key technological advantage for the application of BCI, which would make the system more mobile, easier to setup and long-time use in the real life. In this paper, to decrease the number of channels, multi-channel common spatial pattern (MCSP) algorithm is used to extract the features with two mental tasks (i.e., mental arithmetic and spatial imagery), and support vector machine (SVM) is used to classify the tasks performed. In detail, the separability value of each individual channel is computed based on between/within-group variance and a modified entropy criterion to evaluate its contribution to classification performance. The optimal channels are chosen based on the separability ranking. The performance of proposed methods is compared with recursive channel elimination and genetic algorithm. The results demonstrate that the EEG signals have different trends between the two mental tasks with highest brain activity in left central-parietal and parietal lobes, and the separability values allow reduction of number of electrodes from 15 to 4 and 10 while the classification accuracy reaches 80% and 90% respectively. Therefore, the optimal-channel algorithms can reduce the number of channels and improve the performance of the mental tasks based BCI.

UR - http://www.scopus.com/inward/record.url?scp=85046817189&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85046817189&partnerID=8YFLogxK

U2 - 10.1145/3180382.3180388

DO - 10.1145/3180382.3180388

M3 - Conference contribution

AN - SCOPUS:85046817189

T3 - ACM International Conference Proceeding Series

SP - 118

EP - 123

BT - Proceedings of the 2018 8th International Conference on Bioscience, Biochemistry and Bioinformatics, ICBBB 2018

PB - Association for Computing Machinery

ER -

Sun H, Zhang Y, Gluckman B, Zhong X, Zhang X. Optimal-channel selection algorithms in mental tasks based brain-computer interface. In Proceedings of the 2018 8th International Conference on Bioscience, Biochemistry and Bioinformatics, ICBBB 2018. Association for Computing Machinery. 2018. p. 118-123. (ACM International Conference Proceeding Series). https://doi.org/10.1145/3180382.3180388