Novel BCI classification method using cross-channel-region CSP features

Yongkoo Park, Wonzoo Chung

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

12 Citations (Scopus)

Abstract

In this paper, we explore locally generated cross-channel-region CSP features to improve motor imagery classification in EEG-based BCIs. We set several clustered sub-channel regions covering the entire measured channels and extract CSP features by cross-combining the sub-channel regions with each single channel. The features generated by this cross-channel-region combinations have regional information on sensor space for motor imagery and can be used to improve classification accuracy when fed to LS-SVM classifier. The performance improvement of the proposed algorithm is verified by simulations.

Original languageEnglish
Title of host publication2018 6th International Conference on Brain-Computer Interface, BCI 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1-4
Number of pages4
ISBN (Electronic)9781538625743
DOIs
Publication statusPublished - 2018 Mar 9
Event6th International Conference on Brain-Computer Interface, BCI 2018 - GangWon, Korea, Republic of
Duration: 2018 Jan 152018 Jan 17

Publication series

Name2018 6th International Conference on Brain-Computer Interface, BCI 2018
Volume2018-January

Other

Other6th International Conference on Brain-Computer Interface, BCI 2018
Country/TerritoryKorea, Republic of
CityGangWon
Period18/1/1518/1/17

Keywords

  • Brain-Computer Interfaces (BCIs)
  • Common Spatial Pattern (CSP)
  • cross-channel-region combinations
  • electroencephalography (EEG)

ASJC Scopus subject areas

  • Artificial Intelligence
  • Human-Computer Interaction
  • Behavioral Neuroscience

Fingerprint

Dive into the research topics of 'Novel BCI classification method using cross-channel-region CSP features'. Together they form a unique fingerprint.

Cite this