Presentation 2006-02-24
Datacleansing for EEG based Brain Computer Interface
Kenji TANAKA, Takio KURITA, Friedrich MEYER, Luc BERTHOUZE, Tohru KAWABE,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The potential of brain-computer interfaces (BCI) in serving a useful purpose, e.g., supporting communication to paralyzed patients. This paper proposes a method to construct a classifier with improved generalization performance. A feature selection method if applied to features calculated from the EEG signals so that unnecessary features for the classification task can be removed. Kernel support vector machines were used as a classifier and the best combinations of features were searched by backward stepwise selection and by evaluating the resulting generalization performance through cross validation. Experiments showed that the generalization performance of the classifier constructed from the best set of features was better.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Brain Computa Interface / EEG / Support Vector Machine / feature selection
Paper # TL2005-72,PRMU2005-207
Date of Issue

Conference Information
Committee TL
Conference Date 2006/2/17(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Thought and Language (TL)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Datacleansing for EEG based Brain Computer Interface
Sub Title (in English)
Keyword(1) Brain Computa Interface
Keyword(2) EEG
Keyword(3) Support Vector Machine
Keyword(4) feature selection
1st Author's Name Kenji TANAKA
1st Author's Affiliation Graduate School of System and Information Engineering, University of Tsukuba()
2nd Author's Name Takio KURITA
2nd Author's Affiliation Neuroscience Research Institute, National Institute of Advanced Industrial Science and Technology:Graduate School of System and Information Engineering, University of Tsukuba
3rd Author's Name Friedrich MEYER
3rd Author's Affiliation Neuroscience Research Institute, National Institute of Advanced Industrial Science and Technology (AIST)
4th Author's Name Luc BERTHOUZE
4th Author's Affiliation Neuroscience Research Institute, National Institute of Advanced Industrial Science and Technology (AIST)
5th Author's Name Tohru KAWABE
5th Author's Affiliation Graduate School of System and Information Engineering, University of Tsukuba
Date 2006-02-24
Paper # TL2005-72,PRMU2005-207
Volume (vol) vol.105
Number (no) 613
Page pp.pp.-
#Pages 6
Date of Issue