Presentation 2006-12-05
Classification of cognitive state from EEG spectrum measured during different mental tasks
Hideaki TAKAI, Kenta UCHIO, Michiteru KITAZAKI, Shigeki NAKAUCHI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This study aims to classify cognitive states by support vector machines (SVM) from EEG spectrum. Spontaneous brain waves were measured from a scalp of subjects with electrocap who opened their eyes, closed their eyes and performed a mental calculation task. Training data for SVMs consists of spectrum calculated from data selected by applying a sliding time window on the measured EEG. Classification accuracy for open/close states exceeds 90%, for close-eyes/mental calculation task was over 80%, suggesting that EEG spectrum can be used for accurate estimation of cognitive states by SVMs.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) EEG / Brain-Machine Interface / Support Vector Machine / Time-frequency Analysis
Paper # NC2006-75
Date of Issue

Conference Information
Committee NC
Conference Date 2006/11/28(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 Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Classification of cognitive state from EEG spectrum measured during different mental tasks
Sub Title (in English)
Keyword(1) EEG
Keyword(2) Brain-Machine Interface
Keyword(3) Support Vector Machine
Keyword(4) Time-frequency Analysis
1st Author's Name Hideaki TAKAI
1st Author's Affiliation Toyohashi University of Technology()
2nd Author's Name Kenta UCHIO
2nd Author's Affiliation Toyohashi University of Technology
3rd Author's Name Michiteru KITAZAKI
3rd Author's Affiliation Toyohashi University of Technology
4th Author's Name Shigeki NAKAUCHI
4th Author's Affiliation Toyohashi University of Technology
Date 2006-12-05
Paper # NC2006-75
Volume (vol) vol.106
Number (no) 407
Page pp.pp.-
#Pages 6
Date of Issue