Presentation 2016-06-17
Linear and non-linear classification of electroencephalographic activity during hand motor tasks
Sota Ikegami, Yasunari Hashimoto,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The purpose of this study is searchingan appropriate classifier for motor-related cortical activity-based BMI for strolling in the 3-D virtual environment. To obtain this goal, we compared linear discriminant analysis (LDA) and quadratic discriminant analysis (QDA) for electroencephalogram (EEG) classification. Eight healthy volunteers participated the BMI training controlling their own avatar in a virtual reality. We acquired the EEG signals during repeating hand extension in both pre- and post-training conditions. To check the EEG pattern changes, we employed time-frequency analysis. In our results, the binary classification accuracies were 89.4% in LDA and 84.4% in QDA, respectively. This results suggests that LDA is a better method for the BMI system.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) EEG / brain-machine-interface / virtual reality / classification
Paper # MBE2016-10
Date of Issue 2016-06-10 (MBE)

Conference Information
Committee MBE
Conference Date 2016/6/17(1days)
Place (in Japanese) (See Japanese page)
Place (in English) Hokkaido University
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Yutaka Fukuoka(Kogakuin Univ.)
Vice Chair Kazuki Nakajima(Univ. of Toyama)
Secretary Kazuki Nakajima(Kogakuin Univ.)
Assistant Ryota Horie(Shibaura Inst. of Tech.) / Kim Juhyon(Univ. of Toyama)

Paper Information
Registration To Technical Committee on ME and Bio Cybernetics
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Linear and non-linear classification of electroencephalographic activity during hand motor tasks
Sub Title (in English)
Keyword(1) EEG
Keyword(2) brain-machine-interface
Keyword(3) virtual reality
Keyword(4) classification
1st Author's Name Sota Ikegami
1st Author's Affiliation Kitami Institute of Technology(Kitami Inst. of Tech)
2nd Author's Name Yasunari Hashimoto
2nd Author's Affiliation Kitami Institute of Technology(Kitami Inst. of Tech)
Date 2016-06-17
Paper # MBE2016-10
Volume (vol) vol.116
Number (no) MBE-104
Page pp.pp.5-10(MBE),
#Pages 6
Date of Issue 2016-06-10 (MBE)