Presentation 2021-01-22
On decoding left-right movement intention of single arm from EEG
Mitsuhiko Inaba, Kazushi Ikeda, Motoaki Kawanabe,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Brain-machine interface (BMI) is a technology that supports people by manipulating external devices using only changes in brain activity. In non-invasive BMI research, mental states that are inconsistent with intended behaviors such as mental calculation are used for determining manipulation commands in order to achieve high accuracy. This dissociation between mental states and intended behaviors is an obstacle in practical BMI applications. In the present study, we conducted an experiment to investigate the difference in brain activity when imagining moving right (dominant) arm to the left or right towards more natural BMIs. By nested cross-validation for selecting features and optimizing parameters, we showed that the average classification accuracy of 6 subjects was 62%, and thus we can significantly discriminate left-right movement imagination of the same arm. Furthermore, we investigated the results by using SHAP values and time-frequency maps to discuss their possible physiological interpretations.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) BMI / EEG / motor imagery / movement decoding of the same arm / SHAP value
Paper # NC2020-35
Date of Issue 2021-01-14 (NC)

Conference Information
Committee NC / NLP
Conference Date 2021/1/21(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Online
Topics (in Japanese) (See Japanese page)
Topics (in English) NC,NLP
Chair Kazuyuki Samejima(Tamagawa Univ) / Kiyohisa Natsume(Kyushu Inst. of Tech.)
Vice Chair Rieko Osu(Waseda Univ.) / Takuji Kosaka(Chukyo Univ.)
Secretary Rieko Osu(NTT) / Takuji Kosaka(ATR)
Assistant Ken Takiyama(TUAT) / Nobuhiko Wagatsuma(Toho Univ.) / Toshikaza Samura(Yamaguchi Univ.) / Hideyuki Kato(Oita Univ.)

Paper Information
Registration To Technical Committee on Neurocomputing / Technical Committee on Nonlinear Problems
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) On decoding left-right movement intention of single arm from EEG
Sub Title (in English)
Keyword(1) BMI
Keyword(2) EEG
Keyword(3) motor imagery
Keyword(4) movement decoding of the same arm
Keyword(5) SHAP value
1st Author's Name Mitsuhiko Inaba
1st Author's Affiliation Nara Institute of Science and Technology(NAIST)
2nd Author's Name Kazushi Ikeda
2nd Author's Affiliation Nara Institute of Science and Technology(NAIST)
3rd Author's Name Motoaki Kawanabe
3rd Author's Affiliation Advanced Telecommunications Research Institute International(ATR)
Date 2021-01-22
Paper # NC2020-35
Volume (vol) vol.120
Number (no) NC-331
Page pp.pp.18-23(NC),
#Pages 6
Date of Issue 2021-01-14 (NC)