TY - GEN
T1 - Selection of motor imageries for brain-computer interfaces based on partial kullback-leibler information measure
AU - Shibanoki, Taro
AU - Koizumi, Yuki
AU - Yozan, Bi Adriel
AU - Tsuji, Toshio
N1 - Funding Information:
ACKNOWLEDGMENT This work was partially supported by a Grant-in-Aid for Scientific Research from the Japan Society for the Promotion of Science for Young Scientists B (17K12723).
Publisher Copyright:
© 2018 IEEE.
PY - 2018/12/10
Y1 - 2018/12/10
N2 - This paper proposes a selection method of motor imageries for brain-computer interfaces based on partial Kullback-Leibler information measure. In this method, partial KL information is defined as ratio of before:after class elimination and can be obtained by a KL information-based probabilistic neural network training. Therefore, optimal classes can be selected by eliminating ineffective ones one at a time along with network training. In the experiments performed, various motor imageries were learned by the reduced-dimensional recurrent probabilistic neural network and quasi-optimal combinations were selected using the proposed method. The discrimination rates before and after selections were $\mathbf{19.57}\pm \mathbf{7.09}[\%]$ and $\mathbf{68.14}\pm \mathbf{21.70} [\%]$, respectively.
AB - This paper proposes a selection method of motor imageries for brain-computer interfaces based on partial Kullback-Leibler information measure. In this method, partial KL information is defined as ratio of before:after class elimination and can be obtained by a KL information-based probabilistic neural network training. Therefore, optimal classes can be selected by eliminating ineffective ones one at a time along with network training. In the experiments performed, various motor imageries were learned by the reduced-dimensional recurrent probabilistic neural network and quasi-optimal combinations were selected using the proposed method. The discrimination rates before and after selections were $\mathbf{19.57}\pm \mathbf{7.09}[\%]$ and $\mathbf{68.14}\pm \mathbf{21.70} [\%]$, respectively.
KW - Brain Computer Interface
KW - Class Selection
KW - Electroencephalogram (EEG)
KW - Kullback-Leibler Divergence
KW - Motor Imagery
UR - http://www.scopus.com/inward/record.url?scp=85060229639&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85060229639&partnerID=8YFLogxK
U2 - 10.1109/LSC.2018.8572046
DO - 10.1109/LSC.2018.8572046
M3 - Conference contribution
AN - SCOPUS:85060229639
T3 - 2018 IEEE Life Sciences Conference, LSC 2018
SP - 243
EP - 246
BT - 2018 IEEE Life Sciences Conference, LSC 2018
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2018 IEEE Life Sciences Conference, LSC 2018
Y2 - 28 October 2018 through 30 October 2018
ER -