TY - GEN
T1 - Real-Time MEG-Based Brain-Geminoid Control Using Single-trial SVM Classification
AU - Belkacem, Abdelkader Nasreddine
AU - Ishiguro, Hiroshi
AU - Nishio, Shuichi
AU - Hirata, Masayuki
AU - Suzuki, Takafumi
N1 - Publisher Copyright:
© 2018 IEEE.
PY - 2019/1/11
Y1 - 2019/1/11
N2 - In this paper, we presents a novel non-invasive brain-Geminoid control system by using single-trial classification of bimanual movements to achieving a noninvasive brain-computer interface (BCI) with many control dimensions and easily interact with an outdoor complex environment in real-time. Two BCI-naive subjects performed or imagined performing 4 movements of bimanual hand during the measurement of magnetic fields to control a Geminoid HI-2 (humanoid robot) through a multidimensional BCI. We applied a nonlinear support vector machine (SVM) to classify the 4 bimanual hand movements using 114 magnetoencephalography (MEG) sensors over the sensorimotor cortex. The mean classification accuracy of a 2-class decoding was suitable for real-time brain-Geminoid control application, with classification accuracies equivalent to those obtained in precedent BCI studies involving uni-manual movements. Moreover, our results demonstrated that decoding bimanual hand movements in real-time using the amplitudes of the event-related magnetic fields is very promising to implement multidimensional-control based BCIs.
AB - In this paper, we presents a novel non-invasive brain-Geminoid control system by using single-trial classification of bimanual movements to achieving a noninvasive brain-computer interface (BCI) with many control dimensions and easily interact with an outdoor complex environment in real-time. Two BCI-naive subjects performed or imagined performing 4 movements of bimanual hand during the measurement of magnetic fields to control a Geminoid HI-2 (humanoid robot) through a multidimensional BCI. We applied a nonlinear support vector machine (SVM) to classify the 4 bimanual hand movements using 114 magnetoencephalography (MEG) sensors over the sensorimotor cortex. The mean classification accuracy of a 2-class decoding was suitable for real-time brain-Geminoid control application, with classification accuracies equivalent to those obtained in precedent BCI studies involving uni-manual movements. Moreover, our results demonstrated that decoding bimanual hand movements in real-time using the amplitudes of the event-related magnetic fields is very promising to implement multidimensional-control based BCIs.
KW - Bimanual hand movements
KW - Brain-computer interface (BCI)
KW - Geminoid HI-2
KW - Magnetoencephalographic (MEG)
KW - Support vector machine (SVM)
UR - http://www.scopus.com/inward/record.url?scp=85061511821&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85061511821&partnerID=8YFLogxK
U2 - 10.1109/ICARM.2018.8610776
DO - 10.1109/ICARM.2018.8610776
M3 - Conference contribution
AN - SCOPUS:85061511821
T3 - ICARM 2018 - 2018 3rd International Conference on Advanced Robotics and Mechatronics
SP - 679
EP - 684
BT - ICARM 2018 - 2018 3rd International Conference on Advanced Robotics and Mechatronics
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 3rd IEEE International Conference on Advanced Robotics and Mechatronics, ICARM 2018
Y2 - 18 July 2018 through 20 July 2018
ER -