TY - CONF
T1 - Towards a Brain-Computer Interface Based on Unsupervised Methods to Command a Lower-Limb Robotic Exoskeleton
AU - Delisle-Rodriguez, Denis
AU - Villa-Parra, Ana Cecilia
AU - Bastos, Teodiano
PY - 2019/1/16
Y1 - 2019/1/16
N2 - This work presents a brain-computer interface (BCI) based on unsupervised methods for conveying control commands to a robotic exoskeleton, in order to provide support to patients with severe motor disability during walking. For this purpose, an adaptive spatial filter based on similarity indices is proposed to preserve the useful information on electroencephalography (EEG) signals. Additionally, a method for feature selection based on the Maximal Information Compression Index (MICI), and the representation entropy (RE) is used, increasing its robustness for uncertain patterns, such as gait planning. Good values of accuracy (ACC > 75%) and false positive rate (FPR< 10%) were obtained for four subjects. Thus, this BCI based on unsupervised method may be suitable to recognize uncertainty pattern, such as gait planning.
AB - This work presents a brain-computer interface (BCI) based on unsupervised methods for conveying control commands to a robotic exoskeleton, in order to provide support to patients with severe motor disability during walking. For this purpose, an adaptive spatial filter based on similarity indices is proposed to preserve the useful information on electroencephalography (EEG) signals. Additionally, a method for feature selection based on the Maximal Information Compression Index (MICI), and the representation entropy (RE) is used, increasing its robustness for uncertain patterns, such as gait planning. Good values of accuracy (ACC > 75%) and false positive rate (FPR< 10%) were obtained for four subjects. Thus, this BCI based on unsupervised method may be suitable to recognize uncertainty pattern, such as gait planning.
KW - brain-computer interface
KW - feature selection
KW - gait intention
KW - gait planning
KW - spatial filter
UR - https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85062211097&origin=inward
UR - https://www.scopus.com/inward/citedby.uri?partnerID=HzOxMe3b&scp=85062211097&origin=inward
UR - http://www.mendeley.com/research/towards-braincomputer-interface-based-unsupervised-methods-command-lowerlimb-robotic-exoskeleton
U2 - 10.1109/SMC.2018.00194
DO - 10.1109/SMC.2018.00194
M3 - Paper
SP - 1099
EP - 1104
T2 - Proceedings - 2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018
Y2 - 16 January 2019
ER -