TY - GEN
T1 - Applying deep-learning to a top-down SSVEP BMI
AU - Ahn, Min Hee
AU - Min, Byoung-Kyong
N1 - Funding Information:
This work was supported by the Basic Science Research program (grant numbers 2015R1A1A1A05027233), the ICT R&D program of MSIP/Institute for Information & Communications Technology Promotion (IITP; grant number 2017-0-00432), and the Information Technology Research Center (ITRC) support program (grant number IITP-2017-2016-0-00464) supervised by the IITP, which are funded by the Korean government (MSIT) through the National Research Foundation of Korea. The authors declare that they have no competing interests.
Publisher Copyright:
© 2018 IEEE.
PY - 2018/3/9
Y1 - 2018/3/9
N2 - Brain-machine interfaces (BMIs) enable humans to control devices by modulating their brain signals. As the current BMI technology has several obstacles to overcome, additional sources of brain activity need to be explored. It seems plausible that the brain activity associated with top-down cognitive functions could open a new prospect in the field of BMIs. As top-down cognitive BMIs could exploit neural signals from more diverse networks, a deep-learning approach with complex hidden layers may provide a more optimal decoding performance. In this study, using our top-down steady-state visual evoked potential (SSVEP) paradigm (N = 20), we observed that the decoding accuracy (48.42%) of a deep-learning algorithm with a sigmoid activation function was significantly higher than that of regularized linear discriminant analysis (rLDA) with shrinkage (42.52%; t(19) =-3.183, p < 0.01), used in our previous study. Therefore, a deep-learning approach seems to be more optimized for classification in the top-down cognitive BMI paradigm.
AB - Brain-machine interfaces (BMIs) enable humans to control devices by modulating their brain signals. As the current BMI technology has several obstacles to overcome, additional sources of brain activity need to be explored. It seems plausible that the brain activity associated with top-down cognitive functions could open a new prospect in the field of BMIs. As top-down cognitive BMIs could exploit neural signals from more diverse networks, a deep-learning approach with complex hidden layers may provide a more optimal decoding performance. In this study, using our top-down steady-state visual evoked potential (SSVEP) paradigm (N = 20), we observed that the decoding accuracy (48.42%) of a deep-learning algorithm with a sigmoid activation function was significantly higher than that of regularized linear discriminant analysis (rLDA) with shrinkage (42.52%; t(19) =-3.183, p < 0.01), used in our previous study. Therefore, a deep-learning approach seems to be more optimized for classification in the top-down cognitive BMI paradigm.
KW - BMI
KW - DNN
KW - EEG
KW - SSVEP
KW - deep-learning
KW - top-down
UR - http://www.scopus.com/inward/record.url?scp=85050809368&partnerID=8YFLogxK
U2 - 10.1109/IWW-BCI.2018.8311526
DO - 10.1109/IWW-BCI.2018.8311526
M3 - Conference contribution
AN - SCOPUS:85050809368
T3 - 2018 6th International Conference on Brain-Computer Interface, BCI 2018
SP - 1
EP - 3
BT - 2018 6th International Conference on Brain-Computer Interface, BCI 2018
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 6th International Conference on Brain-Computer Interface, BCI 2018
Y2 - 15 January 2018 through 17 January 2018
ER -