Applying deep-learning to a top-down SSVEP BMI

Min Hee Ahn, Byoung-Kyong Min

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

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.

Original languageEnglish
Title of host publication2018 6th International Conference on Brain-Computer Interface, BCI 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1-3
Number of pages3
Volume2018-January
ISBN (Electronic)9781538625743
DOIs
Publication statusPublished - 2018 Mar 9
Event6th International Conference on Brain-Computer Interface, BCI 2018 - GangWon, Korea, Republic of
Duration: 2018 Jan 152018 Jan 17

Other

Other6th International Conference on Brain-Computer Interface, BCI 2018
CountryKorea, Republic of
CityGangWon
Period18/1/1518/1/17

Fingerprint

Brain-Computer Interfaces
Visual Evoked Potentials
Bioelectric potentials
Brain
Learning
Decoding
Discriminant Analysis
Sigmoid Colon
Cognition
Deep learning
Technology
Discriminant analysis
Equipment and Supplies
Learning algorithms
Chemical activation

Keywords

  • BMI
  • deep-learning
  • DNN
  • EEG
  • SSVEP
  • top-down

ASJC Scopus subject areas

  • Artificial Intelligence
  • Human-Computer Interaction
  • Behavioral Neuroscience

Cite this

Ahn, M. H., & Min, B-K. (2018). Applying deep-learning to a top-down SSVEP BMI. In 2018 6th International Conference on Brain-Computer Interface, BCI 2018 (Vol. 2018-January, pp. 1-3). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IWW-BCI.2018.8311526

Applying deep-learning to a top-down SSVEP BMI. / Ahn, Min Hee; Min, Byoung-Kyong.

2018 6th International Conference on Brain-Computer Interface, BCI 2018. Vol. 2018-January Institute of Electrical and Electronics Engineers Inc., 2018. p. 1-3.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Ahn, MH & Min, B-K 2018, Applying deep-learning to a top-down SSVEP BMI. in 2018 6th International Conference on Brain-Computer Interface, BCI 2018. vol. 2018-January, Institute of Electrical and Electronics Engineers Inc., pp. 1-3, 6th International Conference on Brain-Computer Interface, BCI 2018, GangWon, Korea, Republic of, 18/1/15. https://doi.org/10.1109/IWW-BCI.2018.8311526
Ahn MH, Min B-K. Applying deep-learning to a top-down SSVEP BMI. In 2018 6th International Conference on Brain-Computer Interface, BCI 2018. Vol. 2018-January. Institute of Electrical and Electronics Engineers Inc. 2018. p. 1-3 https://doi.org/10.1109/IWW-BCI.2018.8311526
Ahn, Min Hee ; Min, Byoung-Kyong. / Applying deep-learning to a top-down SSVEP BMI. 2018 6th International Conference on Brain-Computer Interface, BCI 2018. Vol. 2018-January Institute of Electrical and Electronics Engineers Inc., 2018. pp. 1-3
@inproceedings{011a6ae3ff8a44eb90123a40683e18d2,
title = "Applying deep-learning to a top-down SSVEP BMI",
abstract = "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.",
keywords = "BMI, deep-learning, DNN, EEG, SSVEP, top-down",
author = "Ahn, {Min Hee} and Byoung-Kyong Min",
year = "2018",
month = "3",
day = "9",
doi = "10.1109/IWW-BCI.2018.8311526",
language = "English",
volume = "2018-January",
pages = "1--3",
booktitle = "2018 6th International Conference on Brain-Computer Interface, BCI 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Applying deep-learning to a top-down SSVEP BMI

AU - Ahn, Min Hee

AU - Min, Byoung-Kyong

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 - deep-learning

KW - DNN

KW - EEG

KW - SSVEP

KW - top-down

UR - http://www.scopus.com/inward/record.url?scp=85050809368&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.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

VL - 2018-January

SP - 1

EP - 3

BT - 2018 6th International Conference on Brain-Computer Interface, BCI 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -