Semi-Supervised Deep Adversarial Learning for Brain-Computer Interface

Wonjun Ko, Eunjin Jeon, Jiyeon Lee, Heung-Il Suk

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

Abstract

Recent advances in deep learning have made a progressive impact on BCI researches. In particular, convolutional neural networks (CNNs) with different architectural forms have been studied for spatio-Temporal or spatio-spectral feature representation learning. However, there still remain many challenges and limitations due to the necessity of a large annotated training samples for robustness. In this paper, we propose a semi-supervised deep adversarial learning framework that effectively utilizes generated artificial samples along with labeled and unlabelled real samples in discovering class-discriminative features to boost robustness of a classifier, thus to enhance BCI performance. It is also noteworthy that the proposed framework allows to exploit unlabelled real samples to better uncover the underlying patterns inherent in a user's EEG signals. In order to justify the validity of the proposed framework, we conducted exhaustive experiments with 'Recurrent Spatio-Temporal Neural Network' CNN architectures over the public BCI Competition IV-IIa dataset. From our experiments, we could observe statistically significant improvements on performance, compared to the competing methods with the conventional framework. We have also visualized learned convolutional weights in terms of activation pattern maps, separability of extracted features, and validity of generated artificial samples.

Original languageEnglish
Title of host publication7th International Winter Conference on Brain-Computer Interface, BCI 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781538681169
DOIs
Publication statusPublished - 2019 Feb 1
Event7th International Winter Conference on Brain-Computer Interface, BCI 2019 - Gangwon, Korea, Republic of
Duration: 2019 Feb 182019 Feb 20

Publication series

Name7th International Winter Conference on Brain-Computer Interface, BCI 2019

Conference

Conference7th International Winter Conference on Brain-Computer Interface, BCI 2019
CountryKorea, Republic of
CityGangwon
Period19/2/1819/2/20

Fingerprint

Brain-Computer Interfaces
Brain computer interface
Learning
Neural networks
Electroencephalography
Network architecture
Classifiers
Experiments
Chemical activation
Weights and Measures
Research
Deep learning

Keywords

  • Brain-Computer Interface
  • Convolutional Neural Network
  • Deep Learning
  • Electroencephalogram
  • Generative Adversarial Learning
  • Motor Imagery
  • Semi-Supervised Learning

ASJC Scopus subject areas

  • Artificial Intelligence
  • Human-Computer Interaction
  • Signal Processing
  • Neuroscience (miscellaneous)

Cite this

Ko, W., Jeon, E., Lee, J., & Suk, H-I. (2019). Semi-Supervised Deep Adversarial Learning for Brain-Computer Interface. In 7th International Winter Conference on Brain-Computer Interface, BCI 2019 [8737345] (7th International Winter Conference on Brain-Computer Interface, BCI 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IWW-BCI.2019.8737345

Semi-Supervised Deep Adversarial Learning for Brain-Computer Interface. / Ko, Wonjun; Jeon, Eunjin; Lee, Jiyeon; Suk, Heung-Il.

7th International Winter Conference on Brain-Computer Interface, BCI 2019. Institute of Electrical and Electronics Engineers Inc., 2019. 8737345 (7th International Winter Conference on Brain-Computer Interface, BCI 2019).

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

Ko, W, Jeon, E, Lee, J & Suk, H-I 2019, Semi-Supervised Deep Adversarial Learning for Brain-Computer Interface. in 7th International Winter Conference on Brain-Computer Interface, BCI 2019., 8737345, 7th International Winter Conference on Brain-Computer Interface, BCI 2019, Institute of Electrical and Electronics Engineers Inc., 7th International Winter Conference on Brain-Computer Interface, BCI 2019, Gangwon, Korea, Republic of, 19/2/18. https://doi.org/10.1109/IWW-BCI.2019.8737345
Ko W, Jeon E, Lee J, Suk H-I. Semi-Supervised Deep Adversarial Learning for Brain-Computer Interface. In 7th International Winter Conference on Brain-Computer Interface, BCI 2019. Institute of Electrical and Electronics Engineers Inc. 2019. 8737345. (7th International Winter Conference on Brain-Computer Interface, BCI 2019). https://doi.org/10.1109/IWW-BCI.2019.8737345
Ko, Wonjun ; Jeon, Eunjin ; Lee, Jiyeon ; Suk, Heung-Il. / Semi-Supervised Deep Adversarial Learning for Brain-Computer Interface. 7th International Winter Conference on Brain-Computer Interface, BCI 2019. Institute of Electrical and Electronics Engineers Inc., 2019. (7th International Winter Conference on Brain-Computer Interface, BCI 2019).
@inproceedings{aa49920a173743ddaa3861949cdb60ca,
title = "Semi-Supervised Deep Adversarial Learning for Brain-Computer Interface",
abstract = "Recent advances in deep learning have made a progressive impact on BCI researches. In particular, convolutional neural networks (CNNs) with different architectural forms have been studied for spatio-Temporal or spatio-spectral feature representation learning. However, there still remain many challenges and limitations due to the necessity of a large annotated training samples for robustness. In this paper, we propose a semi-supervised deep adversarial learning framework that effectively utilizes generated artificial samples along with labeled and unlabelled real samples in discovering class-discriminative features to boost robustness of a classifier, thus to enhance BCI performance. It is also noteworthy that the proposed framework allows to exploit unlabelled real samples to better uncover the underlying patterns inherent in a user's EEG signals. In order to justify the validity of the proposed framework, we conducted exhaustive experiments with 'Recurrent Spatio-Temporal Neural Network' CNN architectures over the public BCI Competition IV-IIa dataset. From our experiments, we could observe statistically significant improvements on performance, compared to the competing methods with the conventional framework. We have also visualized learned convolutional weights in terms of activation pattern maps, separability of extracted features, and validity of generated artificial samples.",
keywords = "Brain-Computer Interface, Convolutional Neural Network, Deep Learning, Electroencephalogram, Generative Adversarial Learning, Motor Imagery, Semi-Supervised Learning",
author = "Wonjun Ko and Eunjin Jeon and Jiyeon Lee and Heung-Il Suk",
year = "2019",
month = "2",
day = "1",
doi = "10.1109/IWW-BCI.2019.8737345",
language = "English",
series = "7th International Winter Conference on Brain-Computer Interface, BCI 2019",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "7th International Winter Conference on Brain-Computer Interface, BCI 2019",

}

TY - GEN

T1 - Semi-Supervised Deep Adversarial Learning for Brain-Computer Interface

AU - Ko, Wonjun

AU - Jeon, Eunjin

AU - Lee, Jiyeon

AU - Suk, Heung-Il

PY - 2019/2/1

Y1 - 2019/2/1

N2 - Recent advances in deep learning have made a progressive impact on BCI researches. In particular, convolutional neural networks (CNNs) with different architectural forms have been studied for spatio-Temporal or spatio-spectral feature representation learning. However, there still remain many challenges and limitations due to the necessity of a large annotated training samples for robustness. In this paper, we propose a semi-supervised deep adversarial learning framework that effectively utilizes generated artificial samples along with labeled and unlabelled real samples in discovering class-discriminative features to boost robustness of a classifier, thus to enhance BCI performance. It is also noteworthy that the proposed framework allows to exploit unlabelled real samples to better uncover the underlying patterns inherent in a user's EEG signals. In order to justify the validity of the proposed framework, we conducted exhaustive experiments with 'Recurrent Spatio-Temporal Neural Network' CNN architectures over the public BCI Competition IV-IIa dataset. From our experiments, we could observe statistically significant improvements on performance, compared to the competing methods with the conventional framework. We have also visualized learned convolutional weights in terms of activation pattern maps, separability of extracted features, and validity of generated artificial samples.

AB - Recent advances in deep learning have made a progressive impact on BCI researches. In particular, convolutional neural networks (CNNs) with different architectural forms have been studied for spatio-Temporal or spatio-spectral feature representation learning. However, there still remain many challenges and limitations due to the necessity of a large annotated training samples for robustness. In this paper, we propose a semi-supervised deep adversarial learning framework that effectively utilizes generated artificial samples along with labeled and unlabelled real samples in discovering class-discriminative features to boost robustness of a classifier, thus to enhance BCI performance. It is also noteworthy that the proposed framework allows to exploit unlabelled real samples to better uncover the underlying patterns inherent in a user's EEG signals. In order to justify the validity of the proposed framework, we conducted exhaustive experiments with 'Recurrent Spatio-Temporal Neural Network' CNN architectures over the public BCI Competition IV-IIa dataset. From our experiments, we could observe statistically significant improvements on performance, compared to the competing methods with the conventional framework. We have also visualized learned convolutional weights in terms of activation pattern maps, separability of extracted features, and validity of generated artificial samples.

KW - Brain-Computer Interface

KW - Convolutional Neural Network

KW - Deep Learning

KW - Electroencephalogram

KW - Generative Adversarial Learning

KW - Motor Imagery

KW - Semi-Supervised Learning

UR - http://www.scopus.com/inward/record.url?scp=85068338345&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85068338345&partnerID=8YFLogxK

U2 - 10.1109/IWW-BCI.2019.8737345

DO - 10.1109/IWW-BCI.2019.8737345

M3 - Conference contribution

AN - SCOPUS:85068338345

T3 - 7th International Winter Conference on Brain-Computer Interface, BCI 2019

BT - 7th International Winter Conference on Brain-Computer Interface, BCI 2019

PB - Institute of Electrical and Electronics Engineers Inc.

ER -