TY - GEN
T1 - Domain Adaptation with Source Selection for Motor-Imagery based BCI
AU - Jeon, Eunjin
AU - Ko, Wonjun
AU - Suk, Heung Il
N1 - Funding Information:
This work was supported by the Institute of Information & Communications Technology Planning & Evaluation (IITP) grant funded by the Korea government (No. 2017-0-00451; Development of BCI based Brain and Cognitive Computing Technology for Recognizing User’s Intentions using Deep Learning).
Publisher Copyright:
© 2019 IEEE.
PY - 2019/2
Y1 - 2019/2
N2 - Recent successes of deep learning methods in various applications have inspired BCI researchers for their use in EEG classification. However, data insufficiency and high intra-and inter-subject variabilities hinder from taking their advantage of discovering complex patterns inherent in data, which can be potentially useful to enhance EEG classification accuracy. In this paper, we devise a novel framework of training a deep network by adapting samples of other subjects as a means of domain adaptation. Assuming that there are EEG trials of motor-imagery tasks from multiple subjects available, we first select a subject whose EEG signal characteristics are similar to the target subject based on their power spectral density in resting-state EEG signals. We then use EEG signals of both the selected subject (called a source subject) and the target subject jointly in training a deep network. Rather than training a single path network, we adopt a multi-path network architecture, where the shared bottom layers are used to discover common features for both source and target subjects, while the upper layers branch out into (1) source-Target subject identification, (2) label prediction optimized for a source subject, and (3) label prediction optimized for a target subject. Based on our experimental results over the BCI Competition IV-IIa dataset, we validated the effectiveness of the proposed framework in various aspects.
AB - Recent successes of deep learning methods in various applications have inspired BCI researchers for their use in EEG classification. However, data insufficiency and high intra-and inter-subject variabilities hinder from taking their advantage of discovering complex patterns inherent in data, which can be potentially useful to enhance EEG classification accuracy. In this paper, we devise a novel framework of training a deep network by adapting samples of other subjects as a means of domain adaptation. Assuming that there are EEG trials of motor-imagery tasks from multiple subjects available, we first select a subject whose EEG signal characteristics are similar to the target subject based on their power spectral density in resting-state EEG signals. We then use EEG signals of both the selected subject (called a source subject) and the target subject jointly in training a deep network. Rather than training a single path network, we adopt a multi-path network architecture, where the shared bottom layers are used to discover common features for both source and target subjects, while the upper layers branch out into (1) source-Target subject identification, (2) label prediction optimized for a source subject, and (3) label prediction optimized for a target subject. Based on our experimental results over the BCI Competition IV-IIa dataset, we validated the effectiveness of the proposed framework in various aspects.
KW - Brain-Computer Interface
KW - Deep Learning
KW - Domain Adaptation
KW - Electroencephalogram (EEG)
KW - Motor Imagery
KW - Transfer Learning
UR - http://www.scopus.com/inward/record.url?scp=85068310816&partnerID=8YFLogxK
U2 - 10.1109/IWW-BCI.2019.8737340
DO - 10.1109/IWW-BCI.2019.8737340
M3 - Conference contribution
AN - SCOPUS:85068310816
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.
T2 - 7th International Winter Conference on Brain-Computer Interface, BCI 2019
Y2 - 18 February 2019 through 20 February 2019
ER -