Deep Source Semi-Supervised Transfer Learning (DS3TL) for Cross-Subject EEG Classification

• Published in: IEEE transactions on biomedical engineering Vol. 71; no. 4; pp. 1308 - 1318
• Main Authors: Jiang, Xue, Meng, Lubin, Wang, Ziwei, Wu, Dongrui
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.04.2024; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Adaptation; Adaptation models; Brain; Brain mapping; Brain modeling; Brain-computer interface; Brain-Computer Interfaces; classification; Classification algorithms; Computer applications; Cyclohexylamines; Data acquisition; EEG; electroencephalogram; Electroencephalography; Human-computer interface; Implants; Indenes; Labels; Machine learning; Modules; Predictive models; Regularization; Semi-supervised learning; Semisupervised learning; Supervised Machine Learning; Training; Transfer learning
• ISSN: 0018-9294; 1558-2531; 1558-2531
• DOI: 10.1109/TBME.2023.3333327

Objective: An electroencephalogram (EEG) based brain-computer interface (BCI) maps the user's EEG signals into commands for external device control. Usually a large amount of labeled EEG trials are required to train a reliable EEG recognition model. However, acquiring labeled EEG data is time-consuming and user-unfriendly. Semi-supervised learning (SSL) and transfer learning can be used to exploit the unlabeled data and the auxiliary data, respectively, to reduce the amount of labeled data for a new subject. Methods: This paper proposes deep source semi-supervised transfer learning (DS3TL) for EEG-based BCIs, which assumes the source subject has a small number of labeled EEG trials and a large number of unlabeled ones, whereas all EEG trials from the target subject are unlabeled. DS3TL mainly includes a hybrid SSL module, a weakly-supervised contrastive module, and a domain adaptation module. The hybrid SSL module integrates pseudo-labeling and consistency regularization for SSL. The weakly-supervised contrastive module performs contrastive learning by using the true labels of the labeled data and the pseudo-labels of the unlabeled data. The domain adaptation module reduces the individual differences by uncertainty reduction. Results: Experiments on three EEG datasets from different tasks demonstrated that DS3TL outperformed a supervised learning baseline with many more labeled training data, and multiple state-of-the-art SSL approaches with the same number of labeled data. Significance: To our knowledge, this is the first approach in EEG-based BCIs that exploits the unlabeled source data for more accurate target classifier training.