EUVIMEDEUVIMED entdecken
Crossref

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

Xue Jiang, Lubin Meng, Ziwei Wang, Dongrui Wu

IEEE Transactions on Biomedical Engineering · 2024-04 · 71 (4) · 1308-1318

DOI: 10.1109/tbme.2023.3333327 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Biomedical Engineering, 2024-04. Verfasst von Xue Jiang und 3 weiteren Autor:innen. Hauptthemen laut MEDLINE: Electroencephalography, Brain-Computer Interfaces, Indenes. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 51 Literaturangaben. Gefördert von: Shenzhen Science and Technology Program, Beijing Fenghuo Wanjia Technology Company Ltd..

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ElectroencephalographyBrain-Computer InterfacesIndenesCyclohexylaminesSupervised Machine Learning

Substanzen

2-benzylidene-3-(cyclohexylamino)-2,3-dihydro-1H-inden-1-oneCyclohexylaminesIndenes

Förderung

  • Shenzhen Science and Technology Program
  • Beijing Fenghuo Wanjia Technology Company Ltd.

Zitieren

APA

Jiang, X., Meng, L., Wang, Z., & Wu, D. (2024). Deep Source Semi-Supervised Transfer Learning (DS3TL) for Cross-Subject EEG Classification. IEEE Transactions on Biomedical Engineering, 71(4), 1308-1318. https://doi.org/10.1109/tbme.2023.3333327

Vancouver

Jiang X, Meng L, Wang Z, Wu D. Deep Source Semi-Supervised Transfer Learning (DS3TL) for Cross-Subject EEG Classification. IEEE Transactions on Biomedical Engineering. 2024;71(4):1308-1318. doi:10.1109/tbme.2023.3333327

BibTeX
@article{Jiang2024,
  author = {Jiang, Xue and Meng, Lubin and Wang, Ziwei and Wu, Dongrui},
  title = {Deep Source Semi-Supervised Transfer Learning (DS3TL) for Cross-Subject EEG Classification},
  journal = {IEEE Transactions on Biomedical Engineering},
  year = {2024},
  volume = {71},
  number = {4},
  pages = {1308--1318},
  doi = {10.1109/tbme.2023.3333327}
}
Kostenlos starten →