EUVIMEDEUVIMED entdecken
Crossref

Semi-supervised multi-source transfer learning for cross-subject EEG motor imagery classification

Fan Zhang, Hanliang Wu, Yuxin Guo

Medical & Biological Engineering & Computing · 2024

DOI: 10.1007/s11517-024-03032-z ↗

Kurz gefasst

Fachartikel in der Zeitschrift Medical & Biological Engineering & Computing, 2024. Verfasst von Fan Zhang und 2 weiteren Autor:innen. Beteiligte Einrichtung: Jinan University, Guangzhou, China. Hauptthemen laut MEDLINE: Electroencephalography, Brain-Computer Interfaces, Imagination. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 93 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Electroencephalogram (EEG) motor imagery (MI) classification refers to the use of EEG signals to identify and classify subjects' motor imagery activities; this task has received increasing attention with the development of brain-computer interfaces (BCIs). However, the collection of EEG data is usually time-consuming and labor-intensive, which makes it difficult to obtain sufficient labeled data from the new subject to train a new model. Moreover, the EEG signals of different individuals exhibit significant differences, leading to a significant drop in the performance of a model trained on the existing subjects when directly classifying EEG signals acquired from new subjects. Therefore, it is crucial to make full use of the EEG data of the existing subjects and the unlabeled EEG data of the new target subject to improve the MI classification performance achieved for the target subject. This research study proposes a semi-supervised multi-source transfer (SSMT) learning model to address the above problems; the model learns informative and domain-invariant representations to address cross-subject MI-EEG classification tasks. In particular, a dynamic transferred weighting schema is presented to obtain the final predictions by integrating the weighted features derived from multi-source domains. The average accuracies achieved on two publicly available EEG datasets reach 83.57 % and 85.09 % , respectively, validating the effectiveness of the SSMT process. The SSMT process reveals the importance of informative and domain-invariant representations in MI classification tasks, as they make full use of the domain-invariant information acquired from each subject.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ElectroencephalographyBrain-Computer InterfacesImaginationHumansSignal Processing, Computer-AssistedAlgorithmsSupervised Machine Learning

Stichwörter der Autor:innen

Brain-computer interfacesDynamic weightingElectroencephalogramMotor imageryMulti-source transfer learningSemi-supervised learning

Autor:innen und Institutionen

  • Jinan University, Guangzhou, China.
  • Liwan District People's Hospital of Guangzhou, Guangzhou, China. hlwu1982@foxmail.com.
  • Guangzhou Institute of Science and Technology, Guangzhou, China.

Zitieren

APA

Zhang, F., Wu, H., & Guo, Y. (2024). Semi-supervised multi-source transfer learning for cross-subject EEG motor imagery classification. Medical & Biological Engineering & Computing. https://doi.org/10.1007/s11517-024-03032-z

Vancouver

Zhang F, Wu H, Guo Y. Semi-supervised multi-source transfer learning for cross-subject EEG motor imagery classification. Medical & Biological Engineering & Computing. 2024. doi:10.1007/s11517-024-03032-z

BibTeX
@article{Zhang2024,
  author = {Zhang, Fan and Wu, Hanliang and Guo, Yuxin},
  title = {Semi-supervised multi-source transfer learning for cross-subject EEG motor imagery classification},
  journal = {Medical & Biological Engineering & Computing},
  year = {2024},
  doi = {10.1007/s11517-024-03032-z}
}
Kostenlos starten →