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

• Published in: Medical & biological engineering & computing Vol. 62; no. 6; pp. 1655 - 1672
• Main Authors: Zhang, Fan, Wu, Hanliang, Guo, Yuxin
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.06.2024; Springer Nature B.V
• Subjects: Attention; Attention task; Biomedical and Life Sciences; Biomedical Engineering and Bioengineering; Biomedicine; Classification; Computer Applications; data collection; EEG; Electroencephalography; Human Physiology; Human-computer interface; Image classification; Imaging; Invariants; Mental task performance; Motor skill learning; Original Article; Radiology; Representations; Semi-supervised learning; Signal classification; Transfer learning; Multi-source transfer learning; Brain-computer interfaces; Motor imagery; Electroencephalogram; Semi-supervised learning; Dynamic weighting
• ISSN: 0140-0118; 1741-0444; 1741-0444
• DOI: 10.1007/s11517-024-03032-z

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. Graphical abstract