TFTL: A Task-Free Transfer Learning Strategy for EEG-Based Cross-Subject and Cross-Dataset Motor Imagery BCI

• Published in: IEEE transactions on biomedical engineering Vol. 72; no. 2; pp. 810 - 821
• Main Authors: Wang, Yihan, Wang, Jiaxing, Wang, Weiqun, Su, Jianqiang, Bunterngchit, Chayut, Hou, Zeng-Guang
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.02.2025; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Accuracy; Adult; Algorithms; Brain modeling; Brain-Computer Interfaces; Calibration; Clinical trials; cross-dataset; cross-subject; Data models; Datasets; Decoding; Deep Learning; EEG; Electroencephalogram (EEG); Electroencephalography; Electroencephalography - methods; Feature extraction; Female; Human-computer interface; Humans; Imagery; Imagination - physiology; Knowledge management; Machine learning; Male; Mental task performance; motor imagery; Motor skill learning; Performance evaluation; Signal Processing, Computer-Assisted; Statistical analysis; Statistical methods; task-free; Training; Transfer learning; User experience; Young Adult

Objective: Motor imagery-based brain-computer interfaces (MI-BCIs) have been playing an increasingly vital role in neural rehabilitation. However, the long-term task-based calibration required for enhanced model performance leads to an unfriendly user experience, while the inadequacy of EEG data hin...