Supervised Contrastive Learning-Based Domain Generalization Network for Cross-Subject Motor Decoding

• Published in: IEEE transactions on biomedical engineering Vol. 72; no. 1; pp. 401 - 412
• Main Authors: Zhi, Hongyi, Yu, Tianyou, Gu, Zhenghui, Lin, Zhuobin, Che, Le, Li, Yuanqing, Yu, Zhuliang
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.01.2025; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Ablation; Adaptation; Adult; Algorithms; Alignment; Brain modeling; Brain-computer interface (BCI); Contrastive learning; Decoding; domain generalization (DG); EEG; Effectiveness; electroencephalogram (EEG); Electroencephalography; Electroencephalography - methods; Feature extraction; Humans; Invariants; Learning; Male; Mental task performance; motor execution (ME); motor imagery (MI); Motor skill learning; Motors; Regularization; Representations; Signal Processing, Computer-Assisted; supervised contrastive learning (SCL); Supervised Machine Learning; Training; Transfer learning

Developing an electroencephalogram (EEG)-based motor imagery and motor execution (MI/ME) decoding system that is both highly accurate and calibration-free for cross-subject applications remains challenging due to domain shift problem inherent in such scenario. Recent research has increasingly embrac...