AdaptEEG: A Deep Subdomain Adaptation Network With Class Confusion Loss for Cross-Subject Mental Workload Classification

• Published in: IEEE journal of biomedical and health informatics Vol. 29; no. 3; pp. 1940 - 1949
• Main Authors: Sun, Wu, Li, Junhua
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.03.2025
• Subjects: Accuracy; Adaptation models; Adult; Algorithms; Bioinformatics; brain computer interface; Brain modeling; Convolution; cross-subject classification; Deep Learning; Deep subdomain adaptation network; EEG; Electroencephalography; Electroencephalography - classification; Electroencephalography - methods; Feature extraction; Female; Humans; Kernel; Male; mental workload; Signal Processing, Computer-Assisted; Transfer learning; Workload - classification

EEG signals exhibit non-stationary characteristics, particularly across different subjects, which presents significant challenges in the precise classification of mental workload levels when applying a trained model to new subjects. Domain adaptation techniques have shown effectiveness in enhancing...