Motor Imagery Classification via Kernel-Based Domain Adaptation on an SPD Manifold

• Published in: Brain sciences Vol. 12; no. 5; p. 659
• Main Authors: Jiang, Qin, Zhang, Yi, Zheng, Kai
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 18.05.2022; MDPI
• Subjects: Algorithms; brain–computer interfaces; Classification; Competition; domain adaptation; EEG; Hilbert space; Interfaces; Mental task performance; Riemannian manifolds; subspace learning; symmetric positive definite matrices; subspace learning; Riemannian manifolds; brain–computer interfaces; symmetric positive definite matrices; domain adaptation; EEG

Background: Recording the calibration data of a brain–computer interface is a laborious process and is an unpleasant experience for the subjects. Domain adaptation is an effective technology to remedy the shortage of target data by leveraging rich labeled data from the sources. However, most prior m...