Manifold Embedded Knowledge Transfer for Brain-Computer Interfaces

• Published in: IEEE transactions on neural systems and rehabilitation engineering Vol. 28; no. 5; pp. 1117 - 1127
• Main Authors: Zhang, Wen, Wu, Dongrui
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.05.2020; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Brain-computer interfaces; Classification; Computational neuroscience; Covariance matrices; Covariance matrix; Domains; EEG; electroencephalogram; Electroencephalography; Feature extraction; Geometry; Human-computer interface; Interfaces; Knowledge management; Learning; Manifolds; Probability distribution; Riemann manifold; Riemannian manifold; Symmetric matrices; Task analysis; Transfer learning
• ISSN: 1534-4320; 1558-0210; 1558-0210
• DOI: 10.1109/TNSRE.2020.2985996

Transfer learning makes use of data or knowledge in one problem to help solve a different, yet related, problem. It is particularly useful in brain-computer interfaces (BCIs), for coping with variations among different subjects and/or tasks. This paper considers offline unsupervised cross-subject electroencephalogram (EEG) classification, i.e., we have labeled EEG trials from one or more source subjects, but only unlabeled EEG trials from the target subject. We propose a novel manifold embedded knowledge transfer (MEKT) approach, which first aligns the covariance matrices of the EEG trials in the Riemannian manifold, extracts features in the tangent space, and then performs domain adaptation by minimizing the joint probability distribution shift between the source and the target domains, while preserving their geometric structures. MEKT can cope with one or multiple source domains, and can be computed efficiently. We also propose a domain transferability estimation (DTE) approach to identify the most beneficial source domains, in case there are a large number of source domains. Experiments on four EEG datasets from two different BCI paradigms demonstrated that MEKT outperformed several state-of-the-art transfer learning approaches, and DTE can reduce more than half of the computational cost when the number of source subjects is large, with little sacrifice of classification accuracy.