A Hybrid Transfer Learning Approach for Motor Imagery Classification in Brain-Computer Interface

The classification of motor imagery (MI) signal is a representative problem in brain-computer interface (BCI) systems. Because one main application field of MI-based BCI is medical rehabilitation, it is often difficult to obtain a large amount of labeled data from the same subject. Moreover, there are huge individual differences among subjects, so the data from other subjects can not be directly used to train the classifier of the target subject. A transfer learning approach which based on data alignment and deep transfer learning is proposed to solve above problem, and the effectiveness of the proposed approach is verified by experiments based on open dataset.