A widely discussed paradigm for brain-computer interface (BCI) is themotor imagery task using noninvasive electroencephalography\n(EEG) modality. It often requires long training session for collecting a large amount of EEG data which makes user exhausted.\nOne of the approaches to shorten this session is utilizing the instances from past users to train the learner for the novel user. In this\nwork, direct transferring from past users is investigated and applied to multiclass motor imagery BCI. Then, active learning (AL)\ndriven informative instance transfer learning has been attempted for multiclass BCI. Informative instance transfer shows better\nperformance than direct instance transfer which reaches the benchmark using a reduced amount of training data (49% less) in\ncases of 6 out of 9 subjects. However, none of these methods has superior performance for all subjects in general. To get a generic\ntransfer learning framework for BCI, an optimal ensemble of informative and direct transfer methods is designed and applied.The\noptimized ensemble outperforms both direct and informative transfer method for all subjects except one in BCI competition IV\nmulticlass motor imagery dataset. It achieves the benchmark performance for 8 out of 9 subjects using average 75% less training\ndata.Thus, the requirement of large training data for the new user is reduced to a significant amount.
Loading....