Transfer Kernel Common Spatial Patterns for Motor Imagery Brain-Computer Interface Classification

Motor-imagery-based brain-computer interfaces (BCIs) commonly use the common spatial pattern (CSP) as preprocessing step before classifcation. Te CSP method is a supervised algorithm. Terefore a lot of time-consuming training data is needed to build the model. To address this issue, one promising approach is transfer learning, which generalizes a learning model can extract discriminative information from other subjects for target classifcation task. To this end, we propose a transfer kernel CSP (TKCSP) approach to learn a domain-invariant kernel by directly matching distributions of source subjects and target subjects. Te dataset IVa of BCI Competition III is used to demonstrate the validity by our proposed methods. In the experiment, we compare the classifcation performance of the TKCSP against CSP, CSP for subject-to-subject transfer (CSP SJ-to-SJ), regularizing CSP (RCSP), stationary subspace CSP (ssCSP), multitask CSP (mtCSP), and the combined mtCSP and ssCSP (ss + mtCSP) method. Te results indicate that the superior mean classifcation performance of TKCSP can achieve 81.14%, especially in case of source subjects with fewer number of training samples. Comprehensive experimental evidence on the dataset verifes the efectiveness and efciency of the proposed TKCSP approach over several state-of-the-art methods.