A Bayesian Multiple Kernel Learning Algorithm for SSVEP BCI Detection

This paper deals with the classification of steady-state visual evoked potentials (SSVEP), which is a multiclass classification problem addressed in SSVEP-based brain–computer interfaces. In particular, our method named MultiLRM_MKL uses multiple linear regression models under a Sparse Bayesian Learning (SBL) framework to discriminate between the SSVEP classes. The regression coefficients of each model are learned using the Variational Bayesian (VB) framework and the kernel trick is adopted not only for reducing the computational cost of our method, but also for enabling the combination of different kernel spaces. We verify the effectiveness of our method in handling different kernel spaces by evaluating its performance with a new kernel based on canonical correlation analysis. In particular, we prove the benefit of combining multiple kernels by outperforming several state-of-the-art methods in two SSVEP datasets, reaching an information transfer rate of 93 b/min using only three channels from the occipital area (<inline-formula><tex-math notation="LaTeX">$O_z$</tex-math></inline-formula>, <inline-formula><tex-math notation="LaTeX">$O_1$</tex-math></inline-formula>, and <inline-formula><tex-math notation="LaTeX">$O_2$</tex-math></inline-formula>).