Title: A Bayesian Multiple Kernel Learning Algorithm for SSVEP BCI detection
Abstract: Our work deals with the classification of Steady State Visual Evoked Potentials (SSVEP) which isa multiclass classification problem addressed in SSVEPbased Brain Computer Interfaces (BCIs). 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 (CCA). 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 (ITR) of 93 bits/min using only 3 channels from the occipital area (O z , O 1 and O 2 ).
Early access: The manuscript (in early access) can be found here!