Brain-computer interfaces (BCIs) based on eventrelated potentials (ERP) are communicating tools with severely disabled people. P300 which is observed after 300 mili seconds from stimuli is widely used for the operation principle of BCIs. However the response time to the stimuli depends on a subject, trial, and also a channel. Many existing approaches ignore this variation and extract only low frequency component. We propose a method to estimate the response time of P300 using Bayesian estimation. The proposed method exhibited higher performance in our auditory BCI.

No abstract

Channel selection or reduction in Brain computer interface (BCI) is important to reduce the cost and improve the generalized accuracy. A channel selection method using group automatic relevance determination (GARD) for P300 based BCI has been reported. In this paper, we apply the penalized ARD (PARD) which is an extension of ARD, and compare with GARD in our auditory BCI. Experimental results show that PARD provides more sparse solution than GARD while PARD shows almost the same classification accuracy as GARD.

No abstract