Bayesian delay time estimation of brainwaves using N100 response in tactile-force Brain-Computer Interface

Brain Computer Interfaces (BCIs) are useful communication tools for disabled people. P300 which is observed around 300ms after the onset of stimulus is widely used for BCI principle. The latency variation of P300 is affected by the degree of mental fatigue, habituation, or the level of attention, and incurs a distortion of P300 waveform. To estimate the delay time, a method using the Bayesian estimation has been introduced and the improvement of classification accuracy has been confirmed for an auditory BCI. In this paper, we apply the modified delay time estimation method to tactile-force BCI. The classification accuracy was improved 7.80% in comparison with the conventional simple averaging method and a significant differences between the conventional and the proposed method was found with the paired t-test. From these results, the efficacy of the proposed method for tactile-force BCI was thus confirmed.