P300 based brain-computer interface using Hidden Markov Models

This paper reports on preliminary work on the use of hidden Markov models (HMMs) approach for tasks classification in P300-based brain-computer interface (BCI) system. Every HMM is trained on a set of electroencephalogram (EEG) records issued from different sessions corresponding to the same task. The HMMs that has been built take into account the variability of EEGs during different sessions. Based on Bayesian inference criterion (BIC), the proposed HMM training algorithm is able to select the optimal number of states corresponding to each set of EEG training records. For every state number, each iteration is initialized by the most appropriate model using data clustering, and by the rejection of the least probable state of the previous iteration. Consequently, every training iteration begin by a more precise model. We report training procedures and validation results of the models. The obtained results give a correct and promising classification rates for all subjects which is the objective of this work.