The new post processing method for self-paced BCI system

Self-paced Brain Computer Interface (SBCI) is an important class of BCI systems which has not received enough attention yet. Certain events, such as motor imagery, can elicit Event-Related Synchronization/ De synchronization (ERD/ERS) of neurons in the brain which manifest themselves in terms of band power changes in brain signals. The activation/deactivation of brain´s cortical neural systems during a motor activity changes the complexity or randomness of the spontaneous EEG and can be quantified accurately with the fractal dimension and entropy. In the systems which use this phenomenon, in non-control intervals, ERD/ERS patterns are rarely observed with powerful amplitude, short interval and cut-off nature without any clear source that result in increasing the error of movement distinction in an asynchronous state. In other words, separating the movement from the inactive part of the signal is a big step which most BCI groups have been confronted. In this paper, a new post processing method is proposed which can improve the results of distinguishing a non-control state from a control one. Also, the performance of BCI systems is improved in term of decreasing the FP rate so that the system is more suitable for practical applications. In this process, we used data of BCI competition 2008(dataset 1) and some conditions are considered by paying attention to the structure of neurological phenomena.