Improving Asynchronous Control for P300-based BCI: towards a completely autoadaptative system

Brain-computer interface ({BCI}) systems allow people with severe motor disabilities to communicate and interact with the external world. The P300 potential is one of the most used control signals for {EEG}-based {BCIs}. Classic P300-based {BCIs} work in a synchronous mode; the synchronous control assumes that the user is constantly attending to the stimulation, and the number of stimulation sequences is fixed a priori. This issue is an obstacle for the use of these systems in everyday life; users will be engaged in a continuous control state, their distractions will cause misclassification and the speed of selection will not take into account users' current psychophysical condition. An efficient {BCI} system should be able to understand the user's intentions from the ongoing {EEG} instead. Also, it has to refrain from making a selection when the user is engaged in a different activity and it should increase or decrease its speed of selection depending on the current user's state. We addressed these issues by introducing an asynchronous {BCI} and tested its capabilities for effective environmental monitoring, involving 11 volunteers in three recording sessions. Results show that this {BCI} system can increase the bit rate during control periods while the system is proved to be very efficient in avoiding false negatives when the users are engaged in other tasks.