Simultaneous Classification of Multiple Motor Imagery and P300 for Increase in Output Information of Brain–Computer Interface

SUMMARY The brain–computer interface (BCI) is a system to obtain information from brain signals to control computers. P300 and motor imagery tasks in electroencephalograms are the most used features for BCI. However, BCI with P300 classifies only two states and the features of the motor imagery task are too obscure to be classified easily. Therefore, we propose a method of increasing the number of classified states with high accuracy by mixed signal processing for P300 and motor imagery tasks. BCI using P300 and a motor imagery task will have a higher bit rate than conventional BCI. We design an experiment that gives four data classes, namely, control, P300, and P300 for motor imagery of the right hand or left hand. First, we confirm that P300 appears during motor imagery tasks. In addition, we investigate the best method of feature extraction. Finally, we classify four classes by means of multiclass support vector machines, and show the effectiveness of mixed signals that contain P300 and motor imagery.