A brain-computer interface in the context of a head up display system

In this paper, we propose a new P300-based brain-computer interface (BCI) with visual stimuli being displayed on a car windshield by a Head Up Display (HUD) system. A 3*3 matrix of characters representing nine predefined locations were developed as P300 stimuli. A linear discriminant analysis (LDA) classifier with the features selected from EEG potentials by principal component analysis (PCA) was used to recognize the P300 and thus determine the desired locations. Experimental results of three healthy participants with no subject screening being conducted indicate that the average accuracy of the new BCI system is above 75% when fifty rounds of EEG data were used, showing that the proposed BCI system is feasible. The potential benefit of this system is that it can cause little distraction when applied to control mobile robots or automobiles in a known environment.