Performance Enhancement of an SSVEP-Based Brain-Computer Interface in Augmented Reality Through Adaptive Color Adjustment of Visual Stimuli for Optimal Background Contrast

The aim of this study is to develop a steady-state visual evoked potential (SSVEP)-based brain-computer interface (BCI) system with enhanced performance in an augmented reality (AR) environment by dynamically adjusting colors of visual stimuli to contrast with the background seen through the transparent display. Our proposed method extracts the average color value from the area surrounding the visual stimulus location. It then calculates the contrast value using the HSV color model and applies this to the stimulus color. In an offline experiment, we determined the optimal visual stimulus presentation strategy by comparing the performances of three different methods for determining the colors of visual stimuli in an AR environment. We then evaluated the feasibility of the proposed strategy through online experiments conducted in both indoor and outdoor conditions. The classification performance of the SSVEP-BCI system in an AR environment based on our proposed stimulus presentation strategy was 95.0% for a window size of 3.5 s in offline experiments performed with 17 participants. This was significantly higher than the performance of the conventional black-and-white color strategy. Additionally, it was confirmed by the online experiments that there was no large performance degradation between indoor and outdoor uses.