Freeing P300-Based Brain-Computer Interfaces From Daily Recalibration by Extracting Daily Common ERPs

Abstract

When people use brain-computer interfaces (BCIs) based on event-related potentials (ERPs) over different days, they often need to repeatedly calibrate BCIs every day using ERPs acquired on the same day. This cumbersome recalibration procedure would make it difficult to use BCIs daily. We aim to address the daily recalibration issue by examining across-day variations of the BCI performance and proposing a method to avoid daily recalibration. To this end, we implemented a P300-based BCI system designed to control a home appliance over five days. We first examined how the BCI performance varied across days with or without daily recalibration. On each day, the BCIs were tested using recalibration-based and recalibration-free decoders (RB and RF), with an RB or an RF decoder being built on the training data on each day or those on the first day, respectively. Using the RF decoder resulted in lower BCI performance on subsequent days compared to the RB decoder. Then, we developed a method to extract daily common ERP patterns from observed ERP signals using the sparse dictionary learning algorithm. We applied this method to the RF decoder and retested the BCI performance over days. Using the proposed method improved the RF decoder performance on subsequent days; the performance was closer to the level of the RB decoder compared to the original RF decoder. The method may provide a novel approach to addressing the daily-recalibration issue for P300-based BCIs, which is essential to implementing BCIs into daily life.