Improvement of spelling speed in P300 speller using transition probability of letters

Brain-Computer Interfaces (BCIs) control a computer or a machine based on the information of the signal of human´s brain, and P300 speller is one of the BCI communication tools, which uses P300 as the feature quantity and allows users to select letters just by thinking. Because of the low signal-to-noise ratio of the P300, signal averaging is often performed to improve the spelling accuracy instead of the degradation of the spelling speed. In texts, there is some variability in the transition probabilities between letters. This paper proposes P300 speller considering the frequencies and the transition probabilities as the priori probabilities. It shows that the spelling speed is improved by the proposed method comparing with the conventional method.