Comparative Evaluation of Facial Paradigms for Devanagari Script-based P300 Speller: Preliminary Findings

Abstract

Display paradigm design is an important stage in the design of any brain-computer interface (BCI) device including the P300 speller system. Conventional grey-to-white intensification limits the usability of the existing Devanagari-script-based P300 speller (DSP3S) as it suffers from reduced visual contrast, diminished user engagement, limited personalization, minimal cognitive stimulation, and the risk of visual fatigue. The use of a facial paradigm can address the above-mentioned limitations through emotionally resonant stimuli, offering diverse cognitive stimulation, and potentially reducing visual fatigue by introducing dynamic and engaging facial stimuli. In this context, this study is the first attempt to investigate the efficacy of facial paradigms in further improving the usability of DSP3S. The authors investigated three facial paradigms based on the smiley face, famous face, and family faces for DSP3S. The three facial paradigms are evaluated based on their effectiveness, efficiency, and satisfaction. Effectiveness was measured using classification performance and amplitude difference waveform. Whereas efficiency and satisfaction were measured using NASA-TLX, VAS-F scale, and SUS respectively. The obtained results showed that using the proposed family face intensification, efficiency, and satisfaction could be improved. However, no significant difference was observed in effectiveness among the three display paradigms. In this study, apart from investigating the usability of three display paradigms, authors also propose brain signal decoding using morphological filtering and extreme gradient boosting (XGBoost). Finally, the study concludes that the design of display paradigms using different intensification patterns affects the usability of the speller system and should be taken into consideration.