A Novel Dictionary-Driven Mental Spelling Application Based on Code-Modulated Visual Evoked Potentials

摘要: Brain–computer interfaces (BCIs) based on code-modulated visual evoked potentials (c-VEPs) typically utilize a synchronous approach to identify targets (i.e., after preset time periods the system produces command outputs). Hence, users have only limited amount of fixate desired target. This hinders usage more complex interfaces, as these require BCI distinguish between intentional and unintentional fixations. In this article, we investigate dynamic sliding window mechanism well implementation software-based stimulus synchronization enable threshold-based target identification for c-VEP paradigm. To further improve usability system, an ensemble-based classification strategy was investigated. addition, on-set determination is proposed, which allows easier setup it reduces additional hardware dependencies. The methods were tested with eight-target spelling application utilizing n-gram word prediction model. performance eighteen participants without disabilities tested; all completed word- sentence tasks using mean information transfer rate (ITR) 75.7 57.8 bpm, respectively.