Nonspecific Visuospatial Imagery as a Novel Mental Task for Online EEG-Based BCI Control.

摘要: Brain-computer interfaces (BCIs) can provide a means of communication to individuals with severe motor disorders, such as those presenting locked-in. Many BCI paradigms rely on neural pathways, which are often impaired in these individuals. However, recent findings suggest that visuospatial function may remain intact. This study aimed determine whether imagery, previously unexplored task, could be used signify intent an online electroencephalography (EEG)-based BCI. Eighteen typically developed participants imagined checkerboard arrow stimuli four quadrants the visual field 5-s trials, while signals were collected using 16 dry electrodes over cortex. In blocks, received graded feedback based their performance. An initial pipeline (visuospatial imagery classifier I) attained mean accuracy [Formula: see text]% classifying rest against trials. was further improved restriction alpha band features II), resulting pseudo-online text]%. Accuracies exceeded threshold for practical BCIs 12 participants. supports use real-time, binary EEG-BCI control paradigm.