Towards cognitive BCI: Neural correlates of sustained attention in a continuous performance task

Development of brain-computer interfaces interacting with cognitive functions is a hot topic in neural engineering since it may lead to innovative and powerful diagnosis, rehabilitation, and training methods. This paper addresses the problem of measuring sustained visual attention using electroencephalography and presents an experiment inspired by continuous performance tasks used in neuropsychology along with the classification results obtained when trying to discriminate between low and high attention states. Following a leave-one-subject-out validation approach, 76% accuracy was obtained when discriminating thirty second epochs and 69% accuracy using five second epochs.