Neuro-driving: Automatic perception technique for upcoming emergency situations

Abstract

We propose a neuro-driving simulation framework for the detection of emergency situation under general circum-stances. Previous work on neuro-driving has been shown that neural activity related with emergency situations while driving generates a different characteristic spatio-temporal event-related potential (ERP) pattern compared to normal state [1]. In this paper, on the basis of those study, three kinds of emergency situations are designed to discriminate ERP patterns between a variety of emergencies and normal driving situation. Based on comparison analysis based on KU and BBCI dataset, it is believed that the proposed framework can be considered as a novel EEG-based automatic perception technique for upcoming emergency situations.