Research on EEG-based Novice and Experienced Drivers' Identification Using BP Neural Network during Simulated Driving

• Published in: 2020 4th CAA International Conference on Vehicular Control and Intelligence (CVCI) pp. 475 - 480
• Main Authors: Wu, Yingzhang, Zhang, Jie, Tang, Bangbei, Guo, Gang
• Format: Conference Proceeding
• Language: English
• Published: IEEE 18.12.2020
• Subjects: Adaptation models; Automotive engineering; Back Propagation (BP) Neural Network; Brain modeling; Driving experience recognition; Electroencephalogram (EEG); Electroencephalography; Feature extraction; Neural networks; Traffic safety; Vehicles
• DOI: 10.1109/CVCI51460.2020.9338490

Drivers play an important role in the transportation system. Novice drivers have insufficient driving risk awareness due to lack of driving experience, which has become a potential hazard in the traffic system. The automotive driving assistance system (ADAS) can more or less help the novice driver to avoid danger. In order to further improve the ADAS control strategy for drivers with different driving experience, it is necessary to identify novice drivers and experienced drivers. In this study, a twelve-kilometer two-way straight highway was designed as the driving scenario. Electroencephalogram(EEG) data generated in the frontal region was recorded as an indicator to evaluate the driver's perception of danger. We aim to identify novice drivers and experienced drivers by using beta waves extracted from collected EEG data when facing dangerous situations. The results indicate that the EEG features (PSD value of beta wave) extracted from the frontal region can effectively recognize the novice driver and the experienced driver through the BP neural network, and achieve a relatively high accuracy at nearly 88%.