Open Access
ARTICLE
NARX Network Based Driver Behavior Analysis and Prediction Using Time-series Modeling
Ling Wu1, Haoxue Liu2, Tong Zhu2, Yueqi Hu3
1 School of Vehicle Engineering, Xi'an Aeronautical University, Xi’an, Shaanxi, China
2 Key Laboratory for Automotive Transportation Safety Enhancement Technology of the Ministry of Communication, Chang’an University, Xi’an, Shaanxi, China
3 School of Automobiles, Chang’an University, Xi’an, Shaanxi, China
* Corresponding Author: Ling Wu,
Intelligent Automation & Soft Computing 2018, 24(3), 633-642. https://doi.org/10.31209/2018.100000030
Abstract
The objective of the current study was to examine how experienced and
inexperienced driver behaviour changed (including heart rate and longitudinal
speeds) when approaching and exiting highway tunnels. Simultaneously, the
NARX neural network was used to predict real-time speed with the heart rate
regarded as the input variable. The results indicated that familiarity with the
experimental route did decrease drivers’ mental stress but resulted in higher
speed. The proposed NARX model could predict synchronous speed with high
accuracy. These results of the present study concern how to establish the
automated driver model in the simulation environment.
Keywords
Cite This Article
L. Wu, H. Liu, T. Zhu and Y. Hu, "Narx network based driver behavior analysis and prediction using time-series modeling,"
Intelligent Automation & Soft Computing, vol. 24, no.3, pp. 633–642, 2018. https://doi.org/10.31209/2018.100000030