Citation

Magana VC, Munoz-Organero M. IEEE Veh. Tech. Mag. 2017; 12(4): 69-76.

Copyright

(Copyright © 2017, Institute of Electrical and Electronics Engineers, Inc.)

DOI

10.1109/MVT.2017.2692059

PMID

unavailable

Abstract

Driver stress is a growing problem in the transportation industry. It causes a deterioration of cognitive skills, resulting in poor driving and an increase in the likelihood of traffic accidents. Prediction models allow us to avoid or at least minimize the negative consequences of stress. In this article, an algorithm based on deep learning is proposed to predict driver stress. This type of algorithm detects complex relationships among variables. At the same time, it avoids overfitting. The prediction of the upcoming stress level is made by taking into account driving behavior (acceleration, deceleration, speed) and the previous stress level.

Language: en

Keywords

Acceleration; Human factors; road safety; Vehicle safety; behavioural sciences computing; cognitive systems; deep learning; driver stress; driving behavior; habitual routes; Heart rate variability; Prediction algorithms; stress level; Stress measurement; traffic accidents; transportation industry