Incorporating Personality Traits to Assess the Risk Level of Aberrant Driving Behaviors for Truck Drivers

Chien-Hung Wei, Ying Lee, Yu-Wen Luo and Jyun-Jie Lu
Additional contact information
Chien-Hung Wei: Department of Transportation and Communication Management Science, National Cheng Kung University, Tainan City 701, Taiwan
Ying Lee: Department of Supply Chain Management, National Kaohsiung University of Science and Technology, Kaohsiung 811, Taiwan
Yu-Wen Luo: Department of Transportation and Communication Management Science, National Cheng Kung University, Tainan City 701, Taiwan
Jyun-Jie Lu: Department of Transportation and Communication Management Science, National Cheng Kung University, Tainan City 701, Taiwan

IJERPH, 2021, vol. 18, issue 9, 1-18

Abstract: Economic globalization and the internet economy have resulted in a dramatic increase in freight transportation. Traffic crashes involving trucks usually result in severe losses and casualties. The fatality and injury rates for heavy truck accidents have been 10 times higher than for sedans in Taiwan in recent years. Thus, understanding driving behavior and risk are important for freight carriers. Since personality traits may result in different driving behaviors, the main objective of this study is to apply artificial neural network (ANN) models to predict the frequency of aberrant driving behavior and the risk level of each driver according to drivers’ personality traits. In this case study, relevant information on truck drivers’ personality traits and their tendency to engage in aberrant driving behavior are collected by using respectively a questionnaire and a fleet surveillance system from a truck company. A relative risk level evaluation mechanism is developed considering the frequency and distribution of aberrant driving behavior. The Jenks natural breaks optimization method and the elbow method are adopted to optimally classify 40 truck drivers into 4 aberrant driving behavior levels and 5 driving risk levels. It was found that 5% of drivers were at the highest aberrant driving behavior level, and 7.5% of drivers were at the highest driving risk level. Based on the results, the proposed models show good and stable predictive performance, especially for the class of drivers with excessive rotation speed, hard acceleration, excessive rotation speed, hard deceleration, and driving risk. With the proposed models, the predictive class for aberrant driving behavior and driving risk can be determined by plugging in a driver’s personality traits before or after employment. Based on the prediction results, the manager of a transportation company could plan the training program for each driver to reduce the aberrant driving behavior occurrence.

Keywords: truck drivers; personality traits; aberrant driving behavior; artificial neural network; driving risk level (search for similar items in EconPapers)
JEL-codes: I I1 I3 Q Q5 (search for similar items in EconPapers)
Date: 2021
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (3)

Downloads: (external link)
https://www.mdpi.com/1660-4601/18/9/4601/pdf (application/pdf)
https://www.mdpi.com/1660-4601/18/9/4601/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jijerp:v:18:y:2021:i:9:p:4601-:d:543929

Access Statistics for this article

IJERPH is currently edited by Ms. Jenna Liu

More articles in IJERPH from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().