Title: Investigating spatio-temporal characteristics and evaluation of heavy goods vehicle risky driving behaviours based on vehicle networking dataset during naturalistic driving

Authors: Li Jiang; Huiying Wen; Gang Xue

Addresses: School of Civil Engineering and Transportation, South China University of Technology, Guangzhou 510000, Guangdong, China ' School of Civil Engineering and Transportation, South China University of Technology, Guangzhou 510000, Guangdong, China ' School of Automobile and Transportation Engineering, Guangdong Polytechnic Normal University, Guangzhou 510665, Guangdong, China

Abstract: This study analysed the factors that affect vehicle warnings driving incidents caused by risky distracted driving behaviours of Heavy Goods Vehicles (HGV) drivers. The analysis was based on the natural driving networking dataset collected over a 6-month period and comprising 81 fleets made by 5396 HGV drivers in Guangdong, China. First, the spatio-temporal coupling characteristics of warning incidents on HGV risky driving behavior and various levels of roads were established. Then, a global Moran index was built to measure the comprehensive score of risky driving behaviour, based on which the safety level of driving behaviour of HGV drivers was assessed. Results showed that 50% of the HGV drivers tended to drive in a substantially dangerous driving way, and HGV drivers received the highest total number of driving warning events in September, with the dangerous warning types being mainly deviation or blocking cameras and smoking.

Keywords: monitoring and warning system; heavy goods vehicles; spatiotemporal effects; behavioural coaching; global Moran Index; kernel density.

DOI: 10.1504/IJHVS.2022.127833

International Journal of Heavy Vehicle Systems, 2022 Vol.29 No.4, pp.389 - 406

Received: 05 Oct 2021
Accepted: 12 Apr 2022

Published online: 19 Dec 2022 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article