Izvorni znanstveni članak
https://doi.org/10.7307/ptt.v38i6.1153
A Quantitative Method for Assessing Freeway Driving Risk Based on Continuous Observation Data
Chonghao Pang
; School of Civil Engineering and Transportation, South China University of Technology, Guangzhou, China
Peiqun Lin
; School of Civil Engineering and Transportation, South China University of Technology, Guangzhou, China
*
Minping Gong
; Shenzhen Wanwuyun Technology Co., Ltd, Shenzhen, China
Qiang Zeng
; School of Civil Engineering and Transportation, South China University of Technology, Guangzhou, China
Chuhao Zhou
; School of Civil Engineering and Transportation, South China University of Technology, Guangzhou, China
* Dopisni autor.
Sažetak
Frequent freeway accidents cause significant casualties and economic losses, necessitating robust risk assessment methods. This study proposes a quantitative method for assessing freeway driving risk using continuous observational data from toll transactions. Based on toll data from the Yongguan Freeway in Guangdong Province, China (June–August 0), 8 risk characteristic indicators for cargo vehicles and for passenger vehicles were developed. Factor analysis reduced these indicators into five common factors, followed by K-means++ clustering to categorise vehicles into risk groups. The entropy weight method calculated risk scores, determining risk levels. The model identified 7.7% of cargo vehicles as high-risk and .0% as moderately high-risk, and 7.7% of passenger vehicles as high-risk and .08% as moderately high-risk. Validation using rescue events per 0,000 vehicles (RM) from a Guangdong Province accident database, due to limited crash data availability, confirmed consistency with model-assigned risk levels, supporting targeted safety interventions.
Ključne riječi
driving risk classification; driving risk features; vehicle user profile; freeway toll data; dimensionality reduction
Hrčak ID:
348614
URI
Datum izdavanja:
29.6.2026.
Posjeta: 0 *