Research on Multi-Classification Prediction of Traffic Accident Severity on Mountainous Expressways

Authors

WANG Hao, Shandong Hi-Speed Company Limited , Jinan , Shandong 250031 , ChinaFollow
YAN Jie, Shandong Transportation Research Institute , Jinan , Shandong 250031 , ChinaFollow
GUO Jianmin, Shandong Hi-Speed Company Limited , Jinan , Shandong 250031 , China
ZHANG Yu, Shandong Transportation Research Institute , Jinan , Shandong 250031 , China
SUN Chengji, Shandong Hi-Speed Company Limited , Jinan , Shandong 250031 , China

Corresponding Author

闫杰，男，硕士，助理工程师.E-mail：yanjie@sdjtky.cn

Abstract

To enhance the safety level of mountainous expressways and establish an accurate and effective prediction model for traffic accident severity,this study analyzed 2 484 traffic accidents on mountainous expressways in Chongqing from 2010 to 2016.A total of 17 influencing factors were selected from four aspects:human,vehicle,road,and environment,to serve as explanatory variables.Partial proportional odds model,random forest algorithm,and XGBoost algorithm were used to construct multi-class prediction models for traffic accident severity.The model performance was evaluated using the confusion matrix,accuracy,and minority class recall rate.The results show that the XGBoost model achieves the highest prediction accuracy in multi-class prediction of traffic accident severity on mountainous highways.The overall accuracy rate of the XGBoost model is 69.58%,with a recall rate for severe accidents of 61.11%.These figures are significantly higher than those of the partial proportional odds model and the random forest algorithm.Furthermore,the absence of nighttime lighting,involvement of large vehicles,and bridge segments were identified as strong contributing factors in both the partial proportional odds model and the XGBoost model.Specifically,the probability of severe accidents occurring on bridge segments is 2.649 times higher than on other road segments.

Publication Date

8-15-2025

DOI

10.14048/j.issn.1671-2579.2025.04.025

First Page

203

Last Page

210

Submission Date

August 2025

Recommended Citation

Hao, WANG; Jie, YAN; Jianmin, GUO; Yu, ZHANG; and Chengji, SUN (2025) "Research on Multi-Classification Prediction of Traffic Accident Severity on Mountainous Expressways," Journal of China & Foreign Highway: Vol. 45: Iss. 4, Article 25.
DOI: 10.14048/j.issn.1671-2579.2025.04.025
Available at: https://zwgl1980.csust.edu.cn/journal/vol45/iss4/25

Reference

[1]邱文利,杨海峰,张少波,等.基于改进 Apriori算法的高速公 路 交 通 事 故 关 联 分 析 [J].中 外 公 路,2024,44(3):227-235.QIU Wenli,YANG Haifeng,ZHANG Shaobo,et al.Correlation analysis of highway traffic accidents based on improved apriori algorithm [J].Journal of China & Foreign Highway,2024,44(3):227-235.
[2]CHEN Y,WANG X H,ZHANG X B,et al.Experimental study on driver ’s mental load in hairpin curves of mountainous highway [J].Transport,2023,38(3):127-138.
[3]陈莹,王晓辉,张晓波,等.山区公路回头曲线的车道偏移行为与自由行驶轨迹模型 [J].交通运输工程学报,2022,22(4):382-395.CHEN Ying,WANG Xiaohui,ZHANG Xiaobo,et al.Lane offset behavior and free driving trajectory model of hairpin curves of mountain roads [J].Journal of Traffic and Transportation Engineering,2022,22(4):382-395.
[4]杨昌凤,余蜀予.基于施工及救援因素的艰险山区公路路线方案研究 [J].中外公路,2023,43(5):273-276.YANG Changfeng,YU Shuyu.Research on route scheme of highway in difficult and dangerous mountainous area based on construction and rescue factors [J].Journal of China & Foreign Highway,2023,43(5):273-276.
[5]SHANGGUAN Q Q,WANG J H,FU T,et al.An empirical investigation of driver car-following risk evolution using naturistic driving data and random parameters multinomial logit model with heterogeneity in means and variances [J].Analytic Methods in Accident Research,2023,38:100265.
[6]YAN J,ZENG S,TIAN B J,et al.Relationship between highway geometric characteristics and accident risk:A multilayer perceptron model (MLP ) approach [J].Sustainability,2023,15(3):1893.
[7]YAKAR F.Identification of accident-prone road sections by using relative frequency method [J].PROMET - Traffic&Transportation,2015,27(6):539-547.
[8]吕能超,王玉刚,周颖,等.道路交通安全分析与评价方法综述 [J].中国公路学报,2023,36(4):183-201.LYU Nengchao,WANG Yugang,ZHOU Ying,et al.Review of road traffic safety analysis and evaluation methods [J].China Journal of Highway and Transport,2023,36(4):183-201.
[9]戢晓峰,吴亚欣,袁华智,等.二级公路交通流特征对事故严重程度的影响 [J].中国公路学报,2020,33(2):135-145.JI Xiaofeng,WU Yaxin,YUAN Huazhi,et al.Influences of traffic flow characteristics on accident severity on secondary roads [J].China Journal of Highway and Transport,2020,33(2):135-145.
[10]胡骥,闫章存,卢小钊,等.基于有序 Logit与Probit模型的交通事故严重性影响因素分析 [J].安全与环境学报,2018,18(3):836-843.HU Ji,YAN Zhangcun,LU Xiaozhao,et al.Analysis for the influential factors of the accident severity based on the ordinal Logit and Probit models [J].Journal of Safety and Environment,2018,18(3):836-843.
[11]ABEGAZ T,BERHANE Y,WORKU A,et al.Effects of excessive speeding and falling asleep while driving on crash injury severity in Ethiopia:A generalized ordered logit model analysis [J].Accident Analysis & Prevention,2014,71:15-21.
[12]何庆龄,裴玉龙,刘静,等.基于 WOA-LSSVM 的城市道路交通事故严重度识别 [J].中国安全生产科学技术,2023,19(9):176-182.HE Qingling,PEI Yulong,LIU Jing,et al.Recognition of urban road traffic accident severity based on WOA-LSSVM [J].Journal of Safety Science and Technology,2023,19(9):176-182.
[13]杨文臣,周燕宁,田毕江,等.基于聚类分析和 SVM的二级公路交通事故严重度预测 [J].中国安全科学学报,2022,32(5):163-169.YANG Wenchen,ZHOU Yanning,TIAN Bijiang,et al.Traffic accident severity prediction for secondary highways based on cluster analysis and SVM model [J].China Safety Science Journal,2022,32(5):163-169.
[14]PARSA A B,MOVAHEDI A,TAGHIPOUR H,et al.Toward safer highways,application of XGBoost and SHAP for real-time accident detection and feature analysis [J].Accident Analysis & Prevention,2020,136:105405.
[15]杨文臣,谢碧珊,房锐,等.山区双车道公路机动车碰撞事故严重度致因比较分析与预测 [J].交通运输系统工程与信息,2021,21(1):190-195.YANG Wenchen,XIE Bishan,FANG Rui,et al.Comparative analysis and prediction of motor vehicle crash severity on mountainous two-lane highways [J].Journal of Transportation Systems Engineering and Information Technology,2021,21(1):190-195.
[16]田引安.山区崩积体条件下互通式立交设置分析 [J].中外公路,2023,43(6):345-350.TIAN Yin ’an.Analysis of interchange setting under condition of mountain eolluvial deposit [J].Journal of China & Foreign Highway,2023,43(6):345-350.
[17]胡立伟,吕一帆,赵雪亭,等.基于数据驱动的交通事故伤害程度影响因素及其耦合关系研究 [J].交通运输系统工程与信息,2022,22(5):117-124,134.HU Liwei,LYU Yifan,ZHAO Xueting,et al.Influence factors and coupling relationship of traffic accident injury degree based on a data-driven approach [J].Journal of Transportation Systems Engineering and Information Technology,2022,22(5):117-124,134.
[18]吴建清,张子毅,王钰博,等.考虑多模态数据的重载货车危险驾驶行为识别方法 [J].交通运输系统工程与信息,2024,24(2):63-75.WU Jianqing,ZHANG Ziyi,WANG Yubo,et al.Method for identifying dangerous driving behaviors in heavy-duty trucks based on multi-modal data [J].Journal of Transportation Systems Engineering and Information Technology,2024,24(2):63-75.
[19]高雪林,汤厚骏,沈佳平,等.基于 XGBoost 的高速公路事故类型及严重程度预测方法 [J].交通信息与安全,2023,41(4):55-63.GAO Xuelin,TANG Houjun,SHEN Jiaping,et al.A method for predicting the type and severity of freeway accidents based on XGBoost [J].Journal of Transport Information and Safety,2023,41(4):55-63.
[20]严远亭,朱原玮,吴增宝,等.构造性覆盖算法的 SMOTE过采样方法 [J].计算机科学与探索,2020,14(6):975-984.YAN Yuanting,ZHU Yuanwei,WU Zengbao,et al.Constructive covering algorithm-based SMOTE over-sampling method [J].Journal of Frontiers of Computer Science and Technology,2020,14(6):975-984.