Contributing factors on the level of delay caused by crashes: a hybrid method of latent class analysis and XGBoost based SHAP algorithm

被引:5
|
作者
Wang, Zehao [1 ]
Jiao, Pengpeng [1 ]
Wang, Jianyu [1 ]
Luo, Wei [1 ]
Lu, Huapu [2 ]
机构
[1] Beijing Univ Civil Engn & Architecture, Beijing Key Lab Gen Aviat Technol, Beijing 100044, Peoples R China
[2] Tsinghua Univ, Inst Transportat Engn & Geomatics, Beijing, Peoples R China
关键词
Road crash; The level of delay caused by crashes (LDC); Unobserved heterogeneity; Latent class analysis; XGBoost based SHAP; DRIVER INJURY SEVERITY; CLASS CLUSTER-ANALYSIS; STATISTICAL-ANALYSIS; AUTOMATED VEHICLES; TRAFFIC ACCIDENTS; RANDOM PARAMETERS; TIME; RISK; MODEL; IMPACTS;
D O I
10.1080/19439962.2023.2189339
中图分类号
U [交通运输];
学科分类号
08 ; 0823 ;
摘要
Road crashes cause significant traffic delay and bring unnecessary financial losses. This study investigates the impact of contributing factors on the level of delay caused by crashes (LDC) using Texas crash data. To capture the unobserved heterogeneity, a latent class analysis (LCA) was first used to segment the whole dataset into several homogeneous clusters. Then, XGBoost based SHAP was developed on each cluster to identify the main contributing factors hidden in the latent classes. The interaction effects between the contributing factors were subsequently analyzed, including the effects between high importance features and between high and low importance features. The LCA results indicate that season is the main factor producing heterogeneity, hence the data were divided into four clusters. The main contributing factors and the interaction effects are different among the four clusters, as shown by the XGBoost based SHAP algorithm. For example, Sunrise_Sunset, Peak_hours and Crossing are the main contributing factors in Fall and Winter crash, whereas Traffic_Signal, Workday and Junction are the main contributing factors in Summer and Spring crash. The interaction effects of Highway and Zone are different in Fall and Winter crash. This study can provide insightful information for regulators to develop targeted policies in different seasons.
引用
收藏
页码:97 / 129
页数:33
相关论文
共 4 条
  • [1] Understanding key contributing factors on the severity of traffic violations by elderly drivers: a hybrid approach of latent class analysis and XGBoost based SHAP
    Sun, Zhiyuan
    Wang, Zhicheng
    Qi, Xin
    Wang, Duo
    Gu, Xin
    Wang, Jianyu
    Lu, Huapu
    Chen, Yanyan
    [J]. INTERNATIONAL JOURNAL OF INJURY CONTROL AND SAFETY PROMOTION, 2024, 31 (02) : 273 - 293
  • [2] Factors Affecting Single and Multivehicle Motorcycle Crashes: Insights from Day and Night Analysis Using XGBoost-SHAP Algorithm
    Wisutwattanasak, Panuwat
    Se, Chamroeun
    Champahom, Thanapong
    Kasemsri, Rattanaporn
    Jomnonkwao, Sajjakaj
    Ratanavaraha, Vatanavongs
    [J]. Big Data and Cognitive Computing, 2024, 8 (10)
  • [3] Investigating contributing factors to injury severity levels in crashes involving pedestrians and cyclists using latent class clustering analysis and mixed logit models
    Liu, Shaojie
    Lin, Zijing
    Fan, Wei
    [J]. JOURNAL OF TRANSPORTATION SAFETY & SECURITY, 2022, 14 (10) : 1674 - 1701
  • [4] Investigating risk factors associated with injury severity in highway crashes: A hybrid approach integrating two-step cluster analysis and latent class ordered regression model with covariates
    Luan, Siliang
    Jiang, Zhongtai
    Qu, Dayi
    Yang, Xiaoxia
    Meng, Fanyun
    [J]. ACCIDENT ANALYSIS AND PREVENTION, 2024, 208