Real-time crash risk prediction in freeway tunnels considering features interaction and unobserved heterogeneity: A two-stage deep learning modeling framework

IF 12.5 1区 工程技术 Q1 PUBLIC, ENVIRONMENTAL & OCCUPATIONAL HEALTH
Jieling Jin , Helai Huang , Chen Yuan , Ye Li , Guoqing Zou , Hongli Xue
{"title":"Real-time crash risk prediction in freeway tunnels considering features interaction and unobserved heterogeneity: A two-stage deep learning modeling framework","authors":"Jieling Jin ,&nbsp;Helai Huang ,&nbsp;Chen Yuan ,&nbsp;Ye Li ,&nbsp;Guoqing Zou ,&nbsp;Hongli Xue","doi":"10.1016/j.amar.2023.100306","DOIUrl":null,"url":null,"abstract":"<div><p>Real-time prediction of crash risk is an effective method for enhancing traffic safety, but it is not fully explored in freeway tunnels. A two-stage deep learning modeling framework comprising a preliminary exploration stage and a prediction and analysis stage is proposed for real-time crash risk prediction in freeway tunnels. A random parameters logit model with heterogeneity in means and variances is used in the preliminary exploration stage to investigate the unobserved heterogeneity and influence mechanism of precursors on real-time crash risk. In the prediction and analysis stage, a random deep and cross network model considering feature interactions and unobserved heterogeneities is developed to predict and analyze real-time crash risk, which is interpreted by the shapley additive explanations approach. The multi-source fusion dataset, collected from the Caltrans performance measurement system and the weather information website, is used to validate the proposed framework for exploring real-time crash risk in freeway tunnels. Results reveal that: (1) the random parameters logit model with heterogeneity in means and variances outperforms the traditional logit model in terms of the model fitting, providing a reference for deep learning modeling that may be able to improve model performance by addressing heterogeneity; (2) the important crash precursors such as the average difference in speed between detectors of tunnel entrance and exit are discovered based on the marginal effect analysis of the random parameters logit model with heterogeneity in means and variances; (3) the random deep and cross network model yields the best prediction performance compared to its counterparts (some other data-driven models), demonstrating the superior performance of deep learning models for real-time risk prediction tasks. It also indicates that considering feature interaction and heterogeneity in deep learning modeling can improve prediction performance; and (4) the important precursors found in the random deep and cross network model using the shapley additive explanations approach are close to those discovered in the statistical model, indicating that the proposed deep learning model can capture the similar effects of precursors as the statistical models, and the precursor interactions and heterogeneities also can be observed by the shapley additive explanations approach.</p></div>","PeriodicalId":47520,"journal":{"name":"Analytic Methods in Accident Research","volume":null,"pages":null},"PeriodicalIF":12.5000,"publicationDate":"2023-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Analytic Methods in Accident Research","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2213665723000416","RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"PUBLIC, ENVIRONMENTAL & OCCUPATIONAL HEALTH","Score":null,"Total":0}
引用次数: 0

Abstract

Real-time prediction of crash risk is an effective method for enhancing traffic safety, but it is not fully explored in freeway tunnels. A two-stage deep learning modeling framework comprising a preliminary exploration stage and a prediction and analysis stage is proposed for real-time crash risk prediction in freeway tunnels. A random parameters logit model with heterogeneity in means and variances is used in the preliminary exploration stage to investigate the unobserved heterogeneity and influence mechanism of precursors on real-time crash risk. In the prediction and analysis stage, a random deep and cross network model considering feature interactions and unobserved heterogeneities is developed to predict and analyze real-time crash risk, which is interpreted by the shapley additive explanations approach. The multi-source fusion dataset, collected from the Caltrans performance measurement system and the weather information website, is used to validate the proposed framework for exploring real-time crash risk in freeway tunnels. Results reveal that: (1) the random parameters logit model with heterogeneity in means and variances outperforms the traditional logit model in terms of the model fitting, providing a reference for deep learning modeling that may be able to improve model performance by addressing heterogeneity; (2) the important crash precursors such as the average difference in speed between detectors of tunnel entrance and exit are discovered based on the marginal effect analysis of the random parameters logit model with heterogeneity in means and variances; (3) the random deep and cross network model yields the best prediction performance compared to its counterparts (some other data-driven models), demonstrating the superior performance of deep learning models for real-time risk prediction tasks. It also indicates that considering feature interaction and heterogeneity in deep learning modeling can improve prediction performance; and (4) the important precursors found in the random deep and cross network model using the shapley additive explanations approach are close to those discovered in the statistical model, indicating that the proposed deep learning model can capture the similar effects of precursors as the statistical models, and the precursor interactions and heterogeneities also can be observed by the shapley additive explanations approach.

考虑特征交互和未观察异质性的高速公路隧道实时碰撞风险预测:一个两阶段深度学习建模框架
碰撞风险实时预测是提高交通安全的有效手段,但在高速公路隧道中尚未得到充分的研究。针对高速公路隧道碰撞风险的实时预测,提出了一种包括初步探索阶段和预测分析阶段的两阶段深度学习建模框架。在初步探索阶段,采用均值和方差均具有异质性的随机参数logit模型,研究了前驱体对实时崩溃风险的未观测异质性及其影响机制。在预测分析阶段,采用shapley加性解释方法,建立了考虑特征相互作用和不可观测异质性的随机深度交叉网络模型,对实时碰撞风险进行预测分析。从Caltrans性能测量系统和天气信息网站收集的多源融合数据集用于验证所提出的框架,以探索高速公路隧道的实时碰撞风险。结果表明:(1)均值和方差均存在异质性的随机参数logit模型在模型拟合方面优于传统的logit模型,为深度学习建模提供了参考,可以通过解决异质性来提高模型的性能;(2)基于均值和方差均非均匀的随机参数logit模型的边际效应分析,发现了隧道出入口探测器速度平均差等重要的碰撞前兆;(3)与其他数据驱动模型相比,随机深度和跨网络模型的预测性能最好,表明深度学习模型在实时风险预测任务中的优越性能。研究表明,在深度学习建模中考虑特征交互和异质性可以提高预测性能;(4)使用shapley加性解释方法在随机深度和交叉网络模型中发现的重要前体与统计模型中发现的重要前体接近,表明所提出的深度学习模型可以捕捉到与统计模型相似的前体效果,并且shapley加性解释方法也可以观察到前体的相互作用和异质性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
CiteScore
22.10
自引率
34.10%
发文量
35
审稿时长
24 days
期刊介绍: Analytic Methods in Accident Research is a journal that publishes articles related to the development and application of advanced statistical and econometric methods in studying vehicle crashes and other accidents. The journal aims to demonstrate how these innovative approaches can provide new insights into the factors influencing the occurrence and severity of accidents, thereby offering guidance for implementing appropriate preventive measures. While the journal primarily focuses on the analytic approach, it also accepts articles covering various aspects of transportation safety (such as road, pedestrian, air, rail, and water safety), construction safety, and other areas where human behavior, machine failures, or system failures lead to property damage or bodily harm.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信