SHAP-based convolutional neural network modeling for intersection crash severity on Thailand's highways

IF 3.2 Q3 TRANSPORTATION IATSS Research Pub Date : 2024-12-30 DOI:10.1016/j.iatssr.2024.12.003
Jirapon Sunkpho , Chamroeun Se , Warit Wipulanusat , Vatanavongs Ratanavaraha
{"title":"SHAP-based convolutional neural network modeling for intersection crash severity on Thailand's highways","authors":"Jirapon Sunkpho ,&nbsp;Chamroeun Se ,&nbsp;Warit Wipulanusat ,&nbsp;Vatanavongs Ratanavaraha","doi":"10.1016/j.iatssr.2024.12.003","DOIUrl":null,"url":null,"abstract":"<div><div>Intersection-related crashes on Thailand's highways pose a significant risk to road users, particularly motorcyclists. This study develops customized Convolutional Neural Network (CNN) models to classify the severity of intersection crashes and utilizes SHapley Additive exPlanations (SHAP) to interpret the models. The methodology involves using three years of crash data from Thailand's highways, covering the period from 2018 to 2020. Additionally, three CNN model variations were developed: a basic CNN, a CNN with dropout (CNN-D), and a CNN with both dropout and L2 regularization (CNN-DR). The results demonstrate the superior performance of the CNN-DR model in classifying crash severity for both motorcycle-related and nonmotorcycle-related intersection crashes. SHAP analysis reveals key factors influencing crash severity, including the year of the crash, with a clear distinction between pre-COVID-19 years (2018–2019) and the pandemic year (2020). Crash mechanisms, such as impacts with vehicles from adjacent approaches and rear-end collisions, are significant factors that increase the likelihood of serious crashes. The study also identifies the type of intersection, specifically curved intersections, T-intersections, and Y-intersections, as major determinants of crash severity, particularly for motorcycle-related crashes. Time-of-day analysis reveals early morning hours (00:00 to 5:59) as high-risk periods for nonmotorcycle-related crashes. Furthermore, the influence of highway types and vehicle involvement, such as regional secondary highways and the presence of trucks, is linked to the increased severity of motorcycle-related crashes. The insights derived from this study can guide road safety managers in implementing targeted interventions to reduce intersection crash severity on Thailand's highways.</div></div>","PeriodicalId":47059,"journal":{"name":"IATSS Research","volume":"49 1","pages":"Pages 27-41"},"PeriodicalIF":3.2000,"publicationDate":"2024-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IATSS Research","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0386111224000591","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"TRANSPORTATION","Score":null,"Total":0}
引用次数: 0

Abstract

Intersection-related crashes on Thailand's highways pose a significant risk to road users, particularly motorcyclists. This study develops customized Convolutional Neural Network (CNN) models to classify the severity of intersection crashes and utilizes SHapley Additive exPlanations (SHAP) to interpret the models. The methodology involves using three years of crash data from Thailand's highways, covering the period from 2018 to 2020. Additionally, three CNN model variations were developed: a basic CNN, a CNN with dropout (CNN-D), and a CNN with both dropout and L2 regularization (CNN-DR). The results demonstrate the superior performance of the CNN-DR model in classifying crash severity for both motorcycle-related and nonmotorcycle-related intersection crashes. SHAP analysis reveals key factors influencing crash severity, including the year of the crash, with a clear distinction between pre-COVID-19 years (2018–2019) and the pandemic year (2020). Crash mechanisms, such as impacts with vehicles from adjacent approaches and rear-end collisions, are significant factors that increase the likelihood of serious crashes. The study also identifies the type of intersection, specifically curved intersections, T-intersections, and Y-intersections, as major determinants of crash severity, particularly for motorcycle-related crashes. Time-of-day analysis reveals early morning hours (00:00 to 5:59) as high-risk periods for nonmotorcycle-related crashes. Furthermore, the influence of highway types and vehicle involvement, such as regional secondary highways and the presence of trucks, is linked to the increased severity of motorcycle-related crashes. The insights derived from this study can guide road safety managers in implementing targeted interventions to reduce intersection crash severity on Thailand's highways.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
求助全文
约1分钟内获得全文 去求助
来源期刊
IATSS Research
IATSS Research TRANSPORTATION-
CiteScore
6.40
自引率
6.20%
发文量
44
审稿时长
42 weeks
期刊介绍: First published in 1977 as an international journal sponsored by the International Association of Traffic and Safety Sciences, IATSS Research has contributed to the dissemination of interdisciplinary wisdom on ideal mobility, particularly in Asia. IATSS Research is an international refereed journal providing a platform for the exchange of scientific findings on transportation and safety across a wide range of academic fields, with particular emphasis on the links between scientific findings and practice in society and cultural contexts. IATSS Research welcomes submission of original research articles and reviews that satisfy the following conditions: 1.Relevant to transportation and safety, and the multiple impacts of transportation systems on security, human health, and the environment. 2.Contains important policy and practical implications based on scientific evidence in the applicable academic field. In addition to welcoming general submissions, IATSS Research occasionally plans and publishes special feature sections and special issues composed of invited articles addressing specific topics.
期刊最新文献
Critical conflict probability: A novel risk measure for quantifying intensity of crash risk at unsignalized intersections Analysis of land-use and POIs contributing to traffic accidents around intersections SHAP-based convolutional neural network modeling for intersection crash severity on Thailand's highways Road safety studies at micro, meso, and macroscopic levels: A systematic review Nudging drivers: The influence of innovative green-phase forewarning systems on drivers' start-up behavior at signalized intersections
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1