Single-vehicle roadway departure crashes at rural two-lane highway curved segments:A diagnosis using pattern recognition  

作　　者：Ahmed Hossain Xiaoduan Sun Shahrin Islam Ashifur Rahman Subasish Das 

机构地区：[1]Department of Civil Engineering,University of Louisiana at Lafayette,Lafayette,LA 70504,USA [2]Department of Civil and Mineral Engineering,University of Toronto,Toronto,ON M5S 1A4,Canada [3]Louisiana Transportation Research Center,Baton Rouge,LA 70808,USA [4]College of Science of Engineering,Texas State University,601 University Drive,San Marcos,TX 78666-4684,USA

出　　处：《International Journal of Transportation Science and Technology》2024年第3期298-318,共21页交通科学与技术(英文)

摘　　要：Curved segments account for a disproportionately high proportion of fatal and serious injury crashes,with most of these crashes occurring on rural two-lane(R2L)highways.During the 10-year period from 2008 to 2017,a total of 1234 fatal single-vehicle roadway departure(SV-RwD)crashes occurred on R2L roads in Louisiana,out of which 635(51.5%)crashes occurred on curved segments.Therefore,it is critical to investigate the causes of SV-RwD crashes,specifically those that occur on curved segments.This study aimed to investigate the‘association knowledge’of the factors contributing to SV-RwD crashes on R2L curved segments in Louisiana using fatal and injury crash data collected from 2008 to 2017.The study utilized Cluster Correspondence Analysis(CCA),a robust joint dimen-sion reduction and clustering method for handling high-dimensionality and multicollinear-ity of crash data,to achieve this objective.Based on the cluster validation measures,the study identified five clusters with specific traits,including alcohol-impaired male drivers with no seatbelt usage,young(15–24 years old)female drivers’crash involvement in cloudy weather conditions,animal-involved crashes in rainy weather conditions,crashes occurring on hillcrest locations under cloudy weather conditions,and crashes in the dark with the presence of streetlights and higher traffic volume.Furthermore,young(15–24 years)female drivers were identified in most clusters,implying that this specific age group of female drivers requires special consideration when dealing with SV-RwD colli-sions on R2L curved segments.To improve safety on R2L curved segments,policymakers can use the findings of this study to develop targeted countermeasures.

关 键 词：Curved segment single-vehicle roadway departure(SV-RwD) Cluster correspondence analysis(CCA) Alcohol And seat-belt usage 

分 类 号：U49[交通运输工程—交通运输规划与管理]