Exploring the influential factors of roadway departure crashes on rural two-lane highways with logit model and association rules mining

دسته: , تاریخ انتشار: 4 اردیبهشت 1400تعداد بازدید: 354
قیمت محصول


جزئیات بیشتر



پایگاه داده

نشریه الزویر

نوع نگارش مقاله

مقاله پژوهشی


scopus – master journals – JCR

ایمپکت فاکتور

۴٫۲۷۶ در سال ۲۰۲۰

شاخص H_index

۲۶ در سال ۲۰۲۱

شاخص SJR

۰٫۹۰۱ در سال ۲۰۲۰

شاخص Quartile (چارک)

Q1 در سال ۲۰۲۰

مدل مفهومی








قوانین استفاده

خرید محصول توسط کلیه کارت های شتاب امکان پذیر است و بلافاصله پس از خرید، لینک دانلود محصول در اختیار شما قرار خواهد گرفت و هر گونه فروش در سایت های دیگر قابل پیگیری خواهد بود.

توضیحات مختصر محصول
Exploring the influential factors of roadway departure crashes on rural two-lane highways with logit model and association rules mining

فهرست مطالب مقاله:


Roadway departure (RwD)  crashes are  a major contributor of rural two-lane (R2L) highway       ۲۸ crashes and fatalities. For  targeted reduction of  crashes and fatalities due to roadway       ۲۹ departure, a thorough understanding of factors associated with RwD  crashes is necessary.      ۳۰

This  study quantitatively assessed the available pre-crash factors that might influence the vehicle and driver-related characteristics of  ۱۲۲,۹۷۸ crashes that occurred in  Louisiana      

RwD crashes by developing a logit model comparing roadway, crash environment, and the       

بخشی از متن مقاله:
  1. Introduction

A roadway departure (RwD) crash is a non-intersection crash, which occurs after a vehicle crosses an edge line  or a cen-

54         terline, or otherwise leaves the traveled roadway (Federal Highway Administration, 2017a). RwD crashes are  the result of

55         drivers running off  the road to  the right, crossing the centerline/median into an  oncoming lane of  traffic (head-on or

56         opposite-direction-sideswipe crashes), or running off the road to  the left.  Vehicles running off the road may also  involve a

57         rollover, an  immersion, or the hitting of a fixed  object. The  FHWA mentions four  key  reasons for  roadway departure from

58          the drivers’ perspective – roadway condition, collision avoidance, vehicle component failure, and driver error (FHWA, 2019).

59         Because vehicles involved in  RwD  crashes often end up  hitting moving vehicles or  fixed  rigid structures  (bridges, poles,

60         guardrails, etc.),  the outcome of RwD crashes tends to  be  severe (see  Fig. 1).

61                Roadway departure (RwD)  crashes are  considered to  be  a major contributor of highway fatalities in  the United States.

62         During 2015–۲۰۱۷, more  than  half   of  all   roadway  fatalities occurred due  to   roadway  departure  (Federal Highway

63         Administration, 2017a). RwD crashes are  a serious concern in the Louisiana State, specifically on rural two-lane (R2L) high-

64          ways. According to the Louisiana crash data, between 2005 and 2017, 29.5  percent of all non-intersection crashes are  caused

65        by roadway departure on the state-controlled highways (LADOTD, n.d.).  RwD crashes on the R2L highways consisted of 72.2

66         percent of all R2L non-intersection crashes over  the course of thirteen years. In the same period, 79.7  percent of total fatal

67         non-intersection crashes (4,903 of 6,151) were reported as  having been caused by  the roadway departure, including 37.4

68         percent from R2L highways. The  general descriptive statistics indicate that RwD crashes require serious attention.

69                National transportation agencies have identified lowering the frequency of roadway departure crashes as a national pri-

70         ority (AASHTO, 2008; Julian,  ۲۰۱۳). To prevent RwD crashes by  keeping vehicles on  the roadway, the FHWA and AASHTO

71          (American Association of State Highway Transportation Officials) recommended several countermeasures, such as – pave-

72         ment friction, alerting drivers with rumble strips, enhancing delineation along horizontal curves, and improving nighttime

73        visibility, etc.  (AASHTO, 2008; Federal Highway Administration, 2017a). In line  with the nationwide urgency to  cut  down

74        RwD crashes, Louisiana Department of Transportation and Development (DOTD) also  reported preventing RwD crashes as

75        one  of the top  priorities in  obtaining the goal  of halving traffic fatalities and severe injuries from 2009 to  ۲۰۳۰ (LADOTD,

76         ۲۰۱۸). The Louisiana DOTD has  already implemented several countermeasures on a large scale in recent years, notably cen-

77         terline rumble strips and shoulder rumble strips on  R2L highways. However, a  data-driven approach with an  improved

78         understanding of the multitude of factors associated with the RwD crash is required for  the application of safety counter-

79         measures aiming towards its  targeted reduction and prevention.

80               The approach of this study is twofold. First,  the research team utilized a conventional binary logistic regression model to

81         analyze roadway, driver, vehicle, crash and environmental characteristics from crash data of  thirteen years. In  the logit

82         model, the crashes essentially form one  element of the binary outcome of a crash (RwD  versus non-RwD) to estimate the

83         strength of association each crash characteristic carries in the occurrence of RwD crashes. This prediction model also  helps

84        to  estimate the probability of an  RwD crash as a function of a specified group of characteristics.

85                Second, aiming at gaining more knowledge on the associative contributing factors, we  applied ‘Association Rule Mining’

۸۶        (ARM) – a non-parametric unsupervised data mining algorithm – that offers analysts the flexibility to explore interconnec-

87         tions among factors without prior knowledge of them. Widely used in business disciplines, this method has  been popular

88         among transportation safety researchers. Pande and Abdel-Aty (2009) suggested that ARM could be very  useful to uncover

89         unknown patterns in the crash data obtained from large jurisdictions and potentially be  a decision support tool  for  traffic

90         safety administrators. The ability of this technique in detecting interdependencies among crash factors has  been reiterated

91        in a number of studies in the last  decade, especially in recent years (e.g.  Das  et al., 2020a, 2018b; Weng et al., 2016). We

92         utilized this data mining tool  to  identify patterns of  crashes that are  related to  the selected key  contributing  factors of

93        RwD  crashes from the logit   model and to  demonstrate how interconnections of  multiple  crash contributing  factors of

94        RwD crashes can  be  explored further.


نمایش بیشتر
دیدگاه های کاربران
دیدگاهتان را با ما درمیان بگذارید
تعداد دیدگاه : 0 امتیاز کلی : 0.0 توصیه خرید : 0 نفر
بر اساس 0 خرید

هیچ دیدگاهی برای این محصول نوشته نشده است.

لطفا پیش از ارسال نظر، خلاصه قوانین زیر را مطالعه کنید: فارسی بنویسید و از کیبورد فارسی استفاده کنید. بهتر است از فضای خالی (Space) بیش‌از‌حدِ معمول، شکلک یا ایموجی استفاده نکنید و از کشیدن حروف یا کلمات با صفحه‌کلید بپرهیزید. نظرات خود را براساس تجربه و استفاده‌ی عملی و با دقت به نکات فنی ارسال کنید؛ بدون تعصب به محصول خاص، مزایا و معایب را بازگو کنید و بهتر است از ارسال نظرات چندکلمه‌‌ای خودداری کنید.  

اولین کسی باشید که دیدگاهی می نویسد “Exploring the influential factors of roadway departure crashes on rural two-lane highways with logit model and association rules mining”

نشانی ایمیل شما منتشر نخواهد شد. بخش‌های موردنیاز علامت‌گذاری شده‌اند *

قیمت محصول