当前位置: X-MOL 学术Journal of Transportation Safety & Security › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Real-time crash prediction for a long low-traffic volume corridor using corrected-impurity importance and semi-parametric generalized additive model
Journal of Transportation Safety & Security ( IF 2.825 ) Pub Date : 2021-03-25 , DOI: 10.1080/19439962.2021.1898069
Arash Khoda Bakhshi 1 , Mohamed M. Ahmed 1
Affiliation  

Abstract

Real-time risk assessment studies have investigated a limited length of corridors. However, the necessity of assessing the safety performance of Connected Vehicles (CVs) requires looking into an entire corridor. Aligned with the CV Pilot Program on 402-miles Interstate-80 in Wyoming, this study serves as a baseline to quantify the safety performance of the corridor during CV pre-deployment. Real-time traffic-related predictors were characterized to capture the spatial variation in traffic characteristics, both longitudinally and laterally. Nine Crash Prediction Models (CPMs) were conducted following the matched-case control design within two main parts. First, important predictors were detected using three feature selection techniques; Corrected-Impurity Importance (CII), Mean Decrease Impurity, and Mean Decrease Accuracy. Secondly, for each of the three sets of selected features, three different Logistic Regression models were developed; the Generalized Additive Model (GAM), Generalized Linear Model, and Generalized Nonlinear Model. The combined GAM and CII outperformed other CPMs by obtaining minimum error, maximum prediction performance, and detecting a larger number of significant predictors, which would enhance the safety performance measurement of the few numbers of CVs by comparing CVs pre- to post-deployment. Findings showed that investigating individual lanes is beneficial to comprehend crash patterns on corridors with comparatively less traffic volume.



中文翻译:

使用校正杂质重要性和半参数广义加性模型对长低交通量走廊进行实时碰撞预测

摘要

实时风险评估研究调查了有限长度的走廊。然而,评估联网车辆 (CV) 安全性能的必要性需要调查整个走廊。本研究与怀俄明州 402 英里 80 号州际公路上的 CV 试点计划相一致,可作为量化 CV 预部署期间走廊安全性能的基准。实时交通相关预测器的特征是捕捉纵向和横向交通特征的空间变化。在两个主要部分的匹配案例控制设计之后,进行了九个碰撞预测模型 (CPM)。首先,使用三种特征选择技术检测重要的预测变量;校正杂质重要性 (CII)、平均减少杂质和平均减少准确度。第二,对于三组选定特征中的每一个,都开发了三种不同的逻辑回归模型;广义加法模型 (GAM)、广义线性模型和广义非线性模型。组合的 GAM 和 CII 通过获得最小误差、最大预测性能和检测大量重要预测因子来优于其他 CPM,这将通过比较部署前和部署后的 CV 来增强对少数 CV 的安全性能测量。研究结果表明,调查个别车道有助于了解交通量相对较少的走廊上的碰撞模式。组合的 GAM 和 CII 通过获得最小误差、最大预测性能和检测大量重要预测因子来优于其他 CPM,这将通过比较部署前和部署后的 CV 来增强对少数 CV 的安全性能测量。研究结果表明,调查个别车道有助于了解交通量相对较少的走廊上的碰撞模式。组合的 GAM 和 CII 通过获得最小误差、最大预测性能和检测大量重要预测因子来优于其他 CPM,这将通过比较部署前和部署后的 CV 来增强对少数 CV 的安全性能测量。研究结果表明,调查个别车道有助于了解交通量相对较少的走廊上的碰撞模式。

更新日期:2021-03-25
down
wechat
bug