This study develops new real-time freeway rear-end crash potential predictors using support vector machine(SVM) technique. The relationship between rear-end crash occurrences and traffic conditions were explored using...This study develops new real-time freeway rear-end crash potential predictors using support vector machine(SVM) technique. The relationship between rear-end crash occurrences and traffic conditions were explored using historical loop detector data from Interstate-894 in Milwaukee, Wisconsin, USA. The extracted loop detection data were aggregated over different stations and time intervals to produce explanatory features. A feature selection process, which addresses the interaction between SVM classifiers and explanatory features, was adopted to identify the features that significantly influence rear-end crashes. Afterwards, the identified significant explanatory features over three separate time levels were used to train three SVM models. In the end, the multi-layer perceptron(MLP) artificial neural network models were used as benchmarks to evaluate the performance of SVM models. The results show that the proposed feature selection procedure greatly enhances the accuracy and generalization capability of SVM models. Moreover, the optimal SVM classifier achieves 81.1% overall prediction precision rate. In comparison with MLP artificial neural networks, SVM models provide better results in terms of crash prediction accuracy and false positive rate, which confirms the superior performance of SVM technique in rear-end crash potential prediction analysis.展开更多
Rear-end crashes are among the most common crash types at signalized intersections. To examine the risk factors for the occurrence of this crash type, this study involved the analysis of nine years of intersection cra...Rear-end crashes are among the most common crash types at signalized intersections. To examine the risk factors for the occurrence of this crash type, this study involved the analysis of nine years of intersection crash records in the state of Wyoming. With that, the contributing factors related to crash, driver, environmental, and roadway characteristics, including pavement surface friction, were investigated. A binomial logistic regression modeling approach was applied to achieve the study’s objective. The results showed that three factors related to crash and driver’s attributes (commercial vehicle involvement, speeding, and driver’s age) and four factors related to environmental and roadway characteristics (lighting, weather conditions, area type, whether urban or rural and pavement friction) are associated with the risk of rear-end crash occurrence at signalized intersections. This study provides insights into the mitigation measures to implement concerning rear-end crashes at signalized intersections.展开更多
深入分析交通事故数据可以为规避事故发生、降低事故严重程度提供重要理论依据,然而,在事故数据采集、传输、存储过程中往往会产生数据缺失,导致统计分析结果的准确性下降、模型的误判风险上升。本文以芝加哥2016—2021年的101452条追...深入分析交通事故数据可以为规避事故发生、降低事故严重程度提供重要理论依据,然而,在事故数据采集、传输、存储过程中往往会产生数据缺失,导致统计分析结果的准确性下降、模型的误判风险上升。本文以芝加哥2016—2021年的101452条追尾事故数据为研究对象,将原始数据按照7∶3随机分为训练集和测试集。在训练集数据上,利用生成式插补网络(Generative Adversarial Imputation Network,GAIN)实现对缺失数据的填补。为对比不同数据填补方法的效果,同时选择多重插补(Multiple Imputation by Chained Equations,MICE)算法、期望最大化(Expectation Maximization,EM)填充算法、缺失森林(MissForest)算法和K最近邻(K-Nearest Neighbor,KNN)算法对同一数据集进行数据填补,并基于填补前后变量方差变化比较不同填补算法对数据变异性的影响。在完成数据填补的基础上,构建LightGBM三分类事故严重程度影响因素分析模型。使用原始训练集数据,以及填补后的训练集数据分别训练模型,并使用未经填补的测试集数据检验模型预测效果。结果表明,经缺失值填补后,模型性能得到一定改善,使用GAIN填补数据集训练的模型,相较于原始数据训练的模型,准确率提高了6.84%,F1提高了4.61%,AUC(Area Under the Curve)提高了10.09%,且改善效果优于其他4种填补方法。展开更多
Vehicles involved in traffic accidents generally experience divergent vehicle motion,which causes severe damage.This paper presents a self-learning drift-control method for the purpose of stabilizing a vehicle’s yaw ...Vehicles involved in traffic accidents generally experience divergent vehicle motion,which causes severe damage.This paper presents a self-learning drift-control method for the purpose of stabilizing a vehicle’s yaw motions after a high-speed rear-end collision.The struck vehicle generally experiences substantial drifting and/or spinning after the collision,which is beyond the handling limit and difficult to control.Drift control of the struck vehicle along the original lane was investigated.The rear-end collision was treated as a set of impact forces,and the three-dimensional non-linear dynamic responses of the vehicle were considered in the drift control.A multi-layer perception neural network was trained as a deterministic control policy using the actor-critic reinforcement learning framework.The control policy was iteratively updated,initiating from a random parameterized policy.The results show that the self-learning controller gained the ability to eliminate unstable vehicle motion after data-driven training of about 60,000 iterations.The controlled struck vehicle was also able to drift back to its original lane in a variety of rear-end collision scenarios,which could significantly reduce the risk of a second collision in traffic.展开更多
为实现急弯路段的追尾碰撞风险主动防控,提出了一种基于多源数据融合的追尾冲突动态预测方法。首先,基于无人机、毫米波雷达等采集的车辆运行数据,提出了适用于急弯路段交通流特征的追尾冲突判别模型及冲突等级阈值划分标准,分析了急弯...为实现急弯路段的追尾碰撞风险主动防控,提出了一种基于多源数据融合的追尾冲突动态预测方法。首先,基于无人机、毫米波雷达等采集的车辆运行数据,提出了适用于急弯路段交通流特征的追尾冲突判别模型及冲突等级阈值划分标准,分析了急弯路段的追尾冲突空间分布特征。然后,筛选车型、大车比率、断面速度差等13个交通流特征指标作为输入变量,以粒子群算法为基础,分别构建了其与BP神经网络、随机森林、支持向量机算法的追尾冲突动态组合预测模型,并根据混淆矩阵和曲线下面积评估各模型的预测性能,利用黑箱解释方法分析冲突发生概率的显著性影响因素及影响程度。结果表明:相较于平直或一般弯道路段,急弯路段的追尾冲突TTC(Time to Collision)值更小,出弯缓和曲线段冲突更为严重,且弯道内侧碰撞风险最高;粒子群-随机森林模型的追尾冲突预测性能最佳,灵敏度达90.70%;急弯路段追尾冲突受车辆平均车头间距的影响程度最大,当平均车头间距为25 m左右时,冲突发生概率最小,向心加速度均值、速度均值等因素亦对其有显著影响。展开更多
基金Project(BK20160685)supported by the Science Foundation of Jiangsu Province,ChinaProject(61620106002)supported by the National Natural Science Foundation of China
文摘This study develops new real-time freeway rear-end crash potential predictors using support vector machine(SVM) technique. The relationship between rear-end crash occurrences and traffic conditions were explored using historical loop detector data from Interstate-894 in Milwaukee, Wisconsin, USA. The extracted loop detection data were aggregated over different stations and time intervals to produce explanatory features. A feature selection process, which addresses the interaction between SVM classifiers and explanatory features, was adopted to identify the features that significantly influence rear-end crashes. Afterwards, the identified significant explanatory features over three separate time levels were used to train three SVM models. In the end, the multi-layer perceptron(MLP) artificial neural network models were used as benchmarks to evaluate the performance of SVM models. The results show that the proposed feature selection procedure greatly enhances the accuracy and generalization capability of SVM models. Moreover, the optimal SVM classifier achieves 81.1% overall prediction precision rate. In comparison with MLP artificial neural networks, SVM models provide better results in terms of crash prediction accuracy and false positive rate, which confirms the superior performance of SVM technique in rear-end crash potential prediction analysis.
文摘Rear-end crashes are among the most common crash types at signalized intersections. To examine the risk factors for the occurrence of this crash type, this study involved the analysis of nine years of intersection crash records in the state of Wyoming. With that, the contributing factors related to crash, driver, environmental, and roadway characteristics, including pavement surface friction, were investigated. A binomial logistic regression modeling approach was applied to achieve the study’s objective. The results showed that three factors related to crash and driver’s attributes (commercial vehicle involvement, speeding, and driver’s age) and four factors related to environmental and roadway characteristics (lighting, weather conditions, area type, whether urban or rural and pavement friction) are associated with the risk of rear-end crash occurrence at signalized intersections. This study provides insights into the mitigation measures to implement concerning rear-end crashes at signalized intersections.
文摘深入分析交通事故数据可以为规避事故发生、降低事故严重程度提供重要理论依据,然而,在事故数据采集、传输、存储过程中往往会产生数据缺失,导致统计分析结果的准确性下降、模型的误判风险上升。本文以芝加哥2016—2021年的101452条追尾事故数据为研究对象,将原始数据按照7∶3随机分为训练集和测试集。在训练集数据上,利用生成式插补网络(Generative Adversarial Imputation Network,GAIN)实现对缺失数据的填补。为对比不同数据填补方法的效果,同时选择多重插补(Multiple Imputation by Chained Equations,MICE)算法、期望最大化(Expectation Maximization,EM)填充算法、缺失森林(MissForest)算法和K最近邻(K-Nearest Neighbor,KNN)算法对同一数据集进行数据填补,并基于填补前后变量方差变化比较不同填补算法对数据变异性的影响。在完成数据填补的基础上,构建LightGBM三分类事故严重程度影响因素分析模型。使用原始训练集数据,以及填补后的训练集数据分别训练模型,并使用未经填补的测试集数据检验模型预测效果。结果表明,经缺失值填补后,模型性能得到一定改善,使用GAIN填补数据集训练的模型,相较于原始数据训练的模型,准确率提高了6.84%,F1提高了4.61%,AUC(Area Under the Curve)提高了10.09%,且改善效果优于其他4种填补方法。
基金supported by International Science&Technology Cooperation Program of China(Grant No.2019YFE0100200)the National Natural Science Foundation of China(Grant No.51905483).This paper is also partially supported by Toyota.
文摘Vehicles involved in traffic accidents generally experience divergent vehicle motion,which causes severe damage.This paper presents a self-learning drift-control method for the purpose of stabilizing a vehicle’s yaw motions after a high-speed rear-end collision.The struck vehicle generally experiences substantial drifting and/or spinning after the collision,which is beyond the handling limit and difficult to control.Drift control of the struck vehicle along the original lane was investigated.The rear-end collision was treated as a set of impact forces,and the three-dimensional non-linear dynamic responses of the vehicle were considered in the drift control.A multi-layer perception neural network was trained as a deterministic control policy using the actor-critic reinforcement learning framework.The control policy was iteratively updated,initiating from a random parameterized policy.The results show that the self-learning controller gained the ability to eliminate unstable vehicle motion after data-driven training of about 60,000 iterations.The controlled struck vehicle was also able to drift back to its original lane in a variety of rear-end collision scenarios,which could significantly reduce the risk of a second collision in traffic.
文摘为实现急弯路段的追尾碰撞风险主动防控,提出了一种基于多源数据融合的追尾冲突动态预测方法。首先,基于无人机、毫米波雷达等采集的车辆运行数据,提出了适用于急弯路段交通流特征的追尾冲突判别模型及冲突等级阈值划分标准,分析了急弯路段的追尾冲突空间分布特征。然后,筛选车型、大车比率、断面速度差等13个交通流特征指标作为输入变量,以粒子群算法为基础,分别构建了其与BP神经网络、随机森林、支持向量机算法的追尾冲突动态组合预测模型,并根据混淆矩阵和曲线下面积评估各模型的预测性能,利用黑箱解释方法分析冲突发生概率的显著性影响因素及影响程度。结果表明:相较于平直或一般弯道路段,急弯路段的追尾冲突TTC(Time to Collision)值更小,出弯缓和曲线段冲突更为严重,且弯道内侧碰撞风险最高;粒子群-随机森林模型的追尾冲突预测性能最佳,灵敏度达90.70%;急弯路段追尾冲突受车辆平均车头间距的影响程度最大,当平均车头间距为25 m左右时,冲突发生概率最小,向心加速度均值、速度均值等因素亦对其有显著影响。
