基于 Logistic 回归模型的三线城市道路事故数据分析

根据乌鲁木齐市2006~2010年的交通事故统计资料,分别以城市道路中9类不同的交通事故形态为因变量,从道路设施、道路环境等方面选取了9个因素作为自变量,通过二项logistic模型进行事故形态分析,建立事故形态与9个影响因素间的线性相关模型,对模型参数进行了估计,并对模型的拟合程度、可靠性进行了分析,研究了所有自变量单独/组合等不同情况下对因变量的影响。再通过多项Logistic模型对不同道路条件下,各种形态的事故发生几率进行了预测,并与实际情况进行对比,检验了模型拟合效果。      

高速公路交通事故非线性负二项预测模型

以京港澳高速公路（G4）粤境北段3年发生的1 354起交通事故为研究对象,将基础数据根据路段长度一致、曲线半径一致和坡度一致划分路段单元对基础数据进行处理,从道路线形和环境条件2个方面选取13个自变量,分别采用负二项（Negative Binomial,NB）回归模型和非线性负二项（Nonlinear Negative Binomial,NNB）回归模型建立交通事故起数预测模型,根据模型的拟合优度和预测准确性对比分析负二项回归和非线性负二项回归模型的优劣,并找出影响交通事故起数的显著自变量,分析显著自变量对交通事故起数的影响程度。研究结果表明：无论采用上述何种路段划分方法,非线性负二项回归模型构建的交通事故起数预测模型均优于负二项回归模型;采用坡度一致划分方法明显优于路段长度一致和曲线半径一致划分方法,更适合应用于山区高速公路交通事故数预测研究;从显著变量相关性来看,路段长度、相邻路段坡度变化值、弯坡组合、曲率、是否存在隧道路段以及是否为易结冰和起雾路段均是非线性模型的显著影响因素。     

Influence of segment length on the fitness of multivariate crash prediction models applied to a Brazilian multilane highway

Road safety modeling enables the development of crash prediction models and the investigation of which factors contribute to crash occurrence. Developing multivariate response models is also valuable, but such models are currently under-exploited. Machine learning techniques, especially artificial neural networks (ANN), have been presented as possible alternatives. Furthermore, selecting a proper roadway segmentation is one of the first tasks in the standard crash modeling workflow. However, this is a challenging task, especially in terms of choosing a segment length. This article presents a study of the influence of segment length on the development of multivariate response models (i.e., three response variables: property damage only crashes, injured victims crashes, and fatal crashes). The models use ANN for a road segment of a Brazilian divided multilane highway. The highway to be modeled was divided into segments with 10 different fixed lengths. The model characterization included geometric and operational data available for the years from 2011 to 2017. The models were evaluated in terms of errors and by residual plot analysis. The 5-km segment of the northbound carriageway and the 4.5-km segment of the southbound carriageway presented the smallest errors and the highest values of R². The residual analyses confirmed the trend to improve the model with the greater segment lengths. This was clear by the residues' distribution around zero, except for the output “Fatal crashes”. The better performance of the longer segments models was expected because these models aggregate more crashes into one segment. The reduction of no crash observations also facilitated the improvement of the models' goodness-of-fit. The use of ANNs also revealed its potential value. However, it is still important to seek strategies to deal with the excess of zeros in fatal crashes; a problem that also occurs in the traditional statistical modeling process.     

Design of ANFIS networks using hybrid genetic and SVD methods for modeling and prediction of rubber engine mount stiffness

Genetic Algorithm (GA) and Singular Value Decomposition (SVD) are deployed for optimal design of both the Gaussian membership functions of antecedents and the vector of linear coefficients of consequents, respectively, of ANFIS networks. These networks are used for stiffness modelling and prediction of rubber engine mounts. The aim of such modelling is to show how the stiffness of an engine mount changes with variations in geometric parameters. It is demonstrated that SVD can be optimally used to find the vector of linear coefficients of conclusion parts using ANFIS (Adaptive Neuro-Fuzzy Inference Systems) models. In addition, the Gaussian membership functions in premise parts can be determined using a GA. In this study, the stiffness training data of 36 different bush type engine mounts were obtained using the finite element analysis (FEA).     

Modeling the accuracy of traffic crash prediction models

Crash forecasting enables safety planners to take appropriate actions before casualty or loss occurs. Identifying and analyzing the attributes influencing forecasting accuracy is of great importance in road crash forecasting. This study aims to model the forecasting accuracy of 31 provinces using their macroeconomic variables and road traffic indicators. Iran's road crashes throughout 2011–2018 are calibrated and cross-validated using the Holt-Winters (HW) forecasting method. The sensitivity of crash forecast reliability is studied by a regression model. The results suggested that the root mean square error (RMSE) of crash prediction increased among the provinces with higher and more variant average monthly crashes. On the contrary, the accuracy of crash prediction improved in provinces with higher per capita GDP, and higher traffic exposure. A 1% increase in crash variability, average historical crash count, GDP per capita, and traffic exposure, respectively, resulted in a 0.65%, 0.52%, −0.38%, and −0.13% change in the RMSE of forecasting. The addition of traffic exposure and macroeconomic factors significantly enhanced the model fit and improved the adjusted R-squared by 14% compared to the reduced model that only used the historical average and variability of crash count as the independent variables. The findings of this research suggest planners and policymakers should consider the notable influence of macroeconomic factors and traffic indicators on the crash forecasting accuracy.     

Predicting downgrade crash frequency with the random-parameters negative binomial model: Insights into the impacts of geometric variables on downgrade crashes in Wyoming

Road deaths, injuries and property damage place a huge burden on the economy of most nations. Wyoming has a high crash rate on mountain passes. The crash rates observed in the state is as a result of many factors mainly related to the challenging mountainous terrain in the state, which places extra burden on drivers in terms of requiring higher levels of alertness and driving skill. This study was conducted to investigate factors leading to crashes on Wyoming downgrades, with a focus on geometric variables. Traditionally, crash frequency analysis is conducted using count models such as Poisson or negative binomial models. However, factors that affect crash frequency are known to vary across observations. The use of a methodology that fails to take into account heterogeneity in observed and unobserved effects relating to roadway characteristics can lead to biased and inconsistent estimates. Inferences made from such parameter estimates may be misleading. This study employed the random-parameters negative binomial regression models to evaluate the impact of geometric variables on crash frequency. Five separate models were estimated for total, fatal/injury, property damage only (PDO), truck, and non-truck crash frequencies. Several geometric and traffic variables were found to influence the frequency of crashes on downgrades. These included segment length, vertical grade, shoulder width, lane width, presence of downgrade warning sign, vertical curve length, presence of a passing lane, percentage of trucks, number of lanes and AADT. The results suggest that segment length, lane width, presence of a passing lane, presence of a downgrade warning sign, vertical grade, and percentage of trucks are best modeled as random parameters. The findings of this study will provide transportation agencies with a better understanding of the impact of geometric variables on downgrade crashes.     

基于经验贝叶斯法的道路事故预测分析研究

传统事故预测模型存在对原始数据的序列性、分布性等方面高要求,以及预测精度的不足,利用经验贝叶斯法对先验信息（原始事故数据）进行调整,得到后验信息以形成更好的预测效果。就交通事故数据进行事前与事后累计统计分析,并对比其他预测模型证明经验贝叶斯法的预测结果更接近实际情形,基于经验贝叶斯法的此类模型可以提高小样本数据预测精度。     

基于干预分析技术的交通事故灰色预测模型研究

加强对交通事故预测技术的研究,以便根据交通事故未来趋势变化提出有针对性的预防措施。在北京市交通事故数据的基础上,提出利用干预分析技术对传统的灰色预测模型进行修正,提高在政策干预等特殊事件影响下交通事故的预测准确度,为交通事故预防提供科学的依据。     

基于时空交互模型的高速公路季节事故频次影响因素分析

为了深入了解影响高速公路事故频次的显著因素,采集2014年广东省开阳高速公路的事故、道路、交通和气象数据,以曲率和坡度同质性为原则将整条公路划分为154条路段,采用时空交互模型拟合路段季节事故数和道路设计参数、交通特征、气象因素间的内在关系。该模型不仅解释了相邻路段间的空间效应和相邻季节间的时间效应,而且还考虑了时空效应间的相互作用,有助于提高模型的拟合预测性能、减少参数估计偏倚。基于贝叶斯推断的模型估计和评价结果显示：事故数据中存在显著的时空关联和交互效应;时空交互模型比传统层级泊松模型的拟合优度更高;路段长度与事故频次线性相关,而交通量则与事故频次间存在非线性关系;高速公路交通安全性随着中、大型客、货车（三类车）比例的增加而显著提高;路段曲率、坡度越大,交通事故风险越高;风速越高、降水量越多的季节,事故频次将显著上升。研究结果可为高速公路交通安全改善方案的制定提供理论依据。     

Safety performance functions for low-volume rural minor collector two-lane roadways

The Fixing America's Surface Transportation Act (FAST Act) highlights a data-driven method to improve traffic safety on all public paved roads in the U.S. The first edition of the Highway Safety Manual (HSM) is a widely used tool that provides crash predictive models in the form of safety performance functions (SPFs). There are no specific SPFs for low-volume roadways in the HSM. It is important to know that low-volume roadways are the major roadway types in terms of total mileage. This study used 2015–2019 crash data from Texas, incorporating with other relevant geometric and traffic variables, to develop SPFs for a specific low-volume roadway type (rural minor collector two-lane roadways). This study proposed a rules-based SPF developed approach that makes the prediction accuracies higher compared to the full model. The R² values range from 0.18 to 0.22 for all data (without splitting) for different injury level models. The prediction accuracies are improved in the decision tree-based models. For different class specific models (based on injury levels), the R² values range from 0.25 to 0.41. Three SPF groups are developed based on crash injury types. The SPFs can provide guidance in refining the prediction accuracies of rural minor collectors.     

高速公路平面线形与安全关系的探讨

建立线形指标、交通量与事故间的模型是当前事故规律微观研究的主要方法，虽然在模型中纳入更多的指标能够提高的解释能力，但增加了模型的复杂性，加剧了数据采集困难．简洁的模型有时候在分析特定类型事故时反而更具优势，因此，作者在研究高速公路线形条件与事故的关系时，主要提取了平面线形的圆曲线、缓和曲线和超高等指标，重点分析平面线形与安全的关系。作者首先对国内外有关平面线形与安全关系的研究进行了简要回顾，利用贵州省贵黄、贵新两务高速公路的事故、线形、交通量数据建立了回归模型。此外，还结合具体案例，对曲线超高对行车安全的影响进行了剖析，并提出了一些针对平面线形安全问题的具体措施和建议。     

高速公路危化品事件处置持续时间预测模型

为准确预估危化品事件影响的时间、支撑高速公路危化品运输应急处置,基于危化品运输事故历史数据,构建高速公路危化品事件处置持续时间的预测模型.首先在事故特征分析的基础上,初步选取影响因子;利用Spearman秩相关系数对各因子进行相关性检验,确定危化品特性、危化品泄漏量及所需要驳货车的数量作为模型的输入变量;基于TSK型模糊推理系统,采用ANFIS方法建模;最后采用实例对模型进行验证并作误差分析.结果表明,模型预测结果与实测值吻合良好,且输入参数数目控制在合理范围内,能够为危化品事件救援提供必要的参考.      

Impacts of accident severity factors and loss values of crashes on expressways in Thailand

The number of road accidents and the level of accident severity have been extensively applied as the indicators for measuring the efficiency of service provision in road network systems of each country. This research utilized accident data on expressway networks during B.E.2550 (2007) to B.E.2553 (2010) (updated data was collected), in which Expressway Authority of Thailand (EXAT) as legislatively mandated unit has taken responsibility for the execution of nine expressway routes covering distances totaling over 207 km with a record of 2194 crashes. The chief objective of the study aims to forecast the accident severity through formulating Multiple Logistic Regression Model to analyze the probability of injury accident and fatal accident in comparison with property damage only accident. Its measurement comprehensively considers statistical relationship among variables such as average speed on road section, average traffic volume per day, period of time, weather conditions, physical characteristics of accident area, and causes of accident. Together, the research question is to verify whether these variables affect the opportunity or probability of three levels of accidents and investigate impacts of accident loss values due to the reduction in crash severity measures.     

双车道高速公路追尾事故实时预测模型

现有的高速公路实时事故预测模型对高速公路信息化采集设备的布设密度和采集的数据粒度要求很高,在低信息化的高速公路管理工作上难以得到应用.结合国内高速公路信息化现状,使用单个检测器所采集的数据,对高速公路追尾事故实时风险进行研究.基于江苏省扬州市启扬高速公路上布设的超声波交通流检测器所采集的交通流数据,采用配对案例对照方法和二元逻辑回归,建立了双车道高速公路追尾事故实时预测模型.对事故前5~20 min的交通流数据分别构建流量时空矩阵、速度时空矩阵、平均车头间距时空矩阵,通过引入矩阵特征值简化建模过程并避免了指标间的相关性过高问题.模型总体精度85.7%,事故预测精度33.3%,误报率低于2%,相比已有模型总体预测精度较高,误报率较低,表明了该方法应用于追尾事故实时预测领域的可行性和有效性.      

斜碰撞再现反推算法研究

结合近年来积累的交通事故调研经验,通过建立轮胎侧偏特性模型、四车轮车辆运动仿真分析模型,解决车辆轮胎印迹内的垂直载荷分布不同的问题,以及由地面多种因素对车辆运动产生不同影响的问题和车辆本身复杂的受力问题,达到事故再现的目的。通过反推计算车辆在碰撞事故发生时的运动状态,可以科学的再现车辆斜碰撞事故发生的过程,明确当事人的事故责任,提供了重要的参考。最后通过运用车辆碰撞分析软件PC-crash,结合具体的交通事故实例,验证了关于汽车斜碰撞反推计算理论的研究结果在实际的交通事故处理中具有较高的实用性与可靠性。     

Data-driven train set crash dynamics simulation

Traditional finite element (FE) methods are arguably expensive in computation/simulation of the train crash. High computational cost limits their direct applications in investigating dynamic behaviours of an entire train set for crashworthiness design and structural optimisation. On the contrary, multi-body modelling is widely used because of its low computational cost with the trade-off in accuracy. In this study, a data-driven train crash modelling method is proposed to improve the performance of a multi-body dynamics simulation of train set crash without increasing the computational burden. This is achieved by the parallel random forest algorithm, which is a machine learning approach that extracts useful patterns of force–displacement curves and predicts a force–displacement relation in a given collision condition from a collection of offline FE simulation data on various collision conditions, namely different crash velocities in our analysis. Using the FE simulation results as a benchmark, we compared our method with traditional multi-body modelling methods and the result shows that our data-driven method improves the accuracy over traditional multi-body models in train crash simulation and runs at the same level of efficiency.     

山区公路小半径弯道路段事故严重度影响因素及其异质性比较分析

为分析影响山区公路小半径路段典型事故的严重程度的相关因素及其异质性效应，基于某山区双车道公路1 067起交通事故数据，从驾驶员、车辆、道路和环境4个方面选取15个潜在特征变量，采用二项Logit模型和随机参数二项Logit模型，分别构建小半径弯道路段上追尾碰撞、正面碰撞和侧面碰撞3类典型事故的严重度分析模型，分析3类典型事故严重度的显著影响因素，并采用边际弹性系数量化分析影响因素的作用强度。结果表明，小半径弯道路段上不同形态事故的严重度影响因素存在明显差异:①追尾碰撞严重度的显著影响因素依次为摩托车、夜间、弯道转角、驾驶员年龄、季节，摩托车和冬季分别是服从(2.716.1.5642)和(-1.495，2.1162)正态分布的异质性影响因素，导致发生伤亡事故的概率为95.72%和23.58%；②正面碰撞严重度的显著影响因素依次为货车、摩托车、驾驶员超车、弯道转角和弯道长度，货车导致其伤亡事故概率增加108.8%，摩托车和弯道长度分别是服从(6.941，9.9012)和(-0.004，0.0032)正态分布的异质性影响因素，导致发生伤亡事故的概率为76.11%和9.18%；③侧面碰撞严重度的显著影响因素依次为摩托车、驾驶员年龄及弯道有接入口，摩托车和接入口分别是服从(5.211，5.1112)和(-1.408，2.1462)正态分布的异质性影响因素，导致发生伤亡事故的概率为88.87%和25.47%。④与传统二项Logit模型相比，追尾碰撞、正面碰撞和侧面碰撞的随机参数二项Logit模型的拟合优度分别提高了2.85%，4.15%，6.76%，且定量捕捉了异质性影响因素，更适用于事故严重度的精细化分析。      

A novel deep ensemble based approach to detect crashes using sequential traffic data

Crash is one of the leading causes of death in the United States. Real time detection of crashes plays a pivotal role in increasing safety of highways. In this study, a deep ensemble modelling approach is proposed in which we first employed three powerful deep learning techniques, Long Short-Term Memory (LSTM), Gated Recurrent Units (GRUs), and Deep Neural Network (DNN), then these three models are combined using eight ensemble techniques to detect crashes in real time. Loop detectors' traffic condition, crash information, and weather condition are the main sources of data used in this study. In addition, since the dataset of this study includes 241 crash and 6038 non-crash cases, Synthetic Minority Over-sampling Technique (SMOTE) is used to overcome problem of imbalanced data before training the models. The results show that while deep learning models are performing well in detecting crashes, ensemble of these three deep learning models using Multilayer Perceptron (MLP) and Random Forest Classifier (RFC) can improve detection performance. Interestingly, MLP and RFC ensemble models achieved the highest detection rate and lowest false alarm rate values, respectively, among all the studied models. Comparing the models regarding area under curve (AUC) of ROC curve also shows that the best five models are MLP ensemble, RFC ensemble, DNN, GRU, and LSTM, respectively, with AUC of 97.2%, 95.2%, 93.7%, 91.8%, and 91.3%.     

Using a surrogate safety approach to prioritize hazardous segments in a rural highway in a developing country

Road safety is a global concern particularly in developing countries where some road sections are disproportionately more vulnerable in terms of the frequency and severity of crashes. Other than using historical crash data based reactive approaches, those sections need to be identified proactively, so that mitigation measures can be applied. Moreover, those approaches are sometimes questioned mainly due to data reliability issues in developing countries. The study reported here is aimed at highlighting the applicability of traffic conflict techniques as surrogate safety measures to identify those sections of a rural highway in a developing country, which are most likely at risk. An adapted framework is demonstrated to identify traffic conflicts using combined surrogate indicators acknowledging the limited resources and facilities in developing countries. A new model is put forwarded using a count data modelling approach. Both fixed and random parameters model derivatives have been explored as an alternative methodological approach to relate the factors affecting the number and probability of conflicts. The partial effects of individual independent variables were estimated to gain a better insight of their impact. The results show that the model can predict high risk segments in terms of probability of conflicts as well as safety risk, as well as prioritize road sections according to the likelihood of their safety level. The model provides a less expensive alternative to the collection of historical crash data in order to identify hazardous road locations or black spots on two-lane highways in developing countries.¹     

双车道等级公路路侧事故预测模型研究

借鉴国内外事故预测模型(也称安全性能函数SPF)研究领域的最新成果,收集了31条双车道公路(总里程约740 km)的事故、交通量和线形数据,采用了泊松、负二项、零堆积泊松和零堆积负二项四种统计概率分布,从路侧事故数、路侧事故死亡人数、路侧事故受伤人数三方面对路侧事故规律进行了研究,通过弹性分析从量化的角度给出了道路几何条件、交通量水平与构成等指标与路侧安全的关系。