交通事件持续时间预测贝叶斯网方法研究

交通事件持续时间的预测是事件管理系统的重要组成部分,根据I-880实测数据集,利用逐步回归分析的方法确定事件持续时间的主要影响因素,分别建立了应用于事件持续时间预测的朴素贝叶斯(NB)模型、加树朴素贝叶斯(TAN)模型以及一般贝叶斯网(BN)模型,在分析数据特点的基础上确定了贝叶斯网的推理算法、参数学习以及结构学习方法.在不同数据缺失的程度和不同训练样本规模下,分别对三种模型的预测准确率进行了评价,结果表明贝叶斯网预测模型在数据缺失30%的情况下30min准确率高于80%.     

含水率对砖砌体抗剪强度的影响

通过含水率对砖砌体抗剪强度影响规律的试验,分别测出不同砖砌体试件整体含水率、砖的含水率和砂浆缝砂浆的含水率与抗剪强度之间的关系,得到砖砌体试件随浸泡时间含水率的变化规律,给出了考虑含水率的砖砌体抗剪强度计算公式.通过试验可以看出,含水率对砖砌体抗剪强度有着重要影响,有关规范中应予以考虑.     

河北北部山区通村公路土基回弹模量对路面设计的影响研究

通过对河北北部山区通村公路进行现场试验,由回归分析得到土基回弹模量与弯沉的关系式,并根据不同土基强度与不同标准轴载对路面厚度设计的影响,对土基强度进行分级,可作为路面设计的依据。     

Lights,camera, legal action! The effectiveness of red light cameras on collisions in Los Angeles

This study estimates the effect of red light cameras (henceforth cameras) on collisions under the Los Angeles Automated Photo Enforcement Program that ran from 2006 to 2011. To control for selection bias and unobservables, a data set is constructed such that intersections with cameras are compared to control groups of nearby intersections without cameras, matched on observable characteristics. To capture potential spillover effects of cameras, control groups at various distances from the intersections with cameras are considered. A Poisson panel data model with random coefficients is applied to these data and estimated using Bayesian methods. The program suffered from weaknesses in enforcement. The city’s courts did not uphold citations and this dampened the effect cameras had on drivers. These problems are accounted for in modeling. Controlling for these concerns, results indicate that the cameras decreased red light running related collisions, but increased right-angle and injury collisions, as well as collisions overall.     

Findings from subjective evaluations and driver ratings of vehicle dynamics: steering and handling

This paper investigates subjective assessments (SA) of vehicle handling and steering feel tests, both numerical and verbal, to understand drivers’ use of judgement scales, rating tendencies and spread. Two different test methods are compared: a short multi-vehicle first-impression test with predefined-driving vs the standard extensive single-vehicle free-driving tests, both offering very similar results but with the former saving substantial testing time. Rating repeatability is evaluated by means of a blind test. Key SA questions are identified by numerical subjective assessment autocorrelations and by generating word clouds from the most used terms in verbal assessments, with both methods leading to similar key parameters. The results exposed in this paper enable better understanding of SA, allowing improving the overall subjective testing and evaluation process, and improving the data collection and analysis process needed before identifying correlations between SA and objective metrics.     

Safety modeling for two‐way left‐turn lanes and a procedure to identify two‐way left‐turn lane segments with safety concerns

In the past, two‐way left‐turn lane (TWLTL) median treatments have been frequently used in Florida to inexpensively improve traffic and safety performances. In order to identify factors that may have significant impacts on safety operations in TWLTL sections and to identify TWLTL locations that present existing and future safety concerns, a research project was carried out and results are summarized in the paper. In the research, a three‐year crash history database with crashes and section characteristics from a total of 1688 TWLTL sections all over Florida was developed and used. A negative binomial regression model was developed to determine the statistical relationship between the number of crashes per mile per year and several variables such as traffic volume, access density, posted speed, and number of lanes. In regard to the methodology, in order to identify locations with safety concerns, several steps are needed: development of real crash data distribution, determination of statistical distribution models that better represent the actual crash data, determination of percentile values for the average number of crashes, estimation of crash rates for sections with the same characteristics, estimation of critical values for the variables corresponding to the percentile values for average number of crashes, calculation of tables of critical average annual daily traffic values, and generation of a list of TWLTL locations with critical safety concerns. Results presented in the paper have been used in real applications. Copyright © 2012 John Wiley & Sons, Ltd.     

The performance of route modification and demand stabilization strategies in stochastic vehicle routing

A key concern in managing vehicle routing operations under stochastic demands is whether, on the basis of travel distance, route modification yields materially greater logistical efficiency than fixed routes. This research uses statistical calibration as the primary technique to develop a robust and tractable model for estimating this difference in logistical efficiency. Based on features such as the models predictive accuracy and generalizability, it constitutes a substantive improvement over existing models. The present study also expands the range of predictive models relevant to vehicle routing under stochastic demands with models to estimate the transportation and inventory effects of persuading customers to stabilize their ordering patterns.     

困难山区铁路主要技术标准与工程投资关系研究

铁路主要技术标准与工程投资有着十分密切的关系,通过深入探讨铁路主要技术标准,从统计学的角度研究铁路主要技术标准与工程投资的关系,建立工程投资关于铁路主要技术标准的多元非线性回归模型。并结合实际算例说明回归模型的良好的拟合度,研究各项主要技术标准之间的相关性,分析各项主要技术标准对工程投资的影响趋势与影响程度,从而在实际的应用中能够有的放矢地关注关键的技术标准以及科学合理地决策出各项主要技术标准,以达到优化线路设计、节约工程投资的目的。     

土工液塑限试验中的新方法应用与比较

针对公路与水电土工试验规程中所采用的作图法确定液塑限值而带来的诸多不便,采用数学解析法、最小二乘法、回归分析法计算液塑限试验数据,并将其编制成QBASIC程序上机处理,由此确定出的液限、塑限值较传统方法方便、快捷、准确。同时对公路与水电土工试验规程中所采用的不同圆锥下沉深度而计算出的液塑限值进行了比较。     

基于模糊线性回归分析的编组站运营指标预测方法

运用模糊线性回归分析方法,建立编组站运营指标的模糊预测模型。利用该模型,对向塘西编组站中时进行了预测。在对中时影响因素分析的基础上,选取办理车数、有调中转车数、无调中转车数、折角车流量、货物列车到发列数和到发均衡程度等6个影响因素,结合车站近几年相关历史数据,确定了中时与6个影响因素之间的模糊函数关系。依据此函数关系对未来时期的中时进行了预测,预测结果表明所提出的运营指标预测方法有较好的适用性。