Rationalizing Reliable Imputation Durations of Genetically Designed Time Delay Neural Network and Locally Weighted Regression Models

Abstract

Estimating missing values is known as data imputation. Previous research has shown that genetic algorithms (GAs) designed locally weighted regression (LWR) and time delay neural network (TDNN) models can generate more accurate hourly volume imputations for a period of 12 successive hours than traditional methods used by highway agencies. It would be interesting and important to further refine the models for imputing larger missing intervals. Therefore, a large number of genetically designed LWR and TDNN models are developed in this study and used to impute up to a week-long missing interval (168 hours) for sample traffic counts obtained from various groups of roads in Alberta, Canada. It is found that road type and functional class have considerable influences on reliable imputations. The reliable imputation durations range from 4–5 days for traffic counts with most unstable patterns to over 10 days for those with most stable patterns. The study results clearly show that calibrated GA-designed models can provide reliable imputations for missing data with ‘block patterns’, and demonstrate their further potentials in traffic data programs.     

Analysis of Characteristics of the Dynamic Flow-Density Relation and its Application to Traffic Flow Models

Abstract

Online traffic flow modeling is of increasing importance due to intelligent transport systems and technologies. The flow-density relation plays an important role in traffic flow modeling and provides a basic way to illustrate traffic flow behavior under different traffic flow and traffic density conditions. Until now the research effort has focused mainly on the shape of the relation. The time series of the relation has not been identified clearly, even though the time series of the relation reflects the upstream/downstream traffic conditions and should be considered in the traffic flow modeling. In this paper, the dynamic flow-density relation is identified based on the classification of traffic states and is quantified employing fuzzy logic. The quantified dynamic flow-density relation builds the basis for online application of a macroscopic traffic flow model. The new approach to online modeling of traffic flow applying the dynamic flow-density relation alleviates parameter calibration problems stemming from the static flow-density relation.     

广西高速公路木冲隧道交通安全性分析

长大隧道是高速公路的控制路段,其运营安全对高速公路畅通和安全有重要影响。文章通过研究木冲隧道交通事故分布特征,分析了长大隧道发生交通事故的原因,提出了改善木冲隧道交通安全状况的工程措施和管理建议,其对提高木冲隧道运营安全性具有指导意义。     

高速公路交通安全水平定量化评价方法浅析

文章根据我国的交通安全现状,提出了基于年公里事故数、百万车年公里事故率、年公里死亡数及百万车年公里死亡率四项评价指标的综合安全度指数定量化评价方法,为高速公路安全水平的改善提供科学依据。     

城市客运交通枢纽预警分级阈值简析

交通枢纽作为服务于公共交通之间以及公共交通与其它交通方式之间客流转换的场所,是改善整个交通系统,提高居民出行效率、解决出行换乘等问题的重要影响因素。本文结合东直门综合运输枢纽信息服务平台工程,采集枢纽客流进出量,总结客流统计规律,对东直门交通枢纽预警分级阈值进行简析,相关研究成果可为交通枢纽预警分级阈值分析提供参考。     

设置间歇式公交专用进口道的流量条件研究

针对交叉口处公交车辆对道路资源需求的动态特征,提出了一种间歇式公交专用进口道的控制系统及控制方法。为了得到间歇式公交专用进口道适用的交通流量条件,首先研究了设置间歇式公交专用进口道后社会车辆和公交车辆的延误;然后通过算例定量分析了设置间歇式公交专用进口道前后交叉口人总延误差的变化规律。研究结果表明：在同一交通流向有两条进口车道的情况下,周期时长为60s、100S、120S的交叉口设置间歇式公交专用进口道的临界交通饱和度分别为0．75、0．65、0．60。当进口道交通饱和度小于临界交通饱和度时,可以考虑在该流向设置间歇式公交专用进口道。     

满足交通网络流量增长态势的扩能优化研究

在交通网络的实际应用中,流量的发展态势往往超出现存网络的最大流量承载能力,这就需要考虑如何提高网络的输送能力,即如何对交通网络进行扩能。本文基于发展态势的流量需求、扩能代价最低以及扩能拥堵程度高的线路条件,构造了最优的扩能算法。通过此算法,可以选择交通网络中最优的扩能路线。在交通运输领域,由于流量的发展态势需要扩能的问题普遍存在,本文的研究内容可以为交通网络的扩能决策、优化、设计等提供应用基础。     

站点设置形式对公交专用道通行能力的影响分析

通过分析现有公交专用道通行能力的计算方法,发现在计算公交专用道通行能力时没有考虑站点设置形式对其造成的影响。将国内常见的公交专用道站点设置形式分为4类,针对其中3类主要的设置形式进行交通流影响分析,提出了考虑站点设置形式的公交专用道通行能力计算模型。最后利用仿真软件对站点处公交专用道通行能力进行实验,仿真数据证明了计算方法的有效性。     

高速公路跨路施工

高速公路跨路施工中制约因素较多、条件比较复杂,施工安全较难控制。以阜盘八标为例,对跨越高速公路的施工实践经验进行介绍。     

Singapore motorisation restraint and its implications on travel behaviour and urban sustainability

The example of Singapore shows that rapid urban and economic growth does not have to bring traffic congestion and pollution. Singapore has chosen to restrain car traffic demand due to its limited land supply. Transport policy based on balanced development of road and transit infrastructure and restraint of traffic has been consistently implemented for the past 30 years. Combined with land use planning, it resulted in a modern transport system, which is free from major congestion and provides users with different travel alternatives. As the economic growth caused a substantial increase in demand for cars, several pricing policies were introduced with the aim of restraining car ownership and usage. Growth of the vehicle population is now controlled and potentially congested roads are subject to road pricing. These measures help to keep the roads free from major congestion, maintain car share of work trips below 25% and keep the transport energy usage low. Although Singapore conditions are in many aspects unique, its travel demand experience can provide useful lessons for other rapidly growing cities in Asia.