基于贝叶斯网络模型的交通状态预测

城市的交通状态是可以预测的。有效的交通状态预测能优化交通状态,减少交通阻塞。贝叶斯网络(Bayesian Networks,BN)是目前不确定知识和推理领域最有效的理论模型之一。文章在综合考虑交通阻塞成因的基础上构建网络模型,在已有的交通状态数据的基础上提出基于贝叶斯法则的学习算法,并通过计算变量间的条件概率来计算交通阻塞发生的可能性,达到预测的目的。     

A note on the consistent aggregation of nested logit demand functions

The present paper derives a set of rules allowing for the consistent aggregation of nested logit travel demand functions across origin and destination zones. Presented aggregation rules are derived for the case when the mode choice is performed conditional on destination choice. The derivation is based on the principles of consistency between aggregate and disaggregate travel demand models introduced by Sweet as well as upon the sampling theory.     

Error and optimism bias in toll road traffic forecasts

Traffic forecasts are employed in the toll road sector, inter alia, by private sector investors to gauge the bankability of candidate investment projects. Although much is written in the literature about the theory and practice of traffic forecasting, surprisingly little attention has been paid to the predictive accuracy of traffic forecasting models. This paper addresses that shortcoming by reporting the results from the largest study of toll road forecasting performance ever conducted. The author had access to commercial-in-confidence documentation released to project financiers and, over a 4-year period, compiled a database of predicted and actual traffic usage for over 100 international, privately financed toll road projects. The findings suggest that toll road traffic forecasts are characterised by large errors and considerable optimism bias. As a result, financial engineers need to ensure that transaction structuring remains flexible and retains liquidity such that material departures from traffic expectations can be accommodated.

Effective environmental marketing of green cars: A nested-logit approach

Using market data, we assess the effectiveness of an eco-marketing campaign on purchases of ‘green’ vehicles. The eco-marketing was designed as a quasi-experiment, having one region exposed to the marketing while the other region was the control. A two-level nested-logit model consistent with utility maximization reveals the campaign had short-term positive effects on green-car sales. Results also indicate green-car buyers come from highly educated communities. Age has a positive but non-linear effect on green car sales.     

Toll product preferences and implications for alternative payment options and going cashless

There has been a great deal of research on deriving estimates of the value of travel time savings (VTTS) as a way of converting travel time benefits of toll roads relative to free routes into monetary units, the major user benefit in the development of forecasts of traffic and hence revenue streams. By contrast there has been almost no consideration given to identifying the role that various tollroad products play in establishing preferences for toll routes over non-tolled routes. Increasingly tollroads give users the option to pay by cash at a toll booth, by electronic tolling or by a pre- or post-paid debit and credit account system involving vehicle identification. The efficiency gained by electronic tolling for both the users and the operator have resulted in moves in many jurisdictions to eliminate cash collection entirely (or not introduce it when introducing a new tolled road facility), and to introduce a range of pre- and post-payment options. This has been accompanied by a growing move to distance-based charging in some contexts which is more cumbersome to structure with a cash option. This paper investigates current and potential travellers’ preferences for a range of toll products and how much individual’s are willing to pay for very specific toll products. Data from a stated choice experiment is used in a mixed logit model to establish the role that toll products play in the context of offered times and costs of alternative routes, in choosing between alternative ways of paying for the use of tolled routes.

城市道路车道宽度计算模型的修正研究

文章以城市生活性主干道为例,对计算车道宽度的波良可夫公式进行了修正,得到了横向安全距离计算模型以及机动车道宽度适用推荐值,并论证了该模型应用的可行性与经济性。     

Towards a standardized European road network database

Many Driver Information Systems, especially those that provide location information and route guidance instruction, rely on some form of digital map data, i.e. data that represent the location and other properties of earth-bound objects. A deeperinformation analysis of the data needs of the systems reveals that many needs are very close to the demands that a human navigator makes on a classical paper map. But it also reveals some hidden needs, which relate to the fact that the current Driver Information Systems have only a very poor or no general knowledge. Gathering all these data, putting them into a database and keeping them up to date is an enormous task. Therefore it is very important to know whatsurveying and digitizing techniques are the most suitable for such data. This question is currently being investigated by two DRIVE projects, PANDORA and Task Force EDRM.To guarantee the efficiency of a road network database and to guarantee the exchangeability of traffic messages, a certainstandardization will be inevitable. One possibility is to standardize the finished article, i.e. the map data in the form in which they are represented on the medium used by the system itself (e.g. CD, coded beacon message). This is the solution that has been chosen in Japan, where a CD-ROM based standard has been defined. It is also the solution chosen by the European manufacturers of beacon-supported systems such as Autoguide and LISB, who have defined a standard for the road-vehicle communication link. Another possibility is to standardize the semi-manufactured article, i.e. the map data as they occur in a general purpose road database or in the datafiles produced by data suppliers. This solution has been chosen by Bosch and Philips and had led to their GDF, in which they define a standard data content, a data model and an exhange format for these files. If the systems are going to combine data coming from different sources, the need arises for standard reference numbers. This means that an organizational infrastructure will have to be set up to create and maintain such a reference numbering system. A road database that is kept up to date, represents a lot of money. It will be vitally important for such databases to be legally protected against copying activities.     

A study of traveler behavior under traffic information-provided conditions in the Beijing area

ABSTRACT

The quality of traffic information has become one of the most important factors that can affect the distribution of urban and highway traffic flow by changing the travel route, transportation mode, and travel time of travelers and trips. Past research has revealed traveler behavior when traffic information is provided. This paper summarizes the related study achievements from a survey conducted in the Beijing area with a specially designed questionnaire considering traffic conditions and the provision of traffic information services. With the survey data, a Logit model is estimated, and the results indicate that travel time can be considered the most significant factor that affects highway travel mode choice between private vehicles and public transit, whereas trip purpose is the least significant factor for private vehicle usage for both urban and highway travel.     

A dynamic Bayesian network model for real-time crash prediction using traffic speed conditions data

Traffic crashes occurring on freeways/expressways are considered to relate closely to previous traffic conditions, which are time-varying. Meanwhile, most studies use volume/occupancy/speed parameters to predict the likelihood of crashes, which are invalid for roads where the traffic conditions are estimated using speed data extracted from sampled floating cars or smart phones. Therefore, a dynamic Bayesian network (DBN) model of time sequence traffic data has been proposed to investigate the relationship between crash occurrence and dynamic speed condition data. Moreover, the traffic conditions near the crash site were identified as several state combinations according to the level of congestion and included in the DBN model. Based on 551 crashes and corresponding speed information collected on expressways in Shanghai, China, DBN models were built with time series speed condition data and different state combinations. A comparative analysis of the DBN model using flow detector data and a static Bayesian network model was also conducted. The results show that, with only speed condition data and nine traffic state combinations, the DBN model can achieve a crash prediction accuracy of 76.4% with a false alarm rate of 23.7%. In addition, the results of transferability testing imply that the DBN models are applicable to other similar expressways with 67.0% crash prediction accuracy.     

Understanding suburban travel demand: Flexible modelling with revealed and stated choice data

We analyse the choice of mode in suburban corridors using nested logit specifications with revealed and stated preference data. The latter were obtained from a choice experiment between car and bus, which allowed for interactions among the main policy variables: travel cost, travel time and frequency. The experiment also included parking cost and comfort attributes. The attribute levels in the experiment were adapted to travellers’ experience using their revealed preference information. Different model specifications were tested accounting for the presence of income effect, systematic taste variation, and incorporating the effect of latent variables. We also derived willingness-to-pay measures, such as the subjective value of time, that vary among individuals as well as elasticity values. Finally, we analysed the demand response to various policy scenarios that favour public transport use by considering improvements in level-of-service, fare reductions and/or increases in parking costs. In general, demand was shown to be more sensitive to policies that penalise the private car than those improving public transport.