基于V-支持向量分类机的交通事件检测方法研究

基于支持向量机在解决分类问题的优势，本文提出基于V-支持向量分类机的交通事件检测方法。首先把交通事件是否发生看成是一个特殊的分类问题，选取V-支持向量分类机和核函数，根据以往的交通事件是否发生的检测数据，即分别在发生交通事件和不发生交通事件两种情况下的上下游车道占有率，计算出其当前时段的上下游车道占有率的绝对差、相对差，以及下游前两时段与当前时段车道占有率的相对差，以此作为V-支持向量分类机的输入，对其进行训练，然后输入现阶段检测到的相应车道占有率统计结果，利用训练完成的V-支持向量分类机来判别是否发生交通事件。最后，本文以微观交通模拟的数据验证模型的效果。     

城市交通拥挤的社会成本分析初探

交通拥挤的社会成本可分为生产成本、使用成本、时间耗费成本及外部成本,本文在定性分析的基础上,对使用成本和时间耗费成本做了定量分析,给出了计算公式,并通过对大连市西南路某路段在拥挤时段的调查,计算出了居民出行时间成本的损失和城市交通使用成本的损失,这一结果可以推广到整条道路或区域路网,从而为城市交通的良性发展和减少经济损失等方面提供了有效的理论依据。     

Congestion pricing for Latin America: Prospects and constraints

In an effort to reduce the adverse impacts of the car and promote sustainable transport in Latin America, some governments have either implemented travel demand management policies or have considered ways of directly reducing the number of vehicles in congested areas. While demand management measures have been promoted in a small number of countries, including vehicular restrictions as well as the promotion of public transport modes, there are currently no congestion pricing programmes in operation in Latin America. This paper begins with an overview of travel demand management, including its principal aims as well as its primary objectives within the Latin American context. It discusses past efforts to promote traffic restraint and perspectives for developing congestion pricing schemes in both São Paulo and Santiago. Finally, it examines the potential role of congestion pricing as a demand management tool. While it is one of the most effective demand management measures in the industrialised world, a number of barriers currently prevent it from being widely adopted in Latin America.     

A novel peer-to-peer congestion pricing marketplace enabled by vehicle-automation

This paper proposes a novel concept of congestion pricing based on voluntary peer-to-peer exchange of money between motorists in exchange for one ceding priority to another in a traffic stream. While in the classical congestion charging paradigm payments are compulsory and flow only towards the system operator, in the proposed marketplace participation is voluntary and motorists directly compensate each other. A particular motorist may find that he/she is a ‘payer’ at certain points in a given journey and a ‘payee’ at others.Humans would not be expected to successfully seek, negotiate and execute a continuous series of peer-to-peer trades involving micro-payments while also handling the cognitively-demanding task of driving; real-world implementation will therefore require vehicles operating under fully-automated control in both the longitudinal and lateral dimensions during the time periods that they seek and engage in trades. The automated vehicle control algorithms must be sufficiently intelligent and adaptable to enable alternative maneuvers on short timescales, given the inherent uncertainty of whether or not a potential trade will in fact be executed. The peer-to-peer trading would be executed algorithmically, subject to strategic-level guidance given by a vehicle’s occupant(s) regarding the occupant’s relative valuation of money and priority in the traffic stream.In this paper we detail the prospective marketplace and present a simple simulation model to expose its properties. We show that the proposed peer-to-peer marketplace could lead to both desirable and undesirable outcomes; which of these would be predominant is a matter requiring empirical study. The paper concludes with a discussion of further research needs to refine and develop these concepts into practice.     

Understanding public response to a congestion charge: A random-effects ordered logit approach

Public acceptance is consistently listed as having an enormous impact on the implementation and success of a congestion charge scheme. This paper investigates public acceptance of such a scheme in Australia. Surveys were conducted in Brisbane and Melbourne, the two fastest growing Australian cities. Using an ordered logit modeling approach, the survey data including stated preferences were analyzed to pinpoint the important factors influencing people’s attitudes to a congestion charge and, in turn, to their transport mode choices. To accommodate the nature of, and to account for the resulting heterogeneity of the panel data, random effects were considered in the models. As expected, this study found that the amount of the congestion charge and the financial benefits of implementing it have a significant influence on respondents’ support for the charge and on the likelihood of their taking a bus to city areas. However, respondents’ current primary transport mode for travelling to the city areas has a more pronounced impact. Meanwhile, respondents’ perceptions of the congestion charge’s role in protecting the environment by reducing vehicle emissions, and of the extent to which the charge would mean that they travelled less frequently to the city for shopping or entertainment, also have a significant impact on their level of support for its implementation. We also found and explained notable differences across two cities. Finally, findings from this study have been fully discussed in relation to the literature.     

Nonlinear pricing on private roads with congestion and toll collection costs

Nonlinear pricing (a form of second-degree price discrimination) is widely used in transportation and other industries but it has been largely overlooked in the road-pricing literature. This paper explores the incentives for a profit-maximizing toll-road operator to adopt some simple nonlinear pricing schemes when there is congestion and collecting tolls is costly. Users are assumed to differ in their demands to use the road. Regardless of the severity of congestion, an access fee is always profitable to implement either as part of a two-part tariff or as an alternative to paying a toll. Use of access fees for profit maximization can increase or decrease welfare relative to usage-only pricing for profit maximization. Hence a ban on access fees could reduce welfare.     

Managing network mobility with tradable credits

A system of tradable travel credits is explored in a general network with homogeneous travelers. A social planner is assumed to initially distribute a certain number of travel credits to all eligible travelers, and then there are link-specific charges to travelers using that link. Free trading of credits among travelers is assumed. For a given credit distribution and credit charging scheme, the existence of a unique equilibrium link flow pattern is demonstrated with either fixed or elastic demand. It can be obtained by solving a standard traffic equilibrium model subject to a total credit consumption constraint. The credit price at equilibrium in the trading market is also conditionally unique. The appropriate distribution of credits among travelers and correct selection of link-specific rates is shown to lead to the most desirable network flow patterns in a revenue-neutral manner. Social optimum, Pareto-improving and revenue-neutral, and side-constrained traffic flow patterns are investigated.     

The tax treatment of company cars, commuting and optimal congestion taxes

In Europe, the preferential tax treatment of company cars implies that many employees receive a company car as part of their compensation package. In this paper, we consider a model in which wages and the decision whether or not to provide a company car are the result of direct negotiation between employer and employee. Using this framework, we theoretically and numerically study first- and second-best optimal tax policies on labour and transport markets, focusing on the role of the tax treatment of company cars. We obtain the following results. First, higher labour taxes and a more favourable tax treatment of company cars raise the fraction employees that receives a company car; congestion and congestion tolls reduce it. Second, in countries that provide large implicit subsidies to company cars, eliminating the preferential tax treatment of company cars may be an imperfect but quite effective substitute for currently unavailable congestion tolls. The numerical illustration, calibrated using Belgian data, suggests that it yields about half the welfare gain attainable through optimal congestion taxes. Third, the favourable tax treatment of company cars justifies large public transport subsidies; the numerical results are consistent with zero public transport fares. Finally, we find that earlier models that ignored the preferential tax treatment of company cars may have substantially underestimated optimal congestion tolls in Europe. The numerical illustration suggests that about one third of the optimal congestion toll we obtain can be attributed to the current tax treatment of company cars.