A method to estimate trip O‐D patterns using a neural network approach

This paper proposes a method which identifies the trip origin‐destination (O‐D) matrix when many pairs of values for the right hand side column (B) and the bottom row (A) of the matrix are given. The method considers B and A as the cause (input) and effect (output) of a system, respectively, and that the O‐D matrix represents the relationship between the cause and the effect. The relationship which satisfies all pairs of the cause and the effect data exactly may not be identified, but, should a general pattern of the relationship exist, it should emerge when many data sets of B and A are given. Two steps are involved in the method: the first step examines if a consistent O‐D pattern exists; if a pattern is found to exist, the second step identifies the values of the elements of the O‐D matrix. The first step is based on the shape of the possibility distributions of the values of the matrix elements. The second step uses a simple back‐propagation neural network. The method is useful to problems that require identification of the cause‐effect relationship when many sets of data for the cause and effect are available, for example, the station‐to‐station travel pattern on a rapid transit line when the total entering and exiting passengers are known at each station for many different days. The model can also be applied to other transportation problems which involve input and output relation.     

基于WOS数据库的文献计量分析的城市交通事故态势研究

为从宏观上了解交通事故的研究态势,利用文献计量法对WOS数据库收录的474篇文献进行数据可视化分析。研究发现,发文量历经了零阶段、稳定阶段和上升阶段;中国研究机构数量和发文量都位于世界第一;研究领域形成了由122位作者组成的核心作者群体;研究方向经历了以交通参与者、道路交通事故、交通事故安全为研究目的的变化;关键词分析得出该领域未来的研究热点将集中在交通事故安全、交通事故严重程度及交通事故影响三方面。     

Representing mental maps and cognitive learning in micro-simulation models of activity-travel choice dynamics

This paper develops a model, based on Bayesian beliefs networks, for representing mental maps and cognitive learning into micro-simulation models of activity-travel behavior. Mental maps can be used to address the problem that choice sets in models of travel demand are often ad hoc specified. The theory underlying the model is discussed, a specification is derived and numerical simulation is used to illustrate the properties of the model.     

Short-Term Prediction of Travel Time using Neural Networks on an Interurban Highway

The main purpose of this study was to investigate the predictability of travel time with a model based on travel time data measured in the field on an interurban highway. Another purpose was to determine whether the forecasts would be accurate enough to implement the model in an actual online travel time information service. The study was carried out on a 28-kilometre-long rural two-lane road section where traffic congestion was a problem during weekend peak hours. The section was equipped with an automatic travel time monitoring and information system. The prediction models were made as feedforward multilayer perceptron neural networks. The main results showed that the majority of the forecasts were close to the actual measured values. Consequently, use of the prediction model would improve the quality of travel time information based directly on the sum of the latest measured travel times.     

基于BP人工神经网络的滑坡预测分析

文章以汶川地震引发的滑坡为研究对象,以震中距、地震烈度、坡度、前缘高程、坡高和岩性等影响坡体稳定性的因素为切入点,利用BP人工神经网络对实际坡体的稳定性进行了预测分析。结果表明,BP人工神经网络方法能有效预测坡体的稳定情况。     

Selatm — a GIS based program for evaluating the safety benefits of local area traffic management schemes

Particular safety problems relate to traffic on local streets. Local Area Traffic Management (LATM) schemes are often implemented with the objective of counteracting these safety problems. One analytical difficulty in appraising the effectiveness of LATM in dealing with safety problems has been the ‘footloose’ nature of accident locations in a local street network. Seldom are there distinct ‘blackspot’ locations. An area‐wide approach is needed and the interaction between the system and arterial road network must be considered. The paper describes the development of a Safety Evaluation Method for Local Area Traffic Management (termed SELATM). It is a GIS‐based program for analysing accident patterns over time and the evaluation of the safety benefits of LATM schemes. The evaluation is perform at different network levels for various accident variables. The thrust of the program involved the integration of network data with data on accidents and the installed devices to generate summary accident statistics for the various network levels allowing for before and after comparison with a control area. This program as developed is applied to a LATM scheme at Enfield, a suburb in metropolitan Adelaide.     

Revenue management in the parking industry: a multiple garage intelligent reservation model

This paper explores how advanced reservations, coupled with dynamic pricing (based on booking limits) can be used to maximize parking revenue. An integer programing formulation that maximizes parking revenue over a system of garages is presented. Furthermore, an intelligent parking reservation model is developed that uses an artificial neural network procedure for online reservation decision-making. Finally, the paper provides some strategic and managerial implications of multi-garage revenue management systems, and discusses techniques for identifying and implementing micro-market segmentation in the parking industry.     

Improving the forecasting accuracy of air passenger and air cargo demand: the application of back-propagation neural networks

This study employs back-propagation neural networks (BPN) to improve the forecasting accuracy of air passenger and air cargo demand from Japan to Taiwan. The factors which influence air passenger and air cargo demand are identified, evaluated and analysed in detail. The results reveal that some factors influence both passenger and cargo demand, and the others only one of them. The forecasting accuracy of air passenger and air cargo demand has been improved efficiently by the proposed procedure to evaluate input variables. The established model improves dramatically the forecasting accuracy of air passenger demand with an extremely low mean absolute percentage error (MAPE) of 0.34% and 7.74% for air cargo demand.     

Adaptive scheduling for real-time and temporal information services in vehicular networks

Vehicular networks represent a research area of significant importance in improving the safety, efficiency and sustainability of transportation systems. One of the key research problems in vehicular networks is real-time data dissemination, which is crucial to the satisfactory performance of many emergent applications providing real-time information services in vehicular networks. Specifically, the two issues need to be addressed in this problem are maintenance of temporal data freshness and timely dissemination of data. Most existing works only considered periodical data update via backbone wired networks in maintaining temporal data freshness. However, many applications rely on passing vehicles to upload their collected information via wireless network, which imposes new challenges as the uplink data update will have to compete with the downlink data dissemination for the limited wireless bandwidth. With such observations, we propose a temporal information service system, in which vehicles are able to collect up-to-date temporal information and upload them to the roadside units (RSU) along their trajectories. Meanwhile, RSU can disseminate its available data items to vehicles based on their specific requests. Particularly, in this paper, we first quantitatively analyze the freshness of temporal data and propose a mathematical model to evaluate the usefulness of the temporal data. Next, we give the formulation of the proposed real-time and temporal information service (RTIS) problem, and prove the NP-hardness of this problem by constructing a polynomial-time reduction from 0–1 knapsack problem. Subsequently, we establish a probabilistic model to theoretically analyze the tradeoff between timely temporal data update and requested data dissemination sharing a common communication resource, which provides a deeper insight of the proposed RTIS. Further, a heuristic algorithm, namely adaptive update request scheduling (AURS), is designed to enhance the efficacy of RTIS by synthesizing the broadcast effect, the real-time service requirement and the service quality in making scheduling decisions. The computational complexity and scalability analysis of AURS is also discussed. Last but not least, a simulation model is implemented and a comprehensive performance evaluation has been carried out to demonstrate the superiority of ARUS against several state-of-the-art approaches in a variety of application scenarios.