Advanced Traveler Information Systems Research Articles

Bayesian predictive travel time methodology for advanced traveller information system

AbstractTravellers can benefit from the availability of point‐to‐point driving time estimates on a real time basis for making travel decisions such as route choice at strategic locations (e.g. junctions of major routes). This paper reports a predictive travel time methodology that features a Bayesian approach to fusing and updating information for use in advanced traveller information system. The methodology addresses the issue that data captured in real time on travel conditions becomes obsolete and has archival value only unless it is used as an input to a predictive travel time method for updating the information. The need for fusing real time data with other factors that influence travel time is defined and the concept of predictive travel time is discussed. The methodological framework and its components are advanced and an example application is provided for illustrating the fusion of data captured by infrastructure‐based and mobile technology with model‐based predictions in order to produce expected travel times. Copyright © 2010 John Wiley & Sons, Ltd.

A new model for studying the SO-based pre-trip information release strategy and route choice behaviour

In reality, the predictive traffic information is rarely perfect. It is thus a rational assumption that travellers would not be completely in compliance with the guidance by advanced traveller information systems (ATIS). This article presents a Markovian decision programming (MDP) model for investigating the day-to-day receiving and adjusting process to the pre-trip information released by ATIS at route level. The goal is to seek an optimal information release strategy (IRS) for minimising the overall disutility under the assumption that travellers’ route choice is governed by a logit model on the base of adopted travel times. The properties of the model solution are analysed. It is found that there exists an optimal IRS that can drive the flow pattern to a system optimum (SO) if the behaviour adjustment parameter satisfies a condition as . The predictive information provided to drivers results in the oscillation of traffic flow among alternative routes when . The solution of the MDP model is obtained by solving a series of sequential minimisation programs. The model and algorithm are numerically verified on a test network.

Simulation-based dynamic traffic assignment for short-term planning applications

Evaluation of Intelligent Transportation Systems (ITS) at the planning level requires the use of appropriate tools that can capture the dynamic and stochastic interactions between demand and supply. The objective of this paper is to present a methodological simulation-based framework for such applications and implement it in the context of dynamic traffic assignment. The framework consists of a mesoscopic supply simulator and a demand simulator that combines OD estimation capabilities with discrete travel behavior models. Simulation-based DTA systems are particularly suited to evaluate a wide range of Advanced Traffic Management Systems (ATMS) and Advanced Traveler Information Systems (ATIS). The simulation model performance is illustrated through two large-scale case studies in Irvine, California, and Lower Westchester County, NY.

Day-To-Day Route Choice Decision Simulation Based on Dynamic Feedback Information

In reality, the individual's day-to-day route choice behavior is a long-time evolution process, and travelers choose their traveling routes according to the combination of historical experience and real-time traffic information. Considering two classes of users, one equipped with advanced traveler information systems (ATIS) and the other without, this paper investigates the travel efficiency under two different information feedback strategies, namely, travel time feedback strategy and mean velocity feedback strategy. The simulation results given by the cellular automaton model show that the more users rely on historical experience, the quicker the system evolves to the equilibrium. To all users, the travel efficiency decreases with travel demand and firstly increases then decreases with the dependent degree to historical experience. However, as far as the ATIS market penetration rate is concerned, the users' travel efficiency under two feedback strategies exhibits different trends. The equipped travelers have shorter travel time, particularly under mean velocity feedback strategy. In addition, the difference of travel efficiencies between two classes of users decreases as days evolve.

Hybrid model for prediction of bus arrival times at next station

AbstractEffective prediction of bus arrival times is important to advanced traveler information systems (ATIS). Here a hybrid model, based on support vector machine (SVM) and Kalman filtering technique, is presented to predict bus arrival times. In the model, the SVM model predicts the baseline travel times on the basic of historical trips occurring data at given time‐of‐day, weather conditions, route segment, the travel times on the current segment, and the latest travel times on the predicted segment; the Kalman filtering‐based dynamic algorithm uses the latest bus arrival information, together with estimated baseline travel times, to predict arrival times at the next point. The predicted bus arrival times are examined by data of bus no. 7 in a satellite town of Dalian in China. Results show that the hybrid model proposed in this paper is feasible and applicable in bus arrival time forecasting area, and generally provides better performance than artificial neural network (ANN)–based methods. Copyright © 2010 John Wiley & Sons, Ltd.

ROUTE PLANNING METHODOLOGY OF AN ADVANCED TRAVELLER INFORMATION SYSTEM IN VILNIUS CITY

As a subsystem of an Intelligent Transportation System (ITS), an Advanced Traveller Information System (ATIS) disseminates real‐time traffic information to travellers. To help them with making better decisions on choosing their routes, a strong need to predict traffic congestion and to disseminate the predicted congestion information relating to travellers can be seen. This paper describes a methodology used by drivers for calculating an optimal driven route in Vilnius. The paper discusses how ATIS systems will likely evolve the experience of Information Service Providers (ISP) and optimal route planning calculations. A few methods of route planning have been taken into account. The paper presents the following types of route calculation: 1) the shortest route; 2) the quickest route; 3) the quickest forecasted route according to historical traffic information. Also, the paper deals with the architecture of the WEB based information system for drivers in Vilnius and analyzes data on traffic workflow. Furthermore, a comprehensive route planning procedure that forecasts data on driving time considering historical traffic is followed.

Real-time Traveler Information Performance Measures for Work Zone Congestion Management

This study evaluates the use of an advanced traveler information system (ATIS) to promote the use of alternative routes and improve local road network performance during work projects. The ATIS system was implemented on a four-lane divided highway in Edgerton, Wisconsin during a bridge reconstruction. Field comparisons between ATIS presence and absence showed different diversion patterns in northbound and southbound directions associated with traffic delay. Drivers remained on the freeway when the displayed delay was less than 15 minutes while more drivers chose to leave the freeway with displayed delay greater than or equal to 15 minutes. A linear regression analysis showed that freeway volume, ramp exiting volume during normal days, and delay time were significant variables associated with a high diversion rate. The ATIS also was shown to perform effectively in increasing the work zone operational capacity.

Web-Based Advanced Traveler Information System for Developing Countries

Advanced traveler information systems (ATISs) are continuously becoming key intelligent transportation system for disseminating valuable traveler information such as traffic, incident, and transit information. Developed countries such as the United States, Canada, Japan, U.K., Australia, and Germany have adopted ATIS expeditiously in comparison to developing countries that face considerable financial and framework constraints. Moreover, local traffic, roadway, signalization, demographic, topological, and social conditions in developing countries are quite different from those in developed countries. In this paper, a comprehensive framework comprising of system architecture, development methodology, and salient features of a developed ATIS for metropolitan cities in developing countries has been discussed. Development of proposed system is based on integration of two well-known information technologies, viz., geographic information systems and World Wide Web. Combination of these technologies can be used to develop an integrated ATIS that targets different types of travelers such as private vehicle owners, transit users, and casual outside visitors.

INFLUENCE OF TRAFFIC BOTTLENECK ON TWO-ROUTE SCENARIO WITH MEAN VELOCITY INFORMATION FEEDBACK

In this paper, traffic bottleneck is introduced on one of the routes (say route A) in a two-route scenario with mean velocity information feedback. The simulations show that four different system states, i.e. zero state (no dynamic vehicle chooses route A), periodic oscillation state (mean velocity on route A is in periodic oscillations), alternation state (alternation of zero state and oscillation state), and equal velocity state (mean velocities on the two routes are equal), are identified. Complex nonlinear changing behavior of critical vehicle arrival probability λcdepending on bottleneck length and location as well as dynamic vehicle ratio is revealed. Our work is expected to be useful for designing Advanced Traveller Information Systems.

New travel time prediction algorithms for intelligent transportation systems

Recently, travel time prediction has become a crucial part of trip panning and dynamic route guidance for many advanced traveler information and transportation management systems. Moreover, a scalable prediction system with high accuracy is critical for the successful deployment of ATIS (Advanced Travelers Information Systems) in road networks. In this paper, we propose two travel time prediction algorithms using naive Bayesian classification and rule-based classification. Both classification techniques provide a velocity class to be used for measuring travel time accurately. Our algorithms exhibit high accuracy in predicting travel time when using a large amount of historical traffic database. In addition, our travel time prediction algorithms are suitable for road networks with arbitrary travel routes. It is shown from our performance comparison, our travel time prediction algorithms significantly outperform the existing prediction algorithms, such as the link-based algorithm, the switching model, and the linear regression algorithm. In addition, it is revealed that our algorithm using naive Bayesian classification is better on the performance of mean absolute relative error than our algorithm using rule-based classification.

Intelligent Transportation System as Evaluation Tool in a Regional Demand Modeling Environment

A number of tools have been developed to support the evaluation of intelligent transportation system (ITS) alternatives. However, the methodologies and some associated parameters in these tools were developed and selected before widespread deployments of ITSs. Significant experience gained with ITS in recent years warrants a new assessment of the evaluation methodologies and parameters of these systems. There are also advantages to incorporating the evaluation of ITS deployments as part of existing regional demand forecasting modeling environments rather than using external tools to perform this functionality. This paper discusses the development and implementation of a tool and methodologies to estimate the benefits and costs of these systems as part of a travel demand forecasting modeling environment. It also presents an application of the developed tool to evaluate two of the most widely deployed types of ITS: incident management and advanced traveler information systems. Case study results indicate that the methodologies developed in this study can be used to assess ITS deployments.

Parallel SMO for Traffic Flow Forecasting

Accurate traffic flow forecasting is crucial to the development of intelligent transportation systems and advanced traveler information systems. Since Support Vector Machine (SVM)have better generalization performance and can guarantee global minima for given training data, it is believed that SVR is an effective method in traffic flow forecasting. But with the sharp increment of traffic data, traditional serial SVM can not meet the real-time requirements of traffic flow forecasting. Parallel processing has been proved to be a good method to reduce training time. In this paper, we adopt a parallel sequential minimal optimization (Parallel SMO) method to train SVM in multiple processors. Our experimental and analytical results demonstrate this model can reduce training time, enhance speed-up ratio and efficiency and better satisfy the real-time demands of traffic flow forecasting.

Development of a Latent Variable Model to Capture the Impact of Risk Aversion on Travelers' Switching Behavior

Advanced Traveler Information Systems (ATIS) are becoming increasingly available throughout the world. While the impact of the provided information on the switching behavior has been investigated in the past, an area of research that is less well understood relates to the effect of the travelers' risk aversion (or risk-seeking) in their travel behavior. The objective of this research is to examine the impact of information acquisition on travelers' switching travel behavior and to identify and quantify the role of attitudes and perceptions on switching behavior. A combined choice and latent variable model has been developed, in which the individual traveler's risk aversion has been modeled as a latent variable. The model has been estimated using data collected through travel diaries in the Puget Sound Region (PSRC) in 2000. As expected, travelers in general tend to maintain their habitual travel pattern. However, specific travel information-such as that regarding an incident or road closure-influences behavioral switches such as departure time change and route change.

Analyzing Travelers’ Intention to Accept Travel Information

Advanced traveler information systems (ATIS) cannot improve the traffic environment if travelers do not accept the travel information provided by the system. To understand better why travelers accept or refuse travel information and to explain, predict, and increase travelers’ acceptance of travel information, a research framework based on the technology acceptance model is developed to establish the relationship between travelers’ intention to accept travel information, trust in travel information, perceived usefulness of travel information, perceived ease of its use, and other related variables. Then structural equation modeling is used to examine and analyze the relationship among these variables. The results show that the factors that significantly determine travelers’ intention to accept travel information are trust in travel information, its perceived usefulness, its perceived ease of use, and information attributes. Through an examination of the direct, indirect, and total effects in the model system, it is discovered that perceived ease of use has the largest total effect on intention to accept by a standardized coefficient of 0.522, followed by trust in information (0.348), perceived usefulness (0.199), and information attributes (0.079). These results indicate the practical value of the estimated model for guiding recommendations aimed at increasing travelers’ intention to accept travel information and at improving the service quality of travel information in China.

Special Issue: Knowledge-based intelligent systems and their applications

Intelligent techniques derived from knowledge-based engineering and related computing paradigms have provided useful concepts and tools to undertake a variety of real-world problems. These systems mimic the analytical and learning capabilities of the human brain. They harness the benefits of knowledge and intelligence to form an integrated framework for problem solving. In this special issue, a total of thirteen articles comprising extended papers from the 12th International Conference on Knowledge-Based and Intelligent Information & Engineering Systems (KES2008) as well as from other submissions that highlight a small number of innovative knowledge-based intelligent systems and their applications to solving problems in different domains are presented. A summary of each article is as follows. With the development of advanced travelers information systems, it is important to have a prompt and accurate travel time prediction system for road networks. In the first article, two travel time prediction algorithms using naive Bayesian classification and rulebased classification are proposed. Based on a historical traffic database, the algorithms are able to yield high accuracy in travel time prediction. The algorithms are also useful for road networks with arbitrary travel routes. The results also reveal that naive Bayesian classification produces better mean absolute relative error than that of rule-based classification. For large-scale complex process plants that involve safety critical systems, real-time diagnosis is an important aspect. In the second article, an ontology for

Predicting Freeway Travel Time under Incident Conditions

Prediction of corridor travel time is essential to achieving the promise of advanced traveler information systems. Although much research has been done on travel time prediction, procedures for practical prediction of travel time under incident conditions are lacking. This paper presents a framework for online prediction of freeway corridor travel time under incident conditions on the basis of inductive loop detector and incident data. The core component is a model for prediction of corridor travel time under incident conditions that produces estimated physical queue length at various time intervals. Testing shows that the method offers enhanced accuracy in prediction of corridor travel time compared with those methods that do not consider the impact of incidents.

Freeway Sensor Spacing and Probe Vehicle Penetration

Accurate travel time prediction–estimation is important for advanced traveler information systems and advanced traffic management systems. Traffic managers and operators are interested in estimating optimal sensor density for new construction and retrofits. In addition, with the development of vehicle-tracking technologies, they may be interested in estimating optimal probe vehicle percentage. Unlike most studies focusing on data-driven models, this paper extends some limited previous work and describes a concept developed from first principles of traffic flow. The goal is to establish analytical relationships between travel time prediction–estimation accuracy and sensor spacing by means of two basic travel time prediction–estimation algorithms, as well as to probe vehicle penetration rate. The methods are based on computing the magnitude of under- and overprediction–estimation of total travel time (TTT) during shock passages in a time–space plane by using the midpoint method for online travel time prediction and the Coifman method for offline travel time estimation. Three shock wave configurations are assessed with each method so as to consider representative traffic dynamics situations. TTT prediction–estimation errors are calculated and expressed as a function of sensor spacing and probe vehicle percentage. Optimal sensor spacing is calculated with consideration of the tradeoff between TTT estimation error and sensor deployment cost. The results from this study can provide simple and effective support for detector placement and probe vehicle deployment, especially along a freeway corridor with existing detectors. Optimal sensor spacing results are analyzed and compared for various methods of travel time estimation during different types of shock waves.

Advanced Traveler Information System for Guiding Route Choice to Ocean City, Maryland

A real-time advanced traveler information system for traffic heading to Ocean City, Maryland, is presented. It can provide dynamic route choice guidance for en route travelers, offer web-based historical data for pretrip tourists, and perform real-time traffic monitoring as well as emergency evacuation for responsible agencies with its 40 detectors. The proposed system is designed to contend with most critical issues associated with real-time operations, including automated detection of incidents, reliable estimation of missing data, and continuous updates of historical databases. Implementation results demonstrate that the travel time information displayed by the proposed system has been well received by drivers and is viewed as the primary resource for choice of routes to Ocean City. The evolution of traffic volumes on alternative routes during congested periods reveals that the travel time information from variable message signs not only provides guidance to drivers but also leads to better use of roadway capacity and results in more throughputs for the same period of operation.

Route Change Decision Making by Hurricane Evacuees Facing Congestion

Successful evacuations of metropolitan areas require overcoming unexpected congestion that reduces traffic flows. Congestion may result from accidents, incidents, or other events that reduce road capacity. Traffic professionals and emergency managers may promote deviations from planned routes to bypass an area of congestion and speed mass exit. However, some route changes may actually reduce traffic flow rates, and in these cases decision makers may want to discourage use of alternate routes. By using results of a behavioral survey of potential hurricane evacuees, this study identifies variables associated with the decision to alter routes and also identifies frequently used information sources. A dynamic traffic simulation with a decision-making model using this information is proposed as a means for evacuation decision makers to assess impacts of driver decisions. Results from more than 800 responses showed the potentially strong influence of effective advanced traveler information systems to support decisions made by hurricane evacuees on whether to use an alternate route when faced with congestion. Results of this study are a timely contribution to those seeking a better understanding of driver behavior during evacuations and improvement of emergency management efficiency and efficacy.

Inefficiency of Logit-Based Stochastic User Equilibrium in a Traffic Network Under ATIS

This paper makes a contribution to the literature by bounding the travel time inefficiency of the logit-based stochastic user equilibrium (SUE) under Advanced Traveler Information Systems (ATIS). All drivers are divided into two groups, one equipped with ATIS and another without, and both of which follow the logit-based SUE principle in making route choices. The equipped drivers have less degree of travel time variability than the unequipped ones. The inefficiency of the two-user class SUE is defined in two different ways, i.e., in comparison with the SO in terms of total actual system travel time, or in comparison with the corresponding SSO in terms of total perceptive system travel time of all users. The effects of various parameters on the bounds are further investigated. It is found that the inefficiency bound against the SSO is only dependent upon the degree of link congestion and independent of the network topology. In contrast, besides the effect of the degree of link congestion, the increasing of total demand and network complexity will also make the inefficiency bound against the SO go up, while the promotion of ATIS market penetration and perception benefit will reduce the bound.