Real-time Travel Time Information Research Articles

Artificial Neural Network Travel Time Prediction Model for Buses Using Only GPS Data

Real-time and accurate travel time information of transit vehicles is valuable as it allows passengers to plan their trips to minimize waiting times. The objective of this research was to develop a dynamic artificial neural network (ANN) model that can provide accurate prediction of bus travel times to give real-time information at a given downstream bus stop using only global positioning system (GPS) data. The ANN model is trained off-line but can be used to provide real-time travel time information. To achieve this, care was taken in selecting a unique set of input-output combinations for prediction. The results obtained from the case study are promising to implement an Advanced Public Transportation System (APTS). The performance of the proposed ANN model was compared with a historical average model under two criteria: prediction accuracy and robustness. It was shown that the ANN outperformed the average approach in both aspects.

Switching threshold of commuting Travelers’ route choice under different patterns of information

Travelers always exhibit bounded rationality due to limited perception. Based on the theory of bounded rationality, switching thresholds under different patterns of information are analyzed in this paper. An experiment platform including four scenarios, such as historical descriptive information, real-time descriptive information, historical travel time information and real-time travel time information is designed to obtain the participants’ travel preference and route choice behavior. The relationship among route switching behavior, perceived travel time difference and travelers’ preference is analyzed based on experiment’s results. The Probit regression method is utilized for calibrating the switching threshold under different patterns of information. The results prove the dissimilarity of switching thresholds in diverse patterns of information. The switching threshold under real-time information is lower than that under historical information. The estimated results of risk parameters prove that the traveler has a slight tendency to pursue risk. The method proposed in this paper can effectively quantify the degree of bounded rationality.

Data Processing Techniques for Real-Time Traveler Information: Use of Dedicated Short-Range Communications Probes on Suburban Arterial

Background:As wireless communication technologies evolve, probe-based travel-time collection systems are becoming popular around the globe. However, two problems generally arise in probe-based systems: one is the outlier and the other is time lag. To resolve the problems, methods for outlier removal and travel-time prediction need to be applied.Methods:In this study, data processing methods for addressing the two issues are proposed. After investigating the characteristic of the travel times on the test section, the modified z-score was suggested for censoring outliers contained in probe travel times. To mitigate the time-lag phenomenon, a recurrent neural network, a class of deep learning where temporal sequence data are normally treated, was applied to predict travel times.Results:As a result of evaluation with ground-truth data obtained through test-car runs, the proposed methods showed enhanced performances with prediction errors lower than 13% on average compared to current practices.Conclusion:The suggested methods can make drivers to better arrange their trip schedules with real-time travel-time information with improved accuracy.

Sequential Route Choice Modeling Based on Dynamic Reference Points and Its Empirical Study

Aiming at the influence of information, we investigate and analyze the sequential route choice behavior under dynamic reference points based on cumulative prospect theory in this paper. An experiment platform collecting the sequential route choices based on C/S structure is designed and four types of information are released to participants, respectively. Real-time travel time prediction methods are then proposed for travelers’ decision-making. Using nonlinear regression method, the parameters of the value function and weight function of cumulative prospect theory are estimated under different types of information, respectively. It is found that travelers’ behavior showed obvious characteristic of risk pursuit under the circumstance where real-time travel time information is released. Instead, when they have access to descriptive information, they tend to be more conservative.

Method for the Annual Accuracy Assessment of Freeway Travel Time Systems

Motivated by Title 23 Code of Federal Regulation 511, the U.S. Department of Transportation has recently established real-time systems management information programs to improve the consistency of traveler information provided to the public. Part of these requirements is to review the quality of the information provided to the public. Because limited information is available about current practices for meeting this new regulation, this article presents a method of evaluating real-time travel time information along metropolitan interstate freeways in the context of 23 CFR (Code of Federal Regulations) 511. This article presents a method and a case study of collecting travel time information from multiple sources (such as Google Maps and TravelMidwest.com ) and comparing them to measure accuracy. The findings suggested that the travel time information in the Chicago, Illinois, metropolitan area meets the accuracy requirements of 23 CFR 511, and this study has identified areas for future improvement and system expansion.

THE SENSOR LOCATION PROBLEM: METHODOLOGICAL APPROACH AND APPLICATION

The sensor location problem is of particular importance when planning the allocation of limited field equipment intended to be used for advanced traffic management systems and traveller information services. The locations within a network that satisfy specific goals need to be carefully selected, based on predefined goals related to the effective collection of data and the subsequent estimation of traffic related information. The detection of traffic volumes is mainly associated with two purposes, the travel time and the Origin–Destination (O–D) trip matrix estimation. In this context, this paper presents a quadratic programing model, able to determine the optimal location of tracking sensors. The model is implemented in the urban road network of the city of Thessaloniki (Greece) in which specific number of sensors is installed and utilized for real-time travel time information provision. The proposed methodology models the sensor location problem under the general framework of a set covering problem, which is one of the most popular optimization problems and has been applied in many industrial problems. The results of the case study in Thessaloniki reveal that the proposed model defines the optimal location of the limited number of sensors in such a way that the network, which is created having all sensors as origin or destination of all possible paths, represents to great extent (87% of the traffic flow along the major paths) the traffic volumes of the whole road network of the city.

Mitigating flash crowd effect using connected vehicle technology

A Flash Crowd Effect (FCE) occurs when in the case of non-recurring congestion a large portion of drivers follows similar re-routing advice. Consequently, congestion is transferred from one road to another. Coping with the FCE is challenging, especially if the congestion results from a temporary loss of capacity (e.g. due to a traffic incident). The existing route guidance systems do not address FCE, as they either do not consider the effects of guidance on the rest of the road network, or predict link travel times based on the number of vehicles travelling on the link, which in the case of the loss of capacity is unreliable. We demonstrate that the FCE can be addressed in a distributed way with Vehicle-to-Vehicle (V2V) communication provided by Connected Vehicle (CV) technology. The proposed in-vehicle TrafficEQ system provides vehicles with mixed route guidance strategy—i.e. a route is autonomously chosen by the vehicle with a probability that is inversely proportional to the latest reported travel time on the route. Real-time travel time information is crowd-sourced by TrafficEQ users. Using realistic simulations of incident-related capacity drops on a classic two-route highway example and a realistic urban road network, we demonstrate that TrafficEQ can address the FCE by reducing travel time oscillations among the alternative routes. The system's drawbacks—in particular the occasional necessity of providing incentives to follow the guidance—are discussed.

Dynamic Bus Travel Time Prediction Models on Road with Multiple Bus Routes.

Accurate and real-time travel time information for buses can help passengers better plan their trips and minimize waiting times. A dynamic travel time prediction model for buses addressing the cases on road with multiple bus routes is proposed in this paper, based on support vector machines (SVMs) and Kalman filtering-based algorithm. In the proposed model, the well-trained SVM model predicts the baseline bus travel times from the historical bus trip data; the Kalman filtering-based dynamic algorithm can adjust bus travel times with the latest bus operation information and the estimated baseline travel times. The performance of the proposed dynamic model is validated with the real-world data on road with multiple bus routes in Shenzhen, China. The results show that the proposed dynamic model is feasible and applicable for bus travel time prediction and has the best prediction performance among all the five models proposed in the study in terms of prediction accuracy on road with multiple bus routes.

Real-time travel time predictor for route guidance consistent with driver behavior

Providing reliable real-time travel time information is a critical challenge to all existing traffic routing systems. This study develops a new model for estimating and predicting real-time traffic conditions and travel times for variable message signs-based route guidance system. The proposed model is based on real-time limited detected traffic data, stochastic nonlinear macroscopic traffic flow model, and adaptive Kalman filtering theory. The method has the following main features: (1) real-time estimation and prediction of traffic conditions on a network level using limited traffic detectors, (2) travel time prediction in free flow and congested flow, and (3) prediction of drivers’ en-route diversion behavior. Field testing is conducted based on the Route Guidance Pilot Project sponsored by the National Science and Technology Ministry of China. The achieved testing results are satisfactory and have potential use for future works and field applications.

Online Travel Time Estimation in Urban Areas Using the Occupancy of Long Loop Detectors

Roads in the Netherlands are often heavily congested. Real-time travel time information can be a valuable instrument to reduce the impact of increasing traffic demand on travel time with advantages for traffic participants as well as for the traffic network managers. For urban roads travel time estimation is a more complex problem than for freeways. In order to provide online, real-time and accurate travel times, in this paper a new estimation approach is developed based on measurements supplied by the (vehicle-dependent) traffic controllers. These measurements include the occupancy from the corresponding long loop, the flow from the short loop, and the green percentages. Based on these measurements the location and length of the queues is estimated. Moreover, the approach transforms the data in a way that the underlying reason(s) of congestion becomes apparent (in terms of bottleneck location), which can be very useful for, e.g., advanced traffic information systems or decision support systems. Compared with the approach based on license plate recognition cameras, which is used in the Netherlands in many locations, this approach is expected to be more accurate in heavily congested situations, since for license plate recognition vehicles have to pass the end of the route before the traveled time can be measured. The approach is tested with real traffic data for an urban route in the Netherlands. The test case presented in the paper shows that the use of the additional data from traffic controllers (occupancy, green percentage, waiting time of first vehicle in queue) is beneficial.

Dynamic Message Sign Deployment and Diversion Behavior of Travelers on Central Florida Toll Roads

Advanced traveler information systems are particularly helpful in supporting route diversion decisions. The effect of information on diversion behavior on nontolled roads is well documented in the literature. Revealed and stated preference studies traditionally have been conducted to analyze route diversion behavior. However, the effect of realtime traffic information on the behavior of toll road users is unexplored. This study examines the behavior of toll road users in Orlando, Florida. Orlando is serviced by a toll road network where dynamic message signs (DMSs) provide real-time travel time information to travelers. The response of toll road users to information was expected to differ from that of non-toll users. To capture the effects of information, specifically the DMS, a survey was conducted in two phases: predeployment (with only one DMS installed) and postdeployment (after 29 DMSs were installed). A detailed behavioral data set with rigorous modeling was used to investigate the relationship between information and travel decisions in the context of toll road trips. The surveys revealed that higher travel time savings due to diversion, 511 use, and toll payment by cash were associated with a greater propensity to divert in postdeployment. Travelers who experienced abnormal travel times or who reported that DMS helped them during congestion were more likely to divert. The study further showed that toll road users might have more inertia and avoid leaving the toll road than non-toll road users. Implications of the results are discussed.

Determinants of Route Choice and Value of Traveler Information

Drivers receive value from traveler information in several ways, including the ability to save time, but perhaps more important is the value of certainty as it affects other personal, social, safety, or psychological factors. This information can be economically valued. The benefit of reduction in driver uncertainty when information is provided at the beginning of the trip is the main variable measured in this research. User preferences for routes were assessed as a function of the presence and accuracy of information while controlling for other trip and route attributes. Data were collected in a field experiment in which 113 drivers, given real-time travel time information with varying degrees of accuracy, drove four alternative routes between a preselected origin-destination pair in the Twin Cities, Minnesota, metropolitan area. Ordinary regression, multinomial, and rank-ordered logit models produced estimates of the value of information with some variation. Results showed that travelers were willing to pay up to $1 per trip for pretrip travel-time information. The value of information is higher for commute and event trips and when congestion on the usual route is heavier. The accuracy of the traveler information was also a crucial factor. Travelers will not pay for information unless they perceive it to be accurate. Most travelers (70%) prefer that such information be provided free by the public sector, whereas some (19%) believe that it is better for the private sector to provide such service at a charge.

A recursive, cell processing model for predicting freeway travel times

Travel time information influences driver behaviour and can contribute to reducing congestion and improving network efficiency. Consequently many road authorities disseminate travel time information on road side signs, web sites and radio traffic broadcasts. Operational systems commonly rely on speed data obtained from inductive loop detectors and estimate travel times using simple algorithms that are known to provide poor predictions particularly on either side of the peak period. This paper presents a new macroscopic model for predicting freeway travel times which overcomes the limitations of operational ‘instantaneous’ speed models by drawing on queuing theory to model the processing of vehicles in sections or cells of the freeway. The model draws on real-time speed, flow and occupancy data and is formulated to accommodate varying geometric conditions, the relative distribution of vehicles along the freeway, variations in speed limits, the impact of ramp flows and fixed or transient bottlenecks. Field validation of the new algorithm was undertaken using data from two operational freeways in Melbourne, Australia. Consistent with the results of simulation testing, the validation confirmed that the recursive model provided a substantial improvement in travel time predictions when compared to the model currently used to provide real-time travel time information to motorists in Melbourne.

Simulation Model for Real-Time Emergency Vehicle Dispatching and Routing

A simulation model for evaluation of a real-time emergency medical service vehicle response system that uses real-time travel time information and that assists the emergency vehicle dispatchers in assigning response vehicles and guiding those vehicles through noncongested routes is developed. Different response strategies are evaluated with this simulation model. These include the first-called, first-served strategy, the nearest-origin assignment strategy, and the flexible assignment strategy that uses real-time travel time information to assign and dispatch response vehicles. Different assumptions and conditions are used to test the sensitivity of the flexible assignment strategy.