Practical approach for travel time estimation from point traffic detector data

Accurate estimation of travel time is critical to the success of advanced traffic management systems and advanced traveler information systems. Travel time estimation also provides basic data support for travel time reliability research, which is being recognized as an important performance measure of the transportation system. This paper investigates a number of methods to address the three major issues associated with travel time estimation from point traffic detector data: data filling for missing or error data, speed transformation from time‐mean speed to space‐mean speed, and travel time estimation that converts the speeds recorded at detector locations to travel time along the highway segment. The case study results show that the spatial and temporal interpolation of missing data and the transformation to space‐mean speed improve the accuracy of the estimates of travel time. The results also indicate that the piecewise constant‐acceleration‐based method developed in this study and the average speed method produce better results than the other three methods proposed in previous studies. Copyright © 2011 John Wiley & Sons, Ltd.     

Experienced travel time prediction for congested freeways

Travel time is an important performance measure for transportation systems, and dissemination of travel time information can help travelers make reliable travel decisions such as route choice or departure time. Since the traffic data collected in real time reflects the past or current conditions on the roadway, a predictive travel time methodology should be used to obtain the information to be disseminated. However, an important part of the literature either uses instantaneous travel time assumption, and sums the travel time of roadway segments at the starting time of the trip, or uses statistical forecasting algorithms to predict the future travel time. This study benefits from the available traffic flow fundamentals (e.g. shockwave analysis and bottleneck identification), and makes use of both historical and real time traffic information to provide travel time prediction. The methodological framework of this approach sequentially includes a bottleneck identification algorithm, clustering of traffic data in traffic regimes with similar characteristics, development of stochastic congestion maps for clustered data and an online congestion search algorithm, which combines historical data analysis and real-time data to predict experienced travel times at the starting time of the trip. The experimental results based on the loop detector data on Californian freeways indicate that the proposed method provides promising travel time predictions under varying traffic conditions.     

Modeling the effects of traveler information on freeway origin–destination demand prediction

The primary focus of this research is to develop an approach to capture the effect of travel time information on travelers’ route switching behavior in real-time, based on on-line traffic surveillance data. It also presents a freeway Origin–Destination demand prediction algorithm using an adaptive Kalman Filtering technique, where the effect of travel time information on users’ route diversion behavior has been explicitly modeled using a dynamic, aggregate, route diversion model. The inherent dynamic nature of the traffic flow characteristics is captured using a Kalman Filter modeling framework. Changes in drivers’ perceptions, as well as other randomness in the route diversion behavior, have been modeled using an adaptive, aggregate, dynamic linear model where the model parameters are updated on-line using a Bayesian updating approach. The impact of route diversion on freeway Origin–Destination demands has been integrated in the estimation framework. The proposed methodology is evaluated using data obtained from a microscopic traffic simulator, INTEGRATION. Experimental results on a freeway corridor in northwest Indiana establish that significant improvement in Origin–Destination demand prediction can be achieved by explicitly accounting for route diversion behavior.     

Bus running time prediction using a statistical pattern recognition technique

Abstract

Given that real-time bus arrival information is viewed positively by passengers of public transit, it is useful to enhance the methodological basis for improving predictions. Specifically, data captured and communicated by intelligent systems are to be supplemented by reliable predictive travel time. This paper reports a model for real-time prediction of urban bus running time that is based on statistical pattern recognition technique, namely locally weighted scatter smoothing. Given a pattern that characterizes the conditions for which bus running time is being predicted, the trained model automatically searches through the historical patterns which are the most similar to the current pattern and on that basis, the prediction is made. For training and testing of the methodology, data retrieved from the automatic vehicle location and automatic passenger counter systems of OC Transpo (Ottawa, Canada) were used. A comparison with other methodologies shows enhanced predictive capability.     

Hybrid model for prediction of bus arrival times at next station

Effective 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.     

International experience with speed limits during and prior to the energy crisis of 1973–4

This paper presents an artificial neural network (ANN) based method for estimating route travel times between individual locations in an urban traffic network. Fast and accurate estimation of route travel times is required by the vehicle routing and scheduling process involved in many fleet vehicle operation systems such as dial‐a‐ride paratransit, school bus, and private delivery services. The methodology developed in this paper assumes that route travel times are time‐dependent and stochastic and their means and standard deviations need to be estimated. Three feed‐forward neural networks are developed to model the travel time behaviour during different time periods of the day‐the AM peak, the PM peak, and the off‐peak. These models are subsequently trained and tested using data simulated on the road network for the City of Edmonton, Alberta. A comparison of the ANN model with a traditional distance‐based model and a shortest path algorithm is then presented. The practical implication of the ANN method is subsequently demonstrated within a dial‐a‐ride paratransit vehicle routing and scheduling problem. The computational results show that the ANN‐based route travel time estimation model is appropriate, with respect to accuracy and speed, for use in real applications.     

Probe vehicle based real-time traffic monitoring on urban roadways

Travel time estimation and prediction on urban arterials is an important component of Active Traffic and Demand Management Systems (ATDMS). This paper aims in using the information of GPS probes to augment less dynamic but available information describing arterial travel times. The direction followed in this paper chooses a cooperative approach in travel time estimation using static information describing arterial geometry and signal timing, semi-dynamic information of historical travel time distributions per time of day, and utilizes GPS probe information to augment and improve the latter. First, arterial travel times are classified by identifying different travel time states, then link travel time distributions are approximated using mixtures of normal distributions. If prior travel time data is available, travel time distributions can be estimated empirically. Otherwise, travel time distribution can be estimated based on signal timing and arterial geometry. Real-time GPS travel time data is then used to identify the current traffic condition based on Bayes Theorem. Moreover, these GPS data can also be used to update the parameters of the travel time distributions using a Bayesian update. The iterative update process makes the posterior distributions more and more accurate. Finally, two comprehensive case studies using the NGSIM Peachtree Street dataset, and GPS data of Washington Avenue in Minneapolis, were conducted. The first case study estimated prior travel time distributions based on signal timing and arterial geometry under different traffic conditions. Travel time data were classified and corresponding distributions were updated. In addition, results from the Bayesian update and EM algorithm were compared. The second case study first tested the methodologies based on real GPS data and showed the importance of sample size. In addition, a methodology was proposed to distinguish new traffic conditions in the second case study.     

Incorporating uncertainty into short-term travel time predictions

To improve the quality of travel time information provided to motorists, there is a need to move away from point forecasts of travel time. Specifically, techniques are needed which predict the range of travel times which motorists may experience. This paper focuses on travel time prediction on motorways and evaluates three models for predicting the travel time range in real time as well as up to 1 h ahead. The first model, termed lane by lane tracing, relies on speed data from each lane to replicate the trajectories of relatively slow and relatively fast vehicles on the basis of speed differences across the lanes. The second model is based on the relationship between mean travel time (estimated using a neural network model) and driver-to-driver travel time variability. The results provide insight into the relative merits of the proposed techniques and confirm that they provide a basis for reliable travel time range prediction in the short-term prediction context (up to 1 h ahead).     

Estimating performance of traffic signals based on link travel times

Recent advances in communication and computing technology have made travel time measurements more available than ever before. In urban signalized arterials, travel times are strongly influenced by traffic signals. This study presents a novel method based on well‐known principles to estimate traffic signal performance (or more precisely their major “through” movements) based on travel time measurements. The travel times were collected between signals in the field by using point‐to‐point travel time measurement technologies. Closed‐circuit television cameras and signal databases were used to collect traffic demand and signal timings, respectively. Then, the volume/capacity ratio of major downstream signal movements was computed based on demand and signal timings. This volume/capacity ratio was then correlated with travel times on the relevant intersection approach. The best volume‐delay function was found, along with many other functions, to fit the field data. This volume‐delay function was then used to estimate volume/capacity ratios and, indirectly, a few other signal performance metrics. The method, called travel time‐based signal performance measurements, was automated and displayed on a Google Map. The findings show that the proposed method is accurate and robust enough to provide necessary information about signal performance. A newly developed volume‐delay function was found to work just slightly better than the Bureau of Public Roads curve. Several issues, which may reduce the accuracy of the proposed method, are identified, and their solutions are proposed for future research. Copyright © 2016 John Wiley & Sons, Ltd.     

Modeling Travel Time Under ATIS Using Mixed Linear Models

The objective of this paper is to model travel time when drivers are equipped with pre-trip and/or en-route real-time traffic information/advice. A travel simulator with a realistic network and real historical congestion levels was used as a data collection tool. The network included 40 links and 25 nodes. This paper presents models of the origin-to-destination travel time and en-route short-term route (link) travel time under five different types and levels of advanced traveler information systems (ATIS). Mixed linear models with the repeated observation's technique were used in both models. Different covariance structures (including the independent case) were developed and compared. The effect of correlation was found significant in both models. The trip travel time analysis showed that as the level of information increases (adding en-route to the pre-trip and advice to the advice-free information), the average travel time decreases. The model estimates show that providing pre-trip and en-route traffic information with advice could result in significant savings in the overall travel time. The en-route short-term (link) travel time analysis showed that the en-route short-term (link) information has a good chance of being used and followed. The short-term qualitative information is more likely to be used than quantitative information. Learning and being familiar with the system that provides the information decreases en-route short-term delay.     

Reducing bias in probe-based arterial link travel time estimates

The use of probe vehicles to provide estimates of link travel times has been suggested as a means of obtaining travel times within signalized networks for use in advanced traveler information systems. Previous research has shown that bias in arrival time distributions of probe vehicles will lead to a systematic bias in the sample estimate of the mean. This paper proposes a methodology for reducing the effect of this bias. The method, based on stratified sampling techniques, requires that vehicle count data be obtained from an in-road loop detector or other traffic surveillance method. The effectiveness of the methodology is illustrated using simulation results for a single intersection approach and for an arterial corridor. The results for the single intersection approach indicate a correlation (R²) between the biased estimate and the population mean of 0.61, and an improved correlation between the proposed estimation method and the population mean of 0.81. Application of the proposed method to the arterial corridor resulted in a reduction in the mean travel time error of approximately 50%, further indicating that the proposed estimation method provides improved accuracy over the typical method of computing the arithmetic mean of the probe reports.     

Accuracy of distance‐based travel time decomposition in probe vehicle systems

Probe vehicle data (PVD) are commonly used for area‐wide measurements of travel time in road networks. In this context, travel times usually refer to fixed edges of an underlying (digital) map. That means measured travel times have to be transformed into so‐called link travel times first. This paper analyzes a common method being applied for solving this task (distance‐based travel time decomposition). It is shown that, in general, its inherent imprecision must not be neglected. Instead, it might cause a serious misinterpretation of data if potential errors in the context of travel time decomposition are ignored. For this purpose, systematic as well as maximum deviations between “decomposed” and “true” link travel times are mathematically analyzed. By that, divergent statements in the literature about the accuracy of PVD are harmonized. Moreover, conditions for the applicability of the so‐called distance‐proportion method are derived depending on the permitted error level. Three examples ranging from pure theory to real world confirm the analytical findings and underline the problems resulting from distance‐based travel time decomposition at local level, for example, at individual intersections. Copyright © 2013 John Wiley & Sons, Ltd.     

Modeling real-time human mobility based on mobile phone and transportation data fusion

Even though a variety of human mobility models have been recently developed, models that can capture real-time human mobility of urban populations in a sustainable and economical manner are still lacking. Here, we propose a novel human mobility model that combines the advantages of mobile phone signaling data (i.e., comprehensive penetration in a population) and urban transportation data (i.e., continuous collection and high accuracy). Using the proposed human mobility model, travel demands during each 1-h time window were estimated for the city of Shenzhen, China. Significantly, the estimated travel demands not only preserved the distribution of travel demands, but also captured real-time bursts of mobility fluxes during large crowding events. Finally, based on the proposed human mobility model, a predictive model is deployed to predict crowd gatherings that usually cause severe traffic jams.     

Updating free speed models through mechanistic principles for Indian conditions

The prediction of free speeds of vehicles is an integral part of the economic appraisal of highways. It is to be noted that speeds not only govern the travel time costs, but also have major impacts on Vehicle Operating Costs (VOC). The World Bank has proposed a mechanistic free speed model based on the limiting speed concept for Highway Design and Maintenance (HDM)‐III. This model along with some refinements has been included in HDM‐4. The underlying assumption in the HDM free speed prediction model is that the free speed at any given point of time is the minimum of possible constraining speeds. This paper mainly addresses the methodology considered to update the free speed models through mechanistic principles (based on HDM‐4). This is accomplished by calibration of the model using the current data on free speeds, road and vehicle characteristics. Subsequently, the validation of the developed models has been carried out.     

Travel time estimation from sparse floating car data with consistent path inference: A fixed point approach

Estimation of urban network link travel times from sparse floating car data (FCD) usually needs pre-processing, mainly map-matching and path inference for finding the most likely vehicle paths that are consistent with reported locations. Path inference requires a priori assumptions about link travel times; using unrealistic initial link travel times can bias the travel time estimation and subsequent identification of shortest paths. Thus, the combination of path inference and travel time estimation is a joint problem. This paper investigates the sensitivity of estimated travel times, and proposes a fixed point formulation of the simultaneous path inference and travel time estimation problem. The methodology is applied in a case study to estimate travel times from taxi FCD in Stockholm, Sweden. The results show that standard fixed point iterations converge quickly to a solution where input and output travel times are consistent. The solution is robust under different initial travel times assumptions and data sizes. Validation against actual path travel time measurements from the Google API and an instrumented vehicle deployed for this purpose shows that the fixed point algorithm improves shortest path finding. The results highlight the importance of the joint solution of the path inference and travel time estimation problem, in particular for accurate path finding and route optimization.     

A method for solving the multi‐objective transit frequency optimization problem

Frequency setting takes place at the strategic and tactical planning stages of public transportation systems. The problem consists in determining the time interval between subsequent vehicles for a given set of lines, taking into account interests of users and operators. The result of this stage is considered as input at the operational level. In general, the problem faced by planners is how to distribute a given fleet of buses among a set of given lines. The corresponding decisions determine the frequency of each line, which impacts directly on the waiting time of the users and operator costs. In this work, we consider frequency setting as the problem of minimizing simultaneously users' total travel time and fleet size, which represents the interest of operators. There is a trade‐off between these two measures; therefore, we face a multi‐objective problem. We extend an existing single‐objective formulation to account explicitly for this trade‐off, and propose a Tabu Search solving method to handle efficiently this multi‐objective variant of the problem. The proposed methodology is then applied to a real medium‐sized problem instance, using data of Puerto Montt, Chile. We consider two data sets corresponding to morning‐peak and off‐peak periods. The results obtained show that the proposed methodology is able to improve the current solution in terms of total travel time and fleet size. In addition, the proposed method is able to efficiently suggest (in computational terms) different trade‐off solutions regarding the conflicting objectives of users and operators. Copyright © 2017 John Wiley & Sons, Ltd.     

Modeling the evolutions of day‐to‐day route choice and year‐to‐year ATIS adoption with stochastic user equilibrium

Suppose that in an urban transportation network there is a specific advanced traveler information system (ATIS) which acts for reducing the drivers' travel time uncertainty through provision of pre‐trip route information. Because of the imperfect information provided, some travelers are not in compliance with the ATIS advice although equipped with the device. We thus divide all travelers into three groups, one group unequipped with ATIS, another group equipped and in compliance with ATIS advice and the third group equipped but without compliance with the advice. Each traveler makes route choice in a logit‐based manner and a stochastic user equilibrium with multiple user classes is reached for every day. In this paper, we propose a model to investigate the evolutions of daily path travel time, daily ATIS compliance rate and yearly ATIS adoption, in which the equilibrium for every day's route choice is kept. The stability of the evolution model is initially analyzed. Numerical results obtained from a test network are presented for demonstrating the model's ability in depicting the day‐to‐day and year‐to‐year evolutions.     

Validation of a multimodal travel simulator with travel information provision

This paper presents a computer based travel simulator for collecting data concerning the use of next-generation ATIS and their effects on traveler decision making in a multimodal travel environment. The tool distinguishes itself by presenting a completely abstract multimodal transport network, where knowledge levels are fully controlled for in terms of awareness of mode-route combinations as well as in terms of variability of characteristics of known alternatives. Furthermore, it contains an information service-module that provides a variety of advanced types of travel information, with controlled for levels of reliability. These novel features warrant an extensive validation of the travel simulator. Such a validation is performed, using two datasets (one with revealed data, one with data from an experiment held in the simulator) obtained among 264 participants. Results suggest that the simulator succeeds in collecting useful data on multimodal travel choice making under provision of advanced types of travel information.     

Estimating time dependent O‐D trip tables during peak periods

Intelligent transportation systems (ITS) have been used to alleviate congestion problems arising due to demand during peak periods. The success of ITS strategies relies heavily on two factors: 1) the ability to accurately estimate the temporal and spatial distribution of travel demand on the transportation network during peak periods, and, 2) providing real‐time route guidance to users. This paper addresses the first factor. A model to estimate time dependent origin‐destination (O‐D) trip tables in urban areas during peak periods is proposed. The daily peak travel period is divided into several time slices to facilitate simulation and modeling. In urban areas, a majority of the trips during peak periods are work trips. For illustration purposes, only peak period work trips are considered in this paper. The proposed methodology is based on the arrival pattern of trips at a traffic analysis zone (TAZ) and the distribution of their travel times. The travel time matrix for the peak period, the O‐D trip table for the peak period, and the number of trips expected to arrive at each TAZ at different work start times are inputs to the model. The model outputs are O‐D trip tables for each time slice in the peak period. 1995 data for the Las Vegas metropolitan area are considered for testing and validating the model, and its application. The model is reasonably robust, but some lack of precision was observed. This is due to two possible reasons: 1) rounding‐off, and, 2) low ratio of total number of trips to total number of O‐D pair combinations. Hence, an attempt is made to study the effect of increasing this ratio on error estimates. The ratio is increased by multiplying each O‐D pair trip element with a scaling factor. Better estimates were obtained. Computational issues involved with the simulation and modeling process are discussed.