Journal of Intelligent Transportation Systems Technology Planning and Operations

Published by Taylor & Francis
Online ISSN: 1547-2442
Publications
Article
Understanding how reliability is valued is important because it provides insight into how aims of policies that aspire to provide better transport options can be more fully integrated with user expectations. Better reliability is a desired outcome of transportation policies because it reduces scheduling costs. This study uses a stated preference survey to collect route preference data, in which each route is described by the travel time experience on it. Because travel-time decisions are made from momentary recollections of past experience, the paradigm adopted in this study is that the mode travel time rather than the mean is the important basis for travel time decisions. The authors then explore three alternate measures of reliability and use them to estimate route choice models on the basis of the stated preference data. Two of the measures, range coupled with lateness probability and standard deviation, have been explored before. A third measure based on time moment (moments of inertia) measured from the mode travel time is also proposed and tested. Each measure reveals something different about how people value different aspects of reliability. In all cases, reliability is valued highly, although differently depending on how it is defined. The values of reliability and travel time highlight that transportation policy makers can provide significant benefits to users from strategies that seek to increase reliability.
 
Article
In transportation planning there can be long lead times to adapt capacity. This paper addresses two questions. First, in a one mode world (say rail or road), what is the optimal capacity choice when faced with uncertain demand, long lead times and congestion. Using a simple analytical model it is shown that when demand is inelastic, it is socially optimal to invest more than if only the expected level of demand is taken into account. In this case it may be beneficial to overinvest in capacity because congestion costs are a convex function of relative use. This result holds with or without optimal tolling. The second question deals with two competing modes and where only one mode has long lead times for capacity while the other has flexible capacity. This is typical for the competition between High Speed Rail and air for the medium distance trips (500 to 1000 km), or for the competition between inland waterways and trucks for freight. We find that overinvestment is less justified because the substitute mode can more easily absorb the high demand outcomes.
 
Article
The growing demand for real-time traffic information brought about various types of traffic collection mechanisms in the area of Intelligent Transport Systems (ITS). There are, however, two procedures in making various traffic data into information. First, a robust information-making process of utilizing data into the representative information for each traffic collection mechanism is required. Second, the integration process of fusing the "estimated" information into the "representative information" for each link out of each source is also required. That is, both data reduction and/or data-to-information process and a higher-level information fusion are required. This article focuses on the development of an information fusion algorithm based on a voting technique, fuzzy regression, and Bayesian pooling technique for estimating dynamic link travel time in congested urban road networks. The algorithm has been proposed and validated using field experimental data--GPS probes and detector data collected over various roadway segments. It has been found that the estimated link travel time from the proposed algorithm is more accurate than the mere arithmetic mean counterpart from each traffic source. The limitations of the algorithm and future research agenda have also been discussed.
 
Article
Intelligent transportation systems-based lane management technologies were introduced to work zones in an attempt to reduce congestion and diminish queue lengths. Two forms of lane merging—the early merge and the late merge—were designed to advise drivers on definite merging locations. This study suggests two SDLMS—early merge and late merge—to supplement the current Florida Maintenance of Traffic (MOT) plans. Data were collected in work zones on I-95, Florida using three different traffic maintenance treatments. The first MOT plan treatment was the standard MOT used by the Florida Department of Transportation. The second MOT plan was the early SDLMS, and the third MOT was the late SDLMS. Results showed that the maximum queue discharge rate (or capacity) of the work zone was significantly higher for the early SDLMS compared to the conventional Florida Department of Transportation MOT plans. The late SDLMS did not result in significant increase in the work zone capacity. Moreover, results showed that early merging rate was the highest for the early SDLMS and the lowest for the late SDLMS, which suggests that some drivers were complying with the messages displayed by the system.
 
Article
Recent research on map matching algorithms for land vehicle navigation has been based on either a conventional topological analysis or a probabilistic approach. The input to these algorithms normally comes from the global positioning system (GPS) and digital map data. Although the performance of some of these algorithms is good in relatively sparse road networks, they are not always reliable for complex roundabouts, merging or diverging sections of motorways, and complex urban road networks. In high road density areas where the average distance between roads is less than 100 m, there may be many road patterns matching the trajectory of the vehicle reported by the positioning system at any given moment. Consequently, it may be difficult to precisely identify the road on which the vehicle is travelling. Therefore, techniques for dealing with qualitative terms such as likeliness are essential for map matching algorithms to identify a correct link. Fuzzy logic is one technique that is an effective way to deal with qualitative terms, linguistic vagueness, and human intervention. This article develops a map matching algorithm based on fuzzy logic theory. The inputs to the proposed algorithm are from GPS augmented with data from deduced reckoning sensors to provide continuous navigation. The algorithm is tested on different road networks of varying complexity. The validation of this algorithm is carried out using high precision positioning data obtained from GPS carrier phase observables. The performance of the developed map matching algorithm is evaluated against the performance of several well-accepted existing map matching algorithms. The results show that the fuzzy logic-based map matching algorithm provides a significant improvement over existing map matching algorithms both in terms of identifying correct links and estimating the vehicle position on the links.
 
Article
Adaptive traffic signal control (ATSC) is a promising technique to alleviate traffic congestion. This article focuses on the development of an adaptive traffic signal control system using Reinforcement Learning (RL) as one of the efficient approaches to solve such stochastic closed loop optimal control problem. A generic RL control engine is developed and applied to a multi-phase traffic signal at an isolated intersection in Downtown Toronto in a simulation environment. Paramics, a microscopic simulation platform, is used to train and evaluate the adaptive traffic control system. This article investigates the following dimensions of the control problem: 1) RL learning methods, 2) traffic state representations, 3) action selection methods, 4) traffic signal phasing schemes, 5) reward definitions, and 6) variability of flow arrivals to the intersection. The system was tested on three networks (i.e., small, medium, large-scale) to ensure seamless transferability of the system design and results. The RL controller is benchmarked against optimized pretimed control and actuated control. The RL-based controller saves 48% average vehicle delay when compared to optimized pretimed controller and fully-actuated controller. In addition, the effect of the best design of RL-based ATSC system is tested on a large-scale application of 59 intersections in downtown Toronto and the results are compared versus the base case scenario of signal control systems in the field which are mix of pretimed and actuated controllers. The RL-based ATSC results in the following savings: average delay (27%), queue length (28%), and l CO2 emission factors (28%).
 
Measured and Scaled Occupancy using Proposed CAIDA Scheme
Original and Preprocessd Traffic Volume
Performance Matrix under Variable Incident Duration Lengths
Article
Non-recurrent congestion or incidents are detrimental to the operability and efficiency of busy urban transport networks. There exist multiple automatic incident detection algorithms (AIDAs) to remotely detect the occurrence of an incident in highway or freeway scenarios; however, very little research has been performed to automatically detect incidents in signalized urban arterials. This limited research attention has mostly been focused on developing new urban arterial specific algorithms, rather than identifying alternative methods to synthesize existing freeway-based algorithms for urban conditions. The main hindrance to such synthesis is that the traffic patterns on the signalized urban arterials are significantly different from the same on highways/freeways due to the presence of traffic intersections. This article introduces a new strategy of customizing the existing AIDAs (freeway based or otherwise) to significantly improve their adaptability to signalized urban arterial transport networks. The new strategy focuses on preprocessing the traffic information before being used as input to a freeway/highway-based AIDA to lessen the effect of traffic signals and to imitate the input patterns in highway/freeway-based incident conditions. The effectiveness of this new strategy has been established with the help of four existing AIDAs. The proposed strategy is a simple solution to implement existing algorithms to signalized urban networks without any further instrumentation or operational cost.
 
Article
Traditionally, traffic monitoring requires data from traffic cameras, loop detectors, or probe vehicles that are usually operated by dedicated employees. In efforts to reduce the capital and operational costs associated with traffic monitoring, departments of transportation have explored the feasibility of using global positioning system (GPS) data loggers on their probe vehicles that are postprocessed for analyzing the traffic patterns on desired routes. Furthermore, most cell phones are equipped with embedded assisted-GPS (AGPS) chips, and if the mode of transportation the phone is in can be anonymously identified, the phones can be treated as if they are probe vehicles that are voluntarily hovering throughout the city, at minimal additional costs. Emerging cell phones known as “smartphones” are equipped with additional sensors including an accelerometer and magnetometer. The accelerometer can directly measure the acceleration values, as opposed to having acceleration values derived from speed values in conventional GPS sensors. The magnetometer can measure mode-specific electromagnetic levels. Smartphones are subscribed with roadside Internet data plans that can provide an essential platform for real-time traffic monitoring. In this article, neural network-based artificial intelligence is used to identify the mode of transportation by detecting the patterns of distinct physical profile of each mode that consists of speed, acceleration, number of satellites in view, and electromagnetic levels. Results show that newly available values in smartphones improve the mode detection rates when compared with using conventional GPS data loggers. When smartphones are in known orientations, they can provide three-dimensional (3-D) acceleration values that can further improve mode detection accuracies.
 
Test network 
Network entries [veh/h] over iterations of plain simulation 
Sensor link inflows [veh/h] over iterations of plain simulation 
Network entries [veh/h] over iterations of calibration experiment 2 ( σ =10 veh/h) 
Sensor link inflows [veh/h] over iterations of calibration experiment 2 ( σ =10 veh/h) 
Article
This article describes the first application of a novel path flow and origin/destination (OD) matrix estimator for iterated dynamic traffic assignment (DTA) microsimulations. The presented approach, which operates on a trip-based demand representation, is derived from an agent-based DTA calibration methodology that relies on an activity-based demand model (Flötteröd, Bierlaire, & Nagel, 2011). The objective of this work is to demonstrate the transferability of the agent-based approach to the more widely used OD matrix-based demand representation. The calibration (i) operates at the same disaggregate level as the microsimulation and (ii) has drastic computational advantages over conventional OD matrix estimators in that the demand adjustments are conducted within the iterative loop of the DTA microsimulation, which results in a running time of the calibration that is in the same order of magnitude as a plain simulation. We describe an application of this methodology to the trip-based DRACULA microsimulation and present an illustrative example that clarifies its capabilities.
 
PAG and MAG test networks.
Comparison of the accuracy of the all the three strategies (STD, LVD, TVD) versus memory usage.
Travel time and time interval distribution for LVD and TVD strategies. intelligent transportation systems vol. 18 no. 4 2014
Comparison of computational time LVD and TVD in MAG network.
Article
Within the simulation-based dynamic traffic assignment (SBDTA) model, the time-dependent shortest path (TDSP) algorithm plays a crucial role in the path-set update procedure by solving for the current optimal auxiliary solution (shortest path). Common types of TDSP algorithms require temporal discretization of link/node time/cost data, and the discretization could affect the solution quality of TDSP and of the overall SBDTA as well. This article introduces two variable time-discretization strategies applicable to TDSP algorithms. The strategies are aimed at determining the optimal time discretization for time-dependent links/nodes travel time data. The first proposed strategy produces a specific discretization interval for each link. The second proposed strategy generates time-varying intervals for the same link over the analysis period. The proposed strategies are implemented in a link-based time-dependent A* algorithm in a SBDTA model DynusT and tested with two numerical experiments on two traffic networks. The results show that the proposed discretization methods achieve the research goal—to flexibly and scalably balance the memory usage and run time for SBDTA without degrading the convergence. This property is rather important when dealing with a large real-world network with a long analysis period.
 
Comparisons of Performance Measures
Paired Samples Test
Article
To ensure the effective operation of traffic signal systems, different signal timings should be designed to accommodate traffic pattern variations. One of the greatest challenges is the identification of appropriate time-of-day (TOD) breakpoints, where different signal timings could be implemented during the time periods between two consecutive breakpoints. This research presents an advanced cluster analysis aimed at identifying TOD breakpoints for coordinated, semiactuated modes when it is necessary for multiple intersection operations to be considered simultaneously. Different from previous studies, this proposed methodology considers the time of traffic occurring as one dimension in clustering and uses continuous traffic data obtained through innovative, nonintrusive data collection techniques, which significantly improve this method's performance. The operability of this proposed method is demonstrated in a case study of a corridor located in Tampa, FL. The traffic simulation results reported in this article reveal that this novel procedure performs better than existing TOD signal timing plans.
 
Conceptual diagram of the process used to adjust the travel speed of a bus.
Outline of routes
Observed and theoretical distributions.
Comparison between observed and composite travel time distributions.
Article
The rapid progress of information technology (IT) may provide us with new insights into understanding traffic phenomena, and could help mitigate traffic problems. One of the key applications of IT to traffic and transport analysis is the identification of the location of moving objects using the Global Positioning System (GPS). It is expected that detailed traffic analysis could be carried out using these data. In this article, we first summarize the various applications of probe data in transport analysis. GPS data are merely a sequence of locations, and further data transformation such as map-matching, data-reduction, processing, and reporting is needed to use them effectively. We then discuss the application of bus probe data to evaluating travel time variability and the level of service (LOS) of roads. A methodology for evaluating the road network from the viewpoint of travel time stability and reliability using bus probe data is proposed. Travel time distributions of arbitrary routes are estimated by statistically summing up directly observed multiple travel time distributions. Based on the development of methodologies to estimate travel time distributions of arbitrary routes covered by the bus probe survey, this study proposes an approach to evaluate the LOS of road networks based on the concept of travel time reliability.
 
Updated results from various settings of mean activity duration (S a ) and level of travel time variations ( ). 
Article
This article proposes a maximum-likelihood method to update travel behavior model parameters and estimate vehicle trip chain based on plate scanning. The information from plate scanning consists of the vehicle passing time and sequence of scanned vehicles along a series of plate scanning locations (sensor locations installed on road network). The article adopts the hierarchical travel behavior decision model, in which the upper tier is an activity pattern generation model, and the lower tier is a destination and route choice model. The activity pattern is an individual profile of daily performed activities. To obtain reliable estimation results, the sensor location schemes for predicting trip chaining are proposed. The maximum-likelihood estimation problem based on plate scanning is formulated to update model parameters. This problem is solved by the expectation-maximization (EM) algorithm. The model and algorithm are then tested with simulated plate scanning data in a modified Sioux Falls network. The results illustrate the efficiency of the model and its potential for an application to large and complex network cases.
 
Article
In conventional transportation planning models, it was always assumed that the population density is given and fixed in the study areas. Therefore, the effects of population density on travel choice have not been explicitly incorporated into these existing models for long-term transportation planning. Meanwhile, travel choice models in previous studies are usually developed by using discrete choice theories or user equilibrium principle. Thus, many significant characteristics of travelers’ behaviors, such as risk preference and learning process over time, cannot be considered in these conventional models. This article proposes a convex prospect theory-based model to investigate the effects of population density on the travelers’ mode-choice behavior under an advanced transportation information system (ATIS) in a multimodal transportation corridor. It is shown that population density is closely co-related to the modal split results and dependent on the performance of the railway mode in the study corridor. The park-and-ride mode may not be suitable for areas with high population density. This article also investigates the travelers’ reference points on the generalized travel costs by modes. A numerical example is given to illustrate the properties of the proposed model together with some insightful findings.
 
Article
In this article a nonlinear model predictive control approach to the problem of coordinated ramp metering is presented. The previously designed optimal control tool Advanced Motorway Optimal Control (AMOC) is used within the framework of a hierarchical control structure which consists of three basic layers: the estimation/prediction layer, the optimization layer, and the direct control layer. More emphasis is given to the last two layers where the control actions on a network-wide and on a local level, respectively, are decided. The hierarchical control strategy combines AMOC’s coordinated ramp metering control with local feedback Asservissement LIn´eaire d’Entr´e Autorouti`ere (ALINEA) control in an efficient way. Simulation investigations for the Amsterdam ring-road are reported whereby the results are compared with those obtained by applying ALINEA as a stand-alone strategy. It is shown that the proposed control scheme is efficient, fair, and real-time feasible.
 
Article
Freeway incidents not only threaten travelers’ safety but also cause severe congestion. Incident-induced delay (IID) refers to the extra travel delay resulting from incidents on top of the recurrent congestion. Quantifying IID would help people better understand the real cost of incidents, maximize the benefit-cost ratio of investment on incident remedy actions, and develop active traffic management and integrated corridor management strategies. By combining a modified queuing diagram and short-term traffic flow forecasting techniques, this study proposes an approach to estimate the temporal IID for a roadway section, given that the incidents occurs between two traffic flow detectors. The approach separates IID from the total travel delay, estimates IID for each individual incident, and only takes volume as input for IID quantification, avoiding using speed data that are widely involved in previous algorithms yet are less available or prone to poor data quality. Therefore, this approach can be easily deployed to broader ranges where only volume data are available. To verify its estimation accuracy, this study captures two incident videos and extracts ground-truth IID data, which is rarely done by previous studies. The verification shows that the IID estimation errors of the proposed approach are within 6% for both cases. The approach has been implemented in a Web-based system, which enables quick, convenient, and reliable freeway IID estimation in the Puget Sound region in the state of Washington.
 
Article
Single-loop detectors are the most common sensors employed by freeway traffic management agencies. The data are used for traffic management and traveler information. Single-loop detectors can only measure flow and occupancy. Although speed is often the most useful metric, it can only be estimated at conventional single-loop detectors. Typically this estimate comes from the quotient of flow and occupancy multiplied by the fixed, assumed average effective vehicle length. This conventional approach is limited because the actual average effective vehicle length will vary from sample to sample. Many researchers have proposed alternatives to address this problem, and although many of the methods work well under normal conditions, there has been limited research into methods that yield reliable estimates under heavy truck traffic. Heavy truck flows may arise as a function of location or time of day, for example, with proximity to a trucking facility or in early mornings when the number of passenger vehicles drops, respectively. This article presents a new methodology to estimate speed from single-loop detectors in conditions where trucks comprise a large percentage of the fleet. While the focus is on single loop detectors, the work is equally applicable to side-fire microwave radar detectors that emulate single-loop detectors.
 
Article
In this article, we investigate discretionary lane change (DLC) characteristics using Next Generation SIMulation (NGSIM) data sets. We first develop a set of heuristic rules to automatically filter out abnormal samples from a massive trajectory data set and identify DLC trajectories from a mixture of mandatory lane change (MLC) and DLC trajectories. Then, we investigate a variety of DLC characteristics. We demonstrate that the kernel part of every normal DLC trajectory can be approximately depicted by a certain fifth-order polynomial. Moreover, we discuss the definition of begin/end points of DLC actions and show that the duration time of DLC actions follows a log-normal distribution with respect to navigation speed. All the findings can help promote temporal and spatial accuracy of lane changing models.
 
Article
In most metropolitan areas, an emergency evacuation may require a potentially large number of pedestrians to walk some distance to access their passenger cars or resort to transit systems. In this process, the massive number of pedestrians may place a tremendous burden on vehicles in the roadway network, especially at critical intersections. Thus, the effective road enforcement of the vehicle and pedestrian flows and the proper coordination between these two flows at critical intersections during a multimodal evacuation process is a critical issue in evacuation planning. This article presents an integrated linear model for the design of optimized flow plans for massive mixed pedestrian–vehicle flows within an evacuation zone. The optimized flow can also be used to generate signal timing plans at critical intersections. In addition, the linear nature of the model can circumvent the computational burden to apply in large-scale networks. An illustrating example of the evacuation around the M&T Bank Stadium in downtown Baltimore, MD, is presented and used to demonstrate the model's capability to address the complex interactions between vehicle and pedestrian flows within an evacuation zone. Results of simulation experiments verify the applicability of our model to a real-world scenario and further indicate that accounting for such conflicting movements will yield more reliable estimation of an evacuation's required clearance time.
 
Article
An integral component of (in-vehicle) navigation systems is the determination of optimal routes to the desired destination. An implicit assumption in the underlying algorithms is that people do not make mistakes when following the prescribed routes. This is, however, not always consistent with reality, especially when driving in unfamiliar environments. This article presents a first look at the possibility of mistakes when driving. This possibility is formalized in a Markov decision process. It is demonstrated that quite paradoxical situations can occur when accounting for mistakes. As the most interesting—but perhaps extreme—example, we have shown that under certain conditions, it is no longer optimal to recommend drivers to take the shortest route. Instead, a longer route (in certain cases even the longest!) becomes optimal. Numerical results are provided throughout the article to reveal the fundamental properties of this problem.
 
Article
Traffic congestion has become a major challenge in recent years in many countries of the world. One way to alleviate congestion is to manage the traffic efficiently by applying intelligent transportation systems (ITS). One set of ITS technologies helps in diverting vehicles from congested parts of the network to alternate routes having less congestion. Congestion is often measured by traffic density, which is the number of vehicles per unit stretch of the roadway. Density, being a spatial characteristic, is difficult to measure in the field. Also, the general approach of estimating density from location-based measures may not capture the spatial variation in density. To capture the spatial variation better, density can be estimated using both location-based and spatial data sources using a data fusion approach. The present study uses a Kalman filter to fuse spatial and location-based data for the estimation of traffic density. Subsequently, the estimated data are utilized for predicting density to future time intervals using a time-series regression model. The models were estimated and validated using both field and simulated data. Both estimation and prediction models performed well, despite the challenges arising from heterogeneous traffic flow conditions prevalent in India.
 
Article
The positioning quality of global navigation satellite system (GNSS), or GNSS quality of service (QoS), is a major factor impacting real-time navigation performance. Commonly requested routes (i.e., shortest or fastest) may include areas with poor GNSS QoS, which can subsequently degrade navigation performance. To provide alternative routes with high or acceptable GNSS QoS along a route, a novel optimal routing for navigation systems/services based on GNSS QoS by utilizing integrated GNSS (iGNSS) QoS prediction is presented in this article. New routing criteria based on GNSS QoS are maximum availability, maximum accuracy, maximum continuity, and maximum reliability. Two experiments were conducted to compare GNSS QoS-based routes against shortest routes. In one experiment, routes were simulated, and in another, generated routes based on GNSS QoS were evaluated against GPS-based trajectories as ground truths. The results show that GNSS QoS-based routes provide routes with higher QoS, more than 50%, and longer, about 50%, than shortest routes.
 
MAPEs (%) of the prediction results on test bed #1 (Highway No.5) 
MAPEs of the prediction results on test bed #2 (Highway No.1)
Prediction performances for three selected incidents on Highway No.5 in June, 2011
Article
This research proposes a short-term highway traffic state prediction method based on a structural state space model, with the intention to provide a robust approach for obtaining accurate forecasts of traffic state under both recurring and non-recurring conditions. True traffic state is decomposed to three components, namely, regular traffic pattern, structural deviation, and random fluctuation. Particularly, the structural deviation term reflects the change of true traffic state from regular (historical) pattern, due to unexpected capacity reduction and/or demand variations. A polynomial trend is adopted to describe the temporal evolution of structural deviations across different time intervals. We derive an analytical form of structural deviations in a single bottleneck case based on cumulative flow count diagrams. The proposed model is incorporated in a Kalman filtering-based algorithmic framework, together with an adaptive scheme for determining the variances of random errors. A set of numerical experiments was conducted on two test beds in the northern Taiwan highway network. Experimental results show that the proposed approach is particularly superior to an ordinary Kalman filtering method presented in the literature under non-recurring conditions, highlighting the advantage of combining both the polynomial trend model and historical pattern into the proposed short-term traffic state prediction approach.
 
Article
This article introduces a new measure of travel time reliability for implementation in the dynamic routing algorithm of an intelligent car navigation system. The measure is based on the log-normal distribution of travel time on a link and consists of two indices corresponding to the extreme values of the distribution, such that they reflect the shortest and longest travel times that may be experienced on the link. Through a series of mathematical manipulations, the indices are expressed in terms of the characteristic values of the speed distribution on the link. An expression relating the indices of a route and the indices of the individual links forming it is derived. The accuracy of the measure is then assessed through a field experiment and the results are presented.
 
Article
The day-to-day volatility of traffic series provides valuable information for accurately tracking the complex characteristics of short-term traffic such as stochastic noise and nonlinearity. Recently, support vector regression (SVR) has been applied for short-term traffic forecasting. However, standard SVR adopts a global and fixed -margin, which not only fails to tolerate the day-to-day traffic variation, but also requires a blind and time-consuming searching procedure to obtain a suitable value for . In this work, on the ground of stochastic modeling of day-to-day traffic variation, we propose an adaptive SVR short-term traffic forecasting model. The time-varying deviation of the day-to-day traffic variation, described in a bilevel formula, is integrated into SVR as heuristic information to construct an adaptive -margin, in which both local and normalized factors are considered. Comparative experiments using field traffic data indicate that the proposed model consistently outperforms the standard SVR with an improved computational efficiency.
 
Article
Despite its ever-increasing computing power, dynamic origin–destination (OD) estimation in congested networks remains troublesome. In previous research, we have shown that an unbiased estimation requires the calculation of the sensitivity of the link flows to all origin–destination flows, in order to incorporate the effects of congestion spillback. This is, however, computationally infeasible for large-scale networks. To overcome this issue, we propose a hierarchical approach for off-line application that decomposes the dynamic OD estimation procedure in space. The main idea is to perform a more accurate dynamic OD estimation only on subareas where there is congestion spillback. The output of this estimation is then used as input for the OD estimation on the whole network. This hierarchical approach solves many practical and theoretical limitations of traditional OD estimation methods. The main advantage is that different OD estimation method can be used for different parts of the network as necessary. This allows applying more advanced and accurate, but more time-consuming, methods only where necessary. The hierarchical approach is tested on a study network and on a real network. In both cases the proposed methodology performs better than traditional OD estimation approaches, indicating its merit.
 
Article
Abandoned objects in a road can be a potential threat to urban traffic. In this article we present a new threat degree analysis method of abandoned objects, which is based on dynamic multifeature fusion to detect the abandoned objects and analyze the threat degree automatically. The image sequence is acquired with a visible sensor installed at overbridges, and is processed by a PC-based image-processing system. In this method, we first put forward a multivehicle tracking algorithm to acquire the vehicles' moving information as preprocessing. Then we extracted the dynamic features and built a security threat model upstream of the abandoned object to facilitate further analysis. Finally, we proposed a fusion decision method, based on dynamic multiple features, to analyze the threat degree. The experiments show that the developed method can determine the threat degree of abandoned objects well and truly, and it is appropriate in the intelligent traffic monitoring system.
 
CACC controller operation 
CACC controller block diagram 
Experimental test including gap closing and regulation controllers
Article
Cooperative Adaptive Cruise Control (CACC) systems are a candidate to improve highway capacity by shortening headways and attenuating traffic disturbances. Although encouraging results have been obtained until now, a wide range of traffic circumstances has to be investigated in order to get reliable CACC systems driving on real roads. Among them, handling both vehicle-to-vehicle (V2V) communications equipped and unequipped vehicles merging into the string of CACC vehicles is a commonly-mentioned challenge. In this paper, an algorithm for managing the transitions in response to cut-ins from V2V or non-V2V equipped vehicles is developed and tested using a string of four CACC vehicles. A CACC controller is implemented in four production Infiniti M56s vehicles and tested in real traffic, where non-V2V equipped vehicles can cut in. The effects of a vehicle performing a cut-out, are also investigated. Then, responses to cut-ins by equipped and non-equipped vehicles are simulated for longer strings of vehicles using car-following models for both the production Adaptive Cruise Control (ACC) system and the newly developed CACC controller. Results demonstrate that the CACC system is able to handle cut-in vehicles without causing major perturbations and also reducing significantly the impact of this maneuver on the following vehicles, improving traffic flow.
 
Article
Optimization of externalities and accessibility using dynamic traffic management measures on a strategic level is a specific example of solving a multi-objective network design problem. Solving this optimization problem is time consuming, because heuristics like evolutionary multi objective algorithms are needed and solving the lower level requires solving the dynamic user equilibrium problem. Using function approximation like response surface methods (RSM) in combination with evolutionary algorithms could accelerate the determination of the Pareto optimal set. Three algorithms in which RSM are used in different ways in combination with the Strength Pareto Evolutionary Algorithm 2+ (SPEA2+) are compared with employing the SPEA2+ without the use of these methods. The results show that the algorithms using RSM methods accelerate the search considerably at the start, but tend to converge more quickly, possibly to a local optimum, and therefore loose their head start. Therefore, usage of function approximation is mainly of interest if a limited number of exact evaluations can be done or this can be used as a pre phase in a hybrid approach.
 
Article
New mobility transport systems are expected to be autonomously driven. Even if public interest and a priori acceptability of such systems are high, there is only a few studies with people that already experienced an automated mobility system. This paper presents the results of a questionnaire study after experience the automated vehicle in the Tornado project. 155 users tested the vehicle in an itinerary of 6.5 km with an average speed of 25 km/h and a maximum speed of 50 km/h including straight stretches, intersections, traffic lights, roundabouts, narrow roads and a tunnel. Questionnaire content is based on some of the determinants of the unified theory of acceptance and use of technology (UTAUT) and car technology acceptance models (CTAM) together with an additional determinant introduced to analyze if vehicle performance seems natural. Usefulness, safety and enjoyment of automated vehicles already claimed in other projects are here confirmed even if speed is increased compared to previous projects. The increase in the maximum speed is not directly associated to a reduction on the safety feeling on-board. Answers have also been correlated to demographic characteristics of respondents, confirming some findings in the literature, and adding new ones related to previous autonomous vehicle experience and education level.
 
Article
Artificial intelligence (AI) methods for traffic video analysis have been widely identified as potential solutions for solving hard problems in intelligent transport systems (ITS). To exploit the advantages of AI, dense cameras to monitor the traffic are required to be deployed along the road and at the intersections. The captured videos of these cameras should be back-hauled to the control center, acting as the inputs of the AI methods. To bear such large data traffic load and to cover long transmission range, directional communication technology can be employed, which concentrate the energy of the wireless signal in a specified direction to provide high data rate and long transmission range (up to hundreds of kilometers). In this paper, the communication time extension problem (CTEP) is identified when directional transmission is applied to the dense urban traffic surveillance system, where the wireless signal propagation time approximates the data transmission time. A link distance division-based time division multiple access (LDD-TDMA) protocol is proposed to address the identified CTEP. Firstly, the directional wireless communication links are classified into categories according to the link distance, where nodes located in the same communication ring belong to the same category. Then a link distance aware (LDA)-based slot allocation algorithm is proposed to assign the time slots to the links. The optimal communication rings’ radius is derived in closed form formula, and the minimum average links’ distance is derived. Simulation results show that LDD-TDMA outperforms TDMA by 13.37% when the ring number is 4.
 
Article
Following the rapid development of the Internet of vehicles (IoV), many issues and challenges do come up as the storage of large quantities of vehicle network data and improvement of the retrieval efficiency. A great deal of global positioning system (GPS) log data and vehicle monitoring data is generated on IoV. When many small files in the conventional Hadoop Distributed File System (HDFS) are accessed, a series of problems arise such as high occupancy rate, low access efficiency and low retrieval efficiency, which lead to degrade the performance of IoV. In an attempt to tackle these bottleneck problems, a small Files Correlation Probability (FCP) model is proposed, which is based on the Text Feature Vector (TFV) presented in this paper. The Small Files Merge Scheme based on FCP (SFMS-FCP) and the Small File Prefetching and Caching Strategies (SFPCS) are proposed to optimize the storage and access performance of HDFS. Finally, experiments show that the proposed optimization solutions achieve better performance in terms of high occupancy of HDFS name nodes and low access efficiency, compared with the native HDFS read-write scheme and HAR-based read-write optimization scheme.
 
Article
With the development of urbanization, road congestion has become increasingly serious, and an important cause is the traffic accidents. In this article, we aim to predict the duration of traffic accidents given a set of historical records and the feature of the new accident, which can be collected from the vehicle sensors, in order to help guide the congestion and restore the road. Existing work on predicting the duration of accidents seldom consider the imbalance of samples, the interaction of attributes, and the cost-sensitive problem sufficiently. Therefore, in this article, we propose a two-level model, which consists of a cost-sensitive Bayesian network and a weighted K-nearest neighbor model, to predict the duration of accidents. After data preprocessing and variance analysis on the traffic accident data of Xiamen City in 2015, the model uses some important discrete attributes for classification, and then utilizes the remaining attributes for K-nearest neighbor regression prediction. The experiment results show that our proposed approach to predicting the duration of accidents achieves higher accuracy compared with classical models.
 
Article
Design of signal progression for arterials accommodating significant transit and passenger car flows is a challenging task, as its effectiveness with state-of-the-art methodologies often degrades with the increasing percentage of bus flows due to the inevitable mutual impedance in the mixed traffic. Conceivably, bus flows, prior to reaching a link’s downstream intersection, may first experience excessive delays incurred by passenger-car queues before arriving or dwelling at a roadside stop. Those dwelling bus flows will in turn constitute a temporary lane-blockage, causing passenger cars, especially those in the rightmost lane, either to perform lane changes to interfere with neighboring traffic or to endure the excessive delay. The recently-emerged innovative design methodologies producing a bus-based signal progression system or dual-modal progression band, despite their effectiveness at the experimental level, are difficult to be supported by responsible agencies in practice unless with the policy mandate of promoting transit usage. Hence, this study proposes an alternative to facilitate bus flows by incorporating the bus delay minimization in the progression design for passenger-car flows, using the optimized offsets, phase sequences, and link progression speed. The proposed model explicitly accounts for all types of bus delays under various traffic scenarios constituting the bus entry time, bus stop location, and the patterns of passenger-car queues. The results from the extensive numerical experiments confirm that the proposed model can generate a bus-friendly signal progression plan for a wide range of mixed bus and passenger car traffic scenarios.
 
Article
Traffic speed estimation is a fundamental task for traffic management centers and a critical element of intelligent transportation systems. For this purpose, various sensors are used to collect traffic speed information. The cellular probe system is gaining market penetration and becomes a newly effective and practical traffic speed measurement technique. In this article, the handoff system, one type of cellular probe technology, is used for speed detection. However, the handoff coverage size is usually variable and consecutive handoff points are usually far apart on a freeway. To improve the accuracy of speed estimation, this article proposes a travel-time-based method to aggregate the estimation results of the cellular probe system and loop detectors. For the purpose of a rigorous analysis, data are generated from microscopic simulation models of virtual one-direction freeway segments under various traffic conditions. Thus, the correlations between estimation accuracy and handoff distance, traffic condition, and the number of loop detectors are evaluated and analyzed. The results show that best performance is achieved with the shortest handoff distance. The aggregation of estimated speeds from cellular probe system and loop detectors can improve the speed estimation accuracy by taking advantage of each sensor if the space of loop detectors is more than 500 m. Also, an increasing number of loop detectors will improve the accuracy. Furthermore, the improvement of integration accuracy is much better under free flow conditions than under congested conditions.
 
Article
As with travel time collection, the accuracy of observed travel time and the optimal travel time data quantity should be determined before using travel time reliability (TTR) data. The statistical accuracy of TTR measures should be evaluated so that the statistical behavior and belief can be fully understood. More specifically, this issue can be formulated as a question: using a certain amount of travel time data, how accurate is the travel time reliability for a specific freeway corridor, time of day (TOD), and day of week (DOW)? A framework for answering this question has not been proposed previously. Our study proposes a framework based on bootstrapping to evaluate the accuracy of TTR measures and answer the question. Bootstrapping is a computer-based method for assigning measures of accuracy to multiple types of statistical estimators without requiring a specific probability distribution. Three scenarios representing three traffic flow conditions (free-flow, congestion, and transition) were used to evaluate the accuracy of TTR measures under different traffic conditions and quantities of data. The results of the accuracy measurements demonstrated that: 1) the proposed framework supports assessment of TTR accuracy, and 2) stabilization of the TTR measures did not necessarily correspond to statistical accuracy. The findings in our study also suggested that moment-based TTR measures may not be statistically sufficient for measuring freeway TTR. Additionally, our study suggested that four or five weeks of travel time data is sufficient for measuring freeway TTR under free-flow conditions, 40 weeks for congested conditions, and 35 weeks for transition conditions.
 
Article
In the present study the impact of real time travel information acquired through mobile devices on traveler behavior is investigated taking into consideration individuals’ attitudes towards the use of smart mobile devices. The effect of traffic information acquisition, in activity rescheduling is also considered. A case study was developed for the Athens Metropolitan Area, Greece in 2009. A survey was conducted that included both revealed and stated preference data, as well as attitudes and perceptions of individual decision makers. This paper focuses on the modeling and analysis of the stated preferences experiment conducted. An integrated error component latent variable model was estimated, predicting the probability of travelers’ switching behavior as a function of travel information and traffic information seekers through mobile devices. The analysis of the results indicates that traffic information seekers through mobile devices are more likely to switch travel behavior, while traffic information appears to affect the rescheduling of individuals’ activities that in many cases is also accompanied by mode or route switching. Read my paper at http://tandfonline.com/doi/full/10.1080/15472450.2015.1012865 Modeling the Impact of Traffic Information Acquisition From Mobile Devices During the Primary Tour of the Day
 
Article
This study provides a novel solution for the synchronized and coordinated railway scheduling optimization (SCSO) problem by the determination of the departure times of a public transit network. Railway timetable optimization is dealt with maximizing the number of synchronized meetings to allow for smooth transfers at interchanges. The developed model uses binary variables to record the number of synchronized meetings considering the importance of transfer stations and rail lines without the need to apply the modeling of passenger assignments. The model allows for a permissible and flexible transfer waiting time for making a connection between rails instead of the commonly used and assumed values. The solution of the mixed-integer programing problem of larger-sized railway networks is based on a synchronized and coordinated scheduling optimization genetic algorithm (SCSO-GA) with a local search strategy (LSS). This solution method is proved to be more efficient and accurate than the CPLEX solver. In addition it is proven to be a periodic event-scheduling problem (PESP) solver. The model is tested computationally on the Beijing urban rail transit network. The results demonstrate the advantage of the novel approach over other methods.
 
Article
Vehicle platooning, a coordinated and controlled vehicle-following strategy, addresses the issue of high fuel consumption of heavy-duty vehicles. This research considers platoons that are formed on the fly in an ad-hoc manner. We investigate two types of ad-hoc platoon formation and corresponding platoon dissolution strategies. The first approach forms a platoon greedily without considering the order of destinations of the platoon members. This approach enables a quick formation but imposes an overhead of platoon rebuilding, and consequently, additional fuel cost when platoon members leave. An alternative approach forms a platoon in the order of the destinations of its platoon members. This ordered approach incurs a comparatively higher formation time due to vehicles’ reorganization but does not lead to further overhead of platoon rebuilding. We investigate whether these ad-hoc formation and dissolution strategies can preserve the original fuel benefit of platooning, and which of the two ad-hoc formation strategies are more fuel-efficient. The experimental results show that the greedy formation of the platoon is more fuel-efficient for a multi-lane highway. The proposed prediction model provides 90.4% prediction accuracy for the greedy approach and 82.2% prediction accuracy for the ordered approach on average, for platoon sizes from two to six vehicles.
 
Article
Truck platooning is an application of connected and automated vehicle technology that has a near-term potential to revolutionize the trucking industry. In addition to potential operational improvements in capacity and flow, its primary benefits include potential reductions in fuel consumption and emissions. In a real-world environment, there are many factors that can influence the ability to form stable and uninterrupted platoons as well as maintain tight platoon spacing. These, in turn, affect the emission benefits of truck platooning. This study developed a mechanism to evaluate truck platooning’s impact on emissions under different scenarios. We modeled truck platooning in VISSIM; a microscopic simulation software and estimated emission rates from second-by-second trajectory data. We used this simulation to evaluate the environmental impact of truck platooning with respect to volume, market penetration rate (MPR) of equipped vehicles, gap setting for platoons, wireless communication quality, and lane use restriction policy. MOVES2014 emission model was used to estimate the emission rates from the vehicle trajectory data with adjusted wind drag coefficients for close spacing during platooning. The results showed that the gap setting of platoons is an important parameter in reducing the emissions where smaller gaps resulted in longer platoons and higher emission reductions. A lane use restriction policy where a platoon is only allowed on the left lane also improves emission benefits because it helps promote platoon formation especially at a low MPR of equipped vehicles.
 
Article
In the past decades, Vehicular Ad hoc Networks (VANETs) have been increasingly developed. Providing secure and efficient communication is essential in VANETs. One of most important challenges in the secure and efficient communications is proposing an appropriate authentication scheme. In this paper, we suggest an efficient and novel authentication scheme for VANETs. In the proposed scheme, vehicles authenticate each other without any limitation such as need for group of signers, online Road Side Units (RSUs), a set of pseudo identities and tamper-proof devices. Moreover, our simulation shows that the proposed scheme is well designed and efficient.
 
Article
Since the introduction of the vehicle infrastructure integration (VII) and connected vehicle (CV) initiatives in the United States, numerous in-vehicle technologies based on wireless communications are currently being deployed. One of these technologies is cooperative adaptive cruise control (CACC) systems, which provide better connectivity, safety, and mobility by allowing vehicles to travel in denser platoons through vehicle-to-vehicle (V2V) communication. Accordingly, the research presented in this article develops a simulation/optimization tool that optimizes the movement of CACC-equipped vehicles as a replacement for traditional intersection control. This system, which is named iCACC, assumes that the intersection controller receives vehicle requests to travel through an intersection and advises each vehicle on the optimum course of action ensuring no crashes occur while at the same time minimizing the intersection delay. Four intersection control scenarios are compared, namely: a traffic signal, an all-way stop control (AWSC), a roundabout, and the iCACC controller. The results show that the proposed iCACC system significantly reduces the average intersection delay and fuel consumption level by 90 and 45%, respectively. Additionally, the article investigates the impact of vehicle dynamics, weather conditions, and level of market penetration of equipped vehicles on the future of automated vehicle control.
 
Article
Cooperative Adaptive Cruise Control (CACC), as an advanced version of adaptive cruise control (ACC), automates brake and engine controls based on the information received from wireless V2V communications and remote sensors, enabling smaller vehicle-following time gaps. It can improve the safety of vehicle platooning and increase fuel savings. As an extension of our previous investigation of truck drivers’ acceptance of CACC, this case study investigates factors affecting the use of CACC for truck platooning. Nine commercial fleet drivers were recruited to operate two following trucks in a CACC-enabled string on freeways in Northern California. We analyzed the usage of CACC time gaps and its correlation with truck drivers’ stated preferences for these time gaps, and we found that the highest preferred Gap 3 (1.2 s) was used the most. Moreover, a Bayesian regression model was built to show that truck drivers are more likely to disengage CACC when driving in low-speed traffic or on downgrades where this CACC could not provide sufficient braking. In high-speed traffic or on upgrades, truck drivers are more likely to engage CACC, particularly at Gap 3. Truck position, however, does not affect truck drivers’ time gap selection. The findings encourage the adoption of CACC in the trucking industry through implementing driver-preferred time gaps and responsive braking systems, and operating on routes with minimal interference to truck speeds.
 
Article
An essential activity of driving is making lane changes. Depending on the driver’s motivation, lane changing events may be classified as discretionary or mandatory. Past research has shown that there is a difference in drivers’ risk-taking behavior when making discretionary and mandatory lane changes. A lane changing decision model, based on Fuzzy Inference System (FIS), has been developed with promising accuracy. This research investigates if such model can be adapted to make decisions for mandatory lane changing moves and if it is necessary to develop a new model from scratch that is dedicated to mandatory lane changes. Vehicle trajectory data of mandatory lane changing events in the NGSIM database was extracted to form a training and a test data set for comparative evaluation. First, the FIS model developed in earlier research for discretionary lane changes was directly applied to the mandatory lane changing data. Then, an Adaptive FIS (AFIS) model was implemented by adjusting a critical parameter in the FIS-based discretionary lane changing model to optimize its performance for the mandatory lane changing training data set. Additionally, new models based on Adaptive Neuro-Fuzzy Inference Systems (ANFIS) were developed for mandatory lane changes using the training data set. These models were evaluated using the mandatory lane changing test data set. Based on the test results, one of the ANFIS models is recommended, as it gave a higher overall correct decision rate compared to the existing FIS, AFIS, and other ANFIS models.
 
Article
In a connected vehicle environment, vehicle location, speed, and other traffic information are readily available; hence, such environments provide new data sources for traffic signal control optimization. Existing adaptive signal control systems based on fixed detectors cannot directly obtain vehicle location and speed information, and thus, cannot provide accurate information about real-time traffic flow changes. This study presents a dynamic optimization method for adaptive signal control in a connected vehicle environment. First, the proposed method developed a dynamic platoon dispersion model to predict vehicle arrivals by using connected vehicle data. Then, a signal timing optimization model is constructed by regarding the minimization of average vehicle delay as the optimization objective, and setting the green time duration of each phase as a constraint. To achieve real-time adaptive signal control, a genetic algorithm is adopted to solve the optimization model through rolling optimization. Finally, a real-world road network was modeled in Vissim to validate the proposed method. Simulation results show that compared with the classical adaptive signal control algorithm, the proposed method is able to reduce vehicle delays and queue lengths at least 50% penetration rates. At 100% penetration rate, the proposed method improved the average vehicle delay and the average queue length by 22.7% and 24.8%, respectively. Moreover, it catered to all directions in a balanced manner.
 
Article
Ensuring transportation systems are efficient is a priority for modern society. Intersection traffic signal control can be modeled as a sequential decision-making problem. To learn how to make the best decisions, we apply reinforcement learning techniques with function approximation to train an adaptive traffic signal controller. We use the asynchronous n-step Q-learning algorithm with a two hidden layer artificial neural network as our reinforcement learning agent. A dynamic, stochastic rush hour simulation is developed to test the agent’s performance. Compared against traditional loop detector actuated and linear Q-learning traffic signal control methods, our reinforcement learning model develops a superior control policy, reducing mean total delay by up 40% without compromising throughput. However, we find our proposed model slightly increases delay for left turning vehicles compared to the actuated controller, as a consequence of the reward function, highlighting the need for an appropriate reward function which truly develops the desired policy.
 
Top-cited authors
B. van Arem
  • Delft University of Technology
Dimitris Milakis
  • German Aerospace Center (DLR)
Martin Trépanier
  • Polytechnique Montréal
Eleni I Vlahogianni
  • National Technical University of Athens
Winnie Daamen
  • Delft University of Technology