Evaluation of Information Applications of a Self‐Organizing Distributed Traffic Information System for a Large‐Scale Real‐World Traffic Network

Abstract: This article presents an evaluation of the system performance of a proposed self‐organizing, distributed traffic information system based on vehicle‐to‐vehicle information‐sharing architecture. Using microsimulation, several information applications derived from this system are analyzed relative to the effectiveness and efficiency of the system to estimate traffic conditions along each individual path in the network, to identify possible incidents in the traffic network, and to provide rerouting strategies for vehicles to escape congested spots in the network. A subset of vehicles in the traffic network is equipped with specific intervehicle communication devices capable of autonomous traffic surveillance, peer‐to‐peer information sharing, and self‐data processing. A self‐organizing traffic information overlay on the existing vehicular roadway network assists their independent evaluation of route information, detection of traffic incidents, and dynamic rerouting in the network based both on historical information stored in an in‐vehicle database and on real‐time information disseminated through intervehicle communications. A path‐based microsimulation model is developed for these information applications and the proposed distributed traffic information system is tested in a large‐scale real‐world network. Based on simulation study results, potential benefits both for travelers with such equipment as well as for the traffic system as a whole are demonstrated.     

Spreading Patterns of Malicious Information on Single‐Lane Platooned Traffic in a Connected Environment

The connected vehicle can be easily attacked by cyber threats due to its communication through the wireless network in an open‐access environment. But very few studies have paid attention to the spreading of malicious information such as denial of service, message delay/replay, and eavesdropping generated by cyberattacks. To this end, this article introduces an analytical model, named vehicular malicious information propagation (VMIP), which integrates a classical epidemic model through two‐layer system structure, in which the upper layer describes the malicious information spreading and the lower describes the traffic flow dynamics. The proposed VMIP model is designated for platooned (one‐lane, particularly) traffic. Numerical experiments show the proposed model can efficiently describe the interactions between traffic dynamics and malicious information spreading; and the information propagation highly depends on traffic flow patterns. This article is expected to contribute to a better understanding of the impacts of cyberattacks on traffic and lays a foundation for future development of control strategies on mitigating the disastrous effects of cyberattacks.     

A graph deep learning method for short‐term traffic forecasting on large road networks

Short‐term traffic flow prediction on a large‐scale road network is challenging due to the complex spatial–temporal dependencies, the directed network topology, and the high computational cost. To address the challenges, this article develops a graph deep learning framework to predict large‐scale network traffic flow with high accuracy and efficiency. Specifically, we model the dynamics of the traffic flow on a road network as an irreducible and aperiodic Markov chain on a directed graph. Based on the representation, a novel spatial–temporal graph inception residual network (STGI‐ResNet) is developed for network‐based traffic prediction. This model integrates multiple spatial–temporal graph convolution (STGC) operators, residual learning, and the inception structure. The proposed STGC operators can adaptively extract spatial–temporal features from multiple traffic periodicities while preserving the topology information of the road network. The proposed STGI‐ResNet inherits the advantages of residual learning and inception structure to improve prediction accuracy, accelerate the model training process, and reduce difficult parameter tuning efforts. The computational complexity is linearly related to the number of road links, which enables citywide short‐term traffic prediction. Experiments using a car‐hailing traffic data set at 10‐, 30‐, and 60‐min intervals for a large road network in a Chinese city shows that the proposed model outperformed various state‐of‐the‐art baselines for short‐term network traffic flow prediction.     

Data Fusion of Fixed Detector and Probe Vehicle Data for Incident Detection

An important feature of many advanced traveler information systems (ATIS) is real-time information about incidents on the street network. This paper describes a system for automatically detecting incidents for such an ATIS developed using artificial neural networks and statistical prediction methods. The system monitors traffic conditions using two types of data: inductive loop detectors (ILDs) and vehicle probes. For both neural network and statistical methods, incident detection is accomplished using two approaches: by processing traffic input data directly and by processing the output of specialized algorithms that detect incidents using information from each data source. Analysis data generated from a simulation of a typical suburban signalized major arterial street are used. Different model configurations are examined and tested to identify the input variables and methods that are the best predictors of incident occurrence. The neural network approaches consistently perform at least as well as the discriminant analysis models, especially when results are adjusted to avoid false alarms.     

Dynamic origin‐destination flow estimation using automatic vehicle identification data: A 3D convolutional neural network approach

Dynamic origin‐destination (OD) flow estimation is one of the most fundamental problems in traffic engineering. Despite numerous existing studies, the OD flow estimation problem remains challenging, as there is large dimensional difference between the unknown values to be estimated and the known traffic observations. To meet the needs of active traffic management and control, accurate time‐dependent OD flows are required to understand time‐of‐day traffic flow patterns. In this work, we propose a three‐dimensional (3D) convolution‐based deep neural network, “Res3D,” to learn the high‐dimensional correlations between local traffic patterns presented by automatic vehicle identification observations and OD flows. In this paper, a practical framework combining simulation‐based model training and few‐shot transfer learning is introduced to enhance the applicability of the proposed model, as continuously observing OD flows could be expensive. The proposed model is extensively tested based on a realistic road network, and the results show that for significant OD flows, the relative errors are stable around 5%, outperforming several other models, including prevalent neural networks as well as existing estimation models. Meanwhile, corrupted and out‐of‐distribution samples are generated as real‐world samples to validate Res3D's transferability, and the results indicated a 60% improvement with few‐shot transfer learning. Therefore, this proposed framework could help to bridge the gaps between traffic simulations and empirical cases.     

Time‐Varying Lane‐Based Capacity Reversibility for Traffic Management

Abstract: This article presents a new bi‐level formulation for time‐varying lane‐based capacity reversibility problem for traffic management. The problem is formulated as a bi‐level program where the lower level is the cell‐transmission‐based user‐optimal dynamic traffic assignment (UODTA). Due to its Non‐deterministic Polynomial‐time hard (NP‐hard) complexity, the genetic algorithm (GA) with the simulation‐based UODTA is adopted to solve multiorigin multidestination problems. Four GA variations are proposed. GA1 is a simple GA. GA2, GA3, and GA4 with a jam‐density factor parameter (JDF) employ time‐dependent congestion measures in their decoding procedures. The four algorithms are empirically tested on a grid network and compared based on solution quality, convergence speed, and central processing unit (CPU) time. GA3 with JDF of 0.6 appears best on the three criteria. On the Sioux Falls network, GA3 with JDF of 0.7 performs best. The GA with the appropriate inclusion of problem‐specific knowledge and parameter calibration indeed provides excellent results when compared with the simple GA.     

A Dantzig‐Wolfe Decomposition‐Based Heuristic for Off‐line Capacity Calibration of Dynamic Traffic Assignment

Abstract: One of the critical elements in considering any real‐time traffic management strategy requires assessing network traffic dynamics. Traffic is inherently dynamic, since it features congestion patterns that evolve over time and queues that form and dissipate over a planning horizon. Dynamic traffic assignment (DTA) is therefore gaining wider acceptance among agencies and practitioners as a more realistic representation of traffic phenomena than static traffic assignment. Though it is imperative to calibrate the DTA model such that it can accurately reproduce field observations and avoid erroneous flow predictions when evaluating traffic management strategies, DTA calibration is an onerous task due to the large number of variables that can be modified and the intensive computational resources required. To compliment other research on behavioral and trip table issues, this work focuses on DTA capacity calibration and presents an efficient Dantzig‐Wolfe decomposition‐based heuristic that decomposes the problem into a restricted master problem and a series of pricing problems. The restricted master problem is a capacity manipulation problem, which can be solved by a linear programming solver. The pricing problem is the user optimal DTA which can be optimally solved by an existing combinatorial algorithm. In addition, the proposed set of dual variable approximation techniques is one of a very limited number of approaches that can be used to estimate network‐wide dual information in facilitating algorithmic designs while maintaining scalability. Two networks of various sizes are empirically tested to demonstrate the efficiency and efficacy of the proposed heuristic. Based on the results, the proposed heuristic can calibrate the network capacity and match the counts within a 1% optimality gap.     

Empirical Innovation of Computational Dual‐Loop Models for Identifying Vehicle Classifications against Varied Traffic Conditions

Clarifying traffic flow phases is a primary requisite for applying length‐based vehicle classifications with dual‐loop data under various traffic conditions. One challenge lies in identifying traffic phases using variables that could be directly calculated from the dual‐loop data. This article presents an innovative approach and associated algorithm for identifying traffic phases through a hybrid method that incorporates level of service method and K‐means clustering method. The “phase representative variables” are identified to represent traffic characteristics in the traffic flow phase identification algorithm. The traffic factors influencing the vehicle classification accuracy under non‐free traffic conditions are successfully identified using video‐based vehicular trajectory data, and the innovative length‐based vehicle classification models are then developed. The result of the concept‐of‐evidence test with use of sample data indicates that compared with the existing model, the accuracy of the estimated vehicle lengths is increased from 42% to 92% under synchronized and stop‐and‐go conditions. The results also foster a better understanding of the traffic stream characteristics and associated theories to lay out a good foundation for further development of relevant microscopic simulation models with other sensing traffic data sources.     

End‐to‐End Deep Learning Methodology for Real‐Time Traffic Network Management

This article presents a novel real‐time traffic network management system using an end‐to‐end deep learning (E2EDL) methodology. A computational learning model is trained, which allows the system to identify the time‐varying traffic congestion pattern in the network, and recommend integrated traffic management schemes to reduce this congestion. The proposed model structure captures the temporal and spatial congestion pattern correlations exhibited in the network, and associates these patterns with efficient traffic management schemes. The E2EDL traffic management system is trained using a laboratory‐generated data set consisting of pairings of prevailing traffic network conditions and efficient traffic management schemes designed to cope with these conditions. The system is applied for the US‐75 corridor in Dallas, Texas. Several experiments are conducted to examine the system performance under different traffic operational conditions. The results show that the E2EDL system achieves travel time savings comparable to those recorded for an optimization‐based traffic management system.     

A Cyber‐Physical System Simulator for Risk‐Free Transport Studies

The article introduces a novel platform for conducting controlled and risk‐free driving and traveling behavior studies, called Cyber‐Physical System Simulator (CPSS). The key features of CPSS are: (1) simulation of multiuser immersive driving in a three‐dimensional (3D) virtual environment; (2) integration of traffic and communication simulators with human driving based on dedicated middleware; and (3) accessibility of multiuser driving simulator on popular software and hardware platforms. This combination of features allows us to easily collect large‐scale data on interesting phenomena regarding the interaction between multiple user drivers, which is not possible with current single‐user driving simulators. The core original contribution of this article is threefold: (1) we introduce a multiuser driving simulator based on DiVE, our original massively multiuser networked 3D virtual environment; (2) we introduce OpenV2X, a middleware for simulating vehicle‐to‐vehicle and vehicle‐to‐infrastructure communication; and (3) we present two experiments based on our CPSS platform. The first experiment investigates the “rubbernecking” phenomenon, where a platoon of four user drivers experiences an accident in the oncoming direction of traffic. Second, we report on a pilot study about the effectiveness of a Cooperative Intelligent Transport Systems advisory system.     

Effect of Pulse‐and‐Glide Strategy on Traffic Flow for a Platoon of Mixed Automated and Manually Driven Vehicles

The fuel consumption of ground vehicles is significantly affected by how they are driven. The fuel‐optimized vehicular automation technique can improve fuel economy for the host vehicle, but their effectiveness on a platoon of vehicles is still unknown. This article studies the performance of a well‐known fuel‐optimized vehicle automation strategy, i.e., Pulse‐and‐Glide (PnG) operation, on traffic smoothness and fuel economy in a mixed traffic flow. The mixed traffic flow is assumed to be a single‐lane highway on flat road consisting of both driverless and manually driven vehicles. The driverless vehicles are equipped with fuel economy‐oriented automated controller using the PnG strategy. The manually driven vehicles are simulated using the Intelligent Driver Models (IDM) to mimic the average car‐following behavior of human drivers in naturalistic traffics. A series of simulations are conducted with three scenarios, i.e., a single car, a car section, and a car platoon. The simulation results show that the PnG strategy can significantly improve the fuel economy of individual vehicles. For traffic flows, the fuel economy and traffic smoothness vary significantly under the PnG strategy.     

A Hybrid Branch‐and‐Bound and Benders Decomposition Algorithm for the Network Design Problem

Given a set of candidate road projects associated with costs, finding the best subset with respect to a limited budget is known as the network design problem (NDP). The NDP is often cast in a bilevel programming problem which is known to be NP‐hard. In this study, we tackle a special case of the NDP where the decision variables are integers. A variety of exact solutions has been proposed for the discrete NDP, but due to the combinatorial complexity, the literature has yet to address the problem for large‐size networks, and accounting for the multimodal and multiclass traffic flows. To this end, the bilevel problem is solved by branch‐and‐bound. At each node of the search tree, a valid lower bound based on system optimal (SO) traffic flow is calculated. The SO traffic flow is formulated as a mixed integer, non‐linear programming (MINLP) problem for which the Benders decomposition method is used. The algorithm is coded on a hybrid and synchronized platform consisting of MATLAB (optimization engine), EMME 3 (transport planning module), MS Access (database), and MS Excel (user interface). The proposed methodology is applied to three examples including Gao's network, the Sioux‐Falls network, and a real size network representing the city of Winnipeg, Canada. Numerical tests on the network of Winnipeg at various budget levels have shown promising results.     

A Cell‐Based Model for Multi‐class Doubly Stochastic Dynamic Traffic Assignment

Abstract: This article proposes a cell‐based multi‐class dynamic traffic assignment problem that considers the random evolution of traffic states. Travelers are assumed to select routes based on perceived effective travel time, where effective travel time is the sum of mean travel time and safety margin. The proposed problem is formulated as a fixed point problem, which includes a Monte–Carlo‐based stochastic cell transmission model to capture the effect of physical queues and the random evolution of traffic states during flow propagation. The fixed point problem is solved by the self‐regulated averaging method. The results illustrate the properties of the problem and the effectiveness of the solution method. The key findings include the following: (1) Reducing perception errors on traffic conditions may not be able to reduce the uncertainty of estimating system performance, (2) Using the self‐regulated averaging method can give a much faster rate of convergence in most test cases compared with using the method of successive averages, (3) The combination of the values of the step size parameters highly affects the speed of convergence, (4) A higher demand, a better information quality, or a higher degree of the risk aversion of drivers can lead to a higher computation time, (5) More driver classes do not necessarily result in a longer computation time, and (6) Computation time can be significantly reduced by using small sample sizes in the early stage of solution processes.     

Random Process Model for Urban Traffic Flow Using a Wavelet‐Bayesian Hierarchical Technique

Abstract: The existing well‐known short‐term traffic forecasting algorithms require large traffic flow data sets, including information on current traffic scenarios to predict the future traffic conditions. This article proposes a random process traffic volume model that enables estimation and prediction of traffic volume at sites where such large and continuous data sets of traffic condition related information are unavailable. The proposed model is based on a combination of wavelet analysis (WA) and Bayesian hierarchical methodology (BHM). The average daily “trend” of urban traffic flow observations can be reliably modeled using discrete WA. The remaining fluctuating parts of the traffic volume observations are modeled using BHM. This BHM modeling considers that the variance of the urban traffic flow observations from an intersection vary with the time‐of‐the‐day. A case study has been performed at two busy junctions at the city‐centre of Dublin to validate the effectiveness of the strategy.     

Modeling Vehicle Interactions during Lane‐Changing Behavior on Arterial Streets

Abstract: Lane‐changing algorithms have attracted increased attention during recent years in traffic modeling. However, little has been done to address the competition and cooperation of vehicles when changing lanes on urban streets. The main goal of this study is to quantify the vehicle interactions during a lane‐changing maneuver. Video data collected at a busy arterial street in Gainesville, Florida, were used to distinguish between free, forced, and competitive/cooperative lane changes. Models particularly for competitive/cooperative lane changes were developed, depending on whether the following vehicle cooperates with the subject vehicle or not. By referring to the “TCP/IP” protocol in computer network communications, a sequence of “hand‐shaking” negotiations were designed to handle the competition and cooperation among vehicles. The developed model was implemented and validated in the CORSIM microsimulator package, with the simulation capabilities compared against the original lane‐changing model in CORSIM. The results indicate that the new model better replicates the observed traffic under different levels of congestion.     

Topological Structure Matching Measure between Two Graphs

There have been a plethora of algorithms and techniques for the one‐to‐one correspondence matching between two small graphs at the element level. However, it is a daunting task for large graphs. It is necessary to design an aggregate statistical measurement to measure the degree of matching at the coarse grained level between two large graphs. This work presents a novel contribution with the proposal of an aggregate statistical measurement of the matching between two large networks at the macro topological structure level. In the viewpoint of strategic planning application, decision makers want to know whether the road infrastructure network meets the traffic flow network at the macro level rather than the micro level. The macro topological structure of the graph is described by a partition of all the vertices by the singular value decomposition based on the weighted vertex‐path incidence matrix. The topological structure matching measurement (TSMM) of the two graphs is defined as the degree of similarity between two partitions. As a case study, the TSMM is considered between the road network and the traffic flow network for Shanghai. The result is 0.2129, which shows that the two networks mismatch to a certain degree. This, agreeing with the current situation of the traffic congestion in Shanghai, suggests the improvement in the urban traffic.     

Distributed Computing and Simulation in a Traffic Research Test Bed

This article describes the laboratory backbone of the California Advanced Research Testbed (CART), which is integrated with an actual urban traffic network. The research laboratory is based at the University of California at Irvine (UCI) and has real-time communication capabilities with several traffic-control centers in Orange County, California. We discuss a simulation and optimization environment that provides the capabilities to study various components of Advanced Traveler Information Systems (ATIS) and Advanced Traffic Management Systems (ATMS) in conjunction with the available real-world connections. The platform accommodates system components such as communications, computing, modeling, prediction, optimization, and control with sufficient flexibility that different candidate system designs can be studied. The article focuses on distributed computing issues and implementation of the hybrid simulation framework that includes integrated microscopic and macroscopic simulation models.     

Network‐wide traffic speed forecasting: 3D convolutional neural network with ensemble empirical mode decomposition

Accurate traffic speed forecasting is one of the most critical tasks in proactive traffic management and the deployment of advanced traveler information systems. This paper proposes a hybrid forecasting approach named DeepEnsemble by integrating the three‐dimensional convolutional neural network (3D CNN) with ensemble empirical mode decomposition (EEMD). There are four steps in this hybrid approach. First, EEMD is adopted to decompose the complex traffic speed time series data with noise into several intrinsic mode functions (IMFs) and a residue. Second, a three‐dimensional tensor is established and fed into 3D CNN for prediction. Third, the output of 3D CNN prediction is obtained by a linear combination of the results of all components. Finally, the 3D CNN prediction output, external features, and historical features are fused to predict the network‐wide traffic speed simultaneously. The proposed DeepEnsemble approach is tested on the three‐month traffic speed series data of a real‐world large‐scale urban expressway network with 308 traffic flow detectors in Beijing, China. The experimental results indicate that DeepEnsemble outperforms the state‐of‐the‐art network‐wide traffic speed forecasting models. 3D CNN learns temporal, spatial, and depth information better than 2D CNN. Moreover, forecasting accuracy can be improved by employing EEMD. DeepEnsemble is a promising model with scalability and portability for network‐wide traffic speed prediction and can be further extended to conduct traffic status monitoring and congestion mitigation strategies.     

面向出行者的综合信息服务系统设计

以城市信息模块为单元,运用交通服务总线搭建了出行者信息服务系统的空间框架.设计了城市信息模块的体系结构,简要设计和介绍了结构中的各部分职能.按照微型控制器的概念,重点设计了城市信息模块的数据中心和运营中心.城市信息模块为出行者信息系统所托,综合运用交通信息融合技术、动态路径规划技术、异构系统融合技术收集信息,在多种信息发布渠道中,依靠互联网及3G移动网络技术着重建设互联网信息发布平台.对出行者信息服务系统中涉及的关键技术进了论证,提出了出行者信息服务系统技术标准.     

A Two‐Dimension Dynamic Bayesian Network for Large‐Scale Degradation Modeling with an Application to a Bridges Network

Modeling the stochastic evolution of a large‐scale fleet or network generally proves to be challenging. This difficulty may be compounded through complex relationships between various assets in the network. Although a great number of probabilistic graph‐based models (e.g., Bayesian networks) have been developed recently to describe the behavior of single assets, one can find significantly fewer approaches addressing a fully integrated network. It is proposed an extension to the standard dynamic Bayesian network (DBN) by introducing an additional dimension for multiple elements. These elements are then linked through a set of covariates that translate the probabilistic dependencies. A Markov chain is utilized to model the elements and develop a distribution‐free mathematical framework to parameterize the transition probabilities without previous data. This is achieved by borrowing from Cooke's method for structured expert judgment and also applied to the quantification of the covariate relationships. Some metrics are also presented for evaluating the sensitivity of information inserted into the covariate DBN where the focus is given on two specific types of configurations. The model is applied to a real‐world example of steel bridge network in the Netherlands. Numerical examples highlight the inference mechanism and show the sensitivity of information inserted in various ways. It is shown that information is most valuable very early and decreases substantially over time. Resulting observations entail the reduction of inference combinations and by extension a computational gain to select the most sensitive pieces of information.