Showing papers in "IEEE Intelligent Transportation Systems Magazine in 2018"

Road Traffic Forecasting: Recent Advances and New Challenges

Abstract: Due to its paramount relevance in transport planning and logistics, road traffic forecasting has been a subject of active research within the engineering community for more than 40 years. In the beginning most approaches relied on autoregressive models and other analysis methods suited for time series data. More recently, the development of new technology, platforms and techniques for massive data processing under the Big Data umbrella, the availability of data from multiple sources fostered by the Open Data philosophy and an ever-growing need of decision makers for accurate traffic predictions have shifted the spotlight to data-driven procedures. This paper aims to summarize the efforts made to date in previous related surveys towards extracting the main comparing criteria and challenges in this field. A review of the latest technical achievements in this field is also provided, along with an insightful update of the main technical challenges that remain unsolved. The ultimate goal of this work is to set an updated, thorough, rigorous compilation of prior literature around traffic prediction models so as to motivate and guide future research on this vibrant field.

Smart ITS Sensor for the Transportation Planning Based on IoT Approaches Using Serverless and Microservices Architecture

Abstract: Currently, there are many challenges in the transportation scope that researchers are attempting to resolve, and one of them is transportation planning. The main contribution of this paper is the design and implementation of an ITS (Intelligent Transportation Systems) smart sensor prototype that incorporates and combines the Internet of Things (IoT) approaches using the Serverless and Microservice Architecture, to help the transportation planning for Bus Rapid Transit (BRT) systems. The ITS smart sensor prototype can detect several Bluetooth signals of several devices (e.g., from mobile phones) that people use while travelling by the BRT system (e.g., in Bogota city). From that information, the ITS smart-sensor prototype can create an O/D (origin/destiny) matrix for several BRT routes, and this information can be used by the Administrator Authorities (AA) to produce a suitable transportation planning for the BRT systems. In addition, this information can be used by the center of traffic management and the AA from ITS cloud services using the Serverless and Microservice architecture.

Generative Adversarial Networks for Parallel Transportation Systems

Abstract: Generative Adversaria Networks (GANs) have emerged as a promising and effective mechanism for machine learning due to its recent successful applications. GANs share the same idea of producing, testing, acquiring, and utilizing data as well as knowledge based on artificial systems, computational experiments, and parallel execution of actual and virtual scenarios, as outlined in the theory of parallel transportation. Clearly, the adversarial concept is embedded implicitly or explicitly in both GANs and parallel transportation systems. In this article, we first introduce basics of GANs and parallel transportation systems, and then present an approach of using GANs in parallel transportation systems for traffic data generation, traffic modeling, traffic prediction and traffic control. Our preliminary investigation indicates that GANs have a great potential and provide specific algorithm support for implementing parallel transportation systems.

Velocity Control Strategies to Improve Automated Vehicle Driving Comfort

Abstract: Automated vehicles are rapidly emerging as the new generation of transport tools. Relevant research mainly focuses on collision avoidance, lane keeping, and coordination control to ensure driving safety and improve efficiency, with little emphasis on passenger comfort. This paper proposes a set of comfortbased velocity control strategies on the basis of driving safety. Driving comfort was evaluated by multiple accelerometers fixed inside vehicles. Power spectral density analysis and one-third octave band filtering were applied to derive the weighted root mean square acceleration as an evaluation indicator for comfort. The annoy rate model is proposed to describe individual sensitivity to vibration. Field tests were conducted to investigate interactions between pavement roughness, speed, and comfort, and multiple linear relationships were identified. Three typical processes were considered: deceleration phase, uniform speed phase and abnormal occasions. The hyperbolic tangent function was utilized to provide moderate deceleration. Model parameters were set to guarantee maximal deceleration and jerk within acceptable limits. Nonlinear programming was used to balance between rapid deceleration and bumps caused by abnormal obstacles. The proposed strategy can potentially be applied for automated vehicles to improve the perceived quality of automated driving.

Comparative Study and Application-Oriented Classification of Vehicular Map-Matching Methods

Abstract: Vehicular map-matching aims to identify the position of a vehicle in a road-network. Different map-matching applications make use of different formulations of the problem leading to some ambiguous usage. This work intends to make a step towards resolution of this issue. We cross-link mapmatching methods, classes and applications in order to provide insight into this area of study. A selection of current map-matching methods is reviewed, classified and appropriately linked with other methods. Conclusions on trends and influential ideas are drawn with respect to the specific flavor of individual applications. Finally, the trade-offs that must be considered when selecting a map-matching method are discussed and selection guidelines are provided.

Reliable Intersection-Based Traffic Aware Routing Protocol for Urban Areas Vehicular Ad Hoc Networks

Abstract: Nowadays, providing reliable vehicle to vehicle communications in vehicular ad hoc networks is essential to serve the emerging intelligent transportation systems. Traffic aware routing is considered a promising approach for delivering data packets between geographically separated vehicles. However, most of the existing traffic aware routing protocols greedily select the next-hop based on distance. Consequently, high packet loss ratio occurs especially with the vehicles high speed mobility. Some existing forwarding schemes attempted to improve the next-hop selection by considering inter-vehicle communication quality or neighbours predicted positions. Nevertheless, such schemes depend on the neighbours mobility information received through beacons regardless of its freshness. In addition, the differentiation between road and intersection areas while forwarding packets was neglected. Therefore, a reliable traffic aware routing protocol is proposed, which selects the next-hop based on roads structure, neighbours predicted positions and their received signal strength, and the recentness of the mobility information received from neighbours. The simulation results show significant improvements in terms of packet delivery ratio and end-to-end delays.

Vision-Based Occlusion Handling and Vehicle Classification for Traffic Surveillance Systems

Abstract: Due to the factors such as visual occlusion, illumination change and pose variation, it is a challenging task to develop effective and efficient models for vehicle detection and classification in surveillance videos. Although plenty of existing related models have been proposed, many issues still need to be resolved. Typically, vehicle detection and classification methods should be vulnerable in complex environments. Moreover, in spite of many thoughtful attempts on adaptive appearance models to solve the occlusion problem, the corresponding approaches often suffer from high computational costs. This paper aims to address the above mentioned issues. By analyzing closures and convex hulls of vehicles, we propose a simple but effective recursive algorithm to segment vehicles involved in multiple-vehicle occlusions. Specifically, a deep convolutional neural network (CNN) model is constructed to capture high level features of images for classifying vehicles. Furthermore, a new pre-training strategy based on the sparse coding and auto-encoder is developed to pre-train CNNs. After pre-training, the proposed deep model yields a high performance with a limited labeled training samples.

Estimating Maximum Queue Length for Traffic Lane Groups Using Travel Times from Video-Imaging Data

Abstract: Queue length is an important measure that helps traffic managers collect and evaluate feedback about traffic signal control. Some mobile-sensor-based approaches developed in recent years can help identify critical points for understanding the queue process. This involves using sample data related to travel time or trajectory. The latest video imaging detectors facilitate the collection of significant lane-based travel time data, from detectors installed at fixed locations. This paper presents a method to estimate lane-based queue length using the travel time data collected by these new detectors. The first vehicle leaving the downstream stop line is defined as the "leading vehicle" in each signal cycle. The key premise underlying this new method is that the maximum queue length in the first cycle, when the "leading vehicle" is queued, is related to the leading vehicle's delay time and the duration of the red light in each cycle. Queue length in the current cycle is derived by analyzing the recursive formula of maximum queue lengths across different cycles. Finally, the new model's precision is evaluated using a field survey. The results show that the new method has a higher precision compared to the existing method based in a similar concept, with maximum and average deviations of 39.36% and 12.25% respectively, over twenty cycles. The findings of this paper can be applied to improve on traffic signal control systems.

Bike Fleet Allocation Models for Repositioning in Bike-Sharing Systems

Abstract: Public bike-sharing systems provide an alternative transportation method and have been rapidly implemented throughout the world in recent years. Using these systems, individuals can find a bike station near their location, rent a bike for free or at a low cost and then ride to another station near their destination. This paper studies how to determine the number of bikes to be deployed at each station during bike repositioning in bike-sharing systems. The goal is to maximize the time interval between repositioning events, which occur when the demand for renting or returning a bike is not satisfied, or to maximize the satisfaction of demands within a fixed time interval between two repositioning events. To achieve these goals, two mathematical programming models are developed, and a numerical example is used to demonstrate the efficiency of the proposed models.

Road Traffic Conditions Classification Based on Multilevel Filtering of Image Content Using Convolutional Neural Networks

Abstract: Classification of traffic conditions is a vital task for determining traffic control strategies in ITS. Systematic assessment of the volume of traffic enables appropriate changes of control measures for directing traffic streams to reach set goals of performance. Video traffic monitoring is a suitable and convenient source of traffic data. The paper presents a method of classification of road traffic conditions based on video surveillance data. Convolutional neural network is used to classify the video content and establish measures of congestion of the observed traffic. Four levels of traffic conditions are distinguished which correspond to LOS categories. The network is validated using video data from several traffic observation sites. The trained CNN is capable of processing video data for systematic use by subsystems of ITS responsible for traffic management. The results of classification are compared with neural network based classifiers: a MLP (multi layer perceptron) and a DLN (deep learning network) with autoencoders. The proposed method is more accurate and less sensitive to the quality of video data.

Performance Measurement Evaluation Framework and Co-Benefit\/Tradeoff Analysis for Connected and Automated Vehicles (CAV) Applications: A Survey

Abstract: A number of Connected and/or Automated Vehicle (CAV) applications have recently been designed to improve the performance of our transportation system. Safety, mobility and environmental sustainability are three cornerstone performance metrics when evaluating the benefits of CAV applications. These metrics can be quantified by various measures of effectiveness (MOEs). Most of the existing CAV research assesses the benefits of CAV applications on only one (e.g., safety) or two (e.g., mobility and environment) aspects, without holistically evaluating the interactions among the three types of MOEs. This paper first proposes a broad classification of CAV applications, i.e., vehicle-centric, infrastructure-centric, and traveler-centric. Based on a comprehensive literature review, a number of typical CAV applications have been examined in great detail, where a categorized analysis in terms of MOEs is performed. Finally, several conclusions are drawn, including the identification of influential factors on system performance, and suggested approaches for obtaining co-benefits across different types of MOEs.

System Architecture of a Driverless Electric Car in the Grand Cooperative Driving Challenge

Abstract: This paper presents the complete system architecture of a connected driverless electric car designed to participate in the Grand Cooperative Driving Challenge 2016. One of the main goals of this challenge was to demonstrate the feasibility of multiple autonomous vehicles cooperating via wireless communications on public roads. Several complex cooperative scenarios were considered, including the merging of two lanes and cooperation at an intersection. We describe in some detail an implementation using the open-source PACPUS framework that successfully completed the different tasks in the challenge. Our description covers localization, mapping, perception, control, communication and the human-machine interface. Some experimental results recorded in real-time during the challenge are reported.

Robust Communication for Cooperative Driving Maneuvers

Abstract: The proposed benefits of enabling automated and autonomous vehicles to cooperate are manifold - however, these functions introduce a new level of uncertainty and unreliability inherent of wireless communication into a realm of safety-critical decisions. Since vehicle-to-vehicle communication in either ad hoc or managed environments can be inherently unreliable, it is of highest importance to critically evaluate the level and design of integration of cooperative information into the decision making process of automated functions. Thus, a robust integration of communication as a sensor has to take into account key issues such as penetration rate, reliability of communication and trust and develop appropriate methods of handling these issues to provide fail-safety. In this paper we present an approach to cooperative maneuvers in automated vehicles with emphasis on handling potential hazards introduced by communication. In this regard we propose the complimentary Collaborative Maneuver Protocol (CMP), combining novel approaches to enable robust, functionally safe collaboration between vehicles in vehicle-tovehicle communication.

Accuracy Assessment of Weigh-in-Motion Systems for Vehicle?s Direct Enforcement

Abstract: The use of Weigh-in-Motion (WIM) systems for vehicle's direct enforcement depends, first of all, on their high and constant accuracy under variable measurement conditions. This work concerns improving accuracy of weighing results obtained in WIM systems. The method commonly employed for achieving this goal is to increase the number of axle load sensors at the weighing site. The objective of this study is to compare the accuracy of Weigh-in-Motion systems equipped with different numbers of axle load sensors. The paper presents the results of in situ tests and simulations. Experiments were carried out on 16-sensors system and were supplemented by results obtained by simulations using multibody dynamic software. For accuracy assessment of weighing systems, two criteria were used: the 95%-percent relative error and the reliability characteristic. Quantitative relationship between the number of axle load sensors and weighing accuracy was estimated. Optimal number of sensors was evaluated for multi-sensor systems which is a step forward in implementation of WIM systems for direct enforcement of overloading.

Dynamic Trajectory Optimization Design for Railway Driver Advisory System

Abstract: Driver Advisory Systems (DAS) aim to provide reliable and efficient driving instructions to the driver with optimized trajectory. This paper studies trajectory optimization method to achieve energy efficiency and punctuality for DAS. Firstly, the design of offline trajectory optimization is studied, using the Genetic Algorithm (GA) to optimize the energy-efficient trajectory. The performance of offline optimization is evaluated by the application of three different driving styles. Online optimization is constructed to dynamically adjust the trajectory when a driving deviation occurs. The combination of offline optimization and online optimization method is simulated as a dynamic trajectory optimization system, to represent a practical solution for DAS systems to achieve energy efficiency and punctuality by real-time adjustment during the journey. An evaluation of energy saving and computation efficiency for the trajectory optimization is conducted based on a simulation of a real-scale route.

Distributed Radio Map Reconstruction for 5G Automotive

Abstract: Radio maps are expected to be an essential tool for the resource optimization and management of 5G automotive. In this paper, we consider the problem of radio map reconstruction using a wireless sensor network formed by sensor nodes in vehicles, access nodes from a smart city infrastructure, etc. Due to limited resource constraints in sensor networks, it is crucial to select a small number of sensor measurements for field reconstruction. In this context, we present a novel distributed incremental clustering algorithm based on the regression Kriging method for radio map reconstruction in terms of average received power at locations where no sensor measurements are available. The path-loss and shadowing components of the wireless channel are separately estimated. For shadowing estimation, clusters of sensors are adaptively formed and their size is optimized in terms of the least number of sensors by minimizing the ordinary Kriging variance. The complexity of the proposed algorithm is analyzed and simulation results are presented to showcase the algorithm efficacy to field reconstruction.

A Novel Approach to Estimate Freeway Traffic State: Parallel Computing and Improved Kalman Filter

Abstract: This paper presents a novel approach for freeway traffic state estimation. Although there is currently a wide variety of estimation methods, new designs and technologies can still be created and implemented to improve the accuracy and time efficiency. In this study, a parallel computing framework is developed. The parallel computing framework uses a genetic algorithm process to calibrate the parameters of the traffic model based on the freeway traffic data once an hour. Meanwhile, the framework uses a Kalman filter algorithm process to optimize the traffic model results with the real-time freeway traffic data. Under the framework, the operations of the two processes will not interfere with each other, thus reducing the time it takes to estimate, increasing the efficiency. Furthermore, an improved Kalman filter algorithm is proposed. The algorithm optimizes the traffic model results by balancing the ratio of detector measurements to model results based on their variances, instead of using the Taylor series expansion. Therefore, time efficiency and accuracy of the Kalman filter algorithm are improved. The effectiveness of the approach is evaluated using real field data. Experiments have shown that this approach has high real-time tracking accuracy, and is faster and more accurate than the extended Kalman filter. Results also indicated that the estimation accuracy can be enhanced by accessing additional data sources.

Smart Mobility Trends: Open Data and Other Tools

Abstract: The Strategic Implementation Plan for speeding up the transformation of European Cities into "Smart cities" establishes 6 Actions Clusters and 11 Priority Areas. Some of them are directly related to the transport and sustainable urban mobility. The main goal is the application of new technologies to minimize the loss of time and energy, and to improve the satisfaction of citizens. The use and reuse of information as open data, already collected from the Public Administration and private entities is a source of possibilities adding extra value. Technologies such as Bluetooth sensors, Open Data platforms etc., become essential elements to achieve this goal. This paper highlights the opportunity to take advantage of emerging technologies, like the open source data platforms, or to use services for data linked queries. As an example of application of these technologies to the transport domain, several use cases with some results are presented.

Traffic Events Oriented Dynamic Traffic Assignment Model for Expressway Network: A Network Flow Approach

Abstract: In this paper, we focus on the dynamic traffic assignment (DTA) problem on large-scale expressway networks especially under the condition of traffic events (such as severe weather, large traffic accidents etc.). We formulate the expressway network DTA problem as a nonconvex optimization problem. Considering the difficulty of solving the problem, we put forward an approximate solution algorithm based on the network flow theory with high computational efficiency and strong applicability. Specifically, a machine learning approach and a series of customization strategies of network flow model (including multi-origin and multidestination split, flow discretization and parallel edges addition methods) are proposed to transform the DTA problem into a resoluble network flow problem. After that, in order to improve the operational efficiency of an expressway network after traffic events occurring, the proposed network flow based two-layer DTA model (NTDM) is separated into two parts-traffic flow limitation model based on maximum flow algorithm and traffic assignment model based on minimum cost flow algorithm. Experiments on real expressway network data in some provinces of China show that our method can make a significant 26.03% reduction in saturation rate in a particular scenario. In efficiency test, the NTDM is at least 600 times faster than the traditional analytic method in a network with thousands of nodes.

Distributed Agent-Based Traffic Simulations

Abstract: Modeling and simulation play an important role in transportation networks analysis. With the widespread of personalized real-time information sources, it is relevant for the simulation model to be individual-centered. The agent-based simulation is the most promising paradigm in this context. However, representing the movements of realistic numbers of travelers within reasonable execution times requires significant computational resources. It also requires relevant methods, architectures and algorithms that respect the characteristics of transportation networks. In this paper, we tackle the problem of using high-performance computing for agent-based traffic simulations. To do so, we define two generic agent-based simulation models, representing the existing sequential agent-based traffic simulations. The first model is macroscopic, in which travelers do not interact directly and use a fundamental diagram of traffic flow to continuously compute their speeds. The second model is microscopic, in which travelers interact with their neighbors to adapt their speeds to their surrounding environment. We define patterns to distribute these simulations in a high-performance environment. The first distributes agents equally between available computation units. The second pattern splits the environment over the different units. We finally propose a diffusive method to dynamically balance the load between units during execution. The results show that agent-based distribution is more efficient with macroscopic simulations, with a speedup of 6 compared to the sequential version, while environmentbased distribution is more efficient with microscopic simulations, with a speedup of 14. Our diffusive load-balancing algorithm improves further the performance of the environment based approach by 150%.

Fast Joint Object Detection and Viewpoint Estimation for Traffic Scene Understanding

Abstract: Environment perception is a critical enabler for automated driving systems since it allows a comprehensive understanding of traffic situations, which is a requirement to ensure safe and reliable operation. Among the different applications, obstacle identification is a primary module of the perception system. We propose a vision-based method built upon a deep convolutional neural network that can reason simultaneously about the location of objects in the image and their orientations on the ground plane. The same set of convolutional layers is used for the different tasks involved, avoiding the repetition of computations over the same image. Experiments on the KITTI dataset show that our efficiency-oriented method achieves state-of-the-art accuracies for object detection and viewpoint estimation, and is particularly suitable for the recognition of traffic situations from on-board vision systems. Code is available at https://github.com/cguindel/lsi-faster-rcnn.

Software Defined Wi-V2G: A V2G Network Architecture

Abstract: The valley-to-peak difference in power consumption is a crucial problem in load regulation and control for a power grid. By allowing electric vehicles (EVs) to charge during off-peak hours and feed power back into the grid during peak hours, Vehicle-to-Grid (V2G) technology can help to shave the power peak. Long-distance communication is essential for data exchange between dispersed EVs and charging stations for the realization of V2G systems. However, because of the high mobility of EVs, the highvolume data transmission required and the limitations of the third-party infrastructure, it is challenging to achieve efficient and effective communication. To address these challenges, we propose a new V2G network architecture based on software-defined networking (SDN) technology. (1) We use an IEEE 802.11 WiFibased long-distance (WiLD) network with the TDMA scheme as the backhaul network, and (2) we partially replace the road side units (RSUs) with some of the WiLD nodes to provide access for, and to rapidly broadcast data to, EVs. In addition, we propose: (3) a two-stage flow table mechanism and a double roaming mechanism to address the mobility demands of V2G network terminals; and (4) a rapid data transmission scheme for communication from charging stations to EVs. A testbed was built to validate the proposed network architecture. Experimental results show that the communication time delay is in the order of milliseconds and that the reliability is higher than 99.9%.

Virtual Vehicle-Based Cooperative Maneuver Planning for Connected Automated Vehicles at Single-Lane Roundabouts

Abstract: This paper presents a distributed maneuver planner for connected automated vehicles (CAVs) built upon the idea of CAVs being able to explicitly share their intentions by creating virtual vehicles (VVs) on the targeted traffic stream. Specifically, this work focuses on the decision-making process concerning the merging maneuver at single-lane roundabouts, for which a traffic model is exploited to assess the suitability of potential merging gaps. An optimization-based trajectory planner is then used to generate collision-free, smooth trajectories to successfully perform the planned maneuver. The algorithm is tested in simulation and its performance is compared with a gap-acceptance-based driving policy. The results show the potential positive impact that the proposed VV-based interaction mechanism along with the traffic-model based cooperative maneuver planner could have on traffic coordination.

Adaptive Security for Intelligent Transport System Applications

Abstract: The transportation system is gradually migrating toward autonomous, electric and intelligent vehicles. Wireless-enabled vehicles along with infrastructure units on the road are connected with traffic management centers that use intelligent data analysis tools to efficiently manage city's traffic. However, such wireless connectivity can make the ITS networks vulnerable to security threats; thus, impacting the application's reliability. On the other hand, the use of robust security techniques could hamper applications' quality of service (QoS). To understand the interplay between these two conflicting requirements, this article reviews the security and QoS design challenges in the ITS aspect of smart cities. Using an experimental test-bed, we evaluate the standard compliant security processing delays, develop an on-line tool that presents detailed security benchmark results, and study the impact of security on QoS using simulation results. We also discuss how machine learning based adaptive signature verification techniques can enhance QoS in ITS. We further present future opportunities to optimize the security-QoS balance for ITS applications.

Multiscale Site Matching for Vision-Only Self-Localization of Intelligent Vehicles

Abstract: Self-localization is a challenging issue in intelligent vehicle (IV) systems. Traditional self-localization methods, such as the Global Navigation Satellite System (GNSS), Inertial Navigation System (INS) and vision simultaneous localization and mapping (vSLAM), are subject to low accuracy, high cost or low robustness. To this end, this paper proposes a new multi-scale site matching localization (MS2ML) method for IV systems by using one single monocular camera. The MS2ML consists of a coarse localization, an image-level localization and a metric localization. In coarse localization, the proposed MS2ML calls the Bayesian vision-motion topological localization to obtain a set of nodes from a visual map. Furthermore, the holistic feature is generated for each query image, and hence, the holistic feature matching is implemented to realize image-level localization. A node is then selected from the candidate nodes. In metric localization, the closest node and vehicle pose are calculated through matching local features with three-dimension (3D) data. In order to evaluate the proposed MS2ML, real-world driving tests have been carried out in three different routes, two of which are from an urban roadway and an industrial park in Wuhan, China and the third one is from public KITTI (Karlsruhe Institute of Technology and Toyota Technology Institute) data set. The total lengths of these routes are more than 7 km. The experiment results demonstrate that the average localization errors of the proposed MS2ML method are less than 0.45 frame and the pose errors are less than 0.59 m. As a result, the proposed method remains high accuracy and great robustness in various environments.

PCIV, an RFID-Based Platform for Intelligent Vehicle Monitoring

Abstract: This article presents a new platform called PCIV (intelligent platform for vehicular control) for traffic monitoring, based on radio frequency Identification (RFID) and cloud computing, applied to road traffic monitoring in public transportation systems. This paper shows the design approach and the experimental validation of the platform in two real scenarios: a university campus and a small city. Experiments demonstrated RFID technology is viable to be implemented to monitor traffic in smart cities.

Methods for Multi-Type Sensor Allocations Along a Freeway Corridor

Abstract: Existing layouts of sensors on freeways usually have room for improvement. The optimal allocation of multi-type sensors could increase the accuracy and coverage of data acquisition for traffic control and management. This paper aims to explore the appropriate method to solve the multi-type sensor allocation problem on freeways. Two types of sensors, the micro-loop sensor and the microwave sensor, are considered in this study. Three sensor allocation methods, the Integer Programming-Genetic Algorithm (IP-GA) method, the cluster method, and the two-stage method, are proposed to identify the optimal sensor locations. To investigate the performances of our proposed methods, a case study of sensor allocations on Ning-Hang freeway in Jiangsu province, China was conducted. The analysis results demonstrated that the IP-GA method has the best performance among the three proposed algorithms in view of the Mean Absolute Relative Errors (MAREs) of link travel time. Besides, this study also found that optimizing the composition of sensors has a far greater impact on data accuracy than just increasing the number of sensors. Within a specific range, data accuracy increases along with the number of sensors. Under the cases of the total number being constant, the greater the proportion of high accuracy sensors, the more accurate of the estimated traffic information.

Vehicular Cloud Construction and Content Acquisition

Abstract: With the evolution of the inherent properties of vehicular contents, the Vehicular Cloud (VC) has emerged as a new vehicular system. The VC can rapidly and locally provide contents to improve driving safety and efficiency. The characteristics of vehicles such as large populations and high mobility result in frequent content acquisition that leads to heavy vehicular content traffic. Moreover, the VC employs content-centric flooding to achieve content acquisition, and this flooding further exacerbates the situation. Therefore, one critical problem faced by the VC is the considerable content acquisition cost. In this paper, we focus on the content acquisition issue in the VC and propose a new content acquisition solution to reduce the content acquisition cost. The main idea of our solution is to employ address-centric unicast instead of content-centric flooding to achieve the content acquisition in the VC. To make the idea work, we propose a new address structure in order to build the relationship between a specific kind of content and the address of the provider of the content. Based on the new address structure, we present a new unicastbased content acquisition algorithm. The content acquisition cost is quantitatively evaluated. According to the experimental results, our solution reduces the content acquisition cost by nearly 78% compared with the content-centric approaches.

Examining the Impact on Road Safety of Different Penetration Rates of Vehicle-to-Vehicle Communication and Adaptive Cruise Control

Abstract: In recent years, significant attention has been paid to the implementation of cooperative driving by means of the integration of Advanced Driver Assistance Systems (ADAS) and Vehicle-to-Vehicle (V2V) communication, which has led to a wide range of applications with the potential to enhance road safety and prevent traffic accidents Prior to the implementation of these systems in vehicles, comprehensive analysis through exhaustive and realistic simulations is vital Accordingly, this paper presents the effects on road safety of a variety of penetration rates of vehicles equipped with ADAS and V2V, either separately or combined, using the simulation platforms Scene Suite and Simulation of Urban Mobility (SUMO) A total of six simulation scenarios were developed, three for intersections and three for urban cases The obtained results show that the ADAS Adaptive Cruise Control (ACC) requires combination with V2V communication in order to increase safety, especially in certain scenarios with side and rear-end collisions However, V2V alone at the lowest penetration rate already provided a level of safety similar to the one reached by combining it with ADAS-ACC

A Multi-Objective Decision Support System for Real-Time Train Rescheduling

Abstract: This study proposes a multi-objective simulation-based optimization framework to effectively manage the train traffic after the occurrences of a disturbance caused by a partial/full blockage. In such conditions, the train orders and the corresponding priorities can be changed to effectively manage the disturbed situation. At this point, a multi-objective version of the variable neighborhood search meta-heuristic is proposed to solve the real-time traffic rescheduling problem and generate Pareto frontiers. The obtained Pareto optimal solutions for disturbance management model supports the decisions made by the rail controllers to find a trade-off between both user and operator viewpoints. We evaluate the proposed approach on a set of disturbance scenarios covering a large part of the Iranian rail network. The computational results demonstrate that the proposed model can generate good-quality disposition timetables with the minimum total average delay of trains at destinations and deviation from the initial timetable. The results indicate that the disturbance management methodology has important advantages in producing practical solution quickly when compared to existing solutions.