Search

Driven by the massive number of connected vehicles and the stringent requirements of data-intensive applications, logistics transportation systems have evolved to fully comprehend its effectiveness and quality to meet public transportation needs. As a result, to meet public transportation requirements and analyze the data efficiently at the edge of the networks, an advanced artificial intelligent technique needs to be introduced to make the transportation system intelligent by supporting efficient decision making, intelligent traffic control, and intrusion and misuse detection.Motivated by the challenges mentioned above, in this paper, we develop a logistic agent-based model for analyzing public transports such as cars, bus or trains in the intelligent transportation system. The intelligent logistic framework is built on a parallel neural network structure, known as a Swarm-Neural Network (SWNN). The proposed SWNN model analyzes the sensory data and recognizes the public transportation at the edge of the networks. The SWNN model is constructed so that it fits within the intelligent logistic transportation framework, and the proposed model shortens the transit time of every small-scale logistics delivery to its destination. The performance of the proposed SWNN model is evaluated using a standard TMD dataset, where the SWNN model is trained using data, retrieved multiple sensors such as accelerometer, gyroscope, magnetometer, and audio sensors. The features of the sensory data are extracted based on a 5-s time interval. The performance of the proposed SWNN model is studied over various standard machine learning techniques such as Random Forest, XGBoost, and Decision Tree. As per the simulation results, the proposed technique achieves 78–98% accuracy over a real-time dataset's different sets of features. [ABSTRACT FROM AUTHOR]

The increasing adoption of intelligent transportation system (ITS) data in smart-city initiatives worldwide has offered unprecedented opportunities for improving transportation air quality management. In this paper, we demonstrate the effective use of ITS and other traffic data to develop a link-level and hourly-based dynamic vehicle emission inventory. Our work takes advantage of the extensive ITS infrastructure deployed in Nanjing, China (6600 km 2 ) that offers high-resolution, multi-source traffic data of the road network. Improved than conventional emission inventories, the ITS data empower the strength of revealing significantly temporal and spatial heterogeneity of traffic dynamics that pronouncedly impacts traffic emission patterns. Four urban districts account for only 4% of the area but approximately 30%–40% of vehicular emissions (e.g., CO 2 and air pollutants). Owing to the detailed resolution of road network traffic, two types of emission hotspots are captured by the dynamic emission inventory: those in the urban area dominated by urban passenger traffic, and those along outlying highway corridors reflecting inter-city freight transportation (especially in terms of NO X ). Fine-grained quantification of emissions reductions from traffic restriction scenarios is explored. ITS data-driven emission management systems coupled with atmospheric models offer the potential for dynamic air quality management in the future. [ABSTRACT FROM AUTHOR]

Abstract Based on the cellular automaton model and the concept of ant pheromone, this paper proposes a new route guidance strategy, called the ant pheromone route guidance strategy, in which the vehicles are regarded as special types of ants and their traffic information is regarded as the ant pheromone. To evaluate its performance, the new route guidance strategy was applied and compared with other three typical route guidance strategies under three different route scenarios, respectively, with open boundary conditions based on the Nagel–Schreckenberg cellular automaton model. First, in a symmetrical two-route scenario with two exits, results showed that the new route guidance strategy and vacancy length route guidance strategy were optimal. They outperformed the other strategies in terms of the value, stability, and balance of vehicle number, and the average speed and average flux on each route. To understand the impact of the strategy on traffic states, flux–density evolution process was studied. In addition, the influence of evaporation rate was also investigated. Second, in an asymmetrical two-route scenario with one exit, the simulation results also proved that ant pheromone route guidance strategy and vacancy length route guidance strategy were the best. Finally, in a symmetrical two-route scenario with a traffic accident, we compared the new route guidance strategy with the vacancy length route guidance strategy. Results indicated that the new route guidance strategy has distinct advantages. In short, in all three route scenarios we investigated, the ant pheromone route guidance strategy performed best. Highlights • This paper proposes the ant pheromone route guidance strategy based on CA model. • The new strategy takes vehicles as ants and vehicles' data as ant pheromones. • Adopting the NS model, this strategy is applied to three two-route scenarios. • Results indicate that the new strategy outperforms other route guidance strategies. • In traffic accident, the new strategy can reduce congestion and save recovery time. [ABSTRACT FROM AUTHOR]

A smart city improves the quality of its citizens by providing access to ubiquitous services. Intelligent Transportation Systems (ITS) have a fundamental role in transforming a metropolitan area into a smart city. In the past two decades, many applications of ITS, e.g. city-wide traffic management and monitoring, smart parking, public transportation information services (bus, train, taxi, plane, etc.), logistics, real-time traffic, road speed limit monitoring and management etc., are deployed in smart cities. The sensors or mobile objects in ITS constantly generate mobility data and the scale at which this data is generated is witnessing an exponential increase in volumes. To store and subsequently analyze such massive data generated by sensors, new architectures are needed which are primarily designed for working with big data. In this work, we propose a big data analytics architecture for ITS. The proposed architecture has a built-in storage and analysis capability to work with ITS data and is composed of four modules, namely (1) Big Data Acquisition and Preprocessing Unit (2) Big Data Processing Unit (3) Big Data Analytics Unit and (4) Data Visualization Unit. A detailed analysis of ITS big data for monitoring the average speed of a vehicle at w.r.t. the time attribute is provided. The proposed architecture is evaluated using Hadoop thus validating the proof of concept. The empirical results are encouraging and open directions for future research. [ABSTRACT FROM AUTHOR]

An important question for the practical applicability of the highly efficient traffic intersection control is about the minimal level of intelligence the vehicles need to have so as to move beyond the traffic light control. We propose an efficient intersection traffic control scheme without the traffic lights, that only requires a majority of vehicles on the road to be equipped with a simple driver assistance system. The algorithm of our scheme is completely decentralised, and takes into full account the non-linear interaction between the vehicles at high density. For vehicles approaching the intersection in different directions, our algorithm imposes simple interactions between vehicles around the intersection, by defining specific conditions on the real-time basis, for which the involved vehicles are required to briefly adjust their dynamics. This leads to a self-organised traffic flow that is safe, robust, and efficient. We also take into account of the driver comfort level and study its effect on the control efficiency. The scheme has low technological barrier, minimal impact on the conventional driving behaviour, and can coexist with the traffic light control. It also has the advantages of being easily scalable, and fully compatible with both the conventional road systems as well as the futuristic scenario in which driverless vehicles dominate the road. The mathematical formulation of our scheme permits large scale realistic numerical simulations of busy intersections, allowing a more complete evaluation of the control performance, instead of just the collision avoidance at the intersection. [ABSTRACT FROM AUTHOR]

Automatic vehicle classification is very important for video surveillance, especially for intelligent transportation system. Currently, some approaches have been proposed. However, almost all of these methods cannot play well in the practical crowded traffic scenes with heavy occlusions, shadows, and different views, etc. To solve this difficult problem, we propose a new vehicle classification method based on hierarchical multi-SVMs. First, we extract the foreground objects from the surveillance videos. Then, we use the proposed hierarchical multi-SVMs method for vehicle classification. Moreover, we present a voting based correction scheme by tracking the classified vehicles for the final precision. Based on the proposed approach, we have built a practical system for robust vehicle classification in complicated traffic scenes. Extensive experimental results show that our solution can achieve convincing results. [ABSTRACT FROM AUTHOR]

Transitions between two lanes often have a significant impact on various forms of road traffic. To address this problem, we have developed a two-lane asymmetric simple exclusion process model and two hypothetical traffic control strategies, to simulate a futuristic scenario where the timing and location of transitions between two lanes are highly controlled. Various scenarios were proposed to study the effectiveness of these control strategies. An optimized control strategy, whose parameters were determined through an optimization algorithm, is confirmed to effectively maximize the average traffic flow. Consequently, we may identify suitable road sections and the corresponding timings of transitions to resolve congestion in this model. • Regulated transitions between two lanes can improve traffic flow. • Regulations are simulated using the ASEP model and a hypothetical control strategy. • Parameters of the control strategy are determined with an optimization algorithm. • The control strategy can determine positions and timings suitable for transitions. [ABSTRACT FROM AUTHOR]

Improvement of traffic signal control (TSC) efficiency has been found to lead to improved urban transportation and enhanced quality of life. Recently, the use of reinforcement learning (RL) in various areas of TSC has gained significant traction; thus, we conducted a systematic literature review as a systematic, comprehensive, and reproducible review to dissect all the existing research that applied RL in the network-level TSC domain, called as RL in NTSC or RL-NTSC for brevity. The review only targeted the network-level articles that tested the proposed methods in networks with two or more intersections. This review covers 160 peer-reviewed articles from 30 countries published from 1994 to March 2020. The goal of this study is to provide the research community with statistical and conceptual knowledge, summarize existence evidence, characterize RL applications in NTSC domains, explore all applied methods and major first events in the defined scope, and identify areas for further research based on the explored research problems in current research. We analyzed the extracted data from the included articles in the following seven categories: (i) publication and authors' data, (ii) method identification and analysis, (iii) environment attributes and traffic simulation, (iv) application domains of RL-NTSC, (v) major first events of RL-NTSC and authors' key statements, (vi) code availability, and (vii) evaluation. This paper provides a comprehensive view of the past 26 years of research on applying RL to NTSC. It also reveals the role of advancing deep learning methods in the revival of the research area, the rise of using non-commercial microscopic traffic simulators, a lack of interaction between traffic and transportation engineering practitioners and researchers, and a lack of proposal and creation of testbeds which can likely bring different communities together around common goals. • A review on Reinforcement Learning in the network-scale Traffic Signal Control area. • Presents a comprehensive systematic literature review of 160 included articles. • Consolidates and characterizes the existing research on the defined area. • Explores the methods, applications, domains, and first events in the defined scope. • Identifies past and present trends and directions for further research in the area. [ABSTRACT FROM AUTHOR]

Lane change maneuvers contribute to a significant number of road traffic accidents. Advanced driver assistance systems (ADAS) that can assess a traffic situation and warn drivers of unsafe lane changes can offer additional safety and convenience. In addition, ADAS can be extended for use in automatic lane changing in driverless vehicles. This paper investigated two ensemble learning methods, random forest, and AdaBoost, for developing a lane change assistance system. The focus on increasing the accuracy of safety critical lane change events has a significant impact on lowering the occurrence of crashes. This is the first study to explore ensemble learning methods for modeling lane changes using a comprehensive set of variables. Detailed vehicle trajectory data from the Next Generation Simulation (NGSIM) dataset in the US were used for model development and testing. The results showed that both ensemble learning methods produced higher classification accuracy and lower false positive rates than the Bayes/Decision tree classifier used in the literature. The impact of misclassification of lane changing events was also studied. A sensitivity analysis performed by varying the accuracy of lane changing showed that the lane keeping accuracy can be increased to as high as 99.1% for the AdaBoost system and 98.7% for the random forest system. The corresponding true positive rates were 96.3% and 94.6%. High accuracy of lane keeping and high true positive rates are desirable due to their safety implications. [ABSTRACT FROM AUTHOR]

Recent advances in Inter-Vehicle Communications (IVC) and Vehicle-Infrastructure Integration (VII) paved ways to real-time information sharing among vehicles, which are beneficial for vehicle energy management strategies (EMS). This is especially valuable for power-split hybrid electrical vehicles (HEV) in order to determine the optimal power-split between two different power sources at any particular time. Certainly, researches in this area have been done, but tradeoffs between optimality, driving-cycle sensitivity, speed of calculation and charge-sustaining (CS) conditions have not been cohesively addressed before. In light of this, a combined approach of a time-efficient powertrain optimization strategy, utilizing trajectory prediction based on IVC and VII is proposed. First, Gipps’ car following model for traffic prediction is used to predict the interactions between vehicles, combined with the cell-transmission-model (CTM) for the leading vehicle trajectory prediction. Secondly, a computationally efficient charge-sustaining (CS) HEV powertrain optimization strategy is analytically derived and simulated, based on the Pontryagin’s Minimum Principle and a CS-condition constraint. A 3D lookup-map, generated offline to interpolate the optimizing parameters based on the predicted speed, is also utilized to speed up the calculations. Simulations are conducted for 6-mile and 15-mile cases with different prediction update timings to test the performance of the proposed strategy against a Rule-Based (RB) control strategy. Results for accurate-prediction cases show 9.6% average fuel economy improvements in miles-per-gallon (MPG) over RB for the 6-mile case and 7% improvements for the 15-mile case. Prediction-with-error cases show smaller average MPG’s improvements, with 1.6% to 4.3% improvements for the 6-mile case and 2.6% to 3.4% improvements for the 15-mile case. [ABSTRACT FROM AUTHOR]

• In MCS, the GPS embedded vehicles and motorist mobiles are used to sense and collect the vehicular data. • MCS-DTEF mechanism is applied to assign time slot and allocate fastest path dynamically to every vehicle to minimize traffic congestions. • MCS-DTEF strategy demonstrates significantly improved traffic flow performance in terms of reducing time and fuel consumption. Mobile Crowd Sensing (MCS) is a developing category of Internet of Things applications that are used in Intelligent Transportation System to improve the transport system. In today's metropolitan life, traffic congestion in busy hours is the main problem due to which many commuters are unable to reach their destination on time, motorist time and extra fuel are wasted. In this paper, the MCS-based Dynamic Traffic Efficiency Framework (MCS-DTEF) for traffic congestion control is presented. The basic characteristics of MCS-DTEF are: traffic detection can be performed without deploying sensor devices on both sides of the road. The traffic data can be collected in real time, traffic flow can be predicted and managed according to current situations which reducing fuel consumption and driving time. Simulation of Urban Mobility simulator is used for evaluation. Meaningful and reliable statistical data is obtained by the traffic flow which is built according to Normal Traffic Conditions (NTC's) in the first scenario. In the second simulation scenario, the MCS-DTEF mechanism is applied to assign a time slot to a requested vehicle and dynamically allocate the fastest path to each vehicle which is introduced to avoid traffic congestion. To validate the results of the proposed framework technique by comparing with NTC's and real-world traffic flow in three different situations morning, afternoon and evening are examined and tested to explore the traffic usage parameter. The results show that the MCS-DTEF strategy demonstrates significantly improved traffic flow performance in terms of reducing time to destination, fuel consumption and increased vehicle average speed. [ABSTRACT FROM AUTHOR]

Abstract: Connected Vehicle (CV) technology, formerly known as IntelliDrive, has emerged and is expected to provide unprecedented improvements in mobility. A recent study developed a cooperative vehicle intersection control (CVIC) algorithm for an urban intersection that does not require a stop-and-go style traffic signal and demonstrated significant mobility improvements over an actuated traffic signal control. This paper expanded the algorithm and implemented it to a corridor consisting of multiple intersections. In addition, this paper investigated sustainability aspects of the CVIC system for an urban traffic control system by applying surrogate safety assessment model (SSAM) and VT-Micro model to measure safety and environmental impacts, respectively. A simulation-based case study was performed on a hypothetical arterial consisting of four intersections with eight traffic congestion cases covering low to high volume conditions. When compared to the coordinated actuated control, the CVIC system dramatically reduced the total delay times for the volume cases considered (i.e., from 82% to 100% delay time savings observed). The CVIC system also reduced the number of rear-end crash events by 30–87% for the volume cases considered, indicating that safer driving conditions would be achieved with the CVIC system. Finally, the CVIC system contributed to improving the air quality (i.e., 12–36% CO2 emission reduction) and saving fuel consumptions (11–37% of gas saving). [Copyright &y& Elsevier]

Abstract: The performance of many components in intelligent transportation systems depends heavily on the quality of traffic forecasting. After analyzing the deficiency of existing algorithm and methods in traffic forecasting, we develop a new traffic forecasting model based on logic reasoning and in this paper, we describe the details of each part of this model. Finally through an example, we introduce the working order of the model in traffic forecasting. [Copyright &y& Elsevier]

Abstract: Sensors are becoming increasingly critical elements in contemporary transportation systems, gathering essential (real-time) traffic information for the planning, management and control of these complex systems. In a recent paper, Hu, Peeta and Chu introduced the interesting problem of determining the smallest subset of links in a traffic network for counting sensor installation, in such a way that it becomes possible to infer the flows on all remaining links. The problem is particularly elegant because of its limited number of assumptions. Unfortunately, path enumeration was required, which – as recognized by the authors – is infeasible for large-scale networks without further simplifying assumptions (that would destroy the assumption-free nature of the problem). In this paper, we present a reformulation of this link observability problem, requiring only node enumeration. Using this node-based approach, we prove a conjecture made by Hu, Peeta and Chu by deriving an explicit relationship between the number of nodes and links in a transportation network, and the minimum number of sensors to install in order to be able to infer all link flows. In addition, we demonstrate how the proposed method can be employed for road networks that already have sensors installed on them. Numerical examples are presented throughout. [Copyright &y& Elsevier]

Abstract: Augmented Reality “AR” is a promising paradigm that can offer users with real-time, high-quality visualization of a wide variety of information. In AR, virtual objects are added to the real-world view in real time. The AR technology can offer a very realistic environment for enhancing drivers’ performance on the road and testing drivers’ ability to react to different road design and traffic operations scenarios. This can be achieved by adding virtual objects (people, vehicles, hazards, and other objects) to the normal view while driving an actual vehicle in a real environment. This paper explores a new Augmented Reality Vehicle “ARV” system and attempts to apply this new concept to a selected traffic engineering application namely the left-turn maneuver at two-way stop-controlled “TWSC” intersection. This TWSC intersection experiment, in addition to testing the feasibility of the application, tries to quantify the size of gaps accepted by different driver’s characteristics (age and gender). The ARV system can be installed in any vehicle where the driver can see the surrounding environment through a Head Mounted Display “HMD” and virtual objects are generated through a computer and added to the scene. These different environments are generated using a well defined set of scenarios. The results from this study supported the feasibility and validity of the proposed ARV system and they showed promise for this system to be used in the field-testing for the safety and operation aspects of transportation research. Results of the left-turn maneuver study revealed that participants accepted gaps in the range of 4.0–9.0s. This finding implies that all gaps below 4s are rejected and all gaps above 9s are likely to be accepted. The mean value of the left-turn time was 4.67s which is a little bit higher than reported values in the literature (4.0–4.3s). Older drivers were found to select larger gaps to make left turns than younger drivers. The conservative driving attitude of older drivers indicates the potential presence of reduced driving ability of elderly. Drivers’ characteristics (age and gender) did not significantly affect the left-turn time. Based on the survey questions that were handed to participants, most participants indicated good level of comfort with none or small level of risk while driving the vehicle with the ARV system. None of the participants felt any kind of motion sickness and the participants’ answers indicated a good visibility and realism of the scene with overall good system fidelity. [Copyright &y& Elsevier]

Abstract: This paper presents an application of diverse soft-computing techniques to adaptive traffic light controls. The proposed methodology consists of two main phases: off-line and on-line. First, clustering techniques and optimization methods are used at the off-line stage to discover the prototypes which characterize the traffic mobility patterns at an intersection. After this process an optimum timing plan is decided for each mobility pattern detected. In the on-line phase, a prediction model is then constructed on the basis of the prototypes found. Fuzzy Logic based techniques are used to formally represent the prototypes in the prediction model and these prototypes are parametrically defined through frameworks. During the on-line phase an intelligent transportation system, by using the prediction model, matches the current traffic conditions to the mobility patterns detected at the off-line stage in order to identify the most suitable one to be used. The use of these techniques supposes a substantial contribution to the significance of the prediction model, making it robust in the face of anomalous mobility patterns, and efficient from the point of view of real-time computation. [ABSTRACT FROM AUTHOR]