Search

Machine learning (ML) methods, particularly Reinforcement Learning (RL), have gained widespread attention for optimizing traffic signal control in intelligent transportation systems. However, existing ML approaches often exhibit limitations in scalability and adaptability, particularly within large traffic networks. This paper introduces an innovative solution by integrating decentralized graph-based multi-agent reinforcement learning (DGMARL) with a Digital Twin to enhance traffic signal optimization, targeting the reduction of traffic congestion and network-wide fuel consumption associated with vehicle stops and stop delays. In this approach, DGMARL agents are employed to learn traffic state patterns and make informed decisions regarding traffic signal control. The integration with a Digital Twin module further facilitates this process by simulating and replicating the real-time asymmetric traffic behaviors of a complex traffic network. The evaluation of this proposed methodology utilized PTV-Vissim, a traffic simulation software, which also serves as the simulation engine for the Digital Twin. The study focused on the Martin Luther King (MLK) Smart Corridor in Chattanooga, Tennessee, USA, by considering symmetric and asymmetric road layouts and traffic conditions. Comparative analysis against an actuated signal control baseline approach revealed significant improvements. Experiment results demonstrate a remarkable 55.38% reduction in Eco_PI, a developed performance measure capturing the cumulative impact of stops and penalized stop delays on fuel consumption, over a 24 h scenario. In a PM-peak-hour scenario, the average reduction in Eco_PI reached 38.94%, indicating the substantial improvement achieved in optimizing traffic flow and reducing fuel consumption during high-demand periods. These findings underscore the effectiveness of the integrated DGMARL and Digital Twin approach in optimizing traffic signals, contributing to a more sustainable and efficient traffic management system. [ABSTRACT FROM AUTHOR]

With the increasing number of urban vehicles, as well as the current situation of non-intelligent traffic control systems, spatiotemporal non-uniform traffic resource occupation, and limited traffic planning and design, existing urban traffic planning methods cannot effectively solve problems such as frequent traffic congestion and uncontrollable commuting time for residents. In order to solve the above problems, this paper first constructs a multi-queue, multi-server queuing model based on the server vacation and a multi-hop cascaded queuing model from the perspective of local intersections and global commuting paths. We analyze the theoretical changes in passage delay costs at local intersections and on global commuting paths as a function of traffic flow and the random duration of traffic signals. On this basis, this article proposes a collaborative intelligent traffic planning algorithm based on artificial intelligence, which utilizes traffic sensors to dynamically perceive traffic congestion status and collaboratively plans the optimal duration of traffic signals and the optimal driving path of vehicles from both local and global perspectives, thereby maximizing the on-time arrival ratio of vehicles while ensuring the required commuting delay. The simulation results show that the proposed method can increase the on-time arrival ratio of vehicles by at least 20% compared to contrast methods while meeting the requirements relating to commuting delays. This verifies that our method can provide support for the improvement in efficiency in future Internet of vehicles. [ABSTRACT FROM AUTHOR]

License plate detection is an important task in Intelligent Transportation Systems (ITS) and has a wide range of applications in vehicle management, traffic control, and public safety. In order to improve the accuracy and speed of mobile recognition, an improved lightweight YOLOv5s model is proposed for license plate detection. First, an improved Stemblock network is used to replace the original Focus layer in the network, which ensures strong feature expression capability and reduces a large number of parameters to lower the computational complexity; then, an improved lightweight network, ShuffleNetv2, is used to replace the backbone network of the YOLOv5s, which makes the model lighter and ensures the detection accuracy at the same time. Then, a feature enhancement module is designed to reduce the information loss caused by the rearrangement of the backbone network channels, which facilitates the information interaction in the feature fusion process; finally, the low‐, medium‐ and high‐level features in the Shufflenetv2 network structure are fused to form the final high‐level output features. Experimental results on the CCPD dataset show that compared to other methods this paper obtains better performance and faster speed in the license plate detection task, in which the average precision mean value reaches 96.6%, and can achieve a detection speed of 43.86 frame/s, and the parameter volume is reduced to 5.07 M. [ABSTRACT FROM AUTHOR]

Summary: Road accidents and traffic congestion are the unavoidable consequences of the growing number of vehicles on the road. Conventional management systems are not effective in mitigating these issues. However, a range of technologies, including sensors, processors, vehicle‐based resources, and mobile cloud computing, can help solve traffic and safety problems. Vehicular cloud networks, a cutting‐edge technology for the development of intelligent transportation systems, face significant challenges, such as ensuring reliable service providers that maintain stable connections between vehicles. Roadside units (RSUs) play a crucial role in these networks, but they come with several drawbacks, including high costs, imbalanced load distribution, and unreliable connections. To address these issues, we propose the Traffic Control and Safety in Vehicular Networks (TCaS‐VN) algorithm, a cloud‐based sharing services framework for vehicles that eliminates the need for RSUs. This approach offers several advantages, including a twofold improvement in the lifetime of clusters, the elimination of noncluster head nodes, a 54% reduction in overhead, a 58% reduction in service search time, and a success rate of over 95% in service provisioning. [ABSTRACT FROM AUTHOR]

Vehicle trajectory prediction can provide important support for intelligent transportation systems in areas such as autonomous driving, traffic control, and traffic flow optimization. Predicting vehicle trajectories is an extremely challenging task that not only depends on the vehicle's historical trajectory but also on the dynamic and complex social-temporal relationships of the surrounding traffic network. The trajectory of the target vehicle is influenced by surrounding vehicles. However, existing methods have shortcomings in considering both time dependency and interactive dependency between vehicles or insufficient consideration of the impact of surrounding vehicles. To address this issue, we propose a hybrid deep learning model based on a temporal convolutional network (TCN) that considers local and global interactions between vehicles. Specifically, we use a social convolutional pooling layer to capture local interaction features between vehicles and a multihead self-attention layer to capture global interaction features between vehicles. Finally, we combine these two features using an encoder-decoder structure to predict vehicle trajectories. Through experiments on the Next-Generation Simulation (NGSIM) public dataset and ablation experiments, we validate the effectiveness of our model. [ABSTRACT FROM AUTHOR]

The rapid advancements in computer systems and wireless sensor networks (WSNs) motivate many intelligent transportation systems (ITSs) applications in smart cities, such as vehicular ad hoc networks (VANETs). The WSN supports data exchange between mobile vehicles and servers to provide effective traffic control and smooth service for VANET users. However, the vehicle environment still faces many challenges. One of the VANET concerns is the privacy and security of data flows from heterogeneous systems. Therefore, we suggest a Provably Online/Offline Signcryption (POOSC) protocol for vehicular communication in VANET to preserve data confidentiality and ciphertext unforgeability. In this architecture, the transmitter registered in the Identity-Based Cryptosystems (IBC) environment can safely and efficiently communicate with the receiver in the Public-Key Infrastructure (PKI) environment despite the limitations and challenges of heterogeneous systems. In a Random Oracle Model (ROM), we show that our protocol is safe against Indistinguishability-Adaptive Chosen-Ciphertext Attacks (IND-CCA2) under the Computational Diffie–Hellman (CDH) assumption and Existential Unforgeability-Adaptive Chosen Message Attacks (EUF-CMA) under the Discret-Logarithm (DL) assumption. Moreover, the POOSC protocol overcomes the certificate authority burden. Besides, we designed the POOSC protocol with a free pairing that achieves low computation cost and better scalability for VANET environments. The POOSC effectively meets non-repudiation, integrity, and authentication in a logically single step. [ABSTRACT FROM AUTHOR]

Smart cities can effectively improve urban life quality. But, with the rise in population size, there is an increase in the use of vehicles for transportation. In smart city development, traffic control and route planning are the primary tasks to address the problem of travel time estimation. It has become complex due to concerns of wrapped spatio-temporal data on dynamic real-time traffic conditions. The existing methods failed to estimate travel time efficiently due to not considering the spatio-temporal features and lack of computing resources. There is a need for a system like intelligent transportation system to monitor and accurately predict traffic flow to avoid traffic congestion and reduce the impact on the ecological system. This paper developed a novel hybrid deep learning model to estimate optimized travel time and possible trajectories. In this work, U-Net used to reduce the number of feature points for each temporal data and GNN is used to build the graph with connectivity between vehicular nodes. This hybrid model helps us predict traffic flow and aims to estimate accurate travel time from one location (node) to another. The model's performance is evaluated on the standard benchmark datasets Q-Traffic, TaxiBJ, and Chengdu. The experimental results show that the proposed framework significantly improves performance in extracting travel patterns and provides an optimal route with an estimated travel time than existing methods with RMSE 4%, MAE 20.49%, and MAPE 18%. The proposed model has accurately predicted the estimation of travel time of the vehicle for the given urban traffic data. [ABSTRACT FROM AUTHOR]

As urban areas continue to expand, traffic congestion has emerged as a significant challenge impacting urban governance and economic development. Frequent regional traffic congestion has become a primary factor hindering urban economic growth and social activities, necessitating improved regional traffic management. Addressing regional traffic optimization and control methods based on the characteristics of regional congestion has become a crucial and complex issue in the field of traffic management and control research. This paper focuses on the macroscopic fundamental diagram (MFD) and aims to tackle the control problem without relying on traffic determination information. To address this, we introduce the Q-learning (QL) algorithm in reinforcement learning and the Deep Deterministic Policy Gradient (DDPG) algorithm in deep reinforcement learning. Subsequently, we propose the MFD-QL perimeter control model and the MFD-DDPG perimeter control model. We conduct numerical analysis and simulation experiments to verify the effectiveness of the MFD-QL and MFD-DDPG algorithms. The experimental results show that the algorithms converge rapidly to a stable state and achieve superior control effects in optimizing regional perimeter control. [ABSTRACT FROM AUTHOR]

The rise of surveillance systems has led to exponential growth in collected data, enabling several advances in Deep Learning to exploit them and automate tasks for autonomous systems. Vehicle detection is a crucial task in the fields of Intelligent Vehicle Systems and Intelligent Transport systems, making it possible to control traffic density or detect accidents and potential risks. This paper presents an optimal meta-method that can be applied to any instant segmentation model, such as Mask R-CNN or YOLACT++. Using the initial detections obtained by these models and super-resolution, an optimized re-inference is performed, allowing the detection of elements not identified a priori and improving the quality of the rest of the detections. The direct application of super-resolution is limited because instance segmentation models process images according to a fixed dimension. Therefore, in cases where the super-resolved images exceed this fixed size, the model will rescale them again, thus losing the desired effect. The advantages of this meta-method lie mainly in the fact that it is not required to modify the model architecture or re-train it. Regardless of the size of the images given as input, super-resolved areas that fit the defined dimension of the object segmentation model will be generated. After applying our proposal, experiments show an improvement of up to 8.1% for the YOLACT++ model used in the Jena sequence of the CityScapes dataset. [ABSTRACT FROM AUTHOR]

The emerging technologies of connected and automated vehicles (CAVs) and deep reinforcement learning (DRL) provide innovative methods and have a great potential for developing new solutions to improve the efficiency of several intersection systems. Based on the multisource data collected from the transportation environments, CAVs with the cooperative adaptive cruise control (CACC) system could merge into platoons and traverse the intersection quickly and smoothly. Meanwhile, the traffic information about the CAVs enables intelligent traffic signal controls with the help of DRL technologies. This research investigates the performance of a state-shared multiagent deep reinforcement learning (MADRL) controlled signal corridor with platooning-based CAVs. A corridor with seven intersections from the Ingolstadt Traffic Scenario (InTAS) in Germany is selected as a case study. The state information is shared between neighboring intersections to overcome the partial information observation of the decentralized agents in the MADRL framework. A platooning framework with specific CACC systems for the leading and following vehicles is proposed. Results indicate that the state-shared MADRL with CAV platoons could significantly decrease the total waiting time, average queue length, and total CO2 emission of the corridor by 80%, 73%, and 54%, respectively, which could be beneficial in further improving the intersection efficiency, designing future intersections, and cooperating signals and CAVs platoons. [ABSTRACT FROM AUTHOR]

Accurate assessment of road conditions can effectively alleviate traffic congestion and guide people's travel plans, traffic control decisions of transportation departments, and formulation of traffic-related laws and regulations. This paper proposes a quantum particle swarm optimization (QPSO) and adaptive hybrid exponential smoothing with residual correction (AHES-RC) for the nonlinearity and randomness of traffic flow. In the proposed algorithm, the single–double-exponential smoothing method is mixed with adaptive weights to form AHES, a new method of mixing weights according to real-time traffic trend changes. After the residual correction of AHES is calculated by the extreme learning machine algorithm, the parameters of AHES-RC are optimized using QPSO to improve the prediction accuracy further. This paper comprehensively compares the QPSO-AHES-RC algorithm with other benchmark models through testing on 26 real-world data sets. The results show that the proposed algorithm can adaptive forecasting under various traffic conditions, yielding the best forecasting performance in terms of various forecast error metrics. Compared with advanced machine learning algorithms such as XGBoost and CatBoost, the mean RMSE and mean MAPE have been improved by over 20% on average. In addition, it is revealed that the real-time dynamic capture of traffic flow can effectively improve prediction accuracy. [ABSTRACT FROM AUTHOR]

Increasing congestion levels and their elusive impact warrants the development of congestion mitigation strategies. Quantifying congestion and analyzing the spatiotemporal variations is imperative to achieve this target. Travel time is being explored as a measure of congestion with the advent of Intelligent Transportation Systems (ITS) and the deployment of related technologies. Researchers identified congested conditions when the average travel time exceeds 1.33 or 1.66 times free-flow travel time (FFTT). It is well known that travel time under congested conditions (T c) is more sensitive to land use, road geometry, and traffic control characteristics than the FFTT. Therefore, the extension of FFTT to derive T c may not be appropriate. This study focuses on developing a hazard-based model to derive T c. Travel time is modeled using a parametric accelerated failure time (AFT) model. The applicability of the proposed methodology is justified using empirical and simulated datasets. The T c derived from the AFT model is close to the travel time for the level of service (LOS F). Based on the T c , a new measure of congestion, termed congestion index (CI), is proposed. The proposed index can quantify the frequency and intensity of congestion on a link or network. The traffic states identified based on CI were mapped on the fundamental diagram (FD) and the macroscopic fundamental diagram (MFD). It was concluded that if travel times are uncertain and unstable under low-density conditions, then the ascending leg of the FD or MFD can be marked congested. Uncertain and unstable travel times indicate that traffic flow is unstable, and therefore, it can be concluded that traffic instabilities significantly affect congestion. • A hazard-based duration model is applied to model travel times to derive travel time under congested conditions. • Travel time corresponding to the inflection point of hazard function was considered as travel time under congested conditions. • Instabilities in travel times under low-density conditions mark the ascending leg of the fundamental diagram as congested. • The application of the study is demonstrated by evaluating the effect of traffic signal control. [ABSTRACT FROM AUTHOR]

Microscopic traffic simulation is a powerful tool for studying complex traffic systems when analytical or empirical approaches cannot define response patterns adequately and accurately. The application of simulation techniques for evaluating the characteristics of controlled intersections is effective due to their quick and reliable outcomes. This paper presents a methodology for model development and a unique calibration process for mixed traffic streams using the widely used simulation software Vissim. An isolated signalised intersection was selected for the model development. Most of the calibration methodologies described in previous literature were based on informal practices based on a homogeneous traffic stream. This study frames a novel calibration process suitable for mixed traffic streams. The validity of the proposed methodology was evaluated using field data from another signalised intersection by means of a feasibility comparison of field data and simulation outputs. The calibrated parameters produced suitable simulation outputs, with the measure of effectiveness matching the result obtained from actual field conditions. In contrast, simulations with default or best-guess parameters resulted in significant discrepancies between the observed and simulated outputs. [ABSTRACT FROM AUTHOR]

The technology that can recognize the license plates of vehicles in real time and manage them automatically is a key element of building an intelligent transportation system. License plate recognition is the most important technique in vehicle image processing used to identify a vehicle. Object recognition using a camera is greatly influenced by environmental factors in which the camera is installed. When the vehicle image is acquired, the image is distorted due to the tilting of the license plate, reflection of light, lighting effects, rainy weather, and nighttime, so that it is difficult to accurately recognize the license plate. In addition, when the geometric distortion of the license plate image or the degradation of the image quality is intensified, it may be more difficult to automatically recognize the license plate image. Therefore, in this paper, we propose a deep learning–based vehicles' license plate recognition method to detect license plate and recognize characters accurately in complex and diverse environments. As a deep learning model, the YOLO model can be used to detect robust license plates in a variety of environments and to recognize characters quickly and accurately. It can also be seen that the license plate accurately recognizes the license plate with geometric distortion. [ABSTRACT FROM AUTHOR]

This paper aims to investigate the influence of time delay effect and steady flow control strategy on traffic flow. Consider that the time delay in sensing flux information during the operation of traffic system is inevitable. Meanwhile, a new method is applied to model and analyse traffic system. A novel discrete‐time lattice hydrodynamic model considering time delay is introduced in this paper. Based on the proposed model with constant and varying time‐delay, the asymptotic stabilities are investigated and corresponding stable conditions are derived. The traffic flow evolution trend with and without time delay is conducted and compared by numerical simulations. Also, under the influence of different control gain conditions, density wave characteristics for traffic flow system with time delay are intuitively shown. The results indicate that time delay effect in sensing density and flux information can aggravate traffic congestion, and traffic congestion will be effectively relieved by considering steady flow control signal. [ABSTRACT FROM AUTHOR]

Recently, telesurgery, as a branch of telemedicine, is growing at great speed. In telesurgery, a remote surgeon can communicate with operating room through communication networks in order to perform remote operation. Because human life is at stake in telesurgery, it is necessary to implement appropriate Traffic Engineering (TE) techniques to manage and route telesurgical data traffics over communication networks. Implementing proper TE technique can increase Quality of Experience (QoE) for the remote surgeon, and as a result, it increases the accuracy and performance of telesurgery. In recent years, the advent of Software Defined Network (SDN) has facilitated network providers to develop efficient TE methods to guarantee QoE for their customer applications. In this paper, a novel multi-objective TE technique called SMOTE is proposed to guarantee QoE for telesurgery applications over SDN. The goal of this paper is to enable a network administrator to provide a satisfactory remote operation by providing QoE for the remote surgeon. The objectives, which are considered in our proposed method, are the minimization of end-to-end delay and packet loss. SMOTE uses Non-dominated Sorting Genetic Algorithm (NSGA-II) a well-known multi-objective algorithm, to solve the optimization model for calculating optimal routes between the remote surgeon and the operating room. We conducted comprehensive simulations to evaluate the performance of SMOTE in terms of QoE. Simulation results confirmed that SMOTE guarantees QoE in telesurgery. [ABSTRACT FROM AUTHOR]

• A partial grey prediction model with control matrix (CMPGM(1, M)) is proposed. • The matrices sequence and partial derivatives of mean sequence are used to replace the points sequence. • The novel model can predict traffic flow with better accuracy amongst the comparison models. Short-term traffic flow analysis is the core part of the intelligent transportation system, and also the critical basis for traffic management and control system to guide traffic flow. Real-time and accurate short-term traffic flow prediction can be effectively applied to traffic control and guidance, providing reliable and effective information for traffic managers and travelers, and improving travel efficiency. Based on the spatiotemporal characteristics of traffic flow and periodicity of traffic flow, this paper uses partial differential equation variables to reflect the spatiotemporal characteristics of traffic flow, combines the modelling mechanism of partial differential and the grey prediction model organically, and establishes a partial grey prediction model with control matrix by using the partial derivatives of the mean sequence. At the same time, the parameters estimation and modelling steps of the novel model are obtained by matrix analysis and recursion. A set of data is used from two perspectives to verify the proposed model's effectiveness. Experimental results show that the proposed model is stable and effective. Finally, the novel model is applied to the short-time traffic flow simulation and prediction of the highway. The research results show that the novel model is better than other comparison models. The novel model mainly aims at the matrix data form of traffic flow and is applied to general short-term traffic flow prediction. On the one hand, the prediction results of the novel model can provide theoretical basis and basic methods for the traffic management system, traffic data for traffic information system, and new ideas for the traffic flow prediction research. On the other hand, it can help traffic managers solve accurate real-time traffic flow information, provide real-time traffic information for travelers, and help them plan and adjust routes in advance. [ABSTRACT FROM AUTHOR]

Traffic flow prediction is one of the most important tasks of the Intelligent Transportation Systems (ITSs) for traffic management, and it is also a challenging task affected by many complex factors, such as weather and time. Many cities adopt efficient traffic prediction methods to control traffic congestion. However, most of the existing methods of traffic prediction focus on urban road scenarios, neglecting the complexity of multivariate auxiliary information in highways. Moreover, these methods have difficulty explaining the prediction results based only on the historical traffic flow sequence. To tackle these problems, we propose a novel traffic prediction model, namely Multi-variate and Multi-horizon prediction based on Long Short-Term Memory (MMLSTM). MMLSTM can effectively incorporate auxiliary information, such as weather and time, based on a strategy of multi-horizon time spans to improve the prediction performance. Specifically, we first exploit a multi-horizon bidirectional LSTM model for fusing the multivariate auxiliary information in different time spans. Then, we combine an attention mechanism and multi-layer perceptron to conduct the traffic prediction. Furthermore, we can use the information of multivariate (weather and time) to provide interpretability to manage the model. Comprehensive experiments are conducted on Hangst and Metr-la datasets, and MMLSTM achieves better performance than baselines on traffic prediction tasks. [ABSTRACT FROM AUTHOR]

As technology continues to develop, computer vision (CV) applications are becoming increasingly widespread in the intelligent transportation systems (ITS) context. These applications are developed to improve the efficiency of transportation systems, increase their level of intelligence, and enhance traffic safety. Advances in CV play an important role in solving problems in the fields of traffic monitoring and control, incident detection and management, road usage pricing, and road condition monitoring, among many others, by providing more effective methods. This survey examines CV applications in the literature, the machine learning and deep learning methods used in ITS applications, the applicability of computer vision applications in ITS contexts, the advantages these technologies offer and the difficulties they present, and future research areas and trends, with the goal of increasing the effectiveness, efficiency, and safety level of ITS. The present review, which brings together research from various sources, aims to show how computer vision techniques can help transportation systems to become smarter by presenting a holistic picture of the literature on different CV applications in the ITS context. [ABSTRACT FROM AUTHOR]

Vehicular ad hoc networks (VANETs) are vital to many Intelligent Transportation System (ITS)-enabled technologies, including efficient traffic control, media applications, and encrypted financial transactions. Due to an increase in traffic, vehicular network topology is constantly changing, and sparse vehicle distribution (on highways) hinders network scalability. Thus, there is a challenge for all vehicles (in the network) to maintain a stable route, which would increase network instability. Concerning IoT-based network transportation, this study proposes a bio-inspired, cluster-based algorithm for routing, i.e., the intelligent, probability-based, and nature-inspired whale optimization algorithm (p-WOA), which produces cluster formation in vehicular communication. Various parameters, such as communication range, number of nodes, velocity, and route along the highway were considered, and their probaabilities were incorporated into the fitness function, hence resulting in randomness reduction. Results were compared to existing methods such as Ant Lion Optimizer (ALO) and Grey Wolf Optimization (GWO), demonstrating that the developed p-WOA technique produces an optimal number of cluster heads (CH). The results achieved by calculating the Packet Delivery Ratio (PDR), average throughput, and latency demonstrate the superiority of the proposed method over other well-established methodologies (ALO and GWO). This study confirms statistically that VANETs employing ITS applications optimize their clusters by a factor of 75, which has the twin benefits of decreasing communication costs and routing overhead and extending the life of the cluster as a whole. [ABSTRACT FROM AUTHOR]

Vehicle classification is a crucial task owing to vehicles' diverse and intricate features, such as edges, colors, shadows, corners, and textures. The accurate classification of vehicles enables their detection and identification on roads and facilitates the development of an electronic tollcollection system for smart cities. Furthermore, vehicle classification is useful for traffic signal control strategy. However, achieving accurate vehicle classification poses significant challenges due to the limited processing time for real-time applications, image resolution, illumination variations in the video, and other interferences. This study proposes a method for automated automobile detection, recognition, and classification using statistics derived from approximately 11,000 images. We employ SURF-based detection and different classifiers to categorize vehicles into three groups. The Traffic Management System (TMS) is crucial for studying mobility and smart cities. Our study achieves a high automobile classification rate of 91% with the medium Gaussian Support Vector Machine (SVM) classifier. The paper's main objective is to analyze five object classifiers for vehicle recognition: Decision Tree, Discriminant Analysis, SVM, K-Nearest Neighbor Classifier (KNN), and Ensemble Classifier. In the discussion section, we present the limitations of our work and provide insights into future research directions. [ABSTRACT FROM AUTHOR]

Developing transportation systems (TSs) under the structure of a wireless sensor network (WSN) along with great preponderance can be an Achilles' heel from the standpoint of cyber-attacks, which is worthy of attention. Hence, a crucial security concern facing WSNs embedded in electrical vehicles (EVs) is malware attacks. With this in mind, this paper addressed a cyber-detection method based on the offense–defense game model to ward off malware attacks on smart EVs developed by a wireless sensor for receiving data in order to control the traffic flow within TSs. This method is inspired by the integrated Nash equilibrium result in the game and can detect the probability of launching malware into the WSN-based EV technology. For effective realization, modeling the malware attacks in conformity with EVs was discussed. This type of attack can inflict untraceable detriments on TSs by moving EVs out of their optimal paths for which the EVs' power consumption tends toward ascending thanks to the increasing traffic flow density. In view of this, the present paper proposed an effective traffic-flow density-based dynamic model for EVs within transportation systems. Additionally, on account of the uncertain power consumption of EVs, an uncertainty-based UT function was presented to model its effects on the traffic flow. It was inferred from the results that there is a relationship between the power consumption and traffic flow for the existence of malware attacks. Additionally, the results revealed the importance of repressing malware attacks on TSs. [ABSTRACT FROM AUTHOR]

This article discusses recent developments in the area of interoperable Internet of Things, using an example of delivering data-driven transportation services. Initial results obtained by exploiting heterogeneous traffic data streams reveal interesting traffic patterns for different vehicle types. [ABSTRACT FROM AUTHOR]

Variable speed limit control (VSLC) is one of the services from the domain of intelligent transport systems applied to alleviate or prevent congestion on urban motorways. The main idea of VSLC is to change the speed limit according to current traffic or weather in order to improve the traffic situation. Improvement of the traffic situation on urban motorways depends on the applied controller and its parameters. For this reason, the controllers chosen for implementation have to be tested in simulations using a realistic urban motorway segment, placement of sensors and traffic scenario, and a relevant set of control parameters. An analysis of two VSLC controllers, including the influence of their parameters on controller performance with respect to traffic and environmental aspects, is presented in this paper. To this end, an appropriate microscopic simulation framework was developed, the fundamental diagram of a simulated synthetic urban motorway segment was measured and traffic parameters, with vehicle emissions values, were obtained. The effectiveness of the two analysed controllers was compared based on the obtained simulation results. The results revealed that appropriate settings of the controller are crucial to ensure optimal use of urban motorways with minimum travel times and vehicle emissions. [ABSTRACT FROM AUTHOR]

The intelligent transportation system (ITS) has been proven capable of effectively addressing traffic congestion issues. For vehicles to perform effectively and improve mobility under the intelligent driving environment, real-time prediction of traffic speed is undoubtedly essential. Considering the complex spatiotemporal dependency inherent in traffic data, conventional prediction models encounter many limitations. To improve the prediction performance and investigate the temporal features, this study focuses on emerging deep neural networks (DNNs) using the Caltrans Performance Measurement System (PeMS) data. This research also establishes an intelligent driving environment in the simulation and compares the traditional car-following model with deep learning methods in terms of multiple performance metrics. The results indicate that both supervised learning and unsupervised learning are superior to the simulation-based model on the freeway, and the two deep learning networks are almost identical to one another. Besides, the result reveals that all models have their latent features for different time dimensions under the low traffic loads, transition states, and heavy traffic loads. This is critical in the application of prediction technologies in ITS. The findings can assist transportation researchers and traffic engineers in both traffic operation and management, such as bottleneck identification, platooning control, and route planning. [ABSTRACT FROM AUTHOR]

Summary: Miniaturization of Internet of Things (IoT) enabled devices has led to advancement in Intelligent Transportation System. Some of the challenges for efficient traffic management are connection of vehicles through an IP based infrastructure for transportation, reliable, and flexible traffic control management, maintaining quality of services for video streaming applications in Internet of Vehicles and many more. Today there is a need of an efficient transportation system with improved efficiency of traffic safety and lower traveling costs. An intelligent traffic control system using Ant Colony Optimization (ACO) algorithm has been proposed and analyzed in this paper. Proposed algorithm has been compared with existing state of art algorithms in terms of average waiting time and average traveling time. [ABSTRACT FROM AUTHOR]

Traffic congestion alleviation around intersections has been a growing challenge, and a competent traffic signal control scheme plays a pivotal role in intelligent transportation systems. Recent studies using deep reinforcement learning techniques have shown promising results for traffic signal control, but they only focus on extracting features from traffic conditions of isolated or adjacent intersections. In this work, we employed navigation information for traffic signal control, greatly enriching the features for traffic signal control with deep reinforcement learning. In addition, we are the first to propose a novel scheme DeepNavi to exploit the temporal-spatial relations from numerous navigation routes and extract dynamic real-time and future traffic features. We tested our scheme on a challenging real-world traffic dataset with 16 intersections in a residential district of Hangzhou, China. Extensive experiments were conducted and the results demonstrated that our DeepNavi scheme achieves superior performance over five popular and state-of-the-art baseline methods on different metrics, including queue length, speed, travel time and accumulative waiting time. In addition, with our method, vehicles suffer the least red lights and enjoy the most green waves, which further validates that our scheme greatly relieves the congestion and provides excellent experience for drivers. Simulations with different penetration levels of navigation routes showed that even with only part of navigation routes available in the traffic network, our scheme can obtain superior performance, further demonstrating the effectiveness and feasibility of DeepNavi. [ABSTRACT FROM AUTHOR]

With the steadily growing traffic demand, urban traffic congestion is becoming a critical issue threatening several factors, including public safety, emissions of greenhouse gas, and transport inefficiencies. Thus, intelligent transport systems (ITS) have emerged as a promising solution to easing the burden of congestion. ITS rely on different technologies such as VANET (Vehicular Adhoc Networks) which provide the transportation system with ubiquitous connectivity allowing the exchange of traffic information between vehicles and roadside terminals. This can support numerous smart mobility applications such as traffic signal control and real-time traffic management. Hence, mobility models were developed to emulate and forecast the distribution of traffic which will be helpful to the design and management of traffic control strategies. In this context, this study specifically concentrates on developing a mobility model that reflects vehicular activities in urban environments based on vehicular information collected using vehicular communications. The behavior of vehicles along multi-lane roads and intersections is modeled as a stochastic process using queuing theory. Particularly, the queue system is analyzed as a continuous-time Markov chain (CTMC) and by calculating the steady-state probabilities, different performance measures are derived and analyzed under various scenarios. To validate the model, the obtained forecasts are compared with a queue model and realistic traces. The results show that the model is capable of reproducing the realistic behavior of traffic in urban roads without incurring heavy costs and time-consuming computing. The obtained estimates were then used to design an actuated traffic light and a vehicle speed adaptor. From the simulation results, it is clear that using the proposed traffic forecasting model helps reduce vehicles idling and travel times. • Using real-time traffic data collected via V2X increases prediction accuracy. • Markov chains allow realistic, fast and efficient urban traffic prediction. • CTMC traffic model shows better prediction accuracy compared to basic queue models. • Traffic prediction improves the performance of traffic-aware ITS applications. [ABSTRACT FROM AUTHOR]

In recent years, the growing development of Connected Autonomous Vehicles (CAV), Intelligent Transport Systems (ITS), and 5G communication networks have led to the advent of Autonomous Intersection Management (AIM) systems. AIMs present a new paradigm for CAV control in future cities, taking control of CAVs in scenarios where cooperation is necessary and allowing safe and efficient traffic flows, eliminating traffic signals. So far, the development of AIM algorithms has been based on basic control algorithms, without the ability to adapt or keep learning new situations. To solve this, in this paper we present a new advanced AIM approach based on end-to-end Multi-Agent Deep Reinforcement Learning (MADRL) and trained using Curriculum through Self-Play, called advanced Reinforced AIM (adv.RAIM). adv.RAIM enables the control of CAVs at intersections in a collaborative way, autonomously learning complex real-life traffic dynamics. In addition, adv.RAIM provides a new way to build smarter AIMs capable of proactively controlling CAVs in other highly complex scenarios. Results show remarkable improvements when compared to traffic light control techniques (reducing travel time by 59% or reducing time lost due to congestion by 95%), as well as outperforming other recently proposed AIMs (reducing waiting time by 56%), highlighting the advantages of using MADRL. [ABSTRACT FROM AUTHOR]

Traffic prediction is the key for Intelligent Transport Systems (ITS) to achieve traffic control and traffic guidance, and the key challenge is that traffic flow has complex spatial-temporal dependence and nonlinear dynamics. Aiming at the lack of the ability to model complex and dynamic spatial-temporal dependencies in current research, this paper proposes a traffic flow prediction model Attention based Graph Convolution Network (GCN) and Transformer (AGCN-T) to model spatial-temporal network dynamics of traffic flow, which can extract dynamic spatial dependence and long-distance temporal dependence to improve the accuracy of multistep traffic prediction. AGCN-T consists of three modules. In the spatial dependency extraction module, according to the similarity of historical traffic flow sequences of different loop detectors, an adjacency matrix for the road network is constructed based on a sequence similarity calculation method, Predictive Power Score (PPS), to express latent spatial dependency; and then GCN is used on the adjacency matrix to capture the global spatial correlation and Transformer is used to capture dynamic spatial dependency from the most recently flow sequences. And then, the dynamic spatial dependency is merged with the global spatial correlation to obtain the overall spatial dependency pattern. In the temporal dependency extraction module, the temporal dependency pattern of each traffic flow sequence is learned by the temporal Transformer. The prediction module integrates both patterns to form spatial-temporal dependency patterns and performs multistep traffic flow prediction. Four sets of experiments are performed on three actual traffic datasets to show that AGCN-T can effectively capture the dynamic spatial-temporal dependency of the traffic network, and its prediction performance and efficiency are better than existing baselines. AGCN-T can effectively capture the dynamics in traffic flow. In addition to traffic flow prediction, it can also be applied to other spatial-temporal prediction tasks, such as passenger demand prediction and crowd flow prediction. [ABSTRACT FROM AUTHOR]

With the acceleration of urbanization and the development of the automobile industry, the contradiction between the traffic capacity of existing urban roads and the growing traffic demand has become increasingly acute. Traffic congestion is becoming increasingly prominent. The purpose of this article is to consider the characteristics of traffic risk factors and to study the method of establishing a flexible traffic system. It can relieve traffic congestion and provide a smooth and orderly traffic environment using intelligent transportation systems to control and direct traffic flow. Based on the large urban road network, this research uses the theory of coordinated control and learning mechanism, fuzzy control, dynamic reprogramming, and other theories to study phase sequence, balance peripheral load, and overall traffic flow. It also uses on-board sensors to optimize the collection and processing of network information, decompose traffic guidance work, select the optimal route, and autonomously guide the intelligent transportation system. Under the flexible demand scheme, the average load of the trunk road is reduced by a larger degree, which is 4% lower than that of the fixed demand scheme. At the same time, the average load of the branch has increased more, which is 4% higher than that of the fixed demand scheme. It can be seen that under the elastic demand scheme, the distribution of traffic flow in the road network is more balanced and the optimization effect of relieving traffic pressure on trunk roads and improving the utilization rate of branch roads is more significant. [ABSTRACT FROM AUTHOR]

Traffic volume data are the important part of research and application of intelligent transportation systems (ITS). However, data loss often happens due to various factors in the real world, which may cause large deviations in prediction or bad accuracy of optimizations. Imputation is a valid way to handle missing values. A multilayer perceptron-multivariate imputation of chain equation (MLP-MICE) regression imputation method optimized by the limit-memory-BFGS algorithm is proposed, considering the temporal and spatial characteristics of traffic volume. Also, 32 groups of simulated imputation experiments based on the detected traffic volume of road sections in the Guangdong freeway system are conducted, which take the scenarios of continuous missing and jumped missing into account. The results of the experiments show that the MLP-MICE can optimize the imputation performance in the missing value of traffic volume with the MAPE of imputation results from 6.38% to 30%. Meanwhile, the proposed model has higher imputation accuracy for the traffic volume data with a lower degree of mutation. Lastly, the performance of the proposed model of imputation in short-term traffic volume prediction is discussed using the support vector machine. The results of it show that the MAPE of prediction under the proposed model is much lower than all-zero imputation. Therefore, the proposed model in this study is positive on improving the accuracy of traffic volume prediction and intelligent traffic control and management. [ABSTRACT FROM AUTHOR]

Research explored VDC (vehicle detections) and compared the current classifier to new design classifiers like RTM (real-time traffic flow monitoring). It has considerable financial value, but it is also an important tool for maintaining public safety. In view of the current situation, where the accuracy of existing traffic flow statistics algorithms is poor and it is easy to generate false detections, a multi-lane traffic flow statistics algorithm based on a novel design classifier is proposed. Our suggested framework includes input data type, vehicle type, scale, scope, dynamicity, vehicle detection method, vehicle classification method, application, and assessment method. Following that, we use the offered framework to investigate the history of VDC approaches and highlight several open challenges that have evolved in the field. This article is intended to serve as a guide for researchers who want to utilize or build dependable VDC systems that satisfy their needs. [ABSTRACT FROM AUTHOR]

In the last decades, the Italian road transport system has been characterized by severe and consistent traffic congestion and in particular Rome is one of the Italian cities most affected by this problem. In this study, a Leven berg Marquardt (LM) artificial neural network heuristic model was used to predict the traffic flow of non-autonomous vehicles. Traffic datasets were collected using both inductive loop detectors and video cameras as acquisition systems and selecting some parameters including vehicle speed, time of day, traffic volume and number of vehicles. The model showed a training, test and regression value (R² ) of 0.99892, 0.99615 and 0.99714 respectively. The results of this research add to the growing body of literature on traffic flow modelling and help urban planners and traffic managers in terms of the traffic control and the provision of convenient travel routes for pedestrians and motorists. [ABSTRACT FROM AUTHOR]

The autonomous vehicles emergence is a significant step forward in the development of safe and dependable intelligent transportation systems. In vehicular automation, digital connectivity has been one of the most critical specifications. In this paper, we focus on the autonomous train, which is one of the most rapidly growing applications of autonomous vehicles. In this context, we address the issue of safety by the proposition of Enhanced Train-centric Communication-Based Train Control (ETcCBTC), which provides efficient control of rail traffic. To ensure the operation's safety, we've implemented a new safety-checking approach based on process algebra, which aims to track and correct in real time the train behavior. The proposed ETcCBTC system's performance is tested using extensive simulations and compared to CBTC and TcCBTC. In terms of checking success, transmission load, and response time, the obtained results demonstrate that ETcCBTC outperforms the concurrent systems. [ABSTRACT FROM AUTHOR]

Improving the efficiency of traffic signal control is an effective way to alleviate traffic congestion at signalized intersections. To achieve effective management of the system-wide traffic flows, current research tends to focus on applying reinforcement learning (RL) techniques for collaborative traffic signal control in a traffic road network. However, the existing collaboration-based methods often ignore the impact of transmission delay for exchanging traffic flow information on the system. Most of the studies assume that the signal controllers can collect all instantaneous vehicular features without delay. To fill the gap, we propose an RL-based cooperative traffic signal control scheme considering the data transmission delay issue in a traffic road network. In this paper, we (1) design our new RL agents to cooperatively control the traffic signals by improving the reward and state representation based on the state-of-the-art max-pressure control theory; (2) propose a traffic state prediction method to address the data transmission delay issue by decreasing the discrepancy between the real-time and delayed traffic conditions; (3) evaluated the performance of our proposed work on both synthetic and real-world scenarios with a different range of data transmission delays. The results demonstrate that our method surpassed the performance of the previous max-pressure-based traffic signal control methods and addressed the data transmission delay issue. [ABSTRACT FROM AUTHOR]

Understanding the resilience of transportation networks has received considerable research attention. Nevertheless in the field of network traffic flow control, few control approaches target the mitigation from hyper-congestion, and the control objective has rarely touched the system resilience requirement which focuses on system recovering from hyper-congested state. This paper sheds light on a resilience-oriented network control. We firstly define the traffic resilience as the integral of deviation against optimal state from disturbance generation moment t 0 to recovery moment t f. Then, we propose a control method under hyper-congested situations by formulating the analytical problem using a two-reservoir transportation system with parabola-shaped Macroscopic Fundamental Diagrams (MFDs), using phase diagram analysis, attraction region derivation and switched controller design. Afterwards, we evaluate the system resilience performances between two classic perimeter control schemes (constant perimeter control (CPC) and state-feedback control (SFC)) and the proposed resilient control scheme. Results show that proposed controller can ensure the system to recover from hyper-congestion to the optimal state while existing studies failed to recover. This resilience is confirmed in various case study scenarios, e.g., when the level of hyper-congestion is different. More promisingly, the proposed control shows high compatibility with the form of the MFDs, e.g., the recover can be achieved under hysteresis conditions which are common for network-level traffic dynamics. These findings will help to design an intelligent transportation system with enhanced resilience. • We propose a traffic resilience measure as a control objective. • We propose a resilient control method to recover system to the optimal state from hyper-congestion. • We extend our methodology to two typical scenarios where the shape of the MFD changes under disruptions. [ABSTRACT FROM AUTHOR]

Concerning the critical role of Intelligent Transportation System (ITS) in tackling the problem of traffic congestion, and enhancing the safety, mobility and sustainability of the transport network, this paper provides a comprehensive review of recent developments in Connected Vehicle (CV) technology, its features and terminology. The real-world implementation of the CV technologies can result in a better understanding of the practical and technical issues. Given the technical and conceptual challenges, as well as novelty factors associated with CVs, many CV pilot studies around the world are reviewed, and their findings are summarized. The paper contributes to the literature by reviewing the characteristics, communication platform, multimodality, size and type of study areas of the pilot CV testbeds across the world. This research also paves the way for the better development of CV technology by comparing and discussing the pros and cons of the existing CV pilot testbeds. Moreover, we have discussed the evaluation plans and the advantages and disadvantages of different testbeds. Besides, as a main component of the CV system, the traffic signal control algorithms, as well as transit signal priority in a CV ecosystem, are also reviewed. Based on our findings, the real-time data obtained from the CV system could result in a better adjustment of traffic signal parameters which consequently enhance the traffic regulation in the network (say up to 30% in terms of travel time in comparison with an actuated coordinated traffic signal). However, a major criticism of the existing traffic signal strategies in a CV system is that they do not utilize the maximum capability of the CV system (V2 V, V2I and I2I communications). [ABSTRACT FROM AUTHOR]

Intelligent Transportation Systems (ITS) face the formidable challenge of large-scale missing data, particularly in the imputation of traffic data. Existing studies have mainly relied on modeling network-level spatiotemporal correlations to address this issue. However, these methods often overlook the rich semantic information (e.g., road infrastructure, sensor location, etc.) inherent in road networks when capturing network-wide spatiotemporal correlations. We address this limitation by presenting the Graph Transformer-based Traffic Data Imputation (GT-TDI) model, which imputes missing values in extensive traffic data by leveraging spatiotemporal semantic understanding of road networks. The proposed model leverages semantic descriptions that capture the spatial and temporal dynamics of traffic across road networks, enhancing its capacity to infer comprehensive spatiotemporal relationships. Moreover, to augment the model's capabilities, we employ a Large Language Model (LLM) and prompt engineering to enable natural and intuitive interactions with the traffic data imputation system, allowing users to query and request in plain language, without requiring expert knowledge or complex mathematical models. The proposed model, GT-TDI, utilizes Graph Neural Networks (GNN) and Transformer architectures to perform large-scale traffic data imputation using deficient observations, sensor social connectivity, and semantic descriptions as inputs. We evaluate the GT-TDI model on the PeMS freeway dataset and benchmark it against cutting-edge models. The experimental evidence demonstrates that GT-TDI surpasses the cutting-edge approaches in scenarios with intricate patterns and varying rates of missing data. • A novel semantic description for traffic data imputation that captures spatiotemporal correlations flexibly. • A pioneering application of prompt engineering to ITS that bridges the gap between LLMs and ITS. • The proposed model leverages LLMs and semantic prompts for traffic data imputation. • Extensive experiments on real-world traffic data show the superiority. • A potential framework for integrating LLMs and semantic prompts into other ITS tasks. [ABSTRACT FROM AUTHOR]

Effective traffic control methods have great potential in alleviating network congestion. Particularly, in an urban network consisting of heterogeneous roads (e.g., freeways and urban roads), how to integrate and coordinate control policies on different roads is a critical issue in large-scale networks. This study addresses this question from two aspects: modeling and control. From the modeling aspect, we formulate the hybrid traffic modeling in heterogeneous networks with the Asymmetric Cell Transmission Model (ACTM) for freeways and the generalized bathtub model for urban roads. For the control aspect, this study considers two representative control approaches: ramp metering for freeways and perimeter control for urban roads, and we aim to develop a deep reinforcement learning (DRL)-based coordinated control framework for large-scale networks. However, there are two significant challenges in the coordinated control in large-scale networks with DRL methods: non-stationary environment and large search space. To address both issues, we incorporate the demonstration to guide the DRL method for better convergence by introducing the concept of "teacher" and "student" models. The teacher models are traditional controllers that provide control demonstrations. For instance, ALINEA and Gating are two representative feedback controllers for ramp metering and perimeter control which can be "teacher" models. The student models are DRL methods, which learn from teachers and aim to surpass the teachers' performance. Additionally, we develop a parallel training scheme to accelerate the proposed DRL method. To validate the proposed framework, we conduct two case studies in a small-scale network and a real-world large-scale traffic network in Hong Kong. Numerical results show that the proposed DRL method outperforms demonstrators as well as DRL methods, and the coordinated control is more effective than just controlling ramps or perimeters respectively. The research outcome reveals the great potential of combining traditional controllers with DRL for coordinated control in large-scale networks. • A generalized hybrid traffic model supporting simulation in large-scale networks. • A novel demonstration-guided DRL method for coordinated traffic control. • A parallel training scheme for DRL methods. • The proposed DRL method is examined in real networks in Hong Kong SAR. [ABSTRACT FROM AUTHOR]

Traffic flow forecasting (TFF) is critical for constructing intelligent transportation systems and offering real-time traffic applications, and especially accurate flow forecasting based on traffic big data can drive reliable strategies for traffic management and control. To consider the weight of the influence of the spatial correlation among the road segments and capture the nonlinear characteristics of traffic flow, this paper presents a parallel Normal Distribution and Attention Mechanism Weighted Deep Bidirectional Long Short-Term Memory (NAW-DBLSTM) algorithm on Spark. Specifically, we employ the resilient distributed data set (RDD) to preprocess large-scale mobile trajectory data (e.g., taxi GPS trajectory data), and then Kalman Filter (KF) is utilized to smooth the taxi trajectory big data. Next, the parallel NAW-DBLSTM algorithm is put forward on a Spark distributed computing platform to enhance the accuracy and scalability of TFF, combined with the attention mechanism and the normal distribution, and then the time window is used for TFF. Finally, the traffic flow is forecasted successfully on Spark by our NAW-DBLSTM algorithm with the real-world GPS trajectories of taxicabs. The experimental results demonstrate that, compared with LSTM, BiLSTM, DBLSTM, DNN, SVR, KNN, SAEs, BP, CNN, GRU, and ANNs, NAW-DBLSTM can produce better performance with the MAPE value that is 85.1%, 80.1%, 85.8%, 73.1%, 78.2%, 77.9%, 78.8%, 84.6%, 96.4%, 86.2%, and 73.2% lower than that of comparable algorithms, respectively. Particularly, the MAPE value of NAW-DBLSTM is 28.3%, 20.1%, 71.1%, and 79.1% lower than that of LSTM weighted with the normal distribution and the attention mechanism (NAW-LSTM), BiLSTM weighted with the normal distribution and the attention mechanism (NAW-BiLSTM), DBLSTM weighted with the normal distribution (NW-DBLSTM), and NAW-DBLSTM weighted without the time window (NT-NAW-DBLSTM), respectively. [ABSTRACT FROM AUTHOR]

Traffic flow forecasting is the key to an intelligent transportation system (ITS). Currently, the short-term traffic flow forecasting methods based on deep learning need to be further improved in terms of accuracy and computational efficiency. Therefore, a short-term traffic flow forecasting model GA-TCN based on genetic algorithm (GA) optimized time convolutional neural network (TCN) is proposed in this paper. The prediction error was considered as the fitness value and the genetic algorithm was used to optimize the filters, kernel size, batch size, and dilations hyperparameters of the temporal convolutional neural network to determine the optimal fitness prediction model. Finally, the model was tested using the public dataset PEMS. The results showed that the average absolute error of the proposed GA-TCN decreased by 34.09%, 22.42%, and 26.33% compared with LSTM, GRU, and TCN in working days, while the average absolute error of the GA-TCN decreased by 24.42%, 2.33%, and 3.92% in weekend days, respectively. The results indicate that the model proposed in this paper has a better adaptability and higher prediction accuracy in short-term traffic flow forecasting compared with the existing models. The proposed model can provide important support for the formulation of a dynamic traffic control scheme. [ABSTRACT FROM AUTHOR]

An understanding of the change in follower behaviour as a driver characteristic in traffic simulations is necessary because these behavioural changes are frequently observed in traffic oscillations. The change in follower behaviour due to traffic acceleration and deceleration waves can be classified according to different behavioural patterns resulting from different driver reactions. Combinations of existing behavioural patterns (under-reaction–timid, over-reaction–timid and constant over-reaction–timid patterns) were thus analysed. The method of analysis was based on an artificial neural network model at the microscopic level in order to simulate the extent to which follower behaviour deviates from Newell's car-following model. The most influential parameters of all the behavioural patterns were determined. Based on the under-reaction–timid pattern, decreasing the reaction speed resulted in a change in behaviour due to the development of safe spacing at the reaction point. In addition, follower spacing was the most influential in the over-reaction–timid pattern, resulting in increasing and then decreasing behavioural change. In the constant over-reaction–timid pattern, the follower's speed resulted in increasing and then decreasing the change in behaviour. The application of behavioural change to an intelligent transportation system would improve safety. [ABSTRACT FROM AUTHOR]

The concept of searching and localizing vehicles fromlive traffic videos based on descriptive textual input has yet to be explored in the scholarly literature. Endowing Intelligent Transportation Systems (ITS) with such a capability could help solve crimes on roadways. One major impediment to the advancement of fine-grain vehicle recognition models is the lack of video testbench datasets with annotated ground truth data. Additionally, to the best of our knowledge, no metrics currently exist for evaluating the robustness and performance efficiency of a vehicle recognition model on live videos and even less so for vehicle search and localization models. In this paper, we address these challenges by proposing V-Localize, a novel artificial intelligence framework for vehicle search and continuous localization captured from live traffic videos based on input textual descriptions. An efficient hashgraph algorithm is introduced to compute valid target information from textual input. This work further introduces two novel datasets to advance AI research in these challenging areas. These datasets include (a) the most diverse and large-scale Vehicle Color Recognition (VCoR) dataset with 15 color classes--twice as many as the number of color classes in the largest existing such dataset--to facilitate finer-grain recognition with color information; and (b) a Vehicle Recognition in Video (VRiV) dataset, a first of its kind video testbench dataset for evaluating the performance of vehicle recognition models in live videos rather than still image data. The VRiV dataset will open new avenues for AI researchers to investigate innovative approaches that were previously intractable due to the lack of annotated traffic vehicle recognition video testbench dataset. Finally, to address the gap in the field, five novel metrics are introduced in this paper for adequately accessing the performance of vehicle recognition models in live videos. Ultimately, the proposed metrics could also prove intuitively effective at quantitative model evaluation in other video recognition applications. T One major advantage of the proposed vehicle search and continuous localization framework is that it could be integrated in ITS software solution to aid law enforcement, especially in critical cases such as of amber alerts or hit-and-run incidents. [ABSTRACT FROM AUTHOR]

In current practice, hardware-in-the-loop simulation and software-in-the-loop simulation are two typical methods for traffic signal control research. The former uses a controller interface device (CID) to connect an actual traffic signal controller to micro-simulation software when conducting a simulation, whereas the latter uses software packages to take the roles of actual signal controllers. Using an actual signal controller can help to generate more reliable simulation results; however, the operational costs of CIDs limit the applicability of hardware-in-the-loop simulations. In this paper, a virtual controller interface device (VCID) is proposed to connect the actual signal controllers to simulation software. The proposed device communicates with the actual signal controller through the US national transportation communications for intelligent transportation systems protocol (NTCIP), which provides great operation flexibility, such as remote control, and reduces the operating costs compared with previous hardware-in-the-loop simulations. The simulation performance of the VCID is compared with software-in-the-loop simulations through a case study in this paper. It is found that the proposed device is able to provide accurate and reliable traffic simulation results: the relative difference with software-in-the-loop simulations is only 1·8%, but it requires significantly less effort and has a lower cost. [ABSTRACT FROM AUTHOR]

A co-operative driving system for road junctions is an example of a vehicle cyber–physical system. It integrates the cyber systems in vehicles with their physical systems to optimise co-operative driving at traffic intersections. Depending on 'vehicle-to-everything' technology, the system can facilitate co-operation between moving vehicles and traffic control systems, improve traffic operation and management, and help vehicles negotiate junctions safely and efficiently. To optimise the system, an improved membrane-computing-based multi-vehicle optimisation method is proposed in this paper. The method is a potential solution to the multi-vehicle optimisation problem with constrained conditions and incommensurable objectives. It can better guarantee the safety of multiple moving vehicles at a junction than several traditional multi-objective optimisation methods. Experimental analyses show how the method can reduce delays at junctions, increase junction throughput and shorten overall journey times. [ABSTRACT FROM AUTHOR]

The quest for self-driving networks poses growing pressure to manage network events at a nano-second scale. In this article, we make a case for leveraging programmable forwarding planes to achieve self-driving networks and respond to their dynamism in real time by in-network intelligence and without performing traffic steering/mirroring to centralized management solutions (intelligent or not). We briefly cover throughout the article preliminary ideas in the in-network neural networks field and discuss the technical challenges of running machine learning techniques entirely in the forwarding plane. We also highlight potential use cases of having an autonomous intelligent network capable of self-adapting to dynamic network behavior changes with minimal to no human intervention, including smart network telemetry, smart traffic engineering, real-time flow classification, and network tomography. We close with a roadmap of research opportunities enabled by distributed in-network intelligence in programma-ble forwarding planes. [ABSTRACT FROM AUTHOR]

Urban traffic control has become a big issue to help traffic management in recent years. With data explosion, Intelligent Transportation System (ITS) is developing rapidly. ITS is an advanced data-based method for traffic control, which requires timely and effective information supply. This research aims at providing real-time and accurate traffic flow data by intelligent prediction method. Applying multiple road traffic flow data of the Caltrans Performance Measurement System (PeMS) and separating the time series, the mechanism of spatial-temporal differences was taken into consideration. Based on the basic Long Short-Term Memory (LSTM) model, an improved LSTM model with Dropout and Bi-structure (Bi-LSTM) for traffic flow prediction was presented. In the prediction process, we applied three models including the improved Bi-LSTM model, Gated Recurrent Unit (GRU) model and Linear Regression in the experiment, and made a comparison from aspects of model structure complexity, operating efficiency and prediction accuracy. To validate the portability of the prediction model, the features of traffic flow from different datasets were further analyzed. The experimental results show that the improved Bi-LSTM model performs best in traffic flow prediction with comprehensive rationality, which reaches an accuracy of about 92% when considering temporal differences. Particularly, the specific factors of traffic situations and locations which is more applicable to be predicted by the improved Bi-LSTM model are summarized considering spatial differences. This research proposes an advanced and accurate model to provide real-time and short-term traffic flow prediction data, which is of great help to intelligent traffic control. Considering the mechanism between model and road traffic properties, the results suggest that it is more applicable in urban commercial area. [ABSTRACT FROM AUTHOR]

Light detection and ranging (LiDAR) technology is a key component of an autonomous vehicle’s sensing system. It also has the potential to be used at the roadside as a major infrastructure-based detection for connected and autonomous traffic infrastructure systems, as well as for the general purpose of traffic data collection and performance evaluation. Lane and movement-based traffic volume data collection is a basic function of roadside traffic sensing systems. The accuracy of volume detection is mainly impacted by occlusion for most of the advanced traffic sensing technologies, such as LiDAR, video, and radar. This paper presents research results to quantify the influence of occlusion on LiDAR systems’ traffic volume detection in different traffic demand scenarios. A method for automatic identification and classification of LiDAR specific occlusion was first developed based on the inherent characteristics of LiDAR sensors, which can report occlusion ratios of roadside LiDAR data. Then, the study was extended to accommodate all traffic demand scenarios, traffic levels of service (LOS A to E), and different truck compositions (5% to 30%) by integrating the developed method and traffic simulation. Lastly, a comprehensive case study first verified the accuracy of the simulation results using field data collected from two testbeds, and then at the third testbed, a lane and movement-based traffic volume study was demonstrated. The practical significance of this paper is to help traffic engineers making informed decisions when considering LiDAR as their choice of sensing technology in the field from two aspects: (1) the quantitative relationship between expected occlusion rate and resulted detection accuracy under various traffic conditions; (2) lessons learned from the pilot field implementation on LiDAR, installation strategy, data storage, and communication. [ABSTRACT FROM AUTHOR]

In the era of internet of vehicles, both the traffic signal control and the rerouting of connected and autonomous vehicles (CAVs) are essential techniques to alleviate traffic congestion and improve traffic efficiency. However, these two schemes have been treated separately without a unified framework allowing for joint optimization in the previous studies. In the case of traffic congestion at the bottleneck intersections, either of the two schemes alone is not enough. To this end, we propose to jointly control the traffic lights and the CAVs under the reinforcement learning (RL) framework. To lower the dimensionality of this learning problem, we propose to control the route choices of the CAVs through a few common scalar parameters instead of controlling the CAVs individually. In particular, the rerouting ratios are dynamically adjusted. A model-based method is further proposed to estimate the expected travel time with reduced estimation error. We then exploit the tools from deep RL and put forth an efficient algorithm that is able to control the green time allocation of traffic signals and the rerouting of CAVs jointly. Comprehensive numerical experiments demonstrate the validity of our proposed models and show the traffic efficiency can be significantly improved with our proposed algorithm. [ABSTRACT FROM AUTHOR]