Search

An automatic vehicle classification (AVC) system designed from either still images or videos has the potential to bring significant benefits to the development of a traffic control system. On AVC, numerous articles have been published in the literature. Over the years, researchers in this domain have created and used a variety of datasets, but most often, these datasets may not reflect the exact scenarios of the Indian subcontinent due to specific peculiarities of the road conditions, road congestion nature, and vehicle types usually seen in Indian subcontinent. The primary goal of this paper is to create a new still image dataset, called JUIVCDv1, which contains 12 different local vehicle classes that are collected using mobile cameras in a different way for developing an automated vehicle management system. We have also discussed the characteristics of the current datasets, and various other factors taken into account while creating the dataset for the Indian scenario. Apart from this, we have benchmarked the results on the developed dataset using eight state-of-the-art pre-trained convolutional neural network (CNN) models, namely Xception, InceptionV3, DenseNet121, MobileNetV2, and VGG16, NasNetMobile, ResNet50 and ResNet152. Among these, the Xception, InceptionV3 and DenseNet121 models produce the best classification accuracy scores of 0.94, 0.93 and 0.92 respectively. These models are further utilized to make an ensemble model to enhance the performance of the overall categorization model. Majority voting-based ensemble, Weighted average-based ensemble, and Sum rule-based ensemble approaches are used as ensemble models that give accuracy scores of 0.95, 0.94, and 0.94, respectively. [ABSTRACT FROM AUTHOR]

In urban system management and public safety, accurate traffic flow forecasting is pivotal for real-world applications such as traffic control, resource-sharing scheduling platforms, and intelligent transportation systems. The challenge lies in effectively capturing complex spatio-temporal correlations. To address this, we introduce ST-DSTN, a novel spatial-temporal fusion attention-based deep neural network that significantly advances the current state-of-the-art. ST-DSTN utilizes three distinct temporal branches to capture temporal dependencies and a convolutional neural network to encapsulate spatial dependencies. Our innovative contribution includes a spatio-temporal fusion attention module, effectively modeling the dynamic spatio-temporal dependencies of traffic data, thus improving upon existing methods. Additionally, we propose a hierarchical fusion method that permeates the entire model, capturing complex correlations at various levels through multi-level fusion. Our comprehensive experiments on the BikeNYC dataset demonstrate ST-DSTN's superior performance, supported by numerical results that substantiate its improvement over current methods, surpassing the DeepSTN+ model by 4.31%. [ABSTRACT FROM AUTHOR]

Recent advancements in the industrial revolution and artificial intelligence have aided in the development of novel approaches that have considerable potential for increasing the efficiency of traffic networks. Emerging concepts of autonomous driving and machine learning can be incorporated intelligently for improving traffic operations and control. In the coming years, traffic composition can vary in terms of autonomous vehicle (AV) penetration rate, which can lead to a heterogeneous traffic environment. Traffic control methods for such complex networks need to be designed effectively for accommodating the positive effects of AV implementation without compromising the safety and level of service in the presence of regular vehicles (RVs). An intelligent-based optimization framework for traffic signal control under heterogeneous AV-based traffic is proposed in this paper. This framework utilizes state-of-the-art machine-learning approaches to represent and design different components of the optimization process of cycle length. Further, SHapley Additive exPlanations (SHAP) is used to enhance model interpretability. The proposed optimization framework improves performance under congested traffic conditions compared with that of the conventional optimization methods. Compared to pure RV-based traffic, the penetration rates of 25%, 50%, and 100% can decrease optimized cycle lengths by 26%, 39%, and 53%, respectively, which can result in delay reductions of approximately 18%, 31%, and 56%, respectively. The proposed framework when applied in an adaptive-based manner can help in the generalization of controlling existing signalized intersections with the gradual penetration of AVs without the extra infrastructure or specific operational and connectivity capabilities of the involved vehicles. [ABSTRACT FROM AUTHOR]

This paper introduces a library for cross-simulator comparison of reinforcement learning models in traffic signal control tasks. This library is developed to implement recent state-of-the-art reinforcement learning models with extensible interfaces and unified cross-simulator evaluation metrics. It supports commonly-used simulators in traffic signal control tasks, including Simulation of Urban MObility(SUMO) and CityFlow, and multiple benchmark datasets for fair comparisons. We conducted experiments to validate our implementation of the models and to calibrate the simulators so that the experiments from one simulator could be referential to the other. Based on the validated models and calibrated environments, this paper compares and reports the performance of current state-of-the-art RL algorithms across different datasets and simulators. This is the first time that these methods have been compared fairly under the same datasets with different simulators. [ABSTRACT FROM AUTHOR]

Compared to traditional traffic signal control methods, the method driven by Deep Reinforcement Learning (DRL) has shown better performance. But the problem of low sample utilization in reinforcement learning also arises. To deal with the problem, this paper presents a novel Twin Delayed Deep Deterministic Policy Gradient with Dual Buffer (TD3_DB) for traffic signal control. In the proposed framework, two experience buffers are used to store important samples and normal samples, separately, and the proportion of the two buffers is adjusted adaptively. In addition, lane pressure, describing the dynamic feature of lane traffic flow, is used for the state design of the TD3 agent, which enhances the perception of the agent toward intersections. Comprehensive experiments on different traffic flow modes has shown, the dual experience replay scheme can improve the sample utilization, and the proposed TD3_DB performs better than other methods such as original TD3, Proximal Policy Optimization (PPO), etc., effectively reducing vehicle queue length and waiting time. [ABSTRACT FROM AUTHOR]

One of the focal points in the field of intelligent transportation is the intelligent control of traffic signals (TS), aimed at enhancing the efficiency of urban road networks through specific algorithms. Deep Reinforcement Learning (DRL) algorithms have become mainstream, yet they suffer from inefficient training sample selection, leading to slow convergence. Additionally, enhancing model robustness is crucial for adapting to diverse traffic conditions. Hence, this paper proposes an enhanced method for traffic signal control (TSC) based on DRL. This approach utilizes dueling network and double q-learning to alleviate the overestimation issue of DRL. Additionally, it introduces a priority sampling mechanism to enhance the utilization efficiency of samples in memory. Moreover, noise parameters are integrated into the neural network model during training to bolster its robustness. By representing high-dimensional real-time traffic information as matrices, and employing a phase-cycled action space to guide the decision-making of intelligent agents. Additionally, utilizing a reward function that closely mirrors real-world scenarios to guide model training. Experimental results demonstrate faster convergence and optimal performance in metrics such as queue length and waiting time. Testing experiments further validate the method's robustness across different traffic flow scenarios. [ABSTRACT FROM AUTHOR]

Deep-buried tunnels with weak surrounding rock are frequently encountered issues in traffic engineering. It plays an important role in the excavation process and the project operation. This paper applies the theoretical analysis and laboratory test related to four different conditions in terms of their thickness to determine the mechanical response of deep-buried tunnel lining. Then, the energy dissipative structure theory is employed to explain the experimental results. This paper has made the following achievements: firstly, it is found that the toughness of the secondary lining was found to be often the most important indicator of tunnel safety, with better-toughness linings having higher tensile strength and crack resistance. Secondly, it suggests that the inclusion of steel reinforcement in the concrete lining can effectively improve the secondary lining toughness. Finally, it proves that the more ductile liner had more energy, higher load-carrying capacity, and was better able to maintain the overall stability of the structure. [ABSTRACT FROM AUTHOR]

In recent years, the problem of traffic congestion has become increasingly serious, and research on traffic system control has become a new hotspot. Studying the bifurcation characteristics of traffic flow systems and designing control schemes for unstable support points can alleviate traffic congestion from a new perspective. This article improves the full speed differential model considering strong wind models from the perspective of bifurcation control to adjust traffic flow. This article theoretically proves the existence conditions of Hopf bifurcation and saddle node bifurcation in the model and finds the stability mutation point of the transportation system stability. A nonlinear system feedback controller was designed for unstable bifurcation points using Chebyshev polynomial approximation and random feedback control methods. Without changing the system equilibrium point, the advance, delay, and elimination of Hopf bifurcation were achieved, and the abrupt behavior of the transportation system was controlled, thereby alleviating traffic congestion. This article explains the changes in the stability of complex transportation systems from the perspective of bifurcation analysis, which can better capture the characteristics of traffic flow. By adjusting the control parameters in the feedback controller, the influence of boundary conditions on the stability of the transportation system is fully described, and the influence of unstable focal points and saddle points on the system is suppressed, thereby slowing down the traffic flow. In addition, unstable bifurcation points can be eliminated, and the Hopf bifurcation can be controlled to advance, delay, and disappear, thereby achieving control over the stable behavior of the transportation system. This helps alleviate traffic congestion and also helps describe actual traffic phenomena. [ABSTRACT FROM AUTHOR]

Forecasting traffic flow is crucial for Intelligent Traffic Systems (ITS), traffic control, and traffic management systems. Complex spatial and temporal interactions of traffic networks make traffic forecasting tasks challenging. Recently, Graph Convolutional Network (GCN) has attracted researchers' attention as it can better represent graph-shaped road networks and extract spatial features of traffic. However, traditional GCN has some drawbacks since it uses a static adjacency matrix which is unable to capture the time-varying features of traffic propagation. To overcome this, we represent the traffic road network as a dynamic graph and use a probabilistic spatiotemporal adjacency matrix to identify the time-varying impacts of adjacent roads on target roads in GCN. In addition, to find the similarity among the nonadjacent nodes, we have employed node-specific learning in GCN rather than sharing parameters in traditional GCN. This node-specific learning helps our model to learn detailed characteristics of road networks. For temporal feature extractions, we used a Gated Recurrent Unit (GRU) that captures the local trend of traffic flow and an attention mechanism to capture the global trend of traffic flow. We compared the performance of our model with baseline models using two real-world datasets. Experimental results show that our model is effective in forecasting both short and long-term traffic flow. Source code of our model is available at https://github.com/atkia/PSTGCN [ABSTRACT FROM AUTHOR]

Efficient traffic signal management is crucial for regulating traffic flow and fostering sustainable development within road transportation systems. To address the challenges in traffic management, numerous studies have applied the Adaptive Traffic Signal Control (ATSC) technology, using Deep Reinforcement Learning (DRL) to decrease vehicles' average waiting times. Nonetheless, the intricate nature of DRL, characterized by its extensive parameter connections, often complicates the assurance of real-time responsiveness. Additionally, by prioritizing reduced waiting times, these methods may overlook potential rises in queue lengths, risking congestion. In this paper, we propose an Efficient Double Broad Reinforcement Learning (E-DBRL) algorithm based on a Double Broad Q-Network (Double BQN) to alleviate the overestimation of action values common in Broad Reinforcement Learning (BRL). To enhance the Quality of Experience (QoE) of drivers, we develop a new reward function that optimizes the average waiting time and the range between the longest and shortest waiting times, thus avoiding the need for dimension normalization. Moreover, we conduct simulation experiments using actual traffic data collected from Hangzhou, China. The experimental results indicate that, compared to the traditional Double DQN, the proposed E-DBRL algorithm achieves a 45.78% reduction in the average training time per round and a 5.57% increase in the average rewards. [ABSTRACT FROM AUTHOR]

Traveling demand increased rapidly on the roads of big cities. Traffic congestion is observed on a regular basis and causes serious problems for citizens. It is a vital need in larger cities to deal with the problem of overcrowded roads because Traffic congestion has negative consequences on daily routines and activities. All of the factors that cause traffic-jam affect our lives physically, mentally, and economically. It has been observed that one of the factors of the traffic jam is traffic diversion. Traffic diversion reroutes all the traffic towards alternative tracks that causes traffic jams to the diverted road. It has been observed in the past that the researchers less considered traffic congestion due to traffic diversion. There is a need for analysis to determine the risk factor related to traffic diversion that impacts the causes of traffic jams. This paper focuses on proposing an architecture based on the Internet Cloud of Vehicles for traffic congestion control through the mobile crowdsensing technique. [ABSTRACT FROM AUTHOR]

Network traffic classification is a fundamental and intricate component of network management in the modern, high-tech era of 5G architectural design, planning of resources, and other areas. Investigation of traffic classification is a key responsibility of traffic engineering in SDN. SDN is a network programmability technology used in 5G networks that divides the control plane from the data plane. It also points the way for autonomous and dynamic network control. SDN needs data from the classification system's flow statistics to apply the appropriate network flow policies. To control the volume of heterogeneous network traffic data in 5G network service, the network administrator must implement a carefully supervised traffic investigation system. This study uses machine learning techniques to examine alternative ways of handling heterogeneous network traffic. The suggested approach is Ensemble Learning for Automated Network Traffic Categorization. i.e., CatBoosting for Automated network traffic classification for multiclass (Cat-ANTC) predicts traffic categorization and offers a higher prediction accuracy than individual models and a more regularized model formalization to decrease over-fitting and boost efficiency. The Cat-ANTC is evaluated using benchmark network traffic datasets that are openly accessible and contrasted with current classifiers and optimization methods. It is clear that when compared to the currently used ensemble techniques, the suggested ensemble methodology produces promising outcomes. Additionally, the proposed method is tested and shown to perform better than the classification of traffic flow using the current model. [ABSTRACT FROM AUTHOR]

Due to recent advancements in connected and autonomous vehicles (CAVs), freeway traffic control (FTC) has become a trendy area of research. Combining CAVs and control measures has opened more efficient traffic flow possibilities. However, while there is extensive research on how traffic control and CAVs can enhance traffic flow performance, their safety benefits should be evaluated more comprehensively. It is challenging to distinguish their contributions to traffic flow safety. Studies on the safety of CAVs in traffic flow indicate that traffic flow safety improves with higher market penetration rates (MPR) of CAVs. However, this finding only sometimes aligns with the traffic flow performance effects of CAVs on freeways. This paper introduces a framework for assessing the safety effects of FTC strategies in mixed traffic scenarios involving human-driven vehicles and CAVs. The proposed framework is tested through a microsimulation-based case study in Istanbul, Turkey. The results show that, despite varying MPRs, the safety effects of CAVs and FTC methods do not consistently reduce the number of conflicts in the traffic flow context. [ABSTRACT FROM AUTHOR]

Given the role of road tunnels in a road network, it is relevant to quantitatively assess their resilience due to disruptive events. In this respect, the travel speed of traffic flow, as a metric of resilience, in the event of traffic accidents in road tunnels has been scarcely used. This represents a gap of knowledge that this paper intends to fill. For the purpose, the research method applied involves the development of a traffic macro-simulation model, and the analysis of results using the average travel speed and its spatial profile as a resilience metric. Particularly, we have evaluated the resilience of a twin-tube motorway tunnel when a traffic accident occurs in a tube. The findings showed how the best functionality level of the system, expressed in terms of average vehicles' speed, with its related greatest resilience index, is associated with the partial closure of the disrupted tube rather than the complete one. Further benefits might be obtained by activating Variable Message Signs (VMSs) that alert only the Heavy Goods Vehicles (HGVs) to exit the motorway before entering the tunnel and to use an alternative itinerary identified in the nearby transportation network. In this respect, we found that by means of the activation of VMSs as a traffic control strategy, the resilience index increased by about 7–17% when the traffic accident caused the partial closure of the disrupted tube for 1–3 h. Improvements might also be achieved by rapidly opening the two traffic by-passes at the tunnel portals that allow for the use of the adjacent undisrupted tube for two-way traffic. The unavailability of an alternative itinerary in the nearby transportation network along which to re-route the HGVs is also examined, finding a reduction in the functionality conditions of the system. The results obtained might serve as a support tool in the choice of functional recovery strategies in the case of the temporary partial or complete block of a tunnel tube due to a traffic accident. [ABSTRACT FROM AUTHOR]

This paper describes the effects of running in-network quality adaption by trimming the packets of layered video streams at the edge. The video stream is transmitted using the BPP transport protocol, which is like UDP, but has been designed to be both amenable to trimming and to provide low-latency and high reliability. The traffic adaption uses the Packet Wash process of Big Packet Protocol (BPP) on the transmitted Scalable Video Coding (SVC) video streams as they pass through a network function which is BPP-aware and embedded at the edge. Our previous work has either demonstrated the use of Software Defined Networking (SDN) controllers to implement Packet Wash directly, or the use of a network function in the core of the network to do the same task. This paper presents our effort to deploy and evaluate such a process at the edge, highlighting the packet trimming algorithm and showing the packet trimming effects on the streams. We compare the performance of transmitting video using BPP and the Packet Wash trimming, against alternative transmission schemes, namely UDP and HTTP adaptive streaming (HAS), presenting a number of quality parameters. The results demonstrate that providing traffic engineering using in-network quality adaption using packet trimming, provides high quality at the receiver. [ABSTRACT FROM AUTHOR]

In many real-life scenarios, multiple agents necessitate cooperation to accomplish tasks. Benefiting from the significant success of deep learning, many single-agent deep reinforcement learning algorithms have been extended to multi-agent scenarios. Overestimation in value estimation of Q-learning is a significant issue that has been studied comprehensively in the single-agent domains, but rarely in multi-agent reinforcement learning. In this paper, we first demonstrate that Q-learning-based multi-agent reinforcement learning (MARL) methods generally have notably serious overestimation issues, which cannot be alleviated by current methods. To tackle this problem, we introduce the double critic networks structure and the delayed policy update to Q-learning-based multi-agent MARL methods, which reduce the overestimation and enhance the quality of policy updating. To demonstrate the versatility of our proposed method, we select several Q-learning based MARL methods and evaluate them on several multi-agent tasks on the multi-agent particle environment and SMAC. Experimental results demonstrate that the proposed method can avoid the overestimation problem and significantly improve performance. Besides, application in the Traffic Signal Control verifies the feasibility of applying the proposed method in real-world scenarios. [ABSTRACT FROM AUTHOR]

Recently, there has been considerable interest in the classification of flows among existing applications in SDN, such as traffic engineering, service quality, and network management. Particularly, the classification methods used for elephant flow detection play an essential role. With elephant flow detection, the high bandwidth provided by data centers is used effectively, and traffic routing can be performed on the network without delay. The most important goals in elephant flow classification are to detect elephant flows in the shortest possible time and with high accuracy. This study aims to lead further studies by analyzing different classifiers for elephant flow detection, which is the preliminary step of elephant flow routing in SDN. For this purpose, a new framework is proposed for elephant flow detection. The framework is tested with six different classifiers; most have not been used in the literature before in elephant flow detection on SDN. The proposed framework's first step is to convert UNI1 and UNI2 datasets containing actual network data into flowing datasets using the Flowrecorder tool. The OTSU thresholding method is used for ground-truth labeling. Then, feature extraction is made for the six different classifiers. In the proposed framework, 11 various features are extracted for each flow. In addition, the most suitable parameters for each classifier are determined by the grid search method. The success of classification techniques is calculated using accuracy, precision, recall, F-score, and running time measures. When the results are examined, the proposed framework obtained pretty successful results in SVM and decision tree methods. [ABSTRACT FROM AUTHOR]

Since its outbreak in December 2019, COVID-19 has spread rapidly across the world. To slow down the spread of the pandemic, various countries have implemented a series of policies and measures. The transportation system is not only an important carrier for COVID-19, but also a vital means for the prevention and control of the spread of the pandemic. Therefore, most anti-pandemic measures are based on travel restrictions, thereby slowing down the spread of the pandemic. As a result, because of the impact of the pandemic and corresponding control measures, the transportation system has undergone tremendous changes. By analyzing the evolution of the transportation system in response to the influence of COVID-19, it is possible to better understand socioeconomic changes and the changes in residents' daily life. Based on rich license plate recognition data, the characteristics of urban motorized travel under the influence of COVID-19 has been analyzed. According to the processes associated with the control of the pandemic and the resumption of work and production, the analysis period is divided into four stages. The changes in indicators of macroscopic traffic status are analyzed for each stage. The three types of typical motor vehicle groups (i.e., non-localized operating vehicles, taxis, and localized operating vehicles) are characterized by the traffic flow they contribute, the number of vehicles in transit, the average travel intensity, the average daily travel time of a vehicle, the average daily travel distance of a vehicle, and the spatiotemporal distributions of origins and destinations of trips. These data clarify the spatiotemporal evolution characteristics of peoples' travel behavior at different stages of the pandemic. The results of data analysis show that COVID-19 has deeply changed the motorized travel behavior of urban residents. In the initial stage of resumption of work and production, the willingness to engage in motorized travel had decreased significantly compared with that in the first stage. This willingness gradually resumed until the third and fourth stages, but still did not fully reach the level before the onset of the pandemic. Specifically, the traffic status during morning and evening peaks has basically recovered, and has even increased beyond the level before the pandemic; however, a certain gap was still found between off-peak hours. There were also significant differences in the extent to which different types of vehicles were affected by the pandemic. Among these, taxis were impacted the most by the pandemic. In the fourth stage (at the end of April), the average daily travel time of a vehicle and the average daily travel distance of a vehicle still decreased by 29.25% and 22.63% compared with the first stage, respectively. The operating time of many taxis was shortened from 22:00 PM to 19:00 PM. The spatiotemporal characteristics of vehicles show that the reduction of flexible travel demand (e.g., shopping, catering, and entertainment) is key to the reduction of the travel demand of the road network. This research provides data support for the implementation of traffic control measures under future grave public health events and enables the formulation of urban traffic policies in the post COVID-19 era. [ABSTRACT FROM AUTHOR]

In this study, a traffic queue model is employed to simulate traffic parameters for optimization purposes. The primary objective is to enhance the average queue length, cumulative delay, and cumulative reward for varying numbers of vehicles generated using an innovative approach. The proposed methodology integrates deep Reinforcement Q-Learning techniques implemented through a realistic simulator, Simulation of Urban MObility, based on OpenStreetMap. This simulator is used to balance the flow of traffic by monitoring traffic conditions and adjusting signals (Red/Yellow/Green) accordingly. The research extensively evaluates simulation outcomes across different scenarios involving 50, 100, 500, and 1000 vehicles, with episodes 10, 50 and 100. The results provide valuable insights into training times, simulation durations, and total rewards obtained, indicating improvements in mitigating traffic congestion. The introduction of a traffic control strategy enhances model effectiveness through the utilization of four-layer deep neural network architectures with 400 neurons in hidden layers. However, the study also highlights persistent challenges related to real-time implementation and complexities in state-action-agent relationships. The progress highlights improvements in reducing congestion and enhancing efficiency at junctions by dynamically adjusting signal phases while leveraging historical data. The results highlight the potential of dynamic traffic management strategies in effectively addressing urban traffic challenges. [ABSTRACT FROM AUTHOR]

To investigate the influence mechanism of geostress on rockburst characteristics, three groups of gneiss rockburst experiments were conducted under different initial geostress conditions. A high-speed photography system and acoustic emission (AE) monitoring system were used to monitor the entire rockburst process in real time. The experimental results show that when the initial burial depth increases from 928 m to 1320 m, the proportion of large fracture scale in rockburst increases by 154.54%, and the AE energy increases by 565.63%, reflecting that the degree and severity of rockburst increase with the increase of burial depth. And then, two mechanisms are proposed to explain this effect, including (i) the increase of initial geostress improves the energy storage capacity of gneiss, and then, the excess energy which can be converted into kinetic energy of debris ejection increases, consequently, a more pronounced violent ejection phenomenon is observed at rockburst; (ii) the increase of initial geostress causes more sufficient plate cracks of gneiss after unloading of σh, which provides a basis for more severe ejection of rockburst. What's more, a precursor with clear physical meaning for rockburst is proposed under the framework of dynamic response process of crack evolution. Finally, potential value in long term rockburst warning of the precursor obtained in this study is shown via the comparison of conventional precursor. [ABSTRACT FROM AUTHOR]

Purpose: To mitigate the urban traffic noise within the frequency range of 100–400 Hz, this paper proposes a novel ventilated metamaterial barrier (VMB). Methods: With the help of the finite-element method, the sound mitigation property of the proposed VMB is simulated. Using the Monte Carlo method, the proposed VMB is designed. The ventilation efficiency of the proposed VMB is evaluated in terms of flow resistivity. Furthermore, a parametric analysis is conducted to investigate the influences of the geometric size of the unit cell, acoustic incident angle, layer spacing, and layer number on the noise mitigation performance. Results and Conclusions: Numerical results confirm that the VMB has a significant noise reduction effect in the low-frequency sound range. After passing through the VMB, the peak normal incidence sound absorption coefficient displays a reduction of 92.5%. Overall, the VMB solves the conflict between acoustic performance and ventilation efficiency of traditional road sound barriers, which has lots of potential applications in traffic engineering. [ABSTRACT FROM AUTHOR]

Automated Vehicles (AVs) are designed and programmed to follow traffic rules. However, there is no separate and comprehensive regulatory framework dedicated to AVs. The current Queensland traffic rules were designed for humans. These rules often contain open texture expressions, exceptions, and potential conflicts (conflict arises when exceptions cannot be handled in rules), which makes it hard for AVs to follow. This paper presents an automatic compliance checking framework to assess AVs behaviour against current traffic rules by addressing these issues. Specifically, it proposes a framework to determine which traffic rules and open texture expressions need some additional interpretation. Essentially this enables AVs to have a suitable and executable formalization of the traffic rules. Defeasible Deontic Logic (DDL) is used to formalize traffic rules and reasoning with AV information (behaviour and environment). The representation of rules in DDL helps effectively in handling and resolving exceptions, potential conflicts, and open textures in rules. 40 experiments were conducted on eight realistic traffic scenarios to evaluate the framework. The evaluation was undertaken both quantitatively and qualitatively. The evaluation result shows that the proposed framework is a promising system for checking Automated Vehicle interpretation and compliance with current traffic rules. [ABSTRACT FROM AUTHOR]

Traffic light optimization is known to be a cost-effective method for reducing congestion and energy consumption in urban areas without changing physical road infrastructure. However, due to the high installation and maintenance costs of vehicle detectors, most intersections are controlled by fixed-time traffic signals that are not regularly optimized. To alleviate traffic congestion at intersections, we present a large-scale traffic signal re-timing system that uses a small percentage of vehicle trajectories as the only input without reliance on any detectors. We develop the probabilistic time-space diagram, which establishes the connection between a stochastic point-queue model and vehicle trajectories under the proposed Newellian coordinates. This model enables us to reconstruct the recurrent spatial-temporal traffic state by aggregating sufficient historical data. Optimization algorithms are then developed to update traffic signal parameters for intersections with optimality gaps. A real-world citywide test of the system was conducted in Birmingham, Michigan, and demonstrated that it decreased the delay and number of stops at signalized intersections by up to 20% and 30%, respectively. This system provides a scalable, sustainable, and efficient solution to traffic light optimization and can potentially be applied to every fixed-time signalized intersection in the world. Without relying on any infrastructure-based vehicle detectors, the authors present a scalable traffic signal re-timing system that uses a small percentage of connected vehicle trajectories as the only input. Real-world tests demonstrate that the system decreases both delays and number of stops. [ABSTRACT FROM AUTHOR]

Accurately obtaining accurate information about the future traffic flow of all roads in the transportation network is essential for traffic management and control applications. In order to address the challenges of acquiring dynamic global spatial correlations between transportation links and modeling time dependencies in multi-step prediction, we propose a spatial linear transformer and temporal convolution network (SLTTCN). The model is using spatial linear transformers to aggregate the spatial information of the traffic flow, and bidirectional temporal convolution network to capture the temporal dependency of the traffic flow. The spatial linear transformer effectively reduces the complexity of data calculation and storage while capturing spatial dependence, and the time convolutional network with bidirectional and gate fusion mechanisms avoids the problems of gradient vanishing and high computational cost caused by long time intervals during model training. We conducted extensive experiments using two publicly available large-scale traffic data sets and compared SLTTCN with other baselines. Numerical results show that SLTTCN achieves the best predictive performance in various error measurements. We also performed attention visualization analysis on the spatial linear transformer, verifying its effectiveness in capturing dynamic global spatial dependency. [ABSTRACT FROM AUTHOR]

The alleviation of traffic congestion relies on efficient traffic control and traffic guidance, which are based on real-time short-term traffic flow prediction. In this paper, the stacked autoencoder (SAE) deep learning model with powerful feature learning capability is selected to predict the traffic flow on road sections. The process of training SAE includes the pre-training phase and the fine-tuning phase, which mainly apply the BP algorithm. However, the process of training SAE is time-consuming and cannot meet the real-time performance of modern application systems. This paper proposes a parallel training strategy for the SAE prediction model based on data parallel mode. The gradient solution process in our algorithm satisfies the conditions of parallel computing, so the training process can be designed in a parallel manner. The original dataset is distributed to some computing nodes, which are work nodes. The work node is responsible for gradient calculation using the local data. The task of the sole master node is to synthesize the gradient calculation results and then broadcast the updated gradient to each work node. The simulation results show that the SAE-based prediction model achieves better results than the traditional model, and the parallel algorithm reduces the running time of training processes. [ABSTRACT FROM AUTHOR]

With the widespread application of large-section quasi-rectangular pipe-jacking tunnels in urban road traffic engineering in China, higher requirements have been put forward to control the influence of their construction on the surrounding environment. To scientifically evaluate the stability of large-section quasi-rectangular pipe-jacking tunnels under-passing existing box culverts, we proposed a novel viscoelastic–plastic model coupling Biot consolidation with non-stationary parameter shear creep (NPSCBCVPM) to fully characterize the coupling effect of consolidation and rheology of saturated soft soil. NPSCCBVPM was developed in Fortran as an ABAQUS user material subroutine. In addition, the NPSCBCVPM was compared with the creep tests of undisturbed soft soil and the generalized Nishihara creep model (GNCM). Finally, the proposed model was applied to the large-section quasi-rectangular pipe-jacking tunnel under-passing existing box culverts of Songhu Road in Shanghai. The results show that NPSCBCVPM are in good agreement with the creep tests of soft soil, and NPSCBCVPM can better reflect the nonlinear rheological characteristics of soft soil than GNCM. Furthermore, the proposed model can scientifically evaluate the viscoelastic–plastic stability analysis of large-section quasi-rectangular pipe-jacking tunnel under-passing box culvert. Further research should focus on developing three-dimensional NPSCBCVPM to better evaluate the spatial response of the box culvert structure and surrounding soil to the entire construction process of large-section quasi-rectangular pipe-jacking tunnels. [ABSTRACT FROM AUTHOR]

The research of traffic congestion control has been developed rapidly in recent years. Researching the bifurcation characteristics of traffic flow and designing control schemes for unstable bifurcation points can provide some new methods for relieving the traffic congestion. In this paper, we study the bifurcation characteristics and nonlinear control of traffic flow based on the continuum model considering the new energy vehicles effect. First, a macroscopic traffic flow model considering the number of new energy vehicles and their range is proposed. Then, we transform it into a traffic flow stability model suitable for branching analysis using the traveling wave transformation. Therefore, we can transform the traffic flow problem into the stability analysis problem of systems and reflect unstable traffic characteristics such as congestion. Based on the stability model, the existence conditions of the Hopf bifurcation are proved and some bifurcation points of the traffic system are found. Second, we study the congestion and stability abrupt change behaviors near the equilibrium point and branching point to seek for the formation mechanism of traffic congestion. Finally, for the unstable bifurcation point, the control scheme is designed by Chebyshev polynomial approximation, stochastic feedback control, and other methods to delay or disappear the unstable bifurcation point and alleviate traffic congestion. It has important theoretical significance and application value. [ABSTRACT FROM AUTHOR]

Recently, the Non-Standalone Architecture option 3 standard is proposed to facilitate the deployment of 5th Generation (5G) New Radio (NR) cellular systems. According to this standard, 5G NR base stations can utilize the 4th Generation (4G) Long-Term Evolution (LTE) core network to provide network services. Additionally, the network can be configured to support LTE-NR dual connectivity enhancement, which means that a User Equipment (UE) can connect to a 4G LTE and a 5G NR base station at the same time. In such a dual connectivity network, the 4G LTE base station dispatches downlink traffic flows between the 4G LTE and 5G NR base stations for UEs. As investigated in previous works, traffic flow controls between 4G LTE and 5G NR base stations will affect network performance. In this work, we propose a downlink flow control algorithm based on the concept of Genetic Algorithm, with the objectives of maximizing throughput and fairness of throughput. We verify our designs through simulation programs and experiments on real platforms. The results indicate that the proposed solution effectively achieves the designed objectives. [ABSTRACT FROM AUTHOR]

Traffic engineering of software-defined networks (SDNs) refers to network traffic monitoring and network status analysis to improve network performance, which can be achieved by addressing a variety of issues such as routing, congestion control, flow control, and load balancing. In this paper, a new traffic engineering approach is proposed that attempts to manage the traffic of SDN by adjusting the retransmission timeout. In the proposed approach, the initial retransmission timeout is determined based on transmission and propagation delays, and then this time is adaptively adjusted according to the priority of the packets, which depends on the type of packet and the number of elapsed hops. The conducted simulations in the Mininet tool have validated the effectiveness of the proposed approach in comparison to counterpart methods in terms of average throughput, average bandwidth utilization, end-to-end delay, and packet loss ratio. Eventually, analysis of the time complexity and message complexity demonstrates that the overhead of the proposed approach is negligible. [ABSTRACT FROM AUTHOR]

Traffic lights are crucial for urban traffic management, as they significantly impact congestion reduction and travel safety. Traditional methods relying on hand-crafted rules and operator experience are limited in their ability to adapt to changing traffic environments. To address this challenge, we have been exploring intelligent traffic light control using deep reinforcement learning techniques. However, current approaches often suffer from inadequate training data and unstable training processes, leading to suboptimal performance and real-world consequences. In this study, we propose RELight, a novel random ensemble reinforcement learning-based traffic light control framework. RELight effectively utilizes collected empirical data, ensuring a stable and efficient training process. To evaluate the performance of our proposed framework, we conducted a comprehensive set of experiments on a variety of datasets, including four synthetic datasets and a real traffic dataset collected from surveillance cameras at an intersection in Hangzhou, China. The results show that RELight outperforms existing approaches, demonstrating its superiority and potential for practical traffic light control applications. [ABSTRACT FROM AUTHOR]

The findings of this article expounds a multi-server priority queueing model by taking into account the preemptive resume priority scheduling and threshold based phase-type distribution ( P H D ) for retrial process. On the basis of priority, the incoming heterogeneous traffic is categorized as high priority traffic ( H P T ) and low priority traffic ( L P T ). When all the channels are busy, an arriving L P T will be denied for the service, and it will enter the orbit (virtual space) to retry after some time. The retrial process will follow P H D when the number of L P T is less than some threshold value otherwise the retrial process will follow exponential distribution. One of the following two instances may occur when all of the channels are occupied and a H P T enters the system. In the first instance, the arriving H P T will be discarded from the system if all the channels are packed with H P T solely. On the contrary, in the second instance, the approaching H P T will be provided service by employing preemptive priority when at least one L P T is receiving service, and that preempted L P T will enter a buffer of finite capacity. Whenever an idle channel is found, the preempted L P T will begin its service from the termination phase. The level dependent quasi-birth-death process is used for the modeling and analysis of the proposed framework. By establishing that the proposed Markov chain satisfies the asymptotically quasi-Toeplitz Markov chain classification, the ergodicity conditions for the chain are demonstrated. For the numerical illustration, the expressions of several performance measures have been developed. The non-dominated sorting genetic algorithm-II approach has been used to address an optimization problem for resource optimization and traffic control. [ABSTRACT FROM AUTHOR]

The paper presents a framework to realise "meaningful human control" over Automated Driving Systems. The framework is based on an original synthesis of the results of the multidisciplinary research project "Meaningful Human Control over Automated Driving Systems" lead by a team of engineers, philosophers, and psychologists at Delft University of the Technology from 2017 to 2021. Meaningful human control aims at protecting safety and reducing responsibility gaps. The framework is based on the core assumption that human persons and institutions, not hardware and software and their algorithms, should remain ultimately—though not necessarily directly—in control of, and thus morally responsible for, the potentially dangerous operation of driving in mixed traffic. We propose an Automated Driving System to be under meaningful human control if it behaves according to the relevant reasons of the relevant human actors (tracking), and that any potentially dangerous event can be related to a human actor (tracing). We operationalise the requirements for meaningful human control through multidisciplinary work in philosophy, behavioural psychology and traffic engineering. The tracking condition is operationalised via a proximal scale of reasons and the tracing condition via an evaluation cascade table. We review the implications and requirements for the behaviour and skills of human actors, in particular related to supervisory control and driver education. We show how the evaluation cascade table can be applied in concrete engineering use cases in combination with the definition of core components to expose deficiencies in traceability, thereby avoiding so-called responsibility gaps. Future research directions are proposed to expand the philosophical framework and use cases, supervisory control and driver education, real-world pilots and institutional embedding [ABSTRACT FROM AUTHOR]

Traffic congestion not only has a great impact on people's travel, but also increases energy consumption and air pollution. The control analysis of the macroscopic traffic flow model considering the vehicle braking effect is particularly important, reflecting the impact on the actual traffic flow density wave, so as to better solve the actual traffic problems. In this paper, based on a speed difference optimization speed model, the micro–macro-variables are transformed into a high-order continuous traffic flow model. Then, a random function considering the physical correlation of random components is added to the high-order continuous traffic flow model to establish a random traffic flow model that can reflect the uncertain behavior of traffic flow acceleration or deceleration. Based on this stochastic traffic model, the existence of Hopf bifurcation and bifurcation control of the traffic flow system model considering stochastic characteristics are derived by using Hopf bifurcation theorem. By Chebyshev polynomial approximation method, the stochastic problem of the system is transformed into the bifurcation control problem of its equivalent deterministic system. A feedback controller is designed to delay the occurrence of Hopf bifurcation and control the amplitude of the limit cycle. Without changing the equilibrium point of the system, the complete elimination of Hopf bifurcation can be achieved by controlling the amplitude of the limit cycle. That is, the feedback controller is used to modify the bifurcation characteristics of the system, such as the bifurcation appearing at the equilibrium point in the control system moves forward, moves backward or disappears, so as to achieve the effect of preventing or alleviating traffic congestion. [ABSTRACT FROM AUTHOR]

In the process of collecting traffic information, traditional traffic flow control methods have some problems, such as high loss rate of sensing and detection information and long average queue length, which lead to the unsatisfactory effect of traffic control and evacuation in main roads. Therefore, based on multi-sensor information fusion technology, this study designs a new intelligent control method of traffic flow on main road. According to the multi-sensor information, the fusion algorithm and measurement equation are designed to obtain the main road traffic sensor position, vehicle linear velocity and other parameters, and update the fusion results in real time. Then, the short-term characteristics of traffic flow are used to control the appearance time of target section. Based on the ordinary differential equation, the main road traffic network is represented by intelligent directed graph, and the intelligent dredging model of urban main road traffic flow is constructed. The simulation results show that in five experimental roads, the average delay time of this method is less than 35 s, the maximum average number of stops is only 8.8, the average queue length is less than 30 m, the average travel speed is more than 25 km/h, the traffic flow per unit time is more than 250veh/10 min, and the traffic congestion index of main road is always more than 5.5. The above indexes of this method are better than those of traditional methods, which verifies that this method has better application performance. [ABSTRACT FROM AUTHOR]

Moving aerial targets are tracked in new era of integrated computing with intelligent gadgets as well as systems. Traditional matched filter-based techniques estimation performance would suffer significantly when tracking multiple targets, as weak target is obscured by strong target or strong sidelobes. This exploration propose novel method in radar optical communication handling in light of flying objective examination by recurrence transfer speed with mess concealment. The conventional static radar-based Boundary Element mmwave signal bandwidth and frequency development is used here for the high-profile aerial target detection. Following that, adaptive processing based low rant spatio-temporal with MIMO (multiple input multiple output) is used to suppress radar clutter. Signal-to-clutter-plus-noise ratio (SCPNR), detection accuracy, traffic control, congestion control, and mAP (mean average precision) all play a role in the experimental analysis. Simulation results demonstrate proposed techniques efficacy. The proposed technique attained SCPNR of 85%, detection accuracy of 92%, traffic control of 53%, congestion controlof 55%, mAP of 55%. [ABSTRACT FROM AUTHOR]

Urban traffic congestion is of utmost importance for modern societies due to population and economic growth. Thus, it contributes to environmental problems like increasing greenhouse gas emissions and noise pollution. Improved traffic flow in urban networks relies heavily on traffic signal control. Hence, optimizing cycle timing at many intersections is paramount to reducing congestion and increasing sustainability. This paper introduces an alternative to conventional traffic signal control, EcoLight+, which incorporates future noise predictions with the deep dueling Q-network reinforcement Learning algorithm to reduce noise levels, CO 2 emissions, and fuel consumption. An innovative data fusion approach is also proposed to improve our LSTM-based noise prediction model by integrating heterogeneous data from different sources. Our proposed solution allows the system to achieve higher efficiency than its competitors based on real-world data from Tallinn, Estonia. [ABSTRACT FROM AUTHOR]

In urban areas, utilizing traffic lights to prioritize vehicles at the intersection is a solution to control traffic. Among the smart traffic light methods, the methods based on machine learning are particularly important due to their simplicity and performance. In this paper, Q-learning with deep neural network are combined and used in two different intersection models. The first one is an individual intersection, and the second one is two intersections that are connected and shared their actions. By using this method, the traffic light can make an intelligent decision at the intersection to reduce vehicle consumption time by managing the allocation of phases. The proposed smart traffic light is studied and simulated via SUMO. The results illustrated that compared to fixed-time traffic lights, the average queue time of each vehicle in different traffic scenarios has been reduced by 34% in the individual intersection. In the case of two intersections, awareness and communication between agents led to a 24% reduction in the queue time of all cars in the heavy traffic scenario. [ABSTRACT FROM AUTHOR]

A distributed firewall is a security application that monitors and controls traffic on an organization's network. While centralized firewalls are used against attacks coming from outside a network, distributed firewalls are considered for inside attacks from internal networks such as wireless access and VPN tunnel. Distributed firewalls use policies, which are stated by rules, to find anomalous packets. However, such static rules may be incomplete. In this case, by monitoring firewall logs, the anomalies can be detected. Such logs become big when networks have high traffic, but their hidden knowledge contains valuable information about existing anomalies. In this paper, to detect the anomalies, we extract patterns from big data logs of distributed firewalls using data mining and machine learning. The proposed method is applied to big logs from distributed firewalls in a real security environment, and results are analyzed. [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]

With the emergence of the internet and cellular networks, interest in using computer communication networks and communication systems has skyrocketed. However, unusual occurrences, like cyber attacks, power outages, network congestion, equipment failures, etc. lead to abrupt changes in the state of the system and pose a significant risk to these systems. Consequently, some/all users can be promptly eliminated from the system. These type of scenarios can be well modeled by the multi-server catastrophic queueing model (MSCQ). This article elaborates a MSCQ with the consideration of retrial phenomenon and preemptive repeat priority (PRP) scheduling. For brevity, the working of system before and after the catastrophe phenomenon is referred to as the normal and catastrophic environment, respectively. This study identifies the incoming traffic as calls which are further categorized on the basis of the model operation scenarios. In normal operation scenario, the calls are classified as handoff ( H C ) and new calls ( N C ). This study provides priority to H C over N C using PRP. Whereas, in the catastrophic environment, when the calamity strikes, the whole system is rendered inoperable, and all types of busy/waiting calls are flushed out. To reinstate services in the concerned region, a set of backup/standby channels are quickly deployed. In response to the emergency circumstances in the area, the calls made to emergency personnel are referred as emergency calls ( E C ). Hence, in this case, the incoming calls are categorized as H C , N C , and E C . The E C are given priority using PRP over N C / H C due to the pressing need to save lives in such crucial situations. The system is modeled by a multi-dimensional Markov chain and by demonstrating that the Markov chain satisfies the requirements for asymptotically quasi-Toeplitz Markov chains, the chain's ergodicity conditions are established. Furthermore, a non-dominated sorting genetic algorithm-II method has been employed to define and address an optimization problem to achieve the optimal number of resources. [ABSTRACT FROM AUTHOR]

Traffic signal control (TSC) can be described as a multi-agent cooperative game. To realize cooperation, multi-agent reinforcement learning (MARL) is a significant approach, with communication being a core component. The large-scale traffic signals and the partially observable information in TSC pose a considerable challenge in finding the optimal joint control policy. This paper proposed a deep MARL model named attentional graph relations communications network (AGRCNet). Based on the Actor-Critic framework, AGRCNet designs a communication network to exchange observation information with agents to help obtain the optimal joint action, reducing the decision error caused by the partially observable condition. Specifically, through the communication network, the chain propagation of graph attention networks (GAT) and graph convolutional networks is used to expand the receptive domain of agents, improve communication efficiency and promote cooperative behavior. We simulate the traffic situation near the Nanjing Yangtze River Bridge in Simulation of Urban MObility. With a compound reward, our method performs best. Meanwhile, AGRCNet is applied to two abstract environments, and the results show that our approach can also adapt to dynamic agent relationships and is more efficient than comparison algorithms. [ABSTRACT FROM AUTHOR]

A new automata-based programming language built by extending the Event-B specification language is proposed. When developing models in Event-B, it becomes possible to use automata-based methods in addition to the popular refinement method. The automata-based software engineering based on Event-B is demonstrated by the example of traffic control on a bridge from the Event-B system manual. A simpler solution with verification in the Rodin tool is proposed. The effectiveness of Event-B verification methods is confirmed by finding three nontrivial bugs in our solution. [ABSTRACT FROM AUTHOR]

Software-Defined Networking (SDN) has emerged as a promising paradigm to enhance network control and management by decoupling the planes. With SDN, the centralized controller plays a critical role in managing network resources and traffic flows. Throughout the most recent couple of years, networks turned out to be more imaginative for developing different applications with the help of SDN. Network traffic analysis is a vital task in understanding network behaviour, identifying anomalies, and optimizing network performance. To deal with the load of changes in the networking industry, there is an extraordinary requirement for a productive SDN controller to work on the usage of network resources for a better presentation of the network. Therefore, the proposed approach leverages the RYU controller, an open-source SDN controller framework, to collect and analyse network traffic data. By utilizing RYU's capabilities, we can dynamically monitor and capture network traffic statistics, such as bandwidth, throughput, packet counts, and Round trip time (RTT). These statistics provide valuable insights into network performance, and traffic patterns. By leveraging real-time traffic analysis, we can dynamically adjust routing paths, and allocate network resources efficiently. Hence, the proposed work assesses the development of SDN architecture through a network topology and then, implementation of RYU controller has been done to evaluate various network performance parameters. To evaluate the effectiveness of our approach, we conduct experiments using a simulated SDN environment. We compare the performance parameters of our traffic analysis techniques with traditional methods and showcase the advantages of utilizing SDN and the Ryu controller for network traffic analysis. The results demonstrate that our approach provides accurate and timely insights into network traffic behaviour, facilitating efficient network management. In conclusion, this study highlights the significance of network traffic analysis in SDN environments and demonstrates the effectiveness of the Ryu controller for extracting valuable insights from network traffic data. [ABSTRACT FROM AUTHOR]

Accurately predicting network traffic is helpful for improving a variety of spatial-temporal data mining applications, such as intelligent traffic control, network planning and anomaly detection. The mainstream graph-based methods are limited by the node-level message passing mechanism and require transforming dimensions to generate edge representations. Accordingly, some researchers propose using edge convolution to directly learn edge representations for network traffic prediction. However, node-level and edge-level information aggregation are two different perspectives, and their combination of them can achieve better performance. This paper proposes a novel model for network traffic prediction named the Enhanced Edge Convolution-based Spatial-Temporal Network (EESTN). Armed with a Graph Neural Network and Hypergraph Neural Network, EESTN employs the edge convolutions defined on the graph and hypergraph to effectively extract spatial features. EESTN further combines node convolution to capture the complex correlations among nodes and utilizes an attention mechanism to generate the edge convolution kernel for the decoder. Moreover, a 3D convolution-based multihead self-attention mechanism and a hierarchical loss function are proposed to capture the long-term temporal dependence and make full use of the model's represent ability. Finally, we conduct extensive experiments to validate the effectiveness of EESTN, and the related results demonstrate that EESTN outperforms the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Traffic congestion is a major concern in urban centers, as it can affect society, the environment, and the economy. There are many studies on the use of computational intelligence (CI) to improve mobility in urban centers. Some of these researches focus on developing strategies for traffic light programming, since traffic coordination is complex due to its many parameters, variables, and dynamic behavior, and also an inefficient traffic control plan can lead to increased delays and contribute to traffic congestion. Although there are many works in the literature on strategies for traffic control, there are still some contributions and gaps to be filled, especially because some studies do not consider the automatic optimization of traffic signals in real time, that is, according to the demand of vehicles on the roads, considering multiple objectives and the use of a network of intersections in their experiments. In addition, some of the proposed models are not independent of simulation to evaluate the solutions of CI algorithms, resulting in a more complex deployment in real situations. In this context, this paper presents a new method to optimize traffic light plan in a network of intersections and in real time, called Active Control of Traffic Signals (ACTS) associated with the Non-Dominated Sorting Genetic Algorithm, considering multiple objectives in the optimization process (minimizing the average delay time and the number of vehicles stops per cycle). To test the applicability of the model, a real dataset of vehicle demand collected by the Company of Transport and Traffic of Belo Horizonte (BHTrans) is loaded into the AIMSUN simulator, then the method is applied and compared with the current traffic control plan used by BHTrans. The results show that the ACTS method reduces the average vehicle delay by almost half compared to the results obtained with the current solution used by BHTrans. In real life, this means less time spent in traffic, which promotes faster traffic flow, reducing traffic congestions. [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]

Using reinforcement learning to control traffic signal systems has been discussed in recent years, but most works focused on simple scenarios such as a single crossroads, and the methods aiming at large-scale traffic scenarios face long-time training and suboptimal results. In this work, we develop a new multi-agent reinforcement model for large-scale traffic signal control tasks, and a curriculum transfer learning method is developed to optimize the joint policy step by step. The policies for different intersections are trained in a partially observable Markov decision process with centralized training and decentralized execution mechanism, and we design transformer modules for both the policy and evaluation networks by attention mechanism. We first train policies in a simple traffic scenario, and then these policies are transferred to the next curriculum by policy reloading, while the experiences of the source task are reused selectively. With the number of agents increasing, our method can achieve satisfactory performances quickly by reusing the knowledge from previous curriculums. We conduct several experiments on the Cityflow testbed. In the case of more than 10 crossroads, our model improve the mean reward from 3.0 to 5.0. [ABSTRACT FROM AUTHOR]

Since high-quality real data acquired from selected road sections are not always available, a traffic control solution can use data from software traffic simulators working offline. The results show that in contrast to microscopic traffic simulation, the algorithms employing neural networks can work in real-time, so they can be used, among others, to determine the speed displayed on variable message road signs. This paper describes an experiment to develop and test machine learning models, i.e., long short-term memory, gated recurrent unit recurrent networks, and stacked autoencoder networks. It compares their effectiveness with traffic prediction results generated using a widely recognized traffic simulator that analyzes traffic at the level of individual vehicles. [ABSTRACT FROM AUTHOR]

The rapid development of urbanization in China has contributed to traffic events, such as traffic accidents and delays. It is difficult to detect and resolve highway traffic congestion in a timely manner using traditional methods because they are slow, require a large number of workers, and require the installation of a large amount of monitoring equipment. Therefore, it is imperative to introduce advanced technology to address these challenges. Recently, deep learning technology has made significant breakthroughs and has been widely applied to various fields with satisfactory results. Deep learning is among the most important technologies for the detection and evaluation of traffic congestion, enabling the accurate detection of the state of the expressway network's traffic congestion, the evaluation of traffic congestion, and the prediction of possible traffic congestion. This enables management to formulate traffic dredging strategies in advance to prevent the negative impact of traffic congestion on normal traffic flow. This paper proposes a framework based on deep learning for next-generation highway traffic management. This framework selects traffic congestion indicators to construct an index model, and then constructs a deep learning model based on self-coding. It predicts and classifies highway traffic environment data and excavates sample data based on the characteristics of traffic parameters. As soon as traffic data were classified, a prediction model based on SoftMax was established to detect and predict highway traffic congestion. We conducted a traffic congestion analysis of the Shanghai expressway network based on the speed performance data obtained from the China Traffic Management Bureau. As a result of their research, we developed an index to measure highway traffic congestion. For traffic control and management organizations to function effectively, it is crucial to have an accurate and clear picture of traffic network operations. We evaluated the proposed framework using data gathered from highway monitoring scenes, and the results indicated that 98.6% of the data could be correctly detected. Using the prediction model based on SoftMax for expressway vehicles during peak hours, the accuracy was 92%, and the misjudgment rate was 8%. This study demonstrates that detecting and evaluating the state of highway traffic environments using deep learning has high accuracy, can be applied to actual highway traffic systems, and is extremely useful for detecting highway congestion. This framework is a promising solution for next-generation highway traffic management and provides accurate and timely traffic congestion detection and evaluation. [ABSTRACT FROM AUTHOR]

Rapid increase in the private and public vehicles fleet causes urban centers heavily populated with limited transport road infrastructure. To overcome this, in real-time scenarios, queue length-based traffic light controllers are being designed utilizing light-weighted S-Edge devices. This system suffers from starvation problems if a road lane at the intersection continuously receives vehicles during peak hours. With this, higher green phase duration can be allocated to the same-lane multiple times despite vehicles on the other lanes' longer waiting time. To tackle this problem, an efficient and smart edge computing (S-Edge)-driven traffic light controller is proposed by accounting the real-time heterogeneous vehicular dynamics at the fog computing node. The fog node executes the proposed fuzzy inference system to generate phase-cycle duration. Further, to allocate the phase duration effectively, a method for estimating the lane pressure is proposed for the edge controller utilizing average queue length and waiting time. S-Edge is a light-weighted actuated traffic light controller that generates traffic light control cycle duration and phase (red/yellow/green) duration. To validate the S-Edge controller, a prototype is developed on an Indian city OpenStreetMap utilizing the low-computing power IoT devices, i.e., Raspberry Pi, and a well-known open-source simulator, i.e., Simulation of Urban MObility. [ABSTRACT FROM AUTHOR]