Search

Artificial Intelligence is a medium for machine intelligence that offers tremendous opportunities for the intelligent industrial revolution. Smart transport, computer networks, and networked intelligent cities benefit from the rapid development of networking technologies. It has opened up new possibilities for traffic safety, comfort, and quality solutions. Data-driven approaches are refined using artificial intelligence, a widely used technique in various scientific fields. The new 5G network infrastructure challenges the existing networking situation by addressing the failings of 4G. These emerging technologies give intelligent cities and autonomous networks an additional means of being completely connected, including in high-mobility or densely populated areas, with massive simultaneous connecting and the ubiquity of the web. In this paper, an artificial intelligence-based Vehicle to everything (AI-V2X) system has been used. The proposed method can collect knowledge from various sources, increase driver awareness, and anticipate possible collisions, thus increasing driving comfort, security, and performance. Combining high-speed, robust, low latency networking and AI technology, the complementary between the real world and digital information in Industry 4.0 is transformed into an intelligent vehicle. AI-V2X aims to explore the possible contribution of the new AI approaches to an autonomous vehicle search. This discussion comprehensively illustrates the effects of 5G technologies on Smart Cities, Smart Transportation Networks – including Autonomous and Semi-Auto-Communications, Technological, Economic and Legal challenges. Finally, AI-V2X has open issues and concerns in research that must be resolved to realize AI's responsibility to enhance V2X systems fully. The results are obtained various analysis of vehicles image recognition of 5G networking as follows: improvement of transportation with 5G ratio is 84.2%, vehicle image monitoring on traffic ratio is 88.2%, development of V2X communication is 85.36%, increasing driving comfort ratio is 82.15% and reduction of road congestion on traffic ratio is 91.84%. [ABSTRACT FROM AUTHOR]

Wildfires are increasing in scale, frequency and longevity, and are affecting new locations as environmental conditions change. This paper presents a dataset collected during a community evacuation drill performed in Roxborough Park, Colorado (USA) in 2019. This is a wildland–urban interface community including approximately 900 homes. Data concerning several aspects of community response were collected through observations and surveys: initial population location, pre-evacuation times, route use, and arrival times at the evacuation assembly point. Data were used as inputs to benchmark two evacuation models that adopt different modelling approaches. The WUI-NITY platform and the Evacuation Management System model were applied across a range of scenarios where assumptions regarding pre-evacuation delays and the routes used were varied according to original data collection methods (and interpretation of the data generated). Results are mostly driven by the assumptions adopted for pre-evacuation time inputs. This is expected in communities with a low number of vehicles present on the road and relatively limited traffic congestion. The analysis enabled the sensitivity of the modelling approaches to different datasets to be explored, given the different modelling approaches adopted. The performance of the models were sensitive to the data employed (derived from either observations or self-reporting) and the evacuation phases addressed in them. This indicates the importance of monitoring the impact of including data in a model rather than simply on the data itself, as data affects models in different ways given the modelling methods employed. The dataset is released in open access and is deemed to be useful for future wildfire evacuation modelling calibration and validation efforts. [ABSTRACT FROM AUTHOR]

Road Side Units (RSUs) are an integral component of Vehicular ad hoc Networks (VANET) along with connected and autonomous vehicles. RSUs have been used to host numerous traffic sensing and control mechanisms to enhance transportation throughput in terms of safety, congestion avoidance, route planning, etc. In order to reduce installation and maintenance costs and associated network and security overhead, it is highly desirable to deploy these RSUs optimally, particularly in strategic and influential positions. While too many RSUs may increase overhead, too few RSUs may fail to map the entire region properly, resulting in erroneous computations. This paper aims to address this trade-off by incorporating a novel scheme called Intersection Influence Analysis System for Optimal RSU Deployment (IIA-ORD). The primary objective of IIA-ORD is achieved through modelling the transportation network as connected graphs and executing a modified K-shell and TOPSIS-based framework. Specifically, the network vertices are mapped with road intersections, and live traffic data is used to analyze various statistical measures, leading to the identification of influential junctions. Extensive performance analysis in an open-source simulation platform backed by real-time data justifies the performance superiority of the IIA-ORD system over existing RSU deployment strategies in terms of an overall number of deployed RSUs, average coverage, coverage time ratio, packet delivery ratio, and delay. The system is validated by a traffic forecasting application. The RSU is equipped with the Stacked Bidirectional Long Short-Term Memory (SBi-LSTM) based traffic prediction model, under which the RSU of a particular junction predicts the traffic congestion of the entire region without the deployment of additional RSUs. Comparative analysis records high accuracy with low loss values for the proposed model in relation to the vanilla LSTM model. [ABSTRACT FROM AUTHOR]

In today's era, thinking of Vehicular Ad-hoc Network as a midrib for the leaf of academic, social, corporate, and economic activities will not be erroneous. To avoid any panic situations like road accidents, heavy traffic jams, etc., the timely availability of correct information is obligatory. The presence of malicious nodes within the network will ruin the dream of establishing a safe, secure, and accident-free vehicular network. This objective can be fulfilled only when malicious nodes within the network are identified correctly, and respective actions are taken at the right time. Therefore, there is a great requirement for efficient and intelligent misbehavior detection techniques to deal with such situations. Vehicular networks are very prone to numerous attacks, such as Sybil attacks, unauthorized access, etc. due to their dynamic nature. The main goal of this study is to discuss and bundle various available misbehavior detection schemes and respective solutions to cope with harmful attackers in the network. We have categorized different misbehavior detections on the criteria of architecture, approach, node-centric, and data-centric. The subcategorization is also given within the paper. One section of this paper focuses on the role of machine learning techniques in misbehavior detection as an emerging foot strap for further enhancement. A comparative analysis of various misbehavior detection schemes is also conducted based on performance measures like accuracy, False Positive Rate, Recall, Precision and F-measurement. Finally, the paper concluded by discussing open issues and various research challenges associated with misbehavior detection in the Vehicular Ad-hoc Network. [ABSTRACT FROM AUTHOR]

This work aims to design a sustainable two-echelon supply chain not only based on the widely used cost perspective, but also based on the efficient use and preservation of limited resources. For this purpose, a branch and efficiency (B&E) algorithm is developed, which includes an optimization model and an evaluation model. The proposed tri-objective optimization model simultaneously minimizes the total cost of the supply chain, maximizes the sustainability score, and minimizes inequity among customers. The solutions obtained from the optimization model are then evaluated by extended data envelopment analysis (EDEA) models based on common criteria (i.e., cost and service) and traffic congestion criterion. To take into account real-world conditions, parameters related to labor and demand are assumed under uncertainty. Since the presented models consist of more than one objective function, fuzzy goal programming (FGP) method is utilized to tread the multi-objectiveness. The obtained results from tackling a case study problem demonstrate that considering sustainability issues can positively affect both the economic and social aspects of the problem. Furthermore, the developed B&E algorithm is able to reduce costs in each iteration; this is what supply chain managers are interested in. On the other hand, this algorithm can provide more services to applicants compared to one of the competing algorithms. [ABSTRACT FROM AUTHOR]

With the rapid development of internet technology and mobile devices, massive streaming data of spatiotemporal information is available for real-time data mining. Outlier detection is playing as one of the most important analysis tasks for trajectory stream processing, such as traffic control and urban planning. Existing work about this issue can be divided into two main categories: individual outlier detection (IOD) and group outlier detection (GOD). IOD focuses on detecting an individual trajectory outlier generated by a single moving object (e.g., an over-speeding car), while GOD aims to detect a group outlier generated by various moving objects (e.g., a group of cars influenced by a traffic jam). However, existing studies only support one of them and cannot comprehensively understand the traffic conditions by combining both of them. To this end, we propose a novel framework for real-time urban traffic outlier detection (RUTOD) in this paper. RUTOD contains IOD based on current traffic conditions and GOD according to historical data. In addition, we adopt a street-based trajectory division to accelerate investigation. Experimental results show that our proposal is not only effective but also efficient for detecting both individual outliers and group outliers in real-time scenario. [ABSTRACT FROM AUTHOR]

With the development of artificial intelligence (AI) and the Internet of Things (IoT), public transportation systems in our daily lives are smarter than ever. A large number of wireless sensors are distributed in roadside units (RSUs), collecting traffic flow and public vehicle information to monitor and learn about road congestion, subway arrival, and traffic accidents in real-time. In this paper, we propose probabilistic model checking based path planning for a multimodal transportation system. First, a traffic network with different means of travel is formalized as a directional graph, and the traffic congestion probability is generated from IoT sensor data. Moreover, a discrete-time Markov chain (DTMC) is introduced as the formal model to support quantitative verification. Second, users may have different travel requirements except the shortest path, so user-oriented critical paths are proposed. Then, the minimum cost and the minimum congestion requirements are defined in the form of probabilistic computation tree logic (PCTL) to describe the verification property for evaluating the selected path. We focus on the temporal relations of key points that a user needs to visit to build the travel path. Third, the optimal path is identified and confirmed based on the quantitative results returned by the probabilistic model checker, PRISM, which is a supporting tool that verifies the property against the formal model. Finally, case studies are conducted to demonstrate the feasibility and availability of our proposed method for the smart transportation system. [ABSTRACT FROM AUTHOR]

Location and allocation problems in supply chain networks are considered as strategic decisions; because they both require investment and have long-term effects. On the other hand, the supply chain network is not protected against disruptions in the real world. In this paper, a branch and efficiency (B&E) algorithm is developed which integrates a multi-objective optimization model used for designing the supply chain network with an extended data envelopment analysis (EDEA) model. Through this integration, efficient solutions are obtained that lead to minimization of the costs. The objective functions of the optimization model include the operational costs, resilience costs and inequality in satisfying customer demand. Then, the efficiency of the solutions is measured using EDEA in terms of the costs, service level and traffic congestion. The solutions derived from EDEA are added to the multi-objective optimization model based on efficiency cuts. This iterative procedure continues until an efficient design is developed for the supply chain network. The proposed B&E algorithm is implemented on a real case using fuzzy goal programming to illustrate its applicability. The results show that the proposed algorithm has better performance in reducing the costs and measuring efficiency compared to the competing algorithms in the literature. [ABSTRACT FROM AUTHOR]

The science of cities aims to model urban phenomena as aggregate properties that are functions of a system's variables. Following this line of research, this study seeks to combine two well-known approaches in network and transportation science: (i) The macroscopic fundamental diagram (MFD), which examines the characteristics of urban traffic flow at the network level, including the relationship between flow, density, and speed. (ii) Percolation theory, which investigates the topological and dynamical aspects of complex networks, including traffic networks. Combining these two approaches, we find that the maximum number of congested clusters and the maximum MFD flow occur at the same moment, precluding network percolation (i.e. traffic collapse). These insights describe the transition of the average network flow from the uncongested phase to the congested phase in parallel with the percolation transition from sporadic congested links to a large, congested cluster of links. These results can help to better understand network resilience and the mechanisms behind the propagation of traffic congestion and the resulting traffic collapse. This study analyzes the way car traffic networks collapse by connecting classical traffic flow descriptors with percolation theory: The maximum average car traffic flow in a network and the maximum number of congested clusters occur at the same moment, precluding the network percolation. [ABSTRACT FROM AUTHOR]

Most traffic control systems are centralized, where all the collected data can be analyzed to make a decision. However, there are problems with computational complexity and, more seriously, real-time decision-making. This paper proposes a decentralized traffic routing system based on a new pheromone model of ant colony optimization algorithm and an automated negotiation technique in a connected vehicle environment. In particular, connected vehicles utilize a new pheromone model, namely the inverted pheromone model, which generates a repulsive force between vehicles and gives negative feedback to the congested roads. They also perform a collective learning-based negotiation process for distributing traffic flows throughout the road networks, reducing traffic congestion. Via extensive simulations based on the Simulation of Urban Mobility, the proposed system shows that it can significantly reduce travel time and fuel consumption compared to existing systems. [ABSTRACT FROM AUTHOR]

The advent of autonomous vehicles (AVs) is likely to introduce new mobility experiences for travelers. In particular, AVs would allow travelers to get off at the destinations and then drive themselves elsewhere to park rather than cruise for parking or park at a location with a high parking fee. The self-parking capability is likely to increase the utility of private-owned AVs (PAVs) and make this mobility option more attractive than human-driven vehicles. The present study investigates the dynamics of travelers shifting to PAVs from other transport modes and its negative impact on road traffic congestion. To this end, we propose an agent-based demand model which considers different travel cost components depending on crucial travel attributes such as trip purpose and activity duration. The estimated demand is then fed into a mesoscopic traffic simulation model to examine the resulting road traffic conditions. As charging private vehicles for the congestion they cause is an effective tool for demand management and congestion alleviation, we also integrate a distance-based pricing scheme into the overall modeling framework to investigate its impact on mode choice and transport network performance. A case study is conducted in Melbourne, Australia to demonstrate the proposed methodology. The results indicate that the distance-based pricing scheme can effectively limit the usage of PAVs and reduce traffic congestion, especially in the city center and peripheral suburbs. [ABSTRACT FROM AUTHOR]

The performance of end-to-end wireless link congestion control algorithm in the vehicular internet of things network is plagued by the inherent limitations of spurious rate control initiation, slow convergence time, and fairness disparity. In this article, the delay assisted rate tuning (DART) approach is proposed for the vehicular network that implements two algorithms, utilization assisted reduction (UAR) and super linear convergence (SLC), to overcome the transmission control protocol (TCP) limitations. The UAR algorithm is responsible for initiating the proportionate rate control process based on the bottleneck prediction parameter, thereby regulating the needless rate control during non-congested losses. In the congestion recovery mode, the SLC algorithm executes a dynamic rate update mechanism that enhances the flow rate and minimizes bandwidth sharing disparity among TCP flows. An analytical model was developed to study the DART convergence rate and fairness performance against the existing algorithm. The vehicular simulation outcome also confirms significant enhancement in average transmission rate, average message latency, and average bandwidth sharing performances of the DART algorithms against the RFC 6582, TCP-LoRaD, and CERL + congestion avoidance algorithms under varying traffic flows and node movement scenarios. [ABSTRACT FROM AUTHOR]

Predicting urban crowd flow spatial distributions plays a critical role in optimizing urban public safety and traffic congestion management. The spatial dependency between regions and the temporal dynamics of the local crowd flow are two important features in urban crowd flow prediction. However, few studies considered geographic characteristic in terms of spatial features. To fill this gap, we propose an urban crowd flow prediction model integrating geographic characteristics (FPM-geo). First, three geographic characteristics, proximity, functional similarity, and road network connectivity, are fused by a residual multigraph convolution network to model the spatial dependency relationship. Then, a long short-term memory network is applied as a framework to integrate both the temporal dynamic patterns of local crowd flow and the spatial dependency between regions. A 4-day mobile phone dataset validates the effectiveness of the proposed method by comparing it with several widely used approaches. The result shows that the root mean square error decreases by 15.37% compared with those of the typical models with the prediction interval at the 15-min level. The prediction error increases with the crowd flow size in a local area. Moreover, the error reaches the top of the morning peak and the evening peak and slopes down to the bottom at night. [ABSTRACT FROM AUTHOR]

Segmentation of vehicles into images of road traffic with congested and unstructured traffic patterns is a challenging task. For the same, this paper presents a modified-UNet which segments the input image by the sequential encoding and decoding steps. The modified-UNet uses a number of convolutions, inception modules, and batch normalization to encode the image into feature map. The extracted map is decoded into segmented image by performing the transposed convolutions in different layers. To validate the performance, two publicly available datasets have been considered, namely autorickshaw and IDD-Lite. Performance of the proposed model has been analyzed against state-of-the-art segmentation models in terms of seven parameters, namely intersection over union, accuracy, error, specificity, sensitivity, F1-score, and correlation-coefficient. Furthermore, ablation experiments have also been conducted. Experimental results depict that the proposed model outperforms the other models and reported the best IoU-Scores of 0.82 and 0.61 on autorickshaw and IDD-Lite datasets respectively. [ABSTRACT FROM AUTHOR]

In order to improve the traffic visualization management technology of smart cities, this paper applies machine learning to smart traffic management, and uses machine learning methods to process and analyze traffic data generated in smart cities. Moreover, this paper uses it to understand the distribution law of traffic data and the internal connections between data, excavate traffic characteristics in smart cities, and accurately predict the future traffic situation, so as to solve the problems of traffic congestion and route planning in smart cities. Moreover, this paper combines improved machine learning algorithms to construct a traffic visualization management system, and designs experiments to verify the performance of the system proposed in this paper. It can be seen from the experimental research results that the method proposed in this paper can play an important role in the traffic management of smart cities. [ABSTRACT FROM AUTHOR]

Traffic management continues to be one of the most critical challenges facing smart cities. Timely detection of incidents plays an important role in reducing fatality rates, avoiding congestion and improving traffic conditions. Currently, traditional traffic event detection approaches often rely on one source of data, such as road sensor readings or social media posts. However, there is a need for new approaches that can combine these channels and benefit from the diversity of the collected data for better event detection performance. This paper presents a new framework for near real-time event detection based on the fusion of sensor readings and social media data. The shapelets technique, used for sensor readings, generates sub-sequences of the time series representing distinctive patterns. Each pattern is called a shapelet and is selected based on the maximal differentiation achieved between the different classes of a time series set. In traffic events, shapelets can represent patterns of incidents/congestion as well as normal traffic situations that the framework utilizes to detect the occurrence of events. Similarly, social media posts can be featured as shapelets to enable the combination of both media channels creating a multi-modal solution. In the proposed framework, two pipelines are defined : sensor readings detection pipeline and social media detection pipeline. In addition, two multi-modal fusion techniques based on Shapelet Transform are suggested and compared, namely early fusion and late fusion. They help in combining the two pipelines either at the data level or at the decision level. Validation using the M25 London Circular road data shows that early fusion of both sources has better detection rate and better performance over late fusion. [ABSTRACT FROM AUTHOR]

To improve the efficiency of the traffic signal control and alleviate traffic congestion, many researchers focus on applying deep reinforcement learning (DRL) for traffic signal control systems (TSCS). The TSCS consider all the vehicles' waiting time around the intersection and decrease them so as to alleviate the traffic congestion. However, it has been confirmed that the DRL model is vulnerable to backdoor attacks. In this paper, we propose the first backdoor attack against DRL based TSCS. We define a special drive behavior as malicious input (called trigger). Once the trigger is activated via an attacker, the TSCS will only take into waiting time for the attacker's vehicle at the intersection. Our empirical experiments show that our proposed backdoor attacks are effective with negligible impact on TSCS's normal operation. [ABSTRACT FROM AUTHOR]

With the gradual increase of commercial banks and the expansion of their branches, the demand for cash transportation inflates sharply, bringing opportunities to the business development of Cash-In-Transit (CIT) sectors. However, the branches are often distributed in densely populated areas where traffic jams occur from time to time, which poses a severe challenge to the route planning of CIT vehicles. In addition, risk factors need to be considered during the optimization process because the goods transported belong to valuables. In order to effectively deal with the routing problem of CIT sectors, this paper established a bi-objective model and a goal programming model of Risk-Constrained Multi Depot Vehicle Routing Problems (RCMDVRPs) using real-time traffic data. Based on the traditional genetic algorithm, a Hybrid Genetic Algorithm with Intensification procedures (HGAI) is proposed to solve the goal programming model by using a three-level linked list structure to express chromosomes visually. Then, a new Self-constrained Hybrid Genetic Algorithm (SHGA) is designed for the bi-objective model. Besides, an online path updating strategy is developed to guide remote vehicles against time-dependent traffic flows. Finally, the HGAI is performed on benchmark instances to verify its accuracy. Experimental results of performance test show that the algorithm can achieve a gap of about 3% compared with the Best Known Result (BKR). The results of a case study also show that the two models and the corresponding algorithms are feasible and can be used to solve large-scale problems according to the special preferences and goals of decision-makers. [ABSTRACT FROM AUTHOR]

Predicting traffic accident duration is necessary for ensuring traffic safety. Several attempts have been made to achieve high prediction accuracy, but researchers have not considered traffic accident text data in much detail. The limited text data of the first report on an incident describes the characteristics of an accident that are initially available. This paper uses text data fusing and ensemble learning algorithms to build a model to predict an accident's duration, and a preprocessing scheme of accident duration text data is established. Next, the random forest (RF) algorithm is applied to select feature variables of text data related to the traffic incident duration. Last, a text feature vector is introduced to models such as decision tree, k nearest neighbor, support vector regression, random forest, Gradient Boosting Decision Tree, and Xtreme Gradient Boosting. Our results show that the improved RF model has good prediction accuracy with RMSE, MAPE and R2. From this, the textual factors important to determining the duration of the accident are identified. Further, we investigated that the cumulative importance of 60% is sufficient for traffic accident prediction using text data. These results provide insights into minimizing traffic congestion related to accidents and contribute to the input optimization in text prediction. [ABSTRACT FROM AUTHOR]

The increasingly crucial role of human displacements in complex societal phenomena, such as traffic congestion, segregation, and the diffusion of epidemics, is attracting the interest of scientists from several disciplines. In this article, we address mobility network generation, i.e., generating a city's entire mobility network, a weighted directed graph in which nodes are geographic locations and weighted edges represent people's movements between those locations, thus describing the entire mobility set flows within a city. Our solution is MoGAN, a model based on Generative Adversarial Networks (GANs) to generate realistic mobility networks. We conduct extensive experiments on public datasets of bike and taxi rides to show that MoGAN outperforms the classical Gravity and Radiation models regarding the realism of the generated networks. Our model can be used for data augmentation and performing simulations and what-if analysis. [ABSTRACT FROM AUTHOR]

Bifurcation of traffic flow involves complex dynamic characteristics of the system. In order to understand the complex traffic phenomenon, this work designed a macro traffic model considering the driver's memory which plays an important role in the traffic flow. Based on this model, we investigate the effects of the driver's memory and wave velocity on the stability of the traffic flow. By means of one and two parameter bifurcation analysis, we explore how these parameters affect the bifurcation structure of the system, and further investigate the dynamic mechanisms of traffic flow. We explain various traffic phenomena related to the different types of equilibrium points and limit cycles by phase plane analysis. We also study how the initial density and bifurcation structure affect the energy consumption in the system. The results show that the driver's memory and wave velocity play an important role in the stability of the traffic flow. By considering the change of bifurcation structure, we can better understand the source of traffic congestion, and further predict and control the possible traffic congestion. [ABSTRACT FROM AUTHOR]

Global urbanization has vastly enhanced the quality of people's lives in various domains. Nevertheless, the global rise in urban dwellers is often accompanied by additional difficulties and challenges such as traffic jams, air pollution, greenhouse gas emissions, and waste production. The term 'Smart City' is introduced to address these challenges by pushing residents to concentrate on the innovative solutions for economic growth of their cities as well as enhancing people's standard of living. The distributed ledger technology, also known as Blockchain, is best known for its instrumental role in forming the cryptocurrency space (e.g. Bitcoin and Ethereum). Due to features that include decentralization, transparency, democracy, security, and immutability; the deployment of Blockchain technologies in smart cities drastically improves data integrity, openness in city maintenance, and fosters the execution of reliable, transparent, safe, and democratized services and applications. In this survey, we perform an exhaustive study of research works that include the use of Blockchain technologies for smart city services and applications. First, we will examine the brief history of smart cities and Blockchain. We will then delve into the various ways that Blockchain technologies can be integrated into various smart city domains that include smart governance, smart transportation, smart grids, smart management, trade & finance, smart healthcare, smart home, e-commerce, and others that have a scope of development. Finally, this paper will provide areas of interest where Blockchain can be analyzed further to promote the development of smart cities application and services using Blockchain. [ABSTRACT FROM AUTHOR]

Autonomous driving has attracted significant research interests in the past two decades as it offers many potential benefits, including releasing drivers from exhausting driving and mitigating traffic congestion, among others. Despite promising progress, lane-changing remains a great challenge for autonomous vehicles (AV), especially in mixed and dynamic traffic scenarios. Recently, reinforcement learning (RL) has been widely explored for lane-changing decision makings in AVs with encouraging results demonstrated. However, the majority of those studies are focused on a single-vehicle setting, and lane-changing in the context of multiple AVs coexisting with human-driven vehicles (HDVs) have received scarce attention. In this paper, we formulate the lane-changing decision-making of multiple AVs in a mixed-traffic highway environment as a multi-agent reinforcement learning (MARL) problem, where each AV makes lane-changing decisions based on the motions of both neighboring AVs and HDVs. Specifically, a multi-agent advantage actor-critic (MA2C) method is proposed with a novel local reward design and a parameter sharing scheme. In particular, a multi-objective reward function is designed to incorporate fuel efficiency, driving comfort, and the safety of autonomous driving. A comprehensive experimental study is made that our proposed MARL framework consistently outperforms several state-of-the-art benchmarks in terms of efficiency, safety, and driver comfort. [ABSTRACT FROM AUTHOR]

We propose in this article a linear quadratic regulation model for urban road networks. The model combines semi-decentralization of the control with the additive conflict flow model. The idea is to consider a centralized optimal control for the traffic, where optimal split times are determined for the traffic lights. We then relax the centralization to some optimally chosen times windows, during which main streams get green lights and are considered as priority streams, while secondary ones get yellow lights and are considered as non-priority streams. We assume that during such time periods, the traffic is managed locally at each intersection, by applying the additive conflict flow model. By this semi-decentralization, we aim to relax the rigid central control (Red/Green) during the free flow time periods. We simulate our traffic control model numerically using the simulator SUMO (Simulation of Urban Mobility), and illustrate the results on some selected traffic scenarios. The results show that our proposed model increases the capacity of the road network by more than 800 vehicles per hour, compared to the semi-decentralized control model. This performance proves clearly the effectiveness of our approach. [ABSTRACT FROM AUTHOR]

With traffic network becoming increasingly complicated, traffic flow prediction has important practical significance for the management of traffic roads and public safety. For example, an accurate taxi demand prediction can help to improve efficiency of vehicle scheduling and reduce traffic congestion. The main issue of flow prediction is how to extract the information of complex spatio-temporal dependencies and interactions between arrival and departure. To solve these problems, we develop a deep learning method based on time-dependent attention convolutional LSTM (TDAConvLSTM) in which a time-dependent attention mechanism is designed to learn similarities of historical traffic flows among different time intervals and a fusion mechanism is introduced to aggregate the feature information produced by convolutional LSTM and attention module. And then, the result of the feature aggregation is fed to a multi-layer deconvolutional network to gain the results of flow prediction. Experimental studies on two real-life datasets indicate that TDAConvLSTM achieves better results than the compared models. The source code of our proposed method is available at the URL1. [ABSTRACT FROM AUTHOR]

Ridesharing has become popular over the last decade, bringing significant changes to residents' travel patterns and city traffic. Relevant to the growth and impact of ridesharing activities in populous urban areas are the side effects, such as air pollution and traffic congestion. Despite a number of studies on these side effects, few have focused on their underlying causes and explained the behavioral incentive. Drawing on the theory of averting behavior, this paper investigates the ridesharing choices of individuals who face but would prefer to avoid ambient air pollution. Such air pollution–averting behavior tends to increase the demand for ridesharing services, which further results in more motorized traffic and pollutant emissions. Utilizing trip records from DiDi company and data on air pollutants in Haikou, China, we find that an additional 10 μg/m3 of PM2.5 leads to an increase of 2.6% in the count of DiDi trip orders. Results also show that traffic congestion increases due to elevated DiDi usage and the effect varies with time. This could further worsen the air quality and bring other potential side effects. These empirical results offer unique insights into the impact of air pollution on ridesharing and traffic from the perspective of individual behavioral motivation. [ABSTRACT FROM AUTHOR]

Temporal networks are an effective way to encode temporal information into graph data losslessly. Finding the bursting cohesive subgraph (BCS), which accumulates its cohesiveness at the fastest rate, is an important problem in temporal networks. The BCS has a large number of applications, such as representing emergency events in social media, traffic congestion in road networks and epidemic outbreak in communities. Nevertheless, existing methods demand the BCS lasting for a time interval, which neglects the timeliness of the BCS. In this paper, we design an early bursting cohesive subgraph (EBCS) model based on the k-core to enable identifying the burstiness as soon as possible. To find the EBCS, we first construct a time weight graph (TWG) to measure the bursting level by integrating the topological and temporal information. Then, we propose a global search algorithm, called GS-EBCS, which can find the exact EBCS by iteratively removing nodes from the TWG. Further, we propose a local search algorithm, named LS-EBCS, to find the EBCS by first expanding from a seed node until obtaining a candidate k-core and then refining the k-core to the result subgraph in an optimal time complexity. Subsequently, considering the situation that the massive temporal networks cannot be completely put into the memory, we first design an I/O method to build the TWG and then develop I/O efficient global search and local search algorithms, namely I/O-GS and I/O-LS respectively, to find the EBCS under the semi-external model. Extensive experiments, conducted on four real temporal networks, demonstrate the efficiency and effectiveness of our proposed algorithms. For example, on the DBLP dataset, I/O-LS and LS-EBCS have comparable running time, while the maximum memory usage of I/O-LS is only 6.5 MB, which is much smaller than that of LS-EBCS taking 308.7 MB. [ABSTRACT FROM AUTHOR]

In order to solve the problem of traffic congestion in a certain area, this paper develops a set of traffic optimization decision system. For analyzing the actual traffic conditions and calculating the traffic volume, density and traffic speed, a traffic prediction model is established and updated iteratively to modify the prediction model parameters. Based on this model, the congestion degree is estimated at the current road section, thus, an intelligent decision-making and the coordinated optimization methods are proposed. Moreover, this paper implements some application experiments on the isometric road of a three-intersection and obtains better prediction results of traffic density and traffic speed on the three-section highway. At the same time, compared with other existing prediction methods, the prediction model presented in this paper not only has higher accuracy, shorter prediction time and stronger anti-interference ability, but also has better effect on vehicle diversion. In addition, it also greatly relieves the traffic pressure on the road, maximizes the complementary advantages between intersections, and balances the good cooperation between each intersection. [ABSTRACT FROM AUTHOR]

When an emergency vehicle approaches form behind, the driver must change his/her lane to the left lane and pull over to gave way to the emergency vehicle. However, in most cases the abrupt lane change maneuver of the vehicles in front of the emergency vehicle will cause a traffic congestion, and the emergency vehicles must decelerate as a result. To avoid the above situation, we designed a lane change algorithm based on a look-ahead concept for the vehicle driving in front of the emergency vehicle (defined as the ego vehicle). To reduce calculation load, a rule-based control method is adopted to control the longitudinal motion and a cosine function is adopted to control the lateral motion of the ego vehicle. This lane change algorithm allows the ego vehicle to choose a gap in the left lane or the right lane to merge to as soon as possible, and to change its lane safely without affecting the surrounding vehicles. The objective of the control method is to let the emergency vehicle pass smoothly without deceleration in congested traffic condition. A computer simulation was conducted to validate the effectiveness of the proposed method. The simulation results for 1000 initial conditions show that, for 720 initial conditions the proposed method manages to merge the ego vehicle effectively without collision, and the emergency vehicle does not need to slow down. Compared with a lane change control method without look-ahead concept, the proposed method increases the number of successful lane change maneuver by 555 cases. [ABSTRACT FROM AUTHOR]

Accurate traffic flow prediction plays a significant role in urban traffic management, including traffic congestion control and public travel route planning. Recently, several approaches have been put forward to learn the patterns from historical traffic data. However, there exist some limitations resulting from the use of the static learning method to explore the dynamical characteristics of the road network. Besides, the dynamic global temporal and spatial properties are not considered in these models. These drawbacks lead to a low prediction performance and make applying to a more extensive road network challenging. To address these issues, from the inspiration of Chebyshev polynomial, we proposed an improved dynamic Chebyshev graph convolution neural network model called iDCGCN. In the proposed approach, a novel updating method for the Laplacian matrix, which approximately constructs features from different period data, is proposed based on the attention mechanism. In addition, a novel feature construction method is proposed to integrate long-short temporal and local-global spatial features for complex traffic flow representation. Experimental results have shown that iDCGCN outperforms the state-of-the-art GCN-based methods on four real-world highway traffic datasets. [ABSTRACT FROM AUTHOR]

With ongoing urbanization, traffic congestion and the air pollution it induces are worsening. Using a system dynamics (SD) approach, this study constructed a driving-restriction policy model to explore the effects of different stages of policy implementation on variables such as traffic congestion, emissions, and parking demand. Medium- and long-term dynamic simulation showed that the effect of the policy was obvious in the initial stage but gradually weakened in the medium term, leading to a "fading" effect on traffic-congestion alleviation; a "rebound" effect was even observed at the end of the simulation. Thus, the policy will not effectively reduce traffic congestion in the long term and will induce a new demand for car purchases, resulting in paradoxical effects, which will aggravate parking demand, congestion, and pollution. Yet, it was also found that introducing penalty policies and an air pollution charging fee could weaken the paradoxical effects and compensate for some defects of the policy. Such strategies could help reduce emissions, traffic congestion, parking demand, the number of illegal trips, and the overall number of vehicle trips. These findings can provide not only a theoretical basis for further research but also practical guidance for policy improvement. [ABSTRACT FROM AUTHOR]

The vehicular ad hoc network, combined with the distribution of roadside units (RSUs), play a significant role in reducing accidents and traffic jams by sending warning and emergency messages to drivers in real-time. However, communication is not always available owing to the lack of RSUs, reliability of data access and control, to avoid such problems we have proposed a new strategy for the deployment of least possible number of RSUs by developing a support protocol in case of loss of communication that relies on smartphones. The simulation results show that the proposed distribution method clearly reduces the number of RSUs required (compared to existing methods), and contributes towards increased coverage, reduced costs, and less missing data. [ABSTRACT FROM AUTHOR]

Traffic waves occur when the density of vehicles exceeds a critical threshold, and traffic management draws more and more attention due to the increasing need to alleviate traffic congestion in metropolises. In the present study, energy–energy flux models were introduced into the modeling of start and stop waves of vehicles, based on analysis of characteristics of traffic waves. An indicator system was established to evaluate the service quality of single-signalized intersections. The results showed that under given time costs the service quality was negatively correlated to the energy and the absolute value of energy flux of the stop wave, which highlights the need to optimize the time cost. To this end, we built a stop-wave time cost model on the basis of the energy–energy flux models and simulation data. The model was then optimized by the formulation of a multi-objective optimization problem that can be solved by adjusting the parameters of the fgoalattain function in Matlab. It was found that under certain constraints, the optimal service quality was achieved when the traffic signal cycle length was 150 s and green/cycle ratio was 0.5; with the aid of optimization, the average energy density of the stop wave reduced by 37.10%, while the energy flux density increased by 1.50%. Additionally, the Elman algorithm was employed to forecast the energy and energy flux of the stop wave, the forecast error of which was controlled within 5% under the optimal time cost. A visualization window to monitor the single-signalized intersection was produced to improve the service quality. It is therefore expected that main findings from current study may contribute to promoting construction of intelligent traffic management systems. [ABSTRACT FROM AUTHOR]

Effective measures to improve road accessibility during storms are required as traffic congestion caused by storm floods increasingly constrains the efficiency of urban commuting. However, flood impacts on urban road connectivity are not yet well assessed due to inaccurate simulation of flood processes in urban areas where high-resolution data for drainage networks and gauged hydrological data are insufficient. Thus, this study assesses flood impacts on road network connectivity in an urban area of southern China through joint modeling of 1-D hydrodynamic processes in drainage networks and 2-D flood inundation processes on roads using MIKE Urban and MIKE 21. High-resolution DEM images of 5 m and a drainage network of 5635 pipelines were used for urban hydrological simulation. Flood depths were gauged for model calibration and validation by recruited volunteers in the context of citizen science. The results show that road network connectivity decreases as rainfall increases. More than 40% of road connectivity is lost in the study area when a 1-in-100-year return period rainfall occurs. The study results can help to inform more adaptive strategies for local flood control. The study methods are also applicable to improving urban hydrological modeling in broader regions. [ABSTRACT FROM AUTHOR]

Traffic congestion, accidents, and pollution are becoming a challenge for researchers. It is essential to develop new ideas to solve these problems, either by improving the infrastructure or applying the latest technology to use the existing infrastructure better. This research paper presents a high-resolution dataset that will help the research community to apply AI techniques to classify any emergency vehicle from traffic and road noises. Demand for such datasets is high as they can control traffic flow and reduce traffic congestion. It also improves emergency response time, especially for fire and health events. This work collects audio data using different methods, and pre-processed them to develop a high-quality and clean dataset. The dataset is divided into two labelled classes one for emergency vehicle sirens and one for traffic noises. The developed dataset offers high quality and range of real-world traffic sounds and emergency vehicle sirens. The technical validity of the dataset is also established. Measurement(s) Ambulance Siren and Road Noises. (Recordings) Technology Type(s) Microphone Sample Characteristic - Environment Roads Sample Characteristic - Location Pakistan [ABSTRACT FROM AUTHOR]

Traffic congestion is one of serious problems in cities; rainfalls would exacerbate traffic congestion, and thus result in huge economic losses. However, limited studies focused on how rainfalls influenced traffic congestion and its associated economic losses. Based on detailed hourly data, we estimated how traffic congestion index (TCI) changed with different rainfall intensities in the Beijing-Tianjin-Hebei (BTH) region, and we also explored their economic losses. The results illustrated that all cities presented the similar trend of daily traffic congestion, and morning peak occurred 2 h later on holidays than workdays. Rainfall had significant impacts on traffic congestion for most time windows, except midnight. Traffic congestion increased with rainfall intensities, but smaller cities were more vulnerable to rainfall intensity than megacities. Rainfalls led to 0.95 billion yuan of extra economic losses in 2019, 38% of which occurred under heavy rainfalls. Traffic congestion in 2019 caused a total economic cost of 30.08 billion yuan in the BTH region (0.4% of its GDP), including the recurrent cost and economic losses due to rainfalls; besides, the social cost and direct cost contributed the same share of 49.5%, with 1% from the environmental costs. Considering future urban development and climate change, it is beneficial to establish the climate-resilient transportation system for avoiding future serious traffic congestion as well as huge economic losses in future. [ABSTRACT FROM AUTHOR]

Taxis play an important role in urban transportation system. Efficient taxi cruising strategies are helpful to alleviate urban traffic congestions, reduce pollution emission, attenuate greenhouse gas, and also provide a fast service for passengers. However, in real scenarios, taxis cruising strategies are mostly based on their own experiences. At unfamiliar urban areas or during off-peak hours, drivers usually have no good idea for an optimal cruising strategy, which causes a low efficiency for service and also increases taxi operation costs. Considering that it is difficult to construct an analytical model for the taxis scheduling and cruising, in this paper, we put forward a data-driven model for multi-taxis cruising based on reinforcement learning. Furthermore, an evolutionary reinforcement learning method is proposed, which aims at improving the exploration of reinforcement learning and enhancing reinforcement learning to maximize the global reward in multi-agent tasks. In the experimental part, two other kinds of deep Q-learning methods and a roaming strategy are employed in the comparisons. The results demonstrate the superiority of our proposed algorithm. [ABSTRACT FROM AUTHOR]

In recent years demand for high speed and robust wireless networks are increasing due to the growth of accessing social networks from mobiles and computer systems. The recent solution for this is used by Fiber-Wireless (FiWi) network which it can provide the high throughput for end users. FiWi supports the mobility of wireless networks as well as high bandwidth of optical networks. But the major problem with these networks is as the number of mobile user's increases, queuing delay is increasing at FiWi's Optical Network Unit (ONU). Increasing queuing delay resulted into decreasing the throughput performance of FiWi networks. Hence, it is required to have efficient queuing method at ONU to allocate bandwidth efficiently to get high speed performance of FiWi; one of such methods is called as Dynamic Bandwidth Allocation (DBA). To solve the problem of increasing delay in FiWi networks due to increasing number of users, connection patterns and traffic congestion, in this work we proposed a multilevel, multi-queue based DBA method, so it is called Multilevel Multi-queue DBA. The innovation of the proposed method compared to previous methods provides a complete multilevel framework for reducing delays to an acceptable level. In proposed method, every ONU is configured with three levels of priority queues. The real time data is placed into the queue which is having the highest priority queue, while the non-real-time data is placed into other two queues depending on the threshold values set for them. This algorithm works according to different TDMA slots (those are treated as levels) in order minimize the congestion in FiWi Networks, so it can help to minimize the queuing delay performance. The proposed method is simulated and evaluated using MATLAB simulator. From the simulation results, it is showing that proposed DBA method is having better performance in terms of queuing delay and packet delivery ratio as compared to existing methods. The performance of FiWi networks is increased by 60% for proposed DBA approach whereas throughput is increased by 55% as compared to existing DBA method. The simulation results also show that queuing delay is minimized by 30% as compared to existing DBA method. [ABSTRACT FROM AUTHOR]

In this paper, the effect of utilizing urban buses with either outdated or modern environmental technologies on the air pollution of Arak city is modeled. Arak is an industrial city with population and traffic congestion; hence, such modeling is of paramount significance. Here, the roads with heavy traffic are modeled and the PM2.5 pollutants emitted by light and heavy vehicles in the rush hours over the entire 365 days of the year were contemplated. Three different cases of only light vehicles, 2 light vehicles and EURO3 urban buses, and 3 light vehicles and EURO4 urban buses were considered. All required data including synoptic and upper air meteorological data, topography data and mobile source data are utilized for modeling. For modeling vehicle-caused emission, all traffic data including type of the vehicle, number of vehicles and quality of traffic were used. Results showed that urban busses are highly influential on the PM2.5 pollutants in Arak city. In the presence of EURO3 and EURO4 urban buses, the concentration exceeds 5 and 10 times the standard level, respectively. Moreover, with the replacement of EURO3 urban buses with their EURO4 rivals, the number of polluted days over the period of a year would decrease from 26 to 10 days. [ABSTRACT FROM AUTHOR]

Accurate traffic flow prediction is crucial for the development of intelligent transportation. It can not only effectively avoid traffic congestion and other traffic problems, but also provide a data basis for other complex tasks. The rapid development of social technology and the increasingly complex traffic environment lead to the emergence of massive traffic data. Traffic flow prediction as a spatial-temporal prediction problem has been widely concerned, but the traditional forecasting methods often ignore the spatial-temporal dependence, difficult to meet the prediction requirements. Therefore, this paper proposes a novel spatial-temporal model based on an attention one-dimension convolutional neural network (1D-CNN) and a gated interpretable framework, which models historical traffic data from the perspectives of time and space respectively. The core of the model proposed in this paper is to construct spatial-temporal blocks. First, a 1D-CNN based on channel attention mechanism and "inception" structure is proposed to extract temporal correlation. Then, considering the complexity of the actual traffic network, an interpretable multi-graph gated graph convolution framework is proposed to extract the spatial correlation. Finally, extensive experiments are carried out on real data sets, which prove the effectiveness of the proposed model, and it is very competitive compared with some state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Increasing traffic congestion is a major obstacle to the development of cities. The prediction of traffic flow is very important to city planning and dredging. A good model of flow is able to accurately predict future flow by learning historical flow data. Traffic flow is usually affected by macro and micro factors. At the macro level, the whole city can be divided into different subregions according to the similarity in the traffic flow patterns. At the micro-level, there is a temporal and spatial correlation between the traffic flow of different road sections at di fferent times. In this paper, we propose a multi-mode traffic flow prediction method with Clustering based Attention Convolution LSTM (CACLSTM) to model spatial-temporal data of traffic flow. The framework includes three modules: a convolution LSTM encoding-decoding layer which is used to predict the traffic flow of the next time slice by encoding the historical traffic information, a clustering based attention layer which is able to extract different temporal features by clustering based attention, and an additional factors layer which can integrate weather, wind speed, holidays and other factors to improve the prediction accuracy. The experimental results on Beijing taxis data show that the CACLSTM method performs more effective than the six well-known compared methods. [ABSTRACT FROM AUTHOR]

With the acceleration of urbanization, traffic congestion and vehicle exhaust pollution are becoming increasingly serious problems. Focusing on the problem of urban pollution from vehicle exhaust, this study used system dynamics to establish an urban congestion mitigation and emission-reduction management model. Specifically, a nonlinear function that integrates system dynamics and a non-homogeneous discrete grey model (SD-NDGM) was used to construct an algorithm, which improved the accuracy of the model. Thereafter, the mid- and long-term effects of the restriction policy were explored. The main findings from dynamic model simulations were as follows: All types of restrictions alleviated traffic congestion to varying degrees, but "odd and even" restrictions had more obvious effects, with an average annual reduction rate of 43.53% in the number of motor vehicle trips. The driving-restriction policy had a time effect, significantly reducing the number of vehicle trips in the short term. However, it could have negative effects in the long term (e.g., agglomeration effect, emission-reduction paradox), and it does not fundamentally solve traffic and environmental problems. Thus, it could only be used as a phased policy, not a long-term measure. The purchase-restriction policy controlled excessive increases in the number of private cars, but it had little effect in terms of solving environmental problems. Compared with a single policy, the combination of public-transport development and driving-restriction policy not only reduced traffic congestion, air pollution, and air quality health indexes by 29.13%, 52.63%, and 54.63%, respectively, but also improved environmental carrying capacity by 294.26%. A combined approach can therefore be said to have certain benefits for society, health, and the environment. [ABSTRACT FROM AUTHOR]

When imposing traffic congestion pricing around downtown commercial centers, there is a concern that commercial activities will have to consider relocating due to reduced demand, at a cost to merchants. Concerns like these were important in the debates before the introductions of congestion charges in both London and Stockholm and influenced the final policy design choices. This study introduces a sequential experimental game to study reactions to congestion pricing in the commercial sector. In the game, merchants first make location choices. Consumers, who drive to do their shopping, subsequently choose where to shop. Initial responses to the introduction of congestion pricing and equilibrium selection adjustments over time are observed. These observations are compared to responses and adjustments in a condition where congestion pricing is reduced from an initially high level. Payoffs are non-linear and non-transparent, making it less than obvious that the efficient equilibrium will be selected, and introducing possibilities that participants need to discover their preferences and anchor on past experiences. We find that initial responses reflect standard inverse price–demand relations, and that adjustments over time rely on signaling by consumers leading to the efficient equilibrium. There is also evidence that priming from initial experiences influence play somewhat. We confirm that commercial activities relocate following the introduction of congestion pricing and that the adjustment process is costly to merchants. [ABSTRACT FROM AUTHOR]

Traffic congestion in urban areas poses several challenges to municipal authorities including pollution, productivity loss, reckless driving, and delays in dealing with emergencies. Smart cities can use modern IoT infrastructure to solve the congestion problem and reduce pollution and delays. In this article, we focus on congestion mapping and mitigation for emergency vehicles in smart cities. We use a novel traffic light control technique to change the flow of cars on lights of interest thereby making way for emergency vehicles. We use a simulation model for a selected area of Manhattan to implement congestion mapping and to help find the fastest path for routing emergency vehicles based on the congestion metrics. The system controls traffic lights to block off the roads feeding into congestion and allows flow away from the congested path. This helps in clearing the preferred route to help emergency vehicles reach the destination faster. We show that the proposed algorithm can map congestion on city roads with accuracy thus helping to improve the response time of the emergency services and saving precious lives. [ABSTRACT FROM AUTHOR]

In marine container drayage (CD), which refers to the transport of goods over a short distance, empty containers (ECs) are required to be transported long distances between a terminal and a shipper/consignee by conventional transportation. This causes truck traffic congestion in harbor districts that increases CO2 emissions (CO2EM). This study addresses the vehicle dispatch problem with respect to the environmental impact of marine CD, considering the tractor dwell time is long at the customer site due to cumbersome container loading/unloading (L/U). We model this problem as an extended version of the vehicle routing problem with precedence constraints to minimize the total CO2 weighted travel distance. To improve CD operation in long L/U time, we propose a new practice for CD operations. Additionally, we develop a mixed integer programing model (MIP) for the new practice representation, and propose a Simulated Annealing (SA) based heuristic approach to solving the new practice instance. By implementing our proposed new operation, in a long L/U time, the CO2EM, EC move and number of tractors required can also be reduced by allowing uncoupled tractor move. [ABSTRACT FROM AUTHOR]

With the acceleration of urbanization construction, the contradiction between supply and demand of urban public transportation resources is becoming increasingly prominent, resulting in increasingly serious problems such as traffic congestion and environmental pollution, which has a great impact on the sustainable development of cities. The experience of mature markets both domestically and internationally indicates that priority must be given to the development of public transportation networks with rail transit as the backbone. Due to the fact that the operation of the rail transit system should not only focus on market benefits but also meet social benefits as much as possible, evaluating efficiency has become a prerequisite for managing rail transit and an important topic in the performance evaluation of urban public transportation. The urban public transport operations evaluation is a multiple-attribute group decision-making (MAGDM). Then, the TODIM and EDAS method has been constructed to deal with MAGDM issues. The interval neutrosophic sets (INSs) are constructed as an effective tool for representing uncertain information during the urban public transport operations evaluation. In this manuscript, the interval neutrosophic number TODIM-EDAS (INN-TODIM-EDAS) method is constructed to solve the MAGDM under INSs. Finally, a numerical example study for urban public transport operations evaluation is constructed to validate the INN-TODIM-EDAS method. The main research contribution of this paper is constructed: (1) the INN-TODIM-EDAS method is put up for MAGDM with INSs; (2) the INN-TODIM-EDAS method is put up for urban public transport operations evaluation and were compared with existing methods; (3) Through the detailed comparison, it is evident that INN-TODIM-EDAS method for urban public transport operations evaluation proposed in this paper are effective. [ABSTRACT FROM AUTHOR]

Enhancing the task offload performance of UAV-assisted Vehicular Edge Computing Networks (VECNs) is complex, especially in vehicle-to-everything (V2X) applications. These networks rely on UAVs and roadside units (RSUs) to offload heavy computational tasks and reduce the load on the on-board systems. However, UAV-assisted VECNs face severe challenges from heterogeneous offload node resources and dynamic edge network environments in providing low-latency and high-response task offloading, especially during traffic congestion or infrastructure failures. In this paper, we propose a digital twin (DT)-driven task offloading framework for UAV-assisted VECNs. The aim of the proposed framework is to improve the global performance of VECN task offloading under limited computational and communication resource constraints. Firstly, we construct a decentralized offloading decision-centralized evaluation task offloading framework for UAV-assisted VECNs based on the asynchronous advantage actor-critic (A3C) algorithm. Secondly, we integrate the graph attention networks (GAT) into the framework to incorporate the dynamically changing DT network topology information into the state evaluation of VECNs. By simulating a DT-driven multi-UAV cooperative system and comprehensive evaluation of real-world task request datasets. The framework has a better task throughput rate and stability when performing task offloading in local resource overload and dynamic edge environment scenarios. [ABSTRACT FROM AUTHOR]

Improving bus travel time reliability can attract more commuters to use bus transit, and therefore reduces the share of cars and alleviates traffic congestion. This paper formulates a new bus travel time reliability metric that jointly considers two stochastic processes: the in-stop waiting process and in-vehicle travel time process, and the bus travel time reliability function is calculated by the convolution of independent events' probabilities. The new reliability metric is defined as the probability when bus travel time is less than a certain threshold and can be used in both conditions with and without bus transfer. Next, Automatic Vehicle Location (AVL) data of the city of Harbin is used to demonstrate the applicability of the proposed method. Results show that factors such as weather, day of the week, departure time, travel distance, and the distance from the boarding stop to the bus departure station can significantly affect the travel time reliability. Then, a case with low bus departure frequency is analyzed to show the impact of travelers' arrival distribution on their bus travel time reliability. Further, it is demonstrated that the travel time reliabilities of two bus transfer schemes of the same Origin–Destination (O–D) pair can have significantly different patterns. Understanding the bus travel time reliability pattern of the alternative bus routes can help passengers to choose a more reliable bus route under different conditions. The proposed bus travel time reliability metric is tested to be sensitive to the effect of different factors and can be applied in bus route recommendation, bus service evaluation, and optimization. [ABSTRACT FROM AUTHOR]

Recently Green Location-Routing Problem (GLRP) has been considered by many researchers. The GLRP includes location for depots and routing the vehicles simultaneously by considering environmental aspects. In this work an extension of GLRP in the presence of traffic congestion and based on variable speed is presented. The speed of vehicles (and hence the travel time), fuel consumption and environmental effects are not only dependent on the distance traveled but also they are dependent on the traffic congestion at a different time of the day, as well considered in this paper. For the addressed problem, a nonlinear mixed-integer programming formulation is delivered and then a set of preprocessing rules to linearize the formulation is done. The objective of the proposed model is to minimize the fixed cost of operating depots, delayed and early servicing penalties as well as the costs of the CO2 emissions and the fuel consumption. The amount of fuel consumption and emissions are measured by a widely used comprehensive modal emission model. In the end, a heuristic algorithm based on the PSO algorithm is proposed to solve generated test instances. Computational results over test instances confirm the proposed algorithm can find optimal or near-optimal solutions. [ABSTRACT FROM AUTHOR]

Enhancing the construction of transportation infrastructure is considered one of the viable pathways to ease traffic congestion and air pollution problems. To investigate whether increasing the level of transportation infrastructure construction can help reduce haze problem, a random-effects model is used to test the effects of haze reduction, based on inter-provincial panel data of 31 Chinese provinces from 2013 to 2017. The empirical results deliver several interesting findings. Firstly, enhancing transportation infrastructure construction has a statistically significant and positive impact on haze emission reduction; secondly, upgrading the industrial structure enhances this optimistic effect. Finally, improving transportation infrastructure construction shows more significant effects in haze reduction within highly polluted areas than lightly polluted cities. Therefore, to reduce haze pollution more effectively, China needs to improve the level of transportation infrastructure construction further and adopt a differentiated haze management strategy for high and low pollution areas. [ABSTRACT FROM AUTHOR]