Search

The increasing demand for mobility in our society poses various challenges to traffic engineering, computer science in general, and artificial intelligence in particular. Increasing the capacity of road networks is not always possible, thus a more efficient use of the available transportation infrastructure is required. Another issue is that many problems in traffic management and control are inherently decentralized and/or require adaptation to the traffic situation. Hence, there is a close relationship to multiagent reinforcement learning. However, using reinforcement learning poses the challenge that the state space is normally large and continuous, thus it is necessary to find appropriate schemes to deal with discretization of the state space. To address these issues, a multiagent system with agents learning independently via a learning algorithm was proposed, which is based on estimating Q-values from k-nearest neighbors. In the present paper, we extend this approach and include transfer of experiences among the agents, especially when an agent does not have a good set of k experiences. We deal with traffic signal control, running experiments on a traffic network in which we vary the traffic situation along time, and compare our approach to two baselines (one involving reinforcement learning and one based on fixed times). Our results show that the extended method pays off when an agent returns to an already experienced traffic situation. [ABSTRACT FROM AUTHOR]

Traffic systems play a key role in modern society. However, these systems are increasingly suffering from problems, such as congestions. A well-known way to efficiently reduce this kind of problem is to perform traffic light control intelligently through reinforcement learning (RL) algorithms. In this context, extracting relevant features from the traffic environment to support decision-making becomes a central concern. Examples of such features include vehicle counting on each queue, identification of vehicles' origins and destinations, among others. Recently, the advent of deep learning has paved to way to efficient methods for extracting some of the aforementioned features. However, the problem of identifying vehicles and their origins and destinations within an intersection has not been fully addressed in the literature, even though such information has shown to play a role in RL-based traffic signal control. Building against this background, in this work we propose a deep learning pipeline for extracting relevant features from intersections based on traffic scenes. Our pipeline comprises three main steps: (i) a YOLO-based object detector fine-tuned using the UAVDT dataset, (ii) a tracking algorithm to keep track of vehicles along their trajectories, and (iii) an origin-destination identification algorithm. Using this pipeline, it is possible to identify vehicles as well as their origins and destinations within a given intersection. In order to assess our pipeline, we evaluated each of its modules separately as well as the pipeline as a whole. The object detector model obtained 98.2% recall and 79.5% precision, on average. The tracking algorithm obtained a MOTA of 72.6% and a MOTP of 74.4%. Finally, the complete pipeline obtained an average error rate of 3.065% in terms of origin and destination counts. [ABSTRACT FROM AUTHOR]

This study aims to assemble and present the status of the published information available regarding pedestrian safety near crosswalks and bus stops through a comprehensive search of various databases. It focuses on the influence of crossing environment and bus stops, underlining land-use components, crosswalk quality, traffic control, placement of facilities, and other aspects of pedestrian crossing safety. It also offers a detailed discussion of various study designs and statistical modeling techniques implemented in this context over the years, followed by the suggested interventions to improve safety at such high-risk locations. The existing literature elucidates that traffic management strategies and designs have often prioritized the movement of motorized vehicles, resulting in higher risk to pedestrians. This is especially true for low- and middle-income countries. Also, previous research is mostly aligned with offering solutions with limited reference to the reported crash data. Thus, a holistic approach is needed to identify the contributing factors associated with fatal crashes, assess the safety performance at such locations, and thereby offer sustainable planning and design for pedestrian facilities. [ABSTRACT FROM AUTHOR]

The Traffic Locus of Control scale (T-LOC) serves as a measure of drivers' personality attributes, providing insights into their perceptions of potential causes of road traffic crashes (RTCs). This study meticulously evaluated the psychometric properties of the Arabic version of T-LOC (T-LOC-A) among Lebanese drivers. Additionally, the study aimed to explore associations between the T-LOC scale and various driving variables, including driver behavior, accident involvement, and traffic offenses. A cross-sectional study was conducted among Lebanese drivers using a face-to-face approach. The validation of the Arabic version of T-LOC (T-LOC-A) occurred through a two-stage process: translating and culturally adapting T-LOC in the first stage, and testing its psychometric properties in the second stage. Data were collected using a comprehensive self-reported questionnaire in Arabic, covering demographic and travel-related variables, risk involvement, and measures such as the Driver Behavior Questionnaire (DBQ) and T-LOC. Exploratory factor analysis and confirmatory factor analysis were performed to scrutinize the factorial structure of T-LOC. Pearson correlation and chi-square tests were used for continuous and categorical variables, respectively. Two logistic regression analyses were executed to probe associations between T-LOC and involvement in road traffic crashes (RTCs) and T-LOC subscales with the occurrence of traffic offenses. The study included 568 drivers, predominantly male (69%) and aged between 30 and 49 years (42.1%). The findings revealed that T-LOC-A exhibited robust psychometric properties, with excellent reliabilities (α = 0.85) and adherence to the original four-factor structure, encompassing self (α = 0.88), other drivers (α = 0.91), vehicle/environment (α = 0.86), and fate (α = 0.66). The multidimensional structure was statistically supported by favorable fit indices. Gender differences revealed men attributing responsibility to other drivers, while women leaned towards fate and luck beliefs. Regarding driver behavior, the "other drivers" and self-dimensions of T-LOC-A correlated positively with aggressive violations. The fate dimension showed positive associations with aggressive violations and lapses. The "other drivers" subscale correlated positively with errors, and the vehicle/environment subscale with lapses. External T-LOC factors were positively associated with accident involvement, while the "LOC self" factor emerged as a protective element. In terms of traffic offenses, "LOC fate" displayed a positive association, while the "LOC self" factor showed a protective effect. In conclusion, the Arabic T-LOC is a reliable and valuable instrument, suggesting potential improvements in driving safety by addressing drivers' locus of control perceptions. [ABSTRACT FROM AUTHOR]

In the field of traffic management and control systems, we are witnessing a symbiotic evolution, where intelligent infrastructure is progressively collaborating with smart vehicles to produce benefits for traffic monitoring and security, by rapidly identifying hazardous behaviours. This exponential growth is due to the rapid development of deep learning in recent years, as well as the improvements in computer vision models. These technologies allow for monitoring tasks without the need to install numerous sensors or stop the traffic, using the extensive camera network of surveillance cameras already present in worldwide roads. This study proposes a computer vision-based solution that allows for real-time processing of video streams through edge computing devices, eliminating the need for Internet connectivity or dedicated sensors. The proposed system employs deep learning algorithms and vision techniques that perform vehicle detection, classification, tracking, speed estimation, and vehicle geolocation. [ABSTRACT FROM AUTHOR]

When a work zone is located at an intersection, it greatly reduces the capacity and change the traffic flow characteristics. However, the impacts of work zones have not attracted much attention, and the signal control method of the intersection with a work zone has not been investigated yet. This paper focuses on a specific type of work zone, which is located within the area of an intersection. The saturation flow rate model, traffic wave model, traffic delay model, and emptying time model are proposed to capture the traffic flow characteristics of the intersection with an island work zone, and a signal control model is further put forward. The real data is collected to calibrate, validate, and evaluate the proposed models. The results indicate that the proposed signal control model can reduce about 15.6% of queue length and 17.2% of traffic delay for the intersection with an island work zone. [ABSTRACT FROM AUTHOR]

In recent years, high-resolution traffic signal event data has provided valuable insights into understanding and managing congestion at signalized intersections. While existing applications primarily employ automated traffic signal performance monitoring (ATSPM) systems as postanalysis tools for identifying everyday congestion causes, traffic engineers are increasingly overwhelmed by the number of ATSPM-capable intersections. The workload increases extensively as the number of ATSPM-capable intersections rises mainly due to the necessity of manually checking and generating performance figures. Nonetheless, an advanced ATSPM system capable of automatically detecting time-of-day congestion bottlenecks among multiple intersections and suggesting "top intersections of interest" would significantly aid traffic managers in monitoring historical congestion and preventing future congestion occurrences. This paper introduces an efficient graphical automated congestion ranking method for capable intersections, leveraging high-resolution traffic signal event data as the basis for automated congestion ranking. To accomplish these objectives, we build upon ATSPM concepts by continuously generating ATSPM measures of effectiveness (MOEs). Utilizing continuously generated ATSPM performance measures in Frisco, Texas, over several months, we devise an efficient graphical method for ranking hourly congestion levels among the studied ATSPM-capable intersections. All intersections are assessed and ranked using a multiobjective optimization technique, the Pareto front method. The points on the Pareto front represent dominating intersections with at least one inferior performance measurement, warranting prioritized improvement. The dominating points identified from the test dataset were validated and further explained using Purdue coordination diagrams (PCD), along with another individual dataset--Wejo-connected vehicle data. The outcomes of this approach have proven the validity of the method. [ABSTRACT FROM AUTHOR]

With the promotion of ChatGPT to the public, Large language models indeed showcase remarkable common sense, reasoning, and planning skills, frequently providing insightful guidance. These capabilities hold significant promise for their application in urban traffic management and control. However, large language models (LLMs) struggle with addressing traffic issues, especially processing numerical data and interacting with simulations, limiting their potential in solving traffic-related challenges. In parallel, specialized traffic foundation models exist but are typically designed for specific tasks with limited input-output interactions. Combining these models with LLMs presents an opportunity to enhance their capacity for tackling complex traffic-related problems and providing insightful suggestions. To bridge this gap, we present TrafficGPT—a fusion of multiple LLMs and traffic foundation models. This integration yields the following key enhancements: 1) empowering LLMs with the capacity to view, analyze, process traffic data, and provide insightful decision support for urban transportation system management; 2) facilitating the intelligent deconstruction of broad and complex tasks and sequential utilization of traffic foundation models for their gradual completion; 3) aiding human decision-making in traffic control through natural language dialogues; and 4) enabling interactive feedback and solicitation of revised outcomes. By seamlessly intertwining large language model and traffic expertise, TrafficGPT not only advances traffic management but also offers a novel approach to leveraging AI capabilities in this domain. The TrafficGPT demo can be found in https://github.com/lijlansg/TrafficGPT.git. • We propose the TrafficGPT framework, which combines large language models with expertise in traffic management. • TrafficGPT empowers LLMs to observe, analyze, process traffic data, and offer insightful decisions for traffic management. • We compare the proposed model with ChatGPT-4 Data Analyst to highlight its response accuracy and efficiency. • The adaptability and stability of TrafficGPT across various tasks, utilizing different foundational LLMs, are validated. [ABSTRACT FROM AUTHOR]

Trajectory data from connected vehicles (CVs) provide a continuous and reliable means of obtaining information that can be leveraged to optimize traffic signals. This paper proposes a real‐time traffic signal control method using CV trajectory data as the sole input. The primary goal of the proposed signal control method is to prevent queue spillover, which may significantly decrease the traffic efficiency on urban networks and induce high delays to the travelers. The proposed method formulates the signal control problem via a linear quadratic optimization model, considering the constraints related to the duration and variability of green lights in practical traffic signal control systems. Compared to conventional max‐pressure‐based methods, the optimization model offers enhanced efficiency in handling these constraints, making it highly suitable for real‐life implementation. The proposed method has undergone testing in both simulated environments and real‐world applications. In the simulation experiments, the proposed method has been demonstrated to effectively reduce spillover risks and outperform a conventional max‐pressure‐based approach even when the CV penetration rate is as low as 5%. In the real‐world experiment, the proposed method had been tested in a traffic network around the Beijing Capital International Airport for several months. The severity of spillovers, which was represented by two performance indicators, had been significantly reduced after implementing the proposed method. [ABSTRACT FROM AUTHOR]

Accurate and fast traffic prediction is the data-based foundation for achieving traffic control and management, and the accuracy of prediction results will directly affect the effectiveness of traffic control and management. This paper proposes a new spatiotemporal periodic polynomial model for road traffic, which integrates the temporal, spatial, and periodic features of speed time series and can effectively handle the nonlinear mapping relationship from input to output. In terms of the model, we establish a road traffic speed prediction model based on polynomial regression. In terms of spatial feature extraction methods, we introduce a maximum mutual information coefficient spatial feature extraction method. In terms of periodic feature extraction methods, we introduce a periodic trend modeling method into the prediction of speed time series, and effective fusion is carried out. Four strategies are evaluated based on the Guangzhou road speed dataset: a univariate polynomial model, a spatiotemporal polynomial model, a periodic polynomial model, and a spatiotemporal periodic polynomial model. The test results show that the three methods proposed in this article can effectively improve prediction accuracy. Comparing the spatiotemporal periodic polynomial model with multiple machine learning models and deep learning models, the prediction accuracy is improved by 5.94% compared to the best feedforward neural network. The research in this article can effectively deal with the temporal, spatial, periodic, and nonlinear characteristics of speed prediction, and to a certain extent, improve the accuracy of speed prediction. [ABSTRACT FROM AUTHOR]

Traffic state classification and relevance calculation at intersections are both difficult problems in traffic control. In this paper, we propose an intersection relevance model based on a temporal graph attention network, which can solve the above two problems at the same time. First, the intersection features and interaction time of the intersections are regarded as input quantities together with the initial labels of the traffic data. Then, they are inputted into the temporal graph attention (TGAT) model to obtain the classification accuracy of the target intersections in four states—free, stable, slow moving, and congested—and the obtained neighbouring intersection weights are used as the correlation between the intersections. Finally, it is validated by VISSIM simulation experiments. In terms of classification accuracy, the TGAT model has a higher classification accuracy than the three traditional classification models and can cope well with the uneven distribution of the number of samples. The information gain algorithm from the information entropy theory was used to derive the average delay as the most influential factor on intersection status. The correlation from the TGAT model positively correlates with traffic flow, making it interpretable. Using this correlation to control the division of subareas improves the road network's operational efficiency more than the traditional correlation model does. This demonstrates the effectiveness of the TGAT model's correlation. [ABSTRACT FROM AUTHOR]

Context: Hexahydrocannabinol (HHC), a compound derived from synthetic production using cannabidiol (CBD) or delta-9-tetrahydrocannabinol (Δ9 -THC), has gained recent attention due to its presence in seized materials across Europe. Sold legally in various forms, HHC poses potential health risks, particularly as a legal alternative to THC in some countries. Despite its historical description in the 1940s, limited toxicology data, pharmacological understanding, and analytical methods for HHC exist. Method: This study proposes analytical techniques using mass spectrometry to detect, identify, and quantify (9R)-HHC and (9S)-HHC, concurrently with THC and CBD in various matrices, including oral fluid, whole blood, and seized material. Three distinct methods were employed for different matrices: GC/MS for seized material, GC/MS/MS for whole blood, and UHPLC/MS/MS for oral fluid. Methods were validated qualitatively for oral fluid with a FLOQSwab® device and quantitatively in whole blood and seized material according to Peters et al's recommendations and ICH guidelines. Results: Validated methods were considered reliable in detecting and quantifying HHC isomers in terms of repeatability, reproducibility, and linearity with r ² systematically >0.992. These methods were applied to authentic cases, including seized materials and biological samples from traffic control (whole blood and oral fluid). In seized materials, (9R)-HHC levels ranged from 2.09% to 8.85% and (9R)- HHC/(9S)-HHC ratios varied from 1.36 to 2.68. In whole blood sample, (9R)-HHC and (9S)-HHC concentrations were, respectively, 2.38 and 1.39 ng/mL. For all analyzed samples, cannabinoids such as THC and CBD were also detected. Conclusion: This research contributes analytical insights into differentiating and simultaneously analyzing (9R)-HHC and (9S)-HHC, using widely applicable mass spectrometric methods. The study emphasizes the need for vigilance among toxicologists, as new semisynthetic cannabinoids continue to emerge in Europe, with potential health implications. The findings underscore the importance of reliable analytical methods for monitoring these compounds in forensic and clinical settings. [ABSTRACT FROM AUTHOR]

With the introduction of connected and automated vehicles (CAVs), the integrated control of traffic signals, lane assignments, and vehicle trajectories becomes feasible, offering notable benefits for enhancing intersection operations. However, during the prolonged transition to an entirely CAV environment, how to fully leverage the advantage of CAVs while considering the characteristics of human‐driven vehicles remains a huge challenge. To address this challenge, this paper proposes a joint optimization method for spatiotemporal resources at isolated intersections under mixed‐autonomy traffic conditions. Initially, the lane assignment optimization problem is modeled as a mixed integer linear program model to maximize the reserve capacity. Subsequently, the signal‐vehicle coupled control is formulated as a dynamic programming model with the objective of reducing vehicle travel time. Additionally, criteria are established to assess the need for re‐optimizing lane assignments. Simulations validate the superiority of the proposed control method over adaptive control in terms of traffic efficiency and intersection capacity amid substantial traffic demand fluctuations. Sensitivity analyses reveal that the proposed control method can yield higher benefits under medium traffic demand levels. Furthermore, the proposed algorithm exhibits no significant sensitivity to the CAV market adoption rate, suggesting its applicability throughout the CAV adoption process. [ABSTRACT FROM AUTHOR]

Cooperative Vehicular Platooning (Co-VP) is a prime example of Cooperative Cyber-Physical Systems (Co-CPS), offering great potential for enhancing road safety by reducing human involvement in driving. However, this domain presents significant challenges, incorporating control theory, communications, vehicle dynamics, security, and traffic engineering. This survey explores recent advancements in Co-VP, covering control strategies, communication infrastructures, and cybersecurity. It also examines testing and validation methods, such as simulation tools, hardware-in-the-loop setups, and vehicular testbeds. Lastly, it outlines open challenges within the Co-VP field. This comprehensive overview serves as a guide for further developments in this complex and critical area. [ABSTRACT FROM AUTHOR]

Prediction models have been extensively used in the field of road safety. However, none of these models have yet been particularly applied to injuries related to zero-emission electric vehicles (EVs), which may lead to different outcomes due to their inaudible engines. Using an optimisable classification tree, the aim of this first-ever study was to predict the likelihood of personal injury severities stemming from EV-related crashes on Britain's roads. The prediction model was found to be capable of detecting significant and insignificant factors. These factors provide important insights into how the severity of injuries could be reduced in the future deployment of EVs. Although there was an increased risk for injuries classified as 'slight severity', particularly at lower urban speed limits, several predictors are suggesting that EVs do not pose more of a risk to a certain group. Contrary to popular belief, no convincing evidence was found to suggest that eco-friendly EVs are 'silent killers' for vulnerable road users. [ABSTRACT FROM AUTHOR]

High collision rates on horizontal curves compared with other roadway elements make them one of the most critical elements in a transportation network and thus good candidates for new studies, especially of the stability of a vehicle driving on a horizontal curve. In this regard, spiral transition curves as facilities to enter horizontal alignments are very important. While the superelevation changes in these curves have always been linear, the aim of this study was to evaluate non-linearity in the superelevation attainment function (SAF). Various scenarios were used in order to cover different situations. As a simulation tool, the CarSim software package was used to model three kinds of passenger cars (sport utility vehicle, utility truck and sedan). In addition, 16 types of spiral–curve–spiral road plans for three different conditions of road slope, six types of warping in the SAF and two types of functional speed were examined (a total of 1728 scenarios). The results showed that non-linearity might produce better results than other proposed methods; for example, it was found that a parabolic function reduced the lateral acceleration rate by over 50% for high superelevation and design speed. [ABSTRACT FROM AUTHOR]

Due to the complex routes and the dynamic changing factors in transportation, precise traffic speed prediction is very difficult. Traditional prediction methods only focus on a single monitoring site, without establishing a relationship between different sites, so the precision is poor. The deep learning method can model traffic networks well, but suffers from information loss and the disadvantage of single input data. A multisource spatio-temporal hybrid dilated graph convolutional network (GCN) for forecasting traffic speed is proposed in this paper. A GCN based on hybrid dilated convolution can extract the influence of adjacent information and capture dynamic spatial and non-linear temporal correlations. Considering multisource data will increase the forecasting precision and improve the generalisation ability. Using a real-world data set, the performance of the proposed model was validated against other baselines (a fully connected neural network, convolutional neural network and spatio-temporal GCN). The proposed model was found to be superior to other models as it considers proximity information, which is often overlooked, and multifactorial influence. [ABSTRACT FROM AUTHOR]

The use of natural river silt treated as a 'waste material' has become the focus of research in the Yellow River flooded area, especially in the field of highway engineering. It is therefore of great significance to study the deformation and stiffness degradation of Yellow River silt (YRS) under long-term cyclic loads. To this end, a series of undrained cyclic triaxial tests on YRS for a large number of cycles (10 000) was carried out using a triaxial apparatus and the effects of confining pressure and cyclic stress ratio on the resilient strain of the YRS were explored. The critical cyclic stress and the critical cyclic stress ratio between the plastic shakedown state and incremental collapse state of the YRS were determined, and the modulus-softening behaviour of the YRS was assessed. The results of this study not only provide theoretical support for the long-term engineering performance of YRS, but also provide theoretical guidance for the cyclic response of all similar types of subgrade soils. [ABSTRACT FROM AUTHOR]

Information about spatial distribution (OD flows) is a key element in traffic management systems in urban transport networks that enables efficient traffic control and decisions to redirect traffic to less congested sections of the network in emergencies. With the development of modern techniques of remote sensing, more and more advanced methods are used to measure traffic and determine OD flows. However, they may produce results with different levels of errors caused by various factors. The article examines the impact of traffic volume and its variability on the error values of short-term prediction of the OD matrix in the urban network. The OD flows were determined using a deep learning network based on data obtained from video remote sensing devices. These data were recorded at earlier intervals concerning the forecasting time. The extent to which there is a correlation between the size of OD flows and the prediction error was examined. The most frequently used measure of prediction accuracy, i.e., MAPE (mean absolute percentage error), was considered. The analysis carried out made it possible to determine the ranges of traffic flow rate for which the MAPE stabilizes at the level of approximately 6%. A set of video remote sensing devices was used to collect spatiotemporal data. They were located at the entrances and exits from the study area on important roads of a medium-sized city in Poland. The conclusions obtained may be helpful in further research on improving methods to determine OD matrices and estimate their reliability. This, in turn, involves the development of more precise methods that allow for reliable traffic forecasting and improve the efficiency of traffic management in urban areas. [ABSTRACT FROM AUTHOR]

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

Adaptive signal control technology (ASCT) is an advanced traffic control system that optimizes signal timing based on real-time traffic demand. ASCT can potentially improve the operation and safety of intersections by establishing dynamic coordination among signalized intersections in real-time. This study used a binary Bayesian logit model with random effects, which accounts for unobserved heterogeneity, to explore the impacts of ASCT on the severity of intersection-related crashes in Florida. Two distinct ASCT types (Type I and II) were analyzed to assess their impacts on crash severity. The analysis revealed that ASCT reduced the likelihood of a fatal plus injury (FI) crash by 14.6%. This reduction was significant at a 90% Bayesian credible interval (BCI). Also, each ASCT type (Type I and II) showed a potential reduction in the likelihood of a FI crash, although the decrease was not significant at a 90% BCI. Other factors such as driving under the influence, angle crashes, dark lighting conditions, posted speed limit, and median along a minor approach, were associated with a higher risk of a FI crash. Transportation agencies could use the study results to justify the deployment and expansion of ASCT at signalized intersections with a high frequency of severe crashes. [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]

Using historical traffic flow information to accurately and real-time predict future traffic flow information is particularly important for the management and control of traffic scenarios, and the guidance and planning of traffic travel. Short-term traffic flow prediction requires a large amount of forecast data and complex changes in traffic flow in space and time. However, the current prediction model cannot meet the requirements of real-time and accuracy of short-term traffic flow prediction. This paper proposes two traffic flow prediction models based on the changing trend and correlation of short-term traffic flow in time and space, combined with deep learning related theories. Firstly, this paper takes the traffic flow of the expressway as the research object, explores the basic parameters of traffic flow-flow, speed occupancy rate in time and space distribution law and change trend, and selects the speed as the research object, analyzes its temporal and spatial characteristics and correlation to provide data support for this study. Then, this paper introduces the related theories and frameworks of deep learning, mainly including neural network theory and hyperparameter optimization theory, as well as the deep learning model design framework. Pytorch and hyperparameter optimization framework Optuna, so as to provide theoretical foundation and technical support for this research. Finally, experiments of short-term traffic prediction based on single detection point and short-term traffic prediction based on multiple detection points are carried out on the PeMS dataset. Firstly, a multi-lane spatiotemporal convolutional network model (MSCTAN) based on traffic flow prediction at a single detection point is proposed to capture the spatiotemporal correlation of multi-lane traffic at a single detection point. Spatiotemporal Convolution and Spatiotemporal Attention Network Model (MSCSAN). For the two models proposed in this paper, comparative experiments were designed, and the mean absolute error (MAE), the root mean square error (RMSE) and the mean absolute percentage error (MAPE) were used as evaluation indicators to verify their performance at a single detection point and multiple detection points. The results show that, whether it is a single detection point experiment or a multi-detection point experiment, the two models achieve the best performance compared with the comparison model. [ABSTRACT FROM AUTHOR]

The development and changes in land use in the city of Serang have triggered new travel patterns, significantly influencing existing traffic movement patterns. As the capital of Banten Province, the presence of Serang City is expected to drive regional development and economy in the surrounding area, which requires adequate facilities and infrastructure to support its population's activities. The performance of the Bts. Kota Serang - Bts. Kota Tangerang road section, currently an arterial road, already exhibits a V/C Ratio of 0.80 and Level of Service (LoS) D, indicating poor road performance. To address this, it is necessary to identify and address traffic problems, especially in the New Serang City Area, by proposing traffic management and engineering designs that directly benefit road users. This study uses the Manual Kapasitas Jalan Indonesia (MKJI) method from 1997 and the PTV Vissim application tool. Based on validation results, the model data does not show significant differences from existing data, thus enabling its use for forecasting road performance in 2038 with a V/C Ratio of 1.35 and LoS F. Several proposed interventions include side barrier regulation, closure of median openings at the 3-way intersection of Untirta complex, installation of ATCS at Pakupatan terminal intersection, Parung intersection, and Pakupatan intersection, as well as road widening on the Bts. Kota Serang - Bts. Kota Tangerang road section. The efforts made in 2038 have resulted in improved road performance with a V/C Ratio of 0.64, speed of 39.64 km/h, and LoS C. [ABSTRACT FROM AUTHOR]

To reduce the risk of traffic conflicts in merging area, driver's behavior pattern was analyzed to provide a theoretical basis for traffic control and conflict risk warning. The unmanned aerial vehicle (UAV) was used to collect the videos in two different types of merging zones: freeway interchange and service area. A vehicle tracking detection model based on YOLOv5 (the fifth version of You Only Look Once) and Deep SORT was constructed to extract traffic flow, speed, vehicle type, and driving trajectory. Acceleration/deceleration distribution and vehicle lane-changing behavior were analyzed. The influence of different vehicle models on vehicle speed and lane-changing behavior was summarized. Based on this data, the mean and standard deviation of velocity, acceleration, and variable acceleration were selected as the characteristic variables for driving style clustering. To avoid redundant information between features, principal component dimensionality reduction was performed, and the dimensionality reduction data was used for K-means and K-means++ clustering to obtain three driving styles. The results show that there are obvious differences in the driving behaviors of vehicles in different types of merging areas, and the characteristics of different areas should be fully considered when conducting traffic conflict warnings. [ABSTRACT FROM AUTHOR]

The paper presents a model-based demand-responsive traffic control system for mixed traffic conditions using sample travel time data. The model incorporates mixed traffic characteristics such as heterogeneity, limited lane discipline of varied vehicle types, and spatio-temporal traffic dynamics across the width of the road. The methodology includes optimization of intersection performance by accommodating the varying traffic demand through signal timing variables. On validation, the model yielded reliable queue estimates within a close proximity of the actual, ranging from 20 to 40 meters. Upon optimization, the proposed model reduced total intersection delay by 15.42% on an average across 14 cycles, for near-saturated traffic conditions. The optimal green splits are found to be responsive to the varying traffic demand. The proposed system is simple and can be easily implemented in the mixed traffic conditions. [ABSTRACT FROM AUTHOR]

Currently, 1060 aluminum alloy is widely applied in the electronics industry, construction, the aerospace field, traffic engineering, decorations, and the consumer goods market for its good chemical, physical, and mechanical properties. In general, excellent processing property is necessary and important for the manufacturing of complicated panels. In this paper, a special 2D ultrasonic vibration incremental forming method is designed to improve its plasticity and mechanical properties. Three kind of processing methods, including traditional single-point incremental forming, longitudinal ultrasonic vibration incremental forming, and 2D ultrasonic vibration incremental forming, are used for the flexible manufacturing of cones and cylindrical cups of 1060 aluminum alloy sheet. Then, micro-hardness tests, residual stress tests, and scanning electron microscopy tests are carried out to probe the changes in micro-structure and mechanical properties and to analyze the effects of different types of ultrasonic vibration on the plasticity and fracture characteristic of 1060 aluminum alloy. It is proven that 2D ultrasonic vibration facilitates the improvement of plasticity and surface qualities of 1060 aluminum alloy better than the other two processing methods. Therefore, the novel 2D ultrasonic vibration incremental forming process possesses substantial application value for the flexible and rapid manufacturing of complicated thin-walled component of aluminum alloy. [ABSTRACT FROM AUTHOR]

Urbanization has led to accelerated traffic congestion, posing a significant obstacle to urban development. Traditional traffic signal scheduling methods are often inefficient and cumbersome, resulting in unnecessary waiting times for vehicles and pedestrians, exacerbating the traffic situation. To address this issue, this article proposes a dynamic traffic signal scheduling system based on an improved greedy algorithm. Unlike conventional approaches, we introduce a reward function and a cost model to ensure fair scheduling plans. A constraint function is also established, and the traffic signal scheduling is iterated through the feasible matrix using the greedy algorithm to simplify the decision-making process and enhance solution efficiency. Moreover, an emergency module is integrated to prioritize special emergency vehicles, reducing their response time during emergencies. To validate the effectiveness of our dynamic traffic signal scheduling system, we conducted simulation experiments using the Simulation of Urban Mobility (SUMO) traffic simulation suite and the SUMO traffic control interface Traci. The results indicate that our system significantly improves intersection throughput and adapts well to various traffic conditions, effectively resolving urban traffic congestion while ensuring fair scheduling plans. [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]

Three-colour four-way traffic light completed 100 years in 2020. Even though the traffic light in the form of Semaphore arms has been in use in London since 1868, electric traffic lights came into existence in 1912 and the standard three-colour four-way light in 1920. Research is continuously being carried out to develop better algorithms to improve safety, reduce travel delays, and optimize road capacity. Hence a review of the evolution of traffic lights is warranted. This paper presents an all-round review using a six-prong approach. Timeline of the evolution of the literature in the last 100 years, the evolution of hardware, algorithms, traffic control schemes, standards and the pedestrian lights and count down timer are the six areas in which the review is carried out. A timeline of the different keywords related to the various algorithms in use is presented. This article delves into the thinking and meticulous approach of early researchers and practitioners of the field while dwelling on the past. They laid the rock-solid foundation of today's research. Also, future research areas like connected vehicles and automated vehicles are pointed out, and a summary of the findings is presented at the end. [ABSTRACT FROM AUTHOR]

This paper proposes a reinforcement learning (RL)-based traffic control strategy integrated with attention mechanism for large-scale adaptive traffic signal control (ATSC) system. The proposed attention RL integrates attention mechanism into a multiagent RL model, namely multiagent proximal policy optimization (MAPPO), so as to enable more effective, scalable, and stable learning in complex ATSC envi)ronments. In the attention RL, decentralized policies are trained using a centrally computed critic that shares an attention model, while the attention model selects relevant intersections for each agent to estimate the global critic. This framework effectively reduces the computa)tional complexity and stabilizes the training process, enhancing the ability of RL agents to control large-scale traffic networks. The proposed control strategy is tested in both a large synthetic traffic grid and a large real-world traffic network of Yangzhou city using the microscopic traffic simulation tool, SUMO. Experimental results demonstrate that the proposed approach learns stable and sustainable policies that achieve lower congestion level and faster recovery, which outperforms other state-of-art RL-based approaches, as well as a gap-based actuated controller. [ABSTRACT FROM AUTHOR]

With the development of autonomous driving, a mixed traffic flow state composed of connected automated vehicles (CAVs) and human-driven vehicles (HVs) will last for an extended period. The abundant computing resources and CAVs with high compliance in the intelligent connected environment provide a good situation for variable speed limit control on highways, which helps even the traffic flow and improves traffic efficiency and safety. In this paper, we propose a variable speed limit control method for mixed traffic flow based on deep-reinforcement learning. First, the variable speed limit control problem is abstracted into a Markov decision process and the factors of real-time CAV penetration rates and predictions are considered in the state description. Different from variable message signs (VMS), CAVs are taken as the executive objects of the controller so that the variable speed limit control for mixed traffic flow is realized indirectly through the interaction with HVs. Next, double deep Q network (DDQN) is introduced to calculate the optimal speed limit in different states. Finally, the empirical study on US101-S proves the effectiveness of the proposed model. The results show that the variable speed limit control model based on the DDQN algorithm can effectively improve the efficiency and environmental benefits of mixed traffic flow. Moreover, the multi-objective reward function can achieve a better control effect than the single objective. Besides, the proposed model outperforms other models in this paper and predictive factors can further improve proactive control performance. In addition, with the increasing penetration of CAV, the proposed model achieves a better control effect. [ABSTRACT FROM AUTHOR]

High bit-error rates and high transmission rates are required for the Multimedia Wireless Sensor Networks (MWSN) to transmit high-quality pictures through smart devices. To fully utilize the advantages of the technology known as Multiple-Input Multiple-Output, MWSN heavily relies on cooperative communication. Large-scale wireless networks use multi-radio-multi-channel to improve performance by simultaneous broadcasts across symmetrical channels to reduce interference. Expanding cooperative communication in vast networks is subject to severe interference. And, as each node in the network is mobile, routing and transmission delay pose significant problems for cooperative multimedia wireless sensor networks. Mobility increases the MWSNs' dynamic nature, which reflects in the overhead control traffic. To address above issues, a Cluster-based Delay Aware Cooperative Relay Selection (CDACRS) was proposed by employing mobility and distance metrics and channel assignment (CA) using dynamic Global Table (GT). To minimize the end-to-end transmission latency without compromising aggregate throughput, our approach chooses a relay-node depending on the mobility and the maximum available channel capacity. Further, to improve the end-to-end energy consumption, Power Aware Transmission (PAT) protocol is developed by calculating maximum transmission power required to meet target bit error rate (BER). The proposed method's performance is evaluated against the Cluster-based Cooperative Multi-Hop Optimal Relay Selection (CCORS); energy efficient and quality aware multi-hop cooperative image transmission; and Energy Aware Cooperative Image Transmission (EACIT) algorithms and observed that our approach improves the transmission delay by 37.5% (approx.) and end-to-end energy consumption by 48.8%. [ABSTRACT FROM AUTHOR]

Walking speed is an essential parameter used in determining pedestrians' walking behavioural characteristics, the performance of a pedestrian facility, the capacity of the system, and several traffic engineering policy-related applications. While several studies have focussed on understanding walking behavioural patterns over at-grade facilities, there is still a paucity of research on understanding the influence of pedestrians' individual and group behavioural characteristics on walking speed over elevated facilities. This study uses extensive video data collected from different foot-over bridges (FOBs) and skywalks to comprehensively understand walking speed characteristics and their variations over both elevated facilities. The results of the study demonstrated the importance of considering socio-demographic factors with the associative activities involved in walking, group characteristics, and land use type in the estimation of pedestrians' walking speed. The outcome of the study results would provide relevant policy-related strategies to designers and planners for improving infrastructures, developing realistic crowd behavioural simulation models, and estimating overall crowd dynamics. • Mean walking speed was higher over skywalks compared to FOBs. • Lane formation and leader-follower observed towards side of facility. • Pedestrians in faster-is-slower effect showed reduced walking speeds. • Squeezing effect significantly reduced the walking speeds. • Pedestrians engaged in texting/calling/listening to music reduced speeds. [ABSTRACT FROM AUTHOR]

Several manufacturing industries try to reduce transportation waste using automated material handling systems, which can enhance the transportation of raw materials from one location to another in the production line of a manufacturing area. The issue with transportation and job flow is a critical factor in a production line because some production stations need to wait for the work-in-progress to be delivered. Automated guided vehicle (AGV) transportation needs a setup of traffic control over a factory's physical infrastructure and simulation. Doing so can help showcase and evaluate possible deficiencies that can be improved in the real job flow scenario of the production line. The design of experiment plays a huge role in finding and explaining variations of information under conditions that are regularly put as a hypothesis to reflect or describe the variation. A simulation model is implemented by adopting simplified AGV parameters. The model development follows the structure of system specification → machine specification → AGV specification → discrete-event simulation model → experimental design → analysis of performance indicators (PIs). To precisely reflect an alternative for evaluating aforementioned issues, this study proposes the model stated above and an analysis that is based on the PIs. Analysis of variance (ANOVA) results are chosen to analyze different factors affecting the PIs. Using the factorial ANOVA test results, this study uses one-way and two-way interactions to compare the relationship between job flow time, AGVs, AGV utilization, number of AGVs, and average waiting time. [ABSTRACT FROM AUTHOR]

The continuous evolution of artificial intelligence and cyber–physical systems has presented promising opportunities for optimizing traffic signal control in densely populated urban areas, with the aim of alleviating traffic congestion. One area that has garnered significant interest from both researchers and practitioners is the application of deep reinforcement learning (DRL) in traffic signal control. However, DRL-based algorithms often suffer from instability due to the dynamic nature of traffic flows. Discrepancies between the environments used for training and those encountered during deployment often lead to operational failures. Moreover, conventional DRL-based traffic signal control algorithms tend to reveal vulnerabilities when faced with unforeseen events, such as sensor failure. These challenges highlight the need for innovative solutions to enhance the robustness and adaptability of such systems. To address these pertinent issues, this paper introduces StageLight, a novel two-stage multiscale learning approach, which involves learning optimal timings on a coarse time scale in stage 1, while finetuning them on a finer time scale in stage 2. Our experimental results demonstrate StageLight's remarkable capability to generalize across diverse traffic conditions and its robustness to various sensor-failure scenarios. [ABSTRACT FROM AUTHOR]

In order to solve the existing problem of the combination of traffic signs at typical grassland highway intersections, the combination setting of intersection traffic engineering facilities was optimized. Through simulation experiments, the electroencephalogram (EEG) signals of 40 drivers were collected, clustered into 5 (MS1—MS5) microstate topographic maps, and the reaction time and duration, coverage, frequency of occurrence and conversion probability of the drivers were statistically analyzed. The experimental results showed that the default network and the dorsal attention network in the driver's EEG microstate played a major role in the cognitive process of the combination of traffic facilities at the grassland highway intersection. The duration of MS4 and the conversion probability of MS1—MS3 increased with the increase of transportation facilities, which can be used as direct indicators to evaluate driver's cognitive load. Microstate indicators and reaction time trend analysis found that at the information level C, that was, the combination of four traffic engineering facilities, the driver's brain state had the best performance, the strongest cognitive ability, the smaller load and the fastest response. [ABSTRACT FROM AUTHOR]

Ensuring the correctness of road network data is critical for navigation, traffic control and urban planning. Errors like missing roads and absent connections can hinder its quality. Trajectory data emerges as a cost-effective source to uncover such errors. Existing methods often analyze the mismatches between trajectories and road networks to identify specific errors. They heavily rely on manually established rules and fail to fully leverage the diverse patterns of trajectories and the underlying road network structure. The article introduces a sequential classification approach to detect diverse road network errors. It starts with partial map matching (PMM) to associate trajectories with a road network, allowing unmatched portions. Context features are subsequently extracted by encoding patterns in the map matching (MM) outputs, raw trajectories and road network. Finally, a bidirectional recurrent neural network (BiRNN) model is trained to identify the network error category for each trajectory point. Experiments were performed on detecting errors in OpenStreetMap (OSM) road network with a real-world trajectory dataset. It demonstrates that the proposed method achieves accuracy over 96%, significantly surpassing four baselines. An ablation study confirms the necessity of considering different types of context features. This method advances error detection by effectively utilizing trajectories in identifying diverse network errors. [ABSTRACT FROM AUTHOR]