Road Traffic System Research Articles

Application of Artificial Intelligence Technology in Optimizing Control Parameters of Traffic Signal Group Systems

On the basis of introducing the concept of intersection signal state phase difference, the author proposes a proportional signal phase difference design scheme for traffic signal system control, on the basis of the HCM signal delay calculation formula, a standardized signal cycle and effective green signal ratio optimization design model were compiled, thus forming a complete set of optimization design modes for the control parameters of the urban main road traffic signal group system. The experimental results indicate that, the entire simulation experiment took 6000 seconds to compare the traditional fuzzy algorithm with the controller implemented by the author's fuzzy neural network, each case was simulated 5 times, the data in the Table is the average of 5 times, compared with traditional fuzzy algorithms, the author's method shows an improvement of 20.8% to 45.67% in average vehicle delay time, especially when the traffic flow is different in the east-west and north-south directions, the improvement is more significant.

Road traffic crash data in Southwestern Nigeria: a qualitative analysis of sources, contents and management methods

Objective This study qualitatively examined road traffic crash (RTC) data collection and management in southwest Nigeria, with the goal of addressing the tenets of the UN Decade of Action Plan on Road Safety’s call for an effective data system. Methods Data on RTCs data collection in the study area was obtained through key informant interviews with five hospital accident emergency unit directors, three Federal Road Safety Commission (FRSC) Sector commanders, and three Nigeria Police Force (NPF) commissioners. Datasets were transcribed, categorized, and interpreted using content analysis, descriptive statistics, and WHO recommended minimal crash data element requirements. Results The study found disparate systems, a lack of synergy, and discrepancy in the various data sources in the country when compared with WHO recommendations on road traffic data collection systems, with 55% of agencies using non-standardized paper forms. The study also reveals that the minimum crash data elements recommended by WHO are not consistently captured in the NPF, FRSC, and hospital traffic crash data sources. Conclusions The study suggested the use of an upgraded National Road Traffic Crash Data Management System (NRTCDMS) Data Template to unify data gathering and linkage issues, but recommends a digital version of the template.

A Comparative Study of Traffic Signal Control Based on Reinforcement Learning Algorithms

In recent years, the increasing production and sales of automobiles have led to a notable rise in congestion on urban road traffic systems, particularly at ramps and intersections with traffic signals. Intelligent traffic signal control represents an effective means of addressing traffic congestion. Reinforcement learning methods have demonstrated considerable potential for addressing complex traffic signal control problems with multidimensional states and actions. In this research, the team propose Q-learning and Deep Q-Network (DQN) based signal control frameworks that use variable phase sequences and cycle times to adjust the order and the duration of signal phases to obtain a stable traffic signal control strategy. Experiments are simulated using the traffic simulator Simulation of Urban Mobility (SUMO) to test the average speed and the lane occupancy rate of vehicles entering the ramp to evaluate its safety performance and test the vehicle’s traveling time to assess its stability. The simulation results show that both reinforcement learning algorithms are able to control cars in dynamic traffic environments with higher average speed and lower lane occupancy rate than the no-control method and that the DQN control model improves the average speed by about 10% and reduces the lane occupancy rate by about 30% compared to the Q-learning control model, providing a higher safety performance.

A scoping review of road traffic data systems in the Eastern Mediterranean Region

Background: Road traffic injury is a major global health risk, however, under-reporting of road traffic crashes data and the use of different reporting systems have made it difficult to compare data across countries. Aim: To examine published and grey literature for better understanding of available health and non-health road traffic data systems in the Eastern Mediterranean Region (EMR) countries. Methods: We conducted a systematic search of databases to identify studies reporting road traffic data systems in the EMR countries between 2011 and January 2022. We also searched grey literature on the websites of government, WHO, World Bank, UNICEF, regional economic commissions and other relevant institutions. We assembled the data in Microsoft Excel and presented the counts of data sources, data types and data quality. Results: We included 84 of 2238 studies accessed in this review. One-third of the publications was from the Islamic Republic of Iran while 10% was from Pakistan. Police databases were the primary sources of data in most of the studies (79%) while hospital and death registration systems together accounted for one-quarter of the databases. The most common indicators reported in the publications were deaths (61%), crashes (48%) and injuries (35%). Only 40% of the studies disaggregated their analyses by gender and 44% by age. No papers identified permanently linked data sources, although more than a quarter of the papers reviewed used some form of modelling or data mining. Conclusion: This scoping review highlights an over-reliance on police data, poor quality traffic data systems, and multiple stakeholders collecting similar data, leading to redundancy. EMR countries need to establish robust road safety data systems to provide data for relevant policies and interventions

CHANGE IN THE NUMBER OF TRAFFIC ACCIDENTS IN THE LVIV REGION DURING 2019–2023

Current trends in the development and modernisation of transportation systems focus on safety. However, it is worth conducting an in-depth analysis of data related to traffic safety factors to maximise the safety emphasis in future strategies. This approach concentrates the efforts of engineers and scientists primarily on combating the causes of road accidents rather than their consequences, as is often the case today. The object of research in this article is the street and road network of Lviv region, as it is necessary to take into account the regional aspects of traffic and their differences in the country’s regions, given the density of streets and roads, climatic and hydrometeorological conditions, as well as the typology of roads. One of the scientific problems that the study’s results can partially solve is to identify time patterns and dynamics of changes in the number of road accidents in the Lviv region and compare the results with the targets set out in strategic documents in the field of road safety in Ukraine. The article analyses the data on the number of road traffic accidents in the region from 2019 to 2023. At the same time, it carries out the statistical distribution of traffic accidents by the causes of their occurrence. We also account for the time aspect – a breakdown by time of day and days of the week, including the general trend over the past years. We established that the dynamics of the number and severity of road accidents for the period under consideration is negative; however, the patterns of their occurrence persist, which explains the positive statistical result obtained due to quantitative but not qualitative factors affecting traffic safety. The results obtained are of more value from an engineering and scientific point of view, particularly in comparison with traffic accident statistics disseminated on information resources or social media. The analysis conducted in this article allows us to identify problematic areas in the functioning of both the bodies that ensure the safety and organisation of road traffic and transport systems. Keywords: road safety, road traffic accident, accident rate, transport systems.

Methodology for assessing the level of development and efficiency of the functioning of the traffic management system, taking into account the environmental factor

The scientific article presents a methodology for assessing the level of development and efficiency of traffic management systems, taking into account environmental factors. The order and algorithms for all calculations to assess the level of effectiveness for road traffic management systems of motor transport, while taking into account the impact of environmental factors, are provided. The methodology for assessing the current state of the traffic management system relies on the degree of deviation of each individual indicator from its target value. The resulting value of the composite indicator for the system’s condition is then compared to its standard value, and an estimated overall state for the system is determined. According to some indicators, there has been an increase in emissions of toxic substances in the city's streets and roads, which are assessed as “poor”. To improve the state of the environment, an immediate set of organizational and technical measures has been proposed for the rational development of the traffic management system.

Application of a time series to analyse the evaluation of road traffic accidents in Slovakia

Road traffic accidents represent an important part of the road traffic system. In many cases, they may lead not only to damage to vehicles and property, but also serious injuries or even death of road traffic participants. The prevalence of road traffic accidents and the related fatality rates in a country is a significant indicator of the maturity of that country and its inhabitants. The purpose of this article was to review the prevalence of road traffic accidents and fatality rates in the Slovak Republic over the period from 2009 to 2022. The analysis was conducted by applying basic statistical methods and a time series analysis (exponential smoothing method – ETS). The ETS is a method used for forecasting a time series univariate. The focus of this method is on three time series components (error E, trend T and seasonal S), while defining how the individual components interact. The results of the analysis indicated a positive, i.e. a falling trend in road traffic accident rates, according to the numbers of persons killed/injured in road traffic accidents in Slovakia. Compared to 2009, in 2020 there was a decrease in the number of road traffic accidents by almost 54%. In 2022, the number of fatalities decreased by almost 30% compared to those in 2009. The modelling also involved a forecast of the number of persons killed/injured in road traffic accidents for a period of 5 years.

Formulation, Proposition and Application of Interval Semigraph

Semigraph represents a versatile extension within graph theory, offering a broader framework for exploration. Among these, intersection graphs hold pivotal roles, serving as essential analytical tools with wide-ranging applications. In this study, we introduce the integration of intersection graphs into the generalized structure of semigraphs, aiming to invigorate researchers’ interest and encourage further advancements in this domain. This paper introduces two novel concepts: edge intersection semigraphs and interval semigraphs. Additionally, foundational results pertaining to these concepts are established, elucidating their fundamental properties. Furthermore, we illustrate the practical utility of interval semigraphs through an illustrative example involving their application in optimizing road traffic management systems.

Validation of a statistical-dynamic framework for predicting energy consumption: A study on vehicle energy conservation equation

Predictive models for vehicle energy consumption are crucial for sustainable development in urban road traffic systems. This paper comprehensively reviews classic predictive models and develops a novel statistical-dynamical energy consumption prediction framework called Vehicle Energy Conservation Equation (VECE). VECE is constructed based on the principles of vehicle energy flow and regression analysis, employing a continuous and concise mathematical formulation. Its coefficients possess clear physical interpretations, allowing for application in various vehicle categories. To validate VECE, this study collected energy consumption data from 28 vehicles, including 9 diesel vehicles, 16 gasoline vehicles, 1 ethanol gasoline vehicle, and 2 battery electric vehicles. A rigorous data processing procedure was designed. Data analysis revealed that the VECE coefficients are correlated with vehicle type, speed, and acceleration. VECE's predictive performance is minimally impacted by the number of vehicle categories, effectively modeling energy consumption for vehicles of the same fuel type or size category. Comparative analysis with E-EcoGest, VT-Micro, PERE, and CMEM demonstrates the moderate accuracy of VECE in predicting instantaneous vehicle energy consumption while excelling in predicting cumulative energy consumption. The minimum relative percentage error for the cumulative predicted values is 4.2%. Overall, VECE demonstrates outstanding performance in computational simplicity, coefficient interpretability, adaptability, and extensibility, making it a crucial tool for achieving energy-efficient road transport systems.

Preparation of strong and tough conductive hydrogel based on Grafting, Fe3+-Catechol complexations and salting out for triboelectric nanogenerators

The development of a strong and tough conductive hydrogel capable of meeting the strict requirements of the electrode of a hydrogel-based triboelectric nanogenerator (H-TENG) remains an enormous challenge. Herein, a robust conductive polyvinyl alcohol (PVA) hydrogel is designed via a three-step method: (1) grafting with 3,4-dihydroxy benzaldehyde, (2) metal complexation using ferric chloride (FeCl3) and (3) salting-out using sodium citrate. The hydrogel contains robust crystalline PVA domains and reversible/high-density non-covalent interactions, such as hydrogen bonding, π–π interactions and Fe3+-catechol complexations. Benefiting from the crystalline domains, the hydrogel can resist external forces to the hydrogel network; meanwhile, the reversible/high-density of non-covalent interactions can impart gradual and persistent energy dissipation during deformation. The hydrogel possesses multiple cross-linked networks, with 6.47 MPa tensile stress, 1000 % strain, 35.24 MJ/m3 toughness and 37.59 kJ/m2 fracture energy. Furthermore, the inter-connected porous hydrogel has an ideal structure for ionic-conducing channels. The hydrogel is assembled into an H-TENG, which can generate open circuit voltage of ∼ 150 V, short-circuit current of ∼ 3.0 μA, with superb damage immunity. Subsequently, road traffic monitoring systems are innovatively developed and demonstrated by using the H-TENG. This study provides a novel strategy to prepare superiorly strong and tough hydrogels that can meet the high demand for H-TENGs.

Real-Time Pavement Crack Detection Based on Artificial Intelligence

Pavement as a structural element is closely related to the road traffic system because it is essentially a support structure for the movement of vehicles. Modern technology has attained significant improvements in road durability, quality, and safety through the use of new materials and construction technology. All civil engineering infrastructures have a specific lifespan. The road surface can be the worst, and repair is more costly if the pavement is not maintained. The objective of this research is to spot the damages over the inspected road and detect cracks in a short time, useful to achieve more comprehensive monitoring and assessment of the condition of road pavement using a smartphone equipped with You Only Look Once (YOLO) to reduce maintenance costs. The method uses advanced image processing techniques and uses YOLO to detect cracked pavement in a short time. More specifically, it is based on the latest generation of Deep Neural Network (DNN) algorithms, such as YOLO V5. YOLO V5 is used as a detector for cracked pavement and image processing as an automated pavement distress detector. The obtained result for longitudinal cracks shows that the area of cracks is 1.1682 m2, with a threshold value of 0.91, while the result for transversal cracks shows the area of cracks of 1.9627 m2, with a threshold value of 0.85. Otsu’s method works best under conditions such as low noise level, homogeneous lighting, and higher intra-class variance than an inter-class variance. The outcome of this project is improved recognition accuracy compared to the manual recognition currently used.

Impact of road transport system on groundwater quality inferred from explainable artificial intelligence (XAI)

Road networks constitute a vital component of modern society, facilitating rapid transportation and driving economic activities by enabling the smooth movement of goods and people. However, the expansion of road systems carries significant environmental considerations, particularly regarding its impact on groundwater quality. Thus, it is crucial to understand the complex relationship between groundwater quality and the road traffic system. This paper aims to identify the impact of road transport systems on groundwater quality using a data-driven approach. Specifically, road network and groundwater chemistry data in Texas were obtained from an open data portal. This study was carried out in two phases: the explainable artificial intelligence (XAI) modeling phase and the multivariate analysis phase. In the XAI modeling phase, a prediction model was developed using eXtreme Gradient Boosting (XGB), with groundwater chemistry parameters as output features and road transport attributes as input features, i.e., elevation, annual average daily traffic, distance, lane-miles, speed limit and well depth. Furthermore, the relationships between groundwater chemistry parameters and road transport attributes were examined using feature importance and accumulated local effect (ALE). In the multivariate phase, Piper diagrams and principal component analysis (PCA) were utilized to identify the source of the selected groundwater chemistry parameters from the XAI models. The results of the prediction model showed that five groundwater chemistry parameters were significantly impacted by road transport systems with below a mean absolute percentage error of 0.20, including, pH, temperature, aluminum (Al), bicarbonate (HCO3−), and alkalinity. Additionally, XAI models were developed to understand the relationship between the road transport attributes on five selected parameters. The findings collectively indicated that the Texas groundwater qualities are greatly impacted by road transport systems within a distance of 50-meters and a well depth of 100-meters. This study provides a novel contribution to monitoring point sources of groundwater pollution using XAI techniques.

Spatiotemporal-restricted A∗ algorithm as a support for lane-free traffic at intersections with mixed flows

Improving the capacity of intersections is the key to enhancing road traffic systems. Benefiting from the application of Connected Automated Vehicles (CAVs) in the foreseeing future, it is promising to fully utilize spatiotemporal resources at intersections through cooperative and intelligent trajectory planning for CAVs. Lane-free traffic is currently a highly anticipated solution that can achieve more flexible trajectories without being limited by lane boundaries. However, it is challenging to apply efficient lane-free traffic to be compatible with the traditional intersection control mode for mixed flow composed of CAVs and Human-driving Vehicles (HVs). To address the research gap, this paper proposes a spatiotemporal-restricted A∗ algorithm to obtain efficient and flexible lane-free trajectories for CAVs. First, we restrict the feasible area of the heuristic search algorithm by considering the feasible area and orientation of vehicles to maintain the trajectory directionality of different turning behaviors. Second, we propose a spatiotemporal sparse sampling method by defining the four-dimensional spatiotemporal grid to accelerate the execution of the heuristic search algorithm. Third, we consider the motions of HVs as dynamic obstacles with rational trajectory fluctuation during the process of trajectory planning for CAVs. The proposed method can retain the advantage of efficiently exploring feasible trajectories through the hybrid A∗ algorithm, while also utilizing multiple spatiotemporal constraints to accelerate solution efficiency. The experimental results of the simulated and real scenarios with mixed flows show that the proposed model can continuously enhance traffic efficiency and fuel economy as the penetration of CAVs gradually increases.

The impact of driver turnover on traffic safety

This article discusses socio-economic approaches to ensuring road safety, which is one of the main problems facing road transport in our republic. In the road traffic system, the driver is the controlling link, so the problem of traffic safety should be considered not only as a technical one, but also as a social one, coordinating a link of other links. For this reason, the driver was chosen as the subject of the study. First of all, an analysis of road accidents that occurred in our country over the past two years was presented, according to the social indicator of the driver. At the next stage, the main indicators of the study were determined and research methods were developed for each indicator: Methods for studying statistical accounting and reporting, Interviewing, Questionnaire method. In conclusion , the study presents the results of a sociological study reflecting the problems of individual safety in the road traffic system. An assessment is given for road safety socio-economic factors. A sociological model of accident rates and driver stability is proposed .

FedBEVT: Federated Learning Bird's Eye View Perception Transformer in Road Traffic Systems

FedBEVT: Federated Learning Bird's Eye View Perception Transformer in Road Traffic Systems

Evaluation of Car-Following Model for Mixed Autonomous and Human Driven Vehicles on Road Facilities.

Driverless cars are emerging slowly but bear the opportunity to improve the traffic system efficiency and user comfort. For the near future, a mix of human-driven and driver-less vehicle co- existence is inevitable. The quest to integrate autonomous and human-driven vehicles has created numerous critical questions in the road traffic system: How can autonomous and human- driven vehicles co-exist efficiently? What are the prospects of breaching the existing car-following model widely adopted to control the longitudinal movement of vehicles and control the driver’s maintenance of a safe distance? There is no doubt, that the emergence of autonomous vehicles and their integration is altering the existing traffic theories and the idea behind the car-following model. Currently, researchers are working hard to efficiently describe the physics behind the traffic flow theory of car-following models in mixed traffic. This work investigated a homogeneous car-following model sensitivity with varying human drivers’ reaction time in mixed traffic. The ability to predict the optimal vehicle response time in a platoon to the behaviour of its predecessor is vital in predicting the effect a change in the driving environment of mixed traffic has on traffic flow. The major complexities surrounding the car- following model in a mixed traffic flow environment are how the traffic participants share the road intersection space and the car-following behavior of human-driven vehicles. Investigation in microscopic traffic flow describes the way a single car be- haves and then introduces the impact another car has on a car’s behavior to address the mixed traffic flow. The traffic speed performance under the different traffic conditions suggests that the proposed mixed traffic car-following model outperforms the existing car-following model for human-driven vehicles with an average of 22.59mph. There is a significant throughput improvement in a mixed traffic environment when the distance headway of autonomous vehicles is adjusted to support the research hypothesis.

An Urban Traffic Dataset Composed of Visible Images and Their Semantic Segmentation Generated by the CARLA Simulator

A dataset of aerial urban traffic images and their semantic segmentation is presented to be used to train computer vision algorithms, among which those based on convolutional neural networks stand out. This article explains the process of creating the complete dataset, which includes the acquisition of the images, the labeling of vehicles, pedestrians, and pedestrian crossings as well as a description of the structure and content of the dataset (which amounts to 8694 images including visible images and those corresponding to the semantic segmentation). The images were generated using the CARLA simulator (but were like those that could be obtained with fixed aerial cameras or by using multi-copter drones) in the field of intelligent transportation management. The presented dataset is available and accessible to improve the performance of vision and road traffic management systems, especially for the detection of incorrect or dangerous maneuvers.

Further steps in the digitalisation of tax law

The digitalization of tax law has a decade-long history, the primary goal of which is to increase government revenues and reduce tax evasion. Several elements of this digitalization process are known: the online cash register, the Electronic Road Traffic Control System (EKÁER) system and the Online Invoicing System. My main objective is to prove how useful the state-of-the-art technological solutions that have been debuting in recent years are from the point of view of public finances, since, for example, VAT revenues have more than doubled. In this study, I undertake to review the most important rules of the Online Invoicing System. After examining the legal background, I am processing a case brought before the Curia in which the plaintiff of the dispute was a VAT taxpayer who was unentitled to deduct tax, and the defendant was the Appeal Directorate of the National Tax and Customs Administration (NAV). Next, I will look at an Argentine procedure, electronic invoicing – e-Factura in Spanish – which has been optional on a voluntary basis since 2003 and has become mandatory for all taxpayers subject to VAT since 2016. The introduction of the new system was implemented in stages and was finally fully implemented by 2019. At the end of the article, I discuss the changes affecting the Hungarian regulations in 2023, and then I present the revised rules of e-VAT and finally the e-receipt.

Characteristics of heavy metals in road dust: An overview of South Korean cases

The urbanization and industrialization of our society necessitate the extension of road traffic systems. Road dust generated by road traffic is harmful to the human respiratory system. In particular, heavy metals adsorbed on road dust can pose substantial risks to human health owing to their toxicity, environmental longevity, and ability to accumulate in the human body. Although the evaluation of the concentration of heavy metals in road dust is essential for understanding their sources and risks to human health, there is a lack of comprehensive information on the heavy metal content in road dust in South Korea. In this review, sampling methods and analytical techniques for characterizing the contents of various heavy metals in road dust collected from different regions of South Korea are discussed. Cu, Zn, Cd, Pb, Ni, Cr, As, and Hg are the most frequently found heavy metals in road dust, and their concentrations are strongly associated with the sampling locations (e.g., industrial vs. residential sites and rural vs. urban areas) and particle size of the road dust. Road dust samples collected from more industrialized regions tend to contain more heavy metals. Further, smaller dust particles are likely apt to contain more heavy metals. The application of non-destructive analytical techniques is also necessary for the accurate characterization of heavy metals in road dust.

Temporal variations in urban road network traffic performance during the early application of a cooperative vehicle infrastructure system: Evidence from the real world

A cooperative vehicle infrastructure system (CVIS) can promote the sustainable development of urban road traffic systems. This study collected over 7 million vehicle operating data points using a CVIS in the early stage over 28 days. The data were divided into two categories based on the CVIS type: passive CVIS (P-CVIS), which does not utilize a speed-guidance function, and active CVIS (A-CVIS), which incorporates a speed-guidance function. By comprehensively utilizing traffic flow parameter relationships, the Two-Fluid model, and vehicle energy flow theory, this study analyzed the impact of the CVIS in the early stage on traffic efficiency and energy consumption in the long-term cycle. The correlation between the different evaluation variables was also analyzed. The results indicate that the A-CVIS is more effective than the P-CVIS at improving traffic efficiency. However, driver unfamiliarity with the speed-guidance function results in increased vehicle acceleration, decreased travel comfort, and increased vehicle and network energy consumption. Furthermore, as time progresses, drivers become more proficient with the CVIS, resulting in a gradual improvement in traffic efficiency but a continuous increase in traffic energy consumption. Additionally, the study suggests that drivers may require at least a week to understand the basic skills of using an A-CVIS. This study can contribute to the development and application of eco-intelligent transportation system.