Traffic Density Research Articles

Traffix : Efficient Traffic Control using IoT

This paper aims to alleviate traffic congestion brought on by antiquated, ineffective traffic management systems that are based on a predefined countdown. Long red light delays are the result of these traditional systems, which have a predefined countdown regardless of the actual traffic on a given road. Our system makes sure that time set for the traffic lights reflects the traffic density in real time, which ensures efficient use of time. In order to do this, we first compute the traffic density, which is ascertained by combining image processing methods along with the use of ultrasonic sensors. The Raspberry Pi then processes this data and then manages the time set for the traffic light. Furthermore, the use of SQL Alchemy ensures that this processed information is stored to the cloud, where it may be utilized in events of sensor failure or system malfunction. Index Terms—Image Processing, Raspberry Pi, Traffic Congestion, Ultrasonic sensors

Traffic Flow Optimization for Metropolitan Cities

This research paper presents the design and implementation of an adaptive traffic signal timer system that utilizes real-time traffic density calculation and an intelligent signal switching algorithm to optimize traffic flow at intersections. The proposed system leverages computer vision techniques like object detection to count and classify vehicles, and then dynamically adjusts the green signal durations based on the detected traffic density. A simulation module is also developed to visualize the system's performance and compare it to a static traffic signal implementation. The results demonstrate the effectiveness of the adaptive approach in reducing vehicle waiting times and improving overall intersection throughput

Research on a Simulation and Prediction Method of Traffic Flow Information Based on PINN

Traffic flow prediction can help intelligent transportation effectively be carried out. This paper employs the Physics-Informed Neural Network (PINN) as a deep learning method and partial differential equation (PDE) multivariable methods to approximate solutions for the Lighthill-Whitham-Richards (LWR) traffic flow equation system. The relationship between traffic flow density function and time/displacement is obtained by setting different function conditions and initial boundary constraints. Furthermore, a series of three-dimensional graphics are generated during the research process through dynamic comparisons and evaluations of independent variables to intuitively display and analyze traffic flow trends and gradients. Additionally, before the commencement of the study, the authors propose specific initial condition combinations corresponding to real-world application scenarios to enhance the practicality of the research. Moreover, through the interpretation and reflection on the obtained images, the study identifies inconsistencies between actual situations and predictions, leading to necessary adjustments. Furthermore, the research explores the compatibility of the u(x) function and hard constraint conditions in different scenarios, aiming to accurately predict traffic information and ultimately enhance the utilization of traffic resources. By leveraging PINN and PDE technologies, this study contributes to advancing traffic flow analysis and optimization, potentially influencing urban planning and traffic management strategies positively.

A census tract-level assessment of social determinants of health, traffic exposure, and asthma exacerbations in New York State's Medicaid Population (2005–2015)

This study aims to evaluate the association between social determinants, environmental exposure metrics, and the risk of asthma emergency department (ED) visits in the New York State (NYS) Medicaid population using small-area analysis. Traffic densities for each census tract in NYS were calculated using the length of road segments within each tract and total area of the tract to produce a measure of average number of vehicles per square meter per day. Data on social determinants of health including internal and external environments and other demographic factors were obtained from various sources. Poisson regression analyses were conducted to identify significant factors associated with asthma ED visits in Medicaid claim and encounter data for years 2005–2015. High traffic density in NYS excluding New York City (NYC) correlated with increased risk of asthma ED visits (RR 1.69; 95% CI: 1.42, 2.00), mitigated by adjusting for environmental and social determinants (RR 1.00; 95% CI: 0.85, 1.19). Similar trends were observed in NYC only (RR 1.19; 95% CI: 1.00, 1.41), with the adjusted risk remaining elevated (RR 1.14; 95% CI: 0.98, 1.33) albeit not statistically significant. Living in census tracts with high concentrated disadvantage index, high proportions of minorities, and less green space predicted higher asthma ED visits. We mapped predicted rates and model residuals to identify areas of high risk. Our results support previous findings that environmental and social risk factors in poor and urban areas contribute to asthma exacerbations in the NYS Medicaid population, even if they may not necessarily contribute to its development.

When Do Users Prefer Voice Control Systems in Vehicles? A Survey of Chinese Drivers

Voice control systems (VCSs) are becoming increasingly common in modern vehicles, but concerns are still expressed by drivers about adopting them in smart cockpits. Previous research on privacy and recognition accuracy may not fully address users’ needs with regard to VCSs. In addition, studies on the safety impacts of different interaction modalities may not reveal drivers’ preference for interaction modalities, given that driver choice may not be solely based on interaction safety. Thus, to better understand and optimize VCSs design, an online survey was conducted in China to investigate drivers’ choices between VCSs and manual interaction. In total, we analyzed 168 drivers’ preferred interaction modality (i.e., either VCSs or manual interaction) in different scenarios defined by passenger presence (i.e., present versus absent), traffic complexity (i.e., low versus high traffic density), roadway type (i.e., urban road versus highway), and task characteristics (i.e., six in-vehicle interaction tasks). Compared with manual interactions, drivers preferred VCSs when driving alone, driving on highways, and driving in complex traffic. Further, drivers preferred VCSs when in-vehicle tasks were more distracting and time-demanding (e.g., compiling a text message). The preference for interaction modalities could also be affected by the characteristics of drivers: those with lower driving frequencies and higher VCSs familiarity and those who perceived higher VCSs usability tended to choose VCSs as an interaction modality for in-vehicle interaction tasks. These findings offer insights for adaptive interface design and future optimization of VCSs.

Signal Master using YOLO

As urban populations and automobile numbers continue to swell, traffic congestion emerges as a pressing concern, inflicting delays, stress, heightened fuel consumption, and increased air pollution. Megacities, in particular, bear the brunt of this escalating issue. Real-time assessment of road traffic density becomes imperative for efficient signal control and traffic management. Among the pivotal factors influencing traffic flow, the traffic controller stands paramount, necessitating optimization to meet the surging demand. Our proposed system capitalizes on live camera feeds from traffic junctions to conduct traffic density calculations through image processing techniques and artificial intelligence (AI). By harnessing these technologies, the system aims to offer a dynamic solution to the persistent challenge of congestion. The core focus lies in devising an algorithm that dynamically adjusts traffic light signals based on the detected vehicle density, thereby mitigating congestion and fostering smoother transit experiences for commuters. This innovative approach not only promises expedited travel times but also holds the potential to curtail pollution levels, contributing to a more sustainable urban environment. By seamlessly integrating image processing and AI-driven traffic control mechanisms, our system endeavors to pave the way towards a more efficient and eco-friendly transportation infrastructure

Multi-Agent Cooperative Camera-Based Semantic Grid Generation

The idea of cooperative perception for navigation assistance was introduced about a decade ago with the aim to increase safety on dangerous areas like intersections. In this context, roadside infrastructure appeared very recently to provide a new point of view of the scene. In this paper, we propose to combine the Vehicle-To-Vehicle (V2V) and Vehicle-To-Infrastructure (V2I) approaches in order to take advantage of the elevated points of view offered by the infrastructure and the in-scene points of view offered by the vehicles to build a semantic grid map of the moving elements in the scene. To create this map, we chose to use camera information and 2-Dimentional (2D) bounding boxes in order to minimize the impact on the network and ignored possible depth information as opposed to all state-of-the art methods. We propose a framework based on two fusion methods: one based on the Bayesian theory and the other on the Dempster-Shafer Theory (DST) to merge the information and chose a label for each cell of the semantic grid in order to assess the best fusion method. Finally, we evaluate our approach on a set of datasets that we generated from the CARLA simulator varying the proportion of Connected Vehicle (CV) and the traffic density. We also show the superiority of the method based on the DST with a gain on the mean intersection over union between the two methods of up to 23.35%.

REAL-TIME TRAFFIC LIGHT OPTIMIZATION USING AI AND IOT

In modern cities, the escalating number of vehicles has led to significant traffic issues, affecting road capacity and service quality. Traditional traffic control systems, reliant on fixed signal timers, struggle to adapt to changing traffic dynamics, exacerbating congestion. This paper proposes an innovative approach to traffic management utilizing advanced Computer Vision technology, specifically the YOLOv7 object detection algorithm. By analysing live CCTV footage at intersections, the system dynamically assesses traffic density, identifies vehicle types, and adjusts signal timings in real-time. The system architecture ensures swift processing and response times, with YOLOv7 enabling rapid and accurate vehicle detection. This enables the system to make timely decisions, thereby enhancing overall traffic management efficacy. Leveraging Artificial Intelligence (AI) and Machine Learning techniques, the proposed solution addresses the urgent need for innovative traffic management strategies in urban areas, aiming to alleviate congestion, enhance traffic flow, and reduce environmental impact. Hence, the integration of YOLOv7 technology with adaptive traffic signal switching algorithms represents a promising step towards addressing the complex challenges of urban traffic congestion. Key Words: Computer Vision, Artificial Intelligence, Machine Learning, Traffic Prediction, Adaptive Control, YOLO.

A novel real-time data driven method for floating vehicle speed trend prediction

Traffic congestion in urban areas has become a major worldwide problem. As an important direction of the Intelligent Transportation System (ITS), traffic-speed prediction can help drivers better plan routes and shorten travel time according to IOT techniques, thereby effectively alleviating the problem of traffic congestion. Traffic speed changes dynamically over time, so forecasting using historical data may not be able to quickly adapt to sudden changes in traffic conditions, and predicted traffic conditions may lag behind. The use of real-time data can capture instantaneous changes in traffic conditions, which is more adaptable to different traffic scenarios. In order to further explore the advantages of using real-time data for traffic forecasting, a novel real-time Data Driven method for traffic Speed trend Prediction (2DSP) is proposed. The 2DSP method can predict the macro-level traffic speed trend (rising or falling) by using only near-real-time microscopic vehicle information, which effectively captures the dynamic changes in traffic speed. In addition, an adaptive time-slicing strategy based on traffic density is proposed. This strategy dynamically divides time slices based on traffic density, reducing the frequency of data processing and improving the user experience. The effectiveness of the 2DSP method is validated using two real traffic datasets of floating vehicles. The experimental results show that the 2DSP method has good potential for real-time traffic-speed trend prediction.

Evaluating Environmental Justice and Public Housing in a Data-Rich Era

We examined the spatial concentration of public housing, demographic indicators of low socioeconomic status, and environmental locally unwanted land uses (LULUs) in eight populous U.S. cities. Using the updated EJScreen database and its geographic information systems capabilities, we, as expected, found subsidized housing to be disproportionately colocated in areas with poor and underserved residents. Underground storage tanks and high traffic density were consistently associated with the location of public housing, whereas Superfund sites were located near public housing in only half of the cities in the study. Increasing our understanding of the variables typically used to measure environmental and social justice is important to expand the discussion around a broader set of environmental measures that might be more relevant to the communities that live near them without ignoring the traditional ones that have marked the early legacy of the environmental justice movement.

Incorporating Driving Behavior Metrics Derived from Naturalistic Driving Data into Macroscopic Safety Modeling

This research leveraged datasets from the Strategic Highway Research Program 2 (SHRP2) Naturalistic Driving Study (NDS) to explore the potential benefits of incorporating macroscopic measures derived from NDS into traditional safety modeling. Large datasets with traversals from more than 1,700 unique drivers were used to extract driving behavior on freeway segments. New sets of time series totaling over 1,600 h of driving were developed, including vehicle dynamics exclusively during car-following, while also tracking the spacing between the instrumented vehicle and the vehicle being followed. This paper focuses on the statistical modeling of crash frequency incorporating macroscopic metrics derived from the new time-series datasets as regards the mean, median, variance, and 85th percentile of vehicle spacing, vehicle speed, and traffic density. Results of this exploration indicate that an increase in the traffic density variance, an increase in the speed variance, and a decrease in the mean vehicle spacing had significant effects associated with increases in multi-vehicle crash frequencies. These results can be used to estimate the safety effect of countermeasures that may change speed, density, and or spacing, along with changes in annual average daily traffic (AADT).

Safe Hybrid-Action Reinforcement Learning-Based Decision and Control for Discretionary Lane Change

Autonomous lane-change, a key feature of advanced driver-assistance systems, can enhance traffic efficiency and reduce the incidence of accidents. However, safe driving of autonomous vehicles remains challenging in complex environments. How to perform safe and appropriate lane change is a popular topic of research in the field of autonomous driving. Currently, few papers consider the safety of reinforcement learning in discretionary lane-change scenarios. We introduce safe hybrid-action reinforcement learning into discretionary lane change for the first time and propose the Parameterized Soft Actor–Critic with PID Lagrangian (PASAC-PIDLag) algorithm. Furthermore, we conduct a comparative analysis with Parameterized Soft Actor–Critic (PASAC), which is an unsafe version of PASAC-PIDLag. Both algorithms are employed to train the lane-change strategy to output both discrete lane-change decisions and continuous longitudinal vehicle acceleration. Our simulation results indicate that at a traffic density of 15 vehicles per kilometer (15 veh/km), the PASAC-PIDLag algorithm exhibits superior safety with a collision rate of 0%, outperforming the PASAC algorithm, which has a collision rate of 1%. The generalization assessments reveal that at low traffic density levels, both the PASAC-PIDLag and PASAC algorithms are proficient in attaining zero collision rates. However, at high traffic density levels, although both algorithms result in collisions, PASAC-PIDLag has a much lower collision rate than PASAC.

Contrails and Their Dependence on Meteorological Situations

Contrails created by aircraft are a very hot topic today because they contribute to the warming of the atmosphere. Air traffic density is very high, and current forecasts predict a further significant increase. Increased air traffic volume is associated with an increased occurrence of contrails and induced cirrus clouds. The scientific level of contrails and their impact on the Earth’s climate is surprisingly low. The scientific studies published so far are mainly based on global models, in situ measurements, and satellite observations of contrails. The research is based on observations of contrails in flight paths in the vicinity of Děčín and Prague, and the collection of flight and meteorological data. It focused on the influence of the meteorological situation on the formation of persistent contrails. The collected data on contrails and meteorological variables were statistically processed using machine learning methods for classification models. Several models were developed to predict and simulate the properties of contrails as a function of given air traffic and meteorological conditions. The Random Forests model produced the best results. Dependencies between meteorological conditions, formation, and contrail lifetime were found. The aim of the study was to identify the possibility of using available meteorological data to predict persistent contrails.

Wildlife fencing at German highways and federal roads – requirements and management implications

In Germany, the high risk of wildlife–vehicle collisions (WVC) is further increasing due to increasing traffic volumes and road densities as well as the growing population densities of common ungulate species. As a result, threats to human health and property as well as wildlife mortality of widely spread and rare species increase. Currently, three basic types of wildlife fences are used in Germany: type A, a conventional galvanized‐high tensile deer fence (made of knot braid); type B, a chain wire (mesh wire) fence; type C, a rigid welded wire mesh fence panels. Since fencing needs to restrict access of many different species with different behaviours (e.g. jumping, climbing, digging), fencing needs to be multifaceted to be effectively. Furthermore, the occurrence of wildlife species with habits such as jumping, climbing or digging determines the optimal (functional) fence design per location. We surveyed road managers in combination with a personal assessment of road sections in Germany and derived the following recommendations for optimal fencing to reduce WVC: 1) To deter digging, use plates made of recycled synthetic materials or a concrete foundation, instead of barbed wire. 2) Fencing should be made of chain wire (mesh wire, type B) fence or rigid welded wire mesh fence panels (type C) instead of knot braid mesh (type A). 3) To restrict climbing, use angled chain wire fence or rigid welded wire mesh fence panels at the top of the fences. 4) Maintain fences so that they are kept free from ingrown vegetation/woods. Maintenance conditions should be considered while planning and building the fence, especially to ensure sufficient space on both sides for accessibility. 5) Fencing should be established preferably near the roadside and moved away from property lines. In conclusion, wildlife fencing could be a very effective mitigation measure to prevent WVC with common as well as protected species, when proper designed and recommendations of the survey will be consequently considered. Currently many wildlife fences lack functionality due to an inappropriate design and maintenance issues in Germany.

Urban structure types and students’ academic performance

ABSTRACT In this study, we propose a novel approach for estimating the relationship between neighborhood characteristics and students’ academic performance. We propose the concept of urban morphology by Urban Structure Types (USTs). USTs are spatial indicators that describe the urban system through its physical, environmental, and functional characteristics. Our academic performance data includes 344,175 students from 256 public schools in the Federal District (FD), Brazil. This is student-level academic achievement data from 2017 to 2020. We performed the UST mapping in the FD by using visual interpretation. We classified 21 different types of UST. We fit mixed-effects regression models with a student-specific random intercept and slope. The model was adjusted for temporal factors, SES factors, and variables representing the characteristics and the location of each school. Our findings suggest associations between several types of USTs surrounding schools and academic performance. Overall, areas characterized as low population density, with high green index, and high standard residences were associated with an increase in student performance. In contrast, areas that include old buildings near streets, with significant traffic density, and areas with significant exposed soil (areas devasted) were associated with a decrease in student performance. The results of our study support the creation of effective educational and urban planning policies for local interventions. These interventions are likely to translate into healthier schools and improvements in children's behavioral development and learning performance.

LNG Logistics Model to Meet Demand for Bunker Fuel

The main objective of this manuscript is to build a model for the distribution of LNG as a marine fuel in the southern Baltic Sea based on a genetic algorithm in terms of cost. In order to achieve this, it was necessary to develop, in detail, research sub-objectives like analysis of the intensity of ship traffic in the indicated area and analysis of LNG demand in maritime transport. In the first part of this study, the authors use data from the IALA IWRAP Mk2 and the Statistical Office in Szczecin to analyse the marine traffic density (by type of vessel) in the southern part of the Baltic Sea. LNG used as marine fuel reduces toxic emissions into the atmosphere. The authors specify the LNG fleet size and locations of LNG storage facilities in a way to ensure that the defined LNG bunker vessels can supply fuel to LNG-powered vessels within the shortest possible time period. The database contains a set of traits necessary to determine the optimal demand for LNG. The traits were developed based on an existing LNG fleet and appropriately selected infrastructure, and they represent existing LNG-powered vessels as well as LNG bunker vessels and their specifications. Based on the created LNG distribution model, were performed in Matlab R2019a software. An LNG distribution model was developed, which uses a genetic algorithm to solve the task. The demand for LNG for the sea area under analysis was determined based on data on the capacity of LNG-powered vessels (by type of vessel) and their distance from the specified port.

SEATANI: hazards from seamounts in Southeast Asia, Taiwan, and Andaman and Nicobar Islands (eastern India)

Abstract. Submarine volcanism makes up approximately 85 % of volcanism that occurs on Earth, and its eruptions have the potential to cause several hazards including ash dispersal, pumice rafts, pyroclastic density currents, sector collapses, and tsunamis. Recent examples include the eruptions in Japan and in the Kingdom of Tonga in 2021 and 2022 respectively, but there has been little to no study of submarine volcanism in Southeast Asia and surroundings. Here we provide a compilation of 466 seamounts from the region, from different published sources, through the SEATANI dataset (Southeast Asia, Taiwan, and the Andaman and Nicobar Islands). We use this newly compiled dataset to assess on a regional level the seamount hazard potential and exposure potential as a springboard for future more quantitative hazard studies of the region. The hazard potential was assessed through seamount morphological and structural analyses, to determine the seamount evolution stage and grade of maturity. The exposure potential was evaluated with two different approaches: an areal analysis of the number of assets within a 100 km radius of each seamount and the development of a hazard-weighted seamount density map to highlight potential areas of interest for future more-in-depth studies. Our results show that there are several potentially hazardous seamounts in this region. Taiwan has the highest hazard and exposure potential, for all assets considered, while the Philippines, Indonesia, and Vietnam have relatively high exposure potential for submarine communication cables and ship traffic density. The results from this work serve as a first step towards Southeast Asia and neighbouring countries becoming more resilient against and prepared for submarine volcanic eruptions in the region.

Fair and efficient resource allocation via vehicle-edge cooperation in 5G-V2X networks

To cope with safety risks and operational efficiency problems, it is of paramount importance to ensure high data rates and meet the latency requirements in Connected and Autonomous Vehicles. The problem in such environments is two-fold: 1. Heavy load on the network due to increasing demands; 2) Resource imbalance, due to variations in the vehicular traffic density in certain regions. The consequences of these two phenomena may lead to service disruptions, as well as the fairness of resource allocation across vehicles. In this work, we propose a resource allocation method that distributes high workload among edge nodes and allocates network resources efficiently and fairly. Performance of the proposed method is evaluated under realistic scenarios, and compared to the state-of-the-art approaches in the literature. Behavior and performance of all methods in overload conditions in certain regions were analyzed. Simulation results exhibit a 38% improvement in the successful demand rate and a 48% improvement in capacity usage compared to state-of-the-art approaches.

Modelling and numerical simulation of high-speed railway slab track structure

In terms of maintenance and structural behavior, slab track proves to be an advantage over conventional ballasted track due to increasing train speed, axle load, and traffic density. Since the vibration, noise, and risk of derailment, all accelerate as train speed increases, an in-depth investigation of track dynamics becomes essential for identifying the fundamental cause of the problem. In this paper modelling and numerical simulation of high-speed railway slab track structure has been studied using finite element method. Using the multi-body simulation approach and the finite element method a model of the 3D slab track system is developed. The slab track model has rail, rail pad, and concrete slab, HBL, and subgrade layers. In order to determine the fundamental frequency and the mode shapes associated with it, a modal analysis is carried out. Dynamic response, or acceleration against frequency curves derived via harmonic response analysis, is the result of the numerical simulation. The dynamic reaction of the structure of a high-speed slab track is studied, and the effect of elastic materials on reducing vibration is investigated. The results suggest that a layer of elastic material, like a slab of mat, inserted between a layer of concrete slab and a layer of HBL is capable of lowering the amount of vibration response of the track.

A multi-criteria framework for electric vehicle charging location selection using double hierarchy preferences and unknown weights

The adverse effects of traditional vehicles on the environment increase the demand for clean vehicles, such as electric vehicles (EVs). The correct positioning of the charging points for such vehicles certainly promotes the acceptance and spread of EVs. Indeed, selecting optimal locations for electric vehicle charging stations (EVCS) is crucial for shaping a sustainable future. This study introduces an integrated methodology under a double hierarchy linguistic context with a criteria importance through an inter-criteria correlation (CRITIC) technique for experts' reliability determination, an attitudinal Cronbach's method for criteria weight estimation, and a novel multi-criteria technique considering the compromise ranking of alternatives from distance to ideal solution (CRADIS) formulation for optimal EVCS location selection. Based on the results, criteria such as service capability, ecological impact, land cost, and traffic density are the most crucial, with Manapparai, India, as the optimal location for a new EVCS construction. Further, a crucial finding is that the social dimension is substantial compared to the economy and environment dimensions for EVCS location selection. The novelty of the paper is that (i) uncertainty and expression of choices in natural language form for locations for EVCS are modeled effectively using a double hierarchy structure, (ii) experts' weights are obtained methodically by considering hesitation and interactions among experts, (iii) interdependencies among criteria and importance of experts are considered during criteria weight determination, and (iv) locations are ranked by not only considering criteria type but also resembles closely to the human-centric decision process. A detailed sensitivity analysis is further conducted to prove the proposed approach's effectiveness and stability. In the context of sustainable transportation, the work could contribute to the relevant literature through a powerful decision-making tool.