Traffic Flow Research Articles

Complex Traffic Flow Model for Analysis and Optimization of Fuel Consumption and Emissions at Large Roundabouts

Complex Traffic Flow Model for Analysis and Optimization of Fuel Consumption and Emissions at Large Roundabouts

Laboratory and Field Evaluation of Asphalt Concrete Modulus &Critical Strain Inputs for M-E Flexible Pavement Design in the State of Illinois

This study aims to update the current algorithm for modulus prediction of hot mix asphalt in the state of Illinois-USA. Numerically, laboratory, and field-obtained modulus and strain levels were connected to advances in asphalt materials and current design criteria. Four mix designs were selected and combined with seven different binders for modulus measurements. The reference experimental results were compared to: the current Illinois Department of Transportation (IDOT) modulus algorithm, traditional regression models, a Bayesian Neural Network (BNN) model, and field measurements obtained using the Traffic Speed Deflectometer. Results showed that the current IDOT algorithm under-predicts modulus and BNN (840 data points, R^2 = 0.986) outperformed the Witczak and Hirsch models. Field modulus and critical strains were sensitive to temperature and showed considerable variability, but confirmed that HMA in perpetual pavement sections performs under low strain levels. These findings guided considerations for an updated design method: realistic modulus prediction can be achieved using data-driven methods and less conservative strain criterion might be considered.

Research on traffic flow forecasting based on interactive dynamic meta-graph learning

Traffic flow exhibits intricate dynamic spatial-temporal correlation. Aiming at the difficulty in capturing the long-term dependence and dynamic spatial correlations among concealed road nodes of in traffic flow, a new Interactive Dynamic forecasting model based on Meta-graph learning (Mega-ID) is proposed, which combines spatial-temporal transformer and interactive dynamic graph convolution (IDGCN) to optimize the Meta-graph module. Specifically, it optimizes a spatial-temporal meta-graph with memory and discrimination capabilities. The model introduces a Dynamic Graph Convolution (DGCN) embedded Interactive Learning structure, which simultaneously captures the hidden dynamic spatial correlations and long-term dependency of traffic flow. The experimental results demonstrate that the method proposed in this paper can capture the hidden dynamic spatial correlation and long-term dependence, leading to better forecasting performance compared to other baseline models.

Identifying patterns of change in traffic flows’ parameters depending on the organization of public transport movement

This study examines the issue of traffic organization on sections of city streets, in which there are public transport stop zones of different configurations (with a drive-in pocket and along a traffic lane). Accordingly, the object of research is the parameters of traffic flows; the subject is the regularities in their change on such specific sections of the street-road network, taking into account the configuration of stops, the number of traffic lanes, and priority conditions for the movement of public transport. The task addressed in this work was the quantitative assessment of the efficiency of traffic management in public transport stop zones. It was also important to compare different configurations of street segments in terms of their impact on delays of private and public transport. As a result of the research, the speed and time characteristics of the traffic flow and their dependence on its composition and intensity for different number and specialization of traffic lanes, as well as the location of the public transport stop, were determined. The resulting quantitative indicators of delays of all types of transport for each modeling option made it possible to determine the best of them according to the criterion of minimal time loss. This applies to both private and public transport, as the values of delays may differ from each other by 10–50 %. An applied aspect related to using the scientific result is the possibility of justifying the number of traffic lanes, or their allocation for public transport, as well as determining the appropriate configuration of stops. This constitutes the prerequisites for the transfer of the scientific results to the relevant interested structures in the field of transport, which are responsible for the organization and safety of traffic under urban conditions

Modeling and Simulation of Vehicle Velocity-Density on Buah Batu Road Using Decision Tree Regression

This study aims to explore and simulate the traffic flow model on Buah Batu Road using the velocity-density function generated by the Decision Tree Regression method. The model utilizes a macroscopic approach, specifically the Lightill, Whitham, and Richards (LWR) model, which considers vehicle interactions. Observational data were collected directly from Buah Batu Road and processed to produce a velocity-density function, which shows that vehicle speed decreases as density increases, following a non-linear but step-like pattern. The velocity function generated by the Decision Tree Regression indicates that for low density (ρ < 0.102), the average speed is predicted to be around 3.681 to 4.551, while at high density (ρ > 0.273), the speed drops to around 1.411 or lower. The simulation was conducted on a 60-meter road segment with a total simulation time of 5 minutes and a grid resolution of 300 points. At the beginning of the simulation, a peak density of 0.70 was recorded in the 15-25 meter segment, which then shifted and decreased to 0.50 in the 30-50 meter segment by the end. The results indicate that vehicle movement reduces density and improves traffic flow. Thus, the Decision Tree Regression method has proven effective in modelling and simulating the velocity-density relationship to understand traffic dynamics on Buah Batu Road.

Efficient Vehicle Detection and Optimization in Multi-Graph Mode Considering Multi-Section Tracking Based on Geographic Similarity

Vehicle detection is an important part of modern intelligent transportation systems. At present, complex deep learning algorithms are often used for vehicle detection and tracking, but high-precision detection results are often obtained at the cost of time, and the existing research rarely considers optimization algorithms for vehicle information. Based on this, we propose an efficient method for vehicle detection in multi-graph mode and optimization method considering multi-section tracking based on geographic similarity. In this framework, we design a vehicle extraction method based on multi-graph mode and a vehicle detection technology based on traffic flow characteristics, which can cope with the challenge of vehicle detection under an unstable environment. Further, a multi-section tracking optimization technology based on geographic similarity at a high video frame rate is proposed, which can efficiently identify lane change behavior and match, track, and optimize vehicles. Experiments are carried out on several road sections, and the model performance and optimization effect are analyzed. The experimental results show that the vehicle detection and optimization algorithm proposed in this paper has the best effect and high detection accuracy and robustness. The average results of Recall, Precision, and F1 are 0.9715, 0.979, and 0.9752, respectively, all of which are above 0.97, showing certain competitiveness in the field of vehicle detection.

Evaluation of traffic management at Futa Northgate, Akure Ondo state, Nigeria

Due to increasing usage of automobiles, traffic congestion in most cities is becoming an issue and slowing down the day-to-day activities of human and also deteriorating the quality of the road due to the constant congestion. The movement of products and services between locations has become essential and integral to both global and metropolitan economic existence, and modern enterprises, industries, trades, and general activities are dependent on transportation and transportation infrastructure, hence this project is to evaluate the traffic management on the FUTA North Gate Road and propose recommendations to improve traffic flow and reduce congestion. The research identified the causes of traffic congestion, proffered a solution to traffic congestion for the single carriageway under study and analyzed the implications of the proffered traffic management strategy. Data collection on the road was done during peak days of the week (Tuesday – Friday) and also during peak hours of the day i.e. early hours of the morning and in the evening using the traffic count method. The study revealed that the existing single carriageway has a dimension of 3.75-meter width per each side, with a 2.7-meter shoulder, showed 2,585 as the maximum number of vehicles that ply the road causing traffic congestion as a result of poor road conditions, lack of proper traffic management systems, increased population and vehicle ownership, inadequate road infrastructure, and poor driving habits exceeding the capacity. The study concludes that implementing traffic management strategies which includes promoting the use of public transportation, improving the design of intersections and roundabouts, investing in road infrastructure, and educating drivers on safe and responsible driving habits can help improve the traffic flow and reduce congestion on busy roads. While some recommendations may require significant investment, the benefits of a more efficient and sustainable transportation system will far outweigh the costs in the long run. It is important that all stakeholders work together to implement these recommendations and create a transportation system that benefits everyone. Overall, this project highlights the importance of having an efficient and effective traffic management system, and the need to consider all possible impacts before implementing road expansion projects. By adopting a holistic approach to traffic management and implementing the recommended measures, we can create a more efficient and sustainable transportation system that benefits both motorists and the environment giving a long-term solution going ahead.

Traffic flow parameter estimation for complex environments based on improved YOLOv8

Estimation of traffic flow parameters based on computer vision is still a very popular challenge. In particular, the detection problems such as occlusion, small targets, luminance variations, and lighting jitter, etc., are caused by dense traffic scenes and complex weather conditions. Previous studies about detecting and tracking methods focused on daytime and nighttime or single weather condition, but the performance of this model will decline dramatically due to complex conditions. In this paper, a framework for estimating traffic flow parameters in complex environments is presented, in which Ghost-YOLOv8 vehicle detection model is proposed. GhostConv is used to replace part of Conv and a new C2fGhost module is designed to replace part of C2f, reducing the number of parameters and improving the detection performance of the model; The global attention mechanism module is added to the neck network, which strengthens the semantic and location information in the features and improves the model’s ability of feature fusion; In view of the loss of semantic information caused by different scales in detecting small targets, a small target detection layer is added to enhance a combination of deep and shallow semantic information; The GIoU bounding loss function is used instead of the original loss function, which improves the performance of the network’s bounding box regression. Then, combining DeepSORT tracking algorithm and virtual line counting method, the proposed framework estimates traffic flow parameters, including volume, speed, and density in complex environments. The experimental results show that compared with the original model in the UA-DETRAC dataset, the improved YOLOv8 model’s the accuracy is increased by 1.4%, and the parameter number and model size are reduced by 0.229G and 0.2MB respectively. In addition, the framework has good robustness, reaching 97.56% accuracy when estimating average traffic flow parameters. It is sufficient to overcome complex weather conditions and effectively help control traffic for intelligent transportation systems and traffic management to provide good data support. In conclusion, it shows that the model can reduce the number and size of model parameters and improve the detection precision as well as meeting the requirements of edge computing devices and having better real-time performance, so it has practical application value.

Stochastic Lighthill-Whitham-Richards traffic flow model for nonlinear speed-density relationships

Stochasticity is becoming increasingly essential in traffic flow research, given its notable influence in several applications, such as real-time traffic management. To consider stochasticity in macroscopic traffic flow modeling, this paper introduces a stochastic Lighthill-Whitham-Richards (SLWR) model, which not only captures equilibrium values in steady-state conditions but also describes stochastic variabilities. The SLWR model follows a conservation law, in which the free-flow speed is randomized to represent heterogeneities of drivers. To more accurately reflect real-life traffic patterns, a nonlinear speed-density relationship is considered. For addressing this highly nonlinear problem, a dynamically bi-orthogonal (DyBO) method is coupled with the Taylor series expansion technique. The results of simulation experiments show that the SLWR model can effectively describe the evolution of stochastic dynamic traffic with temporal or geometric bottlenecks. Moreover, the DyBO solutions exhibit reasonable accuracy while significantly reducing computation costs compared with the Monte Carlo method.

Development of the intelligent traffic light system based on image processing and fuzzy control techniques

In Viet Nam's current traffic conditions, congestion and jams—especially at intersections during peak hours—present major challenges. Traditional traffic light systems, which rely on fixed timing principles, often fail to manage traffic flow efficiently, particularly when vehicle density varies significantly across different directions. This research aims to develop an intelligent traffic light system where the signal timings automatically adjust based on the vehicle density at intersections. The study uses an object recognition algorithm to identify, classify, and count vehicles. The data was then fed into a fuzzy logic model to calculate the optimal signal timings. Experimental results demonstrate an accuracy of approximately 88% in vehicle detection. The fuzzy logic model and the programmable logic controller were able to effectively compute reasonable signal timings based on real-time vehicle density. Future developments include expanding the system's functionalities, creating a user-friendly interface, and developing a management application for mobile devices.

Exploring Smart Mobility Potential in Kinshasa (DR-Congo) as a Contribution to Mastering Traffic Congestion and Improving Road Safety: A Comprehensive Feasibility Assessment

The urban landscape of Kinshasa, Democratic Republic of Congo, faces significant mobility challenges, primarily stemming from rapid urbanization, overpopulation, and outdated infrastructure. These challenges necessitate the exploration of modern smart mobility concepts to improve traffic flow, road safety, and sustainability. This study investigates the potential of solutions such as Mobility-as-a-Service, car sharing, micro-mobility, Vehicle-as-a-Service, and electric vehicles in addressing these challenges. Through a comparative analysis of global implementations, this research identifies key success factors and barriers that inform the feasibility of integrating these solutions into Kinshasa’s unique socio-political and infrastructural context. The study presents a conceptual framework, supported by stakeholder analysis, for adapting these solutions locally. A detailed feasibility analysis considers technological, economic, social, environmental, and regulatory factors, offering a clear roadmap for implementation. Drawing on lessons from cities facing similar urban mobility challenges, the paper concludes with actionable recommendations and insights for policymakers and urban planners in Kinshasa. This research not only highlights the viability of smart mobility solutions in Kinshasa but also contributes to the broader discourse on sustainable urban development in rapidly growing cities. While smart mobility studies have largely focused on cities with developed infrastructure, there is a gap in understanding how these solutions apply to cities like Kinshasa with different infrastructural and socio-political contexts. Previous research has often overlooked the challenges of integrating smart mobility in rapidly urbanizing cities with underdeveloped transportation systems and financial constraints. This study fills that gap by offering a feasibility analysis tailored to Kinshasa, assessing smart mobility solutions for its traffic congestion and road safety issues. The smart mobility solutions studied—Mobility-as-a-Service (MaaS), car sharing, electric vehicles (EVs), and micro-mobility—were chosen for their ability to address Kinshasa’s key mobility challenges. MaaS reduces reliance on private vehicles, easing congestion and improving public transport. Car sharing offers affordable alternatives to vehicle ownership, essential in a city with income inequality. EVs align with sustainability goals by reducing emissions, while micro-mobility (bikes and e-scooters) improves last-mile connectivity, addressing public transit gaps. These solutions are adaptable to Kinshasa’s context and offer scalable, sustainable improvements for urban mobility.

Towards Predictive Pollution Control Through Traffic Flux Forecasting With Deep Learning: A Case Study in the City of Valencia

ABSTRACTTraffic congestion represents a significant urban challenge, with notable implications for public health and environmental well‐being. Consequently, urban decision‐makers prioritize the mitigation of congestion. This study delves into the efficacy of harnessing extensive data on urban traffic dynamics, coupled with comprehensive knowledge of road networks, to enable Artificial Intelligence (AI) in forecasting traffic flux well in advance. Such forecasts hold promise for informing emission reduction measures, particularly those aligned with Low Emission Zone policies. The investigation centers on Valencia, leveraging its robust traffic sensor infrastructure, one of the most densely deployed worldwide, encompassing approximately 3500 sensors strategically positioned across the city. Employing historical data spanning 2016 and 2017, we undertake the task of training and characterizing a Long Short‐Term Memory (LSTM) Neural Network for the prediction of temporal traffic patterns. Our findings demonstrate the LSTM's efficacy in real‐time forecasting of traffic flow evolution, facilitated by its ability to discern salient patterns within the dataset.

Design and Implementation of a Microcontroller-Based Adaptive Four-Way Traffic Light Control System for Traffic Optimization

This paper presents the design and construction of a microcontroller-based four-way traffic light control system aimed at optimizing traffic flow by automatically adjusting signal timing based on traffic density at each intersection. The system is built around an Arduino ATmega328 microcontroller inter-faced with break beam infrared (IR) sensors (transmitters and receivers) and LED displays. The IR sensors are installed on both sides of the lanes at regulated intervals to detect traffic density. The system is powered by a 12V DC battery and a 5V, 3A power supply is provided using a buck converter IC (LM2596), which steps down the 12V from the battery to 5V, 3A. This 5V power is used to run the Arduino microcontroller and the Darlington pair ICs for current sinking and sourcing. As vehicles pass through the areas monitored by the IR sensors, the traffic density is measured for each opposing lane, allowing the system to determine which lane should be prioritized for traffic flow. The corresponding LED indicators are then activated accordingly.

Linear Regression-Based Traffic Flow Simulation: Vehicle Density and Speed Analysis on Buah Batu Road

Traffic congestion has become an increasingly severe problem in many major cities around the world, including in the city of Bandung. Population growth and increased vehicle use exacerbate congestion. Jalan Buah Batu, one of the main roads in the city of Bandung, often experiences congestion due to high density. This study explains the traffic flow simulation using the Lighthill-Whitham-Richards (LWR) model with a speed-density function obtained from observation data on Jalan Buah Batu, Bandung. The data included the relationship between vehicle density and speed which was then analyzed using the linear regression method. The approximation of the velocity-density function obtained from linear regression is v(ρ)= -6.904+4.302. Traffic flow simulations were carried out with a road length of 60 meters, a total time of 5 minutes, and high resolution with 300 grid points. At the beginning of the simulation, a peak density of 0.70 occurred in a 15-25 meter road segment. Over time, the peak density shifted and decreased: 0.65 at 20-30 meters at 1.25 minutes, 0.60 at 25-35 meters at 2.5 minutes, and 0.50 at 30-50 meters at the end of the simulation (5 minutes). These results show the movement of vehicles that reduce congestion and improve the smooth flow of traffic. In conclusion, linear regression is effective in determining the velocity-density function.

A Study on Predicting Traffic Flow by Random Forest Based on Treatment of Eliminating Skewed Distribution

A Study on Predicting Traffic Flow by Random Forest Based on Treatment of Eliminating Skewed Distribution

Fenomena Keterkaitan Kecepatan Faktual Kendaraan dengan Tingkat Pelayanan Jalan (Studi Kasus: Jalan Asrikaton, Kabupaten Malang)

Asrikaton street, Pakis, Malang Regency is one of the roads with moderate population density and moderate traffic flow conditions. This road is classified as a secondary arterial road and is a border road with Malang City. This road has a length of 1,200 m and a pavement width of 9 meters, with a road type of two undivided lanes (2/2 UD). This study aims to observe and assess the phenomenon of the relevance between the degree of saturation and various types of light vehicle speeds of a road. The traffic volume is 6436 vehicles/hour with a low side obstacle classification, and the degree of saturation shows that the road conditions are still relatively smooth. The maximum traffic flow volume of 2039.95 smp/h occurred at 06:45-07:45 WIB. with a low side obstacle class (equivalent value 198.7), resulting in a degree of saturation of 0.66. The most significant relevance between degree of saturation and vehicle movement speed is journey speed with the equation y = -1196.9x3 + 2008.6x2 - 1095.1x + 234.37, the coefficient of determination of 0.8867.

A Novel Two-Lane Lattice Model Considering the Synergistic Effects of Drivers’ Smooth Driving and Aggressive Lane-Changing Behaviors

Most existing two-lane traffic flow lattice models fail to fully consider the interactions between drivers’ aggressive lane-changing behaviors and their desire for smooth driving, as well as their combined effects on traffic dynamics. To fill this research gap, under symmetric lane-changing rules, this paper proposes a novel two-lane lattice model that incorporates these two factors as co-influencers. Based on linear and nonlinear stability analyses, we derive the linear stability conditions of the new model, along with the density wave equation and its solutions describing traffic congestion propagation near critical points. Numerical simulations validate the theoretical findings. The results indicate that in the two-lane framework, enhancing either drivers’ lane-changing aggressiveness or introducing the desire for smooth driving alone can somewhat improve traffic flow stability. However, when considering their synergistic effects, traffic flow stability is enhanced more significantly, and the traffic congestion is suppressed more effectively.

AI for Traffic Prediction and Management

Urban traffic congestion is a growing problem in cities across the globe, contributing to long delays, higher fuel consumption, environmental degradation, and economic losses. Conventional traffic management systems often depend on static data and rule-based approaches, which fall short in dealing with the complexity and variability of modern traffic. This paper introduces an AI-based traffic management approach that utilizes machine learning models to provide real-time traffic forecasts. By integrating historical data, live sensor inputs, and machine learning techniques, this system aims to enhance traffic flow, alleviate congestion, and improve travel efficiency. The model is compared against existing systems, demonstrating improved accuracy, flexibility, and scalability. Results indicate that the AI-based system offers significant advantages in managing urban traffic, surpassing traditional methods. The study further elaborates on how AI-powered traffic management can cut travel times by ensuring efficiency and safety, therefore playing a part in environmental sustainability through emission reduction, and the opportunities and challenges it brings to the table in the implementation of AI in traffic systems.

IMPROVING SCHOOL TRAFFIC FLOW: A HUMAN PERFORMANCE IMPROVEMENT CASE STUDY

Managing the flow of people (queue management) is a crucial task for many organizations. This case study examines the traffic flow during pick up and drop off times at a public middle school in the rural southeastern U.S. using a Human Performance Improvement (HPI) framework to address the problem of traffic backups when dropping off and picking up students. Environmental analysis revealed that carpool procedures were not well known and staff were underutilized. Recommendations included job aids and signage to inform parents of traffic procedures, efficient scheduling and use of school space, and utilization of the staff to assist with the carpool lane.

Phase transition in heterogeneous macro continuum model integrating the jerk effect with the mixed traffic flow involving human driving and ADAS vehicles

Vehicles equipped with advanced driving assistance systems (ADAS) can acquire information about preceding and following vehicles, which will have an undeniable impact on the phase transition of traffic flow. Therefore, we establish a new heterogeneous continuum model of traffic flow considering the jerk effect mixed with human driving (HD) and ADAS vehicles. The neutral stability condition associated with the permeability of ADAS vehicle is inferred via stability analysis. According to simulation, shock wave occurs, implying that our model can emerge correct wave propagation trend. Moreover, the simulation of density evolution and flow changes also suggests that an increase in ADAS vehicle penetration and jerk effect can enhance traffic system stability and reduce energy consumption.