Vehicular Traffic Flow Research Articles

Deep Learning's Current and Future Applications in Predicting Vehicle Traffic Flow

With the acceleration of urbanization and the continuous growth of traffic flow, accurate prediction of highway traffic flow has become a key demand for optimizing traffic management and alleviating congestion. Traditional prediction methods are often inefficient in dealing with complex traffic patterns, while deep learning technology brings new solutions for traffic flow prediction with its powerful feature learning and pattern recognition capabilities. This paper reviews deep learning applications' current state and future trends in highway traffic flow prediction. It introduces deep learning technology and its advantages in traffic flow prediction. The paper then analyzes the specific applications of Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and their variants in data processing, feature extraction, and prediction performance. The challenges currently faced, such as data preprocessing and the capture of long-term dependencies, are also discussed, along with proposed solutions. Finally, the paper looks forward to the future development of deep learning in the field of traffic flow prediction, highlighting its importance in improving traffic management efficiency.

Checkpoint data-driven GCN-GRU vehicle trajectory and traffic flow prediction

With the development of information technology, massive traffic data-driven short-term traffic situation analysis of urban road networks has become a research hotspot in urban traffic management. Accurate vehicle trajectory and traffic flow prediction can provide technical support for vehicle path planning and road congestion warning. Unlike most studies that use GPS data to predict vehicle trajectories, this paper combines the broad coverage, high reliability, and lighter weight of traffic checkpoint data to propose a method that uses trajectory prediction technology to forecast the traffic flow in urban road networks accurately. The method adopts a checkpoint data-driven approach for data collection, combines graph convolutional neural network (GCN) and gated recurrent unit (GRU) models to more effectively learn and extract spatiotemporal correlation features of vehicle trajectories, which significantly improves the accuracy of vehicle trajectory prediction, and uses the output of the trajectory prediction model to forecast traffic flow more accurately. Firstly, transforming the checkpoint data into daily vehicle trajectories with time series characteristics, realizing the vehicle trajectory travel chain division. Secondly, the adjacency matrix is established by using the spatial relationship of each checkpoint, and the feature matrix of the vehicle’s driving trajectory over time is established, which is used as the input of GCN to learn the spatial characteristics of the vehicle while driving on the road network, and then GRU is added to further process the data after GCN training, constructing a GCN-GRU vehicle trajectory prediction model for vehicle trajectory prediction. Finally, the traffic flow of each checkpoint is calculated based on the prediction result of vehicle trajectory and compared with the real checkpoint flow. This paper conducts many experiments on the Qingdao City Shinan district checkpoint dataset. The results show that compared with the single models GCN, GRU, BiGRU, and BiLSTM, the GCN-GRU model has reduced the MAE by 0.75, 0.46, 0.52, and 0.57, and the RMSE by 0.76, 0.52, 0.58, and 0.68, respectively, demonstrating stronger spatial and temporal correlation characteristics and higher prediction accuracy. The MAPE between the forecasted flow and the real flow is 0.18, which verifies the reliability of the proposed method.

Vehicular Traffic Flow Detection and Monitoring for Implementation of Smart Traffic Light: A Case Study for Road Intersection in Limeira, Brazil

This paper proposes the development of a smart traffic light prototype based on vehicular traffic flow measurement in the stretch between two avenues in the city of Limeira, SP, Brazil, focusing on the stretch towards UNICAMP’s School of Technology. To this end, we initially developed a Python code using the OpenCV library in order to detect and count vehicles. With the counting in operation, programming logic was inserted, aiming at preparing traffic light timers based on vehicular traffic. Finally, the traffic lights were added to display video via a code change to show the ongoing color changes, also obtaining a code for identifying vehicles and flow, in addition to the virtual traffic light system itself in the system. Vehicle counting accuracy was 75% for large vehicles, 90% for passenger cars, and 100% for motorcycles. The simulation of a smart traffic light implementation worked satisfactorily according to the post-processing of the video recorded for validation.

Determinants of driver injury severity in electric vehicle crashes: A random parameters binary probit model with heterogeneity in means and variances

This study aims to investigate the factors significantly affecting occupant injury severity in electric vehicle (EV) accidents, with a particular focus on traffic flow characteristics before accidents, which have often been overlooked in previous research. Using data on EV accidents from January 1, 2021, to December 31, 2021, in Guangdong Province, China, this study considers various vehicle, road, weather, and pre-accident traffic flow characteristics. The research employs the random parameters binary probit model with heterogeneity in means and variances, comparing it with the binary probit model and the random parameters binary probit model to comprehensively address unobserved heterogeneity and further explain the factors contributing to the randomness of random variables. The results indicate that the random parameters binary probit model with heterogeneity in means and variances provides a superior fit. The findings reveal that variables such as the time of day, type of vehicle involved in the collision, color of EV, average morning/evening peak traveling hours significantly impact the severity of injuries in EV accidents. Additionally, the black indicator exhibits heterogeneity in mean and variance during the afternoon period. This study offers an in-depth understanding of the mechanisms behind driver injury severity in EV accidents and contributes to the development of effective countermeasures to protect drivers from severe injuries.

Traffic Impact Analysis Due to Construction of Special Eye Hospital Padang Eye Center

Padang Eye Center is one of the hospitals under construction on Jalan Khatib Sulaiman, Lolong Belanti, North Padang District, Padang City, West Sumatra. The construction of the hospital will certainly have an impact on traffic on Jalan Khatib Sulaiman. The purpose of conducting andalalin is to analyze the amount of travel demand that occurs at the Padang Eye Center Hospital in pre-construction, construction period, operational period, and post 5 years of construction, as well as seeing the impacts that occur and how alternative solutions are carried out. The parameters used are based on the Regulation of the Minister of Transportation of the Republic of Indonesia Number 17 of 2021 concerning the implementation of andalalin, the Indonesian Road Capacity Guidelines (PKJI) of 2023 concerning the performance of road sections and the Directorate General of Land Transportation of 1996 concerning parking. The results of the analysis, namely the existing conditions obtained a V / C ratio of 0.43 level B, the construction period obtained a V / C ratio of 0.45 level C, the operational period with a V / C ratio of 0.45 level C, and after 5 years of operation the V / C ratio is 0.58 level C which means that the flow is stable, but the operating speed begins to be limited based on the level of service (LOS) table. Parking needs based on the building area of 2832 m2 were obtained as many as 113 srp, while based on the available parking area it can accommodate as many as 121 srp, so the parking space requirements of the Padang Eye Center Special Eye Hospital have been met. The alternative solution to this analysis is the placement of regulatory officers in front of the entrance and exit of the Khatib Sulaiman Road intersection during the construction period, regulating parking circulation within the hospital area, and making barrier gates to regulate vehicle traffic flow.

METHODOLOGY OF BUILDING INFORMATION MODELING OF URBAN STREETS AND ROADS

Problem statement. New challenges in road construction require the application of modern and globally recognized best practices in the design and management of road infrastructure construction processes, involving the use of the latest Building Information Modeling (BIM) technologies. The implementation of BIM technologies necessitates conducting research to systematize information, forecast and evaluate outcomes, and develop a modeling methodology. The purpose of the article is to develop a methodology for Building Information Modeling of urban streets and roads. Research Results. The proposed methodology for Building Information Modeling is demonstrated using sections of the street and road network in the city of Dnipro. Digital terrain and site models were created in the InfraWorks software based on geospatial data from remote sensing. Conceptual models of urban streets and roads were developed. The conceptual models were exported to Civil 3D, where the terrain model was refined using ground survey data, analyzed, and used to develop route plans, longitudinal and cross profiles of streets and roads. The detailed and coordinated road design solutions in Civil 3D were exported to InfraWorks to build an integrated road infrastructure. An analysis of the spatial smoothness of routes and sight distances on roads was conducted using the building information model. Models of an overpass and bridge developed in Revit were exported to the road infrastructure model. Traffic management measures were modeled. Using the “Traffic Simulation” tools in InfraWorks, vehicle traffic flows on roads and interchanges of the studied street and road network were simulated, taking into account the actual traffic intensity. The building information models were checked for structural deficiencies using Navisworks software. Conclusion. The proposed methodology for designing urban streets and roads using BIM technology involves the step-by-step development of a digital model utilizing software for the automated design of road infrastructure with the required level of detail at each stage of the design process.

A two-context-aware approach for navigation: A case study for vehicular route recommendation

In contemporary urban environments, route recommendation systems have become an indispensable tool in moving the population from large centers, serving as valuable resources for circumventing traffic congestion. Enhancing vehicular traffic flow through strategic route adjustments is a pivotal element in improving traffic mobility. However, depending exclusively on traffic-related data for route recommendations fails to meet the essential criteria for ensuring effective management and safety for drivers and passengers during travel. Thus, context awareness and traffic data are crucial for enhancing efficiency and safety in traffic management. Our study proposes a two-context-aware approach to recommend safe routes for urban traffic management, considering road safety and travel time. Experiments were carried out using the widely recognized tool — HERE Navigation. Comparatively, our approach signifies a progressive stride in balancing mobility and security when contrasted with a single focus on travel time.

A local fractional modified Crank–Nicolson scheme for fractal LWR model of traffic flow

This research proposes a modified Crank–Nicolson finite difference scheme with local fractional derivatives to approximate the solutions of local fractional LWR traffic flow model. The stability and consistency of the scheme are examined. Further, convergence of the scheme is assured by using Lax’s equivalence theorem. Some exemplary instances are discussed along with their simulations to validate the proposed method. The obtained numerical solutions show the dynamical evolution of traffic density with respect to time and space. The results derived using the proposed numerical scheme establish that they are quite effective in obtaining the numerical solution to the fractal vehicular traffic flow problem.

Optimizing energy efficiency in intelligent vehicle-oriented road network design: A novel traffic assignment method for sustainable transportation

In light of the development of intelligent vehicles and the persistent energy crisis, improving the predictive accuracy of macroscopic traffic flow and formulating energy-efficient road network design solutions are essential to promote sustainable development in road transportation. This study introduces a dual-objective impedance function that incorporates considerations of both travel time and energy consumption. The function is developed utilizing the principles of intelligent vehicle energy flow and traffic flow parameters. Then, an enhanced user equilibrium traffic assignment (E-UE) model is formulated. The effectiveness of the E-UE function was validated through road experimental data. The performance of E-UE was analyzed using a planned road network consisting of 28 sections. In comparison with the classical UE model, the E-UE model promotes uniform traffic distribution and alleviates congestion, leading to a 1.1 % reduction in average road energy consumption. This highlights the E-UE model’s effectiveness in accurately capturing the impacts on energy consumption with enhanced predictive precision. Strategies to mitigate potential energy consumption include implementing the E-UE model with realistic weights, adjusting weights for specific roads, employing a design speed of 50 km/h, and utilizing 6-lane roads. This study contributes to the advancement of energy-saving technologies in sustainable transportation.

Emission analysis based on mixed traffic flow and license plate recognition model

With the rising ownership of new energy vehicles (NEVs), accurate road traffic emission estimations are crucial. This study combined mixed traffic flow and license plate recognition (LPR) using improved 3D convolutional neural network (3D-CNN) and Transformer models. The 3D-CNN model is designed for vehicle localization and traffic flow data acquisition, while the Transformer-based LPR model accurately recognizes license plates, distinguishing NEVs from conventional vehicles. The overall model is validated by the training and test datasets, and then with field application along a primary arterial segment in the South 2nd Ring Road, Xi’an, China. The results demonstrate capability for the traffic emission approximation of the mixed traffic flow including new energy vehicles, revealing that mixed traffic flow identification plays an important role in road emission approximation. Results and procedures of the study may provide benchmark for the subsequent research and the verification of related transportation policies.

Analisis Kebutuhan Fasilitas Pedestrian di Kawasan Stasiun

The Ampera LRT Station is located in the center of Palembang City and on the banks of the Musi River. This area is a center of community activity, with the presence of hospitals, offices, restaurants, hotels, and shopping centers. The existence of the Palembang LRT is intended to overcome congestion and accommodate the mobility needs of the community in Palembang, especially in the Ampera area. However, there are several issues related to pedestrian facilities in the Ampera LRT Station area, such as the misuse of sidewalk functions, the presence of many side barriers in the form of street vendors and on-street parking, as well as the lack of safe and comfortable crossing facilities for pedestrians, especially for people with disabilities. This study analyzes the pedestrian facility needs in the Ampera LRT Station area of Palembang. The method used in this study is the calculation of the level of service (LOS) based on the Indonesian Highway Capacity Manual (MKJI) 1997 and the empirical formula calculation of pedestrian conflicts based on the pedestrian flow and vehicle traffic flow (PV2) using quantitative data. The research results show that it is necessary to repair and add pedestrian facilities under the concept of walkability, such as providing sidewalks that can be used according to their function, providing crossing facilities such as pelicans with waiting platforms on Merdeka Street, Sudirman Street, and Tengkuruk Permai Street, while on Masjid Lama Street and Palembang Darussalam Street, zebra crossings or pedestrian platforms are needed. The results of this study are expected to be input for the Palembang City Government to improve the quality of pedestrian facilities in the Ampera LRT Station area so that it can support the station's function as a center of community activity and movement in the area.

Stabilization of Stop-and-Go Waves in Vehicle Traffic Flow

Stabilization of Stop-and-Go Waves in Vehicle Traffic Flow

Tipping points, multistability, and stochasticity in a two-dimensional traffic network dynamics

Mitigating traffic jams is a critical step for the betterment of the urban transportation system, which comprises a large number of interconnected routes to form an intricate network. To understand distinct features of vehicular traffic flow on a network, a macroscopic two-dimensional traffic network model is proposed incorporating intra-nodal and inter-nodal vehicular interaction. Utilizing the popular techniques of nonlinear dynamics, we investigate the impact of different parameters like occupancy, entry rates, and exit rates of vehicles. The existence of saddle-node, Hopf, homoclinic, Bogdanov–Takens, and cusp bifurcations have been shown using single or biparametric bifurcation diagrams. The occurrences of different multistability (bistability/tristability) phenomena, stochastic switching, and critical transitions are explored in detail. Further, we calculate the possibility of achieving each alternative state using the basin stability metric to characterize multistability. In addition, critical transitions from free flow to congestion are identified at different magnitudes of stochastic fluctuations. The applicability of critical slowing down based generic indicators, e.g., variance, lag-1 autocorrelation, skewness, kurtosis, and conditional heteroskedasticity are investigated to forewarn the critical transition from free flow to traffic congestion. It is demonstrated through the use of simulated data that not all of the measures exhibit sensitivity to rapid phase transitions in traffic flow. Our study reveals that traffic congestion emerges because of either bifurcation or stochasticity. The result provided in this study may serve as a paradigm to understand the qualitative behavior of traffic jams and to explore the tipping mechanisms occurring in transport phenomena.

A Dynamic Traffic Light Control Algorithm to Mitigate Traffic Congestion in Metropolitan Areas.

This paper proposes a convolutional neural network (CNN) model of the signal distribution control algorithm (SDCA) to maximize the dynamic vehicular traffic signal flow for each junction phase. The aim of the proposed algorithm is to determine the reward value and new state. It deconstructs the routing components of the current multi-directional queuing system (MDQS) architecture to identify optimal policies for every traffic scenario. Initially, the state value is divided into a function value and a parameter value. Combining these two scenarios updates the resulting optimized state value. Ultimately, an analogous criterion is developed for the current dataset. Next, the error or loss value for the present scenario is computed. Furthermore, utilizing the Deep Q-learning methodology with a quad agent enhances previous study discoveries. The recommended method outperforms all other traditional approaches in effectively optimizing traffic signal timing.

Cooperative traffic optimization with multi-agent reinforcement learning and evolutionary strategy: Bridging the gap between micro and macro traffic control

The emergence of connected and autonomous vehicles (CAVs) holds promise for fine-grained traffic control. However, due to the longevity of future mixed traffic scenarios, there is a need for an in-depth exploration of integrating the microscopic speed control of CAVs with the macroscopic variable speed limit (VSL) of human-driven vehicles (HDVs). This paper proposes a Cooperative Traffic Optimization with Multi-agent Reinforcement Learning and Evolutionary VSL (CTO-ME) framework, which combines microscopic CAV control with macroscopic VSL control. The framework incorporates a Graph Attention Mechanism (GATs) into the multi-agent reinforcement learning framework for intelligent decision-making by microscopic-level vehicles. Additionally, an evolutionary strategy is developed to design the VSL network architecture, enabling macroscopic level real-time speed limit adjustments based on infrastructure. A multi-objective reward function is proposed to optimize both micro and macro efficiency and safety, accounting for both vehicle behavior and traffic flow. Experiments on the designed Bottleneck traffic scenarios show that the proposed approach, CTO-ME, is able to achieve superior performance and outperforms other baselines in terms of traffic throughput, average speed, and safety. Specifically, CTO-ME enhances average velocity by 37%, increases overall throughput by 309%, and raises arrival ratio by 70% than traditional Intelligent Driver Model (IDM).

RETRACTED: Data-driven traffic signal adaptive control algorithm integrating vehicle perception and traffic flow data

This article has been retracted. A retraction notice can be found at https://doi.org/10.3233/JIFS-219433.

Prediction of Vehicular Traffic Flow Using Optimized Neural Network

Prediction of Vehicular Traffic Flow Using Optimized Neural Network

Multi-objective arterial coordination control method based on induction control and vehicle speed guidance

The fixed green wave speed and staged statistical flow used in arterial signal coordination are not adaptable to the fluctuations in vehicle travel speed and traffic flow on roads, resulting in a mismatch between the signal scheme and the optimal green wave speed and traffic flow demand. This discrepancy negatively impacts the efficiency of intersection traffic. In traditional signal control systems, the cycle and green light timing are typically set independently. However, such a setting method poses problems in practical operation. In this paper, we combine vehicle arrival and vehicle location information, and consider the interaction of speed guidance and dynamic signal optimization to construct a model. This study is developed along the following steps: in the vehicle-road coordination environment, based on the MAXBAND model, a global coordination scheme is obtained, incorporating the speed guidance method; then, based on the vehicle saturation of the inlet lane of the arterial intersection, a multi-objective optimization model for arterial signal coordination under vehicle speed guidance is established based on global coordination with the maximum green wave bandwidth and the minimum delay of arterial vehicles, the minimum number of arterial stops and the minimum delay in the minor direction road as the optimization objectives. Based on global coordination, adopting an integrated control mechanism of cycle and green light timing allows for dynamic adjustments according to real-time traffic conditions. The improved multi-objective particle swarm algorithm is chosen to solve the model, and the simulation environment is built based on the COM interface of VISSIM software and C# platform. Three adjacent intersections of Ganjiang Middle Road in Nanchang are selected as case studies, and the methods in this paper are compared with the current timing scheme, the MAXBAND method and the optimization scheme under speed guidance only, respectively. The results show that the model proposed in this paper achieves significant optimization effects on the indicators of arterial delay, arterial stopping times and the delay of minor roads.

Quantitative Analysis of Vehicular Traffic Flow Order at Signalized Intersections

Quantitative Analysis of Vehicular Traffic Flow Order at Signalized Intersections

Distributed and explainable GHSOM for anomaly detection in sensor networks

The identification of anomalous activities is a challenging and crucially important task in sensor networks. This task is becoming increasingly complex with the increasing volume of data generated in real-world domains, and greatly benefits from the use of predictive models to identify anomalies in real time. A key use case for this task is the identification of misbehavior that may be caused by involuntary faults or deliberate actions. However, currently adopted anomaly detection methods are often affected by limitations such as the inability to analyze large-scale data, a reduced effectiveness when data presents multiple densities, a strong dependence on user-defined threshold configurations, and a lack of explainability in the extracted predictions. In this paper, we propose a distributed deep learning method that extends growing hierarchical self-organizing maps, originally designed for clustering tasks, to address anomaly detection tasks. The SOM-based modeling capabilities of the method enable the analysis of data with multiple densities, by exploiting multiple SOMs organized as a hierarchy. Our map-reduce implementation under Apache Spark allows the method to process and analyze large-scale sensor network data. An automatic threshold-tuning strategy reduces user efforts and increases the robustness of the method with respect to noisy instances. Moreover, an explainability component resorting to instance-based feature ranking emphasizes the most salient features influencing the decisions of the anomaly detection model, supporting users in their understanding of raised alerts. Experiments are conducted on five real-world sensor network datasets, including wind and photovoltaic energy production, vehicular traffic, and pedestrian flows. Our results show that the proposed method outperforms state-of-the-art anomaly detection competitors. Furthermore, a scalability analysis reveals that the method is able to scale linearly as the data volume presented increases, leveraging multiple worker nodes in a distributed computing setting. Qualitative analyses on the level of anomalous pollen in the air further emphasize the effectiveness of our proposed method, and its potential in determining the level of danger in raised alerts.