Road Traffic Flow Research Articles

Evaluation of the efficiency of roundabouts in modern cities

The article presents the results of studies that allow to reduce time delays by determining the optimal parameters of roundabouts based on the established dependencies of road characteristics on the geometric parameters of road intersections and traffic flows. In analytical studies, we identify the most effective types of configurations of the road intersection at the same level and establish the dependence of the average vehicle speed on the total traffic intensity for these configurations. Moreover, the paper establishes the dependence of the average speed on the intensity of traffic flow at different radii of the central guide island of the roundabout and the dependence of the average speed on the radius of the central guide island with different bandwidth of the carriageway on the approach to the roundabout.

Mathematical modeling of air pollution in city tunnels and evaluating mitigation strategies

A mаthemаtical model has been developed that is able to describe the environment of the city tunnels being affected by the road traffic, natural and forced air convective flows. The mathematical model describes the peculiarities of the traffic flows on one-lane roads with a satisfactory accuracy. The model well matches experimental data on traffic flows. Multidimensional calculations of the influence of cars on the airflow in tunnels are performed. The numerical model for simulating exhaust gas emissions by automobiles and their accumulation in a tunnel and evolution with traffic induced air flow was developed. The results of numerical investigations make it possible providing recommendations for transport researchers and policy-makers. In particular, it was shown that in the presence of long tunnels on automobile roads it is necessary to choose the traffic arrangement avoiding the necessity for vehicles to come to a full stop and then accelerate in tunnels. This could happen in the presence of traffic lights or other type of traffic regulation near the exit of the tunnel. Thus it is necessary in arranging traffic regulation avoiding placing traffic lights in the proximity of tunnel exit for the waiting cars line to be shorter than the distance from the tunnel exit. In venting the tunnel, the direction of the wind should coincide with the direction of traffic flow. Attempts to arrange venting in the opposite direction for high blockage ratio of a tunnel by vehicles could result in bringing to a worse situation with air pollution.

Dynamic model of high speed following traffic flow

For the physical phenomenon of high-speed car following in the road traffic flow, all the vehicles with small spacing do not run at low speed. The speeds of the vehicles are significantly higher than those they normally should be when they are in this vehicles’s density. There are more than 7% of high-speed following vehicles in the measured data. At present, the traditional traffic flow model cannot simulate the phenomenon of high-speed car following, so a new nonlinear dynamic mathematical model is needed to describe and analyze the physical phenomenon. In order to study the physical phenomenon of high-speed car following in road traffic, a traffic flow dynamics model for simulating the phenomena is proposed, which combines with the prospect theory and takes into account some factors such as driver’s decision-making behavior and randomization. It is called HCCA (high-speed car following celluar automat) model. In the model, the prospect theory is used to analyze the driver’s lane changing behavior under the uncertain conditions. Combined with the characteristics of the radical driver, the dynamic prediction speed is considered for the front car followed by the radical driver, and the HCCA dynamics rules of high-speed following traffic flow mechanics are defined. By the computer numerical simulation, the evolution mechanism and the characteristics of high-speed car-following flow are studied. The results show that compared with the symmetric two-lane cellular automata (STCA) dynamic model, the HCCA dynamic model established in this paper can simulate abundant traffic physical phenomena, and reproduce complex traffic phenomena such as free flow, synchronous flow and wide-range motion congestion. Finally, the phenomenon of high-speed car following is simulated and the results of high-speed car following rate over 7% with small spacing are in good agreement with the measured results. It overcomes the shortage that traditional STCA model cannot simulate the synchronous flow. It is found that the larger the proportion of radical drivers, the larger the high-speed car following rate and traffic flow with small spacing are under the same road density. The high-speed car following traffic flow mechanics model proposed in this paper has a certain reference significance and practical value for analyzing the physical phenomenon of high-speed car following and enriching the traffic flow theory.

Truck Traffic Flow Prediction Based on LSTM and GRU Methods With Sampled GPS Data

Given the enormous traffic issues, such as congestion and crashes, resulting from the conflicts between trucks and passenger cars, an accurate and reliable prediction of truck traffic flow is needed to enhance the traffic flow efficiency and safety in the mixed traffic condition. Enabled by emerging sensing technologies, the GPS data become available and will reveal some insights to improve the understanding of truck traffic flow prediction. In the paper, a novel method of truck traffic flow prediction is proposed by using sampled GPS data in the roadway network. The proposed method consists of two phases, which are expansion and prediction. In the data expansion phase, a piece-wise constant coefficient method is designed to minimize errors between the sampled truck flow and the actual truck flow, where the coefficients are determined according to road grades and traffic flow size. In the prediction phase, Long Short Term Memory (LSTM) and Gated Recursive Unit (GRU) neural network methods are first time employed to improve the prediction accuracy. Considering that the sequence of the expansion and prediction could have different prediction performance, approaches using both `previous-prediction', `post-expansion' and `previous-expansion', `post-prediction' were used and the results compared with the survey data from traffic flows. The results demonstrate that LSTM and GRU have a superior performance compared to existing approaches using SRV and ARIMA for truck traffic flow prediction. For the whole prediction period, LSTM has better prediction results than GRU overall with an accuracy which is 4.10% better than that of GRU. Furthermore, the accuracy of the `previous-prediction', `post-expansion' is 8.26% greater than that of the `previous-expansion', `post-prediction'.

Road traffic optimisation based on a learning approach

Road traffic management is an important issue for authorities, road operators and users. Many researchers have worked since many years in order to propose smart solutions. Some of them have been adopted by road operators and applied on road signalling or on traffic light management. During the last decade, cooperative intelligent transport systems (C-ITS) have emerged and are being deployed. They permit on one hand to increase the number of connected vehicles and on another hand to deploy road side units (RSU) along roads and junctions. RSUs together with central road operator servers compose the road infrastructure used for infrastructure to vehicle communications (I2V). RSUs disseminate continuously messages about road safety and traffic flows to vehicles. Vehicles and RSUs are able to measure, to compute, and to disseminate relevant information. In this study, we add to these actors the ability to learn road behaviours in order to be able to provide the optimal path in terms of travel time for vehicles seeking to reach their destination. The solution is based on a reinforcement learning technique, in particular the Q-learning, that is used to learn the best action to take into account according to various situations. The transit delay from one location to another is used to evaluate the rewards. The simulation results confirm that the proposed Q-learning approach outperforms the existing greedy algorithm with better performances in terms of a transit delay.

Road traffic optimisation based on a learning approach

Road traffic management is an important issue for authorities, road operators and users. Many researchers have worked since many years in order to propose smart solutions. Some of them have been adopted by road operators and applied on road signalling or on traffic light management. During the last decade, cooperative intelligent transport systems (C-ITS) have emerged and are being deployed. They permit on one hand to increase the number of connected vehicles and on another hand to deploy road side units (RSU) along roads and junctions. RSUs together with central road operator servers compose the road infrastructure used for infrastructure to vehicle communications (I2V). RSUs disseminate continuously messages about road safety and traffic flows to vehicles. Vehicles and RSUs are able to measure, to compute, and to disseminate relevant information. In this study, we add to these actors the ability to learn road behaviours in order to be able to provide the optimal path in terms of travel time for vehicles seeking to reach their destination. The solution is based on a reinforcement learning technique, in particular the Q-learning, that is used to learn the best action to take into account according to various situations. The transit delay from one location to another is used to evaluate the rewards. The simulation results confirm that the proposed Q-learning approach outperforms the existing greedy algorithm with better performances in terms of a transit delay.

IEEE Access Special Section Editorial: Big Data Technology and Applications in Intelligent Transportation

During the last few years, information technology and transportation industries, along with automotive manufacturers and academia, are focusing on leveraging intelligent transportation systems (ITS) to improve services related to driver experience, connected cars, Internet data plans for vehicles, traffic infrastructure, urban transportation systems, traffic collaborative management, road traffic accidents analysis, road traffic flow prediction, public transportation service plan, personal travel route plans, and the development of an effective ecosystem for vehicles, drivers, traffic controllers, city planners, and transportation applications. Moreover, the emerging technologies of the Internet of Things (IoT) and cloud computing have provided unprecedented opportunities for the development and realization of innovative intelligent transportation systems where sensors and mobile devices can gather information and cloud computing, allowing knowledge discovery, information sharing, and supported decision making. However, the development of such data-driven ITS requires the integration, processing, and analysis of plentiful information obtained from millions of vehicles, traffic infrastructures, smartphones, and other collaborative systems like weather stations and road safety and early warning systems. The huge amount of data generated by ITS devices is only of value if utilized in data analytics for decision-making such as accident prevention and detection, controlling road risks, reducing traffic carbon emissions, and other applications which bring big data analytics into the picture.

Application of Artificial Intelligence in Traffic Control System of Non-autonomous Vehicles at Signalized Road Intersection.

Abstract The increase in both rural and urban road traffic flow in recent years has led to several disasters in the transportation sector which include traffic congestion, accidents, and high rate of pollution. Alternative traffic control measures are needed whenever there is failure of conventional traffic control or real time traffic issues at road intersection. This current study seeks to investigate the stability and efficiency of Artificial Intelligence (AI) techniques, the artificial neural network (ANN) for eliminating or reducing traffic volume in the case of non-autonomous vehicles in a mixed South African traffic flow conditions. Electronic traffic data of one hundred and twenty six (126) vehicles were observed from Mikros Traffic Monitoring (MTM) firm, a subsidiary of Syntell Group of Company, South Africa. The traffic data was obtained via the traffic technologies employed at MTM which are basically sensor embedded on road surfaces to monitor and control vehicles which passes the traffic counter daily. The dataset obtained from MTM was trained, tested and validated using artificial neural network model under signalized road intersection in heterogeneous condition by using the class description of the vehicles, and corresponding speed as input variables. After series of training, the results suggest that ANN model produced the best possible results for traffic congestion in a heterogeneous traffic condition.

The impacts of road network density on motor vehicle travel: An empirical study of Chinese cities based on network theory

Abstract This paper examines the impacts of road network density on motor vehicle travel through traffic flow and network analysis of cities in China from three perspectives: multi-city comparison with traffic flow data, multi-city and multi-period comparisons with structural characteristics. When we examine the correlation between road network density and traffic flow characteristics including the travel time and speed of 35 major cities in China, no correlation exists between them which may result from different network structures, dynamic traffic demands, traffic control plans, driving behaviors, and so on. It inspires us to explore the correlation between road network density and static travel indicators. Then structural characteristic of road networks can be treated as a fixed relatively attribute and becomes the next research emphasis of this work. Comparative analysis results of three current cities (Xiamen, Washington D.C., San Jose) indicate that the average travel distance in different cities with the similar land area will not increase significantly as road network density increases. Results of an analysis of road network evolution of Changchun, China show that the increase of road network density shortens the average road segment length as well as travel distance in general. This impact on average travel distance is also related to evolution periods or modes of urban road networks. These findings provide important empirical support for planners and policymakers to understand the impacts of road network density on transport performance and design more effective urban road networks.

Research on visual analysis technology and application of urban road data

Many cities use the current wealth of multi-source data to create intelligent transportation systems, which visually process road data so that traffic consumers and traffic managers can better understand urban traffic conditions. Due to the heterogeneity, complexity and mass of these data, it is not easy to conduct effective analysis on them, and it is often necessary to integrate human perception in the analysis process, so as to cause extensive application of visualization. In this paper, we first briefly introduce the pre-processing of urban trajectory data, then systematically analyze the visualization of two data types of road traffic flow and traffic events, and finally briefly summarize the research trend of traffic visualization in recent years and put forward corresponding challenges. The results show that the early research focused on the visualization of road flow, including the main arrow diagram, Mosaic diagram, track wall, etc. With the deepening of visual analysis, the analysis of traffic flow increases to the analysis of traffic events. In recent years, there has been a new trend of mining and utilizing the attributes or semantics of traffic trajectories or traffic events. The research on traffic data visualization has been greatly expanded in breadth and depth.

Short Term Road Traffic Flow Forecasting using Artificial Neural Network

In recent days, road traffic management and congestion control has become major problems in any busy junction in Hyderabad city. Hence short term traffic flow forecasting has gained greater importance in Intelligent Transport System(ITS). Artificial Neural Network(ANN) models have been fruitfully applied for classification and prediction of time series. In this paper, an attempt has been made to model and forecast short-term traffic flow at 6.no. junction in Amberpet, Hyderabad, Telangana state, India applying Neural Network models. The traffic data has been considered for peak hours in the morning for 8A.M to 12 Noon, for 5 days. Multilayer Perceptron (MLP) network model is used in this study. These results can be considered to monitor traffic signals and explore methods to avoid congestion at that junction.

An Integrated Turning Movements Estimation to Petri Net Based Road Traffic Modeling

The tremendous increase in the urban population highlights the need for more efficient transport systems and techniques to alleviate the increasing number of the resulting traffic-associated problems. Modeling and predicting road traffic flow are a critical part of intelligent transport systems (ITSs). Therefore, their accuracy and efficiency have a direct impact on the overall functioning. In this scope, a new approach for predicting the road traffic flow is proposed that combines the Petri nets model with a dynamic estimation of intersection turning movement counts to ensure a more accurate assessment of its performance. Thus, this manuscript extends our work by introducing a new feature, namely turning movement counts, to attain a better prediction of road traffic flow. A simulation study is conducted to get a better understanding of how predictive models perform in the context of estimating turning movements.

Marginal costs for railway level crossing accidents in Sweden

The purpose of the present study is to estimate accident risks and marginal costs for railway level crossings in Sweden. The marginal effect of train traffic on the accident risk is used to derive the marginal cost per train passage that is due to level crossing accidents. The estimations are based on Swedish data from 2000 to 2012 on level crossing accidents, train volume, and crossing characteristics. In this study we estimate the accidents risk for both motorized road traffic and vulnerable road users. As a proxy for road traffic flow we use three categories of road type, and to capture the influences of pedestrians and bicyclists we use information about the number of persons living nearby the level crossing. The results show that both protection device, road type, traffic volume of the trains, and number of persons living nearby the level crossing have significant influence on the accident probability. The marginal cost per train passage regarding motor vehicle accidents is estimated at EUR 0.15 on average in 2012 (price level of 2017). The corresponding number for accidents with vulnerable road users excluding suicides is EUR 0.08 or including suicides EUR 0.50. The cost per train passage varies substantially depending on type of protection device, road type, the traffic volume of the trains, and number of persons living nearby the crossing.

Research on short-term traffic flow prediction method based on real-time traffic status

In order to improve the accuracy of short-term traffic flow prediction, this paper focuses on the influence of road traffic status division on the accuracy of short-term traffic flow prediction. When dividing the road traffic status, the improved road load coefficient is adopted, and the kalman filter method and ARMA algorithm are selected to predict the short-term road traffic flow.

Research on Road Traffic Flow Status Based on Multi-source Monitoring Data

This paper mainly solves the traffic flow problem based on multi-source monitoring data. By using the methods of time-space fusion, traffic flow dynamics, in-depth learning and queuing theory model, the multi-monitoring data of Shenzhen's main roads are analyzed. The traffic flow description model and congestion prediction model are constructed, and the optimal plan for traffic police departments to cope with the traffic situation is explored, which provides a new way to solve the urban traffic pressure.

Analytical study of multifractal invariant attributes of traffic flows

The motor transport complex is formed by a multitude of motor traffic flows and a network of automobile roads. Transition to a new level of the motor functioning transport complex requires the development of new methods of formalizing the collective interaction of all road users. This is connected to an increase in the number of autonomous vehicles in joint traffic. We established that the transport-technological self-organization of motor transport flows is a multifractal structure. Such a structure is reliably enough described by regular hierarchical ‒ sets of Cantor regarding the parameter of the dynamic dimension of an individual vehicle. We proved that the main multifractal attributes of road traffic flows are their fragmentation parameter and fractal dimensionality. These attributes are functionally determined by the speed, traffic density and interval of vehicles movement. Accordingly, there are three modes of vehicles movement. The absence of mutual obstacles between vehicles, low speed and low traffic intensity characterizes free movement. Such a movement determines the boundary of the collective and synchronized flows. Collective movement is characterized by a high density of traffic flow, and speed is limited by the possibilities of the road. If the indicators of the technical and operational condition of the road become decisive, we get a saturated synchronized flow. Analytical studies established a log-exponential functional relationship between the fragmentation parameter of the motor flow and the fractal dimension. We found that the combination of several road traffic flows in the case of multi-lane traffic management determines the dynamics of changes in the basic multifractal characteristics of vehicles variety. At the same time, an increase in the number of road lanes leads to an increase in the fragmentation parameter and a decrease in the fractal dimension of motor traffic flows aggregate. We considered the possibility of creating appropriate navigation algorithms for the variable optimization of the fractal attributes of road traffic. In this case, safe transport and technological modes of the motor transport complex are provided. The same applies to the conditions for increasing the part of autonomous robotic unmanned vehicles in the composition of motor vehicles.

Urban Settlements and Road Network Analysis on the Surrounding Area of the Almirante Alvaro Alberto Nuclear Complex, Angra dos Reis, Brazil

Nuclear power plants accidents should be seen as very complex issues, once they encompass environmental and social aspects that must be integrated to sustain appropriate management measures in a potential disaster event. Therefore, emergency plans require sounds spatial information knowledge and the interactions of their environments. The herein study aims to contribute to the emergency plans, especially to the possible evacuation routes identification for a Nuclear Power Plant located in Angra dos Reis, Brazil. The study was conducted within 120 km radius around the power plant. Results indicate that evacuation plans should be elaborated for the urban cores with low roads availability, or even for high population density areas, that in spite of being well served by alternative routes, exhibit increased road traffic and population flow. These results present important information to provide support to local emergency management actions and guidelines, playing a key role to assist on the evacuation planning.

An Elastic Combination Forecasting Method for Urban Road Traffic Status

In intelligent transportation system, urban road traffic flow status prediction plays an important role. Study shows that the traffic flow status has fractal phenomenon in a certain time scale, so using fractal method to excavate the inherent regularity of traffic flow time series can avoid some difficulties of analyzing the traffic flow influencing factors. This paper proposes a new forecasting algorithm of urban road traffic status based on fractal theory, and in the algorithm, the calculation of fractal dimension is based on the structural function method, and the design of the algorithm takes into account the traffic conditions at different time intervals based on the prediction time. The experimental results indicate that the proposed algorithm is capable of dealing with complex nonlinear urban traffic flow forecasting with satisfying accuracy and effectiveness.

Estimating the Parameters of Traffic Flows on the Basis of Processing of Localization Data on the Movement of Vehicles

The article describes the method of estimating the parameters of transport flows using the two-fluid mathematical model of Herman-Prigogine and developed and based on the proposed method of estimating the parameters of the system on the basis of passive processing of navigation data on the movement of vehicles. The efficiency of the proposed algorithms, mathematical models for estimating the parameters of road traffic flow and system as a whole was confirmed during its testing using a set of tracks on the main highways of Commonwealth of Independent States.

Deep spatiotemporal residual early-late fusion network for city region vehicle emission pollution prediction

Regulation on the urban vehicle emission has great impact on our daily lives and can protect public health. However, there are sparse emission remote sensing stations in city, and vehicle emission data is both spatial and temporal non-stationary, which is influenced by various internal and external factors, such as spatial dependencies (nearby and distant), temporal dependencies (closeness, period, trend), environments (road network, meteorology, events, traffic flow and POIs). In this paper, we introduce a semi-supervised learning approach with co-training geographical weighted regression model, which aims to construct the historical emission observations with the insufficient stations records. And then we formulate the region emission prediction as a spatiotemporal sequence forecasting problem and propose a deep spatiotemporal residual early-late fusion network based on unique properties of spatiotemporal data, to predict vehicle emissions in each region of the given city. And the residual convolution network is employed to model the temporal properties of region vehicle emissions. Finally, we present experiments with the remote sensing records of Hefei, where the proposed model outperforms the other baselines. This result demonstrates that combining deep spatiotemporal residual early-late fusion network with the semi-supervised geographical weighted regression can predict vehicle emission in each region of city effectively.