Search

The rapid development of urbanization in China has contributed to traffic events, such as traffic accidents and delays. It is difficult to detect and resolve highway traffic congestion in a timely manner using traditional methods because they are slow, require a large number of workers, and require the installation of a large amount of monitoring equipment. Therefore, it is imperative to introduce advanced technology to address these challenges. Recently, deep learning technology has made significant breakthroughs and has been widely applied to various fields with satisfactory results. Deep learning is among the most important technologies for the detection and evaluation of traffic congestion, enabling the accurate detection of the state of the expressway network's traffic congestion, the evaluation of traffic congestion, and the prediction of possible traffic congestion. This enables management to formulate traffic dredging strategies in advance to prevent the negative impact of traffic congestion on normal traffic flow. This paper proposes a framework based on deep learning for next-generation highway traffic management. This framework selects traffic congestion indicators to construct an index model, and then constructs a deep learning model based on self-coding. It predicts and classifies highway traffic environment data and excavates sample data based on the characteristics of traffic parameters. As soon as traffic data were classified, a prediction model based on SoftMax was established to detect and predict highway traffic congestion. We conducted a traffic congestion analysis of the Shanghai expressway network based on the speed performance data obtained from the China Traffic Management Bureau. As a result of their research, we developed an index to measure highway traffic congestion. For traffic control and management organizations to function effectively, it is crucial to have an accurate and clear picture of traffic network operations. We evaluated the proposed framework using data gathered from highway monitoring scenes, and the results indicated that 98.6% of the data could be correctly detected. Using the prediction model based on SoftMax for expressway vehicles during peak hours, the accuracy was 92%, and the misjudgment rate was 8%. This study demonstrates that detecting and evaluating the state of highway traffic environments using deep learning has high accuracy, can be applied to actual highway traffic systems, and is extremely useful for detecting highway congestion. This framework is a promising solution for next-generation highway traffic management and provides accurate and timely traffic congestion detection and evaluation. [ABSTRACT FROM AUTHOR]

A macroscopic traffic flow model considering the effects of curves, ramps, and adverse weather is proposed, and nonlinear bifurcation theory is used to describe and predict nonlinear traffic phenomena on highways from the perspective of global stability of the traffic system. Firstly, the stability conditions of the model shock wave were investigated using the linear stability analysis method. Then, the long-wave mode at the coarse-grained scale is considered, and the model is analyzed using the reduced perturbation method to obtain the Korteweg-de Vries (KdV) equation of the model in the sub-stable region. In addition, the type of equilibrium points and their stability are discussed by using bifurcation analysis, and a theoretical derivation proves the existence of Hopf bifurcation and saddle-knot bifurcation in the model. Finally, the simulation density spatio-temporal and phase plane diagrams verify that the model can describe traffic phenomena such as traffic congestion and stop-and-go traffic in real traffic, providing a theoretical basis for the prevention of traffic congestion. [ABSTRACT FROM AUTHOR]

Urban traffic congestion is one of the major problems of the developing countries. In routine practice, traffic managers use their knowledge and exposure to address this urban mobility menace. This heuristic approach based on individual experience results in inconsistency causing further delays and an increase in travel time. The aim of this research is to incorporate urban mobility dynamics of the developing countries in a microsimulator for real-time decision making. A pilot-scale research was conducted in Peshawar, one of the ten largest cities of Pakistan. Traffic volume, travel time, vehicle specifications and geometry parameters were determined in the field as input for the microsimulation model. Calibration and validation of the model were done, and results of traffic volume and travel time were compared with actual field data and statistical similarity confirmed through paired t-test. The analysis of queue delay, travel time and traffic flow indicates that in most of the cases congestion was found near the intersections and U-turns which was verified from the field data as well. The options of a roundabout and a flyover were assumed in the analysis; resultant queue delay and travel time decreased. With the provision of the roundabout and flyover, the capacity of traffic flow was also improved. [ABSTRACT FROM AUTHOR]

Due to the rapidly growing population of the city of Ankara (Turkey) and increased traffic congestion, it has become necessary to widen the Ankara-Eskişehir (E-90) highway connecting the newly built areas west of the city to the city center. During widening, several cut slopes were formed along the highway route. As a result, some instability problems (small-sized rock falls/sliding, sloughing, raveling) produced detachment zones along a cut slope in highly jointed, folded and sheared limestone, causing local degradation of the cut slope. Identification of the areas that are likely to detach from the cut slope in the future is considered to be very important for the application of remedial measures. For this purpose, the relationships between the existing detachment zones and various parameters (e.g., point load strength index, weathering, block size, daylighting, shear zone) were investigated using GIS-based statistical detachment susceptibility analyses in order to predict the further aerial extension of the detachment zones with time. During the overlay analyses, statistical index and weighting factor methods were used. The outcomes of the analyses were compared and evaluated with the field observations to check the reliability of the methods and to assess the detachment zones that may develop in the future. The detachment susceptibility map without the block-size layer gives the best result and indicates some risky zones where detachments are likely to occur in the future. Recommendations on remedial measures of the cut slope should consider these risky zones. [ABSTRACT FROM AUTHOR]

This paper deals with the continuum modeling of traffic dynamics for freeways with two lanes where the faster vehicles are allowed to travel on both lanes while the slower vehicles are allowed to travel on one lane only. The speed gradient-based momentum equation is used to develop the traffic models for each lane. Using the proposed models, some nonequilibrium phenomena such as small disturbance instability and stop-and-go waves, together with results from numerical tests are investigated. The conditions for keeping the models' linear stability are presented. [ABSTRACT FROM AUTHOR]

Prediction of traffic congestion is one of the core issues in the realization of smart traffic. Accurate prediction depends on understanding of interactions and correlations between different city locations. While many methods merely consider the spatio-temporal correlation between two locations, here we propose a new approach of capturing the correlation network in a city based on realtime traffic data. We use the weighted degree and the impact distance as the two major measures to identify the most influential locations. A road segment with larger weighted degree or larger impact distance suggests that its traffic flow can strongly influence neighboring road sections driven by the congestion propagation. Using these indices, we find that the statistical properties of the identified correlation network is stable in different time periods during a day, including morning rush hours, evening rush hours, and the afternoon normal time respectively. Our work provides a new framework for assessing interactions between different local traffic flows. The captured correlation network between different locations might facilitate future studies on predicting and controlling the traffic flows. [ABSTRACT FROM AUTHOR]