Adaptive spatial-temporal graph attention network for traffic speed prediction

Considering the nonlinear structure and spatial-temporal correlation of traffic network,and the influence of potential correlation between nodes of traffic network on the spatial features,this paper proposes a traffic speed prediction model based on the combination of graph attention network with self-adaptive adjacency matrix(SAdpGAT)and bidirectional gated recurrent unit(BiGRU).First-ly,the model introduces graph attention network(GAT)to extract the spatial features of real road network and potential road network respectively in spatial dimension.Secondly,the spatial features are input into BiGRU to extract the time series features.Finally,the prediction results of the real road network and the potential road network are connected to generate the final prediction results of the model.The experimental results show that the prediction accuracy of the proposed model is im-proved obviously on METR-LA and PEMS-BAY datasets,which proves the advantages of the pro-posed spatial-temporal model in traffic speed prediction.

A BP neural network based information fusion method for urban traffic speed estimation

Obtaining comprehensive and accurate information is very important in intelligent tragic system （ITS）. In ITS, the GPS floating car system is an important approach for traffic data acquisition. However, in this system, the GPS blind areas caused by tall buildings or tunnels could affect the acquisition of tragic information and depress the system performance. Aiming at this problem, a novel method employing a back propagation （BP） neural network is developed to estimate the traffic speed in the GPS blind areas. When the speed of one road section is lost, the speed of its related road sections can be used to estimate its speed. The complete historical data of these road sections are used to train the neural network, using Levenberg-Marquardt learning algorithm. Then, the current speed of the related roads is used by the trained neural network to get the speed of the road section without GPS signal. We compare the speed of the road section estimated by our method with the real speed of this road section, and the experimental results show that the proposed method of traffic speed estimation is very effective.

Effect of Traffic Speed on Stresses and Strains in Asphalt Perpetual Pavement

Increasing traffic volumes and loads as well as public expectation for a long-lasting transportation infrastructure have necessitated designing perpetual pavements. The KDOT （Kansas Department of Transportation） conducted a field trial to investigate the suitability of perpetual pavement concept for Kansas highway pavements. The experiment involved construction of four thick pavement structures. To verify the approach of designing perpetual pavements on the basis of an endurance strain limit, the pavements were instrumented with gauges for measuring tensile strains at the bottom of asphalt base layers at various speeds. Pavements were also instrumented with pressure cells to measure stress on the top of subgrade. Pavement response measurements under known vehicle load were performed in August 2006. FWD （Falling-weight deflectometer） was also used to collect deflection data at 15 m intervals on the same date. FWD first-sensor （center） deflections were normalized and corrected to 20 ℃ temperature based on measured mid-depth pavement temperature. The result shows that strain and stress measurements show significant amount of variations. Measurements in the thickest section are the most consistent. The higher the traffic speed, the lower the strains and stresses. The difference between strains and stresses at 30 kmhar and 65 km/hr is higher than the difference between 65 km/hr and 95 kin/hr. This shows the effect of speed on stresses and strains decreases as the speed increases. Softer binder in the asphalt base layer results in lower strains, which confirms that softer binder results in higher fatigue life.

Traffic Speed Interface Development in Route Choice Decision

In this paper,a method has been developed based on historic traffic data(speed),which helps the commuters to choose routes by their intelligence knowing the traffic conditions in Google maps.Data has been collected on basis of video analysis from several segments between Tuker Bazar and Bandar Bazar route.For each of the video footage,a reference length has been recorded with measurement tape for use in video analysis.A software has been also developed based on Java language to get the traffic information from historic data,which shows the output as images consisting of traffic speed details on the available routes by giving day and time limit as inputs.The developed models provide useful insights and helpful for the policy makers that can lead to the reduction of traffic congestion and increase the scope of intelligence of the road users,at least for the underdeveloped or developing country where navigation is still unavailable.

Extended speed gradient model for traffic flow on two-lane freeways

In this paper, the speed gradient （SG） model is extended to describe the traffic flow on two-lane freeways. Terms related to lane change are added into the continuity equations and velocity dynamic equations. The empirically observed two-lane phenomena, such as lane usage inversion and lane change rate versus density, are reproduced by extended SG model. The local cluster effect is also investigated by numerical simulations.

Speed–density functional relationship for heterogeneous traffic data: a statistical and theoretical investigation

This study is an attempt to establish a suitable speed–density functional relationship for heterogeneous traffic on urban arterials. The model must reproduce the traffic behaviour on traffic stream and satisfy all static and dynamic properties of speed–flow–density relationships. As a first attempt for Indian traffic condition, two behavioural parameters, namely the kinematic wave speed at jam(Cj) and a proposed saturation flow(k), are estimated using empirical observations. The parameter Cjis estimated by developing a relationship between driver reaction time and vehicle position in the queue at the signalised intersection. Functional parameters are estimated using Levenberg–Marquardt algorithm implemented in the R statistical software.Numerical measures such as root mean squared error, average relative error and cumulative residual plots are used for assessing models fitness. We set out several static and dynamic properties of the flow–speed–density relationships to evaluate the models, and these properties equally hold good for both homogenous and heterogeneous traffic states.From the numerical analysis, it is found that very few models replicate empirical speed–density data traffic behaviour.However, none of the existing functional forms satisfy all the properties. To overcome the shortcomings, we proposed two new speed–density functional forms. The uniqueness of these models is that they satisfy both numerical accuracy and the properties of fundamental diagram. These new forms would certainly improve the modelling accuracy, especially in dynamic traffic studies when coupling with dynamic speed equations.

Mathematical Modeling,Field Calibration and Numerical Simulation of Low-Speed Mixed Traffic Flow in Cities

Ｗｉｔｈｔｈｅｒａｐｉｄｄｅｖｅｌｏｐｍｅｎｔｏｆｔｒａｎｓｐｏｒｔａｔｉｏｎａｎｄａｕｔｏｍｏｂｉｌｅｉｎｄｕｓｔｒｙ，ｔｈｅｃｏｎｆｌｉｃｔｂｅｔｗｅｅｎｍｏｔｏｒｍａｎｕｆａｃｔｕｒｅａｎｄｈｉｇｈｗａｙｃｏｎｓｔｒｕｃｔｉｏｎｂｅｃｏｍｅｓｓ...

A cellular automata traffic flow modeling of desired speed variability

The satisfaction rate of desired velocity in the case of a mixture of fast and slow vehicles is studied by using a cellular automaton method. It is found that at low density the satisfaction rate depends on the maximal velocity. However, the behavior of the satisfaction rate as a function of the coefficient of variance is independent of the maximal velocity. This is in good agreement with empirical results obtained by Lipshtat [Phys. Rev. E 79 066110 （2009）]. Furthermore, our numerical result demonstrates that at low density the satisfaction rate takes higher values, whereas the coefficient of variance is close to zero. The coefficient of variance increases with increasing density, while the satisfaction rate decreases to zero. Moreover, we have also shown that, at low density the coefficient variance depends strongly on the probability of overtaking.

Evaluating Traffic Congestion Using the Traffic Occupancy and Speed Distribution Relationship: An Application of Bayesian Dirichlet Process Mixtures of Generalized Linear Model

Accurate classification and prediction of future traffic conditions are essential for developing effective strategies for congestion mitigation on the highway systems. Speed distribution is one of the traffic stream parameters, which has been used to quantify the traffic conditions. Previous studies have shown that multi-modal probability distribution of speeds gives excellent results when simultaneously evaluating congested and free-flow traffic conditions. However, most of these previous analytical studies do not incorporate the influencing factors in characterizing these conditions. This study evaluates the impact of traffic occupancy on the multi-state speed distribution using the Bayesian Dirichlet Process Mixtures of Generalized Linear Models (DPM-GLM). Further, the study estimates the speed cut-point values of traffic states, which separate them into homogeneous groups using Bayesian change-point detection (BCD) technique. The study used 2015 archived one-year traffic data collected on Florida’s Interstate 295 freeway corridor. Information criteria results revealed three traffic states, which were identified as free-flow, transitional flow condition (congestion onset/offset), and the congested condition. The findings of the DPM-GLM indicated that in all estimated states, the traffic speed decreases when traffic occupancy increases. Comparison of the influence of traffic occupancy between traffic states showed that traffic occupancy has more impact on the free-flow and the congested state than on the transitional flow condition. With respect to estimating the threshold speed value, the results of the BCD model revealed promising findings in characterizing levels of traffic congestion.

Steady state speed distribution analysis for a combined cellular automaton traffic model

Cellular Automaton （CA） based traffic flow models have been extensively studied due to their effectiveness and simplicity in recent years. This paper develops a discrete time Markov chain （DTMC） analytical framework for a Nagel-Schreckenberg and Fukui Ishibashi combined CA model （W^2H traffic flow model） from microscopic point of view to capture the macroscopic steady state speed distributions. The inter-vehicle spacing Maxkov chain and the steady state speed Markov chain are proved to be irreducible and ergodic. The theoretical speed probability distributions depending on the traffic density and stochastic delay probability are in good accordance with numerical simulations. The derived fundamental diagram of the average speed from theoretical speed distributions is equivalent to the results in the previous work.

Speed Spatial Distribution Models for Traffic Accident Section of Freeway Based on Computer Simulation

Simulation models for accident section on freeway are built in microscopic traffic flow simulation environment. In these models involving 2-lane,3-lane and 4-lane freeway,one detector is set every 10 m to measure section running speed. According to the simulation results,speed spatial distribution curves for traffic accident section on freeway are drawn which help to determine dangerous sections on upstream of accident section. Furthermore,the speed spatial distribution models are obtained for every speed distribution curve. The results provide theoretical basis for determination on temporal and spatial influence ranges of traffic accident and offer reference to formulation of speed limit scheme and other management measures.

Real-Time Traffic State and Boundary Flux Estimation with Distributed Speed Detecting Networks

The rapid development of 5G mobile communication and portable traffic detection technologies enhances highway transportation systems in detail and at a vehicle level. Besides the advantage of no disturbance to the regular traffic operation, these ubiquitous sensing technologies have the potential for unprecedented data collection at any temporal and spatial position. While as a typical distributed parameter system, the freeway traffic dynamics are determined by the current system states and the boundary traffic demand-supply. Using the three-step extended Kalman filtering, this paper simultaneously estimates the real-time traffic state and the boundary flux of freeway traffic with the distributed speed detector networks organized at any location of interest. In order to assess the effectiveness of the proposed approach, a freeway segment from Interstate 80 East (I-80E) in Alameda, Emeryville, and Northern California is selected. Experimental results show that the proposed method has the potential of using only speed detecting data to monitor the state of urban freeway transportation systems without access to the traditional measurement data, such as the boundary flows.

On-line Popularity Monitoring Method Based on Bloom Filters and Hash tables for Differentiated Traffic

Towards line speed and accurateness on-line content popularity monitoring on Content Centric Networking(CCN) routers, we propose a three-stage scheme based on Bloom filters and hash tables for differentiated traffic. At the first stage, we decide whether to deliver the content to the next stage depending on traffic types. The second stage consisting of Standard Bloom filters(SBF) and Counting Bloom filters(CBF) identifies the popular content. Meanwhile, a scalable sliding time window based monitoring scheme for different traffic types is proposed to implement frequent and real-time updates by the change of popularities. Hash tables according with sliding window are used to record the popularity at the third stage. Simulation results reveal that this method reaches a 40 Gbps processing speed at lower error probability with less memory, and it is more sensitive to the change of popularity. Additionally, the architecture which can be implemented in CCN router is flexible and scalable.

A simulation study of using active traffic management strategies on congested freeways

The main objective of this study is to evaluate the effectiveness of using active traffic management （ATM） strategies on freeways in terms of the driver＇s behavior and operational impacts. A few test beds were selected to evaluate the impacts of ATM such as speed harmonization, shoulder utilization, and ramp metering. Test beds used in this study were at places where an ATM is either proposed or previously implemented, i.e., where data exists for condi- tions prior to and after the implementation of ATM. Data collected from the test beds were used in a simulation model to evaluate the impacts of each ATM strategy on speed, travel time, and crash rates. Simulation results indicated that the implementation of speed harmonization on US 90 showed a 14% reduction in crashes and a 2%-3% increase in freeway speed; the implementation of hard shoulders on US 90 showed a 39% increase in travel time, 22% increase in freeway capacity and 60% decrease in delays; and the implementation of ramp metering on US 59 between Bissonnet St. and Fondern road showed a decrease of 23 % in freeway travel time, a 14% increase in freeway speed and 11% decrease in accident rates.

Evaluation of Transverse Markings as a Speed Transition Zone Countermeasures in Small, Rural Communities

Small rural communities located along major state or county roadways typically find most of the traffic along their main thoroughfares is pass-through rather than local traffic. Unfortunately, drivers passing through these communities often enter at high rates of speeds, which are often significantly higher than the speed limit of the local segment. Speed management in rural areas requires different considerations compared to urban areas and, within the US, rural speed management is not as advanced with little experience or guidance for agencies to draw on. This paper summarizes the results of a study that evaluated, in part, several different types of transverse pavement markings within the speed transition zones in small rural communities. Three different countermeasures were evaluated: converging chevrons, transverse lane markings, and optical speed bars.

Spatial Impact of High-speed Railway on the Urban Scale:An Empirical Analysis from Northeast China

The emergence of rapid transit,primarily represented by high-speed railway(HSR),while reshaping the regional traffic patterns,leads to the reconstruction and redistribution of population and industry.This leads to either shrinkage or expansion of urban scale.However,research on the influence mechanisms of the urban scale has mostly concentrated on historical,economic and social factors.The influence of traffic factors is rarely mentioned in current research.Therefore,this study examines Northeast China,where the change in urban scale is most significant,to discuss the spatial impact of high-speed railway on the urban scale.This is of great significance in terms of enriching current understanding of the factors affecting the urban scale.The results included the following:1)The high-speed railway produced considerable space-time convergence effects,however,simultaneously aggravated the imbalance in traffic development in Northeast China.The increase in accessibility presents attenuation characteristics from the high-speed railway.Additionally,the high-speed railway has changed the mode of cooperation between cities in the provinces,inter-regional and inter-provincial cooperation models gradually become popular.2)The change rate of accessibility and the urban scale present significant spatial coupling phenomena,with the change rate of the Harbin-Dalian trunk lines and its surroundings being more significant.3)There are predominantly four modes of the influence of high-speed railway on the urban scale,which make difference city present expansion or shrinkage.

Threshold values of traffic flow for the provision of exclusive bus lanes

A simulation network model was established using VISSIM software and verified by the T- test. The model took into consideration the road conditions, pedestrian crossing, traffic composi- tion, bus stops and traffic signal. The operating characteristics of buses and cars under different flow conditions were studied using the simulation model, and the speed-flow models of buses and cars were established based on the simulation results. Finally, the threshold values of traffic flow for the provision of exclusive bus lanes was determined with the target of optimal travel benefits （per capi- ta） , which would provide a basis for the planning and design of exclusive bus lanes on urban roads.

Development of Risk Index of Uninterrupted Traffic Flow According to the Occurrence of Fog

The driver’s visibility is degraded when weather conditions deteriorate, which affects the traffic flow and induces traffic congestion or accidents. In particular, traffic accidents can be?led to chain reaction collisions, with high rate of fatality, when fog occurs in contrast to other weather factors that may restrict visibility. For the development of a traffic risk index, a deviation of the vehicle’s speed was set for the traffic risk index by referring to previous study results. In addition, factors that affected the deviation in a vehicle’s speed were selected as independent variables based on the traffic flow analysis during occurrences of fog. The visible distance, traffic volume, and speed were selected as the independent variables to estimate the optimal parameters in the regression model. The traffic risk index model during occurrences of fog proposed in this study is an exponential model, with the visible distance and the traffic volume defined as independent variables. According to the study model, traffic risk increased as the visible distance decreased and the traffic volume was lower. Thus, the visible distance that can affect traffic flow during occurrences of fog can be determined in the future based on the results of this study. The study results will be expected to contribute to not only traffic safety improvements, but also the facilitation of traffic flow as drivers and traffic operation managers intuitively recognize the level of risk.

The KdV-Burgers equation in a modified speed gradient continuum model

Based on the full velocity difference model, Jiang et al. put forward the speed gradient model through the micromacro linkage （Jiang R, Wu Q S and Zhu Z J 2001 Chin. Sci. Bull 46 345 and Jiang R, Wu Q S and Zhu Z J 2002 Trans. Res. B 36 405）. In this paper, the Taylor expansion is adopted to modify the model. The backward travel problem is overcome by our model, which exists in many higher-order continuum models. The neutral stability condition of the model is obtained through the linear stability analysis. Nonlinear analysis shows clearly that the density fluctuation in traffic flow leads to a variety of density waves. Moreover, the Korteweg-de Vries-Burgers （KdV-Burgers） equation is derived to describe the traffic flow near the neutral stability line and the corresponding solution for traffic density wave is derived. The numerical simulation is carried out to investigate the local cluster effects. The results are consistent with the realistic traffic flow and also further verify the results of nonlinear analysis.