Search

Detecting road accident impacts as promptly as possible is essential for intelligent traffic management systems. This paper presents a sequential two-stage framework for predicting the most congested traffic level that appears after an accident and the recovery time required for returning to the level of service that existed at the accident report time. As fewer accident characteristics are available at the report time, stage one models rely on real-time traffic and weather variables. With the arrival of the responders at the accident scene, more information is gained; therefore, the second stage model is activated, which updates the remaining accident duration time. We used eXtreme Gradient Boosting (XGBoost), a machine learning algorithm, and Shapley Additive exPlanations (SHAP) for making predictions and interpreting results, respectively. The results show that our framework predicts traffic levels with overall accuracies of around 80%, and duration models have high forecast accuracy with mean absolute percentage errors ranging between 7.26% and 21.59%. Overall, in the absence of accident information, SHAP values identified that weather factors, the traffic speed difference before and after an accident, traffic volume, and the percentage of heavy vehicles before the accident are the most important variables. However, accident variables, including the occurrence of injury or fatal accidents, rear-end collisions, and the number of involved vehicles, are among the most important variables in the second stage of the framework. The findings have practical implications for real-time traffic management of accident events. Road operators could manage post-accident traffic conditions more effectively, and road users could be alerted to take another route or manage their trip. [ABSTRACT FROM AUTHOR]

Network traffic state prediction has been constantly challenged by complex spatiotemporal features of traffic information as well as imperfection in streaming data. This paper proposes a traffic flow prediction model for spatiotemporal graph networks based on fusion of attention mechanisms (STGNN-FAM) to simultaneously tackle these challenges. This model contains a spatial feature extraction layer, a bidirectional temporal feature extraction layer, and an attention fusion layer, which not only fully considers the temporal and spatial features of the traffic flow problem but also uses the attention mechanism to enhance the critical temporal and spatial features to achieve more accurate and robust predictions. Experimental results on a network traffic speed dataset PeMSD7 show that the proposed STGNN-FAM outperforms several important benchmarks in prediction accuracy and the ability to withstand interference in the data stream, especially for mid- and long-term prediction of 30 minutes and 45 minutes. [ABSTRACT FROM AUTHOR]

To enhance the traffic operation efficiency at signalized intersections, a model for coupled control of traffic signals and connected autonomous vehicles at isolated signalized intersections is proposed. This model estimates the time that CAVs reach stop lines with real-time information about the speed and position of CAVs. The arrival time is leveraged to optimize traffic signal timing by rolling horizon, with the maximization of phase saturation as the optimization objective. Based on the optimized traffic signal timing, the speed profile of CAVs is optimized by a linear integer programming, with the maximization of speed at the moment of reaching the stop line as the optimization objective. Through the coupled control of travel speed and the traffic signal, CAVs can pass through the intersection safely, efficiently, and smoothly. NetLogo, a multiagent microscopic simulator, is developed to test this strategy, and an intersection in Weihai is taken for verification and analysis lastly. The simulation results demonstrate that, compared with the fixed traffic signal timing control and the model optimizing only speed profile of CAVs, the proposed model can reduce the average number of stops by 47.0% and the queuing time by 41.3%. In addition, the optimization is better during off-peak hours, about 10% higher than the peak hours. [ABSTRACT FROM AUTHOR]

On-ramps are considered to be one of the common traffic bottlenecks. In order to improve the operation efficiency of on-ramps, scholars worldwide have proposed various vehicle merging strategies. In this study, we designed different rules to express three collaborative strategies and studied their impact on on-ramp systems. Cellular automata models were used to simulate the systems under different situations, and the average speed and traffic flow rate of both the main roads and ramps were analyzed. The results show that (1) all the three merging strategies give excessive "priority" to the merging vehicle, leading to a severe reduction in the traffic performance of the main road; (2) nevertheless, these strategies have different effects on the entire system with a one-lane or two-lane main road. Due to the lane-changing behavior, the system with a two-lane main road has more advantages than that featured with a one-lane road, making the former system performing better than the latter under the same strategies; (3) the vehicles on the ramp and main road affect each other, and as the vehicle entering probabilities become large, the traffic flow rate on the main road decreases whereas that on the ramp increases. However, the effect is not unlimited, the flow rate on both roads finally reaches a stable level (forming a "platform"); and (4) large values of the merging safety distance parameter decrease the flow rate of the entire system. All the previous results provide a deep understanding of the impact of the three merging strategies on traffic flow, contributing to the design of on-ramp systems that have better operation efficiency and low levels of congestion. [ABSTRACT FROM AUTHOR]

The intelligent transportation system (ITS) has been proven capable of effectively addressing traffic congestion issues. For vehicles to perform effectively and improve mobility under the intelligent driving environment, real-time prediction of traffic speed is undoubtedly essential. Considering the complex spatiotemporal dependency inherent in traffic data, conventional prediction models encounter many limitations. To improve the prediction performance and investigate the temporal features, this study focuses on emerging deep neural networks (DNNs) using the Caltrans Performance Measurement System (PeMS) data. This research also establishes an intelligent driving environment in the simulation and compares the traditional car-following model with deep learning methods in terms of multiple performance metrics. The results indicate that both supervised learning and unsupervised learning are superior to the simulation-based model on the freeway, and the two deep learning networks are almost identical to one another. Besides, the result reveals that all models have their latent features for different time dimensions under the low traffic loads, transition states, and heavy traffic loads. This is critical in the application of prediction technologies in ITS. The findings can assist transportation researchers and traffic engineers in both traffic operation and management, such as bottleneck identification, platooning control, and route planning. [ABSTRACT FROM AUTHOR]

Pedestrian crossing chaos has become one of the significant problems of urban traffic nowadays, and the irregular behavior of pedestrians affects traffic operation and regional safety to a certain extent. Aiming at the safety of pedestrian crossing in the advance right-turn lane, the pedestrian path deviation (PPD) is proposed to quantitatively describe the pedestrian crossing path deviation and analyze the impact of PPD on pedestrian crossing safety. With four advance right-turn lanes at an intersection in Qingdao as the investigation site, the spatiotemporal information of pedestrians and motor vehicles is collected to analyze the characteristics of pedestrian path distribution and the influencing factors of pedestrian crossing under the factors of traffic flow and environment. The pedestrian-vehicle conflict characteristics are analyzed from the perspective of conflict rate and deceleration-to-safety. The severity level of human-vehicle conflict is classified according to the cumulative frequency of safety deceleration, and the severity model of human-vehicle conflict based on ordered probit is established. The results show that buildings such as large shopping malls and transportation hubs have an attractive effect on pedestrians. Under the influence of unilateral buildings, the proportion of irregular use of pedestrian crosswalks reaches 46.9%. There is a significant positive correlation between pedestrian flow and PPD index, and the increase of pedestrian flow causes the aggravation of pedestrian path deviation. The results of the analysis of PPD with pedestrian-vehicle conflict rate and conflict severity show that the increase of PPD significantly increases the risk of pedestrian-vehicle conflict occurrence; in addition, motor vehicle speed and PPD have significant effects on the severity of pedestrian-vehicle conflict, and the increase of both vehicle traffic speed and PPD causes the aggravation of the severity level of pedestrian-vehicle conflict. Combined with the above findings, the PPD index has some value in quantifying pedestrian spatial violations as well as regional safety evaluation, and the findings can provide theoretical guidance for the establishment of traffic facilities. [ABSTRACT FROM AUTHOR]

With the great development of urban transportation systems, immediate urban traffic information has become an essential resource for the public. Traffic estimation is to predict current or future traffic situation (traffic speed and/or volume) in a road or a region of a city, and can benefit our daily life from many aspects, such as routing planning and traffic management. Existing works focus on estimating future traffic for individual road segments from a perspective of fine-grained level. This paper presents a new approach to estimating future traffic from a perspective of coarse-grained level, by which we estimate the traffic situation of a region, instead of an individual road segment. We propose a new concept about regional traffic named Ω-region, which aims to reflect the traffic situation of a region precisely. Two challenges in the regional traffic estimation problem are how to partition the road network into reasonable regions and how to estimate the regional traffic effectively. To address these challenges, first we define reasonable regions Ω-regions with traffic situations so that the all the road segment in the region has similar traffic. Then, we propose a three-phase partition method to divide the road network into Ω-regions based on historical trajectory data. Thirdly, we propose an effective linear-based model to estimate regional traffic. Experimental results on real-world dataset show that our proposed method achieves high performance. [ABSTRACT FROM AUTHOR]

As a typical spatiotemporal problem, there are three main challenges in traffic forecasting. First, the road network is a nonregular topology, and it is difficult to extract complex spatial dependence accurately. Second, there are short- and long-term dependencies between traffic dates. Third, there are many other factors besides the influence of spatiotemporal dependence, such as semantic characteristics. To address these issues, we propose a spatiotemporal DeepWalk gated recurrent unit model (ST-DWGRU), a deep learning framework that fuses spatial, temporal, and semantic features for traffic speed forecasting. In the framework, the spatial dependency between nodes of an entire road network is extracted by graph convolutional network (GCN), whereas the temporal dependency between speeds is captured by a gated recurrent unit network (GRU). DeepWalk is used to extract semantic information from road networks. Three publicly available datasets with different time granularities of 15, 30, and 60 min are used to validate the short- and long-time prediction effect of this model. The results show that the ST-DWGRU model significantly outperforms the state-of-the-art baselines. [ABSTRACT FROM AUTHOR]

Timely and precise traffic state estimation of urban roads is significant for urban traffic management and operation. However, most of the advanced studies focus on building complex deep learning structures to learn the spatiotemporal feature of the urban traffic flow, ignoring improving the efficiency of the traffic state estimation. Considering the benefit of the tensor decomposition, we present a novel urban traffic state estimation based on dynamic tensor and Bayesian probabilistic decomposition. Firstly, the real-time traffic speed data are organized in the form of a dynamic tensor which contains the spatiotemporal characteristics of the traffic state. Then, a dynamic tensor Bayesian probabilistic decomposition (DTBPD) approach is built by decomposing the dynamic tensor into the outer product of several vectors. Afterward, the Gibbs sampling method is introduced to calibrate the parameters of the DTBPD models. Finally, the real-world traffic speeds data extracted from online car-hailing trajectories are employed to validate the model performance. Experimental results indicate that the proposed model can greatly reduce computational time while maintaining relatively high accuracy. Meanwhile, the DTBPD model outperforms the state-of-the-art models in terms of both single-step-ahead and multistep-ahead traffic state estimation. [ABSTRACT FROM AUTHOR]

As a typical spatiotemporal problem, there are three main challenges in traffic forecasting. First, the road network is a nonregular topology, and it is difficult to extract complex spatial dependence accurately. Second, there are short- and long-term dependencies between traffic dates. Third, there are many other factors besides the influence of spatiotemporal dependence, such as semantic characteristics. To address these issues, we propose a spatiotemporal DeepWalk gated recurrent unit model (ST-DWGRU), a deep learning framework that fuses spatial, temporal, and semantic features for traffic speed forecasting. In the framework, the spatial dependency between nodes of an entire road network is extracted by graph convolutional network (GCN), whereas the temporal dependency between speeds is captured by a gated recurrent unit network (GRU). DeepWalk is used to extract semantic information from road networks. Three publicly available datasets with different time granularities of 15, 30, and 60 min are used to validate the short- and long-time prediction effect of this model. The results show that the ST-DWGRU model significantly outperforms the state-of-the-art baselines. [ABSTRACT FROM AUTHOR]

This study proposed a modified metric inspired by the well-applied "resilience-triangle" framework to integrate the resilience concept within the traffic speed. Firstly, for setting the evolving normal functionality, this study added the concepts of robustness loss and rapidity to characterize and compare the recovery processes of local roads and assess the corresponding resilience under different traffic operation conditions. Secondly, these different evolving resilience patterns provide a quantitative benchmark for detecting the links between resilience and traffic operating conditions and exploring its impact on total resilience. Finally, this study simulated and compared the dynamic evolution of the total resilience of local roads, which accurately captured the weak and poorly resilient road locations. Our findings indicated that the proposed metric was quite efficient and accurate in assisting stakeholders to prioritize the transport planning and the retrofit projects of some specific local roads, which could improve the resilience of overall transport system significantly. [ABSTRACT FROM AUTHOR]

The superblock has become a typical land use in China and many growing Asian cities. Superblock access points generate traffic congestion and many conflicts among all road users. Driveway design is a critical process and has a major impact on traffic conditions around superblocks. There are various guidelines for the two key factors for driveway design, driveway width and curb radius, but they provide reference values corresponding to traffic volume and speed; these are not sufficient for managing the complex traffic environment around superblocks. To improve driveway design, we develop detailed access point design models that account for conflicts between turning and through motorized vehicles, conflicts between motorized and nonmotorized traffic, speed differential larger than 10 km/h, and lane encroachments of entering and exiting vehicles. The crash risk models evaluate and optimize the combination of driveway width and curb radius with respect to three traffic safety indexes: traffic conflict, lane encroachment, and speed differential. A case study evaluation shows that the updated driveway design models produce a lower crash risk; seven of the ten driveways improved by 16.14% or more. The updated driveway design for superblocks would be beneficial for analyzing, permitting, and managing traffic operations at superblocks and oversized development with many and complex driveways. [ABSTRACT FROM AUTHOR]

Driven by the emission peak and carbon neutrality targets, traditional cruising taxis are also under pressure to reduce emissions, and reducing taxi vacant time is an effective way to reduce emissions. This paper aims to examine the influence mechanism of built environment characteristics on vacant time of taxi trips from the supply-side perspective. To do so, the study uses a one week of taxi trajectory data of 2019 provided by a taxi company in Chongqing, a megacity in China. We take the divided square grid cell as the study units, calculate the taxi vacant time of 168 (7 × 24) hourly slots for each grid, and then calculate the built environment indicators of the grids with Point of Interest (POI) and vector road network data. A generalized additive model (GAM) based on panel data is constructed to investigate the influence mechanism of built environment on taxi vacant time. The results show that the time-varying trend of taxi vacant time is opposite to the time-varying trend of taxi trips and is similar to taxi trips in spatial distribution with significant spatial dependence. Taxi vacant time is negatively correlated with taxi trips. POI mixture, the number of enterprises, governmental agencies, and shopping services are negatively correlated with vacant time, while the number of sports and leisure services, hotel services, healthcare services, financial and insurance services, and living services are positively correlated with vacant time. An interesting finding is that metro stations significantly increase the vacant taxi time in the region. Average traffic flow speed, road density, the number of bus stops, catering services, residence communities, and motor vehicle services show strong nonlinear relationships with taxi vacant time, and their influence effects are alternately positive and negative. The study provides useful insights for understanding mechanisms of the role of built environment on taxi vacant time and has important implications for driver searching strategy improvement, taxi management measures development, spatial and temporal scheduling of taxi capacity resources, and urban transportation facilities layout planning. [ABSTRACT FROM AUTHOR]

In order to accurately analyse the impact of the rainy environment on the characteristics of highway traffic flow, a short-term traffic flow speed prediction model based on gate recurrent unit (GRU) and adaptive nonlinear inertia weight particle swarm optimization (APSO) was proposed. Firstly, the rainfall and highway traffic flow data were cleaned, and then they are matched according to the spatiotemporal relationship. Secondly, through the method of multivariate analysis of variance, the significance of the impact of potential factors on traffic flow speed was explored. Then, a GRU-based traffic flow speed prediction model in rainy environment is proposed, and the actual road sections under different rainfall scenarios were verified. After that, in view of the problem that the prediction accuracy of the GRU model was low in the continuous rainfall scenario, the APSO algorithm was used to optimize the parameters of the GRU network, and the APSO-GRU prediction model was constructed and verifications under the same road section and rain scene were carried out. The results show that the APSO-GRU model has significantly improved prediction stability than the GRU model and can better extract rainfall features during continuous rainfall, with an average prediction accuracy rate of 96.74%. [ABSTRACT FROM AUTHOR]

Weaving sections are components of highway networks that introduce a heightened likelihood for bottlenecks and collisions. Automated vehicle technology could address this as it holds considerable promise for transportation mobility and safety improvements. However, the implications of combining automated vehicles (AuVs) with traditional human-driven vehicles (HuVs) in weaving freeway sections have not been quantitatively measured. To address this gap, this paper objectively experimented with bidirectional (i.e., longitudinal and lateral) motion dynamics in a microscopic modeling framework to measure the mobility and safety implications for mixed traffic movement in a freeway weaving section. Our research begins by establishing a multilane microscopic model for studied vehicle types (i.e., AuV and HuV) from model predictive control with the provision to form a CACC platoon of AuV vehicles. The proposed modeling framework was tested first with HuV only on a two-lane weaving section and validated using standardized macroscopic parameters from the Highway Capacity Manual. This model was then applied to incrementally expand the AuV share for varying inflow rates of traffic. Simulation results showed that the maximum flow rate through the weaving section was attained at a 65% AuV share. At the same time, steadiness in the average speed of traffic was experienced with increasing AuV share. The results also revealed that a 95% AuV share could reduce potential conflicts by 94.28%. Finally, the results of simulated scenarios were consolidated and scaled to report expected mobility and safety outcomes from the prevailing traffic state and the optimal AuV share for the current inflow rate in weaving sections. [ABSTRACT FROM AUTHOR]

Children pedestrians represent road users with some specifics because of which it is important to study and take into account their traffic behaviour when traffic infrastructure is designed. Design should ensure and enhance their traffic safety because for decades, traffic accidents have been among the first few causes of children and adolescent mortality. Pedestrian speed is one of the important inputs when pedestrian infrastructure, especially crosswalks, is designed. On corridors where children are expected on a daily basis as independent pedestrians, the infrastructure should be adjusted to their characteristics and needs. The results of a study conducted in two Croatian cities of a similar size but of different urban and traffic conditions are presented in this paper. This study aimed at establishing and analysing children's pedestrian speed while crossing the signalized crosswalk in the buffer area of elementary schools, mostly on primary roads in the school vicinity. Children aged 5–15 were observed, and accordingly V15, V50, and V85 speeds were established on the basis of altogether 600 measurements. Speed was established for children walking individually, in a group and supervised by adults, and of a different age, and based on their gender, the impact of infrastructural elements on their speed in traffic was also analysed. Significant differences were found between children's speed measured in similar conditions in analysed cities and between some of the analysed groups. This fact proves that when improving conditions for children's independent movement, it is important to consider their specifics in order to ensure safe design adjusted to children's needs and limitations. As design speed in this paper, 15 percentile speed (V15) is considered. Suggestions on how to establish children pedestrian speed for design of routes regularly used by school children are proposed as well as some inputs elicited from the study done in Croatia are presented. [ABSTRACT FROM AUTHOR]

Children pedestrians represent road users with some specifics because of which it is important to study and take into account their traffic behaviour when traffic infrastructure is designed. Design should ensure and enhance their traffic safety because for decades, traffic accidents have been among the first few causes of children and adolescent mortality. Pedestrian speed is one of the important inputs when pedestrian infrastructure, especially crosswalks, is designed. On corridors where children are expected on a daily basis as independent pedestrians, the infrastructure should be adjusted to their characteristics and needs. The results of a study conducted in two Croatian cities of a similar size but of different urban and traffic conditions are presented in this paper. This study aimed at establishing and analysing children's pedestrian speed while crossing the signalized crosswalk in the buffer area of elementary schools, mostly on primary roads in the school vicinity. Children aged 5–15 were observed, and accordingly V15, V50, and V85 speeds were established on the basis of altogether 600 measurements. Speed was established for children walking individually, in a group and supervised by adults, and of a different age, and based on their gender, the impact of infrastructural elements on their speed in traffic was also analysed. Significant differences were found between children's speed measured in similar conditions in analysed cities and between some of the analysed groups. This fact proves that when improving conditions for children's independent movement, it is important to consider their specifics in order to ensure safe design adjusted to children's needs and limitations. As design speed in this paper, 15 percentile speed (V15) is considered. Suggestions on how to establish children pedestrian speed for design of routes regularly used by school children are proposed as well as some inputs elicited from the study done in Croatia are presented. [ABSTRACT FROM AUTHOR]

In a low-visibility environment, the speed of traffic flow is more discrete on highways, which easily causes traffic accidents. To improve the safety and efficiency level of low-visibility zones on highways, a comprehensive optimization control method is proposed. The method uses formations of a low-visibility zone to queue discrete vehicles from the upstream intersection. Then, according to the relationship between the arrival time of the fleet and the phase state of the intersection, speed guidance and trajectory optimization are carried out to improve the traffic efficiency of the fleet that enters the low-visibility zone. Finally, a low-visibility zone of a highway segment is analysed with different traffic flows for the main road and the secondary roads, and the results show that the proposed optimization control method can prevent trajectory overlap and effectively decrease traffic delays on highways. [ABSTRACT FROM AUTHOR]

In order to reduce driving risk in the rainfall days, developing the variable speed limits (VSL) is effective. However, it is hard to develop suitable VSL aligning with travel speed of mainstream that it affected by the traffic flow, rainfall intensity, individual travel speed, peak hours, working days, random events, and so on. In this paper, the average travel speed and traffic flow of each road section are calculated from the toll collection data of Xi'an Ring Road from May to July in 2018 in Shaanxi Province, China. The weather data are collected and extrapolated to the corresponding road sections. Travel speed, traffic flow, and rainfall intensity are integrated to predict the fluctuation trend of travel speed through the proposed deep belief-radial basis function network. The experimental results show that a significant decrease happens in the travel speed in the rainfall day during peak hours. Furthermore, the deep learning algorithm that considers more factors such as the rainfall intensity and traffic flow could improve the prediction accuracy. Then, a VSL method and an expressway risk coefficient evaluation method based on estimation of average travel speed are proposed. The experimental results show that the variable 85th percentile speed limit method proposed in this paper can reduce the risk of expressway driving. This can promote road safety in the development of intelligent transportation system (ITS) in future. [ABSTRACT FROM AUTHOR]

The COVID-19 pandemic crisis has impacted numerous areas of people's work and free-time activities. This article aims to present the main impacts of the COVID-19 movement restrictions on the road traffic in the Czech Republic, measured during the first epidemic wave, i.e., from 12 March to 17 May 2020. The state of emergency was imposed by the Czech government as a de jure measure for coping with the perceived crisis, although the measure eventually resulted only in a quite liberal de facto form of stay-at-home instruction. Unique country-scale traffic data of the first six months of 2020 from 37,002 km of roads, constituting 66% of all roads in the Czech Republic, were collected and analyzed. For the prediction of the prepandemic traffic conditions and their comparison with the measured values in the period of the state of emergency, a long-term traffic speed prediction ensemble model consisting of case-based reasoning, linear regression, and fallback submodels was used. The authors found out that the COVID-19 movement restrictions had a significant impact on the country-wide traffic. Traffic density was reduced considerably in the first three weeks, and the weekly average traffic speed in all road types increased by up to 21%, expectedly due to less crowded roads. The exception was motorways, where a different trend in traffic was found. In sum, during the first three weeks of the state of emergency, people followed government regulations and restrictions and changed their travel behavior accordingly. However, following this period, the traffic gradually returned to the prepandemic state. This occurred three weeks before the state of emergency was terminated. From a behavioral perspective, this article briefly discusses the possible causes of such discrepancies between de jure and de facto pandemic measures, i.e., the governmental communication strategy related to loosening of movement restrictions, media reality, and certain culture-related traits. [ABSTRACT FROM AUTHOR]

Variable speed limit (VSL) control dynamically adjusts the displayed speed limit to harmonize traffic speed, prevent congestions, and reduce crash risks based on prevailing traffic stream and weather conditions. Previous research studies examine the impacts of VSL control on reducing corridor-level crash risks and improving bottleneck throughput. However, less attention focuses on utilizing real-world data to see how compliant the drivers are under different VSL values and how the aggregated driving behavior changes. This study aims to fill the gap. With the high-resolution lane-by-lane traffic big data collected from a European motorway, this study performs statistical analysis to measure the difference in driving behavior under different VSL values and analyze the safety impacts of VSL controls on aggregate driving behaviors (mean speed, average speed difference, and the percentage of small space headway). The data analytics show that VSL control can effectively decrease the mean speed, the speed difference, and the percentage of small space headways. The safety impacts of VSL control on aggregated driving behavior are also discussed. The aggregated driving behavior variables follow a trend of first decreasing and then increasing with the continuous decrease in VSL values, indicating that potential traffic safety benefits can be achieved by adopting suitable VSL values that match with prevailing traffic conditions. [ABSTRACT FROM AUTHOR]

This paper presents the development and evaluation of short-term traffic prediction models using unidirectional and bidirectional deep learning long short-term memory (LSTM) neural networks. The unidirectional LSTM (Uni-LSTM) model provides high performance through its ability to recognize longer sequences of traffic time series data. In this work, Uni-LSTM is extended to bidirectional LSTM (BiLSTM) networks which train the input data twice through forward and backward directions. The paper presents a comparative evaluation of the two models for short-term speed and traffic flow prediction using a common dataset of field observations collected from multiple freeways in Australia. The results showed BiLSTM performed better for variable prediction horizons for both speed and flow. Stacked and mixed Uni-LSTM and BiLSTM models were also investigated for 15-minute prediction horizons resulting in improved accuracy when using 4-layer BiLSTM networks. The optimized 4-layer BiLSTM model was then calibrated and validated for multiple prediction horizons using data from three different freeways. The validation results showed a high degree of prediction accuracy exceeding 90% for speeds up to 60-minute prediction horizons. For flow, the model achieved accuracies above 90% for 5- and 10-minute prediction horizons and more than 80% accuracy for 15- and 30-minute prediction horizons. These findings extend the set of AI models available for road operators and provide them with confidence in applying robust models that have been tested and evaluated on different freeways in Australia. [ABSTRACT FROM AUTHOR]

Unpredictable and heterogeneous weather conditions and road incidents are common factors that impact highway traffic speeds. A better understanding of the interplay of different factors that affect roadway traffic speeds is essential for policymakers to mitigate congestion and improve road safety. This study investigates the effect of precipitation and incidents on the speed of traffic in the eastbound direction of I-64 in Virginia. To the best of our knowledge, this is the first study that studies the relationship between precipitation and incidents as factors that would have a combined effect on traffic stream speeds. Furthermore, using a mixture model of two linear regressions, we were able to model the two different regimes that the traffic speed could be classified into, namely, free-flow and congested. Using INRIX traffic data from 2013 through 2016 along a 25.6-mi section of Interstate 64 in Virginia, results show that the reduction of traffic speed only due to incidents ranges from 41% to 75% if the road is already congested. In this case, precipitation was found to be statistically insignificant. However, regardless of the incident impact, the effect of light rain in free-flow conditions ranges from insignificant to a 4% speed reduction while the effect of heavy rain ranges from a 0.6% to a 6.5% speed reduction when the incident severity is low but has a roughly double effect when the incident severity is high. [ABSTRACT FROM AUTHOR]

As a typical time series, the length of the data sequence is critical to the accuracy of traffic state prediction. In order to fully explore the causality between traffic data, this study established a temporal backtracking and multistep delay model based on recurrent neural networks (RNNs) to learn and extract the long- and short-term dependencies of the traffic state data. With a real traffic data set, the coordinate descent algorithm was employed to search and determine the optimal backtracking length of traffic sequence, and multistep delay predictions were performed to demonstrate the relationship between delay steps and prediction accuracies. Besides, the performances were compared between three variants of RNNs (LSTM, GRU, and BiLSTM) and 6 frequently used models, which are decision tree (DT), support vector machine (SVM), k-nearest neighbour (KNN), random forest (RF), gradient boosting decision tree (GBDT), and stacked autoencoder (SAE). The prediction results of 10 consecutive delay steps suggest that the accuracies of RNNs are far superior to those of other models because of the more powerful and accurate pattern representing ability in time series. It is also proved that RNNs can learn and mine longer time dependencies. [ABSTRACT FROM AUTHOR]

Traffic congestion in the adjacent region between the highway and urban expressway is becoming more and more serious. This paper proposes a traffic speed forecast method based on the Macroscopic Fundamental Diagram (MFD) and Gated Recurrent Unit (GRU) model to provide the necessary traffic guidance information for travelers in this region. Firstly, considering that the road traffic speed is affected by the macroscopic traffic state, the adjacent region between the highway and expressway is divided into subareas based on the MFD. Secondly, the spatial-temporal correlation coefficient is proposed to measure the correlation between subareas. Then, the matrix of regional traffic speed data is constructed. Thirdly, the matrix is input into the GRU prediction model to get the predicted traffic speed. The proposed algorithm's prediction performance is verified based on the GPS data collected from the adjacent region between Beijing Highways and Expressway. [ABSTRACT FROM AUTHOR]

Short-term traffic speed prediction is a promising research topic in intelligent transportation systems (ITSs), which also plays an important role in the real-time decision-making of traffic control and guidance systems. However, the urban traffic speed has strong temporal, spatial correlation and the characteristic of complex nonlinearity and randomness, which makes it challenging to accurately and efficiently forecast short-term traffic speeds. We investigate the relevant literature and found that although most methods can achieve good prediction performance with the complete sample data, when there is a certain missing rate in the database, it is difficult to maintain accuracy with these methods. Recent studies have shown that deep learning methods, especially long short-term memory (LSTM) models, have good results in short-term traffic flow prediction. Furthermore, the attention mechanism can properly assign weights to distinguish the importance of traffic time sequences, thereby further improving the computational efficiency of the prediction model. Therefore, we propose a framework for short-term traffic speed prediction, including data preprocessing module and short-term traffic prediction module. In the data preprocessing module, the missing traffic data are repaired to provide a complete dataset for subsequent prediction. In the prediction module, a combined deep learning method that is an attention-based LSTM (ATT-LSTM) model for predicting short-term traffic speed on urban roads is proposed. The proposed framework was applied to the urban road network in Nanshan District, Shenzhen, Guangdong Province, China, with a 30-day traffic speed dataset (floating car data) used as the experimental sample. Results show that the proposed method outperforms other deep learning algorithms (such as recurrent neural network (RNN) and convolutional neural network (CNN)) in terms of both calculating efficiency and prediction accuracy. The attention mechanism can significantly reduce the error of the LSTM model (up to 12.4%) and improves the prediction performance. [ABSTRACT FROM AUTHOR]

This study proposes a methodology for the calibration of microscopic traffic flow simulation models by enabling simultaneous selection of traffic links and associated parameters. The analyst selects any number and combination of links and model parameters for calibration. Most calibration methods consider the entire network and use ad hoc approaches without enabling a specific selection of location and associated parameters. In practice, only a subset of links and parameters is used for calibration based on several factors such as expert knowledge of the system or constraints imposed by local governance. In this study, the calibration problem for the simultaneous selection of links and parameters was formulated using a mathematical programming approach. The proposed methodology is capable of calibrating model parameters considering multiple time periods and performance measures simultaneously. Traffic volume and speed are the performance measures used in this study, and the methodology is developed without considering the characteristics of a specific traffic flow model. A genetic algorithm was implemented to find a solution to the proposed mathematical program. In the experiments, two traffic models were calibrated: the first set of experiments included selection of links only, while all associated parameters were considered for calibration. The second set of experiments considered simultaneous selection of links and parameters. The implications of these experiments indicate that the models were calibrated successfully subject to selection of a minimum number of links. As expected, the more links and parameters that are used for calibration, the more time it takes to find a solution, but the overall results are better. All parameter values were reasonable and within constraints after successful calibration. [ABSTRACT FROM AUTHOR]

Connected and autonomous vehicles (CAVs) are on the way to the field application. In the beginning stage, there will be a mixed traffic flow, containing the regular human-driven vehicles and CAVs with a low penetration rate. Recently, the discussion about the impact of a small proportion of CAVs in the mixed traffic is controversial. This paper investigated the possibility of applying the limited data from these lowly penetrated CAVs to estimate the average freeway link speeds based on the Kalman filtering (KF) method. First, this paper established a VISSIM-based microsimulation model to mimic the mixed traffic with different CAV penetration rates. The characteristics of this mixed traffic were then discussed based on the simulation data, including the sample size distribution, data-missing rate, speed difference, and fundamental diagram. Accordingly, the traditional KF-based method was introduced and modified to adapt data from CAVs. Finally, the evaluations of the estimation accuracy and the sensitive analysis of the proposed method were conducted. The results revealed the possibility and applicability of link speed estimation using data from a small proportion of CAVs. [ABSTRACT FROM AUTHOR]

Current studies on traffic crash prediction mainly focus on the crash frequency and crash severity of freeways or arterials. However, collision type for urban expressway crash is rarely considered. Meanwhile, with the rapid development of urban expressway systems in China in recent years, traffic safety problems have attracted more attention. In addition, the traffic characteristics are considered to be a potentially important predictor of traffic accidents; however, their impact on crashes has been controversial. Therefore, a crash frequency predicting model for urban expressway considering collision types is proposed in this study. The loop detector traffic data and historical crash data were aggregated based on the similarities of the traffic conditions 5 minutes before crash occurrence, among which crashes were divided by collision type (rear-end collision and side-impact collision). The impact of traffic characteristics along with weather variables as well as their interactions on crash frequency was modelled by using negative binomial regression model. The results indicated that the influence of traffic and weather factors on two collision types shared similar trend, but different level. For rear-end collisions, crash frequency increased with lower average speed and high traffic volume under low speed limit. And when the speed limit is high, higher average speed coupled with larger volume increases the probability of crash. Higher average speed and traffic volume increase the probability of side-impact collisions, without being affected by the speed limit. The findings of the present study could help to determine efficient safety countermeasures aimed at improving the safety performance of urban expressway. [ABSTRACT FROM AUTHOR]

In recent years, there are more and more applications of traffic violation monitoring in some countries. The present work aims to analyze the vehicle speeds nearby road traffic violation monitoring area on urban main roads and find out the impact of road traffic violation monitoring on the vehicle speeds. A representative urban main road section was selected and the traffic flow was recorded by camera method. The vehicle speeds before, within, and after the road traffic violation monitoring area were obtained by the calculation method. The speed data was classified and processed by SPSS software and mathematical method to establish the vehicle speed probability density models before, within, and after the road traffic violation monitoring area. The results show that the average speed and maximum speed within the traffic violation monitoring area are significantly slower than those before and after the traffic violation monitoring area. 70.1% of the vehicles before the road traffic violation monitoring area were speeding, and 80.2% of the vehicles after the road traffic violation monitoring area were speeding, while within the road traffic violation monitoring area, the speeding vehicles were reduced to 15.9%. When vehicles pass through the road traffic violation monitoring area, the vehicle speeds tend to first decrease and subsequently increase. In its active area, road traffic violation monitoring can effectively regulate driving behaviors and reduce speeding, but this effect is limited to the vicinity of the traffic violation monitoring. The distribution of vehicle speeds can be calculated from vehicle speed probability density models. [ABSTRACT FROM AUTHOR]

Speeding is a major risk factor for traffic-related injuries. As a countermeasure against speeding, automated speed enforcement systems (ASES) have been deployed in many countries. However, drivers' awareness of enforcement locations allows themselves to adjust vehicle speeds in the vicinity of the enforcement locations. This enforcement avoidance behavior leads to a criticism of the effectiveness of ASES, in which the system promotes abrupt changes in vehicle speed near enforcement locations, increasing crash risk as a side effect. To address this issue, the section speed enforcement system (SSES), which enforces overspeeding vehicles by their average travel speed over a section, has been devised. In this study, we evaluate traffic speed and safety data that were collected from sections with SSES on Korean expressways. The speed analysis showed that the vehicles reduced their speeds inside the enforcement section, and this reduction in speed variations across vehicles was also noticeable, signifying that the risk of traffic crash should be lower. In view of this, we have performed before and after comparative analysis using the empirical Bayes method with the comparison group. The outcomes estimate 43% reduction in crash occurrence after installation of SSES. Furthermore, turning point analysis confirmed that the reduction in crash occurrence ensued immediately after installation of SSES. [ABSTRACT FROM AUTHOR]

The HOV carpooling lane offers a feasible approach to alleviate traffic congestion. The connected vehicle environment is able to provide accurate traffic data, which could optimize the design of HOV carpooling schemes. In this paper, significant tidal traffic flow phenomenon with severe traffic congestion was identified on North Beijing road (bidirectional four-lane) and South Huaihai road (bidirectional six-lane) in Huai'an, Jiangsu Province. The historical traffic data of the road segments were collected through the connected vehicle environment facilities. The purpose of this study is to investigate the effect of adopting two HOV schemes (regular HOV scheme and reversible HOV carpooling scheme) on the urban arterial road under connected vehicle environment. VISSIM was used to simulate the proposed two HOV carpooling schemes at the mentioned road segment. The simulation results showed that the reversible HOV carpooling scheme could not only mitigate the traffic congestion caused by traffic tidal phenomenon but also improve the average speed and traffic volume of the urban arterial road segment, while the regular HOV scheme may exert a negative impact on the average speed and traffic volume on the urban arterial road segment. [ABSTRACT FROM AUTHOR]

Operating speed is a critical indicator for road alignment consistency design and safety evaluation. Although extensive studies have been conducted on operating speed prediction, few models can finish practical continuous prediction at each point along alignment on multilane highways. This study proposes a novel method to estimate the operating speed for multilane highways in China from the aspect of the three-dimensional alignment combination. Operating speed data collected in field experiments on 304 different alignment combination sections are detected by means of Global Positioning System. First, the alignment comprehensive index (ACI) is designed and introduced to describe the function accounting for alignment continuity and driving safety. The variables used in ACI include horizontal curve radius, change rate of curvature, deflection angle of curve, grade, and lane width. Second, the influence range of front and rear alignment on speed is determined on the basis of drivers' fixation range and dynamical properties of vehicles. Furthermore, a prediction model based on exponential relationships between road alignment and speeds is designed to predict the speed of passenger cars and trucks. Finally, three common criteria are utilized to evaluate the effectiveness of the prediction models. The results indicate that the prediction models outperform the other two operating speed models for their higher prediction accuracy. [ABSTRACT FROM AUTHOR]

A shockwave-based speed harmonization algorithm for the longitudinal movement of automated vehicles is presented in this paper. In the advent of Connected/Automated Vehicle (C/AV) environment, the proposed algorithm can be applied to capture instantaneous shockwaves constructed from vehicular speed profiles shared by individual equipped vehicles. With a continuous wavelet transform (CWT) method, the algorithm detects abnormal speed drops in real-time and optimizes speed to prevent the shockwave propagating to the upstream traffic. A traffic simulation model is calibrated to evaluate the applicability and efficiency of the proposed algorithm. Based on 100% C/AV market penetration, the simulation results show that the CWT-based algorithm accurately detects abnormal speed drops. With the improved accuracy of abnormal speed drop detection, the simulation results also demonstrate that the congestion can be mitigated by reducing travel time and delay up to approximately 9% and 18%, respectively. It is also found that the shockwave caused by nonrecurrent congestion is quickly dissipated even with low market penetration. [ABSTRACT FROM AUTHOR]

Reasonable parking charge and supply policy are essential for the regular operation of the traffic in city center. This paper develops an evaluation model for parking policies using system dynamics. A quantitative study is conducted to examine the effects of parking charge and supply policy on traffic speed. The model, which is composed of three interrelated subsystems, first summarizes the travel cost of each travel mode and then calibrates the travel choice model through the travel mode subsystem. Finally, the subsystem that evaluates the state of traffic forecasts future car speed based on bureau of public roads (BPR) function and generates new travel cost until the entire model reaches a steady state. The accuracy of the model is verified in Hangzhou Wulin business district. The related error of predicted speed is only 2.2%.The results indicate that the regular pattern of traffic speed and parking charge can be illustrated using the proposed model based on system dynamics, and the model infers that reducing the parking supply in core area will increase its congestion level and, under certain parking supply conditions, there exists an interval of possible pricing at which the service reaches a level that is fairly stable. [ABSTRACT FROM AUTHOR]

Road crashes are a major cause of death in many countries. Qatar has been battling to improve road safety on several fronts using different strategies, including road policing. The purpose of this study is to ascertain drivers' perceptions towards five existing and four proposed police traffic enforcement strategies and associated penalties and rewards in Qatar using face-to-face surveys. The results show that red-light running cameras were perceived to be the most successful existing strategy. The high violation fine and the automation of the system were mentioned as the main reasons for making this strategy the most successful. Three of the existing strategies, fixed-speed enforcement cameras, police enforcement, and mobile speed cameras, were conferred almost the same success percentage, followed by the demerit point system. Regarding the proposed strategies, rewarding safe drivers was selected by the participants as the most successful proposed strategy, followed by introducing more automated enforcement methods. Community service for traffic tickets came in third, followed by defensive driving school. These results can be used to influence future enhancements of existing strategies and guide the development of future traffic strategies being introduced in the traffic system. [ABSTRACT FROM AUTHOR]

The objective of this research is to identify the factors differentiating between single heavy vehicle collisions at intersections and midblocks by using a binary logit model. Our results show that single vehicle crashes involving heavy vehicle at intersections are more likely to occur on main roads and highways, whereas crashes at midblocks are more likely to occur on divided two-way roads, roads with special facilities or features (e.g. bridge) and roads with a higher percentage of heavy vehicle traffic. Intersection crashes are also more likely to involve vehicles that are turning left or right, resulting in angle crashes and vehicle overturn, whereas midblock crashes are more likely to involve vehicles on higher posted speed roads. Copyright © 2017 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

The cumulative travel-time responsive (CTR) algorithm determines optimal green split for the next time interval by identifying the maximum cumulative travel time (CTT) estimated under the connected vehicle environment. This paper enhanced the CTR algorithm and evaluated its performance to verify a feasibility of field implementation in a near future. Standard Kalman filter (SKF) and adaptive Kalman filter (AKF) were applied to estimate CTT for each phase in the CTR algorithm. In addition, traffic demand, market penetration rate (MPR), and data availability were considered to evaluate the CTR algorithm's performance. An intersection in the Northern Virginia connected vehicle test bed is selected for a case study and evaluated within vissim and hardware in the loop simulations. As expected, the CTR algorithm's performance depends on MPR because the information collected from connected vehicle is a key enabling factor of the CTR algorithm. However, this paper found that the MPR requirement of the CTR algorithm could be addressed (i) when the data are collected from both connected vehicle and the infrastructure sensors and (ii) when the AKF is adopted. The minimum required MPRs to outperform the actuated traffic signal control were empirically found for each prediction technique (i.e., 30% for the SKF and 20% for the AKF) and data availability. Even without the infrastructure sensors, the CTR algorithm could be implemented at an intersection with high traffic demand and 50-60% MPR. The findings of this study are expected to contribute to the field implementation of the CTR algorithm to improve the traffic network performance. Copyright © 2017 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

At non-signalized mid-block street crossings in China's cities, pedestrians often weave between motor vehicle flows. This paper investigated the influence patterns of the gender and age of pedestrians, the presence of a pedestrian group, vehicles' interference and the crossing direction on the crossing time at non-signalized mid-block street crossings in Changsha, China. The results show that the crossing speed is approximately 1-1.1 m/s; the crossing time increases with increasing age, and the crossing speed of a pedestrian will be quicker when the time gap between the pedestrian and the oncoming vehicle is smaller if he/she decides to cross. This paper also analyzed the crossing time pattern when pedestrians cross lane by lane and found that pedestrians spend the most time crossing the first lane and the least time crossing the middle lane, regardless of whether they are crossing from the curb to the central island or from the central island to the curb. The crossing speed is an important input to the design of pedestrian facilities, so these findings can be applied to the assessment of pedestrian crossing safety in China's cities and can provide a basis for the design of pedestrian crossing facilities. Copyright © 2017 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

This study aims to develop work zone speed-flow and capacity models, which incorporate work zone configuration factors including the number of work zones, geometrical alignment, work zone speed limit, and work zone length. On the basis of the traffic data from six work zone sites with various work zone configurations, two nonlinear traffic speed and flow models including work zone configuration factors are developed for the uncongested and congested traffic conditions, respectively. A work zone capacity model is proposed on the basis of the two models. The three models can further be used to examine the effects of work zone configuration factors on the speed-flow relationship and capacity at work zones. Results show that traffic speed, traffic flow, and work zone capacity increase with the posted speed limit. Traffic speed under uncongested conditions decreases with the geometric alignment, the number of work zones, work zone length, and heavy vehicle percentage. Under congested conditions, the increase of the number of work zones is found to exhibit a larger negative impact on the traffic flow than the increase of geometric alignment. The number of work zones is also found to have the largest negative impacts on work zone capacity, followed by the geometric alignment. Short work zone length exhibits a relatively minor contribution to increasing work zone capacity. Copyright © 2014 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

SUMMARY In this paper, we develop a macro traffic flow model with consideration of varying road conditions. Our analytical and numerical results illustrate that good road condition can enhance the speed and flow of uniform traffic flow whereas bad road condition will reduce the speed and flow. The numerical results also show that good road condition can smooth shock wave and improve the stability of traffic flow whereas bad road condition will lead to steeper shock wave and reduce the stability of traffic flow. Our results are also qualitatively accordant with empirical results, which implies that the proposed model can qualitatively describe the effects of road conditions on traffic flow. These results can guide traffic engineers to improve the road quality in traffic engineering. Copyright © 2012 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]