Search

The Time Space Diagram (TSD) can abstractly represent multiple data sources and the macroscopic state of road traffic. However, the TSDs may be incomplete due to missing data, which seriously affects traffic management. Therefore, this paper proposed a Multi-Directional Recurrent Graph Convolutional Network (MDRGCN) for reconstructing TSDs and estimating missing traffic speeds given sparse data. We designed multi-directional RNN layers for scanning the TSDs from horizontal and vertical directions, which can fully exploit the contextual dependencies of the traffic information. In addition, our model includes graph convolution layers for mining potential spatial correlations in the TSDs. The performance of the model reconstructed from TSDs is validated on the NGSIM dataset. We also provided a comparison with other advanced methods, and the experimental results show that our method can perform well at both low and high missing rates, significantly outperforming the baseline methods. [ABSTRACT FROM AUTHOR]

Accurate and fast traffic prediction is the data-based foundation for achieving traffic control and management, and the accuracy of prediction results will directly affect the effectiveness of traffic control and management. This paper proposes a new spatiotemporal periodic polynomial model for road traffic, which integrates the temporal, spatial, and periodic features of speed time series and can effectively handle the nonlinear mapping relationship from input to output. In terms of the model, we establish a road traffic speed prediction model based on polynomial regression. In terms of spatial feature extraction methods, we introduce a maximum mutual information coefficient spatial feature extraction method. In terms of periodic feature extraction methods, we introduce a periodic trend modeling method into the prediction of speed time series, and effective fusion is carried out. Four strategies are evaluated based on the Guangzhou road speed dataset: a univariate polynomial model, a spatiotemporal polynomial model, a periodic polynomial model, and a spatiotemporal periodic polynomial model. The test results show that the three methods proposed in this article can effectively improve prediction accuracy. Comparing the spatiotemporal periodic polynomial model with multiple machine learning models and deep learning models, the prediction accuracy is improved by 5.94% compared to the best feedforward neural network. The research in this article can effectively deal with the temporal, spatial, periodic, and nonlinear characteristics of speed prediction, and to a certain extent, improve the accuracy of speed prediction. [ABSTRACT FROM AUTHOR]

In urban Vehicular Ad-hoc Networks (VANETs), disseminating traffic data efficiently is challenging due to the dynamic and complex nature of the network. Multi-hop-based broadcasting approaches are commonly used to address this issue. However, selecting the optimal relay nodes poses a challenge and directly impacts network performance. Existing relay selection strategies, such as beacon-based methods, have limitations in scaling under different traffic conditions. This paper proposes a multi-attribute relay selection strategy for urban multi-hop VANETs to overcome these challenges. The strategy evaluates the rebroadcast capability of each receiving node based on its real-time status. It utilizes a fuzzy-BCM-based weight estimation strategy to determine the contribution of each attribute to the node's capability. The node with the highest broadcasting capability is given priority to access the channel and broadcast the data packet. The proposed scheme is evaluated through simulation tests in VANET simulation environments, considering various traffic flow and speed variations. Performance comparison with four benchmark methods is conducted. The results show that the proposed scheme improves the overall dissemination efficiency by 51.1% compared to the benchmarked methods. [ABSTRACT FROM AUTHOR]

Curb space is one of the busiest areas in urban road networks. Especially in recent years, the rapid increase of ride-hailing trips and commercial deliveries has induced massive pick-ups/drop-offs (PUDOs), which occupy the limited curb space that was designed and built decades ago. These PUDOs could jam curbside utilization and disturb the mainline traffic flow, evidently leading to significant negative societal externalities. However, there is a lack of an analytical framework that rigorously quantifies and mitigates the congestion effect of PUDOs in the system view, particularly with little data support and involvement of confounding effects. To bridge this research gap, this paper develops a rigorous causal inference approach to estimate the congestion effect of PUDOs on general regional networks. A causal graph is set to represent the spatiotemporal relationship between PUDOs and traffic speed, and a double and separated machine learning (DSML) method is proposed to quantify how PUDOs affect traffic congestion. Additionally, a rerouting formulation is developed and solved to encourage passenger walking and traffic flow rerouting to achieve system optimization. Numerical experiments are conducted using real-world data in the Manhattan area. On average, 100 additional units of PUDOs in a region could reduce the traffic speed by 3.70 and 4.54 miles/hour (mph) on weekdays and weekends, respectively. Rerouting trips with PUDOs on curb space could respectively reduce the system-wide total travel time (TTT) by 2.44% and 2.12% in Midtown and Central Park on weekdays. A sensitivity analysis is also conducted to demonstrate the effectiveness and robustness of the proposed framework. Funding: The work described in this paper was supported by the National Natural Science Foundation of China [Grant 52102385], grants from the Research Grants Council of the Hong Kong Special Administrative Region, China [Grants PolyU/25209221 and PolyU/15206322], a grant from the Otto Poon Charitable Foundation Smart Cities Research Institute (SCRI) at the Hong Kong Polytechnic University [Grant P0043552], and a grant from Hong Kong Polytechnic University [Grant P0033933]. S. Qian was supported by a National Science Foundation Grant [Grant CMMI-1931827]. Supplemental Material: The e-companion is available at https://doi.org/10.1287/trsc.2022.0195. [ABSTRACT FROM AUTHOR]

Accurate and real-time traffic speed prediction remains challenging due to the irregularity and asymmetry of real-traffic road networks. Existing models based on graph convolutional networks commonly use multi-layer graph convolution to extract an undirected static adjacency matrix to map the correlation of nodes, which ignores the dynamic symmetry change of correlation over time and faces the challenge of oversmoothing during training iterations, making it difficult to learn the spatial structure and temporal trend of the traffic network. To overcome the above challenges, we propose a novel multi-head self-attention gated spatiotemporal graph convolutional network (MSGSGCN) for traffic speed prediction. The MSGSGCN model mainly consists of the Node Correlation Estimator (NCE) module, the Time Residual Learner (TRL) module, and the Gated Graph Convolutional Fusion (GGCF) module. Specifically, the NCE module aims to capture the dynamic spatiotemporal correlations between nodes. The TRL module utilizes a residual structure to learn the long-term temporal features of traffic data. The GGCF module relies on adaptive diffusion graph convolution and gated recurrent units to learn the key spatial features of traffic data. Experimental analysis on a pair of real-world datasets indicates that the proposed MSGSGCN model enhances prediction accuracy by more than 4% when contrasted with state-of-the-art models. [ABSTRACT FROM AUTHOR]

Large and expanding cities suffer from a traffic congestion problem that harms the environment, travelers, and the economy. This paper aims to predict short term traffic congestion on a road section of expressway in Delhi city. For this purpose, we first propose a traffic congestion index based on traffic speed and flow. Clustering techniques and the Greenshield's model were used for the derivation of the congestion index. Using this congestion index, congested time intervals of each day and each location of a weekday were identified. This study also introduces a feature series long short-term memory neural network (FSLSTMNN), which links a long short-term memory (LSTM) layer to each feature. It is trained using the many heterogeneous traffic features data collected in Delhi city for the next five minutes of traffic flow and speed prediction. FSLSTMNN achieved the good capability to learn feature series data. We also trained several traditional and deep-learning models using the same traffic data. The FSLSTMNN reduces mean absolute error 12.90% and 17.13%, respectively, in speed and traffic flow prediction compared to the second good-performance long short-term memory neural network (LSTMNN). Finally, traffic congestion is predicted classwise (light, medium, and congested) using the developed congestion index and traffic speed and flow predicted by the FSLSTMNN. Predicted results are consistent with the measured field data. Study results confirm that the developed congestion index and FSLSTMNN can be used successfully to predict traffic congestion. [ABSTRACT FROM AUTHOR]

The Dirichlet process mixture (DPM) model has been widely used as a Bayesian nonparametric model for clustering. However, the exchangeability assumption of the Dirichlet process is not valid for clustering spatially correlated time series as these data are indexed spatially and temporally. While analyzing spatially correlated time series, correlations between observations at proximal times and locations must be appropriately considered. In this study, we propose a location‐dependent DPM model by extending the traditional DPM model for clustering spatially correlated time series. We model the temporal pattern as an infinite mixture of Gaussian processes while considering spatial dependency using a location‐dependent Dirichlet process prior over mixture components. This encourages the assignment of observations from proximal locations to the same cluster. By contrast, because mixture atoms for modeling temporal patterns are shared across space, observations with similar temporal patterns can be still grouped together even if they are located far apart. The proposed model also allows the number of clusters to be automatically determined in the clustering procedure. We validate the proposed model using simulated examples. Moreover, in a real case study, we cluster adjacent roads based on their traffic speed patterns that have changed as a result of a traffic accident occurred in Seoul, South Korea. [ABSTRACT FROM AUTHOR]

This paper presents the background, setup, and results of a stated choice experiment investigating the influence of three different intersection based innovations on cyclists' route choice decisions. Next to commonly used route attributes, the following three intersection based innovations were investigated: 'Flo', a bicycle speed advice tool; 'Schwung', a bicycle - traffic light communication tool; and 'BikeScout', an intersection flashing system. The generated stated choice experiment was included in an online questionnaire that was filled out by 608 respondents who evaluated in total 3648 choice tasks. The evaluations were analyzed using a Multinomial Mixed Logit model. The model estimation results show that the commonly used route attributes (travel time, type of bicycle path facility, pavement quality level, motorized traffic speed, bicycle crowdedness, and number of traffic light intersections) have the highest influence on cyclists' route choice decisions. The impact of intersection based innovations on cyclists' route choice decisions is limited. • Most of the respondents indicated that they are not familiar with the included innovations (BikeScout and Flo/Schwung). • Most respondents indicated that they understand the meaning/working of the presented innovations after looking at movie. • Commonly used route attributes have the highest influence on cyclists' route choice decisions. • Impact of intersection related innovations on cyclists' route choice decisions is limited. [ABSTRACT FROM AUTHOR]

• The number and mean duration of glances away from the non-driving related tasks (NDRTs) increased significantly when the standard deviation (SD) of speed was high. • The mean speed had a significant effect on the mean glance duration, with longer glances away from NDRTs when mean speed was low, compared to that in high speed. • There was a significant effect of age on NDRT engagement, with older drivers less likely to engage in NDRTs, while female drivers were more engaged in NDRTs than males. Previous simulator and real-world studies with SAE Level 2 automated vehicles (AVs) have shown that, when compared to manual driving, drivers are more inattentive to the driving environment when automation is engaged, as reflected by fewer glances towards the forward roadway and side/rear view mirrors, and more focus on non-driving related tasks (NDRTs). Manual driving studies also suggest that drivers are more likely to engage in NDRTs during slow-moving or stationary traffic conditions. The aim of the current study was to understand whether NDRT engagement and visual attention patterns are impacted by the driving environment while drivers experienced a ride in a real-world SAE Level 3 AV. Forty-six video clips, from 32 drivers interacting with NDRTs during L3 motorway driving were analysed for this study. Due to the absence of externally facing cameras, the mean and standard deviation (SD) of driving speed were used as a proxy for assessing the surrounding traffic volume. The number of glances, and mean glance duration away from NDRTs per minute, were used as proxy measures for NDRT engagement. A generalised linear mixed model (GLMM) was used to investigate the effect of surrounding traffic on NDRT engagement. Results showed that the number and mean duration of glances away from the NDRT increased significantly when the SD of speed was high. The mean speed had a significant effect on the mean glance duration, with longer glances away from NDRTs when mean speed was low, compared to that in high speed. There was a significant effect of age on NDRT engagement, with older drivers less likely to engage in another task, while female drivers were more engaged in NDRTs than males. Overall, the results indicate that drivers' propensity to engage in NDRTs is impacted by the AV's speed, which is influenced by the volume of surrounding traffic. These results are useful for understanding the implications of surrounding traffic on drivers' self-regulated engagement in NDRTs in the real world during SAE Level 3 driving. [ABSTRACT FROM AUTHOR]

The COVID-19 pandemic had a significant impact on mobility worldwide, specifically through stay-at-home orders. There is a general consensus in the literature regarding the reduction of traffic during that period, and a trend toward increased speeds. However, the literature is still scarce regarding the pandemic's long-term and site-specific effects on traffic volumes and speed behavior. In this context, the present study looks at speed and traffic volume data, using several temporal and spatial filters to isolate the effect of the pandemic from other elements that can influence speeds, such as congestion, construction, weather, and faulty detector data. Data from Wisconsin for the stay-at-home period in 2020 and corresponding time periods in 2019 and 2021 were used. Traffic volume and speed were analyzed using descriptive and inferential (Kolmogorov–Smirnov Test and Mann Whitney U Test) statistics. While the results for traffic showed the expected reduction in 2020 in relation to other years, speeds also showed a reduction in 2020 for eight of the twelve analyzed locations, most of these rural areas. Furthermore, the results show a return of speeds to pre-pandemic levels in 2021, associated with the partial or complete recovery of traffic volumes. • Evaluation of speeds and traffic volumes before, during, and after Covid-19 lockdown in Wisconsin. • Speed and traffic data quality control from several data sources. • Reduction of traffic volumes in 2020 and partial or complete recover in 2021. • Reduction of speeds in 2020 and a return to pre-pandemic levels in 2021. [ABSTRACT FROM AUTHOR]

Inappropriate or unsafe speed is one of the main factors that affects the number of road crashes as well as the severity of the consequences. Research shows that speed is an influential factor in the occurrence of road crashes in more than 30% of road crashes with fatal outcomes and in over 12% of all road crashes. With an increase in speed, the risk of road crashes increases as well as the severity of the consequences. The perception of the vehicle speed in the traffic lane is one of the basic prerequisites for the safe functioning of traffic, that is, for the successful and timely interaction of all road users. Therefore, the challenge of this paper is to examine how the assessment of the speed of a passenger vehicle in different environments affects the prediction of the respondent's participation in road crashes. Bearing the above in mind, an experimental study was carried out, in real traffic conditions (RTC) as well as in a virtual environment using a driving simulator (DS), at different passenger vehicle speeds (30, 50 and 70 km/h), and at different perspectives of observing the oncoming vehicle (observing the vehicle from the front, from the back, from the side and from the driver's seat) by the respondents. The respondents had the task of evaluating the passenger vehicle speed, in all tested conditions and at all tested speeds. Standard statistical models and fuzzy logic were used to analyze the obtained results. The results show statistically significant differences for all tested situations and all tested speeds as well as statistically significant differences depending on the gender of the respondents, the driver's license category, the driver's experience, frequency of driving and depending on whether respondents wear glasses. Bearing in mind the results of the developed model, by applying fuzzy logic, it can be concluded that the proposed model can be used to assess the propensity of respondents to participate in road crashes, based on perception of vehicle speeds in two tested environments. [ABSTRACT FROM AUTHOR]

The degradation of bus system attractiveness is primarily caused by low‐level service quality and reliability. As an essential technology for bus operation management, online bus speed control has proven to be a flexible and effective solution to mitigate bus bunching and enhance the service level of bus operation systems. In this study, we propose a robust nonlinear decision mapping (RNDM) approach that uses real‐time key bus system states to control bus speeds and accounts for uncertainties associated with passenger demands at stations and traffic speeds of interstation links. We develop this approach through a design process that involves learning the input–output mapping relation of a nonlinear programming simulation‐based optimization (NLPSO) method using regression tree with AdaBoost. Critical parameters of the fitted regression tree with AdaBoost are then optimized offline using a distributionally robust simulation‐based optimization (DRSO) model that is solved by a simulation‐based optimization (SO) algorithm. The resulting RNDM method effectively handles two types of uncertainties, expressed by two ambiguity sets of probability distributions, and ensures good bus operation performance even under worst‐case uncertainty levels. Numerical experiments reveal that the RNDM, NLPSO, and integer programming SO (IPSO) methods successfully mitigate bus bunching and improve service efficiency and robustness, compared to the no‐control scenario. Furthermore, the RNDM method outperforms NLPSO and IPSO in terms of comprehensive performance under uncertainties and demonstrates practical operability. In conclusion, this study presents an innovative general framework that uses a nonlinear decision mapping optimized offline by an SO approach to address online simulation‐based optimal decision‐making problems under uncertainties, which can be applied to solve similar problems. [ABSTRACT FROM AUTHOR]

• A methodology to set credible speed limits is provided. • The methodology considers the roadway design characteristics and the drivers' operating speeds. • Speed prediction models and driving simulator experiments have been integrated and compared. • The methodology has been tested on the A16 Naples–Canosa motorway, section Baiano–Candela, in southern Italy. • The proposed safety countermeasures have a benefit/cost ratio of 4.66. Speed management is an integral part of the Safe System approach and tackling unsafe speeds is the first action to fix a transport system that fails to protect people. There is a consensus that where traffic speeds are a safety issue, lowering the speed limit is considered "reasonable and safe" for conditions. Nevertheless, not only should a speed limit be reasonable and safe, but it should also be credible. Otherwise, that posted speed limit is likely to be ignored. In many instances, speed limits are not credible and highway agencies still need guidance on appropriate procedures to set credible speed limits. The main objective of this study is to propose and test a novel methodology to set credible speed limits, based on the integration of the results achieved by numerical analyses and driving simulator experiments. The proposed methodology is innovative since it takes into consideration both the design characteristics of the road infrastructure according to a specific procedure as well as the drivers' operating speeds, which are evaluated using the results of both speed prediction models and driving simulator experiments. The methodology was tested to set new speed limits on the A16 Naples–Canosa motorway, section Baiano–Candela, in southern Italy, where a posted speed limit of 80 km/h is installed in both travel directions and a new speed limit of 100 km/h is proposed, based on the results of the experiments developed within the methodology. Since the speed limit selection is associated with the expected crash frequency, the final selection of the speed limit should take into account also a safety impact assessment, considering both the expected change in the speed distribution as well as the effects of the safety countermeasures implemented in association to the speed limit change. In this study, the proposed safety countermeasures are the activation of four sections with point-to-point speed control and targeted measures at 45 curves, consisting of (1) high friction surface treatments, (2) correction of superelevation deficiencies, (3) installation of curve warning signs, chevrons, and sequential flashing beacons, and (4) shoulder rumble strips. The safety impact assessment shows that the increase in the speed limit combined with the implementation of the proposed safety countermeasures allows a crash reduction of 23%. The estimated benefit/cost ratio of the safety countermeasures is 4.66. [ABSTRACT FROM AUTHOR]

Real-time prediction of crash risk can support traffic incident management by generating critical information for practitioners to allocate resources for responding to anticipated traffic crashes proactively. Unlike previous studies using archived traffic data covering a limited highway environment such as a segment or corridor, this study uses a statewide live traffic database from HERE to develop real-time traffic crash prediction models. This database provides crowdsourced probe vehicle data that are high-resolution real-time traffic speed for the entire freeway network (nearly 2,000 miles) in Alabama. This study aims to use machine learning models to predict crash risk on freeways according to pre-crash traffic dynamics (e.g., mean speed, speed reduction) along with static freeway attributes. Traffic speed characteristics were extracted from the HERE database for both pre-crash and crash-free traffic conditions. Random Forest (RF), Support Vector Machine (SVM) and Extreme Gradient Boosting (XGBoost) were developed and compared. Separate models were estimated for three major crash types: single-vehicle, rear-end, and sideswipe crashes. The model prediction accuracy indicated that the RF models outperform other models. Models for rear-end crashes are found to have greater accuracy than other models, which implies that rear-end crashes have a significant relationship with pre-crash traffic dynamics and are more predictable. The traffic speed factors that are ranked high in terms of feature importance are the speed variance and speed reduction prior to crashes. According to partial dependence plots, the rear-end crash risk is positively related to the speed variance and speed reductions. More results are discussed in the paper. [ABSTRACT FROM AUTHOR]

Permanent deformation is the primary failure mode for the asphalt concrete (AC) pavement in urban environment. It is mainly caused by a combination of heavy traffic load, low vehicle speed and channelised traffic. A rut prediction model would therefore be a valuable tool for planning maintenance scheduling and selecting an appropriate asphalt material. This study uses the PEDRO (Permanent deformation in asphalt concrete layers for roads) model to evaluate the rutting performance of flexible pavements in dedicated bus lanes and intersections in urban areas. For this purpose, three road sections along a bus lane in Malmö, Sweden, were selected. To achieve this, AC cores from the road sections were tested using a Shear Box Tester to characterise the asphalt mixtures. Traffic data such as axle load, tyre configuration, speed, and lateral wander distribution of vehicles, and climate data were measured for the selected sections. Field measurements were carried out to assess the structural conditions of the pavements and to measure transverse profiles. This study introduced a procedure for the evaluation and local calibration of the PEDRO rutting model. The results revealed that the prediction of the transverse profiles are generally in good agreement with the rut measurements. [ABSTRACT FROM AUTHOR]

Road agencies are looking for efficient pavement management tools to maintain adequate service levels and preserve the asset value. The traffic speed deflectometer (TSD) allows to continuously assess the structural condition of the pavement while moving at traffic speeds, thus overcoming the typical drawbacks of traditional non-destructive testing equipment. However, managing the huge amount of data deriving from TSD surveys is challenging, and there is no established method to use those data for identifying the remaining service life (RSL) of the pavement network. This study aimed at developing a new practical and reliable methodology to assess the RSL of motorway pavements at the network level from TSD measurements. The methodology is based on the use of the surface curvature index SCI300 and includes the temperature adjustment, the definition of a representative SCI300 value for each pavement section and the estimation of the residual fatigue resistance (considering bottom-up cracking as the critical distress). The methodology was implemented using the deflection data deriving from a TSD survey carried out on about 400 km of motorway pavement. The obtained RSL predictions can be used to identify the structural ranking of different pavement sections and guide budget forecasting, according to the actual maintenance and rehabilitation priorities. [ABSTRACT FROM AUTHOR]

The response of asphalt material depends on the rate of loading and varies from elastic to plastic. Therefore, the behaviour of flexible pavement would also be different along the entire length of a road because of truck speed changes due to the existence of police checkpoints, bus stations, speed bumps, intersections, horizontal and vertical curves, and climbing lanes. The objective of this study is to investigate the effect of truck speed on the performance of flexible pavement. Thus, analyses were conducted for various truck speeds (1–75 km/hr) on three different pavement structures and three traffic levels using AASHTOWare Pavement ME Design 2.5.5 for the local conditions of Izmir, Turkey. The analysis results of the study manifested that a reduction in traffic speed (75–1 km/hr) on a road resulted in higher pavement distress. According to the results, reducing truck speed from 25 to 1 km/hr resulted in a rapid increase in AC rutting, alligator cracking and top-down cracking by 13.3 mm, 10.6% and 1473.8 m/km, respectively. It is expected that the outcomes of this study would promote the local calibration of the mechanistic-empirical pavement design guide (MEPDG) and pavement design in Turkey and the region. [ABSTRACT FROM AUTHOR]

Wet pavement surface on rainy days poses a challenge for traffic safety as it greatly impacts the safe driving speed and increases the hydroplaning risk. This study proposed a new approach to analyse and mitigate hydroplaning risk on roadways based on spatial-temporal water conditions and hydroplaning speeds. A theoretical analysis was conducted to predict the spatial-temporal water film depth under dynamic rainfall profile, considering the effects of roadway slope and pavement surface texture. The tire-water-pavement interaction model was then used to predict hydroplaning speeds of vehicles driving on different traffic lanes. According to the hydroplaning and traffic flow speeds, the spatial and temporal pattern of roadway hydroplaning risk was analysed. Considering traffic flow speeds, rainfall intensity, roadway geometry, and surface condition, the probability of hydroplaning occurrence at different times of rainfall and separate traffic lanes can be estimated using the proposed approach. Finally, the variable speed limits (VSL) approach was proposed to mitigate hydroplaning risk, which can be determined based on the hydroplaning threshold probability and the design speed limit of the roadway section. [ABSTRACT FROM AUTHOR]

Accurate estimation of traffic emissions and analysis of spatio-temporal distribution on urban roads play a crucial role in the development of low-carbon transportation system. Traditionally, a region's emission characteristics have been studied using numerous emission models with GPS-based spatio-temporal data. Due to the heavy data processing needs of GPS-based data, emission characteristics for a large region have been studied by dividing the region into a limited number of smaller areas or units. Additionally, GPS data are based on a few vehicles in the traffic which does not fully reflect road conditions. This paper proposed an approach that can be used to study and calculate the spatio-temporal emission pattern of a region at a roadway section level by using Baidu's online traffic data and COPERT model. The proposed method can be used to estimate road-level emission patterns while avoiding the impact of redundant data in large datasets, making the dataset more reliable, applicable, and scalable. The proposed approach has been demonstrated through a study of spatio-temporal emission patterns in the Qiaoxi district within city of Shijiazhuang, China. Online data crawling technology was used to obtain data on urban road traffic speed and driving distance. The linear reference technology was used to construct a two-layer road network model to conduct the coupling and matching of traffic data with the road network data. The COPERT model was implemented to calculate the average traffic emissions on each road in the road network, and a traffic emission intensity index was proposed to quantify the CO, VOC, NOx and CO2 emissions on urban roads in the study area. The analysis results show that the traffic emission intensity of the expressway, trunk road, secondary road, and branch road is high during the morning peak (7 AM-9 AM) and evening peak (5 PM—7 PM). The sections with higher traffic emission intensity are mainly concentrated on the main roads and secondary roads such as Jiefang South Street, Shitong Road and Xinhua Road. Nearly one-third of 2nd Ring and 3rd Ring roads also have relatively high emission intensity. The research results provide new ideas for estimating traffic emissions in urban road networks and analyzing the spatio-temporal distribution of traffic emissions. The research results can also provide a decision-making basis for traffic management departments to formulate energy-saving and emission-reduction measures and promote the development of urban green and low-carbon transportation. [ABSTRACT FROM AUTHOR]

Low and medium speed magnetic levitation traffic with short power supply distance and complex grounding network structure, prone to power supply rail grounding faults. However, the existing fault location methods do not accurately locate the fault point, making it difficult for the protective device to act to cut off the fault. To address the above problems, this paper builds a dynamic simulation model of the low and medium speed magnetic levitation power supply rails to study the distribution characteristics of the fault traveling waves after a ground fault occurs in the power supply rails, and analyses the generation mechanism of the traveling wave spectrum through formula calculation. First, the difference in current between the positive and negative bus bars is analyzed to determine whether a ground fault has occurred. Second, the direction of the current difference between stations is compared to locate the faulty section. Finally, the fault distance is calculated from the frequency difference of the fault voltage at the double‐ended station. Through simulation, the method is validated to be unaffected by fault location, fault transition resistance, noise interference, and is applicable to short circuit faults caused by lightning strikes, and the ranging error always remains within 20 m. The method has strong robustness, can effectively solve the problem of protection misoperation and accurately locate the fault point. It is suitable for low and medium speed magnetic levitation transportation power supply rail ground fault. [ABSTRACT FROM AUTHOR]

Pavement performance prediction is widely considered as a significant element of road infrastructure asset-management systems or Pavement Management Systems (PMS) by pavement researchers and practitioners. Predicting pavement performance significantly reduces the huge costs of constructing roads, especially in the case of countries that made incredible investments in road construction. This study mainly focuses on the implementation of the mechanistic-empirical (M-E) analysis method using the AASHTOWare Pavement ME Design (AASHTOWare PMED) software for flexible pavement distress prediction-models generation. To achieve that four steps were followed. First, the most accurate assessment that shows the combined impact of the most important parameters that affect flexible pavement performance was used to perform the AASHTOWare runs. In which, 378 design combinations of (3 traffic speed levels × 3 traffic load levels ×3 climatic zones ×7 Surface HMA mixes widely used in Egypt) at two input levels of the AASHTOWare PMED hierarchy (levels 1 &2) that typically are required for binders and hot-mix-asphalt (HMA) were used. Second, a sensitivity analysis to study the combined effect and impact of the investigated parameters on AASHTOWare PMED-predicted performance (cracking, rutting, and roughness) was conducted at the two input levels. Third, a Multiple Linear Regression (MLR) was implemented as a modeling approach to develop five performance prediction models for flexible pavements based on the AASHTOWare PMED software results. The proposed MLR models predicted each distress as a function of climatic factors, the surface HMA properties, different regions' speed levels, and traffic volume levels. Finally, a validation process of the proposed MLR prediction models was conducted. Results indicated that the proposed models yield an overall good prediction, asserting the robustness of the proposed process. Proposed MLR prediction models can be perceived as a function of Average Annual Daily Truck Traffic, Traffic speed, mean annual air temperature, and the percentage of air voids. This study provides a procedure to develop the performance prediction models of flexible pavements based on the AASHTOWare PMED approach and in accordance with different regions’ input levels. [ABSTRACT FROM AUTHOR]

The exponential growth of vehicles has led to increased traffic congestion and pollutants emission in cities. Intelligent transportation systems (ITS) shall be built by integrating Artificial Intelligence(AI). Planning optimal route with minimum travel time is a great challenge for the traffic management system. A hybrid model integrating long-short-term memory(LSTM) deep-learning model and Dijkstra's algorithm for recommending the fastest route is proposed in this work. The proposed hybrid approach reduces the travel time to a greater extent. Vehicle speed greatly influences eco-driving factors such as fuel consumption and exhaust emission. Thus, for each road links, the fuel consumption and emission of pollutants such as carbon monoxide(CO), nitrogen oxides(NOx), and hydrocarbon(HC) are estimated for different type of vehicles. The results showed the proposed approach decreases fuel consumption, CO emission, NOx emission, and HC emission up to 54.5%, 61.5%, 64.2%, and 81.9%, respectively, compared to the traditional shortest path. [ABSTRACT FROM AUTHOR]

Fine-grained urban traffic data are often incomplete owing to limitations in sensor technology and economic cost. However, data-driven traffic analysis methods in intelligent transportation systems (ITSs) heavily rely on the quality of input data. Thus, accurately estimating missing traffic observations is an essential data engineering task in ITSs. The complexity of underlying node-wise correlation structures and various missing scenarios presents a significant challenge in achieving high-precision estimation. This study proposes a novel multiview neural network termed MVCV-Traffic, equipped with a cross-view learning mechanism, to improve traffic estimation. The contributions of this model can be summarized into two parts: multiview learning and cross-view fusing. For multiview learning, several specialized neural networks are adopted to fit diverse correlation structures from different views. For cross-view fusing, a new information fusion strategy merges multiview messages at both feature and output levels to enhance the learning of joint correlations. Experiments on two real-world datasets demonstrate that the proposed model significantly outperforms existing traffic speed estimation methods for different types and rates of missing data. [ABSTRACT FROM AUTHOR]

Traffic speed is an essential indicator for measuring traffic conditions. Real-time and accurate traffic speed prediction is an essential part of building intelligent transportation systems (ITS). Currently, speed prediction methods are characterized by insufficient short-term prediction accuracy and stability, nonlinear, nonstationary, strong fluctuation and relatively small sample size. To better explore the traffic characteristics of the road networks, a hybrid prediction model based on wavelet transform (WT) of the autoregressive moving average model (ARIMA) and gate recurrent unit (GRU) was constructed. First, this model decomposes the original traffic speed data into low-frequency data, and high-frequency data by WT. Second, the ARIMA and GRU models are used to model data predictions in two frequency bands, respectively. Finally, the prediction result of the predicted value is fused. In addition, in this paper, traffic speed data of four sections in Guangzhou from 1 August to 31 September 2016 are taken as examples to test the validity, applicability, and practicability of the model. The results show that compared with ARIMA, LSTM, GRU, RNN, and other single models and hybrid models, the prediction method proposed in this paper has higher prediction accuracy and can provide a more scientific decision-making basis for urban traffic management. [ABSTRACT FROM AUTHOR]

In Asian megacities undergoing rapid urbanization such as Bangkok, heavy rainfall exacerbates traffic congestion owing to inadequate drainage systems. This study statistically analyzed the extent to which rainfall affects urban traffic speed and how this impact varies depending on regional environmental factors and traffic demand trends, utilizing probe vehicles and rainfall data from 2018 to 2020 in Bangkok. The results clearly indicate that both the intensity of rainfall during driving and previous cumulative rainfall significantly reduce traffic speed. This impact is particularly pronounced during morning and evening rush hours, and in areas with a high proportion of narrow roads or in low-lying areas. On the other hand, areas with rich urban green space, which naturally absorb and retain water, tend to mitigate the speed reduction due to rainfall. This study highlights the fact that the impact of rainfall on traffic varies with time and location, suggesting that the exacerbation of rain-induced congestion can be more effectively mitigated by coordinated improvements in drainage facilities, traffic management and land use. [ABSTRACT FROM AUTHOR]

This article delineates the characterization of traffic-induced turbulent kinetic energy (TKE) in areas proximate to roadways using real-world traffic conditions. Traffic-induced TKE serves as a pivotal tool to refine the parameters of eddy diffusivity within air dispersion modeling, thereby facilitating a more accurate representation of near-road model-estimated traffic emission with TKE-related traffic conditions. Six hundred observations facilitated the detailed TKE characterization, which incorporated a comprehensive assessment of wind speed and traffic conditions, including parameters such as vehicle flow rate, speed, and classifications into categories such as heavy-duty vehicles (HDVs) and light-duty vehicles (LDVs). Five-minute measurement intervals were utilized to pinpoint the substantial variations in TKE generated through traffic flow, particularly highlighting the more chaotic yet swiftly dissipating energy contributions from HDVs. Monitoring was conducted on two urban freeways characterized by markedly different traffic compositions (quantified with HDV%) and distinct road configurations. The TKE derived from traffic over five-minute intervals is correlated with concurrently measured variables such as vehicle flow, speed, and traffic types. The ensemble mean method was utilized to delineate the characteristics of traffic-induced TKE during both steady- and unsteady-state traffic flows, with a focus on traffic density as a key parameter. The results reveal different trends in the behavior of traffic induced TKE. The substantial impact of HDV-induced TKE was quantified using a comparative analysis of normalized traffic-induced TKEs between HDVs and LDVs. This analysis demonstrates that the influence exerted by a single HDV is approximately eleven times that of a single LDV in close proximity to road locations. Within the traffic fleet, HDVs constitute only a minor fraction, typically amounting to 1 to 10% of the total vehicle flow rate. However, their considerable impact and positive correlation with traffic induced TKE was evaluated using a detailed analysis of LDV flow subdivisions. [ABSTRACT FROM AUTHOR]

Traffic fatalities from 2015 to 2019 in Uttar Pradesh (UP), India show that pedestrians and cyclists have the largest share of total road fatalities. This study analyzed the pedestrian's perceptions of risk in the medium-sized city-Bulandshahr-UP, India regarding the traffic and road features. Perception of risk provides important information in identifying potential risks and explaining travel choices by pedestrians. The study locations were selected based on identified blackspots i.e. clustering of actual fatal crashes during 2015–2019 in UP. The types of locations at the blackspots were intersections below flyover, four-way signalized intersections, midblocks and foot of flyovers. An empirical analysis is presented in the study by taking pedestrians' ranking of the selected risk factors like traffic speed, free left turn at intersections, unmarked crosswalks, median width, traffic volume and the number of lanes and using the Rank-ordered logit model. Traffic speed and median width were ranked as the two highest risk factors by pedestrians. The results also indicated that increased numbers of lanes are more likely to be perceived riskier by older age groups of pedestrians and females at intersections below flyovers and midblocks. A comparison of different locations shows that all the factors were significant at four-way signalized intersections, indicating more perceived risk by pedestrians at intersections. These significant results can be used by practitioners to design safer intersections and midblocks at selected locations for pedestrians in UP, India. [ABSTRACT FROM AUTHOR]

Various studies have investigated the relationship between speed and accidents using different definitions of speed variation. This research considers the speed in mixed traffic as heterogeneous based on the vehicle categories. This research aims to develop a traffic safety model with speed heterogeneity as expressed in accident modification factor (AMF) index. The data types include traffic data, road volumes and geometrics from 18 roads in 8 provinces in Indonesia: Central Sulawesi, Southeast Sulawesi, South Sulawesi, West Kalimantan, Central Kalimantan, NTB, NTT and Bali. The power model is adopted to model the relationship between speed changes and the number of accidents and victims. Change in paratransit speed is significant in predicting all types of AMFs, but the effects are lower than those of the other categories. Truck speed change has the highest impact of fatalities. A 10% decrease in truck speed results in a 29.9% decrease in the number of fatalities, whilst the same 10% decrease in paratransit decreases 17.4% of fatalities. The study resulted in AMF models based on the vehicle speed heterogeneity that could be used in road safety evaluation by looking at the effects of vehicle speed changes in specific categories. [ABSTRACT FROM AUTHOR]

Accurate traffic speed forecasting is a prerequisite for anticipating future traffic status and increasing the resilience of intelligent transportation systems. However, most studies ignore the involvement of context information ubiquitously distributed over the urban environment to boost speed prediction. The diversity and complexity of context information also hinder incorporating it into traffic forecasting. Therefore, this study proposes a multimodal context-based graph convolutional neural network (MCGCN) model to fuse context data into traffic speed prediction, including spatial and temporal contexts. The proposed model comprises three modules, ie (a) hierarchical spatial embedding to learn spatial representations by organizing spatial contexts from different dimensions, (b) multivariate temporal modeling to learn temporal representations by capturing dependencies of multivariate temporal contexts and (c) attention-based multimodal fusion to integrate traffic speed with the spatial and temporal context representations for multi-step speed prediction. We conduct extensive experiments in Singapore. Compared to the baseline model (spatial-temporal graph convolutional network, STGCN), our results demonstrate the importance of multimodal contexts with the mean-absolute-error improvement of 0.29 km/h, 0.45 km/h and 0.89 km/h in 30-min, 60-min and 120-min speed prediction, respectively. We also explore how different contexts affect traffic speed forecasting, providing references for stakeholders to understand the relationship between context information and transportation systems. [ABSTRACT FROM AUTHOR]

In recent years, it has been shown that deep learning methods have excellent performance in establishing spatio-temporal correlations for traffic speed prediction. However, due to the complexity of deep learning models, most of them use only short-term historical data in the time dimension, which limits their effectiveness in handling long-term information. We propose a new model, the Multi-feature Two-stage Attention Convolution Network (MTA-CN), to address this issue. The MTA-CN intercepts longer single-feature historical data, converts them into shorter multi-feature data with multiple time period features, and uses the most recent past point as the main feature. Furthermore, two-stage attention mechanisms are introduced to capture the importance of different time period features and time steps, and a Temporal Graph Convolutional Network (T-GCN) is used instead of traditional recurrent neural networks. Experimental results on both the Los Angeles Expressway (Los-loop) and Shen-zhen Luohu District Taxi (Sz-taxi) datasets demonstrate that the proposed model outperforms several baseline models in terms of prediction accuracy. [ABSTRACT FROM AUTHOR]

Axle load limits for single axles, 89 kN (≈20 kips), and tandem axles, 151 kN (≈34 kips), are set to control potential pavement damage. These axles, at their corresponding weight limits, are considered equivalent. Because pavement layers are more complicated than a linear elastic material, using linear elastic theory would result in erroneous loading response prediction and, hence, potential pavement damage. Thus, actual tandem- and single-axle loading, along with flexible pavement structure, were modeled using an advanced finite-element model. The influences of a 1.2-m-spaced tandem axle and a single axle on flexible pavement responses were assessed qualitatively. Transfer functions from AASHTOWare were used to compute pavement distresses. Tandem and single axles were found to be inequivalent, confirming that the distresses due to the tandem axle were greater than those of the single. Load equivalency was calculated for different parameters, such as tire type, pavement material, and structure. The load equivalency was found to be dependent on various parameters. Wide-base tires (tire type) had the highest influence on the weight limits [135 kN (≈30 kips)]. Because 72% of national goods are moved on highways, accurate weight limits should be applied using an established equivalency factor. [ABSTRACT FROM AUTHOR]

Vibration energy harvesters (VEHs) can utilize the vibration of the track to generate electricity and provide power for other devices within the harvester. To analyze whether energy harvesters arranged in an array harm track operation, we conducted a simulation analysis. Based on the vehicle–track coupling model, the influence of inductive electromotive force on track vibration was analyzed and compared with the simulation results obtained from the classical vehicle–track coupling model. The rail vibration displacement was reduced from 0.5 to 0.0692 mm, and the maximum vibration acceleration of the rail was reduced from 2.3759 to 0.4534 m/s2. The energy harvester can attenuate the vibration of the track significantly, and has a minor influence on the regular operation of the track. The vibration of a railway can be transformed to electric energy and used to power sensors at the railway side and train sides, such as velocity sensors, temperature sensors, accelerometers, wireless transmission modules, and other wireless sensor network (WSN) devices. It also can be used as backup power for the auxiliary load on the railway side, such as traffic lights and speed measuring radar. A vibration energy harvester installed at the fastener has a simple structure and can provide enough power for WSN sensors. It provides a good energy supply for line-side monitors and auxiliary devices. Because safety is the most critical issue for track devices, the effect of the installation of VEHs on the operation of the track should be analyzed. The vibration of a track with a fastener VEH is less than that without a VEH, which will reduce the impact of vibration on the environment and ensure the safe running of trains. This method also applies to the safety analysis of other track energy harvesting devices. [ABSTRACT FROM AUTHOR]

Predicting future traffic state (e.g., traffic speed, volume, travel time, etc.) accurately is highly desirable for traffic management and control. However, network-wide traffic flow has complicated spatial-temporal dependencies, making it challenging to predict. This study proposes a multi-weighted graph 3D convolution network (MWG3D) to predict future network-wide traffic speed, considering the spatial-temporal heterogeneous effects of multiple external factors (i.e., points of interests (POIs), roadway physical characteristics and incidents). The network is composed of a Graph-3D convolution (G3D) module and an incident impact module. In G3D module, a weighted graph convolution is developed first, which extracts complex spatial dependencies of traffic flow considering heterogeneous effects of POIs and roadway physical characteristics. These external factors have great influence on the periodicity of human daily activities, which in turn cyclically affect traffic flow. The weighted graph convolution is further connected with 3D convolutions to extract temporal dependencies of traffic flow, accounting for temporal heterogeneous effects of these external factors. An incident impact module is separately developed to account for spatial-temporal heterogeneous effects of incidents. These external factors could lead to abrupt and temporary changes in traffic flow. The proposed network is evaluated on two real-world datasets. The results show that MWG3D outperforms a selection of the state-of-the-art models. Furthermore, the spatial-temporal heterogeneous effects of external factors are crucial to prediction accuracy. [ABSTRACT FROM AUTHOR]

The new generation smart highways (NGSH) have emerged as irresistible trends to enhance the efficiency and safety of transportation systems. An integral component of the NGSH is the automation of the intelligent traffic management system (ITMS). This study investigates an integrated framework for the ITMS that incorporates the fine-grained microscopic simulation and deep learning technologies based on real-time traffic data. The framework commences by performing dynamic corrections based on the license plate, vehicle speed, location, and other information provided by the real-time bayonet data in order to simulate the realistic traffic flow along the highway. A deep learning model based on long short-term memory (LSTM) is then applied to predict the short-term traffic volume on major highway segments. Based on prediction results, a collaborative management method is constructed that combines variable speed limits and ramp metering. The case study on the Shanghai–Hangzhou–Ningbo Highway in China suggests the real-time simulation model can control the average error of the traffic volume on the main segments by 4.58%. The LSTM-based model can accurately predict the short-term traffic volume with a relative error of 85% below 15% in both offline and online modes. Consequently, the proposed collaborative framework improves the average speed and traffic volume of controlled sections by 3.62% and 4.35%, respectively, demonstrating its effectiveness in improving the operation and management of the smart highways. DOI: 10.1061/JTEPBS.TEENG-7729. © 2023 American Society of Civil Engineers. [ABSTRACT FROM AUTHOR]

The traffic speed deflectometer (TSD) can collect network-level deflection data in a cost-effective and timely manner. However, an automated feature extraction method is needed to interpret such large amounts of data. Basis pursuit (BP) is one such technique: BP can sparsely decompose TSD measurements over a given basis or set of bases of the signal vector space that can represent a particular signal feature. For instance, the TSD surface deflection estimates can be reconstructed as a combination of wavelets, which represent continuously varying features like changes in pavement properties, plus pulses representing the response from structurally weak spots. Yet, the denoised measurements estimated by BP may either be riddled with several false positives (spikes that mismatch real weak spots) or be constructed out of true positive features with damped amplitude. This paper presents reweighed L1 minimization (RWL1), an enhancement to BP to both correct the dampening and discard false positives. This paper introduces RWL1 with examples from simulated data to show its advantage over vanilla BP denoising, plus a demonstration featuring real TSD measurements from a networkwide survey to demonstrate RWL1's potential as an exploratory analysis tool to detect structurally weak locations within the pavement network worthy of further investigation at the project level. [ABSTRACT FROM AUTHOR]