Search

Traffic speed deflection devices (TSDDs) have been developed since around 2000 to allow for safe and efficient structural evaluation of highway networks. One barrier to TSDD implementation is the inherent differences in deflections produced by moving truck loads and by falling weight deflectometer (FWD), the current deflection testing standard. To better understand the differences in data produced by the two devices, FHWA sponsored research into one particular TSDD, the rolling wheel deflectometer (RWD). The study utilized the finite layer program ViscoWave to model both FWD and RWD loads to demonstrate the effect of their inherent differences on pavement deflections and other simulated parameters. In addition, ViscoWave was used to generate theoretical FWD and RWD deflections for a diverse set of pavement structures and subgrade conditions. The resulting deflections were used to develop correlations between the two devices, which were validated with side-by-side FWD and RWD field tests performed on 23 sites. The research determined that the differences between FWD and RWD deflections vary depending on pavement factors and loading characteristics. The two devices produced similar deflections on thicker, stiffer, lower-deflection pavements, while the FWD produced relatively higher deflections on thinner, weaker, higher-deflection pavements. Therefore, use of common FWD data analysis programs will produce different results, such as layer moduli, for TSDD devices. Advanced analysis routines capable of modeling the TSDD’s moving load and loading configurations are needed.

The traditional practice for pavement structural capacity evaluation is mostly dependent on the falling weight deflectometer (FWD) measurements. However, this practice has several challenges due to...

The Internet of Things (IoT) enables us to collect traffic data from multiple sources, which makes it possible to predict traffic speed in time with big traffic data. This article presents a novel spatio-temporal deep learning framework that aims to provide accurate and timely traffic speed forecasting. To extract the spatial and temporal features of traffic data simultaneously, this framework combines two different deep learning models, namely convolutional long short-term memory (ConvLSTM) and the graph convolutional network (GCN). Specifically, the ConvLSTM model is used to learn the temporal dynamics of traffic data to extract temporal features. On the other hand, the GCN model is used to learn the spatial complexity of traffic data to extract spatial features. Experiments show that the prediction performance of our framework at different time horizons outperforms three baseline approaches.

Accurate and timely traffic forecasting is significant for intelligent transportation management. However, existing approaches model the temporal and spatial features of traffic flow inadequately. To address these limitations, a novel deep learning traffic forecasting framework based on graph attention network (GAT) and temporal convolutional network (TCN) is presented in this paper, termed as graph attention temporal convolutional networks (GATCN). More specifically, GATCN deal with the spatial features by GAT, and the temporal features by TCN. The layer fused by GAT and TCN enables the proposed model to learn the spatio-temporal characteristics that lie in traffic flow, while considering exogenous factors. In addition, nodes in the graph can capture the information of their neighborhoods by stacking multiple layers. Precision and robustness of the proposed method have been evaluated through testing on the real-world dataset. Results show that the proposed model outperforms other baselines.

Traffic speed forecasting plays an increasingly essential role in successful intelligent transportation systems. However, this still remains a challenging task when the accuracy requirement is dema...

The introduction of deep learning (DL) models and data analysis may significantly elevate the performance of traffic speed prediction. Adverse weather causes mobility and safety concerns because of varying traffic speeds with poor visibility and road conditions. Most previous modeling approaches have not considered the heterogeneity of temporal and spatial data, such as traffic and weather conditions. This paper presents a framework, consisting of two DL models, to predict traffic speed under normal conditions and during adverse weather, considering prevailing traffic speed, wind speed, traffic volume, road capacity, wind bearing, precipitation intensity, and visibility. To ensure the accuracy of speed prediction, different DL models were assessed. The results indicated that the proposed one-dimensional convolutional neural network model outperformed others in relation to the least root mean square error and the least mean absolute error. Considering real-time weather data feeds on a 15-min basis, a tool was also developed for displaying predicted traffic speeds on New Jersey freeways. Application of the proposed framework models for predicting spatio-temporal hot-spot congestion caused by adverse weather is discussed.

A non-destructive testing method suitable for network-level pavement structural evaluation is the traffic speed deflectometer (TSD) test. However, the analysis of TSD measurements still needs a proper parameter back-calculation procedure, which requires an accurate and efficient forward calculation model. As a first step to solving this issue, a nonlinear spectral element model which can simulate TSD tests of asphalt pavements is developed. The model is used to investigate the characteristics and parameter sensitivity of the response of asphalt pavements caused by the TSD loading. The results indicate that the vertical deflection curve along the direction of movement observed on the asphalt pavement surface is slightly asymmetric, and the maximum deflection appears behind the centre of the loading area. In addition, the slope curve of vertical deflection is highly sensitive to the magnitude of the applied force, the moduli of the base layer and subgrade, and the thicknesses of the asphalt layer and base layer. Furthermore, the slope curve is relatively sensitive to the glassy modulus of the asphalt layer. Because of its good predictive capability and high computational efficiency, the proposed model has the desired characteristics to be used as the computational kernel for parameter back-calculation procedures of TSD measurements.

This paper presents a Neural Convolutional Network (NCN) based approach for learning traffic as images and predicting high accuracy network-wide broad traffic speed. In the recent past, images describe time and space of traffic flow, where a 2-dimensional time-space matrix is used to convert space dynamics. In recent years, neural networks have been widely used for the prediction of short term traffic, where the description is covered by an NCN in two consecutive steps: abstract data extraction and network-wide traffic forecast. This paper proposes Prediction Architecture of Neural Convolutional Short Long Term Network (PANCSLTN) for the purpose of effectively capturing dynamic nonlinear traffic systems with deep learning assistance. The PANCSLTN can resolve the problem of backdated decay error via memory blocks and shows superior prediction capacity for time series with long-time dependency. Moreover, PANCSLTN can determine the optimum time laggards automatically and the travel data from Beijing microwave traffic detectors which are used for model the training and testing to validate the effective PANCSLTN using remote sensing technique. PANCSLTN can deliver the most accurate and stable prediction performance compared to different topologies in dynamical neural resealing networks or other dominant parametric and nonparametric algorithms during experimental analysis.

The horizontal tensile strain at the top of asphalt concrete (AC) layer is considered as the most appropriate response of pavement for analysing Top-down cracking (TDC). In this study, influence of...

Backcalculation analysis of pavement layer moduli is typically conducted based on falling weight deflectometer (FWD) deflection measurements; however, the stationary nature of the FWD requires lane closure and traffic control. In recent years, traffic speed deflection devices such as the traffic speed deflectometer (TSD), which can continuously measure pavement surface deflections at traffic speed, have been introduced. In this study, a mechanistic-based approach was developed to convert TSD deflection measurements into the equivalent FWD deflections. The proposed approach uses 3D-Move software to calculate the theoretical deflection bowls corresponding to FWD and TSD loading configurations. Since 3D-Move requires the definition of the constitutive behaviors of the pavement layers, cores were extracted from 13 sections in Louisiana and were tested in the laboratory to estimate the dynamic complex modulus of asphalt concrete. The 3D-Move generated deflection bowls were validated with field TSD and FWD data with acceptable accuracy. A parametric study was then conducted using the validated 3D-Move model; the parametric study consisted of simulating pavement designs with varying thicknesses and material properties and their corresponding FWD and TSD surface deflections were calculated. The results obtained from the parametric study were then incorporated into a Windows-based software application, which uses artificial neural network as the regression algorithm to convert TSD deflections to their corresponding FWD deflections. This conversion would allow backcalculation of layer moduli using TSD-measured deflections, as equivalent FWD deflections can be used with readily available tools to backcalculate the layer moduli.

Wireless magnetic sensor networks (WMSNs) provide a low-power, low-cost solution for traffic information acquisition. Systems used for traffic speed estimation based on WMSNs have been well studied only when the geomagnetic field has not interfered. However, the widely developed electric rail transit systems, such as subways, light rails, and high-speed rail systems, produce magnetic field radiation that interferes with the geomagnetic field. So it is imperative to filter out noise in order to increase the detection accuracy. This article proposes a system for traffic speed estimation which can effectively eliminate the geomagnetic background interference. A morphological filter is designed for removing the interference and extracting the magnetic signatures of vehicles. The speed estimation is implemented based on the signatures reidentification. Experimental results verify that the proposed system is more accurate than existing systems.

Traffic speed prediction is a critically important component of intelligent transportation systems. Recently, with the rapid development of deep learning and transportation data science, a growing body of new traffic speed prediction models have been designed that achieved high accuracy and large-scale prediction. However, existing studies have two major limitations. First, they predict aggregated traffic speed rather than lane-level traffic speed; second, most studies ignore the impact of other traffic flow parameters in speed prediction. To address these issues, the authors propose a two-stream multi-channel convolutional neural network (TM-CNN) model for multi-lane traffic speed prediction considering traffic volume impact. In this model, the authors first introduce a new data conversion method that converts raw traffic speed data and volume data into spatial–temporal multi-channel matrices. Then the authors carefully design a two-stream deep neural network to effectively learn the features and correlations between individual lanes, in the spatial–temporal dimensions, and between speed and volume. Accordingly, a new loss function that considers the volume impact in speed prediction is developed. A case study using 1-year data validates the TM-CNN model and demonstrates its superiority. This paper contributes to two research areas: (1) traffic speed prediction, and (2) multi-lane traffic flow study.

Transportation network companies (TNC) provide mobility services that are influencing travel behavior in unknown ways due to limited TNC trip-level data. How they interact with other modes of transportation can have direct societal impacts, prompting appropriate policy intervention. This paper outlines a method to inform such policies through a data-driven approach that specifically analyzes the interaction between TNCs and bus services in Pittsburgh, PA. Uber surge multiplier data is used over a 6-month time period to approximate TNC usage (i.e., demand over supply ratio) for ten predefined points of interest throughout the city. Bus boarding data near each point of interest is used to relate TNC usage. Data from multiple sources (weather, traffic speed data, bus levels of service) are used to control for conditions that influence bus ridership. We find significant changes in bus boardings during periods of unusually high TNC usage at four locations during the evening hours. The remaining six locations observe no significant change in bus boardings. We find that the presence of a dedicated bus way transit station or a nearby university (or dense commercial zones in general) both influence ad-hoc substitutional behavior between TNCs and public transit. We also find that this behavior varies by location and time of day. This finding is significant and important for targeted policies that improve transportation network efficiency.

Accurate traffic forecasting on citywide networks is one of the crucial urban data mining applications that accurately provide congestion warning and transportation scheduling. While previo...

Traffic management in a city has become a major problem due to the increasing number of vehicles on roads. Intelligent Transportation System (ITS) can help the city traffic managers to tackle the problem by providing accurate traffic forecasts. For this, ITS requires a reliable traffic prediction algorithm that can provide accurate traffic prediction at multiple time steps based on past and current traffic data. In recent years, a number of different methods for traffic prediction have been proposed which have proved their effectiveness in terms of accuracy. However, most of these methods have either considered spatial information or temporal information only and overlooked the effect of other. In this paper, to address the above problem a deep learning based approach has been developed using both the spatial and temporal dependencies. To consider spatio-temporal dependencies, nearby road sensors at a particular instant are selected based on the attributes like traffic similarity and distance. Two pre-trained deep auto-encoders were cross-connected using the concept of latent space mapping and the resultant model was trained using the traffic data from the selected nearby sensors as input. The proposed deep learning based approach was trained using the real-world traffic data collected from loop detector sensors installed on different highways of Los Angeles and Bay Area. The traffic data is freely available from the web portal of the California Department of Transportation Performance Measurement System (PeMS). The effectiveness of the proposed approach was verified by comparing it with a number of machine/deep learning approaches. It has been found that the proposed approach provides accurate traffic prediction results even for 60-min ahead prediction with least error than other techniques.

Stroke is a major cause of death in Thailand. It requires a specific time period of 4.5 h from onset to treatment to increase recovery rates, and therefore, it can be categorized as a time-sensitive disease. The objective of this research is to identify whether the service areas of the main existing Emergency Medical Services (EMS) prehospital stroke practices cover all areas in Bangkok. This is determined by using GIS mapping. After verifying the current EMS delivery models, comparisons are drawn to find the travelling time of each model. The conditioning factors for GIS mapping were collected and verified, including the traffic speed and duration spent in each mode of the prehospital stroke process. After inputting all of the data into GIS, the service areas were visualized to show the area serviced in each delivery model. The results also show the different hospital groups, including the service areas for (1) non-network hospitals and (2) hospitals with stroke networks. Suggestions for re-networking and adding more hospitals to the existing networks were also identified using GIS. Regularly updating the service area with up-to-date data in GIS is key to improving stroke service areas.

Dynamic Graph Neural Networks (DGNNs) have become one of the most promising methods for traffic speed forecasting. However, when adapting DGNNs for traffic speed forecasting, existing approaches are usually built on a static adjacency matrix (no matter predefined or self-learned) to learn spatial relationships among different road segments, even if the impact of two road segments can be changeable dynamically during a day. Moreover, the future traffic speed cannot only be related with the current traffic speed, but also be affected by other factors such as traffic volumes. To this end, in this paper, we aim to explore these dynamic and multi-faceted spatio-temporal characteristics inherent in traffic data for further unleashing the power of DGNNs for better traffic speed forecasting. Specifically, we design a dynamic graph construction method to learn the time-specific spatial dependencies of road segments. Then, a dynamic graph convolution module is proposed to aggregate hidden states of neighbor nodes to focal nodes by message passing on the dynamic adjacency matrices. Moreover, a multi-faceted fusion module is provided to incorporate the auxiliary hidden states learned from traffic volumes with the primary hidden states learned from traffic speeds. Finally, experimental results on real-world data demonstrate that our method can not only achieve the state-of-the-art prediction performances, but also obtain the explicit and interpretable dynamic spatial relationships of road segments.

This paper reviews the optimization of traffic flow through C-ITS in relation to public transport. In particular, a new model of traffic signal control based on C-ITS frame was constructed and it focuses on improving the traffic speed and reducing the emission of public transport by avoiding unnecessary stops at signalized intersections. The investigations were carried out in a simulation as well as in the C-ITS test area Kassel.

Location data from mobile devices is a sensitive yet valuable commodity for location-based services and advertising. We investigate the intrinsic value of location data in the context of strong privacy, where location information is only available from end users via purchase. We present an algorithm to compute the expected value of location data from a user, without access to the specific coordinates of the location data point. We use decision-theoretic techniques to provide a principled way for a potential buyer to make purchasing decisions about private user location data. We illustrate our approach in three scenarios: the delivery of targeted ads specific to a user’s home location, the estimation of traffic speed, and location prediction. In all three cases, the methodology leads to quantifiably better purchasing decisions than competing methods.

Two traffic features [unique cellphone counts (UCC) and pseudo speed (PS)] could be extracted from cellphone activity (CA) data that contain all wireless communication records of a standby or active cellphone. PS has been validated to be close to the traffic speed in the previous works. Further investigation was conducted in this study on the relationship between UCC and the traffic volume. First, a dynamic time warping (DTW)-based method was proposed to analyse the UCC time-series from different freeway links, which consisted of a DTW-based hierarchical clustering step and a DTW-based classification step. Field data was applied in the case study and this proposed analysis method found that UCCs varied from link to link. Besides, this method efficiently classified the links into different groups based on the similarity between UCC and the traffic volume. Moreover, the analysis results were applied to formalising the relationship model between UCC and traffic volume. The case study indicated that a generic linear relationship model might be calibrated, if those links were classified in the same group and were neighbouring enough for a shared close traffic volume value. Besides, it was validated that this model has a good performance under the uncongested traffic condition.

The rolling wheel deflectometer (RWD) and traffic speed deflectometer (TSD) are continuous deflection measuring devices used for structural evaluation of in-service pavements. Although recent studies have demonstrated the benefits of these devices, state agencies are inclined to believe that surface indices are generally sufficient to describe in-service pavement conditions (functional and structural conditions) and to make cost-effective maintenance and rehabilitation decisions. The main objective of this study was to assess whether the use of surface indices only or the declining rates of these indices to identify structurally damaged sections is feasible instead of relying on RWD and TSD estimated pavement structural indices. Results of the analysis showed that structural deficiency, rates of deterioration, and surface indices were correlated to a certain extent. These results were expected, as pavements that are structurally deteriorated will exhibit surface deficiencies over time. Yet, surface indices cannot be used as a reliable predictor of structural capacity. For RWD, the most accurate surface index, which was the alligator cracking surface index, erroneously identified 35% of structurally sound sections as structurally deficient and 51.5% of structurally deficient sections as structurally sound. Similar results were obtained for the TSD; in this case, the most accurate surface index, which was the random cracking index, erroneously identified 16.7% of structurally sound sections as structurally deficient and 51.0% of structurally deficient sections as structurally sound. The cost implication associated with misinterpreted sections from functional indices was investigated. The incorporation of structural indices is expected to provide significant savings to state agencies.

Pavement deflection is the primary indicator reflecting road-bearing capacity. The falling weight deflectometer (FWD) and the Benkelman beam deflectometer (BBD) are widely used in deflection measurement, and are suitable for measuring the elastic deflection of pavement under static loading or dynamic impact loading. In recent years, there has been an increasing interest in continuous dynamic deflectometers, especially velocity-based deflectometers. The velocity-based continuous dynamic deflectometers, such as the laser dynamic deflectometer (LDD), are used to solve the problems of traffic speed and non-destructive pavement deflection measurement. However, there can be many deviations caused by the varied environmental parameters in practical application. In this article, through the review of the mechanism of the Euler-Bernoulli beam upon an elastic foundation and the corresponding influencing factors, the internal and external factors causing dynamic deflection measurement deviation are analyzed and summarized. The influences of pavement temperature, vehicle speed, pavement condition, and other factors are summarized and discussed. On this basis, a model of environmental parameter correction for the continuous dynamic deflectometer is established using a regression analysis method. Numbers of experiments confirmed the reliability of the correction model under different measurement conditions. The correlation experiments between the LDD and different types of deflectometer confirmed the accuracy of the correction model under different measurement conditions. The results showed that the correction model for the continuous deflection measurement of pavements under dynamic loads has strong robustness in different environments and conditions.

The accurate prediction of the highway traffic speed plays an important role in improving the production efficiency and the convenience of lives, and it is also one of the important issues in vehicle social big data analyses. Aiming at the problem of highway traffic speed data preprocessing, this paper proposes the algorithm of Redundant Data Reducing (RDR) that can greatly reduce the amount of data in model training of long short-term memory (LSTM) and improve the training speed under the condition that the influence on prediction accuracy is small and controllable. Aiming at the problem of low prediction accuracy for holiday traffic speeds due to small data volume, this paper proposes the Segment Prediction Algorithm (SPA) based on the speed features, which can effectively improve the prediction accuracy. The experimental results show that RDR can reduce the training data by up to 60% without notably affecting the prediction accuracy, while it improves the training speed by 60%. Compared with the current LSTM algorithm, the prediction accuracy of SPA improves significantly.

The full utilization of Location-Based Vehicle Sensor Data (LB-VSD) can improve the efficiency of traffic control and management. Currently, LB-VSD is widely applied to the prediction of traffic speed. Like the GPS system, BeiDou satellite navigation system (BDS) can collect LB-VSD. In China, the key operation vehicles on the expressway are equipped with BDS to monitor the travel path. This provides a basis for predicting the traffic speed on expressway accurately. In this paper, considering the abnormal data collected by BDS, the screening and processing rules are made, and then the traffic speed sequence is extracted. Considering the data-missing problem caused by equipment failure or abnormal data elimination and the data sparse problem caused by small size of sample, a filling method based on trend-historical data is proposed. Traffic flow evolution is a complex process. Sudden accidents or bad weather can cause a sudden change in traffic flow and non-recurrent traffic congestion. The prediction accuracy of traditional machine learning methods is low when non-recurrent congestion occurred. In order to solve this problem, this paper adopts a deep learning model?Long Short-Term Memory (LSTM) to predict the traffic speed. Moreover, three-regime algorithm is used while building the prediction model. The prediction method is compared with Support Vector Regression (SVR) method. The results show that the prediction accuracy of the proposed method is higher than that of SVR algorithm, and the robustness is better in the case of non-recurrent traffic congestion.

Pavement structural condition evaluation plays an important role in assessing rehabilitation needs and making prudent investment decisions. Recently the use of Traffic Speed Deflectometer (TSD), is...

In this study, experimental studies that the authors have previously performed on a test road for fixed observer conditions to determine the visibility levels are extended to the moving observer position. As a result of the measurements and tests, when the vehicle speed is constant at the current speed limits for urban roads, it has been seen that the visibility level values in the calculation area remain within the acceptable limits and changing the luminous fluxes will not significantly change the visual performance of the drivers up to two lower lighting classes. It has been shown that the light level can be reduced to create two additional classes besides the current one when the traffic density decreases, at the times when vehicle speeds do not decrease. The results are applied as a case study on the Cendere Street. Road lighting classes are determined according to the EN 13201-1 Technical Report. Road lighting classes that can be applied at different times in the Cendere Street change between M3 and M5 according to the average speed of the passing vehicles, traffic density, road and ambient conditions. It is estimated that about 40% energy saving can be achieved when a lighting automation system is installed.

Among traffic flow analysis, there are many methods presented for microscopic and mesoscopic traffic flow in past decades. However, the methods for macroscopic traffic flow analysis are relatively few. That is because the macroscopic traffic flow analysis needs more data and computational resources. In this paper, we focus on macroscopic traffic flow analysis using massive traffic data. A new method, traffic speed cloud maps, is proposed. It can present the traffic states in a large scale, accurately. Also, it can describe the variations of the congestion area. More importantly, with traffic speed cloud maps, people can capture the forming and degrading processes of the congestion and investigate the operation rules of macroscopic traffic flow. In order to evaluate the effectiveness of traffic speed cloud maps, 14 786 073 traffic samples are taken to perform experiments. Experimental results show that traffic speed cloud maps can present the traffic state of large areas accurately, and help us to investigate the variation of macroscopic traffic flow states intuitively and efficiently.

Traffic speed forecasting is one of the important issues in the intelligent transportation system, which is related to traffic management planning. The existing studies tend to use single models to forecast the traffic speed, and cannot completely extract the complex information of the traffic speed sequence. This research proposes a new hybrid model based on reinforcement learning for the accurate forecasting of traffic speed. The model contains the LSTM network and the GRU network as predictors for in-depth mining of the characteristics of traffic speed data and uses reinforcement learning to integrate the results of the two predictors, combining the advantages of multiple predictors to achieve stable and accurate forecasting results of traffic speed. This paper uses two sets of measured traffic data from Guangzhou to test the effectiveness, and five other traffic speed forecasting models are also established for comparison. Experimental results show that the hybrid model applied in the article has the best performance on both data sets, and the MAPEs are 5.02% and 3.25%.

Weak joints are the source of most performance problems in jointed concrete pavements (JPCPs) and composite pavements created by overlaying a JPCP. Until recently, it has been prohibitively...

On the basis of the online car-hailing platform, the data of road network, weather, and GPS track of the second ring road in Chengdu during November 2018, taking into account the temporal and spatial distribution of orders, aiming at the shortest travel time and distance in the passengers' travel demands. This article constructs the minimum travel cost model in the peak period to dynamically adjust the route, and get the real-time optimal route, to provide a recommended route choice for online car-hailing. The experimental results show that the improved ant colony algorithm is superior to the ordinary ant colony algorithm in terms of iteration efficiency and trip cost, indicating that the improved ant colony algorithm can recommend the best real-time driving route for drivers.

Climate change has become a worldwide concern. Reducing CO2 emission is a major challenge for road transportation sector and is of critical importance. This paper, after studying and analyzing the influence of speed on vehicle CO2 emission, proposes a recommended speed calculation scheme based on IoV to obtain vehicle speed and traffic signal phase information. In the recommended speed scenario, the vehicle is informed of the traffic phase information before arriving at the intersection and can set and optimize the current speed. This paper analyzes the three different status of traffic lights and studies the speed that should be adopted in each status. Under the proposed scheme, the recommended speed helps the driver to reach the destination with higher driving efficiency. The average wait time at red traffic lights is shorter than at speeds that are not recommended, resulting in reduced total travel time, higher uninterrupted pass rates, and decreased vehicle fuel consumption and CO2 emissions.

Asphalt concrete stripping is a critical distress that occurs underneath the pavement surface due to the accumulation of moisture with no visual indication at the surface. Past studies have...

The main objective of this research was to evaluate the impact of temporary speed humps and speed tables on vehicle speeds, vehicle speed profiles, and traffic volumes along local and/or collector streets in several rural Iowa cities. A 25 mile per hour (mph) temporary speed hump and a 30 mph temporary speed table, both made of recycled rubber, were purchased to test the impact of temporary devices. Two cities volunteered and the speed hump/table was installed on two test streets on the city of Atlantic and one test street in the city of Le Claire. The speed hump was installed first and then converted to a speed table. Each device was installed for a period of at least two weeks at the same location. Speed, volume, and resident opinion data were then collected and evaluated. In general, the devices were shown to be effective with the temporary speed table performing as well or better than the speed hump. Both the speed hump and the speed table were effective in reducing mean speeds at the device and immediately downstream, while speeds immediately upstream and farther downstream were less likely to be affected. The speed hump and speed table also reduced the number of vehicles exceeding the speed limit in the immediate vicinity of the devices.

Accurate traffic speed prediction is an important and challenging topic for transportation planning. Previous studies on traffic speed prediction predominately used spatio-temporal and context features for prediction. However, they have not made good use of the impact of traffic incidents. In this work, we aim to make use of the information of incidents to achieve a better prediction of traffic speed. Our incident-driven prediction framework consists of three processes. First, we propose a critical incident discovery method to discover traffic incidents with high impact on traffic speed. Second, we design a binary classifier, which uses deep learning methods to extract the latent incident impact features. Combining above methods, we propose a Deep Incident-Aware Graph Convolutional Network (DIGC-Net) to effectively incorporate traffic incident, spatio-temporal, periodic and context features for traffic speed prediction. We conduct experiments using two real-world traffic datasets of San Francisco and New YorkCity. The results demonstrate the superior performance of our model compared with the competing benchmarks.

Asian countries are major contributors to global air pollution and greenhouse gas emissions, with transportation demand and emissions expected to increase. However, few studies have been performed to evaluate policies that could reduce transport-related emissions in the region. This study explores transport-related CO2 and air pollutant emissions in major Asian nations along with the impacts of transport, climate, and emission control policies using the Asia-Pacific Integrated Model (AIM)/Transport model. Our results show that by 2050, CO2 emissions in developing countries will be 1.4&ndash, 4.7-fold greater than the levels in 2005, while most air pollutant emissions will show large reductions (mean annual reduction rates of 0.2% to 6.1%). Notably, implementation of transport, emission control, and carbon pricing policies would reduce CO2 emissions by up to 33% and other air pollutants by 43% to 72%, depending on the emission species. An emission control policy represents the strongest approach for short-term and mid-term reduction of air pollutants. A carbon pricing policy would lead to a direct reduction in CO2 emissions, more importantly, air pollutant emissions would also be effectively reduced. Shifting to public transportation in developing countries can also greatly influence emissions reductions. An increase in traffic speed shows relatively small effects, but can be meaningful in Japan.

This study aims to provide a solution to the incessant land acquisition to surmount growing traffic by promoting the application of adaptable lane dividers meant to be implemented in smart cities. A flexible lane span manipulates the width of the road as a whole, avoiding the need for road expansion. Video data is obtained from cameras placed along a single stretch and is analyzed in real-time. The model uses Computer Vision, ROI (Region of Interest) based execution, exploiting both traffic speed and occupied lane area to determine traffic density. Each camera is assigned a priority value with cameras down the lane possessing higher priority. The decision of each camera constitutes the final decision. The design also adopts pattern recognition based on learning, besides real-time analysis for more conclusive results.

Increasingly serious traffic congestion requires an accurate and timely traffic speed prediction, which will significantly benefit both individual drivers and decision makers in travel planning and traffic management. However, traffic speed prediction is a long-standing and challenging topic. Due to the availability of traffic datasets and powerful computation resources, deep learning becomes a promising solution to this problem. In this paper, based on Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) models, we propose a model named CLM, which is the first to make use of CNN to extract the features of daily and weekly periodicity of traffic speed at the target area and also extract the spatiotemporal features together with the output of CNN by LSTM layers. We conduct comprehensive simulations to assess the performance of our proposed method based on the real-world dataset of Hong Kong. The results indicate that our proposed CLM model can better predict traffic speed in different forecast time periods than the other five competing methods, including SVR, MLP, Lasso, Random forest, and LSTM.

Fundamental diagram, a graphical representation of the relationship among traffic flow, speed, and density, has been the foundation of traffic flow theory and transportation engineering for many years. Underlying a fundamental diagram is the relation between traffic speed and density, which serves as the basis to understand system dynamics. Empirical observations of the traffic speed versus traffic density show a wide-scattering of traffic speeds over a certain level of density, which would form a speed distribution over a certain level of density. The main aim of the current research is to study on the distribution of traffic speed in different traffic conditions in the urban roads since the distribution of traffic speed is necessary for many traffic engineering applications including generating traffic in micro-simulation systems. To do so, the traffic stream is videotaped at various locations in the city of Budapest (Hungary). The recorded videos were analysed by traffic engineering experts and different traffic conditions were extracted from these recorded videos based on the predefined scenarios. Then their relevant speeds in that time interval were estimated with the so-called “g-estimator method” using the outputs of the available loop detectors among the videotaped locations. Then different parametric candidate distributions have been fitted to the speeds by Maximum Likelihood Estimation (MLE) method. Having fitted different parametric distributions to speed data, they were compared by three goodness-of-fit tests along with two penalized criteria (Akaike Information Criterion – AIC and Bayesian Information Criterion – BIC) in order to overcome the over-fitting problems. The results showed that the speed of traffic flow follows exponential, normal, lognormal, gamma, beta and chisquare distribution in the condition that traffic flow followed over-saturated congestion, under saturated flow, free flow, congestion, accelerated flow and decelerated flow respectively.

In recent years, cities in developing countries have become more and more reliant on natural gas as a clean energy source for transportation to reduce air pollution. In this study, we used street-level measurement of atmospheric CH4 and CO2 concentrations to quantify CH4 emissions from natural gas vehicles (NGVs) in China. These measurements were made in eight cities (Chengdu, Urumqi, Jinan, Nanjing, Lanzhou, Harbin, Guangzhou) with varying sizes of NGV fleet. A traffic CH4:CO2 emission ratio (TER) was determined via linear regression of CH4 versus CO2 concentration data obtained from each street transect. The TER value was combined with the ratio of NGVs in the street traffic in a mathematical model to obtain the CH4 emission factor for NGVs. Results show that the TER increases with increasing NGV ratio and decreases with increasing traffic speed. Overall, the NGV CH4 emission factor in these cities is 0.022 ± 0.0033 kg m−3, about 8 times the Intergovernmental Panel on Climate Change (IPCC) default factor for NGVs and is more than 100% higher than the mean NGV tailpipe emission factor found in the published literature. That the overall emission factor is much larger than the tailpipe emission factor indicates that on-road vehicle gas leakage is a widespread problem. A business-as-usual scenario suggests that NGVs may emit 1.23 Tg CH4 yr−1 in 2030, or about 3% of China's current total anthropogenic emission. Our study suggest that curbing the emissions from this sector should be a high priority for global climate mitigation efforts.

Traffic speed is an indicator reflecting the traffic state and it is important for traffic control and optimization. Traffic speed forecasting is a typical application of spatial-temporal forecasting problems. However, it is very difficult to accurately predict the traffic speed especially when we need a long-term forecasting result. And how to capture the spatial features is also a huge challenge. In this paper, a sequence to sequence (Seq2Seq) model based on Graph Convolutional LSTM (GC-LSTM) was proposed, which is an end-to-end deep learning model that uses the network topology and historical speed data. The Graph Convolutional Networks (GCN) is used to deal with spatial relationship features while LSTM for temporal relationship features. The Seq2Seq model is a structure that can predict the multi-step traffic speed. Then an experiment on a real-world dataset shows that our model can get a good result for the long-term traffic forecasting problem.

Traffic state reconstruction gets more and more attention for various important applications such as traffic optimization, traffic control, and congestion avoidance. There exist several approaches to detect traffic parameters like speed, flow, and density. A quite common approach in the past was to use stationary detectors like induction loops. An emerging technology is to handle traffic state by floating-car data (probe vehicles) with a high resolution of time and location measurements via GPS. A third methodology is to detect vehicles using the recognition of in-use Bluetooth devices and to derive an average travel time between two Bluetooth detectors. For the first two approaches, several traffic state reconstruction methods exist. This paper aims at reconstructing the prevailing traffic situation out of low-resolution travel times based on Bluetooth captions. A methodology is developed on how to reconstruct the traffic speed and is applied to three months of data from a German autobahn equipped with Bluetooth detectors.

The development of transportation is increasing rapidly from year to year in accordance with existing technological developments, currently transportation plays an important role in human life, roads are the means of transportation that play the most role in this, along with the increasing volume of passing vehicles as well as road widening of course. Produces a new problem that may still be underestimated, that problem is noise. One of them is a place of education or a school that is right next to the main road, namely Wiyata Mandala Junior High School, Bogor Regency. The speed of private vehicles has a significant effect on noise. From all analysis calculations, the biggest equation is found in the first day of the third point of research (Sound Level Meter 3), with a contribution of 28.95%. The calculation below shows, y = 61.62 + 0.004x1 at a distance of 15.25m SLM. This equation means that if there is no decrease in motorbike speed, the noise level on the SLM3 is 61.62 dBA. The second largest equation was obtained in the first day of research at the second point (Sound Level Meter 2) with a contribution of 27.14% based on the calculation of the equation below, y = 64.23 + 0.007x1 with a distance of 3.44m SLM. The purpose of the above equation is that if there is an increase in motorbike speed, private vehicle speed and public vehicle speed, then the noise on the SLM2 is 64.23 dBA. During the Covid-19 pandemic, motorcycles at moderate speed often passed this school area. So based on the results of observations and calculations, it was found that the decrease in motorcycles was 45% which crossed the Wiyata Mandala Junior High School Bogor.

The mechanical performance of epoxy asphalt concrete has been well reported in existing studies. This study investigated the surface characteristics of asphalt concrete, including the permeability, friction coefficient, moisture damage resistance and surface texture. The permeability test, dynamic friction test, Cantabro test, Hamburg test and laser texture scanning test were carried out for such investigations. Test results show that the permeability of the epoxy asphalt concrete was very low, which is desirable for protecting the steel deck. The friction coefficient can satisfy the requirement for steel deck bridge according to the Pendulum Number. However, it was found that the skid resistance could be a concern when the vehicle speed is higher than a certain level according to the dynamic friction test. The results suggested to control the traffic speed when epoxy asphalt concrete is applied as steel bridge pavement. In terms of the raveling and stripping, it was found that the epoxy asphalt mixture has an excellent anti-stripping performance based on the Cantabro test and Hamburg wheel tracking test results. The yield point was not reached after 20,000 loading cycles at 60 °C in the immersed Hamburg wheel tracking test. The mean profile depth of the epoxy asphalt concrete is 0.305 mm, much lower than conventional asphalt concrete indicating a very fine surface texture. Keywords: Surface characteristics, Epoxy asphalt, Skid resistance, Permeability, Anti-stripping, Surface texture

This research uses data from observations of 8277 motorcyclists at various types of roads of the road hierarchy in Malaysia in 2015, to investigate the effects of road characteristics, motorcyclists’ riding behaviour, motorcyclists’ and motorcycles’ characteristics on the occurrence of riding with excessive speed. For data collection and analysis, new software, i.e. MECHROM, was developed. The speed analysis shows that motorcyclists go faster than other vehicles on dual carriageway primary roads with three-lanes and dual carriageway collector roads with four-lanes. In general, 42.2% of the observed motorcycles exceed the speed limit and 28.6% of them go beyond the 85th percentile of the traffic speed. In determining the factors associated with motorcyclists riding with excessive speed, a mixed effect logistic regression model was produced, with three levels statistically significant random effect parameters. The fixed parameters factors are: primary road, roads with no shoulder, motorcycles with engine capacity of more than 150cc, not overloaded motorcycle, bright motorcycle, male rider, wears helmet and shoes, riding in the middle of the lane or shoulder, lane splitting (i.e. passing through in between two vehicles) and weaving between vehicles. The random parameters show that the majority of variation in the outcomes (56.5%) occurs at level 1 (the rider), while 12.2% of variation occurs at level 2 (motorcycle), and 31.2% at level 3 (location). The variations indicate that the motorcyclist’s characteristics and riding behaviour are of importance, while the variable “type of motorcycle” clearly indicates that riding with excessive speed occurs regardless of the type of motorcycle.

The sounds produced by humans, industries, transport and animals in the atmosphere that pose a threat to the health of humans or animals can be characterized as noise pollution. Adverse effects due to noise exposure can involve speech communication interference and declining learning skills of children. Highway traffic noise contributes to 80% of all noise. It has grown to a massive scale because of growth in population along the roads leading to a rapid change in land use and has evolved into a common reality in various Indian cities. The main objective of this work is to develop a road traffic noise prediction model using ArcGIS 10.3 for the busy corridors of Chennai. The collected data includes traffic volume, speed, and noise level in lateral and vertical directions. Noise levels were measured in 9 locations using a noise level meter. It is observed that the noise levels vary from 50 dB to 96 dB. It is found that the noise problem is severe in 18% of the area, and 6.3% of people are exposed to the traffic noise problem. The results obtained in this study show that the city is affected by severe noise pollution due to road traffic.

Traffic speed prediction in the urban road network is an important and promising task of intelligent transportation systems. Precise traffic speed prediction can mitigate traffic congestion and improve road network utilization. This task is challenging because of the complexity of the spatiotemporal dependency of traffic data among road network. Existing approaches mainly focus on the whole road network and it may capture much redundant information and lead to high computational cost. In this paper, we propose a Key Path-Based Deep Learning Approach: Path-Based CNN-1D + GRU + CNN-2D (P-CGC), a novel deep learning model for traffic speed prediction. Specifically, we use EST-matching algorithm to match the float car data into the road network. Then we select several key paths and build the model for the loop detectors which are in the same key path. We introduce CNN-1D, GRU to extract the temporal dependency of the data, where CNN-1D is used to fuse the contextual information, and GRU is used to capture the features of the temporal dimension. Then we concatenate the output of all CNN-1D+GRU models and use CNN-2D to capture the spatial dependency of the data. Finally, a fully connected neural network is used to transform features into the prediction. We conduct extensive experiments on Zhangzhou real-world datasets, and the proposed approach achieves a good result.