Nowadays the number of cores that are integrated into NoC (Network on Chip) systems is steadily increasing, and real application traffic, running in such multi-core environments requires more and more bandwidth. In th...Nowadays the number of cores that are integrated into NoC (Network on Chip) systems is steadily increasing, and real application traffic, running in such multi-core environments requires more and more bandwidth. In that sense, NoC architectures should be properly designed so as to provide efficient traffic engineering, as well as QoS support. Routing algorithm choice in conjunction with other parameters, such as network size and topology, traffic features (time and spatial distribution), as well as packet injection rate, packet size, and buffering capability, are all equivalently critical for designing a robust NoC architecture, on the grounds of traffic engineering and QoS provision. In this paper, a thorough numerical investigation is achieved by taking into consideration the criticality of selecting the proper routing algorithm, in conjunction with all the other aforementioned parameters. This is done via implementation of four routing evaluation traffic scenarios varying each parameter either individually, or as a set, thus exhausting all possible combinations, and making compact decisions on proper routing algorithm selection in NoC architectures. It has been shown that the simplicity of a deterministic routing algorithm such as XY, seems to be a reasonable choice, not only for random traffic patterns but also for non-uniform distributed traffic patterns, in terms of delay and throughput for 2D mesh NoC systems.展开更多
Small rural communities located along major state or county roadways typically find most of the traffic along their main thoroughfares is pass-through rather than local traffic. Unfortunately, drivers passing through ...Small rural communities located along major state or county roadways typically find most of the traffic along their main thoroughfares is pass-through rather than local traffic. Unfortunately, drivers passing through these communities often enter at high rates of speeds, which are often significantly higher than the speed limit of the local segment. Speed management in rural areas requires different considerations compared to urban areas and, within the US, rural speed management is not as advanced with little experience or guidance for agencies to draw on. This paper summarizes the results of a study that evaluated, in part, several different types of transverse pavement markings within the speed transition zones in small rural communities. Three different countermeasures were evaluated: converging chevrons, transverse lane markings, and optical speed bars.展开更多
The ownership of motorised two wheelers(MTWs)has been on the rise across various countries across the globe.The growth has been especially higher in developing countries which have typical traffic characteristics and ...The ownership of motorised two wheelers(MTWs)has been on the rise across various countries across the globe.The growth has been especially higher in developing countries which have typical traffic characteristics and higher populations.This steady rise has resulted in increased accident and fatalities.This abrupt increase warranted attention from the researchers to carry out specific studies for MTWs,which have a very different behaviour as compared to cars in terms of physical and dynamic parameters.Moreover,the unique traffic patterns usually found in the developing countries pose an additional challenge to the researchers,since the conventional focus of transportation safety researchers was a homogeneous car-based traffic.Many such studies have been attempted,especially in the recent decades,which have considered various risk factors related to MTW safety.However,the studies have considered different sets of risk factors and have given surprising and even conflicting results.Therefore,a comprehensive review of the diverse studies needs to be carried out which incorporates all the risk factors considered in previous research.This study reviews such research papers which have analysed various risk factors related to safety of MTWs,especially in heterogeneous,non-lane based traffic.Specifically,this paper aims to incorporate results from those studies and highlight the conclusions from state of the art.The paper also discusses about the research gaps that are crucial for MTW safety in mixed traffic conditions.The review will be useful for researchers working in the field of MTW safety and for policy implementation and analysis.展开更多
Short-term taxi demand forecasting is of great importance to incentivize vacant cars moving from over-supply regions to over-demand regions,which can minimize the wait time for passengers and drivers.With the consider...Short-term taxi demand forecasting is of great importance to incentivize vacant cars moving from over-supply regions to over-demand regions,which can minimize the wait time for passengers and drivers.With the consideration of spatiotemporal dependences,this study proposes a multi-task deep learning(MTDL)model to predict short-term taxi demand in multi-zone level.The nonlinear Granger causality test is applied to explore the causality relationships among various traffic zones,and long short-term memory(LSTM)is used as the core neural unit to construct the framework of the multi-task deep learning model.In addition,several hyperparameter optimization methods(e.g.,grid search,random search,Bayesian optimization,hyperopt)are used to tune the model.Using the taxi trip data in New York City for validation,the multi-task deep learning model considering spatiotemporal dependences(MTDL*)is compared with the single-task deep learning model(STDL),the full-connected multi-task deep learning model(MTDL#)and other benchmark algorithms(such as LSTM,support vector machine(SVM)and k-nearest neighbors(k-NN)).The experiment results show that the proposed MTDL model is promising to predict short-term taxi demand in multi-zone level,the nonlinear Granger causality analysis is able to capture the spatiotemporal correlations among various traffic zones,and the Bayesian optimization is superior to the other three methods,which verified the feasibility and adaptability of the proposed method.展开更多
The main of the research was to analyze the leaf metal accumulation capability of </span><i><span style="font-family:Verdana;">Platanus acerifolia</span></i><span style="...The main of the research was to analyze the leaf metal accumulation capability of </span><i><span style="font-family:Verdana;">Platanus acerifolia</span></i><span style="font-family:Verdana;"> (Aiton) Willd., </span><i><span style="font-family:Verdana;">Ailantus altissima</span></i><span style="font-family:Verdana;"> (Mill.) Swingle, </span><i><span style="font-family:Verdana;">Robinia pseudoacacia </span></i><span style="font-family:Verdana;">L. and</span><i><span style="font-family:Verdana;"> Quercus ilex</span></i><span style="font-family:Verdana;"> L., largely distributed in Rome. In addition, metal concentration was analyzed in the soil, sampling sites were chosen in historical parks (A sites) and high traffic level sites (B sites). The results highlight significant higher leaf and soil metal concentrations in B than in A sites. The ratio between metal concentration in leaves and soils (Biological Absorption Coefficient, BAC) for all the considered sites was significantly different among the species.</span><i> </i><span style="font-family:Verdana;">Morphological and anatomical leaf traits of the considered species show significant differences in A and B sites in response to traffic level. Overall, the results highlight the importance of the selection of tree species in urban areas for their ability to lower pollution levels.展开更多
This study evaluates the Dynamic Message Signs (DMSs) use to dissipate incident information on the freeways in Las Vegas, Nevada. It focuses on the DMSs message timing, extent, and content, from the operators’ and dr...This study evaluates the Dynamic Message Signs (DMSs) use to dissipate incident information on the freeways in Las Vegas, Nevada. It focuses on the DMSs message timing, extent, and content, from the operators’ and drivers’ perspectives, considering the variability in drivers’ freeway experience. Two-week incidents data with fifty-nine incidents, DMS log data, and responses from a survey questionnaire were used. The descriptive analysis of the incidents revealed that about 54% of the incidents had their information posted on the DMSs;however, information of only 18.6% of the incidents was posted on time. The posted information covered the incident type (54.2%), location (49.2%), and lane blockage (45.8%), while the expected delay or the time the incident has lasted are rarely posted. Further, the standard DMSs are the most preferred sources of traffic information on the freeway compared to the travel time only DMSs, and the graphical map boards. The logistic regression applied to the survey responses revealed that regular freeway users are less likely to take an alternative route when they run into congestion, given no other </span><span style="font-family:Verdana;">information is available. Conversely, when given accurate information</span><span style="font-family:Verdana;"> through DMSs, regular freeway users are about 2.9 times more likely to detour. Furthermore, regular freeway users perceive that the DMSs show clear information about the incident location. Upon improving the DMSs usage, 73% of respondents suggested that the information be provided earlier, and 54% requested improvements on congestion duration and length information. These findings can be used by the DMSs operators in Nevada and worldwide to improve freeway operations.展开更多
The purpose of this paper is to provide a summary of a quick overview of the latest developments and unprecedented opportunities for scholars who want to set foot in the field of traditional taxi and online car-hailin...The purpose of this paper is to provide a summary of a quick overview of the latest developments and unprecedented opportunities for scholars who want to set foot in the field of traditional taxi and online car-hailing(TTOC).From the perspectives of peoples(e.g.,passenger,driver,and policymaker),vehicle,road,and environment,this paper describes the current research status of TTOC's big data in six hot topics,including the ridership factor,spatio-temporal distribution and travel behavior,cruising strategy and passenger service market partition,route planning,transportation emission and new-energy,and TTOC's data extensional application.These topics were included in five mainstreams as follows:(1)abundant studies often focus only on determinant analysis on given transportation(taxi,transit,online car-hailing);the exploration of ridership patterns for a multimodal transportation mode is rare;furthermore,multiple aspects of factors were not considered synchronously in a wide time span;(2)travel behavior research mainly concentrates on the commuting trips and distribution patterns of various travel indices(e.g.,distance,displacement,time);(3)the taxi driver-searching strategy can be divided into autopsychic cruising and system dispatching;(4)the spatio-temporal distribution character of TTOC's fuel consumption(FC)and greenhouse gas(GHG)emissions has become a hotspot recently,and there has been a recommendation for electric taxi(ET)in urban cities to decrease transportation congestion is proposed;and(5)based on TTOC and point of interest(POI)multi-source data,many machine learning algorithms were used to predict travel condition indices,land use,and travel behavior.Then,the main bottlenecks and research directions that can be explored in the future are discussed.We hope this result can provide an overview of current fundamental aspects of TTOC's utilization in the urban area.展开更多
Estimating safety effectiveness of roadway improvements and countermeasures,using cross-sectional models,generally requires large amounts of data such as road geometric and traffic-related characteristics at road segm...Estimating safety effectiveness of roadway improvements and countermeasures,using cross-sectional models,generally requires large amounts of data such as road geometric and traffic-related characteristics at road segment levels.These models do not consider all confounding crash contributory factors such as driving culture and environmental conditions at the segment level due to a lack of readily available data.This may result in inaccurate models representing actual conditions at road segment levels,followed by erroneous estimations of safety effectiveness.To minimize the effect of not including such variables,this study develops a new methodology to estimate safety effectiveness of roadway countermeasures,based on generalized linear mixed models,assuming zeroinflated Poisson distribution for the response,and adjusting for spatial autocorrelation using the spatial random effect.The Bayesian approach,with Integrated Nested Laplace Approximation,was used to make inference on this model with computational efficiency.Results showed that incorporating a spatial random effect into the models provided better model fit than non-spatial models;hence,estimated safety effectiveness based on such models is more accurate.The proposed approach is a methodological advancement in traffic safety,which allows evaluation of safety effectiveness or roadway improvements when data are not readily available.展开更多
Under mixed traffic conditions prevailing on Indian roads,drivers show complex response when faced with yellow signal because lane assignment gets dynamic in nature.The present study analyzes the effect of surrounding...Under mixed traffic conditions prevailing on Indian roads,drivers show complex response when faced with yellow signal because lane assignment gets dynamic in nature.The present study analyzes the effect of surrounding vehicles on response of the drivers while facing dilemma at intersections.Although dilemma zone definitions hold true in case of homogeneous traffic mix,a statistical analysis is performed to check the consistency across the definitions under mixed traffic condition.Present study shows a significant difference in percentage of red light running in comparison to homogeneous traffic as reported by various studies.For carrying out the research,study locations are chosen in such a way to reflect diversity in road geometry,traffic composition and signal characteristics.The results deduced in this study indicate a strong correlation between the driver's decision making choice and the effect of presence of surrounding vehicle at the onset of yellow signal.The effect of critical time analysis has been found out to be one of the parameters other than critical distance in categorizing driver's aggressiveness while facing the yellow signal.In the process of identifying the statistical significance of dilemma zone definitions,it has been found that under heterogeneous traffic condition,drivers behave differently as compared to homogenous traffic when it comes to dilemma zone.It is observed that the percentage of vehicles crossing the intersection when faced with dilemma by violating the red light is 11.6%according to dilemma zone definition I whereas the definition II has yielded about 10.8%violation covering different vehicle types.The above violation figures derived based on the above definition is somewhat higher as compared to homogeneous traffic condition which is observed to be of the order of 5%-6%.展开更多
At two-way stop controlled(TWSC)intersections drivers on minor stream are generally at risk because of the difficulty in judging safe gap between major stream vehicles.Any misjudgment by the driver while choosing gap ...At two-way stop controlled(TWSC)intersections drivers on minor stream are generally at risk because of the difficulty in judging safe gap between major stream vehicles.Any misjudgment by the driver while choosing gap may result in a collision with major stream vehicle.This paper provides important insights for determining and analyzing spatial critical gaps of drivers at high speed and medium speed TWSC intersections.The critical gap line(CGL)fitted for the accepted and rejected gaps using parametric(binary logit model-BLM)and non-parametric(support vector machines-SVM)techniques gives critical gap values at 15 th,50 th and 85 th percentile speeds.The evaluation of spatial critical gap with respect to major road vehicle(conflicting vehicle)speed makes it easier to understand the impact of variation in speed on spatial gaps accepted by the drivers on the minor road.The logit models developed revealed that the probability of accepting gap decreases with increase in the speed of the conflicting vehicle and it increases with increase in the distance of conflicting vehicle.The spatial critical gaps estimated using support vector machines were found in close approximation with those estimated using binary logit model.The study results showed that SVMs have very good potential to be an alternative tool for the estimation of driver's critical gap.The spatial critical gaps corresponding to 15 th,50 th and 85 th percentile speeds for medium speed intersections were 32 m,38 m and 46 m respectively and for high speed intersections these values were 64 m,76 m and 104 m respectively.The increase in the magnitude of gap value with respect to the percentile speed clearly states the effect of speed on spatial gaps.The insights from the study can be used to suggest various measures to improve the safety of crossing drivers at uncontrolled intersections.展开更多
Purpose The increasing number of deaths due to road traffic accidents(RTAs)has attracted global attention.However,the influence of road types is rarely considered in the study of RTAs.This study evaluates the influenc...Purpose The increasing number of deaths due to road traffic accidents(RTAs)has attracted global attention.However,the influence of road types is rarely considered in the study of RTAs.This study evaluates the influence of different road types in RTAs in northern Guizhou to provide a basis for the formulation of evidence-based policies and measures.Methods We obtained the data from the Zunyi Traffic Management Data Platform for the years 2009–2018.The mortality rates of RTAs were calculated.Descriptive methods and Chi-square tests were used to analyze the characteristics of road traffic collisions on different road types.We also examined the associations between the mortality rate per 10,000 vehicles and the growth of per capital gross domestic product(GDP)with Spearman’s rank correlation analysis.According to the passing volume and the infrastructure,we defined different types of roads,like administrative road,functional road,general urban road and urban expressway.Results In 2012,the traffic mortality rate of administrative roads was 8.9 per 100,000 people,and the mortality rate of functional roads was 7.4 per 100,000 people,which decreased in 2018 to 6.1 deaths per 100,000 people and 5.2 deaths per 100,000 people,respectively.The mortality rate per 10,000 vehicles reached the highest level in 2011(28.8 per 10,000 vehicles and 22.5 per 10,000 vehicles on administrative and functional roads,respectively).The death rate of county roads was the highest among administrative roads(χ^(2)=17.389,p<0.05)and that of fourth-class roads was the highest among functional roads(χ^(2)=21.785,p<0.05).The mortality rate per 10,000 vehicles was negatively correlated with per capital GDP.Conclusion Although our research shows that RTAs in northern Guizhou have steadily declined in recent years,the range of decline is relatively small.Many measures and sustainable efforts are needed to control road traffic death and accelerate the progress in road traffic safety in northern Guizhou.展开更多
The year 2020 is an extremely unusual year.The world lost more than one million lives due to the attack of COVID-19.Economic production has been greatly reduced,and daily activities are largely restricted.Luckily the ...The year 2020 is an extremely unusual year.The world lost more than one million lives due to the attack of COVID-19.Economic production has been greatly reduced,and daily activities are largely restricted.Luckily the work of Chinese Journal of Traumatology(CJTEE)has not been adversely affected.2020 is a harvest year for the journal,which(1)was included in the high-quality academic journals by China Association for Science and Technology;(2)cover of each issue is newly designed;(3)submission increased by about 60%with more countries and regions covered;(4)usage in the ScienceDirect database exceeded a million;(5)the CiteScore rises to more than 2.0 the first time.This study reviewed the articles published in the year 2020 by CJTEE.展开更多
This study presents an order exponential model for estimating road traffic safety in city clusters.The proposed model introduces the traffic flow intrinsic properties and uses the characteristics and regular patterns ...This study presents an order exponential model for estimating road traffic safety in city clusters.The proposed model introduces the traffic flow intrinsic properties and uses the characteristics and regular patterns of traffic development to identify road traffic safety levels in city clusters.Additionally,an evaluation index system of city cluster road traffic safety was constructed based on the spatial and temporal distribution.Then Order Exponential Evaluation Model(OEEM),a comprehensive model using order exponent function for road traffic safety evaluation,was put forward,which considers the main characteristics and the generation process of traffic accidents.The model effectively controlled the unsafe behavior of the traffic system.It could define the levels of city cluster road traffic safety and dynamically detect road safety risk.The proposed model was verified with statistical data from three Chinese city clusters by comparing the common model for road traffic safety with an ideal model.The results indicate that the order exponent approach undertaken in this study can be extended and applied to other research topics and fields.展开更多
Traffic is a main source of air pollutants in urban areas and consequently daily peak exposures tend to occur during commuting.Personal exposure to particulate matter(PM)was monitored while cycling and travelling by b...Traffic is a main source of air pollutants in urban areas and consequently daily peak exposures tend to occur during commuting.Personal exposure to particulate matter(PM)was monitored while cycling and travelling by bus,car and metro along an assigned route in Lisbon(Portugal),focusing on PM2.5 and PM10(PM with aerodynamic diameter<2.5 and 10μm,respectively)mass concentrations and their chemical composition.In vehicles,the indoor-outdoor interplay was also evaluated.The PM2.5 mean concentrations were 28±5,31±9,34±9 and 38±21μg/m 3 for bus,bicycle,car and metro modes,respectively.Black carbon concentrations when travelling by car were 1.4 to 2.0 times higher than in the other transport modes due to the closer proximity to exhaust emissions.There are marked differences in PM chemical composition depending on transport mode.In particular,Fe was the most abundant component of metro PM,derived from abrasion of rail-wheel-brake interfaces.Enhanced concentrations of Zn and Cu in cars and buses were related with brake and tyre wear particles,which can penetrate into the vehicles.In the motorised transport modes,Fe,Zn,Cu,Ni and K were correlated,evidencing their common traffic-related source.On average,the highest inhaled dose of PM2.5 was observed while cycling(55μg),and the lowest in car travels(17μg).Cyclists inhaled higher doses of PM2.5 due to both higher inhalation rates and longer journey times,with a clear enrichment in mineral elements.The presented results evidence the importance of considering the transport mode in exposure assessment studies.展开更多
Bridge in Clouds An aerial photo of the Heshandu Wujiang River Bridge in Guizhou Province,southwest China,on December 29,2020.The bridge,spanning 2000 meters,is a key part of the Meitan-Shiqian Expressway.It was compl...Bridge in Clouds An aerial photo of the Heshandu Wujiang River Bridge in Guizhou Province,southwest China,on December 29,2020.The bridge,spanning 2000 meters,is a key part of the Meitan-Shiqian Expressway.It was completed on January 3 and will open to traffic in July.展开更多
Scheduling schemes assign limited resources to appropriate users,which are critical for wireless network performance.Most current schemes have been designed based on saturated traffic,i.e.,assuming users in networks a...Scheduling schemes assign limited resources to appropriate users,which are critical for wireless network performance.Most current schemes have been designed based on saturated traffic,i.e.,assuming users in networks always have data to transmit.However,the user buffer may sometimes be empty in actual network.Therefore,these algorithms will allocate resources to users having no data to transmit,which results in resource waste.In view of this,we propose new scheduling schemes for onehop and two-hop link scenario with unsaturated traffic.Furthermore,this paper analyzes their key network performance indicators,including the average queue length,average throughput,average delay and outage probability.The two scheduling algorithms avoid scheduling the links whose buffers are empty and thus improve the network resource utilization.For the one-hop link scenario,network provides differentiated services via adjusting the scheduling probabilities of the destination nodes(DNs)with different priorities.Among the DNs with same priority,the node with higher data arrival rate has larger scheduling probability.For the two-hop link scenario,we prioritize the scheduling of relay-to-destination(R-D)link and dynamically adjust the transmission probability of source-to-relay(S-R)link,according to the length of remaining buffer.The experiment results show the effectiveness and advantage of the proposed algorithms.展开更多
The modeling of an efficient classifier is a fundamental issue in automatic training involving a large volume of representative data.Hence,automatic classification is a major task that entails the use of training meth...The modeling of an efficient classifier is a fundamental issue in automatic training involving a large volume of representative data.Hence,automatic classification is a major task that entails the use of training methods capable of assigning classes to data objects by using the input activities presented to learn classes.The recognition of new elements is possible based on predefined classes.Intrusion detection systems suffer from numerous vulnerabilities during analysis and classification of data activities.To overcome this problem,new analysis methods should be derived so as to implement a relevant system to monitor circulated traffic.The main objective of this study is to model and validate a heterogeneous traffic classifier capable of categorizing collected events within networks.The new model is based on a proposed machine learning algorithm that comprises an input layer,a hidden layer,and an output layer.A reliable training algorithm is proposed to optimize the weights,and a recognition algorithm is used to validate the model.Preprocessing is applied to the collected traffic prior to the analysis step.This work aims to describe the mathematical validation of a new machine learning classifier for heterogeneous traffic and anomaly detection.展开更多
文摘Nowadays the number of cores that are integrated into NoC (Network on Chip) systems is steadily increasing, and real application traffic, running in such multi-core environments requires more and more bandwidth. In that sense, NoC architectures should be properly designed so as to provide efficient traffic engineering, as well as QoS support. Routing algorithm choice in conjunction with other parameters, such as network size and topology, traffic features (time and spatial distribution), as well as packet injection rate, packet size, and buffering capability, are all equivalently critical for designing a robust NoC architecture, on the grounds of traffic engineering and QoS provision. In this paper, a thorough numerical investigation is achieved by taking into consideration the criticality of selecting the proper routing algorithm, in conjunction with all the other aforementioned parameters. This is done via implementation of four routing evaluation traffic scenarios varying each parameter either individually, or as a set, thus exhausting all possible combinations, and making compact decisions on proper routing algorithm selection in NoC architectures. It has been shown that the simplicity of a deterministic routing algorithm such as XY, seems to be a reasonable choice, not only for random traffic patterns but also for non-uniform distributed traffic patterns, in terms of delay and throughput for 2D mesh NoC systems.
文摘Small rural communities located along major state or county roadways typically find most of the traffic along their main thoroughfares is pass-through rather than local traffic. Unfortunately, drivers passing through these communities often enter at high rates of speeds, which are often significantly higher than the speed limit of the local segment. Speed management in rural areas requires different considerations compared to urban areas and, within the US, rural speed management is not as advanced with little experience or guidance for agencies to draw on. This paper summarizes the results of a study that evaluated, in part, several different types of transverse pavement markings within the speed transition zones in small rural communities. Three different countermeasures were evaluated: converging chevrons, transverse lane markings, and optical speed bars.
文摘The ownership of motorised two wheelers(MTWs)has been on the rise across various countries across the globe.The growth has been especially higher in developing countries which have typical traffic characteristics and higher populations.This steady rise has resulted in increased accident and fatalities.This abrupt increase warranted attention from the researchers to carry out specific studies for MTWs,which have a very different behaviour as compared to cars in terms of physical and dynamic parameters.Moreover,the unique traffic patterns usually found in the developing countries pose an additional challenge to the researchers,since the conventional focus of transportation safety researchers was a homogeneous car-based traffic.Many such studies have been attempted,especially in the recent decades,which have considered various risk factors related to MTW safety.However,the studies have considered different sets of risk factors and have given surprising and even conflicting results.Therefore,a comprehensive review of the diverse studies needs to be carried out which incorporates all the risk factors considered in previous research.This study reviews such research papers which have analysed various risk factors related to safety of MTWs,especially in heterogeneous,non-lane based traffic.Specifically,this paper aims to incorporate results from those studies and highlight the conclusions from state of the art.The paper also discusses about the research gaps that are crucial for MTW safety in mixed traffic conditions.The review will be useful for researchers working in the field of MTW safety and for policy implementation and analysis.
基金supported by the National Natural Science Foundation of China(71871227)the Innovation Driven Plan of Central South University(20180016040002)。
文摘Short-term taxi demand forecasting is of great importance to incentivize vacant cars moving from over-supply regions to over-demand regions,which can minimize the wait time for passengers and drivers.With the consideration of spatiotemporal dependences,this study proposes a multi-task deep learning(MTDL)model to predict short-term taxi demand in multi-zone level.The nonlinear Granger causality test is applied to explore the causality relationships among various traffic zones,and long short-term memory(LSTM)is used as the core neural unit to construct the framework of the multi-task deep learning model.In addition,several hyperparameter optimization methods(e.g.,grid search,random search,Bayesian optimization,hyperopt)are used to tune the model.Using the taxi trip data in New York City for validation,the multi-task deep learning model considering spatiotemporal dependences(MTDL*)is compared with the single-task deep learning model(STDL),the full-connected multi-task deep learning model(MTDL#)and other benchmark algorithms(such as LSTM,support vector machine(SVM)and k-nearest neighbors(k-NN)).The experiment results show that the proposed MTDL model is promising to predict short-term taxi demand in multi-zone level,the nonlinear Granger causality analysis is able to capture the spatiotemporal correlations among various traffic zones,and the Bayesian optimization is superior to the other three methods,which verified the feasibility and adaptability of the proposed method.
文摘The main of the research was to analyze the leaf metal accumulation capability of </span><i><span style="font-family:Verdana;">Platanus acerifolia</span></i><span style="font-family:Verdana;"> (Aiton) Willd., </span><i><span style="font-family:Verdana;">Ailantus altissima</span></i><span style="font-family:Verdana;"> (Mill.) Swingle, </span><i><span style="font-family:Verdana;">Robinia pseudoacacia </span></i><span style="font-family:Verdana;">L. and</span><i><span style="font-family:Verdana;"> Quercus ilex</span></i><span style="font-family:Verdana;"> L., largely distributed in Rome. In addition, metal concentration was analyzed in the soil, sampling sites were chosen in historical parks (A sites) and high traffic level sites (B sites). The results highlight significant higher leaf and soil metal concentrations in B than in A sites. The ratio between metal concentration in leaves and soils (Biological Absorption Coefficient, BAC) for all the considered sites was significantly different among the species.</span><i> </i><span style="font-family:Verdana;">Morphological and anatomical leaf traits of the considered species show significant differences in A and B sites in response to traffic level. Overall, the results highlight the importance of the selection of tree species in urban areas for their ability to lower pollution levels.
文摘This study evaluates the Dynamic Message Signs (DMSs) use to dissipate incident information on the freeways in Las Vegas, Nevada. It focuses on the DMSs message timing, extent, and content, from the operators’ and drivers’ perspectives, considering the variability in drivers’ freeway experience. Two-week incidents data with fifty-nine incidents, DMS log data, and responses from a survey questionnaire were used. The descriptive analysis of the incidents revealed that about 54% of the incidents had their information posted on the DMSs;however, information of only 18.6% of the incidents was posted on time. The posted information covered the incident type (54.2%), location (49.2%), and lane blockage (45.8%), while the expected delay or the time the incident has lasted are rarely posted. Further, the standard DMSs are the most preferred sources of traffic information on the freeway compared to the travel time only DMSs, and the graphical map boards. The logistic regression applied to the survey responses revealed that regular freeway users are less likely to take an alternative route when they run into congestion, given no other </span><span style="font-family:Verdana;">information is available. Conversely, when given accurate information</span><span style="font-family:Verdana;"> through DMSs, regular freeway users are about 2.9 times more likely to detour. Furthermore, regular freeway users perceive that the DMSs show clear information about the incident location. Upon improving the DMSs usage, 73% of respondents suggested that the information be provided earlier, and 54% requested improvements on congestion duration and length information. These findings can be used by the DMSs operators in Nevada and worldwide to improve freeway operations.
基金supported by the National Natural Science Foundation of China,grant number 51878062the National Key Research and Development Program of China,grant number 2019YFB1600300the National Science Foundation of Shaanxi Province,grant number 2020JQ-387。
文摘The purpose of this paper is to provide a summary of a quick overview of the latest developments and unprecedented opportunities for scholars who want to set foot in the field of traditional taxi and online car-hailing(TTOC).From the perspectives of peoples(e.g.,passenger,driver,and policymaker),vehicle,road,and environment,this paper describes the current research status of TTOC's big data in six hot topics,including the ridership factor,spatio-temporal distribution and travel behavior,cruising strategy and passenger service market partition,route planning,transportation emission and new-energy,and TTOC's data extensional application.These topics were included in five mainstreams as follows:(1)abundant studies often focus only on determinant analysis on given transportation(taxi,transit,online car-hailing);the exploration of ridership patterns for a multimodal transportation mode is rare;furthermore,multiple aspects of factors were not considered synchronously in a wide time span;(2)travel behavior research mainly concentrates on the commuting trips and distribution patterns of various travel indices(e.g.,distance,displacement,time);(3)the taxi driver-searching strategy can be divided into autopsychic cruising and system dispatching;(4)the spatio-temporal distribution character of TTOC's fuel consumption(FC)and greenhouse gas(GHG)emissions has become a hotspot recently,and there has been a recommendation for electric taxi(ET)in urban cities to decrease transportation congestion is proposed;and(5)based on TTOC and point of interest(POI)multi-source data,many machine learning algorithms were used to predict travel condition indices,land use,and travel behavior.Then,the main bottlenecks and research directions that can be explored in the future are discussed.We hope this result can provide an overview of current fundamental aspects of TTOC's utilization in the urban area.
文摘Estimating safety effectiveness of roadway improvements and countermeasures,using cross-sectional models,generally requires large amounts of data such as road geometric and traffic-related characteristics at road segment levels.These models do not consider all confounding crash contributory factors such as driving culture and environmental conditions at the segment level due to a lack of readily available data.This may result in inaccurate models representing actual conditions at road segment levels,followed by erroneous estimations of safety effectiveness.To minimize the effect of not including such variables,this study develops a new methodology to estimate safety effectiveness of roadway countermeasures,based on generalized linear mixed models,assuming zeroinflated Poisson distribution for the response,and adjusting for spatial autocorrelation using the spatial random effect.The Bayesian approach,with Integrated Nested Laplace Approximation,was used to make inference on this model with computational efficiency.Results showed that incorporating a spatial random effect into the models provided better model fit than non-spatial models;hence,estimated safety effectiveness based on such models is more accurate.The proposed approach is a methodological advancement in traffic safety,which allows evaluation of safety effectiveness or roadway improvements when data are not readily available.
文摘Under mixed traffic conditions prevailing on Indian roads,drivers show complex response when faced with yellow signal because lane assignment gets dynamic in nature.The present study analyzes the effect of surrounding vehicles on response of the drivers while facing dilemma at intersections.Although dilemma zone definitions hold true in case of homogeneous traffic mix,a statistical analysis is performed to check the consistency across the definitions under mixed traffic condition.Present study shows a significant difference in percentage of red light running in comparison to homogeneous traffic as reported by various studies.For carrying out the research,study locations are chosen in such a way to reflect diversity in road geometry,traffic composition and signal characteristics.The results deduced in this study indicate a strong correlation between the driver's decision making choice and the effect of presence of surrounding vehicle at the onset of yellow signal.The effect of critical time analysis has been found out to be one of the parameters other than critical distance in categorizing driver's aggressiveness while facing the yellow signal.In the process of identifying the statistical significance of dilemma zone definitions,it has been found that under heterogeneous traffic condition,drivers behave differently as compared to homogenous traffic when it comes to dilemma zone.It is observed that the percentage of vehicles crossing the intersection when faced with dilemma by violating the red light is 11.6%according to dilemma zone definition I whereas the definition II has yielded about 10.8%violation covering different vehicle types.The above violation figures derived based on the above definition is somewhat higher as compared to homogeneous traffic condition which is observed to be of the order of 5%-6%.
文摘At two-way stop controlled(TWSC)intersections drivers on minor stream are generally at risk because of the difficulty in judging safe gap between major stream vehicles.Any misjudgment by the driver while choosing gap may result in a collision with major stream vehicle.This paper provides important insights for determining and analyzing spatial critical gaps of drivers at high speed and medium speed TWSC intersections.The critical gap line(CGL)fitted for the accepted and rejected gaps using parametric(binary logit model-BLM)and non-parametric(support vector machines-SVM)techniques gives critical gap values at 15 th,50 th and 85 th percentile speeds.The evaluation of spatial critical gap with respect to major road vehicle(conflicting vehicle)speed makes it easier to understand the impact of variation in speed on spatial gaps accepted by the drivers on the minor road.The logit models developed revealed that the probability of accepting gap decreases with increase in the speed of the conflicting vehicle and it increases with increase in the distance of conflicting vehicle.The spatial critical gaps estimated using support vector machines were found in close approximation with those estimated using binary logit model.The study results showed that SVMs have very good potential to be an alternative tool for the estimation of driver's critical gap.The spatial critical gaps corresponding to 15 th,50 th and 85 th percentile speeds for medium speed intersections were 32 m,38 m and 46 m respectively and for high speed intersections these values were 64 m,76 m and 104 m respectively.The increase in the magnitude of gap value with respect to the percentile speed clearly states the effect of speed on spatial gaps.The insights from the study can be used to suggest various measures to improve the safety of crossing drivers at uncontrolled intersections.
基金The study was supported by the National Natural Science Foundation of China(NSFC No.81760233)Science and Technology Project of Guizhou Province(No.[2020]4Y149 and[2019]5661).
文摘Purpose The increasing number of deaths due to road traffic accidents(RTAs)has attracted global attention.However,the influence of road types is rarely considered in the study of RTAs.This study evaluates the influence of different road types in RTAs in northern Guizhou to provide a basis for the formulation of evidence-based policies and measures.Methods We obtained the data from the Zunyi Traffic Management Data Platform for the years 2009–2018.The mortality rates of RTAs were calculated.Descriptive methods and Chi-square tests were used to analyze the characteristics of road traffic collisions on different road types.We also examined the associations between the mortality rate per 10,000 vehicles and the growth of per capital gross domestic product(GDP)with Spearman’s rank correlation analysis.According to the passing volume and the infrastructure,we defined different types of roads,like administrative road,functional road,general urban road and urban expressway.Results In 2012,the traffic mortality rate of administrative roads was 8.9 per 100,000 people,and the mortality rate of functional roads was 7.4 per 100,000 people,which decreased in 2018 to 6.1 deaths per 100,000 people and 5.2 deaths per 100,000 people,respectively.The mortality rate per 10,000 vehicles reached the highest level in 2011(28.8 per 10,000 vehicles and 22.5 per 10,000 vehicles on administrative and functional roads,respectively).The death rate of county roads was the highest among administrative roads(χ^(2)=17.389,p<0.05)and that of fourth-class roads was the highest among functional roads(χ^(2)=21.785,p<0.05).The mortality rate per 10,000 vehicles was negatively correlated with per capital GDP.Conclusion Although our research shows that RTAs in northern Guizhou have steadily declined in recent years,the range of decline is relatively small.Many measures and sustainable efforts are needed to control road traffic death and accelerate the progress in road traffic safety in northern Guizhou.
文摘The year 2020 is an extremely unusual year.The world lost more than one million lives due to the attack of COVID-19.Economic production has been greatly reduced,and daily activities are largely restricted.Luckily the work of Chinese Journal of Traumatology(CJTEE)has not been adversely affected.2020 is a harvest year for the journal,which(1)was included in the high-quality academic journals by China Association for Science and Technology;(2)cover of each issue is newly designed;(3)submission increased by about 60%with more countries and regions covered;(4)usage in the ScienceDirect database exceeded a million;(5)the CiteScore rises to more than 2.0 the first time.This study reviewed the articles published in the year 2020 by CJTEE.
基金Sponsored by the National Natural Science Foundation of China(Grant No.51178157)the High-level Project of the Top Six Talents in Jiangsu Province(Grant No.JXQC-021)+1 种基金the Key Science and Technology Program in Henan Province(Grant No.182102310004)the Humanities and Social Science Research Programs Foundation of Ministry of Education of China(Grant No.18YJAZH028).
文摘This study presents an order exponential model for estimating road traffic safety in city clusters.The proposed model introduces the traffic flow intrinsic properties and uses the characteristics and regular patterns of traffic development to identify road traffic safety levels in city clusters.Additionally,an evaluation index system of city cluster road traffic safety was constructed based on the spatial and temporal distribution.Then Order Exponential Evaluation Model(OEEM),a comprehensive model using order exponent function for road traffic safety evaluation,was put forward,which considers the main characteristics and the generation process of traffic accidents.The model effectively controlled the unsafe behavior of the traffic system.It could define the levels of city cluster road traffic safety and dynamically detect road safety risk.The proposed model was verified with statistical data from three Chinese city clusters by comparing the common model for road traffic safety with an ideal model.The results indicate that the order exponent approach undertaken in this study can be extended and applied to other research topics and fields.
基金European Union through the project LIFE Index-Air(LIFE15 ENV/PT/000674)supported by Portuguese Foundation for Science and Technology(FCT)through the projects Expo LIS(LISBOA-01-0145-FEDER-032088)and UID/Multi/04349/2013,the contract CEECIND/04228/2018 and the Ph D grants SFRH/BD/129149/2017 and SFRH/BD/147074/2019。
文摘Traffic is a main source of air pollutants in urban areas and consequently daily peak exposures tend to occur during commuting.Personal exposure to particulate matter(PM)was monitored while cycling and travelling by bus,car and metro along an assigned route in Lisbon(Portugal),focusing on PM2.5 and PM10(PM with aerodynamic diameter<2.5 and 10μm,respectively)mass concentrations and their chemical composition.In vehicles,the indoor-outdoor interplay was also evaluated.The PM2.5 mean concentrations were 28±5,31±9,34±9 and 38±21μg/m 3 for bus,bicycle,car and metro modes,respectively.Black carbon concentrations when travelling by car were 1.4 to 2.0 times higher than in the other transport modes due to the closer proximity to exhaust emissions.There are marked differences in PM chemical composition depending on transport mode.In particular,Fe was the most abundant component of metro PM,derived from abrasion of rail-wheel-brake interfaces.Enhanced concentrations of Zn and Cu in cars and buses were related with brake and tyre wear particles,which can penetrate into the vehicles.In the motorised transport modes,Fe,Zn,Cu,Ni and K were correlated,evidencing their common traffic-related source.On average,the highest inhaled dose of PM2.5 was observed while cycling(55μg),and the lowest in car travels(17μg).Cyclists inhaled higher doses of PM2.5 due to both higher inhalation rates and longer journey times,with a clear enrichment in mineral elements.The presented results evidence the importance of considering the transport mode in exposure assessment studies.
文摘Bridge in Clouds An aerial photo of the Heshandu Wujiang River Bridge in Guizhou Province,southwest China,on December 29,2020.The bridge,spanning 2000 meters,is a key part of the Meitan-Shiqian Expressway.It was completed on January 3 and will open to traffic in July.
基金This work was supported in part by the Natural Science Foundation of China under Grant 61725103,Grant 91638202,Grant 61801361 and Grant U19B2025,and was supported by“the Fundamental Research Funds for the Central Universities”.
文摘Scheduling schemes assign limited resources to appropriate users,which are critical for wireless network performance.Most current schemes have been designed based on saturated traffic,i.e.,assuming users in networks always have data to transmit.However,the user buffer may sometimes be empty in actual network.Therefore,these algorithms will allocate resources to users having no data to transmit,which results in resource waste.In view of this,we propose new scheduling schemes for onehop and two-hop link scenario with unsaturated traffic.Furthermore,this paper analyzes their key network performance indicators,including the average queue length,average throughput,average delay and outage probability.The two scheduling algorithms avoid scheduling the links whose buffers are empty and thus improve the network resource utilization.For the one-hop link scenario,network provides differentiated services via adjusting the scheduling probabilities of the destination nodes(DNs)with different priorities.Among the DNs with same priority,the node with higher data arrival rate has larger scheduling probability.For the two-hop link scenario,we prioritize the scheduling of relay-to-destination(R-D)link and dynamically adjust the transmission probability of source-to-relay(S-R)link,according to the length of remaining buffer.The experiment results show the effectiveness and advantage of the proposed algorithms.
文摘The modeling of an efficient classifier is a fundamental issue in automatic training involving a large volume of representative data.Hence,automatic classification is a major task that entails the use of training methods capable of assigning classes to data objects by using the input activities presented to learn classes.The recognition of new elements is possible based on predefined classes.Intrusion detection systems suffer from numerous vulnerabilities during analysis and classification of data activities.To overcome this problem,new analysis methods should be derived so as to implement a relevant system to monitor circulated traffic.The main objective of this study is to model and validate a heterogeneous traffic classifier capable of categorizing collected events within networks.The new model is based on a proposed machine learning algorithm that comprises an input layer,a hidden layer,and an output layer.A reliable training algorithm is proposed to optimize the weights,and a recognition algorithm is used to validate the model.Preprocessing is applied to the collected traffic prior to the analysis step.This work aims to describe the mathematical validation of a new machine learning classifier for heterogeneous traffic and anomaly detection.