In order to estimate vehicular queue length at signalized intersections accurately and overcome the shortcomings and restrictions of existing studies especially those based on shockwave theory,a new methodology is pre...In order to estimate vehicular queue length at signalized intersections accurately and overcome the shortcomings and restrictions of existing studies especially those based on shockwave theory,a new methodology is presented for estimating vehicular queue length using data from both point detectors and probe vehicles. The methodology applies the shockwave theory to model queue evolution over time and space. Using probe vehicle locations and times as well as point detector measured traffic states,analytical formulations for calculating the maximum and minimum( residual) queue length are developed. The proposed methodology is verified using ground truth data collected from numerical experiments conducted in Shanghai,China. It is found that the methodology has a mean absolute percentage error of 17. 09%,which is reasonably effective in estimating the queue length at traffic signalized intersections. Limitations of the proposed models and algorithms are also discussed in the paper.展开更多
Vehicle model recognition(VMR)benefits the parking,surveillance,and tolling system by automatically identifying the exact make and model of the passing vehicles.Edge computing technology enables the roadside facilitie...Vehicle model recognition(VMR)benefits the parking,surveillance,and tolling system by automatically identifying the exact make and model of the passing vehicles.Edge computing technology enables the roadside facilities and mobile cameras to achcieve VMR in realtime.Current work generally relies on a specific view of the vehicle or requires huge calculation capability to deploy the end-to-end deep learning network.This paper proposes a lightweight two-stage identification method based on object detection and image retrieval techniques,which empowers us the ability of recognizing the vehicle model from an arbitrary view.The first-stage model estimates the vehicle posture using object detection and similarity matching,which is cost-efficient and suitable to be programmed in the edge computing devices;the second-stage model retrieves the vehicle’s label from the dataset based on gradient boosting decision tree(GBDT)algorithm and VGGNet,which is flexible to the changing dataset.More than 8000 vehicle images are labeled with their components’information,such as headlights,windows,wheels,and logos.The YOLO network is employed to detect and localize the typical components of a vehicle.The vehicle postures are estimated by the spatial relationship between different segmented components.Due to the variety of the perspectives,a 7-dimensional vector is defined to represent the relative posture of the vehicle and screen out the images with a similar photographic perspective.Two algorithms are used to extract the features from each image patch:(1)the scale invariant feature transform(SIFT)combined with the bag-of-features(BoF)and(2)pre-trained deep neural network.The GBDT is applied to evaluate the weight of each component regarding its impact on VMR.The descriptors of each component are then aggregated to retrieve the best matching image from the database.The results showed its advantages in terms of accuracy(89.2%)and efficiency,demonstrating the vast potential of applying this method to large-scale vehicle model recognition.展开更多
Safe and aesthetic interaction between horizontal and vertical alignment may significantly occur when they are combined or closed to each other resulting in safety problems.Previous researches have been limited to foc...Safe and aesthetic interaction between horizontal and vertical alignment may significantly occur when they are combined or closed to each other resulting in safety problems.Previous researches have been limited to focusing on qualitative analysis,which are difficult to implement in the design.To assess the quantitative impact of the combination equilibrium of horizontal and sag vertical curves on safety,KNN,SVR and KNN-SVR machine learning methods were applied for model training to analyze the influence of alignment combination of the horizontal curve(HC)and the sag vertical curve(SVC)on accidents.The highway alignment(a total of 1208 km),the traffic data and accident data from 2011 to 2018 of six interstate roads in Washington,D.C.have been used to train the models.The combination equilibrium of horizontal and sag vertical curves is expressed by the variables such as the radius of the horizontal and vertical curves,the length of the horizontal and vertical curves and the dislocation of horizontal and sag vertical curves.KNN model,SVR model,and KNN-SVR model were built by training the variables as well as the accident rate per 100,000,000 vehicle kilometers.The results show that for the HC-SVC alignment combination,the KNN-SVR model has higher accuracy in predicting the accident rate.At the same time,this paper also suggests the value range of the variables when the horizontal curve radius is small.The research conclusions can provide a reference for the subsequent quantitative optimization design and safety improvement of horizontal and vertical alignment combination.展开更多
A series of Ln^3＋（Ln^3＋= Er^3＋/Dy^3＋） ions doped Na2 NbAlO5（NNAO） phosphors were synthesized by solidstate method. The Er^3＋ and Dy^3＋ ions doped phosphors were characterized by XRD, photoluminescence（PL） ...A series of Ln^3＋（Ln^3＋= Er^3＋/Dy^3＋） ions doped Na2 NbAlO5（NNAO） phosphors were synthesized by solidstate method. The Er^3＋ and Dy^3＋ ions doped phosphors were characterized by XRD, photoluminescence（PL） and decay profiles. The Ln^3＋-doped samples are consistent with the pure NNAO phase which is analyzed by the X-ray diffraction result. The PL graphs show that the intensity of luminescence increases with the increasing doping concentrations up to their critical certain values and then decreases at higher concentrations due to the concentration quenching effect of Er^3＋/Dy^3＋ ions. The energy level diagrams containing the positions of 4 f and 5 d energy levels of Er^3＋ and Dy^3＋ ions have been established and studied. In addition, under the ultraviolet light, the prepared NNAO：xLn^3＋（Ln^3＋=Er^3＋/Dy^3＋） phosphors show the characteristic green（Er^3＋）, cyan（Dy^3＋） emission, respectively. Under the excitation of 365 nm,the quantum efficiencies of NNAO：0.01 Er^3＋ and NNAO：0.03 Dy^3＋ phosphors are measured to be 61.7% and72.2%, respectively. The obtained results indicate that the new NNAO：xLn^3＋（Ln^3＋=Er^3＋/Dy^3＋） phosphors are promising applications in white-light emitting diodes field.展开更多
Quantum computing,a field utilizing the principles of quantum mechanics,promises great advancements across various industries.This survey paper is focused on the burgeoning intersection of quantum computing and intell...Quantum computing,a field utilizing the principles of quantum mechanics,promises great advancements across various industries.This survey paper is focused on the burgeoning intersection of quantum computing and intelligent transportation systems,exploring its potential to transform areas such as traffic optimization,logistics,routing,and autonomous vehicles.By examining current research efforts,challenges,and future directions,this survey aims to provide a comprehensive overview of how quantum computing could affect the future of transportation.展开更多
At the intersection of artificial intelligence and urban development,this paper unveils the pivotal role of Foundation Models(FMs)in revolutionizing Intelligent Transportation Systems(ITS).Against the backdrop of esca...At the intersection of artificial intelligence and urban development,this paper unveils the pivotal role of Foundation Models(FMs)in revolutionizing Intelligent Transportation Systems(ITS).Against the backdrop of escalating urbanization and environmental concerns,we rigorously assess how FMs-spanning large language models,vision-language models,large multimodal models,etc.-can redefine urban mobility paradigms.Our discussion extends to the potential of modular,scalable models and strategic public-private partnerships in facilitating seamless integration.Through a comprehensive literature review and theoretical framework,this paper underscores the significant role of FMs in steering the future of transportation towards unprecedented levels of intelligence and responsiveness.The insights offered aim to guide policymakers,engineers,and researchers in the ethical and effective adoption of FMs,paving the way for a new era in transportation systems.展开更多
基金Sponsored by the National Natural Science Foundation of China(Grant No.51138003)
文摘In order to estimate vehicular queue length at signalized intersections accurately and overcome the shortcomings and restrictions of existing studies especially those based on shockwave theory,a new methodology is presented for estimating vehicular queue length using data from both point detectors and probe vehicles. The methodology applies the shockwave theory to model queue evolution over time and space. Using probe vehicle locations and times as well as point detector measured traffic states,analytical formulations for calculating the maximum and minimum( residual) queue length are developed. The proposed methodology is verified using ground truth data collected from numerical experiments conducted in Shanghai,China. It is found that the methodology has a mean absolute percentage error of 17. 09%,which is reasonably effective in estimating the queue length at traffic signalized intersections. Limitations of the proposed models and algorithms are also discussed in the paper.
基金supported by the Scientific Research Project of Shanghai Science and Technology Commission of China(No.21DZ1200601)the National Natural Science Foundation of China(No.NSFC52108411).
文摘Vehicle model recognition(VMR)benefits the parking,surveillance,and tolling system by automatically identifying the exact make and model of the passing vehicles.Edge computing technology enables the roadside facilities and mobile cameras to achcieve VMR in realtime.Current work generally relies on a specific view of the vehicle or requires huge calculation capability to deploy the end-to-end deep learning network.This paper proposes a lightweight two-stage identification method based on object detection and image retrieval techniques,which empowers us the ability of recognizing the vehicle model from an arbitrary view.The first-stage model estimates the vehicle posture using object detection and similarity matching,which is cost-efficient and suitable to be programmed in the edge computing devices;the second-stage model retrieves the vehicle’s label from the dataset based on gradient boosting decision tree(GBDT)algorithm and VGGNet,which is flexible to the changing dataset.More than 8000 vehicle images are labeled with their components’information,such as headlights,windows,wheels,and logos.The YOLO network is employed to detect and localize the typical components of a vehicle.The vehicle postures are estimated by the spatial relationship between different segmented components.Due to the variety of the perspectives,a 7-dimensional vector is defined to represent the relative posture of the vehicle and screen out the images with a similar photographic perspective.Two algorithms are used to extract the features from each image patch:(1)the scale invariant feature transform(SIFT)combined with the bag-of-features(BoF)and(2)pre-trained deep neural network.The GBDT is applied to evaluate the weight of each component regarding its impact on VMR.The descriptors of each component are then aggregated to retrieve the best matching image from the database.The results showed its advantages in terms of accuracy(89.2%)and efficiency,demonstrating the vast potential of applying this method to large-scale vehicle model recognition.
基金supported by Washington DOT for traffic crash and road design datasponsored by the Natural Science Foundation of Guangdong,project number 2022A1515011974+1 种基金the Guangdong Provincial Key Laboratory of Modern Civil Engineering Technology Foundation,project number 2021B1212040003the National Natural Science Founda-tion of China,project number 51878297.
文摘Safe and aesthetic interaction between horizontal and vertical alignment may significantly occur when they are combined or closed to each other resulting in safety problems.Previous researches have been limited to focusing on qualitative analysis,which are difficult to implement in the design.To assess the quantitative impact of the combination equilibrium of horizontal and sag vertical curves on safety,KNN,SVR and KNN-SVR machine learning methods were applied for model training to analyze the influence of alignment combination of the horizontal curve(HC)and the sag vertical curve(SVC)on accidents.The highway alignment(a total of 1208 km),the traffic data and accident data from 2011 to 2018 of six interstate roads in Washington,D.C.have been used to train the models.The combination equilibrium of horizontal and sag vertical curves is expressed by the variables such as the radius of the horizontal and vertical curves,the length of the horizontal and vertical curves and the dislocation of horizontal and sag vertical curves.KNN model,SVR model,and KNN-SVR model were built by training the variables as well as the accident rate per 100,000,000 vehicle kilometers.The results show that for the HC-SVC alignment combination,the KNN-SVR model has higher accuracy in predicting the accident rate.At the same time,this paper also suggests the value range of the variables when the horizontal curve radius is small.The research conclusions can provide a reference for the subsequent quantitative optimization design and safety improvement of horizontal and vertical alignment combination.
基金Project supported by the Science and Technology Special Development in Guangdong Province of China(2016A010103029)the Science and Technology Project of Guangzhou of China(201607010179)
文摘A series of Ln^3＋（Ln^3＋= Er^3＋/Dy^3＋） ions doped Na2 NbAlO5（NNAO） phosphors were synthesized by solidstate method. The Er^3＋ and Dy^3＋ ions doped phosphors were characterized by XRD, photoluminescence（PL） and decay profiles. The Ln^3＋-doped samples are consistent with the pure NNAO phase which is analyzed by the X-ray diffraction result. The PL graphs show that the intensity of luminescence increases with the increasing doping concentrations up to their critical certain values and then decreases at higher concentrations due to the concentration quenching effect of Er^3＋/Dy^3＋ ions. The energy level diagrams containing the positions of 4 f and 5 d energy levels of Er^3＋ and Dy^3＋ ions have been established and studied. In addition, under the ultraviolet light, the prepared NNAO：xLn^3＋（Ln^3＋=Er^3＋/Dy^3＋） phosphors show the characteristic green（Er^3＋）, cyan（Dy^3＋） emission, respectively. Under the excitation of 365 nm,the quantum efficiencies of NNAO：0.01 Er^3＋ and NNAO：0.03 Dy^3＋ phosphors are measured to be 61.7% and72.2%, respectively. The obtained results indicate that the new NNAO：xLn^3＋（Ln^3＋=Er^3＋/Dy^3＋） phosphors are promising applications in white-light emitting diodes field.
文摘Quantum computing,a field utilizing the principles of quantum mechanics,promises great advancements across various industries.This survey paper is focused on the burgeoning intersection of quantum computing and intelligent transportation systems,exploring its potential to transform areas such as traffic optimization,logistics,routing,and autonomous vehicles.By examining current research efforts,challenges,and future directions,this survey aims to provide a comprehensive overview of how quantum computing could affect the future of transportation.
文摘At the intersection of artificial intelligence and urban development,this paper unveils the pivotal role of Foundation Models(FMs)in revolutionizing Intelligent Transportation Systems(ITS).Against the backdrop of escalating urbanization and environmental concerns,we rigorously assess how FMs-spanning large language models,vision-language models,large multimodal models,etc.-can redefine urban mobility paradigms.Our discussion extends to the potential of modular,scalable models and strategic public-private partnerships in facilitating seamless integration.Through a comprehensive literature review and theoretical framework,this paper underscores the significant role of FMs in steering the future of transportation towards unprecedented levels of intelligence and responsiveness.The insights offered aim to guide policymakers,engineers,and researchers in the ethical and effective adoption of FMs,paving the way for a new era in transportation systems.
