Opportunistic mobile crowdsensing(MCS)non-intrusively exploits human mobility trajectories,and the participants’smart devices as sensors have become promising paradigms for various urban data acquisition tasks.Howeve...Opportunistic mobile crowdsensing(MCS)non-intrusively exploits human mobility trajectories,and the participants’smart devices as sensors have become promising paradigms for various urban data acquisition tasks.However,in practice,opportunistic MCS has several challenges from both the perspectives of MCS participants and the data platform.On the one hand,participants face uncertainties in conducting MCS tasks,including their mobility and implicit interactions among participants,and participants’economic returns given by the MCS data platform are determined by not only their own actions but also other participants’strategic actions.On the other hand,the platform can only observe the participants’uploaded sensing data that depends on the unknown effort/action exerted by participants to the platform,while,for optimizing its overall objective,the platform needs to properly reward certain participants for incentivizing them to provide high-quality data.To address the challenge of balancing individual incentives and platform objectives in MCS,this paper proposes MARCS,an online sensing policy based on multi-agent deep reinforcement learning(MADRL)with centralized training and decentralized execution(CTDE).Specifically,the interactions between MCS participants and the data platform are modeled as a partially observable Markov game,where participants,acting as agents,use DRL-based policies to make decisions based on local observations,such as task trajectories and platform payments.To align individual and platform goals effectively,the platform leverages Shapley value to estimate the contribution of each participant’s sensed data,using these estimates as immediate rewards to guide agent training.The experimental results on real mobility trajectory datasets indicate that the revenue of MARCS reaches almost 35%,53%,and 100%higher than DDPG,Actor-Critic,and model predictive control(MPC)respectively on the participant side and similar results on the platform side,which show superior performance compared to baselines.展开更多
Remote sensing data acquisition is one of the most essential processes in the field of Earth observation.However,traditional methods to acquire data do not satisfy the requirements of current applications because larg...Remote sensing data acquisition is one of the most essential processes in the field of Earth observation.However,traditional methods to acquire data do not satisfy the requirements of current applications because large-scale data processing is required.To address this issue,this paper proposes a data acquisition framework that carries out remote sensing metadata planning and then realizes the online acquisition of large amounts of data.Firstly,this paper establishes a unified metadata cataloging model and realizes the catalog of metadata in a local database.Secondly,a coverage calculation model is presented,which can show users the data coverage information in a selected geographical region under the data requirements of a specific application.Finally,according to the data retrieval results and the coverage calcula-tion,a machine-to-machine interface is provided to acquire target remote sensing data.Experiments were conducted to verify the availability and practicality of the proposed frame-work,and the results show the strengths and powerful capabilities of our framework by overcoming deficiencies in traditional methods.It also achieved the online automatic acquisi-tion of large-scale heterogeneous remote sensing data,which can provide guidance for remote sensing data acquisition strategies.展开更多
Sensor network synthesis means to select certain variables to be measured, to select suitable sensors, to observe all the important variables, and to get reliable and accurate process data. The steady state online ...Sensor network synthesis means to select certain variables to be measured, to select suitable sensors, to observe all the important variables, and to get reliable and accurate process data. The steady state online data reconciliation can remove the influences of errors in the measurements on the acquired data, and get consistent process data that satisfy the process constraints. These two techniques have been studied often but separately. This paper proposed to integrate these two techniques into a unified system to get better information about the process data. An industrial application of the integrated system to a crude oil distillation unit was also described, where valid process data were obtained and applied for online process optimization system, which led to a profit increase of about four million RMB annually.展开更多
Under the background of urban renewal, this paper re-explores the tourism development modeof Nanluoguxiang historical and cultural block based on online review data, and puts forward correspondingdevelopment strategie...Under the background of urban renewal, this paper re-explores the tourism development modeof Nanluoguxiang historical and cultural block based on online review data, and puts forward correspondingdevelopment strategies. As a cultural label of a city, historical and cultural blocks should be updated first inorder to achieve sustainable development. By using multi-source big data review and qualitative researchmethods, the perception evaluation of tourists in Nanluoguxiang is obtained, and the shortcomings ofcurrent tourism development mode are analyzed. Furthermore, corresponding improvement strategies andsuggestions are put forward, in order to provide some effective ideas for the sustainable development ofhistorical and cultural blocks in the future.展开更多
The fast-growing demand of computational fluid dynamics（CFD） application for computing resources stimulates the development of high performance computing（HPC） and meanwhile raises new requirements for the technolo...The fast-growing demand of computational fluid dynamics（CFD） application for computing resources stimulates the development of high performance computing（HPC） and meanwhile raises new requirements for the technology of parallel application performance monitor and analysis.In response to large-scale and long-time running for the application of CFD,online and scalable performance analysis technology is required to optimize the parallel programs as well as to improve their operational efficiency.As a result,this research implements a scalable infrastructure for online performance analysis on CFD application with homogeneous or heterogeneous system.The infrastructure is part of the parallel application performance monitor and analysis system（PAPMAS） and is composed of two modules which are scalable data transmission module and data storage module.The paper analyzes and elaborates this infrastructure in detail with respect to its design and implementation.Furthermore,some experiments are carried out to verify the rationality and high efficiency of this infrastructure that could be adopted to meet the practical needs.展开更多
Computational psychiatry is an emerging field that not only explores the biological basis of mental illness but also considers the diagnoses and identifies the underlying mechanisms.One of the key strengths of computa...Computational psychiatry is an emerging field that not only explores the biological basis of mental illness but also considers the diagnoses and identifies the underlying mechanisms.One of the key strengths of computational psychiatry is that it may identify patterns in large datasets that are not easily identifiable.This may help researchers develop more effective treatments and interventions for mental health problems.This paper is a narrative review that reviews the literature and produces an artificial intelligence ecosystem for computational psychiatry.The artificial intelligence ecosystem for computational psychiatry includes data acquisition,preparation,modeling,application,and evaluation.This approach allows researchers to integrate data from a variety of sources,such as brain imaging,genetics,and behavioral experiments,to obtain a more complete understanding of mental health conditions.Through the process of data preprocessing,training,and testing,the data that are required for model building can be prepared.By using machine learning,neural networks,artificial intelligence,and other methods,researchers have been able to develop diagnostic tools that can accurately identify mental health conditions based on a patient’s symptoms and other factors.Despite the continuous development and breakthrough of computational psychiatry,it has not yet influenced routine clinical practice and still faces many challenges,such as data availability and quality,biological risks,equity,and data protection.As we move progress in this field,it is vital to ensure that computational psychiatry remains accessible and inclusive so that all researchers may contribute to this significant and exciting field.展开更多
With the ever increasing complexity of industrial systems,model-based control has encountered difficulties and is facing problems,while the interest in data-based control has been booming.This paper gives an overview ...With the ever increasing complexity of industrial systems,model-based control has encountered difficulties and is facing problems,while the interest in data-based control has been booming.This paper gives an overview of data-based control,which divides it into two subfields,intelligent modeling and direct controller design.In the two subfields,some important methods concerning data-based control are intensively investigated.Within the framework of data-based modeling,main modeling technologies and control strategies are discussed,and then fundamental concepts and various algorithms are presented for the design of a data-based controller.Finally,some remaining challenges are suggested.展开更多
We proposed a generalized adaptive learning rate (GALR) PCA algorithm, which could be guaranteed that the algorithm’s convergence process would not be affected by the selection of the initial value. Using the determi...We proposed a generalized adaptive learning rate (GALR) PCA algorithm, which could be guaranteed that the algorithm’s convergence process would not be affected by the selection of the initial value. Using the deterministic discrete time (DDT) method, we gave the upper and lower bounds of the algorithm and proved the global convergence. Numerical experiments had also verified our theory, and the algorithm is effective for both online and offline data. We found that choosing different initial vectors will affect the convergence speed, and the initial vector could converge to the second or third eigenvectors by satisfying some exceptional conditions.展开更多
Background OneGeology is an initiative of Geological Survey Organisations(GSO)around the globe that dates back to Brighton,UK in 2007.Since then OneGeology has been a leader in developing geological online map data us...Background OneGeology is an initiative of Geological Survey Organisations(GSO)around the globe that dates back to Brighton,UK in 2007.Since then OneGeology has been a leader in developing geological online map data using a new international standard–a geological exchange language known as the‘GeoSciML’.Currently version 3.2 exists,which enables instant interoperability of the data.Increased use of this new language allows geological data to be shared and integrated across the planet with other organisations.In autumn 2013 OneGeology was transformed into a Consortium with a clearly defined governance structure,making its structure more official.展开更多
In strong light environments,images often appear overexposed,which seriously impacts the accuracy of target detection.Most existing research,however,requires additional modules to assist in detection,which affects the...In strong light environments,images often appear overexposed,which seriously impacts the accuracy of target detection.Most existing research,however,requires additional modules to assist in detection,which affects the timeliness of the detection process.To address the issues of reduced target detection accuracy and timeliness in overexposed environments,this paper proposes a realtime anti-light target detection improvement algorithm based on you-only-look-once v8n(YOLO v8n),focusing on enhancing the model’s ability to extract features from overexposed images without the need for additional modules.Firstly,online overexposure enhancement technology is integrated into model training to simulate overexposed images produced in overexposed environments,enhancing the model’s robustness in detecting overexposed environments.Deformable convolution networks v2 is used to improve the cross-stage partial bottleneck with two convolutions layer,addressing the issue of traditional convolution’s poor feature extraction performance for overexposed images,thereby aiding the model in capturing targets with weakened or missing features and enhancing the model’s ability to construct the geometric shape of targets.Secondly,large separable kernel attention is introduced to enhance the spatial pyramid pooling fast layer,strengthening the model’s overall connectivity for targets with missing features.Finally,distance intersection over union is utilized to optimize the detection accuracy of overlapping targets in overexposed environments.The experimental results show that,compared to the original model,the mAP50 and mAP50–95 of the model designed in this paper are improved by 23.2%and 15.7%,respectively,and the model size only increases by 0.3 M.While improving detection accuracy,the lightweight requirements for actual deployment are also met.展开更多
This article presents and analyses the modular architecture and capabilities of CODE-DE(Copernicus Data and Exploitation Platform–Deutschland,www.code-de.org),the integrated German operational environment for accessi...This article presents and analyses the modular architecture and capabilities of CODE-DE(Copernicus Data and Exploitation Platform–Deutschland,www.code-de.org),the integrated German operational environment for accessing and processing Copernicus data and products,as well as the methodology to establish and operate the system.Since March 2017,CODE-DE has been online with access to Sentinel-1 and Sentinel-2 data,to Sentinel-3 data shortly after this time,and since March 2019 with access to Sentinel-5P data.These products are available and accessed by 1,682 registered users as of March 2019.During this period 654,895 products were downloaded and a global catalogue was continuously updated,featuring a data volume of 814 TByte based on a rolling archive concept supported by a reload mechanism from a long-term archive.Since November 2017,the element for big data processing has been operational,where registered users can process and analyse data themselves specifically assisted by methods for value-added product generation.Utilizing 195,467 core and 696,406 memory hours,982,948 products of different applications were fully automatically generated in the cloud environment and made available as of March 2019.Special features include an improved visualization of available Sentinel-2 products,which are presented within the catalogue client at full 10 m resolution.展开更多
Through a case study on 24 Taobao villages in Guangzhou,this paper analyzes the relationship between the spatial distribution characteristics and influencing factors of Taobao villages using the online data mining met...Through a case study on 24 Taobao villages in Guangzhou,this paper analyzes the relationship between the spatial distribution characteristics and influencing factors of Taobao villages using the online data mining methodology,and compares e-commerce-based industry clusters with traditional industry clusters.The result shows that Taobao villages in Guangzhou are mainly distributed in peripheral areas of the central city,with low population and employment density; villages running the same kind of business present the trend of concentration.And the formation of Taobao villages is highly relevant to the distribution of factories,wholesale markets,express services,and low-rent housing,as well as the learning and demonstration effect among subjects.It further proves that,under the influence of e-commerce,the importance of economies of scale and economies of scope brought by geographic proximity has been weakened,while the importance of interaction and communication effect among subjects have been obviously strengthened.展开更多
基金sponsored by Qinglan Project of Jiangsu Province,and Jiangsu Provincial Key Research and Development Program(No.BE2020084-1).
文摘Opportunistic mobile crowdsensing(MCS)non-intrusively exploits human mobility trajectories,and the participants’smart devices as sensors have become promising paradigms for various urban data acquisition tasks.However,in practice,opportunistic MCS has several challenges from both the perspectives of MCS participants and the data platform.On the one hand,participants face uncertainties in conducting MCS tasks,including their mobility and implicit interactions among participants,and participants’economic returns given by the MCS data platform are determined by not only their own actions but also other participants’strategic actions.On the other hand,the platform can only observe the participants’uploaded sensing data that depends on the unknown effort/action exerted by participants to the platform,while,for optimizing its overall objective,the platform needs to properly reward certain participants for incentivizing them to provide high-quality data.To address the challenge of balancing individual incentives and platform objectives in MCS,this paper proposes MARCS,an online sensing policy based on multi-agent deep reinforcement learning(MADRL)with centralized training and decentralized execution(CTDE).Specifically,the interactions between MCS participants and the data platform are modeled as a partially observable Markov game,where participants,acting as agents,use DRL-based policies to make decisions based on local observations,such as task trajectories and platform payments.To align individual and platform goals effectively,the platform leverages Shapley value to estimate the contribution of each participant’s sensed data,using these estimates as immediate rewards to guide agent training.The experimental results on real mobility trajectory datasets indicate that the revenue of MARCS reaches almost 35%,53%,and 100%higher than DDPG,Actor-Critic,and model predictive control(MPC)respectively on the participant side and similar results on the platform side,which show superior performance compared to baselines.
基金supported by the Strategic Priority Research Program of the Chinese Academy of Sciences[grant number XDA19020201]。
文摘Remote sensing data acquisition is one of the most essential processes in the field of Earth observation.However,traditional methods to acquire data do not satisfy the requirements of current applications because large-scale data processing is required.To address this issue,this paper proposes a data acquisition framework that carries out remote sensing metadata planning and then realizes the online acquisition of large amounts of data.Firstly,this paper establishes a unified metadata cataloging model and realizes the catalog of metadata in a local database.Secondly,a coverage calculation model is presented,which can show users the data coverage information in a selected geographical region under the data requirements of a specific application.Finally,according to the data retrieval results and the coverage calcula-tion,a machine-to-machine interface is provided to acquire target remote sensing data.Experiments were conducted to verify the availability and practicality of the proposed frame-work,and the results show the strengths and powerful capabilities of our framework by overcoming deficiencies in traditional methods.It also achieved the online automatic acquisi-tion of large-scale heterogeneous remote sensing data,which can provide guidance for remote sensing data acquisition strategies.
文摘Sensor network synthesis means to select certain variables to be measured, to select suitable sensors, to observe all the important variables, and to get reliable and accurate process data. The steady state online data reconciliation can remove the influences of errors in the measurements on the acquired data, and get consistent process data that satisfy the process constraints. These two techniques have been studied often but separately. This paper proposed to integrate these two techniques into a unified system to get better information about the process data. An industrial application of the integrated system to a crude oil distillation unit was also described, where valid process data were obtained and applied for online process optimization system, which led to a profit increase of about four million RMB annually.
基金National Social Science Foundation Project of China(21FYSB048)Humanities and Social Sciences Research Project of the Ministry of Education(20YJAZH1010).
文摘Under the background of urban renewal, this paper re-explores the tourism development modeof Nanluoguxiang historical and cultural block based on online review data, and puts forward correspondingdevelopment strategies. As a cultural label of a city, historical and cultural blocks should be updated first inorder to achieve sustainable development. By using multi-source big data review and qualitative researchmethods, the perception evaluation of tourists in Nanluoguxiang is obtained, and the shortcomings ofcurrent tourism development mode are analyzed. Furthermore, corresponding improvement strategies andsuggestions are put forward, in order to provide some effective ideas for the sustainable development ofhistorical and cultural blocks in the future.
基金Aeronautical Science Foundation of China(2010ZA04001)National Natural Science Foundation of China (61073013,90818024)
文摘The fast-growing demand of computational fluid dynamics（CFD） application for computing resources stimulates the development of high performance computing（HPC） and meanwhile raises new requirements for the technology of parallel application performance monitor and analysis.In response to large-scale and long-time running for the application of CFD,online and scalable performance analysis technology is required to optimize the parallel programs as well as to improve their operational efficiency.As a result,this research implements a scalable infrastructure for online performance analysis on CFD application with homogeneous or heterogeneous system.The infrastructure is part of the parallel application performance monitor and analysis system（PAPMAS） and is composed of two modules which are scalable data transmission module and data storage module.The paper analyzes and elaborates this infrastructure in detail with respect to its design and implementation.Furthermore,some experiments are carried out to verify the rationality and high efficiency of this infrastructure that could be adopted to meet the practical needs.
文摘Computational psychiatry is an emerging field that not only explores the biological basis of mental illness but also considers the diagnoses and identifies the underlying mechanisms.One of the key strengths of computational psychiatry is that it may identify patterns in large datasets that are not easily identifiable.This may help researchers develop more effective treatments and interventions for mental health problems.This paper is a narrative review that reviews the literature and produces an artificial intelligence ecosystem for computational psychiatry.The artificial intelligence ecosystem for computational psychiatry includes data acquisition,preparation,modeling,application,and evaluation.This approach allows researchers to integrate data from a variety of sources,such as brain imaging,genetics,and behavioral experiments,to obtain a more complete understanding of mental health conditions.Through the process of data preprocessing,training,and testing,the data that are required for model building can be prepared.By using machine learning,neural networks,artificial intelligence,and other methods,researchers have been able to develop diagnostic tools that can accurately identify mental health conditions based on a patient’s symptoms and other factors.Despite the continuous development and breakthrough of computational psychiatry,it has not yet influenced routine clinical practice and still faces many challenges,such as data availability and quality,biological risks,equity,and data protection.As we move progress in this field,it is vital to ensure that computational psychiatry remains accessible and inclusive so that all researchers may contribute to this significant and exciting field.
基金This work was supported by the National Natural Science Foundation of China(Grant Nos.60874013,60953001 and 61034002).
文摘With the ever increasing complexity of industrial systems,model-based control has encountered difficulties and is facing problems,while the interest in data-based control has been booming.This paper gives an overview of data-based control,which divides it into two subfields,intelligent modeling and direct controller design.In the two subfields,some important methods concerning data-based control are intensively investigated.Within the framework of data-based modeling,main modeling technologies and control strategies are discussed,and then fundamental concepts and various algorithms are presented for the design of a data-based controller.Finally,some remaining challenges are suggested.
文摘We proposed a generalized adaptive learning rate (GALR) PCA algorithm, which could be guaranteed that the algorithm’s convergence process would not be affected by the selection of the initial value. Using the deterministic discrete time (DDT) method, we gave the upper and lower bounds of the algorithm and proved the global convergence. Numerical experiments had also verified our theory, and the algorithm is effective for both online and offline data. We found that choosing different initial vectors will affect the convergence speed, and the initial vector could converge to the second or third eigenvectors by satisfying some exceptional conditions.
文摘Background OneGeology is an initiative of Geological Survey Organisations(GSO)around the globe that dates back to Brighton,UK in 2007.Since then OneGeology has been a leader in developing geological online map data using a new international standard–a geological exchange language known as the‘GeoSciML’.Currently version 3.2 exists,which enables instant interoperability of the data.Increased use of this new language allows geological data to be shared and integrated across the planet with other organisations.In autumn 2013 OneGeology was transformed into a Consortium with a clearly defined governance structure,making its structure more official.
基金supported by the Natural Science Foundation of Guangdong Province(Grant No.2022A1515010011)the Basic and Theoretical Science and Technology Programme of Jiangmen City(Grant No.2023JC01020)in 2023。
文摘In strong light environments,images often appear overexposed,which seriously impacts the accuracy of target detection.Most existing research,however,requires additional modules to assist in detection,which affects the timeliness of the detection process.To address the issues of reduced target detection accuracy and timeliness in overexposed environments,this paper proposes a realtime anti-light target detection improvement algorithm based on you-only-look-once v8n(YOLO v8n),focusing on enhancing the model’s ability to extract features from overexposed images without the need for additional modules.Firstly,online overexposure enhancement technology is integrated into model training to simulate overexposed images produced in overexposed environments,enhancing the model’s robustness in detecting overexposed environments.Deformable convolution networks v2 is used to improve the cross-stage partial bottleneck with two convolutions layer,addressing the issue of traditional convolution’s poor feature extraction performance for overexposed images,thereby aiding the model in capturing targets with weakened or missing features and enhancing the model’s ability to construct the geometric shape of targets.Secondly,large separable kernel attention is introduced to enhance the spatial pyramid pooling fast layer,strengthening the model’s overall connectivity for targets with missing features.Finally,distance intersection over union is utilized to optimize the detection accuracy of overlapping targets in overexposed environments.The experimental results show that,compared to the original model,the mAP50 and mAP50–95 of the model designed in this paper are improved by 23.2%and 15.7%,respectively,and the model size only increases by 0.3 M.While improving detection accuracy,the lightweight requirements for actual deployment are also met.
基金funding from the German Federal Ministry of Transport and Digital Infrastructure(BMVI).
文摘This article presents and analyses the modular architecture and capabilities of CODE-DE(Copernicus Data and Exploitation Platform–Deutschland,www.code-de.org),the integrated German operational environment for accessing and processing Copernicus data and products,as well as the methodology to establish and operate the system.Since March 2017,CODE-DE has been online with access to Sentinel-1 and Sentinel-2 data,to Sentinel-3 data shortly after this time,and since March 2019 with access to Sentinel-5P data.These products are available and accessed by 1,682 registered users as of March 2019.During this period 654,895 products were downloaded and a global catalogue was continuously updated,featuring a data volume of 814 TByte based on a rolling archive concept supported by a reload mechanism from a long-term archive.Since November 2017,the element for big data processing has been operational,where registered users can process and analyse data themselves specifically assisted by methods for value-added product generation.Utilizing 195,467 core and 696,406 memory hours,982,948 products of different applications were fully automatically generated in the cloud environment and made available as of March 2019.Special features include an improved visualization of available Sentinel-2 products,which are presented within the catalogue client at full 10 m resolution.
基金supported by the Sub-Projec ts in the National Science&Technology Pillar Program(2013BAJ13B03-02)
文摘Through a case study on 24 Taobao villages in Guangzhou,this paper analyzes the relationship between the spatial distribution characteristics and influencing factors of Taobao villages using the online data mining methodology,and compares e-commerce-based industry clusters with traditional industry clusters.The result shows that Taobao villages in Guangzhou are mainly distributed in peripheral areas of the central city,with low population and employment density; villages running the same kind of business present the trend of concentration.And the formation of Taobao villages is highly relevant to the distribution of factories,wholesale markets,express services,and low-rent housing,as well as the learning and demonstration effect among subjects.It further proves that,under the influence of e-commerce,the importance of economies of scale and economies of scope brought by geographic proximity has been weakened,while the importance of interaction and communication effect among subjects have been obviously strengthened.
