Qinghai-Tibet Plateau lakes are important carriers of water resources in the‘Asian’s Water Tower’,and it is of great significance to grasp the spatial distribution of plateau lakes for the climate,ecological enviro...Qinghai-Tibet Plateau lakes are important carriers of water resources in the‘Asian’s Water Tower’,and it is of great significance to grasp the spatial distribution of plateau lakes for the climate,ecological environment,and regional water cycle.However,the differences in spatial-spectral characteristics of various types of plateau lakes,and the complex background information of plateau both influence the extraction effect of lakes.Therefore,it is a great challenge to completely and effectively extract plateau lakes.In this study,we proposed a multiscale contextual information aggregation network,termed MSCANet,to automatically extract Plateau lake regions.It consists of three main components:a multiscale lake feature encoder,a feature decoder,and a Multicore Pyramid Pooling Module(MPPM).The multiscale lake feature encoder suppressed noise interference to capture multiscale spatial-spectral information from heterogeneous scenes.The MPPM module aggregated the contextual information of various lakes globally.We applied the MSCANet to the lake extraction of the Qinghai-Tibet Plateau based on Google data;additionally,comparative experiments showed that the MSCANet proposed had obvious improvement in lake detection accuracy and morphological integrity.Finally,we transferred the pre-trained optimal model to the Landsat-8 and Sentinel-2A dataset to verify the generalization of the MSCANet.展开更多
With the frequent occurrences of emergency events,emergency decision making(EDM)plays an increasingly significant role in coping with such situations and has become an important and challenging research area in recent...With the frequent occurrences of emergency events,emergency decision making(EDM)plays an increasingly significant role in coping with such situations and has become an important and challenging research area in recent times.It is essential for decision makers to make reliable and reasonable emergency decisions within a short span of time,since inappropriate decisions may result in enormous economic losses and social disorder.To handle emergency effectively and quickly,this paper proposes a new EDM method based on the novel concept of q-rung orthopair fuzzy rough(q-ROPR)set.A novel list of q-ROFR aggregation information,detailed description of the fundamental characteristics of the developed aggregation operators and the q-ROFR entropy measure that determine the unknown weight information of decision makers as well as the criteria weights are specified.Further an algorithm is given to tackle the uncertain scenario in emergency to give reliable and reasonable emergency decisions.By using proposed list of q-ROFR aggregation information all emergency alternatives are ranked to get the optimal one.Besides this,the q-ROFR entropy measure method is used to determine criteria and experts’weights objectively in the EDM process.Finally,through an illustrative example of COVID-19 analysis is compared with existing EDM methods.The results verify the effectiveness and practicability of the proposed methodology.展开更多
We proposed an Intemet resource aggregation platform based on semantic web. The platform includes an Web Ontology Language（OWL） ontology design toolkit（VO-Editor） and a selective inference algorithm engine so that...We proposed an Intemet resource aggregation platform based on semantic web. The platform includes an Web Ontology Language（OWL） ontology design toolkit（VO-Editor） and a selective inference algorithm engine so that it can visually editing ontology and using novel selective reasoning for information aggregation. We introduce the VO-Editor and the principle of selective inference algorithm. At last a case of budget travel system is used to interpret the approach of Internet resources aggregation by this platform.展开更多
A kind of single linked lists named aggregative chain is introduced to the algorithm, thus improving the architecture of FP tree. The new FP tree is a one-way tree and only the pointers that point its parent at each n...A kind of single linked lists named aggregative chain is introduced to the algorithm, thus improving the architecture of FP tree. The new FP tree is a one-way tree and only the pointers that point its parent at each node are kept. Route information of different nodes in a same item are compressed into aggregative chains so that the frequent patterns will be produced in aggregative chains without generating node links and conditional pattern bases. An example of Web key words retrieval is given to analyze and verify the frequent pattern algorithm in this paper.展开更多
The maximal entropy ordered weighted averaging （ME-OWA） operator is used to aggregate metasearch engine results, and its newly analytical solution is also applied. Within the current context of the OWA operator, the...The maximal entropy ordered weighted averaging （ME-OWA） operator is used to aggregate metasearch engine results, and its newly analytical solution is also applied. Within the current context of the OWA operator, the methods for aggregating metasearch engine results are divided into two kinds. One has a unique solution, and the other has multiple solutions. The proposed method not only has crisp weights, but also provides multiple aggregation results for decision makers to choose from. In order to prove the application of the ME-OWA operator method, under the context of aggregating metasearch engine results, an example is given, which shows the results obtained by the ME-OWA operator method and the minimax linear programming （ minimax-LP ） method. Comparison between these two methods are also made. The results show that the ME-OWA operator has nearly the same aggregation results as those of the minimax-LP method.展开更多
Accurate and reliable fault diagnosis is critical for secure operation in complex smart power systems.While graph neural networks show promise for this task,existing methods often neglect the long-tailed distribution ...Accurate and reliable fault diagnosis is critical for secure operation in complex smart power systems.While graph neural networks show promise for this task,existing methods often neglect the long-tailed distribution inherent in real-world grid fault data and fail to provide reliability estimates for their decisions.To address these dual challenges,we propose a novel multi-expert collaboration uncertainty-aware power fault recognition framework with cross-view graph learning.Its core innovations are two synergistic modules:(1)The infographics aggregation module tackles the long-tail problem by learning robust graph-level representations.It employs an information-driven optimization loss within a contrastive graph architecture,explicitly preserving global invariance and local structural information across diverse(including rare)fault states.This ensures balanced representation learning for both the head and tail classes.(2)The multi-expert reliable decision module addresses prediction uncertainty.It trains individual expert classifiers using the Dirichlet distribution to explicitly model the credibility(uncertainty)of each expert’s decision.Crucially,a complementary collaboration rule based on evidence theory dynamically integrates these experts.This rule generates active weights for expert participation,prioritizing more certain experts and fusing their evidence to produce a final decision with a quantifiable reliability estimate.Collaboratively,these modules enable reliable diagnosis under data imbalance:The Infographics Module provides discriminative representations for all fault types,especially tail classes,while the Multi-Expert Module leverages these representations to make decisions with explicit uncertainty quantification.This synergy significantly improves both the accuracy and the reliability of fault recognition,particularly for rare or ambiguous grid conditions.Ultimately,extensive experiment evaluations on the four datasets reveal that the proposed method outperforms the state-of-the-art methods in the fault diagnosis of smart grids,in terms of accuracy,precision,f score and recall.展开更多
Exploring structural characteristics implied in initialdecision making information is an important issue in the process of aggregation. In this paper we provide a new family of aggregation operator called density weig...Exploring structural characteristics implied in initialdecision making information is an important issue in the process of aggregation. In this paper we provide a new family of aggregation operator called density weighted averaging operator（abbreviated as DWA operator）, which carries out the aggregation by classification. In this case, not only the hidden structural characteristics can be identified, some commonly known aggregation operators can also be incorporated into the function of the DWA operator. We further discuss the basic properties of this new operator, such as commutativity, idempotency, boundedness and monotonicity withcertain condition. Afterwards, two important issues related to the DWA operator are investigated, including the arguments partition and the determination of density weights. At last a numerical example regarding performance evaluation of employees is developed to illustrate the using of this new operator.展开更多
In this study, a new method for a comprehensive evaluation of air quality in urban agglomerations was developed based on a prototype used to solve the spatial Steiner-Weber point. With this method, the air quality inf...In this study, a new method for a comprehensive evaluation of air quality in urban agglomerations was developed based on a prototype used to solve the spatial Steiner-Weber point. With this method, the air quality information of each city in the city group is aggregated into an optimal gathering point, and then the air quality of the city group is then dynamically evaluated each year. According to the relevant data of the China Statistical Yearbook 2018, we applied this method to aggregate the air quality indices of the major cities in the Beijing-Tianjin-Hebei urban agglomeration from 2014 to 2017. Using the plant growth simulation algorithm (PGSA), the optimal assembly points were calculated to be of a higher accuracy, compared to the traditional mean value aggregation method. Finally, the air quality of the Beijing-Tianjin-Hebei urban agglomeration during each year was evaluated dynamically based on the obtained assembly points. The results show that the air quality of the urban agglomeration is ranked as follows: <span>Y2016<img src="Edit_28ddcae1-12ec-4d20-a4e9-77309c996766.bmp" alt="" /></span><span></span><span>Y2015<img src="Edit_5f164e96-55aa-4e37-98e1-6833665979d1.bmp" alt="" /></span><span></span><span>Y2017<img src="Edit_cfc0da49-7e3a-4aa8-82ac-ede99621d1ec.bmp" alt="" /></span><span></span><span>Y2014.</span>展开更多
When a crowdsourcing approach is used to assist the classification of a set of items,the main objective is to classify this set of items by aggregating the worker-provided labels.A secondary objective is to assess the...When a crowdsourcing approach is used to assist the classification of a set of items,the main objective is to classify this set of items by aggregating the worker-provided labels.A secondary objective is to assess the workers’skill levels in this process.A classical model that achieves both objectives is the famous Dawid-Skene model.In this paper,we consider a third objective in this context,namely,to learn a classifier that is capable of labelling future items without further assistance of crowd workers.By extending the DawidSkene model to include the item features into consideration,we develop a Classification-Oriented Dawid Skene(CODS)model,which achieves the three objectives simultaneously.The effectiveness of CODS on this three dimensions of the problem space is demonstrated experimentally.展开更多
Knowledge graph completion aims to enhance the completeness of knowledge graphs by predicting missing links.Link prediction is a common approach for this task,but existing methods,particularly those based on similarit...Knowledge graph completion aims to enhance the completeness of knowledge graphs by predicting missing links.Link prediction is a common approach for this task,but existing methods,particularly those based on similarity computation,are often computationally expensive,especially for large models.To address this,we propose a novel method,positionally restricted masked knowledge graph completion(PR-MKGC),which reduces inference time by leveraging masked prediction and relying solely on structural information from the knowledge graph,without using textual data.We introduce a multi-head mutual attention mechanism that aggregates neighbor information more effectively,improving the model's ability to predict missing links.Experimental results demonstrate that PR-MKGC outperforms existing models in terms of both predictive performance and inference time on the FB15K-237 dataset.展开更多
基金supported by the Second Tibetan Plateau Scientific Expedition and Research(STEP)program under Grant 2019QZKK0106the Science and Technology Major Project of Henan Province under Grant 201400210900.
文摘Qinghai-Tibet Plateau lakes are important carriers of water resources in the‘Asian’s Water Tower’,and it is of great significance to grasp the spatial distribution of plateau lakes for the climate,ecological environment,and regional water cycle.However,the differences in spatial-spectral characteristics of various types of plateau lakes,and the complex background information of plateau both influence the extraction effect of lakes.Therefore,it is a great challenge to completely and effectively extract plateau lakes.In this study,we proposed a multiscale contextual information aggregation network,termed MSCANet,to automatically extract Plateau lake regions.It consists of three main components:a multiscale lake feature encoder,a feature decoder,and a Multicore Pyramid Pooling Module(MPPM).The multiscale lake feature encoder suppressed noise interference to capture multiscale spatial-spectral information from heterogeneous scenes.The MPPM module aggregated the contextual information of various lakes globally.We applied the MSCANet to the lake extraction of the Qinghai-Tibet Plateau based on Google data;additionally,comparative experiments showed that the MSCANet proposed had obvious improvement in lake detection accuracy and morphological integrity.Finally,we transferred the pre-trained optimal model to the Landsat-8 and Sentinel-2A dataset to verify the generalization of the MSCANet.
基金This Project was funded by the Deanship of Scientific Research(DSR),King Abdulaziz University,Jeddah,under the Grant No.(G:578-135-1441)The authors,therefore,acknowledge with thanks DSR for technical and financial support.
文摘With the frequent occurrences of emergency events,emergency decision making(EDM)plays an increasingly significant role in coping with such situations and has become an important and challenging research area in recent times.It is essential for decision makers to make reliable and reasonable emergency decisions within a short span of time,since inappropriate decisions may result in enormous economic losses and social disorder.To handle emergency effectively and quickly,this paper proposes a new EDM method based on the novel concept of q-rung orthopair fuzzy rough(q-ROPR)set.A novel list of q-ROFR aggregation information,detailed description of the fundamental characteristics of the developed aggregation operators and the q-ROFR entropy measure that determine the unknown weight information of decision makers as well as the criteria weights are specified.Further an algorithm is given to tackle the uncertain scenario in emergency to give reliable and reasonable emergency decisions.By using proposed list of q-ROFR aggregation information all emergency alternatives are ranked to get the optimal one.Besides this,the q-ROFR entropy measure method is used to determine criteria and experts’weights objectively in the EDM process.Finally,through an illustrative example of COVID-19 analysis is compared with existing EDM methods.The results verify the effectiveness and practicability of the proposed methodology.
基金Supported by the Foundation of Hubei Information Indus-try (05050)
文摘We proposed an Intemet resource aggregation platform based on semantic web. The platform includes an Web Ontology Language（OWL） ontology design toolkit（VO-Editor） and a selective inference algorithm engine so that it can visually editing ontology and using novel selective reasoning for information aggregation. We introduce the VO-Editor and the principle of selective inference algorithm. At last a case of budget travel system is used to interpret the approach of Internet resources aggregation by this platform.
基金Supported by the Natural Science Foundation ofLiaoning Province (20042020)
文摘A kind of single linked lists named aggregative chain is introduced to the algorithm, thus improving the architecture of FP tree. The new FP tree is a one-way tree and only the pointers that point its parent at each node are kept. Route information of different nodes in a same item are compressed into aggregative chains so that the frequent patterns will be produced in aggregative chains without generating node links and conditional pattern bases. An example of Web key words retrieval is given to analyze and verify the frequent pattern algorithm in this paper.
基金The National Natural Science Foundation of China(No.71171048)
文摘The maximal entropy ordered weighted averaging （ME-OWA） operator is used to aggregate metasearch engine results, and its newly analytical solution is also applied. Within the current context of the OWA operator, the methods for aggregating metasearch engine results are divided into two kinds. One has a unique solution, and the other has multiple solutions. The proposed method not only has crisp weights, but also provides multiple aggregation results for decision makers to choose from. In order to prove the application of the ME-OWA operator method, under the context of aggregating metasearch engine results, an example is given, which shows the results obtained by the ME-OWA operator method and the minimax linear programming （ minimax-LP ） method. Comparison between these two methods are also made. The results show that the ME-OWA operator has nearly the same aggregation results as those of the minimax-LP method.
基金supported by the Development Department Science and Technology Project(52992624000X).
文摘Accurate and reliable fault diagnosis is critical for secure operation in complex smart power systems.While graph neural networks show promise for this task,existing methods often neglect the long-tailed distribution inherent in real-world grid fault data and fail to provide reliability estimates for their decisions.To address these dual challenges,we propose a novel multi-expert collaboration uncertainty-aware power fault recognition framework with cross-view graph learning.Its core innovations are two synergistic modules:(1)The infographics aggregation module tackles the long-tail problem by learning robust graph-level representations.It employs an information-driven optimization loss within a contrastive graph architecture,explicitly preserving global invariance and local structural information across diverse(including rare)fault states.This ensures balanced representation learning for both the head and tail classes.(2)The multi-expert reliable decision module addresses prediction uncertainty.It trains individual expert classifiers using the Dirichlet distribution to explicitly model the credibility(uncertainty)of each expert’s decision.Crucially,a complementary collaboration rule based on evidence theory dynamically integrates these experts.This rule generates active weights for expert participation,prioritizing more certain experts and fusing their evidence to produce a final decision with a quantifiable reliability estimate.Collaboratively,these modules enable reliable diagnosis under data imbalance:The Infographics Module provides discriminative representations for all fault types,especially tail classes,while the Multi-Expert Module leverages these representations to make decisions with explicit uncertainty quantification.This synergy significantly improves both the accuracy and the reliability of fault recognition,particularly for rare or ambiguous grid conditions.Ultimately,extensive experiment evaluations on the four datasets reveal that the proposed method outperforms the state-of-the-art methods in the fault diagnosis of smart grids,in terms of accuracy,precision,f score and recall.
基金Supported by the National Natural Science Foundation of China(71671031,71701040)
文摘Exploring structural characteristics implied in initialdecision making information is an important issue in the process of aggregation. In this paper we provide a new family of aggregation operator called density weighted averaging operator（abbreviated as DWA operator）, which carries out the aggregation by classification. In this case, not only the hidden structural characteristics can be identified, some commonly known aggregation operators can also be incorporated into the function of the DWA operator. We further discuss the basic properties of this new operator, such as commutativity, idempotency, boundedness and monotonicity withcertain condition. Afterwards, two important issues related to the DWA operator are investigated, including the arguments partition and the determination of density weights. At last a numerical example regarding performance evaluation of employees is developed to illustrate the using of this new operator.
文摘In this study, a new method for a comprehensive evaluation of air quality in urban agglomerations was developed based on a prototype used to solve the spatial Steiner-Weber point. With this method, the air quality information of each city in the city group is aggregated into an optimal gathering point, and then the air quality of the city group is then dynamically evaluated each year. According to the relevant data of the China Statistical Yearbook 2018, we applied this method to aggregate the air quality indices of the major cities in the Beijing-Tianjin-Hebei urban agglomeration from 2014 to 2017. Using the plant growth simulation algorithm (PGSA), the optimal assembly points were calculated to be of a higher accuracy, compared to the traditional mean value aggregation method. Finally, the air quality of the Beijing-Tianjin-Hebei urban agglomeration during each year was evaluated dynamically based on the obtained assembly points. The results show that the air quality of the urban agglomeration is ranked as follows: <span>Y2016<img src="Edit_28ddcae1-12ec-4d20-a4e9-77309c996766.bmp" alt="" /></span><span></span><span>Y2015<img src="Edit_5f164e96-55aa-4e37-98e1-6833665979d1.bmp" alt="" /></span><span></span><span>Y2017<img src="Edit_cfc0da49-7e3a-4aa8-82ac-ede99621d1ec.bmp" alt="" /></span><span></span><span>Y2014.</span>
基金supported in part by the National Key R&D Program of China(2021ZD0110700)in part by the Fundamental Research Funds for the Central Universities,in part by the State Key Laboratory of Software Development Environmentin part by a Leverhulme Trust Research Project Grant.
文摘When a crowdsourcing approach is used to assist the classification of a set of items,the main objective is to classify this set of items by aggregating the worker-provided labels.A secondary objective is to assess the workers’skill levels in this process.A classical model that achieves both objectives is the famous Dawid-Skene model.In this paper,we consider a third objective in this context,namely,to learn a classifier that is capable of labelling future items without further assistance of crowd workers.By extending the DawidSkene model to include the item features into consideration,we develop a Classification-Oriented Dawid Skene(CODS)model,which achieves the three objectives simultaneously.The effectiveness of CODS on this three dimensions of the problem space is demonstrated experimentally.
文摘Knowledge graph completion aims to enhance the completeness of knowledge graphs by predicting missing links.Link prediction is a common approach for this task,but existing methods,particularly those based on similarity computation,are often computationally expensive,especially for large models.To address this,we propose a novel method,positionally restricted masked knowledge graph completion(PR-MKGC),which reduces inference time by leveraging masked prediction and relying solely on structural information from the knowledge graph,without using textual data.We introduce a multi-head mutual attention mechanism that aggregates neighbor information more effectively,improving the model's ability to predict missing links.Experimental results demonstrate that PR-MKGC outperforms existing models in terms of both predictive performance and inference time on the FB15K-237 dataset.
