Pub Date : 2011-10-13DOI: 10.1109/CCIS.2011.6045065
T. R. G. Nair, K. Madhuri
State of the art research in data mining is focusing on loosely distributed regionalized large scale databases using cloud computing for business applications. Cloud computing poses a diversity of challenges in data mining operation arising out of the dynamic structure of data distribution as against the use of typical database scenarios in conventional architecture. Realization of maximum efficiency depends much on the initiation of accurate decision data mining. This paper presents a specific method of implementing k-means approach for data mining in such scenarios. In this approach data is geographically distributed in multiple regions formed under several virtual machines. The results show that hierarchical virtual k-means approach is an efficient mining scheme for cloud databases.
{"title":"Data mining using hierarchical virtual k-means approach integrating data fragments in cloud computing environment","authors":"T. R. G. Nair, K. Madhuri","doi":"10.1109/CCIS.2011.6045065","DOIUrl":"https://doi.org/10.1109/CCIS.2011.6045065","url":null,"abstract":"State of the art research in data mining is focusing on loosely distributed regionalized large scale databases using cloud computing for business applications. Cloud computing poses a diversity of challenges in data mining operation arising out of the dynamic structure of data distribution as against the use of typical database scenarios in conventional architecture. Realization of maximum efficiency depends much on the initiation of accurate decision data mining. This paper presents a specific method of implementing k-means approach for data mining in such scenarios. In this approach data is geographically distributed in multiple regions formed under several virtual machines. The results show that hierarchical virtual k-means approach is an efficient mining scheme for cloud databases.","PeriodicalId":128504,"journal":{"name":"2011 IEEE International Conference on Cloud Computing and Intelligence Systems","volume":"225 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126126732","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2011-10-13DOI: 10.1109/CCIS.2011.6045085
C. Man, Makoto Kayashima
Finding optimal placement of virtual machines on numerous physical servers is one kind of bin-packing problem, which is known as an NP-hard. We propose the use of a heuristic algorithm to solve this problem where the virtual machines play the roles of personal desktops. As we have found out that the changes in the amount of hardware resources required by a desktop often repeat a certain pattern, in the proposed algorithm, we uses the correlation between the patterns to find the group of desktops that are most suitable for sharing the same physical server. Simulation results show that the proposed algorithm can be used to reduce the number of physical servers required for hosting a certain number of virtual desktops.
{"title":"Virtual machine placement algorithm for virtualized desktop infrastructure","authors":"C. Man, Makoto Kayashima","doi":"10.1109/CCIS.2011.6045085","DOIUrl":"https://doi.org/10.1109/CCIS.2011.6045085","url":null,"abstract":"Finding optimal placement of virtual machines on numerous physical servers is one kind of bin-packing problem, which is known as an NP-hard. We propose the use of a heuristic algorithm to solve this problem where the virtual machines play the roles of personal desktops. As we have found out that the changes in the amount of hardware resources required by a desktop often repeat a certain pattern, in the proposed algorithm, we uses the correlation between the patterns to find the group of desktops that are most suitable for sharing the same physical server. Simulation results show that the proposed algorithm can be used to reduce the number of physical servers required for hosting a certain number of virtual desktops.","PeriodicalId":128504,"journal":{"name":"2011 IEEE International Conference on Cloud Computing and Intelligence Systems","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127345049","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2011-10-13DOI: 10.1109/CCIS.2011.6045099
Lian-Ming Mou
The Generalized Traveling Salesman Problem (GTSP) is an extension of the classical traveling salesman problem and has many interesting applications. In this paper we present a New Generalized Traveling Salesman Problem (NGTSP), and the current GTSP is only a special case of the NGTSP. To solve effectively the NGTSP, we extend the ant colony system method from TSP to NGTSP. Meanwhile, to improve the quality of solution, a local searching technique is introduced into this method to speed up the convergence, and a novel parameter adaptive technique is also introduced into this method to avoid locking into local minima. Experimental results on numerous TSPlib instances show that the proposed method can deal with the NGTSP problems fairly well, and the developed improvement techniques is significantly effective.
{"title":"An efficient ant colony system for solving the new Generalized Traveling Salesman Problem","authors":"Lian-Ming Mou","doi":"10.1109/CCIS.2011.6045099","DOIUrl":"https://doi.org/10.1109/CCIS.2011.6045099","url":null,"abstract":"The Generalized Traveling Salesman Problem (GTSP) is an extension of the classical traveling salesman problem and has many interesting applications. In this paper we present a New Generalized Traveling Salesman Problem (NGTSP), and the current GTSP is only a special case of the NGTSP. To solve effectively the NGTSP, we extend the ant colony system method from TSP to NGTSP. Meanwhile, to improve the quality of solution, a local searching technique is introduced into this method to speed up the convergence, and a novel parameter adaptive technique is also introduced into this method to avoid locking into local minima. Experimental results on numerous TSPlib instances show that the proposed method can deal with the NGTSP problems fairly well, and the developed improvement techniques is significantly effective.","PeriodicalId":128504,"journal":{"name":"2011 IEEE International Conference on Cloud Computing and Intelligence Systems","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131065240","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2011-10-13DOI: 10.1109/CCIS.2011.6045056
Yawei Zhao, Dongri Yang
XML data cube has characteristics of large scale data and complex join operations during query process. In general, due to the large amount of fact data, the efficiency of join query is inefficient. Cloud computing is a high-performance computing environment, and parallel query technology can be adopted for XML data cube to improve efficiency of multi-dimensional query, when the cube is based on cloud pattern. A kind of XML data cube model-pXCube based on path computation is analyzed and parallel query method based on cloud pattern is proposed for the model. In particularly, Non-symmetrical strategy is used in pXCube's fact and dimension partition and the vector is uniform. On the basis, the query algorithm is provided. Experimental data shows that pXCube query parallel based on the cloud pattern has a good speedup and it is well-suitable for decision support query.
{"title":"Research on parallel query technology of pXCube model based on cloud pattern","authors":"Yawei Zhao, Dongri Yang","doi":"10.1109/CCIS.2011.6045056","DOIUrl":"https://doi.org/10.1109/CCIS.2011.6045056","url":null,"abstract":"XML data cube has characteristics of large scale data and complex join operations during query process. In general, due to the large amount of fact data, the efficiency of join query is inefficient. Cloud computing is a high-performance computing environment, and parallel query technology can be adopted for XML data cube to improve efficiency of multi-dimensional query, when the cube is based on cloud pattern. A kind of XML data cube model-pXCube based on path computation is analyzed and parallel query method based on cloud pattern is proposed for the model. In particularly, Non-symmetrical strategy is used in pXCube's fact and dimension partition and the vector is uniform. On the basis, the query algorithm is provided. Experimental data shows that pXCube query parallel based on the cloud pattern has a good speedup and it is well-suitable for decision support query.","PeriodicalId":128504,"journal":{"name":"2011 IEEE International Conference on Cloud Computing and Intelligence Systems","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123735856","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2011-10-13DOI: 10.1109/CCIS.2011.6045118
Zhong-jie Ma, Chengyao Wang, Zongjie Wang
As cloud computing going, data integration and data center have reemerged as an active research topic recently, due to the increased requirements for exchange of data in various formats in our increasingly interconnected but inevitably heterogeneous world. Three-layered metadata model, including data source metadata, business metadata and topic metadata, is proposed to realize heterogeneous data integration, and components and functions for each layer are introduced. Then RDF-based metadata representation is introduced for data interchange. The architecture of a typical heterogeneous data integration system based on metadata has been put forward, the applications can directly use HTTP protocol to access the broker by uniform data access interfaces based on RESTful Web Services, and the data broker provides all applications with integrated access to multiple, heterogeneous data sources, giving each client the illusion of a single, homogeneous database designed for his specific need. Metadata make it easy to query and locate data resources, and eliminate heterogeneity of multiple data sources. Meanwhile, it provides users with transparent and quick access to resources services.
随着云计算的发展，数据集成和数据中心最近重新成为一个活跃的研究课题，因为在我们日益相互关联但不可避免地异构的世界中，对各种格式的数据交换的需求不断增加。提出了数据源元数据、业务元数据和主题元数据三层元数据模型来实现异构数据集成，并介绍了各层元数据的组成和功能。然后引入基于rdf的元数据表示，实现数据交换。提出了一种典型的基于元数据的异构数据集成系统的体系结构，应用程序可以直接使用HTTP协议通过基于RESTful Web Services的统一数据访问接口访问代理，数据代理为所有应用程序提供对多个异构数据源的集成访问，使每个客户端都有一个针对其特定需求而设计的单一、同构数据库的错觉。元数据可以方便地查询和定位数据资源，消除多个数据源的异构性。同时，为用户提供透明、快捷的资源服务访问。
{"title":"Research on three-layered metadata model for oil-gas data integration","authors":"Zhong-jie Ma, Chengyao Wang, Zongjie Wang","doi":"10.1109/CCIS.2011.6045118","DOIUrl":"https://doi.org/10.1109/CCIS.2011.6045118","url":null,"abstract":"As cloud computing going, data integration and data center have reemerged as an active research topic recently, due to the increased requirements for exchange of data in various formats in our increasingly interconnected but inevitably heterogeneous world. Three-layered metadata model, including data source metadata, business metadata and topic metadata, is proposed to realize heterogeneous data integration, and components and functions for each layer are introduced. Then RDF-based metadata representation is introduced for data interchange. The architecture of a typical heterogeneous data integration system based on metadata has been put forward, the applications can directly use HTTP protocol to access the broker by uniform data access interfaces based on RESTful Web Services, and the data broker provides all applications with integrated access to multiple, heterogeneous data sources, giving each client the illusion of a single, homogeneous database designed for his specific need. Metadata make it easy to query and locate data resources, and eliminate heterogeneity of multiple data sources. Meanwhile, it provides users with transparent and quick access to resources services.","PeriodicalId":128504,"journal":{"name":"2011 IEEE International Conference on Cloud Computing and Intelligence Systems","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132857852","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2011-10-13DOI: 10.1109/CCIS.2011.6045124
Guang Li, Guisheng Chen
Share and innovation of education resource is one of the urgent issues nowadays, In this paper we proposed an innovatory computing paradigm merging volunteer contributing and Cloud approaches into EduCloud@Home in the education project. This proposal represents a solution for building Clouds, starting from heterogeneous and independent nodes. This can implement a generalization of both Volunteer and Cloud computing by aggregating the computational potentialities of many small, low power systems of rich education resource, exploiting the long tail effect of computing. The basic idea is to reuse “domestic” computing resources to build voluntary contributors' Clouds in the education application project. With the enhanced EduCloud@Home, anyone can experience the power of Cloud computing, both actively providing teacher or students' own resources and services, and passively submitting their applications.
{"title":"A novel enhanced education application of Cloud computing","authors":"Guang Li, Guisheng Chen","doi":"10.1109/CCIS.2011.6045124","DOIUrl":"https://doi.org/10.1109/CCIS.2011.6045124","url":null,"abstract":"Share and innovation of education resource is one of the urgent issues nowadays, In this paper we proposed an innovatory computing paradigm merging volunteer contributing and Cloud approaches into EduCloud@Home in the education project. This proposal represents a solution for building Clouds, starting from heterogeneous and independent nodes. This can implement a generalization of both Volunteer and Cloud computing by aggregating the computational potentialities of many small, low power systems of rich education resource, exploiting the long tail effect of computing. The basic idea is to reuse “domestic” computing resources to build voluntary contributors' Clouds in the education application project. With the enhanced EduCloud@Home, anyone can experience the power of Cloud computing, both actively providing teacher or students' own resources and services, and passively submitting their applications.","PeriodicalId":128504,"journal":{"name":"2011 IEEE International Conference on Cloud Computing and Intelligence Systems","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123015240","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2011-10-13DOI: 10.1109/CCIS.2011.6045062
Xiaofei Zhao, Zhongzhi Shi
The organization of the metadata in repository systems exhibits a complex structure which is layered, multi-level and dynamically adaptable; the validating of well-formedness constraints is insufficiently specified in existing repository system standard, the above two reasons make it becomes a major challenge how to validate well-formedness constraints for MOF-based metadata repository systems. In this paper we propose a method to automatically detect the operations that may potentially violate a well-formedness constraint in the meta-level. Our approach can detect potentially violating operations by determining the construction actions that may violate the constraint and checking whether those actions appear in the operation specification. Our approach helps to improve efficiency of well-formedness constraint checking since its results can be used to discard many irrelevant tests.
{"title":"Detecting operations that potentially violate well-formedness constraints for metadata repository systems","authors":"Xiaofei Zhao, Zhongzhi Shi","doi":"10.1109/CCIS.2011.6045062","DOIUrl":"https://doi.org/10.1109/CCIS.2011.6045062","url":null,"abstract":"The organization of the metadata in repository systems exhibits a complex structure which is layered, multi-level and dynamically adaptable; the validating of well-formedness constraints is insufficiently specified in existing repository system standard, the above two reasons make it becomes a major challenge how to validate well-formedness constraints for MOF-based metadata repository systems. In this paper we propose a method to automatically detect the operations that may potentially violate a well-formedness constraint in the meta-level. Our approach can detect potentially violating operations by determining the construction actions that may violate the constraint and checking whether those actions appear in the operation specification. Our approach helps to improve efficiency of well-formedness constraint checking since its results can be used to discard many irrelevant tests.","PeriodicalId":128504,"journal":{"name":"2011 IEEE International Conference on Cloud Computing and Intelligence Systems","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125129945","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2011-10-13DOI: 10.1109/CCIS.2011.6045086
Song Liu, Xiao Xie
An improved algorithm of point cloud ICP registration base on MapReduce is proposed. This method applies parallel computing of MapReduce to registration of point cloud in order to reduce the requirements of computing and improve the efficiency of computing. At last, the results of three examples running on a Hadoop cluster show that the efficiency of registration has been improved and the results achieve the expectant target.
{"title":"Research on algorithm of point cloud MapReduce registration","authors":"Song Liu, Xiao Xie","doi":"10.1109/CCIS.2011.6045086","DOIUrl":"https://doi.org/10.1109/CCIS.2011.6045086","url":null,"abstract":"An improved algorithm of point cloud ICP registration base on MapReduce is proposed. This method applies parallel computing of MapReduce to registration of point cloud in order to reduce the requirements of computing and improve the efficiency of computing. At last, the results of three examples running on a Hadoop cluster show that the efficiency of registration has been improved and the results achieve the expectant target.","PeriodicalId":128504,"journal":{"name":"2011 IEEE International Conference on Cloud Computing and Intelligence Systems","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122461818","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2011-10-13DOI: 10.1109/CCIS.2011.6045144
Ping Yuan, Yuan Ma
Concept lattice, which is a core data structure of the theory of formal concept analysis, has been widely applied to many fields. By computing the distance between concepts of a concept lattice, objects of the formal context can be analyzed clusteredly, so that the required data of the users can be obtained. In the concept lattice, a new approach to computing the distance between concepts is proposed, and the mathematical induction is used to prove this. The approach firstly computes the waned value of intension between concepts, and then computes the distance between concepts of a concept lattice by using the addition of the waned value of intension.
{"title":"An approach to the computation of distance of concept lattice by utilizing waned value of intension","authors":"Ping Yuan, Yuan Ma","doi":"10.1109/CCIS.2011.6045144","DOIUrl":"https://doi.org/10.1109/CCIS.2011.6045144","url":null,"abstract":"Concept lattice, which is a core data structure of the theory of formal concept analysis, has been widely applied to many fields. By computing the distance between concepts of a concept lattice, objects of the formal context can be analyzed clusteredly, so that the required data of the users can be obtained. In the concept lattice, a new approach to computing the distance between concepts is proposed, and the mathematical induction is used to prove this. The approach firstly computes the waned value of intension between concepts, and then computes the distance between concepts of a concept lattice by using the addition of the waned value of intension.","PeriodicalId":128504,"journal":{"name":"2011 IEEE International Conference on Cloud Computing and Intelligence Systems","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127930594","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2011-10-13DOI: 10.1109/CCIS.2011.6045028
Yuehua Yang, Junping Du, M. Liang
From aspects of domain ontology construction, concept similarity computation based on ontology and semantic query expansion study the related technologies of information retrieval system based on ontology; establish food safety domain ontology and ontology-based concept similarity computation model, put forward a new semantic query expansion method based on concept similarity computation; design and implement food safety semantic retrieval system. The experiments show that this food safety semantic retrieval system is superior to the retrieval system based on keywords both in the recall ratio and the precision, and realize certain intelligent retrieval.
{"title":"Study on food safety semantic retrieval system based on domain ontology","authors":"Yuehua Yang, Junping Du, M. Liang","doi":"10.1109/CCIS.2011.6045028","DOIUrl":"https://doi.org/10.1109/CCIS.2011.6045028","url":null,"abstract":"From aspects of domain ontology construction, concept similarity computation based on ontology and semantic query expansion study the related technologies of information retrieval system based on ontology; establish food safety domain ontology and ontology-based concept similarity computation model, put forward a new semantic query expansion method based on concept similarity computation; design and implement food safety semantic retrieval system. The experiments show that this food safety semantic retrieval system is superior to the retrieval system based on keywords both in the recall ratio and the precision, and realize certain intelligent retrieval.","PeriodicalId":128504,"journal":{"name":"2011 IEEE International Conference on Cloud Computing and Intelligence Systems","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131796950","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：