Pub Date : 2011-10-13DOI: 10.1109/CCIS.2011.6045042
Kansheng Shi, Lemin Li, Jie He, Haitao Liu, Naitong Zhang, Wentao Song
The traditional K-means algorithm is sensitive to the initial point, easy to fall into local optimum. In order to avoid this kind of flaw, an improved K-means text clustering method WIKTCM is proposed. The new method creates an innovative initial centers selection method and accommodates the contribution of characteristics of different parts of speech to the text. In addition, the impact of outliers is considered. Experimental results show that the new method has better clustering results.
{"title":"A linguistic feature based text clustering method","authors":"Kansheng Shi, Lemin Li, Jie He, Haitao Liu, Naitong Zhang, Wentao Song","doi":"10.1109/CCIS.2011.6045042","DOIUrl":"https://doi.org/10.1109/CCIS.2011.6045042","url":null,"abstract":"The traditional K-means algorithm is sensitive to the initial point, easy to fall into local optimum. In order to avoid this kind of flaw, an improved K-means text clustering method WIKTCM is proposed. The new method creates an innovative initial centers selection method and accommodates the contribution of characteristics of different parts of speech to the text. In addition, the impact of outliers is considered. Experimental results show that the new method has better clustering results.","PeriodicalId":128504,"journal":{"name":"2011 IEEE International Conference on Cloud Computing and Intelligence Systems","volume":"14 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":"128072692","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.2011.6045095
Rong Wang, Xin-long Luo, Jiaru Lin
In this paper, we propose a cooperative relay selection scheme based on geographical information in cellular networks. According to the current user equipment density in a certain cell, we firstly choose the potential relays among the user equipments. Then, the localization algorithm based on time difference of arrival has been adapted to locate the potential nodes. Finally, we select the cooperative relay from the potential relays based on the known geographical information. We also give simulation experiments. Simulation results show that the scheme can choose the best cooperative relay to increase effectively the user capacity and to improve system performance as well.
{"title":"Cooperative relay selection scheme based on geographical information","authors":"Rong Wang, Xin-long Luo, Jiaru Lin","doi":"10.1109/CCIS.2011.6045095","DOIUrl":"https://doi.org/10.1109/CCIS.2011.6045095","url":null,"abstract":"In this paper, we propose a cooperative relay selection scheme based on geographical information in cellular networks. According to the current user equipment density in a certain cell, we firstly choose the potential relays among the user equipments. Then, the localization algorithm based on time difference of arrival has been adapted to locate the potential nodes. Finally, we select the cooperative relay from the potential relays based on the known geographical information. We also give simulation experiments. Simulation results show that the scheme can choose the best cooperative relay to increase effectively the user capacity and to improve system performance as well.","PeriodicalId":128504,"journal":{"name":"2011 IEEE International Conference on Cloud Computing and Intelligence Systems","volume":"34 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":"125338970","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.2011.6045105
Bo Zhang
With the proliferation of Web services and the evolution towards the Semantic Web comes the opportunity to automate various Web services tasks. In this paper, we propose the conception of Sub Web Service and present an algorithm of automatic web service composition which based on Sub Web Service. The most contribution of this paper is: (1) propose the conception of Sub Web Service; (2) present a automatic composition algorithm. The simulation experiment indicated that the algorithm we proposed is effective and efficiency when applied in web service composition engine.
{"title":"A Web service composition method based on Sub Web Service","authors":"Bo Zhang","doi":"10.1109/CCIS.2011.6045105","DOIUrl":"https://doi.org/10.1109/CCIS.2011.6045105","url":null,"abstract":"With the proliferation of Web services and the evolution towards the Semantic Web comes the opportunity to automate various Web services tasks. In this paper, we propose the conception of Sub Web Service and present an algorithm of automatic web service composition which based on Sub Web Service. The most contribution of this paper is: (1) propose the conception of Sub Web Service; (2) present a automatic composition algorithm. The simulation experiment indicated that the algorithm we proposed is effective and efficiency when applied in web service composition engine.","PeriodicalId":128504,"journal":{"name":"2011 IEEE International Conference on Cloud Computing and Intelligence Systems","volume":"16 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":"125222946","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.2011.6045069
L. Hou, Lin Zuo, Pei Luo, Dong Liu
In this paper, a new wavelength assignment scheme called CSSIR (collision-safe source-initiated reservation) has been proposed for distributed lightpath establishment in GMPLS/PCE based Wavelength-switched Optical Networks (WSONs), which has DIR-like forward blocking probability with SIR-like backward blocking probability. In CSSIR, the PCE selects one wavelength reserved with multi-backup to protect the collision. Simulations are conducted to compare it with SIR&DIR. The results show that CSSIR performs better in total blocking than the others under various traffic loads.
{"title":"Collision-safe wavelength assignment scheme for lightpath establishment in WSONs","authors":"L. Hou, Lin Zuo, Pei Luo, Dong Liu","doi":"10.1109/CCIS.2011.6045069","DOIUrl":"https://doi.org/10.1109/CCIS.2011.6045069","url":null,"abstract":"In this paper, a new wavelength assignment scheme called CSSIR (collision-safe source-initiated reservation) has been proposed for distributed lightpath establishment in GMPLS/PCE based Wavelength-switched Optical Networks (WSONs), which has DIR-like forward blocking probability with SIR-like backward blocking probability. In CSSIR, the PCE selects one wavelength reserved with multi-backup to protect the collision. Simulations are conducted to compare it with SIR&DIR. The results show that CSSIR performs better in total blocking than the others under various traffic loads.","PeriodicalId":128504,"journal":{"name":"2011 IEEE International Conference on Cloud Computing and Intelligence Systems","volume":"4 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":"122298889","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.2011.6045058
Xiuqin Lin, Xiaowei Yan, Liutong Xu, Xinyang Piao
Cloud computing is a fusion of network technology and traditional computer technology. It aims to deliver the powerful computing capability to end users through the advanced business model such as SaaS, PaaS, and IaaS. IaaS can provide a convenient, flexible and pay-per-use infrastructure for PaaS and SaaS. This paper is focused on Eucalyptus — a famous open source IaaS platform. After a brief introduction to the Eucalyptus, a detailed analysis about information synchronization mechanism shows some issues of information synchronization mechanism. According to the specific scenes, we have given a reasonable solution. With this solution, Eucalyptus can automatically restore to the state before when physical machine reboot for some reason and Eucalyptus can support live migration and dynamic adjustment of the virtual machine resources. At the end of the paper, experiments show the effect of the improvement on the Eucalyptus.
{"title":"A method for improving information synchronization mechanism in Eucalyptus","authors":"Xiuqin Lin, Xiaowei Yan, Liutong Xu, Xinyang Piao","doi":"10.1109/CCIS.2011.6045058","DOIUrl":"https://doi.org/10.1109/CCIS.2011.6045058","url":null,"abstract":"Cloud computing is a fusion of network technology and traditional computer technology. It aims to deliver the powerful computing capability to end users through the advanced business model such as SaaS, PaaS, and IaaS. IaaS can provide a convenient, flexible and pay-per-use infrastructure for PaaS and SaaS. This paper is focused on Eucalyptus — a famous open source IaaS platform. After a brief introduction to the Eucalyptus, a detailed analysis about information synchronization mechanism shows some issues of information synchronization mechanism. According to the specific scenes, we have given a reasonable solution. With this solution, Eucalyptus can automatically restore to the state before when physical machine reboot for some reason and Eucalyptus can support live migration and dynamic adjustment of the virtual machine resources. At the end of the paper, experiments show the effect of the improvement on the Eucalyptus.","PeriodicalId":128504,"journal":{"name":"2011 IEEE International Conference on Cloud Computing and Intelligence Systems","volume":"29 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":"133275899","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.2011.6045021
Anqi Cui, Min Zhang, Yiqun Liu, Shaoping Ma
Microblogging services are attracting people and companies to share their ideas and interests. Since the texts of microblog messages are limited, people post URLs to link to other websites for detailed information. Hence, URLs with higher attentions are spread widely and represent popular information. However, not all these URLs are useful. Many of them are spam URLs which are posted by automated agents or by pushing services from other websites automatically. Based on the features of the popular URLs, we divide them into four categories and propose a clustering and classification algorithm to distinguish spam URLs from the really popular ones. Comparative experiments are conducted on English (Twitter) and Chinese (Sina Weibo) messages. We conclude that more than half of the popular URLs are spam. Most of them are pushed from other websites; even the really popular ones gain much attention from the pushing services. Although the proportions of URLs in Twitter and Sina Weibo messages are different, the characteristics of the spam URLs are similar. Our method is efficient for detecting spam URLs and their authors without annotations, and is helpful for both research and business on microblog.
{"title":"Are the URLs really popular in microblog messages?","authors":"Anqi Cui, Min Zhang, Yiqun Liu, Shaoping Ma","doi":"10.1109/CCIS.2011.6045021","DOIUrl":"https://doi.org/10.1109/CCIS.2011.6045021","url":null,"abstract":"Microblogging services are attracting people and companies to share their ideas and interests. Since the texts of microblog messages are limited, people post URLs to link to other websites for detailed information. Hence, URLs with higher attentions are spread widely and represent popular information. However, not all these URLs are useful. Many of them are spam URLs which are posted by automated agents or by pushing services from other websites automatically. Based on the features of the popular URLs, we divide them into four categories and propose a clustering and classification algorithm to distinguish spam URLs from the really popular ones. Comparative experiments are conducted on English (Twitter) and Chinese (Sina Weibo) messages. We conclude that more than half of the popular URLs are spam. Most of them are pushed from other websites; even the really popular ones gain much attention from the pushing services. Although the proportions of URLs in Twitter and Sina Weibo messages are different, the characteristics of the spam URLs are similar. Our method is efficient for detecting spam URLs and their authors without annotations, and is helpful for both research and business on microblog.","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":"124924561","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.2011.6045123
Shu-Min Chuang, Kuo-En Chang, Y. Sung
The total initial cost of enterprise learning management system is very high on the infrastructure and software applications, so that enterprises start to adopt cloud computing to reduce expenditure on infrastructure, software and IT human resource. The paper provides a cost effective structure of hybrid cloud architecture that has been implemented the multi-tenant model for enterprise to support customization sharing among different virtualized applications in a tenant area. The schema-sharing and multi-tenant data storage architecture also supports the learning content delivery. The important basis for the design method of software development shall embed with the cost effective structure, such as using multithreads to compute background processing and unzip the content files to reduce brand width usage. Even the file sizes of learning content shall be zipped to the less small size and duplicate to different servers for cutting down the traffic flow of brand width. The detailed calculation of the all I/O computer processing and brand width become the crucial implementation way.
{"title":"The cost effective structure for designing hybrid cloud based enterprise E-learning platform","authors":"Shu-Min Chuang, Kuo-En Chang, Y. Sung","doi":"10.1109/CCIS.2011.6045123","DOIUrl":"https://doi.org/10.1109/CCIS.2011.6045123","url":null,"abstract":"The total initial cost of enterprise learning management system is very high on the infrastructure and software applications, so that enterprises start to adopt cloud computing to reduce expenditure on infrastructure, software and IT human resource. The paper provides a cost effective structure of hybrid cloud architecture that has been implemented the multi-tenant model for enterprise to support customization sharing among different virtualized applications in a tenant area. The schema-sharing and multi-tenant data storage architecture also supports the learning content delivery. The important basis for the design method of software development shall embed with the cost effective structure, such as using multithreads to compute background processing and unzip the content files to reduce brand width usage. Even the file sizes of learning content shall be zipped to the less small size and duplicate to different servers for cutting down the traffic flow of brand width. The detailed calculation of the all I/O computer processing and brand width become the crucial implementation way.","PeriodicalId":128504,"journal":{"name":"2011 IEEE International Conference on Cloud Computing and Intelligence Systems","volume":"81 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":"134371731","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.2011.6045077
Feifei Liu, Dawu Gu, Haining Lu
Cloud computing is becoming increasingly popular. Many companies, organizations and individuals choose to outsource their computing demands and storage demands. In order to ensure the integrity of the data in the Cloud, especially the dynamic files which can be updated online, we propose an improved dynamic provable data possession model: It divides file into blocks, generates a tag for each block, computes a hash value for each tag, uses tags to ensure the integrity of the file blocks, and uses hash values to ensure the integrity of the tags. Compared with previous works, it reduces the computational and communication complexity from logn to constant. Although client needs to store some secret values which may create some additional storage expense, it only takes up about 0.02% of the original file size. Hence it is acceptable in most cases.
{"title":"An improved dynamic provable data possession model","authors":"Feifei Liu, Dawu Gu, Haining Lu","doi":"10.1109/CCIS.2011.6045077","DOIUrl":"https://doi.org/10.1109/CCIS.2011.6045077","url":null,"abstract":"Cloud computing is becoming increasingly popular. Many companies, organizations and individuals choose to outsource their computing demands and storage demands. In order to ensure the integrity of the data in the Cloud, especially the dynamic files which can be updated online, we propose an improved dynamic provable data possession model: It divides file into blocks, generates a tag for each block, computes a hash value for each tag, uses tags to ensure the integrity of the file blocks, and uses hash values to ensure the integrity of the tags. Compared with previous works, it reduces the computational and communication complexity from logn to constant. Although client needs to store some secret values which may create some additional storage expense, it only takes up about 0.02% of the original file size. Hence it is acceptable in most cases.","PeriodicalId":128504,"journal":{"name":"2011 IEEE International Conference on Cloud Computing and Intelligence Systems","volume":"5 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":"114675767","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.2011.6045032
Li-Na Li, Jihong Ouyang, Da-you Liu, Hong Qi, Huiling Chen
Collective classification, which is represented to classify unobserved nodes simultaneously in networked data is becoming an important research area with applications in several domains, such as the classification of documents, image processing. Most algorithms are based on the hypothesis that nearby nodes tend to have the same label. However, there are many networks that do not necessarily satisfy this hypothesis. In this paper, we present a new method based on random walk and link pattern of the network. It adopts the pseudoinverse laplacian matrix of the graph as similarity measure to identify nearby nodes and assigns an initial label for each unlabeled node, then iteratively update the label of unlabeled nodes based on the link pattern. The experimental results on two real world datasets demonstrate that the proposed method outperforms the other state-of-art approaches for this problem.
{"title":"A new hybrid collective classification method based on random walk and link pattern","authors":"Li-Na Li, Jihong Ouyang, Da-you Liu, Hong Qi, Huiling Chen","doi":"10.1109/CCIS.2011.6045032","DOIUrl":"https://doi.org/10.1109/CCIS.2011.6045032","url":null,"abstract":"Collective classification, which is represented to classify unobserved nodes simultaneously in networked data is becoming an important research area with applications in several domains, such as the classification of documents, image processing. Most algorithms are based on the hypothesis that nearby nodes tend to have the same label. However, there are many networks that do not necessarily satisfy this hypothesis. In this paper, we present a new method based on random walk and link pattern of the network. It adopts the pseudoinverse laplacian matrix of the graph as similarity measure to identify nearby nodes and assigns an initial label for each unlabeled node, then iteratively update the label of unlabeled nodes based on the link pattern. The experimental results on two real world datasets demonstrate that the proposed method outperforms the other state-of-art approaches for this problem.","PeriodicalId":128504,"journal":{"name":"2011 IEEE International Conference on Cloud Computing and Intelligence Systems","volume":"13 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":"130012627","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.2011.6045108
M. Cao, Guannan Fang, F. Ren
Emotion recognition is becoming a more and more hot topic nowadays. Many researches on facial recognition and speech recognition have been done. In this paper, we develop a method to facilitate emotion recognition with electroencephalographic (EEG) signals. The main objective of our study is to reveal the relation between emotional responses and EEG data gathered through giving seven subjects word-imagination stimuli. To induce emotions we choose 20 Chinese emotional words which have relatively high emotional intensities. We use support vector machine (SVM) and linear discriminant analysis (LDA) to recognize emotion, respectively, the average recognition rates of 48.78% and 57.04% could be achieved.
{"title":"EEG-based emotion recognition in Chinese emotional words","authors":"M. Cao, Guannan Fang, F. Ren","doi":"10.1109/CCIS.2011.6045108","DOIUrl":"https://doi.org/10.1109/CCIS.2011.6045108","url":null,"abstract":"Emotion recognition is becoming a more and more hot topic nowadays. Many researches on facial recognition and speech recognition have been done. In this paper, we develop a method to facilitate emotion recognition with electroencephalographic (EEG) signals. The main objective of our study is to reveal the relation between emotional responses and EEG data gathered through giving seven subjects word-imagination stimuli. To induce emotions we choose 20 Chinese emotional words which have relatively high emotional intensities. We use support vector machine (SVM) and linear discriminant analysis (LDA) to recognize emotion, respectively, the average recognition rates of 48.78% and 57.04% could be achieved.","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":"129530480","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：