Querying a sensor network requires the acquisition from sensors of measurements describing the state of the monitored environment. To transmit the required information, sensors consume energy. Since sensors are battery-powered, reduced energy consumption allows the extension of a sensor's lifetime. Hence, an important issue in this context is the reduction of energy consumption during data collection. We propose a framework that performs the analysis of historical sensor readings to provide better quality models for sensor networks under realistic assumptions (e.g., presence of outliers) without restrictive hypotheses on sensor variables. The framework exploits clustering techniques to select a subset of representative sensors, which will be queried instead of the whole network to reduce communication and computation costs and balance energy consumption among sensors. Preliminary experimental results, performed on data collected from 54 sensors deployed in the Intel Berkeley Research lab show the adaptability and the effectiveness of the proposed approach.
{"title":"Modeling a Sensor Network by means of Clustering","authors":"Elena Baralis, T. Cerquitelli, V. D'Elia","doi":"10.1109/DEXA.2007.23","DOIUrl":"https://doi.org/10.1109/DEXA.2007.23","url":null,"abstract":"Querying a sensor network requires the acquisition from sensors of measurements describing the state of the monitored environment. To transmit the required information, sensors consume energy. Since sensors are battery-powered, reduced energy consumption allows the extension of a sensor's lifetime. Hence, an important issue in this context is the reduction of energy consumption during data collection. We propose a framework that performs the analysis of historical sensor readings to provide better quality models for sensor networks under realistic assumptions (e.g., presence of outliers) without restrictive hypotheses on sensor variables. The framework exploits clustering techniques to select a subset of representative sensors, which will be queried instead of the whole network to reduce communication and computation costs and balance energy consumption among sensors. Preliminary experimental results, performed on data collected from 54 sensors deployed in the Intel Berkeley Research lab show the adaptability and the effectiveness of the proposed approach.","PeriodicalId":314834,"journal":{"name":"18th International Workshop on Database and Expert Systems Applications (DEXA 2007)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121698601","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}
We present a security engineering process based on security problem frames and concretized security problem frames. Both kinds of frames constitute patterns for analyzing security problems and associated solution approaches. They are arranged in a pattern system that makes dependencies between them explicit. We describe step-by-step how the pattern system can be used to analyze a given security problem and how solution approaches can be found. Further, we introduce a new frame that focuses on the privacy requirement anonymity.
{"title":"A Security Engineering Process based on Patterns","authors":"Denis Hatebur, M. Heisel, Holger Schmidt","doi":"10.1109/DEXA.2007.36","DOIUrl":"https://doi.org/10.1109/DEXA.2007.36","url":null,"abstract":"We present a security engineering process based on security problem frames and concretized security problem frames. Both kinds of frames constitute patterns for analyzing security problems and associated solution approaches. They are arranged in a pattern system that makes dependencies between them explicit. We describe step-by-step how the pattern system can be used to analyze a given security problem and how solution approaches can be found. Further, we introduce a new frame that focuses on the privacy requirement anonymity.","PeriodicalId":314834,"journal":{"name":"18th International Workshop on Database and Expert Systems Applications (DEXA 2007)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125306137","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}
Neuro-genetic systems are biologically inspired computational models that use evolutionary algorithms (EAs) in conjunction with neural networks (NNs) to solve problems. They are especially useful in classification problems in which classifier systems are not able to provide easy answers. In this paper a novel neuro-genetic approach is used in order to predict a known classification problem, related to dermatology diseases.
{"title":"Dermatology Disease Classification via Novel Evolutionary Artificial Neural Network","authors":"A. Azzini, S. Marrara","doi":"10.1109/DEXA.2007.71","DOIUrl":"https://doi.org/10.1109/DEXA.2007.71","url":null,"abstract":"Neuro-genetic systems are biologically inspired computational models that use evolutionary algorithms (EAs) in conjunction with neural networks (NNs) to solve problems. They are especially useful in classification problems in which classifier systems are not able to provide easy answers. In this paper a novel neuro-genetic approach is used in order to predict a known classification problem, related to dermatology diseases.","PeriodicalId":314834,"journal":{"name":"18th International Workshop on Database and Expert Systems Applications (DEXA 2007)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131764088","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}
In this paper, we examine the application of manifold learning to the clustering problem. The method used is Locality Preserving Projections (LPP), which is chosen because of its computational efficiency. A detailed derivation of the method is presented, as well as the theoretical justification behind it. Experiments performed on CMU's PIE database show that the projections created by LPP yield better clustering results than those obtained by k-means alone.
{"title":"Unsupervised Learning of Manifolds via Linear Approximations","authors":"H. Kingravi, M. E. Celebi, P. Rajauria","doi":"10.1109/DEXA.2007.107","DOIUrl":"https://doi.org/10.1109/DEXA.2007.107","url":null,"abstract":"In this paper, we examine the application of manifold learning to the clustering problem. The method used is Locality Preserving Projections (LPP), which is chosen because of its computational efficiency. A detailed derivation of the method is presented, as well as the theoretical justification behind it. Experiments performed on CMU's PIE database show that the projections created by LPP yield better clustering results than those obtained by k-means alone.","PeriodicalId":314834,"journal":{"name":"18th International Workshop on Database and Expert Systems Applications (DEXA 2007)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122187357","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}
With the increasing number of users and applications, enterprises or organizations need to effectively protect their important information and easily administrate the security policy. In this paper we analyze the existing access control models and propose an improved role-based access control model and its administration with practical experience to handle with the user privilege assignment relation flexibly.
{"title":"A Flexible Applicable RBAC Model and Its Administration","authors":"Zhenxing Luo, NuerMaimaiti Heilili, Zuoquan Lin","doi":"10.1109/DEXA.2007.7","DOIUrl":"https://doi.org/10.1109/DEXA.2007.7","url":null,"abstract":"With the increasing number of users and applications, enterprises or organizations need to effectively protect their important information and easily administrate the security policy. In this paper we analyze the existing access control models and propose an improved role-based access control model and its administration with practical experience to handle with the user privilege assignment relation flexibly.","PeriodicalId":314834,"journal":{"name":"18th International Workshop on Database and Expert Systems Applications (DEXA 2007)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115030067","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}
The current effort to extend the power of information systems by making use of the semantics associated with terms and structures has resulted in a need to establish correspondences between different systems to allow a rich exchange of information. This paper describes the early efforts taking place in the STASIS project to identify the issues underlying support for mapping of corresponding entities between such heterogeneous systems. The STASIS system is meant to help a user establish such mappings by exploiting a semantic environment where he/she can contribute his/her own entities and relate them with other pre-existing entities. This process needs support at the entity representation level, to encapsulate each item into an appropriately rich representation structure, and at the logical level, where the resulting model is verified for consistency towards its future use. Examples are offered and discussed to highlight the issues and propose solutions.
{"title":"Mapping of heterogeneous schemata, business structures, and terminologies","authors":"D. Beneventano, S. E. Haoum, D. Montanari","doi":"10.1109/DEXA.2007.123","DOIUrl":"https://doi.org/10.1109/DEXA.2007.123","url":null,"abstract":"The current effort to extend the power of information systems by making use of the semantics associated with terms and structures has resulted in a need to establish correspondences between different systems to allow a rich exchange of information. This paper describes the early efforts taking place in the STASIS project to identify the issues underlying support for mapping of corresponding entities between such heterogeneous systems. The STASIS system is meant to help a user establish such mappings by exploiting a semantic environment where he/she can contribute his/her own entities and relate them with other pre-existing entities. This process needs support at the entity representation level, to encapsulate each item into an appropriately rich representation structure, and at the logical level, where the resulting model is verified for consistency towards its future use. Examples are offered and discussed to highlight the issues and propose solutions.","PeriodicalId":314834,"journal":{"name":"18th International Workshop on Database and Expert Systems Applications (DEXA 2007)","volume":"356 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134457968","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}
Folksonomies, collaboratively created sets of metadata, are becoming more and more important for organising information and knowledge of communites in the Web. While for a single user the difference to keyword assignment is marginal, the power of folksonomies emerges from the collaborative aspects. Folksonomies are already issue of research. Within this publication we analyse underlying statistical properties of broad folksonomies aiming to identify laws and characteristics, which allow inferring properties for folksonomy based retrieval. The actual benefit of folksonomies for retrieval and the derived methods are concluded from experiments with aggregated data from del.icio.us1.
{"title":"Aspects of Broad Folksonomies","authors":"M. Lux, M. Granitzer, Roman Kern","doi":"10.1109/DEXA.2007.80","DOIUrl":"https://doi.org/10.1109/DEXA.2007.80","url":null,"abstract":"Folksonomies, collaboratively created sets of metadata, are becoming more and more important for organising information and knowledge of communites in the Web. While for a single user the difference to keyword assignment is marginal, the power of folksonomies emerges from the collaborative aspects. Folksonomies are already issue of research. Within this publication we analyse underlying statistical properties of broad folksonomies aiming to identify laws and characteristics, which allow inferring properties for folksonomy based retrieval. The actual benefit of folksonomies for retrieval and the derived methods are concluded from experiments with aggregated data from del.icio.us1.","PeriodicalId":314834,"journal":{"name":"18th International Workshop on Database and Expert Systems Applications (DEXA 2007)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122136843","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}
Associative classification is a supervised classification method. Many experimental studies have shown that associative classification is a promising approach. There are several associative classification approaches. However, the latter suffer from a major drawback: the huge number of the generated classification rules which takes efforts to select the best ones in order to construct the classifier. To overcome such drawback, we propose in this paper a new direct associative classification method called IGARC, an improvement of GARC approach, that extracts directly generic associative classification rules from a training set in order to reduce the number of associative classification rules without jeopardizing the classification accuracy. A detailed description of this method is presented, as well as the experimentation study on 12 benchmark data sets proving that IGARC is highly competitive in terms of accuracy in comparison with popular classification approaches.
{"title":"Integrated Generic Association Rule Based Classifier","authors":"I. Bouzouita, S. Elloumi","doi":"10.1109/DEXA.2007.145","DOIUrl":"https://doi.org/10.1109/DEXA.2007.145","url":null,"abstract":"Associative classification is a supervised classification method. Many experimental studies have shown that associative classification is a promising approach. There are several associative classification approaches. However, the latter suffer from a major drawback: the huge number of the generated classification rules which takes efforts to select the best ones in order to construct the classifier. To overcome such drawback, we propose in this paper a new direct associative classification method called IGARC, an improvement of GARC approach, that extracts directly generic associative classification rules from a training set in order to reduce the number of associative classification rules without jeopardizing the classification accuracy. A detailed description of this method is presented, as well as the experimentation study on 12 benchmark data sets proving that IGARC is highly competitive in terms of accuracy in comparison with popular classification approaches.","PeriodicalId":314834,"journal":{"name":"18th International Workshop on Database and Expert Systems Applications (DEXA 2007)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122276847","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}
In this paper we present and study a clustering technique based on genetic algorithms Clustering Genetic Algorithm. Performance of the algorithm is demonstrated on experiments. We have shown that it outperforms the k-means algorithm on some tasks. In addition, it is capable of optimising the number of clusters for tasks with well formed and separated clusters.
{"title":"Clustering Genetic Algorithm","authors":"P. Kudová","doi":"10.1109/DEXA.2007.65","DOIUrl":"https://doi.org/10.1109/DEXA.2007.65","url":null,"abstract":"In this paper we present and study a clustering technique based on genetic algorithms Clustering Genetic Algorithm. Performance of the algorithm is demonstrated on experiments. We have shown that it outperforms the k-means algorithm on some tasks. In addition, it is capable of optimising the number of clusters for tasks with well formed and separated clusters.","PeriodicalId":314834,"journal":{"name":"18th International Workshop on Database and Expert Systems Applications (DEXA 2007)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125100775","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}
H. Nakakubo, Shinsuke Nakajima, K. Hatano, Jun Miyazaki, Shunsuke Uemura
We propose a new Web page scoring method based on the link analysis among sets of Web pages. Conventional link analyses such as PageRank and HITS calculate importance degree of each Web page; however, the authors of Web pages often create multiple pages to describe a specific topic. The importance degrees of such multiple Web pages cannot be derived by the conventional link analyses accurately. To cope with this problem, we need to treat the Web pages with the same contents edited by the same author as a Web page set (WPS). After constructing the link structure among WPSs, we calculate their importance degrees by using conventional link analysis schemes. In this paper, we compared our approach with the conventional method by using the NTCIR test collection, and found that our approach was better than the conventional method in terms of both WRR and DCG evaluation measures.
{"title":"Web Page Scoring Based on Link Analysis ofWeb Page Sets","authors":"H. Nakakubo, Shinsuke Nakajima, K. Hatano, Jun Miyazaki, Shunsuke Uemura","doi":"10.1109/DEXA.2007.126","DOIUrl":"https://doi.org/10.1109/DEXA.2007.126","url":null,"abstract":"We propose a new Web page scoring method based on the link analysis among sets of Web pages. Conventional link analyses such as PageRank and HITS calculate importance degree of each Web page; however, the authors of Web pages often create multiple pages to describe a specific topic. The importance degrees of such multiple Web pages cannot be derived by the conventional link analyses accurately. To cope with this problem, we need to treat the Web pages with the same contents edited by the same author as a Web page set (WPS). After constructing the link structure among WPSs, we calculate their importance degrees by using conventional link analysis schemes. In this paper, we compared our approach with the conventional method by using the NTCIR test collection, and found that our approach was better than the conventional method in terms of both WRR and DCG evaluation measures.","PeriodicalId":314834,"journal":{"name":"18th International Workshop on Database and Expert Systems Applications (DEXA 2007)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127280800","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：