%0 Conference Paper %1 oai:CiteSeerPSU:190072 %A wan Ryu, Tae %A Eick, Christoph F. %B Fourth International Conference on Computer Science and Informatics (CS&I'98) %C Research Triangle Park, NC, U.S.A. %D 1998 %K algorithms, genetic programming %T Discovering Discriminant Characteristic Queries from Databases through Clustering %U http://citeseer.ist.psu.edu/190072.html %X this paper, we will describe a methodology and a set of computerized tools that discover characteristic queries as discriminant rules from structured databases. In order to discover useful set of discriminant characteristic queries from a database, our approach is first to cluster the target database and to discover a set of queries from each cluster. Figure 1 depicts the overall steps in our methodology. First, the input data set that user is interested in is selected, preprocessed, and represented in a proper format for clustering process. Second, generalized clustering algorithms are then applied to the preprocessed data set grouping the target database into clusters of objects with similar properties. In the third step, we try to characterize the clusters found in the clustering process. For this purpose, we use a query discovery system called MASSON that uses database queries as its rule representation language 9. MASSON discovers a discriminant query (or set of queries) that describes a given set of objects in databases using genetic programming (GP) 4. The discovered query or a set of queries can distinctively describe the commonalities for the given set of objects with respect to the other objects in a database 8,10. %Z The Pennsylvania State University CiteSeer Archives

@inproceedings{oai:CiteSeerPSU:190072, abstract = {this paper, we will describe a methodology and a set of computerized tools that discover characteristic queries as discriminant rules from structured databases. In order to discover useful set of discriminant characteristic queries from a database, our approach is first to cluster the target database and to discover a set of queries from each cluster. Figure 1 depicts the overall steps in our methodology. First, the input data set that user is interested in is selected, preprocessed, and represented in a proper format for clustering process. Second, generalized clustering algorithms are then applied to the preprocessed data set grouping the target database into clusters of objects with similar properties. In the third step, we try to characterize the clusters found in the clustering process. For this purpose, we use a query discovery system called MASSON that uses database queries as its rule representation language [9]. MASSON discovers a discriminant query (or set of queries) that describes a given set of objects in databases using genetic programming (GP) [4]. The discovered query or a set of queries can distinctively describe the commonalities for the given set of objects with respect to the other objects in a database [8,10].}, added-at = {2008-06-19T17:46:40.000+0200}, address = {Research Triangle Park, NC, U.S.A.}, annote = {The Pennsylvania State University CiteSeer Archives}, author = {wan Ryu, Tae and Eick, Christoph F.}, biburl = {https://www.bibsonomy.org/bibtex/2a5b5c40eed01f99ea41b26712a164e10/brazovayeye}, booktitle = {Fourth International Conference on Computer Science and Informatics (CS\&I'98)}, citeseer-references = {oai:CiteSeerPSU:524488; \cite{oai:CiteSeerPSU:45760}; oai:CiteSeerPSU:97771}, interhash = {bd970f438fcae9ea291196e0a51a1195}, intrahash = {a5b5c40eed01f99ea41b26712a164e10}, keywords = {algorithms, genetic programming}, language = {en}, month = {October 23-28}, notes = {Not verified: try also JCIS-98}, oai = {oai:CiteSeerPSU:190072}, rights = {unrestricted}, timestamp = {2008-06-19T17:50:54.000+0200}, title = {Discovering Discriminant Characteristic Queries from Databases through Clustering}, url = {http://citeseer.ist.psu.edu/190072.html}, year = 1998 }