Data Reduction Method for Categorical Data Clustering Export

@incollection{Rendon2008, abstract = {Categorical data clustering constitutes an important part of data mining; its relevance has recently drawn attention from several researchers. As a step in data mining, however, clustering encounters the problem of large amount of data to be processed. This article offers a solution for categorical clustering algorithms when working with high volumes of data by means of a method that summarizes the database. This is done using a structure called CM-tree. In order to test our method, the K-Modes and Click clustering algorithms were used with several databases. Experiments demonstrate that the proposed summarization method improves execution time, without losing clustering quality.}, author = {Rend\'{o}n, Er\'{e}ndira and S\'{a}nchez, J. and Garcia, Rene and Abundez, Itzel and Gutierrez, Citlalih and Gasca, Eduardo}, citeulike-article-id = {3987830}, citeulike-linkout-0 = {http://dblp.uni-trier.de/rec/bibtex/conf/iberamia/RendonSGAGG08}, citeulike-linkout-1 = {http://dx.doi.org/10.1007/978-3-540-88309-8_15}, citeulike-linkout-2 = {http://www.springerlink.com/content/y551uq4183664755}, doi = {10.1007/978-3-540-88309-8_15}, journal = {Advances in Artificial Intelligence – IBERAMIA 2008}, keywords = {clustering, db, entityguides, phd, summary}, pages = {143--152}, posted-at = {2009-01-31 09:34:44}, priority = {3}, title = {Data Reduction Method for Categorical Data Clustering}, url = {http://dx.doi.org/10.1007/978-3-540-88309-8_15}, year = {2008} }

TY - CHAP ID - Rendon2008 L3 - citeulike-article-id:3987830 N2 - Categorical data clustering constitutes an important part of data mining; its relevance has recently drawn attention from several researchers. As a step in data mining, however, clustering encounters the problem of large amount of data to be processed. This article offers a solution for categorical clustering algorithms when working with high volumes of data by means of a method that summarizes the database. This is done using a structure called CM-tree. In order to test our method, the K-Modes and Click clustering algorithms were used with several databases. Experiments demonstrate that the proposed summarization method improves execution time, without losing clustering quality. JF - Advances in Artificial Intelligence – IBERAMIA 2008 EP - 152 TI - Data Reduction Method for Categorical Data Clustering SP - 143 KW - clustering KW - db KW - entityguides KW - phd KW - summary AU - Rendón, Eréndira AU - Sánchez, J AU - Garcia, Rene AU - Abundez, Itzel AU - Gutierrez, Citlalih AU - Gasca, Eduardo PY - 2008/// UR - http://dx.doi.org/10.1007/978-3-540-88309-8_15 ER -