{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T19:09:37Z","timestamp":1776280177976,"version":"3.50.1"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2008,9,4]],"date-time":"2008-09-04T00:00:00Z","timestamp":1220486400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Knowl Inf Syst"],"published-print":{"date-parts":[[2009,7]]},"DOI":"10.1007\/s10115-008-0159-x","type":"journal-article","created":{"date-parts":[[2008,9,3]],"date-time":"2008-09-03T15:53:00Z","timestamp":1220457180000},"page":"1-33","source":"Crossref","is-referenced-by-count":29,"title":["\u201cBest K\u201d: critical clustering structures in categorical datasets"],"prefix":"10.1007","volume":"20","author":[{"given":"Keke","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ling","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2008,9,4]]},"reference":[{"issue":"1","key":"159_CR1","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1109\/69.979972","volume":"14","author":"CC Aggarwal","year":"2002","unstructured":"Aggarwal CC, Magdalena C, Yu PS (2002) Finding localized associations in market basket data. IEEE Trans Knowl Data Eng 14(1): 51\u201362","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"159_CR2","volume-title":"Categorical Data Analysis","author":"A Agresti","year":"1990","unstructured":"Agresti A (1990) Categorical Data Analysis. Wiley, NY"},{"key":"159_CR3","doi-asserted-by":"crossref","unstructured":"Andritsos P, Tsaparas P, Miller RJ, Sevcik KC (2004) Limbo:scalable clustering of categorical data. In: Proceedings of international conference on extending database technology (EDBT)","DOI":"10.1007\/978-3-540-24741-8_9"},{"key":"159_CR4","doi-asserted-by":"crossref","unstructured":"Ankerst M, Breunig MM, Kriegel HP, Sander J (1999) OPTICS: Ordering points to identify the clustering structure. In: Proceedings of ACM SIGMOD conference, pp 49\u201360","DOI":"10.1145\/304182.304187"},{"key":"159_CR5","volume-title":"Applications of data mining in computer security","year":"2002","unstructured":"Barbara D, Jajodia S (eds) (2002) Applications of data mining in computer security. Kluwer, Dordrecht"},{"key":"159_CR6","doi-asserted-by":"crossref","unstructured":"Barbara D, Li Y, Couto J (2002) Coolcat: an entropy-based algorithm for categorical clustering. In: Proceedings of ACM conference on information and knowledge management (CIKM)","DOI":"10.1145\/584792.584888"},{"key":"159_CR7","doi-asserted-by":"crossref","unstructured":"Baulieu F (1997) Two variant axiom systems for presence\/absence based dissimilarity coefficients. J Classif 14","DOI":"10.1007\/s003579900009"},{"key":"159_CR8","doi-asserted-by":"crossref","unstructured":"Baxevanis A, Ouellette F (eds) (2001) Bioinformatics: a practical guide to the analysis of genes and proteins, 2nd edn. Wiley, NY","DOI":"10.1002\/0471223921"},{"key":"159_CR9","doi-asserted-by":"crossref","unstructured":"Bock H (1989) Probabilistic aspects in cluster analysis. In: Conceptual and numerical analysis of data. Springer, Berlin","DOI":"10.1007\/978-3-642-75040-3_2"},{"key":"159_CR10","unstructured":"Brand M (1998) An entropic estimator for structure discovery. In: Proceedings Of neural information processing systems (NIPS). pp 723\u2013729"},{"key":"159_CR11","doi-asserted-by":"crossref","unstructured":"Celeux G, Govaert G (1991) Clustering criteria for discrete data and latent class models. J Classif","DOI":"10.1007\/BF02616237"},{"key":"159_CR12","doi-asserted-by":"crossref","unstructured":"Chakrabarti D, Papadimitriou S, Modha DS, Faloutsos C (2004) Fully automatic cross-associations. In: Proceedings of ACM SIGKDD conference","DOI":"10.21236\/ADA459025"},{"issue":"4","key":"159_CR13","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1057\/palgrave.ivs.9500076","volume":"3","author":"K Chen","year":"2004","unstructured":"Chen K, Liu L (2004) VISTA: Validating and refining clusters via visualization. Inf Vis 3(4): 257\u2013270","journal-title":"Inf Vis"},{"key":"159_CR14","unstructured":"Chen K, Liu L (2005) The \u201cbest k\u201d for entropy-based categorical clustering. In: Proceedings of international conference on scientific and statistical database management (SSDBM). pp 253\u2013262"},{"key":"159_CR15","doi-asserted-by":"crossref","unstructured":"Chen K, Liu L (2006) Detecting the change of clustering structure in categorical data streams. In: SIAM data mining conference","DOI":"10.1137\/1.9781611972764.49"},{"key":"159_CR16","doi-asserted-by":"crossref","unstructured":"Cheng CH, Fu AW-C, Zhang Y (1999) Entropy-based subspace clustering for mining numerical data. In: Proceedings of ACM SIGKDD conference","DOI":"10.1145\/312129.312199"},{"key":"159_CR17","doi-asserted-by":"crossref","DOI":"10.1002\/0471200611","volume-title":"Elements of information theory","author":"T Cover","year":"1991","unstructured":"Cover T, Thomas J (1991) Elements of information theory. Wiley, NY"},{"key":"159_CR18","doi-asserted-by":"crossref","unstructured":"Dhillon IS, Mellela S, Modha DS (2003) Information-theoretic co-clustering. In: Proceedings of ACM SIGKDD conference","DOI":"10.1145\/956750.956764"},{"key":"159_CR19","unstructured":"Ester M, Kriegel H-P, Sander J, Xu X (1996) A density-based algorithm for discovering clusters in large spatial databases with noise. In: Second international conference on knowledge discovery and data mining, pp 226\u2013231"},{"key":"159_CR20","doi-asserted-by":"crossref","unstructured":"Ganti V, Gehrke J, Ramakrishnan R (1999) CACTUS-clustering categorical data using summaries. In: Proceedings of ACM SIGKDD Conference","DOI":"10.1145\/312129.312201"},{"key":"159_CR21","doi-asserted-by":"crossref","unstructured":"Gibson D, Kleinberg J, Raghavan P (2000) Clustering categorical data: An approach based on dynamical systems. In: Proceedings of very large databases conference (VLDB). pp 222\u2013236","DOI":"10.1007\/s007780050005"},{"issue":"1","key":"159_CR22","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s10115-006-0009-7","volume":"12","author":"D Gondek","year":"2007","unstructured":"Gondek D, Hofmann T (2007) \u2018Non-redundant data clustering\u2019. Knowl Inf Syst 12(1): 1\u201324","journal-title":"Knowl Inf Syst"},{"issue":"5","key":"159_CR23","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1016\/S0306-4379(00)00022-3","volume":"25","author":"S Guha","year":"2000","unstructured":"Guha S, Rastogi R, Shim K (2000) ROCK: A robust clustering algorithm for categorical attributes. Inf Syst 25(5): 345\u2013366","journal-title":"Inf Syst"},{"issue":"2","key":"159_CR24","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1145\/565117.565124","volume":"31","author":"M Halkidi","year":"2002","unstructured":"Halkidi M, Batistakis Y, Vazirgiannis M (2002) Cluster validity methods: Part I and II. SIGMOD Rec 31(2): 40\u201345","journal-title":"SIGMOD Rec"},{"key":"159_CR25","doi-asserted-by":"crossref","DOI":"10.1007\/978-0-387-21606-5","volume-title":"The elements of statistical learning","author":"T Hastie","year":"2001","unstructured":"Hastie T, Tibshirani R, Friedmann J (2001) The elements of statistical learning. Springer, Berlin"},{"key":"159_CR26","unstructured":"Huang Z (1997) A fast clustering algorithm to cluster very large categorical data sets in data mining. In: Workshop on research issues on data mining and knowledge discovery"},{"key":"159_CR27","volume-title":"Algorithms for clustering data","author":"AK Jain","year":"1988","unstructured":"Jain AK, Dubes RC (1988) Algorithms for clustering data. Prentice hall, New York"},{"key":"159_CR28","doi-asserted-by":"crossref","first-page":"264","DOI":"10.1145\/331499.331504","volume":"31","author":"AK Jain","year":"1999","unstructured":"Jain AK, Dubes RC (1999) Data clustering: a review. ACM Comput Surv 31: 264\u2013323","journal-title":"ACM Comput Surv"},{"key":"159_CR29","volume-title":"Theory of Point Estimation","author":"EL Lehmann","year":"1998","unstructured":"Lehmann EL, Casella G (1998) Theory of Point Estimation. Springer, Berlin"},{"key":"159_CR30","doi-asserted-by":"crossref","unstructured":"Li T, Ma S, Ogihara M (2004) Entropy-based criterion in categorical clustering. In: Proceedings of international conference on machine learning (ICML)","DOI":"10.1145\/1015330.1015404"},{"key":"159_CR31","first-page":"397","volume":"2","author":"C Meek","year":"2002","unstructured":"Meek C, Thiesson B, Heckerman D (2002) The learning-curve sampling method applied to model-based clustering. J Mach Learn Res 2: 397\u2013418","journal-title":"J Mach Learn Res"},{"key":"159_CR32","volume-title":"Applied multivariate techniques","author":"S Sharma","year":"1995","unstructured":"Sharma S (1995) Applied multivariate techniques. Wiley, NY"},{"key":"159_CR33","unstructured":"Tishby N, Pereira FC, Bialek W (1999) The information bottleneck method. In: Proceedings of the 37-th annual allerton conference on communication, control and computing"},{"issue":"1","key":"159_CR34","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1007\/s10115-005-0216-7","volume":"9","author":"J Wang","year":"2006","unstructured":"Wang J, Karypis G (2006) \u2018On efficiently summarizing categorical databases\u2019. Knowl Inf Syst 9(1): 19\u201337","journal-title":"Knowl Inf Syst"},{"key":"159_CR35","volume-title":"Categorical data analysis for geographers and environmental scientists","author":"N Wrigley","year":"1985","unstructured":"Wrigley N (1985) Categorical data analysis for geographers and environmental scientists. Longman, London"},{"issue":"3","key":"159_CR36","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1007\/s10115-005-0197-6","volume":"9","author":"JX Yu","year":"2006","unstructured":"Yu JX, Qian W, Lu H, Zhou A (2006) Finding centric local outliers in categorical\/numerical spaces. Knowl Inf Syst 9(3): 309\u2013338","journal-title":"Knowl Inf Syst"}],"container-title":["Knowledge and Information Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-008-0159-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10115-008-0159-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-008-0159-x","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,29]],"date-time":"2019-05-29T10:10:18Z","timestamp":1559124618000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10115-008-0159-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2008,9,4]]},"references-count":36,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2009,7]]}},"alternative-id":["159"],"URL":"https:\/\/doi.org\/10.1007\/s10115-008-0159-x","relation":{},"ISSN":["0219-1377","0219-3116"],"issn-type":[{"value":"0219-1377","type":"print"},{"value":"0219-3116","type":"electronic"}],"subject":[],"published":{"date-parts":[[2008,9,4]]}}}