{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2022,4,3]],"date-time":"2022-04-03T14:08:08Z","timestamp":1648994888353},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2009,6,17]],"date-time":"2009-06-17T00:00:00Z","timestamp":1245196800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Data Min Knowl Disc"],"published-print":{"date-parts":[[2010,1]]},"DOI":"10.1007\/s10618-009-0134-5","type":"journal-article","created":{"date-parts":[[2009,6,16]],"date-time":"2009-06-16T10:36:10Z","timestamp":1245148570000},"page":"1-27","source":"Crossref","is-referenced-by-count":6,"title":["SCALE: a scalable framework for efficiently clustering transactional data"],"prefix":"10.1007","volume":"20","author":[{"given":"Hua","family":"Yan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Keke","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ling","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhang","family":"Yi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2009,6,17]]},"reference":[{"key":"134_CR1","doi-asserted-by":"crossref","unstructured":"Abello J, Resende MGC, Sudarsky S (2002) Massive quasi-clique detection. In: Proceedings of the 5th Latin American symposium on theoretical informatics, pp 598\u2013612","DOI":"10.1007\/3-540-45995-2_51"},{"issue":"1","key":"134_CR2","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":"134_CR3","unstructured":"Agrawal R, Srikant R (1994) Fast algorithms for mining association rules. In: Proceedings of the 20th international conference on very large data bases (VLDB), pp 487\u2013499"},{"key":"134_CR4","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), pp 123\u2013146","DOI":"10.1007\/978-3-540-24741-8_9"},{"key":"134_CR5","doi-asserted-by":"crossref","unstructured":"Babcock B, Datar M, Motwani R, O\u2019Callaghan L (2003) Maintaining variance and k-medians over data stream windows. In: Proceedings of the 22nd ACM SIGMOD-SIGACT-SIGART symposium on principles of database systems, pp 234\u2013243","DOI":"10.1145\/773153.773176"},{"key":"134_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), pp 582\u2013589","DOI":"10.1145\/584792.584888"},{"key":"134_CR7","doi-asserted-by":"crossref","unstructured":"Brijs T, Swinnen G, Vanhoof K, Wets G (1999) Using association rules for product assortment decisions: a case study. In: Proceedings of the 5th ACM SIGKDD international conference on knowledge discovery and data mining, pp 254\u2013260","DOI":"10.1145\/312129.312241"},{"key":"134_CR8","doi-asserted-by":"crossref","unstructured":"Chakrabarti D, Papadimitriou S, Modha DS, Faloutsos C (2004) Fully automatic cross-associations. In: Proceedings of ACM SIGKDD international conference on knowledge discovery and data mining, pp 79\u201388","DOI":"10.21236\/ADA459025"},{"issue":"4","key":"134_CR9","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":"134_CR10","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":"134_CR11","doi-asserted-by":"crossref","unstructured":"Dhillon IS (2001) Co-clustering documents and words using bipartite spectral graph partitioning. In: Proceedings of the 7th ACM SIGKDD international conference on knowledge discovery and data mining, pp 269\u2013274","DOI":"10.1145\/502512.502550"},{"key":"134_CR12","doi-asserted-by":"crossref","unstructured":"Ding CHQ, He X, Zha H, Gu M, Simon HD (2001) A min\u2013max cut algorithm for graph partitioning and data clustering. In: Proceedings of ICDM 2001, pp 107\u2013114","DOI":"10.1109\/ICDM.2001.989507"},{"key":"134_CR13","doi-asserted-by":"crossref","unstructured":"Ganti V, Gehrke J, Ramakrishnan R (1999) Cactus: clustering categorical data using summaries. In: Proceedings of ACM SIGKDD international conference on knowledge discovery and data mining, pp 73\u201383","DOI":"10.1145\/312129.312201"},{"key":"134_CR14","unstructured":"Gibson D, Kleinberg J, Raghavan P (1998) Clustering categorical data: an approach based on dynamical systems. In: Proceedings of the 24th international conference on very large data bases (VLDB), pp 311\u2013322"},{"key":"134_CR15","doi-asserted-by":"crossref","unstructured":"Guha S, Rastogi R, Shim K (1999) Rock: a robust clustering algorithm for categorical attributes. In: Proceedings of IEEE international conference on data engineering (ICDE), pp 512\u2013521","DOI":"10.1109\/ICDE.1999.754967"},{"key":"134_CR16","doi-asserted-by":"crossref","unstructured":"Guha S, Mishra N, Motwani R (2000) Clustering data streams. In: Proceeding of IEEE symposium on foundations of computer science, pp 359\u2013366","DOI":"10.1109\/SFCS.2000.892124"},{"issue":"2","key":"134_CR17","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":"134_CR18","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, New York"},{"issue":"3","key":"134_CR19","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1023\/A:1009769707641","volume":"2","author":"Z Huang","year":"1998","unstructured":"Huang Z (1998) Extensions to the k-means algorithm for clustering large data sets with categorical values. Data Min Knowl Discov 2(3): 283\u2013304","journal-title":"Data Min Knowl Discov"},{"key":"134_CR20","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":"134_CR21","first-page":"1069","volume":"4304","author":"Y Li","year":"2006","unstructured":"Li Y, Gopalan R (2006) Clustering transactional data streams. Lect Notes Artif Intell 4304: 1069\u20131073","journal-title":"Lect Notes Artif Intell"},{"key":"134_CR22","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), pp 68\u201375","DOI":"10.1145\/1015330.1015404"},{"key":"134_CR23","doi-asserted-by":"crossref","unstructured":"Meil\u030c M (2005) Comparing clusterings: an axiomatic view. In: Proceedings of the 22nd international conference on machine learning, pp 577\u2013584","DOI":"10.1145\/1102351.1102424"},{"key":"134_CR24","doi-asserted-by":"crossref","unstructured":"Mishra N, Ron D, Swaminathan R (2003) On finding large conjunctive clusters. In: Proceedings of the 16th annual conference on computational learning theory (COLT), pp 448\u2013462","DOI":"10.1007\/978-3-540-45167-9_33"},{"key":"134_CR25","doi-asserted-by":"crossref","unstructured":"Ong K-l, Li Wy, Ng W-k, Lim E-p (2004) SCLOPE: an algorithm for clustering data streams of categorical attributes. In: Proceedings of international conference on data warehousing and knowledge discovery, pp 209\u2013218","DOI":"10.1007\/978-3-540-30076-2_21"},{"key":"134_CR26","doi-asserted-by":"crossref","unstructured":"Ordonez C (2003) Clustering binary data streams with K-means. In: Proceedings of the 8th ACM SIGMOD workshop on research issues on data mining and knowledge discovery, pp 12\u201319","DOI":"10.1145\/882082.882087"},{"key":"134_CR27","unstructured":"Tishby N, Pereira FC, Bialek W (1999) The information bottleneck method. In: Proceedings of the 37th annual allerton conference on communication, control and computing, pp 368\u2013377"},{"key":"134_CR28","doi-asserted-by":"crossref","unstructured":"Wang K, Xu C, Liu B (1999) Clustering transactions using large items. In: Proceedings of ACM conference on information and knowledge management (CIKM), pp 483\u2013490","DOI":"10.1145\/319950.320054"},{"key":"134_CR29","doi-asserted-by":"crossref","unstructured":"Yan H, Zhang L, Zhang Y (2005) Clustering categorical data using coverage density. In: Proceedings of international conference on advance data mining and application, pp 248\u2013255","DOI":"10.1007\/11527503_30"},{"key":"134_CR30","doi-asserted-by":"crossref","unstructured":"Yan H, Chen K, Liu L (2006) Efficiently clustering transactional data with weighted coverage density. In: Proceedings of ACM conference on information and knowledge management (CIKM), pp 367\u2013376","DOI":"10.1145\/1183614.1183668"},{"key":"134_CR31","doi-asserted-by":"crossref","unstructured":"Yang Y, Guan X, You J (2002) Clope: a fast and effective clustering algorithm for transactional data. In: Proceedings of the 8th ACM SIGKDD international conference on knowledge discovery and data mining, pp 682\u2013687","DOI":"10.1145\/775047.775149"},{"key":"134_CR32","doi-asserted-by":"crossref","unstructured":"Zha H, He X, Ding CHQ, Gu M, Simon HD (2001) Bipartite graph partitioning and data clustering. In: Proceedings of the 10th international conference on information and knowledge management, pp 25\u201332","DOI":"10.2172\/816202"}],"container-title":["Data Mining and Knowledge Discovery"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10618-009-0134-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10618-009-0134-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10618-009-0134-5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,30]],"date-time":"2019-05-30T19:29:40Z","timestamp":1559244580000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10618-009-0134-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009,6,17]]},"references-count":32,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2010,1]]}},"alternative-id":["134"],"URL":"https:\/\/doi.org\/10.1007\/s10618-009-0134-5","relation":{},"ISSN":["1384-5810","1573-756X"],"issn-type":[{"value":"1384-5810","type":"print"},{"value":"1573-756X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2009,6,17]]}}}