{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T15:09:37Z","timestamp":1782313777586,"version":"3.54.5"},"reference-count":76,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2003,5,1]],"date-time":"2003-05-01T00:00:00Z","timestamp":1051747200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Knowl. Data Eng."],"published-print":{"date-parts":[[2003,5]]},"DOI":"10.1109\/tkde.2003.1198387","type":"journal-article","created":{"date-parts":[[2003,5,14]],"date-time":"2003-05-14T18:46:26Z","timestamp":1052937986000},"page":"515-528","source":"Crossref","is-referenced-by-count":537,"title":["Clustering data streams: theory and practice"],"prefix":"10.1109","volume":"15","author":[{"given":"S.","family":"Guha","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"A.","family":"Meyerson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"N.","family":"Mishra","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"R.","family":"Motwani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"L.","family":"O'Callaghan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/380752.380858"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/s0196-6774(02)00295-x"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/276304.276314"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/237814.237823"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/304182.304187"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/276698.276718"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/380752.380755"},{"key":"ref8","article-title":"Sampling from a Moving Window over Streaming Data","volume-title":"Proc. ACM Symp. Discrete Algorithms","author":"Babcock"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/380752.380754"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/301250.301367"},{"key":"ref11","first-page":"9","article-title":"Scaling Clustering Algorithms to Large Databases","volume-title":"Proc. ACM SIGKDD Int\u2019l Conf. Knowledge Discovery and Data Mining","author":"Bradley"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/335168.335230"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/258533.258657"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/SFFCS.1999.814609"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/301250.301257"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-69346-7_14"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1137\/S0097539701398363"},{"key":"ref18","article-title":"Clustering in Large Graphs and Matrices","volume-title":"Proc. ACM Symp. Discrete Algorithms","author":"Drineas"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.5555\/3001460.3001507"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/360402.360419"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/62212.62255"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/SFFCS.1999.814623"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/0022-0000(85)90041-8"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/SFCS.1998.743487"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/69.908980"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1090\/dimacs\/050\/02"},{"key":"ref27","article-title":"Fast, Small-Space Algorithms for Approximate Histogram Maintanance","volume-title":"Proc. Ann. ACM Symp. Theory of Computing","author":"Gilbert"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/B978-155860869-6\/50047-0"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/509907.509933"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/375663.375670"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1006\/jagm.1998.0993"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2002.994775"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/380752.380841"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/SFCS.2000.892124"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/276304.276312"},{"key":"ref36","first-page":"311","article-title":"Sampling-Based Estimation of the Number of Distinct Values of an Attribute","volume-title":"Proc. Int\u2019l Conf. Very Large Data Bases","author":"Haas"},{"key":"ref37","volume-title":"Data Mining: Concepts and Techniques","author":"Han","year":"2000"},{"key":"ref38","article-title":"Computing on Data Streams","author":"Henzinger","year":"1998"},{"key":"ref39","article-title":"An Efficient Approach to Clustering Large Multimedia Databases with Noise","volume-title":"Proc. Fourth Int\u2019l Conf. Knowledge Discovery and Data Mining","author":"Hinneburg"},{"key":"ref40","article-title":"Optimal Grid-Clustering: Towards Breaking the Curse of Dimensionality in High-Dimensional Clustering","volume-title":"Proc. Int\u2019l Conf. Very Large Data Bases","author":"Hinneburg"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1287\/moor.10.2.180"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/301250.301366"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/SFFCS.1999.814587"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/SFCS.2000.892082"},{"key":"ref45","volume-title":"Algorithms for Clustering Data.","author":"Jain","year":"1988"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/509907.510012"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/SFFCS.1999.814571"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/SFCS.2000.892125"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1137\/0137041"},{"key":"ref50","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316801","volume-title":"Finding Groups in Data. An Introduction to Cluster Analysis.","author":"Kaufman","year":"1990"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1006\/jcss.1998.1578"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-48481-7_33"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/0020-0190(92)90208-D"},{"key":"ref54","article-title":"$\\big. \\epsilon\\bigr.$-approximations with Minimum Packing Constraint Violations","volume-title":"Proc. Ann. ACM Symp. Theory of Computing","author":"Lin"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1023\/A:1009735908398"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/276305.276342"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/304181.304204"},{"key":"ref58","article-title":"A Statistical Method for Profiling Network Traffic","volume-title":"Proc. Workshop Intrusion Detection and Network Monitoring","author":"Marchette"},{"key":"ref59","article-title":"The Onlike Median Problem","volume-title":"Proc. ACM Symp. Foundations of Computer Science","author":"Mettu"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1023\/b:mach.0000033114.18632.e0"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/SFCS.2001.959917"},{"key":"ref62","volume-title":"Discrete Location Theory","author":"Mirchandani","year":"1990"},{"key":"ref63","article-title":"Sublinear Time Approximate Clustering","volume-title":"Proc. ACM Symp. Discrete Algorithms","author":"Mishra"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1016\/0304-3975(80)90061-4"},{"key":"ref65","article-title":"Offline Network Intrusion Detection: Looking for Footprints","author":"Nauta","year":"2000"},{"key":"ref66","first-page":"144","article-title":"Efficient and Effective Clustering Methods for Spatial Data Mining","volume-title":"Proc. Int\u2019l Conf. Very Large Data Bases","author":"Ng"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2002.994785"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/SFCS.2000.892123"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/564691.564739"},{"key":"ref70","first-page":"428","article-title":"Wavecluster: A Multi-Resolution Clustering Approach for Very Large Spatial Databases","volume-title":"Proc. Int\u2019l Conf. Very Large Data Bases","author":"Sheikholeslami"},{"key":"ref71","first-page":"265","article-title":"Approximation Algorithms for Facility Location Problems","volume-title":"Proc. Ann. ACM Symp. Theory of Computing","author":"Shmoys"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1145\/564691.564741"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-48224-5_21"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/springerreference_57547"},{"key":"ref75","article-title":"Sting: A Statistical Information Grid Approach to Spatial Data Mining","volume-title":"Proc. Int\u2019l Conf. Very Large Data Bases","author":"Wang"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1145\/233269.233324"}],"container-title":["IEEE Transactions on Knowledge and Data Engineering"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/69\/26974\/01198387.pdf?arnumber=1198387","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,16]],"date-time":"2025-03-16T04:03:07Z","timestamp":1742097787000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/1198387\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2003,5]]},"references-count":76,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2003,5]]}},"URL":"https:\/\/doi.org\/10.1109\/tkde.2003.1198387","relation":{},"ISSN":["1041-4347"],"issn-type":[{"value":"1041-4347","type":"print"}],"subject":[],"published":{"date-parts":[[2003,5]]}}}