{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T09:51:00Z","timestamp":1760608260464},"reference-count":27,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2005,10,29]],"date-time":"2005-10-29T00:00:00Z","timestamp":1130544000000},"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":[[2006,7]]},"DOI":"10.1007\/s10115-005-0210-0","type":"journal-article","created":{"date-parts":[[2005,11,3]],"date-time":"2005-11-03T06:34:47Z","timestamp":1130999687000},"page":"17-40","source":"Crossref","is-referenced-by-count":66,"title":["Fast and exact out-of-core and distributed k-means clustering"],"prefix":"10.1007","volume":"10","author":[{"given":"Ruoming","family":"Jin","sequence":"first","affiliation":[]},{"given":"Anjan","family":"Goswami","sequence":"additional","affiliation":[]},{"given":"Gagan","family":"Agrawal","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2005,10,29]]},"reference":[{"key":"210_CR1","doi-asserted-by":"crossref","unstructured":"Badoiu M, Har-Pelad S, Indyk P (2002) Approximate clustering via core-sets. In: Proceedings of the annual ACM symposium on theory of computing","DOI":"10.1145\/509907.509947"},{"key":"210_CR2","unstructured":"Berkhin P (2002) Survey of clustering data mining techniques. Technical report, Accrue Software"},{"key":"210_CR3","unstructured":"Bottou L, Bengio Y (1995) Convergence properties of the K-means algorithms. In: Tesauro G, Touretzky D, Leen T (eds) Advances in neural information processing systems, vol 7. The MIT Press, pp 585\u2013592"},{"key":"210_CR4","unstructured":"Bradley PS, Fayyad U, Reina C (1998) Scaling clustering algorithms to large databases. In: Proceedings of the 4th international conference on knowledge discovery and data mining"},{"key":"210_CR5","doi-asserted-by":"crossref","unstructured":"Charikar M, O'Callaghan L, Panigrahi R (2003) Better streaming algorithms for clustering problems. In: Proceedings of the 35th annual ACM symposium on theory of computing","DOI":"10.1145\/780542.780548"},{"key":"210_CR6","doi-asserted-by":"crossref","unstructured":"Cherikar M, Chekuri C, Feder T, Motwani R (1997) Incremental clustering and dynamic information retrieval. In: Proceedings of symposium of theory of computing","DOI":"10.1145\/258533.258657"},{"key":"210_CR7","first-page":"towards","volume":"grid","author":"Chervenak","year":"2001","unstructured":"Chervenak A, Foster I, Kesselman C, Salisbusy C, Tuecke S (2001) The data grid: towards an architecture for the distributed management and analysis of large scientific datasets. J Network Comput Appl","journal-title":"The data"},{"key":"210_CR8","unstructured":"Lopez de Teruel PE, Garcia JM, Acacio M (1999) A parallel algorithm and its application to computer vision. In: Proceedings of PDPTA"},{"key":"210_CR9","unstructured":"Dhillon IS, Modha DS (1999) A data-clustering algorithm on distributed memory multiprocessors. In: Lecture notes in computer science, revised papers from large-scale parallel data mining, workshop on large-scale parallel KDD systems. SIGKDD, Springer-Verlag, Berlin Heidelberg New York, pp 245\u2013260"},{"key":"210_CR10","unstructured":"Domingos P, Hulten G (2001) A general method for scaling up machine learning algorithms and its application to clustering. In: Proceedings of the 18th international conference on machine learning"},{"issue":"1","key":"210_CR11","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1145\/360402.360419","volume":"2","author":"F Farnstrom","year":"2000","unstructured":"Farnstrom F, Lewis J, Elkan C (2000) Scalability for clustering algorithms revisited. SIGKDD Explor 2(1): 51\u201357","journal-title":"SIGKDD Explor"},{"key":"210_CR12","doi-asserted-by":"crossref","unstructured":"Forman G, Zhang B (2000) Distributed data clustering can be efficient and exact. SIGKDD Explor 2","DOI":"10.1145\/380995.381010"},{"key":"210_CR13","unstructured":"Ghosh J (2003) Scalable clustering methods for data mining. In: Ye N (ed) Handbook of data mining. Lawrence Earlbaum Associates, pp 247\u2013277"},{"issue":"3","key":"210_CR14","doi-asserted-by":"crossref","first-page":"515","DOI":"10.1109\/TKDE.2003.1198387","volume":"15","author":"S Guha","year":"2003","unstructured":"Guha S, Meyerson A, Mishra N, Motwani R, O'Callaghan L (2003) Clustering data streams: theory and practice. IEEE Trans on Knowl Data Eng 15(3): 515\u2013528","journal-title":"IEEE Trans on Knowl Data Eng"},{"key":"210_CR15","first-page":"concepts","volume":"mining","author":"Han","year":"2000","unstructured":"Han J, Kamber M (2000) Data mining: concepts and techniques. Morgan Kaufmann","journal-title":"Data"},{"key":"210_CR16","doi-asserted-by":"crossref","first-page":"100","DOI":"10.2307\/2346830","volume":"28","author":"JA Hartigan","year":"1979","unstructured":"Hartigan JA, Wong MA (1979) A k-means clustering algorithm. Appl Stat 28:100\u2013108","journal-title":"Appl Stat"},{"key":"210_CR17","unstructured":"Jain AK, Dubes RC (1988) Algorithms for clustering data. Prentice-Hall International"},{"key":"210_CR18","unstructured":"Januzaj E, Kriegel H-P, Pfeifle M (2003) Towards effective and efficient distributed clustering. In: Proceedings of the ICDM 2003 workshop on clustering large datasets"},{"issue":"4","key":"210_CR19","doi-asserted-by":"crossref","first-page":"422","DOI":"10.1007\/PL00011677","volume":"3","author":"H Kargupta","year":"2001","unstructured":"Kargupta H, Huang W, Sivakumar K, Johnson E (2001) Distributed clustering using collective principal component analysis. Knowl Inf Syst 3(4): 422\u2013448","journal-title":"Knowl Inf Syst"},{"key":"210_CR20","unstructured":"Kargupta H, Chan P (1999) (eds) Advances in distributed data mining. AAI\/MIT Press"},{"key":"210_CR21","doi-asserted-by":"crossref","unstructured":"Kruengkrai C, Jaruskulchai C (2002) A parallel learning algorithm for text classification. In: Proceedings of ACM SIGKDD 2002, ACM Press, pp 201\u2013206","DOI":"10.1145\/775047.775077"},{"key":"210_CR22","unstructured":"MacQueen J (1967) Some methods for classification and analysis of multivariate observations. In: Proceedings of the 5th Berkeley symposium on mathematical statistics and probability, vol 1, pp 281\u2013297"},{"key":"210_CR23","unstructured":"Nittel S, Leung KT, Braverman A (2003) Scaling clustering algorithms for massive data sets using data stream. In: Dayal U, Ramamritham K, Vijayaraman TM (eds) Proceedings of the 19th international conference on data engineering, March 5\u20138, 2003, Bangalore, India. IEEE Computer Society"},{"key":"210_CR24","unstructured":"OCallaghan L, Mishra N, Meyerson A, Guha S, Motwani R (2002) Streaming-data algorithms for high-quality clustering. In: Proceedings of international conference of data engineering"},{"key":"210_CR25","doi-asserted-by":"crossref","unstructured":"Parthasarathy S, Ogihara M (2000) Clustering distributed homogeneous datasets. In: Proceedings of the 4th European conference on principles of data mining and knowledge discovery, Lecture notes in computer science, vol 1910. pp 566\u2013574. Springer-Verlag, Berlin Heidelberg New York","DOI":"10.1007\/3-540-45372-5_67"},{"key":"210_CR26","doi-asserted-by":"crossref","unstructured":"Pelleg D, Moore A (1999) Accelerating exact k-means algorithms with geometric reasoning. In: Proceedings of 5th international conference of knowledge discovery and data mining, pp 277\u2013281","DOI":"10.1145\/312129.312248"},{"issue":"2","key":"210_CR27","first-page":"157","volume":"11","author":"NF Samatova","year":"2002","unstructured":"Samatova NF, Ostrouchov G, Geist A, Melechko A (2002) RACHET: an efficient cover-based merging of clustering hierarchies from distributed datasets. Distrib Parallel Databases 11(2):157\u2013180","journal-title":"Distrib Parallel Databases"}],"container-title":["Knowledge and Information Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-005-0210-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10115-005-0210-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-005-0210-0","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,29]],"date-time":"2019-05-29T10:10:14Z","timestamp":1559124614000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10115-005-0210-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2005,10,29]]},"references-count":27,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2006,7]]}},"alternative-id":["210"],"URL":"https:\/\/doi.org\/10.1007\/s10115-005-0210-0","relation":{},"ISSN":["0219-1377","0219-3116"],"issn-type":[{"value":"0219-1377","type":"print"},{"value":"0219-3116","type":"electronic"}],"subject":[],"published":{"date-parts":[[2005,10,29]]}}}