{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,3]],"date-time":"2025-05-03T23:05:40Z","timestamp":1746313540203,"version":"3.40.4"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319058092"},{"type":"electronic","value":"9783319058108"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014]]},"DOI":"10.1007\/978-3-319-05810-8_24","type":"book-chapter","created":{"date-parts":[[2014,4,16]],"date-time":"2014-04-16T03:31:25Z","timestamp":1397619085000},"page":"357-371","source":"Crossref","is-referenced-by-count":20,"title":["An Efficient K-means Clustering Algorithm on MapReduce"],"prefix":"10.1007","author":[{"given":"Qiuhong","family":"Li","sequence":"first","affiliation":[]},{"given":"Peng","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Wei","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Hao","family":"Hu","sequence":"additional","affiliation":[]},{"given":"Zhongsheng","family":"Li","sequence":"additional","affiliation":[]},{"given":"Junxian","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"24_CR1","unstructured":"http:\/\/hadoop.apache.org\/"},{"key":"24_CR2","unstructured":"http:\/\/mahout.apache.org\/"},{"key":"24_CR3","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"355","DOI":"10.1007\/3-540-48912-6_47","volume-title":"Methodologies for Knowledge Discovery and Data Mining","author":"K. AlSabti","year":"1999","unstructured":"AlSabti, K., Ranka, S.: An efficient space-partitioning based algorithm for the K-means clustering. In: Zhong, N., Zhou, L. (eds.) PAKDD 1999. LNCS (LNAI), vol.\u00a01574, pp. 355\u2013360. Springer, Heidelberg (1999)"},{"key":"24_CR4","doi-asserted-by":"crossref","unstructured":"Andoni, A., Indyk, P.: Near-optimal hashing algorithms for approximate nearest neighbor in high dimensions. In: FOCS, pp. 459\u2013468 (2006)","DOI":"10.1109\/FOCS.2006.49"},{"key":"24_CR5","unstructured":"Arthur, D., Vassilvitskii, S.: k-means++: the advantages of careful seeding. In: SODA, pp. 1027\u20131035 (2007)"},{"key":"24_CR6","doi-asserted-by":"crossref","unstructured":"Bahmani, B., Moseley, B., Vattani, A., Kumar, R., Vassilvitskii, S.: Scalable k-means++. CoRR, abs\/1203.6402 (2012)","DOI":"10.14778\/2180912.2180915"},{"issue":"1","key":"24_CR7","first-page":"285","volume":"3","author":"Y. Bu","year":"2010","unstructured":"Bu, Y., Howe, B., Balazinska, M., Ernst, M.: Haloop: Efficient iterative data processing on large clusters. PVLDB\u00a03(1), 285\u2013296 (2010)","journal-title":"PVLDB"},{"key":"24_CR8","unstructured":"Cordeiro, R.L.F., Traina Jr., C., Traina, A.J.M., L\u00f3pez, J., Kang, U., Faloutsos, C.: Clustering very large multi-dimensional datasets with mapreduce. In: KDD, pp. 690\u2013698 (2011)"},{"key":"24_CR9","doi-asserted-by":"crossref","unstructured":"Datar, M., Immorlica, N., Indyk, P., Mirrokni, V.S.: Locality-sensitive hashing scheme based on p-stable distributions. In: Symposium on Computational Geometry, pp. 253\u2013262 (2004)","DOI":"10.1145\/997817.997857"},{"key":"24_CR10","unstructured":"Dean, J., Ghemawat, S.: Mapreduce: simplified data processing on large clusters. In: OSDI (2004)"},{"key":"24_CR11","unstructured":"Dean, J., Ghemawat, S.: Mapreduce: simplified data processing on large clusters. In: OSDI (2004)"},{"key":"24_CR12","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1007\/3-540-46502-2_13","volume-title":"Large-Scale Parallel Data Mining","author":"I.S. Dhillon","year":"2000","unstructured":"Dhillon, I.S., Modha, D.S.: A data-clustering algorithm on distributed memory multiprocessors. In: Zaki, M.J., Ho, C.-T. (eds.) KDD 1999. LNCS (LNAI), vol.\u00a01759, pp. 245\u2013260. Springer, Heidelberg (2000)"},{"key":"24_CR13","doi-asserted-by":"crossref","unstructured":"Ene, A., Im, S., Moseley, B.: Fast clustering using mapreduce. In: KDD, pp. 681\u2013689 (2011)","DOI":"10.1145\/2020408.2020515"},{"issue":"5","key":"24_CR14","doi-asserted-by":"publisher","first-page":"657","DOI":"10.1109\/TPAMI.2005.95","volume":"27","author":"J.Z. Huang","year":"2005","unstructured":"Huang, J.Z., Ng, M.K., Rong, H., Li, Z.: Automated variable weighting in k-means type clustering. IEEE Trans. Pattern Anal. Mach. Intell.\u00a027(5), 657\u2013668 (2005)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"24_CR15","doi-asserted-by":"crossref","unstructured":"Indyk, P., Motwani, R.: Approximate nearest neighbors: Towards removing the curse of dimensionality. In: STOC, pp. 604\u2013613 (1998)","DOI":"10.1145\/276698.276876"},{"key":"24_CR16","doi-asserted-by":"crossref","unstructured":"Kriegel, H.-P., Kr\u00f6ger, P., Zimek, A.: Clustering high-dimensional data: A survey on subspace clustering, pattern-based clustering, and correlation clustering. TKDD\u00a03(1) (2009)","DOI":"10.1145\/1497577.1497578"},{"key":"24_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"516","DOI":"10.1007\/978-3-540-30192-9_51","volume-title":"Current Trends in Database Technology - EDBT 2004 Workshops","author":"A. Mondal","year":"2004","unstructured":"Mondal, A., Lifu, Y., Kitsuregawa, M.: P2PR-tree: An R-tree-based spatial index for peer-to-peer environments. In: Lindner, W., Fischer, F., T\u00fcrker, C., Tzitzikas, Y., Vakali, A.I. (eds.) EDBT 2004. LNCS, vol.\u00a03268, pp. 516\u2013525. Springer, Heidelberg (2004)"},{"issue":"8","key":"24_CR18","doi-asserted-by":"publisher","first-page":"909","DOI":"10.1109\/TKDE.2004.25","volume":"16","author":"C. Ordonez","year":"2004","unstructured":"Ordonez, C., Omiecinski, E.: Efficient disk-based k-means clustering for relational databases. IEEE Trans. Knowl. Data Eng.\u00a016(8), 909\u2013921 (2004)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"24_CR19","unstructured":"Pelleg, D., Moore, A.W.: X-means: Extending k-means with efficient estimation of the number of clusters. In: ICML, pp. 727\u2013734 (2000)"},{"issue":"1","key":"24_CR20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10115-007-0114-2","volume":"14","author":"X. Wu","year":"2008","unstructured":"Wu, X., Kumar, V., Quinlan, J.R., Ghosh, J., Yang, Q., Motoda, H., McLachlan, G.J., Ng, A.F.M., Liu, B., Yu, P.S., Zhou, Z.-H., Steinbach, M., Hand, D.J., Steinberg, D.: Top 10 algorithms in data mining. Knowl. Inf. Syst.\u00a014(1), 1\u201337 (2008)","journal-title":"Knowl. Inf. Syst."},{"key":"24_CR21","doi-asserted-by":"crossref","unstructured":"Yang, Y.-H., Lin, Y.-C., Chen, H.H.: Clustering for music search results. In: ICME, pp. 874\u2013877 (2009)","DOI":"10.1109\/ICME.2009.5202634"}],"container-title":["Lecture Notes in Computer Science","Database Systems for Advanced Applications"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-05810-8_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,2]],"date-time":"2025-05-02T11:28:05Z","timestamp":1746185285000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-05810-8_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014]]},"ISBN":["9783319058092","9783319058108"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-05810-8_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2014]]}}}