{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,12]],"date-time":"2025-06-12T04:12:37Z","timestamp":1749701557432,"version":"3.41.0"},"publisher-location":"Cham","reference-count":19,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319484716"},{"type":"electronic","value":"9783319484723"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016]]},"DOI":"10.1007\/978-3-319-48472-3_20","type":"book-chapter","created":{"date-parts":[[2016,10,17]],"date-time":"2016-10-17T08:43:13Z","timestamp":1476693793000},"page":"344-362","source":"Crossref","is-referenced-by-count":3,"title":["A Framework for Clustering and Classification of\u00a0Big Data Using Spark"],"prefix":"10.1007","author":[{"given":"Xristos","family":"Mallios","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vasilis","family":"Vassalos","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tassos","family":"Venetis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Akrivi","family":"Vlachou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,10,18]]},"reference":[{"key":"20_CR1","unstructured":"Balcan, M.-F.F., Ehrlich, S., Liang, Y.: Distributed k-means and k-median clustering on general topologies. In: Burges, C., Bottou, L., Welling, M., Ghahramani, Z., Weinberger, k. (eds.) Advances in Neural Information Processing Systems 26, pp. 1995\u20132003. Curran Associates Inc. (2013)"},{"key":"20_CR2","unstructured":"Bradley, P.S., Mangasarian, O.L., Street, W.N.: Clustering via concave minimization. In: Advances in Neural Information Processing Systems, pp. 368\u2013374 (1997)"},{"issue":"15","key":"20_CR3","doi-asserted-by":"crossref","first-page":"2883","DOI":"10.1016\/S0167-8655(03)00146-6","volume":"24","author":"Y-M Cheung","year":"2003","unstructured":"Cheung, Y.-M.: k-means: a new generalized k-means clustering algorithm. Pattern Recogn. Lett. 24(15), 2883\u20132893 (2003)","journal-title":"Pattern Recogn. Lett."},{"key":"20_CR4","doi-asserted-by":"crossref","unstructured":"Datta, S., Giannella, C., Kargupta, H.: K-means clustering over a large, dynamic network. In: SDM, pp. 153\u2013164 (2006)","DOI":"10.1137\/1.9781611972764.14"},{"key":"20_CR5","doi-asserted-by":"crossref","unstructured":"Ferreira Cordeiro, R.L., Traina Jr., C., Machado Traina, A.J., L\u00f3pez, J., Kang, U., Faloutsos, C.: Clustering very large multi-dimensional datasets with mapreduce. In: SIGKDD, pp. 690\u2013698 (2011)","DOI":"10.1145\/2020408.2020516"},{"key":"20_CR6","unstructured":"Fisher, D.H., McKusick, K.B.: An empirical comparison of id3 and back-propagation. In: IJCAI, pp. 788\u2013793 (1989)"},{"issue":"3","key":"20_CR7","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\u2019Callaghan, L.: Clustering data streams: theory and practice. IEEE Trans. Knowl. Data Eng. 15(3), 515\u2013528 (2003)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"20_CR8","doi-asserted-by":"crossref","unstructured":"Guha, S., Mishra, N., Motwani, R., O\u2019Callaghan, L.: Clustering data streams. In: Foundations of Computer Science, pp. 359\u2013366 (2000)","DOI":"10.1109\/SFCS.2000.892124"},{"key":"20_CR9","doi-asserted-by":"crossref","unstructured":"Jasso-Luna, O., Sosa-Sosa, V., Lopez-Arevalo, I.: An approach to building a distributed id3 classifier. In: DCAI, pp. 385\u2013394 (2009)","DOI":"10.1007\/978-3-540-85863-8_45"},{"issue":"1","key":"20_CR10","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1007\/s10115-005-0210-0","volume":"10","author":"R Jin","year":"2006","unstructured":"Jin, R., Goswami, A., Agrawal, G.: Fast and exact out-of-core and distributed k-means clustering. Knowl. Inf. Syst. 10(1), 17\u201340 (2006)","journal-title":"Knowl. Inf. Syst."},{"issue":"7","key":"20_CR11","doi-asserted-by":"crossref","first-page":"881","DOI":"10.1109\/TPAMI.2002.1017616","volume":"24","author":"T Kanungo","year":"2002","unstructured":"Kanungo, T., Mount, D.M., Netanyahu, N.S., Piatko, C.D., Silverman, R., Wu, A.Y.: An efficient k-means clustering algorithm: analysis and implementation. Pattern Anal. Mach. Intell. 24(7), 881\u2013892 (2002)","journal-title":"Pattern Anal. Mach. Intell."},{"key":"20_CR12","first-page":"281","volume":"1","author":"JB MacQueen","year":"1967","unstructured":"MacQueen, J.B.: Some methods for classification and analysis of multivariate observations. Berkeley Symposium on Mathematical Statistics and Probability 1, 281\u2013297 (1967)","journal-title":"Berkeley Symposium on Mathematical Statistics and Probability"},{"key":"20_CR13","doi-asserted-by":"crossref","unstructured":"Poteras, C.M., Mihaescu, M.C., Mocanu, M.: An optimized version of the k-means clustering algorithm. In: Computer Science and Information Systems, pp. 695\u2013699 (2014)","DOI":"10.15439\/2014F258"},{"issue":"1","key":"20_CR14","first-page":"81","volume":"1","author":"JR Quinlan","year":"1986","unstructured":"Quinlan, J.R.: Induction of decision trees. Mach. Learn. 1(1), 81\u2013106 (1986)","journal-title":"Mach. Learn."},{"key":"20_CR15","doi-asserted-by":"crossref","unstructured":"Shi, J., Qiu, Y., Minhas, U.F., Jiao, L., Wang, C., Reinwald, B., \u00d6zcan, F.: Clash of the titans: Mapreduce vs. spark for large scale data analytics. PVLDB 8(13), 2110\u20132121 (2015)","DOI":"10.14778\/2831360.2831365"},{"key":"20_CR16","doi-asserted-by":"crossref","unstructured":"Vaidya, J., Clifton, C.: Privacy-preserving k-means clustering over vertically partitioned data. In: SIGKDD, pp. 206\u2013215 (2003)","DOI":"10.1145\/956750.956776"},{"key":"20_CR17","doi-asserted-by":"crossref","unstructured":"Xiao, M.-J., Huang, L.-S., long Luo, Y., Shen, H.: Privacy preserving id3 algorithm over horizontally partitioned data. In: PDCAT, pp. 239\u2013243 (2005)","DOI":"10.1109\/PDCAT.2005.191"},{"key":"20_CR18","unstructured":"Zaharia, M., Chowdhury, M., Franklin, M.J., Shenker, S., Stoica, I.: Spark: Cluster computing with working sets. In: USENIX Conference on Hot Topics in Cloud Computing, p. 10 (2010)"},{"key":"20_CR19","doi-asserted-by":"crossref","unstructured":"Zhang, J., Wu, G., Hu, X., Li, S., Hao, S.: A parallel k-means clustering algorithm with mpi. In: Parallel Architectures, Algorithms and Programming, pp. 60\u201364 (2011)","DOI":"10.1109\/PAAP.2011.17"}],"container-title":["Lecture Notes in Computer Science","On the Move to Meaningful Internet Systems: OTM 2016 Conferences"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-48472-3_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,11]],"date-time":"2025-06-11T15:16:30Z","timestamp":1749654990000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-48472-3_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319484716","9783319484723"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-48472-3_20","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2016]]}}}