{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T09:05:09Z","timestamp":1768035909222,"version":"3.49.0"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319618449","type":"print"},{"value":"9783319618456","type":"electronic"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017]]},"DOI":"10.1007\/978-3-319-61845-6_7","type":"book-chapter","created":{"date-parts":[[2017,6,23]],"date-time":"2017-06-23T03:33:33Z","timestamp":1498188813000},"page":"61-73","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["Comparative Study of Apache Spark MLlib Clustering Algorithms"],"prefix":"10.1007","author":[{"given":"Sasan","family":"Harifi","sequence":"first","affiliation":[]},{"given":"Ebrahim","family":"Byagowi","sequence":"additional","affiliation":[]},{"given":"Madjid","family":"Khalilian","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2017,6,24]]},"reference":[{"key":"7_CR1","doi-asserted-by":"publisher","first-page":"7746","DOI":"10.1016\/j.eswa.2015.05.007","volume":"42","author":"X Chen","year":"2015","unstructured":"Chen, X.: A new clustering algorithm based on near neighbor influence. Expert Syst. Appl. 42, 7746\u20137758 (2015)","journal-title":"Expert Syst. Appl."},{"key":"7_CR2","doi-asserted-by":"publisher","first-page":"308","DOI":"10.1016\/j.ins.2015.04.011","volume":"316","author":"D G\u00f3mez","year":"2015","unstructured":"G\u00f3mez, D., Zarrazola, E., Y\u00e1\u00f1ez, J., Montero, J.: A Divide-and-Link algorithm for hierarchical clustering in networks. Inf. Sci. 316, 308\u2013328 (2015)","journal-title":"Inf. Sci."},{"key":"7_CR3","unstructured":"Pan, X., Papailiopoulos, D., Oymak, S., Recht, B., Ramchan-dran, K., I. Jordan, M.: Parallel correlation clustering on big graphs. In: Advances in Neural Information Processing Systems, pp. 82\u201390 (2015)"},{"key":"7_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40537-015-0036-x","volume":"3","author":"M Khalilian","year":"2016","unstructured":"Khalilian, M., Mustapha, N., Sulaiman, N.: Data stream clustering by divide and conquer approach based on vector model. J. Big Data 3, 1 (2016)","journal-title":"J. Big Data"},{"key":"7_CR5","series-title":"Information, Systems Sciences, and Engineering","doi-asserted-by":"publisher","first-page":"1181","DOI":"10.1007\/978-1-4614-3535-8_97","volume-title":"Innovations and Advances in Computer","author":"M Khalilian","year":"2013","unstructured":"Khalilian, M., Mustapha, N., Sulaiman, N., Mamat, A.: Different aspects of data stream clustering. In: Elleithy, K., Sobh, T. (eds.) Innovations and Advances in Computer. Information, Systems Sciences, and Engineering, pp. 1181\u20131191. Springer, New York (2013). doi:10.1007\/978-1-4614-3535-8_97"},{"key":"7_CR6","doi-asserted-by":"crossref","unstructured":"Wan, R., Yan, X., Su, X.: A weighted fuzzy clustering algorithm for data stream. In: 2008 ISECS International Colloquium on Computing, Communication, Control, and Management, pp. 360\u2013364. IEEE (2008)","DOI":"10.1109\/CCCM.2008.186"},{"key":"7_CR7","doi-asserted-by":"crossref","unstructured":"Wang, J., Wang, J., Ke, Q., Zeng, G., Li, S.: Fast approximate k-means via cluster closures. In: Multimedia Data Mining and Analytics, pp. 373\u2013395. Springer International Publishing (2015)","DOI":"10.1007\/978-3-319-14998-1_17"},{"key":"7_CR8","doi-asserted-by":"publisher","first-page":"463","DOI":"10.1007\/s00477-014-0931-2","volume":"29","author":"F Finazzi","year":"2014","unstructured":"Finazzi, F., Haggarty, R., Miller, C., Scott, M., Fass\u00f2, A.: A comparison of clustering approaches for the study of the temporal coherence of multiple time series. Stochast. Environ. Res. Risk Assess. 29, 463\u2013475 (2014)","journal-title":"Stochast. Environ. Res. Risk Assess."},{"key":"7_CR9","doi-asserted-by":"crossref","unstructured":"Brust, M.R., Turgut, D.: VBCA: a virtual forces clustering algorithm for autonomous aerial drone systems. In: 2016 Annual IEEE Systems Conference (SysCon), pp. 1\u20136. IEEE (2016)","DOI":"10.1109\/SYSCON.2016.7490517"},{"key":"7_CR10","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1016\/j.asoc.2014.11.040","volume":"28","author":"C Ozturk","year":"2015","unstructured":"Ozturk, C., Hancer, E., Karaboga, D.: Dynamic clustering with improved binary artificial bee colony algorithm. Appl. Soft Comput. 28, 69\u201380 (2015)","journal-title":"Appl. Soft Comput."},{"key":"7_CR11","doi-asserted-by":"publisher","first-page":"593","DOI":"10.1007\/s10462-013-9398-7","volume":"43","author":"S Ding","year":"2015","unstructured":"Ding, S., Wu, F., Qian, J., Jia, H., Jin, F.: Research on data stream clustering algorithms. Artif. Intell. Rev. 43, 593\u2013600 (2015)","journal-title":"Artif. Intell. Rev."},{"key":"7_CR12","doi-asserted-by":"publisher","first-page":"2984","DOI":"10.1109\/TIP.2015.2438540","volume":"24","author":"Y Yan","year":"2015","unstructured":"Yan, Y., Ricci, E., Liu, G., Sebe, N.: Egocentric daily activity recognition via multitask clustering. IEEE Trans. Image Process. 24, 2984\u20132995 (2015)","journal-title":"IEEE Trans. Image Process."},{"key":"7_CR13","unstructured":"Karau, H., Konwinski, A., Wendell, P., Zaharia, M.: Learning Spark: Lightning-Fast Big Data Analysis. O\u2019Reilly Media, Inc., (2015)"},{"issue":"34","key":"7_CR14","first-page":"1","volume":"17","author":"X Meng","year":"2016","unstructured":"Meng, X., Bradley, J., Yuvaz, B., Sparks, E., Venkataraman, S., Liu, D., Freeman, J.: Mllib: machine learning in apache spark. JMLR 17(34), 1\u20137 (2016)","journal-title":"JMLR"},{"key":"7_CR15","doi-asserted-by":"publisher","first-page":"701","DOI":"10.1111\/j.1541-0420.2008.01160.x","volume":"65","author":"C Maugis","year":"2009","unstructured":"Maugis, C., Celeux, G., Martin-Magniette, M.: Variable selection for clustering with gaussian mixture models. Biometrics 65, 701\u2013709 (2009)","journal-title":"Biometrics"},{"key":"7_CR16","doi-asserted-by":"publisher","first-page":"1406","DOI":"10.1109\/TKDE.2010.259","volume":"23","author":"X He","year":"2011","unstructured":"He, X., Cai, D., Shao, Y., Bao, H., Han, J.: Laplacian regularized gaussian mixture model for data clustering. IEEE Trans. Knowl. Data Eng. 23, 1406\u20131418 (2011)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"7_CR17","unstructured":"Clustering - RDD-based API - Spark 2.1.0 Documentation. http:\/\/spark.apache.org\/docs\/latest\/mllib-clustering.html"},{"key":"7_CR18","first-page":"993","volume":"3","author":"DM Blei","year":"2003","unstructured":"Blei, D.M., Ng, A.Y., Jordan, M.I.: Latent dirichlet allocation. J. Mach. Learn. Res. 3, 993\u20131022 (2003)","journal-title":"J. Mach. Learn. Res."},{"key":"7_CR19","doi-asserted-by":"crossref","unstructured":"Krestel, R., Fankhauser, P., Nejdl, W.: Latent dirichlet allocation for tag recommendation. In: Proceedings of the Third ACM Conference on Recommender Systems, pp. 61\u201368. ACM (2009)","DOI":"10.1145\/1639714.1639726"},{"key":"7_CR20","doi-asserted-by":"publisher","first-page":"224","DOI":"10.1109\/TPAMI.1979.4766909","volume":"PAMI-1","author":"D Davies","year":"1979","unstructured":"Davies, D., Bouldin, D.: A cluster separation measure. IEEE Trans. Pattern Anal. Mach. Intell. PAMI-1, 224\u2013227 (1979)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"7_CR21","unstructured":"Lin, F., Cohen, W.: Power iteration clustering. In: Proceedings of the 27th International Conference on Machine Learning (ICML 2010), pp. 655\u2013662 (2010)"},{"key":"7_CR22","doi-asserted-by":"publisher","first-page":"352","DOI":"10.1016\/j.jpdc.2012.06.009","volume":"73","author":"W Yan","year":"2013","unstructured":"Yan, W., Brahmakshatriya, U., Xue, Y., Gilder, M., Wise, B.: p-PIC: parallel power iteration clustering for big data. J. Parallel Distrib. Comput. 73, 352\u2013359 (2013)","journal-title":"J. Parallel Distrib. Comput."},{"key":"7_CR23","unstructured":"Wagstaff, K., Cardie, C., Rogers, S., Schr\u00f6dl, S.: Constrained k-means clustering with background knowledge. In: ICML, pp. 577\u2013584 (2001)"},{"key":"7_CR24","unstructured":"Alsabti, K., Ranka, S., Singh, V.: An efficient k-means clustering algorithm. Electrical Engineering and Computer Science (1997)"},{"key":"7_CR25","doi-asserted-by":"publisher","first-page":"622","DOI":"10.14778\/2180912.2180915","volume":"5","author":"B Bahmani","year":"2012","unstructured":"Bahmani, B., Moseley, B., Vattani, A., Kumar, R., Vassil-vitskii, S.: Scalable k-means++. Proc. VLDB Endowment 5, 622\u2013633 (2012)","journal-title":"Proc. VLDB Endowment"},{"key":"7_CR26","unstructured":"Meila, M., Shi, J.: A random walks view of spectral segmentation (2001)"},{"key":"7_CR27","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1016\/S0168-1699(99)00046-0","volume":"24","author":"J Blackard","year":"1999","unstructured":"Blackard, J., Dean, D.: Comparative accuracies of artificial neural networks and discriminant analysis in predicting forest cover types from cartographic variables. Comput. Electron. Agric. 24, 131\u2013151 (1999)","journal-title":"Comput. Electron. Agric."},{"key":"7_CR28","doi-asserted-by":"publisher","first-page":"2372","DOI":"10.1109\/TCYB.2015.2477416","volume":"46","author":"D Kumar","year":"2016","unstructured":"Kumar, D., Bezdek, J., Palaniswami, M., Rajasegarar, S., Leckie, C., Havens, T.: A hybrid approach to clustering in big data. IEEE Trans. Cybern. 46, 2372\u20132385 (2016)","journal-title":"IEEE Trans. Cybern."},{"key":"7_CR29","unstructured":"Alvarez, S.A., Kawato, T., Ruiz, C.: Mining over loosely coupled data sources using neural experts. In: International Workshop on Multimedia Data Mining. In Conjunction with the Ninth ACM SIGKDD International Conference on Knowledge Dis-cover and Data Mining (2003)"},{"key":"7_CR30","unstructured":"Lichman, M.: UCI Machine Learning Repository. University of California, School of Information and Computer Science, Irvine, CA (2013). http:\/\/archive.ics.uci.edu\/ml"}],"container-title":["Lecture Notes in Computer Science","Data Mining and Big Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-61845-6_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T17:18:32Z","timestamp":1710263912000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-61845-6_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319618449","9783319618456"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-61845-6_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017]]},"assertion":[{"value":"24 June 2017","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"DMBD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Data Mining and Big Data","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Fukuoka","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2017","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 July 2017","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 August 2017","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"dmbd2017","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/dmbd2017.ic-si.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}