{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2022,4,5]],"date-time":"2022-04-05T13:05:44Z","timestamp":1649163944355},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2017,1,11]],"date-time":"2017-01-11T00:00:00Z","timestamp":1484092800000},"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":["Mach Learn"],"published-print":{"date-parts":[[2017,6]]},"DOI":"10.1007\/s10994-016-5622-4","type":"journal-article","created":{"date-parts":[[2017,1,11]],"date-time":"2017-01-11T20:02:42Z","timestamp":1484164962000},"page":"837-862","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Big Data: from collection to visualization"],"prefix":"10.1007","volume":"106","author":[{"given":"Mohammed","family":"Ghesmoune","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanene","family":"Azzag","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Salima","family":"Benbernou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mustapha","family":"Lebbah","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tarn","family":"Duong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mourad","family":"Ouziri","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,1,11]]},"reference":[{"key":"5622_CR1","doi-asserted-by":"publisher","unstructured":"Aggarwal, C. C., Watson, T. J., Ctr, R., Han, J., Wang, J., & Yu, P. S. (2003). A framework for clustering evolving data streams. In VLDB (pp. 81\u201392).","DOI":"10.1016\/B978-012722442-8\/50016-1"},{"key":"5622_CR2","unstructured":"Ailon, N., Jaiswal, R., & Monteleoni, C. (2009). Streaming k-means approximation. In Advances in neural information processing systems 22: 23rd annual conference on neural information processing systems 2009. Proceedings of a meeting held 7\u201310 December 2009, Vancouver, BC (pp. 10\u201318)."},{"key":"5622_CR3","doi-asserted-by":"publisher","unstructured":"Benbernou, S., Huang, X., & Ouziri, M. (2015). Fusion of Big RDF data: A semantic entity resolution and query rewriting-based inference approach. In WISE (2) (pp. 300\u201330).","DOI":"10.1007\/978-3-319-26187-4_27"},{"issue":"3","key":"5622_CR4","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1016\/S0168-1699(99)00046-0","volume":"24","author":"JA Blackard","year":"1999","unstructured":"Blackard, J. A., & Dean, D. J. (1999). Comparative accuracies of artificial neural networks and discriminant analysis in predicting forest cover types from cartographic variables. Computers and Electronics in Agriculture, 24(3), 131\u2013151.","journal-title":"Computers and Electronics in Agriculture"},{"key":"5622_CR5","unstructured":"Bolanos, M., Forrest, J., & Hahsler, M. (2014). stream: Infrastructure for Data Stream Mining, r package version 0.2-0. http:\/\/CRAN.R-project.org\/package=stream ."},{"key":"5622_CR6","doi-asserted-by":"publisher","unstructured":"Braverman, V., Meyerson, A., Ostrovsky, R., Roytman, A., Shindler, M., & Tagiku, B. (2011). Streaming k-means on well-clusterable data. In Proceedings of the twenty-second annual ACM-SIAM symposium on discrete algorithms, SODA 2011, San Francisco, CA (pp. 26\u201340).","DOI":"10.1137\/1.9781611973082.3"},{"key":"5622_CR7","doi-asserted-by":"publisher","unstructured":"Cao, F., Ester, M., Qian, W., & Zhou, A. (2006). Density-based clustering over an evolving data stream with noise. In SDM (pp. 328\u2013339).","DOI":"10.1137\/1.9781611972764.29"},{"issue":"1","key":"5622_CR8","first-page":"13","volume":"46","author":"J Andrade Silva de","year":"2013","unstructured":"de Andrade Silva, J., Faria, E. R., Barros, R. C., Hruschka, E. R., de Carvalho, A. C., & Gama, J. (2013). Data stream clustering: A survey. ACM Computing Surveys, 46(1), 13.","journal-title":"ACM Computing Surveys"},{"issue":"1","key":"5622_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.2200\/S00578ED1V01Y201404DTM040","volume":"7","author":"XL Dong","year":"2015","unstructured":"Dong, X. L., & Srivastava, D. (2015). Big data integration. Synthesis Lectures on Data Management, 7(1), 1\u2013198.","journal-title":"Synthesis Lectures on Data Management"},{"key":"5622_CR10","doi-asserted-by":"publisher","unstructured":"Demchenko, Y., Grosso, P., De Laat, C., & Membrey, P. (2013). Addressing big data issues in scientific data infrastructure. In Collaboration technologies and systems (CTS), 2013 international conference on, IEEE (pp. 48\u201355).","DOI":"10.1109\/CTS.2013.6567203"},{"key":"5622_CR11","doi-asserted-by":"publisher","unstructured":"Endrullis, S., Thor, A., & Rahm, E. (2012). WETSUIT: An efficient mashup tool for searching and fusing web entities. Proceedings of the VLDB Endowment, 5(12). 1970\u20131973.","DOI":"10.14778\/2367502.2367550"},{"key":"5622_CR12","unstructured":"Fernandez, R. C., Migliavacca, M., Kalyvianaki, E., & Pietzuch, P. (2014). Making state explicit for imperative big data processing. In 2014 USENIX annual technical conference (USENIX ATC 14) (pp. 49\u201360)."},{"issue":"1","key":"5622_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10618-011-0242-x","volume":"26","author":"A Forestiero","year":"2013","unstructured":"Forestiero, A., Pizzuti, C., & Spezzano, G. (2013). A single pass algorithm for clustering evolving data streams based on swarm intelligence. Data Mining and Knowledge Discovery, 26(1), 1\u201326.","journal-title":"Data Mining and Knowledge Discovery"},{"key":"5622_CR14","doi-asserted-by":"crossref","unstructured":"Ghesmoune, M., Azzag, H., & Lebbah, M. (2014). G-stream: Growing neural gas over data stream. In Neural information processing\u201421st international conference, ICONIP 2014, Kuching, Malaysia. Proceedings, Part I (pp. 207\u2013214).","DOI":"10.1007\/978-3-319-12637-1_26"},{"key":"5622_CR15","doi-asserted-by":"publisher","unstructured":"Ghesmoune, M., Lebbah, M., & Azzag, H. (2015). Clustering over data streams based on growing neural gas. In Advances in knowledge discovery and data mining\u201419th Pacific-Asia conference, PAKDD 2015, Ho Chi Minh City, Proceedings, Part II (pp. 134\u2013145).","DOI":"10.1007\/978-3-319-18032-8_11"},{"key":"5622_CR16","doi-asserted-by":"publisher","unstructured":"Goasdou\u00e9, F., Kaoudi, Z., Manolescu, I., Ruiz, J. A. Q., & Zampetakis, S. (2015). CliqueSquare: Flat plans for massively parallel RDF queries. In 31st IEEE international conference on data engineering, ICDE, Seoul (pp. 771\u2013782).","DOI":"10.1109\/ICDE.2015.7113332"},{"key":"5622_CR17","doi-asserted-by":"publisher","unstructured":"Gurajada, S., Seufert, S., Miliaraki, I., & Theobald, M. (2014). TriAD: A distributed shared-nothing RDF engine based on asynchronous message passing. In SIGMOD conference (pp. 289\u2013300).","DOI":"10.1145\/2588555.2610511"},{"key":"5622_CR18","doi-asserted-by":"publisher","unstructured":"Halpin, H., Hayes, P., McCusker, J. P., McGuinness, D., & Thompson, H. S. (2010). When owl:sameAs isn\u2019t the same: An analysis of identity in linked data. In Proceedings of the ISWC.","DOI":"10.1007\/978-3-642-17746-0_20"},{"key":"5622_CR19","unstructured":"Hang\u00a0Du, J., Wang, H., Ni, Y., & Yu, Y. (2012). HadoopRDF: A scalable semantic data analytical engine. In Intelligent computing theories and applications\u20148th international Conference, ICIC 2012, Huangshan, China. Proceedings (pp. 633\u2013641)."},{"issue":"12","key":"5622_CR20","doi-asserted-by":"publisher","first-page":"1848","DOI":"10.14778\/2824032.2824083","volume":"8","author":"R Harbi","year":"2015","unstructured":"Harbi, R., Abdelaziz, I., Kalnis, P., & Mamoulis, N. (2015). Evaluating SPARQL queries on massive RDF datasets. Proceedings of the VLDB Endowment, 8(12), 1848\u20131859.","journal-title":"Proceedings of the VLDB Endowment"},{"key":"5622_CR21","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-84858-7","volume-title":"The elements of statistical learning: Data mining, inference, and prediction","author":"T Hastie","year":"2009","unstructured":"Hastie, T., Tibshirani, R., & Friedman, J. (2009). The elements of statistical learning: Data mining, inference, and prediction (2nd ed.). New York: Springer.","edition":"2"},{"key":"5622_CR22","doi-asserted-by":"publisher","unstructured":"Isaksson, C., Dunham, M. H., & Hahsler, M. (2012). SOStream: Self organizing density-based clustering over data stream. In MLDM. (pp. 264\u2013278).","DOI":"10.1007\/978-3-642-31537-4_21"},{"key":"5622_CR23","volume-title":"Self-organizing maps","year":"2001","unstructured":"Kohonen, T., Schroeder, M. R., & Huang, T. S. (Eds.). (2001). Self-organizing maps (3rd ed.). Secaucus, NJ: Springer New York Inc.","edition":"3"},{"key":"5622_CR24","doi-asserted-by":"publisher","unstructured":"Knoblock, C. A., Szekely, P.A., Ambite, J.\u00a0L., Goel, A., Gupta, S., Lerman, K., et al. (2012). Semi-automatically Mapping Structured Sources into the Semantic Web. In The Semantic Web: Research and Applications\u20149th Extended Semantic Web Conference, ESWC, 2012, Heraklion, Crete.","DOI":"10.1007\/978-3-642-30284-8_32"},{"issue":"2","key":"5622_CR25","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1007\/s10115-010-0342-8","volume":"29","author":"P Kranen","year":"2011","unstructured":"Kranen, P., Assent, I., Baldauf, C., & Seidl, T. (2011). The ClusTree: Indexing micro-clusters for anytime stream mining. Knowledge and Information Systems, 29(2), 249\u2013272.","journal-title":"Knowledge and Information Systems"},{"key":"5622_CR26","unstructured":"Lichman, M. (2013). UCI Machine Learning Repository. Irvine, CA: University of California, School of Information and Computer Science."},{"key":"5622_CR27","doi-asserted-by":"publisher","unstructured":"Madden, S., Franklin, M. J. Hellerstein, J. M., & Hong, W. (2003). The design of an acquisitional query processor for sensor networks. In Proceedings of the 2003 ACM SIGMOD international conference on management of data (pp. 491\u2013502). ACM.","DOI":"10.1145\/872757.872817"},{"key":"5622_CR28","unstructured":"Marz, N., & Warren, J. (2015). Big Data: Principles and best practices of scalable realtime data systems. Manning Publications Co."},{"issue":"8\u20139","key":"5622_CR29","doi-asserted-by":"publisher","first-page":"1041","DOI":"10.1016\/S0893-6080(02)00078-3","volume":"15","author":"S Marsland","year":"2002","unstructured":"Marsland, S., Shapiro, J., & Nehmzow, U. (2002). A self-organising network that grows when required. Neural Networks, 15(8\u20139), 1041\u20131058.","journal-title":"Neural Networks"},{"key":"5622_CR30","unstructured":"Martinetz, T., & Schulten, K. (1991). A \u201cneural-gas\u201d network learns topologies. Artificial Neural Networks, I, 397\u2013402."},{"issue":"1","key":"5622_CR31","first-page":"1235","volume":"17","author":"X Meng","year":"2016","unstructured":"Meng, X., Bradley, J., Yavuz, B., Sparks, E., Venkataraman, S., Liu, D., et al. (2016). MLlib: Machine learning in apache spark. Journal of Machine Learning Research, 17(1), 1235\u20131241.","journal-title":"Journal of Machine Learning Research"},{"key":"5622_CR32","unstructured":"Papailiou, N., Tsoumakos, D., Konstantinou, I., Karras, P., & Koziris, N. (2014). $$\\text{H}_{2}\\text{ RDF }{+}$$ H 2 RDF + : An efficient data management system for big RDF graphs. In International conference on management of data, SIGMOD 2014, Snowbird, UT (pp. 909\u2013912)."},{"issue":"336","key":"5622_CR33","doi-asserted-by":"publisher","first-page":"846","DOI":"10.1080\/01621459.1971.10482356","volume":"66","author":"W Rand","year":"1971","unstructured":"Rand, W. (1971). Objective criteria for the evaluation of clustering methods. Journal of the American Statistical Association, 66(336), 846\u2013850.","journal-title":"Journal of the American Statistical Association"},{"key":"5622_CR34","unstructured":"Shindler, M., Wong, A., & Meyerson, A. (2011). Fast and accurate k-means for large datasets. In Advances in neural information processing systems 24: 25th annual conference on neural information processing systems 2011. Proceedings of a meeting held 12\u201314 December 2011, Granada (pp. 2375\u20132383)."},{"key":"5622_CR35","doi-asserted-by":"publisher","unstructured":"Sledge, I. J., & Keller, J. M. (2008). Growing neural gas for temporal clustering. In 19th International conference on pattern recognition (ICPR 2008), Tampa, FL (pp. 1\u20134).","DOI":"10.1109\/ICPR.2008.4761768"},{"key":"5622_CR36","unstructured":"Stolfo, J. (2000). Cost-based modeling and evaluation for data mining with application to fraud and intrusion detection. In Results from the JAM Project by Salvatore."},{"key":"5622_CR37","doi-asserted-by":"publisher","unstructured":"Street, W. N., & Kim, Y. (2001). A streaming ensemble algorithm (SEA) for large-scale classification. In Proceedings of the seventh ACM SIGKDD international conference on knowledge discovery and data mining (pp. 377\u2013382). ACM.","DOI":"10.1145\/502512.502568"},{"key":"5622_CR38","first-page":"583","volume":"3","author":"A Strehl","year":"2002","unstructured":"Strehl, A., & Ghosh, J. (2002). Cluster ensembles\u2014A knowledge reuse framework for combining multiple partitions. Journal of Machine Learning Research, 3, 583\u2013617.","journal-title":"Journal of Machine Learning Research"},{"issue":"6","key":"5622_CR39","doi-asserted-by":"publisher","first-page":"468","DOI":"10.14778\/2904121.2904123","volume":"9","author":"J Subercaze","year":"2016","unstructured":"Subercaze, J., Gravier, C., Chevalier, J., & Laforest, F. (2016). Inferray: Fast in-memory RDF inference. Proceedings of the VLDB Endowment, 9(6), 468\u2013479.","journal-title":"Proceedings of the VLDB Endowment"},{"key":"5622_CR40","unstructured":"Therneau, T., Atkinson, B., & Ripley, B. (2015). rpart: Recursive partitioning and regression trees. R package version 4.1-10. https:\/\/CRAN.R-project.org\/package=rpart ."},{"key":"5622_CR41","unstructured":"Wache, H., Vgele, T., Visser, U., Stuckenschmidt, H., Schuster, G., Neumann, H., & Hbner, S. (2001). Ontology-based integration of information\u2014A survey of existing approaches. In IJCAI-01 workshop: Ontologies and information sharing (pp. 108\u2013117)."},{"key":"5622_CR42","unstructured":"Zaharia, M., Chowdhury, M., Das, T., Dave, A., Ma, J., McCauly, M., et al. (2012a). Resilient distributed datasets: A fault-tolerant abstraction for in-memory cluster computing. In Proceedings of the 9th USENIX Symposium on networked systems design and implementation, NSDI 2012, San Jose, CA, USA (pp. 15\u201328)."},{"key":"5622_CR43","doi-asserted-by":"crossref","unstructured":"Zaharia, M., Das, T., Li, H., Shenker, S., & Stoica, I. (2012b). Discretized streams: An efficient and fault-tolerant model for stream processing on large clusters. In Proceedings of the 4th USENIX conference on hot topics in cloud Ccomputing, HotCloud\u201912 (pp. 10\u201310).","DOI":"10.21236\/ADA575859"},{"key":"5622_CR44","doi-asserted-by":"publisher","unstructured":"Zhang, T., Ramakrishnan, R., & Livny, M. (1996). Birch: An efficient data clustering method for very large databases. In SIGMOD conference (pp. 103\u2013114).","DOI":"10.1145\/235968.233324"}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10994-016-5622-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-016-5622-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-016-5622-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,17]],"date-time":"2019-09-17T12:01:50Z","timestamp":1568721710000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10994-016-5622-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,1,11]]},"references-count":44,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2017,6]]}},"alternative-id":["5622"],"URL":"https:\/\/doi.org\/10.1007\/s10994-016-5622-4","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"value":"0885-6125","type":"print"},{"value":"1573-0565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,1,11]]}}}