{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T05:49:35Z","timestamp":1769147375149,"version":"3.49.0"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2017,9,5]],"date-time":"2017-09-05T00:00:00Z","timestamp":1504569600000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Big Data"],"published-print":{"date-parts":[[2017,12]]},"DOI":"10.1186\/s40537-017-0087-2","type":"journal-article","created":{"date-parts":[[2017,9,5]],"date-time":"2017-09-05T01:18:50Z","timestamp":1504574330000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":48,"title":["Clustering large datasets using K-means modified inter and intra clustering (KM-I2C) in Hadoop"],"prefix":"10.1186","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4098-1440","authenticated-orcid":false,"given":"Chowdam","family":"Sreedhar","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nagulapally","family":"Kasiviswanath","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pakanti","family":"Chenna Reddy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,9,5]]},"reference":[{"key":"87_CR1","unstructured":"De Camargo RY, Goldchleger A, Kon F. InteGrade: a tool for executing parallel applications on a grid for opportunistic computing. In: Proceedings of 23th Brazilian symposium on computer networks. 2005."},{"issue":"13","key":"87_CR2","first-page":"41","volume":"130","author":"C Sreedhar","year":"2015","unstructured":"Sreedhar C, Kasiviswanath N, Reddy PC. A survey on big data management and job scheduling. Int J Comput Appl. 2015;130(13):41\u201349.","journal-title":"Int J Comput Appl."},{"key":"87_CR3","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1016\/0304-3975(85)90224-5","volume":"38","author":"TF Gonzalez","year":"1985","unstructured":"Gonzalez TF. Clustering to minimize the maximum intercluster distance. Theor Comput Sci. 1985;38:293\u2013306.","journal-title":"Theor Comput Sci"},{"key":"87_CR4","isbn-type":"print","volume-title":"Data mining: concepts and techniques","author":"J Han","year":"2005","unstructured":"Han J. Data mining: concepts and techniques. San Francisco: Morgan Kaufmann Publishers Inc.; 2005. ISBN 1558609016.","ISBN":"https:\/\/id.crossref.org\/isbn\/1558609016"},{"key":"87_CR5","unstructured":"Babuska R. Fuzzy clustering. http:\/\/homes.di.unimi.it\/~valenti\/SlideCorsi\/Bioinformatica05\/Fuzzy-Clustering-lecture-Babuska.pdf . Accessed 4 Jan 2016."},{"key":"87_CR6","doi-asserted-by":"crossref","unstructured":"McCallum A, Nigam K, Ungar LH. Efficient clustering of high-dimensional datasets with application to reference matching. In: Proceedings of the ACM SIGKDD international conference on knowledge discovery and data mining. 2000. p. 169\u201378.","DOI":"10.1145\/347090.347123"},{"key":"87_CR7","isbn-type":"print","volume-title":"Programs for machine learning","author":"JR Quinlan","year":"1993","unstructured":"Quinlan JR. Programs for machine learning. San Francisco: Morgan Kaufmann Publishers Inc; 1993. ISBN 1-55860-238-0.","ISBN":"https:\/\/id.crossref.org\/isbn\/1558602380"},{"key":"87_CR8","unstructured":"Domingos P. Linear-time rule induction. In: Proceedings of knowledge discovery and data mining (KDD-96), Portland, Oregon. 1996."},{"issue":"2","key":"87_CR9","first-page":"139","volume":"2","author":"D Fisher","year":"1987","unstructured":"Fisher D. Knowledge acquisition via incremental conceptual clustering. Mach Learn J. 1987;2(2):139\u201372.","journal-title":"Mach Learn J"},{"key":"87_CR10","unstructured":"Cheeseman P, Stutz J. Bayesian classification (AutoClass): theory and results. In: Advances in knowledge discovery and data mining, 1996. p. 153\u201380. ISBN: 0-262-56097-6."},{"key":"87_CR11","unstructured":"Fayyad UM, Piatetsky-Shapiro G, Smyth P, Uthurusamy R, editors. Cambridge: AAAI\/MIT Press; 1996. p. 153\u201380."},{"key":"87_CR12","unstructured":"Biswas G, Weinberg J, Li C. ITERATE: a conceptual clustering method for knowledge discovery in databases. In: Braunschweig B, Day R, editors. Innovative applications of artificial intelligence in the oil and gas industry. 1995."},{"key":"87_CR13","unstructured":"Das G, Mannila H, Ronkainen P. Similarity of attributes by external probes. In: Proceedings of the fourth international conference on knowledge discovery and data mining KDD\u201998. New York: AAAI Press; 1998. p. 23\u20139."},{"issue":"6","key":"87_CR14","doi-asserted-by":"crossref","first-page":"905","DOI":"10.1109\/69.738357","volume":"10","author":"M Ortega","year":"1998","unstructured":"Ortega M, Rui Y, Chakrabarti K, Mehrotra S, Huang T. Supporting ranked boolean similarity queries in mars. IEEE Trans Knowl Data Eng. 1998;10(6):905\u201325.","journal-title":"IEEE Trans Knowl Data Eng"},{"issue":"1","key":"87_CR15","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1023\/A:1007612920971","volume":"42","author":"IS Dhillon","year":"2001","unstructured":"Dhillon IS, Modha DS. Concept decompositions for large sparse text data using clustering. Mach Learn. 2001;42(1):143\u201375.","journal-title":"Mach Learn"},{"key":"87_CR16","first-page":"2967","volume":"5","author":"J Mao","year":"1994","unstructured":"Mao J, Jain AK. Self-organizing network for hyperellipsoidal clustering (HEC). Proc IEEE Neural Netw. 1994;5:2967\u201372.","journal-title":"Proc IEEE Neural Netw"},{"issue":"1","key":"87_CR17","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1007\/BF01039681","volume":"8","author":"RJ Shanley","year":"1974","unstructured":"Shanley RJ, Mahtab MA. Delineation and analysis of clusters in orientation data. J Int Assoc Math Geol. 1974;8(1):9\u201323.","journal-title":"J Int Assoc Math Geol"},{"key":"87_CR18","doi-asserted-by":"publisher","unstructured":"Sreedhar C, Kasiviswanath N, Reddy PC. A novel multilevel queue based performance analysis of Hadoop job schedulers. Indian J Sci Technol. 2016;9(44). doi: 10.17485\/ijst\/2016\/v9i44\/96414","DOI":"10.17485\/ijst\/2016\/v9i44\/96414"},{"key":"87_CR19","doi-asserted-by":"crossref","unstructured":"haimov N, Malony A, Canon S, Iancu C, Ibrahim KZ, Srinivasan J. Scaling spark on HPC systems. In: Proceedings of 25th ACM international symposium on high-performance parallel and distributed computing. 2016. p. 97\u2013110.","DOI":"10.1145\/2907294.2907310"},{"key":"87_CR20","doi-asserted-by":"crossref","unstructured":"Olston C, Reed B, Srivastava U, Kumar R, Tomkins A. Pig latin: a not-so-foreign language for data processing. In: Proceedings of 2008 ACM SIGMOD international conference on management of data. 2008. p. 1099\u2013110.","DOI":"10.1145\/1376616.1376726"},{"key":"87_CR21","unstructured":"Hunt P, Konar M, Junqueira FP, Reed B. ZooKeeper: wait free coordination for internet-scale systems. In: Proceedings of USENIX conference. 2010."},{"key":"87_CR22","doi-asserted-by":"crossref","unstructured":"Wadkar S, Siddalingaiah M. HCatalog and Hadoop in the enterprise. In: Proceedings of Apache Hadoop 2014; Apress, Berkeley, CA.","DOI":"10.1007\/978-1-4302-4864-4_12"},{"issue":"2","key":"87_CR23","doi-asserted-by":"crossref","first-page":"1626","DOI":"10.14778\/1687553.1687609","volume":"2","author":"A Thusoo","year":"2009","unstructured":"Thusoo A, Sarma JS, Jain N, Shao Z, Chakka P, Anthony S, Liu H, Wyckoff P, Murthy R. Hive: a warehousing solution over a map-reduce framework. J VLDB Endow. 2009;2(2):1626\u20139.","journal-title":"J VLDB Endow"},{"key":"87_CR24","doi-asserted-by":"crossref","unstructured":"Vohra D. Apache Avro. Book of practical Hadoop ecosystem. 2016. p. 303\u201323.","DOI":"10.1007\/978-1-4842-2199-0_7"},{"key":"87_CR25","unstructured":"Shastry K, Madhyastha S, Kumar S, Bresniker KM, Battas G. Transaction support for HBase. In: Proceedings of international conference on management of data. 2014. p. 117\u201320."},{"key":"87_CR26","doi-asserted-by":"crossref","unstructured":"Wadkar S, Siddalingaiah M. Apache Ambari. Book of Pro Apache Hadoop. 2014. p. 399\u2013401.","DOI":"10.1007\/978-1-4302-4864-4_20"},{"key":"87_CR27","doi-asserted-by":"crossref","unstructured":"Ferreira Cordeiro RL, Traina Junior C, Machado Traina AJ, L\u00f3pez J, Kang U, Faloutsos C. Clustering very large multi-dimensional datasets with MapReduce. In: Proceedings of KDD\u201911, ACM, California, August 21\u201324. 2011.","DOI":"10.1145\/2020408.2020516"},{"key":"87_CR28","doi-asserted-by":"crossref","unstructured":"Zhao W, Ma H, He Q. Parallel K-means clustering based on MapReduce. In: CloudCom 2009, LNCS 5931. Berlin: Springer; 2009. pp. 674\u20139.","DOI":"10.1007\/978-3-642-10665-1_71"},{"issue":"11","key":"87_CR29","first-page":"102","volume":"17","author":"M Chen","year":"2017","unstructured":"Chen M. Soft clustering for very large data sets. Comput Sci Netw Secur J. 2017;17(11):102\u20138.","journal-title":"Comput Sci Netw Secur J"},{"issue":"10","key":"87_CR30","doi-asserted-by":"crossref","first-page":"1269","DOI":"10.1243\/0954406042369008","volume":"218","author":"DT Pham","year":"2004","unstructured":"Pham DT, Dimov SS, Nguyen CD. A two-phase K-means algorithm for large datasets. Mech Eng Sci J. 2004;218(10):1269\u201373.","journal-title":"Mech Eng Sci J"},{"key":"87_CR31","doi-asserted-by":"crossref","unstructured":"Chu C-T, Kim SK, Lin Y-A. Map-reduce for machine learning on multicore. In: Proceedings of the 20th annual conference on neural information processing systems (NIPS\u201906), Vancouver, Canada. 2006. p. 281\u20138.","DOI":"10.7551\/mitpress\/7503.003.0040"},{"issue":"C","key":"87_CR32","doi-asserted-by":"crossref","first-page":"246","DOI":"10.1016\/j.neucom.2015.12.013","volume":"179","author":"D Xia","year":"2016","unstructured":"Xia D, Wang B, Li H, Li Y, Zhang Z. A distributed spatial\u2013temporal weighted model on MapReduce for short-term traffic flow forecasting. J Neurocomput. 2016;179(C):246\u201363.","journal-title":"J Neurocomput"},{"key":"87_CR33","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1007\/978-3-642-25661-5_13","volume":"123","author":"L Chao","year":"2011","unstructured":"Chao L, Yan Y, Tonny R. A parallel Cop-K means clustering algorithm based on MapReduce framework. Adv Intell Soft Comput J. 2011;123:93\u2013102.","journal-title":"Adv Intell Soft Comput J"},{"key":"87_CR34","doi-asserted-by":"crossref","unstructured":"Wang C, Guo M, Liu Y. EST clustering in large dataset with MapReduce. In: Proceedings of pervasive computing, signal processing and applications, Sept 2010. 2010.","DOI":"10.1109\/PCSPA.2010.239"},{"key":"87_CR35","unstructured":"Zhang LD, Yuan DJ, Zhang JW, Wang SP and Zhang QF. A new method for EST clustering. J Yi chuan xue bao\u00a0=\u00a0Acta genetica Sinica. 2003."},{"key":"87_CR36","doi-asserted-by":"publisher","unstructured":"Fang W, Sheng VS, Wen X, Pan W. Meteorological data analysis using MapReduce. Sci World J. 2014;2014. doi: 10.1155\/2014\/646497","DOI":"10.1155\/2014\/646497"},{"key":"87_CR37","doi-asserted-by":"crossref","unstructured":"Tsai CW, Hsieh CH, Chiang MC. Parallel black hole clustering based on MapReduce. In: Proceedings of IEEE international conference on systems, man and cybernetics. 2015.","DOI":"10.1109\/SMC.2015.445"},{"key":"87_CR38","unstructured":"https:\/\/www.gutenberg.org\/ . Accessed 10 Aug 2016."},{"key":"87_CR39","unstructured":"Palecki MA, Lawrimore JH, Leeper RD, Bell JE, Embler S, Casey N. US climate reference network processed data from USCRN database version 2. 2015."},{"key":"87_CR40","unstructured":"Bertin-Mahieux T, Ellis DP, Whitman B, Lamere P. The million song dataset. In: Proceedings of the 12th International conference on music information. Retrieval (ISMIR 2011). 2011."},{"key":"87_CR41","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1016\/0377-0427(87)90125-7","volume":"20","author":"PJ Rousseeuw","year":"1987","unstructured":"Rousseeuw PJ. Silhouettes: a graphical aid to the interpretation and validation of cluster analysis. J Comput Appl Math. 1987;20:53\u201365.","journal-title":"J Comput Appl Math"},{"key":"87_CR42","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316801","volume-title":"Finding groups in data: an introduction to cluster analysis","author":"L Kaufman","year":"1990","unstructured":"Kaufman L, Rousseeuw PJ. Finding groups in data: an introduction to cluster analysis. New York: Wiley; 1990."}],"container-title":["Journal of Big Data"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s40537-017-0087-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/s40537-017-0087-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s40537-017-0087-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,25]],"date-time":"2023-08-25T12:08:45Z","timestamp":1692965325000},"score":1,"resource":{"primary":{"URL":"http:\/\/journalofbigdata.springeropen.com\/articles\/10.1186\/s40537-017-0087-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,9,5]]},"references-count":42,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2017,12]]}},"alternative-id":["87"],"URL":"https:\/\/doi.org\/10.1186\/s40537-017-0087-2","relation":{},"ISSN":["2196-1115"],"issn-type":[{"value":"2196-1115","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,9,5]]},"article-number":"27"}}