{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T16:17:24Z","timestamp":1780503444628,"version":"3.54.1"},"reference-count":147,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2015,10,1]],"date-time":"2015-10-01T00:00:00Z","timestamp":1443657600000},"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":["Journal of Big Data"],"published-print":{"date-parts":[[2015,12]]},"DOI":"10.1186\/s40537-015-0030-3","type":"journal-article","created":{"date-parts":[[2015,10,1]],"date-time":"2015-10-01T11:42:42Z","timestamp":1443699762000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":606,"title":["Big data analytics: a survey"],"prefix":"10.1186","volume":"2","author":[{"given":"Chun-Wei","family":"Tsai","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chin-Feng","family":"Lai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Han-Chieh","family":"Chao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Athanasios V.","family":"Vasilakos","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2015,10,1]]},"reference":[{"key":"30_CR1","unstructured":"Lyman P, Varian H. How much information 2003? Tech. Rep, 2004. [Online]. Available: http:\/\/www2.sims.berkeley.edu\/research\/projects\/how-much-info-2003\/printable_report.pdf ."},{"key":"30_CR2","volume-title":"Clustering","author":"R Xu","year":"2009","unstructured":"Xu R, Wunsch D. Clustering. Hoboken: Wiley-IEEE Press; 2009."},{"key":"30_CR3","doi-asserted-by":"crossref","unstructured":"Ding C, He X. K-means clustering via principal component analysis. In: Proceedings of the Twenty-first International Conference on Machine Learning, 2004, pp 1\u20139.","DOI":"10.1145\/1015330.1015408"},{"issue":"5","key":"30_CR4","doi-asserted-by":"crossref","first-page":"1170","DOI":"10.1109\/TKDE.2003.1232271","volume":"15","author":"G Kollios","year":"2003","unstructured":"Kollios G, Gunopulos D, Koudas N, Berchtold S. Efficient biased sampling for approximate clustering and outlier detection in large data sets. IEEE Trans Knowl Data Eng. 2003;15(5):1170\u201387.","journal-title":"IEEE Trans Knowl Data Eng"},{"issue":"3","key":"30_CR5","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1145\/2168931.2168943","volume":"19","author":"D Fisher","year":"2012","unstructured":"Fisher D, DeLine R, Czerwinski M, Drucker S. Interactions with big data analytics. Interactions. 2012;19(3):50\u20139.","journal-title":"Interactions"},{"key":"30_CR6","unstructured":"Laney D. 3D data management: controlling data volume, velocity, and variety, META Group, Tech. Rep. 2001. [Online]. Available: http:\/\/blogs.gartner.com\/doug-laney\/files\/2012\/01\/ad949-3D-Data-Management-Controlling-Data-Volume-Velocity-and-Variety.pdf ."},{"key":"30_CR7","unstructured":"van Rijmenam M. Why the 3v\u2019s are not sufficient to describe big data, BigData Startups, Tech. Rep. 2013. [Online]. Available: http:\/\/www.bigdata-startups.com\/3vs-sufficient-describe-big-data\/ ."},{"key":"30_CR8","unstructured":"Borne K. Top 10 big data challenges a serious look at 10 big data v\u2019s, Tech. Rep. 2014. [Online]. Available: https:\/\/www.mapr.com\/blog\/top-10-big-data-challenges-look-10-big-data-v ."},{"key":"30_CR9","unstructured":"Press G. $16.1 billion big data market: 2014 predictions from IDC and IIA, Forbes, Tech. Rep. 2013. [Online]. Available: http:\/\/www.forbes.com\/sites\/gilpress\/2013\/12\/12\/16-1-billion-big-data-market-2014-predictions-from-idc-and-iia\/ ."},{"key":"30_CR10","unstructured":"Big data and analytics\u2014an IDC four pillar research area, IDC, Tech. Rep. 2013. [Online]. Available: http:\/\/www.idc.com\/prodserv\/FourPillars\/bigData\/index.jsp ."},{"key":"30_CR11","unstructured":"Taft DK. Big data market to reach $46.34 billion by 2018, EWEEK, Tech. Rep. 2013. [Online]. Available: http:\/\/www.eweek.com\/database\/big-data-market-to-reach-46.34-billion-by-2018.html ."},{"key":"30_CR12","unstructured":"Research A. Big data spending to reach $114 billion in 2018; look for machine learning to drive analytics, ABI Research, Tech. Rep. 2013. [Online]. Available: https:\/\/www.abiresearch.com\/press\/big-data-spending-to-reach-114-billion-in-2018-loo ."},{"key":"30_CR13","unstructured":"Furrier J. Big data market $50 billion by 2017\u2014HP vertica comes out #1\u2014according to wikibon research, SiliconANGLE, Tech. Rep. 2012. [Online]. Available: http:\/\/siliconangle.com\/blog\/2012\/02\/15\/big-data-market-15-billion-by-2017-hp-vertica-comes-out-1-according-to-wikibon-research\/ ."},{"key":"30_CR14","unstructured":"Kelly J, Vellante D, Floyer D. Big data market size and vendor revenues, Wikibon, Tech. Rep. 2014. [Online]. Available: http:\/\/wikibon.org\/wiki\/v\/Big_Data_Market_Size_and_Vendor_Revenues ."},{"key":"30_CR15","unstructured":"Kelly J, Floyer D, Vellante D, Miniman S. Big data vendor revenue and market forecast 2012-2017, Wikibon, Tech. Rep. 2014. [Online]. Available: http:\/\/wikibon.org\/wiki\/v\/Big_Data_Vendor_Revenue_and_Market_Forecast_2012-2017 ."},{"key":"30_CR16","volume-title":"Big data: a revolution that will transform how we live, work, and think","author":"V Mayer-Schonberger","year":"2013","unstructured":"Mayer-Schonberger V, Cukier K. Big data: a revolution that will transform how we live, work, and think. Boston: Houghton Mifflin Harcourt; 2013."},{"issue":"4","key":"30_CR17","doi-asserted-by":"crossref","first-page":"1165","DOI":"10.2307\/41703503","volume":"36","author":"H Chen","year":"2012","unstructured":"Chen H, Chiang RHL, Storey VC. Business intelligence and analytics: from big data to big impact. MIS Quart. 2012;36(4):1165\u201388.","journal-title":"MIS Quart"},{"issue":"1","key":"30_CR18","first-page":"1","volume":"79","author":"R Kitchin","year":"2014","unstructured":"Kitchin R. The real-time city? big data and smart urbanism. Geo J. 2014;79(1):1\u201314.","journal-title":"Geo J"},{"issue":"3","key":"30_CR19","first-page":"37","volume":"17","author":"UM Fayyad","year":"1996","unstructured":"Fayyad UM, Piatetsky-Shapiro G, Smyth P. From data mining to knowledge discovery in databases. AI Mag. 1996;17(3):37\u201354.","journal-title":"AI Mag"},{"key":"30_CR20","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."},{"issue":"2","key":"30_CR21","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1145\/170036.170072","volume":"22","author":"R Agrawal","year":"1993","unstructured":"Agrawal R, Imieli\u0144ski T, Swami A. Mining association rules between sets of items in large databases. Proc ACM SIGMOD Int Conf Manag Data. 1993;22(2):207\u201316.","journal-title":"Proc ACM SIGMOD Int Conf Manag Data"},{"key":"30_CR22","volume-title":"Data mining: practical machine learning tools and techniques","author":"IH Witten","year":"2005","unstructured":"Witten IH, Frank E. Data mining: practical machine learning tools and techniques. San Francisco: Morgan Kaufmann Publishers Inc.; 2005."},{"key":"30_CR23","doi-asserted-by":"crossref","DOI":"10.4018\/978-1-93070-825-9","volume-title":"Data mining: a heuristic approach","author":"H Abbass","year":"2002","unstructured":"Abbass H, Newton C, Sarker R. Data mining: a heuristic approach. Hershey: IGI Global; 2002."},{"issue":"6","key":"30_CR24","doi-asserted-by":"crossref","first-page":"2451","DOI":"10.1109\/TSMCB.2004.836890","volume":"34","author":"M Cannataro","year":"2004","unstructured":"Cannataro M, Congiusta A, Pugliese A, Talia D, Trunfio P. Distributed data mining on grids: services, tools, and applications. IEEE Trans Syst Man Cyber Part B Cyber. 2004;34(6):2451\u201365.","journal-title":"IEEE Trans Syst Man Cyber Part B Cyber"},{"issue":"3","key":"30_CR25","doi-asserted-by":"crossref","first-page":"433","DOI":"10.1109\/3477.764879","volume":"29","author":"K Krishna","year":"1999","unstructured":"Krishna K, Murty MN. Genetic $$k$$ k -means algorithm. IEEE Trans Syst Man Cyber Part B Cyber. 1999;29(3):433\u20139.","journal-title":"IEEE Trans Syst Man Cyber Part B Cyber"},{"issue":"1","key":"30_CR26","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1109\/SURV.2013.103013.00206","volume":"16","author":"C-W Tsai","year":"2014","unstructured":"Tsai C-W, Lai C-F, Chiang M-C, Yang L. Data mining for internet of things: a survey. IEEE Commun Surveys Tutor. 2014;16(1):77\u201397.","journal-title":"IEEE Commun Surveys Tutor"},{"issue":"3","key":"30_CR27","doi-asserted-by":"crossref","first-page":"264","DOI":"10.1145\/331499.331504","volume":"31","author":"AK Jain","year":"1999","unstructured":"Jain AK, Murty MN, Flynn PJ. Data clustering: a review. ACM Comp Surveys. 1999;31(3):264\u2013323.","journal-title":"ACM Comp Surveys"},{"key":"30_CR28","unstructured":"McQueen JB. Some methods of classification and analysis of multivariate observations. In: Proceedings of the Berkeley Symposium on Mathematical Statistics and Probability, 1967. pp 281\u2013297."},{"issue":"3","key":"30_CR29","doi-asserted-by":"crossref","first-page":"660","DOI":"10.1109\/21.97458","volume":"21","author":"S Safavian","year":"1991","unstructured":"Safavian S, Landgrebe D. A survey of decision tree classifier methodology. IEEE Trans Syst Man Cyber. 1991;21(3):660\u201374.","journal-title":"IEEE Trans Syst Man Cyber"},{"key":"30_CR30","unstructured":"McCallum A, Nigam K. A comparison of event models for naive bayes text classification. In: Proceedings of the National Conference on Artificial Intelligence, 1998. pp. 41\u201348."},{"key":"30_CR31","doi-asserted-by":"crossref","unstructured":"Boser BE, Guyon IM, Vapnik VN. A training algorithm for optimal margin classifiers. In: Proceedings of the annual workshop on Computational learning theory, 1992. pp. 144\u2013152.","DOI":"10.1145\/130385.130401"},{"key":"30_CR32","doi-asserted-by":"crossref","unstructured":"Han J, Pei J, Yin Y. Mining frequent patterns without candidate generation. In : Proceedings of the ACM SIGMOD International Conference on Management of Data, 2000. pp. 1\u201312.","DOI":"10.1145\/342009.335372"},{"issue":"3","key":"30_CR33","doi-asserted-by":"crossref","first-page":"587","DOI":"10.1016\/j.fss.2004.09.014","volume":"152","author":"M Kaya","year":"2005","unstructured":"Kaya M, Alhajj R. Genetic algorithm based framework for mining fuzzy association rules. Fuzzy Sets Syst. 2005;152(3):587\u2013601.","journal-title":"Fuzzy Sets Syst"},{"key":"30_CR34","doi-asserted-by":"crossref","unstructured":"Srikant R, Agrawal R. Mining sequential patterns: generalizations and performance improvements. In: Proceedings of the International Conference on Extending Database Technology: Advances in Database Technology, 1996. pp 3\u201317.","DOI":"10.1007\/BFb0014140"},{"issue":"1\u20132","key":"30_CR35","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1023\/A:1007652502315","volume":"42","author":"MJ Zaki","year":"2001","unstructured":"Zaki MJ. Spade: an efficient algorithm for mining frequent sequences. Mach Learn. 2001;42(1\u20132):31\u201360.","journal-title":"Mach Learn"},{"key":"30_CR36","volume-title":"Modern Information Retrieval","author":"RA Baeza-Yates","year":"1999","unstructured":"Baeza-Yates RA, Ribeiro-Neto B. Modern Information Retrieval. Boston: Addison-Wesley Longman Publishing Co., Inc; 1999."},{"key":"30_CR37","volume-title":"Web data mining: exploring hyperlinks, contents, and usage data","author":"B Liu","year":"2007","unstructured":"Liu B. Web data mining: exploring hyperlinks, contents, and usage data. Berlin, Heidelberg: Springer-Verlag; 2007."},{"key":"30_CR38","doi-asserted-by":"crossref","unstructured":"d\u2019Aquin M, Jay N. Interpreting data mining results with linked data for learning analytics: motivation, case study and directions. In: Proceedings of the International Conference on Learning Analytics and Knowledge, pp 155\u2013164.","DOI":"10.1145\/2460296.2460327"},{"key":"30_CR39","doi-asserted-by":"crossref","unstructured":"Shneiderman B. The eyes have it: a task by data type taxonomy for information visualizations. In: Proceedings of the IEEE Symposium on Visual Languages, 1996, pp 336\u2013343.","DOI":"10.1109\/VL.1996.545307"},{"key":"30_CR40","unstructured":"Mani I, Bloedorn E. Multi-document summarization by graph search and matching. In: Proceedings of the National Conference on Artificial Intelligence and Ninth Conference on Innovative Applications of Artificial Intelligence, 1997, pp 622\u2013628."},{"key":"30_CR41","doi-asserted-by":"crossref","unstructured":"Kopanakis I, Pelekis N, Karanikas H, Mavroudkis T. Visual techniques for the interpretation of data mining outcomes. In: Proceedings of the Panhellenic Conference on Advances in Informatics, 2005. pp 25\u201335.","DOI":"10.1007\/11573036_3"},{"key":"30_CR42","unstructured":"Elkan C. Using the triangle inequality to accelerate k-means. In: Proceedings of the International Conference on Machine Learning, 2003, pp 147\u2013153."},{"key":"30_CR43","doi-asserted-by":"crossref","unstructured":"Catanzaro B, Sundaram N, Keutzer K. Fast support vector machine training and classification on graphics processors. In: Proceedings of the International Conference on Machine Learning, 2008. pp 104\u2013111.","DOI":"10.1145\/1390156.1390170"},{"key":"30_CR44","doi-asserted-by":"crossref","unstructured":"Zhang T, Ramakrishnan R, Livny M. BIRCH: an efficient data clustering method for very large databases. In: Proceedings of the ACM SIGMOD International Conference on Management of Data, 1996. pp 103\u2013114.","DOI":"10.1145\/233269.233324"},{"key":"30_CR45","unstructured":"Ester M, Kriegel HP, Sander J, Xu X. A density-based algorithm for discovering clusters in large spatial databases with noise. In: Proceedings of the Second International Conference on Knowledge Discovery and Data Mining, 1996. pp 226\u2013231."},{"key":"30_CR46","unstructured":"Ester M, Kriegel HP, Sander J, Wimmer M, Xu X. Incremental clustering for mining in a data warehousing environment. In: Proceedings of the International Conference on Very Large Data Bases, 1998. pp 323\u2013333."},{"issue":"8","key":"30_CR47","doi-asserted-by":"crossref","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. 2004;16(8):909\u201321.","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"30_CR48","volume-title":"Introduction to clustering large and high-dimensional data","author":"J Kogan","year":"2007","unstructured":"Kogan J. Introduction to clustering large and high-dimensional data. Cambridge: Cambridge Univ Press; 2007."},{"issue":"1","key":"30_CR49","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1109\/72.977258","volume":"13","author":"S Mitra","year":"2002","unstructured":"Mitra S, Pal S, Mitra P. Data mining in soft computing framework: a survey. IEEE Trans Neural Netw. 2002;13(1):3\u201314.","journal-title":"IEEE Trans Neural Netw"},{"key":"30_CR50","doi-asserted-by":"crossref","unstructured":"Mehta M, Agrawal R, Rissanen J. SLIQ: a fast scalable classifier for data mining. In: Proceedings of the 5th International Conference on Extending Database Technology: Advances in Database Technology. 1996. pp 18\u201332.","DOI":"10.1007\/BFb0014141"},{"issue":"7","key":"30_CR51","doi-asserted-by":"crossref","first-page":"731","DOI":"10.1016\/0167-8655(96)00032-3","volume":"17","author":"L Mic\u00f3","year":"1996","unstructured":"Mic\u00f3 L, Oncina J, Carrasco RC. A fast branch and bound nearest neighbour classifier in metric spaces. Pattern Recogn Lett. 1996;17(7):731\u20139.","journal-title":"Pattern Recogn Lett"},{"issue":"3","key":"30_CR52","doi-asserted-by":"crossref","first-page":"277","DOI":"10.1109\/34.584107","volume":"19","author":"A Djouadi","year":"1997","unstructured":"Djouadi A, Bouktache E. A fast algorithm for the nearest-neighbor classifier. IEEE Trans Pattern Anal Mach Intel. 1997;19(3):277\u201382.","journal-title":"IEEE Trans Pattern Anal Mach Intel"},{"issue":"12","key":"30_CR53","doi-asserted-by":"crossref","first-page":"2956","DOI":"10.1016\/j.sigpro.2008.07.001","volume":"88","author":"D Ververidis","year":"2008","unstructured":"Ververidis D, Kotropoulos C. Fast and accurate sequential floating forward feature selection with the bayes classifier applied to speech emotion recognition. Signal Process. 2008;88(12):2956\u201370.","journal-title":"Signal Process"},{"key":"30_CR54","unstructured":"Pei J, Han J, Mao R. CLOSET: an efficient algorithm for mining frequent closed itemsets. In: Proceedings of the ACM SIGMOD Workshop on Research Issues in Data Mining and Knowledge Discovery, 2000. pp 21\u201330."},{"issue":"4","key":"30_CR55","doi-asserted-by":"crossref","first-page":"462","DOI":"10.1109\/TKDE.2005.60","volume":"17","author":"MJ Zaki","year":"2005","unstructured":"Zaki MJ, Hsiao C-J. Efficient algorithms for mining closed itemsets and their lattice structure. IEEE Trans Knowl Data Eng. 2005;17(4):462\u201378.","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"30_CR56","doi-asserted-by":"crossref","unstructured":"Burdick D, Calimlim M, Gehrke J. MAFIA: a maximal frequent itemset algorithm for transactional databases. In: Proceedings of the International Conference on Data Engineering, 2001. pp 443\u2013452.","DOI":"10.1109\/ICDE.2001.914857"},{"key":"30_CR57","doi-asserted-by":"crossref","unstructured":"Chen B, Haas P, Scheuermann P. A new two-phase sampling based algorithm for discovering association rules. In: Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2002. pp 462\u2013468.","DOI":"10.1145\/775047.775114"},{"issue":"1\u20132","key":"30_CR58","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1023\/A:1007652502315","volume":"42","author":"MJ Zaki","year":"2001","unstructured":"Zaki MJ. SPADE: an efficient algorithm for mining frequent sequences. Mach Learn. 2001;42(1\u20132):31\u201360.","journal-title":"Mach Learn"},{"key":"30_CR59","doi-asserted-by":"crossref","unstructured":"Yan X, Han J, Afshar R. CloSpan: mining closed sequential patterns in large datasets. In: Proceedings of the SIAM International Conference on Data Mining, 2003. pp 166\u2013177.","DOI":"10.1137\/1.9781611972733.15"},{"key":"30_CR60","unstructured":"Pei J, Han J, Asl MB, Pinto H, Chen Q, Dayal U, Hsu MC. PrefixSpan mining sequential patterns efficiently by prefix projected pattern growth. In: Proceedings of the International Conference on Data Engineering, 2001. pp 215\u2013226."},{"key":"30_CR61","doi-asserted-by":"crossref","unstructured":"Ayres J, Flannick J, Gehrke J, Yiu T. Sequential PAttern Mining using a bitmap representation. In: Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2002. pp 429\u2013435.","DOI":"10.1145\/775047.775109"},{"issue":"1","key":"30_CR62","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1016\/S0169-023X(02)00209-4","volume":"46","author":"F Masseglia","year":"2003","unstructured":"Masseglia F, Poncelet P, Teisseire M. Incremental mining of sequential patterns in large databases. Data Knowl Eng. 2003;46(1):97\u2013121.","journal-title":"Data Knowl Eng"},{"issue":"3","key":"30_CR63","doi-asserted-by":"crossref","first-page":"645","DOI":"10.1109\/TNN.2005.845141","volume":"16","author":"R Xu","year":"2005","unstructured":"Xu R, Wunsch-II DC. Survey of clustering algorithms. IEEE Trans Neural Netw. 2005;16(3):645\u201378.","journal-title":"IEEE Trans Neural Netw"},{"issue":"4","key":"30_CR64","doi-asserted-by":"crossref","first-page":"716","DOI":"10.1016\/j.ins.2010.10.008","volume":"181","author":"M-C Chiang","year":"2011","unstructured":"Chiang M-C, Tsai C-W, Yang C-S. A time-efficient pattern reduction algorithm for k-means clustering. Inform Sci. 2011;181(4):716\u201331.","journal-title":"Inform Sci"},{"key":"30_CR65","unstructured":"Bradley PS, Fayyad UM. Refining initial points for k-means clustering. In: Proceedings of the International Conference on Machine Learning, 1998. pp 91\u201399."},{"key":"30_CR66","first-page":"1909","volume":"7","author":"P Laskov","year":"2006","unstructured":"Laskov P, Gehl C, Kr\u00fcger S, M\u00fcller K-R. Incremental support vector learning: analysis, implementation and applications. J Mach Learn Res. 2006;7:1909\u201336.","journal-title":"J Mach Learn Res"},{"key":"30_CR67","unstructured":"Russom P. Big data analytics. TDWI: Tech. Rep ; 2011."},{"issue":"12","key":"30_CR68","doi-asserted-by":"crossref","first-page":"798","DOI":"10.1016\/j.tplants.2014.08.004","volume":"19","author":"C Ma","year":"2014","unstructured":"Ma C, Zhang HH, Wang X. Machine learning for big data analytics in plants. Trends Plant Sci. 2014;19(12):798\u2013808.","journal-title":"Trends Plant Sci"},{"issue":"5","key":"30_CR69","doi-asserted-by":"crossref","first-page":"662","DOI":"10.1080\/1369118X.2012.678878","volume":"15","author":"D Boyd","year":"2012","unstructured":"Boyd D, Crawford K. Critical questions for big data. Inform Commun Soc. 2012;15(5):662\u201379.","journal-title":"Inform Commun Soc"},{"key":"30_CR70","doi-asserted-by":"crossref","unstructured":"Katal A, Wazid M, Goudar R. Big data: issues, challenges, tools and good practices. In: Proceedings of the International Conference on Contemporary Computing, 2013. pp 404\u2013409.","DOI":"10.1109\/IC3.2013.6612229"},{"issue":"6018","key":"30_CR71","doi-asserted-by":"crossref","first-page":"717","DOI":"10.1126\/science.1197448","volume":"331","author":"RG Baraniuk","year":"2011","unstructured":"Baraniuk RG. More is less: signal processing and the data deluge. Science. 2011;331(6018):717\u20139.","journal-title":"Science"},{"key":"30_CR72","doi-asserted-by":"crossref","unstructured":"Lee J, Hong S, Lee JH. An efficient prediction for heavy rain from big weather data using genetic algorithm. In: Proceedings of the International Conference on Ubiquitous Information Management and Communication, 2014. pp 25:1\u201325:7.","DOI":"10.1145\/2557977.2558048"},{"issue":"1\u20134","key":"30_CR73","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1016\/S1088-467X(98)00007-9","volume":"1","author":"A Famili","year":"1997","unstructured":"Famili A, Shen W-M, Weber R, Simoudis E. Data preprocessing and intelligent data analysis. Intel Data Anal. 1997;1(1\u20134):3\u201323.","journal-title":"Intel Data Anal"},{"key":"30_CR74","unstructured":"Zhang H. A novel data preprocessing solution for large scale digital forensics investigation on big data, Master\u2019s thesis, Norway, 2013."},{"issue":"1","key":"30_CR75","first-page":"1","volume":"6","author":"YJ Ham","year":"2014","unstructured":"Ham YJ, Lee H-W. International journal of advances in soft computing and its applications. Calc Paralleles Reseaux et Syst Repar. 2014;6(1):1\u201318.","journal-title":"Calc Paralleles Reseaux et Syst Repar"},{"key":"30_CR76","doi-asserted-by":"crossref","unstructured":"Cormode G, Duffield N. Sampling for big data: a tutorial. In: Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2014. pp 1975\u20131975.","DOI":"10.1145\/2623330.2630811"},{"key":"30_CR77","doi-asserted-by":"crossref","unstructured":"Satyanarayana A. Intelligent sampling for big data using bootstrap sampling and chebyshev inequality. In: Proceedings of the IEEE Canadian Conference on Electrical and Computer Engineering, 2014. pp 1\u20136.","DOI":"10.1109\/CCECE.2014.6901029"},{"key":"30_CR78","doi-asserted-by":"crossref","unstructured":"Jun SW, Fleming K, Adler M, Emer JS. Zip-io: architecture for application-specific compression of big data. In: Proceedings of the International Conference on Field-Programmable Technology, 2012, pp 343\u2013351.","DOI":"10.1109\/FPT.2012.6412159"},{"key":"30_CR79","doi-asserted-by":"crossref","unstructured":"Zou H, Yu Y, Tang W, Chen HM. Improving I\/O performance with adaptive data compression for big data applications. In: Proceedings of the International Parallel and Distributed Processing Symposium Workshops, 2014. pp 1228\u20131237.","DOI":"10.1109\/IPDPSW.2014.138"},{"issue":"8","key":"30_CR80","doi-asserted-by":"crossref","first-page":"1563","DOI":"10.1016\/j.jcss.2014.04.022","volume":"80","author":"C Yang","year":"2014","unstructured":"Yang C, Zhang X, Zhong C, Liu C, Pei J, Ramamohanarao K, Chen J. A spatiotemporal compression based approach for efficient big data processing on cloud. J Comp Syst Sci. 2014;80(8):1563\u201383.","journal-title":"J Comp Syst Sci"},{"key":"30_CR81","doi-asserted-by":"crossref","unstructured":"Xue Z, Shen G, Li J, Xu Q, Zhang Y, Shao J. Compression-aware I\/O performance analysis for big data clustering. In: Proceedings of the International Workshop on Big Data, Streams and Heterogeneous Source Mining: Algorithms, Systems, Programming Models and Applications, 2012. pp 45\u201352.","DOI":"10.1145\/2351316.2351323"},{"key":"30_CR82","unstructured":"Pospiech M, Felden C. Big data\u2014a state-of-the-art. In: Proceedings of the Americas Conference on Information Systems, 2012, pp 1\u201323. [Online]. Available: http:\/\/aisel.aisnet.org\/amcis2012\/proceedings\/DecisionSupport\/22 ."},{"key":"30_CR83","unstructured":"Apache Hadoop, February 2, 2015. [Online]. Available: http:\/\/hadoop.apache.org ."},{"key":"30_CR84","unstructured":"Cuda, February 2, 2015. [Online]. Available: URL: http:\/\/www.nvidia.com\/object\/cuda_home_new.html ."},{"key":"30_CR85","unstructured":"Apache Storm, February 2, 2015. [Online]. Available: URL: http:\/\/storm.apache.org\/ ."},{"key":"30_CR86","first-page":"801","volume":"14","author":"RR Curtin","year":"2013","unstructured":"Curtin RR, Cline JR, Slagle NP, March WB, Ram P, Mehta NA, Gray AG. MLPACK: a scalable C++ machine learning library. J Mach Learn Res. 2013;14:801\u20135.","journal-title":"J Mach Learn Res"},{"key":"30_CR87","unstructured":"Apache Mahout, February 2, 2015. [Online]. Available: http:\/\/mahout.apache.org\/ ."},{"key":"30_CR88","doi-asserted-by":"crossref","unstructured":"Huai Y, Lee R, Zhang S, Xia CH, Zhang X. DOT: a matrix model for analyzing, optimizing and deploying software for big data analytics in distributed systems. In: Proceedings of the ACM Symposium on Cloud Computing, 2011. pp 4:1\u20134:14.","DOI":"10.1145\/2038916.2038920"},{"key":"30_CR89","doi-asserted-by":"crossref","unstructured":"Rusu F, Dobra A. GLADE: a scalable framework for efficient analytics. In: Proceedings of LADIS Workshop held in conjunction with VLDB, 2012. pp 1\u20136.","DOI":"10.1145\/2146382.2146386"},{"key":"30_CR90","doi-asserted-by":"crossref","unstructured":"Cheng Y, Qin C, Rusu F. GLADE: big data analytics made easy. In: Proceedings of the ACM SIGMOD International Conference on Management of Data, 2012. pp 697\u2013700.","DOI":"10.1145\/2213836.2213936"},{"key":"30_CR91","doi-asserted-by":"crossref","unstructured":"Essa YM, Attiya G, El-Sayed A. Mobile agent based new framework for improving big data analysis. In: Proceedings of the International Conference on Cloud Computing and Big Data. 2013, pp 381\u2013386.","DOI":"10.1109\/CLOUDCOM-ASIA.2013.75"},{"key":"30_CR92","doi-asserted-by":"crossref","unstructured":"Wonner J, Grosjean J, Capobianco A, Bechmann D Starfish: a selection technique for dense virtual environments. In: Proceedings of the ACM Symposium on Virtual Reality Software and Technology, 2012. pp 101\u2013104.","DOI":"10.1145\/2407336.2407356"},{"key":"30_CR93","doi-asserted-by":"crossref","unstructured":"Demchenko Y, de Laat C, Membrey P. Defining architecture components of the big data ecosystem. In: Proceedings of the International Conference on Collaboration Technologies and Systems, 2014. pp 104\u2013112.","DOI":"10.1109\/CTS.2014.6867550"},{"key":"30_CR94","doi-asserted-by":"crossref","unstructured":"Ye F, Wang ZJ, Zhou FC, Wang YP, Zhou YC. Cloud-based big data mining and analyzing services platform integrating r. In: Proceedings of the International Conference on Advanced Cloud and Big Data, 2013. pp 147\u2013151.","DOI":"10.1109\/CBD.2013.13"},{"issue":"1","key":"30_CR95","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1109\/TKDE.2013.109","volume":"26","author":"X Wu","year":"2014","unstructured":"Wu X, Zhu X, Wu G-Q, Ding W. Data mining with big data. IEEE Trans Knowl Data Eng. 2014;26(1):97\u2013107.","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"30_CR96","unstructured":"Laurila JK, Gatica-Perez D, Aad I, Blom J, Bornet O, Do T, Dousse O, Eberle J, Miettinen M. The mobile data challenge: big data for mobile computing research. In: Proceedings of the Mobile Data Challenge by Nokia Workshop, 2012. pp 1\u20138."},{"issue":"1","key":"30_CR97","doi-asserted-by":"crossref","first-page":"412","DOI":"10.1016\/j.dss.2012.05.048","volume":"55","author":"H Demirkan","year":"2013","unstructured":"Demirkan H, Delen D. Leveraging the capabilities of service-oriented decision support systems: putting analytics and big data in cloud. Decision Support Syst. 2013;55(1):412\u201321.","journal-title":"Decision Support Syst"},{"issue":"5","key":"30_CR98","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1109\/MC.2013.162","volume":"46","author":"D Talia","year":"2013","unstructured":"Talia D. Clouds for scalable big data analytics. Computer. 2013;46(5):98\u2013101.","journal-title":"Computer"},{"issue":"4","key":"30_CR99","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1109\/MNET.2014.6863131","volume":"28","author":"R Lu","year":"2014","unstructured":"Lu R, Zhu H, Liu X, Liu JK, Shao J. Toward efficient and privacy-preserving computing in big data era. IEEE Netw. 2014;28(4):46\u201350.","journal-title":"IEEE Netw"},{"key":"30_CR100","doi-asserted-by":"crossref","unstructured":"Cuzzocrea A, Song IY, Davis KC. Analytics over large-scale multidimensional data: The big data revolution!. In: Proceedings of the ACM International Workshop on Data Warehousing and OLAP, 2011. pp 101\u2013104.","DOI":"10.1145\/2064676.2064695"},{"key":"30_CR101","doi-asserted-by":"crossref","unstructured":"Zhang J, Huang ML. 5Ws model for big data analysis and visualization. In: Proceedings of the International Conference on Computational Science and Engineering, 2013. pp 1021\u20131028.","DOI":"10.1109\/CSE.2013.149"},{"key":"30_CR102","doi-asserted-by":"crossref","unstructured":"Chandarana P, Vijayalakshmi M. Big data analytics frameworks. In: Proceedings of the International Conference on Circuits, Systems, Communication and Information Technology Applications, 2014. pp 430\u2013434.","DOI":"10.1109\/CSCITA.2014.6839299"},{"key":"30_CR103","unstructured":"Apache Drill February 2, 2015. [Online]. Available: URL: http:\/\/drill.apache.org\/ ."},{"key":"30_CR104","doi-asserted-by":"crossref","first-page":"652","DOI":"10.1109\/ACCESS.2014.2332453","volume":"2","author":"H Hu","year":"2014","unstructured":"Hu H, Wen Y, Chua T-S, Li X. Toward scalable systems for big data analytics: a technology tutorial. IEEE Access. 2014;2:652\u201387.","journal-title":"IEEE Access"},{"key":"30_CR105","doi-asserted-by":"crossref","unstructured":"Sagiroglu S, Sinanc D, Big data: a review. In: Proceedings of the International Conference on Collaboration Technologies and Systems, 2013. pp 42\u201347.","DOI":"10.1109\/CTS.2013.6567202"},{"issue":"2","key":"30_CR106","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2481244.2481246","volume":"14","author":"W Fan","year":"2013","unstructured":"Fan W, Bifet A. Mining big data: current status, and forecast to the future. ACM SIGKDD Explor Newslett. 2013;14(2):1\u20135.","journal-title":"ACM SIGKDD Explor Newslett"},{"key":"30_CR107","unstructured":"Diebold FX. On the origin(s) and development of the term \u201cbig data\u201d, Penn Institute for Economic Research, Department of Economics, University of Pennsylvania, Tech. Rep. 2012. [Online]. Available: http:\/\/economics.sas.upenn.edu\/sites\/economics.sas.upenn.edu\/files\/12-037.pdf ."},{"key":"30_CR108","volume-title":"Predictive data mining: a practical guide","author":"SM Weiss","year":"1998","unstructured":"Weiss SM, Indurkhya N. Predictive data mining: a practical guide. San Francisco: Morgan Kaufmann Publishers Inc.; 1998."},{"issue":"3","key":"30_CR109","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1109\/TETC.2014.2330519","volume":"2","author":"A Fahad","year":"2014","unstructured":"Fahad A, Alshatri N, Tari Z, Alamri A, Khalil I, Zomaya A, Foufou S, Bouras A. A survey of clustering algorithms for big data: taxonomy and empirical analysis. IEEE Trans Emerg Topics Comp. 2014;2(3):267\u201379.","journal-title":"IEEE Trans Emerg Topics Comp"},{"key":"30_CR110","doi-asserted-by":"crossref","unstructured":"Shirkhorshidi AS, Aghabozorgi SR, Teh YW, Herawan T. Big data clustering: a review. In: Proceedings of the International Conference on Computational Science and Its Applications, 2014. pp 707\u2013720.","DOI":"10.1007\/978-3-319-09156-3_49"},{"issue":"12","key":"30_CR111","doi-asserted-by":"crossref","first-page":"1886","DOI":"10.14778\/2367502.2367529","volume":"5","author":"H Xu","year":"2012","unstructured":"Xu H, Li Z, Guo S, Chen K. Cloudvista: interactive and economical visual cluster analysis for big data in the cloud. Proc VLDB Endowment. 2012;5(12):1886\u20139.","journal-title":"Proc VLDB Endowment"},{"issue":"89","key":"30_CR112","doi-asserted-by":"crossref","first-page":"505","DOI":"10.1016\/j.sysarc.2006.02.003","volume":"52","author":"X Cui","year":"2006","unstructured":"Cui X, Gao J, Potok TE. A flocking based algorithm for document clustering analysis. J Syst Archit. 2006;52(89):505\u201315.","journal-title":"J Syst Archit"},{"issue":"7","key":"30_CR113","doi-asserted-by":"crossref","first-page":"1736","DOI":"10.1016\/j.future.2012.07.009","volume":"29","author":"X Cui","year":"2013","unstructured":"Cui X, Charles JS, Potok T. GPU enhanced parallel computing for large scale data clustering. Future Gener Comp Syst. 2013;29(7):1736\u201341.","journal-title":"Future Gener Comp Syst"},{"key":"30_CR114","doi-asserted-by":"crossref","unstructured":"Feldman D, Schmidt M, Sohler C. Turning big data into tiny data: Constant-size coresets for k-means, pca and projective clustering. In: Proceedings of the ACM-SIAM Symposium on Discrete Algorithms, 2013. pp 1434\u20131453.","DOI":"10.1137\/1.9781611973105.103"},{"key":"30_CR115","doi-asserted-by":"crossref","unstructured":"Tekin C, van\u00a0der Schaar M. Distributed online big data classification using context information. In: Proceedings of the Allerton Conference on Communication, Control, and Computing, 2013. pp 1435\u20131442.","DOI":"10.1109\/Allerton.2013.6736696"},{"key":"30_CR116","doi-asserted-by":"crossref","unstructured":"Rebentrost P, Mohseni M, Lloyd S. Quantum support vector machine for big feature and big data classification. CoRR, vol. abs\/1307.0471, 2014. [Online]. Available: http:\/\/dblp.uni-trier.de\/db\/journals\/corr\/corr1307.html#RebentrostML13 .","DOI":"10.1103\/PhysRevLett.113.130503"},{"key":"30_CR117","doi-asserted-by":"crossref","unstructured":"Lin MY, Lee PY, Hsueh SC. Apriori-based frequent itemset mining algorithms on mapreduce. In: Proceedings of the International Conference on Ubiquitous Information Management and Communication, 2012. pp 76:1\u201376:8.","DOI":"10.1145\/2184751.2184842"},{"key":"30_CR118","doi-asserted-by":"crossref","unstructured":"Riondato M, DeBrabant JA, Fonseca R, Upfal E. PARMA: a parallel randomized algorithm for approximate association rules mining in mapreduce. In: Proceedings of the ACM International Conference on Information and Knowledge Management, 2012. pp 85\u201394.","DOI":"10.1145\/2396761.2396776"},{"key":"30_CR119","doi-asserted-by":"crossref","unstructured":"Leung CS, MacKinnon R, Jiang F. Reducing the search space for big data mining for interesting patterns from uncertain data. In: Proceedings of the International Congress on Big Data, 2014. pp 315\u2013322.","DOI":"10.1109\/BigData.Congress.2014.53"},{"key":"30_CR120","doi-asserted-by":"crossref","unstructured":"Yang L, Shi Z, Xu L, Liang F, Kirsh I. DH-TRIE frequent pattern mining on hadoop using JPA. In: Proceedings of the International Conference on Granular Computing, 2011. pp 875\u2013878.","DOI":"10.1109\/GRC.2011.6122552"},{"key":"30_CR121","doi-asserted-by":"crossref","unstructured":"Huang JW, Lin SC, Chen MS. DPSP: Distributed progressive sequential pattern mining on the cloud. In: Proceedings of the Advances in Knowledge Discovery and Data Mining, vol. 6119, 2010, pp 27\u201334.","DOI":"10.1007\/978-3-642-13672-6_3"},{"issue":"2","key":"30_CR122","first-page":"141","volume":"10","author":"CE Paz","year":"1998","unstructured":"Paz CE. A survey of parallel genetic algorithms. Calc Paralleles Reseaux et Syst Repar. 1998;10(2):141\u201371.","journal-title":"Calc Paralleles Reseaux et Syst Repar"},{"key":"30_CR123","unstructured":"kranthi Kiran B, Babu AV. A comparative study of issues in big data clustering algorithm with constraint based genetic algorithm for associative clustering. Int J Innov Res Comp Commun Eng 2014; 2(8): 5423\u20135432."},{"key":"30_CR124","unstructured":"Bu Y, Borkar VR, Carey MJ, Rosen J, Polyzotis N, Condie T, Weimer M, Ramakrishnan R. Scaling datalog for machine learning on big data, CoRR, vol. abs\/1203.0160, 2012. [Online]. Available: http:\/\/dblp.uni-trier.de\/db\/journals\/corr\/corr1203.html#abs-1203-0160 ."},{"key":"30_CR125","doi-asserted-by":"crossref","unstructured":"Malewicz G, Austern MH, Bik AJ, Dehnert JC, Horn I, Leiser N, Czajkowski G. Pregel: A system for large-scale graph processing. In: Proceedings of the ACM SIGMOD International Conference on Management of Data, 2010. pp 135\u2013146.","DOI":"10.1145\/1807167.1807184"},{"key":"30_CR126","doi-asserted-by":"crossref","unstructured":"Hasan S, Shamsuddin S, \u00a0Lopes N. Soft computing methods for big data problems. In: Proceedings of the Symposium on GPU Computing and Applications, 2013. pp 235\u2013247.","DOI":"10.1007\/978-981-287-134-3_15"},{"key":"30_CR127","unstructured":"Ku-Mahamud KR. Big data clustering using grid computing and ant-based algorithm. In: Proceedings of the International Conference on Computing and Informatics, 2013. pp 6\u201314."},{"key":"30_CR128","doi-asserted-by":"crossref","unstructured":"Deneubourg JL, Goss S, Franks N, Sendova-Franks A, Detrain C, Chr\u00e9tien L. The dynamics of collective sorting robot-like ants and ant-like robots. In: Proceedings of the International Conference on Simulation of Adaptive Behavior on From Animals to Animats, 1990. pp 356\u2013363.","DOI":"10.7551\/mitpress\/3115.003.0048"},{"key":"30_CR129","unstructured":"Radoop [Online]. https:\/\/rapidminer.com\/products\/radoop\/ . Accessed 2 Feb 2015."},{"key":"30_CR130","unstructured":"PigMix [Online]. https:\/\/cwiki.apache.org\/confluence\/display\/PIG\/PigMix . Accessed 2 Feb 2015."},{"key":"30_CR131","unstructured":"GridMix [Online]. http:\/\/hadoop.apache.org\/docs\/r1.2.1\/gridmix.html . Accessed 2 Feb 2015."},{"key":"30_CR132","unstructured":"TeraSoft [Online]. http:\/\/sortbenchmark.org\/ . Accessed 2 Feb 2015."},{"key":"30_CR133","unstructured":"TPC, transaction processing performance council [Online]. http:\/\/www.tpc.org\/ . Accessed 2 Feb 2015."},{"key":"30_CR134","doi-asserted-by":"crossref","unstructured":"Cooper BF, Silberstein A, Tam E, Ramakrishnan R, Sears R. Benchmarking cloud serving systems with ycsb. In: Proceedings of the ACM Symposium on Cloud Computing, 2010. pp 143\u2013154.","DOI":"10.1145\/1807128.1807152"},{"key":"30_CR135","doi-asserted-by":"crossref","unstructured":"Ghazal A, Rabl T, Hu M, Raab F, Poess M, Crolotte A, Jacobsen HA. BigBench: Towards an industry standard benchmark for big data analytics. In: Proceedings of the ACM SIGMOD International Conference on Management of Data, 2013. pp 1197\u20131208.","DOI":"10.1145\/2463676.2463712"},{"key":"30_CR136","unstructured":"Cheptsov A. Hpc in big data age: An evaluation report for java-based data-intensive applications implemented with hadoop and openmpi. In: Proceedings of the European MPI Users\u2019 Group Meeting, 2014. pp 175:175\u2013175:180."},{"key":"30_CR137","doi-asserted-by":"crossref","unstructured":"Yuan LY, Wu L, You JH, Chi Y. Rubato db: A highly scalable staged grid database system for oltp and big data applications. In: Proceedings of the ACM International Conference on Conference on Information and Knowledge Management, 2014. pp 1\u201310.","DOI":"10.1145\/2661829.2661879"},{"key":"30_CR138","doi-asserted-by":"crossref","unstructured":"Zhao JM, Wang WS, Liu X, Chen YF. Big data benchmark - big DS. In: Proceedings of the Advancing Big Data Benchmarks, 2014, pp. 49\u201357.","DOI":"10.1007\/978-3-319-10596-3_5"},{"key":"30_CR139","unstructured":"\u00a0Saletore V, Krishnan K, Viswanathan V, Tolentino M. HcBench: Methodology, development, and full-system characterization of a customer usage representative big data\/hadoop benchmark. In: Advancing Big Data Benchmarks, 2014. pp 73\u201393."},{"key":"30_CR140","doi-asserted-by":"crossref","unstructured":"Zhang L, Stoffel A, Behrisch M, \u00a0Mittelstadt S, Schreck T, Pompl R, Weber S, Last H, Keim D. Visual analytics for the big data era\u2014a comparative review of state-of-the-art commercial systems. In: Proceedings of the IEEE Conference on Visual Analytics Science and Technology, 2012. pp 173\u2013182.","DOI":"10.1109\/VAST.2012.6400554"},{"key":"30_CR141","doi-asserted-by":"crossref","unstructured":"Harati A, Lopez S, Obeid I, Picone J, Jacobson M, Tobochnik S. The TUH EEG CORPUS: A big data resource for automated eeg interpretation. In: Proceeding of the IEEE Signal Processing in Medicine and Biology Symposium, 2014. pp 1\u20135.","DOI":"10.1109\/SPMB.2014.7002953"},{"issue":"2","key":"30_CR142","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. Proc VLDB Endowment. 2009;2(2):1626\u20139.","journal-title":"Proc VLDB Endowment"},{"key":"30_CR143","unstructured":"Beckmann M, Ebecken NFF, de\u00a0Lima BSLP, Costa MA. A user interface for big data with rapidminer. RapidMiner World, Boston, MA, Tech. Rep., 2014. [Online]. Available: http:\/\/www.slideshare.net\/RapidMiner\/a-user-interface-for-big-data-with-rapidminer-marcelo-beckmann ."},{"key":"30_CR144","doi-asserted-by":"crossref","unstructured":"Januzaj E, Kriegel HP, Pfeifle M. DBDC: Density based distributed clustering. In: Proceedings of the Advances in Database Technology, 2004; vol. 2992, 2004, pp 88\u2013105.","DOI":"10.1007\/978-3-540-24741-8_7"},{"key":"30_CR145","doi-asserted-by":"crossref","first-page":"674","DOI":"10.1007\/978-3-642-10665-1_71","volume":"5931","author":"W Zhao","year":"2009","unstructured":"Zhao W, Ma H, He Q. Parallel k-means clustering based on mapreduce. Proceedings Cloud Comp. 2009;5931:674\u20139.","journal-title":"Proceedings Cloud Comp"},{"issue":"1","key":"30_CR146","first-page":"115","volume":"57","author":"RL Nolan","year":"1979","unstructured":"Nolan RL. Managing the crises in data processing. Harvard Bus Rev. 1979;57(1):115\u201326.","journal-title":"Harvard Bus Rev"},{"key":"30_CR147","doi-asserted-by":"crossref","unstructured":"Tsai CW, Huang WC, Chiang MC. Recent development of metaheuristics for clustering. In: Proceedings of the Mobile, Ubiquitous, and Intelligent Computing, 2014; vol. 274, pp. 629\u2013636.","DOI":"10.1007\/978-3-642-40675-1_93"}],"container-title":["Journal of Big Data"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s40537-015-0030-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/s40537-015-0030-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s40537-015-0030-3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,11]],"date-time":"2024-06-11T14:06:38Z","timestamp":1718114798000},"score":1,"resource":{"primary":{"URL":"http:\/\/www.journalofbigdata.com\/content\/2\/1\/21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,10,1]]},"references-count":147,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2015,12]]}},"alternative-id":["30"],"URL":"https:\/\/doi.org\/10.1186\/s40537-015-0030-3","relation":{},"ISSN":["2196-1115"],"issn-type":[{"value":"2196-1115","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,10,1]]},"article-number":"21"}}