{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,13]],"date-time":"2026-11-13T21:14:50Z","timestamp":1794604490464,"version":"4.9.1"},"reference-count":77,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2018,11,1]],"date-time":"2018-11-01T00:00:00Z","timestamp":1541030400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/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":[[2018,12]]},"DOI":"10.1186\/s40537-018-0151-6","type":"journal-article","created":{"date-parts":[[2018,11,1]],"date-time":"2018-11-01T09:28:57Z","timestamp":1541064537000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":677,"title":["A survey on addressing high-class imbalance in big data"],"prefix":"10.1186","volume":"5","author":[{"given":"Joffrey L.","family":"Leevy","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Taghi M.","family":"Khoshgoftaar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Richard A.","family":"Bauder","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Naeem","family":"Seliya","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2018,11,1]]},"reference":[{"key":"151_CR1","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1007\/s13755-018-0051-3","volume":"6","author":"RA Bauder","year":"2018","unstructured":"Bauder RA, Khoshgoftaar TM. The effects of varying class distribution on learner behavior for medicare fraud detection with imbalanced Big Data. Health Inf Sci Syst. 2018;6:9 (14 pages).","journal-title":"Health Inf Sci Syst"},{"issue":"9","key":"151_CR2","doi-asserted-by":"publisher","first-page":"1263","DOI":"10.1109\/TKDE.2008.239","volume":"21","author":"H He","year":"2009","unstructured":"He H, Garcia E. Learning from imbalanced data. IEEE Trans Knowl Data Eng. 2009;21(9):1263\u201384.","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"151_CR3","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1016\/j.knosys.2015.05.027","volume":"87","author":"I Triguero","year":"2015","unstructured":"Triguero I, Rio S, Lopez V, Bacardit J, Ben\u00edtez J, Herrera F. ROSEFW-RF: the winner algorithm for the ECBDL\u201914 big data competition: an extremely imbalanced big data bioinformatics problem. Knowl Based Syst. 2015;87:69\u201379.","journal-title":"Knowl Based Syst"},{"key":"151_CR4","doi-asserted-by":"crossref","unstructured":"Seliya N, Khoshgoftaar TM, Van Hulse J. A study on the relationships of classifier performance metrics. In: 21st international conference on tools with artificial intelligence (ICTAI 2009). IEEE. 2009. pp. 59\u201366.","DOI":"10.1109\/ICTAI.2009.25"},{"key":"151_CR5","doi-asserted-by":"crossref","unstructured":"Katal A, Wazid M, Goudar R. Big data: issues, challenges, tools, and good practices. In: Sixth international conference on contemporary computing. 2013.","DOI":"10.1109\/IC3.2013.6612229"},{"key":"151_CR6","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1186\/s40537-018-0138-3","volume":"5","author":"M Herland","year":"2018","unstructured":"Herland M, Khoshgoftaar TM, Bauder RA. Big Data fraud detection using multiple medicare data sources. J Big Data. 2018;5:29 (21 pages).","journal-title":"J Big Data"},{"key":"151_CR7","doi-asserted-by":"crossref","unstructured":"Bauder RA, Khoshgoftaar TM. Medicare fraud detection using random forest with class imbalanced Big Data. In: 2018 IEEE international conference on information reuse and integration (IRI), IEEE. 2018. pp. 80\u20137.","DOI":"10.1109\/IRI.2018.00019"},{"issue":"3","key":"151_CR8","first-page":"176","volume":"7","author":"A Ali","year":"2015","unstructured":"Ali A, Shamsuddin SM, Ralescu AL. Classification with class imbalance problem: a review. Int J Adv Soft Comput Appl. 2015;7(3):176\u2013204.","journal-title":"Int J Adv Soft Comput Appl."},{"key":"151_CR9","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1016\/j.fss.2014.01.015","volume":"258","author":"V Lopez","year":"2015","unstructured":"Lopez V, Rio S, Benitez J, Herrera F. Cost-sensitive linguistic fuzzy rule based classification systems under the MapReduce framework for imbalanced Big Data. Fuzzy Sets Syst. 2015;258:5\u201338.","journal-title":"Fuzzy Sets Syst"},{"key":"151_CR10","volume-title":"Fuzzy algorithms with applications to image processing and pattern recognition","author":"Z Chi","year":"1996","unstructured":"Chi Z, Yan H, Pham T. Fuzzy algorithms with applications to image processing and pattern recognition. Singapore: World Scientific; 1996."},{"key":"151_CR11","unstructured":"Wang D, Wu P, Zhao P, Hoi S. A framework of sparse online learning and its applications. Comput Sci. 2015."},{"key":"151_CR12","first-page":"777","volume":"10","author":"J Langford","year":"2009","unstructured":"Langford J, Li L, Zhang T. Sparse online learning via truncated gradient. J Mach Learn Res. 2009;10:777\u2013801.","journal-title":"J Mach Learn Res"},{"key":"151_CR13","doi-asserted-by":"crossref","unstructured":"Maurya A. Bayesian optimization for predicting rare internal failures in manufacturing processes. In: IEEE international conference on Big Data. 2016.","DOI":"10.1109\/BigData.2016.7840827"},{"key":"151_CR14","doi-asserted-by":"publisher","first-page":"748681","DOI":"10.1155\/2015\/748681","volume":"2015","author":"D Galpert","year":"2015","unstructured":"Galpert D, del R\u00edo S, Herrera F, Ancede-Gallardo E, Antunes A, Ag\u00fcero-Chapin G. An effective Big Data supervised imbalanced classification approach for ortholog detection in related yeast species. BioMed Res Int. 2015;2015:748681. \n                    https:\/\/doi.org\/10.1155\/2015\/748681\n                    \n                  .","journal-title":"BioMed Res Int"},{"key":"151_CR15","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1016\/j.jss.2016.09.007","volume":"122","author":"C Tsai","year":"2016","unstructured":"Tsai C, Lin W, Ke S. Big Data mining with parallel computing: a comparison of distributed and MapReduce methodologies. J Syst Softw. 2016;122:83\u201392.","journal-title":"J Syst Softw"},{"key":"151_CR16","doi-asserted-by":"crossref","unstructured":"Triguero I, Galar M, Merino D, Maillo J, Bustince H, Herrera F. Evolutionary undersampling for extremely imbalanced Big Data classification under Apache Spark. In: IEEE congress on evolutionary computation (CEC). 2016.","DOI":"10.1109\/CEC.2016.7743853"},{"key":"151_CR17","doi-asserted-by":"crossref","unstructured":"Khoshgoftaar TM, Seiffert C, Van Hulse J, Napolitano A, Folleco A. Learning with limited minority class data. In: Sixth international conference on machine learning and applications (ICMLA 2007), IEEE. 2007. pp. 348\u201353.","DOI":"10.1109\/ICMLA.2007.76"},{"key":"151_CR18","doi-asserted-by":"crossref","unstructured":"Van Hulse J, Khoshgoftaar TM, Napolitano A. Experimental perspectives on learning from imbalanced data. In: Proceedings of the 24th international conference on machine learning, ACM. 2007. pp. 935\u201342.","DOI":"10.1145\/1273496.1273614"},{"key":"151_CR19","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1016\/j.asoc.2014.11.023","volume":"27","author":"R Malhotra","year":"2015","unstructured":"Malhotra R. A systematic review of machine learning techniques for software fault prediction. Appl Soft Comput. 2015;27:504\u201318.","journal-title":"Appl Soft Comput"},{"issue":"1","key":"151_CR20","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1142\/S0218194015400057","volume":"25","author":"H Wang","year":"2015","unstructured":"Wang H, Khoshgoftaar TM, Napolitano A. An empirical investigation on Wrapper-Based feature selection for predicting software quality. Int J Softw Eng Knowl Eng. 2015;25(1):93\u2013114.","journal-title":"Int J Softw Eng Knowl Eng"},{"key":"151_CR21","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/j.neucom.2012.04.039","volume":"105","author":"L Yin","year":"2013","unstructured":"Yin L, Ge Y, Xiao K, Wang X, Quan X. Feature selection for high-dimensional imbalanced data. Neurocomputing. 2013;105:3\u201311.","journal-title":"Neurocomputing"},{"key":"151_CR22","unstructured":"Mladenic D, Grobelnik M. Feature selection for unbalanced class distribution and Na\u00efve Bayes. In: International conference on machine learning. 1999."},{"issue":"1","key":"151_CR23","doi-asserted-by":"publisher","first-page":"80","DOI":"10.1145\/1007730.1007741","volume":"6","author":"Z Zheng","year":"2014","unstructured":"Zheng Z, Wu X, Srihari R. Feature selection for text categorization on imbalanced data. Explor Newsletter. 2014;6(1):80\u20139.","journal-title":"Explor Newsletter"},{"issue":"1","key":"151_CR24","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1109\/TSMCA.2009.2029559","volume":"40","author":"C Seiffert","year":"2010","unstructured":"Seiffert C, Khoshgoftaar TM. RUSBoost: a hybrid approach to alleviating class imbalance. IEEE Trans Syst Man Cybern Part A. 2010;40(1):185\u201397.","journal-title":"IEEE Trans Syst Man Cybern Part A"},{"key":"151_CR25","doi-asserted-by":"publisher","first-page":"340","DOI":"10.1007\/978-3-642-12101-2_35","volume-title":"Intelligent Information and Database Systems","author":"Magdalena Graczyk","year":"2010","unstructured":"Graczyk M, Lasota T, Trawinski B, Trawinski K. Comparison of bagging, boosting and stacking ensembles applied to real estate appraisal. In: Asian conference on intelligent information and database systems. 2010. pp. 340\u201350."},{"key":"151_CR26","unstructured":"McCallum A, Nigam K. A comparison of event models for Naive Bayes text classification. In: AAAI-98 workshop on learning for text categorization. 1998."},{"issue":"1","key":"151_CR27","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L Breiman","year":"2001","unstructured":"Breiman L. Random forests. Mach Learn. 2001;45(1):5\u201332.","journal-title":"Mach Learn"},{"key":"151_CR28","unstructured":"Ho T. Random decision forests. In: Proceedings of the third international conference on document analysis and recognition. 1995."},{"key":"151_CR29","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1613\/jair.953","volume":"16","author":"NV Chawla","year":"2002","unstructured":"Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP. SMOTE: synthetic minority over-sampling technique. J Artif Intell Res. 2002;16:321\u201357.","journal-title":"J Artif Intell Res"},{"key":"151_CR30","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1007\/978-3-540-39804-2_12","volume-title":"Knowledge Discovery in Databases: PKDD 2003","author":"Nitesh V. Chawla","year":"2003","unstructured":"Chawla N, Lazarevic A, Hall L, Bowyer K. SMOTEBoost: improving prediction of the minority class in boosting. In: 7th European conference on principles and practice of knowledge discovery in databases. 2003."},{"key":"151_CR31","doi-asserted-by":"crossref","unstructured":"Rodriguez D, Herraiz I, Harrison R, Dolado J, Riquelme J. Preliminary comparison of techniques for dealing with imbalance in software defect prediction. In: Proceedings of the 18th international conference on evaluation and assessment in software engineering. Article no. 43. 2014.","DOI":"10.1145\/2601248.2601294"},{"key":"151_CR32","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1007\/s40747-017-0037-9","volume":"3","author":"A Fernandez","year":"2017","unstructured":"Fernandez A, Rio S, Chawla N, Herrera F. An insight into imbalanced Big Data classification: outcomes and challenges. Complex Intell Syst. 2017;3:105\u201320.","journal-title":"Complex Intell Syst"},{"key":"151_CR33","doi-asserted-by":"publisher","first-page":"280","DOI":"10.1007\/978-3-642-37456-2_24","volume-title":"Advances in Knowledge Discovery and Data Mining","author":"Peng Cao","year":"2013","unstructured":"Cao P, Zhao D, Zaiane O. An optimized cost-sensitive SVM for imbalanced data learning. In: Pacific-Asia conference on knowledge discovery and data mining. 2013. pp. 280\u201392."},{"key":"151_CR34","first-page":"452","volume-title":"Lecture Notes in Computer Science","author":"Peng Cao","year":"2013","unstructured":"Cao P, Zhao D, Zaiane O. A PSO-based cost-sensitive neural network for imbalanced data classification. In: Pacific-Asia conference on knowledge discovery and data mining. 2013. pp. 452\u201363."},{"issue":"6","key":"151_CR35","doi-asserted-by":"publisher","first-page":"1370","DOI":"10.1109\/TPAMI.2012.172","volume":"35","author":"N Li","year":"2013","unstructured":"Li N, Tsang IW, Zhou Z-H. Efficient optimization of performance measures by classifier adaptation. IEEE Trans Pattern Anal Mach Intell. 2013;35(6):1370\u201382.","journal-title":"IEEE Trans Pattern Anal Mach Intell."},{"key":"151_CR36","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1016\/S0169-2070(97)00044-7","volume":"14","author":"G Zhang","year":"1998","unstructured":"Zhang G, Patuwo B, Hu M. Forecasting with artificial neural networks: the state of the art. Int J Forecast. 1998;14:35\u201362.","journal-title":"Int J Forecast"},{"issue":"7","key":"151_CR37","doi-asserted-by":"publisher","first-page":"6585","DOI":"10.1016\/j.eswa.2011.12.043","volume":"39","author":"V L\u00f3pez","year":"2012","unstructured":"L\u00f3pez V, Fernandez A, Moreno-Torres J, Herrera F. Analysis of preprocessing vs. cost-sensitive learning for imbalanced classification. Open problems on intrinsic data characteristics. Expert Syst Appl. 2012;39(7):6585\u2013608.","journal-title":"Expert Syst Appl"},{"issue":"1","key":"151_CR38","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1007\/s10100-017-0479-6","volume":"26","author":"B Kaminski","year":"2017","unstructured":"Kaminski B, Jakubczyk M, Szufel P. A framework for sensitivity analysis of decision trees. CEJOR. 2017;26(1):135\u201359.","journal-title":"CEJOR"},{"key":"151_CR39","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1007\/978-3-540-30115-8_7","volume-title":"Machine Learning: ECML 2004","author":"Rehan Akbani","year":"2004","unstructured":"Akbani R, Kwek S, Japkowicz N. Applying support vector machines to imbalanced datasets. In: European conference on machine learning. 2004. pp. 39\u201350."},{"issue":"1","key":"151_CR40","doi-asserted-by":"publisher","first-page":"281","DOI":"10.1109\/TSMCB.2008.2002909","volume":"39","author":"Y Tang","year":"2009","unstructured":"Tang Y, Chawla N. SVMs modeling for highly imbalanced classification. IEEE Trans Syst Man Cybern. 2009;39(1):281\u20138.","journal-title":"IEEE Trans Syst Man Cybern"},{"key":"151_CR41","doi-asserted-by":"crossref","unstructured":"Ahumada H, Grinblat G, Uzal L, Granitto P, Ceccatto A. REPMAC: a new hybrid approach to highly imbalanced classification problems. In: Eighth international conference on hybrid intelligent systems. 2008.","DOI":"10.1109\/HIS.2008.142"},{"issue":"4","key":"151_CR42","doi-asserted-by":"publisher","first-page":"15","DOI":"10.5121\/ijdkp.2013.3402","volume":"3","author":"M Bekkar","year":"2013","unstructured":"Bekkar M, Alitouche T. Imbalanced data learning approaches review. Int J Data Mining Knowl Manag Process. 2013;3(4):15\u201333.","journal-title":"Int J Data Mining Knowl Manag Process"},{"key":"151_CR43","doi-asserted-by":"crossref","unstructured":"Khoshgoftaar TM, Golawala M, Van Hulse J. An empirical study of learning from imbalanced data using random forest. In: 19th IEEE international conference on tools with artificial intelligence (ICTAI 2007), IEEE, vol. 2, pp. 310\u201317. 2007.","DOI":"10.1109\/ICTAI.2007.46"},{"key":"151_CR44","unstructured":"Chen C, Liaw A, Breiman L. Using random forest to learn imbalanced data. Tech Report 666, University of California, Berkeley. 2004."},{"issue":"4","key":"151_CR45","doi-asserted-by":"publisher","first-page":"463","DOI":"10.1109\/TSMCC.2011.2161285","volume":"42","author":"M Galar","year":"2012","unstructured":"Galar M, Fernandez A, Barrenechea E, Bustince H, Herrera F. A review on ensembles for the class imbalance problem: bagging-, boosting-, and hybrid-based approaches. IEEE Trans Syst Man Cybern C Appl Rev. 2012;42(4):463\u201384.","journal-title":"IEEE Trans Syst Man Cybern C Appl Rev"},{"key":"151_CR46","doi-asserted-by":"publisher","first-page":"112","DOI":"10.1016\/j.ins.2014.03.043","volume":"285","author":"S R\u00edo","year":"2014","unstructured":"R\u00edo S, Lopez V, Ben\u00edtez J, Herrera F. On the use of MapReduce for imbalanced Big Data using random forest. Inf Sci. 2014;285:112\u201337.","journal-title":"Inf Sci"},{"key":"151_CR47","unstructured":"The Apache Software Foundation. Apache Mahout. 2017. \n                    http:\/\/mahout.apache.org\/users\/classification\/\n                    \n                  . Accessed Apr 2018."},{"issue":"24","key":"151_CR48","first-page":"1","volume":"2","author":"S Landset","year":"2015","unstructured":"Landset S, Khoshgoftaar TM, Richter A, Hasanin T. A survey of open source tools for machine learning with big data in the Hadoop ecosystem. J Big Data. 2015;2(24):1\u201336.","journal-title":"J Big Data"},{"key":"151_CR49","volume-title":"The WEKA Workbench: data mining: practical machine learning tools and techniques","author":"E Frank","year":"2016","unstructured":"Frank E, Hall MA, Witten IH. The WEKA Workbench: data mining: practical machine learning tools and techniques. 4th ed. Burlington: Morgan Kaufmann; 2016.","edition":"4"},{"key":"151_CR50","unstructured":"Evolutionary computation for Big Data and Big learning workshop data mining competition 2014: self-deployment track. 2014. \n                    http:\/\/cruncher.ico2s.org\/bdcomp\/\n                    \n                  . Accessed 4 Sept 2018."},{"key":"151_CR51","doi-asserted-by":"crossref","unstructured":"Rio S, Benitez J, Herrera F. Analysis of data preprocessing: increasing the oversampling ratio for extremely imbalanced Big Data classification. In: IEEE Trustcom\/BigDataSE\/ISPA. 2015.","DOI":"10.1109\/Trustcom.2015.579"},{"issue":"3","key":"151_CR52","doi-asserted-by":"publisher","first-page":"275","DOI":"10.1162\/evco.2009.17.3.275","volume":"17","author":"S Garc\u0131a","year":"2009","unstructured":"Garc\u0131a S, Herrera F. Evolutionary under-sampling for classification with imbalanced data sets: proposals and taxonomy. Evol Comput. 2009;17(3):275\u2013306.","journal-title":"Evol Comput"},{"key":"151_CR53","doi-asserted-by":"crossref","unstructured":"Triguero I, Galar M, Vluymans S, Cornelis C, Bustince H, Herrera F, Saeys Y. Evolutionary under sampling for imbalanced big data classification. In: IEEE congress on evolutionary computation (CEC), May 2015, pp. 715\u201322.","DOI":"10.1109\/CEC.2015.7256961"},{"issue":"7","key":"151_CR54","doi-asserted-by":"publisher","first-page":"2815","DOI":"10.1007\/s11227-016-1624-z","volume":"72","author":"S Park","year":"2016","unstructured":"Park S, Kim S, Ha Y. Highway traffic accident prediction using VDS big data analysis. J Supercomput. 2016;72(7):2815\u201331.","journal-title":"J Supercomput"},{"key":"151_CR55","first-page":"605","volume":"14","author":"A Ng","year":"2002","unstructured":"Ng A, Jordan M. On discriminative vs. generative classifiers: a comparison of logistic regression and Na\u00efve Bayes. Adv Neural Inf Process Syst. 2002;14:605\u201310.","journal-title":"Adv Neural Inf Process Syst"},{"key":"151_CR56","doi-asserted-by":"crossref","unstructured":"Park S, Ha Y. Large imbalance data classification based on MapReduce for traffic accident prediction. In: Eighth international conference on innovative mobile and internet services in ubiquitous computing. 2014.","DOI":"10.1109\/IMIS.2014.6"},{"issue":"5","key":"151_CR57","doi-asserted-by":"publisher","first-page":"980","DOI":"10.1136\/amiajnl-2012-001409","volume":"20","author":"K Chai","year":"2013","unstructured":"Chai K, Anthony S, Coiera E, Magrabi F. Using statistical text classification to identify health information technology incidents. J Am Med Inform Assoc. 2013;20(5):980\u20135.","journal-title":"J Am Med Inform Assoc"},{"issue":"11","key":"151_CR58","doi-asserted-by":"publisher","first-page":"1322","DOI":"10.14778\/3137628.3137642","volume":"10","author":"NG Marchant","year":"2017","unstructured":"Marchant NG, Rubinstein BIP. In search of an entity resolution OASIS: optimal asymptotic sequential importance sampling. Proc VLDB Endow. 2017;10(11):1322\u201333.","journal-title":"Proc VLDB Endow"},{"issue":"5","key":"151_CR59","doi-asserted-by":"publisher","first-page":"1189","DOI":"10.1214\/aos\/1013203451","volume":"29","author":"J Friedman","year":"2001","unstructured":"Friedman J. Greedy function approximation: a gradient boosting machine. Ann Stat. 2001;29(5):1189\u2013232.","journal-title":"Ann Stat"},{"key":"151_CR60","doi-asserted-by":"crossref","unstructured":"Veeramachaneni K, Arnaldo I, Korrapati V, Bassias C, Li K. AI2: training a Big Data machine to defend. In: IEEE 2nd international conference on Big Data security on cloud. 2016.","DOI":"10.1109\/BigDataSecurity-HPSC-IDS.2016.79"},{"issue":"6841","key":"151_CR61","doi-asserted-by":"publisher","first-page":"1040","DOI":"10.1038\/35082561","volume":"411","author":"A Hirsh","year":"2001","unstructured":"Hirsh A, Fraser H. Protein dispensability and rate of evolution. Nature. 2001;411(6841):1040\u20139.","journal-title":"Nature"},{"issue":"13","key":"151_CR62","doi-asserted-by":"publisher","first-page":"1710","DOI":"10.1093\/bioinformatics\/btg213","volume":"19","author":"D Wall","year":"2003","unstructured":"Wall D, Fraser H, Hirsh A. Detecting putative orthologs. Bioinformatics. 2003;19(13):1710\u20131.","journal-title":"Bioinformatics"},{"key":"151_CR63","doi-asserted-by":"publisher","first-page":"518","DOI":"10.1186\/1471-2105-9-518","volume":"9","author":"A Roth","year":"2008","unstructured":"Roth A, Gonnett G, Dessimoz C. Algorithm of OMA for large-scale orthology inference. BMC Bioinform. 2008;9:518.","journal-title":"BMC Bioinform"},{"issue":"4","key":"151_CR64","doi-asserted-by":"publisher","first-page":"449","DOI":"10.1007\/s11280-012-0178-0","volume":"16","author":"W Wei","year":"2013","unstructured":"Wei W, Li J, Cao L, Ou Y, Chen J. Effective detection of sophisticated online banking fraud on extremely imbalanced data. World Wide Web. 2013;16(4):449\u201375.","journal-title":"World Wide Web"},{"issue":"1","key":"151_CR65","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1016\/j.tcs.2004.12.014","volume":"335","author":"L Wang","year":"2005","unstructured":"Wang L, Zhao H, Dong G, Li J. On the complexity of finding emerging patterns. Theor Comput Sci. 2005;335(1):15\u201327.","journal-title":"Theor Comput Sci"},{"key":"151_CR66","doi-asserted-by":"crossref","unstructured":"Jong D, Li J. Efficient mining of emerging patterns: discovering trends and differences. In: Fifth ACMSIGKDD international conference on knowledge discovery and data mining. 1999. pp. 43\u201352.","DOI":"10.1145\/312129.312191"},{"key":"151_CR67","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1016\/j.patrec.2015.05.008","volume":"62","author":"A D\u2019Addabbo","year":"2015","unstructured":"D\u2019Addabbo A, Maglietta R. Parallel selective sampling method for imbalanced and large data classification. Pattern Recogn Lett. 2015;62:61\u20137.","journal-title":"Pattern Recogn Lett"},{"issue":"11","key":"151_CR68","first-page":"769","volume":"6","author":"I Tomek","year":"1976","unstructured":"Tomek I. Two modifications of CNN. IEEE Trans Syst Man Cybern. 1976;6(11):769\u201372.","journal-title":"IEEE Trans Syst Man Cybern"},{"key":"151_CR69","doi-asserted-by":"publisher","first-page":"332","DOI":"10.1016\/j.neucom.2012.06.009","volume":"97","author":"I Triguero","year":"2012","unstructured":"Triguero I, Derrac J, Garc\u00eda S, Herrera F. Integrating a differential evolution feature weighting scheme into prototype generation. Neurocomputing. 2012;97:332\u201343.","journal-title":"Neurocomputing"},{"issue":"3","key":"151_CR70","doi-asserted-by":"publisher","first-page":"1009","DOI":"10.1007\/s13042-015-0478-7","volume":"8","author":"J Zhai","year":"2017","unstructured":"Zhai J, Zhang S, Wang C. The classification of imbalanced large data sets based on MapReduce and ensemble of ELM classifiers. Int J Mach Learn Cybern. 2017;8(3):1009\u201317.","journal-title":"Int J Mach Learn Cybern"},{"issue":"1\u20133","key":"151_CR71","doi-asserted-by":"publisher","first-page":"489","DOI":"10.1016\/j.neucom.2005.12.126","volume":"70","author":"G Huang","year":"2006","unstructured":"Huang G, Zhu Q, Siew C. Extreme learning machine: theory and applications. Neurocomputing. 2006;70(1\u20133):489\u2013501.","journal-title":"Neurocomputing"},{"key":"151_CR72","doi-asserted-by":"crossref","unstructured":"Hebert J. Predicting rare failure events using classification trees on large scale manufacturing data with complex interactions. In: IEEE international conference on Big data. 2016.","DOI":"10.1109\/BigData.2016.7840825"},{"key":"151_CR73","doi-asserted-by":"crossref","unstructured":"Chen T, Guestrin C. XGBoost: a scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining. 2016. pp. 785\u201394.","DOI":"10.1145\/2939672.2939785"},{"issue":"1","key":"151_CR74","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1109\/TCIAIG.2013.2285651","volume":"6","author":"A Baughman","year":"2014","unstructured":"Baughman A, Chuang W, Dixon K, Benz Z, Basilico J. Deepqa jeopardy! gamification: a machine-learning perspective. IEEE Trans Comput Intell AI Games. 2014;6(1):55\u201366.","journal-title":"IEEE Trans Comput Intell AI Games"},{"issue":"3","key":"151_CR75","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1609\/aimag.v31i3.2303","volume":"31","author":"D Ferrucci","year":"2010","unstructured":"Ferrucci D, Brown E, Chu-Carroll J, Fan J, Gondek D, Kalyanpur A, Lally A, Murdock J, Nyberg E, Prager J, Schlaefer N, Welty C. Building Watson: an overview of the DeepQA project. AI Mag. 2010;31(3):59\u201379.","journal-title":"AI Mag"},{"issue":"4","key":"151_CR76","doi-asserted-by":"publisher","first-page":"687","DOI":"10.1142\/S0218001409007326","volume":"23","author":"Y Sun","year":"2009","unstructured":"Sun Y, Wong A, Kamel M. Classification of imbalanced data: a review. Int J Pattern Recogn Artif Intell. 2009;23(4):687\u2013719.","journal-title":"Int J Pattern Recogn Artif Intell"},{"key":"151_CR77","doi-asserted-by":"publisher","first-page":"7940","DOI":"10.1109\/ACCESS.2016.2619719","volume":"4","author":"A Amin","year":"2016","unstructured":"Amin A, Anwar S, Adnan A, Nawaz M, Howard N, Qadir J, Hawalah A, Hussain A. Comparing oversampling techniques to handle the class imbalance problem: a customer churn prediction case study. IEEE Access. 2016;4:7940\u201357.","journal-title":"IEEE Access"}],"container-title":["Journal of Big Data"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s40537-018-0151-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/s40537-018-0151-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s40537-018-0151-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T05:51:14Z","timestamp":1572587474000},"score":1,"resource":{"primary":{"URL":"https:\/\/journalofbigdata.springeropen.com\/articles\/10.1186\/s40537-018-0151-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,11,1]]},"references-count":77,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2018,12]]}},"alternative-id":["151"],"URL":"https:\/\/doi.org\/10.1186\/s40537-018-0151-6","relation":{},"ISSN":["2196-1115"],"issn-type":[{"value":"2196-1115","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,11,1]]},"assertion":[{"value":"29 August 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 October 2018","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 November 2018","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"42"}}