{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,17]],"date-time":"2026-01-17T19:29:24Z","timestamp":1768678164187,"version":"3.49.0"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2019,6,13]],"date-time":"2019-06-13T00:00:00Z","timestamp":1560384000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2019,6,13]],"date-time":"2019-06-13T00:00:00Z","timestamp":1560384000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Syst Assur Eng Manag"],"published-print":{"date-parts":[[2019,8]]},"DOI":"10.1007\/s13198-019-00817-6","type":"journal-article","created":{"date-parts":[[2019,6,13]],"date-time":"2019-06-13T18:34:36Z","timestamp":1560450876000},"page":"824-835","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Benchmarking framework for class imbalance problem using novel sampling approach for big data"],"prefix":"10.1007","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9132-8401","authenticated-orcid":false,"given":"Khyati","family":"Ahlawat","sequence":"first","affiliation":[]},{"given":"Anuradha","family":"Chug","sequence":"additional","affiliation":[]},{"given":"Amit Prakash","family":"Singh","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,6,13]]},"reference":[{"issue":"3","key":"817_CR1","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1016\/j.bdr.2015.04.001","volume":"2","author":"OY Al-Jarrah","year":"2015","unstructured":"Al-Jarrah OY, Yoo PD, Muhaidat S, Karagiannidis GK, Taha K (2015) Efficient machine learning for big data: a review. Big Data Res 2(3):87\u201393. \n                    https:\/\/doi.org\/10.1016\/j.bdr.2015.04.001","journal-title":"Big Data Res"},{"key":"817_CR2","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1016\/j.ins.2015.10.041","volume":"332","author":"A Bechini","year":"2016","unstructured":"Bechini A, Marcelloni F, Segatori A (2016) A MapReduce solution for associative classification of big data. Inf Sci 332:33\u201355. \n                    https:\/\/doi.org\/10.1016\/j.ins.2015.10.041","journal-title":"Inf Sci"},{"issue":"3","key":"817_CR3","doi-asserted-by":"publisher","first-page":"186","DOI":"10.1504\/IJBDI.2017.10006111","volume":"4","author":"AM Chacko","year":"2017","unstructured":"Chacko AM, Gupta A, Kumar SDM (2017) Improving execution speed of incremental runs of MapReduce using provenance. Int J Big Data Intell 4(3):186\u2013194. \n                    https:\/\/doi.org\/10.1504\/IJBDI.2017.10006111","journal-title":"Int J Big Data Intell"},{"issue":"Sup1","key":"817_CR4","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1080\/18756891.2016.1180820","volume":"9","author":"A Fern\u00e1ndez","year":"2016","unstructured":"Fern\u00e1ndez A, Carmona CJ, Jesus MJ, Herrera F (2016) A view on fuzzy systems for big data: progress and opportunities. Int J Comput Intell Syst 9(Sup1):69\u201380. \n                    https:\/\/doi.org\/10.1080\/18756891.2016.1180820","journal-title":"Int J Comput Intell Syst"},{"key":"817_CR5","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1016\/j.procs.2015.04.108","volume":"48","author":"MR Ghazi","year":"2015","unstructured":"Ghazi MR, Gangodkar D (2015) Hadoop, MapReduce and HDFS: a developers perspective. Procedia Comput Sci 48:45\u201350. \n                    https:\/\/doi.org\/10.1016\/j.procs.2015.04.108","journal-title":"Procedia Comput Sci"},{"key":"817_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.csda.2017.01.005","volume":"111","author":"J Gong","year":"2017","unstructured":"Gong J, Kim H (2017) RHSBoost: improving classification in imbalance data. Comput Stat Data Anal 111:1\u201313. \n                    https:\/\/doi.org\/10.1016\/j.csda.2017.01.005","journal-title":"Comput Stat Data Anal"},{"key":"817_CR7","doi-asserted-by":"publisher","first-page":"327","DOI":"10.1016\/B978-0-12-381479-1.00008-3","volume-title":"Data Mining","author":"Jiawei Han","year":"2012","unstructured":"Han J, Kamber M, Pei J (2012) Classification: basic concepts. In: Elsevier (ed) Data mining concepts and techniques, 3rd ed. Morgan Kaufmann, Waltham, pp 327\u2013383"},{"key":"817_CR8","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1016\/j.fss.2014.01.016","volume":"258","author":"Q He","year":"2015","unstructured":"He Q, Wang H, ZhuangF Shang T, Shi Z (2015) Parallel sampling from big data with uncertainty distribution. Fuzzy Sets Syst 258:117\u2013133. \n                    https:\/\/doi.org\/10.1016\/j.fss.2014.01.016","journal-title":"Fuzzy Sets Syst"},{"key":"817_CR9","doi-asserted-by":"publisher","unstructured":"Hochbaum DS, Baumann P (2014) Sparse computation for large-scale data mining. In: 2014 IEEE international conference on big data. \n                    https:\/\/doi.org\/10.1109\/bigdata.2014.7004252","DOI":"10.1109\/bigdata.2014.7004252"},{"key":"817_CR10","doi-asserted-by":"publisher","first-page":"652","DOI":"10.1109\/access.2014.2332453","volume":"2","author":"H Hu","year":"2014","unstructured":"Hu H, Wen Y, Chua T, Li X (2014) Toward scalable systems for big data analytics: a technology tutorial. IEEE Access 2:652\u2013687. \n                    https:\/\/doi.org\/10.1109\/access.2014.2332453","journal-title":"IEEE Access"},{"key":"817_CR11","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1016\/j.cmpb.2016.04.005","volume":"131","author":"S Kamal","year":"2016","unstructured":"Kamal S, Ripon SH, Dey N, Ashour AS, Santhi V (2016) A MapReduce approach to diminish imbalance parameters for big deoxyribonucleic acid dataset. Comput Methods Programs Biomed 131:191\u2013206. \n                    https:\/\/doi.org\/10.1016\/j.cmpb.2016.04.005","journal-title":"Comput Methods Programs Biomed"},{"key":"817_CR12","doi-asserted-by":"publisher","first-page":"4263","DOI":"10.1109\/tcyb.2016.2606104","volume":"47","author":"Q Kang","year":"2017","unstructured":"Kang Q, Chen X, Li S, Zhou M (2017) A noise-filtered under-sampling scheme for imbalanced classification. IEEE Trans Cybern 47:4263\u20134274. \n                    https:\/\/doi.org\/10.1109\/tcyb.2016.2606104","journal-title":"IEEE Trans Cybern"},{"issue":"4","key":"817_CR13","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1007\/s13748-016-0094-0","volume":"5","author":"B Krawczyk","year":"2016","unstructured":"Krawczyk B (2016) Learning from imbalanced data: open challenges and future directions. Progr Artif Intell 5(4):221\u2013232. \n                    https:\/\/doi.org\/10.1007\/s13748-016-0094-0","journal-title":"Progr Artif Intell"},{"issue":"1","key":"817_CR14","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1186\/s40537-015-0032-1","volume":"2","author":"S Landset","year":"2015","unstructured":"Landset S, Khoshgoftaar TM, Richter AN, Hasanin T (2015) A survey of open source tools for machine learning with big data in the Hadoop ecosystem. J Big Data 2(1):24. \n                    https:\/\/doi.org\/10.1186\/s40537-015-0032-1","journal-title":"J Big Data"},{"key":"817_CR15","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1016\/j.ins.2013.07.007","volume":"250","author":"V L\u00f3pez","year":"2013","unstructured":"L\u00f3pez V, Fern\u00e1ndez A, Garc\u00eda S, Palade V, Herrera F (2013) An insight into classification with imbalanced data: empirical results and current trends on using data intrinsic characteristics. Inf Sci 250:113\u2013141. \n                    https:\/\/doi.org\/10.1016\/j.ins.2013.07.007","journal-title":"Inf Sci"},{"key":"817_CR16","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1016\/j.fss.2014.01.015","volume":"258","author":"V L\u00f3pez","year":"2015","unstructured":"L\u00f3pez V, R\u00edo SD, Ben\u00edtez JM, Herrera F (2015) Cost-sensitive linguistic fuzzy rule based classification systems under the MapReduce framework for imbalanced big data. Fuzzy Sets Syst 258:5\u201338. \n                    https:\/\/doi.org\/10.1016\/j.fss.2014.01.015","journal-title":"Fuzzy Sets Syst"},{"key":"817_CR17","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/j.knosys.2016.06.012","volume":"117","author":"J Maillo","year":"2017","unstructured":"Maillo J, Ram\u00edrez S, Triguero I, Herrera F (2017) KNN-IS: AN Iterative Spark-based design of the k-Nearest Neighbors classifier for big data. Knowl-Based Syst 117:3\u201315. \n                    https:\/\/doi.org\/10.1016\/j.knosys.2016.06.012","journal-title":"Knowl-Based Syst"},{"key":"817_CR18","doi-asserted-by":"publisher","DOI":"10.4018\/ijghpc.2017040105","author":"IHA Meddah","year":"2017","unstructured":"Meddah IHA, Belkadi K (2017) Parallel distributed patterns mining using Hadoop MapReduce framework. Int J Grid High Perform Comput. \n                    https:\/\/doi.org\/10.4018\/ijghpc.2017040105","journal-title":"Int J Grid High Perform Comput"},{"key":"817_CR19","doi-asserted-by":"publisher","first-page":"582","DOI":"10.1016\/j.procs.2015.02.097","volume":"46","author":"R Pandey","year":"2015","unstructured":"Pandey R, Dhoundiyal M (2015) Quantitative evaluation of big data categorical variables through R. Procedia Comput Sci 46:582\u2013588. \n                    https:\/\/doi.org\/10.1016\/j.procs.2015.02.097","journal-title":"Procedia Comput Sci"},{"key":"817_CR20","doi-asserted-by":"publisher","unstructured":"Park S-H, Ha Y-G (2014) Large imbalance data classification based on MapReduce for traffic accident prediction. In: Eighth international conference on innovative mobile and internet services in ubiquitous computing, IEEE, pp 45\u201349 \n                    https:\/\/doi.org\/10.1109\/imis.2014.6","DOI":"10.1109\/imis.2014.6"},{"key":"817_CR21","doi-asserted-by":"publisher","unstructured":"Patil SS, Sonavane SP (2017) Enriched Over_Sampling techniques for improving classification of imbalanced big data. In: Third international conference on big data computing service and applications, IEEE, \n                    https:\/\/doi.org\/10.1109\/bigdataservice.2017.19","DOI":"10.1109\/bigdataservice.2017.19"},{"key":"817_CR22","doi-asserted-by":"publisher","first-page":"112","DOI":"10.1016\/j.ins.2014.03.043","volume":"285","author":"SD R\u00edo","year":"2014","unstructured":"R\u00edo SD, L\u00f3pez V, Ben\u00edtez JM, Herrera F (2014) On the use of MapReduce for imbalanced big data using Random Forest. Inf Sci 285:112\u2013137. \n                    https:\/\/doi.org\/10.1016\/j.ins.2014.03.043","journal-title":"Inf Sci"},{"key":"817_CR23","doi-asserted-by":"publisher","first-page":"422","DOI":"10.1080\/18756891.2015.1017377","volume":"8","author":"SD R\u00edo","year":"2015","unstructured":"R\u00edo SD, L\u00f3pez V, Ben\u00edtez JM, Herrera F (2015) A MapReduce approach to address big data classification problems based on the fusion of linguistic fuzzy rules. Int J Comput Intell Syst 8:422\u2013437. \n                    https:\/\/doi.org\/10.1080\/18756891.2015.1017377","journal-title":"Int J Comput Intell Syst"},{"key":"817_CR24","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1016\/j.imu.2016.01.002","volume":"1","author":"JA Rodger","year":"2015","unstructured":"Rodger JA (2015) Discovery of medical big data analytics: improving the prediction of traumatic brain injury survival rates by data mining Patient Informatics Processing Software Hybrid Hadoop Hive. Inf Med Unlocked 1:17\u201326. \n                    https:\/\/doi.org\/10.1016\/j.imu.2016.01.002","journal-title":"Inf Med Unlocked"},{"issue":"4","key":"817_CR25","doi-asserted-by":"publisher","first-page":"973","DOI":"10.1109\/tfuzz.2014.2336263","volume":"23","author":"JA Sanz","year":"2015","unstructured":"Sanz JA, Bernardo D, Herrera F, Bustince H, Hagras H (2015) A compact evolutionary interval-valued fuzzy rule-based classification system for the modeling and prediction of real-world financial applications with imbalanced data. IEEE Trans Fuzzy Syst 23(4):973\u2013990. \n                    https:\/\/doi.org\/10.1109\/tfuzz.2014.2336263","journal-title":"IEEE Trans Fuzzy Syst"},{"key":"817_CR26","doi-asserted-by":"publisher","first-page":"489","DOI":"10.1007\/s10766-013-0288-z","volume":"43","author":"K Slagter","year":"2015","unstructured":"Slagter K, Hsu C-H, Chung Y-C (2015) An adaptive and memory efficient sampling mechanism for partitioning in MapReduce. Int J Parallel Program 43:489\u2013507. \n                    https:\/\/doi.org\/10.1007\/s10766-013-0288-z","journal-title":"Int J Parallel Program"},{"key":"817_CR27","doi-asserted-by":"publisher","first-page":"331","DOI":"10.1016\/j.neucom.2014.04.078","volume":"150","author":"I Triguero","year":"2015","unstructured":"Triguero I, Peralta D, Bacardit J, Garc\u00eda S, Herrera F (2015a) MRPR: a MapReduce solution for prototype reduction in big data classification. Neurocomputing 150:331\u2013345. \n                    https:\/\/doi.org\/10.1016\/j.neucom.2014.04.078","journal-title":"Neurocomputing"},{"key":"817_CR28","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, R\u00edo SD, L\u00f3pez V, Bacardit J, Ben\u00edtez JM, Herrera F (2015b) ROSEFW-RF: the winner algorithm for the ECBDL\u201914 big data competition: an extremely imbalanced big data bioinformatics problem. Knowl-Based Syst 87:69\u201379. \n                    https:\/\/doi.org\/10.1016\/j.knosys.2015.05.027","journal-title":"Knowl-Based Syst"},{"key":"817_CR29","doi-asserted-by":"publisher","unstructured":"Triguero I, Galar M, Merino D, Maillo J, Bustince H, Herrera F (2016) Evolutionary undersampling for extremely imbalanced big data classification under apache spark. In: IEEE congress on evolutionary computation (CEC). \n                    https:\/\/doi.org\/10.1109\/cec.2016.7743853","DOI":"10.1109\/cec.2016.7743853"},{"key":"817_CR30","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1016\/j.envsoft.2017.11.024","volume":"106","author":"A Troncoso","year":"2018","unstructured":"Troncoso A, Ribera P, Asencio-Cortes G, Vega I, Gallego D (2018) Imbalanced classification techniques for monsoon forecasting based on a new climatic time series. Environ Model Softw 106:48\u201356. \n                    https:\/\/doi.org\/10.1016\/j.envsoft.2017.11.024","journal-title":"Environ Model Softw"},{"key":"817_CR31","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-015-0030-3","author":"CW Tsai","year":"2015","unstructured":"Tsai CW, Lai CF, Chao HC, Vasilakos AV (2015) Big data analytics: a survey. J Big Data. \n                    https:\/\/doi.org\/10.1186\/s40537-015-0030-3","journal-title":"J Big Data"},{"key":"817_CR32","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1016\/j.procs.2015.07.187","volume":"56","author":"R Uskenbayeva","year":"2015","unstructured":"Uskenbayeva R, Kuandykov A, Cho YI, Temirbolatova T, Amanzholova S, Kozhamzharova D (2015) Integrating of data using the Hadoop and R. Procedia Comput Sci 56:145\u2013149. \n                    https:\/\/doi.org\/10.1016\/j.procs.2015.07.187","journal-title":"Procedia Comput Sci"},{"key":"817_CR33","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1016\/j.patcog.2015.12.002","volume":"53","author":"S Vluymans","year":"2016","unstructured":"Vluymans S, Tarrag\u00f3 DS, Saeys Y, Cornelis C, Herrera F (2016) Fuzzy rough classifiers for class imbalanced multi-instance data. Pattern Recogn 53:36\u201345. \n                    https:\/\/doi.org\/10.1016\/j.patcog.2015.12.002","journal-title":"Pattern Recogn"},{"issue":"1","key":"817_CR34","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1109\/TKDE.2013.109","volume":"26","author":"X Wu","year":"2014","unstructured":"Wu X, Zhu X, Wu GQ, Ding W (2014) Data mining with big data. IEEE Trans Knowl Data Eng 26(1):97\u2013107. \n                    https:\/\/doi.org\/10.1109\/TKDE.2013.109","journal-title":"IEEE Trans Knowl Data Eng"},{"issue":"2","key":"817_CR35","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1109\/tbdata.2015.2472014","volume":"1","author":"EP Xing","year":"2015","unstructured":"Xing EP, Ho Q, Dai W, Kim JK, Wei J et al (2015) Petuum: a new platform for distributed machine learning on big data. IEEE Trans Big Data 1(2):49\u201367. \n                    https:\/\/doi.org\/10.1109\/tbdata.2015.2472014","journal-title":"IEEE Trans Big Data"},{"key":"817_CR36","doi-asserted-by":"publisher","first-page":"1186","DOI":"10.4028\/www.scientific.net\/amm","volume":"687\u2013691","author":"X Zhang","year":"2014","unstructured":"Zhang X, Cheng M, Liu Y, Li DH, Wu RM (2014) Short-term load forecasting based on big data technologies. Appl Mech Mater 687\u2013691:1186\u20131192. \n                    https:\/\/doi.org\/10.4028\/www.scientific.net\/amm","journal-title":"Appl Mech Mater"},{"key":"817_CR37","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1016\/j.bdr.2015.12.001","volume":"5","author":"Q Zou","year":"2016","unstructured":"Zou Q, Xie S, Lin Z, Wu M, Ju Y (2016) Finding the best classification threshold in imbalanced classification. Big Data Res 5:2\u20138. \n                    https:\/\/doi.org\/10.1016\/j.bdr.2015.12.001","journal-title":"Big Data Res"}],"container-title":["International Journal of System Assurance Engineering and Management"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s13198-019-00817-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s13198-019-00817-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s13198-019-00817-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,6,11]],"date-time":"2020-06-11T23:42:35Z","timestamp":1591918955000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s13198-019-00817-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,6,13]]},"references-count":37,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2019,8]]}},"alternative-id":["817"],"URL":"https:\/\/doi.org\/10.1007\/s13198-019-00817-6","relation":{},"ISSN":["0975-6809","0976-4348"],"issn-type":[{"value":"0975-6809","type":"print"},{"value":"0976-4348","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,6,13]]},"assertion":[{"value":"9 October 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 April 2019","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 June 2019","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}