{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T13:49:51Z","timestamp":1775051391842,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":36,"publisher":"ACM","license":[{"start":{"date-parts":[[2018,1,4]],"date-time":"2018-01-04T00:00:00Z","timestamp":1515024000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2018,1,4]]},"DOI":"10.1145\/3170521.3170535","type":"proceedings-article","created":{"date-parts":[[2018,3,23]],"date-time":"2018-03-23T12:30:47Z","timestamp":1521808247000},"page":"1-6","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":12,"title":["Imbalanced big data classification"],"prefix":"10.1145","author":[{"given":"Avnish Kumar","family":"Rastogi","sequence":"first","affiliation":[{"name":"HCL Technologies, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nitin","family":"Narang","sequence":"additional","affiliation":[{"name":"HCL Technologies, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zamir Ahmad","family":"Siddiqui","sequence":"additional","affiliation":[{"name":"HCL Technologies, India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2018,1,4]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.5555\/1622407.1622416"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Yu H Hong S Yang X Ni J Dan Y Qin B. 2013. Recognition of multiple imbalanced cancer types based on DNA microarray data using ensemble classifiers. BioMed Research International 1--13.  Yu H Hong S Yang X Ni J Dan Y Qin B. 2013. Recognition of multiple imbalanced cancer types based on DNA microarray data using ensemble classifiers. BioMed Research International 1--13.","DOI":"10.1155\/2013\/239628"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2014.08.002"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2008.239"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1142\/S0218001409007326"},{"issue":"20","key":"e_1_3_2_1_6_1","first-page":"113","article-title":"An insight into classification with imbalanced data: empirical results and current trends on using data intrinsic characteristics","volume":"250","author":"Fern\u00e1ndez A.","year":"2017","unstructured":"Fern\u00e1ndez , A. , Chawla , Nitesh, Garc\u00eda , S. , Palade , V. , Herrera , F. 2017 An insight into classification with imbalanced data: empirical results and current trends on using data intrinsic characteristics . Complex and Intelligent Systems 250 ( 20 ), 113 -- 141 . Fern\u00e1ndez, A., Chawla, Nitesh, Garc\u00eda, S., Palade, V., Herrera, F. 2017 An insight into classification with imbalanced data: empirical results and current trends on using data intrinsic characteristics. Complex and Intelligent Systems 250(20), 113--141.","journal-title":"Complex and Intelligent Systems"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/1007730.1007735"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2014.2371472"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/312129.312220"},{"key":"e_1_3_2_1_10_1","volume-title":"3D data management: Controlling data volume, velocity, and variety. Tech. rep","author":"Laney","unstructured":"D. Laney . 2001. 3D data management: Controlling data volume, velocity, and variety. Tech. rep ., META Group . D. Laney. 2001. 3D data management: Controlling data volume, velocity, and variety. Tech. rep., META Group."},{"key":"e_1_3_2_1_11_1","unstructured":"Apache Spark https:\/\/spark.apache.org\/docs\/latest\/index.html.  Apache Spark https:\/\/spark.apache.org\/docs\/latest\/index.html."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","unstructured":"Prati R.C. G.E. Batista and M.C. Monard. 2004. Learning with class skews and small disjuncts Advances in Artificial Intelligence-SBIA Springer 296--306.  Prati R.C. G.E. Batista and M.C. Monard. 2004. Learning with class skews and small disjuncts Advances in Artificial Intelligence-SBIA Springer 296--306.","DOI":"10.1007\/978-3-540-28645-5_30"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/1007730.1007737"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2012.09.003"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1162\/evco.2009.17.3.275"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2016.04.005"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.12733\/jics20104484"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/602259.602266"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/98524.98564"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.14778\/2336664.2336674"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.14778\/2180912.2180915"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/276698.276876"},{"key":"e_1_3_2_1_23_1","volume-title":"Mining of Massive Datasets","author":"Rajaraman","unstructured":"Rajaraman , Jure Leskovec, Jeffrey D. Ullman . 2014. Mining of Massive Datasets . Cambridge University Press . Rajaraman, Jure Leskovec, Jeffrey D. Ullman. 2014. Mining of Massive Datasets. Cambridge University Press."},{"key":"e_1_3_2_1_24_1","volume-title":"Locality-Sensitive Hashing for Finding Nearest Neighbors","author":"Slaney M.","unstructured":"Slaney , M. , Casey , M. , 2008. Locality-Sensitive Hashing for Finding Nearest Neighbors . IEEE Signal Processing Machine . 129--131. Slaney, M., Casey, M., 2008. Locality-Sensitive Hashing for Finding Nearest Neighbors. IEEE Signal Processing Machine. 129--131."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.14778\/2556549.2556574"},{"key":"e_1_3_2_1_26_1","volume-title":"Proceedings of the 33rd VLDB, 950--961","author":"Liv Q","year":"2007","unstructured":"Liv , Q , Josephson , W. , Wang , Z. , Charikar , M. , Li , K. 2007 . Multi Probe LSH: Efficient Indexing for High Dimensional Similarity Search . Proceedings of the 33rd VLDB, 950--961 . Liv, Q, Josephson, W., Wang, Z., Charikar, M., Li, K. 2007. Multi Probe LSH: Efficient Indexing for High Dimensional Similarity Search. Proceedings of the 33rd VLDB, 950--961."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/997817.997857"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2005.50"},{"key":"e_1_3_2_1_29_1","unstructured":"ECBDL'14 dataset. http:\/\/cruncher.ncl.ac.uk\/bdcomp\/  ECBDL'14 dataset. http:\/\/cruncher.ncl.ac.uk\/bdcomp\/"},{"key":"e_1_3_2_1_30_1","unstructured":"Scikit Learn. http:\/\/contrib.scikit-learn.org\/imbalanced-learn\/stable\/generated\/imblearn.over_sampling.SMOTE.html.  Scikit Learn. http:\/\/contrib.scikit-learn.org\/imbalanced-learn\/stable\/generated\/imblearn.over_sampling.SMOTE.html."},{"key":"e_1_3_2_1_31_1","first-page":"2","article-title":"KEEL Data-Mining Software Tool: Data Set Repository, Integration of Algorithms and Experimental Analysis Framework","volume":"17","author":"Alcal\u00e1-Fdez A.","year":"2011","unstructured":"J. Alcal\u00e1-Fdez , A. Fernandez , J. Luengo , J. Derrac , S. Garc\u00eda , L. S\u00e1nchez , F. Herrera . 2011 . KEEL Data-Mining Software Tool: Data Set Repository, Integration of Algorithms and Experimental Analysis Framework . Journal of Multiple-Valued Logic and Soft Computing 17 : 2 - 3 , 255--287. J. Alcal\u00e1-Fdez, A. Fernandez, J. Luengo, J. Derrac, S. Garc\u00eda, L. S\u00e1nchez, F. Herrera. 2011. KEEL Data-Mining Software Tool: Data Set Repository, Integration of Algorithms and Experimental Analysis Framework. Journal of Multiple-Valued Logic and Soft Computing 17:2-3, 255--287.","journal-title":"Journal of Multiple-Valued Logic and Soft Computing"},{"key":"e_1_3_2_1_32_1","unstructured":"Abalone dataset http:\/\/sci2s.ugr.es\/keel\/dataset.php?cod=115.  Abalone dataset http:\/\/sci2s.ugr.es\/keel\/dataset.php?cod=115."},{"key":"e_1_3_2_1_33_1","unstructured":"Yeast dataset http:\/\/sci2s.ugr.es\/keel\/dataset.php?cod=133.  Yeast dataset http:\/\/sci2s.ugr.es\/keel\/dataset.php?cod=133."},{"key":"e_1_3_2_1_34_1","unstructured":"H2o https:\/\/www.h2o.ai.  H2o https:\/\/www.h2o.ai."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"crossref","unstructured":"Krawczyk Bartosz. 2016. Learning from imbalanced data:Open challenges and future directions. Progress in Artificial Intelligence. Vol 5 Issue 4 221--232.  Krawczyk Bartosz. 2016. Learning from imbalanced data:Open challenges and future directions. Progress in Artificial Intelligence. Vol 5 Issue 4 221--232.","DOI":"10.1007\/s13748-016-0094-0"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/11538059_91"}],"event":{"name":"Workshops ICDCN 2018: Workshops co-located with the International Conference on Distributed Computing and Networks 2018","location":"Varanasi India","acronym":"Workshops ICDCN 2018"},"container-title":["Proceedings of the Workshop Program of the 19th International Conference on Distributed Computing and Networking"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3170521.3170535","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3170521.3170535","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T02:26:58Z","timestamp":1750213618000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3170521.3170535"}},"subtitle":["a distributed implementation of SMOTE"],"short-title":[],"issued":{"date-parts":[[2018,1,4]]},"references-count":36,"alternative-id":["10.1145\/3170521.3170535","10.1145\/3170521"],"URL":"https:\/\/doi.org\/10.1145\/3170521.3170535","relation":{},"subject":[],"published":{"date-parts":[[2018,1,4]]},"assertion":[{"value":"2018-01-04","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}