{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T21:26:43Z","timestamp":1730323603448,"version":"3.28.0"},"publisher-location":"New York, NY, USA","reference-count":35,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,1,2]]},"DOI":"10.1145\/3430984.3431029","type":"proceedings-article","created":{"date-parts":[[2020,12,28]],"date-time":"2020-12-28T05:34:44Z","timestamp":1609133684000},"page":"198-202","update-policy":"http:\/\/dx.doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Aided Selection of Sampling Methods for Imbalanced Data Classification"],"prefix":"10.1145","author":[{"given":"Deep","family":"Sahni","sequence":"first","affiliation":[{"name":"Department of Ocean Engineering IIT Madras, India"}]},{"given":"Satya Jayadev","family":"Pappu","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering Robert Bosch Centre for Data Science and AI (RBCDSAI) IIT Madras, India"}]},{"given":"Nirav","family":"Bhatt","sequence":"additional","affiliation":[{"name":"Department of Biotechnology Robert Bosch Centre for Data Science and AI (RBCDSAI) IIT Madras, India"}]}],"member":"320","published-online":{"date-parts":[[2021,1,2]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.5555\/1953048.2078195"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.5555\/3122009.3122026"},{"key":"e_1_3_2_1_3_1","article-title":"Keel data-mining software tool: data set repository, integration of algorithms and experimental analysis framework","author":"Alcal\u00e1-Fdez J.","year":"2011","unstructured":"[ 3 ] Alcal\u00e1-Fdez , J. , Fern\u00e1ndez , A. , Luengo , J. , Derrac , J. , Garc\u00eda , S. , S\u00e1nchez , L. , & Herrera , F. ( 2011 ). Keel data-mining software tool: data set repository, integration of algorithms and experimental analysis framework . Journal of Multiple-Valued Logic & Soft Computing, 17. [3] Alcal\u00e1-Fdez, J., Fern\u00e1ndez, A., Luengo, J., Derrac, J., Garc\u00eda, S., S\u00e1nchez, L., & Herrera, F. (2011). Keel data-mining software tool: data set repository, integration of algorithms and experimental analysis framework. Journal of Multiple-Valued Logic & Soft Computing, 17.","journal-title":"Journal of Multiple-Valued Logic & Soft Computing, 17."},{"key":"e_1_3_2_1_4_1","volume-title":"Complexity measures of supervised classification problems","author":"Ho T. K.","year":"2002","unstructured":"[ 4 ] Ho , T. K. , & Basu , M. ( 2002 ). Complexity measures of supervised classification problems . IEEE transactions on pattern analysis and machine intelligence, 24(3), 289-300. [4] Ho, T. K., & Basu, M. (2002). Complexity measures of supervised classification problems. IEEE transactions on pattern analysis and machine intelligence, 24(3), 289-300."},{"key":"e_1_3_2_1_5_1","volume-title":"Joint IAPR International Workshops on Statistical Techniques in Pattern Recognition (SPR) and Structural and Syntactic Pattern Recognition (SSPR) (pp. 707-715)","author":"Fr\u00e9licot C.","year":"1998","unstructured":"[ 5 ] Fr\u00e9licot , C. , & Emptoz , H. ( 1998 , August). A pretopological approach for pattern classification with reject options . In Joint IAPR International Workshops on Statistical Techniques in Pattern Recognition (SPR) and Structural and Syntactic Pattern Recognition (SSPR) (pp. 707-715) . Springer, Berlin, Heidelberg. [5] Fr\u00e9licot, C., & Emptoz, H. (1998, August). A pretopological approach for pattern classification with reject options. In Joint IAPR International Workshops on Statistical Techniques in Pattern Recognition (SPR) and Structural and Syntactic Pattern Recognition (SSPR) (pp. 707-715). Springer, Berlin, Heidelberg."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.953"},{"key":"e_1_3_2_1_7_1","first-page":"1322","volume-title":"ADASYN: Adaptive synthetic sampling approach for imbalanced learning. In 2008 IEEE international joint conference on neural networks","author":"He H.","unstructured":"[ 7 ] He , H. , Bai , Y. , Garcia , E. A. , & Li , S. (2008, June ). ADASYN: Adaptive synthetic sampling approach for imbalanced learning. In 2008 IEEE international joint conference on neural networks (IEEE world congress on computational intelligence) (pp. 1322 - 1328 ). IEEE. [7] He, H., Bai, Y., Garcia, E. A., & Li, S. (2008, June). ADASYN: Adaptive synthetic sampling approach for imbalanced learning. In 2008 IEEE international joint conference on neural networks (IEEE world congress on computational intelligence) (pp. 1322-1328). IEEE."},{"key":"e_1_3_2_1_8_1","volume-title":"International conference on intelligent computing (pp. 878-887)","author":"Han H.","year":"2005","unstructured":"[ 8 ] Han , H. , Wang , W. Y. , & Mao , B. H. ( 2005 , August). Borderline-SMOTE: a new over-sampling method in imbalanced data sets learning . In International conference on intelligent computing (pp. 878-887) . Springer, Berlin, Heidelberg. [8] Han, H., Wang, W. Y., & Mao, B. H. (2005, August). Borderline-SMOTE: a new over-sampling method in imbalanced data sets learning. In International conference on intelligent computing (pp. 878-887). Springer, Berlin, Heidelberg."},{"key":"e_1_3_2_1_9_1","first-page":"24","volume-title":"Proceedings: Fifth International Workshop on Computational Intelligence & Applications (Vol.","author":"Nguyen H. M.","year":"2009","unstructured":"[ 9 ] Nguyen , H. M. , Cooper , E. W. , & Kamei , K. ( 2009 , November). Borderline over-sampling for imbalanced data classification . In Proceedings: Fifth International Workshop on Computational Intelligence & Applications (Vol. 2009, No. 1, pp. 24 - 29 ). IEEE SMC Hiroshima Chapter. [9] Nguyen, H. M., Cooper, E. W., & Kamei, K. (2009, November). Borderline over-sampling for imbalanced data classification. In Proceedings: Fifth International Workshop on Computational Intelligence & Applications (Vol. 2009, No. 1, pp. 24-29). IEEE SMC Hiroshima Chapter."},{"key":"e_1_3_2_1_10_1","volume-title":"Proceedings of workshop on learning from imbalanced datasets (Vol. 126)","author":"Mani I.","year":"2003","unstructured":"[ 10 ] Mani , I. , & Zhang , I. ( 2003 , August). kNN approach to unbalanced data distributions: a case study involving information extraction . In Proceedings of workshop on learning from imbalanced datasets (Vol. 126) . [10] Mani, I., & Zhang, I. (2003, August). kNN approach to unbalanced data distributions: a case study involving information extraction. In Proceedings of workshop on learning from imbalanced datasets (Vol. 126)."},{"key":"e_1_3_2_1_11_1","first-page":"769","article-title":"Two modifications of CNN","volume":"6","author":"Tomek I.","year":"1976","unstructured":"[ 11 ] Tomek , I. ( 1976 ). Two modifications of CNN . IEEE Transactions on Systems, Man, and Cybernetics(vol. 6 , pp. 769 - 772 ) [11] Tomek, I. (1976). Two modifications of CNN. IEEE Transactions on Systems, Man, and Cybernetics(vol. 6, pp. 769-772)","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics(vol."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1972.4309137"},{"key":"e_1_3_2_1_13_1","volume-title":"An experiment with the edited nearest-neighbor rule","author":"Tomek I.","year":"1976","unstructured":"[ 13 ] Tomek , I. An experiment with the edited nearest-neighbor rule . IEEE Transactions on Systems, Man, and Cybernetics , vol. 6(6), pp. 448- 452 , 1976 . [13] Tomek, I. An experiment with the edited nearest-neighbor rule. IEEE Transactions on Systems, Man, and Cybernetics, vol. 6(6), pp. 448-452, 1976."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1968.1054155"},{"key":"e_1_3_2_1_15_1","first-page":"179","volume-title":"ICML (Vol. 97","author":"Kubat M.","year":"1997","unstructured":"[ 15 ] Kubat , M. , & Matwin , S. ( 1997 , July). Addressing the curse of imbalanced training sets: one-sided selection . In ICML (Vol. 97 , pp. 179 - 186 ). [15] Kubat, M., & Matwin, S. (1997, July). Addressing the curse of imbalanced training sets: one-sided selection. In ICML (Vol. 97, pp. 179-186)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-48229-6_9"},{"key":"e_1_3_2_1_17_1","volume-title":"An instance level analysis of data complexity. Machine learning, 95(2), 225-256","author":"Smith M. R.","year":"2014","unstructured":"[ 17 ] Smith , M. R. , Martinez , T. , & Giraud-Carrier , C. ( 2014 ). An instance level analysis of data complexity. Machine learning, 95(2), 225-256 . [17] Smith, M. R., Martinez, T., & Giraud-Carrier, C. (2014). An instance level analysis of data complexity. Machine learning, 95(2), 225-256."},{"key":"e_1_3_2_1_18_1","volume-title":"A study of the behavior of several methods for balancing machine learning training data. ACM SIGKDD explorations newsletter, 6(1), 20-29","author":"Batista G. E.","year":"2004","unstructured":"[ 18 ] Batista , G. E. , Prati , R. C. , & Monard , M. C. ( 2004 ). A study of the behavior of several methods for balancing machine learning training data. ACM SIGKDD explorations newsletter, 6(1), 20-29 . [18] Batista, G. E., Prati, R. C., & Monard, M. C. (2004). A study of the behavior of several methods for balancing machine learning training data. ACM SIGKDD explorations newsletter, 6(1), 20-29."},{"key":"e_1_3_2_1_19_1","unstructured":"[\n 19\n ] Batista G. E. Bazzan A. L. & Monard M. C. (2003 December). Balancing Training Data for Automated Annotation of Keywords: a Case Study. In WOB (pp. 10-18). [19] Batista G. E. Bazzan A. L. & Monard M. C. (2003 December). Balancing Training Data for Automated Annotation of Keywords: a Case Study. In WOB (pp. 10-18)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2008.239"},{"key":"e_1_3_2_1_21_1","volume-title":"A study of the behavior of several methods for balancing machine learning training data. ACM SIGKDD explorations newsletter, 6(1), 20-29","author":"Batista G. E.","year":"2004","unstructured":"[ 21 ] Batista , G. E. , Prati , R. C. , & Monard , M. C. ( 2004 ). A study of the behavior of several methods for balancing machine learning training data. ACM SIGKDD explorations newsletter, 6(1), 20-29 . [21] Batista, G. E., Prati, R. C., & Monard, M. C. (2004). A study of the behavior of several methods for balancing machine learning training data. ACM SIGKDD explorations newsletter, 6(1), 20-29."},{"key":"e_1_3_2_1_22_1","volume-title":"Special issue on learning from imbalanced data sets. ACM SIGKDD explorations newsletter, 6(1), 1-6","author":"Chawla N. V.","year":"2004","unstructured":"[ 22 ] Chawla , N. V. , Japkowicz , N. , & Kotcz , A. ( 2004 ). Special issue on learning from imbalanced data sets. ACM SIGKDD explorations newsletter, 6(1), 1-6 . [22] Chawla, N. V., Japkowicz, N., & Kotcz, A. (2004). Special issue on learning from imbalanced data sets. ACM SIGKDD explorations newsletter, 6(1), 1-6."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/34.809107"},{"key":"e_1_3_2_1_24_1","volume-title":"18th Annual Symposium of the Pattern Recognition Association of South Africa (PRASA).","author":"Van der Walt C. M.","year":"2007","unstructured":"[ 24 ] Van der Walt , C. M. , & Barnard , E. ( 2007 ). Measures for the characterisation of pattern-recognition data sets . 18th Annual Symposium of the Pattern Recognition Association of South Africa (PRASA). [24] Van der Walt, C. M., & Barnard, E. (2007). Measures for the characterisation of pattern-recognition data sets. 18th Annual Symposium of the Pattern Recognition Association of South Africa (PRASA)."},{"key":"e_1_3_2_1_25_1","volume-title":"Complexity measures of supervised classification problems","author":"Ho T. K.","year":"2002","unstructured":"[ 25 ] Ho , T. K. , & Basu , M. ( 2002 ). Complexity measures of supervised classification problems . IEEE transactions on pattern analysis and machine intelligence, 24(3), 289-300. [25] Ho, T. K., & Basu, M. (2002). Complexity measures of supervised classification problems. IEEE transactions on pattern analysis and machine intelligence, 24(3), 289-300."},{"key":"e_1_3_2_1_27_1","volume-title":"An insight into classification with imbalanced data: Empirical results and current trends on using data intrinsic characteristics. Information sciences, 250, 113-141","author":"L\u00f3pez V.","year":"2013","unstructured":"[ 27 ] 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. Information sciences, 250, 113-141 . [27] 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. Information sciences, 250, 113-141."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00500-010-0625-8"},{"key":"e_1_3_2_1_29_1","volume-title":"Statistical pattern recognition","author":"Webb A. R.","year":"2003","unstructured":"[ 29 ] Webb , A. R. ( 2003 ). Statistical pattern recognition . John Wiley & Sons . [29] Webb, A. R. (2003). Statistical pattern recognition. John Wiley & Sons."},{"key":"e_1_3_2_1_30_1","volume-title":"A study of the behavior of several methods for balancing machine learning training data. ACM SIGKDD explorations newsletter, 6(1), 20-29","author":"Batista G. E.","year":"2004","unstructured":"[ 30 ] Batista , G. E. , Prati , R. C. , & Monard , M. C. ( 2004 ). A study of the behavior of several methods for balancing machine learning training data. ACM SIGKDD explorations newsletter, 6(1), 20-29 . [30] Batista, G. E., Prati, R. C., & Monard, M. C. (2004). A study of the behavior of several methods for balancing machine learning training data. ACM SIGKDD explorations newsletter, 6(1), 20-29."},{"key":"e_1_3_2_1_31_1","volume-title":"Cross-validation for imbalanced datasets: Avoiding overoptimistic and overfitting approaches [research frontier]","author":"Santos M. S.","year":"2018","unstructured":"[ 31 ] Santos , M. S. , Soares , J. P. , Abreu , P. H. , Araujo , H. , & Santos , J. ( 2018 ). Cross-validation for imbalanced datasets: Avoiding overoptimistic and overfitting approaches [research frontier] . IEEE Computational Intelligence magazine, 13(4), 59-76. [31] Santos, M. S., Soares, J. P., Abreu, P. H., Araujo, H., & Santos, J. (2018). Cross-validation for imbalanced datasets: Avoiding overoptimistic and overfitting approaches [research frontier]. IEEE Computational Intelligence magazine, 13(4), 59-76."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143874"},{"key":"e_1_3_2_1_33_1","volume-title":"Joint IAPR international workshops on statistical techniques in pattern recognition (SPR) and structural and syntactic pattern recognition (SSPR) (pp. 806-814)","author":"Barandela R.","year":"2004","unstructured":"[ 33 ] Barandela , R. , Valdovinos , R. M. , S\u00e1nchez , J. S. , & Ferri , F. J. ( 2004 , August). The imbalanced training sample problem: Under or over sampling? . In Joint IAPR international workshops on statistical techniques in pattern recognition (SPR) and structural and syntactic pattern recognition (SSPR) (pp. 806-814) . Springer, Berlin, Heidelberg. [33] Barandela, R., Valdovinos, R. M., S\u00e1nchez, J. S., & Ferri, F. J. (2004, August). The imbalanced training sample problem: Under or over sampling?. In Joint IAPR international workshops on statistical techniques in pattern recognition (SPR) and structural and syntactic pattern recognition (SSPR) (pp. 806-814). Springer, Berlin, Heidelberg."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.5555\/559152"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2008.06.108"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.5555\/1314498.1314514"}],"event":{"name":"CODS COMAD 2021: 8th ACM IKDD CODS and 26th COMAD","acronym":"CODS COMAD 2021","location":"Bangalore India"},"container-title":["Proceedings of the 3rd ACM India Joint International Conference on Data Science & Management of Data (8th ACM IKDD CODS & 26th COMAD)"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3430984.3431029","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,13]],"date-time":"2023-01-13T18:46:51Z","timestamp":1673635611000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3430984.3431029"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,2]]},"references-count":35,"alternative-id":["10.1145\/3430984.3431029","10.1145\/3430984"],"URL":"https:\/\/doi.org\/10.1145\/3430984.3431029","relation":{},"subject":[],"published":{"date-parts":[[2021,1,2]]},"assertion":[{"value":"2021-01-02","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}