{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T16:09:34Z","timestamp":1771258174202,"version":"3.50.1"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2023,1,2]],"date-time":"2023-01-02T00:00:00Z","timestamp":1672617600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,2]],"date-time":"2023-01-02T00:00:00Z","timestamp":1672617600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Pattern Anal Applic"],"published-print":{"date-parts":[[2023,5]]},"DOI":"10.1007\/s10044-022-01129-5","type":"journal-article","created":{"date-parts":[[2023,1,2]],"date-time":"2023-01-02T03:02:32Z","timestamp":1672628552000},"page":"735-749","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Instance hardness and multivariate Gaussian distribution-based oversampling technique for imbalance classification"],"prefix":"10.1007","volume":"26","author":[{"given":"Jie","family":"Xie","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3423-074X","authenticated-orcid":false,"given":"Mingying","family":"Zhu","sequence":"additional","affiliation":[]},{"given":"Kai","family":"Hu","sequence":"additional","affiliation":[]},{"given":"Jinglan","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,1,2]]},"reference":[{"key":"1129_CR1","unstructured":"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. J Multiple-Valued Logic & Soft Comput 17"},{"key":"1129_CR2","doi-asserted-by":"crossref","unstructured":"Arora V, Sun M, Wang C (2019) Deep embeddings for rare audio event detection with imbalanced data. ICASSP 2019\u20132019 IEEE International Conference on Acoustics. Speech and Signal Processing (ICASSP), IEEE, pp 3297\u20133301","DOI":"10.1109\/ICASSP.2019.8682395"},{"key":"1129_CR3","doi-asserted-by":"crossref","unstructured":"Barua S, Islam M, Murase K, et\u00a0al. (2013) Prowsyn: Proximity weighted synthetic oversampling technique for imbalanced data set learning. In: Pacific-Asia Conference on Knowledge Discovery and Data Mining, Springer, pp 317\u2013328","DOI":"10.1007\/978-3-642-37456-2_27"},{"issue":"3\u20134","key":"1129_CR4","doi-asserted-by":"publisher","first-page":"561","DOI":"10.1016\/S0167-9473(02)00163-9","volume":"41","author":"C Biernacki","year":"2003","unstructured":"Biernacki C, Celeux G, Govaert G (2003) Choosing starting values for the em algorithm for getting the highest likelihood in multivariate gaussian mixture models. Comput Statistics & Data Anal 41(3\u20134):561\u2013575","journal-title":"Comput Statistics & Data Anal"},{"issue":"3","key":"1129_CR5","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1016\/S0895-4356(98)00168-1","volume":"52","author":"PD Bridge","year":"1999","unstructured":"Bridge PD, Sawilowsky SS (1999) Increasing physicians\u2019 awareness of the impact of statistics on research outcomes: comparative power of the t-test and wilcoxon rank-sum test in small samples applied research. J Clin Epidemiol 52(3):229\u2013235","journal-title":"J Clin Epidemiol"},{"key":"1129_CR6","doi-asserted-by":"crossref","unstructured":"Bunkhumpornpat C, Sinapiromsaran K, Lursinsap C (2009) Safe-level-smote: Safe-level-synthetic minority over-sampling technique for handling the class imbalanced problem. In: Pacific-Asia conference on knowledge discovery and data mining, Springer, pp 475\u2013482","DOI":"10.1007\/978-3-642-01307-2_43"},{"key":"1129_CR7","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 (2002) Smote: synthetic minority over-sampling technique. J Artificial Intell Res 16:321\u2013357","journal-title":"J Artificial Intell Res"},{"key":"1129_CR8","doi-asserted-by":"publisher","first-page":"397","DOI":"10.1016\/j.ins.2020.10.013","volume":"553","author":"B Chen","year":"2021","unstructured":"Chen B, Xia S, Chen Z, Wang B, Wang G (2021) Rsmote: A self-adaptive robust smote for imbalanced problems with label noise. Inf Sci 553:397\u2013428","journal-title":"Inf Sci"},{"key":"1129_CR9","doi-asserted-by":"crossref","unstructured":"Chongomweru H, Kasem A (2021) A novel ensemble method for classification in imbalanced datasets using split balancing technique based on instance hardness (sbal_ih). Neural Comput Appl pp 1\u201322","DOI":"10.1007\/s00521-020-05570-7"},{"key":"1129_CR10","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1016\/j.ins.2015.07.025","volume":"325","author":"JF D\u00edez-Pastor","year":"2015","unstructured":"D\u00edez-Pastor JF, Rodr\u00edguez JJ, Garc\u00eda-Osorio CI, Kuncheva LI (2015) Diversity techniques improve the performance of the best imbalance learning ensembles. Inf Sci 325:98\u2013117","journal-title":"Inf Sci"},{"key":"1129_CR11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.ins.2018.06.056","volume":"465","author":"G Douzas","year":"2018","unstructured":"Douzas G, Bacao F, Last F (2018) Improving imbalanced learning through a heuristic oversampling method based on k-means and smote. Inf Sci 465:1\u201320","journal-title":"Inf Sci"},{"key":"1129_CR12","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.115230","volume":"183","author":"G Douzas","year":"2021","unstructured":"Douzas G, Rauch R, Bacao F (2021) G-somo: An oversampling approach based on self-organized maps and geometric smote. Exp Syst Appl 183:115230","journal-title":"Exp Syst Appl"},{"key":"1129_CR13","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1016\/j.ins.2019.07.070","volume":"505","author":"D Elreedy","year":"2019","unstructured":"Elreedy D, Atiya AF (2019) A comprehensive analysis of synthetic minority oversampling technique (smote) for handling class imbalance. Inf Sci 505:32\u201364","journal-title":"Inf Sci"},{"key":"1129_CR14","doi-asserted-by":"publisher","first-page":"863","DOI":"10.1613\/jair.1.11192","volume":"61","author":"A Fern\u00e1ndez","year":"2018","unstructured":"Fern\u00e1ndez A, Garcia S, Herrera F, Chawla NV (2018) Smote for learning from imbalanced data: progress and challenges, marking the 15-year anniversary. J Artificial Intell Res 61:863\u2013905","journal-title":"J Artificial Intell Res"},{"issue":"4","key":"1129_CR15","first-page":"42","volume":"2","author":"V Ganganwar","year":"2012","unstructured":"Ganganwar V (2012) An overview of classification algorithms for imbalanced datasets. Int J Emerg Technol Adv Eng 2(4):42\u201347","journal-title":"Int J Emerg Technol Adv Eng"},{"key":"1129_CR16","doi-asserted-by":"crossref","unstructured":"Gazzah S, Amara NEB (2008) New oversampling approaches based on polynomial fitting for imbalanced data sets. In: 2008 the eighth iapr international workshop on document analysis systems, IEEE, pp 677\u2013684","DOI":"10.1109\/DAS.2008.74"},{"key":"1129_CR17","doi-asserted-by":"crossref","unstructured":"Han H, Wang WY, Mao BH (2005) Borderline-smote: a new over-sampling method in imbalanced data sets learning. In: International conference on intelligent computing, Springer, pp 878\u2013887","DOI":"10.1007\/11538059_91"},{"key":"1129_CR18","unstructured":"He H, Bai Y, Garcia EA, Li S (2008) Adasyn: Adaptive synthetic sampling approach for imbalanced learning. In: 2008 IEEE international joint conference on neural networks (IEEE world congress on computational intelligence), IEEE, pp 1322\u20131328"},{"key":"1129_CR19","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2019.105662","volume":"83","author":"G Kov\u00e1cs","year":"2019","unstructured":"Kov\u00e1cs G (2019) An empirical comparison and evaluation of minority oversampling techniques on a large number of imbalanced datasets. Appl Soft Comput 83:105662","journal-title":"Appl Soft Comput"},{"key":"1129_CR20","doi-asserted-by":"publisher","first-page":"714","DOI":"10.1016\/j.asoc.2015.08.060","volume":"38","author":"B Krawczyk","year":"2016","unstructured":"Krawczyk B, Galar M, Jele\u0144 \u0141, Herrera F (2016) Evolutionary undersampling boosting for imbalanced classification of breast cancer malignancy. Appl Soft Comput 38:714\u2013726","journal-title":"Appl Soft Comput"},{"key":"1129_CR21","doi-asserted-by":"crossref","unstructured":"Lee J, Kim Nr, Lee JH (2015) An over-sampling technique with rejection for imbalanced class learning. In: Proceedings of the 9th International Conference on Ubiquitous Information Management and Communication, pp 1\u20136","DOI":"10.1145\/2701126.2701181"},{"key":"1129_CR22","doi-asserted-by":"crossref","unstructured":"Liu Z, Cao W, Gao Z, Bian J, Chen H, Chang Y, Liu TY (2020) Self-paced ensemble for highly imbalanced massive data classification. In: 2020 IEEE 36th International Conference on Data Engineering (ICDE), IEEE, pp 841\u2013852","DOI":"10.1109\/ICDE48307.2020.00078"},{"key":"1129_CR23","doi-asserted-by":"crossref","unstructured":"L\u00f3pez V, Fern\u00e1ndez A, Moreno-Torres JG, Herrera F (2012) Analysis of preprocessing vs. cost-sensitive learning for imbalanced classification. open problems on intrinsic data characteristics. Expert Systems with Applications 39(7):6585\u20136608","DOI":"10.1016\/j.eswa.2011.12.043"},{"issue":"1","key":"1129_CR24","doi-asserted-by":"publisher","first-page":"15","DOI":"10.32604\/cmc.2019.03708","volume":"58","author":"M Luo","year":"2019","unstructured":"Luo M, Wang K, Cai Z, Liu A, Li Y, Cheang CF (2019) Using imbalanced triangle synthetic data for machine learning anomaly detection. Comput, Mater Continua 58(1):15\u201326","journal-title":"Comput, Mater Continua"},{"key":"1129_CR25","unstructured":"Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Blondel M, Prettenhofer P, Weiss R, Dubourg V, et\u00a0al. (2011) Scikit-learn: Machine learning in python. J Mach Learn Res 12:2825\u20132830"},{"key":"1129_CR26","doi-asserted-by":"publisher","first-page":"184","DOI":"10.1016\/j.ins.2014.08.051","volume":"291","author":"JA S\u00e1ez","year":"2015","unstructured":"S\u00e1ez JA, Luengo J, Stefanowski J, Herrera F (2015) Smote-ipf: Addressing the noisy and borderline examples problem in imbalanced classification by a re-sampling method with filtering. Inf Sci 291:184\u2013203","journal-title":"Inf Sci"},{"key":"1129_CR27","doi-asserted-by":"crossref","unstructured":"Sandhan T, Choi JY (2014) Handling imbalanced datasets by partially guided hybrid sampling for pattern recognition. In: 2014 22nd International Conference on Pattern Recognition, IEEE, pp 1449\u20131453","DOI":"10.1109\/ICPR.2014.258"},{"key":"1129_CR28","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1016\/j.ins.2020.07.014","volume":"542","author":"P Soltanzadeh","year":"2021","unstructured":"Soltanzadeh P, Hashemzadeh M (2021) Rcsmote: range-controlled synthetic minority over-sampling technique for handling the class imbalance problem. Inf Sci 542:92\u2013111","journal-title":"Inf Sci"},{"key":"1129_CR29","unstructured":"Wang S, Li Z, Chao W, Cao Q (2012) Applying adaptive over-sampling technique based on data density and cost-sensitive svm to imbalanced learning. In: The 2012 international joint conference on neural networks (IJCNN), IEEE, pp 1\u20138"},{"key":"1129_CR30","doi-asserted-by":"publisher","first-page":"200","DOI":"10.1016\/j.neucom.2020.05.030","volume":"422","author":"X Wang","year":"2021","unstructured":"Wang X, Xu J, Zeng T, Jing L (2021) Local distribution-based adaptive minority oversampling for imbalanced data classification. Neurocomputing 422:200\u2013213","journal-title":"Neurocomputing"},{"issue":"3","key":"1129_CR31","doi-asserted-by":"publisher","first-page":"119","DOI":"10.2307\/3001946","volume":"3","author":"F Wilcoxon","year":"1947","unstructured":"Wilcoxon F (1947) Probability tables for individual comparisons by ranking methods. Biometrics 3(3):119\u2013122","journal-title":"Biometrics"},{"key":"1129_CR32","unstructured":"Xie Y, Qiu M, Zhang H, Peng L, Chen Z (2020) Gaussian distribution based oversampling for imbalanced data classification. IEEE Transactions on Knowledge and Data Engineering pp 1\u20131, 10.1109\/TKDE.2020.2985965"},{"key":"1129_CR33","doi-asserted-by":"crossref","unstructured":"Zhou H, Dong X, Xia S, Wang G (2021) Weighted oversampling algorithms for imbalanced problems and application in prediction of streamflow. Knowledge-Based Systems p 107306","DOI":"10.1016\/j.knosys.2021.107306"}],"container-title":["Pattern Analysis and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10044-022-01129-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10044-022-01129-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10044-022-01129-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,15]],"date-time":"2023-04-15T04:39:23Z","timestamp":1681533563000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10044-022-01129-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,2]]},"references-count":33,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2023,5]]}},"alternative-id":["1129"],"URL":"https:\/\/doi.org\/10.1007\/s10044-022-01129-5","relation":{},"ISSN":["1433-7541","1433-755X"],"issn-type":[{"value":"1433-7541","type":"print"},{"value":"1433-755X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1,2]]},"assertion":[{"value":"7 November 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 November 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 January 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}