{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T03:32:14Z","timestamp":1777347134010,"version":"3.51.4"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2023,5,13]],"date-time":"2023-05-13T00:00:00Z","timestamp":1683936000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,5,13]],"date-time":"2023-05-13T00:00:00Z","timestamp":1683936000000},"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":["Knowl Inf Syst"],"published-print":{"date-parts":[[2023,10]]},"DOI":"10.1007\/s10115-023-01881-y","type":"journal-article","created":{"date-parts":[[2023,5,15]],"date-time":"2023-05-15T12:04:56Z","timestamp":1684152296000},"page":"4157-4183","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Imbalance factor: a simple new scale for measuring inter-class imbalance extent in classification problems"],"prefix":"10.1007","volume":"65","author":[{"given":"Mohsen","family":"Pirizadeh","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8067-0383","authenticated-orcid":false,"given":"Hadi","family":"Farahani","sequence":"additional","affiliation":[]},{"given":"Saeed Reza","family":"Kheradpisheh","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,5,13]]},"reference":[{"issue":"6","key":"1881_CR1","doi-asserted-by":"publisher","first-page":"1429","DOI":"10.1007\/s10115-021-01560-w","volume":"63","author":"D Brzezinski","year":"2021","unstructured":"Brzezinski D, Minku LL, Pewinski T, Stefanowski J, Szumaczuk A (2021) The impact of data difficulty factors on classification of imbalanced and concept drifting data streams. Knowl Inf Syst 63(6):1429\u20131469","journal-title":"Knowl Inf Syst"},{"key":"1881_CR2","doi-asserted-by":"crossref","unstructured":"Japkowicz N (2001) Concept-learning in the presence of between-class and within-class imbalances. In: Conference of the Canadian society for computational studies of intelligence. Springer, pp 67\u201377","DOI":"10.1007\/3-540-45153-6_7"},{"key":"1881_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108114","volume":"120","author":"M Koziarski","year":"2021","unstructured":"Koziarski M (2021) Potential anchoring for imbalanced data classification. Pattern Recognit 120:108114","journal-title":"Pattern Recognit"},{"issue":"4","key":"1881_CR4","doi-asserted-by":"publisher","first-page":"1119","DOI":"10.1109\/TSMCB.2012.2187280","volume":"42","author":"S Wang","year":"2012","unstructured":"Wang S, Yao X (2012) Multiclass imbalance problems: analysis and potential solutions. IEEE Trans Syst Man Cybern B Cybern 42(4):1119\u20131130","journal-title":"IEEE Trans Syst Man Cybern B Cybern"},{"issue":"2","key":"1881_CR5","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1007\/s10994-020-05913-4","volume":"110","author":"S Bej","year":"2021","unstructured":"Bej S, Davtyan N, Wolfien M, Nassar M, Wolkenhauer O (2021) LoRAS: an oversampling approach for imbalanced datasets. Mach Learn 110(2):279\u2013301","journal-title":"Mach Learn"},{"issue":"3","key":"1881_CR6","doi-asserted-by":"publisher","first-page":"605","DOI":"10.1007\/s10994-017-5670-4","volume":"107","author":"C Bellinger","year":"2018","unstructured":"Bellinger C, Drummond C, Japkowicz N (2018) Manifold-based synthetic oversampling with manifold conformance estimation. Mach Learn 107(3):605\u2013637","journal-title":"Mach Learn"},{"issue":"3","key":"1881_CR7","doi-asserted-by":"publisher","first-page":"841","DOI":"10.1007\/s10115-019-01380-z","volume":"62","author":"C Bellinger","year":"2020","unstructured":"Bellinger C, Sharma S, Japkowicz N, Za\u00efane OR (2020) Framework for extreme imbalance classification: SWIM\u2014sampling with the majority class. Knowl Inf Syst 62(3):841\u2013866","journal-title":"Knowl Inf Syst"},{"key":"1881_CR8","doi-asserted-by":"publisher","first-page":"220","DOI":"10.1016\/j.eswa.2016.12.035","volume":"73","author":"G Haixiang","year":"2017","unstructured":"Haixiang G, Yijing L, Shang J, Mingyun G, Yuanyue H, Bing G (2017) Learning from class-imbalanced data: review of methods and applications. Expert Syst Appl 73:220\u2013239","journal-title":"Expert Syst Appl"},{"issue":"11","key":"1881_CR9","doi-asserted-by":"publisher","first-page":"3059","DOI":"10.1007\/s10994-021-06012-8","volume":"110","author":"M Koziarski","year":"2021","unstructured":"Koziarski M, Bellinger C, Wo\u017aniak M (2021) RB-CCR: radial-based combined cleaning and resampling algorithm for imbalanced data classification. Mach Learn 110(11):3059\u20133093","journal-title":"Mach Learn"},{"key":"1881_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.petrol.2020.108214","volume":"198","author":"M Pirizadeh","year":"2021","unstructured":"Pirizadeh M, Alemohammad N, Manthouri M, Pirizadeh M (2021) A new machine learning ensemble model for class imbalance problem of screening enhanced oil recovery methods. J Pet Sci Eng 198:108214","journal-title":"J Pet Sci Eng"},{"issue":"23","key":"1881_CR11","doi-asserted-by":"publisher","first-page":"14955","DOI":"10.1007\/s00500-021-06080-x","volume":"25","author":"R Gillala","year":"2021","unstructured":"Gillala R, Vuyyuru KR, Jatoth C, Fiore U (2021) An efficient chaotic SALP swarm optimization approach based on ensemble algorithm for class imbalance problems. Soft Comput 25(23):14955\u201314965","journal-title":"Soft Comput"},{"issue":"21","key":"1881_CR12","doi-asserted-by":"publisher","first-page":"10755","DOI":"10.1007\/s00500-018-3629-4","volume":"23","author":"S Kumar","year":"2019","unstructured":"Kumar S, Biswas SK, Devi D (2019) TLUSBoost algorithm: a boosting solution for class imbalance problem. Soft Comput 23(21):10755\u201310767","journal-title":"Soft Comput"},{"issue":"1","key":"1881_CR13","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1016\/j.knosys.2011.06.013","volume":"25","author":"V Garc\u00eda","year":"2012","unstructured":"Garc\u00eda V, S\u00e1nchez JS, Mollineda RA (2012) On the effectiveness of preprocessing methods when dealing with different levels of class imbalance. Knowl Based Syst 25(1):13\u201321","journal-title":"Knowl Based Syst"},{"issue":"5","key":"1881_CR14","doi-asserted-by":"publisher","first-page":"429","DOI":"10.3233\/IDA-2002-6504","volume":"6","author":"N Japkowicz","year":"2002","unstructured":"Japkowicz N, Stephen S (2002) The class imbalance problem: a systematic study. Intell Data Anal 6(5):429\u2013449","journal-title":"Intell Data Anal"},{"key":"1881_CR15","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1016\/j.ins.2020.12.006","volume":"553","author":"VH Barella","year":"2021","unstructured":"Barella VH, Garcia LP, de Souto MC, Lorena AC, de Carvalho AC (2021) Assessing the data complexity of imbalanced datasets. Inf Sci 553:83\u2013109","journal-title":"Inf Sci"},{"key":"1881_CR16","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","journal-title":"Inf Sci"},{"key":"1881_CR17","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1016\/j.patrec.2017.08.002","volume":"98","author":"J Ortigosa-Hern\u00e1ndez","year":"2017","unstructured":"Ortigosa-Hern\u00e1ndez J, Inza I, Lozano JA (2017) Measuring the class-imbalance extent of multi-class problems. Pattern Recognit Lett 98:32\u201338","journal-title":"Pattern Recognit Lett"},{"key":"1881_CR18","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1016\/j.patrec.2020.03.004","volume":"133","author":"R Zhu","year":"2020","unstructured":"Zhu R, Guo Y, Xue J-H (2020) Adjusting the imbalance ratio by the dimensionality of imbalanced data. Pattern Recognit Lett 133:217\u2013223","journal-title":"Pattern Recognit Lett"},{"key":"1881_CR19","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1016\/j.patrec.2018.09.012","volume":"116","author":"R Zhu","year":"2018","unstructured":"Zhu R, Wang Z, Ma Z, Wang G, Xue J-H (2018) LRID: a new metric of multi-class imbalance degree based on likelihood-ratio test. Pattern Recognit Lett 116:36\u201342","journal-title":"Pattern Recognit Lett"},{"key":"1881_CR20","unstructured":"R\u00e9nyi A (1961) On measures of entropy and information. In: Proceedings of the fourth Berkeley symposium on mathematical statistics and probability, volume 1: contributions to the theory of statistics. University of California Press, pp 547\u2013561"},{"issue":"1","key":"1881_CR21","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1016\/j.fss.2010.11.012","volume":"184","author":"W Waegeman","year":"2011","unstructured":"Waegeman W, Verwaeren J, Slabbinck B, De Baets B (2011) Supervised learning algorithms for multi-class classification problems with partial class memberships. Fuzzy Sets Syst 184(1):106\u2013125","journal-title":"Fuzzy Sets Syst"},{"issue":"1","key":"1881_CR22","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1007\/s10115-014-0794-3","volume":"45","author":"RC Prati","year":"2015","unstructured":"Prati RC, Batista GE, Silva DF (2015) Class imbalance revisited: a new experimental setup to assess the performance of treatment methods. Knowl Inf Syst 45(1):247\u2013270","journal-title":"Knowl Inf Syst"},{"key":"1881_CR23","volume-title":"Mathematical statistics and data analysis","author":"JA Rice","year":"2006","unstructured":"Rice JA (2006) Mathematical statistics and data analysis. Cengage Learning, Boston"},{"key":"1881_CR24","volume-title":"Information measures: information and its description in science and engineering","author":"C Arndt","year":"2003","unstructured":"Arndt C (2003) Information measures: information and its description in science and engineering. Springer, Berlin"},{"issue":"6","key":"1881_CR25","doi-asserted-by":"publisher","first-page":"497","DOI":"10.1177\/0165551505057012","volume":"31","author":"D Shi-fei","year":"2005","unstructured":"Shi-fei D, Zhong-zhi S (2005) Studies on incidence pattern recognition based on information entropy. J Inf Sci 31(6):497\u2013502","journal-title":"J Inf Sci"},{"issue":"452","key":"1881_CR26","first-page":"10","volume":"6","author":"K Conrad","year":"2004","unstructured":"Conrad K (2004) Probability distributions and maximum entropy. Entropy 6(452):10","journal-title":"Entropy"},{"key":"1881_CR27","unstructured":"UCI (2022) Machine Learning Repository. https:\/\/archive.ics.uci.edu\/ml\/datasets.php"},{"key":"1881_CR28","doi-asserted-by":"crossref","unstructured":"Gaudreault J-G, Branco P, Gama J 2021) An analysis of performance metrics for imbalanced classification. In: International conference on discovery science. Springer, pp 67\u201377","DOI":"10.1007\/978-3-030-88942-5_6"},{"key":"1881_CR29","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.106490","volume":"210","author":"E Mortaz","year":"2020","unstructured":"Mortaz E (2020) Imbalance accuracy metric for model selection in multi-class imbalance classification problems. Knowl Based Syst 210:106490","journal-title":"Knowl Based Syst"},{"key":"1881_CR30","doi-asserted-by":"crossref","unstructured":"Branco P, Torgo L, Ribeiro RP (2017) Relevance-based evaluation metrics for multi-class imbalanced domains. In: Pacific-Asia conference on knowledge discovery and data mining. Springer, pp 698\u2013710","DOI":"10.1007\/978-3-319-57454-7_54"},{"issue":"4","key":"1881_CR31","doi-asserted-by":"publisher","first-page":"427","DOI":"10.1016\/j.ipm.2009.03.002","volume":"45","author":"M Sokolova","year":"2009","unstructured":"Sokolova M, Lapalme G (2009) A systematic analysis of performance measures for classification tasks. Inf Process Manag 45(4):427\u2013437","journal-title":"Inf Process Manag"},{"issue":"9","key":"1881_CR32","doi-asserted-by":"publisher","first-page":"1263","DOI":"10.1109\/TKDE.2008.239","volume":"21","author":"H He","year":"2009","unstructured":"He H, Garcia EA (2009) Learning from imbalanced data. IEEE Trans Knowl Data Eng 21(9):1263\u20131284","journal-title":"IEEE Trans Knowl Data Eng"},{"issue":"1","key":"1881_CR33","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1080\/00031305.1988.10475524","volume":"42","author":"J Lee Rodgers","year":"1988","unstructured":"Lee Rodgers J, Nicewander WA (1988) Thirteen ways to look at the correlation coefficient. Am Stat 42(1):59\u201366","journal-title":"Am Stat"},{"issue":"1","key":"1881_CR34","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1111\/j.0824-7935.2004.t01-1-00228.x","volume":"20","author":"A Estabrooks","year":"2004","unstructured":"Estabrooks A, Jo T, Japkowicz N (2004) A multiple resampling method for learning from imbalanced data sets. Comput Intell 20(1):18\u201336","journal-title":"Comput Intell"},{"key":"1881_CR35","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.105845","volume":"196","author":"XW Liang","year":"2020","unstructured":"Liang XW, Jiang AP, Li T, Xue YY, Wang GT (2020) LR-SMOTE\u2014an improved unbalanced data set oversampling based on K-means and SVM. Knowl Based Syst 196:105845","journal-title":"Knowl Based Syst"},{"key":"1881_CR36","doi-asserted-by":"publisher","first-page":"341","DOI":"10.1016\/j.solener.2021.05.095","volume":"224","author":"Y Nie","year":"2021","unstructured":"Nie Y, Zamzam AS, Brandt A (2021) Resampling and data augmentation for short-term PV output prediction based on an imbalanced sky images dataset using convolutional neural networks. Sol Energy 224:341\u2013354","journal-title":"Sol Energy"}],"container-title":["Knowledge and Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-023-01881-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10115-023-01881-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-023-01881-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,22]],"date-time":"2023-08-22T17:08:03Z","timestamp":1692724083000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10115-023-01881-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,13]]},"references-count":36,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2023,10]]}},"alternative-id":["1881"],"URL":"https:\/\/doi.org\/10.1007\/s10115-023-01881-y","relation":{},"ISSN":["0219-1377","0219-3116"],"issn-type":[{"value":"0219-1377","type":"print"},{"value":"0219-3116","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,5,13]]},"assertion":[{"value":"14 March 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 April 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 April 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 May 2023","order":4,"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 known competing financial interests or personal relationships that could have appeared to influence the work reported in this paper.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}