{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T18:27:35Z","timestamp":1785436055169,"version":"3.56.0"},"reference-count":64,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2024,4,9]],"date-time":"2024-04-09T00:00:00Z","timestamp":1712620800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,4,9]],"date-time":"2024-04-09T00:00:00Z","timestamp":1712620800000},"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":[[2024,7]]},"DOI":"10.1007\/s10115-024-02079-6","type":"journal-article","created":{"date-parts":[[2024,4,9]],"date-time":"2024-04-09T04:01:36Z","timestamp":1712635296000},"page":"4011-4042","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Noise-free sampling with majority framework for an imbalanced classification problem"],"prefix":"10.1007","volume":"66","author":[{"given":"Neni Alya","family":"Firdausanti","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Israel","family":"Mendon\u00e7a","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Masayoshi","family":"Aritsugi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,4,9]]},"reference":[{"key":"2079_CR1","doi-asserted-by":"publisher","unstructured":"Spelmen VS, Porkodi R (2018) A review on handling imbalanced data. In: 2018 International conference on current trends towards converging technologies (ICCTCT), pp. 1\u201311. https:\/\/doi.org\/10.1109\/ICCTCT.2018.8551020","DOI":"10.1109\/ICCTCT.2018.8551020"},{"key":"2079_CR2","doi-asserted-by":"publisher","first-page":"486","DOI":"10.1007\/978-3-030-16657-1_45","volume-title":"Intelligent systems design and applications","author":"G Rekha","year":"2020","unstructured":"Rekha G, Tyagi AK, Krishna Reddy V (2020) A novel approach to solve class imbalance problem using noise filter method. In: Abraham A, Cherukuri AK, Melin P, Gandhi N (eds) Intelligent systems design and applications. Springer, Cham, pp 486\u2013496. https:\/\/doi.org\/10.1007\/978-3-030-16657-1_45"},{"key":"2079_CR3","doi-asserted-by":"publisher","first-page":"438","DOI":"10.1016\/j.ins.2021.03.041","volume":"565","author":"J Li","year":"2021","unstructured":"Li J, Zhu Q, Wu Q, Fan Z (2021) A novel oversampling technique for class-imbalanced learning based on SMOTE and natural neighbors. Inf Sci 565:438\u2013455. https:\/\/doi.org\/10.1016\/j.ins.2021.03.041","journal-title":"Inf Sci"},{"key":"2079_CR4","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.114301","volume":"168","author":"A Guzm\u00e1n-Ponce","year":"2021","unstructured":"Guzm\u00e1n-Ponce A, S\u00e1nchez JS, Valdovinos RM, Marcial-Romero JR (2021) DBIG-US: A two-stage under-sampling algorithm to face the class imbalance problem. Expert Syst Appl 168:114301. https:\/\/doi.org\/10.1016\/j.eswa.2020.114301","journal-title":"Expert Syst Appl"},{"key":"2079_CR5","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2023.110415","volume":"143","author":"S Rezvani","year":"2023","unstructured":"Rezvani S, Wang X (2023) A broad review on class imbalance learning techniques. Appl Soft Comput 143:110415. https:\/\/doi.org\/10.1016\/j.asoc.2023.110415","journal-title":"Appl Soft Comput"},{"key":"2079_CR6","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1016\/j.neucom.2018.04.089","volume":"343","author":"M Koziarski","year":"2019","unstructured":"Koziarski M, Krawczyk B, Wo\u017aniak M (2019) Radial-based oversampling for noisy imbalanced data classification. Neurocomputing 343:19\u201333. https:\/\/doi.org\/10.1016\/j.neucom.2018.04.089","journal-title":"Neurocomputing"},{"key":"2079_CR7","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.115492","volume":"184","author":"J Liu","year":"2021","unstructured":"Liu J (2021) A minority oversampling approach for fault detection with heterogeneous imbalanced data. Expert Syst Appl 184:115492. https:\/\/doi.org\/10.1016\/j.eswa.2021.115492","journal-title":"Expert Syst Appl"},{"key":"2079_CR8","doi-asserted-by":"publisher","unstructured":"Isangediok M, Gajamannage K (2022) Fraud detection using optimized machine learning tools under imbalance classes. https:\/\/doi.org\/10.48550\/arXiv.2209.01642","DOI":"10.48550\/arXiv.2209.01642"},{"key":"2079_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2022.109637","volume":"130","author":"J Sun","year":"2022","unstructured":"Sun J, Li J, Fujita H (2022) Multi-class imbalanced enterprise credit evaluation based on asymmetric bagging combined with light gradient boosting machine. Appl Soft Comput 130:109637. https:\/\/doi.org\/10.1016\/j.asoc.2022.109637","journal-title":"Appl Soft Comput"},{"issue":"12","key":"2079_CR10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1371\/journal.pone.0243907","volume":"15","author":"K Teh","year":"2020","unstructured":"Teh K, Armitage P, Tesfaye S, Selvarajah D, Wilkinson ID (2020) Imbalanced learning: Improving classification of diabetic neuropathy from magnetic resonance imaging. PLoS ONE 15(12):1\u201315. https:\/\/doi.org\/10.1371\/journal.pone.0243907","journal-title":"PLoS ONE"},{"key":"2079_CR11","doi-asserted-by":"publisher","DOI":"10.3390\/healthcare10071293","author":"V Kumar","year":"2022","unstructured":"Kumar V, Lalotra GS, Sasikala P, Rajput DS, Kaluri R, Lakshmanna K, Shorfuzzaman M, Alsufyani A, Uddin M (2022) Addressing binary classification over class imbalanced clinical datasets using computationally intelligent techniques. Healthcare. https:\/\/doi.org\/10.3390\/healthcare10071293","journal-title":"Healthcare"},{"key":"2079_CR12","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1186\/s40645-021-00459-y","volume":"8","author":"D Matsuoka","year":"2021","unstructured":"Matsuoka D (2021) Classification of imbalanced cloud image data using deep neural networks: performance improvement. Prog Earth Planet Sci 8:68. https:\/\/doi.org\/10.1186\/s40645-021-00459-y","journal-title":"Prog Earth Planet Sci"},{"key":"2079_CR13","doi-asserted-by":"publisher","unstructured":"Xu Y, Li Y-L, Li J, Lu C (2022) Constructing balance from imbalance for long-tailed image recognition. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision\u2013ECCV 2022, pp. 38\u201356. Springer, Cham. https:\/\/doi.org\/10.1007\/978-3-031-20044-1_3","DOI":"10.1007\/978-3-031-20044-1_3"},{"key":"2079_CR14","doi-asserted-by":"publisher","DOI":"10.1016\/j.mlwa.2022.100361","volume":"9","author":"J Ahmed","year":"2022","unstructured":"Ahmed J, Green RC II (2022) Predicting severely imbalanced data disk drive failures with machine learning models. Mach Learn Appl 9:100361. https:\/\/doi.org\/10.1016\/j.mlwa.2022.100361","journal-title":"Mach Learn Appl"},{"key":"2079_CR15","doi-asserted-by":"publisher","first-page":"1815","DOI":"10.1016\/j.procs.2023.01.159","volume":"218","author":"S Pandey","year":"2023","unstructured":"Pandey S, Kumar K (2023) Software fault prediction for imbalanced data: a survey on recent developments. Proc Comput Sci 218:1815\u20131824. https:\/\/doi.org\/10.1016\/j.procs.2023.01.159","journal-title":"Proc Comput Sci"},{"key":"2079_CR16","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.115011","volume":"178","author":"N Moniz","year":"2021","unstructured":"Moniz N, Cerqueira V (2021) Automated imbalanced classification via meta-learning. Expert Syst Appl 178:115011. https:\/\/doi.org\/10.1016\/j.eswa.2021.115011","journal-title":"Expert Syst Appl"},{"key":"2079_CR17","doi-asserted-by":"publisher","unstructured":"Saripuddin M, Suliman A, Syarmila\u00a0Sameon S, Jorgensen BN (2022) Random undersampling on imbalance time series data for anomaly detection. In: Proceedings of the 2021 4th international conference on machine learning and machine intelligence. MLMI \u201921, pp. 151\u2013156. Association for computing machinery, New York, NY, USA. https:\/\/doi.org\/10.1145\/3490725.3490748","DOI":"10.1145\/3490725.3490748"},{"key":"2079_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2019.113026","volume":"158","author":"V Garc\u00eda","year":"2020","unstructured":"Garc\u00eda V, S\u00e1nchez JS, Marqu\u00e9s AI, Florencia R, Rivera G (2020) Understanding the apparent superiority of over-sampling through an analysis of local information for class-imbalanced data. Expert Syst Appl 158:113026. https:\/\/doi.org\/10.1016\/j.eswa.2019.113026","journal-title":"Expert Syst Appl"},{"key":"2079_CR19","doi-asserted-by":"publisher","DOI":"10.3389\/fpubh.2020.00178","author":"K Fujiwara","year":"2020","unstructured":"Fujiwara K, Huang Y, Hori K, Nishioji K, Kobayashi M, Kamaguchi M, Kano M (2020) Over- and under-sampling approach for extremely imbalanced and small minority data problem in health record analysis. Front Public Health. https:\/\/doi.org\/10.3389\/fpubh.2020.00178","journal-title":"Front Public Health"},{"issue":"1","key":"2079_CR20","doi-asserted-by":"publisher","DOI":"10.1088\/1755-1315\/58\/1\/012031","volume":"58","author":"B Santoso","year":"2017","unstructured":"Santoso B, Wijayanto H, Notodiputro KA, Sartono B (2017) Synthetic over sampling methods for handling class imbalanced problems: a review. IOP Conf Ser Earth Environ Sci 58(1):012031. https:\/\/doi.org\/10.1088\/1755-1315\/58\/1\/012031","journal-title":"IOP Conf Ser Earth Environ Sci"},{"key":"2079_CR21","doi-asserted-by":"publisher","unstructured":"Mohammed R, Rawashdeh J, Abdullah M (2020) Machine learning with oversampling and undersampling techniques: overview study and experimental results. In: 2020 11th International conference on information and communication systems (ICICS), pp. 243\u2013248. https:\/\/doi.org\/10.1109\/ICICS49469.2020.239556","DOI":"10.1109\/ICICS49469.2020.239556"},{"key":"2079_CR22","doi-asserted-by":"publisher","DOI":"10.3390\/info14010054","author":"T Wongvorachan","year":"2023","unstructured":"Wongvorachan T, He S, Bulut O (2023) A comparison of undersampling, oversampling, and SMOTE methods for dealing with imbalanced classification in educational data mining. Information. https:\/\/doi.org\/10.3390\/info14010054","journal-title":"Information"},{"key":"2079_CR23","doi-asserted-by":"publisher","unstructured":"Shamsudin H, Yusof UK, Jayalakshmi A, Akmal\u00a0Khalid MN (2020) Combining oversampling and undersampling techniques for imbalanced classification: a comparative study using credit card fraudulent transaction dataset. In: 2020 IEEE 16th international conference on control & automation (ICCA), pp. 803\u2013808. https:\/\/doi.org\/10.1109\/ICCA51439.2020.9264517","DOI":"10.1109\/ICCA51439.2020.9264517"},{"key":"2079_CR24","doi-asserted-by":"publisher","first-page":"401","DOI":"10.1007\/s00607-020-00854-1","volume":"103","author":"S Park","year":"2021","unstructured":"Park S, Park H (2021) Combined oversampling and undersampling method based on slow-start algorithm for imbalanced network traffic. Computing 103:401\u2013424. https:\/\/doi.org\/10.1007\/s00607-020-00854-1","journal-title":"Computing"},{"issue":"3","key":"2079_CR25","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. https:\/\/doi.org\/10.1007\/s10115-019-01380-z","journal-title":"Knowl Inf Syst"},{"key":"2079_CR26","doi-asserted-by":"publisher","unstructured":"Firdausanti NA, Fatyanosa TN, Data M, Mendon\u00e7a I, Aritsugi M (2022) Two-stage sampling: a framework for imbalanced classification with overlapped classes. In: 2022 IEEE international conference on big data (Big Data) pp. 271\u2013280. https:\/\/doi.org\/10.1109\/BigData55660.2022.10020788","DOI":"10.1109\/BigData55660.2022.10020788"},{"issue":"6","key":"2079_CR27","doi-asserted-by":"publisher","first-page":"3413","DOI":"10.1016\/j.jksuci.2021.01.014","volume":"34","author":"NU Asniar Maulidevi","year":"2022","unstructured":"Asniar Maulidevi NU, Surendro K (2022) SMOTE-LOF for noise identification in imbalanced data classification. J King Saud Univ Comput Inf Sci 34(6):3413\u20133423. https:\/\/doi.org\/10.1016\/j.jksuci.2021.01.014","journal-title":"J King Saud Univ Comput Inf Sci"},{"key":"2079_CR28","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107056","volume":"223","author":"J Li","year":"2021","unstructured":"Li J, Zhu Q, Wu Q, Zhang Z, Gong Y, He Z, Zhu F (2021) Smote-nan-de: addressing the noisy and borderline examples problem in imbalanced classification by natural neighbors and differential evolution. Knowl-Based Syst 223:107056. https:\/\/doi.org\/10.1016\/j.knosys.2021.107056","journal-title":"Knowl-Based Syst"},{"key":"2079_CR29","doi-asserted-by":"publisher","unstructured":"Hao S, Zhou X, Song H (2015) A new method for noise data detection based on DBSCAN and SVDD. In: 2015 IEEE International conference on cyber technology in automation, control, and intelligent systems (CYBER), pp. 784\u2013789. https:\/\/doi.org\/10.1109\/CYBER.2015.7288042","DOI":"10.1109\/CYBER.2015.7288042"},{"key":"2079_CR30","doi-asserted-by":"publisher","first-page":"2025","DOI":"10.1007\/s11277-017-4961-1","volume":"98","author":"H Saeedi Emadi","year":"2018","unstructured":"Saeedi Emadi H, Mazinani SM (2018) A novel anomaly detection algorithm using DBSCAN and SVM in wireless sensor networks. Wireless Pers Commun 98:2025\u20132035. https:\/\/doi.org\/10.1007\/s11277-017-4961-1","journal-title":"Wireless Pers Commun"},{"issue":"2","key":"2079_CR31","doi-asserted-by":"publisher","first-page":"917","DOI":"10.32604\/cmc.2020.05981","volume":"62","author":"H Chen","year":"2020","unstructured":"Chen H, Yu G, Liu F, Cai Z, Liu A, Chen S, Huang H, Cheang CF (2020) Unsupervised anomaly detection via DBSCAN for KPIs jitters in network managements. Comput Materi Cont 62(2):917\u2013927. https:\/\/doi.org\/10.32604\/cmc.2020.05981","journal-title":"Comput Materi Cont"},{"key":"2079_CR32","doi-asserted-by":"publisher","unstructured":"Sheridan K, Puranik TG, Mangortey E, Pinon-Fischer OJ, Kirby M, Mavris DN. An application of DBSCAN clustering for flight anomaly detection during the approach phase. https:\/\/doi.org\/10.2514\/6.2020-1851","DOI":"10.2514\/6.2020-1851"},{"issue":"1","key":"2079_CR33","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1869\/1\/012077","volume":"1869","author":"S Wibisono","year":"2021","unstructured":"Wibisono S, Anwar MT, Supriyanto A, Amin IHA (2021) Multivariate weather anomaly detection using dbscan clustering algorithm. J Phys Conf Ser 1869(1):012077. https:\/\/doi.org\/10.1088\/1742-6596\/1869\/1\/012077","journal-title":"J Phys Conf Ser"},{"key":"2079_CR34","doi-asserted-by":"publisher","unstructured":"Chandralekha HM C, PS N, PS SP, Ghosh MK (2022) Anomaly detection in recorded CAN log using DBSCAN and LSTM autoencoder. In: 2022 IEEE 3rd global conference for advancement in technology (GCAT), pp. 1\u20137. https:\/\/doi.org\/10.1109\/GCAT55367.2022.9971885","DOI":"10.1109\/GCAT55367.2022.9971885"},{"key":"2079_CR35","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 Artif Intell Res 16:321\u2013357. https:\/\/doi.org\/10.1613\/jair.953","journal-title":"J Artif Intell Res"},{"key":"2079_CR36","doi-asserted-by":"publisher","first-page":"878","DOI":"10.1007\/11538059_91","volume-title":"Advances in intelligent computing","author":"H Han","year":"2005","unstructured":"Han H, Wang W-Y, Mao B-H (2005) Borderline-smote: a new over-sampling method in imbalanced data sets learning. In: Huang D-S, Zhang X-P, Huang G-B (eds) Advances in intelligent computing. Springer, Berlin, pp 878\u2013887"},{"issue":"11","key":"2079_CR37","doi-asserted-by":"publisher","first-page":"769","DOI":"10.1109\/TSMC.1976.4309452","volume":"6","author":"I Tomek","year":"1976","unstructured":"Tomek I (1976) Two modifications of CNN. IEEE Trans Syst Man Cybern 6(11):769\u2013772. https:\/\/doi.org\/10.1109\/TSMC.1976.4309452","journal-title":"IEEE Trans Syst Man Cybern"},{"issue":"3","key":"2079_CR38","doi-asserted-by":"publisher","first-page":"408","DOI":"10.1109\/TSMC.1972.4309137","volume":"2","author":"DL Wilson","year":"1972","unstructured":"Wilson DL (1972) Asymptotic properties of nearest neighbor rules using edited data. IEEE Trans Syst Man Cybern 2(3):408\u2013421. https:\/\/doi.org\/10.1109\/TSMC.1972.4309137","journal-title":"IEEE Trans Syst Man Cybern"},{"issue":"1","key":"2079_CR39","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1145\/1007730.1007735","volume":"6","author":"GEAPA Batista","year":"2004","unstructured":"Batista GEAPA, Prati RC, Monard MC (2004) A study of the behavior of several methods for balancing machine learning training data. SIGKDD Explor Newsl 6(1):20\u201329. https:\/\/doi.org\/10.1145\/1007730.1007735","journal-title":"SIGKDD Explor Newsl"},{"key":"2079_CR40","doi-asserted-by":"publisher","first-page":"420","DOI":"10.1016\/j.procs.2020.08.043","volume":"176","author":"T Sasada","year":"2020","unstructured":"Sasada T, Liu Z, Baba T, Hatano K, Kimura Y (2020) A resampling method for imbalanced datasets considering noise and overlap. Proc Comput Sci 176:420\u2013429. https:\/\/doi.org\/10.1016\/j.procs.2020.08.043","journal-title":"Proc Comput Sci"},{"key":"2079_CR41","doi-asserted-by":"publisher","first-page":"417","DOI":"10.1007\/978-3-642-02319-4_50","volume-title":"Hybrid artificial intelligence systems","author":"ALB Miranda","year":"2009","unstructured":"Miranda ALB, Garcia LPF, Carvalho ACPLF, Lorena AC (2009) Use of classification algorithms in noise detection and elimination. In: Corchado E, Wu X, Oja E, Herrero \u00c1, Baruque B (eds) Hybrid artificial intelligence systems. Springer, Berlin, Heidelberg, pp 417\u2013424. https:\/\/doi.org\/10.1007\/978-3-642-02319-4_50"},{"key":"2079_CR42","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.115179","volume":"181","author":"A Puri","year":"2021","unstructured":"Puri A, Kumar Gupta M (2021) Knowledge discovery from noisy imbalanced and incomplete binary class data. Expert Syst Appl 181:115179. https:\/\/doi.org\/10.1016\/j.eswa.2021.115179","journal-title":"Expert Syst Appl"},{"key":"2079_CR43","doi-asserted-by":"publisher","unstructured":"Fang X, Chong CF, Yang X, Wang Y (2022) Clustering algorithms based noise identification from air pollution monitoring data. In: 2022 IEEE Asia-pacific conference on computer science and data engineering (CSDE), pp. 1\u20136. https:\/\/doi.org\/10.1109\/CSDE56538.2022.10089276","DOI":"10.1109\/CSDE56538.2022.10089276"},{"issue":"4","key":"2079_CR44","doi-asserted-by":"publisher","first-page":"2545","DOI":"10.1007\/s11277-021-08836-y","volume":"121","author":"DK Kotary","year":"2021","unstructured":"Kotary DK, Nanda SJ (2021) A distributed neighbourhood DBSCAN algorithm for effective data clustering in wireless sensor networks. Wireless Pers Commun 121(4):2545\u20132568. https:\/\/doi.org\/10.1007\/s11277-021-08836-y","journal-title":"Wireless Pers Commun"},{"key":"2079_CR45","doi-asserted-by":"publisher","DOI":"10.1145\/3068335","author":"E Schubert","year":"2017","unstructured":"Schubert E, Sander J, Ester M, Kriegel HP, Xu X (2017) DBSCAN revisited, revisited: why and how you should (still) use DBSCAN. ACM Trans Database Syst. https:\/\/doi.org\/10.1145\/3068335","journal-title":"ACM Trans Database Syst"},{"issue":"2\u20133","key":"2079_CR46","first-page":"255","volume":"17","author":"J Alcal\u00e1-Fdez","year":"2011","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-Val Logic Soft Comput 17(2\u20133):255\u2013287","journal-title":"J Multiple-Val Logic Soft Comput"},{"key":"2079_CR47","doi-asserted-by":"publisher","first-page":"6207","DOI":"10.1007\/s10462-022-10150-3","volume":"55","author":"MS Santos","year":"2022","unstructured":"Santos MS, Abreu PH, Japkowicz N, Fern\u00e1ndez A, Soares C, Wilk S, Santos J (2022) On the joint-effect of class imbalance and overlap: a critical review. Artif Intell Rev 55:6207\u20136275. https:\/\/doi.org\/10.1007\/s10462-022-10150-3","journal-title":"Artif Intell Rev"},{"key":"2079_CR48","doi-asserted-by":"publisher","unstructured":"Patro SGK, Sahu KK (2015) Normalization: a preprocessing stage. https:\/\/doi.org\/10.48550\/arXiv.1503.06462","DOI":"10.48550\/arXiv.1503.06462"},{"key":"2079_CR49","doi-asserted-by":"publisher","DOI":"10.3390\/s22093246","author":"EF Swana","year":"2022","unstructured":"Swana EF, Doorsamy W, Bokoro P (2022) Tomek link and smote approaches for machine fault classification with an imbalanced dataset. Sensors. https:\/\/doi.org\/10.3390\/s22093246","journal-title":"Sensors"},{"key":"2079_CR50","doi-asserted-by":"publisher","first-page":"95","DOI":"10.5311\/JOSIS.2014.8.123","volume":"8","author":"M Tonini","year":"2014","unstructured":"Tonini M, Abellan A (2014) Rockfall detection from terrestrial LiDAR point clouds: a clustering approach using R. J Spat Inf Sci 8:95\u2013110. https:\/\/doi.org\/10.5311\/JOSIS.2014.8.123","journal-title":"J Spat Inf Sci"},{"issue":"3","key":"2079_CR51","doi-asserted-by":"publisher","first-page":"209","DOI":"10.2478\/jaiscr-2020-0014","volume":"10","author":"A Starczewski","year":"2020","unstructured":"Starczewski A, Goetzen P, Er MJ (2020) A new method for automatic determining of the dbscan parameters. J Artif Intell Soft Comput Res 10(3):209\u2013221. https:\/\/doi.org\/10.2478\/jaiscr-2020-0014","journal-title":"J Artif Intell Soft Comput Res"},{"key":"2079_CR52","doi-asserted-by":"publisher","unstructured":"Bessrour M, Elouedi Z, Lef\u00e9vre E (2020) E-DBSCAN: An evidential version of the DBSCAN method. In: 2020 IEEE Symposium series on computational intelligence (SSCI), pp. 3073\u20133080. https:\/\/doi.org\/10.1109\/SSCI47803.2020.9308578","DOI":"10.1109\/SSCI47803.2020.9308578"},{"key":"2079_CR53","doi-asserted-by":"publisher","unstructured":"McKinney: data structures for statistical computing in python. In: Walt, Millman (eds.) Proceedings of the 9th python in science conference, pp. 56\u201361 (2010). https:\/\/doi.org\/10.25080\/Majora-92bf1922-00a","DOI":"10.25080\/Majora-92bf1922-00a"},{"issue":"7825","key":"2079_CR54","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1038\/s41586-020-2649-2","volume":"585","author":"CR Harris","year":"2020","unstructured":"Harris CR, Millman KJ, Walt SJ, Gommers R, Virtanen P, Cournapeau D, Wieser E, Taylor J, Berg S, Smith NJ, Kern R, Picus M, Hoyer S, Kerkwijk MH, Brett M, Haldane A, R\u00edo JF, Wiebe M, Peterson P, G\u00e9rard-Marchant P, Sheppard K, Reddy T, Weckesser W, Abbasi H, Gohlke C, Oliphant TE (2020) Array programming with NumPy. Nature 585(7825):357\u2013362. https:\/\/doi.org\/10.1038\/s41586-020-2649-2","journal-title":"Nature"},{"key":"2079_CR55","doi-asserted-by":"publisher","unstructured":"Virtanen P, Gommers R, Oliphant TE, Haberland M, Reddy T, Cournapeau D, Burovski E, Peterson P, Weckesser W, Bright J, van der Walt SJ, Brett M, Wilson J, Millman KJ, Mayorov N, Nelson ARJ, Jones E, Kern R, Larson E, Carey CJ, Polat \u0130, Feng Y, Moore EW, VanderPlas J, Laxalde D, Perktold J, Cimrman R, Henriksen I, Quintero EA, Harris CR, Archibald AM, Ribeiro AH, Pedregosa F, van Mulbregt P, SciPy 1.0 Contributors (2020) SciPy 1.0: fundamental algorithms for scientific computing in Python. Nat Methods 17:261\u2013272. https:\/\/doi.org\/10.1038\/s41592-019-0686-2","DOI":"10.1038\/s41592-019-0686-2"},{"issue":"3","key":"2079_CR56","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1109\/MCSE.2007.55","volume":"9","author":"JD Hunter","year":"2007","unstructured":"Hunter JD (2007) Matplotlib: A 2d graphics environment. Comput Sci Eng 9(3):90\u201395. https:\/\/doi.org\/10.1109\/MCSE.2007.55","journal-title":"Comput Sci Eng"},{"key":"2079_CR57","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Blondel M, Prettenhofer P, Weiss R, Dubourg V, Vanderplas J, Passos A, Cournapeau D, Brucher M, Perrot M, Duchesnay E (2011) Scikit-learn: machine learning in python. J Mach Learn Res 12:2825\u20132830","journal-title":"J Mach Learn Res"},{"issue":"17","key":"2079_CR58","first-page":"1","volume":"18","author":"G Lema\u00eetre","year":"2017","unstructured":"Lema\u00eetre G, Nogueira F, Aridas CK (2017) Imbalanced-learn: a python toolbox to tackle the curse of imbalanced datasets in machine learning. J Mach Learn Res 18(17):1\u20135","journal-title":"J Mach Learn Res"},{"key":"2079_CR59","doi-asserted-by":"publisher","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), pp. 1322\u20131328. https:\/\/doi.org\/10.1109\/IJCNN.2008.4633969","DOI":"10.1109\/IJCNN.2008.4633969"},{"key":"2079_CR60","first-page":"878","volume-title":"Adv Intell Comput","author":"H Han","year":"2005","unstructured":"Han H, Wang W-Y, Mao B-H (2005) Borderline-SMOTE: a new over-sampling method in imbalanced data sets learning. In: Huang D-S, Zhang X-P, Huang G-B (eds) Adv Intell Comput. Springer, Berlin, Heidelberg, pp 878\u2013887"},{"key":"2079_CR61","unstructured":"Zhang J, Mani I (2003) kNN approach to unbalanced data distributions: a case study involving information extraction. In: Proceedings of the ICML\u20192003 workshop on learning from imbalanced datasets"},{"key":"2079_CR62","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1007\/3-540-48229-6_9","volume":"2101","author":"J Laurikkala","year":"2001","unstructured":"Laurikkala J (2001) Improving identification of difficult small classes by balancing class distribution. Artif Intell Med 2101:63\u201366. https:\/\/doi.org\/10.1007\/3-540-48229-6_9","journal-title":"Artif Intell Med"},{"key":"2079_CR63","doi-asserted-by":"publisher","unstructured":"Scheff SW (2016) Chapter 8 - nonparametric statistics. In: Scheff, S.W. (ed.) Fundamental Statistical Principles for the Neurobiologist, pp. 157\u2013182. https:\/\/doi.org\/10.1016\/B978-0-12-804753-8.00008-7 . https:\/\/www.sciencedirect.com\/science\/article\/pii\/B9780128047538000087","DOI":"10.1016\/B978-0-12-804753-8.00008-7"},{"key":"2079_CR64","doi-asserted-by":"publisher","unstructured":"Xia Y (2020) Chapter eleven - correlation and association analyses in microbiome study integrating multiomics in health and disease. In: Sun, J. (ed.) The Microbiome in health and disease. Progress in Molecular Biology and Translational Science, vol. 171, pp. 309\u2013491. https:\/\/doi.org\/10.1016\/bs.pmbts.2020.04.003 . https:\/\/www.sciencedirect.com\/science\/article\/pii\/S1877117320300478","DOI":"10.1016\/bs.pmbts.2020.04.003"}],"container-title":["Knowledge and Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-024-02079-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10115-024-02079-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-024-02079-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,21]],"date-time":"2024-06-21T03:10:12Z","timestamp":1718939412000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10115-024-02079-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,9]]},"references-count":64,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2024,7]]}},"alternative-id":["2079"],"URL":"https:\/\/doi.org\/10.1007\/s10115-024-02079-6","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-3337189\/v1","asserted-by":"object"}]},"ISSN":["0219-1377","0219-3116"],"issn-type":[{"value":"0219-1377","type":"print"},{"value":"0219-3116","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4,9]]},"assertion":[{"value":"8 September 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 January 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 February 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 April 2024","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 there is no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}