{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T20:46:48Z","timestamp":1743108408143,"version":"3.40.3"},"publisher-location":"Cham","reference-count":18,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031769337"},{"type":"electronic","value":"9783031769344"}],"license":[{"start":{"date-parts":[[2024,12,12]],"date-time":"2024-12-12T00:00:00Z","timestamp":1733961600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,12]],"date-time":"2024-12-12T00:00:00Z","timestamp":1733961600000},"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":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-76934-4_5","type":"book-chapter","created":{"date-parts":[[2024,12,17]],"date-time":"2024-12-17T18:15:42Z","timestamp":1734459342000},"page":"79-91","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Provable Imbalanced Point Clustering"],"prefix":"10.1007","author":[{"given":"David","family":"Denisov","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dan","family":"Feldman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shlomi","family":"Dolev","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Segal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,12]]},"reference":[{"key":"5_CR1","unstructured":"Arthur, D., Vassilvitskii, S.: K-means++: the advantages of careful seeding. In: Proceedings of the ACM-SIAM Symposium on Discrete Algorithms (SODA), SODA 2007, pp. 1027\u20131035. Society for Industrial and Applied Mathematics, USA (2007)"},{"key":"5_CR2","unstructured":"Batista, G.E., Bazzan, A.L., Monard, M.C., et al.: Balancing training data for automated annotation of keywords: a case study. Wob 3, 10\u20138 (2003)"},{"key":"5_CR3","unstructured":"Bradski, G.: The OpenCV library. Dr. Dobb\u2019s J. Softw. Tools (2000)"},{"key":"5_CR4","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1613\/jair.953","volume":"16","author":"NV Chawla","year":"2002","unstructured":"Chawla, N.V., Bowyer, K.W., Hall, L.O., Kegelmeyer, W.P.: SMOTE: synthetic minority over-sampling technique. J. Artif. Intell. Res. 16, 321\u2013357 (2002)","journal-title":"J. Artif. Intell. Res."},{"key":"5_CR5","unstructured":"Denisov, D., Feldman, D., Dolev, S., Segal, M.: Provable imbalanced point clustering. arXiv preprint arXiv:2408.14225 (2024)"},{"key":"5_CR6","series-title":"Unsupervised and Semi-Supervised Learning","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1007\/978-3-030-29349-9_2","volume-title":"Sampling Techniques for Supervised or Unsupervised Tasks","author":"D Feldman","year":"2020","unstructured":"Feldman, D.: Core-sets: updated survey. In: Ros, F., Guillaume, S. (eds.) Sampling Techniques for Supervised or Unsupervised Tasks. Unsupervised and Semi-Supervised Learning, pp. 23\u201344. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-29349-9_2"},{"key":"5_CR7","doi-asserted-by":"publisher","unstructured":"Feldman, D., Langberg, M.: A unified framework for approximating and clustering data. In: Proceedings of the Annual ACM Symposium on Theory of Computing (2011). https:\/\/doi.org\/10.1145\/1993636.1993712","DOI":"10.1145\/1993636.1993712"},{"key":"5_CR8","doi-asserted-by":"crossref","unstructured":"Feldman, D., Schulman, L.J.: Data reduction for weighted and outlier-resistant clustering. In: Proceedings of the Twenty-Third Annual ACM-SIAM Symposium on Discrete Algorithms, pp. 1343\u20131354. Society for Industrial and Applied Mathematics (2012)","DOI":"10.1137\/1.9781611973099.106"},{"issue":"4","key":"5_CR9","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1007\/s13748-016-0094-0","volume":"5","author":"B Krawczyk","year":"2016","unstructured":"Krawczyk, B.: Learning from imbalanced data: open challenges and future directions. Progr. Artif. Intell. 5(4), 221\u2013232 (2016)","journal-title":"Progr. Artif. Intell."},{"key":"5_CR10","doi-asserted-by":"crossref","unstructured":"Lamrous, S., Taileb, M.: Divisive hierarchical k-means. In: 2006 International Conference on Computational Intelligence for Modelling Control and Automation and International Conference on Intelligent Agents Web Technologies and International Commerce (CIMCA 2006), p. 18. IEEE (2006)","DOI":"10.1109\/CIMCA.2006.89"},{"key":"5_CR11","unstructured":"Last, F., Douzas, G., Bacao, F.: Oversampling for imbalanced learning based on k-means and SMOTE (2017)"},{"key":"5_CR12","unstructured":"Lewis, R.J.: An introduction to classification and regression tree (CART) analysis. In: Annual Meeting of the Society for Academic Emergency Medicine in San Francisco, California, vol.\u00a014. Citeseer (2000)"},{"key":"5_CR13","unstructured":"Mani, I., Zhang, I.: knn approach to unbalanced data distributions: a case study involving information extraction. In: Proceedings of Workshop on Learning from Imbalanced Datasets, vol.\u00a0126, pp.\u00a01\u20137. ICML (2003)"},{"issue":"1","key":"5_CR14","first-page":"86","volume":"2","author":"F Murtagh","year":"2012","unstructured":"Murtagh, F., Contreras, P.: Algorithms for hierarchical clustering: an overview. Wiley Interdisc. Rev.: Data Min. Knowl. Discov. 2(1), 86\u201397 (2012)","journal-title":"Wiley Interdisc. Rev.: Data Min. Knowl. Discov."},{"key":"5_CR15","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa, F., et al.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825\u20132830 (2011)","journal-title":"J. Mach. Learn. Res."},{"key":"5_CR16","unstructured":"Rosenberg, A., Hirschberg, J.: V-measure: a conditional entropy-based external cluster evaluation measure. In: Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL), pp. 410\u2013420 (2007)"},{"key":"5_CR17","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1016\/0377-0427(87)90125-7","volume":"20","author":"PJ Rousseeuw","year":"1987","unstructured":"Rousseeuw, P.J.: Silhouettes: a graphical aid to the interpretation and validation of cluster analysis. J. Comput. Appl. Math. 20, 53\u201365 (1987). https:\/\/doi.org\/10.1016\/0377-0427(87)90125-7","journal-title":"J. Comput. Appl. Math."},{"key":"5_CR18","doi-asserted-by":"publisher","first-page":"012031","DOI":"10.1088\/1755-1315\/58\/1\/012031","volume":"58","author":"B Santoso","year":"2017","unstructured":"Santoso, B., Wijayanto, H., Notodiputro, K., Sartono, B.: Synthetic over sampling methods for handling class imbalanced problems\u202f: a review. IOP Conf. Ser.: Earth Environ. Sci. 58, 012031 (2017). https:\/\/doi.org\/10.1088\/1755-1315\/58\/1\/012031","journal-title":"IOP Conf. Ser.: Earth Environ. Sci."}],"container-title":["Lecture Notes in Computer Science","Cyber Security, Cryptology, and Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-76934-4_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,17]],"date-time":"2024-12-17T19:02:46Z","timestamp":1734462166000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-76934-4_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,12]]},"ISBN":["9783031769337","9783031769344"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-76934-4_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,12]]},"assertion":[{"value":"12 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CSCML","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Symposium on Cyber Security, Cryptology, and Machine Learning","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Be'er Sheva","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cscml2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.cscml.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}