{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T06:55:00Z","timestamp":1742972100635,"version":"3.40.3"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031333736"},{"type":"electronic","value":"9783031333743"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-33374-3_17","type":"book-chapter","created":{"date-parts":[[2023,5,26]],"date-time":"2023-05-26T10:02:30Z","timestamp":1685095350000},"page":"210-222","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Selecting the\u00a0Number of\u00a0Clusters K with\u00a0a\u00a0Stability Trade-off: An Internal Validation Criterion"],"prefix":"10.1007","author":[{"given":"Alex","family":"Mourer","sequence":"first","affiliation":[]},{"given":"Florent","family":"Forest","sequence":"additional","affiliation":[]},{"given":"Mustapha","family":"Lebbah","sequence":"additional","affiliation":[]},{"given":"Hanane","family":"Azzag","sequence":"additional","affiliation":[]},{"given":"J\u00e9r\u00f4me","family":"Lacaille","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,5,27]]},"reference":[{"key":"17_CR1","doi-asserted-by":"crossref","unstructured":"Balcan, M.F., Liang, Y.: Clustering under perturbation resilience. SIAM J. Comput. (2016)","DOI":"10.1137\/140981575"},{"key":"17_CR2","unstructured":"Barton, T.: https:\/\/github.com\/deric\/clustering-benchmark"},{"key":"17_CR3","doi-asserted-by":"crossref","unstructured":"Ben-David, S.: Clustering-what both theoreticians and practitioners are doing wrong. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.12221"},{"key":"17_CR4","unstructured":"Ben-David, S., P\u00e1l, D., Simon, H.U.: Stability of k-means clustering. In: International Conference on Computational Learning Theory (2007)"},{"key":"17_CR5","unstructured":"Ben-David, S., Von Luxburg, U.: Relating clustering stability to properties of cluster boundaries. In: 21st Annual Conference on Learning Theory, COLT 2008 (2008)"},{"key":"17_CR6","doi-asserted-by":"crossref","unstructured":"Ben-David, S., Von Luxburg, U., P\u00e1l, D.: A sober look at clustering stability. In: International Conference on Computational Learning Theory (2006)","DOI":"10.1007\/11776420_4"},{"key":"17_CR7","doi-asserted-by":"crossref","unstructured":"Ben-David, S., Reyzin, L.: Data stability in clustering: a closer look. Theoretical Computer Science (2014)","DOI":"10.1016\/j.tcs.2014.09.025"},{"key":"17_CR8","unstructured":"Ben-Hur, A., Elisseeff, A., Guyon, I.: A stability based method for discovering structure in clustered data. Pacific Symposium on Biocomputing (2002)"},{"key":"17_CR9","doi-asserted-by":"crossref","unstructured":"Bubeck, S., Meila, M., Luxburg, U.V.: How the initialization affects the stability of the k-means algorithm. ESAIM - Probability and Statistics (2012)","DOI":"10.1051\/ps\/2012013"},{"key":"17_CR10","doi-asserted-by":"crossref","unstructured":"Cali\u0144ski, T., Harabasz, J.: A dendrite method for cluster analysis. Commun. Stat.(1974)","DOI":"10.1080\/03610927408827101"},{"key":"17_CR11","doi-asserted-by":"crossref","unstructured":"Davies, D.L., Bouldin, D.W.: A cluster separation measure. IEEE Trans. Pattern Anal. Mach. Intell. (1979)","DOI":"10.1109\/TPAMI.1979.4766909"},{"key":"17_CR12","unstructured":"Dem\u0161ar, J.: Statistical comparisons of classifiers over multiple data sets. J. Mach. Learn. Res. (2006)"},{"key":"17_CR13","doi-asserted-by":"crossref","unstructured":"Desgraupes, B.: ClusterCrit: clustering indices. CRAN Package (2013)","DOI":"10.32614\/CRAN.package.clusterCrit"},{"key":"17_CR14","doi-asserted-by":"crossref","unstructured":"Dunn, J.C.: Well-Separated clusters and optimal fuzzy partitions. J. Cybern. (1974)","DOI":"10.1080\/01969727408546059"},{"key":"17_CR15","doi-asserted-by":"crossref","unstructured":"Falasconi, M., Gutierrez, A., Pardo, M., Sberveglieri, G., Marco, S.: A stability based validity method for fuzzy clustering. Pattern Recogn. (2010)","DOI":"10.1016\/j.patcog.2009.10.001"},{"issue":"3","key":"17_CR16","doi-asserted-by":"publisher","first-page":"468","DOI":"10.1016\/j.csda.2011.09.003","volume":"56","author":"Y Fang","year":"2012","unstructured":"Fang, Y., Wang, J.: Selection of the number of clusters via the bootstrap method. Comput. Stat. Data Anal. 56(3), 468\u2013477 (2012)","journal-title":"Comput. Stat. Data Anal."},{"key":"17_CR17","doi-asserted-by":"crossref","unstructured":"Gagolewski, M., Bartoszuk, M., Cena A.G.: A new, fast, and outlier-resistant hierarchical clustering algorithm (2016)","DOI":"10.1016\/j.ins.2016.05.003"},{"key":"17_CR18","unstructured":"Hamerly, G., Elkan, C.: Learning the k in k-means. In: NIPS (2004)"},{"issue":"1","key":"17_CR19","doi-asserted-by":"publisher","first-page":"258","DOI":"10.1016\/j.csda.2006.11.025","volume":"52","author":"C Hennig","year":"2007","unstructured":"Hennig, C.: Cluster-wise assessment of cluster stability. Comput. Stat. Data Anal. 52(1), 258\u2013271 (2007)","journal-title":"Comput. Stat. Data Anal."},{"key":"17_CR20","doi-asserted-by":"crossref","unstructured":"Hess, S., Duivesteijn, W.: K is the magic number - inferring the number of clusters through nonparametric concentration inequalities. In: EMCL-PKDD (2019)","DOI":"10.1007\/978-3-030-46150-8_16"},{"key":"17_CR21","unstructured":"Hofmeyr, D.P.: Degrees of freedom and model selection for k-means clustering. arXiv preprint arXiv:1806.02034 (2018)"},{"key":"17_CR22","doi-asserted-by":"crossref","unstructured":"Lange, T., Roth, V., Braun, M.L., Buhmann, J.M.: Stability-based validation of clustering solutions. Neural Comput. (2004)","DOI":"10.1162\/089976604773717621"},{"key":"17_CR23","unstructured":"Maechler, M., Rousseeuw, P., Struyf, A., Hubert, M., et al.: Package \u2018cluster\u2019 (2013)"},{"key":"17_CR24","unstructured":"Meila, M.: How to tell when a clustering is (approximately) correct using convex relaxations. In: Advances in Neural Information Processing Systems (2018)"},{"key":"17_CR25","doi-asserted-by":"crossref","unstructured":"M\u00f6ller, U., Radke, D.: A cluster validity approach based on nearest-neighbor resampling. In: Proceedings - International Conference on Pattern Recognition (2006)","DOI":"10.1109\/ICPR.2006.42"},{"key":"17_CR26","unstructured":"Pelleg, D., Moore, A.: X-means: extending k-means with efficient estimation of the number of clusters. In: International Conference on Machine Learning (2000)"},{"key":"17_CR27","unstructured":"Ray, S., Turi, R.: Determination of number of clusters in k-means clustering and application in colour image segmentation. In: Proceedings of the 4th International Conference on Advances in Pattern Recognition and Digital Techniques (1999)"},{"key":"17_CR28","doi-asserted-by":"crossref","unstructured":"Rousseeuw, P.J.: Silhouettes: A graphical aid to the interpretation and validation of cluster analysis. J. Comput. Appl. Math. (1987)","DOI":"10.1016\/0377-0427(87)90125-7"},{"key":"17_CR29","unstructured":"Shamir, O., Tishby, N.: Cluster stability for finite samples. In: Advances in Neural Information Processing Systems (2007)"},{"key":"17_CR30","doi-asserted-by":"crossref","unstructured":"Smith, S.P., Dubes, R.: Stability of a hierarchical clustering. Pattern Recogn. (1980)","DOI":"10.1016\/0031-3203(80)90042-4"},{"key":"17_CR31","doi-asserted-by":"crossref","unstructured":"Strauss, J.S., Bartko, J.J., Carpenter, W.T.: The use of clustering techniques for the classification of psychiatric patients. British J. Psychiatry (1973)","DOI":"10.1192\/bjp.122.5.531"},{"key":"17_CR32","doi-asserted-by":"crossref","unstructured":"Tibshirani, R., Walther, G., Hastie, T.: Estimating the number of clusters in a data set via the gap statistic. J. Royal Stat. Soc. Ser. B (2001)","DOI":"10.1111\/1467-9868.00293"},{"key":"17_CR33","unstructured":"Vijayaraghavan, A., Dutta, A., Wang, A.: Clustering stable instances of euclidean k-means. In: Advances in Neural Information Processing Systems (2017)"},{"key":"17_CR34","unstructured":"Von Luxburg, U.: Clustering stability: an overview. Found. Trends\u00ae Mach. Learn. (2010)"},{"key":"17_CR35","doi-asserted-by":"crossref","unstructured":"Yeung, K.Y., Haynor, D.R., Ruzzo, W.L.: Validating clustering for gene expression data. Bioinformatics (2001)","DOI":"10.1093\/bioinformatics\/17.4.309"},{"key":"17_CR36","doi-asserted-by":"crossref","unstructured":"Zhao, Q., Xu, M., Fr\u00e4nti, P.: Extending external validity measures for determining the number of clusters. Intell. Syst. Design Appl. (2011)","DOI":"10.1109\/ISDA.2011.6121777"}],"container-title":["Lecture Notes in Computer Science","Advances in Knowledge Discovery and Data Mining"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-33374-3_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,21]],"date-time":"2024-10-21T04:54:26Z","timestamp":1729486466000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-33374-3_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031333736","9783031333743"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-33374-3_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"27 May 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PAKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific-Asia Conference on Knowledge Discovery and Data Mining","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Osaka","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 May 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 May 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pakdd2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/pakdd2023.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"813","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"143","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"18% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.5","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"10","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}