{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T15:23:16Z","timestamp":1780500196171,"version":"3.54.1"},"publisher-location":"Singapore","reference-count":32,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819722419","type":"print"},{"value":"9789819722426","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-981-97-2242-6_20","type":"book-chapter","created":{"date-parts":[[2024,4,24]],"date-time":"2024-04-24T09:02:31Z","timestamp":1713949351000},"page":"246-258","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["AutoClues: Exploring Clustering Pipelines via\u00a0AutoML and\u00a0Diversification"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0805-1051","authenticated-orcid":false,"given":"Matteo","family":"Francia","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0990-3893","authenticated-orcid":false,"given":"Joseph","family":"Giovanelli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0437-0725","authenticated-orcid":false,"given":"Matteo","family":"Golfarelli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,4,25]]},"reference":[{"key":"20_CR1","unstructured":"Arthur, D., Vassilvitskii, S.: k-means++: The advantages of careful seeding. Technical report, Stanford (2006)"},{"issue":"3","key":"20_CR2","doi-asserted-by":"publisher","first-page":"295","DOI":"10.1162\/neco.1989.1.3.295","volume":"1","author":"HB Barlow","year":"1989","unstructured":"Barlow, H.B.: Unsupervised learning. Neural Comput. 1(3), 295\u2013311 (1989)","journal-title":"Neural Comput."},{"key":"20_CR3","doi-asserted-by":"crossref","unstructured":"Breunig, M.M., Kriegel, H.P., Ng, R.T., Sander, J.: LoF: identifying density-based local outliers. In: Proceedings of the 2000 ACM SIGMOD International Conference on Management of Data. , pp. 93\u2013104 (2000)","DOI":"10.1145\/342009.335388"},{"key":"20_CR4","doi-asserted-by":"crossref","unstructured":"Davies, D.L., Bouldin, D.W.: A cluster separation measure. IEEE Trans. Pattern Anal. Mach. Intell. PAMI-1(2), 224\u2013227 (1979)","DOI":"10.1109\/TPAMI.1979.4766909"},{"key":"20_CR5","doi-asserted-by":"crossref","unstructured":"Dutta, D., Dutta, P., Sil, J.: Simultaneous continuous feature selection and k clustering by multi objective genetic algorithm. In: 2013 3rd IEEE International Advance Computing Conference (IACC), pp. 937\u2013942 (2013)","DOI":"10.1109\/IAdCC.2013.6514352"},{"key":"20_CR6","doi-asserted-by":"crossref","unstructured":"ElShawi, R., Sakr, S.: TPE-autoclust: a tree-based pipline ensemble framework for automated clustering. In: 2022 IEEE International Conference on Data Mining Workshops (ICDMW), pp. 1144\u20131153 (2022)","DOI":"10.1109\/ICDMW58026.2022.00149"},{"key":"20_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.inffus.2022.12.017","volume":"93","author":"J Enes","year":"2023","unstructured":"Enes, J., Exp\u00f3sito, R.R., Fuentes, J., Cacheiro, J.L., Touri\u00f1o, J.: A pipeline architecture for feature-based unsupervised clustering using multivariate time series from HPC jobs. Inf. Fusion 93, 1\u201320 (2023)","journal-title":"Inf. Fusion"},{"key":"20_CR8","doi-asserted-by":"publisher","first-page":"182","DOI":"10.1016\/j.future.2022.12.035","volume":"142","author":"M Francia","year":"2023","unstructured":"Francia, M., Giovanelli, J., Pisano, G.: Hamlet: a framework for human-centered automl via structured argumentation. Futur. Gener. Comput. Syst. 142, 182\u2013194 (2023)","journal-title":"Futur. Gener. Comput. Syst."},{"key":"20_CR9","doi-asserted-by":"crossref","unstructured":"Fr\u00e4nti, P., Sieranoja, S.: K-means properties on six clustering benchmark datasets (2018)","DOI":"10.1007\/s10489-018-1238-7"},{"key":"20_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.softx.2022.101270","volume":"20","author":"M Gagolewski","year":"2022","unstructured":"Gagolewski, M.: A framework for benchmarking clustering algorithms. SoftwareX 20, 101270 (2022)","journal-title":"SoftwareX"},{"key":"20_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.is.2021.101957","volume":"108","author":"J Giovanelli","year":"2022","unstructured":"Giovanelli, J., Bilalli, B., Abell\u00f3, A.: Data pre-processing pipeline generation for autoETL. Inf. Syst. 108, 101957 (2022)","journal-title":"Inf. Syst."},{"key":"20_CR12","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2019.103307","volume":"87","author":"E Hancer","year":"2020","unstructured":"Hancer, E.: A new multi-objective differential evolution approach for simultaneous clustering and feature selection. Eng. Appl. Artif. Intell. 87, 103307 (2020)","journal-title":"Eng. Appl. Artif. Intell."},{"issue":"5","key":"20_CR13","doi-asserted-by":"publisher","first-page":"657","DOI":"10.1109\/TPAMI.2005.95","volume":"27","author":"J Huang","year":"2005","unstructured":"Huang, J., Ng, M., Rong, H., Li, Z.: Automated variable weighting in k-means type clustering. IEEE Trans. Pattern Anal. Mach. Intell. 27(5), 657\u2013668 (2005)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"20_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"507","DOI":"10.1007\/978-3-642-25566-3_40","volume-title":"Learning and Intelligent Optimization","author":"F Hutter","year":"2011","unstructured":"Hutter, F., Hoos, H.H., Leyton-Brown, K.: Sequential model-based optimization for general algorithm configuration. In: Coello, C.A.C. (ed.) LION 2011. LNCS, vol. 6683, pp. 507\u2013523. Springer, Heidelberg (2011). https:\/\/doi.org\/10.1007\/978-3-642-25566-3_40"},{"key":"20_CR15","doi-asserted-by":"publisher","first-page":"1596","DOI":"10.1016\/j.procs.2020.09.182","volume":"176","author":"R Kamoshida","year":"2020","unstructured":"Kamoshida, R., Ishikawa, F.: Automated clustering and knowledge acquisition support for beginners. Procedia Comput. Sci. 176, 1596\u20131605 (2020)","journal-title":"Procedia Comput. Sci."},{"key":"20_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"538","DOI":"10.1007\/978-3-319-55849-3_35","volume-title":"Applications of Evolutionary Computation","author":"A Lensen","year":"2017","unstructured":"Lensen, A., Xue, B., Zhang, M.: Using particle swarm optimisation and the silhouette metric to estimate the number of clusters, select features, and perform clustering. In: Squillero, G., Sim, K. (eds.) EvoApplications 2017. LNCS, vol. 10199, pp. 538\u2013554. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-55849-3_35"},{"issue":"1","key":"20_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2133360.2133363","volume":"6","author":"FT Liu","year":"2012","unstructured":"Liu, F.T., Ting, K.M., Zhou, Z.H.: Isolation-based anomaly detection. ACM Trans. Knowl. Discov. Data (TKDD) 6(1), 1\u201339 (2012)","journal-title":"ACM Trans. Knowl. Discov. Data (TKDD)"},{"key":"20_CR18","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"246","DOI":"10.1007\/978-3-030-75768-7_20","volume-title":"Advances in Knowledge Discovery and Data Mining","author":"Y Liu","year":"2021","unstructured":"Liu, Y., Li, S., Tian, W.: AutoCluster: meta-learning based ensemble method for automated unsupervised clustering. In: Karlapalem, K., et al. (eds.) PAKDD 2021. LNCS (LNAI), vol. 12714, pp. 246\u2013258. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-75768-7_20"},{"key":"20_CR19","unstructured":"Van\u00a0der Maaten, L., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learni. Res. 9(11) (2008)"},{"key":"20_CR20","doi-asserted-by":"crossref","unstructured":"Murtagh, F., Contreras, P.: Algorithms for hierarchical clustering: an overview. Wiley Interdisc. Rev. Data Min. Knowl. Discov. 7(6) (2017)","DOI":"10.1002\/widm.1219"},{"key":"20_CR21","doi-asserted-by":"crossref","unstructured":"Poulakis, Y., Doulkeridis, C., Kyriazis, D.: Autoclust: a framework for automated clustering based on cluster validity indices. In: ICDM, pp. 1220\u20131225. IEEE (2020)","DOI":"10.1109\/ICDM50108.2020.00153"},{"issue":"6","key":"20_CR22","doi-asserted-by":"publisher","first-page":"2083","DOI":"10.1007\/s00500-017-2923-x","volume":"23","author":"J Prakash","year":"2019","unstructured":"Prakash, J., Singh, P.K.: Gravitational search algorithm and k-means for simultaneous feature selection and data clustering: a multi-objective approach. Soft. Comput. 23(6), 2083\u20132100 (2019)","journal-title":"Soft. Comput."},{"key":"20_CR23","doi-asserted-by":"crossref","unstructured":"Saha, S., Spandana, R., Ekbal, A., Bandyopadhyay, S.: Simultaneous feature selection and symmetry based clustering using multiobjective framework. Appl. Soft Comput. 29(C), 479\u2013486 (2015)","DOI":"10.1016\/j.asoc.2014.12.009"},{"key":"20_CR24","first-page":"784","volume":"7","author":"I Sobol","year":"1967","unstructured":"Sobol, I.: The distribution of points in a cube and the accurate evaluation of integrals (in Russian) zh. Vychisl. Mat. i Mater. Phys 7, 784\u2013802 (1967)","journal-title":"Vychisl. Mat. i Mater. Phys"},{"key":"20_CR25","doi-asserted-by":"crossref","unstructured":"Thornton, C., Hutter, F., Hoos, H.H., Leyton-Brown, K.: Auto-Weka: combined selection and hyperparameter optimization of classification algorithms. In: Proceedings of the 19th ACM SIGKDD, pp. 847\u2013855 (2013)","DOI":"10.1145\/2487575.2487629"},{"key":"20_CR26","doi-asserted-by":"publisher","DOI":"10.1016\/j.dib.2020.105501","volume":"30","author":"MC Thrun","year":"2020","unstructured":"Thrun, M.C., Ultsch, A.: Clustering benchmark datasets exploiting the fundamental clustering problems. Data Brief 30, 105501 (2020)","journal-title":"Data Brief"},{"issue":"3","key":"20_CR27","doi-asserted-by":"publisher","first-page":"501","DOI":"10.1007\/s10115-018-1186-x","volume":"58","author":"E Toch","year":"2019","unstructured":"Toch, E., Lerner, B., Ben-Zion, E., Ben-Gal, I.: Analyzing large-scale human mobility data: a survey of machine learning methods and applications. Knowl. Inf. Syst. 58(3), 501\u2013523 (2019)","journal-title":"Knowl. Inf. Syst."},{"key":"20_CR28","unstructured":"Tschechlov, D., Fritz, M., Schwarz, H.: Automl4clust: efficient autoML for clustering analyses, pp. 343\u2013348 (2021)"},{"key":"20_CR29","doi-asserted-by":"crossref","unstructured":"Vieira, M.R., et al.: On query result diversification. In: 27th IEEE International Conference on Data Engineering (ICDE), pp. 1163\u20131174. IEEE (2011)","DOI":"10.1109\/ICDE.2011.5767846"},{"key":"20_CR30","doi-asserted-by":"crossref","unstructured":"Vinh, N.X., Epps, J., Bailey, J.: Information theoretic measures for clusterings comparison: is a correction for chance necessary? In: Proceedings of the 26th Annual International Conference on Machine Learning, pp. 1073\u20131080 (2009)","DOI":"10.1145\/1553374.1553511"},{"key":"20_CR31","doi-asserted-by":"crossref","unstructured":"Zhao, Z., Liu, H.: Spectral feature selection for supervised and unsupervised learning. In: Proceedings of the 24th International Conference on Machine Learning (2007)","DOI":"10.1145\/1273496.1273641"},{"issue":"2","key":"20_CR32","first-page":"139","volume":"30","author":"L Zhu","year":"2010","unstructured":"Zhu, L., Ma, B., Zhao, X.: Clustering validity analysis based on silhouette coefficient. J. Comput. Appl. 30(2), 139\u2013141 (2010)","journal-title":"J. Comput. Appl."}],"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\/978-981-97-2242-6_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,24]],"date-time":"2024-04-24T23:09:49Z","timestamp":1714000189000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-2242-6_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819722419","9789819722426"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-2242-6_20","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"25 April 2024","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":"Taipei","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Taiwan","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":"7 May 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 May 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pakdd2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/pakdd2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}