{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T02:11:20Z","timestamp":1762567880830,"version":"build-2065373602"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"15","license":[{"start":{"date-parts":[[2025,9,18]],"date-time":"2025-09-18T00:00:00Z","timestamp":1758153600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,18]],"date-time":"2025-09-18T00:00:00Z","timestamp":1758153600000},"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":["Appl Intell"],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1007\/s10489-025-06770-1","type":"journal-article","created":{"date-parts":[[2025,9,18]],"date-time":"2025-09-18T13:21:59Z","timestamp":1758201719000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["PretopoMD: pretopology-based mixed data hierarchical clustering"],"prefix":"10.1007","volume":"55","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6089-6185","authenticated-orcid":false,"given":"Loup-No\u00e9","family":"Levy","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6773-221X","authenticated-orcid":false,"given":"Guillaume","family":"Guerard","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2249-7727","authenticated-orcid":false,"given":"Sonia","family":"Djebali","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8949-8030","authenticated-orcid":false,"given":"Soufian Ben","family":"Amor","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,9,18]]},"reference":[{"key":"6770_CR1","doi-asserted-by":"crossref","unstructured":"Abumalloh R, Alrahhal M, El-Haggar N, Alsumayt A, Alfawaer Z, Aljameel S (2024) Exploring individuals\u2019 experiences with security attacks: a text mining and qualitative study. Emerg Sci J 8(1)","DOI":"10.28991\/ESJ-2024-08-01-010"},{"key":"6770_CR2","doi-asserted-by":"publisher","first-page":"31883","DOI":"10.1109\/ACCESS.2019.2903568","volume":"7","author":"A Ahmad","year":"2019","unstructured":"Ahmad A, Khan SS (2019) Survey of state-of-the-art mixed data clustering algorithms. IEEE Access 7:31883\u201331902","journal-title":"IEEE Access"},{"key":"6770_CR3","doi-asserted-by":"publisher","first-page":"100850","DOI":"10.1016\/j.seps.2020.100850","volume":"73","author":"G Caruso","year":"2021","unstructured":"Caruso G, Gattone S, Fortuna F, Di Battista T (2021) Cluster analysis for mixed data: an application to credit risk evaluation. Socioecon Plann Sci 73:100850","journal-title":"Socioecon Plann Sci"},{"key":"6770_CR4","doi-asserted-by":"publisher","first-page":"644724","DOI":"10.3389\/fmed.2021.644724","volume":"8","author":"L Han","year":"2021","unstructured":"Han L, Shen P, Yan J, Huang Y, Ba X, Lin W, Wang H, Huang Y, Qin K, Wang Y et al (2021) Exploring the clinical characteristics of covid-19 clusters identified using factor analysis of mixed data-based cluster analysis. Front Med 8:644724","journal-title":"Front Med"},{"issue":"28","key":"6770_CR5","doi-asserted-by":"publisher","first-page":"4548","DOI":"10.1002\/sim.7371","volume":"36","author":"D McParland","year":"2017","unstructured":"McParland D, Phillips CM, Brennan L, Roche HM, Gormley IC (2017) Clustering high-dimensional mixed data to uncover sub-phenotypes: joint analysis of phenotypic and genotypic data. Stat Med 36(28):4548\u20134569","journal-title":"Stat Med"},{"key":"6770_CR6","doi-asserted-by":"crossref","unstructured":"Yu W, Qiang G, Xiao-li L (2006) A kernel aggregate clustering approach for mixed data set and its application in customer segmentation. In: 2006 international conference on management science and engineering. IEEE, pp 121\u2013124","DOI":"10.1109\/ICMSE.2006.313893"},{"issue":"3","key":"6770_CR7","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1023\/A:1009769707641","volume":"2","author":"Z Huang","year":"1998","unstructured":"Huang Z (1998) Extensions to the k-means algorithm for clustering large data sets with categorical values. Data Min Knowl Disc 2(3):283\u2013304","journal-title":"Data Min Knowl Disc"},{"key":"6770_CR8","unstructured":"Huang Z (1997) Clustering large data sets with mixed numeric and categorical values. In: Proceedings of the 1st Pacific-asia Conference on Knowledge Discovery and Data mining, (PAKDD). Citeseer, pp 21\u201334"},{"issue":"3","key":"6770_CR9","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1023\/A:1024016609528","volume":"52","author":"DS Modha","year":"2003","unstructured":"Modha DS, Spangler WS (2003) Feature weighting in k-means clustering. Mach Learn 52(3):217\u2013237","journal-title":"Mach Learn"},{"key":"6770_CR10","unstructured":"Biernacki C (2016) Bigstat for big data: big data clustering through the bigstat saas platform. In: Journ\u00e9e scientifique big data & data science"},{"issue":"3","key":"6770_CR11","doi-asserted-by":"publisher","first-page":"419","DOI":"10.1007\/s10994-016-5575-7","volume":"105","author":"A Foss","year":"2016","unstructured":"Foss A, Markatou M, Ray B, Heching A (2016) A semiparametric method for clustering mixed data. Mach Learn 105(3):419\u2013458","journal-title":"Mach Learn"},{"issue":"2","key":"6770_CR12","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1007\/s11634-016-0238-x","volume":"10","author":"D McParland","year":"2016","unstructured":"McParland D, Gormley IC (2016) Model based clustering for mixed data: clustmd. Adv Data Anal Classif 10(2):155\u2013169","journal-title":"Adv Data Anal Classif"},{"issue":"2","key":"6770_CR13","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1111\/j.1475-4754.1983.tb00671.x","volume":"25","author":"G Philip","year":"1983","unstructured":"Philip G, Ottaway B (1983) Mixed data cluster analysis: an illustration using cypriot hooked-tang weapons. Archaeometry 25(2):119\u2013133","journal-title":"Archaeometry"},{"key":"6770_CR14","first-page":"14008","volume":"38","author":"S Liu","year":"2024","unstructured":"Liu S, Cao W, Fu R, Yang K, Yu Z (2024) Rpsc: robust pseudo-labeling for semantic clustering. Proc AAAI Conf Artif Intell 38:14008\u201314016","journal-title":"Proc AAAI Conf Artif Intell"},{"issue":"7","key":"6770_CR15","doi-asserted-by":"publisher","first-page":"197334","DOI":"10.1007\/s11704-024-40004-w","volume":"19","author":"Z Yu","year":"2025","unstructured":"Yu Z, Dong Z, Yu C, Yang K, Fan Z, Chen CP (2025) A review on multi-view learning. Front Comp Sci 19(7):197334","journal-title":"Front Comp Sci"},{"key":"6770_CR16","doi-asserted-by":"publisher","first-page":"109573","DOI":"10.1016\/j.engappai.2024.109573","volume":"139","author":"I Iqbal","year":"2025","unstructured":"Iqbal I, Ullah I, Peng T, Wang W, Ma N (2025) An end-to-end deep convolutional neural network-based data-driven fusion framework for identification of human induced pluripotent stem cell-derived endothelial cells in photomicrographs. Eng Appl Artif Intell 139:109573","journal-title":"Eng Appl Artif Intell"},{"issue":"1","key":"6770_CR17","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1109\/TKDE.2023.3283425","volume":"36","author":"Z Yu","year":"2023","unstructured":"Yu Z, Zhong Z, Yang K, Cao W, Chen CP (2023) Broad learning autoencoder with graph structure for data clustering. IEEE Trans Knowl Data Eng 36(1):49\u201361","journal-title":"IEEE Trans Knowl Data Eng"},{"issue":"3","key":"6770_CR18","doi-asserted-by":"publisher","first-page":"716","DOI":"10.28991\/HIJ-2024-05-03-012","volume":"5","author":"C Chenghu","year":"2024","unstructured":"Chenghu C, Thammano A (2024) A novel classification model based on hybrid k-means and neural network for classification problems. HighTech and Innovation Journal 5(3):716\u2013729","journal-title":"HighTech and Innovation Journal"},{"issue":"12","key":"6770_CR19","doi-asserted-by":"publisher","first-page":"12369","DOI":"10.1109\/TKDE.2023.3271120","volume":"35","author":"Y Shi","year":"2023","unstructured":"Shi Y, Yang K, Yu Z, Chen CP, Zeng H (2023) Adaptive ensemble clustering with boosting bls-based autoencoder. IEEE Trans Knowl Data Eng 35(12):12369\u201312383","journal-title":"IEEE Trans Knowl Data Eng"},{"issue":"2","key":"6770_CR20","doi-asserted-by":"publisher","first-page":"394","DOI":"10.28991\/ESJ-2024-08-02-02","volume":"8","author":"AS Yaro","year":"2024","unstructured":"Yaro AS, Maly F, Prazak P, Mal\u1ef3 K (2024) Improved fingerprint-based localization based on sequential hybridization of clustering algorithms. Emerg Sci J 8(2):394\u2013406","journal-title":"Emerg Sci J"},{"issue":"2","key":"6770_CR21","first-page":"137","volume":"4","author":"B Escofier","year":"1979","unstructured":"Escofier B (1979) Traitement simultan\u00e9 de variables qualitatives et quantitatives en analyse factorielle. Cahiers de l\u2019Analyse des Donn\u00e9es 4(2):137\u2013146","journal-title":"Cahiers de l\u2019Analyse des Donn\u00e9es"},{"issue":"201","key":"6770_CR22","first-page":"1","volume":"22","author":"Y Wang","year":"2021","unstructured":"Wang Y, Huang H, Rudin C, Shaposhnik Y (2021) Understanding how dimension reduction tools work: An empirical approach to deciphering t-sne, umap, trimap, and pacmap for data visualization. J Mach Learn Res 22(201):1\u201373","journal-title":"J Mach Learn Res"},{"issue":"1","key":"6770_CR23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1080\/03610927408827101","volume":"3","author":"T Cali\u0144ski","year":"1974","unstructured":"Cali\u0144ski T, Harabasz J (1974) A dendrite method for cluster analysis. Comm Stat-Theor Methods 3(1):1\u201327","journal-title":"Comm Stat-Theor Methods"},{"key":"6770_CR24","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1016\/0377-0427(87)90125-7","volume":"20","author":"PJ Rousseeuw","year":"1987","unstructured":"Rousseeuw PJ (1987) Silhouettes: a graphical aid to the interpretation and validation of cluster analysis. J Comput Appl Math 20:53\u201365","journal-title":"J Comput Appl Math"},{"key":"6770_CR25","doi-asserted-by":"publisher","first-page":"224","DOI":"10.1109\/TPAMI.1979.4766909","volume":"2","author":"DL Davies","year":"1979","unstructured":"Davies DL, Bouldin DW (1979) A cluster separation measure. IEEE Trans Pattern Anal Mach Intell 2:224\u2013227","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"6770_CR26","first-page":"27","volume":"7","author":"J-P Auray","year":"2009","unstructured":"Auray J-P, Bonnevay S, Bui M, Duru G, Lamure M (2009) Pr\u00e9topologie et applications: un \u00e9tat de l\u2019art. Studia Inform Univ 7:27\u201344","journal-title":"Studia Inform Univ"},{"key":"6770_CR27","unstructured":"Le TV (2007) Classification pr\u00e9topologique des donn\u00e9es: application \u00e0 l\u2019analyse des trajectoires patients. PhD thesis, Lyon 1"},{"key":"6770_CR28","unstructured":"Laborde J (2019) Pretopology, a mathematical tool for structuring complex systems: methods, algorithms and applications. PhD thesis. Paris Sciences et Lettres (ComUE)"},{"key":"6770_CR29","unstructured":"Belmandt, Z., Fortet RM (1993) Manuel de pr\u00e9topologie et ses applications: sciences humaines et sociales, r\u00e9seaux, jeux, reconnaissance des formes, processus et mod\u00e8les, classification, imagerie, math\u00e9matiques"},{"issue":"3","key":"6770_CR30","doi-asserted-by":"publisher","first-page":"90081","DOI":"10.1371\/journal.pone.0090081","volume":"9","author":"KB Gorman","year":"2014","unstructured":"Gorman KB, Williams TD, Fraser WR (2014) Ecological sexual dimorphism and environmental variability within a community of antarctic penguins (genus pygoscelis). PLoS ONE 9(3):90081","journal-title":"PLoS ONE"},{"key":"6770_CR31","doi-asserted-by":"crossref","unstructured":"Kramer O, Kramer O (2016) Scikit-learn. Mach Learn Evol Strat 45\u201353","DOI":"10.1007\/978-3-319-33383-0_5"},{"key":"6770_CR32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.18637\/jss.v051.i12","volume":"51","author":"V Melnykov","year":"2012","unstructured":"Melnykov V, Chen W-C, Maitra R (2012) Mixsim: an r package for simulating data to study performance of clustering algorithms. J Stat Softw 51:1\u201325","journal-title":"J Stat Softw"},{"key":"6770_CR33","doi-asserted-by":"crossref","unstructured":"Costa E, Papatsouma I, Markos A (2022) Benchmarking distance-based partitioning methods for mixed-type data. Adv Data Anal Class 1\u201324","DOI":"10.1007\/s11634-022-00521-7"},{"key":"6770_CR34","doi-asserted-by":"crossref","unstructured":"Beyer K, Goldstein J, Ramakrishnan R, Shaft U (1999) When is \u201cnearest neighbor\u201d meaningful? In: Database Theory\u2014ICDT\u201999: 7th International Conference Jerusalem, Israel, January 10\u201312, 1999 Proceedings 7. Springer, pp 217\u2013235","DOI":"10.1007\/3-540-49257-7_15"},{"key":"6770_CR35","doi-asserted-by":"crossref","unstructured":"Verleysen M, Fran\u00e7ois D (2005) The curse of dimensionality in data mining and time series prediction. In: Computational intelligence and bioinspired systems: 8th International Work-Conference on Artificial Neural Networks, IWANN 2005, Vilanova i la Geltr\u00fa, Barcelona, Spain, June 8-10, 2005. Proceedings 8. Springer, pp 758\u2013770","DOI":"10.1007\/11494669_93"},{"key":"6770_CR36","doi-asserted-by":"crossref","unstructured":"Steinbach M, Ert\u00f6z L, Kumar V (2004) The challenges of clustering high dimensional data. New directions in statistical physics: econophysics, bioinformatics, and pattern recognition. pp 273\u2013309","DOI":"10.1007\/978-3-662-08968-2_16"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-025-06770-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-025-06770-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-025-06770-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T02:05:10Z","timestamp":1762567510000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-025-06770-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,18]]},"references-count":36,"journal-issue":{"issue":"15","published-print":{"date-parts":[[2025,10]]}},"alternative-id":["6770"],"URL":"https:\/\/doi.org\/10.1007\/s10489-025-06770-1","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"type":"print","value":"0924-669X"},{"type":"electronic","value":"1573-7497"}],"subject":[],"published":{"date-parts":[[2025,9,18]]},"assertion":[{"value":"6 July 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 September 2025","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of Interest\/Competing Interests"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics Approval and Consent to Participate"}},{"value":"All authors consent for publication.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for Publication"}}],"article-number":"973"}}