{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T12:05:47Z","timestamp":1777982747903,"version":"3.51.4"},"reference-count":23,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2025,7,29]],"date-time":"2025-07-29T00:00:00Z","timestamp":1753747200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,7,29]],"date-time":"2025-07-29T00:00:00Z","timestamp":1753747200000},"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":["Int J Data Sci Anal"],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1007\/s41060-025-00874-0","type":"journal-article","created":{"date-parts":[[2025,7,29]],"date-time":"2025-07-29T16:04:36Z","timestamp":1753805076000},"page":"6973-6983","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Robust sparse k-means clustering against STOF observations"],"prefix":"10.1007","volume":"20","author":[{"given":"Ariel Basso","family":"Madjoukeng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Edith B\u00e9lise","family":"Kenmogne","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Beno\u00eet","family":"Fr\u00e9nay","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,7,29]]},"reference":[{"key":"874_CR1","unstructured":"MacQueen, J. et\u00a0al.: Some methods for classification and analysis of multivariate observations. In Proceedings of the fifth Berkeley symposium on mathematical statistics and probability, volume\u00a01, pages 281\u2013297. Oakland, CA (1967)"},{"key":"874_CR2","first-page":"226","volume":"96","author":"M Ester","year":"1996","unstructured":"Ester, M., Kriegel, H.-P., Sander, J., Xiaowei, X., et al.: A density-based algorithm for discovering clusters in large spatial databases with noise. KDD 96, 226\u2013231 (1996)","journal-title":"KDD"},{"key":"874_CR3","unstructured":"Khan, I.K., Daud, H., Zainuddin, N., Sokkalingam, R., Abdussamad, A., A.S. Iqbal, M., Zafar, M., Ullah, A., Elahi, M., Suleiman, A.A.: Exploring k-means clustering efficiency: accuracy and computational time across multiple datasets. J. Adv. Res. Appl. Sci. Eng. Technol. 62(3), 57\u201369 (2024)"},{"key":"874_CR4","doi-asserted-by":"crossref","unstructured":"Khan, I.K., Daud, H.B., Zainuddin, N.B., Sokkalingam, R., Abdussamad, M., A., Inayat, A.: Addressing limitations of the k-means clustering algorithm: outliers, non-spherical data, and optimal cluster selection. AIMS Math 9, 25070\u201325097 (2024)","DOI":"10.3934\/math.20241222"},{"key":"874_CR5","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":"874_CR6","doi-asserted-by":"crossref","unstructured":"Ahmed, M., Mahmood, A.N.: A novel approach for outlier detection and clustering improvement. In: 2013 IEEE 8th Conference on Industrial Electronics and Applications (iciea). IEEE , pp. 577\u2013582 (2013)","DOI":"10.1109\/ICIEA.2013.6566435"},{"issue":"490","key":"874_CR7","doi-asserted-by":"publisher","first-page":"713","DOI":"10.1198\/jasa.2010.tm09415","volume":"105","author":"DM Witten","year":"2010","unstructured":"Witten, D.M., Tibshirani, R.: A framework for feature selection in clustering. J. Am. Stat. Assoc. 105(490), 713\u2013726 (2010)","journal-title":"J. Am. Stat. Assoc."},{"key":"874_CR8","doi-asserted-by":"publisher","first-page":"246","DOI":"10.1016\/j.aej.2025.01.034","volume":"118","author":"IK Khan","year":"2025","unstructured":"Khan, I.K., Daud, H., Zainuddin, N., Sokkalingam, R.: Standardizing reference data in gap statistic for selection optimal number of cluster in k-means algorithm. Alex. Eng. J. 118, 246\u2013260 (2025)","journal-title":"Alex. Eng. J."},{"key":"874_CR9","doi-asserted-by":"publisher","first-page":"100504","DOI":"10.1016\/j.eij.2024.100504","volume":"27","author":"IK Khan","year":"2024","unstructured":"Khan, I.K., Daud, H.B., Zainuddin, N.B., Sokkalingam, R., Farooq, M., Baig, M.E., Ayub, G., Zafar, M.: Determining the optimal number of clusters by enhanced gap statistic in k-mean algorithm. Egypt. Inform. J. 27, 100504 (2024)","journal-title":"Egypt. Inform. J."},{"issue":"2","key":"874_CR10","doi-asserted-by":"publisher","first-page":"411","DOI":"10.1111\/1467-9868.00293","volume":"63","author":"R Tibshirani","year":"2001","unstructured":"Tibshirani, R., Walther, G., Hastie, T.: Estimating the number of clusters in a data set via the gap statistic. J. Royal Stat. Society: Series b (Stat. Methodol.) 63(2), 411\u2013423 (2001)","journal-title":"J. Royal Stat. Society: Series b (Stat. Methodol.)"},{"key":"874_CR11","unstructured":"Arthur, D., Vassilvitskii, S.: k-means++: The advantages of careful seeding. Technical report, Stanford (2006)"},{"issue":"11","key":"874_CR12","doi-asserted-by":"publisher","first-page":"994","DOI":"10.1016\/j.patrec.2009.04.013","volume":"30","author":"M Al Hasan","year":"2009","unstructured":"Al Hasan, M., Chaoji, V., Salem, S., Zaki, M.J.: Robust partitional clustering by outlier and density insensitive seeding. Patt. Recogn. Lett. 30(11), 994\u20131002 (2009)","journal-title":"Patt. Recogn. Lett."},{"key":"874_CR13","volume-title":"Understanding why and how. A modern introduction to probability and statistics","author":"FM Dekking","year":"2006","unstructured":"Dekking, F.M., Cornelis, K., Hendrik, P.L., Ludolf, E.M.: Understanding why and how. A modern introduction to probability and statistics. Springer, Berlin (2006)"},{"issue":"8","key":"874_CR14","doi-asserted-by":"publisher","first-page":"6365","DOI":"10.1016\/j.jksuci.2021.07.003","volume":"34","author":"NHMM Shrifan","year":"2022","unstructured":"Shrifan, N.H.M.M., Akbar, M.F., Isa, N.A.M.: An adaptive outlier removal aided k-means clustering algorithm. J. King Saud Univer.-Comput. Inform. Sci. 34(8), 6365\u20136376 (2022)","journal-title":"J. King Saud Univer.-Comput. Inform. Sci."},{"key":"874_CR15","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1016\/j.patrec.2020.11.015","volume":"142","author":"A Vouros","year":"2021","unstructured":"Vouros, A., Vasilaki, E.: A semi-supervised sparse k-means algorithm. Patt. Recogn. Lett. 142, 65\u201371 (2021)","journal-title":"Patt. Recogn. Lett."},{"key":"874_CR16","first-page":"905","volume":"13","author":"\u0160 Brodinov\u00e1","year":"2019","unstructured":"Brodinov\u00e1, \u0160, Filzmoser, P., Ortner, T., Breiteneder, C., Rohm, M.: Robust and sparse k-means clustering for high-dimensional data. Adv. Data Anal. Classif. 13, 905\u2013932 (2019)","journal-title":"Adv. Data Anal. Classif."},{"key":"874_CR17","unstructured":"Kondo, Y., Salibian-Barrera, M., Zamar, R.: A robust and sparse k-means clustering algorithm; 2012. Available: arXiv preprint arXiv:1201.6082"},{"key":"874_CR18","doi-asserted-by":"crossref","unstructured":"Liu, F.T., Ting, K.M., Zhou, Z.-H.: Isolation forest. In 2008 eighth IEEE international conference on data mining. IEEE, pp 413\u2013422 (2008)","DOI":"10.1109\/ICDM.2008.17"},{"key":"874_CR19","doi-asserted-by":"crossref","unstructured":"Madjoukeng, A.B., Kenmogne, E.B., Frenay, B.: Fast k-means with stable instance sets. In: 2024 International Joint Conference on Neural Networks (IJCNN). IEEE, pp. 1\u20138 (2024)","DOI":"10.1109\/IJCNN60899.2024.10650923"},{"issue":"4","key":"874_CR20","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1007\/BF02289263","volume":"18","author":"RL Thorndike","year":"1953","unstructured":"Thorndike, R.L.: Who belongs in the family? Psychometrika 18(4), 267\u2013276 (1953)","journal-title":"Psychometrika"},{"issue":"2","key":"874_CR21","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1007\/s10618-024-01086-z","volume":"39","author":"BVS Vinces","year":"2025","unstructured":"Vinces, B.V.S., Schubert, E., Zimek, A., Cordeiro, R.L.F.: A comparative evaluation of clustering-based outlier detection. Data Min. Knowl. Disc. 39(2), 13 (2025)","journal-title":"Data Min. Knowl. Disc."},{"key":"874_CR22","unstructured":"Pei, Y., Za\u00efane, O.: A synthetic data generator for clustering and outlier analysis. (2006)"},{"issue":"11","key":"874_CR23","doi-asserted-by":"publisher","first-page":"2230","DOI":"10.3390\/electronics14112230","volume":"14","author":"L Petricioli","year":"2025","unstructured":"Petricioli, L., Humski, L., Vrani\u0107, M.: Preserving clusters in synthetic data sets based on correlations and distributions. Electronics 14(11), 2230 (2025)","journal-title":"Electronics"}],"container-title":["International Journal of Data Science and Analytics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s41060-025-00874-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s41060-025-00874-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s41060-025-00874-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,4]],"date-time":"2025-11-04T10:30:00Z","timestamp":1762252200000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s41060-025-00874-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,29]]},"references-count":23,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["874"],"URL":"https:\/\/doi.org\/10.1007\/s41060-025-00874-0","relation":{"has-preprint":[{"id-type":"doi","id":"10.36227\/techrxiv.174114537.78354861\/v1","asserted-by":"object"}]},"ISSN":["2364-415X","2364-4168"],"issn-type":[{"value":"2364-415X","type":"print"},{"value":"2364-4168","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,29]]},"assertion":[{"value":"27 March 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 July 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 July 2025","order":3,"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 they have no conflict of interest","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}