{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,1,21]],"date-time":"2024-01-21T00:07:07Z","timestamp":1705795627301},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,11,24]],"date-time":"2023-11-24T00:00:00Z","timestamp":1700784000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,11,24]],"date-time":"2023-11-24T00:00:00Z","timestamp":1700784000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Ministry of Science and Technology","award":["MOST 105-2118-M-305-003"],"award-info":[{"award-number":["MOST 105-2118-M-305-003"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Stat Comput"],"published-print":{"date-parts":[[2024,2]]},"DOI":"10.1007\/s11222-023-10355-8","type":"journal-article","created":{"date-parts":[[2023,11,24]],"date-time":"2023-11-24T07:02:36Z","timestamp":1700809356000},"update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Randomized self-updating process for clustering large-scale data"],"prefix":"10.1007","volume":"34","author":[{"given":"Shang-Ying","family":"Shiu","sequence":"first","affiliation":[]},{"given":"Yen-Shiu","family":"Chin","sequence":"additional","affiliation":[]},{"given":"Szu-Han","family":"Lin","sequence":"additional","affiliation":[]},{"given":"Ting-Li","family":"Chen","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,11,24]]},"reference":[{"key":"10355_CR1","doi-asserted-by":"crossref","unstructured":"Adams, A., Gelfand, N., Dolson, J., Levoy, M.: Gaussian kd-trees for fast high-dimensional filtering. In: ACM SIGGRAPH 2009 papers, pp. 1\u201312 (2009)","DOI":"10.1145\/1576246.1531327"},{"key":"10355_CR2","unstructured":"Barton, T.: Clustering benchmarks (2015). https:\/\/github.com\/deric\/clustering-benchmark"},{"issue":"6","key":"10355_CR3","doi-asserted-by":"publisher","first-page":"671","DOI":"10.1080\/17445760.2018.1446210","volume":"34","author":"M Bendechache","year":"2019","unstructured":"Bendechache, M., Tari, A.K., Kechadi, M.T.: Parallel and distributed clustering framework for big spatial data mining. Int. J. Parallel Emergent Distrib. Syst. 34(6), 671\u2013689 (2019)","journal-title":"Int. J. Parallel Emergent Distrib. Syst."},{"issue":"1","key":"10355_CR4","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1007\/s10463-013-0443-8","volume":"67","author":"TL Chen","year":"2015","unstructured":"Chen, T.L.: On the convergence and consistency of the blurring mean-shift process. Ann. Inst. Stat. Math. 67(1), 157\u2013176 (2015)","journal-title":"Ann. Inst. Stat. Math."},{"issue":"15","key":"10355_CR5","doi-asserted-by":"publisher","first-page":"3047","DOI":"10.1080\/00949655.2014.949715","volume":"85","author":"JH Chen","year":"2015","unstructured":"Chen, J.H., Hung, W.L.: An automatic clustering algorithm for probability density functions. J. Stat. Comput. Simul. 85(15), 3047\u20133063 (2015)","journal-title":"J. Stat. Comput. Simul."},{"key":"10355_CR6","unstructured":"Chen, T.L., Shiu, S.Y.: A clustering algorithm by self-updating process. In: JSM Proceedings, Statistical Computing Section, Salt Lake City, Utah, pp. 2034\u20132038 (2007)"},{"issue":"1","key":"10355_CR7","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1214\/13-AOAS680","volume":"8","author":"TL Chen","year":"2014","unstructured":"Chen, T.L., Hsieh, D.N., Hung, H., Tu, I.P., Wu, P.S., Wu, Y.M., Chang, W.H., Huang, S.Y.: $$\\gamma $$-SUP: a clustering algorithm for cryo-electron microscopy images of asymmetric particles. Ann. Appl. Stat. 8(1), 259\u2013285 (2014)","journal-title":"Ann. Appl. Stat."},{"key":"10355_CR8","doi-asserted-by":"publisher","first-page":"109,238","DOI":"10.1016\/j.patcog.2022.109238","volume":"136","author":"S Ding","year":"2023","unstructured":"Ding, S., Li, C., Xu, X., Ding, L., Zhang, J., Guo, L., Shi, T.: A sampling-based density peaks clustering algorithm for large-scale data. Pattern Recogn. 136, 109,238 (2023)","journal-title":"Pattern Recogn."},{"key":"10355_CR9","doi-asserted-by":"crossref","unstructured":"Dong, W., Moses, C., Li, K.: Efficient k-nearest neighbor graph construction for generic similarity measures. In: Proceedings of the 20th International Conference on World Wide Web, pp. 577\u2013586 (2011)","DOI":"10.1145\/1963405.1963487"},{"key":"10355_CR10","doi-asserted-by":"publisher","first-page":"104,743","DOI":"10.1016\/j.engappai.2022.104743","volume":"110","author":"AE Ezugwu","year":"2022","unstructured":"Ezugwu, A.E., Ikotun, A.M., Oyelade, O.O., Abualigah, L., Agushaka, J.O., Eke, C.I., Akinyelu, A.A.: A comprehensive survey of clustering algorithms: state-of-the-art machine learning applications, taxonomy, challenges, and future research prospects. Eng. Appl. Artif. Intell. 110, 104,743 (2022)","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10355_CR11","doi-asserted-by":"publisher","first-page":"100,722","DOI":"10.1016\/j.softx.2021.100722","volume":"15","author":"M Gagolewski","year":"2021","unstructured":"Gagolewski, M.: genieclust: Fast and robust hierarchical clustering. SoftwareX 15, 100,722 (2021)","journal-title":"SoftwareX"},{"key":"10355_CR12","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1016\/j.ins.2016.05.003","volume":"363","author":"M Gagolewski","year":"2016","unstructured":"Gagolewski, M., Bartoszuk, M., Cena, A.: Genie: a new, fast, and outlier-resistant hierarchical clustering algorithm. Inf. Sci. 363, 8\u201323 (2016)","journal-title":"Inf. Sci."},{"issue":"2","key":"10355_CR13","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1145\/276305.276312","volume":"27","author":"S Guha","year":"1998","unstructured":"Guha, S., Rastogi, R., Shim, K.: Cure: an efficient clustering algorithm for large databases. ACM SIGMOD Rec. 27(2), 73\u201384 (1998)","journal-title":"ACM SIGMOD Rec."},{"key":"10355_CR14","unstructured":"Hahsler, M., Piekenbrock, M.: dbscan: Density-based spatial clustering of applications with noise (DBSCAN) and related algorithms (2022). https:\/\/CRAN.R-project.org\/package=dbscan. R package version 1.1-10"},{"key":"10355_CR15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.18637\/jss.v091.i01","volume":"91","author":"M Hahsler","year":"2019","unstructured":"Hahsler, M., Piekenbrock, M., Doran, D.: dbscan: Fast density-based clustering with r. J. Stat. Softw. 91, 1\u201330 (2019)","journal-title":"J. Stat. Softw."},{"issue":"10","key":"10355_CR16","doi-asserted-by":"publisher","first-page":"2259","DOI":"10.1080\/02664763.2012.706268","volume":"39","author":"WL Hung","year":"2012","unstructured":"Hung, W.L., Chang-Chien, S.J., Yang, M.S.: Self-updating clustering algorithm for estimating the parameters in mixtures of von Mises distributions. J. Appl. Stat. 39(10), 2259\u20132274 (2012)","journal-title":"J. Appl. Stat."},{"key":"10355_CR17","doi-asserted-by":"crossref","unstructured":"Ikotun, A.M., Ezugwu, A.E., Abualigah, L., Abuhaija, B., Heming, J.: K-means clustering algorithms: a comprehensive review, variants analysis, and advances in the era of big data. Inf. Sci. (2022)","DOI":"10.1016\/j.ins.2022.11.139"},{"key":"10355_CR18","volume-title":"Finding Groups in Data: An Introduction to Cluster Analysis","author":"L Kaufman","year":"2009","unstructured":"Kaufman, L., Rousseeuw, P.J.: Finding Groups in Data: An Introduction to Cluster Analysis, vol. 344. John Wiley & Sons, London (2009)"},{"issue":"11","key":"10355_CR19","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278\u20132324 (1998)","journal-title":"Proc. IEEE"},{"key":"10355_CR20","unstructured":"Lin, S.H., Chen, T.L., Tu, I.P.: Distributed $$t$$-sne. (manuscript) (2023)"},{"issue":"1","key":"10355_CR21","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1109\/TNN.2007.901277","volume":"19","author":"H Lu","year":"2008","unstructured":"Lu, H., Plataniotis, K.N., Venetsanopoulos, A.N.: MPCA: Multilinear principal component analysis of tensor objects. IEEE Trans. Neural Netw. 19(1), 18\u201339 (2008)","journal-title":"IEEE Trans. Neural Netw."},{"key":"10355_CR22","unstructured":"Maechler, M., Rousseeuw, P., Struyf, A., Hubert, M., Hornik, K.: cluster: Cluster analysis basics and extensions (2022). https:\/\/CRAN.R-project.org\/package=cluster. R package version 2.1.3"},{"key":"10355_CR23","doi-asserted-by":"crossref","unstructured":"March, W.B., Ram, P., Gray, A.G.: Fast Euclidean minimum spanning tree: algorithm, analysis, and applications. In: Proceedings of the 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 603\u2013612 (2010)","DOI":"10.1145\/1835804.1835882"},{"issue":"5","key":"10355_CR24","doi-asserted-by":"publisher","first-page":"1003","DOI":"10.1109\/TKDE.2002.1033770","volume":"14","author":"RT Ng","year":"2002","unstructured":"Ng, R.T., Han, J.: Clarans: a method for clustering objects for spatial data mining. IEEE Trans. Knowl. Data Eng. 14(5), 1003\u20131016 (2002)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"issue":"6191","key":"10355_CR25","doi-asserted-by":"publisher","first-page":"1492","DOI":"10.1126\/science.1242072","volume":"344","author":"A Rodriguez","year":"2014","unstructured":"Rodriguez, A., Laio, A.: Clustering by fast search and find of density peaks. Science 344(6191), 1492\u20131496 (2014)","journal-title":"Science"},{"key":"10355_CR26","doi-asserted-by":"publisher","first-page":"101,804","DOI":"10.1016\/j.is.2021.101804","volume":"101","author":"E Schubert","year":"2021","unstructured":"Schubert, E., Rousseeuw, P.J.: Fast and eager k-medoids clustering: O (k) runtime improvement of the PAM, CLARA, and CLARANS algorithms. Inf. Syst. 101, 101,804 (2021)","journal-title":"Inf. Syst."},{"issue":"5","key":"10355_CR27","doi-asserted-by":"publisher","first-page":"1010","DOI":"10.1080\/00949655.2015.1049605","volume":"86","author":"SY Shiu","year":"2016","unstructured":"Shiu, S.Y., Chen, T.L.: On the strengths of the self-updating process clustering algorithm. J. Stat. Comput. Simul. 86(5), 1010\u20131031 (2016)","journal-title":"J. Stat. Comput. Simul."},{"key":"10355_CR28","doi-asserted-by":"crossref","unstructured":"Sun, T., Shu, C., Li, F., Yu, H., Ma, L., Fang, Y.: An efficient hierarchical clustering method for large datasets with map-reduce. In: 2009 International Conference on Parallel and Distributed Computing, Applications and Technologies, pp. 494\u2013499. IEEE (2009)","DOI":"10.1109\/PDCAT.2009.46"},{"key":"10355_CR29","unstructured":"Van\u00a0der Maaten, L., Hinton, G.: Visualizing data using t-sne. J Mach. Learn. Res. 9(11) (2008)"},{"issue":"2","key":"10355_CR30","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1007\/s10700-018-9290-7","volume":"18","author":"T Vovan","year":"2019","unstructured":"Vovan, T.: An improved fuzzy time series forecasting model using variations of data. Fuzzy Optim. Decis. Mak. 18(2), 151\u2013173 (2019)","journal-title":"Fuzzy Optim. Decis. Mak."},{"key":"10355_CR31","unstructured":"Wu, W., Shiu, S.Y.: supc: The self-updating process clustering algorithms (2021). https:\/\/CRAN.R-project.org\/package=supc. R package version 0.2.6.2"}],"container-title":["Statistics and Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11222-023-10355-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11222-023-10355-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11222-023-10355-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,20]],"date-time":"2024-01-20T10:20:29Z","timestamp":1705746029000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11222-023-10355-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,24]]},"references-count":31,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,2]]}},"alternative-id":["10355"],"URL":"https:\/\/doi.org\/10.1007\/s11222-023-10355-8","relation":{},"ISSN":["0960-3174","1573-1375"],"issn-type":[{"value":"0960-3174","type":"print"},{"value":"1573-1375","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,24]]},"assertion":[{"value":"22 March 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 October 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 November 2023","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 no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"47"}}