{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,30]],"date-time":"2025-04-30T02:30:22Z","timestamp":1745980222769,"version":"3.37.3"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2020,6,27]],"date-time":"2020-06-27T00:00:00Z","timestamp":1593216000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,6,27]],"date-time":"2020-06-27T00:00:00Z","timestamp":1593216000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SN COMPUT. SCI."],"published-print":{"date-parts":[[2020,7]]},"DOI":"10.1007\/s42979-020-00227-7","type":"journal-article","created":{"date-parts":[[2020,6,27]],"date-time":"2020-06-27T13:04:15Z","timestamp":1593263055000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["A Comparative Study of the Some Methods Used in Constructing Coresets for Clustering Large Datasets"],"prefix":"10.1007","volume":"1","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3351-8960","authenticated-orcid":false,"given":"Nguyen","family":"Le Hoang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Le Hong","family":"Trang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tran Khanh","family":"Dang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,6,27]]},"reference":[{"issue":"4","key":"227_CR1","doi-asserted-by":"publisher","first-page":"606","DOI":"10.1145\/1008731.1008736","volume":"51","author":"PK Agarwal","year":"2004","unstructured":"Agarwal PK, Procopiuc CM, Varadarajan KR. Approximating extent measures of points. J ACM. 2004;51(4):606\u201335.","journal-title":"J ACM."},{"key":"227_CR2","first-page":"1","volume":"52","author":"PK Agarwal","year":"2005","unstructured":"Agarwal PK, Procopiuc CM, Varadarajan KR. Geometric approximation via coresets. Comb Comput Geom. 2005;52:1\u201330.","journal-title":"Comb Comput Geom."},{"issue":"5","key":"227_CR3","doi-asserted-by":"publisher","first-page":"753","DOI":"10.1145\/290179.290180","volume":"45","author":"S Arora","year":"1998","unstructured":"Arora S. Polynomial time approximation schemes for Euclidean traveling salesman and other geometric problems. J Assoc Comput Mach. 1998;45(5):753\u201382.","journal-title":"J Assoc Comput Mach."},{"key":"227_CR4","unstructured":"Arthur D, Vassilvitskii S. k-Means++: the advantages of careful seeding. In: Proceedings of the eighteenth annual ACM-SIAM symposium on discrete algorithms, 2007, pp. 1027\u20131035."},{"key":"227_CR5","unstructured":"Bachem O, Lucic M, Krause A. Coresets for nonparametric estimation\u2014the case of DP-means. In: International Conference on Machine Learning (ICML), 2015."},{"key":"227_CR6","unstructured":"Bachem O, Lucic M, Lattanzi S. One-shot coresets: the case of k-clustering. In: International conference on articial intelligence and statistics (AISTATS), 2018."},{"key":"227_CR7","doi-asserted-by":"crossref","unstructured":"Bachem O, Lucic M, Krause A. Scalable and distributed clustering via lightweight coresets. In: International conference on knowledge discovery and data mining (KDD), 2018.","DOI":"10.1145\/3219819.3219973"},{"key":"227_CR8","unstructured":"Bachem O, Lucic M, Krause A. Practical coreset constructions for machine learning. arXiv preprint, 2017."},{"key":"227_CR9","doi-asserted-by":"crossref","unstructured":"Charikar M, O\u2019Callaghan L, Panigrahy. Better streaming algorithms for clustering problems. In: Proceedings of the 35th annual ACM symposium on theory of computing, 2003, pp. 30\u201339.","DOI":"10.1145\/780542.780548"},{"key":"227_CR10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2019\/8123259","volume":"2019","author":"TK Dang","year":"2019","unstructured":"Dang TK, Tran KTK. The meeting of acquaintances: a cost-efficient authentication scheme for light-weight objects with transient trust level and plurality approach. Secur Commun Netw. 2019;2019:1\u201318.","journal-title":"Secur Commun Netw"},{"key":"227_CR11","doi-asserted-by":"publisher","unstructured":"Frahling G, Sohler C. Coresets in dynamic geometric data streams. In: Proceedings of the thirty-seventh annual ACM symposium on theory of computing, pp. 209\u2013217, STOC 2005. https:\/\/doi.org\/10.1145\/1060590.1060622","DOI":"10.1145\/1060590.1060622"},{"key":"227_CR12","doi-asserted-by":"crossref","unstructured":"Feldman D, Monemizadeh M, Sohler C. A PTAS for k- means clustering based on weak coresets. In: Symposium on Computational Geometry (SoCG), ACM, 2007, pp 11\u201318.","DOI":"10.1145\/1247069.1247072"},{"key":"227_CR13","doi-asserted-by":"crossref","unstructured":"Feldman D, Monemizadeh M, Sohler C, Woodruff DP, Coresets and sketches for high dimensional subspace approximation problems. In: Symposium on discrete algorithms (SODA), Society for Industrial and Applied Mathematics, pp. 630\u2013649, 2010.","DOI":"10.1137\/1.9781611973075.53"},{"key":"227_CR14","unstructured":"Feldman D, Faulkner M, Krause A, Scalable training of mixture models via coresets. In: Advances in neural information processing systems (NIPS), 2011, pp. 2142\u20132150"},{"key":"227_CR15","doi-asserted-by":"crossref","unstructured":"Feldman D, Schmidt M, Sohler C, Turning big data into tiny data: constant-size coresets for k-means, PCA and projective clustering. In: Symposium on discrete algorithms (SODA), Society for industrial and applied mathematics, pp. 1434\u20131453, 2013.","DOI":"10.1137\/1.9781611973105.103"},{"key":"227_CR16","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1016\/0304-3975(85)90224-5","volume":"38","author":"TF Gonzalez","year":"1985","unstructured":"Gonzalez TF. Clustering to minimize the maximum inter-cluster distance. Theor Comput Sci. 1985;38:293\u2013306.","journal-title":"Theor Comput Sci."},{"key":"227_CR17","volume-title":"Geometric approximation algorithms","author":"S Har-Peled","year":"2011","unstructured":"Har-Peled S. Geometric approximation algorithms, vol. 173. Washington: American mathematical society Providence; 2011."},{"key":"227_CR18","doi-asserted-by":"crossref","unstructured":"Har-Peled S, Kushal A. Smaller coresets for k-median and k- means clustering. In: Symposium on computational geometry (SoCG), ACM, pp. 126\u2013134, 2005.","DOI":"10.1145\/1064092.1064114"},{"key":"227_CR19","doi-asserted-by":"crossref","unstructured":"Har-Peled S, Mazumdar S, On coresets for k-means and k-median clustering. In: Symposium on theory of computing (STOC), ACM, pp. 291\u2013300, 2004.","DOI":"10.1145\/1007352.1007400"},{"key":"227_CR20","doi-asserted-by":"publisher","unstructured":"Hoang NL, Dang TK, Trang LH, A Comparative Study of the Use of Coresets for Clustering Large Datasets. In: LNCS 11814 Future Data and Security Engineering, pp. 45-55, 2019. https:\/\/doi.org\/10.1007\/978-3-030-35653-8","DOI":"10.1007\/978-3-030-35653-8"},{"key":"227_CR21","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1109\/TIT.1982.1056489","volume":"28","author":"SP Lloyd","year":"1982","unstructured":"Lloyd SP. Least squares quantization in PCM. IEEE Trans Inf Theory. 1982;28:129\u201337.","journal-title":"IEEE Trans Inf Theory."},{"key":"227_CR22","unstructured":"Lucic M, Bachem O, Krause A, Strong coresets for hard and soft Bregman clustering with applications to exponential family mixtures. In: International conference on artificial intelligence and statistics (AISTATS), pp. 1\u20139, 2016."},{"key":"227_CR23","first-page":"1","volume":"18","author":"M Lucic","year":"2017","unstructured":"Lucic M, Faulkner M, Krause A. Training mixture models at scale via coresets. J Mach Learn. 2017;18:1\u201325.","journal-title":"J Mach Learn"},{"key":"227_CR24","doi-asserted-by":"crossref","unstructured":"Inaba M, Katoh N, Imai H, Applications of weighted Voronoi diagrams and randomization to variance-based k-clustering. In: Proceeding of 10th annual symposium on computational geometry, pp. 332\u2013339, 1994.","DOI":"10.1145\/177424.178042"},{"key":"227_CR25","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1007\/s004540010019","volume":"24","author":"J Matousek","year":"2000","unstructured":"Matousek J. On approximate geometric k-clustering. Discrete Comput Geometry. 2000;24:61\u201384.","journal-title":"Discrete Comput Geometry."},{"key":"227_CR26","doi-asserted-by":"publisher","unstructured":"Phan TN, Dang TK. A Lightweight Indexing Approach for Efficient Batch Similarity Processing with MapReduce. SN Comput Sci. 2020;1(1). https:\/\/doi.org\/10.1007\/s42979-019-0007-y.","DOI":"10.1007\/s42979-019-0007-y"},{"key":"227_CR27","doi-asserted-by":"publisher","first-page":"349","DOI":"10.1016\/j.eswa.2016.03.008","volume":"56","author":"F Ros","year":"2016","unstructured":"Ros F, Guillaume S. DENDIS: a new density-based sampling for clustering algorithm. Expert Syst Appl. 2016;56:349\u201359.","journal-title":"Expert Syst Appl."},{"key":"227_CR28","doi-asserted-by":"publisher","first-page":"543","DOI":"10.1007\/s10115-016-0946-8","volume":"50","author":"F Ros","year":"2017","unstructured":"Ros F, Guillaume S. DIDES: a fast and effective sampling for clustering algorithm. Knowl Inf Syst. 2017;50:543\u201368.","journal-title":"Knowl Inf Syst."},{"key":"227_CR29","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1016\/j.eswa.2018.03.052","volume":"105","author":"F Ros","year":"2018","unstructured":"Ros F, Guillaume S. ProTraS: a probabilistic traversing sampling algorithm. Expert Syst Appl. 2018;105:65\u201376.","journal-title":"Expert Syst Appl."},{"key":"227_CR30","doi-asserted-by":"publisher","first-page":"563","DOI":"10.1137\/0206041","volume":"6","author":"DJ Rosenkrantz","year":"1977","unstructured":"Rosenkrantz DJ, Stearns RE, Lewis PM II. An analysis of several Heuristics for the traveling salesman problem. SIAM J Comput. 1977;6:563\u201381.","journal-title":"SIAM J Comput."},{"key":"227_CR31","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1007\/978-3-030-03192-3_11","volume":"11251","author":"LH Trang","year":"2018","unstructured":"Trang LH, Ngoan PV, Duc NV. A sample-based algorithm for visual assessment of cluster tendency (VAT) with large datasets. Future Data Secur Eng LNCS. 2018;11251:145\u201357.","journal-title":"Future Data Secur Eng LNCS"},{"key":"227_CR32","doi-asserted-by":"publisher","unstructured":"Trang LH, Hoang NL, Dang TK. A farthest first traversal based sampling algorithm for k-clustering. In: 2020 14th international conference on ubiquitous information management and communication (IMCOM), Taichung, Taiwan, 2020, pp. 1-6. https:\/\/doi.org\/10.1109\/IMCOM48794.2020.9001738","DOI":"10.1109\/IMCOM48794.2020.9001738"},{"key":"227_CR33","unstructured":"Vega WFdl, Karpinski M, Kenyon C, Rabani Y. Approximation schemes for clustering problems. In: Proceedings of the 35th annual ACM symposium on theory of computing, pp. 50\u201358, 2003."},{"key":"227_CR34","unstructured":"https:\/\/cs.joensuu.fi\/sipu\/datasets. Accessed Jan 2020."},{"key":"227_CR35","unstructured":"https:\/\/github.com\/deric\/clustering-benchmark. Accessed Jan 2020."}],"container-title":["SN Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-020-00227-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42979-020-00227-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-020-00227-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,6,26]],"date-time":"2021-06-26T23:27:16Z","timestamp":1624750036000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42979-020-00227-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,6,27]]},"references-count":35,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2020,7]]}},"alternative-id":["227"],"URL":"https:\/\/doi.org\/10.1007\/s42979-020-00227-7","relation":{},"ISSN":["2662-995X","2661-8907"],"issn-type":[{"type":"print","value":"2662-995X"},{"type":"electronic","value":"2661-8907"}],"subject":[],"published":{"date-parts":[[2020,6,27]]},"assertion":[{"value":"6 May 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 June 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 June 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with Ethical Standards"}},{"value":"The authors report no conflicts of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of Interest"}}],"article-number":"215"}}