{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T01:34:27Z","timestamp":1777685667066,"version":"3.51.4"},"reference-count":41,"publisher":"SAGE Publications","issue":"1","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["HIS"],"published-print":{"date-parts":[[2020,3,23]]},"DOI":"10.3233\/his-190277","type":"journal-article","created":{"date-parts":[[2019,7,2]],"date-time":"2019-07-02T10:41:16Z","timestamp":1562064076000},"page":"35-53","source":"Crossref","is-referenced-by-count":1,"title":["Empirical evaluation of five algorithms for the initialization phase of the k-Means algorithm"],"prefix":"10.1177","volume":"16","author":[{"given":"Maria","family":"do Carmo Nicoletti","sequence":"first","affiliation":[{"name":"Centro Universit\u00e1rio C. Limpo Paulista, C. L. Paulista, SP, Brazil"},{"name":"Universidade Federal de S. Carlos, S. Carlos, SP, Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anderson Francisco","family":"de Oliveira","sequence":"additional","affiliation":[{"name":"Centro Universit\u00e1rio C. Limpo Paulista, C. L. Paulista, SP, Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","reference":[{"issue":"3","key":"10.3233\/HIS-190277_ref1","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1109\/TETC.2014.2330519","article-title":"A survey of clustering algorithms for big data: taxonomy and empirical analysis","volume":"2","author":"Fahad","year":"2014","journal-title":"IEEE Transactions on Emerging Topics in Computing"},{"key":"10.3233\/HIS-190277_ref2","unstructured":"A.F. Oliveira and M.C. Nicoletti, (2018) Favouring the k-means algorithm with initialization methods, In: Abraham A, Cherukuri A, Melin P, Gandhi N. (eds), Intelligent Systems Design and Applications. ISDA 2018 2018. Advances in Intelligent Systems and Computing, v. 940, Springer, Cham."},{"key":"10.3233\/HIS-190277_ref3","unstructured":"A.F. Oliveira, Favouring the performance of k-Means via centroid initialization methods, M. Sc.dissertation, UNIFACCAMP, C.L. Paulista, Brazil, 2018 (in Portuguese)."},{"key":"10.3233\/HIS-190277_ref4","first-page":"30","article-title":"Clustering aggregation","author":"Gionis","year":"2007","journal-title":"ACM Transactions on Knowledge. Discovery. Data (ACM TKDD)"},{"issue":"8","key":"10.3233\/HIS-190277_ref5","doi-asserted-by":"crossref","first-page":"651","DOI":"10.1016\/j.patrec.2009.09.011","article-title":"Data clustering: 50 years beyond K-means","volume":"31","author":"Jain","year":"2010","journal-title":"Pattern Recognition Letters"},{"issue":"3","key":"10.3233\/HIS-190277_ref6","doi-asserted-by":"crossref","first-page":"264","DOI":"10.1145\/331499.331504","article-title":"Data clustering: a review","volume":"31","author":"Jain","year":"1991","journal-title":"ACM Computing Surveys"},{"key":"10.3233\/HIS-190277_ref7","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/11590316_1","article-title":"Data clustering: a user\u2019s dilemma","volume":"3776","author":"Jain","year":"2005","journal-title":"Lecture Notes in Computer Science"},{"issue":"1","key":"10.3233\/HIS-190277_ref8","first-page":"33","article-title":"Design of efficient k-Means clustering algorithm with improved initial centroids","volume":"5","author":"Maedeh","year":"2013","journal-title":"International Journal of Engineering and Technology"},{"key":"10.3233\/HIS-190277_ref10","unstructured":"C.C. Aggarwal and C.K. Reddy, Data clustering algorithms and applications, Chapman & Hall\/CRC Data Mining and Knowledge Discovery Series, CRC Press, 2013."},{"key":"10.3233\/HIS-190277_ref11","doi-asserted-by":"crossref","unstructured":"C. Pizzuti, D. Talia and G. Vonella, A divisive initialisation method for clustering algorithms, Proc. of The 3rd. European Conference on Principles and Practice of Knowledge Discovery in Databases, 1999, pp.\u00a0484\u2013491.","DOI":"10.1007\/978-3-540-48247-5_62"},{"key":"10.3233\/HIS-190277_ref12","unstructured":"D. Arthur and S. Vassilvitskii, K-Means++: the advantages of careful seeding, Proc. of the Eighteenth Annual ACM-SIAM Symposium on Discrete Algorithms, 2007, pp. 1027\u20131035."},{"key":"10.3233\/HIS-190277_ref14","doi-asserted-by":"crossref","unstructured":"D.J. Hand, F. Daly, A.D. Lunn, K.J. McConway and E. Ostrowski, Handbook of Small Data Sets, Chapman and Hall\/CRC,1st. edition, 1993.","DOI":"10.1007\/978-1-4899-7266-8_1"},{"issue":"3","key":"10.3233\/HIS-190277_ref15","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1016\/S0020-0255(70)80056-1","article-title":"Numerical methods for fuzzy clustering","volume":"2","author":"Ruspini","year":"1970","journal-title":"Information Sciences"},{"key":"10.3233\/HIS-190277_ref16","first-page":"388","article-title":"Cluster validity measurement techniques","author":"Kov\u00e1cs","year":"2006","journal-title":"Proc. of the Fifth WSEAS International Conference on Artificial Intelligence, Knowledge Engineering and Data Bases"},{"key":"10.3233\/HIS-190277_ref17","doi-asserted-by":"crossref","unstructured":"G. Gan, C. Ma and J. Wu, Data Clustering \u2013 Theory, Algorithms and Applications, Philadelphia, USA:SIAM, 2007.","DOI":"10.1137\/1.9780898718348"},{"key":"10.3233\/HIS-190277_ref19","unstructured":"H. Chernoff, The use of faces to represent points in n-dimensional space graphically, Technical Report n\u2218 71, Department of Statistics, Stanford University, 1971."},{"key":"10.3233\/HIS-190277_ref21","unstructured":"J.B. MacQueen, Some methods for classification and analysis of multivariate observations, Proc. of 5th. Berkeley Symposium on Mathematical Statistics and Probability, University of California Press, 1967, pp. 281\u2013297."},{"key":"10.3233\/HIS-190277_ref22","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1080\/01969727408546059","article-title":"Well separated clusters and optimal fuzzy partitions","volume":"4","author":"Dunn","year":"1974","journal-title":"Journal of Cybernetics"},{"key":"10.3233\/HIS-190277_ref23","unstructured":"J. Han, M. Kamber and J. Pei, Data mining \u2013 concepts and techniques, 3rd Ed., Amsterdam: Morgan Kaufmann Publishers, 2012."},{"issue":"5","key":"10.3233\/HIS-190277_ref24","doi-asserted-by":"crossref","first-page":"147","DOI":"10.5121\/ijcsit.2011.3513","article-title":"Robust seed selection algorithm for k-means type algorithms","volume":"3","author":"Pavan","year":"2011","journal-title":"International Journal of Computer Science & Information Technology (IJCSIT)"},{"issue":"11","key":"10.3233\/HIS-190277_ref25","doi-asserted-by":"crossref","first-page":"60","DOI":"10.3844\/jcssp.2010.60.66","article-title":"Single pass seed selection algorithm for k-Means","volume":"6","author":"Pavan","year":"2010","journal-title":"Journal of Computer Science"},{"key":"10.3233\/HIS-190277_ref26","unstructured":"L. Kaufman and P.J. Rousseeuw, Finding Groups in Data, USA: John Wiley & Sons, Inc., 2005."},{"key":"10.3233\/HIS-190277_ref27","doi-asserted-by":"crossref","first-page":"451","DOI":"10.1016\/0167-8655(95)00119-0","article-title":"New methods for the initialisation of clusters","volume":"17","author":"Al-Daoud","year":"1996","journal-title":"Pattern Recognition Letters"},{"issue":"4","key":"10.3233\/HIS-190277_ref28","first-page":"175","article-title":"Fuzzy C-Means algorithm with a point symmetry distance","volume":"7","author":"Su","year":"2005","journal-title":"International Journal of Fuzzy Systems"},{"key":"10.3233\/HIS-190277_ref29","doi-asserted-by":"crossref","first-page":"200","DOI":"10.1016\/j.eswa.2012.07.021","article-title":"A comparative study of efficient initialization methods for the k-means clustering algorithm","volume":"40","author":"Celebi","year":"2013","journal-title":"Expert Systems with Applications"},{"issue":"2\u20133","key":"10.3233\/HIS-190277_ref30","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1023\/A:1012801612483","article-title":"On clustering validation techniques","volume":"17","author":"Halkidi","year":"2001","journal-title":"Journal of Intelligent Information Systems"},{"key":"10.3233\/HIS-190277_ref31","doi-asserted-by":"crossref","unstructured":"M.R. Berthold, C. Borgelt, F. H\u00f6ppner and F. Klawonn, Guide to Intelligent Data Analysis, London:Springer-Verlag, 2010.","DOI":"10.1007\/978-1-84882-260-3"},{"issue":"6","key":"10.3233\/HIS-190277_ref32","doi-asserted-by":"crossref","first-page":"734","DOI":"10.1109\/TPAMI.2002.1008381","article-title":"Density-based multiscale data condensation","volume":"24","author":"Mitra","year":"2002","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.3233\/HIS-190277_ref33","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1016\/0377-0427(87)90125-7","article-title":"Silhouettes: a graphical-aid to the interpretation and validation of cluster analysis","volume":"20","author":"Rousseeuw","year":"1987","journal-title":"Computational and Applied Mathematics"},{"key":"10.3233\/HIS-190277_ref34","unstructured":"P.-N. Tan, M. Steinback and V. Kumar, Introduction to Data Mining, Pearson Education, Inc., 2006."},{"key":"10.3233\/HIS-190277_ref35","doi-asserted-by":"crossref","first-page":"1701","DOI":"10.1016\/j.patrec.2011.07.011","article-title":"A new algorithm for initial cluster centers in k-Means algorithms","volume":"3","author":"Erisoglu","year":"2011","journal-title":"Pattern Recognition Letters"},{"key":"10.3233\/HIS-190277_ref36","doi-asserted-by":"crossref","first-page":"645","DOI":"10.1109\/TNN.2005.845141","article-title":"Survey of clustering algorithms","volume":"16","author":"Xu","year":"2005","journal-title":"IEEE Transactions on Neural Networks"},{"key":"10.3233\/HIS-190277_ref37","unstructured":"S. Theodoridis and K. Koutroumbas, Pattern Recognition, 4th ed., USA: Elsevier, 2009."},{"key":"10.3233\/HIS-190277_ref38","doi-asserted-by":"crossref","first-page":"1197","DOI":"10.1016\/S0031-3203(01)00108-X","article-title":"Genetic clustering for automatic evolution of clusters and application to image classification","volume":"35","author":"Bandyopadhyay","year":"2002","journal-title":"Pattern Recognition"},{"key":"10.3233\/HIS-190277_ref39","unstructured":"S. Burks, G. Harrell and J. Wang, On initial effects of the k-Means clustering, Proc. of The 2015 World Congress in Computer Science, Computer Engineering, & Applied Computing, USA, 2015, pp. 200\u2013205."},{"issue":"8","key":"10.3233\/HIS-190277_ref40","doi-asserted-by":"crossref","first-page":"1107","DOI":"10.1016\/S0167-8655(02)00257-X","article-title":"Validation indices for graph clustering","volume":"24","author":"G\u00fcnter","year":"2003","journal-title":"Pattern Recognition Letters"},{"key":"10.3233\/HIS-190277_ref42","doi-asserted-by":"crossref","first-page":"1293","DOI":"10.1016\/j.patrec.2004.04.007","article-title":"Cluster center initialization algorithm for k-Means clustering","volume":"25","author":"Khan","year":"2004","journal-title":"Pattern Recognition Letters"},{"key":"10.3233\/HIS-190277_ref43","unstructured":"T.M. Mitchell, Machine Learning, USA: McGraw-Hill, 1997."},{"issue":"336","key":"10.3233\/HIS-190277_ref44","doi-asserted-by":"crossref","first-page":"846","DOI":"10.1080\/01621459.1971.10482356","article-title":"Objective criteria for the evaluation of clustering methods","volume":"66","author":"Rand","year":"1971","journal-title":"Journal of the American Statistical Association"},{"key":"10.3233\/HIS-190277_ref45","unstructured":"X. Zhu, Semi-supervised learning literature survey, Technical Report 1530, University of Wisconsin-Madison, 2006."},{"key":"10.3233\/HIS-190277_ref46","doi-asserted-by":"crossref","unstructured":"Y. Liu, Z. Li, H. Xiong, X. Gao and J. Wu, Understanding of internal clustering validation measures, Proc. of the 10th International IEEE Conference on Data Mining (ICMD), 2010, pp. 911\u2013916.","DOI":"10.1109\/ICDM.2010.35"}],"container-title":["International Journal of Hybrid Intelligent Systems"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/HIS-190277","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T08:52:48Z","timestamp":1777452768000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/HIS-190277"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,3,23]]},"references-count":41,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.3233\/his-190277","relation":{},"ISSN":["1448-5869","1875-8819"],"issn-type":[{"value":"1448-5869","type":"print"},{"value":"1875-8819","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,3,23]]}}}