{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T06:57:18Z","timestamp":1760597838726,"version":"3.37.3"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319989310"},{"type":"electronic","value":"9783319989327"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-319-98932-7_7","type":"book-chapter","created":{"date-parts":[[2018,8,14]],"date-time":"2018-08-14T11:51:14Z","timestamp":1534247474000},"page":"76-88","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Fast and Simple Deterministic Seeding of\u00a0KMeans for Text Document Clustering"],"prefix":"10.1007","author":[{"given":"Ehsan","family":"Sherkat","sequence":"first","affiliation":[]},{"given":"Julien","family":"Velcin","sequence":"additional","affiliation":[]},{"given":"Evangelos E.","family":"Milios","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,8,15]]},"reference":[{"issue":"4","key":"7_CR1","doi-asserted-by":"publisher","first-page":"433","DOI":"10.1002\/wics.101","volume":"2","author":"H Abdi","year":"2010","unstructured":"Abdi, H., Williams, L.J.: Principal component analysis. Wiley Interdiscip. Rev.: Comput. Stat. 2(4), 433\u2013459 (2010)","journal-title":"Wiley Interdiscip. Rev.: Comput. Stat."},{"key":"7_CR2","doi-asserted-by":"crossref","unstructured":"Aggarwal, C.C., Yu, P.S.: Outlier detection for high dimensional data. In: Proceedings of the 2001 ACM SIGMOD International Conference on Management of Data, SIGMOD 2001, pp. 37\u201346. ACM, New York (2001)","DOI":"10.1145\/375663.375668"},{"key":"7_CR3","unstructured":"Arthur, D., Vassilvitskii, S.: K-means++: the advantages of careful seeding. In: Proceedings of the Eighteenth Annual ACM-SIAM Symposium on Discrete Algorithms, SODA 2007, pp. 1027\u20131035. Society for Industrial and Applied Mathematics, Philadelphia (2007)"},{"key":"7_CR4","unstructured":"Bachem, O., Lucic, M., Hassani, H., Krause, A.: Fast and provably good seedings for k-means. In: Lee, D.D., Sugiyama, M., Luxburg, U.V., Guyon, I., Garnett, R. (eds.) Advances in Neural Information Processing Systems 29, pp. 55\u201363. Curran Associates, Inc. (2016)"},{"key":"7_CR5","first-page":"1345","volume":"6","author":"A Banerjee","year":"2005","unstructured":"Banerjee, A., Dhillon, I.S., Ghosh, J., Sra, S.: Clustering on the unit hypersphere using von mises-fisher distributions. J. Mach. Learn. Res. 6, 1345\u20131382 (2005)","journal-title":"J. Mach. Learn. Res."},{"key":"7_CR6","doi-asserted-by":"crossref","DOI":"10.1201\/9781584889977","volume-title":"Constrained Clustering: Advances in Algorithms, Theory, and Applications","author":"S Basu","year":"2008","unstructured":"Basu, S., Davidson, I., Wagstaff, K.: Constrained Clustering: Advances in Algorithms, Theory, and Applications, 1st edn. Chapman & Hall\/CRC, Boca Raton (2008)","edition":"1"},{"key":"7_CR7","unstructured":"Bekkerman, R., Raghavan, H., Allan, J., Eguchi, K.: Interactive clustering of text collections according to a user-specified criterion. In: Proceedings of the 20th International Joint Conference on Artifical Intelligence, IJCAI 2007, pp. 684\u2013689. Morgan Kaufmann Publishers Inc., San Francisco (2007)"},{"issue":"1","key":"7_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TPAMI.1980.4766964","volume":"2","author":"JC Bezdek","year":"1980","unstructured":"Bezdek, J.C.: A convergence theorem for the fuzzy ISODATA clustering algorithms. IEEE Trans. Pattern Anal. Mach. Intell. 2(1), 1\u20138 (1980)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"7_CR9","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, SIGMOD 2000, pp. 93\u2013104. ACM, New York (2000)","DOI":"10.1145\/342009.335388"},{"issue":"12","key":"7_CR10","doi-asserted-by":"publisher","first-page":"1624","DOI":"10.1109\/TKDE.2005.198","volume":"17","author":"D Cai","year":"2005","unstructured":"Cai, D., He, X., Han, J.: Document clustering using locality preserving indexing. IEEE Trans. Knowl. Data Eng. 17(12), 1624\u20131637 (2005)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"7_CR11","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1007\/978-3-319-09259-1_3","volume-title":"Partitional Clustering Algorithms","author":"ME Celebi","year":"2015","unstructured":"Celebi, M.E., Kingravi, H.A.: Linear, deterministic, and order-invariant initialization methods for the k-means clustering algorithm. In: Celebi, M.E. (ed.) Partitional Clustering Algorithms, pp. 79\u201398. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-09259-1_3"},{"issue":"1","key":"7_CR12","doi-asserted-by":"publisher","first-page":"200","DOI":"10.1016\/j.eswa.2012.07.021","volume":"40","author":"ME Celebi","year":"2013","unstructured":"Celebi, M.E., Kingravi, H.A., Vela, P.A.: A comparative study of efficient initialization methods for the k-means clustering algorithm. Expert Syst. Appl. 40(1), 200\u2013210 (2013)","journal-title":"Expert Syst. Appl."},{"key":"7_CR13","unstructured":"Chang, M., Ratinov, L., Roth, D., Srikumar, V.: Importance of semantic representation: dataless classification. In: AAAI, July 2008"},{"issue":"1\u20132","key":"7_CR14","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1023\/A:1007612920971","volume":"42","author":"IS Dhillon","year":"2001","unstructured":"Dhillon, I.S., Modha, D.S.: Concept decompositions for large sparse text data using clustering. Mach. Learn. 42(1\u20132), 143\u2013175 (2001)","journal-title":"Mach. Learn."},{"key":"7_CR15","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"498","DOI":"10.1007\/978-3-662-44848-9_32","volume-title":"Machine Learning and Knowledge Discovery in Databases","author":"D Greene","year":"2014","unstructured":"Greene, D., O\u2019Callaghan, D., Cunningham, P.: How many topics? stability analysis for topic models. In: Calders, T., Esposito, F., H\u00fcllermeier, E., Meo, R. (eds.) ECML PKDD 2014 Part I. LNCS (LNAI), vol. 8724, pp. 498\u2013513. Springer, Heidelberg (2014). https:\/\/doi.org\/10.1007\/978-3-662-44848-9_32"},{"issue":"11","key":"7_CR16","doi-asserted-by":"publisher","first-page":"994","DOI":"10.1016\/j.patrec.2009.04.013","volume":"30","author":"MA Hasan","year":"2009","unstructured":"Hasan, M.A., Chaoji, V., Salem, S., Zaki, M.J.: Robust partitional clustering by outlier and density insensitive seeding. Pattern Recogn. Lett. 30(11), 994\u20131002 (2009)","journal-title":"Pattern Recogn. Lett."},{"issue":"10","key":"7_CR17","doi-asserted-by":"publisher","first-page":"144","DOI":"10.1109\/97.329844","volume":"1","author":"I Katsavounidis","year":"1994","unstructured":"Katsavounidis, I., Kuo, C.C.J., Zhang, Z.: A new initialization technique for generalized Lloyd iteration. IEEE Sig. Process. Lett. 1(10), 144\u2013146 (1994)","journal-title":"IEEE Sig. Process. Lett."},{"issue":"1\u20132","key":"7_CR18","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1002\/nav.3800020109","volume":"2","author":"HW Kuhn","year":"1955","unstructured":"Kuhn, H.W.: The Hungarian method for the assignment problem. Nav. Res. Logist. Q. 2(1\u20132), 83\u201397 (1955)","journal-title":"Nav. Res. Logist. Q."},{"key":"7_CR19","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1016\/j.cag.2014.01.006","volume":"41","author":"RM Martins","year":"2014","unstructured":"Martins, R.M., Coimbra, D.B., Minghim, R., Telea, A.: Visual analysis of dimensionality reduction quality for parameterized projections. Comput. Graph. 41, 26\u201342 (2014)","journal-title":"Comput. Graph."},{"key":"7_CR20","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1016\/j.compbiomed.2017.10.014","volume":"91","author":"N Nidheesh","year":"2017","unstructured":"Nidheesh, N., Nazeer, K.A., Ameer, P.: An enhanced deterministic k-means clustering algorithm for cancer subtype prediction from gene expression data. Comput. Biol. Med. 91, 213\u2013221 (2017)","journal-title":"Comput. Biol. Med."},{"issue":"4","key":"7_CR21","doi-asserted-by":"crossref","first-page":"319","DOI":"10.3233\/IDA-2007-11402","volume":"11","author":"T Su","year":"2007","unstructured":"Su, T., Dy, J.G.: In search of deterministic methods for initializing k-means and Gaussian mixture clustering. Intell. Data Anal. 11(4), 319\u2013338 (2007)","journal-title":"Intell. Data Anal."}],"container-title":["Lecture Notes in Computer Science","Experimental IR Meets Multilinguality, Multimodality, and Interaction"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-98932-7_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,11,7]],"date-time":"2020-11-07T19:20:38Z","timestamp":1604776838000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-98932-7_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319989310","9783319989327"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-98932-7_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]}}}