dc.contributor.author | Cordeiro De Amorim, Renato | |
dc.contributor.author | Komisarczuk, Peter | |
dc.date.accessioned | 2016-04-04T11:47:09Z | |
dc.date.available | 2016-04-04T11:47:09Z | |
dc.date.issued | 2012 | |
dc.identifier.citation | Cordeiro De Amorim , R & Komisarczuk , P 2012 , On Initializations for the Minkowski Weighted K-Means . in Advances in Intelligent Data Analysis XI . Lecture Notes in Computer Science , vol. 7619 , Springer Nature , pp. 45-55 , 11th Int Symposium, IDA 2012 , Helsinki , Finland , 25/10/12 . https://doi.org/10.1007/978-3-642-34156-4_6 | |
dc.identifier.citation | conference | |
dc.identifier.isbn | 978-3-642-34155-7 | |
dc.identifier.isbn | 978-3-642-34156-4 | |
dc.identifier.uri | http://hdl.handle.net/2299/16910 | |
dc.description.abstract | Minkowski Weighted K-Means is a variant of K-Means set in the Minkowski space, automatically computing weights for features at each cluster. As a variant of K-Means, its accuracy heavily depends on the initial centroids fed to it. In this paper we discuss our experiments comparing six initializations, random and five other initializations in the Minkowski space, in terms of their accuracy, processing time, and the recovery of the Minkowski exponent p. We have found that the Ward method in the Minkowski space tends to outperform other initializations, with the exception of low-dimensional Gaussian Models with noise features. In these, a modified version of intelligent K-Means excels. | en |
dc.language.iso | eng | |
dc.publisher | Springer Nature | |
dc.relation.ispartof | Advances in Intelligent Data Analysis XI | |
dc.relation.ispartofseries | Lecture Notes in Computer Science | |
dc.title | On Initializations for the Minkowski Weighted K-Means | en |
dc.contributor.institution | School of Computer Science | |
rioxxterms.versionofrecord | 10.1007/978-3-642-34156-4_6 | |
rioxxterms.type | Other | |
herts.preservation.rarelyaccessed | true | |