Local Modelling in Classification on Different Feature Subspaces

dc.contributor.author	Szepannek, Gero
dc.contributor.author	Weihs, Claus
dc.date.accessioned	2006-02-27T14:00:32Z
dc.date.available	2006-02-27T14:00:32Z
dc.date.issued	2006-02-27T14:00:32Z
dc.description.abstract	Sometimes one may be confronted with classification problems where classes are constituted of several subclasses that possess different distributions and therefore destroy accurate models of the entire classes as one similar group. An issue is modelling via local models of several subclasses. In this paper, a method is presented of how to handle such classification problems where the subclasses are furthermore characterized by different subsets of the variables. Situations are outlined and tested where such local models in different variable subspaces dramatically improve the classification error.	en
dc.format.extent	101246 bytes)
dc.format.extent	273558 bytes
dc.format.mimetype	application/pdf
dc.format.mimetype	application/postscript
dc.identifier.uri	http://hdl.handle.net/2003/22204
dc.identifier.uri	http://dx.doi.org/10.17877/DE290R-14151
dc.language.iso	en
dc.subject	Classification error	en
dc.subject	Classification problem	en
dc.subject	Local model	en
dc.subject	Subclass	en
dc.subject	Variable subspace	en
dc.subject.ddc	004
dc.title	Local Modelling in Classification on Different Feature Subspaces	en
dc.type	Text
dc.type.publicationtype	report	en
dcterms.accessRights	open access

Files

Now showing 1 - 2 of 2

Now showing 1 - 1 of 1