Measures for unsupervised fuzzy-rough feature selection

H...............H

Show simple item record

dc.contributor.author Mac Parthaláin, Neil
dc.contributor.author Jensen, Richard
dc.date.accessioned 2011-04-06T13:43:34Z
dc.date.available 2011-04-06T13:43:34Z
dc.date.issued 2011-04-06
dc.identifier.citation Mac Parthaláin , N & Jensen , R 2011 , ' Measures for unsupervised fuzzy-rough feature selection ' International Journal of Hybrid Intelligent Systems , pp. 249 . en
dc.identifier.other PURE: 167363
dc.identifier.other dspace: 2160/6424
dc.identifier.uri http://hdl.handle.net/2160/6424
dc.description N. Mac Parthalain and R. Jensen. Measures for unsupervised fuzzy-rough feature selection. International Journal of Hybrid Intelligent Systems, vol. 7, pp. 249¿259, 2010. en
dc.description.abstract For supervised learning, feature selection algorithms attempt to maximise a given function of predictive accuracy. This function usually considers the ability of feature vectors to reflect decision class labels. It is therefore intuitive to retain only those features that are related to or lead to these decision classes. However, in unsupervised learning, decision class labels are not provided, which poses questions such as; which features should be retained? and, why not use all of the information? The problem is that not all features are important. Some of the features may be redundant, and others may be irrelevant and noisy. In this paper, some new fuzzy-rough set-based approaches to unsupervised feature selection are proposed. These approaches require no thresholding or domain information, can operate on realvalued data, and result in a significant reduction in dimensionality whilst retaining the semantics of the data. en
dc.format.extent 249 en
dc.language.iso eng
dc.relation.ispartof International Journal of Hybrid Intelligent Systems en
dc.title Measures for unsupervised fuzzy-rough feature selection en
dc.type Text en
dc.type.publicationtype Article (Journal) en
dc.contributor.institution Department of Computer Science en
dc.description.status Peer reviewed en


Files in this item

This item appears in the following Collection(s)

Show simple item record

Search Cadair


Advanced Search

Browse

My Account