Measures for Unsupervised Fuzzy-Rough Feature Selection

Math Trafodion Cynhadledd (Nid-Cyfnodolyn fathau)
Iaith wreiddiolSaesneg
Teitl9th International Conference on Intelligent Systems Design and Applications (ISDA'09) Event: Conference
CyhoeddwrIEEE Press
Tudalennau249-259
Nifer y tudalennau11
Cyfrol7
Argraffiad4
ISBN (Electronig)978-0-7695-3872-3
ISBN (Argraffiad)978-1-4244-4735-0
Dangosyddion eitem ddigidol (DOIs)
StatwsCyhoeddwyd - 30 Tach 2009
Digwyddiad9th International Conference on Intelligent Systems Design and Applications (ISDA'09) - Pisa, Yr Eidal
Hyd: 30 Nov 200902 Dec 2009

Cynhadledd

Cynhadledd9th International Conference on Intelligent Systems Design and Applications (ISDA'09)
GwladYr Eidal
DinasPisa
Cyfnod30 Nov 200902 Dec 2009
Cysylltiadau
Handle.net
Arddangos ystadegau lawrlwytho
Gweld graff cysylltiadau
Fformatau enwi

Crynodeb

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, and result in a significant reduction in dimensionality whilst retaining the semantics of the data.

Dogfennau