Clustering-Based Feature Selection in Semi-supervised Problems

Author

Quinzan, I. ; Sotoca, José M. ; Pla, Filiberto

Author_Institution

Dept. Llenguatges i Sistemes Inf., Univ. Jaume I, Castellon de la Plana, Spain

fYear

2009

fDate

Nov. 30 2009-Dec. 2 2009

Firstpage

535

Lastpage

540

Abstract

In this contribution a feature selection method in semi-supervised problems is proposed. This method selects variables using a feature clustering strategy, using a combination of supervised and unsupervised feature distance measure, which is based on conditional mutual information and conditional entropy. Real databases were analyzed with different ratios between labelled and unlabelled samples in the training set, showing the satisfactory behaviour of the proposed approach.

Keywords

entropy; learning (artificial intelligence); pattern clustering; clustering-based feature selection; conditional entropy; conditional mutual information; feature clustering; semisupervised learning; unsupervised feature distance measure; Clustering algorithms; Data analysis; Entropy; Filters; Intelligent systems; Labeling; Mutual information; Programmable logic arrays; Semisupervised learning; Spatial databases; Semi-supervised learning; feature selection; information measures;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Systems Design and Applications, 2009. ISDA '09. Ninth International Conference on

Conference_Location

Pisa

Print_ISBN

978-1-4244-4735-0

Electronic_ISBN

978-0-7695-3872-3

Type

conf

DOI

10.1109/ISDA.2009.211

Filename

5364964