Presentation 2001/10/11
The Study of Effectiveness of Class-Dependent Features
Kazuaki AOKI, Mineichi KUDO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In pattern recognition, feature selection is used for reducing the measurement cost of features or for improving the performance of classifiers of both. Especially, removing of features with no discriminative information is effective for improving the precision of estimated parameters of parametric classifiers. Many feature selection algorithms choose a feature subset that is useful for all classes in common. However, a best feature subset for separating one group of classes from another group of classes depends on the two groups. In this study, we investigate the basic effectiveness of an idea such that feature subsets are chosen depending of groups of classes and a classifer system is built as a decition tree in which nodes have those different feature subsets.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Feature Selection / Class-Dependent Feature Subset / Large Scale Problem / Decision Tree
Paper # PRMU2001-101,NC2001-51
Date of Issue

Conference Information
Committee PRMU
Conference Date 2001/10/11(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Pattern Recognition and Media Understanding (PRMU)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) The Study of Effectiveness of Class-Dependent Features
Sub Title (in English)
Keyword(1) Feature Selection
Keyword(2) Class-Dependent Feature Subset
Keyword(3) Large Scale Problem
Keyword(4) Decision Tree
1st Author's Name Kazuaki AOKI
1st Author's Affiliation Division of Systems and Information Engineering Graduate School of Engineering Hokkaido University()
2nd Author's Name Mineichi KUDO
2nd Author's Affiliation Division of Systems and Information Engineering Graduate School of Engineering Hokkaido University
Date 2001/10/11
Paper # PRMU2001-101,NC2001-51
Volume (vol) vol.101
Number (no) 362
Page pp.pp.-
#Pages 8
Date of Issue