White Rose University Consortium logo
University of Leeds logo University of Sheffield logo York University logo

Feature subset selection and ranking for data dimensionality reduction

Wei, H.L. and Billings, S.A. (2007) Feature subset selection and ranking for data dimensionality reduction. IEEE Transactions on Pattern Analysis and Machine Intelligence, 29 (1). pp. 162-166. ISSN 0162-8828

Full text available as:
[img]
Preview
Text
weihl3.pdf

Download (1017Kb)

Abstract

A new unsupervised forward orthogonal search (FOS) algorithm is introduced for feature selection and ranking. In the new algorithm, features are selected in a stepwise way, one at a time, by estimating the capability of each specified candidate feature subset to represent the overall features in the measurement space. A squared correlation function is employed as the criterion to measure the dependency between features and this makes the new algorithm easy to implement. The forward orthogonalization strategy, which combines good effectiveness with high efficiency, enables the new algorithm to produce efficient feature subsets with a clear physical interpretation.

Item Type: Article
Copyright, Publisher and Additional Information: Copyright © 2007 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
Keywords: dimensionality reduction, feature selection, high-dimensional data
Institution: The University of Sheffield
Academic Units: The University of Sheffield > Faculty of Engineering (Sheffield) > Department of Automatic Control and Systems Engineering (Sheffield)
Depositing User: Sherpa Assistant
Date Deposited: 06 Feb 2007
Last Modified: 05 Jun 2014 01:22
Published Version: http://dx.doi.org/10.1109/TPAMI.2007.250607
Status: Published
Publisher: IEEE Computer Society
Refereed: Yes
Identification Number: 10.1109/TPAMI.2007.250607
URI: http://eprints.whiterose.ac.uk/id/eprint/1947

Actions (login required)

View Item View Item