Feature subset selection and ranking for data dimensionality reduction

Hua-Liang Wei; Stephen A Billings

doi:10.1109/tpami.2007.250607

Feature subset selection and ranking for data dimensionality reduction

IEEE Trans Pattern Anal Mach Intell. 2007 Jan;29(1):162-6. doi: 10.1109/tpami.2007.250607.

Authors

Hua-Liang Wei¹, Stephen A Billings

Affiliation

¹ Department of Automatic Control and Systems Engineering, The University of Sheffield, Mappin Street, Sheffield S1 3JD UK. w.hualiang@sheffield.ac.uk

PMID: 17108391
DOI: 10.1109/tpami.2007.250607

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.

MeSH terms

Algorithms
Artificial Intelligence*
Cluster Analysis
Data Compression / methods*
Image Enhancement / methods*
Image Interpretation, Computer-Assisted / methods*
Imaging, Three-Dimensional / methods*
Pattern Recognition, Automated / methods*
Sensitivity and Specificity