Publications
Methodology of selecting the most informative variables for decision-making problems of classification type
Proceedings name:
Proceedings 6th Int. Conf. on Information and Management Sciences
Publisher:
California Polytechnic State University, USA
Serie:
Lhasa, Tibet, China
Keywords:
feature selection, decision making, pattern recognition
Anotation:
The paper gives an overview of feature selection (abbreviated FS in the sequel) techniques in statistical pattern recognition with particular emphasis to recent knowledge. FS methods constitute the methodology of selecting the most informative variables for decision-making problems of classification type. Besides discussing the advances in methodology it attempts to put them into a taxonomical framework. The methods discussed include the latest variants of the optimal algorithms, enhanced sub-optimal techniques and the simultaneous semi-parametric probability density function modeling and feature space selection method. Some related issues are illustrated on real data with use of Feature Selection Toolbox software.