Authors:
Vincent Bombardier
1
;
Laurent Wendling
2
and
Emmanuel Schmitt
1
Affiliations:
1
Université Henri Poincaré, France
;
2
LIPADE and Laboratoire Informatique Paris Descartes, France
Keyword(s):
Feature Selection, Pattern Recognition, Fuzzy Rules.
Related
Ontology
Subjects/Areas/Topics:
Artificial Intelligence
;
Biomedical Engineering
;
Biomedical Signal Processing
;
Computational Intelligence
;
Computer-Supported Education
;
Domain Applications and Case Studies
;
Fuzzy Image, Speech and Signal Processing, Vision and Multimedia
;
Fuzzy Systems
;
Health Engineering and Technology Applications
;
Human-Computer Interaction
;
Industrial, Financial and Medical Applications
;
Methodologies and Methods
;
Neural Networks
;
Neurocomputing
;
Neurotechnology, Electronics and Informatics
;
Pattern Recognition
;
Pattern Recognition: Fuzzy Clustering and Classifiers
;
Physiological Computing Systems
;
Sensor Networks
;
Signal Processing
;
Soft Computing
;
Theory and Methods
Abstract:
This paper proposed an extension of an iterative method to select suitable features for pattern recognition context. The main improvement is to replace its iterative step with another criterion based on importance and interaction indexes, providing suitable feature reduced set. This new scheme is embedded on a hierarchical fuzzy rule classification system. At last, each node gathers a set of classes having a similar aspect. The aim of the proposed method is to automatically extract an efficient subset of suitable features for each node. A selection of features is given. The associated criterion is directly based on importance index and assessment of positive and negative interaction between features. An experimental study, made in a wood defect recognition industrial context, shows the proposed method is efficient to producing significantly fewer rules.