On the selection and classification of independent features

Authors:
M. Bressan;J. Vitria
Affiliations:
Departament Informatica, Univ. Autonoma de Barcelona, Bellaterra, Spain;-
Venue:
IEEE Transactions on Pattern Analysis and Machine Intelligence
Year:
2003

Citing 0
Cited 11

Real-Time Gesture Recognition by Learning and Selective Control of Visual Interest Points

IEEE Transactions on Pattern Analysis and Machine Intelligence
Equivalence of Some Common Linear Feature Extraction Techniques for Appearance-Based Object Recognition Tasks

IEEE Transactions on Pattern Analysis and Machine Intelligence
Evolving a Bayesian classifier for ECG-based age classification in medical applications

Applied Soft Computing
Independent components extraction from image matrix

Pattern Recognition Letters
Texture measures combination for improved meningioma classification of histopathological images

Pattern Recognition
Partition-conditional ICA for Bayesian classification of microarray data

Expert Systems with Applications: An International Journal
Discrimination-Based feature selection for multinomial naïve bayes text classification

ICCPOL'06 Proceedings of the 21st international conference on Computer Processing of Oriental Languages: beyond the orient: the research challenges ahead
Statistical Analysis of Textural Features for Improved Classification of Oral Histopathological Images

Journal of Medical Systems
The small sample size problem of ICA: A comparative study and analysis

Pattern Recognition
Variational learning of a Dirichlet process of generalized Dirichlet distributions for simultaneous clustering and feature selection

Pattern Recognition
On fuzzy-rough attribute selection: Criteria of Max-Dependency, Max-Relevance, Min-Redundancy, and Max-Significance

Applied Soft Computing

Quantified Score

Hi-index	0.15

Visualization

Abstract

This paper is focused on the problems of feature selection and classification when classes are modeled by statistically independent features. We show that, under the assumption of class-conditional independence, the class separability measure of divergence is greatly simplified, becoming a sum of unidimensional divergences, providing a feature selection criterion where no exhaustive search is required. Since the hypothesis of independence is infrequently met in practice, we also provide a framework making use of class-conditional Independent Component Analyzers where this assumption can be held on stronger grounds. Divergence and the Bayes decision scheme are adapted to this class-conditional representation. An algorithm that integrates the proposed representation, feature selection technique, and classifier is presented. Experiments on artificial, benchmark, and real-world data illustrate our technique and evaluate its performance.