Input feature selection by mutual information based on Parzen window

Top Cited Papers

1 December 2002

journal article
Published by Institute of Electrical and Electronics Engineers (IEEE)

Vol. 24 (12) , 1667-1671
https://doi.org/10.1109/tpami.2002.1114861

Abstract

Mutual information is a good indicator of relevance between variables, and have been used as a measure in several feature selection algorithms. However, calculating the mutual information is difficult, and the performance of a feature selection algorithm depends on the accuracy of the mutual information. In this paper, we propose a new method of calculating mutual information between input and class variables based on the Parzen window, and we apply this to a feature selection algorithm for classification problems.

Keywords

This publication has 11 references indexed in Scilit:

Relevance feedback and category search in image databases
Published by Institute of Electrical and Electronics Engineers (IEEE) ,2003
Learning from examples with quadratic mutual information
Published by Institute of Electrical and Electronics Engineers (IEEE) ,2002
Nonlinear feature transforms using maximum mutual information
Published by Institute of Electrical and Electronics Engineers (IEEE) ,2002
Evaluation of a modified Parzen classifier in high dimensional spaces
Published by Institute of Electrical and Electronics Engineers (IEEE) ,2002
Input feature selection for classification problems
IEEE Transactions on Neural Networks, 2002
Elements of Information Theory
Published by Wiley ,2001
On the behavior of artificial neural network classifiers in high-dimensional spaces
Published by Institute of Electrical and Electronics Engineers (IEEE) ,1996
Using mutual information for selecting features in supervised neural net learning
IEEE Transactions on Neural Networks, 1994
The reduced Parzen classifier
IEEE Transactions on Pattern Analysis and Machine Intelligence, 1989
On Estimation of a Probability Density Function and Mode
The Annals of Mathematical Statistics, 1962