Share Email Print
cover

Proceedings Paper

Large-scale feature selection using evolved neural networks
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

In this paper computational intelligence, referring here to the synergy of neural networks and genetic algorithms, is deployed in order to determine a near-optimal neural network for the classification of dark formations in oil spills and look-alikes. Optimality is sought in the framework of a multi-objective problem, i.e. the minimization of input features used and, at the same time, the maximization of overall testing classification accuracy. The proposed method consists of two concurrent actions. The first is the identification of the subset of features that results in the highest classification accuracy on the testing data set i.e. feature selection. The second parallel process is the search for the neural network topology, in terms of number of nodes in the hidden layer, which is able to yield optimal results with respect to the selected subset of features. The results show that the proposed method, i.e. concurrently evolving features and neural network topology, yields superior classification accuracy compared to sequential floating forward selection as well as to using all features together. The accuracy matrix is deployed to show the generalization capacity of the discovered neural network topology on the evolved sub-set of features.

Paper Details

Date Published: 6 October 2006
PDF: 9 pages
Proc. SPIE 6365, Image and Signal Processing for Remote Sensing XII, 636513 (6 October 2006); doi: 10.1117/12.688149
Show Author Affiliations
Demetris Stathakis, Joint Research Ctr. of the European Commission (Italy)
Kostas Topouzelis, Joint Research Ctr. of the European Commission (Italy)
Vassilia Karathanassi, National Technical Univ. of Athens (Greece)


Published in SPIE Proceedings Vol. 6365:
Image and Signal Processing for Remote Sensing XII
Lorenzo Bruzzone, Editor(s)

© SPIE. Terms of Use
Back to Top