A new evolutionary neural network and its application for the extraction of vegetation anomalies

Authors:
Yan Guo;Lishan Kang;Fujiang Liu;Linlu Mei
Affiliations:
School of Computer, China University of Geosciences, Wuhan, China;School of Computer, China University of Geosciences, Wuhan, China and School of Computer Sciences, Wuhan University, Wuhan, China;Faculty of Information Engineering, China University of Geosciences, Wuhan, China;Faculty of Information Engineering, China University of Geosciences, Wuhan, China
Venue:
ISICA'07 Proceedings of the 2nd international conference on Advances in computation and intelligence
Year:
2007

Citing 6
Cited 0

Genetic neural networks on MIMD computers

Genetic neural networks on MIMD computers
Remote Sensing: Digital Image Analysis

Remote Sensing: Digital Image Analysis
Evolving neural networks to identify bent-double galaxies in the FIRST survey

Neural Networks - 2003 Special issue: Neural network analysis of complex scientific data: Astronomy and geosciences
An alternative approach for neural network evolution with a genetic algorithm: Crossover by combinatorial optimization

Neural Networks
An empirical comparison of combinations of evolutionary algorithms and neural networks for classification problems

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
A new evolutionary system for evolving artificial neural networks

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper proposes an evolutionary neural network (ENN). In this ENN model evolutionary algorithms (EAs) are adopted to train the multilayer perceptrons (MLPs) to overcome backpropagation (BP) algorithm shortcomings. The proposed ENN technique was used to the extraction of vegetation anomalies in remote sensing imagery compared against MLPs with BP algorithm. The experiments of extracting vegetation anomalies were carried out by ENN classifiers and BP classifiers in a 1241×1149 pixel Landsat-7 Enhanced Thematic Mapper plus (ETM+) high-resolution image of Zhaoyuan gold deposits, Shandong, China. We found that the use of EAs for finding the optimal weights of MLPs results mainly in improvements in overall accuracy of MLPs.