Comparison of advanced neural network architectures for hyperspectral data classification

Author

Marpu, Prashanth ; Licciardi, Giorgio ; Gamba, Paolo ; Del Frate, Fabio

Author_Institution

Dept. of Electron., Univ. of Pavia, Pavia, Italy

fYear

2010

fDate

14-16 June 2010

Firstpage

1

Lastpage

4

Abstract

We investigate the performance of two advanced neural network architectures proposed earlier for hyperspectral data classification. While the first architecture uses feature reduction based on the samples of the classes, the second architecture uses a completely unsupervised approach for feature reduction using auto-associative neural networks. The aim of this study is to identify the pros and cons of such multi-level neural network architectures while classifying hyperspectral data.

Keywords

data handling; neural net architecture; pattern classification; autoassociative neural networks; feature reduction; hyperspectral data classification; multilevel neural network architectures; Accuracy; Artificial neural networks; Asphalt; Classification algorithms; Computer architecture; Hyperspectral imaging; Training; Class-dependent neural networks; auto-associative neural networks; classification; feature reduction;

fLanguage

English

Publisher

ieee

Conference_Titel

Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS), 2010 2nd Workshop on

Conference_Location

Reykjavik

Print_ISBN

978-1-4244-8906-0

Electronic_ISBN

978-1-4244-8907-7

Type

conf

DOI

10.1109/WHISPERS.2010.5594919

Filename

5594919