Evaluation of Neural Pattern Classifiers for a Remote Sensing Application

WSG 46/95 Working Paper

29 Pages Posted: 21 May 2018

See all articles by Manfred M. Fischer

Manfred M. Fischer

Vienna University of Economics and Business - Institute for Economic Geography and GIScience, Department of Socioeconomics

Sucharita Gopal

Boston University - Department of Geography

Petra Staufer-Steinnocher

University of Vienna - Department of Economics

Klaus Steinnocher

Austrian Research Center, Seibersdorf

Date Written: May 1, 1995

Abstract

This paper evaluates the classification accuracy of three neural network classifiers on a satellite image-based pattern classification problem. The neural network classifiers used include two types of the Multi-Layer-Perceptron (MLP) and the Radial Basis Function Network. A normal (conventional) classifier is used as a benchmark to evaluate the performance of neural network classifiers. The satellite image consists of 2,460 pixels selected from a section (270 x 360) of a Landsat-5 TM scene from the city of Vienna and its northern surroundings. In addition to evaluation of classification accuracy, the neural classifiers are analysed for generalization capability and stability of results. Best overall results (in terms of accuracy and convergence time) are provided by the MLP-1 classifier with weight elimination. It has a small number of parameters and requires no problem-specific system of initial weight values. Its in-sample classification error is 7.87% and its out-of-sample classification error is 10.24% for the problem at hand. Four classes of simulations serve to illustrate the properties of the classifier in general and the stability of the result with respect to control parameters, and on the training time, the gradient descent control term, initial parameter conditions, and different training and testing sets.

Suggested Citation

Fischer, Manfred M. and Gopal, Sucharita and Staufer-Steinnocher, Petra and Steinnocher, Klaus, Evaluation of Neural Pattern Classifiers for a Remote Sensing Application (May 1, 1995). WSG 46/95 Working Paper, Available at SSRN: https://ssrn.com/abstract=1523788 or http://dx.doi.org/10.2139/ssrn.1523788

Manfred M. Fischer (Contact Author)

Vienna University of Economics and Business - Institute for Economic Geography and GIScience, Department of Socioeconomics ( email )

Welthandelsplatz 1, D4
Vienna, 1020
Austria

Sucharita Gopal

Boston University - Department of Geography ( email )

United States

Petra Staufer-Steinnocher

University of Vienna - Department of Economics ( email )

Bruennerstrasse 72
Vienna, A-1210
Austria

Klaus Steinnocher

Austrian Research Center, Seibersdorf ( email )

Seibersdorf
Austria

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
8
Abstract Views
226
PlumX Metrics