Classification accuracy improvement of neural network classifiers by using unlabeled data

Author

Fardanesh, M.T. ; Ersoy, Okan K.

Author_Institution

Dept. of Commun. Sci. & Technol., California State Univ., Monterey Bay, CA, USA

Volume

36

Issue

3

fYear

1998

fDate

5/1/1998 12:00:00 AM

Firstpage

1020

Lastpage

1025

Abstract

Classification accuracy improvement of neural network classifiers using unlabeled testing data is presented. In order to increase the classification accuracy without increasing the number of training data, the network makes use of testing data along with training data for learning. It is shown that including the unlabled samples from underrepresented classes in the training set improves the classification accuracy of some of the classes during supervised-unsupervised learning

Keywords

feedforward neural nets; geophysical signal processing; geophysical techniques; geophysics computing; image classification; neural nets; remote sensing; accuracy improvement; geophysical measurement technique; image classification; image processing; land surface; neural net; neural network classifier; remote sensing; supervised learning; terrain mapping; training; underrepresented class; unlabeled data; unlabelled data; unsupervised learning; Artificial neural networks; High-resolution imaging; Image resolution; Neural networks; Optical imaging; Remote sensing; Space technology; Spatial resolution; Testing; Training data;

fLanguage

English

Journal_Title

Geoscience and Remote Sensing, IEEE Transactions on

Publisher

ieee

ISSN

0196-2892

Type

jour

DOI

10.1109/36.673695

Filename

673695