Share Email Print

Proceedings Paper

Equalizing the training set for neural network recognizer
Author(s): Yunhong Wang; Guo-Sui Liu; Yiding Wang
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

The unequally training set causes the low classification rate of a neural network recognizer. In order to equalize the training set, two methods are proposed in this paper. The first way controls the training parameters according to the property of training samples, i.e. adjusts the study rate with a fuzzy rule. The fuzzy rule is defined by the distribution of the training set and the important level of each kind of samples. The classification rate can be improved in this way and the fast convergence property can be achieved. The second means of equalizing the training set reduces the over- represented samples by fuzzy clustering and increases the deficient samples by interpolating. The BP neural network is used as recognizer here. From the results of the computer simulations, the two methods show to be effective when the training data are imbalance. The two ways improve the classification rate of neural network recognizer by equalizing the training set.

Paper Details

Date Published: 23 June 1997
PDF: 9 pages
Proc. SPIE 3069, Automatic Target Recognition VII, (23 June 1997); doi: 10.1117/12.277135
Show Author Affiliations
Yunhong Wang, Nanjing Univ. of Science and Technology (China)
Guo-Sui Liu, Nanjing Univ. of Science and Technology (China)
Yiding Wang, Nanjing Univ. of Science and Technology (China)

Published in SPIE Proceedings Vol. 3069:
Automatic Target Recognition VII
Firooz A. Sadjadi, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?