2002 개방형GIS 춘계 학술대회
Current Result Document : 8 / 8
| 한글제목(Korean Title) |
Effects of randomizing patterns and training unequally represented classes for artificial neural networks |
| 영문제목(English Title) |
Effects of randomizing patterns and training unequally represented classes for artificial neural networks |
| 저자(Author) |
Youngsup Kim
Tommy L. coleman
|
| 원문수록처(Citation) |
VOL 01 NO. 01 PP. 0045 ~ 0052 (2002. 03) |
한글내용
(Korean Abstract) |
|
영문내용
(English Abstract) |
artificial neural networks(ANN) have been successfully used for classifuing remotely sensed imagery. However, ANN still in not the preferable choice for classification over the conventional classification methodology such as the maximum likelihood classifier commonly used in the industry production environment. This can be attributed to the ANN characteristic built-in stochastic process that creates difficulties in dealing with unequally represented training classes, and its training performance speed.
In this paper we examined some practical aspects of training classes when using a back propagation neural network model for remotely sensed imagery. During the classification process of remotely sensed imagery, representative training patterns for each class are collected by polygons or by using a region- growing methodology over the imagery. The number of collected training patters for each class may vary from several pixels to thousands. This unequally populated training data amy cause the significant problems some neural network empirical models such as back-propagation have experienced.
We investigate the effects of training over-or under-represented training patters in classes and propose the pattern repopulation algorithm,, and an adaptive alpha adjustment(AAA) algorithm to handle unequally represented classes. We also show the performance improvement when input patterns are presented in random fashion during the back-propagation training.
|
| 키워드(Keyword) |
Randomizing pattern
Artificial Neural Networks(ANN)
|
| 파일첨부 |
PDF 다운로드
|
