An enhanced generalized adaptive resonance theory neural network and its application to medical pattern classification
Generalized Adaptive Resonance Theory (GART) is a neural network model based on the integration of Gaussian ARTMAP and the Generalized Regression Neural Network. As demonstrated in our previous work, GART is capable of online learning and is effective in tackling both classification and regression t...
Saved in:
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Published: |
2023
|
| Subjects: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| id |
my.uniten.dspace-30732 |
|---|---|
| record_format |
dspace |
| spelling |
my.uniten.dspace-307322023-12-29T15:52:04Z An enhanced generalized adaptive resonance theory neural network and its application to medical pattern classification Yap K.S. Lim C.P. Mohamad-Saleh J. 24448864400 55666579300 6505808410 Adaptive resonance theory Fuzzy rule extraction Generalized regression neural network Medical diagnosis Pattern classification Classification (of information) Diagnosis Fuzzy rules Medical problems Regression analysis Resonance Adaptive resonance theory Fuzzy rule extraction Generalized regression neural networks Medical diagnosis Pattern classification Neural networks Generalized Adaptive Resonance Theory (GART) is a neural network model based on the integration of Gaussian ARTMAP and the Generalized Regression Neural Network. As demonstrated in our previous work, GART is capable of online learning and is effective in tackling both classification and regression tasks. In this paper, we propose an Enhanced GART (EGART) network whereby the capability of GART is further enhanced with the Laplacian function, a new vigilance function, a new match-tracking mechanism, and a fuzzy rule extraction procedure. The applicability of EGART to pattern classification and fuzzy rule extraction problems is evaluated using three benchmark medical data sets and one real medical diagnosis problem. The experimental results are analyzed, discussed, and compared with other reported results. The outcomes demonstrate that EGART is capable of producing high accuracy rates and of extracting useful rules for tackling medical pattern classification problems. � 2010-IOS Press and the authors. All rights reserved. Final 2023-12-29T07:52:04Z 2023-12-29T07:52:04Z 2010 Article 10.3233/IFS-2010-0436 2-s2.0-76149127693 https://www.scopus.com/inward/record.uri?eid=2-s2.0-76149127693&doi=10.3233%2fIFS-2010-0436&partnerID=40&md5=13e95b1ea340f00f1736ee0b3e72cf20 https://irepository.uniten.edu.my/handle/123456789/30732 21 01/02/2023 65 78 Scopus |
| institution |
Universiti Tenaga Nasional |
| building |
UNITEN Library |
| collection |
Institutional Repository |
| continent |
Asia |
| country |
Malaysia |
| content_provider |
Universiti Tenaga Nasional |
| content_source |
UNITEN Institutional Repository |
| url_provider |
http://dspace.uniten.edu.my/ |
| topic |
Adaptive resonance theory Fuzzy rule extraction Generalized regression neural network Medical diagnosis Pattern classification Classification (of information) Diagnosis Fuzzy rules Medical problems Regression analysis Resonance Adaptive resonance theory Fuzzy rule extraction Generalized regression neural networks Medical diagnosis Pattern classification Neural networks |
| spellingShingle |
Adaptive resonance theory Fuzzy rule extraction Generalized regression neural network Medical diagnosis Pattern classification Classification (of information) Diagnosis Fuzzy rules Medical problems Regression analysis Resonance Adaptive resonance theory Fuzzy rule extraction Generalized regression neural networks Medical diagnosis Pattern classification Neural networks Yap K.S. Lim C.P. Mohamad-Saleh J. An enhanced generalized adaptive resonance theory neural network and its application to medical pattern classification |
| description |
Generalized Adaptive Resonance Theory (GART) is a neural network model based on the integration of Gaussian ARTMAP and the Generalized Regression Neural Network. As demonstrated in our previous work, GART is capable of online learning and is effective in tackling both classification and regression tasks. In this paper, we propose an Enhanced GART (EGART) network whereby the capability of GART is further enhanced with the Laplacian function, a new vigilance function, a new match-tracking mechanism, and a fuzzy rule extraction procedure. The applicability of EGART to pattern classification and fuzzy rule extraction problems is evaluated using three benchmark medical data sets and one real medical diagnosis problem. The experimental results are analyzed, discussed, and compared with other reported results. The outcomes demonstrate that EGART is capable of producing high accuracy rates and of extracting useful rules for tackling medical pattern classification problems. � 2010-IOS Press and the authors. All rights reserved. |
| author2 |
24448864400 |
| author_facet |
24448864400 Yap K.S. Lim C.P. Mohamad-Saleh J. |
| format |
Article |
| author |
Yap K.S. Lim C.P. Mohamad-Saleh J. |
| author_sort |
Yap K.S. |
| title |
An enhanced generalized adaptive resonance theory neural network and its application to medical pattern classification |
| title_short |
An enhanced generalized adaptive resonance theory neural network and its application to medical pattern classification |
| title_full |
An enhanced generalized adaptive resonance theory neural network and its application to medical pattern classification |
| title_fullStr |
An enhanced generalized adaptive resonance theory neural network and its application to medical pattern classification |
| title_full_unstemmed |
An enhanced generalized adaptive resonance theory neural network and its application to medical pattern classification |
| title_sort |
enhanced generalized adaptive resonance theory neural network and its application to medical pattern classification |
| publishDate |
2023 |
| _version_ |
1806426719986384896 |
| score |
13.222552 |