DIGITAL LIBRARY ARCHIVE
HOME > DIGITAL LIBRARY ARCHIVE
< Previous   List   Next >  
Physiological Fuzzy Neural Networks for Image Recognition
Full-text Download
Kwang-Baek Kim (Dept. Computer Engineering, Silla University)
Yong-Eun Moon (Dept. of MIS, Silla University)
Choong-Shik Park (Dept. of Computer Engineering, Yongdong University)
Vol. 11, No. 2, Page: 81 ~ 103
Keywords
Nervous System, Agonistic Neuron, Antagonist Neurons, Bronchial Squamous Cell Carcinoma Images, Car Plate Images
Abstract
The Neuron structure in a nervous system consists of inhibitory neurons and excitory neurons. Both neurons are activated by agonistic neurons and inactivated by antagonist neurons. In this paper, we proposed a physiological fuzzy neural network by analyzing the physiological neuron structure in the nervous system. The proposed structure selectively activates the neurons which go through a state of excitement caused by agonistic neurons and also transmit the signal of these neurons to the output layers. The proposed physiological fuzzy neural networks based on the nervous system consists of a input player, and the hidden layer which classifies features of learning data, and output layer. The proposed fuzzy neural network is applied to recognize bronchial squamous cell carcinoma images and car plate images. The result of the experiments shows that the learning time, the convergence, and the recognition rate of the proposed physiological fuzzy neural networks outperform the conventional neural networks.
Show/Hide Detailed Information in Korean
영상 인식을 위한 생리학적 퍼지 신경망
김광백 (신라대학교 컴퓨터공학과)
문용은 (신라대학교 경영정보학과)
박충식 (영동대학교 컴퓨터공학과)
Abstract
신경계의 뉴런 구조는 흥분 뉴런과 억제 뉴런으로 구성되며 각각의 흥분 뉴런과 억제 뉴런은 주동근 뉴런(agonistic neuron)에 의해 활성화되며 길항근 뉴런(antagonist neuron)에 의해 비활성화 된다. 본 논문에서는 인간 신경계의 생리학적 뉴런 구조를 분석하여 퍼지 논리를 이용한 생리학적 퍼지 신경망을 제안한다. 제안된 구조는 주동근 뉴런에 의해 흥분 뉴런이 될 수 있는 뉴런들을 선택하여 흥분시켜 출력층으로 전달하고 나머지 뉴런들을 억제시켜 출력층에 전달시키지 않는다. 신경계를 기반으로 한 제안된 생리학적 퍼지 신경망의 학습구조는 입력층, 학습 데이터의 특징을 분류하는 중간층, 그리고 출력 층으로 구성된다. 제안된 퍼지 신경망의 학습 및 인식 성능을 평가하기 위해 정확성이 요구되는 의학의 한 분야인 기관지 편평암 영상 인식과 영상 인식의 주요 응용 분야인 차량번호판 인식에 적용하여 기존의 신경망과 성능을 비교 분석하였다. 실험 결과에서는 제안된 생리학적 퍼지 신경망이 기존의 신경망보다 학습 시간과 수렴성이 개선되었을 뿐만 아니라, 인식에 있어서도 우수한 성능이 있음을 확인하였다.
Cite this article
JIIS Style
Kim, K.-B., Y.-E. Moon, and C.-S. Park, "Physiological Fuzzy Neural Networks for Image Recognition", Journal of Intelligence and Information Systems, Vol. 11, No. 2 (2005), 81~103.

IEEE Style
Kwang-Baek Kim, Yong-Eun Moon, and Choong-Shik Park, "Physiological Fuzzy Neural Networks for Image Recognition", Journal of Intelligence and Information Systems, vol. 11, no. 2, pp. 81~103, 2005.

ACM Style
Kim, K.-B., Moon, Y.-E., and Park, C.-S., 2005. Physiological Fuzzy Neural Networks for Image Recognition. Journal of Intelligence and Information Systems. 11, 2, 81--103.
Export Formats : BiBTeX, EndNote

Warning: include(/home/hosting_users/ev_jiisonline/www/admin/archive/advancedSearch.php) [function.include]: failed to open stream: No such file or directory in /home/hosting_users/ev_jiisonline/www/archive/detail.php on line 429

Warning: include() [function.include]: Failed opening '/home/hosting_users/ev_jiisonline/www/admin/archive/advancedSearch.php' for inclusion (include_path='.:/usr/local/php/lib/php') in /home/hosting_users/ev_jiisonline/www/archive/detail.php on line 429
@article{Kim:JIIS:2005:230,
author = {Kim, Kwang-Baek and Moon, Yong-Eun and Park, Choong-Shik},
title = {Physiological Fuzzy Neural Networks for Image Recognition},
journal = {Journal of Intelligence and Information Systems},
issue_date = {November 2005},
volume = {11},
number = {2},
month = Nov,
year = {2005},
issn = {2288-4866},
pages = {81--103},
url = {},
doi = {},
publisher = {Korea Intelligent Information System Society},
address = {Seoul, Republic of Korea},
keywords = { Nervous System, Agonistic Neuron, Antagonist Neurons, Bronchial Squamous Cell Carcinoma Images and Car Plate Images },
}
%0 Journal Article
%1 230
%A Kwang-Baek Kim
%A Yong-Eun Moon
%A Choong-Shik Park
%T Physiological Fuzzy Neural Networks for Image Recognition
%J Journal of Intelligence and Information Systems
%@ 2288-4866
%V 11
%N 2
%P 81-103
%D 2005
%R
%I Korea Intelligent Information System Society