지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
논문 기본 정보
- 자료유형
- 학술저널
- 저자정보
- 저널정보
- 한국정보통신학회JICCE Journal of information and communication convergence engineering Journal of information and communication convergence engineering 제9권 제6호
- 발행연도
- 2011.12
- 수록면
- 637 - 640 (4page)
이용수
이 논문의 연구 히스토리 (2)
2011
Hybrid Neural Networks for Pattern Recognition
Kwang-Baek Kim
Journal of information and communication convergence engineering
2011.12
학술저널
Enhanced Hybrid Neural Networks for Pattern Recognition
Kwang-Baek Kim
,
Intaek Lim
,
Am-Suk Oh
외 2명
INTERNATIONAL CONFERENCE ON FUTURE INFORMATION & COMMUNICATION ENGINEERING
2011.06
학술대회자료
- 이 논문의 후속연구가 궁금하신가요?
- 연관 학술논문 또는 학술발표를 통해 보다 발전된 연구결과를 확인하실 수 있습니다.
- 이 논문의 연구 히스토리 확인하기
초록· 키워드
오류제보하기
The hybrid neural networks have characteristics such as fast learning times, generality, and simplicity, and are mainly used to classify learning data and to model non-linear systems. The middle layer of a hybrid neural network clusters the learning vectors by grouping homogenous vectors in the same cluster. In the clustering procedure, the homogeneity between learning vectors is represented as the distance between the vectors. Therefore, if the distances between a learning vector and all vectors in a cluster are smaller than a given constant radius, the learning vector is added to the cluster. However, the usage of a constant radius in clustering is the primary source of errors and therefore decreases the recognition success rate.
To improve the recognition success rate, we proposed the enhanced hybrid network that organizes the middle layer effectively by using the enhanced ART1 network adjusting the vigilance parameter dynamically according to the similarity between patterns. The results of experiments on a large number of calling card images showed that the proposed algorithm greatly improves the character extraction and recognition compared with conventional recognition algorithms.
To improve the recognition success rate, we proposed the enhanced hybrid network that organizes the middle layer effectively by using the enhanced ART1 network adjusting the vigilance parameter dynamically according to the similarity between patterns. The results of experiments on a large number of calling card images showed that the proposed algorithm greatly improves the character extraction and recognition compared with conventional recognition algorithms.
목차
Abstract
Ⅰ. INTRODUCTION
Ⅱ. HYBRID NEURAL NETWORKSFOR PATTERN RECOGNITION
Ⅲ. PERFORMANCE EVALUATIONS
Ⅳ. CONCLUSIONS
REFERENCES
참고문헌 (7)
참고문헌 신청
1. [학술대회논문] - M. Watanabe / 1994 / Adaptive Tree- Structured Self Generating Radial Basis Function and its Application to Nonlinear Identification Problem / Proceedings of IIZUKA : 167 ~ 170
2. [단행본] - J. Park / 1991 / Universal Approximation Using Radial Basis Function Network / Neural Comp : 246 ~ 257
3. [학술대회논문] - C. Panchapakesan / 1998 / Effects of Moving the Centers in an RBF Network / Proceedings of IJCNN : 1256 ~ 1260
4. [학술지(정기간행물)] - K. B. Kim / 2005 / Performance Improvement of Fuzzy RBF Networks / Lecture Notes in Computer Science 3610 : 237 ~ 244
5. [학술지(정기간행물)] - K. B. Kim / 2005 / Enhanced RBF Network by Using ART2 Algorithm and Fuzzy Control Method / IEICE Trans. Fundamentals E88-A (6) : 1497 ~ 1501
2. [단행본] - J. Park / 1991 / Universal Approximation Using Radial Basis Function Network / Neural Comp : 246 ~ 257
3. [학술대회논문] - C. Panchapakesan / 1998 / Effects of Moving the Centers in an RBF Network / Proceedings of IJCNN : 1256 ~ 1260
4. [학술지(정기간행물)] - K. B. Kim / 2005 / Performance Improvement of Fuzzy RBF Networks / Lecture Notes in Computer Science 3610 : 237 ~ 244
5. [학술지(정기간행물)] - K. B. Kim / 2005 / Enhanced RBF Network by Using ART2 Algorithm and Fuzzy Control Method / IEICE Trans. Fundamentals E88-A (6) : 1497 ~ 1501
이 논문의 저자 정보
최근 본 자료
댓글(0)
0
UCI(KEPA) : I410-ECN-0101-2023-004-000411118