Browse > Article

Hierarchical Ann Classification Model Combined with the Adaptive Searching Strategy  

김도현 (부산대학교 전자계산학과)
차의영 (부산대학교 전자계산학과)
Abstract
We propose a hierarchical architecture of ART2 Network for performance improvement and fast pattern classification model using fitness selection. This hierarchical network creates coarse clusters as first ART2 network layer by unsupervised learning, then creates fine clusters of the each first layer as second network layer by supervised learning. First, it compares input pattern with each clusters of first layer and select candidate clusters by fitness measure. We design a optimized fitness function for pruning clusters by measuring relative distance ratio between a input pattern and clusters. This makes it possible to improve speed and accuracy. Next, it compares input pattern with each clusters connected with selected clusters and finds winner cluster. Finally it classifies the pattern by a label of the winner cluster. Results of our experiments show that the proposed method is more accurate and fast than other approaches.
Keywords
ART2; HART2; Hierarchical Neural Network; Pruning Strategy; Fitness Selection;
Citations & Related Records
Times Cited By KSCI : 2  (Citation Analysis)
연도 인용수 순위
1 B. D. Ripley, 'Pattern Recognition and neural networks,' Cambridge, 1996
2 김대수, '신경회로망 이론과 응용 (I), (II)', 하이테크 정보, 1994
3 박창순, 김두영, '오프라인 필기체 숫자 인식을 위한 다양한 특징들의 비교 및 인식률 개선 방안', 한국 정보처리학회 논문지, 제3권 4호, 1996년 7월
4 Sergios Theodoridis, Konstantinos Koutroumbas, 'Pattern Recognition,' ACADEMIC PRESS, 1999
5 Teuvo Kohonen, 'The Self Organizing Map,' Proceeding of the IEEE, Vol.78, No.9, pp.1464-1480, Sep. 1990   DOI   ScienceOn
6 Simon Haykin, 'Neural Networks A Comprehensive Foundation,' PRENTICE HALL, 1999
7 Lefteri H. Tsoukalas, Robert E. Uhrig, 'Fuzzy and Neural Approachs in Engineering,' Wiley Interscience publication, 1997
8 G. A. Capenter, S. Grossverg, 'ART2: Self Organization of Stable Category Recognition Codes for Analog Input Patterns,' Applied Optics, Vol. 26, No. 23, 1987, pp.4919-4930
9 G. A. Carpenter, S. Grossberg, 'The ART of Adaptive Pattern Recognition by a Self Organizing Neural Network,' Computer, Vol. 21, No.3, 1988, pp.77-88   DOI   ScienceOn
10 김도현, 강동구, 강민경, 차의영, '문자 인식을 위한 효율적인 획 정규화', 한국 정보처리학회 추게학술대회 상권, 2001년   과학기술학회마을
11 Nikhil R. Pal, James C. Bezdek, 'Generalized Clustering Networks and Kohonen's Self Organizing Scheme,' IEEE Transaction on Neural Networks, Vol.4, No.4, pp.549-557, July 1993   DOI   ScienceOn
12 Jing Wu, Hong Yan, 'Combined SOM and LVQ Based Classifiers for Handwritten Digit Recognition,' Proceeding of the IEEE on Neural Networks, Vol.6, pp.3074-3077, 1995   DOI
13 A. Sanker. R.J.Mammone, 'Neural Tree Networks,' in Neural Networks : Theory and Applications, Academic Press, 1991
14 A. Sanker, R.J.Mammone, 'Growing and pruning neural tree networks,' IEEE transaction Computer, Vol.42, pp.291-299, 1993   DOI   ScienceOn
15 Pham, D.T. Sukkar, M.F., 'Supervised adaptive resonance theory neural network for modelling dynamic systems,' Systems, Man and Cybernetics, Vol. 3 , 1995, pp.2500-2505   DOI
16 Sorheim, E., 'A combined network architecture using ART2 and back propagation for adaptive estimation of dynamical processes,' System Sciences, Proceedings of the Twenty Fourth Annual Hawaii International Conference on, Vol. 1, 1991, pp.468-475   DOI
17 Behnke, S.; Karayiannis, N.B., 'Competitive neural trees for pattern classification Neural Networks,' IEEE Transactions on Neural Networks , Vol.9, No.6, pp. 1352-1369, Nov 1998   DOI   ScienceOn