DOI QR코드

DOI QR Code

Design of Fuzzy Neural Networks Based on Fuzzy Clustering and Its Application

퍼지 클러스터링 기반 퍼지뉴럴네트워크 설계 및 적용

  • Park, Keon-Jun (Department of Information Communication Engineering, Wonkwang University) ;
  • Lee, Dong-Yoon (Department of Electrical Electronic Engineering, Joongbu University)
  • 박건준 (원광대학교 정보통신공학과) ;
  • 이동윤 (중부대학교 전기전자공학과)
  • Received : 2012.10.11
  • Accepted : 2013.01.10
  • Published : 2013.01.31

Abstract

In this paper, we propose the fuzzy neural networks based on fuzzy c-means clustering algorithm. Typically, the generation of fuzzy rules have the problem that the number of fuzzy rules exponentially increases when the dimension increases. To solve this problem, the fuzzy rules of the proposed networks are generated by partitioning the input space in the scatter form using FCM clustering algorithm. The premise parameters of the fuzzy rules are determined by membership matrix by means of FCM clustering algorithm. The consequence part of the rules is expressed in the form of polynomial functions and the learning of fuzzy neural networks is realized by adjusting connections of the neurons, and it follows a back-propagation algorithm. The proposed networks are evaluated through the application to nonlinear process.

본 논문에서는 FCM 클러스터링 알고리즘을 기반으로 하는 퍼지뉴럴네트워크를 제안한다. 일반적으로, 퍼지규칙을 생성할 때 차원이 증가하면 퍼지 규칙의 수가 기하급수적으로 증가하는 문제를 가지고 있다. 이를 해결하기 위해, 제안된 네트워크의 퍼지 규칙은 FCM 클러스터링 알고리즘을 이용하여 입력 공간을 분산 형태로 분할함으로써 생성한다. 퍼지 규칙의 전반부 파라미터는 FCM 클러스터링 알고리즘에 의한 소속행렬로 결정된다. 퍼지 규칙의 후반부는 다항식 함수의 형태로 표현되며, 퍼지뉴럴네트워크의 학습은 뉴런의 연결을 조절함으로써 실현되고, 오류 역전파 알고리즘에 의해 행해진다. 마지막으로, 제안된 네트워크는 비선형 공정으로의 적용을 통해 성능을 평가한다.

Keywords

References

  1. T. Yamakawa, "A Neo Fuzzy Neuron and Its Application to System Identication and Predition of the System Behavior", Proceeding of the 2nd International Conference on Fuzzy logic & Neural Networks, pp. 447-483, 1992.
  2. J. J. Buckley and Y. Hayashi, "Fuzzy neural networks: A survey", Fuzzy Sets and Systems, Vol. 66, pp. 1-13, 1994. DOI: http://dx.doi.org/10.1016/0165-0114(94)90297-6
  3. J.-S. R. Jang, C. -T. Sun, E. Mizutani, Neuro-Fuzzy And Soft Computing, Prentice-Hall, 1997.
  4. J. S. Roger Jang, "ANFIS : Adaptive-Network-based Fuzzy Inference Systems", IEEE Transactions on Systems, Man, and Cybernetics, Vol. 23, No. 3, pp. 665-685, 1993. DOI: http://dx.doi.org/10.1109/21.256541
  5. K. J. Park, D. Y. Lee, "Characteristics of Fuzzy Inference Systems by Means of Partition of Input Spaces in Nonlinear Process", The Korea Contents Association, Vol. 11, No. 3, pp. 48-55, 2011. DOI: http://dx.doi.org/10.5392/JKCA.2011.11.3.048
  6. K. J. Park, D. Y. Lee, "Characteristics of Input-Output Spaces of Fuzzy Inference Systems by Means of Membership Functions and Performance Analyses", The Korea Contents Association, Vol. 11, No. 4, pp. 74-82, 2011. https://doi.org/10.5392/JKCA.2011.11.4.074
  7. K. J. Park, D. Y. Lee, "Nonlinear Characteristics of Fuzzy Inference Systems by Means of Individual Input Space", The Korea Academia-Industrial Cooperation Society, Vol. 12, No. 11, pp. 5164-5171, 2011. DOI: http://dx.doi.org/10.5762/KAIS.2011.12.11.5164
  8. K. C. Yoon, B. G. Park, S. K. Oh, S. H. Lee, "The Design of Fuzz-Neural Networks Using FCM Algorithms", The Proceeding of KIEE conference, pp. 803-805, 2000.11
  9. J. N. Choi, S. K. Oh, H. K. Kim, "Genetic Optimization of Fuzzy C-Means-Based Fuzzy Neural Networks", KIEE, Vol, 57, No. 3, pp. 466-472, 2008.3
  10. J. C. Bezdek, Pattern Recognition with Fuzzy Objective Function Algorithms, PlenumPress, NewYork, 1981.
  11. Box and Jenkins, Time Series Analysis, Forcasting and Control, Holden Day, SanFrancisco, CA.

Cited by

  1. Characteristics of Gas Furnace Process by Means of Partition of Input Spaces in Trapezoid-type Function vol.12, pp.4, 2014, https://doi.org/10.14400/JDC.2014.12.4.277