Variable cluster analysis method for building neural network model

Article
Received:
Accepted:
  • 37 Downloads

Abstract

To address the problems that input variables should be reduced as much as possible and explain output variables fully in building neural network model of complicated system, a variable selection method based on cluster analysis was investigated. Similarity coefficient which describes the mutual relation of variables was defined. The methods of the highest contribution rate, part replacing whole and variable replacement are put forwarded and deduced by information theory. The software of the neural network based on cluster analysis, which can provide many kinds of methods for defining variable similarity coefficient, clustering system variable and evaluating variable cluster, was developed and applied to build neural network forecast model of cement clinker quality. The results show that all the network scale, training time and prediction accuracy are perfect. The practical application demonstrates that the method of selecting variables for neural network is feasible and effective.

Key words

variable cluster neural network information theory cluster tree 

CLC number

TP183 
This is a preview of subscription content, log in to check access.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    Skrzpek T. Neural Network Simulation Environments [M]. Massachusetts: Kluwer Academic Publishers, 1993.Google Scholar
  2. [2]
    Patterson D W. Artificial Neural Networks: Theory and Applications [M]. New Jersey: Prentice Hall, 1996.Google Scholar
  3. [3]
    Arbib M M. The Handbook of Brain Theory and Neural Networks [M]. Boston: The MIT Press, 1995.Google Scholar
  4. [4]
    Kastra M. Forecasting combined with neural networks[J]. Journal of Forecast, 1996,15(1):49–61.CrossRefGoogle Scholar
  5. [5]
    Widrow B. Neural network application in industry, business and science[J]. Communcation of the ACM, 1994,37: 93–105.CrossRefGoogle Scholar
  6. [6]
    YAN Ping-fan, ZHANG Chang-shui. Artificial Neural Network and Computing with the Simulation of Evolution [M]. Beijing: Tsinghua University Publishers, 2000. (in Chinese)Google Scholar
  7. [7]
    Hornik K. Multilayer feedforward network are universal approximators [J]. Neural Network, 1989, 15(2): 359–366.CrossRefGoogle Scholar
  8. [8]
    Jedward J. Principal components and factor analysis: principal components(Part 1) [J]. Journal of Quality Technology. 1980,12(4):512–517.Google Scholar
  9. [9]
    Michael J, Piovoso K, Kosanovich A. Applications of multivariate statistical methods to process monitoring and controller design [J]. Control, 1994,59(3):743–765.MATHMathSciNetGoogle Scholar
  10. [10]
    REN Ruo-en, WANG Hui-wen. Multiple Statistic Data Analysis-theories, Methods and Examples [M]. Beijing: Defence Industry Publishers, 1997. (in Chinese)Google Scholar
  11. [11]
    Pal N R, Bezdek J C. On cluster validity for the fuzzy mean model[J]. IEEE Trans on Fuzzy System, 1995,3(3):370–379.CrossRefGoogle Scholar
  12. [12]
    FANG Kai-tai, PAN En-pei. Cluster Analysis [M]. Beijing: Geologic Publishers, 1982. (in Chinese)Google Scholar
  13. [13]
    Donald G F. Object-oriented Requirements Analysis and Logical Design [M]. New York: John Wiley & Sons Inc, 1993.Google Scholar
  14. [14]
    Graham I. Object-oriented methods [M]. London: Addison Welseley Publishers Ltd, 1993.Google Scholar
  15. [15]
    SHEN Wei, HUANG Wen-xi, MIN Pan-rong. Technology of Cement [M]. Wuhan: Wuhan Industry University, 1995. (in Chinese)Google Scholar

Copyright information

© Science Press 1998

Authors and Affiliations

  1. 1.School of Resources Processing and BioengineeringCentral South UniversityChangshaChina

Personalised recommendations