Journal of the Korean Institute of Intelligent Systems (한국지능시스템학회논문지)

Korean Institute of Intelligent Systems (한국지능시스템학회)
권호 표지

Fuzzy Learning Algorithms for Time Series Prediction

시계열 예측을 위한 퍼지 학습 알고리즘

  • 김인택 (명지대학교 제어계측공학과) ;
  • 공창욱 (명지대학교 제어계측공학과)
  • Published : 1997.08.01
Download PDF
⟨ Previous Next ⟩

Abstract

This paper presents new fuzzy learning algorithms and their applications to time series prediction. During generating fuzzy rules from numerical data, there is a tendency to produce conflicting rules which have same premise but different consequence. To resolve the problem, we propose MCM(Modified Center Method) which is proven to reduce the error in the prediction. We have applied MCM to the analysis of Mackey-Glass time series and Gas Furnace da.ta to verify its efficiency.

본 논문은 새로은 퍼지 규칙의 생성을 위한 학습 알고리즘과 시계열 예측에의 응용을 다루고 있다. 데이터에서 IF-THEN문 형태의 퍼지 규칙을 생성시키는 과정에서 동일한 전건부(IF문)에 대해 상이한 후건부(THEN문)가 생겨 모순된 규칙을 형성시키는 경향이 있다. 수정된 중심값 방법(Modified Center Method)으로 명명된 새로운 알고리즘은 이와 같은 모순된 규칙의 형성을 효과적으로 해결하여, 시계열 예측을 수행하는데 그 오차를 줄일 수 있다. 알고리즘의 효과를 살표보기 위해 Mackey-Glass time series와 Gas Furnace data 분석에 적용하였다.

Keywords

References

  1. Time Series Prediction Andress S. Weigend;Neil A. Gerhenfeld(ED.)
  2. Physica D . v.8 The Infinite Number of Generalizes Dimnensions of Fractals and Strange Attractors H.G.E. Hentschel;I.Procaccia
  3. TIME SERIES Forecasting, Simulation, Applications G.Jnacek;L.Swin
  4. Time Series Anlysis:Forecasting and Control(2nd ed.) G.E.P.Box;F.M.Jenkins
  5. Time Series Prediction Time Series Prediction by Using a Connectionist Network with Internal Delay Lines E.R.Wan
  6. IEEE Trans. on Power Systems v.10 no.1 Practical Experiences with An Adaptive Neural Network Short-Term Load Forecasting System O. Mohammed;D. Park;R. Merchant;R. Dinh;C. Tong;A. Azzem;J. Farah;C. Drake
  7. IEEE Trans. on Systems, Man, and Cybern. v.22 no.6 Generating fuzzy rules from numerical data;with applications L.X.Wang;J.M.Mendel
  8. 3rd International Conf. on Fuzzy Logic;Netural Nets and Soft Computing Chaotic Time Series Prediction I. Kim;S. Lee
  9. Proc. IEEE International Conf. on fuzzy Systems Fuzzy systems are universal approximators L. X. Wang
  10. Neural Network v.2 Multilayer feedforward networks are universal approximators K.Hornik;M.Stinchcombe;H.White
  11. Fuzzy Ssets and Systems v.4 The Ecaluation of Fuzzy Models derived frim Experimental Data R.M.Tong
  12. Fuzzy Control and Fuzzy Systems W. Pedrycz
  13. 2nd IEEE Inter. Conf. Fuzzy Systems Predicting Chaotic Tome Series with Fuzzy If-Then Rules J. R. Jang;C. Su