Evolution-fuzzy rule based system with parameterized consequences

Piotr Czekalski

International Journal of Applied Mathematics and Computer Science (2006)

  • Volume: 16, Issue: 3, page 373-385
  • ISSN: 1641-876X

Abstract

top
While using automated learning methods, the lack of accuracy and poor knowledge generalization are both typical problems for a rule-based system obtained on a given data set. This paper introduces a new method capable of generating an accurate rule-based fuzzy inference system with parameterized consequences using an automated, off-line learning process based on multi-phase evolutionary computing and a training data covering algorithm. The presented method consists of the following steps: obtaining an initial set of rules with parameterized consequences using the Michigan approach combined with an evolutionary strategy and a covering algorithm for the training data set; reducing the obtained rule base using a simple genetic algorithm; multi-phase tuning of the fuzzy inference system with parameterized consequences using the Pittsburgh approach and an evolutionary strategy. The paper presents experimental results using popular benchmark data sets regarding system identification and time series prediction, providing a reliable comparison to other learning methods, particularly those based on neuro-fuzzy, clustering and ε-insensitive methods. An examplary fuzzy inference system with parameterized consequences using the Reichenbach implication and the minimum t-norm was implemented to obtain numerical results. sm

How to cite

top

Czekalski, Piotr. "Evolution-fuzzy rule based system with parameterized consequences." International Journal of Applied Mathematics and Computer Science 16.3 (2006): 373-385. <http://eudml.org/doc/207800>.

@article{Czekalski2006,
abstract = {While using automated learning methods, the lack of accuracy and poor knowledge generalization are both typical problems for a rule-based system obtained on a given data set. This paper introduces a new method capable of generating an accurate rule-based fuzzy inference system with parameterized consequences using an automated, off-line learning process based on multi-phase evolutionary computing and a training data covering algorithm. The presented method consists of the following steps: obtaining an initial set of rules with parameterized consequences using the Michigan approach combined with an evolutionary strategy and a covering algorithm for the training data set; reducing the obtained rule base using a simple genetic algorithm; multi-phase tuning of the fuzzy inference system with parameterized consequences using the Pittsburgh approach and an evolutionary strategy. The paper presents experimental results using popular benchmark data sets regarding system identification and time series prediction, providing a reliable comparison to other learning methods, particularly those based on neuro-fuzzy, clustering and ε-insensitive methods. An examplary fuzzy inference system with parameterized consequences using the Reichenbach implication and the minimum t-norm was implemented to obtain numerical results. sm},
author = {Czekalski, Piotr},
journal = {International Journal of Applied Mathematics and Computer Science},
keywords = {evolutionary strategy; off-linelearning; hybrid system; fuzzy inference system; off-line learning},
language = {eng},
number = {3},
pages = {373-385},
title = {Evolution-fuzzy rule based system with parameterized consequences},
url = {http://eudml.org/doc/207800},
volume = {16},
year = {2006},
}

TY - JOUR
AU - Czekalski, Piotr
TI - Evolution-fuzzy rule based system with parameterized consequences
JO - International Journal of Applied Mathematics and Computer Science
PY - 2006
VL - 16
IS - 3
SP - 373
EP - 385
AB - While using automated learning methods, the lack of accuracy and poor knowledge generalization are both typical problems for a rule-based system obtained on a given data set. This paper introduces a new method capable of generating an accurate rule-based fuzzy inference system with parameterized consequences using an automated, off-line learning process based on multi-phase evolutionary computing and a training data covering algorithm. The presented method consists of the following steps: obtaining an initial set of rules with parameterized consequences using the Michigan approach combined with an evolutionary strategy and a covering algorithm for the training data set; reducing the obtained rule base using a simple genetic algorithm; multi-phase tuning of the fuzzy inference system with parameterized consequences using the Pittsburgh approach and an evolutionary strategy. The paper presents experimental results using popular benchmark data sets regarding system identification and time series prediction, providing a reliable comparison to other learning methods, particularly those based on neuro-fuzzy, clustering and ε-insensitive methods. An examplary fuzzy inference system with parameterized consequences using the Reichenbach implication and the minimum t-norm was implemented to obtain numerical results. sm
LA - eng
KW - evolutionary strategy; off-linelearning; hybrid system; fuzzy inference system; off-line learning
UR - http://eudml.org/doc/207800
ER -

References

top
  1. Angelov P. (2002): Evolving Rule-Based Models. A Tool for Design of Flexible Adaptive Systems. - Wurzburg: Physica-Verlag. Zbl1043.93001
  2. Arabas J. (2001): Lectures on Evolutionary Algorithms. - Warsaw: Wydawnictwa Naukowo-Techniczne, (in Polish). 
  3. Baron L., Achiche S. and Balazinski M. (2001): Fuzzy decision support system knowledge base generation using a genetic algorithm. - Int. J. Approx. Reason., Vol. 1, No. 28, pp. 125-148. Zbl0991.68089
  4. Bezdek J. (1981): Pattern Recognition with Fuzzy Objective Function Algorithms. - New York: Plenum Press. Zbl0503.68069
  5. Bonarini A. (1996): Evolutionary learning of fuzzy rules: Competition and cooperation, In: Fuzzy Modelling: Paradigms and Practice (W. Pedrycz, Ed.). - Norwell: Kluwer. Zbl0881.68098
  6. Box G. and Jenkins G. (1976): Time Series Analysis. Forecasting and Control. - San Francisco: Holden-Day. Zbl0363.62069
  7. Carse B., Fogarty T.C. and Munro A. (1996): Evolving fuzzy rule based controllers using genetic algorithms. - Fuzzy Sets Syst., Vol. 80, No. 3, pp. 273-294. 
  8. Chen J.Q., Xi Y.G. and Zhang Z.J. (1998): A clustering algorithm for fuzzy model identification. - Fuzzy Sets Syst., Vol. 98,No. 3, pp. 319-329. 
  9. Cordon O. and Herrera F. (1997a): Identification of linguistic fuzzy models by means of genetic algorithms, In: Fuzzy Model Identification. Selected Approaches (D. Driankow and H. Hellendoorn, Eds.). - Berlin: Springer. Zbl0899.93008
  10. Cordon O. and Herrera F. (1997b): A three-stage evolutionary process for learning descriptive and approximative fuzzy logic controller knowledge bases from examples. - Int. J. Approx. Reason., Vol. 17, No. 4, pp. 369-407. Zbl1078.93541
  11. Cordon O. and Herrera F. (2001): Hybridizing genetic algorithms with sharing scheme and evolution strategies for designing approximate fuzzy rule-based systems. - Fuzzy Sets Syst., Vol. 118, No. 2, pp. 235-255. Zbl0985.68049
  12. Cordon O., Del Jesus M., Herrera F. and Lozano M. (1999): MOGUL: A methodology to obtain genetic fuzzy rule-based systems under the iterative rule learning approach. - Int. J. Intell. Syst., Vol. 14, No. 11, pp. 1123-1153. Zbl0941.68750
  13. Cordon O., Herrera F., Hoffmann F. and Magdalena L. (2001): Genetic Fuzzy Systems: Evolutionary Tuning and Learning of Fuzzy Knowledge Bases. - Singapore: World Scientific. Zbl1042.68098
  14. Cordon O., Gomide F., Herrera F., Hoffmann F. and Magdalena L. (2004): Ten years of genetic fuzzy systems: Current framework and new trends. - Fuzzy Sets Syst., Vol. 141, No. 1, pp. 5-31. Zbl1050.93513
  15. Czogala E. and Łęski J. (1996): A new fuzzy inference system with moving consequent in if-then rules. Application to pattern recognition. - J. Bull. Polish Acad. Sci., Vol. 45, No. 4, pp. 643-655. Zbl0954.68133
  16. Czogala E. and Łęski J. (1999): Fuzzy and Neuro-Fuzzy Intelligent Systems. - Heidelberg: Physica-Verlag. Zbl0953.68122
  17. Fuller R. (1999): Introduction to Neuro-Fuzzy Systems. - Wurzburg: Physica-Verlag. Zbl0937.68098
  18. Gonzalez A. and Perez R. (1999): SLAVE: A genetic learning system based on an iterative approach. - IEEE Trans. Fuzzy Syst., Vol. 7, No. 2, pp. 176-191. 
  19. Herrera F. and Verdegay J. (1996): Genetic Algorithms and Soft Computing. - Wurzburg: Physica-Verlag. Zbl0870.68019
  20. Herrera F., Lozano M. and Verdegay J.L. (1995): Tuning fuzzy logiccontrollers by genetic algorithms. - Int. J. Approx. Reason., Vol. 12, No. 3, pp. 299-315. Zbl0875.93242
  21. Hoffmann F. and Pfister G. (1997): Evolutionary design of a fuzzy knowledge base for a mobile robot. - Int. J. Approx. Reason., Vol. 17, No. 4, pp. 447-469. Zbl1078.93543
  22. Holland J. (1975): Adaptation in Natural and Artificial Systems. - University of Michigan Press, Ann Arbor. 
  23. Holland J. and Reitman J. (1978): Cognitive systems based on adaptive algorithms, In: Pattern-Directed Inference Systems (D.A. Waterman and F. Hayes-Roth, Eds.). - New York: Academic Press. 
  24. Ishibuchi H., Nakashima T. and Murata T. (1999): Performance evaluation of fuzzy classifier systems for multidimensional pattern classification problems. - IEEE Trans. Syst. Man Cybern., Vol. 29, No. 5, pp. 601-618. 
  25. Kim E., Park M. and Ji S. (1997): A new approach to fuzzy modeling. - IEEE Trans. Fuzzy Syst., Vol. 5, No. 3, pp. 328-337. 
  26. Lee M.A. and Takagi H. (1993): Integrating design stages of fuzzy systems using genetic algorithms. - Proc. 2nd IEEE Int. Conf. s Fuzzy Systems, San Francisco, CA, pp. 613-617. 
  27. Łęski J. (2005): TSK-fuzzy modeling based on ε-insensitive learning. - IEEE Trans. Fuzzy Syst., Vol. 13, No. 2, pp. 181-193. 
  28. Łęski J. (2006): Neuro-Fuzzy Systems. - Warsaw: Wydawnictwa Naukowo-Techniczne, (in Polish). Zbl0953.68122
  29. Łęski J. and Czogala E. (1999): A new artifficial neural network based fuzzy inference system with moving consequents in if-then rules and selected applications. - Fuzzy Sets Syst., Vol. 108, No. 3, pp. 289-297. Zbl0942.93022
  30. Lin Y. and Cunningham H. (1995): A new approach to fuzzy-neural modeling. - IEEE Trans. Fuzzy Syst., Vol. 3, No. 2, pp. 190-197. 
  31. Magdalena L. and Monasterio F. (1997): A Fuzzy logic controller with learning through the evolution of its knowledge base. - Int. J. Approx. Reason., Vol. 16, Nos. 3-4, pp. 335-358. Zbl0947.93513
  32. Mamdani E. and Assilian S. (1975): An experiment in linguistic synthesis with a fuzzy logic controller. - Int. J. Man-Mach. Stud., Vol. 7, No. 1, pp. 1-13. Zbl0301.68076
  33. Michalewicz Z. (2003): Genetic Algorithms + Data Structures = Evolution Programs. - Warsaw: Wydawnictwa Naukowo-Techniczne, (in Polish). Zbl0841.68047
  34. Park D., Kandel A. and Langholz G. (1994): Genetic-based new fuzzy reasoning models with application to fuzzy control. - IEEE Trans. Syst. Man Cybern., Vol. 24, No. 1,linebreak pp. 39-47. Zbl0850.93452
  35. Parodi A. and Bonelli P. (1993): A new approach to fuzzy classifier systems. - Proc. 5-th Int. Conf. s Genetic Algorithms, Los Altos, pp. 223-230. 
  36. Pedrycz W. (1984): An identification algorithm in fuzzy relational systems. - Fuzzy Sets Syst., Vol. 13, No. 2, pp. 153-167. Zbl0554.93070
  37. Pedrycz W. (1997): Fuzzy Evolutionary Computation. - Dordrecht: Kluwer. Zbl0869.00012
  38. Pham D. and Karaboga D. (1991): Optimum design of fuzzy logic controllers using genetic algorithms. - J. Syst. Eng., Vol. 1, No. 2, pp. 114-118. 
  39. Sugeno M. and Kang G. (1988): Structure identification of fuzzy model. - Fuzzy Sets Syst., Vol. 28, No. 1, pp. 15-33. Zbl0652.93010
  40. Sugeno M. and Yasukawa T. (1993): A fuzzy-logic based approach to qualitative modeling. - IEEE Trans. Fuzzy Syst., Vol. 1, No. 1, pp. 7-31. 
  41. Tadeusiewicz R. (1998): Fundamental introduction to neural neworks techniques with sample implementations. - Warsaw: Akademicka Oficyna Wydawnicza PLJ, (in Polish). 
  42. Takagi T. and Sugeno M. (1985): Fuzzy identification of systems and its application to modelling and control. - IEEE Trans. Syst. Man Cybern., Vol. 15, No. 1, pp. 116-132. Zbl0576.93021
  43. Thrift P. (1991): Fuzzy logic synthesis with genetic algorithms. - Proc. 4-th Int. Conf. s Genetic Algorithms, Los Altos, pp. 509-513. 
  44. Tong R. (1980): The evaluation of fuzzy models derived from experimental data. - Fuzzy Sets Syst., Vol. 4, pp. 1-12. Zbl0453.93003
  45. Valenzuela-Rendon M. (1991): The fuzzy classifier system: Motivations and first results. - Proc. 1-st Int. Conf. Parallel Problem Solving from Nature, Berlin, pp. 330-334. 
  46. Velasco J. (1998): Genetic-based on-line learning for fuzzy process control. - Int. J. Intell. Syst., Vol. 13, Nos. 10-11, pp. 891-903. 
  47. Wang L. and Langari R. (1995): Building Sugeno-type models using fuzzy discretization and orthogonal parameter estimation techniques. - IEEE Trans. Fuzzy Syst., Vol. 3, No. 4, pp. 454-458. 
  48. Weigend A., Huberman B. and Rumelhart D. (1990): Predicting the future: A connectionist approach. - Int. J. Neural Syst., Vol. 1, No. 3, pp. 193-209. 
  49. Xu C. and Lu Y. (1987): Fuzzy modeling identification and self-learining for dynamic systems. - IEEE Trans. Syst. Man Cybern., Vol. 17, No. 4, pp. 683-689. Zbl0643.93018
  50. Zadeh L. (1971): Towards a theory of fuzzy systems, In: Aspects of Network and System Theory (R.E. Kalman and N. De Claris, Eds.). - New York: Holt, Rinehart and Winston. 
  51. Zikidis K. and Vasilakos A. (1996): ASAFES2: A novel, neuro-fuzzy architecture for fuzzy computing, based on functional reasoning. - Fuzzy Sets Syst., Vol. 83, No. 1, pp. 63-68. 

NotesEmbed ?

top

You must be logged in to post comments.