ADAPTATION SCHEMES FOR A NEURO-FUZZY PREDICTOR

The paper presents, in a comparative study, six hybrid configurations that can assist the adaptation of the neuro-fuzzy system parameters. The suggested configurations involve various combinations of the gradient descent algorithm, the k-means clustering procedure and the genetic algorithms. The neurofuzzy system architecture is adopted from literature. The applicability of the methodology is investigated with respect to the time series prediction.

[1]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[2]  Andreas S. Weigend,et al.  Time Series Prediction: Forecasting the Future and Understanding the Past , 1994 .

[3]  Horia-Nicolai L. Teodorescu,et al.  A hybrid data-mining approach in genomics and text structures , 2003, Third IEEE International Conference on Data Mining.

[4]  Detlef Nauck,et al.  Foundations Of Neuro-Fuzzy Systems , 1997 .

[5]  Takeshi Yamakawa,et al.  Neuro-fuzzy systems: hybrid configurations , 1996 .

[6]  D. Zaldivar,et al.  Neurofuzzy prediction for visual tracking , 2004, (ICEEE). 1st International Conference on Electrical and Electronics Engineering, 2004..

[7]  Zbigniew Michalewicz,et al.  Evolutionary Computation 2 , 2000 .

[8]  Mihiar Ayoubi.  Nonlinear system identification based on neural networks with locally distributed dynamics and application to technical process , 1996 .

[9]  Zbigniew Michalewicz,et al.  Evolutionary Computation 2 : Advanced Algorithms and Operators , 2000 .

[10]  Robert Babuska,et al.  Neuro-fuzzy methods for nonlinear system identification , 2003, Annu. Rev. Control..

[11]  Hannu T. Toivonen,et al.  A NEURO-FUZZY MODEL PREDICTIVE CONTROLLER APPLIED TO A PH-NEUTRALIZATION PROCESS , 2002 .

[12]  H.-N. Teodorescu,et al.  Genome bases sequences characterization by a neuro-fuzzy predictor , 2003, Proceedings of the 25th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (IEEE Cat. No.03CH37439).