From Epanechnikov Mixture Model to Rule-Centered Fuzzy Model and its Application to Stock Index Prediction


Article Preview

In this paper, the mathematical equivalence between the conditional mean of a Epanechnikov mixture model (EMM) and the defuzzified output of a rule-centered generalized fuzzy model (RCGFM) is derived theoretically. Our results provide a new perspective for fuzzy systems, i.e., interpreting them from a probabilistic viewpoint. Thus, instead of directly estimating the parameters of the fuzzy rules in a rule-centered generalized fuzzy model, we can first estimate the parameters of the corresponding EMM using any popular density estimation algorithm like the expectation maximization (EM) algorithm. Our experimental results clearly indicate that a rule-centered generalized fuzzy model trained in such a new way has higher approximation accuracy and generalization ability than other models.



Advanced Materials Research (Volumes 989-994)

Edited by:

S.Z. Cai, Q.F. Zhang, X.P. Xu, D.H. Hu and Y.M. Qu




Q. L. Zhang, "From Epanechnikov Mixture Model to Rule-Centered Fuzzy Model and its Application to Stock Index Prediction", Advanced Materials Research, Vols. 989-994, pp. 2719-2722, 2014

Online since:

July 2014





* - Corresponding Author

[1] Ming-Tao Gan and Madasu Hanmandlu: IEEE Transactions on Fuzzy System , vol. 13(2005), p.303.

[2] Y M. F. Azeem, M. Hanmandlu, and N. Ahmad: IEEE Trans. On Neural Networks, vol. 11(2000), p.1332.

[3] Janos Abonyi, Robert Babuska and Ferenc Szeifert: IEEE Trans. on Systems, Man, and Cybernetics, vol. 31(2001), p.755.

[4] Marwan Bikdash: IEEE Trans. Fuzzy Systems , vol. 7(1999), p.686.

[5] Dorin Comaniciu and Peter Meer: IEEE Trans. On Pattern Analysis and Machine Intellegence, vol. 24(2002), p.603.

[6] Wan-cai Yang, Xin-qian Wu, Er-xin Zhang and Guang Zhu, in: Proc. 19th international conference on industrial engineering and engineering management, edited by Qi Ershi et. al. /Springer, Changsha Hunan(2013).


[7] Benjamin Hartmann, Oliver Banfer, Oliver Nelles, Anton Sodja, Luka Teslic, and Igor Skrjanc, IEEE Transactions on Fuzzy ystems, vol. 19(2011), p.1163.