Approximation and its implementation process of the stochastic hybrid fuzzy system

Abstract The stochastic Mamdani and Takagi–Sugeno fuzzy systems are firstly unified in a random environment, and the resulting stochastic hybrid fuzzy system is established according to some stochastic parameters. Secondly, A canonical representation of the stochastic process with orthogonal increments is presented by the properties of the Lebesgue–Stieltjes measure and stochastic integral, the approximation of the stochastic hybrid fuzzy system in the mean square sense is proved. Finally, an implementation process of this system is described through a simulation example, and the surface figure of the covariance function shows that the stochastic hybrid fuzzy system has excellent approximation capability.

[1]  Xizhao Wang,et al.  Induction of multiple fuzzy decision trees based on rough set technique , 2008, Inf. Sci..

[2]  Xiaoping Li,et al.  Universal approximation of polygonal fuzzy neural networks in sense of K-integral norms , 2011, Science China Information Sciences.

[3]  Hongxing Li,et al.  Approximation of stochastic processes by T-S fuzzy systems , 2005, Fuzzy Sets Syst..

[4]  Duan Chen-xia,et al.  Generalized hierarchical hybrid fuzzy system and its universal approximation , 2012 .

[5]  Basil K. Papadopoulos,et al.  Hybrid (fuzzy-stochastic) modelling in construction operations management , 2013, Int. J. Mach. Learn. Cybern..

[6]  Ricardo J. G. B. Campello,et al.  Hierarchical fuzzy relational models: linguistic interpretation and universal approximation , 2002, IEEE Transactions on Fuzzy Systems.

[7]  Emil M. Petriu,et al.  Experiment-Based Teaching in Advanced Control Engineering , 2011, IEEE Transactions on Education.

[8]  Alexander A. Gushchin.  General Theory of Stochastic Processes , 2015 .

[9]  Li-Xin Wang,et al.  Universal approximation by hierarchical fuzzy systems , 1998, Fuzzy Sets Syst..

[10]  Liu Puyin.  Approximation of generalized fuzzy system to integrable function , 2000 .

[11]  Wang Gui,et al.  Universal Approximation and Its Realization of Generalized Mamdani Fuzzy System Based on K-integral Norms , 2014 .

[12]  Hongxing Li,et al.  Analyses for Lp(µ)-norm approximation capability of generalized Mamdani fuzzy systems , 2001, Inf. Sci..

[13]  Chunmei He,et al.  Approximation of polygonal fuzzy neural networks in sense of Choquet integral norms , 2014, Int. J. Mach. Learn. Cybern..

[14]  Li Hong-xing,et al.  Generalized hierarchical Mamdani fuzzy systems and their universal approximation , 2006 .

[15]  Korris Fu-Lai Chung,et al.  Positive and negative fuzzy rule system, extreme learning machine and image classification , 2011, Int. J. Mach. Learn. Cybern..

[16]  G Wang,et al.  Capability of Universal Approximation of Feedforward Regular Fuzzy Neural Networks in K-Integral Norm , 2013 .

[17]  Paolo Crippa,et al.  On the approximation of stochastic processes by approximate identity neural networks , 1998, IEEE Trans. Neural Networks.

[18]  Mohammad Ghasem Akbari,et al.  Some fuzzy stochastic orderings for fuzzy random variables , 2012, Fuzzy Optim. Decis. Mak..

[19]  J. Doob.  Stochastic processes , 1953 .

[20]  Didier Maquin,et al.  Fault detection, isolation and estimation for Takagi-Sugeno nonlinear systems , 2014, J. Frankl. Inst..

[21]  Esfandiar Eslami,et al.  Some Types of Filters in BL Algebras , 2007, Soft Comput..

[22]  Puyin Liu,et al.  Mamdani fuzzy system: universal approximator to a class of random processes , 2002, IEEE Trans. Fuzzy Syst..

[23]  Li-Juan Wang,et al.  An improved multiple fuzzy NNC system based on mutual information and fuzzy integral , 2011, Int. J. Mach. Learn. Cybern..

[24]  Pei-Hwa Huang,et al.  Robust fuzzy control for uncertain stochastic time-delay Takagi-Sugeno fuzzy models for achieving passivity , 2010, Fuzzy Sets Syst..

[25]  Xiao-Jun Zeng,et al.  Approximation Capabilities of Hierarchical Fuzzy Systems , 2005, IEEE Transactions on Fuzzy Systems.