USING HIGHER ORDER STATISTICS AND FUZZY MODELS
Jilali Antari, Radouane Iqdour, Saïd Safi, Abdelouhab Zeroual, Abdelouahid Lyhyaoui, Tangier Principal Morocco · 2006
In this work we compare tow methods for the identification of non-linear systems. The first one uses a quadratic non linear model of which parameters are estimated using a new algorithm based on the fourth order cumulants. The second one is based on the Takagi-Sugeno fuzzy models. The simulation results show that the fuzzy models give the good results in noiseless and weak noise environment. However the quadratic model of which parameters are identified using the proposed algorithm works well in the high noise environment case.