Choquet Integral-OWA Based Adaptive Neural Fuzzy Inference System and Its Application

In order to solve the defects of consequent part expression in ANFIS(adaptive neural fuzzy inference system) model and several shortcomings in FTS(fuzzy inference system),this paper presents a Choquet integral-OWA(outlook web access) based FTS,known as AggFIS.This model has advantages in consequent part of fuzzy rule,universal expression of fuzzy inference operator and importance factor of each input and each rule,aiming at establish fuzzy inference system that can fully reflect the essence of fuzzy logic and human thinking patterns.If AggFIS is combined with a feed forward-type neural network according to the basic principles of fuzzy neural network,the Choquet integral-OWA based adaptive neural fuzzy inference system(Agg-ANFTS) is obtained,which is applied to the evaluation of traffic level of service.Experimental results show that Agg-ANFTS is a universal approximator because of its nonlinear mapping capability by training and can be used in,analysis and prediction of complex systems modelling.