Adaptive network-based fuzzy inference system with pruning

There have been many researches about fuzzy model having the approximation property of the given input-output relationship. Especially, Takagi-Sugeno fuzzy models are widely used because they show very good performance in the nonlinear function approximation problem. But generally there is not the systematic method encapsulating the human expert´s knowledge or experience in fuzzy rules and besides it is not easy to find the membership function of fuzzy rule to minimize the output error. The ANFIS (Adaptive Network-based Fuzzy Inference Systems) is one of the fuzzy modelling methods that work quite well and are used with various types of fuzzy rules. But in this model, it is the problem to find the optimum number of fuzzy rules in fuzzy model. In this paper, a new fuzzy modelling method based on the ANFIS and pruning technique with appropriate measure named impact factor is proposed and the performance of proposed method is evaluated with several simulation results.