Nonlinear system identification using ANFIS based on emotional learning

Abstract

In this paper using emotional learning, the performance of Adaptive Network Fuzzy Inference System (ANFIS) will be enhanced. Neural networks and Neurofuzzy models have been successfully used in nonlinear time series prediction. Many of the existing methods for learning algorithm of these networks, constructed over Takagi Sugeno fuzzy inference system, are characterized by high generalization. However, they differ in computational complexity. A practical approach towards the prediction of real world data such as the sunspot number time series profound a method to follow multiple goals. For example predicting the peaks of sunspot numbers (maximum of solar activity) is more important due to its major effects on earth and satellites. The proposed Emotional Learning Based Fuzzy Inference System (ELFIS) has the advantage of low computational complexity in comparison with other multi-objective optimization methods. © Springer-Verlag Berlin Heidelberg 2004.