Design for Self-Organizing Fuzzy Neural Network with Extended Kalman Filter

Abstract

In this paper, a Self-organizing Fuzzy Neural Network employing an Extended Kalman Filter (EKF), termed Self-organizing Fuzzy Neural Networks with Extended Kalman Filter (SOFNNEKF) is designed and developed. The learning algorithm based on an EKF is simple and effective and is able to generate a fuzzy neural network with a high accuracy and compact structure. The structure learning of the SOFNNEKF, based on adding and pruning techniques is proposed. The EKF algorithm is used to adjust free parameters of the SOFNNEKF. Simulation and comparative studies with other methods demonstrate that a more compact structure with high performance can be achieved by the proposed algorithm.