A Functional-link-based Fuzzy Brain Emotional Learning Network for Breast Tumor Classification and Chaotic System Synchronization

Abstract

This paper aims to propose an efficient neural network and applies it for both classification and control problems. A functional link-based fuzzy brain emotional learning network is developed. The proposed network is a generalization of several existing neural networks, such as a function link neural network, a fuzzy neural network and a brain emotional learning network. This network can be used as a classifier in which breast tumors are divided as either benign tumors or malignant tumors. Meanwhile, it can be also applied to control an uncertain nonlinear system. The parameters of the network are all modified online by the derived adaptation laws. In addition, a stable convergence is guaranteed by utilizing the Lyapunov stability theorem. Finally, the proposed method is applied for the breast tumor classification and the chaotic system synchronization. A comparison between the proposed method with other networks show that the proposed network has higher accuracy and sensitivity when serving as a classifier and can reduce the tracking error effectively when serving as a controller.