Solution to the Outlier Samples Problem in Function Approximation Based on an Adapted Neural Fuzzy Inference System

2nd International Conference on Engineering Sciences

Raheema, M.N.^1 ; Abdullah, A.S.^2

Prosthetics and Orthotics Engineering Department, Engineering College, University of Kerbala, Kerbala, Iraq^1

College Al Safwa University, Karbala, Iraq^2

关键词: Function approximation;    Function approximation problems;    Fuzzy Inference systems (FIS);    Gaussian functions;    Neural fuzzy inference systems;    Novel applications;    Outlier samples;    Radial basis function neural networks;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/433/1/012079/pdf
DOI  :  10.1088/1757-899X/433/1/012079

来源: IOP

【 摘 要 】

This paper describes a novel application of the Adapted Neural Fuzzy Inference System (ANFIS) to function approximation. Several functions in one dimension are realised in this work, including a Gaussian function and a combination of sine waves with exponential functions, in order to confirm the efficiency of the ANFIS method; these results are then compared with those from a Radial Basis Function Neural Network (RBFNN) and Fuzzy Inference System (FIS), which have previously been successfully applied to function approximation problems. This paper introduces the ANFIS as a robust method that mitigates, or is insensitive to, outliers. The results show that the ANFIS method can solve the outlier samples problem, and that the performance of ANFIS proposed in this work is thus better than that of the NN and FIS methods; the function approximated outputs of the presented ANFIS are more faithful to the original test functions and RMSEs of the ANFIS are also lower, especially during the checking process.