Previously, we have shared the implementation of ANFIS for nonlinear regression, in this link. Using the same implementation and converting the time-series modeling, to a function approximation problem, ANFIS is applied to the Time-Series Forecasting problem. The implemented approach, is used to build a model of and predict the global ice volume, based on the observed data in last 440,000 ...

Training of an ANFIS structure is a special kind of optimization problem. So metaheuristics and evolutionary algorithms can be used to train (tune the parameters of) an ANFIS structure. In this post, we are going to share with you, the MATLAB implementation of the evolutionary ANFIS training. The code, firstly creates an initial raw ANFIS structure and then uses Genetic ...

An approach to tune the PID controller using Fuzzy Logic, is to use fuzzy gain scheduling, which is proposed by Zhao, in 1993, in this paper. In this post, we are going to share with you, a MATLAB/Simulink implementation of Fuzzy PID Controller, which uses the blocksets of Fuzzy Logic Toolbox in Simulink. Three examples of the reference paper, are ...

Adaptive Neuro-Fuzzy Inference System (ANFIS) is a combination of artificial neural network (ANN) and Takagi-Sugeno-type fuzzy system, and it is proposed by Jang, in 1993, in this paper. ANFIS inherits the benefits of both neural networks and fuzzy systems; so it is a powerful tool, for doing various supervised learning tasks, such as regression and classification. Fuzzy Logic Toolbox provides ...