Showing papers by "Mojtaba Ahmadieh Khanesar published in 2010"

A novel type-2 fuzzy membership function: application to the prediction of noisy data

Abstract: A novel, diamond-shaped type-2 fuzzy member- ship function is introduced in this study. The proposed type-2 fuzzy membership function has certain values on 0 and 1, but it has some uncertainties for the other membership values. It has been shown that the type-2 fuzzy system using this type of membership function introduced in this study has some noise reduction property in the presence of noisy inputs. The appropriate parameter selection to be able to achieve noise reduction property is also considered. A hybrid method consisting of particle swarm optimization (PSO) and gradient descent (GD) algorithm is used to optimize the parameters of the proposed type-2 fuzzy system. PSO is a derivative-free optimizer, and the possibility of the entrapment of this optimizer in local minimums is less than the gradient descent method. The proposed type-2 fuzzy system and the hybrid parameter estimation method are then tested on the prediction of a noisy, chaotic dynamical system. The simulation results show that the type-2 fuzzy predictor with the proposed novel membership functions shows a superior performance when compared to the other existing type-2 fuzzy systems in the presence of noisy inputs.

Subspace identification of dynamical neurofuzzy system using LOLIMOT

Abstract: In this paper a novel method for identification of dynamical neurofuzzy system is proposed. The proposed method benefits from both LOLIMOT as the premise part optimizer of the system and the subspace identification method of N4SID to optimize the state space parameters of the conclusion part. The resulting neurofuzzy system is a nonlinear dynamical system which is modeled by some locally linear state space models. using this model it is then possible to use different parallel distributed control techniques such as linear matrix inequality to control the identified system. The proposed approach is tested on a flexible robot arm and satisfactory results are generated.

Identification of interval fuzzy models using recursive least square method

Abstract: In this paper, we present a new method of interval fuzzy model identification. Unlike the previously introduced methods, this method uses recursive least square methods to estimate the parameters. The idea behind interval fuzzy systems is to introduce optimal lower and upper bound fuzzy systems that define the band which contains all the measurement values. This results in lower and upper fuzzy models or a fuzzy model with a set of lower and upper parameters. The model is called the interval fuzzy model (INFUMO). This type of modeling has various applications such as nonlinear circuits modeling. There has been tremendous amount of activities to use linear matrix inequality based techniques to design a controller for this type of fuzzy systems. The fact that the actual desired data must lie between upper and lower fuzzy systems, introduces some constrains on the identification process of the lower and upper fuzzy systems. We would introduce a cost function which includes the violation of constrains and try to find an adaptation law which minimizes this cost function and at the same time tries to be less conservative.