Moez Soltani

A novel fuzzy c-regression model algorithm using a new error measure and particle swarm optimization

Abstract This paper presents a new algorithm for fuzzy c-regression model clustering. The proposed methodology is based on adding a second regularization term in the objective function of a Fuzzy C-Regression Model (FCRM) clustering algorithm in order to take into account noisy data. In addition, a new error measure is used in the objective function of the FCRM algorithm, replacing the one used in this type of algorithm. Then, particle swarm optimization is employed to finally tune parameters of the obtained fuzzy model. The orthogonal least squares method is used to identify the unknown parameters of the local linear model. Finally, validation results of two examples are given to demonstrate the effectiveness and practicality of the proposed algorithm.

A novel weighted recursive least squares based on Euclidean particle swarm optimization

Purpose – The purpose of this paper is to present a new methodology for identification of the parameters of the local linear Takagi‐Sugeno fuzzy models using weighted recursive least squares. The weighted recursive least squares (WRLS) is sensitive to initialization which leads to no converge. In order to overcome this problem, Euclidean particle swarm optimization (EPSO) is employed to optimize the initial states of WRLS. Finally, validation results are given to demonstrate the effectiveness and accuracy of the proposed algorithm. A comparative study is presented. Validation results involving simulations of numerical examples and the liquid level process have demonstrated the practicality of the algorithm.Design/methodology/approach – A new method for nonlinear system modelling. The proposed algorithm is employed to optimize the initial states of WRLS algorithm in two phases of learning algorithm.Findings – The results obtained using this novel approach were comparable with other modeling approaches repo...

A PSO-Based Fuzzy c-Regression Model Applied to Nonlinear Data Modeling

This paper presents a new method for fuzzy c-regression models clustering algorithm. The main motivation for this work is to develop an identification procedure for nonlinear systems using weighted recursive least squares and particle swarm optimization. The fuzzy c-regression models algorithm is sensitive to initialization which leads to the convergence to a local minimum of the objective function. In order to overcome this problem, particle swarm optimization is employed to achieve global optimization of FCRM and to finally tune parameters of obtained fuzzy model. The weighted recursive least squares is used to identify the unknown parameters of the local linear model. Finally, validation results involving simulation of two examples have demonstrated the effectiveness and practicality of the proposed algorithm.

A modified fuzzy c-regression model clustering algorithm for T-S fuzzy model identification

In this paper, a modified fuzzy c-regression model (FCRM) clustering algorithm for identification of Takagi-Sugeno (T-S) fuzzy model is proposed. The FCRM clustering algorithm has considerable sensitive to noise. To overcome this problem, a modified FCRM clustering algorithm is presented. This latter is based to adding a second regu-larization term in the alternative optimization process of FCRM. This regularization term is introduce in objective function in order to take in account the data are noisy. The parameters of the local linear models are identified based on orthogonal least squares (OLS). The proposed approach is demonstrated by means of the identification of nonlinear numerical examples.

Modified fuzzy model identification clustering algorithm for liquid level process

In this paper the problem of nonlinear system identification is investigated from a new point of view. If the nonlinear system is affected by measurement noise and if the noise cluster is arbitrarily far away, then there is no way to guarantee that any clustering algorithm will select the best cluster instead of the bad one. The proposed methodology is based to adding a noise cluster to clustering algorithm. The proposed approach allows the identification of the premise parameters and the consequence parameters together via iterative minimization using four criteria. This new technique is demonstrated by means of the identification of liquid level process.

Takagi-Sugeno fuzzy model parameters identification based on fuzzy c-regression model clustering algorithm and particle swarm optimization

A methodology for identification of the parameters of the local linear Takagi-Sugeno fuzzy models using weighted recursive least square is presented in this paper. The weighted recursive least square (WRLS) is sensitive to initialization which leads to no converge. In order to overcome this problem, particle swarm optimization is employed to optimize the initial states of WRLS. This new approach combines the advantages of fuzzy c-regression model clustering algorithm and particle swarm optimization. Validation results involving simulation of the identification of nonlinear systems have demonstrated the effectiveness of the proposed algorithm.

A new objective function for fuzzy c-regression model and its application to T-S fuzzy model identification

This paper proposes a new objective function for fuzzy c-regression model (FCRM) clustering algorithm. The main motivation for this work is to develop an identification procedure for nonlinear systems affected by measurement noise. The proposed methodology is based to adding a second regularization term in the objective function of FCRM clustering algorithm in order to take in account the data are noisy. the orthogonal least square is used to identify the consequent parameters. A comparative study is presented. Validation results involving simulation of the identification of nonlinear benchmark problems have demonstrated the effectiveness and practicality of the proposed algorithm.

Design of new fuzzy sliding mode controller based on parallel distributed compensation controller and using the scalar sign function

This paper presents a new design of fuzzy sliding mode controller based on parallel distributed compensation and using a scalar sign function. The proposed fuzzy sliding mode controller (FSMC) uses the parallel distributed compensation (PDC) scheme to design the state feedback control law. The controller gains are determined in offline mode via linear quadratic regulator technique. Moreover, the fuzzy sliding surface of the system is designed using stable eigenvectors and the scalar sign function in order to overcome the discontinuous switching. This later is obtained by a sign function of the standard FSMC. The advantages of the proposed design are a minimum energy control effort, faster response and zero steady-state error. Finally, the validity of the proposed design strategy is demonstrated through the simulation of a flexible joint robot.

Comparative study on textual data set using fuzzy clustering algorithms

Purpose The purpose of this paper is to apply the Takagi-Sugeno (T-S) fuzzy model techniques in order to treat and classify textual data sets with and without noise. A comparative study is done in order to select the most accurate T-S algorithm in the textual data sets. Design/methodology/approach From a survey about what has been termed the “Tunisian Revolution,” the authors collect a textual data set from a questionnaire targeted at students. Five clustering algorithms are mainly applied: the Gath-Geva (G-G) algorithm, the modified G-G algorithm, the fuzzy c-means algorithm and the kernel fuzzy c-means algorithm. The authors examine the performances of the four clustering algorithms and select the most reliable one to cluster textual data. Findings The proposed methodology was to cluster textual data based on the T-S fuzzy model. On one hand, the results obtained using the T-S models are in the form of numerical relationships between selected keywords and the rest of words constituting a text. Consequently, it allows the authors to interpret these results not only qualitatively but also quantitatively. On the other hand, the proposed method is applied for clustering text taking into account the noise. Originality/value The originality comes from the fact that the authors validate some economical results based on textual data, even if they have not been written by experts in the linguistic fields. In addition, the results obtained in this study are easy and simple to interpret by the analysts.

Affine Takagi-Sugeno fuzzy model identification based on a novel fuzzy c-regression model clustering and particle swarm optimization

In this paper, a novel Takagi-Sugeno fuzzy model identification based on a new fuzzy c-regression model clustering algorithm and particle swarm optimization is presented. The main motivation for this work is to develop an identification procedure for nonlinear systems taking into account the noise. In addition, a new distance is used in the objective function of the FCRM algorithm, replacing the one used in this type of algorithm. Thereafter, particle swarm optimization is employed to fine tune parameters of the obtained fuzzy model. The performance of the proposed approach is validated by studying the nonlinear plant modeling problem.