Evolutionary learning of fuzzy models

Pham, Duc Truong; Castellani, Marco

doi:10.1016/j.engappai.2006.01.007

Cited by 14 publications

(6 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The concept of evolvability is perceived in different ways and in some cases it looks at the underlying optimization processes (which exhibit a great deal of adaptive mechanisms). The category of genetic-based optimization of fuzzy models has assumed here a visible position [the reader may refer here to (Akbarzadeh-T et al 2008); (Al-Razgan and Domeniconi 2006); (Aliev et al 2009); (Antonelli et al 2009); (Molina et al 2006(Molina et al , 2007; ; (Pham and Castellani 2006)]. …”

Section: Introductionmentioning

confidence: 99%

Evolvable fuzzy systems: some insights and challenges

Pedrycz

2010

Evolving Systems

View full text Add to dashboard Cite

The emerging category of evolvable fuzzy systems has opened a new uncharted territory of system modeling by enhancing the capabilities of existing fuzzy models and formulating new methodological and algorithmic challenges and opportunities. In this study, we revisit the underlying concept and identify a number of essential optimization problems arising therein. It is shown that the behavior and characteristics of evolvable systems can be classified under the rubric of perception-based evolvability (being inherently associated with the humancentric systems and the development of efficient mechanisms of relevance feedback) and a distribution of knowledge representation resources of evolvable systems. We elaborate on the essence of these problems and define the corresponding optimization criteria. A selected detailed design scenario is presented as well in which the dynamics of information granules is exploited as a vehicle to cope with the evolving modeling environment.

show abstract

Section: Introductionmentioning

confidence: 99%

Evolvable fuzzy systems: some insights and challenges

Pedrycz

2010

Evolving Systems

View full text Add to dashboard Cite

show abstract

“…Along with the associated tangible benefits and better rapport with reality (distributed systems, various modeling perspectives), this shift brings a number of new challenges irrespectively from the development technologies one has started with. There is no surprise that in fuzzy modeling and computing with words [21] with its plethora of design techniques, see [1][2][3]6,[10][11][12]18] involving criteria of accuracy and interpretability [4,9] and invoking promising methods of global optimization [17], this concept has to translate into sound concepts, methodology, design strategies, and finally detailed algorithms.…”

Section: Introductionmentioning

confidence: 99%

Granular fuzzy models: a study in knowledge management in fuzzy modeling

Pedrycz

Song

2012

International Journal of Approximate Reasoning

View full text Add to dashboard Cite

a b s t r a c tIn system modeling, knowledge management comes vividly into the picture when dealing with a collection of individual models. These models being considered as sources of knowledge, are engaged in some collective pursuits of a collaborative development to establish modeling outcomes of global character. The result comes in the form of a so-called granular fuzzy model, which directly reflects upon and quantifies the diversity of the available sources of knowledge (local models) involved in knowledge management. In this study, several detailed algorithmic schemes are presented along with related computational aspects associated with Granular Computing. It is also shown how the construction of information granules completed through the use of the principle of justifiable granularity becomes advantageous in the realization of granular fuzzy models and a quantification of the quality (specificity) of the results of modeling. We focus on the design of granular fuzzy models considering that the locally available models are those fuzzy rule-based. It is shown that the model quantified in terms of two conflicting criteria, that is (a) a coverage criterion expressing to which extent the resulting information granules ''cover'' include data and (b) specificity criterion articulating how detailed (specific) the obtained information granules are. The overall quality of the granular model is also assessed by determining an area under curve (AUC) where the curve is formed in the coverage-specificity coordinates. Numeric results are discussed with intent of displaying the most essential features of the proposed methodology and algorithmic developments.

show abstract

“…To achieve a good model performance, one of the most important stages is to obtain the model's parameters quickly and accurately. For this purpose, artificial intelligence (AI)-based algorithms such as genetic algorithms (GAs), evolutionary design, tabu search, differential evolution algorithm (DEA), particle swarm optimization (PSO) and the artificial bee colony (ABC) algorithm can produce fast and efficient solutions (Bagis, 2003(Bagis, , 2008Bagis and Konar, 2014;Belarbi et al, 2005;Farag et al, 1998;Guely et al, 1999;Guney and Sarikaya, 2009a;Habbi et al, 2015;Juang and Wang, 2009;Kang et al, 2000;Pham and Castellani, 2006;Precup et al, 2012;Su and Yang, 2011;Su et al, 2012;Wu and Yu, 2000;Zade et al, 2012;Zhao et al, 2010). From the literature review, it is clearly shown that selection of the optimization algorithm plays a major role in the determination of the fuzzy model parameters for a good model performance.…”

Section: Introductionmentioning

confidence: 99%

“…As shown in the literature, many different AI-based optimization algorithms have been tested for fuzzy system modelling (Bagis, 2003(Bagis, , 2008Bagis and Konar, 2014;Bagis and Saracoglu, 2001;Banakar and Azeem, 2011;Belarbi, et al 2005;Cordon et al, 2001;Du and Zhang, 2008;Farag et al, 1998;Guely et al, 1999;Guney and Sarikaya, 2009a;Habbi et al, 2015;Juang and Lo, 2008;Juang and Wang, 2009;Juang et al, 2010;Kang et al, 2000;Karaboga et al, 2008;Papadakis and Theocharis, 2002;Pham and Castellani, 2006;Precup et al, 2012;Siarry and Guely, 1998;Su and Yang, 2011;Su et al, 2012;Wu and Yu, 2000;Zade et al, 2012;Zhao et al, 2010). A study about fuzzy rule base design using the tabu search algorithm (TSA) for nonlinear system modelling was presented by Bagis (2008).…”

Section: Introductionmentioning

confidence: 99%

Comparison of Sugeno and Mamdani fuzzy models optimized by artificial bee colony algorithm for nonlinear system modelling

Bağış

Konar

2015

Transactions of the Institute of Measurement and Control

View full text Add to dashboard Cite

This paper is an extended version of the paper presented at TOK 2014 (Turkish Automatic Control National Meeting) which examined the determination of Sugeno type fuzzy model parameters optimized by the artificial bee colony (ABC) algorithm for a microstrip antenna. This paper presents a performance comparison of the Sugeno and Mamdani type fuzzy models proposed for nonlinear system modelling. To determine the parameters of the fuzzy models, the ABC algorithm is used. For this purpose, several nonlinear system examples which given in the literature were considered, and the results obtained by the optimized fuzzy models were compared with the other modelling approaches in the literature. Simulation results demonstrate that the use of the ABC algorithm provides a remarkable contribution to the model's performance.

show abstract

Evolutionary learning of fuzzy models

Cited by 14 publications

References 21 publications

Evolvable fuzzy systems: some insights and challenges

Evolvable fuzzy systems: some insights and challenges

Granular fuzzy models: a study in knowledge management in fuzzy modeling

Comparison of Sugeno and Mamdani fuzzy models optimized by artificial bee colony algorithm for nonlinear system modelling

Contact Info

Product

Resources

About