Comparing simulated annealing and genetic algorithm in learning FCM

Ghazanfari, Mehdi; Alizadeh, Somayeh; Fathian, Mohammad; Koulouriotis, Dimitrios E.

doi:10.1016/j.amc.2007.02.144

Cited by 68 publications

(33 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…De modo resumido, mapas cognitivos Fuzzy é uma técnica baseada no conhecimento que funciona como uma rede cognitiva artificial e herda características de mapas cognitivos e redes neurais artificiais (GLYKAS, 2010). O FCM pode ser considerado um modelo híbrido (fusão de duas áreas de conhecimento de sistemas inteligentes) com um forte grau de iteração, no qual não se pode identificar e separar as estruturas das áreas de origens, somente a semântica de construção (GHAZANFARI et al, 2007).…”

Section: Introductionunclassified

Redes Cognitivas Dinâmicas, Fundamentos e Aplicações

et al. 2013

View full text Add to dashboard Cite

ResumoEste trabalho apresenta uma proposta de redes cognitivas dinâmicas, do inglês Dynamic Cognitive Networks (DCN), evolução dos Mapas Cognitivos e dos Mapas Cognitivos Fuzzy. Os Mapas Cognitivos Fuzzy ou Fuzzy Cognitive Maps (FCM) têm aplicações em diversas áreas de conhecimento, entretanto apresentam algumas restrições para sistemas dinâmicos. Devido a essas restrições existem na literatura algumas propostas de arquiteturas baseadas nos FCM clássicos e propostas de modelos cognitivos baseados nessa ferramenta, Redes Cognitivas Dinâmicas é uma dessas abordagens. Este trabalho apresenta uma proposta original com fundamentos para a construção de uma DCN e aplicações em controle de processos e navegação autônoma. Palavras-chave: Redes cognitivas dinâmicas. Mapas cognitivos Fuzzy. Navegação autônoma. AbstractThis study presents the proposal of dynamic cognitive networks (DCN), and also the evolution of Cognitive Maps and Fuzzy Cognitive Maps. Fuzzy Cognitive Maps (FCM) can be applied in several areas of knowledge; however, it presents some restrictions in dynamic systems. Due to these restrictions, some architectures proposals are based on FCM and also classical proposals for cognitive models based on these concepts are available in the literature. Dynamic Cognitive Networks is one of these approaches. Hence, this study presents an original proposal with background for the construction of DCN and applications in process control and autonomous navigation.

show abstract

Section: Introductionunclassified

Redes Cognitivas Dinâmicas, Fundamentos e Aplicações

et al. 2013

View full text Add to dashboard Cite

show abstract

“…In general, there are two stopping rules; The first one works when the number of temperature transitions satisfies the temperature termination rules, while the second rule takes effects when the neighbor solution is not improved after a certain period [27]. In our strategy, the algorithm stopped when the average change on the value of the fitness function at the current point was less than 10 -6 after 300 iterations.…”

Section: Determination Of Sa Algorithm Parametersmentioning

confidence: 99%

“…The random disturbance can be regarded as the jumping of the optimal model. The metropolis criterion was used to determine whether a new point was acceptable or not by calculating the difference of function values at the current point and the new point [27]. The annealing schedule behaves exponentially, which updates the current temperature based on the following formula:…”

Section: Determination Of Sa Algorithm Parametersmentioning

confidence: 99%

Application of a hybrid variable selection method for the classification of rapeseed oils based on 1H NMR spectral analysis

Chen

Han

et al. 2010

Eur Food Res Technol

View full text Add to dashboard Cite

1 H nuclear magnetic resonance (NMR) spectroscopy was utilized to distinguish the brands of rapeseed oils. As there are more than four hundreds of NMR variables which can cause the discrimination model redundancy, it is necessary to do effective variable selection. Successive projections algorithm (SPA) executed on the full spectrum only improved a few correct answer rate (CAR) and Cohen's kappa coefficient (K) compared to full spectrum-least-square support vector machine (LS-SVM) model. The better results of uninformative variable elimination (UVE)-based SPA calculation show that it is necessary to do UVE before SPA. Because the cutoff threshold selection in UVE algorithm using an artificial random noise cannot obtain the optimal results, we applied simulated annealing (SA) algorithm to estimate the optimal cutoff threshold. The discrimination results show that UVE-SA did better works than conventional UVE. Only 13 variables were obtained by UVE-SA-SPA while the conventional UVE-based SPA selected 77 variables. The best 97.5% CAR and K of 0.967 result of UVE-SPA-LS-SVM model show that it is feasible to distinguish different brands of rapeseed oils using 1 H NMR spectra. It shows that a combination of SA, UVE, and SPA is effective method for the classification of rapeseed oils. Final result shows that all acyl chains, linolenyl and linoleyl chains, and triglycerides were most important for the classification.

show abstract

“…For instance, in [9] the PSO algorithm with constriction factor is adopted; in [23] it is presented a FCM learning based on a Tabu Search (TS) and GA combination; in [24] a variation of GA named RCGA (real codec-G.A.) is proposed; in [25] a comparison between GA and Simulated Annealing (SA) is done; in [16] the authors presented a GA based algorithm named Extended Great Deluge Algorithm.…”

Section: Hebbian Learning Based Algorithm;mentioning

confidence: 99%

A comparative analysis of three metaheuristic methods applied to fuzzy cognitive maps learning

et al. 2013

View full text Add to dashboard Cite

ABSTRACT. This work analyses the performance of three different population-based metaheuristic approaches applied to Fuzzy cognitive maps (FCM) learning in qualitative control of processes. Fuzzy cognitive maps permit to include the previous specialist knowledge in the control rule. Particularly, Particle Swarm Optimization (PSO), Genetic Algorithm (GA) and an Ant Colony Optimization (ACO) are considered for obtaining appropriate weight matrices for learning the FCM. A statistical convergence analysis within 10000 simulations of each algorithm is presented. In order to validate the proposed approach, two industrial control process problems previously described in the literature are considered in this work.

show abstract

Comparing simulated annealing and genetic algorithm in learning FCM

Cited by 68 publications

References 22 publications

Redes Cognitivas Dinâmicas, Fundamentos e Aplicações

Redes Cognitivas Dinâmicas, Fundamentos e Aplicações

Application of a hybrid variable selection method for the classification of rapeseed oils based on 1H NMR spectral analysis

A comparative analysis of three metaheuristic methods applied to fuzzy cognitive maps learning

Contact Info

Product

Resources

About