InterCriteria Analysis of Genetic Algorithms Performance
In this paper we apply InterCriteria Analysis (ICrA) approach based on the apparatus of Index Matrices and Intuitionistic Fuzzy Sets. The main idea is to use ICrA to establish the existing relations and dependencies of defined parameters in a non-linear model of an E. coli fed-batch cultivation process. We perform a series of model identification procedures applying Genetic Algorithms (GAs). We proposed a schema of ICrA of ICrA results to examine the obtained model identification results. The discussion about existing relations and dependencies is performed according to criteria defined in terms of ICrA. We consider as ICrA criteria model parameters and GAs outcomes on the one hand, and 14 differently tuned GAs on the other. Based on the results, we observe the mutual relations between model parameters and GAs outcomes, such as computation time and objective function value. Moreover, some conclusions about the preferred tuned GAs for the considered model parameter identification in terms of achieved accuracy for given computation time are presented.
KeywordsInterCriteria analysis Index matrices Intuitionistic fuzzy sets Genetic algorithm Parameter identification E. coli Cultivation process
The work presented here is partially supported by the Bulgarian National Scientific Fund under Grant DFNI-I02/5 and by the Polish-Bulgarian collaborative Grant “Parallel and Distributed Computing Practices”.
- 1.Angelova, M., Roeva, O., Pencheva, T.: InterCriteria analysis of crossover and mutation rates relations in simple genetic algorithm. In: Proceedings of the 2015 Federated Conference on Computer Science and Information Systems, pp. 419–424 (2015)Google Scholar
- 6.Atanassov, K., Mavrov, D., Atanassova, V.: Intercriteria decision making: a new approach for multicriteria decision making, based on index matrices and intuitionistic fuzzy sets. Iss. Intuitionistic Fuzzy Sets Gen. Nets 11, 1–8 (2014)Google Scholar
- 7.Atanassov, K., Atanassova, V., Gluhchev, G.: InterCriteria analysis: ideas and problems. Not Intuitionistic Fuzzy Sets 21(1), 81–88 (2015)Google Scholar
- 8.Bastin, G., Dochain, D.: On-line Estimation and Adaptive Control of Bioreactors. Elsevier Scientific Publications, Amsterdam (1991)Google Scholar
- 10.Doughabadi, M.H., Bahrami, H., Kolahan, F.: Evaluating the effects of parameters setting on the performance of genetic algorithm using regression modeling and statistical analysis. J. Ind. Eng. Spec. Iss. 61–68 (2011)Google Scholar
- 11.Goldberg, D.E.: Genetic algorithms in search, optimization and machine learning. Addison Wesley Longman, London (2006)Google Scholar
- 12.Ilkova, T., Petrov, M.: Intercriteria analysis for identification of Escherichia coli fed-batch mathematical model. J. Int. Sci. Publ.: Mater., Meth. Technol 9, 598–608 (2015)Google Scholar
- 13.Pencheva, T., Angelova, M., Atanassova, V., Roeva, O.: InterCriteria analysis of genetic algorithm parameters in parameter identification. Notes Intuitionistic Fuzzy Sets 21(2), 99–110 (2015)Google Scholar
- 16.Razali, N.M., Geraghty, J.: Genetic algorithm performance with different selection strategies in solving TSP. In: Proceedings of the World Congress on Engineering 2011 – WCE 2011, vol. II (2011)Google Scholar
- 19.Roeva, O., Pencheva, T., Hitzmann, B., Tzonkov, St.: A genetic algorithms based approach for identification of Escherichia coli fed-batch fermentation. Int. J. Bioautom. 1, 30–41 (2004)Google Scholar
- 20.Roeva, O., Fidanova, S., Paprzycki, M.: Influence of the population size on the genetic algorithm performance in case of cultivation process modelling. In: Proceedings of the 2013 Federated Conference on Computer Science and Information Systems, pp. 371–376 (2013)Google Scholar
- 21.Roeva, O., Pencheva, T., Tzonkov, S., Hitzmann, B.: Functional state modelling of cultivation processes: dissolved oxygen limitation state. Int. J. Bioautom. 19(1 Suppl.1), S93–S112 (2015)Google Scholar