An Improved Fuzzy Adaptive Genetic Algorithm for Function Optimization

Abstract:

The critical operators for genetic algorithms to avoid premature and improve globe convergence is the adaptive selection of crossover probability and mutation probability. This paper proposed an improved fuzzy adaptive genetic algorithm in which the variance of population and individual fitness value are used to measure the overall population diversity and individual difference, meanwhile, both of them are applied to design fuzzy reference system for adaptively estimation of crossover probability and mutation probability. Simulation results of function optimization show that the new algorithm can converge faster and is more effective at avoiding premature convergence in comparison with standard genetic algorithm.

• Periodical: Advanced Materials Research (Volumes 403-408)
• Pages: 2598-2601
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.403-408.2598
• Online since: November 2011
• Authors: Lan Yao, Yu Lian Jiang, Jian Xiao
• Keywords: Adaptive, Fuzzy Reference System, Genetic Algorithm (GA)

References

[1] Han Wan lin and Zhang You di," Improvement of Genetic Algorithm," Journal of china university of mining &technology, Vol.29 No.1, pp.103-105, Jan 2000.

[2] Wu H, Mendel J. Uncertainty bounds and their use in the design of interval type-2 fuzzy logic system[J]. IEEE Trans on Fuzzy Systems,2002,15(1):622-639.

DOI: 10.1109/tfuzz.2002.803496

[3] LI-MIN LIU, NIAN-PENG WANG, FA-CHAO LI." STUDY ON CONVERGENCE OF SELF-ADAPTIVE AND MULTI-POPULATION COMPOSITE GENETIC ALGORITHM", Proceedings of the Eighth International Conference on Machine Learning and Cybernetic, 2009.7

DOI: 10.1109/icmlc.2009.5212122

[4] Zhang Qi-yi, Chang Shu-chun."An Improved Crossover Operator of Genetic Algorithm", 2009 Second International Symposium on Computational Intelligence and Design2009 Second International Symposium on Computational Intelligence and Design,82-86.

DOI: 10.1109/iscid.2009.169

[5] Goldberg.D..Genetic algorithms in search, optimization and machine learning [M].USA:Addison-Wesley Publishing Company.1988,pp.7-10,59-308.

[6] Fogel D B. Evolutionary computation: toward a new philosophy of machine intelligence [M].Institute of Electrical and Electronics Engineers, Inc, New York,1995,pp.155-17.