A Taguchi method-based crossover operator for the parametrical problems

Chan, K. Y.; Aydin, M. E.; Fogarty, T. C.

Abstract

Based on our observation, some major steps in the genetic algorithm, such as the crossover operator, can be considered as experiments. The aim is to apply experimental design techniques to improve the crossover operator, so that the resulting operator can be more robust and statistically sound. Taguchi method is a systematic and time-efficient approach that can aid in experimental design. Here we apply Taguchi method to tailor a new crossover operator so that the operator can estimate the best point in the search space determined by the parents. Experimental result shows that the proposed operator outperforms the classical GA crossover strategy on some parametrical problems. © 2003 IEEE.

• Presentation Conference Type: Conference Paper (published)
• Conference Name: The 2003 Congress on Evolutionary Computation, 2003. CEC '03
• Start Date: Dec 8, 2004
• End Date: Dec 12, 2003
• Online Publication Date: May 24, 2004
• Publication Date: May 24, 2004
• Deposit Date: Jul 14, 2021
• Publisher: Institute of Electrical and Electronics Engineers (IEEE)
• Book Title: The 2003 Congress on Evolutionary Computation, 2003. CEC '03
• ISBN: 0780378040
• DOI: https://doi.org/10.1109/CEC.2003.1299772
• Public URL: https://uwe-repository.worktribe.com/output/6545533