An empirical study on the performance of factorial design based crossover on parametrical problems

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

Abstract

In the past, empirical studies have shown that factorial design based crossover can outperform standard crossover on parametrical problems. However, up to now, no conclusion has been reached as to what kind of landscape factorial design based crossover outperforms standard crossover on. In this paper we have tested the performance of a factorial design based crossover operator embedded in a classical genetic algorithm and investigated whether or not it outperforms the standard crossover operator on a set of benchmark problems. We found that the factorial design based crossover performed significantly better than the standard crossover operator on landscapes that have a single optimum.

• Presentation Conference Type: Conference Paper (published)
• Conference Name: Proceedings of the 2004 Congress on Evolutionary Computation, CEC2004
• Start Date: Jun 19, 2004
• End Date: Jun 23, 2004
• Publication Date: Sep 3, 2004
• Deposit Date: Apr 30, 2021
• Volume: 1
• Pages: 620-627
• ISBN: 0780385152
• DOI: https://doi.org/10.1109/CEC.2004.1330818
• Public URL: https://uwe-repository.worktribe.com/output/6545529