Parameterisation of mutation in evolutionary algorithms using the estimated main effect of genes

Chan K., AYDIN M. E., Fogarty T.

Proceedings of the 2004 Congress on Evolutionary Computation, CEC2004, Portland, OR, Amerika Birleşik Devletleri, 19 - 23 Haziran 2004, cilt.2, ss.1972-1979, (Tam Metin Bildiri) identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Cilt numarası: 2
  • Basıldığı Şehir: Portland, OR
  • Basıldığı Ülke: Amerika Birleşik Devletleri
  • Sayfa Sayıları: ss.1972-1979
  • İstanbul Ticaret Üniversitesi Adresli: Evet

Özet

This paper describes how to estimate the main effect of genes in genetic algorithms (GAs). The resulting estimates can not only be used to understand the domination of genes in a GA but also employed to tailor the mutation rate in the GA. A new approach to varying the mutation rate across the representation and over the run of the GA depending on estimates of the main effect of genes is proposed. We demonstrate the use of the proposed method for solving uncapacitatied facility location problems. For many well-known benchmark problems, the proposed method yields better results than the previously used method.