A genetic algorithm that simulates social behaviour
by Nagham Azmi AL-Madi, Ahamad Tajudin Khader
International Journal of Internet Technology and Secured Transactions (IJITST), Vol. 1, No. 3/4, 2009

Abstract: Genetic algorithms (GAs), as general search models, have proved its success in several applications, however recently, several researchers have argued that they have slow convergence; this slowness is due to the randomness in all their operations. Therefore, recent researches have employed structured populations, in order to eliminate randomness, such as island models, cellular model, multinational evolutionary algorithms, etc. In this paper, a social based GA is introduced; this model is trying to mimic the actual social behaviour and the actual death and birth process. The authors will restrict the recombination for males to the only permitted females. The authors' motivation to such an approach is that they expect the nature to be more robust and optimal; hence, the objectives of this work are to study the effects of these social rules and customs on the standard GA and to investigate its effects on the speed of convergence of GA. The primary results show a faster convergence than a standard GA and a controlled diffusion of individuals and hence better spanning of the search space.

Online publication date: Wed, 18-Mar-2009

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Internet Technology and Secured Transactions (IJITST):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com