An evolutionary algorithm based on Reed-Muller partition tree model
by Jixiang Zhu; Tiefei Zhang
International Journal of Wireless and Mobile Computing (IJWMC), Vol. 8, No. 3, 2015

Abstract: In order to reduce the evolution time in evolutionary design Boolean functions, we encode the Reed-Muller expression as the chromosome and devise a Reed-Muller Partition Tree Model (RMPT) for decomposition. Moreover, we introduce three operators, i.e. layer evaluation, merisis of partition tree and benign mutation, into the genetic algorithm and adopt bisection test to reduce the time overhead of single chromosome evaluation. Layer evaluation operator picks up the speciality individuals during evolution. Merisis of partition tree operator utilises the complementary of speciality individuals. The ultimate solution is catenated by the evolved slices from different chromosomes. These schemes improve the evolution efficiency. Benign mutation operator explores the search space from two directions simultaneously, which further promotes the performance of the proposed algorithm. The experiments are implemented to evolve functions in various dimensions. The experimental results illustrate that the proposed algorithm decreases the evolution time from exponential complexity to approximately linear complexity, which indicates that the proposed approaches have the capability to address the scalability problem of evolving Boolean functions.

Online publication date: Thu, 14-May-2015

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 Wireless and Mobile Computing (IJWMC):
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