By Topic

A linear map-based mutation scheme for real coded genetic algorithms

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

5 Author(s)
Yue-jiao Gong ; Department of Computer Science, Sun Yat-sen University, Guangzhou, China ; Xiao-min Hu ; Jun Zhang ; Ou Liu
more authors

Real coded genetic algorithms (RCGAs) have been widely studied and applied to deal with continuous optimization problems for years. However, how to improve the degree of accuracy so as to produce high quality solutions is still one of the main difficulties that RCGAs face with. This paper proposes a novel mutation scheme for RCGAs. The mutation operator is defined as a linear map in the space of chromosomes (in RCGAs each chromosome is a floating point vector). It operates on a whole chromosome instead of several single genes to produce the new chromosome. The linear map is represented by a randomly generated mapping matrix which satisfies some predefined constraints. By this way, the constraints restrict the mutations of genes on a same chromosome as a whole. RCGA with the proposed mutation scheme is tested on 16 benchmark functions. Results demonstrate that the proposed scheme not only improves the solution accuracy that RCGA can obtain, but also presents a very fast convergence speed. The linear map-based mutation scheme has a bright future to improve RCGAs.

Published in:

IEEE Congress on Evolutionary Computation

Date of Conference:

18-23 July 2010