International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
|
Volume 65 - Issue 18 |
Published: March 2013 |
Authors: Amouda Nizam, Buvaneswari Shanmugham |
![]() |
Amouda Nizam, Buvaneswari Shanmugham . Self-Organizing Genetic Algorithm: A Survey. International Journal of Computer Applications. 65, 18 (March 2013), 25-32. DOI=10.5120/11025-5659
@article{ 10.5120/11025-5659, author = { Amouda Nizam,Buvaneswari Shanmugham }, title = { Self-Organizing Genetic Algorithm: A Survey }, journal = { International Journal of Computer Applications }, year = { 2013 }, volume = { 65 }, number = { 18 }, pages = { 25-32 }, doi = { 10.5120/11025-5659 }, publisher = { Foundation of Computer Science (FCS), NY, USA } }
%0 Journal Article %D 2013 %A Amouda Nizam %A Buvaneswari Shanmugham %T Self-Organizing Genetic Algorithm: A Survey%T %J International Journal of Computer Applications %V 65 %N 18 %P 25-32 %R 10.5120/11025-5659 %I Foundation of Computer Science (FCS), NY, USA
Self-organization systems are an increasingly attractive dynamic processes without a central control, emerge global order from local interactions in a bottom up approach. The advantage of blending the concept of self-organization enhances the working efficiency of other techniques to find a solution of huge search problem. Genetic Algorithms (GA) is such a technique, inspired by the natural evolution process, used to solve difficult optimization problem of large space solution, for an example, multiple sequence alignment (MSA) problem in a bioinformatics research. Self-organization technique automates the selection of appropriate parameter values of GA during execution without the user's intervention. An attempt towards applying Self-organizing Genetic Algorithm (SOGA) on MSA requires a complete knowledge of the various parameters of SO and its relationships. This lead us to make a complete survey on inherent properties of SO and the method of blending GA in order to develop a self-organizing genetic algorithm (SOGA) for MSA. The aim of the research is to make use of the efficiency of GA without getting any input from the non-trained users to tune the parameters in order to achieve the expected result.