Pair Bonds In Genetic Algorithm
Loading...
Date
2015-07
Authors
Lim, Ting Yee
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
This work presents a comprehensive investigation on the concept of pair bonds (monogamous
pairs) for the mating phase of genetic algorithms (GAs). GA is a heuristic search technique
based on the principles and mechanisms of natural selection. Traditionally, parents are
selected at every generation to reproduce offspring through crossover and mutation operations.
The process reiterates until some termination conditions are met. However, nature sometimes
exhibits the formation of enduring relationships between mating partners. In modern human
society, some avian models, fish, rodents, and even lizards, pair bonds are integral aspects
of their social behaviour. These species usually share the same mating partners throughout
their lifetime - socially monogamous. Taking the cue from nature, this thesis studies the feasibilities
of pair bonds in GA. Consequently, two methodologies are proposed: Firstly, in the
Monogamous Pairs Genetic Algorithm (MopGA), parents are bonded and mated consistently
over several predefined generations. Selection of new parents pairs will only take place at the
end of pair bond tenure. Meanwhile, competition occurs between siblings to ensure only the
best offspring are retained. Occasional infidelity generates variety, spreads genetic information
across the population and speeds up convergence. Secondly, to improve the ease-of-use
of MopGA, an adaptive MopGA (AMopGA) is introduced. Algorithm sensitive-parameters
are tuned adaptively throughout the evolutionary process - further improving the performance.
Rigorous performance investigation of both methodologies are carried out on different notable
benchmark problems. The results reveal that the algorithms are very competitive to existing
approaches in terms of solution quality as well as computational effort.
Description
Keywords
Electronic Computer