Effect of Polygamy with Selection in Genetic Algorithms
Rakesh Kumar1, Jyotishree2
1Rakesh Kumar, DCSA. Kurukshetra University, Kurukshetra, Haryana, India.
2Jyotishree, DCSA, Guru Nanak Girls College, Santpura, Yamunanagar, Haryana, India.
Manuscript received on February 15, 2012. | Revised Manuscript received on February 20, 2012. | Manuscript published on March 05, 2012. | PP: 162-170 | Volume-2 Issue-1, March 2012. | Retrieval Number: A0413022112/2012©BEIESP
Open Access | Ethics and Policies | Cite
© The Authors. Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Genetic algorithms are based on evolutionary ideas of natural selection and genetics. Important operators used in GA are selection, crossover and mutation, where selection operator is used to select the individuals from a population to create a mating pool which will participate in reproduction process. A number of selection operators have been used in the past like roulette wheel selection, ranked selection, elitism etc. where elitism is used to enforce the preservation of best solution found so far unless a new best individual is discovered. Elitism is implemented by copying the best individual of a generation into the next generation without any change. In this paper a particular form of elitism, polygamy, is proposed and implemented in which in each generation the best individual is selected and that participates in crossover with all other individuals in the mating pool created by any other selection mechanism. Polygamy has also been observed in a number of animals like lion, elk, baboons etc. Results obtained show the improvement over traditional selection operators available in literature.
Keywords: Genetic algorithm, polygamy, rank selection, roulette wheel, selection.