Effects of Diversity on Optimality in GA

Authors:
Glen Macdonald;Gu Fang
Affiliations:
School of Engineering, University of Western Sydney, Penrith South DC, Australia 1797;School of Engineering, University of Western Sydney, Penrith South DC, Australia 1797
Venue:
AICI '09 Proceedings of the International Conference on Artificial Intelligence and Computational Intelligence
Year:
2009

Citing 9
Cited 0

Evolutionary computation

Evolutionary computation
Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control and Artificial Intelligence

Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control and Artificial Intelligence
Genetic Algorithms in Search, Optimization and Machine Learning

Genetic Algorithms in Search, Optimization and Machine Learning
Adapting Operator Probabilities in Genetic Algorithms

Proceedings of the 3rd International Conference on Genetic Algorithms
Varying the Probability of Mutation in the Genetic Algorithm

Proceedings of the 3rd International Conference on Genetic Algorithms
Optimal Mutation Rates in Genetic Search

Proceedings of the 5th International Conference on Genetic Algorithms
Diversity-Guided Evolutionary Algorithms

PPSN VII Proceedings of the 7th International Conference on Parallel Problem Solving from Nature
Towards an Optimal Mutation Probability for Genetic Algorithms

PPSN I Proceedings of the 1st Workshop on Parallel Problem Solving from Nature
Simultaneous Inductive and Deductive Modeling of Ecological Systems via Evolutionary Computation and Information Theory

Simulation

Quantified Score

Hi-index	0.00

Visualization

Abstract

Genetic Algorithms (GA) is an evolutionary inspired heuristic search algorithm. Like all heuristic search methods, the probability of locating the optimal solution is not unity. Therefore, this reduces GA's usefulness in areas that require reliable and accurate optimal solutions, such as in system modeling and control gain setting. In this paper an alteration to Genetic Algorithms (GA) is presented. This method is designed to create a specific type of diversity in order to obtain more optimal results. In particular, it is done by mutating bits that are not constant within the population. The resultant diversity and final optimality for this method is compared with standard Mutation at various probabilities. Simulation results show that this method improves search optimality for certain types of problems.