Author:
Ghodrat Moghadampour
Affiliation:
Vaasa University of Applied Sciences, Finland
Keyword(s):
Evolutionary algorithm, Genetic algorithm, Function optimization, Mutation operator, Self-adaptive mutation operators, Integer mutation operator, Decimal mutation operator, Fitness evaluation and analysis.
Related
Ontology
Subjects/Areas/Topics:
Artificial Intelligence and Decision Support Systems
;
Enterprise Information Systems
;
Evolutionary Programming
Abstract:
Evolutionary algorithms are affected by more parameters than optimization methods typically. This is at the same time a source of their robustness as well as a source of frustration in designing them. Adaptation can be used not only for finding solutions to a given problem, but also for tuning genetic algorithms to the particular problem. Adaptation can be applied to problems as well as to evolutionary processes. In the first case adaptation modifies some components of genetic algorithms to provide an appropriate form of the algorithm, which meets the nature of the given problem. These components could be any of representation, crossover, mutation and selection. In the second case, adaptation suggests a way to tune the parameters of the changing configuration of genetic algorithms while solving the problem. In this paper two new self-adaptive mutation operators; integer and decimal mutation are proposed for implementing efficient mutation in the evolutionary process of genetic algori
thm for function optimization. Experimentation with 27 test cases and 1350 runs proved the efficiency of these operators in solving optimization problems.
(More)