On the efficiency of crossover operators in genetic algorithms with binary representation

Authors:
Stjepan Picek;Marin Golub
Affiliations:
Faculty of Electrical Engineering and Computing, Zagreb, Croatia;Faculty of Electrical Engineering and Computing, Zagreb, Croatia
Venue:
NN'10/EC'10/FS'10 Proceedings of the 11th WSEAS international conference on nural networks and 11th WSEAS international conference on evolutionary computing and 11th WSEAS international conference on Fuzzy systems
Year:
2010

Citing 7
Cited 1

Adaptation in natural and artificial systems

Adaptation in natural and artificial systems
Genetic algorithms + data structures = evolution programs (3rd ed.)

Genetic algorithms + data structures = evolution programs (3rd ed.)
Evolutionary computation

Evolutionary computation
Handbook of Evolutionary Computation

Handbook of Evolutionary Computation
Practical Genetic Algorithms with CD-ROM

Practical Genetic Algorithms with CD-ROM
CIXL2: a crossover operator for evolutionary algorithms based on population features

Journal of Artificial Intelligence Research
Representation and hidden bias II: eliminating defining length bias in genetic search via shuffle crossover

IJCAI'89 Proceedings of the 11th international joint conference on Artificial intelligence - Volume 1

Comparison of a crossover operator in binary-coded genetic algorithms

WSEAS Transactions on Computers

Quantified Score

Hi-index	0.00

Visualization

Abstract

Genetic Algorithm (GA) represents robust, adaptive method successfully applied to various optimization problems. To evaluate the performance of the genetic algorithm, it is common to use some kind of test functions. However, the "no free lunch" theorem states it is not possible to find the perfect, universal solver algorithm. To evaluate the algorithm, it is necessary to characterize the type of problems for which that algorithm is suitable. That would allow conclusions about the performance of the algorithm based on the class of a problem. In performance of a genetic algorithm, crossover operator has an invaluable role. To better understand performance of a genetic algorithm in a whole, it is necessary to understand the role of the crossover operator. The purpose of this paper is to compare larger set of crossover operators on the same test problems and evaluate their's efficiency. Results presented here confirm that uniform and two-point crossover operators give the best results but also show some interesting comparisons between less used crossover operators like segmented or half-uniform crossover.