Title :
Bee System: finding solution by a concentrated search
Author :
Sato, Takao ; Hagiwara, Masafumih
Author_Institution :
Dept. of Electr. Eng., Keio Univ., Yokohama, Japan
Abstract :
We propose an improved genetic algorithm named Bee System. The concept of the Bee System comes from the behavior of bees: first, a bee finds feed and then it notifies this information to the other bees by a dance to work together. In the proposed Bee System, each chromosome tries to find a good solution individually. When some chromosome is regarded as superior one, other chromosomes try to find a solution around there using multiple populations. Such a procedure is then repeated. The Bee System employs some new operations such as concentrated crossover, and Pseudo-Simplex Method. By computer simulations it is confirmed that the Bee System has better performance than the conventional genetic algorithm
Keywords :
genetic algorithms; genetics; search problems; Bee System; Pseudo-Simplex Method; chromosome; computer simulations; concentrated crossover; concentrated search; improved genetic algorithm; multiple populations; Airplanes; Biological cells; Computer simulation; Electronic mail; Feeds; Genetic algorithms; Neural networks; Optimization methods; Pattern matching; Pipelines;
Conference_Titel :
Systems, Man, and Cybernetics, 1997. Computational Cybernetics and Simulation., 1997 IEEE International Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-4053-1
DOI :
10.1109/ICSMC.1997.633289
