S.-T. Hsieh, T.-Y. Sun, J.-M. Chen, C.-C. Liu, and S.-J. Tsai (Taiwan)
Genetic algorithm, offspring, seesaw method, optimization
The genetic algorithm (GA) is a population-based optimization technique that can be applied to wide range of problems. It has ability for widely search solutions by mutation operator and nearly searches by cross-over operator. This paper proposes a seesaw method to decide suitable cross-over and mutation rate according to solution searching status. The seesaw method can significantly improve efficiency of offspring generation of the original genetic algorithm. In another word, it can enhance population’s searching ability and can avoid populations to fall into local minimal. Experiments were conducted on unimodal and multimodal test functions such as Sphere, Rastrigin, Ackley, Griewanks and Generalized Penalized Function. Our approach performs better performance on solution search ability than other GA approaches.
Important Links:
Go Back
