Title :
Heterogeneous variable-length genotypes for evolutionary optimization
Author_Institution :
Inst. of Intelligent Syst., National Inst. of Adv. Industrial Sci. & Technol., Tsukuba, Japan
Abstract :
This paper deals with evolutionary programming for optimization problems. The algorithm manipulates chromosomes of which genotypes contains heterogeneous data (integer and float numbers), depending on each other. Moreover, length of the chromosomes is different within a common evolution. The evolutionary algorithm is described and optimization results are compared to the previously implemented methodology. Stability of the algorithm facing a change of problem dimensions is also tested and discussed.
Keywords :
evolutionary computation; chromosomes; evolutionary optimization; heterogeneous data; heterogeneous genotypes; Automatic generation control; Biological cells; Intelligent robots; Intelligent systems; Optimization methods; Paper technology; Robot kinematics; Robotics and automation; Stability; Testing;
Conference_Titel :
Robot Motion and Control, 2004. RoMoCo'04. Proceedings of the Fourth International Workshop on
Print_ISBN :
83-7143-272-0
DOI :
10.1109/ROMOCO.2004.240570
