[4L3-J-8] Soft computing

[4L3-J-8-03] Real-Coded GA Introducing Problem Decomposition and Cooperation

〇Takatoshi Niwa¹, Koya Ihara^1,2, Shohei Kato^1,2 (1. Dept. of Computer Science and Engineering Graduate School of Engineering, Nagoya Institute of Technology, 2. Frontier Research Institute for Information Science, Nagoya Institute of Technology)

Keywords:Genetic Algorithm, Co-evolution, Group Work

Genetic algorithms (GAs) are stochastic optimization methods that mimic the evolution of living organisms. Among them, Real-Coded GA (RCGA) is effective in continuous function optimization problems and is applied in various fields. Problem decomposition and cooperation is known as a method for improving search performance. In this research, we aim to improve efficiency of search by introducing problem decomposition and cooperation into RCGA. We focused on the group work which put into practice problem decomposition and cooperation in the real world. In group work, each of members collaborates with the others and is evaluated comprehensively from the outcome of the group and personal contribution to the group. We evaluated the search performance of the proposed method using six benchmark functions. As a result, we confirmed that the proposed method obtained the optimal solution with less evaluation number than the conventional methods.