研究者情報 | 神奈川大学

ノト　マサト Noto Masato 能登　正人所属神奈川大学情報学部システム数理学科神奈川大学大学院工学研究科工学専攻（電気電子情報工学領域）職種教授
言語種別	英語
発行・発表の年月	2024/08
形態種別	学術雑誌
査読	査読あり
標題	Improved Kepler Optimization Algorithm Based on Mixed Strategy
執筆形態	共著
掲載誌名	Lecture Notes in Computer Science
掲載区分	国外
出版社・発行元	Springer Nature
巻・号・頁	14788,pp.157-170
著者・共著者	J. Li, M. Noto, Y. Zhang
概要	The original Kepler optimization algorithm (KOA) is characterized by slow convergence speed, weak global search capability, low solution accuracy, and susceptibility to local optima. In this paper, we propose MSKOA, a hybrid strategy designed to improve the features of the original KOA. Specifically, we adopt a Sobol sequence to initialize the population, aiming to achieve a more uniform distribution of initial solutions across the solution space, and integrate a sine-cosine algorithm with mutation opposition-based learning to enhance both the global search and local exploitation capabilities. The results of experimental comparative analysis on ten benchmark test functions demonstrate that the improved Kepler optimization algorithm based on a mixed strategy exhibits notable improvements in both convergence speed and solution accuracy.