Memetic frog leaping algorithm for global optimization

作     者：Tang, Deyu Liu, Zhen Yang, Jin Zhao, Jie 

作者机构：Guangdong Pharmaceut Univ Sch Med Informat & Engn Guangzhou 510006 Guangdong Peoples R China South China Univ Technol Sch Comp Sci & Engn Guangzhou 510006 Guangdong Peoples R China Guangdong Univ Technol Sch Management Dept Informat Management Engn Guangzhou 510520 Guangdong Peoples R China Amer Univ Dept Comp Sci Washington DC 20016 USA 

出 版 物：《SOFT COMPUTING》 (Soft Comput.)

年 卷 期：2019年第23卷第21期

页      面：11077-11105页

核心收录：

学科分类：08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：Guang Dong Provincial Natural fund project, Drug-target interaction prediction method based on collaborative intelligent optimization [2016A030310300] Natural Science Foundation of China NSFC Guangdong province precise medicine and big data engineering technology research center for traditional Chinese medicine, Guang Dong Provincial Natural fund [2014A030313585, 2015A030310267, 2015A030310483] Major scientific research projects of Guangdong, Research of Behavioral Trust resisting collusion reputation attack based on implicit and explicit big behavior data analysis [2017WTSCX021] Philosophy and Social Sciences of Guangzhou '13th Five-Year' program [2018GZGJ48] 

主　　题：Memetic algorithm Shuffled frog leaping algorithm Gravity search algorithm Levy flight Continuous optimization 

摘      要：Developing an effective memetic algorithm that integrates leaning units and achieves the synergistic coordination between exploration and exploitation is a difficult task. In this paper, we propose a memetic algorithm based on the shuffled frog leaping algorithm, which is fulfilled by three units: memetic diffusion component, memetic evolutionary component and memetic learning component. Memetic diffusion component enhances the diversity of population by the shuffled process. Memetic evolutionary component accomplishes the exploitation task by integrating the frog leaping rule, geometric center, Newton s gravitational force-based gravitational center and Levy flight operator. Memetic learning component improves the exploration by an adaptive learning rule based on the individual selection and the dimension selection. In order to evaluate the effectiveness of the proposed algorithm, 30 benchmark functions and a real-world optimization problem are used to compare our algorithm against 13 well-known heuristic methods. The experimental results demonstrate that the performance of our algorithm is better than others for the continuous optimization problems.