MCOA: mutated and self-adaptive cuckoo optimization algorithm

详细信息    查看全文

• 作者：Seyed Alireza Mohseni ; Tony Wong ; Vincent Duchaine
• 刊名：Evolutionary Intelligence
• 出版年：2016
• 出版时间：June 2016
• 年：2016
• 卷：9
• 期：1-2
• 页码：21-36
• 全文大小：1,160 KB
• 刊物类别：Engineering
• 刊物主题：Applied Mathematics and Computational Methods of Engineering
  Artificial Intelligence and Robotics
  Automation and Robotics
  Complexity
  Bioinformatics
  Applications of Mathematics
  
• 出版者：Springer Berlin / Heidelberg
• ISSN：1864-5917
• 卷排序：9

文摘

As with other nature-inspired algorithms, the cuckoo optimization algorithm (COA) produces a population of candidate solutions to find the (near-) optimal solutions to a problem. In this paper, several modifications, including a dynamic mutation operator, are proposed for this algorithm. Design of experiments is employed to determine factors controlling the value of parameters and the target levels of those values to achieve desirable output. The efficiency of the modified COA algorithm is substantiated with the help of several optimization test problems. The results are then compared to other well-known algorithms such as PSO, DE and harmony search using a non-parametric statistical procedure. In order to analyze its effectiveness, the proposed modified COA is applied to a feature selection problem and spacecraft attitude control problem.KeywordsEvolutionary algorithms (EAs)Cuckoo optimization algorithm (COA)Self-adaptive mutationDesign of experimentsMulti comparison testKruskal–Wallis test