Crossover Interaction Between the Individuals in Structured Quantum Evolutionary Algorithms

摘要：

In this paper we propose a new crossover interaction operator between the individuals in structured Quantum Evolutionary Algorithms for improving the performance of Quantum Evolutionary Algorithms (QEA).The proposed structures for QEA are cellular, ring, star, grid, ladder and other structures. The proposed structures provides a better exploitation of local neighbourhoods before they move towards a global best, hence it increases population diversity. This paper compares the effects of the different structures and the proposed operator on the performance of the algorithm and diversity of the population. The proposed algorithm is tested on Knapsack problem, Trap problem and 14 numerical benchmark functions on several dimensions of 100, 250, 500 and 1000.Experimental results show that the proposed algorithm consistently exceeds the performance of QEA while keeping than QEA.

关键词： Quantum Evolutionary Algorithms Cellular Genetic Algorithms Knapsack Problem Optimization Structured Evolutionary algorithms

作者: Hossein Mohamadi Ali Nodehi Mohamad Tayarani Fariborz Mahmoudi

作者单位: Islamic Azad University Azadshahr Branch Gorgan, Iran Islamic Azad University Gorgan Branch Gorgan, Iran Islamic Azad University Mashhad Branch Mashhad, Iran Islamic Azad University Qazvin Branch Tehran, Iran

会议类型: 国际会议

会议名称: 2010 International Conference on Measuring Technology and Mechatronics Automation(ICMTMA 2010)(2010年检测技术与机电自动化国际会议)

会议地点: 长沙

会议语种:英文

页码: 869-873

在线出版日期: 2010-03-13（万方平台首次上网日期，不代表论文的发表时间）