带自适应迁入的生物地理学优化算法  

Biogeography-based optimization with self-adaptive immigrate

作　　者：范会联[1] 曾广朴[1] 

机构地区：[1]长江师范学院计算机工程学院,重庆408100

出　　处：《计算机应用研究》2015年第12期3642-3645,共4页Application Research of Computers

基　　金：重庆市教委自然科学技术研究项目(KJ131307)

摘　　要：为提高生物地理学优化算法的全局和局部搜索能力,提出一种自适应迁入混合拉丁超立方采样的改进生物地理学优化算法。算法基于混沌函数优化种群初始分布,综合当前最优栖息地和当前迁出地优化迁入地适应度指数变量,以增加算法的全局搜索能力。在满足预定条件时,围绕当前最优栖息地进行拉丁超立方采样展开深度搜索,提高算法的收敛精度。同时,辅以适应度相关的变异机制。基于标准测试函数的仿真实验结果表明,算法在全局搜索、收敛速度和收敛精度上均优于对比算法。To improve global and local search ability, this paper proposed a biogeography-based optimization algorithm with adaptive immigration and Latin hypercube sampling. In this algorithm, it generated initial populations based on chaotic map, took into account two factors of global optimum habitat and the emigrating habitat to adaptive change the immigrating habitat, and performed Latin hypercube sampling around the best habitat when to meet some criteria. Meanwhile, it used self-adaptive probability mutation rate in the iterative process. The experiments on benchmark functions show that the proposed algorithm is superior to the compared algorithms in global search, convergence speed and optimization performance.

关 键 词：生物地理学优化 自适应迁入 拉丁超立方采样 混沌映射 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]