引力搜索算法在投影寻踪优化求解中的应用  

Application of gravitation research algorithm for solving projection pursuit optimization problem

作　　者：秦晋[1,2] 于本海[1,2] 智荣腾 

机构地区：[1]山东工商学院管理科学与工程学院,山东烟台264000 [2]山东省车联网工程技术研究中心,山东烟台264000

出　　处：《计算机工程与设计》2017年第7期1844-1847,1987,共5页Computer Engineering and Design

基　　金：国家自然科学基金项目(71471103;71301089)

摘　　要：针对投影寻踪方法中投影指标函数构造与优化较为困难的问题,引入引力搜索算法(gravitation research algorithm,GSA)的思想,采用罚函数法构造新的投影指标函数,提出引力搜索-投影寻踪算法(GSA-PP),简化投影指标函数的复杂程度,提高运算效率,给出GSA-PP算法的详细步骤。实验结果表明,将GSA用于投影寻踪优化求解中是可行的,为各领域使用投影寻踪评价模型提供了一种思路。Aiming at the difficulties of projection index function construction and optimization in projection pursuit,ideology of the gravitation research algorithm（GSA） was introduced,penalty function method was used to build new projection index function,and gravitation search based on projection pursuit algorithm（GSA-PP） was presented,which not only simplified the complexity of the projection index function,but improved the operation efficiency,and the detailed steps of the algorithm were given.Experimental results show that it is feasible to apply GSA in projection pursuit optimization problem,and provides a train of thought for fields involving projection pursuit evaluation model.

关 键 词：引力搜索算法 投影寻踪 罚函数 群体智能算法 软件质量 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程] TP301.6[自动化与计算机技术—控制科学与工程]