新的采用球面杂交的克隆选择算法  

New clone selection algorithm used sphere crossover

作　　者：周瑞琼[1] 吴洪丽[1,2] 

机构地区：[1]海南师范大学信息科学与技术学院,海口571158 [2]中国科学院成都计算机应用研究所,成都610041

出　　处：《计算机应用研究》2010年第11期4111-4113,共3页Application Research of Computers

基　　金：海南省自然科学基金资助项目(807050)

摘　　要：针对传统克隆选择算法的不足,提出了一个基于球面杂交的新型克隆选择算法。在该算法的每次迭代过程中,动态地计算出每个抗体的变异概率,根据抗体的亲和度将抗体种群动态分为记忆单元和一般抗体单元,并以球面杂交方式对种群进行调整,从而加快了算法的全局搜索速度。实例验证了所提算法的有效性、可行性。According to deficiencies of traditional clone selection algorithm,this paper proposed a new clone selection algorithm based on sphere crossover.Firstly,calculated mutation probability of each antibody dynamically.And then,divided according to antibody affinity,antibody populations dynamically into memory antibody units and general antibody units.Subsequently,adjusted antibody populations by sphere crossover so that accelerated global search speed of the proposed algorithm.The effectiveness and the feasibility of the proposed algorithm are verified by examples.

关 键 词：球面杂交 克隆选择算法 变异概率 抗体亲和度 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]