基于等级制度的病毒进化遗传算法  

Virus-evolutionary genetic algorithm based on hierarchy

作　　者：顾民[1,2] 杨峰[1] 蒋开明[2] 

机构地区：[1]电子科技大学电子工程学院,成都611731 [2]成都理工大学核技术与自动化工程学院,成都610059

出　　处：《计算机应用》2010年第11期2884-2886,共3页journal of Computer Applications

基　　金：国家自然科学基金资助项目(10876007)

摘　　要：按照适应度将主群体分成高等主子群和低等主子群,病毒也相应地分为小病毒群和大病毒群。高等主子群个体感染小病毒后其显性值产生小尺度变化,低等主子群个体感染大病毒后其显性值产生大尺度变化,使优良个体在自身区域小范围内搜索,而不良个体则远离自身区域进行搜索,从而提高其搜索速度和精度。实例证明,改进算法在性能上优于传统病毒进化遗传算法。The host population was divided into high-rank and low-rank sub-populations according to fitness. Correspondingly, the viruses were divided into small virus and big virus population population. Small-scale change in the phenotype value of high-rank host individual occurred due to the infection of small virus. Large-scale change in the phenotype value of low-rank host individual occurred due to the infection of big virus, which made the best individual search in its own small-scale region, and made the poor individual search away from their own region, so as to enhance its search speed and accuracy. The experiments demonstrate that the proposed algorithm outperforms the traditional virus-evolutionary genetic algorithm.

关 键 词：遗传算法 病毒进化 适应度 等级制度 优化问题 

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]