摘要
克隆选择算法是目前应用较广的一种智能优化算法,但它在选择时具有一定的盲目性。为了克服它的这个不足,论文提出了一种改进型动态自适应克隆选择算法。在该算法中,首先根据抗体的亲和度将抗体群动态分为记忆单元和一般抗体单元,然后再借助抗体的亲和度修正抗体的变异概率并根据修正后的变异概率进行变异操作,紧接着以球面杂交方式对种群进行调整以产生新的种群。上述策略使得该算法在选择时具有一定的针对性,从而加快了它的全局搜索速度,仿真结果验证了所提算法的有效性、可行性。
At present,clone selection algorithm is an intelligent optimization algorithm which is widely applied.However,traditional clone selection algorithm has the deficiency of blind selection.In order to overcome this deficiency,an improved dynamic adaptive clone selection algorithm was proposed.Firstly,according to affinity,antibody population was dynamically divided into memory antibody units and general antibody units.And then,variation probability of each antibody which was dynamically corrected by means of affinity was used to carry out variation operation.Subsequently,antibody population was adjusted by sphere crossover to generate new population.The selection and the global search speed of the proposed algorithm are improved through the afore-mentioned strategies.The effectiveness and the feasibility of the proposed algorithm are verified by simulation results.
出处
《计算机与数字工程》
2012年第1期11-13,共3页
Computer & Digital Engineering
基金
河南省科技厅重点项目(编号:112102210395)资助
关键词
克隆选择
抗体
变异概率
球面杂交
clone selection
antibody
variation probability
sphere crossover
