基于非一致性自适应变异的克隆选择算法

基金项目: 国家863计划资助项目(2007AA12Z181,2007AA12Z148)；国家自然科学基金资助项目(40771139,40523005,40721001)；模式识别国家重点实验室开放研究基金资助项目

详细信息

A Clonal Selection Algorithm Based on Non-uniform Adaptive Mutation

¹State Key Laboratory for Information Engineering in Surveying,Mapping and Remote Sensing, Wuhan University,129 Luoyu Road,Wuhan 430079,China

Funds: 国家863计划资助项目(2007AA12Z181,2007AA12Z148)；国家自然科学基金资助项目(40771139,40523005,40721001)；模式识别国家重点实验室开放研究基金资助项目

摘要: 提出了一种基于非一致性自适应变异的克隆选择算法。该算法根据抗体的亲和力自适应地确定相应抗体的变异率,同时采用非一致性变异方法来提高算法的效率。实验证明,与传统的克隆选择算法相比,本文提出的方法所需要的收敛时间更少,且能快速地找到最优解,具有一定的实用价值。
- 人工免疫系统 /
- 克隆选择 /
- 非一致性变异
Abstract: We propose an adaptive clonal selection algorithm,which can adaptively set the mutation rate of each antibody according to its affinity and utilize the non-uniform mutation to decrease the complexity of the algorithm and computational costs.Experiments were performed to evaluate the performance of our proposed algorithm in comparison with other methods,genetic algorithm,simulated annealing algorithm,genetic simulated annealing algorithm.The results show that our proposed algorithm consistently outperforms the traditional algorithms.Compared with traditional CSA,our proposed algorithm can more quickly find the optimal solution and hence provides an effective solution.
- artificial immune system /
- clonal selection /
- non-uniform mutation