基于智能互补策略的免疫算法

摘要

There are redundant antibodies after training in self-organization Antibody Network (soAbNet) and its network performance is instable. In order to improve the performance of soAbNet, a hybrid immune diagnosis method was proposed based on intelligence complementary strategy. Immune operator was introduced into soAbNet, which consisted of two components: vaccination and immunoselection. Vaccines obtained through K-means algorithm were taken as initial antibodies in immune operator, and immune network architecture was optimized by immunoselection. The experimental results on Iris dataset demonstrate that, the proposed hybrid immune algorithm sufficiency makes use of prior knowledge and learns data characteristics effectively, and the diagnostic accuracy and data enrichment rate are higher compared with soAbNet.%针对自组织抗体网络存在冗余抗体和网络性能不稳定的问题,提出一种基于智能互补策略的免疫算法.基于智能互补观点,该方法引入免疫进化算法中的免疫算子,它由接种疫苗和免疫选择两部分操作构成.接种疫苗利用K-means聚类算法抽取疫苗作为初始抗体,形成关于系统的粗略描述；免疫选择对记忆抗体进行优化,调整网络结构.在Iris数据集上的测试结果表明,该方法能够充分利用系统的先验知识快速有效地提取样本的数据特征,使得数据浓缩率和分类正确率更高.