基于自适应人工免疫网络算法的数据挖掘

基于人工免疫网络(Artificial Immune Network:aiNet),提出了一种自适应的人工免疫网络聚类算法。在该算法中,网络抗体间的抑制阀值、抗体的克隆数目、抗体的选择和再选择数目、抗体的变异大小都随网络进化而自适应变化,使最终网络结构更符合原始数据的内在结构,降低了算法对决策者的先验知识的依赖,也提高了算法的泛化能力,很好地解决了算法与问题的相关性。仿真实验结果表明了该算法的有效性和实用性。

Data mining based on adaptive artificial immune network algorithm

An adaptive artificial immune network algorithm for clustering,based on artificial Immune network model,is presented in this paper.The algorithm has the ability to achieve final network structure well-imaging the crude data feature because its parameters ,such as immune suppression threshold among the antibodies ,clone number of antibodies ,selected and re-selected number of antibodies,the maturation magnitude of antibodies,are all self-adapted well to the entire network structure during the process of evolution.The algorithm can also relieve the dependence on prior knowledge of decision maker and enlarge the application situation and solve the relativity between the algorithm and the issue.Simulation results demonstrate the validity and the practicability of the proposed algorithm.