论文部分内容阅读
在传统的人工免疫网络基础上，将多智能体技术的典型策略融入到免疫网络的进化过程中。算法引入了邻域克隆选择，操作过程从局部到整体，能够更加全面地模拟免疫网络的自然进化模型；同时在免疫网络进化过程中增加了抗体间的竞争和协作操作，提高了网络的动态分析能力。后续实验中，分别采用常用的3组UCI数据和一幅红树林多光谱TM遥感图像对算法加以验证，实验结果表明算法对遥感图像有较高的分类效率，对UCI数据也有较好的分类效果，表明该算法一种有效的数据分类方法。
Based on the traditional artificial immune network, the typical strategy of multi-agent technology is integrated into the evolution of immune network. The algorithm introduced the selection of neighborhood cloning, and the operation process from part to whole can more completely simulate the natural evolutionary model of immune network. At the same time, the competition and collaboration between antibodies were increased in the process of immune network evolution, which improved the dynamic analysis of the network ability. In the follow-up experiments, the commonly used three sets of UCI data and one mangrove multi-spectral TM remote sensing image are respectively used to verify the algorithm. The experimental results show that the algorithm has higher classification efficiency for remote sensing images and better classification results for UCI data , Show that the algorithm is an effective data classification method.