【摘要】 提出了一种基于人工免疫系统重要模型aiNet模型的层次聚类算法aiNHA。该算法首先采用aiNet的方法生成抗体的记忆细胞矩体和相似性矩阵,这样就将数据集划分为若干子簇。再按照层次聚类的方法,合并连接相似度高的子簇,得到最终的聚类结果。该算法适用于发现任意形状的聚类簇,并且继承了免疫算法搜索速度快、效率高的优点。更多还原

【Abstract】 This paper presents a hierarchical clustering algorithm aiNHA based on the aiNet model which is an important model of Artificial Immune System.Firstly,it generates the memory matrix and the similarity matrix of the antibodies in the aiNet method.So it can divide the data set into several sub-clusters.Then it combines the sub-clusters with higher similarities in the hierarchical clustering method and gets the final clustering result.The algorithm can be used in clustering the arbitrary shapes of data sets.And it has the fast discovering speed high efficiency,which inherit the advantages of the immune algorithms.更多还原