摘要 聚类分析旨在根据元素的相似性将其分类。本文提出了一种新的聚类方法:“We propose an approach based on the idea that cluster centers are characterized by a higher density than their neighbors and by a relatively large distance from points with higher densities”。 正文 已有的聚类方法例如K-means和K-medoids通过距离之和最小来找到最佳聚类中心,这些方法无法检测非球面的聚类。 人们选择一个阈值