【摘要】 针对传统K-means聚类中存在的一系列问题,文中提出了一种基于K-means聚类的改进算法。该算法首先利用K-means++聚类从数据中选择K个距离尽可能远的对象作为初始聚类中心,然后利用K-mediods聚类选择数据样本的中位数作为聚类中心的对象,最后与两步聚类结合。通过对几个常用UCI标准数据集进行仿真实验,结果表明该算法比传统算法更优。更多还原

【Abstract】 Aiming at a series of problems in traditional K-means clustering,this paper proposes an improved algorithm based on K-means clustering. The algorithm uses K-means + + clustering to select K objects as far as possible from the data as the initial clustering center firstly,and then uses K-mediods clustering to select the median of the data samples as the cluster center object,and finally combined with Two-step clustering. Simulation experiments on several common UCI standard datasets show that the proposed algorithm is superior to traditional algorithms.更多还原