Abstract: Aimed to solve the problem that the density-based clustering algorithm dose not work well when data distribution is not even，a new clustering algorithm based on representatives and point density is provided.The algorithm discovers the clusters by examining k neighbors of each point in the data base.It chooses a seed point as the first representative and the representative’s k neighbors as its represent area.If the point in the represent areas satisfies the density threshold，this point will be a new representative.And repeating searching like this，all the linked represent areas and representatives will be a cluster.Experimental results show that this algorithm can discover clusters with arbitrary shapes and densities at different levels.

Key words: data mining, clustering, point density, representative, density threshold

摘要： 针对基于密度的聚类方法不能发现密度分布不均的数据样本的缺陷，提出了一种基于代表点和点密度的聚类算法。算法通过检查数据库中每个点的k近邻来寻找聚类。首先选取一个种子点作为类的第一个代表点，其k近邻为其代表区域，如果代表区域中的点密度满足密度阈值，则将该点作为一个新的代表点，如此反复地寻找代表点，这些区域相连的代表点及其代表区域将构成一个聚类。实验结果表明，该算法能够发现任意形状、大小和密度的聚类。

关键词: 数据挖掘, 聚类, 点密度, 代表点, 密度阈值