一种基于DBS的聚类算法

摘要

As the popularization of the internet and the quick increase of information, it makes us more difficult to find the useful knowledge from huge data. A new clustering algorithm based on density biased sampling is proposed, and the results of experiments show that the proposed algorithm is indeed better than the old algorithm as the increase of information and data dimensions, such as exactness rate of clustering and speed of deal with the data.%随着网络的普及和信息量的急剧增加,从海量数据中提取有用的数据信息已迫在眉睫.本文提出了一种基于密度偏差抽样的聚类算法,实验表明,随着信息量、数据维数的增加,该算法聚类的正确率以及对数据的处理速度都要较传统的聚类算法有所提高.