决策系统在K-means算法中的应用

Application of K-means Algorithm in the Decision MakingSystem

如今的聚类算法在数据挖掘和信息安全方面已有相当的应用。事实上在大数据时代之中,为了识别已知的或未知的数据则需要将通过数据聚类的算法来计算和实现。数据聚类算法是一种智能性的算法,其可以使得机器通过自我的学习来识别已知和未知的数据。目前的数据聚类算法,有基于划分的聚类算法、基于层次的聚类算法等各种的聚类算法。但在这些聚类算法中经典的算法仍然是基于距离的聚类算法,如K-means算法。因此论文的作者在查阅了一些关于距离聚类的算法之后,提出了将粗糙集中决策系统在K-means算法中进行首次的应用,这是论文的创新点。

Nowadays,clustering algorithms have already applied in data mining and information security.In fact,in the era of large data,in order to identify known or unknown data will need to be calculated and realized through data clustering algorithm.Data clustering algorithm is a kind of intelligent algorithm,which can make the machine identify the known and unknown data through self study.The current data clustering algorithm,clustering algorithm based on clustering,hierarchical clustering algorithm and other clustering algorithm.However,the classical algorithm of clustering algorithm is still based on the distance based clustering algorithm,such as K-means algorithm.So the author of this paper after consulting some about distance clustering algorithm proposes the rough set decision system in the K-means algorithm for the first application,which is the innovation of this paper.