摘要
聚类算法是数据挖掘的核心技术。介绍了几类主要的传统聚类算法,给出了每类算法的基本概念、基本原理、各类表示聚类的算法以及这些算法的特征。然后再提出了一种新的聚类算法———覆盖聚类算法,给出了该算法的具体步骤,并对模糊聚类算法和该算法用实验的方式进行比较,证明了覆盖聚类算法的可行性和有效性。最后分析了当前聚类算法存在的问题和发展方向。
Clustering method is the core of data mining technology. Introduces some main and traditional clustering algorithm and presents the basic concepts, principles of each algorithm and representative clustering methods of each category algorithms, it compares the main characters of these algorithms. Then brings forward a new clustering algorithm——covering clustering algorithm and presents its specific process and compares the fuzzy clustering algorithem and covering clustering algorithm with experimental results. The results show the feasibility and effectiveness of the covering clustering algorithm. And analyzes the research directions of the algorithm.
出处
《计算机技术与发展》
2007年第1期123-124,127,共3页
Computer Technology and Development
基金
国家自然科学基金资助项目(60475017)
教育部博士点基金资助项目(20040357002)
关键词
聚类算法
模糊聚类算法
覆盖聚类算法
clustering algorithm
fuzzy clustering algorithm
covering clustering algorithm