期刊名称：International Journal of Computer Science and Network Security
印刷版ISSN：1738-7906
出版年度：2006
卷号：6
期号：8A
页码：43-47
出版社：International Journal of Computer Science and Network Security
摘要：K-means with its rapidity, simplicity and high scalability, has become one of the most widely used text clustering techniques. However, owing to its random selection of initial centers, unstable results were often gotten while using traditional K-means and its variants. Here a new technique of optimizing initial centers of clustering is proposed based on self-adoptively selecting density radius. The result of the experiments shows that K-means with the proposed technique can produce cluster results with high accuracy as well as stability
关键词：Text clustering, K-means, Density radius, Self-adoptively
