期刊名称：Journal of Modern Applied Statistical Methods
出版年度：2006
卷号：5
期号：1
页码：21
出版社：Wayne State University
摘要：The clustering problem has been widely studied because it arises in many knowledge management oriented applications. It aims at identifying the distribution of patterns and intrinsic correlations in data sets by partitioning the data points into similarity clusters. Traditional clustering algorithms use distance functions to measure similarity centroid, which subside the influences of data points. Hence, in this article a novel non-distance based clustering algorithm is proposed which uses Combined Standard Deviation (CSD) as measure of similarity. The performance of CSD based K-means approach, called K-CSD clustering algorithm, is tested on synthetic data sets. It compared favorably to widely used K-means clustering algorithm.
关键词：Clustering algorithm; combined standard deviation
