On clustering tree structured data with categorical nature

摘要: Clustering consists in partitioning a set of objects into disjoint and homogeneous clusters. For many years, clustering methods have been applied wide variety disciplines they also utilized scientific areas. Traditionally, deal with numerical data, i.e. represented by conjunction attribute values. However, nowadays commercial or databases usually contain categorical attributes. In this paper we present dissimilarity measure which is capable to tree structured data. Thus, it can be used for extending the various versions very popular k-means algorithm such We discuss how an extension achieved. Moreover, empirically prove that proposed accurate, compared other well-known (dis)similarity measures