Scale-invariant density-based clustering initialization algorithm and its application

Abstract

In this paper, we bring out a new density-based clustering initialization algorithm which is invariant to the scale factor. Instead of using the scale factor while the cluster initialization, in this research, we determine the number and position of clusters according to the changes of cluster density with the division and agglomeration processes. During the division process, the initial cluster seeds are produced by a self-propagate method according to the density changes. The number of clusters is determined by agglomerating pair of RNN (reciprocal nearest neighbor) cluster seeds, when the density of newly merged cluster is increased. When no more cluster seeds can be merged any more, the remained number of cluster seeds is regarded as the real cluster number. Through various experiments, the effectiveness of the proposed algorithm has been proved.