A density-based method for selection of the initial clustering centers of K-means algorithm

Abstract

The initial clustering centers of traditional K-means algorithm are randomly generated from a data set, clustering effect is not very stable. Aimed at this problem, this paper puts forward a kind of optimal selection of the initial clustering center of K-means algorithm based on density, by calculating the local density of each data point and the minimum distance between that point and any other point with higher local density, choose K points with higher local density as the initial clustering centers. Through the UCI standard database for contrast experiment, proved that the improved K-means algorithm can eliminate the dependence on the initial clustering center, has relatively higher accuracy and stability than the traditional algorithm.