Construction of small world networks based on K-means clustering analysis

In this paper we present a new method to create small world networks based on K-means clustering analysis. Because of the close relationship between the small world networks and the data with clustering characteristics, the resulting networks based on K-means method have many properties of small world networks including small average distance, right skewed degree distribution, and the clustering effect. Moreover the constructing process also has shown some behaviors including networks formation and evolution of small world networks.