A Novel K-means Clustering Algorithm Based on Weighted Complex Networks Feature
Qingyi Wang · Computer Technology and Development · 2007
After analyzing the advantages and disadvantages of the traditional partitioned K-means clustering algorithm and based on the new theory results achieved in the field of complex networks,the definitions of weighted degree,weighted clustering degree,and weighted clustering coefficient of complex networks and a novel K-means clustering algorithm based on the weighted complex networks feature were proposed.The clustering of datum was transformed into clustering of nodes in complex networks.The experimental results show that this algorithm can find clustering centers better based on the weighted complex networks feature of nodes and it is robust to initialization,so the quality of clustering is improved greatly.