An Improved K-means Clustering Algorithm for Complex Networks

DOI

10.2991/iset-15.2015.24How to use a DOI?

Keywords

Complex networks, K-means, Clustering, Node importance

Abstract

The exploration about cluster structure in Complex Networks is crucial for analyzing and understanding Complex Networks. K-means algorithm is a widely used clustering algorithm. In this paper, a novel algorithm is proposed based on K-means. Considering, Complex Networks obeys Power-law Degree Distribution, this improved algorithm chooses nodes with high importance as the initial clustering centroids, and uses the distance to these key nodes as clustering measurement. The experiments prove that the new algorithm can conduct accurate clustering with acceptable performance.

Copyright

© 2015, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Hao Li
AU  - Haoxiang Wang
AU  - Zengxian Chen
PY  - 2015/03
DA  - 2015/03
TI  - An Improved K-means Clustering Algorithm for Complex Networks
BT  - Proceedings of the First International Conference on Information Science and Electronic Technology
PB  - Atlantis Press
SP  - 90
EP  - 93
SN  - 2352-538X
UR  - https://doi.org/10.2991/iset-15.2015.24
DO  - 10.2991/iset-15.2015.24
ID  - Li2015/03
ER  -