摘要
许多经典的聚类方法已成功应用于复杂网络社团挖掘问题,如C均值聚类、模糊C均值等。但这些传统的聚类算法对初始节点敏感,并且需要提前给定网络社团的个数。为此,提出一种基于PageRank重要性度量和模糊C均值聚类的社团挖掘算法(记为PFCM)。利用节点的PageRank重要性度量和最大最小模块度值来确定网络中最优种子节点,通过谱映射方法建立网络数据到特征空间的映射,进而利用模糊聚类对网络节点进行划分。最后通过真实网络数据对本文所提出的社团挖掘算法进行了验证,结果表明PFCM算法能够克服传统模糊C均值聚类算法稳定性差的缺点,提高了社团挖掘算法的有效性。
Many classical clustering methods,such as C-means clustering and fuzzy C-means,have been applied to community detection problems on complex networks.But these traditional clustering algorithms are very sensitive to initial nodes,and the number of communities must be given in advance.This paper proposes a new community detection method based on nodes’PageRank values and fuzzy C-mean(denoted by PFCM).The PageRank centrality and the maximum and minimum modularity values of the nodes are first calculated to determine the optimal seed nodes in the network.We map the network into feature vectors by spectral method,and then the fuzzy clustering is evoked to partition the nodes into different communities.Finally,the numerical experiments on real network data show that the proposed algorithm overcomes the shortcomings of the fuzzy c-means clustering algorithm,and improve the performance of the community detection approach.
作者
马丽娜
MA Lina(School of Economics and Statistics, Xingzhi College of Xi’an University of Finance and Economics, Xi’an 710038, China)
出处
《微型电脑应用》
2022年第6期34-36,共3页
Microcomputer Applications
基金
陕西省教育厅专项科学研究计划项目(19JK0330)。