摘要
通过凝聚式聚类方法抽取网络的层次结构,并基于拓扑结构分析,给出了社会网络的标注密度估计函数。通过对密度估计函数在网络层次结构上的聚合操作,计算聚簇的特征性指标,从而达到发现特征聚簇的目的。在大规模的真实数据上对这些方法和模型进行了验证,实验结果表明,所提出的思路和模型是合理的,算法是高效、可伸缩的。
A hierarchical structure extraction approach based on agglomerative clustering was proposed, and a density estimation based on topological structure was designed. By conducting the hierarchical aggregation on layers of hierarchical structure, the characteristic of clusters could be measured. The empirical study conducted on a large real data set indicates that the model and measures are interesting and meaningful, and the algorithms are effective and efficient in practice.
出处
《通信学报》
EI
CSCD
北大核心
2012年第5期38-48,共11页
Journal on Communications
基金
国家自然科学基金资助项目(60933005
60873204)
国家高技术研究发展计划("863"计划)基金资助项目(2010AA012505)~~
关键词
社会网络
特征簇
数据挖掘
social network
characteristic clusters
data mining
