基于活跃点的社区跟踪算法
发布时间:2018-06-15 23:48
本文选题:社会网络分析 + 时域网络 ; 参考:《应用科学学报》2017年05期
【摘要】:针对复杂网络社区跟踪中存在忽略演化时域因素以及忽略网络成员演化差异性不足等问题,提出一种社区跟踪方法.对相似函数添加时域信息,并考虑网络演化的平滑性与节点间的差异性,提取网络中的活跃节点进行社区跟踪.实验表明,该算法在DBLP数据集上能比其他社区跟踪算法更好地发现社区演化过程,且找到的社区信息相似度较高.
[Abstract]:Aiming at the problems of neglecting evolution time domain factors and neglecting the difference of evolution of network members in complex network community tracking, a community tracking method is proposed. The time-domain information is added to the similarity function, and considering the smoothness of network evolution and the difference between nodes, the active nodes in the network are extracted for community tracking. Experiments show that the proposed algorithm can detect the evolution process of the community better than other community tracking algorithms on DBLP datasets, and the community information similarity is higher.
【作者单位】: 兰州交通大学电子信息学院;
【基金】:国家自然科学基金(No.61163010) 兰州市科技计划项目基金(No.2014-1-171) 金川公司预研基金(No.JCYY2013012)资助
【分类号】:O157.5
,
本文编号:2024202
本文链接:https://www.wllwen.com/kejilunwen/yysx/2024202.html