摘要
针对社区结构发现问题,提出了一种基于隐马尔可夫随机场社区发现算法。该方法将网络中的顶点度数映射为顶点信息值,用马尔可夫随机场模型描述网络中上下文信息并构造系统能量函数,使用迭代条件模式算法对能量方程进行优化。该方法在Zachary空手道俱乐部网络、海豚关系网络以及美国大学足球联赛网络上进行验证,实验结果表明,该算法的准确率较高。
For the problem of community structure detection of complex network,a community detection algorithm based on hidden Markov random field is presented.In this method,the network vertices information value corresponding to its degree is assumed,the HMRF model is applied to characterize the contexture-dependent information,and the energy function of system is defined,iterated conditional mode algorithm is applied to fulfill optimization.The algorithm is tested on Zachary karate clue network,dolphin social network and American College football network,and experimental result shows it has high accuracy rate.
出处
《计算机工程与设计》
CSCD
北大核心
2012年第9期3481-3484,共4页
Computer Engineering and Design
基金
天津市科技型中小企业创新基金项目(11ZXCXGX07700)
关键词
社区发现
隐马尔可夫随机场
复杂网络
顶点度数
迭代条件模式
community detection
hidden Markov random field
complex network
vertex degree
iterated conditional modes
