基于边权重局部扩展的机会网络社区检测方法

Link-weight local expansion based communities detection method in opportunistic networks

为解决机会网络中社区重叠问题,提出一种基于边权重局部扩展的社区检测方法 (LWLE)。利用相遇时间和相遇间隔时间信息,计算节点间的关系强度作为边权重,根据它局部扩展初始节点社区。针对局部扩展方法中初始节点选择随机、重复计算的不足,给出一种利用节点聚集系数对初始节点进行选择的局部扩展优化策略。ONE模拟器仿真结果表明LWLE算法能够较准确地检测节点社区归属,能够得到重叠社区。

To solve the problem of overlapping community detection in opportunistic networks, a method called link-weight local expansion based community detection algorithm （LWLE） was proposed. According to the contact duration and the inter contact time, the strength of relation between nodes was calculated as the link-weight that was used to expand the community where the initial node belonged. For the deficiencies of randomly selecting initial nodes and repeatedly calculating in the local expansion process, an optimization strategy was proposed by exploiting node clustering coefficient to select initial nodes. In the end, the re suits of the simulation on ONE simulator show that the LWLE method can get high correct rate of community detection and obtain overlapping communities.