机会网络中新节点归属性判断方法

Judgment method of new node belongingness in opportunistic network

提出一种基于神经网络的判断新节点归属性的方法。通过将节点间的相遇频率、相遇持续时间、相遇次数作为神经网络的输入向量,不断调整模型的权值和阀值进行模型的训练,训练完成后,把新节点组成的向量输入该模型,经过网络计算得出获胜的神经元,获胜的神经元代表输入数据的分类,以此判断新节点的归属性。在人工数据集LFK基准网络上进行测试,测试结果表明,该方法可以有效判断新节点的归属性。

A method that could judge which community a new node belonged to was proposed. Meeting frequency, meeting dura-tion and the number of meeting between two nodes were treated as the input vector of neural network. The weights and thres-holds of the model were adjusted constantly in the process of training this model. After the model was completed, a vector made up of new nodes was fed into the model, through network computing, winning neuron could be obtained, the winning neuron was the representative of the input data classification, based on this, new node belongingness was judged Tests were made on the artificial data sets of LFK, the results show that this method can effectively determine which community new nodes belong to.