【摘要】 针对在KAD网络中核心节点的识别问题,提出了一种基于BP模型对节点重要程度进行实时判定的方法。结合KAD网络测量的结果,对网络中核心节点的属性特征进行提取和归一化处理,获得了一组可分离度较高特征集合。采用MatLab设计相应的学习算法对BP网络进行训练,使结果收敛于预定误差区间。将完成训练的BP网络模型应用于对测试节点的判定,实验结果表明该方法可以实时地完成核心节点的判定,并且识别准确率可达到约70%。更多还原

【Abstract】 In view of the core node recognition in the KAD(Kademlia),a model based on BP is presented to determine whether a node is core node in real time.According to the result of the measurement for KAD,some attribute characteristics extraction and normalization processing is implemented to obtain an attribute set with higher separable degree.An algorithm in MatLab is designed to train the BP network until the results limit in a predetermined error range.In addition,the trained BP model is adapt to test prepared data,the results of the experiment show that the method can judge a node degrees of importance,and the recognition accuracy rate is up to about 70%.更多还原