基于调整互信息的二进制协议一类分类算法

为解决未知协议种类繁多、聚类结果不能涵盖所有协议的问题，提出一种基于调整互信息的一类分类算法。采用改进的k-means 聚类，构建目标样本的合理覆盖模型，计算每个聚类中心的调整互信息阈值，得到各个聚类中心的调整互信息值，对不同聚类互信息阈值进行比较，并通过实验验证了算法的有效性。实验结果表明：与其他传统的一类分类方法相比，该方法在二进制协议一类分类中取得了较好的结果。

A Class of Classification Algorithm for Binary Protocol Based onAdjusting Mutual Information

In order to solve the problem that there are many kinds of unknown protocols and the clustering results cannot cover all protocols, a classification algorithm based on adjusting mutual information is proposed. By using theimproved k-means clustering, the reasonable coverage model of the target sample is constructed, the adjusted mutualinformation threshold of each clustering center is calculated, the adjusted mutual information value of each clusteringcenter is obtained, and the different clustering mutual information threshold is compared. The effectiveness of the algorithmis verified by experiments. The experimental results show that compared with other traditional classification methods, thismethod has achieved better results in the classification of binary protocols.