基于半监督学习的应用流分类方法
A Semi-Supervised Clustering Method for Network Application Flow Classification
-
摘要: 将半监督学习应用到应用流分类问题中,提出了一种基于半监督聚类的应用流分类算法(PSOSC).首先采用粒子群优化的K均值聚类方法对大量的无标记数据和少量的标记数据进行聚类,利用少量标记数据确定簇与应用类型的映射关系,实现应用流分类.实验表明PSOSC算法有较高的流准确率,同时,降低了对标记数据的需求.Abstract: In this paper, a feature selection method based on entropy is proposed firstly. Five TCP connection features are selected for classifier. Then, a semi-supervised classification method that allows classifiers to be designed from training data consisting of only a few labelled and many unlabelled is proposed. The experiment shows that the detection results precedes on Kmeans method.