基于主动学习方法的网络流分类研究
Network Flow Classification Based on Active Learning
-
摘要: 提出了一种基于主动学习方法的网络流分类方法, 采用主动学习技术提取少量高质量的训练样本进行建模.并提出了一种基于轮盘赌选择的样本筛选方法, 能够有效避免已有主动学习方法中的早熟收敛现象.实验结果表明, 其相对于已有的流识别方法, 能够在仅依赖少量高质量训练样本的前提下, 保证较高的识别正确率, 更适用于现实网络环境.Abstract: This paper introduces an active learning method to select the most qualified data for training and propose a roulette wheel selection method.The experimental results demonstrate that the proposed method is able to guarantee high identification accuracy by using a small quantity of high qualified data.Therefore, it is more suitable for the real network applications than the traditional ones.