摘要
在互联网产生的早期阶段对其进行准确有效的识别,对于网络管理和网络安全来说都有着极其重要的意义。鉴于此,近年来越来越多的研究致力于仅仅基于流量早期的数个数据包,建立有效的机器学习模型对其进行识别。本文力图基于柔性神经树(FNT)构建有效的互联网流量早期识别模型。两个开放数据集和一个实验室采集的数据集用于实验研究,并将FNT与8种经典算法进行对比。实验结果表明,FNT在大多数情况下,其识别率和误报率指标优于其他算法,这说明FNT是一种有效的流量早期识别模型。
Identifying Internet traffic at their early stages accurately is very important for network management and security.Recent years,more and more studies have devoted to find effective machine learning models to identify traffics with the few packets at the early stage. This paper tries to build an effective early stage traffic identification model by applying flexible neural trees. Three network traffic data sets including two open data sets are used for the study. Eight classical classifiers are employed as the comparing methods in the identification experiments. FNT outperforms the other methods for most cases in the identification experiments,and it behaves very well for both of TPR and FPR. Thus,FNT is effective for early stage traffic identification.
出处
《智能计算机与应用》
2015年第2期21-24,共4页
Intelligent Computer and Applications
基金
国家973重点基础研究发展计划(2011CB302605)
国家863高技术研究发展计划(2011AA010705
2012AA012502
2012AA012506)
"十一五"国家科技支撑计划(2012BAH37B01)
国家自然科学基金(11226239
6110018
61173144
61472164)
关键词
流量识别
机器学习
早期特征
柔性神经树
Traffic Identification
Machine Learning
Early Stage Features
Flexible Neural Trees