| 基于DPI和机器学习的网络流量分类方法 |
| |
| 引用本文： | 李国平,王勇,陶晓玲.基于DPI和机器学习的网络流量分类方法[J].桂林电子科技大学学报,2012,32(2):140-144. |
| |
| 作者姓名： | 李国平 王勇 陶晓玲 |
| |
| 作者单位： | 1. 桂林电子科技大学 计算机科学与工程学院,广西 桂林,541004
2. 桂林电子科技大学 信息与通信学院,广西 桂林,541004 |
| |
| 基金项目： | 国家自然科学基金，广西自然科学基金 |
| |
| 摘 要： | 网络流量分类是实现网络管理的重要技术之一,但是单一的基于DPI或是机器学习的分类方法分类精确度低.提出了一种基于DPI和机器学习相结合的网络流量分类方法.该方法采用DPI检测已知特征的网络流量,利用机器学习方法辅助分析未知特征以及加密的网络流.实验表明该方法能够提高网络流量分类的精确度.
|
| 关 键 词： | 流量分类 深度包检测 机器学习 朴素贝叶斯 |
A novel method for network traffic classification based on DPI and machine learning |
| |
| Li Guoping
,
Wang Yong
,
Tao Xiaoling.A novel method for network traffic classification based on DPI and machine learning[J].Journal of Guilin Institute of Electronic Technology,2012,32(2):140-144. |
| |
| Authors: | Li Guoping Wang Yong Tao Xiaoling |
| |
| Affiliation: | 1.School of Computer Science and Engineering,Guilin University of Electronic Technology,Guilin 541004,China; 2.School of Information and Communication Engineering,Guilin University of Electronic Technology,Guilin 541004,China) |
| |
| Abstract: | Network traffic classification is one of the important technology to implement network management,but the method for network traffic classification based on single DPI or machine learning is very poor.An algorithm based on DPI with machine learning for network traffic classification was proposed.Unencrypted network traffic was detected by DPI and others classified by maching learning.The experimental result shows that this method can get a more accuracy classification result. |
| |
| Keywords: | network traffic classification deep packet inspection machine learning Nave Bayesian |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
