Internet traffic classification using SVM with flexible feature space

Yaguan QIAN; Xiaohui GUAN; Bensheng YUN; Qiong LOU; Pengfei MA

doi:10.11959/j.issn.1000-0801.2016132

您当前的位置：

首页 >

文章列表页 >

Internet traffic classification using SVM with flexible feature space

research and development | 更新时间：2024-06-05

- Internet traffic classification using SVM with flexible feature space
- Observation and communication Vol. 32, Issue 5, Pages: 105-113(2016)
- 作者机构：
  
  1. 浙江科技学院理学院，浙江杭州 310023
  2. 浙江水利水电学院，浙江杭州 310018
- 作者简介：
- 基金信息：
- DOI：10.11959/j.issn.1000-0801.2016132
  CLC： TP393.04
- Published Online：2016-05，
  
  Published：20 May 2016
- 稿件说明：
移动端阅览
Yaguan QIAN, Xiaohui GUAN, Bensheng YUN, et al. Internet traffic classification using SVM with flexible feature space[J]. Observation and communication, 2016, 32(5): 105-113.
DOI：

Yaguan QIAN, Xiaohui GUAN, Bensheng YUN, et al. Internet traffic classification using SVM with flexible feature space[J]. Observation and communication, 2016, 32(5): 105-113. DOI： 10.11959/j.issn.1000-0801.2016132.

摘要

支持向量机（support vector machine

SVM）是一类具有良好泛化能力的机器学习算法，适合应用于互联网动态环境下的流量分类问题。目前将SVM扩展到流量分类这样的多分类问题的方法主要有One-Against-All和One-Against-One方法。这些方法都基于单一的特征空间训练SVM两分类器，没有考虑到不同特征对不同流量类的不同区分能力，因此获得的分离超平面并不是最合理的。为此提出了可变特征空间的SVM集成方法，即为每个两分类 SVM 构建具有最优区分能力的独立特征空间，单独训练两分类 SVM，最后再利用One-Against-All和One-Against-One方法集成为多分类器。实验表明，与原来的单一特征空间的One-Against-All和One-Against-One集成方法相比，提出的方法能有效提高流量分类器分类精度和召回率，更易获得最优分离超平面。

Abstract

SVM is a typical machine learning algorithm with prefect generalization capacity

which is suitable for the internet traffic classification.At present

there are two approaches

One-Against-All and One-Against-One

proposed for extending SVM to multi-class problem like traffic classification.However

these approaches are both based on a unique feature space.In fact

the separating capacity of a special traffic feature is not similar to different applications.Hence

flexible feature space for extending SVM was proposed

which constructs independent feature space with optimal discriminability for each binary-SVM and trains them under their own feature space.Finally

these trained binary-SVM were ensemble by One-Against-All and One-Against-One approaches.The experiments show that the proposed approach can efficiently improve the precision and callback of the traffic classifier and easily obtain more reasonable optimal separating hyper-plane.

关键词

Keywords

references

BUJLOW T , CARELA-ESPANOL V , BARLET-ROS P . Independent comparison of popular DPI tools for traffic classification . Computer Networks , 2015 ( 76 ): 75 - 89 .

钱亚冠，张旻 . 基于过抽样技术的 P2P流量识别方法 [J ] . 电信科学 2014 , 30 ( 4 ): 109 - 113 .

QIAN Y G ， ZHANG M . P2P traffic identification based over-sampling technique [J ] . Telecommunications Science , 2014 30 ( 4 ): 109 - 113 .

TONGAONKAR A , TORRES R , ILIOFOROU M , et al . Towards self-adaptive network traffic classification [J ] . Computer Communications , 2015 ( 56 ): 35 - 46 .

SOYSALA M , SCHMIDT E G . Machine learning algorithms for accurate flow-based network trafficclassification:evaluation and comparison . Performance Evaluation , 2010 , 67 ( 6 ): 451 - 467 .

SINGH H . Performance analysis of unsupervised machine learning techniques for network traffic classification [C ] // 2015 Fifth International Conference on Advanced Computing &Communication Technologies （ACCT）， Feb 21 - 25 , 2015 , Haryana,India . New Jersey : IEEE Press , 2015 : 401 - 404 .

徐鹏，刘琼，林森 . 基于支持向量机的Internet流量分类研究 [J ] . 计算机研究与发展 2009 , 46 ( 3 ): 407 - 414 .

XU P ， LIU Q ， LIN S . Internet traffic classification using support vector machine [J ] . Journal of Computer Research and Development , 2009 46 ( 3 ): 407 - 414 .

ESTE A , GRINGOLI F , SALGARELLI L . Support vector machines for TCP traffic classification [J ] . The International Journal of Computer and Telecommunications Networking , 2009 , 53 ( 14 ): 2476 - 2490 .

ZHOU X S . A P2P traffic classification method based on SVM [C ] // The 2008 International Symposium on Computer Science and Computational Technology ， Dec 20 - 22 , 2008 , Washington,DC,USA .[S.1.:s.n. ] , 2008 : 53 - 57 .

LI Z , YUAN R , GUAN X . Accurate classification of the internet traffic based on the svm method [C ] // The IEEE International Conference onCommunications,2007（ICC'07）， June 24 - 28 , 2007 , Glasgow,Scotland . New Jersey : IEEE Press , 2007 : 1373 - 1378 .

CHANG C C , LIN C J . LIBSVM:a library for support vector machines [EB/OL ] . [ 2001 - 07 - 20 ] . http://www.csie.ntu.edu.tw/cjlin/libsvm http://www.csie.ntu.edu.tw/cjlin/libsvm .

KREBEL H G . Pairwise classification and support vector machines [A ] // SCHOLKIPF B,BURGES C J C,SMOLA A.Advances in kernel methods:support vector learning [M ] . Cambridge : The MIT Press ， 1999 : 255 - 268 .

XIE G , ILIOFOTOU M , KERALAPURA R , et al . Subflow:Towards practical flow-level traffic classification [C ] // IEEE INFOCOM 2012 ， March 25 - 30 , 2012 , Orlando,FL,USA . New Jersey : IEEE Press , 2012 : 2541 - 2545 .

GUYONG I , WESTON J , BARNHILL S , et al . Gene selection for cancer classification using support vector machines [J ] . Machine Learning , 2002 , 46 ( 1 - 3 ): 389 - 422 .

MOORE A W.Dataset [EB/OL ] . [ 2009 - 06 - 29 ] . http://www.cl.cam.ac.uk/research/srg/netos/nprobe/data/papers/sigmetrics/ http://www.cl.cam.ac.uk/research/srg/netos/nprobe/data/papers/sigmetrics/ .

Views

421

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

GMTBLC: a deep learning-based bi-modal network traffic classification method

Time-frequency image and high-order spectrum characteristics based radar signal recognition

Research on network traffic classification based on machine learning and deep learning

Overview of research on fiber nonlinear equalization algorithm based on artificial intelligence

Application of machine learning in the fake user identification of IoT

Related Author

WANG Xinrui

WEN Jinglong

JIANG Qinlong

WEI Debin

Xiaoping JIN

Xiaofeng WANG

Yun CHEN

Zeyu TANG

Related Institution

School of Information Engineering, Dalian University

Tsinghua University

Tsinghua Shenzhen International Graduate School

Research Institute of China United Network Communication Co.,Ltd.

Commerce Center, China United Network Communication Co. , Ltd. , Beijing

⁰