Network traffic classification based on optimized SVM model

被引：0

作者：

Cao, Jie ^{[1
,2
]}

Fang, Zhiyi ^{[1
]}

Qu, Guannan ^{[1
]}

Zhang, Dan ^{[1
]}

机构：

[1] College of Computer Science and Technology, Jilin University, Changchun

[2] College of Information Engineering, Northeast Dianli University, Jilin

来源：

Qu, Guannan | 1600年 / Binary Information Press卷 / 10期

关键词：

Feature selection; Machine learning; Support vector machine; Traffic classification;

D O I：

10.12733/jcis12788

中图分类号：

学科分类号：

摘要：

The traffic classification approach based on support vector machine (SVM) is proposed which converts the network traffic classification problem to a quadratic optimization problem using non-linear transformation and structural risk minimization. It performs good accuracy and stability. However, the traditional classification approach of SVM without considering the feature selection problem, makes the SVM classification performance is not ideal. We design an optimized SVM model (RI-SVM). The experiments on RI-SVM model prove that the dimension of attribute features is reduced significantly, computational complexity is declined greatly, and training time is shorten obviously. The traffic classification performance of RI-SVM is better than that of the traditional SVM. Copyright © 2014 Binary Information Press.

引用

页码：9529 / 9538

页数：9

共 17 条

[1]

(2009)

[2]

Moore A., Toward the accurate identification of network application, Proceedings of PAM, (2005)

[3]

Application Layer Packet Classifier for Linux, (2009)

[4]

Dainotti, Issues and future directions in traffic classification, 26, pp. 35-40, (2012)

[5]

Branch, Rapid identification of Skype traffic flows, Proceedings of the 18th International Workshop on Network and Operating System Support for Digital Audio and Video, pp. 91-96, (2009)

[6]

Gonzaez-Castano, Support vector machine detection of peer-to-peer traffic, Proceedings of IEEE International Conference on Computational Intelligence for Measurement Systems and Applications, pp. 103-108, (2006)

[7]

Moore A., Internet traffic classification using bayesian analysis techniques, ACM SIGMETRICS Perform, Eval. Rev., 33, 1, pp. 50-60, (2005)

[8]

Zhang J., Network Traffic Classification Using Correlation Information, IEEE Trans. on Parallel and Distributed Systems, 24, pp. 104-117, (2013)

[9]

Gu C., Realtime Traffic Classification Based on Semi-supervised Learning, Journal of Computational Information Systems, 7, 7, pp. 2347-2355, (2011)

[10]

Mcgregor A., Flow clustering using machine learning techniques, Proceedings of the Passive and Active Measurement Workshop, 3015, pp. 205-214, (2004)

← 1 2 →