A New Network Traffic Classification Method Based on Optimized Hadamard Matrix and ECOC-SVM

Abstract:

The traditional network traffic classification methods have many shortcomings, the classification accuracy is not high, the encrypted traffic cannot be analyzed, and the computational burden is usually large. To overcome above problems, this paper presents a new network traffic classification method based on optimized Hadamard matrix and ECOC. Through restructuring the Hadamard matrix and erasing the interference rows and columns, the ECOC table is optimized while eliminating SVM sample imbalance, and the error correcting ability for classification is reserved. The experiments results show that the proposed method outperform in network traffic classification and improve the classification accuracy.

• Periodical: Advanced Materials Research (Volumes 989-994)
• Pages: 1895-1900
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.989-994.1895
• Online since: July 2014
• Authors: Hong Zhi Wang*, Li Hui Yan
• Keywords: ECOC, Hadamard Matrix, Network Traffic Classification, SVM

References

[1] Xiong Gang, Meng Jiao, Cao Zigang, et al. Research Progress and Prospects of Network Traffic Classification[J]. Journal of Integration Technology, 2012, 1(1): 32-42.

[2] Li Wei, Canini M, Moore A W. Efficient Application Identification and the Temporal and Spatial Stability of Classification Schema[J]. Computer Networks, 2009, 53(6): 790-809.

DOI: 10.1016/j.comnet.2008.11.016

[3] Sen S, Spatscheck O, Wang D. Accurate, Scalable in Network Identification of P2P Traffic Using Application Singntures[C]. In WWW2004. USA (New York), 2004: 512-521.

DOI: 10.1145/988672.988742

[4] Moore A, Papagiannaki K. Toward the accurate identification of network applications[C]. Proceedings of Passive and Active Measurement workshop. USA (Boston), 2005: 41-54.

DOI: 10.1007/978-3-540-31966-5_4

[5] Karagiannis T, Broido A, Faloutsos M, et al. Transport Layer Identification of P2P Traffic[C]. Internet Measurement Conference (IMC) 2004. USA (New York), 2004: 121-134.

DOI: 10.1145/1028788.1028804

[6] Wang Junsong, Gao Zhiwei. Network Traffic Modeling and Prediction Based on RBF Neural Network[J]. Computer Engineering and Applications, 2008, 44(13): 6-11.

[7] She Feng, Wang Xiaoling. Network Traffic Classification Based on Semi-supervised Learning[J]. Computer Engineering, 2009, 35(12): 90-94.

[8] Liang Sheng. Identification method of Internet Streaming based on SVM and clustering[J]. Computer Engineering and Design, 2010, 31(7): 1566-1569.

[9] Qiu Jing, Xia Jingbo, Bai Jun. Network Traffic Classification Using SVM Decision Tree[J]. Electrnoics Optics & Control, 2012, 19(6): 13-16.

[10] Ouyang guang, Li Qianqian, Man Junfeng. The Network Traffic Classification Techniques Based on DDAG-SVM[J]. Mathematics in Practice and Theory, 2013, 43(8): 197-203.

[11] Li Jianwu, Lu Yao. A Fast Multi-class Support Vector Machine[J]. Pattern Recognition and Artificial Inteligence, 2007, 20(3): 301-307.

[12] Yin Anrong, Xie Xiang, Kuang Jingming. Application of Hadamard ECOC in Multi-Class Problems Based on SVM[J]. ACTA ELECTRONICA SINICA, 2008, 36(1): 122-126.

DOI: 10.21437/interspeech.2005-672

[13] Cortes C, Vapnik V. Support-vector networks [J]. Machine Learning, 1995, 20: 273-297.

DOI: 10.1007/bf00994018

[14] Xu Peng, Liu Qiong, Lin Sen. Internet Traffic Classification Using Support Vector Machine[J]. Journal of Computer Research and Development, 2009, 46(3): 407-414.

[15] Ran Wang, Sam Kwong, Degang Chen. A new method for multi-class support vector machines by training least number of classifiers[C]. Proceedings of the 2011 International Conference on Machine Learning and Cybernetics. China(Guilin), 2011: 648-653.

DOI: 10.1109/icmlc.2011.6016830

[16] V N Vapnik. Statistical Learning Theory[M]. Wiley Inter-Science, 1998: 493-520.

[17] J Friedman. Another approach to polychotomous classification, Technical report [R] Stanford University, Department of Statistics, (1996).

[18] T G Dietterieh, G Bakiri. Solving Multi-class Learning Problems via Error-Correcting Output Codes[J]. Journal of Artificial Intelligence Research, 1994, 2(1): 263-286.

DOI: 10.1613/jair.105

[19] Wang Wanjiang. The Construction of Hadamard Matrix and Its Application[D]. Tianjin: Tianjin Polytechnic Uinversity, (2007).