基于过抽样技术的P2P流量识别方法

doi:10.3969/j.issn.1000-0801.2014.04.016

电信科学 ›› 2014, Vol. 30 ›› Issue (4): 109-113.doi: 10.3969/j.issn.1000-0801.2014.04.016

基于过抽样技术的P2P流量识别方法

钱亚冠¹,张旻²

¹ 浙江科技学院理学院杭州 310023
² 杭州电子科技大学计算机学院杭州 310018

出版日期:2014-04-15 发布日期:2017-06-29
基金资助:
浙江省网络媒体云处理与分析工程技术中心开放课题

P2P Traffic Identification Based Over-Sampling Technique

Yaguan Qian¹,Min Zhang²

¹ College of Science, Zhejiang University of Science and Technology, Hangzhou 310023, China
² College of Computer Science, Hangzhou Dianzi University, Hangzhou 310018, China

Online:2014-04-15 Published:2017-06-29

摘要/Abstract

摘要：

针对P2P类不平衡问题提出将复杂的多类不平衡问题转化为简单的两类不平衡问题，再通过迭代SMOTE过抽样技术丰富P2P的概念表达，从而提高P2P流量的识别率。实验结果表明，该方法可以显著提高诸如Na?ve Bayes这样的简单模型在P2P上的识别率，由此可证明该方法对于改善P2P类不平衡问题的有效性。

关键词: 类不平衡, 过抽样, P2P流量识别

Abstract:

A new approach that transfers the multi-class imbalanced problem into simple two-class imbalanced problem was proposed, and a mended SMOTE over-sampling algorithm to enrich the P2P concept was applied. The experimental results show the approach can efficiently improve the P2P identifying rate using the Na?ve Bayes model.

Key words: class imbalance, over-sampling, P2P traffic identification

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.

Yaguan Qian,Min Zhang. P2P Traffic Identification Based Over-Sampling Technique[J]. Telecommunications Science, 2014, 30(4): 109-113.

图/表 7

图1

表1

表2

图2

图3

图4

图5

参考文献 17

1	Mochalski K , Schulze H . Ipoque internet study 2008/2009. , http://www.ipoque.com/resources/internet-studies/internet-study-2008_2009, 2009
2	MacManus R . Trend watch: P2P traffic much bigger than Web traffic. , http://www.readwriteweb.com/archives/p2p_growth_ trend_watch.php, 2006
3	Sun X , Torres R , Rao S . Preventing DDoS attacks on internet servers exploiting P2P systems. Computer Networks, 2010,54(15): 2756～2774
4	Dainotti A , Pescapè A , Claffy K C . Issues and future directions in traffic classification. Network, IEEE, 2012,26(1): 35～40
5	Gong S F , Chen J . A P2P traffic detection method based on support vector machine. Applied Mechanics and Materials, 2012,198: 1280～1285
6	Erman J , Mahanti A , Arlitt M . Byte me: a case for byte accuracy in traffic classification. Proceedings of the 3rd Annual ACM Workshop on Mining Network Data, San Diego, California, USA, 2007: 35～38
7	Liu Q , Liu Z . A comparison of improving multi-class imbalance for internet traffic classification. Information Systems Frontiers, 2012(7): 1～13
8	Ling C , Li C . Data mining for direct marketing problems and solutions. Proceedings of the Fourth International Conference on Knowledge Discovery and Data Mining（KDD-98）, New York, NY, 1998
9	Chawla N V , Bowyer K W , Hall L O , et al. SMOTE: synthetic minority over-sampling technique. Journal of Artificial Intelligence Research, 2002(16)
10	Wang R Y , Zhang L , Liu Z . Classifying imbalanced internet traffic based PCDD: a per concept drift detection method. Smart Computing Review, 2013(2)
11	Hall M A . Correlation-based Feature Selection for Machine Learning. The University of Waikato, The University of Waikato, 1999
12	Moore A W , Zuev D . Internet traffic classification using bayesian analysis techniques. ACM SIGMETRICS Performance Evaluation Review, 2013,33(1):50～60
13	Xu P , Lin S . Internet traffic classification using C4.5 decision tree. Journal of Software, 2009,20(10):2692～2704
14	Yuan R , Li Z , Guan X , et al. An SVM-based machine learning method for accurate internet traffic classification. Information Systems Frontiers, 2010, 12(2): 149～156
15	Sun R , Yang B , Peng L , et al. Traffic classification using probabilistic neural networks. Proceedings of Natural Computation （ICNC）, 2010 Sixth International Conference on IEEE, Valencia, Spain, 2010
16	Moore A W . Dataset. http://www.cl.cam.ac.uk/research/srg/netos/nprobe/data/papers/ sigmetrics/
17	Yu L , Liu H . Feature selection for high-dimensional data: a fast correlation-based filter solution. Proceedings of the Twentieth International Conference on Machine Learning （ICML 2003）, Piscataway, NJ, USA, 2003

抽样	P2P	non-P2P
第1次	339/1.36%	24 524/98.94%
第2次	678/2.69%	24 524/97.31%
第3次	1 356/5.24%	24 524/94.76%
第4次	2 712/9.96%	24 524/90.04%
第5次	5 424/18.11%	24 524/81.89%
第6次	10 848/30.67%	24 524/69.33%

抽样	P2P	non-P2P
第1次	18 632/5.72%	306 906/94.28%
第2次	37 264/10.83%	306 906/89.17%
第3次	55 892/15.41%	306 906/84.59%
第4次	74 528/19.54%	306 906/80.46%
第5次	93 160/23.29%	306 906/76.71%
第6次	111 792/26.70%	306 906/73.30%

[1]	徐雅斌,李艳平,刘曦子. 一个基于云计算的P2P流量识别系统模型的研究[J]. 电信科学, 2012, 28(10): 58-63.
[2]	陆慧娟,张金伟,马小平,杨小兵. 基于特征选择的过抽样算法的研究[J]. 电信科学, 2012, 28(1): 87-91.
[3]	陆慧娟,张金伟,张金伟,张金伟,马小平,杨小兵. 基于特征选择的过抽样算法的研究[J]. 电信科学, 2012, 28(1): 91-95.

基于过抽样技术的P2P流量识别方法

P2P Traffic Identification Based Over-Sampling Technique

在线阅读

PDF下载

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 7

参考文献 17

相关文章 3

Metrics

推荐阅读 0