基于互信息选择聚类集成的网络流量分类方法

doi:10.3724/SP.J.1087.2013.00080

计算机应用 ›› 2013, Vol. 33 ›› Issue (01): 80-82.DOI: 10.3724/SP.J.1087.2013.00080

基于互信息选择聚类集成的网络流量分类方法

丁要军¹,²,蔡皖东¹

1. 西北工业大学计算机学院，西安 710129
2. 咸阳师范学院信息工程学院, 陕西咸阳 712000

收稿日期:2012-08-01 修回日期:2012-08-28 出版日期:2013-01-01 发布日期:2013-01-09
通讯作者: 丁要军
作者简介:丁要军(1980-),男,河南许昌人,讲师,博士研究生，主要研究方向：网络与信息安全；蔡皖东(1955-),男,陕西西安人,教授,博士生导师,主要研究方向：网络安全、信息对抗。
基金资助:
国家863计划项目(2009AA01Z424);陕西省教育厅专项(12JK0933)

Internet traffic classification method based on selective clustering ensemble of mutual information

DING Yaojun¹,²,CAI Wandong¹

1. School of Computer Science, Northwestern Polytechnical University, Xi'an Shaanxi 710129, China
2. School of Information Engineering, Xianyang Normal University, Xianyang Shaanxi 712000, China

Received:2012-08-01 Revised:2012-08-28 Online:2013-01-01 Published:2013-01-09
Contact: DING Yaojun

摘要/Abstract

摘要： 针对互联网流量标注困难以及单个聚类器的泛化能力较弱，提出一种基于互信息(MI)理论的选择聚类集成方法，以提高流量分类的精度。首先计算不同初始簇个数K的K均值聚类结果与训练集中流量协议的真实分布之间的规范化互信息(NMI)；然后基于NMI的值来选择用于聚类集成的K均值基聚类器的K值序列；最后采用二次互信息(QMI)的一致函数生成一致聚类结果,并使用一种半监督方法对聚类簇进行标注。通过实验比较了聚类集成方法与单个聚类算法在4个不同测试集上总体分类精度。实验结果表明，聚类集成方法的流量分类总体精度能达到90%。所提方法将聚类集成模型应用到网络流量分类中，提高了流量分类的精度和在不同数据集上的分类稳定性。

关键词: 聚类集成, K均值, 流量分类, 互信息

Abstract: Because it is difficult to label Internet traffic and the generalization ability of single clustering algorithm is weak, a selective clustering ensemble method based on Mutual Information (MI) was proposed to improve the accuracy of traffic classification. In the method, the Normalized Mutual Information (NMI) between clustering results of K-means algorithm with different initial cluster number and the distribution of protocol labels of training set was computed first, and then a serial of K which were the initial cluster number of K-means algorithm based on NMI were selected. Finally, the consensus function based on Quadratic Mutual Information (QMI) was used to build the consensus partition, and the labels of clusters were labeled based on a semi-supervised method. The overall accuracies of clustering ensemble method and single clustering algorithm were compared over four testing sets, and the experimental results show that the overall accuracy of clustering ensemble method can achieve 90%. In the proposed method, a clustering ensemble model was used to classify Internet traffic, and the overall accuracy of traffic classification along with the stability of classification over different dataset got enhanced.

Key words: clustering ensemble, K-means, traffic classification, Mutual Information (MI)

中图分类号:

TP393.06

丁要军蔡皖东. 基于互信息选择聚类集成的网络流量分类方法[J]. 计算机应用, 2013, 33(01): 80-82.

DING Yaojun CAI Wandong. Internet traffic classification method based on selective clustering ensemble of mutual information[J]. Journal of Computer Applications, 2013, 33(01): 80-82.

参考文献

［1］MOORE A W, ZUEV D. Internet traffic classification using Bayesian analysis techniques ［C］// Proceedings of the 2005 ACM SIGMETRICS Conference on Measurement and Modeling of Computer Systems. New York: ACM Press, 2005: 50-60.

［2］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.

［3］胡婷,王勇,陶晓玲.混合模式的网络流量分类方法［J］.计算机应用,2010,30(10):2653-2655.

［4］BERNAILLE L, TEIXEIRA R, SALAMATIAN K. Early application identification ［C］// Proceedings of the 2006 ACM Conference on Emerging Networking Experiments and Technologies. New York: ACM Press, 2006: 70-82.

［5］ERMAN J, ARLITT M, MAHANTI A. Traffic classification using clustering algorithms ［C］// Proceedings of the 2006 SIGCOMM Workshop on Mining Network Data. New York: ACM Press, 2006: 281-286.

［6］刘琼,刘珍,黄敏.基于机器学习的IP流量分类研究［J］.计算机科学,2010,37(12):35-40.

［7］STREHL A, GHOSH J. Cluster ensembles-a knowledge reuse framework for combining multiple partitions ［J］. Journal of Machine Learning Research, 2003, 3(3): 583-617.

［8］TOPCHY A, JAIN A K, PUNCH W. Clustering ensembles: models of consensus and weak partitions ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(12): 1866-1881.

［9］唐伟,周志华.基于Bagging的选择性聚类集成［J］.软件学报,2005,16(4):496-502.

［10］罗会兰.聚类集成关键技术研究［D］.杭州:浙江大学,2007.

［11］ERMAN J, MAHANTI A, ARLITT M. Semi-supervised network traffic classification ［C］// Proceedings of the 2007 ACM SIGMETRICS Conference on Measurement and Modeling of Computer Systems. New York: ACM Press, 2007: 369-370.

［12］LI W, CANINI M, MOORE A W, et al. Efficient application identification and the temporal and spatial stability of classification schema ［J］. Computer Networks, 2009, 53(6): 790-809.

[1]	郭帅, 苏旸. 基于数据流的加密流量分类方法[J]. 计算机应用, 2021, 41(5): 1386-1391.
[2]	刘丹, 姚立霜, 王云锋, 裴作飞. 面向类不平衡流量数据的分类模型[J]. 计算机应用, 2020, 40(8): 2327-2333.
[3]	沈亮, 王鑫, 陈曙晖. 面向移动应用识别的结构化特征提取方法[J]. 计算机应用, 2020, 40(4): 1109-1114.
[4]	程玉胜, 宋帆, 王一宾, 钱坤. 基于专家特征的条件互信息多标记特征选择算法[J]. 计算机应用, 2020, 40(2): 503-509.
[5]	雍菊亚, 周忠眉. 基于互信息的多级特征选择算法[J]. 计算机应用, 2020, 40(12): 3478-3484.
[6]	王煜, 徐建民. 用于网络新闻热点识别的热点新词发现[J]. 计算机应用, 2020, 40(12): 3513-3519.
[7]	陈旖, 张美璟, 许发见. 基于一维卷积神经网络的HTTP慢速DoS攻击检测方法[J]. 计算机应用, 2020, 40(10): 2973-2979.
[8]	张晓博, 杨燕, 李天瑞, 陆凡, 彭莉兰. 基于医疗文本数据聚类的帕金森病早期诊断预测[J]. 计算机应用, 2020, 40(10): 3088-3094.
[9]	赵瑞祥, 侯宏花, 张鹏程, 刘祎, 田珠, 桂志国. 结合全卷积网络和K均值聚类的球栅阵列焊球边缘气泡分割[J]. 计算机应用, 2019, 39(9): 2580-2585.
[10]	李贺, 江登英, 黄樟灿, 王占占. 彩色图像颜色量化问题的求解方法[J]. 计算机应用, 2019, 39(9): 2646-2651.
[11]	魏嘉旺, 王肖, 袁玉波. 人脸特征点定位的自适应窗回归方法[J]. 计算机应用, 2019, 39(5): 1459-1465.
[12]	毛莺池, 曹海, 平萍, 李晓芳. 基于最大联合条件互信息的特征选择[J]. 计算机应用, 2019, 39(3): 734-741.
[13]	邹腾宽, 汪钰颖, 吴承荣. 网络背景流量的分类与识别研究综述[J]. 计算机应用, 2019, 39(3): 802-811.
[14]	丁成, 王秋萍, 王晓峰. 基于广义反向学习的磷虾群算法及其在数据聚类中的应用[J]. 计算机应用, 2019, 39(2): 336-342.
[15]	胡健, 苏永东, 黄文载, 肖鹏, 刘玉婷, 杨本富. 基于互信息加权集成迁移学习的入侵检测方法[J]. 计算机应用, 2019, 39(11): 3310-3315.

基于互信息选择聚类集成的网络流量分类方法

Internet traffic classification method based on selective clustering ensemble of mutual information

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics