基于证据推理融合的网络数据流识别方法

doi:10.11772/j.issn.1001-9081.2014.08.2235

计算机应用 ›› 2014, Vol. 34 ›› Issue (8): 2235-2238.DOI: 10.11772/j.issn.1001-9081.2014.08.2235

基于证据推理融合的网络数据流识别方法

张剑¹,²,曹萍³,寿国础¹

1. 北京邮电大学通信测试技术研究中心，北京100876；
2. 上海工程技术大学航空运输学院，上海201620
3. 福州大学经济与管理学院，福州350116

收稿日期:2014-02-10 修回日期:2014-03-10 出版日期:2014-08-01 发布日期:2014-08-10
通讯作者: 张剑
作者简介:张剑(1974-),男,甘肃武威人,讲师,博士,主要研究方向：接入网流量识别与分类;曹萍(1971-),女,重庆江津人,副教授,博士,主要研究方向：智能决策算法;寿国础(1965-),男,浙江诸暨人,教授,博士,主要研究方向：智能光接入网安全。
基金资助:
国家863计划项目;国家社会科学基金资助项目;校科研基金资助项目

Identification method of network traffic flow based on evidence theory fusion

ZHANG Jian¹,²,CAO Ping³,SHOU Guochu¹

1. Comtest Research and Development Center, Beijing University of Posts and Telecommunications, Beijing 100876, China;
2. School of Air Transportation, Shanghai University of Engineering Science, Shanghai 201620, China;
3. School of Economics and Management, Fuzhou University, Fuzhou Fujian 350116, China

Received:2014-02-10 Revised:2014-03-10 Online:2014-08-01 Published:2014-08-10
Contact: ZHANG Jian

摘要/Abstract

摘要：

针对多分类器决策融合研究中利用有限的训练数据对分类器概率参数估计时存在较大偏差的问题，提出一种基于D-S证据推理(ER)的多分类器决策融合算法。利用不确定性描述分类器性能，并针对D-S组合规则在分类器结果高冲突情形下易出现决策融合悖论的问题，提出基于分类器信度加权融合算法实现流量识别决策融合。实验结果表明，多数投票法和Bayes最大后验概率法识别准确率分别为78.3%和81.7%，证据推理决策融合的识别准确率提高到82.2%~91.6%，而拒识率则保持在4.1%~6.2%。

Abstract:

In multi-classifier decision fusion, there is great warp when using limited training data to estimate the probability parameters of classifier. For dealing with this problem, a multi-classifier decision fusion method based on D-S (Dempster-Shafer) Evidential Reasoning (ER) was presented. The method utilized the advantages of D-S theory to describe uncertainty of classifiers. To solve the paradox problem in high conflict circumstance among multiple classifiers, a reliability weighted fusion algorithm was proposed to realize the traffic identification decision fusion. The experimental results show that the accuracy rate of majority voting and Bayes maximum posteriori probability are 78.3% and 81.7% respectively, while the proposed algorithm can improve the accuracy rate up to 82.2%-91.6%, and remain the reject rate between 4.1% and 6.2%.

中图分类号:

TP393.06

张剑曹萍寿国础. 基于证据推理融合的网络数据流识别方法[J]. 计算机应用, 2014, 34(8): 2235-2238.

ZHANG Jian CAO Ping SHOU Guochu. Identification method of network traffic flow based on evidence theory fusion[J]. Journal of Computer Applications, 2014, 34(8): 2235-2238.

参考文献

［1］ANTONELLO R, FERNANDES S, KAMIENSKI C, et al. Deep packet inspection tools and techniques in commodity platforms: challenges and trends ［J］. Journal of Network and Computer Applications, 2012, 35(6): 1863-1878.
［2］XU K, ZHANG M, YE M, et al. Identify P2P traffic by inspecting data transfer behavior ［J］. Computer Communications, 2010, 33(10): 1141-1150.
［3］DEWAELE G, HIMURA Y, BORGNAT P, et al. Unsupervised host behavior classification from connection patterns ［J］. International Journal of Network Management, 2010, 20(5): 317-337.
［4］ZHANG J, XIANG Y, ZHOU W, et al. Unsupervised traffic classification using flow statistical properties and IP packet payload ［J］. Journal of Computer and System Sciences, 2013, 79(1): 573-585.
［5］AULD T, MOORE A W, GULL S F. Bayesian neural networks for Internet traffic classification ［J］. IEEE Transactions on Neural Networks, 2007, 18(1): 223-239.
［6］GU C, ZHANG S. Network traffic classification based on improved support vector machine ［J］. Chinese Journal of Science Instrument, 2011, 32(7): 1507-1513.(顾成杰,张顺颐.基于改进SVM的网络流量分类方法研究［J］.仪器仪表学报,2011,32(7):1507-1513.)
［7］CALLADO A, KAMIENSKI C, SZABO G, et al. A survey on Internet traffic identification ［J］. IEEE Communications Survey and Tutorials, 2009, 11(3): 37-52.
［8］GUAN X, YI X, SUN X, et al. Efficient fusion approach for conflicting evidence ［J］. Journal of Tsinghua University: Science and Technology, 2009, 49(1): 138-141.(关欣,衣晓,孙晓明,等.有效处理冲突证据的融合方法［J］.清华大学学报:自然科学版,2009,49(1): 138-141.)
［9］KRISHNAPURAM B, HARTERNINK A J, CARIN L, et al. A Bayesian approach to joint feature selection and classifier design ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(9): 1105-1111.
［10］FISCH D, HOFMANN A, SICK B. On the versatility of radial basis function neural networks: a case study in the field of intrusion detection ［J］. Information Sciences, 2010, 180(12): 2421-2439.
［11］JIANG W, PENG J, DENG Y, New representation method of evidential conflict ［J］. Systems Engineering and Electronics, 2010, 32(3): 562-565.(蒋雯,彭进业,邓勇.一种新的证据冲突表示方法［J］.系统工程与电子技术,2010,32(3):562-565.)
［12］ZHANG J, QIAN Z, SHOU G, et al. Network traffic identification based on online clustering ［J］. Journal of Beijing University of Posts and Telecommunications, 2011, 34(3): 103-106.(张剑,钱宗珏,寿国础,等.在线聚类的网络流量识别［J］.北京邮电大学学报,2011,34(3):103-106.)

[1]	向雄, 田检. 基于软件定义网络的对等网传输调度优化[J]. 计算机应用, 2020, 40(3): 777-782.
[2]	陈禹, 毛莺池. 基于随机森林和遗传算法的Ceph参数自动调优[J]. 计算机应用, 2020, 40(2): 347-351.
[3]	向雄田检. 基于SDN的P2P传输调度优化研究[J]. 计算机应用, 0, (): 0-0.
[4]	唐俊勇, 田鹏辉, 王辉. 基于马尔可夫链与服务质量的网络可用性[J]. 计算机应用, 2018, 38(12): 3518-3523.
[5]	唐俊勇. 基于马尔科夫链与QoS的网络可用性研究[J]. 计算机应用, 0, (): 0-0.
[6]	范晓波, 李兴明. 基于线性松弛方法的网络故障链路诊断[J]. 计算机应用, 2018, 38(7): 2005-2008.
[7]	范晓波李兴明. 基于线性松弛方法的网络故障链路诊断[J]. 计算机应用, 0, (): 0-0.
[8]	孙美东刘勤让刘冬培燕昺昊. 面向非全互连3D NoC的自适应单播路由算法[J]. 计算机应用, 0, (): 0-0.
[9]	皮艾迪, 喻剑, 周笑波. 基于学习的容器环境Spark性能监控与分析[J]. 计算机应用, 2017, 37(12): 3586-3591.
[10]	夏羽, 廖苹秀, 崔雷. 数据中心中TCP连接建立过程的优化方法[J]. 计算机应用, 2017, 37(8): 2157-2162.
[11]	袁斌, 黎文伟. 个人云存储体验质量测量工具的设计与实现[J]. 计算机应用, 2016, 36(9): 2409-2415.
[12]	汤海建, 鲍宇, 闵玄, 罗煜璇, 邹宇驰. 无线传感器网络中载体的自主移动策略[J]. 计算机应用, 2016, 36(2): 478-482.
[13]	徐小琼, 周朝荣, 马小霞, 杨柳. 容迟网络中基于演化博弈的合作行为[J]. 计算机应用, 2016, 36(2): 483-487.
[14]	丁要军. 基于改进的旋转森林算法的不平衡网络流量分类方法[J]. 计算机应用, 2015, 35(12): 3348-3351.
[15]	田朔玮, 杨岳湘, 何杰, 王晓磊, 江志雄. 基于统计特征的隐匿P2P主机实时检测系统[J]. 计算机应用, 2015, 35(7): 1892-1896.

基于证据推理融合的网络数据流识别方法

Identification method of network traffic flow based on evidence theory fusion

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