English

应用科学学报 >

2015 , Vol. 33 >Issue 2: 117 - 128

DOI: https://doi.org/10.3969/j.issn.0255-8297.2015.02.002

通信工程

无监督的视频业务特征分析与分类

展开
  • 南京邮电大学通信与信息工程学院，南京210003
董育宁，教授，博导，研究方向：多媒体通信与无线网络，E-mail: dongyn@njupt.edu.cn

收稿日期: 2014-07-17

  修回日期: 2014-12-16

  网络出版日期: 2014-12-16

基金资助

国家自然科学基金(No.61271233, No.60972038)；教育部博士点基金(No.20103223110001)资助

收起

Unsupervised Feature Analysis and Classification of Video Streams

Expand
  • College of Telecommunications & Information Engineering, Nanjing University of Posts and
    Telecommunications, Nanjing 210003, China

Received date: 2014-07-17

  Revised date: 2014-12-16

  Online published: 2014-12-16

Fold

摘要

基于机器学习的流统计特征识别的方法关键在于如何找到具有区分力度的业务流统
计特征. 为此，提出了一些能够较好地区分视频业务的QoS 相关的统计特征. 为了充分地发
挥多级聚类算法的优势，以灵活的特征选择策略标记不同层级的网络视频流，通过大量的真
实网络视频数据进行实验验证. 结果表明，该方法能比现有同类方法取得更高的分类准确率.

关键词： 视频流; 统计特征; QoS; 流分类; 多级聚类

本文引用格式

姚利涛， 董育宁 . 无监督的视频业务特征分析与分类[J]. 应用科学学报, 2015 , 33(2) : 117 -128 . DOI: 10.3969/j.issn.0255-8297.2015.02.002

Abstract

 For recognition of flow statistical features based on machine learning, the key is
to select distinguishable features of different traffic flows. This paper presents several QoSrelated
statistical features that can well discriminate video traffics. To make full use of the
advantages of hierarchical clustering algorithm, this paper uses a flexible feature selection
strategy to mark the network video streaming of different levels. Experiments are performed
on a large scale real network video data. The results show that the proposed method can
achieve significantly higher classification accuracy compared to existing methods.
Keywords: video streaming, statistical features, QoS, traffic classification, hierarchical
clustering

参考文献

[1] Cisco visual network index: forecast and methodology, 2012-2017. http://www.cisco.com/c/en/us/solutions/collateral/service-provider/ip-ngn-ip-next-generation-network/white_paper_c11-481360.html

[2] 胡婷，勇，等.网络流量分类方法的比较研究 [J]. 桂林电子科技大学学报，2010, 30(3): 216-219.

HU Ting, WANG Yong, TAO Xiao Ling. Comparisonresearch on the methods of networktraffic classification [J]. Journal of Guilin University of Electronic Technology, 2010, 30(3): 216-219.

[3] TAKESHITA K, KUROSAWA T, TSUJINO M, et al. Evaluation of HTTP video classification method using flow group information [C]∥Proceedings of 14th International Telecommunications Network Strategy and Planning Symposium, 2010: 1-6.

[4] 董育宁，王再见，等. 多媒体通信业务流识别与分类方法综述 [J]. 南京邮电大学学报：自然科学版，2013, 33(3):  35-44.

DONG Yu Ning, WANG Zai Jian, FANG Shu Guang, et al. Survey of methods for traffic identification and classification in multimedia communications [J]. Journal of Nanjing University of Posts and Telecommunications: Natural Sciences, 2013, 33(3): 35-44.

[5] YANG Ning, TANG Chang Jie, WANG Yue, et al. Mining hotspots from multiple text streams based on stream information distance [J]. Journalof Software, 2011, 22(8): 1761-1770．

[6] PARK B C, WON Y J, KIM M S. Towards automated application signature generation for traffic identification [C]//Proceedings of Network Operations and Management Symposium.2008:160-167.

[7] RAAHEMI B，ZHONG W，LIU J. Peer-to-Peer traffic identification by mining IP layer data stream using concept-adapting very fast decision tree［C]∥Proceedings of 20th IEEE Computer Society Washington,2008．

[8] LI W, MOORE A W. A machine learning approach for efficient traffic classification［C]∥Proceedings of 15th IEEE International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems.IEEE Computer Society，Washington, 2008: 310-317.

[9] NGUYEN T, ARMITAGE G. A survey of techniques for Internet traffic classification using machine learning [J]. IEEE Communication. Surveys Tuts. 2008, 4(10): 56-76.

[10] JABER Mohanad, CASELLA Roberto G, BARAKAT Chadi. Can we trust the inter-packet time for traffic classification? [C]//Proceedings of Communications Society (ICC). IEEE, 2011: 1-5.

[11] HAN Young Tae, SUN Wei Qiang, PARK Hong Shik. Service differentiation based on packet size and flow length in best-effort networks [C]//Information Networking, 2009: 1-3

[12] MUJTABA G, PARISH D J. Detection of applications within encrypted tunnels using packet size distributions [C]//Internet Technology and Secured Transactions, 2009. ICITST 2009: 1-6.

[13] BERNAILLE Laurent, TEIXEIRA Renata, AKODJENOU Ismael, SOULE Augustin, SALAMATIAN Kave. Traffic classification on the fly [C]//Proceedings of the ACM SIGCOMM Computer Communication Review, 2006: 23-26.

[14] DIVAKARANL Dinil Mon, MURTHY Hema A, GONSALVES Timothy A. Traffic modeling and classification using packet train length and packet train size [J]. ACM SIGCOMM Computer Communication Review, 2007, 3065(1): 1-12.

[15] DU Jiang, LONG Tao. P2P traffic identification research based on the SVM [C]//Wireless and Optical Communication Conference (WOCC), 2013 22nd: 683-686.

[16] LI W, CANII M,  MOORE A W, BOLLA R. Efficient application identification and the temporal and spatial stability of classification schema. Computer Networks, 2009, 53(6): 790-809.

[17] JAISWAL R C, LOKHANDE S D. Machine learning based internet traffic recognition with statistical approach [C]//India Conference (INDICON), 2013 Annual IEEE: 1-6.

[18] IBRAHIM H A H, MOHDNORS, AHMED A. Internet traffic classification algorithm based on hybrid classifiers to identify online games traffic [J]. Jurnal Teknologi, 2013, 64(3): 55-60.

[19] JEFFREY E, MARTIN A, ANIRBAN M. Traffic classification using clustering algorithms [C]//Proceedings of SIGCOMM 2006, New York, USA: 281-286.

[20] BERNAILLE L, TEIXEIRA R, AKODKENOU I, SOULE A, SALAMATIAN K. Traffic classification on the fly [J]. ACMSIGCOMM Computer Communication Review, 2006, 36(2): 23-26.

[21] LIU Duo, LUNG Chung Hong. P2P traffic identification and optimization using fuzzy c-means clustering [C]// India Conference (INDICON), 2013 Annual IEEE Fuzzy Systems (FUZZ), 2011 IEEE International Conference on 27-30 June 2011: 2245 - 2252.

[22] ZHIBIN Y, KIL G B, KIM S. Traffic classification based on visualization [C]//Networked Embedded Systems for Enterprise Applications (NESEA), 2011 IEEE 2nd International Conference on. IEEE, 2011: 1-6.

[23] ZHANG J, CHEN C, XIANG Y, et al. Classification of correlated Internet traffic flows [C]//Trust, Security and Privacy in Computing and Communications (TrustCom), 2012 IEEE 11th International Conference on. IEEE, 2012: 490-496.
Options
文章导航

/

〈 〉