基于粒关系矩阵的流量在线分类

doi:10.12263/DZXB.20191174

电子学报 ›› 2021, Vol. 49 ›› Issue (1): 1-7.DOI: 10.12263/DZXB.20191174

• 学术论文 • 下一篇

基于粒关系矩阵的流量在线分类

汤萍萍^1,2, 董育宁¹

1. 南京邮电大学通信与信息工程学院, 江苏南京 210003;
2. 安徽师范大学物理与电子信息学院, 安徽芜湖 241000

收稿日期:2019-10-14 修回日期:2020-07-20 出版日期:2021-01-25
- 通讯作者:
- 董育宁
- 作者简介:
- 汤萍萍 女,1981年生于安徽芜湖.现为南京邮电大学通信与信息工程学院博士研究生,主要研究领域为多媒体数据通信、网络流分类传输、QoS保证技术等.E-mail:tpping@ahnu.edu.cn
- 基金资助:
- 国家自然科学基金 (No.61271233）; 安徽省高校自然科学研究基金 (No.KJ2019A0491）

Online Traffic Classification Based on Granular Relation Matrix

TANG Ping-ping^1,2, DONG Yu-ning¹

1. College of Telecommunications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, Jiangsu 210003, China;
2. College of Physics and Electronic Information, Anhui Normal University, Wuhu, Anhui 241000, China

Received:2019-10-14 Revised:2020-07-20 Online:2021-01-25 Published:2021-01-25

摘要/Abstract

摘要： 随着各种网络应用爆发式增长，流量的在线分类陷入困境之中.传统的基于包统计特征的机器学习方法适用于稳定的网络环境，当网络拥塞出现严重的时延和丢包时将产生较大误差.因而本文提出基于粒计算模型的分类方法.粒计算属于人工智能计算的分支，当数据缺失、信息不完全或是有噪数据仍拥有较高的分辨能力.为此本文将网络流量定义成粒子并构造粒子间关系，再建立粒关系矩阵.传统的包统计特征只是粒关系矩阵当观测角度达到最大时的特例，因此粒关系矩阵对流量特性的描述更为全面，以此进行分类也更为精准.最后实验数据证明了该方法的有效性和优越性.

关键词: 网络流量, 在线分类, 粒计算, 关系矩阵, 差异度

Abstract: Online traffic classification is getting into troubles when the network applications are exploding.The traditional machine learning methods based on statistical characteristics of packets work well in stable network environment,but not in congestion environment with serious delay and packet loss.Therefore,a novel classification method based on granular computing is proposed in this paper.Granular computing belongs to the field of artificial intelligence computing,which is usually used to process missing,incomplete or noisy data.So we first define granules for the traffic,then construct the relations between the granules,and finally establish the relation matrix.The traditional statistical characteristics are only the special case of the relation matrix when the scale is the largest.The granular relation matrix can describe the traffic more comprehensively and classify them more accurately.The experiment results show its validity and advantages when compared with other methods.

Key words: network traffic, online classification, granular computing, relation matrix, difference degree

中图分类号:

TN919

汤萍萍, 董育宁. 基于粒关系矩阵的流量在线分类[J]. 电子学报, 2021, 49(1): 1-7.

TANG Ping-ping, DONG Yu-ning. Online Traffic Classification Based on Granular Relation Matrix[J]. Acta Electronica Sinica, 2021, 49(1): 1-7.

参考文献

[1] 谭晓衡,谢朝臣,郭坦.基于区域感知贝叶斯决策的5G超密集异构网络联合垂直切换技术研究[J].电子学报,2018,46(3):582-588. TAN Xiao-heng,XIE Chao-chen,GUO Tan.Sensing Bayesian decision in ultra-dense HetNet for 5G[J].Acta Electronica Sinica,2018,46(3):582-588.(in Chinese)
[2] 黄建洋,兰巨龙,胡宇翔.一种基于分段路由的多路径流传输机制[J].电子学报,2018,46(6):211-218. HUANG Jian-yang,LAN Ju-long,HU Yu-xiang.A segment routing based multipath flow transmission mechanism[J].Acta Electronica Sinica,2018,46(6):211-218.(in Chinese)
[3] 申健,夏靖波,张晓燕,等.基于分治排序策略的流量二次特征选择[J].电子学报,2017,45(1):128-134. SHEN Jian,XIA Jing-bo,ZHANG Xiao-yan,et al.Secondary feature extraction of network traffic based on divide-conquer and ranking strategy[J].Acta Electronica Sinica,2017,45(1):128-134.(in Chinese)
[4] LI M,CHEN L H.Energy-efficient traffic regulation and scheduling for video streaming services over LTE-A networks[J].IEEE Transactions on Mobile Computing,2019,18(2):334-347.
[5] GARCIA J,KORHONEN T,ANDERSSON R,VASTLUND F.Towards video flow classification at a million encrypted flows per second[A].Proceedings of the International Conference on Advanced Information Networking & Applications[C].Cracow,Poland:IEEE,2018.358-365.
[6] GARCIA J,BRUNSTROM A.Clustering-based separation of media transfers in DPI-classified cellular video and VoIP traffic[A].Wireless Communications and Networking Conference[C].Barcelona,Spain:IEEE,2018.1-6.
[7] YUN X,WANG Y,ZHANG Y,ZHOU Y,et al.A semantics-aware approach to the automated network protocol identification[J].IEEE/ACM Transactions on Networking,2016,24(1):583-595.
[8] KORNYCKY J,ABDUL-HAMEED O,KONDOZ A,et al.Radio frequency traffic classification over WLAN[J].IEEE Transactions on Parallel and Distributed Systems,2017,25(1):56-68.
[9] YAO L,QIN S,ZHU H.Feature selection algorithm for hierarchical text classification using Kullback-Leibler divergence[A].International Conference on Cloud Computing & Big Data Analysis[C].Chengdu,China:IEEE,2017.28-33.
[10] ORCZYKT AND PORWIK P.Investigation of the impact of missing value imputation methods on the k-NN classification accuracy[A].Computational Collective Intelligence[M].Berlin:Springer International Publishing,2015.557-565.
[11] SUN G,LIANG L,CHEN T,et al.Network traffic classification based on transfer learning[J].Computers & Electrical Engineering,2018,25(3):177-193.
[12] CANOVAS A,JIMENEZ J M,ROMERO O,LLORET J,et al.Multimedia data flow traffic classification using intelligent models based on traffic patterns[J].IEEE Network,2018,32(6):100-107.
[13] SHIM K S,HAM J H,SIJA B D.Application traffic classification using payload size sequence signature[J].International Journal of Network Management,2017,27(5):e1981.
[14] GHOFRANI F,JAMSHIDI A,KESHAVARZ-HADDAD A,et al.Internet traffic classification using Hidden Naive Bayes model[A].International Conference on Electrical Engineering[C].Tehran,Iran:IEEE,2015.235-240.
[15] TEJERO-DE-PABLOS A,NAKASHIMA Y,SATO T.Summarization of user-generated sports video by using deep action recognition features[J].IEEE Transactions on Multimedia,2018,20(8):2000-2011.
[16] LI W,YU X.An online flow-level packet classification method on multi-core network processor[A].International Conference on Computational Intelligence and Security[C].Shenzhen,China:IEEE,2015.407-411.
[17] AMBUSAIDI M,HE X,NANDA P,et al.Building an intrusion detection system using a filter-based feature selection algorithm[J].IEEE Transactions on Computers,2016,65(10):2986-2998.
[18] FUJITA H,GAETA A,LOIA V,et al.Resilience analysis of critical infrastructures:a cognitive approach based on granular computing[J].IEEE Transactions on Cybernetics,2019,49(5):1835-1848.
[19] CHAKRABORTY D B AND PAL S K.Neighborhood granules and rough rule-base in tracking[J].Natural Computing,2016,15(3):359-370.
[20] BARAKAT C,THIRAN P,IANNACCONE G,et al.Modeling internet backbone traffic at the flow level[J].IEEE Transactions on Signal Processing Special Issue on Networking,2003,51(8):2111-2124.
[21] ZADEH L A.Toward a generalized theory of uncertainty (GTU)-an outline[J].Information Sciences,2005,172(16):1-2.
[22] MANDELBROT B B,WALLIS J R.Some long-run properties of geophysical records[J].Water Resources Research,2010,5(2):321-340.
[23] HERNANDEZ-CARRASCO I,GARCON V,SUDRE J,et al.Increasing the resolution of ocean pCO2 maps in the south eastern Atlantic Ocean merging multifractal satellite-derived ocean variables[J].IEEE Transactions on Geoscience & Remote Sensing,2018,56(11):2243-2249.
[24] DA K,YUN S,PARK H.SymNMF:Nonnegative low-rank approximation of a similarity matrix for graph clustering[J].Journal of Global Optimization,2015,62(3):1-30.
[25] OTSU N.A threshold selection method from gray-Level histogram[J].IEEE Transactions on Systems Man & Cybernetics B,1979,9(1):94-98.
[26] UNB ISCX VPN-nonVPN traffic dataset[OL].http://www.unb.ca/cic/research/datasets/vpn.html.
[2016] .
[27] HAO S,HU J,LIU S,et al.Improved SVM method for internet traffic classification based on feature weight learning[A].International Conference on Computer Applications and Information Sciences[C].Changshu,China:IEEE,2015.102-106.
[28] 汤萍萍,董育宁.小波域基于分段Hurst指数的视频流分类[J].电子与信息学报,2017,39(6):1298-1304. TANG Ping-ping,DONG Yu-ning.Classifying video fows based on segmented hurst exponent in wavelet domain[J].Journal of Electronics & Information Technology,2017,39(6):1298-1304.(in Chinese)

基于粒关系矩阵的流量在线分类

Online Traffic Classification Based on Granular Relation Matrix

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

[1]	智慧来, 张丽, 李金海. 旁观者视角下粒的多层次描述[J]. 电子学报, 2022, 50(11): 2568-2574.
[2]	张清华, 吕功勋, 陈玉洪, 谢秦. 基于字符型属性值更新的动态三支决策模型[J]. 电子学报, 2019, 47(2): 344-350.
[3]	邓大勇, 卢克文, 黄厚宽, 邓志轩. 概念的属性约简及异构数据概念漂移探测[J]. 电子学报, 2018, 46(5): 1234-1239.
[4]	符海东, 彭燊, 黄莉, 顾进广. HDVM:基于关系矩阵的关联数据压缩查询模型[J]. 电子学报, 2018, 46(3): 721-729.
[5]	米允龙, 李金海, 刘文奇, 林晶. MapReduce框架下的粒概念认知学习系统研究[J]. 电子学报, 2018, 46(2): 289-297.
[6]	孙野, 王加阳, 张思同. 代数商空间的同余结构研究[J]. 电子学报, 2017, 45(10): 2434-2438.
[7]	陈林书, 王加阳, 杨正华, 李力. 基于代数结构的商空间模型研究[J]. 电子学报, 2016, 44(4): 952-958.
[8]	王加阳, 杨正华. 两种结构的商空间模型比较研究[J]. 电子学报, 2013, 41(11): 2262-2269.
[9]	温祥西, 孟相如, 马志强, 张永春. 小时间尺度网络流量混沌性分析及趋势预测[J]. 电子学报, 2012, 40(8): 1609-1616.
[10]	陈强;蒋咏梅;陆军;匡纲要. 一种基于目标散射鉴别的POLSAR图像地物无监督分类新方法[J]. 电子学报, 2011, 39(3): 613-618.
[11]	李丹丹;张润彤;王传臣;肖东坡. 认知网络中基于蚁群算法的网络流量预测模型[J]. 电子学报, 2011, 39(10): 2245-2250.
[12]	张华川, 田杰, 许静. 自相似网络流量模拟的分布式系统的设计与实现[J]. 电子学报, 2009, 37(S1): 31-35,30.
[13]	魏进武, 汪斌强, 邬江兴. 多重分形网络流量的单队列输入排队性能研究[J]. 电子学报, 2006, 34(4): 658-663.
[14]	魏进武;邬江兴;陈庶樵. 网络流量的联合多重分形模型及特性分析[J]. 电子学报, 2004, 32(9): 1459-1463.
[15]	周永权;焦李成. 高属性维稀疏数据聚类回归逻辑神经网络模型及学习算法[J]. 电子学报, 2004, 32(8): 1342-1345.