一种基于残差网络的改进网络流量分类算法

陆煜斌; 宣涵; 王炎豪; 徐凯; 朱嘉豪; 沈建华

doi:10.13756/j.gtxyj.2021.01.001

您当前的位置：

首页 >

文章列表页 >

一种基于残差网络的改进网络流量分类算法

光通信系统与网络技术

- 一种基于残差网络的改进网络流量分类算法
- A Residual Network based Improved Network Traffic Classification Algorithm
- 光通信研究 2021年第1期页码：1-4,14
- 作者机构：
  
  南京邮电大学　通信与信息工程学院，南京　210003
- 作者简介：
  
  陆煜斌（1996-），男，江苏南通人。硕士，主要研究方向为光通信。
  沈建华，教授。E-mail：shenjh@njupt.edu.cn
- 基金信息：
- DOI：10.13756/j.gtxyj.2021.01.001
  中图分类号： TN915
- 纸质出版日期：2021-02-10，
  
  收稿日期：2020-07-13，
扫描看全文
陆煜斌, 宣涵, 王炎豪, 等. 一种基于残差网络的改进网络流量分类算法[J]. 光通信研究, 2021,(1):1-4,14.

LU Yu-bin, XUAN Han, WANG Yan-hao, et al. A Residual Network based Improved Network Traffic Classification Algorithm[J]. Study on Optical Communications, 2021,(1):1-4,14.
陆煜斌, 宣涵, 王炎豪, 等. 一种基于残差网络的改进网络流量分类算法[J]. 光通信研究, 2021,(1):1-4,14. DOI： 10.13756/j.gtxyj.2021.01.001.

LU Yu-bin, XUAN Han, WANG Yan-hao, et al. A Residual Network based Improved Network Traffic Classification Algorithm[J]. Study on Optical Communications, 2021,(1):1-4,14. DOI： 10.13756/j.gtxyj.2021.01.001.

摘要

基于卷积神经网络的网络流量分类算法中，为了提高分类准确度，其结构设计日趋复杂，容易出现梯度下滑甚至梯度消失，导致预测准确度不升反降。文章提出了一种基于残差网络的改进流量分类算法，引入残差网络层代替传统卷积神经网络中的卷积层和池化层，不仅缓解了传统卷积网络因层次太深导致难以训练的问题，同时与传统卷积运算相比，所提出的残差网络在训练时学习到的数据特征信息更加全面，训练后的模型也更加准确。仿真结果表明，改进后的算法比常规的神经网络算法表现更佳，分类准确度从92.05%提高到了96.18%。

Abstract

Convolutional neural network based network traffic classification scheme suffers many disadvantages such as the complex structure designing

gradient declines or even explodes

the deterioration of prediction accuracy

and etc. A residual network based improved traffic classification algorithm is proposed. The convolution layer and pooling layer in the traditional convolutional neural network are replaced by the residual network layer

which can alleviate the problem that the traditional convolution network is too deep to train effectively. The data feature information learned by the proposed algorithm in the training stage is more comprehensive

and the trained model can also be more accurate. Simulation results show that the improved algorithm has higher accuracy than the traditional neural network

which can be improved from 92.05%to 96.18%.

关键词

网络流量分类卷积神经网络残差网络

Keywords

network traffic classificationconvolutional neural networkresidual network

references

Cotton M, Eggert L, Touch J, et al. Internet Assigned Numbers Authority(IANA)Procedures for the Management of the Transport Protocol Port Number and Service Name Registry[J]. American Journal of Tropical Medicine & Hygiene, 2011, 85(5): 957-960.

Sherry J, Lan C, Popa R A, et al. Blind Box: Deep Packet Inspection over Encrypted Traffic[J]. Acm Sigcomm Computer Communication Review, 2015, 45(4): 213-226.

Finsterbusch M, Richter C, Rocha E, et al. A Survey of Payload-Based Traffic Classification Approaches[J]. IEEE Communications Surveys & Tutorials, 2014, 16(2): 1135-1156.

He H. A Network Traffic Classification Method Using Support Vector Machine with Feature Weighted-Degree[J]. Journal of Digital Information Management, 2017, 15(2): 76-83.

Nguyen T T T, Armitage G J. A Survey of Techniques for Internet Traffic Classification Using Machine Learning[J]. IEEE Communications Surveys & Tutorials, 2008, 10(3): 56-76.

Park B, Hong W K, Won Y J. Toward Fine-Grained Traffic Classification[J]. IEEE Communications Magazine, 2011, 49(7): 104-111.

Lecun Y, Bengio Y, Hinton G. Deep Learning[J]. Nature, 2015, 521(7553): 436-444.

Kabanga E K, Kim C H. Malware Images Classification Using Convolutional Neural Network[J]. Journal of Computer & Communications, 2018, 6(1): 153-158.

He K, Zhang X, Ren S, et al. Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2014, 37(9): 1904-1916.

Wang W, Zhu M, Wang J, et al. End-to-End Encrypted Traffic Classification with One-Dimensional Convolution Neural Networks[C]//IEEE International Conference on Intelligence and Security Informatics. Beijing, China: IEEE, 2017: 43-48.

Lotfollahi M, Zade R S H, Siavoshani M J, et al. Deep Packet: A Novel Approach for Encrypted Traffic Classification Using Deep Learning[J]. Soft Computing, 2020, 24(3): 1999-2012.

Bengio Y, Simard P, Frasconi P. Learning Long-Term Dependencies with Gradient Descent is Difficult[J]. IEEE Transactions on Neural Networks, 1994, 5(2): 157-166.

He K, Zhang X, Ren S, et al. Deep Residual Learning for Image Recognition[C]//IEEE Conference on Computer Vision & Pattern Recognition. Las Vegas, NV, USA: IEEE, 2016: 770-778.

Lecun Y, Bottou L. Gradient-Based Learning Applied to Document Recognition[J]. Proceedings of the IEEE, 1998, 86(11): 2278-2324.

Dainotti A, Pescape A, Claffy K C. Issues and Future Directions in Traffic Classification[J]. IEEE Network, 2012, 26(1): 35-40.

更多指标>

浏览量

176

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

暂无数据