Machine Learning and Intelligent Communications. Third International Conference, MLICOM 2018, Hangzhou, China, July 6-8, 2018, Proceedings

Research Article

A Research of Network Applications Classification Based on Deep Learning

Download
125 downloads
  • @INPROCEEDINGS{10.1007/978-3-030-00557-3_2,
        author={Hong Shao and Liujun Tang and Ligang Dong and Long Chen and Xian Jiang and Weiming Wang},
        title={A Research of Network Applications Classification Based on Deep Learning},
        proceedings={Machine Learning and Intelligent Communications. Third International Conference, MLICOM 2018, Hangzhou, China, July 6-8, 2018, Proceedings},
        proceedings_a={MLICOM},
        year={2018},
        month={10},
        keywords={Deep learning Deep belief network Network applications classification},
        doi={10.1007/978-3-030-00557-3_2}
    }
    
  • Hong Shao
    Liujun Tang
    Ligang Dong
    Long Chen
    Xian Jiang
    Weiming Wang
    Year: 2018
    A Research of Network Applications Classification Based on Deep Learning
    MLICOM
    Springer
    DOI: 10.1007/978-3-030-00557-3_2
Hong Shao1,*, Liujun Tang1,*, Ligang Dong1,*, Long Chen1,*, Xian Jiang1,*, Weiming Wang1,*
  • 1: Zhejiang Gongshang University
*Contact email: 1564027103@qq.com, tlj2016@126.com, donglg@zjgsu.edu.cn, smllchuju@163.com, jiangxian@zjgsu.edu.cn, wmwang@zjgsu.edu.cn

Abstract

Nowadays, the huge traffic generated by a growing number of network applications occupies enormous network bandwidth and increases the burden of network management. The ability to identify and categorize network applications accurately is crucial for learning network traffic conditions, finding people’s online behavior and accelerating the development of the Internet. The prior traffic classification methods often have unstable recognition rate and high computational complexity, which affects the network traffic management and application categories monitoring. Therefore, this paper proposes a method of using the deep learning technology to classify network applications. First, we propose a network application classification model based on Deep Belief Network (DBN). Then we construct a DBN-based model suitable for network applications classification with the Tensorflow framework. Finally, the classification performances of this DBN-based model and the BP-based model are compared on the real data sets. The experimental results show that the applications classification model based on DBN has higher classification accuracy for P2P applications.