About | Contact Us | Register | Login
ProceedingsSeriesJournalsSearchEAI
e-Infrastructure and e-Services for Developing Countries. 13th EAI International Conference, AFRICOMM 2021, Zanzibar, Tanzania, December 1-3, 2021, Proceedings

Research Article

Community Network Traffic Classification Using Two-Dimensional Convolutional Neural Networks

Download(Requires a free EAI acccount)
2 downloads
Cite
BibTeX Plain Text
  • @INPROCEEDINGS{10.1007/978-3-031-06374-9_9,
        author={Shane Weisz and Josiah Chavula},
        title={Community Network Traffic Classification Using Two-Dimensional Convolutional Neural Networks},
        proceedings={e-Infrastructure and e-Services for Developing Countries. 13th EAI International Conference, AFRICOMM 2021, Zanzibar, Tanzania, December 1-3, 2021, Proceedings},
        proceedings_a={AFRICOMM},
        year={2022},
        month={5},
        keywords={Network traffic classification Convolutional neural networks Deep learning Community networks},
        doi={10.1007/978-3-031-06374-9_9}
    }
    
  • Shane Weisz
    Josiah Chavula
    Year: 2022
    Community Network Traffic Classification Using Two-Dimensional Convolutional Neural Networks
    AFRICOMM
    Springer
    DOI: 10.1007/978-3-031-06374-9_9
Shane Weisz1,*, Josiah Chavula1
  • 1: Computer Science Department
*Contact email: wszsha001@myuct.ac.za

Abstract

Network traffic classification plays an important role in quality of service engineering. In recent years, it has become apparent that deep learning techniques are effective for this classification task, especially since classical approaches struggle to deal with encrypted traffic. However, deep learning models often tend to be computationally expensive, which weakens their suitability in low-resource community networks. This paper explores the computational efficiency and accuracy of two-dimensional convolutional neural networks (2D-CNNs) deep learning models for packet-based classification of traffic in a community network. We find that 2D-CNNs models attain higher out-of-sample accuracy than traditional support vector machines classifiers and the simpler multi-layer perceptron neural networks, given the same computational resource constraints. The improvement in accuracy offered by the 2D-CNNs has a tradeoff of slower prediction speed, which weakens their relative suitability for use in real-time applications. However, we observe that by reducing the size of the input supplied to the 2D-CNNs, we can improve their prediction speed whilst maintaining higher accuracy than other simpler models.

Keywords
Network traffic classification Convolutional neural networks Deep learning Community networks
Published
2022-05-26
Appears in
SpringerLink
http://dx.doi.org/10.1007/978-3-031-06374-9_9
Copyright © 2021–2025 ICST
EBSCOProQuestDBLPDOAJPortico
EAI Logo

About EAI

  • Who We Are
  • Leadership
  • Research Areas
  • Partners
  • Media Center

Community

  • Membership
  • Conference
  • Recognition
  • Sponsor Us

Publish with EAI

  • Publishing
  • Journals
  • Proceedings
  • Books
  • EUDL