INTERNET TRAFFIC ZONE IDENTIFICATION BY BACKPROPAGATION AND PROBABILISTIC NEURAL NETWORKS
DOI:
https://doi.org/10.17770/etr2023vol2.7265Keywords:
accuracy, backpropagation, probabilistic, traffic identificationAbstract
The article proposes an approach based on the concept of Artificial Intelligence for the categorization of urban areas of Internet content by corporate customers. The applicability of different neural apparatus was analyzed as well as three-layer Backpropagation Neural Networks (BPN) and four-layer Probabilistic Neural Networks (PNN) as the most suitable for the purpose of the study were selected. The synthesis of BPN architectures for Internet traffic identification was carried out according to a different number of computing units in the hidden layers with hyperbolic tangent sigmoid, log-sigmoid and linear transfer functions. The variations of a set of specific criteria were examined as Accuracy, Mean-Squared Error, Mean Absolute Error, Correlation coefficients, etc. The selection of PNNs against the defined quality indicators was based on a stepwise increase of the spread indicator of the Kernel functions in a Radial-Basis (RB) structural layer by analogy similar to that applied to BPNs. In the research processes, high levels of neural recognition indicators were established in processing with the Incoming flows of Internet Packages in an Accuracy of over 90.00%.
Downloads
References
D. Petrova, Analysis of SMEs in Bulgaria – Assessment of their innovation activities: International Scientific and Practical Conference, July 20-22, 2013, Rezekne, Latvia.
D. Petrova, Innovativeand sustainable industry in Bulgaria – prospects and challenges: International Scientific and Practical Conference „Environment, Technology and Resources“, June 20-22, 2019, Rezekne, Latvia.
M. L. Martin, B. Carro, A. Esguevillas, and J. Lloret, "Network traffic classifier with convolutional and recurrent neural networks for internet of things," IEEE Access, vol. 5, pp. 18042-18050, Sep. 2017.
G. Freine, "Deep learning for the analysis of network traffic measurements," M.S. thesis, Universidad de la Republica, Montevideo, ON, Uruguay, 2019.
G. Mihaylov, T. Iliev, I. stoyanov, and E. Ivanova, An approach for point-to-point link within mobile network coverage: International Scientific Conference on Communications, Information, Electronic and Energy Systems,November 25-27, 2022, Ruse, Bulgaria.
W. Aitken and D. Brown, "Application traffic classification using neural networks," Defence Research and Development Canada, Canada, Tech. Rep. DRDC-RDDC-2022-R052, 2022.
X. Hu, Ch. Gu, and F. Wei, " A Network Combining CNN and LSTM for Internet Encrypted Traffic Classification," Hindawi, Security and Communication Networks, vol. 2021, pp. 1-15, June 2021.
M. B. Umair, Z. Iqbal, M. Bilal, J. Nebhen, T. Almohamed, and R. Mehmood, "An Efficient Internet Traffic Classification System Using Deep Learning for IoT," Computers, Materials & Continua, vol. 71, pp. 407-422, Nov. 2022.
Sh. Rezaei and X. Iu, "Deep Learning for Encrypted Traffic Classification: An Overview," IEEE Communications Magazine, vol. 57, pp. 76-81, May 2019.
P. Michael, E. Valla, and N. Neggatu, " Network traffic classification via neural networks," University of Cambridge, United Kingdom, Tech. Rep. UCAM-CL-TR-912, Sep. 2017.
