Deep Learning-Based Traffic Classification Speed Improvement Through Sequential Data Processing 


Vol. 47,  No. 12, pp. 2103-2110, Dec.  2022
10.7840/kics.2022.47.12.2096


PDF
  Abstract

Due to the development of networks and the changed environment, various application programs are being developed and used. Accordingly, the amount of network traffic is also increasing, and application traffic classification is required for efficient network management. Application traffic classification focus on classification accuracy, and is needed to quickly process traffic classification in a network environment where large-capacity traffic. In this paper, we propose a method to improve the traffic classification speed based on deep learning by sequentially processing data, and define the threshold and reliability used in the proposed method. The appropriate threshold in the ensemble model was 0.7, which achieved a reliability of 99.78% and correctly classified 58.99% of the data. As a result of testing by applying the remaining data classified from the ensemble model to the deep learning model, the overall processing speed of the proposed method was 0.88 seconds faster than the result using only 1D CNN.

  Statistics
Cumulative Counts from November, 2022
Multiple requests among the same browser session are counted as one view. If you mouse over a chart, the values of data points will be shown.


  Related Articles
  Cite this article

[IEEE Style]

M. Lee, J. Park, U. Baek, J. Choi, C. Shin, M. Kim, "Deep Learning-Based Traffic Classification Speed Improvement Through Sequential Data Processing," The Journal of Korean Institute of Communications and Information Sciences, vol. 47, no. 12, pp. 2103-2110, 2022. DOI: 10.7840/kics.2022.47.12.2096.

[ACM Style]

Min-Seong Lee, Jee-Tae Park, Ui-Jun Baek, Jung-woo Choi, Chang-Yui Shin, and Myung-Sup Kim. 2022. Deep Learning-Based Traffic Classification Speed Improvement Through Sequential Data Processing. The Journal of Korean Institute of Communications and Information Sciences, 47, 12, (2022), 2103-2110. DOI: 10.7840/kics.2022.47.12.2096.

[KICS Style]

Min-Seong Lee, Jee-Tae Park, Ui-Jun Baek, Jung-woo Choi, Chang-Yui Shin, Myung-Sup Kim, "Deep Learning-Based Traffic Classification Speed Improvement Through Sequential Data Processing," The Journal of Korean Institute of Communications and Information Sciences, vol. 47, no. 12, pp. 2103-2110, 12. 2022. (https://doi.org/10.7840/kics.2022.47.12.2096)
Vol. 47, No. 12 Index

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880