Mobile Service Content Prediction Method through PDCCH Channel Learning 


Vol. 46,  No. 2, pp. 324-332, Feb.  2021
10.7840/kics.2021.46.2.324


PDF
  Abstract

Although various traffic classification techniques have been studied for each application, most of the technologies classify traffic by analyzing headers or payload signatures at the packet level. In this paper, we propose a method for classifying mobile service contents by learning only the physical downlink control channel (PDCCH) information of the physical layer. Since the proposed method uses only information of the physical layer, it can be applied to encrypted packets. For the experiment, PDCCH channel information was collected from the currently operating LTE (Long Term Evolution) base station, and mobile service content prediction was performed using random forest, SVM, AutoEncoder, deep neural network, and convolutional neural network as classification techniques. The prediction accuracy was observed up to 99%.

  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.


  Cite this article

[IEEE Style]

S. Moon, S. Kim, H. Shin, K. Cheon, H. Yoon, Y. Choi, "Mobile Service Content Prediction Method through PDCCH Channel Learning," The Journal of Korean Institute of Communications and Information Sciences, vol. 46, no. 2, pp. 324-332, 2021. DOI: 10.7840/kics.2021.46.2.324.

[ACM Style]

Sung-woo Moon, Sung-hyun Kim, Hong-gi Shin, Kyung-yul Cheon, Hyungoo Yoon, and Yong-Hoon Choi. 2021. Mobile Service Content Prediction Method through PDCCH Channel Learning. The Journal of Korean Institute of Communications and Information Sciences, 46, 2, (2021), 324-332. DOI: 10.7840/kics.2021.46.2.324.

[KICS Style]

Sung-woo Moon, Sung-hyun Kim, Hong-gi Shin, Kyung-yul Cheon, Hyungoo Yoon, Yong-Hoon Choi, "Mobile Service Content Prediction Method through PDCCH Channel Learning," The Journal of Korean Institute of Communications and Information Sciences, vol. 46, no. 2, pp. 324-332, 2. 2021. (https://doi.org/10.7840/kics.2021.46.2.324)

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880