Channel Equalization Using Deep Neural Network in Underwater OFDM Communication 


Vol. 44,  No. 8, pp. 1450-1459, Aug.  2019
10.7840/kics.2019.44.8.1450


PDF Full-Text
  Abstract

In the underwater communication environment, since the propagation medium is water, multipath occurs due to the medium fluctuation, and the propagation speed changes due to the water temperature or the like, which makes it difficult to estimate the channel. In this paper, deep neural network based channel equalization technique is proposed when QPSK symbols are OFDM modulated and transmitted thorough the underwater channel environment. We modeled the underwater channel in the West Sea using the Bellhop Ray Tracing method. From the computer simulation, when 128 or 64 pilot symbols were allocated in a symbol block which consist of 256 symbols, the proposed scheme performed better than the conventional LS scheme. In a further experiment, the proposed scheme without any pilot symbols is still better than the LS scheme with 64 pilot symbols. As a result, we confirmed that the performance of the proposed deep neural network based channel equalization method is more robust and better than the existing LS scheme in underwater channel environment.

  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]

T. Song, Y. Kim, H. Ko, "Channel Equalization Using Deep Neural Network in Underwater OFDM Communication," The Journal of Korean Institute of Communications and Information Sciences, vol. 44, no. 8, pp. 1450-1459, 2019. DOI: 10.7840/kics.2019.44.8.1450.

[ACM Style]

Tae-Young Song, Yong-Kwan Kim, and Hak-Lim Ko. 2019. Channel Equalization Using Deep Neural Network in Underwater OFDM Communication. The Journal of Korean Institute of Communications and Information Sciences, 44, 8, (2019), 1450-1459. DOI: 10.7840/kics.2019.44.8.1450.

[KICS Style]

Tae-Young Song, Yong-Kwan Kim, Hak-Lim Ko, "Channel Equalization Using Deep Neural Network in Underwater OFDM Communication," The Journal of Korean Institute of Communications and Information Sciences, vol. 44, no. 8, pp. 1450-1459, 8. 2019. (https://doi.org/10.7840/kics.2019.44.8.1450)

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880