Feature-Based Automatic Modulation Classification Using Deep Learning in Cognitive Radio 


Vol. 43,  No. 6, pp. 930-944, Jun.  2018
10.7840/kics.2018.43.6.930


PDF Full-Text
  Abstract

The AMC (automatic modulation scheme classification) plays an important role in identifying the modulation scheme of the primary user signal in the cognitive radio environment. In this paper, we propose a method of extracting the spectral correlation function and other statistical features from the received signal and distinguishing the modulation technique of the signal through the deep learning using the extracted data. In the proposed method, CNN (Convolutional Neural Network), one of the deep learning algorithms, was used as a method of recognizing and classifying features extracted from signals and used for classifying analog and digital modulated signals. Simulation results show that the proposed method shows better performance than other modulation signal classification methods at low SNR.

  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]

I. Choi, S. Jang, S. Yoo, "Feature-Based Automatic Modulation Classification Using Deep Learning in Cognitive Radio," The Journal of Korean Institute of Communications and Information Sciences, vol. 43, no. 6, pp. 930-944, 2018. DOI: 10.7840/kics.2018.43.6.930.

[ACM Style]

Ik-Soo Choi, Sung-Jeen Jang, and Sang-Jo Yoo. 2018. Feature-Based Automatic Modulation Classification Using Deep Learning in Cognitive Radio. The Journal of Korean Institute of Communications and Information Sciences, 43, 6, (2018), 930-944. DOI: 10.7840/kics.2018.43.6.930.

[KICS Style]

Ik-Soo Choi, Sung-Jeen Jang, Sang-Jo Yoo, "Feature-Based Automatic Modulation Classification Using Deep Learning in Cognitive Radio," The Journal of Korean Institute of Communications and Information Sciences, vol. 43, no. 6, pp. 930-944, 6. 2018. (https://doi.org/10.7840/kics.2018.43.6.930)

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880