Design of Deep Learning Model for Automatic Modulation Classification in Cognitive Radio Network 


Vol. 45,  No. 8, pp. 1364-1372, Aug.  2020
10.7840/kics.2020.45.8.1364


PDF
  Abstract

In this paper, light weight deep learning-based light weight Convolutional Neural Network (CNN) model is proposed for automatic modulation classification in cognitive radio. To minimize the vanishing gradient problem he skip connection structure of ResNet is applied to the proposed model, and to reduce computation complexity the proposed model is designed as bottleneck architectures. To extract the features through the proposed model synchronization, normalization, and aggregation dealt with for the input signals, and for performance evaluation the proposed model is compared with the conventional networks, ResNet and VGG, about the accuracy and inference by using the dataset that has 24 modulation classes. According to the simulation result by Matlab analysis tool, the proposed model has better performance on the predicted accuracy than others, especially over than 10% at SNR 10 dB. The performance of inference time also has smaller time than others.

  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. Kim, C. Kim, S. Yoo, D. Kim, "Design of Deep Learning Model for Automatic Modulation Classification in Cognitive Radio Network," The Journal of Korean Institute of Communications and Information Sciences, vol. 45, no. 8, pp. 1364-1372, 2020. DOI: 10.7840/kics.2020.45.8.1364.

[ACM Style]

Seung-Hwan Kim, Chi-Yoon Kim, Sang-Ho Yoo, and Dong-Seong Kim. 2020. Design of Deep Learning Model for Automatic Modulation Classification in Cognitive Radio Network. The Journal of Korean Institute of Communications and Information Sciences, 45, 8, (2020), 1364-1372. DOI: 10.7840/kics.2020.45.8.1364.

[KICS Style]

Seung-Hwan Kim, Chi-Yoon Kim, Sang-Ho Yoo, Dong-Seong Kim, "Design of Deep Learning Model for Automatic Modulation Classification in Cognitive Radio Network," The Journal of Korean Institute of Communications and Information Sciences, vol. 45, no. 8, pp. 1364-1372, 8. 2020. (https://doi.org/10.7840/kics.2020.45.8.1364)

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880