ResNet/SVM-Based GNSS Jamming Classification Scheme 


Vol. 48,  No. 12, pp. 1589-1592, Dec.  2023
10.7840/kics.2023.48.12.1589


PDF
  Abstract

In this paper, we propose a jamming classification scheme that extracts the features of Global Navigation Satellite System (GNSS) simple jamming with Residual Neural Network (ResNet) which is one of the representative transfer learning methods, classifies it as one of the six jamming with Supported Vector Machine (SVM), and shows its performance via simulation. ResNet is classified according to the depth of the layer used, and in this paper, ResNet using 18, 50, and 101 layers was constructed, and the accuracy for extracting features using ResNet-18/50/101 and classifying them as SVMs are 96.33%, 97.25%, and 97.50%, respectively, indicating that the accuracy improves as the layer gets deeper.

  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]

S. Yoo, J. Yoo, S. Heo, S. Y. Kim, "ResNet/SVM-Based GNSS Jamming Classification Scheme," The Journal of Korean Institute of Communications and Information Sciences, vol. 48, no. 12, pp. 1589-1592, 2023. DOI: 10.7840/kics.2023.48.12.1589.

[ACM Style]

Seungsoo Yoo, Jaeduk Yoo, Soeun Heo, and Sun Yong Kim. 2023. ResNet/SVM-Based GNSS Jamming Classification Scheme. The Journal of Korean Institute of Communications and Information Sciences, 48, 12, (2023), 1589-1592. DOI: 10.7840/kics.2023.48.12.1589.

[KICS Style]

Seungsoo Yoo, Jaeduk Yoo, Soeun Heo, Sun Yong Kim, "ResNet/SVM-Based GNSS Jamming Classification Scheme," The Journal of Korean Institute of Communications and Information Sciences, vol. 48, no. 12, pp. 1589-1592, 12. 2023. (https://doi.org/10.7840/kics.2023.48.12.1589)
Vol. 48, 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