EUVIMEDEUVIMED entdecken
Crossref

Meta Supervised Contrastive Learning for Few-Shot Open-Set Modulation Classification With Signal Constellation

Jikui Zhao, Huaxia Wang, Shengliang Peng, Yu-Dong Yao

IEEE Communications Letters · 2024-04 · 28 (4) · 837-841

DOI: 10.1109/lcomm.2024.3363630 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Communications Letters, 2024-04. Verfasst von Jikui Zhao und 3 weiteren Autor:innen. Die Arbeit wurde bisher 27-mal zitiert (Crossref) und nennt 13 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In this work, we introduce a method for few-shot open-set modulation classification utilizing signal constellation diagrams, based on a Meta Supervised Contrastive Learning (MSCL) algorithm. MSCL combines the strengths of supervised contrastive learning and meta-learning to effectively amplify inter-class distinctions and reinforce intra-class compactness. The experimental results demonstrate that MSCL exhibits superior performance in both few-shot and open-set Automatic Modulation Classification (AMC) recognition. Code available at: https://github.com/jikuizhao/MSCL

Zitieren

APA

Zhao, J., Wang, H., Peng, S., & Yao, Y. (2024). Meta Supervised Contrastive Learning for Few-Shot Open-Set Modulation Classification With Signal Constellation. IEEE Communications Letters, 28(4), 837-841. https://doi.org/10.1109/lcomm.2024.3363630

Vancouver

Zhao J, Wang H, Peng S, Yao Y. Meta Supervised Contrastive Learning for Few-Shot Open-Set Modulation Classification With Signal Constellation. IEEE Communications Letters. 2024;28(4):837-841. doi:10.1109/lcomm.2024.3363630

BibTeX
@article{Zhao2024,
  author = {Zhao, Jikui and Wang, Huaxia and Peng, Shengliang and Yao, Yu-Dong},
  title = {Meta Supervised Contrastive Learning for Few-Shot Open-Set Modulation Classification With Signal Constellation},
  journal = {IEEE Communications Letters},
  year = {2024},
  volume = {28},
  number = {4},
  pages = {837--841},
  doi = {10.1109/lcomm.2024.3363630}
}
Kostenlos starten →