EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Method for Few-Shot Modulation Recognition Based on Reinforcement Metric Meta-Learning

Fan Zhou, Xiao Han, Jinyang Ren, Wei Wang, Yang Wang, Peiying Zhang, Shaolin Liao

Computers · 22.08.2025 · 14 (9) · 346

DOI: 10.3390/computers14090346 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computers, online erschienen am 22.08.2025. Verfasst von Fan Zhou und 6 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Shenyang Science and Technology Program, Education Department of Liaoning Province, Central Government Leads Local Science and Technology Development Projects.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In response to the problem where neural network models fail to fully learn signal sample features due to an insufficient number of signal samples, leading to a decrease in the model’s ability to recognize signal modulation methods, a few-shot signal modulation mode recognition method based on reinforcement metric meta-learning (RMML) is proposed. This approach, grounded in meta-learning techniques, employs transfer learning to building a feature extraction network that effectively extracts the data features under few-shot conditions. Building on this, by integrating the measurement of features of similar samples and the differences between features of different classes of samples, the metric network’s target loss function is optimized, thereby improving the network’s ability to distinguish between features of different modulation methods. The experimental results demonstrate that this method exhibits a good performance in processing new class signals that have not been previously trained. Under the condition of 5-way 5-shot, when the signal-to-noise ratio (SNR) is 0 dB, this method can achieve an average recognition accuracy of 91.8%, which is 2.8% higher than that of the best-performing baseline method, whereas when the SNR is 18 dB, the model’s average recognition accuracy significantly improves to 98.5%.

Förderung

  • Shenyang Science and Technology Program
  • Education Department of Liaoning Province
  • Central Government Leads Local Science and Technology Development Projects
  • National Natural Science Foundation of China

Zitieren

APA

Zhou, F., Han, X., Ren, J., Wang, W., Wang, Y., Zhang, P., & Liao, S. (2025). A Method for Few-Shot Modulation Recognition Based on Reinforcement Metric Meta-Learning. Computers, 14(9), 346. https://doi.org/10.3390/computers14090346

Vancouver

Zhou F, Han X, Ren J, Wang W, Wang Y, Zhang P, et al. A Method for Few-Shot Modulation Recognition Based on Reinforcement Metric Meta-Learning. Computers. 2025;14(9):346. doi:10.3390/computers14090346

BibTeX
@article{Zhou2025,
  author = {Zhou, Fan and Han, Xiao and Ren, Jinyang and Wang, Wei and Wang, Yang and Zhang, Peiying and Liao, Shaolin},
  title = {A Method for Few-Shot Modulation Recognition Based on Reinforcement Metric Meta-Learning},
  journal = {Computers},
  year = {2025},
  volume = {14},
  number = {9},
  pages = {346},
  doi = {10.3390/computers14090346}
}
Kostenlos starten →