EUVIMEDEUVIMED entdecken
Crossref

A Multialignment Task-Adaptive Method for MFR Mode Recognition on Few-Shot Open-Set Learning

Qihang Zhai, Jiabin Liu, Zilin Zhang, Yan Li, Shafei Wang

IEEE Transactions on Aerospace and Electronic Systems · 2024-12 · 60 (6) · 7559-7574

DOI: 10.1109/taes.2024.3396416 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Aerospace and Electronic Systems, 2024-12. Verfasst von Qihang Zhai und 4 weiteren Autor:innen. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 65 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Multifunction radars can perform multiple missions simultaneously by optimizing transmission signals using programmable parameters, which is a great challenge for reconnaissance and identification. In particular, this recognition becomes more challenging when there is no prior information on radiation sources and when the available labeled signal data are insufficient. The received signal is also often a mixture of signals from targets, noise, unknown radiation sources, or unknown working modes. This article proposes a multialignment task-adaptive method to simultaneously complete the detection of unknown signals and the classification of target mode signals with limited samples. The proposed method utilizes generative model to map the observed signal sample and its semantic descriptions of the working mode to the same latent variables space through multialignment. Each working mode generates a prototype using a small number of projections in this space to support classification. This article additionally generates negative prototypes without unknown signal sample provided to meet the requirement of dynamic adjusting the detection boundary in different tasks for unknown samples. The proposed method shows the best experimental results compared with baselines, which achieves a 96.73% accuracy for five-categories providing one sample per class under few-shot open-set learning condition.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Zhai, Q., Liu, J., Zhang, Z., Li, Y., & Wang, S. (2024). A Multialignment Task-Adaptive Method for MFR Mode Recognition on Few-Shot Open-Set Learning. IEEE Transactions on Aerospace and Electronic Systems, 60(6), 7559-7574. https://doi.org/10.1109/taes.2024.3396416

Vancouver

Zhai Q, Liu J, Zhang Z, Li Y, Wang S. A Multialignment Task-Adaptive Method for MFR Mode Recognition on Few-Shot Open-Set Learning. IEEE Transactions on Aerospace and Electronic Systems. 2024;60(6):7559-7574. doi:10.1109/taes.2024.3396416

BibTeX
@article{Zhai2024,
  author = {Zhai, Qihang and Liu, Jiabin and Zhang, Zilin and Li, Yan and Wang, Shafei},
  title = {A Multialignment Task-Adaptive Method for MFR Mode Recognition on Few-Shot Open-Set Learning},
  journal = {IEEE Transactions on Aerospace and Electronic Systems},
  year = {2024},
  volume = {60},
  number = {6},
  pages = {7559--7574},
  doi = {10.1109/taes.2024.3396416}
}
Kostenlos starten →