Instancewise Feature Selection for UAV Classification Based on Radar Micro-Doppler Signatures
IEEE Sensors Journal · 15.07.2026 · 26 (14) · 21497-21507
DOI: 10.1109/jsen.2026.3700600 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Sensors Journal, erschienen am 15.07.2026. Verfasst von Guidong He und 3 weiteren Autor:innen. Die Arbeit nennt 42 Literaturangaben. Gefördert von: Aeronautical Science Foundation of China, Fundamental Research Funds for the Central Universities.
Abstract (Originalsprache)
Unmanned aerial vehicle (UAV) classification using radar micro-Doppler signatures remains challenging due to the diversity, variability, and heterogeneity of the observed features. Most existing feature selection methods adopt a global strategy, which overlooks sample-specific differences arising from diverse UAV categories, flight dynamics, and observation conditions. To address this limitation, we propose an instancewise feature selection framework based on the information bottleneck (IB) principle. The method jointly optimizes a differentiable feature selector and a classifier via variational inference and the Gumbel–Softmax reparameterization, enabling adaptive identification of discriminative features for each sample. Experimental evaluations on real radar data validate the effectiveness and interpretability of the proposed approach.
Förderung
- Aeronautical Science Foundation of China
- Fundamental Research Funds for the Central Universities
Zitieren
APA
He, G., Lei, P., Wang, J., & Zhu, J. (2026). Instancewise Feature Selection for UAV Classification Based on Radar Micro-Doppler Signatures. IEEE Sensors Journal, 26(14), 21497-21507. https://doi.org/10.1109/jsen.2026.3700600
Vancouver
He G, Lei P, Wang J, Zhu J. Instancewise Feature Selection for UAV Classification Based on Radar Micro-Doppler Signatures. IEEE Sensors Journal. 2026;26(14):21497-21507. doi:10.1109/jsen.2026.3700600
BibTeX
@article{He2026,
author = {He, Guidong and Lei, Peng and Wang, Jun and Zhu, Jiangyou},
title = {Instancewise Feature Selection for UAV Classification Based on Radar Micro-Doppler Signatures},
journal = {IEEE Sensors Journal},
year = {2026},
volume = {26},
number = {14},
pages = {21497--21507},
doi = {10.1109/jsen.2026.3700600}
}
EUVIMED