EUVIMEDEUVIMED entdecken
Crossref

LCO-BNN: A Lightweight Collaborative Optimization Binary Neural Network for Radar Jamming Recognition

Haixiao Wu, Tao Liu, Weijian Liu, Wenchong Xie, Tao Zhang

IEEE Transactions on Aerospace and Electronic Systems · 2026 · 62 · 5486-5500

DOI: 10.1109/taes.2026.3660940 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Aerospace and Electronic Systems, 2026. Verfasst von Haixiao Wu und 4 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 39 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Hubei Provincial Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Advancements in electronic technology have made the battlefield electromagnetic environment increasingly complex, posing challenges for radar systems in accurately detecting targets and countering jamming. Especially, lightweight platforms, such as unmanned aerial vehicles and individual soldier devices, have limited computational resources, and there is an urgent need for jamming recognition models with low power consumption and strong real-time performance. However, existing deep-learning-based methods suffer from high computational costs, large model sizes in the algorithms, and poor adaptability to composite jamming scenarios. To address these limitations, this article proposes a lightweight collaborative optimization binary neural network (LCO-BNN) for radar jamming recognition. First, the LCO-BNN integrates a two-stream input that combines cross-ambiguity function contours and range–Doppler spectrograms to extract complementary spatiotemporal features. Second, although binary neural networks with 1-bit weights and activations significantly reduce computational costs, their severe information degradation hinders deployment. To mitigate this, we propose two mechanisms: variance-aligned adaptive scaling (VAS) in forward propagation, which enables the binary weights to approximate the statistical distribution of the original weights and effectively preserve a greater amount of information, and gradient-adaptive coordination in backward propagation to guarantee stable gradient updates. Furthermore, the network employs binary depthwise separable convolutions and real-valued retention skip, which efficiently balance efficiency and accuracy while lowering computational complexity and information loss. Experimental results demonstrate that the proposed LCO-BNN achieves a recognition accuracy of 99.33% under mixed jamming-to-noise ratio conditions. Compared with other full-precision models such as 2-D convolutional neural network, it significantly reduces the number of parameters to 4.30 Mbit and computational 1.34 × ${{10}^{6}}$ floating point operations (FLOPs), minimizing resource overhead by orders of magnitude. Furthermore, it outperforms existing binary methods with an accuracy improvement of at least 5.92%, providing a robust and low-power solution for real-time jamming recognition in resource-limited battlefield scenarios.

Förderung

  • National Natural Science Foundation of China
  • Hubei Provincial Natural Science Foundation of China

Zitieren

APA

Wu, H., Liu, T., Liu, W., Xie, W., & Zhang, T. (2026). LCO-BNN: A Lightweight Collaborative Optimization Binary Neural Network for Radar Jamming Recognition. IEEE Transactions on Aerospace and Electronic Systems, 62, 5486-5500. https://doi.org/10.1109/taes.2026.3660940

Vancouver

Wu H, Liu T, Liu W, Xie W, Zhang T. LCO-BNN: A Lightweight Collaborative Optimization Binary Neural Network for Radar Jamming Recognition. IEEE Transactions on Aerospace and Electronic Systems. 2026;62:5486-5500. doi:10.1109/taes.2026.3660940

BibTeX
@article{Wu2026,
  author = {Wu, Haixiao and Liu, Tao and Liu, Weijian and Xie, Wenchong and Zhang, Tao},
  title = {LCO-BNN: A Lightweight Collaborative Optimization Binary Neural Network for Radar Jamming Recognition},
  journal = {IEEE Transactions on Aerospace and Electronic Systems},
  year = {2026},
  volume = {62},
  pages = {5486--5500},
  doi = {10.1109/taes.2026.3660940}
}
Kostenlos starten →