aiqbench takeMachine Learning

This research proposes a hybrid framework combining hand-crafted micro-motion descriptors with deep learning to distinguish real maritime targets from corner-reflector-array jamming using frequency-agile radar. By fusing statistical features like mean weighted residual with CNN-derived embeddings and an XGBoost classifier, the method demonstrates superior robustness against non-rigid decoys in simulation environments. The work advances signal processing techniques critical for maintaining reliable sensing integrity in contested electromagnetic spectra where AI-driven discrimination is essential.

Source coveringarXiv

What this isA model's reading of the article and related coverage, written for aiqbench. Not the publisher's words.

Corner Reflector Array Jamming Discrimination Using Multi-Dimensional Micro-Motion Features with Frequency Agile Radar

arXivJuly 28, 20261 min read

arXiv:2604.16008v3 Announce Type: replace Abstract: This paper introduces a robust discrimination method for distinguishing real ship targets from corner-reflector-array jamming with frequency-agile radar. The key idea is to exploit the multidimensional micro-motion signatures that separate rigid ships from non-rigid decoys. From Range-Velocity maps we derive two new hand-crafted descriptors-mean weighted residual (MWR) and complementary contrast factor (CCF) and fuse them with deep features learned by a lightweight CNN. An XGBoost classifier then gives the final decision. Extensive simulations show that the hybrid feature set consistently outperforms state-of-the-art alternatives, confirming the superiority of the proposed approach.

Abstract:This paper introduces a robust discrimination method for distinguishing real ship targets from corner-reflector-array jamming with frequency-agile radar. The key idea is to exploit the multidimensional micro-motion signatures that separate rigid ships from non-rigid decoys. From Range-Velocity maps we derive two new hand-crafted descriptors-mean weighted residual (MWR) and complementary contrast factor (CCF) and fuse them with deep features learned by a lightweight CNN. An XGBoost classifier then gives the final decision. Extensive simulations show that the hybrid feature set consistently outperforms state-of-the-art alternatives, confirming the superiority of the proposed approach.

Machine Learning (cs.LG)

arXiv:2604.16008 [cs.LG]

(or arXiv:2604.16008v3 [cs.LG] for this version)

Full text under the publisher's open licence · 101 words

Read at arXiv ↗Ask about this article