FISTA-Net: A Deep Unfolding Network for Scattering Center Extraction

Le résumé fourni par la source

Electromagnetic scattering center (SC) extraction and signal reconstruction are crucial in high-frequency computational electromagnetics. Traditional iterative optimization methods face limitations in accuracy and efficiency. To address this, we propose FISTA-Net, a deep unfolding network based on fast iterative shrinkage-thresholding algorithm (FISTA). By integrating the mathematical interpretability of optimization methods with the expressive power of deep learning, FISTA-Net efficiently extracts SCs and achieves high-quality signal reconstruction. Experimental results on measured data validate its effectiveness.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.