%0 Journal Article
%T A Learned-SVD Approach to the Electromagnetic Inverse Source Problem.
%A Capozzoli A
%A Catapano I
%A Cinotti E
%A Curcio C
%A Esposito G
%A Gennarelli G
%A Liseno A
%A Ludeno G
%A Soldovieri F
%J Sensors (Basel)
%V 24
%N 14
%D 2024 Jul 11
%M 39065893
%F 3.847
%R 10.3390/s24144496
%X We propose an artificial intelligence approach based on deep neural networks to tackle a canonical 2D scalar inverse source problem. The learned singular value decomposition (L-SVD) based on hybrid autoencoding is considered. We compare the reconstruction performance of L-SVD to the Truncated SVD (TSVD) regularized inversion, which is a canonical regularization scheme, to solve an ill-posed linear inverse problem. Numerical tests referring to far-field acquisitions show that L-SVD provides, with proper training on a well-organized dataset, superior performance in terms of reconstruction errors as compared to TSVD, allowing for the retrieval of faster spatial variations of the source. Indeed, L-SVD accommodates a priori information on the set of relevant unknown current distributions. Different from TSVD, which performs linear processing on a linear problem, L-SVD operates non-linearly on the data. A numerical analysis also underlines how the performance of the L-SVD degrades when the unknown source does not match the training dataset.