This study addresses a 2D scalar electromagnetic inverse source problem by using a deep neural network-based artificial intelligence technique. Specifically, the Learned Singular Value Decomposition (L-SVD) approach based on hybrid autoencoding is adopted. The main goal is to reproduce the singular value decomposition through neural networks and compare the reconstruction performance of L-SVD and truncated SVD (TSVD) in the case of noiseless data, which represents a reference benchmark. The results demonstrate that L-SVD outperforms TSVD in terms of spatial resolution.
An autoencoder solution for the electromagnetic inverse source problem / Cinotti, E.; Esposito, G.; Gennarelli, G.; Ludeno, G.; Catapano, I.; Capozzoli, A.; Curcio, C.; Liseno, A.; Soldovieri, F.. - 12621:Volume 12621(2023), pp. 1-5. (Intervento presentato al convegno Multimodal Sensing and Artificial Intelligence: Technologies and Applications III tenutosi a Munich, Germany nel Jun. 27-29, 2023) [10.1117/12.2675891].
An autoencoder solution for the electromagnetic inverse source problem
Cinotti E.;Capozzoli A.;Curcio C.;Liseno A.;
2023
Abstract
This study addresses a 2D scalar electromagnetic inverse source problem by using a deep neural network-based artificial intelligence technique. Specifically, the Learned Singular Value Decomposition (L-SVD) approach based on hybrid autoencoding is adopted. The main goal is to reproduce the singular value decomposition through neural networks and compare the reconstruction performance of L-SVD and truncated SVD (TSVD) in the case of noiseless data, which represents a reference benchmark. The results demonstrate that L-SVD outperforms TSVD in terms of spatial resolution.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
