Dottoressa di ricerca

ciclo: XXXV

relatore: prof. Raffaele Parisi
co-supervisore: prof. Fabrizio Frezza

Titolo della tesi: A Generalized learning approach to Deep Neural Networks

This thesis in the first part proposes a Machine Learning (ML) approach for the analysis and classi cation of Ground Penetrating Radar (GPR) given a limited number of B-scan images obtain with a dedicated simulation tool. Speci cally, both a custom Convolutional Neural Network (CNN) and a a well-established Deep Learning (DL) architecture, DenseNet, that is opportunely scaled-down to take into account the small dataset, are considered. Those networks are then employed to classify B-scan simulations from buried cylinders in order to retrieve the host media permittivity, the cylinder depth respect to surface, and cylinders radius. The main aim of the proposed work is to test the applicability of a scaled down version of DenseNet architecture to the analysis of B-scan images and compare the performance respect to a classical CNN. The architecture chosen has shown interesting results in retrieving information from a limited images data set. The second part of the thesis presents a Generalized Newton’s Method as a powerful approach to learning in Deep Neural Networks. This technique was compared to two popular approaches, namely the Stochastic Gradient Descent and the Adam algorithm, in two popular classification tasks. The performance of the proposed approach confirmed it as an attractive alternative to state-of-the-art first order solutions

Produzione scientifica

11573/1653177 - 2021 - GPR radargrams analysis through machine learning approach
Ponti, F.; Barbuto, F.; Di Gregorio, P. P.; Frezza, F.; Mangini, F.; Parisi, R.; Simeoni, P.; Troiano, M. - 01a Articolo in rivista
rivista: JOURNAL OF ELECTROMAGNETIC WAVES AND APPLICATIONS (VSP International Science Publishers:Godfried van Seystlaan 47, 3703 BR Zeist Netherlands:011 31 30 6925790, EMAIL:, INTERNET:, Fax: 011 31 30 6932081) pp. 1678-1686 - issn: 0920-5071 - wos: WOS:000639667900001 (2) - scopus: 2-s2.0-85104339134 (5)

11573/1443747 - 2020 - Machine learning for analysis of GPR images and electromagnetic diagnostics
Barbuto, F.; Di Gregorio, P. P.; Dinia, L.; Frezza, F.; Mangini, F.; Ponti, F.; Troiano, M.; Simeoni, P. - 04b Atto di convegno in volume
congresso: URSI GASS 2020 (Roma)
libro: Proc. URSI GASS 2020 - ()

11573/1683629 - 2020 - Ultrasound imaging, a stethoscope for body composition assessment
Ponti, F; De Cinque, A; Fazio, N; Napoli, A; Guglielmi, G; Bazzocchi, A - 01a Articolo in rivista
rivista: QUANTITATIVE IMAGING IN MEDICINE AND SURGERY (Hong Kong : AME Publishing Company) pp. 1699-1722 - issn: 2223-4292 - wos: WOS:000548923000009 (15) - scopus: 2-s2.0-85089920162 (23)

11573/1291306 - 2019 - Deep Learning for applications to Ground Penetrating Radar and electromagnetic diagnostic
Ponti, Francesca; Barbuto, F.; Di Gregorio, Pietro Paolo; Mangini, Fabio; Simeoni, Patrizio; Troiano, Maurizio; Frezza, Fabrizio - 04b Atto di convegno in volume
congresso: PIERS 2019 (Roma)
libro: PIERS - ()

11573/1412516 - 2019 - F. Ponti, F. Barbuto, P. P. Di Gregorio, F. Mangini, P. Simeoni, M. Troiano, F. Frezza, “Deep Learning for analysis of GPR images”, Radar and Remote Sensing Workshop (RRSW) 2019, Roma, 30-31 maggio 2019.
Ponti, Francesca; Barbuto, Francesco; Di Gregorio, Pietro Paolo; Mangini, Fabio; Simeoni, Patrizio; Troiano, Maurizio; Frezza, Fabrizio - 04f Poster
congresso: Radar and Remote Sensing Workshop (RRSW) (ROME; ITALY)
libro: Radar and Remote Sensing Workshop - ()

© Università degli Studi di Roma "La Sapienza" - Piazzale Aldo Moro 5, 00185 Roma