In the last decades, the majority of the existing infrastructure heritage is approaching the end of its nominal design life mainly due to aging, deterioration, and degradation phenomena, threatening the safety levels of these strategic routes of communications. For civil engineers and researchers devoted to assessing and monitoring the structural health (SHM) of existing structures, the demand for innovative indirect non-destructive testing (NDT) methods aided with artificial intelligence (AI) is progressively spreading. In the present study, the authors analyzed the exertion of various deep learning models in order to increase the productivity of classifying ground penetrating radar (GPR) images for SHM purposes, especially focusing on road tunnel linings evaluations. Specifically, the authors presented a comparative study employing two convolutional models, i.e. the ResNet-50 and the EfficientNet-B0, and a recent transformer model, i.e. the Vision Transformer (ViT). Precisely, the authors evaluated the effects of training the models with or without pre-processed data through the bi-dimensional Fourier transform. Despite the theoretical advantages envisaged by adopting this kind of pre-processing technique on GPR images, the best classification performances have been still manifested by the classifiers trained without the Fourier pre-processing.

Comparative deep learning studies for indirect tunnel monitoring with and without Fourier pre-processing / Rosso, Marco Martino; Aloisio, Angelo; Randazzo, Vincenzo; Tanzi, Leonardo; Cirrincione, Giansalvo; Marano, Giuseppe Carlo. - In: INTEGRATED COMPUTER-AIDED ENGINEERING. - ISSN 1069-2509. - ELETTRONICO. - 31:2(2024), pp. 213-232. [10.3233/ICA-230709]

Comparative deep learning studies for indirect tunnel monitoring with and without Fourier pre-processing

Rosso, Marco Martino;Randazzo, Vincenzo;Tanzi, Leonardo;Marano, Giuseppe Carlo
2024

Abstract

In the last decades, the majority of the existing infrastructure heritage is approaching the end of its nominal design life mainly due to aging, deterioration, and degradation phenomena, threatening the safety levels of these strategic routes of communications. For civil engineers and researchers devoted to assessing and monitoring the structural health (SHM) of existing structures, the demand for innovative indirect non-destructive testing (NDT) methods aided with artificial intelligence (AI) is progressively spreading. In the present study, the authors analyzed the exertion of various deep learning models in order to increase the productivity of classifying ground penetrating radar (GPR) images for SHM purposes, especially focusing on road tunnel linings evaluations. Specifically, the authors presented a comparative study employing two convolutional models, i.e. the ResNet-50 and the EfficientNet-B0, and a recent transformer model, i.e. the Vision Transformer (ViT). Precisely, the authors evaluated the effects of training the models with or without pre-processed data through the bi-dimensional Fourier transform. Despite the theoretical advantages envisaged by adopting this kind of pre-processing technique on GPR images, the best classification performances have been still manifested by the classifiers trained without the Fourier pre-processing.
File in questo prodotto:
File Dimensione Formato  
Comparative_DL_tunnel_monitoring_with_without_Fourier_rev2.pdf

accesso aperto

Tipologia: 2. Post-print / Author's Accepted Manuscript
Licenza: PUBBLICO - Tutti i diritti riservati
Dimensione 5.83 MB
Formato Adobe PDF
5.83 MB Adobe PDF Visualizza/Apri
ica-31-ica230709.pdf

non disponibili

Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Non Pubblico - Accesso privato/ristretto
Dimensione 6.86 MB
Formato Adobe PDF
6.86 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11583/2984048