GPR radargrams analysis through machine learning approach. Issue 12 (13th August 2021)

• Record Type: Journal Article
• Authors: Ponti, F.; Barbuto, F.; Di Gregorio, P. P.; Frezza, F.; Mangini, F.; Parisi, R.; Simeoni, P.; Troiano, M.
• Is Part Of: Journal of electromagnetic waves and applications. Volume 35:Issue 12(2021)
• Page Start: 1678
• Page End: 1686
• Publication Date: 2021-08-13
• Subjects: GPR -- machine learning -- neural network -- classification; Electromagnetic waves -- Periodicals; Electromagnetic devices -- Periodicals; 621.3
• DOI: 10.1080/09205071.2021.1906329
• Languages: English
• ISSNs: 0920-5071

Abstract

Abstract : This work proposes a Machine Learning (ML) approach for the analysis and classification of Ground Penetrating Radar (GPR) given a limited number of B-scan images. Specifically, we consider both a custom Convolutional Neural Network (CNN) and a wellestablished Deep Learning (DL) architecture, DenseNet, that is opportunely scaled down to take into account the small dataset. 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. A prediction based on the mean-square error (MSE) is applied. 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 data set. Limitations of the considered approach are also discussed.