Buried Object Characterization Using Ground Penetrating Radar Assisted by Data-Driven Surrogate-Models

Yurt, Reyhan; Torpi, Hamid; Mahoutı, Peyman; Kızılay, Ahmet; Koziel, Slawomir

doi:10.1109/access.2023.3243132

Cited by 9 publications

(8 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The results indicate that linear regression assisted hyperbolic signature approach with the proposed deep-learning-based M2LP framework features smaller error as compared to other cases including different data sets with the proposed framework and different method (A-scan analysis) with TFRM framework 49 . It can be observed that, in a qualitative sense, according to the presented results the proposed methodology is superior to the benchmark cases.…”

Section: Resultsmentioning

confidence: 87%

“…10 , for a sample test scenario the principal components as an image (in 2D data form), and a B-scan image pre-processed (clutter reduced) using PCA are demonstrated. In addition, the last benchmark case including a study of characterization of geophysical parameters with A-scan analysis 49 . The performance results of that study which is computationally efficient surrogate modeling via a novel deep learning-based framework that focuses on the object characterization in terms of its geophysical parameters with A-scan analysis 49 and by using raw data (without any background subtraction operations) are added.…”

Section: Methodsmentioning

confidence: 99%

“…In addition, the last benchmark case including a study of characterization of geophysical parameters with A-scan analysis 49 . The performance results of that study which is computationally efficient surrogate modeling via a novel deep learning-based framework that focuses on the object characterization in terms of its geophysical parameters with A-scan analysis 49 and by using raw data (without any background subtraction operations) are added. These benchmark cases only have approximate training and testing time durations, so this data is not considered in the comparative study.…”

Section: Methodsmentioning

confidence: 99%

See 2 more Smart Citations

Buried object characterization by data-driven surrogates and regression-enabled hyperbolic signature extraction

Yurt

Torpi

Kızılay

et al. 2023

Sci Rep

Self Cite

View full text Add to dashboard Cite

This work addresses artificial-intelligence-based buried object characterization using FDTD-based electromagnetic simulation toolbox of a Ground Penetrating Radar (GPR) to generate B-scan data. In data collection, FDTD-based simulation tool, gprMax is used. The task is to estimate geophysical parameters of a cylindrical shape object of various radii, buried at different positions in the dry soil medium simultaneously and independently of each other. The proposed methodology capitalizes on a fast and accurate data-driven surrogate model developed for object characterization in terms of its vertical and lateral position, and the size. The surrogate is constructed in a computationally efficient manner as compared to methodologies using 2D B-scan image. This is achieved by operating at the level of hyperbolic signatures extracted from the B-scan data through linear regression, which effectively reduces the dimensionality and the size of data. The proposed methodology relies on reducing of 2D B-scan image to 1D data including variation of reflected electric fields’ amplitudes with respect to the scanning aperture. The input of the surrogate model is the extracted hyperbolic signature obtained through linear regression executed on the background subtracted B-scan profiles. The hyperbolic signatures encode information about the geophysical parameters of the buried object, including depth, lateral position, and radius, all of which can be extracted using proposed methodology. Parametric estimation of the object radius and the estimation of the location parameters simultaneously is a challenging problem. Applying the application of processing steps on B-scan profiles incurs high computational costs, which is a limitation of the current methodologies. The metamodel itself is rendered using a novel deep-learning-based modified multilayer perceptron (M2LP) framework. The presented object characterization technique is favourably benchmarked against the state-of-the-art regression techniques, including Multilayer Perceptron (MLP), Support Vector Regression Machine (SVRM), and Convolutional Neural Network (CNN). The verification results demonstrate the average mean absolute error of 10 mm, and the average relative error of 8 percent, both corroborating the relevance of the proposed M2LP framework. In addition, the presented methodology provides a well-structured relation between the geophysical parameters of object and the extracted hyperbolic signatures. For the sake of supplementary verification under realistic scenarios, it is also applied for scenarios involving noisy data. The environmental and internal noise of the GPR system and their effect is analyzed as well. Furthermore, the proposed surrogate modeling approach is validated using measurement data, which is indicative of suitability of the approach to handle physical measurements as data sources.

show abstract

Section: Resultsmentioning

confidence: 87%

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Buried object characterization by data-driven surrogates and regression-enabled hyperbolic signature extraction

Yurt

Torpi

Kızılay

et al. 2023

Sci Rep

Self Cite

View full text Add to dashboard Cite

show abstract

“…This problem represents an interesting test bed since the targets are usually located very close to each other and thus the mutual interactions between them significantly affect the image quality. In the frame of GPR data processing, various machine/deep learning strategies have been recently proposed to characterize buried targets [53]- [55], retrieve permittivity maps [56], or perform de-cluttering of raw radargrams [57]- [60]. As for decluttering, the available DL strategies do not focus on target-target interactions.…”

Section: Introductionmentioning

confidence: 99%

A Deep Learning Strategy for Multipath Ghosts Filtering via Microwave Tomography

Esposito,

Catapano,

Ludeno

et al. 2024

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

Radar imaging algorithms generally exploit linear models of the electromagnetic scattering phenomenon. This assumption leads to qualitative and computationally effective data inversion schemes, which only account for direct scattering from targets, whereas multipath signal contributions are neglected. As a result, multipath ghosts, i.e. false targets reconstructed at positions where no real target exists, affect the radar images thus preventing a reliable interpretation of the observed scene. This paper proposes a fully data-driven deep learning approach based on a convolutional neural network and microwave tomography to face this challenge. The approach achieves multipath ghost suppression for the case of small targets in terms of probing wavelength. In the proposed training scheme, the tomographic image affected by ghosts represents the input of the network while a ghost-free reconstruction is the output. Numerical simulations addressing the detection of metallic rebars via ground penetrating radar are presented. As shown, the proposed ghost removal strategy is effective and robust to variations of the scenario parameters on which the network is trained. Finally, an experimental validation shows the effectiveness of the proposed strategy even in operative conditions.

show abstract

“…With the continuous development of big data technology and high-performance computing, machine learning and deep learning have been applied to many fields [16]. In addition to common fields such as image analysis and natural language processing [17], they have also been implemented in the field of electronic and electrical engineering [18][19][20]. Some researchers use machine learning and deep learning to solve the problem of parasitic parameter extraction.…”

Section: Introductionmentioning

confidence: 99%

Extraction of Interconnect Parasitic Capacitance Matrix Based on Deep Neural Network

Yan

et al. 2023

Electronics

View full text Add to dashboard Cite

Interconnect parasitic capacitance extraction is crucial in analyzing VLSI circuits’ delay and crosstalk. This paper uses the deep neural network (DNN) to predict the parasitic capacitance matrix of a two-dimensional pattern. To save the DNN training time, the neural network’s output includes only coupling capacitances in the matrix, and total capacitances are obtained by summing corresponding predicted coupling capacitances. In this way, we can obtain coupling and total capacitances simultaneously using a single neural network. Moreover, we introduce a mirror flip method to augment the datasets computed by the finite element method (FEM), which doubles the dataset size and reduces data preparation efforts. Then, we compare the prediction accuracy of DNN with another neural network ResNet. The result shows that DNN performs better in this case. Moreover, to verify our method’s efficiency, the total capacitances calculated from the trained DNN are compared with the network (named DNN-2) that takes the total capacitance as an extra output. The results show that the prediction accuracy of the two methods is very close, indicating that our method is reliable and can save the training workload for the total capacitance. Finally, a solving efficiency comparison shows that the average computation time of the trained DNN for one case is not more than 2% of that of FEM.

show abstract

Buried Object Characterization Using Ground Penetrating Radar Assisted by Data-Driven Surrogate-Models

Cited by 9 publications

References 44 publications

Buried object characterization by data-driven surrogates and regression-enabled hyperbolic signature extraction

Buried object characterization by data-driven surrogates and regression-enabled hyperbolic signature extraction

A Deep Learning Strategy for Multipath Ghosts Filtering via Microwave Tomography

Extraction of Interconnect Parasitic Capacitance Matrix Based on Deep Neural Network

Contact Info

Product

Resources

About