A Review of Deep Learning Approaches for Inverse Scattering Problems (Invited Review)

Chen, Xudong; Wei, Zhun; Li, Maokun; Rocca, and Paolo

doi:10.2528/pier20030705

Cited by 203 publications

(102 citation statements)

References 34 publications

Supporting

Mentioning

102

Contrasting

Order By: Relevance

“…In 2020, a two-stage data-to-image deep learning workflow was presented for 2-D imaging in which the first stage converted microwave measurement data to a compressed form of the target image, and a second stage improved the image quality [28]. An enlightening review of the various options for applying deep learning to the electromagnetic inverse scattering problem can be found in [29].…”

Section: Introductionmentioning

confidence: 99%

A Machine Learning Workflow for Tumour Detection in Breasts Using 3D Microwave Imaging

et al. 2021

View full text Add to dashboard Cite

A two-stage workflow for detecting and monitoring tumors in the human breast with an inverse scattering-based technique is presented. Stage 1 involves a phaseless bulk-parameter inference neural network that recovers the geometry and permittivity of the breast fibroglandular region. The bulk parameters are used for calibration and as prior information for Stage 2, a full phase contrast source inversion of the measurement data, to detect regions of high relative complex-valued permittivity in the breast based on an assumed known overall tissue geometry. We demonstrate the ability of the workflow to recover the geometry and bulk permittivity of the different sized fibroglandular regions, and to detect and localize tumors of various sizes and locations within the breast model. Preliminary results show promise for a synthetically trained Stage 1 network to be applied to experimental data and provide quality prior information in practical imaging situations.

show abstract

Section: Introductionmentioning

confidence: 99%

A Machine Learning Workflow for Tumour Detection in Breasts Using 3D Microwave Imaging

et al. 2021

View full text Add to dashboard Cite

show abstract

“…In recent times, deep learning methods have been applied in diverse applications [10][11][12] with significant amount of success. This has inspired researchers to gravitate towards applying relevant deep learning approaches in PHM implementations [13,14].…”

Section: Introductionmentioning

confidence: 99%

A Bidirectional LSTM-Based Prognostication of Electrolytic Capacitor

Kulevome¹,

Wang²,

Wang³

2021

PIER C

View full text Add to dashboard Cite

Knowing the state-of-health (SOH) of equipment, device or component is very essential for the secure and dependable operation of a system. Electrolytic capacitors are undoubtedly one of the essential components of power supply modules used in aerial and underwater vehicles, and every equipment requires a conversion of voltage from one level to another. This has encouraged research into the components of the power supply used in such systems of which electrolytic capacitor is of interest in this study. In this paper, we explore a new approach to implementing prognostics and health management (PHM) for electrolytic capacitors and propose a method of estimating the SOH leading to the prediction of the remaining useful life (RUL). This is accomplished by using a bidirectional long short-term memory (BLSTM) network to capture the degradation trends. We demonstrate the power and leverage that this method brings to bear in encoding time-domain dependencies in accurately estimating the SOH bereft of state models as employed in traditional methods. We validate the proposed approach using capacitor data recorded at different electrical over-stress accelerated aging conditions. The proposed method surpasses other existing methods in RUL prediction as indicated by the error and relative accuracy.

show abstract

“…On the other hand, the ever-increasing available computing power is providing unvaluable tools for the practical implementation of the proposed solution techniques. In this rapidly-evolving situation, the recent introduction of novel methods based on artificial intelligence [21] and in particular deep learning approaches [22], [23] is opening new doors, overcoming several limitations of the traditional inversion techniques and lowering computational times [24]- [27].…”

Section: Introductionmentioning

confidence: 99%

Microwave Tomography With LSTM-Based Processing of the Scattered Field

Fedeli

2021

IEEE Open J. Antennas Propag.

View full text Add to dashboard Cite

The quantitative inspection of unknown targets or bodies by means of microwave tomography requires a proper modeling of the field scattered by the structures under test, which in turn depends on several factors related to the adopted antennas and measurement configuration. In this article, a multifrequency tomographic approach in nonconstant-exponent Lebesgue spaces is enhanced by a preliminary step that processes the measured scattered field with a neural network based on long short-term memory cells. In the considered cases, this approach allows dealing with measurements in three-dimensional settings obtained with non-ideal antennas and measurement points, while retaining a canonical two-dimensional formulation of the inverse problem. The adopted data-driven model is trained with a set of simulations of cylindrical targets performed with a finite-difference time domain method, considering a simplified bistatic measurement configuration as an initial case study. The inversion procedure is then validated with numerical simulations involving cylindrical and spherical structures.INDEX TERMS Microwave imaging, inverse scattering, long short-term memory.

show abstract

A Review of Deep Learning Approaches for Inverse Scattering Problems (Invited Review)

Cited by 203 publications

References 34 publications

A Machine Learning Workflow for Tumour Detection in Breasts Using 3D Microwave Imaging

A Machine Learning Workflow for Tumour Detection in Breasts Using 3D Microwave Imaging

A Bidirectional LSTM-Based Prognostication of Electrolytic Capacitor

Microwave Tomography With LSTM-Based Processing of the Scattered Field

Contact Info

Product

Resources

About