File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Two-Step Enhanced Deep Learning Approach for Electromagnetic Inverse Scattering Problems

TitleTwo-Step Enhanced Deep Learning Approach for Electromagnetic Inverse Scattering Problems
Authors
KeywordsElectromagnetic interference
Deep learning
Mathematical model
Convolutional neural networks
Inverse problems
Issue Date2019
PublisherInstitute of Electrical and Electronics Engineers. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=7727
Citation
IEEE Antennas and Wireless Propagation Letters, 2019, v. 18 n. 11, p. 2254-2258 How to Cite?
AbstractIn this letter, a new deep learning (DL) approach is proposed to solve the electromagnetic inverse scattering (EMIS) problems. The conventional methods for solving inverse problems face various challenges including strong ill-conditions, high contrast, expensive computation cost, and unavoidable intrinsic nonlinearity. To overcome these issues, we propose a new two-step machine learning based approach. In the first step, a complex-valued deep convolutional neural network is employed to retrieve initial contrasts (permittivities) of dielectric scatterers from measured scattering data. In the second step, the previously obtained contrasts are input into a complex-valued deep residual convolutional neural network to refine the reconstruction of images. Consequently, the EMIS problem can be solved with much higher accuracy even for high-contrast objects. Numerical examples have demonstrated the capability of the newly proposed method with the improved accuracy. The proposed DL approach for EMIS problem serves a new path for realizing real-time quantitative microwave imaging for high-contrast objects.
Persistent Identifierhttp://hdl.handle.net/10722/278144
ISSN
2023 Impact Factor: 3.7
2023 SCImago Journal Rankings: 1.634
ISI Accession Number ID
Grants

 

DC FieldValueLanguage
dc.contributor.authorYAO, HM-
dc.contributor.authorSha, WEI-
dc.contributor.authorJiang, L-
dc.date.accessioned2019-10-04T08:08:21Z-
dc.date.available2019-10-04T08:08:21Z-
dc.date.issued2019-
dc.identifier.citationIEEE Antennas and Wireless Propagation Letters, 2019, v. 18 n. 11, p. 2254-2258-
dc.identifier.issn1536-1225-
dc.identifier.urihttp://hdl.handle.net/10722/278144-
dc.description.abstractIn this letter, a new deep learning (DL) approach is proposed to solve the electromagnetic inverse scattering (EMIS) problems. The conventional methods for solving inverse problems face various challenges including strong ill-conditions, high contrast, expensive computation cost, and unavoidable intrinsic nonlinearity. To overcome these issues, we propose a new two-step machine learning based approach. In the first step, a complex-valued deep convolutional neural network is employed to retrieve initial contrasts (permittivities) of dielectric scatterers from measured scattering data. In the second step, the previously obtained contrasts are input into a complex-valued deep residual convolutional neural network to refine the reconstruction of images. Consequently, the EMIS problem can be solved with much higher accuracy even for high-contrast objects. Numerical examples have demonstrated the capability of the newly proposed method with the improved accuracy. The proposed DL approach for EMIS problem serves a new path for realizing real-time quantitative microwave imaging for high-contrast objects.-
dc.languageeng-
dc.publisherInstitute of Electrical and Electronics Engineers. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=7727-
dc.relation.ispartofIEEE Antennas and Wireless Propagation Letters-
dc.rightsIEEE Antennas and Wireless Propagation Letters. Copyright © Institute of Electrical and Electronics Engineers.-
dc.rights©20xx IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.-
dc.subjectElectromagnetic interference-
dc.subjectDeep learning-
dc.subjectMathematical model-
dc.subjectConvolutional neural networks-
dc.subjectInverse problems-
dc.titleTwo-Step Enhanced Deep Learning Approach for Electromagnetic Inverse Scattering Problems-
dc.typeArticle-
dc.identifier.emailJiang, L: jianglj@hku.hk-
dc.identifier.authorityJiang, L=rp01338-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1109/LAWP.2019.2925578-
dc.identifier.scopuseid_2-s2.0-85075020062-
dc.identifier.hkuros306194-
dc.identifier.volume18-
dc.identifier.issue11-
dc.identifier.spage2254-
dc.identifier.epage2258-
dc.identifier.isiWOS:000498566200008-
dc.publisher.placeUnited States-
dc.relation.projectNOVEL COMPUTATIONAL ELECTROMAGNETIC METHODS FOR NONLINEAR PLASMONIC RESPONSES WITH ORBITAL ANGULAR MOMENTUM-
dc.identifier.issnl1536-1225-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats