File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: APPLYING CONVOLUTIONAL NEURAL NETWORKS FOR THE SOURCE RECONSTRUCTION

TitleAPPLYING CONVOLUTIONAL NEURAL NETWORKS FOR THE SOURCE RECONSTRUCTION
Authors
KeywordsConvolution
Learning systems
Neural networks
Convolutional neural network
Direction of arrivalestimation(DOA)
Issue Date2018
PublisherEMW Publishing. The Journal's web site is located at http://www.jpier.org/PIERM/
Citation
Progress in Electromagnetics Research M, 2018, v. 76, p. 91-99 How to Cite?
AbstractThis paper proposes a novel source reconstruction method (SRM) based on the convolutional neural network algorithm. The conventional SRM method usually requires the scattered field data oversampled compared to that of target object grids. To achieve higher accuracy, the conventional SRM numerical system is highly singular. To overcome these difficulties, we model the equivalent source reconstruction process using the machine learning. The equivalent sources of the target are constructed by a convolutional neural networks (ConvNets). It allows us to employless scattered field samples or radar cross section (RCS) data. And the ill-conditioned numerical system is effectively avoided. Numerical examples are provided to demonstrate the validity and accuracy of the proposed approach. Comparison with the traditional NN is also benchmarked. We further expand the proposed method into the direction of arrival (DOA) estimation to demonstrate the generality of the proposed procedure.
DescriptionLink to Free access
Persistent Identifierhttp://hdl.handle.net/10722/278140
ISSN
2023 Impact Factor: 0.7
2023 SCImago Journal Rankings: 0.254
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorYAO, HM-
dc.contributor.authorSha, WEI-
dc.contributor.authorJiang, LJ-
dc.date.accessioned2019-10-04T08:08:16Z-
dc.date.available2019-10-04T08:08:16Z-
dc.date.issued2018-
dc.identifier.citationProgress in Electromagnetics Research M, 2018, v. 76, p. 91-99-
dc.identifier.issn1937-8726-
dc.identifier.urihttp://hdl.handle.net/10722/278140-
dc.descriptionLink to Free access-
dc.description.abstractThis paper proposes a novel source reconstruction method (SRM) based on the convolutional neural network algorithm. The conventional SRM method usually requires the scattered field data oversampled compared to that of target object grids. To achieve higher accuracy, the conventional SRM numerical system is highly singular. To overcome these difficulties, we model the equivalent source reconstruction process using the machine learning. The equivalent sources of the target are constructed by a convolutional neural networks (ConvNets). It allows us to employless scattered field samples or radar cross section (RCS) data. And the ill-conditioned numerical system is effectively avoided. Numerical examples are provided to demonstrate the validity and accuracy of the proposed approach. Comparison with the traditional NN is also benchmarked. We further expand the proposed method into the direction of arrival (DOA) estimation to demonstrate the generality of the proposed procedure.-
dc.languageeng-
dc.publisherEMW Publishing. The Journal's web site is located at http://www.jpier.org/PIERM/-
dc.relation.ispartofProgress in Electromagnetics Research M-
dc.subjectConvolution-
dc.subjectLearning systems-
dc.subjectNeural networks-
dc.subjectConvolutional neural network-
dc.subjectDirection of arrivalestimation(DOA)-
dc.titleAPPLYING CONVOLUTIONAL NEURAL NETWORKS FOR THE SOURCE RECONSTRUCTION-
dc.typeArticle-
dc.identifier.emailJiang, LJ: jianglj@hku.hk-
dc.identifier.authorityJiang, LJ=rp01338-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.2528/PIERM18082907-
dc.identifier.scopuseid_2-s2.0-85060234141-
dc.identifier.hkuros306187-
dc.identifier.volume76-
dc.identifier.spage91-
dc.identifier.epage99-
dc.identifier.isiWOS:000455122000009-
dc.publisher.placeUnited States-
dc.identifier.issnl1937-8726-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats