Repository logo
 
Publication

GPR target detection using a neural network classifier designed by a multi-objective genetic algorithm

2019-06Journal article Restricted access
Simple item page
dc.contributor.authorHarkat, Houda
dc.contributor.authorRuano, Antonio
dc.contributor.authorGraca Ruano, Maria
dc.contributor.authorBennani, S. D.
dc.date.accessioned2020-07-24T10:52:14Z
dc.date.available2020-07-24T10:52:14Z
dc.date.issued2019-06
dc.description.abstractGround Penetrating Radar (GPR) is an electromagnetic sensing technology employed for localization of underground utilities, pipes, and other types of objects. The radargrams typically obtained have a high dimensionality, containing a number of signatures with hyperbolic pattern shapes, and can be processed to retrieve information about the target's locations, depths and material type of underground soil. The classical Hough Transform approach used to reconstruct these hyperbola shapes is computationally expensive, given the large dimensionality of the radargrams. In literature, several approaches propose to first approximate the location of hyperbolas to small segments through a classification stage, before applying the Hough transform over these segments. However, the published classifiers designed for this task present a relatively complex architecture. Aiming at an improved target localization, we propose an alternative classification methodology. The goal is to classify windows of GPR radargrams into two classes (with or without target) using a neural network radial basis function (RBF), designed via a multi-objective genetic algorithm (MOGA). To capture samples' fine details, high order statistic cumulant features (HOS) were used. Feature selection was performed by MOGA, with an optional prior reduction using a mutual information (MIFS) approach. The obtained results demonstrate improvement of the classification performance when compared with other models designed with the same data and are among the best results available in the literature, albeit the large reduction in classifier complexity. (C) 2019 Elsevier B.V. All rights reserved.
dc.description.sponsorshipPortuguese Erasmus National Agency [2015-01-PT01-KA107-04276]
dc.description.sponsorshipPortuguese Foundation for Science and Technology, through IDMEC, under LAETA [UID/EMS/50022/2019]
dc.description.versioninfo:eu-repo/semantics/publishedVersion
dc.identifier.doi10.1016/j.asoc.2019.03.030
dc.identifier.issn1568-4946
dc.identifier.issn1872-9681
dc.identifier.urihttp://hdl.handle.net/10400.1/14335
dc.language.isoeng
dc.peerreviewedyes
dc.publisherElsevier
dc.relationBridging continents across the sea: Multi-disciplinary perspectives on the emergence of long-distance maritime contacts in prehistory
dc.relationLINKING RINGS INTO COMPLEX STRUCTURES
dc.subjectGround-penetrating radar
dc.subjectLandmine detection
dc.subjectFeatures
dc.subjectSignal
dc.subjectHyperbolas
dc.subjectSelection
dc.titleGPR target detection using a neural network classifier designed by a multi-objective genetic algorithm
dc.typejournal article
dspace.entity.typePublication
oaire.awardTitleBridging continents across the sea: Multi-disciplinary perspectives on the emergence of long-distance maritime contacts in prehistory
oaire.awardTitleLINKING RINGS INTO COMPLEX STRUCTURES
oaire.awardURIinfo:eu-repo/grantAgreement/EC/FP7/206148/EU
oaire.awardURIinfo:eu-repo/grantAgreement/EC/FP7/219588/EU
oaire.citation.endPage325
oaire.citation.startPage310
oaire.citation.titleApplied Soft Computing
oaire.citation.volume79
oaire.fundingStreamFP7
oaire.fundingStreamFP7
person.familyNameHarkat
person.familyNameRuano
person.familyNameRuano
person.givenNameHouda
person.givenNameAntonio
person.givenNameMaria
person.identifier.ciencia-id9811-A0DD-D5A5
person.identifier.orcid0000-0002-7827-1527
person.identifier.orcid0000-0002-6308-8666
person.identifier.orcid0000-0002-0014-9257
person.identifier.ridB-4135-2008
person.identifier.ridA-8321-2011
person.identifier.scopus-author-id7004284159
person.identifier.scopus-author-id7004483805
project.funder.identifierhttp://doi.org/10.13039/501100008530
project.funder.identifierhttp://doi.org/10.13039/501100008530
project.funder.nameEuropean Commission
project.funder.nameEuropean Commission
rcaap.rightsrestrictedAccess
rcaap.typearticle
relation.isAuthorOfPublicationff3a322c-945f-465a-b746-c69eab18be72
relation.isAuthorOfPublication13813664-b68b-40aa-97a9-91481a31ebf2
relation.isAuthorOfPublication61fc8492-d73f-46ca-a3a3-4cd762a784e6
relation.isAuthorOfPublication.latestForDiscoveryff3a322c-945f-465a-b746-c69eab18be72
relation.isProjectOfPublication0dc88e03-3c91-4117-8801-a8072116bfb9
relation.isProjectOfPublicationd328ccc1-3e87-4012-a63c-3dbcbf5c71e6
relation.isProjectOfPublication.latestForDiscovery0dc88e03-3c91-4117-8801-a8072116bfb9

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
1-s2.0-S1568494619301541-main.pdf
Size:
3.45 MB
Format:
Adobe Portable Document Format
Download

Collections

FCT2-Artigos (em revistas ou actas indexadas)