No Cover Image

Journal article 147 views 73 downloads

Identification of metallic objects using spectral magnetic polarizability tensor signatures: Object classification

Ben Wilson, Paul D. Ledger Orcid Logo, William R. B. Lionheart Orcid Logo

International Journal for Numerical Methods in Engineering, Volume: 123, Issue: 9, Pages: 2076 - 2111

Swansea University Author: Ben Wilson

  • 59248.pdf

    PDF | Version of Record

    © 2022 The Authors. This is an open access article under the terms of the Creative Commons Attribution License

    Download (4.73MB)

Check full text

DOI (Published version): 10.1002/nme.6927

Abstract

The early detection of terrorist threat objects, such as guns and knives, through improved metal detection, has the potential to reduce the number of attacks and improve public safety and security. To achieve this, there is considerable potential to use the fields applied and measured by a metal det...

Full description

Published in: International Journal for Numerical Methods in Engineering
ISSN: 0029-5981 1097-0207
Published: Wiley 2022
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa59248
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2022-01-26T12:38:54Z
last_indexed 2023-01-11T14:40:23Z
id cronfa59248
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2022-08-16T15:32:48.9586492</datestamp><bib-version>v2</bib-version><id>59248</id><entry>2022-01-26</entry><title>Identification of metallic objects using spectral magnetic polarizability tensor signatures: Object classification</title><swanseaauthors><author><sid>7aad8167510801e63f1b9879d307c2ca</sid><firstname>Ben</firstname><surname>Wilson</surname><name>Ben Wilson</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2022-01-26</date><deptcode>REWI</deptcode><abstract>The early detection of terrorist threat objects, such as guns and knives, through improved metal detection, has the potential to reduce the number of attacks and improve public safety and security. To achieve this, there is considerable potential to use the fields applied and measured by a metal detector to discriminate between different shapes and different metals since, hidden within the field perturbation, is object characterization information. The magnetic polarizability tensor (MPT) offers an economical characterization of metallic objects and its spectral signature provides additional object characterization information. The MPT spectral signature can be determined from measurements of the induced voltage over a range of frequencies in a metal signature for a hidden object. With classification in mind, it can also be computed in advance for different threat and non-threat objects. In this article, we evaluate the performance of probabilistic and non-probabilistic machine learning algorithms, trained using a dictionary of computed MPT spectral signatures, to classify objects for metal detection. We discuss the importance of using appropriate features and selecting an appropriate algorithm depending on the classification problem being solved, and we present numerical results for a range of practically motivated metal detection classification problems.</abstract><type>Journal Article</type><journal>International Journal for Numerical Methods in Engineering</journal><volume>123</volume><journalNumber>9</journalNumber><paginationStart>2076</paginationStart><paginationEnd>2111</paginationEnd><publisher>Wiley</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>0029-5981</issnPrint><issnElectronic>1097-0207</issnElectronic><keywords>Finite element method; Magnetic polarizability tensor; Machine learning; Metal detection; Object classification; Reduced order model; Spectral; Validation</keywords><publishedDay>15</publishedDay><publishedMonth>5</publishedMonth><publishedYear>2022</publishedYear><publishedDate>2022-05-15</publishedDate><doi>10.1002/nme.6927</doi><url/><notes/><college>COLLEGE NANME</college><department>Reaching Wider</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>REWI</DepartmentCode><institution>Swansea University</institution><apcterm/><funders>Engineering and Physical Sciences Research Council. Grant Numbers: EP/R002134/2, EP/R002177/1, EP/V009028/1, EP/V009109/1, EP/V049453/1, EP/V049496/1 ; Royal Society</funders><projectreference/><lastEdited>2022-08-16T15:32:48.9586492</lastEdited><Created>2022-01-26T12:24:28.7353251</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Engineering and Applied Sciences - Uncategorised</level></path><authors><author><firstname>Ben</firstname><surname>Wilson</surname><order>1</order></author><author><firstname>Paul D.</firstname><surname>Ledger</surname><orcid>0000-0002-2587-7023</orcid><order>2</order></author><author><firstname>William R. B.</firstname><surname>Lionheart</surname><orcid>0000-0003-0971-4678</orcid><order>3</order></author></authors><documents><document><filename>59248__23760__f05bced97e6645cb97591aae9a7c766d.pdf</filename><originalFilename>59248.pdf</originalFilename><uploaded>2022-04-01T14:54:32.1381632</uploaded><type>Output</type><contentLength>4961266</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>&#xA9; 2022 The Authors. This is an open access article under the terms of the Creative Commons Attribution License</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>http://creativecommons.org/licenses/by/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling 2022-08-16T15:32:48.9586492 v2 59248 2022-01-26 Identification of metallic objects using spectral magnetic polarizability tensor signatures: Object classification 7aad8167510801e63f1b9879d307c2ca Ben Wilson Ben Wilson true false 2022-01-26 REWI The early detection of terrorist threat objects, such as guns and knives, through improved metal detection, has the potential to reduce the number of attacks and improve public safety and security. To achieve this, there is considerable potential to use the fields applied and measured by a metal detector to discriminate between different shapes and different metals since, hidden within the field perturbation, is object characterization information. The magnetic polarizability tensor (MPT) offers an economical characterization of metallic objects and its spectral signature provides additional object characterization information. The MPT spectral signature can be determined from measurements of the induced voltage over a range of frequencies in a metal signature for a hidden object. With classification in mind, it can also be computed in advance for different threat and non-threat objects. In this article, we evaluate the performance of probabilistic and non-probabilistic machine learning algorithms, trained using a dictionary of computed MPT spectral signatures, to classify objects for metal detection. We discuss the importance of using appropriate features and selecting an appropriate algorithm depending on the classification problem being solved, and we present numerical results for a range of practically motivated metal detection classification problems. Journal Article International Journal for Numerical Methods in Engineering 123 9 2076 2111 Wiley 0029-5981 1097-0207 Finite element method; Magnetic polarizability tensor; Machine learning; Metal detection; Object classification; Reduced order model; Spectral; Validation 15 5 2022 2022-05-15 10.1002/nme.6927 COLLEGE NANME Reaching Wider COLLEGE CODE REWI Swansea University Engineering and Physical Sciences Research Council. Grant Numbers: EP/R002134/2, EP/R002177/1, EP/V009028/1, EP/V009109/1, EP/V049453/1, EP/V049496/1 ; Royal Society 2022-08-16T15:32:48.9586492 2022-01-26T12:24:28.7353251 Faculty of Science and Engineering School of Engineering and Applied Sciences - Uncategorised Ben Wilson 1 Paul D. Ledger 0000-0002-2587-7023 2 William R. B. Lionheart 0000-0003-0971-4678 3 59248__23760__f05bced97e6645cb97591aae9a7c766d.pdf 59248.pdf 2022-04-01T14:54:32.1381632 Output 4961266 application/pdf Version of Record true © 2022 The Authors. This is an open access article under the terms of the Creative Commons Attribution License true eng http://creativecommons.org/licenses/by/4.0/
title Identification of metallic objects using spectral magnetic polarizability tensor signatures: Object classification
spellingShingle Identification of metallic objects using spectral magnetic polarizability tensor signatures: Object classification
Ben Wilson
title_short Identification of metallic objects using spectral magnetic polarizability tensor signatures: Object classification
title_full Identification of metallic objects using spectral magnetic polarizability tensor signatures: Object classification
title_fullStr Identification of metallic objects using spectral magnetic polarizability tensor signatures: Object classification
title_full_unstemmed Identification of metallic objects using spectral magnetic polarizability tensor signatures: Object classification
title_sort Identification of metallic objects using spectral magnetic polarizability tensor signatures: Object classification
author_id_str_mv 7aad8167510801e63f1b9879d307c2ca
author_id_fullname_str_mv 7aad8167510801e63f1b9879d307c2ca_***_Ben Wilson
author Ben Wilson
author2 Ben Wilson
Paul D. Ledger
William R. B. Lionheart
format Journal article
container_title International Journal for Numerical Methods in Engineering
container_volume 123
container_issue 9
container_start_page 2076
publishDate 2022
institution Swansea University
issn 0029-5981
1097-0207
doi_str_mv 10.1002/nme.6927
publisher Wiley
college_str Faculty of Science and Engineering
hierarchytype
hierarchy_top_id facultyofscienceandengineering
hierarchy_top_title Faculty of Science and Engineering
hierarchy_parent_id facultyofscienceandengineering
hierarchy_parent_title Faculty of Science and Engineering
department_str School of Engineering and Applied Sciences - Uncategorised{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Engineering and Applied Sciences - Uncategorised
document_store_str 1
active_str 0
description The early detection of terrorist threat objects, such as guns and knives, through improved metal detection, has the potential to reduce the number of attacks and improve public safety and security. To achieve this, there is considerable potential to use the fields applied and measured by a metal detector to discriminate between different shapes and different metals since, hidden within the field perturbation, is object characterization information. The magnetic polarizability tensor (MPT) offers an economical characterization of metallic objects and its spectral signature provides additional object characterization information. The MPT spectral signature can be determined from measurements of the induced voltage over a range of frequencies in a metal signature for a hidden object. With classification in mind, it can also be computed in advance for different threat and non-threat objects. In this article, we evaluate the performance of probabilistic and non-probabilistic machine learning algorithms, trained using a dictionary of computed MPT spectral signatures, to classify objects for metal detection. We discuss the importance of using appropriate features and selecting an appropriate algorithm depending on the classification problem being solved, and we present numerical results for a range of practically motivated metal detection classification problems.
published_date 2022-05-15T04:16:24Z
_version_ 1763754099317145600
score 11.013619

Similar Items