Weakly Supervised Acoustic Defect Detection in Concrete Structures Using Clustering-Based Augmentation
The automation of inspection methods for concrete structures is a pressing issue worldwide. Weakly supervised approaches, i.e., approaches based on supervision in other forms than traditional class labels, offer a unique mix of automation and human involvement that is highly effective for critical t...
Saved in:
Published in | IEEE/ASME transactions on mechatronics Vol. 26; no. 6; pp. 2826 - 2834 |
---|---|
Main Authors | , , , |
Format | Journal Article |
Language | English |
Published |
New York
IEEE
01.12.2021
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | The automation of inspection methods for concrete structures is a pressing issue worldwide. Weakly supervised approaches, i.e., approaches based on supervision in other forms than traditional class labels, offer a unique mix of automation and human involvement that is highly effective for critical tasks such as inspection work. Generating weak supervision is less tedious than generating training data for supervised learning approaches. However, since it is less informative, high amounts of weak supervision are often needed. In practice, it is often the case that only scarce amounts of weak supervision are available. In this article, we propose a novel approach for weakly supervised acoustic defect detection in concrete structures that augment human-provided weak supervision. Experiments in both laboratory and field conditions showed that the proposed method allows for considerable performance gains for low amounts of weak supervision. |
---|---|
AbstractList | The automation of inspection methods for concrete structures is a pressing issue worldwide. Weakly supervised approaches, i.e., approaches based on supervision in other forms than traditional class labels, offer a unique mix of automation and human involvement that is highly effective for critical tasks such as inspection work. Generating weak supervision is less tedious than generating training data for supervised learning approaches. However, since it is less informative, high amounts of weak supervision are often needed. In practice, it is often the case that only scarce amounts of weak supervision are available. In this article, we propose a novel approach for weakly supervised acoustic defect detection in concrete structures that augment human-provided weak supervision. Experiments in both laboratory and field conditions showed that the proposed method allows for considerable performance gains for low amounts of weak supervision. |
Author | Yamashita, Atsushi Asama, Hajime Kasahara, Jun Younes Louhi Fujii, Hiromitsu |
Author_xml | – sequence: 1 givenname: Jun Younes Louhi orcidid: 0000-0002-5924-8858 surname: Kasahara fullname: Kasahara, Jun Younes Louhi email: louhi@robot.t.u-tokyo.ac.jp organization: Department of Precision Engineering, The University of Tokyo, Tokyo, Japan – sequence: 2 givenname: Hiromitsu orcidid: 0000-0002-7051-1194 surname: Fujii fullname: Fujii, Hiromitsu email: hiromitsu.fujii@p.chibakoudai.jp organization: Department of Advanced Robotics, Chiba Institute of Technology, Chiba, Japan – sequence: 3 givenname: Atsushi orcidid: 0000-0003-1280-069X surname: Yamashita fullname: Yamashita, Atsushi email: yamashita@robot.t.u-tokyo.ac.jp organization: Department of Precision Engineering, The University of Tokyo, Tokyo, Japan – sequence: 4 givenname: Hajime orcidid: 0000-0002-9482-497X surname: Asama fullname: Asama, Hajime email: asama@robot.t.u-tokyo.ac.jp organization: Department of Precision Engineering, The University of Tokyo, Tokyo, Japan |
BookMark | eNo9kEtPwzAQhC0EEm3hD8AlEueU9SNxciyhUKQiDm0FN8t1NlVK6xQ7Qeq_x32I06xW-81qpk8ubWORkDsKQ0ohf5y_j4vJkAGjQw5Sijy9ID2aCxoDFV-XYYaMx0Lw5Jr0vV8DgKBAe6T6RP292Uezbofut_ZYRiPTdL6tTfSMFZo2SBukbmxU26horHFhEc1a15m2c-ijha_tKio2gUIXxvhJH3261RZtqw_oDbmq9Mbj7VkHZPEynheTePrx-laMprERkLQxggEutAAmqF5iVmZLLGVSpZksJS5lmmal5ixJU8azoGwJpkq0qCQYiongA_Jw8t255qdD36p10zkbXiqWhsAy5E7CFTtdGdd477BSO1dvtdsrCurQpzr2qQ59qnOfAbo_QTUi_gO5YDzJM_4HOxR0HA |
CODEN | IATEFW |
CitedBy_id | crossref_primary_10_1109_TIM_2024_3382737 crossref_primary_10_1109_TMECH_2023_3272797 crossref_primary_10_1109_TMECH_2022_3167412 crossref_primary_10_1109_JSEN_2023_3346470 crossref_primary_10_3390_e25071034 |
Cites_doi | 10.1109/CVPR.2006.167 10.22260/ISARC2017/0094 10.1109/LRA.2018.2820178 10.1109/GCCE46687.2019.9015437 10.1145/1823746.1823752 10.1007/3-540-47979-1_52 10.1109/SII.2017.8279318 10.1016/j.patcog.2005.12.004 10.1016/j.autcon.2015.07.022 10.1109/ICRoM.2015.7367821 10.22260/ISARC2020/0183 10.20965/jrm.2019.p0762 10.1007/978-3-540-74958-5_16 10.1016/j.neucom.2016.01.032 10.1109/SII46433.2020.9026304 10.1007/978-3-540-74048-3 10.1016/j.patcog.2008.05.018 10.3390/rs9080782 10.1109/ICRA.2016.7487573 10.1007/s00500-015-1643-3 10.1080/01691864.2020.1861977 10.1109/SoSE50414.2020.9130517 |
ContentType | Journal Article |
Copyright | Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021 |
Copyright_xml | – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021 |
DBID | 97E ESBDL RIA RIE AAYXX CITATION 7SC 7SP 7TB 8FD FR3 JQ2 L7M L~C L~D |
DOI | 10.1109/TMECH.2021.3077496 |
DatabaseName | IEEE All-Society Periodicals Package (ASPP) 2005-present IEEE Xplore Open Access Journals IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Xplore CrossRef Computer and Information Systems Abstracts Electronics & Communications Abstracts Mechanical & Transportation Engineering Abstracts Technology Research Database Engineering Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional |
DatabaseTitle | CrossRef Technology Research Database Computer and Information Systems Abstracts – Academic Mechanical & Transportation Engineering Abstracts Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Engineering Research Database Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Professional |
DatabaseTitleList | Technology Research Database |
Database_xml | – sequence: 1 dbid: RIE name: IEEE Xplore url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/ sourceTypes: Publisher |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Engineering |
EISSN | 1941-014X |
EndPage | 2834 |
ExternalDocumentID | 10_1109_TMECH_2021_3077496 9423598 |
Genre | orig-research |
GrantInformation_xml | – fundername: JSPS KAKENHI grantid: JP21K17829 – fundername: Suzuki foundation – fundername: Satomi scholarship foundation |
GroupedDBID | -~X 0B8 0R~ 29I 4.4 5GY 5VS 6IK 97E 9M8 AAJGR AASAJ ABQJQ ABVLG ACGFS ACIWK ACKIV AETIX AI. AIBXA AKJIK ALLEH ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 EBS EJD ESBDL F5P H~9 IFIPE IFJZH IPLJI JAVBF LAI M43 OCL RIA RIE RIG RNS TN5 VH1 XFK AAYXX CITATION 7SC 7SP 7TB 8FD FR3 JQ2 L7M L~C L~D |
ID | FETCH-LOGICAL-c405t-e0c034a40241abe8d8bed75f687d7eb7668da325662383252b0cf5a4f70c1e543 |
IEDL.DBID | RIE |
ISSN | 1083-4435 |
IngestDate | Thu Oct 10 17:03:04 EDT 2024 Fri Aug 23 01:01:47 EDT 2024 Wed Jun 26 19:25:38 EDT 2024 |
IsDoiOpenAccess | true |
IsOpenAccess | true |
IsPeerReviewed | true |
IsScholarly | true |
Issue | 6 |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-LOGICAL-c405t-e0c034a40241abe8d8bed75f687d7eb7668da325662383252b0cf5a4f70c1e543 |
ORCID | 0000-0002-5924-8858 0000-0003-1280-069X 0000-0002-7051-1194 0000-0002-9482-497X |
OpenAccessLink | https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/document/9423598 |
PQID | 2610170045 |
PQPubID | 85420 |
PageCount | 9 |
ParticipantIDs | proquest_journals_2610170045 ieee_primary_9423598 crossref_primary_10_1109_TMECH_2021_3077496 |
PublicationCentury | 2000 |
PublicationDate | 2021-Dec. 2021-12-00 20211201 |
PublicationDateYYYYMMDD | 2021-12-01 |
PublicationDate_xml | – month: 12 year: 2021 text: 2021-Dec. |
PublicationDecade | 2020 |
PublicationPlace | New York |
PublicationPlace_xml | – name: New York |
PublicationTitle | IEEE/ASME transactions on mechatronics |
PublicationTitleAbbrev | TMECH |
PublicationYear | 2021 |
Publisher | IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
Publisher_xml | – name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
References | ref13 ref12 ref15 ref14 ref30 ref10 ref17 bar-hillel (ref27) 2005; 6 ref19 news (ref2) 2018 ref18 ref23 kasahara (ref11) 2020; 20 ref26 henderson (ref3) 0 ref25 ref20 takahashi (ref24) 0 yang (ref22) 0; 9 kasahara (ref6) 0 ref28 yang (ref21) 0; 190 ref29 ref8 ref7 ref9 ref4 ref5 news (ref1) 2012 bar-hillel (ref16) 0 |
References_xml | – ident: ref19 doi: 10.1109/CVPR.2006.167 – ident: ref25 doi: 10.22260/ISARC2017/0094 – start-page: nov. 4, 2019. year: 2018 ident: ref2 article-title: Italy bridge collapse: Genoa death toll rises to 43 contributor: fullname: news – ident: ref8 doi: 10.1109/LRA.2018.2820178 – ident: ref9 doi: 10.1109/GCCE46687.2019.9015437 – ident: ref20 doi: 10.1145/1823746.1823752 – ident: ref17 doi: 10.1007/3-540-47979-1_52 – ident: ref7 doi: 10.1109/SII.2017.8279318 – ident: ref18 doi: 10.1016/j.patcog.2005.12.004 – volume: 6 start-page: 937 year: 2005 ident: ref27 article-title: Learning a Mahalanobis metric from equivalence constraints publication-title: J Mach Learn Res contributor: fullname: bar-hillel – ident: ref29 doi: 10.1016/j.autcon.2015.07.022 – start-page: 446 year: 0 ident: ref24 article-title: Velocity control mechanism of the under-actuated hammering robot for gravity compensation publication-title: Proc Int Symp Autom Robot Construction contributor: fullname: takahashi – ident: ref30 doi: 10.1109/ICRoM.2015.7367821 – ident: ref10 doi: 10.22260/ISARC2020/0183 – volume: 20 year: 2020 ident: ref11 article-title: Acoustic inspection of concrete structures using active weak supervision and visual information publication-title: SENSORS contributor: fullname: kasahara – ident: ref26 doi: 10.20965/jrm.2019.p0762 – ident: ref13 doi: 10.1007/978-3-540-74958-5_16 – volume: 190 start-page: 70 year: 0 ident: ref21 article-title: Metric learning based object recognition and retrieval publication-title: Neurocomputing doi: 10.1016/j.neucom.2016.01.032 contributor: fullname: yang – start-page: 11 year: 0 ident: ref16 article-title: Learning distance functions using equivalence relations publication-title: Proc Int Conf Mach Learn contributor: fullname: bar-hillel – start-page: 219 year: 0 ident: ref3 article-title: Acoustic inspection of concrete bridge decks publication-title: Proc Nondestruct Eval Techn Aging Infrastructures Manuf Int Soc Opt Photon contributor: fullname: henderson – ident: ref28 doi: 10.1109/SII46433.2020.9026304 – ident: ref15 doi: 10.1007/978-3-540-74048-3 – ident: ref23 doi: 10.1016/j.patcog.2008.05.018 – volume: 9 start-page: 782 year: 0 ident: ref22 article-title: Discriminative feature metric learning in the affinity propagation model for band selection in hyperspectral images publication-title: Remote Sensing doi: 10.3390/rs9080782 contributor: fullname: yang – start-page: 319 year: 0 ident: ref6 article-title: Unsupervised learning approach to detection of void-type defects in concrete structure using hammering and clustering publication-title: Proc Int Conf Adv Mechatron JSME contributor: fullname: kasahara – ident: ref4 doi: 10.1109/ICRA.2016.7487573 – ident: ref14 doi: 10.1007/s00500-015-1643-3 – start-page: nov. 4, 2019 year: 2012 ident: ref1 article-title: Japan Sasago tunnel collapse killed nine contributor: fullname: news – ident: ref12 doi: 10.1080/01691864.2020.1861977 – ident: ref5 doi: 10.1109/SoSE50414.2020.9130517 |
SSID | ssj0004101 |
Score | 2.4241984 |
Snippet | The automation of inspection methods for concrete structures is a pressing issue worldwide. Weakly supervised approaches, i.e., approaches based on supervision... |
SourceID | proquest crossref ieee |
SourceType | Aggregation Database Publisher |
StartPage | 2826 |
SubjectTerms | Acoustics Augmentation Automation Clustering Clustering methods Concrete Concrete structures Construction industry defect detection infrastructure inspection Inspection Mel frequency cepstral coefficient Supervision Training data weak supervision |
Title | Weakly Supervised Acoustic Defect Detection in Concrete Structures Using Clustering-Based Augmentation |
URI | https://ieeexplore.ieee.org/document/9423598 https://www.proquest.com/docview/2610170045 |
Volume | 26 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV07T8MwED5BJxh4I8pLHtjAxUmdxBmhgCqkshQEWxTbF4SAFKnJAL-es5NCBQxM8RBblu9y91189x3AESHQUBUi5VZq5DJWyFO0mmshg0SHeaH8jenoJh7eyeuH6GEBTr5qYRDRJ59hzw39Xb6dmNr9KjtNyfdHqVqERSXCplbruwYy8K2OA4IUXBIGmBXIiPT0dnQ5GFIoGAY90uhEOoL-OSfku6r8MsXev1ytwmi2syat5LlXV7pnPn6QNv5362uw0gJNdtZoxjosYLkBy3P0g5tQ3GP-_PLOxvWbsxhTtOzMTHx7L3aBLs-DHpXP1SrZU8kGk5IwZoVs7Elna4rUmU85YIOX2hEu0JCf536d-vG1rWoqt-Du6vJ2MORt3wVuCL5VHIURfZlTZCmDXKOySqNNoiJWiU1QJ3GsbN4nrETQiQxCFGphiiiXRSJMgJHsb0OnnJS4Ayy1gdE60Na4OhRhVCGjnEwGScE44p0uHM8Ekb019BqZD0tEmnmxZU5sWSu2Lmy6k_16sz3ULuzPZJe1X-A0o8jQUQMRYt39e9YeLLm1m9SUfejQyeEBAYxKH3rN-gTaMs13 |
link.rule.ids | 315,786,790,802,27955,27956,55107 |
linkProvider | IEEE |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1Lc9MwEN5Jy4FyKI_QISUFHbiBEjmRbfkY0mYCJL00HXLzWNK6wyQ4mal9gF_PSnbSDPTAyTr4odmVd7-Vdr8F-EAIdKBykXArNXIZKeQJWs21kEGsB1mu_Inp_Dqa3sqvy3DZgk_7WhhE9Mln2HNDf5ZvN6ZyW2X9hHx_mKgjeEJ-XsR1tdZDFWTgmx0HBCq4JBSwK5ERSX8xvxpPKRgcBD1a07F0FP0Hbsj3VfnHGHsPM3kO893c6sSSVa8qdc_8_ou28X8n_wJOG6jJRvXaeAktLF7BswMCwjbk3zFbrX-xm2rrbMY9WjYyG9_gi12iy_SgS-mztQr2o2DjTUEos0R242lnK4rVmU86YON15SgXaMg_Z_491d3Ppq6peA23k6vFeMqbzgvcEIArOQojhjKj2FIGmUZllUYbh3mkYhujjqNI2WxIaInAE5mEcKCFycNM5rEwAYZyeAbHxabAN8ASGxitA22Nq0QRRuUyzMhokBaMo97pwMedItJtTbCR-sBEJKlXW-rUljZq60DbSXZ_ZyPUDnR3ukubf_A-pdjQkQMRZj1__Kn38HS6mM_S2Zfrb2_hxH2nTlTpwjFJES8IbpT6nV9lfwDYStDL |
openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Weakly+Supervised+Acoustic+Defect+Detection+in+Concrete+Structures+Using+Clustering-Based+Augmentation&rft.jtitle=IEEE%2FASME+transactions+on+mechatronics&rft.au=Kasahara%2C+Jun+Younes+Louhi&rft.au=Fujii%2C+Hiromitsu&rft.au=Yamashita%2C+Atsushi&rft.au=Asama%2C+Hajime&rft.date=2021-12-01&rft.issn=1083-4435&rft.eissn=1941-014X&rft.volume=26&rft.issue=6&rft.spage=2826&rft.epage=2834&rft_id=info:doi/10.1109%2FTMECH.2021.3077496&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TMECH_2021_3077496 |
thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1083-4435&client=summon |
thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1083-4435&client=summon |
thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1083-4435&client=summon |