{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T21:37:47Z","timestamp":1773956267378,"version":"3.50.1"},"reference-count":49,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100014188","name":"Ministry of Science and ICT, South Korea","doi-asserted-by":"publisher","award":["2022R1C1C1006507"],"award-info":[{"award-number":["2022R1C1C1006507"]}],"id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Engineering Applications of Artificial Intelligence"],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1016\/j.engappai.2025.113670","type":"journal-article","created":{"date-parts":[[2025,12,27]],"date-time":"2025-12-27T16:15:49Z","timestamp":1766852149000},"page":"113670","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PB","title":["Developing fully convolutional networks with permittivity-based class mapping for tunnel lining defects detection in ground penetration radar scan data"],"prefix":"10.1016","volume":"166","author":[{"given":"Viet Dinh","family":"Le","sequence":"first","affiliation":[]},{"given":"Gyu-Hyun","family":"Go","sequence":"additional","affiliation":[]},{"given":"Sayali","family":"Pangavhane","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7706-5190","authenticated-orcid":false,"given":"Chang Kyoon","family":"Yoo","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"issue":"12","key":"10.1016\/j.engappai.2025.113670_bib1","doi-asserted-by":"crossref","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","article-title":"SegNet: a deep convolutional encoder-decoder architecture for image segmentation","volume":"39","author":"Badrinarayanan","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.engappai.2025.113670_bib2","first-page":"2852","article-title":"Deep neural networks segment neuronal membranes in electron microscopy images","volume":"25","author":"Ciresan","year":"2012","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.engappai.2025.113670_bib3","doi-asserted-by":"crossref","DOI":"10.1016\/j.tust.2020.103487","article-title":"Deterioration mapping in subway infrastructure using sensory data of GPR","volume":"103","author":"Dawood","year":"2020","journal-title":"Tunn. Undergr. Space Technol."},{"issue":"2","key":"10.1016\/j.engappai.2025.113670_bib4","article-title":"A deep convolutional activation feature for generic visual recognition","volume":"1","author":"Donahue","year":"2013","journal-title":"UC Berkeley and ICSI, Berkeley, CA, USA"},{"key":"10.1016\/j.engappai.2025.113670_bib5","first-page":"633","article-title":"Restoring an image taken through a window covered with dirt or rain","author":"Eigen","year":"2013","journal-title":"Proceedings of the IEEE International Conference on Computer Vision"},{"issue":"2","key":"10.1016\/j.engappai.2025.113670_bib52","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","article-title":"The pascal visual object classes (voc) challenge","volume":"88","author":"Everingham","year":"2010","journal-title":"Int. J. Comput. Vision"},{"issue":"8","key":"10.1016\/j.engappai.2025.113670_bib6","doi-asserted-by":"crossref","first-page":"1915","DOI":"10.1109\/TPAMI.2012.231","article-title":"Learning hierarchical features for scene labeling","volume":"35","author":"Farabet","year":"2012","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.engappai.2025.113670_bib7","series-title":"Introduction to the Finite-Difference Time-Domain (FDTD) Method for Electromagnetics","first-page":"113","article-title":"The perfectly matched layer (PML) absorbing medium","author":"Gedney","year":"2011"},{"issue":"1","key":"10.1016\/j.engappai.2025.113670_bib8","doi-asserted-by":"crossref","first-page":"134","DOI":"10.1109\/74.997945","article-title":"Higher-order finite-difference schemes for electromagnetic radiation, scattering, and penetration","volume":"44","author":"Georgakopoulos","year":"2002","journal-title":"IEEE Antenn. Propag. Mag."},{"key":"10.1016\/j.engappai.2025.113670_bib9","first-page":"580","article-title":"Rich feature hierarchies for accurate object detection and semantic segmentation","author":"Girshick","year":"2014","journal-title":"Paper presented at the"},{"issue":"4","key":"10.1016\/j.engappai.2025.113670_bib10","doi-asserted-by":"crossref","first-page":"413","DOI":"10.1016\/0886-7798(95)00030-3","article-title":"Report to ITA working group on maintenance and repair of underground structures: State-of-the-art of non-destructive testing methods for determining the state of a tunnel lining","volume":"10","author":"Haack","year":"1995","journal-title":"Tunn. Undergr. Space Technol."},{"issue":"6","key":"10.1016\/j.engappai.2025.113670_bib11","doi-asserted-by":"crossref","first-page":"814","DOI":"10.1111\/mice.13042","article-title":"A deep learning framework based on improved self-supervised learning for ground-penetrating radar tunnel lining inspection","volume":"39","author":"Huang","year":"2024","journal-title":"Comput. Aided Civ. Infrastruct. Eng."},{"issue":"9","key":"10.1016\/j.engappai.2025.113670_bib12","doi-asserted-by":"crossref","first-page":"1247","DOI":"10.1016\/j.cageo.2005.11.006","article-title":"Numerical modeling of ground-penetrating radar in 2-D using MATLAB","volume":"32","author":"Irving","year":"2006","journal-title":"Comput. Geosci."},{"key":"10.1016\/j.engappai.2025.113670_bib13","author":"Khan"},{"key":"10.1016\/j.engappai.2025.113670_bib14","article-title":"ImageNet classification with deep convolutional neural networks","volume":"25","author":"Krizhevsky","year":"2012","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"6","key":"10.1016\/j.engappai.2025.113670_bib15","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1145\/3065386","article-title":"ImageNet classification with deep convolutional neural networks","volume":"60","author":"Krizhevsky","year":"2017","journal-title":"Commun. ACM"},{"key":"10.1016\/j.engappai.2025.113670_bib16","first-page":"1","article-title":"Foundations of semialgebraic gene-environment networks","author":"Kropat","year":"2020","journal-title":"J. Dynam. Game"},{"issue":"7553","key":"10.1016\/j.engappai.2025.113670_bib17","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"10.1016\/j.engappai.2025.113670_bib18","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1016\/j.tust.2016.12.011","article-title":"An overview of ahead geological prospecting in tunneling","volume":"63","author":"Li","year":"2017","journal-title":"Tunn. Undergr. Space Technol."},{"issue":"10","key":"10.1016\/j.engappai.2025.113670_bib19","doi-asserted-by":"crossref","first-page":"8305","DOI":"10.1109\/TGRS.2020.3046454","article-title":"GPRInvNet: deep learning-based ground-penetrating radar data inversion for tunnel linings","volume":"59","author":"Liu","year":"2021","journal-title":"IEEE Trans. Geosci. Rem. Sens."},{"key":"10.1016\/j.engappai.2025.113670_bib20","doi-asserted-by":"crossref","DOI":"10.1016\/j.autcon.2022.104633","article-title":"Simultaneous tunnel defects and lining thickness identification based on multi-tasks deep neural network from ground penetrating radar images","volume":"145","author":"Liu","year":"2023","journal-title":"Autom. ConStruct."},{"key":"10.1016\/j.engappai.2025.113670_bib21","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"3431","article-title":"Fully convolutional networks for semantic segmentation","author":"Long","year":"2015"},{"key":"10.1016\/j.engappai.2025.113670_bib22","first-page":"488","article-title":"Multi-digit recognition using a space displacement neural network","volume":"4","author":"Matan","year":"1991","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.engappai.2025.113670_bib23","doi-asserted-by":"crossref","DOI":"10.1016\/j.dib.2025.111338","article-title":"Intelligent recognition of subsurface utilities and voids: a ground penetrating radar dataset for deep learning applications","volume":"59","author":"Mojahid","year":"2025","journal-title":"Data Brief"},{"key":"10.1016\/j.engappai.2025.113670_bib24","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1016\/j.autcon.2015.02.003","article-title":"Past, present and future of robotic tunnel inspection","volume":"59","author":"Montero","year":"2015","journal-title":"Autom. ConStruct."},{"key":"10.1016\/j.engappai.2025.113670_bib25","author":"Perlin"},{"key":"10.1016\/j.engappai.2025.113670_bib51","article-title":"Procedural generation: 2D Perlin noise. CMSC 425","volume":"13","author":"Mount","year":"2018","journal-title":"Lecture"},{"key":"10.1016\/j.engappai.2025.113670_bib26","series-title":"Proceedings of the 29th Annual Conference on Computer Graphics and Interactive Techniques","first-page":"681","article-title":"Improving noise","author":"Perlin","year":"2002"},{"key":"10.1016\/j.engappai.2025.113670_bib27","series-title":"International Conference on Machine Learning","first-page":"82","article-title":"Recurrent convolutional neural networks for scene labeling","author":"Pinheiro","year":"2014"},{"key":"10.1016\/j.engappai.2025.113670_bib28","doi-asserted-by":"crossref","DOI":"10.1016\/j.autcon.2021.103830","article-title":"Automatic recognition of tunnel lining elements from GPR images using deep convolutional networks with data augmentation","volume":"130","author":"Qin","year":"2021","journal-title":"Autom. ConStruct."},{"issue":"5","key":"10.1016\/j.engappai.2025.113670_bib29","doi-asserted-by":"crossref","first-page":"334","DOI":"10.1002\/1098-2760(20001205)27:5<334::AID-MOP14>3.0.CO;2-A","article-title":"Convolution PML (CPML): an efficient FDTD implementation of the CFS-PML for arbitrary media","volume":"27","author":"Roden","year":"2000","journal-title":"Microw. Opt. Technol. Lett."},{"key":"10.1016\/j.engappai.2025.113670_bib30","doi-asserted-by":"crossref","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","article-title":"U-net: convolutional networks for biomedical image segmentation","volume":"9351","author":"Ronneberger","year":"2015","journal-title":"Lect. Notes Comput. Sci."},{"key":"10.1016\/j.engappai.2025.113670_bib31","doi-asserted-by":"crossref","first-page":"696","DOI":"10.1007\/s10957-017-1159-3","article-title":"A stochastic maximum principle for a markov regime-switching jump-diffusion model with delay and an application to finance","volume":"179","author":"Savku","year":"2018","journal-title":"J. Optim. Theor. Appl."},{"key":"10.1016\/j.engappai.2025.113670_bib32","first-page":"746","article-title":"Indoor segmentation and support inference from RGBD images","volume":"2012","author":"Silberman","year":"2012","journal-title":"Computer Vision\u2013ECCV"},{"key":"10.1016\/j.engappai.2025.113670_bib33","series-title":"2016 16th International Conference on Ground Penetrating Radar (GPR)","first-page":"1","article-title":"The NeTTUN project: design of a GPR antenna for a TBM","author":"Simi","year":"2016"},{"key":"10.1016\/j.engappai.2025.113670_bib34","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv preprint arXiv:1409.1556"},{"key":"10.1016\/j.engappai.2025.113670_bib35","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"1","article-title":"Going deeper with convolutions","author":"Szegedy","year":"2015"},{"issue":"10628","key":"10.1016\/j.engappai.2025.113670_bib36","first-page":"306","article-title":"Generative adversarial networks for ground-penetrating radar in handheld explosive hazard detection. Detection and Sensing of Mines, Explosive Objects, and","volume":"XXIII","author":"Veal","year":"2018","journal-title":"Obscured Targets"},{"key":"10.1016\/j.engappai.2025.113670_bib37","series-title":"2015 8th International Workshop on Advanced Ground Penetrating Radar (IWAGPR)","first-page":"1","article-title":"Investigation of forward-looking synthetic circular array for subsurface imaging in tunnel boring machine applications","author":"Wang","year":"2015"},{"issue":"2","key":"10.1016\/j.engappai.2025.113670_bib38","doi-asserted-by":"crossref","first-page":"G37","DOI":"10.1190\/1.3548506","article-title":"Creating finite-difference time-domain models of commercial ground-penetrating radar antennas using Taguchi's optimization method","volume":"76","author":"Warren","year":"2011","journal-title":"Geophysics"},{"key":"10.1016\/j.engappai.2025.113670_bib39","doi-asserted-by":"crossref","first-page":"163","DOI":"10.1016\/j.cpc.2016.08.020","article-title":"gprMax: open source software to simulate electromagnetic wave propagation for ground-penetrating radar","volume":"209","author":"Warren","year":"2016","journal-title":"Comput. Phys. Commun."},{"key":"10.1016\/j.engappai.2025.113670_bib40","first-page":"745","article-title":"Postal address block location using a convolutional locator network","volume":"6","author":"Wolf","year":"1993","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"22","key":"10.1016\/j.engappai.2025.113670_bib41","doi-asserted-by":"crossref","first-page":"4590","DOI":"10.3390\/rs13224590","article-title":"Generation of high-precision ground-penetrating radar images using improved least square generative adversarial networks","volume":"13","author":"Yue","year":"2021","journal-title":"Remote Sens."},{"issue":"2","key":"10.1016\/j.engappai.2025.113670_bib43","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1002\/nsg.12032","article-title":"Application of ground-penetrating radar to detect tunnel lining defects based on improved full waveform inversion and reverse time migration","volume":"17","author":"Zhang","year":"2019","journal-title":"Near Surf. Geophys."},{"key":"10.1016\/j.engappai.2025.113670_bib54","series-title":"European Conference on Computer Vision","first-page":"818","article-title":"Visualizing and understanding convolutional networks","author":"Zeiler","year":"2014"},{"key":"10.1016\/j.engappai.2025.113670_bib44","first-page":"834","article-title":"Part-based R-CNNs for fine-grained category detection","volume":"2014","author":"Zhang","year":"2014","journal-title":"Computer Vision\u2013ECCV"},{"issue":"2","key":"10.1016\/j.engappai.2025.113670_bib45","doi-asserted-by":"crossref","first-page":"234","DOI":"10.3390\/min12020234","article-title":"Three-dimensional quantitative recognition of filler materials ahead of a tunnel face via time-energy density analysis of wavelet transforms","volume":"12","author":"Zhang","year":"2022","journal-title":"Minerals"},{"issue":"6","key":"10.1016\/j.engappai.2025.113670_bib53","doi-asserted-by":"crossref","first-page":"3398","DOI":"10.1109\/TGRS.2018.2799586","article-title":"An automatic GPR B-scan image interpreting model","volume":"56","author":"Zhou","year":"2018","journal-title":"IEEE Transact. Geosci. Remot. Sens."},{"key":"10.1016\/j.engappai.2025.113670_bib46","doi-asserted-by":"crossref","DOI":"10.1016\/j.tust.2023.105568","article-title":"TunGPR: enhancing data-driven maintenance for tunnel linings through synthetic datasets, deep learning and BIM","volume":"145","author":"Zhu","year":"2024","journal-title":"Tunn. Undergr. Space Technol."}],"container-title":["Engineering Applications of Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0952197625037029?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0952197625037029?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T17:22:39Z","timestamp":1773940959000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0952197625037029"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":49,"alternative-id":["S0952197625037029"],"URL":"https:\/\/doi.org\/10.1016\/j.engappai.2025.113670","relation":{},"ISSN":["0952-1976"],"issn-type":[{"value":"0952-1976","type":"print"}],"subject":[],"published":{"date-parts":[[2026,2]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Developing fully convolutional networks with permittivity-based class mapping for tunnel lining defects detection in ground penetration radar scan data","name":"articletitle","label":"Article Title"},{"value":"Engineering Applications of Artificial Intelligence","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.engappai.2025.113670","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"113670"}}