Benchmarking Deep Learning models and hyperparameters for Bridge Defects Classification

Deep learning (DL) is becoming increasingly popular in numerous application fields within the current Fourth Industrial Revolution (4IR) era. This is mainly due to its capability for providing accurate predictions and reliable consistency in decision-making. Bridge engineering focused on structure m...

Full description

Saved in:
Bibliographic Details
Published in:Procedia computer science Vol. 219; pp. 345 - 353
Main Authors: Shahrabadi, Somayeh, Gonzalez, Dibet, Sousa, Nuno, Adão, Telmo, Peres, Emanuel, Magalhães, Luís
Format: Journal Article
Language:English
Published: Elsevier B.V 2023
Subjects:
ISSN:1877-0509, 1877-0509
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Deep learning (DL) is becoming increasingly popular in numerous application fields within the current Fourth Industrial Revolution (4IR) era. This is mainly due to its capability for providing accurate predictions and reliable consistency in decision-making. Bridge engineering focused on structure monitoring and inspection is a crucial activity for disaster prevention. Therefore, it is an application field wherein synergies between professional knowledge and sophisticated machine-based analytics strategies can be established and even drive time-effective interventions. This paper presents a comparison of DL models used to detect defects in bridges, resorting to the following architectures: MobileNetV2, Xception, InceptionV3, NASNetMobile, Visual Geometry Group Network-16 (VGG16), and InceptionResNetV2. Different optimizers (e.g., Nadam, Adam, RMSprop, and SGD) crossed with distinct learning rates (e.g., 1, 10−1, 10−2, 10−3, 10−4, and 10−5) were employed. VGG16, Xception, and NASNetMobile showed the most stable learning curves. Moreover, Gradient-weighted Class Activation Mapping (Grad-CAM) overlapping images clarifies that InceptionResNetV2 and InceptionV3 models seek features outside the areas of interest (defects). Comparing optimizers’ performance, the adaptive ones outperform SGD with decay schedulers for learning rates.
AbstractList Deep learning (DL) is becoming increasingly popular in numerous application fields within the current Fourth Industrial Revolution (4IR) era. This is mainly due to its capability for providing accurate predictions and reliable consistency in decision-making. Bridge engineering focused on structure monitoring and inspection is a crucial activity for disaster prevention. Therefore, it is an application field wherein synergies between professional knowledge and sophisticated machine-based analytics strategies can be established and even drive time-effective interventions. This paper presents a comparison of DL models used to detect defects in bridges, resorting to the following architectures: MobileNetV2, Xception, InceptionV3, NASNetMobile, Visual Geometry Group Network-16 (VGG16), and InceptionResNetV2. Different optimizers (e.g., Nadam, Adam, RMSprop, and SGD) crossed with distinct learning rates (e.g., 1, 10−1, 10−2, 10−3, 10−4, and 10−5) were employed. VGG16, Xception, and NASNetMobile showed the most stable learning curves. Moreover, Gradient-weighted Class Activation Mapping (Grad-CAM) overlapping images clarifies that InceptionResNetV2 and InceptionV3 models seek features outside the areas of interest (defects). Comparing optimizers’ performance, the adaptive ones outperform SGD with decay schedulers for learning rates.
Author Shahrabadi, Somayeh
Adão, Telmo
Magalhães, Luís
Gonzalez, Dibet
Sousa, Nuno
Peres, Emanuel
Author_xml – sequence: 1
  givenname: Somayeh
  surname: Shahrabadi
  fullname: Shahrabadi, Somayeh
  email: Somayeh.Shahrabadi@ccg.pt
  organization: CCG: Centre for Computer Graphics, Campus de Azurém, Edifício 14, 4800-058, Guimarães, Portugal
– sequence: 2
  givenname: Dibet
  surname: Gonzalez
  fullname: Gonzalez, Dibet
  organization: CCG: Centre for Computer Graphics, Campus de Azurém, Edifício 14, 4800-058, Guimarães, Portugal
– sequence: 3
  givenname: Nuno
  surname: Sousa
  fullname: Sousa, Nuno
  organization: CCG: Centre for Computer Graphics, Campus de Azurém, Edifício 14, 4800-058, Guimarães, Portugal
– sequence: 4
  givenname: Telmo
  surname: Adão
  fullname: Adão, Telmo
  organization: CCG: Centre for Computer Graphics, Campus de Azurém, Edifício 14, 4800-058, Guimarães, Portugal
– sequence: 5
  givenname: Emanuel
  surname: Peres
  fullname: Peres, Emanuel
  organization: CITAB, University of Trás-os-Montes e Alto Douro, 5000-801 Vila Real, Portugal
– sequence: 6
  givenname: Luís
  surname: Magalhães
  fullname: Magalhães, Luís
  organization: Algoritmi Centre, University of Minho, Campus de Azurém, Av. da Universidade, 4800-058 Guimarães, Portugal
BookMark eNqFkL9OwzAQhy1UJErpE7DkBRL8p3HigYEWCkiVGEBitBz73LqkcWRHSH173JYBMcAtdzd8p999l2jU-Q4Quia4IJjwm23RB69jQTFlBSYFFeIMjUldVTkusRj9mC_QNMYtTsXqWpBqjN7n0OnNToUP162ze4A-W4EK3WHbeQNtzFRnss2-h9CroHYwQIiZ9SGbB2fWkBgLeojZolUxOuu0GpzvrtC5VW2E6XefoNflw9viKV-9PD4v7la5pilB3tgKODVQMmZwZahhHBM7M7WoGQjT0KZqmC0V55SaWVNqzQUoEIyXShE2Qex0VQcfYwAr--DSM3tJsDzIkVt5lCMPciQmMslJlPhFaTccUw9BufYf9vbEJjPw6SDIqF1SCMaFpEEa7_7kvwBHPYVS
CitedBy_id crossref_primary_10_3390_a17030106
crossref_primary_10_3390_life13112125
crossref_primary_10_1109_ACCESS_2025_3554395
Cites_doi 10.3390/app10030972
10.1007/s42979-021-00592-x
10.1111/mice.12412
10.1177/1475921719896813
10.1016/j.autcon.2019.04.005
10.1016/j.neucom.2020.04.045
10.1109/ACCESS.2021.3053408
10.3390/s21030824
10.1111/mice.12433
10.1186/s12880-022-00793-7
10.1109/ICCV.2017.74
10.1177/1475921720965445
10.1016/j.eng.2020.07.026
10.1007/978-3-030-01424-7_27
10.1016/j.autcon.2018.06.006
10.1109/ACCESS.2022.3148711
10.1109/CVPR.2009.5206848
10.1016/j.adapen.2022.100084
10.1016/j.patter.2021.100336
10.3390/s18061881
ContentType Journal Article
Copyright 2023
Copyright_xml – notice: 2023
DBID 6I.
AAFTH
AAYXX
CITATION
DOI 10.1016/j.procs.2023.01.299
DatabaseName ScienceDirect Open Access Titles
Elsevier:ScienceDirect:Open Access
CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISSN 1877-0509
EndPage 353
ExternalDocumentID 10_1016_j_procs_2023_01_299
S1877050923003083
GroupedDBID --K
0R~
0SF
1B1
457
5VS
6I.
71M
AACTN
AAEDT
AAEDW
AAFTH
AAIKJ
AALRI
AAQFI
AAXUO
ABMAC
ACGFS
ADBBV
ADEZE
AEXQZ
AFTJW
AGHFR
AITUG
ALMA_UNASSIGNED_HOLDINGS
AMRAJ
E3Z
EBS
EJD
EP3
FDB
FNPLU
HZ~
IXB
KQ8
M41
M~E
NCXOZ
O-L
O9-
OK1
P2P
RIG
ROL
SES
SSZ
9DU
AAYWO
AAYXX
ABWVN
ACRPL
ACVFH
ADCNI
ADNMO
ADVLN
AEUPX
AFPUW
AIGII
AKBMS
AKRWK
AKYEP
CITATION
~HD
ID FETCH-LOGICAL-c2889-bf7e62de533d07d2d3601f4d8983e9db2b7b3f5a6622d4b5cc69eae9365aa13
ISSN 1877-0509
IngestDate Sat Nov 29 07:01:55 EST 2025
Tue Nov 18 22:36:27 EST 2025
Sat Jun 17 15:40:38 EDT 2023
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Keywords Transfer Learning
Objective Function Optimization
Learning Rate
Benchmarking
Bridge Defects Inspection
Convolutional Neural Networks
Deep Learning
Language English
License This is an open access article under the CC BY license.
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c2889-bf7e62de533d07d2d3601f4d8983e9db2b7b3f5a6622d4b5cc69eae9365aa13
OpenAccessLink https://dx.doi.org/10.1016/j.procs.2023.01.299
PageCount 9
ParticipantIDs crossref_primary_10_1016_j_procs_2023_01_299
crossref_citationtrail_10_1016_j_procs_2023_01_299
elsevier_sciencedirect_doi_10_1016_j_procs_2023_01_299
PublicationCentury 2000
PublicationDate 2023
2023-00-00
PublicationDateYYYYMMDD 2023-01-01
PublicationDate_xml – year: 2023
  text: 2023
PublicationDecade 2020
PublicationTitle Procedia computer science
PublicationYear 2023
Publisher Elsevier B.V
Publisher_xml – name: Elsevier B.V
References Paullada, Raji, Bender, Denton, Hanna (bib0030) 2021; 2
R. Girshick, J. Donahue, T. Darrell, and J. Malik, “Rich feature hierarchies for accurate object detection and semantic segmentation Tech report (v5).” [Online]. Available
Maguire, Dorafshan, Thomas (bib0005) 2018
Liu, Cao, Wang, Wang (bib0009) 2019; 104
Seo, Duque, Wacker (bib0001) 2018; 94
Yang, Li, Yu, Luo, Huang, Yang (bib0006) 2018; 33
Ribani, Marengoni (bib0018) 2019
Rao, Nguyen, Palaniswami, Ngo (bib0011) 2021; 20
Kim, Cosa-Linan, Santhanam, Jannesari, Maros, Ganslandt (bib0022) 2022; 22
Cormen, Cormen (bib0008) 2001
ON EMPIRICAL COMPARISONS OF OPTIMIZERS FOR DEEP LEARNING.
Ronneberger, Fischer, Thomas (bib0010) 2021; 9
C. Tan, F. Sun, T. Kong, W. Zhang, C. Yang, and C. Liu, “A Survey on Deep Transfer Learning,” Aug. 2018, [Online]. Available
Qiao, Ma, Liu, Wu, Li (bib0014) 2021; 21
Li, Zhang, Qin, Estupinan (bib0023) 2020; 407
Y. Li, S. Xie, X. Chen, P. Dollar, K. He, and R. Girshick, “Benchmarking Detection Transfer Learning with Vision Transformers,” Nov. 2021, [Online]. Available
Mei, Gül (bib0007) 2020; 19
Zhu, Song (bib0015) 2020; 10
J. Deng, W. Dong, R. Socher, L.-J. Li, Kai Li, and Li Fei-Fei, “ImageNet: A large-scale hierarchical image database,” Mar. 2010, pp. 248–255. doi: 10.1109/cvpr.2009.5206848.
Kim, Jeon, Baek, Hong, Jung (bib0016) 2018; 18
Li, Zhao, Zhou (bib0012) 2019; 34
Nov. 2020, doi: 10.1016/j.eng.2020.07.026.
J. Plested and T. Gedeon, “Deep transfer learning for image classification: a survey,” May 2022, [Online]. Available
LabelImg: Image annotation tool
Y. Roh, G. Heo, and S. E. Whang, “A Survey on Data Collection for Machine Learning: a Big Data – AI Integration Perspective,” Nov. 2018, [Online]. Available
.
Pinto, Wang, Roy, Hong, Capozzoli (bib0024) 2022; 5
D. Stoll, J. K. H. Franke, D. Wagner, S. Selg, and F. Hutter, “Hyperparameter Transfer Across Developer Adjustments,” Oct. 2020, [Online]. Available
F. Zhuang et al., “A Comprehensive Survey on Transfer Learning,” Nov. 2019, [Online]. Available
Gross, Buettner, Baumgartl (bib0025) 2022; 10
Q. Zhang, K. Barri, S. K. Babanajad, and A. H. Alavi, “Real-Time Detection of Cracks on Concrete Bridge Decks Using Deep Learning in the Frequency Domain,”
Velarde (bib0003) 2019; 10
V. Badrinarayanan, A. Kendall, and R. Cipolla, “SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation,” Nov. 2015, [Online]. Available
Verma, Tripathi, Pant (bib0028) 2021; 46
Sarker (bib0002) May 2021; 2
R. R. Selvaraju, M. Cogswell, A. Das, R. Vedantam, D. Parikh, and D. Batra, “Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization,” Oct. 2016, doi: 10.1007/s11263-019-01228-7.
Kim (10.1016/j.procs.2023.01.299_bib0022) 2022; 22
Ronneberger (10.1016/j.procs.2023.01.299_bib0010) 2021; 9
Sarker (10.1016/j.procs.2023.01.299_bib0002) 2021; 2
Pinto (10.1016/j.procs.2023.01.299_bib0024) 2022; 5
Velarde (10.1016/j.procs.2023.01.299_bib0003) 2019; 10
10.1016/j.procs.2023.01.299_bib0031
10.1016/j.procs.2023.01.299_bib0032
10.1016/j.procs.2023.01.299_bib0033
Mei (10.1016/j.procs.2023.01.299_bib0007) 2020; 19
10.1016/j.procs.2023.01.299_bib0004
10.1016/j.procs.2023.01.299_bib0026
10.1016/j.procs.2023.01.299_bib0027
Zhu (10.1016/j.procs.2023.01.299_bib0015) 2020; 10
Paullada (10.1016/j.procs.2023.01.299_bib0030) 2021; 2
10.1016/j.procs.2023.01.299_bib0029
Verma (10.1016/j.procs.2023.01.299_bib0028) 2021; 46
Seo (10.1016/j.procs.2023.01.299_bib0001) 2018; 94
Ribani (10.1016/j.procs.2023.01.299_bib0018) 2019
Maguire (10.1016/j.procs.2023.01.299_bib0005) 2018
Rao (10.1016/j.procs.2023.01.299_bib0011) 2021; 20
Liu (10.1016/j.procs.2023.01.299_bib0009) 2019; 104
10.1016/j.procs.2023.01.299_bib0020
Yang (10.1016/j.procs.2023.01.299_bib0006) 2018; 33
10.1016/j.procs.2023.01.299_bib0021
10.1016/j.procs.2023.01.299_bib0034
10.1016/j.procs.2023.01.299_bib0013
Cormen (10.1016/j.procs.2023.01.299_bib0008) 2001
10.1016/j.procs.2023.01.299_bib0017
Qiao (10.1016/j.procs.2023.01.299_bib0014) 2021; 21
Kim (10.1016/j.procs.2023.01.299_bib0016) 2018; 18
Li (10.1016/j.procs.2023.01.299_bib0012) 2019; 34
10.1016/j.procs.2023.01.299_bib0019
Li (10.1016/j.procs.2023.01.299_bib0023) 2020; 407
Gross (10.1016/j.procs.2023.01.299_bib0025) 2022; 10
References_xml – reference: “ON EMPIRICAL COMPARISONS OF OPTIMIZERS FOR DEEP LEARNING.”
– reference: F. Zhuang et al., “A Comprehensive Survey on Transfer Learning,” Nov. 2019, [Online]. Available:
– volume: 2
  year: 2021
  ident: bib0030
  article-title: Data and its (dis)contents: A survey of dataset development and use in machine learning research
  publication-title: Patterns
– reference: R. R. Selvaraju, M. Cogswell, A. Das, R. Vedantam, D. Parikh, and D. Batra, “Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization,” Oct. 2016, doi: 10.1007/s11263-019-01228-7.
– volume: 5
  year: 2022
  ident: bib0024
  article-title: Transfer learning for smart buildings: A critical review of algorithms, applications, and future perspectives
  publication-title: Adv. Appl. Energy
– year: 2001
  ident: bib0008
  article-title: Introduction to algorithms
– reference: Y. Li, S. Xie, X. Chen, P. Dollar, K. He, and R. Girshick, “Benchmarking Detection Transfer Learning with Vision Transformers,” Nov. 2021, [Online]. Available:
– reference: , Nov. 2020, doi: 10.1016/j.eng.2020.07.026.
– reference: J. Plested and T. Gedeon, “Deep transfer learning for image classification: a survey,” May 2022, [Online]. Available:
– reference: J. Deng, W. Dong, R. Socher, L.-J. Li, Kai Li, and Li Fei-Fei, “ImageNet: A large-scale hierarchical image database,” Mar. 2010, pp. 248–255. doi: 10.1109/cvpr.2009.5206848.
– volume: 104
  start-page: 129
  year: 2019
  end-page: 139
  ident: bib0009
  article-title: Computer vision-based concrete crack detection using U-net fully convolutional networks
  publication-title: Autom. Constr.
– volume: 19
  start-page: 1726
  year: 2020
  end-page: 1744
  ident: bib0007
  article-title: Multi-level feature fusion in densely connected deep-learning architecture and depth-first search for crack segmentation on images collected with smartphones
  publication-title: Struct. Heal. Monit.
– year: 2018
  ident: bib0005
  article-title: SDNET2018: A concrete crack image dataset for machine learning applications
– volume: 94
  start-page: 112
  year: 2018
  end-page: 126
  ident: bib0001
  article-title: Drone-enabled bridge inspection methodology and application
  publication-title: Autom. Constr.
– reference: Q. Zhang, K. Barri, S. K. Babanajad, and A. H. Alavi, “Real-Time Detection of Cracks on Concrete Bridge Decks Using Deep Learning in the Frequency Domain,”
– volume: 9
  start-page: 16591
  year: 2021
  end-page: 16603
  ident: bib0010
  article-title: U-Net: Convolutional Networks for Biomedical Image Segmentation
  publication-title: IEEE Access
– reference: R. Girshick, J. Donahue, T. Darrell, and J. Malik, “Rich feature hierarchies for accurate object detection and semantic segmentation Tech report (v5).” [Online]. Available:
– volume: 10
  start-page: 41
  year: 2019
  end-page: 48
  ident: bib0003
  article-title: Artificial Intelligence and its Impact on the Fourth Industrial Revolution: A Review
  publication-title: Int. J. Artif. Intell. Appl.
– start-page: 47
  year: 2019
  end-page: 57
  ident: bib0018
  article-title: A Survey of Transfer Learning for Convolutional Neural Networks
  publication-title: Proceedings - 32nd Conference on Graphics, Patterns and Images Tutorials
– reference: D. Stoll, J. K. H. Franke, D. Wagner, S. Selg, and F. Hutter, “Hyperparameter Transfer Across Developer Adjustments,” Oct. 2020, [Online]. Available:
– volume: 46
  start-page: 11098
  year: 2021
  end-page: 11102
  ident: bib0028
  article-title: Comparison of different optimizers implemented on the deep learning architectures for COVID-19 classification
– volume: 2
  year: May 2021
  ident: bib0002
  article-title: Machine Learning: Algorithms, Real-World Applications and Research Directions
  publication-title: SN Comput. Sci.
– reference: C. Tan, F. Sun, T. Kong, W. Zhang, C. Yang, and C. Liu, “A Survey on Deep Transfer Learning,” Aug. 2018, [Online]. Available:
– reference: Y. Roh, G. Heo, and S. E. Whang, “A Survey on Data Collection for Machine Learning: a Big Data – AI Integration Perspective,” Nov. 2018, [Online]. Available:
– volume: 18
  year: 2018
  ident: bib0016
  article-title: Application of crack identification techniques for an aging concrete bridge inspection using an unmanned aerial vehicle
  publication-title: Sensors (Switzerland)
– volume: 22
  year: 2022
  ident: bib0022
  article-title: Transfer learning for medical image classification: a literature review
  publication-title: BMC Medical Imaging
– reference: .
– volume: 33
  start-page: 1090
  year: 2018
  end-page: 1109
  ident: bib0006
  article-title: Automatic Pixel-Level Crack Detection and Measurement Using Fully Convolutional Network
  publication-title: Comput. Civ. Infrastruct. Eng.
– volume: 10
  start-page: 16977
  year: 2022
  end-page: 16991
  ident: bib0025
  article-title: Benchmarking Transfer Learning Strategies in Time-Series Imaging: Recommendations for Analyzing Raw Sensor Data
  publication-title: IEEE Access
– reference: “LabelImg: Image annotation tool,”
– reference: V. Badrinarayanan, A. Kendall, and R. Cipolla, “SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation,” Nov. 2015, [Online]. Available:
– volume: 407
  start-page: 121
  year: 2020
  end-page: 135
  ident: bib0023
  article-title: A systematic review of deep transfer learning for machinery fault diagnosis
  publication-title: Neurocomputing
– volume: 34
  start-page: 616
  year: 2019
  end-page: 634
  ident: bib0012
  article-title: Automatic pixel-level multiple damage detection of concrete structure using fully convolutional network
  publication-title: Comput. Civ. Infrastruct. Eng.
– volume: 20
  start-page: 2124
  year: 2021
  end-page: 2142
  ident: bib0011
  article-title: Vision-based automated crack detection using convolutional neural networks for condition assessment of infrastructure
  publication-title: Struct. Heal. Monit.
– volume: 21
  start-page: 1
  year: 2021
  end-page: 18
  ident: bib0014
  article-title: Computer vision-based bridge damage detection using deep convolutional networks with expectation maximum attention module
  publication-title: Sensors (Switzerland)
– volume: 10
  year: 2020
  ident: bib0015
  article-title: An intelligent classification model for surface defects on cement concrete bridges
  publication-title: Appl. Sci.
– ident: 10.1016/j.procs.2023.01.299_bib0020
– volume: 10
  issue: 3
  year: 2020
  ident: 10.1016/j.procs.2023.01.299_bib0015
  article-title: An intelligent classification model for surface defects on cement concrete bridges
  publication-title: Appl. Sci.
  doi: 10.3390/app10030972
– volume: 10
  start-page: 41
  issue: 6
  year: 2019
  ident: 10.1016/j.procs.2023.01.299_bib0003
  article-title: Artificial Intelligence and its Impact on the Fourth Industrial Revolution: A Review
  publication-title: Int. J. Artif. Intell. Appl.
– year: 2001
  ident: 10.1016/j.procs.2023.01.299_bib0008
– volume: 2
  issue: 3
  year: 2021
  ident: 10.1016/j.procs.2023.01.299_bib0002
  article-title: Machine Learning: Algorithms, Real-World Applications and Research Directions
  publication-title: SN Comput. Sci.
  doi: 10.1007/s42979-021-00592-x
– volume: 33
  start-page: 1090
  issue: 12
  year: 2018
  ident: 10.1016/j.procs.2023.01.299_bib0006
  article-title: Automatic Pixel-Level Crack Detection and Measurement Using Fully Convolutional Network
  publication-title: Comput. Civ. Infrastruct. Eng.
  doi: 10.1111/mice.12412
– volume: 19
  start-page: 1726
  issue: 6
  year: 2020
  ident: 10.1016/j.procs.2023.01.299_bib0007
  article-title: Multi-level feature fusion in densely connected deep-learning architecture and depth-first search for crack segmentation on images collected with smartphones
  publication-title: Struct. Heal. Monit.
  doi: 10.1177/1475921719896813
– ident: 10.1016/j.procs.2023.01.299_bib0026
– volume: 104
  start-page: 129
  year: 2019
  ident: 10.1016/j.procs.2023.01.299_bib0009
  article-title: Computer vision-based concrete crack detection using U-net fully convolutional networks
  publication-title: Autom. Constr.
  doi: 10.1016/j.autcon.2019.04.005
– volume: 407
  start-page: 121
  year: 2020
  ident: 10.1016/j.procs.2023.01.299_bib0023
  article-title: A systematic review of deep transfer learning for machinery fault diagnosis
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2020.04.045
– volume: 46
  start-page: 11098
  year: 2021
  ident: 10.1016/j.procs.2023.01.299_bib0028
  article-title: Comparison of different optimizers implemented on the deep learning architectures for COVID-19 classification
– volume: 9
  start-page: 16591
  year: 2021
  ident: 10.1016/j.procs.2023.01.299_bib0010
  article-title: U-Net: Convolutional Networks for Biomedical Image Segmentation
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2021.3053408
– volume: 21
  start-page: 1
  issue: 3
  year: 2021
  ident: 10.1016/j.procs.2023.01.299_bib0014
  article-title: Computer vision-based bridge damage detection using deep convolutional networks with expectation maximum attention module
  publication-title: Sensors (Switzerland)
  doi: 10.3390/s21030824
– volume: 34
  start-page: 616
  issue: 7
  year: 2019
  ident: 10.1016/j.procs.2023.01.299_bib0012
  article-title: Automatic pixel-level multiple damage detection of concrete structure using fully convolutional network
  publication-title: Comput. Civ. Infrastruct. Eng.
  doi: 10.1111/mice.12433
– start-page: 47
  year: 2019
  ident: 10.1016/j.procs.2023.01.299_bib0018
  article-title: A Survey of Transfer Learning for Convolutional Neural Networks
– volume: 22
  issue: 1
  year: 2022
  ident: 10.1016/j.procs.2023.01.299_bib0022
  article-title: Transfer learning for medical image classification: a literature review
  publication-title: BMC Medical Imaging
  doi: 10.1186/s12880-022-00793-7
– ident: 10.1016/j.procs.2023.01.299_bib0031
– ident: 10.1016/j.procs.2023.01.299_bib0034
  doi: 10.1109/ICCV.2017.74
– volume: 20
  start-page: 2124
  issue: 4
  year: 2021
  ident: 10.1016/j.procs.2023.01.299_bib0011
  article-title: Vision-based automated crack detection using convolutional neural networks for condition assessment of infrastructure
  publication-title: Struct. Heal. Monit.
  doi: 10.1177/1475921720965445
– ident: 10.1016/j.procs.2023.01.299_bib0004
  doi: 10.1016/j.eng.2020.07.026
– ident: 10.1016/j.procs.2023.01.299_bib0019
  doi: 10.1007/978-3-030-01424-7_27
– ident: 10.1016/j.procs.2023.01.299_bib0027
– volume: 94
  start-page: 112
  year: 2018
  ident: 10.1016/j.procs.2023.01.299_bib0001
  article-title: Drone-enabled bridge inspection methodology and application
  publication-title: Autom. Constr.
  doi: 10.1016/j.autcon.2018.06.006
– volume: 10
  start-page: 16977
  year: 2022
  ident: 10.1016/j.procs.2023.01.299_bib0025
  article-title: Benchmarking Transfer Learning Strategies in Time-Series Imaging: Recommendations for Analyzing Raw Sensor Data
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2022.3148711
– ident: 10.1016/j.procs.2023.01.299_bib0021
– ident: 10.1016/j.procs.2023.01.299_bib0032
– ident: 10.1016/j.procs.2023.01.299_bib0033
  doi: 10.1109/CVPR.2009.5206848
– ident: 10.1016/j.procs.2023.01.299_bib0029
– volume: 5
  year: 2022
  ident: 10.1016/j.procs.2023.01.299_bib0024
  article-title: Transfer learning for smart buildings: A critical review of algorithms, applications, and future perspectives
  publication-title: Adv. Appl. Energy
  doi: 10.1016/j.adapen.2022.100084
– volume: 2
  issue: 11
  year: 2021
  ident: 10.1016/j.procs.2023.01.299_bib0030
  article-title: Data and its (dis)contents: A survey of dataset development and use in machine learning research
  publication-title: Patterns
  doi: 10.1016/j.patter.2021.100336
– volume: 18
  issue: 6
  year: 2018
  ident: 10.1016/j.procs.2023.01.299_bib0016
  article-title: Application of crack identification techniques for an aging concrete bridge inspection using an unmanned aerial vehicle
  publication-title: Sensors (Switzerland)
  doi: 10.3390/s18061881
– year: 2018
  ident: 10.1016/j.procs.2023.01.299_bib0005
– ident: 10.1016/j.procs.2023.01.299_bib0017
– ident: 10.1016/j.procs.2023.01.299_bib0013
SSID ssj0000388917
Score 2.3004365
Snippet Deep learning (DL) is becoming increasingly popular in numerous application fields within the current Fourth Industrial Revolution (4IR) era. This is mainly...
SourceID crossref
elsevier
SourceType Enrichment Source
Index Database
Publisher
StartPage 345
SubjectTerms Benchmarking
Bridge Defects Inspection
Convolutional Neural Networks
Deep Learning
Learning Rate
Objective Function Optimization
Transfer Learning
Title Benchmarking Deep Learning models and hyperparameters for Bridge Defects Classification
URI https://dx.doi.org/10.1016/j.procs.2023.01.299
Volume 219
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 1877-0509
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000388917
  issn: 1877-0509
  databaseCode: M~E
  dateStart: 20100101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lb9NAEF6FwoELb0R5aQ_cwFK9u157j0B5HCBCSgS9WWvvmrRK7ChtqsKB38HPZWYfdmiriB64WIkVrx3P55nd8TffEPJCFJktclsn4P2LROiUJ5UQKtGNTrGu01onx_D1Uz4eFwcH6sto9DvWwpzO87Ytzs7U8r-aGvaBsbF09grm7geFHfAZjA5bMDts_8nwb-BiZgvtcuDgTuwyaqh-921vvCjzDNafK9T9XiAfxokyYKIAi7f2rad4uH6ZyCQajBdmsa66AIDlCOnYE-JlCKR9vmamZ0gWMI4rMOkW-oft884fuvYnhCWXud4_rIYK7Em3PnZz2fG67QYigXuXz11Kd2rni24zUeGriINXLfI8QaEZH3Qu2RdccXSf3plyLzQZ4jL3osIXXL7PPhxhwKlRf51x1GFlSg0RLr7VPxf4ejpiZLodlW6QEgcp99ISBrlGrrM8U0gW_PxryN6hho5y7Zz7_xElrRx58MLFXD7t2ZjKTO-QW2ENQl977NwlI9veI7djfw8a3P198m0TShShRCOUqIcSBSjRc1CiACXqoUQDlOjfUHpAJu_fTd9-TEIjjqRmyIKrmtxKZiwsDcxebpjhsIxvhClUwa0yFavyijeZlpIxI6qsrqWy2iouMw1P_0Oy03atfUSo0k3KBb7Kl1ywFBPZrGbKSGOlFkW6S1i8S2UdNOqxVcq83GKiXfKqP2jpJVq2_1zG21-Gh8PPHktA1LYDH1_tPE_ITfzm03VPyc7Jam2fkRv16cnh8eq5g9MfD_egVQ
linkProvider ISSN International Centre
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=Benchmarking+Deep+Learning+models+and+hyperparameters+for+Bridge+Defects+Classification&rft.jtitle=Procedia+computer+science&rft.au=Shahrabadi%2C+Somayeh&rft.au=Gonzalez%2C+Dibet&rft.au=Sousa%2C+Nuno&rft.au=Ad%C3%A3o%2C+Telmo&rft.date=2023&rft.issn=1877-0509&rft.eissn=1877-0509&rft.volume=219&rft.spage=345&rft.epage=353&rft_id=info:doi/10.1016%2Fj.procs.2023.01.299&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_procs_2023_01_299
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1877-0509&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1877-0509&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1877-0509&client=summon