Abstract
Due to stochastic occurrence of surface defects in a structure, size of acquired image datasets may vary for cracked and un-cracked classes. Further, in crack detection and classification, among misclassified predictions, while, false-positives can be particularly important that can provide added safety factor to the structural health monitoring system to adopt early preventive measures, false negatives can result in an overconfident health monitoring system thereby seriously affecting the durability of a structure. In this study, the authors aimed to address these two problems, by transfer learning five pre-trained deep convolution neural network (DCNN) models on the same target dataset using binary focal loss and evaluated the models’ performance in comparison to the binary cross-entropy loss function. Five model sets each consisting twenty four variations have been generated by varying the dropout and loss function parameters, from which the best performing model has been proposed. The influence of the focussing parameter, γ on the model accuracy has also been investigated. Finally, three independent test datasets are used to evaluate the generalization capacity of the proposed model under optimal thresholds which yielded in appreciable metrics outcome.
Similar content being viewed by others
References
Lu X, Guan H, Sun H et al (2021) A preliminary analysis and discussion of the condominium building collapse in surfside, Florida, US, June 24, 2021. Front Struct Civ Eng. https://doi.org/10.1007/s11709-021-0766-0
Mumbai building that collapsed was 100 years old—Dongri building collapse|The Economic Times. https://economictimes.indiatimes.com/news/politics-and-nation/mumbai-building-that-collapsed-was-100-years-old/dongri-building-collapse/slideshow/70255878.cms. Accessed 31 Oct 2021
Pierre M, Johnson M. Report of the Commission of inquiry into the collapse of a portion of the de la Concorde overpass. http://cip.management.dal.ca/publications/report_eng%20concorde%20overpass%20montreal.pdf
Krizhevsky A, Sutskever I, Hinton GE (2012) ImageNet classification with deep convolutional neural networks. In: NIPS’12: Proceedings of the 25th International Conference on Neural Information Processing Systems 1:1097–1105. https://doi.org/10.1145/3065386
Makantasis K, Protopapadakis E, Doulamis A et al (2015) Deep Convolutional Neural Networks for efficient vision based tunnel inspection. In: Proceedings—2015 IEEE 11th International Conference on Intelligent Computer Communication and Processing, ICCP 2015 335–342. https://doi.org/10.1109/ICCP.2015.7312681
Zhang L, Yang F, Daniel Zhang Y, Zhu YJ (2016) Road crack detection using deep convolutional neural network. In: Proceedings—International Conference on Image Processing, ICIP. IEEE Computer Society, pp 3708–3712
Kumar A, Kim J, Lyndon D et al (2017) An ensemble of fine-tuned convolutional neural networks for medical image classification. IEEE J Biomed Health Inform 21:31–40. https://doi.org/10.1109/JBHI.2016.2635663
Dorafshan S, Thomas RJ, Maguire M (2018) Comparison of deep convolutional neural networks and edge detectors for image-based crack detection in concrete. Constr Build Mater 186:1031–1045. https://doi.org/10.1016/j.conbuildmat.2018.08.011
Dung CV, Anh LD (2019) Autonomous concrete crack detection using deep fully convolutional neural network. Autom Constr 99:52–58. https://doi.org/10.1016/j.autcon.2018.11.028
Feng C, Zhang H, Wang S et al (2019) Structural damage detection using deep convolutional neural network and transfer learning. KSCE J Civ Eng 23:4493–4502. https://doi.org/10.1007/s12205-019-0437-z
Su C, Wang W (2020) Concrete cracks detection using convolutional neural network based on transfer learning. Math Probl Eng. https://doi.org/10.1155/2020/7240129
Ali L, Alnajjar F, Al JH et al (2021) Performance evaluation of deep CNN-based crack detection and localization techniques for concrete structures. Sensors 21:1–22. https://doi.org/10.3390/s21051688
Kim B, Yuvaraj N, Sri Preethaa KR, Arun Pandian R (2021) Surface crack detection using deep learning with shallow CNN architecture for enhanced computation. Neural Comput Appl. https://doi.org/10.1007/s00521-021-05690-8
Lin TY, Goyal P, Girshick R et al (2020) Focal loss for dense object detection. IEEE Trans Pattern Anal Mach Intell 42:318–327. https://doi.org/10.1109/TPAMI.2018.2858826
Dorafshan S, Thomas RJ, Maguire M (2018) SDNET2018: An annotated image dataset for non-contact concrete crack detection using deep convolutional neural networks. Data Brief 21:1664–1668. https://doi.org/10.1016/j.dib.2018.11.015
Özgenel CF (2018) Concrete Crack Images for Classification. In: 15 Jan. https://data.mendeley.com/datasets/5y9wdsg2zt/2. Accessed 10 Jun 2021
Keras Applications. https://keras.io/api/applications/#inceptionresnetv2. Accessed 24 Jul 2021
Chollet F (2018) Deep learning with Python, Manning
Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. In: 3rd International Conference on Learning Representations, ICLR 2015—Conference Track Proceedings pp 1–14
Szegedy C, Liu W, Jia Y et al (2015) Going deeper with convolutions. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition 07–12 June, pp 1–9. https://doi.org/10.1109/CVPR.2015.7298594
Chollet F (2017) Xception: deep learning with depth wise separable convolutions. In: Proceedings—30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017. Institute of Electrical and Electronics Engineers Inc., pp 1800–1807
He K, Zhang X, Ren S, Sun J (2017) Deep residual learning for image recognition. Multimed Tools Appl. https://doi.org/10.1007/s11042-017-4440-4
Szegedy C, Ioffe S, Vanhoucke V, Alemi AA (2017) Inception-v4, inception-ResNet and the impact of residual connections on learning. In: 31st AAAI Conference on Artificial Intelligence, AAAI 2017, pp 4278–4284
Tan M, Le QV (2019) EfficientNet: Rethinking model scaling for convolutional neural networks. In: 36th International Conference on Machine Learning, ICML 2019. International Machine Learning Society (IMLS), pp 10691–10700
Zhou B, Khosla A, Lapedriza A et al (2016) Learning Deep Features for Discriminative Localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp 2921–2929 2004. https://doi.org/10.5465/ambpp.2004.13862426
Hinton GE, Srivastava N, Krizhevsky A et al (2012) Improving neural networks by preventing co-adaptation of feature detectors, pp 1–18. arXiv:1207.0580v1 [cs.NE]. https://doi.org/10.48550/arXiv.1207.0580
Ruder S. An overview of gradient descent optimization algorithms. arXiv:1609.04747v2 [cs.LG]. https://doi.org/10.48550/arXiv.1609.04747
Losses. https://keras.io/api/losses/. Accessed 9 Nov 2021
Accuracy metrics. https://keras.io/api/metrics/accuracy_metrics/#accuracy-class. Accessed 9 Nov 2021
Ziegel E (2005) Introduction to robust estimation and hypothesis testing, 2nd ed
Diez P (2018) Introduction. Smart wheelchairs and brain-computer interfaces: mobile assistive technologies. Elsevier, pp 1–21. https://doi.org/10.1016/B978-0-12-812892-3.00001-7
Japkowicz N, Shah M (2011) Evaluating learning algorithms: a classification perspective. Cambridge University Press. https://doi.org/10.1017/CBO9780511921803
Sasaki Y (2007) The truth of the f-measure. https://www.cs.odu.edu/mukka/cs795sum09dm/Lecturenotes/Day3/F-measure-YS-26Oct07.pdf. Accessed 26 May 2021
Chicco D, Jurman G (2020) The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation. BMC Genomics 21:1–13. https://doi.org/10.1186/s12864-019-6413-7
Kubat M, Holte RC, Matwin S (1998) Machine learning for the detection of oil spills in satellite radar images. Mach Learn 30:195–215. https://doi.org/10.1023/A:1007452223027
Youden Index—an overview|ScienceDirect Topics. https://www.sciencedirect.com/topics/medicine-and-dentistry/youden-index. Accessed 18 Aug 2021
Provost F (2000) Machine learning from imbalanced data sets 101. In: Proceedings of the AAAI’2000 Workshop on … 3
Zhou ZH, Liu XY (2006) Training cost-sensitive neural networks with methods addressing the class imbalance problem. IEEE Trans Knowl Data Eng 18:63–77. https://doi.org/10.1109/TKDE.2006.17
Shi Y, Cui L, Qi Z et al (2016) Automatic road crack detection using random structured forests. IEEE Trans Intell Transp Syst 17:3434–3445. https://doi.org/10.1109/TITS.2016.2552248
Saito T, Rehmsmeier M (2015) The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets. PLoS ONE. https://doi.org/10.1371/journal.pone.0118432
12. Precision-Recall and Receiver Operating Characteristic Curves—Data Science Topics 0.0.1 documentation. https://datascience.oneoffcoder.com/precision-recall-roc.html#Interpretation-of-area-under-the-curve-(AUC) Accessed 15 Nov 2021
Funding
The authors declare that no funds, grants, or other support were received during the preparation of this manuscript.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
On behalf of all authors, the corresponding author states that there is no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Debroy, S., Sil, A. An apposite transfer-learned DCNN model for prediction of structural surface cracks under optimal threshold for class-imbalanced data. J Build Rehabil 7, 83 (2022). https://doi.org/10.1007/s41024-022-00226-6
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s41024-022-00226-6