{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,26]],"date-time":"2026-04-26T09:27:17Z","timestamp":1777195637826,"version":"3.51.4"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T00:00:00Z","timestamp":1755561600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T00:00:00Z","timestamp":1755561600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100004595","name":"Universiti Sains Malaysia","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100004595","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Comp. Appl. Math."],"published-print":{"date-parts":[[2025,12]]},"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>Considering that corrosion is a widespread problem in tropical countries, this study proposes a progressive optimization of EfficientNetV2 for images of corroded objects (corrosion dataset) that can effectively target small and medium-sized corrosion datasets for detection. Compared to other models, the proposed model first adopts EfficientNetV2 as the basic architecture, focusing on the use of only MBConv blocks and MBConv with Fused-MBConv blocks in the hidden layers, as well as the effect of the number of these layers on the model\u2019s classification results. To further improve the performance, this paper attempts to replace the convolutional modules in the input layer with LazyConv, utilizing FReLU and Dy-ReLU as an activation functions in both the input and output layers. The simulation results show that for the medium-sized corrosion dataset in this paper which uses only MBConv blocks for EfficientNetV2 can achieve higher accuracy but lower computational efficiency. Setting a smaller number of layers and replacing the convolutional block in the input layer with LazyConv can significantly reduce the total size of the model and make it more flexible, where the total size of the obtained M2 model being only 58.98\u00a0MB, and capable of automatically determining the number of input channels. Using FReLU in the input and output layers can achieve greater stability, with standard deviations of F1-score and Accuracy under five cycles of only 0.0099 and 0.0126, respectively. In addition, the optimized M2 model also offers advantages in terms of both light weight and stability compared to other classic deep learning models. These findings from this study may serve as a foundation for future innovations in the design of corrosion classification models.<\/jats:p>","DOI":"10.1007\/s40314-025-03382-w","type":"journal-article","created":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T05:44:51Z","timestamp":1755582291000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Progressive optimization of EfficientNetV2 for classification based on images of corroded objects"],"prefix":"10.1007","volume":"44","author":[{"given":"Ziheng","family":"Zhao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Elmi Bin Abu","family":"Bakar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Norizham Bin Abdul","family":"Razak","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohammad Nishat","family":"Akhtar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,8,19]]},"reference":[{"issue":"3","key":"3382_CR1","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1016\/S0951-8339(01)00030-2","volume":"15","author":"UO Akpan","year":"2002","unstructured":"Akpan UO et al (2002) Risk assessment of aging ship hull structures in the presence of corrosion and fatigue. Mar Struct 15(3):211\u2013231. https:\/\/doi.org\/10.1016\/S0951-8339(01)00030-2","journal-title":"Mar Struct"},{"key":"3382_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40537-021-00444-8","volume":"8","author":"L Alzubaidi","year":"2021","unstructured":"Alzubaidi L et al (2021) Review of deep learning: concepts, CNN architectures, challenges, applications, future directions. J Big Data 8:1\u201374. https:\/\/doi.org\/10.1186\/s40537-021-00444-8","journal-title":"J Big Data"},{"issue":"5","key":"3382_CR3","doi-asserted-by":"publisher","first-page":"1110","DOI":"10.1177\/1475921717737051","volume":"17","author":"DJ Atha","year":"2018","unstructured":"Atha DJ, Jahanshahi MR (2018) Evaluation of deep learning approaches based on convolutional neural networks for corrosion detection. Struct Health Monit 17(5):1110\u20131128. https:\/\/doi.org\/10.1177\/1475921717737051","journal-title":"Struct Health Monit"},{"key":"3382_CR4","doi-asserted-by":"publisher","first-page":"10182","DOI":"10.1016\/j.ecoinf.2020.101182","volume":"61","author":"\u00dc Atila","year":"2021","unstructured":"Atila \u00dc et al (2021) Plant leaf disease classification using EfficientNet deep learning model. Ecol Inform 61:10182. https:\/\/doi.org\/10.1016\/j.ecoinf.2020.101182","journal-title":"Ecol Inform"},{"issue":"17","key":"3382_CR5","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics13172746","volume":"13","author":"S Balasubramaniam","year":"2023","unstructured":"Balasubramaniam S et al (2023) A modified LeNet CNN for breast cancer diagnosis in ultrasound images. Diagnostics 13(17):2746. https:\/\/doi.org\/10.3390\/diagnostics13172746","journal-title":"Diagnostics"},{"key":"3382_CR6","doi-asserted-by":"publisher","DOI":"10.1016\/j.ndteint.2019.102134","volume":"107","author":"BT Bastian","year":"2019","unstructured":"Bastian BT et al (2019) Visual inspection and characterization of external corrosion in pipelines using deep neural network. NDT E Int 107:102134. https:\/\/doi.org\/10.1016\/j.ndteint.2019.102134","journal-title":"NDT E Int"},{"key":"3382_CR7","doi-asserted-by":"publisher","unstructured":"Chen Y et al (2020) Dynamic relu. European conference on computer vision. Springer, Cham. https:\/\/doi.org\/10.1007\/978-3-030-58529-7_21","DOI":"10.1007\/978-3-030-58529-7_21"},{"issue":"1","key":"3382_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.corsci.2004.05.007","volume":"47","author":"K-Y Choi","year":"2005","unstructured":"Choi K-Y, Kim SS (2005) Morphological analysis and classification of types of surface corrosion damage by digital image processing. Corros Sci 47(1):1\u201315. https:\/\/doi.org\/10.1016\/j.corsci.2004.05.007","journal-title":"Corros Sci"},{"key":"3382_CR9","doi-asserted-by":"publisher","unstructured":"Cubuk ED et al (2019) Autoaugment: learning augmentation strategies from data. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. https:\/\/doi.org\/10.48550\/arXiv.1805.09501","DOI":"10.48550\/arXiv.1805.09501"},{"key":"3382_CR10","doi-asserted-by":"publisher","unstructured":"Cui J, Li H, Hu Z (2023) Garbage classification algorithm based on improved EfficientNetV2 network. In: Eighth international symposium on advances in electrical, electronics, and computer engineering (ISAEECE 2023), vol 12704. SPIE. https:\/\/doi.org\/10.1117\/12.2680151","DOI":"10.1117\/12.2680151"},{"key":"3382_CR11","doi-asserted-by":"publisher","unstructured":"Dong K et al (2020) MobileNetV2 model for image classification. In: 2020 2nd international conference on information technology and computer application (ITCA). IEEE. https:\/\/doi.org\/10.1109\/ITCA52113.2020.00106","DOI":"10.1109\/ITCA52113.2020.00106"},{"issue":"1","key":"3382_CR12","doi-asserted-by":"publisher","first-page":"188","DOI":"10.3390\/jmse11010188","volume":"11","author":"F Du","year":"2023","unstructured":"Du F, Li C, Wang W (2023) Development of subsea pipeline buckling, corrosion and leakage monitoring. J Mar Sci Eng 11(1):188. https:\/\/doi.org\/10.3390\/jmse11010188","journal-title":"J Mar Sci Eng"},{"key":"3382_CR13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-08236-3","volume-title":"Materials for construction and civil engineering","author":"MC Gon\u00e7alves","year":"2015","unstructured":"Gon\u00e7alves MC, Margarido F (2015) Materials for construction and civil engineering. Springer, Cham. https:\/\/doi.org\/10.1007\/978-3-319-08236-3"},{"key":"3382_CR14","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.109542","volume":"185","author":"E Hassan","year":"2025","unstructured":"Hassan E, Ghadiri H (2025) Advancing brain tumor classification: a robust framework using EfficientNetV2 transfer learning and statistical analysis. Comput Biol Med 185:109542. https:\/\/doi.org\/10.1016\/j.compbiomed.2024.109542","journal-title":"Comput Biol Med"},{"key":"3382_CR15","doi-asserted-by":"publisher","unstructured":"He K et al (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition. https:\/\/doi.org\/10.48550\/arXiv.1512.03385","DOI":"10.48550\/arXiv.1512.03385"},{"key":"3382_CR16","doi-asserted-by":"publisher","unstructured":"Hoang V-T, Jo K-H (2021) Practical analysis on architecture of EfficientNet. In: 2021 14th international conference on human system interaction (HSI). IEEE. https:\/\/doi.org\/10.1109\/HSI52170.2021.9538782","DOI":"10.1109\/HSI52170.2021.9538782"},{"key":"3382_CR17","doi-asserted-by":"publisher","unstructured":"Howard AG (2017) Mobilenets: efficient convolutional neural networks for mobile vision applications. Preprint arXiv:1704.04861. https:\/\/doi.org\/10.48550\/arXiv.1704.04861","DOI":"10.48550\/arXiv.1704.04861"},{"key":"3382_CR18","doi-asserted-by":"publisher","unstructured":"Hu J, Shen L, Sun G (2018) Squeeze-and-excitation networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition. https:\/\/doi.org\/10.48550\/arXiv.1709.01507","DOI":"10.48550\/arXiv.1709.01507"},{"key":"3382_CR19","doi-asserted-by":"publisher","unstructured":"Khan S et al (2018) A guide to convolutional neural networks for computer vision, pp 1\u2013207. https:\/\/doi.org\/10.1007\/978-3-031-01821-3","DOI":"10.1007\/978-3-031-01821-3"},{"key":"3382_CR20","doi-asserted-by":"publisher","DOI":"10.1145\/3065386","author":"A Krizhevsky","year":"2012","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. Adv Neural Inform Process Syst. https:\/\/doi.org\/10.1145\/3065386","journal-title":"Adv Neural Inform Process Syst"},{"key":"3382_CR21","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2024.3464684","author":"M Le","year":"2024","unstructured":"Le M (2024) Detection of corrosion on aircraft structures using an electromagnetic testing sensor and a spiking convolutional neural network. IEEE Sens J. https:\/\/doi.org\/10.1109\/JSEN.2024.3464684","journal-title":"IEEE Sens J"},{"issue":"11","key":"3382_CR22","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun Y et al (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278\u20132324. https:\/\/doi.org\/10.1109\/5.726791","journal-title":"Proc IEEE"},{"issue":"4","key":"3382_CR23","doi-asserted-by":"publisher","DOI":"10.3390\/s21041492","volume":"21","author":"G Li","year":"2021","unstructured":"Li G et al (2021) Practices and applications of convolutional neural network-based computer vision systems in animal farming: a review. Sensors (Basel) 21(4):1492. https:\/\/doi.org\/10.3390\/s21041492","journal-title":"Sensors (Basel)"},{"key":"3382_CR24","doi-asserted-by":"publisher","DOI":"10.1117\/12.2296540","author":"Y Ma","year":"2018","unstructured":"Ma Y et al (2018) Image-based corrosion recognition for ship steel structures. Smart Struct NDE Ind 40. https:\/\/doi.org\/10.1117\/12.2296540","journal-title":"Smart Struct NDE Ind 4.0"},{"key":"3382_CR25","doi-asserted-by":"publisher","unstructured":"Ma N, Zhang X, Sun J (2020) Funnel activation for visual recognition. In: Computer vision-ECCV 2020: 16th European conference, Glasgow, UK, August 23\u201328, 2020, proceedings, part XI 16. Springer. https:\/\/doi.org\/10.1007\/978-3-030-58621-8_21","DOI":"10.1007\/978-3-030-58621-8_21"},{"key":"3382_CR26","doi-asserted-by":"publisher","first-page":"387","DOI":"10.1016\/j.jlp.2015.02.004","volume":"35","author":"R Murata","year":"2015","unstructured":"Murata R, Benaquisto J, Storey C (2015) A methodology for identifying and addressing dead-legs and corrosion issues in a process hazard analysis (PHA). J Loss Prev Process Ind 35:387\u2013392. https:\/\/doi.org\/10.1016\/j.jlp.2015.02.004","journal-title":"J Loss Prev Process Ind"},{"key":"3382_CR27","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2024.112008","volume":"164","author":"OA Oyedeji","year":"2024","unstructured":"Oyedeji OA, Khan S, Erkoyuncu JA (2024) Application of CNN for multiple phase corrosion identification and region detection. Appl Soft Comput 164:112008. https:\/\/doi.org\/10.1016\/j.asoc.2024.112008","journal-title":"Appl Soft Comput"},{"key":"3382_CR28","doi-asserted-by":"publisher","unstructured":"Sandler M et al (2018) Mobilenetv2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE conference on computer vision and pattern recognition. https:\/\/doi.org\/10.48550\/arXiv.1801.04381","DOI":"10.48550\/arXiv.1801.04381"},{"key":"3382_CR29","doi-asserted-by":"publisher","unstructured":"Sifre L, Mallat S (2014) Rigid-motion scattering for texture classification. Preprint arXiv:1403.1687. https:\/\/doi.org\/10.48550\/arXiv.1403.1687","DOI":"10.48550\/arXiv.1403.1687"},{"key":"3382_CR30","doi-asserted-by":"publisher","unstructured":"Tan M, Le Q (2019) Efficientnet: rethinking model scaling for convolutional neural networks. In: International conference on machine learning. PMLR. https:\/\/doi.org\/10.48550\/arXiv.1905.11946","DOI":"10.48550\/arXiv.1905.11946"},{"key":"3382_CR31","doi-asserted-by":"publisher","unstructured":"Tan M, Le Q (2021) Efficientnetv2: smaller models and faster training. In: International conference on machine learning. PMLR. https:\/\/doi.org\/10.48550\/arXiv.2104.00298","DOI":"10.48550\/arXiv.2104.00298"},{"key":"3382_CR32","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6501\/ac7034","author":"Y Wang","year":"2022","unstructured":"Wang Y et al (2022) Corrosion grade recognition for weathering steel plate based on a convolutional neural network. Meas Sci Technol. https:\/\/doi.org\/10.1088\/1361-6501\/ac7034","journal-title":"Meas Sci Technol"},{"key":"3382_CR33","doi-asserted-by":"publisher","unstructured":"Zhang A et al (2021) Dive into deep learning. Preprint arXiv:2106.11342. https:\/\/doi.org\/10.48550\/arXiv.2106.11342","DOI":"10.48550\/arXiv.2106.11342"},{"key":"3382_CR34","unstructured":"Zulfikar Setyo Priyambudi (2023) Corrosion classification dataset. Roboflow universe. https:\/\/universe.roboflow.com\/zulfikar-setyo-priyambudi-hgsff\/corrosion-classification-trvmp"}],"container-title":["Computational and Applied Mathematics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40314-025-03382-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s40314-025-03382-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40314-025-03382-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T11:15:59Z","timestamp":1760440559000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s40314-025-03382-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,19]]},"references-count":34,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["3382"],"URL":"https:\/\/doi.org\/10.1007\/s40314-025-03382-w","relation":{},"ISSN":["2238-3603","1807-0302"],"issn-type":[{"value":"2238-3603","type":"print"},{"value":"1807-0302","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,19]]},"assertion":[{"value":"21 March 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 July 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 August 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 August 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"419"}}