{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,24]],"date-time":"2026-10-24T01:49:55Z","timestamp":1792806595857,"version":"4.5.0"},"reference-count":59,"publisher":"MDPI AG","issue":"22","license":[{"start":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T00:00:00Z","timestamp":1763510400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Universiti Putra Malaysia IPM Grant","award":["9730500"],"award-info":[{"award-number":["9730500"]}],"id":[{"id":"https:\/\/ror.org\/02e91jd64","id-type":"ROR","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100016152","name":"Yayasan Universiti Teknologi PETRONAS","doi-asserted-by":"publisher","award":["YUTP-FRG-015LC0-474"],"award-info":[{"award-number":["YUTP-FRG-015LC0-474"]}],"id":[{"id":"10.13039\/501100016152","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Corrosion in metallic materials is a critical challenge in maintenance and safety, and traditional visual inspection methods are often time-consuming, labor-intensive, and dependent on human expertise, highlighting the need for more efficient and reliable solutions. Deep learning, particularly convolutional neural networks (CNNs), provides a promising approach by enabling automated and accurate image-based classification. This study investigates binary image classification of corrosion using four pre-trained CNN architectures, namely ResNet50, MobileNetV2, NASNetMobile, and EfficientNetV2B0, and integrates explainable artificial intelligence (XAI) techniques to provide interpretability and insight into each model\u2019s decision-making process. A curated dataset of 4012 images, divided between corroded and non-corroded surfaces, was pre-processed, and augmented images resulted in a total of 9636 images used to train and evaluate the models. Performance was assessed through accuracy, confusion matrices, computational timing, receiver operating characteristic curves, precision\u2013recall curves, and Cohen\u2019s Kappa. In this paper, Gradient-weighted Class Activation Mapping (Grad-CAM) visualizations are incorporated as an XAI technique to provide interpretable insight into the model\u2019s reasoning process, enabling clear identification of corrosion regions and offering justification for each prediction produced by the system. A key contribution of this work is the integration of Grad-CAM to enhance explainability. The results showed that EfficientNetV2B0 demonstrates stable training with minimal sign overfitting compared to other models. MobileNetV2 achieved the lowest time to train with the datasets given, and ResNet50 achieved the highest classification performance in terms of confusion matrix, with an accuracy of 96.58%. Through Grad-CAM reasoning, EfficientNetV2B0 shows a specific high activation towards corroded regions compared to the other three models that were evaluated.<\/jats:p>","DOI":"10.3390\/s25227070","type":"journal-article","created":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T10:30:59Z","timestamp":1763634659000},"page":"7070","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Explainable Deep Learning Framework for Binary Corrosion Image Classification Using Grad-CAM"],"prefix":"10.3390","volume":"25","author":[{"given":"Muhammad Amir Imran","family":"Aminudin","sequence":"first","affiliation":[{"name":"Department of Aerospace Engineering, Faculty of Engineering, Universiti Putra Malaysia, Serdang 43400, Malaysia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8498-1560","authenticated-orcid":false,"given":"Mohd Na\u2019im","family":"Abdullah","sequence":"additional","affiliation":[{"name":"Department of Aerospace Engineering, Faculty of Engineering, Universiti Putra Malaysia, Serdang 43400, Malaysia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0191-1653","authenticated-orcid":false,"given":"Faizal","family":"Mustapha","sequence":"additional","affiliation":[{"name":"Department of Aerospace Engineering, Faculty of Engineering, Universiti Putra Malaysia, Serdang 43400, Malaysia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kee Kok","family":"Eng","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, Universiti Teknologi PETRONAS, Seri Iskandar 32610, Malaysia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mazli","family":"Mustapha","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, Universiti Teknologi PETRONAS, Seri Iskandar 32610, Malaysia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7195-5128","authenticated-orcid":false,"given":"Aliyu","family":"Mustapha","sequence":"additional","affiliation":[{"name":"Industrial and Technology Education Department, Federal University of Technology, Minna P.M.B 65, Nigeria"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,11,19]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"485","DOI":"10.4028\/www.scientific.net\/MSF.877.485","article-title":"Corrosion of aluminium aerospace alloys","volume":"877","author":"Staley","year":"2017","journal-title":"Mater. Sci. Forum"},{"key":"ref_2","first-page":"3","article-title":"Corrosion prediction in the oil industry using deep learning techniques","volume":"4","author":"Abdulsadda","year":"2024","journal-title":"Int. J. Robot. Control Syst."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Malashin, I., Tynchenko, V., Nelyub, V., Borodulin, A., Gantimurov, A., Krysko, N.V., and Galinovsky, A. (2024). Deep learning approach for pitting corrosion detection in gas pipelines. Sensors, 24.","DOI":"10.3390\/s24113563"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Do\u011fru, A., Bouarfa, S., Arizar, R., and Aydo\u011fan, R. (2020). Using convolutional neural networks to automate aircraft maintenance visual inspection. Aerospace, 7.","DOI":"10.20944\/preprints202011.0527.v1"},{"key":"ref_5","first-page":"633","article-title":"Color space models hybrid algorithmic for intelligent fire and smoke detection in aircraft cabin","volume":"57","author":"Abdullah","year":"2025","journal-title":"J. Aeronaut. Astronaut. Aviat."},{"key":"ref_6","unstructured":"Goodfellow, I., Bengio, Y., Courville, A., and Bengio, Y. (2016). Deep Learning, MIT Press."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Abdullah Salem, B.T.S., Abdullah, M.N.I., Mustapha, F., Kanirai, N.S.A., and Mustapha, M. (2025). Vibration analysis using multi-layer perceptron neural networks for rotor imbalance detection in quadrotor UAV. Drones, 9.","DOI":"10.3390\/drones9020102"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"030006","DOI":"10.1063\/5.0186367","article-title":"Hybrid model for detection of corrosion in petroleum pipeline images using CNN and comparing accuracy with SVM","volume":"Volume 2816","author":"Reddy","year":"2024","journal-title":"Proceedings of the AIP Conference Proceedings"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"35572","DOI":"10.1109\/JSEN.2024.3464684","article-title":"Detection of corrosion on aircraft structures using an electromagnetic testing sensor and a spiking convolutional neural network","volume":"24","author":"Le","year":"2024","journal-title":"IEEE Sens. J."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"100617","DOI":"10.1016\/j.ijnaoe.2024.100617","article-title":"Corrosion area detection and depth prediction using machine learning","volume":"16","author":"Son","year":"2024","journal-title":"Int. J. Nav. Archit. Ocean Eng."},{"key":"ref_11","first-page":"17","article-title":"Corrosion image classification method based on EfficientNetV2","volume":"10","author":"Zhao","year":"2024","journal-title":"Heliyon"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Huang, X., Duan, Z., Hao, S., Hou, J., Chen, W., and Cai, L. (2025). A deep learning framework for corrosion assessment of steel structures using Inception v3 model. Buildings, 15.","DOI":"10.3390\/buildings15040512"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1797","DOI":"10.1080\/10589759.2024.2360052","article-title":"Hidden corrosion detection in aircraft structures with a lightweight magnetic convolutional neural network","volume":"40","author":"Vu","year":"2025","journal-title":"Nondestruct. Test. Eval."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"2745","DOI":"10.1109\/JSTARS.2022.3158281","article-title":"A spectral-spatial feature extraction method with polydirectional CNN for multispectral image compression","volume":"15","author":"Kong","year":"2022","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"112008","DOI":"10.1016\/j.asoc.2024.112008","article-title":"Application of CNN for multiple phase corrosion identification and region detection","volume":"164","author":"Oyedeji","year":"2024","journal-title":"Appl. Soft Comput."},{"key":"ref_16","first-page":"2587","article-title":"A deep learning approach to industrial corrosion detection","volume":"81","author":"Farooqui","year":"2024","journal-title":"Comput. Mater. Contin."},{"key":"ref_17","unstructured":"Burton, B., Nash, W.T., and Birbilis, N. (2022). RustSEG\u2014Automated segmentation of corrosion using deep learning. arXiv."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Rajendran, M., and Subbian, D. (2025). Deep learning in corrosion assessment and control: A critical review of techniques and challenges. Corros. Rev.","DOI":"10.1515\/corrrev-2024-0060"},{"key":"ref_19","unstructured":"(2025, October 17). masters2022. Corrosion-Classification-v2 Dataset [Open Source Dataset]. Available online: https:\/\/universe.roboflow.com\/masters2022\/corrosion-classification-v2."},{"key":"ref_20","unstructured":"Priyambudi, Z.S. (2025, October 18). Corrosion Classification Dataset [Open Source Dataset]. Available online: https:\/\/universe.roboflow.com\/zulfikar-setyo-priyambudi-hgsff\/corrosion-classification-trvmp."},{"key":"ref_21","unstructured":"Ebrahim, O. (2025, October 18). Marine Corrosion Dataset [Open Source Dataset]. Available online: https:\/\/www.kaggle.com\/datasets\/ebrahim007\/marine-corrosion-dataset."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Talebi, H., and Milanfar, P. (2021, January 11\u201317). Learning to resize images for computer vision tasks. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Montreal, QC, Canada.","DOI":"10.1109\/ICCV48922.2021.00055"},{"key":"ref_23","first-page":"269","article-title":"Enhancing the accuracy of image classification using deep learning and preprocessing methods","volume":"3","author":"Yousif","year":"2023","journal-title":"Artif. Intell. Robot. Dev. J."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"86","DOI":"10.3846\/aviation.2023.18923","article-title":"Digitalization in aircraft maintenance processes","volume":"27","author":"Alomar","year":"2023","journal-title":"Aviation"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Ogundokun, R.O., Li, A., Babatunde, R.S., Umezuruike, C., Sadiku, P.O., Abdulahi, A.T., and Babatunde, A.N. (2023). Enhancing skin cancer detection and classification in dermoscopic images through concatenated MobileNetV2 and Xception models. Bioengineering, 10.","DOI":"10.3390\/bioengineering10080979"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"3815","DOI":"10.1080\/10589759.2024.2410386","article-title":"Lightning damage assessment on solar panels using in-house portable infrared thermography camera with convolutional neural network (CNN) algorithm","volume":"40","author":"Chandrasegaran","year":"2025","journal-title":"Nondestruct. Test. Eval."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Zhang, L., Bian, Y., Jiang, P., and Zhang, F. (2023). A transfer residual neural network based on ResNet-50 for detection of steel surface defects. Appl. Sci., 13.","DOI":"10.3390\/app13095260"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"1569","DOI":"10.1007\/s00521-022-07700-9","article-title":"Fully automatic CNN design with inception and ResNet blocks","volume":"35","author":"Barakbayeva","year":"2023","journal-title":"Neural Comput. Appl."},{"key":"ref_30","first-page":"4","article-title":"Mobile skin disease classification using MobileNetV2 and NASNetMobile","volume":"13","author":"Hestiningsiha","year":"2023","journal-title":"Int. J. Adv. Sci. Eng. Inf. Technol."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"101244","DOI":"10.1016\/j.imu.2023.101244","article-title":"A mobile application based on efficient lightweight CNN model for classification of B-ALL cancer from non-cancerous cells: A design and implementation study","volume":"39","author":"Hosseini","year":"2023","journal-title":"Inform. Med. Unlocked"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Panchumarthy, R., and Benala, T.R. (2025). An overview of AI workload optimization techniques. Boosting Software Development Using Machine Learning, Springer.","DOI":"10.1007\/978-3-031-88188-6_12"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"184119","DOI":"10.1109\/ACCESS.2024.3503413","article-title":"Hybrid deep learning EfficientNetV2 and vision transformer (EffNetV2-ViT) model for breast cancer histopathological image classification","volume":"12","author":"Hayat","year":"2024","journal-title":"IEEE Access"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"38513","DOI":"10.1007\/s11042-022-13157-8","article-title":"Low-res MobileNet: An efficient lightweight network for low-resolution image classification in resource-constrained scenarios","volume":"81","author":"Yuan","year":"2022","journal-title":"Multimed. Tools Appl."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1016\/j.neunet.2020.12.022","article-title":"Quantization friendly MobileNet (QF-MobileNet) architecture for vision-based applications on embedded platforms","volume":"136","author":"Kulkarni","year":"2021","journal-title":"Neural Netw."},{"key":"ref_36","first-page":"485","article-title":"Combining MobileNetV1 and depthwise separable convolution bottleneck with expansion for classifying the freshness of fish eyes","volume":"9","author":"Prasetyo","year":"2022","journal-title":"Inf. Process. Agric."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Molendijk, M.J., de Putter, F.A.M., and Corporaal, H. (2023). Low- and mixed-precision inference accelerators. Embedded Machine Learning for Cyber-Physical, IoT, and Edge Computing: Hardware Architectures, Springer.","DOI":"10.1007\/978-3-031-19568-6_3"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"427","DOI":"10.1016\/j.ipm.2009.03.002","article-title":"A systematic analysis of performance measures for classification tasks","volume":"45","author":"Sokolova","year":"2009","journal-title":"Inf. Process. Manag."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Wardhani, N.W.S., Rochayani, M.Y., Iriany, A., Sulistyono, A.D., and Lestantyo, P. (2019, January 23\u201324). Cross-validation metrics for evaluating classification performance on imbalanced data. Proceedings of the 2019 International Conference on Computer, Control, Informatics and Its Applications (IC3INA), Tangerang, Indonesia.","DOI":"10.1109\/IC3INA48034.2019.8949568"},{"key":"ref_40","first-page":"10","article-title":"A comparative visualization analysis of neural network models using GraD-CAM","volume":"1","author":"Shen","year":"2024","journal-title":"Sci. Technol. Eng. Chem. Environ. Prot."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., and Torralba, A. (2015). Learning deep features for discriminative localization. arXiv.","DOI":"10.1109\/CVPR.2016.319"},{"key":"ref_42","unstructured":"Soladoye, A.A., Adeyanju, I.A., Omodunbi, B.A., and Sobowale, A.A. (2024, January 9). Online Nigerian languages word-level character recognition using deep transfer learning (short paper). Proceedings of the ICCBR Workshops, Salamanca, Spain."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Gondhalekar, G., Bathala, N.K., Merugu, N.B., Joshi, N., and Kumari, P.L. (2024, January 22\u201323). Enhancing Image Classification Performance Through Transfer Learning and Adaptive Augmentation: A MobileNetV2 Approach. Proceedings of the 3rd International Conference on Optimization Techniques in the Field of Engineering (ICOFE-2024), Tamilnadu, India.","DOI":"10.2139\/ssrn.5082255"},{"key":"ref_44","first-page":"4402","article-title":"Real time multi-scale facial mask detection and classification using deep transfer learning techniques","volume":"9","author":"Addagarla","year":"2020","journal-title":"Int. J."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"4023","DOI":"10.53555\/AJBR.v27i4S.4345","article-title":"Confusion matrix-based performance evaluation metrics","volume":"27","author":"Sathyanarayanan","year":"2024","journal-title":"Afr. J. Biomed. Res."},{"key":"ref_46","first-page":"572","article-title":"Automated detection of COVID-19 from CT scan using convolutional neural network. Biocybern","volume":"41","author":"Mishra","year":"2021","journal-title":"Biomed. Eng."},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Jadhav, D., Patayeet, S., Salunkhe, P., Pujari, S., Sakharkar, M., and Zanje, S. (2025, January 25\u201327). BirdClassifier: An advanced bird classification model using deep neural networks. Proceedings of the 2025 International Conference on Inventive Computation Technologies (ICICT), Tamil Nadu, India.","DOI":"10.1109\/ICICT64420.2025.11004874"},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"81","DOI":"10.57152\/predatecs.v2i2.1608","article-title":"Comparative analysis of weather image classification using CNN algorithm with InceptionV3, DenseNet169 and NASNetMobile architecture models","volume":"2","author":"Wulandari","year":"2025","journal-title":"Public Res. J. Eng. Data Technol. Comput. Sci."},{"key":"ref_49","unstructured":"Ghoury, S., Sungur, C., and Durdu, A. (2019, January 24\u201326). Real-time diseases detection of grape and grape leaves using faster R-CNN and SSD MobileNet architectures. Proceedings of the International Conference on Advanced Technologies, Computer Engineering and Science (ICATCES 2019), Safranbolu, Turkey."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"1266","DOI":"10.1016\/j.mfglet.2025.06.146","article-title":"Performance evaluation of CNN models for steel surface defect detection in lean manufacturing","volume":"44","author":"Hosseinzadeh","year":"2025","journal-title":"Manuf. Lett."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"1073","DOI":"10.1007\/s42452-025-07732-5","article-title":"Aluminum profile surface defect detection system integrating deep learning and industrial internet of things","volume":"7","author":"Che","year":"2025","journal-title":"Discov. Appl. Sci."},{"key":"ref_52","doi-asserted-by":"crossref","unstructured":"Das, A., Dorafshan, S., and Kaabouch, N. (2024). Autonomous image-based corrosion detection in steel structures using deep learning. Sensors, 24.","DOI":"10.3390\/s24113630"},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1016\/j.knosys.2019.03.016","article-title":"Automated identification and grading system of diabetic retinopathy using deep neural networks","volume":"175","author":"Zhang","year":"2019","journal-title":"Knowl.-Based Syst."},{"key":"ref_54","doi-asserted-by":"crossref","unstructured":"Genc, S., Akpinar, K.N., and Karagol, S. (2020, January 26\u201328). Automated abnormality classification of chest radiographs using MobileNetV2. Proceedings of the 2020 International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA), Ankara, Turkey.","DOI":"10.1109\/HORA49412.2020.9152607"},{"key":"ref_55","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Long, C., Shang, W., Si, Z., Liu, Z., Feng, Z., and Zuo, Y. (2024). A composite scaling network of EfficientNet for improving spatial domain identification performance. Commun. Biol., 7.","DOI":"10.1038\/s42003-024-07286-z"},{"key":"ref_56","doi-asserted-by":"crossref","unstructured":"Walid, M.A.A., Mollick, S., Shill, P.C., Baowaly, M.K., Islam, M.R., Ahamad, M.M., and Samad, M.A. (2023). Adapted deep ensemble learning-based voting classifier for osteosarcoma cancer classification. Diagnostics, 13.","DOI":"10.3390\/diagnostics13193155"},{"key":"ref_57","unstructured":"Rajpurkar, P., Irvin, J., Zhu, K., Yang, B., Mehta, H., Duan, T., and Ng, A.Y. (2017). CheXNet: Radiologist-level pneumonia detection on chest X-rays with deep learning. arXiv."},{"key":"ref_58","unstructured":"Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., and Adam, H. (2017). MobileNets: Efficient convolutional neural networks for mobile vision applications. arXiv."},{"key":"ref_59","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., and Chen, L.C. (2018, January 18\u201322). MobileNetV2: Inverted residuals and linear bottlenecks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00474"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/25\/22\/7070\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T10:36:22Z","timestamp":1763634982000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/25\/22\/7070"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,19]]},"references-count":59,"journal-issue":{"issue":"22","published-online":{"date-parts":[[2025,11]]}},"alternative-id":["s25227070"],"URL":"https:\/\/doi.org\/10.3390\/s25227070","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,19]]}}}