Citation :

Ida Barkiah, Nurul Fathanah Mustamin, Yuslena Sari, Ayuddin, Amry Dasar, Muhammad Tommy Maulidyanto, "A Machine Learning Model Based on MobileNet V2 and IGOA-XGBoost for Structural Health Monitoring," International Journal of Civil Engineering, vol. 13, no. 5, pp. 260-267, 2026. Crossref, https://doi.org/10.14445/23488352/IJCE-V13I5P117

Abstract

Monitoring the structural health of infrastructure such as buildings, bridges, and roads requires efficient and accurate crack detection methods. This research proposes the integration of MobileNet V2 for concrete crack image feature extraction with the Improved Grasshopper Optimization Algorithm (IGOA) and XGBoost for classification. MobileNet V2 was chosen for its efficiency in feature extraction, while IGOA was implemented to optimize the hyperparameters of XGBoost, improving classification performance. The dataset used includes 40,000 concrete crack images with a proportion of 70% training data and 30% test data. The experimental results show that the IGOA-XGBoost method provides the best performance with 99.75% accuracy, 99.80% precision, 99.70% recall, and 99.75% F1-score. The advantage of this method lies in IGOA's adaptive metaheuristic optimization mechanism, which balances exploration and exploitation in the search for optimal hyperparameters. This research proves the potential integration of MobileNet V2 and IGOA-XGBoost as an effective solution for an accurate and efficient machine learning-based crack detection system, supporting the development of real-world structural health monitoring systems.

Keywords

Concrete Crack Classification, Feature Extraction, Hyperparameter Optimization, IGOA-XGBoost, MobileNet V2.

References

1. Mohammad Shahin et al., “Improving the Concrete Crack Detection Process via a Hybrid Visual Transformer Algorithm,” Sensors, vol. 24, no. 10, pp. 1-32, 2024.
   [CrossRef] [Google Scholar] [Publisher Link]
2. Fujie Yang, “Enhancing Concrete Crack Image Detection Using MobileNetV2 and Transfer Learning,” Frontiers in Science and Engineering, vol. 4, no. 4, pp. 110-119, 2024.
   [CrossRef] [Google Scholar] [Publisher Link]
3. Hatice Catal Reis, and Kourosh Khoshelham, “ReCRNet: A Deep Residual Network for Crack Detection in Historical Buildings,” Arabian Journal of Geosciences, vol. 14, 2021.
   [CrossRef] [Google Scholar] [Publisher Link]
4. Chunzheng Zhang et al., “Res-FPN–SqueezeNet Segmentation Architecture for Enhanced Identification of Concrete Cracks within a Deep-Learning Framework,” Journal of Computing in Civil Engineering, vol. 39, no. 5, 2025.
   [CrossRef] [Google Scholar] [Publisher Link]
5. Miao Su et al., “Utilizing Pretrained Convolutional Neural Networks for Crack Detection and Geometric Feature Recognition in Concrete Surface Images,” Journal of Building Engineering, vol. 98, 2024.
   [CrossRef] [Google Scholar] [Publisher Link]
6. Ali Mayya et al., “Efficient Hybrid Ensembles of CNNs and Transfer Learning Models for Bridge Deck Image-Based Crack Detection,” Structures, vol. 64, 2024.
   [CrossRef] [Google Scholar] [Publisher Link]
7. Li Guo, Runze Li, and Bin Jiang, “A Cascade Broad Neural Network for Concrete Structural Crack Damage Automated Classification,” IEEE Transactions on Industrial Informatics, vol. 17, no. 4, pp. 2737-2742, 2021.
   [CrossRef] [Google Scholar] [Publisher Link]
8. Ganesh Kolappan Geetha, and Sung-Han Sim, “Fast Identification of Concrete Cracks using 1D Deep Learning and Explainable Artificial Intelligence-Based Analysis,” Automation in Construction, vol. 143, 2022.
   [CrossRef] [Google Scholar] [Publisher Link]
9. Lijie Zhao et al., “Transfer Learning and Multi-Level Image Processing for Crack Classification and Quantitative Measurement in Concrete Structures Under Complex Contexts,” Structures, vol. 80, 2025.
   [CrossRef] [Google Scholar] [Publisher Link]
10. MobileNet, MobileNetV2, and MobileNetV3, Keras 3 API Documentation, 2024. [Online]. Available: https://keras.io/api/applications/mobilenet/
11. Nuwan Madusanka et al., “Impact of H&E Stain Normalization on Deep Learning Models in Cancer Image Classification: Performance, Complexity, and Trade-Offs,” Cancers, vol. 15, no. 16, pp. 1-17, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
12. Sergio Saponara, and Abdussalam Elhanashi, “Impact of Image Resizing on Deep Learning Detectors for Training Time and Model Performance,” Applications in Electronics Pervading Industry, Environment and Society, vol. 866, pp. 10-17, 2022.
    [CrossRef] [Google Scholar] [Publisher Link]
13. Andrea Cina et al., “Comparing Image Normalization Techniques in an End-to-End Model for Automated Modic Changes Classification from MRI Images,” Brain and Spine, vol. 4, pp. 1-6, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
14. Florian June, Optimization Algorithm: From SGD to Adam, Medium, 2023. [Online]. Available: https://medium.com/@florian_algo/optimization-algorithm-from-sgd-to-adam-50ea22187951
15. Eman M.G. Younis et al., “A Hybrid Deep Learning Model with Data Augmentation to Improve Tumor Classification Using MRI Images,” Diagnostics, vol. 14, no. 23, pp. 1-14, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
16. Wenguan Wang, Jianbing Shen, and Haibin Ling, “A Deep Network Solution for Attention and Aesthetics Aware Photo Cropping,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 41, no. 7, pp. 1531-1544, 2019.
    [CrossRef] [Google Scholar] [Publisher Link]
17. Muneeb A. Khan, Heemin Park, and Jinseok Chae, “A Lightweight Convolutional Neural Network (CNN) Architecture for Traffic Sign Recognition in Urban Road Networks,” Electronics, vol. 12, no. 8, pp. 1-18, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
18. Liquan Zhao et al., “A Lightweight Deep Neural Network with Higher Accuracy,” PLoS One, vol. 17, no. 8 2022.
    [CrossRef] [Google Scholar] [Publisher Link]
19. Zeravan Arif Ali et al., “Exploring the Power of eXtreme Gradient Boosting Algorithm in Machine Learning: a Review,” Academic Journal of Nawroz University (AJNU), vol. 12, no. 2, pp. 320-334, 2023.
    [Google Scholar] [Publisher Link]
20. Shangkun Deng et al., “Stock Price Crash Warning in the Chinese Security Market Using a Machine Learning-Based Method and Financial Indicators,” Systems, vol. 10, no. 4, pp. 1-25, 2022.
    [CrossRef] [Google Scholar] [Publisher Link]
21. Vimal Rathakrishnan, Salmia Beddu, and Ali Najah Ahmed, “Comparison Studies Between Machine Learning Optimisation Techniques on Predicting Concrete Compressive Strength,” Research Square, pp. 1-54, 2021.
    [CrossRef] [Google Scholar] [Publisher Link]
22. Adil Mehdary et al., “Hyperparameter Optimization with Genetic Algorithms and XGBoost: A Step Forward in Smart Grid Fraud Detection,” Sensors, vol. 24, no. 4, pp. 1-24, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
23. Peng Qin, Hongping Hu, and Zhengmin Yang, “The Improved Grasshopper Optimization Algorithm and its Applications,” Scientific Reports, vol. 11, pp. 1-14, 2021.
    [CrossRef] [Google Scholar] [Publisher Link]
24. Wei Liu et al., “A Multi-Strategy Improved Grasshopper Optimization Algorithm for Solving Global Optimization and Engineering Problems,” International Journal of Computational Intelligence Systems, vol. 17, pp. 1-28, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
25. Çağlar Fırat Özgenel, Concrete Crack Images for Classification, Kaggle, 2019. [Online]. Available:  https://www.kaggle.com/datasets/arnavr10880/concrete-crack-images-for-classification
26. Mark Sandler et al., MobileNetV2: Inverted Residuals and Linear Bottlenecks, [Online]. Available: https://openaccess.thecvf.com/content_cvpr_2018/papers/Sandler_MobileNetV2_Inverted_Residuals_CVPR_2018_paper.pdf