A Scalable AIoT-Based Decision Support System for Real-Time Pavement Distress Identification in Urban Information Technology Infrastructure
DOI:
https://doi.org/10.51903/hz3hfh21Keywords:
AIoT, Decision Support System, Deep Learning, Pavement Distress, Smart City, YOLOv8Abstract
Urban road infrastructure faces escalating deterioration due to inadequate real-time monitoring, driving demand for automated pavement distress detection within smart city frameworks. This study proposes a scalable Artificial Intelligence of Things (AIoT) decision support system (DSS) for real-time pavement distress identification. A mixed-methods experimental design integrates A quantitative experimental design that integrates a YOLOv8-based deep learning model deployed on Raspberry Pi 4B edge nodes with MQTT-based cloud communication and a municipal management dashboard. A dataset of 12,400 labeled pavement images aggregated from RDD2022, CrackForest, and field collection was used for training and evaluation across six distress classes. The system achieved a classification accuracy of 92.4%, macro F1-score of 0.89, and [email protected] of 0.87, with an end-to-end latency of 412 ms, surpassing the 500 ms real-time threshold. System reliability was confirmed with Cohen’s κ = 0.87 and ICC = 0.91. Results demonstrate the viability of a fully integrated AIoT architecture for transitioning municipal maintenance from reactive to proactive strategies. The proposed framework provides a replicable blueprint for embedding AI-driven decision support into urban IT infrastructure governance.
References
[1] N. J. Owor, Y. Adu-Gyamfi, A. Aboah, and M. Amo-Boateng, "PaveSAM – segment anything for pavement distress," Road Mater. Pavement Des., vol. 26, pp. 593–617, 2024.
[2] M. Amândio, M. Parente, J. Neves, and P. Fonseca, "Integration of smart pavement data with decision support systems: A systematic review," Buildings, vol. 11, no. 12, p. 579, 2021.
[3] E. Ranyal, A. Sadhu, and K. Jain, "Road condition monitoring using smart sensing and artificial intelligence: A review," Sensors, vol. 22, 2022.
[4] M. M. Topu, M. A. Anik, and M. M. Ahsan, "Digital twin-driven pavement health monitoring and maintenance optimization using graph neural networks," ArXiv, abs/2511.02957, 2025.
[5] N. V. Sankar, Y.-T. Huang, and M. Jahanshahi, "AI-enabled road condition monitoring: A scalable and affordable approach," Proc. 15th Int. Workshop Structural Health Monit., 2025.
[6] B. Benmhahe and J. Chentoufi, "Automated pavement distress detection, classification and measurement: A review," Int. J. Adv. Comput. Sci. Appl., 2021.
[7] Z. Ye, Y. Wei, S. Yang, P. Li, F. Yang, B. Yang, and L. Wang, "IoT-enhanced smart road infrastructure systems for comprehensive real-time monitoring," Internet Things Cyber-Phys. Syst., 2024.
[8] I. Aburqaq, S. Naimi, S. Saedi, and M. Shahin, "Assessment of UAV usage for flexible pavement inspection using GCPs: Case study on Palestinian urban road," Sustainability, 2025.
[9] S. Cano-Ortiz, P. Pascual-Muñoz, and D. Castro-Fresno, "Machine learning algorithms for monitoring pavement performance," Autom. Constr., 2022.
[10] M. Moradi and G. Assaf, "Designing and building an intelligent pavement management system for urban road networks," Sustainability, 2023.
[11] S. Xu, K. Zhao, J. Loney, Z. Li, and A. Visentin, "Image-based large language model approach to road pavement monitoring," Comput.-Aided Civil Infrastruct. Eng., vol. 40, pp. 4448–4464, 2025.
[12] Z. Lv, Z. Hao, Y. Zhu, and C. Lu, "A review on automated detection and identification algorithms for highway pavement distress," Appl. Sci., 2025.
[13] S. Alqaydi, W. Zeiada, A. E. Wakil, A. Alnaqbi, and A. Azam, "A comprehensive review of smartphone and other device-based techniques for road surface monitoring," Eng, 2024.
[14] S. Youwai, A. Chaiyaphat, and P. Chaipetch, "YOLO9tr: A lightweight model for pavement damage detection utilizing a generalized efficient layer aggregation network and attention mechanism," J. Real-Time Image Process., vol. 21, 2024.
[15] L. L. Huang, J.-D. Lin, W.-H. Huang, C.-H. Kuo, and M.-Y. Huang, "Application of automated pavement inspection technology in provincial highway pavement maintenance decision-making," Appl. Sci., 2024.
[16] M. Khan, R. Harseno, S.-H. Kee, and A. A. Nahid, "Development of AI- and robotics-assisted automated pavement-crack-evaluation system," Remote Sens., vol. 15, p. 3573, 2023.
[17] T. García-Segura, L. Montalbán-Domingo, D. Llopis-Castelló, A. Sanz-Benlloch, and E. Pellicer, "Integration of deep learning techniques and sustainability-based concepts into an urban pavement management system," Expert Syst. Appl., vol. 231, p. 120851, 2023.
[18] A. R. Sugiarto, G. N. Abdi, I. Sadidan, M. R. Fitrianto, and F. Ramadhani, "Road condition monitoring with drones and LiDAR in infrastructure technology," Semesta Teknika, 2025.
[19] E. Ibragimov, Y. Kim, J. H. Lee, J. Cho, and J.-J. Lee, "Automated pavement condition index assessment with deep learning and image analysis: An end-to-end approach," Sensors, vol. 24, 2024.
[20] A. R. M. Forkan, Y. Kang, F. Martí, A. Banerjee, C. McCarthy, H. Ghaderi, B. G. S. Costa, A. Dawod, D. Georgakopoulos, and P. Jayaraman, "AIoT-CitySense: AI and IoT-driven city-scale sensing for roadside infrastructure maintenance," Data Sci. Eng., pp. 1–15, 2023.
[21] M. Hijji, R. Iqbal, A. K. Pandey, F. Doctor, C. Karyotis, W. Rajeh, A. Alshehri, and F. Aradah, "6G connected vehicle framework to support intelligent road maintenance using deep learning data fusion," IEEE Trans. Intell. Transp. Syst., vol. 24, pp. 7726–7735, 2023.
[22] S. T. Matarneh, F. Elghaish, D. Edwards, F. Rahimian, E. Abdellatef, and O. Ejohwomu, "Automatic crack classification on asphalt pavement surfaces using convolutional neural networks and transfer learning," J. Inf. Technol. Constr., vol. 29, pp. 1239–1256, 2024.
[23] F. Liu, J. Liu, and L. Wang, "Deep learning and infrared thermography for asphalt pavement crack severity classification," Autom. Constr., 2022.
[24] S. Pawar, D. Jadhav, M. P. Lokhande, P. Raskar, and M. Patil, "Evaluation of quality of service parameters for MQTT communication in IoT application by using deep neural network," Int. J. Inf. Technol., pp. 1–14, 2023.
[25] T. Haryanti, N. A. Rakhmawati, and A. P. Subriadi, "Measuring the digital transformation maturity level independently with the design science research methodology," Syst. Eng., vol. 27, pp. 159–176, 2023.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Imanuel Natan Natan, Dani Sasmoko Sasmoko, Samsul Arifin (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
