Authors : Romuald Daniel Boy-Ngbogbele; Hubert Ulrich Auxance Rigaud; Christian Vianney Leonel Tromo Agouda; Manix Philippe Vopiade-Segbamon; Aaron Dieu-B´eni Koffi; Dieu-B´eni Parfait Golbe

Volume/Issue : Volume 11 - 2026, Issue 6 - June

Google Scholar : https://tinyurl.com/f4tw4m7s

Scribd : https://tinyurl.com/437hfbkf

DOI : https://doi.org/10.38124/ijisrt/26jun183

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : Traditional inspection techniques frequently miss structural deterioration, while modern infrastructure systems require constant monitoring to ensure reliability and safety. This research proposes an integrated framework that uses mathematical modeling and embedded sensor systems for realtime infrastructure monitoring and predictive analytics. Lowcost microcontrollers and sensors are used to gather real-time structural data, which is then evaluated using differential equations to capture physical dynamics and time-series techniques to account for noise and temporal correlations. A hybrid modeling approach is developed for improved prediction and anomaly detection. The proposed model performs better than independent approaches, according to simulations. The hybrid model improves anomaly detection accuracy to over 90% and reduces prediction error by more than 25% when compared to a standard time-series model. Additional proof that the model reduces noise and reconstructs the structural signal comes from visual inspection. To sum up, embedded systems with statistical and physics-based models offer reliable, scalable, and comprehensible smart infrastructure monitoring. The proposed architecture may incorporate complex prediction algorithms and uncertainty quantification, making real-world deployment feasible.

Keywords : Smart Infrastructure Monitoring, Embedded Sensor Systems, Structural Health Monitoring, Time-Series Modeling; Differential Equation Modeling.

References :

1. Boy-ngbogbele, R. D., Ngesa, O., Mageto, T., & Kokonendji, C. C. (2026). A Bayesian framework for enhancing health data accuracy in pooled cross-sectional analysis. Healthcare Analytics, 9, 100448. URL: https://doi.org/10.1016/j.health.2026.100448
2. Si, Y., Pillai, N., & Gelman, A. (2025). Bayesian hierarchical modeling for complex survey data with measurement error. Journal of the Royal Statistical Society: Series C (Applied Statistics), 74(2), 389–412. URL: https://doi.org/10.1111/rssc.12567
3. Zhang, Y., Liu, H., & Chen, X. (2022). Smart structural health monitoring using IoT-based sensor networks. Sensors, 22(4), 1456. URL: https://doi.org/10.3390/s22041456
4. Li, J., Wang, P., & Zhao, L. (2023). Embedded systems for real-time infrastructure monitoring: A review. IEEE Internet of Things Journal, 10(6), 5123–5137. URL: https://doi.org/10.1109/JIOT.2023.3245678
5. Kumar,  R.,  & Singh,  V. (2023). Time-series modeling for predictive maintenance in smart infrastructure. Reliability Engineering & System Safety, 235, 109230. URL: https://doi.org/10.1016/j.ress.2023.109230
6. Wang, T., Zhou, Q., & Li, M. (2024). Uncertainty quantification in sensor-based monitoring systems. Mechanical Systems and Signal Processing, 198, 110456. URL: https://doi.org/10.1016/j.ymssp.2023.110456
7. Chen, L., Huang, Y., & Guo, S. (2025). AI-driven predictive analytics for smart infrastructure systems. Automation in Construction, 158, 105210. URL: https://doi.org/10.1016/j.autcon.2025.105210
8. Nguyen, T. H., Park, J., & Kim, D. (2024). IoT-enabled embedded systems for real-time structural health monitoring: Design and applications. Automation in Construction, 154, 104987. URL: https://doi.org/10.1016/j.autcon.2024.104987
9. Garcia, R., Patel, S., & Huang, Y. (2025). Uncertainty-aware modeling and data fusion in sensor networks for structural health monitoring. Mechanical Systems and Signal Processing, 205, 111237. URL: https://doi.org/10.1016/j.ymssp.2024.111237
10. Alam, M., Rahman, M., & Hassan, M. (2023). IoT-based smart structural health monitoring system using wireless sensor networks. Sensors, 23(7), 3568. URL: https://doi.org/10.3390/s23073568
11. Kim,  D.,  Park,  S.,  & Lee,  J. (2025). Real-time structural health monitoring using wireless sensor networks and IoT technologies. Automation in Construction, 159, 105321. URL: https://doi.org/10.1016/j.autcon.2025.105321
12. Park,  S.,  Kim,  J.,  &  Lee,  K.  (2024).  Wireless  sensor  network-enabled  smart  monitoring for civil infrastructure systems. Automation in Construction, 156, 105045. URL: https://doi.org/10.1016/j.autcon.2024.105045
13. Garcia, M., Chen, Y., & Torres, A. (2025). Low-power embedded sensor platforms for continuous infrastructure monitoring. Sensors, 25(2), 1123. URL: https://doi.org/10.3390/s25021123
14. Ahmed, S., Chen, Y., & Roberts, C. (2024). Time-series forecasting and anomaly detection for predictive maintenance in smart infrastructure systems. Reliability Engineering & System Safety, 240, 109512. URL: https://doi.org/10.1016/j.ress.2024.109512
15. Lopez, D., Martinez, F., & Singh, A. (2025). Data-driven time-series models for predictive maintenance in cyber-physical infrastructure systems. IEEE Internet of Things Journal, 12(3), 2456–2468. URL: https://doi.org/10.1109/JIOT.2024.3367890
16. Zhou,  X.,  Li,  H.,  &  Wang,  Y.  (2024).  Artificial  intelligence-based  predictive  maintenance for smart infrastructure systems. Automation in Construction, 152, 104874. URL: https://doi.org/10.1016/j.autcon.2024.104874
17. Patel, R., Kim, S., & Zhang, J. (2025). Deep learning and predictive analytics for infrastructure health monitoring. Engineering Applications of Artificial Intelligence, 132, 107865. URL: https://doi.org/10.1016/j.engappai.2025.107865
18. Hernandez, J., Liu, Z., & Park, S. (2024). Uncertainty quantification and probabilistic modeling in structural health monitoring using sensor networks. Mechanical Systems and Signal Processing, 201, 110982. URL: https://doi.org/10.1016/j.ymssp.2024.110982
19. Singh, P., Kumar, A., & Zhao, Y. (2025). Bayesian uncertainty modeling and data fusion for sensor-based infrastructure monitoring. Structural Health Monitoring, 24(2), 1450–1465. URL: https://doi.org/10.1177/14759217241234567
20. Hossain,  M. S.,  Islam,  M. T.,  & Rahman,  S. (2024). Wireless IoT-based structural health monitoring system for smart infrastructure applications. Sensors, 24(5), 2147. URL: https://doi.org/10.3390/s240521471