Optimizing Civil Infrastructure Predictions Using Hybrid Feature Selection and Advanced Machine Learning Models
DOI:
https://doi.org/10.64137/XXXXXXXX/IJCSEI-V1I1P105Keywords:
Civil infrastructure monitoring, Structural health monitoring, Feature selection, Machine learning, Hybrid approach, Predictive modeling, Random forest, XGBoost, LASSO, Sensor data analytics, Ensemble learning, Smart infrastructureAbstract
As civil infrastructure systems have become more complicated and technology progresses, the amount of high-dimensional data has grown significantly. For effective maintenance, lowering risks and safe structures, meaningful insights must be obtained from large amounts of data. This research puts forward a way to blend feature selection with advanced ML to make infrastructure predictions more accurate and efficient. The suggested method applies filter, wrapper and embedded feature selection techniques, including IG, RFE, Random Forest importance and LASSO regularization to reduce the number of variables without losing the important ones. The evaluation procedure was performed using actual structural monitoring data from sensors, taking into account over 200 parameters associated with stress, displacement, vibration and various conditions. Training and evaluation of Random Forest, XGBoost, Support Vector Regression and deep neural networks was carried out under various feature selection scenarios. Tests found that the combination of methods improved the RMSE by 12% and cut the training time needed by up to 30%. Ensemble models using hybrid-selected features always achieved higher accuracy than those using all features. Data from engineering projects with many features underscores that joining experience in the field with data analysis leads to stronger infrastructure predictions
References
[1] Khan, M. W., Saad, S., Ammad, S., Rasheed, K., & Jamal, Q. (2024). Smart Infrastructure and AI. In AI in Material Science (pp. 193-215). CRC Press.
[2] Mondal, T. G., & Chen, G. (2022). Artificial intelligence in civil infrastructure health monitoring—Historical perspectives, current trends, and future visions. Frontiers in Built Environment, 8, 1007886.
[3] Brownlee, J. (2019). How to choose a feature selection method for machine learning. Machine Learning Mastery, 10, 1-7.
[4] Gangani, C. M. (2023). Role of machine learning in optimizing IT infrastructure. Kuwait Journal of Information Technology and Decision Sciences, 1(1), 12-22.
[5] Seow, J. H., & Rajaharia, N. K. (2023, March). Artificial Intelligence in Information Technology Infrastructure Management and Support in Singapore. In Sustainability, Economics, Innovation, Globalisation and Organisational Psychology Conference (pp. 447-471). Singapore: Springer Nature Singapore.
[6] Mishra, S., Tiwary, D., Ohri, A., & Agnihotri, A. K. (2018). Assessment of groundwater quality using WQI and GIS near the Karsara municipal landfill site, Varanasi, India. Arabian Journal of Geosciences, 11, 1-9.
[7] Deogun, J. S., Choubey, S. K., Raghavan, V. V., & Sever, H. (1998). Feature selection and effective classifiers. Journal of the American Society for Information Science, 49(5), 423-434.
[8] Chughtai, F., & Zayed, T. (2008). Infrastructure condition prediction models for sustainable sewer pipelines. Journal of Performance of Constructed Facilities, 22(5), 333-341.
[9] Visalakshi, S., & Radha, V. (2014, December). A literature review of feature selection techniques and applications: Review of feature selection in data mining. In 2014 IEEE international conference on computational intelligence and computing research (pp. 1-6). IEEE.
[10] Bocca, F. F., & Rodrigues, L. H. A. (2016). The effect of tuning, feature engineering, and feature selection in data mining applied to rainfed sugarcane yield modelling. Computers and electronics in agriculture, 128, 67-76.
[11] Dowling, C. P. (2019). Applications of Statistical and Machine Learning to Civil Infrastructure (Doctoral dissertation).
[12] Tang, S., He, B., Yu, C., Li, Y., & Li, K. (2020). A survey on spark ecosystem: Big data processing infrastructure, machine learning, and applications. IEEE Transactions on Knowledge and Data Engineering, 34(1), 71-91.
[13] Jurado, S., Nebot, À., Mugica, F., & Avellana, N. (2015). Hybrid methodologies for electricity load forecasting: Entropy-based feature selection with machine learning and soft computing techniques. Energy, 86, 276-291.
[14] Abdel-salam, M., Kumar, N., & Mahajan, S. (2024). A proposed framework for crop yield prediction using hybrid feature selection approach and optimized machine learning. Neural Computing and Applications, 36(33), 20723-20750.
[15] Jaafaru, H., & Agbelie, B. (2022). Bridge maintenance planning framework using machine learning, multi-criteria decision analysis and evolutionary optimization models. Automation in Construction, 143, 104585.
[16] Agarwal S. “Multi-Modal Deep Learning for Unified Search-Recommendation Systems in Hybrid Content Platforms”. IJAIBDCMS [International Journal of AI, BigData, Computational and Management Studies]. 2025 May 30 [cited 2025 Jun. 4]; 4(3):30-39. Available from: https://ijaibdcms.org/index.php/ijaibdcms/article/view/154
[17] Pulivarthy, P. (2023). Enhancing Dynamic Behaviour in Vehicular Ad Hoc Networks through Game Theory and Machine Learning for Reliable Routing. International Journal of Machine Learning and Artificial Intelligence, 4(4), 1-13.
[18] Praveen Kumar Maroju, "Optimizing Mortgage Loan Processing in Capital Markets: A Machine Learning Approach, " International Journal of Innovations in Scientific Engineering, 17(1), PP. 36-55 , April 2023.
[19] Animesh Kumar, “Redefining Finance: The Influence of Artificial Intelligence (AI) and Machine Learning (ML)”, Transactions on Engineering and Computing Sciences, 12(4), 59-69. 2024.
[20] Advancing Energy Management in Hybrid Electric Vehicles (HEVs) and Hybrid Energy Storage System Electric Vehicles (HESS EVs): A Hybrid Fuzzy Logic Approach - Sree Lakshmi Vineetha Bitragunta - IJSAT Volume 15, Issue 3, July-September 2024, PP-1-12, DOI 10.71097/IJSAT.v15.i3.2261.
[21] C. C. Marella and A. Palakurti, “Harnessing Python for AI and machine learning: Techniques, tools, and green solutions,” In Advances in Environmental Engineering and Green Technologies, IGI Global, 2025, pp. 237–250
[22] Kirti Vasdev (2024).” Spatial Data Clustering and Pattern Recognition Using Machine Learning”. International Journal for Multidisciplinary Research (IJFMR).6(1). PP. 1-6. DOI: https://www.ijfmr.com/papers/2024/1/23474
[23] Susmith Barigidad. “Edge-Optimized Facial Emotion Recognition: A High-Performance Hybrid Mobilenetv2-Vit Model". IJAIBDCMS [International JournalofAI,BigData,ComputationalandManagement Studies]. 2025 Apr. 3 [cited 2025 Jun. 4]; 6(2):PP. 1-10.
[24] Puneet Aggarwal, Amit Aggarwal. "Future-Proofing SAP HANA With Hybrid Cloud Architecture: Achieving Agility, Compliance, And Cost Efficiency", International Journal Of Science And Research, 13 (3), 1930-1937, 2024.
[25] S. Gupta, S. Barigidad, S. Hussain, S. Dubey and S. Kanaujia, "Hybrid Machine Learning for Feature-Based Spam Detection," 2025 2nd International Conference on Computational Intelligence, Communication Technology and Networking (CICTN), Ghaziabad, India, 2025, pp. 801-806, doi: 10.1109/CICTN64563.2025.10932459.
[26] Optimizing Boost Converter and Cascaded Inverter Performance in PV Systems with Hybrid PI-Fuzzy Logic Control - Sree Lakshmi Vineetha. B, Muthukumar. P - IJSAT Volume 11, Issue 1, January-March 2020,PP-1-9,DOI 10.5281/zenodo.14473918
[27] Multiconnected Interleaved Boost Converter for Hybrid Energy System, Sree Lakshmi Vineetha Bitragunta, International Journal Of Scientific Research In Engineering And Management (Ijsrem), Volume: 08 Issue: 03 | March – 2024, PP-1-9.
[28] Patel, Bhavikkumar; Mallisetty, Harikrishna; and Rao, Kolati Mallikarjuna, "Artificial Intelligence Helper Application for Delivering Effective Presentations", Technical Disclosure Commons, (January 04, 2024) https://www.tdcommons.org/dpubs_series/6572
[29] Dr. Priya. A., Dr. Charles Arockiasamy J., “The Global Reach of AI: A Postcolonial Analysis of Technological Dominance,” International Journal of Scientific Research in Science and Technology, 11(2), 1-5, 2025.
