2023 · Machine Learning
Applications of ML/IoT in Concrete Technology
Machine Learning IoT Civil Engineering
Applications of ML/IoT in Concrete Technology
BITS Pilani | May 2023 – Dec 2023
Python Random Forest XGBoost IoT Sensors Springer Publication
Published in Springer's "Advances in Data-Driven Computing and Intelligent Systems"
Project Overview
Conducted comprehensive study on machine learning and IoT applications for concrete strength prediction and quality monitoring in civil engineering applications.
Key Contributions
Literature Synthesis: Synthesized 50+ peer-reviewed papers on ML-based concrete compressive strength prediction, identifying Random Forest and XGBoost as top-performing models (R² up to 0.89)
IoT Integration Framework: Proposed IoT sensor integration framework for real-time curing environment monitoring, enabling dynamic strength estimation
Sustainability Analysis: Evaluated ML approaches for optimizing supplementary cementitious materials (SCMs) usage, projecting 15% cement reduction with maintained structural integrity
Technologies Used
- Languages: Python
- ML Models: Random Forest, XGBoost, SVR
- IoT: Sensor Integration Framework
- Domain: Concrete Technology, Materials Science
Key Results
| Metric | Value |
|---|---|
| Papers Synthesized | 50+ |
| Best Model R² | 0.89 |
| Cement Reduction Potential | 15% |
| Publication Venue | Springer |
Publication
Shrivastava, N., et al. (2024). “Advances in ML/IoT for Sustainable Concrete Technology.” In Advances in Data-Driven Computing and Intelligent Systems, Springer Singapore.