Using Statistical Models and Machine Learning Techniques to Process Big Data from the Forth Road Bridge

A comparative analysis of machine learning techniques revealed that Random Forest outperforms traditional Artificial Neural Networks in predicting strain data from the Forth Road Bridge's Structural Health Monitoring (SHM) system. This study leveraged Principal Component Analysis (PCA) to reduce dataset dimensionality, thereby optimizing computational efficiency, and employed Autoregressive Integrated Moving Average (ARIMA) models for traffic volume predictions. The findings underscore the potential of Random Forest in damage detection and structural response prediction, offering a robust framework for assessing bridge integrity using big data from SHM systems.

Xu, D., Chong, H., Main, I., Mineter, M., De Bold, R., Forde, M. C., Gair, C., Madden, P., Angus, E., & Ho, C. (2019). Using Statistical Models and Machine Learning Techniques to Process Big Data from the Forth Road Bridge. International Conference on Smart Infrastructure and Construction 2019 (ICSIC), 411–419. https://doi.org/10.1680/icsic.64669.411