IoT/Big Data with advanced analytic tools in the construction industry: Studies in climate-improved concrete

Data analytic techniques uncover patterns from raw data and extract valuable insights for making informed decisions.

Machine Learning (ML) provides optimum mathematical methods for extracting meaningful features from data and binning the data into meaningful patterns that can be utilized for decision making, assessment, and forecasting.

Today, IoT data with ML-integrated smart analytic tools have been gradually adopted in other sectors but are not fully implemented in the construction industry.

By virtue of the preceding works, we have IoT/Big Data regarding multiple aspects of concrete properties of the hardening process for optimization in hand.

Therefore, we are in a unique and advantageous position that enables us to study data analytic tools applicable for the construction (and concrete) industry for decision-making on selecting the optimal measures considering the impacts on the environment and its trade-offs.

In this project, we will learn how the construction (and concrete) industry could make benefit from using IoT/Big Data in combination with advanced analytic tools.

The outcome will lead us to the next phase, where we obtain new insights about the performance of new climate-improved concrete types that have been otherwise “hidden” or “undiscovered” by traditional analytic methods.

Two concrete-related cases on which we aim to apply the data-driven analytic methods are, namely, Case 1) Drying out of climate-improved concrete and Case 2) Temperature and strength development of climate-improved concrete types in civil engineering projects