| Title |
Analysis and Prediction of Quantity Takeoff in Reinforced Concrete Apartments Using Open-source Machine Learning Techniques |
| DOI |
https://doi.org/10.5659/JAIK.2024.40.5.183 |
| Keywords |
Reinforced Concrete; Apartment; Quantity Takeoff; Prediction; Open-source; Machine Learning |
| Abstract |
Accurate analysis and prediction of Quantity Takeoff (QTO) is crucial for construction project success, enabling efficient resource
management, cost and time savings, quality improvement, and project continuity. However, current QTO methods rely on manual labor,
posing challenges in productivity and accuracy due to the dependence on workers' experience and skills. This study utilizes an open-source
machine learning-based data analysis tool to analyze major QTO components such as reinforcement, concrete, and formwork in a previously
executed apartment project. By integrating fundamental project information applicable in the early stages, a predictive model capable of
estimating major quantities based on various situational variable combinations was proposed and its reliability was validated. |