Construction data preparation framework using fuzzy approach

Most research works in simulating construction operations have predominantly focused on modeling and mistreated data preparation that is paramount for modeling, simulation, and knowledge discovery. A 60% of time goes into preparing data for mining; however, actual mining step typically constitutes about 10% of the overall effort. In order to prepare data for mining or knowledge discovery, a knowledge discovery system is indispensable in extracting hidden knowledge from construction data sets. The presented research develops, using Fuzzy approach, a framework for data preparation of construction processes when predicting work task durations. It consists of three stages: data identification, processing and knowledge management. Data identification stage recognizes qualitative and quantitative variables that affect a construction process. Data processing stage consists of cleaning, integrating, transforming, and selecting the appropriate knowledge. Knowledge management includes modeling and validating data. The developed framework is tested using a construction case study in which the results found satisfactory with an efficiency of 11.5%. The developed framework will guide construction model builders to enhance the modeling and knowledge discovery process by improving data quality and modeling the relation of qualitative and quantitative variables on process durations.