Hide/Show Apps

AI-based predictive modeling for safety assessment in construction industry

Ayhan, Bilal Umut
The predictive modeling is a popular research area among the researchers. Most of the proposed models cannot provide a solution for the needs of every contractor as the existing ones served for only a specific task. Therefore, using these systems become inevitably burden on contractors due to its difficulty of use. The thesis aims to provide an AI-based safety assessment strategy for every project. The assessment strategy encapsulated the detection of trends in safety failures and corrective actions to prevent them. The study covered two parts. The first part explained a hybrid model of ANN and Fuzzy Set Theory, based on over 17,000 incident cases. The ANN model achieved to forecast 84% incident within 90% confidence, and integrating the fuzzy inference system increased the prediction performance slightly. The second part introduced the use of LCCA as a Big Data analytics to address the heterogeneity problem. Although the model employed around 5,000 cases for training, the prediction performance was quite similar to the first part. Besides, this part included a comparison of CBR and ANN to reveal which approach demonstrated better compliance with the incident data. Results exhibited the inclusion of big data analytic improved the prediction performance despite a significant decrease in sample size. The study advanced with the fatal accident analysis to promote prevention measures. Measures offered attribute-based corrections by examining the relationships between the attributes. Ultimately, the proposed methodology can aid construction industry professionals in analyzing prospective safety problems using the large-scale collected data during the construction.