Akademik Veri Yönetim Sistemi
ARABIAN JOURNAL FOR SCIENCE AND ENGINEERING, cilt.49, sa.10, ss.13315-13332, 2024 (SCI-Expanded)
To improve site safety status, the construction safety literature has investigated machine learning (ML) prediction models with a particular emphasis on their prediction accuracy. This study shifts its focus on reliability of a construction safety model beyond their prediction accuracy by increasing its representativeness. A novel dual-edge construction safety network was synthesized that considers the mutual contribution of behaviors (human factors) and the physical environment (workplace factors). A graph convolutional network (GCN) was created to learn the high-level information of the dual-edge network to predict the severity outcome of construction accidents. The dual-edge GCN model was tested on a comprehensive construction safety dataset collected from 73 projects that resulted in an 85.67% prediction accuracy while leveraging shared human and workplace factors in predicting construction accident outcomes. The incorporated dual-edge safety network offers more representative and explainable accident visualization that enables prioritizing related safety interventions and developing tailored prevention strategies based on two different decision objectives. Compared with other ML approaches, the proposed construction safety model emphasizes both human and workplace factors without trading off its prediction accuracy, thereby increasing the reliability of the prediction outcome for integration in relevant safety decisions. The transparency of the input network and its accident visualization enable practitioners to develop tailored prevention strategies while increasing trust in accident prediction outcomes.