Date of Graduation
Spring 2017
Degree
Master of Science in Project Management
Department
Technology and Construction Management
Committee Chair
Amir H. Behzadan
Abstract
Construction sites comprise constantly moving heterogeneous resources that interact in close proximity of each other. The sporadic nature of such interactions creates an accident prone physical space surrounding workers. Despite efforts to improve site safety using location-aware proximity sensing techniques, major scientific gaps still remain in reliably forecasting impending hazardous scenarios before they occur. In the research documented in this thesis, spatiotemporal data of workers and site hazards are fused with a quantifiable model of an individual's attitude toward risk to generate proximity-based safety alerts in real time. In particular, two trajectory prediction models, namely polynomial regression (PR) and hidden Markov model (HMM) are investigated and their effectiveness in predicting a worker's position given his or her past movement trajectory is evaluated. Next, HMM prediction is further improved and calibrated by factoring in a worker's risk profile, a measure of his affinity for or aversion to risky behavior near hazards. Finally, a mobile application is designed and tested in a series of field experiments involving trajectories of different shape and complexity to verify the applicability and value of the designed methodology in addressing construction safety-related problems. Results demonstrate that the developed risk-calibrated HMM-based motion trajectory prediction can reliably detect unsafe movements and impending collision events.
Keywords
construction safety, trajectory prediction, real-time tracking, GPS, Markov model, risk attitude.
Subject Categories
Business Administration, Management, and Operations
Copyright
© Khandakar Mamunur Rashid
Recommended Citation
Rashid, Khandakar Mamunur, "Coupling Mobile Technology, Position Data Mining, and Attitude toward Risk to Improve Construction Site Safety" (2017). MSU Graduate Theses. 3158.
https://bearworks.missouristate.edu/theses/3158
