Machine Learning–Based Bayesian Framework for Interval Estimate of Unsafe-Event Prediction in Construction
Publication: Journal of Construction Engineering and Management
Volume 149, Issue 11
Abstract
Construction safety is a critical concern for industry and academia, and numerous models and algorithms have been developed to predict incidents or accidents to facilitate proactive decision-making. However, previous studies have been limited due to the inability to account for uncertainties because predictions are given as a single value (i.e., Yes or No) and the failure to integrate subjective judgment. To address these limitations, this research proposes a machine learning–based Bayesian framework for predicting construction incidents using interval estimates. This framework combines a state-of-the-art machine-learning algorithm with a binary Bayesian inference model to develop an incident predictor that considers a range of project characteristics and conditions. Notably, this framework also is capable of incorporating historical or subjective judgment through prior selection and outputs the unsafe event prediction as an interval of possibilities, thus accounting for various uncertainties. The efficacy of our framework was demonstrated in a real-life case study, showcasing its practical implications for proactive decision-making and risk management in the construction industry and representing a valuable contribution to the field of construction safety.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
Some or all data, models, or codes used during the study were provided by a third party. Direct requests for these materials may be made to the provider as indicated in the Acknowledgments; some data, models, or code generated or used during the study are available in a repository online in accordance with funder data-retention policies.
Acknowledgments
This project was supported by a Collaborative Research and Development Grant (CRDPJ 492657) from the Natural Sciences and Engineering Research Council of Canada. The authors thank Graham Construction for their continued support and for providing case study data.
References
Abdat, F., S. Leclercq, X. Cuny, and C. Tissot. 2014. “Extracting recurrent scenarios from narrative texts using a Bayesian network: Application to serious occupational accidents with movement disturbance.” Accid. Anal. Prev. 70 (Sep): 155–166. https://doi.org/10.1016/j.aap.2014.04.004.
Alexander, D., M. Hallowell, and J. Gambatese. 2017. “Precursors of construction fatalities. II: Predictive modeling and empirical validation.” J. Constr. Eng. Manage. 143 (7): 04017024. https://doi.org/10.1061/(ASCE)CO.1943-7862.0001297.
Baker, H., M. R. Hallowell, and A. J.-P. Tixier. 2020. “AI-based prediction of independent construction safety outcomes from universal attributes.” Autom. Constr. 118 (Oct): 103146. https://doi.org/10.1016/j.autcon.2020.103146.
Bayes, T. 1763. “An essay towards solving a problem in the doctrine of chances. By the late Rev. Mr. Bayes, F. R. S. communicated by Mr. Price, in a letter to John Canton, A. M. F. R. S.” Philos. Trans. R. Soc. London 53 (Dec): 370–418. https://doi.org/10.1098/rstl.1763.0053.
Borg, A., H. Bjelland, and O. Nja. 2014. “Reflections on Bayesian network models for road tunnel safety design: A case study from Norway.” Tunnelling Underground Space Technol. 43 (Jul): 300–314. https://doi.org/10.1016/j.tust.2014.05.004.
Chan, A. P. C., F. K. W. Wong, C. K. H. Hon, and T. N. Y. Choi. 2018. “A Bayesian network model for reducing accident rates of electrical and mechanical (E&M) work.” Int. J. Environ. Res. Public Health 15 (11): 2496. https://doi.org/10.3390/ijerph15112496.
Chung, T. H., Y. Mohamed, and S. AbouRizk. 2006. “Bayesian updating application into simulation in the North Edmonton Sanitary Trunk tunnel project.” J. Constr. Eng. Manage. 132 (8): 882–894. https://doi.org/10.1061/(ASCE)0733-9364(2006)132:8(882).
Demirmen, F. 1998. “Reserves uncertainty: Some historical trends and wider implications.” First Break 16 (5): 143–149. https://doi.org/10.1046/j.1365-2397.1998.00689.x.
Fernández, A., S. García, M. Galar, R. C. Prati, B. Krawczyk, and F. Herrera. 2018. Learning from imbalanced data sets, 978. Berlin: Springer.
Garcia, S., S. Ramírez-Gallego, J. Luengo, J. M. Benítez, and F. Herrera. 2016. “Big data preprocessing: Methods and prospects.” Big Data Anal. 1 (1): 1–22. https://doi.org/10.1186/s41044-016-0014-0.
Gardoni, P., K. F. Reinschmidt, and R. Kumar. 2007. “A probabilistic framework for Bayesian adaptive forecasting of project progress.” Comput.-Aided Civ. Infrastruct. Eng. 22 (3): 182–196. https://doi.org/10.1111/j.1467-8667.2007.00478.x.
Gelman, A. 2013. Bayesian data analysis. Boca Raton, FL: CRC Press.
Giorgi, F., and L. O. Mearns. 2002. “Calculation of average, uncertainty range, and reliability of regional climate changes from AOGCM simulations via the ‘reliability ensemble averaging’ (REA) method.” J. Clim. 15 (10): 1141–1158. https://doi.org/10.1175/1520-0442(2002)015%3C1141:COAURA%3E2.0.CO;2.
Goh, Y. M., and D. Chua. 2013. “Neural network analysis of construction safety management systems: A case study in Singapore.” Construct. Manage. Econ. 31 (5): 460–470. https://doi.org/10.1080/01446193.2013.797095.
Goh, Y. M., and C. U. Ubeynarayana. 2017. “Construction accident narrative classification: An evaluation of text mining techniques.” Accid. Anal. Prev. 108 (Nov): 122–130. https://doi.org/10.1016/j.aap.2017.08.026.
Goh, Y. M., C. U. Ubeynarayana, K. L. X. Wong, and B. H. W. Guo. 2018. “Factors influencing unsafe behaviors: A supervised learning approach.” Accid. Anal. Prev. 118 (Sep): 77–85. https://doi.org/10.1016/j.aap.2018.06.002.
Hallowell, M. R., D. Alexander, and J. A. Gambatese. 2017. “Energy-based safety risk assessment: Does magnitude and intensity of energy predict injury severity?” Construct. Manage. Econ. 35 (1–2): 64–77. https://doi.org/10.1080/01446193.2016.1274418.
Hallowell, M. R., S. Bhandari, and W. Alruqi. 2020. “Methods of safety prediction: Analysis and integration of risk assessment, leading indicators, precursor analysis, and safety climate.” Construct. Manage. Econ. 38 (4): 308–321. https://doi.org/10.1080/01446193.2019.1598566.
Hon, C. K., C. Sun, B. Xia, N. L. Jimmieson, K. A. Way, and P. P.-Y. Wu. 2021. “Applications of Bayesian approaches in construction management research: A systematic review.” Eng. Constr. Archit. Manage. 29 (5): 2153–2182. https://doi.org/10.1108/ECAM-10-2020-0817.
Huang, X., et al. 2022. “Exploring the spatial disparity of home-dwelling time patterns in the USA during the COVID-19 pandemic via Bayesian inference.” Trans. GIS 26 (4): 1939–1961. https://doi.org/10.1111/tgis.12918.
Jafari, P., E. Mohamed, E. Pereira, S.-C. Kang, and S. AbouRizk. 2019. “Leading safety indicators: Application of machine learning for safety performance measurement.” In Proc., Int. Symp. on Automation and Robotics in Construction, 501–506. Waterloo, ON, Canada: IAARC. https://doi.org/10.22260/ISARC2019/0067.
Ji, W., and S. M. AbouRizk. 2017. “Credible interval estimation for fraction nonconforming: Analytical and numerical solutions.” Autom. Constr. 83 (Nov): 56–67. https://doi.org/10.1016/j.autcon.2017.07.003.
Kang, K., and H. Ryu. 2019. “Predicting types of occupational accidents at construction sites in Korea using random forest model.” Saf. Sci. 120 (Dec): 226–236. https://doi.org/10.1016/j.ssci.2019.06.034.
Kang, Y., Z. Jin, C. Hyun, and H. Park. 2018. “Construction management functions for developing countries: Case of Cambodia.” J. Manage. Eng. 34 (3): 05018004. https://doi.org/10.1061/(ASCE)ME.1943-5479.0000609.
Kelly, D. 2011. Bayesian inference for probabilistic risk assessment a practitioner’s guidebook. London: Springer.
Kruschke, J. 2014. Doing Bayesian data analysis: A tutorial with R, JAGS, and Stan. London: Academic Press.
Kuhn, M., and K. Johnson. 2013. “Measuring performance in classification models.” In Applied predictive modeling, 247–273. New York: Springer. https://doi.org/10.1007/978-1-4614-6849-3_11.
Kursa, M. B., and W. R. Rudnicki. 2010. “Feature selection with the Boruta package.” J. Stat. Software 36 (11): 1–13. https://doi.org/10.18637/jss.v036.i11.
Li, Z., L. Wu, and S. AbouRizk. 2019. XiaomoLing/Longestcommonsubstring: First release of longest common SubString R library. Geneva: Zenodo. https://doi.org/10.5281/zenodo.4057067.
Liu, C., Z. Lei, D. Morley, and S. M. AbouRizk. 2020. “Dynamic, data-driven decision-support approach for construction equipment acquisition and disposal.” J. Comput. Civ. Eng. 34 (2): 04019053. https://doi.org/10.1061/(ASCE)CP.1943-5487.0000871.
Mistikoglu, G., I. H. Gerek, E. Erdis, P. E. Mumtaz Usmen, H. Cakan, and E. E. Kazan. 2015. “Decision tree analysis of construction fall accidents involving roofers.” Expert Syst. Appl. 42 (4): 2256–2263. https://doi.org/10.1016/j.eswa.2014.10.009.
Mofidi, A., E. Tompa, S. B. Mortazavi, A. Esfahanipour, and P. A. Demers. 2020. “A probabilistic approach for economic evaluation of occupational health and safety interventions: A case study of silica exposure reduction interventions in the construction sector.” BMC Public Health 20 (Dec): 210. https://doi.org/10.1186/s12889-020-8307-7.
Mohamed, E., P. Jafari, S.-C. Kang, E. Pereira, and S. AbouRizk. 2019. “Leading indicators for safety management: Understanding the impact of project performance data on safety performance.” In Proc., Canadian Society for Civil Engineering. Montreal. Pointe Claire, QC, Canada: Canadian Society for Civil Engineering.
Mohammadi, A., M. Tavakolan, and Y. Khosravi. 2018. “Factors influencing safety performance on construction projects: A review.” Saf. Sci. 109 (Nov): 382–397. https://doi.org/10.1016/j.ssci.2018.06.017.
Nath, N. D., A. H. Behzadan, and S. G. Paal. 2020. “Deep learning for site safety: Real-time detection of personal protective equipment.” Autom. Constr. 112 (Apr): 103085. https://doi.org/10.1016/j.autcon.2020.103085.
Neyman, J. 1937. “Outline of a theory of statistical estimation based on the classical theory of probability.” Philos. Trans. R. Soc. London Ser. A Math. Phys. Sci. 236 (767): 333–380. https://doi.org/10.1098/rsta.1937.0005.
Oguz Erkal, E. D., M. R. Hallowell, and S. Bhandari. 2021. “Practical assessment of potential predictors of serious injuries and fatalities in construction.” J. Constr. Eng. Manage. 147 (10): 04021129. https://doi.org/10.1061/(ASCE)CO.1943-7862.0002146.
OSHA (Occupational Safety and Health Administration). 2022. “What is the difference between accidents and incidents?” Accessed July 6, 2023. https://www.osha.com/blog/incident-accident-difference.
Pareek, P., S. Han, and S. Misra. 2016. “Application of Bayesian updating for real-time schedule estimation in a concreting operation.” Int. J. Constr. Manage. 16 (1): 54–66. https://doi.org/10.1080/15623599.2015.1117710.
Patel, D. A., and K. N. Jha. 2017. “Developing a process to evaluate construction project safety hazard index using the possibility approach in India.” J. Constr. Eng. Manage. 143 (1): 04016081. https://doi.org/10.1061/(ASCE)CO.1943-7862.0001205.
Pereira, E., S. Ahn, S. Han, and S. Abourizk. 2020a. “Finding causal paths between safety management system factors and accident precursors.” J. Manage. Eng. 36 (2): 04019049. https://doi.org/10.1061/(ASCE)ME.1943-5479.0000738.
Pereira, E., M. Ali, L. Wu, and S. Abourizk. 2020b. “Distributed simulation–based analytics approach for enhancing safety management systems in industrial construction.” J. Constr. Eng. Manage. 146 (1): 04019091. https://doi.org/10.1061/(ASCE)CO.1943-7862.0001732.
Phan, T. D., J. C. R. Smart, S. J. Capon, W. L. Hadwen, and O. Sahin. 2016. “Applications of Bayesian belief networks in water resource management: A systematic review.” Environ. Model. Software 85 (Nov): 98–111. https://doi.org/10.1016/j.envsoft.2016.08.006.
Poh, C. Q. X., C. U. Ubeynarayana, and Y. M. Goh. 2018. “Safety leading indicators for construction sites: A machine learning approach.” Autom. Constr. 93 (Sep): 375–386. https://doi.org/10.1016/j.autcon.2018.03.022.
Sarkar, S., S. Vinay, R. Raj, J. Maiti, and P. Mitra. 2019. “Application of optimized machine learning techniques for prediction of occupational accidents.” Comput. Oper. Res. 106 (Jun): 210–224. https://doi.org/10.1016/j.cor.2018.02.021.
Tixier, A. J.-P., M. R. Hallowell, B. Rajagopalan, and D. Bowman. 2016a. “Application of machine learning to construction injury prediction.” Autom. Constr. 69 (Sep): 102–114. https://doi.org/10.1016/j.autcon.2016.05.016.
Tixier, A. J.-P., M. R. Hallowell, B. Rajagopalan, and D. Bowman. 2016b. “Automated content analysis for construction safety: A natural language processing system to extract precursors and outcomes from unstructured injury reports.” Autom. Constr. 62 (Feb): 45–56. https://doi.org/10.1016/j.autcon.2015.11.001.
Wang, L., and X. Zhang. 2018. “Bayesian analytics for estimating risk probability in PPP waste-to-energy projects.” J. Manage. Eng. 34 (6): 04018047. https://doi.org/10.1061/(ASCE)ME.1943-5479.0000658.
Weber, P. 2016. Benefits of Bayesian network models. Hoboken, NJ: Wiley-ISTE.
Winge, S., E. Albrechtsen, and B. A. Mostue. 2019. “Causal factors and connections in construction accidents.” Saf. Sci. 112 (Feb): 130–141. https://doi.org/10.1016/j.ssci.2018.10.015.
Witten, I. H., E. Frank, M. A. Hall, and C. J. Pal. 2016. Data mining: Practical machine learning tools and techniques. Burlington, MA: Morgan Kaufmann.
Wu, L. 2023. “Supplementary Tables S1, S2 and S3, GitHub Repository, Version 1.” Accessed August 20, 2023. https://github.com/XiaomoLing/ML-based-Bayesian-Safety-Prediction-Research/blob/0198345b65de6184ab854cc2fbad3d09ad73a8ca/Supplementary%20Tables%20S1%20S2%20and%20S3.xlsx.
Wu, L., and S. AbouRizk. 2023. “Towards construction’s digital future: A roadmap for enhancing data value.” In Proc., Canadian Society of Civil Engineering Annual Conf. 2021. Singapore: Springer. https://doi.org/10.1007/978-981-19-1029-6_17.
Wu, L., W. Ji, and S. M. AbouRizk. 2020a. “Bayesian inference with Markov chain Monte Carlo–based numerical approach for input model updating.” J. Comput. Civ. Eng. 34 (1): 04019043. https://doi.org/10.1061/(ASCE)CP.1943-5487.0000862.
Wu, L., Z. Li, and S. AbouRizk. 2020b. “Automation in extraction and sharing information between BIM and project management databases.” In Proc., Int. Conf. on Construction and Real Estate Management (ICCREM), 37–46. Reston, VA: ASCE. https://doi.org/10.1061/9780784483237.005.
Wu, L., Z. Li, and S. AbouRizk. 2022. “Automating common data integration for improved data-driven decision-support system in industrial construction.” J. Comput. Civ. Eng. 36 (2): 04021037. https://doi.org/10.1061/(ASCE)CP.1943-5487.0001001.
Xia, N., P. X. W. Zou, X. Liu, X. Wang, and R. Zhu. 2018. “A hybrid BN-HFACS model for predicting safety performance in construction projects.” Saf. Sci. 101 (Jan): 332–343. https://doi.org/10.1016/j.ssci.2017.09.025.
Xu, J., C. Cheung, P. Manu, and O. Ejohwomu. 2021a. “Safety leading indicators in construction: A systematic review.” Saf. Sci. 139 (Jul): 105250. https://doi.org/10.1016/j.ssci.2021.105250.
Xu, Y., Y. Zhou, P. Sekula, and L. Ding. 2021b. “Machine learning in construction: From shallow to deep learning.” Dev. Built Environ. 6 (May): 100045. https://doi.org/10.1016/j.dibe.2021.100045.
Zhang, S., C. Du, W. Sa, C. Wang, and G. Wang. 2014. “Bayesian-based hybrid simulation approach to project completion forecasting for underground construction.” J. Constr. Eng. Manage. 140 (1): 04013031. https://doi.org/10.1061/(ASCE)CO.1943-7862.0000764.
Zou, Y., A. Kiviniemi, and S. W. Jones. 2017. “Retrieving similar cases for construction project risk management using natural language processing techniques.” Autom. Constr. 80 (Aug): 66–76. https://doi.org/10.1016/j.autcon.2017.04.003.
Information & Authors
Information
Published In
Journal of Construction Engineering and Management
Volume 149 • Issue 11 • November 2023
Copyright
© 2023 American Society of Civil Engineers.
History
Received: Jan 11, 2023
Accepted: Jul 12, 2023
Published online: Sep 14, 2023
Published in print: Nov 1, 2023
Discussion open until: Feb 14, 2024
ASCE Technical Topics:
- Algorithms
- Analysis (by type)
- Artificial intelligence and machine learning
- Bayesian analysis
- Business management
- Computer programming
- Computing in civil engineering
- Construction engineering
- Construction equipment
- Construction management
- Decision making
- Engineering fundamentals
- Equipment and machinery
- Mathematics
- Occupational safety
- Practice and Profession
- Public administration
- Public health and safety
- Safety
- Statistical analysis (by type)
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.