The DOI matches its Crossref record; 58 of the 58 references it cites were found in a registry or an index.
Safety leading indicators for construction sites: A machine learning approach
Abstract
The construction industry is one of the most dangerous industries in many countries. To improve the situation, senior managers overseeing portfolios of construction projects need to understand the safety risk levels of their projects so that interventions can be implemented proactively. Safety leading indicators is one way to flag sites that are of higher risk. However, there is a lack of validated leading indicators that can reliably classify sites according to their safety risk levels. On the other hand, despite the success of machine learning (ML) approaches in other domains, it is not widely utilized in the construction industry, especially in the development of safety leading indicators. This paper presents a ML approach to developing leading indicators that classify sites in accordance to their safety risk in construction projects. This study was guided by the industry-recognized Cross-Industry Standard Process for Data Mining (CRISP-DM) framework and the key types of data used include safety inspection records, accident cases and project-related data. These data were obtained from a large contractor in Singapore and the data were accumulated from year 2010 to 2016. Out of thirty-three input variables (also known as features or independent variables), 13 input variables were selected using a combination of Boruta feature selection technique and decision tree. Of the 13 selected input variables, six of them are project-related (project type, project ownership, contract sum, percent completed, magnitude of delay and project manpower) and seven of them are items in the contractor's safety inspection checklists (crane/lifting operations, scaffold, mechanical-elevated working platform, falling hazards/openings, environmental management, good practices and weighted safety inspection score). Five popular ML algorithms were then used to train models for prediction of accident occurrence and severity. During validation, random forest (RF) provided the best prediction performance with an accuracy of 0.78 and has achieved a substantial strength of agreement with Weighted-Kappa Statistics of 0.70. Comparing with similar studies, this result is promising. The prediction (i.e. the output variable) provided by the RF model can be used as a safety leading indicator of the risk level of a site. It is recommended that the predictive RF model be deployed in construction organizations, especially large public and private developers, contractors and industry associations, to provide monthly forecast of project safety performance so that pre-emptive inspections and interventions can be implemented in a more targeted manner.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
The Measurement of Observer Agreement for Categorical Data
Landis, J. R., & Koch, G. G. (1977) · Biometrics · doi:10.2307/2529310 · Cited by 81,148
Scikit-learn: Machine Learning in Python
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Müller, A., Nothman, J., Louppe, G., et al. (2012) · arXiv · doi:10.48550/arxiv.1201.0490 · Cited by 71,016
A Coefficient of Agreement for Nominal Scales
Cohen, J. (1960) · Educational and Psychological Measurement · doi:10.1177/001316446002000104 · Cited by 42,398
SMOTE synthetic minority over-sampling technique
Chawla, N. V., Bowyer, K. W., Hall, L. O., & Kegelmeyer, W. P. (2002) · Journal of Artificial Intelligence Research · doi:10.1613/jair.953 · Cited by 32,865
Data Mining: Practical Machine Learning Tools and Techniques
(2011) · Elsevier eBooks · doi:10.1016/c2009-0-19715-5 · Cited by 25,437
He, H., & Garcia, E. A. (2009) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2008.239 · Cited by 10,359
An introduction to variable and feature selection
GuyonIsabelle, & ElisseeffAndré (2003) · Journal of Machine Learning Research · doi:10.5555/944919.944968 · Cited by 7,715
Kuhn, M., & Johnson, K. (2013) · doi:10.1007/978-1-4614-6849-3 · Cited by 6,788
An Introduction to Variable and Feature Selection.
Guyon, I., & Elisseeff, A. (2003) · Cited by 6,576
Feature Selection with the Boruta Package
Kursa, M. B., & Rudnicki, W. R. (2010) · Journal of Statistical Software · doi:10.18637/jss.v036.i11 · Cited by 5,659
Managing the Risks of Organizational Accidents
Reason, J. (2016) · Routledge eBooks · doi:10.4324/9781315543543 · Cited by 4,430
Thirty years of safety climate research: Reflections and future directions
Zohar, D. (2010) · Accident Analysis & Prevention · doi:10.1016/j.aap.2009.12.019 · Cited by 1,114
Overview and analysis of safety management studies in the construction industry
Zhou, Z., Goh, Y. M., & Li, Q. (2015) · Safety Science · doi:10.1016/j.ssci.2014.10.006 · Cited by 601
Self-citationTransformational leadership and group interaction as climate antecedents: A social network analysis.
Zohar, D., & Tenne-Gazit, O. (2008) · Journal of Applied Psychology · doi:10.1037/0021-9010.93.4.744 · Cited by 436
Application of machine learning to construction injury prediction
Tixier, A. J.-P., Hallowell, M. R., Rajagopalan, B., & Bowman, D. (2016) · Automation in Construction · doi:10.1016/j.autcon.2016.05.016 · Cited by 350
Hofmann, D. A., Burke, M. J., & Zohar, D. (2017) · Journal of Applied Psychology · doi:10.1037/apl0000114 · Cited by 335
Quantification of Agreement in Psychiatric Diagnosis: A New Approach
Spitzer, R. L. (1967) · Archives of General Psychiatry · doi:10.1001/archpsyc.1967.01730250085012 · Cited by 333
Machine learning and data mining
Kononenko, I., & Kukar, M. (2007) · Woodhead Publishing Limited eBooks · doi:10.1533/9780857099440 · Cited by 293
Data mining in building automation system for improving building operational performance
Xiao, F., & Fan, C. (2014) · Energy and Buildings · doi:10.1016/j.enbuild.2014.02.005 · Cited by 258
Hallowell, M. R., Hinze, J. W., Baud, K. C., & Wehle, A. (2013) · Journal of Construction Engineering and Management · doi:10.1061/(asce)co.1943-7862.0000730 · Cited by 246
Doing No Harm: Enabling, Enacting, and Elaborating a Culture of Safety in Health Care.
Vogus, T. J., Sutcliffe, K. M., & Weick, K. E. (2010) · Academy of Management Perspectives · doi:10.5465/amp.2010.55206385 · Cited by 222
Cheng, C.-W., Lin, C.-C., & Leu, S.-S. (2010) · Safety Science · doi:10.1016/j.ssci.2009.12.005 · Cited by 209
Building Safety indicators: Part 1 – Theoretical foundation
Øien, K., Utne, I. B., & Herrera, I. (2010) · Safety Science · doi:10.1016/j.ssci.2010.05.012 · Cited by 198
Thinking About Process Safety Indicators
(2009) · Safety Science · doi:10.1016/j.ssci.2007.12.006 · Cited by 193
Data mining for occupational injuries in the Taiwan construction industry
Liao, C.-W., & Perng, Y.-H. (2008) · Safety Science · doi:10.1016/j.ssci.2007.04.007 · Cited by 183
Soibelman, L., & Kim, H. (2002) · Journal of Computing in Civil Engineering · doi:10.1061/(asce)0887-3801(2002)16:1(39 · Cited by 173
Predicting construction cost overruns using text mining, numerical data and ensemble classifiers
Williams, T. P., & Gong, J. (2014) · Automation in Construction · doi:10.1016/j.autcon.2014.02.014 · Cited by 164
Lingard, H., Hallowell, M., Salas, R., & Pirzadeh, P. (2017) · Safety Science · doi:10.1016/j.ssci.2016.08.020 · Cited by 164
More thinking about process safety indicators
Ale, B. (2009) · Safety Science · doi:10.1016/j.ssci.2008.07.012 · Cited by 160
Cheng, M., Tsai, H., & Hsieh, W.-S. (2008) · Automation in Construction · doi:10.1016/j.autcon.2008.07.001 · Cited by 154
Cognitive Factors Influencing Safety Behavior at Height: A Multimethod Exploratory Study
Goh, Y. M., & Sa’adon, N. F. B. (2015) · Journal of Construction Engineering and Management · doi:10.1061/(asce)co.1943-7862.0000972 · Cited by 147
Self-citationZohar, D. M., Huang, Y.-H., Lee, J., & Robertson, M. M. (2013) · Accident Analysis & Prevention · doi:10.1016/j.aap.2013.09.005 · Cited by 143
Developing Leading Indicators to Monitor the Safety Conditions of Construction Projects
Guo, B. H. W., & Yiu, T. W. (2015) · Journal of Management in Engineering · doi:10.1061/(asce)me.1943-5479.0000376 · Cited by 139
Neural network analysis of construction safety management systems: a case study in Singapore
Goh, Y. M., & Chua, D. K. H. (2013) · Construction Management and Economics · doi:10.1080/01446193.2013.797095 · Cited by 124
Self-citationPredicting Disputes in Public-Private Partnership Projects: Classification and Ensemble Models
Chou, J., & Lin, C. (2012) · Journal of Computing in Civil Engineering · doi:10.1061/(asce)cp.1943-5487.0000197 · Cited by 96
Cheng, M., Hoang, N., & Wu, Y.-W. (2013) · Automation in Construction · doi:10.1016/j.autcon.2013.05.018 · Cited by 91
Son, H., Kim, C., & Kim, C. (2012) · Automation in Construction · doi:10.1016/j.autcon.2012.05.013 · Cited by 78
Factor selection for delay analysis using Knowledge Discovery in Databases
Kim, H., Soibelman, L., & Grobler, F. (2007) · Automation in Construction · doi:10.1016/j.autcon.2007.10.001 · Cited by 67
Kononenko, I., & Kukar, M. (2007) · Elsevier eBooks · doi:10.1533/9780857099440.59 · Cited by 52
Wang, K., Makond, B., & Wang, K.-M. (2013) · BMC Medical Informatics and Decision Making · doi:10.1186/1472-6947-13-124 · Cited by 47
Measuring Performance in Classification Models
Kühn, M., & Johnson, K. (2013) · Springer eBooks · doi:10.1007/978-1-4614-6849-3_11 · Cited by 44
Yu, W., & Liu, Y.-C. (2005) · Automation in Construction · doi:10.1016/j.autcon.2005.01.007 · Cited by 44
Poisson Model of Construction Incident Occurrence
Chua, D. K. H., & Goh, Y. M. (2005) · Journal of Construction Engineering and Management · doi:10.1061/(asce)0733-9364(2005)131:6(715 · Cited by 44
Self-citationLiu, Z., Sadiq, R., Rajani, B. B., & Najjaran, H. (2009) · Journal of Computing in Civil Engineering · doi:10.1061/(asce)cp.1943-5487.0000032 · Cited by 43
Association between safety leading indicators and safety climate levels
Givehchi, S., Hemmativaghef, E., & Hoveidi, H. (2017) · Journal of Safety Research · doi:10.1016/j.jsr.2017.05.003 · Cited by 41
A WICE approach to real-time construction cost estimation
Yu, W., Lai, C.-C., & Lee, W.-L. (2005) · Automation in Construction · doi:10.1016/j.autcon.2005.01.005 · Cited by 39
Chaovalitwongse, W. A., Wang, W., Williams, T. P., & Chaovalitwongse, P. (2011) · Journal of Construction Engineering and Management · doi:10.1061/(asce)co.1943-7862.0000386 · Cited by 39
Assessing Residual Value of Heavy Construction Equipment Using Predictive Data Mining Model
Fan, H., AbouRizk, S., Kim, H., et al. (2008) · Journal of Computing in Civil Engineering · doi:10.1061/(asce)0887-3801(2008)22:3(181 · Cited by 38
Gläßel, A., Kirchberger, I., Stucki, G., & Cieza, A. (2010) · Physiotherapy · doi:10.1016/j.physio.2010.08.010 · Cited by 37
Zhang, H., Yang, F., Li, Y., & Li, H. (2015) · Automation in Construction · doi:10.1016/j.autcon.2015.03.001 · Cited by 33
Using a Pressure-State-Practice Model to Develop Safety Leading Indicators for Construction Projects
Guo, B. H. W., Yiu, T., González, V., & Goh, Y. M. (2017) · Journal of Construction Engineering and Management · doi:10.1061/(asce)co.1943-7862.0001218 · Cited by 33
Self-citationYu, W., & Skibniewski, M. J. (2009) · Journal of Computing in Civil Engineering · doi:10.1061/(asce)0887-3801(2010)24:1(35 · Cited by 32
Robson, L. S., Ibrahim, S. A., Hogg‐Johnson, S., Steenstra, I. A., Eerd, D. V., & Amick, B. C. (2017) · Journal of Safety Research · doi:10.1016/j.jsr.2017.02.008 · Cited by 29
Decision support in machine vision system for monitoring of TFT-LCD glass substrates manufacturing
Yousefian-Jazi, A., Ryu, J.-H., Yoon, S., & Liu, J. J. (2014) · Journal of Process Control · doi:10.1016/j.jprocont.2013.12.009 · Cited by 28
Hammad, A., AbouRizk, S., & Mohamed, Y. (2013) · Journal of Management in Engineering · doi:10.1061/(asce)me.1943-5479.0000280 · Cited by 25
Love, P. E. D., & Teo, P. (2017) · Journal of Construction Engineering and Management · doi:10.1061/(asce)co.1943-7862.0001326 · Cited by 25
A VaFALCON neuro-fuzzy system for mining of incomplete construction databases
Yu, W., & Lin, H.-W. (2005) · Automation in Construction · doi:10.1016/j.autcon.2005.01.006 · Cited by 24
Hybrid Soft Computing Approach for Mining of Complex Construction Databases
Yu, W. (2007) · Journal of Computing in Civil Engineering · doi:10.1061/(asce)0887-3801(2007)21:5(343 · Cited by 23
Research works printed but not linked: 15
- Akhavian, 2013, Knowledge-based simulation modeling of construction fleet operations using multimodal-process data mining, J. Constr. Eng. Manag., 139, 10.1061/(ASCE)CO.1943-7862.0000775 · doi:10.1061/(asce)co.1943-7862.0000775
- Cheng, 2012, Applying data mining techniques to explore factors contributing to occupational injuries in Taiwan's construction industry, Accid. Anal. Prev., 48, 214, 10.1016/j.aap.2011.04.014 · doi:10.1016/j.aap.2011.04.014
- Cheung, 2006, Application of cross validation techniques for modelling construction costs during the very early design stage, Build. Environ., 41, 1973, 10.1016/j.buildenv.2005.09.011 · doi:10.1016/j.buildenv.2005.09.011
- Gao, 2014, Construction of neurofuzzy models for imbalanced data classification, IEEE Trans. Fuzzy Syst., 22, 1472, 10.1109/TFUZZ.2013.2296091 · doi:10.1109/tfuzz.2013.2296091
- Hale, 2009, Why safety performance indicators?, Saf. Sci., 47, 479, 10.1016/j.ssci.2008.07.018 · doi:10.1016/j.ssci.2008.07.018
- Hallowell, 2016, Predictive validity of safety leading indicators: empirical assessment in the oil and gas sector, J. Constr. Eng. Manag., 142, 4016052, 10.1061/(ASCE)CO.1943-7862.0001167 · doi:10.1061/(asce)co.1943-7862.0001167
- Kononenko, 2007, Chapter 1 - Introduction, 1
- Kononenko, 2007, Chapter 7 - Data preprocessing, 181
- Li, 2017, Developing dimensions and key indicators for the safety climate within China's construction teams: a questionnaire survey on construction sites in Nanjing, Saf. Sci., 93, 266, 10.1016/j.ssci.2016.11.006 · DOI
- Skibniewski, 2014, Research trends in information technology applications in construction safety engineering and management, 1 (3), 246
- Øien, 2011, Building safety indicators: part 2 – application, practices and results, Saf. Sci., 49, 162, 10.1016/j.ssci.2010.05.015 · doi:10.1016/j.ssci.2010.05.015
- Ranegger, 2015, Implementation of the Austrian nursing minimum data set (NMDS-AT): a feasibility study, BMC Med. Inform. Decis. Mak., 15, 75, 10.1186/s12911-015-0198-7 · doi:10.1186/s12911-015-0198-7
- Reiman, 2012, Leading indicators of system safety – monitoring and driving the organizational safety potential, Saf. Sci., 50, 1993, 10.1016/j.ssci.2011.07.015 · doi:10.1016/j.ssci.2011.07.015
- Salas, 2016, Predictive validity of safety leading indicators: empirical assessment in the oil and gas sector, J. Constr. Eng. Manag., 142, 10.1061/(ASCE)CO.1943-7862.0001167 · doi:10.1061/(asce)co.1943-7862.0001167
- Vogus, 2010, 24, 60
Cited by
Abioye, S. O., Oyedele, L. O., Akanbi, L., Ajayi, A., Davila Delgado, J. M., Bilal, M., Akinade, O. O., & Ahmed, A. (2021) · Journal of Building Engineering · doi:10.1016/j.jobe.2021.103299 · Cited by 1,015
Baduge, S. K., Thilakarathna, S., Perera, J. S., Arashpour, M., Sharafi, P., Teodosio, B., Shringi, A., & Mendis, P. (2022) · Automation in Construction · doi:10.1016/j.autcon.2022.104440 · Cited by 1,007
“…SVM [158] Decision Trees [159] K-Nearest Neighbours (KNN) [160] Logistics Regression [160] Progress Monitoring ANN [161] CNN [134] SVM [153] [161] KNN [162] Construction Safety ANN [141] [144] CNN [163] KNN [145] SVM [145] [148] LSTM [140] Random Forest [136] Decision Trees [136] essential subject.”
MethodA Systematic Literature Review on Applying CRISP-DM Process Model
Schröer, C., Kruse, F., & Gómez, J. M. (2021) · Procedia Computer Science · doi:10.1016/j.procs.2021.01.199 · Cited by 635
Opportunities and Adoption Challenges of AI in the Construction Industry: A PRISMA Review
Regona, M., Yigitcanlar, T., Xia, B., & Li, R. Y. M. (2022) · Journal of Open Innovation: Technology, Market, and Complexity · doi:10.3390/joitmc8010045 · Cited by 543
Ghimire, P., Kim, K., & Acharya, M. (2024) · Buildings · doi:10.3390/buildings14010220 · Cited by 175
“These studies demonstrate AI and machine learning applications across the construction management spectrum, including safety management [12–17], cost predictions [18–22], schedule optimization [1,4,23,24], progress monitoring [25–29], quality control [30,31], supply chain management [32–36],…”
Metadata
- Authors
- Poh, C. Q. X., Ubeynarayana, C. U., & Goh, Y. M.
- Venue
- Automation in Construction
- Publisher
- Elsevier BV
- Published
- 2018-09
- Volume
- 93
- Pages
- 375-386
- ISSN
- 0926-5805 (ISSN-L)
- OpenAlex
- W2796105695
- Cited by
- 290
- References
- 58
- FWCI
- 26.16
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- www.elsevier.com/tdm/userlicense/1.0/ (tdm)
- www.elsevier.com/legal/tdmrep-license (tdm)
- Funders
- Ministry of Education - Singapore (R-296-000-161-112)
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.