Abstract
The construction industry suffers from workplace accidents, including injuries and fatalities, which represent a significant economic and social burden for employers, workers, and society as a whole. The existing research on construction accidents heavily relies on expert evaluations, which often suffer from issues such as low efficiency, insufficient intelligence, and subjectivity. However, expert opinions provided in construction accident reports offer a valuable source of knowledge that can be extracted and utilized to enhance safety management. Today this valuable resource can be mined as the advent of artificial intelligence has opened up significant opportunities to advance construction site safety. Ontology represents an attractive representation scheme. Though ontology has been used in construction safety to solve the problem of information heterogeneity using formal conceptual specifications, the establishment and development of ontologies that utilize construction accident reports are currently in an early stage of development and require further improvements. Moreover, research on the exploration of incorporating deep learning methodologies into construction safety ontologies for predicting construction safety incidents is relatively limited. This paper describes a novel approach to improving the performance of accident prediction models by incorporating ontology into a deep learning model. First, a domain word discovery algorithm, based on mutual information and adjacency entropy, is used to analyze the causes of accidents mentioned in construction reports. This analysis is then combined with technical specifications and the literature in the field of construction safety to build an ontology encompassing unsafe factors related to construction accidents. By employing a Translating on Hyperplane (TransH) model, the reports are transformed into conceptual vectors using the constructed ontology. Building on this foundation, we propose a Text Convolutional Neural Network (TextCNN) model that incorporates the ontology specifically designed for construction accidents. We compared the performance of the TextCNN model against five traditional machine learning models, namely Naive Bayes, support vector machine, logistic regression, random forest, and multilayer perceptron, using three different data sets: One-Hot encoding, word vector, and conceptual vectors. The results indicate that the TextCNN model integrated with the ontology outperformed the other models in terms of performance achieving an impressive accuracy rate of 88% and AUC value of 0.92.
Similar content being viewed by others
References
Aneziris ON, Topali E, Papazoglou IA (2012) Occupational risk of building construction. Reliab Eng Syst Saf 105:36–46
Aziz A, Ahmed S, Khan FI (2019) An ontology-based methodology for hazard identification and causation analysis. Process Saf Environ Prot 123:87–98
Basaran I, Yilmaz S (2016) Developing rail safety competencies based on accident and incident investigations: using root cause taxonomies to learn from accidents. In: 2016 IEEE International conference on industrial engineering and engineering management (IEEM). IEEE, pp 481–485
Bashar MA, Li Y (2018) Interpretation of text patterns. Data Min Knowl Discov 32:849–884
Benjaoran V, Bhokha S (2010) An integrated safety management with construction management using 4d cad model. Saf Sci 48:395–403
Cao T, Mu W, Gou J, Peng L (2020) A study of risk relevance reasoning based on a context ontology of railway accidents. Risk Anal 40:1589–1611
Carbonari A, Giretti A, Naticchia B (2011) A proactive system for real-time safety management in construction sites. Autom Constr 20:686–698
Chen WT, Bria TA (2022) A review of ontology-based safety management in construction. Sustainability 15:413
Chen Y (2015) Convolutional neural network for sentence classification. Master’s thesis. University of Waterloo
Cheng EW, Ryan N, Kelly S (2012) Exploring the perceived influence of safety management practices on project performance in the construction industry. Saf Sci 50:363–369
Chi NW, Lin KY, Hsieh SH (2014) Using ontology-based text classification to assist job hazard analysis. Adv Eng Inform 28:381–394
Eardley W, Ashe D, Fletcher B (2016) An ontology engineering approach to user profiling for virtual tours of museums and galleries. Int J Knowl Eng 2:85–91
Farghaly K, Soman RK, Collinge W, Mosleh MH, Manu P, Cheung CM (2022) Construction safety ontology development and alignment with industry foundation classes (IFC). J Inf Technol Constr 27:94–108
Fernández-López M, Gómez-Pérez A, Juristo N (1997) Methontology: from ontological art towards ontological engineering. In: Proceedings of the ontological engineering AAAI-97 Spring symposium series
Fu Y, Wen P, Wu J, Shu Y Knowledge graph-based policy analysis from a hybrid prospect of external attributes and internal characteristics under carbon peaking and carbon neutrality goal. Available at SSRN 4384948
Gao S, Ren G, Li H (2022) Knowledge management in construction health and safety based on ontology modeling. Appl Sci 12:8574
Ge J, Zhang Y, Chen S, Xu K, Yao X, Li J, Liu B, Yan F, Wu C, Li S (2022) Accident causation models developed in china between 1978 and 2018: review and comparison. Saf Sci 148:105653
Gruninger M (1995) Methodology for the design and evaluation of ontologies. In: Proceedings of IJCAI’95, workshop on basic ontological issues in knowledge sharing, pp 85–91
Hai N, Gong D, Liu S (2021) Ontology knowledge base combined with Bayesian networks for integrated corridor risk warning. Comput Commun 174:190–204
Halder A, Batra S (2023) Application of predictive analytics in built environment research: a comprehensive bibliometric study to explore knowledge domains and future research agenda. Arch Comput Methods Eng 1–26
Huang JH, Powers D (2003) Chinese word segmentation based on contextual entropy. In: Proceedings of the 17th Pacific Asia conference on language, information and computation, pp 152–158
Jiang X, Tan AH (2009) Learning and inferencing in user ontology for personalized semantic web search. Inf Sci 179:2794–2808
Jiang X, Wang S, Wang J, Lyu S, Skitmore M (2020) A decision method for construction safety risk management based on ontology and improved CBR: example of a subway project. Int J Environ Res Public Health 17:3928
Jin R, Zou Y, Gidado K, Ashton P, Painting N (2019) Scientometric analysis of bim-based research in construction engineering and management. Eng Constr Archit Manag 26:1750–1776
Johansen KW, Schultz C, Teizer J (2023) Hazard ontology and 4d benchmark model for facilitation of automated construction safety requirement analysis. Comput Aided Civ Infrastruct Eng
Joulin A, Grave E, Bojanowski P, Mikolov T (2016) Bag of tricks for efficient text classification. arXiv preprint arXiv:1607.01759
Kamel MN, Lee AY, Powers EC (2007) A methodology for developing ontologies using the ontology web language (owl) In: ICEIS (4), pp 261–268
Kastrati Z, Imran AS, Yayilgan SY (2019) The impact of deep learning on document classification using semantically rich representations. Inf Process Manag 56:1618–1632
Kim HM, Fox MS, Gruninger M (1995) An ontology of quality for enterprise modelling. In: Proceedings 4th IEEE workshop on enabling technologies: infrastructure for collaborative enterprises (WET ICE’95), IEEE. pp 105–116
Knight K, Chander I, Haines M, Hatzivassiloglou V, Hovy E, Iida M, Luk SK, Whitney R, Yamada K (1995) Filling knowledge gaps in a broad-coverage machine translation system. arXiv preprint cmp-lg/9506009
Knight K, Luk SK (1994) Building a large-scale knowledge base for machine translation. In: AAAI, pp 773–778
Le QT, Lee DY, Park CS (2014) A social network system for sharing construction safety and health knowledge. Autom Constr 46:30–37
Le QT, Pedro A, Park CS (2015) A social virtual reality based construction safety education system for experiential learning. J Intell Robot Syst 79:487–506
Leu SS, Chang CM (2013) Bayesian-network-based safety risk assessment for steel construction projects. Acc Anal Prev 54:122–133
Liu M, Huang R, Xu F (2023) Research on the construction of safety information ontology knowledge base and accident reasoning for complex hazardous production systems-taking methanol production process as an example. Sustainability 15:2568
Liu X, Gao J, He X, Deng L, Duh K, Wang YY (2015) Representation learning using multi-task deep neural networks for semantic classification and information retrieval
Lu Y, Li Q, Zhou Z, Deng Y (2015) Ontology-based knowledge modeling for automated construction safety checking. Saf Sci 79:11–18
Luo G (2009) Design and evaluation of the imed intelligent medical search engine. In: 2009 IEEE 25th international conference on data engineering, IEEE, pp 1379–1390
Macêdo JB, das Chagas Moura M, Aichele D, Lins ID (2022) Identification of risk features using text mining and bert-based models: application to an oil refinery. Process Saf Environ Prot 158:382–399
Mohamed E, Seresht NG, AbouRizk S (2023) Context-driven ontology-based risk identification for onshore wind farm projects: a domain-specific approach. Adv Eng Inform 56:101962
Musen MA (2015) The protégé project: a look back and a look forward. AI Matters 1:4–12
Noy NF, Fergerson RW, Musen MA (2000) The knowledge model of protege-2000: combining interoperability and flexibility. In: Knowledge engineering and knowledge management methods, models, and tools: 12th international conference, EKAW 2000 Juan-les-Pins, France, October 2–6, 2000 Proceedings 12, Springer, pp 17–32
Oberle D (2014) How ontologies benefit enterprise applications. Semantic Web 5:473–491
Park CS, Kim HJ (2013) A framework for construction safety management and visualization system. Autom Constr 33:95–103
Park M, Lee, KW, Lee HS, Jiayi P, Yu J (2013) Ontology-based construction knowledge retrieval system. KSCE J Civ Eng 17:1654–1663
Pedro A, Baik S, Jo J, Lee D, Hussain R, Park C (2023) A linked data and ontology-based framework for enhanced sharing of safety training materials in the construction industry. IEEE Access
Pedro A, Pham-Hang AT, Nguyen PT, Pham HC (2022) Data-driven construction safety information sharing system based on linked data, ontologies, and knowledge graph technologies. Int J Environ Res Public Health 19:794
Peraketh B, Menzel C, Mayer RJ, Fillion F, Futrell MT, DeWitte P et al (1994) Ontology capture method (idef5). Knowledge Based Systems, Incorporated Technical report
Phengsuwan J, Shah T, Sun R, James P, Thakker D, Ranjan R (2022) An ontology-based system for discovering landslide-induced emergencies in electrical grid. Trans Emerg Telecommun Technol 33:e3899
Pinto A (2014) Qram a qualitative occupational safety risk assessment model for the construction industry that incorporate uncertainties by the use of fuzzy sets. Saf Sci 63:57–76
Pulido J, Herrera R, Arechiga M, Block A, Acosta R, Legrand S (2006) Identifying ontology components from digital archives for the semantic web. In: IASTED advances in computer science and technology (ACST), pp 1–6
Qiu Q, Xie Z, Zhang D, Ma K, Tao L, Tan Y, Zhang Z, Jiang B (2023) Knowledge graph for identifying geological disasters by integrating computer vision with ontology. J Earth Sci 34:1418–1432
Shen Q, Wu S, Deng Y, Deng H, Cheng JC (2022) Bim-based dynamic construction safety rule checking using ontology and natural language processing. Buildings 12:564
Studer R, Benjamins VR, Fensel D (1998) Knowledge engineering: principles and methods. Data Knowl Eng 25:161–197
Swartout B, Patil R, Knight K, Russ T (1996) Toward distributed use of large-scale ontologies. In: Proceedings of the tenth workshop on knowledge acquisition for knowledge-based systems, p 25
Teizer J, Johansen K, Schultz C (2022) The concept of digital twin for construction safety. Constr Res Congress 2022:1156–1165
Uschold M, Gruninger M (1996) Ontologies: principles, methods and applications. Knowl Eng Rev 11:93–136
Wachter JK, Yorio PL (2014) A system of safety management practices and worker engagement for reducing and preventing accidents: An empirical and theoretical investigation. Acc Anal Prev 68:117–130
Wang Q, Yu X (2014) Ontology based automatic feature recognition framework. Comput Ind 65:1041–1052
Wang H, Zhang F, Xie X, Guo M (2018) Dkn: deep knowledge-aware network for news recommendation. In: Proceedings of the 2018 world wide web conference, pp 1835–1844
Wang WC, Liu JJ, Chou SC (2006) Simulation-based safety evaluation model integrated with network schedule. Autom Constr 15:341–354
Wang Z, Zhang J, Feng J, Chen Z (2014) Knowledge graph embedding by translating on hyperplanes. In: Proceedings of the AAAI conference on artificial intelligence, pp 1112–1119
Wu H, Zhong B, Li H, Love P, Pan X, Zhao N (2021) Combining computer vision with semantic reasoning for on-site safety management in construction. J Build Eng 42:103036
Wu H, Zhong B, Medjdoub B, Xing X, Jiao L (2020) An ontological metro accident case retrieval using CBR and NLP. Appl Sci 10:5298
Wu L, Rao Y, Yu H, Wang Y, Ambreen N (2019) A multi-semantics classification method based on deep learning for incredible messages on social media. Chin J Electron 28:754–763
Xing X, Zhong B, Luo H, Li H, Wu H (2019) Ontology for safety risk identification in metro construction. Comput Ind 109:14–30
Xu Q, Xu K (2021) Analysis of the characteristics of fatal accidents in the construction industry in China based on statistical data. Int J Environ Res Public Health 18:2162
Ye Y, Yang D, Jiang Z, Tong L (2008) Ontology-based semantic models for supply chain management. Int J Adv Manuf Technol 37:1250–1260
Zhang S, Boukamp F, Teizer J (2014) Ontology-based semantic modeling of safety management knowledge. In: Computing in civil and building engineering, pp 2254–2262
Zhang S, Boukamp F, Teizer J (2015) Ontology-based semantic modeling of construction safety knowledge: towards automated safety planning for job hazard analysis (jha). Autom Constr 52:29–41
Zhao L, Ichise R (2014) Ontology integration for linked data. J Data Semant 3:237–254
Zhu YL (2013) The construction safety accident emergency decision support system based on ontology and CBR. Appl Mech Mater 423:2149–2153
Acknowledgements
This work was supported by Humanity and Social Science Research Project of Anhui Provincial Education Department in 2022 (2022AH050224) and Housing Urban and Rural Construction Science and Technology Plan Project of Anhui Province in 2022 (2022-YF082).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Shi, D., Li, Z., Zurada, J. et al. Ontology-based text convolution neural network (TextCNN) for prediction of construction accidents. Knowl Inf Syst 66, 2651–2681 (2024). https://doi.org/10.1007/s10115-023-02036-9
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10115-023-02036-9