journal article·2024-12-11Open access

A Generative Artificial-Intelligence-Based Workbench to Test New Methodologies in Organisational Health and Safety

Andrea Falegnami, Andrea Tomassi, Giuseppe Corbelli, Francesco Saverio Nucci, Elpidio Romano

Applied Sciences· Volume 14· Issue 24

Abstract

This paper introduces a novel generative artificial intelligence workbench specifically tailored to the field of safety sciences. Utilizing large language models (LLMs), this innovative approach significantly diverges from traditional methods by enabling the rapid development, refinement, and preliminary testing of new safety methodologies. Traditional techniques in this field typically depend on slow, iterative cycles of empirical data collection and analysis, which can be both time-intensive and costly. In contrast, our LLM-based workbench leverages synthetic data generation and advanced prompt engineering to simulate complex safety scenarios and generate diverse, realistic data sets on demand. This capability allows for more flexible and accelerated experimentation, enhancing the efficiency and scalability of safety science research. By detailing an application case, we demonstrate the practical implementation and advantages of our framework, such as its ability to adapt quickly to evolving safety requirements and its potential to significantly cut down development time and resources. The introduction of this workbench represents a paradigm shift in safety methodology development, offering a potent tool that combines the theoretical rigor of traditional methods with the agility of modern AI technologies.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Occupational Health and Safety Research · Risk and Safety Analysis · Safety Systems Engineering in Autonomy

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

Management Engineering Faculty, Uninettuno University, 00186 Rome, Italy

Psychology Faculty, Uninettuno University, 00186 Rome, Italy

Research and Innovation Area, Uninettuno University, 00186 Rome, Italy

Funding

Horizon Europe. Digital Industry and Space

References (38)

Show source-provided references
1. Scenario-Based Automated Data Preprocessing to Predict Severity of Construction Accidents10.1016/j.autcon.2022.104351 ↗
2. Tsalidis, G.A. (2024). Introducing the Occupational Health and Safety Potential Midpoint Impact Indicator in Social Life Cycle Assessment. Sustainability, 16.10.3390/su16093844 ↗
3. Stepanovic, S., Naous, D., and Mettler, T. (2024, November 11). A Privacy Impact Assessment Method for Organizations Implementing IoT for Occupational Health and Safety. Available online: https://aisel.aisnet.org/icis2023/ishealthcare/ishealthcare/14/.
4. Bond, T.G., and Fox, C.M. (2013). Applying the Rasch Model, Psychology Press.10.4324/9781410614575 ↗
5. Teaming with Industrial Cobots: A Socio-Technical Perspective on Safety Analysis10.1002/hfm.20939 ↗
6. A Study of the Resilience Analysis Grid Method and Its Applicability to the Water Sector in England and Wales10.1111/wej.12539 ↗
7. Duros, S.E. (2024, November 11). Supporting Resilience in Distributed Work Systems through Modeling Adaptive Capacity. Available online: https://rave.ohiolink.edu.
8. Brown, T.B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., and Askell, A. (2020). Language Models Are Few-Shot Learners. arXiv.
9. Exploring Large Language Models for the Generation of Synthetic Training Samples for Aspect-Based Sentiment Analysis in Low Resource Settings10.1016/j.eswa.2024.125514 ↗
10. Zhao, F., Yu, F., Trull, T., and Shang, Y. (2023, January 5–6). A New Method Using LLMs for Keypoints Generation in Qualitative Data Analysis. Proceedings of the 2023 IEEE Conference on Artificial Intelligence (CAI), Santa Clara, CA, USA.10.1109/CAI54212.2023.00147 ↗
11. Applicability of ChatGPT 3.5 in the Development of New Analytical Procedures10.1016/j.microc.2024.110787 ↗
12. Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
13. Artificial Intelligence in Advancing Occupational Health and Safety: An Encapsulation of Developments10.1093/joccuh/uiad017 ↗
14. Artificial Intelligence in Occupational Health and Safety Risk Management of Construction, Mining, and Oil and Gas Sectors: Advances and Prospects10.9734/jerr/2024/v26i61177 ↗
15. Advancements and Applications of Generative Artificial Intelligence and Large Language Models on Business Management: A Comprehensive Review10.32996/jcsts.2024.6.1.26 ↗
16. Taiwo, R., Bello, I.T., Abdulai, S.F., Yussif, A.-M., Salami, B.A., Saka, A., and Zayed, T. (2024). Generative AI in the Construction Industry: A State-of-the-Art Analysis. arXiv.
17. Lu, Y., Shen, M., Wang, H., Wang, X., van Rechem, C., Fu, T., and Wei, W. (2023). Machine Learning for Synthetic Data Generation: A Review. arXiv.
18. Machine Learning in Occupational Safety and Health: Protocol for a Systematic Review: (Protocol)10.24840/2184-0954_005.001_0004 ↗
19. Guo, X., and Chen, Y. (2024). Generative AI for Synthetic Data Generation: Methods, Challenges and the Future. arXiv.
20. Generation of Pseudo-Synthetic Seismograms from Gamma-Ray Well Logs of Highly Radioactive Formations10.1007/s00024-018-1979-6 ↗
21. Deepfakes and Disinformation: Exploring the Impact of Synthetic Political Video on Deception, Uncertainty, and Trust in News10.1177/2056305120903408 ↗
22. Reliability in Semantic Segmentation: Can We Use Synthetic Data?
23. Johannesson, P., and Perjons, E. (2021). An Introduction to Design Science, Springer International Publishing.10.1007/978-3-030-78132-3 ↗
24. Galli, C., Cusano, C., Meleti, M., Donos, N., and Calciolari, E. (2024). Topic Modeling for Faster Literature Screening Using Transformer-Based Embeddings. Metrics, 1.10.20944/preprints202407.2198.v1 ↗
25. Design Principles for Systematic Search Systems: A Holistic Synthesis of a Rigorous Multi-Cycle Design Science Research Journey10.1007/s12599-018-0569-6 ↗
26. Pishgar, M., Issa, S.F., Sietsema, M., Pratap, P., and Darabi, H. (2021). REDECA: A Novel Framework to Review Artificial Intelligence and Its Applications in Occupational Safety and Health. Int. J. Environ. Res. Public Health, 18.10.3390/ijerph18136705 ↗
27. Knowledge Contributions in Design Science Research: Paths of Knowledge Types10.1016/j.dss.2022.113898 ↗
28. Falegnami, A., Romano, E., and Tomassi, A. (2024). The Emergence of the GreenSCENT Competence Framework: A Constructivist Approach: The GreenSCENT Theory. The European Green Deal in Education, Routledge.10.4324/9781003492597-17 ↗
29. Tomassi, A., Falegnami, A., and Romano, E. (2024). Mapping Automatic Social Media Information Disorder. The Role of Bots and AI in Spreading Misleading Information in Society. PLoS ONE, 19.10.1371/journal.pone.0303183 ↗
30. A Knowledge Graph-Based Bio-Inspired Design Approach for Knowledge Retrieval and Reasoning
31. Falegnami, A., Tomassi, A., Corbelli, G., and Romano, E. (2024). Managing Complexity in Socio-Technical Systems by Mimicking Emergent Simplicities in Nature: A Brief Communication. Biomimetics, 9.10.3390/biomimetics9060322 ↗
32. Retrieval-Augmented Generation for Knowledge-Intensive Nlp Tasks
33. Improving RAG Quality for Large Language Models with Topic-Enhanced Reranking
34. (2024, November 13). Exploring TITAN’s Approach to Integrating Socratic Thinking and AI in Chatbot Dialogue. Available online: https://www.titanthinking.eu/post/exploring-titan-s-approach-to-integrating-socratic-thinking-and-ai-in-chatbot-dialogue.
35. Empirical Research Methods in Operations Management10.1016/0272-6963(90)90098-X ↗
36. Hollnagel, E. (2017). Safety-II in Practice: Developing the Resilience Potentials, Routledge.10.4324/9781315201023 ↗
37. Hollnagel, E. (2019). Epilogue: RAG—The Resilience Analysis Grid. Resilience Engineering in Practice, CRC Press.10.1201/9781315585444-14 ↗
38. Winzar, H. (2024, November 11). LikertMakeR: Synthesise and Correlate Rating-Scale Data with Predefined First & Second Moments; 2022, 0.4.0. Available online: https://github.com/WinzarH/LikertMakeR.