With rising complexity of work systems, occupational safety experts need to keep up with risk analysis, while smaller enterprises furthermore struggle due to a lack of specialist personnel and due to absence of systematic safety processes. To alleviate this problem, we propose the use of state-of-the-art Machine Learning techniques to support occupational safety risk analysis in enterprises. In this paper we provide an overview over the inherent challenges of such a system, encompassing data availability and extraction, handling of missing, heterogeneous or just too sparse data with appropriate algorithms and their variants, and User Interface aspects including explainability. We map out the next steps in the process of implementing a real world application to support occupational safety experts in a large enterprise to prove the feasibility of such an approach and to gather experience, which can eventually be drawn upon to develop a generalized tool, if possible for all the stakeholders present in the occupational safety process.
CITATION STYLE
Westhoven, M., & Adolph, L. (2022). Concept for Supporting Occupational Safety Risk Analysis with a Machine Learning Tool. In Communications in Computer and Information Science (Vol. 1580 CCIS, pp. 468–473). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-031-06417-3_63
Mendeley helps you to discover research relevant for your work.