ORCID
Mary Helander: 0000-0002-5185-6867
Document Type
Article
Date
2024
Keywords
binary classification, hazard analysis, logistic regression, mission critical system, network centrality, neural network, random forest, risk prediction, risk to force, support vector machine
Language
English
Disciplines
Artificial Intelligence and Robotics | Data Science | Occupational Health and Industrial Hygiene | Operational Research | Other Social and Behavioral Sciences | Risk Analysis | Systems Engineering | Systems Science
Description/Abstract
This work formulates the hazard prediction problem while addressing the research question: Can machine learning create a model to automatically recognize patterns that correspond to hazard state conditions during a mission-critical operation? Supervised learning models were trained and tested on data observed from mission simulators, which allowed for safe observation of dynamic system states and undesirable casualty events. The prediction task was formulated as a binary classification problem, producing the probability of being in a hazard state at time t and providing situational awareness of a possible imminent loss. Several modeling architectures were investigated: neural networks, logistic regression, a support vector machine (SVM), and random forest models. The models were tuned, trained, evaluated using k-fold cross validation, and compared across a range of metrics to assess prediction quality. Computation time for training convergence and propensity for over-fitting were assessed across model architectures. Results showed that hazard states, without pre-specification, are predictable from limited system state data, enabling the possibility for real-time anticipation and loss avoidance.
Recommended Citation
Mary E. Helander, Brendan Smith, Sylvia Charchut, Erika Swiatowy, Calvin Nau, Gregory Cavaretta, Timothy Schuler, Adam Schunk, Héctor J. Ortiz-Peña (2024). “The hazard prediction problem.” SAFETY SCIENCE. Safety Science, Volume 176, https://doi.org/10.1016/j.ssci.2024.106559.
Source
submission
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Included in
Artificial Intelligence and Robotics Commons, Data Science Commons, Occupational Health and Industrial Hygiene Commons, Operational Research Commons, Other Social and Behavioral Sciences Commons, Risk Analysis Commons, Systems Engineering Commons, Systems Science Commons
