Despite rapid advancements in military science and technology, safety accidents causing non-combat losses remain a chronic challenge that threatens combat readiness and public trust. In particular, given that the primary causes of accidents are predominantly attributed to human factors rather than mechanical defects, a transition to a preemptive prevention system based on big data is imperative. Therefore, this study proposes an accident prediction model that integrates Artificial Intelligence (AI) technology with human factors theory, utilizing rotary-wing aircraft—characterized by complex mechanical features and high cognitive load—as a test-bed. Specifically, accumulated accident data were analyzed using Large Language Model (LLM)-based text mining techniques to identify latent risk factors, and the Delphi method was applied to verify and structure the causality among these factors. The data-driven prediction framework presented in this study is expected to serve as an effective model contributing to the establishment of a preemptive safety management system for the entire military, encompassing the Army, Navy, and Air Force.
Seongdeok Lee (Mon,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: