Return
A data-driven model of human factors contributing to loss of control in-flight and on the ground in general aviation
E
B
K
K
C
DOI:10.1016/j.ress.2025.112124.png)
Abstract
En 中文
• Novel ML–DBN framework for retrospective and predictive human error analysis. • Empirical CPT construction from co-occurrence data reduces subjectivity. • Bayesian forecasting with Monte Carlo enables monthly risk trajectories. • Upstream precursors identified as most effective intervention targets. • Modular Python framework scalable across diverse aviation contexts.
Journal
R
IF:
11
Papers:
9.0K
Citations:
4.2W
