Expert-rule Bayesian network fusing vision model outputs raises physiological assessment accuracy from 15-19% to 42-46% and overall triage accuracy from 14% to 53% in DARPA field scenarios while expanding coverage to 95% of cases.
SMILE: Structural Modeling, Inference, and Learning Engine and GeNIe: a development environment for graphical decision-theoretic models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Multimodal Bayesian Network for Robust Assessment of Casualties in Autonomous Triage
Expert-rule Bayesian network fusing vision model outputs raises physiological assessment accuracy from 15-19% to 42-46% and overall triage accuracy from 14% to 53% in DARPA field scenarios while expanding coverage to 95% of cases.