Predictive situation awareness reference model using Multi-Entity Bayesian Networks
Cheol Young Park, Kathryn Blackmond Laskey, Paulo Costa, Shou Matsumoto · International Conference on Information Fusion · 2014
Predictive Situation Awareness (PSAW) emphasizes the ability to make predictions about aspects of a temporally evolving situation. Higher-level fusion to support PSAW requires a semantically rich representation to handle complex real world situations and the ability to reason under uncertainty about the situation. Multi-Entity Bayesian Networks (MEBN) are rich enough to represent and reason about uncertainty in complex, knowledge-rich domains. In previous applications of MEBN to PSAW, the models, called MTheories, were constructed from scratch for each application. Designing models from scratch is inefficient and fails to build on the experience gained from prior work. In this paper, we argue that applications of MEBN to PSAW share similar goals and common model elements. We propose a reference model for designing a MEBN model for PSAW and evaluate our model on a case study of a defense system.