Predictive analysis network tool for human knowledge elicitation and reasoning
Jennifer Thompson, Jessica Bradley · 2007
Bayesian networks are useful for predicting future activities on the battlefield. Bayesian mathematics provides the most benefit in JDL fusion levels 2+, i.e. situation, threat, and performance assessment. However, these networks are exceedingly difficult for the average person to develop, much less a soldier in the middle of a war. We are in the process of developing a Bayesian modeling aid that walks the user through each step of the process, supplying help, suggesting alternatives, and translating their model into a human language description that is understandable by non-experts. This effort was originally funded as an AFRL Phase I SBIR (FA8750-06-C-0089) and is currently a Phase II SBIR. In this paper we will walk through the process of developing a Bayesian network and discuss how our tool helps at each step.