A Theoretical Framework for Context-Sensitive Temporal Probability Model Construction with Application to Plan Projection
This work addresses the need for more efficient probabilistic inference in temporal domains, such as medical treatment evaluation, but appears incremental as it builds on existing Bayesian network and logic programming concepts.
The authors tackled the problem of constructing context-sensitive temporal probability models by defining a temporal probability logic and providing a Bayesian network construction algorithm that yields sound and complete query answers, with an application demonstrated in evaluating treatments for acute cardiac conditions.
We define a context-sensitive temporal probability logic for representing classes of discrete-time temporal Bayesian networks. Context constraints allow inference to be focused on only the relevant portions of the probabilistic knowledge. We provide a declarative semantics for our language. We present a Bayesian network construction algorithm whose generated networks give sound and complete answers to queries. We use related concepts in logic programming to justify our approach. We have implemented a Bayesian network construction algorithm for a subset of the theory and demonstrate it's application to the problem of evaluating the effectiveness of treatments for acute cardiac conditions.