A Dynamic Bayesian Intelliegent Interface

This paper presents an intelligent user interface agent architecture based on Bayesian networks. Using a Bayesian network not only dynamically captures and models user behavior, but it also dynamically captures and models uncertainty in the interface's reasoning process. We present an approach that allows our intelligent interface agent (IIA) to alter its own topology to better adapt itself to modeling a particular user. We present several metrics that provide useful information concerning the performance of our IIA. IIA's sound semantics and mathematical basis enhances its ability to make correct, intelligent inferences as to the user's needs.