Harrington, R. A. 1996. Utilizing bayesian techniques for user interface intelligence. Master's thesis, Air Force Institute of Technology. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
A Dynamic Bayesian Intelliegent Interface Agent - Brown, Santos, Jr., Banks (Correct)
....state is true using Bayes Theorem [10] This value represents the probability that the node s state is true. This node is named after the state it represents, for example, User is Using Graphical Communication. 3 Dynamic Interface Learning Networks The networks used and presented previously [5, 6] have been pedagogical examples. While although they represent the concepts and advantages of using Bayesian networks as a knowledge representation in intelligent user interfaces, they represent only a microcosm of the entire system and the possible actions a user may perform while using the ....
....suddenly change behavior, perhaps as the result of some new stimuli in the user s environment. A fast rate of convergence will quickly allow the user model to overcome the past behavior and accurately model the current behavior. 4 Conclusions The prototype interface learning network used to date [5] needs to be expanded to capture additional actions. Expansion of the number of actions GESIA will monitor allows a more accurate model of the user s behavior to be maintained. Our current IIA uses a dynamic hand coded interface learning network. We determine a priori the actions we will ....
Robert A. Harrington. Utilizing bayesian techniques for user interface intelligence. Master's thesis, Air Force Institute of Technology, Wright-Patterson AFB, OH, 1996.
Intelligent Interface Learning with Uncertainty - Harrington, Brown (1997) Self-citation (Harrington) (Correct)
....Prediction Accuracy Testing Prediction accuracy testing was accomplished by observing the dynamics of the agent s suggestion generation capabilities when given a set of test cases that mimic user behavior. We present the test case of the implemented system. Other cases can be found elsewhere (Harrington 1996). As implemented, GESIA makes two main suggestion to the user upon login. The suggestions are a a combination of suggestions including Bayesian knowledge base (BKB) filename, system function, and communication mode. After system login, two BKB filenames are suggested. Once one is chosen or both ....
Harrington, R. A. 1996. Utilizing bayesian techniques for user interface intelligence. Master's thesis, Air Force Institute of Technology.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC