Knowledge Acquisition, Representation \& Manipulation in Decision Support Systems
This work addresses the challenge of making complex reasoning systems more accessible and interpretable for researchers and users in decision support, though it appears incremental in its application of existing methods.
The paper tackles the problem of integrating statistical and expert approaches for data analysis and knowledge acquisition in decision support systems, presenting a methodology that applies Dempster-Shafer theory to belief revision and introduces an interface for user interaction with belief networks.
In this paper we present a methodology and discuss some implementation issues for a project on statistical/expert approach to data analysis and knowledge acquisition. We discuss some general assumptions underlying the project. Further, the requirements for a user-friendly computer assistant are specified along with the nature of tools aiding the researcher. Next we show some aspects of belief network approach and Dempster-Shafer (DST) methodology introduced in practice to system SEAD. Specifically we present the application of DS methodology to belief revision problem. Further a concept of an interface to probabilistic and DS belief networks enabling a user to understand the communication with a belief network based reasoning system is presented