Share Email Print
cover

Proceedings Paper

Adding explanation capability to a knowledge-based system: a case study
Author(s): Susan M. Bridges; Matthew Lybanon
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

An explanation component has been developed for an existing oceanographic expert system that predicts the movement of mesoscale features associated with the Gulf Stream. The structure of the original system was not amenable to the incorporation of an explanation facility because the knowledge needed for explanation was not explicitly represented in the knowledge base. A set of design principles that facilitate the implementation of an explanation component were developed and used as a basis for revision of the rule base. The explanation component consists of an introspection module that `watches' the reasoning process and a presentation module that uses the information gathered by the introspection module to construct a detailed natural language trace of the rules or a shorter natural language summary of the reasoning used for the prediction.

Paper Details

Date Published: 23 March 1993
PDF: 10 pages
Proc. SPIE 1963, Applications of Artificial Intelligence 1993: Knowledge-Based Systems in Aerospace and Industry, (23 March 1993); doi: 10.1117/12.141753
Show Author Affiliations
Susan M. Bridges, Mississippi State Univ. (United States)
Matthew Lybanon, Naval Research Lab. (United States)


Published in SPIE Proceedings Vol. 1963:
Applications of Artificial Intelligence 1993: Knowledge-Based Systems in Aerospace and Industry
Usama M. Fayyad; Ramasamy Uthurusamy, Editor(s)

© SPIE. Terms of Use
Back to Top