Applied Methods and Models of Knowledge Engineering in Information Based Health Assessment Systems
Abstract
This report results from a contract tasking St. Petersburg Institute for Informatics & Automation of the Russian Academy of Sciences as follows: The contractor will investigate knowledge engineering as applied to system diagnostics by rigorous mathematical justification for already existing diagnostic procedures utilizing statistical clustering and Bayes' technique. A software package implementing cluster analysis of statistical data, including selection and evaluation of particular subspaces in the factor space, and facilitating definition of cluster models will be developed. The software will utilize computer graphics to facilitate previewing of the clustering pattern in particular subspaces. Applications of Algebraic Bayes' Network approach to various classes of applications of experts' analysis techniques to diagnostics related problems will be considered. Further, a software tool and numerical examples utilizing model data, demonstrating the concept, will be developed. In addition, applications of classical regression analysis to such problems of diagnostics as estimation of remaining life expectancy of hardware subjected to adverse effects, and analysis of combined effects of several adverse conditions of hardware failure will be subjected to analysis, and implemented in software. A software tool and numerical examples utilizing model data, demonstrating the concept, will be developed.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jan 01, 1999
- Accession Number
- ADA368834
Entities
People
- V. I. Gorodetski
Organizations
- Russian Academy of Sciences