Knowledge Extraction from Experts in View of the Construction of Expert Systems

Author(s):  
F. Vandamme
1986 ◽  
Vol 30 (5) ◽  
pp. 492-496 ◽  
Author(s):  
R. Koubek ◽  
G. Salvendy ◽  
H. Dunsmore

A current bottleneck In the automation of software Is the lack of available, standardized, reliable and valid methods for extracting knowledge from expert programmers. This paper discusses the development of Computer Aided Protocol (CAP) to automatically collect the general and specific cognitive task components of a programmer. Results Indicate that CAP was able to collect lower level goals while protocol analysis collected only 56 percent of these lower level goals. However, protocol analysis was able to obtain significantly more procedural knowledge relating to cognitive states of the subject and more high level goals than CAP (F(1,8)=11.23; p<.004). This work suggests that the integration of the information derived from both protocol and CAP for knowledge extraction would provide more effective information for the development of expert systems than is feasible with either system alone.


1993 ◽  
Author(s):  
M. A. Bramer ◽  
R. W. Milne

1986 ◽  
Vol 31 (6) ◽  
pp. 448-449
Author(s):  
Elaine A. Rich
Keyword(s):  

IEE Review ◽  
1991 ◽  
Vol 37 (6) ◽  
pp. 228
Author(s):  
Peter Zorkoczy
Keyword(s):  

2002 ◽  
Vol 81 (6) ◽  
pp. 270-271
Author(s):  
J. Fallows
Keyword(s):  

1989 ◽  
Vol 28 (02) ◽  
pp. 69-77 ◽  
Author(s):  
R. Haux

Abstract:Expert systems in medicine are frequently restricted to assisting the physician to derive a patient-specific diagnosis and therapy proposal. In many cases, however, there is a clinical need to use these patient data for other purposes as well. The intention of this paper is to show how and to what extent patient data in expert systems can additionally be used to create clinical registries and for statistical data analysis. At first, the pitfalls of goal-oriented mechanisms for the multiple usability of data are shown by means of an example. Then a data acquisition and inference mechanism is proposed, which includes a procedure for controlling selection bias, the so-called knowledge-based attribute selection. The functional view and the architectural view of expert systems suitable for the multiple usability of patient data is outlined in general and then by means of an application example. Finally, the ideas presented are discussed and compared with related approaches.


1996 ◽  
Vol 35 (02) ◽  
pp. 88-92 ◽  
Author(s):  
E.-H. W. Kluge

AbstractKay and Purves' proposed narratological model of the medical record is based on the familiar phenomenological insight that the perception of data is conditioned by the conceptual framework of the perceiver. Unfortunately, unless handled very carefully, this approach will make the significance of a medical record unique to the person who constructed it and impermeable to outside scrutiny. However, when integrated into the analog-model of the medical record, the narratological model can be accommodated as the clinician-relative construction of a patient profile within the data that make up the medical record. Some implications for the construction of expert systems and competence analysis are indicated.


Sign in / Sign up

Export Citation Format

Share Document