By Topic

Experts' estimation of uncertain quantities and its implications for knowledge acquisition

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

1 Author(s)
T. M. Mullin ; Decision Sci. Consortium Inc., Reston, VA, USA

The elicitation and encoding of expert judgments for machine use has been justified on the basis of different models of human expert performance that have very different implications for how this knowledge should be encoded and used. Studies of expert problem-solving in well-defined problem domains typically indicate that an expert's conceptualization of the problem and the solution processes it suggests differ markedly from and are superior to those of a nonexpert. This supports the acquisition of both an expert's object knowledge and his processing and control strategies. Other studies have found the judgment performance of experts to be somewhat inferior to that of simple linear models developed by bootstrapping the expert's judgments. This suggests that acquisition of expert judgments should be limited to the identification of key process parameters for subsequent use in relatively simple models. A protocol study of electric fields experts' and groundwater experts' estimations of quantities, involving few versus numerous sources of technical uncertainty, has provided preliminary evidence that both of the aforementioned models of expert performance may be valid for the same expert, for different problems in his domain. The findings suggest that knowledge engineering for expert systems should involve a combined application of these two approaches to elicitation and encoding of expert knowledge

Published in:

IEEE Transactions on Systems, Man, and Cybernetics  (Volume:19 ,  Issue: 3 )