Knowledge acquisition for multi-channel electroencephalogram interpretation

Authors:
J.Karim Meddahi;Ben H. Jansen
Affiliations:
Department of Electrical Engineering and Bioengineering Research Center, University of Houston, Houston, TX 77204-4793, USA;Department of Electrical Engineering and Bioengineering Research Center, University of Houston, Houston, TX 77204-4793, USA
Venue:
Artificial Intelligence in Medicine
Year:
1992

Citing 7
Cited 1

A practical guide to designing expert systems

A practical guide to designing expert systems
Building expert systems

Building expert systems
Blackboard systems part two: Blackboard application systems

AI Magazine
Expert systems techniques, tools and applications

Expert systems techniques, tools and applications
Expertise transfer and complex problems: using AQUINAS as a knowledge-acquisition workbench for knowledge-based systems

Readings in knowledge acquisition and learning
MOLE: a tenacious knowledge-acquisition tool

Readings in knowledge acquisition and learning
Handbook of AI

Handbook of AI

An integrated intelligent computing model for the interpretation of EMG based neuromuscular diseases

Expert Systems with Applications: An International Journal

Quantified Score

Hi-index	0.00

Visualization

Abstract

Knowledge-based systems for the automated interpretation of electrophysiological data require: (1) domain-dependent knowledge as used by, say, a cardiologist, and (2) digital signal processing knowledge. Typically, a knowledge engineer is used to encode the rules of thumb used by the domain expert, but it is more desirable that the domain expert directly enters his/her knowledge into the system. This is even more so in our application domain, where the knowledge of two experts needs to be extracted and encoded. A knowledge representation scheme and acquisition tool is presented here that makes it possible to actively involve the domain expert(s) in the encoding of the domain knowledge. The system has been evaluated on a well-defined problem taken from the area of automated EEG analysis. The results obtained indicate that the approach is especially useful in coding and handling complex spatio-temporal relationships.