knowledge acquisition in the fuzzy knowledge representation framework of a medical consultation...
TRANSCRIPT
Knowledge Acquisition in the Fuzzy Knowledge
Representation Framework of a Medical Consultation System
By: Karl Boegl, Klaus-Peter Adlassnig, Yoichi Hayashi, Thomas Rothenfluh, and Harald Leitich
MedFrame/CADIAG-IV
- The predecessor: CADIAG-II - Consultation System- New Implementation- Generalized Domain Model- Fuzzy Dice
Definitions
Fuzzy Set Theory Fuzzy Logic Fuzzy Control
Rule-Based Fuzzy Logic System
• Rules
• antecedent
• consequent
• Fuzzifier
• inference engine
• output processor
Fuzzy Logic Example
tall(x) = { 0, if height(x) < 5 ft.,(height(x)-5ft.)/2ft., if 5 ft. <= height (x) <= 7 ft.,
1, if height(x) > 7 ft. }
Membership Function
1.0 + +-------------------
| /
| /
0.5 + /
| /
| /
0.0 +-------------+-----+-------------------
| |
5.0 7.0
height, ft. ->
Person Height degree of tallness
--------------------------------------
Billy 3' 2" 0.00
Yoke 5' 5" 0.21
Drew 5' 9" 0.38
Erik 5' 10" 0.42
Mark 6' 1" 0.54
Kareem 7' 2" 1.00
Logic Operations in Fuzzy Logic
truth (not x) = 1.0 - truth (x)
truth (x and y) = minimum (truth(x), truth(y))
truth (x or y) = maximum (truth(x), truth(y))
Another Example
old (x) = { 0, if age(x) < 18 yr.
(age(x)-18 yr.)/42 yr., if 18 yr. <= age(x) <= 60 yr. 1, if age(x) > 60 yr. }
a = X is TALL and X is OLD
b = X is TALL or X is OLD
c = not (X is TALL)
height age X is TALL X is OLD a b c
------------------------------------------------------------------------
3' 2" 65 0.00 1.00 0.00 1.00 1.00
5' 5" 30 0.21 0.29 0.21 0.29 0.79
5' 9" 27 0.38 0.21 0.21 0.38 0.62
5' 10" 32 0.42 0.33 0.33 0.42 0.58
6' 1" 31 0.54 0.31 0.31 0.54 0.46
7' 2" 45 1.00 0.64 0.64 1.00 0.00
3' 4" 4 0.00 0.00 0.00 0.00 1.00
Representation within MedFrame/CADIAG-IV
Positive Associations FP Consequent => Antecedent
SP Antecedent => Consequent
Negative Associations FN -(Consequent) => Antecedent
SN Antecedent => -(Consequent)
Knowledge Refinements (1 of 2)
Knowledge Refinements (2 of 2)
Project Successes
References Title: Knowledge Acquisition in the Fuzzy Knowledge Representation Framework
of a Medical Consultation System By: Karl Boegl, Klaus-Peter Adlassnig, Yoichi Hayashi, Thomas Rothenfluh, Harald Leitich Copyright: 2001
Title: The MedFrame Project http://medexpert.imc.akh-wien.ac.at/MedFrame/
By: Dieter KopeckyCopyright: 2000
Title: Medical Expert Systems http://www.computer.privateweb.at/judith/name_3.htm
By: Judith FederhoferCopyright: 2002
(More)
References (continued)
Title: Systematized Nomenclature of Medicine
http://www.snomed.org
By: College of American Pathologists
Copyright: 2001-2003
http://www-2.cs.cmu.edu/Groups/AI/html/faqs/ai/fuzzy/part1/faq/html Mendel, Jerry. “Uncertainty in Fuzzy Logic Systems.” University of
Southern California.