Date post: | 03-Apr-2018 |
Category: |
Documents |
Upload: | safarudin-basri |
View: | 227 times |
Download: | 0 times |
of 26
7/28/2019 Fuzzy Indra
1/26
1
Fuzzy Expert SystemsArtificialIntelligence
7/28/2019 Fuzzy Indra
2/26
2
Introduction
Mamdani fuzzy inference
Sugeno fuzzy inference
Summary
Fuzzy Expert Systems
7/28/2019 Fuzzy Indra
3/26
3
Introduction
Mamdani fuzzy inference
Sugeno fuzzy inference
Summary
Fuzzy Expert Systems
7/28/2019 Fuzzy Indra
4/26
4
The operation of a fuzzy expert system depends onthe execution of FOUR major tasks:
Introduction
Fuzzification of input variables
Inference/rule evaluation
Composition/Aggregation
Defuzzification
7/28/2019 Fuzzy Indra
5/26
5
Introduction
Fuzzification: definition of fuzzy sets, anddetermination of the degree of membership of crisp
inputs in appropriate fuzzy sets.
Inference: evaluation of fuzzy rules to producean output for each rule.
Composition: aggregation or combination ofthe outputs of all rules.
Defuzzification:computation of crisp output
7/28/2019 Fuzzy Indra
6/26
6
Introduction
Mamdani fuzzy inference
Sugeno fuzzy inference
Summary
Fuzzy Expert Systems
7/28/2019 Fuzzy Indra
7/26
7
Mamdani fuzzy inference
Example:a simple two-input one-output problem withthree rules.
Rule: 1 Rule: 1IF xis A3 IF project_funding is adequateOR y is B1 OR project_staffing is small
THEN z is C1 THEN risk is low
Rule: 2 Rule: 2IF xis A2 IF project_funding is marginalAND y is B2 AND project_staffing is largeTHEN zis C2 THEN risk is normal
Rule: 3 Rule: 3IF xis A1 IF project_funding is inadequateTHEN zis C3 THEN risk is high
7/28/2019 Fuzzy Indra
8/26
8
Mamdani fuzzy inference
Fuzzification:determine degree of membership of crispinputsx1 andy1 in appropriate fuzzy sets
7/28/2019 Fuzzy Indra
9/26
9
Mamdani fuzzy inference
Inference:apply fuzzified inputs, (x=A1) = 0.5,(x=A2) = 0.2, (y=B1) = 0.1 and (y=B2) = 0.7, to the
antecedents of the fuzzy rules.
For fuzzy rules with multiple antecedents, the
fuzzy operator (AND or OR) is used to obtain a
single number that represents the result of the
antecedent evaluation. This number (the truth value)
is then applied to the consequent membershipfunction.
7/28/2019 Fuzzy Indra
10/26
10
Mamdani fuzzy inference
Inference:to evaluatei) the disjunction of rule antecedents, we use the OR
fuzzy operation, typically defined by the classical fuzzy
operation union:
AB(x) = max [A(x), B(x)]
ii) the conjunction of rule antecedents, we apply the
AND fuzzy operation intersection:
AB(x) = min [A(x), B(x)]
7/28/2019 Fuzzy Indra
11/26
11
Mamdani fuzzy inference
7/28/2019 Fuzzy Indra
12/26
12
Mamdani fuzzy inference
Inference:Two general methods of applying theresult of the antecedent evaluation to the membership
function of the consequent:
Clipping (alphacut): This is the most common
method. It involves cutting the consequent
membership function at the level of the antecedent
truth. Since the top of the membership function is
sliced, the clipped fuzzy set loses some information.
However, it is often preferred because it involves lesscomplex and faster mathematics, and generates an
aggregated output surface that is easier to defuzzify.
7/28/2019 Fuzzy Indra
13/26
13
Mamdani fuzzy inference
Scaling: Offers a better approach for preserving theoriginal shape of the fuzzy set. The original
membership function of the rule consequent is
adjusted by multiplying all its membership degrees by
the truth value of the rule antecedent. This method,
which generally loses less information, can be very
useful in fuzzy expert systems.
7/28/2019 Fuzzy Indra
14/26
14
Mamdani fuzzy inference
clipped scaled
7/28/2019 Fuzzy Indra
15/26
15
Mamdani fuzzy inference
Composition:aggregation of clipped (or scaled)outputs of all rules into a single fuzzy set.
7/28/2019 Fuzzy Indra
16/26
16
Mamdani fuzzy inference
Defuzzification:conversion of fuzzy set produced bycomposition stage into a crisp value.
Several defuzzification methods exist, but probably the
most popular one is the centroid technique. It findsthe centre of gravity (COG) of the aggregate set:
7/28/2019 Fuzzy Indra
17/26
17
Mamdani fuzzy inference
Centre of gravity (COG): In practice, a reasonableestimate is obtained by calculating it over a sample of
points:
7/28/2019 Fuzzy Indra
18/26
18
Introduction
Mamdani fuzzy inference
Sugeno fuzzy inference
Summary
Fuzzy Expert Systems
7/28/2019 Fuzzy Indra
19/26
19
Sugeno fuzzy inference
Mamdani-style inference is, in general, notcomputationally efficient. This is because it involves
finding the centroid of a two-dimensional shape by
integrating across a continuously varying function.
Michio Sugeno suggested the use of a single spike - a
singleton - as the membership function of the rule
consequent. A fuzzy singleton is a fuzzy set with a
membership function that is unity at a single particular
point on the universe of discourse and zero everywhereelse.
7/28/2019 Fuzzy Indra
20/26
20
Sugeno fuzzy inference
Sugeno- and Mamdani-style fuzzy inference are similar.The only difference is in the rule consequent. Instead of
a fuzzy set, Sugeno used a mathematical function of the
input variable:
IF x is A
AND y is B
THEN zisf(x, y)
wherex,y andzare linguistic variables; A and B arefuzzy sets on universe of discourses X and Y,
respectively; andf(x, y) is a mathematical function.
7/28/2019 Fuzzy Indra
21/26
21
Sugeno fuzzy inference
The zero-order Sugeno fuzzy model, in which the outputof each fuzzy rule is constant, is most commonly used.
Here, the functionf(x, y) = kand all consequent
membership functions are represented by singleton
spikes:
IF x is A
AND y is B
THEN zis k
where kis a constant.
7/28/2019 Fuzzy Indra
22/26
22
Sugeno fuzzy inference
Rule evaluation
7/28/2019 Fuzzy Indra
23/26
23
Sugeno fuzzy inference
Composition
7/28/2019 Fuzzy Indra
24/26
24
Sugeno fuzzy inference
Defuzzification
Weighted average (WA):
7/28/2019 Fuzzy Indra
25/26
25
Mamdani or Sugeno?
Mamdani method widely accepted for capturing expert knowledge - it allows
us to describe the expertise in more intuitive, more
human-like manner.
entails a substantial computational burden.
Sugeno method
computationally effective and works well with optimization
and adaptive techniques, which makes it very attractive incontrol problems, particularly for dynamic nonlinear
systems.
7/28/2019 Fuzzy Indra
26/26
26
Summary
The operation of a fuzzy expert system is in fourmajor stages: fuzzification, inference, composition
and defuzzification.
Mamdani- and Sugeno-style fuzzy inference systems
are two commonly employed methods.
Mamdani fuzzy inference systems use fuzzy sets in
the rule consequent while Sugeno systems use
mathematical functions, most often a constant.
Mamdani systems are computationally expensive but
capture knowledge in intuitive, human-like mannerwhile Sugeno systems are more computationally
efficient but lose linguistic interpretability.