Chap 3: Fuzzy Rules and Fuzzy Reasoning

Fuzzy Rules and Fuzzy Reasoning
Chap 3: Fuzzy Rules and Fuzzy Reasoning

Provided: J.-S. Roger Jang Modified: Vali Derhami
Outline
Extension principle Fuzzy relations Fuzzy if-then rules Compositional rule of inference Fuzzy reasoning
2/28
Extension Principle
A is a fuzzy set on X :
A = A ( x1 ) / x1 + A ( x2 ) / x2 ++ A ( x n ) / x n
The image of A under f( ) is a fuzzy set B:
B = B ( x1 ) / y1 + B ( x2 ) / y2 ++ B ( x n ) / y n
where yi = f(xi), i = 1 to n. If f( ) is a many-to-one mapping, then
B ( y ) = max A ( x )
x= f
1
( y)
3/28
Fuzzy Relations
A fuzzy relation R is a 2D MF:
R = {(( x , y ), R ( x , y ))| ( x , y ) X Y}
Examples:
x is close to y (x and y are numbers) x depends on y (x and y are events) x and y look alike (x, and y are persons or objects) If x is large, then y is small (x is an observed reading and Y is a corresponding action)
4/28
Max-Min Composition
The max-min composition of two fuzzy relations R1 (defined on X and Y) and R2 (defined on Y and Z) is Properties:
R R ( x , z ) = [ R ( x , y ) R ( y , z )]
1 2
Associativity: R (S Distributivity over union:T ) = ( R S ) T Week distributivity over intersection:

R (S ) = ( R S ) R T ) T (
R ( S T ) ( R S ) ( R T ) Monotonicity: S T ( R S ) ( R T )
5/28
Max-Star Composition
Max-product composition:
R R ( x , z ) = [R ( x , y )R ( y , z )]
1 2
In general, we have max-* composition:
R R ( x , z ) = [R ( x , y ) * R ( y , z )]
1 2
where * is a T-norm operator.
6/28
Linguistic Variables
A numerical variables takes numerical values: Age = 65 A linguistic variables takes linguistic values: Age is old A linguistic values is a fuzzy set. All linguistic values form a term set: T(age) = {young, not young, very young, ... middle aged, not middle aged, ... old, not old, very old, more or less old, ... not very yound and not very old, ...}
7/28
Linguistic Values (Terms)
complv.m
8/28
Linguistic Hedges
Very: Somewhat: Extremely
Very ( A) = A
Sm ht oe a w
( A) = A
0.5
Extremely ( A) = A
9/28
Fuzzy Partition
Fuzzy partitions formed by the linguistic values young, middle aged, and old:
lingmf.m
10/28
Fuzzy If-Then Rules

General format: If x is A then y is B Examples:
If pressure is high, then volume is small. If the road is slippery, then driving is dangerous. If a tomato is red, then it is ripe. If the speed is high, then apply the brake a little.
11/28
Fuzzy If-Then Rules

Two ways to interpret If x is A then y is B:
y
A coupled with B
A entails B
A
12/28
Fuzzy If-Then Rules

Two ways to interpret If x is A then y is B:
A coupled with B: (A and B)
R = A B = A B = A ( x ) B ( y )| ( x , y )
~
A entails B: (not A or B) - Material implication - Propositional calculus - Extended propositional calculus - Generalization of modus ponens
13/28
Fuzzy If-Then Rules

Fuzzy implication function:
R ( x , y ) = f ( A ( x ), B ( y )) = f ( a, b )
A coupled with B
14/28
fuzimp.m
Fuzzy If-Then Rules

A entails B
fuzimp.m
15/28
Compositional Rule of Inference

Derivation of y = b from x = a and y = f(x):
y y
b y = f(x) a
a and b: points y = f(x) : a curve
16/28
b y = f(x)
x
a
a and b: intervals
y = f(x) : an interval-valued function
Compositional Rule of Inference

a is a fuzzy set and y = f(x) is a fuzzy relation:
17/28
cri.m
Fuzzy Reasoning
Modus ponens:
Generalized Modus ponens: Approximate reasoning or fuzzy reasoning
18/28
Fuzzy Reasoning
Single rule with single antecedent
Rule: if x is A then y is B Fact: x is A Conclusion: y is B
Degree of compatibility And Method
= sup (T (a ' ( x), a ( x))

x and
And Method is a T- norm such as min, or Prod
Implication Method
19/28
b' ( y ) = T ( , b( y ))
impl .
Implication Method is a T-norm such as min, or Prod
Fuzzy Reasoning
Graphic Representation: And method: min Implication method: min
A A
B
x y
A
x is A x
B
y is B y
20/28
Fuzzy Reasoning
Single rule with multiple antecedent
Rule: if x is A and y is B then z is C Fact: x is A and y is B Conclusion: z is C
Degree of compatibility Degree of compatibility
And Method
And Method
=sup (T ( a ' ( x ), a ( x ))), =sup (T (b' ( y ), b( y )))

x x and y y and
Firing Strength
Implication Method
21/28
= T ( , )
and x y
c' ( z ) = T ( , c( z ))
impl .
Fuzzy Reasoning
Graphic Representation: And method: min Implication method: min
A A
x
B B
T-norm
C2
z
A
x is A
22/28
B
x y is B y
C
z is C z
Fuzzy Reasoning
Multiple rules with multiple antecedent Rule 1: if x is A1 and y is B1 then z is C1 Rule 2: if x is A2 and y is B2 then z is C2 Fact: x is A and y is B Conclusion: z is C
23/28
Fuzzy Reasoning
Multiple rules with multiple antecedent
Firing strength of rule1 And Method Implication
= T ( , ), c ' ( z ) = T ( , c ( z ))
1 and 1x 1y 1 impl . 1 1
= T ( , ), c ' ( z ) = T ( , c ( z ))
2 and 2x 2y 2 impl . 2 2
Aggregation Method
1
Aggregation Method is Sum or a S-norm such as Max.

2
c' ( z ) = Agg .( c ' ( z ), c ' ( z ))

24/28
Fuzzy Reasoning
Graphics representation: And method: min, Implication: min, Aggr. : Max
A A1
X
B B1
1
C1
Y Z
A A2
X
B B2
2
C2
Y Z
T-norm
A
x is A X
B C
y is B Y z is C Z
25/28
Fuzzy Reasoning: MATLAB Demo

>> ruleview mam21
26/28
Other Variants
Some terminology:
Degrees of compatibility (match) Firing strength Qualified (induced) MFs Overall output MF
27/28
Assignment #2
3-2 ,3-4 , and 3-11 from ch.3 (Jang) Note: you have to send me by email figures in 3-11 Dead line: 25/7/89
28/28

Chap 3: Fuzzy Rules and Fuzzy Reasoning

Загружено:

Сведения о документе

Исходное описание:

Оригинальное название

Авторское право

Доступные форматы

Поделиться этим документом

Поделиться или встроить документ

Параметры публикации

Этот документ был вам полезен?

Это неприемлемый материал?

Авторское право:

Доступные форматы

Chap 3: Fuzzy Rules and Fuzzy Reasoning

Загружено:

Авторское право:

Доступные форматы

Fuzzy Rules and Fuzzy Reasoning