Lecture 5 Fuzzy Rule
Lecture 5 Fuzzy Rule
Fuzzy Output
5
CLASSICAL PROPOSITIONS
6
CLASSICAL PROPOSITIONS
Tautologies:
Compound propositions that are always true, irrespective of
the truth values of the individual simple propositions are
called tautologies.
Tautologies are useful for reasoning, for proving theorems,
and for making deductive inferences.
For example, if A is the set of all prime numbers on the real
line universe, X,
(A = 1, A = 2, A = 3, A = 5, . . .)
1 2 3 4
9
CLASSICAL PROPOSITIONS
Tautologies:
Some common tautologies are as follows:
B ∪ B ←→ X
A ∪ X; A ∪ X ←→ X
10
CLASSICAL PROPOSITIONS
11
CLASSICAL PROPOSITIONS
Tautologies:
12
CLASSICAL PROPOSITIONS
Contradictions :
Compound propositions that are always false, regardless of
the truth value of the individual simple propositions
A ∩ Ø; A ∩ Ø.
13
CLASSICAL PROPOSITIONS
Deductive inferences:
Suppose we have a rule of the form IF A, THEN B, where A
is a set defined on universe X and B is a set defined on
universe Y.
Now suppose a new antecedent, say A', is known.
A new consequent, say B', can be inferred from the new
antecedent through the following set-theoretic formulation,
again:
14
FUZZY PROPOSITIONS
The range of truth values of fuzzy propositions is not only {0, 1},
but [0, 1].
The truth of a fuzzy proposition is a matter of degree.
Fuzzy propositions are assigned to fuzzy sets.
The logical connectives of negation, disjunction, conjunction, and
implication are also defined for a fuzzy logic.
15
FUZZY LOGIC
16
FUZZY LOGIC
Example:
17
18
FUZZY LOGIC
Approximate Reasoning:
The theoretical foundation for reasoning about imprecise
propositions
Let
19
FUZZY LOGIC
Example:
21
FUZZY RULES
Here the fuzzy classes height and weight have a given range (i.e., the
universe of discourse).
Assignment statements,
Conditional statements,
Unconditional statements.
Assignment Statements
49
METHODS OF MEMBERSHIP VALUE ASSIGNMENT
Intuition
Inference
Rank ordering
Neural networks
Genetic algorithms
Inductive reasoning
Soft partitioning
50
INTUTITION
Derived from the capacity of humans to develop
membership functions through their own
intelligence and understanding
51
TYPES OF MEMBERSHIP FUNCTIONS
The most commonly used in practice are
Triangles
Trapezoids
Bell curves
Gaussian, and
Sigmoidal
52
TRIANGULAR MF
Specified
by three
parameters {a, b, c} as
follows:
53
TRAPEZOIDAL MF
Specified
by four
parameters {a,b,c,d} as
follows:
54
GAUSSIAN MF
Specified by two
parameters {m, σ}
m
as follows:
57
SIGMOIDAL MF
Specified by two
parameters {a, c}
as follows:
a c
61
• Find “Very Small”, “Not Very Small”, and “Intensely Small”
62
63
INFERENCE
Use knowledge to perform deductive reasoning
64
INFERENCE : EXAMPLE
In the identification of a triangle
Let A, B, C be the inner angles of a triangle
Where A ≥ B ≥ C
Let U be the universe of triangles, i.e.,
U = {(A,B,C) | A ≥ B ≥ C ≥ 0; A+B+C = 180°}
Let’s define a number of geometric shapes
I Approximate isosceles triangle
R Approximate right triangle
IR Approximate isosceles and right triangle
E Approximate equilateral triangle
T Other triangles 65
INFERENCE : EXAMPLE
We can infer membership values for all of these
triangle types through the method of inference
For Isosceles,
µi (A,B,C) = 1- 1/60* min(A-B, B-C)
If A=B OR B=C THEN µi (A,B,C) = 1;
If A=120°,B=60°, and C =0° THEN µi (A,B,C) = 0.
66
INFERENCE : EXAMPLE
For right triangle,
µR (A,B,C) = 1- 1/90* |A-90°|
If A=90° THEN µR (A,B,C) = 1;
If A=180° THEN µR (A,B,C) = 0.
67
INFERENCE : EXAMPLE
For equilateral triangle
µE (A,B,C) = 1 - 1/180° * (A-C)
When A = B = C then µE (A,B,C) = 1,
A = 180° then µE (A,B,C) = 0
69
INFERENCE : EXAMPLE
The membership values for the fuzzy triangle
70
RANK ORDERING
Assessing preferences by a single individual, a
committee, a poll, and other opinion methods can be
used to assign membership values to a fuzzy variable
71
RANK ORDERING: EXAMPLE
Suppose 1000 people respond to a questionnaire about their pair
wise preferences among five colors, X = {red, orange, yellow, green,
blue}.
Define a fuzzy set as on the universe of colors “best color”
Following Table is a summary of the opinion survey. In this table,
for example, out of 1000 people 517 preferred the color red to the
color orange, 841 preferred the color orange to the color yellow, and
so on.
72
RANK ORDERING: EXAMPLE
Membership function for best color
73