4. Introduction
.
In contrast to Classical Set , Fuzzy set does not have crisp boundary.
It is Characterized by Membership functions that gives flexibility that
uses linguistic expression.
Fuzziness comes from uncertain and imprecise nature of abstract
thoughts and concepts.
Membership function assigns each object a grade of membership ranging
between 0 to 1.
Grade of membership depends on the context in which it is considered.
The notion of inclusion, union, intersection, complement and relation can
be extended
5. Introduction
.
In real world, Human thinking and reasoning represents fuzzy
information.
Developed system will not be able to answer to many questions when it
is a classical set.
We are in need to develop a system that should be built with incomplete
and unreliable information.
So we need to describe a set with unambiguous boundary, there is a
uncertainty in set boundary.
Thus fuzzy logic is able to handle imprecise concepts.
6. Fuzzy Sets
.
If X is an universe of discourse and x is a particular element of X,
then a fuzzy set A defined on X and can be written as a collection of
ordered pairs
A = {(x, µÃ (x)), x є X }
Let for example X be the Tall Person with the membership Tall takes
value between [0,1]
Here Tall is the Fuzzy Term with µ as its membership function
7. Membership function
.
It measures the degree of similarity of an element to a fuzzy set.
It can be chosen by user arbitrarily based on user experience.
Or it can be chosen by machine learning models
The membership function can be
Triangular
Trapezoidal
Gaussian
8. Triangular Member function
.
Three parameters are required to specify the membership function
values.
{ a, b, c} where a is the lower boundary, c is upper boundary with
value 0 and b is the center with the highest value 1.