What is Fuzzification?

Fuzzification may be defined as the process of transforming a crisp set to a fuzzy set or a fuzzy
set to fuzzier set. Basically, this operation translates accurate crisp input values into linguistic
variables. In a number of engineering applications, it is necessary to defuzzify the result or rather
"fuzzy result" so that it must be converted to crisp result.
Fuzzification is done by recognizing various assumed crisp quantities as the non-deterministic and
completely uncertain in nature. This uncertainty may be emerged because of imprecision and
uncertain that lead variables to be presented by a membership function because they can be fuzzy
in nature.
Fuzzification translates the crisp input data into linguistic variables which are represented by fuzzy
sets. After that, it applies the membership functions to measure and determine the degree of
membership.

What is Defuzzification?

Defuzzification may be defined as the process of reducing a fuzzy set into a crisp set or to convert
a fuzzy member into a crisp member. Mathematically, the process of Defuzzification is also
called "rounding it off". Defuzzification basically transforms an imprecise data into precise data.
However, it is a relatively complex to implement defuzzification as compared to fuzzification.
Defuzzification is basically the reverse process of fuzzification because it converts the fuzzy data
into crisp data. In some practical implementations, the defuzzification process is required for crisp
control actions to operate the control.
Now, let us discuss the differences between fuzzification and defuzzification.

Difference between Fuzzification and Defuzzification

The following are the important difference between Fuzzification and Defuzzification −

Key Fuzzification Defuzzification

Fuzzification is the process of Defuzzification is the process of

transforming a crisp set to a reducing a fuzzy set into a crisp set or
Definition
fuzzy set or a fuzzy set to converting a fuzzy member into a
fuzzier set. crisp member.

Fuzzification converts a precise Defuzzification converts an imprecise

Purpose
data into imprecise data. data into precise data.

Example Voltmeter. Stepper motor, D/A converter.

Inference, Rank ordering, Maximum membership principle,
Methods
Angular fuzzy sets, Neural Centroid method, Weighted average
used
network. method, Center of sums.

Fuzzification is easy. Defuzzification is quite complex to

Complexity
implement.

Fuzzification uses if-then rules Defuzzification uses center of gravity

Approach
to fuzzify the crisp value. methods to get centroid of sets.

Architecture of a Fuzzy Logic System

In the architecture of the Fuzzy Logic system, each component plays an important role.
The architecture consists of the different four components which are given
below.
1. Rule Base
2. Fuzzification
3. Inference Engine
4. Defuzzification
Following diagram shows the architecture or process of a Fuzzy Logic system:

1. Rule Base

Rule Base is a component used for storing the set of rules and the If-Then conditions given by the
experts are used for controlling the decision-making systems. There are so many updates that come
in the Fuzzy theory recently, which offers effective methods for designing and tuning of fuzzy
controllers. These updates or developments decreases the number of fuzzy set of rules.
2. Fuzzification

Fuzzification is a module or component for transforming the system inputs, i.e., it converts the
crisp number into fuzzy steps. The crisp numbers are those inputs which are measured by the
sensors and then fuzzification passed them into the control systems for further processing. This
component divides the input signals into following five states in any Fuzzy Logic system:

o Large Positive (LP)

o Medium Positive (MP)
o Small (S)
o Medium Negative (MN)
o Large negative (LN)

3. Inference Engine

This component is a main component in any Fuzzy Logic system (FLS), because all the
information is processed in the Inference Engine. It allows users to find the matching degree
between the current fuzzy input and the rules. After the matching degree, this system determines
which rule is to be added according to the given input field. When all rules are fired, then they are
combined for developing the control actions.

4. Defuzzification

Defuzzification is a module or component, which takes the fuzzy set inputs generated by
the Inference Engine, and then transforms them into a crisp value. It is the last step in the process
of a fuzzy logic system. The crisp value is a type of value which is acceptable by the user. Various
techniques are present to do this, but the user has to select the best one for reducing the errors.

What is fuzzy operator tuning?

The tuning method fits the membership functions of the fuzzy rules given by the experts with the
inference system and the defuzzification strategy selected, obtaining high-performance
membership functions by minimizing an error function defined using a set of evaluation input-
output data.
What is defuzzification?
Defuzzification is the process of converting fuzzy variables into crisp or numeric values. It is often
used in fuzzy control systems and is necessary because fuzzy results can't be used directly in
applications.

Methods: There are several methods for defuzzification, including the centroid of area,
smallest of maximum, largest of maximum, and bisector of area. The centroid method is
a common choice.
Purpose: Defuzzification is needed because controller circuits in real-world
applications can only understand scalar inputs.
Selection: The defuzzification method chosen depends on the context of the design.

Defuzzification methods – Solved examples

Defuzzification methods, as we know, are used to convert defuzzified output put of fuzzy inference
engine to crisp value. In the previous few articles, we already have discussed maxima methods,
the Center of Gravity (CoG) method, the Center of Sums (CoS) method, the Center of Largest
Area (CoA) method etc.
In this article, we will see examples of various defuzzification techniques.
Example: Find crisp value corresponding to the following fuzzy output sets using various
defuzzification methods.
Labeled fuzzy output function

Defuzzification methods
A number of defuzzification methods are known. Such as
1. Lambda-cut method
2 Weighted average method
3 Maxima methods
4 Centroid methods

Lambda-cut method
Lmabda-cut method is applicable to derive crisp value of a fuzzy set or relation. Thus
1. Lambda-cut method for fuzzy set
2. Lambda-cut method for fuzzy relation
In many literature, Lambda-cut method is also alternatively termed as
Alph-cut method.
Lamda-cut method for fuzzy set
1. In this method a fuzzy set A is transformed into a crisp set A λ for given value of λ (0
<= λ <=1)2
2. In other-words, Aλ = { x | µA(X) >= λ } λ € (0,1)
3. That is, the value of Lambda-cut set Aλ is x, when the membership value
corresponding to x is greater than or equal to the specified λ.
4 This Lambda-cut set A_ is also called alpha-cut set.
The set Aλ is called a weak lambda-cut set if it consists of all the elements of a fuzzy set
whose membership functions have values greater than or equal to a specified value. On the other
hand, the set Aλ is called a Strong lambda-cut set if it consists of all the elements of a fuzzy set
whose membership functions have values strictly greater than specified value. A strong λ-cut set
is given by

Some properties of _-cut relations

If R and S are two fuzzy relations, defined with the same fuzzy sets
over the same universe of discourses, then
1. (R U S) λ = R λ U S λ
2. (R Π S) λ = R λ Π S λ
3. ( ¯R) λ ≠ R λ
4. For λ<= α, where α is between 0 and 1 , then R α ⸦ R λ

Output of a fuzzy System

The output of a fuzzy system can be a single fuzzy set or union of two
or more fuzzy sets.
To understand the second concept, let us consider a fuzzy system with n-rules.
R1: If x is A1 then y is B1
R2: If x is A2 then y is B2
........................................
........................................
Rn: If x is An then y is Bn
In this case, the output y for a given input x = x1 is possibly B = B1 U B2 U:::::Bn
Debasis
Fuzzy membership functions
Membership function defines the fuzziness in a fuzzy set irrespective of the elements in the set,
which arediscrete or continuous. The membership functions are generally represented in graphical form.

There exist certain limitations for the shapes used to represent graphical form of membership
function. The rules that describe fuzziness graphically are also fuzzy.

Membership function can be thought of as a technique to solve empirical problems on the basis
of experience rather than knowledge. Available histograms and other probability information canalso
help in constructingthe membership function.

There are several ways to characterize fuzziness; In a similar way, there are severalways to
graphically construct a membership function that describes fuzziness.

Features of the Membership Functions

The membership function defines allthe information contained in a fuzzy set.A fuzzy set A in the
universe of discourse X can be definedas a set of ordered pairs:

where is called membership function of .The membership function

maps X to the membershipspace M, i.e.,

The membership value ranges in the interval [0,1], i.e the range of the membership function is a
subset of the non-negative real numbers whose supremum is finite .

Basic features of the membership functions

The Figure below shows the basic features of the membership functions. The three main basic
features involvedin characterizing membership function are the following.

l. Core:The core of a membership function for some fuzzy set is defined as that region of universe is
characterized by complete membership in the set . The core has elements x of the universe such that
The core of a fuzzy set may be an empty set.

2. Support:The support of a membership function for a fuzzy set is defined as that region of universe
thatis characterized by a nonzero membership in the set . The support comprises elements x from the
universesuch that

A fuzzy set whose support is a single element in Xwith is referred to as a fuzzy singleton.

3.Boundary: The support of a membership function for a fuzzy set is defined as that region of
universecontaining elements that have a non zero but not complete membership. The boundary
comprises thoseelements of x of the universe such that

Types of fuzzy set

1) Normal Fuzzy set
A fuzzy set whose membership function has at least one elementx in the universe
whose membership value is unity is callednormal fuzzy set. The element for which the
membership is equal to 1 is called prototypicalelement.

2) Subnormal Fuzzy set

A fuzzy set where in no membershipfunction has its value equal to 1 is called

subnormal fuzzy set.
3) Convex Fuzzy set
A convex fuzzy set has a membership function whose membership values are strictly monotonically
increasingor strictly monotonically decreasing or strictly monotonically increasing than strictly
monotonically decreasingwithincreasing values for elements in the universe .

4) Nonconvex Fuzzy set

Afuzzy set possessing characteristics opposite to that of convex fuzzy set is called
nonconvexfuzzyset, i.e., the membership values of the membership functionare not strictly
monotonically increasing or decreasing or strictly monotonically increasing than decreasing.
Fuzzification
Fuzzification is the process of transforming a crisp set to a fuzzy set or a fuzzy set to a fuzzier set,
i.e.,crisp quantities are converted to fuzzy quantities. This operation translates accurate crisp input
values into linguistic variables.

Fuzzy set , a common fuzzification algorithm is performed by keeping µi

constant and xi being transformed to a fuzzy set Q(xi) depicting the expression about xi. The fuzzy set
Q(xi) is referred to as the kernel of fuzzification. The fuzzified set A can be expressed as

where the symbol ~ means fuzzified.

This process of fuzzification is called support fuzzification (sfuzzification). There is another

method of fuzzification called grade fuzzification (g-fuzzification) whereXiis kept constant and µiis
expressed as a fuzzy set. Thus, using these methods, fuzzification is carried out.

Methods of Membership Value Assignments

The method of assigning membership values are as follows:

1. Intuition
2. Inference
3. Rank Ordering
4. Angular Fuzzy Sets
5. Neural Networks

6. Genetic Algorithm

7. Inductive Reasoning.

1.Intuition
Intuition method is based upon the common intelligence ofhuman. It is the capacity of the human to
developmembership functions on the basis of their own intelligence and understanding capacity. There
should be an in-depth knowledge of the application to whichmembership value assignment has to be
made.

The Figure below shows various shapes of weights of people measured in kilogram in the
universe. Each curve is a membershipfunction corresponding to various fuzzy (linguistic) variables; such
as very light, light, normal, heavy andvery heavy.
The curves are based on context functions and the human developing them. For example, if
theweights are referred to range of thin persons we get one set of curves, and if they are referred to
range ofnormal weighing persons we get another set and so on. The main characteristics of these curves
for their usagein fuzzy operationsare based on their overlapping capacity.

2)Inference
The inference method uses knowledge to perform deductive reasoning. Deduction achieves conclusion
bymeans of forward inference. There are various methods for performing deductive reasoning.

Here the knowledgeof geometrical shapes and geometry is used for defining membership
values. The membership functionsmay be defined by various shapes: triangular, trapezoidal, bell-
shaped, Gaussian and so on. The inferencemethod here is discussed via triangular shape.

Consider a triangle, where X, Yand Zare the angles such that

and let u be the universe of tri angles, i.e.,

There are various types of triangles available. Here a few are considered to explain inference
methodology:

= isosceles triangle (approximate)

= equilateral triangle (approximate)
= right-angle triangle (approximate)
= isosceles and right-angle triangle (approximate) = other triangles

The membership values of approximate isosceles triangle is obtained using

the following definition, wher e: and

If X=Y or Y=Z and if X=120º,Y=60º and Z=0º , we get

The membe rship value of approximate right - angle triangle is given by·

If X= 90°, the membership value of a right-angle triangle is1, andif X=

180º,the membership value becomes 0:

The membership value of approximate isosceles right angle triangle is obtained by raking the logical
intersection of the approximate isosceles and approximate right-angle triangle membership
function.i.e.,
,

and it is given by,

The membership function for a fuzzy equil ateral tr iang l e is given by

The membership function of other triangles, denoted by, is the complement of the. logical union of

and i.e.,

By using De Morgan's law, we get

The membership value can be obtained using the equation

Rank Ordering

The formation of government is based on the polling concept; to identify a best student, ranking
may beperformed; to buy a car, one can ask for several opinions and so on.

All the above mentioned activities are carriedout on the basis of the preferences made by an
individual, a committee, a poll and other opinion methods.

This methodology can be adapted to assign membership values to a fuzzy variable. Pairwise
comparisons enable us to determine preferences and this results in determining the order of the
membership.
Lambda –cuts for fuzzy sets (Alpha-Cuts)
Consider a fuzzy set The set ,called the lambda (λ)- cut or (alpha cut [α]-cut)set, is a crisp
set of the fuzzy set and is defined as follows:

The setAλ.is called a weak lambda-cut set if it consists of all the elements of a fuzzy set whose
membershipfunctions have values greater than or equal to a specified value. On the other hand, the
setAλ, is called a Strong lambda-cut set if it consists ofall the elements of a fuzzy set whose membership
functions have values strictlygreater than specified value. A strong λ-cut set is given by

The properties of λ - cut sets are as follows

The fourth property is essentially used in graphics. The figure below shows a continuousvalued
fuzzy with two λ-cut values.

The Figure below shows the features of the membership functions .

Defuzzification Methods
Defuzzification is the process of conversion of a fuzzy quantity into a precise quantity. The
output of a fuzzy process may be union of two or more fuzzy membership functions defined on the
universe of discourse of the output variable.

Consider a fuzzy output comprising two parts: the first part, , a triangular membership shape as
shown in following Figure:

Th e second pa rt , , a trapezoidal shape as sh o wn in Figure below:

The union of these two membership functions, i.e., involves the m ax

operatorwhich is going to be the outer envelope of the two shapes shown in
Figures above. The final shape of is shown in figure below:

A fuzzy output process may involve many output parts, and the membership function
representingeachpart of the output can have any shape. The membership function of the fuzzy output
need not always be normal. In general,

Defuzzification methods include the following:

1. Max-membership principle.
2. Centroid method 3. Weighted average
method.
4. Mean-max membership.
5. Center of sums.
6. Center oflargest area.
7. First of maxima, last of maxima.

1) Max-Membership Principle

This method is also known as height method and is limited to peak output functions. This
method is givenby the algebraic expression

The method is illustrated in Figure below:

2) Centroid Method

This method is also known as center of mass, center of area or center of gravity method.It is the
mostcommonly used defuzzification method. The defuzzified output x* is defined as

where the symbol denotes an algebraic integration. This method is

illustrated inFigure below:

3) Weighted Average Method

This method is valid for symmetrical output membershipfunction only. Each membership
function is weighted by its maximum membership value. The output in this cas is given by,

whereƩdenotes algebraic sum and is the maximum of the

ithmembership function. The methodis illustrated in Figure below, where two fuzzy sets are considered.
From the Figure, we notice that thedefuzzified output is given by

4) Mean-Max Membership

This method is also known as the middle of the maxima. This is closely related to max-
membershipmethod, except that the locations of the maximum membership can be nonunique. The
output here isgiven by

This is illustrated in Figure below:

From Figure above, we notice that the defuzzified output is given by,

wherea and b are as shown in the figure.

5) Center of Sums

This method employs the algebraic sum of the individual fuzzy subsets instead oftheir union.
The calculations here are very fast, but the main drawback is that intersectingareas are added twice.
The defuzzified value x* is given by

The Figure below illustrates the center of sums method. In center of sums method, the weights
are the areas ofthe respective membership functions, whereas in the weighted average method the
weights are individual membership
v al ues .

6) Center of Largest Area

This method can be adopted when the output consists of at least two convex fuzzy subsets which
are not overlapping. The output in this case is biased towards side of one membership function. When
output fuzzyset has at least two convex regions, then the center of gravity ofthe convex
fuzzysubregionhaving the largest area is used to obtain the defuzzified value x*.This value is given by
Where is the convex subregion that has t he largest area making up
. Figure below illustr a tes the cent er oflargest area.

7) First of Maxima (Last of Maxima)

This method uses the overall output or union of all individual output fuzzysets for determining
the smallest value of the domain with maximized membershipin .The steps used for obtaining
x*areas follows:

1. Initially, the maximum height in the union is found:

wh ere sup is supremum, i.e., the l east upperbou nd :

2. Then the first of maxima is found:

whereinf is the minimum, i.e., the greatest lower bound.

3. After this the last maxima is found:

where sup= supremum, i.e., the least upperbound; inf =infimum, i.e., the greatest lower bound.
This is illustrated in Figure below. From Figure below, the first maxima is also the last maxima, and since
it isa distinct max, it is also the mean-max.