Scribd
Upload
657 views

10 - Sugeno-TSK Model

The document discusses several types of fuzzy rule-based models for function approximation, including Mamdani, TSK, Tsukamoto, and standard additive models. The TSK (Takagi-Sugeno-Kang) model replaces the fuzzy consequent of if-then rules with a crisp function, allowing faster computation compared to Mamdani models. TSK models can be zero-order, first-order, or higher-order depending on the complexity of the consequent function. Tsukamoto models represent consequents as fuzzy sets with monotonic membership functions. Standard additive models provide efficient computation through pre-computing rule weights and centroids.

Uploaded by

Nidhi Arora
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
657 views

10 - Sugeno-TSK Model

The document discusses several types of fuzzy rule-based models for function approximation, including Mamdani, TSK, Tsukamoto, and standard additive models. The TSK (Takagi-Sugeno-Kang) model replaces the fuzzy consequent of if-then rules with a crisp function, allowing faster computation compared to Mamdani models. TSK models can be zero-order, first-order, or higher-order depending on the complexity of the consequent function. Tsukamoto models represent consequents as fuzzy sets with monotonic membership functions. Standard additive models provide efficient computation through pre-computing rule weights and centroids.

Uploaded by

Nidhi Arora
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
You are on page 1/ 23

Fuzzy Rule-based Models

*NeurofuzzyandSoftComputingJ.Jang,C.Sun,and,E.Mizutani,PrenticeHall1997

A Classification of Fuzzy Rule-based models for


function approximation
FuzzyRulebasedModels
AdditiveRuleModels

NonAdditiveRuleModels

TSKModel
(TakagiSugenoKang)
MamdaniModel
(Mamdani)

TsukamotoModel
(Tsukamoto)

StandardAdditiveModel
(Kosko)

*FuzzyLogicJ.Yen,andR.Langari,PrenticeHall1999

Mamdani model
NamedafterE.H.Mamdaniwhodevelopedfirstfuzzy
controller.
Theinputsmaybecrisporfuzzynumbers
Usesruleswhoseconsequentisafuzzyset,i.e.
Ifx1isAi1andandxnisAinthenyisCi,
wherei=1,2.M,Misthenumberofthefuzzyrules
Usesclippinginference
Usesmaxaggregation
*FuzzyLogicJ.Yen,andR.Langari,PrenticeHall1999

Why TSK?
Main motivation
to reduce the number of rules required by the
Mamdani model
For complex and high-dimensional
problems
develop a systematic approach to
generate fuzzy rules from a given inputoutput data set
TSK model replaces the fuzzy consequent,
(then part), of Mamdani rule with function
(equation) of the input variables

*NeurofuzzyandSoftComputingJ.Jang,C.Sun,and,E.Mizutani,PrenticeHall1997

TSK Fuzzy Rule


If x is A and y is B then z = f(x,y)
Where A and B are fuzzy sets in the
antecedent, and
Z = f(x,y) is a crisp function in the
consequence, e.g f(x,y)=ax+by+c.
Usually f(x,y) is a polynomial in the input variables
x and y, but it can be any function describe the
output of the model within the fuzzy region
specified by the antecedence of the rule.

*NeurofuzzyandSoftComputingJ.Jang,C.Sun,and,E.Mizutani,PrenticeHall1997

First order TSK Fuzzy Model


f(x,y) is a first order polynomial
Example: a two-input one-output TSK
IFxisAjandyisBkthenzi=px+qy+r
The degree the input matches ith rule is typically computed using min
operator:

wi=min(Aj(x),Bk(y))

*NeurofuzzyandSoftComputingJ.Jang,C.Sun,and,E.Mizutani,PrenticeHall1997

First-Order TSK Fuzzy Model (Cont)


Each rule has a crisp output
Overall output is obtained via weighted
average (reduce computation time of
defuzzification required in a Mamdani model)

z= iwizi/ i wi

WhereWiismatchingdegreeofruleRi
(resultoftheifpartevaluation)
To further reduce computation, weighted sum may be used, I.e.

z= iwizi

*NeurofuzzyandSoftComputingJ.Jang,C.Sun,and,E.Mizutani,PrenticeHall1997

First-Order: TSK Fuzzy Model

*NeurofuzzyandSoftComputingJ.Jang,C.Sun,and,E.Mizutani,PrenticeHall1997

Example #1: Single-input


A single-input TSK fuzzy model can be
expresses as
If X is small
then Y = 0.1 X +6.4.
If X is medium then Y = -0.5X +4.
If X is large
then Y = X-2.

*NeurofuzzyandSoftComputingJ.Jang,C.Sun,and,E.Mizutani,PrenticeHall1997

Example #1: Non fuzzy rule set


If small, medium. and large are non fuzzy sets ,

then the overall input-output curve is piecewise linear.

*NeurofuzzyandSoftComputingJ.Jang,C.Sun,and,E.Mizutani,PrenticeHall1997

Example #1: Fuzzy rule set


If small, medium, and large are fuzzy sets (smooth
membership functions) , then the overall input-output
curve is a smooth one.

*NeurofuzzyandSoftComputingJ.Jang,C.Sun,and,E.Mizutani,PrenticeHall1997

Example #2 : Two-input
A two-input TSK fuzzy model with 4 rules
can be expresses as

If
If
If
If

X is small
X is small
X is large
X is large

and
and
and
and

Y is small then
Y is large then
Y is small then
Y is large then

*NeurofuzzyandSoftComputingJ.Jang,C.Sun,and,E.Mizutani,PrenticeHall1997

Z = -X +Y +1.
Z = -Y +3.
Z = -X+3.
Z = X+Y+2.

Example #2 : Two-input

*NeurofuzzyandSoftComputingJ.Jang,C.Sun,and,E.Mizutani,PrenticeHall1997

Zero-order TSK Fuzzy Model


When f is constant, we have a zero-order
TSK fuzzy model (a special case of the
Mamdani fuzzy inference system which each
rules consequent is specified by a fuzzy
singleton or a pre defuzzified consequent)
Minimum computation time

*NeurofuzzyandSoftComputingJ.Jang,C.Sun,and,E.Mizutani,PrenticeHall1997

Summary: TSK Fuzzy Model


Overall output via either weighted average or weithted
sum is always crisp
Without the time-consuming defuzzification operation,
the TSK (Sugeno) fuzzy model is by far the most popular
candidate for sample-data-based fuzzy modeling.
Can describe a highly non-linear system using a small
number of rules
Very well suited for adaptive learning.

*NeurofuzzyandSoftComputingJ.Jang,C.Sun,and,E.Mizutani,PrenticeHall1997

Tsukamoto Fuzzy Models


The consequent of each fuzzy if-then rule is
represented by a fuzzy set with monotonical MF
As a result, the inferred output of each rule
is defined as a crisp value induced by the
rules firing strength.
The overall output is taken as the weighted
average of each rules output.

*NeurofuzzyandSoftComputingJ.Jang,C.Sun,and,E.Mizutani,PrenticeHall1997

Tsukamoto Fuzzy Models

*NeurofuzzyandSoftComputingJ.Jang,C.Sun,and,E.Mizutani,PrenticeHall1997

Example: Single-input Tsukamoto fuzzy model


A single-input Tsukamoto fuzzy model
can be expresses as
If X is small
then Y is C1
If X is medium then Y is C2
If X is large
then Y is C3

*NeurofuzzyandSoftComputingJ.Jang,C.Sun,and,E.Mizutani,PrenticeHall1997

Example: Single-input Tsukamoto fuzzy model

*NeurofuzzyandSoftComputingJ.Jang,C.Sun,and,E.Mizutani,PrenticeHall1997

Standard Additive Model (SAM)


Introduced by Bart Kosko in 1996
Efficient to compute
Similar to Mamdani model, but

Assumes the inputs are crisp


Uses the scaling inference method (prod.]
Uses addition to combine the conclusions of rules
Uses the centroid defuzzification technique

*NeurofuzzyandSoftComputingJ.Jang,C.Sun,and,E.Mizutani,PrenticeHall1997

Standard Additive Model (SAM)


IFxisAiandyisBithenzisCi
thenforcrispinputsx=x0andy=y0
Z* = Centroid(i Ai(x0) Bi(y0) Ci(z) )

*NeurofuzzyandSoftComputingJ.Jang,C.Sun,and,E.Mizutani,PrenticeHall1997

Standard Additive Model (SAM)


Z* = Centroid(i Ai(x0) Bi(y0) Ci(z) )
then Z* can be represented
Z* = i (Ai(x0) Bi(y0) ) Areai gi/
i (Ai(x) Bi(y) ) Areai
Where
Areai = Ci(z) dz,

{Area of Ci}

gi = z x Ci(z) dz / Ci(z) dz

{Centroid of Ci}

*NeurofuzzyandSoftComputingJ.Jang,C.Sun,and,E.Mizutani,PrenticeHall1997

Standard Additive Model (SAM)


Main Advantage is the efficiency of its
computation, i.e.
Both Areai and gi can be pre computed!

*NeurofuzzyandSoftComputingJ.Jang,C.Sun,and,E.Mizutani,PrenticeHall1997

You might also like