fuzzy logic e. fuzzy inference engine. “antecedent” “consequent”

22
Fuzzy Logic E. Fuzzy Inference Engine

Upload: charity-barnett

Post on 17-Dec-2015

263 views

Category:

Documents


6 download

TRANSCRIPT

Page 1: Fuzzy Logic E. Fuzzy Inference Engine. “antecedent” “consequent”

Fuzzy Logic

E. Fuzzy Inference Engine

Page 2: Fuzzy Logic E. Fuzzy Inference Engine. “antecedent” “consequent”

“antecedent”

“consequent”

Page 3: Fuzzy Logic E. Fuzzy Inference Engine. “antecedent” “consequent”

Assume that we need to evaluate student applicants based on their GPA and GRE scores.For simplicity, let us have three categories for each score [High (H), Medium (M), and Low(L)]Let us assume that the decision should be Excellent (E), Very Good (VG), Good (G), Fair (F) or Poor (P)An expert will associate the decisions to the GPA and GRE score. They are then Tabulated.

Page 4: Fuzzy Logic E. Fuzzy Inference Engine. “antecedent” “consequent”

Fuzzy Linguistic Variables

Fuzzy Logic

Antecedent Consequent

Fuzzy if-then RulesIf the GRE is HIGH and the GPA is HIGH

then the student will be EXCELLENT.If the GRE is LOW and the GPA is HIGH

then the student will be FAIR.etc

Page 5: Fuzzy Logic E. Fuzzy Inference Engine. “antecedent” “consequent”

Antecedents

Consequents

Page 6: Fuzzy Logic E. Fuzzy Inference Engine. “antecedent” “consequent”

Fuzzifier converts a crisp input into a vector of fuzzy membership values. The membership functions reflects the designer's knowledge provides smooth transition between

fuzzy sets are simple to calculateTypical shapes of the membership function are Gaussian, trapezoidal and triangular.

Page 7: Fuzzy Logic E. Fuzzy Inference Engine. “antecedent” “consequent”

GRE = {L , M ,

H }

GRE

Page 8: Fuzzy Logic E. Fuzzy Inference Engine. “antecedent” “consequent”

GPA

GPA = {L , M ,

H }

Page 9: Fuzzy Logic E. Fuzzy Inference Engine. “antecedent” “consequent”

c

Page 10: Fuzzy Logic E. Fuzzy Inference Engine. “antecedent” “consequent”

Transform the crisp antecedents into a vector of fuzzy membership values.Assume a student with GRE=900 and GPA=3.6. Examining the membership function gives

GRE = {L = 0.8 , M = 0.2 , H = 0}

GPA = {L = 0 , M = 0.6 , H = 0.4}

Page 11: Fuzzy Logic E. Fuzzy Inference Engine. “antecedent” “consequent”

GRE

900

0.2

0.8

Page 12: Fuzzy Logic E. Fuzzy Inference Engine. “antecedent” “consequent”

3.6

0.40.6

Page 13: Fuzzy Logic E. Fuzzy Inference Engine. “antecedent” “consequent”

0.8 0.2 0.0

0.0

0.6

0.4

Page 14: Fuzzy Logic E. Fuzzy Inference Engine. “antecedent” “consequent”

0.8 0.2 0.0

0.0

0.6

0.4

0.0 0.0 0.0

0.6 0.2 0.0

0.4 0.2 0.0

Page 15: Fuzzy Logic E. Fuzzy Inference Engine. “antecedent” “consequent”

0.8 0.2 0.0

0.0

0.6

0.4

0.0 0.0 0.0

0.6 0.2 0.0

0.4 0.2 0.0

The student is GOOD if

(the GRE is HIGH and the GPA is MEDIUM)OR(the GRE is MEDIUM and the GPA is MEDIUM)The consequent GOOD has a membership of max(0.6,0.2)=0.6

Page 16: Fuzzy Logic E. Fuzzy Inference Engine. “antecedent” “consequent”

0.8 0.2 0.0

0.0

0.6

0.4

0.0 0.0 0.0

0.6 0.2 0.0

0.4 0.2 0.0

E = 0.0

VG = 0.0

F = max( 0.0, 0.4)

= 0.4

G = max( 0.6, 0.2)

= 0.6

B = max( 0,0,0.2)

= 0.2

Page 17: Fuzzy Logic E. Fuzzy Inference Engine. “antecedent” “consequent”

0.6

0.4

0.2

c

Page 18: Fuzzy Logic E. Fuzzy Inference Engine. “antecedent” “consequent”

Converts the output fuzzy numbers into a unique (crisp) numberCenter of Mass Method: Add all weighted curves and find the center of mass

0.6

0.4

0.2

c

Page 19: Fuzzy Logic E. Fuzzy Inference Engine. “antecedent” “consequent”

c

0.60.40.2

Center of Mass Method: Add all clipped curves and find the center of mass

Page 20: Fuzzy Logic E. Fuzzy Inference Engine. “antecedent” “consequent”

An Alternate Approach: Fuzzy set with the largest membership value is selected.Fuzzy decision:

{B, F, G,VG, E} = {0.2, 0.4, 0.6, 0.0, 0.0}Final Decision (FD) = Good StudentIf two decisions have same membership max, use the average of the two.

Page 21: Fuzzy Logic E. Fuzzy Inference Engine. “antecedent” “consequent”

CELN MN SN ZE SP MP LP

LN LN LN LN LN MN SN SNMN LN LN LN MN SN ZE ZESN LN LN MN SN ZE ZE SP

E ZE LN MN SN ZE SP MP LPSP SN ZE ZE SP MP LP LPMP ZE ZE SP MP LP LP LPLP SP SP MP LP LP LP LP

Page 22: Fuzzy Logic E. Fuzzy Inference Engine. “antecedent” “consequent”

-3 -2 -1 0 1 2 3

LN MN SN ZE SP MP LP

0

1

m

CE

0 1 3 6-1-3-60

1

m

ECU

ZE SP MP LPSNMNLN