NPTEL Online Certification Courses

Indian Institute of Technology Kharagpur

Course Name: Fuzzy Logic and Neural Networks

Assignment- Week 2
TYPE OF QUESTION: MCQ
Number of questions: 10 Total mark: 10 X 1 = 10
______________________________________________________________________________

QUESTION 1:
Precise fuzzy modeling (Takagi and Sugeno’s Approach) is characterized by

a. High interpretability and high accuracy

b. Low interpretability and low accuracy
c. High interpretability but low accuracy
d. Low interpretability but high accuracy

Correct Answer: d

______________________________________________________________________________

QUESTION 2:
In Mamdani approach of fuzzy reasoning tool, the strength of a fired rule is determined using

a. OR operator
b. AND operator
c. UNION operator
d. Multiplication operator

Correct Answer: b

______________________________________________________________________________
QUESTION 3:
The performance of a fuzzy logic controller depends on its

a. Data base only

b. Rule base only
c. Both data base as well as rule base
d. Neither data base nor rule base

Correct Answer: c

_____________________________________________________________________________
 NPTEL Online Certification Courses
Indian Institute of Technology Kharagpur

QUESTION 4:
The concept of fuzzy sets can be used in

a. Fuzzy reasoning tool only

b. Clustering only
c. Both fuzzy reasoning tool as well as clustering
d. Neither fuzzy reasoning tool nor clustering

Correct Answer: c

______________________________________________________________________________

QUESTION 5:
In Mamdani approach of fuzzy reasoning tool, let us assume that two rules are getting fired for a set of
inputs. The combined fuzzified output considering these two fired rules is found to be as shown in Fig. A.
The membership function distributions are assumed to be Gaussian (𝐺) with different mean and
standard deviation values.

Fig. A: Combined fuzzified output considering two fired rules.

By using the Mean of Maxima method, the crisp output is found to be equal to

a. 120
b. 160
c. 140
d. 180
 NPTEL Online Certification Courses
Indian Institute of Technology Kharagpur

Correct Answer: a

Detailed Solution: Mean of Maxima method

The maximum value of membership (𝜇) (that is, 0.8) occurs on the Gaussian distribution (𝐺1),
whose mean value is kept equal to 120. Therefore, the crisp output becomes equal to 120.

___________________________________________________________________________

QUESTION 6:
Which one of the following statements is TRUE for a fuzzy reasoning tool?

a. Its inputs are to be represented in normalized scale of (0.0, 1.0) only.

b. Its inputs are to be represented in normalized scale of (-1.0, +1.0) only.
c. Its inputs are to be represented in real scales only.
d. Its inputs can be represented in either real scales or normalized scales.

Correct Answer: d

___________________________________________________________________________

QUESTION 7:
Fuzzy reasoning tool aims to

a. obtain the clusters of the data points based on their similarity values.
b. map the higher dimensional data into the lower dimension(s) for the purpose of
visualization.
c. determine the input-output relationships of the data set.
d. remove the noisy data from a data set.

Correct Answer: c

______________________________________________________________________________
QUESTION 8:

Which one of the following statements is TRUE?

a. Takagi and Sugeno’s approach can provide more accuracy compared to

Mamdani approach.
b. Mamdani approach can provide more accuracy compared to Takagi and
Sugeno’s approach.
 NPTEL Online Certification Courses
Indian Institute of Technology Kharagpur

c. Both Mamdani approach as well as Takagi and Sugeno’s approach can provide
the same level of accuracy.
d. Accuracy of Mamdani approach is not comparable to that of Takagi and Sugeno’s
approach.

Correct Answer: a

______________________________________________________________________________
QUESTION 9:

In Mamdani approach of fuzzy reasoning tool, let us consider that two rules are going to be fired for a
set of inputs. The fuzzified outputs of two fired rules are shown in Figs. B and C.

(8.0, 0.6) (10.0, 0.6)

(6.0, 0.0)
(12.0, 0.0)

Fig. B: Fuzzified output of first fired rule.

(11.0, 0.5) (15.0, 0.5)

(9.0, 0.0)
(17.0, 0.0)

Fig. C: Fuzzified output of second fired rule.

By using the Center of Sums method, the crisp output is found to be equal to

a. 10.67
b. 9.80
c. 11.22
d. 16.28

Correct Answer: c
 NPTEL Online Certification Courses
Indian Institute of Technology Kharagpur

Detailed Solution: Center of sums method

Refer to Fig. B (corresponding to the first fired rule):

1
𝐴𝑟𝑒𝑎 𝐴1 = (6.0 + 2.0) × 0.6
2

= 2.4

𝐶𝑒𝑛𝑡𝑒𝑟 𝑜𝑓 𝑎𝑟𝑒𝑎 𝐶1 = 9.0

Refer to Fig. C (corresponding to the second fired rule):

1
𝐴𝑟𝑒𝑎 𝐴2 = (8.0 + 4.0) × 0.5
2

= 3.0

𝐶𝑒𝑛𝑡𝑒𝑟 𝑜𝑓 𝑎𝑟𝑒𝑎 𝐶2 = 13.0

𝐴1 𝐶1 + 𝐴2 𝐶2
𝐶𝑟𝑖𝑝𝑠 𝑜𝑢𝑡𝑝𝑢𝑡 = ( )
𝐴1 + 𝐴2

2.4 × 9.0 + 3.0 × 13.0

=
2.4 + 3.0
21.6 + 39.0
=
5.4
= 11.22

___________________________________________________________________

QUESTION 10:
Centroid method of defuzzification is used in

a. Takagi and Sugeno’s approach of fuzzy reasoning tool only.

b. Mamdani approach of fuzzy reasoning tool only.
c. neither Takagi and Sugeno’s approach nor Mamdani approach of fuzzy
reasoning tool.
d. both Mamdani approach as well as Takagi and Sugeno’s approach of
fuzzy reasoning tool

Correct Answer: b
 NPTEL Online Certification Courses
Indian Institute of Technology Kharagpur

______________________________________________________________________________

************END*******