• Nie Znaleziono Wyników

Zadanie 1 Graduation of fuzzy sets. First Determine the membership values of individuals, whose age is given, the set of "old." Apply the following criterion for membership function:

N/A
N/A
Protected

Academic year: 2021

Share "Zadanie 1 Graduation of fuzzy sets. First Determine the membership values of individuals, whose age is given, the set of "old." Apply the following criterion for membership function:"

Copied!
3
0
0

Pełen tekst

(1)

Zadanie 1

Graduation of fuzzy sets. First Determine the membership values of individuals, whose age is given, the set of "old."

Apply the following criterion for membership function:

name age(x) µage(x)

Ewa 33

Ola 43

Waldek 44 Marek 51

Anna 55

Mirela 57 Grzegorz 61 Marcin 67 Karol 85 Kasia 88

Then, knowing that fuzzy sets can be graded calculate the value of membership function for each person to set a "very old" based on the value of membership function of the "old":

Zadanie 2

Please suggest a function of belonging, which for a given hour will give the appropriate time of day. Use the following illustration of the solution:

Zadanie 3

Suppose we have rules:

And that the functions belonging to different classes of data are as follows:

0 0,5 1 1,5

33 43 44 51 55 57 61 67 85 88

"stary"

"bardzo stary"

(2)

Determine the risk of an insurance company for the customer:

a) Wiek = 35 AND moc samochodu = 150 KM b) Wiek = 55 AND moc samochodu = 150 KM c) Wiek = 35 AND moc samochodu = 190 KM

Zadanie 4

Assume that the system knowledge base contains the following rules:

RULE1: IF temperature is hot or warm, THEN the swimming pool is crowded.

RULE2: IF temperature is cold, THEN the swimming pool is quiet.

Membership functions for the individual sets may be as follows:

1. What is the linguistic variable here and what is the value of linguistic?

2. Construct the membership functions for temperature and number of vendors in the pool.

Additional tasks:

Report of the solution of the following two tasks will be an opportunity to increase the assessment of the subject.

1. Suppose we have a system within a simple controller that uses an error signal e and the error signal de change as input and questions are 4 rules based on fuzzy model that works:

RULE 1: IF e = P AND de = P THEN x = N RULE 2: IF e = P AND de = N THEN x = 0 RULE 3: IF e = N AND de = P THEN x = 0 RULE 4: IF e = N AND de = N THEN x = P

Suppose that the data are two fuzzy sets as the fuzzy input variables e and de: P (positive) and N (negative).

Fuzzy output variable has three values: P (positive), 0 (zero), N (negative) as shown in the figure above.

Assuming that the input variables have the following values in the collection of membership function of input:

µN(e) = 0.4; µP(e) = 0.6 i µN(de) = 0.2; i µP(de) = 0.8

(3)

a. using a Mamdani-type inference Prove that the total value of the output fuzzy set is as shown below (red line). Construct appropriate graphs.

b. Sharpen the output values using the method centroid.

c. Using the method of "zero-order Sugeno" calculate the value of output. Draw graphically.

d. Compare the results for both methods of inference.

2. Design a Mamdani-type fuzzy system, which will assess the likelihood of an accident while driving.

Input variables:

• speed (10 - 200km / h): {small, medium, fast, very fast}

• visibility (0.05 - 4km): {very poor, average, good}

The output of the system:

• The probability of an accident (0 - 1): {very small, small, medium, large}

Cytaty

Powiązane dokumenty

Hardware implementation of the rule-relational, modular fuzzy inference system allows high performance (FATI approximate reasoning method), flexibility (altering parameters of

Use the global angular momentum balance to calculate the time evolution of angular velocity Ω(t) of a rotating lawn sprinkler after the water pressure is turned on.. An arm of a

Calculate the heat flux density vector q and temperature at point A(1.0,1.5) of the configu- ration discretized using 1 finite element.. The following panel is discretized with

Which famous sportsperson appears in “The Hangover”?. What is the name of the hospital where Dr Gregory

The idea of stability in Bayesian robust analysis was developed in M¸ eczarski and Zieli´ nski [5], with some additional results in M¸ eczarski [4] and in Boraty´ nska and M¸

(For the case q = 1, this proof was also given in [11].) In fact, it shows that certain cases of Theorem (3.1) are equivalent to Doob’s results.. We end the section by deriving the

Besides these the proof uses Borel–Carath´ eodory theorem and Hadamard’s three circles theorem (the application of these last two theorems is similar to that explained in [4], pp..

The qualification function qprob A2 (x) qualifying in the medium height has the maximal value equal to 0.8 and not to 1, because 10% of persons of the height 170 cm are qualified by