Scribd
Upload
18 views104 pages

Week9 Softcomp

The document contains solutions to a series of questions related to rough set theory, focusing on concepts such as boundary regions, dependency, approximations, and accuracy of classification. It discusses the characteristics of rough sets, including lower and upper approximations, and provides calculations for various scenarios. The primary aim is to evaluate the significance of attributes and the precision of classifications within rough set theory.

Uploaded by

AJ - The PES Lover
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
18 views104 pages

Week9 Softcomp

The document contains solutions to a series of questions related to rough set theory, focusing on concepts such as boundary regions, dependency, approximations, and accuracy of classification. It discusses the characteristics of rough sets, including lower and upper approximations, and provides calculations for various scenarios. The primary aim is to evaluate the significance of attributes and the precision of classifications within rough set theory.

Uploaded by

AJ - The PES Lover
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

Soft Computing Techniques

Week-09 Assignment-09 (Solution)

1. (c). The boundary region in rough sets represents elements that are indistinguishable between being
inside and outside.

2. (b). Dependency is used to evaluate the significance of an attribute in rough set theory.

3. (c). In rough set theory, the boundary region of a set is the difference between upper and lower
approximations.

4. (c). Unique combinations of A1 and A2 are (1, 0), (1, 1), (0, 0), (0, 1). Each unique combination forms
a distinct equivalence class. So, we get 4 equivalence classes.

5. (a). A rough set X is internally β– undefinable if and only if B(X) = ϕ and B̄(X) ̸= U.

6. (a). The lower approximation of a set in rough set theory represents the set of elements that definitely
belong to the target set.

7. 0, range is -0.9 to 0.1.


Given A = {x1 , x3 , x6 } and the equivalence classes : {x1 , x2 }, {x3 , x4 }, {x5 , x6 }
Now, for {x1 , x2 }, x1 ∈ A but x2 ∈/ A. So, {x1 , x2 } do not entirely contained in A. Similarly, {x3 , x4 }
and {x5 , x6 } are not entirely contained in A. So, lower app. of A is empty set. Therefore, cardinality
of lower approximation of A is 0.

8. 3, range is 2.99 to 3.01. n o


Given that, A = {2, 3, 4, 7} and the set of equivalence classes be X = {1, 2, 3}, {5, 6}, {4}, {7}, {8, 9} .
Now, the lower approximation of A is given by, A(X) = {4, 7} and the upper approximation of A is
given by Ā(X) = {1, 2, 3, 4, 7}.
∴ B(X) = Ā(X) − A(X) = {1, 2, 3} which gives, |B(X)| = 3.

9. (a). A set X is totally β- undefinable if and only if B(X) ̸= ϕ and B̄(X) = U.

10. (c). The value of accuracy of approximation for rough set is less than 1.

11. (a). For upper approximation, {x ∈ U : µB B


X (x) > 0} where µX (x) is the rough membership function.

12. (b). The indiscernibility relation in rough set theory signifies the inability to differentiate between
objects based on available attributes.

13. 0.67, range is 0.66 to 0.68.


Let B = { Headache, Muscle Pain, Temperature}
Now, from the given table we found that four out of six patients can be uniquely classified as having
flu or not, employing attributes Headache, Muscle Pain and Temperature. Therefore we get,
4
k=
6
2
=⇒ k = ≈ 0.67
3
14. 0.5, 0.499 to 0.501.
From the given table in question 13, only P3 , P4 , P6 attributes {T emperature} ⇒ {f lu}. So, we get,
3
k=
6
1
=⇒ k =
2
=⇒ k = 0.5

15. (b). We know that the accuracy of approximation is given by,

B(X)
Accuracy of Approximation =
B̄(X)

So, the accuracy of approximation is the ratio of the size of the lower approximation to the size of the
upper approximation.

16. (b). The primary goal of calculating the accuracy of approximation in the rough set theory is to
quantify the precision of classification.

You might also like