L-Fuzzy Concepts and Linguistic Variables in Knowledge Acquisition Processes.

Full text

Page 1

L-Fuzzy Concepts and linguistic variables in
knowledge acquisition processes.⋆
Cristina Alcalde1, Ana Burusco2, and Ram´ on Fuentes-Gonz´ alez2
1Dpt. Matem´ atica Aplicada. Escuela Univ. Polit´ ecnica
Univ. del Pa´ ıs Vasco. Plaza de Europa, 1
20018 - San Sebasti´ an (Spain)
c.alcalde@ehu.es
2Dpt. Autom´ atica y Computaci´ on. Univ. P´ ublica de Navarra
Campus de Arrosad´ ıa
31006 - Pamplona (Spain)
{burusco,rfuentes}@unavarra.es
Abstract. In this work, we analyze how the linguistic labels of a lin-
guistic variable can be a useful tool in the L-Fuzzy Concept Theory.
In concrete, we study the L-Fuzzy concepts obtained from a departure
set represented by means of these linguistic labels applied to the set of
objects or attributes.
We also illustrate the results by means of an example.
1Introduction.
The Formal Concept Analysis developed by Wille ([18]) tries to extract some
information from a binary table that represents a formal context (X,Y,R) with
X and Y two finite sets (of objects and attributes, respectively) and R ⊆ X ×
Y . This information is obtained by means of the formal concepts which are
pairs (A,B) with A ⊆ X, B ⊆ Y fulfilling A∗= B and B∗= A (where ∗ is
the derivation operator which associates to each object set A the set B of the
attributes related to A, and vice versa). A is the extension and B the intension
of the concept.
The set of the concepts derived from a context (X,Y,R) is a complete lattice
and it is usually represented by a line diagram.
In some previous works ([8],[9]) we defined the L-Fuzzy context (L,X,Y, R),
with L a complete lattice, X and Y the sets of objects and attributes respectively
and R ∈ LX×Yan L-Fuzzy relation between the objects and the attributes, as
an extension to the fuzzy case of the Wille’s formal contexts when the relation
between the objects and the attributes that we want to study takes values in
a complete lattice L. When we work with these L-Fuzzy contexts we use the
⋆Work partially supported by the Research Group “Intelligent Systems and Energy
(SI+E)” of the Basque Government, under Grant IT519-10 and by the Research
Project of the Government of Navarra (Resolution 2031 of 2008).

Page 2

L-Fuzzy Concepts and linguistic variables in knowledge acquisition processes.39
derivation operators 1 and 2 defined by: For every A ∈ LX,B ∈ LY
A1(y) = inf
x∈X{I(A(x),R(x,y))},B2(x) = inf
y∈Y{I(B(y),R(x,y))}
where I is a fuzzy implication defined in (L,≤), I : L × L −→ L, which is
decreasing in its first argument, and, A1represents, in a fuzzy way, the attributes
related to the objects of A and B2the objects related to the attributes of B.
The information of the context is visualized by means of the L-Fuzzy concepts
which are pairs (A,A1) ∈ (LX,LY) with A ∈ fix(ϕ) the set of fixed points of the
operator ϕ, being this one defined by the derivation operators 1 and 2 mentioned
above as ϕ(A) = (A1)2= A12. These pairs, whose first and second components
are the extension and the intension respectively, represent, in a vague way, the
set of objects that share some attributes.
The set L = {(A,A1) : A ∈ fix(ϕ)} with the order relation ≤ defined as:
(A,A1),(C,C1) ∈ L,(A,A1) ≤ (C,C1) if A ≤ C
(or equiv. C1≤ A1) is a complete lattice that is said to be the L-Fuzzy concept
lattice ([8],[9]).
Other extensions of the Formal Concept Analysis to the Fuzzy area are in
[19], [17], [6], [13], [15], [16] and [12].
2Obtaining the closest L-Fuzzy Concept to the
departure set
The process to obtain the closest L-Fuzzy concept to a departure set A ∈ LX
that represents our interest of study begins with the calculus of the closest fixed
point of ϕ to A described in the previous section.
In the Formal Concept Analysis and when we use a residuated implication,
this is an easy process since ϕ is a closure operator and, as A∗= A∗∗∗, then we
only have to apply twice the derivation operator ∗ to obtain the fixed point and
the associate L-Fuzzy concept.
That is, if A ⊆ X, then (A∗∗,A∗) is the formal concept obtained from A.
More arduous is the case of using a non residuated implication. In [9], a
method to obtain this fixed points by means of a calculation process using the
implication of Kleene-Dienes and the operators of Cousot [11] was proposed:
For every A ∈ LX, the L-Fuzzy sets luis(ϕ)◦ llis(f2)(A) and llis(ϕ)◦ luis(f1)(A)
are fixed points of ϕ verifying
luis(ϕ) ◦ llis(f2)(A) ≤ llis(ϕ) ◦ luis(f1)(A),
where luisf1(d) = lim sup(d,f1(d),f12(d),f13(d)...) is the limit of an stationary
upper iteration sequence for f1starting with d and llis(f2)(d) = lim inf(d,f2(d),
f22(d),f23(d)...), the limit of an stationary lower iteration sequence for f2start-
ing with d. Also, we have that f1(d) = d ∨ ϕ(d) and f2(d) = d ∧ ϕ(d).
Moreover, these fixed points are greater than or equal to any fixed point of
ϕ less than or equal to A, and less than or equal to any fixed point of ϕ greater
than or equal to A. (Many times both fixed points are coincident.)

Page 3

40Cristina Alcalde, Ana Burusco and Ram´ on Fuentes-Gonz´ alez
For any of the obtained fixed pointsˆA we calculate the closest L-Fuzzy
concept (ˆA,ˆA1) to the departure set A.
The use of a non residuated implication operator complicates the process
to obtain the associated concept. For this reason, most of times a residuated
implication is used. For example, the Lukasiewicz one.
A study of the obtained results using different implications is in [10].
This process can also be applied to a set of attributes instead of objects.
Now, we will see an example where the L-Fuzzy concepts derived from a
departure set are showed. In all the examples of this paper, we will use the
lattice L = {0,0.1,0.2,...0.9,1} and the Lukasiewicz implication operator I.
Example 1 Let (L,X,Y,R) be an L-Fuzzy context, where X = {x1,x2,x3,x4,x5},
Y = {y1,y2,y3,y4} and the L-Fuzzy relation R is represented by Table 1.
Table 1. Relation R.
R y1 y2 y3 y4
x1 11 0.1 1
x2 0.9 0.1 0
x3 0.1 1 0.9 0.9
x4 0 0.1 1 0.1
x5 0.8 0.2 1
0
0
In this case, we want to study for which attributes, the membership degree of
the objects x1and x3is high. To do this, we take a set A ∈ LXthat represents the
situation to analyze: A = {(x1/1,x2/0,x3/1,x4/0,x5/0)}, obtaining the L-Fuzzy
concept:
{(x1/1,x2/0.1,x3/1,x4/0.1,x5/0.1),(y1/0.1,y2/1,y3/0.1,y4/0.9)}
In order to interpret the meaning of this L-Fuzzy concept, we will focus on
those objects and attributes whose membership degrees stand out from the rest.
In this case, we say that y2and y4are the attributes that have high values of x1
and x3.
However, this method not always provides satisfactory results. For example,
if we want to see what objects share the attributes y2and y4but, in addition, do
not have the attributes y1and y3, the previous method does not give us a good
result, since if we take the L-Fuzzy set B = {(y1/0,y2/1,y3/0,y4/1)}, then we
obtain the L-Fuzzy concept:
{(x1/1,x2/0,x3/0.9,x4/0.1,x5/0),(y1/0.2,y2/1,y3/0.1,y4/1)}
that it would be interpreted saying that x1and x3verify the required conditions.
Nevertheless, x1does not have low values in y1and x3does not have low values
in y3.

Page 4

L-Fuzzy Concepts and linguistic variables in knowledge acquisition processes. 41
That is, this process goes well for high values of objects or attributes, but
it does not for the low ones. This same problem can be seen in the example
proposed by Pollandt in [17] relating to the weather throughout one week.
Furthermore, sometimes we will be interested not only in studying high or
low values of objects or attributes but also in other ones: medium, medium-
high, very low etc. As we will see in the following section, we can use linguistic
variables to do this.
3 Using linguistic variables to represent departure sets
and calculate their associated L-Fuzzy concepts
3.1Linguistic variables
We begin by summarizing some well-known definitions of fuzzy logic.
A fuzzy number [20] is a normal and convex fuzzy set. There are many kinds of
fuzzy numbers, e.g. triangle, trapezoid, S-shaped, bell etc. These fuzzy numbers
characterize the linguistic variables that appear next.
Taking the definition of Zadeh [20]: By a linguistic variable we mean a vari-
able whose values are words or sentences instead of numbers and that is char-
acterized by a tuple (V,T(V ),[0,1],G,M) where V is the name of the variable,
T(V ) is the set of linguistic labels or values, [0,1] is the Universe of discourse,
G is a syntactic rule which generates the values of T(V ) and M is the semantic
rule which assigns to each linguistic value t ∈ T(V ) its meaning M(t).
The meaning of a linguistic label t is characterized by a compatibility function
ct: [0,1] → [0,1] which assigns its compatibility with [0,1] to every t.
We will now consider linguistic variables defined in the Universal set [0,1]
where the meaning of the label M(t) is represented by a truncated symmetrical
trapezoidal fuzzy number. In concrete, we use those represented in Fig. 1 (the
values a and b define the interval where ct(x) = 1):
?
?
? ?
?
?
??
Fig.1. Fuzzy sets assigned to labels.
Observe that these truncated trapezoidal numbers are the restriction to the
interval [0,1] of the original ones defined in R.
Notation: We denote xtto the compatibility of the value x ∈ [0,1] with label t.

Page 5

42Cristina Alcalde, Ana Burusco and Ram´ on Fuentes-Gonz´ alez
Then for every x ∈ [0,1]:
ct(x) = xt=





1 + m(x − a)
1
1 + m(b − x)
if x ≤ a
if a ≤ x ≤ b
if x ≥ b
where m = min
?1
a,
1
1 − b
?
These two values, a,b ∈ [0,1], are the assigned to the label t ∈ T(V ) in its
definition.
On the other hand, the label set T(V ) have to cover the whole [0,1] so that,
for every x ∈ [0,1], a only label t ∈ T(V ) exists such that xt= 1. In other case,
we have two different definitions from the transformed values of the relation R.
We also have proved some results about interval-valued linguistic variables
in [5].
In the next section, we will see how these linguistic labels can be used to solve
the problem explained at the end of Section 2: we will represent the situation
that we want to study by means of a set of pairs using these linguistic labels.
3.2
L-Fuzzy contexts associated with labels of a linguistic variable
Associated with every label t ∈ T(V ) of a linguistic variable, we can create an
L-Fuzzy context that will be used to obtain the closest L-Fuzzy concept to a
departure set:
Definition 1 Let (L,X,Y,R) be an L-Fuzzy context and let T(V ) be the lin-
guistic labels set assigned to variable V . For every label t ∈ T(V ), we can create
a new L-Fuzzy context (L,X,Y,Rt) where X and Y are the object and attribute
sets of the original context and relation Rtis defined as follows:
Rt(xi,yj) = R(xi,yj)t,∀xi∈ X,∀yj∈ Y
and measures the compatibility of R(xi,yj) with label t. The defined context is
said to be the t-labeled L-Fuzzy context.
As corollary of the next proposition it is not difficult to prove some properties
of this new context:
Proposition 1 Let (L,X,Y,R) be an L-Fuzzy context and let I be a residuated
implication operator. If we take the basic point A ∈ LX, that is:
A(x) =
?
1
0
if x = xi
otherwise
then the intension of the L-Fuzzy concept obtained taking A as a departure point
is A1(y) = Rt(xi,y),∀y ∈ Y , that is, it is coincident with the row xi of the
relation R.
Moreover, the extension verifies that A12(xi) = 1.

Page 6

L-Fuzzy Concepts and linguistic variables in knowledge acquisition processes.43
In the same way, if we take as a departure point the set B ∈ LY:
B(y) =
?
1
0
if y = yj
otherwise
then the extension of the obtained L-Fuzzy concept is B2(x) = R(x,yj),∀x ∈ X.
That is, the values of the column yjof R.
Moreover, B21(yj) = 1 holds.
Proof: We take an object set as the departure point.
Let A ∈ LXbe a basic point,
A(x) =
?
1
0
if x = xi
otherwise
We calculate the L-Fuzzy concept derived from A in the L-Fuzzy context
(L,X,Y,R) :
We can apply the derivation operator and we obtain the intension of the
L-Fuzzy concept:
A1(y) = inf
x∈X{I(A(x),R(x,y))},∀y ∈ Y.
Since the implication operator is residuated, hence ∀z ∈ [0,1], I(0,z) = 1 and
I(1,z) = z holds. Then
A1(y) = I(A(xi),R(xi,y)) = R(xi,y),∀y ∈ Y.
On the other hand, with respect to the extension of the L-Fuzzy concept:
A12(x) = inf
y∈Y{I(A1(y),R(x,y))} = inf
y∈Y{I(R(xi,y),R(x,y))}.
And, as all the residuated implications verify ∀z ∈ [0,1], I(z,z) = 1, we can
say that A12(xi) = 1.
?
The proof from a set of attributes is analogous.
Corollary 1 As Rt(xi,yj) = R(xi,yj)t, the intension (or extension) of the L-
Fuzzy concept obtained from a departure set associated with a basic point created
from an object (or attribute) in the t-labeled L-Fuzzy context (L,X,Y,Rt), is
coincident with the application of label t to the intension (or extension) of the
L-Fuzzy concept obtained in the original L-Fuzzy context (L,X,Y,R).
Corollary 2 Let (L,X,Y,Rt) be the t-labeled L-Fuzzy context, with t ∈ T(V ).
If exists xi∈ X such that Rt(xi,yj) = 1, for some yj∈ Y, and we have A ∈ LX:
A(x) =
?
1
0
if x = xi
otherwise

Page 7

44Cristina Alcalde, Ana Burusco and Ram´ on Fuentes-Gonz´ alez
Then the L-Fuzzy concept of the t-labeled L-Fuzzy context obtained taking A as
a departure set verifies that A1(yj) = 1 and A12(xi) = 1.
Analogous, If exists yj∈ Y such that Rt(xi,yj) = 1, for some xi∈ X, and
we have the set B ∈ LY:
?
0
B(y) =
1if y = yj
otherwise
Then the L-Fuzzy concept of the t-labeled L-Fuzzy context obtained taking B as
a departure set verifies that B2(xi) = 1 y B21(yj) = 1.
That is, the elements xi and yj are outstanding elements in the obtained
L-Fuzzy concepts.
Now, we are going to see an illustrative example.
Example 2 We have the L-Fuzzy context (L,X,Y,R) of the previous example
and we take the label t = high assigned to the values a = 0.8 and b = 1. The
relation of the t-labeled L-Fuzzy context (L,X,Y,Rhigh) is in Table 2.
Table 2. Relation Rhigh.
Rhigh y1 y2 y3 y4
x1
1
x2
1 0.1 0
x3
0.1 1
x4
0 0.1 1 0.1
x5
1 0.2 1
1 0.1 1
0
11
0
If we take R(x5,y1) = 0.8, for instance, then we see that the new relation
has the value Rt(x5,y1) = 1. In this case, the L-Fuzzy concepts associated with
the sets created from x5and y1are:
If we take A = {x1/0,x2/0,x3/0,x4/0,x5/1} we obtain
{(x1/0.1,x2/0,x3/0.1,x4/0,x5/1),(y1/1,y2/0.2,y3/1,y4/0)}
and if we take B = {y1/1,y2/0,y3/0,y4/0},
{(x1/1,x2/1,x3/0.1,x4/0,x5/1),(y1/1,y2/0.1,y3/0,y4/0)}
As can be seen, Corollary 2 holds.
On the other hand, as the L-Fuzzy concepts obtained from R are:
From A = {x1/0,x2/0,x3/0,x4/0,x5/1} :
{(x1/0.1,x2/0,x3/0.3,x4/0.2,x5/1),(y1/0.8,y2/0.2,y3/1,y4/0)}
and from B = {y1/1,y2/0,y3/0,y4/0} :
{(x1/1,x2/0.9,x3/0.1,x4/0,x5/0.8),(y1/1,y2/0.2,y3/0.1,y4/0.1)}
Then Corollary 1 also holds.

Page 8

L-Fuzzy Concepts and linguistic variables in knowledge acquisition processes. 45
We will see now what happens with the more general departure sets (with
several membership degrees equal to 1) and certain special labels.
Proposition 2 Given an L-Fuzzy context (L,X,Y,R), a residuated implication
operator I, and a label t, assigned to the values a and b such that b = 1, we
can create the t-labeled L-Fuzzy context (L,X,Y,Rt) where Rt(x,y) = R(x,y)t.
Then the intension of the L-Fuzzy concept (¯A12,¯A1) derived from any departure
L-Fuzzy set A ∈ LXsuch that A(x) = 0 or 1, in the context (L,X,Y,Rt) is
also equal to the intension of the L-Fuzzy concept (A12,A1) obtained in the L-
Fuzzy context (L,X,Y,R) after applying label t. Analogous, we can write this
proposition taking as a departure point a set B ∈ LY.
Proof: Let (A12,A1) be the L-Fuzzy concept derived from A ∈ LXin the
L-Fuzzy context (L,X,Y,R).
As the implication operator is residuated, ∀z ∈ [0,1], I(0,z) = 1 and I(1,z) =
z holds. Then as A(x) = 0 1, it is true that:
∀y ∈ Y,
¯A1(y) = inf
x∈X{I(A(x),Rt(x,y))} =inf
x∈X/A(x)=1(Rt(x,y))
and, as the label has a increasing compatibility function ct:
A1(y)t=
?
inf
x∈X/A(x)=1R(x,y)
?
t
=inf
x∈X/A(x)=1(Rt(x,y)) =¯A1(y)
?
Example 3 If we come back to the previous example where we used the label
t = high and we take the departure set A = {x1/0,x2/1,x3/0,x4/0,x5/1} in the
t-labeled L-Fuzzy context (L,X,Y,Rhigh), then we obtain the L-Fuzzy concept:
(¯A12,¯A1) = {(x1/1,x2/1,x3/0.1,x4/0,x5/1),(y1/1,y2/0.1,y3/0,y4/0)}
On the other hand, if we have the initial L-Fuzzy context (L,X,Y,R) and the
same departure set, then we obtain the L-Fuzzy concept:
(A12,A1) = {(x1/1,x2/1,x3/0.3,x4/0.2,x5/1),(y1/0.8,y2/0.1,y3/0,y4/0)}
It is easy to see that the intension of the first one can be obtained applying label
t to the intension of the second one.
Remark 1 This result is not always true if we consider a label with a non
increasing compatibility function or if the departure set has a membership degree
different of 0 or 1, as can be seen in the following examples.

Page 9

46Cristina Alcalde, Ana Burusco and Ram´ on Fuentes-Gonz´ alez
Table 3. Relation Rmedium−low.
Rmedium−low y1 y2 y3 y4
x1
x2
x3
x4
x5
00 0.7 0
0.2 0.7 0.5 0.5
0.7 0 0.2 0.2
0.5 0.7 0 0.7
0.3 0.8 0 0.5
Example 4 We have the L-Fuzzy context (L,X,Y,R) of the previous example
and the label medium − low assigned to the values a = 0.3 and b = 0.4. The
relation R of the t-labeled L-Fuzzy context (L,X,Y,Rmedium−low) is showed in
Table 3.
If we take A = {x1/0,x2/1,x3/0,x4/0, x5/0}, the intension of the L-Fuzzy
concept associated with the initial L-Fuzzy context is A1= {y1/0.8,y2/0.1,y3/0,y4/0},
and the intension of the L-Fuzzy concept associated with the t-labeled L-Fuzzy
context¯A1= {y1/0.2,y2/0.7, y3/0,y4/0.5}, and, for instance, A1(y3)medium−low?=
¯A1(y3), as can be seen.
Example 5 In the same L-Fuzzy context (L,X,Y,R) of the previous example,
we take as a departure set A = {x1/0,x2/0.5,x3/0,x4/0,x5/1}.
The intension of the L-Fuzzy concept derived from A is A1= {y1/0.8,y2/0.2,
y3/0.6,y4/0}.
If we consider the t-labeled L-Fuzzy context with t = high assigned to the
values a = 0.8 and b = 1, represented in Table 2, then the intension of the L-
Fuzzy concept obtained from A is¯A1= {y1/1,y2/0.2,y3/0.5,y4/0}, and, as can
be proved, we also have in this case A1(y3)high?=¯A1(y3).
3.3Using linguistic variables in departure sets
Once the previous properties have been studied, we return to the initial point
that is to analyze how can we obtain the L-Fuzzy concepts associated with
departure sets in which several labels take part. To do this, we will follow these
steps:
1. Starting from the L-Fuzzy context (L,X,Y,R) and from the set of labels
T(V ), we represent the situation that we want to study (departure set) by
means of a set of pairs PX = {(xi,txi),xi∈ X,txi∈ T(V )} which assigns
labels of T(V ) to the elements of the set of objects X. In the same way, we
define the set of pairs PY = {(yj,tyj),yj ∈ Y,tyj∈ T(V )} for the set of
attributes Y .
Note that the same label could be associated with different objects or at-
tributes.
2. We construct the t-labeled L-Fuzzy contexts (L,X,Y,Rt) associated with
each of the labels used in the departure point as we defined in Definition 1.

Page 10

L-Fuzzy Concepts and linguistic variables in knowledge acquisition processes.47
3. For each pair (xi,txi) of PX(or, analogously, for each pair (yj,tyj) of PY) we
obtain the corresponding L-Fuzzy concept in the t-labeled L-Fuzzy context
(L,X,Y,Rtxi). Taking as a departure the basic point:
A(x) =
?
1
0
if x = xi
otherwise
4. We apply the intersection associated with the residuated implication opera-
tor that we are using to the intension (or extension) of the obtained L-Fuzzy
concepts.
The obtained L-Fuzzy set is the one that we were looking for.
Let us see two examples:
Example 6 Returning to the L-Fuzzy context (L,X,Y,R) of the previous ex-
ample, we want now to analyze which objects verify that y1 is high and y3 is
low (the values of the rest of the attributes do not matter to us). If we apply the
exposed process:
1. In this case, we take the labels {high,low} of the linguistic variable V choos-
ing in high the values a = 0.8 and b = 1 and in low, a = 0 and b = 0.2 in
the corresponding definition of the compatibility function.
That is, our departure point will be represented by the pair PY = {(y1,high),
(y3,low)}.
2. We consider now the t-labeled L-Fuzzy contexts (L,X,Y,Rhigh) and (L,X,Y,
Rlow) where the relations are the represented ones in Table 2 (used in the
previous section) and Table 4.
Table 4. Rlow relation
Rlow y1 y2 y3 y4
x1
0
x2
0.1 1
x3
1
x4
1
x5
0.2 1
01
1
0
1
0 0.1 0.1
10
0
1
1
3. From the departure set B = {y1/1,y2/0,y3/0,y4/0}, we calculate the L-
Fuzzy concept obtained in the t-labeled L-Fuzzy context (L,X,Y,Rhigh) to
find the objects with high values of y1:
{(x1/1,x2/1,x3/0.1,x4/0,x5/1),(y1/1,y2/0.1,y3/0,y4/0)}
And, we obtain the objects that have low values of y3 calculating the L-
Fuzzy concept in the t-labeled L-Fuzzy context (L,X,Y,Rlow) from the set
B = {y1/0,y2/0,y3/1,y4/0}:
{(x1/1,x2/1,x3/0.1,x4/0,x5/0),(y1/0,y2/0,y3/1,y4/0)}

Page 11

48 Cristina Alcalde, Ana Burusco and Ram´ on Fuentes-Gonz´ alez
4. Finally, we have to calculate the intersection of the extensions using the
bounded difference (i(a,b) = max(0,a+b−1)) associated with the implication
of Lukasiewicz. The obtained result is {(x1/1,x2/1,x3/0,x4/0,x5/0)}, and
we can say that x1and x2are the objects that fulfill the initial condition.
Example 7 Returning to the first example, we wanted to see what objects shared
attributes y2and y4but, in addition, did not have attributes y1and y3.
We apply the process:
1. We also take the labels {high,low} of the linguistic variable V choosing in
high the values a = 0.8 and b = 1 and in low, a = 0 and b = 0.2 in the
corresponding definition of the compatibility function. Our departure set is
PY = {(y1,low),(y2,high),(y3,low),(y4,high)}.
2. We consider now the t-labeled L-Fuzzy contexts (L,X,Y,Rhigh) and (L,X,Y,
Rlow) used in the previous example.
3. From the departure set B = {y1/0,y2/1,y3/0,y4/1}, we calculate the L-
Fuzzy concept obtained in the t-labeled L-Fuzzy context (L,X,Y,Rhigh) to
find the objects with high values of y2and y4:
{(x1/1,x2/0,x3/1,x4/0.1,x5/0),(y1/0.1,y2/1,y3/0.1,y4/1)}
And, we obtain the objects that have low values of y1and y3calculating the
L-Fuzzy concept in the t-labeled L-Fuzzy context (L,X,Y,Rlow) from the set
B = {y1/1,y2/0,y3/1,y4/0}:
{(x1/0,x2/0.1,x3/0.1,x4/0,x5/0),(y1/1,y2/0.9,y3/1,y4/1)}
4. Finally, the intersection of the extensions using the bounded difference associ-
ated with the implication of Lukasiewicz is {(x1/0,x2/0,x3/0.1,x4/0,x5/0)},
and we can say that non object fulfills the initial condition, although if we
had to choose one, then it would be object x3.
4Conclusions and future work
The use of linguistic variables in L-Fuzzy contexts is a good tool in knowledge
acquisition processes since allow us represent our interest of study by means of
an L-Fuzzy set and obtain the derived L-Fuzzy concept that give us the looked
for information.
In future works we will study the use of these linguistic variables in the
interval-valued L-Fuzzy contexts. In concrete, we will obtain significant relations,
to replace erroneous values and to study interval-valued L-Fuzzy subcontexts.
References
1. C. Alcalde, A. Burusco and R. Fuentes-Gonz´ alez, “Treatment of the incomplete
information in L-Fuzzy contexts,” EUSFLAT-LFA 2005, Barcelona, Sep. 2005, pp.
518–523.

Page 12

L-Fuzzy Concepts and linguistic variables in knowledge acquisition processes. 49
2. C. Alcalde, A. Burusco and R. Fuentes-Gonz´ alez, “Implications between attributes
in an L-Fuzzy context based on association rules,” IPMU 2006, Paris, Jul. 2006,
pp. 1403–1410.
3. C. Alcalde, Extracci´ on de conocimiento en contextos borrosos con informaci´ on in-
completa, Ph.D. Dissertation, Universidad del Pas Vasco, San Sebasti´ an, Spain,
Jan. 2007.
4. C. Alcalde, A. Burusco and R. Fuentes-Gonz´ alez, “Contextos con conjuntos de ob-
jetos y atributos iguales,” ESTYLF 2008, Mieres-Langreo, Sep. 2008, pp. 85–89.
5. C. Alcalde, A. Burusco and R. Fuentes-Gonz´ alez, “Interval-valued linguistic vari-
ables: an application to the L-fuzzy contexts with absent values,” International
Journal of General Systems 39 No.3 (2010), pp. 255–270.
6. R. Bˇ elohl´ avek, “Fuzzy Galois connections and fuzzy concept lattices: from binary
relations to conceptual structures”, in: Novak V., Perfileva I. (eds.): Discovering the
World with Fuzzy Logic, Physica-Verlag (2000), pp. 462–494.
7. R. Bˇ elohl´ avek, “Fuzzy relational systems”, in IFSR International Series on Systems
Science and Engineering 20, (2002).
8. A. Burusco and R. Fuentes-Gonz´ alez, “The Study of the L-Fuzzy Concept Lattice.”
Mathware and Soft Computing. 1 No.3 (1994), pp. 209–218.
9. A. Burusco and R. Fuentes-Gonz´ alez, “Construction of the L-Fuzzy Concept Lat-
tice.” Fuzzy Sets and Systems. 97 No.1 (1998), pp. 109–114.
10. A. Burusco and R. Fuentes-Gonz´ alez, “Fuzzy extensions of the Formal Concept
Analysis.” International Conference on knowledge, logic and information. Darm-
stadt, Feb 1998.
11. P. Cousot and R. Cousot, “Constructive versions of Tarski’s fixed point theorems.”
Pacific J. Maths. 82 (1979), pp. 43–57.
12. Y. Djouadi, D. Dubois and H. Prade, “On the possible meanings of degrees when
making formal concept analysis fuzzy.” EUROFUSE workshop. Preference Modelling
and Decision Analysis. Pamplona, Sep 2009, pp. 253–258.
13. A. Jaoua, F. Alvi, S. Elloumi, S. B. Yahia. “Galois Connection in Fuzzy Binary
Relations.” Applications for Discovering Association Rules and Decision Making.
RelMiCS (2000), pp. 141–149.
14. G.J. Klir, B.Yuan. Fuzzy Sets and Fuzzy Logic, Prentice Hall,(1995).
15. S. Krajˇ ci. “A generalized concept lattice.” Logic J. IGPL 13 (5) (2005) pp. 543–550.
16. J. Medina, M. Ojeda-Aciego, and J. Ruiz-Calvio. “On multi-adjoint concept lat-
tices: definition and representation theorem.” Lect. Notes in Artificial Intelligence,
4390,(2007), pp 197–209.
17. S. Pollandt, Fuzzy Begriffe: Formale Begriffsanalyse unscharfer Daten, Springer
(1997).
18. R. Wille. “Restructuring lattice theory: an approach based on hierarchies of con-
cepts”,in: Rival I.(ed.),Ordered Sets, Reidel, Dordrecht-Boston (1982), pp. 445–470.
19. K.E. Wolff. “Conceptual interpretation of fuzzy theory”,in: Proc. 6th European
Congress on Intelligent techniques and Soft computing, 1, (1998), pp. 555–562.
20. L.A. Zadeh, “The Concept of a Linguistic Variable and its Application to Approx-
imate Reasoning-I.” Information Sciences, 8, (1975) pp. 199–249.