Information Technology Reference
In-Depth Information
⎛
⎝
⎞
⎠
1
.
000 0
.
908 0
.
973 0
.
944 0
.
950 0
.
977
0
.
908 1
.
000 0
.
979 0
.
975 0
.
987 0
.
950
0
.
973 0
.
979 1
.
000 0
.
982 0
.
992 0
.
986
C
=
0
.
944 0
.
975 0
.
982 1
.
000 0
.
981 0
.
983
0
.
950 0
.
987 0
.
992 0
.
981 1
.
000 0
.
967
0
.
977 0
.
950 0
.
986 0
.
983 0
.
967 1
.
000
Step 2
By Eq. (
2.87
) we give a detailed analysis with respect to the threshold
λ
,
and then we get all the possible clusters of the samples
y
i
(
i
=
1
,
2
,...,
6
)
:
(1) If
λ
=
1, then
y
i
(
i
=
1
,
2
,...,
6
)
are grouped into the following six types:
{
y
1
}
,
{
y
2
}
,
{
y
3
}
,
{
y
4
}
,
{
y
5
}
,
{
y
6
}
-cutting matrix
C
λ
=
λ
c
ij
m
×
m
of
C
is:
(2) If
λ
=
0
.
992, then by Eq. (
2.87
), the
λ
⎛
⎝
⎞
⎠
100000
010000
001010
000100
001010
000001
C
λ
=
According to Theorem 2.19, we know that
C
λ
is an equivalent Boole matrix,
we can use
C
to cluster the samples
y
i
(
i
=
1
,
2
,...,
6
)
directly, and then
y
i
λ
(
i
=
1
,
2
,...,
6
)
are grouped into the following five types:
{
y
1
}
,
{
y
2
}
,
{
y
3
,
y
5
}
,
{
y
4
}
,
{
y
6
}
λ
=
λ
c
ij
m
×
m
of
C
is:
(3) If
λ
=
0
.
987, then the
λ
-cutting matrix
C
⎛
⎞
100000
010010
001010
000100
011010
000001
⎝
⎠
C
λ
=
Similar to (2),
y
i
(
i
=
1
,
2
,...,
6
)
are grouped into the following four types:
{
y
1
}
,
{
y
2
,
y
3
,
y
5
}
,
{
y
4
}
,
{
y
6
}
Search WWH ::
Custom Search