Information Technology Reference
In-Depth Information
Ta b l e 5 .
Results of clustering of
irises
and
sph
10
D
4
gr
set in form of point-type and hyperboxes
irises
set
sph
10
D
4
gr
set
algorithm
index
point-type granulated point-type granulated
data
data
data
data
R
0.91
0.72
1.0
1.0
SOSIG
DB
0.14, 0.12
0.2
0.01
0.0001
Dunn's 0.39, 0.19
0.25
7.83
9.29
R
0.79
0.82
1.0
1.0
k-means
DB
0.18
0.29
0.01
0.0001
Dunn's
0.06
0.09
7.83
9.29
R
0.77
0.81
1.0
1.0
hcl
DB
0.18
0.28
0.01
0.0001
Dunn's
0.11
0.15
7.83
9.29
R
0.78
0.70
1.0
1.0
hsl
DB
0.13
0.21
0.01
0.0001
Dunn's
0.20
0.22
7.83
9.29
Ta b l e 6 .
Main level of
irises
data hierarchy composed of clustering result of hyperboxes set.
Table contains 3 main granules.
granule id/
class
attributes minimal maximal
diff
Avg
granule size distribution
values
values
100% I-S
SL
4.4-5.4
4.8-5.5
0.25
gr
1
/13
SW
3.0-3.7
3.1-3.9
0.15
PL
1.0-1.5
1.5-1.9
0.29
PW
0.1-0.4
0.1-0.5
0.12
31% I-Ve
SL
5.6-7.1
5.6-7.1
0.04
gr
2
/36
69% I-Vi
SW
2.5-3.4
2.5-3.4
0.03
PL
4.3-6.0
4.4-6.0
0.07
PW
1.4-2.5
1.4-2.5
0.02
100% I-Ve
SL
5.2-6.1
5.2-6.2
0.11
SL
5.2-6.1
5.2-6.2
0.11
gr
3
/15
SW
2.3-2.9
2.3-3.0
0.08
PL
3.5-4.7
3.6-4.7
0.17
PW
1.0-1.4
1.1-0.5
0.08
a consequence there appears an additional feature - the difference between the maximal
and minimal value of particular variables. Average differences are presented in Table 6
in column
diff
Avg
. Granule
gr
1
is characterized by the widest range of all attributes,
granule
gr
2
contains flowers with the smallest size of petals and sepals. Finally, granule
gr
3
is composed of irises with narrow and long petals and sepals.
Table 7 presents granules from the second level of data relationship hierarchy. The
granules are hyperboxes identified in the first phase of the granulation. In the table the
greatest 3 hyperboxes (denoted as
gr
ij
) from every granule of the main level were se-
lected. The second-level granules from the top-level granules
gr
1
and
gr
3
have larger