Information Technology Reference
In-Depth Information
RIL
RIL
1
1
0.8
0.8
0.6
0.6
0.4
0.4
0.2
0.2
AVE
TMSE
EBC
AVE
TMSE
EBC
0
0
0.5
0.2
0.1
0.001
1.0
0.999
0.99
0.9
(a)
K
=2
RIL
RIL
1
1
0.8
0.8
0.6
0.6
0.4
0.4
0.2
0.2
AVE
TMSE
EBC
AVE
TMSE
EBC
0
0
0.5
0.2
0.1
0.001
1.0
0.999
0.99
0.9
(b)
K
=5
RIL
1
RIL
1
0.8
0.8
0.6
0.6
0.4
0.4
0.2
0.2
AVE
TMSE
EBC
AVE
TMSE
EBC
0
0
0.5
0.2
0.1
0.001
1.0
0.999
0.99
0.9
(c)
K
=10
Fig. 15.2.
Experimental results on artificial data of complete orders
NOTE: The left charts show the variation of RIL in the inter-cluster isolation when the
intra-cluster cohesion is fixed to 0
.
999. The right charts show the variation of RIL in the
intra-cluster cohesion when the inter-cluster isolation is fixed to 0
.
2.
this result by
AVE
. The experimental results on artificial data of complete orders (i.e,
L
∗
=10) are shown in Figure 15.2. In Figures 15.2(a), (b), and (c), the means of RIL
are shown in cases of
K
=2, 5,and10, respectively. The left three charts show the
variation of RIL in the inter-cluster isolation when the intra-cluster cohesion is fixed
to 0
.
999. The right three charts show the variation of RIL in the intra-cluster cohesion
when the inter-cluster isolation is fixed to 0
.
2.
As expected, the more inappropriate clusters were obtained when the inter-cluster
isolation or the intra-cluster cohesion decreased and the number of clusters increased.