Information Technology Reference
In-Depth Information
The Chiu
s clustering technique can be summarized by the following algorithm:
'
Algorithm 1:
Identification algorithm
Data
: Dispose of
{ʸ
i
}
N
i
=1
from a given data set (
˕
i
,y
i
)
Main steps
:
-Compute
P
i
N
i
=1
according to (9)
- Determine the filtered local parameters
for every
{ʸ
i
}
N
i
=1
{ʸ
i
}
,(
N <N
)
1
- Compute the first cluster center
ʸ
from (9)
repeat
Compute the other cluster centers according to the updated potential
formula (14)
if
∗
k
>ʳ
then
Compute
V
(
c
)suchas:
P
k
− ʸ
c
V
(
c
)=
ʸ
,
c
=1
, ..., k −
1
.
(16)
ʸ
k
∗
is the current cluster center and
c
,
where
ʸ
c
=1
, ..., k −
1arethe
last selected ones.
if
V
(
c
)
>ʵ, c
=1
, ..., k −
1
then
ʸ
k
∗
as a cluster center and continue
accept
else
reject
ʸ
k
∗
and compute a new potential
end
else
reject
ʸ
k
∗
and break
end
until
V
1;
Result
: Determination of the number of clusters
s
and the parameters
{ʸ
i
}
(
c
)
≤ ʵ,
c
=1
, ...k −
s
i
=1
is a small parameter characterizing the minimum distance between the
new cluster center and the existing ones.
While
e
4.2 The DBSCAN Clustering Technique
The Density-Based Spatial Clustering of Applications with Noise (DBSCAN)
algorithm is a pioneer algorithm of density-based clustering (Chaitali
2012
; Sander
et al.
1998
). This algorithm is based on the concepts of density-reachability and
density-connectivity. These concepts depend on two input parameters: epsilon (
e
)
and (MinPts).
e
e
: is the radius around an object that de
nes its
-neighborhood.
MinPts: is the minimum number of points.
For a given object q, when the number of objects within the
-neighborhood is at
least MinPts, then q is defined as a core object. All objects within its
e
-neighbor-
hood are said to be directly density-reachable from q.
In general, an object p is considered density-reachable if it
e
is within the
e
-neighborhood of an object
that
is directly density-reachable or just density-
Search WWH ::
Custom Search