I
nte
rna
t
io
na
l J
o
urna
l o
f
Adv
a
nces in
Appl
ie
d Science
s
(
I
J
AAS)
Vo
l.
14
,
No
.
2
,
J
u
n
e
2
0
2
5
,
p
p
.
513
~
5
2
2
I
SS
N:
2252
-
8
8
1
4
,
DOI
:
1
0
.
1
1
5
9
1
/ijaas
.
v
14
.
i
2
.
pp
513
-
5
2
2
513
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
a
s
.
ia
esco
r
e.
co
m
Birth data
c
luster
ing
t
o
seg
menta
ti
o
n delay
s in birt
h
cer
ti
ficate
regi
stra
tion
E
rf
a
n
H
a
s
m
in
1
,
Aeda
h Abd
Ra
hm
a
n
2
1
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
mat
i
c
s
,
F
a
c
u
l
t
y
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
D
i
p
a
M
a
k
a
ss
a
r
U
n
i
v
e
r
si
t
y
,
M
a
k
a
s
sar
,
I
n
d
o
n
e
s
i
a
2
S
c
h
o
o
l
o
f
S
c
i
e
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
A
si
a
e
U
n
i
v
e
r
si
t
y
,
K
u
a
l
a
L
u
m
p
u
r
,
M
a
l
a
y
si
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Oct
23
,
2
0
2
4
R
ev
is
ed
Ap
r
25
,
2
0
2
5
Acc
ep
ted
May
10
,
2
0
2
5
Ti
m
e
ly
a
n
d
a
c
c
u
ra
te
b
irt
h
re
g
istra
ti
o
n
is
e
ss
e
n
ti
a
l
fo
r
e
n
su
rin
g
a
c
c
e
ss
to
v
it
a
l
p
u
b
li
c
se
rv
ice
s.
Th
is
st
u
d
y
fo
c
u
se
s
o
n
c
lu
ste
ri
n
g
b
irt
h
d
a
ta
t
o
id
e
n
ti
fy
p
a
tt
e
rn
s
in
re
g
istrati
o
n
d
e
lay
s
,
u
s
in
g
d
a
ta
m
in
i
n
g
tec
h
n
iq
u
e
s
su
c
h
a
s
th
e
K
-
m
e
a
n
s
a
lg
o
rit
h
m
.
B
y
c
l
u
ste
rin
g
b
irt
h
d
a
ta
fro
m
M
a
k
a
ss
a
r
C
it
y
,
In
d
o
n
e
sia
,
b
a
se
d
o
n
v
a
rio
u
s
d
e
m
o
g
ra
p
h
ic
a
n
d
b
irt
h
-
re
late
d
c
ri
teria
,
th
e
stu
d
y
se
g
m
e
n
ts
th
e
d
a
ta
in
t
o
g
ro
u
p
s
th
a
t
re
flec
t
b
o
t
h
ti
m
e
ly
a
n
d
d
e
lay
e
d
re
g
istrat
io
n
s.
Th
e
o
p
ti
m
a
l
n
u
m
b
e
r
o
f
c
lu
ste
rs
is
d
e
ter
m
in
e
d
u
sin
g
t
h
e
e
lb
o
w
a
n
d
silh
o
u
e
tt
e
m
e
th
o
d
s.
Re
su
lt
s
sh
o
w
th
a
t
a
th
re
e
-
c
lu
ste
r
c
o
n
fig
u
ra
ti
o
n
e
ffe
c
ti
v
e
ly
c
a
p
tu
re
s
p
a
tt
e
rn
s
i
n
b
irt
h
re
g
istrati
o
n
d
e
lay
s,
o
ffe
rin
g
c
rit
ica
l
in
sig
h
ts
f
o
r
p
o
li
c
y
m
a
k
e
rs.
Th
e
se
fi
n
d
i
n
g
s
p
ro
v
i
d
e
a
f
o
u
n
d
a
ti
o
n
fo
r
imp
ro
v
in
g
b
irt
h
r
e
g
istratio
n
p
ro
c
e
ss
e
s,
e
n
su
rin
g
m
o
re
ti
m
e
ly
re
g
istratio
n
,
a
n
d
g
u
i
d
in
g
d
a
ta
-
d
riv
e
n
p
u
b
li
c
p
o
li
c
y
d
e
c
isio
n
s.
K
ey
w
o
r
d
s
:
B
ir
th
r
eg
is
tr
atio
n
D
ata
-
b
ased
p
o
licy
E
lb
o
w
K
-
m
ea
n
s
Sil
h
o
u
ette
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
E
r
f
an
Hasm
in
Dep
ar
tm
en
t o
f
I
n
f
o
r
m
atics,
Facu
lty
o
f
C
o
m
p
u
ter
Scien
ce
,
Di
p
a
Ma
k
ass
ar
Un
iv
er
s
ity
Per
in
tis
Kem
er
d
ek
aa
n
I
X,
T
a
m
alan
r
ea
,
Ma
k
ass
ar
9
0
2
4
1
,
I
n
d
o
n
esia
E
m
ail:
er
f
an
.
h
asm
in
@
u
n
d
i
p
a.
ac
.
id
1.
I
NT
RO
D
UCT
I
O
N
Po
licy
m
ak
er
s
r
ely
o
n
ac
c
u
r
at
e
an
d
tim
ely
d
ata
to
s
h
ap
e
t
h
eir
d
ec
is
io
n
s
an
d
o
v
e
r
s
ee
th
e
p
r
o
g
r
ess
o
f
p
o
licies
an
d
p
r
o
g
r
am
s
.
E
s
s
en
tial
s
tati
s
tics
p
er
tain
in
g
to
th
e
q
u
an
tity
an
d
g
eo
g
r
ap
h
ic
s
p
r
e
ad
o
f
b
ir
th
s
,
alo
n
g
with
th
e
r
ea
s
o
n
s
b
e
h
in
d
t
h
ese
d
ea
th
s
,
ar
e
c
r
u
ci
al
f
o
r
g
u
id
i
n
g
s
tr
ateg
ic
p
lan
n
in
g
in
v
a
r
io
u
s
s
ec
to
r
s
,
s
u
ch
as
h
ea
lth
ca
r
e,
e
d
u
ca
tio
n
,
wo
r
k
f
o
r
ce
,
u
r
b
an
d
e
v
elo
p
m
e
n
t,
f
in
a
n
ce
,
ec
o
n
o
m
ic
g
r
o
wth
,
tr
ad
e,
s
o
cial
s
af
ety
n
ets,
en
v
ir
o
n
m
en
tal
m
a
n
ag
em
e
n
t,
an
d
d
em
o
g
r
ap
h
ic
an
aly
s
is
[
1
]
.
Po
licies
th
at
ar
e
n
o
t
b
ased
o
n
d
ata
ca
n
ca
u
s
e
v
ar
io
u
s
p
r
o
b
lem
s
.
P
o
licies
m
ay
n
o
t
b
e
e
f
f
ec
tiv
e
in
s
o
lv
i
n
g
p
r
o
b
lem
s
with
o
u
t
ac
c
u
r
ate
an
d
r
elev
an
t
d
ata
[
2
]
.
W
ith
o
u
t
p
o
licies
b
ased
o
n
d
a
ta,
it
ca
n
r
esu
lt
i
n
a
lack
o
f
a
cc
ess
to
civ
il
r
e
g
is
tr
atio
n
,
s
u
c
h
as
b
i
r
th
s
,
wh
ich
r
esu
lts
in
th
e
in
ab
ilit
y
o
f
in
d
iv
id
u
als
to
ac
ce
s
s
f
u
n
d
am
en
t
al
r
ig
h
ts
s
u
c
h
as
ed
u
ca
tio
n
,
h
ea
lth
s
er
v
ices,
an
d
in
h
er
itan
ce
r
ig
h
ts
[
3
]
.
E
f
f
o
r
ts
an
d
in
itiativ
es
ar
e
u
n
d
er
way
to
en
h
an
c
e
th
e
r
eg
is
tr
atio
n
o
f
b
ir
th
s
ac
r
o
s
s
d
iv
er
s
e
s
ce
n
ar
io
s
,
g
eo
g
r
a
p
h
ical
ar
ea
s
,
an
d
s
o
cial
co
n
tex
ts
with
in
th
e
c
o
m
m
u
n
i
ty
.
I
n
f
ac
t,
g
o
v
er
n
m
e
n
tal
p
o
licies
ar
e
f
o
r
m
u
lated
b
ased
o
n
d
ata,
with
a
p
r
ef
e
r
en
ce
f
o
r
d
ata
a
n
aly
s
is
as
a
cr
u
cial
f
ac
to
r
in
d
ec
is
io
n
-
m
ak
in
g
.
C
u
r
r
en
t
d
ata
m
in
in
g
alg
o
r
ith
m
s
ca
n
b
etter
an
al
y
ze
s
p
ec
if
ic
d
ata
t
h
an
o
th
er
d
ata
a
n
aly
s
is
m
eth
o
d
s
[
4
]
.
T
h
e
n
ee
d
f
o
r
d
ata
clu
s
ter
in
g
in
civ
il
r
eg
is
tr
atio
n
d
ata
in
v
o
l
v
es
s
ev
er
al
r
ea
s
o
n
s
th
at
ar
e
ess
en
tial
in
th
e
co
n
te
x
t
o
f
d
ata
m
an
ag
em
en
t,
p
u
b
lic
p
o
licy
,
an
d
p
o
p
u
latio
n
u
n
d
er
s
tan
d
in
g
wh
ich
in
cl
u
d
e
p
o
p
u
latio
n
g
r
o
u
p
in
g
wh
ic
h
c
an
h
elp
in
b
etter
u
n
d
er
s
tan
d
i
n
g
t
h
e
n
ee
d
s
a
n
d
p
r
ef
er
en
ce
s
o
f
ea
ch
g
r
o
u
p
,
wh
i
ch
is
v
e
r
y
v
alu
ab
le
in
p
o
lic
y
p
lan
n
in
g
p
u
b
lic
an
d
co
m
m
u
n
ity
s
er
v
ices,
p
er
s
o
n
al
izatio
n
o
f
s
er
v
ices
s
o
th
at
civ
il
r
eg
is
tr
atio
n
s
er
v
ices
ca
n
ad
ap
t
s
er
v
ices
to
b
etter
m
ee
t
th
e
n
ee
d
s
o
f
i
n
d
iv
id
u
als
o
r
g
r
o
u
p
s
,
u
n
d
er
s
tan
d
in
g
d
em
o
g
r
ap
h
ic
t
r
en
d
s
to
u
n
d
er
s
tan
d
co
m
p
lex
d
em
o
g
r
a
p
h
ic
tr
e
n
d
s
,
s
u
ch
as
ch
an
g
es
in
p
o
p
u
latio
n
s
tr
u
ctu
r
e,
m
ig
r
atio
n
,
o
r
ch
an
g
es
in
f
am
ily
co
m
p
o
s
itio
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
8
1
4
I
n
t J Ad
v
Ap
p
l Sci
,
Vo
l.
14
,
No
.
2
,
J
u
n
e
2
0
2
5
:
5
1
3
-
522
514
an
d
o
f
co
u
r
s
e
tak
in
g
d
ata
-
b
as
ed
d
ec
is
io
n
s
s
o
th
at
civ
il
r
eg
is
tr
atio
n
s
er
v
ice
p
o
licies
b
ec
o
m
e
m
o
r
e
b
ased
o
n
s
o
lid
d
ata
to
r
ed
u
ce
th
e
r
is
k
o
f
in
ef
f
ec
tiv
e
p
o
licies
[
5
]
.
I
t
is
an
ticip
ated
th
at
th
is
ap
p
r
o
ac
h
will
m
itig
ate
is
s
u
es
ar
is
in
g
f
r
o
m
p
o
licies
aim
ed
at
in
cr
ea
s
in
g
b
ir
th
r
e
g
is
tr
atio
n
,
wh
ich
h
av
e
h
is
to
r
ically
lack
ed
a
f
o
u
n
d
atio
n
i
n
d
ata
p
atter
n
s
an
d
s
eg
m
e
n
tatio
n
.
Su
ch
d
ef
icien
cies
o
f
ten
l
ea
d
to
in
e
f
f
icien
cies
in
r
eso
u
r
ce
allo
ca
tio
n
an
d
b
u
d
g
et
u
tili
za
tio
n
.
Fo
r
th
is
r
ea
s
o
n
,
th
e
d
ata
m
in
in
g
ap
p
r
o
ac
h
em
p
l
o
y
ed
to
ca
teg
o
r
ize
b
ir
t
h
r
e
g
is
tr
atio
n
d
at
a
in
v
o
lv
es
clu
s
ter
in
g
th
e
d
ata
u
s
in
g
m
u
lt
ip
le
cr
iter
ia.
T
h
is
m
u
lti
-
cr
iter
i
a
clu
s
ter
in
g
en
ab
les
th
e
g
o
v
e
r
n
m
en
t
to
d
ev
elo
p
p
u
b
lic
p
o
licies
th
at
alig
n
with
th
e
ac
tu
al
s
itu
atio
n
[
6
]
.
C
lu
s
ter
in
g
b
ir
th
d
ata
ac
co
r
d
i
n
g
to
a
p
p
r
o
p
r
iate
cr
iter
ia,
in
clu
d
in
g
b
ir
th
e
v
en
ts
,
ch
ild
b
io
d
ata,
p
ar
e
n
t
s
,
an
d
r
eg
io
n
al
d
em
o
g
r
a
p
h
ics.
T
h
e
d
ata
clu
s
t
er
s
f
o
r
m
ed
ca
n
b
e
a
b
asis
f
o
r
d
eter
m
in
in
g
p
o
licies
an
d
ac
tiv
ities
to
im
p
r
o
v
e
b
i
r
th
r
eg
is
tr
atio
n
.
B
ir
th
d
ata
an
aly
s
is
u
s
in
g
th
e
n
eu
r
al
n
etwo
r
k
m
eth
o
d
em
p
h
asizes
th
e
n
ee
d
f
o
r
d
ata
m
in
in
g
a
n
aly
s
is
o
n
civ
il
r
eg
is
tr
at
io
n
d
ata
to
u
n
d
e
r
s
tan
d
e
-
g
o
v
e
r
n
an
ce
d
ata
b
etter
[
7
]
.
As
well
as
th
e
u
s
e
o
f
d
ata
m
in
in
g
tec
h
n
iq
u
es
o
n
g
o
v
e
r
n
m
e
n
t
d
ata
is
p
r
o
v
en
to
m
ak
e
b
etter
p
lan
n
in
g
an
d
d
ec
is
io
n
-
m
ak
in
g
[
8
]
.
Utilizatio
n
o
f
b
ir
t
h
d
ata
f
o
r
th
e
d
ev
elo
p
m
en
t
an
d
d
eter
m
in
atio
n
o
f
p
o
licies
an
d
ac
tiv
ities
n
ee
d
s
to
b
e
d
o
n
e
to
in
cr
ea
s
e
th
e
n
u
m
b
er
o
f
r
e
g
i
s
ter
ed
b
ir
th
s
.
Ov
er
th
r
ee
y
ea
r
s
,
b
ir
th
d
ata
ca
n
b
e
ex
am
in
ed
u
s
in
g
d
ata
m
in
in
g
tech
n
iq
u
es
to
ex
tr
ac
t
n
ew
in
s
ig
h
ts
th
at
co
u
ld
in
f
o
r
m
t
h
e
f
o
r
m
u
latio
n
o
f
p
o
licies to
en
h
an
ce
b
i
r
th
r
eg
is
tr
ati
o
n
s
y
s
tem
s
.
T
h
e
s
eg
m
en
tatio
n
o
f
b
ir
th
r
e
g
is
tr
atio
n
d
ata
is
o
f
p
ar
am
o
u
n
t
im
p
o
r
tan
ce
f
o
r
r
esear
ch
,
esp
ec
ially
co
n
s
id
er
in
g
th
e
ch
allen
g
es
in
h
er
en
t
in
co
n
d
u
ctin
g
p
o
p
u
lati
o
n
d
ata
an
al
y
s
is
.
T
h
is
co
m
p
lex
ity
s
tem
s
f
r
o
m
th
e
n
ee
d
to
in
co
r
p
o
r
ate
d
ata
o
n
cr
itical
life
ev
en
ts
,
s
u
ch
as
b
ir
th
s
.
B
y
s
eg
m
en
tin
g
th
is
d
ata,
it
b
ec
o
m
es
f
ea
s
ib
le
to
id
en
tify
an
d
d
elin
ea
te
k
ey
p
a
tter
n
s
,
p
ar
ticu
lar
ly
th
o
s
e
r
elat
ed
to
d
elay
s
in
b
ir
th
r
eg
is
t
r
at
io
n
.
T
h
is
ap
p
r
o
ac
h
p
r
o
v
id
es
a
f
o
u
n
d
atio
n
f
o
r
e
n
h
an
cin
g
th
e
s
y
s
tem
'
s
ef
f
icien
cy
an
d
tim
elin
ess
.
R
esear
ch
r
ela
ted
to
d
ata
m
in
in
g
,
esp
ec
ially
clu
s
ter
in
g
is
d
o
n
e
at
civ
il
r
eg
is
tr
atio
n
o
f
f
ice
s
to
im
p
r
o
v
e
co
m
m
u
n
ity
s
er
v
ices.
C
lu
s
ter
in
g
tech
n
iq
u
es
ar
e
ap
p
lied
to
f
in
d
b
etter
way
s
o
f
m
an
ag
in
g
c
o
m
p
lain
ts
.
C
lu
s
ter
in
g
,
p
ar
ticu
lar
ly
th
e
K
-
m
ea
n
s
tech
n
iq
u
e,
h
as
b
ee
n
em
p
lo
y
e
d
to
ag
g
r
eg
ate
an
d
v
is
u
alize
e
x
ten
s
iv
e,
u
n
s
tr
u
ctu
r
ed
d
ata
c
o
m
p
lain
ts
in
a
clo
u
d
f
o
r
m
at
ac
co
r
d
in
g
to
th
e
d
is
co
v
er
ed
r
o
o
t
ca
u
s
es
[
9
]
.
T
h
e
m
ai
n
co
n
clu
s
io
n
s
o
b
tain
ed
f
r
o
m
t
h
e
g
r
o
u
p
in
g
o
f
d
ata
co
m
p
lain
ts
in
th
e
civ
il
r
e
g
is
tr
y
o
f
f
ice
c
o
n
f
ir
m
th
at
d
ata
m
i
n
in
g
is
ef
f
icien
t
in
o
b
tain
in
g
th
e
r
o
o
t
ca
u
s
es
o
f
co
m
p
lain
ts
[
1
0
]
.
R
es
ea
r
ch
r
el
ated
to
th
e
u
s
e
o
f
b
ir
th
d
ata
i
n
r
ec
o
r
d
s
f
o
r
u
s
e
T
h
e
u
s
e
o
f
p
o
p
u
latio
n
d
ata
at
th
e
civ
il
r
eg
is
tr
atio
n
o
f
f
ice
is
p
r
o
ce
s
s
ed
b
y
ap
p
ly
in
g
d
ata
m
i
n
in
g
clu
s
ter
in
g
u
s
in
g
t
h
e
K
-
m
ea
n
s
alg
o
r
ith
m
to
clu
s
ter
an
d
d
escr
ib
e
th
e
clu
s
ter
in
g
o
f
ch
ild
r
e
n
'
s
d
ata
b
as
e
d
o
n
th
e
n
u
m
b
er
o
f
c
h
ild
r
e
n
'
s
b
ir
th
ce
r
tific
ate
o
wn
er
s
h
ip
in
ea
c
h
s
u
b
-
d
is
tr
ict
wh
er
e
th
e
clu
s
ter
in
g
r
esu
lts
ca
n
b
e
u
s
ed
as
m
ater
ial
f
o
r
p
lan
n
in
g
an
d
ev
alu
atin
g
tar
g
ets
in
b
ir
th
ce
r
t
if
icate
o
wn
er
s
h
ip
s
er
v
ices
an
d
ch
ild
id
e
n
tity
ca
r
d
to
ac
ce
ler
a
te
th
e
ac
h
iev
e
m
en
t
o
f
b
ir
th
ce
r
tific
ate
an
d
ch
ild
i
d
en
tity
ca
r
d
o
w
n
er
s
h
ip
tar
g
et
s
s
et
b
y
th
e
g
o
v
er
n
m
e
n
t
[
1
1
]
.
T
h
e
r
esu
lts
o
f
th
e
f
o
r
m
ed
K
-
m
ea
n
s
clu
s
ter
in
g
p
r
o
d
u
ce
d
g
r
o
u
p
s
o
f
s
u
b
-
d
is
tr
icts
in
ea
ch
cl
u
s
ter
,
ca
teg
o
r
ized
b
ased
o
n
th
e
s
co
p
e
o
f
n
o
n
-
o
wn
e
r
s
h
ip
o
f
b
ir
th
ce
r
t
if
icate
s
[
1
2
]
.
R
esear
ch
r
elate
d
to
d
ata
m
in
i
n
g
an
al
y
s
is
o
n
p
o
p
u
latio
n
d
at
a
b
y
m
in
in
g
p
o
p
u
latio
n
d
ata
b
elo
n
g
in
g
to
th
e
city
g
o
v
er
n
m
en
t
o
f
Al
Kh
u
m
s
in
L
ib
y
a
[
1
3
]
.
T
h
is
s
tu
d
y
u
t
ilizes
p
o
p
u
latio
n
d
ata
in
Al
Kh
u
m
s
m
u
n
icip
ality
in
L
ib
y
a
b
y
m
in
in
g
class
if
icatio
n
d
ata
u
s
in
g
th
e
k
-
n
ea
r
est
n
eig
h
b
o
r
s
(
KNN
)
alg
o
r
ith
m
an
d
g
r
o
u
p
in
g
d
ata
tech
n
iq
u
es
with
th
e
K
-
m
ea
n
s
m
eth
o
d
f
o
r
p
o
v
er
t
y
lev
el
m
ea
s
u
r
em
e
n
t
(
th
r
o
u
g
h
in
c
o
m
e)
,
p
o
p
u
latio
n
r
ate
in
cr
ea
s
e
m
ea
s
u
r
em
en
t
(
th
r
o
u
g
h
m
a
r
r
iag
e)
a
n
d
p
o
p
u
latio
n
r
ate
d
ec
lin
e
m
e
asu
r
em
en
t
(
t
h
r
o
u
g
h
d
ea
th
)
.
T
h
e
s
tu
d
y
'
s
co
n
clu
s
io
n
claim
ed
to
b
e
th
e
f
ir
s
t
o
f
its
k
in
d
,
is
b
ased
o
n
h
elp
in
g
d
ec
is
io
n
-
m
ak
er
s
in
m
u
n
icip
alities
m
ak
e
in
f
o
r
m
e
d
d
ec
is
io
n
s
.
T
h
e
r
esu
lts
o
f
t
h
is
clu
s
t
er
ca
n
b
e
u
s
ed
as
a
r
ef
er
en
ce
f
o
r
th
e
p
o
p
u
latio
n
an
d
civ
il
r
eg
is
tr
atio
n
o
f
f
ice
in
m
ap
p
in
g
b
ir
th
c
er
tific
ate
d
ata
in
I
n
d
o
n
esia.
An
d
r
elat
io
n
to
th
e
g
r
o
u
p
in
g
o
f
b
ir
th
d
ata
with
th
e
r
esear
ch
titl
e
ap
p
licatio
n
o
f
th
e
K
-
m
ea
n
s
m
eth
o
d
f
o
r
c
lu
s
ter
in
g
ch
ild
d
ata
b
as
ed
o
n
b
ir
t
h
ce
r
tific
ate
o
w
n
er
s
h
ip
a
n
d
m
ater
n
al
an
d
ch
i
ld
h
ea
lth
ca
r
e
(
MCH
)
in
th
e
s
tu
d
y
f
o
u
n
d
th
e
b
est
n
u
m
b
er
o
f
clu
s
ter
s
f
o
r
th
e
s
am
e
b
ir
th
d
ata
cl
u
s
ter
in
t
h
e
f
ir
s
t stu
d
y
,
n
a
m
ely
4
clu
s
ter
s
[
1
4
]
,
W
h
ile
th
e
r
esear
ch
o
n
clu
s
ter
in
g
test
ed
f
o
u
r
m
et
h
o
d
s
-
elb
o
w,
g
a
p
s
tatis
tic,
s
ilh
o
u
ette
co
ef
f
icien
t,
a
n
d
ca
n
o
p
y
-
to
d
eter
m
in
e
th
e
K
v
alu
e
in
th
e
K
-
m
ea
n
s
m
eth
o
d
[
1
5
]
.
No
n
e
o
f
th
ese
s
tu
d
ie
s
f
o
cu
s
o
n
d
elay
s
in
b
ir
th
r
eg
is
tr
atio
n
,
d
esp
ite
av
ailab
le
d
a
ta
th
at
co
u
ld
s
u
p
p
o
r
t
s
u
ch
a
n
aly
s
is
.
T
h
ese
d
elay
s
m
ay
s
tem
f
r
o
m
d
ata
ac
ce
s
s
o
r
s
ec
u
r
ity
is
s
u
es
at
th
e
civ
il
r
eg
is
tr
y
o
f
f
ice.
Ho
wev
er
,
th
is
r
esear
ch
o
f
f
er
s
s
eg
m
en
tatio
n
in
s
ig
h
ts
th
at
h
elp
p
o
licy
m
ak
er
s
u
n
d
er
s
tan
d
t
h
e
d
is
tr
ib
u
tio
n
o
f
r
eg
is
tr
atio
n
d
elay
s
,
en
a
b
lin
g
t
ar
g
eted
in
ter
v
en
tio
n
s
an
d
d
ata
-
d
r
iv
en
d
ec
is
io
n
s
to
im
p
r
o
v
e
t
h
e
civ
il r
eg
is
tr
atio
n
s
y
s
tem
an
d
p
r
o
m
o
te
tim
ely
r
eg
i
s
tr
atio
n
s
.
2.
M
E
T
H
O
D
2
.
1
.
K
-
m
e
a
ns
clus
t
er
ing
a
lg
o
rit
hm
T
h
e
K
-
m
ea
n
s
alg
o
r
ith
m
is
a
n
o
n
-
h
ier
a
r
ch
ical
clu
s
ter
in
g
m
eth
o
d
th
at
p
ar
titi
o
n
s
d
ata
i
n
to
d
is
tin
ct
g
r
o
u
p
s
b
ased
o
n
s
h
ar
ed
f
ea
t
u
r
es,
en
s
u
r
i
n
g
h
ig
h
s
im
ilar
ity
with
in
ea
ch
clu
s
ter
[
1
6
]
.
Data
with
d
is
s
im
ilar
ch
ar
ac
ter
is
tics
,
ex
h
ib
itin
g
lo
w
in
ter
-
class
s
im
ilar
ity
,
ar
e
ass
ig
n
ed
t
o
s
ep
ar
ate
clu
s
ter
s
[
1
7
]
.
Su
b
s
eq
u
en
tly
,
th
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ad
v
Ap
p
l Sci
I
SS
N:
2252
-
8
8
1
4
B
ir
th
d
a
ta
clu
s
teri
n
g
to
s
eg
me
n
ta
tio
n
d
el
a
ys in
b
ir
th
ce
r
tifi
ca
te
r
eg
is
tr
a
tio
n
(
E
r
fa
n
Ha
s
min
)
515
alg
o
r
ith
m
co
m
p
u
tes
th
e
d
is
tan
ce
b
etwe
en
ea
ch
d
ata
p
o
in
t
an
d
ea
ch
clu
s
ter
ce
n
t
er
ce
n
ter
s
[
1
8
]
th
e
E
u
clid
ea
n
d
is
tan
ce
f
o
r
m
u
la
is
n
a
m
ed
,
(
)
i
n
(
1
)
.
=
√
∑
{
−
}
2
=
1
(
1)
T
h
e
ca
lcu
latio
n
o
f
t
h
e
in
itial
d
ata
d
is
tan
ce
u
s
in
g
(
1
)
is
p
e
r
f
o
r
m
ed
ag
ain
s
t
th
e
ce
n
tr
o
i
d
v
alu
es
o
f
ea
c
h
clu
s
ter
b
ased
o
n
th
e
s
ev
en
cr
it
er
ia
u
tili
ze
d
.
Dis
tan
ce
b
etwe
en
th
e
f
ir
s
t d
at
a
an
d
th
e
ce
n
tr
o
id
p
o
in
t
o
f
clu
s
ter
_
0
(
C
0
)
,
0
=
√
(
(
2
−
2
)
2
)
+
(
(
1
−
1
)
2
)
+
(
(
2
−
2
)
2
)
+
(
(
3
−
3
)
2
+
(
(
1
−
1
)
2
)
+
(
(
1
−
1
)
2
)
+
(
(
5
−
5
)
2
)
)
0
=
0
Dis
tan
ce
b
etwe
en
th
e
f
ir
s
t d
at
a
an
d
th
e
ce
n
tr
o
id
p
o
in
t
o
f
clu
s
ter
_
1
(
C
1
)
,
C1
=
√
(
(
2
−
1
)
2
)
+
(
(
1
−
1
)
2
)
+
(
(
2
−
2
)
2
)
+
(
(
3
−
2
)
2
+
(
(
1
−
2
)
2
)
+
(
(
1
−
1
)
2
)
+
(
(
5
−
3
)
2
)
)
C1
=
7
Dis
tan
ce
b
etwe
en
th
e
f
ir
s
t d
at
a
an
d
th
e
ce
n
tr
o
id
p
o
in
t
o
f
clu
s
ter
_
2
(
C
2
)
,
2
=
√
(
(
2
−
1
)
2
)
+
(
(
1
−
5
)
2
)
+
(
(
2
−
1
)
2
)
+
(
(
3
−
1
)
2
+
(
(
1
−
2
)
2
)
+
(
(
1
−
1
)
2
)
+
(
(
5
−
4
)
2
)
)
2
=
24
A
d
ata
p
o
in
t
will
b
e
a
s
s
ig
n
ed
t
o
th
e
k
-
th
clu
s
ter
if
its
d
is
tan
c
e
to
th
e
ce
n
ter
o
f
th
e
k
-
th
clu
s
ter
is
th
e
m
in
im
u
m
am
o
n
g
all
d
is
tan
ce
s
to
t
h
e
ce
n
ter
s
o
f
o
th
er
cl
u
s
ter
s
.
T
h
e
ca
lc
u
latio
n
ca
n
b
e
p
er
f
o
r
m
e
d
u
s
in
g
au
to
m
atio
n
o
r
b
y
d
eter
m
in
in
g
th
e
m
in
im
u
m
v
al
u
e
o
f
th
e
o
b
jectiv
e
eq
u
atio
n
.
Su
b
s
eq
u
en
tly
,
t
h
e
c
o
llected
d
ata
is
o
r
g
an
i
z
e
d
in
t
o
s
ev
er
al
clu
s
ter
s
,
ea
ch
co
m
p
r
is
in
g
its
r
esp
ec
tiv
e
m
em
b
e
r
s
.
Min
im
u
m
v
al
u
e
in
(
2
)
.
min
∑
=
1
(
2
)
I
m
p
lem
en
t
(
2
)
b
y
d
eter
m
in
in
g
th
e
s
m
allest v
alu
e
f
r
o
m
t
h
e
r
e
s
u
lts
o
f
th
e
ce
n
tr
o
id
ca
lcu
latio
n
s
.
C
lu
s
ter
=0
→
b
ec
au
s
e
C
0
is
s
m
aller
th
an
C
1
an
d
C
2
.
T
h
e
ca
lcu
latio
n
o
f
th
e
n
ew
c
lu
s
ter
ce
n
ter
v
alu
e
in
v
o
lv
es
d
eter
m
in
in
g
t
h
e
m
ea
n
v
alu
e
o
f
th
e
d
ata
p
o
in
ts
th
at
b
elo
n
g
to
th
e
clu
s
ter
,
as sp
ec
if
ied
b
y
(
3
)
.
=
1
∑
=
1
(
3
)
W
h
ich
∈
o
r
x
ij
is
in
th
e
k
-
th
clu
s
t
er
,
an
d
p
is
th
e
n
u
m
b
er
o
f
m
e
m
b
er
s
o
f
th
e
k
-
th
clu
s
ter
.
T
h
e
n
ew
clu
s
ter
ce
n
ter
p
o
in
t
is
d
eter
m
in
ed
u
s
in
g
th
e
clu
s
t
er
ce
n
ter
p
o
in
t
f
o
r
m
u
la
o
n
(
3
)
b
ased
o
n
d
ata
f
r
o
m
ea
ch
clu
s
ter
m
em
b
e
r
.
N
e
w
p
o
i
n
t
c
l
u
s
t
e
r
_
0
=
(
(
2
+1
)
)
/2
=1
.
5
(
(
1
+1
)
)
/2
=1
(
(
2
+2
)
)
/2
=2
(
(
3
+4
)
)
/2
=3
.
5
(
(
1
+2
)
)
/
2
=1
.
5
(
(
1
+1
)
)
/2
=
2
(
(
5
+6
)
)
/2
=5
.
5
=
1
.
5
,
1
,
2
,
3
.
5
,
1
.
5
,
2
,
5
.
5
T
h
e
f
u
n
d
am
en
tal
al
g
o
r
ith
m
u
t
ili
z
ed
in
K
-
m
ea
n
s
is
i)
s
p
ec
if
y
th
e
n
u
m
b
er
o
f
clu
s
ter
s
(
k
)
an
d
s
et
an
ar
b
itra
r
y
clu
s
ter
ce
n
ter
,
ii)
ca
l
cu
late
th
e
d
is
tan
ce
o
f
ea
ch
r
ec
o
r
d
to
th
e
clu
s
ter
ce
n
ter
u
s
in
g
,
ii)
g
r
o
u
p
d
ata
in
to
clu
s
ter
s
with
th
e
s
h
o
r
te
s
t
d
is
ta
n
ce
,
iv
)
ca
lcu
late
th
e
n
ew
clu
s
ter
ce
n
ter
,
v
)
s
tep
s
2
th
r
o
u
g
h
4
will
b
e
r
e
p
ea
ted
s
o
n
o
m
o
r
e
d
ata
m
o
v
es to
an
o
t
h
er
clu
s
ter
[
1
9
]
.
2
.
2.
E
lbo
w
a
lg
o
rit
h
m
T
h
e
elb
o
w
m
eth
o
d
is
em
p
lo
y
ed
to
ascer
tain
th
e
o
p
tim
al
n
u
m
b
er
o
f
k
clu
s
ter
s
b
y
an
a
ly
zin
g
th
e
o
u
tco
m
es
o
f
th
e
co
m
p
ar
is
o
n
wh
er
e
th
e
n
u
m
b
er
o
f
clu
s
ter
s
ex
h
ib
its
an
in
f
lectio
n
p
o
i
n
t,
r
e
s
em
b
lin
g
an
elb
o
w
[
2
0
]
.
T
h
is
m
eth
o
d
p
er
f
o
r
m
s
u
n
lim
ited
test
clu
s
ter
s
to
s
o
lv
e
th
e
s
am
e
ca
s
e,
m
ak
in
g
th
e
o
p
tim
al
n
u
m
b
er
o
f
clu
s
ter
s
ea
s
ier
to
d
eter
m
in
e
[
2
1
]
.
T
h
e
co
m
p
ar
is
o
n
v
alu
e
b
etwe
en
th
e
n
u
m
b
er
o
f
clu
s
ter
s
is
ca
lcu
lated
b
y
ca
lcu
latin
g
th
e
Su
m
o
f
Sq
u
a
r
e
E
r
r
o
r
(
SSE
)
in
ea
ch
cl
u
s
ter
[
2
2
]
.
=
∑
∑
|
|
−
|
|
2
=
1
(
4
)
W
h
ich
K
is
n
u
m
b
er
o
f
clu
s
ter
s
,
Xi
is
i d
ata,
an
d
C
k
is
c
lu
s
ter
ce
n
tr
o
id
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
8
1
4
I
n
t J Ad
v
Ap
p
l Sci
,
Vo
l.
14
,
No
.
2
,
J
u
n
e
2
0
2
5
:
5
1
3
-
522
516
Plo
ttin
g
th
e
p
e
r
f
o
r
m
an
ce
d
if
f
er
en
ce
s
f
o
r
k
v
alu
es
r
a
n
g
in
g
f
r
o
m
2
to
7
,
it
b
ec
o
m
es
ev
id
e
n
t
th
at
th
e
m
o
s
t
s
ig
n
if
ican
t
im
p
r
o
v
em
en
t
o
cc
u
r
s
at
k
=3
.
T
h
is
s
u
g
g
ests
th
at
th
r
ee
clu
s
ter
s
b
est
r
ep
r
esen
t
th
e
u
n
d
er
ly
in
g
s
tr
u
ctu
r
e
o
f
th
e
d
ata,
b
alan
cin
g
m
o
d
el
co
m
p
le
x
it
y
an
d
ex
p
lan
ato
r
y
p
o
wer
.
Selectin
g
th
is
o
p
tim
al
clu
s
ter
co
u
n
t
h
elp
s
en
s
u
r
e
m
ea
n
in
g
f
u
l
an
d
in
ter
p
r
etab
le
g
r
o
u
p
i
n
g
s
,
wh
ic
h
ca
n
en
h
a
n
ce
s
u
b
s
eq
u
en
t
a
n
aly
s
is
an
d
d
ec
is
io
n
-
m
ak
in
g
p
r
o
ce
s
s
es.
T
ab
le
1
s
h
o
ws
th
at
th
e
lar
g
est
p
er
f
o
r
m
an
ce
d
if
f
er
e
n
ce
o
cc
u
r
s
at
k
=3
,
w
ith
a
v
alu
e
o
f
0
.
6
7
1
,
in
d
icatin
g
th
e
o
p
tim
al
c
lu
s
ter
co
u
n
t.
T
ab
le
1
.
B
ir
th
d
ata
cl
u
s
ter
d
is
tan
ce
p
er
f
o
r
m
an
ce
v
alu
e
k
Av
e
r
a
g
e
c
e
n
t
r
o
i
d
d
i
st
a
n
c
e
D
i
f
f
e
r
e
n
c
e
2
3
.
9
4
0
3
3
.
2
6
9
0
.
6
7
1
4
2
.
8
0
.
4
6
9
5
2
.
4
6
2
0
.
3
3
8
6
2
.
0
8
9
0
.
3
7
3
7
1
.
8
6
3
0
.
2
2
6
2
.
3
.
Sil
ho
uet
t
e
a
lg
o
rit
hm
T
h
e
s
ilh
o
u
ette
co
ef
f
icien
t
is
a
wid
ely
u
s
ed
m
etr
ic
f
o
r
ev
alu
atin
g
th
e
q
u
ality
an
d
s
tr
en
g
th
o
f
clu
s
ter
s
in
a
d
ataset
[
2
3
]
.
I
t
co
m
b
in
es
two
k
ey
asp
ec
ts
:
co
h
esiv
en
ess
,
wh
ich
m
ea
s
u
r
es
h
o
w
clo
s
ely
r
elate
d
o
b
jects
ar
e
with
in
th
e
s
am
e
clu
s
ter
,
an
d
s
ep
ar
atio
n
,
wh
ic
h
ass
ess
es
h
o
w
d
is
tin
ct
o
r
well
-
s
ep
ar
ated
a
cl
u
s
ter
is
f
r
o
m
o
t
h
e
r
clu
s
ter
s
.
B
y
b
alan
cin
g
th
ese
t
wo
f
ac
to
r
s
,
th
e
s
ilh
o
u
ette
co
ef
f
icien
t
p
r
o
v
i
d
es
a
s
in
g
le
v
alu
e
th
at
r
ef
lects
h
o
w
ap
p
r
o
p
r
iately
th
e
d
ata
h
as
b
ee
n
clu
s
ter
ed
[
2
4
]
.
A
h
i
g
h
er
co
ef
f
icien
t
in
d
icate
s
th
at
clu
s
ter
s
ar
e
b
o
th
co
m
p
ac
t
an
d
well
-
s
ep
ar
ated
,
wh
ich
is
d
esira
b
le
f
o
r
m
ea
n
in
g
f
u
l
clu
s
t
er
in
g
r
esu
lts
.
T
h
is
m
eth
o
d
h
elp
s
in
v
alid
atin
g
th
e
ef
f
ec
tiv
en
ess
o
f
clu
s
ter
in
g
al
g
o
r
ith
m
s
an
d
i
n
s
elec
tin
g
th
e
o
p
tim
al
n
u
m
b
e
r
o
f
clu
s
ter
s
.
C
alcu
late
th
e
av
er
ag
e
d
is
tan
ce
o
f
d
o
cu
m
en
t i
with
all
d
o
cu
m
en
ts
in
o
th
er
clu
s
ter
s
.
(
,
)
=
1
∣
∣
∑
(
,
)
∈
(
5
)
C
alcu
late
th
e
s
ilh
o
u
ette
co
ef
f
i
cien
t
v
alu
e.
(
)
=
(
)
−
(
)
(
(
)
,
(
)
)
(
6
)
T
h
e
r
esu
lts
o
f
th
e
b
ir
t
h
d
ata
cl
u
s
ter
ar
e
t
h
en
o
p
tim
ized
u
s
in
g
th
e
s
ilh
o
u
ette
m
eth
o
d
to
d
ete
r
m
in
e
th
e
o
p
tim
al
n
u
m
b
er
o
f
clu
s
ter
s
.
T
h
e
f
o
llo
win
g
ar
e
th
e
r
esu
lts
o
f
th
e
s
ilh
o
u
ette
co
ef
f
icien
t c
alcu
latio
n
b
ased
o
n
th
e
ca
lcu
latio
n
o
f
th
e
v
alu
es
k
=2
to
k
=7
.
r
esu
lts
o
f
t
h
e
s
ilh
o
u
ette
co
ef
f
icien
t
ca
lcu
latio
n
p
r
o
ce
s
s
o
n
th
e
b
ir
t
h
clu
s
ter
d
ata,
th
e
m
ax
im
u
m
s
ilh
o
u
ette
co
ef
f
icien
t
r
esu
lt
is
wh
en
k
=
3
with
a
s
ilh
o
u
ette
v
al
u
e
=0
.
5
7
3
,
as
s
ee
n
in
T
ab
le
2
.
T
ab
le
2
.
B
ir
th
d
ata
s
ilh
o
u
ette
co
ef
f
icien
t
k
S
i
l
h
o
u
e
t
t
e
c
o
e
f
f
i
c
i
e
n
t
R
a
n
k
2
0
.
4
7
0
3
3
0
.
5
7
3
1
4
0
.
4
7
4
2
5
0
.
4
6
2
4
6
0
.
4
6
1
5
7
0
.
4
5
2
6
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
Fo
r
m
in
g
b
ir
th
d
ata
clu
s
ter
s
o
f
f
er
s
v
alu
a
b
le
in
s
ig
h
ts
,
p
a
r
ticu
lar
ly
f
o
r
p
o
licy
p
lan
n
in
g
.
T
h
is
p
r
o
ce
s
s
in
v
o
lv
es
g
r
o
u
p
in
g
b
ir
th
r
ec
o
r
d
s
b
ased
o
n
s
im
ilar
ities
in
s
p
ec
if
ic
f
ea
tu
r
es,
s
er
v
in
g
as
th
e
in
itial
s
tep
in
s
u
b
s
eq
u
en
t
an
aly
s
is
[
2
5
]
.
I
n
t
h
e
clu
s
ter
in
g
p
r
o
ce
s
s
,
it
is
n
e
ce
s
s
ar
y
to
estab
lis
h
th
e
n
u
m
b
er
o
f
clu
s
ter
s
.
T
h
e
f
u
n
ctio
n
o
f
f
o
r
m
in
g
th
e
n
u
m
b
er
o
f
clu
s
ter
s
is
to
d
eter
m
in
e
h
o
w
m
an
y
clu
s
ter
s
will
b
e
u
s
ed
in
th
e
clu
s
ter
in
g
p
r
o
ce
s
s
.
T
h
is
ca
n
af
f
ec
t
th
e
f
i
n
al
r
esu
lt
o
f
th
e
an
aly
s
is
an
d
t
h
e
r
esu
ltin
g
in
ter
p
r
etatio
n
[
2
4
]
.
T
h
e
f
o
r
m
atio
n
o
f
b
ir
th
d
ata
clu
s
ter
s
is
d
iv
id
e
d
b
ased
o
n
s
ev
en
r
ele
v
an
t
c
r
iter
ia,
in
clu
d
i
n
g
i)
p
lace
o
f
b
ir
th
,
i
i)
ty
p
e
o
f
b
ir
th
,
iii)
b
ir
th
,
iv
)
atten
d
an
t
,
v
)
b
i
r
th
o
r
d
er
,
v
i)
g
en
d
er
,
v
ii)
ag
e
o
f
th
e
ch
ild
wh
en
th
e
b
ir
th
was r
eg
is
ter
ed
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ad
v
Ap
p
l Sci
I
SS
N:
2252
-
8
8
1
4
B
ir
th
d
a
ta
clu
s
teri
n
g
to
s
eg
me
n
ta
tio
n
d
el
a
ys in
b
ir
th
ce
r
tifi
ca
te
r
eg
is
tr
a
tio
n
(
E
r
fa
n
Ha
s
min
)
517
3
.
1
.
F
r
a
m
ewo
r
k
T
h
e
f
ir
s
t
s
tag
e
o
f
th
is
r
esear
c
h
d
esig
n
in
v
o
lv
es
p
r
e
-
p
r
o
ce
s
s
in
g
b
ir
th
d
ata
f
r
o
m
th
e
Ma
k
a
s
s
ar
C
ity
p
o
p
u
latio
n
an
d
civ
il
r
e
g
is
tr
atio
n
d
atab
ase
(
2
0
1
9
-
2
0
2
3
)
.
T
h
is
s
tep
is
cr
itical
to
en
s
u
r
e
th
e
d
ata'
s
ac
cu
r
ac
y
,
co
m
p
leten
ess
,
an
d
co
n
s
is
ten
c
y
b
ef
o
r
e
a
n
y
an
aly
s
is
is
co
n
d
u
cted
.
T
h
e
r
esear
ch
f
r
am
ewo
r
k
is
d
iv
id
ed
in
to
two
m
ain
p
ar
ts
,
as
illu
s
tr
ated
in
Fi
g
u
r
e
1
th
e
f
ir
s
t
p
ar
t
f
o
cu
s
es
o
n
d
ata
p
r
ep
ar
atio
n
an
d
clea
n
in
g
,
wh
ile
th
e
s
ec
o
n
d
p
ar
t in
v
o
l
v
es a
p
p
ly
in
g
an
aly
ti
ca
l m
eth
o
d
s
to
u
n
co
v
e
r
p
atter
n
s
an
d
in
s
ig
h
ts
.
B
i
r
t
h
D
a
t
a
R
e
g
i
s
t
r
a
t
i
o
n
C
l
u
s
t
e
r
i
n
g
(
K
-
M
e
a
n
s
)
B
i
r
t
h
D
a
t
a
C
l
u
s
t
e
r
C1
C2
CN
P
R
E
P
R
O
C
E
S
S
I
N
G
D
AT
A
P
R
E
P
AR
AT
I
O
N
C
O
LLE
C
T
D
A
T
A
F
R
O
M
C
I
V
I
L
R
E
GI
S
T
R
AT
I
O
N
O
F
F
I
C
E
S
e
l
e
c
ti
o
n
V
a
l
i
d
a
ti
o
n
C
l
e
a
n
i
n
g
E
v
a
l
u
a
t
i
o
n
C
l
u
st
e
r
w
i
t
h
E
l
b
o
w
a
n
d
S
i
l
h
o
u
e
t
t
e
Fig
u
r
e
1
.
Desig
n
f
r
am
ewo
r
k
T
h
e
d
ata
v
alid
atio
n
p
r
o
ce
s
s
is
an
ess
en
tial
s
tag
e
in
m
a
n
ag
in
g
th
e
d
ataset
to
en
s
u
r
e
th
e
ac
c
u
r
ac
y
an
d
co
n
s
is
ten
cy
o
f
th
e
in
f
o
r
m
atio
n
co
n
tain
e
d
in
th
e
d
ataset.
T
h
is
in
clu
d
es
ch
ec
k
s
to
d
etec
t
d
u
p
licates,
m
is
s
in
g
v
alu
es,
o
r
o
th
er
in
c
o
n
s
is
ten
cies
in
th
e
d
ataset
[
2
6
]
.
T
h
i
s
p
r
o
ce
s
s
in
v
o
lv
es
a
s
er
ies
o
f
s
tep
s
to
id
en
tify
,
o
v
er
co
m
e
,
an
d
r
em
o
v
e
p
r
o
b
le
m
s
in
th
e
d
ataset
s
u
ch
as
i
d
en
tific
atio
n
o
f
m
is
s
in
g
v
alu
es,
n
o
is
y
d
ata
clea
n
i
n
g
,
r
em
o
v
e
o
u
tlier
s
(
r
em
o
v
in
g
o
b
s
er
v
atio
n
r
esu
lts
th
at
ar
e
s
ig
n
i
f
ican
tly
d
if
f
e
r
en
t
f
r
o
m
th
e
m
a
jo
r
ity
o
f
t
h
e
d
ata
in
th
e
d
ataset)
,
an
d
r
eso
lv
e
in
co
n
s
is
ten
cies
[
2
7
]
.
Nex
t,
th
e
K
-
m
ea
n
s
clu
s
ter
in
g
m
o
d
el
is
s
h
o
w
n
in
Fig
u
r
e
2
.
Fig
u
r
e
2
.
K
-
m
ea
n
s
clu
s
ter
in
g
m
o
d
el
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
8
1
4
I
n
t J Ad
v
Ap
p
l Sci
,
Vo
l.
14
,
No
.
2
,
J
u
n
e
2
0
2
5
:
5
1
3
-
522
518
T
h
e
K
-
m
ea
n
s
ap
p
licatio
n
s
tar
ts
b
y
s
elec
tin
g
t
h
e
n
u
m
b
er
o
f
clu
s
ter
s
to
g
r
o
u
p
6
,
0
0
3
b
i
r
th
r
ec
o
r
d
s
,
test
ed
f
r
o
m
2
to
7
clu
s
ter
s
u
s
in
g
s
ev
en
cr
iter
ia.
A
s
im
u
lati
o
n
with
1
0
d
ata
p
o
i
n
ts
illu
s
tr
ates
th
is
c
lu
s
ter
in
g
p
r
o
ce
s
s
.
T
h
e
d
esig
n
ex
p
l
o
r
es
d
if
f
er
e
n
t
clu
s
ter
co
u
n
ts
to
f
i
n
d
th
e
o
p
tim
al
g
r
o
u
p
in
g
,
d
et
er
m
in
ed
u
s
in
g
th
e
elb
o
w
an
d
s
ilh
o
u
ette
m
eth
o
d
s
.
3
.
2
.
Da
t
a
s
et
T
h
e
Ma
k
ass
ar
C
ity
p
o
p
u
latio
n
an
d
ci
v
il
r
eg
is
tr
atio
n
o
f
f
ice
b
ir
th
d
ata
c
o
n
tain
s
1
2
,
3
3
4
r
e
co
r
d
s
with
th
r
ee
s
tatu
s
es:
ac
ce
p
ted
,
r
ejec
ted
,
an
d
in
co
m
p
lete.
On
ly
ac
ce
p
ted
d
ata
is
p
r
o
ce
s
s
ed
.
Dat
a
clea
n
in
g
in
v
o
lv
es
ch
ec
k
in
g
f
o
r
e
m
p
ty
f
ield
s
an
d
m
is
s
in
g
v
alu
es
to
e
n
s
u
r
e
e
r
r
o
r
-
f
r
ee
d
ata.
R
ec
o
r
d
s
with
m
is
s
in
g
v
alu
es
ar
e
r
em
o
v
ed
.
Deta
iled
s
tatu
s
in
f
o
r
m
atio
n
is
s
h
o
wn
in
T
a
b
le
3
.
T
ab
le
3
.
B
ir
th
d
ataset
No
C
o
u
n
t
D
e
scri
p
t
i
o
n
1
1
2
,
3
3
4
O
r
i
g
i
n
a
l
b
i
r
t
h
d
a
t
a
f
r
o
m
c
i
v
i
l
r
e
g
i
st
r
a
t
i
o
n
2
7
,
1
9
3
O
r
i
g
i
n
a
l
b
i
r
t
h
d
a
t
a
w
i
t
h
a
c
c
e
p
t
e
d
st
a
t
u
s
3
6
,
0
0
3
B
i
r
t
h
d
a
t
a
a
f
t
e
r
d
a
t
a
c
l
e
a
n
i
n
g
T
h
e
r
esu
lts
o
f
th
e
d
ata
v
alid
atio
n
en
s
u
r
e
th
at
t
h
e
d
ata
to
b
e
p
r
o
ce
s
s
ed
is
f
r
ee
f
r
o
m
e
r
r
o
r
s
an
d
co
r
r
esp
o
n
d
s
to
th
e
v
u
ln
er
ab
le
v
alu
e
b
ased
o
n
th
is
v
alid
atio
n
p
r
o
ce
s
s
.
Of
th
e
s
ev
en
cr
iter
ia
u
s
ed
in
b
ir
th
d
ata,
th
e
cr
iter
io
n
f
o
r
t
h
e
ag
e
o
f
th
e
ch
ild
(
lab
el/tar
g
et
c
r
iter
ia)
w
h
en
th
e
b
ir
th
was
r
eg
is
ter
ed
p
r
o
v
id
es
in
f
o
r
m
atio
n
o
n
th
e
d
ata,
in
clu
d
in
g
th
e
t
y
p
e
o
f
b
ir
th
r
e
g
is
tr
atio
n
th
at
is
o
n
tim
e
o
r
late.
T
h
e
d
is
tr
ib
u
tio
n
o
f
d
ata
o
n
th
e
cr
iter
ia
o
f
th
e
c
h
ild
'
s
ag
e
at
b
ir
th
is
d
etailed
in
T
ab
le
4
.
T
ab
le
4
.
Ag
e
o
f
th
e
ch
ild
w
h
e
n
th
e
b
ir
th
was r
eg
is
ter
ed
d
ata
s
et
No
V
a
l
u
e
C
o
u
n
t
S
t
a
t
u
s
1
0
m
o
n
t
h
1
,
9
9
1
On
-
t
i
m
e
2
1
-
3
mo
n
t
h
1
,
8
8
2
D
e
l
a
y
3
4
-
6
mo
n
t
h
1
,
0
3
9
D
e
l
a
y
4
7
-
1
2
m
o
n
t
h
1
,
0
7
3
D
e
l
a
y
5
13
-
2
4
m
o
n
t
h
1
,
0
0
0
D
e
l
a
y
6
M
o
r
e
t
h
a
n
2
4
m
o
n
t
h
s
2
0
8
D
e
l
a
y
T
h
e
clu
s
ter
in
g
r
esu
lts
ab
o
v
e
s
h
o
w
th
e
d
is
tr
ib
u
tio
n
o
f
d
ata
i
n
to
s
ev
er
al
clu
s
ter
s
b
ased
o
n
t
h
e
n
u
m
b
er
o
f
k
(
n
u
m
b
e
r
o
f
clu
s
ter
s
)
,
wh
i
ch
v
ar
ies
f
r
o
m
2
to
7
.
T
h
e
h
ig
h
er
th
e
v
alu
e
o
f
k
,
th
e
m
o
r
e
t
h
e
d
ata
is
s
p
lit
in
to
s
m
aller
an
d
m
o
r
e
s
p
ec
if
ic
clu
s
ter
s
.
T
h
e
d
is
tr
ib
u
tio
n
r
esu
lts
f
o
r
clu
s
ter
0
to
clu
s
ter
6
ca
n
b
e
s
ee
n
in
T
ab
le
5
.
T
ab
le
5
.
K
-
m
ea
n
s
clu
s
ter
in
g
r
esu
lts
o
n
b
ir
th
d
ata
k
2
3
4
5
6
7
c
l
u
st
e
r
0
3
,
9
7
3
3
,
6
6
8
2
,
9
5
9
2
,
6
5
9
1
,
0
0
5
1
,
0
6
5
c
l
u
st
e
r
1
2
,
0
3
0
2
,
0
5
9
2
7
6
2
6
9
1
,
8
2
5
1
,
0
0
5
c
l
u
st
e
r
2
2
7
6
8
5
8
1
,
5
8
6
1
,
5
8
6
2
7
2
c
l
u
st
e
r
3
1
,
9
1
0
1
,
2
1
3
2
7
6
1
,
7
9
8
c
l
u
st
e
r
4
2
7
6
1
,
0
3
9
5
2
1
c
l
u
st
e
r
5
2
7
2
1
,
0
6
6
c
l
u
st
e
r
6
2
7
6
3
.
3
.
O
pti
m
a
l num
ber
o
f
clus
t
er
s
Dete
r
m
in
in
g
th
e
o
p
tim
al
clu
s
ter
is
an
es
s
en
tial
s
tep
in
c
lu
s
ter
in
g
an
aly
s
is
to
en
s
u
r
e
th
e
d
ata
is
d
iv
id
ed
in
to
th
e
r
ig
h
t
g
r
o
u
p
s
.
I
n
th
is
an
aly
s
is
u
s
in
g
th
e
elb
o
w,
clu
s
ter
3
em
er
g
ed
as
th
e
o
p
tim
al
ch
o
ice,
as
it
s
h
o
wed
th
e
lar
g
est
d
ec
r
ea
s
e
i
n
v
ar
ian
ce
wh
en
co
m
p
a
r
ed
t
o
clu
s
ter
s
with
f
ewe
r
o
r
m
o
r
e
g
r
o
u
p
in
g
s
,
in
d
icatin
g
a
p
o
in
t
o
f
d
im
in
is
h
in
g
r
etu
r
n
s
.
Fu
r
th
er
m
o
r
e,
t
h
e
s
ilh
o
u
e
tte
m
eth
o
d
,
wh
ich
e
v
alu
ates
th
e
co
h
esio
n
an
d
s
ep
ar
atio
n
o
f
clu
s
ter
s
b
y
ca
lc
u
latin
g
th
e
s
ilh
o
u
ette
co
ef
f
ici
en
t,
co
r
r
o
b
o
r
ated
th
e
r
esu
lts
o
f
th
e
e
lb
o
w
m
eth
o
d
b
y
also
s
elec
tin
g
clu
s
ter
3
as
th
e
o
p
tim
al
co
n
f
ig
u
r
atio
n
.
T
h
e
r
esu
lts
o
f
th
e
co
m
p
a
r
is
o
n
o
f
th
e
elb
o
w
an
d
s
ilh
o
u
ette
m
eth
o
d
s
ca
n
b
e
s
ee
n
in
T
ab
le
6
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ad
v
Ap
p
l Sci
I
SS
N:
2252
-
8
8
1
4
B
ir
th
d
a
ta
clu
s
teri
n
g
to
s
eg
me
n
ta
tio
n
d
el
a
ys in
b
ir
th
ce
r
tifi
ca
te
r
eg
is
tr
a
tio
n
(
E
r
fa
n
Ha
s
min
)
519
T
ab
le
6
.
C
o
m
p
a
r
is
o
n
o
f
b
ir
th
d
ata
o
p
tim
u
m
clu
s
ter
with
elb
o
w
an
d
s
ilh
o
u
ette
k
El
b
o
w
S
i
l
h
o
u
e
t
t
e
a
v
e
r
a
g
e
c
e
n
t
r
o
i
d
d
i
f
f
e
r
e
n
c
e
si
l
h
o
u
e
t
t
e
c
o
e
f
f
i
c
i
e
n
t
r
a
n
k
2
3
.
9
4
0
0
.
4
3
6
3
3
3
.
2
6
9
0
.
6
7
1
0
.
5
7
3
1
4
2
.
8
0
.
4
6
9
0
.
4
7
4
2
5
2
.
4
6
2
0
.
3
3
8
0
.
4
6
2
4
6
2
.
0
8
9
0
.
3
7
3
0
.
4
6
1
5
7
1
.
8
6
3
0
.
2
2
6
0
.
4
5
2
6
3
.
4
.
K
-
m
e
a
ns
clus
t
er
s
a
nd
d
is
t
ributio
n o
f
birt
h r
eg
is
t
ra
t
io
n dela
y
s
T
h
e
co
h
esiv
en
ess
ap
p
r
o
ac
h
a
s
s
es
s
es
th
e
p
r
o
x
im
ity
o
f
r
elatio
n
s
h
ip
s
am
o
n
g
o
b
jects
with
in
a
clu
s
ter
,
wh
ile
th
e
s
ep
ar
atio
n
m
eth
o
d
ev
alu
ates
th
e
d
is
tin
ctio
n
b
etw
ee
n
clu
s
ter
s
.
T
h
is
co
m
b
in
ed
ap
p
r
o
ac
h
co
n
f
ir
m
s
th
at
th
e
ch
o
s
en
clu
s
ter
in
g
s
tr
u
ctu
r
e
b
alan
ce
s
in
ter
n
al
co
n
s
is
ten
cy
an
d
ex
ter
n
al
d
if
f
er
en
tiatio
n
,
lead
in
g
t
o
m
ea
n
in
g
f
u
l
an
d
in
te
r
p
r
etab
le
g
r
o
u
p
in
g
s
in
th
e
d
ataset.
B
as
ed
o
n
b
o
th
th
e
el
b
o
w
an
d
s
ilh
o
u
ette
an
aly
s
es,
a
th
r
ee
-
clu
s
ter
s
o
lu
tio
n
is
d
ee
m
e
d
m
o
s
t e
f
f
ec
tiv
e
f
o
r
s
eg
m
e
n
tin
g
th
e
b
ir
th
d
ata
as sh
o
wn
in
Fig
u
r
e
3
.
Fig
u
r
e
3
.
Dis
tr
ib
u
tio
n
o
f
b
ir
th
d
ata
with
3
clu
s
ter
s
T
h
is
th
r
ee
-
clu
s
ter
d
is
tr
ib
u
tio
n
p
r
o
v
id
es
an
in
s
ig
h
tf
u
l
v
i
ew
o
f
th
e
d
ata,
ca
p
tu
r
in
g
s
ig
n
if
ican
t
g
r
o
u
p
in
g
s
an
d
lik
ely
u
n
d
er
l
y
in
g
p
atter
n
s
.
Fig
u
r
e
3
s
h
o
ws
th
e
d
is
tr
ib
u
tio
n
o
f
b
ir
th
d
at
a
with
a
v
iew
o
f
3
clu
s
ter
s
,
wh
er
e
cl
u
s
ter
0
is
t
h
e
f
ir
s
t
clu
s
ter
with
3
,
66
8
d
at
a
item
s
,
clu
s
ter
1
is
th
e
s
ec
o
n
d
clu
s
ter
,
wh
ich
is
d
is
p
lay
ed
with
g
r
ee
n
item
s
with
2
,
0
5
9
d
ata
item
s
,
an
d
clu
s
te
r
2
is
th
e
th
ir
d
clu
s
ter
wh
ich
is
s
h
o
wn
in
r
e
d
with
276
d
ata
item
s
.
T
h
e
d
is
tr
ib
u
tio
n
o
f
d
ata
f
o
r
ea
ch
clu
s
ter
o
n
th
e
lab
el
cr
iter
ia
ca
n
b
e
s
ee
n
in
T
ab
le
7
.
T
ab
le
7
.
Dis
tr
ib
u
tio
n
o
f
lab
el
cr
iter
ia
f
o
r
ea
c
h
clu
s
ter
No
C
l
u
st
e
r
C
r
i
t
e
r
i
a
l
a
b
e
l
(
M
o
n
t
h
)
0
1
-
3
4
-
6
6
-
12
12
-
24
>
2
4
o
n
-
t
i
m
e
l
a
t
e
1
B
i
r
t
h
c
l
u
st
e
r
0
1
,
7
0
5
1
,
4
6
4
4
9
9
0
0
0
2
B
i
r
t
h
c
l
u
st
e
r
1
0
0
2
5
3
8
3
9
7
8
4
1
8
3
3
B
i
r
t
h
c
l
u
st
e
r
2
21
32
1
2
1
43
58
1
W
e
f
o
u
n
d
th
at
th
e
p
atter
n
o
f
d
ata
d
is
tr
ib
u
tio
n
f
o
r
th
e
r
eg
is
tr
atio
n
cr
iter
ia
o
f
b
ir
th
e
v
en
ts
with
a
ty
p
e
o
f
0
m
o
n
th
s
(
o
n
-
tim
e)
is
co
n
c
en
tr
ated
in
clu
s
ter
0
.
Ad
d
itio
n
ally
,
th
e
late
r
eg
is
tr
atio
n
cr
iter
ia
f
o
r
th
e
1
-
3
m
o
n
th
an
d
4
-
6
-
m
o
n
th
r
an
g
es a
r
e
also
co
n
ce
n
tr
ated
in
cl
u
s
ter
0
.
I
n
c
o
n
tr
ast,
clu
s
ter
1
s
h
o
ws a
d
if
f
e
r
en
t d
is
tr
ib
u
tio
n
o
f
d
ata
r
eg
ar
d
i
n
g
th
e
r
eg
is
tr
atio
n
cr
iter
ia
f
o
r
b
ir
th
d
ata.
T
h
is
th
r
ee
-
clu
s
ter
co
n
f
ig
u
r
atio
n
o
f
f
er
s
d
ee
p
s
eg
m
en
tatio
n
o
f
th
e
b
ir
t
h
d
ata
,
allo
win
g
f
o
r
id
e
n
tify
in
g
s
ig
n
if
ican
t
p
atter
n
s
am
o
n
g
th
e
lea
d
in
g
g
r
o
u
p
s
in
th
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
8
1
4
I
n
t J Ad
v
Ap
p
l Sci
,
Vo
l.
14
,
No
.
2
,
J
u
n
e
2
0
2
5
:
5
1
3
-
522
520
d
ata.
Fu
r
th
e
r
m
o
r
e,
th
e
d
is
tr
ib
u
tio
n
tab
le
o
f
r
eg
is
tr
atio
n
cr
it
er
ia
s
h
o
ws
th
at
t
h
ese
clu
s
ter
s
p
lay
an
im
p
o
r
ta
n
t
r
o
le
in
u
n
d
er
s
tan
d
i
n
g
th
e
d
is
tr
ib
u
tio
n
o
f
d
elay
s
in
b
ir
th
r
e
g
is
tr
atio
n
.
C
lu
s
ter
0
co
n
ce
n
tr
ates
o
n
d
ata
in
v
o
lv
in
g
tim
ely
r
eg
is
tr
atio
n
(
0
m
o
n
th
s
)
an
d
late
r
eg
is
tr
atio
n
in
th
e
1
-
3
m
o
n
t
h
s
an
d
4
-
6
m
o
n
th
s
.
C
lu
s
ter
1
s
h
o
ws
th
e
d
is
tr
ib
u
tio
n
o
f
d
ata
o
n
b
ir
t
h
r
eg
is
tr
atio
n
with
d
if
f
e
r
en
t
ch
ar
ac
ter
is
tics
.
T
h
ese
r
es
u
lts
u
n
d
er
lin
e
th
e
ef
f
ec
tiv
en
ess
o
f
th
e
th
r
ee
-
clu
s
ter
co
n
f
i
g
u
r
a
tio
n
in
o
p
tim
ally
clu
s
ter
in
g
b
ir
t
h
d
ata.
W
ith
s
eg
m
en
tatio
n
r
esu
lts
th
at
s
u
cc
ess
f
u
lly
id
en
tify
th
e
s
tr
u
ctu
r
e
in
th
e
d
ata
[
2
8
]
a
n
d
en
ab
le
clu
s
ter
in
g
f
o
r
f
u
r
t
h
er
p
r
o
ce
s
s
in
g
[
2
9
]
,
clu
s
ter
0
p
r
o
v
id
es
in
f
o
r
m
atio
n
th
at
ca
n
b
e
ex
p
lo
r
ed
to
u
n
d
er
s
tan
d
b
ir
th
ev
en
ts
r
eg
is
ter
e
d
o
n
tim
e
an
d
th
o
s
e
r
eg
is
ter
ed
late,
with
d
elay
s
r
an
g
in
g
f
r
o
m
1
t
o
6
m
o
n
th
s
.
Simil
ar
ly
,
clu
s
ter
1
ca
n
b
e
e
x
am
in
ed
f
u
r
th
er
to
p
r
o
v
id
e
in
s
ig
h
ts
in
to
b
ir
t
h
ev
e
n
ts
r
eg
is
ter
ed
late,
with
d
elay
s
r
an
g
in
g
f
r
o
m
6
m
o
n
th
s
to
m
o
r
e
th
an
2
4
m
o
n
th
s
.
4.
CO
NCLU
SI
O
N
T
h
is
s
tu
d
y
p
r
esen
ts
f
in
d
in
g
s
in
v
o
lv
in
g
th
e
in
clu
s
io
n
o
f
tar
g
et
lab
els
o
r
cr
iter
ia,
s
p
ec
if
ical
ly
wh
eth
er
a
b
ir
th
is
r
e
g
is
ter
ed
in
t
h
e
cl
u
s
ter
in
g
p
r
o
ce
s
s
,
m
ar
k
in
g
a
d
ep
ar
tu
r
e
f
r
o
m
tr
ad
itio
n
al
m
u
lt
i
-
cr
iter
ia
clu
s
ter
in
g
m
eth
o
d
s
th
at
ty
p
ically
ex
clu
d
e
s
u
ch
lab
els.
T
h
is
in
n
o
v
ativ
e
ap
p
r
o
ac
h
r
esu
lted
in
d
ata
d
is
tr
ib
u
tio
n
s
with
in
ea
ch
clu
s
ter
th
at
wer
e
d
is
tin
ctly
co
n
ce
n
tr
ated
ar
o
u
n
d
th
e
s
p
ec
if
ied
lab
el
o
r
tar
g
et
cr
iter
ia,
en
h
an
cin
g
th
e
clar
ity
an
d
r
elev
a
n
ce
o
f
th
e
c
lu
s
ter
in
g
o
u
tco
m
es.
T
h
e
an
al
y
s
is
o
f
b
ir
th
r
eg
is
tr
atio
n
d
ata
r
ev
ea
led
s
ig
n
if
ican
t
p
atter
n
s
,
with
clu
s
ter
0
r
ep
r
e
s
en
tin
g
ca
s
es
o
f
o
n
-
tim
e
o
r
m
in
im
ally
d
elay
ed
r
eg
is
tr
atio
n
s
(
1
-
6
m
o
n
th
s
)
an
d
clu
s
ter
1
h
ig
h
lig
h
tin
g
i
n
s
tan
ce
s
o
f
s
u
b
s
tan
tial
d
elay
s
(
6
-
2
4
m
o
n
th
s
)
.
T
h
ese
s
eg
m
en
t
atio
n
r
esu
lts
o
f
f
er
p
o
licy
m
ak
er
s
v
alu
a
b
le
in
s
ig
h
ts
in
to
th
e
d
is
tr
ib
u
tio
n
an
d
n
atu
r
e
o
f
b
ir
th
r
e
g
is
tr
atio
n
d
elay
s
,
f
a
cilitatin
g
m
o
r
e
tar
g
eted
in
ter
v
e
n
tio
n
s
an
d
d
at
a
-
d
r
iv
en
s
tr
ateg
ies
to
im
p
r
o
v
e
civ
il
r
eg
is
tr
atio
n
s
y
s
tem
s
an
d
en
co
u
r
a
g
e
tim
ely
r
eg
is
tr
atio
n
s
.
Mo
r
eo
v
er
,
th
e
s
tu
d
y
u
n
d
er
s
co
r
es th
e
p
o
ten
tial
b
en
ef
its
o
f
in
co
r
p
o
r
atin
g
lab
el
o
r
tar
g
et
cr
iter
ia
as
in
teg
r
al
f
ac
to
r
s
in
clu
s
ter
in
g
p
r
o
ce
s
s
es
to
d
ee
p
en
th
e
u
n
d
er
s
tan
d
in
g
o
f
b
ir
th
r
eg
is
tr
atio
n
tr
en
d
s
.
L
o
o
k
in
g
ah
ea
d
,
f
u
tu
r
e
r
esear
ch
c
o
u
ld
f
o
cu
s
o
n
ap
p
ly
in
g
m
o
r
e
ad
v
an
ce
d
cl
u
s
ter
in
g
tech
n
iq
u
es,
s
u
ch
as
d
y
n
am
ic
clu
s
ter
in
g
m
o
d
els,
to
b
etter
ca
p
tu
r
e
tem
p
o
r
al
v
ar
iatio
n
s
in
d
elay
ed
r
eg
is
tr
atio
n
s
.
Ad
d
itio
n
ally
,
in
teg
r
atin
g
m
ac
h
in
e
lear
n
in
g
a
p
p
r
o
ac
h
es
lik
e
n
eu
r
al
n
etwo
r
k
s
a
n
d
class
if
icatio
n
alg
o
r
ith
m
s
with
clu
s
ter
in
g
m
a
y
en
h
an
ce
th
e
ac
cu
r
ac
y
o
f
p
r
e
d
ictin
g
u
n
r
eg
is
ter
ed
b
ir
th
s
,
u
ltima
tely
c
o
n
tr
ib
u
tin
g
to
m
o
r
e
ef
f
ec
tiv
e
p
o
licy
f
o
r
m
u
lat
io
n
an
d
r
eso
u
r
ce
allo
ca
tio
n
.
T
h
is
r
esear
ch
th
u
s
lay
s
a
f
o
u
n
d
atio
n
f
o
r
f
u
r
th
er
ex
p
l
o
r
atio
n
in
t
o
h
y
b
r
id
an
al
y
tical
m
eth
o
d
s
th
at
c
o
m
b
in
e
u
n
s
u
p
er
v
is
ed
an
d
s
u
p
er
v
is
ed
lear
n
i
n
g
to
ad
d
r
ess
co
m
p
lex
ch
alle
n
g
es
in
p
o
p
u
latio
n
d
ata
m
an
ag
em
e
n
t.
ACK
NO
WL
E
DG
E
M
E
NT
S
Au
th
o
r
t
h
an
k
s
to
Ma
k
ass
ar
C
ity
C
iv
il
R
eg
is
tr
y
Of
f
ice
f
o
r
t
r
u
s
tin
g
m
e
to
p
r
o
ce
s
s
b
ir
th
r
e
g
is
tr
atio
n
d
ata
f
o
r
t
h
is
r
esear
ch
an
d
to
t
h
e
Dip
an
eg
ar
a
Fo
u
n
d
atio
n
f
o
r
th
eir
tr
u
s
t,
co
n
tr
ib
u
tio
n
,
an
d
f
in
an
cial
s
u
p
p
o
r
t,
wh
ich
h
av
e
b
ee
n
v
er
y
m
ea
n
in
g
f
u
l f
o
r
m
e
in
co
m
p
letin
g
th
is
r
esear
ch
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
T
h
is
r
esear
ch
was
s
u
p
p
o
r
ted
b
y
f
u
n
d
in
g
f
r
o
m
t
h
e
Dip
an
e
g
ar
a
Fo
u
n
d
atio
n
.
A
d
d
itio
n
al
r
eso
u
r
ce
s
wer
e
p
r
o
v
id
e
d
b
y
t
h
e
Ma
k
ass
ar
C
ity
C
iv
il
R
eg
is
tr
at
io
n
Of
f
ice,
wh
ich
g
r
an
ted
ac
ce
s
s
to
th
e
p
o
p
u
latio
n
d
atab
ase
(
2
0
1
9
-
2
0
2
3
)
.
T
h
e
f
u
n
d
in
g
b
o
d
ies
h
ad
n
o
r
o
le
in
t
h
e
d
esig
n
o
f
th
e
clu
s
ter
in
g
m
eth
o
d
o
lo
g
y
,
d
ata
a
n
aly
s
is
,
o
r
in
ter
p
r
etatio
n
o
f
r
esu
lts
r
elate
d
to
b
ir
th
r
eg
is
tr
atio
n
p
atter
n
s
.
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
T
h
is
jo
u
r
n
al
u
s
es
th
e
C
o
n
tr
ib
u
to
r
R
o
les
T
ax
o
n
o
m
y
(
C
R
ed
iT)
to
r
ec
o
g
n
ize
in
d
iv
id
u
al
au
th
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
th
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
llab
o
r
atio
n
.
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
E
r
f
an
Hasm
in
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Aed
ah
Ab
d
R
ah
m
a
n
✓
✓
✓
✓
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ad
v
Ap
p
l Sci
I
SS
N:
2252
-
8
8
1
4
B
ir
th
d
a
ta
clu
s
teri
n
g
to
s
eg
me
n
ta
tio
n
d
el
a
ys in
b
ir
th
ce
r
tifi
ca
te
r
eg
is
tr
a
tio
n
(
E
r
fa
n
Ha
s
min
)
521
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
T
h
e
au
th
o
r
s
d
ec
lar
e
th
at
th
e
r
e
ar
e
n
o
co
n
f
licts
o
f
in
ter
est
r
elate
d
to
th
is
r
esear
ch
.
T
h
e
Ma
k
ass
ar
C
i
ty
C
iv
il
R
eg
is
tr
atio
n
Of
f
ice
p
r
o
v
id
ed
ac
ce
s
s
to
th
e
d
ata
b
u
t
h
ad
n
o
r
o
le
in
t
h
e
s
tu
d
y
d
e
s
ig
n
,
d
ata
an
al
y
s
is
,
in
ter
p
r
etatio
n
,
o
r
m
an
u
s
cr
ip
t
p
r
ep
ar
atio
n
.
All
au
th
o
r
s
h
a
v
e
d
is
clo
s
ed
an
y
p
o
te
n
tial
co
m
p
etin
g
in
ter
ests
an
d
co
n
f
ir
m
t
h
at
n
o
n
e
ex
is
t th
at
co
u
ld
h
av
e
in
f
lu
en
ce
d
th
e
o
u
tco
m
es o
f
th
is
r
esear
ch
.
I
NF
O
RM
E
D
CO
NS
E
N
T
T
h
is
r
esear
ch
was c
o
n
d
u
cted
with
f
o
r
m
al
ap
p
r
o
v
al
f
r
o
m
t
h
e
Ma
k
ass
ar
C
ity
C
iv
il R
eg
is
tr
at
io
n
Of
f
ice.
T
h
e
s
tu
d
y
was
au
th
o
r
ized
u
n
d
er
th
e
p
e
r
m
is
s
io
n
n
u
m
b
er
0
0
0
.
9
_
7
3
3
/Dis
d
u
k
ca
p
il/IX/2
0
2
3
,
en
s
u
r
in
g
th
at
all
d
ata
co
llectio
n
an
d
an
aly
s
is
p
r
o
ce
d
u
r
es c
o
m
p
lied
with
eth
ica
l stan
d
ar
d
s
an
d
r
eg
u
latio
n
s
.
E
T
H
I
CAL AP
P
RO
V
AL
T
h
is
r
esear
ch
r
ec
eiv
ed
eth
ical
ap
p
r
o
v
al
f
r
o
m
th
e
Ma
k
ass
ar
C
ity
C
iv
il
R
eg
is
tr
atio
n
Of
f
ice
u
n
d
er
th
e
o
f
f
icial
p
er
m
is
s
io
n
n
u
m
b
er
0
0
0
.
9
_
7
3
3
/Dis
d
u
k
ca
p
il/IX/2
0
2
3
.
All
p
r
o
ce
d
u
r
es
in
v
o
lv
in
g
d
ata
co
llectio
n
an
d
an
aly
s
is
wer
e
co
n
d
u
cted
in
ac
co
r
d
an
ce
with
eth
ical
s
tan
d
ar
d
s
an
d
g
u
id
elin
es
to
p
r
o
tect
p
ar
ticip
an
t
co
n
f
id
en
tiality
an
d
en
s
u
r
e
r
es
p
o
n
s
ib
le
u
s
e
o
f
p
e
r
s
o
n
al
in
f
o
r
m
atio
n
.
T
h
e
s
tu
d
y
a
d
h
er
e
d
to
r
elev
an
t
r
eg
u
latio
n
s
an
d
m
ain
tain
e
d
tr
an
s
p
ar
e
n
cy
a
n
d
in
teg
r
ity
th
r
o
u
g
h
o
u
t th
e
r
esear
ch
p
r
o
ce
s
s
.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
ata
s
u
p
p
o
r
tin
g
th
e
f
in
d
in
g
s
o
f
th
is
s
tu
d
y
ar
e
av
a
ilab
le
f
r
o
m
th
e
Po
p
u
latio
n
an
d
C
iv
il
R
eg
is
tr
atio
n
Of
f
ice
o
f
Ma
k
ass
ar
C
ity
.
R
estrictio
n
s
ap
p
ly
to
th
e
av
ailab
ilit
y
o
f
th
is
d
ata,
w
h
ich
is
u
s
ed
u
n
d
er
licen
s
e
f
o
r
th
is
r
esear
ch
.
T
h
e
d
ata
is
n
o
t
p
u
b
licly
av
ailab
le
ex
ce
p
t
with
p
er
m
is
s
io
n
f
r
o
m
th
e
Po
p
u
latio
n
an
d
C
iv
il
R
eg
is
tr
atio
n
Of
f
ice
o
f
Ma
k
ass
ar
C
i
ty
b
ec
au
s
e
it
co
n
tain
s
th
e
p
er
s
o
n
al
d
ata
o
f
I
n
d
o
n
esian
citizen
s
.
Sam
p
le
d
ata
is
av
ailab
le
(
h
ttp
s
://www.
k
ag
g
le.
co
m
/d
atasets
/er
f
an
h
asm
in
/b
ir
t
h
-
an
d
-
d
ea
th
-
d
a
ta
-
s
am
p
le
-
in
-
civ
il
-
r
eg
is
tr
atio
n
)
with
p
er
m
is
s
io
n
to
h
elp
u
n
d
er
s
tan
d
th
e
co
n
tex
t
an
d
d
ata
cr
it
er
ia
u
s
ed
in
th
is
s
tu
d
y
.
RE
F
E
R
E
NC
E
S
[
1
]
A
.
S
.
V
e
n
k
a
t
a
r
a
ma
n
i
,
R
.
O
’
B
r
i
e
n
,
G
.
L.
W
h
i
t
e
h
o
r
n
,
a
n
d
A
.
C
.
T
sai
,
“
Ec
o
n
o
m
i
c
i
n
f
l
u
e
n
c
e
s
o
n
p
o
p
u
l
a
t
i
o
n
h
e
a
l
t
h
i
n
t
h
e
U
n
i
t
e
d
S
t
a
t
e
s:
t
o
w
a
r
d
p
o
l
i
c
y
m
a
k
i
n
g
d
r
i
v
e
n
b
y
d
a
t
a
a
n
d
e
v
i
d
e
n
c
e
,
”
PLo
S
Me
d
i
c
i
n
e
,
v
o
l
.
1
7
,
n
o
.
9
,
2
0
2
0
,
d
o
i
:
1
0
.
1
3
7
1
/
j
o
u
r
n
a
l
.
p
me
d
.
1
0
0
3
3
1
9
.
[
2
]
M
.
F
a
v
a
r
e
t
t
o
,
E
.
D
e
C
l
e
r
c
q
,
a
n
d
B
.
S
.
E
l
g
e
r
,
“
B
i
g
d
a
t
a
a
n
d
d
i
scr
i
mi
n
a
t
i
o
n
:
p
e
r
i
l
s,
p
r
o
mi
s
e
s
a
n
d
s
o
l
u
t
i
o
n
s
.
A
s
y
s
t
e
ma
t
i
c
r
e
v
i
e
w
,
”
J
o
u
rn
a
l
o
f
Bi
g
D
a
t
a
,
v
o
l
.
6
,
n
o
.
1
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
8
6
/
s4
0
5
3
7
-
0
1
9
-
0
1
7
7
-
4.
[
3
]
T.
Y
u
e
t
a
l
.
,
“
M
O
P
O
:
m
o
d
e
l
-
b
a
se
d
o
f
f
l
i
n
e
p
o
l
i
c
y
o
p
t
i
m
i
z
a
t
i
o
n
,
”
A
d
v
a
n
c
e
s
i
n
N
e
u
ra
l
I
n
f
o
rm
a
t
i
o
n
Pr
o
c
e
ssi
n
g
S
y
s
t
e
m
s
,
2
0
2
0
.
[
4
]
M
.
H
.
Te
k
i
e
h
a
n
d
B
.
R
a
a
h
e
m
i
,
“
I
mp
o
r
t
a
n
c
e
o
f
d
a
t
a
m
i
n
i
n
g
i
n
h
e
a
l
t
h
c
a
r
e
:
a
s
u
r
v
e
y
,
”
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
2
0
1
5
I
EEE
/
A
C
M
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
A
d
v
a
n
c
e
s
i
n
S
o
c
i
a
l
N
e
t
w
o
r
k
s
A
n
a
l
y
s
i
s
a
n
d
Mi
n
i
n
g
,
A
S
O
N
A
M
2
0
1
5
,
p
p
.
1
0
5
7
–
1
0
6
2
,
2
0
1
5
,
d
o
i
:
1
0
.
1
1
4
5
/
2
8
0
8
7
9
7
.
2
8
0
9
3
6
7
.
[
5
]
R
.
S
i
l
v
a
,
“
P
o
p
u
l
a
t
i
o
n
p
e
r
sp
e
c
t
i
v
e
s
a
n
d
d
e
mo
g
r
a
p
h
i
c
m
e
t
h
o
d
s
t
o
st
r
e
n
g
t
h
e
n
C
R
V
S
s
y
s
t
e
ms
:
i
n
t
r
o
d
u
c
t
i
o
n
,
”
G
e
n
u
s
,
v
o
l
.
7
8
,
n
o
.
1
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
8
6
/
s4
1
1
1
8
-
0
2
2
-
0
0
1
5
6
-
8.
[
6
]
A
.
V
i
l
o
r
i
a
a
n
d
O
.
B
.
P
.
Le
z
a
ma
,
“
I
mp
r
o
v
e
m
e
n
t
s
f
o
r
d
e
t
e
r
m
i
n
i
n
g
t
h
e
n
u
m
b
e
r
o
f
c
l
u
s
t
e
r
s
i
n
K
-
m
e
a
n
s
f
o
r
i
n
n
o
v
a
t
i
o
n
d
a
t
a
b
a
s
e
s
i
n
S
M
Es,
”
Pr
o
c
e
d
i
a
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
1
5
1
,
p
p
.
1
2
0
1
–
1
2
0
6
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
r
o
c
s.
2
0
1
9
.
0
4
.
1
7
2
.
[
7
]
P
.
Y
.
D
e
sai
,
“
I
mp
l
e
m
e
n
t
a
t
i
o
n
o
f
a
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
a
l
g
o
r
i
t
h
m
o
n
v
e
h
i
c
l
e
r
e
g
i
st
r
a
t
i
o
n
d
a
t
a
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
Ad
v
a
n
c
e
d
Re
s
e
a
r
c
h
i
n
E
n
g
i
n
e
e
ri
n
g
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
1
0
,
n
o
.
1
,
p
p
.
8
3
–
8
7
,
2
0
1
9
,
d
o
i
:
1
0
.
3
4
2
1
8
/
I
JA
R
ET.
1
0
.
1
.
2
0
1
9
.
0
0
8
.
[
8
]
K
.
K
o
n
st
a
s
,
P
.
T.
C
h
o
u
n
t
a
l
a
s,
E.
A
.
D
i
d
a
sk
a
l
o
u
,
a
n
d
D
.
A
.
G
e
o
r
g
a
k
e
l
l
o
s,
“
A
p
r
a
g
mat
i
c
f
r
a
mew
o
r
k
f
o
r
d
a
t
a
-
d
r
i
v
e
n
d
e
c
i
si
o
n
-
mak
i
n
g
p
r
o
c
e
ss
i
n
t
h
e
e
n
e
r
g
y
se
c
t
o
r
:
i
n
si
g
h
t
s
f
r
o
m
a
w
i
n
d
f
a
r
m
c
a
se
st
u
d
y
,
”
E
n
e
r
g
i
e
s
,
v
o
l
.
1
6
,
n
o
.
1
7
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
e
n
1
6
1
7
6
2
7
2
.
[
9
]
S
.
B
h
o
s
a
l
e
,
S
.
P
a
t
a
n
k
a
r
,
K
.
K
a
d
a
m
,
R
.
D
h
e
r
e
,
a
n
d
P
.
M
.
D
e
sa
i
,
“
S
u
r
v
e
y
o
n
c
i
v
i
l
c
o
mp
l
a
i
n
t
s
ma
n
a
g
e
me
n
t
sy
st
e
m
b
y
u
s
i
n
g
mac
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
Ad
v
a
n
c
e
d
R
e
s
e
a
r
c
h
i
n
S
c
i
e
n
c
e
,
C
o
m
m
u
n
i
c
a
t
i
o
n
a
n
d
T
e
c
h
n
o
l
o
g
y
,
p
p
.
6
0
6
–
6
1
0
,
2
0
2
1
,
d
o
i
:
1
0
.
4
8
1
7
5
/
i
j
a
r
sct
-
1
4
4
9
.
[
1
0
]
M
.
A
n
i
t
y
a
s
a
r
i
a
n
d
I
.
D
.
A
.
I
n
d
r
i
a
sar
i
,
“
Te
x
t
m
i
n
i
n
g
i
mp
l
e
m
e
n
t
a
t
i
o
n
i
n
c
o
mp
l
a
i
n
t
ma
n
a
g
e
m
e
n
t
:
a
c
a
se
st
u
d
y
a
t
S
u
r
a
b
a
y
a
C
i
t
y
o
f
f
i
c
e
f
o
r
p
o
p
u
l
a
t
i
o
n
a
d
mi
n
i
s
t
r
a
t
i
o
n
a
n
d
c
i
v
i
l
r
e
g
i
s
t
r
a
t
i
o
n
(
C
O
P
A
C
R
)
,
”
AI
P
C
o
n
f
e
re
n
c
e
Pr
o
c
e
e
d
i
n
g
s
,
v
o
l
.
2
6
9
3
,
n
o
.
1
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
6
3
/
5
.
0
1
2
0
5
7
2
.
[
1
1
]
A
.
F
.
G
e
b
r
e
m
e
d
h
i
n
,
A
.
D
a
w
s
o
n
,
a
n
d
A
.
H
a
y
e
n
,
“
Ev
a
l
u
a
t
i
o
n
s
o
f
e
f
f
e
c
t
i
v
e
c
o
v
e
r
a
g
e
o
f
ma
t
e
r
n
a
l
a
n
d
c
h
i
l
d
h
e
a
l
t
h
s
e
r
v
i
c
e
s:
a
sy
st
e
ma
t
i
c
r
e
v
i
e
w
,
”
H
e
a
l
t
h
Po
l
i
c
y
a
n
d
P
l
a
n
n
i
n
g
,
v
o
l
.
3
7
,
n
o
.
7
,
p
p
.
8
9
5
–
9
1
4
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
9
3
/
h
e
a
p
o
l
/
c
z
a
c
0
3
4
.
[
1
2
]
R
.
G
.
A
b
o
a
g
y
e
,
J.
O
k
y
e
r
e
,
A
.
A
.
S
e
i
d
u
,
B
.
O
.
A
h
i
n
k
o
r
a
h
,
E
.
B
u
d
u
,
a
n
d
S
.
Y
a
y
a
,
“
D
e
t
e
r
mi
n
a
n
t
s
o
f
b
i
r
t
h
r
e
g
i
st
r
a
t
i
o
n
i
n
su
b
-
S
a
h
a
r
a
n
A
f
r
i
c
a
:
e
v
i
d
e
n
c
e
f
r
o
m
d
e
m
o
g
r
a
p
h
i
c
a
n
d
h
e
a
l
t
h
s
u
r
v
e
y
s,”
F
ro
n
t
i
e
rs
i
n
P
u
b
l
i
c
H
e
a
l
t
h
,
v
o
l
.
1
1
,
2
0
2
3
,
do
i
:
1
0
.
3
3
8
9
/
f
p
u
b
h
.
2
0
2
3
.
1
1
9
3
8
1
6
.
[
1
3
]
A
.
D
.
G
h
a
n
i
m
a
n
d
Z.
S
.
Z
u
b
i
,
“
D
a
t
a
mi
n
i
n
g
me
t
h
o
d
s
i
n
m
u
n
i
c
i
p
a
l
i
t
y
s
o
c
i
a
l
d
a
t
a
s
y
st
e
m
(
D
M
S
D
S
)
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
C
o
m
p
u
t
e
rs
,
v
o
l
.
7
,
2
0
2
2
.
[
1
4
]
O
.
O
.
B
a
l
o
g
u
n
e
t
a
l
.
,
“
Ef
f
e
c
t
i
v
e
n
e
ss
o
f
t
h
e
ma
t
e
r
n
a
l
a
n
d
c
h
i
l
d
h
e
a
l
t
h
h
a
n
d
b
o
o
k
f
o
r
i
m
p
r
o
v
i
n
g
c
o
n
t
i
n
u
u
m
o
f
c
a
r
e
a
n
d
o
t
h
e
r
mat
e
r
n
a
l
a
n
d
c
h
i
l
d
h
e
a
l
t
h
i
n
d
i
c
a
t
o
r
s:
A
c
l
u
st
e
r
r
a
n
d
o
m
i
z
e
d
c
o
n
t
r
o
l
l
e
d
t
r
i
a
l
i
n
A
n
g
o
l
a
,
”
J
o
u
r
n
a
l
o
f
G
l
o
b
a
l
H
e
a
l
t
h
,
v
o
l
.
1
3
,
2
0
2
3
,
d
o
i
:
1
0
.
7
1
8
9
/
j
o
g
h
.
1
3
.
0
4
0
2
2
.
[
1
5
]
C
.
Y
u
a
n
a
n
d
H
.
Y
a
n
g
,
“
R
e
se
a
r
c
h
o
n
K
-
v
a
l
u
e
sel
e
c
t
i
o
n
me
t
h
o
d
o
f
K
-
mea
n
s
c
l
u
st
e
r
i
n
g
a
l
g
o
r
i
t
h
m
,
”
J
,
v
o
l
.
2
,
n
o
.
2
,
p
p
.
2
2
6
–
2
3
5
,
2
0
1
9
,
d
o
i
:
1
0
.
3
3
9
0
/
j
2
0
2
0
0
1
6
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
8
1
4
I
n
t J Ad
v
Ap
p
l Sci
,
Vo
l.
14
,
No
.
2
,
J
u
n
e
2
0
2
5
:
5
1
3
-
522
522
[
1
6
]
M
.
V
i
c
h
i
,
C
.
C
a
v
i
c
c
h
i
a
,
a
n
d
P
.
J.
F
.
G
r
o
e
n
e
n
,
“
H
i
e
r
a
r
c
h
i
c
a
l
mea
n
s
c
l
u
st
e
r
i
n
g
,
”
J
o
u
r
n
a
l
o
f
C
l
a
ssi
f
i
c
a
t
i
o
n
,
v
o
l
.
3
9
,
n
o
.
3
,
p
p
.
5
5
3
–
5
7
7
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s
0
0
3
5
7
-
0
2
2
-
0
9
4
1
9
-
7.
[
1
7
]
M
.
A
n
n
a
s
a
n
d
S
.
N
.
W
a
h
a
b
,
“
D
a
t
a
mi
n
i
n
g
m
e
t
h
o
d
s
:
K
-
m
e
a
n
s
c
l
u
s
t
e
r
i
n
g
a
l
g
o
r
i
t
h
ms,”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
C
y
b
e
r
a
n
d
I
T
S
e
r
v
i
c
e
Ma
n
a
g
e
m
e
n
t
,
v
o
l
.
3
,
n
o
.
1
,
p
p
.
4
0
–
4
7
,
M
a
r
.
2
0
2
3
,
d
o
i
:
1
0
.
3
4
3
0
6
/
i
j
c
i
t
sm.
v
3
i
1
.
1
2
2
.
[
1
8
]
J.
H
ä
mäl
ä
i
n
e
n
,
T
.
K
ä
r
k
k
ä
i
n
e
n
,
a
n
d
T.
R
o
ssi
,
“
I
mp
r
o
v
i
n
g
sc
a
l
a
b
l
e
K
-
me
a
n
s
+
+
,
”
Al
g
o
ri
t
h
m
s
,
v
o
l
.
1
4
,
n
o
.
1
,
p
p
.
1
–
2
0
,
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
a
1
4
0
1
0
0
0
6
.
[
1
9
]
T.
M
.
G
h
a
z
a
l
e
t
a
l
.
,
“
P
e
r
f
o
r
m
a
n
c
e
s
o
f
K
-
mea
n
s
c
l
u
st
e
r
i
n
g
a
l
g
o
r
i
t
h
m
w
i
t
h
d
i
f
f
e
r
e
n
t
d
i
st
a
n
c
e
m
e
t
r
i
c
s,
”
I
n
t
e
l
l
i
g
e
n
t
Au
t
o
m
a
t
i
o
n
a
n
d
S
o
f
t
C
o
m
p
u
t
i
n
g
,
v
o
l
.
3
0
,
n
o
.
2
,
p
p
.
7
3
5
–
7
4
2
,
2
0
2
1
,
d
o
i
:
1
0
.
3
2
6
0
4
/
i
a
s
c
.
2
0
2
1
.
0
1
9
0
6
7
.
[
2
0
]
A
.
M
.
Ja
b
b
a
r
,
K
.
R
.
K
u
-
M
a
h
a
m
u
d
,
a
n
d
R
.
S
a
g
b
a
n
,
“
A
n
i
mp
r
o
v
e
d
A
C
S
a
l
g
o
r
i
t
h
m
f
o
r
d
a
t
a
c
l
u
s
t
e
r
i
n
g
,
”
I
n
d
o
n
e
si
a
n
J
o
u
rn
a
l
o
f
El
e
c
t
r
i
c
a
l
En
g
i
n
e
e
r
i
n
g
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
1
7
,
n
o
.
3
,
p
p
.
1
5
0
6
–
1
5
1
5
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s.
v
1
7
.
i
3
.
p
p
1
5
0
6
-
1
5
1
5
.
[
2
1
]
D
.
J
o
l
l
y
t
a
,
S
.
Ef
e
n
d
i
,
M
.
Za
r
l
i
s,
a
n
d
H
.
M
a
w
e
n
g
k
a
n
g
,
“
A
n
a
l
y
si
s
o
f
a
n
o
p
t
i
ma
l
c
l
u
s
t
e
r
a
p
p
r
o
a
c
h
:
a
r
e
v
i
e
w
p
a
p
e
r
,
”
J
o
u
r
n
a
l
o
f
Ph
y
s
i
c
s:
C
o
n
f
e
r
e
n
c
e
S
e
ri
e
s
,
v
o
l
.
2
4
2
1
,
n
o
.
1
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
8
8
/
1
7
4
2
-
6
5
9
6
/
2
4
2
1
/
1
/
0
1
2
0
1
5
.
[
2
2
]
M
.
A
.
S
y
a
k
u
r
,
B
.
K
.
K
h
o
t
i
m
a
h
,
E.
M
.
S
.
R
o
c
h
m
a
n
,
a
n
d
B
.
D
.
S
a
t
o
t
o
,
“
I
n
t
e
g
r
a
t
i
o
n
K
-
m
e
a
n
s
c
l
u
st
e
r
i
n
g
m
e
t
h
o
d
a
n
d
e
l
b
o
w
me
t
h
o
d
f
o
r
i
d
e
n
t
i
f
i
c
a
t
i
o
n
o
f
t
h
e
b
e
st
c
u
s
t
o
mer
p
r
o
f
i
l
e
c
l
u
s
t
e
r
,
”
I
O
P
C
o
n
f
e
r
e
n
c
e
S
e
ri
e
s:
Ma
t
e
r
i
a
l
s
S
c
i
e
n
c
e
a
n
d
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
3
3
6
,
n
o
.
1
,
2
0
1
8
,
d
o
i
:
1
0
.
1
0
8
8
/
1
7
5
7
-
8
9
9
X
/
3
3
6
/
1
/
0
1
2
0
1
7
.
[
2
3
]
F
.
W
a
n
g
,
J.
C
h
e
n
,
a
n
d
F
.
Li
u
,
“
K
e
y
f
r
a
me
g
e
n
e
r
a
t
i
o
n
me
t
h
o
d
v
i
a
i
m
p
r
o
v
e
d
c
l
u
st
e
r
i
n
g
a
n
d
si
l
h
o
u
e
t
t
e
c
o
e
f
f
i
c
i
e
n
t
f
o
r
v
i
d
e
o
su
mm
a
r
i
z
a
t
i
o
n
,
”
J
o
u
rn
a
l
o
f
We
b
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
2
0
,
n
o
.
1
,
p
p
.
1
4
7
–
1
7
0
,
2
0
2
1
,
d
o
i
:
1
0
.
1
3
0
5
2
/
j
w
e
1
5
4
0
-
9
5
8
9
.
2
0
1
8
.
[
2
4
]
K
.
R
.
S
h
a
h
a
p
u
r
e
a
n
d
C
.
N
i
c
h
o
l
a
s,
“
C
l
u
st
e
r
q
u
a
l
i
t
y
a
n
a
l
y
si
s
u
si
n
g
si
l
h
o
u
e
t
t
e
s
c
o
r
e
,
”
Pr
o
c
e
e
d
i
n
g
s
-
2
0
2
0
I
EEE
7
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
D
a
t
a
S
c
i
e
n
c
e
a
n
d
A
d
v
a
n
c
e
d
A
n
a
l
y
t
i
c
s,
D
S
A
A
2
0
2
0
,
p
p
.
7
4
7
–
7
4
8
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
D
S
A
A
4
9
0
1
1
.
2
0
2
0
.
0
0
0
9
6
.
[
2
5
]
R
.
C
.
C
h
e
n
,
C
.
D
e
w
i
,
S
.
W
.
H
u
a
n
g
,
a
n
d
R
.
E
.
C
a
r
a
k
a
,
“
S
e
l
e
c
t
i
n
g
c
r
i
t
i
c
a
l
f
e
a
t
u
r
e
s fo
r
d
a
t
a
c
l
a
ss
i
f
i
c
a
t
i
o
n
b
a
s
e
d
o
n
mac
h
i
n
e
l
e
a
r
n
i
n
g
met
h
o
d
s,
”
J
o
u
r
n
a
l
o
f
Bi
g
D
a
t
a
,
v
o
l
.
7
,
n
o
.
1
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
8
6
/
s4
0
5
3
7
-
0
2
0
-
0
0
3
2
7
-
4.
[
2
6
]
S
.
M
.
B
h
a
g
a
v
a
t
h
i
e
t
a
l
.
,
“
W
e
a
t
h
e
r
f
o
r
e
c
a
st
i
n
g
a
n
d
p
r
e
d
i
c
t
i
o
n
u
si
n
g
h
y
b
r
i
d
C
5
.
0
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
m,”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
C
o
m
m
u
n
i
c
a
t
i
o
n
S
y
st
e
m
s
,
v
o
l
.
3
4
,
n
o
.
1
0
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
0
2
/
d
a
c
.
4
8
0
5
.
[
2
7
]
K
.
R
a
h
u
l
a
n
d
R
.
K
.
B
a
n
y
a
l
,
“
D
e
t
e
c
t
i
o
n
a
n
d
c
o
r
r
e
c
t
i
o
n
o
f
a
b
n
o
r
ma
l
d
a
t
a
w
i
t
h
o
p
t
i
m
i
z
e
d
d
i
r
t
y
d
a
t
a
:
a
n
e
w
d
a
t
a
c
l
e
a
n
i
n
g
mo
d
e
l
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
a
n
d
D
e
c
i
si
o
n
Ma
k
i
n
g
,
v
o
l
.
2
0
,
n
o
.
2
,
p
p
.
8
0
9
–
8
4
1
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
4
2
/
S
0
2
1
9
6
2
2
0
2
1
5
0
0
1
8
8
.
[
2
8
]
M
.
C
h
a
u
d
h
r
y
,
I
.
S
h
a
f
i
,
M
.
M
a
h
n
o
o
r
,
D
.
L.
R
.
V
a
r
g
a
s,
E
.
B
.
T
h
o
mp
s
o
n
,
a
n
d
I
.
A
s
h
r
a
f
,
“
A
sy
s
t
e
mat
i
c
l
i
t
e
r
a
t
u
r
e
r
e
v
i
e
w
o
n
i
d
e
n
t
i
f
y
i
n
g
p
a
t
t
e
r
n
s
u
si
n
g
u
n
s
u
p
e
r
v
i
sed
c
l
u
s
t
e
r
i
n
g
a
l
g
o
r
i
t
h
ms:
a
d
a
t
a
m
i
n
i
n
g
p
e
r
s
p
e
c
t
i
v
e
,
”
S
y
m
m
e
t
r
y
,
v
o
l
.
1
5
,
n
o
.
9
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
s
y
m
1
5
0
9
1
6
7
9
.
[
2
9
]
M
.
Z.
R
o
d
r
i
g
u
e
z
e
t
a
l
.
,
“
C
l
u
s
t
e
r
i
n
g
a
l
g
o
r
i
t
h
ms:
a
c
o
m
p
a
r
a
t
i
v
e
a
p
p
r
o
a
c
h
,
”
PL
o
S
O
N
E
,
v
o
l
.
1
4
,
n
o
.
1
,
2
0
1
9
,
d
o
i
:
1
0
.
1
3
7
1
/
j
o
u
r
n
a
l
.
p
o
n
e
.
0
2
1
0
2
3
6
.
[
3
0
]
J.
P
e
r
e
i
r
a
,
P
.
C
o
n
t
r
e
r
a
s,
D
.
C
.
M
o
r
a
i
s,
a
n
d
P
.
A
r
r
o
y
o
-
Ló
p
e
z
,
“
M
u
l
t
i
-
c
r
i
t
e
r
i
a
o
r
d
e
r
e
d
c
l
u
s
t
e
r
i
n
g
o
f
c
o
u
n
t
r
i
e
s
i
n
t
h
e
g
l
o
b
a
l
h
e
a
l
t
h
sec
u
r
i
t
y
i
n
d
e
x
,
”
S
o
c
i
o
-
E
c
o
n
o
m
i
c
Pl
a
n
n
i
n
g
S
c
i
e
n
c
e
s
,
v
o
l
.
8
4
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
s
e
p
s
.
2
0
2
2
.
1
0
1
3
3
1
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Er
fa
n
H
a
sm
in
is
a
lec
tu
re
r
in
th
e
De
p
a
rtme
n
t
o
f
I
n
fo
rm
a
ti
c
s,
a
t
Dip
a
M
a
k
a
ss
a
r
Un
iv
e
rsity
,
M
a
k
a
ss
a
r,
In
d
o
n
e
sia
.
Erf
a
n
d
o
e
s
re
se
a
rc
h
in
d
e
c
isio
n
su
p
p
o
rt
sy
ste
m
s
a
n
d
d
a
ta
m
in
in
g
.
Ha
v
e
e
x
p
e
rti
se
in
so
f
twa
re
d
e
v
e
lo
p
m
e
n
t
a
n
d
a
p
p
li
c
a
ti
o
n
o
f
m
a
th
e
m
a
ti
c
a
l
m
e
th
o
d
s
t
o
p
ro
g
ra
m
m
in
g
.
H
e
c
a
n
b
e
c
o
n
tac
te
d
v
ia em
a
il
:
e
rfa
n
.
h
a
sm
in
@u
n
d
i
p
a
.
a
c
.
id
.
Ae
d
a
h
Abd
Ra
h
m
a
n
is
a
P
ro
fe
so
r
in
S
c
h
o
o
l
o
f
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
As
ia
e
Un
iv
e
rsity
,
Ku
a
la
Lu
m
p
u
r,
M
a
lay
sia
.
Ha
v
e
e
x
p
e
rti
se
in
d
a
ta
m
in
i
n
g
a
n
d
so
ftwa
re
e
n
g
i
n
e
e
rin
g
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
a
e
d
a
h
.
a
b
d
ra
h
m
a
n
@a
e
u
.
e
d
u
.
m
y
.
Evaluation Warning : The document was created with Spire.PDF for Python.