I
n
t
e
r
n
at
ion
al
Jou
r
n
a
l
of
I
n
f
o
r
m
at
ics
an
d
Com
m
u
n
icat
ion
T
e
c
h
n
ol
ogy
(
I
J
-
I
CT
)
Vo
l
.
15
,
N
o
.
2
,
J
un
e
20
26
,
pp.
523
~
534
I
S
S
N:
2252
-
8776
,
DO
I
:
10
.
11591/i
ji
c
t
.
v
15
i
2
.
pp
52
3
-
534
523
Jou
r
n
al
h
o
m
e
page
:
ht
tp:
//
ij
ict
.
iaes
c
or
e
.
c
om
E
n
h
a
n
c
in
g s
u
p
p
or
t
ve
c
t
or
m
a
c
h
in
e
p
e
r
f
or
m
an
c
e
u
si
n
g
p
ar
t
ic
le
sw
a
r
m
o
p
t
i
m
i
z
at
io
n
f
or
se
n
t
im
e
n
t
an
al
y
si
s
Chr
is
t
o
f
e
r
S
at
r
ia
1
,
Ant
h
on
y
Anggr
awan
2
,
P
e
t
e
r
Wij
aya
S
u
gi
j
an
t
o
3
,
Hu
s
ain
Hu
s
ain
2
,
I
Nyom
an
Yoga
S
u
m
ad
e
wa
1
,
Vic
t
or
ia
Cynt
h
ia
Re
b
e
c
c
a
3
1
D
e
pa
r
tm
e
nt
of
V
is
u
a
l
C
o
mm
uni
c
a
ti
o
n D
e
s
ig
n
,
F
a
c
ul
t
y
of
A
r
t
a
nd D
e
s
ig
n
,
B
umi
g
o
r
a
U
ni
ve
r
s
it
y
, M
a
ta
r
a
m, I
nd
o
ne
s
ia
2
D
e
pa
r
tm
e
nt
of
C
o
mpu
te
r
S
c
ie
n
c
e
,
F
a
c
ul
t
y
of
E
ngi
n
e
e
r
in
g
,
B
u
mi
gor
a
U
ni
ve
r
s
it
y
, M
a
ta
r
a
m, I
nd
o
n
e
s
ia
3
D
e
pa
r
tm
e
nt
of
M
e
di
c
a
l,
F
a
c
u
lt
y
of
M
e
di
c
i
al
a
nd
H
e
a
lt
h S
c
ie
n
c
e
s
, B
u
mi
g
or
a
U
ni
ve
r
s
it
y
, M
a
ta
r
a
m, I
nd
o
n
e
s
ia
Ar
t
ic
l
e
I
n
f
o
AB
S
T
RA
CT
A
r
ti
c
le
h
is
tor
y
:
R
e
c
e
i
ve
d
J
u
l
9
,
2025
R
e
vi
s
e
d
De
c
24
,
2025
A
c
c
e
pt
e
d
M
a
r
30
,
2026
Rece
n
t
l
y
,
s
o
ci
al
me
d
i
a
h
as
e
s
t
ab
l
i
s
h
ed
i
t
s
e
l
f
as
a
l
e
ad
i
n
g
p
l
at
fo
rm
i
n
v
ari
o
u
s
s
e
c
t
o
rs
.
M
e
an
w
h
i
l
e
,
t
e
x
t
e
x
t
ra
c
t
i
o
n
an
d
s
en
t
i
me
n
t
a
n
al
y
s
i
s
cl
as
s
i
fi
c
at
i
o
n
h
av
e
at
t
rac
t
e
d
s
i
g
n
i
fi
c
a
n
t
at
t
e
n
t
i
o
n
i
n
r
e
s
e
ar
c
h
.
R
eg
re
t
t
ab
l
y
,
t
rad
i
t
i
o
n
a
l
s
e
n
t
i
me
n
t
a
n
al
y
s
i
s
o
ft
e
n
fa
l
l
s
s
h
o
rt
o
f
accu
rat
el
y
c
ap
t
u
ri
n
g
s
e
n
t
i
men
t
n
u
an
ce
s
.
A
t
t
h
e
s
a
me
t
i
me
,
m
a
ch
i
n
e
l
e
ar
n
i
n
g
h
as
en
a
b
l
e
d
m
o
r
e
e
ff
ec
t
i
v
e
s
e
n
t
i
me
n
t
an
a
l
y
s
i
s
,
d
at
a
mi
n
i
n
g
,
an
d
c
l
as
s
i
fi
c
at
i
o
n
,
as
w
e
l
l
as
t
h
e
d
ev
e
l
o
p
men
t
o
f
mo
d
el
s
t
h
at
i
n
c
o
rp
o
rat
e
art
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
en
ce
.
T
h
e
r
e
fo
r
e
,
t
h
e
p
u
rp
o
s
e
o
f
t
h
i
s
s
t
u
d
y
i
s
t
o
o
p
t
i
m
i
z
e
s
e
n
t
i
men
t
an
a
l
y
s
i
s
o
f
p
u
b
l
i
c
o
p
i
n
i
o
n
i
n
s
o
c
i
a
l
me
d
i
a
r
e
g
ar
d
i
n
g
G
ran
d
Pri
x
mo
t
o
rcy
cl
e
ra
ci
n
g
(
Mo
t
o
G
P)
an
d
W
o
r
l
d
Su
p
e
rb
i
k
e
(
W
SB
K
)
ev
e
n
t
s
u
s
i
n
g
m
a
c
h
i
n
e
l
e
arn
i
n
g
an
d
an
o
p
t
i
mi
z
e
d
m
a
c
h
i
n
e
l
e
ar
n
i
n
g
me
t
h
o
d
.
T
h
i
s
s
t
u
d
y
ap
p
l
i
e
s
t
h
e
s
u
p
p
o
rt
v
ec
t
o
r
m
a
c
h
i
n
e
(SV
M)
m
a
c
h
i
n
e
l
e
ar
n
i
n
g
me
t
h
o
d
a
n
d
e
n
h
an
ce
s
i
t
s
p
e
rfo
r
m
a
n
ce
t
h
r
o
u
g
h
o
p
t
i
mi
zat
i
o
n
b
y
i
n
t
eg
rat
i
n
g
i
t
w
i
t
h
t
h
e
p
art
i
c
l
e
s
w
ar
m
o
p
t
i
m
i
zat
i
o
n
(PSO
)
al
g
o
r
i
t
h
m
.
T
h
i
s
s
t
u
d
y
fo
u
n
d
t
h
at
t
h
e
SV
M
me
t
h
o
d
a
ch
i
ev
e
d
8
0
.
1
5
%
acc
u
ra
cy
,
7
5
.
6
3
%
re
c
a
l
l
,
an
d
7
6
.
8
9
%
F1
-
s
c
o
re
.
In
co
n
t
r
as
t
,
t
h
e
SV
M
me
t
h
o
d
c
o
m
b
i
n
e
d
w
i
t
h
PSO
a
c
h
i
e
v
e
s
a
c
cu
ra
c
i
e
s
o
f
8
1
.
8
2
%
,
7
9
.
9
%
,
an
d
7
9
.
6
2
%
fo
r
rec
al
l
,
p
reci
s
i
o
n
,
a
n
d
F1
-
s
c
o
r
e,
r
e
s
p
e
c
t
i
v
e
l
y
,
i
n
c
l
as
s
i
f
y
i
n
g
t
h
e
s
e
n
t
i
men
t
o
f
s
p
o
rt
i
n
g
ev
e
n
t
s
.
T
h
e
i
m
p
l
i
c
at
i
o
n
s
s
u
g
g
e
s
t
t
h
at
ap
p
l
y
i
n
g
H
y
b
ri
d
S
V
M
w
i
t
h
PSO
s
i
g
n
i
f
i
c
an
t
l
y
e
n
h
an
ce
s
cl
as
s
i
fi
c
at
i
o
n
a
cc
u
ra
cy
i
n
s
en
t
i
m
en
t
an
a
l
y
s
i
s
.
K
e
y
w
o
r
d
s
:
Da
t
a
m
i
n
i
ng
M
a
c
hi
ne
l
e
a
r
ni
ng
P
a
r
t
i
c
l
e
s
wa
r
m
S
e
n
t
i
m
e
n
t
a
n
a
ly
s
i
s
S
o
c
i
a
l
m
e
d
i
a
S
VM
Th
i
s
i
s
a
n
o
p
en
a
c
ces
s
a
r
t
i
c
l
e
u
n
d
e
r
t
h
e
CC
B
Y
-
SA
l
i
cen
s
e.
C
or
r
e
s
pon
din
g
A
u
th
or
:
C
h
r
i
s
t
o
f
e
r
S
a
t
r
i
a
De
pa
r
t
m
e
n
t
o
f
V
i
s
ua
l
C
o
m
m
u
ni
c
a
t
i
o
n
De
s
i
g
n
,
F
a
c
u
l
t
y
o
f
A
r
t
a
n
d
De
s
i
g
n
,
B
u
m
i
go
r
a
Uni
ve
r
s
i
t
y
M
a
t
a
r
a
m
,
I
n
do
n
e
s
i
a
E
m
a
i
l
:
c
h
r
i
s
87
@
u
ni
ve
r
s
i
t
a
s
b
u
m
i
go
r
a
.
a
c
.
i
d
1.
I
NT
RODU
C
T
I
ON
I
n
r
e
c
e
n
t
e
r
a
s
,
n
u
m
e
r
o
us
us
e
r
s
h
a
ve
t
ur
n
e
d
to
s
o
c
i
a
l
m
e
d
i
a
t
o
s
h
a
r
e
t
h
e
i
r
t
h
o
ugh
t
s
a
n
d
e
x
pr
e
s
s
t
h
e
i
r
o
pi
ni
o
n
s
[
1]
,
[
2
]
.
S
o
c
i
a
l
m
e
d
i
a
ha
s
e
s
t
a
bli
s
h
e
d
i
t
s
e
l
f
a
s
a
d
o
m
i
na
n
t
publ
i
c
us
e
r
-
ge
ne
r
a
t
e
d
m
e
d
i
a
p
l
a
t
f
o
r
m
a
c
r
o
s
s
v
a
r
i
o
us
f
i
e
l
ds
[
3]
,
i
nc
l
ud
i
n
g
t
o
u
r
i
s
m
[
4]
.
I
n
e
s
s
e
n
c
e
,
publi
c
o
pi
ni
o
n
da
t
a
s
e
t
s
o
n
s
o
c
i
a
l
m
e
d
i
a
pr
o
vi
de
v
a
l
ua
bl
e
i
ns
i
g
h
t
s
i
n
t
o
us
e
r
s
’
s
e
n
t
i
m
e
n
t
s
t
h
r
o
u
gh
s
e
n
t
i
m
e
n
t
a
n
a
l
y
s
i
s
[
5]
.
S
e
n
t
i
m
e
n
t
a
n
a
ly
s
i
s
i
s
t
h
e
c
l
a
s
s
if
i
c
a
t
i
o
n
o
f
t
h
e
po
l
a
r
i
t
y
o
f
e
m
o
t
i
o
n
s
,
a
tt
i
t
ude
s
,
o
r
publ
i
c
o
pi
ni
o
ns
[
6]
–
[
8]
r
e
ga
r
di
n
g
a
n
o
bj
e
c
t
o
r
s
ubj
e
c
t
[
7]
,
whi
c
h
c
l
a
s
s
if
i
e
s
t
h
e
o
bj
e
c
t
i
n
to
p
o
s
i
t
i
v
e
,
n
e
ga
t
i
v
e
,
a
n
d
n
e
ut
r
a
l
s
e
n
t
i
m
e
n
t
c
a
t
e
g
o
r
i
e
s
[
8]
.
S
e
n
t
i
m
e
n
t
a
n
a
ly
s
i
s
h
a
s
r
e
c
e
i
ve
d
c
o
ns
i
de
r
a
bl
e
a
t
t
e
n
t
i
o
n
i
n
r
e
s
e
a
r
c
h
f
o
r
e
x
t
r
a
c
t
i
n
g
a
n
d
c
l
a
s
s
i
f
yi
ng
s
e
n
t
i
m
e
n
t
po
l
a
r
it
i
e
s
[
7]
.
I
n
s
h
o
r
t,
t
h
e
pr
i
m
a
r
y
b
e
n
e
f
i
t
o
f
s
e
n
t
i
m
e
n
t
a
n
a
l
y
s
is
i
s
to
de
t
e
r
m
i
ne
publi
c
r
e
a
c
t
i
o
n
s
a
n
d
o
pi
ni
o
ns
to
wa
r
d
a
n
e
w
s
i
s
s
ue
[
9]
–
[
11]
,
a
n
d
t
h
e
r
e
s
u
l
t
s
pr
o
vi
de
a
s
t
r
o
n
g
b
a
s
i
s
f
o
r
m
a
k
i
ng
m
o
r
e
a
c
c
ur
a
t
e
a
n
d
pr
e
c
i
s
e
de
c
i
s
i
o
n
s
[
12]
.
Unf
o
r
t
un
a
t
e
l
y
,
t
r
a
di
t
i
o
n
a
l
s
e
n
t
i
m
e
n
t
a
n
a
ly
s
is
o
f
t
e
n
s
t
r
uggl
e
s
to
e
x
tr
a
c
t
s
e
n
t
i
m
e
n
t
a
c
c
ur
a
t
e
l
y
[
4]
.
A
s
a
c
o
n
s
e
que
n
c
e
,
s
e
n
t
i
m
e
n
t
a
n
a
ly
s
i
s
r
e
qu
i
r
e
s
a
c
o
m
p
l
e
x
c
l
a
s
s
i
f
i
c
a
t
i
o
n
m
o
de
l
[
7]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8776
I
n
t
J
I
n
f
&
C
o
m
m
u
n
T
e
c
hn
o
l
,
Vo
l
.
15
,
N
o.
2
,
J
un
e
20
26
:
523
-
534
524
I
n
t
h
e
m
e
a
n
t
i
m
e
,
a
dv
a
n
c
e
s
i
n
m
a
c
hi
ne
l
e
a
r
ni
ng
h
a
v
e
e
n
a
bl
e
d
t
h
e
pe
r
f
o
r
m
a
n
c
e
o
f
s
e
n
t
i
m
e
n
t
a
n
a
ly
s
is
o
n
l
a
r
ge
da
t
a
s
e
t
s
,
y
i
e
l
d
i
ng
m
o
r
e
e
f
f
e
c
t
i
v
e
r
e
s
u
l
t
s
[
13]
.
M
a
c
hi
ne
l
e
a
r
ni
ng
i
s
a
v
a
l
ua
bl
e
t
oo
l
f
o
r
c
l
a
s
s
if
yi
ng
o
r
pr
e
d
i
c
t
i
n
g
c
l
a
s
s
m
e
m
be
r
s
hi
p,
a
n
d
i
t
p
l
a
y
s
a
s
i
g
ni
f
ica
n
t
r
o
l
e
i
n
da
t
a
m
i
n
i
ng
[
14]
.
M
o
r
e
o
v
e
r
,
m
a
c
hi
ne
l
e
a
r
ni
ng
m
e
t
h
o
ds
c
a
n
pe
r
f
o
r
m
s
e
n
t
i
m
e
n
t
a
n
a
ly
s
i
s
o
n
c
o
m
p
l
e
x
c
l
a
s
s
if
i
c
a
t
i
o
n
m
o
de
l
s
[
7]
.
I
t
a
l
s
o
s
e
r
v
e
s
a
s
a
n
e
f
f
e
c
t
i
v
e
a
n
d
a
c
c
ur
a
t
e
m
e
t
h
o
d
f
o
r
b
u
il
d
i
n
g
m
o
de
l
s
o
r
s
y
s
t
e
m
s
w
i
t
h
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
li
ge
nc
e
[
14]
.
I
n
s
h
o
r
t
,
t
h
e
n
e
e
d
t
o
a
pp
l
y
c
o
m
p
l
e
x
m
o
de
l
s
f
o
r
s
e
n
t
i
m
e
n
t
a
n
a
ly
s
i
s
o
r
to
di
s
t
i
n
gu
i
s
h
c
l
a
s
s
e
s
o
r
o
pi
ni
o
n
l
a
b
e
l
s
i
n
t
e
x
t
ua
l
doc
u
m
e
n
t
s
l
e
a
d
s
to
t
h
e
us
e
o
f
m
a
c
hi
ne
l
e
a
r
ni
ng
m
e
t
h
o
ds
[
6]
.
M
a
c
hi
ne
l
e
a
r
ni
ng
i
s
i
n
c
r
e
a
s
i
ng
ly
r
e
c
o
gni
z
e
d
a
s
a
v
a
l
ua
ble
too
l
f
o
r
da
t
a
m
i
n
i
ng,
e
n
a
bl
i
ng
hi
g
h
-
a
c
c
ur
a
c
y
c
l
a
s
s
if
i
c
a
t
i
o
n
o
f
da
t
a
s
e
t
s
[
15
]
,
[
16
]
.
T
h
a
t
i
s
why
t
hi
s
s
tud
y
a
i
ms
to
o
p
t
i
mi
z
e
s
e
n
t
i
m
e
n
t
a
n
a
ly
s
i
s
o
n
publi
c
o
pi
ni
o
n
us
i
n
g
t
h
e
s
uppo
r
t
v
e
c
to
r
m
a
c
hi
ne
(
S
VM
)
m
a
c
hi
ne
l
e
a
r
ni
ng
m
e
t
h
o
d
a
n
d
t
h
e
S
VM
o
p
t
i
m
i
z
e
d
w
i
t
h
t
h
e
pa
r
t
i
c
l
e
s
wa
r
m
o
p
t
i
mi
z
a
t
i
o
n
(
PSO
)
m
e
t
h
o
d.
S
VM
i
s
a
s
upe
r
vi
s
e
d
m
a
c
hi
ne
l
e
a
r
ni
n
g
[
8]
.
S
VM
i
s
a
m
a
c
hi
ne
l
e
a
r
ni
ng
m
e
t
h
o
d
f
o
r
c
l
a
s
s
i
f
yi
ng
o
r
c
a
t
e
g
o
r
i
z
i
ng
da
t
a
[
17]
.
T
h
e
S
VM
i
s
a
w
i
de
ly
us
e
d
m
a
c
hi
ne
l
e
a
r
ni
ng
t
e
c
hni
qu
e
a
pp
l
i
e
d
i
n
v
a
r
i
o
us
f
i
e
l
ds
o
f
s
c
i
e
n
t
i
f
i
c
r
e
s
e
a
r
c
h
[
18]
.
T
h
e
S
VM
m
a
c
hi
ne
l
e
a
r
ni
n
g
m
e
t
h
o
d
h
a
s
n
u
m
e
r
o
us
a
pp
l
i
c
a
t
i
o
ns
i
n
c
l
a
s
s
i
f
yi
ng
da
t
a
s
e
t
s
[
19]
a
n
d
i
s
we
l
l
k
n
o
wn
a
s
a
c
l
a
s
s
i
f
i
c
a
t
i
o
n
m
e
t
h
o
d
[
19]
.
T
h
e
S
VM
i
s
a
n
a
d
v
a
n
c
e
d
a
l
go
r
i
t
hm
k
n
o
wn
f
o
r
i
t
s
hi
g
h
pr
e
d
i
c
t
i
o
n
a
c
c
ur
a
c
y
[
20]
.
T
h
e
S
VM
c
o
n
s
t
i
t
utes
t
h
e
m
o
s
t
p
o
pul
a
r
l
y
us
e
d
m
a
c
hi
ne
l
e
a
r
ni
ng
a
l
go
r
i
t
hm
f
o
r
s
e
n
t
i
m
e
n
t
a
n
a
ly
s
i
s
[
8]
.
I
n
t
h
e
m
e
a
n
t
i
m
e
,
s
po
r
t
i
n
g
e
v
e
n
t
s
h
a
v
e
b
e
c
o
m
e
a
r
a
p
i
d
ly
gr
o
w
i
n
g
tr
e
n
d,
a
s
t
h
e
y
ha
v
e
a
po
s
i
t
i
v
e
im
pa
c
t
o
n
s
o
c
i
e
t
a
l
e
c
o
n
o
m
i
c
gr
o
w
t
h
[
21]
.
S
p
o
r
t
i
n
g
e
ve
n
t
s
n
ot
o
nl
y
s
e
r
v
e
a
s
e
v
e
n
t
s
b
ut
a
l
s
o
c
o
n
t
r
i
b
ut
e
to
I
n
do
n
e
s
i
a
’
s
to
u
r
i
s
m
[
21]
.
T
h
e
s
e
e
v
e
n
t
s
m
a
y
b
e
w
hy
r
e
s
e
a
r
c
h
o
n
s
uppo
r
t
e
v
e
n
t
s
h
a
s
ga
r
n
e
r
e
d
s
i
g
nif
i
c
a
n
t
a
tt
e
n
t
i
o
n
[
22]
,
[
23
]
.
Unf
o
r
t
un
a
t
e
l
y
,
r
e
s
e
a
r
c
h
o
n
s
po
r
t
i
n
g
e
v
e
n
t
s
i
s
s
t
i
ll
li
mi
t
e
d
[
24]
.
I
n
t
h
e
m
e
a
n
t
i
m
e
,
pr
e
vi
o
us
r
e
s
e
a
r
c
h
[
25]
i
n
d
i
c
a
t
e
s
t
h
a
t
us
i
ng
m
i
xe
d
m
e
t
h
o
ds
c
a
n
e
nh
a
n
c
e
pe
r
f
o
r
m
a
n
c
e
.
T
h
a
t
i
s
why
t
hi
s
pa
pe
r
a
i
m
s
t
o
pe
r
f
o
r
m
s
e
n
t
i
m
e
n
t
a
n
a
ly
s
i
s
o
f
publi
c
o
pi
ni
o
n
o
n
s
po
r
t
s
e
v
e
n
t
s
us
i
n
g
t
h
e
S
VM
m
e
t
h
o
d
a
n
d
a
n
S
VM
o
p
t
i
mi
z
e
d
w
i
t
h
t
h
e
P
S
O
a
l
go
r
i
t
hm
.
T
a
bl
e
1
c
o
m
pa
r
e
s
o
u
r
w
o
r
k
wi
t
h
pr
e
vi
o
us
r
e
l
a
t
e
d
s
t
udi
e
s
.
Al
t
h
o
ugh
e
a
r
l
i
e
r
r
e
s
e
a
r
c
h
i
n
c
l
ude
s
v
a
r
i
o
us
s
t
udi
e
s
o
n
s
e
n
t
i
m
e
n
t
a
n
a
ly
s
i
s
a
n
d
m
e
t
h
o
d
o
l
o
g
i
c
a
l
a
ppr
o
a
c
h
e
s
,
o
u
r
s
t
udy
d
i
f
f
e
r
s
a
n
d
i
s
n
o
t
a
dupl
i
c
a
t
i
o
n
o
r
a
c
a
s
e
o
f
p
l
a
g
i
a
r
i
s
m
o
f
e
xi
s
t
i
n
g
wo
r
k.
Our
s
t
udy
d
if
f
e
r
s
f
r
o
m
pr
e
vi
o
u
s
s
t
udi
e
s
[
6]
,
[
8]
,
[
12]
,
[
21]
,
[
26]
–
[
34]
(
s
e
e
T
a
bl
e
1)
.
A
c
o
m
pa
r
i
s
o
n
o
f
t
hi
s
r
e
s
e
a
r
c
h
w
i
t
h
r
e
l
a
t
e
d
pr
e
vi
o
us
s
t
udi
e
s
r
e
v
e
a
l
s
n
o
t
a
bl
e
d
i
f
f
e
r
e
n
c
e
s
i
n
t
y
pe
,
f
o
c
us
,
m
e
t
h
o
ds
,
r
e
s
ul
t
s
,
a
n
d
s
u
bj
e
c
t
s
.
I
t
m
e
a
n
s
t
h
a
t
t
hi
s
s
t
ud
y
o
f
f
e
r
s
a
n
o
v
e
l
t
y
t
h
a
t
e
a
r
l
i
e
r
r
e
s
e
a
r
c
h
e
r
s
h
a
v
e
n
o
t
e
x
p
l
o
r
e
d.
I
n
e
s
s
e
n
c
e
,
pr
i
o
r
r
e
s
e
a
r
c
h
h
a
s
i
de
n
t
i
f
i
e
d
a
s
i
g
ni
f
i
c
a
n
t
i
s
s
u
e
.
S
h
a
m
i
e
t
al.
[
26]
a
n
d
H
o
us
s
e
i
n
e
t
al.
[
27]
c
h
a
r
a
c
t
e
r
i
z
e
t
h
e
P
S
O
m
e
t
h
o
d
a
s
hi
g
hly
po
pul
a
r
i
n
t
h
e
e
xi
s
t
i
n
g
l
i
t
e
r
a
t
ur
e
.
A
dd
i
t
i
o
na
l
ly
,
S
h
a
m
i
e
t
al.
[
26]
a
n
d
Ho
us
s
e
i
n
e
t
al.
[
27]
p
r
o
vi
de
a
c
o
m
pr
e
h
e
n
s
i
v
e
o
v
e
r
vi
e
w
o
f
P
S
O.
I
n
c
o
n
t
r
a
s
t,
t
h
e
pr
e
vi
o
us
r
e
s
e
a
r
c
h
b
y
S
h
a
mi
e
t
al.
[
26]
a
n
d
Ho
us
s
e
i
n
e
t
al.
[
27
]
us
e
d
a
li
t
e
r
a
t
ur
e
r
e
vi
e
w
f
o
c
us
e
d
o
n
P
S
O,
whi
c
h
d
i
f
f
e
r
s
f
r
o
m
o
ur
a
ppr
o
a
c
h
.
T
hi
s
s
t
ud
y
pr
o
po
s
e
s
a
c
l
a
s
s
if
i
c
a
t
i
o
n
m
o
de
l
t
h
a
t
us
e
s
t
h
e
S
VM
m
e
t
h
o
d
i
n
c
o
nj
u
n
c
t
i
o
n
w
i
t
h
t
h
e
P
S
O
a
l
go
r
i
t
hm
.
M
e
a
n
w
hil
e
,
S
o
ga
s
e
t
al
.
[
21]
r
e
vi
e
w
e
d
t
h
e
e
c
o
n
o
m
i
c
a
n
d
s
o
c
i
a
l
im
pa
c
t
s
o
f
s
po
r
t
i
n
g
e
v
e
n
t
s
us
i
n
g
a
c
o
s
t
-
b
e
ne
f
i
t
a
na
l
y
s
i
s
.
S
o
ga
s
e
t
al
.
[
21]
r
e
s
e
a
r
c
h
i
s
pur
e
l
y
de
s
c
r
i
pt
i
v
e
a
n
d
do
e
s
n
ot
pr
o
p
o
s
e
a
s
e
n
t
i
m
e
n
t
a
n
a
ly
s
i
s
m
o
de
l
us
i
ng
m
a
c
hi
ne
l
e
a
r
ni
ng
m
e
t
h
o
ds
,
unli
ke
o
ur
s
t
udy
.
T
h
e
s
i
mi
l
a
r
i
t
y
b
e
t
we
e
n
S
o
ga
s
e
t
al
[
21]
a
n
d
o
ur
r
e
s
e
a
r
c
h
li
e
s
o
nly
i
n
t
h
e
r
e
s
e
a
r
c
h
o
bj
e
c
t
:
bot
h
di
s
c
us
s
s
po
r
t
i
n
g
e
v
e
n
t
s
.
A
s
t
ud
y
by
B
o
r
do
l
o
i
a
n
d
B
i
s
wa
s
[
28]
r
e
v
i
e
we
d
t
he
e
xi
s
t
i
n
g
l
i
t
e
r
a
t
ur
e
o
n
s
e
n
t
i
m
e
n
t
a
n
a
l
y
s
i
s
r
e
s
e
a
r
c
h
c
o
n
duc
t
e
d
by
pr
e
vi
o
us
s
c
h
o
l
a
r
s
.
T
h
e
go
a
l
i
s
to
de
s
c
r
i
be
va
r
i
o
us
s
y
s
t
e
m
a
t
i
c
t
e
c
hni
que
s
a
n
d
m
e
t
h
o
ds
f
o
r
de
v
e
l
o
p
i
ng
s
e
n
t
i
m
e
n
t
a
n
a
ly
s
i
s
m
o
d
e
l
s
.
A
l
im
i
t
a
t
i
o
n
o
f
pr
i
o
r
r
e
s
e
a
r
c
h
i
s
t
h
a
t
i
t
i
s
a
r
e
vi
e
w
s
t
ud
y
a
n
d
do
e
s
n
ot
pr
o
p
o
s
e
a
s
e
n
t
i
m
e
n
t
a
n
a
ly
s
i
s
m
o
de
l
b
a
s
e
d
o
n
m
a
c
hi
ne
l
e
a
r
ni
ng,
unli
ke
t
h
e
r
e
s
e
a
r
c
h
pr
e
s
e
n
t
e
d
i
n
o
ur
a
r
t
i
c
l
e
.
T
h
e
d
i
f
f
e
r
e
n
c
e
s
be
t
we
e
n
pr
e
vi
o
us
r
e
s
e
a
r
c
h
a
n
d
o
ur
s
t
udy
l
i
e
i
n
t
h
e
r
e
s
e
a
r
c
h
o
bj
e
c
t
i
v
e
s
,
c
a
t
e
g
o
r
i
e
s
,
a
n
d
m
a
c
hi
ne
l
e
a
r
ni
ng
m
e
t
h
o
ds
e
m
p
l
o
y
e
d.
A
pa
pe
r
by
R
o
dr
í
gue
z
-
I
b
á
n
e
z
e
t
al.
[
29]
pr
o
vi
de
s
a
r
e
vi
e
w
o
f
s
e
n
t
i
m
e
n
t
a
n
a
ly
s
i
s
t
e
c
hni
que
s
a
n
d
t
h
e
i
r
a
pp
l
i
c
a
t
i
o
ns
a
c
r
o
s
s
v
a
r
i
o
us
i
n
du
s
t
r
i
e
s
.
A
s
t
udy
by
R
o
dr
í
gue
z
-
I
b
á
n
e
z
e
t
al.
[
29
]
i
s
n
o
t
a
s
t
udy
pr
o
p
o
s
i
n
g
a
s
e
n
t
i
m
e
n
t
a
n
a
l
y
s
i
s
m
o
de
l
,
n
o
r
i
s
i
t
a
n
o
p
t
i
m
i
z
a
t
i
o
n
s
t
udy
,
a
s
i
n
o
ur
a
r
t
i
c
l
e
.
T
h
e
s
i
mi
l
a
r
i
t
y
b
e
t
we
e
n
[
29]
a
n
d
o
ur
r
e
s
e
a
r
c
h
l
i
e
s
s
o
l
e
ly
i
n
t
h
e
f
o
c
us
o
n
t
h
e
o
bj
e
c
t
o
f
s
e
n
t
i
m
e
n
t
a
n
a
ly
s
i
s
r
e
s
e
a
r
c
h
.
Abi
o
l
a
e
t
al.
[
30]
c
o
n
duc
t
e
d
a
s
e
n
t
i
m
e
n
t
a
n
a
ly
s
is
o
n
T
wi
t
t
e
r
r
e
l
a
t
e
d
to
t
h
e
c
or
o
n
a
vi
r
u
s
pa
n
d
e
m
i
c
.
A
bi
o
l
a
e
t
al.
[
30]
u
t
i
l
i
z
e
d
T
e
x
t
B
l
o
b
a
n
d
a
Va
l
e
n
c
e
-
A
wa
r
e
D
i
c
t
i
o
n
a
r
y
i
n
t
e
x
t
m
i
n
i
ng.
I
n
c
o
n
t
r
a
s
t,
o
ur
s
t
udy
us
e
s
t
e
r
m
f
r
e
qu
e
n
c
y
-
i
nve
r
s
e
do
c
um
e
n
t
f
r
e
que
n
c
y
(
T
F
-
I
DF
)
i
n
t
e
x
t
m
i
ni
ng.
Abi
o
l
a
e
t
al.
[
30]
di
d
n
o
t
o
p
t
i
mi
z
e
t
h
e
m
e
t
h
o
d
’
s
pe
r
f
o
r
m
a
n
c
e
f
o
r
s
e
n
t
i
m
e
n
t
a
n
a
ly
s
i
s
c
l
a
s
s
i
f
i
c
a
t
i
o
n
.
De
ne
c
ke
a
n
d
R
e
i
c
h
e
n
p
f
a
de
r
[
31]
o
n
i
nd
i
vi
dua
l
c
l
i
n
i
c
a
l
h
e
a
l
t
h
s
e
n
t
i
m
e
n
t
a
n
a
l
y
s
i
s
wa
s
c
o
n
duc
t
e
d
by
r
e
vi
e
w
i
ng
pr
e
vi
o
us
s
t
ud
i
e
s
.
T
h
e
s
t
ud
y
by
B
o
r
do
l
o
i
a
nd
B
i
s
wa
s
[
28]
i
s
a
r
e
vi
e
w
a
r
t
i
c
l
e
a
n
d
do
e
s
n
o
t
pr
o
p
o
s
e
a
s
e
n
t
i
m
e
n
t
a
n
a
ly
s
i
s
m
o
de
l
b
a
s
e
d
o
n
m
a
c
hi
ne
l
e
a
r
ni
ng
to
im
pr
o
v
e
pe
r
f
o
r
m
a
nc
e
.
T
h
e
r
e
s
e
a
r
c
h
by
[
31]
a
n
d
o
u
r
a
r
t
i
c
l
e
d
i
f
f
e
r
i
n
t
e
r
m
s
o
f
r
e
s
e
a
r
c
h
m
e
t
h
o
ds
a
n
d
o
bj
e
c
t
i
v
e
s
S
i
n
gga
l
e
n
[
32]
a
n
a
l
y
z
e
d
t
h
e
m
o
to
r
s
po
r
t
e
v
e
nt
us
i
n
g
K
-
n
e
a
r
e
s
t
n
e
i
g
hb
o
r
(
K
NN
)
a
n
d
S
VM
a
l
go
r
i
t
hm
s
.
T
h
e
r
e
s
u
l
t
s
de
m
o
ns
t
r
a
t
e
t
h
a
t
t
h
e
KN
N
a
l
go
r
i
t
hm
e
f
f
e
c
t
i
ve
l
y
c
l
a
s
s
if
i
e
s
s
e
n
t
i
m
e
n
t
a
n
a
ly
s
i
s
.
R
e
s
e
a
r
c
h
c
o
n
duc
t
e
d
by
S
i
n
gga
l
e
n
[
32]
i
s
c
l
o
s
e
ly
r
e
l
a
t
e
d
to
t
h
e
s
e
n
t
i
m
e
n
t
a
n
a
ly
s
i
s
o
f
s
po
r
t
s
e
v
e
n
t
s
d
i
s
c
us
s
e
d
i
n
o
ur
a
r
t
i
c
l
e
.
Ho
we
v
e
r
,
t
h
e
di
f
f
e
r
e
n
c
e
l
i
e
s
i
n
[
32]
n
ot
i
n
c
o
r
por
a
t
i
n
g
S
VM
o
p
t
i
mi
z
a
t
i
o
n
vi
a
t
h
e
P
S
O
a
ppr
o
a
c
h
,
unl
i
ke
o
ur
s
t
udy
.
T
h
e
a
dva
n
t
a
ge
o
f
o
ur
r
e
s
e
a
r
c
h
i
s
t
h
a
t
i
t
pr
o
p
o
s
e
s
o
p
t
i
mi
z
i
ng
t
h
e
S
VM
m
e
t
h
o
d
f
o
r
s
e
n
t
i
m
e
n
t
a
n
a
ly
s
i
s
o
f
s
po
r
t
s
e
v
e
n
t
s
us
i
n
g
t
h
e
P
S
O
a
l
go
r
i
t
hm
,
c
o
m
p
a
r
e
d
to
t
h
e
s
t
udy
by
S
i
ngga
l
e
n
[
32]
.
R
e
s
e
a
r
c
h
by
P
r
i
b
a
d
i
e
t
al.
[
33]
e
m
p
l
o
y
e
d
t
h
e
n
a
ïv
e
B
a
y
e
s
m
e
t
h
o
d
us
i
n
g
da
t
a
f
r
o
m
1,
144
r
e
vi
e
w
s
o
f
to
ur
i
s
t
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t
J
I
n
f
&
C
o
m
m
u
n
T
e
c
hn
o
l
I
S
S
N:
2252
-
8776
E
nhanc
ing
s
uppor
t
v
e
c
tor
mac
hine
pe
r
f
or
manc
e
us
ing
par
ti
c
le
s
w
ar
m
opti
miz
ati
on
…
(
C
h
r
is
tof
e
r
Satr
ia)
525
a
tt
r
a
c
t
i
o
n
s
i
n
M
a
n
da
li
ka
,
c
o
m
pr
i
s
i
ng
1,
033
p
o
s
i
t
i
ve
r
e
vi
e
w
s
a
n
d
111
n
e
ga
t
i
v
e
r
e
vi
e
ws
.
A
pa
pe
r
by
P
r
i
ba
d
i
e
t
al.
[
33]
c
a
t
e
gor
i
z
e
s
to
ur
i
s
t
s
’
o
pi
ni
o
n
s
o
f
M
a
n
da
li
ka
to
ur
i
s
t
a
tt
r
a
c
t
i
o
ns
i
n
t
o
p
o
s
i
t
i
v
e
o
r
n
e
ga
t
i
v
e
s
e
n
t
i
m
e
n
t
s
.
T
hi
s
s
t
ud
y
d
i
s
t
i
n
gu
i
s
h
e
s
i
t
s
e
l
f
f
r
o
m
o
ur
a
r
t
i
c
l
e
by
ut
i
li
z
i
ng
m
a
c
hi
ne
l
e
a
r
n
i
n
g
t
e
c
hni
que
s
f
o
r
s
e
n
t
i
m
e
n
t
a
n
a
ly
s
i
s
c
l
a
s
s
i
f
i
c
a
t
i
o
n
[
33]
.
Our
r
e
s
e
a
r
c
h
f
o
c
us
e
s
o
n
d
i
f
f
e
r
e
n
t
s
e
n
t
i
m
e
n
t
s
,
wh
e
r
e
a
s
P
r
i
ba
d
i
e
t
al.
[
33]
r
e
s
e
a
r
c
h
a
n
a
ly
z
e
s
s
e
n
t
i
m
e
n
t
s
r
e
l
a
t
e
d
to
to
ur
i
s
m
.
M
e
a
n
w
hil
e
,
a
s
t
udy
by
An
ggr
a
wa
n
e
t
al.
[
12
]
pr
o
p
o
s
e
d
a
s
e
n
t
i
m
e
n
t
a
n
a
ly
s
i
s
m
o
de
l
t
h
a
t
u
t
i
l
i
z
e
s
t
h
e
K
NN
a
n
d
S
VM
m
a
c
hi
ne
l
e
a
r
ni
n
g
m
e
t
h
o
ds
.
W
hil
e
b
o
t
h
[
12
]
r
e
s
e
a
r
c
h
a
n
d
o
u
r
s
t
udy
f
o
c
us
o
n
s
e
n
t
i
m
e
n
t
a
n
a
ly
s
i
s
us
i
ng
m
a
c
hin
e
l
e
a
r
ni
ng
t
e
c
h
ni
qu
e
s
f
o
r
s
e
n
t
i
m
e
n
t
c
l
a
s
s
i
f
i
c
a
t
i
o
n
a
n
d
c
o
m
pa
r
e
t
h
e
pe
r
f
o
r
m
a
n
c
e
o
f
t
w
o
m
a
c
hi
ne
l
e
a
r
ni
ng
m
e
t
h
o
ds
,
An
ggr
a
wa
n
e
t
al.
[
12]
r
e
s
e
a
r
c
h
do
e
s
n
o
t
i
n
c
l
ude
a
c
o
m
pa
r
i
s
o
n
b
e
t
we
e
n
t
h
e
S
VM
a
n
d
t
h
e
S
VM
c
o
m
b
i
ne
d
w
i
t
h
t
h
e
P
S
O
m
e
t
h
o
d.
T
h
e
r
e
s
e
a
r
c
h
by
An
ggr
a
wa
n
e
t
al.
[
12
]
i
s
n
o
t
r
e
s
e
a
r
c
h
o
n
s
e
n
t
i
m
e
n
t
c
l
a
s
s
i
f
i
c
a
t
i
o
n
us
i
ng
m
a
c
hi
ne
l
e
a
r
ni
ng
m
e
t
h
o
ds
t
h
a
t
h
a
v
e
im
pr
o
v
e
d
(
o
p
t
i
m
i
z
e
d)
t
h
e
i
r
a
c
c
ur
a
c
y
.
O
n
t
h
e
c
o
n
tr
a
r
y
,
t
h
e
r
e
s
e
a
r
c
h
i
n
t
hi
s
a
r
t
i
c
l
e
f
o
c
us
e
s
o
n
s
e
n
t
i
m
e
n
t
c
l
a
s
s
if
i
c
a
t
i
o
n
us
i
n
g
m
a
c
hi
ne
l
e
a
r
ni
ng
m
e
t
h
o
ds
,
a
c
hi
e
vi
ng
i
m
pr
o
v
e
d
a
c
c
ur
a
c
y
.
L
a
m
a
ni
e
t
al.
[
34]
p
r
o
p
o
s
e
s
a
s
y
s
t
e
m
f
o
r
e
f
f
e
c
t
i
v
e
ly
de
t
e
c
t
i
n
g
h
u
m
a
n
a
c
t
i
o
ns
us
i
ng
a
n
S
VM
m
a
c
hi
ne
l
e
a
r
ni
ng
c
l
a
s
s
i
f
i
e
r
.
T
h
e
f
o
c
us
o
f
L
a
m
a
ni
e
t
al.
[
3
4]
r
e
s
e
a
r
c
h
i
s
o
n
d
i
f
f
e
r
e
n
t
o
bj
e
c
t
s
t
h
a
t
di
f
f
e
r
f
r
o
m
t
h
o
s
e
i
n
t
hi
s
a
r
t
i
c
l
e
.
A
dd
i
t
i
o
n
a
ll
y
,
L
a
m
a
ni
e
t
al.
[
34]
r
e
s
e
a
r
c
h
do
e
s
n
ot
v
e
r
i
f
y
t
h
e
a
c
c
ur
a
c
y
o
f
t
h
e
s
e
n
t
i
m
e
n
t
a
n
a
ly
s
i
s
r
e
s
u
l
t
s
o
r
t
h
e
s
y
s
t
e
m
’
s
r
e
c
o
gni
t
i
o
n
o
f
h
u
m
a
n
a
c
t
i
o
n
s
.
L
a
m
a
ni
e
t
al.
[
34]
R
e
s
e
a
r
c
h
i
s
n
o
t
a
b
o
u
t
o
p
t
i
mi
z
i
ng
t
h
e
pe
r
f
o
r
m
a
n
c
e
o
f
t
h
e
S
VM
m
e
t
h
o
d,
a
s
i
n
o
ur
r
e
s
e
a
r
c
h
a
r
t
i
c
l
e
.
I
n
t
h
e
m
e
a
n
t
i
m
e
,
a
pa
pe
r
by
C
h
o
ur
a
s
i
y
a
e
t
al.
[
6
]
r
e
vi
e
ws
v
a
r
i
o
us
a
ppr
o
a
c
h
e
s
to
s
e
n
t
i
m
e
n
t
a
n
a
l
y
s
i
s
,
i
n
c
l
ud
i
ng
m
a
c
hi
ne
l
e
a
r
ni
ng
m
e
t
h
o
ds
s
uc
h
a
s
Va
de
r
,
R
o
b
e
r
t
a
,
Na
ï
v
e
B
a
y
e
s
,
a
n
d
S
VM
.
T
hi
s
pr
i
o
r
r
e
s
e
a
r
c
h
i
s
a
l
i
t
e
r
a
t
ur
e
r
e
vi
e
w
a
n
d
do
e
s
n
o
t
f
o
c
us
o
n
a
s
y
s
t
e
m
.
A
pa
pe
r
by
Z
h
a
o
a
n
d
Ya
n
g
[
8]
e
m
p
l
o
y
e
d
t
h
e
S
V
M
m
e
t
h
o
d
f
o
r
t
e
x
t
e
m
o
t
i
o
n
c
l
a
s
s
i
f
i
c
a
t
i
o
n
.
I
t
p
r
o
p
o
s
e
d
a
m
u
l
t
i
l
e
ve
l
S
VM
-
b
a
s
e
d
e
m
o
t
i
o
n
c
l
a
s
s
if
i
c
a
t
i
o
n
m
o
de
l
to
c
a
t
e
g
o
r
i
z
e
c
u
l
t
ur
a
l
i
nhe
r
i
t
a
n
c
e
t
e
n
de
n
c
i
e
s
i
n
i
n
-
t
e
x
t
c
o
m
m
e
n
t
s
o
n
we
b
n
e
t
w
o
r
ks
.
R
e
s
e
a
r
c
h
by
Z
h
a
o
a
n
d
Ya
n
g
[
8]
i
s
s
im
il
a
r
to
o
u
r
s
t
udy
,
a
s
i
t
a
ppl
i
e
s
m
a
c
hi
ne
l
e
a
r
ni
ng
to
pr
o
p
o
s
e
a
s
e
n
t
i
m
e
n
t
a
na
l
y
s
i
s
c
l
a
s
s
if
i
c
a
t
i
o
n
m
o
de
l
.
T
he
d
i
f
f
e
r
e
nc
e
l
i
e
s
i
n
t
h
e
r
e
s
e
a
r
c
h
o
bj
e
c
t
,
a
s
t
h
e
pr
e
vi
o
us
r
e
s
e
a
r
c
h
i
s
n
o
t
r
e
l
a
t
e
d
to
M
oto
GP
a
n
d
W
S
B
K
o
bj
e
c
t
s
.
A
dd
i
t
i
o
na
l
ly
,
t
h
e
e
a
r
l
i
e
r
r
e
s
e
a
r
c
h
d
i
d
n
ot
t
e
s
t
t
h
e
pe
r
f
o
r
m
a
n
c
e
o
f
S
VM
o
pt
i
m
i
z
a
t
i
o
n
w
i
t
h
s
wa
r
m
pa
r
t
i
c
l
e
s
,
unli
ke
t
h
e
r
e
s
e
a
r
c
h
pr
e
s
e
n
t
e
d
i
n
t
hi
s
a
r
t
i
c
l
e
.
T
h
e
r
e
ha
s
b
e
e
n
i
ns
u
f
f
i
c
i
e
n
t
e
x
p
l
o
r
a
t
i
o
n
o
f
i
n
t
e
gr
a
t
i
n
g
t
h
e
Va
de
r
L
e
xi
c
o
n
m
e
t
h
o
d
w
i
t
h
t
h
e
S
VM
a
l
go
r
i
t
hm
,
pa
r
t
i
c
u
l
a
r
l
y
w
h
e
n
o
p
t
i
m
i
z
e
d
us
i
n
g
P
S
O.
W
i
t
h
o
ut
t
h
e
s
e
o
p
t
i
mi
z
a
t
i
o
n
t
e
c
h
ni
qu
e
s
,
f
e
a
t
ur
e
s
e
l
e
c
t
i
o
n
o
f
t
e
n
r
e
m
a
i
ns
s
u
b
o
pt
i
m
a
l
,
l
e
a
d
i
ng
to
l
o
we
r
a
c
c
ur
a
c
y
i
n
s
e
n
t
i
m
e
n
t
c
l
a
s
s
if
i
c
a
t
i
o
n
.
T
h
e
us
e
o
f
t
he
Va
de
r
L
e
xi
c
o
n
a
n
d
S
VM
,
e
i
t
h
e
r
s
e
pa
r
a
t
e
l
y
o
r
wi
t
h
o
ut
a
p
r
o
pe
r
f
e
a
t
ur
e
o
p
t
i
mi
z
a
t
i
o
n
s
t
r
a
t
e
gy
,
c
a
n
c
a
us
e
t
h
e
m
o
de
l
t
o
s
t
r
uggl
e
to
di
s
t
i
n
gu
i
s
h
c
o
m
p
l
e
x
s
e
n
t
i
m
e
n
t
p
o
l
a
r
i
t
ies
,
e
s
pe
c
i
a
ll
y
w
i
t
h
a
m
bi
guo
us
o
r
m
u
l
t
i
-
m
e
a
ni
ng
tex
t
da
t
a
.
T
h
e
r
e
f
o
r
e
,
t
h
e
c
o
m
bi
na
t
i
o
n
o
f
t
h
e
s
e
t
h
r
e
e
a
ppr
o
a
c
h
e
s
h
a
s
t
he
pot
e
n
t
i
a
l
t
o
pr
o
vi
de
a
n
i
nn
o
v
a
t
i
v
e
s
o
l
ut
i
o
n
t
o
o
v
e
r
c
o
m
e
t
h
e
l
i
mi
t
a
t
i
o
ns
o
f
pr
e
vi
o
us
r
e
s
e
a
r
c
h
.
I
n
e
s
s
e
n
c
e
,
t
hi
s
r
e
s
e
a
r
c
h
s
e
r
ve
s
a
s
a
n
e
x
a
mp
l
e
o
f
a
pe
r
f
o
r
m
a
n
c
e
o
p
t
i
mi
z
a
t
i
o
n
m
o
de
l
f
o
r
a
m
a
c
hi
ne
l
e
a
r
ni
ng
m
e
t
h
o
d
us
i
n
g
P
S
O
i
n
s
c
i
e
nc
e
,
a
n
d
t
h
e
r
e
s
u
l
t
s
c
o
n
t
r
i
b
ut
e
to
t
h
e
c
o
m
m
u
ni
t
y
o
f
o
b
s
e
r
v
e
r
s
a
n
d
or
ga
ni
z
e
r
s
r
e
ga
r
di
n
g
publi
c
s
e
n
t
i
m
e
n
t
(
p
o
s
i
t
i
v
e
,
n
e
ut
r
a
l
,
o
r
n
e
ga
t
i
v
e
)
to
wa
r
d
s
p
o
r
t
i
n
g
e
ve
n
t
s
(
M
oto
G
P
a
n
d
W
S
B
K
)
.
T
a
bl
e
1.
C
o
m
pa
r
i
s
o
n
o
f
pr
i
o
r
r
e
l
a
t
e
d
wor
ks
wi
t
h
o
ur
s
t
udy
R
e
s
e
a
r
c
h a
ut
hor
s
R
e
s
e
a
r
c
h t
y
pe
R
e
s
e
a
r
c
h
f
oc
us
U
s
in
g me
th
o
d
M
e
th
o
d p
e
r
f
o
r
ma
n
c
e
S
por
ti
ng
e
v
e
nt
r
e
s
e
a
r
ch
S
V
M
PSO
S
V
M
S
V
M
w
it
h P
S
O
H
o
us
s
e
in
e
t
al
.
[
27
]
L
it
e
r
a
tu
r
e
r
e
v
i
e
w
R
e
vi
e
w
P
S
O
No
Y
e
s
N
o
n
e
N
o
n
e
No
S
o
ga
s
e
t
al
.
[
21]
D
e
s
c
r
ip
ti
v
e
a
na
l
y
s
is
C
o
s
t
-
be
n
e
f
it
No
No
N
o
n
e
N
o
n
e
Y
e
s
S
ha
mi
e
t
al
.
[
26]
L
it
e
r
a
tu
r
e
r
e
v
i
e
w
R
e
vi
e
w
P
S
O
N
o
Y
e
s
N
o
n
e
N
o
n
e
No
B
o
r
d
o
l
o
i
e
t
al
.
[
28]
L
it
e
r
a
tu
r
e
r
e
v
i
e
w
S
e
nt
im
e
nt
No
No
N
o
n
e
N
o
n
e
No
R
o
dr
íg
u
e
z
-
I
bá
n
e
z
e
t
al
.
[
29]
L
it
e
r
a
tu
r
e
r
e
v
i
e
w
S
e
nt
im
e
nt
No
No
N
o
n
e
N
o
n
e
No
A
bi
o
la
e
t
al
.
[
30]
P
r
o
p
o
s
e
d s
y
s
t
e
m
S
e
nt
im
e
nt
No
No
N
o
n
e
N
o
n
e
No
D
e
ne
c
k
e
e
t
al
.
[
31
]
L
it
e
r
a
tu
r
e
r
e
v
i
e
w
S
e
nt
im
e
nt
No
No
N
o
n
e
N
o
n
e
No
S
in
gga
le
n
[
32
]
A
na
l
y
s
is
S
e
nt
im
e
nt
Y
e
s
No
87.54%
N
o
n
e
Y
e
s
P
r
ib
a
di
e
t
al
.
[
33]
A
na
l
y
s
is
S
e
nt
im
e
nt
No
No
N
o
n
e
N
o
n
e
No
A
nggr
a
w
a
n
e
t
al
.
[
12]
A
na
l
y
s
is
S
e
nt
im
e
nt
Y
e
s
No
71%
N
o
n
e
No
L
a
ma
ni
e
t
al
.
[
34
]
A
na
l
y
s
is
R
e
c
o
gni
t
i
o
n
Y
e
s
No
N
o
n
e
N
o
n
e
No
L
iu
e
t
al
.
[
6]
L
it
e
r
a
tu
r
e
r
e
v
i
e
w
S
e
nt
im
e
nt
No
No
N
o
n
e
N
o
n
e
No
Z
ha
o
a
nd Y
a
ng
[
8]
A
na
l
y
s
is
S
e
nt
im
e
nt
Y
e
s
No
85%
N
o
n
e
No
O
ur
r
e
s
e
a
r
c
h
O
pt
im
iz
in
g
S
e
nt
im
e
nt
Y
e
s
Y
e
s
80.15%
81.82%
Y
e
s
2.
RE
S
E
AR
CH
M
E
T
HO
D
F
i
gur
e
1
i
ll
us
t
r
a
t
e
s
t
h
a
t
t
h
e
r
e
s
e
a
r
c
h
pr
o
c
e
s
s
c
o
m
men
c
e
d
w
i
t
h
t
e
x
t
p
r
e
pr
o
c
e
s
s
i
n
g,
s
pe
c
if
i
c
a
ll
y
t
o
ur
i
s
t
r
e
vi
e
ws
r
e
l
a
t
e
d
to
t
h
e
i
m
p
l
e
m
e
n
t
a
t
i
o
n
o
f
Mo
t
o
G
P
an
d
W
SB
K
e
v
e
n
t
s
i
n
M
a
n
da
li
ka
.
T
h
e
c
o
l
l
e
c
t
e
d
da
t
a
un
de
r
go
e
s
f
ur
t
h
e
r
t
e
x
t
pr
e
p
r
o
c
e
s
s
i
ng,
i
n
c
l
ud
i
n
g
c
a
s
e
f
o
l
d
i
ng,
t
e
x
t
c
l
e
a
ni
n
g,
n
o
r
m
a
li
z
a
t
i
o
n
,
f
i
l
t
e
r
i
n
g,
to
ke
ni
z
a
t
i
o
n
,
s
t
o
p
-
wor
d
r
e
m
o
v
a
l
,
a
n
d
s
t
e
m
mi
ng.
All
o
f
t
h
e
s
e
t
e
x
t
pr
e
pr
o
c
e
s
s
i
n
g
s
t
a
ge
s
im
pr
o
v
e
da
ta
qua
l
i
t
y
,
m
a
k
i
ng
s
e
n
t
i
m
e
n
t
a
n
a
ly
s
i
s
m
o
r
e
e
f
f
e
c
t
i
v
e
a
n
d
a
c
c
ur
a
t
e
.
Or
e
s
s
e
n
t
i
a
ll
y
,
t
h
e
pr
e
pr
o
c
e
s
s
i
ng
c
o
n
duc
t
e
d
i
n
t
hi
s
r
e
s
e
a
r
c
h
wa
s
t
h
e
f
i
r
s
t
s
t
e
p
to
wa
r
ds
a
c
hi
e
vi
ng
o
p
t
i
m
a
l
pe
r
f
o
r
m
a
n
c
e
f
r
o
m
t
h
e
a
ppl
i
e
d
s
e
n
t
i
m
e
n
t
c
l
a
s
s
if
i
c
a
t
i
o
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8776
I
n
t
J
I
n
f
&
C
o
m
m
u
n
T
e
c
hn
o
l
,
Vo
l
.
15
,
N
o.
2
,
J
un
e
20
26
:
523
-
534
526
m
e
t
h
o
d.
T
h
e
n
e
x
t
s
t
e
p
a
f
t
e
r
t
e
x
t
p
r
e
pr
o
c
e
s
s
i
n
g
i
s
to
we
i
g
h
t
t
h
e
f
e
a
t
ur
e
s
us
i
n
g
t
h
e
T
F
-
I
DF
m
e
t
h
o
d.
TF
-
I
DF
c
o
n
v
e
r
t
s
t
e
x
t
i
n
to
n
u
m
e
r
i
c
a
l
f
e
a
t
ur
e
s
by
e
m
p
ha
s
iz
i
n
g
s
i
g
nif
i
c
a
n
t
t
e
r
m
s
a
n
d
mi
n
im
i
z
i
ng
t
h
e
i
m
pa
c
t
o
f
l
e
s
s
r
e
l
e
v
a
n
t
wor
ds
.
T
h
e
n
e
x
t
s
t
e
p
i
s
to
c
o
n
duc
t
s
e
n
t
i
men
t
a
n
a
ly
s
i
s
us
i
ng
t
h
e
Va
de
r
L
e
xi
c
o
n
t
o
o
b
t
a
i
n
t
h
e
s
e
n
t
i
me
n
t
po
l
a
r
i
t
y
o
f
e
a
c
h
r
e
vi
e
w.
T
h
e
c
l
a
s
s
i
f
i
c
a
t
i
o
n
s
t
a
ge
,
us
i
n
g
t
h
e
S
VM
m
e
t
h
o
d
a
n
d
P
S
O
to
o
p
t
i
mi
z
e
a
c
c
ur
a
c
y
,
i
s
t
h
e
n
e
x
t
s
t
e
p.
T
h
e
f
i
na
l
s
t
e
p
i
s
t
o
m
e
a
s
ur
e
o
r
e
v
a
l
ua
t
e
t
h
e
m
o
de
l
’
s
pe
r
f
o
r
m
a
n
c
e
u
s
i
ng
a
c
o
nf
us
i
o
n
m
a
t
r
i
x
,
w
hi
c
h
i
nc
l
ude
s
m
e
t
r
i
c
s
s
u
c
h
a
s
a
c
c
ur
a
c
y
,
pr
e
c
i
s
i
o
n
,
r
e
c
a
ll
,
a
n
d
F1
-
s
c
o
r
e
.
T
h
e
n
e
x
t
s
t
e
p
i
s
t
o
e
v
a
l
ua
t
e
t
h
e
b
e
s
t
m
o
de
l
f
o
r
c
l
a
s
s
i
f
yi
ng
to
ur
i
s
t
s
e
n
t
i
m
e
n
t
to
wa
r
ds
e
v
e
n
t
s
h
e
l
d
i
n
M
a
n
da
li
ka
.
T
hi
s
s
t
ud
y
e
m
p
l
o
y
s
t
h
e
P
y
t
h
o
n
pr
o
g
r
a
m
mi
ng
l
a
n
gua
ge
f
o
r
da
t
a
pr
e
pr
o
c
e
s
s
i
n
g
a
n
d
im
p
l
e
m
e
n
t
i
n
g
T
F
-
I
DF
.
F
i
gur
e
1.
R
e
s
e
a
r
c
h
m
e
t
h
o
do
l
o
g
y
f
l
o
w
d
i
a
gr
a
m
2
.
1.
T
e
x
t
p
r
e
p
r
oc
e
s
s
in
g
T
e
x
t
pr
e
pr
o
c
e
s
s
i
n
g
i
s
a
n
e
s
s
e
n
t
i
a
l
s
t
a
ge
i
n
t
e
x
t
ua
l
da
t
a
p
r
o
c
e
s
s
i
ng
t
h
a
t
a
i
m
s
t
o
c
l
e
a
n
a
n
d
pr
e
pa
r
e
da
t
a
f
o
r
e
a
s
i
e
r
a
n
a
ly
s
i
s
.
I
n
t
hi
s
s
t
ud
y
,
v
a
r
i
o
us
t
e
x
t
pr
e
pr
o
c
e
s
s
i
n
g
t
e
c
hni
que
s
we
r
e
us
e
d,
i
nc
l
ud
i
ng
t
e
x
t
c
l
e
a
ni
ng
(
c
l
e
a
ns
i
n
g)
,
c
a
s
e
f
o
l
d
i
ng,
to
ke
ni
z
a
t
i
o
n
,
s
to
p
w
or
d
r
e
m
o
va
l
,
a
n
d
s
t
e
m
mi
ng.
T
h
e
e
n
t
i
r
e
t
e
x
t
pr
e
p
r
o
c
e
s
s
i
ng
pr
o
c
e
s
s
i
nv
o
l
v
e
s
a
c
t
i
o
ns
o
n
t
h
e
pu
bli
c
o
p
i
ni
o
n
d
a
tas
e
t
r
e
l
a
t
e
d
to
t
h
e
i
m
p
l
e
m
e
n
t
a
t
i
o
n
o
f
e
v
e
n
t
s
i
n
M
a
n
da
li
ka
.
C
a
s
e
f
o
l
d
i
ng
i
s
t
h
e
pr
o
c
e
s
s
o
f
c
h
a
n
g
i
ng
a
ll
l
e
t
t
e
r
s
i
n
a
t
e
x
t
to
l
o
we
r
c
a
s
e
t
o
m
a
t
c
h
t
h
e
f
o
r
m
a
t
o
f
t
h
e
tex
t
.
T
e
x
t
c
l
e
a
n
up
i
nv
o
l
ve
s
r
e
m
o
vi
ng
i
r
r
e
l
e
va
n
t
c
h
a
r
a
c
t
e
r
s
o
r
e
l
e
m
e
n
t
s
,
s
u
c
h
a
s
pun
c
t
ua
t
i
o
n
m
a
r
ks
(
e
.
g.
,
pe
r
i
o
ds
,
c
o
m
m
a
s
,
e
x
c
l
a
m
a
t
i
o
n
m
a
r
ks
)
,
n
u
m
b
e
r
s
,
s
pe
c
i
a
l
c
ha
r
a
c
t
e
r
s
(
e
.
g.
,
#
,
@
,
%
)
,
a
n
d
HT
M
L
e
l
e
m
e
n
t
s
o
r
U
R
L
s
.
F
ur
t
h
e
r
m
o
r
e
,
to
ke
ni
z
a
t
i
o
n
b
r
e
a
k
s
t
e
x
t
i
n
t
o
t
h
e
s
m
a
l
l
e
s
t
uni
t
s
,
c
a
l
l
e
d
to
ke
n
s
,
s
uc
h
a
s
wo
r
ds
o
r
s
e
n
t
e
n
c
e
s
.
T
h
e
pr
o
c
e
s
s
o
f
r
e
m
o
vi
ng
s
t
o
p
w
o
r
ds
a
i
m
s
t
o
e
l
im
i
na
t
e
c
o
m
m
o
n
wo
r
ds
t
h
a
t
a
ppe
a
r
f
r
e
qu
e
n
t
l
y
b
ut
h
a
v
e
l
o
w
a
n
a
ly
t
i
c
a
l
v
a
l
ue
,
s
uc
h
a
s
“
a
n
d
”
,
“
w
hi
c
h
”
,
or
“
f
o
r
”
,
s
o
t
h
a
t
t
h
e
a
n
a
l
y
s
i
s
c
a
n
f
o
c
us
o
n
m
o
r
e
m
e
a
ni
ng
f
u
l
wo
r
ds
.
F
i
n
a
ll
y
,
t
h
e
s
t
e
m
mi
ng
pr
o
c
e
s
s
i
s
c
a
r
r
i
e
d
o
u
t
to
r
e
duc
e
w
o
r
ds
to
t
h
e
i
r
b
a
s
i
c
f
o
r
m
b
y
r
e
m
o
vi
ng
a
f
f
i
xe
s
,
t
h
e
r
e
by
b
r
i
n
g
i
ng
v
a
r
i
a
t
i
o
ns
i
n
w
o
r
d
f
o
r
m
s
to
ge
t
h
e
r
i
n
to
a
c
o
n
s
i
s
t
e
n
t
r
e
pr
e
s
e
n
t
a
t
i
o
n
.
2
.
2
.
TF
-
I
DF
w
e
igh
t
in
g
T
h
e
T
F
-
I
DF
m
e
t
h
o
d
i
s
a
t
e
x
t
r
e
pr
e
s
e
n
t
a
t
i
o
n
t
e
c
hni
que
w
i
de
ly
u
s
e
d
i
n
t
h
e
f
i
e
l
ds
o
f
i
nf
o
r
m
a
t
i
o
n
r
e
tr
i
e
va
l
a
n
d
t
e
x
t
m
i
ni
ng
[
35]
.
T
h
e
pr
i
m
a
r
y
pur
po
s
e
o
f
t
hi
s
m
e
t
h
o
d
i
s
t
o
m
e
a
s
ur
e
t
h
e
l
e
v
e
l
o
f
i
m
po
r
t
a
n
c
e
o
f
a
wo
r
d
(
t
e
r
m
)
i
n
a
do
c
u
m
e
n
t
r
e
l
a
t
i
v
e
t
o
t
h
e
e
n
t
i
r
e
c
o
ll
e
c
t
i
o
n
o
f
do
c
u
m
e
n
t
s
(
c
o
r
pus
)
.
T
h
e
T
F
-
I
DF
p
l
a
y
s
a
c
r
uc
i
a
l
r
o
l
e
i
n
d
i
s
t
i
n
gu
i
s
hi
ng
wo
r
ds
t
h
a
t
h
a
v
e
s
i
g
nif
i
c
a
n
t
m
e
a
ni
ng
i
n
a
gi
ve
n
c
o
n
t
e
x
t
by
a
s
s
i
g
ni
ng
e
a
c
h
t
e
r
m
a
we
i
g
h
t
b
a
s
e
d
o
n
i
t
s
f
r
e
que
n
c
y
o
f
o
c
c
ur
r
e
n
c
e
i
n
i
n
d
i
v
i
dua
l
do
c
um
e
n
t
s
a
n
d
i
t
s
r
a
r
i
t
y
i
n
t
h
e
o
v
e
r
a
l
l
c
o
r
pus
.
T
h
e
T
F
-
I
DF
m
e
t
h
o
d
c
o
n
s
i
s
t
s
o
f
t
w
o
m
a
i
n
c
o
m
po
n
e
n
t
s
.
F
i
r
s
t
,
t
e
r
m
f
r
e
que
n
c
y
(
T
F
)
,
whi
c
h
i
s
a
m
e
a
s
ur
e
o
f
h
o
w
o
f
t
e
n
a
t
e
r
m
a
ppe
a
r
s
i
n
a
do
c
u
m
e
n
t
.
T
hi
s
f
r
e
que
n
c
y
i
s
c
a
l
c
u
l
a
t
e
d
by
d
i
v
i
d
i
ng
t
h
e
n
u
m
be
r
o
f
o
c
c
ur
r
e
n
c
e
s
o
f
a
g
i
v
e
n
t
e
r
m
by
t
h
e
t
ot
a
l
n
u
m
be
r
o
f
t
e
r
m
s
i
n
t
h
e
do
c
u
m
e
n
t
.
T
hi
s
T
F
v
a
l
u
e
i
n
d
i
c
a
t
e
s
t
h
e
i
m
po
r
t
a
n
c
e
o
f
a
t
e
r
m
w
i
t
hi
n
a
do
c
um
e
n
t
’
s
l
o
c
a
l
c
o
n
t
e
x
t
.
S
e
c
o
n
d,
I
DF
m
e
a
s
ur
e
s
t
h
e
de
gr
e
e
o
f
r
a
r
i
t
y
o
f
a
t
e
r
m
i
n
t
h
e
e
n
t
i
r
e
c
o
r
pus
—
t
h
e
f
e
we
r
do
c
um
e
n
t
s
t
h
a
t
c
o
n
t
a
i
n
t
h
e
t
e
r
m
,
t
h
e
hi
g
h
e
r
t
h
e
I
DF
v
a
l
ue
.
T
h
e
c
o
m
bi
na
t
i
o
n
o
f
t
h
e
s
e
t
w
o
c
o
m
po
n
e
n
t
s
,
i
.
e
.
,
t
h
e
r
e
s
u
l
t
o
f
m
u
l
t
i
p
li
c
a
t
i
o
n
b
e
t
we
e
n
T
F
a
n
d
I
D
F
,
r
e
s
u
l
t
s
i
n
t
h
e
we
i
g
h
t
o
f
T
F
-
I
DF
.
T
hi
s
we
i
g
h
t
r
e
f
l
e
c
t
s
t
h
e
t
e
r
m
’
s
s
i
g
ni
f
i
c
a
n
c
e
i
n
a
do
c
u
m
e
n
t
r
e
l
a
t
i
v
e
t
o
t
h
e
e
n
t
i
r
e
c
o
r
pus
,
e
n
a
bli
ng
a
m
o
r
e
a
c
c
ur
a
t
e
a
n
d
m
e
a
ni
ng
f
u
l
a
n
a
ly
s
i
s
o
f
t
h
e
t
e
x
t
,
a
s
s
h
o
wn
i
n
(
1
)
-
(
3
)
.
(
,
)
=
,
(
1)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t
J
I
n
f
&
C
o
m
m
u
n
T
e
c
hn
o
l
I
S
S
N:
2252
-
8776
E
nhanc
ing
s
uppor
t
v
e
c
tor
mac
hine
pe
r
f
or
manc
e
us
ing
par
ti
c
le
s
w
ar
m
opti
miz
ati
on
…
(
C
h
r
is
tof
e
r
Satr
ia)
527
T
h
e
c
a
l
c
u
l
a
t
i
o
n
o
f
t
h
e
I
DF
v
a
l
ue
ut
i
li
z
e
d
(
2)
.
M
e
a
n
w
hil
e
,
t
h
e
(
3)
f
u
n
c
t
i
o
n
s
t
o
o
b
t
a
i
n
t
h
e
T
F
-
I
D
F
v
a
l
ue
f
o
r
t
e
r
m
t
i
n
do
c
um
e
n
t
d.
I
n
t
h
e
[
2]
,
|D|
i
n
d
i
c
a
t
e
s
t
h
e
tot
a
l
n
u
m
be
r
o
f
do
c
um
e
n
t
s
i
n
t
h
e
c
o
r
pus
,
whil
e
|d:
t
∈
d|
i
n
d
i
c
a
t
e
s
t
h
e
n
u
m
be
r
o
f
r
e
c
o
r
ds
t
h
a
t
c
o
n
ta
i
n
t
h
e
t
e
r
m
t
a
t
l
e
a
s
t
o
n
c
e
.
T
h
e
r
e
s
u
l
t
o
f
m
u
l
t
ip
l
i
c
a
t
i
o
n
b
e
t
we
e
n
T
F
a
n
d
I
D
F
r
e
s
u
l
t
s
i
n
t
h
e
f
i
na
l
we
i
g
h
t
o
f
T
F
-
I
DF
,
whi
c
h
r
e
f
l
e
c
t
s
t
h
e
l
e
ve
l
o
f
s
i
g
nif
i
c
a
n
c
e
o
f
t
h
e
t
e
r
m
i
n
t
h
e
do
c
u
m
e
n
t
r
e
l
a
t
i
ve
to
t
h
e
o
v
e
r
a
l
l
c
o
r
pus
.
(
,
)
=
(
|
|
1
+
|
:
∈
|
)
(
2)
−
(
,
,
)
=
(
,
)
(
,
)
(
3)
2
.
3
.
Vader
L
e
x
icon
Va
de
r
o
r
Va
l
e
n
c
e
A
wa
r
e
D
i
c
t
i
o
n
a
r
y
a
n
d
S
e
n
t
i
m
e
n
t
R
e
a
s
o
n
e
r
i
s
a
l
e
xi
c
o
n
-
b
a
s
e
d
s
e
n
t
i
m
e
n
t
a
n
a
l
y
s
i
s
m
e
t
h
o
d
de
s
i
g
n
e
d
to
c
l
a
s
s
i
f
y
t
e
x
t
s
i
n
t
o
p
o
s
i
t
i
v
e
,
n
e
ga
t
i
v
e
,
a
n
d
n
e
ut
r
a
l
s
e
n
t
i
m
e
n
t
c
a
t
e
gor
i
e
s
[
36]
.
T
hi
s
m
e
t
h
o
d
ut
i
li
z
e
s
a
d
i
c
t
i
o
n
a
r
y
o
f
wo
r
ds
(
l
e
xi
c
o
n
)
t
h
a
t
h
a
s
b
e
e
n
a
s
s
i
g
n
e
d
a
va
l
e
n
c
e
s
c
o
r
e
b
a
s
e
d
o
n
t
h
e
e
m
o
t
i
o
n
a
l
po
l
a
r
i
t
y
o
f
e
a
c
h
wo
r
d
[
37]
.
On
e
o
f
Va
de
r
’
s
s
t
r
e
n
gt
h
s
i
s
i
t
s
a
bil
i
t
y
t
o
h
a
n
d
l
e
i
nf
o
r
m
a
l
l
a
n
gua
ge
,
i
n
c
l
ud
i
ng
e
m
o
t
i
c
o
n
s
,
i
n
t
e
r
n
e
t
a
bb
r
e
vi
a
t
i
o
ns
,
a
n
d
e
m
p
h
a
s
i
s
o
n
wr
i
t
i
n
g
s
t
yl
e
s
s
uc
h
a
s
c
a
p
i
t
a
l
i
z
a
t
i
o
n
o
r
e
x
c
l
a
m
a
t
i
o
n
m
a
r
ks
[
38]
,
[
39
]
.
T
h
e
pr
i
m
a
r
y
o
ut
pu
t
o
f
Va
de
r
i
s
t
h
e
tot
a
l
s
c
o
r
e
,
a
l
s
o
kn
o
wn
a
s
t
h
e
c
o
m
po
un
d
s
c
o
r
e
,
whi
c
h
i
s
c
a
l
c
u
l
a
t
e
d
by
s
u
m
mi
ng
t
h
e
v
a
l
e
n
c
e
s
c
o
r
e
s
o
f
a
l
l
wo
r
ds
i
n
t
h
e
t
e
x
t
[
37
]
a
n
d
t
h
e
n
n
o
r
m
a
li
z
e
d
to
a
r
a
n
ge
o
f
-
1
to
+
1.
A
v
a
l
ue
c
l
o
s
e
to
-
1
i
n
d
i
c
a
t
e
s
hi
g
hly
n
e
ga
t
i
v
e
s
e
n
t
i
m
e
n
t
,
a
v
a
l
ue
c
l
o
s
e
t
o
+
1
i
n
d
i
c
a
t
e
s
s
t
r
o
n
g
p
o
s
i
t
i
v
e
s
e
n
t
i
m
e
n
t
,
a
n
d
a
v
a
l
ue
c
l
o
s
e
to
0
i
n
d
i
c
a
t
e
s
n
e
ut
r
a
l
s
e
n
t
i
m
e
n
t
.
2
.
4
.
Cl
as
s
if
i
c
at
ion
m
e
t
h
od
T
h
e
S
VM
m
e
t
h
o
d
c
l
a
s
s
i
f
i
e
s
us
i
ng
t
r
a
i
ni
ng
a
n
d
t
e
s
t
i
n
g
da
t
a
.
I
n
t
hi
s
s
t
udy
,
t
h
e
da
t
a
s
e
t
i
s
s
p
li
t
i
n
t
o
80:20,
wi
t
h
80%
f
o
r
t
r
a
i
ni
ng
a
n
d
20%
f
o
r
t
e
s
t
i
n
g.
T
h
e
S
VM
i
s
a
po
we
r
f
u
l
a
n
d
ve
r
s
a
t
i
l
e
c
l
a
s
s
if
i
c
a
t
i
o
n
a
l
go
r
i
t
hm
i
n
m
a
c
hi
ne
l
e
a
r
ni
n
g.
T
hi
s
a
l
go
r
i
t
hm
wo
r
ks
by
s
e
a
r
c
hi
ng
f
o
r
hy
pe
r
p
l
a
n
e
s
i
n
a
hi
g
h
-
d
i
mens
i
o
n
a
l
f
e
a
t
ur
e
s
pa
c
e
t
h
a
t
c
a
n
s
e
pa
r
a
t
e
da
t
a
c
l
a
s
s
e
s
w
i
t
h
m
a
xim
u
m
m
a
r
g
i
ns
[
40]
.
T
h
e
hy
pe
r
p
l
a
n
e
s
e
r
v
e
s
a
s
a
de
c
i
s
i
o
n
b
o
un
da
r
y
t
h
a
t
di
s
t
i
n
gu
i
s
h
e
s
t
h
e
t
w
o
c
l
a
s
s
e
s
,
i
n
t
e
nd
i
n
g
t
o
m
a
xim
i
z
e
t
h
e
d
i
s
t
a
n
c
e
(
m
a
r
g
i
n)
be
t
we
e
n
t
h
e
da
t
a
po
i
n
t
s
o
f
t
h
e
t
wo
c
l
a
s
s
e
s
c
l
o
s
e
s
t
to
t
h
e
hy
pe
r
p
l
a
n
e
.
T
h
e
da
t
a
p
o
i
n
t
s
c
l
o
s
e
s
t
to
t
h
e
hy
pe
r
p
l
a
n
e
a
r
e
c
a
l
l
e
d
s
uppo
r
t
v
e
c
tor
s
,
a
s
s
h
o
wn
i
n
(
4)
.
(
)
=
(
.
+
)
=
{
+
1
.
.
+
≥
0
−
1
.
.
+
<
0
}
(
4)
2
.
5
.
P
e
r
f
o
r
m
an
c
e
e
val
u
at
ion
A
c
o
nf
u
s
i
o
n
m
a
t
r
i
x
i
s
a
m
e
t
h
o
d
f
o
r
e
v
a
l
ua
t
i
ng
t
h
e
pe
r
f
o
r
m
a
n
c
e
o
f
c
l
a
s
s
i
f
i
c
a
t
i
o
n
m
o
de
l
s
by
c
o
m
pa
r
i
ng
t
h
e
m
o
de
l
’
s
pr
e
d
i
c
t
i
o
ns
to
t
h
e
a
c
t
ua
l
lab
e
l
s
.
T
hi
s
m
a
t
r
i
x
t
y
p
i
c
a
l
ly
c
o
ns
i
s
t
s
o
f
t
w
o
m
a
i
n
c
l
a
s
s
e
s
-
P
o
s
i
t
i
v
e
(
P
)
a
n
d
Ne
ga
t
i
v
e
(
N)
-
a
n
d
c
o
n
t
a
i
ns
f
o
ur
ke
y
c
o
m
po
n
e
n
t
s
.
T
r
ue
p
o
s
i
t
i
ve
(
T
P
)
r
e
f
e
r
s
to
t
h
e
n
u
m
be
r
o
f
po
s
i
t
i
v
e
da
t
a
p
o
i
n
t
s
wh
o
s
e
pr
e
d
i
c
t
i
o
n
s
a
r
e
a
c
c
ur
a
te.
A
t
t
h
e
s
a
m
e
t
i
m
e
,
a
f
a
l
s
e
n
e
ga
t
i
v
e
(
F
N)
i
s
t
h
e
a
m
o
u
n
t
o
f
po
s
i
t
i
v
e
da
t
a
wh
o
s
e
pr
e
d
i
c
t
i
o
n
i
s
wr
o
n
g
a
s
n
e
ga
t
i
ve
.
I
n
c
o
n
tr
a
s
t,
a
f
a
l
s
e
po
s
i
t
i
v
e
(
F
P
)
i
n
d
i
c
a
t
e
s
t
h
e
n
u
m
be
r
o
f
n
e
ga
t
i
v
e
da
t
a
po
i
n
t
s
t
h
a
t
a
r
e
i
n
c
o
r
r
e
c
t
l
y
pr
e
d
i
c
t
e
d
a
s
po
s
i
t
i
v
e
,
a
n
d
a
t
r
ue
n
e
ga
t
i
v
e
(
T
N)
i
n
d
i
c
a
t
e
s
t
h
e
n
u
m
be
r
o
f
n
e
g
a
t
i
v
e
da
t
a
po
i
n
t
s
t
h
a
t
a
r
e
c
or
r
e
c
t
l
y
pr
e
d
i
c
t
e
d
a
s
n
e
ga
t
i
v
e
[
15]
.
A
c
c
ur
a
c
y
m
e
a
s
ur
e
s
t
h
e
pe
r
c
e
n
t
a
ge
o
f
tot
a
l
c
o
r
r
e
c
t
pr
e
di
c
t
i
o
n
s
f
r
o
m
t
h
e
o
v
e
r
a
ll
d
a
t
a
.
R
e
c
a
l
l
,
o
r
s
e
n
s
i
t
i
vi
t
y
,
i
nd
i
c
a
t
e
s
t
h
e
pr
o
p
or
t
i
o
n
o
f
po
s
it
i
v
e
da
t
a
t
h
a
t
t
h
e
m
o
de
l
c
o
r
r
e
c
t
l
y
r
e
c
o
gni
z
e
s
.
P
r
e
c
i
s
i
o
n
m
e
a
s
ur
e
s
t
h
e
e
x
t
e
n
t
to
whi
c
h
t
h
e
m
o
de
l
’
s
po
s
i
t
i
v
e
pr
e
d
i
c
t
i
o
ns
a
r
e
a
c
c
ur
a
t
e
.
M
e
a
n
w
hil
e
,
t
h
e
F
1
-
s
c
o
r
e
i
s
t
h
e
h
a
r
mo
ni
c
a
v
e
r
a
ge
o
f
pr
e
c
i
s
i
o
n
a
n
d
r
e
c
a
ll
,
w
hi
c
h
i
s
us
e
f
u
l
w
h
e
n
t
h
e
r
e
i
s
a
c
l
a
s
s
im
ba
l
a
n
c
e
i
n
t
h
e
da
t
a
.
F
i
n
a
ll
y
,
s
p
e
c
i
f
i
c
i
t
y
i
nd
i
c
a
t
e
s
t
h
e
m
o
de
l
’
s
a
bil
i
t
y
t
o
c
o
r
r
e
c
t
l
y
i
d
e
n
t
i
f
y
n
e
ga
t
i
v
e
da
t
a
,
i
.
e
.
,
t
h
e
tr
ue
n
e
ga
t
i
v
e
pr
o
por
t
i
o
n
o
f
a
ll
n
e
g
a
t
i
ve
da
t
a
,
a
s
s
h
o
wn
i
n
T
a
bl
e
2
(
s
e
e
e
qua
t
i
o
ns
5
-
7)
.
T
a
bl
e
2.
C
o
nf
us
i
o
n
m
a
tr
i
x
A
c
tu
a
l
P
o
s
it
iv
e
N
e
g
a
ti
v
e
P
r
e
di
c
te
d
P
o
s
it
iv
e
TP
FP
N
e
g
a
ti
v
e
FN
TN
=
TP
+
TN
TP
+
FP
+
TN
+
FN
(
5)
=
TP
TP
+
FN
(
6)
1
−
=
2
∗
(
P
r
e
c
i
s
i
on
∗
R
e
c
a
ll
)
(
P
r
e
c
i
s
i
on
+
R
e
c
a
ll
)
(
7)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8776
I
n
t
J
I
n
f
&
C
o
m
m
u
n
T
e
c
hn
o
l
,
Vo
l
.
15
,
N
o.
2
,
J
un
e
20
26
:
523
-
534
528
3.
RE
S
UL
T
S
AN
D
DI
S
CU
S
S
I
ON
T
hi
s
s
e
c
t
i
o
n
pr
e
s
e
n
t
s
t
h
e
r
e
s
u
l
t
s
o
f
s
e
n
t
i
m
e
n
t
a
n
a
ly
s
i
s
o
f
a
da
t
a
s
e
t
o
f
to
ur
i
s
t
r
e
vi
e
w
s
o
n
t
h
e
im
p
l
e
m
e
n
t
a
t
i
o
n
o
f
s
po
r
t
i
n
g
e
v
e
n
t
s
.
T
h
e
a
n
a
ly
s
i
s
pr
o
c
e
s
s
c
o
m
pr
i
s
e
s
s
e
v
e
r
a
l
s
t
a
ge
s
,
i
n
c
l
ud
i
ng
t
e
x
t
pr
e
pr
o
c
e
s
s
i
ng,
f
e
a
t
ur
e
we
i
g
h
t
i
n
g,
a
pp
l
i
c
a
t
i
o
n
o
f
t
h
e
Va
de
r
L
e
xi
c
o
n
m
e
t
h
o
d,
a
n
d
o
p
t
i
mi
z
a
t
i
o
n
us
i
n
g
th
e
P
S
O
a
l
go
r
i
t
hm
.
T
h
e
da
t
a
s
e
t
us
e
d
i
n
t
hi
s
s
t
ud
y
c
o
m
pr
i
s
e
d
7,
1
84
r
e
vi
e
w
s
o
f
t
h
e
i
m
p
l
e
m
e
n
t
a
t
i
o
n
o
f
v
a
r
i
o
us
e
v
e
n
t
s
i
n
M
a
n
da
li
ka
,
a
s
s
h
o
wn
i
n
T
a
bl
e
3.
E
a
c
h
r
e
vi
e
w
c
o
n
t
a
i
ns
t
r
a
v
e
l
e
r
o
p
i
ni
o
ns
l
a
b
e
l
e
d
po
s
i
t
i
v
e
,
n
e
ut
r
a
l
,
o
r
n
e
ga
t
i
v
e
.
I
n
pr
e
pa
r
i
n
g
f
o
r
f
ur
t
h
e
r
a
n
a
l
y
s
i
s
,
da
t
a
p
r
e
pa
r
a
t
i
o
n
o
c
c
ur
s
dur
i
n
g
t
h
e
t
e
x
t
pr
e
p
r
o
c
e
s
s
i
ng
s
t
a
g
e
.
T
e
x
t
pr
e
pr
o
c
e
s
s
i
ng
i
n
c
l
ude
s
c
l
e
a
ni
ng,
c
a
s
e
f
o
l
d
i
ng,
r
e
m
o
vi
n
g
unim
po
r
t
a
n
t
w
o
r
ds
,
tokeni
z
a
t
i
o
n
,
a
n
d
s
t
e
m
mi
ng.
T
a
bl
e
3.
Da
t
a
s
e
t
s
e
n
t
i
m
e
n
t
T
e
x
t
S
e
nt
im
e
nt
s
angat bahagi
a adik
P
o
s
it
i
ve
P
o
ld
a anti
s
ip
as
i
k
e
m
ac
e
ta
n l
al
u l
in
ta
s
di
m
ot
ogp mandalika
N
e
ut
r
a
l
P
e
r
tu
nj
uk
an I
ndone
s
ia
ak
an dime
r
ia
hk
an ole
h pe
nam
pi
la
n ar
ti
s
nas
io
nal
P
o
s
it
i
ve
di
to
nt
on ole
h r
at
us
an j
ut
a or
ang di s
e
lu
r
uh dunia
N
e
ut
r
a
l
s
ia
pa y
ang ak
an m
e
nj
adi
pe
m
e
nangny
a
P
o
s
it
i
ve
…………………………….
.
……….
.
…………………………….
.
……….
.
di
ne
gar
a k
it
a s
e
ndi
r
i
de
bun
y
a j
e
le
k
N
e
ga
ti
v
e
T
a
bl
e
s
4
-
7
pr
e
s
e
n
t
t
h
e
r
e
s
u
l
t
s
o
f
e
a
c
h
pr
e
pr
o
c
e
s
s
i
ng
pr
o
c
e
s
s
.
F
i
gur
e
2
s
h
o
ws
t
h
e
s
o
u
r
c
e
c
o
de
o
f
t
e
x
t
pr
e
-
pr
o
c
e
s
s
i
n
g.
M
e
a
n
w
hil
e
,
T
a
bl
e
8
i
ll
u
s
t
r
a
t
e
s
t
h
e
s
ub
s
e
que
n
t
pr
o
c
e
s
s
a
f
t
e
r
pr
e
pr
o
c
e
s
s
i
n
g,
s
pe
c
i
f
ica
l
ly
t
h
e
a
pp
l
i
c
a
t
i
o
n
o
f
t
h
e
T
F
-
I
DF
we
i
g
h
t
i
n
g
t
e
c
hni
que
.
T
a
bl
e
4
.
C
a
s
e
f
o
l
d
i
n
g
P
r
e
P
r
o
c
e
s
s
i
n
g
A
f
te
r
c
a
s
e
f
o
ld
i
ng
C
a
s
e
f
o
ld
in
g
bahagia
bange
t
d
e
k
P
o
ld
a
ant
is
ip
as
i
k
e
m
ac
e
ta
n
la
lu
l
in
ta
s
m
ot
ogp mandalika
pe
r
tu
nj
uk
an i
ndone
s
ia
ak
an dim
e
r
ia
hk
an pe
na
m
pi
la
n ar
ti
s
nas
i
onal
di
to
nt
on r
at
us
an
ju
ta
or
ang dunia
s
ia
pa j
adi
pe
m
e
nang
........................................................
........................................................
ne
gar
a s
e
ndi
r
i
de
bu j
e
le
k
T
a
bl
e
5
.
S
to
p
w
or
d
r
e
m
o
v
a
l
P
r
e
P
r
o
c
e
s
s
i
n
g
A
f
te
r
s
to
p
w
o
r
d
r
e
mo
v
a
l
St
op
w
or
d r
e
m
ov
a
l
“
bahagia
”
,
“
bange
t
”
,
“
d
e
k
”
“
pol
da
”
,
“
ant
is
ip
as
i
”
,
“
ke
m
ac
e
ta
n
”
,
“
la
lu
”
,
“
li
nt
as
”
,
“
m
ot
og
p
”
,
“
m
andali
k
a
”
“
pe
r
tu
nj
uk
an
”
,
“
in
done
s
ia
”
,
“
ak
an
”
,
“
di
m
e
r
ia
hk
an
”
,
“
pe
nam
pi
la
n
”
,
“
ar
ti
s
”
,
“
nas
io
nal
”
“
di
to
nt
on
”
,
“
r
at
us
an
”
,
“
ju
ta
”
,
“
or
ang
”
,
“
duni
a
”
“
s
ia
pa
”
,
“
ja
di
”
,
“
pe
m
e
nang
”
........................................................
........................................................
“
ne
gar
a
”
,
“
s
e
ndi
r
i
”
,
“
de
bu
”
,
“
je
le
k
”
T
a
bl
e
6
.
T
o
ke
ni
z
i
ng
P
r
e
P
r
o
c
e
s
s
i
n
g
A
f
te
r
t
o
ke
n
iz
in
g
T
o
k
e
ni
z
in
g
“
bahagia
”
,
“
bange
t
”
,
“
d
e
k
”
“
pol
da
”
,
“
ant
is
ip
as
i
”
,
“
ke
m
ac
e
ta
n
”
,
“
la
lu
”
,
“
li
nt
as
”
,
“
m
ot
og
p
”
,
“
m
andali
k
a
”
“
pe
r
tu
nj
uk
an
”
,
“
in
done
s
ia
”
,
“
ak
an
”
,
“
di
m
e
r
ia
hk
an
”
,
“
pe
nam
pi
la
n
”
,
“
ar
ti
s
”
,
“
nas
io
nal
”
“
di
to
nt
on
”
,
“
r
at
us
an
”
,
“
ju
ta
”
,
“
or
ang
”
,
“
duni
a
”
“
s
ia
pa
”
,
“
ja
di
”
,
“
pe
m
e
nang
”
........................................................
........................................................
“
ne
gar
a
”
,
“
s
e
ndi
r
i
”
,
“
de
bu
”
,
“
je
le
k
”
F
i
gur
e
3
i
ll
us
t
r
a
t
e
s
a
s
ni
ppe
t
o
f
s
o
ur
c
e
c
o
de
t
h
a
t
i
m
p
l
e
m
e
n
t
s
t
h
e
S
VM
a
l
go
r
i
t
hm
c
o
m
bi
ne
d
w
i
t
h
t
h
e
P
S
O
m
e
t
h
o
d
to
e
n
h
a
n
c
e
c
l
a
s
s
i
f
i
c
a
t
i
o
n
pe
r
f
o
r
m
a
n
c
e
.
I
n
t
hi
s
e
n
c
o
d
i
n
g,
P
S
O
o
p
t
i
mi
z
e
s
t
h
e
hy
pe
r
pa
r
a
m
e
t
e
r
s
o
f
t
h
e
S
VM
,
n
a
m
e
ly
C
(
r
e
gu
l
a
r
i
z
a
t
i
o
n
)
a
n
d
ga
mm
a
(
R
B
F
ke
r
n
e
l
pa
r
a
m
e
t
e
r
)
,
whi
c
h
s
i
g
nif
i
c
a
n
t
l
y
i
nf
l
u
e
n
c
e
t
h
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t
J
I
n
f
&
C
o
m
m
u
n
T
e
c
hn
o
l
I
S
S
N:
2252
-
8776
E
nhanc
ing
s
uppor
t
v
e
c
tor
mac
hine
pe
r
f
or
manc
e
us
ing
par
ti
c
le
s
w
ar
m
opti
miz
ati
on
…
(
C
h
r
is
tof
e
r
Satr
ia)
529
m
o
de
l
’
s
a
c
c
ur
a
c
y
.
T
h
e
pr
o
c
e
s
s
b
e
g
i
ns
by
de
f
ini
ng
o
bj
e
c
t
i
v
e
f
u
nc
t
i
o
ns
—
t
h
e
f
u
n
c
t
i
o
n
s
t
h
e
P
S
O
w
i
l
l
mi
n
im
i
z
e
.
T
h
e
f
u
n
c
t
i
o
n
r
e
t
ur
n
s
a
n
e
ga
t
i
v
e
v
a
l
ue
f
o
r
t
h
e
a
v
e
r
a
ge
c
r
o
s
s
-
v
a
li
da
t
i
o
n
a
c
c
ur
a
c
y
o
f
a
n
S
V
M
m
o
de
l
w
i
t
h
a
s
pe
c
i
f
i
c
pa
r
a
m
e
t
e
r
c
o
m
bi
na
t
i
o
n
.
T
h
e
P
S
O
th
e
n
pe
r
f
o
r
m
s
a
g
l
o
b
a
l
s
e
a
r
c
h
o
v
e
r
a
pr
e
de
f
i
ne
d
pa
r
a
m
e
t
e
r
s
pa
c
e
to
f
i
n
d
t
h
e
C
a
n
d
ga
m
m
a
v
a
l
ue
s
t
h
a
t
y
i
e
l
d
t
he
hi
g
h
e
s
t
c
l
a
s
s
i
f
i
c
a
t
i
o
n
a
c
c
ur
a
c
y
,
a
s
s
h
o
wn
i
n
T
a
ble
9.
T
a
bl
e
7
.
S
t
e
m
mi
ng
P
r
e
p
r
o
c
e
s
s
in
g
A
f
t
e
r
s
t
e
mm
in
g
St
e
m
m
in
g
“
bahagia
”
,
“
bange
t
”
,
“
de
k
”
“
pol
da
”
,
“
ant
is
ip
as
i
”
,
“
k
e
m
ac
e
ta
n
”
,
“
la
lu
”
,
“
li
nt
as
”
,
“
m
ot
og
p
”
,
“
m
andali
k
a
”
“
pe
r
tu
nj
uk
an
”
,
“
in
done
s
ia
”
,
“
ak
an
”
,
“
di
m
e
r
ia
hk
an
”
,
“
pe
nam
pi
la
n
”
,
“
ar
ti
s
”
,
“
nas
io
nal
”
“
di
to
nt
on
”
,
“
r
at
us
an
”
,
“
ju
ta
”
,
“
or
ang
”
,
“
duni
a
”
“
s
ia
pa
”
,
“
ja
di
”
,
“
pe
m
e
nang
”
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
“
ne
gar
a
”
,
“
s
e
ndi
r
i
”
,
“
de
bu
”
,
“
je
le
k
”
F
i
gur
e
2.
S
o
ur
c
e
c
o
de
o
f
t
e
x
t
pr
e
p
r
o
c
e
s
s
i
ng
T
a
bl
e
.
8
T
F
-
I
DF
Tf
Df
I
D
F
(
l
o
g
D
/d
f
)
W
D1
D2
D3
D1
D2
D3
1
0
0
1
0.85
0,85
0
0
0
1
0
1
0.85
0
0.28
0
0
1
0
1
0.85
0
0.28
0
0
1
0
1
0.85
0
0.28
0
0
0
1
1
0.85
0
0
0.28
0
0
1
1
0.37
0
0
0.12
0
0
1
1
0.37
0
0
0.12
F
i
gur
e
3.
S
o
ur
c
e
c
o
de
S
VM
P
S
O
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8776
I
n
t
J
I
n
f
&
C
o
m
m
u
n
T
e
c
hn
o
l
,
Vo
l
.
15
,
N
o.
2
,
J
un
e
20
26
:
523
-
534
53
0
T
a
bl
e
9
.
hy
p
e
r
pa
r
a
m
e
t
e
r
S
VM
P
S
O
B
e
s
t
h
y
p
e
r
pa
r
a
m
e
t
e
r
(
c
)
A
c
c
u
r
a
c
y
1,4347501497014852
0,818282
F
i
gur
e
4
s
h
o
ws
t
h
e
c
l
a
s
s
if
i
c
a
t
i
o
n
r
e
s
u
l
t
s
us
i
ng
t
h
e
o
r
i
g
i
na
l
S
VM
m
o
de
l
(
w
i
t
h
o
ut
o
p
t
i
m
i
z
a
t
i
o
n
)
.
B
a
s
e
d
o
n
t
h
e
s
e
r
e
s
u
l
t
s
,
t
h
e
m
o
de
l
c
o
r
r
e
c
t
l
y
pr
e
d
ict
e
d
50
i
ns
t
a
n
c
e
s
f
o
r
t
h
e
n
e
ga
t
i
v
e
c
l
a
s
s
,
191
c
a
s
e
s
f
o
r
t
h
e
m
e
ut
r
a
l
c
l
a
s
s
,
a
n
d
286
i
ns
t
a
n
c
e
s
f
o
r
t
h
e
P
o
s
i
t
i
v
e
c
l
a
s
s
.
T
h
e
s
e
r
e
s
u
l
t
s
i
n
d
i
c
a
t
e
t
h
a
t
c
l
a
s
s
if
i
c
a
t
i
o
n
a
c
c
ur
a
c
y
r
e
m
a
i
ns
li
mi
t
e
d,
pa
r
t
i
c
u
l
a
r
ly
i
n
t
h
e
n
e
g
a
t
i
ve
c
l
a
s
s
,
whi
c
h
h
a
s
t
h
e
l
o
we
s
t
tr
ue
pr
e
di
c
t
i
o
n
r
a
t
e
.
C
onv
e
r
s
e
ly
,
F
i
gur
e
5
s
h
o
ws
t
h
e
c
l
a
s
s
i
f
i
c
a
t
i
o
n
r
e
s
u
l
t
s
o
b
t
a
i
n
e
d
w
i
t
h
a
n
S
VM
m
o
de
l
o
pt
i
mi
z
e
d
u
s
i
ng
P
S
O.
I
n
t
hi
s
m
o
de
l
,
t
h
e
n
u
m
be
r
o
f
c
o
r
r
e
c
t
pr
e
di
c
t
i
o
n
s
h
a
s
i
nc
r
e
a
s
e
d
s
igni
f
i
c
a
n
t
l
y
:
105
f
o
r
t
h
e
n
e
ga
t
i
v
e
c
l
a
s
s
,
410
f
o
r
t
h
e
n
e
ut
r
a
l
c
l
a
s
s
,
a
n
d
531
f
o
r
t
h
e
p
o
s
i
t
i
ve
c
l
a
s
s
.
T
h
e
i
mpr
o
v
e
d
pe
r
f
o
r
m
a
n
c
e
a
c
r
o
s
s
t
h
e
c
l
a
s
s
de
m
o
n
s
t
r
a
t
e
d
t
h
a
t
im
p
l
e
m
e
n
t
i
n
g
t
h
e
P
S
O
a
l
go
r
i
t
hm
im
pr
o
v
e
d
t
h
e
qua
l
i
t
y
o
f
hy
pe
r
pa
r
a
m
e
t
e
r
s
e
l
e
c
t
i
o
n
i
n
S
VM
,
m
a
k
i
n
g
t
h
e
m
o
de
l
m
o
r
e
a
da
pt
a
bl
e
t
o
da
t
a
pa
tt
e
r
n
s
a
n
d
r
e
s
u
l
t
i
ng
i
n
hi
g
h
e
r
o
v
e
r
a
l
l
c
l
a
s
s
i
f
i
c
a
t
i
o
n
a
c
c
ur
a
c
y
.
F
i
gur
e
6
i
ll
us
t
r
a
t
e
s
t
h
a
t
a
ppl
yi
ng
t
h
e
P
S
O
m
e
t
h
o
d
a
s
a
n
o
p
t
i
m
i
z
a
t
i
o
n
a
l
go
r
i
t
hm
t
o
t
h
e
S
VM
m
o
de
l
yi
e
l
ds
a
s
i
g
nif
i
c
a
n
t
i
m
pr
o
v
e
m
e
n
t
i
n
c
l
a
s
s
if
i
c
a
t
i
o
n
pe
r
f
o
r
m
a
n
c
e
.
P
S
O
pl
a
y
s
a
r
o
l
e
i
n
f
i
nd
i
n
g
t
h
e
o
p
t
i
m
a
l
c
o
m
bi
na
t
i
o
n
o
f
hy
p
e
r
pa
r
a
m
e
t
e
r
s
,
i
nc
l
ud
i
ng
C
(
c
os
t
)
a
n
d
ot
h
e
r
ke
r
n
e
l
pa
r
a
m
e
t
e
r
s
t
h
a
t
a
f
f
e
c
t
t
h
e
m
a
r
g
i
n
o
f
s
e
pa
r
a
t
i
o
n
be
t
we
e
n
c
l
a
s
s
e
s
.
T
h
e
e
x
pe
r
im
e
n
t
a
l
r
e
s
u
l
t
s
s
h
o
we
d
t
h
a
t
P
S
O
s
uc
c
e
s
s
f
u
ll
y
i
m
pr
o
v
e
d
t
h
e
m
o
de
l
’
s
a
c
c
ur
a
c
y
c
o
m
pa
r
e
d
to
S
VM
s
r
un
wi
t
h
de
f
a
u
l
t
pa
r
a
m
e
t
e
r
s
o
r
wi
t
h
o
u
t
o
p
t
i
m
i
z
a
t
i
o
n
.
T
h
e
o
p
t
i
m
a
l
p
a
r
a
m
e
t
e
r
v
a
l
ue
f
o
u
n
d
i
s
1.
4347,
r
e
pr
e
s
e
n
t
i
n
g
t
h
e
o
pt
i
m
a
l
c
o
nf
i
gur
a
t
i
o
n
o
b
t
a
i
n
e
d
by
P
S
O
a
f
t
e
r
a
n
i
t
e
r
a
t
i
v
e
pr
o
c
e
s
s
to
i
de
n
t
i
f
y
t
h
e
b
e
s
t
s
o
l
ut
i
o
n
i
n
t
h
e
pa
r
a
m
e
t
e
r
s
pa
c
e
.
T
hi
s
i
nc
r
e
a
s
e
i
n
a
c
c
ur
a
c
y
s
ugg
e
s
t
s
t
h
a
t
pa
r
a
m
e
t
e
r
s
e
a
r
c
h
vi
a
P
S
O
c
a
n
b
e
t
t
e
r
t
a
i
l
o
r
t
h
e
m
o
de
l
to
t
h
e
da
t
a
’
s
c
h
a
r
a
c
t
e
r
i
s
t
i
c
s
,
r
e
s
u
l
t
i
n
g
i
n
m
o
r
e
pr
e
c
i
s
e
c
l
a
s
s
i
f
i
c
a
t
i
o
n
.
I
n
a
dd
i
t
i
o
n
,
i
t
i
n
d
i
c
a
t
e
s
t
h
a
t
S
VM
s
r
e
l
y
he
a
vil
y
o
n
pa
r
a
m
e
t
e
r
s
e
l
e
c
t
i
o
n
a
n
d
t
h
a
t
m
e
t
a
h
e
ur
i
s
t
i
c
-
b
a
s
e
d
a
pp
r
o
a
c
h
e
s
,
s
uc
h
a
s
P
S
O,
c
a
n
b
e
a
n
e
f
f
i
c
i
e
n
t
s
t
r
a
t
e
gy
f
o
r
i
mpr
o
vi
n
g
t
h
e
i
r
pe
r
f
o
r
m
a
nc
e
.
T
h
us
,
i
n
t
e
gr
a
t
i
n
g
P
S
O
i
n
t
o
t
h
e
S
VM
m
o
de
l
t
r
a
i
ni
ng
pr
o
c
e
s
s
n
o
t
o
nl
y
im
pr
o
v
e
s
n
u
m
e
r
i
c
a
l
a
c
c
ur
a
c
y
b
ut
a
l
s
o
de
m
o
n
s
t
r
a
t
e
s
t
h
a
t
a
n
o
p
t
i
mi
z
a
t
i
o
n
-
ba
s
e
d
a
ppr
o
a
c
h
c
a
n
e
nha
n
c
e
t
h
e
m
o
de
l
’
s
a
bil
i
t
y
t
o
c
a
p
t
ur
e
e
s
s
e
n
t
i
a
l
pa
t
t
e
r
n
s
i
n
t
h
e
da
t
a
,
pa
r
t
i
c
u
l
a
r
l
y
i
n
hi
g
h
-
c
o
m
p
l
e
xi
t
y
s
e
n
t
i
m
e
n
t
c
l
a
s
s
if
i
c
a
t
i
o
n
t
a
s
ks
.
F
i
gur
e
4.
C
o
nf
u
s
i
o
n
m
a
t
r
i
x
o
f
S
VM
o
r
i
g
i
na
l
F
i
gur
e
5.
C
o
nf
u
s
i
o
n
m
a
t
r
i
x
o
f
S
VM
P
S
O
T
h
e
r
e
s
ul
t
s
o
f
t
h
i
s
s
t
udy
de
m
o
n
s
tr
a
t
e
t
h
a
t
us
i
n
g
t
h
e
S
VM
m
e
t
h
o
d
to
c
l
a
s
s
i
f
y
s
e
n
t
i
m
e
n
t
i
n
s
p
o
r
t
s
e
v
e
n
t
t
e
x
t
da
t
a
,
wh
e
n
op
t
i
m
i
z
e
d
wi
t
h
P
S
O
,
y
i
e
l
d
s
i
m
pr
ov
e
d
pe
r
f
or
m
a
n
c
e
m
e
t
r
i
c
s
.
S
pe
c
i
f
i
c
a
l
ly
,
t
h
e
a
c
c
u
r
a
c
y
,
r
e
c
a
l
l
,
a
n
d
F1
-
s
c
o
r
e
i
n
c
r
e
a
s
e
d
to
8
1.
82%
,
79
.
9
%
,
a
n
d
79
.
6
2%
,
r
e
s
pe
c
t
i
v
e
l
y
.
I
n
c
o
n
tr
a
s
t,
t
h
e
pe
r
f
o
r
m
a
n
c
e
w
i
t
h
ou
t
P
S
O
y
i
e
l
de
d
l
o
we
r
m
e
t
r
i
c
s
:
80.
15
%
a
c
c
ur
a
c
y
,
7
5.
63
%
r
e
c
a
l
l
,
a
n
d
76.
89
%
F1
-
s
c
or
e
.
T
h
e
f
i
n
d
i
n
gs
o
f
t
h
i
s
s
tudy
a
l
i
g
n
wi
t
h
t
h
e
opi
ni
o
n
s
o
f
p
r
e
vi
o
us
r
e
s
e
a
r
c
h
[
2
7]
,
[
41
]
t
h
a
t
P
S
O
i
s
a
c
r
uc
i
a
l
a
s
pe
c
t
o
f
o
p
t
i
m
i
z
a
t
i
o
n
r
e
s
e
a
r
c
h
i
n
s
c
i
e
n
c
e
a
n
d
t
e
c
h
n
o
l
o
gy
,
a
s
de
m
o
n
s
tr
a
ted
b
y
t
h
i
s
s
t
u
dy
,
whi
c
h
s
h
o
ws
t
h
a
t
S
VM
wi
t
h
P
S
O
i
m
pr
o
v
e
s
S
VM
c
l
a
s
s
i
f
i
c
a
t
i
o
n
pe
r
f
or
m
a
n
c
e
.
I
n
a
ddi
t
i
o
n
,
t
h
i
s
s
t
u
dy
s
tr
e
n
g
t
h
e
n
s
t
h
e
l
i
t
e
r
a
tur
e
r
e
v
i
e
w
o
f
[
26
]
,
whi
c
h
s
ugg
e
s
t
s
t
h
a
t
t
h
e
us
e
o
f
o
p
t
i
m
i
z
a
t
i
o
n
t
e
c
h
ni
que
s
,
s
uc
h
a
s
P
S
O,
c
a
n
i
m
pr
o
v
e
t
h
e
pe
r
f
or
m
a
n
c
e
o
f
c
l
a
s
s
i
f
i
c
a
t
i
o
n
m
o
de
l
s
,
pa
r
t
i
c
u
l
a
r
l
y
f
o
r
t
h
e
S
VM
m
e
t
h
o
d
i
n
s
e
n
t
i
m
e
n
t
a
n
a
l
y
s
i
s
t
a
s
ks
.
T
h
i
s
r
e
s
e
a
r
c
h
i
s
uni
que
a
n
d
di
s
t
i
nc
t
f
r
o
m
pr
e
v
i
o
us
r
e
l
a
t
e
d
s
t
u
di
e
s
[
6]
,
[
8
]
,
[
1
2]
,
[
21]
,
[
26
]
–
[
3
4]
;
i
n
ot
h
e
r
w
or
ds
,
t
h
e
r
e
s
ul
t
s
o
f
t
h
i
s
r
e
s
e
a
r
c
h
a
r
e
n
o
v
e
l
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t
J
I
n
f
&
C
o
m
m
u
n
T
e
c
hn
o
l
I
S
S
N:
2252
-
8776
E
nhanc
ing
s
uppor
t
v
e
c
tor
mac
hine
pe
r
f
or
manc
e
us
ing
par
ti
c
le
s
w
ar
m
opti
miz
ati
on
…
(
C
h
r
is
tof
e
r
Satr
ia)
531
F
i
gur
e
6
.
C
o
m
pa
r
i
s
o
n
o
f
S
VM
a
n
d
S
VM
P
S
O
4.
CONC
L
USI
ON
AN
D
F
UT
UR
E
WORK
T
h
e
r
e
s
u
l
t
s
s
h
o
we
d
t
h
a
t
c
l
a
s
s
i
f
yi
ng
t
e
x
t
da
t
a
r
e
l
a
t
e
d
to
s
e
n
t
i
m
e
n
t
to
wa
r
ds
t
h
e
s
por
t
i
n
g
e
ve
n
t
i
n
to
t
h
r
e
e
c
l
a
s
s
e
s
-
po
s
i
t
i
ve
,
n
e
ut
r
a
l
,
a
n
d
n
e
ga
t
i
v
e
-
pr
o
duc
e
d
a
c
c
ur
a
c
y
,
r
e
c
a
l
l
,
a
n
d
F
1
-
s
c
o
r
e
o
f
81.
82%
,
79.
9%
,
a
n
d
79.
62%
,
r
e
s
pe
c
t
i
ve
ly
,
w
h
e
n
us
i
ng
t
h
e
S
VM
m
e
t
h
o
d
o
p
t
i
m
i
z
e
d
w
i
t
h
P
S
O.
M
e
a
n
w
hil
e
,
t
h
e
S
VM
m
e
t
h
o
d
w
i
t
h
o
ut
o
p
t
i
m
i
z
a
t
i
o
n
(
o
r
i
g
i
na
l
)
y
i
e
l
ds
a
c
c
ur
a
c
y
,
r
e
c
a
l
l
,
a
n
d
F1
-
s
c
o
r
e
s
o
f
80.
15
%
,
75.
63
%
,
a
n
d
76.
89
%
,
r
e
s
pe
c
t
i
ve
ly
.
T
hi
s
r
e
s
e
a
r
c
h
r
e
pr
e
s
e
n
t
s
a
n
e
w
s
t
udy
i
n
t
e
r
m
s
o
f
i
t
s
to
pi
c
s
,
r
e
s
e
a
r
c
h
o
bj
e
c
t
s
,
o
bj
e
c
t
i
v
e
s
,
a
n
d
r
e
s
u
l
t
s
,
whi
c
h
h
a
v
e
n
o
t
b
e
e
n
e
x
p
l
o
r
e
d
by
r
e
s
e
a
r
c
he
r
s
b
e
f
o
r
e
.
T
h
e
m
a
i
n
c
o
n
t
r
i
b
ut
i
o
n
o
f
t
hi
s
s
t
ud
y
i
s
t
o
r
e
v
e
a
l
t
h
e
s
e
n
t
i
m
e
n
t
o
f
us
e
r
X
t
o
wa
r
ds
t
h
e
e
v
e
n
t
i
n
M
a
n
d
a
l
i
ka
i
n
m
o
r
e
de
pt
h
by
c
l
a
s
s
if
yi
ng
o
pi
ni
o
ns
i
n
t
o
t
h
r
e
e
m
a
in
c
a
t
e
g
o
r
i
e
s
.
A
dd
i
t
i
o
n
a
ll
y
,
t
hi
s
s
t
ud
y
de
m
o
n
s
t
r
a
t
e
s
th
a
t
a
pp
l
yi
ng
P
S
O
c
a
n
s
i
g
nif
i
c
a
n
t
l
y
im
pr
o
v
e
t
h
e
a
c
c
ur
a
c
y
o
f
S
VM
f
o
r
s
e
n
t
i
m
e
n
t
c
l
a
s
s
i
f
i
c
a
t
i
o
n
.
T
hi
s
r
e
s
e
a
r
c
h
c
o
nf
i
r
m
s
t
h
a
t
S
VM
r
e
l
i
e
s
h
e
a
vil
y
o
n
a
ppr
o
pr
i
a
t
e
pa
r
a
m
e
t
e
r
s
e
l
e
c
t
i
o
n
a
n
d
t
h
a
t
m
e
t
a
h
e
ur
i
s
t
i
c
-
ba
s
e
d
a
ppr
o
a
c
h
e
s
s
uc
h
a
s
P
S
O
c
a
n
im
pr
o
v
e
i
t
s
pe
r
f
o
r
m
a
n
c
e
.
T
h
e
f
i
nd
i
ng
s
o
f
t
hi
s
s
t
udy
s
uppo
r
t
t
h
e
vi
e
w
s
o
f
pr
e
vi
o
us
r
e
s
e
a
r
c
he
r
s
wh
o
h
a
v
e
a
r
gue
d
t
h
a
t
P
S
O
i
s
a
c
r
uc
i
a
l
e
l
e
m
e
n
t
i
n
o
p
t
i
mi
z
a
t
i
o
n
r
e
s
e
a
r
c
h
w
i
t
hi
n
s
c
i
e
n
c
e
a
n
d
t
e
c
hn
o
l
o
g
y
.
T
hi
s
s
t
ud
y
de
m
o
n
s
t
r
a
t
e
s
t
h
a
t
us
i
n
g
P
S
O
wi
t
h
S
VM
c
a
n
i
m
pr
o
v
e
S
VM
c
l
a
s
s
if
i
c
a
t
i
o
n
pe
r
f
o
r
m
a
n
c
e
.
A
dd
i
t
i
o
n
a
ll
y
,
t
h
e
s
e
r
e
s
u
l
t
s
a
r
e
c
o
n
s
i
s
t
e
n
t
wi
t
h
e
a
r
l
i
e
r
li
t
e
r
a
t
ur
e
i
n
d
i
c
a
t
i
ng
t
h
a
t
P
S
O
c
a
n
i
m
pr
o
v
e
t
h
e
pe
r
f
o
r
m
a
n
c
e
o
f
m
a
c
hi
ne
l
e
a
r
ni
ng
c
l
a
s
s
if
i
c
a
t
i
o
n
m
o
de
l
s
.
T
h
e
we
a
k
n
e
s
s
o
f
t
hi
s
s
t
udy
is
t
h
a
t
i
t
o
nl
y
c
o
m
pa
r
e
s
t
h
e
or
i
g
i
na
l
S
V
M
w
i
t
h
t
h
e
S
VM
o
p
t
i
m
i
z
e
d
us
i
n
g
P
S
O.
F
ur
t
h
e
r
a
n
a
ly
s
i
s
w
i
t
h
di
v
e
r
s
e
o
bj
e
c
t
da
t
a
s
e
t
s
i
s
n
e
e
d
e
d
to
c
l
a
r
i
f
y
t
h
e
a
c
c
ur
a
c
y
d
if
f
e
r
e
n
c
e
s
b
e
t
we
e
n
t
h
e
S
VM
m
e
t
h
o
d
w
i
t
h
o
ut
P
S
O
a
n
d
t
h
e
S
VM
m
e
t
h
o
d
wi
t
h
P
S
O.
B
e
s
i
de
s
t
h
a
t
,
f
ur
t
h
e
r
r
e
s
e
a
r
c
h
pr
o
p
o
s
a
l
s
s
h
o
ul
d
c
o
m
pa
r
e
ot
h
e
r
m
a
c
hi
ne
l
e
a
r
ni
ng
m
e
t
h
o
ds
,
s
uc
h
a
s
Na
ï
v
e
B
a
y
e
s
a
n
d
r
a
n
do
m
f
o
r
e
s
t
,
b
ot
h
wi
t
h
o
ut
a
n
d
w
i
t
h
P
S
O
tr
e
a
t
m
e
n
t
.
T
o
de
t
e
r
mi
ne
t
h
e
e
x
t
e
n
t
o
f
o
p
t
i
mi
z
a
t
i
o
n
i
n
a
c
c
ur
a
c
y
,
r
e
c
a
l
l
,
a
n
d
F
1
-
s
c
o
r
e
us
i
n
g
P
S
O
o
n
v
a
r
i
o
us
m
a
c
hi
ne
l
e
a
r
ni
ng
m
e
t
h
o
ds
.
I
n
a
dd
i
t
i
o
n
,
i
t
i
s
n
e
c
e
s
s
a
r
y
t
o
c
o
n
duc
t
f
ur
t
h
e
r
r
e
s
e
a
r
c
h
by
a
pp
lyi
ng
ot
h
e
r
o
p
t
i
m
i
z
a
t
i
o
n
m
e
t
h
o
ds
,
s
uc
h
a
s
ge
n
e
t
i
c
a
l
go
r
i
t
hm
,
gr
i
d
s
e
a
r
c
h
,
o
r
b
a
y
e
s
i
a
n
o
p
t
i
mi
z
a
t
i
o
n
,
to
c
o
m
pa
r
e
a
n
d
de
t
e
r
m
i
ne
t
h
e
be
s
t
o
p
t
i
mi
z
a
t
i
o
n
m
e
t
h
o
d
a
n
d
to
de
t
e
r
m
i
ne
w
hi
c
h
m
a
c
hi
ne
l
e
a
r
ni
ng
m
e
t
h
o
d
to
us
e
.
F
UN
DI
NG
I
N
F
ORM
AT
I
ON
A
ut
h
o
r
s
s
t
a
t
e
n
o
f
u
n
d
i
ng
i
nv
o
l
v
e
d.
AU
T
HO
R
CONT
RI
B
UT
I
ONS
S
T
AT
E
M
E
NT
T
hi
s
j
o
ur
n
a
l
u
s
e
s
t
h
e
C
o
n
t
r
i
b
ut
or
R
o
l
e
s
T
a
x
o
n
o
m
y
(
C
R
e
d
i
T
)
to
r
e
c
o
gni
z
e
i
n
d
i
v
i
dua
l
a
ut
h
o
r
c
o
n
t
r
i
b
ut
i
o
ns
,
r
e
duc
e
a
ut
h
or
s
hi
p
d
i
s
put
e
s
,
a
n
d
f
a
c
il
i
t
a
t
e
c
o
l
l
a
b
o
r
a
t
i
o
n
.
Nam
e
of
Aut
h
or
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
C
h
r
i
s
t
o
f
e
r
S
a
t
r
i
a
An
t
h
o
ny
An
ggr
a
wa
n
P
e
t
e
r
W
i
j
a
y
a
S
ug
ij
a
n
t
o
Hus
a
i
n
Hu
s
a
i
n
I
Ny
o
m
a
n
Yo
ga
S
u
m
a
de
wa
V
i
c
t
o
r
i
a
C
y
n
t
hi
a
R
e
b
e
c
c
a
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8776
I
n
t
J
I
n
f
&
C
o
m
m
u
n
T
e
c
hn
o
l
,
Vo
l
.
15
,
N
o.
2
,
J
un
e
20
26
:
523
-
534
532
C
:
C
o
n
c
e
pt
ua
li
z
a
ti
o
n
M
:
M
e
th
o
d
o
l
o
g
y
So
:
So
f
twa
r
e
Va
:
Va
li
da
ti
o
n
Fo
:
Fo
r
ma
l
a
na
l
y
s
is
I
:
I
nve
s
ti
ga
ti
o
n
R
:
R
e
s
o
u
r
c
e
s
D
:
D
a
ta
C
ur
a
ti
o
n
O
:
W
r
it
in
g
-
O
r
ig
in
a
l
D
r
a
f
t
E
:
W
r
it
in
g
-
R
e
v
i
e
w
&
E
d
it
in
g
Vi
:
Vi
s
ua
li
z
a
ti
o
n
Su
:
Su
pe
r
v
is
io
n
P
:
P
r
o
j
e
c
t
a
dmi
ni
s
tr
a
ti
o
n
Fu
:
Fu
ndi
ng a
c
qui
s
it
i
o
n
CONF
L
I
CT
OF
I
NT
E
RE
S
T
S
T
AT
E
M
E
NT
T
h
e
a
ut
h
o
r
s
s
t
a
t
e
n
o
c
o
n
f
li
c
t
o
f
i
n
t
e
r
e
s
t
.
DA
T
A
AV
AI
L
AB
I
L
I
T
Y
T
h
e
da
t
a
us
e
d
i
n
t
hi
s
s
t
ud
y
c
a
n
b
e
a
c
c
e
s
s
e
d
a
t
t
h
e
f
o
l
l
o
w
i
ng
l
i
nk:
h
t
t
ps
:/
/s
h
o
r
t
ur
l
.
a
t
/dal
3
F
.
RE
F
E
R
E
NC
E
S
[
1]
M
.
W
a
nkha
de
,
A
.
C
.
S
.
R
a
o
,
a
nd
C
.
K
ul
ka
r
ni
,
“
A
s
ur
v
e
y
o
n
s
e
nt
im
e
nt
a
na
l
y
s
is
m
e
th
o
ds
,
a
ppl
ic
a
ti
o
ns
,
a
nd
c
ha
ll
e
ng
e
s
,
”
A
r
ti
f
ic
ia
l
I
nt
e
ll
ig
e
nc
e
R
e
v
ie
w
, vo
l.
55, n
o
. 7, pp. 5731
–
5780, O
c
t.
2022, d
o
i:
10.1007/s
10462
-
022
-
10144
-
1.
[
2]
M
.
Z
.
A
s
gha
r
,
A
.
K
ha
n,
A
.
B
ib
i,
F
.
M
.
K
und
i,
a
nd
H
.
A
hma
d,
“
S
e
nt
e
n
c
e
-
l
e
ve
l
e
m
o
ti
o
n
de
t
e
c
ti
o
n
f
r
a
m
e
w
o
r
k
us
in
g
r
ul
e
-
ba
s
e
d
c
la
s
s
if
i
c
a
ti
o
n,
”
Co
gni
ti
v
e
C
om
put
at
io
n
, vo
l.
9, n
o
. 6, pp. 868
–
8
94, De
c
. 2017, d
oi
:
10.1007/s
12559
-
017
-
9503
-
3.
[
3]
A
.
S
.
T
a
la
a
t,
“
S
e
nt
i
me
nt
a
na
l
y
s
is
c
la
s
s
if
ic
a
ti
o
n
s
y
s
t
e
m
us
in
g
h
y
br
id
B
E
R
T
m
o
de
ls
,
”
J
our
nal
of
B
ig
D
at
a
,
vol
.
10,
n
o
.
1,
p.
1
10,
J
un. 2023, do
i:
10.1186/s
40537
-
0
23
-
00781
-
w.
[
4]
M
.
Á
gua
,
N
.
A
nt
óni
o
,
P
.
C
a
r
r
a
s
c
o
,
a
nd
C
. R
a
s
s
a
l,
“
L
a
r
ge
la
ngua
ge
mo
d
e
ls
po
w
e
r
e
d
a
s
pe
c
t
-
ba
s
e
d
s
e
nt
im
e
nt
a
na
l
y
s
is
f
or
e
nha
n
c
e
d
c
us
to
me
r
i
ns
ig
ht
s
,
”
T
our
is
m
and M
anage
m
e
nt
St
udi
e
s
, v
o
l.
21,
no
. 1, pp. 1
–
19, 2025, d
o
i:
10.18089/t
ms
.202501011.
[5
]
O
. A
ls
e
ma
r
e
e
, A
. S
.
A
la
m, S
. S
.
G
i
ll
, a
nd S
. U
hl
ig
,
“
S
e
nt
i
me
nt
a
na
l
y
s
is
of
A
r
a
bi
c
s
oc
ia
l
m
e
di
a
t
e
x
ts
:
a
ma
c
hi
n
e
l
e
a
r
ni
ng a
ppr
oa
c
h
to
d
e
c
ip
he
r
in
g
c
us
to
m
e
r
pe
r
c
e
pt
i
o
ns
,
”
H
e
li
y
on
, vo
l.
10, n
o
. 9, p
. e
27863, M
a
y
2024, d
o
i:
10.1016/
j.
he
l
i
y
on.2024.e
27863.
[
6]
A
.
C
ho
ur
a
s
i
y
a
,
A
.
K
ha
n,
K
.
B
a
ja
j,
M
.
T
o
ma
r
,
T
.
K
o
hl
i,
a
nd
D
.
C
ha
uha
n,
“
A
r
e
v
i
e
w
of
s
e
nt
im
e
nt
a
na
l
y
s
is
a
nd
e
m
o
ti
o
n
d
e
t
e
c
ti
o
n
f
r
o
m
t
e
x
t
us
in
g
di
f
f
e
r
e
nt
m
o
de
ls
,
”
I
nt
e
r
nat
io
nal
J
our
nal
of
E
ngi
ne
e
r
in
g
A
ppl
ie
d
Sc
ie
nc
e
and
M
anage
m
e
nt
I
SSN
,
vo
l.
6,
n
o
.
1,
pp. 258
2
–
6948, 2025.
[
7]
X
.
L
iu
,
R
.
L
i,
S
.
Y
e
,
G
.
Z
ha
ng,
a
nd
X
.
W
a
ng,
“
M
ul
ti
m
o
da
l
a
s
pe
c
t
-
ba
s
e
d
s
e
nt
im
e
nt
a
na
l
y
s
is
unde
r
c
o
ndi
ti
o
na
l
r
e
la
ti
o
n,
”
in
P
r
oc
e
e
di
ngs
-
I
nt
e
r
nat
io
nal
C
onf
e
r
e
nc
e
on
C
om
put
at
io
nal
L
in
gui
s
ti
c
s
, C
O
L
I
N
G
, 2025, pp. 313
–
323.
[
8]
Z
.
Z
ha
o
a
nd
S
.
Y
a
ng,
“
R
e
s
e
a
r
c
h
o
n
r
e
d
c
ul
tu
r
a
l
in
h
e
r
it
a
n
c
e
a
nd
a
ppl
ic
a
ti
o
n
of
S
V
M
s
uppo
r
t
ve
c
t
or
,
”
A
ppl
ie
d
M
at
he
m
at
ic
s
and
N
onl
in
e
ar
Sc
ie
nc
e
s
, v
o
l.
10, n
o
. 1, pp. 1
–
18, 2025.
[
9]
M
.
A
.
J
.
E
lj
a
ti
n,
R
.
W
.
S
.
S
uma
di
na
ta
,
a
nd
D
.
S
.
S
a
r
i,
“
S
p
or
t
s
a
nd
c
ul
tu
r
a
l
di
pl
o
ma
c
y
in
te
g
r
a
t
i
o
n
in
p
o
s
t
-
pa
nde
mi
c
C
O
V
I
D
-
19
in
te
r
na
ti
o
na
l
e
ve
nt
s
:
e
v
id
e
n
c
e
f
r
o
m
I
nd
o
n
e
s
ia
’
s
M
o
t
oG
P
M
a
nda
li
ka
2022,
”
D
ae
ngk
u:
J
our
nal
of
H
um
ani
ti
e
s
and
Soc
ia
l
Sc
ie
nc
e
s
I
nnov
at
io
n
, vo
l.
5, n
o
. 1, pp. 113
–
120,
F
e
b. 2025, d
oi
:
10.3587
7/
454R
I
.da
e
ngku3745.
[
10]
H
.
Q
.
L
o
w
,
P
.
K
e
ik
h
o
s
r
o
ki
a
ni
,
a
nd
M
.
P
.
A
s
l,
“
D
e
c
o
di
ng
vi
o
l
e
n
c
e
a
ga
in
s
t
w
o
m
e
n:
a
na
l
y
s
in
g
ha
r
a
s
s
me
nt
in
mi
ddl
e
e
a
s
t
e
r
n
li
te
r
a
tu
r
e
w
it
h
ma
c
hi
n
e
le
a
r
n
in
g
a
nd
s
e
nt
im
e
nt
a
na
l
y
s
is
,
”
H
um
ani
ti
e
s
and
Soc
ia
l
Sc
ie
nc
e
s
C
om
m
uni
c
at
io
ns
,
v
o
l.
11,
no
.
1,
p.
497,
A
pr
. 2024, do
i:
10.1057
/s
41599
-
024
-
02908
-
7.
[
11]
N
.
A
.
S
e
ma
r
y
,
W
.
A
hm
e
d,
K
.
A
mi
n,
P
.
P
ła
w
ia
k,
a
nd
M
.
H
a
mm
a
d,
“
E
nha
nc
in
g
ma
c
hi
n
e
l
e
a
r
ni
ng
-
ba
s
e
d
s
e
nt
im
e
nt
a
na
l
y
s
is
th
r
o
ugh
f
e
a
tu
r
e
e
x
t
r
a
c
ti
o
n t
e
c
hni
qu
e
s
,
”
P
L
O
S O
N
E
,
vo
l.
19, n
o
.
2, p. e
0294968, F
e
b. 2024, d
o
i:
10.1371/j
o
u
r
na
l.
po
n
e
.0
294968.
[
12
]
A
.
A
nggr
a
w
a
n,
C
.
S
a
tr
ia
,
H
.
W
a
r
dha
na
,
P
.
W
.
S
ugi
ja
nt
o
,
A
.
D
.
D
a
y
a
ni
,
a
nd
A
.
S
.
A
bdi
,
“
C
o
mpa
r
is
o
n
of
s
e
nt
im
e
nt
a
na
l
y
s
is
e
v
a
lu
a
ti
o
n
r
e
ga
r
d
in
g
in
te
r
na
ti
o
na
l
mo
bi
l
e
e
qui
pm
e
nt
id
e
nt
i
t
y
bl
oc
ki
ng
be
tw
e
e
n
th
e
K
-
n
e
a
r
e
s
t
ne
ig
hb
o
r
a
nd
s
uppo
r
t
ve
c
t
o
r
ma
c
h
in
e
m
e
th
o
ds
,
”
in
2024
5t
h
I
nt
e
r
nat
io
nal
C
on
f
e
r
e
nc
e
on
C
om
put
at
io
nal
S
c
ie
nc
e
&
am
p;
I
nf
or
m
at
io
n
M
anage
m
e
nt
(
I
C
oC
SI
M
)
, I
E
E
E
, O
c
t.
2024, pp. 193
–
199. d
o
i
:
10.1109/I
C
o
C
S
I
M
65098.2024.00003.
[
13]
V
. E
c
ha
mba
di
a
nd I
.
H
ig
h,
“
F
in
a
n
c
ia
l
ma
r
ke
t
s
e
nt
im
e
nt
a
na
l
y
s
i
s
us
in
g L
L
M
a
nd R
A
G
,
”
J
our
nal
SSR
N
, pp. 1
–
7, 2025.
[
14]
A
.
A
nggr
a
w
a
n,
C
.
S
a
tr
ia
,
C
.
K
.
N
ur
a
in
i,
L
.
-
,
N
.
G
.
A
.
D
a
s
r
ia
n
i,
a
nd
M
.
-
,
“
M
a
c
hi
ne
le
a
r
ni
ng
f
or
di
a
gn
o
s
in
g
dr
ug
us
e
r
s
a
nd
t
y
p
e
s
of
d
r
ugs
us
e
d,
”
I
nt
e
r
nat
io
nal
J
our
nal
o
f
A
dv
anc
e
d
C
om
put
e
r
Sc
ie
nc
e
and
A
ppl
ic
at
io
ns
,
vo
l.
12,
no
.
11,
pp.
111
–
118,
2
021,
do
i:
10.14569/
I
J
A
C
S
A
.2021.0121113.
[
15]
D
.
R
if
a
ld
i
e
t
al
.
,
“
M
a
c
hi
ne
le
a
r
ni
ng
5.0:
in
-
d
e
pt
h
a
na
l
y
s
is
tr
e
nd
s
in
c
la
s
s
if
ic
a
ti
o
n,
”
Sc
ie
nt
if
ic
J
our
nal
of
C
om
put
e
r
Sc
ie
n
c
e
,
v
o
l
.
1,
no
. 1, pp. 1
–
15, 2025, d
o
i:
10.64539
/s
j
c
s
.v
1i
1.2025.18.
[
16]
P
.
G
ul
e
r
ia
,
S
.
A
hm
e
d,
A
.
A
lh
uma
m,
a
nd
P
.
N
.
S
r
in
i
v
a
s
u,
“
E
mpi
r
ic
a
l
s
tu
d
y
o
n
c
la
s
s
if
i
e
r
s
f
or
e
a
r
li
e
r
pr
e
di
c
ti
o
n
of
C
O
V
I
D
-
19
in
f
e
c
ti
o
n
c
ur
e
a
nd
d
e
a
th
r
a
te
in
th
e
I
ndi
a
n
S
ta
te
s
,
”
H
e
al
th
c
ar
e
,
v
o
l.
10,
n
o
.
1,
p.
85,
J
a
n.
2022,
do
i:
10.3
390/
he
a
lt
h
c
a
r
e
10010085.
[
17]
A
.
A
lq
a
r
ni
,
“
A
s
upp
o
r
t
ve
c
t
o
r
ma
c
hi
n
e
(
S
V
M
)
m
o
d
e
l
f
o
r
pr
i
va
c
y
r
e
c
o
mm
e
ndi
ng
da
ta
p
r
o
c
e
s
s
in
g
m
o
d
e
l
(
P
R
D
P
M
)
i
n
in
te
r
n
e
t
of
ve
hi
c
le
s
,
”
C
om
put
e
r
, M
at
e
r
ia
ls
&
C
ont
in
ua
, vo
l.
82, n
o
. 1, pp.
389
–
406, 2024, do
i:
10.48084/
e
ta
s
r
.7743.
[
18
]
T
.
K
a
v
z
o
g
lu
,
F
.
B
il
u
c
a
n,
a
nd
A
.
T
e
k
e
,
“
C
o
mpa
r
is
o
n
of
s
upp
o
r
t
ve
c
t
o
r
ma
c
hi
n
e
s
,
r
a
ndo
m
f
or
e
s
t
a
nd
de
c
is
io
n
t
r
e
e
m
e
th
o
ds
f
o
r
c
la
s
s
if
i
c
a
ti
o
n
of
s
e
nt
in
e
l
-
2A
im
a
ge
us
in
g
di
f
f
e
r
e
n
t
ba
nd
c
ombi
na
ti
o
ns
,
”
in
A
C
R
S
2020
-
41s
t
A
s
ia
n
C
onf
e
r
e
n
c
e
on
R
e
m
ot
e
Se
ns
in
g
, 20
20.
[
19]
M
.
S
he
y
khm
o
us
a
,
M
.
M
a
hdi
a
npa
r
i,
H
.
G
ha
nba
r
i,
F
.
M
o
ha
mm
a
di
ma
ne
s
h,
P
.
G
ha
mi
s
i,
a
nd
S
.
H
oma
y
o
uni
,
“
S
upp
o
r
t
ve
c
t
o
r
ma
c
hi
ne
ve
r
s
us
r
a
nd
o
m
f
or
e
s
t
f
o
r
r
e
m
o
t
e
s
e
ns
in
g
im
a
ge
c
la
s
s
if
i
c
a
ti
o
n:
a
m
e
ta
-
a
na
l
y
s
is
a
nd
s
y
s
te
ma
ti
c
r
e
v
i
e
w
,
”
I
E
E
E
J
our
nal
of
Se
le
c
te
d
T
opi
c
s
in
A
ppl
ie
d
E
ar
th
O
bs
e
r
v
at
io
n
s
and
R
e
m
ot
e
Se
ns
in
g
,
v
o
l.
13,
pp.
6308
–
6325,
2020,
do
i:
10.1109/J
S
T
A
R
S
.2020.3026724.
[
20]
S
.
X
u,
H
.
W
u,
J
.
L
u
o
,
J
.
C
he
n,
a
nd
H
.
J
ia
,
“
T
h
e
a
ppl
ic
a
ti
o
n
of
s
upp
o
r
t
ve
c
t
o
r
ma
c
hi
n
e
(
S
V
M
)
in
in
dus
tr
ia
l
c
a
r
b
o
n
a
c
c
o
un
ti
ng
pr
e
di
c
t
i
o
n
a
nd
gr
e
e
n
e
l
e
c
t
r
i
c
it
y
c
o
nt
r
o
l
s
tr
a
te
gi
e
s
,
”
E
3S
W
e
b
of
C
on
f
e
r
e
nc
e
s
,
v
o
l.
615,
p.
01012,
F
e
b.
2025,
do
i:
10.1051/e
3s
c
o
n
f
/2
02561501012.
[
21]
P
.
C
.
S
o
ga
s
,
I
.
F
.
M
o
li
na
,
À
.
A
.
B
a
tl
le
,
a
nd
J
.
M
.
R
.
V
íl
c
he
z
,
“
E
c
o
n
o
mi
c
a
nd
s
o
c
ia
l
y
i
e
ld
of
in
ve
s
ti
ng
in
a
s
po
r
ti
ng
e
ve
nt
:
s
us
ta
in
a
bl
e
v
a
lu
e
c
r
e
a
ti
o
n i
n a
t
e
r
r
it
o
r
y
,
”
Sus
ta
in
abi
li
ty
,
vo
l.
13,
no
. 13, p. 7033, 2021, d
o
i:
10.3390/s
u13137033.
Evaluation Warning : The document was created with Spire.PDF for Python.