I
AE
S
I
nte
rna
t
io
na
l J
o
urna
l o
f
Art
if
icia
l In
t
ellig
ence
(
I
J
-
AI
)
Vo
l.
13
,
No
.
4
,
Dec
em
b
er
2
0
2
4
,
p
p
.
4
9
4
8
~
4
9
5
6
I
SS
N:
2
2
5
2
-
8
9
3
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijai.v
13
.i
4
.
p
p
4
9
4
8
-
4
9
5
6
4948
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
i
.
ia
esco
r
e.
co
m
Indo
nesia
n senti
ment
towa
rds g
lo
ba
l econo
mic rece
ss
io
n in 20
2
3
using
optimized
h
y
perpa
ra
meters o
f
supp
o
rt
vector
ma
chine
kernels
Da
ira
t
ul M
a
a
rif
,
Adin
da
Au
lia
H
a
f
izha
,
Andi
K
urnia
wa
n
D
e
p
a
r
t
me
n
t
o
f
I
n
t
e
r
n
a
t
i
o
n
a
l
R
e
l
a
t
i
o
n
s
,
F
a
c
u
l
t
y
o
f
S
o
c
i
a
l
a
n
d
P
o
l
i
t
i
c
a
l
S
c
i
e
n
c
e
s,
U
n
i
v
e
r
si
t
a
s P
e
mb
a
n
g
u
n
a
n
N
a
s
i
o
n
a
l
V
e
t
e
r
a
n
Ja
k
a
r
t
a
,
Jak
a
r
t
a
,
I
n
d
o
n
e
si
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
n
1
4
,
2
0
2
3
R
ev
is
ed
Ma
r
6
,
2
0
2
4
Acc
ep
ted
Ap
r
1
4
,
2
0
2
4
Th
e
p
o
te
n
ti
a
l
fo
r
t
h
e
2
0
2
3
g
lo
b
a
l
re
c
e
ss
io
n
h
a
s
tro
u
b
le
d
p
e
o
p
le
wo
rld
wi
d
e
,
p
a
rti
c
u
larly
in
l
ig
h
t
o
f
th
e
CO
VID
-
1
9
p
a
n
d
e
m
ic.
Th
is
st
u
d
y
e
m
p
lo
y
s
a
se
n
ti
m
e
n
t
a
n
a
ly
sis
a
p
p
r
o
a
c
h
to
e
x
a
m
in
e
h
o
w
th
e
I
n
d
o
n
e
sia
n
in
tern
e
t
c
o
m
m
u
n
it
y
,
p
a
rti
c
u
larly
o
n
Twit
t
e
r,
p
e
rc
e
iv
e
s
th
e
to
p
ics
re
late
d
to
th
e
g
l
o
b
a
l
e
c
o
n
o
m
ic
re
c
e
ss
io
n
.
We
c
o
ll
e
c
ted
1
1
,
0
1
7
u
p
lo
a
d
e
d
twe
e
ts
th
a
t
we
re
a
n
a
ly
z
e
d
u
sin
g
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
c
las
sifier
with
li
n
e
a
r,
r
a
d
ial
b
a
sis
fu
n
c
ti
o
n
(RBF
)
,
sig
m
o
id
,
a
n
d
p
o
ly
n
o
m
ial
k
e
r
n
e
l
sc
h
e
m
e
s.
F
u
rth
e
rm
o
re
,
we
o
p
ti
m
ize
d
th
e
c
las
sifiers
with
C,
G
a
m
m
a
,
a
n
d
d
e
g
re
e
h
y
p
e
rp
a
ra
m
e
ters
.
Emp
iri
c
a
l
e
v
id
e
n
c
e
in
d
ica
tes
a
lac
k
o
f
p
re
p
a
re
d
n
e
ss
to
fa
c
e
a
g
lo
b
a
l
re
c
e
ss
io
n
,
e
v
i
d
e
n
c
e
d
b
y
m
o
st
r
e
sp
o
n
se
s
t
o
wa
rd
s
2
0
2
3
g
l
o
b
a
l
re
c
e
ss
io
n
e
x
h
ib
it
in
g
c
o
n
c
e
rn
s
a
b
o
u
t
h
ig
h
in
flati
o
n
a
n
d
e
c
o
n
o
m
ic
i
n
sta
b
il
it
y
.
T
h
e
fin
d
i
n
g
a
lso
su
g
g
e
sts
th
a
t
th
e
o
p
t
imiz
e
d
RBF
is
a
su
p
e
ri
o
r
m
o
d
e
li
n
g
k
e
rn
e
l
re
lativ
e
t
o
o
th
e
rs.
Co
ll
e
c
ti
v
e
ly
,
t
h
e
se
re
su
lt
s
p
r
o
v
id
e
in
si
g
h
ts
with
s
ig
n
ifi
c
a
n
t
imp
li
c
a
ti
o
n
s
f
o
r
se
n
ti
m
e
n
t
a
n
a
ly
sis,
n
a
tu
ra
l
lan
g
u
a
g
e
p
r
o
c
e
ss
in
g
,
a
n
d
t
h
e
stu
d
y
o
f
b
e
h
a
v
io
u
ra
l
e
c
o
n
o
m
ic
s.
K
ey
w
o
r
d
s
:
Glo
b
al
r
ec
ess
io
n
Ker
n
els
Op
tim
ized
h
y
p
e
r
p
ar
am
ete
r
s
Sen
tim
en
t a
n
aly
s
is
Su
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
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
:
Ad
in
d
a
Au
lia
Haf
izh
a
Dep
ar
tm
en
t o
f
I
n
ter
n
atio
n
al
R
elatio
n
s
,
Facu
lty
o
f
So
cial
an
d
Po
liti
ca
l Scie
n
ce
s
Un
iv
er
s
itas
Pem
b
an
g
u
n
an
Nasio
n
al
Vete
r
an
J
ak
ar
ta
R
S.
Fatm
awa
ti
Stre
et,
Po
n
d
o
k
L
ab
u
,
So
u
th
J
ak
ar
ta
1
2
4
5
0
,
I
n
d
o
n
esia
E
m
ail: h
af
izh
ad
in
d
a@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
I
n
r
ec
en
t
y
ea
r
s
,
ec
o
n
o
m
ic
r
ec
ess
io
n
h
as
h
ad
s
ig
n
if
ican
t
n
eg
ativ
e
im
p
ac
ts
o
n
th
e
g
lo
b
al
c
o
m
m
u
n
ity
,
n
o
tab
ly
h
ig
h
lig
h
ted
b
y
th
e
f
ar
-
r
ea
ch
in
g
co
n
s
eq
u
en
ce
s
o
f
th
e
2
0
0
8
g
lo
b
al
f
in
an
cial
c
r
is
is
o
n
ec
o
n
o
m
ies
wo
r
ld
wid
e.
Sin
ce
2
0
1
9
,
th
e
C
OVI
D
-
1
9
p
an
d
em
ic
h
as
d
ir
ec
t
ly
im
p
ac
ted
v
ar
io
u
s
ec
o
n
o
m
ic
asp
ec
ts
,
g
iv
en
th
at
th
e
r
elate
d
s
h
u
td
o
wn
s
m
a
n
d
at
ed
b
y
th
e
g
o
v
e
r
n
m
en
t
p
r
o
d
u
c
ed
a
m
o
m
en
t
o
u
s
s
h
o
ck
to
t
h
e
g
lo
b
al
ec
o
n
o
m
y
as
well
as
an
ex
ce
s
s
iv
e
lo
s
s
o
f
em
p
lo
y
m
e
n
t
th
at
h
ea
v
il
y
af
f
ec
t
ed
th
e
wo
r
k
in
g
class
[
1
]
.
Fu
r
t
h
er
m
o
r
e
,
g
iv
e
n
th
e
tig
h
ten
in
g
f
in
an
cial
c
o
n
d
itio
n
s
in
m
an
y
r
e
g
io
n
s
,
d
eb
ates
r
e
g
ar
d
in
g
g
lo
b
al
ec
o
n
o
m
ic
r
ec
e
s
s
io
n
ar
e
in
ev
itab
le,
esp
ec
ially
in
I
n
d
o
n
esia w
ith
2
7
7
m
illi
o
n
in
h
ab
itan
ts
.
Deb
ates
r
eg
ar
d
in
g
th
e
2
0
2
3
g
lo
b
al
ec
o
n
o
m
ic
r
ec
ess
io
n
in
I
n
d
o
n
esia
ar
e
f
ier
ce
ly
a
r
g
u
e
d
i
n
T
witter
.
So
m
e
T
witter
u
s
er
s
f
ee
l
o
p
ti
m
is
tic
th
at
I
n
d
o
n
esia
will
n
o
t
b
e
s
u
b
jecte
d
to
ec
o
n
o
m
ic
r
ec
ess
io
n
in
2
0
2
3
b
ec
au
s
e
f
ew
ec
o
n
o
m
ic
in
d
ic
ato
r
s
f
o
r
I
n
d
o
n
esia
s
h
o
w
p
r
o
m
is
in
g
r
esu
lts
.
Ho
wev
er
,
a
cc
o
r
d
in
g
to
o
th
e
r
s
,
I
n
d
o
n
esia
will
b
e
s
u
b
ject
to
p
r
o
g
r
ess
iv
ely
“
d
a
r
k
”
g
lo
b
al
u
n
ce
r
tain
ties
in
2
0
2
3
,
c
o
n
v
e
y
ed
b
y
th
e
d
ec
r
ea
s
e
i
n
p
eo
p
le’
s
p
u
r
c
h
asin
g
p
o
wer
an
d
th
e
I
n
d
o
n
esia
co
m
p
o
s
ite
in
d
ex
(
I
C
I
)
d
u
e
to
th
e
C
OVI
D
-
1
9
p
an
d
e
m
ic.
T
h
is
co
n
tr
o
v
e
r
s
ial
d
eb
ate
co
n
tin
u
e
s
to
s
p
r
ea
d
,
wh
ich
in
tu
r
n
f
o
r
m
ed
v
a
r
io
u
s
p
u
b
lic
o
p
in
i
o
n
s
with
co
n
f
lictin
g
v
iews.
E
co
n
o
m
is
ts
an
d
d
ec
is
io
n
-
m
ak
e
r
s
m
ay
f
in
d
th
is
d
eb
a
te
co
n
ce
r
n
in
g
s
in
ce
p
u
b
lic
o
p
i
n
io
n
h
as
th
e
p
o
wer
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
I
n
d
o
n
esia
n
s
en
timen
t to
w
a
r
d
s
g
lo
b
a
l e
c
o
n
o
mic
r
ec
ess
io
n
in
2
0
2
3
u
s
in
g
o
p
timiz
ed
…
(
Da
ir
a
tu
l Ma
a
r
if)
4949
to
im
p
ac
t
m
ac
r
o
ec
o
n
o
m
ics
an
d
th
e
s
tate
o
f
th
e
wo
r
ld
ec
o
n
o
m
y
.
T
h
is
s
u
p
p
o
r
ts
Ak
er
lo
f
'
s
co
n
ten
tio
n
th
at
th
e
in
clu
s
io
n
o
f
s
o
cial
an
d
p
s
y
ch
o
lo
g
ical
v
iewp
o
in
ts
wo
u
l
d
f
a
cilitate
a
b
etter
u
n
d
er
s
tan
d
in
g
o
f
s
o
m
e
ec
o
n
o
m
ic
ev
en
ts
[
2
]
.
P
r
e
v
i
o
u
s
s
t
u
d
i
es
h
a
v
e
e
x
a
m
i
n
ed
p
u
b
l
i
c
o
p
i
n
i
o
n
s
o
n
e
c
o
n
o
m
i
c
i
s
s
u
e
s
.
W
i
e
l
e
n
a
n
d
B
a
r
r
i
o
s
[
3
]
u
s
e
d
d
a
t
a
f
r
o
m
G
o
o
g
l
e
T
r
e
n
d
s
t
o
i
d
e
n
t
if
y
a
s
i
g
n
i
f
i
c
a
n
t
c
h
a
n
g
e
i
n
e
c
o
n
o
m
i
c
a
t
ti
t
u
d
e
s
d
u
r
i
n
g
t
h
e
C
O
V
I
D
-
1
9
c
r
is
is
a
n
d
s
u
b
s
e
q
u
e
n
t
l
o
c
k
d
o
w
n
i
n
t
h
e
E
u
r
o
p
e
a
n
U
n
i
o
n
.
A
d
d
i
ti
o
n
a
l
l
y
,
C
a
r
o
s
i
a
et
a
l
.
[
4
]
a
n
a
l
y
ze
d
s
en
t
i
m
e
n
t
s
r
e
l
at
e
d
t
o
B
r
a
z
il
i
a
n
s
t
o
c
k
m
a
r
k
et
m
o
v
e
m
e
n
t
s
o
n
T
w
i
tt
e
r
u
s
i
n
g
v
a
r
i
o
u
s
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s
.
T
h
e
s
t
u
d
y
s
u
g
g
e
s
ts
a
c
o
r
r
e
l
a
t
i
o
n
b
e
tw
e
e
n
t
h
e
s
e
n
ti
m
e
n
t
e
x
p
r
e
s
s
e
d
o
n
s
o
ci
a
l
m
e
d
i
a
a
n
d
t
h
e
f
l
u
c
t
u
a
ti
o
n
s
i
n
s
t
o
c
k
p
r
i
c
e
s
i
n
t
h
e
f
i
n
a
n
ci
a
l
m
a
r
k
e
t
.
S
w
at
h
i
e
t
a
l
.
[
5
]
a
l
s
o
p
r
e
d
i
c
t
e
d
s
t
o
c
k
p
r
ic
e
s
u
s
i
n
g
T
w
i
t
t
e
r
s
e
n
ti
m
e
n
t
a
n
a
l
y
s
is
.
C
a
r
o
s
i
a
e
t
a
l
.
[
4
]
f
o
u
n
d
th
at
m
u
ltil
ay
er
p
er
ce
p
tr
o
n
s
(
ML
P)
wer
e
th
e
b
est m
o
d
el
f
o
r
p
r
ed
ictin
g
s
to
ck
p
r
ices.
Ho
wev
er
,
Swath
i
et
a
l
.
[
5
]
h
as
s
h
o
wn
th
at
a
n
o
v
el
teac
h
in
g
an
d
lea
r
n
in
g
b
ased
o
p
t
im
izatio
n
(
T
L
B
O)
m
o
d
el
with
lo
n
g
s
h
o
r
t
-
ter
m
m
em
o
r
y
(
L
STM
)
ac
h
iev
ed
e
v
en
g
r
ea
ter
ac
cu
r
ac
y
,
r
ea
ch
i
n
g
9
4
.
7
3
%.
C
r
u
z
et
a
l
.
[
6
]
co
n
d
u
cte
d
r
esear
c
h
im
p
lem
en
tin
g
lex
ico
n
-
b
ased
a
n
aly
s
is
.
T
h
e
s
tu
d
y
p
r
esen
ts
s
u
b
s
tan
tial
ev
id
en
ce
s
u
p
p
o
r
tin
g
th
e
ass
u
m
p
tio
n
t
h
at
T
witter
m
ess
ag
es
alter
ed
f
in
an
cial
in
d
ices
d
u
r
in
g
th
e
C
OVI
D
-
1
9
an
d
H1
N1
p
an
d
em
ics,
with
n
o
tab
le
ef
f
ec
ts
in
th
e
ca
s
e
o
f
C
OVI
D
-
19.
Sev
er
al
s
tu
d
ies
h
av
e
u
tili
ze
d
s
en
tim
en
t
an
aly
s
is
tech
n
iq
u
es,
in
clu
d
in
g
d
ee
p
l
ea
r
n
in
g
,
ML
P,
an
d
l
ex
ico
n
-
b
ased
m
et
h
o
d
s
,
to
ca
p
tu
r
e
p
u
b
lic
o
p
in
io
n
s
o
n
ec
o
n
o
m
ic
is
s
u
es
[
3
]
–
[
6
]
.
Ho
wev
e
r
,
n
o
s
im
ilar
s
tu
d
y
h
as
b
ee
n
co
n
d
u
cted
t
o
an
aly
ze
p
u
b
lic
o
p
in
io
n
s
o
n
th
e
2
0
2
3
ec
o
n
o
m
ic
r
ec
ess
io
n
,
p
a
r
ticu
lar
ly
am
o
n
g
I
n
d
o
n
esian
s
.
T
h
er
ef
o
r
e,
t
h
is
r
esear
ch
aim
s
to
i
d
en
tify
h
o
w
th
e
I
n
d
o
n
esi
an
in
ter
n
et
co
m
m
u
n
ity
,
p
ar
tic
u
lar
ly
o
n
T
witter
,
p
er
ce
iv
es
th
e
to
p
ics
r
elate
d
t
o
th
e
g
lo
b
al
ec
o
n
o
m
ic
r
ec
ess
io
n
.
Ad
d
itio
n
ally
,
th
is
r
esear
ch
will
u
tili
ze
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
(
SVM)
k
er
n
el
s
th
at
h
av
e
b
ee
n
im
p
r
o
v
e
d
th
r
o
u
g
h
h
y
p
er
p
a
r
am
eter
s
o
p
tim
izatio
n
.
T
h
e
ch
o
s
en
m
eth
o
d
was
s
elec
ted
f
o
r
th
eir
p
o
ten
tial
to
e
n
h
an
ce
th
e
p
e
r
f
o
r
m
an
ce
o
f
th
e
SVM
class
if
ic
atio
n
m
o
d
el,
eith
er
b
y
u
tili
zin
g
k
er
n
els
[
7
]
–
[
1
3
]
o
r
im
p
lem
en
tin
g
h
y
p
er
p
a
r
am
et
er
s
o
p
tim
izatio
n
[
1
4
]
,
[
1
5
]
.
T
h
er
ef
o
r
e,
to
in
cr
ea
s
e
th
e
n
o
v
elty
a
n
d
v
alu
e
o
f
th
is
r
esear
ch
,
we
co
m
b
in
e
d
k
er
n
els an
d
h
y
p
er
p
a
r
am
eter
s
o
p
tim
iza
tio
n
to
im
p
r
o
v
e
th
e
ac
cu
r
ac
y
o
f
th
e
r
esu
lts
.
T
h
e
s
tu
d
y
’
s
f
in
d
i
n
g
s
will
h
av
e
p
r
a
ctica
l
im
p
licatio
n
s
f
o
r
ec
o
n
o
m
ic
p
o
licy
m
ak
er
s
t
o
tailo
r
co
m
m
u
n
icatio
n
s
tr
ateg
ies,
ec
o
n
o
m
ic
p
o
licies,
a
n
d
c
r
is
is
m
an
ag
em
en
t
a
p
p
r
o
ac
h
es
to
r
e
f
lect
p
u
b
lic
s
en
tim
en
t
d
u
r
in
g
th
e
g
lo
b
al
ec
o
n
o
m
ic
r
ec
ess
io
n
.
T
h
is
s
tu
d
y
also
en
h
an
ce
s
th
e
m
eth
o
d
o
lo
g
ical
asp
ec
ts
o
f
s
en
tim
en
t
an
aly
s
is
b
y
s
h
o
wc
asin
g
th
e
s
ig
n
if
ican
ce
o
f
o
p
tim
izin
g
SVM
h
y
p
er
p
ar
am
et
er
s
f
o
r
co
n
tex
tu
al
d
o
m
ain
s
.
2.
M
E
T
H
O
D
2
.
1
.
Da
t
a
s
et
T
h
is
r
esear
ch
u
s
es
I
n
d
o
n
esian
s
twee
ts
f
r
o
m
T
witter
as
a
d
at
aset,
r
an
g
in
g
f
r
o
m
1
J
an
u
ar
y
2
0
2
2
t
o
3
1
Dec
em
b
er
2
0
2
2
.
Fig
u
r
e
1
o
u
tlin
es
th
e
s
tep
s
tak
en
in
th
is
s
tu
d
y
b
ased
o
n
th
e
g
en
er
al
f
r
am
ewo
r
k
u
s
ed
to
an
aly
ze
tex
tu
al
d
ata
with
th
e
ad
d
itio
n
o
f
h
y
p
er
p
ar
a
m
eter
s
o
p
tim
izatio
n
s
tep
[
1
4
]
.
T
h
is
wo
r
k
is
co
n
d
u
cted
u
s
in
g
Py
th
o
n
p
r
o
g
r
am
m
in
g
la
n
g
u
ag
e
,
v
er
s
io
n
3
.
7
.
0
.
Usi
n
g
th
e
k
ey
wo
r
d
s
‘
I
n
d
o
n
esia
g
lo
b
al
r
ec
ess
io
n
2
0
2
3
’
,
we
s
u
cc
ess
f
u
lly
cr
awle
d
1
1
.
0
1
7
twee
ts
with
th
e
T
wee
p
y
lib
r
ar
y
.
Af
ter
cr
awlin
g
f
r
o
m
T
witter
,
th
e
f
r
esh
-
m
in
ed
d
ataset
was
f
u
r
th
er
p
r
o
ce
s
s
ed
with
te
x
t
p
r
ep
r
o
c
ess
in
g
s
tep
,
wh
ich
co
n
s
is
ted
o
f
tex
t
clea
n
in
g
with
r
eg
u
lar
ex
p
r
ess
io
n
s
(
R
E
)
,
ca
s
e
f
o
ld
in
g
,
to
k
en
izatio
n
with
n
ltk
.
to
k
en
ize
f
u
n
ctio
n
,
s
to
p
wo
r
d
r
em
o
v
al,
an
d
s
tem
m
in
g
with
Po
r
ter
s
tem
m
e
r
[
1
6
]
.
Fig
u
r
e
1
.
T
h
e
f
lo
wch
a
r
t o
f
s
en
tim
en
t a
n
aly
s
is
r
esear
ch
u
s
in
g
SVM
k
er
n
els with
h
y
p
er
p
ar
a
m
eter
s
o
p
tim
izatio
n
Af
ter
th
e
p
r
ep
r
o
ce
s
s
in
g
s
tep
,
th
e
clea
n
ed
d
ataset
was
d
iv
i
d
ed
in
to
tr
ain
d
ata
an
d
test
d
ata
with
a
p
er
ce
n
tag
e
r
atio
o
f
8
0
:2
0
.
T
h
en
,
th
e
tr
ain
d
ata
was
lab
eled
in
to
two
f
ea
tu
r
es,
wh
ic
h
wer
e
p
o
s
itiv
e
an
d
n
eg
ativ
e,
b
y
u
tili
zin
g
T
e
x
tB
lo
b
.
T
h
is
m
eth
o
d
en
s
u
r
es
m
o
r
e
ac
cu
r
ate
an
d
p
r
ec
is
e
r
esu
lts
in
s
en
tim
en
t
an
aly
s
is
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
13
,
No
.
4
,
Dec
em
b
er
2
0
2
4
:
4
9
4
8
-
4
9
5
6
4950
ca
s
es,
o
u
tp
er
f
o
r
m
i
n
g
AFI
NN
an
d
v
alen
ce
awa
r
e
d
ictio
n
ar
y
f
o
r
s
en
tim
en
t
r
ea
s
o
n
in
g
(
VADE
R
)
[
1
7
]
.
W
h
e
n
th
e
tr
ain
ed
d
ata
h
as
b
ee
n
an
n
o
tated
with
T
ex
tB
lo
b
,
t
h
e
n
e
x
t
s
tep
is
to
im
p
lem
en
t
th
e
v
ec
t
o
r
izatio
n
s
tag
e
with
t
er
m
f
r
eq
u
e
n
cy
-
i
n
v
er
s
e
d
o
c
u
m
en
t
f
r
eq
u
e
n
cy
(
T
F
-
I
DF)
.
TF
-
I
DF
is
r
ec
o
g
n
ized
as
th
e
m
o
s
t
r
o
b
u
s
t
f
ea
tu
r
e
ex
tr
ac
tio
n
e
v
er
u
s
ed
f
o
r
cl
u
s
ter
in
g
a
n
d
class
if
y
in
g
tex
tu
al
d
ata
[
1
8
]
‒
[
2
0
]
,
o
u
tp
er
f
o
r
m
in
g
b
ag
o
f
w
o
r
d
s
[
2
1
]
,
an
d
wo
r
d
2
v
ec
[
2
2
]
.
W
e
u
tili
ze
th
e
T
f
id
f
Vec
to
r
ize
r
lib
r
ar
y
with
p
ar
am
eter
s
m
ax
_
f
ea
tu
r
es
(
2
,
0
0
0
)
,
m
in
_
d
f
(
5
)
,
m
ax
_
d
f
(
0
.
7
)
,
s
to
p
wo
r
d
s
.
wo
r
d
s
(
‘
E
n
g
lis
h
’
)
,
a
n
d
n
g
r
am
_
r
a
n
g
e
(
1
.
3
)
.
Fo
llo
win
g
t
h
e
v
ec
to
r
izatio
n
s
tep
,
th
e
r
esear
ch
p
r
o
ce
s
s
will c
o
n
tin
u
e
with
m
o
d
el
co
n
s
tr
u
ctio
n
.
2
.
2
.
M
o
del
co
ns
t
ruct
io
n a
nd
hy
perpa
ra
m
et
er
s
o
ptim
iz
a
t
i
o
n
Af
ter
p
r
ep
r
o
ce
s
s
in
g
,
lab
elin
g
,
an
d
v
ec
to
r
i
z
atio
n
,
class
if
icatio
n
m
o
d
els
wer
e
b
u
ilt
u
s
in
g
SVM
k
er
n
el
f
u
n
ctio
n
s
.
T
y
p
ically
,
k
er
n
el
f
u
n
ctio
n
s
p
r
o
ject
d
ata
f
r
o
m
its
o
r
ig
in
al
s
p
ac
e
in
t
o
a
h
ig
h
e
r
-
d
im
en
s
io
n
al
s
p
ac
e,
m
ak
in
g
it
p
o
s
s
ib
le
to
s
ep
a
r
ate
th
e
d
ata
u
s
in
g
a
lin
ea
r
d
ec
is
io
n
b
o
u
n
d
ar
y
[
2
3
]
,
[
2
4
]
.
T
h
is
r
esear
ch
u
tili
ze
d
th
e
s
cik
it
-
lear
n
lib
r
ar
y
b
y
ca
llin
g
“
f
r
o
m
s
k
lear
n
.
s
v
m
im
p
o
r
t
S
VC
”
co
m
m
an
d
t
o
ass
ig
n
ea
c
h
k
er
n
els
in
to
o
u
r
m
o
d
el,
as
s
ee
n
i
n
T
ab
le
1
[
2
5
]
.
Af
ter
war
d
,
we
ad
d
k
e
r
n
el
a
s
p
ar
am
eter
s
in
th
e
SVC
f
u
n
ct
io
n
,
with
its
d
ef
a
u
lt
s
ettin
g
.
T
ab
le
1
.
T
y
p
es o
f
k
er
n
els in
S
VM
K
e
r
n
e
l
s
F
u
n
c
t
i
o
n
s
[
2
6
]
Li
n
e
a
r
(
,
)
=
〈
,
〉
(
1
)
R
a
d
i
a
l
b
a
s
i
s f
u
n
c
t
i
o
n
(
R
B
F
)
(
,
)
=
−
‖
−
‖
2
,
>
0
(
2
)
P
o
l
y
n
o
m
i
a
l
(
,
)
=
(
〈
,
〉
+
)
,
>
0
,
≥
0
(
3
)
S
i
g
m
o
i
d
(
,
)
=
ℎ
(
(
−
)
+
)
(
4
)
Ho
wev
er
,
SVM
k
e
r
n
el
f
u
n
cti
o
n
s
h
av
e
lim
itatio
n
s
th
at
s
h
o
u
ld
b
e
co
n
s
id
er
ed
[
2
3
]
.
Firstl
y
,
s
ev
er
al
s
tu
d
ies
h
av
e
im
p
lied
th
at
alth
o
u
g
h
th
e
d
atasets
u
s
ed
in
v
ar
io
u
s
r
esear
ch
o
f
SVM
k
er
n
els
ar
e
co
n
s
is
ten
t
(
twee
ts
d
ata)
,
th
e
o
p
tim
izatio
n
o
u
tco
m
es
o
f
th
e
u
tili
ze
d
m
o
d
el
y
ield
d
is
tin
ct
r
esu
lts
.
A
d
d
itio
n
ally
,
it
lack
s
ef
f
icien
cy
in
h
an
d
lin
g
m
u
lticl
ass
p
r
o
b
lem
s
.
T
o
ad
d
r
ess
th
e
i
s
s
u
e
o
f
in
ef
f
icien
cy
in
m
u
lticlas
s
ta
s
k
s
,
th
is
s
tu
d
y
u
tili
ze
d
o
n
ly
two
s
ets
o
f
lab
el
s
:
p
o
s
itiv
e
an
d
n
eg
ativ
e
s
en
tim
en
ts
.
I
n
ad
d
itio
n
to
u
s
in
g
k
e
r
n
els,
th
is
r
esear
ch
also
ap
p
lies
h
y
p
er
p
ar
am
eter
s
o
p
tim
izatio
n
.
H
y
p
er
p
a
r
am
eter
s
ar
e
v
ar
ia
b
les
th
at
af
f
ec
t
th
e
lear
n
in
g
p
r
o
ce
s
s
an
d
in
f
lu
en
ce
th
e
m
o
d
el
p
ar
am
ete
r
s
lear
n
ed
b
y
an
alg
o
r
ith
m
[
1
4
]
.
T
ab
le
2
s
h
o
ws
th
e
h
y
p
er
p
ar
am
eter
s
o
f
ea
ch
SVM
k
er
n
el
ap
p
licab
le
f
o
r
o
p
tim
izatio
n
.
T
h
e
n
,
u
s
in
g
g
r
id
s
ea
r
ch
,
h
y
p
e
r
p
ar
am
eter
s
wer
e
o
p
tim
ized
b
y
p
r
ep
ar
in
g
th
e
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
f
o
r
ev
er
y
co
n
ce
i
v
ab
le
co
m
b
in
atio
n
o
f
p
ar
am
ete
r
s
[
1
4
]
,
[
1
5
]
.
T
ab
le
2
.
Hy
p
er
p
ar
a
m
eter
s
o
p
ti
m
izatio
n
p
ar
am
s
in
SVM
K
e
r
n
e
l
s
C
S
c
o
r
e
(
R
e
g
u
l
a
r
i
sa
t
i
o
n
)
G
a
mm
a
D
e
g
r
e
e
Li
n
e
a
r
[
0
.
0
0
1
,
0
.
0
1
,
0
.
1
,
1
,
1
0
,
1
0
0
,
1
0
0
0
]
-
-
RBF
[
0
.
0
0
1
,
0
.
0
1
,
0
.
1
,
1
,
1
0
,
1
0
0
,
1
0
0
0
]
[
1
,
0
.
1
,
0
.
0
1
,
0
.
0
0
1
,
0
.
0
0
0
1
,
s
c
a
l
e
,
a
u
t
o
]
-
P
o
l
y
n
o
m
i
a
l
[
0
.
0
0
1
,
0
.
0
1
,
0
.
1
,
1
,
1
0
,
1
0
0
,
1
0
0
0
]
[
1
,
0
.
1
,
0
.
0
1
,
0
.
0
0
1
,
0
.
0
0
0
1
,
s
c
a
l
e
,
a
u
t
o
]
[
2
,
3
,
4
,
5
]
S
i
g
m
o
i
d
[
0
.
0
0
1
,
0
.
0
1
,
0
.
1
,
1
,
1
0
,
1
0
0
,
1
0
0
0
]
[
1
,
0
.
1
,
0
.
0
1
,
0
.
0
0
1
,
0
.
0
0
0
1
,
s
c
a
l
e
,
a
u
t
o
]
-
Nev
er
th
eless
,
it
s
h
o
u
ld
b
e
n
o
ted
th
a
t
h
y
p
e
r
p
ar
a
m
eter
s
ar
e
n
o
t
p
r
o
n
e
to
o
v
er
f
itti
n
g
is
s
u
es
[
2
7
]
.
T
o
h
an
d
le
th
is
p
r
o
b
lem
,
th
is
r
esea
r
ch
u
s
es
cr
o
s
s
v
alid
atio
n
(
C
V)
.
C
V
ca
n
id
en
tify
a
s
tab
le
o
p
tim
u
m
th
at
p
e
r
f
o
r
m
s
well
in
m
o
s
t
s
u
b
s
ets,
r
ath
er
t
h
an
a
s
h
ar
p
o
p
tim
u
m
th
at
o
n
ly
p
er
f
o
r
m
s
well
in
a
s
in
g
le
v
alid
atio
n
s
et.
T
o
m
itig
ate
th
is
,
we
r
ep
ea
t
ea
ch
i
ter
atio
n
p
r
o
ce
s
s
o
f
f
in
d
in
g
th
e
b
est
p
a
r
am
eter
s
in
th
e
p
r
e
d
ef
in
ed
SVM
k
e
r
n
els.
Her
e,
we
u
tili
z
e
Gr
id
Sear
ch
C
V
f
u
n
ctio
n
f
r
o
m
s
k
lear
n
.
m
o
d
el_
s
elec
tio
n
an
d
d
ef
in
ed
th
e
p
ar
am
eter
s
r
an
g
e
o
f
ea
ch
k
er
n
els
(
C
,
Gam
m
a,
Deg
r
ee
)
in
p
ar
am
_
g
r
i
d
v
ar
iab
le.
T
h
en
,
we
r
u
n
Gr
id
Sear
c
h
C
V
with
r
ef
it=T
r
u
e
an
d
v
er
b
o
s
e=
3
.
Af
ter
b
u
ild
in
g
th
e
m
o
d
el,
th
e
n
e
x
t
s
tep
is
v
alid
atin
g
th
e
m
o
d
els
th
at
h
av
e
b
e
en
b
u
ilt
to
f
in
d
t
h
e
b
est
p
er
f
o
r
m
a
n
ce
o
f
th
ese
m
o
d
els
with
co
n
f
u
s
io
n
m
atr
ix
.
I
n
th
e
co
n
f
u
s
io
n
m
atr
ix
,
th
e
cl
ass
if
icatio
n
p
r
o
ce
s
s
o
u
tco
m
es
ar
e
d
e
n
o
ted
b
y
f
o
u
r
ter
m
s
:
tr
u
e
p
o
s
itiv
e
(
T
P),
tr
u
e
n
eg
ativ
e
(TN
)
,
f
alse
p
o
s
itiv
e
(
FP
)
,
an
d
f
alse
n
eg
ativ
e
(
FN)
.
T
a
b
le
3
illu
s
tr
a
tes th
e
p
er
f
o
r
m
an
ce
p
a
r
am
eter
s
in
th
e
co
n
f
u
s
io
n
m
atr
ix
.
T
ab
le
3
.
C
o
n
f
u
s
io
n
m
atr
ix
P
r
e
d
i
c
t
e
d
/
A
c
t
u
a
l
c
l
a
sses
P
r
e
d
i
c
t
e
d
c
l
a
ss (
p
o
s
i
t
i
v
e
)
P
r
e
d
i
c
t
e
d
c
l
a
ss
(
n
e
g
a
t
i
v
e
)
A
c
t
u
a
l
c
l
a
ss (
p
o
si
t
i
v
e
)
TP
FN
A
c
t
u
a
l
c
l
a
ss (
n
e
g
a
t
i
v
e
)
FP
TN
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
I
n
d
o
n
esia
n
s
en
timen
t to
w
a
r
d
s
g
lo
b
a
l e
c
o
n
o
mic
r
ec
ess
io
n
in
2
0
2
3
u
s
in
g
o
p
timiz
ed
…
(
Da
ir
a
tu
l Ma
a
r
if)
4951
E
a
c
h
p
e
r
f
o
r
m
a
n
c
e
m
e
t
r
i
c
i
n
t
h
e
c
o
n
f
u
s
i
o
n
m
a
t
r
i
x
i
s
f
u
r
t
h
e
r
c
a
l
c
u
l
a
t
e
d
t
o
d
e
t
e
r
m
i
n
e
t
h
e
a
c
c
u
r
a
c
y
o
f
t
h
e
m
o
d
e
l
,
u
s
i
n
g
i
n
d
i
c
a
t
o
r
s
s
u
c
h
a
s
a
c
c
u
r
a
c
y
,
p
r
e
c
i
s
i
o
n
,
r
e
c
a
l
l
,
a
n
d
F
1
s
c
o
r
e
,
w
h
i
c
h
e
q
u
a
t
i
o
n
s
a
r
e
s
h
o
w
n
i
n
(
5
)
t
o
(
8
)
:
Acc
u
r
ac
y
=
+
+
+
+
100%
(
5
)
R
ec
all=
+
100%
(
6
)
Pre
cisi
o
n
=
+
100%
(
7
)
F1
Sco
r
e=
2
+
(
8
)
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
3
.
1
.
Resul
t
s
o
f
s
ent
im
ent
cla
s
s
if
ica
t
io
n
T
h
e
s
t
u
d
y
’
s
i
n
i
tia
l
o
b
jec
ti
v
e
w
as
t
o
i
d
e
n
ti
f
y
t
h
e
s
e
n
ti
m
e
n
ts
r
eg
ar
d
i
n
g
t
h
e
2
0
2
3
ec
o
n
o
m
ic
r
ec
ess
io
n
i
n
I
n
d
o
n
esi
a
t
h
r
o
u
g
h
T
wit
te
r
.
W
e
u
ti
liz
e
R
s
o
f
tw
ar
e
’
s
GG
p
l
o
t
p
a
ck
ag
e
f
o
r
d
at
a
v
is
u
al
izat
io
n
t
o
e
n
h
a
n
c
e
co
m
p
r
eh
e
n
s
i
o
n
o
f
th
e
o
b
t
ai
n
e
d
r
esu
lts
.
Usi
n
g
t
h
e
ti
m
e
-
s
e
r
i
es
f
u
n
cti
o
n
,
we
m
a
p
th
e
ti
m
e
lin
e
o
f
I
n
d
o
n
esi
an
s
en
t
im
en
ts
,
e
n
c
o
m
p
ass
i
n
g
t
h
e
h
i
g
h
est
a
n
d
t
h
e
l
o
west
p
e
r
ce
p
t
io
n
s
o
f
e
ac
h
s
en
tim
e
n
t
t
h
r
o
u
g
h
o
u
t 2
0
2
2
.
T
h
is
s
te
p
r
es
u
lt
e
d
in
F
i
g
u
r
e
2
,
w
h
ic
h
p
r
e
s
en
ts
I
n
d
o
n
es
ia
n
s
p
e
r
ce
p
t
io
n
s
o
f
g
l
o
b
a
l r
ec
ess
io
n
t
h
r
o
u
g
h
c
o
m
m
en
ts
o
n
T
wit
te
r
.
T
o
ai
d
i
n
p
r
ese
n
ti
n
g
t
h
e
r
es
u
lts
an
d
o
b
s
e
r
v
i
n
g
tr
e
n
d
s
,
w
e
ca
te
g
o
r
i
ze
d
t
h
e
s
e
n
ti
m
e
n
t
an
al
y
s
is
b
y
q
u
a
r
t
er
,
s
p
e
ci
f
ic
all
y
Q1
(
J
a
n
u
a
r
y
-
M
a
r
c
h
)
,
Q
2
(
A
p
r
il
-
J
u
n
e)
,
Q3
(
J
u
ly
-
Sep
te
m
b
er
)
,
an
d
Q
4
(
O
ct
o
b
er
-
Dec
em
b
e
r
)
.
Fig
u
r
e
2
.
Dy
n
am
ics o
f
c
o
m
m
e
n
ts
ex
p
r
ess
in
g
d
if
f
e
r
en
t sen
ti
m
en
ts
to
war
d
s
g
lo
b
al
r
ec
ess
io
n
in
2
0
2
3
Sen
tim
en
ts
o
f
th
e
I
n
d
o
n
esian
s
r
eg
ar
d
i
n
g
th
e
g
lo
b
al
r
ec
ess
io
n
ar
e
f
l
u
ctu
atin
g
.
Du
r
in
g
th
e
f
ir
s
t
q
u
ar
ter
(
Q1
)
o
f
2
0
2
2
,
b
o
t
h
p
o
s
itiv
e
a
n
d
n
eg
ativ
e
s
en
tim
e
n
ts
wer
e
r
elativ
ely
in
s
ig
n
if
ican
t
an
d
s
e
ld
o
m
d
is
cu
s
s
ed
b
y
T
witter
u
s
er
s
in
th
e
co
u
n
tr
y
,
as
s
h
o
wn
b
y
th
e
n
eg
ativ
e
b
ar
s
th
at
d
id
n
o
t
ex
ce
ed
5
0
in
c
o
u
n
ts
.
Me
an
wh
ile,
s
en
tim
en
ts
in
cr
ea
s
ed
d
u
r
in
g
th
e
last
m
o
n
th
o
f
th
e
s
ec
o
n
d
q
u
ar
ter
(
Q2
)
o
f
2
0
2
2
.
An
e
x
p
lan
atio
n
f
o
r
th
is
m
ig
h
t
b
e
th
at
th
e
p
o
s
s
ib
ilit
y
o
f
a
g
lo
b
al
r
ec
ess
io
n
b
eg
an
to
b
e
d
is
cu
s
s
ed
in
v
a
r
io
u
s
o
n
lin
e
m
ed
ia.
Me
an
wh
ile,
at
th
e
b
eg
in
n
in
g
o
f
Q3
,
n
e
g
ativ
e
s
e
n
tim
en
ts
s
u
d
d
en
ly
i
n
cr
ea
s
ed
co
m
p
ar
ed
to
th
e
to
tal
o
f
s
en
ti
m
en
ts
at
th
e
en
d
o
f
Q2
.
Ho
wev
er
,
it
q
u
ic
k
ly
d
is
s
ip
ated
in
Sep
tem
b
er
,
as
s
h
o
wn
b
y
th
e
d
ec
r
ea
s
e
in
s
en
tim
e
n
t
g
r
ap
h
d
u
r
i
n
g
Q3
.
T
h
e
s
en
tim
en
ts
p
ea
k
was
d
u
r
in
g
Octo
b
er
2
0
2
2
,
wh
en
th
e
n
eg
ativ
e
s
en
tim
en
ts
r
ea
ch
ed
2
0
0
-
2
5
0
twee
ts
p
er
d
ay
.
I
t
h
as
also
o
b
s
er
v
e
d
a
s
ig
n
if
ican
t
in
c
r
ea
s
e
in
p
o
s
itiv
e
s
en
tim
en
ts
,
r
ea
ch
in
g
m
o
r
e
th
a
n
2
0
twee
ts
d
u
r
i
n
g
Octo
b
er
.
T
h
is
f
in
d
i
n
g
m
ay
i
n
d
icate
th
at
I
n
d
o
n
esian
s
ar
e
in
cr
ea
s
in
g
ly
awa
r
e
o
f
t
h
e
im
p
en
d
in
g
ec
o
n
o
m
ic
r
ec
ess
io
n
in
2
0
2
3
.
T
h
e
r
ev
ela
tio
n
h
as
ca
u
s
ed
wid
esp
r
ea
d
p
an
ic,
p
r
o
m
p
tin
g
d
e
b
ates
o
n
w
h
eth
er
I
n
d
o
n
esia
’
s
ec
o
n
o
m
y
is
s
u
s
ce
p
tib
le
to
r
ec
e
s
s
io
n
ar
y
p
r
ess
u
r
es.
W
e
c
a
n
t
u
r
n
t
o
a
d
e
e
p
e
r
a
n
a
l
y
s
i
s
o
f
p
u
b
l
i
c
s
e
n
ti
m
e
n
t
t
o
wa
r
d
s
r
e
c
e
s
s
i
o
n
i
n
2
0
2
3
b
y
e
x
a
m
i
n
i
n
g
n
e
g
a
t
i
v
e
a
n
d
p
o
s
i
t
i
v
e
t
w
e
et
s
u
s
i
n
g
t
h
e
m
o
s
t
f
r
e
q
u
e
n
t
l
y
u
s
e
d
w
o
r
d
s
.
F
i
g
u
r
e
3
h
i
g
h
l
i
g
h
t
s
t
h
e
f
i
v
e
m
o
s
t
-
u
s
e
d
w
o
r
d
s
i
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
13
,
No
.
4
,
Dec
em
b
er
2
0
2
4
:
4
9
4
8
-
4
9
5
6
4952
t
w
e
e
ts
c
la
s
s
i
f
i
e
d
a
s
n
e
g
a
ti
v
e
s
e
n
t
i
m
e
n
t
.
F
r
o
m
t
h
e
F
i
g
u
r
e
3
,
i
t
is
a
p
p
a
r
e
n
t
t
h
at
I
n
d
o
n
e
s
i
a
n
s
o
c
i
e
t
y
’
s
n
e
g
a
t
i
v
e
s
e
n
t
i
m
e
n
t
t
o
w
a
r
d
s
r
ec
e
s
s
i
o
n
is
c
i
r
c
u
l
a
ti
n
g
t
h
e
f
i
n
a
n
c
i
a
l
i
m
p
ac
t
o
f
i
t
.
A
f
u
r
t
h
e
r
i
n
f
e
r
e
n
c
e
t
h
a
t
c
a
n
b
e
d
r
a
w
n
f
r
o
m
t
h
e
i
n
f
o
r
m
a
t
i
o
n
p
r
es
e
n
t
e
d
i
s
t
h
a
t
I
n
d
o
n
e
s
i
a
n
s
v
i
ew
e
c
o
n
o
m
i
c
r
e
c
e
s
s
i
o
n
as
a
m
e
n
a
c
i
n
g
f
o
r
ce
.
T
h
i
s
u
n
f
a
v
o
r
a
b
l
e
o
u
t
l
o
o
k
s
t
e
m
s
f
r
o
m
a
n
x
i
e
t
y
o
v
e
r
t
h
e
p
o
t
e
n
t
ia
l
f
o
r
j
o
b
l
o
s
s
a
n
d
o
n
g
o
i
n
g
d
e
s
t
i
t
u
ti
o
n
,
w
h
i
c
h
u
n
f
o
r
t
u
n
a
t
e
l
y
r
e
m
a
i
n
s
u
n
s
t
e
a
d
y
i
n
s
o
m
e
r
e
c
e
s
s
i
o
n
-
i
m
p
a
c
t
e
d
n
a
t
i
o
n
s
.
A
c
c
o
r
d
i
n
g
t
o
S
s
e
n
y
o
n
g
a
a
n
d
S
h
a
f
i
u
l
l
a
h
[
2
8
]
,
th
e
p
an
d
e
m
ic
h
as
led
to
a
d
ec
lin
e
in
o
u
tp
u
t
ac
r
o
s
s
m
o
s
t
I
n
d
o
n
esian
ec
o
n
o
m
i
c
s
ec
to
r
s
,
r
esu
ltin
g
i
n
a
s
u
r
g
e
in
u
n
em
p
lo
y
m
en
t
f
r
o
m
5
.
2
8
%
in
th
e
th
ir
d
q
u
a
r
ter
o
f
2
0
1
9
to
7
.
0
7
%
in
th
e
t
h
ir
d
q
u
ar
te
r
o
f
2
0
2
0
.
C
o
n
s
eq
u
e
n
tly
,
th
e
in
cr
ea
s
in
g
lev
els
o
f
u
n
em
p
lo
y
m
en
t
an
d
b
an
k
r
u
p
tcy
ca
u
s
ed
b
y
th
e
C
OVI
D
-
1
9
p
an
d
em
ic,
co
m
b
in
ed
with
th
e
g
lo
b
al
r
ec
ess
io
n
,
h
av
e
t
h
e
p
o
ten
tial
to
d
estab
ilize
th
e
co
u
n
tr
y
.
T
h
e
r
ef
o
r
e,
g
iv
en
th
e
wid
esp
r
ea
d
r
ec
o
g
n
itio
n
th
at
th
e
g
lo
b
al
ec
o
n
o
m
ic
cr
is
is
wo
r
s
e
n
s
p
o
v
er
ty
,
cr
ea
tes
in
eq
u
ality
,
an
d
d
ec
r
ea
s
es
life
ex
p
ec
tan
cy
,
it
is
u
n
s
u
r
p
r
is
in
g
th
at
a
r
ec
ess
io
n
ca
n
elicit
u
n
f
a
v
o
r
ab
le
r
ea
ctio
n
s
with
in
th
e
p
o
p
u
latio
n
.
Fig
u
r
e
3
.
Mo
s
t c
o
m
m
o
n
wo
r
d
s
u
s
ed
in
n
eg
ativ
e
s
en
tim
en
ts
Hav
in
g
d
is
cu
s
s
ed
th
e
n
eg
ativ
e
s
en
tim
en
ts
o
n
g
lo
b
al
r
ec
ess
io
n
,
th
e
n
ex
t
s
ec
tio
n
in
th
is
p
ap
er
will
d
is
cu
s
s
th
e
p
o
s
itiv
e
s
en
tim
en
ts
.
Fig
u
r
e
4
illu
s
tr
ates
p
u
b
lic
o
p
in
io
n
to
war
d
a
r
ec
ess
io
n
t
h
at
is
class
if
ied
as
p
o
s
itiv
e.
B
ased
o
n
th
e
b
ar
c
h
ar
t,
we
ca
n
c
o
n
clu
d
e
th
at
“wo
r
k
,
”
“p
o
ten
tial,”
an
d
“g
r
o
wth
”
ar
e
th
e
m
o
s
t
u
s
ed
wo
r
d
s
in
th
e
twee
ts
o
f
I
n
d
o
n
e
s
ian
s
o
ciety
r
e
g
ar
d
in
g
t
h
e
d
eb
ate
o
n
th
e
g
lo
b
al
ec
o
n
o
m
ic
r
e
ce
s
s
io
n
.
A
m
in
o
r
ity
with
in
I
n
d
o
n
esian
s
o
ciety
p
o
s
its
th
at
th
e
co
u
n
tr
y
will
n
o
t
s
u
f
f
er
s
ig
n
if
ican
tly
f
r
o
m
th
e
g
l
o
b
al
r
ec
ess
io
n
.
T
h
ey
co
n
ten
d
th
at
th
r
o
u
g
h
co
n
tin
u
e
d
wo
r
k
o
n
p
o
ten
tial
r
eso
u
r
ce
s
,
th
e
n
atio
n
m
ay
with
s
tan
d
th
e
s
e
lo
o
m
in
g
h
az
ar
d
s
an
d
ev
e
n
s
ee
a
p
o
s
itiv
e
im
p
ac
t
o
n
g
r
o
s
s
d
o
m
esti
c
p
r
o
d
u
ct
(
GDP
)
.
B
y
f
o
llo
win
g
th
ese
m
e
asu
r
es,
th
e
o
p
tim
is
t
s
o
ciety
f
ee
ls
m
o
r
e
co
n
f
i
d
en
t
i
n
I
n
d
o
n
esia
’
s
ab
ilit
y
to
with
s
tan
d
a
p
o
te
n
tial
ec
o
n
o
m
ic
d
o
wn
tu
r
n
.
Oth
er
t
h
an
u
tili
zin
g
th
e
p
o
ten
tial
r
eso
u
r
ce
s
,
it
is
wo
r
th
n
o
tin
g
th
at
a
s
m
all
p
ar
t
o
f
I
n
d
o
n
esian
s
o
ciety
also
u
s
ed
‘
s
tate
-
o
wn
ed
en
ter
p
r
is
es
’
in
c
o
r
r
elatio
n
to
th
e
p
o
s
itiv
e
s
en
ti
m
en
ts
.
T
h
is
in
ter
esti
n
g
r
esu
lt
m
ig
h
t
b
e
ex
p
lain
e
d
b
y
th
e
f
ac
t
th
at
s
tate
-
o
wn
ed
e
n
ter
p
r
is
es
s
er
v
e
as
a
m
o
d
el
f
o
r
th
e
n
atio
n
’
s
ec
o
n
o
m
y
s
in
c
e
v
ar
io
u
s
s
ec
to
r
s
o
f
s
tate
-
o
wn
ed
en
ter
p
r
is
es
ac
tiv
ities
co
n
tr
ib
u
te
to
ac
h
iev
in
g
t
h
e
co
u
n
tr
y
’
s
lo
f
ty
g
o
als.
T
h
is
is
in
lin
e
with
th
e
o
b
jectiv
e
o
f
I
n
d
o
n
esian
s
tate
-
o
wn
ed
e
n
ter
p
r
is
es
,
wh
ic
h
is
t
o
p
r
o
v
id
e
p
u
b
lic
s
er
v
ices
to
aid
th
e
g
o
v
e
r
n
m
e
n
t
in
p
r
o
m
o
tin
g
th
e
well
-
b
ein
g
an
d
p
r
o
s
p
er
ity
o
f
th
e
p
o
p
u
latio
n
[
2
9
]
.
Giv
en
t
h
e
im
p
o
r
tan
ce
o
f
s
tate
-
o
wn
ed
en
ter
p
r
is
es
in
th
e
I
n
d
o
n
esian
ec
o
n
o
m
y
,
it
is
n
o
t
u
n
e
x
p
ec
t
ed
th
at
p
eo
p
le
b
eliev
e
th
e
lo
ca
l
ec
o
n
o
m
y
m
ay
s
u
r
v
iv
e
an
d
g
r
o
w
ex
p
o
n
en
tiall
y
th
r
o
u
g
h
t
h
e
in
d
u
s
tr
ial
ad
v
an
ce
m
en
t o
f
s
tate
-
o
wn
e
d
en
ter
p
r
is
es.
3
.
2
.
Resul
t
s
o
f
m
o
del c
o
ns
t
ruct
io
n
T
ab
le
4
d
is
p
lay
s
th
e
v
alu
es
o
f
m
o
d
el
v
alid
atio
n
u
s
in
g
f
o
u
r
k
er
n
els
o
f
SVM
with
o
u
t
o
p
tim
iz
ed
h
y
p
er
p
ar
am
eter
s
.
Fr
o
m
th
is
f
i
n
d
in
g
,
th
e
b
est
m
o
d
el
f
o
r
th
e
T
witter
d
ataset
is
lin
ea
r
k
er
n
e
l,
with
an
ac
cu
r
ac
y
s
co
r
e
o
f
9
3
.
7
3
%.
T
h
is
f
in
d
in
g
is
co
n
s
is
ten
t
with
[
7
]
,
[
8
]
.
B
o
th
r
esear
ch
er
s
s
tated
t
h
at
t
h
e
lin
ea
r
k
er
n
el
o
f
SVM
with
d
ef
au
lt
p
ar
a
m
eter
s
ca
n
g
e
n
er
ate
r
esu
lts
ab
o
v
e
9
0
%,
m
ak
in
g
it
h
ig
h
ly
ap
p
r
o
p
r
iate
f
o
r
th
e
T
witter
d
ataset.
A
p
o
s
s
ib
le
ex
p
lan
atio
n
f
o
r
th
is
s
u
p
p
o
r
tiv
e
r
esu
lt
is
t
h
e
d
ataset
its
e
lf
,
wh
er
e
th
e
em
o
tio
n
s
co
n
tain
ed
in
T
witter
d
ata
ca
n
b
e
s
ep
ar
ate
d
lin
ea
r
ly
d
u
e
t
o
th
e
p
r
esen
ce
o
f
o
n
ly
two
f
ea
tu
r
es:
p
o
s
itiv
e
an
d
n
eg
ativ
e.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
I
n
d
o
n
esia
n
s
en
timen
t to
w
a
r
d
s
g
lo
b
a
l e
c
o
n
o
mic
r
ec
ess
io
n
in
2
0
2
3
u
s
in
g
o
p
timiz
ed
…
(
Da
ir
a
tu
l Ma
a
r
if)
4953
T
h
er
ef
o
r
e,
f
r
o
m
th
is
r
esu
lt,
t
h
e
lin
ea
r
k
er
n
el
with
o
u
t
o
p
tim
ized
h
y
p
er
p
ar
am
eter
s
ar
e
s
u
itab
le
f
o
r
tex
tu
a
l
d
atasets
with
em
o
tio
n
al
f
ea
tu
r
es.
Fig
u
r
e
4
.
Mo
s
t c
o
m
m
o
n
wo
r
d
s
in
p
o
s
itiv
e
s
en
tim
en
ts
T
ab
le
4
.
Mo
d
el
v
alid
atio
n
v
al
u
es u
s
in
g
f
o
u
r
k
e
r
n
els o
f
SV
M
K
e
r
n
e
l
s
A
c
c
u
r
a
c
y
(
%)
P
r
e
c
i
s
i
o
n
(
%)
R
e
c
a
l
l
(
%)
F
1
s
c
o
r
e
(
%)
Li
n
e
a
r
9
3
.
7
3
1
3
.
0
1
8
4
.
2
1
2
2
.
5
4
RBF
9
3
.
5
5
8
.
1
3
1
0
0
.
0
0
1
5
.
0
4
P
o
l
y
n
o
m
i
a
l
9
3
.
6
7
1
0
.
5
7
9
2
.
8
6
1
8
.
9
8
S
i
g
m
o
i
d
9
3
.
6
1
9
.
7
6
9
2
.
3
1
1
7
.
6
5
Me
an
wh
ile,
T
ab
le
5
p
r
ese
n
ts
th
e
m
o
d
el
v
alid
atio
n
v
alu
es
o
f
ea
ch
k
er
n
el
i
n
SVM
af
ter
h
y
p
er
p
ar
am
eter
s
o
p
tim
izatio
n
.
Su
r
p
r
is
in
g
ly
,
a
clo
s
er
in
s
p
ec
tio
n
o
f
th
e
tab
le
s
h
o
ws
th
at
th
e
o
p
tim
ized
R
B
F
i
s
th
e
b
est
m
o
d
el
f
o
r
th
e
p
r
ev
i
o
u
s
ly
lab
eled
twee
ts
d
ataset,
with
a
h
ig
h
er
ac
cu
r
ac
y
s
co
r
e
th
an
th
e
d
ef
a
u
lt
o
n
e,
wh
ich
r
ea
ch
ed
9
4
.
3
5
%.
Po
s
s
ib
le
ex
p
lan
atio
n
f
o
r
th
is
r
esu
lt
is
th
at
th
e
im
p
r
o
v
e
d
R
B
F
(
o
p
tim
ized
R
B
F)
wo
r
k
s
well
in
h
ig
h
-
d
im
en
s
io
n
al
s
p
ac
e
d
ata.
I
t
is
al
s
o
ap
p
ar
en
t
th
at
th
e
o
p
tim
ized
R
B
F
i
s
th
e
m
o
s
t
s
u
itab
le
alg
o
r
ith
m
f
o
r
t
h
e
r
esear
c
h
b
ec
au
s
e
o
f
it
i
s
ca
p
ab
ilit
y
to
h
a
n
d
le
im
m
en
s
e
d
atasets
,
m
atch
in
g
th
e
ch
ar
ac
ter
is
tics
o
f
k
-
n
ea
r
est
n
eig
h
b
o
r
s
(k
-
NN)
alg
o
r
ith
m
,
wh
ic
h
is
co
n
s
id
er
ed
ef
f
icien
t
ag
ain
s
t
lar
g
e
am
o
u
n
ts
o
f
d
ata,
an
d
k
n
o
wn
f
o
r
its
ab
ilit
y
to
with
s
tan
d
n
o
is
e.
T
h
is
f
in
d
in
g
r
e
f
l
ec
t
th
o
s
e
o
f
[
2
3
]
w
h
o
also
f
o
u
n
d
th
at
wh
e
n
th
e
d
ataset
is
lar
g
e,
th
e
R
B
F
k
er
n
el
f
u
n
ctio
n
p
e
r
f
o
r
m
s
m
o
r
e
ac
cu
r
ately
th
an
th
e
p
o
ly
n
o
m
ial
k
er
n
el
f
u
n
ctio
n
f
o
r
class
if
icatio
n
task
s
.
Alth
o
u
g
h
th
er
e
is
n
o
s
tan
d
ar
d
ized
d
ef
in
i
tio
n
o
f
wh
at
c
o
n
s
titu
tes
‘
lar
g
e
d
ata
’
,
we
ass
u
m
e
th
at
th
e
d
ata
in
th
is
r
esear
ch
is
co
n
s
id
er
ed
lar
g
e
b
ec
a
u
s
e
it e
x
ce
ed
s
1
0
,
0
0
0
r
ec
o
r
d
s
.
T
ab
le
5
.
Mo
d
el
v
alid
atio
n
v
al
u
es a
f
ter
h
y
p
er
p
ar
a
m
eter
s
o
p
ti
m
izatio
n
u
s
in
g
f
o
u
r
k
er
n
els o
f
SVM
K
e
r
n
e
l
s
A
c
c
u
r
a
c
y
(
%)
P
r
e
c
i
s
i
o
n
(
%)
R
e
c
a
l
l
(
%)
F
1
s
c
o
r
e
(
%)
Li
n
e
a
r
9
3
.
7
3
1
3
.
0
1
8
4
.
2
1
2
2
.
5
4
RBF
9
4
.
3
5
2
4
.
3
9
8
3
.
3
3
3
7
.
7
4
P
o
l
y
n
o
m
i
a
l
9
3
.
7
3
1
1
.
3
8
9
3
.
3
3
2
0
.
2
9
S
i
g
m
o
i
d
9
3
.
7
3
1
3
.
0
1
8
4
.
2
1
2
2
.
5
4
T
h
is
o
u
tco
m
e
v
ar
ies
f
r
o
m
th
e
d
ef
au
lt
p
a
r
am
eter
m
o
d
el
.
T
h
i
s
d
is
cr
ep
an
cy
co
u
ld
b
e
attr
ib
u
ted
to
th
e
ef
f
ec
t
o
f
h
y
p
er
p
ar
am
eter
s
o
p
tim
izatio
n
,
wh
ich
is
p
r
o
v
en
e
f
f
ec
tiv
e
in
o
p
tim
izin
g
t
h
e
d
ef
a
u
lt
m
o
d
el.
I
f
we
tak
e
a
clo
s
er
lo
o
k
at
th
e
co
m
p
ar
i
s
o
n
o
f
d
ef
au
lt
an
d
p
o
s
t
-
tu
n
e
d
m
o
d
els
o
f
SVM
k
er
n
els
,
alm
o
s
t
all
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
s
co
r
e
s
h
o
w
a
r
ath
er
s
ig
n
if
ican
t
i
n
cr
ea
s
e
o
r
r
em
ain
s
tag
n
an
t
a
f
ter
h
y
p
er
p
a
r
am
eter
s
o
p
tim
izatio
n
wer
e
im
p
lem
e
n
ted
.
T
h
e
in
cr
ea
s
e
i
n
ea
ch
m
o
d
el
v
alid
atio
n
h
as
also
p
r
o
v
e
n
th
at
im
p
lem
en
tin
g
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
13
,
No
.
4
,
Dec
em
b
er
2
0
2
4
:
4
9
4
8
-
4
9
5
6
4954
o
p
tim
ized
h
y
p
er
p
ar
am
eter
s
wi
ll
im
p
r
o
v
e
th
e
m
o
d
el
p
er
f
o
r
m
an
ce
o
r
,
at
th
e
v
er
y
least,
r
em
ain
s
tag
n
an
t
in
b
o
th
p
o
s
t
-
tu
n
ed
an
d
p
r
e
-
tu
n
e
d
m
o
d
els.
T
h
e
in
cr
ea
s
ed
ac
cu
r
ac
y
s
c
o
r
e
in
th
e
SVM
k
er
n
els
in
th
is
s
tu
d
y
c
o
r
r
o
b
o
r
ates
th
e
ea
r
lier
f
in
d
in
g
s
[
1
4
]
,
[
1
5
]
,
wh
er
e
it
h
as
b
ee
n
s
tated
th
at
th
e
o
p
tim
ized
SVM
with
C
,
Gam
m
a,
an
d
d
e
g
r
ee
p
ar
am
eter
s
wo
r
k
e
d
b
est
to
wa
r
d
s
th
e
twee
ts
d
ataset.
Ho
wev
er
,
we
ca
n
o
b
s
er
v
e
a
s
lig
h
t
d
ec
r
ea
s
e
o
n
r
ec
all
s
co
r
es
in
th
e
tu
n
ed
SVM
k
er
n
el
m
o
d
els
.
T
h
is
co
u
ld
h
av
e
h
a
p
p
en
ed
b
ec
au
s
e
o
f
t
h
e
im
b
ala
n
ce
d
d
ataset,
wh
er
e
n
eg
ativ
e
s
en
tim
en
ts
ar
e
h
ig
h
er
th
an
p
o
s
itiv
e
o
n
es,
s
o
t
h
e
m
o
d
el
m
ay
ex
h
ib
it
b
ias
to
war
d
p
r
e
d
ictin
g
t
h
e
m
ajo
r
ity
class
,
lead
in
g
to
a
lo
wer
r
ec
all
f
o
r
t
h
e
m
in
o
r
ity
cla
s
s
.
C
o
n
s
id
er
in
g
an
o
th
e
r
m
ea
s
u
r
e
m
en
t
o
f
s
u
p
er
v
is
ed
m
ac
h
in
e
lear
n
in
g
m
o
d
el
p
er
f
o
r
m
a
n
ce
,
Fig
u
r
e
5
d
is
p
lay
s
th
e
co
n
f
u
s
io
n
m
atr
i
x
o
f
th
e
im
p
r
o
v
ed
R
B
F
k
er
n
el
a
lg
o
r
ith
m
s
.
Up
o
n
clo
s
er
i
n
s
p
ec
tio
n
o
f
th
e
m
atr
ix
,
th
e
o
p
tim
ized
SVM
-
R
B
F
m
o
d
el
ex
h
ib
its
m
o
d
er
ate
er
r
o
r
s
i
n
q
u
ad
r
an
ts
two
an
d
th
r
ee
,
b
u
t
h
ig
h
er
v
alu
es
in
q
u
ad
r
a
n
t
f
o
u
r
,
in
d
icatin
g
TP
.
T
h
er
ef
o
r
e,
we
ca
n
co
n
clu
d
e
th
at
th
e
o
p
tim
ized
SVM
-
R
B
F
m
o
d
el
s
till
h
as
r
elativ
ely
m
in
o
r
er
r
o
r
s
.
T
h
e
r
ea
s
o
n
f
o
r
th
ese
er
r
o
r
s
m
ay
b
e
d
u
e
to
an
im
b
alan
ce
d
d
ataset.
As
a
r
e
s
u
lt,
th
e
o
p
tim
ized
m
o
d
el
h
ad
l
o
w
TP
an
d
T
N
v
alu
es
f
o
r
th
e
s
ep
ar
at
ed
class
es.
T
o
ad
d
r
ess
th
is
is
s
u
e,
f
u
tu
r
e
r
esear
ch
ca
n
u
s
e
a
m
o
r
e
b
alan
ce
d
d
ata
s
et,
in
co
r
p
o
r
ate
o
th
er
ca
s
e
s
tu
d
ies,
s
et
an
ap
p
r
o
p
r
iate
t
h
r
esh
o
ld
f
o
r
th
e
m
o
d
el,
ex
p
er
im
en
t
with
ad
d
itio
n
al
f
e
atu
r
e
ex
tr
ac
tio
n
tec
h
n
iq
u
es,
i
m
p
lem
en
t
d
ataset
class
if
icatio
n
,
an
d
o
p
tim
ize
th
e
SVM
k
er
n
el
r
esear
ch
with
h
y
p
er
p
ar
am
eter
s
to
cr
ea
te
a
b
etter
class
if
ier
.
Fig
u
r
e
5
.
Co
n
f
u
s
io
n
m
atr
i
x
SVM
-
R
B
F k
er
n
el
’
s
o
p
tim
ized
m
o
d
el
4.
CO
NCLU
SI
O
N
B
ased
o
n
th
e
co
n
d
u
cted
r
esear
ch
,
th
e
r
esu
lts
in
d
icate
th
at
th
e
I
n
d
o
n
esian
s
h
o
l
d
s
m
o
s
tly
n
eg
ativ
e
v
iewp
o
in
ts
o
n
th
e
g
lo
b
al
ec
o
n
o
m
ic
r
ec
ess
io
n
in
2
0
2
3
.
T
h
e
m
o
s
t
co
m
m
o
n
ly
u
s
ed
wo
r
d
s
wer
e
‘
th
r
ea
t,
’
‘
cr
is
is
,
’
an
d
‘
in
f
latio
n
’.
T
h
ese
f
in
d
in
g
s
s
u
g
g
est
th
at
th
e
p
u
b
lic
n
e
ed
s
to
b
e
f
in
an
cially
p
r
ep
a
r
e
d
to
d
ea
l
with
th
e
r
ec
ess
io
n
d
u
e
to
co
n
ce
r
n
s
ab
o
u
t
th
e
p
o
ten
tial
f
o
r
h
i
g
h
i
n
f
lat
io
n
,
wh
ic
h
c
o
u
ld
lead
to
p
r
o
l
o
n
g
ed
p
o
v
er
ty
an
d
jo
b
less
n
ess
.
Me
an
wh
ile,
th
e
o
p
tim
ized
SVM
-
R
B
F
m
o
d
el
was
f
o
u
n
d
to
b
e
th
e
b
est
m
o
d
el.
T
h
is
s
u
p
p
o
r
ts
p
r
ev
io
u
s
s
tu
d
ies
’
f
in
d
i
n
g
s
th
at
im
p
lem
en
tin
g
o
p
tim
ized
h
y
p
er
p
ar
am
eter
s
ca
n
im
p
r
o
v
e
m
o
d
el
p
er
f
o
r
m
an
ce
o
r
,
at
th
e
v
er
y
least,
m
ain
tain
it
in
b
o
t
h
p
o
s
t
-
tu
n
ed
a
n
d
p
r
e
-
tu
n
ed
m
o
d
els.
T
h
e
s
tu
d
y
d
e
m
o
n
s
tr
ates
th
r
o
u
g
h
em
p
ir
ical
ev
id
en
ce
th
at
th
e
o
p
tim
ized
h
y
p
er
p
ar
am
eter
s
tech
n
iq
u
e
ca
n
y
ield
s
atis
f
ac
to
r
y
r
esu
lts
in
s
en
tim
en
t
an
aly
s
is
r
esear
ch
.
T
h
is
es
tab
lis
h
es
a
f
o
u
n
d
atio
n
f
o
r
f
u
t
u
r
e
r
esear
ch
in
an
alter
n
ativ
e
m
eth
o
d
o
f
o
p
tim
izin
g
SVM
k
er
n
els.
T
h
e
p
r
ac
tical
im
p
licatio
n
s
o
f
th
is
s
tu
d
y
in
clu
d
e
o
p
p
o
r
tu
n
ities
f
o
r
im
p
r
o
v
in
g
p
o
licy
m
ak
in
g
to
war
d
s
cr
is
es
b
y
an
aly
zin
g
p
u
b
lic
d
em
a
n
d
s
,
p
r
o
v
i
d
in
g
an
i
n
d
ir
ec
t
m
ea
s
u
r
e
o
f
s
o
cial
an
d
ec
o
n
o
m
ic
s
tab
ilit
y
,
an
d
u
n
d
er
s
tan
d
in
g
co
n
s
u
m
er
b
eh
av
io
r
am
id
s
t
ec
o
n
o
m
ic
r
e
ce
s
s
io
n
.
Alth
o
u
g
h
th
er
e
was
a
s
lig
h
t
d
ec
lin
e
i
n
R
ec
all
v
alu
es,
th
is
m
ay
b
e
d
u
e
to
t
h
e
im
b
alan
c
ed
d
ataset
n
o
t
wo
r
k
in
g
well
wh
en
k
er
n
e
ls
wer
e
o
p
tim
ized
.
Fu
tu
r
e
r
esear
ch
ca
n
a
d
d
r
ess
t
h
is
s
h
o
r
tco
m
in
g
b
y
u
s
in
g
a
m
o
r
e
b
ala
n
ce
d
d
ataset,
u
tili
zin
g
o
th
er
ca
s
e
s
tu
d
ies,
an
d
s
ettin
g
an
a
p
p
r
o
p
r
iate
th
r
e
s
h
o
ld
f
o
r
th
e
m
o
d
el.
ACK
NO
WL
E
DG
E
M
E
NT
S
T
h
e
au
th
o
r
s
g
r
atef
u
lly
ac
k
n
o
wled
g
e
th
e
s
u
p
p
o
r
t
o
f
Un
iv
e
r
s
itas
Pem
b
an
g
u
n
an
Nasio
n
al
Vete
r
an
J
ak
ar
ta
f
o
r
th
is
r
esear
ch
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
I
n
d
o
n
esia
n
s
en
timen
t to
w
a
r
d
s
g
lo
b
a
l e
c
o
n
o
mic
r
ec
ess
io
n
in
2
0
2
3
u
s
in
g
o
p
timiz
ed
…
(
Da
ir
a
tu
l Ma
a
r
if)
4955
RE
F
E
R
E
NC
E
S
[
1
]
R
.
V
.
B
u
r
k
h
a
u
ser
,
K
.
C
o
r
i
n
t
h
,
a
n
d
D
.
H
.
-
Ea
k
i
n
,
“
P
o
l
i
c
i
e
s
t
o
h
e
l
p
t
h
e
w
o
r
k
i
n
g
c
l
a
ss
i
n
t
h
e
a
f
t
e
r
m
a
t
h
o
f
C
O
V
I
D
-
1
9
:
l
e
sso
n
s
f
r
o
m
t
h
e
g
r
e
a
t
r
e
c
e
ssi
o
n
,
”
T
h
e
A
N
N
ALS
o
f
t
h
e
Am
e
r
i
c
a
n
A
c
a
d
e
m
y
o
f
Po
l
i
t
i
c
a
l
a
n
d
S
o
c
i
a
l
S
c
i
e
n
c
e
,
v
o
l
.
6
9
5
,
n
o
.
1
,
p
p
.
3
1
4
–
3
3
0
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
7
7
/
0
0
0
2
7
1
6
2
2
1
1
0
3
1
7
7
2
.
[
2
]
G
.
A
k
e
r
l
o
f
,
“
B
e
h
a
v
i
o
r
a
l
m
a
c
r
o
e
c
o
n
o
mi
c
s
a
n
d
m
a
c
r
o
e
c
o
n
o
m
i
c
b
e
h
a
v
i
o
r
,
”
Am
e
ri
c
a
n
Ec
o
n
o
m
i
c
Re
v
i
e
w
,
v
o
l
.
9
2
,
n
o
.
3
,
p
p
.
4
1
1
–
4
3
3
,
2
0
0
2
.
[
3
]
W
.
V.
D.
W
i
e
l
e
n
a
n
d
S
.
B
a
r
r
i
o
s,
“
E
c
o
n
o
m
i
c
se
n
t
i
me
n
t
d
u
r
i
n
g
t
h
e
C
O
V
I
D
p
a
n
d
e
m
i
c
:
E
v
i
d
e
n
c
e
f
r
o
m
s
e
a
r
c
h
b
e
h
a
v
i
o
u
r
i
n
t
h
e
EU
,
”
J
o
u
rn
a
l
o
f
Ec
o
n
o
m
i
c
s
a
n
d
Bu
si
n
e
ss
,
v
o
l
.
1
1
5
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
e
c
o
n
b
u
s
.
2
0
2
0
.
1
0
5
9
7
0
.
[
4
]
A
.
E.
O
.
C
a
r
o
s
i
a
,
G
.
P
.
C
o
e
l
h
o
,
a
n
d
A
.
E.
A
.
S
i
l
v
a
,
“
A
n
a
l
y
z
i
n
g
t
h
e
B
r
a
z
i
l
i
a
n
f
i
n
a
n
c
i
a
l
mar
k
e
t
t
h
r
o
u
g
h
p
o
r
t
u
g
u
e
se
se
n
t
i
me
n
t
a
n
a
l
y
si
s
i
n
s
o
c
i
a
l
me
d
i
a
,
”
A
p
p
l
i
e
d
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
3
4
,
n
o
.
1
,
p
p
.
1
–
1
9
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
8
0
/
0
8
8
3
9
5
1
4
.
2
0
1
9
.
1
6
7
3
0
3
7
.
[
5
]
T.
S
w
a
t
h
i
,
N
.
K
a
s
i
v
i
sw
a
n
a
t
h
,
a
n
d
A
.
A
.
R
a
o
,
“
A
n
o
p
t
i
mal
d
e
e
p
l
e
a
r
n
i
n
g
-
b
a
s
e
d
LS
TM
f
o
r
st
o
c
k
p
r
i
c
e
p
r
e
d
i
c
t
i
o
n
u
s
i
n
g
t
w
i
t
t
e
r
sen
t
i
m
e
n
t
a
n
a
l
y
si
s
,
”
Ap
p
l
i
e
d
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
5
2
,
n
o
.
1
2
,
p
p
.
1
3
6
7
5
–
1
3
6
8
8
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
0
4
8
9
-
022
-
0
3
1
7
5
-
2.
[
6
]
D
.
V
.
-
C
r
u
z
,
V
.
F
.
-
C
o
r
t
e
z
,
A
.
L
.
-
C
h
a
u
,
a
n
d
R
.
S
.
-
A
l
maz
á
n
,
“
D
o
e
s
Tw
i
t
t
e
r
a
f
f
e
c
t
st
o
c
k
mar
k
e
t
d
e
c
i
si
o
n
s?
f
i
n
a
n
c
i
a
l
s
e
n
t
i
m
e
n
t
a
n
a
l
y
si
s d
u
r
i
n
g
p
a
n
d
e
mi
c
s:
a
c
o
mp
a
r
a
t
i
v
e
s
t
u
d
y
o
f
t
h
e
H
1
N
1
a
n
d
t
h
e
C
O
V
I
D
-
1
9
p
e
r
i
o
d
s
,
”
C
o
g
n
i
t
i
v
e
C
o
m
p
u
t
a
t
i
o
n
,
v
o
l
.
1
4
,
n
o
.
1
,
p
p
.
3
7
2
–
3
8
7
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
2
5
5
9
-
0
2
1
-
0
9
8
1
9
-
8.
[
7
]
D
.
F
.
S
e
n
g
k
e
y
,
A
.
J
a
c
o
b
u
s,
a
n
d
J.
M
.
F
a
b
i
a
n
,
“
Ef
f
e
c
t
s
o
f
k
e
r
n
e
l
s
a
n
d
t
h
e
p
r
o
p
o
r
t
i
o
n
o
f
t
r
a
i
n
i
n
g
d
a
t
a
o
n
t
h
e
a
c
c
u
r
a
c
y
o
f
S
V
M
sen
t
i
m
e
n
t
a
n
a
l
y
s
i
s
i
n
l
e
c
t
u
r
e
r
e
v
a
l
u
a
t
i
o
n
,
”
I
AE
S
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
(
I
J
-
AI
)
,
v
o
l
.
9
,
n
o
.
4
,
p
p
.
7
3
4
–
7
4
3
,
D
e
c
.
2
0
2
0
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
a
i
.
v
9
.
i
4
.
p
p
7
3
4
-
7
4
3
.
[
8
]
L.
K
.
R
a
m
a
sam
y
,
S
.
K
a
d
r
y
,
Y
.
N
a
m
,
a
n
d
M
.
N
.
M
e
q
d
a
d
,
“
P
e
r
f
o
r
ma
n
c
e
a
n
a
l
y
si
s
o
f
se
n
t
i
m
e
n
t
s
i
n
Tw
i
t
t
e
r
d
a
t
a
set
u
si
n
g
S
V
M
mo
d
e
l
s
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
El
e
c
t
ri
c
a
l
a
n
d
C
o
m
p
u
t
e
r
E
n
g
i
n
e
e
r
i
n
g
(
I
J
EC
E)
,
v
o
l
.
1
1
,
n
o
.
3
,
p
p
.
2
2
7
5
–
2
2
8
4
,
Ju
n
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
c
e
.
v
1
1
i
3
.
p
p
2
2
7
5
-
2
2
8
4
.
[
9
]
M
.
R
a
h
a
r
d
i
,
A
.
A
mi
n
u
d
d
i
n
,
F
.
F
.
A
b
d
u
l
l
o
h
,
a
n
d
R
.
A
.
N
u
g
r
o
h
o
,
“
S
e
n
t
i
me
n
t
a
n
a
l
y
si
s
o
f
C
o
v
i
d
-
1
9
v
a
c
c
i
n
a
t
i
o
n
u
s
i
n
g
su
p
p
o
r
t
v
e
c
t
o
r
mac
h
i
n
e
i
n
I
n
d
o
n
e
si
a
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
Ad
v
a
n
c
e
d
C
o
m
p
u
t
e
r S
c
i
e
n
c
e
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
3
,
n
o
.
6
,
p
p
.
5
3
4
–
5
3
9
,
2
0
2
2
,
d
o
i
:
1
0
.
1
4
5
6
9
/
I
JA
C
S
A
.
2
0
2
2
.
0
1
3
0
6
6
5
.
[
1
0
]
H
.
S
y
a
h
p
u
t
r
a
,
“
S
e
n
t
i
me
n
t
a
n
a
l
y
s
i
s
o
f
c
o
mm
u
n
i
t
y
o
p
i
n
i
o
n
o
n
o
n
l
i
n
e
st
o
r
e
i
n
i
n
d
o
n
e
si
a
o
n
t
w
i
t
t
e
r
u
si
n
g
su
p
p
o
r
t
v
e
c
t
o
r
mac
h
i
n
e
a
l
g
o
r
i
t
h
m (S
V
M
)
,
”
J
o
u
r
n
a
l
o
f
P
h
y
s
i
c
s:
C
o
n
f
e
re
n
c
e
S
e
r
i
e
s
,
v
o
l
.
1
8
1
9
,
n
o
.
1
,
M
a
r
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
8
8
/
1
7
4
2
-
6
5
9
6
/
1
8
1
9
/
1
/
0
1
2
0
3
0
.
[
1
1
]
R
.
N
.
C
h
o
r
y
,
M
.
N
a
sr
u
n
,
a
n
d
C
.
S
e
t
i
a
n
i
n
g
si
h
,
“
S
e
n
t
i
me
n
t
a
n
a
l
y
si
s
o
n
u
ser
s
a
t
i
sf
a
c
t
i
o
n
l
e
v
e
l
o
f
m
o
b
i
l
e
d
a
t
a
ser
v
i
c
e
s
u
si
n
g
s
u
p
p
o
r
t
v
e
c
t
o
r
m
a
c
h
i
n
e
(
S
V
M
)
a
l
g
o
r
i
t
h
m
,
”
i
n
Pro
c
e
e
d
i
n
g
s
-
2
0
1
8
I
EE
E
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
I
n
t
e
r
n
e
t
o
f
T
h
i
n
g
s
a
n
d
I
n
t
e
l
l
i
g
e
n
c
e
S
y
s
t
e
m
,
I
O
T
AI
S
2
0
1
8
,
I
EEE,
2
0
1
9
,
p
p
.
1
9
4
–
2
0
0
.
d
o
i
:
1
0
.
1
1
0
9
/
I
O
TA
I
S
.
2
0
1
8
.
8
6
0
0
8
8
4
.
[
1
2
]
M
.
A
l
k
a
f
f
,
A
.
R
.
B
a
s
k
a
r
a
,
a
n
d
Y
.
H
.
W
i
c
a
k
s
o
n
o
,
“
S
e
n
t
i
me
n
t
a
n
a
l
y
s
i
s
o
f
I
n
d
o
n
e
s
i
a
n
mo
v
i
e
t
r
a
i
l
e
r
o
n
Y
o
u
Tu
b
e
u
si
n
g
d
e
l
t
a
TF
-
I
D
F
a
n
d
S
V
M
,
”
i
n
2
0
2
0
5
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
I
n
f
o
rm
a
t
i
c
s
a
n
d
C
o
m
p
u
t
i
n
g
,
I
C
I
C
2
0
2
0
,
2
0
2
0
.
d
o
i
:
1
0
.
1
1
0
9
/
I
C
I
C
5
0
8
3
5
.
2
0
2
0
.
9
2
8
8
5
7
9
.
[
1
3
]
N
.
P
.
A
r
t
h
a
m
e
v
i
a
,
A
d
i
w
i
j
a
y
a
,
a
n
d
M
.
D
.
P
u
r
b
o
l
a
k
s
o
n
o
,
“
A
sp
e
c
t
-
b
a
se
d
s
e
n
t
i
me
n
t
a
n
a
l
y
si
s
i
n
b
e
a
u
t
y
p
r
o
d
u
c
t
r
e
v
i
e
w
s
u
si
n
g
TF
-
I
D
F
a
n
d
S
V
M
a
l
g
o
r
i
t
h
m,”
i
n
2
0
2
1
9
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
I
n
f
o
rm
a
t
i
o
n
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
(
I
C
o
I
C
T
)
,
2
0
2
1
,
p
p
.
1
9
7
–
2
0
1
.
d
o
i
:
1
0
.
1
1
0
9
/
I
C
o
I
C
T5
2
0
2
1
.
2
0
2
1
.
9
5
2
7
4
8
9
.
[
1
4
]
K
.
S
.
C
h
o
n
g
a
n
d
N
.
S
h
a
h
,
“
C
o
m
p
a
r
i
so
n
o
f
n
a
i
v
e
B
a
y
e
s
a
n
d
S
V
M
c
l
a
ssi
f
i
c
a
t
i
o
n
i
n
g
r
i
d
-
sea
r
c
h
h
y
p
e
r
p
a
r
a
me
t
e
r
t
u
n
e
d
a
n
d
n
o
n
-
h
y
p
e
r
p
a
r
a
me
t
e
r
t
u
n
e
d
h
e
a
l
t
h
c
a
r
e
s
t
o
c
k
mar
k
e
t
se
n
t
i
me
n
t
a
n
a
l
y
si
s
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
A
d
v
a
n
c
e
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
3
,
n
o
.
1
2
,
p
p
.
9
0
–
9
4
,
2
0
2
2
,
d
o
i
:
1
0
.
1
4
5
6
9
/
I
JA
C
S
A
.
2
0
2
2
.
0
1
3
1
2
1
3
.
[
1
5
]
M
.
A
h
m
a
d
,
S
.
A
f
t
a
b
,
M
.
S
.
B
a
sh
i
r
,
a
n
d
N
.
H
a
me
e
d
,
“
S
e
n
t
i
me
n
t
a
n
a
l
y
s
i
s
u
s
i
n
g
S
V
M
:
A
s
y
st
e
ma
t
i
c
l
i
t
e
r
a
t
u
r
e
r
e
v
i
e
w
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
A
d
v
a
n
c
e
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
9
,
n
o
.
2
,
p
p
.
1
8
2
–
1
8
8
,
2
0
1
8
,
d
o
i
:
1
0
.
1
4
5
6
9
/
I
JA
C
S
A
.
2
0
1
8
.
0
9
0
2
2
6
.
[
1
6
]
G
.
M
i
n
e
r
,
D
.
D
e
l
e
n
,
J.
El
d
e
r
,
A
.
F
a
st
,
T.
H
i
l
l
,
a
n
d
R
.
N
i
sb
e
t
,
“
C
h
a
p
t
e
r
3
-
c
o
n
c
e
p
t
u
a
l
f
o
u
n
d
a
t
i
o
n
s
o
f
t
e
x
t
mi
n
i
n
g
a
n
d
p
r
e
p
r
o
c
e
ssi
n
g
st
e
p
s,”
i
n
Pr
a
c
t
i
c
a
l
T
e
x
t
Mi
n
i
n
g
a
n
d
S
t
a
t
i
st
i
c
a
l
A
n
a
l
y
si
s
f
o
r
N
o
n
-
st
r
u
c
t
u
r
e
d
T
e
x
t
D
a
t
a
A
p
p
l
i
c
a
t
i
o
n
s
,
G
.
M
i
n
e
r
,
D
.
D
e
l
e
n
,
J.
E
l
d
e
r
,
A
.
F
a
st
,
T.
H
i
l
l
,
a
n
d
R
.
A
.
B
.
T.
-
P
.
T
.
M
.
a
n
d
S
.
A
.
f
o
r
N
.
T
.
D
.
A
.
N
i
s
b
e
t
,
Ed
s
.
,
B
o
s
t
o
n
:
A
c
a
d
e
m
i
c
P
r
e
s
s,
2
0
1
2
,
p
p
.
4
3
–
5
1
.
d
o
i
:
1
0
.
1
0
1
6
/
B
9
7
8
-
0
-
12
-
3
8
6
9
7
9
-
1
.
0
0
0
0
3
-
7.
[
1
7
]
W
.
A
l
j
e
d
a
a
n
i
e
t
a
l
.
,
“
S
e
n
t
i
me
n
t
a
n
a
l
y
si
s
o
n
Tw
i
t
t
e
r
d
a
t
a
i
n
t
e
g
r
a
t
i
n
g
T
e
x
t
B
l
o
b
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
mo
d
e
l
s
:
Th
e
c
a
se
o
f
U
S
a
i
r
l
i
n
e
i
n
d
u
st
r
y
,
”
K
n
o
w
l
e
d
g
e
-
Ba
s
e
d
S
y
st
e
m
s
,
v
o
l
.
2
5
5
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
k
n
o
s
y
s
.
2
0
2
2
.
1
0
9
7
8
0
.
[
1
8
]
M
.
A
l
i
a
n
d
Y
.
M
o
h
a
me
d
,
“
A
m
e
t
h
o
d
f
o
r
c
l
u
st
e
r
i
n
g
u
n
l
a
b
e
l
e
d
B
I
M
o
b
j
e
c
t
s
u
s
i
n
g
e
n
t
r
o
p
y
a
n
d
TF
-
I
D
F
w
i
t
h
R
D
F
e
n
c
o
d
i
n
g
,
”
Ad
v
a
n
c
e
d
En
g
i
n
e
e
r
i
n
g
I
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
3
3
,
p
p
.
1
5
4
–
1
6
3
,
A
u
g
.
2
0
1
7
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
e
i
.
2
0
1
7
.
0
6
.
0
0
5
.
[
1
9
]
M
.
K
a
m
y
a
b
,
G
.
L
i
u
,
a
n
d
M
.
A
d
j
e
i
sa
h
,
“
A
t
t
e
n
t
i
o
n
-
b
a
s
e
d
C
N
N
a
n
d
B
i
-
LST
M
mo
d
e
l
b
a
se
d
o
n
TF
-
I
D
F
a
n
d
G
l
o
V
e
w
o
r
d
e
m
b
e
d
d
i
n
g
f
o
r
se
n
t
i
me
n
t
a
n
a
l
y
s
i
s,
”
A
p
p
l
i
e
d
S
c
i
e
n
c
e
s
,
v
o
l
.
1
1
,
n
o
.
2
3
,
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
1
2
3
1
1
2
5
5
.
[
2
0
]
R
.
S
.
P
a
t
i
l
a
n
d
S
.
R
.
K
o
l
h
e
,
“
S
u
p
e
r
v
i
s
e
d
c
l
a
ss
i
f
i
e
r
s
w
i
t
h
TF
-
I
D
F
f
e
a
t
u
r
e
s
f
o
r
s
e
n
t
i
me
n
t
a
n
a
l
y
si
s
o
f
M
a
r
a
t
h
i
t
w
e
e
t
s
,
”
S
o
c
i
a
l
N
e
t
w
o
rk
An
a
l
y
si
s
a
n
d
Mi
n
i
n
g
,
v
o
l
.
1
2
,
n
o
.
1
,
D
e
c
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
3
2
7
8
-
0
2
2
-
0
0
8
7
7
-
w.
[
2
1
]
S
.
A
k
u
ma
,
T.
Lu
b
e
m,
a
n
d
I
.
T.
A
d
o
m,
“
C
o
m
p
a
r
i
n
g
b
a
g
o
f
w
o
r
d
s
a
n
d
T
F
-
I
D
F
w
i
t
h
d
i
f
f
e
r
e
n
t
m
o
d
e
l
s
f
o
r
h
a
t
e
sp
e
e
c
h
d
e
t
e
c
t
i
o
n
f
r
o
m
l
i
v
e
t
w
e
e
t
s,”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
1
4
,
n
o
.
7
,
p
p
.
3
6
2
9
–
3
6
3
5
,
D
e
c
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s
4
1
8
7
0
-
0
2
2
-
0
1
0
9
6
-
4.
[
2
2
]
D
.
E.
C
a
h
y
a
n
i
a
n
d
I
.
P
a
t
a
si
k
,
“
P
e
r
f
o
r
man
c
e
c
o
m
p
a
r
i
s
o
n
o
f
t
f
-
i
d
f
a
n
d
w
o
r
d
2
v
e
c
m
o
d
e
l
s
f
o
r
e
m
o
t
i
o
n
t
e
x
t
c
l
a
ssi
f
i
c
a
t
i
o
n
,
”
B
u
l
l
e
t
i
n
o
f
El
e
c
t
r
i
c
a
l
En
g
i
n
e
e
r
i
n
g
a
n
d
I
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
1
0
,
n
o
.
5
,
p
p
.
2
7
8
0
–
2
7
8
8
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
5
9
1
/
e
e
i
.
v
1
0
i
5
.
3
1
5
7
.
[
2
3
]
A
.
P
a
t
l
e
a
n
d
D
.
S
.
C
h
o
u
h
a
n
,
“
S
V
M
k
e
r
n
e
l
f
u
n
c
t
i
o
n
s
f
o
r
c
l
a
ssi
f
i
c
a
t
i
o
n
,
”
i
n
2
0
1
3
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
Ad
v
a
n
c
e
s
i
n
T
e
c
h
n
o
l
o
g
y
a
n
d
E
n
g
i
n
e
e
r
i
n
g
(
I
C
ATE)
,
I
EEE,
Ja
n
.
2
0
1
3
,
p
p
.
1
–
9
.
d
o
i
:
1
0
.
1
1
0
9
/
I
C
A
d
TE
.
2
0
1
3
.
6
5
2
4
7
4
3
.
[
2
4
]
I
.
S
.
A
l
-
M
e
j
i
b
l
i
,
J.
K
.
A
l
w
a
n
,
a
n
d
D
.
H
.
A
b
d
,
“
Th
e
e
f
f
e
c
t
o
f
g
a
mm
a
v
a
l
u
e
o
n
s
u
p
p
o
r
t
v
e
c
t
o
r
ma
c
h
i
n
e
p
e
r
f
o
r
ma
n
c
e
w
i
t
h
d
i
f
f
e
r
e
n
t
k
e
r
n
e
l
s
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
t
ri
c
a
l
a
n
d
C
o
m
p
u
t
e
r
En
g
i
n
e
e
ri
n
g
(
I
J
EC
E)
,
v
o
l
.
1
0
,
n
o
.
5
,
p
p
.
5
4
9
7
–
5
5
0
6
,
O
c
t
.
2
0
2
0
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
c
e
.
v
1
0
i
5
.
p
p
5
4
9
7
-
5
5
0
6
.
[
2
5
]
C
.
C
o
r
t
e
s
a
n
d
V
.
V
a
p
n
i
k
,
“
S
u
p
p
o
r
t
-
v
e
c
t
o
r
n
e
t
w
o
r
k
s
,
”
Ma
c
h
i
n
e
l
e
a
r
n
i
n
g
,
v
o
l
.
2
0
,
p
p
.
2
7
3
–
2
9
7
,
1
9
9
5
.
[
2
6
]
G
.
N
.
K
o
u
z
i
o
k
a
s,
“
S
V
M
k
e
r
n
e
l
b
a
sed
o
n
p
a
r
t
i
c
l
e
sw
a
r
m
o
p
t
i
mi
z
e
d
v
e
c
t
o
r
a
n
d
B
a
y
e
s
i
a
n
o
p
t
i
mi
z
e
d
S
V
M
i
n
a
t
m
o
sp
h
e
r
i
c
p
a
r
t
i
c
u
l
a
t
e
m
a
t
t
e
r
f
o
r
e
c
a
st
i
n
g
,
”
A
p
p
l
i
e
d
S
o
f
t
C
o
m
p
u
t
i
n
g
,
v
o
l
.
9
3
,
A
u
g
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
s
o
c
.
2
0
2
0
.
1
0
6
4
1
0
.
[
2
7
]
L.
Y
a
n
g
a
n
d
A
.
S
h
a
mi
,
“
O
n
h
y
p
e
r
p
a
r
a
met
e
r
o
p
t
i
m
i
z
a
t
i
o
n
o
f
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms
:
T
h
e
o
r
y
a
n
d
p
r
a
c
t
i
c
e
,
”
N
e
u
ro
c
o
m
p
u
t
i
n
g
,
v
o
l
.
4
1
5
,
p
p
.
2
9
5
–
3
1
6
,
N
o
v
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
n
e
u
c
o
m
.
2
0
2
0
.
0
7
.
0
6
1
.
[
2
8
]
M
.
S
s
e
n
y
o
n
g
a
a
n
d
M
.
S
h
a
f
i
u
l
l
a
h
,
“
I
mp
e
r
a
t
i
v
e
s
f
o
r
p
o
s
t
C
O
V
I
D
-
1
9
r
e
c
o
v
e
r
y
o
f
I
n
d
o
n
e
si
a
’
s
e
d
u
c
a
t
i
o
n
,
l
a
b
o
r
,
a
n
d
S
M
E
sec
t
o
r
s,”
C
o
g
e
n
t
Ec
o
n
o
m
i
c
s
a
n
d
F
i
n
a
n
c
e
,
v
o
l
.
9
,
n
o
.
1
,
Ja
n
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
8
0
/
2
3
3
2
2
0
3
9
.
2
0
2
1
.
1
9
1
1
4
3
9
.
[
2
9
]
Y
.
S
.
R
a
n
g
k
u
t
i
,
B
.
N
a
s
u
t
i
o
n
,
H
.
Ju
w
a
n
a
,
a
n
d
M
.
S
i
r
e
g
a
r
,
“
L
i
a
b
i
l
i
t
y
o
f
st
a
t
e
-
o
w
n
e
d
h
o
l
d
i
n
g
c
o
mp
a
n
y
i
n
f
a
c
i
n
g
t
h
e
i
m
p
a
c
t
o
f
C
O
V
I
D
-
1
9
p
a
n
d
e
m
i
c
,
”
Ru
ss
i
a
n
L
a
w
J
o
u
rn
a
l
,
v
o
l
.
1
1
,
n
o
.
1
,
p
p
.
1
–
8
,
2
0
2
3
,
d
o
i
:
1
0
.
5
2
7
8
3
/
r
l
j
.
v
1
1
i
1
.
2
8
6
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
13
,
No
.
4
,
Dec
em
b
er
2
0
2
4
:
4
9
4
8
-
4
9
5
6
4956
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Da
ira
tu
l
Ma
a
r
if
h
o
ld
s
a
M
a
ste
r
o
f
Arts
d
e
g
re
e
fro
m
G
a
jah
M
a
d
a
Un
iv
e
rsit
y
i
n
In
d
o
n
e
sia
i
n
2
0
1
3
.
He
is
a
n
a
s
sista
n
t
p
r
o
fe
ss
o
r
a
t
In
ter
n
a
ti
o
n
a
l
Re
latio
n
s
De
p
a
rtme
n
t
in
Un
iv
e
rsitas
P
e
m
b
a
n
g
u
n
a
n
Na
sio
n
a
l
Ve
tera
n
Ja
k
a
rta,
S
o
u
t
h
Ja
k
a
r
ta,
In
d
o
n
e
sia
.
His
re
se
a
rc
h
in
tere
sts
a
re
in
b
i
g
d
a
ta
in
i
n
tern
a
ti
o
n
a
l
re
lati
o
n
s,
in
ter
n
a
ti
o
n
a
l
p
o
li
ti
c
a
l
e
c
o
n
o
m
y
,
a
n
d
e
n
v
iro
n
m
e
n
talism
in
in
tern
a
ti
o
n
a
l
re
latio
n
s.
He
h
a
s
p
a
rti
c
i
p
a
ted
i
n
se
v
e
ra
l
n
a
ti
o
n
a
l
a
c
c
re
d
it
e
d
re
se
a
rc
h
e
s
in
c
lu
d
in
g
c
o
m
m
u
n
it
y
se
rv
ice
s
a
n
d
sc
ien
ti
fic
wo
rk
sh
o
p
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
d
a
iratu
l@u
p
n
v
j.
a
c
.
id
.
A
d
i
n
d
a
A
u
l
i
a
H
a
f
i
z
h
a
i
s
c
u
r
r
e
n
t
l
y
a
r
e
s
e
a
r
c
h
a
s
s
i
s
ta
n
t
t
o
t
h
e
l
e
c
t
u
r
e
r
s
in
I
n
t
e
r
n
a
t
i
o
n
a
l
R
e
l
a
t
i
o
n
s
m
a
j
o
r
o
f
U
n
i
v
e
r
s
i
t
a
s
P
e
m
b
a
n
g
u
n
a
n
N
a
s
i
o
n
a
l
V
e
t
e
r
a
n
J
a
k
a
r
t
a
.
H
e
r
r
e
s
e
a
r
c
h
i
n
t
e
re
s
t
s
a
r
e
b
i
g
d
a
t
a
i
n
i
n
t
e
r
n
a
t
i
o
n
a
l
r
e
l
a
t
i
o
n
s
,
n
a
t
u
r
a
l
l
a
n
g
u
a
g
e
p
r
o
c
e
s
s
i
n
g
,
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
,
a
n
d
g
l
o
b
a
l
p
o
l
i
t
i
c
a
l
e
c
o
n
o
m
y
.
S
h
e
c
a
n
b
e
c
o
n
t
a
c
t
e
d
a
t
e
m
a
il
:
h
a
f
i
z
h
a
d
i
n
d
a
@
g
m
a
i
l
.
c
o
m
.
And
i
K
u
r
n
ia
w
a
n
re
c
e
iv
e
d
th
e
M
a
ste
r
o
f
S
c
ien
c
e
d
e
g
re
e
in
U
n
iv
e
rsit
y
o
f
In
d
o
n
e
sia
in
2
0
1
4
.
He
is
c
u
rr
e
n
tl
y
lec
tu
ri
n
g
a
t
I
n
tern
a
ti
o
n
a
l
Re
latio
n
s
De
p
a
rtme
n
t
in
Un
iv
e
rsitas
P
e
m
b
a
n
g
u
n
a
n
Na
sio
n
a
l
Ve
tera
n
Ja
k
a
rta,
S
o
u
t
h
Ja
k
a
r
ta,
In
d
o
n
e
sia
.
His
re
se
a
rc
h
a
re
a
s
o
f
in
tere
st
in
c
lu
d
e
p
o
li
ti
c
a
l
e
c
o
n
o
m
y
o
f
n
a
tu
ra
l
re
so
u
rc
e
s,
b
ig
d
a
ta
in
in
ter
n
a
ti
o
n
a
l
re
latio
n
s,
p
o
li
ti
c
a
l
e
c
o
n
o
m
y
o
f
m
u
lt
in
a
ti
o
n
a
l
c
o
rp
o
ra
ti
o
n
s,
a
n
d
m
e
th
o
d
s
o
f
q
u
a
n
ti
tativ
e
re
se
a
r
c
h
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
a
n
d
i.
k
@u
p
n
v
j.
a
c
.
id
.
Evaluation Warning : The document was created with Spire.PDF for Python.