I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
pu
t
er
Science
Vo
l.
36
,
No
.
3
,
Dec
em
b
er
20
24
,
p
p
.
1
8
1
6
~1
826
I
SS
N:
2
502
-
4
7
52
,
DOI
: 1
0
.
1
1
5
9
1
/ijee
cs
.v
36.
i
3
.
p
p
1
8
1
6
-
1
8
2
6
1816
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs
.
ia
esco
r
e.
co
m
A
ro
bust
metho
d
for det
ecting
fake
news using
bo
th
ma
chine
a
nd deep l
ea
rning
alg
o
rithms
E
na
s
Ahm
a
d Alik
ha
s
ha
s
hn
e
h
1
,
K
ha
lid
M
.
O
.
Na
ha
r
2,
3
,
M
o
ha
m
m
ed
Abua
l
-
Rub
4
,
H
eda
y
a
M
.
Alk
ha
ldy
1
1
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
mat
i
o
n
S
y
s
t
e
ms
,
F
a
c
u
l
t
y
o
f
I
n
f
o
r
ma
t
i
o
n
T
e
c
h
n
o
l
o
g
y
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
Y
a
r
m
o
u
k
U
n
i
v
e
r
si
t
y
,
I
r
b
i
d
,
J
o
r
d
a
n
2
F
a
c
u
l
t
y
o
f
C
o
mp
u
t
e
r
S
t
u
d
i
e
s,
A
r
a
b
O
p
e
n
U
n
i
v
e
r
si
t
y
,
R
i
y
a
d
h
,
S
a
u
d
i
A
r
a
b
i
a
3
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
F
a
c
u
l
t
y
o
f
I
n
f
o
r
ma
t
i
o
n
Te
c
h
n
o
l
o
g
y
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
s
,
Y
a
r
m
o
u
k
U
n
i
v
e
r
si
t
y
,
I
r
b
i
d
,
J
o
r
d
a
n
4
D
e
p
a
r
t
me
n
t
o
f
M
a
n
a
g
e
me
n
t
I
n
f
o
r
ma
t
i
o
n
S
y
st
e
ms,
S
c
h
o
o
l
o
f
B
u
si
n
e
ss
,
K
i
n
g
F
a
i
sa
l
U
n
i
v
e
r
si
t
y
,
H
o
f
u
f
,
S
a
u
d
i
A
r
a
b
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Feb
15
,
2
0
2
4
R
ev
is
ed
Au
g
10
,
2
0
2
4
Acc
ep
ted
A
ug
26
,
2
0
2
4
S
p
re
a
d
in
g
fa
k
e
n
e
ws
a
n
d
fa
lse
in
fo
rm
a
ti
o
n
o
n
s
o
c
ial
m
e
d
ia
is
v
e
r
y
c
o
m
m
o
n
a
n
d
c
a
n
b
e
d
o
n
e
e
ffo
rtl
e
ss
ly
d
u
e
to
th
e
h
u
g
e
n
u
m
b
e
r
o
f
u
se
rs
o
f
e
a
c
h
o
f
th
e
v
a
rio
u
s
s
o
c
ial
m
e
d
ia
p
latfo
rm
s.
An
o
th
e
r
re
a
so
n
fo
r
h
a
v
i
n
g
su
c
h
a
sp
e
e
d
y
sp
re
a
d
o
f
fa
k
e
n
e
ws
(wh
ic
h
m
a
k
e
s
a
b
o
u
t
4
0
%
o
f
t
h
e
i
n
fo
rm
a
ti
o
n
p
u
b
li
sh
e
d
o
n
so
c
ial
m
e
d
ia
p
latfo
rm
s)
is
th
e
in
a
b
i
li
ty
o
f
t
h
e
se
p
latfo
rm
to
v
e
rify
th
e
a
u
th
e
n
ti
c
it
y
o
f
t
h
e
n
e
ws
b
e
fo
re
a
ll
o
win
g
it
to
b
e
p
u
b
li
s
h
e
d
.
Th
i
s
re
se
a
rc
h
will
u
se
i
n
fo
rm
a
ti
o
n
tec
h
n
o
l
o
g
y
to
d
e
tec
t
fa
k
e
n
e
ws
/
fa
lse
in
fo
rm
a
ti
o
n
a
n
d
c
h
a
n
g
e
t
h
is
k
i
n
d
o
f
tec
h
n
o
lo
g
y
fr
o
m
b
e
i
n
g
t
h
e
c
a
u
se
o
f
th
e
p
r
o
b
le
m
to
a
t
o
o
l
to
so
l
v
e
it
.
Th
is
re
se
a
rc
h
p
ro
v
id
e
s
a
m
e
th
o
d
th
a
t
u
se
s
b
o
th
m
a
c
h
in
e
lea
rn
in
g
(M
L)
a
n
d
d
e
e
p
lea
rn
i
n
g
(DL)
a
l
g
o
rit
h
m
s
to
d
e
tec
t
fa
k
e
in
f
o
rm
a
ti
o
n
v
e
rsu
s
re
a
l
in
fo
rm
a
ti
o
n
a
n
d
c
o
m
p
a
re
t
h
e
p
e
rfo
rm
a
n
c
e
o
f
th
e
a
lg
o
rit
h
m
s.
T
h
e
re
su
lt
s
o
f
t
h
is
re
se
a
rc
h
in
d
ica
te
th
a
t
t
h
e
a
lg
o
rit
h
m
s
t
h
a
t
u
se
term
fre
q
u
e
n
c
y
i
n
v
e
rse
d
o
c
u
m
e
n
t
fre
q
u
e
n
c
y
(
TF
-
IDF
)
h
a
v
e
a
c
h
iev
e
d
b
e
t
ter
re
su
lt
s
th
a
n
t
h
e
a
lg
o
rit
h
m
s
th
a
t
u
se
Wo
r
d
2
Ve
c
.
L
o
n
g
sh
o
rt
-
term
m
e
m
o
ry
(L
S
TM
)
a
lg
o
rit
h
m
,
h
o
we
v
e
r,
h
a
s
a
c
h
iev
e
d
t
h
e
b
e
st
p
e
rfo
rm
a
n
c
e
;
o
f
9
9
%
a
c
c
u
ra
c
y
-
w
h
e
n
u
sin
g
TF
-
IDF,
a
n
d
9
4
%
-
wh
e
n
u
si
n
g
W
o
rd
2
Ve
c
.
K
ey
w
o
r
d
s
:
Dee
p
lear
n
in
g
Fak
e
n
ews
I
n
f
o
r
m
atio
n
tech
n
o
lo
g
y
Ma
ch
in
e
lear
n
in
g
So
cial
m
ed
ia
TF
-
I
DF
W
o
r
d
2
Vec
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
E
n
as Ah
m
ad
Alik
h
ash
ash
n
e
h
Dep
ar
tm
en
t o
f
I
n
f
o
r
m
atio
n
Sy
s
tem
s
,
Facu
lty
o
f
I
n
f
o
r
m
atio
n
T
ec
h
n
o
lo
g
y
an
d
C
o
m
p
u
ter
Scien
ce
Yar
m
o
u
k
U
n
iv
er
s
ity
I
r
b
id
,
2
1
1
6
3
,
J
o
r
d
an
E
m
ail: e
n
as.a
@
y
u
.
ed
u
.
jo
1.
I
NT
RO
D
UCT
I
O
N
Giv
en
th
e
tr
em
en
d
o
u
s
d
ev
elo
p
m
en
t
we
ar
e
witn
ess
in
g
in
th
e
f
ield
o
f
in
f
o
r
m
atio
n
tech
n
o
lo
g
y
,
wh
ic
h
h
as
f
ac
ilit
ated
an
d
ac
ce
ler
ate
d
th
e
ac
ce
s
s
o
f
in
f
o
r
m
atio
n
t
o
all
p
e
o
p
le,
a
n
d
b
ec
au
s
e
in
f
o
r
m
atio
n
is
th
e
tr
u
e
ess
en
ce
th
at
we
s
ee
k
as
s
tu
d
en
ts
,
r
esear
ch
er
s
,
an
d
ev
e
n
tea
ch
er
s
,
it
is
s
ig
n
if
ican
t
to
en
s
u
r
e
th
e
r
eliab
ilit
y
o
f
th
is
in
f
o
r
m
atio
n
th
at
f
l
o
ws
to
u
s
f
r
o
m
ev
er
y
wh
er
e.
W
e
h
av
e
r
ec
en
tly
witn
ess
ed
an
alar
m
in
g
in
cr
ea
s
e
in
th
e
u
s
e
o
f
s
o
cial
m
ed
ia
s
ites
b
y
p
eo
p
le
o
f
all
ag
es
an
d
c
u
ltu
r
es.
T
h
is
h
as
ca
u
s
ed
th
e
r
ap
id
an
d
ea
s
y
s
p
r
ea
d
o
f
in
f
o
r
m
atio
n
r
eg
ar
d
less
o
f
its
ac
cu
r
ac
y
an
d
r
eliab
ilit
y
.
A
r
ec
en
t
s
tu
d
y
h
as
f
o
u
n
d
th
at
f
ak
e
n
ews
is
s
p
r
ea
d
s
ix
tim
es f
aster
th
an
r
ea
l n
ews,
an
d
th
at
7
0
% o
f
th
is
f
ak
e
n
ews is r
ep
u
b
lis
h
ed
b
y
u
s
er
s
v
ia
s
o
ci
al
m
ed
ia
[
1
]
.
T
h
e
d
an
g
e
r
o
f
f
ak
e
n
ews
s
tem
s
f
r
o
m
th
e
f
ac
t
th
at
it
is
cr
ea
te
d
to
m
is
lead
o
r
d
ec
eiv
e
th
e
r
e
ad
er
o
r
to
in
f
lu
en
ce
p
eo
p
le
’
s
o
p
in
io
n
s
,
wh
eth
er
f
o
r
p
o
liti
ca
l
o
r
f
in
an
c
ial
p
u
r
p
o
s
es
[
2
]
.
Peo
p
le
wh
o
s
p
r
ea
d
f
ak
e
n
ews
u
s
e
s
ev
er
al
m
eth
o
d
s
to
d
ec
eiv
e
r
e
ad
er
s
an
d
m
ak
e
th
em
b
eliev
e
th
is
n
ews,
s
u
ch
as
u
s
in
g
b
o
ts
to
cr
ea
te
m
u
ltip
le
ac
co
u
n
ts
o
n
s
o
cial
m
ed
ia
s
ites
an
d
in
c
r
ea
s
e
th
e
n
u
m
b
e
r
o
f
“
s
h
ar
es
”
o
f
s
u
ch
n
ews.
An
o
th
e
r
m
eth
o
d
to
s
p
r
ea
d
f
ak
e
n
ews is b
y
cr
ea
tin
g
ad
v
er
tis
em
en
ts
o
n
f
ak
e
web
s
ites
th
at
r
esem
b
le
th
e
o
f
f
icial
n
ews sit
es
[
3
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
A
r
o
b
u
s
t m
eth
o
d
fo
r
d
etec
tin
g
fa
ke
n
ews
u
s
in
g
b
o
th
m
a
ch
in
e
… (
E
n
a
s
A
h
ma
d
A
likh
a
s
h
a
s
h
n
eh
)
1817
So
m
e
m
eth
o
d
s
h
a
v
e
b
ee
n
u
s
e
d
to
d
etec
t
t
h
e
ac
c
u
r
ac
y
an
d
r
eliab
ilit
y
o
f
th
e
n
ews
p
o
s
ted
o
n
th
ese
s
ites
.
A
m
eth
o
d
th
at
h
as
s
h
o
wn
ac
cu
r
ate
r
esu
lts
in
th
is
f
ield
is
m
ac
h
in
e
lan
g
u
ag
e.
T
h
is
m
eth
o
d
b
r
a
n
ch
es
o
f
f
f
r
o
m
ar
tific
ial
in
tellig
en
ce
;
it
u
s
es
d
ata
as
th
e
co
r
e
o
f
its
wo
r
k
.
T
h
e
m
eth
o
d
co
llects
d
ata
an
d
th
en
p
r
o
ce
s
s
es
an
d
an
aly
ze
s
it
to
u
s
e
f
o
r
p
r
e
d
ictio
n
.
Alg
o
r
ith
m
s
m
im
ic
th
e
way
in
wh
ich
h
u
m
an
s
lear
n
;
th
e
th
in
g
th
at
h
elp
s
p
r
o
d
u
ce
v
er
y
ac
cu
r
ate
r
esu
lts
.
Ma
ch
in
e
lear
n
in
g
(
ML
)
alg
o
r
ith
m
s
h
av
e
m
an
y
u
s
es
in
f
o
r
ec
asti
n
g
f
ield
s
s
u
ch
as
f
ir
e
in
cid
en
ts
v
is
u
aliza
tio
n
an
d
p
atter
n
r
ec
o
g
n
itio
n
[
4
]
,
a
win
d
tu
r
b
in
e
with
a
y
aw
m
ec
h
a
n
is
m
[
5
]
,
p
r
ed
i
ctio
n
o
f
ea
r
ly
-
s
tag
e
d
iab
etes
[
6
]
,
W
ea
th
er
p
r
e
d
ic
tio
n
[
7
]
,
t
h
e
n
ex
u
s
o
f
co
r
r
u
p
tio
n
an
d
n
o
n
-
p
er
f
o
r
m
in
g
lo
an
[
8
]
,
Ke
y
lo
g
g
e
r
d
etec
tio
n
[
9
]
,
an
d
m
an
y
o
th
er
ar
ea
s
.
Ho
wev
er
,
th
er
e
ar
e
m
a
n
y
ML
alg
o
r
ith
m
s
th
at
c
an
b
e
u
tili
ze
d
to
id
en
tif
y
f
ak
e
n
ews.
T
h
e
ac
cu
r
ac
y
o
f
e
ac
h
alg
o
r
ith
m
v
ar
ies
f
o
r
th
e
f
o
llo
win
g
r
ea
s
o
n
s
:
th
e
s
p
ec
if
ic
p
r
o
b
lem
,
ty
p
e
an
d
s
ize
o
f
d
ata,
an
d
t
h
e
ex
p
e
r
ien
ce
o
f
d
ata
s
cien
tis
ts
.
T
h
is
r
esear
ch
p
r
o
v
id
es
a
co
m
p
a
r
is
o
n
o
f
d
i
f
f
er
en
t
ML
;
alg
o
r
ith
m
s
th
at
d
etec
t
f
ak
e
n
e
ws;
n
am
ely
lo
g
is
tic
r
eg
r
ess
io
n
(
L
R
)
,
Gau
s
s
ian
Naïv
e
B
ay
es
(
NB
)
,
m
u
ltin
o
m
ial
NB
,
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
i
n
e
(
SVM)
,
lo
n
g
-
s
h
o
r
t
-
ter
m
m
e
m
o
r
y
(
L
STM
)
,
an
d
ca
p
s
u
le
n
etwo
r
k
.
A
d
ataset
co
n
tain
in
g
f
ak
e
n
ews a
n
d
r
ea
l
n
ews w
as u
s
ed
in
th
is
co
m
p
ar
i
s
o
n
.
Acc
u
r
ac
y
s
h
o
u
ld
b
e
m
et
wh
en
co
m
p
ar
in
g
ML
alg
o
r
ith
m
s
to
g
et
p
r
ec
is
e
r
e
s
u
lts
.
T
h
e
r
esear
ch
co
n
d
u
cte
d
b
y
Sh
ar
m
a
et
a
l
.
[
1
0
]
,
it
was
f
o
u
n
d
th
at
th
e
b
e
s
t
ac
cu
r
ate
alg
o
r
ith
m
is
LR
-
with
an
ac
cu
r
ac
y
o
f
6
5
%.
T
h
e
r
esear
ch
er
s
h
a
v
e
in
cr
ea
s
ed
th
e
ac
cu
r
ac
y
b
y
im
p
r
o
v
in
g
t
h
e
s
ea
r
ch
p
ar
am
eter
,
th
e
ac
cu
r
ac
y
o
f
th
e
alg
o
r
ith
m
r
ea
c
h
ed
7
5
%.
T
h
e
ac
cu
r
ac
y
o
f
ML
alg
o
r
ith
m
s
in
class
if
y
in
g
tex
t
d
ata
v
a
r
ies
d
ep
en
d
i
n
g
o
n
th
e
f
ea
tu
r
e
ex
t
r
ac
tio
n
m
et
h
o
d
an
d
th
e
s
p
ec
if
ic
alg
o
r
ith
m
.
T
h
e
f
a
s
ter
th
e
ex
tr
ac
tio
n
m
eth
o
d
,
t
h
e
m
o
r
e
ef
f
icien
tly
it
co
n
v
er
ts
th
e
tex
t
in
to
a
m
ac
h
i
n
e
-
r
ea
d
a
b
le
f
o
r
m
at.
T
h
is
also
ap
p
lies
to
ML
alg
o
r
ith
m
s
,
wh
er
e
th
e
ac
c
u
r
ac
y
o
f
th
e
r
esu
lts
v
ar
ies d
ep
en
d
in
g
o
n
th
e
tr
ain
in
g
d
ata.
T
h
is
h
as
b
ee
n
o
b
s
er
v
ed
b
y
th
e
r
esear
ch
c
o
n
d
u
cte
d
b
y
T
iwar
i
et
a
l
.
[
1
1
]
;
th
e
r
esu
lts
th
is
r
esear
ch
h
av
e
r
ea
ch
ed
in
d
icate
th
at
th
e
LR
alg
o
r
ith
m
h
as
th
e
h
ig
h
est
ac
cu
r
ac
y
am
o
n
g
o
th
er
alg
o
r
ith
m
s
-
ac
h
i
ev
in
g
7
1
%.
T
h
is
h
ig
h
ac
c
u
r
a
cy
p
er
ce
n
ta
g
e
is
r
ea
ch
ed
d
u
e
to
th
e
u
s
e
o
f
ter
m
f
r
eq
u
e
n
cy
in
v
er
s
e
d
o
c
u
m
en
t f
r
eq
u
en
cy
(
TF
-
I
DF
)
v
ec
to
r
.
E
v
er
y
alg
o
r
ith
m
s
h
o
u
ld
p
r
ep
r
o
ce
s
s
th
e
d
ata
s
o
th
at
it
is
ea
s
ier
to
d
ea
l
with
in
ap
p
r
o
p
r
iate
d
ata.
Pan
d
ey
et
a
l
.
[
1
2
]
h
av
e
p
r
o
p
o
s
ed
a
m
o
d
el
th
at
p
r
o
v
es
th
at
th
e
alg
o
r
ith
m
with
th
e
b
est
ac
c
u
r
ac
y
was
LR
-
with
9
0
.
4
6
%
,
th
en
KNN
with
9
8
.
9
8
%,
f
o
llo
wed
b
y
SVM
with
8
9
.
3
3
%,
f
o
llo
wed
b
y
NB
with
8
6
.
8
9
%,
an
d
f
in
ally
d
ec
is
io
n
tr
ee
with
7
3
.
3
3
%.
K
atsar
o
s
et
a
l
.
[
1
3
]
,
h
o
wev
er
,
i
n
d
icate
s
th
at
th
e
lo
n
g
er
th
e
tr
ain
in
g
tim
e
f
o
r
th
e
d
ata
is
,
th
e
h
ig
h
er
th
e
ac
cu
r
ac
y
o
f
th
e
alg
o
r
ith
m
s
is
ac
h
iev
ed
.
Katsar
o
s
et
a
l
.
[
1
3
]
h
a
v
e
ev
alu
ated
eig
h
t
alg
o
r
ith
m
s
:
n
am
ely
r
eg
r
ess
io
n
,
s
u
p
p
o
r
t
v
ec
t
o
r
class
if
icatio
n
,
m
u
lticlas
s
p
er
ce
p
tr
o
n
,
NB
,
d
ec
is
io
n
tr
ee
s
,
p
o
ly
n
o
m
ial,
r
an
d
o
m
f
o
r
ests
,
a
n
d
co
n
v
o
lu
tio
n
al
n
eu
r
al
n
etw
o
r
k
s
(
C
NNs)
u
s
in
g
th
r
ee
s
ets
o
f
f
ak
e
n
ews
d
ata;
d
if
f
er
en
t
in
th
e
e
f
f
icien
cy
a
n
d
s
p
ee
d
o
f
tr
ain
in
g
ea
ch
alg
o
r
ith
m
.
T
h
e
C
NN
alg
o
r
ith
m
h
as
s
h
o
wn
th
e
b
est
r
esu
lts
in
d
etec
tin
g
f
ak
e
n
ews
-
d
esp
ite
o
f
th
e
f
ac
t t
h
at
it r
eq
u
i
r
es a
r
elativ
ely
lar
g
e
tr
ai
n
in
g
t
im
e.
Ab
d
u
laziz
Al
-
B
ah
r
an
d
Ma
r
wan
Al
-
B
ah
r
h
av
e
co
llected
a
p
u
b
lic
d
ataset
co
n
tain
in
g
f
ak
e
an
d
f
alse
n
ews.
T
h
ey
h
av
e
ap
p
lied
f
o
u
r
m
ain
ML
alg
o
r
ith
m
s
:
r
an
d
o
m
f
o
r
est
,
NB
,
n
eu
r
al
n
etwo
r
k
,
a
n
d
d
ec
is
io
n
tr
ee
s
t
o
d
etec
t
f
ak
e
n
ews.
T
h
ey
h
av
e
f
o
u
n
d
o
u
t
th
at
th
e
NB
alg
o
r
ith
m
is
th
e
b
est
in
ter
m
s
o
f
ac
cu
r
ac
y
.
T
h
e
r
ea
s
o
n
wh
y
th
is
alg
o
r
ith
m
o
b
tain
ed
th
e
h
ig
h
est
ac
cu
r
ac
y
-
as
ex
p
l
ain
ed
b
y
th
ese
r
es
ea
r
ch
er
s
-
i
s
th
e
h
ig
h
r
ate
in
ca
lcu
latin
g
co
n
d
itio
n
al
p
r
o
b
a
b
ilit
ies
b
ased
o
n
th
e
o
cc
u
r
r
en
ce
o
f
th
e
tex
t
o
r
n
ews
in
d
iv
id
u
al
ly
,
as
it
ac
h
iev
ed
a
r
ate
o
f
9
9
%
[
1
4
]
.
J
ain
an
d
Kas
be
[
1
5
]
,
o
n
th
e
o
th
er
h
a
n
d
,
h
av
e
u
s
ed
th
e
NB
alg
o
r
ith
m
to
d
etec
t
f
ak
e
n
ews
am
o
n
g
Face
b
o
o
k
p
o
s
ts
.
T
h
ey
h
av
e
co
n
f
ir
m
ed
th
at
th
e
NB
alg
o
r
ith
m
h
as
s
h
o
wn
a
n
ac
c
u
r
ac
y
o
f
8
0
.
6
%
f
o
r
titl
es,
an
d
9
1
.
2
%
ac
cu
r
ac
y
f
o
r
tex
t
titl
e
s
.
W
h
en
u
s
in
g
t
h
e
n
g
r
am
s
tech
n
iq
u
e,
h
o
wev
er
,
th
e
tex
t
ac
cu
r
ac
y
h
as
in
cr
ea
s
ed
to
9
3
.
1
%.
T
h
e
titl
es
’
ac
cu
r
ac
y
,
o
n
th
e
o
th
er
h
an
d
,
h
as in
cr
ea
s
ed
s
lig
h
tly
to
8
0
.
7
%.
T
h
e
m
ain
m
o
tiv
ati
o
n
f
o
r
u
s
in
g
ML
to
d
etec
t
f
ak
e
n
ews
is
to
p
r
o
v
id
e
a
p
o
wer
f
u
l
s
o
lu
tio
n
t
o
u
s
er
s
an
d
h
elp
th
em
n
o
t
f
all
in
t
o
th
e
tr
a
p
o
f
m
is
in
f
o
r
m
atio
n
an
d
lies
.
Nag
ar
aja
et
a
l
.
[
1
6
]
h
av
e
ap
p
l
ied
ML
alg
o
r
ith
m
s
o
n
a
s
et
o
f
d
ata
u
s
in
g
s
em
a
n
tic
m
ea
s
u
r
em
en
t.
T
h
eir
r
esear
ch
in
d
icate
s
th
e
f
o
llo
win
g
r
esu
lts
:
th
e
SVM
alg
o
r
ith
m
is
th
e
m
o
s
t
ac
cu
r
at
e
-
with
an
ac
cu
r
ac
y
o
f
7
5
%
-
wh
ile
th
e
ac
cu
r
ac
y
o
f
NB
is
6
3
%.
T
h
e
r
ea
s
o
n
b
eh
in
d
th
ese
r
esu
lts
-
as
s
tat
ed
b
y
Nag
a
r
a
ja
et
a
l.
[
1
6
]
is
th
at
NB
s
ep
ar
ates
th
e
m
ea
s
u
r
em
en
t
f
ea
tu
r
es.
I
n
ad
d
itio
n
,
SVM
h
as
s
h
o
wn
ex
ce
llen
t
r
esu
lts
in
d
etec
tin
g
f
ak
e
n
ews.
T
h
is
is
co
n
f
ir
m
ed
i
n
th
e
r
esear
ch
p
ap
er
co
n
d
u
cte
d
b
y
B
aa
r
ir
an
d
Dje
f
f
al
[
1
7
]
.
T
h
ese
r
esear
ch
er
s
h
av
e
u
s
ed
a
b
ag
o
f
wo
r
d
s
f
o
r
th
e
m
o
s
t
co
m
m
o
n
wo
r
d
s
in
ad
d
itio
n
to
th
e
n
g
r
a
m
tech
n
iq
u
e.
T
o
o
b
tain
a
g
o
o
d
d
ata
r
ec
o
g
n
itio
n
r
ate,
Sh
ai
k
h
an
d
Patil
[
1
8
]
h
av
e
p
r
o
p
o
s
ed
a
m
o
d
el
t
h
at
ap
p
lie
s
th
e
f
o
llo
win
g
m
eth
o
d
s
an
d
to
ac
h
iev
e
th
e
f
o
llo
win
g
ac
cu
r
ac
y
r
ates:
SVM
in
d
icate
s
th
e
h
i
g
h
est
ac
cu
r
ac
y
o
f
9
5
.
0
5
%,
p
ass
iv
e
ag
g
r
es
s
iv
e
h
as
ac
h
iev
e
d
9
2
.
9
%,
an
d
NB
h
as
ac
h
ie
v
ed
8
4
.
0
5
6
.
X
(
f
o
r
m
er
l
y
k
n
o
wn
as
T
witter
)
is
an
o
th
er
p
latf
o
r
m
th
at
ca
n
co
n
tr
ib
u
te
to
s
p
r
ea
d
in
g
n
e
ws
r
ap
id
ly
s
in
ce
it
ac
h
iev
es
wid
esp
r
ea
d
cir
cu
latio
n
an
d
is
u
s
ed
b
y
in
te
r
n
atio
n
al
ce
leb
r
ities
.
Fo
r
th
is
r
ea
s
o
n
,
Ma
h
ir
et
a
l.
[
1
9
]
h
av
e
c
o
llected
d
ata
f
r
o
m
th
e
X
p
latf
o
r
m
b
y
u
s
in
g
ML
alg
o
r
ith
m
s
th
at
SVM
,
NB
m
eth
o
d
,
LR
,
an
d
r
ec
u
r
r
en
t
n
e
u
r
al
n
etwo
r
k
(
R
NN)
s
ep
ar
ately
.
T
h
ey
h
a
v
e
c
o
m
p
ar
ed
th
e
ac
cu
r
ac
y
o
f
ea
c
h
alg
o
r
ith
m
an
d
h
a
v
e
s
tated
th
e
f
o
llo
win
g
ac
cu
r
ac
y
r
ates:
NB
:
8
9
.
6
%,
SVM:
8
9
.
3
4
%,
LR
:
6
9
.
4
7
%,
th
e
n
eu
r
al
n
etwo
r
k
:
7
4
%
-
by
R
NN,
an
d
L
STM
:7
8
%.
NB
an
d
th
e
SVM
alg
o
r
ith
m
-
as
in
d
icate
d
b
y
th
e
r
esu
lts
-
h
av
e
o
b
tain
ed
th
e
b
est
r
esu
lts
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
36
,
No
.
3
,
Dec
em
b
er
20
24
:
1
8
1
6
-
1
8
2
6
1818
J
ain
et
a
l
.
[
2
0
]
p
r
o
p
o
s
e
a
m
o
d
el
th
at
u
s
es
th
e
f
o
llo
win
g
ML
alg
o
r
ith
m
s
:
NB
,
SVM,
an
d
NL
P.
T
h
is
m
o
d
el
h
as
ac
h
iev
ed
a
h
i
g
h
ac
cu
r
ac
y
r
ate
-
o
f
9
3
.
6
%.
Ah
m
ed
et
a
l.
[
2
1
]
h
a
v
e
p
r
o
v
e
d
th
at
u
s
in
g
ty
p
es
o
f
alg
o
r
ith
m
s
lead
s
to
o
b
tain
in
g
h
ig
h
ac
cu
r
ac
y
.
A
g
r
o
u
p
o
f
ML
alg
o
r
ith
m
s
h
a
v
e
b
ee
n
u
s
ed
to
d
etec
t
f
ak
e
n
ews
an
d
h
a
v
e
ac
h
iev
e
d
th
e
f
o
llo
w
in
g
ac
cu
r
ac
y
r
ates:
r
an
d
o
m
f
o
r
est
alg
o
r
ith
m
an
d
Per
ez
-
L
SVM
h
av
e
ac
h
ie
v
ed
9
9
%,
l
in
ea
r
SVM,
m
u
lti
-
lay
e
r
p
er
ce
p
t
r
o
n
,
b
ag
g
in
g
class
if
i
er
s
,
an
d
b
o
o
s
tin
g
class
if
ier
s
h
av
e
ac
h
ie
v
ed
9
8
%
ac
cu
r
ac
y
.
Mo
r
eo
v
e
r
,
th
er
e
we
r
e
m
an
y
d
if
f
er
e
n
ce
s
in
th
e
r
es
u
lts
f
o
r
ea
ch
g
r
o
u
p
,
all
alg
o
r
it
h
m
s
wer
e
ap
p
lied
to
th
em
in
d
iv
id
u
ally
an
d
co
llectiv
ely
o
n
4
d
atasets
.
Acc
o
r
d
in
g
to
th
eir
r
esu
lts
,
in
all
p
er
f
o
r
m
an
ce
m
ea
s
u
r
es,
th
e
alg
o
r
ith
m
s
in
t
h
e
en
s
em
b
le
w
er
e
b
etter
c
o
m
p
ar
e
d
to
t
h
e
s
in
g
le
alg
o
r
ith
m
,
b
u
t
at
th
e
s
in
g
le
alg
o
r
ith
m
lev
el
,
LR
h
ad
th
e
b
est ac
cu
r
ac
y
,
wit
h
an
av
e
r
ag
e
ac
cu
r
ac
y
o
f
m
o
r
e
th
an
9
0
%.
I
n
th
ei
r
s
tu
d
y
,
K
h
an
am
et
a
l
.
[
2
2
]
h
av
e
u
s
ed
th
e
f
o
llo
win
g
alg
o
r
ith
m
s
o
n
a
s
et
o
f
d
ata:
XG
B
o
o
s
t,
r
an
d
o
m
f
o
r
ests
,
NB
,
K
-
n
ea
r
est
n
eig
h
b
o
r
s
(
KNN)
,
d
ec
is
io
n
t
r
ee
,
an
d
SV
M
.
T
h
e
m
ai
n
g
o
al
was
to
tr
y
to
o
b
tain
a
class
if
icatio
n
m
o
d
el
th
at
is
h
ig
h
ly
ac
cu
r
ate
in
d
etec
tin
g
tr
u
e
a
n
d
f
ak
e
n
ews.
T
h
e
ac
c
u
r
ac
y
r
esu
lts
o
f
all
alg
o
r
ith
m
s
ar
e
v
e
r
y
clo
s
e;
th
e
SVM
alg
o
r
ith
m
h
as
h
ig
h
ac
c
u
r
ac
y
,
as
it
o
b
tai
n
ed
a
r
ate
o
f
7
3
%,
wh
ich
is
th
e
s
ec
o
n
d
af
ter
th
e
alg
o
r
ith
m
th
at
o
b
tain
ed
th
e
h
ig
h
est
ac
cu
r
ac
y
,
XG
B
o
o
s
t
,
wh
ich
ac
h
iev
ed
7
5
%,
wh
ile
NB
o
b
tain
ed
a
r
ate
o
f
6
8
%.
Ah
m
ed
a
n
d
R
am
asam
y
[
2
3
]
p
r
ed
ict
th
at
SVM
wo
u
ld
b
e
t
h
e
b
est
alg
o
r
ith
m
-
s
in
ce
it
d
o
es
n
o
t
u
s
e
p
r
o
b
a
b
ilit
y
d
is
tr
ib
u
tio
n
s
,
b
u
t
r
ath
er
u
s
es
th
e
co
n
ce
p
t
o
f
h
y
p
er
p
lan
es.
T
h
is
is
also
s
ee
n
i
n
th
e
NB
alg
o
r
ith
m
th
at
h
as
co
n
d
u
cted
a
n
ex
p
e
r
i
m
en
t
u
s
in
g
twen
ty
th
o
u
s
an
d
s
am
p
les
o
f
f
ak
e
n
ews
(
co
ll
ec
ted
f
r
o
m
s
ev
er
al
s
o
u
r
ce
s
)
.
T
h
is
ex
p
er
im
en
t
s
h
o
ws
th
at
th
e
n
eu
r
al
n
etwo
r
k
m
o
d
el
h
as
s
h
o
wn
b
etter
ac
cu
r
ac
y
r
esu
lts
th
an
th
e
r
est
o
f
th
e
alg
o
r
ith
m
s
.
NB
alg
o
r
ith
m
r
e
q
u
ir
es
h
ig
h
c
o
m
p
u
tatio
n
al
r
eq
u
ir
em
en
ts
,
as
it
h
as
ac
h
iev
ed
an
ac
cu
r
ac
y
o
f
9
2
%,
SVM,
o
n
th
e
o
th
er
h
an
d
,
h
as
o
b
tain
ed
7
6
.
8
%,
an
d
NB
h
as
o
b
t
ain
ed
6
8
.
4
%.
T
h
e
p
er
f
o
r
m
an
ce
o
f
ML
al
g
o
r
ith
m
s
in
d
etec
tin
g
f
ak
e
n
ews
s
ig
n
if
ican
tly
o
u
t
p
er
f
o
r
m
s
h
u
m
an
a
b
ilit
y
-
ac
co
r
d
in
g
t
o
W
aik
u
m
a
an
d
Go
s
wam
[
2
4
]
.
T
h
ese
r
esear
ch
e
r
s
h
av
e
s
u
c
ce
s
s
f
u
lly
u
s
ed
a
co
m
b
i
n
atio
n
o
f
m
ac
h
i
n
e
d
ata
alg
o
r
ith
m
s
an
d
h
a
v
e
r
ea
ch
ed
th
e
f
o
llo
win
g
ac
cu
r
ac
y
r
ates:
th
e
L
I
AR
en
s
em
b
le,
th
e
b
ag
g
in
g
class
if
ier
,
an
d
XGBo
o
s
t
alg
o
r
ith
m
s
h
av
e
o
b
t
ain
ed
ac
cu
r
ac
y
o
f
3
9
%,
an
d
r
an
d
o
m
f
o
r
est
h
as
ac
h
iev
e
d
an
ac
cu
r
ac
y
o
f
3
7
%.
Ho
wev
er
,
Gr
ad
ien
t
B
o
o
s
t
h
as
ac
h
iev
ed
an
o
v
er
all
ac
cu
r
ac
y
o
f
3
6
%
-
in
ter
m
s
o
f
r
ec
all
an
d
f
1
.
Ho
wev
er
,
af
te
r
r
ec
lass
if
y
in
g
,
u
s
in
g
b
in
ar
y
c
l
a
s
s
i
f
i
c
a
t
i
o
n
t
h
a
t
a
t
t
e
m
p
t
s
t
o
s
i
m
p
l
i
f
y
t
h
e
d
a
t
a
,
a
n
d
t
h
e
n
r
e
-
r
u
n
n
i
n
g
t
h
e
a
l
g
o
r
i
t
h
m
s
,
t
h
e
p
e
r
c
e
n
t
a
g
e
s
c
h
a
n
g
e
d
,
w
i
t
h
B
a
g
g
i
n
g
a
n
d
A
d
a
B
o
o
s
t
a
t
7
0
%
,
a
n
d
r
a
n
d
o
m
f
o
r
e
s
t
a
t
6
5
%
.
B
u
t
b
o
t
h
E
x
t
r
a
T
r
e
e
s
a
n
d
X
G
B
o
o
s
t
r
e
a
c
h
e
d
6
2
%
.
Ou
ass
il
et
a
l.
[
2
5
]
,
th
e
au
th
o
r
s
u
s
ed
a
co
m
b
i
n
atio
n
o
f
d
if
f
e
r
en
t
wo
r
d
e
m
b
ed
d
in
g
tech
n
iq
u
es
an
d
a
h
y
b
r
id
C
N
N
an
d
b
i
d
ir
ec
tio
n
al
lo
n
g
s
h
o
r
t
-
ter
m
m
em
o
r
y
(B
i
-
L
STM
)
m
o
d
el
t
o
d
etec
t
f
a
k
e
n
ews.
T
h
ey
tr
ai
n
ed
th
eir
ap
p
r
o
ac
h
o
n
th
e
W
E
L
F
ak
e
d
ataset.
T
h
e
b
est
ac
cu
r
ac
y
o
f
th
e
m
o
d
el
was
9
7
%.
T
h
e
b
est
m
o
d
el
was
g
en
er
ated
b
y
co
m
b
in
in
g
a
p
r
e
-
tr
ain
ed
W
o
r
d
2
Vec
C
B
OW
m
o
d
el
an
d
a
W
o
r
d
2
Vec
s
k
ip
-
wo
r
d
m
o
d
el
with
a
C
NN
o
n
B
i
-
L
STM
lay
er
s
.
Mo
s
t
p
r
ev
io
u
s
s
tu
d
ies
h
a
v
e
tr
i
ed
to
d
etec
t
f
ak
e
n
ews
u
s
in
g
t
r
ad
itio
n
al
ML
tech
n
i
q
u
es.
As
f
ar
as
we
k
n
o
w,
n
o
n
e
o
f
th
em
h
a
v
e
co
m
p
ar
ed
tr
ad
itio
n
al
tech
n
i
q
u
es
lik
e
SVM
,
LR
,
Gau
s
s
ian
NB
,
a
n
d
m
u
ltin
o
m
ial
NB
with
n
ewe
r
ap
p
r
o
ac
h
es
lik
e
ca
p
s
u
le
n
etwo
r
k
s
an
d
L
STM
.
T
h
e
co
m
p
a
r
is
o
n
was
m
ad
e
af
te
r
ap
p
ly
in
g
eith
er
th
e
TF
-
I
DF
o
r
W
o
r
d
2
Vec
to
a
ch
iev
e
th
e
b
est
ac
cu
r
ac
y
in
d
etec
tin
g
f
a
k
e
n
ews.
Fu
r
th
er
m
o
r
e,
th
is
p
ap
er
d
is
tin
g
u
is
h
es
its
elf
f
r
o
m
p
r
ev
io
u
s
s
tu
d
ies
b
y
u
s
in
g
a
n
ew
d
ataset
f
o
r
tr
ain
in
g
an
d
ev
alu
ati
n
g
b
o
th
tr
ad
itio
n
al
an
d
n
ewe
r
tec
h
n
iq
u
es.
T
h
e
m
a
in
co
n
tr
ib
u
tio
n
s
o
f
t
h
is
r
esear
ch
ar
e:
a)
Mo
d
er
n
tech
n
o
l
o
g
ies
h
av
e
b
e
en
u
s
ed
s
u
c
h
as
ar
tific
ial
i
n
tellig
en
ce
,
n
atu
r
al
lan
g
u
ag
e
p
r
o
ce
s
s
in
g
(
NL
P)
,
an
d
d
ata
a
n
aly
tics
to
d
etec
t f
a
k
e
in
f
o
r
m
atio
n
,
w
h
ich
p
r
o
d
u
c
ed
ex
ce
llen
t r
esu
lts
.
b)
T
h
is
r
esear
ch
p
u
s
h
es
th
e
b
o
u
n
d
ar
ies
o
f
f
ak
e
n
ews
an
d
r
ea
l
n
ews
class
if
icatio
n
b
ey
o
n
d
tr
a
d
itio
n
al
ap
p
r
o
ac
h
es
u
s
in
g
ML
a
n
d
D
L
alg
o
r
ith
m
s
.
T
h
ese
a
d
v
an
ce
d
tech
n
i
q
u
es
allo
w
ML
f
r
o
m
lar
g
e
d
atasets
,
wh
ich
in
tu
r
n
allo
ws
f
o
r
h
ig
h
-
ac
cu
r
ac
y
f
a
k
e
n
ews
d
etec
tio
n
.
T
h
is
is
lar
g
ely
b
ased
o
n
d
if
f
er
en
t
lin
g
u
is
tic
an
d
s
em
an
tic
f
ea
tu
r
es.
c)
T
h
e
u
s
e
o
f
W
o
r
d
2
Vec
a
n
d
T
F
-
I
DF
led
to
en
h
a
n
ce
d
s
em
a
n
tic
u
n
d
e
r
s
tan
d
in
g
o
f
tex
t
u
al
co
n
ten
t,
wh
ic
h
g
r
ea
tly
co
n
tr
ib
u
ted
to
a
m
o
r
e
co
m
p
lex
an
al
y
s
is
o
f
th
e
ch
ar
ac
ter
is
tics
o
f
f
ak
e
n
e
ws.
W
o
r
d
2
Vec
em
b
ed
d
in
g
s
wer
e
u
s
ed
th
at
ca
p
tu
r
e
th
e
s
em
an
tic
s
im
ilar
ity
b
etwe
en
wo
r
d
s
,
id
en
tif
y
in
g
th
e
im
p
o
r
tan
ce
o
f
T
er
m
s
m
ea
s
u
r
ed
b
y
T
F
-
I
DF w
eig
h
ts
,
wh
ich
f
o
c
u
s
o
n
th
e
f
r
e
q
u
en
cy
o
f
ter
m
s
in
d
o
c
u
m
en
ts
.
d)
T
h
is
r
esear
ch
in
clu
d
es
v
ar
io
u
s
ev
alu
atio
n
s
o
f
th
e
p
er
f
o
r
m
a
n
ce
o
f
ML
an
d
d
ee
p
lear
n
i
n
g
(
DL
)
m
o
d
els
in
d
etec
tin
g
f
ak
e
n
ews.
I
t
p
r
o
v
id
es
m
etr
ics
s
u
ch
as
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
-
s
co
r
e
.
T
h
er
ef
o
r
e,
th
is
r
esear
ch
co
n
tr
ib
u
tes
to
th
e
s
c
ien
tific
u
n
d
e
r
s
tan
d
in
g
o
f
th
e
ef
f
ec
tiv
en
ess
o
f
t
h
ese
m
eth
o
d
s
in
r
ea
l
-
wo
r
l
d
s
ce
n
ar
io
s
.
I
t p
r
o
v
es its
g
r
ea
t a
b
ilit
y
to
p
er
f
o
r
m
s
u
c
h
task
s
,
as it h
as a
ch
iev
ed
h
i
g
h
ac
cu
r
ac
y
.
T
h
e
r
e
m
ai
ni
n
g
s
e
ct
i
o
n
s
of
t
h
is
p
a
p
er
o
ur
ar
e
pr
e
s
e
nt
e
d
a
s
f
ol
lo
w
s
:
s
e
ct
i
o
n
2
e
xp
l
ai
n
s
th
e
b
a
s
i
c
m
et
h
od
ol
o
g
y.
I
n
s
ec
ti
on
3
p
r
e
s
e
nt
s
a
nd
di
s
c
u
s
s
e
s
t
h
e
r
e
s
ul
t
s
o
bt
ai
n
e
d
af
t
er
i
m
pl
e
m
e
n
ti
n
g
t
h
e
pr
op
o
s
e
d
m
et
h
od
.
F
i
n
al
l
y,
s
e
ct
i
o
n
4
pr
e
s
en
t
s
t
h
e
c
o
n
cl
u
s
i
on
s
of
o
ur
pr
op
o
s
e
d
m
o
d
el
a
nd
f
ut
ur
e
w
or
k
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
A
r
o
b
u
s
t m
eth
o
d
fo
r
d
etec
tin
g
fa
ke
n
ews
u
s
in
g
b
o
th
m
a
ch
in
e
… (
E
n
a
s
A
h
ma
d
A
likh
a
s
h
a
s
h
n
eh
)
1819
2.
M
E
T
H
O
D
T
h
e
m
eth
o
d
we
p
r
o
p
o
s
e
an
d
u
s
e
to
ad
d
r
ess
th
e
m
ain
c
o
n
tr
i
b
u
tio
n
s
o
f
t
h
is
s
tu
d
y
is
d
iv
id
e
d
in
to
f
o
u
r
m
ain
s
tag
es
as
s
h
o
wn
in
Fig
u
r
e
1
.
T
h
e
d
etails
o
f
th
e
f
o
u
r
s
tag
es
ar
e
ex
p
lain
ed
in
th
e
f
o
llo
win
g
s
u
b
s
ec
tio
n
s
.
Fig
u
r
e
1
. T
h
e
s
tag
es o
f
th
e
p
r
o
p
o
s
ed
m
eth
o
d
2
.
1
.
Da
t
a
s
et
T
h
e
d
ataset
u
s
ed
i
n
th
is
p
r
o
p
o
s
ed
m
eth
o
d
is
th
e
u
n
b
iased
W
E
L
Fak
e
d
ataset,
wh
ich
co
n
s
is
ts
o
f
7
2
,
1
3
4
n
ews
ar
ticles
co
n
tain
in
g
3
7
,
1
0
6
f
ak
e
n
ews
an
d
3
5
,
0
2
8
r
ea
l
n
ews.
T
h
is
d
ataset
h
as
b
ee
n
ca
r
ef
u
lly
cu
r
ated
,
class
if
ied
an
d
ch
ec
k
e
d
b
y
jo
u
r
n
alis
ts
to
en
s
u
r
e
th
e
v
alid
ity
o
f
th
e
d
ata.
T
h
e
W
E
L
Fak
e
d
ataset
is
a
co
m
b
in
atio
n
o
f
f
o
u
r
d
is
tin
ct
s
o
u
r
ce
s
:
R
eu
ter
s
,
Mc
I
n
ty
r
e,
C
ag
le,
an
d
B
u
zz
Feed
Po
lic
y
[
2
6
]
.
T
h
e
g
o
al
o
f
th
e
m
er
g
in
g
s
tr
ateg
y
is
to
av
o
i
d
o
v
er
f
itti
n
g
class
if
ier
s
.
2
.
2
.
P
re
pro
ce
s
s
ing
T
h
e
d
ata
is
p
r
ep
a
r
ed
in
th
is
s
tep
,
as
th
e
d
ata
is
u
s
u
ally
in
a
f
o
r
m
at
th
at
is
n
o
t
a
n
aly
za
b
le,
s
o
th
e
p
r
e
-
p
r
o
ce
s
s
in
g
s
tag
e
p
lay
s
an
im
p
o
r
tan
t
r
o
le
i
n
co
n
v
er
tin
g
th
i
s
d
ata
in
to
a
f
o
r
m
at
t
h
at
is
e
asy
to
h
a
n
d
le
a
n
d
r
aisi
n
g
th
e
q
u
ality
o
f
th
e
in
p
u
t
d
ata,
th
u
s
g
iv
in
g
ML
an
d
DL
alg
o
r
ith
m
s
an
o
p
p
o
r
tu
n
ity
to
p
er
f
o
r
m
m
o
r
e
p
o
wer
f
u
lly
an
d
ac
c
u
r
ately
,
a
s
th
is
was
d
o
n
e
in
th
is
s
te
p
.
T
h
e
s
tag
e
clea
n
s
th
e
tex
t
s
b
y
r
em
o
v
in
g
all
p
u
n
ctu
atio
n
an
d
s
to
p
wo
r
d
s
,
c
o
n
v
er
tin
g
all
tex
ts
to
lo
wer
ca
s
e,
an
d
th
en
cr
ea
tin
g
a
n
ew
“
f
u
lltex
t
”
co
lu
m
n
th
at
co
n
tain
s
ea
ch
tex
t c
o
m
b
in
e
d
with
its
titl
e.
2
.
3
.
F
e
a
t
ure
ex
t
r
a
ct
io
n
Featu
r
e
ex
tr
ac
tio
n
is
a
v
ital
p
r
o
ce
s
s
th
at
en
ab
les
u
s
to
co
n
v
e
r
t
th
e
d
ata
in
to
d
ig
ital
f
ea
tu
r
es
s
o
th
at
it
ca
n
b
e
p
r
o
ce
s
s
ed
with
o
u
t
af
f
ec
tin
g
th
e
o
r
i
g
in
al
d
ata
s
et
an
d
th
u
s
m
ea
n
in
g
f
u
l
in
f
o
r
m
atio
n
is
ex
tr
ac
te
d
f
r
o
m
p
r
e
-
p
r
o
ce
s
s
ed
tex
tu
al
d
ata.
I
n
o
u
r
p
r
o
p
o
s
ed
m
et
h
o
d
,
we
h
a
v
e
u
s
ed
ad
v
a
n
ce
d
an
d
m
o
s
t
wid
ely
u
s
ed
f
ea
tu
r
e
ex
tr
ac
tio
n
tech
n
i
q
u
es,
an
d
th
is
in
clu
d
es b
u
t is n
o
t lim
ited
to
:
−
TF
-
I
DF
v
ec
to
r
:
t
ex
t
d
ata
is
co
n
v
er
ted
in
to
d
ig
ital
v
ec
to
r
s
an
d
e
x
p
lain
s
th
e
i
m
p
o
r
ta
n
ce
o
f
wo
r
d
s
in
d
is
tin
g
u
is
h
in
g
b
etwe
en
r
ea
l n
e
ws an
d
f
ak
e
n
ews.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
36
,
No
.
3
,
Dec
em
b
er
20
24
:
1
8
1
6
-
1
8
2
6
1820
−
W
o
r
d
2
Vec
f
o
r
wo
r
d
em
b
ed
d
i
n
g
:
ea
ch
wo
r
d
is
r
ep
r
esen
ted
as
a
v
ec
to
r
a
n
d
t
h
u
s
ca
n
b
e
u
s
ed
to
r
e
p
r
esen
t
th
e
s
em
an
tic
r
elatio
n
s
h
ip
s
b
et
wee
n
wo
r
d
s
.
2
.
4
.
B
uil
din
g
t
he
m
et
ho
d
Af
ter
s
o
r
tin
g
th
e
d
ata
in
to
two
ca
teg
o
r
ies,
tr
ain
in
g
an
d
test
in
g
,
th
e
p
r
o
p
o
s
ed
m
eth
o
d
m
o
d
el
was
b
u
il
t
u
s
in
g
ML
an
d
DL
alg
o
r
ith
m
s
(
L
R
,
Gau
s
s
ian
NB
,
Po
ly
n
o
m
ial
NB
,
SVM,
C
ap
s
u
le
n
eu
r
al
n
etwo
r
k
(
C
ap
s
Net
)
,
L
STM
,
an
d
th
e
m
o
d
el
was b
u
i
lt o
n
ce
u
s
in
g
T
F
-
I
DF a
n
d
o
n
c
e
u
s
in
g
W
o
r
d
2
Vec
.
2
.
4
.
1
.
L
o
g
is
t
ic
re
g
re
s
s
io
n
LR
is
a
s
u
p
er
v
is
ed
ML
alg
o
r
ith
m
th
at
p
r
ed
icts
th
e
p
r
o
b
ab
ilit
y
o
f
a
b
in
ar
y
o
u
tco
m
e
b
y
an
al
y
zin
g
th
e
r
elatio
n
s
h
ip
s
b
etwe
en
in
d
e
p
en
d
en
t v
ar
iab
les.
T
h
e
f
o
llo
win
g
f
o
r
m
u
la
is
th
e
b
asic f
o
r
m
u
la
f
o
r
LR
b
y
(
1
)
:
(
)
=
1
1
+
−
(
1
)
t
h
is
r
ep
r
esen
ts
a
LR
eq
u
atio
n
,
wh
er
e
e
r
ep
r
esen
ts
th
e
n
atu
r
al
lo
g
ar
ith
m
b
ase,
an
d
x
r
ep
r
esen
ts
th
e
tr
an
s
f
o
r
m
ed
n
u
m
er
ical
in
p
u
t
[
2
7
]
.
LR
was
ch
o
s
en
b
ec
au
s
e
it
is
s
im
p
le
a
n
d
ea
s
y
to
in
ter
p
r
et,
in
ad
d
iti
o
n
to
its
s
u
itab
ilit
y
f
o
r
b
in
ar
y
class
if
icatio
n
task
s
.
2
.
4
.
2
.
G
a
us
s
ia
n
NB
Gau
s
s
ian
NB
is
a
ty
p
e
o
f
co
n
tin
u
o
u
s
p
r
o
b
ab
ilit
y
d
is
tr
ib
u
t
io
n
an
d
is
u
s
ed
i
n
class
if
icatio
n
task
s
.
T
h
er
ef
o
r
e,
it
was
ch
o
s
en
i
n
t
h
e
p
r
o
p
o
s
ed
m
eth
o
d
as
it
is
ch
ar
ac
ter
ized
b
y
s
im
p
licity
,
e
f
f
icien
cy
,
a
n
d
h
ig
h
ab
ilit
y
to
d
ea
l
with
d
ata.
I
ts
i
m
p
o
r
tan
ce
co
m
es
f
r
o
m
th
e
ce
n
tr
al
lim
it
th
eo
r
em
,
wh
er
e
t
h
e
av
er
ag
e
o
f
m
an
y
Sam
p
les
f
r
o
m
a
r
an
d
o
m
v
ar
ia
b
le
with
a
g
iv
en
m
ea
n
an
d
v
ar
ian
ce
ar
e
th
em
s
elv
es
a
r
an
d
o
m
v
ar
iab
le
-
th
eir
d
is
tr
ib
u
tio
n
as
th
e
n
u
m
b
er
o
f
s
am
p
les
in
cr
ea
s
es
co
n
v
er
g
es
t
o
a
n
o
r
m
al
d
is
tr
ib
u
tio
n
.
T
h
e
f
o
llo
win
g
f
o
r
m
u
la
is
th
e
b
asic f
o
r
m
u
la
f
o
r
Gau
s
s
ian
NB
b
y
(
2
)
:
(
)
=
1
√
2
,
2
−
(
−
,
)
2
2
,
2
(
2
)
wh
er
e
x
i
r
ep
r
esen
t th
e
s
p
ec
if
ic
in
p
u
t v
al
u
e
an
d
y
i r
ep
r
esen
t c
lass
lab
el
[
2
8
]
.
2
.
4
.
3
.
M
ultino
m
ia
l
NB
T
h
e
m
u
ltin
o
m
ial
NB
alg
o
r
ith
m
is
a
lear
n
in
g
m
eth
o
d
b
ase
d
o
n
th
e
p
r
in
ci
p
le
o
f
p
r
o
b
ab
i
lity
th
at
is
m
o
s
tly
u
s
ed
in
NL
P
.
I
t
is
a
n
al
g
o
r
ith
m
th
at
is
b
ased
m
ai
n
ly
o
n
B
ay
es
’
th
e
o
r
y
,
wh
er
e
it p
r
ed
icts
a
tex
t
tag
s
u
ch
as
an
em
ail
o
r
a
n
ewsp
ap
er
ar
ticle.
I
t
is
v
er
y
ef
f
ec
tiv
e
in
d
ea
lin
g
with
d
ata,
esp
ec
ially
d
ata
with
m
u
ltip
le
ca
teg
o
r
ies,
an
d
is
ch
a
r
ac
ter
i
ze
d
b
y
s
im
p
licity
in
m
o
d
elin
g
,
s
o
it
was
ch
o
s
en
i
n
th
e
p
r
o
p
o
s
ed
m
eth
o
d
.
I
t
ca
lcu
lates
th
e
p
r
o
b
a
b
ilit
y
o
f
an
e
v
en
t
o
cc
u
r
r
i
n
g
b
ased
o
n
i
ts
p
r
io
r
k
n
o
wled
g
e
o
f
th
e
cir
c
u
m
s
tan
ce
s
th
at
ar
e
r
elate
d
to
th
e
ev
en
t
.
I
t
is
b
ased
o
n
th
e
f
o
llo
win
g
f
o
r
m
u
la
th
at
h
elp
s
ca
lcu
late
th
e
p
r
o
b
ab
il
ity
o
f
tex
tu
al
tag
s
b
y
(
3
)
:
(
|
)
=
(
)
.
(
|
)
(
)
(
3
)
w
e
ca
lcu
late
th
e
p
r
o
b
ab
ilit
y
o
f
class
A
wh
en
p
r
ed
icto
r
B
is
alr
ea
d
y
p
r
o
v
i
d
ed
.
2
.
4
.
4
.
SVM
SVM
ar
e
s
u
p
er
v
is
ed
lear
n
in
g
alg
o
r
ith
m
s
u
s
ed
f
o
r
class
if
ic
atio
n
,
r
eg
r
ess
io
n
,
an
d
o
u
tlier
d
etec
tio
n
.
T
h
e
p
r
im
a
r
y
g
o
al
o
f
SVMs
is
to
f
in
d
a
h
y
p
er
p
lan
e
th
at
b
es
t
s
ep
ar
ates
d
ata
in
to
d
if
f
er
e
n
t
class
es.
T
h
e
SV
M
was
ch
o
s
en
in
th
e
p
r
o
p
o
s
ed
m
eth
o
d
d
u
e
to
its
ab
ilit
y
t
o
wo
r
k
well
in
h
i
g
h
-
d
im
e
n
s
io
n
al
s
p
ac
es
an
d
its
f
lex
ib
ilit
y
in
d
ea
lin
g
with
d
if
f
er
en
t
d
ata,
an
d
it
r
ec
o
r
d
ed
h
ig
h
p
e
r
f
o
r
m
an
ce
i
n
d
ata
class
if
icatio
n
.
T
h
e
f
o
llo
win
g
f
o
r
m
u
la
is
t
h
e
b
asic f
o
r
m
u
la
f
o
r
lin
ea
r
SVM
b
y
(
4
)
:
(
)
=
(
∑
.
+
)
=
1
)
(
4
)
w
h
er
e
“
x
”
r
e
p
r
esen
ts
th
e
in
p
u
t d
ata,
“
w
”
r
ep
r
esen
ts
th
e
weig
h
t f
o
r
ea
c
h
f
ea
tu
r
e,
an
d
“
b
”
is
th
e
b
ias ter
m
[
2
8
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
A
r
o
b
u
s
t m
eth
o
d
fo
r
d
etec
tin
g
fa
ke
n
ews
u
s
in
g
b
o
th
m
a
ch
in
e
… (
E
n
a
s
A
h
ma
d
A
likh
a
s
h
a
s
h
n
eh
)
1821
2
.
4
.
5
.
Wo
rd2
Vec
W
o
r
d
2
Vec
is
a
n
eu
r
al
n
et
wo
r
k
-
b
ased
alg
o
r
ith
m
t
h
at
l
ea
r
n
s
wo
r
d
em
b
ed
d
in
g
t
h
r
o
u
g
h
d
ig
ital
r
ep
r
esen
tatio
n
s
o
f
wo
r
d
s
th
a
t
ca
p
tu
r
e
th
eir
s
em
an
tic
an
d
s
y
n
tactic
r
elatio
n
s
h
ip
s
.
I
t
cr
ea
tes
v
ec
to
r
s
o
f
wo
r
d
s
th
at
ar
e
d
is
tr
ib
u
ted
d
i
g
itally
.
T
h
e
em
b
ed
d
in
g
p
r
o
c
ess
h
elp
s
cr
ea
te
an
ass
o
ciatio
n
o
f
wo
r
d
s
in
th
e
co
n
tex
t
with
s
im
ilar
m
ea
n
in
g
th
r
o
u
g
h
v
ec
to
r
s
.
T
h
e
f
o
llo
win
g
f
o
r
m
u
la
is
th
e
b
asic
f
o
r
m
u
la
f
o
r
W
o
r
d
2
Ve
c
b
y
(
5
)
:
(
|
)
=
∑
ex
p
(
.
)
=
1
ex
p
(
.
)
(
5
)
w
h
er
e
P
(
c|w
)
r
ep
r
esen
ts
th
e
co
n
d
itio
n
al
p
r
o
b
ab
ilit
y
o
f
th
e
co
n
te
x
t
wo
r
d
c
ac
co
r
d
in
g
to
th
e
tar
g
et
wo
r
d
w
.
So
v
c
r
ep
r
esen
ts
th
e
co
n
tex
t
w
o
r
d
c
an
d
v
w
r
e
p
r
esen
ts
th
e
ta
r
g
et
wo
r
d
w
,
b
u
t
exp
(
x
)
r
e
p
r
esen
ts
th
e
ex
p
o
n
en
tial
f
u
n
ctio
n
.
2
.
4
.
6
.
Ca
ps
ule neura
l net
wo
r
k
C
ap
s
u
le
n
eu
r
al
n
etwo
r
k
is
a
t
y
p
e
o
f
ar
tific
ial
n
eu
r
al
n
etwo
r
k
s
cr
ea
ted
to
en
h
a
n
ce
th
e
m
o
d
elin
g
o
f
h
ier
ar
ch
ical
r
elatio
n
s
h
ip
s
,
an
d
its
g
o
al
is
to
o
r
g
an
ize
b
io
lo
g
ical
n
eu
r
al
s
y
s
tem
s
s
o
c
lo
s
ely
an
d
r
o
b
u
s
tly
th
at
th
ey
ca
n
u
n
d
e
r
s
tan
d
b
io
lo
g
ica
lly
co
m
p
lex
v
is
u
al
h
ier
ar
ch
ies
an
d
h
as
a
v
er
y
h
ig
h
ab
ilit
y
to
r
ec
o
g
n
ize
co
m
p
lex
p
atter
n
s
an
d
r
elatio
n
s
h
ip
s
in
d
ata.
T
h
er
ef
o
r
e,
th
e
y
ar
e
ch
o
s
e
n
in
th
e
p
r
o
p
o
s
ed
m
et
h
o
d
.
T
h
e
f
o
llo
win
g
f
o
r
m
u
la
is
th
e
b
asic f
o
r
m
u
la
f
o
r
C
ap
s
Net
b
y
(
6
)
:
,
=
,
.
(
6
)
w
h
er
e
u
i
,
j
r
ep
r
esen
ts
th
e
p
r
ed
ictio
n
v
ec
to
r
f
r
o
m
ca
p
s
u
le
i
t
o
ca
p
s
u
le
j
,
x
i
r
e
p
r
esen
ts
th
e
in
p
u
t
d
ata,
an
d
w
i
r
ep
r
esen
ts
th
e
tr
an
s
f
o
r
m
atio
n
m
atr
ix
.
2
.
4
.
7
.
L
ST
M
L
STM
is
an
alg
o
r
ith
m
ic
R
NN
alg
o
r
ith
m
d
esig
n
ed
to
a
d
d
r
ess
th
e
v
an
is
h
in
g
g
r
a
d
ien
t
p
r
o
b
lem
in
h
er
en
t
in
R
NNs.
I
t
h
as
a
g
r
ea
t
ab
ilit
y
to
m
ain
tain
s
en
s
iti
v
ity
to
lo
n
g
-
ter
m
d
ep
en
d
en
cie
s
an
d
is
r
esp
o
n
s
ib
le
f
o
r
m
an
a
g
in
g
th
e
f
lo
w
o
f
in
f
o
r
m
atio
n
with
in
th
e
n
etwo
r
k
.
I
t
is
b
u
ilt
f
r
o
m
an
A
ce
ll
an
d
th
r
ee
g
ates
(
in
p
u
t,
o
u
tp
u
t,
an
d
f
o
r
g
et)
.
I
t
was
ch
o
s
en
in
th
e
p
r
o
p
o
s
ed
m
et
h
o
d
b
ec
au
s
e
it
is
v
e
r
y
s
u
itab
le
f
o
r
NL
P
,
as
it
h
as
th
e
ab
ilit
y
to
u
n
d
er
s
tan
d
an
d
p
r
o
ce
s
s
co
m
p
lex
s
eq
u
en
ce
s
o
f
in
f
o
r
m
atio
n
.
T
h
e
f
o
llo
win
g
f
o
r
m
u
la
is
th
e
b
asic
f
o
r
m
u
la
f
o
r
L
STM
b
y
(
7
)
:
ℎ
=
(
.
[
ℎ
−
1
,
]
+
(
7
)
w
h
er
e
x
i
r
ep
r
esen
ts
th
e
in
p
u
t
d
ata,
w
r
ep
r
esen
ts
th
e
weig
h
t
m
atr
ix
,
h
i−
1
r
ep
r
esen
ts
th
e
p
r
e
v
io
u
s
h
id
d
en
s
tate,
an
d
b
r
e
p
r
esen
ts
th
e
b
ias
v
e
cto
r
.
T
h
er
ef
o
r
e,
u
s
in
g
a
s
et
o
f
ML
m
eth
o
d
s
th
at
a
r
e
ch
a
r
ac
ter
ized
b
y
th
ei
r
s
im
p
licity
an
d
in
ter
p
r
etab
ilit
y
,
an
d
u
s
in
g
a
s
et
o
f
DL
th
at
h
el
p
s
to
id
en
tify
co
m
p
lex
p
atter
n
s
an
d
d
ep
en
d
en
cies
with
in
tex
tu
al
d
ata,
will
en
ab
l
e
u
s
to
d
etec
t
f
ak
e
n
ews
with
ac
cu
r
ac
y
a
n
d
h
ig
h
p
er
f
o
r
m
an
ce
,
an
d
ex
p
lo
r
e
th
e
im
p
ac
t
o
f
T
F
-
I
DF
an
d
W
o
r
d
2
Vec
o
n
p
e
r
f
o
r
m
an
ce
a
n
d
t
h
e
co
m
p
ar
is
o
n
b
etwe
en
th
e
m
.
F
o
r
th
e
p
er
f
o
r
m
an
ce
ev
alu
atio
n
o
f
th
e
p
r
o
p
o
s
ed
m
e
th
o
d
,
th
e
d
ataset
was sp
lit b
y
7
5
to
2
5
in
ter
m
s
o
f
tr
ain
i
n
g
to
test
in
g
n
ews.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
is
s
ec
tio
n
d
em
en
o
s
tr
ates
th
e
r
esu
lts
o
f
ap
p
ly
in
g
th
e
p
r
o
p
o
s
ed
m
eth
o
d
to
th
e
d
ata
s
et
,
wh
ich
-
as
m
en
tio
n
ed
in
t
h
e
p
r
ev
i
o
u
s
s
ec
tio
n
-
is
a
n
ews
d
ata
s
et
d
iv
id
ed
in
to
r
ea
l
n
ews
an
d
f
a
k
e
n
ew
s
.
T
h
e
d
ataset
was
d
iv
id
ed
in
t
o
tr
ain
in
g
(
7
5
%)
a
n
d
test
in
g
(
2
5
%).
Fig
u
r
e
2
s
h
o
ws
th
e
d
is
tr
ib
u
tio
n
o
f
th
e
class
es
in
th
e
d
ataset
a
f
ter
th
e
p
r
ep
r
o
ce
s
s
in
g
th
at
is
p
er
f
o
r
m
ed
,
w
h
er
e
th
e
s
ize
o
f
t
h
e
d
ataset
h
as
ch
a
n
g
ed
f
r
o
m
t
h
e
s
h
ap
e
(
7
2
1
3
4
,
4
)
-
b
ef
o
r
e
th
e
p
r
ep
r
o
ce
s
s
in
g
p
r
o
ce
s
s
–
to
th
e
s
h
a
p
e
(
7
1
5
3
7
,
4
)
-
af
ter
th
e
p
r
e
p
r
o
ce
s
s
in
g
p
r
o
ce
s
s
h
as
b
ee
n
ap
p
lied
.
Fu
r
th
er
m
o
r
e
,
Fig
u
r
e
2
d
em
o
n
s
tr
ates
th
at
th
er
e
is
n
o
im
b
alan
ce
p
r
o
b
lem
in
th
e
d
ataset.
Fig
u
r
e
3
d
ep
icts
t
h
e
d
is
tr
ib
u
tio
n
o
f
th
e
n
ews w
o
r
d
co
u
n
t.
I
n
th
e
p
r
o
p
o
s
ed
m
eth
o
d
,
th
e
f
o
llo
win
g
alg
o
r
ith
m
s
ar
e
u
s
ed
:
SVM,
LR
,
Gau
s
s
ian
NB
,
m
u
ltin
o
m
ial
NB
,
L
STM
,
an
d
ca
p
s
u
le
n
etwo
r
k
to
p
r
ed
ict
f
a
k
e
n
ews
u
s
in
g
T
F
-
I
DF
an
d
u
s
in
g
W
o
r
d
2
Vec
.
A
co
m
p
ar
is
o
n
o
f
th
e
p
er
f
o
r
m
an
ce
o
f
d
if
f
er
etn
t
alg
o
r
ith
m
s
h
as
b
ee
n
d
o
n
e
u
s
in
g
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
e
ca
ll,
an
d
F1
-
s
co
r
e.
T
h
e
d
if
f
er
e
n
ce
o
f
p
er
f
o
r
am
cn
e
is
o
b
s
er
v
ed
wh
en
u
s
in
g
T
F
-
I
DF
an
d
W
o
r
d
2
Vec
.
I
n
ad
d
iti
o
n
,
cr
o
s
s
-
v
alid
atio
n
h
as
b
ee
n
u
s
ed
to
r
ed
u
ce
o
v
e
r
f
itti
n
g
.
T
ab
le
1
s
h
o
ws
a
c
o
m
p
a
r
is
o
n
o
f
th
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
alg
o
r
ith
m
s
wh
en
u
s
in
g
T
F
-
I
DF,
an
d
T
ab
le
2
s
h
o
ws a
co
m
p
ar
is
o
n
o
f
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
alg
o
r
ith
m
s
wh
e
n
u
s
in
g
W
o
r
d
2
Vec
.
Fro
m
T
ab
le
s
1
an
d
2
,
w
e
c
an
co
n
clu
d
e
th
at
th
e
p
e
r
f
o
r
m
an
ce
o
f
th
e
s
ix
class
if
ier
s
wh
en
u
s
in
g
TF
-
I
DF
co
m
p
ar
ed
to
u
s
in
g
W
o
r
d
2
Vec
is
s
ig
n
if
ican
tly
d
if
f
er
en
t.
Fig
u
r
e
4
a
n
d
T
ab
le
1
d
ep
ict
th
at
am
o
n
g
th
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
36
,
No
.
3
,
Dec
em
b
er
20
24
:
1
8
1
6
-
1
8
2
6
1822
s
ix
clas
s
if
ier
s
,
L
STM
g
iv
es
th
e
m
o
s
t
p
r
o
m
in
en
t
r
esu
lt,
with
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
-
s
co
r
e
all
r
ea
ch
in
g
9
9
%.
Ho
wev
er
,
it
ac
h
iev
ed
9
8
%
in
ter
m
s
o
f
p
r
ec
is
io
n
.
L
ik
ewise,
ca
p
s
u
le
n
etwo
r
k
h
as
ac
h
iev
ed
9
7
%
ac
cu
r
ac
y
,
SVM
h
as
ac
h
iev
ed
9
6
%
ac
c
u
r
ac
y
,
LR
h
as
ac
h
iev
ed
9
5
%,
m
u
ltin
o
m
ial
NB
ac
h
iev
ed
8
5
%,
an
d
Gau
s
s
ian
NB
h
as
ac
h
iev
ed
8
3
%
-
wh
en
u
s
in
g
T
F
-
I
DF.
T
ab
le
2
an
d
Fig
u
r
e
5
,
d
em
o
n
s
tr
ate
th
at
wh
en
u
s
in
g
W
o
r
d
2
Vec
,
L
STM
,
an
d
ca
p
s
u
le
n
etwo
r
k
an
ac
cu
r
ac
y
lev
el
o
f
9
5
%
h
as
b
ee
n
ac
h
iev
ed
.
SVM
h
as
ac
h
iev
ed
9
3
%,
LR
h
as
ac
h
iev
ed
6
3
% a
cc
u
r
ac
y
,
m
u
lti
n
o
m
ial
NB
,
an
d
Gau
s
s
ian
NB
h
av
e
ac
h
iev
e
d
5
8
%.
Fig
u
r
e
2
. T
h
e
d
is
tr
ib
u
tio
n
o
f
t
h
e
d
ata
in
th
e
d
ata
s
et
Fig
u
r
e
3
. T
h
e
d
is
tr
ib
u
tio
n
o
f
t
h
e
n
ews w
o
r
d
c
o
u
n
t
T
ab
le
1
.
C
o
m
p
a
r
is
o
n
o
f
th
e
p
e
r
f
o
r
m
a
n
ce
o
f
all
alg
o
r
ith
m
s
u
s
in
g
T
F
-
I
DF
C
l
a
s
si
f
i
e
r
A
c
c
u
r
a
c
y
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
F1
-
s
c
o
r
e
S
V
M
0
.
9
6
0
.
9
6
0
.
9
6
0
.
9
6
Lo
g
i
s
t
i
c
r
e
g
r
e
ssi
o
n
0
.
9
5
0
.
9
5
0
.
9
5
0
.
9
5
G
a
u
ss
i
a
n
NB
0
.
8
3
0
.
8
3
0
.
8
3
0
.
8
3
M
u
l
t
i
n
o
m
i
a
l
NB
0
.
8
5
0
.
8
5
0
.
8
5
0
.
8
5
LSTM
0
.
9
9
0
.
9
8
0
.
9
9
0
.
9
9
C
a
p
su
l
e
n
e
t
w
o
r
k
0
.
9
7
0
.
9
5
0
.
9
9
0
.
9
7
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
A
r
o
b
u
s
t m
eth
o
d
fo
r
d
etec
tin
g
fa
ke
n
ews
u
s
in
g
b
o
th
m
a
ch
in
e
… (
E
n
a
s
A
h
ma
d
A
likh
a
s
h
a
s
h
n
eh
)
1823
T
ab
le
2
.
C
o
m
p
a
r
is
o
n
o
f
th
e
p
e
r
f
o
r
m
a
n
ce
o
f
all
alg
o
r
ith
m
s
u
s
in
g
W
o
r
d
2
Vec
C
l
a
s
si
f
i
e
r
A
c
c
u
r
a
c
y
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
F1
-
s
c
o
r
e
S
V
M
0
.
9
3
0
.
9
3
0
.
9
3
0
.
9
3
Lo
g
i
s
t
i
c
r
e
g
r
e
ssi
o
n
0
.
6
3
0
.
6
2
0
.
6
3
0
.
6
2
G
a
u
ss
i
a
n
NB
0
.
5
8
0
.
5
8
0
.
5
8
0
.
5
7
M
u
l
t
i
n
o
m
i
a
l
NB
0
.
5
8
0
.
5
8
0
.
5
8
0
.
5
7
LSTM
0
.
9
4
0
.
9
3
0
.
9
6
0
.
9
4
C
a
p
su
l
e
n
e
t
w
o
r
k
0
.
9
4
0
.
9
4
0
.
9
5
0
.
9
4
Fig
u
r
e
4
.
T
h
e
p
er
f
o
r
m
a
n
ce
m
e
tr
ics co
m
p
ar
is
o
n
u
s
in
g
TF
-
I
D
F
Fig
u
r
e
5
.
T
h
e
p
er
f
o
r
m
a
n
ce
m
e
tr
ics co
m
p
ar
is
o
n
u
s
in
g
W
o
r
ld
2
Vec
Fro
m
Fig
u
r
e
6
we
ca
n
co
n
cl
u
d
e
th
at
u
s
in
g
T
F
-
I
DF
with
a
lg
o
r
ith
m
s
h
as
ac
h
iev
ed
h
ig
h
e
r
ac
cu
r
ac
y
th
an
W
o
r
d
2
Vec
-
as
in
d
icate
d
in
T
ab
le
s
1
an
d
2
.
T
h
is
i
s
d
u
e
to
th
e
f
o
llo
win
g
r
ea
s
o
n
s
:
TF
-
I
DF,
(
wh
ich
d
ep
en
d
s
o
n
th
e
f
r
e
q
u
en
c
y
o
f
th
e
wo
r
d
in
t
h
e
tex
t)
f
o
cu
s
es
o
n
th
e
im
p
o
r
tan
ce
o
f
th
e
wo
r
d
,
wh
ile
W
o
r
d
2
Vec
d
ep
en
d
s
o
n
th
e
s
em
an
tic
r
elat
io
n
s
h
ip
s
b
etwe
en
wo
r
d
s
an
d
cr
ea
tes
co
n
tin
u
o
u
s
r
ep
r
esen
tat
io
n
s
f
o
r
all
w
o
r
d
s
.
T
h
e
r
e
p
r
esen
tatio
n
s
cr
ea
te
d
b
y
th
is
m
eth
o
d
ar
e
less
d
y
n
am
i
c
th
an
th
e
r
ep
r
esen
tatio
n
s
c
r
ea
ted
b
y
T
F
-
I
DF.
T
h
e
p
er
f
o
r
m
an
ce
o
f
W
o
r
d
2
Vec
is
af
f
ec
ted
b
y
th
e
s
ize
o
f
th
e
v
e
cto
r
,
wh
ile
th
e
p
er
f
o
r
m
an
ce
o
f
T
F
-
I
DF
d
o
es
n
o
t
d
ep
en
d
o
n
t
h
e
s
ize
o
f
th
e
v
ec
t
o
r
.
Mo
r
eo
v
er
,
we
ca
r
r
ied
o
u
t
a
c
o
m
p
ar
is
o
n
b
etwe
en
o
u
r
p
r
o
p
o
s
ed
m
eth
o
d
wh
ich
is
class
if
ic
atio
n
u
s
in
g
ML
class
if
ier
s
an
d
DL
.
Ad
d
itio
n
ally
,
we
c
o
m
p
a
r
ed
o
u
r
r
esu
lts
with
s
o
m
e
o
th
e
r
r
esea
r
ch
ar
ticles
wh
ich
wo
r
k
ed
o
n
th
e
s
am
e
d
ataset.
I
n
Ou
ass
il
et
a
l.
[
2
5
]
,
r
esear
ch
er
s
ac
h
iev
ed
an
ac
cu
r
ac
y
o
f
9
7
%
b
y
co
m
b
in
i
n
g
a
p
r
e
-
tr
ain
ed
W
o
r
d
2
Vec
C
B
O
W
m
o
d
el
an
d
W
o
r
d
2
Vec
Sk
i
p
-
W
o
r
d
m
o
d
el
with
C
NN
o
n
B
I
L
STM
lay
er
s
.
Ou
r
p
r
o
p
o
s
ed
m
eth
o
d
p
r
o
v
id
e
d
an
im
p
r
o
v
e
d
r
esu
lt f
o
r
th
e
L
STM
with
T
F
-
I
DF.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
36
,
No
.
3
,
Dec
em
b
er
20
24
:
1
8
1
6
-
1
8
2
6
1824
Fig
u
r
e
6
.
Acc
u
r
ac
y
c
o
m
p
ar
is
o
n
:
TF
-
I
DF v
er
s
u
s
W
o
r
d
2
Vec
f
o
r
all
alg
o
r
ith
m
s
Fin
ally
,
th
e
e
x
p
er
im
e
n
tal
r
esu
lts
s
h
o
w
th
at
we
ac
h
iev
ed
th
e
g
o
al
o
f
th
is
r
esear
ch
,
wh
ich
i
s
to
r
ea
ch
th
e
h
ig
h
est
ac
cu
r
ac
y
in
d
etec
t
in
g
f
a
k
e
n
ews.
W
o
r
d
2
Vec
wi
th
alg
o
r
ith
m
s
h
as
b
ee
n
u
s
ed
i
n
s
tead
o
f
T
F
-
I
DF.
Ho
wev
er
,
u
s
in
g
T
F
-
I
DF
with
alg
o
r
ith
m
s
h
as
ac
h
iev
ed
h
ig
h
er
ac
cu
r
ac
y
t
h
an
W
o
r
d
2
Vec
-
as
in
d
icate
d
in
T
ab
le
s
1
an
d
2
.
I
n
co
m
p
a
r
in
g
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
alg
o
r
ith
m
s
th
at
h
av
e
b
ee
n
u
s
ed
with
T
F
-
I
DF,
th
e
f
o
llo
win
g
r
esu
lts
ar
e
f
o
u
n
d
:
L
STM
h
as
ac
h
iev
ed
t
h
e
h
ig
h
est
ac
cu
r
ac
y
r
ate
o
f
9
9
%,
f
o
llo
wed
b
y
ca
p
s
u
le
n
etwo
r
k
w
ith
9
7
%
ac
cu
r
ac
y
,
SVM
ac
h
iev
in
g
9
6
%,
LR
ac
h
i
ev
in
g
9
5
%,
m
u
ltin
o
m
ial
NB
a
ch
iev
in
g
8
5
%,
an
d
Gau
s
s
ian
NB
ac
h
iev
in
g
8
3
%.
W
h
en
u
s
in
g
W
o
r
d
2
Vec
,
th
e
ac
cu
r
ac
y
h
as
d
ec
r
ea
s
ed
s
ig
n
if
ican
tly
in
s
o
m
e
alg
o
r
ith
m
s
.
L
STM
an
d
ca
p
s
u
l
e
n
etwo
r
k
h
av
e
ac
h
iev
ed
9
4
%
ac
cu
r
ac
y
,
an
d
SVM
h
as
ac
h
ie
v
ed
9
3
%
ac
cu
r
ac
y
.
T
h
e
r
est
o
f
th
e
al
g
o
r
ith
m
s
,
o
n
th
e
o
th
e
r
h
a
n
d
,
h
av
e
n
o
t
p
er
f
o
r
m
ed
well;
L
R
h
as
ac
h
iev
ed
6
3
%
ac
cu
r
ac
y
,
an
d
b
o
th
m
u
ltin
o
m
ial
NB
an
d
Gau
s
s
ian
Naiv
e
h
av
e
ac
h
iev
ed
5
8
%
B
ay
es.
T
h
e
L
STM
alg
o
r
ith
m
ac
h
iev
ed
t
h
e
b
est
ac
cu
r
ac
y
in
b
o
th
ex
p
er
im
en
ts
,
s
o
it
is
co
n
s
id
er
e
d
th
e
b
est.
C
ap
s
u
le
n
etwo
r
k
a
n
d
SVM
h
av
e
n
o
t
ac
h
iev
e
d
h
ig
h
ac
cu
r
ac
y
r
ates w
h
en
u
s
in
g
W
o
r
d
2
Vec
alth
o
u
g
h
t
h
eir
p
er
f
o
r
m
an
ce
is
b
etter
th
an
o
th
er
alg
o
r
i
th
m
s
.
4.
CO
NCLU
SI
O
N
T
h
e
wo
r
ld
is
cu
r
r
en
tly
s
u
f
f
er
i
n
g
f
r
o
m
a
m
ass
iv
e
s
p
r
ea
d
o
f
f
ak
e
n
ews,
wh
ich
h
as
n
eg
ativ
e
ef
f
ec
ts
o
n
s
o
cieties
an
d
m
ay
lead
to
s
ig
n
if
ican
tly
n
eg
ativ
e
co
n
s
eq
u
e
n
ce
s
.
I
n
th
is
r
esear
ch
,
a
p
r
o
p
o
s
al
was
p
r
esen
ted
to
d
etec
t
f
ak
e
n
ews
an
d
tr
u
e
n
ew
s
u
s
in
g
b
o
th
DL
an
d
ML
alg
o
r
ith
m
s
.
T
h
e
f
o
llo
win
g
m
et
h
o
d
s
h
av
e
b
ee
n
u
s
ed
in
th
is
r
esear
ch
: SVM
,
LR
,
Gau
s
s
ian
NB
,
m
u
ltin
o
m
ial
NB
,
L
S
T
M,
an
d
ca
p
s
u
le
n
etwo
r
k
.
T
h
i
s
r
esear
ch
in
d
icate
s
th
at
u
s
in
g
al
g
o
r
ith
m
s
with
T
F
-
I
DF
g
iv
es
b
etter
ac
cu
r
ac
y
r
e
s
u
lts
th
an
u
s
in
g
W
o
r
d
2
Vec
;
L
STM
h
as
ac
h
iev
ed
th
e
h
ig
h
est
ac
cu
r
ac
y
o
f
9
9
%
u
s
in
g
T
F
-
I
DF.
I
n
ad
d
itio
n
,
L
STM
an
d
ca
p
s
u
le
n
etwo
r
k
h
av
e
ac
h
iev
ed
th
e
h
ig
h
est
ac
cu
r
ac
y
o
f
9
4
%
u
s
in
g
W
o
r
d
2
Vec
.
T
h
e
ex
p
er
im
en
t
al
r
esu
lts
s
h
o
w
th
at
th
e
g
o
al
o
f
t
h
i
s
r
e
s
e
a
r
c
h
,
w
h
i
c
h
i
s
t
o
r
e
a
c
h
t
h
e
h
i
g
h
e
s
t
a
c
c
u
r
a
c
y
i
n
d
e
t
e
c
t
i
n
g
f
a
k
e
n
e
w
s
,
w
a
s
a
c
h
i
e
v
e
d
.
F
o
r
f
u
t
u
r
e
s
t
u
d
i
e
s
,
t
h
e
r
e
s
e
a
r
c
h
e
r
s
o
f
t
h
i
s
p
a
p
e
r
w
i
l
l
a
i
m
t
o
a
d
d
s
e
m
i
-
s
u
p
e
r
v
i
s
e
d
l
e
a
r
n
i
n
g
t
o
i
m
p
r
o
v
e
a
n
d
s
t
r
e
n
g
t
h
e
n
t
h
e
p
r
o
p
o
s
e
d
m
e
t
h
o
d
.
ACK
NO
WL
E
DG
E
M
E
NT
S
T
h
e
au
th
o
r
s
ex
ten
d
t
h
eir
ap
p
r
e
ciatio
n
to
th
e
Ar
ab
Op
en
Un
i
v
er
s
ity
f
o
r
f
u
n
d
in
g
th
is
wo
r
k
.
RE
F
E
R
E
NC
E
S
[
1
]
P
.
D
h
i
m
a
n
,
A
.
K
a
u
r
,
C
.
I
w
e
n
d
i
,
a
n
d
S
.
K
.
M
o
h
a
n
,
“
A
s
c
i
e
n
t
o
m
e
t
r
i
c
a
n
a
l
y
s
i
s
o
f
d
e
e
p
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
e
s
f
o
r
d
e
t
e
c
t
i
n
g
f
a
k
e
n
e
w
s,
”
E
l
e
c
t
r
o
n
i
c
s
,
v
o
l
.
1
2
,
n
o
.
4
,
p
.
9
4
8
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
e
l
e
c
t
r
o
n
i
c
s
1
2
0
4
0
9
4
8
.
[
2
]
F
.
Z
i
mm
e
r
,
K
.
S
c
h
e
i
b
e
,
M
.
S
t
o
c
k
,
a
n
d
W
.
G
.
S
t
o
c
k
,
“
F
a
k
e
n
e
w
s
i
n
so
c
i
a
l
me
d
i
a
:
b
a
d
a
l
g
o
r
i
t
h
ms
o
r
b
i
a
se
d
u
sers?,
”
J
o
u
r
n
a
l
o
f
I
n
f
o
rm
a
t
i
o
n
S
c
i
e
n
c
e
T
h
e
o
r
y
a
n
d
Pra
c
t
i
c
e
,
v
o
l
.
7
,
n
o
.
2
,
p
p
.
4
0
-
5
3
,
2
0
1
9
,
d
o
i
:
1
0
.
1
6
3
3
/
JI
S
Ta
P
.
2
0
1
9
.
7
.
2
.
4
.
[
3
]
N
.
H
a
j
l
i
,
U
.
S
a
e
e
d
,
M
.
Ta
j
v
i
d
i
,
a
n
d
F
.
S
h
i
r
a
z
i
,
“
S
o
c
i
a
l
b
o
t
s
a
n
d
t
h
e
s
p
r
e
a
d
o
f
d
i
s
i
n
f
o
r
ma
t
i
o
n
i
n
s
o
c
i
a
l
m
e
d
i
a
:
t
h
e
c
h
a
l
l
e
n
g
e
s
o
f
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
,
”
Bri
t
i
s
h
J
o
u
r
n
a
l
o
f
M
a
n
a
g
e
m
e
n
t
,
v
o
l
.
3
3
,
n
o
.
3
,
p
p
.
1
2
3
8
-
1
2
5
3
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
1
1
/
1
4
6
7
-
8
5
5
1
.
1
2
5
5
4
.
[
4
]
J.
R
.
A
s
o
r
,
J
.
L
.
L
e
r
i
o
s,
S
.
B
.
S
a
p
i
n
,
J.
O
.
P
a
d
a
l
l
a
n
,
a
n
d
C
.
A
.
C
.
B
u
a
m
a
,
“
F
i
r
e
i
n
c
i
d
e
n
t
s
v
i
s
u
a
l
i
z
a
t
i
o
n
a
n
d
p
a
t
t
e
r
n
r
e
c
o
g
n
i
t
i
o
n
u
si
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms,
”
I
n
d
o
n
e
s
i
a
n
J
o
u
r
n
a
l
o
f
El
e
c
t
ri
c
a
l
E
n
g
i
n
e
e
r
i
n
g
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
(
I
J
EEC
S
)
,
v
o
l
.
2
2
,
n
o
.
3
,
p
p
.
1
4
2
7
-
1
4
3
5
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s
.
v
2
2
.
i
3
.
p
p
1
4
2
7
-
1
4
3
5
.
[
5
]
S
.
B
.
A
b
h
i
e
t
a
l
.
,
“
A
n
i
n
t
e
l
l
i
g
e
n
t
w
i
n
d
t
u
r
b
i
n
e
w
i
t
h
y
a
w
m
e
c
h
a
n
i
s
m
u
si
n
g
mac
h
i
n
e
l
e
a
r
n
i
n
g
t
o
r
e
d
u
c
e
h
i
g
h
-
c
o
s
t
sen
s
o
r
s q
u
a
n
t
i
t
y
,
”
I
n
d
o
n
e
si
a
n
J
o
u
r
n
a
l
o
f
El
e
c
t
ri
c
a
l
E
n
g
i
n
e
e
r
i
n
g
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
(
I
J
E
EC
S
)
,
v
o
l
.
3
1
,
n
o
.
1
,
p
p
.
1
0
-
2
1
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s
.
v
3
1
.
i
1
.
p
p
1
0
-
2
1
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
A
r
o
b
u
s
t m
eth
o
d
fo
r
d
etec
tin
g
fa
ke
n
ews
u
s
in
g
b
o
th
m
a
ch
in
e
… (
E
n
a
s
A
h
ma
d
A
likh
a
s
h
a
s
h
n
eh
)
1825
[
6
]
R
.
M
.
H
.
L
.
F
l
o
r
e
s,
L
.
H
.
M
a
c
a
t
a
n
g
a
y
,
S
.
M
.
G
.
G
a
r
c
i
a
,
a
n
d
J
.
R
.
M
e
l
o
,
“
C
o
mp
a
r
a
t
i
v
e
a
n
a
l
y
s
i
s
i
n
t
h
e
p
r
e
d
i
c
t
i
o
n
o
f
e
a
r
l
y
-
st
a
g
e
d
i
a
b
e
t
e
s
u
s
i
n
g
m
u
l
t
i
p
l
e
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,
”
I
n
d
o
n
e
s
i
a
n
J
o
u
r
n
a
l
o
f
E
l
e
c
t
ri
c
a
l
E
n
g
i
n
e
e
r
i
n
g
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
(
I
J
EEC
S
)
,
v
o
l
.
3
2
,
n
o
.
2
,
p
.
1
3
,
N
o
v
e
mb
e
r
2
0
2
3
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s.
v
3
2
.
i
2
.
[
7
]
B
.
G
o
v
a
r
d
h
a
n
a
n
d
E
.
A
.
B
a
b
u
,
“
W
e
a
t
h
e
r
p
r
e
d
i
c
t
i
o
n
u
s
i
n
g
r
a
n
d
o
m
f
o
r
e
st
mac
h
i
n
e
l
e
a
r
n
i
n
g
m
o
d
e
l
,
”
I
n
d
o
n
e
si
a
n
J
o
u
rn
a
l
o
f
El
e
c
t
r
i
c
a
l
En
g
i
n
e
e
r
i
n
g
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
(
I
J
E
EC
S
)
,
2
0
2
1
,
p
p
.
1
2
0
8
-
1
2
1
5
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s
.
v
2
2
.
i
2
.
p
p
1
2
0
8
-
1
2
1
5
.
[
8
]
S
.
M
a
sr
o
m,
R
.
A
.
R
a
h
m
a
n
,
N
.
H
.
M
.
S
h
u
k
r
i
,
N
.
A
.
Y
a
h
y
a
,
M
.
Z.
A
.
R
a
s
h
i
d
,
a
n
d
N
.
B
.
Za
k
a
r
i
a
,
“
T
h
e
n
e
x
u
s
o
f
c
o
r
r
u
p
t
i
o
n
a
n
d
n
o
n
-
p
e
r
f
o
r
m
i
n
g
l
o
a
n
:
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
,
”
I
n
d
o
n
e
si
a
n
J
o
u
r
n
a
l
o
f
E
l
e
c
t
ri
c
a
l
E
n
g
i
n
e
e
ri
n
g
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
(
I
J
EE
C
S
)
,
v
o
l
.
3
2
,
n
o
.
2
,
p
p
.
838
-
8
4
4
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s.
v
3
2
.
i
2
.
p
p
8
3
8
-
8
4
4
.
[
9
]
M
.
S
.
A
l
s
u
b
a
i
e
,
S
.
H
.
A
t
a
w
n
e
h
,
a
n
d
M
.
S
.
A
b
u
a
l
-
R
u
b
,
“
B
u
i
l
d
i
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
m
o
d
e
l
w
i
t
h
h
y
b
r
i
d
f
e
a
t
u
r
e
s
e
l
e
c
t
i
o
n
t
e
c
h
n
i
q
u
e
f
o
r
k
e
y
l
o
g
g
e
r
d
e
t
e
c
t
i
o
n
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
A
d
v
a
n
c
e
s
i
n
S
o
f
t
C
o
m
p
u
t
i
n
g
a
n
d
I
t
s
A
p
p
l
i
c
a
t
i
o
n
s,
v
o
l
.
1
5
,
n
o
.
2
,
2
0
2
3
,
d
o
i
:
1
0
.
1
5
8
4
9
/
I
JA
S
C
A
.
2
3
0
7
2
0
.
0
3
.
[
1
0
]
U
.
S
h
a
r
ma
,
S
.
S
a
r
a
n
,
a
n
d
S
.
M
.
P
a
t
i
l
,
“
F
a
k
e
n
e
w
s d
e
t
e
c
t
i
o
n
u
s
i
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
C
re
a
t
i
v
e
Re
se
a
rc
h
T
h
o
u
g
h
t
s (I
J
C
RT)
,
v
o
l
.
8
,
n
o
.
6
,
p
p
.
5
0
9
-
5
1
8
,
2
0
2
0
,
d
o
i
:
1
0
.
2
2
2
1
4
/
i
j
r
a
s
e
t
.
2
0
2
0
.
6
1
2
5
.
[
1
1
]
V
.
T
i
w
a
r
i
,
R
.
G
.
Le
n
n
o
n
,
a
n
d
T.
D
o
w
l
i
n
g
,
“
N
o
t
e
v
e
r
y
t
h
i
n
g
y
o
u
r
e
a
d
i
s
t
r
u
e
!
F
a
k
e
n
e
w
s
d
e
t
e
c
t
i
o
n
u
s
i
n
g
mac
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms,
”
i
n
2
0
2
0
3
1
s
t
I
ri
sh
S
i
g
n
a
l
s
a
n
d
S
y
s
t
e
m
s
C
o
n
f
e
re
n
c
e
(
I
S
S
C
)
,
2
0
2
0
:
I
EEE,
p
p
.
1
-
4
,
d
o
i
:
1
0
.
1
1
0
9
/
I
S
S
C
4
9
9
8
9
.
2
0
2
0
.
9
1
8
0
2
0
6
.
[
1
2
]
S
.
P
a
n
d
e
y
,
S
.
P
r
a
b
h
a
k
a
r
a
n
,
N
.
S
.
R
e
d
d
y
,
a
n
d
D
.
A
c
h
a
r
y
a
,
“
F
a
k
e
n
e
w
s
d
e
t
e
c
t
i
o
n
f
r
o
m
o
n
l
i
n
e
me
d
i
a
u
s
i
n
g
mac
h
i
n
e
l
e
a
r
n
i
n
g
c
l
a
ss
i
f
i
e
r
s,
”
i
n
J
o
u
rn
a
l
o
f
Ph
y
si
c
s:
C
o
n
f
e
re
n
c
e
S
e
ri
e
s,
v
o
l
.
2
1
6
1
,
n
o
.
1
,
p
.
0
1
2
0
2
7
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
8
8
/
1
7
4
2
-
6
5
9
6
/
2
1
6
1
/
1
/
0
1
2
0
2
7
.
[
1
3
]
D
.
K
a
t
s
a
r
o
s
,
G
.
S
t
a
v
r
o
p
o
u
l
o
s,
a
n
d
D
.
P
a
p
a
k
o
s
t
a
s
,
“
W
h
i
c
h
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
p
a
r
a
d
i
g
m
f
o
r
f
a
k
e
n
e
w
s
d
e
t
e
c
t
i
o
n
?
,
”
i
n
I
EEE
/
WIC
/
A
C
M
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
W
e
b
I
n
t
e
l
l
i
g
e
n
c
e
,
2
0
1
9
,
p
p
.
3
8
3
-
3
8
7
.
[
1
4
]
A
.
A
l
b
a
h
r
a
n
d
M
.
A
l
b
a
h
a
r
,
“
A
n
e
m
p
i
r
i
c
a
l
c
o
m
p
a
r
i
s
o
n
o
f
f
a
k
e
n
e
w
s
d
e
t
e
c
t
i
o
n
u
s
i
n
g
d
i
f
f
e
r
e
n
t
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms,
”
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
1
,
n
o
.
9
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
4
5
/
3
3
5
0
5
4
6
.
3
3
5
2
5
5
2
.
[
1
5
]
A
.
J
a
i
n
a
n
d
A
.
K
a
s
b
e
,
“
F
a
k
e
n
e
w
s
d
e
t
e
c
t
i
o
n
,
”
i
n
2
0
1
8
I
EE
E
I
n
t
e
rn
a
t
i
o
n
a
l
S
t
u
d
e
n
t
s
’
C
o
n
f
e
re
n
c
e
o
n
El
e
c
t
ri
c
a
l
,
E
l
e
c
t
r
o
n
i
c
s
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
(
S
C
EEC
S
)
,
2
0
1
8
,
I
EEE,
p
p
.
1
-
5
,
d
o
i
:
1
0
.
1
1
0
9
/
S
C
E
EC
S
.
2
0
1
8
.
8
5
4
6
9
4
4
.
[
1
6
]
A
.
N
a
g
a
r
a
j
a
,
K
.
N
.
S
o
u
my
a
,
A
.
S
i
n
h
a
,
J.
V
.
R
.
K
u
m
a
r
,
a
n
d
P
.
N
a
y
a
k
,
“
F
a
k
e
n
e
w
s
d
e
t
e
c
t
i
o
n
u
si
n
g
mac
h
i
n
e
l
e
a
r
n
i
n
g
me
t
h
o
d
s,
”
i
n
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
D
a
t
a
S
c
i
e
n
c
e
,
E
-
l
e
a
rn
i
n
g
a
n
d
I
n
f
o
rm
a
t
i
o
n
S
y
st
e
m
s
2
0
2
1
,
2
0
2
1
,
p
p
.
1
8
5
-
1
9
2
,
d
o
i
:
1
0
.
1
1
4
5
/
3
4
6
0
6
2
0
.
3
4
6
0
7
5
3
.
[
1
7
]
N
.
F
.
B
a
a
r
i
r
a
n
d
A
.
D
j
e
f
f
a
l
,
“
F
a
k
e
n
e
w
s d
e
t
e
c
t
i
o
n
u
s
i
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
i
n
2
0
2
0
2
n
d
I
n
t
e
r
n
a
t
i
o
n
a
l
w
o
r
k
sh
o
p
o
n
h
u
m
a
n
-
c
e
n
t
ri
c
sm
a
rt
e
n
v
i
r
o
n
m
e
n
t
s
f
o
r
h
e
a
l
t
h
a
n
d
w
e
l
l
-
b
e
i
n
g
(
I
H
S
H
)
,
2
0
2
1
,
I
EEE,
p
p
.
1
2
5
-
1
3
0
,
d
o
i
:
1
0
.
1
1
0
9
/
I
H
S
H
5
1
6
6
1
.
2
0
2
1
.
9
3
7
8
7
4
8
.
[
1
8
]
J.
S
h
a
i
k
h
a
n
d
R
.
P
a
t
i
l
,
“
F
a
k
e
n
e
w
s
d
e
t
e
c
t
i
o
n
u
si
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
i
n
2
0
2
0
I
EEE
I
n
t
e
r
n
a
t
i
o
n
a
l
S
y
m
p
o
s
i
u
m
o
n
S
u
st
a
i
n
a
b
l
e
En
e
r
g
y
,
S
i
g
n
a
l
Pr
o
c
e
ssi
n
g
a
n
d
C
y
b
e
r
S
e
c
u
r
i
t
y
(
i
S
S
S
C
)
,
2
0
2
0
,
I
EEE,
p
p
.
1
-
5
,
d
o
i
:
1
0
.
1
1
0
9
/
i
S
S
S
C
5
0
9
4
1
.
2
0
2
0
.
9
3
5
8
8
9
0
.
[
1
9
]
E
.
M
.
M
a
h
i
r
,
S
.
A
k
h
t
e
r
,
a
n
d
M
.
R
.
H
u
q
,
“
D
e
t
e
c
t
i
n
g
f
a
k
e
n
e
w
s
u
s
i
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
m
s
,
”
i
n
2
0
1
9
7
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
S
m
a
r
t
C
o
m
p
u
t
i
n
g
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
s
(
I
C
S
C
C
)
,
2
0
1
9
,
I
E
E
E
,
p
p
.
1
-
5
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
S
C
C
.
2
0
1
9
.
8
8
4
3
6
1
2
.
[
2
0
]
A
.
Jai
n
,
A
.
S
h
a
k
y
a
,
H
.
K
h
a
t
t
e
r
,
a
n
d
A
.
K
.
G
u
p
t
a
,
“
A
smar
t
sy
s
t
e
m
f
o
r
f
a
k
e
n
e
w
s
d
e
t
e
c
t
i
o
n
u
si
n
g
mac
h
i
n
e
l
e
a
r
n
i
n
g
,
”
i
n
2
0
1
9
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
ss
u
e
s
a
n
d
c
h
a
l
l
e
n
g
e
s
i
n
i
n
t
e
l
l
i
g
e
n
t
c
o
m
p
u
t
i
n
g
t
e
c
h
n
i
q
u
e
s
(
I
C
I
C
T
)
,
2
0
1
9
,
v
o
l
.
1
,
I
EEE,
p
p
.
1
-
4
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
I
C
T4
6
9
3
1
.
2
0
1
9
.
8
9
7
7
6
5
9
.
[
2
1
]
I
.
A
h
ma
d
,
M
.
Y
o
u
saf,
S
.
Y
o
u
saf,
a
n
d
M
.
O
.
A
h
ma
d
,
“
F
a
k
e
n
e
w
s
d
e
t
e
c
t
i
o
n
u
s
i
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
e
n
s
e
mb
l
e
me
t
h
o
d
s,
”
C
o
m
p
l
e
x
i
t
y
,
v
o
l
.
2
0
2
0
,
p
p
.
1
-
1
1
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
0
/
8
8
8
5
8
6
1
.
[
2
2
]
Z
.
K
h
a
n
a
m
,
B
.
A
l
w
a
s
e
l
,
H
.
S
i
r
a
f
i
,
a
n
d
M
.
R
a
s
h
i
d
,
“
F
a
k
e
n
e
w
s
d
e
t
e
c
t
i
o
n
u
s
i
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
e
s
,
”
i
n
I
O
P
C
o
n
f
e
r
e
n
c
e
S
e
r
i
e
s
:
M
a
t
e
r
i
a
l
s
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
2
0
2
1
,
v
o
l
.
1
0
9
9
,
n
o
.
1
:
I
O
P
P
u
b
l
i
s
h
i
n
g
,
p
.
0
1
2
0
4
0
,
d
o
i
:
1
0
.
1
0
8
8
/
1
7
5
7
-
8
9
9
X
/
1
0
9
9
/
1
/
0
1
2
0
4
0
.
[
2
3
]
F
.
A
h
m
a
d
a
n
d
R
.
L
o
k
e
s
h
k
u
m
a
r
,
“
A
c
o
mp
a
r
i
s
o
n
o
f
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms
i
n
f
a
k
e
n
e
w
s d
e
t
e
c
t
i
o
n
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
n
Em
e
rg
i
n
g
T
e
c
h
n
o
l
o
g
i
e
s,
v
o
l
.
1
0
,
n
o
.
4
,
p
p
.
1
7
7
-
1
8
3
,
2
0
1
9
.
[
2
4
]
L.
W
a
i
k
h
o
m
a
n
d
R
.
S
.
G
o
sw
a
mi
,
“
F
a
k
e
n
e
w
s
d
e
t
e
c
t
i
o
n
u
si
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
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
m
e
n
t
s
i
n
C
o
m
p
u
t
i
n
g
and
Ma
n
a
g
e
m
e
n
t
(
I
C
AC
M),
2
0
1
9
,
d
o
i
:
1
0
.
2
1
3
9
/
ssr
n
.
3
4
6
2
9
3
8
.
[
2
5
]
M.
-
A
.
O
u
a
ss
i
l
,
B
.
C
h
e
r
r
a
d
i
,
S
.
H
a
mi
d
a
,
M
.
Er
r
a
mi
,
O
.
E
.
G
a
n
n
o
u
r
,
a
n
d
A
.
R
a
i
h
a
n
i
,
“
A
f
a
k
e
n
e
w
s
d
e
t
e
c
t
i
o
n
sy
st
e
m
b
a
se
d
o
n
c
o
m
b
i
n
a
t
i
o
n
o
f
w
o
r
d
e
m
b
e
d
d
e
d
t
e
c
h
n
i
q
u
e
s
a
n
d
h
y
b
r
i
d
d
e
e
p
l
e
a
r
n
i
n
g
mo
d
e
l
,
”
I
n
t
e
rn
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
A
p
p
l
i
c
a
t
i
o
n
s,
v
o
l
.
1
3
,
n
o
.
1
0
,
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
0
6
1
.
[
2
6
]
P
.
K
.
V
e
r
m
a
,
P
.
A
g
r
a
w
a
l
,
I
.
A
m
o
r
i
m
,
a
n
d
R
.
P
r
o
d
a
n
,
“
W
E
L
F
a
k
e
:
w
o
r
d
e
m
b
e
d
d
i
n
g
o
v
e
r
l
i
n
g
u
i
s
t
i
c
f
e
a
t
u
r
e
s
f
o
r
f
a
k
e
n
e
w
s
d
e
t
e
c
t
i
o
n
,
”
I
E
E
E
T
r
a
n
s
a
c
t
i
o
n
s
o
n
C
o
m
p
u
t
a
t
i
o
n
a
l
S
o
c
i
a
l
S
y
s
t
e
m
s
,
v
o
l
.
8
,
n
o
.
4
,
p
p
.
8
8
1
-
8
9
3
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
T
C
S
S
.
2
0
2
1
.
3
0
6
8
5
1
9
.
[
2
7
]
M
.
K
.
C
h
u
n
g
,
“
I
n
t
r
o
d
u
c
t
i
o
n
t
o
l
o
g
i
st
i
c
r
e
g
r
e
ssi
o
n
,
”
a
rXi
v
p
re
p
ri
n
t
a
rXi
v
:
2
0
0
8
.
1
3
5
6
7
,
2
0
2
0
,
d
o
i
:
1
0
.
4
8
5
5
0
/
a
r
X
i
v
.
2
0
0
8
.
1
3
5
6
7
.
[
2
8
]
F
.
P
e
d
r
e
g
o
sa
e
t
a
l
.
,
“
S
c
i
k
i
t
-
l
e
a
r
n
:
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
i
n
p
y
t
h
o
n
,
”
t
h
e
J
o
u
r
n
a
l
o
f
m
a
c
h
i
n
e
L
e
a
rn
i
n
g
rese
a
r
c
h
,
v
o
l
.
1
2
,
p
p
.
2
8
2
5
-
2
8
3
0
,
2
0
1
1
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
En
a
s
Ah
m
a
d
Alik
h
a
sh
a
shn
e
h
is
a
n
a
ss
istan
t
p
ro
fe
ss
o
r
a
t
th
e
C
o
ll
e
g
e
o
f
In
fo
rm
a
ti
o
n
Tec
h
n
o
l
o
g
y
a
n
d
Co
m
p
u
ter
S
c
ien
c
e
,
Ya
rm
o
u
k
Un
i
v
e
rsity
,
J
o
rd
a
n
.
S
h
e
re
c
e
iv
e
d
a
B.
S
c
.
d
e
g
re
e
i
n
c
o
m
p
u
ter
sc
ien
c
e
fro
m
th
e
Al
Ba
lq
a
Ap
p
li
e
d
Un
iv
e
rsit
y
,
Jo
r
d
a
n
,
a
n
M
.
S
c
.
d
e
g
re
e
in
C
o
m
p
u
ter
a
n
d
I
n
fo
rm
a
ti
o
n
S
y
ste
m
s
fro
m
t
h
e
Ya
rm
o
u
k
Un
iv
e
rsity
,
Jo
r
d
a
n
,
a
n
o
t
h
e
r
M
.
S
c
.
d
e
g
re
e
in
S
c
ien
c
e
fro
m
t
h
e
P
u
r
d
u
e
U
n
iv
e
rsit
y
/
IUPUI
,
U
S
A,
a
n
d
a
P
h
.
D.
d
e
g
re
e
i
n
Co
m
p
u
ter
S
c
ien
c
e
fro
m
P
u
r
d
u
e
Un
iv
e
rsit
y
/
IUPUI
,
USA.
He
r
re
se
a
rc
h
a
re
a
s
a
r
e
m
a
c
h
in
e
lea
rn
in
g
,
d
e
e
p
lea
rn
in
g
,
NLP
,
a
n
d
p
a
tt
e
rn
re
c
o
g
n
it
i
o
n
.
S
h
e
is
As
si
sta
n
t
De
a
n
o
f
t
h
e
Co
l
leg
e
o
f
In
fo
rm
a
ti
o
n
Tec
h
n
o
lo
g
y
a
n
d
C
o
m
p
u
ter
S
c
ie
n
c
e
a
t
Ya
rm
o
u
k
Un
i
v
e
rsity
fro
m
2
0
2
3
t
o
n
o
w.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
e
n
a
s.a
@y
u
.
e
d
u
.
jo
.
Evaluation Warning : The document was created with Spire.PDF for Python.