T
E
L
K
O
M
NIKA
T
elec
o
mm
un
ica
t
io
n Co
m
pu
t
i
ng
E
lect
ro
nics
a
nd
Co
ntr
o
l
Vo
l.
2
3
,
No
.
2
,
A
p
r
il 2
0
2
5
,
p
p
.
3
2
9
~
3
3
9
I
SS
N:
1
6
9
3
-
6
9
3
0
,
DOI
: 1
0
.
1
2
9
2
8
/
T
E
L
KOM
NI
K
A
.
v
2
3
i2
.
2
6
1
1
0
329
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//telko
mn
ika
.
u
a
d
.
a
c.
i
d
Dete
c
ting fa
k
e
ne
w
s throug
h deep
l
ea
rning
:
a
cur
ren
t
sy
ste
m
a
tic
review
I
dza
Ais
a
ra
No
ra
bid
,
M
a
s
it
a
J
a
lil,
Ro
zniza
Ali
,
No
o
r
H
a
f
hiza
h Abd Ra
hi
m
A
r
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
R
e
se
a
r
c
h
I
n
t
e
r
e
st
G
r
o
u
p
,
F
a
c
u
l
t
y
o
f
C
o
mp
u
t
e
r
S
c
i
e
n
c
e
a
n
d
M
a
t
h
e
ma
t
i
c
s
,
U
n
i
v
e
r
si
t
i
M
a
l
a
y
si
a
T
e
r
e
n
g
g
a
n
u
,
K
u
a
l
a
T
e
r
e
n
g
g
a
n
u
,
M
a
l
a
y
si
a
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Feb
2
5
,
2
0
2
4
R
ev
i
s
ed
No
v
2
8
,
2
0
2
4
A
cc
ep
ted
Dec
2
6
,
2
0
2
4
T
h
is s
y
st
e
m
a
ti
c
r
e
v
ie
w ex
p
lo
re
s t
h
e
d
o
m
a
in
o
f
d
e
e
p
lea
rn
in
g
-
b
a
se
d
f
a
k
e
n
e
w
d
e
tec
ti
o
n
e
m
p
lo
y
in
g
a
d
v
a
n
c
e
d
se
a
rc
h
p
ra
c
ti
c
e
s
o
n
S
c
o
p
u
s
a
n
d
W
e
b
o
f
S
c
ien
c
e
(
W
o
S
)
d
a
tab
a
se
s
w
it
h
k
e
y
wo
rd
s
“
f
a
k
e
n
e
w
s,
”
“
d
e
e
p
lea
rn
in
g
,
”
a
n
d
“
m
e
th
o
d
.
”
T
h
e
stu
d
y
e
n
c
o
m
p
a
ss
e
s
3
3
a
rti
c
les
c
a
te
g
o
rize
d
in
to
th
re
e
m
a
in
t
h
e
m
e
s:
i
)
d
a
tas
e
t
a
n
d
b
e
n
c
h
m
a
rk
in
g
f
o
r
f
a
k
e
n
e
w
s
d
e
tec
ti
o
n
,
ii
)
m
u
lt
im
o
d
a
l
a
p
p
r
o
a
c
h
e
s
f
o
r
f
a
k
e
n
e
w
s
d
e
te
c
ti
o
n
,
a
n
d
i
ii
)
d
e
e
p
lea
rn
in
g
a
p
p
li
c
a
ti
o
n
s
a
n
d
tec
h
n
iq
u
e
s
f
o
r
f
a
k
e
n
e
ws
d
e
tec
ti
o
n
.
T
h
e
a
n
a
ly
sis
r
e
v
e
a
ls
th
e
sig
n
if
ica
n
c
e
o
f
c
u
ra
ted
d
a
tas
e
ts
a
n
d
r
o
b
u
st
b
e
n
c
h
m
a
rk
in
g
in
im
p
ro
v
in
g
th
e
e
f
f
ica
c
y
o
f
f
a
k
e
n
e
w
s
d
e
tec
ti
o
n
m
o
d
e
ls.
A
d
d
it
io
n
a
ll
y
,
th
e
re
v
iew
h
ig
h
li
g
h
ts
th
e
e
m
e
r
g
e
n
c
e
o
f
m
u
lt
i
m
o
d
a
l
a
p
p
ro
a
c
h
e
s
th
a
t
in
teg
ra
te
tex
tu
a
l
a
n
d
v
isu
a
l
in
f
o
rm
a
ti
o
n
f
o
r
im
p
ro
v
e
d
d
e
tec
ti
o
n
a
c
c
u
ra
c
y
.
T
h
e
f
in
d
in
g
s
c
larify
th
e
e
ss
e
n
ti
a
l
ro
le
o
f
d
e
e
p
lea
rn
in
g
a
p
p
li
c
a
ti
o
n
s,
e
m
p
h
a
siz
in
g
th
e
d
e
v
e
lo
p
m
e
n
t
o
f
so
p
h
isti
c
a
ted
m
o
d
e
ls
f
o
r
a
u
to
m
a
ted
id
e
n
ti
f
ica
ti
o
n
o
f
f
a
k
e
n
e
w
s.
T
h
is
s
y
st
e
m
a
ti
c
stu
d
y
a
d
d
s
t
o
a
th
o
r
o
u
g
h
g
ra
sp
o
f
c
u
rre
n
t
re
se
a
rc
h
tren
d
s
a
n
d
o
f
f
e
rs
in
sig
h
t
f
u
l
in
f
o
rm
a
ti
o
n
f
o
r
f
u
tu
re
d
e
v
e
lo
p
m
e
n
ts
in
t
h
e
f
ield
o
f
d
e
e
p
lea
rn
in
g
-
b
a
se
d
f
a
lse
n
e
w
s
id
e
n
ti
f
ica
ti
o
n
.
K
ey
w
o
r
d
s
:
Dee
p
lear
n
in
g
Ma
ch
i
n
e
lear
n
i
n
g
Misi
n
f
o
r
m
atio
n
d
etec
tio
n
Natu
r
al
la
n
g
u
a
g
e
p
r
o
ce
s
s
in
g
S
y
s
te
m
a
tic
r
ev
ie
w
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
:
No
o
r
Haf
h
iza
h
A
b
d
R
ah
i
m
A
r
ti
f
icial
I
n
telli
g
e
n
ce
R
esear
c
h
I
n
ter
est Gr
o
u
p
,
Facu
lt
y
o
f
C
o
m
p
u
ter
Scie
n
ce
an
d
Ma
t
h
e
m
atics
Un
i
v
er
s
iti Ma
la
y
s
ia
T
er
en
g
g
a
n
u
2
1
0
3
0
Ku
ala
Ner
u
s
,
T
er
en
g
g
a
n
u
,
Ma
la
y
s
ia
E
m
ail:
n
o
o
r
h
af
h
iza
h
@
u
m
t.e
d
u
.
m
y
1.
I
NT
RO
D
UCT
I
O
N
I
n
an
er
a
d
o
m
i
n
ated
b
y
d
ig
ital
i
n
f
o
r
m
atio
n
a
n
d
u
n
p
ar
alleled
co
n
n
ec
ti
v
it
y
,
t
h
e
wid
esp
r
ea
d
m
is
in
f
o
r
m
at
io
n
p
r
ese
n
ts
a
s
er
i
o
u
s
t
h
r
ea
t
to
t
h
e
co
r
e
o
f
s
o
ciet
al
co
n
v
er
s
atio
n
[
1
]
,
[
2
]
.
T
h
e
d
elib
er
ate
s
p
r
ea
d
o
f
m
is
lead
in
g
co
n
te
n
t,
o
f
ten
d
r
iv
en
b
y
m
al
icio
u
s
i
n
te
n
tio
n
s
,
er
o
d
es th
e
f
o
u
n
d
atio
n
s
o
f
an
in
f
o
r
m
ed
p
u
b
lic.
Giv
e
n
th
e
s
er
io
u
s
n
es
s
o
f
th
e
p
r
o
b
le
m
,
it
is
b
ec
o
m
i
n
g
m
o
r
e
an
d
m
o
r
e
i
m
p
o
r
tan
t
to
estab
li
s
h
r
o
b
u
s
t
m
ec
h
a
n
i
s
m
s
f
o
r
d
etec
tin
g
a
n
d
co
m
b
ati
n
g
f
a
k
e
n
e
w
s
.
T
h
is
ar
ticle
ai
m
s
to
in
v
esti
g
a
te
an
in
n
o
v
at
iv
e
ap
p
r
o
ac
h
to
th
is
ch
al
len
g
e
b
y
e
x
p
lo
r
in
g
d
ee
p
lear
n
i
n
g
,
a
b
r
an
ch
o
f
ar
ti
f
icia
l
in
telli
g
en
ce
(
A
I
)
th
a
t
h
a
s
p
r
o
v
en
to
b
e
v
er
y
e
f
f
ec
ti
v
e
i
n
id
en
ti
f
y
i
n
g
in
tr
icate
p
atter
n
s
i
n
lar
g
e
-
s
ca
le
d
atase
ts
[
3
]
,
[
4
]
.
T
h
e
r
ap
id
ev
o
lu
tio
n
o
f
co
m
m
u
n
ica
tio
n
tec
h
n
o
lo
g
ies,
p
ar
tic
u
lar
l
y
w
i
th
t
h
e
r
is
e
o
f
s
o
cial
m
ed
ia,
h
as
ac
ce
ler
ated
th
e
s
p
r
ea
d
o
f
in
f
o
r
m
atio
n
,
h
en
ce
co
m
p
licati
n
g
th
e
task
to
d
is
tin
g
u
i
s
h
b
et
w
ee
n
t
r
u
th
an
d
d
ec
ep
tio
n
.
C
o
n
v
en
t
io
n
al
m
eth
o
d
s
o
f
f
a
k
e
n
e
w
s
d
etec
tio
n
,
r
el
y
in
g
o
n
r
u
le
-
b
ased
s
y
s
te
m
s
an
d
m
an
u
a
l
f
ac
t
-
ch
ec
k
i
n
g
,
ar
e
p
r
o
v
in
g
in
ad
eq
u
a
te
g
iv
e
n
t
h
e
s
h
ee
r
v
o
l
u
m
e
an
d
s
o
p
h
is
tic
atio
n
o
f
m
is
i
n
f
o
r
m
atio
n
[
5
]
–
[
7
]
.
Dee
p
lear
n
in
g
,
h
ar
n
e
s
s
i
n
g
t
h
e
ca
p
ab
ilit
ies
o
f
n
eu
r
al
n
et
w
o
r
k
s
a
n
d
ad
v
an
ce
d
alg
o
r
ith
m
s
,
e
m
er
g
es
as
a
p
r
o
m
is
i
n
g
s
o
lu
tio
n
to
ad
d
r
ess
th
ese
s
h
o
r
tco
m
in
g
s
[
8
]
–
[
1
0
]
.
B
y
e
m
p
o
w
er
in
g
m
ac
h
in
e
s
to
lear
n
an
d
ad
ap
t
f
r
o
m
v
ast
d
atasets
,
d
ee
p
lear
n
in
g
m
o
d
els
ca
n
u
n
co
v
er
s
u
b
tle
p
atter
n
s
an
d
co
m
p
lex
d
etails
ass
o
ciate
d
w
i
th
f
a
k
e
n
e
w
s
,
th
er
eb
y
en
h
a
n
ci
n
g
o
u
r
ca
p
ac
it
y
to
id
en
ti
f
y
a
n
d
co
u
n
ter
d
ec
ep
tiv
e
n
ar
r
ativ
e
s
[
1
1
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
23
,
No
.
2
,
A
p
r
il
20
25
:
3
2
9
-
339
330
P
r
ev
io
u
s
s
t
u
d
ies
h
a
v
e
s
h
o
w
n
th
at
d
ee
p
lear
n
in
g
tech
n
iq
u
es
ca
n
b
e
ef
f
ec
t
iv
e
i
n
d
etec
tin
g
f
ak
e
n
e
w
s
.
Fo
r
in
s
tan
ce
,
a
s
t
u
d
y
[
1
2
]
h
a
s
in
v
e
s
ti
g
ated
th
e
p
r
ac
ticalit
y
o
f
u
tili
s
i
n
g
d
ee
p
lear
n
in
g
to
d
if
f
er
en
t
iate
f
al
s
e
in
f
o
r
m
atio
n
o
n
t
h
e
in
ter
n
et
j
u
s
t
b
ased
o
n
te
x
t
u
al
c
o
n
ten
t.
T
h
e
s
tu
d
y
d
e
m
o
n
s
tr
ated
th
e
p
r
ac
ticalit
y
o
f
d
ee
p
lear
n
in
g
ap
p
r
o
ac
h
es
in
tack
lin
g
t
h
e
s
er
io
u
s
p
r
o
b
lem
o
f
f
a
k
e
n
e
w
s
in
m
o
d
er
n
s
o
ciet
y
.
I
t p
r
e
s
en
ted
t
h
r
ee
u
n
iq
u
e
n
eu
r
al
n
e
t
w
o
r
k
s
tr
u
c
tu
r
es
w
it
h
o
n
e
o
f
th
e
m
u
tili
s
i
n
g
b
id
ir
ec
tio
n
al
en
co
d
er
r
ep
r
esen
tatio
n
s
f
r
o
m
tr
an
s
f
o
r
m
er
s
(
B
E
R
T
)
.
Fu
r
th
er
m
o
r
e,
Sas
tr
a
w
a
n
et
a
l.
[
1
3
]
d
em
o
n
s
tr
ated
th
e
e
f
f
ec
ti
v
en
e
s
s
co
n
v
o
lu
tio
n
al
n
eu
r
al
n
et
w
o
r
k
-
r
ec
u
r
r
en
t
n
e
u
r
al
n
et
w
o
r
k
s
(
C
NN
-
R
N
N)
f
u
s
io
n
-
b
ased
m
eth
o
d
s
in
d
etec
tin
g
f
a
k
e
n
e
w
s
,
h
ig
h
li
g
h
ti
n
g
t
h
e
ca
p
ab
ilit
y
o
f
d
ee
p
lear
n
i
n
g
-
b
ased
ap
p
r
o
ac
h
es
f
o
r
ac
h
iev
in
g
m
o
r
e
p
r
ec
is
e
i
n
t
h
e
d
etec
t
io
n
o
f
f
a
k
e
n
e
w
s
,
s
u
r
p
ass
in
g
t
h
e
p
er
f
o
r
m
an
ce
o
f
co
n
v
en
tio
n
al
m
ac
h
in
e
lear
n
i
n
g
tech
n
iq
u
e
s
.
I
n
ad
d
itio
n
,
Ha
m
ed
et
a
l.
[
1
4
]
p
r
esen
ted
an
ap
p
r
o
ac
h
u
tili
zin
g
a
b
id
ir
ec
tio
n
al
lo
n
g
s
h
o
r
t
-
ter
m
m
e
m
o
r
y
(
L
ST
M)
m
o
d
el,
a
f
o
r
m
o
f
n
eu
r
al
n
et
w
o
r
k
ar
ch
itect
u
r
e.
T
h
is
w
o
r
k
e
m
p
h
asized
th
e
ch
allen
g
in
g
n
at
u
r
e
o
f
au
to
m
ated
f
a
k
e
n
e
w
s
d
etec
tio
n
an
d
th
e
s
ig
n
i
f
ica
n
ce
o
f
cr
ea
tin
g
m
o
d
el
s
th
at
ar
e
ca
p
ab
le
o
f
u
n
d
er
s
tan
d
i
n
g
th
e
r
elate
d
n
ess
o
f
r
ep
o
r
ted
n
e
w
s
.
Mo
r
eo
v
er
,
Kau
s
ar
et
a
l.
[
1
5
]
s
ee
k
s
to
o
v
er
co
m
e
th
e
co
n
s
tr
a
in
ts
o
f
cu
r
r
en
t
f
a
k
e
n
e
w
s
d
etec
t
io
n
m
et
h
o
d
s
b
y
i
n
t
r
o
d
u
cin
g
a
h
y
b
r
id
m
o
d
el
t
h
at
i
n
teg
r
ate
s
N
-
g
r
a
m
a
n
d
T
F
-
I
DF
f
o
r
co
n
te
n
t
-
b
ased
f
ea
t
u
r
e
ex
tr
ac
tio
n
.
A
d
d
itio
n
all
y
,
it
e
m
p
lo
y
s
ad
v
a
n
ce
d
d
ee
p
le
ar
n
in
g
m
o
d
els
li
k
e
L
ST
M
o
r
B
E
R
T
f
o
r
s
eq
u
en
tial
f
ea
t
u
r
e
ex
tr
ac
tio
n
.
T
h
e
p
r
o
p
o
s
ed
m
o
d
el
h
a
s
ex
ce
p
tio
n
al
p
er
f
o
r
m
a
n
ce
,
ac
h
ie
v
i
n
g
i
m
p
r
es
s
iv
e
p
r
ec
is
io
n
.
Fu
r
t
h
er
m
o
r
e,
Ver
m
a
et
a
l.
[
1
6
]
in
tr
o
d
u
ce
s
th
e
m
es
s
a
g
e
cr
ed
ib
ilit
y
(
MCre
d
)
f
r
a
m
e
w
o
r
k
,
w
h
ic
h
co
m
b
i
n
es
b
o
th
B
E
R
T
an
d
C
NN
w
ith
N
-
g
r
a
m
f
ea
t
u
r
es,
f
o
r
g
lo
b
al
tex
t
s
e
m
an
tics
a
n
d
lo
ca
l
tex
t
s
e
m
an
t
ics,
r
esp
ec
tiv
el
y
.
T
h
is
f
r
a
m
e
w
o
r
k
ex
h
ib
ited
i
m
p
r
o
v
ed
p
r
ec
is
io
n
in
co
m
p
ar
is
o
n
to
t
h
e
ad
v
a
n
ce
d
m
o
d
els
cu
r
r
en
tl
y
ac
ce
s
s
ib
le
.
MCre
d
e
m
p
h
as
izes
th
e
i
m
p
o
r
tan
ce
o
f
in
teg
r
ati
n
g
b
o
th
lo
ca
l
a
n
d
g
lo
b
al
tex
t
s
e
m
an
tics
to
ac
h
ie
v
e
m
o
r
e
e
f
f
icie
n
t
d
etec
tio
n
o
f
f
a
k
e
n
e
w
s
.
E
x
p
a
n
d
in
g
t
h
e
h
o
r
i
zo
n
o
f
f
ak
e
n
e
w
s
d
etec
tio
n
,
Nad
ee
m
et
a
l.
[
1
7
]
p
r
o
p
o
s
e
a
h
y
b
r
id
H
y
p
r
o
B
er
t
m
o
d
el
th
a
t
i
n
te
g
r
ates
D
is
tilB
E
R
T
,
C
NN,
an
d
b
id
ir
ec
tio
n
a
l
g
ated
r
ec
u
r
r
en
t
u
n
it
s
(
B
iGR
U)
.
T
h
eir
w
o
r
k
s
h
o
w
c
ases
t
h
e
m
o
d
el
’
s
h
ig
h
er
p
er
f
o
r
m
a
n
ce
w
h
e
n
co
m
p
ar
ed
to
b
o
th
co
n
v
e
n
tio
n
al
m
et
h
o
d
s
an
d
co
n
te
m
p
o
r
ar
y
ap
p
r
o
ac
h
es,
in
d
icatin
g
t
h
e
p
o
ten
t
ial
o
f
h
y
b
r
id
ap
p
r
o
ac
h
es.
O
v
e
r
al
l
,
t
h
i
s
r
e
c
en
t
r
e
s
e
a
r
c
h
h
ig
h
l
ig
h
ts
t
h
e
th
e
c
o
n
s
t
an
t
ly
e
v
o
lv
in
g
n
at
u
r
e
o
f
f
ak
e
n
ew
s
d
e
t
e
c
ti
o
n
,
em
p
h
as
i
s
in
g
th
e
o
n
g
o
in
g
n
e
e
d
f
o
r
ef
f
i
c
ie
n
t
an
d
a
d
a
p
t
iv
e
d
e
e
p
l
e
a
r
n
in
g
m
o
d
e
ls
t
o
a
d
d
r
e
s
s
th
e
d
y
n
am
i
c
p
r
o
b
l
em
s
g
iv
en
b
y
th
e
r
a
p
i
d
g
r
o
w
th
o
f
m
is
in
f
o
r
m
a
t
i
o
n
s
t
r
a
t
eg
i
es
.
T
h
e
s
e
s
t
u
d
i
es
a
ls
o
h
i
g
h
l
ig
h
t
th
e
n
e
e
d
o
f
t
a
c
k
l
in
g
t
h
e
i
s
s
u
e
s
a
s
s
o
ci
a
t
e
d
w
i
th
au
t
o
m
a
t
e
d
f
ak
e
n
e
w
s
d
e
t
e
ct
i
o
n
,
as
w
el
l
a
s
th
e
n
e
e
d
f
o
r
m
o
r
e
a
d
v
an
c
e
d
m
o
d
el
s
c
a
p
a
b
l
e
o
f
d
e
t
e
r
m
in
in
g
th
e
r
e
la
t
e
d
n
e
s
s
o
f
r
e
p
o
r
t
e
d
n
ew
s
.
T
h
u
s
,
th
is
a
r
t
i
c
l
e
a
t
t
em
p
ts
t
o
o
f
f
e
r
an
i
n
-
d
e
p
t
h
r
ev
iew
o
f
th
e
l
a
n
d
s
c
a
p
e
o
f
f
ak
e
n
e
w
s
d
e
te
c
t
io
n
th
r
o
u
g
h
th
e
l
en
s
o
f
d
e
e
p
l
ea
r
n
in
g
.
I
t
w
il
l
ex
am
in
e
th
e
u
n
d
e
r
ly
in
g
th
e
o
r
e
ti
c
al
p
r
i
n
c
i
p
l
e
s
t
h
a
t
s
u
p
p
o
r
t
th
es
e
m
o
d
e
l
s
,
ex
p
l
o
r
in
g
h
o
w
n
eu
r
al
n
etw
o
r
k
s
c
an
in
d
e
p
en
d
en
t
ly
v
e
r
if
y
th
e
a
u
th
en
ti
c
ity
o
f
i
n
f
o
r
m
a
ti
o
n
.
A
d
d
it
i
o
n
a
lly
,
t
h
e
p
r
a
c
t
i
c
a
l
im
p
l
i
c
at
i
o
n
s
o
f
im
p
l
em
en
ti
n
g
d
e
e
p
l
ea
r
n
i
n
g
in
r
e
al
-
w
o
r
l
d
s
c
en
a
r
i
o
s
w
i
ll
b
e
e
x
am
in
e
d
,
in
c
lu
d
in
g
ch
a
ll
en
g
e
s
an
d
th
e
p
o
t
en
t
ia
l
im
p
a
c
t
o
n
th
e
b
r
o
a
d
e
r
i
n
f
o
r
m
a
ti
o
n
e
co
s
y
s
t
em
.
T
h
is
p
a
p
e
r
i
n
te
n
d
s
t
o
c
o
n
t
r
i
b
u
t
e
t
o
t
h
e
o
n
g
o
i
n
g
d
i
s
cu
s
s
i
o
n
o
n
s
t
r
en
g
th
en
in
g
in
f
o
r
m
at
i
o
n
c
h
an
n
el
s
ag
a
in
s
t
t
h
e
p
e
r
v
a
s
iv
e
t
h
r
ea
t
o
f
f
a
ls
e
n
ew
s
b
y
n
a
v
ig
a
t
in
g
th
e
i
n
te
r
s
e
ct
i
o
n
o
f
t
e
ch
n
o
l
o
g
y
,
in
f
o
r
m
a
ti
o
n
s
c
i
en
ce
an
d
s
o
c
i
et
a
l
r
e
s
i
li
en
c
e
.
T
h
e
r
est
o
f
th
e
p
ap
er
is
s
tr
u
ct
u
r
ed
as
f
o
llo
w
s
.
I
n
s
ec
ti
o
n
2
,
th
e
m
e
th
o
d
s
u
s
ed
to
s
y
s
te
m
atic
all
y
s
e
lect
elig
ib
le
ar
ticle
s
f
o
r
an
al
y
s
is
ar
e
d
escr
ib
ed
.
T
h
e
r
esu
lts
o
f
th
e
an
a
l
y
s
is
o
f
all
t
h
e
ch
o
s
e
n
ar
ticles
a
n
d
th
ei
r
d
is
cu
s
s
io
n
ar
e
p
r
esen
ted
i
n
s
ec
tio
n
3
.
L
astl
y
,
a
co
n
cl
u
s
io
n
is
p
r
o
v
id
ed
in
s
ec
tio
n
4
.
2.
M
E
T
H
O
D
2.
1.
I
dentif
ica
t
io
n
Fo
r
th
is
s
t
u
d
y
,
a
n
ex
ten
s
iv
e
b
o
d
y
o
f
r
elev
a
n
t
li
ter
atu
r
e
w
a
s
s
elec
ted
th
r
o
u
g
h
t
h
e
ap
p
licat
io
n
o
f
k
e
y
s
tag
e
s
w
ith
i
n
th
e
s
y
s
te
m
a
tic
r
ev
ie
w
m
et
h
o
d
o
lo
g
y
.
Fo
llo
w
i
n
g
th
e
id
en
ti
f
icatio
n
o
f
k
e
y
w
o
r
d
s
,
r
elate
d
ter
m
s
w
er
e
s
y
s
te
m
a
ticall
y
id
en
ti
f
ied
a
n
d
r
ef
in
ed
u
s
i
n
g
d
ictio
n
ar
ies,
t
h
esa
u
r
i,
en
c
y
clo
p
ed
ias,
an
d
an
an
al
y
s
is
o
f
p
r
io
r
r
esear
ch
.
T
h
e
s
elec
tio
n
o
f
all
r
elev
an
t
k
e
y
w
o
r
d
s
w
as
m
ad
e
f
o
llo
w
i
n
g
t
h
e
cr
ea
tio
n
o
f
s
ea
r
c
h
s
tr
in
g
s
f
o
r
Sco
p
u
s
an
d
W
o
S
as
in
T
ab
le
1
.
A
co
m
p
ilatio
n
o
f
7
1
6
p
ap
e
r
s
w
as
o
b
tain
ed
f
r
o
m
t
h
e
t
w
o
d
atab
ases
in
t
h
e
in
itiatio
n
o
f
th
e
s
y
s
te
m
atic
r
ev
ie
w
p
r
o
ce
s
s
.
Fo
r
m
an
u
s
cr
ip
t
p
u
b
licatio
n
,
all
p
r
o
v
id
ed
f
ig
u
r
es
m
u
s
t
f
o
ll
o
w
th
e
s
ta
n
d
ar
d
o
f
q
u
alit
y
f
o
r
p
u
b
licatio
n
.
T
ab
le
1
.
T
h
e
q
u
er
y
s
tr
i
n
g
I
n
d
e
x
i
n
g
d
a
t
a
b
a
se
S
e
a
r
c
h
s
t
r
i
n
g
S
c
o
p
u
s
TI
TL
E
-
A
B
S
-
K
EY
(
“
F
a
k
e
N
e
w
s
”
A
N
D
(
d
e
t
e
c
t
*
)
A
N
D
“
D
e
e
p
L
e
a
r
n
i
n
g
”
A
N
D
me
t
h
o
d
)
W
o
S
“
F
a
k
e
N
e
w
s
”
A
N
D
(
d
e
t
e
c
t
*
)
A
N
D
“
D
e
e
p
L
e
a
r
n
i
n
g
”
A
N
D
me
t
h
o
d
2
.
2
.
Scre
ening
T
h
e
f
ir
s
t
s
ta
g
e
o
f
s
cr
ee
n
i
n
g
i
n
v
o
l
v
ed
a
th
o
r
o
u
g
h
e
x
a
m
in
at
io
n
o
f
a
co
llectio
n
o
f
p
o
s
s
ib
ly
r
elev
a
n
t
r
esear
ch
m
ater
ial
s
to
d
eter
m
i
n
e
co
n
te
n
t
t
h
at
is
i
n
li
n
e
w
it
h
th
e
p
r
ed
ef
in
ed
r
esear
ch
q
u
es
tio
n
(
s
)
.
Du
r
i
n
g
th
i
s
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
Dete
ctin
g
fa
ke
n
ews
th
r
o
u
g
h
d
ee
p
lea
r
n
in
g
:
a
cu
r
r
en
t sys
tema
tic
r
ev
iew
(
I
d
z
a
A
is
a
r
a
N
o
r
a
b
id
)
331
p
h
ase,
an
o
r
d
er
ly
eli
m
i
n
atio
n
p
r
o
ce
d
u
r
e
w
as
i
m
p
le
m
e
n
ted
to
elim
i
n
ate
an
y
d
u
p
licate
p
ap
er
s
f
r
o
m
th
e
in
itia
ll
y
o
b
tain
ed
lis
t o
f
p
ap
er
s
.
6
0
9
p
u
b
licatio
n
s
w
er
e
ex
cl
u
d
ed
d
u
r
in
g
t
h
e
in
itial scr
ee
n
in
g
s
tep
.
Af
ter
w
ar
d
s
,
a
to
tal
o
f
1
0
7
p
a
p
er
s
w
er
e
s
u
b
j
ec
ted
to
f
u
r
th
er
e
x
a
m
in
a
tio
n
i
n
t
h
e
s
u
b
s
eq
u
en
t
p
h
ase,
d
u
r
i
n
g
w
h
ich
s
p
ec
if
ic
e
x
cl
u
s
io
n
an
d
in
cl
u
s
io
n
cr
iter
ia,
as
o
u
tli
n
ed
in
T
ab
le
2
o
f
th
is
s
t
u
d
y
,
w
e
r
e
i
m
p
le
m
e
n
ted
.
T
h
e
m
ain
cr
ite
r
io
n
u
tili
ze
d
i
n
th
i
s
ap
p
r
o
ac
h
w
a
s
liter
at
u
r
e
(
r
esear
ch
p
ap
er
s
)
,
as
it
co
n
s
tit
u
tes
t
h
e
p
r
in
cip
al
s
o
u
r
ce
o
f
p
r
ac
tica
l
r
ec
o
m
m
e
n
d
atio
n
s
.
T
h
is
in
cl
u
d
es
v
ar
io
u
s
t
y
p
e
s
o
f
ac
ad
e
m
ic
p
u
b
licat
io
n
s
s
u
c
h
as
r
esear
ch
p
ap
er
s
,
b
o
o
k
s
,
b
o
o
k
s
e
r
ies,
ch
ap
ter
s
,
r
ev
ie
w
s
,
m
eta
-
s
y
n
t
h
e
s
is
,
m
eta
-
an
a
l
y
s
es,
an
d
co
n
f
er
en
ce
p
r
o
ce
ed
in
g
s
.
T
h
ese
p
u
b
licatio
n
s
w
er
e
n
o
t
co
n
s
id
er
ed
in
th
e
p
r
ev
io
u
s
s
tu
d
y
.
I
t
is
i
m
p
o
r
tan
t
to
m
en
tio
n
th
a
t
th
e
r
ev
ie
w
w
as
li
m
ited
to
liter
atu
r
e
w
r
itte
n
in
E
n
g
lis
h
.
I
m
p
o
r
tan
tl
y
,
t
h
e
s
tr
a
te
g
y
s
o
lel
y
co
n
ce
n
tr
ated
o
n
ar
ticles
s
p
ec
if
icall
y
f
r
o
m
t
h
e
y
ea
r
2
0
2
3
.
A
s
a
r
esu
lt,
3
8
p
ap
er
s
w
er
e
r
ej
ec
ted
d
u
e
to
r
ep
etitiv
e
cr
iter
ia.
T
ab
le
2
.
T
h
e
q
u
er
y
s
tr
i
n
g
C
r
i
t
e
r
i
o
n
Inc
l
u
si
o
n
Ex
c
l
u
si
o
n
L
a
n
g
u
a
g
e
E
n
g
l
i
sh
N
o
n
-
e
n
g
l
i
sh
T
i
me
l
i
n
e
2023
<
2
0
2
3
D
o
c
u
me
n
t
t
y
p
e
Jo
u
rna
l
(
a
r
t
i
c
l
e)
C
o
n
f
e
r
e
n
c
e
,
b
o
o
k
,
r
e
v
i
e
w
P
u
b
l
i
c
a
t
i
o
n
st
a
g
e
F
i
n
al
I
n
p
r
e
ss
2
.
3
.
E
lig
ibi
lity
A
co
m
p
r
e
h
en
s
i
v
e
co
llectio
n
o
f
6
9
ar
ticles
w
as
co
m
p
iled
i
n
t
h
e
th
ir
d
s
tag
e,
d
en
o
ted
as
elig
ib
ilit
y
ass
es
s
m
en
t.
D
u
r
in
g
t
h
is
p
h
a
s
e
,
a
co
m
p
r
eh
e
n
s
i
v
e
an
al
y
s
is
was
p
er
f
o
r
m
ed
o
n
th
e
titl
e
s
an
d
p
r
im
ar
y
co
n
ten
t
o
f
ea
ch
ar
ticle
to
en
s
u
r
e
th
at
t
h
e
in
cl
u
s
io
n
cr
iter
ia
is
m
et
an
d
in
lin
e
w
it
h
th
e
o
b
j
ec
tiv
es
o
f
th
e
cu
r
r
en
t
r
esear
ch
.
T
h
u
s
,
3
6
r
ep
o
r
ts
w
er
e
r
u
led
o
u
t
d
u
e
to
i
n
co
n
g
r
u
e
n
ce
w
it
h
t
h
e
s
t
u
d
y
’
s
o
b
j
ec
tiv
es,
as
i
n
d
ic
ated
b
y
i
n
s
u
f
f
icien
t
r
elev
an
ce
i
n
th
e
titl
es
a
n
d
ab
s
tr
ac
ts
,
as
w
ell
as
a
lack
o
f
f
u
ll
-
t
ex
t
ac
ce
s
s
ib
ili
t
y
.
Ulti
m
atel
y
,
3
3
ar
ticles
m
ee
t
t
h
e
elig
ib
ilit
y
cr
iter
ia
an
d
ar
e
av
ai
lab
le
f
o
r
f
u
r
t
h
er
r
ev
ie
w
.
2
.
4
.
Da
t
a
a
bs
t
ra
ct
io
n a
nd
a
na
ly
s
is
A
n
e
v
a
l
u
a
t
i
v
e
m
e
t
h
o
d
o
l
o
g
y
e
m
p
l
o
y
e
d
i
n
t
h
i
s
r
e
s
e
a
r
c
h
i
n
v
o
l
v
e
d
a
n
i
n
t
e
g
r
a
t
i
v
e
a
n
a
l
y
s
i
s
t
h
a
t
c
o
m
p
r
e
h
e
n
s
i
v
e
l
y
e
x
a
m
i
n
e
d
a
n
d
s
y
n
t
h
e
s
i
z
e
d
d
i
v
e
r
s
e
r
e
s
e
a
r
c
h
d
e
s
i
g
n
s
,
p
a
r
t
i
c
u
l
a
r
l
y
t
h
o
s
e
e
m
p
l
o
y
i
n
g
q
u
a
n
t
i
t
a
t
i
v
e
a
p
p
r
o
a
c
h
e
s
.
T
h
e
p
r
i
m
a
r
y
a
i
m
o
f
t
h
i
s
p
r
o
f
i
c
i
e
n
t
s
t
u
d
y
w
a
s
i
d
e
n
t
i
f
y
i
n
g
t
h
e
a
p
p
r
o
p
r
i
a
t
e
s
u
b
j
e
c
t
s
a
n
d
s
u
b
t
o
p
i
c
s
i
n
t
h
e
d
e
v
e
l
o
p
m
e
n
t
o
f
t
h
em
e
s
i
n
v
o
l
v
e
d
i
n
t
h
e
a
c
q
u
i
s
i
t
i
o
n
o
f
d
a
t
a
.
F
i
g
u
r
e
1
i
l
l
u
s
t
r
a
t
e
s
t
h
e
m
e
t
h
o
d
b
y
w
h
i
c
h
a
s
e
l
e
c
t
i
o
n
o
f
3
3
a
r
t
i
c
l
e
s
w
e
r
e
c
a
r
e
f
u
l
l
y
e
x
a
m
in
e
d
i
n
s
e
a
r
c
h
o
f
c
l
a
i
m
s
o
r
i
n
f
o
r
m
a
t
i
o
n
p
e
r
t
i
n
e
n
t
t
o
t
h
e
s
u
b
j
e
c
t
s
u
n
d
e
r
i
n
v
e
s
t
i
g
a
t
i
o
n
.
Fig
u
r
e
1
.
Flo
w
d
iag
r
a
m
o
f
t
h
e
p
r
o
p
o
s
ed
s
ea
r
ch
in
g
s
t
u
d
y
[
1
8
]
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
23
,
No
.
2
,
A
p
r
il
20
25
:
3
2
9
-
339
332
T
h
e
a
u
th
o
r
s
th
en
r
ev
i
ew
e
d
t
h
e
im
p
o
r
ta
n
t
r
e
c
en
t
r
es
e
a
r
ch
o
n
d
ee
p
l
e
a
r
n
in
g
-
b
a
s
e
d
f
a
l
s
e
n
e
w
s
i
d
e
n
tif
i
c
at
i
o
n
.
A
c
o
m
p
r
eh
en
s
i
v
e
r
ev
i
e
w
o
f
th
e
s
tu
d
y
r
e
s
u
l
ts
an
d
m
et
h
o
d
o
l
o
g
i
es
em
p
l
o
y
e
d
in
a
l
l
p
r
i
o
r
i
n
v
es
t
ig
at
i
o
n
s
is
cu
r
r
en
t
ly
u
n
d
e
r
w
ay
.
Su
b
s
e
q
u
en
t
ly
,
c
o
ll
a
b
o
r
a
t
i
o
n
am
o
n
g
c
o
-
au
th
o
r
s
f
ac
i
li
t
at
e
d
th
e
d
ev
el
o
p
m
en
t
o
f
th
em
a
ti
c
c
o
n
s
t
r
u
c
ts
g
r
o
u
n
d
ed
i
n
th
e
c
o
n
t
ex
tu
a
l
f
r
am
ew
o
r
k
o
f
th
e
s
tu
d
y
’
s
d
at
a
.
Du
r
in
g
t
h
e
d
a
t
a
a
n
aly
s
is
p
r
o
c
e
s
s
,
a
d
e
t
a
i
l
e
d
jo
u
r
n
al
w
as
m
et
i
cu
l
o
u
s
ly
m
ain
t
a
in
e
d
t
o
d
o
c
u
m
en
t
r
e
l
e
v
a
n
t
o
b
s
e
r
v
a
t
i
o
n
s
,
p
e
r
s
p
e
c
tiv
es
,
c
h
al
l
en
g
es
,
a
n
d
o
t
h
e
r
c
r
i
ti
c
a
l
c
o
n
c
e
p
ts
e
s
s
en
ti
a
l
f
o
r
a
c
c
u
r
at
e
d
a
t
a
in
t
e
r
p
r
e
ta
t
i
o
n
.
T
h
e
e
v
a
lu
a
ti
o
n
o
f
p
o
t
e
n
t
i
a
l
in
c
o
n
s
i
s
t
en
c
i
es
in
th
e
t
h
em
at
i
c
d
es
ig
n
p
r
o
c
e
s
s
w
as
s
u
b
s
e
q
u
en
tly
u
n
d
e
r
t
ak
en
b
y
c
o
m
p
a
r
in
g
o
u
t
c
o
m
e
s
.
I
t
is
im
p
e
r
a
t
iv
e
t
o
h
i
g
h
l
ig
h
t
th
a
t
a
n
y
d
is
p
a
r
i
ti
e
s
in
o
p
i
n
i
o
n
s
r
eg
a
r
d
i
n
g
th
e
a
f
o
r
em
en
t
i
o
n
e
d
c
o
n
c
e
p
t
s
w
e
r
e
s
u
b
je
c
t
t
o
th
o
r
o
u
g
h
d
e
b
a
t
e
am
o
n
g
th
e
a
u
th
o
r
s
.
Ul
t
im
at
e
ly
,
th
e
t
h
em
es
g
en
e
r
a
te
d
u
n
d
e
r
w
en
t
r
ef
in
em
en
t
t
o
en
s
u
r
e
i
n
t
e
r
n
a
l
c
o
h
e
r
en
c
e
.
T
o
v
a
li
d
a
t
e
th
e
c
h
a
ll
en
g
e
s
en
c
o
u
n
t
e
r
e
d
,
t
w
o
ex
p
e
r
ts
—
s
p
e
c
i
al
i
z
e
d
in
t
ex
t
an
aly
ti
cs
a
n
d
d
e
e
p
l
e
a
r
n
in
g
r
e
s
p
ec
t
i
v
e
ly
c
o
n
d
u
ct
e
d
t
h
e
a
n
a
ly
ti
c
al
s
el
e
c
ti
o
n
p
r
o
c
es
s
.
T
h
e
p
h
a
s
e
o
f
ex
p
e
r
t
ass
e
s
s
m
e
n
t
s
e
r
v
e
s
t
o
e
n
s
u
r
e
th
at
e
a
ch
s
u
b
th
em
e
i
s
cl
e
a
r
,
s
ig
n
if
i
c
an
t
,
an
d
a
p
p
r
o
p
r
i
a
t
e
th
r
o
u
g
h
t
h
e
e
s
t
a
b
l
is
h
m
en
t
o
f
d
o
m
a
i
n
v
al
i
d
i
ty
.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
W
i
t
h
i
n
t
h
e
c
o
n
t
e
x
t
o
f
i
n
f
o
r
m
a
t
i
o
n
s
h
a
r
i
n
g
,
t
h
e
r
i
s
e
o
f
f
a
k
e
n
e
w
s
p
o
s
e
s
a
s
i
g
n
i
f
i
c
a
n
t
t
h
r
e
a
t
,
i
n
f
l
u
e
n
c
i
n
g
p
u
b
l
i
c
o
p
i
n
i
o
n
a
n
d
s
o
c
i
e
t
y
i
n
t
e
r
a
c
t
i
o
n
s
.
E
f
f
o
r
t
s
t
o
c
o
u
n
t
e
r
t
h
i
s
c
h
a
l
l
e
n
g
e
i
n
v
o
l
v
e
t
h
e
d
e
v
e
l
o
p
m
e
n
t
o
f
a
d
v
a
n
c
e
d
d
e
t
e
c
t
i
o
n
m
o
d
e
l
s
.
T
h
e
s
e
m
o
d
e
l
s
a
r
e
t
r
a
i
n
e
d
w
i
t
h
b
e
n
c
h
m
a
r
k
d
a
t
a
s
e
t
s
c
o
n
t
a
i
n
i
n
g
a
w
i
d
e
v
a
r
i
e
t
y
o
f
f
a
k
e
n
e
w
s
s
a
m
p
l
e
s
,
a
r
e
c
a
p
a
b
l
e
o
f
t
o
l
e
a
r
n
a
n
d
a
d
a
p
t
t
o
d
i
f
f
e
r
e
n
t
p
a
t
t
e
r
n
s
a
n
d
c
h
a
r
a
c
t
e
r
i
s
t
i
c
s
i
n
d
i
c
a
t
i
v
e
o
f
f
a
l
s
i
f
i
e
d
i
n
f
o
r
m
a
t
i
o
n
.
F
o
r
i
n
s
t
a
n
c
e
,
K
e
y
a
e
t
a
l
.
[
1
9
]
i
n
t
r
o
d
u
c
e
d
F
a
k
e
S
t
a
c
k
,
a
f
a
k
e
n
ew
s
d
e
t
e
c
t
i
o
n
m
o
d
e
l
t
h
a
t
a
r
e
t
r
a
i
n
e
d
o
n
m
u
l
t
i
p
l
e
d
a
t
a
s
e
t
s
,
t
h
e
m
o
d
e
l
d
e
m
o
n
s
t
r
a
t
e
d
i
m
p
r
e
s
s
i
v
e
a
c
c
u
r
a
c
y
,
o
u
t
p
e
r
f
o
r
m
i
n
g
b
a
s
e
l
i
n
e
m
o
d
e
l
s
i
n
d
e
t
e
c
t
i
n
g
f
a
k
e
n
ew
s
a
c
r
o
s
s
v
a
r
i
o
u
s
d
a
t
a
s
e
t
s
.
R
e
s
e
a
r
c
h
b
y
M
e
r
r
y
t
o
n
a
n
d
A
u
g
a
s
t
a
[
2
0
]
i
n
t
r
o
d
u
c
e
A
A
-
B
i
L
S
T
M
f
r
a
m
ew
o
r
k
a
s
i
n
F
i
g
u
r
e
2
.
Fig
u
r
e
2
.
AA
-
B
i
L
ST
M
f
r
a
m
e
w
o
r
k
i
n
tr
o
d
u
ce
d
b
y
Me
r
r
y
to
n
an
d
Au
g
asta
[
2
0
]
T
h
e
m
o
d
e
l
is
t
r
ain
e
d
a
n
d
ev
alu
a
t
e
d
o
n
b
en
ch
m
a
r
k
d
a
t
as
e
ts
s
p
e
c
i
f
i
c
a
lly
I
S
O
T
,
L
i
a
r
,
K
ag
g
l
e
f
ak
e
r
e
al
n
ew
s
(
2016
)
a
n
d
(
2022
)
.
T
h
e
m
o
d
e
l
p
r
o
p
o
s
e
d
b
y
H
am
za
e
t
a
l
.
[
2
1
]
,
t
r
a
i
n
e
d
o
n
a
f
ak
e
n
ew
s
d
ata
s
e
t
,
u
t
il
i
z
es
a
q
u
a
d
c
h
an
n
e
l
l
o
n
g
s
h
o
r
t
-
t
e
r
m
m
em
o
r
y
(
L
S
T
M
)
a
r
c
h
i
t
e
ctu
r
e
an
d
ac
h
ie
v
es
im
p
r
ess
iv
e
ac
cu
r
a
cy
in
c
l
as
s
i
f
y
in
g
f
ak
e
n
ew
s
.
A
h
m
a
d
et
a
l
.
[
2
2
]
p
r
o
p
o
s
e
d
a
r
o
b
u
s
t
b
e
n
c
h
m
a
r
k
f
o
r
d
e
te
c
t
in
g
p
r
o
p
a
g
an
d
is
t
t
ex
t
u
s
in
g
th
e
R
o
B
E
R
T
a
m
o
d
e
l
,
a
c
h
ie
v
in
g
h
ig
h
a
c
cu
r
a
cy
r
a
t
es
o
n
th
e
Pr
o
T
e
x
t
l
i
b
r
a
r
y
,
ef
f
e
ct
iv
e
ly
c
o
n
t
r
i
b
u
tin
g
t
o
th
e
i
d
en
t
if
i
ca
t
i
o
n
o
f
p
r
o
p
a
g
an
d
a
i
n
t
ex
tu
a
l
d
a
t
a
.
R
a
o
et
a
l
.
[
2
3
]
ta
c
k
le
s
o
c
i
a
l
s
p
am
o
n
p
l
a
tf
o
r
m
s
m
e
r
g
i
n
g
th
r
e
e
d
at
a
s
et
s
;
f
ak
e
n
ew
s
,
S
MS
s
p
am
an
d
l
i
n
g
s
p
am
f
o
r
t
r
ai
n
in
g
an
d
e
v
a
lu
a
ti
o
n
w
h
i
ch
r
esu
l
t
e
d
i
n
th
e
ef
f
i
c
a
cy
o
f
th
e
p
r
o
p
o
s
e
d
f
r
am
ew
o
r
k
.
A
n
o
th
e
r
d
at
a
s
et
,
G
o
s
s
i
p
C
o
p
a
n
d
Po
l
i
t
iF
a
c
t
,
w
e
r
e
u
t
i
li
z
e
d
t
o
ev
a
lu
at
e
t
h
e
a
c
cu
r
a
cy
s
c
o
r
es
,
as
h
i
g
h
l
ig
h
t
e
d
b
y
J
am
s
h
i
d
i
e
t
a
l
.
[
2
4
]
.
Du
a
et
a
l.
[
2
5
]
in
tr
o
d
u
ce
d
I
-
FLA
S
H,
in
ter
p
r
etab
le
f
a
k
e
n
e
ws
d
etec
to
r
u
s
in
g
L
I
ME
an
d
SH
A
P
,
th
at
e
x
p
lain
s
it
s
p
r
ed
ictio
n
s
d
eliv
er
in
g
r
o
b
u
s
t
ac
cu
r
ac
ies
o
n
t
h
e
FactC
h
ec
k
an
d
FactC
h
ec
k
2
d
ataset.
T
h
e
m
o
d
el
is
d
esig
n
ed
to
n
o
t
o
n
l
y
d
etec
t
f
ak
e
n
e
w
s
b
u
t
also
p
r
o
v
id
e
in
ter
p
r
etab
ilit
y
,
en
h
a
n
ci
n
g
tr
u
s
t
in
its
d
ec
is
io
n
s
.
A
m
o
d
e
l G
r
aS
H
E
,
g
a
t
e
d
r
e
cu
r
s
iv
e
an
d
s
e
q
u
en
ti
a
l
d
e
e
p
h
i
e
r
a
r
ch
ic
a
l
en
c
o
d
in
g
,
p
r
o
p
o
s
e
d
b
y
Ku
m
a
r
e
t
a
l
.
[
2
6
]
,
t
r
a
i
n
e
d
o
n
I
SO
T
f
a
k
e
n
ew
s
,
FN
C
an
d
N
E
L
A
-
1
7
d
a
t
as
e
ts
,
s
h
o
w
c
as
in
g
im
p
r
o
v
e
d
p
e
r
f
o
r
m
an
c
e
o
v
e
r
e
x
i
s
t
in
g
m
o
d
e
ls
.
H
a
n
et
a
l
.
[
2
7
]
,
w
h
o
p
r
o
p
o
s
e
th
e
m
u
lti
-
s
o
u
r
ce
in
f
o
r
m
atio
n
a
n
d
lo
ca
l
-
g
lo
b
al
r
elat
io
n
s
h
ip
o
f
h
eter
o
g
e
n
eo
u
s
n
et
w
o
r
k
m
o
d
el
n
a
m
ed
MSL
G,
ev
alu
a
ted
o
n
T
w
itter
1
5
an
d
T
w
i
tter
1
6
d
atasets
.
A
d
d
itio
n
all
y
,
Mo
h
a
w
es
h
et
a
l.
[
2
8
]
h
av
e
ex
p
an
d
ed
th
e
r
esear
ch
ef
f
o
r
ts
to
in
cl
u
d
e
o
th
er
lan
g
u
ag
e
s
.
A
m
u
ltil
i
n
g
u
al
f
ak
e
n
e
w
s
d
etec
tio
n
t
h
at
ar
e
tr
ain
ed
o
n
T
A
L
L
I
P
d
ataset
w
h
ic
h
co
m
p
r
is
es
o
f
m
u
ltip
le
lan
g
u
ag
e
s
.
Mo
r
eo
v
er
,
Ha
m
ed
et
a
l.
[
2
9
]
s
p
ec
if
icall
y
co
n
ce
n
tr
ate
o
n
th
e
I
s
la
m
ic
d
o
m
ai
n
,
tr
ain
ed
o
n
a
d
ataset
s
p
ec
if
ic
to
I
s
la
m
ic
co
n
ten
t
ca
lled
R
I
DI
.
T
h
ese
ap
p
r
o
ac
h
es
h
i
g
h
li
g
h
t
t
h
e
ev
o
lv
i
n
g
o
f
tech
n
iq
u
e
s
o
n
f
a
k
e
n
e
w
s
d
etec
tio
n
,
d
e
m
o
n
s
tr
atin
g
ad
v
an
ce
m
e
n
ts
i
n
m
o
d
e
l
ar
ch
itectu
r
e
s
an
d
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
Dete
ctin
g
fa
ke
n
ews
th
r
o
u
g
h
d
ee
p
lea
r
n
in
g
:
a
cu
r
r
en
t sys
tema
tic
r
ev
iew
(
I
d
z
a
A
is
a
r
a
N
o
r
a
b
id
)
333
ap
p
licatio
n
d
o
m
ai
n
s
w
h
ile
p
r
o
v
in
g
to
th
eir
co
n
s
is
te
n
t
ef
f
ec
ti
v
en
e
s
s
ac
r
o
s
s
m
u
l
tip
le
d
ataset
s
.
T
h
e
k
ey
d
atase
ts
an
d
m
o
d
els u
s
ed
in
t
h
ese
s
tu
d
i
es a
r
e
s
u
m
m
ar
ized
in
T
a
b
le
3
.
T
ab
le
3
.
Ov
er
v
ie
w
o
f
d
ataset
a
n
d
b
en
ch
m
ar
k
in
g
f
o
r
f
a
k
e
n
e
ws d
etec
tio
n
A
u
t
h
o
r
s
T
i
t
l
e
Y
e
a
r
Jo
u
r
n
a
l
M
e
t
h
o
d
o
l
o
g
y
R
e
su
l
t
s
K
e
y
a
e
t
a
l
.
[
1
9
]
F
a
k
e
st
a
c
k
:
h
i
e
r
a
r
c
h
i
c
a
l
t
r
i
-
b
e
r
t
-
c
n
n
-
l
st
m
s
t
a
c
k
e
d
mo
d
e
l
f
o
r
e
f
f
e
c
t
i
v
e
f
a
k
e
n
e
w
s d
e
t
e
c
t
i
o
n
2
0
2
3
P
L
o
S
O
N
E
B
ER
T
e
mb
e
d
d
i
n
g
s w
i
t
h
C
N
N
f
e
a
t
u
r
i
n
g
s
k
i
p
c
o
n
v
o
l
u
t
i
o
n
b
l
o
c
k
a
n
d
L
S
T
M
D
a
t
a
se
t
:
e
n
g
l
i
sh
f
a
k
e
n
e
w
s
o
b
t
a
i
n
e
d
f
r
o
m K
a
g
g
l
e
,
L
I
A
R
a
n
d
W
EL
F
a
k
e
A
c
c
u
r
a
c
y
o
f
9
9
.
7
4
%
.
o
n
K
a
g
g
l
e
f
a
k
e
n
e
w
s
d
a
t
a
se
t
A
c
c
u
r
a
c
y
o
f
7
5
.
5
8
%
o
n
L
I
A
R
d
a
t
a
se
t
A
c
c
u
r
a
c
y
o
f
9
8
.
2
5
%
o
n
W
E
L
F
a
k
e
d
a
t
a
se
t
M
e
r
r
y
t
o
n
a
n
d
A
u
g
a
st
a
[
2
0
]
A
n
a
t
t
r
i
b
u
t
e
-
w
i
se
a
t
t
e
n
t
i
o
n
mo
d
e
l
w
i
t
h
b
i
l
st
m fo
r
a
n
e
f
f
i
c
i
e
n
t
f
a
k
e
n
e
w
s
d
e
t
e
c
t
i
o
n
2
0
2
3
M
u
l
t
i
me
d
i
a
T
o
o
l
s
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
Bi
-
L
S
T
M
a
n
d
a
t
t
r
i
b
u
t
e
-
w
i
se
a
t
t
e
n
t
i
o
n
me
c
h
a
n
i
sm
b
a
se
d
o
n
C
N
N
D
a
t
a
se
t
:
I
S
O
T
,
LI
A
R
,
K
a
g
g
l
e
f
a
k
e
r
e
a
l
n
e
w
s [
2
0
2
2
]
a
n
d
K
a
g
g
l
e
f
a
k
e
r
e
a
l
n
e
w
s
[
2
0
1
6
]
A
c
c
u
r
a
c
y
e
x
c
e
e
d
i
n
g
9
9
%
f
o
r
t
h
e
I
S
O
T
a
n
d
K
a
g
g
l
e
f
a
k
e
r
e
a
l
n
e
w
s
2
0
1
6
d
a
t
a
se
t
s
A
c
c
u
r
a
c
y
o
f
6
0
.
3
1
%
o
n
t
h
e
L
I
A
R
d
a
t
a
se
t
H
a
mz
a
e
t
a
l
.
[
2
1
]
O
p
t
i
mal
q
u
a
d
c
h
a
n
n
e
l
L
S
T
M
b
a
se
d
f
a
k
e
n
e
w
s
c
l
a
ssi
f
i
c
a
t
i
o
n
o
n
e
n
g
l
i
s
h
c
o
r
p
u
s
2
0
2
3
C
o
mp
u
t
e
r
S
y
st
e
ms Sci
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
L
S
T
M
-
b
a
se
d
mo
d
e
l
D
a
t
a
se
t
:
c
o
m
p
r
i
se
s o
f
2
1
4
1
7
r
e
a
l
a
n
d
2
3
4
8
1
f
a
k
e
n
e
w
s
A
c
c
u
r
a
c
y
o
f
9
9
.
1
2
%
A
h
mad
e
t
a
l
.
[
2
2
]
R
o
b
u
st
b
e
n
c
h
m
a
r
k
f
o
r
p
r
o
p
a
g
a
n
d
i
s
t
t
e
x
t
d
e
t
e
c
t
i
o
n
a
n
d
m
i
n
i
n
g
h
i
g
h
-
q
u
a
l
i
t
y
d
a
t
a
2
0
2
3
M
a
t
h
e
ma
t
i
c
s
R
o
B
E
R
T
a
D
a
t
a
se
t
:
P
r
o
T
e
x
t
l
i
b
r
a
r
y
,
d
e
d
i
c
a
t
e
d
t
o
p
r
o
p
a
g
a
n
d
a
t
e
x
t
s
A
c
c
u
r
a
c
y
o
f
9
0
%
o
n
P
r
o
Te
x
t
A
c
c
u
r
a
c
y
o
f
7
5
%
o
n
P
T
C
A
c
c
u
r
a
c
y
o
f
6
8
%
o
n
T
S
H
P
-
17
A
c
c
u
r
a
c
y
o
f
6
5
%
o
n
Q
p
r
o
p
R
a
o
e
t
a
l
.
[
2
3
]
H
y
b
r
i
d
e
n
se
mb
l
e
f
r
a
mew
o
r
k
w
i
t
h
se
l
f
-
a
t
t
e
n
t
i
o
n
me
c
h
a
n
i
sm
f
o
r
so
c
i
a
l
s
p
a
m
d
e
t
e
c
t
i
o
n
o
n
i
mb
a
l
a
n
c
e
d
d
a
t
a
2
0
2
3
Ex
p
e
r
t
S
y
st
e
ms
w
i
t
h
A
p
p
l
i
c
a
t
i
o
n
s
C
o
n
v
1
D
a
n
d
B
i
-
d
i
r
e
c
t
i
o
n
a
l
R
N
N
l
a
y
e
r
s w
i
t
h
t
h
e
se
l
f
-
a
t
t
e
n
t
i
o
n
me
c
h
a
n
i
sm
D
a
t
a
se
t
:
f
a
k
e
n
e
w
s d
a
t
a
se
t
s,
L
i
n
g
S
p
a
m a
n
d
S
M
S
S
p
a
m
A
c
c
u
r
a
c
y
o
f
9
7
.
2
6
%
Jamsh
i
d
i
e
t
a
l
.
[
2
4
]
A
sel
f
-
a
t
t
e
n
t
i
o
n
me
c
h
a
n
i
sm
-
b
a
se
d
mo
d
e
l
f
o
r
e
a
r
l
y
d
e
t
e
c
t
i
o
n
o
f
f
a
k
e
n
e
w
s
2
0
2
3
I
EEE
T
r
a
n
sac
t
i
o
n
s
o
n
C
o
mp
u
t
a
t
i
o
n
a
l
S
o
c
i
a
l
S
y
st
e
ms
S
e
l
f
-
a
t
t
e
n
t
i
o
n
me
c
h
a
n
i
sm
-
b
a
se
d
e
n
c
o
d
e
r
D
a
t
a
se
t
:
F
a
k
e
N
e
w
sN
e
t
(
P
o
l
i
t
i
F
a
c
t
,
G
o
s
si
p
C
o
p
)
G
o
ssi
p
C
o
p
a
n
d
P
o
l
i
t
i
F
a
c
t
F
1
sco
r
e
s
e
x
c
e
e
d
t
h
e
b
e
st
b
a
se
l
i
n
e
mo
d
e
l
b
y
9
%
a
n
d
6
%
D
u
a
e
t
a
l
.
[
2
5
]
I
-
f
l
a
sh
:
i
n
t
e
r
p
r
e
t
a
b
l
e
f
a
k
e
n
e
w
s d
e
t
e
c
t
o
r
u
si
n
g
l
i
me
a
n
d
s
h
a
p
2
0
2
3
W
i
r
e
l
e
ss
P
e
r
so
n
a
l
C
o
mm
u
n
i
c
a
t
i
o
ns
X
A
I
m
e
t
h
o
d
s;
L
I
M
E
a
n
d
S
H
A
P
D
a
t
a
se
t
:
F
a
c
t
C
h
e
c
k
a
n
d
F
a
c
t
C
h
e
c
k
2
A
c
c
u
r
a
c
y
o
f
8
7
.
2
5
±
2
.
4
5
%
o
n
F
a
c
t
C
h
e
c
k
,
a
n
d
9
2
.
9
1
±
2
.
0
7
%
o
n
F
a
c
t
C
h
e
c
k
2
K
u
mar
e
t
a
l
.
[
2
6
]
G
a
t
e
d
r
e
c
u
r
si
v
e
a
n
d
se
q
u
e
n
t
i
a
l
d
e
e
p
h
i
e
r
a
r
c
h
i
c
a
l
e
n
c
o
d
i
n
g
f
o
r
d
e
t
e
c
t
i
n
g
i
n
c
o
n
g
r
u
e
n
t
n
e
w
s
a
r
t
i
c
l
e
s
2
0
2
3
I
EEE
T
r
a
n
sac
t
i
o
n
s
o
n
C
o
mp
u
t
a
t
i
o
n
a
l
S
o
c
i
a
l
S
y
st
e
ms
B
i
L
S
T
M
(
P
a
r
a
g
r
a
p
h
l
e
v
e
l
)
,
c
h
i
l
d
-
su
m
T
r
e
e
L
S
T
M
(
se
n
t
e
n
c
e
l
e
v
e
l
)
D
a
t
a
se
t
:
I
S
O
T
f
a
k
e
n
e
w
s,
F
N
C
a
n
d
N
EL
A
-
1
7
d
a
t
a
se
t
A
v
e
r
a
g
e
a
c
c
u
r
a
c
y
o
f
h
i
g
h
e
r
t
h
a
n
9
0
%
H
a
n
e
t
a
l
.
[
2
7
]
Jo
i
n
t
l
y
mu
l
t
i
-
so
u
r
c
e
i
n
f
o
r
mat
i
o
n
a
n
d
l
o
c
a
l
-
g
l
o
b
a
l
r
e
l
a
t
i
o
n
s o
f
h
e
t
e
r
o
g
e
n
e
o
u
s n
e
t
w
o
r
k
f
o
r
r
u
mo
u
r
d
e
t
e
c
t
i
o
n
2
0
2
3
F
r
o
n
t
i
e
r
s i
n
P
h
y
si
c
s
G
r
a
p
h
c
o
n
v
o
l
u
t
i
o
n
n
e
t
w
o
r
k
D
a
t
a
se
t
:
T
w
i
t
t
e
r
1
5
a
n
d
Tw
i
t
t
e
r
1
6
A
c
c
u
r
a
c
y
9
2
.
0
%
o
n
Tw
i
t
t
e
r
1
5
d
a
t
a
se
t
a
n
d
9
1
.
3
%
o
n
T
w
i
t
t
e
r
1
6
d
a
t
a
se
t
M
o
h
a
w
e
sh
e
t
a
l
.
[
2
8
]
M
u
l
t
i
l
i
n
g
u
a
l
d
e
e
p
l
e
a
r
n
i
n
g
f
r
a
mew
o
r
k
f
o
r
f
a
k
e
n
e
w
s
d
e
t
e
c
t
i
o
n
u
si
n
g
c
a
p
s
u
l
e
n
e
u
r
a
l
n
e
t
w
o
r
k
2
0
2
3
Jo
u
r
n
a
l
o
f
I
n
t
e
l
l
i
g
e
n
t
I
n
f
o
r
mat
i
o
n
S
y
st
e
ms
C
a
p
su
l
e
n
e
u
r
a
l
n
e
t
w
o
r
k
f
o
r
mu
l
t
i
l
i
n
g
u
a
l
f
a
k
e
n
e
w
s
d
e
t
e
c
t
i
o
n
D
a
t
a
se
t
:
T
A
L
LI
P
,
i
n
c
l
u
d
e
d
En
g
l
i
sh
,
V
i
e
t
n
a
me
se
,
S
w
a
h
i
l
i
,
H
i
n
d
i
a
n
d
I
n
d
o
n
e
si
a
n
l
a
n
g
u
a
g
e
s.
T
h
e
a
c
c
u
r
a
c
y
i
mp
r
o
v
e
s a
c
r
o
ss
v
a
r
i
o
u
s l
a
n
g
u
a
g
e
p
a
i
r
s
H
a
me
d
e
t
a
l
.
[
2
9
]
D
i
si
n
f
o
r
mat
i
o
n
d
e
t
e
c
t
i
o
n
a
b
o
u
t
i
sl
a
mi
c
i
ssu
e
s o
n
so
c
i
a
l
me
d
i
a
u
si
n
g
d
e
e
p
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s
2
0
2
3
M
a
l
a
y
si
a
n
Jo
u
r
n
a
l
o
f
C
o
mp
u
t
e
r
S
c
i
e
n
c
e
B
i
L
S
T
M
-
b
a
se
d
mo
d
e
l
.
D
a
t
a
se
t
:
I
s
l
a
mi
c
c
o
n
t
e
n
t
(
R
I
D
I
)
A
c
c
u
r
a
c
y
o
f
9
5
.
4
2
%
G
u
o
e
t
a
l
.
[
3
0
]
A
n
o
v
e
l
f
a
k
e
n
e
w
s
d
e
t
e
c
t
i
o
n
mo
d
e
l
f
o
r
c
o
n
t
e
x
t
o
f
mi
x
e
d
l
a
n
g
u
a
g
e
s
t
h
r
o
u
g
h
m
u
l
t
i
s
c
a
l
e
t
r
a
n
sf
o
r
me
r
2
0
2
3
I
EEE
T
r
a
n
sac
t
i
o
n
s
o
n
C
o
mp
u
t
a
t
i
o
n
a
l
S
o
c
i
a
l
S
y
st
e
ms
M
u
l
t
i
sc
a
l
e
t
r
a
n
sf
o
r
me
r
D
a
t
a
se
t
:
W
e
i
b
o
-
h
y
b
r
i
d
i
n
c
l
u
d
e
b
o
t
h
C
h
i
n
e
se
a
n
d
En
g
l
i
sh
w
o
r
d
s
A
c
c
u
r
a
c
y
a
p
p
r
o
x
i
mat
e
l
y
2
%
-
1
0
%
h
i
g
h
e
r
t
h
a
n
b
a
se
l
i
n
e
mo
d
e
l
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
23
,
No
.
2
,
A
p
r
il
20
25
:
3
2
9
-
339
334
R
esear
ch
er
s
h
a
v
e
d
e
v
elo
p
ed
d
iv
er
s
e
a
u
to
m
a
ted
f
a
k
e
n
e
w
s
d
etec
tio
n
m
et
h
o
d
s
,
y
et
c
h
alle
n
g
es
p
er
s
i
s
t
d
u
e
to
th
e
e
v
o
lv
i
n
g
p
r
esen
ce
o
f
m
u
lti
m
o
d
al
i
n
f
o
r
m
atio
n
i
n
th
e
f
o
r
m
o
f
te
x
t
a
n
d
i
m
ag
e
s
i
n
n
e
w
s
ar
ticle
s
an
d
li
m
ited
m
u
lti
m
o
d
al
d
ata.
A
d
d
r
ess
in
g
t
h
ese
is
s
u
e
s
,
a
m
u
l
ti
m
o
d
al
f
u
s
io
n
f
r
a
m
e
w
o
r
k
ca
lled
th
r
ee
-
le
v
el
f
ea
t
u
r
e
-
b
ased
m
atc
h
in
g
d
i
s
tan
ce
m
u
lti
m
o
d
al
f
u
s
io
n
m
o
d
el
(
T
L
FND
)
w
a
s
p
r
o
p
o
s
ed
[
3
1
]
.
T
L
FND
e
f
f
o
r
tles
s
l
y
co
m
b
in
e
s
tex
t
u
al
(
h
ea
d
li
n
e
an
d
b
o
d
y
)
an
d
v
is
u
al
d
ata
in
n
e
w
s
ar
ti
cles,
lev
er
ag
in
g
b
o
th
m
o
d
els
,
Vis
u
al
Geo
m
etr
y
Gr
o
u
p
19
also
k
n
o
w
n
as
VG
G
-
1
9
an
d
R
o
B
E
R
T
a
,
r
o
b
u
s
tl
y
o
p
ti
m
ized
B
E
R
T
.
Me
el
an
d
Vis
h
w
a
k
ar
m
a
[
3
2
]
r
esp
o
n
d
to
th
e
esca
latin
g
m
i
s
i
n
f
o
r
m
atio
n
b
y
i
n
tr
o
d
u
ci
n
g
a
v
er
ac
it
y
a
n
al
y
s
is
s
y
s
te
m
f
o
cu
s
i
n
g
o
n
b
o
th
te
x
t
u
al
an
d
v
i
s
u
al
attr
ib
u
tes.
T
h
eir
f
r
am
e
w
o
r
k
,
u
tili
z
in
g
B
E
R
T
an
d
AL
B
E
R
T
,
a
lite v
ar
iatio
n
o
f
B
E
R
T
an
d
I
n
ce
p
tio
n
-
R
esNet
-
v
2
,
ac
h
ie
v
es
r
e
m
ar
k
ab
le
ac
cu
r
ac
y
,
n
o
tab
l
y
9
7
.
1
9
%
o
n
th
e
all
d
at
a
d
atas
et.
Nad
ee
m
et
a
l.
[
3
3
]
ad
d
r
ess
th
e
r
is
e
o
f
f
ab
r
icate
d
n
e
w
s
s
to
r
ies
u
s
i
n
g
a
s
t
y
lo
m
etr
ic
an
d
s
e
m
a
n
tic
s
i
m
ilar
it
y
-
o
r
ie
n
ted
m
o
d
el
(
S
SM)
in
co
r
p
o
r
atin
g
h
y
p
er
b
o
lic
h
ier
ar
ch
ical
atte
n
tio
n
n
et
w
o
r
k
(
H
y
p
e
-
H
AN)
an
d
E
f
f
icie
n
tNe
tB
7
.
A
n
e
n
h
an
ce
d
m
u
l
tim
o
d
a
l
f
a
k
e
n
ew
s
d
e
t
e
ct
i
o
n
m
o
d
el
w
a
s
p
r
o
p
o
s
e
d
b
y
K
is
h
o
r
e
a
n
d
Ku
m
a
r
[
3
4
]
,
u
t
i
li
z
in
g
t
h
e
a
d
a
p
t
iv
e
w
a
te
r
s
t
r
i
d
e
r
a
lg
o
r
i
th
m
(A
-
W
SA
)
t
o
o
p
t
im
i
z
e
f
e
a
t
u
r
e
s
e
l
e
ct
i
o
n
f
o
r
b
o
t
h
t
ex
t
an
d
im
ag
e
d
a
t
a
.
T
h
is
m
o
d
e
l
d
em
o
n
s
t
r
a
t
es
i
t
s
e
f
f
ec
t
iv
en
es
s
in
au
t
o
m
a
tin
g
f
ak
e
n
e
w
s
cl
a
s
s
if
i
c
a
ti
o
n
o
n
s
o
ci
a
l
m
e
d
i
a
p
l
a
tf
o
r
m
s
.
M
o
r
e
o
v
e
r
,
N
a
d
e
em
e
t
a
l
.
[
3
5
]
c
o
m
b
in
es
v
a
r
i
o
u
s
d
a
t
a
ty
p
e
s
,
in
c
lu
d
in
g
c
o
n
te
x
tu
a
l
,
v
is
u
a
l
an
d
s
o
c
i
a
l
d
a
t
a
e
x
t
r
a
c
t
e
d
f
r
o
m
s
o
c
i
a
l
m
e
d
ia
an
d
n
ew
s
a
r
t
i
c
l
es
.
A
d
v
a
n
ce
d
m
o
d
els
li
k
e
b
id
ir
ec
tio
n
al
g
ated
r
ec
u
r
r
en
t
u
n
it
(
B
iGR
U
)
an
d
ca
p
s
u
le
n
eu
r
al
n
et
w
o
r
k
(
C
ap
s
Net
)
ar
e
em
p
lo
y
ed
to
d
etec
t
f
ak
e
n
e
w
s
,
p
r
o
p
o
s
in
g
a
co
m
p
r
e
h
en
s
iv
e
ap
p
r
o
ac
h
f
o
r
t
h
e
id
en
ti
f
icatio
n
o
f
f
alse
n
e
w
s
.
Yad
a
v
et
a
l.
[
3
6
]
p
r
o
p
o
s
es
ef
f
icien
t
tr
an
s
f
o
r
m
er
b
ased
m
u
ltil
e
v
el
atte
n
tio
n
(
E
T
MA
)
,
as
s
h
o
w
n
i
n
Fig
u
r
e
3
,
a
f
r
am
e
w
o
r
k
f
o
r
m
u
lti
m
o
d
al
d
etec
tio
n
o
f
f
a
k
e
n
e
w
s
.
I
t
co
n
s
i
s
ts
o
f
t
w
o
tr
an
s
f
o
r
m
er
-
b
ased
en
co
d
er
s
:
o
n
e
f
o
r
tex
tu
a
l
atten
tio
n
an
d
th
e
o
th
er
f
o
r
v
is
u
al
atten
tio
n
.
T
h
ese
s
tu
d
ies
e
m
p
h
as
ize
th
e
ess
e
n
tial
r
o
le
o
f
m
u
lti
m
o
d
al
ap
p
r
o
ac
h
es
i
n
ac
h
iev
in
g
e
f
f
ec
tiv
e
f
a
k
e
n
e
w
s
d
etec
tio
n
.
L
e
v
er
ag
i
n
g
ad
v
a
n
c
ed
m
o
d
els,
f
u
s
io
n
tech
n
iq
u
es,
an
d
atten
tio
n
m
e
ch
an
i
s
m
s
to
o
v
er
co
m
e
c
h
alle
n
g
e
s
in
th
e
ch
a
n
g
i
n
g
d
y
n
a
m
ics
o
f
in
f
o
r
m
atio
n
d
is
s
e
m
in
at
io
n
,
w
h
er
e
th
e
f
o
cu
s
ex
ten
d
s
b
e
y
o
n
d
th
e
tex
t
u
al
s
id
e.
T
a
b
le
4
(
in
A
p
p
en
d
ix
)
[
3
1
]
-
[
3
9
]
p
r
o
v
id
es
a
d
etailed
o
u
tlin
e
o
f
t
h
ese
m
u
lti
m
o
d
al
f
r
a
m
e
w
o
r
k
s
a
n
d
th
e
m
e
th
o
d
o
lo
g
ies ap
p
lied
.
Fig
u
r
e
3
.
Mu
lti
m
o
d
al
E
T
MA
f
r
a
m
e
w
o
r
k
b
y
Yad
av
et
a
l.
[
3
6]
T
h
e
in
cr
ea
s
e
o
f
in
ac
c
u
r
ate
co
n
ten
t
o
n
s
o
cial
n
et
w
o
r
k
i
n
g
p
l
atf
o
r
m
s
o
f
f
er
s
a
s
er
io
u
s
t
h
r
ea
t
to
p
u
b
lic
tr
u
s
t
i
n
th
e
d
y
n
a
m
ic
w
o
r
ld
o
f
d
ig
ital
n
e
w
s
.
I
n
r
esp
o
n
s
e
to
t
h
is
ch
alle
n
g
e,
a
r
an
g
e
o
f
ap
p
r
o
ac
h
es,
n
o
tab
l
y
th
o
s
e
d
ee
p
lear
n
in
g
-
b
ased
m
o
d
els,
h
av
e
b
ee
n
r
ec
o
m
m
e
n
d
ed
to
d
ete
ct
f
alse
in
f
o
r
m
atio
n
.
Dee
p
lear
n
in
g
,
k
n
o
w
n
f
o
r
it
s
ad
v
an
ce
d
p
atter
n
r
ec
o
g
n
itio
n
an
d
f
ea
tu
r
e
ex
tr
ac
tio
n
,
o
u
t
p
er
f
o
r
m
s
tr
ad
itio
n
al
m
ac
h
in
e
lear
n
in
g
m
o
d
el
s
,
en
h
a
n
ci
n
g
ac
c
u
r
ac
y
a
n
d
r
eliab
ilit
y
i
n
id
en
ti
f
y
i
n
g
f
ak
e
n
e
w
s
ac
r
o
s
s
d
if
f
er
e
n
t
d
atasets
a
n
d
s
ce
n
ar
io
s
.
On
e
s
u
c
h
h
y
b
r
id
-
i
m
p
r
o
v
ed
d
ee
p
lear
n
in
g
m
o
d
el,
p
r
esen
ted
b
y
Ha
n
s
h
al
et
a
l.
[
4
0
]
h
y
b
r
id
izes
co
n
v
o
l
u
ti
o
n
al
n
eu
r
al
n
et
w
o
r
k
(
C
NN)
w
it
h
r
ec
u
r
r
en
t
n
eu
r
al
n
et
w
o
r
k
(
R
NN)
,
ac
h
ie
v
in
g
s
u
p
er
io
r
p
er
f
o
r
m
an
ce
w
i
t
h
9
3
.
8
7
%
ac
cu
r
ac
y
.
An
o
th
er
ap
p
r
o
ac
h
,
i
n
tr
o
d
u
ce
d
b
y
Gao
et
a
l.
[
4
1
]
,
e
m
p
lo
y
s
g
r
ap
h
m
atc
h
in
g
a
n
d
ex
ter
n
al
k
n
o
w
led
g
e
to
d
etec
t
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
Dete
ctin
g
fa
ke
n
ews
th
r
o
u
g
h
d
ee
p
lea
r
n
in
g
:
a
cu
r
r
en
t sys
tema
tic
r
ev
iew
(
I
d
z
a
A
is
a
r
a
N
o
r
a
b
id
)
335
f
ak
e
n
e
w
s
u
t
ilizi
n
g
t
h
e
B
i
-
GR
U
-
C
R
F
ar
c
h
itect
u
r
e,
ac
h
ie
v
i
n
g
co
m
m
e
n
d
ab
le
ac
cu
r
ac
y
r
ate
s
o
f
9
1
.
0
7
%
o
n
a
f
ak
e
n
e
w
s
d
ataset.
D
ev
a
r
a
ja
n
e
t
a
l
.
[
4
2
]
p
r
o
p
o
s
e
d
a
n
d
e
e
p
-
NL
P
b
a
s
e
d
f
r
am
ew
o
r
k
as
in
F
ig
u
r
e
4
,
a
n
d
a
ch
i
ev
e
d
a
n
e
v
a
lu
at
i
o
n
p
e
r
f
o
r
m
a
n
c
e
w
ith
av
e
r
ag
e
a
cc
u
r
a
cy
o
f
9
9
.
7
2
%
.
A
li
e
t
a
l
.
[
4
3
]
p
r
o
p
o
s
e
a
m
o
d
e
l
ca
l
l
e
d
s
t
a
t
is
ti
c
a
l
w
o
r
d
em
b
e
d
d
in
g
o
v
e
r
l
in
g
u
is
ti
c
f
ea
t
u
r
es
v
i
a
d
e
e
p
l
e
a
r
n
in
g
(
S
W
E
L
DL
f
ak
e
)
,
a
m
o
d
el
i
n
t
eg
r
a
tin
g
s
t
at
is
t
i
ca
l
w
o
r
d
em
b
e
d
d
in
g
an
d
b
i
d
i
r
e
c
ti
o
n
a
l
L
S
T
M
,
a
c
h
i
ev
i
n
g
an
im
p
r
ess
iv
e
a
c
c
u
r
ac
y
o
f
9
8
.
5
2
%
.
Su
r
y
a
w
an
s
h
i
e
t
a
l
.
[
4
4
]
p
r
e
s
e
n
t
a
n
in
c
r
em
en
t
al
en
s
em
b
l
e
n
eu
r
a
l
n
e
tw
o
r
k
th
a
t
a
d
a
p
t
s
t
o
ev
o
lv
in
g
n
e
w
s
p
a
t
t
e
r
n
s
,
d
em
o
n
s
t
r
a
t
in
g
c
o
n
s
is
t
en
t
p
e
r
f
o
r
m
an
c
e
w
ith
9
7
.
9
0
%
a
cc
u
r
a
cy
.
I
n
r
es
p
o
n
s
e
t
o
th
e
in
f
o
d
em
ic
d
u
r
in
g
th
e
C
OV
I
D
-
1
9
c
r
is
is
,
T
a
h
a
et
a
l
.
[
4
5
]
em
p
l
o
y
B
E
R
T
w
i
th
L
S
T
M
m
o
d
e
l
f
o
r
f
a
k
e
n
e
w
s
d
et
e
c
t
i
o
n
,
a
c
h
ie
v
in
g
ac
cu
r
a
cy
r
a
t
es
o
f
h
ig
h
e
r
th
an
9
8
%
.
T
h
e
p
r
o
p
o
s
e
d
m
o
d
el
s
b
y
M
al
l
ic
k
e
t
a
l
.
[
4
6
]
a
n
d
W
a
n
g
e
t
a
l
.
[
4
7
]
i
n
t
r
o
d
u
c
e
a
C
NN
-
b
a
s
e
d
m
o
d
e
l
f
o
r
f
a
k
e
n
ew
s
r
ef
u
t
er
i
d
e
n
tif
i
c
at
i
o
n
r
e
s
u
lt
in
g
in
h
ig
h
a
c
cu
r
a
cy
r
at
e
s
o
f
9
8
%
.
T
h
es
e
u
t
i
li
z
a
ti
o
n
s
o
f
d
e
e
p
l
e
a
r
n
in
g
s
h
o
w
ca
s
e
th
e
e
f
f
e
ct
iv
en
es
s
o
f
a
d
v
an
c
e
d
t
e
ch
n
i
q
u
e
s
in
c
o
m
b
at
t
in
g
th
e
p
e
r
v
as
iv
e
c
h
al
l
en
g
e
o
f
m
is
in
f
o
r
m
a
t
i
o
n
f
r
o
m
d
if
f
e
r
en
t
a
n
g
l
es
.
A
s
a
r
esu
l
t
,
th
ey
c
o
n
s
is
t
en
tly
o
u
t
p
e
r
f
o
r
m
t
r
a
d
it
i
o
n
a
l
m
o
d
e
ls
w
ith
th
e
i
r
a
d
v
an
c
e
d
ca
p
a
b
i
l
i
ti
e
s
.
T
a
b
l
e
5
(i
n
A
p
p
en
d
ix
)
[
4
0
]
,
[
4
2
]
-
[
5
1
]
p
r
e
s
en
ts
a
n
o
v
e
r
v
i
ew
o
f
th
es
e
d
e
e
p
l
e
a
r
n
in
g
a
p
p
r
o
a
ch
e
s
,
h
ig
h
li
g
h
t
in
g
th
e
a
d
v
an
c
ed
c
a
p
a
b
i
l
i
ti
e
s
o
f
t
h
e
m
o
d
el
s
i
n
a
d
d
r
e
s
s
in
g
m
is
in
f
o
r
m
a
ti
o
n
an
d
co
n
s
i
s
t
en
t
ly
o
u
t
p
e
r
f
o
r
m
in
g
t
r
a
d
it
i
o
n
al
m
e
th
o
d
s
.
Fig
u
r
e
4
.
A
d
ee
p
NL
P
-
b
ased
f
r
a
m
e
w
o
r
k
b
y
De
v
ar
aj
an
et
a
l.
[
4
2
]
4.
CO
NCLU
SI
O
N
T
h
is
co
m
p
r
eh
e
n
s
iv
e
an
a
l
y
s
is
o
f
f
er
s
a
th
o
r
o
u
g
h
a
n
al
y
s
is
o
f
th
e
p
r
esen
t
s
tate
o
f
d
etec
ti
n
g
f
ak
e
n
e
w
s
th
r
o
u
g
h
t
h
e
u
tili
s
atio
n
o
f
d
ee
p
lear
n
in
g
tech
n
iq
u
es.
d
r
a
w
in
g
in
s
i
g
h
t
s
f
r
o
m
3
3
ar
ticles
id
en
ti
f
ied
th
r
o
u
gh
ad
v
an
ce
d
s
ea
r
c
h
tec
h
n
iq
u
es
o
n
Sco
p
u
s
a
n
d
W
o
S
d
atab
ases
.
T
h
e
r
ev
ie
w
e
x
p
lo
r
es
th
r
ee
m
ain
t
h
e
m
es,
n
a
m
el
y
Data
s
et
a
n
d
B
en
ch
m
ar
k
in
g
f
o
r
f
ak
e
n
e
w
s
d
etec
tio
n
,
m
u
lti
m
o
d
al
ap
p
r
o
ac
h
es
f
o
r
f
a
k
e
n
e
w
s
d
etec
tio
n
an
d
d
ee
p
lear
n
in
g
ap
p
licatio
n
s
a
n
d
tech
n
iq
u
es
f
o
r
f
a
k
e
n
e
w
s
d
etec
tio
n
.
T
h
is
ex
p
lo
r
atio
n
h
i
g
h
li
g
h
t
s
t
h
e
e
v
o
lv
i
n
g
s
tr
ateg
ie
s
an
d
m
et
h
o
d
o
lo
g
ies
i
n
th
e
f
ield
.
B
y
b
r
in
g
i
n
g
to
g
et
h
er
th
ese
in
s
ig
h
t
s
,
th
i
s
r
ev
ie
w
e
n
r
ich
e
s
th
e
ac
ad
e
m
ic
d
is
cu
s
s
io
n
o
n
d
etec
ti
n
g
f
a
k
e
n
e
w
s
,
p
r
o
v
id
in
g
v
a
lu
ab
le
p
er
s
p
ec
tiv
es
f
o
r
r
esear
ch
er
s
an
d
p
r
ac
titi
o
n
er
s
to
g
u
id
e
f
u
tu
r
e
i
n
itiati
v
e
s
in
t
h
is
cr
u
cial
d
o
m
ai
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
23
,
No
.
2
,
A
p
r
il
20
25
:
3
2
9
-
339
336
AP
P
E
NDI
X
T
ab
le
4
.
Ov
er
v
ie
w
o
f
m
u
lt
i
m
o
d
al
ap
p
r
o
ac
h
es f
o
r
f
a
k
e
n
e
w
s
d
etec
tio
n
A
u
t
h
o
r
T
i
t
l
e
Y
e
a
r
Jo
u
r
n
a
l
M
e
t
h
o
d
o
l
o
g
y
R
e
su
l
t
s
W
a
n
g
e
t
a
l
.
[
3
1
]
TL
F
N
D
:
a
mu
l
t
i
mo
d
a
l
f
u
si
o
n
mo
d
e
l
b
a
se
d
o
n
t
h
r
e
e
-
l
e
v
e
l
f
e
a
t
u
r
e
mat
c
h
i
n
g
d
i
s
t
a
n
c
e
f
o
r
f
a
k
e
n
e
w
s d
e
t
e
c
t
i
o
n
2
0
2
3
A
p
p
l
i
c
a
t
i
o
n
o
f
I
n
f
o
r
mat
i
o
n
T
h
e
o
r
y
t
o
P
h
y
si
c
a
l
M
o
d
e
l
i
n
g
a
n
d
S
t
a
t
e
A
w
a
r
e
n
e
ss i
n
C
o
mp
l
e
x
S
y
st
e
ms
T
e
x
t
u
a
l
:
R
o
B
E
R
T
a
mo
d
e
l
V
i
su
a
l
:
VGG
-
1
9
mo
d
e
l
A
c
c
u
r
a
c
y
o
f
9
4
.
4
%
o
n
t
h
e
P
o
l
i
t
i
F
a
c
t
d
a
t
a
se
t
a
n
d
9
0
.
9
%
o
n
G
o
ssi
p
C
o
p
d
a
t
a
se
t
M
e
e
l
a
n
d
V
i
sh
w
a
k
a
r
m
a
[
3
2
]
M
u
l
t
i
-
mo
d
a
l
f
u
si
o
n
u
si
n
g
f
i
n
e
-
t
u
n
e
d
se
l
f
-
a
t
t
e
n
t
i
o
n
a
n
d
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
f
o
r
v
e
r
a
c
i
t
y
a
n
a
l
y
si
s o
f
w
e
b
i
n
f
o
r
mat
i
o
n
2
0
2
3
S
o
c
i
a
l
a
n
d
I
n
f
o
r
mat
i
o
n
N
e
t
w
o
r
k
s
T
e
x
t
u
a
l
f
e
a
t
u
r
e
s:
B
E
R
T
a
n
d
A
L
B
ER
T
mo
d
e
l
s
V
i
su
a
l
f
e
a
t
u
r
e
s:
I
n
c
e
p
t
i
o
n
-
R
e
sN
e
t
-
v
2
A
c
c
u
r
a
c
y
o
f
9
7
.
1
9
%
o
n
t
h
e
a
l
l
d
a
t
a
d
a
t
a
se
t
N
a
d
e
e
m
e
t
a
l
.
[
3
3
]
S
S
M
:
st
y
l
o
m
e
t
r
i
c
a
n
d
se
man
t
i
c
s
i
m
i
l
a
r
i
t
y
o
r
i
e
n
t
e
d
m
u
l
t
i
mo
d
a
l
f
a
k
e
n
e
w
s d
e
t
e
c
t
i
o
n
2
0
2
3
Jo
u
r
n
a
l
o
f
K
i
n
g
S
a
u
d
U
n
i
v
e
r
si
t
y
-
C
o
mp
u
t
e
r
a
n
d
I
n
f
o
r
mat
i
o
n
S
c
i
e
n
c
e
s
S
t
y
l
o
me
t
r
i
c
t
e
x
t
u
a
l
f
e
a
t
u
r
e
s:
H
y
p
e
-
H
A
N
V
i
su
a
l
se
ma
n
t
i
c
e
x
p
r
e
ssi
o
n
:
Ef
f
i
c
i
e
n
t
N
e
t
B
7
mo
d
e
l
A
c
c
u
r
a
c
y
o
f
h
i
g
h
e
r
t
h
a
n
9
5
%
o
n
TI
-
C
N
N
,
F
N
D
D
a
n
d
F
N
S
D
S
d
a
t
a
se
t
K
i
sh
o
r
e
a
n
d
K
u
mar
[
3
4
]
En
h
a
n
c
e
d
mu
l
t
i
mo
d
a
l
f
a
k
e
n
e
w
s
d
e
t
e
c
t
i
o
n
w
i
t
h
o
p
t
i
m
a
l
f
e
a
t
u
r
e
f
u
s
i
o
n
a
n
d
mo
d
i
f
i
e
d
b
i
-
L
S
T
M
a
r
c
h
i
t
e
c
t
u
r
e
2
0
2
3
C
y
b
e
r
n
e
t
i
c
s a
n
d
S
y
st
e
ms
I
mag
e
a
n
d
t
e
x
t
f
e
a
t
u
r
e
s:
a
d
a
p
t
i
v
e
w
a
t
e
r
st
r
i
d
e
r
a
l
g
o
r
i
t
h
m (A
-
W
S
A
)
A
c
c
u
r
a
c
y
r
a
t
e
o
f
9
6
.
5
1
%
N
a
d
e
e
m
e
t
a
l
.
[
3
5
]
EF
N
D
:
a
se
man
t
i
c
,
v
i
su
a
l
,
a
n
d
so
c
i
a
l
l
y
a
u
g
me
n
t
e
d
d
e
e
p
f
r
a
mew
o
r
k
f
o
r
e
x
t
r
e
me
f
a
k
e
n
e
w
s d
e
t
e
c
t
i
o
n
2
0
2
3
S
u
st
a
i
n
a
b
l
e
Ed
u
c
a
t
i
o
n
a
n
d
S
o
c
i
a
l
N
e
t
w
o
r
k
s
C
o
n
t
e
x
t
u
a
l
d
a
t
a
:
B
i
G
R
U
a
n
d
a
t
t
e
n
t
i
o
n
me
c
h
a
n
i
sm
V
i
su
a
l
d
a
t
a
:
C
a
p
sN
e
t
w
i
t
h
c
o
n
v
o
l
u
t
i
o
n
A
c
c
u
r
a
c
y
o
f
0
.
9
8
8
%
a
n
d
0
.
9
9
0
%
o
n
P
o
l
i
t
i
F
a
c
t
a
n
d
G
o
ssi
p
C
o
p
d
a
t
a
se
t
s
Y
a
d
a
v
e
t
a
l
.
[
3
6
]
ET
M
A
:
e
f
f
i
c
i
e
n
t
t
r
a
n
sf
o
r
me
r
-
b
a
se
d
mu
l
t
i
l
e
v
e
l
a
t
t
e
n
t
i
o
n
f
r
a
mew
o
r
k
f
o
r
mu
l
t
i
mo
d
a
l
f
a
k
e
n
e
w
s
d
e
t
e
c
t
i
o
n
2
0
2
3
I
EEE
T
r
a
n
sac
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
st
e
ms
T
e
x
t
u
a
l
f
e
a
t
u
r
e
s:
B
E
R
T
V
i
su
a
l
f
e
a
t
u
r
e
s:
T
r
a
n
sf
o
r
me
r
a
t
t
e
n
t
i
o
n
b
a
se
d
e
n
c
o
d
e
r
A
c
c
u
r
a
c
y
o
f
a
b
o
v
e
9
5
%
o
n
a
l
l
f
o
u
r
d
a
t
a
se
t
s:
Jr
u
v
i
k
a
f
a
k
e
n
e
w
s,
P
o
n
t
e
s fa
k
e
n
e
w
s,
Tw
i
t
t
e
r
a
n
d
R
i
s
d
a
l
d
a
t
a
se
t
s
A
l
O
b
a
i
d
e
t
a
l
.
[
3
7
]
R
o
b
u
st
se
mi
-
s
u
p
e
r
v
i
se
d
f
a
k
e
n
e
w
s re
c
o
g
n
i
t
i
o
n
b
y
e
f
f
e
c
t
i
v
e
a
u
g
me
n
t
a
t
i
o
n
s
a
n
d
e
n
se
mb
l
e
o
f
d
i
v
e
r
se
d
e
e
p
l
e
a
r
n
e
r
s
2
0
2
3
I
EEE
A
c
c
e
ss
T
e
x
t
u
a
l
f
e
a
t
u
r
e
s:
X
L
N
ET
t
r
a
n
sf
o
r
me
r
I
mag
e
f
e
a
t
u
r
e
s:
Ef
f
i
c
i
e
n
t
N
e
t
B
3
A
c
c
u
r
a
c
y
o
f
h
i
g
h
e
r
t
h
a
n
8
0
%
o
n
G
o
ssi
p
,
P
o
l
i
t
i
F
a
c
t
a
n
d
J
u
v
r
i
k
a
d
a
t
a
se
t
s
S
h
a
r
ma
e
t
a
l
.
[
3
8
]
F
a
k
e
d
b
i
t
s
-
d
e
t
e
c
t
i
n
g
f
a
k
e
i
n
f
o
r
mat
i
o
n
o
n
so
c
i
a
l
p
l
a
t
f
o
r
ms u
si
n
g
mu
l
t
i
-
mo
d
a
l
f
e
a
t
u
r
e
s
2
0
2
3
K
S
I
I
T
r
a
n
sac
t
i
o
n
s
o
n
I
n
t
e
r
n
e
t
a
n
d
I
n
f
o
r
mat
i
o
n
S
y
st
e
ms
T
e
x
t
u
a
l
f
e
a
t
u
r
e
s:
t
r
a
n
sf
o
r
me
r
V
i
su
a
l
f
e
a
t
u
r
e
s:
Ef
f
i
c
i
e
n
t
N
e
t
B
0
A
c
c
u
r
a
c
i
e
s o
f
8
6
.
4
8
%
o
n
M
e
d
i
a
Ev
a
l
(
T
w
i
t
t
e
r
)
,
8
2
.
5
0
%
o
n
W
e
i
b
o
,
a
n
d
8
8
.
8
0
%
o
n
F
a
k
e
d
d
i
t
d
a
t
a
se
t
G
o
y
a
l
e
t
a
l
.
[
3
9
]
D
e
t
e
c
t
i
o
n
o
f
f
a
k
e
a
c
c
o
u
n
t
s o
n
so
c
i
a
l
me
d
i
a
u
si
n
g
m
u
l
t
i
mo
d
a
l
d
a
t
a
w
i
t
h
d
e
e
p
l
e
a
r
n
i
n
g
2
0
2
3
I
EEE
T
r
a
n
sac
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
st
e
ms
T
e
x
t
u
a
l
f
e
a
t
u
r
e
s:
L
S
T
M
mo
d
e
l
V
i
su
a
l
f
e
a
t
u
r
e
s:
C
N
N
mo
d
e
l
A
c
c
u
r
a
c
y
o
f
9
7
%
o
n
d
a
t
a
se
t
o
f
T
w
i
t
t
e
r
a
c
c
o
u
n
t
s
T
ab
le
5
.
Ov
er
v
ie
w
o
f
d
ee
p
lear
n
in
g
ap
p
r
o
ac
h
es f
o
r
f
a
k
e
n
e
ws d
etec
tio
n
A
u
t
h
o
r
T
i
t
l
e
Y
e
a
r
Jo
u
r
n
a
l
M
e
t
h
o
d
o
l
o
g
y
R
e
su
l
t
s
H
a
n
s
h
a
l
e
t
a
l
.
[
4
0
]
H
y
b
r
i
d
d
e
e
p
l
e
a
r
n
i
n
g
mo
d
e
l
f
o
r
a
u
t
o
ma
t
i
c
f
a
k
e
n
e
w
s
d
e
t
e
c
t
i
o
n
2
0
2
3
A
p
p
l
i
e
d
N
a
n
o
sc
i
e
n
c
e
H
y
b
r
i
d
-
i
mp
r
o
v
e
d
d
e
e
p
l
e
a
r
n
i
n
g
mo
d
e
l
;
c
o
mb
i
n
a
t
i
o
n
o
f
C
N
N
w
i
t
h
R
N
N
A
c
c
u
r
a
c
y
o
f
9
3
.
8
7
%
o
n
B
u
z
z
f
e
e
d
,
F
a
k
e
N
e
w
s
N
e
t
,
a
n
d
F
a
k
e
N
e
w
sC
h
a
l
l
e
n
g
e
s
d
a
t
a
se
t
s
D
e
v
a
r
a
j
a
n
e
t
a
l
.
[
4
2
]
AI
-
a
ssi
st
e
d
d
e
e
p
N
L
P
-
b
a
se
d
a
p
p
r
o
a
c
h
f
o
r
p
r
e
d
i
c
t
i
o
n
o
f
f
a
k
e
n
e
w
s fr
o
m so
c
i
a
l
me
d
i
a
u
se
r
s
2
0
2
3
I
EEE
T
r
a
n
sac
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
st
e
ms
C
N
N
B
i
-
L
S
T
M
(N
-
D
C
B
L
)
a
t
t
e
n
t
i
o
n
n
e
t
w
o
r
k
A
v
e
r
a
g
e
a
c
c
u
r
a
c
y
o
f
9
9
.
7
2
%
o
n
B
u
z
z
f
a
c
e
,
F
a
k
e
N
e
w
sN
e
t
,
a
n
d
T
w
i
t
t
e
r
d
a
t
a
se
t
A
l
i
e
t
a
l
.
[
4
3
]
L
i
n
g
u
i
st
i
c
f
e
a
t
u
r
e
s a
n
d
b
i
-
L
S
T
M
f
o
r
i
d
e
n
t
i
f
i
c
a
t
i
o
n
o
f
f
a
k
e
n
e
w
s
2
0
2
3
El
e
c
t
r
o
n
i
c
s
Bi
-
L
S
T
M
mo
d
e
l
A
c
c
u
r
a
c
y
o
f
9
8
.
5
2
%
o
n
S
W
E
L
D
L
F
a
k
e
d
a
t
a
se
t
S
u
r
y
a
w
a
n
sh
i
e
t
a
l
.
[
4
4
]
F
A
K
E
I
D
C
A
:
f
a
k
e
n
e
w
s
d
e
t
e
c
t
i
o
n
w
i
t
h
i
n
c
r
e
me
n
t
a
l
d
e
e
p
l
e
a
r
n
i
n
g
-
b
a
se
d
c
o
n
c
e
p
t
d
r
i
f
t
a
d
a
p
t
i
o
n
2
0
2
3
M
u
l
t
i
me
d
i
a
T
o
o
l
s
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
I
n
c
r
e
me
n
t
a
l
e
n
se
mb
l
e
n
e
u
r
a
l
n
e
t
w
o
r
k
C
o
n
si
s
t
e
n
c
e
a
c
c
u
r
a
c
y
o
f
h
i
g
h
e
r
t
h
a
n
9
7
%
o
n
b
o
t
h
F
a
k
e
a
n
d
R
e
a
l
n
e
w
s a
n
d
G
e
t
t
i
n
g
R
e
a
l
a
b
o
u
t
F
a
k
e
N
e
w
s d
a
t
a
se
t
s
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
Dete
ctin
g
fa
ke
n
ews
th
r
o
u
g
h
d
ee
p
lea
r
n
in
g
:
a
cu
r
r
en
t sys
tema
tic
r
ev
iew
(
I
d
z
a
A
is
a
r
a
N
o
r
a
b
id
)
337
T
ab
le
5
.
Ov
er
v
ie
w
o
f
d
ee
p
lear
n
in
g
ap
p
r
o
ac
h
es f
o
r
f
a
k
e
n
e
ws d
etec
tio
n
(
co
n
tin
u
ed
)
A
u
t
h
o
r
T
i
t
l
e
Y
e
a
r
Jo
u
r
n
a
l
M
e
t
h
o
d
o
l
o
g
y
R
e
su
l
t
s
T
a
h
a
e
t
a
l
.
[
4
5
]
A
u
t
o
mat
e
d
C
O
V
I
D
-
19
mi
si
n
f
o
r
mat
i
o
n
c
h
e
c
k
i
n
g
sy
st
e
m u
si
n
g
e
n
c
o
d
e
r
r
e
p
r
e
se
n
t
a
t
i
o
n
w
i
t
h
d
e
e
p
l
e
a
r
n
i
n
g
mo
d
e
l
s
2
0
2
3
I
A
ES
I
n
t
e
r
n
a
t
i
o
n
a
l
Jo
u
r
n
a
l
o
f
A
r
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
(
I
J
-
A
I
)
B
ER
T
w
i
t
h
L
S
T
M
mo
d
e
A
c
c
u
r
a
c
y
o
f
9
9
.
1
%
o
n
C
O
V
I
D
-
1
9
d
a
t
a
se
t
M
a
l
l
i
c
k
e
t
a
l
.
[
4
6
]
A
c
o
o
p
e
r
a
t
i
v
e
d
e
e
p
l
e
a
r
n
i
n
g
mo
d
e
l
f
o
r
f
a
k
e
n
e
w
s d
e
t
e
c
t
i
o
n
i
n
o
n
l
i
n
e
so
c
i
a
l
n
e
t
w
o
r
k
s
2
0
2
3
Jo
u
r
n
a
l
o
f
A
mb
i
e
n
t
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
H
u
ma
n
i
z
e
d
C
o
mp
u
t
i
n
g
V
G
G
1
6
,
a
C
N
N
-
b
a
se
d
mo
d
e
l
A
c
c
u
r
a
c
y
r
a
t
e
o
f
9
8
%
o
n
d
a
t
a
c
o
l
l
e
c
t
e
d
f
r
o
m F
a
k
e
N
e
w
s De
t
e
c
t
i
o
n
,
I
S
O
T
a
n
d
F
a
k
e
N
e
w
s d
a
t
a
se
t
s
W
a
n
g
e
t
a
l
.
[
4
7
]
T
o
w
a
r
d
s fak
e
n
e
w
s re
f
t
e
r
i
d
e
n
t
i
f
i
c
a
t
i
o
n
:
mi
x
t
u
r
e
o
f
c
h
i
-
me
r
g
e
g
r
o
u
n
d
e
d
c
n
n
a
p
p
r
o
a
c
h
2
0
2
3
Ex
p
e
r
t
S
y
st
e
ms
w
i
t
h
A
p
p
l
i
c
a
t
i
o
n
s
ER
N
I
E2
mo
d
e
l
w
i
t
h
t
h
e
C
h
i
-
M
e
r
g
e
g
r
o
u
n
d
e
d
C
N
N
A
c
c
u
r
a
c
y
o
f
8
5
.
9
%.
o
n
n
e
a
r
l
y
6
0
,
0
0
0
r
e
a
l
-
w
o
r
l
d
S
i
n
a
W
e
i
b
o
d
a
t
a
Jaw
a
d
a
n
d
O
b
a
i
d
[
4
8
]
T
h
e
c
o
mb
i
n
a
t
i
o
n
o
f
c
o
n
v
o
l
u
t
i
o
n
n
e
u
r
a
l
n
e
t
w
o
r
k
s
a
n
d
d
e
e
p
n
e
u
r
a
l
n
e
t
w
o
r
k
s fo
r
f
a
k
e
n
e
w
s
d
e
t
e
c
t
i
o
n
2
0
2
3
I
n
f
o
r
mat
i
o
n
R
e
t
r
i
e
v
a
l
El
b
o
w
t
r
u
n
c
a
t
e
d
me
t
h
o
d
i
n
c
o
mb
i
n
a
t
i
o
n
w
i
t
h
C
N
N
a
n
d
D
N
N
mo
d
e
l
A
v
e
r
a
g
e
a
c
c
u
r
a
c
y
o
f
8
4
.
6
%
o
n
f
a
k
e
n
e
w
s c
h
a
l
l
e
n
g
e
(
F
N
C
-
1
)
d
a
t
a
se
t
K
o
z
i
k
e
t
a
l
.
[
4
9
]
D
e
e
p
l
e
a
r
n
i
n
g
f
o
r
c
o
mb
a
t
i
n
g
mi
si
n
f
o
r
mat
i
o
n
i
n
mu
l
t
i
c
a
t
e
g
o
r
i
c
a
l
t
e
x
t
c
o
n
t
e
n
t
s
2
0
2
3
D
e
e
p
L
e
a
r
n
i
n
g
f
o
r
I
n
f
o
r
mat
i
o
n
F
u
si
o
n
a
n
d
P
a
t
t
e
r
n
R
e
c
o
g
n
i
t
i
o
n
B
ER
T
l
a
n
g
u
a
g
e
mo
d
e
l
I
mp
r
o
v
e
me
n
t
o
f
n
e
a
r
l
y
3
0
%
i
n
b
a
l
a
n
c
e
d
a
c
c
u
r
a
c
y
C
h
e
n
e
t
a
l
.
[
5
0
]
U
si
n
g
d
e
e
p
l
e
a
r
n
i
n
g
mo
d
e
l
s t
o
d
e
t
e
c
t
f
a
k
e
n
e
w
s a
b
o
u
t
C
O
V
I
D
-
19
2
0
2
3
A
C
M
T
r
a
n
sac
t
i
o
n
s
o
n
I
n
t
e
r
n
e
t
T
e
c
h
n
o
l
o
g
y
B
i
L
S
T
M
mo
d
e
l
A
c
c
u
r
a
c
y
o
f
9
4
%,
9
9
%
f
o
r
sh
o
r
t
a
n
d
l
o
n
g
se
n
t
e
n
c
e
o
f
En
g
l
i
s
h
t
e
x
t
s
A
c
c
u
r
a
c
y
a
t
8
2
%
f
o
r
C
h
i
n
e
se
t
e
x
t
s
M
a
d
a
n
i
e
t
a
l
.
[
5
1
]
F
a
k
e
n
e
w
s d
e
t
e
c
t
i
o
n
u
si
n
g
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
,
n
a
t
u
r
a
l
l
a
n
g
u
a
g
e
p
r
o
c
e
ssi
n
g
,
c
u
r
r
i
c
u
l
u
m
l
e
a
r
n
i
n
g
,
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
2
0
2
3
I
n
t
e
r
n
a
t
i
o
n
a
l
Jo
u
r
n
a
l
o
f
I
n
f
o
r
mat
i
o
n
T
e
c
h
n
o
l
o
g
y
&
D
e
c
i
si
o
n
M
a
k
i
n
g
L
S
T
M
mo
d
e
l
A
c
c
u
r
a
c
y
o
f
a
b
o
v
e
9
5
%
o
n
f
a
k
e
o
r
r
e
a
l
d
a
t
a
se
t
a
n
d
I
S
O
T
d
a
t
a
se
t
A
c
c
u
r
a
c
y
o
f
a
b
o
v
e
8
0
%
o
n
LI
A
R
a
n
d
F
a
k
e
N
e
w
sN
e
t
d
a
t
a
se
t
ACK
NO
WL
E
D
G
E
M
E
NT
S
Fin
a
n
cial
s
u
p
p
o
r
t
f
o
r
th
is
s
t
u
d
y
w
as
g
r
ac
io
u
s
l
y
p
r
o
v
id
ed
by
t
h
e
Fu
n
d
a
m
en
ta
l
R
esear
c
h
Gr
an
t
Sc
h
e
m
e,
Min
i
s
tr
y
o
f
H
ig
h
er
E
d
u
ca
tio
n
Ma
la
y
s
ia,
d
esi
g
n
ated
b
y
g
r
a
n
t
n
u
m
b
er
FR
GS/1
/2
0
2
3
/I
C
T
0
2
/
UM
T
/0
3
/1
.
RE
F
E
R
E
NC
E
S
[
1
]
B
.
C
.
N
e
v
e
s
a
n
d
J.
B
o
r
g
e
s,
“
W
h
y
d
o
e
s
f
a
k
e
n
e
w
s
h
a
v
e
sp
a
c
e
o
n
so
c
i
a
l
me
d
i
a
?
A
d
i
scu
ss
i
o
n
i
n
t
h
e
l
i
g
h
t
o
f
i
n
f
o
c
o
mm
u
n
i
c
a
t
i
o
n
a
l
b
e
h
a
v
i
o
r
a
n
d
d
i
g
i
t
a
l
m
a
r
k
e
t
i
n
g
,
”
I
n
f
o
r
m
a
c
a
o
e
S
o
c
i
e
d
a
d
e
.
2
0
2
0
,
d
o
i
:
1
0
.
2
2
4
7
8
/
u
f
p
b
.
1
809
-
4
7
8
3
.
2
0
2
0
v
3
0
n
2
.
5
0
4
1
0
.
[
2
]
F
.
W
u
a
n
d
X
.
L
u
o
,
“
En
g
l
i
s
h
T
e
x
t
R
e
c
o
g
n
i
t
i
o
n
D
e
e
p
L
e
a
r
n
i
n
g
F
r
a
me
w
o
r
k
t
o
A
u
t
o
ma
t
i
c
a
l
l
y
I
d
e
n
t
i
f
y
F
a
k
e
N
e
w
s,”
C
o
m
p
u
t
a
t
i
o
n
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
N
e
u
ro
s
c
i
e
n
c
e
,
p
p
.
1
–
9
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
2
/
1
4
9
3
4
9
3
.
[
3
]
A
.
M
o
h
a
mm
e
d
a
n
d
R
.
K
o
r
a
,
“
A
n
e
f
f
e
c
t
i
v
e
e
n
se
mb
l
e
d
e
e
p
l
e
a
r
n
i
n
g
f
r
a
m
e
w
o
r
k
f
o
r
t
e
x
t
c
l
a
ssi
f
i
c
a
t
i
o
n
,
”
J
o
u
r
n
a
l
o
f
K
i
n
g
S
a
u
d
U
n
i
v
e
rsi
t
y
-
C
o
m
p
u
t
e
r
a
n
d
I
n
f
o
rm
a
t
i
o
n
S
c
i
e
n
c
e
s
,
v
o
l
.
3
4
,
n
o
.
1
0
,
p
p
.
8
8
2
5
–
8
8
3
7
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
k
s
u
c
i
.
2
0
2
1
.
1
1
.
0
0
1
.
[
4
]
S
.
H
a
b
i
b
,
M
.
A
l
san
e
a
,
M
.
A
l
o
r
a
i
n
i
,
H
.
S
.
A
l
-
R
a
w
a
sh
d
e
h
,
M
.
I
sl
a
m,
a
n
d
S
.
K
h
a
n
,
“
A
n
Ef
f
i
c
i
e
n
t
a
n
d
Ef
f
e
c
t
i
v
e
D
e
e
p
L
e
a
r
n
i
n
g
-
B
a
se
d
M
o
d
e
l
f
o
r
R
e
a
l
-
T
i
me
F
a
c
e
M
a
sk
D
e
t
e
c
t
i
o
n
,
”
S
e
n
so
rs
,
v
o
l
.
2
2
,
n
o
.
7
,
p
p
.
1
–
1
3
,
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
s
2
2
0
7
2
6
0
2
.
[
5
]
F
.
G
h
o
r
b
a
n
p
o
u
r
,
M
.
R
a
m
e
z
a
n
i
,
M
.
A
.
F
a
z
l
i
,
a
n
d
H
.
R
.
R
a
b
i
e
e
,
“
F
N
R
:
a
s
i
m
i
l
a
r
i
t
y
a
n
d
t
r
a
n
s
f
o
r
me
r
-
b
a
s
e
d
a
p
p
r
o
a
c
h
t
o
d
e
t
e
c
t
m
u
l
t
i
-
m
o
d
a
l
f
a
k
e
n
e
w
s
i
n
s
o
c
i
a
l
m
e
d
i
a
,
”
S
o
c
i
a
l
N
e
t
w
o
r
k
A
n
a
l
y
s
i
s
a
n
d
M
i
n
i
n
g
,
v
o
l
.
1
3
,
n
o
.
1
,
p
.
5
6
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
3
2
7
8
-
023
-
0
1
0
6
5
-
0.
[
6
]
M
.
I
.
El
i
a
s,
Y
.
M
a
h
mu
d
,
S
.
M
u
t
a
l
i
b
,
S
.
N
.
K
.
K
a
maru
d
i
n
,
R
.
M
a
sk
a
t
,
a
n
d
S
.
A
.
R
a
h
ma
n
,
“
F
a
k
e
N
e
w
s
P
r
e
d
i
c
t
i
o
n
U
si
n
g
H
y
b
r
i
d
M
o
d
e
l
-
S
y
st
e
mat
i
c
L
i
t
e
r
a
t
u
r
e
R
e
v
i
e
w
,
”
i
n
2
0
2
3
4
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
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
D
a
t
a
S
c
i
e
n
c
e
s
(
Ai
D
A
S
)
,
2
0
2
3
,
p
p
.
2
8
1
–
2
8
6
.
d
o
i
:
1
0
.
1
1
0
9
/
A
i
D
A
S
6
0
5
0
1
.
2
0
2
3
.
1
0
2
8
4
6
2
8
.
[
7
]
S
.
E.
S
o
r
o
u
r
a
n
d
H
.
E
.
A
b
d
e
l
k
a
d
e
r
,
“
A
f
n
d
:
A
r
a
b
i
c
F
a
k
e
N
e
w
s
D
e
t
e
c
t
i
o
n
W
i
t
h
a
n
E
n
se
mb
l
e
D
e
e
p
C
n
n
-
L
st
m
M
o
d
e
l
,
”
J
o
u
r
n
a
l
o
f
T
h
e
o
re
t
i
c
a
l
a
n
d
Ap
p
l
i
e
d
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
1
0
0
,
n
o
.
1
4
,
p
p
.
5
0
7
2
–
5
0
8
6
,
2
0
2
2
.
[
8
]
B
.
S
r
e
e
d
e
v
i
,
L
.
P
.
N
a
r
e
n
d
r
u
n
i
,
B
.
C
h
i
t
r
a
d
e
v
i
,
M
.
S
a
n
t
h
a
n
a
l
a
k
s
h
m
i
,
a
n
d
G
.
S
u
ma
t
h
i
,
“
A
N
o
v
e
l
C
h
a
r
a
c
t
e
r
i
z
a
t
i
o
n
o
f
t
h
e
F
a
k
e
N
e
w
s
i
n
T
w
i
t
t
e
r
N
e
t
w
o
r
k
s,”
i
n
2
0
2
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
I
n
t
e
l
l
i
g
e
n
t
a
n
d
I
n
n
o
v
a
t
i
v
e
T
e
c
h
n
o
l
o
g
i
e
s
i
n
C
o
m
p
u
t
i
n
g
,
E
l
e
c
t
ri
c
a
l
a
n
d
El
e
c
t
r
o
n
i
c
s
(
I
I
T
C
EE)
,
2
0
2
3
,
p
p
.
8
2
5
–
8
2
8
.
d
o
i
:
1
0
.
1
1
0
9
/
I
I
TC
EE5
7
2
3
6
.
2
0
2
3
.
1
0
0
9
0
8
6
9
.
[
9
]
J.
A
.
N
a
si
r
,
O
.
S
.
K
h
a
n
,
a
n
d
I
.
V
a
r
l
a
mi
s,
“
F
a
k
e
n
e
w
s d
e
t
e
c
t
i
o
n
:
A
h
y
b
r
i
d
C
N
N
-
R
N
N
b
a
se
d
d
e
e
p
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
I
n
f
o
rm
a
t
i
o
n
Ma
n
a
g
e
m
e
n
t
D
a
t
a
I
n
si
g
h
t
s
,
v
o
l
.
1
,
n
o
.
1
,
p
p
.
1
–
1
3
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
j
i
me
i
.
2
0
2
0
.
1
0
0
0
0
7
.
[
1
0
]
C
.
A
.
C
.
S
á
e
n
z
,
M
.
D
i
a
s,
a
n
d
K
.
B
e
c
k
e
r
,
“
C
o
mb
i
n
i
n
g
c
o
mp
a
c
t
n
e
w
s
r
e
p
r
e
se
n
t
a
t
i
o
n
s
g
e
n
e
r
a
t
e
d
u
si
n
g
D
i
st
i
l
B
ER
T
a
n
d
t
o
p
o
l
o
g
i
c
a
l
f
e
a
t
u
r
e
s
t
o
c
l
a
ss
i
f
y
f
a
k
e
n
e
w
s,”
i
n
S
y
m
p
o
s
i
u
m
o
n
K
n
o
w
l
e
d
g
e
D
i
s
c
o
v
e
r
y
,
M
i
n
i
n
g
a
n
d
L
e
a
rn
i
n
g
(
K
D
Mi
L
e
)
,
2
0
2
0
,
p
p
.
2
0
9
–
2
1
6
.
d
o
i
:
1
0
.
5
7
5
3
/
k
d
m
i
l
e
.
2
0
2
0
.
1
1
9
7
8
.
[
1
1
]
T
.
C
h
a
u
h
a
n
a
n
d
H
.
P
a
l
i
v
e
l
a
,
“
O
p
t
i
m
i
z
a
t
i
o
n
a
n
d
i
m
p
r
o
v
e
me
n
t
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
e
e
p
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
e
s
f
o
r
so
c
i
e
t
a
l
b
e
n
e
f
i
t
,
”
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
Ma
n
a
g
e
m
e
n
t
D
a
t
a
I
n
si
g
h
t
s
,
v
o
l
.
1
,
n
o
.
2
,
p
p
.
1
–
1
1
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
j
i
me
i
.
2
0
2
1
.
1
0
0
0
5
1
.
[
1
2
]
Á
.
I
.
R
o
d
r
í
g
u
e
z
a
n
d
L
.
L
.
I
g
l
e
s
i
a
s,
“
F
a
k
e
n
e
w
s
d
e
t
e
c
t
i
o
n
u
si
n
g
d
e
e
p
l
e
a
r
n
i
n
g
,
”
a
rXi
v
e
-
p
r
i
n
t
s
,
S
e
p
.
2
0
1
9
,
d
o
i
:
1
0
.
4
8
5
5
0
/
a
r
X
i
v
.
1
9
1
0
.
0
3
4
9
6
.
[
1
3
]
I
.
K
.
S
a
st
r
a
w
a
n
,
I
.
P
.
A
.
B
a
y
u
p
a
t
i
,
a
n
d
D
.
M
.
S
.
A
r
sa,
“
D
e
t
e
c
t
i
o
n
o
f
f
a
k
e
n
e
w
s
u
si
n
g
d
e
e
p
l
e
a
r
n
i
n
g
C
N
N
–
R
N
N
b
a
se
d
me
t
h
o
d
s
,
”
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
23
,
No
.
2
,
A
p
r
il
20
25
:
3
2
9
-
339
338
I
C
T
Ex
p
ress
,
v
o
l
.
8
,
n
o
.
3
,
p
p
.
3
9
6
–
4
0
8
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
c
t
e
.
2
0
2
1
.
1
0
.
0
0
3
.
[
1
4
]
S
.
K
.
H
a
me
d
,
M
.
J.
A
b
A
z
i
z
,
a
n
d
M
.
R
.
Y
a
a
k
u
b
,
“
F
a
k
e
N
e
w
s
D
e
t
e
c
t
i
o
n
M
o
d
e
l
o
n
S
o
c
i
a
l
M
e
d
i
a
b
y
L
e
v
e
r
a
g
i
n
g
S
e
n
t
i
me
n
t
A
n
a
l
y
si
s
o
f
N
e
w
s
C
o
n
t
e
n
t
a
n
d
Emo
t
i
o
n
A
n
a
l
y
si
s
o
f
U
se
r
s’
C
o
mm
e
n
t
s,
”
S
e
n
s
o
rs
,
v
o
l
.
2
3
,
n
o
.
4
,
p
p
.
1
–
2
6
,
F
e
b
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
s
2
3
0
4
1
7
4
8
.
[
1
5
]
N
.
K
a
u
sar,
A
.
A
l
i
K
h
a
n
,
a
n
d
M
.
S
a
t
t
a
r
,
“
T
o
w
a
r
d
s
b
e
t
t
e
r
r
e
p
r
e
se
n
t
a
t
i
o
n
l
e
a
r
n
i
n
g
u
si
n
g
h
y
b
r
i
d
d
e
e
p
l
e
a
r
n
i
n
g
mo
d
e
l
f
o
r
f
a
k
e
n
e
w
s
d
e
t
e
c
t
i
o
n
,
”
S
o
c
i
a
l
N
e
t
w
o
rk
A
n
a
l
y
s
i
s
a
n
d
M
i
n
i
n
g
,
v
o
l
.
1
2
,
n
o
.
1
,
p
.
1
6
5
,
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
9
8
6
-
6.
[
1
6
]
P
.
K
.
V
e
r
m
a
,
P
.
A
g
r
a
w
a
l
,
V
.
M
a
d
a
a
n
,
a
n
d
R
.
P
r
o
d
a
n
,
“
M
C
r
e
d
:
mu
l
t
i
-
mo
d
a
l
me
ssag
e
c
r
e
d
i
b
i
l
i
t
y
f
o
r
f
a
k
e
n
e
w
s
d
e
t
e
c
t
i
o
n
u
s
i
n
g
B
E
R
T
a
n
d
C
N
N
,
”
J
o
u
r
n
a
l
o
f
Am
b
i
e
n
t
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
H
u
m
a
n
i
z
e
d
C
o
m
p
u
t
i
n
g
,
v
o
l
.
1
4
,
n
o
.
8
,
p
p
.
1
0
6
1
7
–
1
0
6
2
9
,
Ju
l
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
2
6
5
2
-
0
2
2
-
0
4
3
3
8
-
2.
[
1
7
]
M
.
I
.
N
a
d
e
e
m
e
t
a
l
.
,
“
H
y
p
r
o
B
e
r
t
:
A
F
a
k
e
N
e
w
s
D
e
t
e
c
t
i
o
n
M
o
d
e
l
B
a
se
d
o
n
D
e
e
p
H
y
p
e
r
c
o
n
t
e
x
t
,
”
S
y
m
m
e
t
ry
,
v
o
l
.
1
5
,
n
o
.
2
,
p
p
.
1
–
2
1
,
F
e
b
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
sy
m1
5
0
2
0
2
9
6
.
[
1
8
]
D
.
M
o
h
e
r
e
t
a
l
.
,
“
P
r
e
f
e
r
r
e
d
r
e
p
o
r
t
i
n
g
i
t
e
ms
f
o
r
s
y
st
e
mat
i
c
r
e
v
i
e
w
s
a
n
d
me
t
a
-
a
n
a
l
y
s
e
s:
T
h
e
P
R
I
S
M
A
st
a
t
e
me
n
t
,
”
PLo
S
Me
d
i
c
i
n
e
,
v
o
l
.
6
,
n
o
.
7
,
2
0
0
9
,
d
o
i
:
1
0
.
1
3
7
1
/
j
o
u
r
n
a
l
.
p
me
d
.
1
0
0
0
0
9
7
.
[
1
9
]
A
.
J.
K
e
y
a
,
H
.
H
.
S
h
a
j
e
e
b
,
M
.
S
.
R
a
h
man
,
a
n
d
M
.
F
.
M
r
i
d
h
a
,
“
F
a
k
e
S
t
a
c
k
:
H
i
e
r
a
r
c
h
i
c
a
l
T
r
i
-
B
E
R
T
-
C
N
N
-
L
S
T
M
st
a
c
k
e
d
mo
d
e
l
f
o
r
e
f
f
e
c
t
i
v
e
f
a
k
e
n
e
w
s d
e
t
e
c
t
i
o
n
,
”
PL
o
S
O
n
e
,
v
o
l
.
1
8
,
n
o
.
1
2
,
p
p
.
1
–
3
1
,
2
0
2
3
,
d
o
i
:
1
0
.
1
3
7
1
/
j
o
u
r
n
a
l
.
p
o
n
e
.
0
2
9
4
7
0
1
.
[
2
0
]
A
.
R
.
M
e
r
r
y
t
o
n
a
n
d
M
.
G
.
A
u
g
a
st
a
,
“
A
n
A
t
t
r
i
b
u
t
e
-
w
i
se
A
t
t
e
n
t
i
o
n
mo
d
e
l
w
i
t
h
B
i
L
S
T
M
f
o
r
a
n
e
f
f
i
c
i
e
n
t
F
a
k
e
N
e
w
s
D
e
t
e
c
t
i
o
n
,
”
Mu
l
t
i
m
e
d
i
a
T
o
o
l
s
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
8
3
,
n
o
.
1
3
,
p
p
.
3
8
1
0
9
–
3
8
1
2
6
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
0
4
2
-
0
2
3
-
1
6
8
2
4
-
6.
[
2
1
]
M
.
A
.
H
a
mz
a
e
t
a
l
.
,
“
O
p
t
i
mal
Q
u
a
d
C
h
a
n
n
e
l
L
o
n
g
S
h
o
r
t
-
Te
r
m
M
e
mo
r
y
B
a
se
d
F
a
k
e
N
e
w
s
C
l
a
ssi
f
i
c
a
t
i
o
n
o
n
En
g
l
i
sh
C
o
r
p
u
s,
”
C
o
m
p
u
t
e
r
S
y
st
e
m
s
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
4
6
,
n
o
.
3
,
p
p
.
3
3
0
3
–
3
3
1
9
,
2
0
2
3
,
d
o
i
:
1
0
.
3
2
6
0
4
/
c
sse
.
2
0
2
3
.
0
3
4
8
2
3
.
[
2
2
]
P
.
N
.
A
h
mad
,
Y
.
L
i
u
,
G
.
A
l
i
,
M
.
A
.
W
a
n
i
,
a
n
d
M
.
El
A
f
f
e
n
d
i
,
“
R
o
b
u
st
B
e
n
c
h
mar
k
f
o
r
P
r
o
p
a
g
a
n
d
i
s
t
T
e
x
t
D
e
t
e
c
t
i
o
n
a
n
d
M
i
n
i
n
g
H
i
g
h
-
Q
u
a
l
i
t
y
D
a
t
a
,
”
M
a
t
h
e
m
a
t
i
c
s
,
v
o
l
.
1
1
,
n
o
.
1
2
,
p
p
.
1
–
2
3
,
J
u
n
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
m
a
t
h
1
1
1
2
2
6
6
8
.
[
2
3
]
S
.
R
a
o
,
A
.
K
.
V
e
r
ma,
a
n
d
T
.
B
h
a
t
i
a
,
“
H
y
b
r
i
d
e
n
se
mb
l
e
f
r
a
mew
o
r
k
w
i
t
h
s
e
l
f
-
a
t
t
e
n
t
i
o
n
me
c
h
a
n
i
s
m
f
o
r
so
c
i
a
l
sp
a
m
d
e
t
e
c
t
i
o
n
o
n
i
mb
a
l
a
n
c
e
d
d
a
t
a
,
”
E
x
p
e
rt
S
y
st
e
m
s w
i
t
h
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
2
1
7
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
sw
a
.
2
0
2
3
.
1
1
9
5
9
4
.
[
2
4
]
B
.
J
a
msh
i
d
i
,
S
.
H
a
k
a
k
,
a
n
d
R
.
L
u
,
“
A
S
e
l
f
-
A
t
t
e
n
t
i
o
n
M
e
c
h
a
n
i
sm
-
B
a
se
d
M
o
d
e
l
f
o
r
Ea
r
l
y
D
e
t
e
c
t
i
o
n
o
f
F
a
k
e
N
e
w
s,”
I
EEE
T
ra
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
st
e
m
s
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
T
C
S
S
.
2
0
2
3
.
3
3
2
2
1
6
0
.
[
2
5
]
V
.
D
u
a
,
A
.
R
a
j
p
a
l
,
S
.
R
a
j
p
a
l
,
M
.
A
g
a
r
w
a
l
,
a
n
d
N
.
K
u
mar,
“
I
-
F
L
A
S
H
:
I
n
t
e
r
p
r
e
t
a
b
l
e
F
a
k
e
N
e
w
s D
e
t
e
c
t
o
r
U
si
n
g
L
I
M
E
a
n
d
S
H
A
P
,
”
Wi
re
l
e
ss
Pe
r
so
n
a
l
C
o
m
m
u
n
i
c
a
t
i
o
n
s
,
v
o
l
.
1
3
1
,
n
o
.
4
,
p
p
.
2
8
4
1
–
2
8
7
4
,
A
u
g
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
2
7
7
-
0
2
3
-
1
0
5
8
2
-
2.
[
2
6
]
S
.
K
u
mar,
D
.
K
u
mar,
a
n
d
S
.
R
.
S
i
n
g
h
,
“
G
a
t
e
d
R
e
c
u
r
si
v
e
a
n
d
S
e
q
u
e
n
t
i
a
l
D
e
e
p
H
i
e
r
a
r
c
h
i
c
a
l
En
c
o
d
i
n
g
f
o
r
D
e
t
e
c
t
i
n
g
I
n
c
o
n
g
r
u
e
n
t
N
e
w
s
A
r
t
i
c
l
e
s,”
I
EEE
T
ra
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
st
e
m
s
,
v
o
l
.
1
1
,
n
o
.
1
,
p
p
.
1
0
2
3
–
1
0
3
4
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
T
C
S
S
.
2
0
2
3
.
3
2
4
7
4
4
5
.
[
2
7
]
X
.
H
a
n
,
M
.
Z
h
a
o
,
Y
.
Z
h
a
n
g
,
a
n
d
T
.
Z
h
a
o
,
“
Jo
i
n
t
l
y
mu
l
t
i
-
so
u
r
c
e
i
n
f
o
r
mat
i
o
n
a
n
d
l
o
c
a
l
-
g
l
o
b
a
l
r
e
l
a
t
i
o
n
s
o
f
h
e
t
e
r
o
g
e
n
e
o
u
s
n
e
t
w
o
r
k
f
o
r
r
u
mo
r
d
e
t
e
c
t
i
o
n
,
”
Fr
o
n
t
i
e
rs
i
n
P
h
y
si
c
s
,
v
o
l
.
1
0
,
p
p
.
1
–
1
2
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
8
9
/
f
p
h
y
.
2
0
2
2
.
1
0
5
6
2
0
7
.
[
2
8
]
R
.
M
o
h
a
w
e
sh
,
S
.
M
a
q
so
o
d
,
a
n
d
Q
.
A
l
t
h
e
b
y
a
n
,
“
M
u
l
t
i
l
i
n
g
u
a
l
d
e
e
p
l
e
a
r
n
i
n
g
f
r
a
me
w
o
r
k
f
o
r
f
a
k
e
n
e
w
s
d
e
t
e
c
t
i
o
n
u
s
i
n
g
c
a
p
su
l
e
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
J
o
u
r
n
a
l
o
f
I
n
t
e
l
l
i
g
e
n
t
I
n
f
o
r
m
a
t
i
o
n
S
y
s
t
e
m
s
,
v
o
l
.
6
0
,
n
o
.
3
,
p
p
.
6
5
5
–
6
7
1
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
0
8
4
4
-
0
2
3
-
0
0
7
8
8
-
y
.
[
2
9
]
S
.
K
.
H
a
me
d
,
M
.
J.
A
b
A
z
i
z
,
a
n
d
M
.
R
.
Y
a
a
k
u
b
,
“
D
i
si
n
f
o
r
mat
i
o
n
D
e
t
e
c
t
i
o
n
A
b
o
u
t
I
sl
a
mi
c
I
ssu
e
s
o
n
S
o
c
i
a
l
M
e
d
i
a
U
s
i
n
g
D
e
e
p
L
e
a
r
n
i
n
g
T
e
c
h
n
i
q
u
e
s,
”
M
a
l
a
y
s
i
a
n
J
o
u
rn
a
l
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
3
6
,
n
o
.
3
,
p
p
.
2
4
2
–
2
7
0
,
2
0
2
3
,
d
o
i
:
1
0
.
2
2
4
5
2
/
mj
c
s.v
o
l
3
6
n
o
3
.
3
.
[
3
0
]
Z
.
G
u
o
,
Q
.
Z
h
a
n
g
,
F
.
D
i
n
g
,
X
.
Z
h
u
,
a
n
d
K
.
Y
u
,
“
A
N
o
v
e
l
F
a
k
e
N
e
w
s
D
e
t
e
c
t
i
o
n
M
o
d
e
l
f
o
r
C
o
n
t
e
x
t
o
f
M
i
x
e
d
L
a
n
g
u
a
g
e
s
T
h
r
o
u
g
h
M
u
l
t
i
sc
a
l
e
Tr
a
n
sf
o
r
me
r
,
”
I
EEE
T
ra
n
sa
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
.
1
1
,
n
o
.
4
,
p
p
.
5
0
7
9
–
5
0
8
9
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
T
C
S
S
.
2
0
2
3
.
3
2
9
8
4
8
0
.
[
3
1
]
J.
W
a
n
g
,
J.
Z
h
e
n
g
,
S
.
Y
a
o
,
R
.
W
a
n
g
,
a
n
d
H
.
D
u
,
“
TL
F
N
D
:
A
M
u
l
t
i
mo
d
a
l
F
u
si
o
n
M
o
d
e
l
B
a
se
d
o
n
T
h
r
e
e
-
L
e
v
e
l
F
e
a
t
u
r
e
M
a
t
c
h
i
n
g
D
i
st
a
n
c
e
f
o
r
F
a
k
e
N
e
w
s D
e
t
e
c
t
i
o
n
,
”
E
n
t
r
o
p
y
,
v
o
l
.
2
5
,
n
o
.
1
1
,
p
p
.
1
–
1
7
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
e
2
5
1
1
1
5
3
3
.
[
3
2
]
P
.
M
e
e
l
a
n
d
D
.
K
.
V
i
s
h
w
a
k
a
r
m
a
,
“
M
u
l
t
i
-
mo
d
a
l
f
u
s
i
o
n
u
si
n
g
F
i
n
e
-
t
u
n
e
d
S
e
l
f
-
a
t
t
e
n
t
i
o
n
a
n
d
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
f
o
r
v
e
r
a
c
i
t
y
a
n
a
l
y
si
s
o
f
w
e
b
i
n
f
o
r
ma
t
i
o
n
,
”
Ex
p
e
r
t
S
y
s
t
e
m
s
w
i
t
h
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
2
2
9
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
sw
a
.
2
0
2
3
.
1
2
0
5
3
7
.
[
3
3
]
M
.
I
.
N
a
d
e
e
m
e
t
a
l
.
,
“
S
S
M
:
S
t
y
l
o
me
t
r
i
c
a
n
d
se
ma
n
t
i
c
s
i
m
i
l
a
r
i
t
y
o
r
i
e
n
t
e
d
mu
l
t
i
mo
d
a
l
f
a
k
e
n
e
w
s
d
e
t
e
c
t
i
o
n
,
”
J
o
u
rn
a
l
o
f
K
i
n
g
S
a
u
d
U
n
i
v
e
rsi
t
y
-
C
o
m
p
u
t
e
r
a
n
d
I
n
f
o
rm
a
t
i
o
n
S
c
i
e
n
c
e
s
,
v
o
l
.
3
5
,
n
o
.
5
,
p
p
.
1
–
1
7
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
k
s
u
c
i
.
2
0
2
3
.
1
0
1
5
5
9
.
[
3
4
]
V
.
K
i
sh
o
r
e
a
n
d
M
.
K
u
mar,
“
E
n
h
a
n
c
e
d
M
u
l
t
i
mo
d
a
l
F
a
k
e
N
e
w
s
D
e
t
e
c
t
i
o
n
w
i
t
h
O
p
t
i
mal
F
e
a
t
u
r
e
F
u
si
o
n
a
n
d
M
o
d
i
f
i
e
d
B
i
-
L
S
T
M
A
r
c
h
i
t
e
c
t
u
r
e
,
”
C
y
b
e
r
n
e
t
i
c
s
a
n
d
S
y
s
t
e
m
s
,
p
p
.
1
–
3
1
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
8
0
/
0
1
9
6
9
7
2
2
.
2
0
2
3
.
2
1
7
5
1
5
5
.
[
3
5
]
M
.
I
.
N
a
d
e
e
m
e
t
a
l
.
,
“
EF
N
D
:
A
S
e
ma
n
t
i
c
,
V
i
su
a
l
,
a
n
d
S
o
c
i
a
l
l
y
A
u
g
me
n
t
e
d
D
e
e
p
F
r
a
mew
o
r
k
f
o
r
Ex
t
r
e
m
e
F
a
k
e
N
e
w
s
D
e
t
e
c
t
i
o
n
,
”
S
u
s
t
a
i
n
a
b
i
l
i
t
y
(
S
w
i
t
zer
l
a
n
d
)
,
v
o
l
.
1
5
,
n
o
.
1
,
p
p
.
1
–
2
4
,
Ja
n
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
s
u
1
5
0
1
0
1
3
3
.
[
3
6
]
A
.
Y
a
d
a
v
,
S
.
G
a
b
a
,
H
.
K
h
a
n
,
I
.
B
u
d
h
i
r
a
j
a
,
A
.
S
i
n
g
h
,
a
n
d
K
.
K
.
S
i
n
g
h
,
“
ET
M
A
:
Ef
f
i
c
i
e
n
t
T
r
a
n
sf
o
r
me
r
-
B
a
se
d
M
u
l
t
i
l
e
v
e
l
A
t
t
e
n
t
i
o
n
F
r
a
mew
o
r
k
f
o
r
M
u
l
t
i
mo
d
a
l
F
a
k
e
N
e
w
s De
t
e
c
t
i
o
n
,
”
I
E
EE
T
ra
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
.
1
1
,
n
o
.
4
,
p
p
.
5
0
1
5
–
5
0
2
7
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
T
C
S
S
.
2
0
2
3
.
3
2
5
5
2
4
2
.
[
3
7
]
A
.
A
l
O
b
a
i
d
,
H
.
K
h
o
t
a
n
l
o
u
,
M
.
M
a
n
so
o
r
i
z
a
d
e
h
,
a
n
d
D
.
Z
a
b
i
h
z
a
d
e
h
,
“
R
o
b
u
st
S
e
mi
-
S
u
p
e
r
v
i
se
d
F
a
k
e
N
e
w
s
R
e
c
o
g
n
i
t
i
o
n
b
y
Ef
f
e
c
t
i
v
e
A
u
g
me
n
t
a
t
i
o
n
s
a
n
d
E
n
se
mb
l
e
o
f
D
i
v
e
r
se
D
e
e
p
L
e
a
r
n
e
r
s,”
I
EEE
Ac
c
e
ss
,
v
o
l
.
1
1
,
p
p
.
5
4
5
2
6
–
5
4
5
4
3
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
3
.
3
2
7
8
3
2
3
.
[
3
8
]
D
.
K
.
S
h
a
r
ma,
B
.
S
i
n
g
h
,
S
.
A
g
a
r
w
a
l
,
H
.
K
i
m,
a
n
d
R
.
S
h
a
r
m
a
,
“
F
a
k
e
d
B
i
t
s
-
D
e
t
e
c
t
i
n
g
F
a
k
e
I
n
f
o
r
mat
i
o
n
o
n
S
o
c
i
a
l
P
l
a
t
f
o
r
ms
u
si
n
g
M
u
l
t
i
-
M
o
d
a
l
F
e
a
t
u
r
e
s,”
K
S
I
I
T
ra
n
s
a
c
t
i
o
n
s
o
n
I
n
t
e
r
n
e
t
a
n
d
I
n
f
o
rm
a
t
i
o
n
S
y
s
t
e
m
s.
,
v
o
l
.
1
7
,
n
o
.
1
,
p
p
.
5
1
–
7
3
,
Jan
.
2
0
2
3
,
d
o
i
:
1
0
.
3
8
3
7
/
t
i
i
s
.
2
0
2
3
.
0
1
.
0
0
4
.
[
3
9
]
B
.
G
o
y
a
l
e
t
a
l
.
,
“
D
e
t
e
c
t
i
o
n
o
f
F
a
k
e
A
c
c
o
u
n
t
s
o
n
S
o
c
i
a
l
M
e
d
i
a
U
s
i
n
g
M
u
l
t
i
mo
d
a
l
D
a
t
a
W
i
t
h
D
e
e
p
L
e
a
r
n
i
n
g
,
”
I
E
EE
T
ra
n
sa
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
st
e
m
s.
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
T
C
S
S
.
2
0
2
3
.
3
2
9
6
8
3
7
.
[
4
0
]
O
.
A
.
H
a
n
sh
a
l
,
O
.
N
.
U
c
a
n
,
a
n
d
Y
.
K
.
S
a
n
j
a
l
a
w
e
,
“
H
y
b
r
i
d
d
e
e
p
l
e
a
r
n
i
n
g
mo
d
e
l
f
o
r
a
u
t
o
mat
i
c
f
a
k
e
n
e
w
s
d
e
t
e
c
t
i
o
n
,
”
A
p
p
l
i
e
d
N
a
n
o
sci
e
n
c
e
,
v
o
l
.
1
3
,
n
o
.
4
,
p
p
.
2
9
5
7
–
2
9
6
7
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
3
2
0
4
-
0
2
1
-
0
2
3
3
0
-
4.
[
4
1
]
X
.
G
a
o
e
t
a
l
.
,
“
A
n
I
n
t
e
r
p
r
e
t
a
b
l
e
F
a
k
e
N
e
w
s
D
e
t
e
c
t
i
o
n
M
e
t
h
o
d
B
a
se
d
o
n
C
o
mm
o
n
se
n
se
K
n
o
w
l
e
d
g
e
G
r
a
p
h
,
”
A
p
p
l
i
e
d
S
c
i
e
n
c
e
s.
,
v
o
l
.
1
3
,
n
o
.
1
1
,
p
p
.
1
–
1
9
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
3
1
1
6
6
8
0
.
[
4
2
]
G
.
G
.
D
e
v
a
r
a
j
a
n
,
S
.
M
.
N
a
g
a
r
a
j
a
n
,
S
.
I
.
A
man
u
l
l
a
h
,
S
.
A
.
S
.
A
.
M
a
r
y
,
a
n
d
A
.
K
.
B
a
s
h
i
r
,
“
A
I
-
A
ssi
st
e
d
D
e
e
p
N
L
P
-
Bas
e
d
A
p
p
r
o
a
c
h
f
o
r
P
r
e
d
i
c
t
i
o
n
o
f
F
a
k
e
N
e
w
s
f
r
o
m
S
o
c
i
a
l
M
e
d
i
a
U
se
r
s,”
I
EEE
T
r
a
n
sa
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
.
1
1
,
n
o
.
4
,
p
p
.
4
9
7
5
–
4
9
8
5
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
T
C
S
S
.
2
0
2
3
.
3
2
5
9
4
8
0
.
[
4
3
]
A
.
A
.
A
l
i
,
S
.
L
a
t
i
f
,
S
.
A
.
G
h
a
u
r
i
,
O
.
Y
.
S
o
n
g
,
A
.
A
.
A
b
b
a
si
,
a
n
d
A
.
J.
M
a
l
i
k
,
“
L
i
n
g
u
i
s
t
i
c
F
e
a
t
u
r
e
s
a
n
d
B
i
-
L
S
TM
f
o
r
I
d
e
n
t
i
f
i
c
a
t
i
o
n
o
f
F
a
k
e
N
e
w
s,”
El
e
c
t
r
o
n
i
c
s (
S
w
i
t
z
e
rl
a
n
d
)
,
v
o
l
.
1
2
,
n
o
.
1
3
,
p
p
.
1
–
1
6
,
J
u
l
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
e
l
e
c
t
r
o
n
i
c
s1
2
1
3
2
9
4
2
.
[
4
4
]
S
.
S
u
r
y
a
w
a
n
sh
i
,
A
.
G
o
s
w
a
mi
,
a
n
d
P
.
P
a
t
i
l
,
“
F
a
k
e
I
D
C
A
:
F
a
k
e
n
e
w
s
d
e
t
e
c
t
i
o
n
w
i
t
h
i
n
c
r
e
me
n
t
a
l
d
e
e
p
l
e
a
r
n
i
n
g
b
a
se
d
c
o
n
c
e
p
t
d
r
i
f
t
a
d
a
p
t
i
o
n
,
”
M
u
l
t
i
m
e
d
i
a
T
o
o
l
s
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
8
3
,
n
o
.
1
0
,
p
p
.
2
8
5
7
9
–
2
8
5
9
4
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
0
4
2
-
0
2
3
-
1
6
5
8
8
-
z.
[
4
5
]
M
.
T
a
h
a
,
H
.
H
.
Z
a
y
e
d
,
M
.
A
z
e
r
,
a
n
d
M
.
G
a
d
a
l
l
a
h
,
“
A
u
t
o
mat
e
d
C
O
V
I
D
-
1
9
m
i
si
n
f
o
r
ma
t
i
o
n
c
h
e
c
k
i
n
g
sy
st
e
m
u
s
i
n
g
e
n
c
o
d
e
r
r
e
p
r
e
se
n
t
a
t
i
o
n
w
i
t
h
d
e
e
p
l
e
a
r
n
i
n
g
mo
d
e
l
s,”
I
AES
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
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
.
,
v
o
l
.
1
2
,
n
o
.
1
,
p
p
.
4
8
8
–
4
9
5
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
a
i
.
v
1
2
.
i
1
.
p
p
4
8
8
-
4
9
5
.
[
4
6
]
C
.
M
a
l
l
i
c
k
,
S
.
M
i
s
h
r
a
,
a
n
d
M
.
R
.
S
e
n
a
p
a
t
i
,
“
A
c
o
o
p
e
r
a
t
i
v
e
d
e
e
p
l
e
a
r
n
i
n
g
m
o
d
e
l
f
o
r
f
a
k
e
n
e
w
s
d
e
t
e
c
t
i
o
n
i
n
o
n
l
i
n
e
s
o
c
i
a
l
n
e
t
w
o
r
k
s
,
”
Evaluation Warning : The document was created with Spire.PDF for Python.