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.
3
9
,
No
.
2
,
A
u
g
u
s
t
2
0
2
5
,
p
p
.
1
092
~
1
0
9
9
I
SS
N:
2
5
0
2
-
4
7
5
2
,
DOI
: 1
0
.
1
1
5
9
1
/ijeecs.v
3
9
.i
2
.
pp
1
0
9
2
-
1
0
9
9
1092
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs.ia
esco
r
e.
co
m
Deepfake
det
ectio
n using
conv
o
luti
o
na
l neural net
wo
rks: a de
ep
lea
rning
appro
a
ch f
o
r digita
l s
ecur
ity
F
enina
Adlin
e
T
wi
nce
T
o
bin
g
1
,
Adhi
K
us
na
di
1
,
I
v
ra
ns
a
Z
uh
di P
a
ne
2
,
Ra
ng
g
a
Wina
nty
o
1
1
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
mat
i
c
s
,
F
a
c
u
l
t
y
o
f
En
g
i
n
e
e
r
i
n
g
a
n
d
I
n
f
o
r
mat
i
c
s
,
U
n
i
v
e
r
si
t
a
s
M
u
l
t
i
me
d
i
a
N
u
sa
n
t
a
r
a
,
Ta
n
g
e
r
a
n
g
,
I
n
d
o
n
e
s
i
a
2
R
e
s
e
a
r
c
h
C
e
n
t
r
e
f
o
r
A
v
i
a
t
i
o
n
Te
c
h
n
o
l
o
g
y
,
N
a
t
i
o
n
a
l
R
e
se
a
r
c
h
a
n
d
I
n
n
o
v
a
t
i
o
n
A
g
e
n
c
y
,
T
a
n
g
e
r
a
n
g
,
I
n
d
o
n
e
si
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
No
v
17
,
2
0
2
4
R
ev
is
ed
Mar
21
,
2
0
2
5
Acc
ep
ted
J
u
l
2
,
2
0
2
5
Th
e
d
e
v
e
lo
p
m
e
n
t
o
f
a
rti
ficia
l
in
telli
g
e
n
c
e
tec
h
n
o
l
o
g
y
,
e
s
p
e
c
ially
d
e
e
p
lea
rn
in
g
,
h
a
s
fa
c
il
it
a
ted
th
e
e
m
e
rg
e
n
c
e
o
f
in
c
re
a
sin
g
ly
so
p
h
isti
c
a
ted
d
e
e
p
fa
k
e
tec
h
n
o
l
o
g
y
.
De
e
p
fa
k
e
s
u
ti
li
z
e
g
e
n
e
ra
ti
v
e
a
d
v
e
rsa
rial
n
e
two
r
k
s
(G
AN
s)
to
m
a
n
ip
u
late
ima
g
e
s o
r
v
id
e
o
s,
m
a
k
i
n
g
it
a
p
p
e
a
r
a
s if
so
m
e
o
n
e
sa
id
o
r
d
id
th
i
n
g
s
th
a
t
n
e
v
e
r
a
c
tu
a
ll
y
h
a
p
p
e
n
e
d
.
As
a
re
su
lt
,
d
e
e
p
fa
k
e
d
e
tec
ti
o
n
h
a
s
b
e
c
o
m
e
a
c
rit
ica
l
c
h
a
ll
e
n
g
e
,
p
a
rti
c
u
larly
in
t
h
e
c
o
n
tex
t
o
f
th
e
sp
re
a
d
o
f
fa
lse
in
fo
rm
a
ti
o
n
a
n
d
d
i
g
it
a
l
c
rime
.
Th
e
p
u
rp
o
se
o
f
th
is
re
se
a
rc
h
is
to
c
re
a
te
a
m
e
th
o
d
f
o
r
d
e
tec
ti
n
g
d
e
e
p
fa
k
e
s
u
sin
g
a
c
o
n
v
o
lu
ti
o
n
a
l
n
e
u
ra
l
n
e
two
r
k
(CNN
)
a
p
p
ro
a
c
h
,
wh
ic
h
h
a
s
b
e
e
n
p
r
o
v
e
n
e
ffe
c
ti
v
e
i
n
v
isu
a
l
p
a
tt
e
rn
re
c
o
g
n
it
i
o
n
.
T
h
ro
u
g
h
trai
n
in
g
wi
th
a
d
a
tas
e
t
o
f
o
rig
in
a
l
fa
c
ial
i
m
a
g
e
s
a
n
d
d
e
e
p
fa
k
e
s,
th
e
CNN
m
o
d
e
l
a
c
h
iev
e
d
a
n
a
c
c
u
ra
c
y
o
f
8
1
.
3
%
in
d
e
tec
ti
n
g
d
e
e
p
fa
k
e
s.
Th
e
e
v
a
lu
a
ti
o
n
re
su
l
t
s
fo
r
m
e
tri
c
s
su
c
h
a
s
p
re
c
isio
n
,
r
e
c
a
ll
,
a
n
d
F1
-
sc
o
re
in
d
ica
ted
g
o
o
d
p
e
rfo
rm
a
n
c
e
o
v
e
ra
ll
,
a
lt
h
o
u
g
h
t
h
e
re
is
stil
l
ro
o
m
fo
r
imp
ro
v
e
m
e
n
t.
Th
is
st
u
d
y
is
e
x
p
e
c
ted
to
m
a
k
e
a
sig
n
if
ica
n
t
c
o
n
tri
b
u
ti
o
n
to
e
n
h
a
n
c
in
g
d
i
g
it
a
l
se
c
u
rit
y
,
e
sp
e
c
i
a
ll
y
in
d
e
tec
ti
n
g
v
isu
a
l
m
a
n
i
p
u
lati
o
n
s b
a
se
d
o
n
d
e
e
p
fa
k
e
s.
K
ey
w
o
r
d
s
:
Ar
tific
ial
in
tellig
en
ce
Au
th
en
ticatio
n
C
o
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
Dee
p
f
ak
e
Face
r
ec
o
g
n
itio
n
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
:
Fen
in
a
Ad
lin
e
T
win
ce
T
o
b
in
g
Dep
ar
tm
en
t o
f
I
n
f
o
r
m
atics,
Facu
lty
o
f
E
n
g
in
ee
r
i
n
g
an
d
I
n
f
o
r
m
atics,
Un
iv
er
s
itas
Mu
ltime
d
i
a
Nu
s
an
tar
a
T
an
g
er
an
g
,
I
n
d
o
n
esia
E
m
ail: f
en
in
a.
to
b
i
n
g
@
u
m
n
.
ac
.
id
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
d
ev
elo
p
m
en
t
o
f
ar
tific
ial
in
tellig
en
ce
(
AI
)
tech
n
o
lo
g
y
h
as
o
p
en
ed
u
p
m
an
y
o
p
p
o
r
t
u
n
ities
in
v
ar
io
u
s
f
ield
s
[
1
]
,
b
u
t
it
h
as
a
ls
o
b
r
o
u
g
h
t
n
ew
c
h
allen
g
es,
o
n
e
o
f
wh
ich
is
th
e
em
er
g
e
n
ce
o
f
d
ee
p
f
ak
es
[
2
]
,
[
3
]
.
Dee
p
f
a
k
e
tech
n
o
l
o
g
y
u
tili
ze
s
AI
,
p
ar
ticu
lar
ly
d
ee
p
lear
n
in
g
tech
n
iq
u
es,
to
m
a
n
ip
u
late
a
p
er
s
o
n
'
s
f
ac
e
in
a
v
id
eo
o
r
im
ag
e,
m
ak
in
g
it
ap
p
ea
r
as
if
th
e
in
d
i
v
id
u
al
is
d
o
in
g
o
r
s
ay
in
g
th
i
n
g
s
th
at
n
ev
e
r
ac
tu
ally
h
ap
p
en
ed
[
4
]
,
[
5
]
.
T
h
is
tech
n
o
lo
g
y
o
f
ten
em
p
lo
y
s
g
en
er
ativ
e
a
d
v
er
s
ar
ial
n
etwo
r
k
s
(
GANs)
[
6
]
to
m
o
d
if
y
o
r
ig
i
n
al
co
n
ten
t
o
r
g
e
n
er
ate
n
ew
co
n
ten
t
th
at
clo
s
ely
r
esem
b
les
r
ea
l
p
eo
p
le
[
7
]
.
T
h
e
p
o
ten
tial
f
o
r
m
is
u
s
e
o
f
d
ee
p
f
ak
es
is
v
er
y
h
ig
h
,
esp
ec
ially
in
t
h
e
co
n
tex
t
o
f
s
p
r
ea
d
i
n
g
f
als
e
in
f
o
r
m
atio
n
,
id
en
tity
m
an
i
p
u
latio
n
,
an
d
d
ig
ital
cr
im
es
s
u
ch
as
f
r
au
d
an
d
ex
to
r
tio
n
[
8
]
.
Fo
r
ex
a
m
p
le,
ca
s
es
o
f
f
r
au
d
u
s
in
g
d
ee
p
f
a
k
es
h
av
e
r
esu
lted
in
lo
s
s
e
s
am
o
u
n
tin
g
to
b
illi
o
n
s
o
f
r
u
p
ia
h
in
in
ter
n
atio
n
al
b
u
s
in
ess
tr
an
s
ac
tio
n
s
[
9
]
.
As
d
ee
p
f
ak
e
tec
h
n
o
lo
g
y
b
ec
o
m
es
m
o
r
e
s
o
p
h
is
ticated
,
d
etec
tin
g
f
ak
e
co
n
te
n
t
b
ec
o
m
es
in
cr
ea
s
in
g
ly
d
if
f
icu
lt
[
1
0
]
,
p
o
s
in
g
a
s
er
io
u
s
ch
allen
g
e
f
o
r
r
esear
ch
e
r
s
,
p
ar
ticu
lar
ly
in
d
ev
e
lo
p
in
g
tech
n
o
l
o
g
y
th
at
ca
n
d
etec
t
an
d
id
en
tify
f
ak
e
c
o
n
ten
t
au
t
o
m
atica
lly
an
d
q
u
ick
ly
.
On
e
o
f
th
e
m
o
s
t
ef
f
ec
tiv
e
ap
p
r
o
ac
h
es
f
o
r
d
etec
tin
g
d
ee
p
f
ak
es
is
th
e
u
s
e
o
f
co
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
s
(
C
NNs),
a
d
ee
p
lear
n
in
g
ar
c
h
itectu
r
e
r
ec
o
g
n
ized
f
o
r
its
ef
f
ec
tiv
en
ess
in
im
ag
e
p
r
o
ce
s
s
in
g
an
d
co
m
p
le
x
v
is
u
al
p
atter
n
r
ec
o
g
n
itio
n
[
1
1
]
.
Alth
o
u
g
h
v
ar
io
u
s
m
et
h
o
d
s
h
a
v
e
b
ee
n
d
ev
elo
p
ed
to
d
etec
t
d
ee
p
f
ak
es,
th
eir
ac
cu
r
ac
y
lev
els
ar
e
s
till
n
o
t
o
p
tim
al,
esp
ec
ially
w
h
en
d
ea
lin
g
with
h
ig
h
-
q
u
ality
d
ee
p
f
ak
e
v
i
d
eo
s
.
T
h
is
s
tu
d
y
aim
s
to
d
ev
elo
p
a
d
ee
p
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:
2502
-
4
7
5
2
Dee
p
fa
ke
d
etec
tio
n
u
s
in
g
co
n
vo
lu
tio
n
a
l
n
eu
r
a
l n
etw
o
r
ks:
a
d
ee
p
lea
r
n
in
g
…
(
F
en
i
n
a
A
d
li
n
e
Tw
in
ce
To
b
in
g
)
1093
lear
n
in
g
-
b
ased
d
ee
p
f
ak
e
d
etec
tio
n
m
eth
o
d
u
s
in
g
C
NNs
[
1
2
]
,
[
1
3
]
.
W
ith
th
is
ap
p
r
o
ac
h
,
th
e
d
etec
tio
n
s
y
s
tem
is
ex
p
ec
ted
to
an
aly
ze
f
ac
ial
f
e
atu
r
es
with
h
ig
h
ac
cu
r
ac
y
,
d
is
tin
g
u
is
h
in
g
r
ea
l
f
ac
es
f
r
o
m
t
h
o
s
e
g
en
e
r
ated
b
y
d
ee
p
f
ak
e
tech
n
o
l
o
g
y
.
I
n
a
d
d
iti
o
n
,
th
is
s
tu
d
y
also
aim
s
to
ev
a
lu
ate
th
e
ef
f
ec
tiv
e
n
ess
o
f
th
e
C
NN
m
eth
o
d
u
n
d
er
v
ar
io
u
s
im
ag
e
a
n
d
v
id
eo
c
o
n
d
i
tio
n
s
.
Sev
er
al
p
r
ev
io
u
s
s
tu
d
ies,
s
u
ch
as
th
o
s
e
b
y
Sh
ar
m
a
et
a
l.
[
1
4
]
,
h
av
e
s
h
o
wn
th
at
d
ee
p
f
ac
ial
r
ec
o
g
n
itio
n
tech
n
o
lo
g
y
h
as
g
r
ea
t
p
o
ten
tial
in
d
etec
tin
g
h
ig
h
-
q
u
ality
d
ee
p
f
a
k
es
u
s
in
g
th
e
C
NN
m
eth
o
d
.
T
h
is
s
tu
d
y
h
o
ld
s
s
ig
n
if
ican
t im
p
o
r
t
an
ce
in
ad
d
r
ess
in
g
th
e
g
r
o
win
g
th
r
ea
t o
f
d
ee
p
f
a
k
es.
T
h
e
r
esu
lts
o
f
th
is
s
tu
d
y
ar
e
ex
p
ec
ted
to
n
o
t
o
n
ly
p
r
o
v
id
e
a
m
o
r
e
ac
cu
r
ate
s
o
lu
tio
n
f
o
r
d
etec
tin
g
d
ee
p
f
ak
es
b
u
t
also
h
elp
en
h
a
n
ce
d
ig
ital
s
ec
u
r
ity
ac
r
o
s
s
v
ar
io
u
s
s
ec
to
r
s
,
p
ar
ticu
lar
ly
in
id
en
tity
a
u
t
h
en
ticatio
n
an
d
c
y
b
er
f
r
au
d
p
r
ev
en
tio
n
.
W
ith
a
m
o
r
e
r
eliab
le
d
etec
tio
n
m
eth
o
d
,
th
e
r
is
k
s
ass
o
ciate
d
with
th
e
s
p
r
ea
d
o
f
f
a
k
e
co
n
ten
t
an
d
i
d
en
tity
m
is
u
s
e
ca
n
b
e
m
in
im
ized
[
1
5
]
.
2.
M
E
T
H
O
D
T
h
is
s
tu
d
y
aim
s
to
d
ev
elo
p
a
d
ee
p
f
ak
e
d
etec
tio
n
s
y
s
tem
u
s
in
g
th
e
C
NN
[
1
6
]
ar
c
h
itectu
r
e
to
d
is
tin
g
u
is
h
b
etwe
en
r
ea
l
an
d
d
ee
p
f
ak
e
f
ac
es.
T
h
e
r
ese
ar
ch
m
eth
o
d
o
l
o
g
y
in
v
o
lv
es
s
ev
er
al
k
ey
s
tag
es,
in
clu
d
in
g
d
ata
c
o
llectio
n
,
d
ata
p
r
o
ce
s
s
in
g
,
m
o
d
el
t
r
ain
in
g
,
a
n
d
m
o
d
el
p
e
r
f
o
r
m
an
ce
ev
alu
a
tio
n
.
T
h
e
f
o
llo
win
g
ar
e
th
e
m
eth
o
d
o
lo
g
ical
s
tep
s
tak
en
in
th
is
s
tu
d
y
.
2
.
1
.
Da
t
a
c
o
llect
io
n
T
h
e
d
ataset
u
s
ed
in
t
h
is
s
tu
d
y
co
n
s
is
ts
o
f
r
ea
l
an
d
d
ee
p
f
a
k
e
f
ac
e
im
ag
es.
T
h
e
d
ataset
is
s
o
u
r
ce
d
f
r
o
m
o
p
en
p
latf
o
r
m
s
s
u
ch
as K
ag
g
l
e
[
1
7
]
,
a
n
d
it in
clu
d
es 1
4
0
,
0
0
0
f
ac
e
im
ag
es,
with
an
eq
u
al
d
i
s
tr
ib
u
tio
n
o
f
7
0
,
0
0
0
r
ea
l
f
ac
es
an
d
7
0
,
0
0
0
d
ee
p
f
a
k
e
f
ac
es
g
en
er
ated
b
y
GANs
[
1
8
]
.
T
h
ese
im
ag
es
h
av
e
a
u
n
if
o
r
m
r
eso
lu
tio
n
o
f
256
×
2
5
6
p
i
x
els to
f
ac
ilit
ate
f
u
r
th
er
p
r
o
ce
s
s
in
g
.
2
.
2
.
Da
t
a
P
re
pro
ce
s
s
ing
B
ef
o
r
e
b
ein
g
u
s
ed
f
o
r
m
o
d
el
t
r
ain
in
g
,
th
e
im
ag
e
d
ata
is
p
r
o
c
ess
ed
th
r
o
u
g
h
th
e
f
o
ll
o
win
g
s
tag
es:
−
No
r
m
aliza
tio
n
:
t
h
e
p
ix
el
v
alu
es
o
f
th
e
im
ag
es
ar
e
s
ca
led
t
o
a
r
an
g
e
b
etwe
en
0
a
n
d
1
t
o
f
ac
ilit
ate
th
e
tr
ain
in
g
p
r
o
ce
s
s
[
1
9
]
.
−
Data
a
u
g
m
en
tatio
n
[
2
0
]
:
t
ec
h
n
iq
u
es
s
u
ch
as
r
o
tatio
n
,
tr
an
s
latio
n
,
an
d
f
lip
p
in
g
ar
e
ap
p
lie
d
to
in
cr
ea
s
e
th
e
v
ar
iatio
n
o
f
tr
ain
in
g
d
ata
an
d
i
m
p
r
o
v
e
th
e
m
o
d
el’
s
g
en
e
r
aliza
tio
n
ab
ilit
y
.
−
Data
s
et
d
iv
is
io
n
:
th
e
d
ataset
is
s
p
lit
in
to
tr
ain
in
g
an
d
v
alid
atio
n
d
ata
with
a
r
atio
o
f
8
0
:2
0
t
o
m
ain
tain
tr
ain
in
g
q
u
ality
an
d
a
v
o
id
o
v
e
r
f
itti
n
g
[
2
1
]
.
2
.
3
.
CNN
m
o
del a
rc
hite
ct
ur
e
T
h
e
C
NN
m
o
d
el
is
u
s
ed
as
t
h
e
f
o
u
n
d
atio
n
al
a
r
ch
itectu
r
e
f
o
r
th
e
d
ee
p
f
ak
e
d
etec
tio
n
p
r
o
ce
s
s
[
2
2
]
.
C
NN
i
s
ch
o
s
en
f
o
r
its
ab
ilit
y
to
r
ec
o
g
n
ize
v
is
u
al
f
ea
tu
r
es
h
ier
ar
ch
ically
[
2
3
]
,
[
2
4
]
,
m
a
k
in
g
it
well
-
s
u
ited
f
o
r
d
etec
tin
g
s
u
b
tle
d
if
f
e
r
en
ce
s
b
e
twee
n
r
ea
l f
ac
es a
n
d
d
ee
p
f
a
k
e
s
.
T
h
e
s
tag
es in
C
NN
[
2
5
]
,
[
2
6
]
in
clu
d
e:
−
C
o
n
v
o
lu
tio
n
lay
er
:
th
is
lay
er
f
u
n
ctio
n
s
t
o
ex
tr
ac
t
f
ea
tu
r
es
f
r
o
m
th
e
in
p
u
t
im
a
g
e
u
s
in
g
a
f
ilt
er
th
at
m
o
v
es
s
p
atially
o
v
er
th
e
im
a
g
e.
−
Po
o
lin
g
:
t
h
e
p
o
o
lin
g
p
r
o
ce
s
s
r
ed
u
ce
s
th
e
d
im
e
n
s
io
n
s
o
f
t
h
e
im
ag
e
with
o
u
t
r
em
o
v
i
n
g
im
p
o
r
tan
t
f
ea
tu
r
es,
h
elp
in
g
to
m
in
im
ize
co
m
p
u
tat
io
n
al
co
m
p
le
x
ity
.
−
Fu
lly
co
n
n
ec
ted
la
y
er
:
th
is
lay
er
p
er
f
o
r
m
s
th
e
f
in
al
class
if
icatio
n
,
d
eter
m
in
i
n
g
wh
eth
e
r
th
e
im
ag
e
is
a
r
ea
l
f
ac
e
o
r
a
d
ee
p
f
a
k
e
2
.
4
.
T
ra
ini
ng
p
a
ra
m
e
t
er
s
T
h
e
C
NN
m
o
d
el
is
tr
ain
ed
u
s
i
n
g
th
e
f
o
llo
win
g
p
ar
am
eter
c
o
n
f
ig
u
r
atio
n
:
−
Op
tim
izer
:
Ad
am
(
ad
ap
tiv
e
m
o
m
en
t
esti
m
atio
n
)
[
2
7
]
is
u
s
ed
to
ac
ce
ler
ate
th
e
co
n
v
er
g
en
c
e
p
r
o
ce
s
s
d
u
r
in
g
tr
ain
in
g
.
−
L
o
s
s
f
u
n
ctio
n
[
2
8
]
:
b
i
n
ar
y
cr
o
s
s
-
en
tr
o
p
y
is
s
elec
ted
as
th
e
lo
s
s
f
u
n
ctio
n
s
in
ce
th
e
p
r
o
b
l
em
is
a
b
in
a
r
y
class
if
icatio
n
.
−
B
atch
s
ize:
a
b
atch
s
ize
o
f
6
4
i
s
u
s
ed
,
p
r
o
v
id
in
g
a
b
alan
ce
b
e
twee
n
tr
ain
in
g
tim
e
a
n
d
m
em
o
r
y
u
s
ag
e.
−
Nu
m
b
er
o
f
e
p
o
ch
s
:
th
e
m
o
d
el
is
tr
ain
ed
f
o
r
2
5
e
p
o
ch
s
,
with
v
alid
atio
n
lo
s
s
m
o
n
i
to
r
in
g
to
av
o
i
d
o
v
er
f
itti
n
g
.
2
.
5
.
M
o
del
e
v
a
lua
t
i
o
n
T
o
m
ea
s
u
r
e
th
e
p
e
r
f
o
r
m
an
ce
o
f
th
e
d
ev
elo
p
ed
C
NN
m
o
d
el,
s
ev
er
al
ev
alu
atio
n
m
etr
ics
[
2
9
]
ar
e
u
s
ed
,
in
clu
d
in
g
:
−
Acc
u
r
ac
y
:
m
ea
s
u
r
es th
e
o
v
er
a
ll a
cc
u
r
ac
y
o
f
th
e
m
o
d
el
in
cla
s
s
if
y
in
g
im
ag
es c
o
r
r
ec
tly
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
9
,
No
.
2
,
Au
g
u
s
t
20
25
:
1
0
9
2
-
1
099
1094
−
Pre
cisi
o
n
,
r
ec
all,
F1
-
s
co
r
e:
th
ese
m
etr
ics
ev
alu
ate
th
e
b
alan
ce
b
etwe
en
p
o
s
itiv
e
an
d
n
eg
a
tiv
e
p
r
ed
ictio
n
s
m
ad
e
b
y
th
e
m
o
d
el.
−
R
ec
eiv
er
o
p
er
atin
g
ch
ar
ac
ter
is
tic
(
R
OC
)
c
u
r
v
e
[
3
0
]
:
t
h
i
s
cu
r
v
e
is
u
s
ed
to
v
is
u
aliz
e
th
e
m
o
d
el’
s
p
er
f
o
r
m
an
ce
ac
r
o
s
s
v
ar
io
u
s
th
r
esh
o
ld
v
alu
es.
2
.
6
.
T
esting
a
nd
v
a
lid
a
t
io
n
T
h
e
m
o
d
el
is
ev
alu
ated
u
s
in
g
v
alid
atio
n
d
ata
th
at
is
d
is
tin
ct
f
r
o
m
th
e
tr
ain
in
g
s
et.
Per
f
o
r
m
an
ce
is
m
ea
s
u
r
ed
th
r
o
u
g
h
m
etr
ics
in
clu
d
in
g
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
e
ca
ll,
an
d
F1
-
s
co
r
e
[
3
1
]
.
Fu
r
th
er
m
o
r
e,
a
c
o
n
f
u
s
io
n
m
atr
ix
is
em
p
lo
y
e
d
to
g
ai
n
m
o
r
e
in
s
ig
h
t in
to
th
e
m
o
d
el’
s
ac
c
u
r
ate
an
d
e
r
r
o
n
eo
u
s
p
r
ed
ictio
n
s
[
3
2
]
.
2
.
7
.
E
rr
o
r
a
na
ly
s
is
Af
ter
th
e
test
in
g
p
r
o
ce
s
s
,
an
a
n
aly
s
is
is
co
n
d
u
cted
o
n
ca
s
es
wh
er
e
th
e
m
o
d
el
m
ak
es
p
r
e
d
ic
tio
n
er
r
o
r
s
[
3
3
]
.
T
h
is
an
aly
s
is
h
elp
s
in
u
n
d
er
s
tan
d
in
g
th
e
m
o
d
el’
s
lim
itatio
n
s
an
d
s
er
v
es
as
a
b
asis
f
o
r
f
u
r
th
er
im
p
r
o
v
em
e
n
ts
.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
3
.
1
.
E
x
perim
ent
a
l
r
esu
lt
s
T
h
is
s
tu
d
y
s
u
cc
ess
f
u
lly
d
ev
el
o
p
ed
a
d
ee
p
f
a
k
e
d
etec
tio
n
s
y
s
tem
b
ased
o
n
a
C
NN
u
s
in
g
a
d
ataset
co
n
s
is
tin
g
o
f
1
4
0
,
0
0
0
f
ac
ial
im
ag
es,
d
iv
id
ed
in
t
o
7
0
,
0
0
0
r
e
al
f
ac
ial
im
ag
es a
n
d
7
0
,
0
0
0
d
e
ep
f
ak
e
f
ac
ial
im
ag
es
f
r
o
m
Kag
g
le
[
1
7
]
.
T
h
e
C
NN
m
o
d
el
was
tr
ain
ed
f
o
r
2
5
e
p
o
ch
s
with
a
b
atch
s
ize
o
f
6
4
u
s
in
g
th
e
r
ec
tifie
d
lin
ea
r
u
n
it
(
R
eL
U
)
ac
tiv
atio
n
f
u
n
ctio
n
an
d
th
e
Ad
a
m
o
p
tim
izer
.
T
h
e
r
esu
lts
s
h
o
wed
th
at
th
is
m
o
d
el
h
as
a
r
elativ
ely
g
o
o
d
p
e
r
f
o
r
m
an
ce
i
n
d
etec
tin
g
d
ee
p
f
ak
es.
T
h
e
p
e
r
f
o
r
m
an
ce
o
f
th
e
m
o
d
el
is
p
r
esen
ted
in
T
ab
le
1
.
B
ased
o
n
th
e
r
esu
lts
o
b
tain
e
d
f
r
o
m
u
s
in
g
th
e
C
NN
m
o
d
e
l
with
a
d
ataset
o
f
1
4
0
,
0
0
0
i
m
ag
es,
an
ac
cu
r
ac
y
o
f
8
1
.
3
%
was
ac
h
iev
ed
o
n
th
e
test
d
ata.
T
h
e
m
et
r
ics
s
h
o
w
th
at
th
e
m
o
d
el
s
u
cc
ess
f
u
lly
class
if
ie
s
m
o
s
t
im
ag
es,
th
o
u
g
h
th
er
e
is
p
o
ten
tial
to
en
h
an
ce
its
ac
cu
r
ac
y
f
u
r
t
h
er
.
B
esid
es
ac
cu
r
ac
y
,
ad
d
itio
n
al
ev
alu
atio
n
m
etr
ics
lik
e
p
r
ec
is
i
o
n
,
r
ec
all,
an
d
F1
-
s
co
r
e
a
r
e
u
t
ilized
to
o
f
f
er
a
m
o
r
e
c
o
m
p
let
e
ass
es
s
m
en
t
o
f
th
e
m
o
d
el'
s
ef
f
ec
tiv
en
ess
in
d
et
ec
tin
g
d
ee
p
f
ak
es.
T
h
e
r
esu
lts
f
o
r
th
ese
m
etr
ics
a
r
e
as
f
o
llo
ws:
a
p
r
ec
is
io
n
v
alu
e
o
f
9
5
%,
in
d
icatin
g
th
at
th
e
m
o
d
el
h
as
a
lo
w
er
r
o
r
r
ate
in
m
is
class
if
y
in
g
f
ak
e
f
ac
es
as
r
ea
l
f
ac
es;
a
r
ec
all
v
alu
e
o
f
9
8
%,
s
h
o
win
g
th
at
th
e
m
o
d
el
is
h
ig
h
ly
s
en
s
itiv
e
to
d
ee
p
f
a
k
e
i
m
ag
es
an
d
ca
n
d
etec
t
m
o
s
t
d
ee
p
f
ak
e
f
ac
es
in
th
e
d
ataset;
an
d
an
F1
-
s
co
r
e
o
f
9
7
%,
t
h
is
in
d
icate
s
th
e
m
o
d
el's
s
tr
o
n
g
ca
p
ab
ilit
y
in
d
is
tin
g
u
is
h
in
g
b
etwe
en
r
ea
l
an
d
d
ee
p
f
ak
e
f
ac
es
in
a
b
in
ar
y
class
if
icatio
n
task
.
T
o
g
ain
d
ee
p
er
in
s
ig
h
ts
in
to
th
e
m
o
d
el'
s
p
e
r
f
o
r
m
a
n
ce
ac
r
o
s
s
d
if
f
er
en
t
class
if
icatio
n
th
r
esh
o
ld
s
,
a
R
OC
cu
r
v
e
an
d
th
e
ar
ea
u
n
d
er
t
h
e
cu
r
v
e
(
AUC)
[
3
4
]
ar
e
g
en
er
ated
,
as illu
s
tr
ated
in
Fig
u
r
e
1
.
T
ab
le
1
.
T
r
ai
n
in
g
e
v
alu
atio
n
o
f
ea
ch
m
o
d
el
M
o
d
e
l
D
a
t
a
s
e
t
Te
st
a
c
c
u
r
a
c
y
F1
-
s
c
o
r
e
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
C
N
N
1
4
0
,
0
0
0
r
e
a
l
a
n
d
f
a
k
e
f
a
c
e
s
0
.
8
1
3
0
.
9
7
0
.
9
5
0
.
9
8
Fig
u
r
e
1
.
R
OC
c
u
r
v
e
C
NN
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:
2502
-
4
7
5
2
Dee
p
fa
ke
d
etec
tio
n
u
s
in
g
co
n
vo
lu
tio
n
a
l
n
eu
r
a
l n
etw
o
r
ks:
a
d
ee
p
lea
r
n
in
g
…
(
F
en
i
n
a
A
d
li
n
e
Tw
in
ce
To
b
in
g
)
1095
B
ased
o
n
th
e
g
e
n
er
ated
R
OC
cu
r
v
e,
th
e
C
NN
m
o
d
el
s
h
o
ws
an
AUC
o
f
9
1
%
o
n
a
d
ataset
co
n
tain
in
g
1
4
0
,
0
0
0
r
ea
l
an
d
f
ak
e
f
ac
e
i
m
ag
es,
in
d
icatin
g
g
o
o
d
p
er
f
o
r
m
an
ce
i
n
d
is
tin
g
u
is
h
in
g
r
ea
l
an
d
d
ee
p
f
ak
e
f
ac
es.
E
x
p
er
im
en
ts
wer
e
c
o
n
d
u
cted
to
ev
alu
ate
th
e
ac
c
u
r
ac
y
o
f
t
h
e
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
.
Fak
e
a
n
d
r
ea
l
p
h
o
to
s
f
r
o
m
ea
ch
m
o
d
el
wer
e
u
s
ed
in
t
h
is
ex
p
er
im
en
t.
As
s
h
o
wn
in
Fig
u
r
e
2
,
alm
o
s
t
all
p
h
o
to
s
wer
e
s
u
cc
ess
f
u
lly
id
en
tifie
d
an
d
co
r
r
ec
tly
class
if
ied
as
eith
er
"Real
"
o
r
"Fa
k
e"
.
T
h
e
r
ea
l
an
d
f
ak
e
p
h
o
t
o
s
wer
e
r
an
d
o
m
ly
s
elec
ted
f
r
o
m
th
e
v
alid
atio
n
f
o
ld
er
.
Fig
u
r
e
3
s
h
o
ws
th
e
d
ec
r
ea
s
e
in
tr
ain
in
g
lo
s
s
an
d
v
alid
atio
n
lo
s
s
ag
ain
s
t
th
e
n
u
m
b
er
o
f
e
p
o
ch
s
in
th
e
C
NN
m
o
d
el.
At
th
e
b
eg
in
n
in
g
o
f
tr
ain
in
g
,
b
o
t
h
th
e
tr
ain
in
g
lo
s
s
an
d
v
alid
atio
n
lo
s
s
d
ec
r
ea
s
ed
s
h
ar
p
ly
,
in
d
icatin
g
th
at
th
e
C
NN
m
o
d
el
q
u
ick
ly
lear
n
e
d
f
r
o
m
th
e
d
ata.
Ho
wev
er
,
af
ter
s
ev
er
al
e
p
o
ch
s
,
th
e
v
alid
atio
n
lo
s
s
o
f
th
e
C
NN
m
o
d
el
b
eg
an
to
in
cr
ea
s
e,
in
d
icatin
g
p
o
ten
ti
al
o
v
er
f
itti
n
g
,
wh
ile
th
e
tr
ain
i
n
g
lo
s
s
co
n
tin
u
ed
to
d
ec
r
ea
s
e,
ap
p
r
o
ac
h
in
g
ze
r
o
,
s
u
g
g
esti
n
g
th
at
th
e
m
o
d
el
was a
b
le
to
lear
n
th
e
tr
ain
in
g
d
ata
w
ell.
Fig
u
r
e
2
.
E
x
am
p
le
o
f
a
r
ea
l im
ag
e
in
th
e
f
i
r
s
t r
o
w
an
d
a
f
ak
e
im
ag
e
in
th
e
s
ec
o
n
d
r
o
w
Fig
u
r
e
3
.
L
o
s
s
o
v
er
ep
o
ch
C
NN
Fig
u
r
e
4
p
r
esen
ts
th
e
co
n
f
u
s
io
n
m
atr
ix
f
o
r
b
in
a
r
y
class
if
icatio
n
u
s
in
g
th
is
C
NN
m
o
d
el,
illu
s
tr
atin
g
th
e
co
m
p
ar
is
o
n
b
etwe
en
t
h
e
ex
p
ec
ted
p
r
e
d
ictio
n
s
an
d
th
e
ac
tu
al
class
if
icatio
n
r
esu
lts
.
T
h
e
d
iag
o
n
al
elem
en
ts
r
ep
r
esen
t
th
e
n
u
m
b
er
o
f
tr
u
e
p
o
s
itiv
es
(
c
o
r
r
ec
t
p
r
ed
icti
o
n
s
f
o
r
r
ea
l
f
ac
es)
an
d
tr
u
e
n
eg
ativ
es
(
co
r
r
ec
t
p
r
ed
ictio
n
s
f
o
r
f
a
k
e
f
ac
es).
I
n
Fig
u
r
e
4
,
it
ca
n
b
e
s
ee
n
th
at
t
h
e
m
o
d
el
p
r
o
d
u
ce
d
9
,
5
8
3
co
r
r
ec
t
p
r
ed
ictio
n
s
f
o
r
r
ea
l
f
ac
es
(
tr
u
e
p
o
s
itiv
es)
an
d
9
,
8
2
7
c
o
r
r
ec
t
p
r
ed
ictio
n
s
f
o
r
f
ak
e
f
ac
es
(
tr
u
e
n
e
g
ativ
es).
Ho
wev
er
,
th
e
m
o
d
el
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
9
,
No
.
2
,
Au
g
u
s
t
20
25
:
1
0
9
2
-
1
099
1096
also
p
r
o
d
u
ce
d
4
1
7
in
c
o
r
r
ec
t
p
r
ed
ictio
n
s
f
o
r
r
ea
l
f
ac
es
th
at
wer
e
class
if
ied
as
f
ak
e
(
f
alse
n
eg
ativ
es)
an
d
1
7
3
f
ak
e
f
ac
es
th
at
wer
e
in
co
r
r
ec
t
ly
class
if
ied
as
r
ea
l
f
ac
es
(
f
al
s
e
p
o
s
itiv
es).
Alth
o
u
g
h
th
e
n
u
m
b
er
o
f
e
r
r
o
r
s
is
r
elativ
ely
s
m
all,
th
is
in
d
icate
s
th
at
th
e
m
o
d
el
is
b
etter
at
d
e
tectin
g
f
ak
e
f
ac
es
th
a
n
r
ea
l
f
a
ce
s
,
as
r
ef
lecte
d
in
th
e
h
ig
h
r
ec
all
v
alu
e.
Fig
u
r
e
4
.
C
NN
co
n
f
u
s
io
n
m
atr
ix
r
esu
lts
3
.
2
.
Dis
cus
s
io
n
T
h
e
r
esu
lts
o
f
th
is
s
tu
d
y
in
d
icate
th
at
C
NN
ca
n
b
e
ef
f
ec
ti
v
ely
u
s
ed
to
d
etec
t
d
ee
p
f
a
k
es,
alth
o
u
g
h
th
er
e
ar
e
s
till
s
o
m
e
ch
allen
g
e
s
th
at
n
ee
d
to
b
e
ad
d
r
ess
ed
.
T
h
e
ac
cu
r
ac
y
o
f
8
1
.
3
%
o
b
tain
e
d
is
s
till
b
elo
w
th
e
o
p
tim
al
p
er
f
o
r
m
an
ce
,
w
h
ich
m
ay
b
e
attr
ib
u
ted
t
o
s
ev
er
al
f
ac
to
r
s
,
s
u
ch
as
lim
ited
d
atasets
o
r
m
o
d
el
p
ar
am
eter
s
th
at
h
av
e
n
o
t
b
ee
n
f
u
lly
o
p
tim
ized
.
I
n
f
u
t
u
r
e
r
esear
ch
,
v
ar
io
u
s
ap
p
r
o
ac
h
es,
s
u
ch
as
in
cr
ea
s
in
g
th
e
am
o
u
n
t
o
f
d
ata
o
r
u
s
in
g
m
o
r
e
co
m
p
lex
o
p
tim
izatio
n
te
ch
n
iq
u
es,
ca
n
b
e
ex
p
lo
r
e
d
to
im
p
r
o
v
e
m
o
d
el
p
er
f
o
r
m
an
ce
.
C
NN
h
as
b
ee
n
s
h
o
wn
to
r
ec
o
g
n
ize
co
m
p
le
x
v
is
u
al
p
atter
n
s
in
im
a
g
es,
m
a
k
in
g
it
s
u
itab
le
f
o
r
task
s
s
u
ch
as
d
ee
p
f
ak
e
d
etec
tio
n
th
at
r
eq
u
i
r
e
a
d
ee
p
u
n
d
er
s
tan
d
in
g
o
f
v
is
u
al
f
ea
tu
r
es.
C
NN
s
u
cc
es
s
f
u
lly
d
is
tin
g
u
is
h
es
d
ee
p
f
ak
e
f
ac
es
f
r
o
m
r
ea
l
f
ac
es
with
a
r
ea
s
o
n
ab
le
lev
el
o
f
ac
c
u
r
ac
y
a
n
d
o
f
f
er
s
ad
v
an
tag
es
in
ter
m
s
o
f
ea
s
e
o
f
im
p
lem
en
tati
o
n
an
d
f
lex
ib
ilit
y
in
m
o
d
if
y
in
g
th
e
ar
ch
itectu
r
e.
Alth
o
u
g
h
C
NN's
p
er
f
o
r
m
an
ce
in
d
etec
tin
g
d
ee
p
f
ak
es
i
s
q
u
ite
s
atis
f
ac
to
r
y
,
th
e
r
e
a
r
e
s
ev
er
al
lim
itatio
n
s
th
at
n
ee
d
to
b
e
co
n
s
id
er
ed
.
On
e
m
ajo
r
c
h
allen
g
e
is
th
e
p
o
ten
tial
f
o
r
o
v
er
f
itti
n
g
o
n
th
e
ex
is
tin
g
d
atasets
,
wh
er
e
th
e
m
o
d
el
m
a
y
lear
n
to
class
if
y
th
e
tr
ain
in
g
d
ata
to
o
s
p
ec
if
ically
b
u
t
f
ail
t
o
g
en
er
alize
well
to
n
ew
d
ata.
Fu
r
th
er
m
o
r
e,
alth
o
u
g
h
d
ata
au
g
m
en
tatio
n
h
as
b
ee
n
ap
p
l
ied
,
a
wid
er
v
ar
iety
o
f
d
atasets
is
n
ee
d
ed
to
h
an
d
le
d
if
f
er
en
t ty
p
es o
f
d
ee
p
f
ak
es th
at
m
ay
b
e
m
o
r
e
d
if
f
icu
l
t to
d
etec
t.
T
h
e
r
esu
lts
o
f
th
is
s
tu
d
y
h
av
e
s
ig
n
if
ican
t
im
p
licatio
n
s
in
ef
f
o
r
ts
to
p
r
ev
en
t
th
e
m
is
u
s
e
o
f
d
ee
p
f
ak
e
tech
n
o
lo
g
y
.
As
d
ee
p
f
a
k
e
tech
n
o
lo
g
y
co
n
tin
u
es
to
ad
v
an
ce
,
d
ee
p
lear
n
in
g
-
b
ased
d
etec
tio
n
m
eth
o
d
s
s
u
ch
as
C
NNs
ca
n
b
e
an
ess
en
tial
to
o
l
in
m
itig
atin
g
th
e
s
p
r
ea
d
o
f
f
ak
e
co
n
ten
t
o
n
th
e
in
ter
n
e
t.
Po
ten
tial
f
u
tu
r
e
d
ev
elo
p
m
e
n
ts
in
clu
d
e
co
m
b
in
in
g
C
NNs
with
o
th
er
,
m
o
r
e
c
o
m
p
lex
ar
c
h
itectu
r
es
o
r
en
s
e
m
b
le
tech
n
iq
u
es
to
im
p
r
o
v
e
p
er
f
o
r
m
an
ce
,
as we
ll a
s
ap
p
ly
in
g
th
ese
m
et
h
o
d
s
to
r
ea
l
-
tim
e
v
id
eo
d
ata
f
o
r
f
u
r
t
h
er
d
etec
tio
n
.
T
h
e
r
esu
lts
o
f
th
e
C
NN
m
o
d
el
in
th
is
s
tu
d
y
a
r
e
g
en
er
ally
co
n
s
is
ten
t
with
p
r
ev
io
u
s
s
tu
d
ies
u
s
in
g
s
im
ilar
m
eth
o
d
s
.
Fo
r
ex
am
p
l
e,
r
esear
ch
b
y
Sh
ar
m
a
et
a
l.
[
1
4
]
also
s
h
o
wed
th
at
C
NN
s
ar
e
ab
le
to
d
etec
t
d
ee
p
f
ak
es
with
an
ac
cu
r
ac
y
o
f
o
v
er
8
0
%,
p
ar
ticu
lar
l
y
o
n
h
ig
h
-
r
eso
lu
tio
n
im
a
g
es.
Ho
we
v
er
,
th
is
s
tu
d
y
also
in
d
icate
s
th
at
th
e
u
s
e
o
f
m
o
r
e
co
m
p
lex
m
o
d
els,
s
u
ch
as
R
esNet
o
r
en
s
em
b
le
lear
n
in
g
tech
n
i
q
u
es,
ca
n
f
u
r
t
h
er
im
p
r
o
v
e
ac
c
u
r
ac
y
,
h
ig
h
lig
h
tin
g
an
o
p
p
o
r
tu
n
ity
f
o
r
f
u
tu
r
e
r
esear
ch
.
4.
CO
NCLU
SI
O
N
T
h
is
s
tu
d
y
s
u
cc
ess
f
u
lly
d
ev
e
lo
p
ed
a
d
ee
p
f
ak
e
d
etec
tio
n
m
eth
o
d
b
ased
o
n
a
C
NN
ar
ch
itectu
r
e,
ac
h
iev
in
g
a
f
air
ly
g
o
o
d
ac
c
u
r
ac
y
r
ate
o
f
8
1
.
3
%.
T
h
is
m
et
h
o
d
h
as
b
e
en
p
r
o
v
en
ca
p
ab
le
o
f
i
d
en
tify
in
g
th
e
d
if
f
er
en
ce
s
b
etwe
en
r
ea
l
f
ac
e
s
an
d
d
ee
p
f
ak
es
u
s
in
g
v
is
u
al
f
ea
tu
r
es
ex
tr
ac
ted
b
y
th
e
C
NN.
Ho
wev
er
,
th
ese
r
esu
lts
in
d
icate
th
at
th
er
e
is
s
till
r
o
o
m
f
o
r
im
p
r
o
v
e
m
en
t,
p
ar
ticu
lar
ly
in
h
an
d
lin
g
h
ig
h
-
q
u
ality
an
d
m
o
r
e
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:
2502
-
4
7
5
2
Dee
p
fa
ke
d
etec
tio
n
u
s
in
g
co
n
vo
lu
tio
n
a
l
n
eu
r
a
l n
etw
o
r
ks:
a
d
ee
p
lea
r
n
in
g
…
(
F
en
i
n
a
A
d
li
n
e
Tw
in
ce
To
b
in
g
)
1097
co
m
p
lex
d
ee
p
f
ak
es.
T
h
e
ev
al
u
atio
n
m
etr
ics,
s
u
ch
as
p
r
ec
is
io
n
an
d
r
ec
all
v
alu
es
ex
ce
ed
in
g
9
5
%,
d
em
o
n
s
tr
ate
th
at
th
e
m
o
d
el
is
h
ig
h
ly
ef
f
ec
tiv
e
in
d
etec
tin
g
d
ee
p
f
a
k
e
f
ac
es,
b
u
t
it
is
s
lig
h
tly
less
o
p
tim
al
in
d
etec
tin
g
r
ea
l
f
ac
es.
Fo
r
f
u
tu
r
e
r
esear
c
h
,
f
u
r
th
er
d
ev
elo
p
m
e
n
t
ca
n
f
o
cu
s
o
n
ex
p
a
n
d
in
g
t
h
e
v
ar
ie
ty
o
f
d
atasets
an
d
im
p
lem
en
tin
g
m
o
r
e
co
m
p
lex
d
ee
p
lear
n
i
n
g
tech
n
iq
u
es,
s
u
ch
as
en
s
em
b
le
lear
n
i
n
g
o
r
th
e
u
s
e
o
f
m
o
r
e
ad
v
an
ce
d
n
eu
r
al
n
etwo
r
k
ar
c
h
itectu
r
es.
T
h
e
r
esu
lts
o
f
th
is
s
t
u
d
y
h
a
v
e
th
e
p
o
ten
tial
to
h
elp
m
itig
ate
th
e
r
is
k
o
f
s
p
r
ea
d
in
g
f
a
k
e
co
n
ten
t,
p
a
r
ticu
lar
ly
in
ap
p
licatio
n
s
th
at
r
eq
u
ir
e
id
en
tity
au
th
e
n
ticatio
n
an
d
d
ig
ital secu
r
ity
.
ACK
NO
WL
E
DG
E
M
E
NT
S
Ou
r
ap
p
r
ec
iatio
n
to
Un
iv
er
s
i
tas
Mu
ltime
d
ia
Nu
s
an
tar
a
f
o
r
p
r
o
v
id
i
n
g
th
e
ess
en
tial
r
es
o
u
r
ce
s
th
at
m
ad
e
th
is
r
esear
ch
p
o
s
s
ib
le.
Fin
ally
,
we
wo
u
ld
lik
e
t
o
th
an
k
o
u
r
d
e
d
icate
d
s
tu
d
en
ts
f
o
r
th
eir
i
n
v
alu
ab
l
e
ass
is
tan
ce
th
r
o
u
g
h
o
u
t t
h
e
r
ese
ar
ch
p
r
o
ce
s
s
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
T
h
is
r
esear
ch
was
f
u
n
d
ed
b
y
Un
iv
e
r
s
itas
Mu
ltime
d
ia
Nu
s
an
tar
a.
T
h
e
au
th
o
r
s
g
r
at
ef
u
lly
ac
k
n
o
wled
g
e
th
e
s
u
p
p
o
r
t p
r
o
v
id
ed
b
y
th
e
u
n
iv
er
s
ity
.
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
T
h
is
jo
u
r
n
al
u
s
es
th
e
C
o
n
tr
ib
u
to
r
R
o
les
T
ax
o
n
o
m
y
(
C
R
ed
iT)
to
r
ec
o
g
n
ize
in
d
iv
id
u
al
au
th
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
th
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
llab
o
r
atio
n
.
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
F
e
n
in
a
Ad
li
n
e
Twi
n
c
e
To
b
i
n
g
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Ad
h
i
K
u
sn
a
d
i
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Iv
ra
n
z
a
Zu
h
d
i
P
a
n
e
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Ra
n
g
g
a
Wi
n
a
n
t
y
o
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
T
h
e
au
th
o
r
s
d
ec
lar
e
th
at
th
e
y
h
av
e
n
o
k
n
o
wn
co
m
p
etin
g
f
in
an
cial
in
ter
ests
o
r
p
er
s
o
n
al
r
el
atio
n
s
h
ip
s
th
at
co
u
ld
h
av
e
ap
p
ea
r
ed
t
o
in
f
lu
en
ce
th
e
wo
r
k
r
e
p
o
r
te
d
in
t
h
is
p
ap
er
.
I
NF
O
RM
E
D
CO
NS
E
N
T
W
e
h
av
e
o
b
tain
ed
in
f
o
r
m
ed
c
o
n
s
en
t f
r
o
m
all
in
d
iv
id
u
als in
c
lu
d
ed
in
t
h
is
s
tu
d
y
.
E
T
H
I
CAL AP
P
RO
V
AL
T
h
e
r
esear
ch
r
elate
d
to
h
u
m
a
n
u
s
e
h
as
b
ee
n
co
m
p
lied
with
all
th
e
r
elev
an
t
n
atio
n
al
r
eg
u
l
atio
n
s
an
d
in
s
titu
tio
n
al
p
o
licies
in
ac
co
r
d
an
ce
wit
h
th
e
te
n
ets
o
f
t
h
e
He
ls
in
k
i
Dec
lar
atio
n
an
d
h
as
b
ee
n
ap
p
r
o
v
e
d
b
y
th
e
au
th
o
r
s
'
in
s
titu
tio
n
al
r
ev
iew
b
o
ar
d
o
r
eq
u
i
v
alen
t c
o
m
m
ittee
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
au
th
o
r
s
co
n
f
ir
m
th
at
th
e
d
ata
s
u
p
p
o
r
tin
g
th
e
f
in
d
in
g
s
o
f
th
is
s
tu
d
y
ar
e
a
v
ailab
le
with
in
th
e
ar
ticle.
RE
F
E
R
E
NC
E
S
[
1
]
H
.
B
e
n
b
y
a
,
T.
H
.
D
a
v
e
n
p
o
r
t
,
a
n
d
S
.
P
a
c
h
i
d
i
,
“
A
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
i
n
o
r
g
a
n
i
z
a
t
i
o
n
s
:
c
u
r
r
e
n
t
st
a
t
e
a
n
d
f
u
t
u
r
e
o
p
p
o
r
t
u
n
i
t
i
e
s
,”
S
S
RN
El
e
c
t
ro
n
i
c
J
o
u
r
n
a
l
,
v
o
l
.
1
9
,
n
o
.
4
,
p
p
.
i
x
–
x
x
i
,
2
0
2
0
,
d
o
i
:
1
0
.
2
1
3
9
/
ssr
n
.
3
7
4
1
9
8
3
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
9
,
No
.
2
,
Au
g
u
s
t
20
25
:
1
0
9
2
-
1
099
1098
[
2
]
S
.
K
i
n
g
r
a
,
N
.
A
g
g
a
r
w
a
l
,
a
n
d
N
.
K
a
u
r
,
“
Em
e
r
g
e
n
c
e
o
f
d
e
e
p
f
a
k
e
s
a
n
d
v
i
d
e
o
t
a
mp
e
r
i
n
g
d
e
t
e
c
t
i
o
n
a
p
p
r
o
a
c
h
e
s:
a
s
u
r
v
e
y
,
”
M
u
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
2
,
n
o
.
7
,
p
p
.
1
0
1
6
5
–
1
0
2
0
9
,
M
a
r
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
1
0
4
2
-
022
-
1
3
1
0
0
-
x.
[
3
]
S
.
K
a
r
n
o
u
s
k
o
s
,
"
A
r
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
i
n
D
i
g
i
t
a
l
M
e
d
i
a
:
T
h
e
Er
a
o
f
D
e
e
p
f
a
k
e
s,"
i
n
I
EEE
Tr
a
n
s
a
c
t
i
o
n
s
o
n
Te
c
h
n
o
l
o
g
y
a
n
d
S
o
c
i
e
t
y
,
v
o
l
.
1
,
n
o
.
3
,
p
p
.
1
3
8
-
1
4
7
,
S
e
p
t
.
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
TTS.
2
0
2
0
.
3
0
0
1
3
1
2
.
[
4
]
J.
T.
H
a
n
c
o
c
k
a
n
d
J.
N
.
B
a
i
l
e
n
so
n
,
“
T
h
e
s
o
c
i
a
l
i
mp
a
c
t
o
f
d
e
e
p
f
a
k
e
s,
”
C
y
b
e
r
p
sy
c
h
o
l
o
g
y
,
Be
h
a
v
i
o
r
,
a
n
d
S
o
c
i
a
l
N
e
t
w
o
r
k
i
ng
,
v
o
l
.
2
4
,
n
o
.
3
,
p
p
.
1
4
9
–
1
5
2
,
M
a
r
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
8
9
/
c
y
b
e
r
.
2
0
2
1
.
2
9
2
0
8
.
j
t
h
.
[
5
]
K
.
A
.
P
a
n
t
ser
e
v
,
“
T
h
e
mal
i
c
i
o
u
s
u
se
o
f
A
I
-
b
a
sed
d
e
e
p
f
a
k
e
t
e
c
h
n
o
l
o
g
y
a
s
t
h
e
n
e
w
t
h
r
e
a
t
t
o
p
sy
c
h
o
l
o
g
i
c
a
l
se
c
u
r
i
t
y
a
n
d
p
o
l
i
t
i
c
a
l
st
a
b
i
l
i
t
y
,
”
i
n
C
y
b
e
r De
f
e
n
c
e
i
n
t
h
e
Ag
e
o
f
AI
,
S
m
a
r
t
S
o
c
i
e
t
i
e
s
a
n
d
A
u
g
m
e
n
t
e
d
H
u
m
a
n
i
t
y
,
S
p
r
i
n
g
e
r
P
u
b
l
i
s
h
i
n
g
,
2
0
2
0
,
p
p
.
3
7
–
5
5
.
[
6
]
H
.
N
a
v
i
d
a
n
e
t
a
l
.
,
“
G
e
n
e
r
a
t
i
v
e
a
d
v
e
r
sari
a
l
n
e
t
w
o
r
k
s
(
G
A
N
s)
i
n
n
e
t
w
o
r
k
i
n
g
:
a
c
o
m
p
r
e
h
e
n
si
v
e
s
u
r
v
e
y
&
e
v
a
l
u
a
t
i
o
n
,
”
C
o
m
p
u
t
e
r
N
e
t
w
o
rks
,
v
o
l
.
1
9
4
,
p
.
1
0
8
1
4
9
,
J
u
l
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
m
n
e
t
.
2
0
2
1
.
1
0
8
1
4
9
.
[
7
]
B
.
K
h
o
o
,
R
.
C
.
‐
W
.
P
h
a
n
,
a
n
d
C
.
Li
m
,
“
D
e
e
p
f
a
k
e
a
t
t
r
i
b
u
t
i
o
n
:
o
n
t
h
e
s
o
u
r
c
e
i
d
e
n
t
i
f
i
c
a
t
i
o
n
o
f
a
r
t
i
f
i
c
i
a
l
l
y
g
e
n
e
r
a
t
e
d
i
ma
g
e
s,
”
WIRE
s
D
a
t
a
M
i
n
i
n
g
a
n
d
K
n
o
w
l
e
d
g
e
D
i
sc
o
v
e
ry
,
v
o
l
.
1
2
,
n
o
.
3
,
M
a
y
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
2
/
w
i
d
m.
1
4
3
8
.
[
8
]
A
.
d
e
R
a
n
c
o
u
r
t
-
R
a
y
m
o
n
d
a
n
d
N
.
S
mai
l
i
,
“
T
h
e
u
n
e
t
h
i
c
a
l
u
s
e
o
f
d
e
e
p
f
a
k
e
s
,
”
J
o
u
r
n
a
l
o
f
F
i
n
a
n
c
i
a
l
C
ri
m
e
,
v
o
l
.
3
0
,
n
o
.
4
,
p
p
.
1
0
6
6
–
1
0
7
7
,
M
a
y
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
8
/
JF
C
-
04
-
2
0
2
2
-
0
0
9
0
.
[
9
]
O
.
M
.
D
a
v
e
y
a
n
d
L.
S
a
u
e
r
w
e
i
n
,
“
D
e
e
p
f
a
k
e
i
n
o
n
l
i
n
e
f
r
a
u
d
c
a
s
e
s:
t
h
e
h
a
z
e
o
f
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
’
s
a
c
c
o
u
n
t
a
b
i
l
i
t
y
b
a
se
d
o
n
t
h
e
i
n
t
e
r
n
a
t
i
o
n
a
l
l
a
w
,
”
S
ri
w
i
j
a
y
a
C
ri
m
e
n
a
n
d
L
e
g
a
l
S
t
u
d
i
e
s
,
v
o
l
.
1
,
n
o
.
2
,
p
.
8
9
,
D
e
c
.
2
0
2
3
,
d
o
i
:
1
0
.
2
8
9
4
6
/
s
c
l
s.
v
1
i
2
.
2
6
5
4
.
[
1
0
]
Y
.
P
a
t
e
l
e
t
a
l
.
,
“
D
e
e
p
f
a
k
e
g
e
n
e
r
a
t
i
o
n
a
n
d
d
e
t
e
c
t
i
o
n
:
c
a
se
st
u
d
y
a
n
d
c
h
a
l
l
e
n
g
e
s,
”
I
E
EE
Ac
c
e
ss
,
v
o
l
.
1
1
,
p
p
.
1
4
3
2
9
6
–
1
4
3
3
2
3
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
3
.
3
3
4
2
1
0
7
.
[
1
1
]
S
.
R
.
A
h
me
d
,
E.
S
o
n
u
c
,
M
.
R
.
A
h
me
d
,
a
n
d
A
.
D
.
D
u
r
u
,
“
A
n
a
l
y
s
i
s
su
r
v
e
y
o
n
d
e
e
p
f
a
k
e
d
e
t
e
c
t
i
o
n
a
n
d
r
e
c
o
g
n
i
t
i
o
n
w
i
t
h
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s,
”
i
n
2
0
2
2
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
g
ress
o
n
H
u
m
a
n
-
C
o
m
p
u
t
e
r
I
n
t
e
r
a
c
t
i
o
n
,
O
p
t
i
m
i
za
t
i
o
n
a
n
d
R
o
b
o
t
i
c
Ap
p
l
i
c
a
t
i
o
n
s (H
O
RA)
,
J
u
n
.
2
0
2
2
,
p
p
.
1
–
7
,
d
o
i
:
1
0
.
1
1
0
9
/
H
O
R
A
5
5
2
7
8
.
2
0
2
2
.
9
7
9
9
8
5
8
.
[
1
2
]
Z.
L
i
,
F
.
Li
u
,
W
.
Y
a
n
g
,
S
.
P
e
n
g
,
a
n
d
J.
Z
h
o
u
,
“
A
s
u
r
v
e
y
o
f
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s
:
a
n
a
l
y
si
s,
a
p
p
l
i
c
a
t
i
o
n
s,
a
n
d
p
r
o
sp
e
c
t
s,”
I
EEE
T
ra
n
s
a
c
t
i
o
n
s
o
n
N
e
u
r
a
l
N
e
t
w
o
rks
a
n
d
L
e
a
r
n
i
n
g
S
y
s
t
e
m
s
,
v
o
l
.
3
3
,
n
o
.
1
2
,
p
p
.
6
9
9
9
–
7
0
1
9
,
D
e
c
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
TN
N
LS.
2
0
2
1
.
3
0
8
4
8
2
7
.
[
1
3
]
A
.
K
a
r
a
n
d
i
k
a
r
,
“
D
e
e
p
f
a
k
e
v
i
d
e
o
d
e
t
e
c
t
i
o
n
u
s
i
n
g
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
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
T
r
e
n
d
s
i
n
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
v
o
l
.
9
,
n
o
.
2
,
p
p
.
1
3
1
1
–
1
3
1
5
,
A
p
r
.
2
0
2
0
,
d
o
i
:
1
0
.
3
0
5
3
4
/
i
j
a
t
c
se
/
2
0
2
0
/
6
2
9
2
2
0
2
0
.
[
1
4
]
J.
S
h
a
r
ma
,
S
.
S
h
a
r
m
a
,
V
.
K
u
m
a
r
,
H
.
S
.
H
u
ssei
n
,
a
n
d
H
.
A
l
s
h
a
z
l
y
,
“
D
e
e
p
f
a
k
e
s
c
l
a
ssi
f
i
c
a
t
i
o
n
o
f
f
a
c
e
s
u
si
n
g
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s,”
T
ra
i
t
e
m
e
n
t
d
u
S
i
g
n
a
l
,
v
o
l
.
3
9
,
n
o
.
3
,
p
p
.
1
0
2
7
–
1
0
3
7
,
J
u
n
.
2
0
2
2
,
d
o
i
:
1
0
.
1
8
2
8
0
/
t
s.
3
9
0
3
3
0
.
[
1
5
]
S
.
R
a
o
,
A
.
K
.
V
e
r
ma
,
a
n
d
T
.
B
h
a
t
i
a
,
“
A
r
e
v
i
e
w
o
n
so
c
i
a
l
s
p
a
m
d
e
t
e
c
t
i
o
n
:
c
h
a
l
l
e
n
g
e
s,
o
p
e
n
i
ssu
e
s,
a
n
d
f
u
t
u
r
e
d
i
r
e
c
t
i
o
n
s,
”
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
.
1
8
6
,
p
.
1
1
5
7
4
2
,
D
e
c
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
s
w
a
.
2
0
2
1
.
1
1
5
7
4
2
.
[
1
6
]
T.
K
a
t
t
e
n
b
o
r
n
,
J
.
Le
i
t
l
o
f
f
,
F
.
S
c
h
i
e
f
e
r
,
a
n
d
S
.
H
i
n
z
,
“
R
e
v
i
e
w
o
n
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s
(
C
N
N
)
i
n
v
e
g
e
t
a
t
i
o
n
r
e
mo
t
e
sen
s
i
n
g
,
”
I
S
P
RS
J
o
u
r
n
a
l
o
f
P
h
o
t
o
g
r
a
m
m
e
t
r
y
a
n
d
R
e
m
o
t
e
S
e
n
si
n
g
,
v
o
l
.
1
7
3
,
p
p
.
2
4
–
4
9
,
M
a
r
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
s
p
r
sj
p
r
s.
2
0
2
0
.
1
2
.
0
1
0
.
[
1
7
]
“
1
4
0
k
r
e
a
l
a
n
d
f
a
k
e
f
a
c
e
s,”
K
a
g
g
l
e
,
2
0
2
0
.
h
t
t
p
s:
/
/
w
w
w
.
k
a
g
g
l
e
.
c
o
m
/
x
h
l
u
l
u
/
1
4
0
k
-
r
e
a
l
-
a
n
d
-
f
a
k
e
-
f
a
c
e
s (
a
c
c
e
sse
d
M
a
y
3
0
,
2
0
2
1
)
.
[
1
8
]
D
.
S
a
x
e
n
a
a
n
d
J
.
C
a
o
,
“
G
e
n
e
r
a
t
i
v
e
a
d
v
e
r
sar
i
a
l
n
e
t
w
o
r
k
s
(
G
A
N
s)
,
”
A
C
M
C
o
m
p
u
t
i
n
g
S
u
rve
y
s
,
v
o
l
.
5
4
,
n
o
.
3
,
p
p
.
1
–
4
2
,
A
p
r
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
4
5
/
3
4
4
6
3
7
4
.
[
1
9
]
K
.
M
a
h
a
r
a
n
a
,
S
.
M
o
n
d
a
l
,
a
n
d
B
.
N
e
m
a
d
e
,
“
A
r
e
v
i
e
w
:
d
a
t
a
p
r
e
-
p
r
o
c
e
ss
i
n
g
a
n
d
d
a
t
a
a
u
g
me
n
t
a
t
i
o
n
t
e
c
h
n
i
q
u
e
s,
”
G
l
o
b
a
l
T
r
a
n
si
t
i
o
n
s
Pro
c
e
e
d
i
n
g
s
,
v
o
l
.
3
,
n
o
.
1
,
p
p
.
9
1
–
9
9
,
Ju
n
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
g
l
t
p
.
2
0
2
2
.
0
4
.
0
2
0
.
[
2
0
]
C
.
S
h
o
r
t
e
n
,
T.
M
.
K
h
o
s
h
g
o
f
t
a
a
r
,
a
n
d
B
.
F
u
r
h
t
,
“
Te
x
t
d
a
t
a
a
u
g
me
n
t
a
t
i
o
n
f
o
r
d
e
e
p
l
e
a
r
n
i
n
g
,
”
J
o
u
r
n
a
l
o
f
B
i
g
D
a
t
a
,
v
o
l
.
8
,
n
o
.
1
,
p
.
1
0
1
,
D
e
c
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
8
6
/
s
4
0
5
3
7
-
0
2
1
-
0
0
4
9
2
-
0.
[
2
1
]
A
.
N
u
r
h
o
p
i
p
a
h
a
n
d
U
.
H
a
s
a
n
a
h
,
“
D
a
t
a
s
e
t
s
p
l
i
t
t
i
n
g
t
e
c
h
n
i
q
u
e
s
c
o
mp
a
r
i
s
o
n
f
o
r
f
a
c
e
c
l
a
ssi
f
i
c
a
t
i
o
n
o
n
C
C
TV
i
m
a
g
e
s,
”
I
J
C
C
S
(
I
n
d
o
n
e
si
a
n
J
o
u
rn
a
l
o
f
C
o
m
p
u
t
i
n
g
a
n
d
C
y
b
e
r
n
e
t
i
c
s
S
y
st
e
m
s)
,
v
o
l
.
1
4
,
n
o
.
4
,
p
.
3
4
1
,
O
c
t
.
2
0
2
0
,
d
o
i
:
1
0
.
2
2
1
4
6
/
i
j
c
c
s.5
8
0
9
2
.
[
2
2
]
A
.
H
.
K
h
a
l
i
f
a
,
N
.
A
.
Za
h
e
r
,
A
.
S
.
A
b
d
a
l
l
a
h
,
a
n
d
M
.
W
.
F
a
k
h
r
,
“
C
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
b
a
s
e
d
o
n
d
i
v
e
r
se
g
a
b
o
r
f
i
l
t
e
r
s
f
o
r
d
e
e
p
f
a
k
e
r
e
c
o
g
n
i
t
i
o
n
,
”
I
E
EE
A
c
c
e
ss
,
v
o
l
.
1
0
,
p
p
.
2
2
6
7
8
–
2
2
6
8
6
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
2
.
3
1
5
2
0
2
9
.
[
2
3
]
A
.
R
a
j
e
s
h
,
S
.
T
i
w
a
r
i
,
V
.
G
o
t
e
c
h
a
,
a
n
d
N
.
Y
.
K
a
p
a
d
n
i
s,
“
D
e
e
p
f
a
k
e
d
e
t
e
c
t
i
o
n
u
si
n
g
C
N
N
,
”
B
u
l
l
e
t
i
n
f
o
r
T
e
c
h
n
o
l
o
g
y
a
n
d
H
i
s
t
o
r
y
J
o
u
rn
a
l
,
v
o
l
.
2
4
,
n
o
.
2
,
p
p
.
7
2
–
7
6
,
2
0
2
4
,
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s:
/
/
w
w
w
.
r
e
sea
r
c
h
g
a
t
e
.
n
e
t
/
p
u
b
l
i
c
a
t
i
o
n
/
3
7
8
6
0
9
5
8
3
.
[
2
4
]
A
.
K
u
sn
a
d
i
,
F
.
A
.
T.
To
b
i
n
g
,
M
.
D
a
f
a
,
R
.
A
.
Za
mza
mi
,
M
.
Ti
o
,
a
n
d
A
.
A
.
N
u
r
p
a
s
h
a
,
“
O
p
t
i
mi
z
i
n
g
3
D
f
a
c
e
r
e
c
o
g
n
i
t
i
o
n
w
i
t
h
P
C
A
a
n
d
C
N
N
f
o
r
e
n
h
a
n
c
e
d
a
c
c
u
r
a
c
y
,
”
i
n
2
0
2
4
9
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
Me
c
h
a
t
ro
n
i
c
s
En
g
i
n
e
e
ri
n
g
(
I
C
O
M)
,
A
u
g
.
2
0
2
4
,
p
p
.
2
0
–
2
6
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
O
M
6
1
6
7
5
.
2
0
2
4
.
1
0
6
5
2
4
6
6
.
[
2
5
]
W
.
H
.
L
o
p
e
z
P
i
n
a
y
a
,
S
.
V
i
e
i
r
a
,
R
.
G
a
r
c
i
a
-
D
i
a
s,
a
n
d
A
.
M
e
c
h
e
l
l
i
,
“
C
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s,”
i
n
M
a
c
h
i
n
e
L
e
a
rn
i
n
g
,
El
se
v
i
e
r
,
2
0
2
0
,
p
p
.
1
7
3
–
1
9
1
.
[
2
6
]
H
.
H
a
r
d
j
a
d
i
n
a
t
a
,
R
.
S
.
O
e
t
a
ma
,
a
n
d
I
.
P
r
a
set
i
a
w
a
n
,
“
F
a
c
i
a
l
e
x
p
r
e
ssi
o
n
r
e
c
o
g
n
i
t
i
o
n
u
si
n
g
x
c
e
p
t
i
o
n
a
n
d
D
e
n
seN
e
t
a
r
c
h
i
t
e
c
t
u
r
e
,
”
i
n
2
0
2
1
6
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
N
e
w
M
e
d
i
a
S
t
u
d
i
e
s
(
C
O
N
ME
D
I
A)
,
O
c
t
.
2
0
2
1
,
p
p
.
6
0
–
6
5
,
d
o
i
:
1
0
.
1
1
0
9
/
C
O
N
M
ED
I
A
5
3
1
0
4
.
2
0
2
1
.
9
6
1
7
1
7
3
.
[
2
7
]
N.
-
D
.
H
o
a
n
g
,
“
I
mag
e
p
r
o
c
e
ss
i
n
g
‐
b
a
se
d
sp
a
l
l
o
b
j
e
c
t
d
e
t
e
c
t
i
o
n
u
si
n
g
g
a
b
o
r
f
i
l
t
e
r
,
t
e
x
t
u
r
e
a
n
a
l
y
si
s
,
a
n
d
a
d
a
p
t
i
v
e
m
o
men
t
e
st
i
m
a
t
i
o
n
(
A
d
a
m)
o
p
t
i
mi
z
e
d
l
o
g
i
s
t
i
c
r
e
g
r
e
ss
i
o
n
m
o
d
e
l
s,”
A
d
v
a
n
c
e
s
i
n
C
i
v
i
l
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
2
0
2
0
,
n
o
.
1
,
J
a
n
.
2
0
2
0
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
0
/
8
8
2
9
7
1
5
.
[
2
8
]
Z.
X
i
o
n
g
,
Q
.
G
u
o
,
M
.
Li
u
,
a
n
d
A
.
L
i
,
“
P
a
n
-
s
h
a
r
p
e
n
i
n
g
b
a
s
e
d
o
n
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
b
y
u
s
i
n
g
t
h
e
l
o
ss
f
u
n
c
t
i
o
n
w
i
t
h
n
o
-
r
e
f
e
r
e
n
c
e
,
”
I
EEE
J
o
u
r
n
a
l
o
f
S
e
l
e
c
t
e
d
T
o
p
i
c
s i
n
Ap
p
l
i
e
d
E
a
rt
h
O
b
ser
v
a
t
i
o
n
s
a
n
d
R
e
m
o
t
e
S
e
n
si
n
g
,
v
o
l
.
1
4
,
p
p
.
8
9
7
–
9
0
6
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
JS
TA
R
S
.
2
0
2
0
.
3
0
3
8
0
5
7
.
[
2
9
]
J.
Z
h
o
u
,
A
.
H
.
G
a
n
d
o
m
i
,
F
.
C
h
e
n
,
a
n
d
A
.
H
o
l
z
i
n
g
e
r
,
“
E
v
a
l
u
a
t
i
n
g
t
h
e
q
u
a
l
i
t
y
o
f
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
e
x
p
l
a
n
a
t
i
o
n
s
:
a
su
r
v
e
y
o
n
met
h
o
d
s
a
n
d
met
r
i
c
s
,
”
El
e
c
t
r
o
n
i
c
s
,
v
o
l
.
1
0
,
n
o
.
5
,
p
.
5
9
3
,
M
a
r
.
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
e
l
e
c
t
r
o
n
i
c
s1
0
0
5
0
5
9
3
.
[
3
0
]
F
.
S
.
N
a
h
m,
“
R
e
c
e
i
v
e
r
o
p
e
r
a
t
i
n
g
c
h
a
r
a
c
t
e
r
i
st
i
c
c
u
r
v
e
:
o
v
e
r
v
i
e
w
a
n
d
p
r
a
c
t
i
c
a
l
u
s
e
f
o
r
c
l
i
n
i
c
i
a
n
s
,
”
K
o
re
a
n
J
o
u
rn
a
l
o
f
An
e
s
t
h
e
si
o
l
o
g
y
,
v
o
l
.
7
5
,
n
o
.
1
,
p
p
.
2
5
–
3
6
,
F
e
b
.
2
0
2
2
,
d
o
i
:
1
0
.
4
0
9
7
/
k
j
a
.
2
1
2
0
9
.
[
3
1
]
R
.
Y
a
c
o
u
b
y
a
n
d
D
.
A
x
m
a
n
,
“
P
r
o
b
a
b
i
l
i
st
i
c
e
x
t
e
n
si
o
n
o
f
p
r
e
c
i
s
i
o
n
,
r
e
c
a
l
l
,
a
n
d
F
1
sc
o
r
e
f
o
r
mo
r
e
t
h
o
r
o
u
g
h
e
v
a
l
u
a
t
i
o
n
o
f
c
l
a
ss
i
f
i
c
a
t
i
o
n
mo
d
e
l
s,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
F
i
rst
W
o
rks
h
o
p
o
n
E
v
a
l
u
a
t
i
o
n
a
n
d
C
o
m
p
a
ri
s
o
n
o
f
N
L
P
S
y
st
e
m
s
,
2
0
2
0
,
p
p
.
7
9
–
9
1
,
d
o
i
:
1
0
.
1
8
6
5
3
/
v
1
/
2
0
2
0
.
e
v
a
l
4
n
l
p
-
1
.
9
.
[
3
2
]
M
.
H
a
sn
a
i
n
,
M
.
F
.
P
a
s
h
a
,
I
.
G
h
a
n
i
,
M
.
I
mr
a
n
,
M
.
Y
.
A
l
z
a
h
r
a
n
i
,
a
n
d
R
.
B
u
d
i
a
r
t
o
,
“
E
v
a
l
u
a
t
i
n
g
t
r
u
s
t
p
r
e
d
i
c
t
i
o
n
a
n
d
c
o
n
f
u
s
i
o
n
mat
r
i
x
m
e
a
s
u
r
e
s
f
o
r
w
e
b
s
e
r
v
i
c
e
s ra
n
k
i
n
g
,
”
I
EEE
Ac
c
e
ss
,
v
o
l
.
8
,
p
p
.
9
0
8
4
7
–
9
0
8
6
1
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
0
.
2
9
9
4
2
2
2
.
[
3
3
]
P
.
A
r
o
r
a
,
H
.
K
u
mar,
a
n
d
B
.
K
.
P
a
n
i
g
r
a
h
i
,
“
P
r
e
d
i
c
t
i
o
n
a
n
d
a
n
a
l
y
si
s
o
f
C
O
V
I
D
-
1
9
p
o
s
i
t
i
v
e
c
a
s
e
s
u
si
n
g
d
e
e
p
l
e
a
r
n
i
n
g
mo
d
e
l
s:
a
d
e
s
c
r
i
p
t
i
v
e
c
a
se
s
t
u
d
y
o
f
I
n
d
i
a
,
”
C
h
a
o
s,
S
o
l
i
t
o
n
s &
Fr
a
c
t
a
l
s
,
v
o
l
.
1
3
9
,
p
.
1
1
0
0
1
7
,
O
c
t
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
h
a
o
s
.
2
0
2
0
.
1
1
0
0
1
7
.
[
3
4
]
I
.
M
.
M
a
n
n
a
a
,
O
.
N
.
El
G
a
z
a
y
e
r
l
y
,
A
.
A
.
A
b
d
e
l
b
a
r
y
,
S
.
S
.
S
a
l
e
h
,
a
n
d
D
.
A
.
M
o
s
t
a
f
a
,
“
V
a
l
i
d
a
t
e
d
g
r
e
e
n
s
p
e
c
t
r
o
sc
o
p
i
c
m
a
n
i
p
u
l
a
t
i
o
n
o
f
a
r
e
a
u
n
d
e
r
t
h
e
c
u
r
v
e
(
A
U
C
)
f
o
r
e
st
i
ma
t
i
o
n
o
f
S
i
mv
a
st
a
t
i
n
:
a
p
p
l
i
c
a
t
i
o
n
t
o
n
a
n
o
-
st
r
u
c
t
u
r
e
d
l
i
p
i
d
c
a
r
r
i
e
r
s
a
n
d
n
i
o
so
ma
l
s
y
st
e
ms,”
J
o
u
rn
a
l
o
f
Re
s
e
a
r
c
h
i
n
P
h
a
rm
a
c
y
,
v
o
l
.
2
7
(
1
)
,
n
o
.
2
7
(
1
)
,
p
p
.
3
0
–
4
2
,
2
0
2
3
,
d
o
i
:
1
0
.
2
9
2
2
8
/
j
r
p
.
2
8
5
.
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:
2502
-
4
7
5
2
Dee
p
fa
ke
d
etec
tio
n
u
s
in
g
co
n
vo
lu
tio
n
a
l
n
eu
r
a
l n
etw
o
r
ks:
a
d
ee
p
lea
r
n
in
g
…
(
F
en
i
n
a
A
d
li
n
e
Tw
in
ce
To
b
in
g
)
1099
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Feni
n
a
Adl
i
n
e
Twin
c
e
T
o
b
i
n
g
,
S
.
K
o
m
.
,
M
.
K
o
m
.
,
g
ra
d
u
a
ted
wit
h
a
M
a
ste
r'
s
d
e
g
re
e
fro
m
th
e
Un
i
v
e
rsity
o
f
No
rth
S
u
m
a
tra
(USU)
in
2
0
1
5
.
Cu
rre
n
tl
y
,
sh
e
is
a
n
a
c
ti
v
e
In
fo
rm
a
ti
c
s
lec
tu
re
r
a
t
U
n
iv
e
rsit
a
s
M
u
lt
ime
d
ia
Nu
sa
n
tara
(UMN
)
in
Ja
k
a
rta,
wh
e
re
sh
e
a
lso
se
rv
e
s
a
s
th
e
Re
se
a
rc
h
Co
o
rd
i
n
a
to
r
f
o
r
t
h
e
F
a
c
u
lt
y
o
f
En
g
i
n
e
e
rin
g
a
n
d
I
n
fo
rm
a
ti
c
s.
S
h
e
is
a
m
e
m
b
e
r
o
f
se
v
e
ra
l
p
ro
fe
ss
io
n
a
l
a
ss
o
c
iatio
n
s
s
u
c
h
a
s
IEE
E
(
In
stit
u
te
o
f
El
e
c
tri
c
a
l
a
n
d
El
e
c
tro
n
ics
E
n
g
in
e
e
rs),
AP
TIKOM
(I
n
d
o
n
e
sia
n
As
so
c
iatio
n
o
f
Hi
g
h
e
r
Ed
u
c
a
ti
o
n
i
n
C
o
m
p
u
ter
S
c
ien
c
e
),
a
n
d
ASP
P
I
(As
so
c
iatio
n
fo
r
S
y
n
e
rg
y
o
f
S
e
r
v
ice
a
n
d
Emp
o
we
rm
e
n
t
in
In
d
o
n
e
sia
).
I
n
a
d
d
it
i
o
n
to
h
e
r
i
n
v
o
lv
e
m
e
n
t
i
n
p
ro
fe
ss
io
n
a
l
o
r
g
a
n
iza
ti
o
n
s,
sh
e
i
s
a
lso
a
c
ti
v
e
in
so
c
ial
a
n
d
c
o
m
m
u
n
it
y
o
r
g
a
n
iza
ti
o
n
s,
i
n
c
lu
d
i
n
g
t
h
e
Dh
a
rm
a
Wan
it
a
P
e
rsa
tu
a
n
(DWP
)
a
t
t
h
e
Ja
k
a
rta
Clas
s
II
Co
rre
c
ti
o
n
a
l
In
stit
u
ti
o
n
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
fe
n
i
n
a
.
t
o
b
in
g
@u
m
n
.
a
c
.
i
d
.
Dr
.
Adh
i
K
u
sn
a
d
i
,
S
T
.
,
M.
S
i
.
c
o
m
p
lete
d
h
is
u
n
d
e
rg
ra
d
u
a
te
d
e
g
re
e
(S
1
)
a
t
S
riwij
a
y
a
Un
i
v
e
rsity
i
n
P
a
lem
b
a
n
g
in
1
9
9
6
.
He
c
o
n
t
in
u
e
d
h
is
e
d
u
c
a
ti
o
n
a
t
IP
B
Bo
g
o
r
,
m
a
jo
rin
g
i
n
c
o
m
p
u
ter
sc
ien
c
e
,
a
n
d
g
ra
d
u
a
ted
wit
h
a
M
a
ste
r'
s
d
e
g
re
e
(S
2
)
in
2
0
0
8
.
He
fin
ish
e
d
d
o
c
to
ra
l
st
u
d
ies
(S
3
)
i
n
c
o
m
p
u
ter
sc
ien
c
e
a
t
IP
B
in
2
0
2
4
.
He
wo
rk
s
a
s
a
p
e
rm
a
n
e
n
t
lec
tu
r
e
r
a
t
Un
iv
e
rsitas
M
u
lt
ime
d
ia
Nu
sa
n
tar
a
in
th
e
De
p
a
rtme
n
t
o
f
In
fo
rm
a
ti
c
s.
He
is
a
c
ti
v
e
ly
in
v
o
l
v
e
d
i
n
v
a
rio
u
s
p
r
o
fe
ss
io
n
a
l
a
ss
o
c
iatio
n
s
,
i
n
c
lu
d
in
g
th
e
I
n
d
o
n
e
sia
n
As
so
c
iatio
n
o
f
Lec
tu
re
rs
a
n
d
t
h
e
Na
ti
o
n
a
l
E
d
u
c
a
ti
o
n
C
o
m
m
issio
n
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
a
d
h
i.
k
u
s
n
a
d
i@
u
m
n
.
a
c
.
id
.
Dr
.
Iv
r
a
n
sa
Zu
h
d
i
P
a
n
e
,
B.
En
g
.
,
M.
En
g
.,
c
o
m
p
lete
d
h
is
u
n
d
e
r
g
ra
d
u
a
te
(S
1
)
a
n
d
m
a
ste
r'
s
(S
2
)
d
e
g
re
e
s
a
t
Ky
u
sh
u
In
stit
u
te
o
f
Tec
h
n
o
l
o
g
y
,
Ja
p
a
n
,
in
t
h
e
field
o
f
c
o
m
p
u
ter
sc
ien
c
e
a
n
d
s
y
ste
m
s
e
n
g
in
e
e
rin
g
in
1
9
9
2
a
n
d
1
9
9
4
,
re
sp
e
c
ti
v
e
ly
.
He
o
b
tai
n
e
d
h
is
d
o
c
to
ra
l
d
e
g
re
e
(S
3
)
fro
m
Ky
u
s
h
u
Un
i
v
e
r
sity
,
Ja
p
a
n
,
i
n
th
e
field
o
f
e
lec
tro
n
ics
in
2
0
1
0
.
Cu
rre
n
tl
y
,
h
e
wo
rk
s
a
s
a
S
e
n
io
r
Ex
p
e
rt
En
g
i
n
e
e
r
a
t
th
e
Na
ti
o
n
a
l
Re
se
a
rc
h
a
n
d
I
n
n
o
v
a
ti
o
n
A
g
e
n
c
y
a
n
d
a
s
a
lec
tu
re
r
in
t
h
e
In
fo
rm
a
ti
c
s
P
r
o
g
ra
m
a
t
Un
iv
e
rsitas
M
u
l
ti
m
e
d
ia
Nu
sa
n
tara
.
He
is
a
c
ti
v
e
ly
e
n
g
a
g
e
d
in
re
se
a
rc
h
a
n
d
d
e
v
e
lo
p
m
e
n
t
a
c
ti
v
it
ies
in
th
e
field
s
o
f
in
f
o
rm
a
ti
o
n
sy
ste
m
e
n
g
in
e
e
rin
g
a
n
d
e
x
p
e
rt
sy
ste
m
s.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
iv
ra
n
sa
.
z
u
h
d
i@l
e
c
tu
re
r.
u
m
n
.
a
c
.
id
.
Dr
.
Ra
n
g
g
a
Wi
n
a
n
t
y
o
P
h
.
D.
M
S
c
,
BCS
,
g
ra
d
u
a
ted
with
a
M
a
ste
r'
s
d
e
g
re
e
fro
m
th
e
Dig
it
a
l
M
e
d
ia,
Un
i
v
e
rsitat
Lu
b
e
c
k
,
G
e
rm
a
n
y
.
He
o
b
tai
n
e
d
h
is
d
o
c
to
ra
l
d
e
g
re
e
(S
3
)
Op
to
e
lek
tr
o
n
ics
a
n
d
Na
n
o
stru
c
tu
re
S
c
ien
c
e
,
S
h
izu
o
k
a
Un
i
v
e
rsity
,
Ja
p
a
n
.
Cu
rre
n
tl
y
,
h
e
w
o
rk
s
a
s
a
S
e
n
i
o
r
lec
tu
re
r
in
t
h
e
In
f
o
r
m
a
ti
c
s
P
r
o
g
ra
m
a
t
U
n
iv
e
rsitas
M
u
lt
ime
d
ia
N
u
sa
n
tara
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
ra
n
g
g
a
.
wi
n
a
n
ty
o
@
u
m
n
.
a
c
.
i
d
.
Evaluation Warning : The document was created with Spire.PDF for Python.