I
n
d
on
e
s
ian
Jou
r
n
al
o
f
E
lec
t
r
ica
l
E
n
gin
e
e
r
in
g
a
n
d
Com
p
u
t
e
r
S
c
ience
Vo
l
.
3
8
,
N
o
.
2
,
M
a
y
20
2
5
,
pp.
1
115
~
1
123
I
S
S
N:
2
502
-
4
7
52
,
DO
I
:
10
.
11591/i
j
e
e
cs
.v
3
8
.
i
2
.
pp
1
115
-
1
123
1115
Jou
r
n
al
h
o
m
e
page
:
ht
tp:
//
ij
e
e
cs
.
iaes
c
or
e
.
c
om
D
e
e
p
l
e
ar
n
in
g
-
b
ase
d
c
r
y
p
t
an
al
y
si
s i
n
r
e
c
o
ve
r
in
g t
h
e
se
c
r
e
t
k
e
y
an
d
p
la
in
t
e
xt
on
li
g
h
t
w
e
ig
h
t
c
r
y
p
t
og
r
ap
h
y
Yul
ia
F
at
m
a
1,
2
,
M
u
h
am
m
ad
Akm
a
l
Re
m
l
i
2
,
3
,
M
oh
d
S
ab
e
r
i
M
oh
am
ad
4
,
Jan
u
ar
Al
Am
ien
1
,
2
1
D
e
pa
r
tm
e
nt
of
I
n
f
or
ma
ti
c
s
E
ng
in
e
e
r
in
g,
F
a
c
ul
t
y
of
C
omput
e
r
S
c
i
e
n
c
e
, U
ni
ve
r
s
it
a
s
M
uha
mm
a
di
y
a
h R
ia
u, R
ia
u, I
ndo
n
e
s
ia
2
F
a
c
ul
t
y
of
D
a
ta
S
c
i
e
n
c
e
a
nd C
o
mput
in
g, U
ni
ve
r
s
it
i
M
a
la
y
s
ia
K
e
la
nt
a
n, K
e
la
nt
a
n, M
a
la
y
s
ia
3
I
ns
ti
tu
t
e
f
o
r
A
r
ti
f
i
c
ia
l
I
nt
e
ll
ig
e
n
c
e
a
nd B
ig
D
a
ta
, U
ni
v
e
r
s
it
i
M
a
la
y
s
ia
K
e
la
nt
a
n,
K
e
la
nt
a
n, M
a
la
y
s
ia
4
H
e
a
lt
h D
a
ta
S
c
ie
n
c
e
L
a
b, D
e
pa
r
tm
e
nt
of
G
e
n
e
ti
c
s
a
nd G
e
n
o
mi
c
s
, C
o
ll
e
g
e
of
M
e
di
c
in
e
a
nd
H
e
a
lt
h S
c
ie
n
c
e
s
,
U
ni
te
d A
r
a
b E
mi
r
a
te
s
U
ni
ve
r
s
it
y
, A
bu D
ha
bi
, U
ni
te
d A
r
a
b E
mi
r
a
te
s
Ar
t
ic
l
e
I
n
f
o
AB
S
T
RA
CT
A
r
ti
c
le
h
is
tor
y
:
R
e
c
e
i
ve
d
M
a
y
22
,
202
4
R
e
vi
s
e
d
No
v
6
,
202
4
A
c
c
e
pt
e
d
N
o
v
11
,
202
4
T
h
e
d
e
v
el
o
p
me
n
t
o
f
m
a
ch
i
n
e
l
e
ar
n
i
n
g
(ML
)
t
ech
n
o
l
o
g
i
e
s
p
ro
v
i
d
e
a
n
ew
d
ev
e
l
o
p
men
t
d
i
r
ec
t
i
o
n
f
o
r
c
r
y
p
t
an
al
y
s
i
s
.
S
ev
e
ral
M
L
r
es
e
arch
i
n
t
h
e
f
i
e
l
d
o
f
c
r
y
p
t
an
al
y
s
i
s
w
as
c
arri
ed
o
u
t
t
o
i
d
e
n
t
i
f
y
t
h
e
c
r
y
p
t
o
g
ra
p
h
i
c
a
l
g
o
ri
t
h
m
u
s
ed
,
fi
n
d
o
u
t
t
h
e
s
ec
r
e
t
k
ey
,
a
n
d
ev
e
n
r
ec
o
v
e
r
t
h
e
s
ec
r
et
me
s
s
ag
e
T
h
e
fi
rs
t
o
b
j
ec
t
i
v
e
o
f
t
h
i
s
s
t
u
d
y
i
s
t
o
s
ee
h
o
w
m
u
ch
i
n
fl
u
e
n
ce
o
p
t
i
mi
zat
i
o
n
an
d
ac
t
i
v
at
i
o
n
f
u
n
c
t
i
o
n
h
av
e
o
n
t
h
e
m
u
l
t
i
-
l
a
y
er
p
e
r
ce
p
t
ro
n
(
ML
P
)
mo
d
el
i
n
p
e
rfo
r
m
i
n
g
c
r
y
p
t
an
al
y
s
i
s
.
T
h
e
s
ec
o
n
d
r
e
s
e
ar
c
h
o
b
j
ec
t
i
v
e,
w
h
i
ch
i
s
t
o
c
o
m
p
ar
e
t
h
e
p
e
rf
o
r
m
an
ce
o
f
c
r
y
p
t
an
al
y
s
i
s
i
n
r
eco
v
e
ri
n
g
k
ey
s
an
d
t
h
e
p
l
ai
n
t
e
x
t
.
S
ev
e
ral
e
x
p
e
ri
men
t
s
h
a
v
e
b
ee
n
c
arri
ed
o
u
t
,
t
h
e
o
b
s
e
r
v
e
d
p
aram
e
t
e
rs
f
o
u
n
d
t
h
at
t
h
e
u
s
e
o
f
t
h
e
r
ec
t
i
f
i
e
d
l
i
n
e
ar
u
n
i
t
(
R
e
L
U
)
a
c
t
i
v
at
i
o
n
fu
n
c
t
i
o
n
a
n
d
t
h
e
A
D
A
M
o
p
t
i
mi
ze
r
i
m
p
ro
v
e
s
t
h
e
p
e
rfo
r
m
a
n
ce
o
f
d
ee
p
l
e
ar
n
i
n
g
(
DL
)
-
b
as
e
d
c
r
y
p
t
an
al
y
s
i
s
as
ev
i
d
e
n
ced
b
y
a
s
i
g
n
i
fi
c
an
t
l
y
s
m
al
l
e
r
e
rro
r
rat
e.
D
L
-
b
as
ed
c
r
y
p
t
an
a
l
y
s
i
s
w
o
r
k
s
m
o
r
e
e
ff
ec
t
i
v
el
y
i
n
r
ec
o
v
e
ri
n
g
k
ey
s
t
h
an
r
eco
v
e
ri
n
g
p
l
a
i
n
t
e
x
t
.
D
L
-
b
as
ed
c
r
y
p
t
an
a
l
y
s
i
s
m
a
n
ag
e
d
t
o
r
ec
o
v
e
r
t
h
e
k
ey
s
w
i
t
h
an
av
e
ra
g
e
l
o
s
s
o
f
0
.
0
0
7
,
an
a
v
e
rag
e
o
f
4
9
e
p
o
ch
s
,
a
n
d
an
av
e
ra
g
e
t
i
me
o
f
0
.
1
7
8
m
i
n
u
t
e
s
.
K
e
y
w
o
r
d
s
:
A
D
AM
C
r
y
pt
a
n
a
ly
s
i
s
De
e
p
l
e
a
r
ni
ng
M
u
l
t
i
-
l
a
y
e
r
pe
r
c
e
pt
r
o
n
S
-
DE
S
Th
i
s
i
s
a
n
o
p
en
a
c
ces
s
a
r
t
i
c
l
e
u
n
d
e
r
t
h
e
CC
B
Y
-
SA
l
i
cen
s
e.
C
or
r
e
s
pon
din
g
A
u
th
or
:
M
uha
m
m
a
d
A
k
m
a
l
R
e
ml
i
F
a
c
u
l
t
y
o
f
Da
t
a
S
c
i
e
n
c
e
a
n
d
C
o
m
put
i
n
g,
Uni
ve
r
s
i
t
i
M
a
l
a
y
s
i
a
K
e
l
a
n
t
a
n
K
e
l
a
n
t
a
n
,
M
a
l
a
y
s
i
a
E
m
a
i
l
:
a
k
m
a
l
@u
m
k.
e
du.
m
y
1.
I
NT
RODU
C
T
I
ON
C
r
y
pt
o
gr
a
phy
i
s
t
h
e
s
t
ud
y
o
f
t
e
c
hni
que
s
t
o
a
s
c
e
r
t
a
i
n
c
o
nf
i
de
n
t
i
a
li
t
y
a
n
d
o
r
a
u
t
h
e
n
t
i
c
i
t
y
o
f
i
nf
or
m
a
t
i
on
.
C
r
y
p
tog
r
a
p
h
y
r
e
s
e
a
r
c
h
p
r
i
m
a
r
i
l
y
f
oc
u
s
e
s
on
tw
o
a
r
e
a
s
:
c
r
y
p
tog
r
a
p
h
i
c
d
e
s
i
gn
a
n
d
c
r
y
p
ta
n
a
l
y
s
i
s
[
1
]
.
C
r
y
pt
a
n
a
ly
s
i
s
,
c
o
m
m
o
nly
k
n
o
wn
a
s
“
c
o
de
-
b
r
e
a
k
i
ng,
”
i
nv
o
l
v
e
s
t
e
c
h
ni
qu
e
s
to
de
c
i
p
h
e
r
e
n
c
r
y
pt
e
d
i
nf
o
r
m
a
t
i
o
n
.
C
r
y
pt
a
n
a
ly
s
i
s
i
s
t
h
e
t
e
c
h
ni
que
s
us
e
d
f
o
r
de
c
i
p
h
e
r
i
ng
a
m
e
s
s
a
g
e
w
i
t
h
o
u
t
a
ny
kn
o
w
l
e
dge
o
f
t
h
e
e
n
c
i
p
h
e
r
i
ng
[
2]
.
E
xi
s
t
i
n
g
c
r
y
pt
a
na
ly
t
i
c
t
e
c
hni
que
s
n
o
l
o
n
ge
r
w
o
r
k
o
n
n
e
w
a
l
go
r
i
t
hm
s
[
3]
.
T
r
a
di
t
i
o
n
a
l
c
r
y
pt
a
n
a
ly
s
i
s
t
e
c
h
ni
que
s
t
e
n
d
to
r
e
qui
r
e
a
l
a
r
ge
a
m
o
un
t
o
f
t
i
me
a
n
d
r
e
s
o
ur
c
e
s
s
o
t
h
a
t
t
h
e
y
a
r
e
n
ot
c
o
m
pa
t
i
bl
e
w
i
t
h
n
e
w
a
l
go
r
i
t
hm
s
,
s
o
a
n
e
w
c
r
y
pt
a
n
a
ly
s
i
s
t
e
c
hni
que
i
s
n
e
e
de
d
[
4]
.
A
dv
a
nc
e
m
e
n
t
s
i
n
m
a
c
hi
ne
l
e
a
r
nin
g
(
M
L
)
t
e
c
h
n
o
l
o
g
y
o
f
f
e
r
a
n
e
w
d
i
r
e
c
t
i
o
n
f
o
r
c
r
y
pt
o
g
r
a
phy
a
n
d
c
r
y
pt
a
na
ly
s
i
s
[
5]
.
T
h
e
c
o
n
n
e
c
t
i
o
n
b
e
t
we
e
n
c
r
y
pt
o
g
r
a
phy
a
n
d
M
L
wa
s
i
ni
t
i
a
l
ly
i
n
t
r
o
duc
e
d
i
n
1991
[
6
]
.
S
i
n
c
e
t
h
e
n
,
n
u
m
e
r
o
us
r
e
s
e
a
r
c
h
e
r
s
h
a
v
e
e
x
p
l
o
r
e
d
us
i
n
g
M
L
t
e
c
h
ni
qu
e
s
to
c
o
n
duc
t
c
r
y
pt
a
na
l
y
s
i
s
o
n
bl
o
c
k
c
i
p
h
e
r
s
.
S
e
v
e
r
a
l
M
L
r
e
s
e
a
r
c
h
i
n
t
h
e
f
i
e
l
d
o
f
c
r
y
pt
a
n
a
ly
s
i
s
wa
s
c
a
r
r
i
e
d
o
u
t
to
gue
s
s
or
i
de
n
t
i
f
y
t
h
e
c
r
y
pt
o
gr
a
phi
c
a
l
go
r
i
t
hm
us
e
d,
gue
s
s
t
h
e
S
-
B
o
x
,
f
i
nd
o
u
t
t
h
e
s
e
c
r
e
t
ke
y
a
n
d
e
v
e
n
r
e
c
o
v
e
r
t
h
e
s
e
c
r
e
t
m
e
s
s
a
ge
[
4]
,
[
7]
,
[
8]
.
B
a
s
e
d
o
n
pr
e
vi
o
us
s
t
ud
i
e
s
,
A
I
c
a
pa
bil
i
t
i
e
s
,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2
5
0
2
-
4
7
52
In
do
n
e
s
i
a
n
J
E
l
e
c
E
n
g
&
C
o
m
p
S
c
i
,
Vo
l
.
3
8
,
N
o
.
2
,
M
a
y
20
2
5
:
1
115
-
1
123
1116
e
s
pe
c
i
a
ll
y
i
n
t
h
e
f
i
e
l
d
o
f
de
e
p
l
e
a
r
ni
ng
(
DL
)
f
o
r
c
r
y
pt
a
n
a
ly
s
i
s
,
a
r
e
c
o
n
s
i
de
r
e
d
qu
i
t
e
e
f
f
e
c
t
i
v
e
a
ga
i
ns
t
e
xi
s
t
i
n
g
a
l
go
r
i
t
hm
s
[
4]
,
[
3]
,
[
9
]
.
R
e
s
e
a
r
c
h
ut
i
li
z
i
ng
DL
f
o
r
c
r
y
pt
a
n
a
ly
s
i
s
i
s
o
f
t
e
n
f
o
un
d
i
n
t
h
e
c
o
n
t
e
x
t
o
f
kn
o
wn
-
p
l
a
i
n
t
e
x
t
a
tt
a
c
k
(
K
P
A
)
,
wh
e
r
e
t
h
e
a
t
t
a
c
ke
r
h
a
s
a
c
c
e
s
s
t
o
pa
i
r
s
o
f
p
l
a
i
n
t
e
x
t
a
n
d
c
i
p
h
e
r
t
e
x
t
,
a
n
d
t
h
e
n
u
s
e
s
t
hi
s
i
n
f
o
r
m
a
t
i
o
n
t
o
r
e
c
o
v
e
r
t
h
e
ke
y
.
[
4]
,
[
9]
,
[
10]
–
[
16]
.
P
r
e
vi
o
us
r
e
s
e
a
r
c
h
i
n
r
e
c
o
v
e
r
p
l
a
i
n
t
e
x
t
[
1]
t
h
e
e
x
pe
r
im
e
n
t
a
l
r
e
s
u
l
t
s
s
h
o
w
t
h
a
t
t
h
e
n
e
ur
a
l
ne
t
wor
k
m
o
de
l
de
v
e
l
o
pe
d
i
n
t
hi
s
p
a
pe
r
a
c
hi
e
ve
s
e
x
c
e
ll
e
n
t
r
e
s
u
l
t
s
i
n
r
e
s
t
o
r
i
n
g
p
l
a
i
n
t
e
x
t
,
wi
t
h
a
f
i
t
t
i
n
g
a
c
c
ur
a
c
y
e
xc
e
e
d
i
ng
90%
c
o
m
pa
r
e
d
to
t
h
e
a
c
t
ua
l
p
l
a
i
n
t
e
x
t
.
F
ut
u
r
e
w
o
r
k
wi
ll
i
nv
o
l
ve
f
ur
t
h
e
r
r
e
f
i
ne
m
e
n
t
i
n
s
e
l
e
c
t
i
n
g
a
n
d
a
da
pt
i
n
g
ne
ur
a
l
n
e
t
wor
k
we
i
g
h
t
s
dur
i
n
g
t
r
a
i
ni
ng.
T
h
e
r
e
m
a
y
b
e
a
l
t
e
r
na
t
i
v
e
t
y
pe
s
o
f
n
e
ur
a
l
n
e
t
wo
r
ks
f
o
r
c
r
y
pt
a
n
a
ly
s
i
s
t
h
a
t
c
o
ul
d
y
i
e
l
d
s
ur
pr
i
s
i
ng
o
u
t
c
o
m
e
s
.
A
l
o
t
o
f
e
x
p
e
r
i
m
e
n
t
s
[
17]
us
i
ng
v
a
r
i
e
d
da
t
a
s
e
t
s
,
ke
y
s
,
a
n
d
n
e
ur
a
l
n
e
t
wo
r
k
t
y
pe
s
a
r
e
pl
a
nn
e
d,
w
i
t
h
t
h
e
a
i
m
o
f
pe
r
f
o
r
m
i
ng
kn
o
wn
c
i
p
h
e
r
t
e
x
t
a
tt
a
c
ks
t
h
r
o
u
gh
ML
a
l
go
r
i
t
hm
s
,
s
pe
c
i
f
i
c
a
ll
y
l
e
ve
r
a
g
i
n
g
n
e
ur
a
l
n
e
t
wo
r
ks
.
R
e
s
e
a
r
c
h
f
o
c
us
e
d
o
n
r
e
c
o
v
e
r
i
n
g
ke
y
s
o
n
t
h
e
S
-
DE
S
a
l
go
r
i
t
hm
w
a
s
c
o
n
duc
t
e
d
[
9]
,
[
16
]
wh
e
r
e
t
h
e
a
c
c
ur
a
c
y
a
c
hi
e
v
e
d
80%
.
B
a
s
e
d
o
n
t
h
e
r
e
s
u
l
t
s
o
f
t
h
e
a
ut
h
or
’
s
s
e
a
r
c
h
,
m
a
ny
c
r
y
pt
a
n
a
ly
s
e
s
o
f
p
l
a
i
n
t
e
x
t
a
n
d
ke
y
r
e
c
o
v
e
r
y
we
r
e
f
o
u
n
d
to
b
e
a
l
m
o
s
t
b
a
l
a
n
c
e
d,
wh
e
r
e
t
h
e
pur
p
o
s
e
of
b
o
t
h
c
r
y
pt
a
na
l
y
s
e
s
i
s
t
h
e
s
a
m
e
to
r
e
c
o
v
e
r
t
h
e
s
e
c
r
e
t
ke
y
.
T
hi
s
r
e
s
e
a
r
c
h
i
s
to
c
o
n
duc
t
o
n
wh
a
t
c
r
y
pt
a
n
a
ly
s
i
s
m
e
t
h
o
d
i
s
m
o
s
t
e
f
f
e
c
t
i
v
e
by
c
o
m
pa
r
i
n
g
t
h
e
t
w
o
t
y
pe
s
o
f
c
r
y
pt
a
n
a
ly
s
e
s
.
I
n
t
hi
s
s
t
ud
y
,
t
h
e
a
ut
h
o
r
us
e
s
t
h
e
m
u
l
t
i
-
l
a
y
e
r
pe
r
c
e
p
t
r
o
n
(
M
L
P
)
n
e
ur
a
l
n
e
t
wo
r
k
m
o
de
l
w
hi
c
h
h
a
s
hi
g
h
e
r
a
c
c
ur
a
c
y
c
o
m
p
a
r
e
d
to
c
o
n
v
o
l
ut
i
o
n
a
l
n
e
ur
a
l
n
e
t
wo
r
k
(
C
NN
)
a
n
d
l
o
n
g
s
h
o
r
t
-
t
e
r
m
m
e
m
o
r
y
(
L
S
T
M
)
[
9]
.
T
r
a
i
ni
ng
n
e
ur
a
l
n
e
t
wo
r
k
a
r
c
hi
t
e
c
t
ur
e
s
s
uc
h
a
s
M
L
P
c
a
n
b
e
f
o
r
m
u
l
a
t
e
d
a
s
o
p
t
i
mi
z
a
t
i
o
n
pr
o
bl
e
ms
;
h
e
n
c
e
,
t
h
e
y
c
a
n
b
e
s
o
l
v
e
d
by
s
o
m
e
o
p
t
i
mi
z
a
t
i
o
n
m
e
t
h
o
ds
[
18]
.
A
DA
M
r
e
pr
e
s
e
n
t
s
t
h
e
l
a
t
e
s
t
tr
e
n
ds
i
n
DL
o
p
t
i
mi
z
a
t
i
o
n
[
19]
,
[
20]
.
M
o
r
e
m
e
m
o
r
y
e
f
f
i
c
i
e
n
t
a
nd
l
e
s
s
c
o
m
put
a
t
i
o
n
a
l
po
we
r
a
r
e
t
w
o
a
dv
a
n
t
a
ge
s
o
f
A
D
AM
.
A
D
AM
i
s
us
e
d
to
m
o
d
i
f
y
t
h
e
we
i
g
h
t
s
to
m
i
n
im
ize
l
o
s
s
e
s
o
n
t
h
e
n
e
t
wo
r
k.
I
n
t
hi
s
s
t
ud
y
,
we
f
o
c
us
o
n
t
h
e
S
-
DE
S
c
i
p
h
e
r
,
whi
c
h
,
de
s
p
i
t
e
i
t
s
s
i
m
p
li
c
i
t
y
,
e
f
f
e
c
t
i
ve
ly
e
n
c
a
ps
u
l
a
t
e
s
t
h
e
c
o
r
e
p
r
i
nc
i
p
l
e
s
o
f
i
t
s
m
o
r
e
c
o
m
p
l
e
x
pr
e
de
c
e
s
s
o
r
s
.
T
h
e
f
i
r
s
t
o
bj
e
c
t
i
v
e
o
f
t
hi
s
s
t
ud
y
i
s
to
s
e
e
h
o
w
m
uc
h
i
nf
l
u
e
n
c
e
o
p
t
i
mi
z
a
t
i
o
n
a
n
d
a
c
t
i
v
a
t
i
o
n
f
u
n
c
t
i
o
n
h
a
v
e
o
n
t
h
e
M
L
P
m
o
de
l
i
n
pe
r
f
o
r
m
i
ng
c
r
y
pt
a
n
a
ly
s
i
s
.
T
h
e
s
e
c
o
n
d
r
e
s
e
a
r
c
h
o
bj
e
c
t
i
v
e
,
w
hi
c
h
i
s
t
o
c
o
m
pa
r
e
t
h
e
pe
r
f
o
r
m
a
n
c
e
o
f
c
r
y
pt
a
n
a
ly
s
i
s
i
n
r
e
c
o
v
e
r
i
ng
ke
y
s
a
n
d
t
h
e
p
l
a
i
n
t
e
x
t
.
S
o
m
e
o
f
t
h
e
pa
r
a
m
e
t
e
r
s
t
h
a
t
w
i
ll
be
o
b
s
e
r
ve
d
a
r
e
l
o
s
s
,
e
po
c
h
a
n
d
t
h
e
t
i
m
e
t
a
ke
f
o
r
t
h
e
c
r
y
pt
a
n
a
ly
s
i
s
pr
o
c
e
s
s
to
r
un
.
T
h
e
c
o
n
t
r
i
b
u
t
i
o
n
s
o
f
t
hi
s
r
e
s
e
a
r
c
h
a
r
e
:
i
)
t
o
s
e
e
h
o
w
m
uc
h
i
nf
l
ue
n
c
e
o
p
ti
mi
z
a
t
i
o
n
a
n
d
a
c
t
i
v
a
t
i
o
n
f
u
n
c
t
i
o
n
s
h
a
ve
o
n
t
h
e
M
L
P
m
o
de
l
i
n
p
e
r
f
o
r
m
i
ng
c
r
y
pt
a
n
a
ly
s
i
s
;
ii
)
t
o
c
o
m
pa
r
e
c
r
y
pt
a
na
l
y
s
i
s
i
n
t
e
r
m
s
o
f
r
e
c
o
v
e
r
i
n
g
ke
y
s
a
n
d
p
l
a
i
n
t
e
x
t
i
n
t
e
r
m
s
o
f
t
i
m
e
,
e
po
c
h
a
n
d
a
c
c
ur
a
c
y
T
hi
s
r
e
s
e
a
r
c
h
o
f
f
e
r
s
v
a
l
ua
bl
e
i
ns
i
g
h
t
s
i
n
t
o
t
h
e
a
pp
l
i
c
a
t
i
o
n
o
f
DL
m
o
de
l
s
f
o
r
c
r
y
pt
a
n
a
ly
s
i
s
,
s
h
o
wc
a
s
i
ng
t
h
e
i
r
po
t
e
n
t
i
a
l
i
n
b
r
e
a
k
i
ng
do
wn
c
o
m
p
l
e
x
e
nc
r
y
pt
i
o
n
s
c
h
e
m
e
s
.
T
hi
s
r
e
s
e
a
r
c
h
d
i
s
c
us
s
e
s
c
r
y
pt
a
n
a
ly
s
i
s
f
o
r
r
e
c
o
v
e
r
i
n
g
p
l
a
i
n
t
e
x
t
a
n
d
ke
y
s
.
Al
t
h
o
ugh
t
h
e
r
e
h
a
v
e
b
e
e
n
s
t
ud
i
e
s
o
n
t
hi
s
to
pi
c
,
th
e
y
h
a
ve
t
y
p
i
c
a
ll
y
b
e
e
n
c
o
n
duc
t
e
d
s
e
pa
r
a
t
e
l
y
a
n
d
n
o
n
e
h
a
v
e
e
x
p
li
c
i
t
ly
a
ddr
e
s
s
e
d
a
c
o
m
pa
r
i
s
o
n
o
f
t
h
e
a
n
a
ly
z
e
d
o
bj
e
c
t
s
.
B
y
de
m
o
n
s
t
r
a
t
i
n
g
h
o
w
t
h
e
s
e
a
d
v
a
n
c
e
d
a
l
go
r
i
t
hm
s
c
a
n
b
e
l
e
v
e
r
a
ge
d
to
a
n
a
ly
z
e
a
n
d
pot
e
n
t
i
a
ll
y
c
o
m
pr
o
m
i
s
e
c
r
y
pt
o
g
r
a
phi
c
s
y
s
t
e
m
s
,
t
h
e
s
t
udy
pa
v
e
s
t
h
e
wa
y
f
o
r
a
pp
l
yi
ng
s
i
mi
l
a
r
t
e
c
h
ni
que
s
to
ot
h
e
r
t
y
pe
s
o
f
c
i
p
he
r
s
.
F
ur
t
h
e
r
m
o
r
e
,
i
t
e
s
t
a
bl
i
s
he
s
a
s
o
l
i
d
f
o
un
da
t
i
o
n
f
o
r
f
ut
ur
e
r
e
s
e
a
r
c
h
i
n
b
o
t
h
c
y
be
r
s
e
c
ur
i
t
y
a
n
d
c
r
y
pt
o
gr
a
phy
,
hi
g
hli
g
h
t
i
n
g
t
h
e
n
e
e
d
f
o
r
c
o
n
t
i
n
u
e
d
e
x
p
l
o
r
a
t
i
o
n
o
f
h
o
w
a
r
t
i
f
i
c
i
a
l
i
n
t
e
ll
i
ge
n
c
e
a
n
d
ML
c
a
n
e
nha
n
c
e
o
u
r
un
de
r
s
t
a
n
d
i
ng
a
n
d
c
a
pa
bil
i
t
i
e
s
i
n
t
he
s
e
c
r
i
t
i
c
a
l
f
i
e
l
ds
.
T
hi
s
wo
r
k
n
ot
o
nl
y
c
o
n
t
r
i
b
ut
e
s
to
t
h
e
a
dva
n
c
e
m
e
n
t
o
f
c
r
y
pt
a
n
a
ly
t
i
c
m
e
t
h
o
ds
b
ut
a
l
s
o
e
n
c
o
ur
a
ge
s
t
h
e
de
v
e
l
o
p
m
e
n
t
o
f
m
o
r
e
r
o
b
us
t
s
e
c
ur
i
t
y
m
e
a
s
ur
e
s
a
ga
i
ns
t
e
m
e
r
g
i
ng
t
h
r
e
a
t
s
.
2.
L
I
T
E
RA
T
UR
E
RE
VI
E
W
2.
1
.
Cr
yp
t
an
al
ys
is
C
r
y
pt
o
gr
a
phy
i
s
a
wa
y
to
e
n
s
ur
e
t
h
e
s
e
c
ur
i
t
y
o
f
i
nf
o
r
m
a
t
i
o
n
b
e
t
we
e
n
c
o
m
m
u
ni
c
a
t
i
n
g
pa
r
t
i
e
s
[
21]
.
C
r
y
pt
o
gr
a
phy
i
nc
l
ude
s
c
r
y
pt
o
g
r
a
phy
a
n
d
c
r
y
pt
a
n
a
ly
s
i
s
[
22]
.
A
n
a
ly
t
i
c
a
l
c
r
i
t
i
c
i
s
m
i
s
k
n
o
wn
a
s
“
b
r
e
a
k
i
n
g
t
h
e
c
o
de
”
.
C
r
y
pt
a
na
l
y
s
i
s
i
s
a
m
e
t
h
o
d
us
e
d
by
a
t
t
a
c
k
e
r
s
to
a
c
c
e
s
s
i
nf
o
r
m
a
t
i
o
n
w
i
t
h
o
u
t
kn
o
wi
n
g
t
h
e
s
e
c
r
e
t
ke
y
us
e
d
[
23]
.
C
r
y
pt
a
n
a
ly
s
i
s
w
i
t
h
a
po
s
i
t
i
ve
d
i
r
e
c
t
i
o
n
c
a
n
b
e
us
e
d
a
s
a
m
e
t
h
o
d
to
e
v
a
l
u
a
t
e
t
h
e
s
e
c
ur
i
t
y
l
e
v
e
l
o
f
c
r
y
pt
o
g
r
a
phi
c
a
l
go
r
i
t
hm
s
s
o
a
s
to
f
i
nd
we
a
k
n
e
s
s
e
s
i
n
o
r
de
r
to
i
m
pr
o
v
e
f
ut
ur
e
de
v
e
l
o
p
m
e
n
t
di
r
e
c
t
i
o
ns
.
C
r
i
t
i
c
a
l
a
n
a
ly
s
i
s
c
a
n
a
l
s
o
pr
e
v
e
n
t
t
h
e
us
e
o
f
i
ns
e
c
u
r
e
a
l
go
r
i
t
hm
s
f
o
r
r
e
a
l
c
o
m
m
u
ni
c
a
t
i
o
n
.
2.
2
.
M
L
P
M
P
L
a
t
y
pe
o
f
f
e
e
d
f
o
r
wa
r
d
a
r
t
i
f
i
c
i
a
l
ne
ur
a
l
ne
t
wor
k
(
A
NN
)
,
i
s
a
n
a
l
go
r
i
t
hm
f
o
r
s
upe
r
vi
s
e
d
l
e
a
r
ni
ng.
I
t
i
s
o
f
t
e
n
r
e
ga
r
de
d
a
s
t
h
e
f
o
un
da
t
i
o
n
a
l
a
r
c
hi
t
e
c
t
ur
e
f
o
r
DL
o
r
de
e
p
n
e
ur
a
l
ne
t
wor
ks
(
DN
N)
.
T
y
p
i
c
a
ll
y
,
a
n
M
L
P
i
s
a
f
u
ll
y
c
o
nn
e
c
t
e
d
n
e
t
w
o
r
k
c
o
m
pr
i
s
i
ng
a
n
i
n
put
l
a
y
e
r
t
h
a
t
h
a
n
d
l
e
s
t
h
e
i
n
c
o
m
i
ng
da
t
a
,
a
n
o
u
t
pu
t
l
a
y
e
r
r
e
s
po
n
s
i
b
l
e
f
o
r
m
a
k
i
ng
de
c
i
s
i
o
n
s
o
r
pr
e
di
c
t
i
o
n
s
a
b
o
ut
t
h
e
i
n
put
,
a
n
d
o
n
e
o
r
m
o
r
e
hi
dde
n
l
a
y
e
r
s
po
s
i
t
i
o
n
e
d
be
t
we
e
n
t
h
e
s
e
t
wo,
whi
c
h
a
r
e
vi
e
we
d
a
s
t
h
e
c
o
r
e
c
o
m
put
a
t
i
o
n
a
l
e
l
e
m
e
n
t
s
o
f
t
h
e
n
e
t
wo
r
k.
M
L
P
e
m
p
l
o
y
s
a
s
upe
r
vi
s
e
d
l
e
a
r
ni
ng
m
e
t
h
o
d
kn
o
wn
a
s
“
B
a
c
kpr
o
pa
ga
t
i
o
n
”
f
o
r
i
t
s
t
r
a
i
ni
ng,
whi
c
h
i
s
c
o
n
s
i
de
r
e
d
a
c
r
uc
i
a
l
c
o
m
po
n
e
n
t
o
f
ne
ur
a
l
n
e
t
wo
r
ks
a
n
d
i
s
wi
de
ly
ut
i
li
z
e
d
f
o
r
tr
a
i
ni
ng
f
e
e
d
f
o
r
wa
r
d
n
e
ur
a
l
ne
t
w
o
r
ks
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
do
n
e
s
i
a
n
J
E
l
e
c
E
n
g
&
C
o
m
p
S
c
i
I
S
S
N:
2
5
0
2
-
4
7
52
De
e
p
lear
ning
-
bas
e
d
c
r
y
ptanal
y
s
is
in
r
e
c
ov
e
r
ing
t
he
s
e
c
r
e
t
k
e
y
and
plai
ntex
t
on
…
(
Y
uli
a
F
atma
)
1117
T
h
e
m
a
i
n
go
a
l
o
f
b
a
c
kpr
o
pa
ga
t
i
o
n
i
s
to
a
dj
us
t
t
h
e
n
e
t
wo
r
k
we
i
g
h
t
s
to
e
f
f
e
c
t
i
v
e
l
y
m
a
p
i
n
put
s
to
t
h
e
de
s
i
r
e
d
o
u
t
pu
t
s
.
M
L
P
i
s
a
f
f
e
c
t
e
d
by
f
e
a
t
ur
e
s
c
a
l
i
ng
a
n
d
r
e
qu
i
r
e
s
t
uni
ng
va
r
i
o
us
hy
p
e
r
pa
r
a
m
e
t
e
r
s
s
uc
h
a
s
t
h
e
n
u
m
be
r
o
f
hi
dd
e
n
l
a
y
e
r
s
,
n
e
ur
o
n
s
,
a
n
d
i
t
e
r
a
t
i
o
ns
,
whi
c
h
c
a
n
m
a
ke
i
t
c
o
m
put
a
t
i
o
n
a
ll
y
i
n
t
e
ns
i
ve
f
o
r
s
o
l
vi
ng
c
o
m
p
l
e
x
s
e
c
ur
i
t
y
m
o
de
l
s
.
No
n
e
t
h
e
l
e
s
s
,
M
L
P
i
s
a
d
va
n
t
a
ge
o
us
i
n
l
e
a
r
ni
ng
n
o
n
-
l
i
ne
a
r
m
o
de
l
s
,
e
v
e
n
i
n
r
e
a
l
-
t
i
m
e
o
r
o
nl
i
ne
l
e
a
r
ni
ng
s
c
e
n
a
r
i
o
s
,
by
u
s
i
ng
pa
r
t
i
a
l
f
i
t
[
24]
.
2.
3
.
S
im
p
l
if
ied
d
at
a
e
n
c
r
yp
t
ion
s
t
an
d
ar
d
(
S
-
DE
S
)
S
-
DE
S
i
s
a
s
im
p
l
if
i
e
d
v
e
r
s
i
o
n
o
f
t
h
e
DE
S
a
l
go
r
i
t
hm
.
W
hil
e
i
t
s
ha
r
e
s
c
h
a
r
a
c
t
e
r
i
s
t
i
c
s
w
i
t
h
DE
S
,
i
t
us
e
s
a
s
m
a
ll
e
r
bl
o
c
k
s
i
z
e
a
n
d
ke
y
,
o
pe
r
a
t
i
n
g
o
n
8
-
bi
t
m
e
s
s
a
ge
bl
o
c
k
s
w
i
t
h
a
10
-
b
i
t
ke
y
.
T
h
e
a
l
go
r
i
t
hm
pr
o
duc
e
s
a
n
8
-
bi
t
c
i
p
h
e
r
t
e
x
t
bl
o
c
k
a
s
o
u
t
pu
t.
T
h
e
de
c
r
y
pt
i
o
n
pr
o
c
e
s
s
i
s
s
im
i
l
a
r
t
o
e
n
c
r
y
pt
i
o
n
,
w
i
t
h
t
h
e
pr
i
m
a
r
y
d
i
s
t
i
n
c
t
i
o
n
b
e
i
ng
t
h
a
t
t
h
e
s
t
e
ps
a
r
e
e
x
e
c
ut
e
d
i
n
r
e
v
e
r
s
e
o
r
de
r
[
14]
.
S
-
DE
S
wa
s
de
s
i
g
n
e
d
a
s
a
t
e
s
t
bl
o
c
k
c
i
p
h
e
r
f
o
r
l
e
a
r
ni
ng
a
b
o
ut
m
o
de
r
n
c
r
y
pt
a
n
a
ly
t
i
c
t
e
c
hni
que
s
[
25]
.
2.
4
.
AD
AM
o
p
t
im
iz
at
ion
T
hi
s
a
l
go
r
i
t
hm
o
pt
i
m
i
z
e
s
s
t
o
c
h
a
s
t
i
c
o
bj
e
c
t
i
v
e
f
u
nc
t
i
o
n
s
us
i
ng
a
f
i
r
s
t
-
or
de
r
gr
a
di
e
n
t
-
b
a
s
e
d
a
ppr
o
a
c
h
t
h
a
t
r
e
l
i
e
s
o
n
a
da
pt
i
v
e
e
s
t
i
m
a
t
e
s
o
f
l
o
we
r
-
o
r
de
r
m
o
m
e
n
t
s
.
I
t
i
s
e
a
s
y
to
i
m
p
l
e
m
e
n
t
,
c
o
m
put
a
t
i
o
n
a
ll
y
e
f
f
i
c
i
e
n
t
,
r
e
qu
i
r
e
s
m
i
n
im
a
l
m
e
m
o
r
y
,
a
n
d
r
e
m
a
i
ns
un
a
f
f
e
c
t
e
d
by
d
i
a
go
n
a
l
r
e
s
c
a
l
i
ng
o
f
gr
a
d
i
e
n
t
s
.
I
t
i
s
pa
r
ti
c
u
l
a
r
l
y
e
f
f
e
c
t
i
v
e
f
o
r
l
a
r
ge
-
s
c
a
l
e
pr
o
bl
e
m
s
i
nv
o
l
v
i
ng
e
x
t
e
ns
i
ve
da
t
a
o
r
n
u
m
e
r
o
us
pa
r
a
m
e
t
e
r
s
a
n
d
pe
r
f
o
r
m
s
we
l
l
w
i
t
h
n
o
n
-
s
t
a
t
i
o
n
a
r
y
o
bj
e
c
t
i
v
e
s
o
r
wh
e
n
gr
a
d
i
e
n
t
s
a
r
e
h
i
g
hly
n
o
i
s
y
o
r
s
pa
r
s
e
.
A
dd
i
t
i
o
n
a
ll
y
,
t
h
e
hy
p
er
-
pa
r
a
m
e
t
e
r
s
a
r
e
i
n
t
u
i
t
i
v
e
ly
m
e
a
ni
ng
f
u
l
a
n
d
ge
n
e
r
a
l
ly
n
e
e
d
mi
n
im
a
l
a
d
j
us
t
m
e
n
t
[
26]
.
2.
5
.
Ac
t
iva
t
ion
f
u
n
c
t
ion
T
h
e
a
c
t
i
va
t
i
o
n
f
u
n
c
t
i
o
n
de
t
e
r
m
i
ne
s
w
h
e
t
h
e
r
t
h
e
n
e
ur
o
n
i
s
a
c
t
i
v
a
t
e
d.
T
hi
s
m
e
a
n
s
us
i
ng
s
im
p
l
e
r
m
a
t
h
e
m
a
t
i
c
a
l
o
pe
r
a
t
i
o
n
s
to
de
t
e
r
m
i
ne
w
h
e
t
h
e
r
th
e
i
n
put
o
f
n
e
ur
o
n
s
to
t
h
e
n
e
t
wor
k
i
s
i
m
po
r
t
a
n
t
i
n
t
h
e
pr
e
d
i
c
t
i
o
n
pr
o
c
e
s
s
.
T
h
e
r
o
l
e
o
f
t
h
e
a
c
t
i
v
a
t
i
o
n
f
u
n
c
t
i
o
n
i
s
to
ge
t
t
h
e
o
u
t
pu
t
o
f
a
s
e
t
o
f
i
n
put
v
a
l
ue
s
s
u
pp
l
i
e
d
to
t
h
e
n
o
de
(
or
l
a
y
e
r
[
27]
.
R
e
c
t
i
f
i
e
d
l
i
ne
a
r
u
ni
t
(
R
e
L
U
)
,
m
a
y
a
pp
e
a
r
to
b
e
a
l
i
ne
a
r
f
u
n
c
t
i
o
n
,
y
e
t
i
t
h
a
s
a
de
r
i
v
a
t
i
v
e
t
h
a
t
s
uppo
r
t
s
b
a
c
kpr
o
pa
ga
t
i
o
n
,
m
a
k
i
ng
i
t
b
ot
h
c
o
m
put
a
t
i
o
n
a
l
ly
e
f
f
i
c
i
e
n
t
a
n
d
s
u
i
t
a
bl
e
f
o
r
t
r
a
i
ni
ng
n
e
ur
a
l
n
e
t
wo
r
ks
.
M
a
t
h
e
m
a
t
i
c
a
ll
y
i
t
c
a
n
b
e
r
e
pr
e
s
e
n
t
e
d
a
s
(
)
=
m
a
x
(
0
,
)
.
A
ke
y
a
s
pe
c
t
o
f
t
h
e
R
e
L
U
f
u
n
c
t
i
o
n
i
s
t
h
a
t
i
t
d
o
e
s
n
o
t
a
c
t
i
v
a
t
e
a
l
l
n
e
ur
o
n
s
s
i
mu
l
t
a
n
e
o
us
ly
;
ne
ur
o
n
s
b
e
c
o
m
e
i
na
c
t
i
v
e
o
nly
i
f
t
h
e
o
ut
pu
t
o
f
t
h
e
l
i
ne
a
r
t
r
a
n
s
f
o
r
m
a
t
i
o
n
i
s
b
e
l
o
w
z
e
r
o
.
L
e
a
k
y
R
e
L
U
e
nh
a
n
c
e
s
t
h
e
R
e
L
U
f
u
n
c
t
i
o
n
by
a
ddr
e
s
s
i
n
g
t
he
d
y
i
ng
R
e
L
U
i
s
s
u
e
,
a
s
i
t
i
n
t
r
o
duc
e
s
a
s
m
a
l
l
po
s
i
t
i
v
e
s
l
o
pe
i
n
t
h
e
n
e
ga
t
i
v
e
r
e
g
i
o
n
.
M
a
t
h
e
m
a
t
i
c
a
ll
y
i
t
c
a
n
b
e
r
e
pr
e
s
e
n
t
e
d
a
s
(
)
=
m
a
x
(
0
.
1
,
)
.
I
t
s
o
u
t
pu
t
i
s
n
o
t
0
f
o
r
n
e
ga
t
i
v
e
i
n
p
ut
s
,
s
o
i
t
i
s
t
h
e
i
m
pr
o
v
e
m
e
n
t
o
f
R
e
L
u
f
u
n
c
t
i
o
n
f
o
r
t
h
e
pr
o
bl
e
m
o
f
“
D
yi
ng
R
e
L
u
”
.
3.
RE
S
E
AR
CH
M
E
T
HO
D
T
h
e
r
e
s
e
a
r
c
h
m
e
t
h
o
d
o
u
t
l
i
ne
s
t
h
e
r
e
s
e
a
r
c
h
f
r
a
m
e
w
o
r
k
i
n
t
h
i
s
s
t
udy
.
T
h
e
f
r
a
m
e
wo
r
k
pr
e
s
e
n
t
s
s
t
e
p
by
s
t
e
p
pr
o
c
e
dur
e
s
to
b
e
c
a
r
r
i
e
d
o
ut
a
t
e
a
c
h
s
t
a
ge
o
f
t
h
e
r
e
s
e
a
r
c
h
.
T
he
c
o
n
c
e
pt
o
f
DL
f
o
r
c
r
y
pt
a
n
a
ly
s
is
i
n
t
hi
s
s
t
udy
c
o
n
s
i
s
t
o
f
t
w
o
e
x
pe
r
i
m
e
n
t
s
,
r
e
c
o
v
e
r
i
n
g
t
h
e
s
e
c
r
e
t
ke
y
a
n
d
r
e
c
o
v
e
r
i
n
g
t
h
e
pl
a
i
n
t
e
x
t
.
T
h
e
e
x
pe
c
t
e
d
r
e
s
ul
t
i
s
a
c
o
m
p
a
r
i
s
o
n
o
f
t
h
e
l
e
ve
l
o
f
a
c
c
ur
a
c
y
,
t
i
m
e
r
e
q
u
i
r
e
d
a
n
d
t
h
e
r
e
s
u
l
t
i
n
g
l
o
s
s
.
T
h
e
ut
i
li
z
e
d
r
e
s
e
a
r
c
h
m
e
t
h
o
d
w
i
ll
b
e
e
x
p
l
a
i
ne
d
i
n
F
i
gur
e
1.
F
i
gur
e
1(
a
)
i
s
a
c
r
y
pt
a
n
a
ly
t
i
c
DL
c
o
n
c
e
pt
f
o
r
r
e
c
o
v
e
r
i
n
g
ke
y
s
.
T
h
e
n
e
t
wo
r
k
r
e
qu
i
r
e
s
i
nput
i
n
t
h
e
f
o
r
m
o
f
a
pa
i
r
o
f
p
l
a
i
n
t
e
x
t
a
n
d
c
i
p
h
e
r
t
e
x
t
.
T
h
e
o
u
t
pu
t
o
f
t
h
e
t
a
r
ge
t
e
d
n
e
t
wor
k
i
s
a
ke
y
.
F
i
gur
e
1(
b
)
s
h
o
ws
t
h
e
c
o
n
c
e
pt
o
f
DL
c
r
y
pt
a
n
a
ly
s
is
to
r
e
c
o
v
e
r
pl
a
i
n
t
e
x
t
.
I
n
put
o
n
t
h
e
n
e
t
wo
r
k
i
n
t
h
e
f
o
r
m
o
f
c
i
p
h
e
r
t
e
x
t
.
T
h
e
t
a
r
ge
t
e
d
o
u
t
pu
t
i
s
p
l
a
i
n
t
e
x
t
.
T
o
s
e
e
t
h
e
pe
r
f
o
r
m
a
n
c
e
o
f
DL
-
b
a
s
e
d
c
r
y
pt
a
n
a
ly
s
i
s
d
o
n
e
w
i
t
h
c
o
m
pa
r
e
t
h
e
R
e
L
u
a
n
d
L
e
a
k
y
R
e
l
u
a
c
t
i
v
a
t
i
o
n
f
u
n
c
t
i
o
n
s
.
T
o
i
m
pr
o
v
e
n
e
t
wo
r
k
a
c
c
ur
a
c
y
,
A
D
A
M
o
p
t
i
mi
z
a
t
i
o
n
i
s
a
dde
d.
M
e
a
s
ur
e
m
e
n
t
o
f
l
o
s
s
v
a
l
ue
i
s
c
a
l
c
u
l
a
ted
us
i
n
g
M
S
E
.
T
h
e
s
uc
c
e
s
s
o
f
m
o
de
l
l
e
a
r
ni
ng
i
s
l
a
r
ge
l
y
de
t
e
r
m
i
ne
d
by
t
h
e
l
o
s
s
a
c
hi
e
v
e
d
≤
0
.
01
.
(
a
)
(
b
)
F
i
g
ur
e
1
.
R
e
s
e
a
r
c
h
m
e
t
h
o
d
o
f
t
h
e
DL
-
b
a
s
e
d
c
r
y
pt
a
n
a
ly
s
(
a
)
to
b
r
e
a
k
t
h
e
ke
y
a
n
d
(
b
)
to
b
r
e
a
k
t
h
e
pl
a
i
n
t
e
x
t
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2
5
0
2
-
4
7
52
In
do
n
e
s
i
a
n
J
E
l
e
c
E
n
g
&
C
o
m
p
S
c
i
,
Vo
l
.
3
8
,
N
o
.
2
,
M
a
y
20
2
5
:
1
115
-
1
123
1118
3.
1.
E
n
c
r
yp
t
ion
u
s
in
g
S
-
DE
S
S
-
DE
S
i
s
a
s
i
m
p
li
f
i
e
d
v
e
r
s
i
o
n
o
f
t
h
e
DE
S
a
l
go
r
i
t
hm
de
s
i
g
n
e
d
f
o
r
e
duc
a
t
i
o
n
a
l
pur
po
s
e
s
.
S
-
DE
S
us
e
s
a
10
-
bi
t
ke
y
a
n
d
o
pe
r
a
t
e
s
o
n
8
-
bi
t
da
t
a
bl
o
c
ks
.
T
h
e
S
-
DE
S
e
n
c
r
y
pt
i
o
n
pr
o
c
e
s
s
i
nv
o
l
ve
s
t
h
e
f
o
l
l
o
w
i
ng
s
t
e
ps
e
x
p
l
a
i
ne
d
i
n
t
h
e
F
i
gur
e
2
.
F
i
g
ur
e
2
. S
-
D
E
S
a
l
go
r
i
t
hm
[
14]
a)
K
e
y
g
e
ne
r
a
t
i
o
n
:
f
r
o
m
t
h
e
o
r
i
g
i
na
l
10
-
bi
t
ke
y
,
t
wo
8
-
bi
t
s
u
b
ke
y
s
a
r
e
ge
n
e
r
a
t
e
d
us
i
n
g
p
e
r
m
ut
a
t
i
o
n
a
n
d
r
ot
a
t
i
o
n
o
pe
r
a
t
i
o
n
s
.
T
h
e
s
e
a
r
e
kn
o
wn
a
s
s
u
b
ke
y
s
K
1
a
n
d
K
2
.
b)
I
ni
t
i
a
l
p
e
r
m
ut
a
t
i
o
n
(
I
P
)
:
t
h
e
8
-
bi
t
p
l
a
i
n
t
e
x
t
bl
o
c
k
un
de
r
go
e
s
a
n
i
ni
t
i
a
l
p
e
r
m
ut
a
t
i
o
n
c
a
ll
e
d
t
h
e
I
P
to
s
c
r
a
m
bl
e
t
h
e
bi
t
s
o
f
t
h
e
p
l
a
i
n
t
e
x
t
.
c)
F
e
i
s
t
e
l
r
o
un
ds
:
t
h
e
e
n
c
r
y
pt
i
o
n
pr
o
c
e
s
s
i
nv
o
l
v
e
s
t
wo
F
e
i
s
t
e
l
r
o
un
ds
.
I
n
e
a
c
h
r
o
un
d:
t
h
e
8
-
bi
t
bl
o
c
k
i
s
d
i
vi
de
d
i
n
t
o
t
w
o
4
-
bi
t
pa
r
t
s
(
L
a
n
d
R
)
.
T
h
e
R
p
a
r
t
i
s
pr
o
c
e
s
s
e
d
us
i
n
g
t
h
e
F
e
i
s
t
e
l
f
u
nc
t
i
o
n
(
F
)
,
whi
c
h
i
nv
o
l
ve
s
e
x
pa
n
s
i
o
n
/per
m
ut
a
t
i
o
n
,
s
ubs
t
i
t
u
t
i
o
n
u
s
i
n
g
S
-
b
o
x
e
s
(
S
0
a
n
d
S
1)
,
a
n
d
pe
r
m
ut
a
t
i
o
n
.
T
h
e
r
e
s
u
l
t
o
f
t
h
e
F
e
i
s
t
e
l
f
u
n
c
t
i
o
n
i
s
XO
R
w
i
t
h
t
h
e
L
pa
r
t
to
pr
o
duc
e
a
n
e
w
R
pa
r
t
,
a
n
d
t
h
e
o
l
d
R
b
e
c
o
m
e
s
t
h
e
n
e
w
L
pa
r
t.
d)
S
ub
ke
y
a
pp
l
i
c
a
t
i
o
n
:
s
ub
k
e
y
K
1
i
s
us
e
d
i
n
t
h
e
f
i
r
s
t
r
o
un
d,
a
n
d
s
ub
ke
y
K
2
i
s
us
e
d
i
n
t
h
e
s
e
c
o
n
d
r
o
un
d.
e)
S
w
i
t
c
hi
ng
(
S
W
)
:
a
f
t
e
r
t
h
e
f
i
r
s
t
r
o
un
d,
L
a
n
d
R
a
r
e
s
wa
ppe
d
be
f
o
r
e
t
h
e
s
e
c
o
n
d
r
o
un
d
b
e
g
i
ns
.
f)
I
nv
e
r
s
e
i
n
i
t
i
a
l
p
e
r
m
ut
a
t
i
o
n
(
I
P
⁻¹)
:
Af
t
e
r
t
h
e
t
w
o
r
oun
ds
a
r
e
c
o
m
p
l
e
t
e
d,
t
h
e
r
e
s
u
l
t
i
n
g
8
-
bi
t
bl
o
c
k
u
n
de
r
go
e
s
a
f
i
na
l
pe
r
m
ut
a
t
i
o
n
c
a
l
l
e
d
t
h
e
I
P
⁻¹
to
p
r
o
duc
e
t
h
e
c
i
ph
e
r
t
e
x
t
.
T
a
bl
e
1
s
h
o
ws
t
h
e
8
v
a
r
y
i
ng
bi
na
r
y
ke
y
s
us
e
d
i
n
t
h
e
S
-
DE
S
e
n
c
r
y
pt
i
o
n
.
T
h
e
ke
y
s
we
r
e
ge
ne
r
a
t
e
d
r
a
n
do
m
ly
t
o
pr
o
duc
e
v
a
r
i
e
d
bi
na
r
y
p
l
a
i
n
t
e
x
t
.
T
h
e
pl
a
i
n
t
e
x
t
us
e
d
i
n
t
hi
s
e
x
pe
r
i
m
e
n
t
c
o
n
s
i
s
t
s
o
f
94
A
S
C
I
I
c
h
a
r
a
c
t
e
r
.
T
a
bl
e
1
.
S
-
D
E
S
bi
n
a
r
y
ke
y
B
in
a
r
y
k
ey
0101010101
1111111111
0000000000
1010101010
1111100000
1100111010
1001111000
3.
2.
De
e
p
l
e
ar
n
in
g
c
r
yp
t
an
a
l
ys
is
I
n
t
hi
s
s
t
ud
y
t
h
e
a
r
c
hi
t
e
c
t
ur
e
o
f
t
h
e
m
o
de
l
us
e
d
i
s
M
P
L
w
i
t
h
10
hi
dde
n
l
a
y
e
r
s
a
n
d
e
a
c
h
c
o
n
s
i
s
t
i
n
g
o
f
512
n
o
de
s
.
T
h
e
a
r
c
hi
t
e
c
t
ur
e
us
e
d
i
s
b
a
s
e
d
o
n
r
e
f
e
r
e
n
c
e
s
f
r
o
m
pr
e
vi
o
u
s
r
e
s
e
a
r
c
he
r
s
[
4]
.
T
h
e
a
r
c
hi
t
e
c
t
ur
e
i
s
b
u
il
t
us
i
n
g
t
h
e
t
e
n
s
o
r
f
l
o
w
2
l
i
br
a
r
y
,
t
h
e
p
y
t
h
o
n
pr
o
g
r
a
m
mi
ng
l
a
n
gua
ge
a
n
d
t
h
e
p
y
c
h
a
r
m
I
DE
.
T
h
e
t
r
a
i
ni
ng
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
do
n
e
s
i
a
n
J
E
l
e
c
E
n
g
&
C
o
m
p
S
c
i
I
S
S
N:
2
5
0
2
-
4
7
52
De
e
p
lear
ning
-
bas
e
d
c
r
y
ptanal
y
s
is
in
r
e
c
ov
e
r
ing
t
he
s
e
c
r
e
t
k
e
y
and
plai
ntex
t
on
…
(
Y
uli
a
F
atma
)
1119
pr
o
c
e
s
s
i
s
c
a
r
r
i
e
d
o
u
t
wi
t
h
t
h
e
t
a
r
ge
t
o
f
s
to
ppi
n
g
t
w
o
c
o
n
d
i
t
i
o
ns
,
n
a
m
e
ly
w
he
n
t
h
e
t
a
r
ge
t
e
r
r
or
i
s
0.
01
o
r
r
e
a
c
h
e
s
a
n
e
po
c
h
o
f
200
,
000.
I
n
de
t
a
i
l
t
h
e
a
r
c
hi
t
e
c
t
ur
e
o
f
t
h
e
DL
m
o
de
l
c
a
n
b
e
s
e
e
n
i
n
T
a
bl
e
2.
T
a
bl
e
2
.
DL
-
b
a
s
e
d
c
r
y
pt
a
n
a
ly
s
i
s
m
o
de
l
s
e
t
up
D
e
s
c
r
ip
ti
o
n
A
mo
unt
H
id
d
e
n l
a
y
e
r
10
H
id
d
e
n n
o
d
e
512
E
r
r
o
r
ta
r
ge
t
≤
0
.0
1
E
poc
h
200
,
000
L
e
a
r
ni
ng
r
a
te
0.001
3.
3.
L
os
s
f
u
n
c
t
ion
T
h
e
l
o
s
s
f
u
n
c
t
i
o
n
a
ddr
e
s
s
e
s
t
h
e
c
o
r
e
t
a
s
k
o
f
a
n
e
ur
a
l
n
e
t
wo
r
k
by
m
e
a
s
ur
i
ng
t
h
e
ga
p
b
e
t
we
e
n
t
h
e
pr
e
d
i
c
t
e
d
o
u
t
pu
t
a
n
d
t
h
e
t
a
r
ge
t
v
a
l
ue
.
T
h
e
t
a
r
ge
t
v
a
l
ue
c
o
m
e
s
w
i
t
h
t
h
e
t
r
a
i
ni
ng
da
t
a
b
ut
i
s
n
o
t
vi
s
i
bl
e
to
t
h
e
n
e
ur
a
l
n
e
t
wo
r
k
dur
i
n
g
t
r
a
i
ni
ng,
whil
e
t
h
e
pr
e
d
i
c
t
e
d
v
a
l
ue
i
s
ge
n
e
r
a
t
e
d
by
t
h
e
ne
t
wor
k.
Di
f
f
e
r
e
n
t
t
y
p
e
s
o
f
l
o
s
s
f
u
n
c
t
i
o
n
s
e
xi
s
t
,
e
a
c
h
s
e
r
vi
ng
s
pe
c
if
i
c
pur
po
s
e
s
.
T
h
e
l
o
s
s
f
u
n
c
t
i
o
n
t
o
b
e
us
e
d
i
n
t
hi
s
r
e
s
e
a
r
c
h
i
s
t
h
e
m
e
a
n
s
qua
r
e
d
e
r
r
o
r
(
M
S
E
)
.
M
S
E
l
o
s
s
a
l
wa
y
s
pr
o
duc
e
s
a
p
o
s
i
t
i
v
e
r
e
s
u
l
t
,
r
e
ga
r
dl
e
s
s
o
f
t
h
e
s
i
g
n
o
f
t
h
e
a
c
t
ua
l
a
n
d
pr
e
d
i
c
t
e
d
v
a
l
ue
s
.
T
o
i
m
pr
o
v
e
t
h
e
m
o
de
l
’
s
a
c
c
ur
a
c
y
,
t
h
e
l
o
s
s
s
h
o
u
l
d
b
e
a
s
s
m
a
ll
a
s
po
s
s
i
b
l
e
o
r
r
e
a
c
h
t
h
e
pe
r
f
e
c
t
v
a
l
ue
o
f
0.
0.
T
h
e
go
a
l
o
f
t
h
e
tr
a
i
ni
ng
p
h
a
s
e
i
n
t
hi
s
DN
N
c
r
y
pt
a
n
a
ly
t
i
c
r
e
s
e
a
r
c
h
m
o
de
l
i
s
to
ge
t
t
h
e
s
a
m
e
pr
e
d
i
c
t
e
d
v
a
l
ue
a
s
t
h
e
p
l
a
i
n
t
e
x
t
.
T
h
e
M
S
E
l
o
s
s
f
u
n
c
t
i
o
n
c
a
n
be
e
x
pr
e
s
s
e
d
a
s
f
o
l
l
o
w
s
:
=
1
.
∑
∑
(
(
)
−
̂
(
)
)
2
−
1
=
0
=
1
w
h
e
r
e
=
n
u
m
be
r
o
f
tr
a
i
ni
ng
s
a
m
pe
l
s
;
(
)
=
i
th
bi
t
o
f
th
e
ke
y
c
o
r
r
e
s
po
n
di
n
g
to
t
h
e
j
th
s
a
m
p
l
e
a
n
d
̂
(
)
=
i
th
o
u
t
pu
t
o
f
t
h
e
DN
N
c
o
r
r
e
s
po
n
d
i
n
g
to
t
h
e
j
th
s
a
m
p
l
e
.
4.
RE
S
UL
T
S
AN
D
DI
S
CU
S
S
I
ON
T
h
e
f
i
r
s
t
e
x
pe
r
i
m
e
n
t
wa
s
c
o
n
duc
t
e
d
to
o
b
t
a
i
n
t
h
e
b
e
s
t
pa
r
a
m
e
t
e
r
s
f
o
r
t
h
e
m
o
de
l
by
c
o
m
pa
r
i
ng
t
h
e
us
e
o
f
R
e
L
U
a
n
d
L
e
a
k
y
R
e
L
U
a
c
t
i
v
a
t
i
o
n
f
u
n
c
t
i
o
n
s
.
T
o
e
n
ha
n
c
e
t
h
e
m
o
de
l
’
s
pe
r
f
o
r
m
a
n
c
e
,
t
h
e
a
ut
h
or
a
tt
e
m
pt
e
d
to
a
dd
A
D
A
M
o
p
t
i
mi
z
a
t
i
o
n
.
T
h
e
r
e
s
u
l
t
i
n
g
l
o
s
s
h
a
s
a
n
a
v
e
r
a
ge
o
f
60.
1784.
S
e
c
o
n
d
e
x
pe
r
i
m
e
n
t
us
e
s
t
h
e
L
e
a
k
y
R
e
L
U
a
c
t
i
va
t
i
o
n
f
u
n
c
t
i
o
n
a
n
d
t
h
e
A
D
AM
o
p
t
i
mi
z
e
r
.
T
h
e
r
e
s
u
l
t
i
n
g
l
o
s
s
h
a
s
a
n
a
v
e
r
a
ge
o
f
40.
2961.
T
hi
r
d
e
x
pe
r
i
m
e
n
t
us
e
s
t
h
e
R
e
L
U
a
c
t
i
va
t
i
o
n
f
u
n
c
t
i
o
n
a
n
d
t
h
e
A
D
AM
o
p
t
i
mi
z
e
r
.
T
h
e
r
e
s
u
l
t
i
n
g
l
o
s
s
h
a
s
a
n
a
v
e
r
a
ge
o
f
0.
04825.
T
h
e
r
e
s
u
l
t
s
o
f
t
hi
s
c
o
m
pa
r
i
s
o
n
c
a
n
be
s
e
e
n
i
n
F
i
gur
e
3.
F
i
g
ur
e
3
.
DL
-
c
r
y
pt
a
n
a
ly
s
i
s
c
o
m
pa
r
i
s
o
n
c
h
a
r
t
o
f
l
e
a
k
y
r
e
l
u
a
n
d
r
e
l
u
us
i
ng
a
da
m
o
pt
i
m
i
z
e
r
F
r
o
m
t
h
e
t
h
r
e
e
e
x
pe
r
i
m
e
n
t
s
,
i
t
c
a
n
b
e
c
o
n
c
l
ude
d
t
h
a
t
t
h
e
b
e
s
t
l
o
s
s
r
e
s
u
l
t
i
n
g
f
r
o
m
t
h
e
DL
-
b
a
s
e
d
c
r
y
pt
a
n
a
ly
s
i
s
m
o
de
l
us
i
ng
t
h
e
R
e
L
U
a
c
t
i
v
a
t
i
o
n
f
u
n
c
t
i
o
n
a
n
d
t
h
e
A
D
AM
o
p
t
i
mi
z
e
r
i
s
0.
04825.
T
hi
s
i
s
due
t
o
t
h
e
t
a
r
ge
t
c
h
a
r
a
c
t
e
r
i
s
t
i
c
s
o
f
t
h
e
o
u
t
pu
t
da
t
a
whi
c
h
m
u
s
t
h
a
v
e
a
r
a
n
ge
b
e
t
we
e
n
0
a
n
d
p
o
s
i
t
i
v
e
n
u
m
be
r
s
,
51,4727
35,0422
0,0865
68,8841
45,55
0,01
L
E
A
K
Y
R
E
L
U
L
E
A
K
Y
R
E
L
U
+
A
D
A
M
R
E
L
U
+
A
D
A
M
L
O
SS
1
0
0
1
1
1
1
0
0
0
1
0
1
0
1
0
1
0
1
0
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2
5
0
2
-
4
7
52
In
do
n
e
s
i
a
n
J
E
l
e
c
E
n
g
&
C
o
m
p
S
c
i
,
Vo
l
.
3
8
,
N
o
.
2
,
M
a
y
20
2
5
:
1
115
-
1
123
1120
R
e
L
U
i
s
a
s
u
i
t
a
bl
e
a
c
t
i
v
a
t
i
o
n
f
u
n
c
t
i
o
n
i
n
t
hi
s
c
a
s
e
.
A
DA
M
i
s
we
l
l
k
n
o
wn
f
o
r
a
c
hi
e
vi
ng
b
e
t
t
e
r
pe
r
f
o
r
m
a
n
c
e
t
h
a
n
ot
h
e
r
m
e
t
h
o
ds
i
n
t
h
e
n
o
n
-
c
o
n
v
e
x
c
a
s
e
.
AD
AM
c
o
m
bi
ne
s
t
h
e
b
e
s
t
pr
o
pe
r
t
i
e
s
o
f
t
h
e
A
da
G
r
a
d
a
n
d
R
M
S
P
r
o
p
a
l
go
r
i
t
hm
s
to
pr
o
vi
de
a
n
o
p
t
i
m
i
z
a
t
i
o
n
a
l
go
r
i
t
hm
t
h
a
t
c
a
n
h
a
n
d
l
e
s
pa
r
s
e
gr
a
d
i
e
n
t
s
i
n
n
o
i
s
e
pr
o
bl
e
m
s
.
I
n
a
dd
i
t
i
o
n
to
t
h
e
a
da
p
t
i
ve
l
e
a
r
ni
ng
r
a
t
e
,
t
h
e
we
i
g
h
t
s
i
n
t
h
e
n
e
ur
a
l
n
e
t
wo
r
k
a
r
e
a
l
s
o
a
d
j
u
s
t
e
d
a
da
pt
i
v
e
ly
ba
s
e
d
o
n
t
h
e
f
i
r
s
t
a
n
d
s
e
c
o
n
d
m
o
m
e
n
t
s
o
f
t
h
e
gr
a
di
e
n
t
.
T
hi
s
h
e
l
ps
a
c
hi
e
v
e
f
a
s
t
e
r
c
o
n
ve
r
ge
n
c
e
,
a
v
o
i
d
l
a
r
ge
s
p
i
ke
s
i
n
we
i
g
h
t
upda
t
e
s
,
a
n
d
o
p
t
i
mi
z
e
o
v
e
r
a
l
l
m
o
de
l
pe
r
f
o
r
m
a
nc
e
a
n
d
yi
e
l
d.
T
h
e
s
e
c
o
n
d
e
x
pe
r
im
e
n
t
wa
s
c
o
n
duc
t
e
d
to
t
e
s
t
t
h
e
pe
r
f
o
r
m
a
nc
e
o
f
DL
-
b
a
s
e
d
c
r
y
pt
a
n
a
ly
s
i
s
us
i
ng
t
h
e
R
e
L
U
a
c
t
i
v
a
t
i
o
n
f
u
n
c
t
i
o
n
a
n
d
t
h
e
A
D
A
M
o
pt
i
m
i
z
e
r
.
T
h
e
e
x
pe
r
i
m
e
n
t
a
l
r
e
s
u
l
t
s
a
r
e
pr
e
s
e
n
t
e
d
i
n
T
a
bl
e
3.
T
a
bl
e
3
.
DL
-
b
a
s
e
d
c
r
y
pt
a
n
a
ly
s
i
s
c
o
m
p
a
r
i
s
o
n
o
n
pl
a
i
n
t
e
x
t
a
n
d
ke
y
r
e
c
o
v
e
r
y
o
n
26
c
h
a
r
a
c
t
e
r
s
P
la
in
te
x
t
r
e
c
ove
r
y
K
e
y
r
e
c
ove
r
y
K
e
y
L
o
s
s
E
poc
h
T
im
e
(
mi
nut
e
s
)
L
o
s
s
E
poc
h
T
im
e
(
mi
nut
e
s
)
0101010101
0
.
01
100
,
661
6
.
71
0
.
010
12
,
241
0
.
8
1111111111
0
.
01
35
,
721
2
.
3
0
.
008
24
,
239
1
.
6
0000000000
0
.
01
32
,
316
2
.
15
0
.
002
10
0
.
0006
1010101010
0
.
01
101
,
546
6
.
7
0
.
009
5
,
923
0
.
39
1111100000
0
.
01
83
,
708
5
.
5
0
.
010
28
,
679
1
.
9
1100111010
0
.
600
119
,
062
7
.
9
0
.
009
22
,
110
1
.
4
1001111000
0
.
086
81
,
756
5
.
4
0
.
010
19
,
571
1
.
3
T
a
bl
e
3
s
h
o
w
i
n
g
t
h
e
c
o
m
pa
r
i
s
o
n
r
e
s
u
l
t
s
b
e
t
we
e
n
ke
y
r
e
c
o
v
e
r
y
a
n
d
p
l
a
i
n
t
e
x
t
r
e
c
o
v
e
r
y
i
n
t
e
r
m
s
o
f
l
o
s
s
,
e
po
c
h
a
n
d
t
i
m
e
r
e
qu
i
r
e
d.
I
n
t
hi
s
e
x
pe
r
im
e
n
t
,
DL
-
b
a
s
e
d
c
r
y
pt
a
n
a
ly
s
i
s
a
t
t
e
m
pt
e
d
to
c
om
pa
r
e
t
h
e
pe
r
f
o
r
m
a
n
c
e
i
n
r
e
c
o
v
e
r
i
n
g
p
l
a
i
n
t
e
x
t
a
n
d
r
e
c
o
v
e
r
i
n
g
ke
y
s
.
T
h
e
da
t
a
s
e
t
t
e
s
t
e
d
wa
s
26
c
h
a
r
a
c
t
e
r
s
c
o
n
s
i
s
t
i
n
g
o
f
t
h
e
l
e
t
t
e
r
s
a
to
z
.
Gi
v
e
n
s
e
v
e
n
d
i
f
f
e
r
e
n
t
k
i
n
ds
o
f
ke
y
s
f
r
o
m
pa
tt
e
r
n
e
d
to
r
a
n
d
o
m
.
T
h
e
DL
-
b
a
s
e
d
c
r
y
pt
a
n
a
ly
s
i
s
e
x
pe
r
i
m
e
n
t
i
n
r
e
c
o
v
e
r
i
n
g
p
l
a
i
n
t
e
x
t
r
e
s
u
l
t
e
d
i
n
a
n
a
v
e
r
a
ge
l
o
s
s
o
f
0.
105.
W
hil
e
t
h
e
e
x
p
e
r
im
e
n
t
in
r
e
c
o
v
e
r
i
n
g
t
h
e
ke
y
r
e
s
u
l
t
e
d
i
n
a
s
m
a
l
l
e
r
l
o
s
s
,
n
a
m
e
ly
a
n
a
v
e
r
a
ge
o
f
0.
008.
I
n
t
e
r
m
s
o
f
t
h
e
e
p
o
c
h
s
i
n
t
h
e
DL
-
b
a
s
e
d
c
r
y
pt
a
na
l
y
s
i
s
e
x
pe
r
i
m
e
n
t
to
r
e
c
o
v
e
r
pl
a
i
n
t
e
x
t
,
t
h
e
a
v
e
r
a
ge
e
po
c
h
wa
s
28,
738.
W
hil
e
t
h
e
e
x
pe
r
im
e
n
t
i
n
r
e
c
o
v
e
r
i
ng
t
h
e
ke
y
r
e
s
u
l
t
e
d
i
n
s
ma
l
l
e
r
e
po
c
h
s
,
n
a
m
e
ly
a
n
a
ve
r
a
ge
o
f
17
e
po
c
h
s
.
T
h
e
t
i
me
r
e
qu
i
r
e
d
i
n
t
h
e
DL
-
b
a
s
e
d
c
r
y
pt
a
n
a
ly
s
i
s
e
x
pe
r
i
m
e
n
t
to
r
e
c
o
v
e
r
t
h
e
pl
a
i
n
t
e
x
t
r
e
s
u
l
t
e
d
i
n
a
n
a
ve
r
a
ge
o
f
5.
23
mi
nut
e
s
.
W
hil
e
t
h
e
e
x
pe
r
im
e
n
t
i
n
r
e
c
o
v
e
r
i
n
g
t
h
e
ke
y
r
e
s
u
l
t
e
d
i
n
a
s
h
o
r
t
e
r
t
i
m
e
,
n
a
m
e
ly
1.
05
mi
nut
e
s
o
n
a
v
e
r
a
ge
.
T
h
e
e
x
pe
r
i
m
e
n
t
a
l
r
e
s
u
l
t
s
i
n
T
a
bl
e
3
a
r
e
vi
s
ua
li
z
e
d
gr
a
phi
c
a
ll
y
i
n
F
i
gur
e
4.
F
i
gur
e
4(
a
)
i
s
a
gr
a
ph
t
h
a
t
vi
s
u
a
l
i
z
e
s
t
h
e
c
o
m
pa
r
i
s
o
n
o
f
e
r
r
o
r
s
i
n
ke
y
a
n
d
p
l
a
i
n
t
e
x
t
r
e
c
o
v
e
r
y
.
T
h
e
ke
y
r
e
c
o
v
e
r
y
e
r
r
o
r
s
h
o
ws
goo
d
a
n
d
c
o
n
s
i
s
t
e
n
t
r
e
s
u
l
t
s
.
Ho
we
v
e
r
,
pl
a
i
n
t
e
x
t
r
e
c
o
v
e
r
y
d
i
s
p
l
a
y
s
a
r
a
n
do
m
pa
t
t
e
r
n
,
wh
e
r
e
t
h
e
6t
h
a
n
d
7t
h
k
e
y
s
us
e
d
f
o
r
e
n
c
r
y
pt
i
o
n
a
f
f
e
c
t
t
h
e
r
e
s
u
l
t
i
n
g
l
o
s
s
.
F
i
gur
e
4(
b
)
i
s
a
gr
a
ph
t
h
a
t
vi
s
ua
li
z
e
s
t
h
e
c
o
m
pa
r
i
s
o
n
o
f
e
p
o
c
h
s
b
e
t
we
e
n
ke
y
a
n
d
p
l
a
i
n
t
e
x
t
r
e
c
o
v
e
r
y
.
F
i
gur
e
4(
c
)
i
s
a
gr
a
ph
t
h
a
t
vi
s
ua
li
z
e
s
t
h
e
c
o
m
pa
r
i
s
o
n
o
f
t
i
m
e
b
e
t
we
e
n
ke
y
a
n
d
p
l
a
i
n
t
e
x
t
r
e
c
o
v
e
r
y
.
P
l
a
i
n
t
e
x
t
r
e
c
o
v
e
r
y
s
h
o
ws
t
h
a
t
m
o
r
e
e
po
c
h
s
a
n
d
t
i
m
e
a
r
e
n
e
e
de
d
c
o
m
pa
r
e
d
t
o
ke
y
r
e
c
o
v
e
r
y
.
T
h
e
l
a
s
t
e
x
pe
r
im
e
n
t
us
e
s
t
h
e
R
e
L
U
a
c
t
i
v
a
t
i
o
n
f
u
nc
t
i
o
n
a
n
d
t
h
e
A
D
AM
o
p
t
i
mi
z
e
r
,
t
h
e
c
ha
r
a
c
t
e
r
i
s
e
x
pa
n
d
t
o
94
c
h
a
r
a
c
t
e
r
s
c
o
n
s
i
s
t
i
n
g
o
f
a
c
o
m
bi
na
t
i
o
n
o
f
l
e
t
t
e
r
s
,
n
u
m
b
e
r
s
a
n
d
s
ym
b
o
l
s
.
T
h
e
e
x
p
e
r
i
m
e
n
t
a
l
r
e
s
u
l
t
s
a
r
e
pr
e
s
e
n
t
e
d
i
n
T
a
bl
e
4.
T
a
bl
e
4
s
h
o
w
i
n
g
t
h
e
c
o
m
pa
r
i
s
o
n
r
e
s
u
l
t
s
b
e
t
we
e
n
ke
y
r
e
c
o
v
e
r
y
a
n
d
p
l
a
i
n
t
e
x
t
r
e
c
o
v
e
r
y
i
n
t
e
r
m
s
o
f
l
o
s
s
,
e
po
c
h
a
n
d
t
i
m
e
r
e
qu
i
r
e
d
w
i
t
h
e
x
pa
n
de
d
da
t
a
.
T
h
e
DL
-
b
a
s
e
d
c
r
y
pt
a
n
a
ly
s
i
s
e
x
pe
r
i
m
e
n
t
i
n
r
e
c
o
v
e
r
i
n
g
p
l
a
i
n
t
e
x
t
wi
t
h
94
c
h
a
r
a
c
t
e
r
s
e
x
pe
r
i
e
n
c
e
d
a
v
e
r
y
l
a
r
ge
i
n
c
r
e
a
s
e
i
n
l
o
s
s
,
n
a
m
e
ly
a
n
a
v
e
r
a
ge
o
f
301,
285.
W
hil
e
t
h
e
e
x
pe
r
im
e
n
t
i
n
r
e
c
o
v
e
r
i
n
g
t
h
e
ke
y
r
e
s
u
l
t
e
d
i
n
a
s
m
a
ll
e
r
l
o
s
s
,
n
a
m
e
ly
a
n
a
ve
r
a
ge
o
f
0.
007.
I
n
t
e
r
m
s
o
f
e
po
c
h
s
r
e
qu
i
r
e
d
i
n
D
L
-
ba
s
e
d
c
r
y
pt
a
n
a
ly
s
i
s
e
x
p
e
r
i
m
e
n
t
s
to
r
e
c
o
v
e
r
p
l
a
i
n
t
e
x
t
y
i
e
l
d
e
d
a
ve
r
a
ge
e
po
c
hs
a
b
o
v
e
200,
000
.
W
hil
e
t
h
e
e
x
pe
r
im
e
n
t
i
n
r
e
c
o
v
e
r
i
n
g
t
h
e
ke
y
r
e
s
u
l
t
e
d
i
n
s
m
a
l
l
e
r
e
po
c
h
s
,
n
a
m
e
ly
a
n
a
v
e
r
a
ge
o
f
49
e
po
c
h
s
.
T
h
e
t
i
m
e
r
e
qu
i
r
e
d
f
o
r
DL
-
b
a
s
e
d
c
r
y
pt
a
n
a
ly
s
i
s
e
x
pe
r
im
e
n
t
s
to
r
e
c
o
v
e
r
pl
a
i
n
t
e
x
t
r
e
s
ul
t
s
i
n
a
n
a
v
e
r
a
ge
o
f
o
v
e
r
30
m
i
nut
e
s
.
W
hil
e
t
h
e
e
x
pe
r
i
m
e
n
t
i
n
r
e
c
o
v
e
r
i
n
g
t
h
e
ke
y
r
e
s
u
l
t
e
d
i
n
a
s
h
o
r
t
e
r
t
i
m
e
,
whi
c
h
wa
s
a
n
a
v
e
r
a
ge
o
f
0.
178
m
i
nut
e
s
.
T
h
e
e
x
pe
r
im
e
n
t
a
l
r
e
s
u
l
t
s
i
n
T
a
bl
e
4
a
r
e
vi
s
u
a
l
i
z
e
d
gr
a
p
hi
c
a
ll
y
i
n
F
i
gur
e
5.
F
i
gur
e
5(
a
)
i
s
a
gr
a
ph
t
h
a
t
vi
s
ua
li
z
e
s
t
h
e
c
o
m
pa
r
i
s
o
n
o
f
e
r
r
o
r
s
i
n
ke
y
a
n
d
p
l
a
i
n
t
e
x
t
r
e
c
o
v
e
r
y
.
F
i
gur
e
5(
b
)
i
s
a
gr
a
ph
t
h
a
t
vi
s
u
a
l
i
z
e
s
t
h
e
c
o
m
p
a
r
i
s
o
n
o
f
e
po
c
h
s
f
o
r
ke
y
a
n
d
p
l
a
i
n
t
e
x
t
r
e
c
o
v
e
r
y
.
F
i
gur
e
5(
c
)
i
s
a
gr
a
ph
t
h
a
t
vi
s
u
a
l
i
z
e
s
t
h
e
c
o
m
pa
r
i
s
o
n
o
f
t
i
m
e
f
o
r
ke
y
a
n
d
p
l
a
i
n
t
e
x
t
r
e
c
o
v
e
r
y
.
W
e
f
o
un
d
t
h
a
t
i
n
c
r
e
a
s
i
ng
t
h
e
a
m
o
u
n
t
o
f
da
t
a
a
f
f
e
c
t
s
t
h
e
e
r
r
or
,
e
p
o
c
h
s
,
a
n
d
t
i
m
e
r
e
qu
i
r
e
d
f
o
r
pl
a
i
n
t
e
x
t
r
e
c
o
v
e
r
y
.
T
h
e
m
o
de
l
w
a
s
una
bl
e
to
r
e
c
o
v
e
r
t
h
e
p
l
a
i
n
t
e
x
t
a
n
d
f
a
i
l
e
d
to
l
e
a
r
n
t
h
e
pr
o
vi
de
d
da
t
a
pa
tt
e
r
n
s
.
T
h
e
hi
g
hly
r
a
n
do
m
n
a
t
ur
e
o
f
l
a
r
ge
da
t
a
s
e
t
s
r
e
qu
i
r
e
s
f
ur
t
h
e
r
r
e
s
e
a
r
c
h
t
o
c
o
n
s
t
r
uc
t
e
f
f
e
c
t
i
v
e
da
t
a
a
n
d
mo
de
l
s
w
i
t
h
e
nh
a
nc
e
d
hy
pe
r
pa
r
a
m
e
t
e
r
s
.
F
ut
u
r
e
s
t
u
d
i
e
s
m
a
y
e
x
p
l
o
r
e
us
i
ng
m
o
r
e
v
a
r
i
e
d
da
t
a
a
n
d
a
n
i
m
pr
o
v
e
d
m
o
de
l
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
do
n
e
s
i
a
n
J
E
l
e
c
E
n
g
&
C
o
m
p
S
c
i
I
S
S
N:
2
5
0
2
-
4
7
52
De
e
p
lear
ning
-
bas
e
d
c
r
y
ptanal
y
s
is
in
r
e
c
ov
e
r
ing
t
he
s
e
c
r
e
t
k
e
y
and
plai
ntex
t
on
…
(
Y
uli
a
F
atma
)
1121
(
a
)
(
b
)
(
c
)
F
i
gur
e
4.
C
o
m
pa
r
i
s
o
n
o
n
p
l
a
i
n
t
e
x
t
a
n
d
ke
y
r
e
c
o
v
e
r
y
:
(
a
)
l
o
s
s
,
(
b
)
e
po
c
h
,
a
n
d
(
c
)
t
i
m
e
r
e
qu
i
r
e
d
o
n
26
c
h
a
r
a
c
t
h
e
r
s
T
a
bl
e
4
.
DL
-
b
a
s
e
d
c
r
y
pt
a
n
a
ly
s
i
s
c
o
m
p
a
r
i
s
o
n
o
n
pl
a
i
n
t
e
x
t
a
n
d
ke
y
r
e
c
o
v
e
r
y
P
la
in
te
x
t
r
e
c
ove
r
y
K
e
y
r
e
c
ove
r
y
K
e
y
L
o
s
s
E
poc
h
T
im
e
(
mi
nut
e
s
)
L
o
s
s
E
poc
h
T
im
e
(
mi
nut
e
s
)
0101010101
752
200.000
>
30
0
.
0082
318
0
.
02
1111111111
331
200.000
>
30
0
.
0088
5
,
429
0
.
36
0000000000
81
200.000
>
30
0
.
0090
7
0
.
0004
1010101010
215
200.000
>
30
0
.
0025
2
,
051
0
.
13
1111100000
145
200.000
>
30
0
.
0085
7
,
629
0
.
5
1100111010
273
200.000
>
30
0
.
0083
1
,
316
0
.
087
1001111000
312
200.000
>
30
0
.
0088
2
,
356
0
.
15
(
a
)
(
b
)
(
c
)
F
i
gur
e
5.
C
o
m
pa
r
i
s
o
n
o
n
p
l
a
i
n
t
e
x
t
a
n
d
ke
y
r
e
c
o
v
e
r
y
:
(
a
)
l
o
s
s
,
(
b
)
e
po
c
h
,
a
n
d
(
c
)
t
i
m
e
r
e
qu
i
r
e
d
o
n
94
c
h
a
r
a
c
t
h
e
r
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2
5
0
2
-
4
7
52
In
do
n
e
s
i
a
n
J
E
l
e
c
E
n
g
&
C
o
m
p
S
c
i
,
Vo
l
.
3
8
,
N
o
.
2
,
M
a
y
20
2
5
:
1
115
-
1
123
1122
5.
CONC
L
USI
ON
T
h
e
f
i
r
s
t
o
b
j
e
c
t
i
v
e
o
f
t
hi
s
s
t
ud
y
i
s
t
o
de
t
e
r
m
in
e
t
h
e
i
nf
l
ue
n
c
e
o
f
o
p
t
i
mi
z
a
t
i
o
n
a
n
d
a
c
t
i
v
a
t
i
o
n
f
u
n
c
t
i
o
n
s
o
n
t
h
e
M
L
P
m
o
de
l
i
n
pe
r
f
o
r
m
i
ng
c
r
y
pta
n
a
ly
s
i
s
.
T
h
e
s
e
c
o
n
d
o
bj
e
c
t
i
v
e
i
s
t
o
c
o
m
pa
r
e
c
r
y
p
t
a
n
a
l
y
s
i
s
i
n
t
e
r
m
s
o
f
r
e
c
o
v
e
r
i
ng
ke
y
s
a
n
d
p
l
a
i
n
t
e
x
t
i
n
t
e
r
m
s
o
f
t
i
m
e
,
e
po
c
h
s
,
a
n
d
a
c
c
ur
a
c
y
.
B
a
s
e
d
o
n
t
h
e
e
x
p
e
r
i
m
e
n
t
a
l
r
e
s
u
l
t
s
,
i
t
i
s
s
h
o
w
n
t
h
a
t
t
h
e
s
e
l
e
c
t
i
o
n
o
f
t
h
e
a
ppr
o
pr
i
a
t
e
a
c
t
i
v
a
t
i
o
n
f
u
n
c
t
i
o
n
a
n
d
o
p
t
i
mi
z
a
t
i
o
n
p
l
a
y
s
a
c
r
uc
i
a
l
r
o
l
e
i
n
im
pr
o
vi
n
g
t
h
e
a
c
c
ur
a
c
y
o
f
t
h
e
n
e
t
wo
r
k
m
o
de
l
.
I
n
t
hi
s
s
t
ud
y
,
t
h
e
b
e
s
t
r
e
s
u
l
t
s
we
r
e
o
b
t
a
i
n
e
d
u
s
i
n
g
t
h
e
R
e
L
U
a
c
t
i
v
a
t
i
o
n
f
u
n
c
t
i
o
n
a
n
d
A
D
A
M
o
pt
i
mi
z
a
t
i
o
n
,
a
s
e
vi
de
n
c
e
d
by
a
s
i
g
ni
f
i
c
a
n
t
r
e
duc
t
i
o
n
i
n
l
o
s
s
.
T
h
e
r
e
s
e
a
r
c
h
r
e
s
u
l
t
s
a
l
s
o
i
n
d
i
c
a
t
e
t
h
a
t
c
r
y
pt
a
n
a
ly
s
i
s
i
s
m
o
r
e
e
f
f
e
c
t
i
v
e
a
t
r
e
c
o
v
e
r
i
n
g
ke
y
s
t
h
a
n
pl
a
i
n
t
e
x
t
.
DL
-
b
a
s
e
d
c
r
y
pt
a
n
a
ly
s
i
s
s
uc
c
e
s
s
f
u
ll
y
r
e
c
o
v
e
r
e
d
ke
y
s
w
i
t
h
a
n
a
v
e
r
a
ge
l
o
s
s
o
f
0.
007,
a
n
a
v
e
r
a
ge
o
f
49
e
po
c
h
s
,
a
n
d
a
n
a
v
e
r
a
ge
t
i
m
e
o
f
0.
178
m
i
nut
e
s
.
F
ut
ur
e
r
e
s
e
a
r
c
h
c
a
n
b
e
de
v
e
l
o
p
e
d
by
a
t
t
e
m
pt
i
n
g
hy
p
e
r
pa
r
a
m
e
t
e
r
s
e
l
e
c
t
i
o
n
us
i
ng
o
p
t
i
mi
z
a
t
i
o
n
a
l
go
r
i
t
hm
s
.
T
h
e
a
ppr
o
pr
i
a
t
e
s
e
l
e
c
t
i
o
n
o
f
hy
p
e
r
pa
r
a
m
e
t
e
r
s
w
i
ll
m
a
xim
i
z
e
t
h
e
m
o
de
l
’
s
pe
r
f
o
r
m
a
n
c
e
in
c
o
n
duc
t
i
n
g
c
r
y
pt
a
n
a
ly
s
i
s
.
C
r
y
pt
a
n
a
ly
s
i
s
e
x
pe
r
i
m
e
n
t
s
o
n
ot
h
e
r
l
i
g
h
t
we
i
g
h
t
c
r
y
pto
gr
a
phi
c
a
l
go
r
i
t
hm
s
c
a
n
a
l
s
o
b
e
c
o
n
duc
t
e
d
c
o
n
s
i
de
r
i
ng
t
h
e
e
m
e
r
ge
n
c
e
o
f
n
e
w
a
lgo
r
i
t
hm
s
.
RE
F
E
R
E
NC
E
S
[
1]
Y
.
Z
ha
o
a
nd
S
.
F
a
n,
“
A
n
a
ly
s
is
of
c
r
y
pt
o
s
y
s
te
m
r
e
c
o
gni
ti
o
n
s
c
he
m
e
ba
s
e
d
o
n
E
u
c
li
d
e
a
n
di
s
ta
nc
e
f
e
a
tu
r
e
e
x
tr
a
c
ti
o
n
in
th
r
e
e
ma
c
hi
ne
le
a
r
n
in
g
c
la
s
s
i
f
i
e
r
s
,
”
J
our
nal
of
P
hy
s
ic
s
:
C
onf
e
r
e
nc
e
Se
r
i
e
s
,
v
o
l.
1314,
n
o
.
1,
20
19,
do
i:
10.1088/1742
-
6596/1314/
1/
012184.
[
2]
W
.
S
ta
ll
in
gs
,
T
he
w
il
li
am
s
ta
ll
in
gs
book
s
on
c
om
put
e
r
dat
a
and
c
om
put
e
r
c
om
m
uni
c
at
io
ns
,
E
ig
ht
h
E
di
ti
on
,
5t
h
e
d.
N
e
w
Y
o
r
k:
P
e
a
r
s
o
n, 2011.
[
3]
A
.
B
e
na
mi
r
a
,
D
.
G
e
r
a
ul
t,
T
.
P
e
y
r
in
,
a
nd
Q
.
Q
.
T
a
n,
“
A
de
e
p
e
r
lo
o
k
a
t
ma
c
hi
n
e
l
e
a
r
ni
ng
-
ba
s
e
d
c
r
y
p
ta
na
l
y
s
is
,
”
in
L
e
c
tu
r
e
N
ot
e
s
in
C
om
put
e
r
S
c
ie
nc
e
(
in
c
lu
di
ng
s
ubs
e
r
ie
s
L
e
c
tu
r
e
N
ot
e
s
in
A
r
t
if
ic
ia
l
I
nt
e
ll
ig
e
nc
e
and
L
e
c
tu
r
e
N
ot
e
s
in
B
io
in
f
o
r
m
at
ic
s
)
,
20
21,
vo
l.
12696
L
N
C
S
, pp. 805
–
835
, d
o
i
:
10.1007/978
-
3
-
030
-
77870
-
5_28.
[
4]
J
.
S
o
,
“
D
e
e
p
l
e
a
r
ni
ng
-
ba
s
e
d
c
r
y
pt
a
na
l
y
s
is
of
li
gh
twe
ig
ht
bl
oc
k
c
ip
h
e
r
s
,
”
Se
c
ur
it
y
and
C
om
m
uni
c
at
io
n
N
e
tw
or
k
s
,
vo
l.
20
20,
pp. 1
–
11, J
ul
. 2020, do
i:
10.1155/2020/
3701067.
[
5]
Y
.
F
a
tm
a
,
R
.
W
a
r
doy
o
,
a
nd
H
.
M
ukht
a
r
,
“
A
n
a
ppr
o
a
c
h
t
o
c
r
y
p
to
gr
a
ph
y
ba
s
e
d
o
n
ne
ur
a
l
ne
twor
k,
”
A
I
P
C
onf
e
r
e
nc
e
P
r
oc
e
e
di
ngs
,
vo
l.
2601, n
o
. 1, pp. 1
–
9, 2023, d
o
i:
10.1063/5.0130464
.
[
6]
R
.
L
.
R
iv
e
s
t,
“
C
r
y
pt
o
g
r
a
ph
y
a
nd
ma
c
hi
n
e
l
e
a
r
ni
ng
,
”
i
n
L
e
c
tu
r
e
N
ot
e
s
in
C
om
put
e
r
Sc
ie
n
c
e
(
in
c
lu
di
ng
s
ub
s
e
r
ie
s
L
e
c
tu
r
e
N
ot
e
s
in
A
r
ti
f
i
c
ia
l
I
nt
e
ll
ig
e
nc
e
and
L
e
c
tu
r
e
N
ot
e
s
in
B
io
in
f
or
m
at
ic
s
)
,
v
o
l.
739
L
N
C
S
,
1993,
pp.
427
–
439
,
do
i:
10.1007/3
-
540
-
57332
-
1_36.
[
7]
S
.
B
a
e
k
a
nd
K
.
K
im
,
“
R
e
c
e
nt
a
d
v
a
nc
e
s
of
n
e
ur
a
l
a
tt
a
c
ks
a
ga
in
s
t
bl
oc
k
c
ip
h
e
r
s
,
”
P
r
oc
e
e
di
ngs
of
th
e
2020
Sy
m
pos
iu
m
on
C
r
y
pt
ogr
aph
y
and I
nf
o
r
m
at
io
n Se
c
ur
it
y
,
2020.
[
8]
E
. M
. M
e
no
,
“
N
e
ur
a
l
c
r
y
pt
a
na
l
y
s
is
f
or
c
y
b
e
r
-
ph
y
s
i
c
a
l
s
y
s
t
e
m
c
i
phe
r
s
,
”
V
ir
gi
ni
a
P
o
l
y
t
e
c
hni
c
I
ns
ti
tu
t
e
a
nd S
ta
te
U
ni
ve
r
s
it
y
, 202
1.
[
9]
B
.
Y
.
C
ho
ng
a
nd
I
.
S
a
la
m,
“
I
n
ve
s
ti
ga
ti
ng
de
e
p
l
e
a
r
ni
ng
a
p
pr
o
a
c
h
e
s
o
n
th
e
s
e
c
u
r
it
y
a
na
l
y
s
is
of
c
r
y
p
t
o
gr
a
phi
c
a
lg
or
it
h
ms
,
”
C
r
y
pt
ogr
aph
y
, v
ol
. 5, n
o
. 4, p. 30, Oc
t.
2021, d
o
i
:
10.3390/c
r
y
p
to
gr
a
ph
y
5040030.
[
10]
M
.
D
a
nz
ig
e
r
a
nd
M
.
A
.
A
ma
r
a
l
H
e
nr
iq
u
e
s
,
“
I
mpr
ove
d
c
r
y
pt
a
na
l
y
s
is
c
ombi
ni
ng
di
f
f
e
r
e
nt
ia
l
a
nd
a
r
ti
f
i
c
ia
l
ne
u
r
a
l
ne
t
w
o
r
k
s
c
he
m
e
s
,
”
in
2014 I
nt
e
r
nat
io
nal
T
e
le
c
om
m
uni
c
at
io
ns
Sy
m
pos
iu
m
(
I
T
S)
, A
ug. 2014, pp. 1
–
5
, d
o
i:
10.1109/
I
T
S
.2014.6948008.
[
11]
L
.
L
e
r
ma
n,
G
.
B
o
nt
e
mpi
,
a
nd
O
.
M
a
r
ko
w
it
c
h,
“
A
ma
c
hi
n
e
l
e
a
r
ni
ng
a
ppr
o
a
c
h
a
ga
in
s
t
a
ma
s
ke
d
A
E
S
:
R
e
a
c
h
in
g
th
e
l
im
it
of
s
id
e
-
c
ha
nne
l
a
tt
a
c
ks
w
it
h
a
le
a
r
ni
ng
m
o
d
e
l,
”
J
our
nal
of
C
r
y
pt
ogr
aphi
c
E
ngi
ne
e
r
in
g
,
v
o
l.
5,
n
o
.
2,
pp.
123
–
139,
20
15,
do
i:
10.1007/s
13389
-
014
-
0089
-
3.
[
12]
S
. A
mi
c
,
K
. M
. S
.
S
oy
ja
uda
h, a
nd G
.
R
a
ms
a
w
o
c
k,
“
B
in
a
r
y
c
a
t
s
w
a
r
m o
pt
im
i
z
a
ti
o
n
f
or
c
r
y
p
ta
na
l
y
s
is
,
”
in
2017 I
E
E
E
I
n
te
r
nat
io
nal
C
onf
e
r
e
nc
e
on
A
dv
anc
e
d
N
e
tw
or
k
s
and
T
e
le
c
om
m
uni
c
at
io
ns
Sy
s
te
m
s
(
A
N
T
S)
,
D
e
c
.
2017,
pp.
1
–
6
,
do
i:
10.1109/AN
T
S
.2017.8384120.
[
13]
R
.
F
o
c
a
r
d
i
a
nd
F
.
L
.
L
u
c
c
i
o
,
“
N
e
ur
a
l
c
r
y
pt
a
na
l
y
s
i
s
of
c
la
s
s
ic
a
l
c
ip
h
e
r
s
?
,
”
C
E
U
R
W
or
k
s
hop
P
r
oc
e
e
di
ngs
,
vo
l.
2243, pp. 104
–
115, 2018.
[
14]
R
.
K
a
ma
l,
M
.
B
a
g,
a
nd
M
.
K
ul
e
,
“
O
n
th
e
c
r
y
pt
a
na
l
y
s
i
s
of
S
-
D
E
S
us
in
g
na
tu
r
e
in
s
pi
r
e
d
o
pt
im
i
z
a
ti
o
n
a
lg
or
it
h
ms
,
”
E
v
ol
ut
io
nar
y
I
nt
e
ll
ig
e
nc
e
, vo
l.
14, n
o
. 1, pp. 163
–
173, 2
021, d
oi
:
10.1007/s
12065
-
020
-
00417
-
5.
[
15]
W
.
T
ia
n
a
nd
B
.
H
u,
“
D
e
e
p
l
e
a
r
ni
ng
a
s
s
is
te
d
di
f
f
e
r
e
nt
ia
l
c
r
y
pt
a
na
l
y
s
is
f
o
r
th
e
li
ght
w
e
ig
ht
c
ip
h
e
r
S
I
M
O
N
,
”
K
SI
I
T
r
ans
ac
ti
on
s
on
I
nt
e
r
ne
t
and I
nf
or
m
at
io
n S
y
s
te
m
s
, v
o
l.
15, n
o
. 2, pp. 600
–
616,
2021, do
i:
10.3837/t
ii
s
.
2021.02.012.
[
16]
H
.
K
im
,
S
.
L
im
,
a
nd
Y
.
K
a
ng,
“
D
e
e
p
l
e
a
r
ni
ng
ba
s
e
d
c
r
y
pt
a
na
l
y
s
is
of
li
gh
twe
ig
ht
bl
oc
k
c
ip
h
e
r
s
,
r
e
v
is
it
e
d,
”
C
r
y
pt
ol
ogy
e
P
r
in
t
A
r
c
hi
v
e
, no
. 886, pp. 1
–
15, 2022, do
i
:
d
o
i.
o
r
g/
10.3390/e
25070986.
[
17]
S
.
A
ndo
n
ov
,
J
.
D
o
br
e
v
a
,
L
.
L
umbu
r
ov
s
ka
,
S
.
P
a
v
l
ov
,
a
nd
A
.
P
o
p
ov
s
ka
-
mi
tr
ov
ik
j,
“
A
ppl
ic
a
ti
o
n
of
ma
c
h
in
e
l
e
a
r
ni
ng
in
D
E
S
c
r
y
pt
a
na
l
y
s
is
,
”
in
I
C
T
-
I
nnov
at
io
ns
2020
, 2020, pp. 124
–
134.
[
18]
A
.
A
l
B
a
ta
in
e
h,
D
.
K
a
ur
,
a
nd
S
.
M
.
J
.
J
a
la
li
,
“
M
ul
ti
-
la
y
e
r
pe
r
c
e
pt
r
o
n
tr
a
in
in
g
o
pt
im
i
z
a
ti
o
n
us
in
g
na
tu
r
e
in
s
pi
r
e
d
c
o
mput
in
g,
”
I
E
E
E
A
c
c
e
s
s
, v
ol
. 10, pp. 36963
–
36977, 2022, d
o
i:
10.1109/A
C
C
E
S
S
.2022.3164669.
[
19]
R
.
Y
.
S
un,
“
O
pt
im
iz
a
ti
o
n
f
or
de
e
p
l
e
a
r
ni
ng:
a
n
ove
r
v
i
e
w
,
”
J
our
nal
of
th
e
O
pe
r
at
io
ns
R
e
s
e
ar
c
h
So
c
ie
ty
o
f
C
hi
na
,
v
ol
.
8,
no.
2,
pp. 249
–
294, 2020, do
i:
10.1007/s
40305
-
020
-
00309
-
6.
[
20]
L
.
A
l
z
uba
id
i
e
t
al
.
,
“
R
e
v
ie
w
of
de
e
p
l
e
a
r
ni
ng:
c
o
n
c
e
pt
s
,
C
N
N
a
r
c
hi
te
c
tu
r
e
s
,
c
ha
ll
e
ng
e
s
,
a
ppl
ic
a
ti
o
ns
,
f
ut
u
r
e
di
r
e
c
ti
ons
,
”
J
our
nal
of
B
ig
D
at
a
, v
o
l.
8, pp. 1
–
74, M
a
r
. 2021, d
o
i:
10.1186/
s
40537
-
021
-
00444
-
8.
[
21]
S
.
R
.
-
S
a
lz
e
d
o
,
C
r
y
pt
o
gr
aphy
.
G
e
w
e
r
b
e
s
tr
a
s
s
e
11,
6330
C
h
a
m,
S
w
it
z
e
r
la
nd:
S
pr
in
g
e
r
I
n
te
r
na
ti
o
na
l
P
ubl
is
hi
ng
A
G
,
20
18
,
do
i:
ht
tp
s
:/
/d
o
i.
or
g/
10.1007/978
-
3
-
319
-
94818
-
8.
[
22]
S
.
F
a
n
a
nd
Y
.
Z
ha
o
,
“
A
na
l
y
s
is
of
d
e
s
pl
a
in
te
xt
r
e
c
ov
e
r
y
ba
s
e
d
o
n
B
P
ne
u
r
a
l
n
e
tw
o
r
k,
”
Se
c
ur
it
y
and
C
om
m
uni
c
a
ti
on
N
e
tw
o
r
k
s
,
vo
l.
2019, pp. 1
–
5, 2019, d
o
i:
10.1155/2019
/9
580862.
[
23]
C
.
Z
hu,
G
.
W
a
ng,
a
nd
K
.
S
un,
“
C
r
y
pt
a
na
l
y
s
is
a
nd
im
pr
ov
e
m
e
nt
o
n
a
n
im
a
ge
e
n
c
r
y
pt
i
o
n
a
lg
or
it
hm
d
e
s
ig
n
us
in
g
a
nove
l
c
ha
o
s
ba
s
e
d s
-
box
,
”
Sy
m
m
e
tr
y
, v
ol
. 10, n
o
. 9, p. 399, 2018, d
o
i:
10.3
3
90/
s
y
m10090399.
[
24]
S
.
H
a
y
ki
n,
N
e
ur
al
N
e
tw
or
k
s
and
L
e
ar
ni
ng
M
ac
hi
ne
s
,
3r
d
e
d.
,
vol
.
1
–
3.
P
e
a
r
s
o
n
E
du
c
a
ti
o
n,
I
n
c
.,
pub
li
s
hi
ng
a
s
P
r
e
nt
i
c
e
H
a
ll
.,
2009.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
do
n
e
s
i
a
n
J
E
l
e
c
E
n
g
&
C
o
m
p
S
c
i
I
S
S
N:
2
5
0
2
-
4
7
52
De
e
p
lear
ning
-
bas
e
d
c
r
y
ptanal
y
s
is
in
r
e
c
ov
e
r
ing
t
he
s
e
c
r
e
t
k
e
y
and
plai
ntex
t
on
…
(
Y
uli
a
F
atma
)
1123
[
25]
K
.
R
a
j,
B
.
S
ha
r
ma
,
N
.
K
uma
r
,
a
nd
D
.
D
.
K
a
ur
,
“
D
i
f
f
e
r
e
nt
ia
l
c
r
y
pt
a
na
l
y
s
is
o
n
S
-
D
E
S
,
”
I
nt
e
r
nat
io
nal
J
our
nal
of
M
anage
m
e
n
t
&
I
nf
or
m
at
io
n T
e
c
hnol
ogy
, v
o
l.
1, n
o
. 2, pp. 42
–
45, 2012, d
o
i:
10.
24297/i
jm
it
.
v
1i
2.1445.
[
26]
D
.
P
.
K
in
gma
a
nd
J
.
L
.
B
a
,
“
A
da
m:
a
m
e
th
o
d
f
or
s
to
c
ha
s
ti
c
o
p
ti
mi
z
a
ti
o
n,
”
in
3r
d
I
nt
e
r
nat
io
nal
C
onf
e
r
e
nc
e
on
L
e
ar
ni
ng
R
e
pr
e
s
e
nt
at
io
ns
, I
C
L
R
2015
-
C
onf
e
r
e
n
c
e
T
r
ac
k
P
r
oc
e
e
di
ngs
,
2015, pp. 1
–
15
, do
i:
d
o
i.
or
g/
10.48550/ar
X
i
v
.1412.6980.
[
27]
J
.
F
e
ng
a
nd
S
.
L
u,
“
P
e
r
f
or
ma
nc
e
a
na
l
y
s
is
of
v
a
r
io
us
a
c
ti
v
a
ti
o
n
f
un
c
ti
o
ns
in
a
r
t
i
f
i
c
ia
l
n
e
ur
a
l
n
e
tw
o
r
ks
,
”
J
our
nal
of
P
hy
s
ic
s
:
C
on
f
e
r
e
nc
e
Se
r
ie
s
, v
o
l.
1237, n
o
.
2, p. 022
030, J
un. 2019, do
i:
10.1088/1742
-
6596/1237/
2
/0
22030.
B
I
OG
RA
P
HI
E
S
OF
AU
T
HO
RS
Y
u
l
i
a
F
a
t
m
a
c
o
m
p
l
e
t
e
d
ed
u
c
at
i
o
n
Ba
c
h
el
o
r
’
s
d
e
g
r
ee
i
n
t
h
e
D
e
p
art
me
n
t
o
f
I
n
f
o
r
m
at
i
c
s
E
n
g
i
n
ee
ri
n
g
,
U
n
i
v
e
rs
i
t
y
o
f
A
m
i
k
o
m
Y
o
g
y
ak
art
a.
Mas
t
e
r
’
s
d
e
g
r
ee
i
n
Mas
t
e
r
o
f
Co
m
p
u
t
e
r
S
ci
e
n
ce
at
G
ad
j
a
h
Ma
d
a
U
n
i
v
e
rs
i
t
y
.
N
o
w
w
o
r
k
i
n
g
as
a
l
ec
t
u
r
e
r
i
n
t
h
e
D
e
p
art
men
t
o
f
In
fo
r
m
at
i
c
s
,
U
n
i
v
e
rs
i
t
y
o
f
Mu
h
a
mm
ad
i
y
ah
R
i
au
.
W
i
t
h
r
e
s
e
ar
ch
i
n
t
e
r
e
s
t
s
i
n
t
h
e
f
i
e
l
d
o
f
Cr
y
p
t
o
g
rap
h
y
an
d
AI
.
S
h
e
c
an
b
e
co
n
t
a
c
t
ed
at
em
ai
l
:
y
u
l
i
afat
m
a@
u
m
ri
.
ac.
i
d
.
M
uh
a
m
m
a
d
A
km
a
l
R
e
m
l
i
j
o
i
n
s
In
s
t
i
t
u
t
e
fo
r
A
rt
i
f
i
c
i
al
In
t
el
l
i
g
en
ce
an
d
Bi
g
D
at
a
(A
I
B
I
G
),
U
n
i
v
e
rs
i
t
i
Mal
a
y
s
i
a
K
el
a
n
t
an
(U
M
K
)
as
a
f
el
l
o
w
r
e
s
e
ar
ch
e
r
i
n
e
ar
l
y
2
0
2
0
an
d
n
o
w
h
e
i
s
A
I
B
I
G
’
s
d
i
r
ec
t
o
r.
H
e
i
s
al
s
o
a
s
en
i
o
r
l
ec
t
u
r
e
r
at
Fa
c
u
l
t
y
o
f
D
at
a
Sci
e
n
ce
an
d
C
o
m
p
u
t
i
n
g
,
U
K
.
H
e
r
ecei
v
ed
a
Mas
t
e
r
an
d
a
P
h
.
D
.
d
eg
r
ee
i
n
C
o
m
p
u
t
e
r
S
ci
e
n
ce
fr
o
m
U
n
i
v
e
rs
i
t
i
T
e
k
n
o
l
o
g
i
Mal
a
y
s
i
a
i
n
2
0
1
4
an
d
2
0
1
8
b
e
fo
re
j
o
i
n
i
n
g
U
n
i
v
e
rs
i
t
i
M
al
a
y
s
i
a
Pa
h
an
g
fro
m
2
0
1
8
u
n
t
i
l
2
0
2
0
.
I
n
2
0
1
6
,
h
e
w
o
r
k
e
d
at
T
h
e
Bi
o
i
n
fo
r
m
a
t
i
c
s
,
In
t
el
l
i
g
en
t
S
y
s
t
em
s
an
d
E
d
u
c
at
i
o
n
a
l
T
ech
n
o
l
o
g
y
(BI
S
I
T
E
)
R
e
s
e
ar
c
h
G
ro
u
p
at
U
n
i
v
e
rs
i
t
y
o
f
Sa
l
a
m
an
c
a
,
Sp
ai
n
as
r
e
s
e
ar
c
h
at
t
ac
h
men
t
an
d
w
as
w
o
rk
i
n
g
i
n
c
a
n
ce
r
b
i
o
i
n
f
o
r
m
at
i
c
s
.
H
i
s
m
a
i
n
r
e
s
e
ar
c
h
i
n
t
e
r
e
s
t
s
are
art
i
fi
ci
al
i
n
t
e
l
l
i
g
e
n
ce
,
d
at
a
s
c
i
e
n
ce,
b
u
s
i
n
e
s
s
i
n
t
e
l
l
i
g
e
n
ce
an
d
c
o
m
p
u
t
at
i
o
n
al
s
y
s
t
ems
b
i
o
l
o
g
y
.
H
e
h
as
p
u
b
l
i
s
h
ed
n
u
me
r
o
u
s
s
c
i
e
n
t
i
f
i
c
r
e
s
e
ar
ch
p
ap
e
rs
i
n
d
e
x
e
d
b
y
S
co
p
u
s
an
d
Cl
ari
v
at
e
W
e
b
o
f
Sci
e
n
ce
i
n
cl
u
d
i
n
g
i
n
E
x
p
e
rt
S
y
s
t
em
s
w
i
t
h
A
p
p
l
i
c
at
i
o
n
s
(
E
SW
A
)
an
d
E
n
g
i
n
ee
r
i
n
g
A
p
p
l
i
c
at
i
o
n
s
o
f
A
rt
i
fi
ci
al
I
n
t
e
l
l
i
g
e
n
ce
(E
A
A
I
)
j
o
u
rn
a
l
s
.
H
e
c
a
n
b
e
c
o
n
t
ac
t
e
d
at
emai
l
:
ak
m
a
l
@
u
m
k
.
ed
u
.
my
.
M
o
h
d
Sa
beri
M
o
h
a
m
a
d
i
s
a
p
ro
fe
s
s
o
r
o
f
art
i
fi
c
i
a
l
i
n
t
el
l
i
g
en
ce
an
d
h
e
al
t
h
d
at
a
s
c
i
e
n
ce.
H
e
i
s
cu
rr
e
n
t
l
y
t
h
e
D
i
r
ec
t
o
r
o
f
t
h
e
H
e
a
l
t
h
D
at
a
S
c
i
en
ce
L
ab
o
rat
o
r
y
,
D
e
p
art
me
n
t
o
f
G
e
n
e
t
i
c
s
an
d
G
e
n
o
m
i
c
s
.
B
e
f
o
r
e
j
o
i
n
i
n
g
CM
H
S
-
U
A
E
U
,
h
e
w
as
w
i
t
h
s
ev
e
ral
u
n
i
v
e
rs
i
t
i
e
s
i
n
Mal
a
y
s
i
a
as
t
h
e
D
i
r
e
c
t
o
r
o
f
t
h
e
In
s
t
i
t
u
t
e
fo
r
A
I
an
d
b
i
g
d
at
a
,
t
h
e
h
e
ad
o
f
t
h
e
A
I
a
n
d
Bi
o
i
n
f
o
rm
at
i
c
s
R
e
s
e
ar
c
h
G
ro
u
p
,
a
Fo
u
n
d
e
r
o
f
t
h
e
D
e
p
ar
t
m
en
t
o
f
D
at
a
S
c
i
en
ce
,
t
h
e
Man
a
g
e
r
o
f
I
T
,
a
n
d
t
h
e
D
e
p
u
t
y
D
i
r
ec
t
o
r
(A
c
a
d
em
i
c
)
fo
r
C
en
t
re
o
f
Co
m
p
u
t
i
n
g
an
d
I
n
f
o
r
m
at
i
c
s
.
I
n
ap
p
rec
i
at
i
o
n
o
f
h
i
s
l
e
a
d
e
rs
h
i
p
,
t
h
e
u
n
i
v
e
rs
i
t
y
h
as
ap
p
o
i
n
t
e
d
h
i
m
as
a
mem
b
e
r
o
f
U
n
i
v
e
rs
i
t
y
Sen
at
e
.
A
d
d
i
t
i
o
n
a
l
l
y
,
h
e
i
s
a
mem
b
e
r
o
f
t
h
e
A
d
v
i
s
o
r
y
B
o
ard
f
o
r
t
h
e
A
I
R
e
s
e
ar
c
h
I
n
s
t
i
t
u
t
e
a
n
d
I
o
T
D
i
g
i
t
al
In
n
o
v
at
i
o
n
H
u
b
i
n
E
u
ro
p
e
.
I
n
ad
d
i
t
i
o
n
t
o
b
e
i
n
g
t
h
e
p
ri
n
c
i
p
al
i
n
v
e
s
t
i
g
at
o
r
o
n
2
1
re
s
e
ar
ch
g
ra
n
t
s
an
d
t
h
e
c
o
-
P
l
o
n
2
0
re
s
e
ar
ch
g
ran
t
s
,
h
e
h
as
p
u
b
l
i
s
h
e
d
3
0
4
art
i
c
l
e
s
i
n
i
n
t
e
r
n
at
i
o
n
al
r
e
fe
r
eed
j
o
u
rn
a
l
s
an
d
i
n
t
e
rn
at
i
o
n
a
l
c
o
n
f
e
r
e
n
ce
s
,
b
o
o
k
ch
ap
t
e
rs
,
an
d
1
7
b
o
o
k
s
.
H
i
s
r
e
s
e
ar
ch
i
n
t
e
r
e
s
t
s
i
n
cl
u
d
e
art
i
f
i
c
i
a
l
i
n
t
el
l
i
g
en
ce
,
d
at
a
s
c
i
en
ce
,
a
n
d
b
i
o
i
n
f
o
r
m
at
i
c
s
.
H
e
c
an
b
e
c
o
n
t
ac
t
e
d
at
em
a
i
l
:
s
ab
e
ri
@
u
a
eu
.
a
c
.
a
e
.
J
a
n
u
a
r
A
l
A
m
i
e
n
c
o
m
p
l
e
t
e
d
e
d
u
c
at
i
o
n
Ba
c
h
el
o
r
’
s
d
eg
r
ee
i
n
t
h
e
D
e
p
art
me
n
t
o
f
I
n
f
o
r
m
at
i
c
s
E
n
g
i
n
ee
r
i
n
g
,
ST
M
IK
-
A
M
IK
Ri
a
u
.
Mas
t
er
’
s
d
eg
r
ee
i
n
Mas
t
e
r
o
f
In
fo
r
m
at
i
o
n
T
e
ch
n
o
l
o
g
y
at
Pu
t
ra
In
d
o
n
e
s
i
a
U
n
i
v
e
rs
i
t
y
Pa
d
an
g
.
N
o
w
w
o
rk
i
n
g
as
a
l
ec
t
u
r
e
r
i
n
t
h
e
D
e
p
art
men
t
o
f
Co
m
p
u
t
e
r
S
c
i
en
ce
,
U
n
i
v
e
rs
i
t
y
M
u
h
a
mmad
i
y
a
h
o
f
R
i
au
.
W
i
t
h
r
e
s
e
ar
ch
i
n
t
e
r
e
s
t
s
i
n
t
h
e
f
i
e
l
d
o
f
m
a
c
h
i
n
e
l
e
arn
i
n
g
al
g
o
r
i
t
h
m
s
an
d
A
I.
H
e
c
an
b
e
c
o
n
t
ac
t
e
d
at
em
a
i
l
:
j
an
u
ara
l
a
m
i
en
@
u
m
ri
.
ac.
i
d.
Evaluation Warning : The document was created with Spire.PDF for Python.