IA
E
S
In
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
Ar
t
i
f
i
c
i
a
l
In
t
e
l
l
i
g
e
n
c
e
(I
J
-
AI
)
Vo
l
.
8
, N
o
.
1
,
Ma
r
c
h
201
9
, p
p
.
4
4
~
5
3
IS
S
N
:
2252
-
8938
,
DOI
:
1
0
.
1
1
5
9
1
/
i
j
a
i
.
v
8
.i
1
.p
p
4
4
-
5
3
r
44
Jou
r
n
al
h
om
e
page
:
ht
t
p:
/
/
i
ae
s
co
r
e
.c
o
m
/o
n
lin
e
/in
d
e
x
.p
h
p
/I
J
A
I
Mu
l
t
i
l
a
y
e
r
n
e
u
r
a
l
n
e
t
w
o
r
k
s
y
n
c
h
r
o
n
i
z
e
d
s
e
c
u
r
e
d
s
e
s
s
i
o
n
k
e
y
ba
s
e
d
e
nc
r
y
pt
i
o
n
i
n
w
i
r
e
l
e
s
s
c
o
m
m
uni
c
a
t
i
o
n
Ar
i
n
d
a
m
S
a
r
k
a
r
Ra
m
a
k
r
i
s
h
n
a
M
i
s
s
i
o
n
V
i
d
y
a
m
a
n
d
i
r
a
,
Be
l
u
r
M
a
t
h
-
711202,
I
ndi
a
Ar
t
i
c
l
e
I
n
f
o
AB
S
T
RACT
Ar
t
i
c
l
e
h
i
s
t
o
r
y
:
Re
c
e
i
v
e
d
No
v
15
, 2
0
1
8
Re
v
i
s
e
d
J
a
n
30
, 2
0
1
9
Ac
c
e
p
t
e
d
F
e
b
15
, 2
0
1
9
In
t
h
i
s
p
a
p
e
r,
m
u
l
t
i
l
a
y
e
r
n
e
u
ra
l
n
e
t
w
o
rk
s
y
n
c
h
ro
n
i
z
e
d
s
e
s
s
i
o
n
k
e
y
b
a
s
e
d
en
cr
y
p
t
i
o
n
h
as
b
een
p
r
o
p
o
sed
f
o
r
w
i
r
el
ess
co
m
m
u
n
i
cat
i
o
n
o
f
d
at
a/
i
n
f
o
r
m
at
i
o
n
.
Mu
l
t
i
l
a
y
e
r
p
e
r
c
e
p
t
r
o
n
t
r
a
n
s
m
i
t
t
i
n
g
s
y
s
t
e
m
s
a
t
b
o
t
h
e
n
d
s
a
c
c
e
p
t
a
n
i
d
e
n
t
i
c
a
l
in
p
u
t
v
e
c
to
r
,
g
e
n
e
r
a
te
a
n
o
u
tp
u
t
b
it
a
n
d
th
e
n
e
tw
o
r
k
a
r
e
tr
a
in
e
d
b
a
s
e
d
o
n
th
e
out
put
bi
t
w
hi
c
h
i
s
us
e
d
t
o
f
or
m
a
pr
ot
e
c
t
e
d
va
r
i
a
bl
e
l
e
ngt
h
s
e
c
r
e
t
-
ke
y.
F
or
each
sessi
o
n
,
d
i
f
f
er
en
t
h
i
d
d
en
l
ay
er
o
f
m
u
l
t
i
l
ay
er
n
eu
r
al
n
et
w
o
r
k
i
s
sel
ect
ed
ra
n
d
o
m
l
y
a
n
d
w
e
i
g
h
t
s
o
r
h
i
d
d
e
n
u
n
i
t
s
o
f
t
h
i
s
s
e
l
e
c
t
e
d
hi
dde
n
l
a
ye
r
he
l
p
t
o
f
or
m
a
secr
et
sessi
o
n
k
ey
.
T
h
e
p
l
ai
n
t
ex
t
i
s
en
cr
y
p
t
ed
t
h
r
o
u
g
h
ch
ai
n
i
n
g
,
cascad
ed
xor
i
ng
of
m
ul
t
i
l
a
ye
r
pe
r
c
e
pt
r
on
ge
ne
r
a
t
e
d
s
e
s
s
i
on
ke
y.
I
f
s
i
z
e
of
t
he
f
i
na
l
bl
oc
k
of
pl
a
i
n
t
e
xt
i
s
l
e
s
s
t
ha
n
t
he
s
i
z
e
of
t
he
ke
y
t
he
n
t
hi
s
bl
oc
k
i
s
ke
pt
una
l
t
e
r
e
d.
Re
c
e
i
v
e
r
w
i
l
l
u
s
e
i
d
e
n
t
i
c
a
l
m
u
l
t
i
l
a
y
e
r
p
e
r
c
e
p
t
r
o
n
g
e
n
e
r
a
t
e
d
s
e
s
s
i
o
n
k
e
y
f
o
r
pe
r
f
or
m
i
ng
de
c
i
phe
r
i
ng
pr
oc
e
s
s
f
or
ge
t
t
i
ng
t
he
pl
a
i
n
t
e
xt
.
P
a
r
a
m
e
t
r
i
c
t
e
s
t
s
ha
ve
be
e
n
done
a
nd
r
e
s
ul
t
s
a
r
e
c
om
pa
r
e
d
i
n
t
e
r
m
s
of
C
hi
-
Sq
u
a
r
e
t
e
s
t
,
r
e
s
p
o
n
s
e
t
i
m
e
in
tr
a
n
s
m
i
ssi
o
n
w
i
t
h
so
m
e
ex
i
st
i
n
g
cl
assi
cal
t
ech
n
i
q
u
es,
w
h
i
ch
sh
o
w
s
co
m
p
ar
ab
l
e
r
esu
l
t
s
f
o
r
t
h
e
p
r
o
p
o
sed
t
ech
n
i
q
u
e.
Ke
y
wo
r
d
s
:
Mu
l
t
i
l
a
y
e
r
N
e
u
r
a
l
N
e
t
w
o
r
k
Se
s
s
i
o
n
K
e
y
Wi
r
e
l
e
s
s
C
o
m
m
u
n
i
c
a
t
i
o
n
Co
p
y
r
i
g
h
t
©
2
0
1
9
In
s
t
i
t
u
t
e
o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
r
i
n
g
a
n
d
S
c
i
e
n
c
e
.
Al
l
ri
g
h
t
s
reserved
.
Co
r
r
e
s
p
o
n
d
i
n
g
Au
t
h
o
r
:
Ar
i
n
d
a
m
S
a
r
k
a
r
,
De
p
a
r
t
m
e
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
Ra
m
a
k
r
i
s
h
n
a
M
i
s
s
i
o
n
V
i
d
y
a
m
a
n
d
i
r
a
,
Be
l
u
r
M
a
t
h
-
711202,
I
ndi
a
.
Em
a
i
l
:
ar
i
n
d
am
.
v
b
@
g
m
ai
l
.
co
m
1.
IN
T
R
O
D
U
C
T
IO
N
In
re
c
e
n
t
t
i
m
e
s
w
i
d
e
ra
n
g
e
s
o
f
t
e
c
h
n
i
q
u
e
s
a
re
d
e
v
e
l
o
p
e
d
t
o
p
ro
t
e
c
t
d
a
t
a
a
n
d
i
n
fo
rm
a
t
i
o
n
fro
m
eav
es
d
r
o
p
p
er
s
[
1
-
6]
.
T
he
s
e
a
l
gor
i
t
hm
s
ha
ve
t
he
i
r
vi
r
t
ue
a
nd
s
h
or
t
c
om
i
ngs
.
F
or
E
xa
m
pl
e
i
n
D
E
S
,
AE
S
a
l
g
o
r
i
t
h
m
s
t
h
e
c
i
p
h
e
r
b
l
o
c
k
l
e
n
g
t
h
i
s
n
o
n
f
l
e
x
i
b
l
e
.
I
n
C
S
C
T
[
7
]
,
K
SO
M
SC
T
[
8
]
,
t
e
c
h
n
i
q
u
e
u
s
e
s
t
w
o
n
e
u
r
a
l
ne
t
w
or
k
one
f
or
s
e
nde
r
a
nd
a
not
he
r
f
or
r
e
c
e
i
ve
r
ha
vi
ng
one
hi
dde
n
l
a
ye
r
f
or
pr
oduc
i
ng
s
ync
hr
oni
z
e
d
w
e
i
ght
ve
c
t
or
f
or
ke
y
ge
ne
r
a
t
i
on.
N
ow
a
t
t
a
c
ke
r
c
a
n
ge
t
a
n
i
de
a
a
bout
s
e
nde
r
a
nd
r
e
c
e
i
ve
r
’
s
ne
ur
a
l
m
a
c
hi
ne
be
c
a
us
e
fo
r
e
ach
s
es
s
i
o
n
ar
ch
i
t
ect
u
r
e
o
f
n
eu
r
al
m
ach
i
n
e
i
s
s
t
at
i
c.
I
n
N
G
K
R
M
S
M
C
al
g
o
r
i
t
h
m
[
9
]
an
y
i
n
t
er
m
ed
i
at
e
b
l
o
ck
s
th
r
o
u
g
h
o
u
t
its
cy
cl
e
t
ak
en
as
t
h
e
en
cr
y
p
t
ed
b
l
o
ck
an
d
t
h
i
s
n
u
m
b
er
o
f
ite
r
a
tio
n
s
a
c
ts
a
s
s
e
c
r
e
t
k
e
y
.
He
r
e
i
f
n
n
u
m
b
e
r
o
f
i
t
e
r
a
t
i
o
n
s
a
r
e
n
e
e
d
e
d
f
o
r
c
y
c
l
e
fo
rm
a
t
i
o
n
a
n
d
i
f
i
n
t
e
rm
e
d
i
a
t
e
b
l
o
c
k
i
s
c
h
o
s
e
n
a
s
a
n
e
n
c
ry
p
t
e
d
bl
oc
k
a
f
t
e
r
n/
2
th
ite
r
a
tio
n
th
e
n
e
x
a
c
tly
s
a
m
e
n
u
m
b
e
r
o
f
ite
r
a
tio
n
s
i.e
.
n
/2
a
r
e
n
e
e
d
e
d
f
o
r
d
e
c
o
d
e
th
e
b
lo
c
k
w
h
ic
h
ma
k
e
s
e
a
s
i
e
r
t
h
e
a
t
t
a
c
k
e
r
s
l
i
f
e
.
T
o
s
o
l
v
e
t
h
e
s
e
t
y
p
e
s
o
f
p
r
o
b
l
e
ms
i
n
t
h
i
s
p
a
p
e
r
we
h
a
v
e
p
r
o
p
o
s
e
d
a
m
u
l
t
i
l
a
y
e
r
ne
ur
a
l
ne
t
w
or
k
gui
de
d
e
nc
r
ypt
i
on
t
e
c
hni
que
i
n
w
i
r
e
l
e
s
s
c
om
m
uni
c
a
t
i
on.
T
he
or
ga
ni
z
a
t
i
on
of
t
hi
s
pa
pe
r
i
s
a
s
fo
l
l
o
w
s
.
S
e
c
t
i
o
n
2
o
f
t
h
e
p
a
p
e
r
d
e
a
l
s
w
i
t
h
t
h
e
p
ro
b
l
e
m
d
o
m
a
i
n
a
n
d
m
e
t
h
o
d
o
l
o
g
y
.
P
ro
p
o
s
e
d
m
u
l
t
i
l
a
y
e
r
n
e
u
ra
l
ne
t
w
or
k
ba
s
e
d
ke
y
ge
ne
r
a
t
i
on
ha
s
be
e
n
di
s
c
us
s
e
d
i
n
s
e
c
t
i
on
3.
T
r
i
a
ngul
a
r
i
z
a
t
i
on
e
nc
r
ypt
i
on
t
e
c
hni
que
i
s
gi
ve
n
in
s
e
c
tio
n
4
.
S
e
c
tio
n
5
p
r
e
s
e
n
ts
e
n
e
r
g
y
c
o
m
p
u
ta
tio
n
te
c
h
n
iq
u
e
.
E
x
p
e
r
im
e
n
ta
l
r
e
s
u
lts
a
r
e
d
e
s
c
r
ib
e
d
in
s
e
c
tio
n
6
.
An
a
l
y
s
i
s
r
e
g
a
r
d
i
n
g
v
a
r
i
o
u
s
s
e
c
u
r
i
t
y
a
s
p
e
c
t
s
o
f
th
e
te
c
h
n
iq
u
e
h
a
s
b
e
e
n
p
r
e
s
e
n
te
d
in
s
e
c
tio
n
7
.
C
o
n
c
lu
s
io
n
s
a
n
d
fu
t
u
re
s
c
o
p
e
a
re
d
ra
w
n
i
n
s
e
c
t
i
o
n
8
a
n
d
t
h
a
t
o
f
re
fe
re
n
c
e
s
a
t
e
n
d
.
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
AI
IS
S
N
:
2252
-
8938
r
Mu
l
t
i
l
a
y
e
r
n
e
u
r
a
l
n
e
t
w
o
r
k
s
y
n
c
h
r
o
n
i
z
e
d
s
e
c
u
r
e
d
s
e
s
s
i
o
n
k
e
y
b
a
s
e
d
e
n
c
r
y
p
t
i
o
n
i
n
…
(
Ar
i
n
d
a
m
S
a
r
k
a
r
)
45
2.
PR
O
B
L
E
M
DO
M
AI
N
AND
M
E
T
H
O
DO
L
O
G
Y
In
s
e
c
u
ri
t
y
b
a
s
e
d
c
o
m
m
u
n
i
c
a
t
i
o
n
t
h
e
m
a
i
n
p
ro
b
l
e
m
i
s
d
i
s
t
ri
b
u
t
i
o
n
o
f
k
e
y
b
e
t
w
e
e
n
s
e
n
d
e
r
a
n
d
re
c
e
i
v
e
r.
Be
c
a
u
s
e
a
t
t
h
e
t
i
m
e
o
f
e
x
c
h
a
n
g
e
o
f
k
e
y
o
v
e
r
p
u
b
l
i
c
c
h
a
n
n
e
l
i
n
t
r
u
d
e
r
s
c
a
n
i
n
t
e
r
c
e
p
t
t
h
e
k
e
y
b
y
re
s
i
d
i
n
g
in
be
t
w
e
e
n
t
he
m
.
T
hi
s
pa
r
t
i
c
ul
a
r
pr
obl
e
m
ha
s
be
e
n
a
d
dr
e
s
s
e
d
a
nd
a
t
e
c
hni
que
ha
s
be
e
n
pr
opos
e
d
t
e
c
hni
que
ad
d
r
es
s
ed
t
h
i
s
p
r
o
b
l
em
.
T
h
es
e
ar
e
p
r
es
en
t
ed
i
n
s
ect
i
o
n
2
.
1
an
d
2
.
2
r
es
p
ect
i
v
el
y
.
2.
1.
Ma
n
-
In
-
Th
e
-
Mi
d
d
l
e
A
t
t
a
c
k
In
t
ru
d
e
rs
in
te
r
c
e
p
tin
g
in
th
e
m
id
d
le
o
f
s
e
n
d
e
r
a
n
d
r
e
c
e
iv
e
r
a
n
d
tr
y
to
c
a
p
tu
r
e
a
ll
th
e
in
f
o
rm
a
t
i
o
n
tr
a
n
s
m
ittin
g
f
r
o
m
b
o
th
p
a
r
tie
s
.
D
if
f
ie
-
He
l
l
m
a
n
k
e
y
e
x
c
h
a
n
g
e
t
e
c
h
n
i
q
u
e
[
1
]
s
u
f
f
e
r
s
f
r
o
m
t
h
i
s
t
y
p
e
o
f
p
r
o
b
l
e
m
s
.
In
t
ru
d
e
rs
c
a
n
a
c
t
a
s
s
e
n
d
e
r
a
n
d
re
c
e
i
v
e
r
s
i
m
u
l
t
a
n
e
o
u
s
l
y
a
n
d
t
ry
t
o
s
t
e
a
l
s
e
c
re
t
s
e
s
s
i
o
n
k
e
y
a
t
t
h
e
t
i
m
e
o
f
ex
ch
an
g
i
n
g
k
ey
v
i
a
p
u
b
l
i
c
ch
an
n
el
.
2.
2.
Me
t
h
o
d
o
l
o
g
y
i
n
P
r
o
p
o
s
e
d
t
e
c
h
n
i
q
u
e
Th
i
s
w
e
l
l
k
n
o
w
n
p
r
o
b
l
e
m
o
f
m
i
d
d
l
e
m
a
n
a
t
t
a
c
k
h
a
s
b
e
e
n
a
d
d
r
e
s
s
e
d
i
n
p
r
o
p
o
s
e
d
t
e
c
h
n
i
q
u
e
w
h
e
r
e
se
c
r
e
t
se
ssi
o
n
k
e
y
i
s
n
o
t
e
x
c
h
a
n
g
e
d
o
v
e
r
p
u
b
l
i
c
i
n
se
c
u
r
e
c
h
a
n
n
e
l
.
A
t
e
n
d
o
f
n
e
u
r
a
l
w
e
i
g
h
t
sy
n
c
h
r
o
n
i
z
a
t
i
o
n
st
r
a
t
e
g
y
o
f
bot
h
pa
r
t
i
e
s
ge
ne
r
a
t
e
s
i
de
nt
i
c
a
l
w
e
i
ght
ve
c
t
or
s
a
nd
a
c
t
i
va
t
e
d
hi
dde
n
l
a
ye
r
out
put
s
f
or
bot
h
t
he
pa
r
t
i
e
s
be
c
om
e
i
de
nt
i
c
a
l
.
T
hi
s
i
de
nt
i
c
a
l
out
put
of
hi
dde
n
l
a
ye
r
f
or
bot
h
pa
r
t
i
e
s
c
a
n
be
us
e
a
s
one
-
tim
e
s
e
c
r
e
t
s
e
s
s
io
n
ke
y
f
or
s
e
c
ur
e
d
da
t
a
e
xc
ha
nge
.
3.
MU
L
T
I
L
A
Y
ER
P
ER
C
EP
TR
O
N
BA
S
ED
S
ES
S
I
O
N
K
EY
G
EN
ER
A
TI
O
N
S
Y
S
TEM
A
m
u
l
t
i
l
a
y
e
r
p
e
r
c
e
p
t
r
o
n
s
y
n
a
p
t
i
c
s
i
m
u
l
a
t
e
d
we
i
g
h
t
b
a
s
e
d
u
n
d
i
s
c
l
o
s
e
d
k
e
y
g
e
n
e
r
a
t
i
o
n
i
s
c
a
r
r
i
e
d
o
u
t
be
t
w
e
e
n
r
e
c
i
pi
e
nt
a
nd
s
e
nde
r
.
F
i
gur
e
1
s
how
s
m
ul
t
i
l
a
ye
r
pe
r
c
e
pt
r
on
ba
se
d
sy
n
a
p
t
i
c
si
m
u
l
a
t
i
o
n
sy
st
e
m
.
Se
n
d
e
r
an
d
r
ecei
v
er
s
m
u
l
t
i
l
ay
er
p
er
cep
t
r
o
n
s
el
ect
s
am
e
s
i
n
g
l
e
h
i
d
d
en
l
ay
er
am
o
n
g
m
u
l
t
i
p
l
e
h
i
d
d
en
l
ay
er
s
f
o
r
a
pa
r
t
i
c
ul
a
r
s
e
s
s
i
on.
F
or
t
ha
t
s
e
s
s
i
on
a
l
l
ot
he
r
hi
dde
n
l
a
ye
r
s
goe
s
i
n
de
a
c
t
i
va
t
e
d
m
ode
m
e
a
ns
hi
dde
n
(
pr
oc
e
s
s
i
ng)
uni
t
s
of
ot
he
r
l
a
ye
r
s
do
not
hi
ng
w
i
t
h
t
h
e
i
n
co
m
i
n
g
i
n
p
u
t
.
E
i
t
h
er
s
y
n
ch
r
o
n
i
zed
i
d
en
t
i
cal
w
ei
g
h
t
v
ect
o
r
o
f
s
en
d
er
an
d
r
ecei
v
er
s
’
i
n
p
u
t
l
ay
er
,
act
i
v
at
ed
h
i
d
d
en
l
ay
er
an
d
o
u
t
p
u
t
l
ay
er
b
eco
m
es
s
es
s
i
o
n
k
ey
o
r
s
es
s
i
o
n
k
ey
can
b
e
fo
rm
u
s
i
n
g
i
d
e
n
t
i
c
a
l
o
u
t
p
u
t
o
f
h
i
d
d
e
n
u
n
i
t
s
o
f
a
c
t
i
v
a
t
e
d
h
i
d
d
e
n
l
a
y
e
r.
T
h
e
ke
y
ge
ne
r
a
t
i
on
t
e
c
hni
que
a
nd
a
na
l
ys
i
s
of
t
he
t
e
c
hni
que
us
i
ng
r
a
ndom
num
be
r
of
node
s
(
ne
ur
ons
)
a
nd
t
he
c
or
r
e
s
pondi
ng
a
l
gor
i
t
hm
i
s
di
s
c
us
s
e
d
i
n
t
he
su
b
se
c
t
i
o
n
s
3
.
1
t
o
3
.
5
i
n
d
e
t
a
i
l
s.
3.
1.
Mu
t
u
a
l
S
y
n
c
h
r
o
n
i
z
a
t
i
o
n
p
r
o
c
e
d
u
r
e
Se
n
d
e
r
a
n
d
r
e
c
e
i
v
e
r
m
u
l
t
i
l
a
y
e
r
p
e
r
cep
t
r
o
n
i
n
each
s
es
s
i
o
n
act
s
as
a
s
i
n
g
l
e
l
ay
er
n
et
w
o
r
k
w
i
t
h
dyna
m
i
c
a
l
l
y
c
hos
e
n
one
a
c
t
i
va
t
e
d
hi
dde
n
l
a
ye
r
a
nd
K
no.
of
hi
dde
n
ne
ur
ons
,
N
no.
of
i
nput
ne
ur
ons
ha
vi
ng
bi
na
r
y
i
nput
ve
c
t
or
,
{
}
1
,
1
+
−
∈
ij
x
,
di
s
c
r
e
t
e
w
e
i
ght
s
,
a
r
e
ge
ne
r
a
t
e
d
f
r
om
i
nput
t
o
o
ut
put
,
a
r
e
l
i
e
s
be
t
w
e
e
n
-
L
a
n
d
+L
,
{
}
L
L
L
w
ij
+
+
−
−
∈
,.
..
,
1
,
.
Wh
e
r
e
i
=
1
,
…
,
K
d
e
n
o
t
e
s
t
h
e
i
th
hi
dde
n
uni
t
of
t
he
pe
r
c
e
pt
r
on
a
nd
j
=
1
,…
,N
th
e
e
le
m
e
n
ts
o
f
th
e
v
e
c
to
r
a
n
d
o
n
e
o
u
tp
u
t
n
e
u
r
o
n
.
O
u
tp
u
t
o
f
th
e
h
id
d
e
n
u
n
its
is
c
a
lc
u
la
te
d
b
y
th
e
we
i
g
h
t
e
d
s
u
m
o
v
e
r
t
h
e
cu
r
r
en
t
i
n
p
u
t
v
al
u
es
.
S
o
,
t
h
e
s
t
at
e
o
f
t
h
e
each
h
i
d
d
en
n
eu
r
o
n
s
i
s
ex
p
r
es
s
ed
u
s
i
n
g
(
1
)
j
i
N
j
j
i
i
i
i
x
w
N
x
w
N
h
,
1
,
1
1
∑
=
=
=
(1
)
Ou
t
p
u
t
o
f
t
h
e
i
th
hi
dde
n
uni
t
i
s
de
f
i
ne
d
a
s
)
sg
n
(
i
i
h
=
σ
(2
)
Bu
t
i
n
c
a
s
e
o
f
i
h
=
0
t
h
e
n
i
σ
=
-
1
t
o
pr
oduc
e
a
bi
na
r
y
out
put
.
H
e
nc
e
a
,
i
σ
=
+1
,
i
f
t
h
e
w
e
i
g
h
t
e
d
s
u
m
ove
r
i
t
s
i
nput
s
i
s
pos
i
t
i
ve
,
or
e
l
s
e
i
t
i
s
i
na
c
t
i
ve
,
i
σ
=
-
1.
T
he
t
ot
a
l
out
put
of
a
pe
r
c
e
pt
r
on
i
s
t
he
pr
oduc
t
of
t
he
hi
dde
n
uni
t
s
e
xpr
e
s
s
e
d
i
n
(
2)
∏
=
=
K
i
i
1
σ
τ
(3
)
Evaluation Warning : The document was created with Spire.PDF for Python.
r
IS
S
N
:
2252
-
8938
IJ
-
AI
Vo
l
.
8
, N
o
.
1
,
Ma
r
c
h
20
1
9
:
4
4
–
5
3
46
Co
m
p
a
r
e
t
h
e
o
u
t
p
u
t
v
a
l
u
e
s
o
f
b
o
t
h
m
u
l
t
i
l
a
y
e
r
p
e
r
c
e
p
t
r
o
n
b
y
e
x
c
h
a
n
g
i
n
g
t
h
e
s
y
s
t
e
m
o
u
t
p
u
t
s
.
i
f
O
u
t
p
u
t
(
A
)
≠
Ou
t
p
u
t
(
B
)
,
Go
t
o
s
t
e
p
3
.
e
l
s
e
i
f
Ou
t
p
u
t
(
A)
=
Ou
t
p
u
t
(
B
)
t
h
e
n
o
n
e
o
f
t
h
e
s
u
i
t
a
b
l
e
l
e
a
r
n
i
n
g
r
u
l
e
i
s
a
p
p
l
i
e
d
o
n
l
y
th
e
h
id
d
e
n
u
n
its
a
r
e
tr
a
in
e
d
w
h
ic
h
h
a
ve
a
n
out
put
bi
t
i
de
nt
i
c
a
l
t
o
t
he
c
om
m
on
out
put
.
U
pda
t
e
t
he
w
e
i
ght
s
onl
y
if
th
e
f
in
a
l
o
u
tp
u
t
v
a
lu
e
s
o
f
th
e
p
e
r
c
e
p
tr
o
n
a
r
e
e
q
u
iv
a
le
n
t.
W
h
e
n
s
y
n
c
h
r
o
n
iz
a
tio
n
is
f
in
a
lly
a
c
h
ie
v
e
d
,
th
e
sy
n
a
p
t
i
c
w
e
i
g
h
t
s
a
r
e
i
d
e
n
t
i
c
a
l
f
o
r
b
o
t
h
t
h
e
sy
st
e
m
.
3.
2.
Mu
l
t
i
l
a
y
e
r
N
e
u
r
a
l N
e
t
w
o
r
k
L
e
a
r
n
in
g
r
u
le
At
t
h
e
b
e
g
i
n
n
i
n
g
o
f
t
h
e
s
y
n
c
h
r
o
n
i
z
a
t
i
o
n
p
r
o
c
e
s
s
m
u
l
t
i
l
a
y
e
r
p
e
r
c
e
p
t
r
o
n
o
f
A
a
n
d
B
s
t
a
r
t
wi
t
h
unc
or
r
e
l
a
t
e
d
w
e
i
ght
ve
c
t
or
s
B
A
i
w
/
.
F
o
r
each
t
i
m
e
s
t
ep
K
,
p
u
b
l
i
c
i
n
p
u
t
v
ect
o
r
s
ar
e
g
en
er
at
ed
r
an
d
o
m
l
y
an
d
t
h
e
co
r
r
es
p
o
n
d
i
n
g
o
ut
put
bi
t
s
τ
A/
B
ar
e
cal
cu
l
at
ed
.
A
f
t
er
w
ar
d
s
A
an
d
B
co
m
m
u
n
i
cat
e
t
h
ei
r
o
u
t
p
u
t
b
i
t
s
t
o
each
o
t
h
er
.
If
t
h
e
y
d
i
s
a
g
re
e
,
τ
A
≠
τ
B
,
th
e
w
e
ig
h
ts
a
r
e
n
o
t
c
h
a
n
g
e
d
.
O
th
e
r
w
is
e
le
a
r
n
in
g
r
u
le
s
s
u
ita
b
le
f
o
r
sy
n
c
h
r
o
n
i
z
a
t
i
o
n
is
a
p
p
lie
d
. I
n
th
e
c
a
s
e
o
f
th
e
H
e
b
b
ia
n
le
a
r
n
in
g
r
u
le
[1
0
]
b
o
t
h
n
e
u
ra
l
n
e
t
w
o
rk
s
l
e
a
rn
fro
m
e
a
c
h
o
t
h
e
r.
(
)
(
)
(
)
B
A
i
j
i
j
i
x
w
g
w
j
i
τ
τ
τ
σ
τ
Θ
Θ
+
=
+
,
,
,
(4
)
Th
e
l
e
a
r
n
i
n
g
r
u
l
e
s
u
s
e
d
f
o
r
s
y
n
c
h
r
o
n
i
z
i
n
g
m
u
l
t
i
l
a
y
e
r
p
e
r
c
e
p
t
r
o
n
s
h
a
r
e
a
c
o
m
m
o
n
s
t
r
u
c
t
u
r
e
.
(
)
(
)
j
i
B
A
i
j
i
x
f
w
g
w
j
i
,
,
,
,
,
τ
τ
σ
+
=
+
(5
)
wi
t
h
a
f
u
n
c
t
i
o
n
(
)
B
A
i
f
τ
τ
σ
,
,
,
w
h
ic
h
c
a
n
ta
k
e
th
e
v
a
lu
e
s
-
1,
0,
or
+
1.
I
n
t
he
c
a
s
e
of
bi
di
r
e
c
t
i
ona
l
in
te
r
a
c
tio
n
it is
g
iv
e
n
b
y
(
)
(
)
(
)
⎪
⎩
⎪
⎨
⎧
−
Θ
Θ
=
1
,
,
σ
σ
τ
τ
στ
τ
τ
σ
B
A
A
B
A
i
f
(6
)
Th
e
c
o
m
m
o
n
p
a
r
t
(
)
(
)
B
A
A
τ
τ
στ
Θ
Θ
of
(
)
B
A
i
f
τ
τ
σ
,
,
co
n
t
r
o
l
s
,
w
h
en
t
h
e
w
ei
g
h
t
v
ect
o
r
o
f
a
h
i
d
d
en
uni
t
i
s
a
dj
us
t
e
d.
B
e
c
a
us
e
i
t
i
s
r
e
s
pons
i
bl
e
f
or
t
he
oc
c
ur
r
e
nc
e
of
a
t
t
r
a
c
t
i
ve
a
nd
r
e
pul
s
i
ve
s
t
e
ps
[
6]
.
3.
3.
We
i
g
h
t
D
i
s
t
r
i
b
u
t
i
o
n
o
f
M
u
l
t
i
l
a
y
e
r
N
e
u
ra
l
N
et
w
o
rk
In
c
a
s
e
o
f
t
h
e
H
e
b
b
i
a
n
ru
l
e
(7
),
A
'
s
a
n
d
B
'
s
m
u
l
t
i
l
a
y
e
r
p
e
rc
e
p
t
ro
n
l
e
a
rn
t
h
e
i
r
o
w
n
o
u
t
p
u
t
.
T
h
e
re
fo
re
th
e
d
ir
e
c
tio
n
in
w
h
ic
h
th
e
w
e
ig
h
t
j
i
w
,
mo
v
e
s
i
s
d
e
t
e
r
mi
n
e
d
b
y
t
h
e
p
r
o
d
u
c
t
j
i
i
x
,
σ
.
A
s
th
e
o
u
tp
u
t
i
σ
is
a
f
u
n
c
tio
n
of
a
l
l
i
nput
va
l
ue
s
,
j
i
x
,
an
d
i
σ
ar
e
co
r
r
el
at
ed
r
an
d
o
m
v
ar
i
ab
l
es
.
T
h
u
s
t
h
e
p
r
o
b
ab
i
l
i
t
i
es
t
o
o
b
s
er
v
e
j
i
i
x
,
σ
=
+1
or
j
i
i
x
,
σ
=
-
1
a
r
e
not
e
qua
l
,
but
de
pe
nd
on
th
e
v
a
lu
e
o
f
th
e
c
o
r
r
e
s
p
o
n
d
in
g
w
e
ig
h
t
j
i
w
,
[1
1
,
1
3
-
16]
.
(
)
⎥
⎥
⎦
⎤
⎢
⎢
⎣
⎡
⎟
⎟
⎟
⎠
⎞
⎜
⎜
⎜
⎝
⎛
−
+
=
=
2
,
,
,
1
2
1
1
j
i
i
j
i
j
i
i
w
NQ
w
er
f
x
P
σ
(7
)
Ac
c
o
r
d
i
n
g
t
o
t
h
i
s
e
q
u
a
t
i
o
n
,
)
sg
n
(
,
,
j
i
j
i
i
w
x
=
σ
oc
c
ur
s
m
or
e
of
t
e
n
t
ha
n
t
he
oppos
i
t
e
,
)
s
gn(
,
,
j
i
j
i
i
w
x
−
=
σ
.
C
o
n
s
e
q
u
e
n
tly
,
th
e
H
e
b
b
ia
n
le
a
r
n
in
g
r
u
le
p
u
s
h
e
s
th
e
w
e
ig
h
ts
to
w
a
r
d
s
th
e
b
o
u
n
d
a
r
ie
s
at
-
L
a
n
d
+
L.
I
n
o
r
d
e
r
t
o
q
u
a
n
t
i
f
y
t
h
i
s
e
f
f
e
c
t
t
h
e
s
t
a
t
i
o
n
a
r
y
p
r
o
b
a
b
i
l
i
t
y
d
i
s
t
r
i
b
u
t
i
o
n
o
f
t
h
e
w
e
i
g
h
t
s
f
o
r
∞
→
t
is
c
a
lc
u
la
te
d
f
o
r
th
e
tr
a
n
s
itio
n
p
r
o
b
a
b
iliti
es
.
T
h
i
s
l
ead
s
t
o
[
1
1
]
.
He
b
b
i
a
n
l
e
a
r
n
i
n
g
ant
i
-
He
b
b
i
a
n
l
e
a
r
n
i
n
g
Ra
n
d
o
m
w
a
lk
le
a
r
n
in
g
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
AI
IS
S
N
:
2252
-
8938
r
Mu
l
t
i
l
a
y
e
r
n
e
u
r
a
l
n
e
t
w
o
r
k
s
y
n
c
h
r
o
n
i
z
e
d
s
e
c
u
r
e
d
s
e
s
s
i
o
n
k
e
y
b
a
s
e
d
e
n
c
r
y
p
t
i
o
n
i
n
…
(
Ar
i
n
d
a
m
S
a
r
k
a
r
)
47
(
)
(
)
∏
=
⎟
⎟
⎟
⎠
⎞
⎜
⎜
⎜
⎝
⎛
−
−
⎟
⎟
⎟
⎠
⎞
⎜
⎜
⎜
⎝
⎛
−
−
−
+
=
=
w
m
i
i
j
i
m
NQ
m
er
f
m
NQ
m
er
f
P
w
w
P
1
2
2
0
,
1
1
1
1
(8
)
He
r
e
t
h
e
n
o
r
m
a
l
i
z
a
t
i
o
n
c
o
n
s
t
a
n
t
0
ρ
is
g
iv
e
n
b
y
(
)
1
1
2
2
0
1
1
1
1
−
−
=
=
⎟
⎟
⎟
⎟
⎟
⎟
⎟
⎠
⎞
⎜
⎜
⎜
⎜
⎜
⎜
⎜
⎝
⎛
⎟
⎟
⎟
⎠
⎞
⎜
⎜
⎜
⎝
⎛
−
−
⎟
⎟
⎟
⎠
⎞
⎜
⎜
⎜
⎝
⎛
−
−
−
+
=
∑
∏
L
L
w
w
m
i
i
m
NQ
m
er
f
m
NQ
m
er
f
P
(9
)
In
t
h
e
l
i
m
i
t
∞
→
N
th
e
a
r
g
u
m
e
n
t
o
f
th
e
e
r
r
o
r
f
u
n
c
tio
n
s
v
a
n
is
h
e
s
,
s
o
th
a
t
th
e
w
e
ig
h
ts
s
ta
y
u
ni
f
or
m
l
y
di
s
t
r
i
but
e
d.
I
n
t
hi
s
c
a
s
e
t
he
i
ni
t
i
a
l
l
e
ngt
h
of
t
he
w
e
i
ght
ve
c
t
or
s
i
s
not
c
ha
nge
d
by
t
he
pr
oc
e
s
s
of
sy
n
c
h
r
o
n
i
z
a
t
i
o
n
.
(
)
3
1
)
0
(
+
=
=
L
L
t
Q
i
(1
0
)
Bu
t
,
f
o
r
f
i
n
i
t
e
N
,
t
h
e
p
r
o
b
a
b
i
l
i
t
y
d
i
s
t
r
i
b
u
t
i
o
n
i
t
s
e
l
f
d
e
p
e
n
d
s
o
n
t
h
e
o
r
d
e
r
p
a
r
a
m
e
t
e
r
i
Q
Th
e
r
e
f
o
r
e
i
t
s
ex
p
ect
at
i
o
n
v
al
u
e
i
s
g
i
v
en
b
y
t
h
e
s
o
l
u
t
i
o
n
o
f
t
h
e
f
o
l
l
o
w
i
n
g
eq
u
at
i
o
n
:
(
)
∑
−
=
=
=
L
L
w
j
i
i
w
w
P
w
Q
,
2
(1
1
)
3.
4.
Or
d
e
r
P
a
r
a
m
e
t
e
r
s
In
o
rd
e
r
t
o
d
e
s
c
ri
b
e
t
h
e
c
o
rre
l
a
t
i
o
n
s
b
e
t
w
e
e
n
t
w
o
m
u
l
t
i
l
a
y
e
r
p
e
rc
e
p
t
ro
n
c
a
u
s
e
d
b
y
t
h
e
sy
n
c
h
r
o
n
i
z
a
t
i
o
n
pr
oc
e
s
s
,
one
c
a
n
l
ook
a
t
t
he
pr
oba
bi
l
i
t
y
di
s
t
r
i
but
i
on
of
t
he
w
e
i
ght
va
l
ue
s
i
n
e
a
c
h
hi
dde
n
uni
t
.
I
t
i
s
gi
ve
n
by
(2
L
+
1
)
v
a
ri
a
b
l
e
s
.
(
)
b
w
a
w
P
P
B
j
i
A
j
i
i
b
a
=
∧
=
=
,
,
,
(1
2
)
wh
i
c
h
a
r
e
d
e
f
i
n
e
d
a
s
t
h
e
p
r
o
b
a
b
i
l
i
t
y
t
o
f
i
n
d
a
we
i
g
h
t
wi
t
h
a
w
A
j
i
=
,
in
A
'
s
m
u
ltila
y
e
r
p
e
r
c
e
p
tr
o
n
a
n
d
b
w
B
j
i
=
,
in
B
'
s
m
u
ltila
y
e
r
p
e
r
c
e
p
tr
o
n
.
I
n
b
o
th
c
a
s
e
s
,
s
im
u
la
tio
n
a
n
d
ite
r
a
tiv
e
c
a
lc
u
la
tio
n
,
th
e
s
ta
n
d
a
r
d
o
r
d
e
r
pa
r
a
m
e
t
e
r
s
,
w
hi
c
h
a
r
e
a
l
s
o
us
e
d
f
or
t
he
a
na
l
ys
i
s
of
onl
i
ne
l
e
a
r
ni
ng,
c
a
n
be
c
a
l
c
ul
a
t
e
d
a
s
f
unc
t
i
ons
of
i
b
a
P
,
[1
2
].
∑
∑
−
=
−
=
=
=
L
L
a
L
L
b
i
b
a
A
i
A
i
A
i
P
a
w
w
N
Q
,
2
1
(1
3
)
∑
∑
−
=
−
=
=
=
L
L
a
L
L
b
i
b
a
B
i
B
i
B
i
P
b
w
w
N
Q
,
2
1
(1
4
)
∑
∑
−
=
−
=
=
=
L
L
a
L
L
b
i
b
a
B
i
A
i
AB
i
ab
P
w
w
N
R
,
1
(1
5
)
Evaluation Warning : The document was created with Spire.PDF for Python.
r
IS
S
N
:
2252
-
8938
IJ
-
AI
Vo
l
.
8
, N
o
.
1
,
Ma
r
c
h
20
1
9
:
4
4
–
5
3
48
Th
e
n
t
h
e
l
e
v
e
l
o
f
s
y
n
c
h
r
o
n
i
z
a
t
i
o
n
i
s
g
i
v
e
n
b
y
t
h
e
n
o
r
m
a
l
i
z
e
d
o
v
e
r
l
a
p
b
e
t
w
e
e
n
t
w
o
c
o
r
r
e
s
p
o
n
d
i
n
g
hi
dde
n
uni
t
s
B
i
A
i
AB
i
B
i
B
i
A
i
A
i
B
i
A
i
AB
i
Q
Q
R
w
w
w
w
w
w
=
=
ρ
(1
6
)
3.
5.
Hi
d
d
e
n
L
a
y
e
r
a
s
a
S
e
c
r
e
t
S
e
s
s
i
o
n
Ke
y
At
e
n
d
o
f
f
u
l
l
we
i
g
h
t
s
y
n
c
h
r
o
n
i
z
a
t
i
o
n
p
r
o
c
e
s
s
,
we
i
g
h
t
v
e
c
t
o
r
s
b
e
t
we
e
n
i
n
p
u
t
l
a
y
e
r
a
n
d
a
c
t
i
v
a
t
e
d
hi
dde
n
l
a
ye
r
of
bot
h
m
ul
t
i
l
a
ye
r
pe
r
c
e
pt
r
on
s
ys
t
e
m
s
be
c
om
e
i
de
nt
i
c
a
l
.
A
c
t
i
va
t
e
d
hi
dde
n
l
a
ye
r
’
s
out
put
of
so
u
r
c
e
mu
l
t
i
l
a
y
e
r
p
e
r
c
e
p
t
r
o
n
i
s
u
s
e
d
t
o
c
o
n
s
t
r
u
c
t
t
h
e
s
e
cr
et
s
es
s
i
o
n
k
ey
.
T
h
i
s
s
es
s
i
o
n
k
ey
i
s
n
o
t
g
et
t
r
an
s
m
i
t
t
ed
o
v
er
publ
i
c
c
ha
nne
l
be
c
a
us
e
r
e
c
e
i
ve
r
m
ul
t
i
l
a
ye
r
pe
r
c
e
pt
r
on
ha
s
s
a
m
e
i
de
nt
i
c
a
l
a
c
t
i
va
t
e
d
hi
dde
n
l
a
ye
r
’
s
out
put
.
Co
m
p
u
t
e
t
h
e
v
a
l
u
e
s
o
f
t
h
e
e
a
c
h
h
i
d
d
e
n
u
n
i
t
b
y
⎟
⎟
⎠
⎞
⎜
⎜
⎝
⎛
=
∑
=
N
j
ij
ij
i
x
w
1
sg
n
σ
(
)
⎪
⎩
⎪
⎨
⎧
−
=
1
0
1
sg
n
x
if
if
if
.
0
,
0
,
0
>
=
<
x
x
x
(1
7
)
Fo
r
e
x
a
m
p
l
e
c
o
n
s
i
d
e
r
8
h
i
d
d
e
n
u
n
i
t
s
o
f
a
c
t
i
v
a
t
e
d
h
i
d
d
e
n
l
a
y
e
r
h
a
v
i
n
g
a
b
s
o
l
u
t
e
v
a
l
u
e
(
1
,
0
,
0
,
1
,
0
,
1
,
0,
1)
be
c
om
e
s
a
n
8
bi
t
bl
oc
k.
T
hi
s
10010101
be
c
om
e
a
s
e
c
r
e
t
s
e
s
s
i
on
ke
y
f
or
a
pa
r
t
i
c
ul
a
r
s
e
s
s
i
on
a
nd
c
a
s
c
a
de
d
xor
e
d
wi
t
h
re
c
u
rs
i
v
e
re
p
l
a
c
e
m
e
n
t
e
n
c
ry
p
t
e
d
t
e
x
t
.
N
o
w
fi
n
a
l
s
e
s
s
i
o
n
k
e
y
b
a
s
e
d
e
n
c
ry
p
t
e
d
t
e
x
t
i
s
t
ra
n
s
m
i
t
t
e
d
t
o
th
e
r
e
c
e
iv
e
r
e
n
d
.
R
e
c
e
iv
e
r
h
a
s
th
e
id
e
n
tic
a
l
s
e
s
s
io
n
k
e
y
i.e
.
th
e
o
u
tp
u
t
o
f
th
e
h
id
d
e
n
u
n
its
o
f
a
c
tiv
a
te
d
h
id
d
e
n
la
y
e
r
o
f
r
e
c
e
iv
e
r
.
T
h
is
s
e
s
s
io
n
k
e
y
u
s
e
d
to
g
e
t
th
e
r
e
c
u
r
s
iv
e
r
e
p
la
c
e
m
e
n
t
e
n
c
r
y
p
te
d
te
x
t
f
r
o
m
th
e
f
in
a
l
c
ip
h
e
r
te
x
t.
I
n
th
e
n
e
x
t
s
e
s
s
io
n
b
o
th
th
e
m
a
c
h
in
e
s
s
ta
r
te
d
tu
n
in
g
a
g
a
in
to
p
r
o
d
u
c
e
a
n
o
th
e
r
s
e
s
s
io
n
k
e
y
.
I
d
e
n
tic
a
l
w
e
ig
h
t
ve
c
t
or
de
r
i
ve
d
f
r
om
s
yna
pt
i
c
l
i
nk
be
t
w
e
e
n
i
nput
a
nd
act
i
v
at
ed
h
i
d
d
en
l
ay
er
o
f
b
o
t
h
m
u
l
t
i
l
ay
er
p
er
cep
t
r
o
n
can
al
s
o
b
eco
m
e
s
ecr
et
s
es
s
i
o
n
k
ey
f
o
r
a
p
ar
t
i
cu
l
ar
s
es
s
i
o
n
af
t
er
f
u
l
l
w
ei
g
h
t
s
y
n
ch
r
o
n
i
zat
i
o
n
i
s
ach
i
ev
ed
.
4.
TR
A
I
N
G
U
LA
R
I
ZA
TI
O
N
EN
C
R
Y
P
TI
O
N
TEC
H
N
I
Q
U
E
Du
r
i
n
g
p
l
a
i
n
t
e
x
t
e
n
c
r
y
p
t
i
o
n
,
i
n
t
h
e
f
i
r
s
t
p
h
a
s
e
co
n
s
i
d
er
a
b
l
o
ck
S
=
s
0
0
s
0
1
s
0
2
s
0
3
s
0
4
s
0
5
…
s
0
n
-
2
s
0
n
-
1
of
si
z
e
n
b
i
t
s,
w
h
e
r
e
s
0
i
=
0
o
r
1
f
o
r
0
<=
i
<=
(
n
-
1)
.
N
ow
,
s
t
a
r
t
i
ng
f
r
om
M
S
B
(
s
0
0
)
a
n
d
t
h
e
n
e
x
t
-
to
-
MS
B
(s
0
1
),
bi
t
s
a
r
e
pa
i
r
-
wi
s
e
XOR
e
d
,
s
o
t
h
a
t
t
h
e
1
st
in
te
r
m
e
d
ia
te
s
u
b
-
st
r
e
a
m
S
1
=
s
1
0
s
1
1
s
1
2
s
1
3
s
1
4
s
1
5
… s
1
n
-
2
is
g
e
n
e
r
a
te
d
co
n
s
i
s
t
i
n
g
o
f
(
n
-
1)
bi
t
s
,
w
he
r
e
s
1
j
=
s
0
j
⊕
s
0
j+
1
fo
r
0
<
=
j
<
=
n
-
2,
⊕
st
a
n
d
s
fo
r
t
h
e
e
x
c
l
u
s
i
v
e
O
R
o
p
e
ra
t
i
o
n
.
Th
i
s
1
st
in
te
r
m
e
d
ia
te
s
u
b
-
st
r
e
a
m
S
1
is
a
ls
o
th
e
n
p
a
ir
-
wi
s
e
XOR
e
d
t
o
g
e
n
e
r
a
t
e
S
2
=
s
2
0
s
2
1
s
2
2
s
2
3
s
2
4
s
2
5
…
s
2
n
-
3
,
wh
i
c
h
i
s
t
h
e
2
nd
in
te
r
m
e
d
ia
te
s
u
b
-
st
r
e
a
m
o
f
l
e
n
g
t
h
(
n
-
2)
.
T
hi
s
pr
oc
e
s
s
c
ont
i
nue
s
(
n
-
1)
t
i
m
e
s
t
o
ul
t
i
m
a
t
e
l
y
ge
ne
r
a
t
e
S
n
-
1
=
s
n
-
1
0
,
w
h
ic
h
is
a
s
in
g
le
b
it
o
n
ly
.
T
h
u
s
th
e
s
iz
e
o
f
th
e
1
st
in
te
r
m
e
d
ia
te
s
u
b
-
st
r
e
a
m
i
s
o
n
e
b
i
t
l
e
ss
th
a
n
th
e
s
o
u
r
c
e
s
u
b
-
st
r
e
a
m
;
t
h
e
si
z
e
o
f
e
a
c
h
o
f
t
h
e
i
n
t
e
r
m
e
d
i
a
t
e
su
b
-
st
r
e
a
m
s
st
a
r
t
i
n
g
f
r
o
m
t
h
e
2
nd
one
i
s
one
bi
t
le
s
s
th
a
n
th
a
t o
f
th
e
s
u
b
-
st
r
e
a
m
w
h
e
r
e
f
r
o
m
i
t
w
a
s
g
e
n
e
r
a
t
e
d
;
a
n
d
f
i
n
a
l
l
y
t
h
e
si
z
e
o
f
t
h
e
f
i
n
a
l
su
b
-
s
tr
e
a
m
in
th
e
pr
oc
e
s
s
i
s
one
bi
t
l
e
s
s
t
ha
n
t
he
f
i
na
l
i
nt
e
r
m
e
di
a
t
e
s
ub
-
st
r
e
a
m
.
F
i
g
u
r
e
1
sh
o
w
t
h
e
p
r
o
c
e
ss.
Fi
g
u
r
e
1
d
e
s
c
r
i
b
e
s
d
i
f
f
e
r
e
n
t
o
p
t
i
o
n
s
f
o
r
c
h
o
o
s
i
n
g
t
a
r
g
e
t
b
l
o
c
k
f
r
o
m
t
r
i
a
n
g
l
e
.
T
h
i
s
o
p
t
i
o
n
i
s
g
e
n
e
r
a
t
e
d
by
m
odul
o
4
di
vi
s
i
on
of
t
he
va
l
ue
of
out
put
ne
ur
o
n
t
he
n
a
ddi
ng
1.
T
he
n
t
a
ke
t
he
bi
na
r
y
ve
r
s
i
on
of
t
he
de
c
i
m
a
l
no.
E
a
c
h
bl
oc
k
s
i
z
e
i
s
r
e
pr
e
s
e
nt
e
d
by
5
bi
t
s
a
nd
3
bi
t
s
a
r
e
us
e
d
t
o
de
not
i
ng
th
e
o
p
tio
n
n
o
.
f
o
r
th
a
t
b
lo
c
k
.
So
,
t
o
t
a
l
8
b
i
t
s
a
r
e
u
s
e
d
t
o
d
e
s
c
r
i
b
e
a
s
i
n
g
l
e
b
l
o
c
k
l
e
n
g
t
h
a
n
d
o
p
t
i
o
n
c
h
o
s
e
n
.
Fo
r
m
u
l
t
ip
le
b
lo
c
k
s
s
e
v
e
r
a
l
8
b
its
ar
e
at
t
ach
ed
t
o
g
et
h
er
p
r
eced
ed
b
y
f
i
r
s
t
8
b
i
t
s
(
2
8
=
2
5
6
b
l
o
c
k
s
c
a
n
b
e
f
o
r
m
e
d
i
n
o
n
e
s
e
s
s
i
o
n
)
t
o
d
e
s
c
r
i
b
e
t
o
t
a
l
no.
of
bl
oc
k
t
o
f
or
m
s
i
nt
e
r
m
e
di
a
t
e
s
ub
ke
y.
M
a
xi
m
um
l
e
ngt
h
of
t
hi
s
s
ub
ke
y
w
i
l
l
be
(
256
bl
oc
ks
X
8
bi
t
s
pe
r
bl
oc
k)
204
8
bi
t
s
.
T
hi
s
s
ub
ke
y
i
s
pa
dde
d
i
n
t
he
f
r
ont
of
t
he
e
nc
r
ypt
e
d
t
e
xt
.
T
he
n
t
he
m
ul
t
i
l
a
ye
r
pe
r
c
e
pt
r
on
ge
ne
r
a
t
e
d
s
ync
hr
oni
z
e
d
one
t
i
m
e
s
e
s
s
i
on
ke
y
i
s
r
e
pe
a
t
e
dl
y
xor
e
d
w
i
t
h
t
he
i
nt
e
r
m
e
di
a
t
e
t
r
a
i
ngul
a
r
i
z
e
d
c
i
phe
r
te
x
t
b
y
c
o
n
s
id
e
r
in
g
s
a
m
e
k
e
y
&
tr
a
in
g
u
la
r
iz
e
d
c
ip
h
er
t
ex
t
l
en
g
t
h
.
T
h
i
s
m
ech
an
i
s
m
i
s
p
er
f
o
r
m
ed
u
n
t
i
l
al
l
t
h
e
bl
oc
ks
ge
t
e
xha
us
t
e
d.
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
AI
IS
S
N
:
2252
-
8938
r
Mu
l
t
i
l
a
y
e
r
n
e
u
r
a
l
n
e
t
w
o
r
k
s
y
n
c
h
r
o
n
i
z
e
d
s
e
c
u
r
e
d
s
e
s
s
i
o
n
k
e
y
b
a
s
e
d
e
n
c
r
y
p
t
i
o
n
i
n
…
(
Ar
i
n
d
a
m
S
a
r
k
a
r
)
49
O
pt
i
on Se
r
i
al
No. 010
O
pt
i
on Se
r
i
al
No. 100
O
pt
i
on Se
r
i
al
No. 001
O
pt
i
on Se
r
i
al
No. 011
Fi
g
u
r
e
1
.
O
p
t
i
o
n
s
d
i
a
g
r
a
m
f
o
r
c
h
o
o
s
i
n
g
T
a
r
g
e
t
B
l
o
c
k
f
r
o
m
T
r
i
a
n
g
l
e
5.
EN
ER
G
Y
C
O
M
P
U
TA
TI
O
N
Si
n
c
e
i
t
i
s
a
v
e
r
y
d
i
f
f
i
c
u
l
t
j
o
b
t
o
f
i
n
d
o
u
t
a
c
t
u
a
l
p
o
w
e
r
c
o
n
s
u
m
e
d
i
n
t
e
rm
s
o
f
“
j
u
l
e
”
,
a
p
p
ro
a
c
h
h
e
re
i
s
to
p
r
e
d
ic
t
p
r
o
b
a
b
le
p
o
w
e
r
c
o
n
s
u
m
p
tio
n
b
y
th
e
p
r
o
p
o
s
e
d
te
c
h
n
iq
u
e
.
I
t
is
a
d
if
f
ic
u
lt
jo
b
f
o
r
a
p
r
o
c
e
s
s
o
r
to
f
in
d
out
w
hi
c
h
pr
oc
e
s
s
i
s
c
ons
um
i
ng
how
m
a
ny
a
m
ount
of
J
ul
e
s
/
s
e
c
,
s
i
nc
e
pr
oc
e
s
s
or
s
r
un
on
t
i
m
e
s
ha
r
i
ng
ba
s
i
s
.
We
c
a
n
c
a
l
c
u
l
a
t
e
w
h
a
t
a
s
i
n
g
l
e
p
r
o
c
e
s
s
o
r
c
y
c
l
e
c
o
n
s
u
m
e
s
b
y
t
a
k
i
n
g
a
s
t
a
n
d
a
r
d
.
A
l
l
b
a
s
i
c
o
p
e
r
a
t
i
o
n
s
s
u
p
p
o
s
e
ad
d
i
t
i
o
n
,
s
u
b
t
r
act
i
o
n
,
m
u
l
t
i
p
l
i
cat
i
o
n
r
eq
u
i
r
es
m
u
l
t
i
p
l
e
cy
cl
es
.
B
as
ed
o
n
t
h
at
f
o
r
each
cy
cl
e
w
e
w
i
l
l
cal
cu
l
at
e
pr
oba
bl
e
pow
e
r
c
ons
um
e
d
by
a
ny
in
s
tr
u
c
tio
n
a
n
d
in
th
e
la
r
g
e
s
c
a
le
w
e
w
ill
tr
y
to
f
in
d
o
u
t
to
ta
l
p
o
w
e
r
c
o
n
s
u
m
e
d
by
t
he
e
nc
r
ypt
i
on/
D
e
c
r
ypt
i
on
t
e
c
hni
que
.
W
e
w
i
l
l
a
l
s
o
t
r
y
t
o
e
s
t
i
m
a
t
e
t
ot
a
l
pow
e
r
c
ons
um
e
d
i
n
m
ut
ua
l
sy
n
c
h
r
o
n
i
z
a
t
i
o
n
t
e
c
h
n
i
q
u
e
o
f
t
h
e
se
n
so
r
n
e
t
w
o
r
k
n
o
d
e
s.
T
h
e
st
e
p
s
a
s
f
o
l
l
o
w
s
:
St
e
p
1
:
E
a
c
h
a
t
o
m
i
c
o
p
e
r
a
t
i
o
n
(
A
d
d
i
t
i
o
n
,
s
u
b
t
r
a
c
t
i
o
n
,
D
i
v
i
s
i
o
n
,
M
u
l
t
i
p
l
i
c
a
t
i
o
n
,
a
s
s
i
g
n
m
e
n
t
)
i
s
d
i
v
i
d
e
d
i
n
t
o
cy
cl
es
i
t
r
eq
u
i
r
e.
St
e
p
2
:
A
s
s
i
g
n
e
a
c
h
c
y
c
l
e
w
i
t
h
m
i
n
i
m
u
m
p
o
s
s
i
b
l
e
p
o
w
e
r
(
l
i
k
e
i
n
t
e
r
m
s
o
f
M
i
c
r
o
J
u
l
e
)
.
St
e
p
3
:
T
h
e
n
f
o
r
a
l
l
o
p
e
r
a
t
i
o
n
w
e
w
i
l
l
c
o
u
n
t
num
be
r
of
c
yc
l
e
s
c
om
pl
e
t
e
d
s
o
f
a
r
.
St
e
p
4
:
W
e
w
i
l
l
c
o
n
t
i
n
u
e
s
t
e
p
3
u
n
t
i
l
a
l
l
t
h
e
i
n
s
t
r
u
c
t
i
o
n
s
a
r
e
f
i
n
i
s
h
e
d
e
x
e
c
u
t
i
o
n
.
St
e
p
5
:
N
o
w
t
o
t
a
l
n
u
m
b
e
r
o
f
c
y
c
l
e
s
i
s
t
h
e
t
o
t
a
l
a
m
o
u
n
t
o
f
p
o
w
e
r
c
o
n
s
u
m
e
d
.
Si
n
c
e
e
a
c
h
c
o
m
p
u
t
e
r
h
a
s
d
i
f
f
e
r
e
n
t
a
r
c
h
i
t
e
c
t
u
r
e
a
n
d
i
n
s
t
r
u
c
t
i
o
n
ex
ecu
t
i
o
n
t
o
t
al
l
y
d
ep
en
d
s
o
f
t
h
e
ar
ch
i
t
ect
u
r
e
o
f
t
h
e
co
m
p
u
t
er
,
s
o
w
e
h
av
e
t
o
b
e
v
er
y
co
n
s
ci
o
u
s
ab
o
u
t
t
h
e
u
n
d
er
l
y
i
n
g
m
ach
i
n
e
s
t
r
u
ct
u
r
e.
S
o
w
e
ne
e
d
t
o
do
t
hor
ough
s
t
udy
of
t
he
a
r
c
hi
t
e
c
t
ur
e
be
f
or
e
dr
a
w
i
ng
a
ny
c
onc
l
us
i
on.
6.
EX
P
ER
I
M
EN
T
R
ES
U
LTS
In
t
h
i
s
p
a
p
e
r
re
s
ul
t
of
t
he
pr
opos
e
d
t
e
c
hni
que
i
s
c
om
put
e
d
on
di
f
f
e
r
e
nt
t
ype
s
of
f
i
l
e
s
w
i
t
h
e
xt
e
ns
i
ve
an
al
y
s
i
s
.
T
h
e
co
m
p
ar
at
i
v
e
s
t
u
d
y
am
o
n
g
p
r
o
p
o
s
ed
t
ech
n
i
q
u
es
,
R
S
A
,
T
r
i
p
l
e
-
DE
S
(
168
bi
t
s
)
,
A
E
S
(
128
bi
t
s
)
ha
s
be
e
n
done
ba
s
e
d
on
t
w
e
nt
y
f
i
l
e
s
by
pe
r
f
or
m
i
ng
di
f
f
e
r
e
nt
t
ype
s
of
ex
p
er
i
m
en
t
.
6.
1.
S
t
at
i
s
t
i
c
al
A
n
al
ys
i
s
Fo
r
a
n
a
l
y
s
i
s
o
f
t
h
e
s
t
a
t
i
s
t
i
c
a
l
t
e
s
t
,
a
l
a
r
g
e
n
u
m
b
e
r
o
f
s
a
m
p
l
e
s
o
f
b
i
t
s
e
q
u
e
n
c
e
s
i
n
t
h
e
k
e
y
h
a
s
b
e
e
n
co
n
s
i
d
er
ed
.
F
o
r
sa
m
p
l
e
s
o
f
b
i
t
se
q
u
e
n
c
e
s
o
b
t
a
i
n
e
d
f
r
o
m
t
h
e
k
e
y
o
f
a
t
e
c
h
n
i
q
u
e
a
r
e
t
e
st
e
d
b
y
p
r
o
d
u
c
i
n
g
o
n
e
P
-
va
l
ue
,
a
s
t
a
t
i
s
t
i
c
a
l
t
hr
e
s
hol
d
va
l
ue
i
s
de
f
i
ne
d
us
i
ng
(
18)
.
ℎ
ℎ
=
1
−
−
3
×
(
)
(1
8
)
Th
e
o
b
j
e
c
t
i
v
e
o
f
t
h
e
t
e
s
t
i
s
t
o
f
i
n
d
p
r
o
p
o
r
t
i
o
n
o
f
zer
o
es
an
d
o
n
es
f
o
r
t
h
e
en
t
i
r
e
s
eq
u
en
ce
w
h
i
ch
d
et
er
m
i
n
e
wh
e
t
h
e
r
t
h
e
n
u
m
b
e
r
o
f
o
n
e
s
a
n
d
z
e
r
o
s
i
n
a
s
e
q
u
e
n
c
e
a
r
e
a
p
p
r
o
x
i
m
a
t
e
l
y
t
h
e
s
a
m
e
a
s
wo
u
l
d
b
e
e
x
p
e
c
t
e
d
f
o
r
a
tr
u
ly
r
a
n
d
o
m
s
e
q
u
e
n
c
e
.
I
n
th
is
e
x
p
e
r
im
e
n
t
e
x
p
e
c
te
d
p
r
o
p
o
r
tio
n
f
o
r
p
a
s
s
in
g
th
e
te
s
t
h
a
s
b
e
e
n
s
e
t
to
0
.
972766
.
Ta
b
l
e
1
s
h
o
w
s
p
r
o
p
o
r
t
i
o
n
o
f
p
a
s
s
i
n
g
a
n
d
u
n
i
f
o
r
m
i
t
y
o
f
d
i
s
t
r
i
b
u
t
i
o
n
l
y
i
n
g
i
n
t
h
e
g
i
v
e
n
r
a
n
g
e
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
r
IS
S
N
:
2252
-
8938
IJ
-
AI
Vo
l
.
8
, N
o
.
1
,
Ma
r
c
h
20
1
9
:
4
4
–
5
3
50
Ta
b
l
e
1
.
P
r
o
p
o
r
t
i
o
n
o
f
p
a
s
s
i
n
g
a
n
d
u
n
i
f
o
r
m
i
t
y
o
f
d
i
s
t
r
i
b
u
t
i
o
n
f
o
r
f
r
e
q
u
e
n
c
y
Te
c
h
n
i
q
u
e
Ex
p
e
c
t
e
d
Pr
o
p
o
r
t
i
o
n
Ob
s
e
r
v
e
d
P
r
o
p
o
r
t
i
o
n
St
a
t
u
s
f
o
r
Pr
o
p
o
r
t
i
o
n
of
pa
s
s
i
ng
p
-
va
l
ue
of
p
-
va
l
ue
s
Pr
o
p
o
s
e
d
0.
972766
0.
985437
Su
c
c
e
s
s
4.
102711e
-
10
TD
ES
0.
983333
Su
c
c
e
s
s
3.
571386e
-
01
AE
S
0.
984871
Su
c
c
e
s
s
3.
915294e
-
07
RS
A
0.
986667
Su
c
c
e
s
s
4.
122711e
-
10
Fr
o
m
T
a
b
l
e
1
i
t
i
s
s
e
e
n
t
h
a
t
a
l
l
p
r
o
p
o
s
e
d
t
e
c
h
n
i
q
u
e
s
a
l
o
n
g
w
i
t
h
ex
i
s
t
i
n
g
t
ech
n
i
q
u
es
p
as
s
ed
t
h
e
f
r
eq
u
en
cy
(m
o
n
o
b
i
t
s
)
t
e
s
t
s
u
c
c
e
s
s
fu
l
l
y
b
e
c
a
u
s
e
o
b
s
e
rv
e
d
p
ro
p
o
rt
i
o
n
v
a
l
u
e
s
o
f
a
l
l
t
h
e
p
ro
p
o
s
e
d
t
e
c
h
n
i
q
u
e
s
a
re
g
ra
t
e
r
t
h
a
n
ex
p
ect
ed
p
r
o
p
o
r
t
i
o
n
v
al
u
e.
I
t
i
s
al
s
o
n
o
t
i
ced
t
h
at
p
r
o
p
o
s
ed
t
ech
n
i
q
u
es
o
u
t
p
er
f
o
r
m
t
h
an
ex
i
s
t
i
n
g
T
D
E
S
an
d
A
E
S
te
c
h
n
iq
u
e
.
6.
2.
E
n
c
r
yp
t
i
on
/
D
e
c
r
yp
t
i
on
T
i
m
e
Tw
e
n
t
y
f
i
l
e
s
o
f
d
i
f
f
e
r
e
n
t
s
i
z
e
s
v
a
r
y
i
n
g
f
r
o
m
3
,
216
byt
e
s
t
o
5
,
456
,
704
byt
e
s
ha
ve
be
e
n
t
a
ke
n
t
o
ge
ne
r
a
t
e
t
he
da
t
a
co
n
t
a
i
n
i
n
g
va
r
i
ous
a
t
t
r
i
but
e
s
f
or
e
va
l
ua
t
i
on
of
t
he
pr
opos
e
d
t
e
c
hni
que
.
T
he
e
nc
r
ypt
i
on
t
i
m
e
s
(E
n
c
.
)
a
n
d
d
e
c
ry
p
t
i
o
n
t
i
m
e
s
(D
e
c
.
)
o
f
.d
ll
ty
p
e
f
ile
s
o
b
ta
in
e
d
u
s
in
g
p
r
o
p
o
s
e
d
a
n
d
e
x
is
tin
g
P
P
M
[
1
7
]
,
T
P
M
[
1
8
]
,
TD
ES
[
1
]
a
n
d
A
ES
[
1
]
.
F
i
g
u
r
e
2
s
h
o
w
s
t
h
e
g
r
a
p
h
i
c
a
l
r
e
p
r
e
s
e
n
t
a
t
i
o
n
o
f
t
h
e
r
e
l
a
t
i
o
n
s
h
i
p
b
e
t
w
e
e
n
t
h
e
e
n
c
r
y
p
t
i
o
n
tim
e
s
a
g
a
in
s
t
th
e
.d
ll
ty
p
e
s
o
u
r
c
e
fi
l
e
s
fo
r
p
ro
p
o
s
e
d
,
A
E
S
a
n
d
T
D
E
S
t
e
c
h
n
i
q
u
e
s
.
E
n
c
.
a
n
d
D
e
c
.
fo
r
p
ro
p
o
s
e
d
an
d
A
E
S
ar
e
n
ear
eq
u
al
b
u
t
m
u
ch
l
o
w
er
t
h
an
t
h
at
o
f
P
P
M
,
T
P
M
an
d
T
D
E
S
.
Fi
g
u
r
e
2
.
E
n
c
r
y
p
t
i
o
n
t
i
m
e
a
g
a
i
n
s
t
t
h
e
v
a
r
y
i
n
g
s
i
z
e
o
f
i
n
p
u
t
s
t
r
e
a
m
o
f
.d
ll
fi
l
e
s
6.
3.
A
n
al
ys
i
s
of
Ch
a
r
a
c
t
e
r
F
r
e
q
u
e
n
c
i
e
s
a
n
d
F
l
o
a
t
i
n
g
F
r
e
q
u
e
n
c
i
e
s
An
a
l
y
s
i
s
o
f
c
h
a
r
a
c
t
e
r
f
r
e
q
u
e
n
c
i
e
s
o
f
t
we
n
t
y
s
o
u
r
c
e
f
i
l
e
s
h
a
s
b
e
e
n
p
e
r
f
o
r
m
e
d
u
s
i
n
g
pr
opos
e
d
.
F
ig
u
r
e
3
sh
o
w
s
t
h
e
sp
e
c
t
r
u
m
o
f
f
r
e
q
u
e
n
c
y
d
i
st
r
i
b
u
t
i
o
n
o
f
c
h
a
r
a
c
t
e
r
s
f
o
r
t
h
e
i
n
p
u
t
so
u
r
c
e
st
r
e
a
m
.
F
i
g
u
r
e
4
sh
o
w
s
t
h
e
s
pe
c
t
r
um
of
f
r
e
que
nc
y
di
s
t
r
i
but
i
on
of
e
nc
r
ypt
e
d
c
ha
r
a
c
t
e
r
s
us
i
ng
pr
opos
e
d
fo
r
t
h
e
s
a
m
e
i
n
p
u
t
s
o
u
rc
e
s
t
re
a
m
.
It
ha
s
be
e
n
obs
e
r
ve
d
t
ha
t
f
r
e
que
nc
i
e
s
of
c
ha
r
a
c
t
e
r
s
a
r
e
w
i
de
l
y
di
s
t
r
i
but
e
d
i
n
pr
opos
e
d
en
cr
y
p
t
ed
f
i
l
e.
A
n
al
y
s
i
s
o
f
fl
o
a
t
i
n
g
fre
q
u
e
n
c
i
e
s
o
f
t
w
e
n
t
y
s
o
u
rc
e
d
i
ffe
re
n
t
fi
l
e
s
h
a
s
b
e
e
n
p
e
rfo
rm
e
d
u
s
i
n
g
pr
opos
e
d
.
T
h
e
f
lo
a
tin
g
f
r
e
q
u
e
n
c
y
of
a
doc
um
e
nt
i
s
a
c
ha
r
a
c
t
e
r
i
s
t
i
c
of
i
t
s
l
oc
a
l
i
nf
or
m
a
t
i
on
c
ont
e
nt
a
t
i
ndi
vi
dua
l
poi
nt
s
i
n
t
he
doc
um
e
nt
.
T
he
fl
o
a
t
i
n
g
fre
q
u
e
n
c
y
s
p
e
c
i
fi
e
s
h
o
w
m
a
n
y
d
i
ffe
re
n
t
c
h
a
ra
c
t
e
rs
a
re
t
o
b
e
fo
u
n
d
i
n
a
n
y
g
i
v
e
n
6
4
-
ch
ar
act
er
l
o
n
g
se
g
m
e
n
t
o
f
t
h
e
d
o
c
u
m
e
n
t
.
F
i
g
u
r
e
5
sh
o
w
s
t
h
e
sp
e
c
t
r
u
m
o
f
f
l
o
a
t
i
n
g
f
r
e
q
u
e
n
c
i
e
s
o
f
c
h
a
r
a
c
t
e
r
s
f
o
r
t
h
e
i
n
p
u
t
so
u
r
c
e
st
r
e
a
m
.
F
i
g
u
r
e
6
sh
o
w
s
t
h
e
sp
e
c
t
r
u
m
o
f
f
l
o
a
t
i
n
g
f
r
e
q
u
e
n
c
i
e
s
o
f
e
n
c
r
y
p
t
e
d
c
h
a
r
a
c
t
e
r
s
u
si
n
g
pr
opos
e
d
fo
r
t
h
e
sa
m
e
i
n
p
u
t
so
u
r
c
e
st
r
e
a
m
.
F
r
o
m
t
h
e
f
i
g
u
r
e
s
i
t
i
s
o
b
se
r
v
e
d
t
h
a
t
f
l
o
a
t
i
n
g
f
r
e
q
u
e
n
c
i
e
s
o
f
pr
opos
e
d
en
cr
y
p
t
ed
ch
ar
act
er
s
i
n
d
i
cat
es
t
h
e
h
i
g
h
d
eg
r
ee
o
f
s
ecu
r
i
t
y
.
0
500
1000
1500
3,
216
6,
656
12,
288
24,
576
58,
784
85,
020
169,
472
359,
936
593,
920
909,
312
1,
293,
824
1,
925,
185
2,
498,
560
3,
485,
968
3,
790,
336
4,
253,
816
4,
575,
232
4,
883,
456
5,
054,
464
5,
456,
704
En
c
r
y
p
ti
o
n
ti
m
e
(i
n
m
.
se
c
.
)
In
p
u
t
s
t
r
e
a
m
s
i
z
e
(
i
n
b
y
t
e
s
)
PPM
TP
M
Pr
o
p
o
s
e
d
AE
S
TD
E
S
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
AI
IS
S
N
:
2252
-
8938
r
Mu
l
t
i
l
a
y
e
r
n
e
u
r
a
l
n
e
t
w
o
r
k
s
y
n
c
h
r
o
n
i
z
e
d
s
e
c
u
r
e
d
s
e
s
s
i
o
n
k
e
y
b
a
s
e
d
e
n
c
r
y
p
t
i
o
n
i
n
…
(
Ar
i
n
d
a
m
S
a
r
k
a
r
)
51
Fi
g
u
r
e
3.
S
pe
c
t
r
um
of
c
ha
r
a
c
t
e
r
s
f
or
t
he
i
nput
s
our
c
e
s
t
r
e
a
m
e
nc
r
ypt
e
d
s
t
r
e
a
m
Fi
g
u
r
e
4
.
Sp
ect
r
u
m
o
f
ch
ar
act
er
s
f
o
r
t
h
e
in
p
u
t s
o
u
r
c
e
s
tr
e
a
m
e
n
c
r
y
p
te
d
s
tr
e
a
m
Fi
g
u
r
e
5
. F
lo
a
tin
g
f
r
e
q
u
e
n
c
y
f
o
r
th
e
in
p
u
t s
o
u
r
c
e
s
tr
e
a
m
e
n
c
r
y
p
te
d
s
tr
e
a
m
Evaluation Warning : The document was created with Spire.PDF for Python.
r
IS
S
N
:
2252
-
8938
IJ
-
AI
Vo
l
.
8
, N
o
.
1
,
Ma
r
c
h
20
1
9
:
4
4
–
5
3
52
Fi
g
u
r
e
6
. F
lo
a
tin
g
f
r
e
q
u
e
n
c
y
f
o
r
th
e
in
p
u
t s
o
u
r
c
e
s
tr
e
a
m
e
n
c
r
y
p
te
d
s
tr
e
a
m
7.
SE
C
U
R
I
T
Y
I
SSU
E
Fr
o
m
r
e
s
u
l
t
s
o
b
t
a
i
n
e
d
i
t
i
s
c
l
e
a
r
t
h
a
t
t
h
e
t
e
c
h
n
i
q
u
e
w
i
l
l
a
c
h
i
e
v
e
o
p
t
i
m
a
l
p
e
r
f
o
r
m
a
n
c
e
s
.
E
n
c
r
y
p
t
i
o
n
t
i
m
e
an
d
d
ecr
y
p
t
i
o
n
t
i
m
e
v
ar
i
es
al
m
o
s
t
l
i
n
ear
l
y
w
i
t
h
r
es
p
ect
t
o
t
h
e
b
l
o
ck
s
i
ze.
A
u
s
er
i
n
p
u
t
k
ey
h
as
t
o
t
r
an
s
m
i
t
o
v
er
th
e
p
u
b
lic
c
h
a
n
n
e
l
a
ll
th
e
w
a
y
to
th
e
r
ecei
v
er
f
o
r
p
er
f
o
r
m
i
n
g
t
h
e
d
ecr
y
p
t
i
o
n
p
r
o
ced
u
r
e.
S
o
t
h
er
e
i
s
a
l
i
k
el
i
h
o
o
d
of
a
t
t
a
c
k
a
t
t
he
t
i
m
e
of
ke
y
e
xc
ha
nge
.
T
o
de
f
e
a
t
t
hi
s
i
ns
e
c
ur
e
s
e
c
r
e
t
ke
y
ge
ne
r
a
t
i
on
t
e
c
hni
que
a
ne
ur
a
l
ne
t
w
or
k
ba
s
e
d
s
e
c
r
e
t
ke
y
ge
ne
r
a
t
i
on
t
e
c
hni
que
ha
s
be
e
n
de
vi
s
e
d.
T
he
s
e
c
ur
i
t
y
i
ssu
e
o
f
e
x
i
st
i
n
g
a
l
g
o
r
i
t
h
m
c
a
n
b
e
im
p
r
o
v
e
d
b
y
u
s
in
g
M
L
P
s
e
c
r
e
t
s
e
s
s
io
n
k
e
y
g
e
n
e
r
a
tio
n
te
c
h
n
iq
u
e
.
I
n
th
is
c
a
s
e
,
th
e
tw
o
p
a
r
tn
e
r
s
A
a
n
d
B
d
o
n
o
t
ha
ve
t
o
s
ha
r
e
a
c
om
m
on
s
e
c
r
e
t
but
us
e
t
he
i
r
i
ndi
s
t
i
ngui
s
ha
bl
e
w
e
i
ght
s
or
out
put
of
a
c
t
i
va
t
e
d
hi
dde
n
l
a
ye
r
a
s
a
se
cr
et
k
ey
n
eed
ed
f
o
r
en
cr
y
p
t
i
o
n
.
T
h
e
f
u
n
d
am
en
t
al
co
n
cep
t
i
o
n
o
f
M
L
P
b
as
ed
k
ey
ex
ch
an
g
e
p
r
o
t
o
co
l
f
o
cu
s
es
mo
s
t
l
y
o
n
t
w
o
k
e
y
a
t
t
r
i
b
u
t
e
s
o
f
M
L
P
.
F
i
r
s
t
l
y
,
t
w
o
n
o
d
e
s
c
o
u
p
l
e
d
o
v
e
r
a
p
u
b
l
i
c
c
h
a
n
n
e
l
w
i
l
l
s
y
n
c
h
r
o
n
i
z
e
e
v
e
n
th
o
u
g
h
e
a
c
h
in
d
iv
id
u
a
l
n
e
tw
o
r
k
e
x
h
ib
its
d
is
o
r
g
an
i
zed
b
eh
av
i
o
u
r
.
S
eco
n
d
l
y
,
an
o
u
t
s
i
d
e
n
et
w
o
r
k
,
ev
en
i
f
id
e
n
tic
a
l
to
th
e
tw
o
c
o
m
m
u
n
ic
a
tin
g
n
e
tw
o
r
k
s
,
w
ill
f
in
d
it
e
x
c
e
p
tio
n
a
lly
d
if
f
ic
u
lt
to
s
y
n
c
h
r
o
n
iz
e
w
ith
th
o
s
e
pa
r
t
i
e
s
,
t
hos
e
pa
r
t
i
e
s
a
r
e
c
om
m
uni
c
a
t
i
ng
ove
r
a
publ
i
c
ne
t
w
or
k.
A
n
a
t
t
a
c
ke
r
E
w
ho
know
s
a
l
l
th
e
p
a
r
tic
u
la
r
s
o
f
th
e
a
lg
o
r
ith
m
a
n
d
r
e
c
o
r
d
s
th
r
o
u
g
h
th
is
c
h
a
n
n
e
l
f
in
d
s
it
th
o
r
n
y
to
s
y
n
c
h
r
o
n
iz
e
w
ith
th
e
p
a
r
tie
s
,
a
n
d
h
e
n
c
e
to
cal
cu
l
at
e
t
h
e
co
m
m
o
n
s
ecr
et
k
ey
.
S
y
n
ch
r
o
n
i
zat
i
o
n
b
y
m
u
t
u
al
l
ear
n
i
n
g
(
A
an
d
B
)
i
s
m
u
ch
q
u
i
ck
er
t
h
an
l
ear
n
i
n
g
by
l
i
s
t
e
ni
ng
(
E
)
[
10
].
F
o
r
u
s
u
a
l
c
ry
p
t
o
g
ra
p
h
i
c
s
y
s
t
e
m
s
,
w
e
c
a
n
i
m
p
ro
v
e
t
h
e
s
a
fe
t
y
o
f
t
h
e
p
ro
t
o
c
o
l
b
y
i
n
c
re
a
s
i
n
g
of
t
he
ke
y
l
e
ngt
h.
I
n
t
he
c
a
s
e
of
M
L
P
,
w
e
i
m
pr
ove
d
i
t
by
i
nc
r
e
a
s
i
ng
t
he
s
yna
pt
i
c
de
pt
h
L
of
t
he
ne
ur
a
l
ne
t
w
or
ks
.
Fo
r
a
b
r
u
t
e
f
o
r
c
e
a
t
t
a
c
k
u
s
i
n
g
K
h
i
d
d
e
n
n
e
u
r
o
n
s
,
K
*
N
i
n
p
u
t
n
e
u
r
o
n
s
a
n
d
b
o
u
n
d
a
r
y
o
f
we
i
g
h
t
s
L
,
g
i
v
e
s
(
2
L
+
1
)
K
N
p
o
s
s
i
b
i
l
i
t
i
e
s
.
F
o
r
e
x
a
m
p
l
e
,
t
h
e
c
o
n
f
i
g
u
r
a
t
i
o
n
K
=
3
,
L
=
3
a
n
d
N
=
1
0
0
g
i
v
e
s
u
s
3
*
1
0
2
5
3
k
e
y
p
o
s
s
i
b
i
l
i
t
i
e
s
,
ma
k
i
n
g
t
h
e
a
t
t
a
c
k
u
n
f
e
a
s
i
b
l
e
w
i
t
h
t
o
d
a
y
’
s
c
o
mp
u
t
e
r
p
o
w
e
r
.
E
c
o
u
l
d
s
t
a
r
t
f
r
o
m
a
l
l
o
f
t
h
e
(
2
L+
1
)
3
N
i
n
i
t
i
a
l
w
e
i
g
h
t
ve
c
t
or
s
a
nd
c
a
l
c
ul
a
t
e
t
he
one
s
w
hi
c
h
a
r
e
c
ons
i
s
t
e
nt
w
i
t
h
t
he
i
nput
/
out
put
s
e
que
nc
e
.
I
t
ha
s
be
e
n
s
how
n,
t
ha
t
a
l
l
of
t
he
s
e
i
ni
t
i
a
l
s
t
a
t
e
s
m
ove
t
ow
a
r
ds
t
he
s
a
m
e
f
i
na
l
w
e
i
ght
ve
c
t
or
,
t
he
ke
y
i
s
uni
que
.
T
hi
s
i
s
not
t
r
ue
f
or
s
i
m
pl
e
pe
r
c
e
pt
r
on
t
he
m
os
t
unbe
a
t
e
n
c
r
ypt
a
na
l
ys
i
s
ha
s
t
w
o
s
uppl
e
m
e
nt
a
r
y
i
ngr
e
di
e
nt
s
f
i
r
s
t
;
a
gr
oup
of
a
t
t
a
c
ke
r
i
s
us
e
d.
Se
c
o
n
d
,
E
m
a
k
e
s
e
x
t
r
a
t
r
a
i
n
i
n
g
s
t
e
p
s
w
h
e
n
A
a
n
d
B
a
r
e
q
u
i
e
t
[
1
0
-
12]
.
S
o
i
nc
r
e
a
s
i
ng
s
yna
pt
i
c
de
pt
h
L
of
t
he
ML
P
w
e
c
a
n
m
a
k
e
o
u
r
ML
P
s
a
f
e
.
8.
FU
T
U
R
E
SC
O
P
E
&
C
O
N
C
LU
S
I
O
N
Th
i
s
p
a
p
e
r
p
r
e
s
e
n
t
e
d
a
n
o
v
e
l
a
p
p
r
o
a
c
h
f
o
r
g
e
n
e
r
a
t
i
o
n
o
f
s
e
c
r
e
t
k
e
y
p
r
o
p
o
s
e
d
a
l
g
o
r
i
t
h
m
u
s
i
n
g
M
LP
si
m
u
l
a
t
i
o
n
.
T
h
i
s
t
e
c
h
n
i
q
u
e
e
n
h
a
n
c
e
s
t
h
e
se
c
u
r
i
t
y
f
e
a
t
u
r
e
s
o
f
t
h
e
k
e
y
e
x
c
h
a
n
g
e
a
l
g
o
r
i
t
h
m
b
y
i
n
c
r
e
a
si
n
g
o
f
t
h
e
sy
n
a
p
t
i
c
d
e
p
t
h
L
o
f
t
h
e
M
L
P
.
H
e
r
e
t
wo
p
a
r
t
n
e
r
s
A
a
n
d
B
d
o
n
o
t
h
a
v
e
t
o
e
x
c
h
a
n
g
e
a
c
o
m
m
o
n
s
e
c
r
e
t
k
e
y
o
v
e
r
a
p
u
b
l
i
c
ch
an
n
el
b
u
t
u
s
e
t
h
ei
r
i
n
d
i
s
t
i
n
g
u
i
s
h
ab
l
e
w
ei
g
h
t
s
o
r
o
u
t
p
u
t
s
o
f
t
h
e
act
i
v
at
ed
h
i
d
d
en
l
ay
er
as
a
s
ecr
et
k
ey
ne
e
de
d
f
or
e
nc
r
ypt
i
on
or
de
c
r
ypt
i
on.
S
o
l
i
ke
l
i
hood
of
a
t
t
a
c
k
pr
opos
e
d
t
e
c
hni
que
i
s
m
uc
h
l
e
s
s
e
r
t
ha
n
t
he
s
i
m
pl
e
ke
y
e
xc
ha
nge
a
l
gor
i
t
hm
.
F
ut
ur
e
s
c
ope
of
t
hi
s
t
e
c
hni
que
i
s
t
ha
t
t
hi
s
M
L
P
m
ode
l
c
a
n
be
us
e
d
i
n
w
i
r
e
l
e
s
s
co
m
m
u
n
i
cat
i
o
n
.
S
o
m
e
ev
o
l
u
t
i
o
n
ar
y
al
g
o
r
i
t
h
m
can
b
e
i
n
co
r
p
o
r
at
ed
w
i
t
h
t
h
i
s
M
L
P
m
o
d
el
t
o
g
et
w
el
l
d
i
s
t
r
i
b
u
t
ed
we
i
g
h
t
v
e
ct
o
r
.
RE
F
E
RE
NCE
S
[1
]
At
u
l
Ka
h
a
t
e
,
C
r
y
p
t
o
g
r
a
p
h
y
a
n
d
Ne
t
wo
r
k
S
e
c
u
r
i
t
y
,
2
0
0
3
,
T
a
t
a
M
c
Gr
a
w
-
Hi
l
l
p
u
b
l
i
s
h
i
n
g
C
o
mp
a
n
y
L
i
mi
t
e
d
,
E
i
g
h
t
h
re
p
ri
n
t
2
0
0
6
.
[2
]
Yo
u
n
s
u
n
g
C
h
o
i
.
C
r
y
p
t
a
n
a
l
y
s
i
s
o
n
P
r
i
v
a
c
y
-
Awa
r
e
T
wo
-
Fa
c
t
o
r
A
u
t
h
e
n
t
i
c
a
t
i
o
n
Pr
o
t
o
c
o
l
f
o
r
W
i
r
e
l
e
s
s
Se
n
s
o
r
N
e
t
w
o
r
k
s
,
In
d
o
n
e
s
i
a
n
J
o
u
r
n
a
l
o
f
E
l
e
c
t
r
i
c
a
l
E
n
g
i
n
e
e
r
i
n
g
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
Vo
l
.
8
,
No
.
2
,
No
v
e
mb
e
r
2
0
1
7
,
p
p
.
2
9
6
-
301
DOI
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s
.
v
8
.
i
2
.
p
p
2
9
6
-
301.
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
AI
IS
S
N
:
2252
-
8938
r
Mu
l
t
i
l
a
y
e
r
n
e
u
r
a
l
n
e
t
w
o
r
k
s
y
n
c
h
r
o
n
i
z
e
d
s
e
c
u
r
e
d
s
e
s
s
i
o
n
k
e
y
b
a
s
e
d
e
n
c
r
y
p
t
i
o
n
i
n
…
(
Ar
i
n
d
a
m
S
a
r
k
a
r
)
53
[3
]
Y
C
h
o
i
e
t
a
l
.
S
e
c
u
r
i
t
y
e
n
h
a
n
c
e
d
u
s
e
r
a
u
t
h
e
n
t
i
c
a
t
i
o
n
p
r
o
t
o
c
o
l
f
o
r
wi
r
e
l
e
s
s
s
e
n
s
o
r
n
e
t
wo
r
k
s
u
s
i
n
g
e
l
l
i
p
t
i
c
c
u
r
ve
s
cr
y
p
t
o
g
r
ap
h
y
.
S
en
so
r
s.
2
0
1
4
;
1
4
(
6
)
:
1
0
0
8
1
-
10106.
[4
]
Q.
J
i
a
n
g
e
t
a
l
.
A
p
r
i
v
a
c
y
-
aw
ar
e
t
w
o
-
fa
c
t
o
r
a
u
t
h
e
n
t
i
c
a
t
i
o
n
p
ro
t
o
c
o
l
b
a
s
e
d
o
n
e
l
l
i
p
t
i
c
c
u
rv
e
c
ry
p
t
o
g
ra
p
h
y
fo
r
w
i
re
l
e
s
s
sen
so
r
n
et
w
o
r
k
s.
In
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
N
e
t
w
o
r
k
M
a
n
a
g
e
m
e
n
t
. 2
0
1
7
; 2
7
(
3
)
.
[5
]
S.
K
u
m
a
r
i
e
t
a
l.
U
s
e
r
a
u
th
e
n
tic
a
tio
n
s
c
h
e
m
e
s
f
o
r
w
ir
e
le
s
s
s
e
n
s
o
r
n
e
tw
o
r
k
s
:
A
r
e
v
ie
w
.
A
d
H
o
c
N
e
tw
o
r
k
s
.
2
0
1
5
;
2
7
:
159
-
194.
[6
]
S.
A
.
C
h
a
u
d
h
r
y
e
t
a
l
.
A
n
i
m
p
r
o
v
e
d
a
n
d
p
r
o
v
a
b
l
y
s
e
c
u
r
e
p
r
i
v
a
c
y
p
r
e
s
e
r
v
i
n
g
a
u
t
h
e
n
t
i
c
a
t
i
o
n
p
r
o
t
o
c
o
l
f
o
r
SI
P.
Pe
e
r
-
to
-
Pe
e
r
N
e
t
w
o
r
k
i
n
g
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
. 2
0
1
7
; 1
0
(
1
)
: 1
-
15.
[7
]
Sa
r
k
a
r
,
A
.
,
&
M
a
n
d
a
l
,
J
.
K
.
(
2
0
1
4
)
.
I
n
t
e
l
l
i
g
e
n
t
So
f
t
C
o
m
p
u
t
i
n
g
b
a
s
e
d
C
r
y
p
t
o
g
r
a
p
h
i
c
Te
c
h
n
i
q
u
e
u
s
i
n
g
C
h
a
o
s
Sy
n
c
h
r
o
n
i
z
a
t
i
o
n
f
o
r
W
i
r
e
l
e
s
s
C
o
m
m
u
n
i
c
a
t
i
o
n
(
C
SC
T)
.
In
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
A
m
b
i
e
n
t
S
y
s
t
e
m
s
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
(IJ
A
S
A
),
2
(3
),
1
1
-
20,
DOI
:
1
0
.
5
1
2
1
/
i
j
a
s
a
.
2
0
1
4
.
2
3
0
2
,
I
S
S
N
2
3
2
0
-
9259
[
O
nl
i
ne
]
;
2321
-
6344
[
P
r
i
nt
]
.
[8
]
Sa
r
k
a
r
,
A
.
,
&
M
a
n
d
a
l
,
J
.
K
.
(
2
0
1
4
)
.
So
f
t
C
o
m
p
u
t
i
n
g
b
a
s
e
d
C
r
y
p
t
o
g
r
a
p
h
i
c
Te
c
h
n
i
q
u
e
u
s
i
n
g
K
o
h
o
n
e
n
'
s
Se
l
f
-
Or
g
a
n
i
z
i
n
g
Ma
p
S
y
n
c
h
r
o
n
i
z
a
t
i
o
n
f
o
r
Wi
r
e
l
e
s
s
c
o
m
m
u
n
i
c
a
t
i
o
n
(
K
S
O
MS
C
T
)
.
In
t
e
r
n
a
t
i
o
nal
J
our
nal
i
n
F
oundat
i
ons
of
C
om
put
e
r
Sc
i
e
nc
e
&
T
e
c
hnol
ogy
(
I
J
F
C
ST
)
,
4
(5
),
8
5
-
100,
D
O
I
:
10.
5121/
i
j
f
c
s
t
.
2014.
4508,
IS
S
N
1
8
3
9
-
7662.
[9
]
Sa
r
k
a
r
,
A
.
,
&
M
a
n
d
a
l
,
J
.
K
.
(
2
0
1
4
)
.
N
e
u
r
o
G
e
n
e
t
i
c
K
e
y
B
a
s
e
d
R
e
c
u
r
s
i
v
e
M
o
d
u
l
o
-
2
S
ubs
t
i
t
ut
i
on
U
s
i
ng
M
ut
a
t
e
d
Ch
a
r
a
c
t
e
r
f
o
r
O
n
l
i
n
e
W
i
r
el
ess
C
o
m
m
u
n
i
cat
i
o
n
(
N
G
K
R
M
S
M
C
)
.
In
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
C
o
m
p
u
t
a
t
i
o
n
a
l
S
c
i
e
n
c
e
a
n
d
In
f
o
r
m
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
(IJ
C
S
IT
Y
),
1
(4
),
4
9
-
59,
D
O
I
:
10.
5121/
i
j
c
s
i
t
y.
2014.
1404,
I
S
S
N
2320
-
7442
[
O
nl
i
ne
]
;
2320
-
8457
[
P
r
i
nt
]
.
[1
0
]
R.
M
i
s
l
o
v
a
t
y
,
Y
.
P
e
r
c
h
e
n
o
k
,
I
.
K
a
n
t
e
r
,
a
n
d
W
.
Ki
n
z
e
l
.
S
e
c
u
r
e
k
e
y
-
ex
ch
an
g
e
p
r
o
t
o
co
l
w
i
t
h
an
ab
sen
ce
o
f
i
n
j
ect
i
v
e
fu
n
c
t
i
o
n
s
.
P
h
y
s
.
R
e
v
.
E
,
6
6
:
0
6
6
1
0
2
,
2
0
0
2
.
[1
1
]
A.
R
u
t
t
o
r
,
W
.
Ki
n
z
e
l
,
R
.
Na
e
h
,
a
n
d
I
.
Ka
n
t
e
r
.
Ge
n
e
t
i
c
a
t
t
a
c
k
o
n
n
e
u
r
a
l
c
r
y
p
t
o
g
r
a
p
h
y
.
P
h
y
s
.
R
e
v
.
E
,
7
3
(
3
)
:
0
3
6
1
2
1
,
2006.
[1
2
]
A.
E
n
g
e
l
a
n
d
C
.
Va
n
d
e
n
B
r
o
e
c
k.
S
t
a
t
i
s
t
i
c
a
l
M
e
c
ha
ni
c
s
of
L
e
a
r
ni
ng.
C
a
m
br
i
dge
U
ni
ve
r
s
i
t
y
P
r
e
s
s
,
C
a
m
br
i
dge
,
2001.
[1
3
]
T.
G
o
d
h
a
v
a
r
i
,
N
.
R
.
A
l
a
i
n
e
l
u
a
n
d
R
.
So
u
n
d
a
r
a
r
a
j
a
n
“
C
r
y
p
t
o
g
r
a
p
h
y
U
s
i
n
g
N
e
u
r
a
l
N
e
t
w
o
r
k
”
I
EEE
I
n
d
i
c
o
n
2
0
0
5
Co
n
f
e
r
e
n
c
e
,
Ch
e
n
n
a
i
,
I
n
d
i
a
,
1
1
-
13
D
e
c
.
2005.
[1
4
]
Wo
l
f
g
a
n
g
K
i
n
z
e
l
a
n
d
l
d
o
Ka
n
t
e
r
,
"
I
n
t
e
r
a
c
t
i
n
g
n
e
u
r
a
l
n
e
t
wo
r
k
s
a
n
d
c
r
y
p
t
o
g
r
a
p
h
y
"
,
Ad
v
a
n
c
e
s
i
n
S
o
l
i
d
S
t
a
t
e
P
h
y
s
i
c
s
,
Ed
.
b
y
B
.
K
r
a
m
e
r
(
Sp
r
i
n
g
e
r
,
B
e
r
l
i
n
.
2
0
0
2
)
,
V
o
l
.
4
2
,
p
.
3
8
3
a
r
X
i
v
-
co
n
d
-
ma
t
/
0
2
0
3
0
1
1
,
2
0
0
2
.
[1
5
]
Wo
l
f
g
a
n
g
K
i
n
z
e
l
a
n
d
l
d
o
K
a
n
t
e
r
,
"
N
e
u
r
a
l
c
r
y
p
t
o
g
r
a
p
h
y
”
p
r
o
c
e
e
d
i
n
g
s
o
f
t
h
e
9
th
in
te
r
n
a
tio
n
a
l
c
o
n
f
e
r
e
n
c
e
o
n
N
e
u
r
a
l
In
fo
rm
a
t
i
o
n
p
ro
c
e
s
s
i
n
g
(IC
O
N
IP
0
2
).
[1
6
]
Do
n
g
Hu
"
A
n
e
w
s
e
r
v
i
c
e
b
a
s
e
d
c
o
mp
u
t
i
n
g
s
e
c
u
r
i
t
y
mo
d
e
l
wi
t
h
n
e
u
r
a
l
c
r
y
p
t
o
g
r
a
p
h
y
"
I
E
E
E
0
7
/
2
0
0
9
.
[1
7
]
Lu
´
ı
s
,
F.
,
Se
o
a
n
e
,
L.
F.
,
&
R
u
t
t
o
r
,
A
.
(
2
0
1
1
)
.
Su
c
c
e
s
s
f
u
l
a
t
t
a
c
k
o
n
PPM
-
ba
s
e
d
ne
ur
a
l
c
r
ypt
ogr
a
phy.
ar
X
i
v
pr
e
pr
i
nt
ar
X
i
v
:1
1
1
1
.5
7
9
2
,2
4
.
[1
8
]
Do
l
e
c
k
i
,
M
.
,
Ko
z
e
r
a
,
R
.
,
&
L
e
n
i
k
,
K.
(
2
0
1
3
)
.
T
h
e
E
v
a
l
u
a
t
i
o
n
o
f
t
h
e
T
P
M
S
y
n
c
h
r
o
n
i
z
a
t
i
o
n
o
n
t
h
e
B
a
s
i
s
o
f
t
h
e
i
r
Ou
t
p
u
t
s
.
Jo
u
rn
a
l
o
f
A
ch
i
evem
en
t
s
i
n
M
a
t
eri
a
l
s
a
n
d
M
a
n
u
f
a
ct
u
ri
n
g
E
n
g
i
n
eeri
n
g
57
(2
),
p
p
.
9
1
-
98.
BI
O
G
R
A
P
H
Y
OF
A
U
T
HOR
Dr
.
AR
I
NDAM
S
AR
KAR
i
s
c
u
r
r
e
n
t
l
y
s
e
r
v
i
n
g
t
h
e
De
p
a
r
me
n
t
o
f
C
o
mp
u
t
e
r
S
c
i
e
n
c
e
&
El
e
c
t
r
o
n
i
c
s
,
Ra
m
a
k
r
i
s
h
n
a
M
i
s
s
i
o
n
V
i
d
y
a
m
a
n
d
i
r
a
,
Be
l
u
r
M
a
t
h
-
711202,
H
ow
r
a
h
a
s
a
n
A
s
t
t
.
P
r
of
e
s
s
or
.
H
e
ha
s
co
m
p
l
et
ed
h
i
s
M
ast
er
o
f
C
o
m
p
u
t
er
A
p
p
l
i
cat
i
o
n
(
M
.
C
.
A
)
d
eg
r
ee
i
n
t
h
e
y
ear
o
f
2
0
0
8
f
r
o
m
V
I
S
V
A
BH
A
RA
T
I
,
S
a
n
t
i
n
i
k
e
t
a
n
,
W
B,
I
n
d
i
a
a
n
d
h
e
s
e
c
u
r
e
d
U
n
i
v
e
r
s
i
t
y
F
i
rs
t
C
l
a
s
s
F
i
rs
t
R
a
n
k
.
In
t
h
e
y
e
a
r
of
2011,
D
r
.
S
a
r
ka
r
ha
s
c
om
pl
e
t
e
d
hi
s
M
.
T
e
c
h
i
n
C
om
ut
e
r
S
c
i
e
nc
e
&
E
nggi
ne
e
r
i
ng
de
gr
e
e
fro
m
Un
i
v
e
r
s
i
t
y
o
f
Ka
l
y
a
n
i
,
W
B
,
In
d
i
a
a
n
d
a
l
s
o
s
e
c
u
re
d
U
n
i
v
e
rs
i
t
y
F
i
rs
t
C
l
a
s
s
F
i
rs
t
R
a
n
k
.
D
r.
S
a
rk
a
r
ha
s
c
om
pl
e
t
e
d
hi
s
D
oc
t
or
of
P
hi
l
os
o
phy
i
n
E
ngi
ne
e
r
i
ng
i
n
t
he
ye
a
r
of
2015
f
r
om
U
ni
ve
r
s
i
t
y
of
Ka
l
y
a
n
i
u
n
d
e
r
t
h
e
I
NS
P
I
R
E
F
e
l
l
o
ws
h
i
p
S
c
h
e
me
o
f
De
p
a
r
t
me
n
t
o
f
S
c
i
e
n
c
e
&
T
e
c
h
n
o
l
o
g
y
(
DS
T
)
,
Ne
w
De
l
h
i
,
I
n
d
i
a
.
I
n
t
h
e
y
e
a
r
o
f
2
0
1
6
h
e
h
a
s
s
e
c
u
r
e
d
2
n
d
Ra
n
k
in
th
e
W
e
s
t
B
e
n
g
a
l
C
o
lle
g
e
S
e
r
v
ic
e
Co
m
m
i
s
s
i
o
n
e
xa
m
i
na
t
i
on.
H
e
ha
s
m
or
e
t
ha
n
65
In
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
a
n
d
C
o
n
fe
re
n
c
e
p
u
b
l
i
c
a
t
i
o
n
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.