T
E
L
K
O
M
NIKA
T
elec
o
mm
un
ica
t
io
n Co
m
pu
t
i
ng
E
lect
ro
nics
a
nd
Co
ntr
o
l
Vo
l.
24
,
No
.
4
,
A
u
g
u
s
t
20
26
,
p
p
.
1
241
~1
2
5
2
I
SS
N:
1
6
9
3
-
6
9
3
0
,
DOI
: 1
0
.
1
2
9
2
8
/
T
E
L
KOM
NI
K
A
.
v
24
i
4
.
27791
1241
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//telko
mn
ika
.
u
a
d
.
a
c.
i
d
Aco
ustic and
vibr
a
tion side cha
nnel
ana
ly
sis
on po
st
-
qua
ntu
m
cryp
tog
ra
phy
using
i
m
a
g
e
-
ba
sed
d
eep learning
Abdu
l H
a
ris M
uh
a
mm
a
d
,
G
a
m
a
ria
M
a
nd
a
r
,
Adelina
I
bra
hi
m
I
n
f
o
r
mat
i
c
s E
n
g
i
n
e
e
r
i
n
g
S
t
u
d
y
P
r
o
g
r
a
m,
M
u
h
a
m
ma
d
i
y
a
h
U
n
i
v
e
r
si
t
y
o
f
N
o
r
t
h
M
a
l
u
k
u
,
T
e
r
n
a
t
e
,
I
n
d
o
n
e
si
a
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
an
10
,
2
0
2
6
R
ev
i
s
ed
A
p
r
6
,
2
0
2
6
A
cc
ep
ted
Ma
y
25
,
2026
P
o
st
-
q
u
a
n
t
u
m
c
r
y
p
to
g
ra
p
h
y
(P
Q
C)
is
d
e
sig
n
e
d
t
o
re
sist
q
u
a
n
t
u
m
-
e
ra
a
tt
a
c
k
s;
h
o
w
e
v
e
r,
p
ra
c
ti
c
a
l
im
p
le
m
e
n
tatio
n
s
re
m
a
in
v
u
ln
e
ra
b
le
t
o
p
h
y
si
c
a
l
sid
e
-
c
h
a
n
n
e
l
lea
k
a
g
e
.
T
h
is
w
o
rk
p
ro
p
o
se
s
a
n
im
a
g
e
-
b
a
se
d
a
c
o
u
stic
–
v
ib
ra
ti
o
n
sid
e
-
c
h
a
n
n
e
l
a
n
a
ly
sis
f
ra
m
e
w
o
rk
to
a
ss
e
ss
n
o
n
-
in
v
a
siv
e
lea
k
a
g
e
in
P
QC
s
y
ste
m
s.
A
c
o
u
stic
a
n
d
v
ib
ra
ti
o
n
sig
n
a
ls
f
ro
m
se
c
r
e
t
-
d
e
p
e
n
d
e
n
t
e
x
e
c
u
ti
o
n
s
a
re
m
o
d
e
led
a
n
d
tran
sf
o
rm
e
d
in
to
ti
m
e
–
f
r
e
q
u
e
n
c
y
sp
e
c
tro
g
ra
m
s
u
sin
g
sh
o
r
t
-
ti
m
e
f
o
u
rier
tran
sf
o
rm
(S
T
F
T
).
Th
e
d
a
tas
e
t
c
o
m
p
rise
s
1
,
5
4
5
sa
m
p
les
(1
,
2
3
6
train
in
g
a
n
d
3
0
9
tes
ti
n
g
),
a
c
q
u
ir
e
d
a
t
1
6
k
Hz
a
n
d
se
g
m
e
n
ted
in
to
2
.
5
-
se
c
o
n
d
w
in
d
o
w
s.
L
e
a
k
a
g
e
c
las
sif
i
c
a
ti
o
n
is
p
e
rf
o
r
m
e
d
u
sin
g
c
o
n
v
o
lu
ti
o
n
a
l
n
e
u
ra
l
n
e
tw
o
rk
s
(CNN
s)
a
n
d
v
isio
n
tran
sf
o
r
m
e
rs
(V
iT
s)
u
n
d
e
r
sin
g
le
-
m
o
d
a
li
ty
a
n
d
m
u
lt
i
m
o
d
a
l
f
u
sio
n
se
tt
in
g
s.
Re
su
lt
s
sh
o
w
th
a
t
a
c
o
u
stic
sig
n
a
ls
y
i
e
ld
stro
n
g
lea
k
a
g
e
,
a
c
h
iev
in
g
u
p
to
1
0
0
%
a
c
c
u
ra
c
y
w
it
h
CNN
,
w
h
il
e
v
ib
ra
ti
o
n
sig
n
a
ls
re
a
c
h
u
p
t
o
9
8
.
7
5
%
.
M
u
lt
im
o
d
a
l
f
u
sio
n
im
p
ro
v
e
s
train
in
g
sta
b
il
it
y
a
n
d
o
v
e
ra
ll
p
e
rf
o
rm
a
n
c
e
,
a
n
d
V
iT
m
o
d
e
ls
d
e
m
o
n
stra
te
b
e
tt
e
r
g
e
n
e
ra
li
z
a
ti
o
n
a
c
ro
ss
m
o
d
a
li
ti
e
s.
T
h
e
se
f
in
d
in
g
s
c
o
n
f
irm
th
a
t
m
u
lt
im
o
d
a
l
sp
e
c
tro
g
ra
m
-
b
a
se
d
d
e
e
p
lea
rn
i
n
g
is
e
ff
e
c
ti
v
e
f
o
r
P
QC
si
d
e
-
c
h
a
n
n
e
l
a
n
a
l
y
sis
a
n
d
u
n
d
e
rsc
o
re
th
e
n
e
e
d
f
o
r
rig
o
ro
u
s
p
h
y
sic
a
l
se
c
u
rit
y
e
v
a
lu
a
ti
o
n
in
r
e
a
l
-
w
o
rld
P
QC
im
p
lem
e
n
tatio
n
s.
K
ey
w
o
r
d
s
:
A
co
u
s
tic
lea
k
a
g
e
Dee
p
lear
n
in
g
P
o
s
t
-
q
u
an
tu
m
cr
y
p
to
g
r
p
h
y
Sid
e
-
c
h
an
n
el
attac
k
Vib
r
atio
n
an
al
y
s
i
s
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
A
b
d
u
l H
ar
i
s
Mu
h
a
m
m
ad
I
n
f
o
r
m
a
tics
E
n
g
i
n
ee
r
i
n
g
S
tu
d
y
P
r
o
g
r
a
m
,
Mu
h
a
m
m
ad
i
y
ah
U
n
iv
er
s
it
y
o
f
No
r
th
Ma
l
u
k
u
K
H
Ah
m
ad
Dah
la
n
Stre
et
No
1
0
0
,
Sas
a,
T
er
n
ate
C
it
y
,
No
r
th
Ma
lu
k
u
,
I
n
d
o
n
e
s
ia
E
m
ail:
a
g
r
y
.
ar
is
a
n
d
i
@
g
m
ail.
c
o
m
1.
I
NT
RO
D
UCT
I
O
N
Qu
a
n
tu
m
co
m
p
u
t
in
g
e
x
p
lo
its
p
r
in
cip
les
o
f
q
u
a
n
t
u
m
m
ec
h
an
ics
to
p
er
f
o
r
m
co
m
p
u
tatio
n
s
b
e
y
o
n
d
class
ical
ca
p
ab
ilit
ie
s
b
y
u
tili
zi
n
g
q
u
b
its
t
h
at
e
x
is
t
i
n
s
u
p
er
p
o
s
itio
n
s
ta
tes.
T
h
is
e
n
ab
les
e
f
f
icie
n
t
s
o
l
u
tio
n
s
to
p
r
o
b
lem
s
s
u
ch
as
lar
g
e
in
te
g
e
r
f
ac
to
r
izatio
n
,
w
h
ic
h
ar
e
in
f
e
asib
le
f
o
r
class
ical
s
y
s
te
m
s
.
Fo
r
in
s
tan
ce
,
Sh
o
r
’
s
alg
o
r
ith
m
ca
n
b
r
ea
k
w
id
el
y
u
s
ed
cr
y
p
to
g
r
ap
h
ic
s
c
h
e
m
es
s
u
ch
as
R
i
v
est
-
S
h
a
m
ir
-
A
d
le
m
a
n
(
R
SA
)
an
d
ellip
tic
cu
r
v
e
cr
y
p
to
g
r
ap
h
y
(
E
C
C
)
,
p
o
s
in
g
s
i
g
n
if
ican
t
r
is
k
s
to
d
ata
s
ec
u
r
it
y
[
1
]
,
[
2
]
.
I
n
ad
d
i
tio
n
,
q
u
an
t
u
m
d
ata
p
r
o
ce
s
s
in
g
o
f
te
n
r
elies
o
n
e
n
co
d
in
g
tech
n
iq
u
e
s
s
u
ch
a
s
a
m
p
lit
u
d
e
an
d
an
g
le
en
co
d
i
n
g
,
w
h
ic
h
m
a
y
n
o
t
p
r
eser
v
e
in
f
o
r
m
atio
n
in
a
lo
s
s
l
ess
m
an
n
er
,
p
ar
ticu
lar
l
y
f
o
r
im
ag
e
-
b
ased
p
r
o
ce
s
s
i
n
g
ta
s
k
s
[
3
]
,
[
4
]
.
T
o
ad
d
r
ess
th
ese
t
h
r
ea
ts
,
p
o
s
t
-
q
u
a
n
t
u
m
cr
y
p
to
g
r
ap
h
y
(
P
QC
)
h
as
b
ee
n
d
ev
e
lo
p
ed
to
en
s
u
r
e
s
ec
u
r
it
y
ag
ain
s
t
b
o
th
clas
s
ical
a
n
d
q
u
a
n
tu
m
a
ttack
s
.
P
QC
s
ch
e
m
e
s
a
r
e
b
ased
o
n
alter
n
ati
v
e
h
ar
d
p
r
o
b
lem
s
,
in
cl
u
d
i
n
g
lattice
-
b
ased
,
co
d
e
-
b
ased
,
h
a
s
h
-
b
ased
,
an
d
m
u
lti
v
ar
iate
cr
y
p
to
g
r
ap
h
y
,
w
h
ic
h
ar
e
c
u
r
r
en
tl
y
co
n
s
id
er
ed
r
esis
ta
n
t
to
q
u
an
tu
m
al
g
o
r
ith
m
s
[
5
]
-
[
7
]
.
Ho
w
e
v
er
,
th
e
s
ec
u
r
it
y
o
f
cr
y
p
to
g
r
ap
h
ic
s
y
s
te
m
s
d
ep
en
d
s
n
o
t
o
n
l
y
o
n
th
eir
m
at
h
e
m
a
tical
s
tr
en
g
t
h
b
u
t
al
s
o
o
n
th
eir
i
m
p
le
m
e
n
tati
o
n
.
I
n
p
r
ac
tice,
cr
y
p
to
g
r
ap
h
i
c
o
p
er
atio
n
s
o
f
te
n
p
r
o
d
u
ce
u
n
i
n
ten
d
ed
p
h
y
s
ical
leak
ag
e,
k
n
o
w
n
a
s
s
id
e
-
ch
a
n
n
el
lea
k
ag
e,
w
h
ic
h
ca
n
b
e
e
x
p
lo
ited
to
r
ec
o
v
er
s
en
s
it
i
v
e
in
f
o
r
m
at
io
n
s
u
c
h
as s
ec
r
et
k
e
y
s
[
8
]
-
[
1
3
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
24
,
No
.
4
,
A
u
g
u
s
t
20
26
:
1
241
-
1
2
5
2
1242
Am
o
n
g
t
h
e
v
ar
io
u
s
t
y
p
e
s
o
f
s
i
d
e
ch
an
n
els,
ac
o
u
s
tic
a
n
d
m
ec
h
an
ica
l
v
ib
r
ati
on
-
b
ased
lea
k
ag
es
r
e
m
ai
n
s
ig
n
i
f
ica
n
tl
y
le
s
s
ex
p
lo
r
ed
co
m
p
ar
ed
to
p
o
w
er
co
n
s
u
m
p
t
io
n
an
d
elec
tr
o
m
ag
n
etic
e
m
i
s
s
io
n
s
.
Me
ch
a
n
ical
v
ib
r
atio
n
s
an
d
ac
o
u
s
t
ic
s
ig
n
al
s
ca
n
n
atu
r
all
y
ar
i
s
e
f
r
o
m
p
r
o
ce
s
s
o
r
ac
tiv
it
y
,
elec
tr
o
n
ic
co
m
p
o
n
en
ts
,
an
d
th
e
m
ec
h
a
n
ical
s
tr
u
ct
u
r
e
o
f
co
m
p
u
ti
n
g
d
ev
ice
s
d
u
r
in
g
th
e
ex
ec
u
tio
n
o
f
cr
y
p
to
g
r
ap
h
ic
alg
o
r
it
h
m
s
.
Fu
r
t
h
er
m
o
r
e,
th
e
w
id
esp
r
ea
d
av
ailab
ilit
y
o
f
m
icr
o
p
h
o
n
es a
n
d
ac
ce
ler
o
m
et
er
s
,
in
cl
u
d
in
g
th
o
s
e
e
m
b
ed
d
ed
in
co
n
s
u
m
er
-
g
r
ad
e
d
ev
ices,
en
ab
les
t
h
e
n
o
n
-
i
n
v
a
s
iv
e
ac
q
u
i
s
itio
n
o
f
ac
o
u
s
tic
a
n
d
v
ib
r
at
io
n
s
i
g
n
a
ls
,
th
er
eb
y
in
cr
ea
s
i
n
g
p
o
ten
t
ial
s
ec
u
r
it
y
r
is
k
s
[
1
4
]
,
[
1
5
]
.
A
m
o
n
g
v
ar
io
u
s
s
id
e
ch
a
n
n
els,
ac
o
u
s
tic
an
d
v
ib
r
atio
n
-
b
ase
d
leak
ag
e
r
e
m
ai
n
s
u
n
d
er
ex
p
lo
r
ed
co
m
p
ar
ed
to
p
o
w
er
an
d
e
lectr
o
m
a
g
n
et
ic
ch
a
n
n
el
s
.
T
h
ese
s
ig
n
al
s
n
atu
r
all
y
ar
is
e
f
r
o
m
d
ev
ic
e
o
p
er
atio
n
s
an
d
ca
n
b
e
ca
p
tu
r
ed
n
o
n
-
in
v
a
s
iv
el
y
u
s
i
n
g
co
m
m
o
n
s
e
n
s
o
r
s
s
u
c
h
as
m
icr
o
p
h
o
n
es
an
d
ac
ce
ler
o
m
eter
s
,
in
cr
ea
s
i
n
g
p
o
ten
tial
s
ec
u
r
it
y
r
is
k
s
[
1
4
]
,
[
1
5
]
.
E
x
is
tin
g
s
tu
d
ies
p
r
i
m
ar
il
y
f
o
cu
s
o
n
class
ica
l
cr
y
p
to
g
r
ap
h
y
a
n
d
r
ely
o
n
m
an
u
al
o
r
o
n
e
-
d
i
m
en
s
io
n
al
f
e
atu
r
e
ex
tr
ac
tio
n
m
eth
o
d
s
,
wh
ich
ar
e
li
m
ited
in
ca
p
tu
r
in
g
co
m
p
le
x
an
d
n
o
is
y
l
ea
k
ag
e
p
atter
n
s
[
1
6
]
-
[
2
0
]
.
Desp
ite
ex
ten
s
i
v
e
r
esear
c
h
o
n
s
id
e
-
c
h
a
n
n
e
l
attac
k
s
tar
g
et
in
g
cla
s
s
ical
cr
y
p
to
g
r
ap
h
ic
i
m
p
le
m
en
ta
tio
n
s
,
s
t
u
d
ies
f
o
cu
s
in
g
s
p
ec
if
ical
l
y
o
n
ac
o
u
s
tic
an
d
v
ib
r
atio
n
-
b
ased
lea
k
a
g
e
i
n
P
QC
r
e
m
ai
n
v
er
y
li
m
ited
.
E
x
is
tin
g
s
id
e
-
ch
a
n
n
el
an
al
y
s
e
s
p
r
ed
o
m
i
n
an
tl
y
in
v
es
tig
ate
p
o
w
er
o
r
elec
tr
o
m
ag
n
et
ic
leak
ag
e
an
d
ar
e
lar
g
el
y
ce
n
ter
ed
o
n
cla
s
s
ica
l
cr
y
p
to
s
y
s
te
m
s
,
w
h
ile
ac
o
u
s
t
ic
an
d
v
ib
r
atio
n
ch
a
n
n
els
ar
e
o
f
ten
o
v
er
lo
o
k
ed
,
p
ar
ticu
lar
l
y
i
n
th
e
co
n
te
x
t
o
f
P
QC
i
m
p
le
m
e
n
tatio
n
s
.
Mo
r
e
o
v
er
,
m
o
s
t
p
r
io
r
w
o
r
k
s
r
el
y
o
n
s
i
n
g
le
-
m
o
d
alit
y
an
al
y
s
is
a
n
d
m
a
n
u
al
o
r
o
n
e
-
d
i
m
e
n
s
io
n
al
f
ea
t
u
r
e
ex
tr
ac
tio
n
tech
n
iq
u
es,
w
h
ich
ar
e
in
s
u
f
f
i
cien
t
f
o
r
m
o
d
elin
g
th
e
co
m
p
le
x
,
n
o
n
-
li
n
ea
r
leak
a
g
e
p
atter
n
s
p
r
o
d
u
ce
d
b
y
m
o
d
er
n
cr
y
p
to
g
r
ap
h
ic
e
x
ec
u
tio
n
.
T
h
is
r
ev
ea
ls
a
cr
itica
l
r
esear
ch
g
ap
i
n
t
h
e
lac
k
o
f
co
m
p
r
e
h
e
n
s
i
v
e
m
u
lti
m
o
d
al
s
id
e
-
ch
an
n
el
a
n
al
y
s
i
s
f
r
a
m
e
w
o
r
k
s
ca
p
ab
le
o
f
ca
p
tu
r
in
g
co
r
r
elate
d
leak
ag
e
b
eh
av
io
r
ac
r
o
s
s
m
u
ltip
le
p
h
y
s
ical
d
o
m
a
in
s
in
P
QC
s
y
s
te
m
s
.
T
h
is
li
m
i
tatio
n
lead
s
to
a
s
ig
n
i
f
ican
t
p
r
o
b
lem
:
c
u
r
r
en
t
s
id
e
-
ch
a
n
n
el
a
n
al
y
s
is
m
et
h
o
d
s
an
d
s
ec
u
r
it
y
ev
alu
a
tio
n
f
r
a
m
e
w
o
r
k
s
ar
e
n
o
t
ad
eq
u
atel
y
d
esi
g
n
ed
to
d
etec
t,
m
o
d
el,
o
r
m
iti
g
ate
m
u
lti
m
o
d
al
ac
o
u
s
tic
an
d
v
ib
r
atio
n
lea
k
ag
e
i
n
P
QC
i
m
p
le
m
e
n
tatio
n
s
.
A
s
a
r
es
u
lt,
t
h
e
tr
u
e
ex
te
n
t
o
f
i
n
f
o
r
m
atio
n
lea
k
ag
e
i
n
r
ea
l
-
w
o
r
ld
en
v
ir
o
n
m
e
n
t
s
r
e
m
ai
n
s
p
o
o
r
l
y
u
n
d
er
s
to
o
d
,
p
o
ten
tiall
y
leav
i
n
g
P
QC
s
y
s
te
m
s
v
u
ln
er
ab
le
t
o
n
o
n
-
in
v
asi
v
e
a
n
d
co
v
er
t a
ttack
s
.
T
o
ad
d
r
ess
th
is
g
ap
,
th
is
s
tu
d
y
i
n
tr
o
d
u
ce
s
a
m
u
lti
m
o
d
al,
i
m
ag
e
-
b
ased
s
id
e
-
c
h
a
n
n
e
l
an
al
y
s
i
s
f
r
a
m
e
w
o
r
k
t
h
at
j
o
in
tl
y
ex
p
lo
i
ts
ac
o
u
s
tic
a
n
d
v
ib
r
atio
n
lea
k
ag
e
in
P
Q
C
i
m
p
le
m
e
n
tat
io
n
s
.
B
y
tr
an
s
f
o
r
m
i
n
g
p
h
y
s
ical
leak
a
g
e
s
i
g
n
al
s
in
to
s
p
ec
tr
o
g
r
am
r
ep
r
esen
ta
tio
n
s
,
th
e
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
lev
er
ag
es
co
n
v
o
lu
tio
n
al
n
eu
r
al
n
et
w
o
r
k
s
(
C
NN
s
)
an
d
v
is
io
n
tr
a
n
s
f
o
r
m
er
s
(
ViT
s
)
to
ca
p
tu
r
e
b
o
th
lo
ca
l
an
d
g
lo
b
al
leak
a
g
e
ch
ar
ac
ter
is
tic
s
ac
r
o
s
s
m
o
d
aliti
es.
T
o
th
e
b
est
o
f
o
u
r
k
n
o
w
led
g
e,
th
i
s
w
o
r
k
i
s
a
m
o
n
g
th
e
f
ir
s
t
to
s
y
s
te
m
atica
ll
y
in
v
e
s
ti
g
ate
m
u
lti
m
o
d
al
ac
o
u
s
t
ic
–
v
ib
r
atio
n
s
p
ec
tr
o
g
r
a
m
f
u
s
i
o
n
u
s
i
n
g
d
ee
p
lear
n
i
n
g
f
o
r
s
i
d
e
-
ch
a
n
n
e
l
a
n
al
y
s
is
o
f
P
QC
i
m
p
le
m
en
tatio
n
s
.
I
n
lig
h
t
o
f
t
h
e
a
f
o
r
e
m
en
tio
n
e
d
ch
allen
g
es,
th
i
s
r
esear
ch
p
r
o
p
o
s
es
a
n
o
v
el
ap
p
r
o
ac
h
f
o
r
an
al
y
z
in
g
ac
o
u
s
tic
an
d
v
ib
r
atio
n
s
id
e
-
c
h
an
n
el
lea
k
a
g
e
in
P
QC
i
m
p
le
m
en
tatio
n
s
u
s
i
n
g
a
m
u
lt
i
m
o
d
al,
i
m
ag
e
-
b
ased
d
ee
p
lear
n
in
g
f
r
a
m
e
w
o
r
k
.
T
h
e
p
r
im
ar
y
o
b
j
ec
tiv
e
o
f
t
h
i
s
s
t
u
d
y
i
s
t
o
d
ev
elo
p
a
s
id
e
-
ch
a
n
n
e
l
an
al
y
s
i
s
m
o
d
el
ca
p
ab
le
o
f
ca
p
tu
r
in
g
t
h
e
r
elatio
n
s
h
ip
b
et
w
ee
n
s
ec
r
et
-
d
ep
en
d
en
t
P
Q
C
ex
ec
u
tio
n
an
d
t
h
e
r
es
u
lti
n
g
p
h
y
s
ical
leak
a
g
e
s
ig
n
al
s
.
Fu
r
t
h
er
m
o
r
e,
th
i
s
r
ese
ar
ch
ai
m
s
to
ev
al
u
ate
th
e
e
x
te
n
t
to
w
h
ic
h
s
e
n
s
i
tiv
e
i
n
f
o
r
m
at
io
n
ca
n
b
e
in
f
er
r
ed
f
r
o
m
ac
o
u
s
tic
an
d
v
ib
r
atio
n
em
is
s
io
n
s
an
d
to
ass
e
s
s
t
h
e
ef
f
ec
ti
v
en
e
s
s
o
f
m
u
lti
m
o
d
al
f
u
s
io
n
b
y
in
te
g
r
ati
n
g
b
o
th
m
o
d
alities
an
d
co
m
p
ar
i
n
g
t
h
e
r
esu
l
ts
w
it
h
s
i
n
g
le
-
m
o
d
ality
a
n
al
y
s
i
s
.
T
o
ac
h
iev
e
th
is
,
ac
o
u
s
t
ic
an
d
v
ib
r
atio
n
s
i
g
n
a
ls
ar
e
tr
an
s
f
o
r
m
ed
in
to
i
m
a
g
e
-
b
ased
r
ep
r
ese
n
tatio
n
s
th
r
o
u
g
h
s
p
ec
tr
o
g
r
a
m
en
co
d
in
g
,
e
n
ab
lin
g
th
e
ap
p
licatio
n
o
f
C
N
Ns
an
d
ViT
s
f
o
r
f
ea
tu
r
e
ex
tr
ac
tio
n
a
n
d
leak
ag
e
in
f
er
en
ce
.
B
y
eli
m
i
n
ati
n
g
t
h
e
r
elian
ce
o
n
m
a
n
u
al
f
ea
tu
r
e
e
n
g
in
ee
r
i
n
g
,
th
e
p
r
o
p
o
s
ed
im
a
g
e
-
b
ased
ap
p
r
o
ac
h
f
ac
ilit
ates
th
e
lear
n
i
n
g
o
f
co
m
p
le
x
a
n
d
n
o
n
-
li
n
ea
r
leak
a
g
e
p
atter
n
s
t
h
at
ar
e
d
if
f
icu
l
t
to
m
o
d
el
u
s
in
g
co
n
v
e
n
tio
n
al
s
i
g
n
a
l
p
r
o
c
ess
i
n
g
tec
h
n
iq
u
e
s
,
th
er
eb
y
p
r
o
v
id
in
g
a
m
o
r
e
co
m
p
r
eh
en
s
i
v
e
p
h
y
s
ica
l secu
r
i
t
y
e
v
alu
a
tio
n
o
f
P
QC
i
m
p
le
m
en
tat
io
n
s
.
2.
RE
L
AT
E
D
WO
RK
S
2
.
1
.
P
Q
C
P
QC
is
a
f
ield
o
f
cr
y
p
to
g
r
ap
h
y
th
a
t
f
o
c
u
s
es
o
n
d
esig
n
i
n
g
cr
y
p
to
g
r
ap
h
ic
al
g
o
r
ith
m
s
th
at
ar
e
r
esis
tan
t
to
an
d
s
e
cu
r
e
a
g
ain
s
t
q
u
a
n
t
u
m
-
co
m
p
u
ter
attac
k
s
.
Un
li
k
e
c
o
n
v
en
t
i
o
n
al
c
r
y
p
t
o
g
r
a
p
h
i
c
s
c
h
em
e
s
,
w
h
ic
h
g
e
n
e
r
a
l
ly
r
e
ly
o
n
m
a
th
em
at
i
c
al
p
r
o
b
l
em
s
s
u
ch
as
i
n
t
eg
e
r
f
a
ct
o
r
i
z
ati
o
n
a
n
d
d
is
c
r
e
t
e
l
o
g
a
r
i
th
m
s
,
PQ
C
al
g
o
r
ith
m
s
a
r
e
d
e
s
ig
n
e
d
a
r
o
u
n
d
p
r
o
b
l
em
s
b
e
li
e
v
e
d
t
o
b
e
d
if
f
i
cu
lt
t
o
s
o
lv
e
ev
en
w
it
h
q
u
an
tu
m
c
o
m
p
u
t
e
r
s
.
T
h
e
r
e
f
o
r
e
,
PQ
C
is
c
o
n
s
i
d
e
r
e
d
a
l
o
n
g
-
t
e
r
m
s
o
lu
t
i
o
n
f
o
r
m
a
in
t
ai
n
in
g
in
f
o
r
m
at
i
o
n
s
y
s
t
em
s
e
cu
r
i
ty
in
t
h
e
f
u
t
u
r
e
[
2
1
]
.
2
.
2
.
P
Q
C
f
ra
m
e
w
o
rk
V
a
r
i
o
u
s
a
p
p
r
o
a
c
h
e
s
h
a
v
e
b
e
e
n
d
e
v
e
l
o
p
e
d
f
o
r
P
Q
C
,
w
h
i
c
h
c
a
n
b
e
b
r
o
a
d
l
y
c
l
a
s
s
i
f
i
e
d
i
n
t
o
f
i
v
e
c
a
t
e
g
o
r
i
e
s
.
F
i
r
s
t
,
h
a
s
h
-
b
a
s
e
d
c
r
y
p
t
o
g
r
a
p
h
y
f
o
c
u
s
e
s
o
n
d
i
g
i
t
a
l
s
i
g
n
a
t
u
r
e
s
s
e
c
u
r
e
d
b
y
h
a
s
h
f
u
n
c
t
i
o
n
s
,
r
e
q
u
i
r
i
n
g
f
e
w
e
r
a
s
s
u
m
p
t
i
o
n
s
c
o
m
p
a
r
e
d
t
o
n
u
m
b
e
r
-
t
h
e
o
r
e
t
i
c
s
c
h
e
m
e
s
s
u
c
h
a
s
R
S
A
a
n
d
d
y
n
am
i
c
s
p
e
c
t
r
u
m
a
c
c
e
s
s
(
D
S
A
)
[
2
2
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
A
co
u
s
tic
a
n
d
vi
b
r
a
tio
n
s
id
e
ch
a
n
n
el
a
n
a
lysi
s
o
n
p
o
s
t
-
q
u
a
n
t
u
m
cryp
to
g
r
a
p
h
y
…
(
A
b
d
u
l H
a
r
is
Mu
h
a
mma
d
)
1243
Se
c
o
n
d
,
c
o
d
e
-
b
a
s
e
d
c
r
y
p
t
o
g
r
ap
h
y
r
e
li
e
s
o
n
th
e
h
a
r
d
n
es
s
o
f
d
e
c
o
d
i
n
g
p
r
o
b
l
em
s
,
s
u
ch
as
s
y
n
d
r
o
m
e
d
e
c
o
d
in
g
an
d
l
e
a
r
n
in
g
p
a
r
ity
w
i
th
n
o
is
e
,
w
it
h
th
e
Mc
E
l
i
ec
e
s
ch
em
e
b
ein
g
a
p
r
o
m
i
n
e
n
t
ex
am
p
l
e
an
d
N
a
t
i
o
n
a
l
I
n
s
t
i
tu
t
e
o
f
S
t
an
d
a
r
d
s
an
d
T
e
c
h
n
o
l
o
g
y
(
N
I
S
T
)
f
in
a
l
is
t
[
2
3
]
-
[
2
5
]
.
T
h
i
r
d
,
m
u
l
t
iv
a
r
i
a
t
e
c
r
y
p
t
o
g
r
a
p
h
y
i
s
b
a
s
e
d
o
n
s
o
lv
i
n
g
s
y
s
tem
s
o
f
m
u
l
ti
v
a
r
i
a
t
e
p
o
ly
n
o
m
i
al
e
q
u
a
t
i
o
n
s
,
w
i
th
s
ch
em
es
s
u
ch
as
u
n
b
al
an
c
e
d
o
i
l
an
d
v
in
eg
a
r
(
UO
V
)
an
d
r
a
i
n
b
o
w
w
i
d
e
ly
u
s
e
d
f
o
r
d
ig
it
a
l
s
ig
n
a
tu
r
es
[
2
6
]
,
[
2
7
]
.
Fo
u
r
th
,
lat
tice
-
b
a
s
ed
cr
y
p
to
g
r
ap
h
y
h
as
b
ec
o
m
e
th
e
m
o
s
t
d
o
m
i
n
an
t
P
QC
ap
p
r
o
ac
h
d
u
e
to
its
s
tr
o
n
g
s
ec
u
r
it
y
f
o
u
n
d
atio
n
s
o
n
p
r
o
b
le
m
s
s
u
c
h
as
s
h
o
r
test
v
ec
to
r
p
r
o
b
lem
(
SVP
)
an
d
r
in
g
lear
n
in
g
w
ith
er
r
o
r
s
(
R
L
W
E
)
,
w
h
ile
al
s
o
en
ab
li
n
g
ad
v
an
ce
d
p
r
i
m
it
iv
e
s
lik
e
h
o
m
o
m
o
r
p
h
ic
e
n
cr
y
p
tio
n
;
ex
a
m
p
le
s
in
cl
u
d
e
Ne
w
Ho
p
e
an
d
b
im
o
d
al
lattice
s
ig
n
a
tu
r
e
s
c
h
e
m
e
(
B
L
I
S
S
)
[
2
8
]
-
[
3
0
]
.
Fin
all
y
,
is
o
g
en
y
-
b
ased
cr
y
p
to
g
r
ap
h
y
u
tili
ze
s
m
ap
p
in
g
s
b
et
w
ee
n
s
u
p
er
s
in
g
u
lar
ellip
tic
c
u
r
v
e
s
,
o
f
f
er
in
g
co
m
p
ac
t
k
e
y
s
ize
s
b
u
t
h
ig
h
co
m
p
u
tatio
n
al
co
m
p
le
x
it
y
,
as
s
ee
n
i
n
s
u
p
er
s
in
g
u
lar
i
s
o
g
e
n
y
Dif
f
ie
–
H
ell
m
a
n
(
SID
H
)
an
d
s
u
p
er
s
i
n
g
u
lar
is
o
g
en
y
k
e
y
en
ca
p
s
u
latio
n
(
SIK
E
)
[
3
1
]
-
[
3
4
]
.
A
s
ill
u
s
tr
ated
i
n
Fi
g
u
r
e
1
,
s
id
e
-
ch
a
n
n
e
l
attac
k
s
ca
n
b
e
ca
teg
o
r
ized
in
to
p
o
w
er
,
ti
m
i
n
g
,
an
d
p
h
y
s
ical
l
ea
k
ag
e
-
b
ased
attac
k
s
,
i
n
clu
d
i
n
g
ac
o
u
s
tic
s
id
e
-
c
h
a
n
n
el
at
tack
s
(
A
S
C
A
s
)
.
U
n
li
k
e
in
v
a
s
i
v
e
m
e
th
o
d
s
,
A
S
C
A
s
e
x
p
lo
it
s
o
u
n
d
e
m
i
s
s
io
n
s
w
it
h
o
u
t
r
eq
u
ir
in
g
p
h
y
s
ical
m
o
d
i
f
ic
atio
n
o
f
t
h
e
tar
g
et
s
y
s
te
m
,
m
a
k
i
n
g
th
e
m
d
i
f
f
ic
u
l
t
to
d
etec
t
[
3
5
]
.
C
o
n
s
eq
u
en
t
l
y
,
cr
y
p
to
g
r
ap
h
ic
i
m
p
le
m
en
ta
t
io
n
s
th
at
ar
e
s
ec
u
r
e
ag
ain
s
t
m
ath
e
m
at
ical
attac
k
s
m
a
y
s
till
le
a
k
s
e
n
s
iti
v
e
i
n
f
o
r
m
at
io
n
th
r
o
u
g
h
ac
o
u
s
tic
ch
an
n
el
s
,
p
o
s
in
g
a
s
ig
n
i
f
ica
n
t r
ea
l
-
w
o
r
ld
th
r
ea
t
[
3
6
]
.
Fig
u
r
e
1
.
T
y
p
es o
f
A
S
C
A
s
[
3
7
]
ASC
As
h
a
v
e
e
m
er
g
ed
as
a
s
i
g
n
i
f
ica
n
t
t
h
r
ea
t
to
in
f
o
r
m
atio
n
s
ec
u
r
it
y
;
h
o
w
e
v
er
,
a
u
n
if
ied
f
r
a
m
e
w
o
r
k
f
o
r
class
i
f
y
in
g
attac
k
m
o
d
aliti
es,
ev
al
u
ati
n
g
m
iti
g
atio
n
s
tr
at
eg
ies,
a
n
d
id
en
ti
f
y
i
n
g
e
m
er
g
i
n
g
v
ec
to
r
s
r
e
m
ai
n
s
lack
i
n
g
[
3
7
]
.
R
ec
en
t
s
tu
d
ie
s
h
a
v
e
ex
p
lo
r
ed
ad
v
an
ce
d
an
al
y
tical
ap
p
r
o
ac
h
es,
in
cl
u
d
in
g
r
ec
o
n
s
tr
u
cti
n
g
d
is
cr
i
m
i
n
ati
v
e
f
ea
t
u
r
es
f
r
o
m
f
ar
-
f
ield
elec
tr
o
m
ag
n
etic
e
m
i
s
s
io
n
s
,
d
e
m
o
n
s
tr
ati
n
g
t
h
at
s
e
n
s
it
iv
e
in
f
o
r
m
a
tio
n
ca
n
b
e
ex
tr
ac
ted
ev
e
n
i
n
n
o
is
y
a
n
d
n
o
n
-
in
v
as
iv
e
s
etti
n
g
s
[
3
8
]
.
I
n
ad
d
itio
n
,
d
ee
p
lea
r
n
in
g
-
b
ased
f
u
s
io
n
s
tr
ateg
ie
s
h
a
v
e
i
m
p
r
o
v
ed
p
r
o
f
ilin
g
attac
k
s
b
y
in
te
g
r
ati
n
g
f
ea
t
u
r
es
f
r
o
m
m
u
l
tip
le
C
N
N
s
,
e
n
h
an
cin
g
r
o
b
u
s
t
n
e
s
s
an
d
g
en
er
aliza
tio
n
[
3
9
]
.
N
ev
er
th
eles
s
,
m
o
s
t
e
x
is
ti
n
g
ap
p
r
o
ac
h
es
r
el
y
o
n
s
i
n
g
le
-
m
o
d
ali
t
y
in
p
u
ts
o
r
o
n
e
-
d
i
m
en
s
io
n
al
r
ep
r
esen
tatio
n
s
,
li
m
iti
n
g
th
eir
ab
ilit
y
to
ca
p
tu
r
e
co
m
p
le
x
m
u
l
ti
m
o
d
al
lea
k
ag
e
p
atter
n
s
.
Dee
p
lear
n
in
g
-
b
ased
s
id
e
-
c
h
an
n
el
a
n
al
y
s
is
h
a
s
g
r
ad
u
all
y
r
ep
lace
d
tr
ad
itio
n
al
s
ig
n
al
p
r
o
ce
s
s
in
g
m
et
h
o
d
s
.
E
v
al
u
atio
n
s
o
n
b
e
n
c
h
m
ar
k
d
ataset
s
s
u
c
h
as
AS
C
AD
h
i
g
h
lig
h
t
th
e
i
m
p
o
r
tan
ce
o
f
C
NN
ar
c
h
itect
u
r
e
d
esig
n
an
d
h
y
p
er
p
ar
a
m
eter
co
n
f
i
g
u
r
atio
n
in
d
eter
m
i
n
i
n
g
attac
k
p
er
f
o
r
m
an
ce
[
4
0
]
,
[
4
1
]
.
T
o
ad
d
r
ess
th
is
,
r
ec
en
t st
u
d
ies
h
a
v
e
p
r
o
p
o
s
ed
a
u
to
m
ated
o
p
ti
m
izatio
n
s
tr
ate
g
i
es,
in
cl
u
d
in
g
m
o
d
el
f
u
s
io
n
a
n
d
ad
ap
tiv
e
lear
n
i
n
g
tech
n
iq
u
es,
to
i
m
p
r
o
v
e
r
o
b
u
s
t
n
es
s
an
d
g
e
n
er
aliza
tio
n
[
4
2
]
,
[
4
3
]
.
E
n
s
e
m
b
le
lear
n
in
g
ap
p
r
o
ac
h
es
f
u
r
t
h
er
en
h
a
n
ce
p
er
f
o
r
m
an
c
e
b
y
lev
er
ag
i
n
g
m
o
d
el
d
iv
er
s
it
y
,
w
h
il
e
s
h
i
f
t
-
i
n
v
ar
ia
n
t
te
m
p
o
r
al
n
et
wo
r
k
s
ad
d
r
ess
m
is
ali
g
n
m
e
n
t
is
s
u
e
s
in
s
id
e
-
c
h
a
n
n
e
l
tr
ac
es
[
4
4
]
,
[
4
5
]
.
Mo
r
e
o
v
er
,
au
to
m
ated
h
y
p
er
p
ar
a
m
eter
o
p
ti
m
izat
io
n
u
s
i
n
g
tec
h
n
iq
u
es
s
u
ch
as
B
a
y
e
s
ia
n
o
p
ti
m
izatio
n
an
d
r
ein
f
o
r
ce
m
e
n
t
lear
n
in
g
h
as b
ee
n
i
n
v
e
s
ti
g
ated
to
r
ed
u
ce
m
a
n
u
al
tu
n
i
n
g
an
d
i
m
p
r
o
v
e
m
o
d
el
s
tab
ilit
y
[
4
6
]
-
[
4
8
]
.
Gen
er
ati
v
e
lear
n
i
n
g
ap
p
r
o
ac
h
es,
s
u
c
h
as
co
n
d
it
io
n
al
g
en
er
a
tiv
e
ad
v
er
s
ar
ial
n
et
w
o
r
k
s
(
cG
A
N
s
)
,
h
a
v
e
also
b
ee
n
ex
p
lo
r
ed
to
r
ed
u
ce
d
ep
en
d
en
c
y
o
n
lar
g
e
p
r
o
f
ili
n
g
d
atase
ts
b
y
s
y
n
th
e
s
izi
n
g
s
id
e
-
ch
a
n
n
el
tr
ac
es.
H
o
w
ev
e
r
,
s
u
ch
g
e
n
e
r
a
t
iv
e
a
p
p
r
o
a
c
h
es
o
f
t
en
i
n
c
u
r
h
ig
h
c
o
m
p
u
t
a
t
i
o
n
a
l
c
o
s
ts
an
d
l
o
n
g
t
r
a
in
in
g
t
im
e
s
d
u
e
t
o
m
o
d
el
c
o
m
p
l
ex
ity
,
w
h
i
ch
p
o
s
es
s
ig
n
i
f
i
c
an
t
ch
a
ll
en
g
e
s
f
o
r
d
e
p
l
o
y
m
en
t
i
n
r
es
o
u
r
c
e
-
c
o
n
s
t
r
a
in
e
d
e
n
v
i
r
o
n
m
en
ts
[
4
9
]
.
Desp
ite
th
ese
ad
v
a
n
ce
s
,
m
o
s
t
d
ee
p
lear
n
in
g
-
b
ased
ap
p
r
o
ac
h
es
s
till
r
el
y
h
ea
v
il
y
o
n
lar
g
e,
h
ig
h
-
q
u
alit
y
d
atasets
,
w
h
ic
h
r
e
m
ain
d
i
f
f
icu
lt to
o
b
tain
in
p
r
ac
tical
s
ce
n
ar
i
o
s
.
3.
M
E
T
H
O
D
T
h
is
s
tu
d
y
i
n
v
esti
g
ate
s
in
f
o
r
m
atio
n
lea
k
ag
e
i
n
P
QC
im
p
le
m
e
n
tat
io
n
s
t
h
r
o
u
g
h
ac
o
u
s
tic
a
n
d
v
ib
r
atio
n
-
b
ased
s
id
e
ch
an
n
els
u
s
i
n
g
an
i
m
a
g
e
-
b
ased
d
ee
p
le
ar
n
in
g
f
r
a
m
e
w
o
r
k
.
A
co
u
s
tic
an
d
v
ib
r
atio
n
s
i
g
n
a
l
s
w
er
e
co
llected
d
u
r
i
n
g
s
ec
r
et
-
d
ep
en
d
en
t
cr
y
p
to
g
r
ap
h
ic
e
x
ec
u
tio
n
s
u
s
i
n
g
n
o
n
-
i
n
v
asi
v
e
ac
q
u
is
i
tio
n
tec
h
n
iq
u
e
s
,
as c
o
m
m
o
n
l
y
ad
o
p
ted
in
r
ec
en
t stu
d
ies
[
5
0
]
,
[
5
1
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
24
,
No
.
4
,
A
u
g
u
s
t
20
26
:
1
241
-
1
2
5
2
1244
T
h
e
d
ataset
co
m
p
r
is
es
f
o
u
r
cl
ass
es
r
ep
r
ese
n
ti
n
g
d
i
f
f
er
en
t
c
r
y
p
to
g
r
ap
h
ic
o
p
er
atio
n
s
,
w
it
h
a
to
tal
o
f
2
0
0
0
s
am
p
le
s
.
T
h
e
o
r
ig
in
al
d
ataset
co
n
tain
s
6
0
0
s
am
p
les,
w
h
ic
h
w
er
e
ex
p
a
n
d
ed
th
r
o
u
g
h
d
ata
au
g
m
en
ta
tio
n
tech
n
iq
u
es,
i
n
cl
u
d
in
g
n
o
is
e
i
n
j
ec
tio
n
,
ti
m
e
s
h
if
t
in
g
,
an
d
f
r
eq
u
en
c
y
m
as
k
i
n
g
,
to
en
h
a
n
ce
r
o
b
u
s
tn
es
s
an
d
g
en
er
ali
za
tio
n
.
T
h
e
d
ataset
w
as
s
p
lit
in
to
tr
ai
n
in
g
,
v
al
id
atio
n
,
an
d
test
i
n
g
s
ets
w
it
h
a
r
atio
o
f
7
0
%:1
0
%:2
0
%.
T
h
e
r
a
w
s
i
g
n
als
w
er
e
tr
an
s
f
o
r
m
ed
in
to
t
i
m
e
–
f
r
eq
u
e
n
c
y
r
ep
r
esen
tatio
n
s
u
s
i
n
g
s
p
ec
tr
o
g
r
a
m
e
n
co
d
in
g
,
w
h
ic
h
ef
f
ec
tiv
e
l
y
p
r
eser
v
es
te
m
p
o
r
al
an
d
s
p
ec
tr
al
c
h
ar
ac
ter
is
tic
s
f
o
r
s
id
e
-
c
h
a
n
n
el
an
al
y
s
is
[
5
2
]
,
[
5
3
]
.
C
NNs
w
er
e
e
m
p
lo
y
ed
f
o
r
lo
ca
l
f
ea
tu
r
e
e
x
t
r
ac
tio
n
,
w
h
ile
ViT
s
w
er
e
u
tili
ze
d
to
ca
p
tu
r
e
g
lo
b
al
d
ep
en
d
en
cies
t
h
r
o
u
g
h
s
el
f
-
atten
tio
n
m
ec
h
an
i
s
m
s
[
5
4
]
-
[
5
6
]
.
Fu
r
th
er
m
o
r
e,
a
m
u
lti
m
o
d
al
f
u
s
io
n
s
tr
ate
g
y
w
a
s
i
m
p
le
m
e
n
ted
b
y
i
n
te
g
r
atin
g
ac
o
u
s
tic
a
n
d
v
ib
r
atio
n
m
o
d
alit
ies to
i
m
p
r
o
v
e
r
o
b
u
s
t
n
es
s
an
d
g
en
er
aliza
tio
n
[
5
7
]
-
[
5
9
]
.
Fo
r
ev
alu
a
tio
n
,
C
NN
w
a
s
u
s
e
d
as
a
b
aseli
n
e
m
o
d
el,
w
h
ile
ViT
s
er
v
ed
as
a
co
m
p
ar
ati
v
e
ar
ch
itect
u
r
e
to
ass
es
s
g
lo
b
al
f
ea
tu
r
e
lear
n
i
n
g
ca
p
ab
ilit
y
.
T
h
r
ee
in
p
u
t
co
n
f
ig
u
r
atio
n
s
(
ac
o
u
s
t
ic,
v
ib
r
ati
o
n
,
an
d
m
u
lt
i
m
o
d
al
f
u
s
io
n
)
w
er
e
s
y
s
te
m
atica
l
l
y
e
v
alu
a
ted
.
T
r
ad
itio
n
al
m
ac
h
i
n
e
lear
n
in
g
m
o
d
els
w
er
e
n
o
t
co
n
s
id
er
ed
,
as
th
is
s
tu
d
y
f
o
c
u
s
e
s
o
n
d
ee
p
lear
n
i
n
g
ap
p
r
o
ac
h
es
f
o
r
m
o
d
eli
n
g
c
o
m
p
le
x
lea
k
ag
e
p
att
er
n
s
.
F
ig
u
r
e
2
illu
s
tr
ates
t
h
e
o
v
er
all
r
esear
ch
f
r
a
m
e
w
o
r
k
,
in
clu
d
i
n
g
d
ata
ac
q
u
is
it
io
n
,
p
r
ep
r
o
ce
s
s
in
g
,
s
p
ec
tr
o
g
r
a
m
tr
an
s
f
o
r
m
atio
n
,
m
u
lti
m
o
d
al
f
u
s
io
n
,
a
n
d
m
o
d
el
ev
alu
at
io
n
.
Fig
u
r
e
2
.
A
co
u
s
tic
a
n
d
v
ib
r
ati
o
n
s
id
e
ch
a
n
n
el
a
n
al
y
s
i
s
r
esea
r
ch
m
et
h
o
d
T
h
e
p
r
o
p
o
s
ed
f
r
a
m
e
w
o
r
k
co
n
s
is
ts
o
f
s
ix
s
ta
g
es
f
o
r
a
n
al
y
z
in
g
s
id
e
-
c
h
a
n
n
el
leak
a
g
e
i
n
P
Q
C
i
m
p
le
m
en
ta
tio
n
s
.
I
n
th
e
f
ir
s
t
s
tag
e,
s
ec
r
et
-
d
ep
en
d
e
n
t
ex
ec
u
ti
o
n
is
m
o
d
eled
,
w
h
er
e
th
e
i
n
te
r
n
al
ex
ec
u
tio
n
p
at
h
o
f
a
cr
y
p
to
g
r
ap
h
ic
al
g
o
r
ith
m
d
ep
en
d
s
o
n
th
e
s
ec
r
et
v
al
u
e
.
T
h
e
leak
a
g
e
s
o
u
r
ce
is
d
ef
i
n
ed
as:
(
)
=
(
(
)
,
)
(
1
)
w
h
er
e
(
)
r
ep
r
esen
ts
th
e
ex
ec
u
tio
n
p
ath
an
d
(
)
d
en
o
tes
ti
m
e
-
v
ar
y
i
n
g
co
m
p
u
tatio
n
a
l
ac
tiv
it
y
.
T
h
is
ac
tiv
it
y
p
r
o
d
u
ce
s
o
b
s
er
v
ab
le
p
h
y
s
ical
leak
ag
e
d
esp
ite
t
h
e
m
ath
e
m
at
i
ca
l secu
r
it
y
o
f
P
QC
.
T
h
e
s
ec
o
n
d
s
ta
g
e
i
n
v
o
l
v
es
n
o
n
-
in
v
asi
v
e
p
h
y
s
ical
lea
k
a
g
e
a
cq
u
is
itio
n
u
s
i
n
g
ac
o
u
s
tic
(
m
i
cr
o
p
h
o
n
e)
an
d
v
ib
r
atio
n
(
ac
ce
ler
o
m
eter
)
s
en
s
o
r
s
.
T
h
e
o
b
s
er
v
ed
s
ig
n
al
i
s
m
o
d
eled
as:
(
)
=
ℎ
(
(
)
)
+
(
)
(
2
)
w
h
er
e
(
)
is
in
ter
n
a
l
ac
tiv
it
y
a
n
d
(
)
is
en
v
ir
o
n
m
en
tal
n
o
is
e.
Sen
s
o
r
s
ar
e
p
lace
d
n
ea
r
th
e
d
ev
ice
w
it
h
o
u
t
h
ar
d
w
ar
e
m
o
d
i
f
icatio
n
.
I
n
th
e
t
h
ir
d
s
ta
g
e,
p
r
ep
r
o
ce
s
s
in
g
is
ap
p
lied
,
in
cl
u
d
in
g
n
o
r
m
aliza
tio
n
,
s
e
g
m
en
tatio
n
,
a
n
d
te
m
p
o
r
al
alig
n
m
e
n
t.
S
ig
n
als
ar
e
r
ec
o
r
d
ed
at
1
6
k
Hz
w
it
h
2
.
5
-
s
ec
o
n
d
d
u
r
atio
n
p
er
s
a
m
p
le.
T
h
e
f
o
u
r
th
s
ta
g
e
tr
an
s
f
o
r
m
s
s
ig
n
al
s
in
to
s
p
ec
tr
o
g
r
a
m
s
u
s
i
n
g
s
h
o
r
t
-
ti
m
e
f
o
u
r
ier
tr
an
s
f
o
r
m
(
ST
F
T
)
:
(
,
)
=
|
(
,
)
|
2
(
3
)
w
it
h
a
w
i
n
d
o
w
s
ize
o
f
1
0
2
4
s
am
p
les
a
n
d
5
0
%
o
v
er
lap
.
Sp
ec
tr
o
g
r
am
s
p
r
eser
v
e
te
m
p
o
r
al
-
s
p
ec
tr
al
ch
ar
ac
ter
is
tic
s
f
o
r
i
m
a
g
e
-
b
ase
d
an
al
y
s
is
.
T
h
e
f
i
f
t
h
s
ta
g
e
p
er
f
o
r
m
s
m
u
lti
m
o
d
al
f
u
s
io
n
at
t
h
e
i
m
ag
e
le
v
el:
∈
ℝ
(
4
)
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
A
co
u
s
tic
a
n
d
vi
b
r
a
tio
n
s
id
e
ch
a
n
n
el
a
n
a
lysi
s
o
n
p
o
s
t
-
q
u
a
n
t
u
m
cryp
to
g
r
a
p
h
y
…
(
A
b
d
u
l H
a
r
is
Mu
h
a
mma
d
)
1245
C
o
m
b
i
n
in
g
ac
o
u
s
tic
an
d
v
ib
r
atio
n
i
n
f
o
r
m
atio
n
to
ca
p
tu
r
e
cr
o
s
s
-
m
o
d
al
co
r
r
elatio
n
s
.
Fin
all
y
,
d
ee
p
lear
n
in
g
m
o
d
el
s
(
C
NN
a
n
d
Vi
T
)
ar
e
u
s
e
d
f
o
r
class
i
f
icatio
n
.
T
h
e
tr
ain
in
g
o
b
j
ec
tiv
e
is
d
ef
in
ed
as:
=
−
∑
l
og
̂
(
5
)
w
h
er
e
is
t
h
e
tr
u
e
lab
el
a
n
d
̂
is
t
h
e
p
r
ed
ictio
n
.
E
ar
l
y
s
to
p
p
in
g
an
d
lear
n
i
n
g
r
ate
s
c
h
ed
u
li
n
g
ar
e
ap
p
lied
to
en
s
u
r
e
s
tab
le
tr
ain
i
n
g
.
T
h
is
f
r
a
m
e
w
o
r
k
d
e
m
o
n
s
tr
ates
th
at
s
en
s
iti
v
e
in
f
o
r
m
a
tio
n
ca
n
b
e
in
f
er
r
ed
f
r
o
m
n
o
n
-
in
v
as
i
v
e
leak
a
g
e
in
P
QC
i
m
p
le
m
e
n
tatio
n
s
.
A
lt
h
o
u
g
h
t
h
e
d
ataset
is
li
m
ited
an
d
p
ar
tiall
y
au
g
m
en
ted
,
th
is
s
tu
d
y
f
o
cu
s
es
o
n
co
m
p
ar
ati
v
e
a
n
al
y
s
i
s
ac
r
o
s
s
m
o
d
ali
ties
a
n
d
ar
ch
itect
u
r
es
u
n
d
er
co
n
tr
o
lled
co
n
d
itio
n
s
.
T
h
i
s
f
o
r
m
u
la
tio
n
en
s
u
r
es
r
ep
r
o
d
u
cib
ilit
y
an
d
p
r
o
v
id
es
a
clea
r
m
ap
p
in
g
b
et
w
e
en
p
h
y
s
ical
lea
k
ag
e
m
o
d
eli
n
g
an
d
d
ee
p
lear
n
i
n
g
-
b
ased
in
f
er
e
n
ce
.
4.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
is
s
ec
tio
n
p
r
esen
t
s
t
h
e
e
x
p
er
i
m
e
n
tal
r
es
u
lt
s
a
n
d
d
is
cu
s
s
io
n
o
f
t
h
e
p
r
o
p
o
s
ed
im
ag
e
-
b
ased
m
u
lti
m
o
d
al
s
id
e
-
c
h
a
n
n
el
a
n
al
y
s
i
s
f
o
r
P
QC
.
T
h
e
ev
al
u
atio
n
co
m
p
ar
es
t
h
r
ee
s
ce
n
ar
io
s
ac
o
u
s
tic,
v
ib
r
atio
n
,
a
n
d
ac
o
u
s
tic
–
v
ib
r
atio
n
f
u
s
io
n
u
s
i
n
g
C
NNs
an
d
ViT
s
.
T
h
e
ex
p
er
i
m
en
ts
ai
m
to
ass
es
s
:
(
i)
th
e
ca
p
ab
ilit
y
o
f
ea
ch
m
o
d
ali
t
y
to
r
ep
r
esen
t
in
f
o
r
m
a
tio
n
leak
a
g
e,
(
ii)
t
h
e
ef
f
ec
ti
v
e
n
es
s
o
f
m
u
l
ti
m
o
d
al
f
u
s
io
n
in
im
p
r
o
v
in
g
in
f
er
en
c
e
p
er
f
o
r
m
a
n
ce
,
a
n
d
(
iii)
th
e
i
m
p
ac
t
o
f
d
ata
au
g
m
en
ta
tio
n
o
n
m
o
d
el
s
tab
ilit
y
a
n
d
g
e
n
er
ali
za
tio
n
.
R
e
s
u
l
ts
ar
e
p
r
esen
ted
th
r
o
u
g
h
s
p
ec
tr
o
g
r
am
v
i
s
u
aliza
tio
n
s
,
lear
n
i
n
g
cu
r
v
es,
co
n
f
u
s
io
n
m
atr
ice
s
,
an
d
q
u
an
t
itati
v
e
m
e
tr
ics.
T
h
e
d
ataset
w
a
s
co
n
s
tr
u
cted
f
r
o
m
p
h
y
s
ical
leak
a
g
e
s
i
g
n
als
g
e
n
er
ated
d
u
r
in
g
P
QC
e
x
ec
u
t
io
n
,
co
n
s
is
tin
g
o
f
ac
o
u
s
tic
s
ig
n
al
s
(
m
icr
o
p
h
o
n
e)
an
d
v
ib
r
atio
n
s
i
g
n
al
s
(
s
e
n
s
o
r
-
b
ased
)
.
T
o
ad
d
r
ess
li
m
i
ted
p
r
o
f
ilin
g
tr
ac
es,
s
y
n
t
h
etic
d
ata
au
g
m
e
n
tatio
n
w
as
ap
p
lied
,
r
esu
lti
n
g
in
3
0
0
-
5
0
0
s
a
m
p
le
s
p
er
class
.
Si
g
n
als
w
er
e
r
ec
o
r
d
e
d
at
a
s
am
p
li
n
g
r
ate
o
f
1
6
k
Hz
w
i
th
a
d
u
r
atio
n
o
f
2
.
5
s
ec
o
n
d
s
,
th
e
n
tr
an
s
f
o
r
m
ed
in
to
f
ix
ed
-
s
ize
s
p
ec
tr
o
g
r
a
m
s
a
n
d
s
p
lit i
n
to
tr
ain
i
n
g
,
v
alid
atio
n
,
a
n
d
test
i
n
g
s
ets
w
it
h
a
r
atio
o
f
7
0
%
:1
0
%:2
0
%.
Fig
u
r
e
3
s
h
o
w
s
r
ep
r
esen
tati
v
e
s
p
ec
tr
o
g
r
a
m
v
is
u
aliza
tio
n
s
f
o
r
ac
o
u
s
tic,
v
ib
r
atio
n
,
an
d
f
u
s
e
d
m
o
d
ali
ties
ac
r
o
s
s
d
if
f
er
en
t
s
ec
r
et
class
es,
s
er
v
in
g
as
i
n
p
u
t
s
f
o
r
th
e
p
r
o
p
o
s
ed
d
ee
p
lear
n
in
g
m
o
d
el
s
.
Fig
u
r
e
s
3
(
a)
an
d
(
b
)
s
h
o
w
th
e
s
p
ec
tr
o
g
r
a
m
r
ep
r
esen
tatio
n
o
f
th
e
ac
o
u
s
tic
s
id
e
ch
an
n
el
s
i
g
n
al
co
r
r
esp
o
n
d
in
g
to
t
w
o
d
if
f
er
en
t
ex
ec
u
tio
n
s
th
at
d
ep
en
d
o
n
th
e
s
ec
r
et.
T
h
e
a
co
u
s
tic
s
p
ec
tr
o
g
r
a
m
s
h
o
w
s
p
r
o
m
i
n
e
n
t
h
o
r
izo
n
ta
l
f
r
eq
u
en
c
y
b
a
n
d
s
an
d
e
n
er
g
y
co
n
ce
n
tr
atio
n
p
atter
n
s
th
at
v
a
r
y
ac
co
r
d
in
g
to
t
h
e
s
ec
r
et
v
al
u
e.
T
h
is
d
if
f
er
en
ce
in
d
icate
s
th
at
ac
o
u
s
tic
e
m
is
s
i
o
n
s
ca
p
t
u
r
e
ex
ec
u
tio
n
-
d
ep
en
d
en
t
c
h
ar
ac
ter
is
tic
s
o
f
P
QC
ca
lcu
latio
n
s
,
m
a
k
in
g
th
e
m
a
s
tr
o
n
g
s
o
u
r
ce
o
f
s
id
e
-
c
h
an
n
el
lea
k
ag
e
.
(
a)
(
b
)
Fig
u
r
e
3
.
T
h
e
s
p
ec
tr
o
g
r
am
r
ep
r
esen
tatio
n
o
f
ac
o
u
s
tic
s
id
e
-
ch
an
n
el
lea
k
a
g
e
:
(
a)
s
ec
r
et
0
an
d
(
b
)
s
ec
r
et
1
Fig
u
r
e
s
4
(
a)
an
d
(
b
)
illu
s
tr
at
e
v
ib
r
atio
n
-
b
ased
s
p
ec
tr
o
g
r
a
m
s
d
er
i
v
ed
f
r
o
m
m
ec
h
an
ical
r
esp
o
n
s
es
d
u
r
in
g
cr
y
p
to
g
r
ap
h
ic
e
x
ec
u
t
i
o
n
.
C
o
m
p
ar
ed
to
ac
o
u
s
tic
s
ig
n
als,
v
ib
r
atio
n
s
p
ec
tr
o
g
r
a
m
s
ex
h
ib
it
a
s
m
o
o
th
er
,
m
o
r
e
d
i
s
p
er
s
ed
en
er
g
y
d
is
tr
i
b
u
tio
n
,
a
n
d
alth
o
u
g
h
lea
k
ag
e
p
atter
n
s
ar
e
les
s
v
is
u
all
y
ap
p
ar
en
t,
d
if
f
er
e
n
t
s
tr
u
ct
u
r
al
v
ar
iatio
n
s
ca
n
s
till
b
e
o
b
s
er
v
ed
ac
r
o
s
s
s
ec
r
et
c
lass
es,
in
d
icat
in
g
t
h
at
v
ib
r
ati
o
n
s
i
g
n
als
p
r
o
v
id
e
co
m
p
le
m
e
n
tar
y
b
u
t
w
ea
k
er
s
i
d
e
-
ch
a
n
n
e
l in
f
o
r
m
at
io
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
24
,
No
.
4
,
A
u
g
u
s
t
20
26
:
1
241
-
1
2
5
2
1246
(
a)
(
b
)
F
ig
u
r
e
4
.
T
h
e
s
p
e
ct
r
o
g
r
am
r
e
p
r
e
s
en
t
at
i
o
n
o
f
v
i
b
r
at
i
o
n
-
b
a
s
e
d
s
id
e
-
ch
an
n
e
l
l
e
ak
ag
e
:
(
a
)
s
e
c
r
e
t
0
a
n
d
(
b
)
s
e
c
r
et
1
Fig
u
r
e
s
5
(
a
)
an
d
(
b
)
s
h
o
w
co
m
b
in
ed
s
p
ec
tr
o
g
r
a
m
s
.
T
h
ese
i
m
ag
e
s
ar
e
cr
ea
ted
b
y
co
m
b
i
n
i
n
g
ac
o
u
s
tic
an
d
v
ib
r
atio
n
d
ata
in
to
a
s
i
n
g
le
m
u
lt
i
-
c
h
a
n
n
e
l
f
o
r
m
at.
T
h
is
co
m
b
in
ed
i
m
a
g
e
h
i
g
h
l
i
g
h
t
s
t
h
e
s
h
ar
ed
a
n
d
d
if
f
er
e
n
t
f
ea
t
u
r
es
o
f
t
h
e
t
w
o
t
y
p
e
s
o
f
p
h
y
s
ical
lea
k
a
g
e.
T
h
is
in
teg
r
ated
ap
p
r
o
ac
h
h
elp
s
cl
ar
if
y
th
e
p
atter
n
s
of
s
ec
r
et
-
d
ep
en
d
en
t e
x
ec
u
tio
n
,
p
r
o
v
id
in
g
m
o
r
e
in
p
u
t d
ata
f
o
r
d
ee
p
lear
n
in
g
m
o
d
els.
(
a)
(
b
)
Fig
u
r
e
5
.
T
h
e
m
u
lti
m
o
d
al
f
u
s
i
o
n
s
p
ec
tr
o
g
r
a
m
c
o
m
b
i
n
i
n
g
a
c
o
u
s
tic
a
n
d
v
ib
r
atio
n
i
n
f
o
r
m
ati
o
n
:
(
a)
s
ec
r
et
0
an
d
(
b
)
s
ec
r
et
1
T
h
is
s
p
ec
tr
o
g
r
a
m
an
d
f
u
s
io
n
i
m
a
g
e
ar
e
d
ir
ec
tl
y
r
elate
d
to
th
e
i
m
ag
e
p
r
o
ce
s
s
i
n
g
an
d
m
u
lti
-
m
o
d
al
f
u
s
io
n
s
ta
g
es
il
lu
s
tr
ated
in
t
h
e
s
y
s
te
m
ar
ch
itect
u
r
e
p
r
o
p
o
s
ed
in
Fi
g
u
r
e
2
,
w
h
ic
h
s
er
v
es
a
s
f
u
n
d
a
m
en
ta
l
in
p
u
t
f
o
r
a
C
NN
a
n
d
ViT
-
b
ased
s
i
d
e
ch
an
n
el
a
n
al
y
s
is
.
Fi
g
u
r
e
6
illu
s
tr
ate
s
t
h
e
tr
ain
in
g
a
n
d
v
alid
atio
n
lear
n
i
n
g
cu
r
v
e
s
o
f
C
N
N
an
d
ViT
s
m
o
d
els ac
r
o
s
s
ac
o
u
s
t
ic,
v
ib
r
atio
n
,
an
d
m
u
lti
m
o
d
al
f
u
s
io
n
s
ce
n
ar
io
s
.
Fig
u
r
e
6
.
L
ea
r
n
i
n
g
c
u
r
v
e
s
f
o
r
C
NN,
ViT
,
an
d
m
u
l
ti
-
m
o
d
al
f
u
s
io
n
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
A
co
u
s
tic
a
n
d
vi
b
r
a
tio
n
s
id
e
ch
a
n
n
el
a
n
a
lysi
s
o
n
p
o
s
t
-
q
u
a
n
t
u
m
cryp
to
g
r
a
p
h
y
…
(
A
b
d
u
l H
a
r
is
Mu
h
a
mma
d
)
1247
Fig
u
r
e
6
p
r
esen
ts
t
h
e
tr
ain
i
n
g
an
d
v
al
id
atio
n
lo
s
s
c
u
r
v
e
s
o
f
C
NN
an
d
ViT
m
o
d
els
a
cr
o
s
s
th
r
ee
s
ce
n
ar
io
s
:
ac
o
u
s
tic,
v
ib
r
atio
n
,
an
d
m
u
lt
i
m
o
d
al
f
u
s
io
n
.
C
NN
m
o
d
els
s
h
o
w
r
ap
id
co
n
v
er
g
e
n
ce
w
ith
n
ea
r
-
ze
r
o
tr
ain
i
n
g
lo
s
s
w
it
h
in
a
f
e
w
ep
o
ch
s
ac
r
o
s
s
all
m
o
d
alit
ies,
in
d
i
ca
tin
g
s
tr
o
n
g
ca
p
ab
ilit
y
i
n
ca
p
tu
r
in
g
lo
ca
l
leak
a
g
e
p
atter
n
s
.
Ho
w
e
v
er
,
th
is
b
eh
a
v
io
r
also
s
u
g
g
es
ts
p
o
ten
tial
o
v
er
f
itti
n
g
,
p
ar
ticu
lar
l
y
i
n
th
e
ac
o
u
s
tic
m
o
d
alit
y
w
h
er
e
s
tr
u
ct
u
r
ed
leak
a
g
e
is
ea
s
ier
to
lear
n
.
T
h
e
v
ib
r
atio
n
m
o
d
alit
y
e
x
h
ib
it
s
s
li
g
h
t
l
y
h
i
g
h
er
i
n
s
tab
ilit
y
,
r
ef
lecti
n
g
its
lo
w
er
s
ig
n
al
-
to
-
n
o
is
e
r
atio
a
n
d
m
o
r
e
co
m
p
le
x
lea
k
ag
e
c
h
ar
ac
ter
is
t
ics.
I
n
t
h
e
f
u
s
io
n
s
ce
n
ar
io
,
C
NN
co
n
v
er
g
e
n
ce
r
e
m
ain
s
f
ast,
b
u
t
th
e
lear
n
i
n
g
p
atter
n
in
d
icate
s
li
m
ited
e
x
p
lo
itat
io
n
o
f
cr
o
s
s
-
m
o
d
al
d
ep
en
d
en
cies.
I
n
co
n
tr
ast,
ViT
m
o
d
els
d
e
m
o
n
s
tr
ate
m
o
r
e
g
r
ad
u
al
an
d
s
t
ab
le
co
n
v
er
g
en
ce
w
i
th
clo
s
el
y
al
ig
n
ed
tr
ain
i
n
g
a
n
d
v
alid
atio
n
lo
s
s
es
,
in
d
icatin
g
b
etter
g
e
n
er
aliza
t
io
n
.
T
h
is
ad
v
an
ta
g
e
is
e
s
p
ec
iall
y
ev
id
en
t
i
n
th
e
v
ib
r
atio
n
m
o
d
ali
t
y
,
w
h
er
e
Vi
T
ef
f
ec
tiv
e
l
y
ca
p
t
u
r
es
d
is
p
er
s
ed
an
d
les
s
s
tr
u
ctu
r
ed
lea
k
a
g
e
p
atter
n
s
.
I
n
t
h
e
m
u
lti
m
o
d
al
f
u
s
io
n
s
etti
n
g
,
Vi
T
ac
h
iev
es
th
e
m
o
s
t
s
tab
le
le
ar
n
in
g
b
eh
a
v
io
r
,
s
u
g
g
e
s
ti
n
g
i
ts
ef
f
ec
ti
v
en
e
s
s
i
n
in
te
g
r
atin
g
co
m
p
le
m
en
tar
y
in
f
o
r
m
at
io
n
ac
r
o
s
s
m
o
d
alities
.
Fi
g
u
r
e
7
p
r
esen
ts
th
e
co
n
f
u
s
io
n
m
atr
ices
o
f
C
NN
-
b
ased
class
if
icatio
n
r
esu
lt
s
f
o
r
ac
o
u
s
tic
(
Fig
u
r
e
7
(
a)
)
,
v
ib
r
atio
n
(
Fig
u
r
e
7
(
b
)
)
,
an
d
m
u
lti
m
o
d
al
f
u
s
io
n
s
id
e
-
ch
an
n
el
i
n
p
u
t
s
(
Fig
u
r
e
7
(
c)
)
.
(
a)
(
b
)
(
c)
Fig
u
r
e
7
.
C
o
n
f
u
s
io
n
m
atr
ices
o
f
C
NN
-
b
ased
c
las
s
if
icatio
n
r
esu
lt
s
:
(
a)
a
co
u
s
tic,
(
b
)
v
ib
r
atio
n
,
an
d
(
c)
m
u
lti
m
o
d
al
f
u
s
io
n
i
n
p
u
ts
Fig
u
r
e
7
s
h
o
w
s
th
e
co
n
f
u
s
i
o
n
m
atr
ices
o
f
C
NN
-
b
ased
m
o
d
el
s
ac
r
o
s
s
ac
o
u
s
tic,
v
ib
r
atio
n
,
an
d
m
u
lti
m
o
d
al
f
u
s
io
n
s
ce
n
ar
io
s
.
A
ll
m
o
d
el
s
ac
h
ie
v
e
p
er
f
ec
t
class
i
f
icatio
n
ac
cu
r
ac
y
,
w
it
h
n
o
m
i
s
clas
s
if
icatio
n
o
b
s
er
v
ed
.
T
h
is
in
d
icate
s
t
h
at
b
o
th
ac
o
u
s
tic
a
n
d
v
ib
r
atio
n
s
p
ec
tr
o
g
r
a
m
s
co
n
tain
s
tr
o
n
g
d
is
cr
i
m
i
n
ati
v
e
leak
a
g
e
p
atter
n
s
d
u
r
i
n
g
P
QC
e
x
ec
u
t
io
n
.
T
h
e
ac
o
u
s
tic
m
o
d
alit
y
d
e
m
o
n
s
tr
ates
h
i
g
h
l
y
s
tr
u
ct
u
r
ed
leak
a
g
e,
en
ab
lin
g
ef
f
ec
ti
v
e
ex
tr
ac
ti
o
n
o
f
lo
c
al
f
ea
t
u
r
es.
Si
m
ilar
l
y
,
d
esp
ite
l
o
w
er
s
i
g
n
al
-
to
-
n
o
is
e
c
h
ar
ac
te
r
is
tics
,
v
ib
r
atio
n
s
ig
n
al
s
s
ti
ll
p
r
o
v
id
e
s
u
f
f
icien
t
in
f
o
r
m
atio
n
f
o
r
ac
cu
r
ate
class
if
icatio
n
.
I
n
th
e
m
u
l
ti
m
o
d
al
f
u
s
io
n
s
ce
n
ar
io
,
th
e
C
NN
m
o
d
el
m
ai
n
tai
n
s
p
er
f
ec
t
p
er
f
o
r
m
a
n
ce
.
H
o
w
ev
e
r
,
th
e
c
o
n
s
is
t
e
n
t
1
0
0
%
a
c
cu
r
a
cy
ac
r
o
s
s
a
ll
m
o
d
a
li
t
i
es
s
u
g
g
es
ts
th
a
t
th
e
d
a
ta
s
et
m
ay
b
e
r
e
l
a
t
iv
ely
s
im
p
l
e
o
r
th
a
t
th
e
m
o
d
e
l
m
ay
h
av
e
o
v
e
r
f
i
tt
e
d
.
C
o
n
s
e
q
u
e
n
t
ly
,
th
e
a
d
v
a
n
t
ag
e
o
f
m
u
l
t
im
o
d
a
l
f
u
s
i
o
n
o
v
e
r
s
in
g
l
e
-
m
o
d
a
l
ity
i
n
p
u
ts
c
an
n
o
t
b
e
c
o
n
c
lu
s
iv
e
ly
d
et
e
r
m
in
e
d
b
as
e
d
s
o
l
e
ly
o
n
a
c
cu
r
a
cy
.
T
h
e
s
e
r
e
s
u
l
ts
c
o
n
f
i
r
m
th
e
e
f
f
e
ct
iv
en
es
s
o
f
C
N
N
in
c
a
p
tu
r
i
n
g
s
i
d
e
-
ch
an
n
e
l
l
e
ak
ag
e
p
a
t
te
r
n
s
,
w
h
il
e
al
s
o
h
i
g
h
l
ig
h
t
in
g
th
e
n
ee
d
f
o
r
f
u
r
th
e
r
e
v
a
lu
at
i
o
n
u
s
in
g
m
o
r
e
c
o
m
p
l
ex
d
a
t
as
e
ts
,
n
o
i
s
e
c
o
n
d
it
i
o
n
s
,
o
r
c
r
o
s
s
-
v
a
li
d
a
t
i
o
n
s
t
r
a
t
eg
ie
s
t
o
as
s
ess
g
en
e
r
al
i
z
at
i
o
n
p
e
r
f
o
r
m
an
c
e
.
Fig
u
r
e
8
p
r
es
en
ts
t
h
e
c
o
n
f
u
s
i
o
n
m
at
r
i
ce
s
o
f
Vi
T
-
b
a
s
e
d
m
o
d
el
s
f
o
r
c
o
m
p
a
r
is
o
n
.
I
n
co
n
tr
ast
to
C
NN
r
es
u
lt
s
,
th
e
ac
o
u
s
tic
-
b
ased
ViT
m
o
d
el
i
n
Fi
g
u
r
e
8
(
a)
s
h
o
w
s
m
i
n
o
r
m
is
c
lass
if
ica
tio
n
,
w
it
h
o
n
e
s
a
m
p
le
in
co
r
r
ec
tl
y
cla
s
s
i
f
ied
.
Alth
o
u
g
h
o
v
er
all
p
e
r
f
o
r
m
an
ce
r
e
m
ain
s
h
i
g
h
,
th
i
s
in
d
icate
s
t
h
at
ViT
ca
p
tu
r
es
m
o
r
e
d
is
tr
ib
u
ted
an
d
g
lo
b
al
leak
ag
e
r
ep
r
ese
n
tatio
n
s
t
h
r
o
u
g
h
s
elf
-
atte
n
tio
n
,
r
ath
er
th
an
r
el
y
i
n
g
o
n
d
o
m
in
a
n
t lo
ca
l
f
ea
tu
r
e
s
.
Fo
r
th
e
v
ib
r
atio
n
m
o
d
ali
t
y
(
Fi
g
u
r
e
8
(
b
)
)
,
Vi
T
also
ac
h
iev
es
h
ig
h
p
er
f
o
r
m
a
n
c
e
w
it
h
m
in
i
m
al
er
r
o
r
s
.
C
o
m
b
i
n
ed
w
it
h
th
e
lear
n
i
n
g
c
u
r
v
e
an
al
y
s
is
,
th
i
s
s
u
g
g
e
s
ts
i
m
p
r
o
v
ed
g
en
er
aliza
tio
n
ca
p
ab
ilit
y
,
p
ar
ticu
lar
l
y
f
o
r
w
ea
k
er
an
d
m
o
r
e
s
p
atiall
y
d
is
tr
ib
u
ted
leak
a
g
e
p
atter
n
s
.
T
h
e
ab
ilit
y
o
f
ViT
to
m
o
d
el
lo
n
g
-
r
an
g
e
d
ep
en
d
e
n
cies
en
ab
les
m
o
r
e
e
f
f
ec
t
iv
e
e
x
tr
ac
t
io
n
o
f
s
u
b
tle
f
ea
t
u
r
es c
o
m
p
ar
e
d
to
C
NN.
Ho
w
e
v
er
,
in
t
h
e
m
u
lti
m
o
d
al
f
u
s
io
n
s
ce
n
ar
io
(
Fig
u
r
e
8
(
c)
)
,
a
p
er
f
o
r
m
a
n
ce
d
ec
r
ea
s
e
is
o
b
s
er
v
ed
co
m
p
ar
ed
to
s
in
g
le
-
m
o
d
alit
y
i
n
p
u
t
s
.
T
h
is
in
d
icate
s
t
h
at
th
e
f
u
s
io
n
s
tr
ateg
y
u
s
ed
in
th
i
s
s
t
u
d
y
d
o
es
n
o
t
f
u
ll
y
ex
p
lo
it
cr
o
s
s
-
m
o
d
al
r
elatio
n
s
h
ip
s
w
it
h
i
n
th
e
ViT
ar
ch
itectu
r
e.
T
h
e
r
esu
lt
s
u
g
g
e
s
ts
t
h
at
m
o
r
e
ad
v
an
ce
d
f
u
s
io
n
m
ec
h
a
n
i
s
m
s
,
lar
g
er
d
ataset
s
,
o
r
b
etter
f
ea
tu
r
e
alig
n
m
en
t a
r
e
r
eq
u
ir
ed
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
24
,
No
.
4
,
A
u
g
u
s
t
20
26
:
1
241
-
1
2
5
2
1248
(
a)
(
b
)
(
c)
Fig
u
r
e
8
.
C
o
n
f
u
s
io
n
m
atr
ices
o
f
ViT
-
b
ased
class
i
f
icatio
n
r
es
u
lts
:
(
a)
ac
o
u
s
tic,
(
b
)
v
ib
r
atio
n
,
an
d
(
c)
m
u
lti
m
o
d
al
f
u
s
io
n
in
p
u
ts
Ov
er
all,
ViT
d
em
o
n
s
tr
ate
s
s
tr
o
n
g
g
en
er
aliza
t
io
n
f
o
r
s
in
g
le
-
m
o
d
ali
t
y
i
n
p
u
ts
,
b
u
t
it
s
ef
f
ec
t
iv
en
e
s
s
i
n
m
u
lti
m
o
d
al
s
e
tti
n
g
s
d
ep
en
d
s
o
n
th
e
d
esig
n
o
f
t
h
e
f
u
s
io
n
s
tr
ate
g
y
a
n
d
d
ata
s
ca
le.
T
ab
le
1
p
r
esen
ts
a
q
u
an
tita
tiv
e
co
m
p
ar
i
s
o
n
o
f
p
er
f
o
r
m
an
ce
i
n
ter
m
s
o
f
ac
c
u
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
-
s
co
r
e
ac
r
o
s
s
all
m
o
d
el
s
an
d
m
o
d
alit
ies.
T
ab
le
1
.
C
lass
if
icatio
n
p
er
f
o
r
m
an
ce
o
f
C
N
N
an
d
ViT
m
o
d
e
ls
f
o
r
d
if
f
er
en
t
s
id
e
-
c
h
an
n
el
m
o
d
alities
M
o
d
e
l
s
A
c
c
u
r
a
c
y
P
r
e
c
i
si
o
n
R
e
c
a
l
l
F1
-
s
c
o
r
e
c
n
n
_
a
c
o
u
st
i
c
1
.
0
1
.
0
1
.
0
1
.
0
c
n
n
_
v
i
b
r
a
t
i
o
n
1
.
0
1
.
0
1
.
0
1
.
0
c
n
n
_
f
u
si
o
n
1
.
0
1
.
0
1
.
0
1
.
0
v
i
t
_
a
c
o
u
s
t
i
c
0
.
9
8
7
5
0
.
9
8
7
8
0
4
8
7
8
0
4
8
7
8
0
5
0
.
9
8
7
5
0
.
9
8
7
4
9
8
0
4
6
5
6
9
7
7
6
5
v
i
t
_
v
i
b
r
a
t
i
o
n
0
.
9
8
7
5
0
.
9
8
7
8
0
4
8
7
8
0
4
8
7
8
0
5
0
.
9
8
7
5
0
.
9
8
7
4
9
8
0
4
6
5
6
9
7
7
6
5
v
i
t
_
f
u
si
o
n
0
.
5
0
.
2
5
0
.
5
0
.
3
3
3
3
3
3
3
3
3
3
3
3
3
3
3
3
Fro
m
T
ab
le
1
,
class
if
icatio
n
p
er
f
o
r
m
a
n
ce
is
i
n
f
l
u
e
n
ce
d
b
y
b
o
th
m
o
d
alit
y
a
n
d
m
o
d
el
ar
ch
itect
u
r
e.
C
NN
m
o
d
els
ac
h
iev
e
n
ea
r
-
p
er
f
ec
t
r
esu
lt
s
ac
r
o
s
s
all
m
o
d
alities
(
all
m
etr
ic
s
=
1
.
0
)
,
in
d
icatin
g
a
s
tr
o
n
g
ca
p
ab
ilit
y
to
ca
p
tu
r
e
s
tr
u
ctu
r
e
d
leak
ag
e
p
atter
n
s
f
r
o
m
s
p
ec
t
r
o
g
r
a
m
s
.
I
n
co
n
tr
ast,
ViT
m
o
d
els
s
h
o
w
s
li
g
h
t
l
y
lo
w
er
p
er
f
o
r
m
a
n
ce
f
o
r
s
i
n
g
l
e
m
o
d
alities
,
w
i
th
9
8
.
7
5
%
ac
cu
r
ac
y
f
o
r
b
o
th
ac
o
u
s
tic
a
n
d
v
ib
r
atio
n
i
n
p
u
t
s
,
s
u
g
g
e
s
ti
n
g
th
a
t
t
h
eir
r
elian
ce
o
n
g
lo
b
al
r
ep
r
esen
tat
io
n
s
m
a
y
b
e
less
e
f
f
ec
tiv
e
th
a
n
C
NN
s
i
n
ex
p
lo
iti
n
g
h
ig
h
l
y
lo
ca
lized
leak
ag
e
f
ea
tu
r
e
s
.
A
s
i
g
n
if
ican
t
p
er
f
o
r
m
a
n
ce
d
r
o
p
is
o
b
s
er
v
ed
in
th
e
m
u
lt
i
m
o
d
al
Vi
T
c
o
n
f
ig
u
r
atio
n
,
w
h
er
e
ac
cu
r
ac
y
d
ec
r
ea
s
es
to
5
0
%
an
d
th
e
F1
-
s
co
r
e
to
0
.
3
3
,
in
d
icatin
g
th
at
t
h
e
s
i
m
p
le
f
u
s
io
n
s
tr
ateg
y
is
n
o
t
w
ell
ali
g
n
ed
w
it
h
tr
an
s
f
o
r
m
er
-
b
a
s
e
d
ar
ch
itect
u
r
es
an
d
h
ig
h
li
g
h
ti
n
g
th
e
m
o
d
el
’
s
s
en
s
iti
v
it
y
to
f
ea
t
u
r
e
alig
n
m
en
t
an
d
d
ata
s
ca
le.
T
h
ese
f
i
n
d
in
g
s
s
h
o
u
ld
b
e
in
t
er
p
r
eted
w
i
th
i
n
t
h
e
co
n
tex
t
o
f
co
n
tr
o
lled
lab
o
r
ato
r
y
co
n
d
it
io
n
s
r
at
h
er
th
a
n
as
g
u
ar
a
n
tees
o
f
r
ea
l
-
w
o
r
ld
p
er
f
o
r
m
a
n
ce
,
as
th
e
p
r
ac
tical
f
ea
s
ib
ilit
y
o
f
ex
p
lo
iti
n
g
lea
k
a
g
e
also
d
ep
en
d
s
o
n
f
ac
to
r
s
s
u
ch
a
s
en
v
ir
o
n
m
en
tal
n
o
is
e,
d
ev
ice
v
ar
iab
ilit
y
,
a
n
d
im
p
le
m
e
n
tat
io
n
d
if
f
er
en
ce
s
.
C
o
n
s
is
te
n
t
w
it
h
p
r
io
r
s
tu
d
ie
s
[
1
6
]
-
[
1
8
]
,
th
is
w
o
r
k
co
n
f
ir
m
s
t
h
e
p
r
ese
n
ce
o
f
p
h
y
s
ical
leak
ag
e
in
cr
y
p
to
g
r
ap
h
ic
s
y
s
te
m
s
.
Ho
w
ev
er
,
u
n
lik
e
p
r
ev
io
u
s
s
in
g
le
-
m
o
d
alit
y
ap
p
r
o
ac
h
es,
th
i
s
s
tu
d
y
i
n
tr
o
d
u
ce
s
a
m
u
lti
m
o
d
al
ac
o
u
s
tic
–
v
ib
r
atio
n
f
r
a
m
e
w
o
r
k
u
s
in
g
i
m
a
g
e
-
b
a
s
e
d
d
ee
p
lear
n
in
g
to
ca
p
tu
r
e
m
o
r
e
co
m
p
le
x
leak
a
g
e
p
atter
n
s
.
Fro
m
a
s
ec
u
r
it
y
p
er
s
p
ec
tiv
e,
th
e
f
i
n
d
i
n
g
s
h
ig
h
li
g
h
t
th
e
n
ee
d
f
o
r
co
u
n
ter
m
ea
s
u
r
es
s
u
ch
a
s
ac
o
u
s
tic
s
h
ield
i
n
g
,
n
o
is
e
i
n
j
ec
tio
n
,
r
an
d
o
m
ized
ex
ec
u
tio
n
,
an
d
h
ar
d
war
e
-
lev
el
p
r
o
tectio
n
.
Desp
ite
p
r
o
m
is
i
n
g
r
es
u
lts
,
li
m
itatio
n
s
r
e
m
ai
n
,
in
cl
u
d
i
n
g
li
m
ited
d
ataset
s
ize,
r
elian
ce
o
n
s
y
n
th
et
ic
au
g
m
e
n
tatio
n
,
co
n
tr
o
lled
ex
p
e
r
i
m
en
tal
c
o
n
d
itio
n
s
,
an
d
a
s
i
m
p
le
f
u
s
io
n
s
tr
ateg
y
.
F
u
t
u
r
e
w
o
r
k
s
h
o
u
ld
f
o
c
u
s
o
n
lar
g
er
d
atasets
,
r
ea
l
-
w
o
r
ld
ac
q
u
is
i
tio
n
s
etti
n
g
s
,
an
d
ad
v
a
n
ce
d
f
u
s
io
n
m
ec
h
an
i
s
m
s
to
i
m
p
r
o
v
e
r
o
b
u
s
tn
e
s
s
a
n
d
g
en
er
aliza
tio
n
.
5.
CO
NCLU
SI
O
N
T
h
is
s
tu
d
y
d
e
m
o
n
s
tr
ate
s
th
at
P
QC
im
p
le
m
e
n
tatio
n
s
r
e
m
ai
n
s
u
s
ce
p
tib
le
to
n
o
n
-
in
v
asi
v
e
p
h
y
s
ica
l
s
id
e
-
c
h
an
n
el
lea
k
ag
e,
d
esp
ite
th
eir
th
eo
r
etica
l
r
esi
s
tan
ce
to
q
u
an
t
u
m
-
b
ased
cr
y
p
ta
n
al
y
s
i
s
.
T
h
e
ex
p
er
im
e
n
tal
r
esu
lt
s
in
d
icate
th
a
t
ac
o
u
s
tic
e
m
is
s
io
n
s
g
e
n
er
all
y
e
x
h
ib
it
s
tr
o
n
g
er
an
d
m
o
r
e
s
tr
u
ct
u
r
ed
leak
ag
e
c
h
ar
ac
ter
is
tic
s
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
A
co
u
s
tic
a
n
d
vi
b
r
a
tio
n
s
id
e
ch
a
n
n
el
a
n
a
lysi
s
o
n
p
o
s
t
-
q
u
a
n
t
u
m
cryp
to
g
r
a
p
h
y
…
(
A
b
d
u
l H
a
r
is
Mu
h
a
mma
d
)
1249
th
an
m
ec
h
an
ical
v
ib
r
atio
n
s
,
w
h
ile
th
e
in
teg
r
atio
n
o
f
m
u
lt
i
m
o
d
al
ac
o
u
s
tic
–
v
ib
r
at
io
n
r
ep
r
esen
tatio
n
s
co
n
s
is
ten
tl
y
e
n
h
an
ce
s
lear
n
in
g
s
tab
il
it
y
an
d
cla
s
s
i
f
icat
io
n
p
er
f
o
r
m
an
ce
.
T
h
e
co
m
p
ar
ati
v
e
ev
alu
a
tio
n
o
f
d
ee
p
lear
n
in
g
ar
c
h
itect
u
r
es
f
u
r
th
er
r
ev
ea
ls
t
h
a
t
C
NN
s
ac
h
iev
e
f
a
s
ter
co
n
v
er
g
e
n
ce
b
u
t
ar
e
m
o
r
e
s
en
s
iti
v
e
to
n
o
is
e
an
d
o
v
er
f
itti
n
g
,
w
h
er
ea
s
Vi
T
m
o
d
els
p
r
o
v
id
e
i
m
p
r
o
v
ed
r
o
b
u
s
tn
e
s
s
a
n
d
g
en
er
aliza
t
i
o
n
w
h
e
n
h
a
n
d
lin
g
co
m
p
le
x
an
d
n
o
n
-
li
n
ea
r
leak
a
g
e
p
atter
n
s
.
T
h
ese
f
in
d
i
n
g
s
h
ig
h
li
g
h
t
t
h
at
co
m
b
i
n
i
n
g
ac
o
u
s
tic
a
n
d
v
ib
r
a
tio
n
m
o
d
alitie
s
w
it
h
ap
p
r
o
p
r
i
ate
i
m
a
g
e
-
b
ased
d
ee
p
lear
n
in
g
ar
ch
itec
tu
r
es
co
n
s
tit
u
tes
a
n
e
f
f
ec
t
iv
e
ap
p
r
o
ac
h
f
o
r
s
id
e
-
ch
a
n
n
el
an
al
y
s
is
i
n
p
o
s
t
-
q
u
an
t
u
m
cr
y
p
to
g
r
ap
h
y
.
T
o
th
e
b
est
o
f
o
u
r
k
n
o
w
led
g
e,
th
i
s
w
o
r
k
r
ep
r
esen
t
s
o
n
e
o
f
th
e
f
ir
s
t
s
y
s
te
m
ati
c
in
v
e
s
tig
a
tio
n
s
o
f
m
u
lti
m
o
d
al
ac
o
u
s
tic
–
v
ib
r
atio
n
s
p
ec
tr
o
g
r
a
m
f
u
s
io
n
f
o
r
p
h
y
s
ical
lea
k
ag
e
a
n
al
y
s
i
s
i
n
P
QC
i
m
p
le
m
e
n
tatio
n
s
.
T
h
e
r
esu
lts
e
m
p
h
a
s
ize
th
e
i
m
p
o
r
tan
ce
o
f
ev
alu
ati
n
g
p
h
y
s
ical
i
m
p
le
m
e
n
tatio
n
s
ec
u
r
it
y
alo
n
g
s
id
e
m
at
h
e
m
atica
l
r
esis
ta
n
ce
,
p
ar
ticu
lar
l
y
f
o
r
cr
y
p
to
g
r
ap
h
ic
s
y
s
te
m
s
d
ep
lo
y
ed
in
p
r
ac
tical
en
v
ir
o
n
m
en
t
s
.
Fu
t
u
r
e
r
esear
ch
w
ill
ex
te
n
d
t
h
is
w
o
r
k
to
w
ar
d
lar
g
er
an
d
m
o
r
e
d
iv
er
s
e
d
ataset
s
,
r
ea
l
h
ar
d
w
ar
e
-
b
ased
P
QC
i
m
p
le
m
en
ta
tio
n
s
,
an
d
r
o
b
u
s
tn
e
s
s
e
v
al
u
atio
n
u
n
d
er
n
o
is
y
an
d
h
e
ter
o
g
en
eo
u
s
o
p
er
atin
g
co
n
d
itio
n
s
,
in
cl
u
d
i
n
g
r
e
m
o
te
attac
k
s
ce
n
a
r
io
s
.
A
d
d
itio
n
al
r
esear
ch
d
ir
ec
tio
n
s
in
cl
u
d
e
th
e
ex
p
lo
r
atio
n
o
f
ad
v
an
ce
d
f
u
s
io
n
s
tr
ateg
ie
s
s
u
ch
a
s
atten
tio
n
-
b
ased
m
ec
h
a
n
is
m
s
,
ad
v
er
s
ar
ial
o
b
f
u
s
ca
t
io
n
d
ef
e
n
s
e
s
,
an
d
ex
p
lain
ab
le
A
I
tech
n
iq
u
es
to
e
n
h
a
n
ce
b
o
th
t
h
e
in
ter
p
r
etab
ilit
y
an
d
r
e
s
i
lie
n
ce
o
f
s
id
e
-
c
h
an
n
el
a
n
al
y
s
i
s
f
r
a
m
e
w
o
r
k
s
.
I
n
t
h
i
s
co
n
tex
t,
t
h
e
p
r
o
p
o
s
ed
f
r
am
e
w
o
r
k
i
s
p
ar
ticu
lar
l
y
r
ele
v
a
n
t
f
o
r
ev
alu
at
in
g
t
h
e
p
h
y
s
ical
s
ec
u
r
it
y
o
f
P
QC
i
m
p
le
m
en
ta
tio
n
s
in
e
m
er
g
i
n
g
I
n
ter
n
et
o
f
T
h
i
n
g
s
(
I
o
T
)
an
d
e
m
b
ed
d
ed
s
y
s
te
m
s
.
ACK
NO
WL
E
D
G
M
E
NT
S
T
h
e
au
th
o
r
w
o
u
ld
li
k
e
to
th
an
k
t
h
e
I
n
f
o
r
m
atic
s
E
n
g
i
n
e
er
in
g
Stu
d
y
P
r
o
g
r
a
m
,
Mu
h
a
m
m
ad
i
y
a
h
Un
i
v
er
s
it
y
o
f
No
r
th
Ma
l
u
k
u
f
o
r
th
eir
ass
is
ta
n
ce
i
n
th
is
r
esea
r
ch
.
F
UNDIN
G
I
NF
O
RM
AT
I
O
N
T
h
e
au
th
o
r
w
o
u
ld
lik
e
to
ex
p
r
ess
h
is
g
r
atit
u
d
e
to
th
e
I
n
f
o
r
m
ati
c
s
E
n
g
i
n
ee
r
in
g
St
u
d
y
P
r
o
g
r
am
,
Facu
lt
y
o
f
E
n
g
i
n
ee
r
i
n
g
,
M
u
h
a
m
m
ad
i
y
a
h
Un
iv
er
s
it
y
o
f
No
r
th
Ma
lu
k
u
,
T
er
n
ate.
AUTHO
R
CO
NT
RIB
UT
I
O
NS ST
A
T
E
M
E
NT
T
h
is
jo
u
r
n
al
u
s
e
s
th
e
C
o
n
tr
ib
u
to
r
R
o
les
T
ax
o
n
o
m
y
(
C
R
ed
iT
)
t
o
r
ec
o
g
n
ize
in
d
i
v
id
u
al
au
t
h
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
t
h
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
lla
b
o
r
atio
n
.
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
A
b
d
u
l H
ar
i
s
Mu
h
a
m
m
ad
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Ga
m
ar
ia
Ma
n
d
ar
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
A
d
eli
n
a
I
b
r
ah
i
m
✓
✓
✓
✓
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
si
s
I
:
I
n
v
e
st
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
si
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
T
h
e
au
th
o
r
s
d
ec
lar
e
th
at
t
h
e
y
h
av
e
n
o
co
n
f
lict o
f
i
n
ter
est.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
atasets
g
e
n
er
ated
an
d
/o
r
an
al
y
ze
d
d
u
r
i
n
g
th
e
c
u
r
r
en
t
s
tu
d
y
ar
e
av
ai
lab
le
f
r
o
m
t
h
e
co
r
r
esp
o
n
d
in
g
au
t
h
o
r
u
p
o
n
r
ea
s
o
n
ab
le
r
eq
u
est.
RE
F
E
R
E
NC
E
S
[
1
]
D.
-
T
.
D
a
m,
T
.
-
H
.
T
r
a
n
,
V
.
-
P
.
H
o
a
n
g
,
C
.
-
K
.
P
h
a
m
,
a
n
d
T
.
-
T
.
H
o
a
n
g
,
“
A
S
u
r
v
e
y
o
f
P
o
st
-
Q
u
a
n
t
u
m
C
r
y
p
t
o
g
r
a
p
h
y
:
S
t
a
r
t
o
f
a
N
e
w
R
a
c
e
,
”
C
r
y
p
t
o
g
r
a
p
h
y
,
v
o
l
.
7
,
n
o
.
3
,
p
.
4
0
,
A
u
g
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
c
r
y
p
t
o
g
r
a
p
h
y
7
0
3
0
0
4
0
.
[
2
]
D
.
U
k
p
a
b
i
e
t
a
l
.
,
“
F
r
a
mew
o
r
k
f
o
r
u
n
d
e
r
st
a
n
d
i
n
g
q
u
a
n
t
u
m
c
o
m
p
u
t
i
n
g
u
se
c
a
se
s
f
r
o
m
a
mu
l
t
i
d
i
s
c
i
p
l
i
n
a
r
y
p
e
r
sp
e
c
t
i
v
e
a
n
d
f
u
t
u
r
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
24
,
No
.
4
,
A
u
g
u
s
t
20
26
:
1
241
-
1
2
5
2
1250
r
e
se
a
r
c
h
d
i
r
e
c
t
i
o
n
s
,
”
Fu
t
u
res,
v
o
l
.
1
5
4
,
p
.
1
0
3
2
7
7
,
D
e
c
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
f
u
t
u
r
e
s.2
0
2
3
.
1
0
3
2
7
7
.
[
3
]
J.
Z
h
a
n
g
e
t
a
l
.
,
“
D
e
si
g
n
a
n
d
i
mp
l
e
me
n
t
a
t
i
o
n
o
f
r
u
n
-
l
e
n
g
t
h
e
n
c
o
d
i
n
g
o
n
q
u
a
n
t
u
m
c
o
mp
u
t
e
r
s
f
o
r
r
e
so
u
r
c
e
-
e
f
f
i
c
i
e
n
t
d
a
t
a
r
e
p
r
e
se
n
t
a
t
i
o
n
,
”
Ap
p
l
i
e
d
S
o
f
t
C
o
m
p
u
t
i
n
g
,
v
o
l
.
1
8
7
,
p
.
1
1
4
2
7
3
,
F
e
b
.
2
0
2
6
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
so
c
.
2
0
2
5
.
1
1
4
2
7
3
.
[
4
]
C
.
H
a
o
,
Q
.
M
a
,
Y
.
C
h
e
n
,
H
.
Z
h
a
n
g
,
a
n
d
D
.
Q
u
,
“
Q
u
a
n
t
u
m
a
u
t
o
e
n
c
o
d
e
r
i
m
p
l
e
me
n
t
a
t
i
o
n
o
f
h
i
g
h
-
d
i
me
n
s
i
o
n
a
l
st
e
g
a
n
o
g
r
a
p
h
i
c
e
n
c
o
d
i
n
g
f
o
r
a
r
b
i
t
r
a
r
y
q
u
a
n
t
u
m
s
t
a
t
e
s
,
”
J
o
u
rn
a
l
o
f
K
i
n
g
S
a
u
d
U
n
i
v
e
rs
i
t
y
C
o
m
p
u
t
e
r
a
n
d
I
n
f
o
rm
a
t
i
o
n
S
c
i
e
n
c
e
s
,
v
o
l
.
3
7
,
n
o
.
8
,
O
c
t
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
0
7
/
s4
4
4
4
3
-
0
2
5
-
0
0
2
7
4
-
1.
[
5
]
S
.
M
a
n
d
r
à
,
H
.
M
u
n
o
z
-
B
a
u
z
a
,
G
.
M
o
ssi
,
a
n
d
E
.
G
.
R
i
e
f
f
e
l
,
“
G
e
n
e
r
a
t
i
n
g
h
a
r
d
I
si
n
g
i
n
s
t
a
n
c
e
s
w
i
t
h
p
l
a
n
t
e
d
so
l
u
t
i
o
n
s
u
s
i
n
g
p
o
st
-
q
u
a
n
t
u
m
c
r
y
p
t
o
g
r
a
p
h
i
c
p
r
o
t
o
c
o
l
s,”
F
u
t
u
re
G
e
n
e
r
a
t
i
o
n
C
o
m
p
u
t
e
r
S
y
st
e
m
s
,
v
o
l
.
1
6
6
,
p
.
1
0
7
7
2
1
,
M
a
y
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
f
u
t
u
r
e
.
2
0
2
5
.
1
0
7
7
2
1
.
[
6
]
Y
.
K
i
m
e
t
a
l
.
,
“
Ev
i
d
e
n
c
e
f
o
r
t
h
e
u
t
i
l
i
t
y
o
f
q
u
a
n
t
u
m
c
o
mp
u
t
i
n
g
b
e
f
o
r
e
f
a
u
l
t
t
o
l
e
r
a
n
c
e
,
”
N
a
t
u
re
,
v
o
l
.
6
1
8
,
n
o
.
7
9
6
5
,
p
p
.
5
0
0
–
5
0
5
,
Ju
n
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
3
8
/
s4
1
5
8
6
-
0
2
3
-
0
6
0
9
6
-
3.
[
7
]
S
.
A
h
ma
d
u
n
n
i
s
a
a
n
d
S
.
E.
M
a
t
h
e
,
“
A
c
o
mp
r
e
h
e
n
si
v
e
r
e
v
i
e
w
o
n
h
a
r
d
w
a
r
e
i
mp
l
e
me
n
t
a
t
i
o
n
s
o
f
l
a
t
t
i
c
e
-
ba
s
e
d
c
r
y
p
t
o
g
r
a
p
h
i
c
sch
e
me
s,”
J
o
u
r
n
a
l
o
f
S
y
st
e
m
s A
r
c
h
i
t
e
c
t
u
re
,
v
o
l
.
1
6
7
,
p
.
1
0
3
4
8
6
,
O
c
t
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
sy
sarc.
2
0
2
5
.
1
0
3
4
8
6
.
[
8
]
M
.
B
a
n
d
a
r
u
,
S
.
E
.
M
a
t
h
e
,
a
n
d
C
.
W
a
t
t
a
n
a
p
a
n
i
c
h
,
“
Ev
a
l
u
a
t
i
o
n
o
f
h
a
r
d
w
a
r
e
a
n
d
so
f
t
w
a
r
e
i
mp
l
e
me
n
t
a
t
i
o
n
s
f
o
r
N
I
S
T
f
i
n
a
l
i
st
a
n
d
f
o
u
r
t
h
-
r
o
u
n
d
p
o
st
-
q
u
a
n
t
u
m
c
r
y
p
t
o
g
r
a
p
h
y
K
EM
s,”
C
o
m
p
u
t
e
rs
a
n
d
E
l
e
c
t
ri
c
a
l
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
1
2
0
,
p
.
1
0
9
8
2
6
,
D
e
c
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
mp
e
l
e
c
e
n
g
.
2
0
2
4
.
1
0
9
8
2
6
.
[
9
]
E.
W
.
A
b
o
o
d
,
A
.
A
.
Y
a
ssi
n
,
Z
.
A
.
A
b
d
u
l
j
a
b
b
a
r
,
V
.
O
.
N
y
a
n
g
a
r
e
si
,
a
n
d
A
.
H
.
A
l
i
,
“
P
r
o
v
a
b
l
y
l
i
g
h
t
w
e
i
g
h
t
a
n
d
se
c
u
r
e
I
o
H
T
sch
e
me
w
i
t
h
p
o
st
-
q
u
a
n
t
u
m
c
r
y
p
t
o
g
r
a
p
h
y
a
n
d
f
o
g
c
o
mp
u
t
i
n
g
:
A
c
o
mp
r
e
h
e
n
si
v
e
s
c
h
e
me
f
o
r
h
e
a
l
t
h
c
a
r
e
sy
st
e
m,”
M
e
t
h
o
d
s
X
,
v
o
l
.
1
5
,
p
.
1
0
3
6
3
1
,
D
e
c
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
me
x
.
2
0
2
5
.
1
0
3
6
3
1
.
[
1
0
]
T.
-
T
.
T
sai
a
n
d
J.
-
H
.
Y
a
n
g
,
“
L
e
a
k
a
g
e
-
r
e
si
l
i
e
n
t
c
e
r
t
i
f
i
c
a
t
e
l
e
ss
p
u
b
l
i
c
k
e
y
e
n
c
r
y
p
t
i
o
n
w
i
t
h
e
q
u
a
l
i
t
y
t
e
st
r
e
si
st
a
n
t
t
o
s
i
d
e
-
c
h
a
n
n
e
l
a
t
t
a
c
k
s,
”
C
o
m
p
u
t
e
r
N
e
t
w
o
r
k
s,
v
o
l
.
2
7
0
,
p
.
1
1
1
4
8
5
,
O
c
t
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
m
n
e
t
.
2
0
2
5
.
1
1
1
4
8
5
.
[
1
1
]
J.
L
i
a
o
,
H
.
W
a
n
g
,
J.
W
a
n
g
,
a
n
d
Y
.
T
a
n
g
,
“
S
w
i
t
c
h
-
T
:
A
n
o
v
e
l
mu
l
t
i
-
t
a
sk
d
e
e
p
-
l
e
a
r
n
i
n
g
n
e
t
w
o
r
k
f
o
r
c
r
o
ss
-
d
e
v
i
c
e
si
d
e
-
c
h
a
n
n
e
l
a
t
t
a
c
k
,
”
J
o
u
rn
a
l
o
f
I
n
f
o
rm
a
t
i
o
n
S
e
c
u
r
i
t
y
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
9
3
,
p
.
1
0
4
1
4
6
,
S
e
p
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
i
sa.
2
0
2
5
.
1
0
4
1
4
6
.
[
1
2
]
V
.
S
.
B
o
k
h
a
r
a
i
e
a
n
d
A
.
Ja
h
a
n
i
a
n
,
“
P
o
w
e
r
si
d
e
-
c
h
a
n
n
e
l
l
e
a
k
a
g
e
a
sse
ssm
e
n
t
a
n
d
l
o
c
a
t
i
n
g
t
h
e
e
x
a
c
t
so
u
r
c
e
s
o
f
l
e
a
k
a
g
e
a
t
t
h
e
e
a
r
l
y
st
a
g
e
s
o
f
A
S
I
C
d
e
si
g
n
p
r
o
c
e
ss,”
T
h
e
J
o
u
rn
a
l
o
f
S
u
p
e
r
c
o
m
p
u
t
i
n
g
,
v
o
l
.
7
8
,
n
o
.
2
,
p
p
.
2
2
1
9
–
2
2
4
4
,
J
u
n
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
2
2
7
-
0
2
1
-
0
3
9
2
7
-
w.
[
1
3
]
J.
X
i
a
n
d
C
.
F
a
n
,
“
M
u
l
t
i
-
b
y
t
e
si
d
e
-
c
h
a
n
n
e
l
a
t
t
a
c
k
s
o
n
c
h
a
o
t
i
c
b
l
o
c
k
c
i
p
h
e
r
:
A
u
t
o
e
n
c
o
d
e
r
-
b
a
se
d
f
e
a
t
u
r
e
se
l
e
c
t
i
o
n
a
n
d
C
N
N
-
T
r
a
n
sf
o
r
me
r
c
o
l
l
a
b
o
r
a
t
i
v
e
a
t
t
a
c
k
f
r
a
me
w
o
r
k
,
”
C
h
a
o
s
,
S
o
l
i
t
o
n
s
&
Fra
c
t
a
l
s
,
v
o
l
.
2
0
0
,
p
.
1
1
7
0
9
7
,
N
o
v
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
h
a
o
s.
2
0
2
5
.
1
1
7
0
9
7
.
[
1
4
]
S
r
i
r
a
mu
d
u
,
V
.
N
a
l
l
a
,
D
.
N
a
r
e
n
d
a
r
,
a
n
d
G
.
P
a
d
m
a
v
a
t
h
i
,
“
M
o
d
e
l
f
o
r
c
a
p
t
u
r
i
n
g
n
o
i
se
f
r
e
e
t
r
a
c
e
s
f
o
r
S
i
d
e
C
h
a
n
n
e
l
P
o
w
e
r
C
r
y
p
t
a
n
a
l
y
si
s
b
a
se
d
o
n
S
A
K
U
R
A
-
G
F
P
G
A
a
n
d
C
a
se
st
u
d
y
o
f
A
ES,”
2
0
2
2
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
Re
c
e
n
t
T
re
n
d
s
i
n
Mi
c
r
o
e
l
e
c
t
r
o
n
i
c
s,
A
u
t
o
m
a
t
i
o
n
,
C
o
m
p
u
t
i
n
g
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
s
S
y
s
t
e
m
s
(
I
C
MA
C
C
)
,
p
p
.
1
–
7
,
D
e
c
.
2
8
,
2
0
2
2
.
d
o
i
:
1
0
.
1
1
0
9
/
i
c
ma
c
c
5
4
8
2
4
.
2
0
2
2
.
1
0
0
9
3
6
7
2
.
[
1
5
]
Z
.
H
u
a
n
g
,
H
.
W
a
n
g
,
B
.
C
a
o
,
D
.
H
e
,
a
n
d
J.
W
a
n
g
,
“
A
c
o
mp
r
e
h
e
n
si
v
e
si
d
e
-
c
h
a
n
n
e
l
l
e
a
k
a
g
e
a
sse
ssm
e
n
t
o
f
C
R
Y
S
TA
L
S
-
K
y
b
e
r
i
n
I
I
o
T
,
”
I
n
t
e
r
n
e
t
o
f
T
h
i
n
g
s
,
v
o
l
.
2
7
,
p
.
1
0
1
3
3
1
,
O
c
t
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
o
t
.
2
0
2
4
.
1
0
1
3
3
1
.
[
1
6
]
K
.
Y
a
n
g
,
Y
.
Z
h
a
n
g
,
T
.
L
i
,
a
n
d
L
.
S
u
n
,
“
A
S
I
D
S
:
A
c
o
u
st
i
c
s
i
d
e
-
c
h
a
n
n
e
l
b
a
se
d
i
n
t
r
u
s
i
o
n
d
e
t
e
c
t
i
o
n
sy
st
e
m
f
o
r
i
n
d
u
st
r
i
a
l
r
o
b
o
t
i
c
a
r
ms,”
C
o
m
p
u
t
e
rs &
S
e
c
u
ri
t
y
,
v
o
l
.
1
5
7
,
p
.
1
0
4
5
8
6
,
O
c
t
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
se
.
2
0
2
5
.
1
0
4
5
8
6
.
[
1
7
]
A
a
k
a
sh
,
V
.
K
.
P
a
n
d
e
y
,
S
.
P
r
a
k
a
s
h
,
S
.
S
i
n
g
h
,
T
.
Y
a
n
g
,
a
n
d
R
.
S
.
R
a
t
h
o
r
e
,
“
A
n
Ef
f
i
c
i
e
n
t
A
p
p
r
o
a
c
h
f
o
r
S
i
d
e
C
h
a
n
n
e
l
A
t
t
a
c
k
i
n
C
l
o
u
d
C
o
mp
u
t
i
n
g
,
”
Pro
c
e
d
i
a
C
o
m
p
u
t
e
r S
c
i
e
n
c
e
,
v
o
l
.
2
5
8
,
p
p
.
1
4
0
4
–
1
4
1
3
,
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
r
o
c
s.
2
0
2
5
.
0
4
.
3
7
3
.
[
1
8
]
S
.
A
l
a
b
d
u
l
w
a
h
a
b
,
M
.
C
h
e
o
n
g
,
A
.
S
e
o
,
Y
.
-
T
.
K
i
m,
a
n
d
Y
.
S
o
n
,
“
E
n
h
a
n
c
i
n
g
d
e
e
p
l
e
a
r
n
i
n
g
-
b
a
se
d
si
d
e
-
c
h
a
n
n
e
l
a
n
a
l
y
si
s
u
s
i
n
g
f
e
a
t
u
r
e
e
n
g
i
n
e
e
r
i
n
g
i
n
a
f
u
l
l
y
si
mu
l
a
t
e
d
I
o
T
s
y
st
e
m,”
Ex
p
e
rt
S
y
st
e
m
s
w
i
t
h
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
2
6
6
,
p
.
1
2
6
0
7
9
,
M
a
r
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
sw
a
.
2
0
2
4
.
1
2
6
0
7
9
.
[
1
9
]
M
.
M
u
s
h
t
a
q
,
M
.
A
.
M
u
k
h
t
a
r
,
V
.
L
a
p
o
t
r
e
,
M
.
K
.
B
h
a
t
t
i
,
a
n
d
G
.
G
o
g
n
i
a
t
,
“
W
i
n
t
e
r
i
s
h
e
r
e
!
A
d
e
c
a
d
e
o
f
c
a
c
h
e
-
b
a
se
d
si
d
e
-
c
h
a
n
n
e
l
a
t
t
a
c
k
s,
d
e
t
e
c
t
i
o
n
&
a
mp
;
mi
t
i
g
a
t
i
o
n
f
o
r
R
S
A
,
”
I
n
f
o
rm
a
t
i
o
n
S
y
s
t
e
m
s
,
v
o
l
.
9
2
,
p
.
1
0
1
5
2
4
,
S
e
p
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
s
.
2
0
2
0
.
1
0
1
5
2
4
.
[
2
0
]
V
.
S
.
B
o
k
h
a
r
a
i
e
a
n
d
A
.
Ja
h
a
n
i
a
n
,
“
S
i
d
e
-
c
h
a
n
n
e
l
l
e
a
k
a
g
e
a
sse
ssm
e
n
t
me
t
r
i
c
s a
n
d
me
t
h
o
d
o
l
o
g
i
e
s a
t
d
e
si
g
n
c
y
c
l
e
:
A
c
a
se
st
u
d
y
f
o
r
a
c
r
y
p
t
o
s
y
st
e
m,”
J
o
u
r
n
a
l
o
f
I
n
f
o
rm
a
t
i
o
n
S
e
c
u
r
i
t
y
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
5
4
,
p
.
1
0
2
5
6
1
,
O
c
t
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
i
sa.
2
0
2
0
.
1
0
2
5
6
1
.
[
2
1
]
S
.
H
o
q
u
e
,
A
.
A
y
d
e
g
e
r
,
a
n
d
E
.
Z
e
y
d
a
n
,
“
Ex
p
l
o
r
i
n
g
P
o
st
Q
u
a
n
t
u
m
C
r
y
p
t
o
g
r
a
p
h
y
w
i
t
h
Q
u
a
n
t
u
m
K
e
y
D
i
st
r
i
b
u
t
i
o
n
f
o
r
S
u
s
t
a
i
n
a
b
l
e
M
o
b
i
l
e
N
e
t
w
o
r
k
A
r
c
h
i
t
e
c
t
u
r
e
D
e
si
g
n
,
”
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
4
t
h
Wo
r
k
s
h
o
p
o
n
P
e
rf
o
rm
a
n
c
e
a
n
d
En
e
rg
y
Ef
f
i
c
i
e
n
c
y
i
n
C
o
n
c
u
rr
e
n
t
a
n
d
D
i
st
r
i
b
u
t
e
d
S
y
s
t
e
m
s
,
p
p
.
9
–
1
6
,
J
u
n
.
0
3
,
2
0
2
4
.
d
o
i
:
1
0
.
1
1
4
5
/
3
6
5
9
9
9
7
.
3
6
6
0
0
3
3
.
[
2
2
]
C
.
B
a
l
a
m
u
r
u
g
a
n
,
K
.
S
i
n
g
h
,
G
.
G
a
n
e
san
,
a
n
d
M
.
R
a
j
a
r
a
j
a
n
,
“
P
o
st
-
Q
u
a
n
t
u
m
a
n
d
C
o
d
e
-
B
a
se
d
C
r
y
p
t
o
g
r
a
p
h
y
—
S
o
me
P
r
o
sp
e
c
t
i
v
e
R
e
se
a
r
c
h
D
i
r
e
c
t
i
o
n
s
,
”
C
ry
p
t
o
g
r
a
p
h
y
,
v
o
l
.
5
,
n
o
.
4
,
p
.
3
8
,
D
e
c
.
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
c
r
y
p
t
o
g
r
a
p
h
y
5
0
4
0
0
3
8
.
[
2
3
]
S
.
K
u
mari,
“
N
e
x
t
-
G
e
n
I
o
T
S
e
c
u
r
i
t
y
u
si
n
g
P
o
l
a
r
C
o
d
e
s
-
b
a
se
d
C
r
y
p
t
o
g
r
a
p
h
y
f
o
r
mal
w
a
r
e
d
e
f
e
n
c
e
t
h
r
o
u
g
h
q
u
a
n
t
u
m
se
l
f
-
a
t
t
e
n
t
i
o
n
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
K
n
o
w
l
e
d
g
e
-
B
a
s
e
d
S
y
st
e
m
s
,
v
o
l
.
3
2
1
,
p
.
1
1
3
7
1
6
,
J
u
n
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
k
n
o
sy
s.2
0
2
5
.
1
1
3
7
1
6
.
[
2
4
]
A
.
S
a
r
a
v
a
n
a
se
l
v
a
n
a
n
d
B
.
P
a
r
a
m
a
si
v
a
n
,
“
A
n
o
n
e
-
t
i
me
p
a
d
c
r
y
p
t
o
g
r
a
p
h
i
c
a
l
g
o
r
i
t
h
m
w
i
t
h
H
u
f
f
ma
n
S
o
u
r
c
e
C
o
d
i
n
g
b
a
se
d
e
n
e
r
g
y
a
w
a
r
e
se
n
so
r
n
o
d
e
d
e
si
g
n
,
”
S
u
s
t
a
i
n
a
b
l
e
C
o
m
p
u
t
i
n
g
:
I
n
f
o
rm
a
t
i
c
s
a
n
d
S
y
s
t
e
m
s
,
v
o
l
.
4
4
,
p
.
1
0
1
0
4
8
,
D
e
c
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
su
s
c
o
m.
2
0
2
4
.
1
0
1
0
4
8
.
[
2
5
]
Z
.
F
u
,
L
.
F
a
n
g
,
H
.
H
u
a
n
g
,
a
n
d
B
.
Y
u
,
“
D
i
st
r
i
b
u
t
e
d
t
h
r
e
e
-
l
e
v
e
l
Q
R
c
o
d
e
s
b
a
se
d
o
n
v
i
su
a
l
c
r
y
p
t
o
g
r
a
p
h
y
sch
e
me
,
”
J
o
u
rn
a
l
o
f
V
i
su
a
l
C
o
m
m
u
n
i
c
a
t
i
o
n
a
n
d
I
m
a
g
e
Re
p
res
e
n
t
a
t
i
o
n
,
v
o
l
.
8
7
,
p
.
1
0
3
5
6
7
,
A
u
g
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
v
c
i
r
.
2
0
2
2
.
1
0
3
5
6
7
.
[
2
6
]
D
.
M
i
sh
r
a
,
K
.
N
a
md
e
o
,
a
n
d
N
.
S
r
i
v
a
st
a
v
a
,
“
T
h
e
r
i
se
a
n
d
r
e
si
l
i
e
n
c
e
o
f
mu
l
t
i
v
a
r
i
a
t
e
c
r
y
p
t
o
g
r
a
p
h
y
:
A
d
v
a
n
c
e
s,
p
i
t
f
a
l
l
s,
a
n
d
p
r
o
mi
si
n
g
p
a
t
h
w
a
y
s,”
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
Re
v
i
e
w
,
v
o
l
.
5
9
,
p
.
1
0
0
8
6
0
,
F
e
b
.
2
0
2
6
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
sr
e
v
.
2
0
2
5
.
1
0
0
8
6
0
.
[
2
7
]
N
.
K
u
n
d
u
,
S
.
K
.
D
e
b
n
a
t
h
,
a
n
d
D
.
M
i
s
h
r
a
,
“
A
se
c
u
r
e
a
n
d
e
f
f
i
c
i
e
n
t
g
r
o
u
p
si
g
n
a
t
u
r
e
sc
h
e
me
b
a
se
d
o
n
mu
l
t
i
v
a
r
i
a
t
e
p
u
b
l
i
c
k
e
y
c
r
y
p
t
o
g
r
a
p
h
y
,
”
J
o
u
r
n
a
l
o
f
I
n
f
o
rm
a
t
i
o
n
S
e
c
u
r
i
t
y
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
5
8
,
p
.
1
0
2
7
7
6
,
M
a
y
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
i
sa.
2
0
2
1
.
1
0
2
7
7
6
.
[
2
8
]
R
.
I
y
s
w
a
r
y
a
a
n
d
R
.
A
n
i
t
h
a
,
“
S
e
c
u
r
e
d
a
t
a
s
t
o
r
a
g
e
i
n
mu
l
t
i
-
c
l
o
u
d
e
n
v
i
r
o
n
me
n
t
s
u
si
n
g
l
a
t
t
i
c
e
-
b
a
se
d
s
a
b
e
r
w
i
t
h
D
i
f
f
i
e
-
H
e
l
l
man
c
r
y
p
t
o
g
r
a
p
h
y
a
n
d
a
u
t
h
e
n
t
i
c
a
t
i
o
n
b
a
s
e
d
o
n
P
U
F
-
EC
C
,
”
D
a
t
a
&
K
n
o
w
l
e
d
g
e
En
g
i
n
e
e
r
i
n
g
,
v
o
l
.
1
6
1
,
p
.
1
0
2
5
1
2
,
Ja
n
.
2
0
2
6
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
d
a
t
a
k
.
2
0
2
5
.
1
0
2
5
1
2
.
[
2
9
]
M
.
G
.
A
.
M
a
l
i
k
,
M
.
H
u
ssa
i
n
,
a
n
d
Z
.
B
a
s
h
i
r
,
“
Ef
f
i
c
i
e
n
t
l
a
t
t
i
c
e
-
b
a
se
d
M
o
r
d
e
l
l
e
l
l
i
p
t
i
c
c
u
r
v
e
S
-
b
o
x
f
o
r
sec
u
r
e
l
i
g
h
t
w
e
i
g
h
t
c
r
y
p
t
o
g
r
a
p
h
y
,
”
I
n
t
e
g
ra
t
i
o
n
,
v
o
l
.
1
0
5
,
p
.
1
0
2
5
0
5
,
N
o
v
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
v
l
si
.
2
0
2
5
.
1
0
2
5
0
5
.
[
3
0
]
Q
.
I
.
M
.
H
u
ss
a
i
n
a
n
d
V
.
K
a
l
e
,
“
M
o
b
i
l
e
n
o
d
e
a
u
t
h
e
n
t
i
c
a
t
i
o
n
w
i
t
h
r
i
s
k
-
b
a
se
d
mo
d
i
f
i
e
d
l
a
t
t
i
c
e
c
r
y
p
t
o
g
r
a
p
h
y
e
n
a
b
l
e
d
a
d
a
p
t
i
v
e
mu
l
t
i
f
a
c
t
o
r
a
u
t
h
e
n
t
i
c
a
t
i
o
n
f
o
r
se
c
u
r
e
d
a
t
a
t
r
a
n
smiss
i
o
n
,
”
C
o
m
p
u
t
e
rs
a
n
d
E
l
e
c
t
ri
c
a
l
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
1
2
4
,
p
.
1
1
0
2
7
2
,
M
a
y
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
mp
e
l
e
c
e
n
g
.
2
0
2
5
.
1
1
0
2
7
2
.
[
3
1
]
Y
.
H
u
a
n
g
,
Y
.
Ji
n
,
Z
.
H
u
,
a
n
d
F
.
Zh
a
n
g
,
“
O
p
t
i
mi
z
i
n
g
t
h
e
e
v
a
l
u
a
t
i
o
n
o
f
ℓ
-
i
so
g
e
n
o
u
s
c
u
r
v
e
f
o
r
i
so
g
e
n
y
-
b
a
se
d
c
r
y
p
t
o
g
r
a
p
h
y
,
”
I
n
f
o
rm
a
t
i
o
n
Pr
o
c
e
ssi
n
g
L
e
t
t
e
rs
,
v
o
l
.
1
7
8
,
p
.
1
0
6
3
0
1
,
N
o
v
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
p
l
.
2
0
2
2
.
1
0
6
3
0
1
.
[
3
2
]
P
.
D
a
r
t
o
i
s,
“
F
a
st
c
o
m
p
u
t
a
t
i
o
n
o
f
2
-
i
s
o
g
e
n
i
e
s
i
n
d
i
me
n
si
o
n
4
a
n
d
c
r
y
p
t
o
g
r
a
p
h
i
c
a
p
p
l
i
c
a
t
i
o
n
s
,
”
J
o
u
rn
a
l
o
f
Al
g
e
b
ra
,
v
o
l
.
6
8
3
,
p
p
.
4
4
9
–
5
1
4
,
D
e
c
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
a
l
g
e
b
r
a
.
2
0
2
5
.
0
6
.
0
3
3
.
Evaluation Warning : The document was created with Spire.PDF for Python.