I
nte
rna
t
io
na
l J
o
urna
l o
f
Rec
o
nfig
ura
ble a
nd
E
m
be
dd
e
d Sy
s
t
e
m
s
(
I
J
R
E
S)
Vo
l.
13
,
No
.
3
,
N
o
v
e
m
b
er
20
24
,
p
p
.
5
8
6
~
59
4
I
SS
N:
2089
-
4864
,
DOI
:
1
0
.
1
1
5
9
1
/i
j
r
es
.
v
13
.
i
3
.
pp
5
8
6
-
59
4
586
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
r
es.ia
esco
r
e.
co
m
Ro
bust e
m
b
edde
d acces
s co
ntrol s
y
ste
m
bas
ed on
face an
d
encryp
ted
QR w
ith
RPi4
Sa
m
ir
M
a
r
w
a
n H
a
m
m
a
m
i
1
,
M
uh
a
mm
a
d Alha
mm
a
m
i
2
1
D
e
p
a
r
t
me
n
t
o
f
M
a
n
a
g
e
me
n
t
I
n
f
o
r
mat
i
o
n
S
y
st
e
ms,
D
h
o
f
a
r
U
n
i
v
e
r
si
t
y
,
S
a
l
a
l
a
h
,
O
ma
n
2
D
e
p
a
r
t
me
n
t
o
f
C
o
mm
u
n
i
c
a
t
i
o
n
,
H
i
g
h
e
r
I
n
st
i
t
u
t
e
f
o
r
A
p
p
l
i
e
d
S
c
i
e
n
c
e
s a
n
d
T
e
c
h
n
o
l
o
g
y
,
D
a
masc
u
s
,
S
y
r
i
a
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
an
2
6
,
2
0
2
4
R
ev
i
s
ed
Ma
y
3
,
2
0
2
4
A
cc
ep
ted
Ma
y
1
7
,
2
0
2
4
F
a
c
ial
-
b
a
se
d
re
c
o
g
n
it
io
n
sy
ste
m
s
a
re
c
o
m
m
o
n
l
y
u
se
d
f
o
r
b
u
il
d
i
n
g
a
c
c
e
s
s
c
o
n
tro
l,
w
it
h
th
e
a
c
c
u
ra
c
y
a
n
d
c
o
m
p
u
ti
n
g
re
q
u
irem
e
n
ts
stil
l
b
e
in
g
im
p
ro
v
e
d
.
On
th
e
o
th
e
r
h
a
n
d
,
QR
c
o
d
e
s
a
re
g
a
in
in
g
risin
g
a
tt
e
n
ti
o
n
a
s
a
n
in
p
u
t
in
terf
a
c
e
to
m
a
n
y
e
m
b
e
d
d
e
d
a
p
p
l
ica
ti
o
n
s.
T
h
is
p
a
p
e
r
p
ro
p
o
se
s
a
n
e
m
b
e
d
d
e
d
a
c
c
e
s
s
c
o
n
tro
l
sy
ste
m
th
a
t
c
u
sto
m
ise
s
b
o
th
p
re
v
io
u
s
tec
h
n
i
q
u
e
s
to
b
e
im
p
le
m
e
n
ted
o
n
th
e
CP
U
o
f
a
lo
w
-
c
o
st
Ra
sp
b
e
rr
y
P
i
4
c
o
m
p
u
ter.
T
h
e
a
c
h
iev
e
d
s
y
ste
m
w
o
rk
s
s
m
o
o
th
ly
w
it
h
a
f
ra
m
e
ra
te
o
f
8
.
2
7
F
P
S
,
i
n
c
re
a
sin
g
th
e
a
c
c
e
ss
in
g
c
o
n
tro
l'
s
ro
b
u
st
n
e
ss
c
o
m
p
a
r
e
d
to
a
sy
st
e
m
b
a
se
d
o
n
f
a
c
e
re
c
o
g
n
it
io
n
o
n
ly
.
It
a
lso
o
ff
e
rs
th
e
a
b
il
it
y
to
c
o
n
tro
l
th
e
a
c
c
e
ss
o
f
u
n
k
n
o
w
n
f
a
c
e
s.
In
tan
d
e
m
w
it
h
in
teg
ra
ti
o
n
,
th
is
stre
n
g
th
e
n
s
se
c
u
rit
y
m
e
a
su
re
s,
im
p
ro
v
e
s
u
se
r
e
x
p
e
rien
c
e
,
a
n
d
o
u
tp
e
rf
o
rm
s
c
o
n
v
e
n
ti
o
n
a
l
a
c
c
e
ss
c
o
n
tr
o
l
a
p
p
ro
a
c
h
e
s,
c
re
a
ti
n
g
a
n
a
tt
ra
c
ti
v
e
o
f
fe
r
f
o
r
m
a
n
y
b
u
sin
e
ss
e
s.
K
ey
w
o
r
d
s
:
A
cc
e
s
s
co
n
tr
o
l
Dee
p
m
e
tr
ic
lear
n
i
n
g
Face
r
ec
o
g
n
itio
n
QR
co
d
es
R
asp
b
er
r
y
P
i 4
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
:
Mu
h
a
m
m
ad
A
l
h
a
m
m
a
m
i
Dep
ar
t
m
en
t o
f
C
o
m
m
u
n
icatio
n
,
Hig
h
er
I
n
s
tit
u
te
f
o
r
A
p
p
lied
Scien
ce
s
a
n
d
T
ec
h
n
o
lo
g
y
P
.
O.
B
o
x
3
1
9
8
3
,
Dam
asc
u
s
,
S
y
r
ia
E
m
ail:
M
u
h
a
m
m
ad
.
A
l
h
a
m
m
a
m
i
@
h
iast
.
ed
u
.
s
y
1.
I
NT
RO
D
UCT
I
O
N
On
e
o
f
th
e
m
o
s
t
i
m
p
o
r
tan
t
asp
ec
ts
o
f
b
u
ild
in
g
s
ec
u
r
it
y
i
s
ac
ce
s
s
co
n
tr
o
l.
C
o
n
v
e
n
tio
n
a
l
s
y
s
te
m
s
g
en
er
all
y
d
ep
en
d
o
n
p
ass
w
o
r
d
s
,
k
e
y
s
,
o
r
ca
r
d
s
t
h
at
ca
n
b
e
m
is
p
lace
d
,
s
to
len
,
o
r
f
o
r
g
o
tte
n
.
Facial
r
ec
o
g
n
itio
n
tech
n
o
lo
g
ies
h
av
e
b
ee
n
e
m
p
lo
y
ed
m
o
r
e
latel
y
an
d
p
r
o
v
id
e
a
m
o
r
e
u
s
er
-
f
r
ien
d
l
y
a
n
d
s
ec
u
r
e
o
p
tio
n
.
No
n
eth
ele
s
s
,
t
h
er
e
ar
e
s
till
is
s
u
es
w
it
h
th
e
s
e
s
y
s
te
m
s
'
ac
cu
r
ac
y
an
d
p
r
o
ce
s
s
in
g
d
e
m
an
d
s
.
Mo
r
eo
v
er
,
th
e
y
ar
e
u
n
ab
le
to
r
estrict
ac
ce
s
s
f
o
r
u
n
id
en
ti
f
ied
f
ac
es.
Nu
m
er
o
u
s
r
esear
ch
es
h
a
v
e
lo
o
k
ed
o
n
t
h
e
ap
p
licatio
n
o
f
f
a
ce
r
ec
o
g
n
itio
n
to
ac
ce
s
s
co
n
t
r
o
l.
T
h
ese
ef
f
o
r
t
s
h
a
v
e
h
elp
ed
to
lo
w
er
th
e
p
r
o
ce
s
s
i
n
g
r
eq
u
ir
e
m
e
n
t
s
an
d
in
cr
ea
s
e
t
h
e
ac
cu
r
ac
y
o
f
f
ac
ial
r
ec
o
g
n
itio
n
s
y
s
te
m
s
.
T
h
e
y
d
o
n
o
t,
h
o
w
ev
er
,
ad
d
r
ess
th
e
p
r
o
b
lem
o
f
li
m
iti
n
g
ac
ce
s
s
f
o
r
u
n
k
n
o
w
n
p
er
s
o
n
s
a
n
d
in
s
tea
d
co
n
ce
n
tr
ate
m
o
s
t
l
y
o
n
w
e
ll
-
k
n
o
w
n
f
ac
es.
Ho
w
e
v
er
,
th
er
e
m
a
y
b
e
a
w
o
r
k
ar
o
u
n
d
f
o
r
th
i
s
is
s
u
e
as
QR
co
d
es
h
av
e
b
ee
n
e
m
p
lo
y
ed
as
a
n
i
n
p
u
t
i
n
ter
f
ac
e
f
o
r
a
n
u
m
b
er
o
f
e
m
b
ed
d
ed
p
r
o
g
r
am
s
.
A
d
eta
ch
ab
le
co
lo
r
t
w
o
-
d
i
m
en
s
io
n
al
co
d
e
d
esi
g
n
is
p
r
esen
ted
[
1
]
in
w
h
ich
th
e
a
u
th
o
r
s
p
r
ese
n
ted
a
s
tate
-
of
-
th
e
-
ar
t
tec
h
n
iq
u
e
f
o
r
p
r
o
d
u
cin
g
t
w
o
-
d
i
m
en
s
io
n
al
c
o
d
es
w
it
h
d
i
s
ti
n
ct
co
lo
r
co
m
p
o
n
en
t
s
.
I
n
f
o
r
m
atio
n
o
n
th
e
p
o
ten
tial
b
en
e
f
its
an
d
ap
p
licatio
n
s
o
f
t
h
is
d
esi
g
n
is
p
r
o
v
id
ed
b
y
th
e
r
esear
c
h
.
R
esear
ch
b
y
Y
a
n
g
et
a
l.
[
2
]
i
n
tr
o
d
u
ce
s
a
t
w
o
-
di
m
en
s
io
n
a
l
co
d
e
h
ier
ar
ch
ical
e
n
cr
y
p
tio
n
alg
o
r
ith
m
b
ased
o
n
attr
ib
u
te
en
cr
y
p
tio
n
.
T
h
e
au
th
o
r
s
p
r
o
p
o
s
e
attr
ib
u
te
-
b
ased
en
cr
y
p
tio
n
as
an
en
cr
y
p
tio
n
m
et
h
o
d
to
in
cr
ea
s
e
t
h
e
s
ec
u
r
it
y
o
f
t
wo
-
d
i
m
e
n
s
io
n
al
co
d
es.
T
h
e
s
tu
d
y
e
m
p
h
asize
s
th
e
ad
v
a
n
ta
g
es
o
f
u
s
i
n
g
th
i
s
h
ier
ar
ch
ical
e
n
cr
y
p
tio
n
m
e
th
o
d
to
p
r
o
tect
s
en
s
iti
v
e
i
n
f
o
r
m
atio
n
.
A
lo
g
is
tic
i
n
f
o
r
m
atio
n
p
r
iv
ac
y
p
r
o
tectio
n
s
y
s
te
m
b
ased
o
n
en
cr
y
p
ted
QR
co
d
e
is
d
escr
ib
ed
[
3
]
.
T
h
ey
p
r
o
v
id
e
a
m
et
h
o
d
th
at
p
r
o
tect
s
th
e
co
n
f
id
en
tialit
y
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
R
ec
o
n
f
i
g
u
r
ab
le
&
E
m
b
ed
d
ed
Sy
s
t
I
SS
N:
2089
-
4864
R
o
b
u
s
t e
mb
ed
d
e
d
a
cc
ess
co
n
t
r
o
l sys
tem
b
a
s
ed
o
n
fa
ce
a
n
d
e
n
cryp
ted
QR
w
ith
…
(
S
a
mir
M
a
r
w
a
n
Ha
mma
mi
)
587
o
f
lo
g
is
tical
d
ata
b
y
u
s
i
n
g
en
cr
y
p
ted
QR
co
d
es.
T
h
e
s
y
s
te
m
d
esig
n
an
d
its
p
o
s
s
ib
le
u
s
e
s
in
p
r
o
tectin
g
s
en
s
iti
v
e
d
ata
ar
e
d
escr
ib
ed
b
y
th
e
au
t
h
o
r
s
.
R
esear
ch
b
y
L
ia
n
g
et
a
l.
[
4
]
o
f
f
er
a
d
esig
n
o
f
s
y
s
te
m
a
n
d
k
e
y
al
g
o
r
ith
m
s
f
o
r
2
D
co
d
e
r
ec
o
g
n
itio
n
w
it
h
v
ar
io
u
s
s
ec
u
r
it
y
le
v
els.
T
h
e
au
th
o
r
s
p
r
o
v
id
e
a
m
et
h
o
d
th
at
co
m
b
i
n
es
t
w
o
-
d
i
m
e
n
s
io
n
al
co
d
e
r
ec
o
g
n
itio
n
w
it
h
v
ar
y
i
n
g
s
ec
u
r
it
y
lev
e
ls
.
T
h
ey
h
ig
h
li
g
h
t
th
e
s
ig
n
i
f
ica
n
c
e
o
f
cu
s
to
m
ized
s
ec
u
r
it
y
lev
el
s
w
h
ile
g
o
in
g
o
v
er
th
e
s
y
s
te
m
's ar
ch
itectu
r
al
co
n
c
er
n
s
a
n
d
i
m
p
o
r
tan
t
alg
o
r
it
h
m
s
.
R
esear
ch
b
y
X
u
et
a
l.
[
5
]
d
etail
th
e
cr
ea
tio
n
an
d
u
s
e
o
f
a
s
y
s
te
m
f
o
r
id
en
ti
f
y
i
n
g
t
w
o
-
d
i
m
e
n
s
io
n
al
co
d
es
t
h
at
r
u
n
s
o
n
a
m
o
b
ile
p
h
o
n
e.
T
h
e
s
y
s
te
m
ar
ch
itect
u
r
e
an
d
its
p
o
s
s
ib
le
u
s
es i
n
a
n
u
m
b
er
o
f
d
o
m
ain
s
ar
e
co
v
er
ed
in
th
e
p
ap
er
.
R
esear
ch
b
y
Z
h
u
et
a
l.
[
6
]
talk
ab
o
u
t
th
e
ap
p
licatio
n
o
f
QR
co
d
e
r
ec
o
g
n
itio
n
tech
n
o
lo
g
y
in
ex
p
r
ess
s
ig
n
.
T
h
e
u
s
e
o
f
Q
R
co
d
e
r
ec
o
g
n
itio
n
tec
h
n
o
lo
g
y
in
ex
p
r
es
s
s
i
g
n
s
y
s
te
m
s
i
s
e
x
a
m
in
ed
b
y
t
h
e
w
r
iter
s
.
T
h
e
y
d
r
a
w
atten
tio
n
to
th
e
b
en
ef
it
s
an
d
r
ea
l
-
w
o
r
ld
ap
p
licatio
n
s
o
f
u
tili
zi
n
g
QR
co
d
es
f
o
r
ef
f
ec
tiv
e
ex
p
r
ess
s
ig
n
p
r
o
ce
d
u
r
es.
R
esear
ch
b
y
Ho
n
g
[
1
]
p
r
esen
ts
t
h
e
p
ap
er
"
d
esig
n
o
f
a
n
i
n
t
ellig
e
n
t
ac
ce
s
s
co
n
tr
o
l
s
y
s
te
m
b
ased
o
n
DE
S
en
cr
y
p
ted
QR
c
o
d
e"
at
t
h
e
2
0
2
0
I
E
E
E
I
n
ter
n
atio
n
al
C
o
n
f
er
en
ce
o
n
A
d
v
a
n
ce
s
i
n
E
lectr
ical
E
n
g
i
n
ee
r
i
n
g
an
d
C
o
m
p
u
ter
A
p
p
licatio
n
s
.
T
h
e
au
th
o
r
s
u
g
g
es
ts
u
s
i
n
g
D
E
S
-
e
n
cr
y
p
ted
QR
co
d
es
i
n
a
n
i
n
telli
g
en
t
ac
ce
s
s
co
n
tr
o
l
s
y
s
te
m
.
T
h
e
s
y
s
te
m
ar
ch
itect
u
r
e,
i
m
p
le
m
e
n
tat
io
n
s
p
ec
if
ic
s
,
an
d
p
o
s
s
ib
le
u
s
es
in
ac
ce
s
s
co
n
tr
o
l
s
ce
n
ar
io
s
ar
e
p
r
esen
ted
in
t
h
i
s
s
tu
d
y
.
E
v
en
w
it
h
t
h
ese
d
ev
e
lo
p
m
en
t
s
,
ac
ce
s
s
co
n
tr
o
l
tech
n
o
lo
g
y
m
a
y
s
ti
ll
b
e
i
m
p
r
o
v
ed
.
I
t
i
s
p
o
s
s
ib
le
to
i
m
p
r
o
v
e
f
ac
ial
r
ec
o
g
n
it
io
n
s
y
s
te
m
s
'
ac
c
u
r
ac
y
an
d
co
m
p
u
t
in
g
e
f
f
icie
n
c
y
.
F
u
r
th
er
m
o
r
e,
li
m
it
in
g
ac
ce
s
s
f
o
r
u
n
f
a
m
iliar
f
ac
es i
s
a
s
er
io
u
s
p
r
o
b
lem
t
h
at
h
as
n
o
t r
ec
eiv
ed
en
o
u
g
h
atten
tio
n
i
n
th
e
l
iter
atu
r
e
.
T
h
is
p
ap
er
s
u
g
g
e
s
ts
a
n
o
v
el
f
i
x
f
o
r
th
e
s
e
is
s
u
e
s
.
I
t
d
escr
ib
es
an
e
m
b
ed
d
ed
ac
ce
s
s
co
n
tr
o
l
s
y
s
te
m
t
h
at
r
u
n
s
o
n
th
e
C
P
U
o
f
an
i
n
ex
p
e
n
s
i
v
e
R
asp
b
er
r
y
P
i
4
co
m
p
u
te
r
an
d
i
n
teg
r
ate
s
f
ac
e
r
ec
o
g
n
iti
o
n
an
d
Q
R
co
d
es.
T
h
is
m
et
h
o
d
p
r
o
v
id
es
ac
ce
s
s
co
n
tr
o
l
f
o
r
u
n
k
n
o
w
n
f
ac
es
i
n
ad
d
itio
n
to
i
m
p
r
o
v
in
g
t
h
e
r
o
b
u
s
t
n
ess
o
f
ac
ce
s
s
co
n
tr
o
l
o
v
er
a
f
ac
ial
r
ec
o
g
n
iti
o
n
-
o
n
l
y
s
y
s
te
m
.
T
h
e
s
y
s
te
m
o
p
er
ates
ac
co
r
d
in
g
to
th
e
f
o
llo
w
i
n
g
p
r
o
ce
d
u
r
es
an
d
ca
n
b
e
r
ec
o
n
f
ig
u
r
ed
to
ad
ap
t
to
d
if
f
er
en
t
ac
ce
s
s
co
n
tr
o
l
r
eq
u
ir
em
e
n
t
s
o
r
s
ce
n
ar
io
s
:
i)
t
h
e
f
ac
es
o
f
all
e
m
p
lo
y
ee
s
ar
e
r
ec
o
r
d
ed
;
ii)
e
ac
h
e
m
p
lo
y
ee
i
s
p
r
o
v
id
ed
w
i
th
a
s
ec
u
r
e
Q
R
co
d
e
;
iii)
f
ea
tu
r
es
ar
e
ex
tr
ac
ted
o
f
f
li
n
e
f
o
r
ea
ch
e
m
p
lo
y
ee
an
d
s
to
r
ed
in
th
e
s
y
s
te
m
.
T
h
ese
f
ea
tu
r
es
w
ill
b
e
u
s
ed
f
o
r
r
ec
o
g
n
itio
n
i
n
r
ea
l
ti
m
e
;
iv
)
a
d
atab
ase
d
ef
i
n
i
n
g
all
e
m
p
lo
y
ee
p
er
m
is
s
io
n
s
is
b
u
ilt
o
f
f
li
n
e
u
s
in
g
s
tr
u
ct
u
r
ed
q
u
er
y
lan
g
u
a
g
e
(
SQ
L
i
te
)
;
v
)
A
n
y
e
m
p
lo
y
ee
e
n
ter
in
g
o
r
ex
iti
n
g
th
e
co
n
tr
o
l s
y
s
te
m
m
u
s
t
s
h
o
w
h
is
/
h
er
o
w
n
s
ec
u
r
e
Q
R
co
d
e
b
esid
es b
ein
g
r
ec
o
g
n
is
ed
b
y
h
is
/h
er
f
ac
e.
T
h
e
e
m
p
lo
y
ee
'
s
Q
R
co
d
e
m
u
s
t
m
atc
h
h
i
s
f
ac
e,
p
l
u
s
h
e
h
a
s
p
er
m
is
s
io
n
to
p
ass
t
h
e
co
n
tr
o
l
s
y
s
te
m
;
v
i)
g
u
est
s
ar
e
p
r
o
v
id
ed
w
it
h
a
d
ir
ec
t
o
n
e
ti
m
e
p
ass
w
o
r
d
(
OT
P)
b
ased
QR
co
d
e,
w
h
ic
h
a
llo
w
s
th
e
m
to
ac
ce
s
s
o
n
ce
d
u
r
i
n
g
a
s
p
ec
if
ic
ti
m
e
; a
n
d
v
ii)
t
h
e
s
y
s
te
m
r
ec
o
r
d
s
all
th
e
lo
g
s
o
f
all
f
u
n
ctio
n
s
.
T
h
e
f
o
llo
w
i
n
g
s
ec
t
io
n
s
o
f
t
h
is
m
a
n
u
s
cr
ip
t
w
ill
d
etail
th
e
d
es
ig
n
a
n
d
i
m
p
le
m
en
ta
tio
n
o
f
o
u
r
p
r
o
p
o
s
ed
s
y
s
te
m
.
W
e
w
ill
p
r
esen
t
e
x
p
er
i
m
en
tal
r
esu
l
ts
d
e
m
o
n
s
tr
ati
n
g
th
e
s
y
s
te
m
’
s
p
er
f
o
r
m
an
ce
,
i
n
clu
d
i
n
g
its
s
m
o
o
th
o
p
er
atio
n
at
a
f
r
a
m
e
r
ate
o
f
8
.
2
7
FP
S.
W
e
w
ill
al
s
o
d
is
cu
s
s
h
o
w
o
u
r
s
y
s
te
m
s
tr
en
g
t
h
en
s
s
ec
u
r
it
y
m
ea
s
u
r
es,
i
m
p
r
o
v
es
u
s
er
ex
p
er
ien
ce
,
an
d
o
u
tp
er
f
o
r
m
s
co
n
v
e
n
tio
n
al
ac
ce
s
s
co
n
tr
o
l
ap
p
r
o
ac
h
es,
m
a
k
in
g
it
an
attr
ac
ti
v
e
o
p
tio
n
f
o
r
m
an
y
b
u
s
in
e
s
s
e
s
.
2.
RE
S
E
ARCH
M
E
T
H
O
D
2
.
1
.
F
un
ct
io
na
litie
s
o
f
f
a
ce
r
ec
o
g
nitio
n
T
h
e
g
o
al
is
to
co
n
s
tr
u
ct
an
e
d
g
e
-
o
p
er
atin
g
f
ac
ia
l
r
ec
o
g
n
iti
o
n
s
y
s
te
m
u
s
i
n
g
lo
w
-
co
s
t
h
ar
d
w
ar
e
lik
e
th
e
R
a
s
p
b
er
r
y
P
i4
.
T
h
is
m
ea
n
s
th
at
it
m
u
s
t
b
e
ap
p
r
o
ac
h
ed
f
ac
e
r
ec
o
g
n
itio
n
as
a
o
n
e
-
ti
m
e
lear
n
in
g
j
o
b
,
w
h
ic
h
is
id
ea
l
f
o
r
d
ee
p
m
etr
ic
lear
n
i
n
g
(
DM
L
)
.
DM
L
tr
ai
n
s
a
n
eu
r
al
n
et
w
o
r
k
to
lear
n
a
n
e
m
b
ed
d
in
g
o
f
a
d
ata
in
p
u
t,
allo
w
i
n
g
d
is
ta
n
ce
o
r
s
i
m
ilar
it
y
b
et
w
ee
n
d
ata
p
o
in
ts
to
b
e
m
ea
s
u
r
ed
.
T
h
is
m
ea
n
s
th
at,
i
n
t
h
e
co
n
te
x
t
o
f
f
ac
e
r
ec
o
g
n
itio
n
,
o
n
e
m
u
s
t
lear
n
a
f
u
n
ctio
n
t
h
at
ca
n
co
n
v
er
t
an
in
p
u
t
i
m
a
g
e
o
f
a
f
ac
e
in
to
a
p
o
in
t
in
a
h
ig
h
-
d
i
m
en
s
io
n
al
s
p
ac
e
w
h
er
e
i
m
a
g
es o
f
t
h
e
s
a
m
e
f
ac
e
ar
e
w
id
el
y
s
ep
ar
ated
f
r
o
m
o
n
e
a
n
o
th
er
.
2
.
1
.
1
.
Cre
a
t
ing
a
d
a
t
a
s
et
T
h
er
e
ar
e
a
f
e
w
i
m
p
o
r
tan
t
p
r
o
ce
d
u
r
es
an
d
th
in
g
s
to
k
ee
p
i
n
m
i
n
d
w
h
ile
co
m
p
il
in
g
a
d
ataset
o
f
th
e
au
th
o
r
ized
i
n
d
iv
id
u
als
f
o
r
th
is
ap
p
licatio
n
.
Us
u
all
y
,
t
h
e
p
r
o
ce
d
u
r
e
b
eg
in
s
w
it
h
d
ata
g
ath
er
i
n
g
,
in
w
h
ic
h
w
eb
ca
m
p
h
o
to
g
r
ap
h
s
o
f
f
ac
e
s
ar
e
tak
en
.
A
b
r
o
ad
r
an
g
e
o
f
ch
an
g
e
s
in
s
ta
n
ce
,
f
ac
e
e
x
p
r
ess
io
n
,
li
g
h
ti
n
g
,
o
cc
lu
s
io
n
,
a
n
d
r
eso
l
u
tio
n
s
h
o
u
ld
id
ea
ll
y
b
e
co
v
er
ed
b
y
t
h
e
s
e
p
h
o
to
g
r
ap
h
s
.
T
h
e
p
er
tin
en
t
d
etails
ab
o
u
t
ea
c
h
f
ac
e
ar
e
th
en
tag
g
ed
in
to
th
e
g
ath
er
ed
p
h
o
to
s
.
B
ec
au
s
e
it
s
u
p
p
lies
th
e
g
r
o
u
n
d
tr
u
t
h
lab
els
r
eq
u
ir
ed
f
o
r
m
ac
h
in
e
lear
n
i
n
g
m
o
d
el
tr
ain
i
n
g
,
t
h
is
a
n
n
o
tatio
n
p
r
o
ce
d
u
r
e
is
ess
e
n
tial.
2
.
1
.
2
.
F
a
ce
det
ec
t
i
o
n
T
h
e
co
m
p
u
ter
v
i
s
io
n
p
r
o
b
le
m
o
f
f
ac
e
d
etec
tio
n
is
d
etec
tin
g
an
d
r
ec
o
g
n
izin
g
h
u
m
an
f
ac
es
in
d
ig
ital
p
h
o
to
s
o
r
m
o
v
ies.
All
f
ac
ial
a
n
al
y
s
i
s
alg
o
r
it
h
m
s
,
s
u
c
h
as
t
h
o
s
e
f
o
r
f
ac
e
ali
g
n
m
e
n
t,
r
ec
o
g
n
itio
n
,
v
er
i
f
icatio
n
,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
9
-
4864
I
n
t J
R
ec
o
n
f
i
g
u
r
ab
le
&
E
m
b
ed
d
ed
Sy
s
t
,
Vo
l.
13
,
No
.
3
,
No
v
e
m
b
er
20
24
:
586
-
59
4
588
an
d
p
ar
s
in
g
,
s
tar
t
w
i
th
th
i
s
p
h
ase.
T
h
e
m
ai
n
o
b
j
ec
tiv
e
o
f
f
ac
e
d
etec
tio
n
g
iv
en
a
d
ig
ital
i
m
ag
e
is
to
f
in
d
o
u
t
if
th
e
i
m
ag
e
co
n
tain
s
an
y
f
ac
es.
T
h
er
e
ar
e
s
ev
er
al
m
eth
o
d
s
f
o
r
f
ac
e
d
etec
tio
n
[
7
]
–
[
9
]
,
ea
ch
w
it
h
it
s
s
tr
e
n
g
th
s
an
d
w
ea
k
n
e
s
s
es.
So
m
e
o
f
th
e
m
o
s
t c
o
m
m
o
n
tec
h
n
iq
u
es in
cl
u
d
e:
−
Haar
-
b
ased
tech
n
iq
u
e:
t
h
i
s
m
et
h
o
d
is
s
p
ee
d
y
an
d
r
eq
u
ir
es
lo
w
co
m
p
u
tatio
n
al
r
eso
u
r
ce
s
,
m
a
k
in
g
it
s
u
itab
le
f
o
r
r
eso
u
r
ce
-
co
n
s
tr
ai
n
ed
d
ev
ices.
Ho
w
e
v
er
,
it
is
h
ig
h
l
y
p
r
o
n
e
to
f
alse
-
p
o
s
iti
v
e
d
etec
tio
n
s
a
n
d
r
eq
u
ir
es
m
a
n
u
a
l tu
n
i
n
g
.
−
Mu
lti
-
ta
s
k
ca
s
ca
d
ed
co
n
v
o
l
u
ti
o
n
al
n
eu
r
al
n
e
t
w
o
r
k
s
(
MT
C
NN)
:
is
a
d
ee
p
lear
n
in
g
-
b
ased
m
et
h
o
d
th
at
h
as
ac
h
iev
ed
s
tate
-
of
-
t
h
e
-
ar
t
r
e
s
u
l
ts
o
n
s
tan
d
ar
d
b
en
ch
m
ar
k
f
ac
e
d
etec
tio
n
d
atasets
.
I
t
i
s
m
o
r
e
co
m
p
lex
a
n
d
co
m
p
u
tatio
n
all
y
in
te
n
s
iv
e
t
h
a
n
th
e
h
aa
r
-
b
ased
tec
h
n
iq
u
e
b
u
t
o
f
f
er
s
h
i
g
h
er
ac
cu
r
ac
y
.
−
His
to
g
r
a
m
o
f
o
r
ien
ted
g
r
ad
ie
n
ts
(H
o
G)
+
s
u
p
p
o
r
t
v
ec
to
r
m
a
ch
in
e
(
S
VM
)
:
T
h
is
m
et
h
o
d
is
also
w
id
el
y
u
s
ed
in
f
ac
e
d
etec
tio
n
.
I
t
in
v
o
lv
es
ex
tr
ac
ti
n
g
H
o
G
f
ea
tu
r
e
s
f
r
o
m
th
e
i
m
a
g
e
an
d
u
s
i
n
g
an
SVM
f
o
r
class
i
f
icatio
n
.
Stan
d
ar
d
s
f
o
r
f
ac
e
d
etec
tio
n
o
f
ten
in
v
o
l
v
e
en
s
u
r
in
g
th
e
q
u
alit
y
a
n
d
d
iv
er
s
it
y
o
f
th
e
i
m
ag
e
s
.
T
h
e
Natio
n
al
I
n
s
tit
u
te
o
f
Stan
d
ar
d
s
an
d
T
ec
h
n
o
lo
g
y
(
NI
ST
)
p
r
o
v
id
es
f
ac
ial
r
ec
o
g
n
i
tio
n
tec
h
n
o
lo
g
y
g
u
id
e
li
n
es
[
1
0
]
,
w
h
ic
h
i
n
clu
d
e
f
ac
e
d
etec
tio
n
.
T
h
ese
s
tan
d
ar
d
s
en
s
u
r
e
th
e
tech
n
o
lo
g
y
i
s
ac
cu
r
ate,
r
eliab
le,
an
d
ca
n
b
e
u
s
ed
s
ea
m
les
s
l
y
ac
r
o
s
s
d
ev
ice
s
.
T
h
e
b
en
ef
its
o
f
f
ac
e
d
etec
ti
o
n
ar
e
n
u
m
er
o
u
s
.
T
h
e
y
en
h
an
ce
th
e
ac
cu
r
ac
y
o
f
f
ac
ial
r
ec
o
g
n
itio
n
s
y
s
te
m
s
b
y
allo
w
i
n
g
t
h
e
m
o
d
el
to
lear
n
d
i
v
er
s
e
f
ea
t
u
r
es
o
f
h
u
m
a
n
f
ac
es.
T
h
is
i
m
p
r
o
v
es
p
er
f
o
r
m
a
n
ce
i
n
r
ec
o
g
n
is
i
n
g
d
if
f
er
en
t
i
n
d
i
v
id
u
als
[
1
1
]
–
[
1
3
]
.
Fu
r
th
er
m
o
r
e,
f
ac
e
d
etec
tio
n
is
an
e
s
s
e
n
t
ial
to
o
l
f
o
r
f
ac
ial
r
ec
o
g
n
itio
n
tech
n
o
lo
g
y
,
p
r
o
v
id
in
g
t
h
e
r
eq
u
i
s
ite
tr
ain
in
g
m
at
er
ials
f
o
r
ac
cu
r
atel
y
id
en
t
if
y
i
n
g
in
d
i
v
id
u
a
ls
'
f
ac
es
in
r
ea
l
-
w
o
r
ld
s
ce
n
ar
io
s
.
I
n
ter
m
s
o
f
co
m
p
u
tat
io
n
al
n
ee
d
s
,
d
if
f
er
en
t
f
ac
e
d
etec
tio
n
m
eth
o
d
s
h
a
v
e
d
if
f
er
en
t
r
eq
u
ir
e
m
en
ts
.
Fo
r
in
s
ta
n
ce
,
Haa
r
-
b
ased
tech
n
iq
u
es
ar
e
less
co
m
p
u
tatio
n
al
l
y
i
n
ten
s
i
v
e
an
d
ca
n
b
e
r
u
n
o
n
e
m
b
ed
d
ed
d
ev
ices.
I
n
co
n
tr
ast,
d
ee
p
lear
n
in
g
-
b
ased
m
et
h
o
d
s
lik
e
MT
C
NN
r
eq
u
ir
e
m
o
r
e
co
m
p
u
tatio
n
al
r
eso
u
r
c
es
b
u
t
o
f
f
er
h
i
g
h
er
ac
cu
r
ac
y
.
T
o
u
s
e
a
f
ac
e
d
etec
tio
n
m
et
h
o
d
,
it
is
ty
p
ical
l
y
n
e
ce
s
s
ar
y
to
lo
ad
th
e
f
ac
e
d
etec
tio
n
m
o
d
el
in
to
th
e
en
v
ir
o
n
m
e
n
t,
p
r
ep
r
o
ce
s
s
th
e
i
m
ag
e
s
(
s
u
c
h
as
r
es
izin
g
a
n
d
n
o
r
m
al
is
atio
.
)
,
an
d
t
h
en
f
ee
d
t
h
e
m
i
n
to
t
h
e
m
o
d
el
f
o
r
f
ac
e
d
etec
tio
n
.
O
n
ce
th
e
f
a
ce
s
ar
e
d
etec
ted
,
th
e
y
ca
n
b
e
u
s
ed
f
o
r
f
u
r
t
h
er
p
r
o
ce
s
s
in
g
o
r
an
al
y
s
i
s
.
His
to
g
r
a
m
o
f
o
r
ie
n
ted
g
r
ad
ien
ts
m
e
th
o
d
"
Ho
G"
,
p
u
b
lis
h
ed
i
n
2
0
0
5
[
1
4
]
,
is
u
s
ed
b
ec
au
s
e
o
f
it
s
s
p
ee
d
,
h
ig
h
d
etec
tio
n
ac
cu
r
ac
y
a
n
d
l
o
w
f
al
s
e
p
o
s
itiv
e
r
ate.
T
h
e
in
p
u
t
o
f
th
i
s
s
tag
e
i
s
a
g
r
e
y
i
m
a
g
e,
an
d
th
e
o
u
tp
u
t
s
ar
e
ar
ea
s
w
h
er
e
f
ac
es
ar
e
lo
ca
ted
,
w
h
ic
h
w
ill
b
e
th
e
in
p
u
t
s
o
f
th
e
n
ex
t
s
tag
e.
Fo
r
ea
ch
p
ix
el
in
th
e
g
r
e
y
i
m
a
g
e,
Ho
G
f
ir
s
t
lo
o
k
s
at
t
h
e
s
u
r
r
o
u
n
d
in
g
p
ix
el
s
,
co
m
p
ar
es
th
e
d
ar
k
n
e
s
s
o
f
t
h
e
p
ix
el
w
it
h
its
s
u
r
r
o
u
n
d
i
n
g
s
an
d
d
r
a
w
s
an
ar
r
o
w
to
w
ar
d
s
t
h
e
d
ar
k
es
t
ar
ea
.
R
ep
ea
tin
g
t
h
is
p
r
o
ce
s
s
o
n
all
th
e
i
m
ag
e
p
ix
el
s
g
i
v
es
a
s
et
o
f
ar
r
o
w
s
ca
lled
a
g
r
ad
ien
t t
h
at
in
d
icate
s
t
h
e
f
l
o
w
f
r
o
m
th
e
b
r
i
g
h
te
s
t r
eg
io
n
t
o
th
e
d
ar
k
est r
eg
io
n
.
Nex
t,
Ho
G
d
iv
id
es th
e
i
m
a
g
e
in
to
1
6
×
1
6
p
ix
el
s
q
u
ar
es
a
n
d
p
lace
s
o
n
l
y
o
n
e
ar
r
o
w
i
n
t
h
e
d
ir
ec
tio
n
o
f
t
h
e
d
o
m
i
n
an
t
ar
r
o
w
s
in
th
at
s
q
u
ar
e,
as
s
h
o
w
n
in
F
ig
u
r
e.
1
.
Fig
u
r
e
1
.
Gr
ad
ien
t
m
ap
2
.
1
.
3
.
F
a
ce
det
ec
t
i
o
n
Face
r
ep
o
s
itio
n
in
g
is
a
tech
n
o
lo
g
y
u
s
ed
in
co
m
p
u
ter
v
i
s
io
n
,
f
ac
ial
id
en
tific
atio
n
,
an
d
m
ed
ical
o
p
er
atio
n
s
.
I
t
is
o
f
ten
r
ef
er
r
ed
to
as
f
ac
e
r
esh
ap
in
g
o
r
f
ac
e
tr
an
s
f
o
r
m
atio
n
.
I
t
en
tail
s
p
h
y
s
i
ca
ll
y
m
o
d
i
f
y
i
n
g
a
f
ac
e
'
s
s
tr
u
ct
u
r
e
o
r
r
ea
r
r
an
g
in
g
th
e
o
r
ien
tatio
n
o
r
p
lace
m
e
n
t o
f
f
ac
ia
l c
h
ar
ac
ter
is
t
ics i
n
a
p
ictu
r
e.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
R
ec
o
n
f
i
g
u
r
ab
le
&
E
m
b
ed
d
ed
Sy
s
t
I
SS
N:
2089
-
4864
R
o
b
u
s
t e
mb
ed
d
e
d
a
cc
ess
co
n
t
r
o
l sys
tem
b
a
s
ed
o
n
fa
ce
a
n
d
e
n
cryp
ted
QR
w
ith
…
(
S
a
mir
M
a
r
w
a
n
Ha
mma
mi
)
589
Face
r
ep
o
s
itio
n
i
n
g
h
as
s
ev
er
al
ad
v
an
ta
g
es.
B
y
g
u
ar
an
tee
in
g
th
at
f
ac
es
ar
e
p
o
s
itio
n
ed
co
n
s
i
s
ten
t
l
y
,
i
t
en
h
a
n
ce
s
t
h
e
ef
f
icien
c
y
o
f
f
a
cial
r
ec
o
g
n
itio
n
alg
o
r
it
h
m
s
in
co
m
p
u
ter
v
i
s
io
n
.
T
h
is
f
ac
ilit
ates
th
e
alg
o
r
ith
m
'
s
ab
ilit
y
to
m
atc
h
a
f
ac
e
in
a
d
atab
ase
w
ith
an
i
n
p
u
t
f
ac
e.
I
n
th
e
m
ed
ical
i
n
d
u
s
tr
y
,
a
p
atie
n
t
'
s
lo
o
k
an
d
s
e
lf
-
es
tee
m
ca
n
b
e
g
r
ea
tl
y
e
n
h
a
n
ce
d
b
y
f
ac
e
r
ea
lig
n
m
e
n
t.
A
d
d
itio
n
al
l
y
,
i
t
ca
n
ad
d
r
ess
f
u
n
ctio
n
al
p
r
o
b
le
m
s
in
cl
u
d
in
g
tr
o
u
b
le
b
r
ea
th
in
g
o
r
ea
tin
g
.
T
h
er
e
ar
e
s
ev
er
al
u
s
e
s
f
o
r
f
ac
e
r
ep
o
s
itio
n
in
g
.
I
t
is
u
s
ed
to
in
cr
ea
s
e
th
e
p
r
ec
is
io
n
o
f
f
ac
e
d
etec
tio
n
a
n
d
r
ec
o
g
n
i
tio
n
al
g
o
r
it
h
m
s
i
n
co
m
p
u
ter
v
is
io
n
a
n
d
f
ac
ial
r
ec
o
g
n
itio
n
.
B
ef
o
r
e
p
u
ttin
g
f
ac
e
s
i
n
to
a
r
ec
o
g
n
itio
n
s
y
s
te
m
,
f
ac
e
r
ep
o
s
itio
n
in
g
,
f
o
r
ex
a
m
p
le,
m
i
g
h
t
n
o
r
m
alize
th
e
m
to
a
s
tan
d
ar
d
p
o
s
tu
r
e.
Face
r
ep
o
s
itio
n
in
g
i
s
u
s
ed
in
m
ed
ici
n
e
to
i
m
p
r
o
v
e
f
ac
ial
co
s
m
etics
o
r
ad
d
r
ess
f
u
n
ct
io
n
al
p
r
o
b
le
m
s
d
u
r
in
g
tr
ea
t
m
e
n
t
s
lik
e
f
ac
eli
f
t
s
an
d
o
r
th
o
g
n
at
h
ic
s
u
r
g
er
y
.
Fo
r
f
ac
e
r
ep
o
s
itio
n
in
g
,
m
an
y
m
et
h
o
d
s
ar
e
em
p
lo
y
ed
[
1
5
]
.
Face
s
in
p
ictu
r
es
ca
n
b
e
r
ep
o
s
itio
n
ed
in
co
m
p
u
ter
v
i
s
io
n
u
s
i
n
g
m
eth
o
d
s
in
clu
d
i
n
g
t
h
i
n
-
p
late
s
p
li
n
e
tr
an
s
f
o
r
m
atio
n
s
,
p
r
o
j
ec
tiv
e
tr
an
s
f
o
r
m
atio
n
s
,
an
d
af
f
in
e
tr
a
n
s
f
o
r
m
atio
n
s
.
T
h
ese
m
eth
o
d
s
co
n
v
er
t
an
i
n
p
u
t
i
m
ag
e
's
f
ac
e
c
h
ar
ac
ter
is
tic
s
to
a
r
ef
er
en
ce
i
m
a
g
e
's
s
tan
d
ar
d
s
et
o
f
f
ac
ial
f
ea
t
u
r
es
.
I
n
th
e
m
ed
ical
in
d
u
s
tr
y
,
alg
o
r
ith
m
s
ar
e
u
s
ed
to
o
r
g
an
ize
s
u
r
g
ical
tr
ea
t
m
e
n
t
s
b
ased
o
n
th
e
s
p
ec
i
f
ic
f
ac
ial
a
n
ato
m
y
o
f
t
h
e
p
atien
t
an
d
t
h
e
i
n
ten
d
ed
r
esu
lt.
R
ep
o
s
itio
n
in
g
f
ac
ial
f
ea
t
u
r
es r
e
f
er
s
to
s
h
i
f
ti
n
g
th
e
ir
d
ir
ec
tio
n
o
r
lo
ca
tio
n
.
T
h
is
ca
n
i
n
v
o
lv
e
s
c
alin
g
f
ea
tu
r
es
to
m
a
k
e
t
h
e
m
b
ig
g
er
o
r
s
m
aller
,
r
o
tatin
g
f
ea
t
u
r
es,
an
d
m
o
v
i
n
g
ele
m
e
n
ts
i
n
b
o
th
h
o
r
izo
n
tal
an
d
v
er
tical
d
ir
ec
tio
n
s
.
T
h
e
p
ar
ticu
lar
alg
o
r
it
h
m
o
r
p
r
o
ce
s
s
th
at
is
e
m
p
lo
y
ed
d
eter
m
i
n
es t
h
e
p
r
ec
is
e
ch
ar
ac
ter
is
t
i
cs o
f
th
e
r
elo
ca
ted
f
ac
e.
Face
r
ep
o
s
itio
n
in
g
is
t
y
p
ica
ll
y
p
er
f
o
r
m
ed
u
s
i
n
g
a
s
o
f
t
w
ar
e
lib
r
ar
y
th
at
i
m
p
le
m
en
ts
t
h
e
n
ec
ess
ar
y
alg
o
r
ith
m
s
.
T
h
e
u
s
er
p
r
o
v
id
es
an
in
p
u
t
i
m
a
g
e
an
d
a
r
ef
er
en
ce
i
m
ag
e,
a
n
d
th
e
s
o
f
t
w
ar
e
r
ep
o
s
itio
n
s
t
h
e
f
ac
e
i
n
th
e
in
p
u
t
i
m
a
g
e
to
m
atc
h
th
e
f
ac
e
in
th
e
r
ef
er
en
ce
i
m
a
g
e.
I
n
th
e
m
ed
ical
f
ield
,
f
ac
e
r
ep
o
s
itio
n
in
g
is
p
er
f
o
r
m
ed
b
y
a
tr
ai
n
ed
s
u
r
g
eo
n
.
T
h
e
s
u
r
g
eo
n
u
s
es
m
ed
ical
i
m
a
g
i
n
g
tec
h
n
o
lo
g
y
to
p
lan
a
n
d
p
er
f
o
r
m
t
h
e
n
ec
es
s
ar
y
s
u
r
g
ical
s
tep
s
.
I
n
th
is
p
r
o
j
ec
t,
p
o
s
t
to
is
o
lati
n
g
th
e
f
ac
e
r
eg
io
n
in
t
h
e
p
r
ev
io
u
s
s
tag
e
an
d
i
n
o
r
d
er
t
o
d
ea
l
w
it
h
t
h
e
r
o
tatio
n
,
ce
n
tr
in
g
an
d
s
ca
li
n
g
o
f
th
e
f
ac
e
s
,
th
e
"
f
ac
e
lan
d
m
a
r
k
esti
m
atio
n
"
alg
o
r
ith
m
b
y
K
az
e
m
i
an
d
S
u
lli
v
an
[
1
6
]
is
u
s
ed
to
f
in
d
6
8
f
ac
e
l
an
d
m
ar
k
s
s
h
o
w
n
i
n
F
ig
u
r
e
2
w
h
er
e
t
h
e
la
n
d
m
ar
k
s
ar
e
s
h
o
w
n
o
n
t
h
e
f
ac
e
i
n
Fig
u
r
e
2
(
a)
an
d
th
e
n
am
e
s
o
f
ea
ch
co
m
p
o
n
en
t
an
d
its
p
o
in
t
r
eg
io
n
in
Fi
g
u
r
e
2
(
b
)
.
E
x
a
m
p
les
o
f
th
e
s
e
lan
d
m
ar
k
s
ar
e
th
e
to
p
o
f
t
h
e
ch
in
,
t
h
e
ed
g
e
s
o
f
th
e
e
y
e,
th
e
e
d
g
es o
f
t
h
e
e
y
eb
r
o
w
,
a
n
d
o
th
e
r
s
.
(
a)
(
b
)
Fig
u
r
e
2
.
F
ac
e
lan
d
m
ar
k
esti
m
atio
n
(
a)
a
lg
o
r
ith
m
b
y
Kaz
e
m
i
an
d
Su
lli
v
a
n
[
1
6
]
o
n
th
e
f
ac
e
an
d
(
b
)
n
a
m
e
o
f
ea
ch
co
m
p
o
n
e
n
t a
n
d
it
s
p
o
in
t
r
eg
io
n
2
.
1
.
4
.
E
x
t
ra
ct
io
n o
f
f
a
cia
l
f
ea
t
ures
v
ec
t
o
r
A
b
r
an
ch
o
f
m
ac
h
in
e
lear
n
in
g
ca
lle
d
DM
L
is
co
n
ce
r
n
ed
w
i
th
ac
q
u
ir
in
g
d
is
ta
n
ce
m
ea
s
u
r
e
m
en
ts
f
o
r
th
e
p
u
r
p
o
s
e
o
f
co
m
p
ar
in
g
an
d
an
al
y
zi
n
g
d
ata
p
o
in
ts
in
h
i
g
h
-
d
i
m
e
n
s
io
n
al
s
p
ac
es
[
1
7
]
.
I
t
s
ee
k
s
to
co
m
p
r
eh
e
n
d
a
s
i
m
ilar
it
y
m
ea
s
u
r
e
th
at
u
s
es
s
a
m
p
les
to
ca
lcu
late
h
o
w
s
i
m
ilar
o
r
d
if
f
er
en
t
t
w
o
o
r
m
o
r
e
ite
m
s
ar
e.
Se
m
an
ti
c
tex
t
u
al
s
i
m
ilar
it
y
,
3
D
f
o
r
m
r
etr
iev
al,
s
p
ea
k
er
v
er
if
icat
io
n
,
f
ac
e
r
ec
o
g
n
itio
n
,
f
ac
e
v
er
if
icat
i
o
n
,
an
d
p
er
s
o
n
r
e
-
id
en
ti
f
icatio
n
ar
e
j
u
s
t
a
f
e
w
o
f
th
e
f
ield
s
in
w
h
ic
h
DM
L
h
as
b
ee
n
u
s
ed
.
I
t
is
a
f
u
n
d
a
m
e
n
tal
co
m
p
o
n
e
n
t
o
f
m
an
y
co
m
p
u
ter
v
is
io
n
ap
p
licatio
n
s
an
d
is
ap
p
lied
to
a
v
ar
iet
y
o
f
task
s
,
in
clu
d
i
n
g
in
f
o
r
m
at
io
n
r
etr
iev
al,
clu
s
ter
i
n
g
,
an
d
k
-
Nea
r
est Ne
ig
h
b
o
r
(
k
-
NN
)
clas
s
i
f
icatio
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
9
-
4864
I
n
t J
R
ec
o
n
f
i
g
u
r
ab
le
&
E
m
b
ed
d
ed
Sy
s
t
,
Vo
l.
13
,
No
.
3
,
No
v
e
m
b
er
20
24
:
586
-
59
4
590
T
h
e
ch
ar
ac
ter
is
tics
o
f
a
d
is
t
an
ce
m
ea
s
u
r
e
s
er
v
e
as
th
e
f
o
u
n
d
atio
n
f
o
r
DM
L
s
ta
n
d
ar
d
s
.
I
t
m
u
s
t
p
o
s
s
ess
tr
ia
n
g
le
i
n
eq
u
a
lit
y
,
s
y
m
m
etr
y
,
th
e
id
e
n
tit
y
o
f
i
n
d
is
ce
r
n
ib
ilit
y
,
an
d
n
o
n
-
n
e
g
ati
v
it
y
.
A
d
d
itio
n
all
y
,
n
et
w
o
r
k
ar
ch
itect
u
r
e,
s
a
m
p
li
n
g
p
o
lic
y
,
an
d
s
u
itab
le
d
is
ta
n
ce
m
ea
s
u
r
e
p
r
o
v
id
e
d
if
f
icu
l
ties
f
o
r
r
esear
ch
er
s
lo
o
k
in
g
to
en
h
a
n
ce
n
et
w
o
r
k
m
o
d
el
p
er
f
o
r
m
an
ce
.
DM
L
h
as
s
ev
er
al
ad
v
an
ta
g
e
s
.
I
t
u
s
es
ac
tiv
a
tio
n
f
u
n
ctio
n
s
to
g
iv
e
a
b
etter
s
o
lu
tio
n
f
o
r
n
o
n
li
n
ea
r
d
ata.
I
t
en
ab
les
co
m
p
u
ter
s
to
lea
r
n
w
e
ll
w
i
th
o
u
t
n
ee
d
in
g
to
b
e
ex
p
licitl
y
ta
u
g
h
t,
p
r
o
v
id
i
n
g
e
f
f
ec
tiv
e
an
s
w
er
s
to
ch
alle
n
g
i
n
g
is
s
u
e
s
an
d
m
as
s
i
v
e
v
o
lu
m
es
o
f
d
ata.
A
d
d
itio
n
a
l
l
y
,
it
en
h
an
ce
s
th
e
lear
n
t
m
etr
ic's
d
is
cr
i
m
i
n
ati
n
g
ca
p
ac
it
y
b
y
p
u
tti
n
g
f
o
r
t
h
cr
ea
tiv
e
s
a
m
p
li
n
g
p
la
n
s
o
r
lo
s
s
f
u
n
ctio
n
s
.
DM
L
u
s
e
s
m
ac
h
in
e
lear
n
i
n
g
t
o
au
to
m
atica
ll
y
cr
ea
te
tas
k
-
s
p
ec
if
ic
d
is
tan
ce
m
ea
s
u
r
es
f
r
o
m
(
w
ea
k
l
y
)
s
u
p
er
v
i
s
ed
d
ata.
T
h
en
,
a
v
ar
iet
y
o
f
ac
tiv
itie
s
m
a
y
b
e
ca
r
r
ied
o
u
t
u
s
in
g
th
e
ac
q
u
ir
ed
d
is
tan
ce
m
etr
ic.
Fro
m
th
e
in
p
u
t
d
o
m
ain
,
it
lear
n
s
a
m
ap
p
in
g
to
a
n
e
m
b
ed
d
i
n
g
s
p
ac
e
w
h
er
e
d
if
f
er
en
t
t
h
in
g
s
ar
e
s
it
u
ated
f
ar
a
w
a
y
f
r
o
m
o
n
e
an
o
th
er
a
n
d
s
e
m
a
n
tical
l
y
r
elate
d
o
n
es a
r
e
lo
ca
ted
ad
j
ac
e
n
t.
I
t
is
r
eq
u
ir
ed
to
ex
tr
ac
t
f
ea
tu
r
es
f
r
o
m
ea
ch
p
ict
u
r
e
an
d
p
r
o
d
u
ce
a
m
o
d
i
f
ied
e
m
b
ed
d
in
g
i
n
o
r
d
er
to
e
m
p
lo
y
DM
L
al
g
o
r
ith
m
s
.
A
v
ar
iet
y
o
f
lear
n
i
n
g
alg
o
r
it
h
m
s
ar
e
av
ailab
le,
in
cl
u
d
in
g
tr
i
p
let
m
in
in
g
,
tr
ip
let
s
a
m
p
li
n
g
,
an
d
Sia
m
e
s
e
n
et
w
o
r
k
s
an
d
r
elate
d
lo
s
s
f
u
n
c
tio
n
s
.
Dee
p
d
is
cr
im
i
n
a
n
t
an
al
y
s
is
t
ec
h
n
iq
u
es
b
ased
o
n
Fis
h
er
's
d
is
cr
i
m
i
n
a
n
t
a
n
al
y
s
is
ar
e
also
an
o
p
tio
n
.
L
ast
l
y
,
m
u
lti
-
m
o
d
al
D
ML
,
f
e
w
-
s
h
o
t
m
etr
ic
lear
n
i
n
g
,
a
n
d
g
eo
m
etr
ic
m
etr
ic
lear
n
i
n
g
u
s
i
n
g
n
e
u
r
al
n
et
w
o
r
k
s
m
a
y
al
l b
e
in
v
e
s
ti
g
ated
.
Dee
p
n
eu
r
al
n
et
w
o
r
k
-
b
ased
m
o
d
el
s
ac
h
ie
v
e
s
tate
-
of
-
t
h
e
-
a
r
t
p
er
f
o
r
m
an
ce
i
n
co
m
p
u
ter
v
is
io
n
tas
k
s
,
in
cl
u
d
in
g
f
ac
e
r
ec
o
g
n
itio
n
.
Ho
w
e
v
er
,
th
er
e
ar
e
t
w
o
o
b
s
tacle
s
in
t
h
i
s
ap
p
licatio
n
.
T
h
e
f
ir
s
t
o
n
e
is
t
h
at
R
asp
b
er
r
y
P
i
h
a
s
li
m
ited
co
m
p
u
tat
io
n
al
r
eso
u
r
ce
s
,
a
n
d
th
e
s
ec
o
n
d
o
b
s
tacle
i
s
t
h
at
t
h
e
n
u
m
b
er
o
f
tr
ain
i
n
g
i
m
a
g
e
ex
a
m
p
les
p
er
f
ac
e
is
r
elativ
el
y
s
m
all
to
lear
n
a
n
e
u
r
al
n
et
w
o
r
k
.
Su
c
h
a
p
r
o
b
lem
is
ca
lled
a
o
n
e
-
s
h
o
t
l
ea
r
n
in
g
p
r
o
b
lem
.
DM
L
g
en
er
ates
clo
s
e
f
ea
tu
r
e
v
ec
to
r
s
co
r
r
esp
o
n
d
in
g
to
f
ac
es
b
elo
n
g
in
g
to
th
e
s
a
m
e
p
er
s
o
n
w
h
ile
i
n
cr
ea
s
i
n
g
th
e
d
is
tan
ce
b
et
w
ee
n
th
o
s
e
b
elo
n
g
i
n
g
to
d
if
f
er
en
t
f
ac
es.
I
n
t
h
i
s
w
o
r
k
,
th
e
DM
L
ap
p
r
o
ac
h
i
s
b
ased
o
n
a
p
r
e
-
tr
ain
ed
R
esNe
t
-
3
4
n
eu
r
al
n
et
w
o
r
k
[
1
8
]
to
g
en
er
ate
f
ea
t
u
r
e
v
ec
to
r
s
o
f
1
2
8
in
teg
er
l
e
n
g
t
h
s
f
o
r
all
e
m
p
lo
y
ee
s
'
f
ac
e
s
in
t
h
e
d
ataset.
2
.
1
.
5
.
Rec
o
g
nizin
g
t
he
f
a
ce
As t
h
is
ap
p
licatio
n
u
s
e
s
t
h
e
D
ML
tec
h
n
iq
u
e;
s
o
t
h
e
la
s
t
s
ta
g
e
is
id
e
n
ti
f
y
in
g
t
h
e
p
er
s
o
n
w
it
h
a
n
i
m
a
g
e
w
h
ic
h
is
n
o
t
in
t
h
e
o
r
ig
in
a
l
d
ataset
b
y
f
in
d
i
n
g
th
e
n
ea
r
es
t
f
ea
tu
r
es
v
ec
to
r
f
r
o
m
th
e
f
o
r
m
er
s
tag
e.
K
-
m
ea
n
f
u
n
ctio
n
is
u
s
ed
to
m
ea
s
u
r
e
t
h
e
s
i
m
ilar
it
y
o
r
d
is
s
i
m
i
lar
it
y
b
et
w
ee
n
p
air
s
o
f
v
ec
to
r
s
.
He
n
ce
,
to
ef
f
ec
ti
v
el
y
m
ea
s
u
r
e
th
e
s
i
m
ilar
it
y
b
et
w
ee
n
d
if
f
er
en
t
f
ac
e
s
.
T
h
e
r
ec
o
g
n
it
io
n
r
esu
l
t
w
ill
g
i
v
e
t
h
e
e
m
p
lo
y
ee
'
s
n
a
m
e
an
d
t
h
is
t
ak
es o
n
l
y
m
ill
is
ec
o
n
d
s
to
b
e
ex
ec
u
ted
.
2
.
2
.
Usi
ng
Q
R
co
des
T
h
er
e
ar
e
t
w
o
m
ai
n
o
b
j
ec
tiv
es
o
f
u
s
in
g
QR
co
d
es
in
t
h
is
s
y
s
te
m
.
T
h
e
f
ir
s
t
o
n
e
is
to
i
n
cr
ea
s
e
th
e
r
eliab
ilit
y
o
f
id
e
n
ti
f
y
i
n
g
a
p
er
s
o
n
b
y
g
iv
i
n
g
h
i
m
h
is
o
w
n
d
y
n
a
m
ic
Q
R
co
d
e
g
en
er
ato
r
as
a
clien
t
ap
p
o
n
h
is
s
m
ar
tp
h
o
n
e
b
ased
o
n
its
in
te
r
n
atio
n
al
m
o
b
ile
eq
u
ip
m
e
n
t
i
d
en
tit
y
(
I
ME
I
)
id
en
tifie
r
b
ase
d
o
n
th
e
ad
v
an
ce
d
en
cr
y
p
tio
n
s
ta
n
d
ar
d
(
A
E
S
)
en
cr
y
p
tio
n
al
g
o
r
ith
m
,
b
esid
es
r
ec
o
g
n
is
i
n
g
h
is
f
ac
e
w
h
en
e
n
ter
in
g
an
d
ex
it
in
g
,
doi
n
g
as
a
s
ec
o
n
d
au
t
h
en
ticati
o
n
f
ac
to
r
w
ill
p
r
ev
e
n
t
t
h
e
in
tr
u
s
io
n
o
f
t
h
e
ac
ce
s
s
co
n
tr
o
l
s
y
s
te
m
b
y
u
s
i
n
g
a
f
a
k
e
p
ictu
r
e
o
f
an
em
p
lo
y
ee
.
T
h
e
d
y
n
a
m
ic
QR
co
d
e
g
en
er
ato
r
ap
p
is
b
u
ilt
u
s
in
g
a
Flu
tter
en
v
ir
o
n
m
e
n
t
b
u
t
is
o
u
t
o
f
th
e
s
co
p
e
o
f
t
h
is
p
ap
er
.
T
h
e
s
ec
o
n
d
o
b
j
ec
tiv
e
is
to
d
ea
l
w
i
t
h
p
eo
p
le
n
o
t
i
n
th
e
d
atab
ase
(
s
u
c
h
as
v
is
ito
r
s
)
o
r
w
h
o
ar
e
n
o
t
u
s
u
all
y
allo
w
ed
to
ac
ce
s
s
ce
r
tain
p
lace
s
.
I
n
t
h
is
ca
s
e,
th
e
y
ar
e
g
i
v
en
a
u
n
iq
u
e
co
d
e
u
s
ed
o
n
l
y
o
n
ce
an
d
d
u
r
in
g
a
s
p
ec
i
f
ic
ti
m
e.
2
.
2
.
1
.
Q
R
s
t
ruct
ure
T
h
e
QR
co
d
e's
s
tr
u
ct
u
r
e
is
m
ad
e
u
p
o
f
b
lac
k
a
n
d
w
h
i
te
c
h
ec
k
er
ed
p
ix
el
p
atter
n
s
t
h
at
ar
e
s
ep
ar
ated
in
to
s
e
v
er
al
p
ar
ticu
l
ar
r
eg
io
n
s
1
,
9
,
8
.
E
ac
h
ar
ea
s
er
v
es
a
d
i
s
tin
c
t
r
o
le.
Fig
u
r
e
3
is
an
e
x
a
m
p
le
o
f
a
v
er
s
io
n
3
QR
co
d
e
co
n
s
tr
u
ctio
n
.
−
Firstl
y
,
"
f
in
d
er
p
atter
n
/p
o
s
itio
n
in
g
m
ar
k
er
(
b
lack
ar
ea
s
,
1
)
"
:
th
r
ee
id
en
tical
ar
ea
s
at
th
e
QR
co
d
e'
s
co
r
n
er
s
.
E
ac
h
p
atter
n
is
r
ep
r
esen
ted
a
s
a
N
x
N
m
atr
i
x
.
"
f
in
d
er
p
atter
n
s
"
aid
th
e
d
ec
o
d
er
in
d
etec
tin
g
t
h
e
QR
co
d
e
an
d
d
eter
m
i
n
i
n
g
th
e
r
ig
h
t o
r
ien
tatio
n
.
−
Seco
n
d
l
y
,
"
d
ata
(
p
in
k
r
eg
io
n
s
,
2
)
"
: b
lo
ck
s
o
f
b
its
co
n
tain
in
g
r
ea
l d
ata.
−
T
h
ir
d
ly
,
f
o
r
m
at
in
f
o
r
m
at
io
n
(
g
r
ee
n
r
e
g
io
n
s
,
3
)
:
th
e
s
e
b
it
s
h
o
ld
in
f
o
r
m
a
t
io
n
ab
o
u
t
th
e
er
r
o
r
co
r
r
ec
tio
n
lev
el
an
d
m
as
k
i
n
g
p
atter
n
u
ti
li
ze
d
.
−
Fo
u
r
th
l
y
,
"
s
ep
ar
ato
r
s
(
y
ello
w
ar
ea
s
,
4
)
"
:
th
ese
ar
ea
s
ar
e
w
h
i
te,
w
h
ich
i
m
p
lies
t
h
e
y
co
n
tai
n
ex
ac
tl
y
ze
r
o
b
its
.
T
h
e
w
id
th
o
f
ea
ch
w
h
ite
s
ep
ar
ato
r
is
o
n
e
p
ix
el.
"
Sep
a
r
ato
r
ar
ea
s
"
en
h
an
ce
th
e
r
ec
o
g
n
izab
il
it
y
o
f
"
f
in
d
er
p
atter
n
s
"
b
y
s
ep
ar
atin
g
th
e
m
f
r
o
m
t
h
e
r
ea
l d
ata.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
R
ec
o
n
f
i
g
u
r
ab
le
&
E
m
b
ed
d
ed
Sy
s
t
I
SS
N:
2089
-
4864
R
o
b
u
s
t e
mb
ed
d
e
d
a
cc
ess
co
n
t
r
o
l sys
tem
b
a
s
ed
o
n
fa
ce
a
n
d
e
n
cryp
ted
QR
w
ith
…
(
S
a
mir
M
a
r
w
a
n
Ha
mma
mi
)
591
−
Fif
t
h
l
y
,
"
ti
m
i
n
g
p
atter
n
(
o
r
an
g
e
r
eg
io
n
s
,
5
)
"
:
th
e
w
id
t
h
o
f
a
s
in
g
le
s
q
u
ar
e
is
d
eter
m
i
n
ed
b
y
alter
n
at
in
g
b
et
w
ee
n
b
lack
an
d
w
h
ite
b
its
.
−
"
E
r
r
o
r
co
r
r
ec
tio
n
(
p
u
r
p
le
r
eg
io
n
s
,
6
)
"
: th
e
a
m
o
u
n
t o
f
er
r
o
r
co
r
r
ec
tio
n
w
o
r
d
s
d
ep
en
d
s
o
n
t
h
e
co
d
e
v
er
s
io
n
an
d
er
r
o
r
s
ev
er
it
y
.
−
"
R
em
a
in
d
er
b
its
(
d
ar
k
b
lu
e,
7
)
"
:
th
is
ar
ea
f
o
llo
w
s
th
e
er
r
o
r
co
r
r
ec
tin
g
zo
n
e
an
d
is
m
ad
e
u
p
o
f
e
m
p
t
y
b
its
th
at
ar
e
n
o
t a
l
w
a
y
s
ze
r
o
.
−
"
Six
th
l
y
,
alig
n
m
en
t
p
atter
n
s
(
b
r
ig
h
t
b
lu
e,
8
)
"
:
th
e
d
ec
o
d
er
u
s
es
th
e
m
to
co
r
r
ec
t
f
o
r
m
i
ld
v
is
u
al
d
is
to
r
tio
n
s
.
Dep
en
d
i
n
g
o
n
t
h
e
ed
itio
n
,
th
ese
p
atter
n
s
m
i
g
h
t b
e
m
o
r
e
th
an
o
n
e
o
r
ze
r
o
.
−
Fin
all
y
,
to
id
en
ti
f
y
it
f
r
o
m
its
s
u
r
r
o
u
n
d
in
g
s
,
th
e
Q
R
co
d
e
is
s
u
r
r
o
u
n
d
ed
b
y
a
"
Sil
e
n
t
zo
n
e"
(
a
r
eg
io
n
w
it
h
j
u
s
t z
er
o
b
its
)
.
T
h
e
d
ec
o
d
in
g
m
ec
h
a
n
is
m
i
s
ca
r
r
ied
o
u
t
ac
co
r
d
in
g
to
th
e
f
lo
w
ch
ar
t
i
n
Fi
g
u
r
e
4
.
Ho
w
e
v
er
,
f
o
r
d
etailed
in
f
o
r
m
atio
n
ab
o
u
t
t
h
e
s
tr
u
ct
u
r
e
o
f
t
h
e
QR
co
d
e
an
d
th
e
p
r
o
ce
s
s
o
f
co
d
in
g
a
n
d
d
ec
o
d
in
g
it,
o
n
e
ca
n
g
et
b
ac
k
to
[
1
9
]
,
[
2
0
]
.
T
h
ese
s
o
u
r
ce
s
p
r
o
v
id
e
co
m
p
r
eh
en
s
i
v
e
i
n
f
o
r
m
atio
n
o
n
th
e
QR
co
d
e's
f
o
r
m
a
t
in
f
o
r
m
atio
n
,
d
ata
m
a
s
k
in
g
p
atter
n
s
,
an
d
t
h
e
m
at
h
e
m
atic
al
p
r
in
cip
les
th
at
g
o
v
er
n
t
h
e
er
r
o
r
co
r
r
ec
tio
n
ca
p
ab
ilit
ies.
T
h
ey
al
s
o
d
ee
p
ly
elab
o
r
ate
o
n
th
e
d
ec
o
d
in
g
p
r
o
ce
s
s
.
Fig
u
r
e
3
.
Stru
ct
u
r
e
o
f
a
QR
co
d
e
Fig
u
r
e
4
.
Flo
w
c
h
ar
t o
f
d
ec
o
d
in
g
Q
R
co
d
e
s
2
.
2
.
2
.
Rea
din
g
Q
R
c
o
de
s
QR
co
d
es
h
a
v
e
a
co
m
p
lex
r
ea
d
in
g
p
r
o
ce
s
s
,
r
eq
u
ir
i
n
g
a
l
o
n
g
co
m
p
u
tatio
n
ti
m
e.
Ho
w
ev
er
,
th
i
s
p
r
o
ce
s
s
in
g
ti
m
e
is
s
ti
ll
ac
ce
p
tab
le
f
o
r
m
a
n
y
ap
p
licatio
n
s
.
A
ll
e
x
is
t
in
g
Q
R
d
ec
o
d
er
s
i
m
p
le
m
en
ted
ar
e
s
o
f
t
w
ar
e
-
b
ased
,
eith
er
i
n
m
o
b
ile
p
h
o
n
e
ap
p
s
o
r
o
th
er
m
i
cr
o
p
r
o
ce
s
s
o
r
-
b
ased
e
m
b
ed
d
ed
s
y
s
te
m
s
s
u
c
h
as
R
asp
b
er
r
y
P
i;
n
ev
er
th
e
less
,
f
o
r
m
o
r
e
ad
v
an
ce
d
ap
p
licatio
n
s
,
s
u
ch
a
s
d
ata
d
ec
r
y
p
tio
n
f
o
r
d
ata
s
ec
u
r
it
y
,
w
h
er
e
ex
tr
a
r
ea
l
-
ti
m
e
an
d
co
m
p
lex
f
u
n
ctio
n
s
w
ill
o
cc
u
p
y
m
o
s
t
o
f
th
e
co
m
p
u
tatio
n
a
l
r
eso
u
r
ce
s
o
f
th
e
p
r
o
ce
s
s
o
r
.
Fig
u
r
e
4
clea
r
ly
illu
s
tr
ates
t
h
e
ca
lcu
latio
n
w
o
r
k
f
o
r
ea
ch
o
f
th
e
th
r
ee
p
r
i
m
ar
y
s
tep
s
o
f
th
e
QR
d
ec
o
d
in
g
p
r
o
ce
s
s
: p
ictu
r
e
ca
p
tu
r
e,
i
m
a
g
e
p
r
ep
r
o
ce
s
s
in
g
,
an
d
QR
d
ec
o
d
in
g
.
2
.
3
.
C
o
m
ple
m
ent
a
ry
f
un
ct
io
ns
2
.
3
.
1
.
G
ener
a
t
ing
a
o
ne
-
t
i
m
e
-
pa
s
s
w
o
rd
a
nd
enco
d
ing
it
wit
h Q
R
On
e
-
ti
m
e
-
p
a
s
s
w
o
r
d
b
ased
o
n
th
e
A
E
S
en
cr
y
p
t
io
n
al
g
o
r
ith
m
g
iv
e
s
d
ir
ec
t
p
er
m
i
s
s
io
n
s
r
e
g
ar
d
less
o
f
f
ac
ial
r
ec
o
g
n
itio
n
b
u
t
o
n
l
y
f
o
r
a
s
p
ec
if
ied
p
er
io
d
.
T
h
is
allo
w
s
th
e
s
y
s
te
m
to
d
ea
l
w
it
h
v
i
s
ito
r
s
w
h
o
s
e
p
h
o
to
s
ar
e
n
o
t
in
t
h
e
d
atab
ase.
T
h
is
p
ass
w
o
r
d
is
co
n
v
er
ted
to
Q
R
en
co
d
i
n
g
in
li
n
e
w
it
h
t
h
e
s
y
s
te
m
's
w
o
r
k
in
g
m
ec
h
a
n
i
s
m
.
T
h
e
g
e
n
er
ated
co
d
e
is
p
r
in
ted
an
d
g
i
v
en
to
th
e
v
is
i
to
r
to
p
ass
o
n
to
t
h
e
d
i
g
ital
ca
m
er
a
u
s
ed
i
n
t
h
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
9
-
4864
I
n
t J
R
ec
o
n
f
i
g
u
r
ab
le
&
E
m
b
ed
d
ed
Sy
s
t
,
Vo
l.
13
,
No
.
3
,
No
v
e
m
b
er
20
24
:
586
-
59
4
592
s
y
s
te
m
.
P
y
OT
P
is
a
P
y
t
h
o
n
p
ac
k
ag
e
t
h
at
w
e
u
s
e
to
cr
ea
te
an
d
v
alid
ate
o
n
e
-
ti
m
e
p
ass
w
o
r
d
s
.
I
t
is
a
p
p
licab
le
to
o
n
lin
e
ap
p
licatio
n
s
an
d
o
th
er
s
y
s
te
m
s
t
h
at
n
ee
d
u
s
er
s
to
lo
g
in
,
w
h
er
e
t
w
o
-
f
ac
to
r
(
2
FA
)
o
r
m
u
lti
-
f
ac
to
r
(
MFA
)
a
u
th
e
n
tica
tio
n
m
ec
h
a
n
is
m
s
ca
n
b
e
u
s
ed
.
R
F
C
4
2
2
6
(
HOT
P
:
a
n
HM
AC
-
b
ased
o
n
e
-
ti
m
e
p
ass
w
o
r
d
alg
o
r
ith
m
)
an
d
R
F
C
6
2
3
8
(
T
OT
P
:
tim
e
-
b
ased
o
n
e
-
ti
m
e
p
as
s
w
o
r
d
al
g
o
r
ith
m
)
e
s
tab
lis
h
t
h
e
o
p
en
MF
A
s
tan
d
ar
d
s
.
B
o
th
o
f
t
h
e
s
e
p
r
o
to
co
ls
h
av
e
s
er
v
er
-
s
id
e
f
u
n
ct
io
n
alit
y
i
m
p
le
m
en
te
d
b
y
P
y
OT
P
.
C
lien
t
-
s
id
e
s
u
p
p
o
r
t
ca
n
b
e
en
ab
led
b
y
tel
lin
g
u
s
er
s
to
u
s
e
Go
o
g
l
e
au
th
e
n
tica
to
r
,
au
th
y
,
o
r
an
o
t
h
e
r
co
m
p
atib
le
s
o
f
t
w
ar
e
f
o
r
T
O
T
P
,
o
r
b
y
d
eli
v
er
in
g
a
u
th
e
n
tic
atio
n
co
d
es
to
u
s
er
s
b
y
e
m
ai
l
o
r
SMS
(
HOT
P
)
.
B
y
u
tili
zi
n
g
th
e
ca
m
er
a
o
n
th
e
i
r
p
h
o
n
e
to
s
ca
n
t
h
e
QR
co
d
es
o
f
f
er
ed
b
y
P
y
OT
P
,
u
s
er
s
m
a
y
q
u
ick
l
y
s
e
t
u
p
au
t
h
to
k
e
n
s
i
n
th
eir
ap
p
s
.
W
e
ad
h
er
ed
to
th
e
r
elev
an
t
R
FC
s
'
s
ec
tio
n
s
o
n
T
OT
P
s
ec
u
r
it
y
co
n
ce
r
n
s
an
d
HOT
P
s
ec
u
r
it
y
cr
iter
ia,
w
h
ich
s
tate,
at
th
e
v
er
y
least:
−
Usi
n
g
HT
T
P
S to
en
s
u
r
e
tr
an
s
p
o
r
t secr
ec
y
.
−
Ma
in
t
ai
n
i
n
g
t
h
e
s
ec
r
ec
y
o
f
H
OT
P
/T
O
T
P
s
ec
r
ets b
y
k
ee
p
i
n
g
th
e
m
i
n
a
d
atab
ase
w
ith
r
es
tr
icted
ac
ce
s
s
.
−
P
r
ev
en
tin
g
r
ep
la
y
attac
k
s
b
y
r
ef
u
s
i
n
g
clie
n
t
-
s
u
p
p
lied
o
n
e
-
ti
m
e
p
ass
w
o
r
d
s
(
th
is
n
ec
ess
itat
es
k
ee
p
in
g
th
e
m
o
s
t
r
ec
en
t
a
u
t
h
en
t
icate
d
ti
m
esta
m
p
,
OT
P
,
o
r
O
T
P
h
ash
i
n
t
h
e
d
atab
ase
an
d
r
ef
u
s
i
n
g
t
h
e
OT
P
u
p
o
n
f
i
n
d
in
g
a
m
atc
h
)
.
−
R
ed
u
ci
n
g
t
h
e
f
r
eq
u
en
c
y
o
f
b
r
u
te
-
f
o
r
ce
atte
m
p
ts
to
ac
ce
s
s
th
e
ap
p
licatio
n
's lo
g
i
n
f
ea
t
u
r
es
2
.
3
.
2
.
Def
in
ing
t
he
per
m
is
s
io
ns
da
t
a
ba
s
e
On
e
i
n
te
g
r
ated
SQ
L
d
atab
ase
en
g
in
e
th
at
d
o
es
n
'
t
n
ee
d
a
s
ep
ar
ate
s
er
v
er
p
r
o
ce
s
s
is
ca
ll
ed
SQL
i
te
[
2
1
]
.
I
t
d
ir
ec
tly
w
r
ites
a
n
d
r
ea
d
s
f
r
o
m
s
tan
d
ar
d
d
is
k
f
ile
s
.
An
w
h
o
le
SQ
L
d
atab
a
s
e
w
it
h
s
e
v
er
al
tab
les,
in
d
ices,
tr
ig
g
er
s
,
an
d
v
ie
w
s
ca
n
b
e
f
o
u
n
d
o
n
a
s
in
g
le
d
is
k
f
il
e.
Sin
ce
th
e
R
asp
b
er
r
y
P
i
4
h
as
li
m
i
ted
r
eso
u
r
ce
s
,
SQLite
is
a
g
r
ea
t o
p
tio
n
b
ec
au
s
e
it is
li
g
h
t
w
ei
g
h
t a
n
d
tin
y
[
2
2
]
.
SQLite
is
s
el
f
-
co
n
ta
in
ed
,
m
ea
n
in
g
n
o
ex
ter
n
al
d
ep
en
d
e
n
cie
s
ar
e
r
eq
u
ir
ed
.
I
t'
s
s
er
v
er
les
s
,
s
o
it
w
ill
n
o
t
co
n
s
u
m
e
t
h
e
R
a
s
p
b
er
r
y
P
i'
s
r
a
n
d
o
m
ac
ce
s
s
m
e
m
o
r
y
(
R
A
M
)
an
d
ce
n
tr
al
p
r
o
ce
s
s
i
n
g
u
n
it
(
C
P
U
)
w
h
en
n
o
t
b
ein
g
u
tili
s
ed
.
SQ
L
ite
h
as
ze
r
o
co
n
f
ig
u
r
atio
n
,
m
a
k
i
n
g
i
t
e
as
y
to
u
s
e
r
i
g
h
t
o
u
t
o
f
th
e
b
o
x
.
I
t's
also
cr
o
s
s
-
p
latf
o
r
m
,
a
v
ailab
le
o
n
UNI
X
(
L
in
u
x
,
Ma
c
OS
-
X,
An
d
r
o
id
,
iOS)
an
d
W
i
n
d
o
w
s
(
W
in
3
2
,
W
in
C
E
,
W
i
n
R
T
)
.
I
n
th
is
p
r
o
j
ec
t,
SQL
ite
d
ef
in
e
s
an
d
m
an
a
g
es
ea
c
h
e
m
p
lo
y
ee
'
s
p
er
m
i
s
s
io
n
s
.
T
h
e
p
er
m
is
s
io
n
s
tab
le
co
n
tain
s
th
e
f
o
llo
w
in
g
co
l
u
m
n
s
(
u
n
iq
u
e
id
en
ti
f
ier
,
e
m
p
lo
y
ee
'
s
I
D,
p
lace
I
D,
v
al
u
e
0
o
r
1
to
b
lo
ck
o
r
a
llo
w
ac
ce
s
s
to
t
h
is
p
lace
)
.
2
.
3
.
3
.
K
ee
pin
g
l
o
g
s
o
f
a
ct
io
n
s
T
h
e
f
o
llo
w
i
n
g
d
ata
is
s
av
ed
co
n
tin
u
o
u
s
l
y
:
i)
e
m
p
lo
y
ee
's
I
D,
d
ate,
tim
e,
p
lace
an
d
en
tr
y
/e
x
it
o
f
p
er
s
o
n
s
u
s
i
n
g
(
f
ac
e
r
ec
o
g
n
itio
n
+Q
R
co
d
e)
;
ii)
th
e
u
s
ed
OT
P
,
th
e
d
ate,
tim
e,
p
lace
an
d
e
n
tr
y
/e
x
it
o
f
p
eo
p
le
(
d
ir
ec
t
O
T
P)
;
iii)
all
s
in
g
le
-
u
s
e
p
ass
w
o
r
d
s
w
it
h
th
eir
n
u
m
b
er
an
d
th
e
ir
g
en
er
ati
n
g
d
ate/ti
m
e
;
iv
)
all
u
n
a
u
t
h
o
r
is
ed
en
tr
y
atte
m
p
ts
b
ec
au
s
e
t
h
e
y
d
o
n
o
t
m
a
tc
h
t
h
e
p
er
m
i
s
s
io
n
d
ef
i
n
itio
n
tab
le
,
an
d
v
)
al
l
u
n
a
u
t
h
o
r
is
ed
en
tr
y
a
tte
m
p
t
s
h
av
e
ex
p
ir
ed
p
ass
w
o
r
d
s
.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
A
ll
t
h
e
p
r
ev
io
u
s
f
u
n
ctio
n
s
ar
e
im
p
le
m
e
n
ted
u
s
i
n
g
a
R
asp
b
er
r
y
P
i
4
n
an
o
co
m
p
u
ter
u
s
i
n
g
P
y
t
h
o
n
en
v
ir
o
n
m
e
n
t
3
.
6
.
Ma
n
y
o
p
en
-
s
o
u
r
ce
lib
r
ar
ies
w
er
e
u
s
ed
i
n
t
h
e
i
m
p
le
m
e
n
tatio
n
.
Mu
l
ti
-
t
h
r
ea
d
in
g
an
d
o
th
er
p
ar
allel
tech
n
iq
u
es
ar
e
u
s
ed
s
o
th
e
s
y
s
te
m
ca
n
w
o
r
k
a
s
f
a
s
t
as
p
o
s
s
ib
le.
I
n
t
h
e
tes
ts
,
t
h
e
s
y
s
te
m
ac
h
ie
v
ed
8
.
2
7
FP
S
an
d
co
m
p
lete
r
o
b
u
s
tn
e
s
s
.
Du
r
i
n
g
th
e
test
s
,
u
s
i
n
g
ca
s
ca
d
e
f
ilter
s
in
f
ac
e
d
etec
tio
n
let
s
th
e
s
y
s
te
m
ac
h
iev
e
1
2
.
2
3
FP
S
b
u
t
w
it
h
a
lo
w
er
d
etec
tio
n
r
ate.
Usi
n
g
co
n
v
o
lu
ti
o
n
al
n
eu
r
al
n
et
w
o
r
k
(
C
NN
)
m
ak
es
th
e
s
y
s
te
m
r
u
n
at
o
n
l
y
1
.
7
FP
S
b
u
t
w
it
h
a
h
i
g
h
er
d
etec
tio
n
r
ate.
Hen
c
e,
Ho
G
w
as
u
lt
i
m
a
tel
y
ch
o
s
en
as
it
is
a
g
o
o
d
co
m
p
r
o
m
is
e
b
et
w
ee
n
s
p
ee
d
an
d
d
etec
tio
n
r
ate.
As
s
h
o
wn
i
n
Fi
g
u
r
e
5
,
th
e
f
in
al
p
r
o
to
ty
p
e
is
b
u
ilt
a
s
a
s
tan
d
alo
n
e
s
y
s
te
m
i
n
a
n
al
u
m
i
n
iu
m
ca
s
e
a
n
d
ca
n
b
e
u
s
ed
u
s
i
n
g
eith
er
a
w
eb
ca
m
o
r
a
R
asp
i
C
a
m
.
I
t
also
h
as
a
b
u
ilt
-
in
s
cr
ee
n
b
u
t
ca
n
b
e
co
n
n
ec
ted
to
an
e
x
ter
n
al
s
cr
ee
n
.
I
t
also
h
a
s
f
o
u
r
k
e
y
s
f
o
r
co
n
tr
o
llin
g
t
h
e
f
lo
w
o
f
th
e
f
u
n
ctio
n
s
.
L
i
k
e
en
cr
y
p
ted
QR
co
d
es
a
n
d
ad
v
an
ce
d
f
ac
e
r
ec
o
g
n
i
tio
n
alg
o
r
it
h
m
s
,
t
h
is
p
o
w
er
f
u
l
s
y
n
er
g
y
,
o
r
ch
estra
ted
b
y
th
e
v
er
s
atil
e
R
asp
b
er
r
y
P
i4
p
latf
o
r
m
,
p
r
esen
ts
a
r
o
b
u
s
t
an
d
co
n
v
en
ien
t
s
o
lu
tio
n
f
o
r
o
r
g
an
is
at
io
n
s
s
ee
k
i
n
g
to
elev
a
te
th
eir
s
ec
u
r
it
y
p
o
s
tu
r
e
an
d
u
s
er
ex
p
er
ien
ce
.
T
h
e
lan
d
s
ca
p
e
o
f
ac
ce
s
s
co
n
tr
o
l
s
y
s
te
m
s
is
u
n
d
er
g
o
in
g
a
tr
an
s
f
o
r
m
a
tiv
e
s
h
if
t
d
r
i
v
en
b
y
th
e
co
n
v
er
g
e
n
ce
o
f
c
u
tti
n
g
-
ed
g
e
tech
n
o
lo
g
ies.
T
h
e
co
n
v
er
g
e
n
ce
o
f
cr
y
p
to
g
r
ap
h
ic
QR
co
d
es
an
d
ad
v
an
ce
d
f
ac
ial
r
ec
o
g
n
itio
n
tech
n
o
lo
g
y
o
n
th
e
R
asp
b
er
r
y
P
i4
p
latf
o
r
m
i
s
r
ev
o
lu
tio
n
i
s
in
g
ac
ce
s
s
co
n
tr
o
l
s
y
s
te
m
s
;
it
p
r
esen
ts
a
r
o
b
u
s
t
a
n
d
co
n
v
en
ien
t
s
o
l
u
tio
n
f
o
r
o
r
g
an
is
at
io
n
s
s
ee
k
in
g
to
ele
v
ate
th
eir
s
ec
u
r
it
y
p
o
s
tu
r
e
a
n
d
u
s
er
ex
p
er
ie
n
ce
.
T
h
is
f
u
s
io
n
cr
ea
tes
a
p
o
w
er
f
u
l
to
o
l
f
o
r
o
r
g
an
iza
tio
n
s
to
o
u
tp
e
r
f
o
r
m
co
n
v
e
n
tio
n
a
l
ac
ce
s
s
co
n
tr
o
l
tech
n
iq
u
es.
T
h
ese
b
en
e
f
it
s
ca
n
b
e
e
m
b
ed
d
ed
in
o
th
er
s
af
e
t
y
ap
p
licatio
n
s
li
k
e
[
2
3
]
–
[
2
5
]
.
A
n
o
t
h
er
i
m
p
ac
t
is
th
e
th
at
t
h
is
i
s
an
ec
o
n
o
m
ical
s
o
l
u
tio
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
R
ec
o
n
f
i
g
u
r
ab
le
&
E
m
b
ed
d
ed
Sy
s
t
I
SS
N:
2089
-
4864
R
o
b
u
s
t e
mb
ed
d
e
d
a
cc
ess
co
n
t
r
o
l sys
tem
b
a
s
ed
o
n
fa
ce
a
n
d
e
n
cryp
ted
QR
w
ith
…
(
S
a
mir
M
a
r
w
a
n
Ha
mma
mi
)
593
co
m
p
ar
i
n
g
to
co
n
v
e
n
tio
n
al
h
ar
d
w
ar
e
-
i
n
te
n
s
i
v
e
s
o
lu
t
io
n
s
.
Usi
n
g
R
a
s
p
b
er
r
y
P
i4
m
ak
e
s
o
u
r
s
o
lu
tio
n
m
o
r
e
f
le
x
ib
le
an
d
af
f
o
r
d
ab
le
o
p
tio
n
.
Ho
w
e
v
er
;
th
er
e
ar
e
s
till
p
o
te
n
tial
co
n
s
id
er
atio
n
s
to
b
e
al
wa
y
s
a
d
d
r
ess
ed
.
Firstl
y
,
p
r
iv
ac
y
co
n
ce
r
n
s
lik
e
h
o
w
to
alla
y
w
o
r
r
ie
s
ab
o
u
t
f
ac
ial
r
ec
o
g
n
itio
n
tec
h
n
o
l
o
g
y
,
it
is
i
m
p
er
ati
v
e
to
p
u
t
in
p
lace
clea
r
d
ata
s
ec
u
r
it
y
p
r
o
ce
d
u
r
es
an
d
ab
id
e
w
it
h
ap
p
licab
le
p
r
iv
ac
y
la
w
s
.
Seco
n
d
l
y
,
l
ig
h
ti
n
g
an
d
en
v
ir
o
n
m
en
ta
l
cir
cu
m
s
ta
n
ce
s
w
h
er
e
ac
cu
r
ate
f
ac
e
r
ec
o
g
n
i
tio
n
p
er
f
o
r
m
a
n
c
es
u
n
d
er
a
r
an
g
e
o
f
li
g
h
ti
n
g
an
d
en
v
ir
o
n
m
en
ta
l
cir
cu
m
s
ta
n
ce
s
d
ep
en
d
o
n
p
r
o
p
er
ca
m
er
a
p
o
s
itio
n
i
n
g
a
n
d
s
etu
p
m
o
d
if
ica
tio
n
s
.
T
h
ir
d
l
y
,
tech
n
ical
d
ep
en
d
en
cie
s
b
y
p
u
tti
n
g
i
n
p
lace
b
ac
k
u
p
p
la
n
s
a
n
d
r
ed
u
n
d
an
t
p
o
w
er
s
u
p
p
l
ies,
o
p
er
atio
n
al
co
n
tin
u
it
y
is
e
n
s
u
r
ed
b
y
r
ed
u
ci
n
g
th
e
r
is
k
o
f
d
is
r
u
p
tio
n
s
f
r
o
m
te
ch
n
ica
l p
r
o
b
lem
s
o
r
p
o
w
er
o
u
t
ag
es.
Fig
u
r
e
5
.
T
h
e
f
in
al
p
r
o
to
ty
p
e
4.
CO
NCLU
SI
O
N
T
h
is
r
esear
ch
d
escr
ib
ed
t
h
e
i
n
teg
r
at
io
n
o
f
f
ac
ial
r
ec
o
g
n
iti
o
n
w
it
h
e
n
cr
y
p
ted
QR
co
d
es
to
cr
ea
te
a
s
tr
o
n
g
ac
ce
s
s
co
n
tr
o
l
s
y
s
te
m
.
A
lt
h
o
u
g
h
th
e
d
atab
ase
is
n
o
w
k
ep
t
o
n
th
e
s
a
m
e
s
y
s
te
m
,
m
o
v
in
g
it
to
th
e
clo
u
d
w
o
u
ld
b
e
p
r
ef
er
ab
le
as
it
w
o
u
ld
m
a
k
e
d
atab
ase
m
o
d
if
icati
o
n
s
m
o
r
e
d
ep
en
d
ab
le
ac
r
o
s
s
v
ar
io
u
s
in
s
ta
n
ce
s
o
f
th
e
s
y
s
te
m
.
A
l
th
o
u
g
h
t
h
e
s
y
s
t
e
m
is
r
u
n
n
i
n
g
s
m
o
o
th
l
y
o
n
R
asp
b
er
r
y
P
i
4
,
it
w
a
s
n
o
t
f
ea
s
i
b
le
to
i
m
p
le
m
e
n
t
it
u
s
i
n
g
an
ea
r
lier
v
er
s
io
n
li
k
e
R
asp
b
er
r
y
P
i 3
.
T
h
e
s
y
n
er
g
is
tic
f
u
s
io
n
o
f
e
n
c
r
y
p
ted
QR
co
d
es
an
d
f
ac
ial
r
ec
o
g
n
itio
n
tech
n
o
lo
g
y
,
p
o
w
er
ed
b
y
th
e
R
asp
b
er
r
y
P
i4
,
r
ep
r
esen
ts
a
p
ar
ad
ig
m
s
h
i
f
t
in
ac
ce
s
s
c
o
n
tr
o
l
s
y
s
te
m
s
.
B
y
p
r
io
r
itis
in
g
r
o
b
u
s
t
s
ec
u
r
it
y
,
s
tr
ea
m
li
n
ed
u
s
er
ex
p
er
ie
n
ce
,
an
d
co
s
t
-
e
f
f
ec
ti
v
en
e
s
s
,
t
h
i
s
in
n
o
v
ativ
e
ap
p
r
o
ac
h
ca
ter
s
to
t
h
e
ev
o
lv
i
n
g
n
ee
d
s
o
f
o
r
g
an
is
at
io
n
s
s
ee
k
in
g
to
s
ec
u
r
e
th
eir
e
n
v
ir
o
n
m
e
n
t
s
w
h
ile
e
n
h
an
ci
n
g
u
s
er
co
n
v
e
n
ien
ce
.
Ho
w
e
v
er
,
a
p
r
o
ac
tiv
e
ap
p
r
o
ac
h
to
ad
d
r
ess
p
o
ten
tial
p
r
iv
ac
y
co
n
ce
r
n
s
,
en
v
ir
o
n
m
en
tal
in
f
l
u
e
n
ce
s
,
an
d
tech
n
ic
al
d
ep
en
d
en
cies
is
cr
u
cial
f
o
r
s
u
cc
ess
f
u
l i
m
p
le
m
e
n
tatio
n
a
n
d
m
a
x
i
m
i
s
in
g
t
h
e
s
y
s
te
m
's b
en
e
f
its
.
RE
F
E
R
E
NC
E
S
[
1]
Y
.
H
o
n
g
,
“
D
e
si
g
n
o
f
i
n
t
e
l
l
i
g
e
n
t
a
c
c
e
ss
c
o
n
t
r
o
l
sy
st
e
m
b
a
se
d
o
n
d
e
s
e
n
c
r
y
p
t
e
d
Q
R
c
o
d
e
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
2
0
2
0
I
EEE
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
A
d
v
a
n
c
e
s i
n
E
l
e
c
t
r
i
c
a
l
En
g
i
n
e
e
ri
n
g
a
n
d
C
o
m
p
u
t
e
r A
p
p
l
i
c
a
t
i
o
n
s,
AE
EC
A
2
0
2
0
,
I
EEE,
A
u
g
.
2
0
2
0
,
p
p
.
1
0
0
5
–
1
0
0
8
,
d
o
i
:
1
0
.
1
1
0
9
/
A
EEC
A
4
9
9
1
8
.
2
0
2
0
.
9
2
1
3
4
7
5
.
[
2
]
K
.
Y
a
n
g
,
H
.
Y
u
a
n
,
a
n
d
Y
.
G
u
o
,
“
Tw
o
-
d
i
me
n
si
o
n
a
l
c
o
d
e
h
i
e
r
a
r
c
h
i
c
a
l
e
n
c
r
y
p
t
i
o
n
a
l
g
o
r
i
t
h
m
b
a
se
d
o
n
a
t
t
r
i
b
u
t
e
e
n
c
r
y
p
t
i
o
n
,
”
C
o
m
p
u
t
e
r
E
n
g
i
n
e
e
r
i
n
g
,
v
o
l
.
4
4
,
n
o
.
0
6
,
p
p
.
1
3
6
–
1
4
0
,
2
0
1
8
,
d
o
i
:
1
0
.
1
9
6
7
8
/
j
.
i
ss
n
.
1
0
0
0
-
3
4
2
8
.
0
0
4
6
3
9
2
[
3
]
X
.
Z
h
a
n
g
,
H
.
L
i
,
Y
.
Y
a
n
g
,
G
.
S
u
n
,
a
n
d
G
.
C
h
e
n
,
“
L
I
P
P
S
:
l
o
g
i
st
i
c
s
i
n
f
o
r
mat
i
o
n
p
r
i
v
a
c
y
p
r
o
t
e
c
t
i
o
n
sy
s
t
e
m
b
a
se
d
o
n
e
n
c
r
y
p
t
e
d
Q
R
c
o
d
e
,
”
i
n
Pro
c
e
e
d
i
n
g
s
-
1
5
t
h
I
E
EE
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
T
r
u
s
t
,
S
e
c
u
ri
t
y
a
n
d
Pri
v
a
c
y
i
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,
1
0
t
h
I
EEE
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
Bi
g
D
a
t
a
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
a
n
d
1
4
t
h
I
EEE
I
n
t
e
r
n
a
t
i
o
n
a
l
S
y
m
p
o
si
u
m
o
n
Pa
r
a
l
l
e
l
a
n
d
D
i
s
t
ri
b
u
t
e
d
Pr
o
c
e
ssi
n
g
w
i
t
h
A
p
p
l
i
c
a
t
i
o
n
s,
I
EE
E
T
r
u
s
t
C
o
m
/
B
i
g
D
a
t
a
S
E/
I
S
PA
2
0
1
6
,
I
EEE,
A
u
g
.
2
0
1
6
,
p
p
.
9
9
6
–
1
0
0
0
,
d
o
i
:
1
0
.
1
1
0
9
/
T
r
u
st
C
o
m.2
0
1
6
.
0
1
6
7
.
[
4
]
R
.
L
i
a
n
g
,
Y
.
W
a
n
g
,
a
n
d
X
.
L
i
,
“
D
e
s
i
g
n
o
f
sy
st
e
m
a
n
d
k
e
y
a
l
g
o
r
i
t
h
ms
f
o
r
2
D
c
o
d
e
r
e
c
o
g
n
i
t
i
o
n
w
i
t
h
d
i
f
f
e
r
e
n
t
se
c
u
r
i
t
y
l
e
v
e
l
s,”
C
o
m
p
u
t
e
r
E
n
g
i
n
e
e
r
i
n
g
a
n
d
D
e
s
i
g
n
,
v
o
l
.
3
8
,
n
o
.
1
1
,
p
p
.
2
9
0
3
–
2
9
0
8
,
2
0
1
7
.
[
5
]
L
.
X
u
,
X
.
J
i
a
n
g
,
a
n
d
J.
Z
h
a
n
g
,
“
D
e
si
g
n
a
n
d
i
m
p
l
e
me
n
t
a
t
i
o
n
o
f
t
w
o
-
d
i
m
e
n
si
o
n
a
l
c
o
d
e
r
e
c
o
g
n
i
t
i
o
n
sy
st
e
m
i
n
mo
b
i
l
e
p
h
o
n
e
,
”
J
o
u
rn
a
l
o
f
C
o
m
p
u
t
e
r A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
3
2
,
n
o
.
5
,
p
p
.
1
4
7
4
–
1
4
7
6
,
A
p
r
.
2
0
1
3
,
d
o
i
:
1
0
.
3
7
2
4
/
s
p
.
j
.
1
0
8
7
.
2
0
1
2
.
0
1
4
7
4
.
[
6
]
J.
Z
h
u
,
Y
.
C
h
a
n
g
,
a
n
d
C
.
Z
h
u
,
“
A
p
p
l
i
c
a
t
i
o
n
o
f
q
r
c
o
d
e
r
e
c
o
g
n
i
t
i
o
n
t
e
c
h
n
o
l
o
g
y
i
n
mo
d
e
r
n
p
o
w
e
r
l
o
g
i
st
i
c
s
ma
n
a
g
e
me
n
t
,
”
i
n
2
0
2
1
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
Bi
g
D
a
t
a
A
n
a
l
y
t
i
c
s
f
o
r
C
y
b
e
r
-
P
h
y
s
i
c
a
l
S
y
st
e
m
i
n
S
m
a
r
t
C
i
t
y
,
M
.
A
t
i
q
u
z
z
a
man
,
N
.
Y
e
n
,
a
n
d
Z
.
X
u
,
Ed
s.
S
i
n
g
a
p
o
r
e
:
S
p
r
i
n
g
e
r
S
i
n
g
a
p
o
r
e
,
2
0
2
2
,
p
p
.
3
5
1
–
3
5
7
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
9
8
1
-
16
-
7
4
6
9
-
3
4
0
.
[
7
]
G
.
Y
a
n
g
a
n
d
T
.
S
.
H
u
a
n
g
,
“
H
u
m
a
n
f
a
c
e
d
e
t
e
c
t
i
o
n
i
n
a
c
o
mp
l
e
x
b
a
c
k
g
r
o
u
n
d
,
”
P
a
t
t
e
r
n
Re
c
o
g
n
i
t
i
o
n
,
v
o
l
.
2
7
,
n
o
.
1
,
p
p
.
5
3
–
6
3
,
Ja
n
.
1
9
9
4
,
d
o
i
:
1
0
.
1
0
1
6
/
0
0
3
1
-
3
2
0
3
(
9
4
)
9
0
0
1
7
-
5.
[
8
]
P
.
V
i
o
l
a
a
n
d
M
.
J.
Jo
n
e
s,
“
R
o
b
u
st
r
e
a
l
-
t
i
me
f
a
c
e
d
e
t
e
c
t
i
o
n
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
C
o
m
p
u
t
e
r
Vi
s
i
o
n
,
v
o
l
.
5
7
,
n
o
.
2
,
p
p
.
1
3
7
–
1
5
4
,
M
a
y
2
0
0
4
,
d
o
i
:
1
0
.
1
0
2
3
/
B
:
V
I
S
I
.
0
0
0
0
0
1
3
0
8
7
.
4
9
2
6
0
.
f
b
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
9
-
4864
I
n
t J
R
ec
o
n
f
i
g
u
r
ab
le
&
E
m
b
ed
d
ed
Sy
s
t
,
Vo
l.
13
,
No
.
3
,
No
v
e
m
b
er
20
24
:
586
-
59
4
594
[
9
]
R
.
B
r
u
n
e
l
l
i
a
n
d
T
.
P
o
g
g
i
o
,
“
F
a
c
e
r
e
c
o
g
n
i
t
i
o
n
:
f
e
a
t
u
r
e
s
v
e
r
su
s
t
e
mp
l
a
t
e
s,”
I
EEE
T
ra
n
s
a
c
t
i
o
n
s
o
n
P
a
t
t
e
r
n
A
n
a
l
y
si
s
a
n
d
M
a
c
h
i
n
e
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
1
5
,
n
o
.
1
0
,
p
p
.
1
0
4
2
–
1
0
5
2
,
1
9
9
3
,
d
o
i
:
1
0
.
1
1
0
9
/
3
4
.
2
5
4
0
6
1
.
[
1
0
]
P
.
J.
G
r
o
t
h
e
r
,
P
.
J.
G
r
o
t
h
e
r
,
M
.
N
g
a
n
,
a
n
d
K
.
H
a
n
a
o
k
a
,
“
F
a
c
e
r
e
c
o
g
n
i
t
i
o
n
v
e
n
d
o
r
t
e
st
(
F
R
V
T
)
,
”
U
S
D
e
p
a
r
t
me
n
t
o
f
C
o
mm
e
r
c
e
,
N
a
t
i
o
n
a
l
I
n
st
i
t
u
t
e
o
f
S
t
a
n
d
a
r
d
s
a
n
d
T
e
c
h
n
o
l
o
g
y
,
Te
c
h
.
R
e
p
.
,
2
0
1
4
,
d
o
i
:
1
0
.
6
0
2
8
/
N
I
S
T
.
I
R
.
8
0
0
9
.
[
1
1
]
M
.
M
a
h
j
e
e
d
,
G
.
T
h
a
mi
l
a
r
a
su
,
N
.
Jo
h
n
so
n
,
a
n
d
C
.
A
l
f
o
n
so
,
“
A
d
e
e
p
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
f
o
r
E
C
G
a
u
t
h
e
n
t
i
c
a
t
i
o
n
o
n
i
mp
l
a
n
t
a
b
l
e
me
d
i
c
a
l
d
e
v
i
c
e
s,”
i
n
P
ro
c
e
e
d
i
n
g
s
-
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
C
o
m
p
u
t
e
r
C
o
m
m
u
n
i
c
a
t
i
o
n
s
a
n
d
N
e
t
w
o
r
k
s,
I
C
C
C
N
,
I
EEE,
Ju
l
.
2
0
2
3
,
p
p
.
1
–
7
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
C
C
N
5
8
0
2
4
.
2
0
2
3
.
1
0
2
3
0
1
9
8
.
[
1
2
]
H
.
W
a
n
g
e
t
a
l
.
,
“
Jo
i
n
t
B
i
o
l
o
g
i
c
a
l
I
D
:
a
se
c
u
r
e
a
n
d
e
f
f
i
c
i
e
n
t
l
i
g
h
t
w
e
i
g
h
t
b
i
o
me
t
r
i
c
a
u
t
h
e
n
t
i
c
a
t
i
o
n
sc
h
e
me
,
”
I
EE
E
T
ra
n
s
a
c
t
i
o
n
s
o
n
D
e
p
e
n
d
a
b
l
e
a
n
d
S
e
c
u
re
C
o
m
p
u
t
i
n
g
,
v
o
l
.
2
0
,
n
o
.
3
,
p
p
.
2
5
7
8
–
2
5
9
2
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
T
D
S
C
.
2
0
2
2
.
3
1
8
6
9
9
9
.
[
1
3
]
D
.
B
a
n
e
r
j
e
e
a
n
d
K
.
Y
u
,
“
3
D
f
a
c
e
a
u
t
h
e
n
t
i
c
a
t
i
o
n
so
f
t
w
a
r
e
t
e
st
a
u
t
o
ma
t
i
o
n
,
”
I
E
EE
Ac
c
e
ss
,
v
o
l
.
8
,
p
p
.
4
6
5
4
6
–
4
6
5
5
8
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
0
.
2
9
7
8
8
9
9
.
[
1
4
]
N
.
D
a
l
a
l
a
n
d
B
.
T
r
i
g
g
s,
“
H
i
st
o
g
r
a
ms
o
f
o
r
i
e
n
t
e
d
g
r
a
d
i
e
n
t
s
f
o
r
h
u
m
a
n
d
e
t
e
c
t
i
o
n
,
”
i
n
P
ro
c
e
e
d
i
n
g
s
-
2
0
0
5
I
EEE
C
o
m
p
u
t
e
r
S
o
c
i
e
t
y
C
o
n
f
e
re
n
c
e
o
n
C
o
m
p
u
t
e
r
Vi
s
i
o
n
a
n
d
Pa
t
t
e
r
n
Re
c
o
g
n
i
t
i
o
n
,
C
VPR
2
0
0
5
,
I
E
EE,
2
0
0
5
,
p
p
.
8
8
6
–
8
9
3
,
d
o
i
:
1
0
.
1
1
0
9
/
C
V
P
R
.
2
0
0
5
.
1
7
7
.
[
1
5
]
S
.
G
h
a
l
i
,
I
n
t
r
o
d
u
c
t
i
o
n
t
o
g
e
o
m
e
t
r
i
c
c
o
m
p
u
t
i
n
g
.
L
o
n
d
o
n
:
S
p
r
i
n
g
e
r
L
o
n
d
o
n
,
2
0
0
8
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
1
-
8
4
8
0
0
-
1
1
5
-
2.
[
1
6
]
V
.
K
a
z
e
mi
a
n
d
J
.
S
u
l
l
i
v
a
n
,
“
O
n
e
mi
l
l
i
se
c
o
n
d
f
a
c
e
a
l
i
g
n
me
n
t
w
i
t
h
a
n
e
n
se
mb
l
e
o
f
r
e
g
r
e
ssi
o
n
t
r
e
e
s,”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
I
E
EE
C
o
m
p
u
t
e
r
S
o
c
i
e
t
y
C
o
n
f
e
re
n
c
e
o
n
C
o
m
p
u
t
e
r
V
i
si
o
n
a
n
d
Pa
t
t
e
rn
R
e
c
o
g
n
i
t
i
o
n
,
I
EEE,
J
u
n
.
2
0
1
4
,
p
p
.
1
8
6
7
–
1
8
7
4
,
d
o
i
:
1
0
.
1
1
0
9
/
C
V
P
R
.
2
0
1
4
.
2
4
1
.
[
1
7
]
J.
H
e
a
t
o
n
,
“
I
a
n
g
o
o
d
f
e
l
l
o
w
,
y
o
sh
u
a
b
e
n
g
i
o
,
a
n
d
a
a
r
o
n
c
o
u
r
v
i
l
l
e
:
d
e
e
p
l
e
a
r
n
i
n
g
,
”
G
e
n
e
t
i
c
Pr
o
g
r
a
m
m
i
n
g
a
n
d
E
v
o
l
v
a
b
l
e
M
a
c
h
i
n
e
s
,
v
o
l
.
1
9
,
n
o
.
1
–
2
,
p
p
.
3
0
5
–
3
0
7
,
J
u
n
.
2
0
1
8
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
0
7
1
0
-
017
-
9
3
1
4
-
z.
[
1
8
]
K
.
H
e
,
X
.
Z
h
a
n
g
,
S
.
R
e
n
,
a
n
d
J
.
S
u
n
,
“
D
e
e
p
r
e
si
d
u
a
l
l
e
a
r
n
i
n
g
f
o
r
i
mag
e
r
e
c
o
g
n
i
t
i
o
n
,
”
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
I
EEE
C
o
m
p
u
t
e
r
S
o
c
i
e
t
y
C
o
n
f
e
re
n
c
e
o
n
C
o
m
p
u
t
e
r
Vi
s
i
o
n
a
n
d
Pa
t
t
e
r
n
Re
c
o
g
n
i
t
i
o
n
,
p
p
.
7
7
0
–
7
7
8
,
2
0
1
6
,
d
o
i
:
1
0
.
1
1
0
9
/
C
V
P
R
.
2
0
1
6
.
9
0
.
[
1
9
]
M
.
A
l
h
a
mm
a
mi
,
C
.
P
.
O
o
i
,
W
.
H
.
T
a
n
,
a
n
d
S
.
N
y
e
a
n
c
h
e
o
n
g
,
“
F
P
G
A
h
a
r
d
w
a
r
e
i
mp
l
e
me
n
t
a
t
i
o
n
f
o
r
a
c
c
e
l
e
r
a
t
i
n
g
Q
R
d
e
c
o
d
i
n
g
,
”
J
o
u
rn
a
l
o
f
En
g
i
n
e
e
ri
n
g
a
n
d
Ap
p
l
i
e
d
S
c
i
e
n
c
e
s
,
v
o
l
.
1
1
,
n
o
.
1
4
,
p
p
.
3
2
7
3
–
3
2
7
8
,
2
0
1
6
,
d
o
i
:
j
e
a
sci
.
2
0
1
6
.
3
2
7
3
.
3
2
7
8
.
[
2
0
]
H
.
S
.
A
l
-
K
h
a
l
i
f
a
,
“
U
t
i
l
i
z
i
n
g
Q
R
c
o
d
e
a
n
d
mo
b
i
l
e
p
h
o
n
e
s
f
o
r
b
l
i
n
d
s
a
n
d
v
i
s
u
a
l
l
y
i
mp
a
i
r
e
d
p
e
o
p
l
e
,
”
i
n
C
o
m
p
u
t
e
rs
H
e
l
p
i
n
g
P
e
o
p
l
e
w
i
t
h
S
p
e
c
i
a
l
N
e
e
d
s:
1
1
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
,
I
C
C
H
P
2
0
0
8
,
L
i
n
z,
Au
s
t
ri
a
,
J
u
l
y
9
-
1
1
,
2
0
0
8
.
Pro
c
e
e
d
i
n
g
s 1
1
,
S
p
r
i
n
g
e
r
B
e
r
l
i
n
H
e
i
d
e
l
b
e
r
g
,
2
0
0
8
,
p
p
.
1
0
6
5
–
1
0
6
9
.
[
2
1
]
K
.
P
.
G
a
f
f
n
e
y
,
D
.
R
.
H
i
p
p
,
M
.
P
r
a
mm
e
r
,
D
.
K
e
n
n
e
d
y
,
L
.
B
r
a
sf
i
e
l
d
,
a
n
d
J.
M
.
P
a
t
e
l
,
“
S
Q
L
i
t
e
:
p
a
st
,
p
r
e
se
n
t
,
a
n
d
f
u
t
u
r
e
,
”
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
VLD
B
E
n
d
o
w
m
e
n
t
,
v
o
l
.
1
5
,
n
o
.
1
2
,
p
p
.
3
5
3
5
–
3
5
4
7
,
A
u
g
.
2
0
2
2
,
d
o
i
:
1
0
.
1
4
7
7
8
/
3
5
5
4
8
2
1
.
3
5
5
4
8
4
2
.
[
2
2
]
S
.
B
a
l
a
r
e
z
o
,
X
.
A
r
i
a
s,
a
n
d
K
.
Esp
í
n
,
“
R
e
mo
t
e
man
i
p
u
l
a
t
i
o
n
o
f
a
r
o
b
o
t
i
c
A
r
m
w
i
t
h
6
D
O
F
v
i
a
I
B
S
V
us
i
n
g
a
R
a
s
p
b
e
r
r
y
P
i
a
n
d
M
a
c
h
i
n
e
V
i
s
i
o
n
,
”
L
e
c
t
u
r
e
N
o
t
e
s
i
n
N
e
t
w
o
rks
a
n
d
S
y
st
e
m
s
,
p
p
.
8
4
5
–
8
5
4
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
0
3
1
-
1
0
4
6
4
-
0
_
5
8
.
[
23]
M
.
A
l
h
a
mm
a
m
i
a
n
d
S
.
M
.
H
a
mm
a
mi
,
“
A
n
F
P
G
A
-
b
a
se
d
I
P
f
o
r
r
e
c
o
g
n
i
z
i
n
g
v
i
o
l
e
n
c
e
a
g
a
i
n
s
t
c
h
i
l
d
r
e
n
,
”
M
e
t
h
o
d
sX
,
v
o
l
.
8
,
p
.
1
0
1
3
7
8
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
me
x
.
2
0
2
1
.
1
0
1
3
7
8
.
[
2
4
]
M
.
A
l
h
a
mm
a
mi
,
S
.
M
.
H
a
mm
a
m
i
,
C
.
P
.
O
o
i
,
a
n
d
W
.
H
.
T
a
n
,
“
O
p
t
i
m
i
se
d
M
L
-
b
a
se
d
sy
st
e
m
mo
d
e
l
f
o
r
a
d
u
l
t
-
c
h
i
l
d
a
c
t
i
o
n
s
r
e
c
o
g
n
i
t
i
o
n
,
”
K
S
I
I
T
r
a
n
sa
c
t
i
o
n
s
o
n
I
n
t
e
rn
e
t
a
n
d
I
n
f
o
rm
a
t
i
o
n
S
y
s
t
e
m
s
,
v
o
l
.
1
3
,
n
o
.
2
,
p
p
.
9
2
9
–
9
4
4
,
F
e
b
.
2
0
1
9
,
d
o
i
:
1
0
.
3
8
3
7
/
t
i
i
s
.
2
0
1
9
.
0
2
.
0
2
4
.
[
2
5
]
S
.
M
.
H
a
mm
a
mi
a
n
d
M
.
A
l
h
a
mm
a
m
i
,
“
V
i
si
o
n
-
b
a
se
d
sy
st
e
m
mo
d
e
l
f
o
r
d
e
t
e
c
t
i
n
g
v
i
o
l
e
n
c
e
a
g
a
i
n
st
c
h
i
l
d
r
e
n
,
”
Me
t
h
o
d
s
X
,
v
o
l
.
7
,
p
p
.
1
0
4
–
1
0
8
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
me
x
.
2
0
1
9
.
1
1
.
0
1
7
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
S
a
m
ir
M
a
r
w
a
n
H
a
m
m
a
m
i
is
a
n
a
ss
o
c
iate
p
ro
f
e
ss
o
r
in
m
a
n
a
g
e
m
e
n
t
in
f
o
rm
a
ti
o
n
s
y
ste
m
s
a
t
Dh
o
f
a
r
Un
iv
e
rsit
y
,
a
n
d
h
e
se
rv
e
s
o
n
d
if
fe
re
n
t
a
d
m
in
istratio
n
p
o
sit
io
n
s
a
n
d
c
o
m
m
it
te
e
s
a
t
Dh
o
f
a
r
Un
iv
e
r
sity
.
He
h
a
s
m
a
n
y
r
e
se
a
r
c
h
p
a
p
e
rs
in
th
e
f
ield
.
His
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
m
a
n
a
g
e
m
e
n
t
in
f
o
r
m
a
ti
o
n
sy
st
e
m
s,
k
n
o
w
led
g
e
m
a
n
a
g
e
m
e
n
t,
c
o
m
p
u
ters
f
o
r
so
c
iety
,
c
o
m
p
u
ter
v
isio
n
,
a
n
d
d
i
g
it
a
l
e
n
tre
p
re
n
e
u
rsh
i
p
.
He
re
c
e
iv
e
d
se
v
e
ra
l
r
e
se
a
r
c
h
f
u
n
d
s
in
O
m
a
n
.
He
is
a
lso
a
m
e
m
b
e
r
o
f
th
e
e
d
it
o
rial
b
o
a
r
d
/sc
ien
ti
f
ic
c
o
m
m
it
tee
s
o
f
se
v
e
r
a
l
p
e
e
r
-
re
v
ie
w
e
d
re
se
a
rc
h
jo
u
rn
a
ls a
n
d
c
o
n
f
e
re
n
c
e
s.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
sa
m
ir@d
u
.
e
d
u
.
o
m
.
M
u
h
a
m
m
a
d
Alh
a
m
m
a
m
i
is
a
re
se
a
rc
h
e
r
a
n
d
lec
tu
re
r
a
t
th
e
H
ig
h
e
r
In
stit
u
te
f
o
r
A
p
p
li
e
d
S
c
ien
c
e
s
a
n
d
T
e
c
h
n
o
l
o
g
y
in
Da
m
a
sc
u
s,
S
y
ri
a
.
His
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
c
o
m
m
u
n
ica
ti
o
n
,
S
o
C
-
F
P
G
A
a
n
d
e
m
b
e
d
d
e
d
sy
ste
m
s,
a
rti
f
icia
l
in
tell
ig
e
n
c
e
a
n
d
m
a
c
h
in
e
lea
rn
in
g
,
im
a
g
e
a
n
d
sig
n
a
l
p
ro
c
e
ss
in
g
,
a
n
d
u
P
C.
He
h
a
s
p
u
b
l
ish
e
d
se
v
e
ra
l
a
rti
c
le
s
in
jo
u
rn
a
ls
a
n
d
c
o
n
f
e
re
n
c
e
s,
su
c
h
a
s
A
d
v
a
n
c
e
s
in
V
is
u
a
l
I
n
f
o
rm
a
ti
c
s,
Da
ta
in
Br
ief
,
M
e
th
o
d
sX
,
a
n
d
Jo
u
rn
a
l
o
f
A
sia
n
F
in
a
n
c
e
,
Eco
n
o
m
ic
s
a
n
d
Bu
sin
e
ss
.
M
u
h
a
m
m
a
d
A
lh
a
m
m
a
m
i'
s
CV
sh
o
w
s
th
a
t
h
e
h
a
s
m
a
d
e
sig
n
if
ica
n
t
c
o
n
tri
b
u
ti
o
n
s
t
o
h
is
f
ield
o
f
stu
d
y
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
Mu
h
a
m
m
ad
.
A
l
h
a
m
m
a
m
i
@
h
ia
s
t.e
d
u
.
s
y
o
r
d
r.
m
h
a
m
m
a
m
i@o
u
tl
o
o
k
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.