T
E
L
K
O
M
NIKA
T
elec
o
mm
un
ica
t
io
n,
Co
m
pu
t
ing
,
E
lect
ro
nics
a
nd
Co
ntr
o
l
Vo
l.
1
8
,
No
.
6
,
Dec
em
b
er
2
0
2
0
,
p
p
.
3
3
5
7
~
3
3
6
4
I
SS
N:
1
6
9
3
-
6
9
3
0
,
ac
cr
ed
ited
First Gr
ad
e
b
y
Ke
m
e
n
r
is
te
k
d
i
k
ti,
Dec
r
ee
No
: 2
1
/E/KPT
/2
0
1
8
DOI
: 1
0
.
1
2
9
2
8
/
T
E
L
KOM
NI
KA
.
v
1
8
i
6
.
1
6
3
3
5
3357
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//jo
u
r
n
a
l.u
a
d
.
a
c.
id
/in
d
ex
.
p
h
p
/TELK
OM
N
I
K
A
I
m
pro
v
ing
f
a
ce
re
co
g
nition by
artifi
cia
l neural ne
tw
o
rk usi
ng
principa
l co
m
po
n
ent
a
na
ly
sis
Sh
a
t
ha
A.
B
a
k
er
1
,
H
esh
a
m
H
a
s
hi
m
M
o
ha
mm
ed
2
,
H
a
na
n A.
Alda
ba
g
h
3
1
,2
De
p
a
rtm
e
n
t
o
f
El
e
c
tri
c
a
l
a
n
d
Co
m
p
u
ter E
n
g
in
e
e
rin
g
,
No
r
th
e
rn
T
e
c
h
n
ica
l
Un
iv
e
rsity
,
Ira
q
3
T
h
e
G
e
n
e
ra
l
Dire
c
to
ra
te o
f
Ed
u
c
a
ti
o
n
i
n
Ni
n
e
v
e
h
G
o
v
e
rn
o
ra
te,
Ira
q
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
A
p
r
1
3
,
2
0
2
0
R
ev
i
s
ed
A
p
r
2
9
,
2
0
2
0
A
cc
ep
ted
J
u
n
2
5
,
2
0
2
0
T
h
e
f
a
c
e
-
re
c
o
g
n
it
io
n
sy
ste
m
is
a
m
o
n
g
th
e
m
o
st
e
ff
e
c
ti
v
e
p
a
tt
e
rn
r
e
c
o
g
n
it
io
n
a
n
d
im
a
g
e
a
n
a
l
y
sis
te
c
h
n
iq
u
e
s.
T
h
is
tec
h
n
iq
u
e
h
a
s
m
e
t
g
r
e
a
t
a
tt
e
n
ti
o
n
f
ro
m
a
c
a
d
e
m
ic
a
n
d
in
d
u
strial
f
ield
s
b
e
c
a
u
se
o
f
it
s
e
x
ten
siv
e
u
se
in
d
e
tec
ti
n
g
th
e
id
e
n
ti
ty
o
f
in
d
iv
id
u
a
ls
f
o
r
m
o
n
it
o
rin
g
sy
ste
m
s,
s
e
c
u
rit
y
a
n
d
m
a
n
y
o
th
e
r
p
ra
c
ti
c
a
l
f
ield
s.
In
th
is
p
a
p
e
r,
a
n
e
ff
e
c
ti
v
e
m
e
th
o
d
o
f
f
a
c
e
re
c
o
g
n
it
io
n
w
a
s
p
ro
p
o
se
d
.
T
e
n
p
e
rso
n
'
s
fa
c
e
s
i
m
a
g
e
s
w
e
re
se
l
e
c
ted
f
ro
m
OR
L
d
a
tas
e
t,
f
o
r
e
a
c
h
p
e
rso
n
(4
2
)
im
a
g
e
w
it
h
to
tal
o
f
(4
2
0
)
im
a
g
e
s
a
s
d
a
tas
e
t.
F
e
a
tu
re
s
a
re
e
x
trac
te
d
u
sin
g
p
ri
n
c
ip
le
c
o
m
p
o
n
e
n
t
a
n
a
ly
sis
P
CA
to
r
e
d
u
c
e
th
e
d
im
e
n
sio
n
a
li
ty
o
f
th
e
f
a
c
e
i
m
a
g
e
s.
F
o
u
r
m
o
d
e
ls
w
h
e
re
c
re
a
ted
,
th
e
f
irst
o
n
e
w
a
s
train
e
d
u
sin
g
f
e
e
d
f
o
r
w
a
rd
b
a
c
k
p
ro
p
a
g
a
ti
o
n
lea
rn
in
g
(F
F
BB
L
)
w
it
h
4
0
f
e
a
tu
re
s,
th
e
se
c
o
n
d
w
a
s
train
e
d
u
sin
g
5
0
f
e
a
tu
re
s
w
it
h
F
F
BBL
,
th
e
th
ird
a
n
d
f
o
u
rth
m
o
d
e
ls
w
e
r
e
train
e
d
u
sin
g
th
e
sa
m
e
f
e
a
tu
re
s
b
u
t
u
sin
g
El
m
a
n
n
e
u
ra
l
n
e
tw
o
rk
.
F
o
r
e
a
c
h
p
e
rso
n
(2
4
)
im
a
g
e
u
se
d
a
s
train
in
g
se
t
f
o
r
th
e
n
e
u
ra
l
n
e
tw
o
rk
s,
w
h
il
e
th
e
re
m
a
in
in
g
ima
g
e
s
u
se
d
a
s
tes
ti
n
g
s
e
t.
T
h
e
re
su
l
ts
sh
o
w
e
d
th
a
t
th
e
p
r
o
p
o
se
d
m
e
th
o
d
w
a
s
e
ff
e
c
ti
v
e
a
n
d
h
ig
h
ly
a
c
c
u
ra
te.
F
F
BBL
g
iv
e
a
c
c
u
ra
c
y
o
f
(9
8
.
3
3
,
9
8
.
8
0
)
w
it
h
(4
0
,
5
0
)
f
e
a
tu
re
s
re
sp
e
c
ti
v
e
l
y
,
wh
il
e
El
m
a
n
g
iv
e
s (9
8
.
3
3
,
9
5
.
1
4
)
f
o
r
w
it
h
(4
0
,
5
0
)
f
e
a
tu
re
s res
p
e
c
ti
v
e
l
y
.
K
ey
w
o
r
d
s
:
A
r
ti
f
icial
n
e
u
r
al
n
et
w
o
r
k
P
atter
n
r
ec
o
g
n
itio
n
P
r
in
cip
le
co
m
p
o
n
e
n
t a
n
al
y
s
is
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
:
Hesh
a
m
Ha
s
h
i
m
Mo
h
a
m
m
ed
,
E
lectr
o
n
ic
C
o
m
p
u
ter
C
e
n
ter
,
No
r
th
er
n
T
ec
h
n
ical
U
n
i
v
er
s
it
y
,
Un
i
v
er
s
it
y
Hi
g
h
W
a
y
Stre
et,
Mo
s
u
l,
I
r
aq
.
E
m
ail:
h
h
m
s
s
8
8
8
@
g
m
ai
l.c
o
m
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
t
e
c
h
n
i
q
u
e
o
f
p
a
t
t
e
r
n
r
e
c
o
g
n
i
t
i
o
n
i
s
o
n
e
o
f
t
h
e
m
o
s
t
s
u
c
c
e
s
s
f
u
l
t
e
c
h
n
i
q
u
e
s
i
n
t
h
e
f
i
e
l
d
o
f
i
m
a
g
e
p
r
o
c
e
s
s
i
n
g
.
R
e
c
e
n
t
l
y
,
t
h
i
s
t
e
c
h
n
o
l
o
g
y
h
a
s
b
e
e
n
u
s
e
d
f
o
r
s
e
c
u
r
i
t
y
p
u
r
p
o
s
e
s
,
a
n
d
h
a
s
b
e
c
o
m
e
c
o
m
p
a
t
i
b
l
e
w
i
t
h
s
e
c
u
r
i
ty
s
y
s
t
e
m
s
b
a
s
e
d
o
n
o
t
h
e
r
b
i
o
m
e
t
r
i
c
s
s
u
c
h
a
s
f
i
n
g
e
r
p
r
i
n
t
s
a
n
d
i
r
i
s
[
1
,
2
]
.
T
h
e
n
e
u
r
a
l
n
e
t
w
o
r
k
-
b
a
s
e
d
t
r
e
e
[
3
]
,
n
e
u
r
a
l
n
e
t
w
o
r
k
s
,
a
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s
[
4
]
a
n
d
k
e
y
c
o
m
p
o
n
e
n
t
a
n
a
l
y
s
i
s
[
5
]
a
r
e
t
h
e
c
o
m
m
o
n
m
e
t
h
o
d
s
u
s
e
d
f
o
r
f
a
c
e
r
e
c
o
g
n
i
t
i
o
n
.
P
r
i
n
c
i
p
l
e
c
o
m
p
o
n
e
n
t
a
n
a
l
y
s
i
s
(
P
C
A
)
i
s
a
s
t
a
t
i
s
t
i
c
a
l
m
e
a
s
u
r
e
m
e
n
t
m
e
t
h
o
d
t
h
a
t
r
e
d
u
c
e
s
t
h
e
l
a
r
g
e
d
i
m
e
n
s
i
o
n
s
o
f
t
h
e
i
m
a
g
e
i
n
t
h
e
d
a
t
a
s
p
a
c
e
t
o
s
m
a
l
l
e
r
d
i
m
e
n
s
i
o
n
s
.
T
h
e
n
e
w
s
p
a
c
e
s
a
r
e
o
f
t
e
n
f
e
a
t
u
r
e
s
p
a
c
e
s
,
t
h
i
s
h
e
l
p
s
t
o
r
e
d
u
c
e
t
h
e
c
a
l
c
u
l
a
t
i
o
n
s
o
f
t
h
e
i
m
a
g
e
d
a
t
a
b
a
s
e
i
n
a
c
o
n
t
r
o
l
l
e
d
w
a
y
t
o
o
b
t
a
i
n
h
i
g
h
e
r
r
e
c
o
g
n
i
t
i
o
n
a
n
d
b
e
s
t
a
c
c
u
r
a
c
y
[6
-
8]
.
P
C
A
c
a
n
b
e
u
s
e
d
f
o
r
e
x
t
r
a
c
t
i
n
g
t
h
e
f
e
a
t
u
r
e
s
f
r
o
m
a
h
u
m
a
n
f
a
c
e
i
n
t
e
n
s
i
t
y
i
m
a
g
e
.
T
h
e
b
a
s
i
c
f
a
c
e
d
a
t
a
b
a
s
e
i
s
d
e
f
i
n
e
d
a
s
a
l
l
t
r
a
i
n
i
n
g
p
a
t
t
e
r
n
s
o
f
t
h
e
s
a
m
e
s
i
z
e
a
n
d
c
o
n
f
i
g
u
r
a
t
i
o
n
.
I
n
t
h
i
s
w
o
r
k
w
e
u
t
i
l
i
z
e
d
f
a
c
i
a
l
r
e
c
o
g
n
i
t
i
o
n
f
r
o
m
t
h
e
O
R
L
d
a
t
a
b
a
s
e
.
N
e
u
r
a
l
n
e
t
w
o
r
k
s
g
a
v
e
h
i
g
h
e
f
f
i
c
i
e
n
c
y
i
n
c
o
m
p
u
t
a
t
i
o
n
a
l
t
e
c
h
n
i
q
u
e
s
t
o
p
a
t
t
e
r
n
r
e
c
o
g
n
i
t
i
o
n
a
n
d
i
m
a
g
e
p
r
o
c
e
s
s
i
n
g
,
w
h
i
c
h
l
e
d
t
o
t
h
e
i
r
w
i
d
e
l
y
u
s
e
i
n
t
h
i
s
f
i
e
l
d
[
9
,
1
0
]
.
I
n
t
h
i
s
r
e
s
e
a
r
c
h
,
t
w
o
t
y
p
e
s
o
f
n
e
u
r
a
l
n
e
t
w
o
r
k
s
w
e
r
e
u
s
e
d
:
a
f
e
e
d
b
a
c
k
n
e
t
w
o
r
k
a
n
d
t
h
e
c
u
r
r
e
n
t
f
r
e
q
u
e
n
c
y
n
e
t
w
o
r
k
(
E
l
m
a
n
)
,
b
o
t
h
n
e
t
w
o
r
k
s
g
a
v
e
h
i
g
h
a
c
c
u
r
a
c
y
.
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.
1
8
,
No
.
6
,
Dec
em
b
er
2020:
33
5
7
-
33
64
3358
2.
RE
L
AT
E
D
WO
RK
S
T
h
e
r
esear
ch
er
s
in
tr
o
d
u
ce
a
r
eliab
le
an
d
au
to
m
ated
s
y
s
te
m
th
at
d
ep
en
d
o
n
u
s
in
g
m
u
lt
i
-
a
lg
o
r
ith
m
s
f
o
r
f
ac
e
r
ec
o
g
n
it
io
n
an
d
it
's
ap
p
lied
o
n
s
tu
d
en
ts
f
ac
es,
t
h
e
s
y
s
te
m
p
r
o
p
o
s
e
u
s
i
n
g
b
o
th
p
r
in
cip
al
co
m
p
o
n
e
n
t
an
al
y
s
is
(
P
C
A
)
a
s
w
ell
a
s
h
is
to
g
r
a
m
o
f
o
r
ien
ted
g
r
ad
ie
n
t
(
HOG)
f
o
r
f
ea
tu
r
e
e
x
tr
ac
tio
n
a
n
d
ar
tif
ic
ial
n
e
u
r
al
n
et
w
o
r
k
(
A
N
N)
f
o
r
r
ec
o
g
n
i
tio
n
,
co
u
p
led
w
it
h
h
elp
v
ec
to
r
m
ac
h
i
n
e
(
SV
M)
.
T
h
e
ac
cu
r
ac
y
o
f
s
y
s
te
m
r
ec
o
g
n
itio
n
w
a
s
9
6
.
8
%
[
1
1
]
.
T
h
e
r
esear
ch
er
s
i
n
[
1
2
]
p
r
esen
ts
a
Face
r
ec
o
g
n
itio
n
s
y
s
te
m
in
w
h
ich
p
r
in
cip
al
co
m
p
o
n
e
n
t
an
a
l
y
s
is
(
P
C
A
)
an
d
b
ac
k
p
r
o
p
ag
atio
n
n
eu
r
al
n
et
w
o
r
k
s
(
B
P
NN)
is
p
er
f
o
r
m
ed
w
h
er
e
u
s
ed
f
o
r
f
ac
e
id
en
ti
f
icatio
n
a
n
d
v
er
i
f
icat
io
n
w
h
ile
t
h
e
y
i
m
p
le
m
e
n
t
f
ac
e
r
ec
o
g
n
itio
n
s
y
s
te
m
is
d
o
n
e
b
y
u
s
i
n
g
n
e
u
r
a
l n
et
w
o
r
k
,
I
ts
ac
ce
p
tan
ce
r
atio
w
a
s
g
r
ea
te
r
th
an
9
0
% f
o
r
th
e
p
r
o
p
o
s
ed
m
atch
i
n
g
m
et
h
o
d
s
.
In
[
1
3
]
,
th
e
r
esear
ch
er
s
i
n
tr
o
d
u
ce
a
f
ac
e
r
ec
o
g
n
itio
n
s
y
s
t
e
m
w
h
ic
h
u
s
e
P
C
A
f
o
r
d
i
m
en
s
io
n
alit
y
r
ed
u
ctio
n
a
n
d
f
ea
tu
r
e
e
x
tr
ac
tio
n
,
w
it
h
SVM
w
er
e
u
s
ed
as c
la
s
s
i
f
ier
.
T
h
e
s
y
s
te
m
ac
cu
r
ac
y
w
a
s
9
6
.
8
%.
I
n
2
0
1
3
,
o
th
er
r
esear
ch
er
s
p
r
o
p
o
s
e
d
f
ace
r
eco
g
n
itio
n
p
a
p
er
u
s
in
g
wav
elet
tr
an
s
f
o
r
m
an
d
PC
A
with
n
eu
r
al
n
etwo
r
k
b
ack
p
r
o
p
ag
atio
n
.
W
av
elet
tr
an
s
f
o
r
m
atio
n
s
wer
e
u
s
ed
t
o
calcu
late
th
e
lev
el
o
f
im
ag
e
d
eco
m
p
o
s
itio
n
.
Usi
n
g
th
r
ee
lev
els
th
e
im
ag
e
was
d
is
ass
em
b
led
.
T
h
e
s
tu
d
y
s
h
o
wed
th
e
th
ir
d
lev
el
is
th
e
b
est
lev
el
o
f
d
is
ass
em
b
l
y
[
1
4
]
.
I
n
th
e
o
th
er
w
o
r
k
[
1
5
]
,
a
d
escr
ip
to
r
is
o
b
tain
ed
b
y
p
r
o
j
ec
tin
g
a
f
ac
e
as
an
in
p
u
t
o
n
a
ei
g
e
n
f
ac
e
s
p
ac
e,
th
en
t
h
e
d
escr
ip
to
r
is
f
ed
as
an
i
n
p
u
t
to
ea
ch
o
b
j
ec
t'
s
p
r
e
-
tr
ai
n
ed
n
et
w
o
r
k
.
T
h
e
y
d
eter
m
i
n
e
a
n
d
r
ep
o
r
t
th
e
m
a
x
i
m
u
m
o
u
tp
u
t
i
f
i
t
p
ass
es t
h
e
th
r
es
h
o
ld
p
r
ev
io
u
s
l
y
estab
lis
h
ed
f
o
r
th
e
r
ec
o
g
n
it
i
o
n
s
y
s
te
m
.
3.
RE
S
E
ARCH
M
E
T
H
O
D
So
m
e
p
ar
ticu
lar
m
et
h
o
d
o
lo
g
i
es
n
ee
d
to
b
e
f
o
llo
w
ed
in
o
r
d
er
to
im
p
le
m
e
n
t
t
h
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
d
ea
lin
g
w
i
th
t
h
e
f
ac
e
r
ec
o
g
n
itio
n
s
y
s
te
m
.
Fo
r
th
is
p
r
o
ce
s
s
,
ce
r
tain
s
tep
s
n
ee
d
to
b
e
tak
en
.
T
h
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
i
n
cl
u
d
ed
m
aj
o
r
s
tep
s
ar
e
as
f
o
llo
w
s
,
s
h
o
w
n
i
n
Fi
g
u
r
e
1.
a.
P
r
e
p
r
o
ce
s
s
in
g
:
I
n
t
h
is
s
tep
,
th
e
f
ac
e
d
etec
tio
n
p
r
o
ce
s
s
ch
ec
k
s
if
t
h
e
i
m
a
g
e
i
s
a
f
ac
e
i
m
a
g
e
o
r
n
o
t.
T
h
e
f
ace
cr
o
p
p
in
g
o
n
l
y
f
r
o
m
t
h
e
en
t
ir
e
i
m
ag
e
u
s
in
g
t
h
e
Vio
la
-
J
o
n
e
s
alg
o
r
ith
m
[
1
6
]
.
T
r
an
s
f
o
r
m
t
h
e
i
m
ag
e
o
f
th
e
f
ac
e
cr
o
p
p
ed
to
s
ize
(
5
0
×6
0
)
,
as sh
o
w
n
i
n
Fi
g
u
r
e
2
.
b.
Fin
d
i
n
g
t
h
e
E
i
g
en
Data
Ma
tr
i
x
to
b
e
u
s
ed
in
s
u
b
s
eq
u
en
t step
s
to
ex
tr
a
ct
f
ea
t
u
r
e
[
1
7
]
,
Fig
u
r
e
3
r
ep
r
esen
ts
th
e
f
lo
w
c
h
ar
t
f
o
r
th
e
f
i
n
d
i
n
g
o
f
th
e
E
i
g
e
n
m
atr
i
x
.
c.
E
x
tr
ac
tin
g
t
h
e
f
ea
t
u
r
es
o
f
th
e
f
ac
es
u
s
in
g
t
h
e
E
i
g
en
v
ec
to
r
s
o
f
th
e
f
ac
e
s
"
ca
lcu
lated
b
y
s
te
p
2
"
,
Fig
u
r
e
4
r
ep
r
esen
t th
e
f
lo
w
ch
ar
t o
f
t
h
e
ex
tr
ac
tio
n
f
ea
t
u
r
es p
r
o
ce
s
s
.
d.
T
r
ain
in
g
a
n
d
test
i
n
g
o
f
t
w
o
a
r
tif
icial
n
e
u
r
al
n
e
t
w
o
r
k
s
.
O
n
e
o
f
th
e
m
is
o
f
t
y
p
e
FF
B
B
L
a
n
d
th
e
o
t
h
er
is
E
l
m
a
n
Neu
r
al
n
et
w
o
r
k
.
Fig
u
r
e
1
.
B
lo
ck
d
iag
r
a
m
o
f
t
h
e
s
y
s
te
m
Fig
u
r
e
2
.
s
tep
s
o
f
P
r
ep
r
o
ce
s
s
in
g
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
I
mp
r
o
vin
g
fa
ce
r
ec
o
g
n
itio
n
b
y
a
r
tifi
cia
l n
eu
r
a
l n
etw
o
r
k
u
s
in
g
… (
S
h
a
th
a
A
.
B
a
ke
r
)
3359
Fig
u
r
e
3
.
S
y
s
te
m
f
lo
w
ch
ar
t o
f
ca
lcu
lati
n
g
E
ig
e
n
m
a
tr
ix
Fig
u
r
e
4
.
S
y
s
te
m
f
lo
w
ch
ar
t
f
o
r
f
in
d
i
n
g
f
ac
e
f
ea
tu
r
es
u
s
in
g
E
ig
en
m
atr
i
x
3
.
1
.
B
a
ck
pro
pa
g
a
t
io
n net
wo
rk
BB
N
h
a
s
p
r
o
v
e
d
s
u
c
c
e
s
s
f
u
l
i
n
i
d
e
n
t
i
f
y
i
n
g
a
n
d
r
e
c
o
g
n
i
t
i
o
n
p
a
t
t
e
r
n
s
[
1
8
,
1
9
]
.
I
t
i
s
a
k
i
n
d
o
f
s
u
p
e
r
v
i
s
e
d
l
e
a
r
n
i
n
g
n
e
tw
o
r
k
.
T
h
e
b
a
s
i
s
o
f
i
t
s
w
o
r
k
d
e
p
e
n
d
s
o
n
t
h
e
g
r
a
d
u
a
l
r
e
g
r
e
s
s
i
o
n
m
e
t
h
o
d
u
s
e
d
t
o
u
p
d
a
t
e
t
h
e
w
e
i
g
h
t
v
a
l
u
e
s
t
o
f
i
n
d
t
h
e
l
o
w
e
s
t
m
e
a
n
s
q
u
a
r
e
e
r
r
o
r
b
e
tw
e
e
n
t
h
e
o
u
t
p
u
t
v
a
l
u
e
s
o
f
t
h
e
n
e
tw
o
r
k
a
n
d
t
h
e
t
a
r
g
e
t
v
a
l
u
e
s
.
T
h
e
r
e
f
o
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.
1
8
,
No
.
6
,
Dec
em
b
er
2020:
33
5
7
-
33
64
3360
t
h
e
u
p
d
a
t
e
d
w
e
i
g
h
t
s
a
r
e
u
s
e
d
i
n
e
a
c
h
l
a
y
e
r
o
f
t
h
e
n
e
t
w
o
r
k
t
o
b
e
g
i
n
w
i
t
h
t
h
e
o
u
t
p
u
t
l
a
y
e
r
a
n
d
e
n
d
w
i
t
h
t
h
e
i
n
p
u
t
l
a
y
e
r
,
s
o
i
t
i
s
c
a
l
l
e
d
t
h
e
b
a
c
k
p
r
o
p
a
g
a
t
i
o
n
[
2
0
]
,
a
n
d
F
i
g
u
r
e
5
i
l
l
u
s
t
r
a
t
e
s
t
h
e
a
r
c
h
i
t
e
c
t
u
r
e
o
f
t
h
i
s
n
e
t
w
o
r
k
.
T
h
e
tr
ain
in
g
o
f
t
h
e
b
ac
k
P
r
o
p
a
g
atio
n
n
et
w
o
r
k
g
o
es th
r
o
u
g
h
t
w
o
p
h
ase
s
[
2
1
]
:
Feed
f
o
r
w
ar
d
s
tag
e:
T
h
e
i
n
p
u
t
f
r
o
m
t
h
e
i
n
p
u
t
la
y
er
m
o
v
es
to
th
e
h
id
d
en
la
y
er
(
s
)
ac
c
o
r
d
in
g
to
th
e
ir
n
u
m
b
er
,
en
d
in
g
w
it
h
t
h
e
o
u
t
p
u
t
la
y
er
,
an
d
th
e
n
co
m
p
ar
i
n
g
th
e
ac
t
u
al
o
u
tp
u
t
v
al
u
es
with
t
h
e
d
esire
d
o
u
tp
u
t v
a
lu
e
s
to
ca
lcu
late
t
h
e
d
if
f
er
e
n
ce
b
et
w
ee
n
t
h
e
m
,
w
h
i
ch
r
ep
r
esen
ts
t
h
e
er
r
o
r
v
alu
e
.
Feed
b
ac
k
p
h
ase:
At
t
h
is
s
ta
g
e,
th
e
w
ei
g
h
ts
o
f
th
e
g
r
id
ar
e
ad
j
u
s
ted
d
ep
en
d
in
g
o
n
th
e
er
r
o
r
v
alu
e.
T
h
is
p
r
o
ce
s
s
co
n
tin
u
es
u
n
til th
e
tr
u
e
o
u
tp
u
t v
al
u
e
b
ec
o
m
e
s
as c
lo
s
e
as p
o
s
s
ib
le
to
th
e
d
esire
d
o
u
tp
u
t
v
al
u
e.
Fig
u
r
e
5
.
A
r
ch
itectu
r
e
o
f
FF
B
B
L
3
.
2
.
E
l
m
a
n
net
w
o
rk
T
h
e
E
l
m
a
n
n
et
w
o
r
k
is
a
s
p
ec
ial
k
in
d
o
f
b
ac
k
p
r
o
p
ag
atio
n
n
et
w
o
r
k
s
.
I
t
i
s
o
n
e
o
f
t
h
e
m
o
s
t
f
a
m
o
u
s
iter
ativ
e
n
et
w
o
r
k
s
.
I
t
h
as
b
e
en
u
s
ed
i
n
t
h
e
f
ield
s
o
f
r
ec
o
g
n
i
tio
n
a
n
d
clas
s
i
f
icatio
n
to
co
n
tain
a
d
y
n
a
m
ic
m
e
m
o
r
y
t
h
at
ca
n
b
e
u
s
ed
to
r
etr
iev
e
th
e
h
id
d
en
la
y
er
to
th
e
in
p
u
t
la
y
er
,
th
u
s
s
p
ee
d
in
g
u
p
th
e
n
et
w
o
r
k
.
T
h
e
E
lm
a
n
n
et
w
o
r
k
co
n
s
is
t
s
o
f
th
e
i
n
p
u
t
a
n
d
o
u
tp
u
t
la
y
er
s
in
ad
d
itio
n
to
th
e
h
id
d
en
la
y
er
.
I
t
h
as
p
r
o
ce
s
s
in
g
u
n
i
ts
eq
u
al
to
th
e
n
u
m
b
er
o
f
p
r
o
ce
s
s
in
g
u
n
its
in
t
h
e
h
id
d
en
la
y
er
.
T
h
ese
u
n
its
s
er
v
e
a
s
m
e
m
o
r
y
to
s
to
r
e
th
e
p
r
ev
io
u
s
s
tate
[
2
2
,
2
3
]
.
At
t
h
e
b
eg
i
n
n
in
g
o
f
t
h
e
tr
ain
i
n
g
,
t
h
e
p
r
o
ce
s
s
in
g
u
n
its
ar
e
g
iv
en
ze
r
o
v
al
u
e
s
an
d
th
e
co
r
r
esp
o
n
d
in
g
w
ei
g
h
ts
ar
e
s
in
g
le
v
al
u
es t
h
en
ad
j
u
s
t d
u
r
in
g
tr
ain
in
g
.
T
h
e
p
r
ev
io
u
s
v
al
u
e
s
ar
e
s
to
r
ed
f
o
r
th
e
h
id
d
en
la
y
er
to
b
e
re
-
en
ter
ed
b
y
th
e
in
p
u
t
la
y
er
af
ter
th
e
w
eig
h
t
s
h
a
v
e
b
ee
n
ad
j
u
s
ted
.
T
h
e
in
s
er
tio
n
o
f
th
e
h
id
d
en
la
y
er
is
th
e
r
esu
lt
o
f
t
h
e
in
p
u
t
v
al
u
es
m
u
ltip
lied
b
y
th
e
w
ei
g
h
t
af
ter
ad
d
in
g
b
ias
v
al
u
es.
Us
in
g
th
e
b
ac
k
-
p
r
o
p
ag
atio
n
f
r
eq
u
en
c
y
o
f
th
e
er
r
o
r
,
th
e
weig
h
ts
ar
e
ad
j
u
s
ted
an
d
t
h
e
n
e
t
w
o
r
k
is
g
iv
e
n
t
h
e
ab
ilit
y
to
r
ec
o
g
n
itio
n
p
atter
n
s
th
r
o
u
g
h
d
i
f
f
er
e
n
t iter
ati
v
e
p
h
a
s
es a
n
d
Fi
g
u
r
e
6
illu
s
tr
ates th
e
ar
ch
itectu
r
e
o
f
E
l
m
a
n
n
et
w
o
r
k
[
2
4
]
.
T
h
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
u
s
ed
t
w
o
s
et
s
o
f
f
ea
t
u
r
es
4
0
an
d
5
0
r
esp
ec
tiv
l
y
.
T
h
ese
f
ea
t
u
r
es
ar
e
ex
tr
ac
te
d
u
s
i
n
g
t
h
e
eig
e
n
f
ac
e
al
g
o
r
ith
m
ill
u
s
tr
ated
in
Fig
u
r
e
2
.
E
ac
h
s
et
o
f
f
ea
tu
r
e
s
ar
e
u
s
ed
to
T
r
ain
t
w
o
t
y
p
e
s
o
f
ar
tif
icial
n
e
u
r
al
n
et
w
o
r
k
s
f
ee
d
f
o
r
w
ar
d
b
ac
k
p
r
o
b
ag
atio
n
lea
r
n
in
g
a
n
d
E
l
m
a
n
n
e
u
r
al
n
et
w
o
r
k
.
T
h
ese
n
et
w
o
r
k
s
w
a
s
tr
ain
ed
u
s
i
n
g
t
h
e
L
ev
e
n
b
e
r
g
-
Ma
r
q
u
ar
d
t B
ac
k
p
r
o
p
ag
atio
n
alg
o
r
it
h
m
f
o
r
b
ac
k
p
r
o
b
ag
atio
n
lear
n
i
n
g
[
2
5
]
.
F
ig
u
r
e
6
.
A
r
ch
itectu
r
e
o
f
E
l
m
an
n
et
w
o
r
k
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
I
mp
r
o
vin
g
fa
ce
r
ec
o
g
n
itio
n
b
y
a
r
tifi
cia
l n
eu
r
a
l n
etw
o
r
k
u
s
in
g
… (
S
h
a
th
a
A
.
B
a
ke
r
)
3361
4.
RE
SU
L
T
S
A
ND
ANA
L
YS
I
S
4
.1
.
Art
if
icia
l
neura
l net
wo
rk
o
f
f
ee
d f
o
rw
a
rd
ba
ck
pro
pa
g
a
t
io
n lea
rning
4
.
1
.
1
.
F
F
B
B
L
t
ra
ined w
it
h 4
0
f
ea
t
ures
T
h
e
i
n
p
u
t
la
y
er
in
t
h
is
n
e
u
r
al
n
et
w
o
r
k
h
a
s
4
0
n
o
d
es
a
n
d
t
h
e
o
u
tp
u
t
la
y
er
h
as
10
n
o
d
es,
Fi
g
u
r
e
7
(
a
)
illu
s
tr
ates
t
h
e
to
p
o
lo
g
y
o
f
t
h
i
s
n
et
w
o
r
k
.
T
h
e
tr
ain
i
n
g
p
r
o
ce
s
s
to
o
k
3
5
m
i
n
u
tes
3
3
s
ec
o
n
d
s
an
d
t
h
e
n
eu
r
al
n
et
w
o
r
k
r
ea
c
h
ed
s
tab
il
it
y
af
t
er
2
1
E
p
o
ch
.
T
h
is
n
et
w
o
r
k
ac
cu
r
ac
y
is
9
8
.
3
3
%
.
N
et
w
o
r
k
p
er
f
o
r
m
a
n
ce
w
as
m
ea
s
u
r
ed
u
s
i
n
g
MSE
an
d
it
's i
llu
s
tr
ated
in
Fi
g
u
r
e
7
(
b
)
.
(
a)
(
b
)
Fig
u
r
e
7
.
FF
B
B
L
ar
tif
icia
l n
e
u
r
al
n
et
w
o
r
k
tr
ain
ed
w
it
h
4
0
f
e
atu
r
es
; (
a)
n
et
w
o
r
k
to
p
o
lo
g
y
a
n
d
(
b
)
p
e
r
f
o
r
m
a
n
ce
c
u
r
v
e
4
.
1
.
2
.
F
F
B
B
L
t
ra
ined w
it
h 5
0
f
ea
t
ures
I
n
th
e
i
n
p
u
t
la
y
er
5
0
n
o
d
es
o
f
t
h
is
n
e
u
r
al
n
et
w
o
r
k
a
n
d
o
u
tp
u
t
la
y
er
1
0
n
o
d
es,
Fig
u
r
e
8
(
a
)
illu
s
tr
ate
s
th
e
to
p
o
lo
g
y
o
f
th
is
n
et
w
o
r
k
.
T
h
e
tr
ain
in
g
p
r
o
ce
s
s
to
o
k
2
4
m
i
n
u
te
s
a
n
d
5
5
s
ec
o
n
d
s
to
r
ea
ch
a
s
tate
o
f
s
tab
ilit
y
af
ter
30
E
p
o
ch
.
T
h
is
n
et
w
o
r
k
r
ec
o
g
n
ized
f
ac
e
s
w
it
h
9
8
.
8
0
%
ac
cu
r
ac
y
.
N
e
t
w
o
r
k
p
er
f
o
r
m
an
ce
w
as
m
ea
s
u
r
ed
u
s
i
n
g
MSE
an
d
it
's ill
u
s
tr
ated
in
Fi
g
u
r
e
8
(
b
)
.
(
a)
(
b
)
Fig
u
r
e
8
.
FF
B
B
L
ar
tif
icia
l n
e
u
r
al
n
et
w
o
r
k
tr
ain
ed
w
it
h
5
0
f
e
atu
r
es
;
(
a)
n
et
w
o
r
k
to
p
o
lo
g
y
a
n
d
(
b
)
p
e
r
f
o
r
m
a
n
ce
c
u
r
v
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.
1
8
,
No
.
6
,
Dec
em
b
er
2020:
33
5
7
-
33
64
3362
4
.2
.
E
l
m
a
n a
rt
if
icia
l neura
l net
w
o
rk
4
.
2
.
1
.
T
he
net
w
o
rk
t
ra
ined o
n 4
0
f
ea
t
ures
I
n
t
h
e
i
n
p
u
t
l
a
y
e
r
4
0
n
o
d
e
s
o
f
t
h
i
s
n
e
u
r
a
l
n
e
tw
o
r
k
a
n
d
o
u
t
p
u
t
l
a
y
e
r
1
0
n
o
d
e
s
,
t
h
e
t
o
p
o
l
o
g
y
o
f
t
h
i
s
n
e
t
w
o
r
k
i
s
s
h
o
w
n
i
n
F
i
g
u
r
e
9
(
a
)
.
T
h
e
t
r
a
i
n
i
n
g
p
r
o
c
e
s
s
t
o
o
k
3
5
m
i
n
u
t
e
s
a
n
d
3
3
s
e
c
o
n
d
s
t
o
r
e
a
c
h
a
s
t
a
t
e
o
f
s
t
a
b
i
l
i
t
y
a
f
t
e
r
4
1
E
p
o
c
h
.
T
h
i
s
n
e
tw
o
r
k
r
e
c
o
g
n
i
z
e
d
t
h
e
f
a
c
e
s
b
y
9
8
.
3
3
%
c
o
r
r
e
c
t
l
y
,
F
i
g
u
r
e
9
(
b
)
s
h
o
w
s
t
h
e
M
S
E
p
e
r
f
o
r
m
a
n
c
e
c
u
r
v
e
.
(
a)
(
b)
Fig
u
r
e
9
.
E
l
m
an
ar
ti
f
icial
n
e
u
r
al
n
et
w
o
r
k
tr
ai
n
ed
w
i
th
4
0
f
ea
tu
r
es
; (
a)
n
et
w
o
r
k
to
p
o
lo
g
y
a
n
d
(
b
)
p
e
r
f
o
r
m
a
n
ce
c
u
r
v
e
4
.
2
.
2
.
Net
w
o
rk
t
ra
ined o
n 5
0
pro
pert
ies
T
h
e
in
p
u
t
la
y
er
h
as
5
0
n
o
d
es
an
d
1
0
n
o
d
es
in
th
e
o
u
tp
u
t
la
y
er
,
Fig
u
r
e
1
0
(
a
)
illu
s
tr
ates
t
h
e
to
p
o
lo
g
y
o
f
t
h
is
n
et
w
o
r
k
.
T
h
e
tr
ain
in
g
p
r
o
ce
s
s
to
o
k
4
2
m
i
n
u
tes
4
4
s
ec
o
n
d
s
an
d
r
ea
c
h
ed
s
tab
il
it
y
a
f
ter
2
5
E
p
o
ch
.
T
h
is
n
et
w
o
r
k
r
ec
o
g
n
ized
f
ac
es
w
i
t
h
9
5
.
1
4
%
ac
cu
r
ac
y
,
a
n
d
Fig
u
r
e
1
0
(
b
)
s
h
o
w
s
t
h
e
MSE
cu
r
v
e
.
T
h
e
ac
cu
r
ac
y
o
f
f
ac
e
r
ec
o
g
n
i
tio
n
o
f
t
h
e
p
r
o
p
o
s
ed
m
et
h
o
d
is
v
er
y
h
i
g
h
.
FF
B
B
L
h
a
s
(
9
8
.
3
3
,
9
8
.
8
0
)
ac
cu
r
ac
y
,
w
h
ile
E
l
m
a
n
h
a
s
(
9
8
.
3
3
,
9
5
.
1
4
)
ac
cu
r
ac
y
f
o
r
(
4
0
,
5
0
)
f
ea
tu
r
es,
r
esp
ec
tiv
el
y
.
T
h
e
T
a
b
le
1
s
u
m
m
ar
ize
th
e
4
m
o
d
u
le
s
an
d
th
eir
r
elate
d
r
esu
lts
i
n
f
o
r
m
atio
n
.
(
a)
(
b
)
Fig
u
r
e
1
0
.
E
lm
a
n
ar
ti
f
icial
n
e
u
r
al
n
et
w
o
r
k
tr
ai
n
ed
w
it
h
5
0
f
e
atu
r
es
; (
a)
n
et
w
o
r
k
to
p
o
lo
g
y
an
d
(
b
)
p
e
r
f
o
r
m
a
n
ce
c
u
r
v
e
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
I
mp
r
o
vin
g
fa
ce
r
ec
o
g
n
itio
n
b
y
a
r
tifi
cia
l n
eu
r
a
l n
etw
o
r
k
u
s
in
g
… (
S
h
a
th
a
A
.
B
a
ke
r
)
3363
T
ab
le
1
.
Fin
al
r
esu
lt
s
s
u
m
m
ar
y
N
e
t
w
o
r
k
t
y
p
e
N
u
mb
e
r
o
f
f
e
a
t
u
r
e
s
N
u
mb
e
r
o
f
e
p
o
c
h
s
T
r
a
i
n
i
n
g
t
i
me
M
i
n
:
S
e
c
A
c
c
u
r
a
c
y
F
F
B
B
L
40
2
1
3
5
:
3
3
9
8
.
3
3
%
50
30
2
4
:
5
5
9
8
.
8
0
%
El
man
40
41
3
5
:
3
3
9
8
.
3
3
%
50
25
4
2
:
4
4
9
5
.
1
4
%
5.
CO
NCLOS
I
O
N
F
a
c
e
r
e
c
o
g
n
i
t
i
o
n
i
s
a
m
o
n
g
t
h
e
m
o
s
t
c
o
m
m
o
n
a
p
p
l
i
c
a
t
i
o
n
s
i
n
m
a
n
y
a
r
e
a
s
w
h
i
c
h
c
a
n
b
e
u
s
e
d
a
s
a
r
e
p
l
a
c
e
m
e
n
t
t
o
a
p
a
s
s
w
o
r
d
o
r
f
o
r
i
d
e
n
t
i
f
i
c
a
t
i
o
n
o
f
c
r
i
m
i
n
a
l
s
.
I
n
t
h
i
s
w
o
r
k
a
p
r
o
p
o
s
e
d
m
e
t
h
o
d
f
o
r
F
a
c
e
r
e
c
o
g
n
i
t
i
o
n
b
y
A
N
N
U
s
i
n
g
P
C
A
w
a
s
p
r
e
s
e
n
t
e
d
.
W
e
c
a
n
i
n
f
e
r
f
r
o
m
t
h
e
r
e
s
u
l
t
t
h
a
t
t
h
e
r
e
i
s
a
n
i
n
v
e
r
s
e
r
e
l
a
t
i
o
n
b
e
t
w
e
e
n
b
o
t
h
t
h
e
n
u
m
b
e
r
o
f
f
e
a
t
u
r
e
s
e
x
t
r
a
c
t
e
d
a
n
d
t
h
e
n
u
m
b
e
r
o
f
E
p
o
c
h
s
t
h
a
t
i
s
w
h
e
n
t
h
e
f
e
a
t
u
r
e
s
i
n
c
r
e
a
s
e
t
h
e
E
p
o
c
h
s
n
u
m
b
e
r
d
e
c
r
e
a
s
e
.
I
n
e
i
t
h
e
r
c
a
s
e
t
h
e
r
e
c
o
g
n
i
t
i
o
n
a
c
c
u
r
a
c
y
i
s
h
i
g
h
.
I
n
F
F
B
B
L
w
i
t
h
5
0
f
e
a
t
u
r
e
s
,
t
h
e
r
e
c
o
g
n
i
t
i
o
n
a
c
c
u
r
a
c
y
i
s
h
i
g
h
c
o
m
p
a
r
i
n
g
w
i
t
h
E
l
m
a
n
w
i
t
h
t
h
e
s
a
m
e
n
u
m
b
e
r
o
f
f
e
a
t
u
r
e
s
,
a
l
s
o
t
h
e
t
r
a
i
n
i
n
g
t
i
m
e
i
n
c
r
e
a
s
e
s
f
r
o
m
2
4
:
5
5
t
o
4
2
:
4
4
.
RE
F
E
R
E
NC
E
S
[1
]
P
ra
j
o
y
P
o
d
d
e
r,
A
.
H.
M
S
h
a
h
a
riar
P
a
rv
e
z
,
M
d
.
M
iza
n
u
r
Ra
h
m
a
n
,
T
a
n
v
ir
Z
a
m
a
n
Kh
a
n
,
“
Ra
m
i
f
ic
a
ti
o
n
s
a
n
d
Dim
in
u
ti
o
n
o
f
Im
a
g
e
No
ise
in
Iris
Re
c
o
g
n
it
io
n
S
y
ste
m
,
”
Co
n
fer
e
n
c
e
:
2
0
1
8
IE
EE
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Cu
rr
e
n
t
T
re
n
d
s to
w
a
rd
s C
o
n
v
e
rg
i
n
g
T
e
c
h
n
o
lo
g
ies
At
:
In
d
i
a
,
p
p
.
2
0
5
-
2
1
1
,
2
0
1
8
.
[2
]
A
.
G
e
o
rg
e
a
n
d
A
.
Ro
u
tray
,
“
A
s
c
o
re
lev
e
l
f
u
sio
n
m
e
th
o
d
f
o
r
e
y
e
m
o
v
e
m
e
n
t
b
io
m
e
tri
c
s,”
Pa
tt
e
rn
Rec
o
g
n
it
.
L
e
tt
.
,
v
o
l.
8
2
,
p
p
.
2
0
7
-
2
1
5
,
2
0
1
6
.
d
o
i:
1
0
.
1
0
1
6
/j
.
p
a
trec
.
2
0
1
5
.
1
1
.
0
2
0
.
[3
]
M
.
Zh
a
n
g
a
n
d
J.
F
u
lch
e
r,
“
F
a
c
e
p
e
rsp
e
c
ti
v
e
u
n
d
e
rsta
n
d
i
n
g
u
sin
g
a
rti
f
i
c
ial
n
e
u
ra
l
n
e
t
w
o
rk
g
ro
u
p
-
b
a
se
d
tree
,
”
IEE
E
In
t.
C
o
n
f
.
Ima
g
e
Pro
c
e
ss
.
,
v
o
l.
3
,
p
p
.
4
7
5
-
4
7
8
,
1
9
9
6
.
d
o
i:
1
0
.
1
1
0
9
/
i
c
ip
.
1
9
9
6
.
5
6
0
5
3
4
.
[4
]
M
.
M
.
Ka
sa
r,
D.
Bh
a
tt
a
c
h
a
r
y
y
a
,
a
n
d
T
.
H.
Ki
m
,
“
F
a
c
e
re
c
o
g
n
it
io
n
u
sin
g
n
e
u
ra
l
n
e
tw
o
rk
:
A
re
v
ie
w
,
”
In
t.
J
.
S
e
c
u
r.
it
s
Ap
p
l
.
,
v
o
l.
1
0
,
n
o
.
3
,
p
p
.
8
1
-
1
0
0
,
2
0
1
6
.
d
o
i:
1
0
.
1
4
2
5
7
/i
jsia.
2
0
1
6
.
1
0
.
3
.
0
8
.
[5
]
T
.
F
.
Ka
rim
,
M
.
S
.
H.
L
ip
u
,
M
.
L
.
Ra
h
m
a
n
,
a
n
d
F
.
S
u
l
tan
a
,
“
F
a
c
e
re
c
o
g
n
it
io
n
u
sin
g
P
CA
-
b
a
se
d
m
e
th
o
d
,
”
ICAM
S
2
0
1
0
-
Pro
c
.
2
0
1
0
I
EE
E
I
n
t.
C
o
n
f
.
Ad
v
.
M
a
n
a
g
.
S
c
i.
,
v
o
l.
3
,
p
p
.
1
5
8
-
1
6
2
,
2
0
1
0
.
d
o
i:
1
0
.
1
1
0
9
/ICA
M
S
.
2
0
1
0
.
5
5
5
3
2
6
6
.
[6
]
A
.
M
a
n
d
h
a
re
a
n
d
S
.
Ka
d
a
m
,
"
P
e
r
f
o
r
m
a
n
c
e
A
n
a
l
y
sis o
f
T
ru
st
-
Ba
s
e
d
,"
S
p
ri
n
g
e
r
S
in
g
a
p
o
re
,
2
0
1
9
.
[7
]
O
.
J
e
r
i
c
h
o
,
M
.
K
e
v
i
n
,
R
.
S
p
e
n
c
e
r,
I
.
K
r
i
s
,
a
n
d
B
.
-
C
.
M
a
g
d
a
l
e
n
a
,
“
U
n
s
u
p
e
r
v
i
se
d
L
e
a
r
n
i
n
g
M
e
t
h
o
d
s
i
n
X
-
r
a
y
S
p
e
c
t
ra
l
Im
a
g
i
n
g
M
a
te
r
i
a
l
S
e
g
m
e
n
t
a
t
i
o
n
,
”
a
r
Xi
v
:
1
9
0
4
.
0
3
7
0
1
[
p
h
y
s
i
c
s
.
m
e
d
-
ph]
,
2
0
1
9
.
d
o
i
:
1
0
.
1
0
8
8
/
1
7
4
8
-
0
2
2
1
/
1
4
/
0
6
/
P
0
6
0
2
2
.
[8
]
H.
X
ie,
J.
L
i,
Q.
Zh
a
n
g
,
a
n
d
Y.
W
a
n
g
,
“
Co
m
p
a
riso
n
a
m
o
n
g
d
im
e
n
sio
n
a
li
ty
re
d
u
c
ti
o
n
tec
h
n
i
q
u
e
s
b
a
se
d
o
n
Ra
n
d
o
m
P
r
o
jec
ti
o
n
f
o
r
c
a
n
c
e
r
c
las
sif
ic
a
ti
o
n
,
”
Co
m
p
u
t.
Bi
o
l.
C
h
e
m.
,
v
o
l.
6
5
,
p
p
.
1
6
5
-
1
7
2
,
2
0
1
6
.
[9
]
N.
Ch
h
il
lar,
N.
Ya
d
a
v
,
a
n
d
N.
J
a
iswa
l,
“
En
h
a
n
c
e
d
Ef
f
ici
e
n
c
y
U
sin
g
P
a
tt
e
rn
Re
c
o
g
n
i
ti
o
n
S
y
ste
m
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
T
e
c
h
n
o
l
o
g
y
E
n
h
a
n
c
e
m
e
n
ts a
n
d
Eme
rg
i
n
g
En
g
in
e
e
rin
g
R
e
se
a
r
c
h
,
v
o
l.
1
,
n
o
.
4
,
p
p
.
1
1
9
-
1
2
2
,
2
0
1
4
.
[1
0
]
D
.
B
e
a
i
n
i
,
S
.
A
c
h
i
c
h
e
,
a
n
d
M
.
R
a
i
s
o
n
,
“
I
m
p
r
o
v
i
n
g
C
o
n
v
o
l
u
t
i
o
n
a
l
N
e
u
r
a
l
N
e
t
w
o
r
k
s
V
i
a
C
o
n
s
e
r
v
a
t
i
v
e
F
i
e
l
d
R
e
g
u
l
a
r
i
s
a
t
i
o
n
a
n
d
I
n
t
e
g
r
a
t
i
o
n
,
”
a
r
X
i
v
:
2
0
0
3
.
0
5
1
8
2
[
c
s
.
C
V
]
,
p
p
.
1
-
1
1
,
2
0
2
0
,
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
:
/
/
a
r
x
i
v
.
o
r
g
/
a
b
s
/
2
0
0
3
.
[1
1
]
Ke
h
in
d
e
S
o
t
o
n
w
a
,
Olu
w
a
sh
in
a
Oy
e
n
iran
,
“
F
ac
i
a
l
Re
c
o
g
n
it
i
o
n
S
y
ste
m
:
A
S
h
i
f
t
I
n
S
tu
d
en
t
s
A
tt
e
n
d
a
n
c
e
M
a
n
a
g
e
m
e
n
t
,”
A
n
a
le S
e
ria In
f
o
rm
a
ti
c
a
,
v
o
l.
X
V
II,
f
a
sc
.
1
,
2
0
1
9
.
[1
2
]
S
.
Ra
sto
g
i
a
n
d
S
.
Ch
o
u
d
h
a
ry
,
“
F
a
c
e
re
c
o
g
n
it
io
n
b
y
u
sin
g
n
e
u
ra
l
n
e
tw
o
rk
,
”
Acta
In
fo
rm
.
M
a
la
y
sia
,
v
o
l.
3
,
n
o
.
2
,
p
p
.
7
-
9
,
2
0
1
9
.
[1
3
]
S
.
Z
h
a
n
g
,
Z
.
Y
.
L
i
,
Y
.
C
.
L
i
u
,
“
R
e
s
e
a
r
c
h
o
n
F
a
c
e
R
e
c
o
g
n
i
t
i
o
n
T
e
c
h
n
o
l
o
g
y
B
a
s
e
d
o
n
P
C
A
a
n
d
S
V
M
,
”
i
n
P
r
o
c
e
e
d
i
n
g
s
o
f
t
h
e
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
o
n
M
o
d
e
l
l
i
n
g
,
I
d
e
n
t
i
f
i
c
a
t
i
o
n
a
n
d
C
o
n
t
r
o
l
(
I
C
M
I
C
2
0
1
9)
,
p
p
.
7
5
-
8
5
,
2
0
2
0
.
[1
4
]
M
.
P
.
S
a
t
o
n
e
a
n
d
G
.
K
.
K
h
a
r
a
t
e
,
"
F
a
c
e
r
e
c
o
g
n
i
t
i
o
n
b
a
s
e
d
o
n
P
C
A
o
n
w
a
v
e
l
e
t
s
u
b
b
a
n
d
,
"
2
0
1
2
I
E
E
E
S
t
u
d
e
n
t
s
'
C
o
n
f
e
r
e
n
c
e
o
n
E
l
e
c
t
r
i
c
a
l
,
E
l
e
c
t
r
o
n
i
c
s
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
B
h
o
p
a
l
,
p
p
.
1
-
4
,
2
0
1
2
.
[1
5
]
M
.
A
.
A
l
-
A
b
a
ji
a
n
d
M
.
M
.
S
a
li
h
,
“
T
h
e
u
sin
g
o
f
P
CA
,
w
a
v
e
let
a
n
d
GL
CM
in
f
a
c
e
re
c
o
g
n
it
io
n
sy
ste
m
,
a
c
o
m
p
a
ra
ti
v
e
stu
d
y
,
”
J
.
Un
iv.
Ba
b
y
lo
n
P
u
re
Ap
p
l.
S
c
i.
,
v
o
l
.
2
6
,
n
o
.
1
0
,
p
p
.
1
3
1
-
1
3
9
,
2
0
1
8
.
[1
6
]
N.
T
.
De
sh
p
a
n
d
e
a
n
d
S
.
Ra
v
ish
a
n
k
a
r,
“
F
a
c
e
De
te
c
ti
o
n
a
n
d
Re
c
o
g
n
i
ti
o
n
u
sin
g
Vio
la
-
Jo
n
e
s
a
lg
o
rit
h
m
a
n
d
f
u
sio
n
o
f
L
D
A
a
n
d
A
NN
,
”
IOS
R
J
.
Co
mp
u
t
.
En
g
.
,
v
o
l.
1
8
,
n
o
.
6
,
p
p
.
1
-
6
,
2
0
1
6
.
d
o
i:
1
0
.
9
7
9
0
/0
6
6
1
-
1
8
0
6
0
2
0
1
0
6
.
[1
7
]
G
.
M
.
Za
f
a
ru
d
d
in
a
n
d
H.
S
.
F
a
d
e
w
a
r,
“
F
a
c
e
r
e
c
o
g
n
it
io
n
u
si
n
g
e
ig
e
n
fa
c
e
s,
”
in
Co
mp
u
ti
n
g
,
C
o
mm
u
n
ica
t
io
n
a
n
d
Si
g
n
a
l
Pro
c
e
ss
in
g
,
S
p
rin
g
e
r,
p
p
.
8
5
5
-
8
6
4
,
2
0
1
9
.
[1
8
]
P
.
M
e
li
n
a
n
d
D.
S
á
n
c
h
e
z
,
“
M
u
lt
i
-
o
b
jec
ti
v
e
o
p
t
im
iza
ti
o
n
f
o
r
m
o
d
u
lar
g
ra
n
u
lar
n
e
u
ra
l
n
e
tw
o
rk
s
a
p
p
li
e
d
t
o
p
a
tt
e
r
n
re
c
o
g
n
it
io
n
,
”
In
f
.
S
c
i.
(
Ny
).
,
v
o
l.
4
6
0
-
4
6
1
,
p
p
.
5
9
4
-
6
1
0
,
2
0
1
8
.
d
o
i:
1
0
.
1
0
1
6
/j
.
i
n
s.
2
0
1
7
.
0
9
.
0
3
1
.
[1
9
]
M
.
M
.
H
u
s
s
e
i
n
,
A
.
H
.
M
u
t
l
a
g
,
a
n
d
H
.
S
h
a
r
e
e
f
,
“
D
e
v
e
l
o
p
e
d
a
r
t
if
i
c
i
a
l
n
e
u
r
a
l
n
e
tw
o
r
k
b
a
s
e
d
o
n
h
u
m
a
n
f
a
c
e
r
e
c
o
g
n
i
t
i
o
n
,
”
I
n
d
o
n
e
s
.
J
.
E
l
e
c
t
r
.
E
n
g
.
C
o
m
p
u
t
.
S
c
i
.
,
v
o
l
.
1
6
,
n
o
.
3
,
p
p
.
1
2
7
9
-
1
2
8
5
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s
.
v
1
6
.
i
3
.
p
p
1
2
7
9
-
1
2
8
5
.
[2
0
]
T
.
A
h
m
a
d
,
A
.
J
a
m
e
e
l,
a
n
d
B.
A
h
m
a
d
,
“
P
a
tt
e
rn
re
c
o
g
n
it
i
o
n
u
si
n
g
sta
ti
stica
l
a
n
d
n
e
u
ra
l
tec
h
n
iq
u
e
s,”
in
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Co
m
p
u
ter
Ne
two
r
k
s a
n
d
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
lo
g
y
,
p
p
.
8
7
-
91
,
2
0
1
1
.
[2
1
]
I.
Ju
n
g
a
n
d
G
.
W
a
n
g
,
“
P
a
tt
e
rn
Clas
sif
ica
ti
o
n
o
f
Ba
c
k
-
P
ro
p
a
g
a
ti
o
n
A
lg
o
rit
h
m
Us
in
g
Ex
c
lu
siv
e
Co
n
n
e
c
ti
n
g
Ne
tw
o
rk
,
”
W
o
rld
Aca
d
.
S
c
i.
En
g
.
T
e
c
h
n
o
l
.
,
v
o
l
.
3
6
,
p
p
.
1
8
9
-
1
9
3
,
2
0
0
7
.
[2
2
]
A
.
S
.
A
b
d
u
ll
a
h
,
M
.
A
.
A
b
e
d
,
a
n
d
I.
A
l
-
Ba
ra
z
a
n
c
h
i,
“
I
m
p
ro
v
in
g
f
a
c
e
re
c
o
g
n
it
io
n
b
y
e
l
m
a
n
n
e
u
ra
l
n
e
tw
o
rk
u
sin
g
c
u
rv
e
let
tran
sf
o
r
m
a
n
d
HSI
c
o
l
o
r
sp
a
c
e
,
”
Per
io
d
.
E
n
g
.
Na
t
.
S
c
i.
,
v
o
l.
7
,
n
o
.
2
,
p
p
.
4
3
0
-
4
3
7
,
2
0
1
9
.
[2
3
]
S
.
Q.
A
lh
a
sh
m
i,
K.
H.
T
h
a
n
o
o
n
,
a
n
d
O.
I.
A
lsa
i
f
,
“
A
P
ro
p
o
se
d
F
a
c
e
R
e
c
o
g
n
it
io
n
b
a
se
d
o
n
Hy
b
rid
A
lg
o
rit
h
m
f
o
r
F
e
a
tu
re
s E
x
trac
ti
o
n
,
”
Pro
c
.
6
t
h
I
n
t.
En
g
.
C
o
n
f
.
S
u
sta
in
a
b
le T
e
c
h
n
o
l
.
De
v
.
IEC
2
0
2
0
,
p
p
.
2
3
2
-
2
3
6
,
2
0
2
0
.
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.
1
8
,
No
.
6
,
Dec
em
b
er
2020:
33
5
7
-
33
64
3364
[2
4
]
Y.
S
h
i
a
n
d
D.
F
e
n
g
,
“
F
a
c
e
Re
c
o
g
n
it
io
n
Ba
se
d
o
n
Bl
o
c
k
P
CA
a
lg
o
rit
h
m
a
n
d
El
m
a
n
n
e
u
ra
l
n
e
tw
o
rk
,
”
IOP
Co
n
f.
S
e
r.
M
a
ter
.
S
c
i.
E
n
g
.
,
v
o
l.
3
8
2
,
n
o
.
5
,
2
0
1
8
.
[2
5
]
S
.
S
a
p
n
a
,
“
Ba
c
k
p
ro
p
a
g
a
ti
o
n
L
e
a
rn
in
g
A
lg
o
rit
h
m
Ba
se
d
o
n
L
e
v
e
n
b
e
r
g
M
a
rq
u
a
rd
t
A
lg
o
rit
h
m
,
”
in
Co
n
fer
e
n
c
e
:
T
h
e
Fo
u
rth
In
ter
n
a
ti
o
n
a
l
W
o
rk
sh
o
p
o
n
C
o
mp
u
ter
Ne
two
rk
s
&
Co
mm
u
n
ica
ti
o
n
s
p
p
.
3
9
3
-
3
9
8
,
2
0
1
2
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
M
r
.
H
e
sh
a
m
H
a
s
h
i
m
,
r
e
c
e
i
v
e
d
h
is
BS
c
a
n
d
M
S
c
d
e
g
re
e
f
ro
m
Un
iv
e
rsit
y
o
f
M
o
su
l
-
Ira
q
,
Co
ll
e
g
e
o
f
c
o
m
p
u
ter
sc
ien
c
e
a
n
d
m
a
th
e
m
a
ti
c
s,
Co
m
p
u
ter
S
c
ien
c
e
d
e
p
a
rtm
e
n
t,
a
t
2
0
1
0
,
2
0
1
3
re
sp
e
c
ti
v
e
l
y
.
He
w
o
rk
e
d
a
s
a
ss
i
sta
n
t
lec
tu
re
r
in
c
o
m
p
u
ter
sc
ien
c
e
d
e
p
a
rt
m
e
n
t,
c
o
ll
e
g
e
o
f
c
o
m
p
u
ter sc
ien
c
e
a
n
d
m
a
th
e
m
a
ti
c
s,
m
o
su
l,
Ira
q
f
o
r
th
e
p
e
ri
o
d
2
0
1
3
to
t
h
e
e
n
d
o
f
2
0
1
6
.
S
in
c
e
2
0
1
7
h
e
w
o
rk
e
d
a
s
a
s
sista
n
t
lec
tu
re
r
in
No
r
th
e
rn
T
e
c
h
n
ica
l
Un
iv
e
rsit
y
(N
T
U),
M
o
su
l,
Ira
q
.
H
e
is
n
o
w
a
P
h
.
D
stu
d
e
n
t
a
t
th
e
c
o
m
p
u
ter
sc
ien
c
e
a
n
d
m
a
th
e
m
a
ti
c
s
c
o
ll
e
g
e
.
His
in
tere
ste
d
re
se
a
rc
h
a
re
a
in
c
lu
d
e
s A
I
a
p
p
li
c
a
ti
o
n
s,
d
ig
it
a
l
im
a
g
e
p
ro
c
e
ss
in
g
a
n
d
b
io
in
f
o
rm
a
ti
c
s.
M
r
s.
S
h
a
th
a
o
b
tain
e
d
a
BS
c
in
Co
m
p
u
ter
S
c
ien
c
e
f
ro
m
th
e
Un
i
v
e
rsit
y
o
f
M
o
su
l
i
n
1
9
9
7
,
a
n
d
in
2
0
1
3
,
sh
e
e
a
rn
e
d
a
n
M
S
c
i
n
C
o
m
p
u
ter
S
c
ien
c
e
f
ro
m
th
e
sa
m
e
Un
iv
e
rsit
y
.
S
h
e
w
o
rk
e
d
a
s
a
lec
tu
re
r
in
No
rth
e
rn
T
e
c
h
n
ic
a
l
Un
iv
e
rsit
y
(N
T
U),
M
o
su
l,
Ira
q
.
He
r
in
tere
ste
d
re
se
a
rc
h
a
re
a
in
c
lu
d
e
s
M
o
b
il
e
p
ro
g
ra
m
m
i
n
g
,
In
f
o
r
m
a
ti
o
n
S
e
c
u
rit
y
a
n
d
M
u
lt
im
e
d
ia
c
o
m
m
u
n
ica
ti
o
n
s
a
n
d
A
rti
f
icia
l
in
telli
g
e
n
c
e
.
S
h
e
is
n
o
w
a
P
h
.
D
stu
d
e
n
t
a
t
t
h
e
c
o
m
p
u
te
r
sc
ien
c
e
a
n
d
m
a
th
e
m
a
ti
c
s c
o
ll
e
g
e
.
M
s.
H
a
n
a
n
,
i
n
2
0
0
8
re
c
e
iv
e
d
h
e
r
BS
c
in
Co
m
p
u
ter
S
c
ien
c
e
f
ro
m
th
e
Un
iv
e
rsity
o
f
M
o
su
l,
a
n
d
in
2
0
1
4
sh
e
e
a
rn
e
d
a
n
M
S
c
in
Co
m
p
u
ter
S
c
ien
c
e
f
ro
m
th
e
sa
m
e
Un
iv
e
rsit
y
.
S
h
e
w
o
rk
s
a
s
a
n
e
m
p
lo
y
e
e
T
h
e
G
e
n
e
ra
l
Di
re
c
to
ra
te
o
f
Ed
u
c
a
ti
o
n
in
Nin
e
v
e
h
G
o
v
e
rn
o
ra
te,
Ira
q
.
He
r
in
tere
ste
d
re
se
a
rc
h
a
r
e
a
in
c
lu
d
e
s
w
ir
e
les
s
n
e
t
w
o
rk
,
In
f
o
r
m
a
ti
o
n
S
e
c
u
rit
y
a
n
d
M
u
lt
im
e
d
ia
c
o
m
m
u
n
ica
ti
o
n
s
a
n
d
A
rti
f
icia
l
i
n
telli
g
e
n
c
e
.
S
h
e
is
n
o
w
a
P
h
.
D
stu
d
e
n
t
a
t
th
e
c
o
m
p
u
ter
sc
ien
c
e
a
n
d
m
a
th
e
m
a
ti
c
s c
o
ll
e
g
e
.
Evaluation Warning : The document was created with Spire.PDF for Python.