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.
23
,
No
.
4
,
A
u
g
u
s
t
20
25
,
p
p
.
1
010
~1
0
1
9
I
SS
N:
1693
-
6
9
3
0
,
DOI
: 1
0
.
1
2
9
2
8
/
T
E
L
KOM
NI
K
A
.
v
23
i
4
.
26778
1010
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
A
co
nv
o
lution ne
ura
l net
w
o
rk
m
o
del f
o
r
knee os
teo
po
ro
sis
cla
ss
ificatio
n usin
g
X
-
ra
y
i
m
a
g
es
O
m
a
r
K
ha
lid
M
.
Ali
1
,
Abeer
K
.
I
bra
hi
m
2
,
B
ila
l R
.
Alt
a
m
er
3
1
D
e
p
a
r
t
me
n
t
o
f
C
o
n
s
t
r
u
c
t
i
o
n
a
n
d
P
r
o
j
e
c
t
s,
M
o
su
l
U
n
i
v
e
r
si
t
y
P
r
e
si
d
e
n
c
y
,
U
n
i
v
e
r
si
t
y
o
f
M
o
su
l
,
M
o
su
l
,
I
r
a
q
2
D
e
p
a
r
t
me
n
t
o
f
E
n
v
i
r
o
n
me
n
t
E
n
g
i
n
e
e
r
i
n
g
,
F
a
c
u
l
t
y
o
f
En
g
i
n
e
e
r
i
n
g
,
U
n
i
v
e
r
si
t
y
o
f
M
o
su
l
,
M
o
s
u
l
,
I
r
a
q
3
D
e
p
a
r
t
me
n
t
o
f
P
r
e
si
d
e
n
c
y
A
f
f
a
i
r
s
,
M
o
su
l
U
n
i
v
e
r
si
t
y
P
r
e
si
d
e
n
c
y
,
U
n
i
v
e
r
si
t
y
o
f
M
o
su
l
,
M
o
su
l
,
I
r
a
q
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
No
v
12
,
2024
R
ev
i
s
ed
Mar
26
,
2
0
2
5
A
cc
ep
ted
Ma
y
10
,
2025
Bo
n
e
stru
c
t
u
re
d
e
terio
ra
ti
o
n
a
lo
n
g
w
it
h
lo
w
lev
e
ls
o
f
b
o
n
e
d
e
n
si
t
y
a
re
th
e
h
a
ll
m
a
r
k
s
o
f
k
n
e
e
o
ste
o
p
o
r
o
sis
(KO
P
)
.
T
h
e
c
o
n
v
e
n
ti
o
n
a
l
a
p
p
ro
a
c
h
f
o
r
d
e
tec
ti
n
g
o
ste
o
p
o
r
o
sis
is
a
c
c
o
m
p
li
sh
e
d
u
sin
g
a
k
n
e
e
ra
d
i
o
g
ra
p
h
,
b
u
t
i
t
re
q
u
ires
sp
e
c
ialize
d
k
n
o
w
led
g
e
.
Ne
v
e
rth
e
le
ss
,
X
-
ra
y
s
c
a
n
b
e
d
if
f
icu
lt
to
in
t
e
rp
re
t
d
u
e
to
th
e
ir
larg
e
v
o
lu
m
e
a
n
d
m
in
o
r
f
lu
c
tu
a
ti
o
n
s.
I
n
th
e
p
a
st
f
e
w
d
e
c
a
d
e
s,
d
e
e
p
lea
rn
in
g
a
lg
o
rit
h
m
s
h
a
v
e
m
in
i
m
i
z
e
d
m
isin
terp
re
tatio
n
a
n
d
m
o
d
if
ied
m
e
d
ica
l
d
iag
n
o
sis.
I
n
p
a
rti
c
u
lar,
a
lg
o
rit
h
m
s
b
a
se
d
o
n
c
o
n
v
o
l
u
ti
o
n
a
l
n
e
u
ra
l
n
e
tw
o
rk
s
(CNN
s)
h
a
v
e
b
e
e
n
u
se
d
t
o
sp
e
e
d
u
p
t
h
e
p
ro
c
e
d
u
re
o
f
d
iag
n
o
sis
b
e
c
a
u
se
o
f
th
e
ir
in
n
a
te
c
a
p
a
c
it
y
to
e
x
tra
c
t
sig
n
if
ica
n
t
f
e
a
tu
re
s
th
a
t
o
f
ten
a
r
e
c
h
a
ll
e
n
g
in
g
to
sp
o
t
b
y
h
a
n
d
.
A
ro
b
u
st
CNN
m
o
d
e
l
w
a
s
p
ro
p
o
se
d
in
th
is
p
a
p
e
r
f
o
r
KO
P
c
las
si
f
ica
ti
o
n
w
h
ich
u
se
s
a
train
a
n
d
tes
t
a
p
p
r
o
a
c
h
to
re
c
o
g
n
ize
h
e
a
lt
h
y
,
o
ste
o
p
e
n
ia
-
p
re
d
icte
d
,
a
n
d
o
ste
o
p
o
ro
sis
k
n
e
e
c
a
se
s
u
sin
g
1
9
4
7
X
-
r
a
y
ima
g
e
s.
T
h
e
p
ro
p
o
se
d
m
o
d
e
l
w
a
s
d
e
sig
n
e
d
u
si
n
g
Ju
p
y
ter
No
teb
o
o
k
a
n
d
is
i
n
P
y
th
o
n
.
T
o
v
e
ri
fy
th
e
e
ff
icie
n
c
y
o
f
th
e
m
o
d
e
l,
so
m
e
fa
c
to
rs
w
e
re
c
a
lcu
late
d
su
c
h
a
s
a
c
c
u
ra
c
y
,
p
re
c
isio
n
,
re
c
a
ll
,
a
n
d
f1
-
sc
o
re
.
In
c
o
m
p
a
riso
n
w
it
h
o
t
h
e
r
si
m
il
a
r
s
y
ste
m
s,
th
e
re
su
lt
s
o
b
tai
n
e
d
sh
o
w
e
d
th
a
t
th
e
a
c
c
u
ra
c
y
o
f
th
e
p
ro
p
o
se
d
s
y
ste
m
re
a
c
h
e
d
9
0
.
2
5
%
.
K
ey
w
o
r
d
s
:
A
cc
u
r
ac
y
C
o
n
v
o
lu
tio
n
al
n
e
u
r
al
n
e
t
w
o
r
k
s
Kn
ee
o
s
teo
p
o
r
o
s
is
Ost
eo
p
en
ia
X
-
r
a
y
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
:
O
m
ar
Kh
a
lid
M.
A
l
i
Dep
ar
t
m
en
t o
f
C
o
n
s
tr
u
c
tio
n
a
n
d
P
r
o
j
ec
ts
,
Mo
s
u
l
Un
i
v
er
s
it
y
P
r
esid
en
c
y
,
Un
i
v
er
s
i
t
y
o
f
Mo
s
u
l
L
e
f
t sid
e,
A
l
-
B
alad
i
y
at
d
is
tr
ict
,
4
1
0
0
2
,
M
o
s
u
l,
I
r
aq
E
m
ail:
o
m
ar
.
k
h
a
lid
@
u
o
m
o
s
u
l
.
ed
u
.
iq
1.
I
NT
RO
D
UCT
I
O
N
Ost
eo
p
o
r
o
s
is
is
d
e
f
i
n
ed
as
a
d
ec
r
ea
s
e
in
b
o
n
e
m
a
s
s
an
d
t
h
e
d
eter
io
r
atio
n
o
f
b
o
n
e
ce
ll
s
,
w
h
ich
lo
w
er
s
th
e
d
en
s
it
y
o
f
b
o
n
es a
n
d
r
aises
th
e
p
o
s
s
ib
ilit
y
o
f
b
o
n
e
f
r
ac
tu
r
es.
K
n
ee
o
s
teo
p
o
r
o
s
is
(
KOP)
,
a
p
ar
ticu
lar
ty
p
e
o
f
o
s
teo
p
o
r
o
s
is
th
at
m
ai
n
l
y
i
m
p
a
cts
t
h
e
k
n
ee
r
e
g
io
n
an
d
h
as
b
ee
n
m
o
r
e
w
ell
-
k
n
o
w
n
i
n
t
h
e
p
ast
f
e
w
y
ea
r
s
,
t
h
r
ea
ten
s
co
u
n
tle
s
s
p
eo
p
le
[
1
]
,
[
2
]
.
T
h
e
W
o
r
ld
Hea
lth
Or
g
a
n
izatio
n
(
W
HO)
h
as
id
e
n
ti
f
ied
n
u
m
e
r
o
u
s
i
m
p
o
r
ta
n
t
r
is
k
asp
ec
ts
f
o
r
th
e
g
r
o
w
th
o
f
KOP
,
co
m
p
r
is
in
g
f
a
m
il
y
h
is
to
r
y
,
g
e
n
d
er
,
ag
e,
h
o
r
m
o
n
e
ab
n
o
r
m
alit
ies,
an
d
h
ab
its
s
u
c
h
as
ex
tr
e
m
e
alco
h
o
l
i
n
ta
k
e
[
3
]
–
[
5
]
.
C
o
m
m
o
n
s
y
m
p
to
m
s
o
f
th
i
s
ill
n
ess
in
cl
u
d
e
d
ec
r
ea
s
ed
m
o
b
ilit
y
,
s
t
if
f
n
es
s
,
an
d
o
n
g
o
i
n
g
p
ain
an
d
d
is
co
m
f
o
r
t
in
th
e
k
n
ee
ar
ea
,
ea
ch
o
f
w
h
ic
h
h
as
a
s
u
b
s
ta
n
tial
n
e
g
ati
v
e
im
p
ac
t
o
n
a
p
e
r
s
o
n
’
s
lif
es
t
y
le
[
3
]
,
[
6
]
.
I
t
i
s
c
r
u
c
i
a
l
to
r
em
em
b
e
r
th
a
t
K
O
P
is
a
n
in
c
u
r
a
b
l
e
il
ln
es
s
,
b
u
t
p
r
o
m
p
t
d
i
ag
n
o
s
is
an
d
t
a
r
g
e
t
ed
t
r
e
a
tm
en
t
c
an
g
r
e
at
ly
r
e
d
u
c
e
o
r
e
v
en
s
t
o
p
i
ts
c
o
u
r
s
e
,
en
h
an
ci
n
g
th
e
g
en
e
r
al
h
e
a
l
th
o
f
th
o
s
e
w
h
o
a
r
e
im
p
a
ct
e
d
[
6
]
.
I
n
th
e
m
ed
ical
f
ield
,
o
s
teo
p
o
r
o
s
is
i
s
id
en
tifie
d
u
s
i
n
g
th
e
d
u
a
l
-
e
n
er
g
y
X
-
r
a
y
ab
s
o
r
p
tio
m
etr
y
tech
n
iq
u
e
(
DXA
)
[
7
]
w
h
ic
h
m
ea
s
u
r
es
b
o
n
e
m
i
n
er
al
d
en
s
it
y
(
B
MD
)
ac
c
o
r
d
in
g
to
th
e
Z
-
s
co
r
e
an
d
T
-
s
co
r
e
p
ar
am
eter
s
th
a
t
th
e
W
HO
h
as
a
p
p
r
o
v
ed
f
o
r
v
ar
io
u
s
p
h
ase
s
o
f
t
h
e
d
is
ea
s
e
[
8
]
.
Nev
er
th
eless
,
t
h
i
s
ap
p
r
o
a
ch
h
a
s
d
r
a
w
b
ac
k
s
,
in
cl
u
d
in
g
ar
ea
l
m
ea
s
u
r
es,
ex
p
e
n
s
e,
an
d
li
m
ited
av
ailab
il
it
y
.
M
ag
n
e
tic
r
eso
n
an
ce
i
m
ag
i
n
g
(
MRI)
[
9
]
,
co
m
p
u
ted
to
m
o
g
r
ap
h
y
(
C
T
)
[
1
0
]
,
an
d
th
e
q
u
a
n
titati
v
e
u
ltra
s
o
u
n
d
s
y
s
te
m
(
QU
S)
[
1
1
]
,
ar
e
o
th
er
im
ag
in
g
tec
h
n
iq
u
es
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
n
vo
l
u
tio
n
n
e
u
r
a
l n
etw
o
r
k
mo
d
el
fo
r
kn
ee
o
s
teo
p
o
r
o
s
is
cla
s
s
ifica
tio
n
…
(
Oma
r
K
h
a
lid
M.
A
li
)
1011
u
tili
ze
d
to
id
en
ti
f
y
o
s
teo
p
o
r
o
s
is
.
A
d
etec
tio
n
s
y
s
te
m
th
a
t
is
p
r
ec
is
e,
af
f
o
r
d
ab
le,
an
d
ea
s
il
y
ac
ce
s
s
ib
le
i
s
n
ec
es
s
ar
y
in
li
g
h
t
o
f
th
ese
co
n
s
tr
ain
t
s
.
Du
e
to
th
is
r
eq
u
ir
e
m
e
n
t,
s
cien
tis
t
s
h
a
v
e
b
ee
n
u
s
i
n
g
co
m
p
u
ter
alg
o
r
ith
m
s
to
ev
al
u
ate
m
ed
ical
i
m
ag
e
s
an
d
cr
ea
te
co
m
p
u
ter
-
aid
ed
d
iag
n
o
s
tic
s
y
s
te
m
s
(
C
A
D)
b
y
u
tili
z
in
g
c
u
r
r
en
t
d
ev
elo
p
m
en
t
s
in
i
m
ag
in
g
tec
h
n
o
lo
g
ies.
T
h
e
ad
v
en
t
o
f
ad
v
an
ce
d
i
m
a
g
i
n
g
tech
n
iq
u
e
s
an
d
co
m
p
u
tatio
n
a
l
m
et
h
o
d
s
h
as
u
s
h
er
ed
in
n
e
w
o
p
p
o
r
tu
n
itie
s
f
o
r
th
e
d
ia
g
n
o
s
i
s
an
d
m
a
n
a
g
e
m
e
n
t
o
f
K
OP
.
T
r
ad
itio
n
al
m
et
h
o
d
s
,
w
h
ile
e
f
f
ec
ti
v
e
to
s
o
m
e
ex
te
n
t,
o
f
te
n
f
all
s
h
o
r
t
i
n
ter
m
s
o
f
ac
c
ess
ib
ilit
y
a
n
d
co
s
t
-
e
f
f
icien
c
y
.
T
h
is
g
ap
h
as
d
r
i
v
e
n
th
e
d
ev
elo
p
m
e
n
t
o
f
C
AD
s
y
s
te
m
s
,
w
h
ich
u
tili
ze
m
ac
h
in
e
lear
n
in
g
a
n
d
i
m
a
g
e
p
r
o
ce
s
s
in
g
tec
h
n
iq
u
es
to
p
r
o
v
id
e
m
o
r
e
ac
c
u
r
ate
an
d
ac
ce
s
s
ib
le
d
iag
n
o
s
i
s
o
p
tio
n
s
[
1
2
]
.
Ma
n
y
y
x
p
er
i
m
e
n
ts
h
a
v
e
s
h
o
w
n
t
h
at
th
e
s
e
A
I
-
b
ased
s
y
s
te
m
s
m
a
y
a
ttai
n
ex
ce
p
tio
n
a
l
lev
el
s
o
f
p
r
ec
is
io
n
,
f
r
eq
u
e
n
tl
y
s
u
r
p
ass
i
n
g
co
n
v
en
t
io
n
al
d
ia
g
n
o
s
tic
ap
p
r
o
ac
h
es
[
1
1
]
.
On
ce
a
m
o
d
el
’
s
d
ec
is
io
n
s
ar
e
co
m
p
letel
y
u
n
d
er
s
ta
n
d
ab
le,
it
w
ill
b
e
in
ter
p
r
eted
[
1
3
]
.
Ho
w
e
v
er
,
ar
tif
icial
in
telli
g
e
n
ce
m
o
d
els
r
e
m
ai
n
m
y
s
ter
io
u
s
to
av
er
a
g
e
u
s
er
s
.
T
h
er
ef
o
r
e,
a
d
ee
p
e
r
co
m
p
r
eh
e
n
s
io
n
o
f
th
e
m
o
d
els
’
o
p
er
atio
n
s
b
ec
o
m
e
s
es
s
en
tial
to
s
et
g
o
al
s
f
o
r
a
lar
g
er
ap
p
licatio
n
o
f
ar
tific
ial
i
n
telli
g
e
n
ce
tech
n
o
lo
g
ies
in
m
ed
icin
e.
A
s
a
r
esu
l
t,
ef
f
o
r
ts
h
av
e
b
ee
n
i
n
itiated
to
en
h
a
n
c
e
ar
tif
icial
in
tel
lig
e
n
ce
m
o
d
el
s
’
tr
an
s
p
ar
en
c
y
a
n
d
in
ter
p
r
etab
ilit
y
[
1
4
]
.
T
h
e
f
o
ll
o
w
i
n
g
ar
e
s
e
v
er
al
p
r
ev
io
u
s
r
esear
ch
f
in
d
i
n
g
s
p
r
o
v
id
ed
b
y
d
if
f
er
e
n
t
s
cie
n
ti
s
ts
th
r
o
u
g
h
o
u
t th
e
p
ast
s
ev
er
al
y
e
ar
s
.
Hata
n
o
et
a
l.
[
1
5
]
,
P
r
o
d
u
ce
d
an
au
to
m
atic
d
ia
g
n
o
s
in
g
s
y
s
te
m
t
h
at
in
c
lu
d
es t
h
r
ee
s
tep
s
: se
g
m
e
n
tat
io
n
,
r
eg
is
tr
atio
n
,
an
d
cla
s
s
i
f
icatio
n
.
T
h
eir
ap
p
r
o
ac
h
w
o
r
k
ed
well,
w
ith
9
2
.
8
9
%
tr
u
e
p
o
s
itiv
es
an
d
5
.
9
6
%
f
al
s
e
p
o
s
itiv
es a
ch
iev
ed
in
th
e
ca
te
g
o
r
izatio
n
r
ates.
Hata
n
o
et
a
l.
[
1
6
]
,
p
r
esen
ted
an
au
to
m
a
tic
id
en
ti
f
icatio
n
m
et
h
o
d
o
f
o
s
teo
p
o
r
o
s
is
f
r
o
m
p
h
ala
n
g
e
s
c
o
m
p
u
ted
r
ad
io
g
r
ap
h
y
(
CR
)
i
m
a
g
es
u
s
in
g
d
ee
p
co
n
v
o
lu
tio
n
al
n
e
u
r
al
n
et
w
o
r
k
(
DC
NN
)
an
d
tes
ted
its
e
f
f
ec
t
iv
en
e
s
s
b
y
a
th
r
ee
-
f
o
ld
cr
o
s
s
-
v
a
lid
atio
n
ap
p
r
o
ac
h
.
T
h
e
au
t
h
o
r
s
u
s
e
a
DC
N
N
class
i
f
ier
to
d
eter
m
i
n
e
if
u
n
k
n
o
w
n
C
R
i
m
a
g
es
ar
e
n
o
r
m
al
o
r
n
o
t.
Fath
i
m
a
et
a
l.
[
1
7
]
,
u
tili
ze
d
an
ad
j
u
s
ted
U
-
Net
w
ith
a
C
o
n
ce
n
tr
atio
n
u
n
it
to
s
eg
m
en
t
th
e
b
o
n
e
r
e
g
io
n
s
f
r
o
m
Du
al
E
n
er
g
y
X
-
r
a
y
A
b
s
o
r
p
tio
m
e
tr
y
(
DE
X
A
)
i
m
a
g
es
a
n
d
X
-
r
a
y
s
.
T
h
e
d
atase
t
w
a
s
cla
s
s
i
f
ied
i
n
to
th
r
ee
cla
s
s
es
b
y
co
m
p
u
ti
n
g
T
-
s
co
r
e
an
d
B
MD
.
T
h
e
ac
cu
r
ac
y
o
f
th
e
p
r
o
p
o
s
ed
m
e
th
o
d
w
as
ab
o
u
t
8
8
%.
Z
h
a
n
g
e
t
a
l.
[
1
8
]
,
d
ev
elo
p
ed
a
m
o
d
el
o
f
DC
NN
f
o
r
class
i
f
y
in
g
o
s
teo
p
o
r
o
s
is
an
d
o
s
teo
p
en
ia
b
a
s
ed
o
n
th
e
X
-
r
a
y
i
m
a
g
es
o
f
t
h
e
lu
m
b
ar
s
p
i
n
e.
T
h
e
d
ev
elo
p
ed
m
o
d
el
w
a
s
ass
e
s
s
ed
b
y
m
ea
s
u
r
i
n
g
t
h
e
T
-
s
co
r
e
f
ac
t
o
r
an
d
th
en
clas
s
i
f
y
i
n
g
th
e
d
at
aset
in
to
t
h
r
ee
class
e
s
:
n
o
r
m
al
,
o
s
teo
p
o
r
o
s
is
,
an
d
o
s
teo
p
en
ia.
T
ec
le
et
a
l.
[
1
9
]
,
c
o
m
p
ar
ed
h
u
m
a
n
a
n
d
m
ac
h
in
e
o
s
teo
p
o
r
o
s
is
d
iag
n
o
s
es u
s
i
n
g
a
s
ec
o
n
d
m
etac
ar
p
al
co
r
tical
p
er
ce
n
tag
e.
T
h
e
r
es
u
lts
i
n
d
icate
t
h
at
t
h
e
Sen
s
iti
v
i
t
y
w
a
s
8
2
.
4
%,
an
d
t
h
e
Sp
ec
if
icit
y
w
a
s
9
4
.
3
%.
Ho
et
a
l.
[
2
0
]
,
p
r
o
p
o
s
ed
a
d
e
ep
lear
n
in
g
ap
p
r
o
ac
h
th
at
ca
n
ac
cu
r
atel
y
p
r
ed
ict
th
e
d
en
s
it
y
o
f
b
o
n
e
m
i
n
er
als
g
ath
er
ed
f
r
o
m
a
p
lai
n
p
elv
ic
X
-
r
a
y
f
o
r
o
s
teo
p
o
r
o
s
is
cla
s
s
i
f
y
in
g
.
T
h
eir
tech
n
iq
u
e
co
m
b
i
n
es
c
o
n
v
o
l
u
tio
n
al
n
e
u
r
al
n
et
w
o
r
k
(
C
NN)
lear
n
in
g
,
i
m
a
g
e
s
eg
m
e
n
tatio
n
,
an
d
(
Dee
p
DX
A
)
w
h
ic
h
i
s
a
co
n
v
o
l
u
tio
n
m
o
d
el
to
esti
m
a
te
b
o
n
e
m
i
n
er
als
d
ata
v
alu
e
b
y
co
n
n
e
ctin
g
s
ep
ar
ated
f
e
m
u
r
b
o
n
e
im
ag
e
s
.
I
n
th
i
s
p
ap
er
,
a
C
NN
m
o
d
el
-
b
ased
KOP
d
etec
tio
n
an
d
clas
s
i
f
icatio
n
i
s
p
r
o
p
o
s
ed
.
T
h
e
m
ain
g
o
al
o
f
th
is
w
o
r
k
is
to
e
n
h
a
n
ce
t
h
e
c
o
n
ce
p
t
o
f
d
iag
n
o
s
is
th
r
o
u
g
h
A
I
b
y
o
b
tain
in
g
h
ig
h
d
iag
n
o
s
t
ic
ac
cu
r
ac
y
.
2.
M
E
T
H
O
D
First
o
f
all,
t
h
e
k
n
ee
X
-
r
a
y
d
at
aset
av
a
ilab
le
o
n
t
h
e
Ka
g
g
le
web
s
ite
is
u
til
ized
[
2
1
]
.
Fig
u
r
e
s
1
(a
)
to
(
c)
illu
s
tr
ate
ex
a
m
p
les
o
f
t
h
e
u
s
ed
d
atasets
,
w
h
ic
h
co
n
s
is
t
o
f
1
9
4
7
i
m
ag
e
s
w
it
h
3
class
e
s
:
h
ea
lt
h
y
,
ac
tu
al
o
s
teo
p
en
ia,
an
d
o
s
teo
p
o
r
o
s
is
.
Nex
t,
th
ese
d
atasets
ar
e
s
p
lit
in
to
t
w
o
p
a
r
ts
,
th
e
f
ir
s
t
is
co
n
ce
r
n
ed
w
it
h
tr
ain
i
n
g
t
h
e
C
N
N
m
o
d
el,
a
n
d
th
e
s
ec
o
n
d
is
co
n
c
er
n
ed
w
it
h
te
s
t
d
a
ta
(
w
h
ic
h
th
e
tr
ain
ed
class
i
f
ier
is
te
s
ted
w
i
th
)
w
it
h
v
alid
atio
n
f
o
r
ea
ch
ep
o
ch
.
Sin
ce
C
N
N
p
er
f
o
r
m
s
b
etter
w
it
h
ad
d
itio
n
al
d
ata,
th
e
tr
ain
in
g
co
llectio
n
’
s
i
m
ag
e
co
u
n
t
is
in
cr
ea
s
ed
b
y
a
u
g
m
e
n
ti
n
g
t
h
e
tr
ain
i
n
g
d
ata.
Af
ter
t
h
at,
t
h
e
C
NN
m
o
d
el
r
ec
eiv
es
th
is
co
l
l
ec
tio
n
o
f
i
m
a
g
es
in
o
r
d
er
t
o
b
e
tr
ain
ed
.
E
v
en
t
u
al
l
y
,
th
e
p
r
ed
ictio
n
p
r
o
p
o
r
tio
n
o
f
b
o
th
test
an
d
tr
ain
d
ata
is
ass
ess
ed
,
an
d
t
h
e
class
i
f
ier
’
s
e
f
f
ic
ien
c
y
i
n
class
i
f
y
in
g
i
m
ag
e
s
in
to
o
s
teo
p
o
r
o
s
is
,
o
s
teo
p
en
ia,
an
d
n
o
r
m
al
i
m
ag
es is
esti
m
ated
.
(
a)
(
b
)
(
c)
Fig
u
r
e
1
.
Sa
m
p
les o
f
t
h
e
u
s
ed
d
ataset
; (
a)
h
ea
lth
y
,
(
b
)
o
s
teo
p
en
ia
p
r
ed
icted
,
an
d
(
c)
o
s
teo
p
o
r
o
s
is
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.
23
,
No
.
4
,
A
u
g
u
s
t
20
25
:
1
0
1
0
-
1
0
1
9
1012
Fig
u
r
e
2
d
em
o
n
s
tr
ates
th
e
s
u
g
g
ested
b
lo
ck
d
iag
r
a
m
m
o
d
el
f
o
r
d
etec
tin
g
o
s
teo
p
o
r
o
s
is
v
ia
k
n
ee
X
-
r
a
y
s
.
I
n
th
i
s
p
r
o
p
o
s
ed
C
NN
m
o
d
el,
th
e
r
ec
ti
f
ied
lin
ea
r
u
n
i
t
(
R
e
L
U)
is
u
ti
lized
af
ter
ea
c
h
co
n
v
o
lu
tio
n
la
y
er
an
d
all
f
u
ll
y
co
n
n
ec
ted
(
FC
)
la
y
er
s
,
w
it
h
t
h
e
e
x
ce
p
tio
n
o
f
t
h
e
f
i
n
al
FC
la
y
er
.
W
h
e
n
C
N
N
u
s
es
t
h
e
R
e
L
U
f
u
n
ctio
n
,
it
tr
ain
s
m
u
ch
m
o
r
e
q
u
ic
k
l
y
t
h
a
n
w
h
en
it
u
s
es
a
lter
n
at
iv
e
ac
t
iv
atio
n
f
u
n
ctio
n
s
li
k
e
s
ig
m
o
id
o
r
T
an
h
f
u
n
ctio
n
s
[
2
2
]
.
T
h
e
m
at
h
e
m
a
tical
ex
p
r
es
s
io
n
o
f
t
h
e
R
e
L
U
ac
ti
v
atio
n
f
u
n
ctio
n
i
s
d
e
m
o
n
s
tr
ated
in
(
1
)
[
2
3
]
.
(
)
=
ma
x
(
0
;
)
(
1
)
T
h
e
o
p
tim
al
C
NN
s
tr
u
ct
u
r
e
cr
ea
ted
u
s
in
g
t
h
e
s
u
g
g
e
s
ted
alg
o
r
ith
m
i
n
v
o
l
v
es
n
i
n
e
co
n
v
o
lu
tio
n
s
tep
s
,
f
o
u
r
p
o
o
lin
g
s
tep
s
,
t
h
r
ee
d
en
s
e
s
tep
s
,
a
n
d
t
w
o
d
r
o
p
o
u
t step
s
,
as s
h
o
w
n
in
T
ab
le
1
.
I
n
ad
d
itio
n
,
t
h
e
ar
c
h
itect
u
r
e
o
f
th
e
p
r
o
p
o
s
ed
C
NN
m
o
d
el
h
as
1
5
,
6
1
0
,
4
9
9
t
o
tal
p
ar
am
eter
s
,
1
5
,
6
0
4
,
0
9
9
tr
ain
ab
le
p
ar
am
et
er
s
,
an
d
6
,
4
0
0
n
o
n
-
tr
ain
ab
le
p
ar
am
eter
s
.
T
h
e
v
alu
e
o
f
th
e
lo
s
s
f
u
n
ctio
n
w
a
s
ca
lcu
l
ated
u
s
in
g
ca
teg
o
r
ical
cr
o
s
s
-
e
n
tr
o
p
y
,
an
d
th
e
n
et
w
o
r
k
’
s
tr
ai
n
ab
le
p
ar
a
m
eter
s
w
er
e
t
h
e
n
m
o
d
if
ied
to
r
ed
u
ce
p
r
ed
ictio
n
lo
s
s
.
Fig
u
r
e
2
.
T
h
e
b
lo
ck
d
iag
r
am
o
f
th
e
p
r
o
p
o
s
ed
C
NN
m
o
d
el
T
ab
le
1
.
T
h
e
p
r
o
p
o
s
ed
C
NN
m
o
d
el
d
esi
g
n
an
d
p
ar
a
m
eter
s
L
a
y
e
r
(
t
y
p
e
)
N
o
.
o
f
k
e
r
n
e
l
K
e
r
n
e
l
si
z
e
O
u
t
p
u
t
s
h
a
p
e
N
o
.
o
f
p
a
r
a
me
t
e
r
s
C
o
n
v
1
(
C
o
n
v
2
D
)
1
2
8
(
8
,
8
)
(
7
3
,
7
3
,
1
2
8
)
2
4
7
0
4
C
o
n
v
2
(
C
o
n
v
2
D
)
2
5
6
(
5
,
5
)
(
7
3
,
7
3
,
2
5
6
)
8
1
9
4
5
6
P
o
o
l
i
n
g
1
(
M
a
x
P
o
o
l
i
n
g
2
D
)
-
(
3
,
3
)
(
2
4
,
2
4
,
2
5
6
)
0
C
o
n
v
3
(
C
o
n
v
2
D
)
2
5
6
(
3
,
3
)
(
2
4
,
2
4
,
2
5
6
)
5
9
0
0
8
0
C
o
n
v
4
(
C
o
n
v
2
D
)
2
5
6
(
1
,
1
)
(
2
4
,
2
4
,
2
5
6
)
6
5
7
9
2
C
o
n
v
5
(
C
o
n
v
2
D
)
2
5
6
(
1
,
1
)
(
2
4
,
2
4
,
2
5
6
)
6
5
7
9
2
C
o
n
v
6
(
C
o
n
v
2
D
)
5
1
2
(
3
,
3
)
(
2
4
,
2
4
,
5
1
2
)
1
1
8
0
1
6
0
P
o
o
l
i
n
g
2
(
M
a
x
P
o
o
l
i
n
g
2
D
)
-
(
2
,
2
)
(
1
2
,
1
2
,
5
1
2
)
0
C
o
n
v
7
(
C
o
n
v
2
D
)
5
1
2
(
3
,
3
)
(
1
2
,
1
2
,
5
1
2
)
2
3
5
9
8
0
8
C
o
n
v
8
(
C
o
n
v
2
D
)
5
1
2
(
3
,
3
)
(
1
2
,
1
2
,
5
1
2
)
2
3
5
9
8
0
8
P
o
o
l
i
n
g
3
(
M
a
x
P
o
o
l
i
n
g
2
D
)
-
(
2
,
2
)
(
6
,
6
,
5
1
2
)
0
C
o
n
v
9
(
C
o
n
v
2
D
)
5
1
2
(
3
,
3
)
(
6
,
6
,
5
1
2
)
2
3
5
9
8
0
8
P
o
o
l
i
n
g
4
(
M
a
x
P
o
o
l
i
n
g
2
D
)
-
(
2
,
2
)
(
3
,
3
,
5
1
2
)
0
F
l
a
t
t
e
n
(
F
l
a
t
t
e
n
)
-
-
4
6
0
9
0
D
e
n
se
1
(
D
e
n
se
)
-
-
1
0
2
4
4
7
1
9
6
1
6
D
r
o
p
1
(
D
r
o
p
o
u
t
)
-
-
1
0
2
4
0
D
e
n
se
2
(
D
e
n
se
)
-
-
1
0
2
4
1
0
4
9
6
0
0
D
r
o
p
2
(
D
r
o
p
o
u
t
)
-
-
1
0
2
4
0
D
e
n
se
3
(
D
e
n
se
)
-
-
3
3
0
7
5
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
n
vo
l
u
tio
n
n
e
u
r
a
l n
etw
o
r
k
mo
d
el
fo
r
kn
ee
o
s
teo
p
o
r
o
s
is
cla
s
s
ifica
tio
n
…
(
Oma
r
K
h
a
lid
M.
A
li
)
1013
2
.
1
.
C
o
n
v
o
l
u
t
i
o
n
a
l
n
eu
r
a
l
n
et
wo
r
k
a
r
c
hi
t
e
c
t
ur
e
C
N
N
i
s
a
k
in
d
o
f
n
e
u
r
a
l
n
e
t
w
o
r
k
w
ith
d
e
e
p
l
ay
e
r
s
th
a
t
u
t
i
li
ze
t
h
e
c
o
n
v
o
l
u
t
i
o
n
p
r
in
c
i
p
l
e
a
t
it
s
s
t
ag
e
o
f
d
e
v
e
l
o
p
m
en
t
.
T
h
e
c
o
m
p
u
t
at
i
o
n
a
l
f
u
n
ct
i
o
n
k
n
o
w
n
as
c
o
n
v
o
lu
t
i
o
n
i
s
u
s
e
d
t
o
c
o
m
b
in
e
t
w
o
f
u
n
c
t
i
o
n
s
t
o
c
r
e
a
te
a
n
o
v
e
l
o
n
e
w
ith
a
l
t
e
r
e
d
p
r
o
p
e
r
t
ie
s
[
2
4
]
.
C
N
N
s
a
r
e
em
p
l
o
y
e
d
t
o
a
n
a
ly
z
e
im
ag
es
t
h
a
t
h
av
e
b
e
en
c
o
n
v
o
lv
e
d
u
s
in
g
a
f
il
t
e
r
t
h
a
t
i
s
s
m
al
l
e
r
in
le
n
g
th
th
a
n
in
w
i
d
th
t
o
m
in
im
i
ze
th
e
im
a
g
e
s
iz
e
w
h
il
e
p
r
e
s
e
r
v
in
g
t
h
e
ess
en
t
i
al
in
f
o
r
m
a
ti
o
n
.
S
c
i
en
ti
s
t
s
a
r
e
m
o
r
e
in
t
e
r
es
t
e
d
in
C
N
N
th
an
o
th
e
r
m
a
ch
in
e
l
e
ar
n
in
g
s
y
s
t
em
s
b
e
c
au
s
e
it
c
an
t
ak
e
a
d
v
an
t
ag
e
o
f
th
e
s
im
u
l
ta
n
e
o
u
s
s
p
at
i
al
an
d
c
o
n
f
ig
u
r
a
l
in
f
o
r
m
a
ti
o
n
o
f
b
o
th
2
D
an
d
3
D
im
ag
es
[
2
5
]
.
C
N
N
’
s
s
t
r
en
g
th
l
i
es
in
i
ts
a
b
il
i
ty
t
o
ex
t
r
a
c
t
f
e
a
tu
r
es
d
i
r
ec
t
ly
f
r
o
m
im
ag
e
s
,
u
n
l
ik
e
o
th
e
r
m
a
ch
in
e
-
le
a
r
n
in
g
t
e
c
h
n
i
q
u
es
th
at
n
e
e
d
o
b
je
c
t
s
eg
m
en
t
at
i
o
n
[
2
6
]
o
r
f
e
at
u
r
e
e
x
t
r
ac
t
i
o
n
[
2
7
]
.
Nu
m
e
r
o
u
s
C
N
Ns
h
a
v
e
b
e
en
c
r
e
at
e
d
t
o
a
d
d
r
e
s
s
d
if
f
e
r
en
t
k
in
d
s
o
f
i
s
s
u
es
;
w
h
i
l
e
th
ey
d
if
f
e
r
s
l
ig
h
t
ly
f
r
o
m
o
n
e
an
o
th
e
r
in
c
e
r
t
a
in
a
r
e
as
,
a
l
l
o
f
th
ei
r
f
u
n
d
am
en
t
a
l
el
em
en
ts
r
em
ain
t
h
e
s
am
e
.
T
h
e
C
NN
s
in
v
o
lv
e
th
r
e
e
k
in
d
s
o
f
l
ay
e
r
s
:
c
o
n
v
o
lu
tio
n
a
l
l
ay
e
r
,
p
o
o
l
in
g
l
ay
e
r
,
a
n
d
f
u
lly
c
o
n
n
e
ct
e
d
l
ay
er
[
2
8
]
,
a
s
d
em
o
n
s
t
r
a
t
e
d
in
F
ig
u
r
e
3
.
F
ig
u
r
e
3
.
T
h
e
C
N
N
a
r
ch
it
e
c
tu
r
e
2
.
2
.
C
o
n
v
o
l
u
t
i
o
n
l
a
y
e
r
T
h
e
c
o
n
v
o
lu
ti
o
n
l
ay
e
r
is
c
o
n
s
i
d
e
r
e
d
th
e
m
o
s
t
s
ig
n
if
i
c
an
t
l
ay
e
r
th
a
t
m
ak
e
s
u
p
c
o
n
v
o
lu
t
i
o
n
a
l
n
eu
r
a
l
n
e
tw
o
r
k
s
a
n
d
is
f
o
u
n
d
e
d
o
n
c
o
n
t
in
u
o
u
s
ly
c
i
r
cu
l
a
tin
g
a
s
p
e
c
if
i
c
f
i
lt
e
r
a
c
r
o
s
s
t
h
e
w
h
o
l
e
im
ag
e
.
I
n
a
n
u
t
s
h
e
ll
,
th
e
im
ag
e
p
ix
el
v
a
lu
es
a
r
e
m
u
lt
i
p
l
ie
d
b
y
t
h
e
k
e
r
n
e
l
f
r
am
e
b
y
d
r
ag
g
in
g
it
r
i
g
h
t
o
r
l
e
f
t
a
c
r
o
s
s
th
e
im
ag
e
b
e
in
g
p
r
o
c
e
s
s
e
d
o
r
t
h
e
im
a
g
e
o
f
th
e
p
r
i
o
r
l
ay
e
r
.
W
h
e
n
t
h
e
f
i
l
te
r
o
r
k
e
r
n
el
r
e
a
ch
es
th
e
m
a
t
r
ix
’
s
b
o
r
d
e
r
,
i
t
i
s
m
o
v
e
d
d
o
w
n
w
i
th
i
n
th
e
r
e
q
u
i
r
e
d
u
n
i
t,
a
n
d
i
d
e
n
t
i
c
al
p
r
o
c
es
s
es
a
r
e
c
a
r
r
i
e
d
o
u
t
.
T
h
en
,
a
f
e
at
u
r
e
m
a
t
r
ix
o
r
a
m
o
r
e
a
c
cu
r
a
t
e
f
e
a
tu
r
e
m
a
p
i
s
p
r
o
d
u
c
e
d
o
n
ce
t
h
e
w
h
o
l
e
im
ag
e
h
as
b
e
en
p
r
o
c
e
s
s
e
d
.
T
h
i
s
f
ea
tu
r
e
m
a
p
s
h
o
w
s
th
e
l
o
c
at
i
o
n
s
o
f
f
e
atu
r
e
s
u
n
iq
u
e
f
o
r
ev
e
r
y
f
i
l
te
r
.
T
h
e
(
2
)
i
l
lu
s
t
r
a
t
es
th
e
m
a
th
em
a
t
i
c
a
l
r
e
p
r
es
en
t
at
i
o
n
o
f
th
e
c
o
n
v
o
l
u
ti
o
n
p
r
o
c
es
s
[
2
9
]
.
(
,
)
=
(
∗
)
(
,
)
=
∑
∑
(
+
,
+
)
(
,
)
(
2
)
w
h
e
r
e:
∗
r
e
p
r
e
s
en
t
s
th
e
c
o
n
v
o
lu
ti
o
n
p
r
o
c
ess
,
d
e
s
c
r
i
b
e
s
th
e
r
e
s
u
lt
o
f
c
o
n
v
o
lu
t
i
o
n
,
r
e
f
e
r
t
o
t
h
e
in
p
u
t
,
a
n
d
r
e
f
e
r
s
t
o
t
h
e
k
e
r
n
el
.
A
t
a
c
o
n
v
o
lu
ti
o
n
al
lay
e
r
,
s
ev
er
a
l
f
e
a
tu
r
e
m
at
r
i
c
es
a
r
e
a
d
d
e
d
t
o
e
i
th
e
r
th
e
i
n
p
u
t
im
ag
e
o
r
th
e
o
u
t
p
u
t
m
a
t
r
i
c
es
f
r
o
m
th
e
p
r
e
c
e
d
in
g
l
ay
e
r
.
T
h
e
s
e
f
e
a
tu
r
e
m
a
t
r
i
ce
s
a
l
l
o
w
f
o
r
p
a
r
am
e
t
e
r
t
r
ai
n
i
n
g
an
d
u
p
d
a
t
i
n
g
e
a
ch
r
o
w
an
d
c
o
l
u
m
n
b
as
e
d
o
n
th
e
p
r
o
p
a
g
a
ted
g
r
a
d
ie
n
t
v
al
u
e
s
af
t
e
r
ev
e
r
y
t
r
ai
n
in
g
cy
c
l
e
.
T
h
e
w
e
ig
h
ts
i
n
th
is
l
ay
e
r
c
an
b
e
s
h
a
r
e
d
b
y
em
p
l
o
y
i
n
g
s
im
il
a
r
f
i
l
t
e
r
s
in
to
t
h
e
i
d
en
t
i
ca
l
f
e
a
tu
r
e
m
a
p
,
r
e
s
u
l
tin
g
in
a
s
ig
n
if
i
c
an
tly
d
e
c
r
e
as
e
d
o
v
e
r
al
l
n
u
m
b
e
r
o
f
p
a
r
am
et
e
r
s
f
o
r
t
h
e
n
eu
r
a
l
n
etw
o
r
k
.
S
ev
e
r
al
c
r
i
ti
c
a
l
p
a
r
am
e
te
r
s
in
t
h
i
s
l
ay
e
r
s
u
ch
as
f
i
lt
e
r
n
u
m
b
e
r
,
f
il
t
e
r
w
id
th
,
p
a
d
d
i
n
g
,
an
d
s
t
r
i
d
e
a
r
e
s
p
e
c
if
i
e
d
b
y
d
e
v
e
l
o
p
e
r
s
[
2
2
]
.
T
h
e
o
v
e
r
a
ll
f
i
lt
e
r
d
im
en
s
i
o
n
s
u
t
il
iz
e
d
in
c
o
n
v
o
lu
t
i
o
n
o
p
e
r
a
t
i
o
n
s
a
r
e
ty
p
i
c
a
lly
o
d
d
,
a
ll
o
w
in
g
t
h
e
f
i
l
t
e
r
t
o
h
av
e
a
c
en
t
r
a
l
p
o
i
n
t
an
d
o
f
f
e
r
a
s
y
m
m
e
t
r
ic
a
l p
a
d
d
i
n
g
.
W
h
e
r
e
as
t
h
e
k
e
r
n
el
m
a
t
r
ix
i
s
m
o
v
in
g
a
c
r
o
s
s
th
e
im
ag
e
,
th
e
s
t
r
i
d
e
(
w
it
h
a
s
h
if
t
q
u
an
ti
ty
)
p
a
r
am
e
t
e
r
c
o
n
tr
o
l
s
th
e
am
o
u
n
t
th
at
i
t
ch
an
g
es
in
ev
e
r
y
s
t
e
p
.
I
n
c
o
n
t
r
as
t
,
p
a
d
d
i
n
g
in
v
o
lv
e
s
a
d
d
in
g
ze
r
o
ev
en
ly
t
o
a
g
iv
en
in
p
u
t
m
a
t
r
ix
i
n
o
r
d
e
r
t
o
p
r
e
s
e
r
v
e
a
d
im
en
s
i
o
n
o
f
th
e
o
u
tp
u
t
m
at
r
i
c
es
e
q
u
a
l
t
o
th
at
o
f
th
e
in
p
u
t
[
3
0
]
.
A
n
ex
am
p
l
e
o
f
th
e
c
o
n
v
o
lu
t
i
o
n
p
r
o
c
ess
u
s
in
g
a
(
4
×
4
)
i
n
p
u
t
im
ag
e
,
(
3
×
3
)
c
o
n
v
o
l
u
t
i
o
n
c
o
r
e
,
an
d
(
1
)
s
t
r
i
d
e
i
s
d
is
p
l
ay
e
d
in
F
ig
u
r
e
4
.
T
o
o
b
t
a
i
n
th
e
a
p
p
r
o
p
r
i
a
t
e
f
ea
tu
r
e
m
a
p
s
,
d
if
f
e
r
en
t
at
t
r
i
b
u
t
es
a
r
e
f
o
u
n
d
u
ti
l
iz
in
g
v
a
r
i
o
u
s
k
er
n
e
ls
an
d
r
e
p
e
a
t
e
d
.
B
e
h
i
n
d
c
o
n
v
o
lu
ti
o
n
,
th
e
r
esu
l
t
in
g
im
ag
e
’
s
s
i
z
e
i
s
c
o
m
p
u
t
e
d
as
(
3
)
[
3
1
]
:
=
+
2
−
+
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.
23
,
No
.
4
,
A
u
g
u
s
t
20
25
:
1
0
1
0
-
1
0
1
9
1014
F
ig
u
r
e
4
.
E
x
am
p
l
e
o
f
c
o
n
v
o
lu
t
io
n
p
r
o
c
e
s
s
[
3
1
]
2
.
3
.
P
o
o
l
i
n
g
l
a
y
e
r
A
s
f
o
r
th
e
p
o
o
l
in
g
l
ay
e
r
,
it
d
e
cr
e
a
s
es
th
e
ex
t
en
t
o
f
t
h
e
f
e
a
tu
r
es
g
a
th
e
r
e
d
f
r
o
m
th
e
p
r
e
c
e
d
in
g
l
ay
e
r
,
a
n
d
i
d
e
n
ti
c
a
l
f
e
a
tu
r
e
s
b
ec
o
m
e
m
o
r
e
p
r
o
m
in
en
t
.
I
t
ac
c
o
m
p
l
is
h
e
s
t
h
i
s
b
y
r
e
a
r
r
an
g
in
g
th
e
im
ag
e
’
s
s
p
ec
i
f
i
e
d
f
i
lt
e
r
s
.
S
t
at
e
d
o
t
h
e
r
w
is
e
,
it
e
x
ec
u
t
es
t
h
e
s
u
b
s
am
p
l
in
g
p
r
o
c
e
d
u
r
e
.
C
o
n
s
e
q
u
en
t
ly
,
th
e
f
o
ll
o
w
in
g
l
ay
e
r
’
s
d
a
t
a
s
i
ze
w
il
l
d
e
c
r
e
as
e
,
a
n
d
t
h
e
r
esu
l
tin
g
m
o
d
e
l
w
o
n
’
t
o
v
e
r
f
i
t
.
I
t
is
v
i
t
al
t
o
r
em
em
b
e
r
th
a
t
t
h
i
s
d
r
o
p
r
e
s
u
l
ts
in
th
e
d
is
a
p
p
e
a
r
an
c
e
o
f
s
o
m
e
c
r
u
ci
al
d
a
t
a
.
T
h
e
m
ain
a
d
v
an
t
ag
e
o
f
th
e
p
o
o
l
in
g
l
ay
e
r
i
s
th
a
t
i
t
r
e
d
u
c
e
s
th
e
n
u
m
b
e
r
o
f
f
ac
t
o
r
s
th
a
t
th
e
n
e
u
r
a
l
n
e
tw
o
r
k
m
u
s
t
e
s
t
im
at
e
,
w
h
i
ch
l
o
w
e
r
s
th
e
n
e
tw
o
r
k
’
s
c
o
m
p
u
t
at
i
o
n
a
l
d
if
f
i
cu
lty
a
n
d
s
p
e
e
d
s
u
p
t
r
a
in
in
g
[
3
2
]
.
A
p
o
o
l
in
g
p
r
o
c
e
d
u
r
e
i
s
a
ch
i
ev
e
d
in
th
r
e
e
f
o
r
m
s
,
m
in
im
u
m
p
o
o
l
in
g
,
a
v
e
r
a
g
e
p
o
o
l
i
n
g
,
an
d
m
ax
im
u
m
p
o
o
l
in
g
.
M
in
im
u
m
p
o
o
l
in
g
i
s
th
e
p
r
o
c
e
s
s
o
f
i
d
en
tif
y
in
g
th
e
v
a
lu
e
th
at
is
l
o
w
es
t
f
r
o
m
th
e
p
ix
e
l
v
alu
e
s
in
s
i
d
e
th
e
s
p
ec
if
i
e
d
f
il
t
e
r
s
i
z
e
,
w
h
e
r
e
as
m
ax
im
u
m
p
o
o
l
in
g
is
p
e
r
f
o
r
m
ed
b
y
c
h
o
o
s
in
g
th
e
h
ig
h
e
s
t
v
a
lu
e
[
3
3
]
.
T
h
e
i
d
e
a
b
e
h
in
d
av
e
r
ag
e
p
o
o
l
i
n
g
is
t
o
d
iv
i
d
e
t
h
e
t
o
t
a
l
n
u
m
b
e
r
o
f
p
ix
e
l
v
alu
es
in
s
i
d
e
th
e
d
im
en
s
i
o
n
o
f
th
e
f
i
l
t
e
r
r
eg
i
o
n
b
y
th
e
d
im
en
s
i
o
n
o
f
th
e
f
i
l
t
e
r
w
in
d
o
w
[
3
4
]
.
F
i
g
u
r
e
5
d
em
o
n
s
t
r
a
t
es
th
e
p
o
o
l
i
n
g
p
r
o
c
e
s
s
.
F
ig
u
r
e
5
.
T
h
e
p
o
o
l
i
n
g
p
r
o
c
es
s
[
3
1
]
2
.
4
.
F
u
l
l
y
c
o
nn
e
c
t
ed
l
a
y
e
r
Pr
a
c
t
i
c
a
l
ly
al
l
ty
p
es
o
f
n
eu
r
al
n
e
t
w
o
r
k
t
o
p
o
l
o
g
ie
s
u
s
e
FC
l
ay
e
r
s
,
w
h
i
ch
a
r
e
am
o
n
g
th
e
m
o
s
t
f
l
ex
i
b
le
l
ay
e
r
s
.
E
v
e
r
y
n
o
d
e
i
s
l
in
k
e
d
t
o
e
v
e
r
y
o
th
e
r
n
o
d
e
in
th
e
p
r
e
c
e
d
i
n
g
a
n
d
s
u
b
s
e
q
u
e
n
t
l
ay
e
r
s
in
t
h
is
l
ay
e
r
[
3
5
]
.
T
h
e
m
a
jo
r
jo
b
o
f
th
e
l
ay
e
r
is
t
o
c
o
n
v
e
r
t
th
e
f
ea
tu
r
e
m
at
r
ix
t
o
m
ak
e
t
h
e
is
s
u
e
m
o
r
e
p
l
ia
b
l
e
.
T
h
r
o
u
g
h
o
u
t
t
h
i
s
c
o
n
v
e
r
s
i
o
n
,
t
h
e
t
o
t
a
l
n
u
m
b
e
r
o
f
v
a
r
i
a
b
l
es
m
ay
r
i
s
e
,
d
e
c
r
e
as
e
,
o
r
r
em
a
in
c
o
n
s
t
an
t
.
I
n
ev
e
r
y
s
it
u
a
t
i
o
n
,
t
h
e
n
ew
ly
c
r
e
a
t
e
d
d
im
en
s
i
o
n
s
a
r
e
a
l
in
ea
r
m
ix
o
f
t
h
e
d
im
en
s
i
o
n
s
f
r
o
m
th
e
p
r
e
c
ed
i
n
g
l
ay
e
r
.
T
h
en
,
u
s
in
g
an
a
c
tiv
a
ti
o
n
f
u
n
c
ti
o
n
,
th
e
a
d
d
i
t
i
o
n
a
l
d
im
en
s
i
o
n
s
a
r
e
p
r
o
v
i
d
e
d
n
o
n
li
n
e
a
r
i
ty
[
3
6
]
.
F
ig
u
r
e
6
.
i
l
lu
s
t
r
a
t
es
a
s
i
x
-
d
im
e
n
s
i
o
n
al
s
p
a
c
e
c
o
n
v
e
r
t
e
d
t
o
a
t
h
r
e
e
-
d
im
en
s
i
o
n
al
f
e
a
tu
r
e
s
p
a
ce
b
y
a
F
C
l
ay
e
r
.
F
C
l
ay
e
r
s
a
l
l
o
w
f
o
r
an
y
ty
p
e
o
f
i
n
t
e
r
a
c
ti
o
n
am
o
n
g
in
p
u
t
p
a
r
am
e
t
e
r
s
.
T
h
is
b
eh
av
i
o
r
en
a
b
le
s
FC
l
ay
e
r
s
t
o
a
c
q
u
i
r
e
an
y
f
u
n
ct
i
o
n
w
it
h
en
o
u
g
h
w
i
d
th
a
n
d
d
e
p
t
h
[
3
5
]
.
N
ev
e
r
th
el
e
s
s
,
a
ctu
a
l
a
p
p
li
c
a
ti
o
n
h
a
s
p
r
o
v
en
th
a
t
s
u
ch
t
h
e
o
r
et
i
c
a
l
p
r
o
m
i
s
e
is
f
r
e
q
u
e
n
t
ly
n
o
t
f
u
lf
i
l
l
e
d
.
T
o
t
a
c
k
le
th
is
i
s
s
u
e
,
s
c
i
en
t
is
t
s
h
av
e
d
ev
e
l
o
p
e
d
p
a
r
t
i
cu
l
a
r
l
ay
e
r
s
s
u
ch
a
s
r
e
cu
r
r
en
t
an
d
c
o
n
v
o
lu
ti
o
n
al
n
eu
r
a
l
n
etw
o
r
k
s
.
T
h
es
e
d
ev
el
o
p
e
d
l
ay
e
r
s
ex
p
l
o
it
in
d
u
c
ti
v
e
b
ia
s
d
e
p
en
d
in
g
o
n
th
e
s
e
q
u
e
n
t
i
al
o
r
s
p
a
ti
a
l
a
r
r
an
g
em
en
ts
o
f
p
a
r
t
i
cu
la
r
d
a
t
a
s
o
u
r
c
es
,
in
c
lu
d
in
g
t
ex
t
,
v
i
d
e
o
s
,
an
d
im
ag
e
s
[
3
6
]
.
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
n
vo
l
u
tio
n
n
e
u
r
a
l n
etw
o
r
k
mo
d
el
fo
r
kn
ee
o
s
teo
p
o
r
o
s
is
cla
s
s
ifica
tio
n
…
(
Oma
r
K
h
a
lid
M.
A
li
)
1015
F
ig
u
r
e
6
.
A
s
y
s
t
em
at
i
c
f
u
lly
c
o
n
n
e
c
t
e
d
l
ay
e
r
2
.
5
.
P
er
f
o
rm
a
nce
m
et
rics
T
h
e
m
ai
n
f
ac
to
r
to
co
n
s
id
er
d
u
r
in
g
s
y
s
te
m
tr
ain
i
n
g
is
ac
c
u
r
ac
y
.
Af
ter
w
h
ic
h
th
e
e
n
tir
e
tr
ain
in
g
p
r
o
ce
d
u
r
e
is
f
o
llo
w
ed
,
th
is
f
ac
to
r
o
f
th
e
tr
ain
in
g
i
m
a
g
e
s
is
r
ec
o
r
d
ed
an
d
p
lo
tted
.
A
cc
u
r
ac
y
r
ef
er
s
to
h
o
w
f
r
eq
u
en
tl
y
a
C
NN
m
o
d
el
p
r
o
p
er
l
y
p
r
ed
icts
o
b
j
ec
ts
,
r
ep
r
esen
ted
b
y
th
e
n
u
m
b
er
o
f
v
alid
d
ata
to
th
e
to
tal
n
u
m
b
er
o
f
d
ata
as
s
h
o
w
n
i
n
(
4
)
.
T
o
v
er
if
y
th
e
m
o
d
el
’
s
ac
cu
r
ac
y
,
th
e
Ker
as
ass
es
s
m
e
n
t
f
u
n
ctio
n
w
a
s
ca
lled
o
n
th
e
co
n
s
tr
u
cted
m
o
d
el,
p
ass
in
g
i
n
th
e
test
in
g
d
ata
as a
n
i
n
p
u
t.
=
(
4
)
I
n
ad
d
itio
n
,
o
th
er
p
ar
am
eter
s
ar
e
ca
lcu
lated
to
esti
m
ate
t
h
e
s
y
s
te
m
ef
f
icie
n
c
y
s
u
ch
as
p
r
ec
is
io
n
,
s
en
s
iti
v
it
y
o
r
r
ec
all,
an
d
F1
-
s
c
o
r
e
b
y
th
e
(
5
)
-
(
7
)
,
[
3
7
]
.
=
+
(
5
)
=
+
(
6
)
1
=
2
∗
∗
+
(
7
)
w
h
er
e:
T
P
is
th
e
n
u
m
b
er
o
f
tr
u
e
p
o
s
itiv
e
FP
is
th
e
n
u
m
b
er
o
f
f
al
s
e
p
o
s
it
iv
e
FN is t
h
e
n
u
m
b
er
o
f
f
alse
n
e
g
ativ
e
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
is
r
esear
ch
ai
m
s
to
d
iag
n
o
s
e
o
s
teo
p
o
r
o
s
is
b
y
clas
s
i
f
y
in
g
th
e
X
-
r
a
y
i
m
a
g
es
i
n
to
th
r
e
e
g
r
o
u
p
s
:
h
ea
lt
h
y
,
ac
t
u
al
o
s
teo
p
en
ia,
an
d
o
s
teo
p
o
r
o
s
is
.
T
h
e
class
if
icat
i
o
n
m
et
h
o
d
o
f
th
e
d
esig
n
ed
C
N
N
is
r
ep
r
esen
ted
b
y
ex
tr
ac
ti
n
g
th
e
f
ea
t
u
r
es o
f
t
h
e
c
o
llectio
n
i
m
ag
e
s
a
n
d
clas
s
if
y
i
n
g
th
e
m
a
u
to
m
atica
ll
y
.
T
h
e
n
t
h
e
m
o
d
el
in
te
n
d
s
to
r
ed
u
ce
h
u
m
a
n
er
r
o
r
an
d
im
p
r
o
v
e
ea
r
l
y
d
is
ea
s
e
d
etec
tio
n
r
ate
s
.
Fig
u
r
e
7
illu
s
tr
ates
th
e
p
er
f
o
r
m
an
ce
o
f
t
h
e
s
y
s
te
m
i
n
ter
m
s
o
f
ac
cu
r
ac
y
w
it
h
3
0
ep
o
ch
s
.
T
h
r
o
u
g
h
o
u
t
th
e
tr
ain
i
n
g
p
er
io
d
,
an
in
itial
in
c
r
ea
s
i
n
g
te
n
d
en
c
y
i
s
n
o
ted
.
Af
ter
th
e
13
th
ep
o
ch
,
th
e
tr
ain
in
g
li
n
e
ex
ce
ed
s
th
e
v
alid
atio
n
li
n
e
a
n
d
s
ta
y
s
co
n
ti
n
u
o
u
s
l
y
ab
o
v
e
it,
but
it
is
less
n
o
is
y
.
A
l
s
o
,
it
ca
n
b
e
o
b
s
er
v
e
d
th
at
th
e
v
alid
atio
n
lin
e
i
s
m
o
r
e
s
tab
le
w
i
th
h
i
g
h
er
v
al
u
es
in
th
e
f
i
n
al
p
h
ase,
w
h
i
ch
m
ea
n
s
t
h
at
t
h
e
d
y
n
a
m
ic
co
n
v
o
l
u
tio
n
i
n
cr
ea
s
e
s
th
e
s
y
s
te
m
’
s
ad
ap
tab
ilit
y
a
n
d
v
alid
atio
n
e
f
f
icie
n
c
y
.
An
y
w
a
y
,
th
e
d
if
f
er
e
n
ce
b
et
w
ee
n
t
h
e
v
alid
atio
n
an
d
tr
ai
n
lin
es r
e
m
ai
n
s
r
ath
er
s
m
al
l,
w
h
ich
in
d
icate
s
t
h
e
ef
f
icie
n
c
y
o
f
th
e
d
esi
g
n
ed
s
y
s
te
m
.
R
eg
ar
d
in
g
lo
s
s
,
d
u
r
in
g
i
n
itial
tr
ain
in
g
,
t
h
e
s
u
g
g
ested
m
o
d
e
l
ex
p
er
ien
ce
s
h
i
g
h
er
an
d
m
o
r
e
u
n
s
tab
le
lo
s
s
.
De
m
o
n
s
tr
ati
n
g
t
h
at
th
e
s
y
s
te
m
i
s
alter
ed
f
u
r
th
er
d
u
r
i
n
g
t
h
e
p
r
eli
m
in
ar
y
p
h
ase,
an
d
th
e
w
eig
h
t
s
ar
e
r
eg
u
lar
l
y
c
h
an
g
ed
,
as
il
lu
s
tr
at
ed
in
Fi
g
u
r
e
8
.
W
ith
co
n
ti
n
u
e
d
tr
ain
in
g
,
t
h
e
v
alid
atio
n
l
in
e
f
l
u
ctu
a
tio
n
s
ca
n
b
e
o
b
s
er
v
ed
to
d
ec
r
ea
s
e
as
t
h
e
lo
s
s
v
al
u
es
d
ec
r
ea
s
e
s
i
g
n
i
f
ica
n
tl
y
.
A
t
t
h
e
f
i
n
al
tr
ai
n
i
n
g
p
h
ase,
th
e
v
alid
atio
n
li
n
e
b
ec
o
m
e
s
m
o
r
e
s
tab
le,
an
d
t
h
e
g
ap
w
ith
t
h
e
tr
ai
n
lin
e
w
id
e
n
s
s
o
m
e
w
h
at.
Fig
u
r
e
9
d
is
p
la
y
s
t
h
e
co
n
f
u
s
i
o
n
m
atr
i
x
d
escr
ib
i
n
g
th
e
r
elatio
n
b
et
w
ee
n
th
e
ac
tu
a
l
v
a
lu
e
s
an
d
t
h
e
p
r
ed
icted
v
alu
es
f
o
r
t
h
e
d
esi
g
n
ed
m
o
d
el.
B
esid
es
p
r
o
v
id
i
n
g
k
n
o
w
led
g
e
ab
o
u
t
th
e
c
lass
if
ie
r
’
s
s
h
o
r
tco
m
i
n
g
s
,
i
t
also
d
is
p
lay
s
an
y
p
ar
ticu
lar
er
r
o
r
s
th
at
m
a
y
b
e
ap
p
ea
r
in
g
.
I
t
also
ass
i
s
ts
in
o
v
er
co
m
i
n
g
th
e
p
r
o
b
lem
o
f
r
el
y
in
g
s
o
lel
y
o
n
clas
s
if
ier
ac
cu
r
ac
y
.
T
h
e
to
tal
ac
cu
r
ac
y
o
f
th
e
s
y
s
te
m
w
as
(
9
0
.
2
5
%)
ca
lcu
lated
b
a
s
ed
o
n
th
e
(
4
)
.
A
ls
o
,
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.
23
,
No
.
4
,
A
u
g
u
s
t
20
25
:
1
0
1
0
-
1
0
1
9
1016
th
e
v
al
u
es
o
f
t
h
e
ca
lc
u
lated
p
a
r
a
m
eter
s
ar
e
s
h
o
w
n
i
n
t
h
e
cla
s
s
if
ica
tio
n
r
ep
o
r
t
in
T
ab
le
2
.
T
h
e
p
r
o
p
o
s
ed
m
o
d
el
’
s
ef
f
icien
c
y
ca
n
b
e
p
r
o
v
en
b
y
c
o
m
p
ar
i
n
g
it
w
it
h
s
i
m
i
lar
s
y
s
te
m
s
s
u
c
h
as
[
3
8
]
–
[
4
1
]
.
T
a
b
le
3
.
illu
s
tr
ates
t
h
at
t
h
e
p
r
o
p
o
s
ed
m
o
d
el
p
er
f
o
r
m
s
b
ett
er
in
ac
cu
r
ac
y
t
h
a
n
o
th
er
w
o
r
k
s
,
w
h
ic
h
r
ev
ea
l
s
a
b
etter
d
iag
n
o
s
is
o
p
er
atio
n
.
Fig
u
r
e
7
.
T
h
e
ac
cu
r
ac
y
o
f
t
h
e
d
esig
n
ed
C
NN
Fig
u
r
e
8
.
T
h
e
lo
s
s
o
f
th
e
d
esi
g
n
ed
C
NN
Fig
u
r
e
9
.
C
o
n
f
u
s
io
n
m
atr
ix
r
el
atin
g
to
th
e
d
ataset
’
s
v
alid
atio
n
s
et
T
ab
le
2
.
C
lass
if
icatio
n
r
ep
o
r
t
C
l
a
ss
P
r
e
c
i
si
o
n
R
e
c
a
l
l
F1
-
sco
r
e
H
e
a
l
t
h
y
0
.
9
6
1
0
.
9
1
9
0
.
9
3
9
A
c
t
u
a
l
o
st
e
o
p
e
n
i
a
0
.
7
8
2
0
.
7
9
4
0
.
7
8
7
O
st
e
o
p
o
r
o
si
s
0
.
8
9
7
0
.
9
3
1
0
.
9
1
3
T
ab
le
3
.
C
o
m
p
ar
is
o
n
o
f
ac
cu
r
ac
y
w
it
h
o
th
er
w
o
r
k
s
R
e
f
e
r
e
n
c
e
T
i
t
l
e
D
a
t
a
se
t
M
e
t
h
o
d
A
c
c
u
r
a
c
y
[
3
8
]
C
o
mp
a
r
i
so
n
o
f
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
mo
d
e
l
a
c
c
u
r
a
c
y
f
o
r
o
st
e
o
p
o
r
o
si
s c
l
a
ssi
f
i
c
a
t
i
o
n
o
n
k
n
e
e
r
a
d
i
o
g
r
a
p
h
2
4
0
X
-
r
a
y
i
mag
e
s
G
o
o
g
L
e
N
e
t
VGG
-
16
R
e
sN
e
t
-
50
9
0
%
8
7
%
8
3
%
[
3
9
]
O
st
e
o
p
o
r
o
si
s
d
i
a
g
n
o
s
i
s
i
n
k
n
e
e
X
-
r
a
y
s
b
y
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
b
a
se
d
o
n
c
o
n
v
o
l
u
t
i
o
n
n
e
u
r
a
l
n
e
t
w
o
r
k
3
8
1
k
n
e
e
X
-
r
a
y
i
mag
e
s
A
l
e
x
N
e
t
R
e
sN
e
t
V
g
g
N
e
t
-
19
V
g
g
N
e
t
-
16
9
0
.
9
1
%
8
6
.
3
%
8
4
.
2
%
8
6
.
3
%
[
4
0
]
U
t
i
l
i
z
i
n
g
d
e
e
p
l
e
a
r
n
i
n
g
f
o
r
o
st
e
o
p
o
r
o
si
s
d
i
a
g
n
o
si
s
t
h
r
o
u
g
h
k
n
e
e
X
-
r
a
y
a
n
a
l
y
si
s
1
5
7
3
X
-
r
a
y
i
mag
e
s
V
G
G
1
9
8
9
%
[
4
1
]
D
e
e
p
l
e
a
r
n
i
n
g
-
b
a
se
d
a
p
p
r
o
a
c
h
e
s
f
o
r
d
i
a
g
n
o
si
s
a
n
d
d
e
t
e
c
t
i
o
n
o
f
o
st
e
o
p
o
r
o
si
s
u
si
n
g
c
l
i
n
i
c
a
l
d
a
t
a
o
f
C
T
a
n
d
X
-
r
a
y
i
mag
e
s
C
T
a
n
d
X
-
r
a
y
t
h
e
e
x
a
c
t
n
u
m
b
e
r
o
f
i
mag
e
s n
o
t
me
n
t
i
o
n
e
d
Ei
g
h
t
d
e
e
p
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
e
s
V
G
G
1
6
h
a
s
t
h
e
b
e
st
a
c
c
u
r
a
c
y
o
f
8
2
.
7
3
%
T
h
e
p
r
o
p
o
se
d
mo
d
e
l
A
C
N
N
m
o
d
e
l
f
o
r
K
O
P
C
l
a
ssi
f
i
c
a
t
i
o
n
u
s
i
n
g
X
-
r
a
y
i
mag
e
s
1
9
4
7
X
-
r
a
y
i
mag
e
s
C
N
N
9
0
.
2
5
%
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
n
vo
l
u
tio
n
n
e
u
r
a
l n
etw
o
r
k
mo
d
el
fo
r
kn
ee
o
s
teo
p
o
r
o
s
is
cla
s
s
ifica
tio
n
…
(
Oma
r
K
h
a
lid
M.
A
li
)
1017
4.
CO
NCLU
SI
O
N
T
h
e
s
er
io
u
s
n
e
s
s
o
f
K
OP
n
ec
ess
itate
s
p
r
o
m
p
t
d
iag
n
o
s
is
a
n
d
tr
ea
tm
e
n
t;
n
e
v
er
th
ele
s
s
,
d
e
p
en
d
in
g
o
n
h
u
m
a
n
s
p
ec
ialis
ts
ca
n
p
r
o
v
e
c
o
s
tl
y
an
d
ti
m
e
-
co
n
s
u
m
i
n
g
.
Ma
k
in
g
ed
u
ca
ted
co
n
cl
u
s
io
n
s
ab
o
u
t i
m
a
g
e
s
o
b
tain
ed
f
r
o
m
d
if
f
er
en
t
p
atien
ts
is
g
r
e
atl
y
aid
ed
b
y
th
e
ass
i
s
ta
n
ce
p
r
o
v
id
ed
b
y
v
i
s
ib
le
A
I
.
T
h
is
p
ap
er
p
r
o
d
u
ce
d
an
ef
f
icien
t
C
N
N
m
o
d
el
d
esi
g
n
f
o
r
class
if
y
i
n
g
th
e
av
ailab
le
d
at
aset.
T
h
e
m
ai
n
g
o
als
o
f
t
h
e
p
r
e
s
en
t
r
esear
c
h
ar
e
to
p
r
o
d
u
ce
1
9
4
7
m
ed
ical
i
m
a
g
es
o
f
k
n
ee
X
-
r
a
y
s
w
it
h
3
class
es:
h
ea
lt
h
y
,
ac
tu
al
o
s
teo
p
en
ia,
an
d
o
s
t
eo
p
o
r
o
s
is
w
h
ich
ar
e
v
alid
ated
b
y
m
u
ltip
le
f
ac
t
o
r
s
,
an
d
to
s
u
g
g
est
a
d
ee
p
lear
n
in
g
m
eth
o
d
u
s
i
n
g
a
n
ef
f
ici
en
t
C
N
N
m
o
d
el
to
class
i
f
y
v
ar
io
u
s
lev
e
ls
o
f
t
h
e
d
is
ea
s
e.
T
h
e
s
u
g
g
e
s
ted
m
o
d
el
p
r
o
d
u
ce
d
en
co
u
r
ag
i
n
g
o
u
tco
m
es
an
d
ca
n
a
s
s
i
s
t
d
o
cto
r
s
in
d
iag
n
o
s
i
n
g
KOP
in
l
ess
ti
m
e
an
d
at
a
r
ea
s
o
n
ab
le
co
s
t.
Fu
r
th
er
i
n
f
o
r
m
atio
n
ca
n
b
e
g
ath
er
ed
in
t
h
e
f
u
tu
r
e,
p
ar
ticu
lar
l
y
f
r
o
m
p
eo
p
le
w
h
o
ar
e
o
s
teo
p
o
r
o
tic
an
d
n
o
r
m
al.
I
n
ad
d
itio
n
,
i
n
o
r
d
er
to
cr
ea
te
a
u
n
iv
er
s
al
o
s
teo
p
o
r
o
s
is
d
iag
n
o
s
is
m
et
h
o
d
,
w
e
ca
n
d
eter
m
i
n
e
th
e
co
r
r
elatio
n
b
et
w
ee
n
o
s
teo
p
o
r
o
s
is
at
th
e
k
n
ee
an
d
o
s
teo
p
o
r
o
s
is
at
d
if
f
er
en
t
lo
ca
tio
n
s
.
F
u
r
th
er
m
o
r
e,
a
s
y
s
te
m
th
at
u
s
es
cli
n
ical
v
ar
iab
les
a
n
d
i
m
a
g
i
n
g
d
ata
to
id
en
ti
f
y
o
s
teo
p
o
r
o
s
is
ca
n
b
e
d
ev
elo
p
ed
.
ACK
NO
WL
E
D
G
M
E
NT
S
T
h
e
au
th
o
r
s
al
s
o
ex
te
n
d
th
eir
ap
p
r
ec
iatio
n
to
th
e
Dep
ar
t
m
e
n
t
o
f
Me
c
h
atr
o
n
ic
s
E
n
g
i
n
ee
r
i
n
g
,
C
o
lleg
e
o
f
E
n
g
in
ee
r
i
n
g
,
Un
i
v
er
s
it
y
o
f
Mo
s
u
l,
f
o
r
t
h
eir
v
al
u
ab
le
ass
i
s
tan
ce
d
u
r
i
n
g
t
h
e
s
t
u
d
y
.
F
UNDIN
G
I
NF
O
RM
AT
I
O
N
Au
t
h
o
r
s
s
tate
n
o
f
u
n
d
in
g
i
n
v
o
l
v
ed
.
T
h
e
au
th
o
r
s
d
ec
lar
e
th
at
t
h
is
r
esear
c
h
w
as
co
n
d
u
c
ted
w
i
th
o
u
t
a
n
y
ex
ter
n
al
f
u
n
d
i
n
g
.
A
l
l e
x
p
en
s
es
w
er
e
p
er
s
o
n
all
y
co
v
er
ed
b
y
t
h
e
au
t
h
o
r
s
.
AUTHO
R
CO
NT
RIB
UT
I
O
NS ST
A
T
E
M
E
NT
T
h
is
j
o
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
)
to
r
ec
o
g
n
ize
in
d
i
v
id
u
al
au
th
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
O
m
ar
Kh
a
lid
M.
A
l
i
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
A
b
ee
r
K.
I
b
r
ah
i
m
✓
✓
✓
✓
✓
✓
✓
B
ilal R.
A
l
ta
m
er
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
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
Au
t
h
o
r
s
s
tate
n
o
co
n
f
lic
t o
f
i
n
t
er
est.
I
NF
O
RM
E
D
CO
NSE
N
T
W
e
u
s
ed
th
e
d
ataset
av
ailab
le
o
n
th
e
Kag
g
le
w
eb
s
i
te,
s
o
w
e
h
av
e
o
b
tain
ed
in
f
o
r
m
ed
co
n
s
e
n
t
f
r
o
m
all
in
d
iv
id
u
als i
n
cl
u
d
ed
in
t
h
is
s
tu
d
y
.
E
T
H
I
CAL AP
P
RO
V
AL
T
h
e
r
esear
ch
r
elate
d
to
h
u
m
a
n
u
s
e
h
as
b
ee
n
co
m
p
lied
w
it
h
all
th
e
r
ele
v
an
t
n
at
io
n
al
r
e
g
u
l
atio
n
s
a
n
d
in
s
t
itu
tio
n
al
p
o
licies
i
n
ac
co
r
d
an
ce
w
ith
t
h
e
ten
e
ts
o
f
th
e
He
ls
in
k
i
Dec
lar
atio
n
an
d
h
as
b
ee
n
ap
p
r
o
v
ed
b
y
th
e
au
th
o
r
s
’
i
n
s
ti
tu
t
io
n
al
r
ev
ie
w
b
o
ar
d
o
r
eq
u
iv
alen
t c
o
m
m
i
ttee
.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
ata
th
at
s
u
p
p
o
r
t
th
e
f
i
n
d
in
g
s
o
f
t
h
i
s
s
tu
d
y
a
r
e
o
p
en
l
y
a
v
ailab
le
i
n
[
K
ag
g
le
]
a
t
h
ttp
s
:/
/
www
.
k
ag
g
le.
co
m
/d
atas
ets/
s
te
v
ep
y
t
h
o
n
/o
s
teo
p
o
r
o
s
is
-
k
n
ee
-
x
r
a
y
-
d
ataset
[
21
].
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.
23
,
No
.
4
,
A
u
g
u
s
t
20
25
:
1
0
1
0
-
1
0
1
9
1018
RE
F
E
R
E
NC
E
S
[
1
]
O
.
Jo
h
n
e
l
l
a
n
d
J.
A
.
K
a
n
i
s,
“
A
n
e
st
i
ma
t
e
o
f
t
h
e
w
o
r
l
d
w
i
d
e
p
r
e
v
a
l
e
n
c
e
a
n
d
d
i
sa
b
i
l
i
t
y
a
sso
c
i
a
t
e
d
w
i
t
h
o
st
e
o
p
o
r
o
t
i
c
f
r
a
c
t
u
r
e
s,
”
O
st
e
o
p
o
r
o
si
s I
n
t
e
rn
a
t
i
o
n
a
l
,
v
o
l
.
1
7
,
n
o
.
1
2
,
p
p
.
1
7
2
6
–
1
7
3
3
,
O
c
t
.
2
0
0
6
,
d
o
i
:
1
0
.
1
0
0
7
/
s
0
0
1
9
8
-
0
0
6
-
0
1
7
2
-
4.
[
2
]
H
.
K
a
t
o
e
t
a
l
.
,
“
I
d
e
n
t
i
f
i
c
a
t
i
o
n
o
f
EN
P
P
1
h
a
p
l
o
i
n
s
u
f
f
i
c
i
e
n
c
y
i
n
p
a
t
i
e
n
t
s
w
i
t
h
d
i
f
f
u
se
i
d
i
o
p
a
t
h
i
c
s
k
e
l
e
t
a
l
h
y
p
e
r
o
st
o
s
i
s
a
n
d
e
a
r
l
y
‐
o
n
se
t
o
st
e
o
p
o
r
o
si
s,”
J
o
u
rn
a
l
o
f
B
o
n
e
a
n
d
M
i
n
e
ra
l
R
e
se
a
rc
h
,
v
o
l
.
3
7
,
n
o
.
6
,
p
p
.
1
1
2
5
–
1
1
3
5
,
D
e
c
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
0
2
/
j
b
mr
.
4
5
5
0
.
[
3
]
I
.
M
.
W
a
n
i
a
n
d
S
.
A
r
o
r
a
,
“
C
o
mp
u
t
e
r
-
a
i
d
e
d
d
i
a
g
n
o
si
s
sy
st
e
ms
f
o
r
o
st
e
o
p
o
r
o
si
s
d
e
t
e
c
t
i
o
n
:
a
c
o
mp
r
e
h
e
n
si
v
e
s
u
r
v
e
y
,
”
Me
d
i
c
a
l
&
Bi
o
l
o
g
i
c
a
l
E
n
g
i
n
e
e
r
i
n
g
&
C
o
m
p
u
t
i
n
g
,
v
o
l
.
5
8
,
n
o
.
9
,
p
p
.
1
8
7
3
–
1
9
1
7
,
S
e
p
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
5
1
7
-
0
2
0
-
0
2
1
7
1
-
3.
[
4
]
H.
-
W
.
C
h
a
n
g
,
Y
.
-
H
.
C
h
i
u
,
H
.
-
Y
.
K
a
o
,
C
.
-
H
.
Y
a
n
g
,
a
n
d
W
.
-
H
.
H
o
,
“
C
o
mp
a
r
i
so
n
o
f
c
l
a
ssi
f
i
c
a
t
i
o
n
a
l
g
o
r
i
t
h
ms
w
i
t
h
w
r
a
p
p
e
r
-
b
a
se
d
f
e
a
t
u
r
e
se
l
e
c
t
i
o
n
f
o
r
p
r
e
d
i
c
t
i
n
g
o
st
e
o
p
o
r
o
si
s
o
u
t
c
o
me
b
a
se
d
o
n
g
e
n
e
t
i
c
f
a
c
t
o
r
s
i
n
a
t
a
i
w
a
n
e
se
w
o
me
n
p
o
p
u
l
a
t
i
o
n
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
En
d
o
c
r
i
n
o
l
o
g
y
,
v
o
l
.
2
0
1
3
,
p
p
.
1
–
8
,
2
0
1
3
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
1
3
/
8
5
0
7
3
5
.
[
5
]
S
.
G
n
u
d
i
,
E.
S
i
t
t
a
,
a
n
d
L
.
L
i
si
,
“
R
e
l
a
t
i
o
n
s
h
i
p
o
f
b
o
d
y
mass
i
n
d
e
x
w
i
t
h
mai
n
l
i
m
b
f
r
a
g
i
l
i
t
y
f
r
a
c
t
u
r
e
s
i
n
p
o
st
me
n
o
p
a
u
sal
w
o
me
n
,
”
J
o
u
rn
a
l
o
f
Bo
n
e
a
n
d
Mi
n
e
r
a
l
Me
t
a
b
o
l
i
sm
,
v
o
l
.
2
7
,
n
o
.
4
,
p
p
.
4
7
9
–
4
8
4
,
J
u
l
.
2
0
0
9
,
d
o
i
:
1
0
.
1
0
0
7
/
s
0
0
7
7
4
-
0
0
9
-
0
0
5
6
-
8.
[
6
]
J.
K
a
n
i
s
e
t
a
l
.
,
“
A
me
t
a
-
a
n
a
l
y
si
s
o
f
p
r
e
v
i
o
u
s
f
r
a
c
t
u
r
e
a
n
d
su
b
se
q
u
e
n
t
f
r
a
c
t
u
r
e
r
i
sk
,
”
Bo
n
e
,
v
o
l
.
3
5
,
n
o
.
2
,
p
p
.
3
7
5
–
3
8
2
,
A
u
g
.
2
0
0
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
b
o
n
e
.
2
0
0
4
.
0
3
.
0
2
4
.
[
7
]
H
.
P
.
D
i
ma
i
,
“
U
se
o
f
d
u
a
l
-
e
n
e
r
g
y
X
-
r
a
y
a
b
so
r
p
t
i
o
me
t
r
y
(
D
X
A
)
f
o
r
d
i
a
g
n
o
s
i
s
a
n
d
f
r
a
c
t
u
r
e
r
i
sk
a
sse
ssm
e
n
t
;
W
H
O
-
c
r
i
t
e
r
i
a
,
T
-
a
n
d
Z
-
sco
r
e
,
a
n
d
r
e
f
e
r
e
n
c
e
d
a
t
a
b
a
se
s,”
B
o
n
e
,
v
o
l
.
1
0
4
,
p
p
.
3
9
–
4
3
,
N
o
v
.
2
0
1
7
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
b
o
n
e
.
2
0
1
6
.
1
2
.
0
1
6
.
[
8
]
W
H
O
,
“
A
ss
e
ssm
e
n
t
o
f
f
r
a
c
t
u
r
e
r
i
sk
a
n
d
i
t
s a
p
p
l
i
c
a
t
i
o
n
t
o
scre
e
n
i
n
g
f
o
r
p
o
st
me
n
o
p
a
u
sal
o
st
e
o
p
o
r
o
si
s,”
1
9
9
4
.
[
9
]
Y
.
C
h
e
n
,
Y
.
G
u
o
,
X
.
Z
h
a
n
g
,
Y
.
M
e
i
,
Y
.
F
e
n
g
,
a
n
d
X
.
Z
h
a
n
g
,
“
B
o
n
e
s
u
sce
p
t
i
b
i
l
i
t
y
map
p
i
n
g
w
i
t
h
M
R
I
i
s a
n
a
l
t
e
r
n
a
t
i
v
e
a
n
d
r
e
l
i
a
b
l
e
b
i
o
mar
k
e
r
o
f
o
st
e
o
p
o
r
o
si
s
i
n
p
o
s
t
me
n
o
p
a
u
s
a
l
w
o
m
e
n
,
”
E
u
ro
p
e
a
n
R
a
d
i
o
l
o
g
y
,
v
o
l
.
2
8
,
n
o
.
1
2
,
p
p
.
5
0
2
7
–
5
0
3
4
,
D
e
c
.
2
0
1
8
,
d
o
i
:
1
0
.
1
0
0
7
/
s
0
0
3
3
0
-
0
1
8
-
5
4
1
9
-
x.
[
1
0
]
A
.
D
.
B
r
e
t
t
a
n
d
J.
K
.
B
r
o
w
n
,
“
Q
u
a
n
t
i
t
a
t
i
v
e
c
o
mp
u
t
e
d
t
o
mo
g
r
a
p
h
y
a
n
d
o
p
p
o
r
t
u
n
i
st
i
c
b
o
n
e
d
e
n
si
t
y
scre
e
n
i
n
g
b
y
d
u
a
l
u
se
o
f
c
o
mp
u
t
e
d
t
o
mo
g
r
a
p
h
y
sca
n
s,”
J
o
u
rn
a
l
o
f
O
r
t
h
o
p
a
e
d
i
c
T
ra
n
sl
a
t
i
o
n
,
v
o
l
.
3
,
n
o
.
4
,
p
p
.
1
7
8
–
1
8
4
,
O
c
t
.
2
0
1
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
o
t
.
2
0
1
5
.
0
8
.
0
0
6
.
[
1
1
]
E.
W
.
G
r
e
g
g
e
t
a
l
.
,
“
T
h
e
e
p
i
d
e
mi
o
l
o
g
y
o
f
q
u
a
n
t
i
t
a
t
i
v
e
u
l
t
r
a
so
u
n
d
:
A
r
e
v
i
e
w
o
f
t
h
e
r
e
l
a
t
i
o
n
sh
i
p
s
w
i
t
h
b
o
n
e
mass,
o
st
e
o
p
o
r
o
si
s
a
n
d
f
r
a
c
t
u
r
e
r
i
sk
,
”
O
s
t
e
o
p
o
r
o
si
s
I
n
t
e
r
n
a
t
i
o
n
a
l
,
v
o
l
.
7
,
n
o
.
2
,
p
p
.
8
9
–
9
9
,
M
a
r
.
1
9
9
7
,
d
o
i
:
1
0
.
1
0
0
7
/
B
F
0
1
6
2
3
6
8
2
.
[
1
2
]
M
.
K
a
l
b
h
o
r
,
S
.
V
.
S
h
i
n
d
e
,
a
n
d
H
.
J
u
d
e
,
“
C
e
r
v
i
c
a
l
c
a
n
c
e
r
d
i
a
g
n
o
s
i
s
b
a
se
d
o
n
c
y
t
o
l
o
g
y
p
a
p
sme
a
r
i
mag
e
c
l
a
ssi
f
i
c
a
t
i
o
n
u
s
i
n
g
f
r
a
c
t
i
o
n
a
l
c
o
e
f
f
i
c
i
e
n
t
a
n
d
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
c
l
a
s
si
f
i
e
r
s,”
T
ELKO
MN
I
K
A
(
T
e
l
e
c
o
m
m
u
n
i
c
a
t
i
o
n
C
o
m
p
u
t
i
n
g
El
e
c
t
r
o
n
i
c
s
a
n
d
C
o
n
t
r
o
l
)
,
v
o
l
.
2
0
,
n
o
.
5
,
p
p
.
1
0
9
1
–
1
1
0
2
,
O
c
t
.
2
0
2
2
,
d
o
i
:
1
0
.
1
2
9
2
8
/
t
e
l
k
o
mn
i
k
a
.
v
2
0
i
5
.
2
2
4
4
0
.
[
1
3
]
M
.
I
b
r
a
h
i
m,
M
.
L
o
u
i
e
,
C
.
M
o
d
a
r
r
e
s,
a
n
d
J
.
P
a
i
sl
e
y
,
“
G
l
o
b
a
l
e
x
p
l
a
n
a
t
i
o
n
s
o
f
n
e
u
r
a
l
n
e
t
w
o
r
k
s,”
i
n
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
2
0
1
9
AAAI/
A
C
M
C
o
n
f
e
r
e
n
c
e
o
n
AI
,
E
t
h
i
c
s
,
a
n
d
S
o
c
i
e
t
y
,
Ja
n
.
2
0
1
9
,
p
p
.
2
7
9
–
2
8
7
.
d
o
i
:
1
0
.
1
1
4
5
/
3
3
0
6
6
1
8
.
3
3
1
4
2
3
0
.
[
1
4
]
O
.
L
o
y
o
l
a
-
G
o
n
z
a
l
e
z
,
“
B
l
a
c
k
-
b
o
x
v
s.
W
h
i
t
e
-
b
o
x
:
u
n
d
e
r
st
a
n
d
i
n
g
t
h
e
i
r
a
d
v
a
n
t
a
g
e
s
a
n
d
w
e
a
k
n
e
sse
s
f
r
o
m
a
p
r
a
c
t
i
c
a
l
p
o
i
n
t
o
f
v
i
e
w
,
”
I
EEE
A
c
c
e
ss
,
v
o
l
.
7
,
p
p
.
1
5
4
0
9
6
–
1
5
4
1
1
3
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
1
9
.
2
9
4
9
2
8
6
.
[
1
5
]
S
.
K
a
j
i
h
a
r
a
,
S
.
M
u
r
a
k
a
mi
,
J.
K
.
T
a
n
,
H
.
K
i
m,
a
n
d
T
.
A
o
k
i
,
“
I
d
e
n
t
i
f
y
r
h
e
u
mat
o
i
d
a
r
t
h
r
i
t
i
s
a
n
d
o
st
e
o
p
o
r
o
si
s
f
r
o
m
p
h
a
l
a
n
g
e
C
R
i
m
a
g
e
s
b
a
se
d
o
n
i
m
a
g
e
r
e
g
i
st
r
a
t
i
o
n
a
n
d
A
N
N
,
”
I
C
I
C
Ex
p
r
e
ss
L
e
t
t
e
rs.
,
v
o
l
.
1
0
,
n
o
.
1
0
,
p
p
.
2
4
3
5
–
2
4
4
0
,
2
0
1
6
,
d
o
i
:
1
0
.
2
4
5
0
7
/
i
c
i
c
e
l
.
1
0
.
1
0
.
2
4
3
5
.
[
1
6
]
K
.
H
a
t
a
n
o
,
S
.
M
u
r
a
k
a
mi
,
H
.
L
u
,
J
.
K
.
T
a
n
,
H
.
K
i
m,
a
n
d
T
.
A
o
k
i
,
“
C
l
a
ssi
f
i
c
a
t
i
o
n
o
f
o
s
t
e
o
p
o
r
o
si
s
f
r
o
m
p
h
a
l
a
n
g
e
s C
R
i
m
a
g
e
s
b
a
se
d
o
n
D
C
N
N
,
”
i
n
2
0
1
7
1
7
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
C
o
n
t
ro
l
,
A
u
t
o
m
a
t
i
o
n
a
n
d
S
y
st
e
m
s
(
I
C
C
A
S
)
,
I
EEE,
2
0
1
7
,
p
p
.
1
5
9
3
–
1
5
9
6
,
d
o
i
:
1
0
.
2
3
9
1
9
/
I
C
C
A
S
.
2
0
1
7
.
8
2
0
4
2
4
1
.
[
1
7
]
S
.
M
.
N
.
F
a
t
h
i
ma,
R
.
T
a
mi
l
se
l
v
i
,
M
.
P
.
B
e
h
a
m,
a
n
d
D
.
S
a
b
a
r
i
n
a
t
h
a
n
,
“
D
i
a
g
n
o
si
s o
f
o
st
e
o
p
o
r
o
si
s
u
s
i
n
g
mo
d
i
f
i
e
d
U
-
n
e
t
a
r
c
h
i
t
e
c
t
u
r
e
w
i
t
h
a
t
t
e
n
t
i
o
n
u
n
i
t
i
n
D
EX
A
a
n
d
X
-
r
a
y
i
mag
e
s,”
J
o
u
rn
a
l
o
f
X
-
R
a
y
S
c
i
e
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
:
C
l
i
n
i
c
a
l
Ap
p
l
i
c
a
t
i
o
n
s
o
f
D
i
a
g
n
o
s
i
s
a
n
d
T
h
e
r
a
p
e
u
t
i
c
s
,
v
o
l
.
2
8
,
n
o
.
5
,
p
p
.
9
5
3
–
9
7
3
,
S
e
p
.
2
0
2
0
,
d
o
i
:
1
0
.
3
2
3
3
/
X
S
T
-
2
0
0
6
9
2
.
[
1
8
]
B
.
Z
h
a
n
g
e
t
a
l
.
,
“
D
e
e
p
l
e
a
r
n
i
n
g
o
f
l
u
m
b
a
r
sp
i
n
e
X
-
r
a
y
f
o
r
o
st
e
o
p
e
n
i
a
a
n
d
o
st
e
o
p
o
r
o
si
s
scre
e
n
i
n
g
:
A
mu
l
t
i
c
e
n
t
e
r
r
e
t
r
o
sp
e
c
t
i
v
e
c
o
h
o
r
t
st
u
d
y
,
”
B
o
n
e
,
v
o
l
.
1
4
0
,
N
o
v
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
b
o
n
e
.
2
0
2
0
.
1
1
5
5
6
1
.
[
1
9
]
N
.
T
e
c
l
e
,
J.
T
e
i
t
e
l
,
M
.
R
.
M
o
r
r
i
s,
N
.
S
a
n
i
,
D
.
M
i
t
t
e
n
,
a
n
d
W
.
C
.
H
a
mm
e
r
t
,
“
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
f
o
r
se
c
o
n
d
me
t
a
c
a
r
p
a
l
r
a
d
i
o
g
r
a
p
h
i
c
o
st
e
o
p
o
r
o
si
s
scre
e
n
i
n
g
,
”
T
h
e
J
o
u
rn
a
l
o
f
H
a
n
d
S
u
r
g
e
r
y
,
v
o
l
.
4
5
,
n
o
.
3
,
p
p
.
1
7
5
–
1
8
1
,
M
a
r
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
h
sa
.
2
0
1
9
.
1
1
.
0
1
9
.
[
2
0
]
C.
-
S
.
H
o
e
t
a
l
.
,
“
A
p
p
l
i
c
a
t
i
o
n
o
f
d
e
e
p
l
e
a
r
n
i
n
g
n
e
u
r
a
l
n
e
t
w
o
r
k
i
n
p
r
e
d
i
c
t
i
n
g
b
o
n
e
mi
n
e
r
a
l
d
e
n
s
i
t
y
f
r
o
m
p
l
a
i
n
X
-
r
a
y
r
a
d
i
o
g
r
a
p
h
y
,
”
Arc
h
i
v
e
s
o
f
O
st
e
o
p
o
r
o
s
i
s
,
v
o
l
.
1
6
,
n
o
.
1
,
D
e
c
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
6
5
7
-
021
-
0
0
9
8
5
-
8.
[
2
1
]
S
t
e
v
e
P
y
t
h
o
n
,
“
O
st
e
o
p
o
r
o
si
s
K
n
e
e
X
r
a
y
D
a
t
a
se
t
,
”
2
0
2
1
.
h
t
t
p
s:
/
/
w
w
w
.
k
a
g
g
l
e
.
c
o
m/
d
a
t
a
se
t
s/
s
t
e
v
e
p
y
t
h
o
n
/
o
st
e
o
p
o
r
o
si
s
-
k
n
e
e
-
x
r
a
y
-
d
a
t
a
se
t
[
2
2
]
A
.
K
r
i
z
h
e
v
sk
y
,
I
.
S
u
t
sk
e
v
e
r
,
a
n
d
G
.
E.
H
i
n
t
o
n
,
“
I
mag
e
N
e
t
c
l
a
ssi
f
i
c
a
t
i
o
n
w
i
t
h
d
e
e
p
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,”
A
d
v
a
n
c
e
s
i
n
n
e
u
ra
l
i
n
f
o
rm
a
t
i
o
n
p
r
o
c
e
ss
i
n
g
s
y
st
e
m
s
,
p
p
.
1
–
9
,
2
0
1
2
.
[
2
3
]
H
.
C
h
u
n
g
,
S
.
J.
L
e
e
,
a
n
d
J.
G
.
P
a
r
k
,
“
D
e
e
p
n
e
u
r
a
l
n
e
t
w
o
r
k
u
si
n
g
t
r
a
i
n
a
b
l
e
a
c
t
i
v
a
t
i
o
n
f
u
n
c
t
i
o
n
s,
”
i
n
2
0
1
6
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
i
n
t
C
o
n
f
e
re
n
c
e
o
n
N
e
u
r
a
l
N
e
t
w
o
r
k
s (I
J
C
N
N
)
,
Ju
l
.
2
0
1
6
,
p
p
.
3
4
8
–
3
5
2
.
d
o
i
:
1
0
.
1
1
0
9
/
I
JC
N
N
.
2
0
1
6
.
7
7
2
7
2
1
9
.
[
2
4
]
A
.
W
.
S
u
g
i
y
a
r
t
o
,
A
.
M
.
A
b
a
d
i
,
a
n
d
S
.
S
u
mar
n
a
,
“
C
l
a
ssi
f
i
c
a
t
i
o
n
o
f
h
e
a
r
t
d
i
se
a
se
b
a
se
d
o
n
P
C
G
si
g
n
a
l
u
si
n
g
C
N
N
,
”
T
ELKO
MN
I
K
A
(
T
e
l
e
c
o
m
m
u
n
i
c
a
t
i
o
n
C
o
m
p
u
t
i
n
g
El
e
c
t
r
o
n
i
c
s
a
n
d
C
o
n
t
ro
l
)
,
v
o
l
.
1
9
,
n
o
.
5
,
p
p
.
1
6
9
7
–
1
7
0
6
,
O
c
t
.
2
0
2
1
,
d
o
i
:
1
0
.
1
2
9
2
8
/
t
e
l
k
o
mn
i
k
a
.
v
1
9
i
5
.
2
0
4
8
6
.
[
2
5
]
Y
.
L
e
c
u
n
,
L
.
B
o
t
t
o
u
,
Y
.
B
e
n
g
i
o
,
a
n
d
P
.
H
a
f
f
n
e
r
,
“
G
r
a
d
i
e
n
t
-
b
a
se
d
l
e
a
r
n
i
n
g
a
p
p
l
i
e
d
t
o
d
o
c
u
me
n
t
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
,
v
o
l
.
8
6
,
n
o
.
1
1
,
p
p
.
2
2
7
8
–
2
3
2
4
,
1
9
9
8
,
d
o
i
:
1
0
.
1
1
0
9
/
5
.
7
2
6
7
9
1
.
[
2
6
]
K
.
S
u
z
u
k
i
,
“
O
v
e
r
v
i
e
w
o
f
d
e
e
p
l
e
a
r
n
i
n
g
i
n
me
d
i
c
a
l
i
m
a
g
i
n
g
,
”
Ra
d
i
o
l
o
g
i
c
a
l
Ph
y
si
c
s
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
1
0
,
n
o
.
3
,
p
p
.
2
5
7
–
2
7
3
,
S
e
p
.
2
0
1
7
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
2
1
9
4
-
017
-
0
4
0
6
-
5.
[
2
7
]
S
.
Jai
n
a
n
d
A
.
O
.
S
a
l
a
u
,
“
A
n
i
mag
e
f
e
a
t
u
r
e
se
l
e
c
t
i
o
n
a
p
p
r
o
a
c
h
f
o
r
d
i
me
n
si
o
n
a
l
i
t
y
r
e
d
u
c
t
i
o
n
b
a
se
d
o
n
k
N
N
a
n
d
S
V
M
f
o
r
A
k
T
p
r
o
t
e
i
n
s
,
”
C
o
g
e
n
t
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
6
,
n
o
.
1
,
Ja
n
.
2
0
1
9
,
d
o
i
:
1
0
.
1
0
8
0
/
2
3
3
1
1
9
1
6
.
2
0
1
9
.
1
5
9
9
5
3
7
.
[
2
8
]
M
.
A
.
A
.
A
l
o
b
a
i
d
y
,
Z
.
M
.
Y
o
si
f
,
a
n
d
A
.
M
.
A
l
k
a
b
a
b
c
h
i
,
“
A
g
e
-
d
e
p
e
n
d
e
n
t
p
a
l
m
p
r
i
n
t
r
e
c
o
g
n
i
t
i
o
n
u
s
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
,
”
Re
v
u
e
d
'
I
n
t
e
l
l
i
g
e
n
c
e
Ar
t
i
f
i
c
i
e
l
l
e
.
,
v
o
l
.
3
7
,
n
o
.
3
,
p
p
.
7
9
5
-
800
,
2
0
2
3
.
[
2
9
]
K
.
G
.
K
i
m,
“
B
o
o
k
r
e
v
i
e
w
:
D
e
e
p
l
e
a
r
n
i
n
g
,
”
H
e
a
l
t
h
c
a
re
I
n
f
o
rm
a
t
i
c
s
Re
se
a
rc
h
,
v
o
l
.
2
2
,
n
o
.
4
,
p
p
.
3
5
1
–
3
5
4
,
2
0
1
6
,
d
o
i
:
1
0
.
4
2
5
8
/
h
i
r
.
2
0
1
6
.
2
2
.
4
.
3
5
1
.
[
3
0
]
M
.
J.
M
o
h
a
m
me
d
,
E.
A
.
M
o
h
a
mm
e
d
,
a
n
d
M
.
S
.
Jar
j
e
e
s,
“
R
e
c
o
g
n
i
t
i
o
n
o
f
mu
l
t
i
f
o
n
t
E
n
g
l
i
sh
e
l
e
c
t
r
o
n
i
c
p
r
e
s
c
r
i
b
i
n
g
b
a
se
d
o
n
c
o
n
v
o
l
u
t
i
o
n
n
e
u
r
a
l
n
e
t
w
o
r
k
a
l
g
o
r
i
t
h
m,
”
B
i
o
-
A
l
g
o
r
i
t
h
m
s
a
n
d
M
e
d
-
S
y
s
t
e
m
s
,
v
o
l
.
1
6
,
n
o
.
3
,
S
e
p
.
2
0
2
0
,
d
o
i
:
1
0
.
1
5
1
5
/
b
a
ms
-
2
0
2
0
-
0
0
2
1
.
[
3
1
]
I
.
P
a
c
a
l
,
D
.
K
a
r
a
b
o
g
a
,
A
.
B
a
s
t
u
r
k
,
B
.
A
k
a
y
,
a
n
d
U
.
N
a
l
b
a
n
t
o
g
l
u
,
“
A
c
o
m
p
r
e
h
e
n
si
v
e
r
e
v
i
e
w
o
f
d
e
e
p
l
e
a
r
n
i
n
g
i
n
c
o
l
o
n
c
a
n
c
e
r
,
”
C
o
m
p
u
t
e
rs
i
n
B
i
o
l
o
g
y
a
n
d
Me
d
i
c
i
n
e
,
v
o
l
.
1
2
6
,
N
o
v
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
mp
b
i
o
me
d
.
2
0
2
0
.
1
0
4
0
0
3
.
[
3
2
]
A
.
Z
a
f
a
r
e
t
a
l
.
,
“
A
c
o
mp
a
r
i
so
n
o
f
p
o
o
l
i
n
g
me
t
h
o
d
s
f
o
r
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,”
A
p
p
l
i
e
d
S
c
i
e
n
c
e
s
,
v
o
l
.
1
2
,
n
o
.
1
7
,
A
u
g
.
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
2
1
7
8
6
4
3
.
[
3
3
]
L
.
O
.
L
y
r
a
,
A
.
E.
F
a
b
r
i
s,
a
n
d
J
.
B
.
F
l
o
r
i
n
d
o
,
“
A
mu
l
t
i
l
e
v
e
l
p
o
o
l
i
n
g
sch
e
me
i
n
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
f
o
r
t
e
x
t
u
r
e
i
mag
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
A
co
n
vo
l
u
tio
n
n
e
u
r
a
l n
etw
o
r
k
mo
d
el
fo
r
kn
ee
o
s
teo
p
o
r
o
s
is
cla
s
s
ifica
tio
n
…
(
Oma
r
K
h
a
lid
M.
A
li
)
1019
r
e
c
o
g
n
i
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
5
2
,
p
.
1
1
1
2
8
2
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
so
c
.
2
0
2
4
.
1
1
1
2
8
2
.
[
3
4
]
E.
A
.
M
o
h
a
me
d
,
T
.
G
a
b
e
r
,
O
.
K
a
r
a
m,
a
n
d
E.
A
.
R
a
s
h
e
d
,
“
A
n
o
v
e
l
C
N
N
p
o
o
l
i
n
g
l
a
y
e
r
f
o
r
b
r
e
a
st
c
a
n
c
e
r
s
e
g
me
n
t
a
t
i
o
n
a
n
d
c
l
a
ssi
f
i
c
a
t
i
o
n
f
r
o
m t
h
e
r
mo
g
r
a
ms,”
PL
O
S
O
N
E
,
v
o
l
.
1
7
,
n
o
.
1
0
,
O
c
t
.
2
0
2
2
,
d
o
i
:
1
0
.
1
3
7
1
/
j
o
u
r
n
a
l
.
p
o
n
e
.
0
2
7
6
5
2
3
.
[
3
5
]
M
.
S
.
B
a
d
a
r
,
A
g
u
i
d
e
t
o
a
p
p
l
i
e
d
m
a
c
h
i
n
e
l
e
a
rn
i
n
g
f
o
r
b
i
o
l
o
g
i
st
s
.
C
h
a
m:
S
p
r
i
n
g
e
r
I
n
t
e
r
n
a
t
i
o
n
a
l
P
u
b
l
i
s
h
i
n
g
,
2
0
2
3
.
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
0
3
1
-
2
2
2
0
6
-
1.
[
3
6
]
T
.
A
.
K
a
l
a
y
c
ı
a
n
d
U
.
A
san
,
“
I
mp
r
o
v
i
n
g
c
l
a
ssi
f
i
c
a
t
i
o
n
p
e
r
f
o
r
man
c
e
o
f
f
u
l
l
y
c
o
n
n
e
c
t
e
d
l
a
y
e
r
s
b
y
f
u
z
z
y
c
l
u
st
e
r
i
n
g
i
n
t
r
a
n
sf
o
r
me
d
f
e
a
t
u
r
e
sp
a
c
e
,
”
S
y
m
m
e
t
ry
,
v
o
l
.
1
4
,
n
o
.
4
,
M
a
r
.
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
sy
m1
4
0
4
0
6
5
8
.
[
3
7
]
R
.
S
u
,
T
.
L
i
u
,
C
.
S
u
n
,
Q
.
Ji
n
,
R
.
Je
n
n
a
n
e
,
a
n
d
L
.
W
e
i
,
“
F
u
si
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
f
e
a
t
u
r
e
s
w
i
t
h
h
a
n
d
-
c
r
a
f
t
e
d
f
e
a
t
u
r
e
s
f
o
r
o
st
e
o
p
o
r
o
si
s d
i
a
g
n
o
se
s,”
N
e
u
ro
c
o
m
p
u
t
i
n
g
,
v
o
l
.
3
8
5
,
p
p
.
3
0
0
–
3
0
9
,
A
p
r
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
n
e
u
c
o
m.2
0
1
9
.
1
2
.
0
8
3
.
[
3
8
]
U
.
B
.
A
b
u
b
a
k
a
r
,
M
.
M
.
B
o
u
k
a
r
,
a
n
d
S
.
A
d
e
sh
i
n
a
,
“
C
o
mp
a
r
i
so
n
o
f
T
r
a
n
sf
e
r
L
e
a
r
n
i
n
g
M
o
d
e
l
A
c
c
u
r
a
c
y
f
o
r
O
st
e
o
p
o
r
o
si
s
C
l
a
ssi
f
i
c
a
t
i
o
n
o
n
K
n
e
e
R
a
d
i
o
g
r
a
p
h
,
”
i
n
2
0
2
2
2
n
d
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
C
o
m
p
u
t
i
n
g
a
n
d
M
a
c
h
i
n
e
I
n
t
e
l
l
i
g
e
n
c
e
(
I
C
MI)
,
A
p
r
.
2
0
2
2
,
p
p
.
1
–
5
.
d
o
i
:
1
0
.
1
1
0
9
/
I
C
M
I
5
5
2
9
6
.
2
0
2
2
.
9
8
7
3
7
3
1
.
[
3
9
]
I
.
M
.
W
a
n
i
a
n
d
S
.
A
r
o
r
a
,
“
O
st
e
o
p
o
r
o
si
s
d
i
a
g
n
o
si
s
i
n
k
n
e
e
X
-
r
a
y
s
b
y
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
b
a
se
d
o
n
c
o
n
v
o
l
u
t
i
o
n
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
Mu
l
t
i
m
e
d
i
a
T
o
o
l
s
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
8
2
,
n
o
.
9
,
p
p
.
1
4
1
9
3
–
1
4
2
1
7
,
A
p
r
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
0
4
2
-
0
2
2
-
1
3
9
1
1
-
y.
[
4
0
]
M
.
S
h
e
n
,
“
U
t
i
l
i
z
i
n
g
d
e
e
p
l
e
a
r
n
i
n
g
f
o
r
o
st
e
o
p
o
r
o
si
s
d
i
a
g
n
o
si
s
t
h
r
o
u
g
h
k
n
e
e
X
-
r
a
y
a
n
a
l
y
si
s,”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
2
0
2
4
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
(
I
C
AI
C
2
0
2
4
)
,
2
0
2
4
,
p
p
.
5
5
3
–
5
6
0
.
d
o
i
:
1
0
.
2
9
9
1
/
9
7
8
-
94
-
6
4
6
3
-
5
1
2
-
6
_
5
8
.
[
4
1
]
S
.
K
a
u
r
,
S
.
K
a
mb
o
j
,
M
.
K
u
mar,
A
.
D
a
g
u
r
,
a
n
d
D
.
K
.
S
h
u
k
l
a
,
C
o
m
p
u
t
a
t
i
o
n
a
l
Me
t
h
o
d
s
i
n
S
c
i
e
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
.
C
R
C
P
r
e
ss,
2
0
2
4
.
d
o
i
:
1
0
.
1
2
0
1
/
9
7
8
1
0
0
3
5
0
1
2
4
4
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
O
m
a
r
K
h
a
li
d
M
.
Ali
re
c
e
i
v
e
d
th
e
B.
En
g
.
d
e
g
re
e
in
T
e
c
h
n
ica
l
Co
m
p
u
ter
En
g
in
e
e
rin
g
f
ro
m
th
e
No
rth
e
rn
T
e
c
h
n
ica
l
Un
iv
e
rsity
,
M
o
su
l,
Ira
q
,
in
2
0
0
6
,
a
n
d
th
e
M
a
ste
r
’
s
d
e
g
re
e
in
T
e
c
h
n
ica
l
Co
m
p
u
ter E
n
g
in
e
e
rin
g
f
ro
m
th
e
sa
m
e
u
n
iv
e
rsity
in
2
0
2
0
,
a
n
d
n
o
w
h
e
is
a
P
h
.
D.
st
u
d
e
n
t
a
t
Un
iv
e
rsity
S
a
i
n
s
M
a
lay
sia
(USM
),
P
e
n
a
n
g
,
M
a
la
y
sia
.
He
is
c
u
rre
n
tl
y
a
n
a
ss
istan
t
lec
tu
re
r.
He
w
o
rk
s
a
t
th
e
Co
n
stru
c
ti
o
n
a
n
d
P
ro
jec
t
De
p
a
rt
m
e
n
t
a
t
t
h
e
U
n
iv
e
rsity
o
f
M
o
su
l
,
w
h
e
re
h
e
is
a
lso
a
lec
tu
re
r
in
th
e
M
e
c
h
a
tro
n
ics
De
p
a
rtm
e
n
t,
F
a
c
u
lt
y
o
f
En
g
in
e
e
rin
g
a
t
th
e
Un
iv
e
rsity
o
f
M
o
su
l.
His
c
u
rre
n
t
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
A
I,
Io
T
a
n
d
c
o
m
p
u
ter
n
e
tw
o
rk
s.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
o
m
a
r.
k
h
a
li
d
@u
o
m
o
su
l.
e
d
u
.
iq
.
Ab
e
e
r
K
.
Ib
r
a
h
i
m
re
c
e
iv
e
d
a
B.
En
g
.
d
e
g
re
e
in
C
o
m
p
u
ter
E
n
g
in
e
e
rin
g
f
ro
m
th
e
Un
iv
e
rsit
y
o
f
M
o
su
l,
M
o
su
l
,
Ira
q
,
in
2
0
0
7
,
a
n
d
a
M
a
ste
r
’
s
d
e
g
re
e
i
n
C
o
m
p
u
ter
E
n
g
in
e
e
rin
g
sc
ien
c
e
f
ro
m
th
e
No
rth
e
rn
T
e
c
h
n
i
q
u
e
Un
iv
e
rsity
/Co
m
p
u
ter
T
e
c
h
n
iq
u
e
E
n
g
in
e
e
rin
g
,
Ira
q
,
in
2
0
2
2
.
S
h
e
is
c
u
rre
n
t
ly
a
n
a
ss
ist
a
n
t
lec
tu
re
r
in
th
e
De
p
a
rtm
e
n
t
o
f
En
v
iro
n
m
e
n
tal
En
g
in
e
e
rin
g
,
a
t
th
e
Un
iv
e
rsity
o
f
M
o
su
l.
He
r
c
u
rre
n
t
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
a
rti
f
icia
l
in
telli
g
e
n
c
e
a
n
d
d
e
e
p
lea
rn
in
g
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t:
a
b
e
e
r.
k
h
a
li
l@u
o
m
o
su
l.
e
d
u
.
iq
.
B
il
a
l
R.
Alta
m
e
r
re
c
e
iv
e
d
th
e
B.
En
g
.
d
e
g
re
e
Tec
h
n
ica
l
Co
m
p
u
ter
En
g
in
e
e
rin
g
f
ro
m
th
e
No
rth
e
r
n
T
e
c
h
n
ica
l
Un
i
v
e
rsit
y
,
M
o
su
l,
Ira
q
,
in
2
0
0
7
,
a
n
d
t
h
e
M
a
ste
r
’
s
d
e
g
re
e
i
n
T
e
c
h
n
ica
l
Co
m
p
u
ter
En
g
i
n
e
e
rin
g
f
ro
m
th
e
sa
m
e
u
n
iv
e
rsit
y
in
2
0
2
0
,
a
n
d
n
o
w
h
e
is
a
P
h
.
D
.
stu
d
e
n
t
a
t
Un
iv
e
rsit
y
S
a
in
s
M
a
la
y
sia
(USM
)
,
P
e
n
a
n
g
,
M
a
lay
sia
.
H
e
is
c
u
rre
n
tl
y
a
n
a
ss
istan
t
lec
tu
re
r.
He
w
o
rk
s
a
t
M
o
s
u
l
U
n
i
v
e
r
si
t
y
P
r
e
si
d
e
n
c
y
w
h
e
re
h
e
is
a
lso
a
lec
tu
re
r
in
th
e
M
e
c
h
a
tro
n
ics
De
p
a
rtm
e
n
t,
F
a
c
u
lt
y
o
f
En
g
in
e
e
rin
g
a
t
th
e
U
n
iv
e
rsity
o
f
M
o
su
l.
His
c
u
rre
n
t
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
Io
T
a
n
d
d
e
e
p
lea
rn
i
n
g
a
n
d
m
a
c
h
in
e
lea
rn
in
g
.
He
c
a
n
b
e
c
o
n
tac
te
d
a
t
e
m
a
il
:
b
il
a
l.
a
lt
a
m
e
r@u
o
m
o
su
l.
e
d
u
.
i
q
.
Evaluation Warning : The document was created with Spire.PDF for Python.