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
.
5
,
Octo
b
er
20
25
,
p
p
.
1
304
~1
3
1
3
I
SS
N:
1
6
9
3
-
6
9
3
0
,
DOI
: 1
0
.
1
2
9
2
8
/
T
E
L
KOM
NI
K
A
.
v
23
i
5
.
26387
1304
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
Adv
a
nced pneu
mo
nia
clas
sifica
tion usin
g
t
ra
nsf
er le
a
rning
on
chest
X
-
r
ay
d
a
ta
w
ith
Efficie
ntNe
t
a
nd ResNe
t
G
re
en
Art
her
Sa
n
da
g
,
T
i
m
o
t
hy
J
.
M
ula
lin
da
,
G
lo
ria
A.
M
.
Su
s
a
nto
,
Ste
nly
R.
P
un
g
us
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
mat
i
c
s,
F
a
c
u
l
t
y
o
f
C
o
mp
u
t
e
r
S
c
i
e
n
c
e
,
K
l
a
b
a
t
U
n
i
v
e
r
si
t
y
,
N
o
r
t
h
S
u
l
a
w
e
si
,
I
n
d
o
n
e
si
a
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
n
9
,
2024
R
ev
i
s
ed
J
u
n
26
,
2025
A
cc
ep
ted
A
u
g
1
,
2025
P
n
e
u
m
o
n
ia
is
a
se
rio
u
s
l
u
n
g
i
n
f
e
c
ti
o
n
t
h
a
t
d
e
m
a
n
d
s
a
c
c
u
ra
te
a
n
d
ti
m
e
l
y
d
iag
n
o
sis
t
o
re
d
u
c
e
m
o
rtalit
y
.
T
h
is
st
u
d
y
e
x
p
lo
re
s
th
e
u
se
o
f
d
e
e
p
lea
rn
i
n
g
a
n
d
tra
n
sf
e
r
lea
rn
in
g
f
o
r
c
las
sify
i
n
g
c
h
e
st
X
-
ra
y
i
m
a
g
e
s
in
to
tw
o
c
a
teg
o
ries
:
n
o
rm
a
l
a
n
d
p
n
e
u
m
o
n
ia.
A
to
tal
o
f
5
,
6
3
2
lab
e
led
im
a
g
e
s
w
e
r
e
u
se
d
to
trai
n
a
n
d
e
v
a
lu
a
te
six
p
re
-
train
e
d
c
o
n
v
o
l
u
ti
o
n
a
l
n
e
u
ra
l
n
e
tw
o
rk
(CNN
)
a
rc
h
it
e
c
tu
re
s:
Eff
icie
n
tNe
tB1
,
B3
,
B5
,
B
7
,
Re
sN
e
t5
0
,
a
n
d
Re
sN
e
t1
0
1
.
T
h
e
m
o
d
e
ls
w
e
re
tes
ted
a
c
ro
ss
th
re
e
train
in
g
sc
e
n
a
rio
s
b
y
v
a
r
y
in
g
lea
r
n
in
g
ra
tes
(L
R)
,
b
a
tch
siz
e
s,
a
n
d
e
p
o
c
h
s.
A
m
o
n
g
a
ll
m
o
d
e
ls,
Ef
f
i
c
ien
tNe
tB3
a
c
h
iev
e
d
th
e
h
ig
h
e
st
p
e
rf
o
rm
a
n
c
e
,
w
it
h
a
c
c
u
ra
c
y
o
f
9
9
.
0
4
%
,
p
re
c
isio
n
o
f
9
9
.
7
6
%
,
r
e
c
a
ll
o
f
9
9
.
2
3
%
,
a
n
d
F
1
-
s
c
o
re
o
f
9
9
.
3
4
%
.
T
h
e
se
re
su
lt
s
in
d
i
c
a
te
th
a
t
Eff
icie
n
tNe
tB3
o
ff
e
rs
a
ro
b
u
st
a
n
d
e
ff
icie
n
t
so
l
u
ti
o
n
f
o
r
pn
e
u
m
o
n
ia
d
e
tec
ti
o
n
.
T
h
is
re
se
a
rc
h
c
o
n
tri
b
u
tes
to
th
e
d
e
v
e
lo
p
m
e
n
t
o
f
in
telli
g
e
n
t
d
iag
n
o
stic
t
o
o
ls
i
n
t
h
e
m
e
d
ica
l
f
ield
a
n
d
p
ro
v
i
d
e
s
p
ra
c
ti
c
a
l
g
u
i
d
a
n
c
e
f
o
r
se
lec
ti
n
g
e
ff
e
c
ti
v
e
d
e
e
p
lea
rn
in
g
m
o
d
e
ls i
n
c
li
n
ica
l
im
a
g
in
g
a
p
p
li
c
a
ti
o
n
s.
K
ey
w
o
r
d
s
:
Dee
p
l
ea
r
n
in
g
E
f
f
icien
tNet
R
esNet
T
r
an
s
f
er
l
ea
r
n
in
g
X
-
r
ay
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
:
Gr
ee
n
A
r
th
er
Sa
n
d
ag
Dep
ar
t
m
en
t o
f
I
n
f
o
r
m
atic
s
,
Fa
cu
lt
y
o
f
C
o
m
p
u
ter
Scie
n
ce
,
Kl
ab
at
Un
iv
er
s
it
y
A
r
n
o
ld
Mo
n
o
n
u
tu
,
No
r
th
Su
la
w
e
s
i
95371
,
I
n
d
o
n
esia
E
m
ail:
g
r
ee
n
s
an
d
a
g
@
u
n
k
lab
.
a
c.
id
1.
I
NT
RO
D
UCT
I
O
N
An
illn
e
s
s
t
h
at
af
f
ec
ts
o
n
e
o
r
b
o
th
lu
n
g
s
is
k
n
o
w
n
a
s
p
n
eu
m
o
n
ia,
o
r
in
f
la
m
m
atio
n
o
f
th
e
lu
n
g
s
[
1
]
.
T
h
is
lead
s
to
th
e
alv
eo
li,
o
r
ai
r
s
ac
s
,
w
h
er
e
p
u
s
o
r
f
lu
id
is
r
e
leased
f
r
o
m
th
e
lu
n
g
s
.
P
n
e
u
m
o
n
ia
ca
n
b
e
b
r
o
u
g
h
t
o
n
b
y
f
u
n
g
u
s
,
v
ir
u
s
e
s
,
o
r
b
a
cter
ia.
T
h
e
illn
e
s
s
ca
n
ca
u
s
e
m
ild
to
s
ev
er
e
s
y
m
p
to
m
s
,
s
u
ch
as
f
ev
er
,
ch
ill
s
,
co
u
g
h
in
g
u
p
b
lo
o
d
o
r
m
u
c
u
s
,
an
d
tr
o
u
b
le
b
r
ea
th
in
g
[
2
]
.
P
n
eu
m
o
n
ia,
o
n
e
o
f
th
e
m
o
s
t
p
r
ev
alen
t
ac
u
te
lo
w
er
r
esp
ir
ato
r
y
tr
ac
t
in
f
ec
tio
n
s
,
co
n
ti
n
u
e
s
to
p
o
s
e
a
m
aj
o
r
g
lo
b
al
h
ea
lth
c
h
alle
n
g
e,
w
it
h
a
n
es
ti
m
ated
4
8
9
m
ill
io
n
n
e
w
ca
s
es
r
ep
o
r
ted
w
o
r
ld
w
i
d
e
in
2
0
1
9
[
3
]
.
E
v
er
y
h
o
u
r
,
t
w
o
to
th
r
ee
c
h
ild
r
en
i
n
B
an
g
lad
e
s
h
d
ie
f
r
o
m
p
n
eu
m
o
n
ia,
w
h
ic
h
also
s
ta
n
d
s
as
th
e
p
r
i
m
ar
y
ca
u
s
e
o
f
h
o
s
p
italizatio
n
i
n
th
o
s
e
u
n
d
er
f
iv
e
[
4
]
.
Ho
w
ev
er
,
it
is
also
i
m
p
o
r
tan
t
to
n
o
te
th
a
t
tec
h
n
o
lo
g
y
i
n
d
ia
g
n
o
s
i
n
g
an
d
m
o
n
ito
r
in
g
l
u
n
g
d
is
ea
s
es,
esp
ec
ia
ll
y
i
n
d
ea
lin
g
w
i
th
co
n
d
itio
n
s
li
k
e
p
n
e
u
m
o
n
ia,
p
la
y
s
a
s
i
g
n
i
f
ica
n
t
r
o
le.
L
u
n
g
X
-
r
a
y
s
ar
e
a
m
eth
o
d
u
s
ed
f
o
r
th
e
in
itial
class
i
f
icatio
n
an
d
ev
al
u
atio
n
o
f
p
n
e
u
m
o
n
ia.
T
h
e
p
r
o
c
ess
o
f
d
iag
n
o
s
i
n
g
p
n
eu
m
o
n
ia
in
v
o
l
v
es
u
s
i
n
g
elec
tr
o
m
ag
n
etic
w
a
v
e
r
ad
iatio
n
to
o
b
tain
i
m
a
g
e
r
es
u
lts
o
f
th
e
lu
n
g
s
[
5
]
.
T
h
e
ad
v
an
ce
m
e
n
t
o
f
ar
tific
ial
in
telli
g
e
n
ce
(
A
I
)
,
p
ar
ticu
lar
l
y
in
m
ac
h
i
n
e
lear
n
i
n
g
a
n
d
d
ee
p
lear
n
in
g
,
h
as
g
r
ea
tl
y
i
m
p
r
o
v
ed
t
h
e
clas
s
if
icatio
n
o
f
p
n
eu
m
o
n
ia
in
X
-
r
a
y
i
m
ag
e
s
t
h
r
o
u
g
h
t
h
e
u
s
e
o
f
c
o
n
v
o
l
u
tio
n
al
n
e
u
r
al
n
et
w
o
r
k
s
(
C
N
Ns)
[
6
]
.
Dee
p
l
ea
r
n
in
g
e
n
ab
les
co
m
p
u
ter
s
to
u
n
d
er
s
ta
n
d
co
m
p
le
x
p
atter
n
s
i
n
d
ata
b
y
u
tili
zi
n
g
la
y
er
ed
n
eu
r
al
n
et
w
o
r
k
s
(
m
u
lt
i
la
y
er
n
e
u
r
al
n
et
w
o
r
k
)
[
7
]
.
B
y
em
p
l
o
y
in
g
d
e
e
p
l
ea
r
n
in
g
m
eth
o
d
s
s
u
ch
a
s
C
N
Ns
,
e
f
f
e
ct
iv
en
es
s
in
im
ag
e
c
l
ass
if
i
c
a
t
i
o
n
t
ask
s
is
a
ch
i
ev
e
d
b
e
ca
u
s
e
th
e
n
u
m
b
e
r
o
f
p
a
r
am
et
er
s
a
n
d
c
o
n
n
e
c
t
i
o
n
s
r
e
q
u
i
r
e
d
in
th
e
s
e
n
e
t
w
o
r
k
s
is
m
u
ch
l
o
w
e
r
c
o
m
p
a
r
e
d
t
o
o
t
h
e
r
ty
p
e
s
o
f
n
eu
r
al
n
etw
o
r
k
s
.
T
h
is
ad
v
an
tag
e
s
i
m
p
li
f
ie
s
t
h
e
n
e
u
r
al
n
et
w
o
r
k
C
NN
tr
ai
n
in
g
p
r
o
ce
s
s
co
m
p
ar
ed
to
t
h
e
u
s
e
o
f
o
t
h
er
n
eu
r
al
n
et
w
o
r
k
s
[
8
]
.
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
d
va
n
ce
d
p
n
e
u
mo
n
ia
cl
a
s
s
ific
a
tio
n
u
s
in
g
tr
a
n
s
fer lea
r
n
in
g
o
n
ch
est X
-
r
a
y
d
a
t
a
…
(
Green
A
r
th
er
S
a
n
d
a
g
)
1305
Ho
w
e
v
er
,
p
r
o
d
u
cin
g
a
cc
u
r
ate
C
NN
m
o
d
el
s
o
f
te
n
r
eq
u
ir
es la
r
g
e
d
atasets
a
n
d
s
i
g
n
i
f
ica
n
t c
o
m
p
u
tat
io
n
al
ti
m
e
to
tr
ain
t
h
e
m
.
T
h
er
ef
o
r
e,
tr
an
s
f
e
r
lear
n
in
g
tec
h
n
iq
u
e
s
b
ec
o
m
e
r
elev
an
t
i
n
t
h
e
d
ev
elo
p
m
e
n
t
o
f
C
N
N
m
o
d
els
f
o
r
p
n
eu
m
o
n
ia
cla
s
s
i
f
icatio
n
.
B
y
u
tili
zi
n
g
t
r
an
s
f
er
l
ea
r
n
i
n
g
,
ex
is
t
i
n
g
C
N
N
m
o
d
els
ca
n
b
e
lev
er
ag
ed
to
lear
n
f
ea
t
u
r
es
f
r
o
m
lar
g
e
d
atasets
,
s
u
ch
as
s
h
ap
es
o
r
tex
t
u
r
es,
to
aid
in
th
e
p
r
o
ce
s
s
o
f
p
n
e
u
m
o
n
i
a
class
i
f
icatio
n
a
n
d
d
iag
n
o
s
i
s
[
9
]
.
T
r
an
s
f
er
l
ea
r
n
i
n
g
is
a
tec
h
n
iq
u
e
i
n
m
ac
h
i
n
e
le
ar
n
in
g
w
h
er
e
a
p
r
e
-
tr
ai
n
ed
m
o
d
el
ca
n
b
e
u
s
ed
to
s
o
lv
e
d
if
f
er
en
t
p
r
o
b
lem
s
w
i
th
o
u
t
r
etr
ain
in
g
f
r
o
m
s
cr
atch
[
1
0
]
.
T
h
is
m
o
d
el
lev
er
ag
es
p
r
io
r
k
n
o
w
led
g
e
f
r
o
m
a
lar
g
e
d
ataset
b
u
t
ca
n
al
s
o
b
e
ap
p
lied
to
s
m
al
ler
d
atasets
.
T
r
an
s
f
er
l
ea
r
n
i
n
g
i
n
v
o
l
v
es
ex
tr
ac
tin
g
k
n
o
w
led
g
e
f
r
o
m
m
u
lt
ip
le
s
o
u
r
ce
tas
k
s
a
n
d
ap
p
ly
i
n
g
it
to
a
d
if
f
er
en
t
tar
g
et
tas
k
.
Un
li
k
e
m
u
lt
itas
k
i
n
g
lear
n
in
g
,
w
h
i
ch
co
n
s
id
er
s
b
o
th
th
e
s
o
u
r
ce
an
d
tar
g
et
task
s
s
i
m
u
lta
n
eo
u
s
l
y
,
t
r
an
s
f
er
lear
n
in
g
f
o
cu
s
e
s
s
o
lel
y
o
n
th
e
tar
g
et
tas
k
.
T
h
e
s
y
m
m
etr
y
b
et
w
ee
n
t
h
e
s
o
u
r
ce
an
d
tar
g
et
ta
s
k
s
is
n
o
t
m
a
n
d
ato
r
y
in
tr
a
n
s
f
er
lear
n
i
n
g
[
1
1
]
.
I
n
o
u
r
s
tu
d
y
,
w
e
u
tili
ze
d
gr
ad
ien
t
-
w
eig
h
ted
class
ac
ti
v
ati
o
n
m
ap
p
in
g
(
Gr
ad
-
C
A
M
)
,
a
tech
n
iq
u
e
w
it
h
i
n
C
NNs,
to
g
en
er
ate
cla
s
s
-
s
p
ec
i
f
ic
h
ea
t
m
ap
s
.
T
h
ese
h
ea
t
m
ap
s
ar
e
tailo
r
ed
to
a
s
p
ec
if
ic
i
n
p
u
t
i
m
a
g
e,
lev
er
ag
i
n
g
a
tr
ai
n
ed
C
N
N
m
o
d
el
[
1
2
]
,
[
1
3
]
.
T
h
e
Gr
ad
-
C
AM
tech
n
iq
u
e
is
e
m
p
l
o
y
ed
to
en
h
a
n
ce
p
n
e
u
m
o
n
i
a
d
etec
tio
n
tr
an
s
p
ar
en
c
y
[
1
4
]
.
I
t
h
i
g
h
l
ig
h
ts
r
eg
io
n
s
i
n
t
h
e
in
p
u
t
i
m
a
g
e
w
h
er
e
t
h
e
m
o
d
el
f
o
cu
s
es
d
u
r
in
g
class
i
f
icatio
n
,
in
d
icati
n
g
th
a
t
f
ea
tu
r
e
m
ap
s
in
th
e
f
in
al
co
n
v
o
lu
tio
n
la
y
er
r
etain
s
p
atial
in
f
o
r
m
atio
n
cr
u
cial
f
o
r
ca
p
tu
r
in
g
v
is
u
al
p
atter
n
s
.
T
h
ese
p
atter
n
s
aid
in
d
is
tin
g
u
i
s
h
i
n
g
ass
i
g
n
ed
class
e
s
.
Gr
ad
-
C
AM
u
tili
ze
s
la
y
er
s
an
d
ex
tr
ac
ted
f
ea
t
u
r
es
f
r
o
m
t
h
e
tr
ain
ed
m
o
d
el
to
ac
h
ie
v
e
t
h
is
[
1
2
]
.
I
n
a
s
tu
d
y
co
n
d
u
cted
b
y
C
h
a
et
a
l
.
[
1
5
]
,
th
e
y
ai
m
e
d
to
class
if
y
p
n
eu
m
o
n
ia
in
c
h
est
X
-
r
a
y
i
m
a
g
es
u
s
i
n
g
atten
tio
n
-
b
a
s
ed
tr
an
s
f
er
lea
r
n
in
g
.
R
esear
c
h
er
s
co
m
b
i
n
ed
f
ea
t
u
r
e
v
ec
to
r
s
f
r
o
m
t
h
r
ee
p
r
e
-
tr
ain
ed
m
o
d
els:
R
esNet1
5
2
,
Den
s
eNe
t1
2
1
,
an
d
R
esNet1
8
.
T
h
e
b
est
r
esu
lt
w
as
ac
h
ie
v
ed
w
it
h
s
q
u
e
ez
e
-
an
d
-
ex
c
itatio
n
(
SE
)
,
w
it
h
an
ac
cu
r
ac
y
o
f
9
6
.
6
3
%,
F1
-
s
c
o
r
e
o
f
0
.
9
7
3
,
ar
ea
u
n
d
er
th
e
c
u
r
v
e
(
A
U
C
)
o
f
9
6
.
0
3
%,
p
r
ec
is
io
n
o
f
9
6
.
2
4
%,
an
d
r
ec
all
o
f
9
8
.
4
6
%.
Ma
h
in
et
a
l
.
[
1
6
]
co
n
d
u
cted
r
esear
ch
o
n
th
e
u
s
e
o
f
tr
an
s
f
e
r
lear
n
in
g
f
o
r
th
e
clas
s
if
icatio
n
o
f
C
OVI
D
-
1
9
an
d
p
n
eu
m
o
n
ia
in
c
h
e
s
t
X
-
r
a
y
i
m
a
g
es.
R
esear
c
h
er
s
u
s
ed
f
o
u
r
d
if
f
er
e
n
t
tr
an
s
f
er
lear
n
i
n
g
alg
o
r
ith
m
s
,
in
cl
u
d
i
n
g
Mo
b
ileNetV2
,
VGG1
9
,
I
n
ce
p
tio
n
v
3
,
a
n
d
E
f
f
Ne
t
t
h
r
es
h
o
ld
,
to
tr
ain
p
r
e
-
tr
ain
ed
m
o
d
els
i
n
tr
a
n
s
f
er
lear
n
i
n
g
.
I
n
th
i
s
s
t
u
d
y
,
th
e
h
i
g
h
est
ac
cu
r
ac
y
ac
h
ie
v
ed
w
as
9
8
%
u
s
i
n
g
t
h
e
Mo
b
ileNetV2
al
g
o
r
ith
m
,
f
o
llo
w
ed
b
y
I
n
ce
p
tio
n
v
3
w
i
th
9
6
.
9
2
%,
E
f
f
Net
t
h
r
e
s
h
o
ld
w
it
h
9
4
.
9
5
%,
an
d
VGG1
9
w
it
h
9
2
.
8
2
%.
T
h
e
s
tu
d
y
ai
m
s
to
d
e
v
elo
p
an
d
ev
alu
a
te
a
p
n
e
u
m
o
n
ia
clas
s
i
f
icatio
n
m
o
d
el
u
s
in
g
l
u
n
g
X
-
r
a
y
i
m
a
g
es
b
y
i
n
teg
r
at
in
g
tr
an
s
f
er
lear
n
i
n
g
tec
h
n
iq
u
es
an
d
i
m
p
le
m
e
n
t
in
g
t
h
e
m
o
d
el
in
to
a
w
eb
ap
p
licatio
n
ca
p
ab
le
o
f
class
i
f
y
in
g
in
to
t
w
o
class
e
s
:
p
ne
u
m
o
n
ia
an
d
n
o
r
m
al.
T
h
e
test
ed
m
o
d
els
in
cl
u
d
e
E
f
f
icie
n
tN
et
B
1
,
E
f
f
icie
n
tNet
B
3
,
E
f
f
icie
n
tNet
B
5
,
E
f
f
icie
n
tNet
B
7
[
1
7
]
,
R
esNet5
0
,
an
d
R
e
s
Net1
0
1
[
1
8
]
,
u
s
in
g
a
d
at
aset
f
r
o
m
t
h
e
Gu
a
n
g
z
h
o
u
W
o
m
e
n
an
d
C
h
ild
r
en
’
s
Me
d
ical
C
e
n
ter
o
b
tain
ed
f
r
o
m
Ka
g
g
le
[
1
9
]
.
2.
M
E
T
H
O
D
I
n
th
is
r
esear
c
h
d
esig
n
,
th
e
d
ata
u
s
ed
co
n
s
is
t
s
o
f
th
e
c
h
est
X
-
r
a
y
i
m
a
g
es
(
p
n
e
u
m
o
n
i
a)
d
ataset
o
b
tain
ed
f
r
o
m
Ka
g
g
le
[
1
9
]
.
T
h
e
d
ata
w
ill
b
e
p
r
o
ce
s
s
ed
u
s
i
n
g
v
ar
io
u
s
f
ea
t
u
r
e
ex
tr
ac
tio
n
te
ch
n
iq
u
es
to
co
n
v
er
t
f
ea
t
u
r
es
i
n
to
a
f
o
r
m
at
s
u
itab
l
e
f
o
r
f
u
r
t
h
er
an
a
l
y
s
is
.
B
y
i
n
t
eg
r
atin
g
tr
a
n
s
f
er
lear
n
i
n
g
ar
c
h
itect
u
r
es
s
u
c
h
as
E
f
f
icien
tNetB
1
,
B
3
,
B
5
,
B
7
,
R
esNet5
0
,
an
d
R
esNet1
0
1
,
th
e
m
o
d
el
lear
n
i
n
g
p
r
o
ce
s
s
w
ill
b
e
f
aster
an
d
m
o
r
e
ef
f
icien
t
i
n
cla
s
s
i
f
y
in
g
lu
n
g
X
-
r
a
y
i
m
ag
e
s
i
n
to
t
w
o
cla
s
s
es:
p
n
e
u
m
o
n
ia
a
n
d
n
o
r
m
al
.
T
h
e
m
o
d
els
w
il
l
b
e
ev
alu
a
ted
u
s
i
n
g
a
co
n
f
u
s
io
n
m
atr
i
x
to
d
eter
m
i
n
e
p
er
f
o
r
m
a
n
ce
m
etr
ics,
i
n
clu
d
i
n
g
ac
cu
r
ac
y
,
r
ec
all,
p
r
ec
is
io
n
,
an
d
F1
-
s
co
r
e.
A
co
m
p
ar
ativ
e
an
al
y
s
is
w
i
ll
b
e
co
n
d
u
cted
am
o
n
g
th
e
s
ix
m
o
d
els
to
id
en
ti
f
y
t
h
e
m
o
s
t
o
p
ti
m
a
l
o
n
e
b
ased
o
n
p
e
r
f
o
r
m
a
n
ce
.
T
h
e
s
e
l
e
c
t
e
d
m
o
d
e
l
w
i
l
l
t
h
e
n
b
e
i
m
p
l
em
e
n
t
e
d
i
n
t
o
a
w
e
b
a
p
p
l
i
c
a
t
i
o
n
.
A
f
t
e
r
d
e
p
l
o
y
m
e
n
t
,
a
l
l
f
e
a
t
u
r
e
f
u
n
c
t
i
o
n
s
w
i
l
l
b
e
t
e
s
t
e
d
t
o
a
d
d
r
e
s
s
p
o
t
e
n
t
i
a
l
e
r
r
o
r
s
.
T
h
e
w
e
b
a
p
p
l
i
ca
t
i
o
n
w
i
l
l
al
l
o
w
u
s
e
r
s
t
o
u
p
l
o
a
d
X
-
r
ay
im
ag
es
,
an
d
th
e
i
n
t
eg
r
a
t
e
d
m
o
d
el
w
il
l
c
l
as
s
i
f
y
th
e
im
ag
es
in
t
o
th
e
t
w
o
c
las
s
es
,
d
is
p
l
ay
in
g
th
e
o
u
t
p
u
t
im
ag
e
a
l
o
n
g
w
i
th
p
r
o
b
ab
i
l
i
ty
p
e
r
c
en
t
ag
e
v
alu
e
s
.
T
h
e
en
t
i
r
e
p
r
o
c
e
s
s
f
l
o
w
is
il
lu
s
t
r
a
t
e
d
i
n
F
ig
u
r
e
1
.
Fig
u
r
e
1
.
P
r
o
p
o
s
ed
m
eth
o
d
o
lo
g
y
f
o
r
d
etec
tin
g
p
n
eu
m
o
n
ia
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
.
5
,
Octo
b
e
r
20
25
:
1
3
0
4
-
1
313
1306
2
.
1
.
Da
t
a
co
llect
io
n
W
e
u
tili
ze
d
th
e
c
h
e
s
t
X
-
r
a
y
i
m
ag
e
s
(
p
n
eu
m
o
n
ia)
d
ataset,
co
m
p
r
i
s
in
g
a
to
tal
o
f
5
,
8
5
6
im
a
g
e
s
a
m
p
les.
T
h
is
d
ataset
w
a
s
th
e
n
d
iv
id
e
d
in
to
1
,
5
8
3
im
a
g
es
o
f
n
o
r
m
al
lu
n
g
s
an
d
4
,
2
7
3
im
ag
e
s
o
f
lu
n
g
s
a
f
f
ec
ted
b
y
p
n
eu
m
o
n
ia.
T
h
e
d
iv
i
s
io
n
w
as
d
is
tr
ib
u
ted
in
to
th
r
ee
f
o
ld
er
s
:
d
ata
test
,
d
ata
tr
ain
,
a
n
d
d
ata
v
alid
.
D
ata
te
s
t
co
n
tain
ed
2
3
4
n
o
r
m
al
lu
n
g
i
m
ag
e
s
an
d
3
9
0
p
n
eu
m
o
n
ia
l
u
n
g
i
m
a
g
es,
d
ata
tr
ain
co
n
s
is
t
ed
o
f
1
,
3
4
1
n
o
r
m
al
lu
n
g
i
m
a
g
e
s
an
d
3
,
8
7
5
p
n
eu
m
o
n
ia
lu
n
g
i
m
a
g
es,
w
h
ile
d
ata
v
alid
co
m
p
r
is
ed
8
n
o
r
m
al
lu
n
g
i
m
a
g
e
s
an
d
8
p
n
eu
m
o
n
ia
lu
n
g
i
m
a
g
es.
T
o
ad
d
r
ess
th
i
s
is
s
u
e,
we
ad
j
u
s
ted
th
e
d
ata
te
s
t
b
y
eq
u
aliz
in
g
t
h
e
n
u
m
b
er
o
f
n
o
r
m
al
an
d
p
n
eu
m
o
n
ia
i
m
a
g
es
to
2
0
0
f
o
r
ea
ch
class
.
Deta
ils
o
f
t
h
e
d
ataset
ar
e
in
Fi
g
u
r
e
2
.
Fig
u
r
e
2
.
Deta
ils
o
f
t
h
e
to
tal
i
m
ag
e
2
.
2
.
Da
t
a
p
re
pro
ce
s
s
ing
I
n
th
is
s
ta
g
e,
w
e
w
ill
p
r
ep
ar
e
th
e
ad
j
u
s
ted
im
a
g
e
d
ata
b
ef
o
r
e
u
s
in
g
it
f
o
r
m
o
d
el
tr
ain
in
g
.
T
h
e
in
itial
s
tep
in
v
o
l
v
es
r
ea
d
in
g
th
e
f
o
ld
er
s
tr
u
ct
u
r
e
o
f
th
e
d
ata
co
n
tai
n
in
g
c
h
e
s
t
X
-
r
a
y
lu
n
g
i
m
a
g
es
,
w
h
ic
h
h
av
e
b
ee
n
d
iv
id
ed
in
to
t
w
o
clas
s
es:
n
o
r
m
al
an
d
p
n
eu
m
o
n
ia
.
T
h
e
im
ag
e
d
ata
w
ill
b
e
o
r
g
an
ized
in
to
a
d
ataf
r
a
m
e,
in
d
icati
n
g
t
h
eir
r
esp
ec
tiv
e
cla
s
s
es.
Ne
x
t,
th
e
d
ata
f
r
a
m
e
w
i
ll
b
e
d
iv
id
ed
in
to
th
r
ee
p
ar
ts
:
t
r
ain
i
n
g
d
ata,
test
i
n
g
d
ata,
an
d
v
alid
atio
n
d
ata,
w
it
h
ap
p
r
o
p
r
iate
p
r
o
p
o
r
tio
n
s
f
o
r
ea
ch
p
ar
t.
T
h
e
i
m
a
g
e
s
izes
w
i
l
l
b
e
ad
j
u
s
ted
to
224
×
2
2
4
p
ix
els
an
d
w
ill
b
e
p
r
o
ce
s
s
ed
in
r
ed
,
g
r
ee
n
,
an
d
b
l
u
e
(
R
GB
)
m
o
d
e.
Su
b
s
eq
u
e
n
tl
y
,
a
d
ata
g
en
er
ato
r
w
il
l
b
e
cr
ea
ted
u
s
in
g
t
h
e
I
m
a
g
eDa
taGe
n
er
ato
r
lib
r
ar
y
f
r
o
m
Ker
as
to
lo
ad
th
e
d
ata
g
r
ad
u
all
y
d
u
r
in
g
t
h
e
m
o
d
el
tr
ain
i
n
g
p
r
o
ce
s
s
[
2
0
]
.
A
d
d
itio
n
all
y
,
t
h
e
b
atch
s
ize
f
o
r
th
e
te
s
tin
g
d
ata
w
ill
b
e
d
y
n
a
m
ical
l
y
ad
j
u
s
ted
to
m
a
tch
th
e
av
a
ilab
le
d
ata,
m
a
x
i
m
izin
g
m
e
m
o
r
y
u
s
a
g
e
a
n
d
p
r
o
ce
s
s
in
g
e
f
f
icie
n
c
y
.
Fu
r
t
h
er
m
o
r
e,
t
h
er
e
w
ill
b
e
s
o
m
e
s
a
m
p
les
f
r
o
m
t
h
e
tr
ai
n
in
g
d
ata
alo
n
g
w
it
h
t
h
eir
class
e
s
w
h
ic
h
ar
e
p
lo
tted
as in
Fig
u
r
e
3
.
Fig
u
r
e
3
.
Sa
m
p
le
o
f
tr
ai
n
in
g
d
ata
2
.
3
.
M
o
delin
g
T
h
e
u
p
co
m
in
g
s
tag
e
o
f
t
h
e
d
ee
p
lear
n
in
g
p
r
o
ce
s
s
w
i
ll
u
tili
ze
C
NN
tec
h
n
iq
u
e
s
,
lev
er
a
g
i
n
g
tr
an
s
f
er
lear
n
in
g
f
r
o
m
t
h
e
E
f
f
icie
n
tNe
t
an
d
R
esNe
t
ar
ch
itect
u
r
es.
E
f
f
icie
n
tNet
i
s
d
esig
n
ed
f
o
r
i
m
a
g
e
r
ec
o
g
n
i
tio
n
a
n
d
class
i
f
icatio
n
,
e
m
p
h
asizi
n
g
r
eso
u
r
ce
ef
f
icie
n
c
y
b
y
o
p
ti
m
izi
n
g
t
h
e
n
u
m
b
er
o
f
p
ar
a
m
eter
s
an
d
co
m
p
u
tat
io
n
s
.
I
t
u
s
e
s
s
ca
li
n
g
m
eth
o
d
s
to
ad
ju
s
t
th
e
C
NN
d
i
m
e
n
s
io
n
s
o
f
d
ep
th
,
w
id
th
,
a
n
d
r
eso
lu
tio
n
w
it
h
a
co
m
p
o
u
n
d
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
d
va
n
ce
d
p
n
e
u
mo
n
ia
cl
a
s
s
ific
a
tio
n
u
s
in
g
tr
a
n
s
fer lea
r
n
in
g
o
n
ch
est X
-
r
a
y
d
a
t
a
…
(
Green
A
r
th
er
S
a
n
d
a
g
)
1307
co
ef
f
icie
n
t [
2
1
]
.
R
esNet,
o
r
r
e
s
id
u
al
n
eu
r
al
n
et
w
o
r
k
(
R
NN)
,
ad
d
r
ess
es th
e
v
a
n
is
h
i
n
g
g
r
ad
ie
n
t p
r
o
b
le
m
in
d
ee
p
n
et
w
o
r
k
s
b
y
in
co
r
p
o
r
atin
g
s
k
ip
co
n
n
ec
tio
n
s
,
en
ab
li
n
g
m
o
r
e
ef
f
ec
ti
v
e
f
ea
t
u
r
e
lear
n
i
n
g
an
d
p
r
ev
en
ti
n
g
p
er
f
o
r
m
a
n
ce
d
eg
r
ad
atio
n
i
n
v
er
y
d
ee
p
n
et
w
o
r
k
s
[
2
2
]
.
B
o
th
ar
ch
itectu
r
e
s
w
ill
b
e
ad
j
u
s
te
d
:
t
h
e
co
n
v
o
lu
tio
n
la
y
er
an
d
m
a
x
p
o
o
lin
g
w
ill b
e
r
etain
ed
,
w
h
i
le
t
h
e
f
latte
n
,
f
u
ll
y
co
n
n
ec
ted
,
an
d
d
r
o
p
o
u
t la
y
e
r
s
w
i
ll
b
e
m
o
d
if
ied
to
p
r
o
d
u
ce
a
s
o
f
t
m
ax
o
u
tp
u
t
with
2
class
e
s
:
p
n
e
u
m
o
n
ia
a
n
d
n
o
r
m
al.
T
ab
le
1
p
r
esen
ts
th
e
p
ar
a
m
e
ter
s
ettin
g
s
u
s
ed
in
ea
ch
o
f
th
e
th
r
ee
ex
p
er
i
m
en
tal
s
ce
n
a
r
io
s
.
E
ac
h
s
ce
n
ar
io
in
v
o
l
v
ed
tr
ain
i
n
g
m
o
d
els
w
i
th
d
i
f
f
er
e
n
t
co
n
f
i
g
u
r
ati
o
n
s
o
f
ep
o
ch
co
u
n
t,
lear
n
i
n
g
r
ate
(
L
R
)
,
an
d
b
atch
s
ize
w
h
ile
k
ee
p
in
g
th
e
lo
s
s
f
u
n
ctio
n
(
ca
teg
o
r
ical)
an
d
o
p
tim
izer
t
y
p
es
(
A
d
a
M
ax
,
s
to
c
h
a
s
tic
g
r
ad
ien
t
d
esce
n
t
(
SGD
)
,
an
d
R
MSp
r
o
p
)
co
n
s
is
ten
t
ac
r
o
s
s
th
e
s
ce
n
ar
io
s
.
T
h
ese
v
ar
iatio
n
s
w
er
e
d
esig
n
e
d
to
ev
alu
ate
th
e
p
er
f
o
r
m
a
n
ce
i
m
p
ac
t
o
f
tr
ai
n
i
n
g
d
u
r
atio
n
a
n
d
h
y
p
er
p
ar
a
m
eter
ad
j
u
s
t
m
en
ts
ac
r
o
s
s
m
u
lt
ip
le
d
ee
p
lear
n
in
g
ar
ch
itect
u
r
es
in
cl
u
d
in
g
E
f
f
ic
ien
tNetB
1
,
E
f
f
ic
ien
t
NetB
3
,
E
f
f
icien
tNetB
5
,
E
f
f
icie
n
tNet
B
7
,
R
esNet5
0
,
an
d
R
esNet1
0
1
.
T
ab
le
1
.
P
ar
am
eter
s
o
f
ea
c
h
s
c
en
ar
io
S
c
e
n
a
r
i
o
O
p
t
i
mi
z
e
r
Ep
o
c
h
LR
L
o
ss
f
u
n
c
t
i
o
n
B
a
t
c
h
s
i
z
e
1
A
d
a
M
a
x
,
S
G
D
,
a
n
d
R
M
S
p
r
o
p
20
0
.
0
0
1
C
a
t
e
g
o
r
i
c
a
l
16
2
A
d
a
M
a
x
,
S
G
D
,
a
n
d
R
M
S
p
r
o
p
30
0
.
0
0
1
C
a
t
e
g
o
r
i
c
a
l
20
3
A
d
a
M
a
x
,
S
G
D
,
a
n
d
R
M
S
p
r
o
p
30
0
.
0
1
C
a
t
e
g
o
r
i
c
a
l
45
I
n
th
e
n
e
x
t
s
tep
,
w
e
co
n
d
u
cted
m
o
d
elin
g
ex
p
er
i
m
en
t
s
u
s
i
n
g
E
f
f
icie
n
tNetB
1
,
E
f
f
ici
en
tNetB
3
,
E
f
f
icien
tNetB
5
,
E
f
f
icien
tNet
B
7
,
R
esNet5
0
,
an
d
R
es
Net1
0
1
.
T
h
e
m
o
d
el
cr
ea
tio
n
p
r
o
ce
s
s
w
as
d
i
v
id
ed
in
to
th
r
ee
s
ce
n
ar
io
s
,
ea
ch
w
i
th
v
a
r
iatio
n
s
in
o
p
ti
m
izer
,
ep
o
ch
s
,
LR
,
lo
s
s
f
u
n
ctio
n
,
an
d
b
atc
h
s
ize.
I
n
th
e
f
ir
s
t
s
ce
n
ar
io
,
w
e
u
s
ed
A
d
a
M
a
x
,
S
GD,
an
d
R
MSP
r
o
p
as
o
p
ti
m
i
ze
r
s
,
w
ith
2
0
ep
o
ch
s
,
L
R
0
.
0
0
1
,
c
ateg
o
r
ical
lo
s
s
f
u
n
ctio
n
,
an
d
a
b
atch
s
ize
o
f
1
6
.
T
h
e
s
ec
o
n
d
s
ce
n
ar
io
als
o
em
p
lo
y
ed
A
d
a
M
a
x
,
SGD,
an
d
R
MSP
r
o
p
as
o
p
tim
izer
s
,
w
it
h
3
0
ep
o
ch
s
,
L
R
0
.
0
0
1
,
c
ateg
o
r
ical
lo
s
s
f
u
n
c
tio
n
,
an
d
a
b
atch
s
ize
o
f
2
0
.
T
h
e
th
ir
d
s
ce
n
ar
io
u
tili
ze
d
A
d
a
M
a
x
,
SGD,
a
n
d
R
MSP
r
o
p
as
o
p
tim
izer
s
,
w
it
h
3
0
ep
o
ch
s
,
L
R
0
.
0
1
,
c
ateg
o
r
ical
lo
s
s
f
u
n
ctio
n
,
an
d
a
b
atch
s
ize
o
f
4
5
.
2
.
3
.
1
.
E
f
f
icient
Net
T
h
e
E
f
f
ic
ien
t
Net
al
g
o
r
ith
m
w
a
s
i
n
itial
l
y
p
r
esen
ted
b
y
T
an
a
n
d
L
e
[
2
2
]
,
w
h
ic
h
p
r
o
v
id
es
a
n
o
v
e
l
ap
p
r
o
ac
h
to
s
ca
lin
g
n
e
u
r
al
n
et
w
o
r
k
m
o
d
el
s
b
y
i
m
p
r
o
v
in
g
d
ep
th
,
w
id
t
h
,
an
d
p
r
ec
is
io
n
.
I
t
is
a
C
NN
d
esig
n
an
d
s
ca
lin
g
m
et
h
o
d
th
at
u
n
i
f
o
r
m
l
y
in
cr
ea
s
e
s
th
e
d
ep
th
,
b
r
ea
d
th
,
an
d
r
e
s
o
lu
tio
n
d
i
m
e
n
s
io
n
s
b
y
u
s
i
n
g
a
co
m
p
o
u
n
d
ed
co
ef
f
icie
n
t.
E
f
f
i
cien
tNet
in
tr
o
d
u
ce
s
a
n
o
v
el
ap
p
r
o
ac
h
to
s
ca
lin
g
m
o
d
els
b
y
u
s
in
g
a
co
ef
f
icie
n
t
th
at
s
i
m
u
lta
n
eo
u
s
l
y
i
n
cr
ea
s
e
s
th
e
n
et
w
o
r
k
’
s
d
ep
th
,
w
id
t
h
,
an
d
r
eso
l
u
tio
n
.
Un
l
ik
e
c
o
n
v
e
n
tio
n
al
s
ca
li
n
g
m
et
h
o
d
s
,
w
h
ic
h
o
f
te
n
m
o
d
if
y
o
n
l
y
o
n
e
o
r
t
w
o
d
i
m
e
n
s
io
n
s
,
E
f
f
icie
n
tNe
t
en
s
u
r
es
t
h
at
all
d
im
e
n
s
io
n
s
ar
e
p
r
o
p
o
r
tio
n
all
y
e
n
h
a
n
ce
d
.
T
h
is
ap
p
r
o
ac
h
allo
w
s
t
h
e
m
o
d
el
to
ac
h
ie
v
e
h
ig
h
er
p
er
f
o
r
m
an
ce
w
it
h
b
etter
co
m
p
u
tatio
n
al
ef
f
icie
n
c
y
[
2
1
]
.
2
.
3
.
2
.
ResNet
T
h
e
R
esNet
ar
c
h
itect
u
r
e
in
tr
o
d
u
ce
s
s
k
ip
(
r
esid
u
a
l)
co
n
n
ec
ti
o
n
s
w
h
ic
h
f
ac
ilit
ate
t
h
e
f
lo
w
o
f
g
r
ad
ien
ts
th
r
o
u
g
h
alter
n
a
tiv
e
p
ath
s
,
s
o
lv
in
g
t
h
e
p
r
o
b
lem
o
f
v
a
n
is
h
i
n
g
g
r
ad
ien
ts
i
n
d
ee
p
n
eu
r
al
n
et
wo
r
k
s
.
W
ith
r
esid
u
al
b
lo
ck
s
,
tr
ain
i
n
g
d
ee
p
n
et
w
o
r
k
s
b
ec
o
m
e
s
m
o
r
e
ef
f
icie
n
t.
R
es
Net
also
o
f
f
er
s
f
le
x
ib
ilit
y
i
n
th
e
n
u
m
b
er
o
f
la
y
er
s
,
lik
e
R
es
Net
-
1
8
co
n
s
i
s
ti
n
g
o
f
1
8
l
ay
er
s
,
R
esNe
t
-
3
4
w
i
t
h
3
4
lay
er
s
,
an
d
R
esNet
-
5
0
w
i
th
5
0
lay
er
s
.
Nev
er
th
e
less
,
a
s
th
e
n
u
m
b
er
o
f
la
y
er
s
in
cr
ea
s
e
s
,
it lea
d
s
to
a
h
ig
h
er
u
s
a
g
e
o
f
p
ar
a
m
eter
s
[
2
3
]
.
2
.
4
.
M
o
del
i
nte
rpre
t
a
t
io
n
Nex
t,
m
o
d
el
i
n
ter
p
r
etatio
n
w
i
l
l
b
e
ap
p
lied
to
th
e
n
o
r
m
al
an
d
p
n
eu
m
o
n
ia
i
m
a
g
e
d
ata
to
h
i
g
h
li
g
h
t
t
h
e
p
n
eu
m
o
n
ia
ar
ea
i
n
t
h
e
l
u
n
g
X
-
r
a
y
i
m
a
g
e
s
[
2
4
]
.
T
h
is
w
il
l
b
e
d
o
n
e
u
s
i
n
g
t
h
e
Gr
ad
-
C
AM
tech
n
iq
u
e,
w
h
ic
h
lev
er
ag
e
s
g
r
ad
ie
n
ts
f
r
o
m
th
e
last
C
NN
la
y
er
to
id
en
ti
f
y
i
m
p
o
r
ta
n
t
ar
ea
s
i
n
m
a
k
in
g
p
r
ed
ictio
n
s
[
2
5
]
.
T
h
e
r
esu
lt,
ca
lled
th
e
Hea
tMa
p
,
is
a
v
is
u
al
r
ep
r
esen
tatio
n
o
f
th
e
ac
tiv
atio
n
in
te
n
s
it
y
i
n
t
h
e
co
n
v
o
lu
tio
n
al
la
y
er
s
o
f
th
e
n
e
u
r
al
n
e
t
w
o
r
k
w
h
ile
p
r
o
ce
s
s
i
n
g
t
h
e
i
m
ag
e
s
[
2
6
]
.
2
.
5
.
E
v
a
lua
t
io
n
I
n
th
e
e
v
al
u
atio
n
s
ta
g
e,
w
e
will
u
s
e
a
co
n
f
u
s
io
n
m
atr
i
x
to
ass
es
s
th
e
class
if
icatio
n
o
f
i
m
ag
e
[
2
7
]
,
ai
m
i
n
g
to
co
m
p
u
te
p
er
f
o
r
m
an
ce
m
e
tr
ics
s
u
ch
as
ac
c
u
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
-
s
co
r
e
f
r
o
m
th
e
u
tili
ze
d
d
ataset.
A
cc
u
r
ac
y
in
d
icate
s
th
e
m
o
d
el
’
s
ab
il
it
y
to
class
if
y
d
ata
co
r
r
ec
tl
y
.
P
r
ec
is
io
n
ch
ar
ac
ter
izes
t
h
e
ag
r
ee
m
e
n
t
b
et
w
ee
n
r
eq
u
e
s
te
d
d
ata
an
d
th
e
m
o
d
el
’
s
p
r
e
d
icted
o
u
tco
m
es.
R
ec
all
ill
u
s
tr
ates
t
h
e
m
o
d
el
’
s
ca
p
ab
ilit
y
to
r
etr
iev
e
s
p
ec
if
ic
i
n
f
o
r
m
atio
n
.
O
n
th
e
o
th
er
h
a
n
d
,
th
e
F1
-
s
co
r
e
r
ep
r
esen
ts
t
h
e
b
alan
ce
d
av
er
ag
e
o
f
p
r
ec
is
io
n
an
d
r
ec
all.
T
h
e
f
o
r
m
u
las
u
tili
ze
d
to
co
m
p
u
te
p
er
f
o
r
m
an
ce
m
etr
ic
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
.
5
,
Octo
b
e
r
20
25
:
1
3
0
4
-
1
313
1308
A
c
c
ura
c
y
=
(
+
)
(
+
+
+
)
(
1
)
=
(
+
)
(
2
)
=
(
+
)
(
3
)
1
=
(
2
×
×
)
(
+
)
(
4
)
T
h
e
p
u
r
p
o
s
e
o
f
e
v
alu
atio
n
is
t
o
m
ea
s
u
r
e
w
h
ic
h
m
o
d
el
ex
h
ib
its
th
e
b
es
t
p
er
f
o
r
m
an
ce
.
T
h
is
p
r
o
v
id
es
a
co
m
p
r
e
h
en
s
iv
e
o
v
er
v
ie
w
o
f
h
o
w
w
el
l
th
e
m
o
d
els
clas
s
i
f
y
d
ata
a
n
d
is
h
i
g
h
l
y
u
s
e
f
u
l
in
a
s
s
es
s
i
n
g
b
in
ar
y
class
i
f
icatio
n
m
o
d
els.
2
.
6
.
Deplo
y
m
e
nt
T
h
e
f
in
al
s
tag
e,
w
e
w
i
ll
cr
ea
te
a
s
tr
aig
h
t
f
o
r
w
ar
d
w
eb
s
y
s
t
e
m
ap
p
licatio
n
to
p
er
f
o
r
m
p
n
eu
m
o
n
ia
class
i
f
icatio
n
o
n
l
u
n
g
X
-
r
a
y
i
m
ag
e
d
ata.
T
h
is
w
eb
ap
p
licatio
n
is
d
esi
g
n
ed
to
p
r
ed
ict
o
r
class
i
f
y
lu
n
g
X
-
r
a
y
i
m
a
g
es
u
p
lo
ad
ed
b
y
u
s
er
s
.
T
h
e
o
u
tp
u
t
w
i
ll
d
is
p
la
y
t
h
e
p
r
o
b
ab
ilit
y
a
n
d
class
i
f
icatio
n
o
f
w
h
eth
er
t
h
e
i
m
a
g
e
b
elo
n
g
s
to
t
h
e
“
p
n
eu
m
o
n
ia
”
o
r
“
n
o
r
m
al
”
clas
s
.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
W
e
co
n
d
u
cted
o
u
r
ex
p
er
i
m
e
n
ts
u
s
in
g
t
w
o
ar
ch
i
tectu
r
al
m
o
d
el
s
,
E
f
f
icie
n
tNet
a
n
d
R
e
s
Net.
I
n
t
h
e
f
o
llo
w
in
g
s
u
b
s
ec
tio
n
s
,
w
e
r
ep
o
r
t th
e
r
esu
lt
s
.
3
.
1
.
Ana
ly
s
is
o
f
o
pti
m
a
l
m
o
del p
er
f
o
r
m
a
nce
a
cr
o
s
s
diff
er
ent
s
ce
na
rio
s
T
ab
le
2
p
r
esen
ts
th
e
b
est
-
p
er
f
o
r
m
i
n
g
m
o
d
els
ac
r
o
s
s
th
r
ee
tr
ain
in
g
s
ce
n
ar
io
s
u
s
i
n
g
A
d
a
M
ax
,
SGD,
an
d
R
MSp
r
o
p
o
p
tim
izer
s
.
I
n
s
ce
n
ar
io
1
,
th
e
co
m
b
in
a
tio
n
o
f
A
d
a
M
ax
a
n
d
E
f
f
icie
n
tNe
tB
3
ac
h
iev
ed
th
e
m
o
s
t
o
u
ts
ta
n
d
in
g
p
er
f
o
r
m
a
n
ce
,
w
it
h
an
a
cc
u
r
ac
y
o
f
9
9
.
0
4
%,
p
r
e
cisi
o
n
o
f
9
9
.
7
6
%,
r
ec
all
o
f
9
9
.
2
3
%,
an
d
F1
-
s
co
r
e
o
f
9
9
.
3
4
%.
T
h
is
in
d
icate
s
a
h
ig
h
l
y
b
ala
n
ce
d
m
o
d
el
w
it
h
m
in
i
m
al
f
alse
p
o
s
iti
v
e
s
an
d
f
als
e
n
eg
at
iv
e
s
.
W
h
ile
SGD
a
n
d
R
M
Sp
r
o
p
also
p
e
r
f
o
r
m
ed
w
ell
w
it
h
E
f
f
ic
ien
t
NetB
7
,
th
eir
p
er
f
o
r
m
a
n
ce
was
s
li
g
h
tl
y
lo
w
er
,
esp
ec
iall
y
in
ter
m
s
o
f
P
r
ec
is
i
o
n
f
o
r
R
MSp
r
o
p
.
I
n
s
ce
n
ar
io
2
,
E
f
f
ic
ien
t
NetB
3
ag
ai
n
d
em
o
n
s
tr
ated
s
u
p
er
io
r
co
n
s
is
ten
c
y
,
p
ar
ticu
lar
l
y
w
h
e
n
tr
ai
n
ed
u
s
in
g
A
d
a
M
a
x
an
d
R
MSp
r
o
p
,
b
o
th
y
ield
i
n
g
a
n
a
cc
u
r
ac
y
o
f
9
9
.
0
4
%
an
d
h
i
g
h
F1
-
s
co
r
es (
9
9
.
1
4
% a
n
d
9
9
.
5
5
%,
r
esp
ec
tiv
ely
)
.
T
ab
le
2
.
B
est
m
o
d
els f
r
o
m
ea
c
h
s
ce
n
ar
io
S
c
e
n
a
r
i
o
O
p
t
i
mi
z
e
r
M
o
d
e
l
A
c
c
u
r
a
c
y
P
r
e
c
i
si
o
n
R
e
c
a
l
l
F1
-
sco
r
e
1
A
d
a
M
ax
E
f
f
i
c
i
e
n
t
N
e
t
B
3
9
9
.
0
4
%
9
9
.
7
6
%
9
9
.
2
3
%
9
9
.
3
4
%
S
G
D
Ef
f
i
c
i
e
n
t
N
e
t
B
7
9
8
.
3
2
%
9
8
.
84
%
9
8
.
12
%
9
8
.
55
%
R
M
S
p
r
o
p
Ef
f
i
c
i
e
n
t
N
e
t
B
7
9
8
.
5
6
%
9
7
.
4
5
%
9
9
.
1
1
%
9
8
.
1
1
%
2
A
d
a
M
ax
E
f
f
i
c
i
e
n
t
N
e
t
B
3
9
9
.
0
4
%
9
8
.
3
4
%
9
9
.
0
2
%
9
9
.
1
4
%
S
G
D
R
e
sN
e
t
5
0
9
8
.
3
2
%
9
7
.
2
2
%
9
8
.
84
%
9
8
.
43
%
R
M
S
p
r
o
p
Ef
f
i
c
i
e
n
t
N
e
t
B
3
9
9
.
0
4
%
9
8
.
5
3
%
9
9
.
0
2
%
9
9
.
5
5
%
3
A
d
a
max
Ef
f
i
c
i
e
n
t
N
e
t
B
1
9
6
.
8
8
%
9
4
.
8
7
%
9
8
.
1
1
%
9
6
.
2
2
%
S
GD
E
f
f
i
c
i
e
n
t
N
e
t
B
3
9
9
.
0
4
%
9
8
.
4
6
%
9
9
.
2
3
%
9
9
.
1
1
%
R
M
S
p
r
o
p
Ef
f
i
c
i
e
n
t
N
e
t
B
1
9
7
.
8
4
%
9
8
.
88
%
9
6
.
4
4
%
9
7
.
1
8
%
T
h
e
g
r
ap
h
s
in
F
ig
u
r
e
4
s
h
o
w
t
h
e
tr
ain
in
g
an
d
v
alid
atio
n
lo
s
s
an
d
ac
cu
r
ac
y
f
o
r
th
r
ee
s
ce
n
ar
io
s
:
Fig
u
r
e
s
4
(
a)
-
(
c)
.
I
n
s
ce
n
ar
io
1
,
b
o
th
tr
ain
in
g
an
d
v
alid
atio
n
lo
s
s
es
d
ec
r
ea
s
e
s
tead
il
y
an
d
co
n
v
er
g
e,
in
d
icat
in
g
ef
f
ec
tiv
e
lear
n
i
n
g
w
ith
m
i
n
i
m
al
o
v
er
f
itti
n
g
.
T
h
e
b
est
ep
o
ch
is
m
ar
k
ed
at
2
0
f
o
r
lo
s
s
a
n
d
1
7
f
o
r
ac
cu
r
ac
y
,
s
h
o
w
i
n
g
o
p
ti
m
al
p
er
f
o
r
m
an
ce
.
Scen
ar
io
2
f
o
llo
w
s
a
s
i
m
ilar
tr
en
d
,
w
ith
lo
s
s
e
s
co
n
v
er
g
i
n
g
an
d
th
e
b
es
t
ep
o
ch
at
2
3
,
r
ef
lectin
g
s
tab
le
lear
n
i
n
g
a
n
d
r
o
b
u
s
t
p
er
f
o
r
m
an
ce
.
B
o
th
s
ce
n
ar
io
s
s
h
o
w
co
n
s
i
s
te
n
t
i
m
p
r
o
v
e
m
e
n
t
s
i
n
tr
ain
i
n
g
a
n
d
v
al
id
atio
n
ac
c
u
r
ac
y
,
w
i
th
n
ea
r
-
p
er
f
ec
t
tr
ai
n
in
g
ac
cu
r
ac
y
an
d
s
lig
h
tl
y
f
l
u
ctu
a
tin
g
b
u
t
h
i
g
h
v
alid
atio
n
ac
c
u
r
ac
y
.
I
n
co
n
tr
ast,
s
ce
n
ar
io
3
ex
h
ib
its
s
ig
n
i
f
ic
an
t
f
lu
ct
u
atio
n
s
i
n
tr
ain
in
g
lo
s
s
an
d
an
i
n
cr
ea
s
i
n
g
v
alid
atio
n
lo
s
s
a
f
ter
th
e
b
e
s
t
ep
o
ch
at
3
,
in
d
icatin
g
o
v
er
f
itt
in
g
.
I
t
s
ac
cu
r
ac
y
tr
en
d
s
ar
e
u
n
s
tab
le,
w
it
h
r
ap
id
tr
ain
i
n
g
ac
c
u
r
ac
y
i
m
p
r
o
v
e
m
e
n
ts
b
u
t
f
l
u
ct
u
ati
n
g
v
alid
atio
n
ac
cu
r
ac
y
.
T
h
is
s
u
g
g
e
s
ts
s
ce
n
a
r
io
3
co
u
ld
b
en
ef
i
t
f
r
o
m
ad
d
itio
n
al
r
eg
u
lar
izatio
n
to
i
m
p
r
o
v
e
g
e
n
er
aliza
tio
n
.
Ov
er
all,
s
ce
n
ar
io
s
1
an
d
2
p
er
f
o
r
m
b
etter
w
it
h
m
i
n
i
m
al
o
v
er
f
itti
n
g
,
w
h
ile
s
ce
n
ar
io
3
h
ig
h
li
g
h
ts
c
h
alle
n
g
e
s
in
m
ai
n
tai
n
i
n
g
s
tab
ilit
y
a
n
d
p
r
ev
en
t
in
g
o
v
er
f
itti
n
g
.
T
h
ese
f
i
n
d
in
g
s
u
n
d
er
s
co
r
e
th
e
im
p
o
r
tan
ce
o
f
s
e
lectin
g
th
e
r
i
g
h
t
ep
o
ch
to
b
alan
ce
ac
cu
r
ac
y
a
n
d
g
en
er
aliza
tio
n
f
o
r
r
o
b
u
s
t
m
o
d
el
p
er
f
o
r
m
a
n
ce
.
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
d
va
n
ce
d
p
n
e
u
mo
n
ia
cl
a
s
s
ific
a
tio
n
u
s
in
g
tr
a
n
s
fer lea
r
n
in
g
o
n
ch
est X
-
r
a
y
d
a
t
a
…
(
Green
A
r
th
er
S
a
n
d
a
g
)
1309
(
a)
(
b
)
(
c)
Fig
u
r
e
4
.
T
r
ain
in
g
an
d
v
a
lid
ati
o
n
lo
s
s
an
d
ac
c
u
r
ac
y
g
r
ap
h
s
f
o
r
th
r
ee
d
if
f
er
en
t scen
ar
io
s
lab
eled
;
(
a
)
s
ce
n
ar
io
1
,
(
b
)
s
ce
n
ar
io
2
,
an
d
(
c
)
s
ce
n
ar
io
3
3
.
2
.
Co
m
pa
riso
n w
it
h r
ela
t
ed
re
s
ea
rc
h
I
n
o
r
d
e
r
t
o
es
t
a
b
li
s
h
t
h
e
c
o
m
p
a
r
a
t
iv
e
ef
f
e
c
tiv
en
e
s
s
o
f
o
u
r
p
r
o
p
o
s
e
d
a
p
p
r
o
a
c
h
,
w
e
b
en
ch
m
a
r
k
e
d
it
s
p
e
r
f
o
r
m
an
c
e
ag
ai
n
s
t
p
r
ev
i
o
u
s
ly
r
e
p
o
r
t
e
d
t
r
an
s
f
e
r
l
e
a
r
n
in
g
m
o
d
e
ls
o
n
ch
es
t
X
-
r
ay
im
ag
e
c
l
as
s
i
f
i
c
a
ti
o
n
f
o
r
p
n
eu
m
o
n
i
a
d
e
te
c
t
i
o
n
.
T
a
b
l
e
3
s
h
o
w
s
th
a
t
o
u
r
m
o
d
el
o
u
t
p
er
f
o
r
m
s
f
o
u
r
o
th
e
r
m
o
d
el
s
in
t
e
r
m
s
o
f
ac
cu
r
a
cy
.
J
a
i
n
e
t
a
l
.
[
8
]
u
s
e
d
m
o
d
e
ls
l
ik
e
2
c
o
n
v
o
lu
ti
o
n
a
l
l
a
y
e
r
,
3
c
o
n
v
o
lu
t
i
o
n
al
l
ay
e
r
,
V
G
G
1
6
,
VGG
1
9
,
R
e
s
N
e
t
5
0
,
a
n
d
I
n
c
e
p
ti
o
n
-
v
3
o
n
th
e
c
h
e
s
t
X
-
r
ay
im
ag
es
(
p
n
eu
m
o
n
i
a
)
d
a
t
a
s
et
,
a
c
h
i
ev
i
n
g
th
e
b
e
s
t
a
c
cu
r
a
cy
o
f
9
2
.
3
1
%
w
i
th
3
c
o
n
v
o
lu
t
i
o
n
a
l
l
ay
e
r
u
s
in
g
c
at
eg
o
r
i
c
al
c
l
as
s
if
i
c
a
ti
o
n
.
K
a
lg
u
tk
a
r
e
t
a
l
.
[
2
8
]
em
p
l
o
y
e
d
V
GG1
6
,
R
e
s
Ne
t
5
0
,
a
n
d
I
n
c
e
p
ti
o
n
V
3
o
n
th
e
l
a
b
e
l
e
d
o
p
t
i
c
a
l
c
o
h
e
r
en
c
e
t
o
m
o
g
r
a
p
h
y
an
d
ch
es
t
X
-
r
ay
im
ag
es
c
l
as
s
i
f
ic
a
t
i
o
n
d
a
t
as
et
,
w
ith
V
G
G
1
6
r
e
a
ch
in
g
t
h
e
h
ig
h
e
s
t
ac
c
u
r
a
cy
o
f
9
4
%
u
s
i
n
g
b
i
n
a
r
y
c
l
a
s
s
if
ic
a
t
i
o
n
.
C
h
a
tt
e
r
je
e
e
t
a
l
.
[
2
9
]
u
s
e
d
V
GG
1
6
,
V
G
G
1
9
,
R
es
N
et
5
0
,
M
o
b
i
l
e
N
et
V
1
,
a
n
d
E
f
f
i
c
ie
n
t
N
et
B
3
o
n
t
h
e
c
h
es
t
X
-
r
ay
im
ag
es
(
p
n
eu
m
o
n
i
a
)
d
a
t
as
e
t
,
w
h
e
r
e
E
f
f
i
ci
en
t
Ne
t
B
3
a
ch
i
ev
e
d
th
e
b
e
s
t
a
cc
u
r
ac
y
o
f
9
3
%
w
it
h
b
i
n
a
r
y
c
l
ass
if
i
ca
t
i
o
n
.
Sim
i
la
r
ly
,
N
iñ
o
e
t
a
l
.
[
3
0
]
u
ti
l
i
z
ed
D
e
n
s
e
Ne
t
,
V
G
G
1
9
,
a
n
d
R
e
s
Ne
t
5
0
o
n
th
e
s
am
e
d
a
t
as
e
t
,
w
it
h
R
es
N
et
5
0
a
ch
i
ev
i
n
g
th
e
h
i
g
h
es
t
ac
cu
r
a
cy
o
f
9
1
%
u
s
in
g
b
in
a
r
y
cl
a
s
s
if
ic
a
t
i
o
n
.
I
n
c
o
n
t
r
as
t
,
o
u
r
m
o
d
el
,
E
f
f
i
c
i
en
t
N
e
t
B
3
,
a
ch
i
ev
e
d
an
a
c
cu
r
a
cy
r
a
t
e
o
f
9
9
.
0
4
%
in
c
a
t
eg
o
r
i
c
a
l
cl
a
s
s
if
ic
a
t
i
o
n
o
n
t
h
e
c
h
es
t
X
-
r
ay
im
ag
es
(
p
n
eu
m
o
n
i
a
)
d
a
t
as
et
.
T
h
i
s
in
d
i
ca
t
es
th
a
t
o
u
r
m
o
d
e
l
is
m
o
r
e
a
c
c
u
r
at
e
th
an
th
e
o
th
e
r
s
,
h
ig
h
l
ig
h
t
in
g
it
s
ef
f
ec
t
iv
en
es
s
f
o
r
p
r
e
ci
s
e
p
n
eu
m
o
n
i
a
d
e
t
ec
t
i
o
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
23
,
No
.
5
,
Octo
b
e
r
20
25
:
1
3
0
4
-
1
313
1310
T
ab
le
3
.
Mo
d
el
co
m
p
ar
is
o
n
with
r
elate
d
r
esear
ch
R
e
f
e
r
e
n
c
e
M
o
d
e
l
D
a
t
a
se
t
B
e
st
mo
d
e
l
a
c
c
u
r
a
c
y
r
e
su
l
t
C
l
a
ssi
f
i
c
a
t
i
o
n
me
t
h
o
d
Jai
n
e
t
a
l
.
[
8
]
2
c
o
n
v
o
l
u
t
i
o
n
a
l
l
a
y
e
r
, 3
c
o
n
v
o
l
u
t
i
o
n
a
l
l
a
y
e
r
,
V
G
G
1
6
,
V
G
G
1
9
,
R
e
sN
e
t
5
0
,
a
n
d
I
n
c
e
p
t
i
o
n
-
v3
C
h
e
st
X
-
r
a
y
i
mag
e
s
(
p
n
e
u
mo
n
i
a
)
3
c
o
n
v
o
l
u
t
i
o
n
a
l
l
a
y
e
r
(
9
2
.
3
1
%)
C
a
t
e
g
o
r
i
c
a
l
K
a
l
g
u
t
k
a
r
e
t
a
l
.
[
2
8
]
V
G
G
1
6
,
R
e
sN
e
t
5
0
,
a
n
d
I
n
c
e
p
t
i
o
n
V
3
L
a
b
e
l
e
d
o
p
t
i
c
a
l
c
o
h
e
r
e
n
c
e
t
o
mo
g
r
a
p
h
y
a
n
d
c
h
e
st
X
-
r
a
y
i
mag
e
s c
l
a
ssi
f
i
c
a
t
i
o
n
V
G
G
1
6
(
9
4
%)
B
i
n
a
r
y
C
h
a
t
t
e
r
j
e
e
e
t
a
l
.
[
2
9
]
V
G
G
1
6
,
V
G
G
1
9
,
R
e
sN
e
t
5
0
,
M
o
b
i
l
e
N
e
t
V
1
,
a
n
d
Ef
f
i
c
i
e
n
t
N
e
t
B
3
C
h
e
st
X
-
r
a
y
i
mag
e
s
(
p
n
e
u
mo
n
i
a
)
Ef
f
i
c
i
e
n
t
N
e
t
B
3
(
9
3
%)
B
i
n
a
r
y
N
i
ñ
o
e
t
a
l
.
[
3
0
]
D
e
n
se
N
e
t
,
V
G
G
1
9
,
a
n
d
R
e
sN
e
t
5
0
C
h
e
st
X
-
r
a
y
i
mag
e
s
(
p
n
e
u
mo
n
i
a
)
R
e
sN
e
t
5
0
(
9
1
%)
B
i
n
a
r
y
Ou
r
r
e
se
a
r
c
h
E
f
f
i
c
i
e
n
t
N
e
t
(
B
1
,
B
3
,
B
5
,
a
n
d
B
7
)
,
a
n
d
R
e
sN
e
t
(
5
0
a
n
d
1
0
1
)
C
h
e
st
X
-
r
ay
i
m
a
g
e
s
(
p
n
e
u
m
o
n
i
a
)
E
f
f
i
c
i
e
n
t
N
e
t
B
3
(
9
9
.
0
4
%
)
C
a
t
e
g
o
r
i
c
a
l
3
.
3
.
G
ra
d
-
CAM
v
is
ua
liza
t
io
n
T
h
is
s
ec
tio
n
e
x
p
lain
s
th
e
r
es
u
lts
o
f
ap
p
l
y
i
n
g
th
e
Gr
ad
-
C
AM
alg
o
r
ith
m
to
th
e
p
r
ev
io
u
s
l
y
test
ed
to
p
-
p
er
f
o
r
m
in
g
m
o
d
el,
E
f
f
icien
t
N
etB
3
.
T
h
is
m
o
d
el
h
i
g
h
li
g
h
ts
s
p
ec
if
ic
ar
ea
s
i
n
i
m
a
g
e
s
,
s
u
c
h
as
r
eg
io
n
s
af
f
ec
ted
b
y
p
n
eu
m
o
n
ia
i
n
l
u
n
g
X
-
r
a
y
s
,
allo
w
in
g
f
o
r
m
o
r
e
ac
cu
r
at
e
d
iag
n
o
s
t
ic
i
n
f
o
r
m
atio
n
.
T
h
e
ex
p
lain
ab
le
d
ee
p
lear
n
in
g
alg
o
r
it
h
m
,
c
u
s
to
m
Gr
ad
-
C
A
M,
r
etr
iev
e
s
in
f
o
r
m
atio
n
f
r
o
m
t
h
e
f
i
n
al
co
n
v
o
l
u
tio
n
al
la
y
er
an
d
tr
an
s
f
o
r
m
s
it
i
n
to
a
h
ea
t
m
ap
.
T
h
e
h
ea
t
m
ap
d
is
p
la
y
s
r
eg
i
o
n
s
th
at
t
h
e
class
i
f
ier
f
o
c
u
s
ed
o
n
to
r
ea
ch
its
co
n
clu
s
io
n
.
R
ed
an
d
y
ello
w
ar
ea
s
o
n
th
e
h
ea
t
m
ap
in
d
icat
e
th
e
lu
n
g
r
eg
io
n
s
m
o
s
t
r
e
le
v
an
t
to
th
e
m
o
d
el
’
s
p
n
eu
m
o
n
ia
p
r
ed
ictio
n
,
w
it
h
c
o
lo
r
in
ten
s
it
y
r
e
f
lecti
n
g
th
e
lev
el
o
f
i
m
p
o
r
tan
ce
.
T
h
e
im
a
g
e
in
Fig
u
r
e
5
s
h
o
w
s
a
s
tan
d
ar
d
ch
est
X
-
r
a
y
,
w
h
ile
th
e
i
m
a
g
e
b
elo
w
it
o
v
er
la
y
s
th
e
Gr
ad
-
C
A
M
h
ea
t
m
ap
.
T
h
is
h
ea
t
m
ap
ass
i
s
ts
r
ad
io
lo
g
is
ts
an
d
m
ed
ical
p
r
o
f
ess
io
n
al
s
i
n
co
n
ce
n
tr
atin
g
o
n
ar
ea
s
lik
el
y
af
f
ec
ted
b
y
p
n
e
u
m
o
n
ia,
f
ac
ilit
ati
n
g
q
u
ick
er
an
d
m
o
r
e
ac
cu
r
ate
d
iag
n
o
s
e
s
.
B
y
o
v
er
la
y
i
n
g
t
h
e
h
ea
t
m
ap
o
n
th
e
o
r
ig
i
n
al
i
m
a
g
e,
h
ea
lt
h
ca
r
e
p
r
o
f
ess
io
n
al
s
ca
n
a
s
s
e
s
s
t
h
e
f
ac
to
r
s
in
f
l
u
e
n
ci
n
g
t
h
e
d
ec
is
io
n
,
e
n
s
u
r
in
g
a
m
o
r
e
i
n
f
o
r
m
ed
an
d
r
eliab
le
d
iag
n
o
s
t
ic
p
r
o
ce
s
s
.
T
h
e
ef
f
ec
tiv
en
e
s
s
o
f
t
h
e
Gr
ad
-
C
AM
h
e
at
m
ap
in
id
en
t
if
y
i
n
g
p
n
e
u
m
o
n
ia
-
af
f
ec
ted
r
eg
io
n
s
ca
n
b
e
v
alid
ated
ag
ai
n
s
t c
li
n
ic
al
f
i
n
d
in
g
s
,
en
s
u
r
in
g
th
e
m
o
d
el’
s
r
eliab
ili
t
y
i
n
a
clin
ical
s
etti
n
g
.
Fig
u
r
e
5
.
Gr
ad
-
C
A
M
o
f
p
n
e
u
m
o
n
ia
l
u
n
g
i
m
a
g
es
3
.
4
.
P
neu
m
o
nia
cla
s
s
if
ica
t
io
n w
e
b sy
s
t
e
m
T
o
tr
an
s
late
th
e
r
e
s
ea
r
ch
f
in
d
in
g
s
i
n
to
a
p
r
ac
tical
to
o
l,
th
e
d
ev
elo
p
ed
m
o
d
el
w
as
i
n
te
g
r
ated
in
to
a
s
i
m
p
le
w
eb
-
b
ased
s
y
s
te
m
.
I
n
Fig
u
r
e
6
,
th
e
f
in
al
s
ta
g
e
af
ter
co
m
p
let
in
g
m
o
d
el
d
ev
elo
p
m
e
n
t
an
d
ev
alu
a
tio
n
is
th
e
d
esig
n
o
f
th
is
w
eb
ap
p
licatio
n
to
test
th
e
tr
ain
ed
m
o
d
el.
T
h
is
w
eb
s
y
s
te
m
e
n
ab
les
u
s
er
s
to
u
p
lo
ad
ch
est
X
-
r
ay
i
m
a
g
es
d
ir
ec
tl
y
t
h
r
o
u
g
h
th
e
in
ter
f
ac
e,
p
r
o
v
id
in
g
an
ac
ce
s
s
ib
le
w
a
y
to
in
ter
ac
t
w
it
h
t
h
e
class
i
f
ier
.
On
ce
t
h
e
i
m
a
g
e
is
u
p
lo
ad
ed
,
th
e
m
o
d
el
au
to
m
atica
ll
y
p
r
o
ce
s
s
e
s
it
an
d
class
if
ies
t
h
e
r
esu
l
t
in
to
o
n
e
o
f
t
w
o
ca
te
g
o
r
ies:
n
o
r
m
al
o
r
p
n
eu
m
o
n
ia,
t
h
er
eb
y
d
em
o
n
s
tr
ati
n
g
th
e
p
r
ac
tical
d
ep
lo
y
m
e
n
t o
f
t
h
e
s
y
s
te
m
.
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
d
va
n
ce
d
p
n
e
u
mo
n
ia
cl
a
s
s
ific
a
tio
n
u
s
in
g
tr
a
n
s
fer lea
r
n
in
g
o
n
ch
est X
-
r
a
y
d
a
t
a
…
(
Green
A
r
th
er
S
a
n
d
a
g
)
1311
Fig
u
r
e
6
.
P
n
eu
m
o
n
ia
clas
s
if
ic
atio
n
w
eb
s
y
s
te
m
4.
CO
NCLU
SI
O
N
T
h
e
u
tili
za
tio
n
o
f
C
N
N
f
o
r
class
i
f
y
in
g
lu
n
g
X
-
r
a
y
i
m
a
g
es
i
n
t
o
n
o
r
m
al
a
n
d
p
n
eu
m
o
n
ia
ca
te
g
o
r
ies
ca
n
b
e
in
teg
r
ated
b
y
lev
er
a
g
in
g
tr
an
s
f
er
lear
n
in
g
tec
h
n
iq
u
e
s
s
u
c
h
as
E
f
f
ic
ien
t
Net
an
d
R
esNet
,
an
d
t
h
en
i
m
p
le
m
en
ted
i
n
to
a
W
eb
A
p
p
.
E
f
f
icie
n
tNetB
3
d
e
m
o
n
s
tr
ate
d
th
e
m
o
s
t
o
p
ti
m
al
a
n
d
b
est
p
er
f
o
r
m
an
ce
w
i
th
a
n
ac
cu
r
ac
y
o
f
9
9
.
0
4
%,
u
s
in
g
a
LR
o
f
0
.
0
0
1
,
b
atch
s
ize
o
f
2
0
,
an
d
3
0
ep
o
ch
s
,
alo
n
g
w
i
th
ca
te
g
o
r
ical
lo
s
s
f
u
n
ctio
n
a
n
d
A
d
a
M
ax
o
p
tim
izer
.
T
h
is
m
o
d
el
o
u
tp
er
f
o
r
m
ed
E
f
f
icie
n
tNetB
1
,
B
5
,
B
7
,
R
esNet5
0
,
an
d
R
esNet1
0
1
m
o
d
els.
Ov
er
all,
th
is
r
esear
ch
f
o
u
n
d
th
at
th
e
ap
p
licatio
n
o
f
C
NN
w
i
th
tr
an
s
f
er
lear
n
in
g
m
o
d
el
E
f
f
icien
tNetB
3
is
a
h
ig
h
l
y
p
r
o
m
is
in
g
ch
o
ice,
o
f
f
er
i
n
g
s
tr
o
n
g
p
o
ten
tial
as
a
s
o
lu
tio
n
f
o
r
clas
s
if
y
i
n
g
p
n
eu
m
o
n
ia
lu
n
g
X
-
r
a
y
i
m
a
g
es.
ACK
NO
WL
E
D
G
M
E
NT
S
T
h
e
au
th
o
r
g
r
atef
u
ll
y
ac
k
n
o
w
led
g
es
t
h
e
Facu
lt
y
o
f
C
o
m
p
u
ter
Scie
n
ce
,
Klab
at
U
n
i
v
er
s
it
y
,
f
o
r
it
s
co
n
tin
u
o
u
s
s
u
p
p
o
r
t
an
d
en
co
u
r
ag
e
m
en
t
t
h
r
o
u
g
h
o
u
t
t
h
e
co
m
p
letio
n
o
f
th
i
s
r
esear
ch
.
T
h
e
ac
a
d
em
ic
en
v
ir
o
n
m
e
n
t a
n
d
r
es
ea
r
ch
f
ac
i
liti
es p
r
o
v
id
ed
b
y
t
h
e
f
ac
u
lt
y
h
av
e
b
ee
n
ess
e
n
tia
l in
f
ac
ilit
a
ti
n
g
t
h
i
s
s
t
u
d
y
.
F
UNDIN
G
I
NF
O
RM
AT
I
O
N
T
h
is
r
esear
ch
w
as s
u
p
p
o
r
ted
b
y
Klab
at
Un
i
v
er
s
i
t
y
.
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
Gr
ee
n
A
r
th
er
Sa
n
d
ag
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
T
im
o
th
y
J
.
Mu
lali
n
d
a
✓
✓
✓
✓
✓
✓
✓
✓
✓
Glo
r
ia
A
.
M.
Su
s
an
to
✓
✓
✓
✓
✓
✓
✓
✓
Sten
l
y
R
.
P
u
n
g
u
s
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
si
s
I
:
I
n
v
e
st
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
si
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
T
h
e
au
th
o
r
d
ec
lar
es th
at
t
h
er
e
is
n
o
co
n
f
lict o
f
i
n
ter
es
t r
eg
ar
d
in
g
t
h
e
p
u
b
licatio
n
o
f
t
h
is
p
a
p
er
.
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
.
5
,
Octo
b
e
r
20
25
:
1
3
0
4
-
1
313
1312
I
NF
O
RM
E
D
CO
NSE
N
T
W
e
u
s
ed
th
e
d
ataset
a
v
ailab
le
o
n
th
e
Ka
g
g
le
w
eb
s
ite,
s
o
w
e
h
av
e
o
b
tain
ed
i
n
f
o
r
m
ed
co
n
s
e
n
t f
r
o
m
a
ll
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
i
s
s
tu
d
y
d
i
d
n
o
t
i
n
v
o
lv
e
an
y
h
u
m
an
p
a
r
t
i
ci
p
a
n
t
s
o
r
an
im
a
l
s
.
T
h
e
r
ef
o
r
e
,
et
h
i
c
a
l
a
p
p
r
o
v
a
l
w
as
n
o
t
r
e
q
u
i
r
e
d
.
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
in
d
i
n
g
s
o
f
t
h
i
s
s
t
u
d
y
ar
e
o
p
en
ly
a
v
ailab
le
i
n
Kag
g
le
at
h
ttp
s
:/
/
www
.
k
ag
g
le.
co
m
/d
atas
ets/
p
au
lt
i
m
o
t
h
y
m
o
o
n
e
y
/c
h
est
-
x
r
a
y
-
p
n
e
u
m
o
n
ia
[
1
9
]
.
RE
F
E
R
E
NC
E
S
[
1
]
V
.
K
u
mar,
“
P
u
l
mo
n
a
r
y
i
n
n
a
t
e
i
mm
u
n
e
r
e
sp
o
n
se
d
e
t
e
r
mi
n
e
s t
h
e
o
u
t
c
o
me
o
f
i
n
f
l
a
mm
a
t
i
o
n
d
u
r
i
n
g
p
n
e
u
mo
n
i
a
a
n
d
se
p
si
s
-
a
sso
c
i
a
t
e
d
a
c
u
t
e
l
u
n
g
i
n
j
u
r
y
,
”
Fro
n
t
i
e
rs
i
n
I
m
m
u
n
o
l
o
g
y
,
v
o
l
.
1
1
,
p
.
1
7
2
2
,
2
0
2
0
,
d
o
i
:
1
0
.
3
3
8
9
/
f
i
mm
u
.
2
0
2
0
.
0
1
7
2
2
.
[
2
]
N
a
t
i
o
n
a
l
H
e
a
r
t
,
L
u
n
g
,
a
n
d
B
l
o
o
d
I
n
st
i
t
u
t
e
,
“
W
h
a
t
i
s
p
n
e
u
m
o
n
i
a
?
,
”
N
I
H
.
A
c
c
e
ss
e
d
:
S
e
p
.
1
4
,
2
0
2
3
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s:
/
/
w
w
w
.
n
h
l
b
i
.
n
i
h
.
g
o
v
/
h
e
a
l
t
h
/
p
n
e
u
mo
n
i
a
[
3
]
D
.
F
e
n
g
e
t
a
l
.
,
“
C
l
i
n
i
c
a
l
t
r
i
a
l
l
a
n
d
sc
a
p
e
f
o
r
p
n
e
u
mo
n
i
a
:
Ev
o
l
v
i
n
g
a
g
e
n
t
s
a
g
a
i
n
st
b
a
c
t
e
r
i
a
l
p
a
t
h
o
g
e
n
s,”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
I
n
f
e
c
t
i
o
u
s D
i
se
a
ses
,
v
o
l
.
1
5
8
,
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
j
i
d
.
2
0
2
5
.
1
0
7
9
6
5
.
[
4
]
S
.
B
.
Z
a
man
,
N
.
H
o
ssa
i
n
,
M
d
.
T
.
U
.
S
.
T
a
l
h
a
,
K
.
H
a
sa
n
,
R
.
B
.
Z
a
ma
n
,
a
n
d
R
.
K
h
a
n
,
“
A
sse
ssi
n
g
t
h
e
r
i
s
k
o
f
a
n
t
i
b
i
o
t
i
c
r
e
si
st
a
n
c
e
i
n
c
h
i
l
d
h
o
o
d
p
n
e
u
m
o
n
i
a
:
A
h
o
sp
i
t
a
l
-
b
a
se
d
s
t
u
d
y
i
n
B
a
n
g
l
a
d
e
sh
,
”
H
e
a
l
t
h
c
a
re
,
v
o
l
.
1
3
,
n
o
.
3
,
p
.
2
0
7
,
Jan
.
2
0
2
5
,
d
o
i
:
1
0
.
3
3
9
0
/
h
e
a
l
t
h
c
a
r
e
1
3
0
3
0
2
0
7
.
[
5
]
A
.
N
a
t
h
a
n
i
a
n
d
H
.
E.
D
i
n
c
e
r
,
“
A
d
v
a
n
c
e
me
n
t
s
i
n
i
m
a
g
i
n
g
t
e
c
h
n
o
l
o
g
i
e
s
f
o
r
t
h
e
d
i
a
g
n
o
si
s
o
f
l
u
n
g
c
a
n
c
e
r
a
n
d
o
t
h
e
r
p
u
l
mo
n
a
r
y
d
i
se
a
se
s,”
D
i
a
g
n
o
st
i
c
s
,
v
o
l
.
1
5
,
n
o
.
7
,
p
.
8
2
6
,
M
a
r
.
2
0
2
5
,
d
o
i
:
1
0
.
3
3
9
0
/
d
i
a
g
n
o
st
i
c
s
1
5
0
7
0
8
2
6
.
[
6
]
K
.
M
.
A
b
u
b
e
k
e
r
a
n
d
S
.
B
a
s
k
a
r
,
“
B
2
-
N
e
t
:
A
n
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
p
o
w
e
r
e
d
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
f
r
a
me
w
o
r
k
f
o
r
t
h
e
c
l
a
ssi
f
i
c
a
t
i
o
n
o
f
p
n
e
u
mo
n
i
a
i
n
c
h
e
s
t
X
-
r
a
y
i
mag
e
s
,”
Ma
c
h
i
n
e
L
e
a
rn
i
n
g
:
S
c
i
e
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
4
,
n
o
.
1
,
A
p
r
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
8
8
/
2
6
3
2
-
2
1
5
3
/
a
c
c
3
0
f
.
[
7
]
I
.
H
.
S
a
r
k
e
r
,
“
D
e
e
p
l
e
a
r
n
i
n
g
:
A
c
o
mp
r
e
h
e
n
si
v
e
o
v
e
r
v
i
e
w
o
n
t
e
c
h
n
i
q
u
e
s
,
t
a
x
o
n
o
my
,
a
p
p
l
i
c
a
t
i
o
n
s
a
n
d
r
e
se
a
r
c
h
d
i
r
e
c
t
i
o
n
s,
”
S
N
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
2
,
n
o
.
6
,
A
u
g
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
0
7
/
s4
2
9
79
-
0
2
1
-
0
0
8
1
5
-
1
.
[
8
]
R
.
Ja
i
n
,
P
.
N
a
g
r
a
t
h
,
G
.
K
a
t
a
r
i
a
,
V
.
S
.
K
a
u
sh
i
k
,
a
n
d
D
.
J
.
H
e
ma
n
t
h
,
“
P
n
e
u
mo
n
i
a
d
e
t
e
c
t
i
o
n
i
n
c
h
e
st
X
-
r
a
y
i
mag
e
s
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
s
a
n
d
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
,
”
Me
a
su
r
e
m
e
n
t
,
v
o
l
.
1
6
5
,
p
.
1
0
8
0
4
6
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
me
a
su
r
e
me
n
t
.
2
0
2
0
.
1
0
8
0
4
6
.
[
9
]
M
.
P
a
t
e
l
,
A
.
S
o
j
i
t
r
a
,
Z
.
P
a
t
e
l
,
a
n
d
M
.
H
.
B
o
h
a
r
a
,
“
P
n
e
u
mo
n
i
a
d
e
t
e
c
t
i
o
n
u
s
i
n
g
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
En
g
i
n
e
e
ri
n
g
Re
s
e
a
rc
h
&
T
e
c
h
n
o
l
o
g
y
(
I
J
ERT)
,
v
o
l
.
10
,
n
o
.
1
0
,
p
p
.
2
5
2
–
2
6
1
,
2
0
2
1
.
[
1
0
]
E
.
B
a
y
k
a
l
,
H
.
D
o
g
a
n
,
M
.
E
.
Er
c
i
n
,
S
.
Er
so
z
,
a
n
d
M
.
E
k
i
n
c
i
,
“
T
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
w
i
t
h
p
r
e
-
t
r
a
i
n
e
d
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
f
o
r
se
r
o
u
s
c
e
l
l
c
l
a
ssi
f
i
c
a
t
i
o
n
,
”
Mu
l
t
i
m
e
d
i
a
T
o
o
l
s
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
7
9
,
p
p
.
1
5
5
9
3
–
1
5
6
1
1
,
Ju
n
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
0
4
2
-
0
1
9
-
0
7
8
2
1
-
9.
[
1
1
]
P
.
C
h
h
i
k
a
r
a
,
P
.
S
i
n
g
h
,
P
.
G
u
p
t
a
,
a
n
d
T
.
B
h
a
t
i
a
,
“
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
w
i
t
h
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
f
o
r
d
e
t
e
c
t
i
n
g
p
n
e
u
mo
n
i
a
o
n
c
h
e
st
X
-
r
a
y
s,
”
A
d
v
a
n
c
e
s
i
n
I
n
t
e
l
l
i
g
e
n
t
S
y
s
t
e
m
s
a
n
d
C
o
m
p
u
t
i
n
g
,
v
o
l
.
1
0
6
4
,
p
p
.
1
5
5
–
1
6
8
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
9
8
1
-
15
-
0
3
3
9
-
9_
1
3
.
[
1
2
]
G
.
A
.
S
a
n
d
a
g
a
n
d
R
.
M
a
r
i
n
g
k
a
,
“
U
t
i
l
i
z
i
n
g
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
f
o
r
b
r
a
i
n
t
u
m
o
r
d
e
t
e
c
t
i
o
n
a
n
d
g
r
a
d
-
C
A
M
v
i
s
u
a
l
e
x
p
l
a
n
a
t
i
o
n
,
”
2
0
2
4
6
t
h
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
y
b
e
r
n
e
t
i
c
s
a
n
d
I
n
t
e
l
l
i
g
e
n
t
S
y
st
e
m
(
I
C
O
RI
S
)
.
I
E
EE
,
2
0
2
4
,
p
p
.
1
–
6,
d
o
i
:
1
0
.
1
1
0
9
/
i
c
o
r
i
s6
3
5
4
0
.
2
0
2
4
.
1
0
9
0
3
9
6
0
.
[
1
3
]
R
.
R
.
S
e
l
v
a
r
a
j
u
,
M
.
C
o
g
sw
e
l
l
,
A
.
D
a
s,
R
.
V
e
d
a
n
t
a
m,
D
.
P
a
r
i
k
h
,
a
n
d
D
.
B
a
t
r
a
,
“
G
r
a
d
-
C
A
M
:
V
i
su
a
l
e
x
p
l
a
n
a
t
i
o
n
s
f
r
o
m
d
e
e
p
n
e
t
w
o
r
k
s
v
i
a
g
r
a
d
i
e
n
t
-
b
a
se
d
l
o
c
a
l
i
z
a
t
i
o
n
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
C
o
m
p
u
t
e
r
Vi
s
i
o
n
,
v
o
l
.
1
2
8
,
n
o
.
2
,
p
p
.
3
3
6
–
3
5
9
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
2
6
3
-
0
1
9
-
0
1
2
2
8
-
7.
[
1
4
]
M
.
K
.
U
.
A
h
a
me
d
e
t
a
l
.
,
“
D
TL
C
x
:
A
n
i
mp
r
o
v
e
d
r
e
sn
e
t
a
r
c
h
i
t
e
c
t
u
r
e
t
o
c
l
a
ssi
f
y
n
o
r
mal
a
n
d
c
o
n
v
e
n
t
i
o
n
a
l
p
n
e
u
mo
n
i
a
c
a
se
s
f
r
o
m
C
O
V
I
D
-
19
i
n
st
a
n
c
e
s
w
i
t
h
G
r
a
d
-
C
A
M
-
b
a
se
d
su
p
e
r
i
mp
o
se
d
v
i
s
u
a
l
i
z
a
t
i
o
n
u
t
i
l
i
z
i
n
g
c
h
e
st
X
-
r
a
y
i
m
a
g
e
s
,
”
D
i
a
g
n
o
st
i
c
s
,
v
o
l
.
1
3
,
n
o
.
3
,
p
.
5
5
1
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
d
i
a
g
n
o
st
i
c
s
1
3
0
3
0
5
5
1
.
[
1
5
]
S
.
-
M
.
C
h
a
,
S
.
-
S
.
L
e
e
,
a
n
d
B
.
K
o
,
“
A
t
t
e
n
t
i
o
n
-
b
a
se
d
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
f
o
r
e
f
f
i
c
i
e
n
t
p
n
e
u
mo
n
i
a
d
e
t
e
c
t
i
o
n
i
n
c
h
e
s
t
X
-
r
a
y
i
mag
e
s
,
”
Ap
p
l
i
e
d
S
c
i
e
n
c
e
s
,
v
o
l
.
1
1
,
n
o
.
3
,
p
.
1
2
4
2
,
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
1
0
3
1
2
4
2
.
[
1
6
]
M
.
M
a
h
i
n
,
S
.
T
o
n
mo
y
,
R
.
I
sl
a
m,
T
.
T
a
z
i
n
,
M
.
M
.
K
h
a
n
,
a
n
d
S
.
B
o
u
r
o
u
i
s
,
“
C
l
a
ssi
f
i
c
a
t
i
o
n
o
f
C
O
V
I
D
-
1
9
a
n
d
p
n
e
u
mo
n
i
a
u
si
n
g
d
e
e
p
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g,
”
J
o
u
rn
a
l
o
f
H
e
a
l
t
h
c
a
r
e
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
2
0
2
1
,
n
o
.
1
,
p
p
.
1
–
1
1
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
1
/
3
5
1
4
8
2
1
.
[
1
7
]
Y
Y
.
A
r
u
n
a
n
d
G
.
S
.
V
i
k
n
e
sh
,
“
L
e
a
f
c
l
a
ssi
f
i
c
a
t
i
o
n
f
o
r
p
l
a
n
t
r
e
c
o
g
n
i
t
i
o
n
u
s
i
n
g
Ef
f
i
c
i
e
n
t
N
e
t
a
r
c
h
i
t
e
c
t
u
r
e
,
”
2
0
2
2
I
EE
E
F
o
u
r
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
Ad
v
a
n
c
e
s
i
n
El
e
c
t
r
o
n
i
c
s,
C
o
m
p
u
t
e
rs a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
s
(
I
C
AEC
C
)
,
B
e
n
g
a
l
u
r
u
,
I
n
d
i
a
,
2
0
2
2
,
p
p
.
1
-
5
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
A
EC
C
5
4
0
4
5
.
2
0
2
2
.
9
7
1
6
6
3
7
.
[
1
8
]
T
.
T
u
n
c
e
r
,
F
.
Er
t
a
m,
S
.
D
o
g
a
n
,
E
.
A
y
d
e
mi
r
,
a
n
d
P
.
P
l
a
w
i
a
k
,
“
En
se
mb
l
e
r
e
si
d
u
a
l
n
e
t
w
o
r
k
-
b
a
se
d
g
e
n
d
e
r
a
n
d
a
c
t
i
v
i
t
y
r
e
c
o
g
n
i
t
i
o
n
me
t
h
o
d
w
i
t
h
s
i
g
n
a
l
s,
”
T
h
e
J
o
u
r
n
a
l
o
f
S
u
p
e
r
c
o
m
p
u
t
i
n
g
,
v
o
l
.
7
6
,
p
p
.
2
1
1
9
-
2
1
3
8
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
1
2
2
7
-
0
2
0
-
0
3
2
0
5
-
1.
[
1
9
]
P
.
M
o
o
n
e
y
,
“
C
h
e
st
X
-
r
a
y
i
mag
e
s
(
P
n
e
u
mo
n
i
a
)
,
”
K
a
g
g
l
e
,
2
0
1
8
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s:
/
/
w
w
w
.
k
a
g
g
l
e
.
c
o
m/
d
a
t
a
se
t
s/
p
a
u
l
t
i
mo
t
h
y
mo
o
n
e
y
/
c
h
e
st
-
x
r
a
y
-
p
n
e
u
mo
n
i
a
[
2
0
]
N
.
A
r
o
r
a
a
n
d
M
.
M
.
A
b
r
a
h
a
m,
“
Le
v
e
r
a
g
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
f
o
r
f
a
c
e
m
a
sk
d
e
t
e
c
t
i
o
n
,
”
2
0
2
2
F
i
f
t
h
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
a
t
i
o
n
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
T
e
c
h
n
o
l
o
g
i
e
s
(
C
C
I
C
T
)
,
S
o
n
e
p
a
t
,
I
n
d
i
a
,
2
0
2
2
,
p
p
.
4
1
8
-
4
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
C
C
i
C
T
5
6
6
8
4
.
2
0
2
2
.
0
0
0
8
0
.
[
2
1
]
A
.
S
.
Eb
e
n
e
z
e
r
,
S
.
D
.
K
a
n
ma
n
i
,
M
.
S
i
v
a
k
u
m
a
r
,
a
n
d
S
.
J
.
P
r
i
y
a
,
“
Ef
f
e
c
t
o
f
i
mag
e
t
r
a
n
sf
o
r
mat
i
o
n
o
n
Ef
f
i
c
i
e
n
t
N
e
t
mo
d
e
l
f
o
r
C
O
V
I
D
-
1
9
C
T
i
m
a
g
e
c
l
a
ssi
f
i
c
a
t
i
o
n
,
”
M
a
t
e
r
i
a
l
st
o
d
a
y
:
Pr
o
c
e
e
d
i
n
g
s
,
v
o
l
.
5
1
,
p
p
.
2
5
1
2
–
2
5
1
9
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
ma
t
p
r
.
2
0
2
1
.
1
2
.
1
2
1
.
[
2
2
]
M
.
T
a
n
a
n
d
Q
.
V
L
e
,
“
Ef
f
i
c
i
e
n
t
N
e
t
:
R
e
t
h
i
n
k
i
n
g
mo
d
e
l
sc
a
l
i
n
g
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
rX
i
v
:
1
9
0
5
.
1
1
9
4
6
,
2
0
1
9
,
d
o
i
:
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
d
va
n
ce
d
p
n
e
u
mo
n
ia
cl
a
s
s
ific
a
tio
n
u
s
in
g
tr
a
n
s
fer lea
r
n
in
g
o
n
ch
est X
-
r
a
y
d
a
t
a
…
(
Green
A
r
th
er
S
a
n
d
a
g
)
1313
1
0
.
4
8
5
5
0
/
a
r
X
i
v
.
1
9
0
5
.
1
1
9
4
6
.
[
2
3
]
S
.
A
.
H
a
san
a
h
,
A
.
A
.
P
r
a
v
i
t
a
sar
i
,
A
.
S
.
A
b
d
u
l
l
a
h
,
I
.
N
.
Y
u
l
i
t
a
,
a
n
d
M
.
H
.
A
sn
a
w
i
,
“
A
d
e
e
p
l
e
a
r
n
i
n
g
r
e
v
i
e
w
o
f
R
e
s
N
e
t
a
r
c
h
i
t
e
c
t
u
r
e
f
o
r
l
u
n
g
d
i
se
a
se
i
d
e
n
t
i
f
i
c
a
t
i
o
n
i
n
C
X
R
i
mag
e
,
”
Ap
p
l
i
e
d
S
c
i
e
n
c
e
s
,
v
o
l
.
1
3
,
n
o
.
2
4
,
p
.
1
3
1
1
1
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
3
2
4
1
3
1
1
1
.
[
2
4
]
C
.
O
.
T
o
r
o
,
A
.
G
.
P
e
d
r
e
r
o
,
M
.
L
.
S
a
a
v
e
d
r
a
,
a
n
d
C
.
G
.
M
a
r
t
í
n
,
“
A
u
t
o
mat
i
c
d
e
t
e
c
t
i
o
n
o
f
p
n
e
u
mo
n
i
a
i
n
c
h
e
st
X
-
r
a
y
i
mag
e
s
u
si
n
g
t
e
x
t
u
r
a
l
f
e
a
t
u
r
e
s,
”
C
o
m
p
u
t
e
rs
i
n
Bi
o
l
o
g
y
a
n
d
Me
d
i
c
i
n
e
,
.
El
se
v
i
e
r
,
v
o
l
.
1
4
5
,
p
.
1
0
5
4
6
6
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
mp
b
i
o
me
d
.
2
0
2
2
.
1
0
5
4
6
6
.
[
2
5
]
S
.
S
o
o
mr
o
,
A
.
N
i
a
z
a
n
d
K
.
N
a
m
C
h
o
i
,
“
G
r
a
d
+
+
S
c
o
r
e
C
A
M
:
En
h
a
n
c
i
n
g
v
i
s
u
a
l
e
x
p
l
a
n
a
t
i
o
n
s
o
f
d
e
e
p
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
t
w
o
r
k
s
u
si
n
g
i
n
c
r
e
me
n
t
e
d
g
r
a
d
i
e
n
t
a
n
d
sco
r
e
-
w
e
i
g
h
t
e
d
me
t
h
o
d
s,
”
in
I
E
EE
Ac
c
e
ss
,
v
o
l
.
1
2
,
p
p
.
6
1
1
0
4
-
6
1
1
1
2
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
4
.
3
3
9
2
8
5
3
.
[
2
6
]
L
.
V
i
su
ñ
a
,
D
.
Y
a
n
g
,
J
.
G
.
B
l
a
s,
a
n
d
J.
C
a
r
r
e
t
e
r
o
,
“
C
o
mp
u
t
e
r
-
a
i
d
e
d
d
i
a
g
n
o
st
i
c
f
o
r
c
l
a
ssi
f
y
i
n
g
c
h
e
st
X
-
r
a
y
i
mag
e
s
u
s
i
n
g
d
e
e
p
e
n
se
mb
l
e
l
e
a
r
n
i
n
g
,
”
B
MC
M
e
d
.
I
m
a
g
i
n
g
,
v
o
l
.
2
2
,
n
o
.
1
,
p
p
.
1
–
1
7
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
8
6
/
s
1
2
8
8
0
-
0
2
2
-
0
0
9
0
4
-
4.
[
2
7
]
N
.
E.
R
a
ml
i
,
Z
.
R
.
Y
a
h
y
a
,
a
n
d
N
.
A
.
S
a
i
d
,
“
C
o
n
f
u
si
o
n
mat
r
i
x
a
s p
e
r
f
o
r
man
c
e
me
a
su
r
e
f
o
r
c
o
r
n
e
r
d
e
t
e
c
t
o
r
s,
”
J
o
u
rn
a
l
o
f
A
d
v
a
n
c
e
d
Re
se
a
rc
h
i
n
A
p
p
l
i
e
d
S
c
i
e
n
c
e
s
a
n
d
E
n
g
i
n
e
e
ri
n
g
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
2
9
,
n
o
.
1
,
2
0
2
2
,
d
o
i
:
1
0
.
3
7
9
3
4
/
a
r
a
se
t
.
2
9
.
1
.
2
5
6
2
6
5
.
[
2
8
]
S
.
K
a
l
g
u
t
k
a
r
e
t
a
l
.,
“
P
n
e
u
mo
n
i
a
d
e
t
e
c
t
i
o
n
f
r
o
m
c
h
e
st
X
-
r
a
y
u
si
n
g
t
r
a
n
s
f
e
r
l
e
a
r
n
i
n
g
,
”
2
0
2
1
6
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
f
o
r
C
o
n
v
e
rg
e
n
c
e
i
n
T
e
c
h
n
o
l
o
g
y
(
I
2
C
T
)
,
M
a
h
a
r
a
s
h
t
r
a
,
I
n
d
i
a
,
2
0
2
1
,
p
p
.
1
-
6
,
d
o
i
:
1
0
.
1
1
0
9
/
I
2
C
T
5
1
0
6
8
.
2
0
2
1
.
9
4
1
7
8
7
2
.
[
2
9
]
R
.
C
h
a
t
t
e
r
j
e
e
,
A
.
C
h
a
t
t
e
r
j
e
e
,
a
n
d
R
.
H
a
l
d
e
r
,
“
A
n
e
f
f
i
c
i
e
n
t
p
n
e
u
mo
n
i
a
d
e
t
e
c
t
i
o
n
f
r
o
m
t
h
e
C
h
e
st
X
-
R
a
y
i
m
a
g
e
s
,
”
Pr
o
c
e
e
d
i
n
g
s
o
f
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
M
a
c
h
i
n
e
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
D
a
t
a
S
c
i
e
n
c
e
A
p
p
l
i
c
a
t
i
o
n
s
,
S
p
r
i
n
g
e
r
,
S
i
n
g
a
p
o
r
e
,
p
p
.
7
7
9
-
7
8
9
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
981
-
33
-
4
0
8
7
-
9
_
6
3
.
[
3
0
]
G
.
L
.
E
.
M
.
N
i
ñ
o
,
J
.
G
.
N
.
F
e
r
n
a
n
d
e
z
,
F
.
Y
.
T
.
C
a
l
d
e
r
o
n
,
I
.
A
.
O
l
a
n
o
,
P
.
D
.
L
.
C
r
u
z
,
a
n
d
G
.
C
.
B
a
r
c
o
,
“
C
l
a
ss
i
f
i
c
a
t
i
o
n
mo
d
e
l
u
s
i
n
g
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
f
o
r
t
h
e
d
e
t
e
c
t
i
o
n
o
f
p
n
e
u
mo
n
i
a
i
n
c
h
e
s
t
X
-
R
a
y
i
mag
e
s
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
O
n
l
i
n
e
a
n
d
Bi
o
m
e
d
i
c
a
l
En
g
i
n
e
e
ri
n
g
(
i
J
O
E)
,
v
o
l
.
2
0
,
n
o
.
5
,
p
p
.
1
5
0
–
1
6
1
,
M
a
r
.
2
0
2
4
,
d
o
i
:
1
0
.
3
9
9
1
/
i
j
o
e
.
v
2
0
i
0
5
.
4
5
2
7
7
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
G
r
e
e
n
Ar
t
h
e
r
S
a
n
d
a
g
re
c
e
iv
e
d
a
Ba
c
h
e
lo
r
’
s
d
e
g
re
e
in
C
o
m
p
u
ter
S
c
ien
c
e
f
ro
m
Un
iv
e
rsitas
Kla
b
a
t,
A
irma
d
id
i,
In
d
o
n
e
sia
,
in
2
0
1
2
,
a
n
d
a
M
a
ste
r
’
s d
e
g
re
e
in
C
o
m
p
u
ter
S
c
ien
c
e
f
ro
m
Yu
a
n
Ze Un
iv
e
rsity
,
T
a
o
y
u
a
n
,
T
a
iw
a
n
,
in
2
0
1
6
.
S
i
n
c
e
A
u
g
u
st 2
0
1
6
,
h
e
h
a
s
b
e
e
n
w
o
rk
in
g
a
s
a
lec
tu
re
r
a
t
Un
iv
e
rsita
s
Kl
a
b
a
t,
A
ir
m
a
d
id
i,
In
d
o
n
e
sia
.
His
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
c
o
m
p
u
ter
v
isio
n
a
n
d
n
a
tu
ra
l
lan
g
u
a
g
e
p
ro
c
e
ss
in
g
,
w
it
h
a
p
a
rti
c
u
lar
f
o
c
u
s
o
n
to
p
ics
su
c
h
a
s
se
n
ti
m
e
n
t
a
n
a
l
y
sis,
e
m
o
ti
o
n
c
las
sif
ica
ti
o
n
,
a
n
d
im
a
g
e
c
las
si
f
ica
ti
o
n
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
g
re
e
n
sa
n
d
a
g
@u
n
k
lab
.
a
c
.
id
.
Ti
m
o
t
h
y
J
.
M
u
la
li
n
d
a
w
a
s
b
o
rn
i
n
Bit
u
n
g
o
n
No
v
e
m
b
e
r
3
0
,
2
0
0
3
.
A
f
t
e
r
c
o
m
p
letin
g
se
c
o
n
d
a
r
y
e
d
u
c
a
ti
o
n
,
c
o
n
ti
n
u
e
d
u
n
d
e
rg
ra
d
u
a
te
stu
d
i
e
s
a
t
Un
iv
e
rsitas
Kla
b
a
t,
f
o
c
u
sin
g
o
n
in
f
o
rm
a
ti
c
s.
Du
rin
g
th
e
ir
ti
m
e
a
s
a
stu
d
e
n
t,
th
e
y
lea
rn
e
d
e
x
ten
siv
e
l
y
a
n
d
e
n
h
a
n
c
e
d
th
e
ir
sk
il
ls
i
n
tec
h
n
o
l
o
g
y
a
n
d
s
o
f
tw
a
r
e
d
e
v
e
lo
p
m
e
n
t.
T
h
e
y
p
a
rti
c
ip
a
ted
in
v
a
rio
u
s
p
ro
jec
ts
a
n
d
a
c
ti
v
it
ies
re
late
d
to
tec
h
n
o
l
o
g
y
,
f
u
rth
e
r
stre
n
g
th
e
n
i
n
g
th
e
ir
a
b
il
it
i
e
s
in
t
h
e
f
ield
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
s2
2
0
0
0
5
6
@s
t
u
d
e
n
t
.
u
n
k
lab
.
a
c
.
id
.
G
lo
r
ia
A.
M
.
S
u
sa
n
t
o
wa
s
b
o
rn
i
n
M
a
n
a
d
o
o
n
A
u
g
u
st
1
5
,
2
0
0
2
.
A
f
t
e
r
c
o
m
p
letin
g
se
c
o
n
d
a
ry
e
d
u
c
a
ti
o
n
,
sh
e
p
u
rs
u
e
d
a
n
u
n
d
e
rg
ra
d
u
a
te
d
e
g
re
e
a
t
Un
iv
e
rsitas
Kla
b
a
t,
f
o
c
u
sin
g
o
n
In
f
o
rm
a
ti
c
s
.
Du
rin
g
h
e
r
c
o
ll
e
g
e
y
e
a
rs,
sh
e
d
e
d
ica
ted
sig
n
if
ica
n
t
ti
m
e
to
stu
d
y
in
g
a
n
d
h
o
n
i
n
g
h
e
r
sk
il
ls
in
tec
h
n
o
lo
g
y
a
n
d
so
f
twa
re
d
e
v
e
lo
p
m
e
n
t.
S
h
e
b
e
li
e
v
e
s
th
a
t
th
e
e
d
u
c
a
ti
o
n
sh
e
h
a
s
re
c
e
iv
e
d
w
il
l
p
ro
v
id
e
a
stro
n
g
f
o
u
n
d
a
ti
o
n
f
o
r
h
e
r
c
a
re
e
r
i
n
th
e
tec
h
i
n
d
u
stry
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
s2
2
0
0
0
5
7
@s
tu
d
e
n
t
.
u
n
k
lab
.
a
c
.
id
.
S
te
n
ly
R.
Pu
n
g
u
s
De
a
n
a
n
d
L
e
c
tu
re
r
in
t
h
e
C
o
m
p
u
ter
S
c
ien
c
e
F
a
c
u
lt
y
a
t
Kla
b
a
t
Un
iv
e
rsit
y
,
A
ir
m
a
d
id
i,
M
a
n
a
d
o
.
He
h
o
ld
s
a
P
h
.
D
.
i
n
Da
ta
M
o
d
e
ll
i
n
g
f
ro
m
th
e
Na
ti
o
n
a
l
Un
iv
e
rsit
y
o
f
M
a
la
y
sia
,
w
h
e
r
e
h
is
re
se
a
rc
h
f
o
c
u
se
d
o
n
a
d
v
a
n
c
e
d
tec
h
n
i
q
u
e
s f
o
r
stru
c
tu
r
in
g
a
n
d
a
n
a
ly
z
in
g
c
o
m
p
lex
d
a
ta
s
y
ste
m
s.
He
is
a
lso
a
n
a
lu
m
n
u
s
o
f
th
e
M
a
ste
r
’
s
p
ro
g
ra
m
in
S
o
f
t
w
a
re
En
g
in
e
e
rin
g
f
ro
m
th
e
Ba
n
d
u
n
g
In
stit
u
te
o
f
T
e
c
h
n
o
l
o
g
y
a
n
d
h
o
l
d
a
M
a
ste
r
’
s
d
e
g
re
e
in
M
a
n
a
g
e
m
e
n
t
f
ro
m
Kla
b
a
t
Un
iv
e
rsity
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
ste
n
ly
.
p
u
n
g
u
s@
u
n
k
lab
.
a
c
.
i
d
.
Evaluation Warning : The document was created with Spire.PDF for Python.