I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
pu
t
er
Science
Vo
l.
3
7
,
No
.
2
,
Feb
r
u
ar
y
20
2
5
,
p
p
.
948
~
958
I
SS
N:
2
502
-
4
7
52
,
DOI
: 1
0
.
1
1
5
9
1
/ijee
cs
.v
3
7
.
i
2
.
pp
948
-
9
5
8
948
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs
.
ia
esco
r
e.
co
m
Dete
c
t
a
nd
env
isio
n of pand
emic
di
sea
se ex
po
sure
us
ing
CNN
Ch
.
Rupa
1
,
K
a
na
k
a
m
Siv
a
R
a
m
a
P
ra
s
a
d
2
,
Are
m
a
nd
a
L
a
k
s
hm
i R
a
j
eswa
ri
2
,
E
lik
a
Sa
m
ba
s
iv
a
Ra
o
2
,
M
o
ha
m
ma
d Sira
j
ud
din
3
1
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
S
i
d
d
h
a
r
t
h
a
A
c
a
d
e
m
y
o
f
H
i
g
h
e
r
Ed
u
c
a
t
i
o
n
(
D
e
e
me
d
t
o
b
e
U
n
i
v
e
r
si
t
y
)
,
V
i
j
a
y
a
w
a
d
a
,
I
n
d
i
a
2
D
e
p
a
r
t
me
n
t
o
f
C
S
E
(
A
I
&
M
L)
,
K
a
l
l
a
m H
a
r
a
n
a
d
h
a
r
e
d
d
y
I
n
st
i
t
u
t
e
o
f
T
e
c
h
n
o
l
o
g
y
(
A
u
t
o
n
o
m
o
u
s)
,
G
u
n
t
u
r
,
I
n
d
i
a
3
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
mat
i
o
n
Te
c
h
n
o
l
o
g
y
,
K
a
l
l
a
m H
a
r
a
n
a
d
h
a
r
e
d
d
y
I
n
st
i
t
u
t
e
o
f
Te
c
h
n
o
l
o
g
y
(
A
u
t
o
n
o
mo
u
s)
,
G
u
n
t
u
r
,
I
n
d
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
May
13
,
2
0
2
4
R
ev
is
ed
Sep
15
,
2
0
2
4
Acc
ep
ted
Sep
30
,
2
0
2
4
COV
ID
-
1
9
h
a
s
e
m
e
rg
e
d
a
s
a
p
a
n
d
e
m
ic,
a
ffe
c
ti
n
g
m
il
li
o
n
s
g
l
o
b
a
l
ly
with
it
s
h
ig
h
tran
sm
issio
n
ra
te,
e
sp
e
c
ially
in
c
o
l
d
e
r
c
li
m
a
tes
.
Th
e
v
iru
s'
s
m
u
lt
ip
le
m
u
tatio
n
s
h
a
v
e
m
a
d
e
it
p
ro
g
re
ss
i
v
e
ly
h
a
rd
e
r
to
d
e
tec
t
a
n
d
m
a
n
a
g
e
.
De
sp
it
e
wid
e
sp
re
a
d
a
wa
re
n
e
ss
o
f
p
re
v
e
n
t
iv
e
m
e
a
su
re
s
su
c
h
a
s
m
a
sk
s
a
n
d
sa
n
it
ize
rs,
e
a
rly
d
e
tec
ti
o
n
re
m
a
in
s
c
rit
ica
l.
Trad
it
i
o
n
a
l
m
e
th
o
d
s
li
k
e
b
l
o
o
d
tes
ts
a
re
ti
m
e
-
c
o
n
su
m
in
g
,
a
n
d
e
x
isti
n
g
st
u
d
ies
u
ti
l
izin
g
f
u
z
z
y
K
-
m
e
a
n
s
c
lu
ste
rin
g
,
p
rin
c
i
p
a
l
c
o
m
p
o
n
e
n
t
a
n
a
l
y
sis
(P
CA),
sto
c
h
a
stic
d
isc
rimin
a
n
t
a
n
a
ly
si
s
(S
DA
)
,
d
e
c
isio
n
tree
s
(DT)
,
a
n
d
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
s
(
S
VM
)
h
a
v
e
fa
c
e
d
li
m
it
a
ti
o
n
s,
in
c
l
u
d
i
n
g
sm
a
ll
d
a
tas
e
ts,
in
su
fficie
n
t
a
c
c
u
ra
c
y
,
i
n
a
d
e
q
u
a
t
e
m
e
d
ica
l
d
a
ta,
we
a
k
m
e
th
o
d
o
l
o
g
ies
,
a
n
d
fa
il
u
re
to
c
o
n
sid
e
r
p
rima
ry
sy
m
p
to
m
s.
Th
is
wo
r
k
p
ro
p
o
se
s
a
d
e
e
p
lea
rn
in
g
(DL)
c
o
n
v
o
lu
ti
o
n
a
l
n
e
u
ra
l
n
e
two
rk
(
CNN
)
a
rc
h
it
e
c
tu
re
u
ti
l
i
z
in
g
CT
sc
a
n
ima
g
e
s
o
f
th
e
lu
n
g
s
fo
r
th
e
ra
p
id
a
n
d
a
c
c
u
ra
te
i
d
e
n
ti
fica
ti
o
n
o
f
COV
ID
-
1
9
in
fe
c
ti
o
n
s.
Th
e
a
p
p
r
o
a
c
h
lev
e
ra
g
e
s
th
e
Visu
a
l
G
e
o
m
e
try
G
ro
u
p
1
6
(
VG
G
1
6
)
m
o
d
e
l
to
e
x
trac
t
sig
n
ifi
c
a
n
t
fe
a
tu
re
s,
su
c
h
a
s
siz
e
a
n
d
c
o
lo
r
d
iffere
n
c
e
s,
fro
m
c
o
m
p
u
te
d
to
m
o
g
ra
p
h
y
(
CT
)
sc
a
n
ima
g
e
s,
fa
c
il
it
a
ti
n
g
a
sw
ift
a
n
d
p
re
c
ise
d
iag
n
o
sis.
Th
e
VG
G
1
6
m
o
d
e
l,
imp
lem
e
n
ted
u
si
n
g
t
h
e
Ke
ra
s
li
b
ra
ry
o
n
to
p
o
f
Te
n
so
rF
l
o
w,
p
ro
c
e
ss
e
s
th
e
p
re
p
r
o
c
e
ss
e
d
ima
g
e
s
th
r
o
u
g
h
n
e
u
ra
l
n
e
two
r
k
la
y
e
rs
t
o
c
las
sif
y
th
e
ima
g
e
s
a
s
COV
I
D
-
1
9
p
o
s
it
iv
e
o
r
n
e
g
a
ti
v
e
.
T
h
e
p
ro
p
o
s
e
d
m
o
d
e
l
d
e
m
o
n
stra
tes
a
h
i
g
h
a
c
c
u
ra
c
y
ra
t
e
o
f
9
4
.
1
2
%
,
in
d
ica
ti
n
g
t
h
a
t
th
is
m
e
th
o
d
is
b
o
t
h
e
fficie
n
t
a
n
d
re
li
a
b
le
fo
r
d
e
tec
ti
n
g
COV
ID
-
1
9
,
o
ffe
ri
n
g
a
sig
n
ifi
c
a
n
t
imp
ro
v
e
m
e
n
t
o
v
e
r
c
o
n
v
e
n
ti
o
n
a
l
d
iag
n
o
stic
tec
h
n
i
q
u
e
s a
n
d
e
x
isti
n
g
stu
d
ies
.
K
ey
w
o
r
d
s
:
C
o
n
v
o
lu
tio
n
n
eu
r
al
n
etwo
r
k
C
OVI
D
-
19
CT
-
Scan
T
en
s
o
r
Flo
w
VGG
-
16
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
:
C
h
.
R
u
p
a
Dep
ar
tm
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
an
d
E
n
g
in
ee
r
in
g
,
Sid
d
h
ar
t
h
a
Aca
d
em
y
o
f
Hig
h
e
r
E
d
u
ca
tio
n
(
Dee
m
ed
to
b
e
Un
iv
er
s
ity
)
Vijay
awa
d
a,
An
d
h
r
a
Pra
d
esh
,
I
n
d
ia
E
m
ail: r
u
p
am
tech
@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
C
OVI
D
-
1
9
p
an
d
em
ic,
w
h
ich
b
eg
an
in
W
u
h
an
,
C
h
in
a
in
Dec
em
b
er
2
0
1
9
,
h
as
s
p
r
ea
d
g
lo
b
ally
,
in
f
ec
tin
g
o
v
er
2
3
m
illi
o
n
p
eo
p
le,
with
ar
o
u
n
d
1
6
m
illi
o
n
r
ec
o
v
er
ies
an
d
0
.
8
m
illi
o
n
d
ea
th
s
[
1
]
-
[
5
]
.
T
h
e
d
is
ea
s
e
is
h
ig
h
ly
co
n
ta
g
io
u
s
,
tr
an
s
m
itted
th
r
o
u
g
h
h
u
m
an
in
ter
ac
tio
n
,
co
u
g
h
in
g
,
a
n
d
s
n
ee
zin
g
[
6
]
,
[
7
]
.
C
o
m
m
o
n
s
y
m
p
to
m
s
in
clu
d
e
f
ev
er
,
co
u
g
h
,
r
esp
ir
ato
r
y
is
s
u
es,
an
d
lo
s
s
o
f
s
en
s
es,
ty
p
ically
ap
p
ea
r
i
n
g
5
t
o
1
4
d
a
y
s
a
f
t
e
r
e
x
p
o
s
u
r
e
.
I
n
f
e
c
t
e
d
i
n
d
i
v
i
d
u
a
l
s
n
e
e
d
t
o
b
e
i
s
o
l
a
t
e
d
f
o
r
a
t
l
e
a
s
t
t
w
o
w
e
e
k
s
u
n
d
e
r
m
e
d
i
c
a
l
s
u
p
e
r
v
i
s
i
o
n
[
8
]
.
T
h
e
p
an
d
em
ic
h
as
led
to
s
ev
er
e
ec
o
n
o
m
ic
cr
is
es
wo
r
ld
wid
e.
Sin
ce
n
o
v
ac
cin
e
is
av
ail
ab
le,
p
r
ev
en
tio
n
is
cr
itical
[
9
]
,
[
1
0
]
.
T
h
e
ab
s
en
c
e
o
f
an
au
to
m
ate
d
C
OVI
D
-
1
9
d
iag
n
o
s
is
p
r
o
ce
s
s
d
u
r
in
g
p
an
d
em
ic
lead
s
to
s
ig
n
if
ican
t c
h
allen
g
es f
o
r
b
o
t
h
m
ed
ical
p
er
s
o
n
s
an
d
p
atien
ts
[
1
1
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
Dete
ct
a
n
d
en
visi
o
n
o
f p
a
n
d
e
mic
d
is
ea
s
e
ex
p
o
s
u
r
e
u
s
in
g
C
N
N
(
C
h
.
R
u
p
a
)
949
E
x
is
tin
g
s
tu
d
ies
th
at
e
m
p
lo
y
tech
n
i
q
u
es
lik
e
f
u
zz
y
K
-
m
ea
n
s
clu
s
ter
in
g
,
p
r
in
cip
al
co
m
p
o
n
en
t
an
aly
s
is
(
PC
A)
,
s
to
ch
asti
c
d
i
s
cr
im
in
an
t
an
aly
s
is
(
SDA)
,
d
ec
is
io
n
tr
ee
s
(
DT
)
,
an
d
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
es
(
SVM)
h
av
e
en
c
o
u
n
ter
e
d
s
ig
n
if
ican
t
ch
allen
g
es.
T
h
ese
ex
i
s
tin
g
tech
n
iq
u
es
u
s
ed
s
m
aller
d
atasets
lead
in
g
to
lo
w
ac
cu
r
ac
y
,
an
d
th
e
u
s
e
o
f
in
s
u
f
f
icien
t
m
ed
ical
d
ata
th
at
d
o
es
n
o
t
f
u
lly
ca
p
tu
r
e
p
atien
t
co
n
d
itio
n
s
.
T
h
ese
s
h
o
r
tco
m
in
g
s
h
ig
h
lig
h
t
th
e
n
ee
d
f
o
r
im
p
r
o
v
ed
m
eth
o
d
o
lo
g
ies
an
d
lar
g
er
,
m
o
r
e
co
m
p
r
eh
en
s
iv
e
d
atasets
to
en
h
an
ce
th
e
r
eliab
ilit
y
an
d
ef
f
ec
tiv
en
ess
o
f
m
ed
ical
d
iag
n
o
s
tics
.
Au
to
m
atin
g
C
OVI
D
-
1
9
test
in
g
th
r
o
u
g
h
a
d
v
an
ce
d
tech
n
o
lo
g
ies,
in
clu
d
in
g
d
ee
p
lear
n
in
g
(
DL
)
an
d
co
n
v
o
l
u
tio
n
al
n
eu
r
al
n
etwo
r
k
s
(
C
NNs),
ca
n
e
n
h
an
ce
th
e
ac
cu
r
ac
y
a
n
d
s
p
ee
d
u
p
d
i
ag
n
o
s
is
p
r
o
ce
s
s
b
y
u
s
in
g
co
m
p
u
ted
to
m
o
g
r
a
p
h
y
(
CT
)
s
ca
n
im
ag
es.
T
h
is
k
i
n
d
o
f
ap
p
r
o
ac
h
r
ed
u
ce
s
h
u
m
an
in
te
r
v
en
tio
n
an
d
er
r
o
r
s
in
d
iag
n
o
s
is
p
r
o
ce
s
s
.
Ad
v
a
n
c
ed
tech
n
o
lo
g
ies
s
u
ch
as
C
NN
s
an
d
Vis
u
al
Geo
m
etr
y
Gr
o
u
p
1
6
(
VGG1
6
)
ar
e
b
ein
g
u
tili
ze
d
to
s
ca
n
th
e
C
T
im
ag
es
o
f
lu
n
g
s
f
o
r
d
etec
tin
g
C
OVI
D
-
1
9
.
C
NNs
ar
e
h
ig
h
ly
ef
f
ec
tiv
e
i
n
im
ag
e
p
r
o
ce
s
s
in
g
task
s
d
u
e
to
th
eir
ab
ilit
y
to
au
to
m
atica
lly
a
n
d
ad
ap
tiv
ely
lea
r
n
s
p
atial
h
ier
ar
ch
ies o
f
f
ea
tu
r
es
f
r
o
m
in
p
u
t im
ag
es.
VGG1
6
,
a
s
p
ec
if
ic
d
ee
p
co
n
v
o
lu
tio
n
al
n
e
two
r
k
ar
ch
itectu
r
e,
is
r
en
o
wn
e
d
f
o
r
its
s
im
p
licity
an
d
d
e
p
th
,
m
ak
in
g
it
p
ar
ticu
lar
ly
well
-
s
u
ited
f
o
r
t
h
e
cl
ass
if
icatio
n
o
f
co
m
p
lex
im
a
g
es.
B
y
em
p
lo
y
in
g
th
ese
tech
n
o
lo
g
ies,
th
e
p
r
o
p
o
s
ed
s
y
s
tem
ca
n
a
n
aly
ze
l
u
n
g
C
T
s
ca
n
s
with
h
ig
h
ac
cu
r
ac
y
,
e
n
ab
lin
g
q
u
ick
an
d
r
eliab
le
C
OVI
D
-
1
9
d
iag
n
o
s
is
d
ea
lin
g
th
e
d
r
awb
ac
k
s
o
f
ex
is
tin
g
s
tu
d
ies.
DL
m
o
d
els
tr
ain
ed
o
n
lar
g
e
d
atasets
o
f
C
T
s
ca
n
im
ag
es
ca
n
au
to
m
atica
lly
an
d
ac
c
u
r
ately
d
etec
t
C
OVI
D
-
1
9
r
elate
d
ab
n
o
r
m
alities
in
th
e
lu
n
g
s
.
Su
ch
m
o
d
els
n
o
t
o
n
ly
s
p
ee
d
u
p
th
e
d
iag
n
o
s
is
p
r
o
ce
s
s
b
u
t
also
im
p
r
o
v
e
p
atien
t o
u
tco
m
es.
T
h
e
m
ain
c
o
n
tr
ib
u
tio
n
s
o
f
th
is
wo
r
k
is
as f
o
llo
ws
:
−
An
aly
ze
an
d
ass
ess
th
e
im
p
ac
t o
f
p
a
n
d
em
ic
d
is
ea
s
es,
p
ar
ticu
lar
ly
f
o
cu
s
in
g
o
n
C
OVI
D
-
1
9
v
ar
ian
ts
.
−
Desig
n
a
s
y
s
tem
to
ef
f
icien
tly
d
etec
t COVI
D
-
1
9
p
atien
ts
u
s
in
g
C
T
s
ca
n
im
ag
es.
−
I
m
p
lem
en
t a
C
NN
an
d
VGG1
6
to
p
r
e
d
ict
C
OVI
D
-
1
9
ca
s
es f
r
o
m
C
T
s
ca
n
im
ag
es.
−
T
est th
e
s
y
s
tem
to
en
s
u
r
e
its
ef
f
ec
tiv
en
ess
an
d
ac
cu
r
ac
y
in
i
d
en
tify
in
g
C
OVI
D
-
19
ca
s
es.
T
h
e
s
tr
u
ctu
r
e
o
f
t
h
e
p
ap
er
is
as
f
o
llo
ws:
s
ec
tio
n
2
s
tates
th
e
r
elate
d
wo
r
k
with
a
s
u
m
m
ar
y
ta
b
le.
Pro
p
o
s
ed
m
eth
o
d
o
lo
g
y
is
ad
d
r
ess
ed
in
s
ec
tio
n
3
,
wh
ich
in
clu
d
es
d
ataset
p
r
ep
ar
atio
n
,
p
r
ep
r
o
ce
s
s
,
f
ea
tu
r
e
ex
tr
ac
tio
n
,
a
n
d
DL
m
o
d
el
d
e
v
elo
p
m
en
t.
Sectio
n
4
p
r
esen
ts
th
e
r
esu
lts
an
d
an
aly
s
is
,
in
cl
u
d
in
g
b
o
th
tr
ain
in
g
an
d
test
in
g
o
u
tc
o
m
es.
Fin
ally
,
s
ec
tio
n
5
co
n
tain
s
th
e
c
o
n
clu
s
i
o
n
.
2.
RE
L
AT
E
D
WO
RK
Pas
in
an
d
Go
n
en
c
[
1
2
]
p
r
o
p
o
s
ed
a
s
y
s
tem
th
at
m
ain
ly
f
o
cu
s
es
o
n
au
to
m
atic
id
en
tifi
ca
tio
n
o
f
ef
f
ec
ted
co
u
n
tr
ies
with
th
e
C
OVI
D
-
1
9
p
an
d
em
ic
u
s
in
g
f
u
zz
y
K
-
m
ea
n
s
an
d
K
-
p
r
o
to
ty
p
e
al
g
o
r
ith
m
s
.
T
h
e
lim
itatio
n
o
f
th
is
wo
r
k
is
its
in
ab
ilit
y
to
p
r
ed
ict
th
e
d
is
ea
s
e.
Sh
v
etco
v
et
a
l.
[
1
3
]
d
e
v
el
o
p
ed
a
m
o
b
ile
ap
p
,
wh
ich
ca
n
b
e
u
s
ed
to
ex
am
i
n
e
th
e
u
s
er
s
b
y
co
n
s
id
er
in
g
th
e
s
p
ec
if
ic
tim
ep
o
in
ts
in
lin
e
with
C
OVI
D
-
1
9
.
T
h
e
m
ain
d
r
aw
b
ac
k
o
f
th
is
s
y
s
tem
is
it
n
eg
lects
p
atien
t
s
y
m
p
to
m
s
f
o
r
m
e
n
tal
an
d
p
h
y
s
ical
h
ea
lth
m
o
n
ito
r
in
g
.
T
h
e
wo
r
k
p
r
o
p
o
s
ed
b
y
Sch
ei
m
et
a
l.
[
1
4
]
f
o
cu
s
es
o
n
d
ete
ctin
g
C
OVI
D
-
1
9
th
r
o
u
g
h
h
u
m
an
r
e
d
b
lo
o
d
ce
ll
(
R
B
C
)
im
ag
es
b
y
a
n
aly
zin
g
b
lo
o
d
clo
ts
,
h
y
p
o
x
ia
an
d
m
y
o
c
ar
d
itis
.
C
h
u
et
a
l
.
[
1
5
]
p
r
o
p
o
s
ed
a
n
o
v
el
f
ea
t
u
r
e
s
elec
tio
n
tech
n
iq
u
e
m
in
im
u
m
r
ed
u
n
d
an
cy
m
a
x
im
u
m
r
elev
an
ce
(
m
R
MR
)
p
er
m
u
te
th
at
ca
n
b
e
u
s
ed
to
p
r
e
d
ict
SAR
S
-
C
o
V
-
2
in
f
ec
tio
n
.
T
h
e
m
ain
lim
itatio
n
o
f
th
is
wo
r
k
i
s
its
lo
w
ac
cu
r
ac
y
a
n
d
less
n
u
m
b
er
o
f
in
s
tan
ce
s
wer
e
co
n
s
id
er
e
d
to
tr
ain
an
d
th
e
test
m
o
d
el.
Ar
s
h
a
d
et
a
l
.
[
1
6
]
u
s
ed
DL
b
ased
m
et
h
o
d
s
f
o
r
d
etec
tio
n
o
f
C
OVI
D
-
1
9
.
Me
r
aih
i
et
a
l.
[
1
7
]
d
ea
ls
with
id
en
tific
atio
n
o
f
co
r
o
n
a
v
ir
u
s
u
s
in
g
SVM,
a
n
d
C
NN
m
eth
o
d
s
.
T
h
e
t
ex
t d
ata,
C
h
est X
-
R
ay
,
C
T
s
ca
n
an
d
clin
ical
d
ata
ar
e
u
s
ed
to
o
b
tain
f
ea
tu
r
es a
n
d
d
etec
t c
o
r
o
n
a
v
ir
u
s
.
T
h
e
lim
itatio
n
is
th
at
th
e
s
m
aller
d
ataset
is
u
s
ed
to
tr
ain
th
e
m
o
d
el.
Ad
d
itio
n
ally
,
th
e
m
o
d
el’
s
ac
cu
r
ac
y
is
r
elativ
ely
lo
w
(
6
5
%),
wh
ich
lead
s
to
er
r
o
r
s
in
t
h
e
id
en
tific
atio
n
p
r
o
ce
s
s
.
Pau
l
et
a
l.
[
1
8
]
s
tu
d
ied
,
ex
am
in
ed
a
n
d
an
al
y
ze
d
C
OVI
D
-
1
9
r
elate
d
wo
r
k
s
,
w
h
ich
ar
e
r
elate
d
to
m
ac
h
in
e
lear
n
in
g
(
ML
)
,
ar
tific
ial
in
tellig
en
ce
(
AI
)
an
d
DL
.
T
h
is
wo
r
k
ad
d
r
ess
ed
ty
p
e
s
o
f
d
ata
u
s
ed
b
y
th
e
r
esear
c
h
er
s
,
tech
n
iq
u
es
an
d
s
ize
o
f
d
atasets
.
Z
o
ab
i
et
a
l
.
[
1
9
]
p
r
o
p
o
s
ed
a
s
y
s
tem
to
d
et
ec
t
th
e
C
OVI
D
-
1
9
ca
s
es
in
th
e
n
atio
n
al
wid
e
o
f
I
s
r
ae
il.
T
h
e
au
th
o
r
s
p
r
o
p
o
s
ed
ML
f
r
am
ewo
r
k
b
y
co
n
s
id
er
in
g
th
e
5
1
,
8
3
1
test
ca
s
es.
T
h
e
m
ain
lim
itatio
n
o
f
th
is
wo
r
k
is
th
e
lack
o
f
d
is
cu
s
s
i
o
n
o
n
ML
tec
h
n
iq
u
es
an
d
wea
k
m
eth
o
d
o
lo
g
y
r
ep
o
r
t.
So
lay
m
an
et
a
l.
[
2
0
]
p
r
o
p
o
s
ed
a
s
y
s
tem
b
ased
o
n
en
s
em
b
le
m
eth
o
d
s
to
p
r
ed
ict
th
e
p
an
d
em
ic
d
is
ea
s
e.
SMOT
E
tech
n
iq
u
e
is
u
s
ed
f
o
r
d
ata
p
r
e
p
r
o
ce
s
s
in
g
.
T
h
e
m
ain
lim
itatio
n
o
f
th
is
wo
r
k
is
th
at
in
co
m
p
lete
m
eth
o
d
o
lo
g
y
,
an
d
n
o
t
co
n
s
id
er
ed
th
e
im
ag
e
d
ata.
R
ash
id
et
a
l.
[
2
1
]
d
is
cu
s
s
ed
th
e
r
o
le
o
f
ML
in
d
iag
n
o
s
is
o
f
p
an
d
em
i
c
d
is
ea
s
e.
T
h
is
wo
r
k
ad
d
r
ess
ed
th
at
av
er
ag
e
ac
cu
r
ac
y
o
f
th
e
task
s
th
r
o
u
g
h
ML
is
9
2
.
9
%.
T
h
e
m
ain
lim
itatio
n
o
f
th
is
wo
r
k
is
lack
o
f
d
is
cu
s
s
io
n
o
n
p
r
ac
tical
im
p
lem
en
tatio
n
s
.
T
ab
le
1
s
u
m
m
ar
izes
th
e
ex
is
tin
g
te
ch
n
iq
u
es
an
d
th
eir
p
er
f
o
r
m
an
ce
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
7
,
No
.
2
,
Feb
r
u
a
r
y
20
2
5
:
9
4
8
-
9
5
8
950
T
ab
le
1
.
Su
m
m
a
r
y
o
f
r
elate
d
wo
r
k
A
u
t
h
o
r
M
e
t
h
o
d
Ty
p
e
o
f
m
o
d
a
l
i
t
y
P
e
r
f
o
r
ma
n
c
e
Ta
sk
V
o
l
u
me
o
f
d
a
t
a
s
e
t
P
a
si
n
a
n
d
G
o
n
e
n
c
.
[
1
2
]
K
-
p
r
o
t
o
t
y
p
e
,
f
u
z
z
y
K
-
m
e
a
n
s
C
l
i
n
i
c
a
l
t
e
s
t
a
n
d
v
a
c
c
i
n
e
s
r
e
p
o
r
t
s
9
6
.
2
%
I
d
e
n
t
i
f
i
e
s
e
f
f
e
c
t
i
n
g
c
o
u
n
t
r
i
e
s
1
0
c
o
u
n
t
r
i
e
s
,
2
c
l
u
st
e
r
s
S
h
v
e
t
c
o
v
et
al
.
[
1
3
]
K
-
m
e
a
n
s
,
P
C
A
,
S
D
A
,
DT
M
e
n
t
a
l
h
e
a
l
t
h
di
a
g
n
o
ses
9
1
%
H
e
a
l
t
h
m
o
n
i
t
o
r
i
n
g
4
0
0
i
n
st
a
n
c
e
s
S
c
h
e
i
m,
e
t
a
l
.
[
1
4
]
N
o
n
-
ML
B
l
o
o
d
c
e
l
l
s
9
6
%
D
i
a
g
n
o
si
s
N
o
t
a
d
d
r
e
ss
e
d
C
h
u
e
t
a
l
.
[
1
5
]
H
y
b
r
i
d
b
l
o
o
d
b
i
o
m
a
r
k
e
r
s a
n
d
r
a
d
i
o
m
i
c
s
8
6
%
P
r
e
d
i
c
t
1
3
7
-
1
7
0
i
n
s
t
a
n
c
e
s
A
r
sh
a
d
e
t
a
l
.
[
1
6
]
DL
C
h
e
st
X
-
r
ay
NA
D
i
a
g
n
o
si
s
N
o
t
s
p
e
c
i
f
i
e
d
M
e
r
a
i
h
i
e
t
a
l
.
[
1
7
]
S
V
M
,
C
N
N
Te
x
t
d
a
t
a
,
C
T
i
ma
g
e
s,
X
-
r
a
y
s,
c
l
i
n
i
c
a
l
d
a
t
a
6
5
%
D
i
a
g
n
o
si
s
,
p
r
e
d
i
c
t
1
6
0
P
a
u
l
e
t
a
l
.
[
1
8
]
M
L,
D
L,
A
I
(
N
o
t
s
p
e
c
i
f
i
e
d
)
Te
x
t
d
a
t
a
,
C
T
i
ma
g
e
s,
X
-
r
a
y
s,
c
l
i
n
i
c
a
l
d
a
t
a
NA
S
u
r
v
e
y
N
o
t
s
p
e
c
i
f
i
e
d
Zo
a
b
i
e
t
a
l
.
[
1
9
]
M
L
(
N
o
t
sp
e
c
i
f
i
e
d
)
N
o
t
s
p
e
c
i
f
i
e
d
9
5
%
D
e
t
e
c
t
5
1
,
8
3
1
S
o
l
a
y
m
a
n
e
t
a
l
.
[
2
0
]
En
se
mb
l
e
Te
x
t
d
a
t
a
9
2
%
P
r
e
d
i
c
t
2
7
4
2
,
5
9
6
R
a
s
h
i
d
e
t
a
l
.
[
2
1
]
ML
(
N
o
t
sp
e
c
i
f
i
e
d
)
N
o
t
s
p
e
c
i
f
i
e
d
9
2
%
S
u
r
v
e
y
1
4
r
e
se
a
r
c
h
a
r
t
i
c
l
e
s
P
r
o
p
o
se
d
m
e
t
h
o
d
VGG
-
16
C
h
e
st
-
CT
9
4
.
1
%
D
i
a
g
n
o
si
s
2
4
8
2
3.
P
RO
P
O
SE
D
M
E
T
H
O
D
As
o
u
r
p
r
o
p
o
s
ed
m
o
d
el
ad
d
r
e
s
s
es
th
e
g
lo
b
al
p
an
d
e
m
ic
is
s
u
e
n
am
ed
C
OVI
D
-
1
9
,
it
s
h
o
u
ld
b
e
tr
ain
ed
with
ap
p
r
o
p
r
iate
d
atasets
to
ac
h
iev
e
h
ig
h
ac
c
u
r
ac
y
in
p
er
f
o
r
m
an
ce
[
2
2
]
.
T
h
e
C
T
s
ca
n
d
ata
s
et
u
s
ed
f
o
r
tr
ain
in
g
th
e
p
r
o
p
o
s
ed
m
o
d
el
is
s
o
u
r
ce
d
f
r
o
m
Ka
g
g
le.
O
u
r
p
r
o
p
o
s
ed
s
y
s
tem
em
p
lo
y
s
VGG1
6
m
o
d
el
th
at
e
x
tr
ac
ts
k
ey
f
ea
tu
r
es
s
u
ch
as
s
ize
an
d
co
lo
u
r
d
if
f
e
r
en
ce
s
in
th
e
s
ca
n
n
e
d
r
ep
o
r
ts
f
r
o
m
th
e
g
iv
e
n
d
ataset
s
[
2
3
]
,
[
2
4
]
.
B
ased
o
n
th
ese
f
ea
t
u
r
es
an
d
s
o
m
e
s
u
b
tle
v
ar
iatio
n
s
,
th
e
m
o
d
el
p
r
ed
icts
wh
eth
er
th
e
in
p
u
t
im
ag
es
ar
e
r
elate
d
to
C
OVI
D
-
1
9
o
r
n
o
t.
T
h
is
in
n
o
v
atio
n
is
d
esig
n
ed
to
allo
w
p
eo
p
le
to
u
p
lo
ad
th
eir
C
T
s
c
an
im
ag
es
in
to
th
e
test
in
g
f
o
ld
er
to
p
r
ed
ict
wh
et
h
er
th
ey
h
a
v
e
C
OVI
D
-
1
9
o
r
n
o
t.
On
ce
th
e
im
ag
e
is
u
p
lo
a
d
ed
,
th
e
n
th
e
m
o
d
e
l
will p
r
e
-
p
r
o
ce
s
s
it to
f
it in
to
it
s
ar
ch
itectu
r
e’
s
s
ize.
3
.
1
.
Da
t
a
s
et
co
llect
i
o
n
T
h
e
d
ataset
co
llected
f
r
o
m
Kag
g
le,
co
n
tain
s
1
,
0
5
0
C
T
s
ca
n
im
ag
es
u
s
ed
to
b
u
ild
a
m
o
d
el
f
o
r
C
OVI
D
-
1
9
d
etec
tio
n
.
I
t
in
clu
d
es
s
ca
n
r
ep
o
r
ts
o
f
b
o
th
C
OVI
D
-
1
9
an
d
n
o
n
-
C
OVI
D
-
1
9
p
atien
ts
as
s
h
o
wn
in
F
ig
u
r
e
1
.
Fig
u
r
e
1
(
a)
d
e
p
icts
non
-
C
OVI
D
-
1
9
C
T
s
ca
n
im
ag
e
an
d
Fig
u
r
e
1
(
b
)
r
ep
r
esen
ts
C
OVI
D
-
1
9
p
o
s
itiv
e
C
T
s
ca
n
im
ag
e.
T
h
e
C
T
s
ca
n
i
m
ag
es
ar
e
o
f
h
u
m
a
n
lu
n
g
s
.
T
h
e
d
ataset
in
clu
d
es 7
0
0
im
ag
es,
with
3
5
0
s
h
o
win
g
C
OVI
D
-
1
9
p
o
s
itiv
e
an
d
3
5
0
s
h
o
win
g
C
OVI
D
-
1
9
n
eg
ativ
e
c
ases
.
(
a)
(
b
)
Fig
u
r
e
1
.
Sam
p
le
im
a
g
es o
f
th
e
d
ataset
(
a)
n
on
-
C
OVI
D
-
19
l
u
n
g
C
T
s
ca
n
an
d
(
b
)
C
OVI
D
-
19
p
o
s
itiv
e
lu
n
g
C
T
s
can
3
.
2
.
P
re
-
pro
ce
s
s
ing
T
h
e
d
ataset
n
ee
d
s
to
b
e
p
r
e
-
p
r
o
ce
s
s
ed
b
ef
o
r
e
ap
p
ly
i
n
g
it
to
t
h
e
m
o
d
el
b
ec
au
s
e
th
e
im
ag
es
co
lo
u
r
o
r
th
e
s
ize
o
f
th
e
im
ag
e
wo
u
ld
b
e
d
if
f
er
e
n
t.
T
h
e
p
r
e
-
p
r
o
ce
s
s
in
g
tech
n
iq
u
e
is
im
p
o
r
tan
t
as
th
er
e
wo
u
ld
b
e
clu
tter
ed
an
d
b
lu
r
im
ag
es.
H
er
e
all
d
i
f
f
er
en
t
s
ize
im
ag
es
ar
e
co
n
v
er
ted
in
to
2
2
4
×2
2
4
p
ix
els
o
f
s
am
e
s
ize
im
ag
es.
T
h
e
o
u
tco
m
e
o
f
th
e
p
r
e
-
p
r
o
ce
s
s
in
g
is
th
e
f
in
al
tr
ain
in
g
s
et.
T
h
e
p
r
e
-
p
r
o
ce
s
s
in
g
s
t
ep
s
ar
e
p
er
f
o
r
m
e
d
b
y
u
s
in
g
Alg
o
r
ith
m
1
.
Alg
o
r
ith
m
1
.
D
ataset
p
r
ep
ar
ati
o
n
Input to the algorithm: Dataset
Output of the algorithm: Processed Dataset
Step 1: Store the Dataset in
Di.
Step 2: Import
Di.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
Dete
ct
a
n
d
en
visi
o
n
o
f p
a
n
d
e
mic
d
is
ea
s
e
ex
p
o
s
u
r
e
u
s
in
g
C
N
N
(
C
h
.
R
u
p
a
)
951
Step 3: Read
Di.
Step 4: Checking cluttered and blurred images from
Di.
Step 5: Store those cluttered and blurred in
Qi.
Step 6: Checking dimension errors in
Di.
Step 7: Store those dimension errors in
Li
.
Step 8: Final Dataset
Si = Di
-
Qi
-
Li.
Ou
r
p
r
o
p
o
s
ed
m
o
d
el
u
s
es
8
0
%
o
f
d
ataset
f
o
r
tr
ain
in
g
an
d
2
0
%
o
f
d
ataset
f
o
r
test
in
g
[
2
5
]
.
T
h
e
p
r
o
p
o
s
ed
m
o
d
el
will
lear
n
f
r
o
m
t
h
e
tr
ain
i
n
g
i
m
ag
es
an
d
p
r
e
d
icts
th
e
o
u
tp
u
t
d
ec
is
io
n
in
th
e
test
in
g
f
o
l
d
er
as
s
h
o
wn
in
Fig
u
r
e
2
.
Fig
u
r
e
2
.
T
r
ain
in
g
a
n
d
test
in
g
s
ets
3
.
3
.
F
e
a
t
ure
ex
t
r
a
ct
io
n
I
n
th
is
s
tep
,
d
esire
d
f
ea
tu
r
es
ar
e
ex
tr
ac
ted
f
r
o
m
th
e
p
r
e
-
p
r
o
c
ess
ed
d
ataset.
I
n
th
is
p
r
o
ce
s
s
,
2
4
8
2
C
T
s
ca
n
im
ag
es
ar
e
an
aly
ze
d
.
As
s
h
o
wn
in
F
ig
u
r
e
3
,
p
eo
p
le
f
ir
s
t
u
p
lo
ad
a
C
T
s
ca
n
im
ag
e,
wh
ich
u
n
d
er
g
o
es
p
r
ep
r
o
ce
s
s
in
g
to
r
em
o
v
e
r
aw
co
n
ten
t.
T
h
e
im
ag
e
is
r
esized
to
2
2
4
×
2
2
4
in
t
h
e
VGG1
6
ar
ch
itectu
r
e.
Key
f
ea
tu
r
es
ar
e
th
en
ex
tr
ac
ted
to
d
eter
m
in
e
if
th
e
p
er
s
o
n
h
as
C
OVI
D
-
1
9
.
I
f
t
ested
with
C
OVI
D
p
o
s
itiv
e,
p
r
ec
a
u
tio
n
s
ar
e
ad
v
i
s
ed
.
T
h
e
d
ataset,
co
n
s
is
tin
g
o
f
lu
n
g
C
T
s
ca
n
r
ep
o
r
ts
co
llected
f
r
o
m
v
a
r
io
u
s
s
o
u
r
ce
s
.
T
h
e
d
ataset
is
th
en
s
p
lit
in
to
th
r
ee
p
a
r
ts
:
tr
ain
in
g
,
v
alid
atio
n
,
a
n
d
test
in
g
s
ets.
T
h
e
n
eu
r
al
n
etwo
r
k
lear
n
s
f
r
o
m
th
e
tr
ain
in
g
d
ata
[
1
0
]
.
T
h
e
tr
ain
in
g
p
ar
t
in
clu
d
e
s
d
if
f
er
en
t
C
NN
lay
er
s
lik
e
c
o
n
v
o
lu
tio
n
lay
er
s
o
f
3
×
3
f
ilter
s
,
p
o
o
lin
g
lay
er
s
o
f
2
×
2
f
ilter
s
,
f
u
lly
co
n
n
ec
ted
lay
er
an
d
S
o
f
t
M
ax
to
class
if
y
th
e
o
u
tp
u
t
(
C
OVI
D
-
1
9
o
r
n
o
n
-
C
OVI
D
-
19
)
.
T
h
e
m
o
d
el
u
s
es
th
e
tr
ain
in
g
d
ata
to
p
r
ed
ict
wh
eth
er
th
e
in
p
u
t
C
T
s
ca
n
in
d
icate
s
C
OVI
D
-
19.
Fig
u
r
e
3
.
Pro
p
o
s
ed
m
et
h
o
d
o
lo
g
y
3
.
4
.
Co
nv
o
lutio
n neura
l net
wo
rk
I
n
DL
,
C
NN
co
m
es
u
n
d
er
d
ee
p
n
eu
r
al
n
etwo
r
k
.
I
t
is
m
o
s
tly
u
s
ed
to
a
n
aly
ze
th
e
im
ag
e
s
.
I
t
is
also
ca
lled
a
s
h
if
t
v
ar
ia
n
t
o
r
s
p
ac
e
in
v
ar
ian
t
ar
tific
ial
n
eu
r
al
n
etwo
r
k
b
ased
o
n
th
eir
ar
ch
itectu
r
e
an
d
ch
ar
ac
ter
is
tics
[
2
6
]
.
C
NN
co
n
tain
s
in
p
u
t
lay
er
,
o
u
tp
u
t
la
y
er
an
d
in
b
etwe
en
s
o
m
e
h
id
d
en
lay
er
s
[
2
7
]
.
I
t
c
o
n
s
i
s
t
s
o
f
f
o
u
r
m
a
i
n
l
a
y
e
r
s
n
a
m
e
l
y
c
o
n
v
o
l
u
t
i
o
n
l
a
y
e
r
,
p
o
o
l
i
n
g
l
a
y
e
r
,
f
u
l
l
y
c
o
n
n
e
c
t
e
d
l
a
y
e
r
a
n
d
S
o
f
t
M
a
x
[
2
8
]
as in
F
ig
u
r
e
4
.
Fig
u
r
e
4
.
VGG1
6
ar
ch
itectu
r
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
7
,
No
.
2
,
Feb
r
u
a
r
y
20
2
5
:
9
4
8
-
9
5
8
952
3.
4
.
1.
Co
nv
o
lutio
n
l
a
y
er
T
h
e
co
n
v
o
l
u
tio
n
la
y
er
i
n
th
e
C
NN
an
aly
ze
s
C
T
s
ca
n
im
ag
es
u
s
in
g
m
u
ltip
le
k
e
r
n
els
th
at
co
v
e
r
th
e
d
ep
th
o
f
in
p
u
t
v
o
lu
m
e
[
2
9
]
.
E
ac
h
k
er
n
el
p
r
o
ce
s
s
es
d
if
f
er
en
t
im
ag
e
p
a
r
ts
b
y
m
u
ltip
ly
in
g
its
v
alu
es
with
co
r
r
esp
o
n
d
in
g
p
ix
el
v
alu
es,
s
u
m
m
in
g
th
em
to
p
r
o
d
u
ce
a
s
in
g
le
v
alu
e
,
ca
lled
th
e
s
ca
lar
p
r
o
d
u
ct
as
illu
s
tr
ate
d
in
F
ig
u
r
e
5
.
T
h
e
k
er
n
el
m
o
v
es
ac
r
o
s
s
th
e
en
tire
im
ag
e
as
s
h
o
wn
in
F
ig
u
r
e
6
,
r
ep
ea
tin
g
th
is
p
r
o
ce
s
s
to
cr
ea
te
a
f
ilter
ed
o
u
tp
u
t
ca
lled
th
e
f
ea
tu
r
e
m
ap
s
h
o
wn
in
Fig
u
r
e
7
.
T
h
e
f
ea
tu
r
e
m
ap
h
ig
h
lig
h
ts
im
p
o
r
tan
t
f
ea
tu
r
es
lik
e
tex
tu
r
e,
ed
g
es,
an
d
an
o
m
alies
in
th
e
C
T
s
ca
n
im
ag
es,
wh
ich
ar
e
cr
u
cial
f
o
r
d
et
ec
tin
g
C
OVI
D
-
19
-
r
elate
d
p
atter
n
s
,
s
u
c
h
as
lu
n
g
ab
n
o
r
m
alities
o
r
s
p
ec
if
ic
r
a
d
io
lo
g
ical
s
ig
n
s
o
f
th
e
v
ir
u
s
,
aid
in
g
i
n
ac
cu
r
ate
d
iag
n
o
s
is
[
3
0
]
.
T
h
e
f
u
n
ctio
n
al
ities
o
f
co
n
v
o
l
u
tio
n
lay
er
ar
e
i
m
p
lem
en
ted
b
y
u
s
in
g
Alg
o
r
ith
m
2
.
Fig
u
r
e
5
.
I
m
ag
e
m
atr
i
x
m
u
ltip
lied
with
f
ilter
m
atr
ix
Fig
u
r
e
6
.
C
o
n
v
o
lv
ed
f
ea
tu
r
e
m
atr
ix
(
C
)
Fig
u
r
e
7
.
3
×
3
co
n
v
o
l
v
ed
f
ea
t
u
r
e
m
atr
ix
(
C
)
Alg
o
r
ith
m
2
.
T
h
e
f
u
n
ctio
n
aliti
es o
f
co
n
v
o
lu
tio
n
lay
er
Input to the algorithm:
Image
Output of the algorithm:
Convolved feature image
Step 1: T
aking the input image from Si.
Step 2: C
onsider it as Image Matrix I
l x b x h
.
Step 3: C
onsider the filter matrix F
fl x fb x h
.
Step 4:
Now perform the operation I x F.
St
ep
5:
St
or
e
th
e
re
s
ul
t
in
Co
nv
ol
ve
Fe
at
ur
e
Ma
p
C
l
x
b
x
h
=
I
x
F
wh
er
e
th
e
di
me
ns
io
n
of
th
e
C is obtained by applying formula C
l
= I
l
–
F
l
+ 1, C
b
= I
b
–
F
b
+1, C
h
= 1.
St
ep
6:
Ne
xt
go
es
to
St
ri
de
,
it
mo
ve
s
th
e
re
qu
ir
ed
nu
mb
er
of
pi
xe
ls
in
th
e
in
pu
t
im
ag
e
matrix I.
St
ep
7:
If
th
e
fi
lt
er
ma
t
ri
x
F
do
es
no
t
fi
t
in
in
p
ut
im
ag
e
ma
tr
ix
,
th
en
pa
d
th
e
im
ag
e
wi
th
additional data A, that can be obtained by using the formula,
=
−
+
2
+
1
.
3
.
4
.
2
.
P
o
o
lin
g
la
y
er
Ma
x
p
o
o
lin
g
s
u
m
m
ar
izes
f
ea
t
u
r
es
lik
e
tex
tu
r
e,
ed
g
es,
an
d
a
n
o
m
alies
in
C
T
s
ca
n
im
ag
es
b
y
s
elec
tin
g
th
e
m
ax
im
u
m
v
alu
e
f
r
o
m
ea
ch
r
e
g
io
n
c
o
v
er
e
d
b
y
a
s
m
aller
p
o
o
lin
g
k
er
n
el
[
3
1
]
.
T
h
is
p
r
o
ce
s
s
r
ed
u
ce
s
th
e
s
p
atial
d
im
en
s
io
n
s
o
f
th
e
f
ea
tu
r
e
m
a
p
s
b
y
ab
o
u
t
h
alf
s
h
o
wn
i
n
F
ig
u
r
e
8
,
p
r
eser
v
in
g
th
e
m
o
s
t
s
ig
n
if
ican
t
in
f
o
r
m
atio
n
an
d
r
ed
u
ci
n
g
co
m
p
u
tatio
n
al
co
m
p
lex
ity
.
T
h
e
r
esu
lt
h
ig
h
lig
h
ts
k
ey
f
ea
tu
r
es
ess
en
t
ial
f
o
r
id
en
tify
in
g
C
OVI
D
-
1
9
r
elate
d
ab
n
o
r
m
alit
ies.
Alg
o
r
ith
m
3
im
p
lem
en
ts
th
e
f
u
n
ctio
n
alities
o
f
m
ax
p
o
o
li
n
g
lay
er
.
Fig
u
r
e
8
.
Ma
x
p
o
o
l w
ith
2
×
2
f
ilter
s
an
d
s
tr
id
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
Dete
ct
a
n
d
en
visi
o
n
o
f p
a
n
d
e
mic
d
is
ea
s
e
ex
p
o
s
u
r
e
u
s
in
g
C
N
N
(
C
h
.
R
u
p
a
)
953
3
.
4
.
3
.
F
ull
y
co
nn
ec
t
ed
la
y
er
T
h
e
f
u
lly
c
o
n
n
ec
te
d
lay
er
in
th
e
C
NN
m
o
d
el
co
n
n
ec
ts
ea
ch
n
eu
r
o
n
to
e
v
er
y
n
eu
r
o
n
in
th
e
p
r
ev
io
u
s
lay
er
[
3
0
]
,
e
n
ab
lin
g
h
ig
h
-
lev
el
r
ea
s
o
n
in
g
b
y
ag
g
r
eg
atin
g
c
o
m
p
lex
f
ea
tu
r
es
f
r
o
m
C
T
s
ca
n
im
ag
es.
I
ts
o
u
tp
u
t
is
th
en
u
s
ed
b
y
th
e
S
o
f
t
M
ax
la
y
er
to
class
if
y
th
e
im
a
g
es
an
d
d
eter
m
i
n
e
th
e
p
r
esen
ce
o
f
C
OVI
D
-
1
9
.
A
f
u
lly
co
n
n
ec
ted
C
NN
m
o
d
el
is
s
h
o
wn
in
Fig
u
r
e
9
.
T
h
e
f
u
n
ctio
n
alities
o
f
f
u
lly
co
n
n
ec
ted
lay
er
ar
e
illu
s
tr
ated
in
Alg
o
r
ith
m
4
.
Fig
u
r
e
9
.
Fu
lly
c
o
n
n
ec
te
d
lay
e
r
3
.
4
.
4
.
So
f
t
M
ax
T
h
e
ac
tiv
atio
n
lay
er
tr
a
n
s
f
o
r
m
s
s
u
m
m
ar
ized
d
ata
in
to
th
e
o
u
tp
u
t
f
o
r
m
at
u
s
in
g
an
ac
tiv
atio
n
f
u
n
ctio
n
.
T
r
ad
itio
n
al
f
u
n
ctio
n
s
lik
e
s
ig
m
o
id
an
d
h
y
p
er
b
o
lic
tan
g
en
t
s
tr
u
g
g
le
with
co
m
p
le
x
f
u
n
ctio
n
s
an
d
s
u
f
f
er
f
r
o
m
v
an
is
h
in
g
g
r
a
d
ien
ts
in
d
ee
p
n
etwo
r
k
s
.
T
h
er
ef
o
r
e,
R
eL
U
is
co
m
m
o
n
l
y
u
s
ed
in
C
NNs
d
u
e
to
its
ef
f
ec
tiv
en
es
s
in
o
v
er
c
o
m
in
g
t
h
ese
is
s
u
es [
3
2
]
.
T
h
e
o
p
er
atio
n
s
o
f
So
f
tMa
x
alg
o
r
ith
m
a
r
e
s
h
o
wn
in
Alg
o
r
ith
m
5
.
Alg
o
r
ith
m
3
.
Fu
n
ctio
n
alities
o
f
m
ax
p
o
o
lin
g
lay
er
Input to the algorithm:
Convolved feature image.
Output of the algorithm:
max pooled feature image.
Step 1:
Now the convolved image C from the convolution layer reaches pooling layer.
Step 2:
It extracts the maximum elements from the convolved future map C.
St
ep
3:
Th
e
ma
xi
mu
m
el
em
e
nt
fr
om
C
ca
n
be
ch
os
en
wi
th
in
te
gr
at
io
n
of
2
x
2
fi
lt
er
(D
)
an
d
Stride(S) of 2.
Step 4:
Generally, formula for finding max pool is given by
(
C
−
D
)
S
+
1
Step 5:
This result in a max pool feature image (Z
i x j
) = (C
-
D).
Alg
o
r
ith
m
4
.
Fu
n
ctio
n
alities
o
f
f
u
lly
c
o
n
n
ec
ted
lay
er
Input to the algorithm:
max pooled feature image.
Output of the algorithm:
a model of combined features.
Step 1:
In this layer, max pooled feature image (Z
i x j
) is taken.
Step 2:
Now this flattened into vectors (X
i
) before passing into FC layer.
Step 3:
These vectors (X
i
) are fed to the fully connected layers.
Step 4:
These X
i
are combined in fully connected layers to create a model.
Step 5:
The outcome is fed to the softmax.
Alg
o
r
ith
m
5
.
Op
er
atio
n
s
o
f
So
f
tMa
x
alg
o
r
ith
m
Input to the algorithm:
a model of combined features.
Output of the algorithm:
classify the affected person.
Step 1: T
he output from
the FC layer (Y
i
) is passed to the softmax for the final result.
Step 2: I
n this the negative inputs from FC layer are neutralized to 0.
St
ep
3:
St
ep
2
in
cr
ea
se
s
th
e
ef
fi
ci
en
cy
of
th
is
l
a
ye
r
by
no
t
ac
ti
va
ti
ng
al
l
ne
ur
on
s
at
sa
me
time.
Step 4:
The activation function is given by f(x) = max (0, x).
St
ep
5:
Th
is
la
ye
r
is
u
se
d
to
cl
as
si
fy
th
e
re
s
ul
t
(T
or
T
1
)
i.
e
wh
et
h
er
th
e
pe
rs
on
i
s
affected with COVID
-
19 or not.
4.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
is
s
ec
tio
n
ev
alu
ates
th
e
p
er
f
o
r
m
a
n
ce
o
f
p
r
o
p
o
s
ed
s
y
s
tem
.
Ou
r
r
esu
lts
d
em
o
n
s
tr
ate
th
at
th
e
p
r
o
p
o
s
ed
s
y
s
tem
ac
h
iev
es
a
n
ac
cu
r
ac
y
o
f
9
4
.
1
2
%.
C
NN
d
eliv
er
s
h
ig
h
ac
cu
r
ac
y
in
im
ag
e
p
r
o
ce
s
s
in
g
[
3
2
]
,
[
3
3
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
7
,
No
.
2
,
Feb
r
u
a
r
y
20
2
5
:
9
4
8
-
9
5
8
954
4
.
1
.
P
er
f
o
r
m
a
nce
a
na
ly
s
is
T
h
e
p
er
f
o
r
m
an
ce
o
f
th
e
p
r
o
p
o
s
ed
s
y
s
tem
is
ev
alu
ated
b
y
co
n
s
id
er
in
g
v
ar
io
u
s
p
ar
am
eter
s
.
Fu
r
th
er
m
o
r
e
,
a
co
m
p
ar
ativ
e
a
n
aly
s
is
o
f
th
e
p
r
o
p
o
s
ed
s
y
s
tem
with
ex
is
tin
g
tech
n
iq
u
es
is
also
co
n
d
u
cted
t
o
ju
s
tify
its
p
er
f
o
r
m
an
ce
.
T
h
is
ev
alu
atio
n
h
ig
h
lig
h
ts
th
e
s
tr
en
g
th
s
an
d
ef
f
ec
tiv
en
ess
o
f
th
e
p
r
o
p
o
s
ed
s
y
s
tem
in
ac
h
iev
in
g
th
e
d
esire
d
o
u
tco
m
e
s
4
.
1
.
1.
T
ra
ini
ng
re
s
ults
T
h
e
C
T
s
ca
n
r
ep
o
r
ts
o
f
b
o
t
h
C
OVI
D
-
1
9
an
d
n
o
n
-
C
OVI
D
-
19
a
r
e
co
n
s
id
er
ed
as
a
d
ataset.
As
th
e
F
ig
u
r
e
1
0
s
h
o
ws th
e
d
ata
s
et
c
o
m
p
r
is
es o
f
3
4
0
im
ag
es a
s
a
tr
ain
in
g
s
et
an
d
3
4
0
im
ag
es o
f
v
alid
atio
n
s
et.
Af
ter
tr
ain
in
g
,
th
e
m
o
d
el
is
test
ed
to
m
ea
s
u
r
e
its
ac
cu
r
ac
y
.
So
,
f
o
r
th
at
p
u
r
p
o
s
e
2
0
im
ag
es a
r
e
lo
a
d
ed
in
to
test
in
g
s
et
to
m
ea
s
u
r
e
th
e
p
e
r
f
o
r
m
an
ce
o
f
th
e
m
o
d
el.
Fu
r
th
er
m
o
r
e,
th
e
m
o
d
el
u
s
es
5
0
ep
o
ch
s
an
d
ea
c
h
ep
o
ch
with
b
atc
h
s
ize
o
f
6
0
.
I
t p
r
o
v
id
es th
e
ac
cu
r
ac
y
an
d
lo
s
s
s
co
r
e
f
o
r
ea
c
h
ep
o
ch
in
th
e
F
ig
u
r
e
s
1
1
an
d
1
2
.
Fig
u
r
e
1
0
.
Nu
m
b
er
o
f
s
am
p
les
Fig
u
r
e
1
2
.
Nu
m
b
er
o
f
e
p
o
ch
s
Fig
u
r
e
1
1
.
Nu
m
b
er
o
f
e
p
o
ch
s
4
.
1
.
2
.
T
esting
re
s
ults
T
h
is
s
ec
tio
n
f
o
cu
s
es
o
n
th
e
r
esu
lts
,
d
escr
ib
in
g
th
e
m
o
d
el'
s
t
r
ain
in
g
p
r
o
ce
s
s
,
in
clu
d
in
g
tr
ai
n
in
g
r
ate,
d
u
r
atio
n
,
a
n
d
p
r
e
d
ictio
n
o
u
t
co
m
es.
Af
ter
tr
ain
in
g
,
th
e
m
o
d
el
u
n
d
er
g
o
es
a
test
in
g
p
h
ase
to
ass
es
s
its
p
er
f
o
r
m
an
ce
.
Fig
u
r
e
1
3
d
ep
ict
s
th
r
ee
k
ey
asp
ec
ts
: m
o
d
el
ac
c
u
r
ac
y
,
lo
s
s
p
er
ce
n
tag
e,
a
n
d
p
r
ed
ictio
n
tim
e
[
1
8
]
.
Fig
u
r
e
1
3
: N
u
m
b
er
o
f
ep
o
ch
s
,
ac
cu
r
ac
y
,
lo
s
s
an
d
tim
e
tak
en
t
o
test
4
.
2
.
G
ra
ph
ica
l r
esu
lt
s
Data
Vis
u
aliza
tio
n
is
cr
u
cial
f
o
r
e
v
alu
atin
g
m
o
d
el
p
er
f
o
r
m
an
ce
.
Fig
u
r
e
1
4
d
e
p
icts
th
e
a
cc
u
r
ac
y
o
f
b
o
th
t
r
ain
in
g
an
d
v
alid
atio
n
s
et.
Acc
u
r
ac
y
is
m
en
tio
n
ed
o
n
y
-
ax
is
an
d
ep
o
ch
s
o
n
x
-
a
x
is
.
Fig
u
r
e
1
5
illu
s
tr
ates
lo
s
s
ca
lcu
latio
n
o
f
b
o
th
tr
ai
n
in
g
an
d
v
alid
atio
n
.
L
o
s
s
p
ar
am
eter
is
m
en
tio
n
e
d
o
n
y
-
ax
is
an
d
e
p
o
ch
is
m
en
tio
n
ed
o
n
x
-
ax
is
.
Fig
u
r
e
1
4
.
Acc
u
r
ac
y
Fig
u
r
e
1
5
.
L
o
s
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
Dete
ct
a
n
d
en
visi
o
n
o
f p
a
n
d
e
mic
d
is
ea
s
e
ex
p
o
s
u
r
e
u
s
in
g
C
N
N
(
C
h
.
R
u
p
a
)
955
T
h
e
p
r
o
p
o
s
ed
m
et
h
o
d
is
co
m
p
ar
ed
with
e
x
is
tin
g
tech
n
iq
u
es
b
y
u
s
in
g
v
ar
io
u
s
p
ar
a
m
eter
s
as
s
u
m
m
ar
ized
in
T
ab
le
2
.
A
b
la
ck
b
o
x
test
in
g
[
1
9
]
is
u
s
ed
to
ev
alu
ate
th
e
m
o
d
el
an
d
s
am
e
is
illu
s
tr
ated
u
s
in
g
T
ab
le
3
.
T
h
e
f
in
al
s
tatu
s
is
d
eter
m
in
ed
b
y
co
m
p
ar
in
g
th
e
p
r
e
d
icted
o
u
tco
m
e
with
th
e
ac
tu
al
o
u
tco
m
e.
T
ab
le
2
.
C
o
m
p
a
r
is
o
n
an
aly
s
is
tab
le
A
u
t
h
o
r
s
M
o
d
e
l
N
a
t
u
r
e
o
f
d
a
t
a
se
t
A
c
c
u
r
a
c
y
/
P
r
e
d
i
c
t
i
o
n
D
a
t
a
si
z
e
A
b
d
e
l
-
B
a
sse
t
e
t
a
l
.
[
2
6
]
I
mp
r
o
v
e
d
m
a
r
i
n
e
p
r
e
d
a
t
o
r
s’
a
l
g
o
r
i
t
h
m (I
M
P
A
)
C
h
e
st
X
-
r
ay
6
6
.
2
6
%
6
5
4
W
a
h
e
e
d
e
t
a
l
.
[
2
9
]
R
e
s
n
e
t
C
h
e
st
X
-
r
ay
7
2
.
3
8
%
3
7
4
A
g
r
a
w
a
l
e
t
a
l
.
[
3
1
]
VGG
-
16
C
h
e
st
X
-
r
ay
9
7
%
1
,
0
1
4
El
a
z
i
z
e
t
a
l
.
[
3
3
]
R
e
s
n
e
t
C
h
e
st
X
-
r
ay
9
4
.
2
%
1
,
8
0
0
R
e
h
ma
n
e
t
a
l
.
[
3
4
]
A
u
x
i
l
i
a
r
y
c
l
a
ss
i
f
i
e
r
g
e
n
e
r
a
t
i
v
e
a
d
v
e
r
s
a
r
i
a
l
n
e
t
w
o
r
k
(
A
C
G
A
N
)
C
h
e
st
X
-
r
ay
9
5
%
1
,
1
2
4
P
r
o
p
o
se
d
m
e
t
h
o
d
VGG
-
16
a
n
d
C
N
N
C
h
e
st
C
T
sca
n
9
4
.
1
2
%
2
,
4
8
2
T
ab
le
3
.
C
ase
s
tu
d
y
test
u
n
it
S
y
st
e
m:
En
v
i
si
o
n
o
f
C
O
V
I
D
-
19
p
a
n
d
e
mi
c
e
x
p
o
s
u
r
e
u
s
i
n
g
d
e
e
p
l
e
a
r
n
i
n
g
Te
st
i
d
:
#
0
1
Te
st
p
r
e
f
e
r
e
n
c
e
:
M
e
d
i
u
m
S
e
c
t
i
o
n
n
a
me:
C
O
V
I
D
-
1
9
d
e
t
e
c
t
i
o
n
Te
st
t
e
c
h
n
i
q
u
e
:
B
l
a
c
k
b
o
x
D
e
scri
p
t
i
o
n
:
Te
s
t
i
n
g
t
h
e
C
T
s
c
a
n
r
e
p
o
r
t
s
P
r
e
t
e
s
t
:
C
h
e
st
C
T
sc
a
n
i
m
a
g
e
S
.
N
o
.
Ty
p
e
o
f
t
e
s
t
D
a
t
a
t
o
t
h
e
t
e
st
P
r
e
d
i
c
t
e
d
o
u
t
c
o
me
R
e
a
l
o
u
t
c
o
m
e
P
a
ss/
F
a
i
l
C
o
mm
e
n
t
1.
C
O
V
I
D
-
1
9
d
e
t
e
c
t
i
o
n
C
O
V
I
D
-
1
9
a
f
f
e
c
t
e
d
C
T
s
c
a
n
C
O
V
I
D
-
1
9
:
p
o
s
i
t
i
v
e
C
O
V
I
D
-
1
9
:
p
o
s
i
t
i
v
e
P
a
ss
N
i
l
2.
N
o
n
-
C
O
V
I
D
-
19
d
e
t
e
c
t
i
o
n
H
e
a
l
t
h
y
p
e
r
s
o
n
s C
T
sca
n
C
O
V
I
D
-
1
9
:
n
e
g
a
t
i
v
e
C
O
V
I
D
-
1
9
:
n
e
g
a
t
i
v
e
P
a
ss
N
i
l
3.
C
h
e
st
C
T
sca
n
d
e
t
e
c
t
i
o
n
C
h
e
st
C
T
sca
n
V
a
l
i
d
C
T
s
c
a
n
i
ma
g
e
V
a
l
i
d
C
T
s
c
a
n
i
ma
g
e
P
a
ss
N
i
l
4.
B
l
u
r
r
y
i
ma
g
e
B
l
u
r
r
y
m
a
g
e
D
i
sca
r
d
e
d
i
n
p
r
e
p
r
o
c
e
ssi
n
g
D
i
sca
r
d
e
d
i
n
p
r
e
p
r
o
c
e
ssi
n
g
P
a
ss
N
i
l
5.
X
-
r
a
y
X
-
r
a
y
C
O
V
I
D
-
1
9
:
P
o
s
i
t
i
v
e
C
O
V
I
D
-
1
9
:
N
e
g
a
t
i
v
e
F
a
i
l
N
i
l
T
h
e
u
n
iq
u
en
ess
o
f
th
is
m
o
d
el
lies
in
its
ab
ilit
y
to
p
r
ed
ict
wh
eth
er
a
p
er
s
o
n
is
af
f
ec
te
d
b
y
C
OVI
D
-
19
b
ased
o
n
th
eir
C
T
s
ca
n
r
e
p
o
r
ts
.
T
h
e
m
o
d
el
o
u
tp
u
ts
an
i
m
ag
e
d
is
p
lay
in
g
t
h
e
d
ia
g
n
o
s
i
s
:
if
th
e
p
atien
t
h
as
C
OVI
D
-
1
9
,
it
will
s
h
o
w
“
C
OVI
D
-
1
9
:
p
o
s
itiv
e
”
alo
n
g
wi
th
p
r
ec
au
tio
n
s
lik
e
“
q
u
ar
an
ti
n
e
an
d
s
an
itizin
g
.
”
Similar
ly
,
if
th
e
p
atien
t
is
h
ea
lth
y
,
th
e
s
tatu
s
will
b
e
“
C
OVI
D
-
1
9
:
n
eg
ativ
e
”
with
p
r
ec
au
tio
n
s
s
u
c
h
as
“
Use
m
ask
an
d
m
ain
tain
s
o
c
ial
d
is
tan
ce
”
.
T
h
ese
r
esu
lts
ar
e
illu
s
tr
ated
in
Fig
u
r
e
1
6
,
wh
er
e
Fig
u
r
e
1
6
(
a)
r
ep
r
esen
ts
th
e
o
r
ig
in
al
C
T
im
a
g
es,
an
d
Fig
u
r
e
1
6
(
b
)
h
ig
h
lig
h
ts
th
e
d
etec
ted
C
OVI
D
-
1
9
s
y
m
p
to
m
s
alo
n
g
with
r
ec
o
m
m
en
d
ed
p
r
ec
au
tio
n
s
.
O
r
i
g
i
n
a
l
d
a
t
a
(
a
)
C
o
r
r
e
s
p
o
n
d
i
n
g
p
r
o
c
e
sse
d
d
a
t
a
(
b
)
O
r
i
g
i
n
a
l
d
a
t
a
(
a
)
C
o
r
r
e
s
p
o
n
d
i
n
g
p
r
o
c
e
sse
d
d
a
t
a
(
b
)
Fig
u
r
e
1
6
.
C
OVI
D
-
1
9
im
ag
e
i
llu
s
tr
atio
n
(
a)
o
r
i
g
in
al
im
ag
es
an
d
(
b
)
C
OVI
D
-
1
9
s
y
m
p
t
o
m
s
s
p
o
tted
an
d
lis
ted
p
r
ec
au
tio
n
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
7
,
No
.
2
,
Feb
r
u
a
r
y
20
2
5
:
9
4
8
-
9
5
8
956
5.
CO
NCLU
SI
O
N
AND
F
U
T
U
RE
SCO
P
E
W
e
p
r
o
p
o
s
ed
C
NN
b
ased
m
o
d
el
to
p
r
ed
ict
th
e
C
OVI
D
-
1
9
f
r
o
m
t
h
e
C
T
s
ca
n
im
a
g
es.
T
h
e
p
r
o
p
o
s
e
d
m
o
d
el
u
s
es
VGG1
6
th
at
au
to
m
ates
th
e
p
r
o
ce
s
s
o
f
C
OVI
D
-
1
9
p
r
e
d
ictio
n
with
less
co
m
p
u
tatio
n
al
r
eso
u
r
ce
s
.
I
n
p
an
d
em
ic
s
itu
atio
n
,
th
is
t
y
p
e
o
f
in
n
o
v
atio
n
s
will
p
r
ed
i
ct
th
e
C
OVI
D
-
1
9
p
o
s
itiv
e
ca
s
es
in
less
er
tim
e.
Ou
r
ex
p
er
im
en
tal
r
esu
lts
ju
s
tify
th
at
p
r
o
p
o
s
ed
m
o
d
el
ac
h
ie
v
ed
a
n
ac
cu
r
ac
y
r
ate
o
f
9
4
.
1
2
%
o
n
5
0
ep
o
ch
s
.
Fu
r
th
er
,
th
e
ac
cu
r
ac
y
ca
n
b
e
e
n
h
an
ce
d
b
y
ad
ju
s
tin
g
t
h
e
d
ata
s
ize
an
d
ep
o
ch
s
co
u
n
t.
T
h
e
f
ea
tu
r
es
o
b
tain
ed
b
y
th
is
m
o
d
el
ar
e
s
tatu
s
o
f
C
O
VI
D
-
1
9
an
d
p
r
ec
au
tio
n
s
wh
ich
n
ee
d
to
b
e
f
o
llo
wed
to
o
v
e
r
co
m
e
th
at
d
is
ea
s
e.
T
h
e
p
r
o
p
o
s
ed
m
o
d
el
h
as
ab
ilit
y
to
lear
n
c
o
m
p
lex
p
atter
n
s
,
ex
tr
ac
t
d
ee
p
f
ea
tu
r
es
f
r
o
m
th
e
g
iv
en
C
T
s
ca
n
im
ag
es
an
d
p
r
ed
ict
th
e
o
u
t
p
u
t
with
h
ig
h
ac
cu
r
ac
y
.
Ou
r
p
r
o
p
o
s
ed
m
o
d
el
is
im
p
lem
en
te
d
u
s
in
g
Ker
as
lib
r
ar
y
o
n
th
e
to
p
o
f
T
en
s
o
r
Flo
w
.
Ou
r
ex
p
er
im
en
tal
r
esu
lts
d
e
m
o
n
s
tr
ate
th
at
t
h
e
p
r
o
p
o
s
ed
m
o
d
el
o
u
tp
e
r
f
o
r
m
s
ex
is
tin
g
ap
p
r
o
ac
h
es,
aid
in
g
m
ed
ical
p
r
o
f
ess
io
n
al
in
ea
r
l
y
d
is
ea
s
e
d
etec
tio
n
an
d
tr
ea
t
m
en
t.
Fu
tu
r
e
w
o
r
k
in
clu
d
es
ap
p
ly
in
g
th
is
m
o
d
el
to
v
ar
io
u
s
m
ed
ical
im
ag
es
an
d
d
ev
elo
p
in
g
a
u
s
er
-
f
r
ien
d
ly
m
o
b
ile
ap
p
f
o
r
au
to
m
ated
d
is
ea
s
e
p
r
ed
ictio
n
.
RE
F
E
R
E
NC
E
S
[
1
]
J.
O
.
A
g
b
a
j
e
e
t
a
l
.
,
“
M
o
d
e
l
i
n
g
C
O
V
I
D
-
1
9
d
i
se
a
se
w
i
t
h
d
e
t
e
r
mi
n
i
s
t
i
c
a
n
d
d
a
t
a
-
d
r
i
v
e
n
m
o
d
e
l
s
u
si
n
g
d
a
i
l
y
e
m
p
i
r
i
c
a
l
d
a
t
a
i
n
t
h
e
U
n
i
t
e
d
K
i
n
g
d
o
m,
”
C
o
v
i
d
,
v
o
l
.
4
,
n
o
.
2
,
p
p
.
2
8
9
–
3
1
6
,
F
e
b
.
2
0
2
4
,
d
o
i
:
1
0
.
3
3
9
0
/
c
o
v
i
d
4
0
2
0
0
2
0
.
[
2
]
G
.
L.
O
’
H
a
r
a
,
S
.
H
a
l
a
b
i
,
a
n
d
O
.
E
g
b
o
k
h
a
r
e
,
“
E
q
u
i
t
a
b
l
e
v
a
c
c
i
n
e
a
c
c
e
ss
i
n
l
i
g
h
t
o
f
C
O
V
I
D
-
1
9
v
a
c
c
i
n
e
p
r
o
c
u
r
e
men
t
st
r
a
t
e
g
i
e
s
i
n
A
f
r
i
c
a
,
”
C
o
v
i
d
,
v
o
l
.
4
,
n
o
.
2
,
p
p
.
2
7
6
–
2
8
8
,
F
e
b
.
2
0
2
4
,
d
o
i
:
1
0
.
3
3
9
0
/
c
o
v
i
d
4
0
2
0
0
1
9
.
[
3
]
C
.
A
.
A
l
v
a
r
e
z
-
M
o
r
e
n
o
e
t
a
l
.
,
“
D
i
f
f
e
r
e
n
t
i
a
l
d
i
a
g
n
o
si
s
i
n
t
h
e
ma
n
a
g
e
me
n
t
o
f
a
c
u
t
e
r
e
s
p
i
r
a
t
o
r
y
i
n
f
e
c
t
i
o
n
s
t
h
r
o
u
g
h
p
o
i
n
t
-
of
-
c
a
r
e
r
a
p
i
d
t
e
st
i
n
g
i
n
a
p
o
st
-
p
a
n
d
e
mi
c
s
c
e
n
a
r
i
o
i
n
l
a
t
i
n
a
m
e
r
i
c
a
:
sp
e
c
i
a
l
f
o
c
u
s
o
n
C
O
V
I
D
-
1
9
,
I
n
f
l
u
e
n
z
a
,
a
n
d
r
e
s
p
i
r
a
t
o
r
y
sy
n
c
y
t
i
a
l
v
i
r
u
s,
”
C
O
VI
D
,
v
o
l
.
4
,
n
o
.
2
,
p
p
.
2
2
1
–
2
6
0
,
F
e
b
.
2
0
2
4
,
d
o
i
:
1
0
.
3
3
9
0
/
c
o
v
i
d
4
0
2
0
0
1
7
.
[
4
]
B
.
S
i
n
g
h
e
t
a
l
.
,
“
T
h
e
C
O
V
I
D
g
u
i
d
e
l
i
n
e
s
I
n
d
i
a
p
r
o
j
e
c
t
:
a
r
a
p
i
d
l
i
v
i
n
g
e
v
i
d
e
n
c
e
s
y
n
t
h
e
s
i
s
d
u
r
i
n
g
a
p
a
n
d
e
m
i
c
i
n
a
LM
I
C
se
t
t
i
n
g
,
”
C
l
i
n
i
c
a
l
E
p
i
d
e
m
i
o
l
o
g
y
a
n
d
G
l
o
b
a
l
H
e
a
l
t
h
,
v
o
l
.
2
8
,
p
.
1
0
1
5
4
8
,
Ju
l
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
e
g
h
.
2
0
2
4
.
1
0
1
5
4
8
.
[
5
]
E.
B
.
A
c
k
a
h
e
t
a
l
.
,
“
H
a
e
ma
t
o
l
o
g
i
c
a
l
p
r
o
f
i
l
e
a
n
d
A
C
E2
l
e
v
e
l
s
o
f
C
O
V
I
D
-
1
9
p
a
t
i
e
n
t
s
i
n
a
m
e
t
r
o
p
o
l
i
s
i
n
G
h
a
n
a
,
”
C
o
v
i
d
,
v
o
l
.
4
,
n
o
.
2
,
p
p
.
1
1
7
–
1
2
9
,
Ja
n
.
2
0
2
4
,
d
o
i
:
1
0
.
3
3
9
0
/
c
o
v
i
d
4
0
2
0
0
1
1
.
[
6
]
U
.
U
d
a
y
e
t
a
l
.
,
“
Z
i
k
a
,
N
i
p
a
h
a
n
d
K
a
l
a
-
a
z
a
r
:
e
mer
g
i
n
g
l
e
t
h
a
l
i
n
f
e
c
t
i
o
u
s
d
i
se
a
ses
a
mi
d
C
O
V
I
D
-
1
9
a
s
a
n
e
sca
l
a
t
i
n
g
p
u
b
l
i
c
h
e
a
l
t
h
t
h
r
e
a
t
i
n
S
o
u
t
h
I
n
d
i
a
,
”
A
n
n
a
l
s
o
f
Me
d
i
c
i
n
e
a
n
d
S
u
rg
e
ry
,
v
o
l
.
7
9
,
Ju
l
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
msu
.
2
0
2
2
.
1
0
3
9
7
2
.
[
7
]
S
.
Ta
n
w
a
r
,
A
.
K
u
mar
i
,
D
.
V
e
k
a
r
i
a
,
N
.
K
u
mar
,
a
n
d
R
.
S
h
a
r
m
a
,
“
A
n
A
I
-
b
a
se
d
d
i
se
a
se
d
e
t
e
c
t
i
o
n
a
n
d
p
r
e
v
e
n
t
i
o
n
sch
e
me
f
o
r
C
O
V
I
D
-
1
9
,
”
C
o
m
p
u
t
e
rs
a
n
d
E
l
e
c
t
r
i
c
a
l
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
1
0
3
,
p
.
1
0
8
3
5
2
,
O
c
t
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
m
p
e
l
e
c
e
n
g
.
2
0
2
2
.
1
0
8
3
5
2
.
[
8
]
S
.
R
a
m
a
K
r
i
s
h
n
a
a
n
d
M
.
S
i
r
a
j
u
d
d
i
n
,
“
A
r
o
l
e
o
f
e
mer
g
i
n
g
t
e
c
h
n
o
l
o
g
i
e
s
i
n
t
h
e
d
e
si
g
n
o
f
n
o
v
e
l
f
r
a
m
e
w
o
r
k
f
o
r
C
O
V
I
D
-
1
9
d
a
t
a
a
n
a
l
y
si
s
a
n
d
d
e
c
i
si
o
n
su
p
p
o
r
t
s
y
st
e
m,
”
i
n
S
t
u
d
i
e
s i
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
,
v
o
l
.
9
6
3
,
2
0
2
2
,
p
p
.
3
1
3
–
3
3
7
.
[
9
]
K
.
Z
i
r
p
e
a
n
d
S
.
G
u
r
a
v
,
“
C
O
V
I
D
-
1
9
p
a
n
d
e
mi
c
i
n
I
n
d
i
a
,
”
i
n
C
O
VI
D
-
1
9
P
a
n
d
e
m
i
c
:
L
e
ss
o
n
s
f
ro
m
t
h
e
Fro
n
t
l
i
n
e
,
E
l
se
v
i
e
r
,
2
0
2
1
,
p
p
.
2
0
5
–
2
1
0
.
[
1
0
]
H
.
A
l
s
h
a
z
l
y
,
C
.
Li
n
s
e
,
M
.
A
b
d
a
l
l
a
,
E.
B
a
r
t
h
,
a
n
d
T.
M
a
r
t
i
n
e
t
z
,
“
C
O
V
I
D
-
N
e
t
s:
d
e
e
p
C
N
N
a
r
c
h
i
t
e
c
t
u
r
e
s
f
o
r
d
e
t
e
c
t
i
n
g
C
O
V
I
D
-
1
9
u
s
i
n
g
c
h
e
st
C
T
s
c
a
n
s,
”
Pe
e
rJ
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
7
,
p
p
.
1
–
4
0
,
Ju
l
.
2
0
2
1
,
d
o
i
:
1
0
.
7
7
1
7
/
p
e
e
r
j
-
c
s
.
6
5
5
.
[
1
1
]
D
.
Ese
n
d
a
ğ
l
i
,
A
.
Y
i
l
m
a
z
,
Ş
.
A
k
ç
a
y
,
a
n
d
T.
Ö
z
l
ü
,
“
P
o
s
t
-
C
O
V
I
D
sy
n
d
r
o
m
e
:
p
u
l
m
o
n
a
r
y
c
o
mp
l
i
c
a
t
i
o
n
s
,
”
T
u
rk
i
s
h
J
o
u
r
n
a
l
o
f
M
e
d
i
c
a
l
S
c
i
e
n
c
e
s
,
v
o
l
.
5
1
,
n
o
.
S
p
e
c
i
a
l
I
ssu
e
1
,
p
p
.
3
3
5
9
–
3
3
7
1
,
D
e
c
.
2
0
2
1
,
d
o
i
:
1
0
.
3
9
0
6
/
sa
g
-
2
1
0
6
-
2
3
8
.
[
1
2
]
O
.
P
a
si
n
a
n
d
S
.
G
o
n
e
n
c
,
“
A
n
i
n
v
e
s
t
i
g
a
t
i
o
n
i
n
t
o
e
p
i
d
e
m
i
o
l
o
g
i
c
a
l
s
i
t
u
a
t
i
o
n
s
o
f
C
O
V
I
D
-
1
9
w
i
t
h
f
u
z
z
y
K
-
me
a
n
s
a
n
d
K
-
p
r
o
t
o
t
y
p
e
c
l
u
s
t
e
r
i
n
g
me
t
h
o
d
s,
”
S
c
i
e
n
t
i
f
i
c
R
e
p
o
rt
s
,
v
o
l
.
1
3
,
n
o
.
1
,
p
.
6
2
5
5
,
A
p
r
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
5
9
8
-
023
-
3
3
2
1
4
-
y.
[
1
3
]
A
.
S
h
v
e
t
c
o
v
e
t
a
l
.
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
i
d
e
n
t
i
f
i
e
s
a
C
O
V
I
D
-
19
-
sp
e
c
i
f
i
c
p
h
e
n
o
t
y
p
e
i
n
u
n
i
v
e
r
si
t
y
s
t
u
d
e
n
t
s
u
s
i
n
g
a
m
e
n
t
a
l
h
e
a
l
t
h
a
p
p
,
”
I
n
t
e
r
n
e
t
I
n
t
e
r
v
e
n
t
i
o
n
s
,
v
o
l
.
3
4
,
p
.
1
0
0
6
6
6
,
D
e
c
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
n
v
e
n
t
.
2
0
2
3
.
1
0
0
6
6
6
.
[
1
4
]
D
.
E.
S
c
h
e
i
m,
P
.
V
o
t
t
e
r
o
,
A
.
D
.
S
a
n
t
i
n
,
a
n
d
A
.
G
.
H
i
r
s
h
,
“
S
i
a
l
y
l
a
t
e
d
g
l
y
c
a
n
b
i
n
d
i
n
g
s
f
r
o
m
S
A
R
S
-
C
o
V
-
2
s
p
i
k
e
p
r
o
t
e
i
n
t
o
b
l
o
o
d
a
n
d
e
n
d
o
t
h
e
l
i
a
l
c
e
l
l
s
g
o
v
e
r
n
t
h
e
se
v
e
r
e
mo
r
b
i
d
i
t
i
e
s
o
f
C
O
V
I
D
-
1
9
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
Mo
l
e
c
u
l
a
r
S
c
i
e
n
c
e
s
,
v
o
l
.
2
4
,
n
o
.
2
3
,
p
.
1
7
0
3
9
,
D
e
c
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
i
j
m
s2
4
2
3
1
7
0
3
9
.
[
1
5
]
W
.
T
.
C
h
u
e
t
a
l
.
,
“
N
o
v
e
l
ma
c
h
i
n
e
-
l
e
a
r
n
i
n
g
a
n
a
l
y
si
s
o
f
S
A
R
S
-
C
o
V
-
2
i
n
f
e
c
t
i
o
n
i
n
a
s
u
b
c
l
i
n
i
c
a
l
n
o
n
h
u
m
a
n
p
r
i
ma
t
e
mo
d
e
l
u
si
n
g
r
a
d
i
o
m
i
c
s
a
n
d
b
l
o
o
d
b
i
o
mark
e
r
s,”
S
c
i
e
n
t
i
f
i
c
Re
p
o
rt
s
,
v
o
l
.
1
3
,
n
o
.
1
,
p
.
1
9
6
0
7
,
N
o
v
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
5
9
8
-
023
-
4
6
6
9
4
-
9.
[
1
6
]
Q
.
U
.
A
.
A
r
sh
a
d
,
W
.
Z.
K
h
a
n
,
F
.
A
z
a
m,
a
n
d
M
.
K
.
K
h
a
n
,
“
D
e
e
p
-
l
e
a
r
n
i
n
g
-
b
a
se
d
C
O
V
I
D
-
1
9
d
e
t
e
c
t
i
o
n
:
c
h
a
l
l
e
n
g
e
s
a
n
d
f
u
t
u
r
e
d
i
r
e
c
t
i
o
n
s,
”
I
EEE
T
r
a
n
s
a
c
t
i
o
n
s
o
n
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
4
,
n
o
.
2
,
p
p
.
2
1
0
–
2
2
8
,
A
p
r
.
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
TA
I
.
2
0
2
2
.
3
2
2
4
0
9
7
.
[
1
7
]
Y
.
M
e
r
a
i
h
i
,
A
.
B
.
G
a
b
i
s,
S
.
M
i
r
j
a
l
i
l
i
,
A
.
R
a
m
d
a
n
e
-
C
h
e
r
i
f
,
a
n
d
F
.
E.
A
l
sa
a
d
i
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
-
b
a
s
e
d
r
e
sea
r
c
h
f
o
r
C
O
V
I
D
-
1
9
d
e
t
e
c
t
i
o
n
,
d
i
a
g
n
o
s
i
s,
a
n
d
p
r
e
d
i
c
t
i
o
n
:
a
s
u
r
v
e
y
,
”
S
N
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
3
,
n
o
.
4
,
p
.
2
8
6
,
M
a
y
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s
4
2
9
7
9
-
022
-
0
1
1
8
4
-
z.
[
1
8
]
S
.
G
.
P
a
u
l
e
t
a
l
.
,
“
C
o
m
b
a
t
i
n
g
C
o
v
i
d
-
1
9
u
s
i
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
:
a
p
p
l
i
c
a
t
i
o
n
s
,
c
h
a
l
l
e
n
g
e
s,
a
n
d
f
u
t
u
r
e
p
e
r
s
p
e
c
t
i
v
e
s
,
”
Arr
a
y
,
v
o
l
.
1
7
,
p
.
1
0
0
2
7
1
,
M
a
r
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
r
r
a
y
.
2
0
2
2
.
1
0
0
2
7
1
.
[
1
9
]
Y
.
Z
o
a
b
i
,
S
.
D
e
r
i
-
R
o
z
o
v
,
a
n
d
N
.
S
h
o
mr
o
n
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
-
b
a
se
d
p
r
e
d
i
c
t
i
o
n
o
f
C
O
V
I
D
-
1
9
d
i
a
g
n
o
s
i
s
b
a
s
e
d
o
n
s
y
mp
t
o
ms,
”
n
p
j
D
i
g
i
t
a
l
Me
d
i
c
i
n
e
,
v
o
l
.
4
,
n
o
.
1
,
p
.
3
,
J
a
n
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
7
4
6
-
0
2
0
-
0
0
3
7
2
-
6.
[
2
0
]
S
.
S
o
l
a
y
m
a
n
,
S
.
A
.
A
u
mi
,
C
.
S
.
M
e
r
y
,
M
.
M
u
b
a
ssi
r
,
a
n
d
R
.
K
h
a
n
,
“
A
u
t
o
mat
i
c
C
O
V
I
D
-
1
9
p
r
e
d
i
c
t
i
o
n
u
s
i
n
g
e
x
p
l
a
i
n
a
b
l
e
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
C
o
g
n
i
t
i
v
e
C
o
m
p
u
t
i
n
g
i
n
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
4
,
p
p
.
3
6
–
4
6
,
J
u
n
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
j
c
c
e
.
2
0
2
3
.
0
1
.
0
0
3
.
[
2
1
]
A
.
S
.
K
.
R
a
sh
i
d
,
H
.
N
.
A
b
d
u
l
j
a
b
b
a
r
,
a
n
d
B
.
A
l
h
a
y
a
n
i
,
“
C
o
r
o
n
a
v
i
r
u
s
d
i
sea
s
e
(
C
O
V
I
D
-
1
9
)
c
a
ses
a
n
a
l
y
si
s
u
si
n
g
mac
h
i
n
e
-
l
e
a
r
n
i
n
g
a
p
p
l
i
c
a
t
i
o
n
s,”
A
p
p
l
i
e
d
N
a
n
o
s
c
i
e
n
c
e
(
S
w
i
t
z
e
rl
a
n
d
)
,
v
o
l
.
1
3
,
n
o
.
3
,
p
p
.
2
0
1
3
–
2
0
2
5
,
M
a
r
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
3
2
0
4
-
021
-
0
1
8
6
8
-
7.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
Dete
ct
a
n
d
en
visi
o
n
o
f p
a
n
d
e
mic
d
is
ea
s
e
ex
p
o
s
u
r
e
u
s
in
g
C
N
N
(
C
h
.
R
u
p
a
)
957
[
2
2
]
P
.
A
smi
t
h
a
,
C
.
R
u
p
a
,
a
n
d
S
.
N
i
k
i
t
h
a
,
“
N
o
v
e
l
a
n
d
e
f
f
e
c
t
i
v
e
a
p
p
r
o
a
c
h
f
o
r
mu
l
t
i
v
i
e
w
b
i
o
me
t
r
i
c
o
b
j
e
c
t
d
e
t
e
c
t
i
o
n
u
si
n
g
d
e
e
p
l
e
a
r
n
i
n
g
b
a
s
e
d
c
u
t
t
i
n
g
e
d
g
e
t
e
c
h
n
i
q
u
e
s,
”
i
n
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
I
n
t
e
g
r
a
t
e
d
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
S
y
s
t
e
m
s,
I
C
I
I
C
S
2
0
2
3
,
N
o
v
.
2
0
2
3
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
I
I
C
S
5
9
9
9
3
.
2
0
2
3
.
1
0
4
2
1
0
2
1
.
[
2
3
]
M
.
I
.
K
h
a
l
i
l
e
t
a
l
.
,
"
D
e
e
p
-
C
O
V
I
D
:
D
e
t
e
c
t
i
o
n
a
n
d
A
n
a
l
y
si
s
o
f
C
O
V
I
D
-
1
9
O
u
t
c
o
m
e
s
U
s
i
n
g
D
e
e
p
L
e
a
r
n
i
n
g
,
"
E
l
e
c
t
r
o
n
i
c
s
,
v
o
l
.
1
1
,
n
o
.
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
e
l
e
c
t
r
o
n
i
c
s1
1
2
2
3
8
3
6
.
[
2
4
]
G
.
N
a
g
a
V
e
n
k
a
t
a
R
i
sh
i
k
a
,
C
.
M
u
k
e
sh
.
,
R
.
C
h
,
a
n
d
N
.
A
k
h
i
l
B
a
b
u
,
“
H
a
sh
b
a
se
d
sec
u
r
e
a
n
d
e
f
f
i
c
i
e
n
t
s
c
a
l
i
n
g
a
p
p
r
o
a
c
h
f
o
r
d
e
t
e
c
t
i
n
g
t
h
e
d
i
a
b
e
t
i
c
r
e
t
i
n
o
p
a
t
h
y
d
i
s
o
r
d
e
r
,
”
i
n
2
0
2
4
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
Em
e
rg
i
n
g
S
m
a
rt
C
o
m
p
u
t
i
n
g
a
n
d
I
n
f
o
rm
a
t
i
c
s
,
E
S
C
I
2
0
2
4
,
M
a
r
.
2
0
2
4
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
ES
C
I
5
9
6
0
7
.
2
0
2
4
.
1
0
4
9
7
2
4
3
.
[
2
5
]
N
.
V
.
N
a
g
a
,
R
.
C
h
,
A
.
B
a
b
u
.
n
,
M
.
N
a
v
e
n
a
,
a
n
d
M
.
S
e
k
h
a
r
.
m,
“
C
l
a
ss
i
f
i
c
a
t
i
o
n
a
n
d
se
g
me
n
t
a
t
i
o
n
o
f
mar
i
n
e
r
e
l
a
t
e
d
r
e
m
o
t
e
se
n
s
i
n
g
i
ma
g
e
r
y
d
a
t
a
u
s
i
n
g
d
e
e
p
l
e
a
r
n
i
n
g
,
”
i
n
Vi
T
E
C
o
N
2
0
2
3
-
2
n
d
I
EEE
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
V
i
si
o
n
T
o
w
a
r
d
s
Em
e
rg
i
n
g
T
re
n
d
s
i
n
C
o
m
m
u
n
i
c
a
t
i
o
n
a
n
d
N
e
t
w
o
rk
i
n
g
T
e
c
h
n
o
l
o
g
i
e
s,
Pro
c
e
e
d
i
n
g
s
,
M
a
y
2
0
2
3
,
p
p
.
1
–
5
,
d
o
i
:
1
0
.
1
1
0
9
/
V
i
TE
C
o
N
5
8
1
1
1
.
2
0
2
3
.
1
0
1
5
7
7
1
7
.
[
2
6
]
M
.
A
b
d
e
l
-
B
a
s
set
,
R
.
M
o
h
a
m
e
d
,
M
.
E
l
h
o
se
n
y
,
R
.
K
.
C
h
a
k
r
a
b
o
r
t
t
y
,
a
n
d
M
.
R
y
a
n
,
“
A
h
y
b
r
i
d
C
O
V
I
D
-
1
9
d
e
t
e
c
t
i
o
n
m
o
d
e
l
u
si
n
g
a
n
i
mp
r
o
v
e
d
mari
n
e
p
r
e
d
a
t
o
r
s
a
l
g
o
r
i
t
h
m
a
n
d
a
r
a
n
k
i
n
g
-
b
a
s
e
d
d
i
v
e
r
si
t
y
r
e
d
u
c
t
i
o
n
st
r
a
t
e
g
y
,
”
I
EEE
A
c
c
e
ss
,
v
o
l
.
8
,
p
p
.
7
9
5
2
1
–
7
9
5
4
0
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
0
.
2
9
9
0
8
9
3
.
[
2
7
]
S
.
Jasm
i
n
e
,
C
.
R
u
p
a
,
a
n
d
R
.
S
r
i
k
a
v
y
a
,
“
M
e
d
i
c
i
n
e
d
r
u
g
n
a
m
e
d
e
t
e
c
t
i
o
n
o
b
j
e
c
t
r
e
c
o
g
n
i
t
i
o
n
u
s
i
n
g
d
e
e
p
l
e
a
r
n
i
n
g
b
a
s
e
d
O
C
R
s
y
st
e
m,
”
i
n
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
I
n
t
e
g
r
a
t
e
d
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
S
y
s
t
e
m
s
,
I
C
I
I
C
S
2
0
2
3
,
N
o
v
.
2
0
2
3
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
I
I
C
S
5
9
9
9
3
.
2
0
2
3
.
1
0
4
2
1
2
2
6
.
[
2
8
]
R
.
C
h
,
V
.
Y
a
d
l
a
p
a
l
l
i
,
S
.
S
.
S
k
,
G
.
T
.
R
e
d
d
y
,
a
n
d
S
.
K
a
u
t
i
s
h
,
“
R
o
b
u
st
s
t
e
g
a
n
o
g
r
a
p
h
i
c
f
r
a
m
e
w
o
r
k
f
o
r
se
c
u
r
i
n
g
se
n
si
t
i
v
e
h
e
a
l
t
h
c
a
r
e
d
a
t
a
o
f
t
e
l
e
m
e
d
i
c
i
n
e
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
,
”
C
AAI
T
r
a
n
s
a
c
t
i
o
n
s
o
n
I
n
t
e
l
l
i
g
e
n
c
e
T
e
c
h
n
o
l
o
g
y
,
M
a
r
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
4
9
/
c
i
t
2
.
1
2
3
1
9
.
[
2
9
]
A
.
W
a
h
e
e
d
,
M
.
G
o
y
a
l
,
D
.
G
u
p
t
a
,
A
.
K
h
a
n
n
a
,
F
.
A
l
-
Tu
r
j
ma
n
,
a
n
d
P
.
R
.
P
i
n
h
e
i
r
o
,
“
C
o
v
i
d
G
A
N
:
d
a
t
a
a
u
g
m
e
n
t
a
t
i
o
n
u
s
i
n
g
a
u
x
i
l
i
a
r
y
c
l
a
s
s
i
f
i
e
r
G
A
N
f
o
r
i
mp
r
o
v
e
d
C
o
v
i
d
-
1
9
d
e
t
e
c
t
i
o
n
,
”
I
E
EE
Ac
c
e
ss
,
v
o
l
.
8
,
p
p
.
9
1
9
1
6
–
9
1
9
2
3
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
0
.
2
9
9
4
7
6
2
.
[
3
0
]
R
.
C
h
,
N
.
V
.
K
a
r
n
a
t
i
,
E
.
C
.
P
i
n
j
a
l
a
,
a
n
d
C
.
K
o
t
h
a
p
a
l
l
i
,
“
E
n
su
r
i
n
g
p
r
i
v
a
c
y
p
r
e
ser
v
a
t
i
o
n
f
o
r
v
a
r
i
o
u
s
p
l
a
n
t
s
m
u
l
t
i
-
p
r
o
d
u
c
t
d
i
s
e
a
s
e
d
e
t
e
c
t
i
o
n
a
n
d
p
e
s
t
i
c
i
d
e
s
r
e
c
o
mm
e
n
d
a
t
i
o
n
d
a
t
a
u
si
n
g
i
n
c
e
p
t
i
o
n
V
3
,
”
S
N
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
5
,
n
o
.
1
,
p
.
6
,
N
o
v
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
0
7
/
s
4
2
9
7
9
-
023
-
0
2
3
4
5
-
4.
[
3
1
]
D
.
K
.
A
g
r
a
w
a
l
,
B
.
S
.
K
i
r
a
r
,
a
n
d
R
.
B
.
P
a
c
h
o
r
i
,
“
A
u
t
o
m
a
t
e
d
g
l
a
u
c
o
ma
d
e
t
e
c
t
i
o
n
u
si
n
g
q
u
a
s
i
-
b
i
v
a
r
i
a
t
e
v
a
r
i
a
t
i
o
n
a
l
m
o
d
e
d
e
c
o
m
p
o
si
t
i
o
n
f
r
o
m
f
u
n
d
u
s
i
ma
g
e
s,
”
I
ET
I
m
a
g
e
Pro
c
e
ss
i
n
g
,
v
o
l
.
1
3
,
n
o
.
1
3
,
p
p
.
2
4
0
1
–
2
4
0
8
,
N
o
v
.
2
0
1
9
,
d
o
i
:
1
0
.
1
0
4
9
/
i
e
t
-
i
p
r
.
2
0
1
9
.
0
0
3
6
.
[
3
2
]
S
.
S
.
S
h
a
i
k
,
C
.
R
u
p
a
,
a
n
d
V
.
Y
a
d
l
a
p
a
l
l
i
,
“
S
e
c
u
r
e
me
d
i
c
a
l
d
a
t
a
a
b
st
r
a
c
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
,
”
i
n
1
1
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
I
n
t
e
rn
e
t
o
f
E
v
e
r
y
t
h
i
n
g
,
Mi
c
r
o
w
a
v
e
E
n
g
i
n
e
e
r
i
n
g
,
C
o
m
m
u
n
i
c
a
t
i
o
n
a
n
d
N
e
t
w
o
rks
,
I
EM
E
C
O
N
2
0
2
3
,
F
e
b
.
2
0
2
3
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
I
EM
EC
O
N
5
6
9
6
2
.
2
0
2
3
.
1
0
0
9
2
3
1
1
.
[
3
3
]
M
.
A
.
El
a
z
i
z
,
K
.
M
.
H
o
s
n
y
,
A
.
S
a
l
a
h
,
M
.
M
.
D
a
r
w
i
s
h
,
S
.
L
u
,
a
n
d
A
.
T.
S
a
h
l
o
l
,
“
N
e
w
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
m
e
t
h
o
d
f
o
r
i
ma
g
e
b
a
s
e
d
d
i
a
g
n
o
si
s
o
f
C
O
V
I
D
-
1
9
,
”
PL
o
S
O
N
E
,
v
o
l
.
1
5
,
n
o
.
6
,
p
.
e
0
2
3
5
1
8
7
,
J
u
n
.
2
0
2
0
,
d
o
i
:
1
0
.
1
3
7
1
/
j
o
u
r
n
a
l
.
p
o
n
e
.
0
2
3
5
1
8
7
.
[
3
4
]
A
.
R
e
h
ma
n
,
M
.
A
.
I
q
b
a
l
,
H
.
X
i
n
g
,
a
n
d
I
.
A
h
me
d
,
“
C
O
V
I
D
-
1
9
d
e
t
e
c
t
i
o
n
e
mp
o
w
e
r
e
d
w
i
t
h
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s
:
A
s
y
st
e
ma
t
i
c
r
e
v
i
e
w
,
”
A
p
p
l
i
e
d
S
c
i
e
n
c
e
s
(
S
w
i
t
zerl
a
n
d
)
,
v
o
l
.
1
1
,
n
o
.
8
,
p
.
3
4
1
4
,
A
p
r
.
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
1
0
8
3
4
1
4
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Dr
.
Ch.
R
u
p
a
(
se
n
io
r
m
e
m
b
e
r
,
IE
EE
)
is
c
u
rre
n
tl
y
a
p
ro
fe
ss
o
r
wit
h
VRSE
C
,
Vijay
a
wa
d
a
.
S
h
e
h
a
s
p
u
b
li
sh
e
d
m
o
re
th
a
n
1
0
0
a
rti
c
les
in
v
a
rio
u
s
jo
u
rn
a
ls
a
n
d
c
o
n
fe
re
n
c
e
s.
He
r
m
a
in
re
s
e
a
rc
h
in
tere
sts
in
c
lu
d
e
in
f
o
rm
a
ti
o
n
se
c
u
rit
y
,
b
l
o
c
k
c
h
a
in
,
m
a
c
h
in
e
lea
rn
in
g
,
a
n
d
AI
b
a
se
d
se
c
u
rit
y
a
p
p
r
o
a
c
h
e
s.
S
h
e
is
a
li
fe
m
e
m
b
e
r
o
f
C
S
I,
I
S
TE
,
IAENG
,
IEI
,
a
n
d
IACSIT
.
S
h
e
wa
s
li
ste
d
in
t
h
e
to
p
2
p
e
rc
e
n
t
o
f
sc
ien
ti
sts
b
y
S
ta
n
fo
r
d
U
n
iv
e
rsity
a
n
d
El
se
v
ier.
S
h
e
a
lso
b
a
g
g
e
d
m
a
n
y
n
a
ti
o
n
a
l
a
n
d
in
tern
a
ti
o
n
a
l
a
wa
rd
s
a
n
d
re
c
o
g
n
it
io
n
s,
l
ik
e
y
o
u
n
g
w
o
m
e
n
e
n
g
i
n
e
e
r,
t
e
c
h
n
o
m
e
d
ia,
I
EI,
a
n
d
IET
E.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
ru
p
a
m
t
e
c
h
@g
m
a
il
.
c
o
m
.
Dr
.
K
a
n
a
k
a
m
S
iv
a
Ra
m
a
Pra
s
a
d
is
c
u
rre
n
tl
y
wo
r
k
in
g
a
s
a
ss
o
c
iate
p
ro
fe
ss
o
r
in
th
e
D
e
p
a
rtme
n
t
o
f
CS
E
(AI&
M
L),
Ka
ll
a
m
Ha
ra
n
a
d
h
a
re
d
d
y
In
stit
u
te
o
f
Tec
h
n
o
lo
g
y
.
He
h
a
s
m
o
re
th
a
n
1
6
y
e
a
rs
o
f
te
a
c
h
in
g
e
x
p
e
rien
c
e
in
v
a
ri
o
u
s
p
re
m
ier
in
stit
u
tes
.
He
re
c
e
iv
e
d
P
h
.
D
.
in
Co
m
p
u
ter
S
c
ien
c
e
fro
m
Ka
li
n
g
a
Un
iv
e
rsity
,
Ra
i
p
u
r
in
2
0
2
1
.
He
p
u
b
li
sh
e
d
1
8
re
se
a
rc
h
a
rti
c
les
in
v
a
rio
u
s
in
ter
n
a
ti
o
n
a
l
jo
u
r
n
a
ls
a
n
d
a
lso
p
re
se
n
ted
re
se
a
r
c
h
c
o
n
tri
b
u
ti
o
n
s
in
in
tern
a
ti
o
n
a
l
c
o
n
fe
re
n
c
e
s.
His
a
re
a
s
o
f
re
se
a
rc
h
in
c
lu
d
e
c
o
m
p
u
ter
n
e
two
rk
s,
b
i
g
d
a
ta
a
n
a
ly
t
ics
,
m
a
c
h
in
e
lea
rn
in
g
,
d
e
e
p
lea
rn
i
n
g
,
a
n
d
c
lo
u
d
c
o
m
p
u
ti
n
g
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
d
r.
k
s
ra
m
p
ra
sa
d
@g
m
a
il
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.