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.
38
,
No
.
2
,
Ma
y
20
25
,
p
p
.
940
~
9
4
9
I
SS
N:
2
502
-
4
7
52
,
DOI
: 1
0
.
1
1
5
9
1
/ijee
cs
.v
38.
i
2
.
p
p
940
-
9
4
9
940
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs
.
ia
esco
r
e.
co
m
Dete
c
tion o
f
CO
V
ID
-
1
9
bas
ed on co
ug
h so
und a
nd
a
ccom
pa
ny
ing
sy
mpto
m using
Lig
htG
BM
alg
o
rith
m
Wiha
rt
o
,
Anna
s
Abd
urra
hm
a
n,
Um
i Sa
la
ma
h
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
m
a
t
i
c
s,
F
a
c
u
l
t
y
o
f
I
n
f
o
r
mat
i
o
n
T
e
c
h
n
o
l
o
g
y
a
n
d
D
a
t
a
S
c
i
e
n
c
e
,
U
n
i
v
e
r
si
t
a
s
S
e
b
e
l
a
s
M
a
r
e
t
,
S
u
r
a
k
a
r
t
a
,
I
n
d
o
n
e
si
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Mar
19
,
2
0
2
4
R
ev
is
ed
Oct
27
,
2
0
2
4
Acc
ep
ted
No
v
11
,
2
0
2
4
Co
ro
n
a
v
iru
s
d
ise
a
se
1
9
(
COV
ID
-
19
)
is
a
n
i
n
fe
c
ti
o
u
s
d
ise
a
se
wh
o
se
d
iag
n
o
sis is
c
a
rried
o
u
t
u
si
n
g
a
n
t
i
g
e
n
-
a
n
ti
b
o
d
y
tes
ts an
d
re
v
e
rse
tran
sc
rip
ti
o
n
p
o
l
y
m
e
ra
se
c
h
a
in
re
a
c
ti
o
n
(RT
-
P
CR).
Ap
a
rt
fro
m
th
e
se
tw
o
m
e
th
o
d
s,
se
v
e
ra
l
a
lt
e
rn
a
ti
v
e
e
a
rly
d
e
tec
ti
o
n
m
e
th
o
d
s
u
si
n
g
m
a
c
h
in
e
lea
r
n
in
g
h
a
v
e
b
e
e
n
d
e
v
e
lo
p
e
d
.
Ho
we
v
e
r,
it
stil
l
h
a
s
li
m
it
a
ti
o
n
s
in
a
c
c
e
ss
ib
il
it
y
,
is
in
v
a
siv
e
,
a
n
d
it
s
imp
lem
e
n
tatio
n
in
v
o
l
v
e
s
m
a
n
y
p
a
rti
e
s,
wh
ic
h
c
o
u
ld
p
o
te
n
t
ially
e
v
e
n
in
c
re
a
se
th
e
risk
o
f
s
p
re
a
d
in
g
C
OV
ID
-
1
9
.
Th
e
re
fo
re
,
th
is
re
se
a
rc
h
a
ims
to
d
e
v
e
lo
p
a
n
a
lt
e
rn
a
ti
v
e
e
a
rly
d
e
t
e
c
ti
o
n
m
e
th
o
d
t
h
a
t
is
n
o
n
-
i
n
v
a
siv
e
b
y
u
ti
li
z
i
n
g
th
e
Li
g
h
tG
BM
a
lg
o
rit
h
m
to
d
e
tec
t
COV
ID
-
1
9
b
a
se
d
o
n
th
e
re
su
lt
s
o
f
fe
a
tu
re
e
x
trac
ti
o
n
fro
m
c
o
u
g
h
so
u
n
d
s
a
n
d
a
c
c
o
m
p
a
n
y
i
n
g
s
y
m
p
to
m
s
th
a
t
c
a
n
b
e
id
e
n
ti
fied
in
d
e
p
e
n
d
e
n
tl
y
.
Th
is
re
se
a
rc
h
u
se
s
c
o
u
g
h
so
u
n
d
sa
m
p
les
an
d
s
y
m
p
to
m
d
a
ta
fr
o
m
t
h
e
Co
sw
a
ra
d
a
tas
e
t,
a
n
d
c
o
u
g
h
so
u
n
d
’s
fe
a
tu
re
s
we
re
e
x
trac
ted
u
sin
g
th
e
lo
g
m
e
l
-
sp
e
c
tro
g
ra
m
,
m
e
l
fre
q
u
e
n
c
y
c
e
p
stru
m
c
o
e
fficie
n
t
(M
F
CC)
,
c
h
ro
m
a
,
z
e
ro
c
ro
ss
in
g
ra
te
(ZCR),
a
n
d
r
o
o
t
m
e
a
n
sq
u
a
re
(RM
S
)
m
e
th
o
d
s.
Ne
x
t
,
t
h
e
c
o
u
g
h
so
u
n
d
fe
a
t
u
re
s
a
re
c
o
m
b
in
e
d
with
sy
m
p
to
m
d
a
ta
t
o
t
ra
in
th
e
Li
g
h
tG
BM
.
T
h
e
m
o
d
e
l
trai
n
e
d
u
si
n
g
c
o
u
g
h
so
u
n
d
fe
a
tu
re
s
a
n
d
p
a
ti
e
n
t
sy
m
p
to
m
s
o
b
tain
e
d
t
h
e
b
e
st
p
e
rfo
rm
a
n
c
e
wit
h
9
5
.
6
1
%
a
c
c
u
ra
c
y
,
9
3
.
3
3
%
a
re
a
u
n
d
e
r
c
u
rv
e
(
AUC
)
,
8
8
.
7
4
%
se
n
siti
v
it
y
,
9
7
.
9
1
%
sp
e
c
ifi
c
it
y
,
9
3
.
1
7
%
p
o
siti
v
e
p
re
d
ictio
n
v
a
lu
e
(
PPV
)
,
a
n
d
9
6
.
3
3
%
n
e
g
a
ti
v
e
p
re
d
ictio
n
v
a
lu
e
(
NPV
)
.
It
c
a
n
b
e
c
o
n
c
l
u
d
e
d
th
a
t
th
e
train
e
d
m
o
d
e
l
h
a
s
e
x
c
e
ll
e
n
t
c
las
sifica
ti
o
n
c
a
p
a
b
i
li
ti
e
s b
a
se
d
o
n
th
e
AU
C
v
a
lu
e
s o
b
tain
e
d
.
K
ey
w
o
r
d
s
:
C
o
r
o
n
av
ir
u
s
d
is
ea
s
e
1
9
C
o
u
g
h
L
ig
h
tGB
M
Sy
m
p
to
m
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
:
W
ih
ar
to
Dep
ar
tm
en
t o
f
I
n
f
o
r
m
atics,
Facu
lty
o
f
I
n
f
o
r
m
at
io
n
T
ec
h
n
o
l
o
g
y
an
d
Data
Scien
ce
Un
iv
er
s
iti Seb
elas M
ar
et
St
.
I
r
.
Su
tam
i,
No
.
3
6
A,
Ken
ti
n
g
an
,
Su
r
ak
ar
ta,
I
n
d
o
n
esia
E
m
ail: w
ih
ar
to
@
s
taf
f
.
u
n
s
.
ac
.
id
1.
I
NT
RO
D
UCT
I
O
N
C
o
r
o
n
av
ir
u
s
d
is
ea
s
e
1
9
(
C
OVI
D
-
19
)
is
a
co
n
tag
io
u
s
d
is
ea
s
e
ca
u
s
ed
b
y
s
ev
er
e
ac
u
te
r
esp
ir
ato
r
y
s
y
n
d
r
o
m
e
co
r
o
n
av
ir
u
s
2
(
SA
R
S
-
C
o
V
-
2
)
an
d
was
f
ir
s
t
d
etec
ted
in
th
e
city
o
f
W
u
h
a
n
,
C
h
in
a,
at
th
e
en
d
o
f
2
0
1
9
.
T
h
e
s
y
m
p
t
o
m
s
v
a
r
y
,
r
an
g
in
g
f
r
o
m
r
esp
ir
ato
r
y
in
f
e
ctio
n
-
lik
e
s
y
m
p
to
m
s
s
u
ch
as
f
ev
er
,
co
u
g
h
,
s
o
r
e
th
r
o
at,
s
tu
f
f
y
n
o
s
e,
h
e
ad
ac
h
e,
m
u
s
cle
p
ain
,
an
d
m
alaise
to
s
e
v
er
e
ca
s
es
th
at
ca
n
lead
to
p
n
e
u
m
o
n
ia
an
d
d
ea
th
.
So
m
e
s
y
m
p
to
m
s
ca
n
also
o
cc
u
r
b
u
t
r
ar
ely
,
s
u
ch
as
d
ia
r
r
h
ea
an
d
an
o
s
m
ia
[
1
]
.
C
lin
ically
d
iag
n
o
s
is
o
f
C
OVI
D
-
1
9
u
s
es
an
tig
en
-
an
ti
b
o
d
y
an
d
r
ev
e
r
s
e
tr
a
n
s
cr
ip
tio
n
p
o
ly
m
er
ase
ch
ai
n
r
ea
ctio
n
(
RT
-
PC
R
)
,
with
RT
-
PC
R
as
th
e
g
o
l
d
s
tan
d
ar
d
[
1
]
.
T
wo
d
if
f
er
en
t
m
eth
o
d
s
h
av
e
lately
b
ee
n
p
u
t
f
o
r
th
in
th
e
liter
atu
r
e
f
o
r
th
e
d
iag
n
o
s
is
o
f
C
OVI
D
-
1
9
in
f
ec
tio
n
u
s
in
g
co
m
p
u
ter
te
m
o
g
r
ap
h
y
(
CT
)
o
r
X
-
r
ay
i
m
ag
e
an
aly
s
is
[
2
]
.
Un
f
o
r
tu
n
atel
y
,
th
is
alter
n
ativ
e
m
eth
o
d
s
till
h
as
p
r
o
b
lem
s
i
n
ter
m
s
o
f
ac
ce
s
s
ib
ilit
y
an
d
h
as
th
e
p
o
ten
tial
to
in
cr
ea
s
e
th
e
r
is
k
o
f
s
p
r
ea
d
in
g
C
OVI
D
-
1
9
b
ec
au
s
e
im
p
lem
en
tatio
n
in
v
o
lv
es m
a
n
y
p
a
r
ties
.
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
ctio
n
o
f COVI
D
-
1
9
b
a
s
ed
o
n
co
u
g
h
s
o
u
n
d
a
n
d
a
cc
o
m
p
a
n
yin
g
s
ymp
to
n
u
s
in
g
…
(
Wih
a
r
to
)
941
Sev
er
al
s
tu
d
ies
h
av
e
also
tr
ied
to
u
s
e
th
e
s
o
u
n
d
o
f
c
o
u
g
h
i
n
g
to
d
etec
t
C
OVI
D
-
1
9
.
C
O
VI
D
-
1
9
h
as
s
y
m
p
to
m
s
o
f
a
d
r
y
c
o
u
g
h
wit
h
ch
ar
ac
ter
is
tics
o
f
h
ig
h
e
r
f
r
e
q
u
en
cy
an
d
s
h
o
r
ter
d
u
r
atio
n
c
o
m
p
ar
ed
to
c
o
u
g
h
s
f
r
o
m
o
th
er
r
esp
ir
at
o
r
y
d
is
ea
s
es
[
3
]
.
T
h
e
co
u
g
h
s
o
u
n
d
o
f
C
OVI
D
-
1
9
also
h
as
d
if
f
er
en
t
late
n
t
f
ea
tu
r
es
an
d
th
e
r
is
k
o
f
laten
t
f
ea
tu
r
e
o
v
e
r
lap
with
th
e
f
ea
tu
r
e
o
f
co
u
g
h
s
o
u
n
d
o
f
o
th
er
d
is
ea
s
es
is
lo
w.
T
h
is
d
if
f
er
en
ce
o
cc
u
r
s
b
ec
au
s
e
C
OVI
D
-
1
9
in
f
ec
tio
n
af
f
ec
ts
th
e
r
esp
ir
ato
r
y
s
y
s
tem
u
n
iq
u
ely
th
an
th
e
o
th
er
[
2
]
.
Var
io
u
s
s
tu
d
ies
h
av
e
ex
p
l
o
r
e
d
d
if
f
er
e
n
t
m
eth
o
d
s
to
ex
tr
ac
t
f
ea
tu
r
es
f
r
o
m
co
u
g
h
s
o
u
n
d
s
an
d
p
atien
t
s
y
m
p
to
m
s
f
o
r
C
OVI
D
-
1
9
d
e
tectio
n
.
I
n
th
e
w
o
r
k
C
h
o
wd
h
u
r
y
e
t
a
l.
[
4
]
,
ex
tr
a
-
tr
ee
s
tr
a
in
ed
o
n
co
m
b
in
ed
d
atasets
ac
h
iev
ed
an
ar
ea
u
n
d
er
cu
r
v
e
(
AUC
)
o
f
0
.
7
9
,
wh
ile
HGBo
o
s
t
o
n
th
e
C
o
s
war
a
d
ataset
r
ea
ch
ed
an
AUC o
f
0
.
6
6
.
An
o
th
er
s
tu
d
y
co
m
b
in
ed
d
atasets
f
r
o
m
m
u
ltip
le
s
o
u
r
ce
s
,
ac
h
iev
in
g
an
ac
cu
r
a
cy
o
f
0
.
9
2
1
an
d
an
AUC
o
f
0
.
9
7
3
with
a
VGGN
et
m
o
d
el.
Un
f
o
r
tu
n
ately
,
in
th
a
t
s
tu
d
y
w
h
en
u
s
in
g
o
n
ly
th
e
C
o
s
war
a
d
ataset,
th
e
m
o
d
el
p
r
o
d
u
ce
d
p
er
f
o
r
m
a
n
ce
,
f
o
r
ac
cu
r
ac
y
p
ar
a
m
eter
s
o
f
0
.
7
1
2
an
d
AUC
o
f
0
.
7
8
1
[
5
]
.
T
h
is
p
er
f
o
r
m
a
n
ce
is
s
till
r
elativ
ely
lo
w,
if
r
ef
er
r
in
g
to
th
e
AUC v
alu
e
th
e
n
t
h
e
m
o
d
el
is
o
n
ly
in
clu
d
ed
in
t
h
e
f
air
ca
teg
o
r
y
.
So
m
e
s
tu
d
ies
h
av
e
also
ex
p
lo
r
ed
a
co
m
b
in
atio
n
o
f
co
u
g
h
s
o
u
n
d
f
ea
tu
r
es
with
s
y
m
p
to
m
an
d
r
esp
ir
ato
r
y
c
o
n
d
itio
n
d
ata
.
T
h
e
wo
r
k
R
ah
o
u
m
a
et
a
l.
[
6
]
u
tili
ze
d
p
atien
t
v
o
ices
an
d
s
y
m
p
to
m
d
ata
f
r
o
m
th
e
C
o
s
war
a
d
ata
s
et.
T
h
e
n
eu
r
al
n
etwo
r
k
tr
ain
ed
with
co
u
g
h
s
o
u
n
d
alo
n
e
ac
h
iev
ed
a
n
av
er
a
g
e
ac
cu
r
ac
y
o
f
8
4
%
an
d
an
AUC
o
f
8
2
%.
Usi
n
g
s
y
m
p
to
m
d
ata
alo
n
e
r
esu
lted
in
an
av
er
a
g
e
ac
cu
r
a
cy
o
f
7
3
%
an
d
an
AUC
o
f
7
8
%.
C
o
m
b
in
in
g
b
o
th
f
ea
tu
r
e
s
y
ield
ed
a
n
av
e
r
ag
e
ac
c
u
r
ac
y
o
f
9
1
%
a
n
d
a
n
AUC
o
f
8
8
%
.
On
e
s
tu
d
y
o
n
th
e
C
o
u
g
h
v
id
d
ataset
u
s
in
g
a
m
u
lti
-
b
r
an
ch
d
ee
p
lear
n
in
g
n
etwo
r
k
(
MBDLN
)
ac
h
iev
ed
a
n
AUC
o
f
9
1
%
[
7
]
.
L
a
s
t
l
y
,
a
h
i
e
r
a
r
c
h
i
c
a
l
m
u
l
t
i
-
m
o
d
a
l
t
r
a
n
s
f
o
r
m
e
r
(
H
M
T
)
t
r
ai
n
e
d
o
n
s
y
m
p
t
o
m
d
a
t
a
a
n
d
c
o
u
g
h
s
o
u
n
d
f
e
a
t
u
r
e
s
f
r
o
m
t
h
e
C
o
u
g
h
v
i
d
a
n
d
C
o
s
w
a
r
a
d
a
ta
s
e
ts
,
a
c
h
i
e
v
e
d
a
n
a
v
e
r
a
g
e
a
c
cu
r
a
c
y
o
f
8
1
.
3
2
%
a
n
d
a
n
A
U
C
o
f
8
2
.
0
6
%
[
8
]
.
Pre
v
io
u
s
r
esear
ch
th
at
co
m
b
i
n
ed
co
u
g
h
s
o
u
n
d
an
d
s
y
m
p
t
o
m
f
ea
tu
r
es
was
ab
le
t
o
p
r
o
v
id
e
b
etter
p
er
f
o
r
m
an
ce
,
c
o
m
p
a
r
ed
to
u
s
in
g
o
n
ly
co
u
g
h
s
o
u
n
d
f
ea
tu
r
es.
Un
f
o
r
tu
n
ately
,
p
r
ev
io
u
s
s
tu
d
i
es
u
s
ed
s
y
m
p
to
m
s
g
en
er
ated
f
r
o
m
ex
p
er
t
e
x
am
i
n
atio
n
.
T
h
is
was
s
h
o
wn
in
a
s
tu
d
y
b
y
[
6
]
,
w
h
ich
u
s
ed
p
n
e
u
m
o
n
ia
a
n
d
asth
m
a
s
y
m
p
to
m
d
ata,
wh
er
e
th
ese
s
y
m
p
to
m
s
r
eq
u
ir
e
ex
p
e
r
t
d
iag
n
o
s
is
[
9
]
.
T
h
e
s
am
e
th
in
g
was
al
s
o
d
o
n
e
in
r
esear
ch
co
n
d
u
cte
d
b
y
[
7
]
,
[
8
]
u
s
in
g
r
e
s
p
ir
ato
r
y
co
n
d
itio
n
d
ata
f
r
o
m
ex
p
er
t
d
iag
n
o
s
is
[
1
0
]
.
R
ef
er
r
i
n
g
to
a
n
u
m
b
e
r
o
f
s
tu
d
ies
th
at
h
av
e
b
ee
n
co
n
d
u
cted
,
it
s
h
o
ws
th
at
th
e
C
OVI
D
-
1
9
ex
am
i
n
atio
n
ca
n
n
o
t
b
e
d
o
n
e
in
d
ep
en
d
en
tly
.
T
h
is
is
b
ec
au
s
e
it
s
till
r
eq
u
ir
e
s
th
e
h
elp
o
f
a
d
o
cto
r
,
n
am
ely
wh
en
i
d
en
tif
y
in
g
s
y
m
p
t
o
m
s
,
s
u
ch
as
p
n
e
u
m
o
n
ia
,
asth
m
a,
an
d
r
esp
ir
ato
r
y
co
n
d
i
tio
n
s
.
I
f
o
n
ly
r
ely
in
g
o
n
th
e
co
u
g
h
s
o
u
n
d
f
ea
tu
r
e,
th
e
m
o
d
el
ca
n
n
o
t
p
r
o
d
u
ce
o
p
tim
al
p
er
f
o
r
m
an
ce
.
R
ef
er
r
in
g
to
a
n
u
m
b
e
r
o
f
p
r
ev
i
o
u
s
s
tu
d
ies,
th
is
s
tu
d
y
p
r
o
p
o
s
es a
C
OVI
D
-
19
d
etec
tio
n
m
o
d
e
l th
at
c
an
b
e
ca
r
r
ied
o
u
t
i
n
d
ep
e
n
d
en
tly
,
u
s
in
g
th
e
L
ig
h
tGB
M
class
if
i
ca
tio
n
alg
o
r
ith
m
.
T
h
is
m
o
d
el
u
s
es
co
u
g
h
s
o
u
n
d
f
ea
tu
r
es
an
d
s
y
m
p
to
m
s
.
T
h
e
s
y
m
p
to
m
s
u
s
ed
ar
e
s
y
m
p
t
o
m
s
th
at
ca
n
b
e
r
ec
o
g
n
ized
in
d
ep
e
n
d
en
tly
,
s
o
th
e
y
d
o
n
o
t
r
e
q
u
ir
e
ex
am
in
atio
n
b
y
a
d
o
cto
r
.
T
h
e
m
o
d
el
was
d
ev
elo
p
ed
u
s
in
g
th
e
C
o
s
war
a
d
ataset,
with
th
e
s
y
m
p
to
m
s
u
s
ed
b
ein
g
d
if
f
icu
lty
b
r
ea
th
in
g
,
r
u
n
n
y
n
o
s
e,
co
u
g
h
,
f
ev
e
r
,
an
o
s
m
ia,
m
u
s
cle
p
ain
,
s
o
r
e
th
r
o
at,
d
iar
r
h
ea
,
an
d
f
atig
u
e.
T
h
e
p
e
r
f
o
r
m
a
n
c
e
o
f
t
h
e
p
r
o
p
o
s
e
d
m
o
d
el
is
m
e
as
u
r
e
d
u
s
i
n
g
t
h
e
p
e
r
f
o
r
m
a
n
c
e
p
a
r
a
m
e
t
e
r
s
o
f
a
c
c
u
r
a
c
y
,
s
e
n
s
i
ti
v
i
t
y
,
s
p
ec
i
f
i
ci
ty
,
AUC
,
p
o
s
i
ti
v
e
p
r
e
d
i
c
t
i
o
n
v
a
lu
e
(
P
P
V
)
,
a
n
d
n
e
g
a
ti
v
e
p
r
e
d
i
c
tio
n
v
a
l
u
e
(
N
P
V
)
.
2.
M
E
T
H
O
D
T
h
e
wo
r
k
s
tag
es
in
th
is
s
tu
d
y
s
tar
t
f
r
o
m
th
e
p
r
e
p
ar
atio
n
o
f
d
atasets
an
d
s
eg
m
en
tatio
n
o
f
c
o
u
g
h
s
o
u
n
d
s
,
d
ata
p
r
e
p
r
o
ce
s
s
in
g
,
tr
ain
in
g
th
r
ee
m
ac
h
in
e
lear
n
i
n
g
m
o
d
els
tr
ain
ed
with
d
if
f
e
r
en
t
f
ea
tu
r
e
s
u
b
s
ets,
an
d
en
d
with
ev
al
u
atin
g
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
t
h
r
ee
m
o
d
els
t
h
at
h
av
e
b
ee
n
t
r
ain
ed
.
T
h
e
s
t
ag
es
o
f
th
e
r
esear
ch
p
r
o
ce
s
s
ca
n
b
e
s
ee
n
i
n
Fig
u
r
e
1
.
2
.
1
.
P
re
pa
ring
t
he
da
t
a
s
et
a
nd
co
ug
h seg
m
ent
a
t
io
n
T
h
e
d
ataset
u
s
ed
co
m
es
f
r
o
m
th
e
C
o
s
war
a
d
ataset.
I
t
co
n
tain
s
r
ec
o
r
d
in
g
s
o
f
co
u
g
h
s
o
u
n
d
s
,
b
r
ea
th
in
g
,
an
d
p
r
o
n
u
n
ciatio
n
o
f
s
o
m
e
letter
s
o
r
p
h
r
ases
f
r
o
m
v
o
lu
n
teer
s
,
alo
n
g
with
m
etad
ata
co
n
tain
in
g
in
f
o
r
m
atio
n
ab
o
u
t
clin
ical
s
y
m
p
to
m
s
an
d
h
ea
lth
h
is
to
r
y
[
1
1
]
.
E
v
e
n
th
o
u
g
h
th
e
v
o
lu
n
tee
r
s
u
b
m
itted
v
a
r
io
u
s
ty
p
es
o
f
s
o
u
n
d
s
,
th
is
r
esear
ch
o
n
ly
u
s
ed
co
u
g
h
s
o
u
n
d
b
ec
a
u
s
e
o
f
its
co
n
s
is
ten
cy
ac
r
o
s
s
i
n
d
iv
id
u
als,
it’s
n
o
t
af
f
ec
ted
b
y
ac
ce
n
t a
n
d
th
e
s
h
a
r
p
s
o
u
n
d
is
ea
s
ily
d
if
f
er
en
tia
te
d
f
r
o
m
o
th
er
s
o
u
n
d
s
[
4
]
.
T
o
o
v
er
c
o
m
e
th
e
im
b
alan
ce
i
n
th
e
am
o
u
n
t
o
f
d
ata
in
th
e
C
o
s
war
a
d
ataset,
o
n
ly
a
f
ew
r
elev
an
t
d
ata
lab
els
wer
e
u
s
ed
an
d
co
m
b
in
e
d
in
to
two
m
ain
class
es,
n
am
e
ly
"n
eg
ativ
e"
(
0
)
class
wh
ich
in
clu
d
es
d
ata
with
th
e
lab
el
"h
ea
lth
y
"
an
d
th
e
"p
o
s
itiv
e"
class
(
1
)
w
h
ich
in
clu
d
es
d
ata
lab
eled
as
"
p
o
s
itiv
e_
m
ild
"
an
d
"p
o
s
itiv
e_
m
o
d
e
r
ate"
.
E
ac
h
v
o
lu
n
teer
s
u
b
m
itted
two
ty
p
e
s
o
f
co
u
g
h
s
o
u
n
d
s
am
p
les,
"h
ea
v
y
_
c
o
u
g
h
"
an
d
"sh
allo
w_
co
u
g
h
"
,
b
u
t
o
n
ly
th
e
h
ea
v
y
c
o
u
g
h
s
o
u
n
d
s
wer
e
u
s
ed
in
th
is
s
tu
d
y
to
en
s
u
r
e
c
o
n
s
is
ten
cy
[
4
]
.
T
h
e
s
elec
ted
s
y
m
p
to
m
s
in
clu
d
e
d
if
f
icu
lty
b
r
ea
th
in
g
,
co
ld
,
c
o
u
g
h
,
f
ev
er
,
a
n
o
s
m
ia,
m
u
s
cle
p
ain
,
s
o
r
e
th
r
o
at,
d
iar
r
h
ea
,
an
d
f
atig
u
e
.
T
h
e
s
elec
tio
n
o
f
th
ese
9
s
y
m
p
to
m
s
was
m
ad
e
b
y
ex
clu
d
i
n
g
asth
m
a,
d
iab
etes,
is
ch
em
ic
h
ea
r
t
d
is
ea
s
e,
ch
r
o
n
ic
o
b
s
t
r
u
c
tiv
e
p
u
lm
o
n
ar
y
d
is
ea
s
e,
an
d
p
n
eu
m
o
n
ia,
d
u
e
to
co
m
p
lex
d
iag
n
o
s
tic
m
eth
o
d
s
in
v
o
lv
i
n
g
v
ar
io
u
s
m
ed
ical
ass
ess
m
en
ts
[
9
]
,
[
1
2
]
–
[
1
5
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
38
,
No
.
2
,
May
20
25
:
9
4
0
-
9
4
9
942
C
o
u
g
h
s
o
u
n
d
s
eg
m
e
n
tatio
n
was
p
er
f
o
r
m
ed
o
n
all
s
am
p
les
to
cr
ea
te
a
n
ew
d
ataset
co
n
s
i
s
tin
g
o
f
a
s
in
g
le
co
u
g
h
s
o
u
n
d
.
Seg
m
en
tatio
n
will
en
h
an
ce
co
n
s
is
ten
cy
,
en
s
u
r
e
co
m
p
lete
co
u
g
h
s
o
u
n
d
s
,
f
o
cu
s
o
n
r
elev
an
t
f
ea
t
u
r
es,
an
d
in
c
r
ea
s
e
tr
ain
in
g
s
am
p
les
b
y
u
s
in
g
th
e
h
y
s
ter
esis
co
m
p
ar
at
o
r
m
et
h
o
d
p
r
o
p
o
s
ed
b
y
[
1
0
]
.
T
h
e
r
esu
lt
is
a
n
ew
d
ataset
co
n
s
is
tin
g
o
f
co
u
g
h
s
o
u
n
d
s
eg
m
en
t
au
d
io
f
iles
,
m
etad
a
ta
wi
th
s
am
p
le
I
Ds,
f
ile
lo
ca
tio
n
s
,
s
y
m
p
to
m
d
ata,
an
d
l
ab
els.
Fig
u
r
e
1
.
Stag
es o
f
r
esear
ch
2
.
2
.
P
re
pro
ce
s
s
ing
At
th
is
s
tag
e,
an
ar
r
ay
th
at
will
b
e
u
s
ed
f
o
r
th
e
m
o
d
el
in
p
u
t
is
f
o
r
m
e
d
.
I
t
will
in
clu
d
e
c
o
u
g
h
s
o
u
n
d
f
ea
tu
r
es
o
b
tain
e
d
th
r
o
u
g
h
au
d
io
f
ea
tu
r
e
e
x
tr
ac
tio
n
u
s
in
g
f
i
v
e
m
eth
o
d
s
:
L
o
g
m
el
-
s
p
ec
tr
o
g
r
am
,
m
el
f
r
e
q
u
en
c
y
ce
p
s
tr
u
m
co
ef
f
icien
t
(
MFC
C
)
,
c
h
r
o
m
a
s
h
o
r
t
tim
e
f
o
u
r
ier
t
r
an
s
f
o
r
m
(
STFT
)
,
ze
r
o
cr
o
s
s
in
g
r
ate
(
Z
C
R
)
,
an
d
r
o
o
t m
ea
n
s
q
u
a
r
e
(
R
MS)
.
L
o
g
m
el
-
s
p
ec
tr
o
g
r
am
r
ep
r
esen
ts
th
e
en
er
g
y
o
f
th
e
a
u
d
io
s
ig
n
al
i
n
th
e
f
r
eq
u
en
cy
a
n
d
tim
e
d
o
m
ain
.
T
h
is
is
d
o
n
e
b
y
t
r
an
s
f
o
r
m
in
g
th
e
s
ig
n
al
in
to
th
e
f
r
eq
u
e
n
cy
d
o
m
ain
u
s
in
g
ST
FT,
th
en
co
n
v
e
r
tin
g
th
e
f
r
eq
u
en
cy
i
n
to
th
e
Me
l
s
c
ale
th
at
is
m
o
r
e
s
u
itab
le
f
o
r
h
u
m
an
h
ea
r
in
g
b
y
c
h
an
g
in
g
th
e
f
r
eq
u
e
n
cy
v
alu
e
f
u
s
in
g
(
1
)
.
(
)
=
2595
×
10
(
1
+
700
)
(
1
)
Fin
ally
,
ap
p
ly
lo
g
ar
ith
m
s
ca
le
o
f
th
e
en
e
r
g
y
t
o
co
n
s
id
er
t
h
e
lo
g
ar
ith
m
ic
p
e
r
ce
p
tio
n
o
f
h
e
ar
in
g
.
T
h
e
r
esu
lt
is
a
m
atr
ix
o
f
en
e
r
g
y
s
p
ec
tr
u
m
in
th
e
m
el
s
ca
le
f
o
r
ea
ch
tim
e
f
r
am
e
[
1
6
]
.
MFC
C
is
in
ten
d
ed
to
r
ep
licate
h
u
m
an
h
ea
r
in
g
ch
a
r
ac
ter
is
tics
.
T
h
i
s
i
n
v
o
l
v
es
t
r
a
n
s
f
o
r
m
i
n
g
th
e
s
i
g
n
a
l
i
n
t
o
t
h
e
f
r
e
q
u
e
n
c
y
d
o
m
a
i
n
u
s
i
n
g
S
T
F
T
,
c
o
n
v
e
r
t
i
n
g
t
h
e
f
r
e
q
u
e
n
c
y
i
n
t
o
t
h
e
m
e
l
s
c
a
l
e
u
s
i
n
g
(
1
)
,
t
a
k
i
n
g
t
h
e
l
o
g
a
r
i
t
h
m
o
f
t
h
e
s
o
u
n
d
i
n
t
e
n
s
i
t
y
,
a
n
d
a
p
p
l
y
i
n
g
t
h
e
d
i
s
c
r
et
e
c
o
s
i
n
e
t
r
a
n
s
f
o
r
m
t
o
g
e
n
e
r
a
t
e
c
e
p
s
t
r
a
l
c
o
e
f
f
i
ci
e
n
ts
,
y
i
e
l
d
i
n
g
a
c
e
p
s
t
r
a
l
c
o
e
f
f
ic
i
e
n
t
m
a
t
r
i
x
[
1
7
]
.
C
h
r
o
m
a
f
ea
tu
r
e
d
iv
i
d
es
th
e
a
u
d
io
s
ig
n
al
i
n
to
ch
r
o
m
a
a
n
d
p
itch
,
m
ap
p
in
g
th
e
f
r
eq
u
e
n
cy
f
r
o
m
th
e
STFT
in
to
th
e
ch
r
o
m
a
s
ca
le,
an
d
p
r
o
d
u
cin
g
a
v
ec
to
r
o
f
1
2
ch
r
o
m
a
v
alu
es
r
e
p
r
esen
tin
g
1
2
b
asic
t
o
n
es
[
1
8
]
.
R
MS
i
s
a
s
im
p
le
f
ea
tu
r
e
th
at
p
r
o
v
id
es
in
f
o
r
m
atio
n
a
b
o
u
t
th
e
s
tr
en
g
th
o
r
in
ten
s
ity
o
f
s
o
u
n
d
o
v
e
r
a
p
er
io
d
o
f
tim
e
[
1
9
]
.
R
MS
ca
n
b
e
o
b
tain
ed
u
s
in
g
(
2
)
.
=
√
1
∑
|
(
)
|
2
(
2
)
Z
C
R
g
iv
es
a
r
o
u
g
h
esti
m
ate
o
f
th
e
d
o
m
i
n
an
t
f
r
eq
u
e
n
cy
in
th
e
au
d
io
s
ig
n
al
b
y
c
o
u
n
tin
g
h
o
w
m
an
y
tim
es
th
e
s
o
u
n
d
am
p
litu
d
e
cr
o
s
s
es
ze
r
o
with
in
a
s
p
ec
if
ic
tim
e
[
1
8
]
.
T
h
e
e
x
tr
ac
tio
n
r
esu
lts
f
o
r
ea
ch
f
ea
tu
r
e
ar
e
p
r
o
ce
s
s
ed
b
y
ca
lcu
latin
g
th
e
m
ea
n
v
alu
e
f
o
r
all
f
r
am
es
f
o
r
ea
ch
f
ea
tu
r
e
co
ef
f
icien
t
o
r
f
ea
tu
r
e
ty
p
e
.
N
e
x
t
,
t
h
e
s
e
l
e
ct
e
d
p
a
t
i
e
n
t
s
y
m
p
t
o
m
d
a
ta
f
o
r
e
a
c
h
s
a
m
p
l
e
is
c
o
n
v
e
r
t
e
d
i
n
t
o
b
i
n
a
r
y
r
e
p
r
e
s
e
n
t
a
ti
o
n
a
n
d
a
d
d
e
d
t
o
t
h
e
d
a
t
a
s
e
t
.
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
ctio
n
o
f COVI
D
-
1
9
b
a
s
ed
o
n
co
u
g
h
s
o
u
n
d
a
n
d
a
cc
o
m
p
a
n
yin
g
s
ymp
to
n
u
s
in
g
…
(
Wih
a
r
to
)
943
2
.
3
.
T
ra
ini
ng
T
h
e
n
ex
t
s
tag
e
is
to
tr
ain
th
e
m
ac
h
in
e
lear
n
in
g
m
o
d
el
u
s
in
g
th
e
s
tr
atif
ied
k
-
f
o
ld
c
r
o
s
s
-
v
alid
atio
n
(
SKC
V)
m
eth
o
d
.
SKC
V
will
d
iv
id
e
th
e
d
ataset
in
t
o
k
s
u
b
s
e
ts
ca
lled
f
o
ld
s
wh
ich
s
ize
an
d
d
ata
d
is
tr
ib
u
tio
n
ar
e
th
e
s
am
e.
Fo
ld
d
iv
is
io
n
is
b
as
ed
o
n
I
D
to
av
o
id
d
u
p
licate
c
o
u
g
h
s
am
p
les
in
tr
ain
in
g
a
n
d
test
in
g
s
u
b
s
ets
with
th
e
s
am
e
I
D.
I
n
ev
er
y
tr
ain
i
n
g
p
r
o
ce
s
s
,
o
n
e
-
f
o
ld
will b
e
s
elec
ted
as v
alid
atio
n
d
ata
an
d
th
e
r
est will b
e
u
s
ed
a
s
d
ata
to
tr
ain
th
e
m
o
d
el.
T
h
en
t
h
e
m
o
d
el
p
er
f
o
r
m
an
ce
is
ca
lcu
lated
f
r
o
m
v
alid
atio
n
d
ata
[
2
0
]
.
T
h
r
ee
m
o
d
els
ar
e
tr
ain
ed
with
d
if
f
er
en
t
f
ea
tu
r
e
s
u
b
s
ets:
co
u
g
h
s
o
u
n
d
(
m
o
d
el
1
)
,
s
y
m
p
to
m
d
ata
(
m
o
d
el
2
)
,
an
d
co
m
b
i
n
atio
n
o
f
b
o
th
f
ea
tu
r
es
(
m
o
d
el
3
)
.
I
n
ea
ch
f
o
l
d
iter
atio
n
,
th
e
tr
a
in
in
g
d
ata
will
b
e
o
v
er
s
am
p
led
f
ir
s
t
u
s
in
g
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
-
s
y
n
t
h
etic
m
in
o
r
ity
o
v
er
s
am
p
lin
g
tech
n
iq
u
e
(
SVM
-
SMOT
E
)
to
h
an
d
le
class
im
b
alan
ce
wh
ich
co
m
b
i
n
es
SVM
an
d
SMOT
E
to
cr
ea
te
s
y
n
th
etic
s
am
p
les
[
2
1
]
.
T
h
e
o
v
er
s
am
p
led
d
ata
is
th
e
n
u
s
e
d
to
tr
ai
n
L
ig
h
tGB
M.
L
ig
h
tGB
M
is
a
g
r
ad
ien
t
b
o
o
s
tin
g
d
e
cisi
o
n
tr
ee
(
GB
DT
)
alg
o
r
i
th
m
th
at
im
p
le
m
en
ts
g
r
a
d
ien
t
-
b
ased
o
n
e
-
s
id
e
s
am
p
lin
g
(
GOSS)
an
d
ex
clu
s
iv
e
f
ea
tu
r
e
b
u
n
d
lin
g
(
E
FB
)
.
GOSS
o
p
tim
izes
tr
ain
in
g
ef
f
icien
cy
b
y
f
o
cu
s
in
g
o
n
tr
ain
in
g
m
o
d
els
o
n
d
ata
with
lar
g
e
g
r
ad
ie
n
ts
an
d
s
am
p
lin
g
d
ata
with
s
m
all
g
r
a
d
ien
ts
.
E
FB
will
r
ed
u
ce
f
ea
tu
r
e
co
m
p
lex
ity
b
y
c
o
m
b
in
i
n
g
m
u
tu
ally
ex
clu
s
iv
e
f
ea
tu
r
es
[
2
2
]
.
I
n
itially
,
L
ig
h
t
GB
M
ap
p
lies
E
FB
to
tr
ain
d
ata.
Mo
d
el
is
in
itialized
with
in
itial
p
r
ed
ictio
n
s
m
in
im
izin
g
lo
s
s
.
Du
r
in
g
GB
DT
im
p
lem
en
tatio
n
,
L
i
g
h
tGB
M
u
s
es
GOS
S
to
r
esam
p
le
th
e
d
ataset.
I
n
f
o
r
m
atio
n
g
ai
n
is
ca
lcu
lated
f
o
r
f
ea
t
u
r
es
in
th
e
r
esam
p
led
d
ataset
to
b
u
ild
a
n
ew
d
ec
is
io
n
tr
ee
.
A
n
ew
d
ec
is
io
n
tr
ee
is
b
u
ilt
o
n
r
esam
p
led
d
ata,
u
p
d
atin
g
th
e
m
o
d
el
e
v
er
y
iter
atio
n
.
T
h
e
en
s
em
b
le
o
f
d
ec
is
io
n
tr
ee
s
will
f
o
r
m
th
e
f
in
al
m
o
d
el
[
2
3
]
.
2
.
4
.
E
v
a
lua
t
i
o
n
T
r
ain
ed
m
o
d
el
p
er
f
o
r
m
a
n
ce
is
ev
alu
ated
b
y
a
v
er
ag
in
g
a
cc
u
r
ac
y
m
etr
ics
lik
e
AUC,
s
en
s
itiv
ity
,
s
p
ec
if
icity
,
PP
V,
an
d
NP
V
a
cr
o
s
s
all
f
o
ld
s
.
T
h
e
co
n
f
u
s
io
n
m
atr
ix
r
esu
lts
f
r
o
m
ea
ch
f
o
ld
ar
e
co
m
b
in
ed
to
ass
es
s
o
v
er
all
p
er
f
o
r
m
a
n
ce
.
T
h
e
co
n
f
u
s
io
n
m
atr
ix
s
u
m
m
ar
izes
th
e
m
o
d
el
p
e
r
f
o
r
m
an
c
e
b
y
co
m
p
a
r
in
g
th
e
p
r
ed
icted
lab
els
with
th
e
ac
t
u
al
lab
els
f
r
o
m
th
e
d
ataset.
I
t
co
n
s
is
ts
o
f
f
o
u
r
p
a
r
ts
:
tr
u
e
p
o
s
itiv
e
(
T
P),
tr
u
e
n
eg
ativ
e
(
T
N)
,
f
alse
p
o
s
itiv
e
(
FP
)
,
an
d
f
alse
n
e
g
ativ
e
(
FN)
.
T
h
is
m
eth
o
d
will
b
e
u
s
ed
t
o
ca
lcu
late
ac
cu
r
ac
y
,
s
en
s
i
tiv
ity
,
s
p
ec
if
icity
,
PP
V,
an
d
NPV
in
(
3
)
to
(
7
)
[
2
4
]
.
T
h
e
r
ep
r
esen
tatio
n
o
f
t
h
e
co
n
f
u
s
io
n
m
atr
ix
ca
n
b
e
s
ee
n
in
T
ab
le
1
.
Acc
u
r
ac
y
m
e
asu
r
es h
o
w
well
th
e
m
o
d
el
ca
n
co
r
r
ec
tly
p
r
ed
ict
r
esu
lts
f
r
o
m
all
d
ata.
=
+
+
+
+
(
3
)
AUC
s
h
o
ws
th
e
m
o
d
el’
s
ab
ilit
y
to
d
i
f
f
er
en
tiate
b
etwe
en
two
d
if
f
er
e
n
t
class
es
co
r
r
ec
tly
.
AUC
m
ea
s
u
r
es
th
e
ar
ea
u
n
d
e
r
th
e
r
ec
eiv
er
o
p
e
r
atin
g
c
h
ar
ac
ter
is
tic
(
R
OC
)
cu
r
v
e,
wh
e
r
e
a
v
alu
e
o
f
0
in
d
icate
s
p
o
o
r
p
e
r
f
o
r
m
a
n
c
e
,
a
v
a
l
u
e
o
f
1
i
n
d
i
c
a
t
es
p
e
r
f
e
c
t
p
e
r
f
o
r
m
a
n
c
e
an
d
a
v
a
l
u
e
o
f
0
.
5
i
n
d
i
c
at
e
s
r
an
d
o
m
p
e
r
f
o
r
m
a
n
c
e
.
S
e
n
s
it
i
v
it
y
,
a
l
s
o
k
n
o
w
n
as
r
e
c
al
l
,
f
u
n
c
t
i
o
n
s
t
o
m
e
a
s
u
r
e
h
o
w
we
l
l
t
h
e
m
o
d
e
l
ca
n
c
o
r
r
e
c
t
l
y
i
d
en
t
i
f
y
p
o
s
i
t
i
v
e
c
a
s
e
s
.
=
+
(
4
)
Sp
ec
if
icity
will m
ea
s
u
r
e
h
o
w
well
th
e
m
o
d
el
ca
n
i
d
en
tify
n
e
g
ativ
e
ca
s
es.
=
+
(
5
)
PP
V
also
k
n
o
wn
as
p
r
ec
is
io
n
m
ea
s
u
r
es
h
o
w
well
th
e
m
o
d
el
p
r
ed
icts
th
e
c
o
r
r
ec
t
p
o
s
itiv
e
ca
s
es
f
r
o
m
all
p
o
s
itiv
e
p
r
ed
ictio
n
r
esu
lts
.
=
+
(
6
)
N
P
V
m
ea
s
u
r
es
h
o
w
w
e
ll
t
h
e
m
o
d
e
l
i
s
i
n
p
r
e
d
i
ct
i
n
g
t
h
e
c
o
r
r
e
ct
n
e
g
a
t
i
v
e
c
as
e
f
r
o
m
a
l
l
n
e
g
a
ti
v
e
p
r
e
d
i
c
t
e
d
r
e
s
u
l
t
s
.
=
+
(
7
)
T
ab
le
1
.
C
o
n
f
u
s
io
n
m
atr
ix
Tr
u
e
c
l
a
ss
P
r
e
d
i
c
t
e
d
c
l
a
ss
N
e
g
a
t
i
v
e
P
o
si
t
i
v
e
N
e
g
a
t
i
v
e
TN
FP
P
o
si
t
i
v
e
FN
TP
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
38
,
No
.
2
,
May
20
25
:
9
4
0
-
9
4
9
944
Af
ter
p
er
f
o
r
m
a
n
ce
ev
alu
atio
n
,
f
ea
tu
r
e
im
p
o
r
tan
ce
an
al
y
s
is
is
co
n
d
u
cted
u
s
in
g
s
p
lit
an
d
g
ain
to
ass
es
s
th
e
co
n
tr
ib
u
tio
n
o
f
ea
ch
f
ea
tu
r
e
t
o
p
r
e
d
ictio
n
s
.
Ga
in
in
d
icate
s
ac
cu
r
ac
y
i
m
p
r
o
v
em
en
t,
wh
ile
s
p
lit
in
d
icate
s
f
ea
tu
r
e
u
s
ag
e
in
d
ec
is
io
n
tr
ee
n
o
d
es
[
2
5
]
.
T
h
i
s
an
aly
s
is
is
ap
p
lied
to
m
o
d
el
3
,
s
o
we
ca
n
u
n
d
er
s
tan
d
th
e
r
elativ
e
co
n
tr
i
b
u
tio
n
o
f
th
e
two
ty
p
es o
f
f
ea
tu
r
es to
th
e
m
o
d
el’
s
p
r
ed
ictio
n
p
er
f
o
r
m
a
n
ce
.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
3
.
1
.
P
re
pa
ring
t
he
da
t
a
s
et
a
nd
co
ug
h seg
m
ent
a
t
io
n
T
ab
le
2
co
n
tain
s
th
e
d
is
tr
ib
u
ti
o
n
o
f
s
am
p
les
f
o
r
ea
ch
class
af
ter
f
o
r
m
i
n
g
th
e
la
b
el
“h
ea
lt
h
y
”
as
th
e
n
eg
ativ
e
class
an
d
th
e
co
m
b
i
n
atio
n
o
f
s
am
p
les
lab
eled
“p
o
s
itiv
e_
m
ild
”
an
d
“p
o
s
itiv
e_
m
o
d
er
ate”
as
d
ata
f
o
r
th
e
p
o
s
itiv
e
class
.
T
h
en
s
eg
m
en
tatio
n
is
p
er
f
o
r
m
ed
o
n
ea
c
h
s
am
p
le
u
s
in
g
th
e
h
y
s
t
er
esis
co
m
p
ar
ato
r
m
eth
o
d
.
Par
am
eter
s
,
s
u
ch
as
m
in
_
co
u
g
h
a
n
d
c
o
u
g
h
_
p
a
d
d
in
g
,
wer
e
lef
t
with
a
d
e
f
au
lt
v
al
u
e
o
f
0
.
2
as
p
r
o
p
o
s
ed
i
n
p
r
ev
io
u
s
r
esear
ch
[
1
0
]
.
So
m
e
tim
es,
n
o
t
all
s
am
p
les
wer
e
d
etec
ted
to
h
av
e
co
u
g
h
s
eg
m
e
n
ts
,
eith
er
b
ec
au
s
e
th
er
e
wer
e
n
o
n
e
o
r
th
e
s
eg
m
en
tatio
n
alg
o
r
ith
m
f
ailed
.
A
co
m
p
ar
is
o
n
o
f
s
u
cc
ess
f
u
l
an
d
f
ailed
co
u
g
h
s
eg
m
en
tatio
n
r
esu
lts
ca
n
b
e
s
e
en
in
Fig
u
r
e
2
.
T
h
e
p
o
s
s
ib
le
ca
u
s
e
is
th
at
th
e
R
MS
v
alu
e
is
to
o
h
ig
h
i
n
s
o
m
e
s
am
p
les
wh
ich
ca
u
s
es
a
wea
k
co
u
g
h
s
o
u
n
d
n
o
t
to
b
e
d
etec
ted
.
An
o
th
er
in
f
lu
e
n
cin
g
f
ac
to
r
is
th
e
ch
o
ice
o
f
p
ar
am
et
er
v
alu
es,
s
u
c
h
as
m
in
_
co
u
g
h
_
le
n
,
wh
er
e
co
u
g
h
s
o
u
n
d
s
th
at
ar
e
to
o
s
h
o
r
t
m
ay
n
o
t
b
e
d
etec
ted
.
Af
ter
all
r
ec
o
r
d
in
g
s
am
p
les
wer
e
s
eg
m
en
ted
,
we
o
b
tain
e
d
a
d
at
aset
co
n
tain
in
g
4
,
4
1
1
s
eg
m
e
n
ts
o
r
ig
in
atin
g
f
r
o
m
1
,
5
7
9
s
am
p
les
with
d
etails
a
s
in
T
ab
le
3
.
T
ab
le
2
.
Sam
p
le
d
is
tr
ib
u
tio
n
a
f
ter
lab
el
m
er
g
i
n
g
La
b
e
l
G
e
n
d
e
r
N
u
mb
e
r
o
f
sa
m
p
l
e
s
To
t
a
l
s
a
m
p
l
e
0
(
n
e
g
a
t
i
v
e
)
M
a
l
e
1
,
0
6
8
1
,
4
3
2
F
e
mal
e
3
6
4
1
(
p
o
s
i
t
i
v
e
)
M
a
l
e
3
6
2
5
9
1
F
e
mal
e
2
2
9
Fig
u
r
e
2
.
E
x
am
p
le
o
f
co
u
g
h
s
o
u
n
d
s
eg
m
en
tatio
n
r
esu
lts
T
ab
le
3
.
Dis
tr
ib
u
tio
n
o
f
c
o
u
g
h
s
o
u
n
d
s
eg
m
e
n
tatio
n
r
esu
lts
La
b
e
l
G
e
n
d
e
r
N
u
mb
e
r
o
f
s
e
g
me
n
t
s
To
t
a
l
s
e
g
me
n
t
s
0
(
n
e
g
a
t
i
v
e
)
M
a
l
e
2
,
6
5
8
3
,
3
3
6
F
e
mal
e
6
7
8
1
(
p
o
s
i
t
i
v
e
)
M
a
l
e
7
1
0
1
,
0
7
5
F
e
mal
e
3
6
5
3
.
2
.
P
re
pro
ce
s
s
ing
A
lib
r
ar
y
ca
lled
lib
r
o
s
a
is
u
s
ed
to
ex
tr
ac
t
f
ea
tu
r
es
f
r
o
m
co
u
g
h
s
eg
m
e
n
ts
.
Par
am
eter
s
lik
e
n
_
f
f
t,
h
o
p
_
le
n
g
th
,
a
n
d
win
d
o
w
ar
e
s
et
to
2
,
0
4
8
,
5
1
2
,
an
d
‘
h
an
n
’
r
esp
ec
tiv
ely
f
o
r
b
ala
n
ce
d
f
r
eq
u
en
cy
-
tim
e
r
eso
lu
tio
n
[
2
6
]
.
Fo
r
ea
ch
f
e
atu
r
e
ex
tr
ac
tio
n
m
eth
o
d
,
n
_
m
f
cc
in
MFC
C
is
s
et
to
3
9
b
ased
o
n
[
4
]
,
an
d
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
ctio
n
o
f COVI
D
-
1
9
b
a
s
ed
o
n
co
u
g
h
s
o
u
n
d
a
n
d
a
cc
o
m
p
a
n
yin
g
s
ymp
to
n
u
s
in
g
…
(
Wih
a
r
to
)
945
p
ar
am
eter
s
in
lo
g
m
el
-
s
p
ec
tr
o
g
r
am
a
n
d
c
h
r
o
m
a
STFT
ar
e
l
ef
t
with
d
ef
au
lt
v
al
u
es.
W
h
ile
R
MS
an
d
Z
C
R
d
o
n
o
t h
av
e
s
p
ec
if
ic
p
ar
am
eter
s
.
Af
ter
th
e
f
ea
tu
r
e
ex
tr
ac
tio
n
p
r
o
ce
s
s
is
c
o
m
p
lete,
we
ca
lcu
late
th
e
av
er
ag
e
o
f
ea
ch
f
e
atu
r
e
v
alu
e
ac
r
o
s
s
all
f
r
am
es.
T
h
u
s
,
th
e
r
esu
lts
o
f
th
e
MF
C
C
m
eth
o
d
h
av
e
3
9
f
ea
tu
r
es,
lo
g
m
el
-
s
p
ec
tr
o
g
r
am
h
as
1
2
8
f
ea
tu
r
es,
c
h
r
o
m
a
STFT
h
as
1
2
f
ea
tu
r
es,
Z
C
R
h
as
1
f
ea
t
u
r
e,
R
MS
h
as
1
f
ea
tu
r
e,
a
n
d
th
e
to
tal
f
ea
tu
r
e
s
o
f
ea
ch
co
u
g
h
s
o
u
n
d
ar
e
1
8
1
.
Fin
ally
,
f
ea
tu
r
e
ex
tr
ac
tio
n
r
esu
lts
f
r
o
m
th
e
co
u
g
h
s
o
u
n
d
ar
e
c
o
m
b
in
ed
with
th
e
s
y
m
p
to
m
d
ata
wh
ich
h
as
b
ee
n
co
n
v
er
ted
in
to
b
in
ar
y
f
o
r
m
,
s
o
th
at
ea
ch
s
eg
m
en
t
h
as
f
ea
tu
r
es
with
d
im
en
s
io
n
s
o
f
1
9
0
.
T
h
e
f
in
al
r
esu
lt
is
a
n
ar
r
ay
wit
h
d
im
e
n
s
io
n
s
o
f
1
9
2
×
4
4
1
1
af
ter
ad
d
in
g
t
h
e
I
D
an
d
l
ab
el
o
f
th
e
o
r
ig
in
al
s
am
p
le
f
o
r
ea
ch
s
eg
m
en
t.
3
.
3
.
T
ra
ini
ng
T
h
r
ee
L
ig
h
tGB
M
m
o
d
els
wer
e
tr
ain
ed
o
n
d
if
f
er
e
n
t
f
ea
tu
r
e
s
u
b
s
ets
an
d
ev
alu
ate
d
f
o
r
th
eir
p
er
f
o
r
m
an
ce
u
s
in
g
th
e
s
tr
atif
ied
k
-
f
o
ld
c
r
o
s
s
-
v
alid
atio
n
m
e
th
o
d
b
y
d
iv
id
in
g
all
s
am
p
le
I
Ds
in
to
f
iv
e
f
o
ld
s
.
T
h
u
s
,
ea
ch
f
o
ld
co
n
tain
s
co
u
g
h
s
eg
m
en
ts
s
o
u
r
ce
d
f
r
o
m
ar
o
u
n
d
3
1
5
s
am
p
les.
I
n
ea
c
h
f
o
ld
iter
atio
n
,
th
e
tr
ain
in
g
d
ata
is
o
v
e
r
s
am
p
led
u
s
in
g
SVM
-
SMOT
E
f
r
o
m
a
lib
r
ar
y
ca
lled
im
b
alan
ce
d
-
l
ea
r
n
[
2
7
]
.
W
e
s
et
k
_
n
eig
h
b
o
r
s
p
ar
a
m
eter
v
alu
e
in
SVM
-
SMOT
E
to
1
b
ec
au
s
e
ex
p
er
im
en
ts
with
k
-
n
eig
h
b
o
r
’
s
v
alu
es
1
–
5
s
h
o
w
th
at
1
y
ield
b
etter
p
er
f
o
r
m
a
n
ce
,
s
o
s
y
n
th
etic
s
am
p
les
ar
e
g
en
e
r
ated
b
ased
o
n
o
n
e
n
ea
r
est
n
eig
h
b
o
r
.
T
h
en
,
L
ig
h
tGB
M
m
o
d
els
wer
e
tr
ain
ed
u
s
in
g
o
v
e
r
s
am
p
led
t
r
ain
in
g
d
ata
with
h
y
p
er
p
ar
a
m
eter
s
ettin
g
s
f
r
o
m
r
esear
ch
r
esu
lts
b
y
[
2
8
]
as
in
T
ab
le
4
.
T
h
e
tr
ain
i
n
g
p
r
o
ce
s
s
u
s
es
f
iv
e
f
o
ld
s
s
o
it
will
p
r
o
v
id
e
p
e
r
f
o
r
m
an
ce
m
etr
ics
f
o
r
ea
ch
m
o
d
el
f
iv
e
t
im
es.
T
h
e
av
er
ag
e
m
o
d
el
p
e
r
f
o
r
m
an
ce
v
alu
e
is
ca
lcu
lated
,
an
d
th
e
co
n
f
u
s
io
n
m
atr
i
x
is
s
u
m
m
ated
.
T
ab
le
4
.
Dis
tr
ib
u
tio
n
o
f
c
o
u
g
h
s
o
u
n
d
s
eg
m
e
n
tatio
n
r
esu
lts
H
y
p
e
r
p
a
r
a
me
t
e
r
D
e
f
i
n
i
t
i
o
n
V
a
l
u
e
l
e
a
r
n
i
n
g
_
r
a
t
e
H
o
w
m
u
c
h
t
h
e
m
o
d
e
l
w
e
i
g
h
t
s
c
h
a
n
g
e
e
a
c
h
t
i
m
e
t
h
e
m
o
d
e
l
i
s
u
p
d
a
t
e
d
0
.
0
3
c
o
l
sam
p
l
e
_
b
y
t
r
e
e
N
u
mb
e
r
o
f
f
e
a
t
u
r
e
s
u
b
s
e
t
s
a
t
e
a
c
h
i
t
e
r
a
t
i
o
n
0
.
2
8
su
b
s
a
m
p
l
e
N
u
mb
e
r
o
f
d
a
t
a
s
u
b
s
e
t
s
i
n
e
a
c
h
i
t
e
r
a
t
i
o
n
0
.
6
8
r
e
g
_
a
l
p
h
a
L1
r
e
g
u
l
a
r
i
z
a
t
i
o
n
1
r
e
g
_
l
a
mb
d
a
L2
r
e
g
u
l
a
r
i
z
a
t
i
o
n
2
n
u
m
_
l
e
a
v
e
s
M
a
x
i
m
u
m
n
u
m
b
e
r
o
f
l
e
a
v
e
s
i
n
o
n
e
t
r
e
e
5
0
0
n
u
m
_
b
o
o
s
t
_
r
o
u
n
d
M
a
x
i
m
u
m
n
u
m
b
e
r
o
f
b
o
o
s
t
i
n
g
i
t
e
r
a
t
i
o
n
s
10
,
000
e
a
r
l
y
_
s
t
o
p
p
i
n
g
_
r
o
u
n
d
Th
e
ma
x
i
mu
m
n
u
m
b
e
r
o
f
i
t
e
r
a
t
i
o
n
s
t
o
st
o
p
t
r
a
i
n
i
n
g
i
f
t
h
e
r
e
i
s
n
o
i
n
c
r
e
a
s
e
i
n
t
h
e
p
e
r
f
o
r
ma
n
c
e
me
t
r
i
c
v
a
l
u
e
1
0
0
3
.
4
.
E
v
a
lua
t
i
o
n
Af
ter
th
e
tr
ain
in
g
p
r
o
ce
s
s
is
f
in
is
h
ed
,
all
th
e
p
er
f
o
r
m
an
ce
m
etr
ic
v
alu
es
as
well
as
th
e
co
n
f
u
s
io
n
m
atr
ix
co
m
b
in
ed
f
r
o
m
f
iv
e
tr
ain
in
g
iter
atio
n
s
ar
e
o
b
tain
ed
f
r
o
m
t
h
r
ee
m
o
d
els
tr
ain
e
d
wit
h
d
if
f
er
en
t
f
ea
tu
r
e
s
u
b
s
ets:
co
u
g
h
s
o
u
n
d
m
o
d
el
(
m
o
d
el
1
)
,
s
y
m
p
to
m
m
o
d
el
(
m
o
d
el
2
)
,
an
d
co
m
b
in
atio
n
m
o
d
el
(
m
o
d
el
3
)
.
T
h
e
s
u
m
m
ed
co
n
f
u
s
io
n
m
atr
ix
f
r
o
m
all
f
o
ld
s
f
o
r
all
m
o
d
els
c
an
b
e
s
ee
n
i
n
Fig
u
r
e
3
an
d
a
ll
th
e
p
er
f
o
r
m
an
ce
m
etr
ic
v
alu
es
f
o
r
all
m
o
d
els
ca
n
b
e
s
ee
n
in
T
ab
le
5
.
B
ased
o
n
th
e
co
n
f
u
s
io
n
m
atr
ix
o
f
all
m
o
d
els,
we
ca
n
s
ee
th
at
m
o
d
el
1
wh
ich
is
tr
ain
e
d
b
ased
o
n
co
u
g
h
s
o
u
n
d
f
ea
tu
r
e
ex
tr
ac
tio
n
h
as
a
h
ig
h
tr
u
e
n
e
g
ativ
e
r
ate
b
u
t
also
h
as
h
ig
h
FN
p
r
ed
ictio
n
.
Mo
d
e
l
2
wh
ich
is
tr
ain
ed
with
s
y
m
p
to
m
d
ata
s
h
o
wed
l
o
wer
FN
an
d
h
ig
h
er
TP
r
ates.
Mo
d
el
3
,
wh
ich
is
co
m
b
in
ed
c
o
u
g
h
s
o
u
n
d
f
ea
tu
r
es
an
d
s
y
m
p
to
m
d
ata
s
h
o
wed
th
e
b
est
p
e
r
f
o
r
m
a
n
ce
,
with
th
e
lo
west
FN
r
ate
an
d
h
ig
h
est
TP
r
ate.
Fig
u
r
e
3
.
Su
m
m
ar
y
o
f
th
e
c
o
n
f
u
s
io
n
m
atr
ix
f
o
r
all
m
o
d
els
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
38
,
No
.
2
,
May
20
25
:
9
4
0
-
9
4
9
946
Fro
m
av
er
ag
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
th
r
ee
m
o
d
els
in
T
ab
le
6
,
ca
n
b
e
d
r
awn
to
th
e
s
am
e
co
n
clu
s
io
n
as
th
e
an
aly
s
is
b
ased
o
n
t
h
e
co
n
f
u
s
io
n
m
atr
i
x
th
at
m
o
d
els
tr
ai
n
ed
with
p
atien
t
s
y
m
p
t
o
m
d
a
ta
ten
d
to
p
e
r
f
o
r
m
b
etter
th
an
m
o
d
els
tr
ain
ed
u
s
in
g
co
u
g
h
s
o
u
n
d
f
ea
tu
r
es.
Patien
t
s
y
m
p
to
m
s
ar
e
ca
teg
o
r
ical
an
d
d
ir
ec
tly
in
d
icate
C
OVI
D
-
1
9
p
r
esen
ce
,
wh
ile
c
o
u
g
h
s
o
u
n
d
f
ea
t
u
r
es
h
av
e
a
w
id
er
r
an
g
e,
m
ak
in
g
it
h
a
r
d
er
f
o
r
th
e
m
o
d
el
to
f
in
d
co
n
s
is
ten
t
p
atter
n
s
.
Ho
we
v
e
r
,
co
m
b
in
in
g
b
o
th
f
ea
tu
r
es
im
p
r
o
v
es
t
h
e
m
o
d
el’
s
p
r
ed
i
ctiv
e
ab
ilit
y
,
with
im
p
r
o
v
em
e
n
ts
in
s
ev
er
al
p
er
f
o
r
m
an
ce
m
etr
ics.
T
h
e
m
o
d
e
l’
s
ac
cu
r
ac
y
,
AUC,
s
en
s
itiv
it
y
,
an
d
s
p
ec
if
icity
in
cr
ea
s
ed
to
9
5
.
6
1
%,
9
3
.
3
3
%,
8
8
.
7
4
%,
a
n
d
9
7
.
9
1
%,
r
esp
e
ctiv
ely
.
T
h
is
in
c
r
ea
s
ed
s
en
s
itiv
ity
an
d
s
p
ec
if
icity
h
av
e
p
o
s
itiv
e
im
p
licatio
n
s
f
o
r
d
etec
tin
g
C
OVI
D
-
1
9
ca
s
es
an
d
r
e
d
u
cin
g
p
r
e
d
ictio
n
er
r
o
r
s
.
T
h
e
m
o
d
el
also
s
h
o
wed
a
h
ig
h
er
p
r
e
d
ictio
n
p
r
o
b
a
b
ilit
y
(
PP
V)
v
alu
e
o
f
9
3
.
1
7
%
an
d
NPV
o
f
9
6
.
3
3
%,
in
d
icatin
g
b
etter
p
r
ed
ictio
n
ac
c
u
r
ac
y
.
T
ab
le
5
.
Per
f
o
r
m
an
ce
m
etr
ic
v
alu
es f
o
r
all
m
o
d
els
F
o
l
d
A
c
c
u
r
a
c
y
AUC
S
e
n
s
i
t
i
v
i
t
y
S
p
e
c
i
f
i
c
i
t
y
PPV
N
P
V
M
o
d
e
l
1
1
0
.
8
9
8
0
.
8
3
3
0
.
7
1
1
0
.
9
5
4
0
.
8
2
2
0
.
9
1
7
2
0
.
9
1
3
0
.
8
3
6
0
.
6
8
3
0
.
9
8
8
0
.
9
4
9
0
.
9
0
5
3
0
.
8
8
8
0
.
8
3
1
0
.
7
2
4
0
.
9
3
7
0
.
7
7
9
0
.
9
1
8
4
0
.
8
8
1
0
.
8
1
3
0
.
6
6
8
0
.
9
5
8
0
.
8
5
3
0
.
8
8
8
5
0
.
9
1
0
0
.
8
2
4
0
.
6
5
7
0
.
9
9
1
0
.
9
5
8
0
.
9
0
1
M
e
a
n
0
.
8
9
8
0
.
8
2
7
0
.
6
8
9
0
.
9
6
6
0
.
8
7
2
0
.
9
0
6
M
o
d
e
l
2
1
0
.
9
4
5
0
.
9
1
7
0
.
8
6
0
0
.
9
7
3
0
.
9
1
1
0
.
9
5
5
2
0
.
9
4
5
0
.
9
0
4
0
.
8
1
4
0
.
9
9
4
0
.
9
8
0
0
.
9
3
6
3
0
.
9
3
6
0
.
9
0
7
0
.
8
5
8
0
.
9
5
7
0
.
8
4
0
0
.
9
6
2
4
0
.
9
4
2
0
.
8
8
3
0
.
7
7
6
0
.
9
9
0
0
.
9
5
6
0
.
9
3
9
5
0
.
9
1
1
0
.
8
8
7
0
.
8
3
2
0
.
9
4
2
0
.
8
4
3
0
.
9
3
7
M
e
a
n
0
.
9
3
6
0
.
8
9
9
0
.
8
2
8
0
.
9
7
1
0
.
9
0
6
0
.
9
4
6
M
o
d
e
l
3
1
0
.
9
1
6
0
.
8
7
5
0
.
7
9
4
0
.
9
5
6
0
.
8
5
2
0
.
9
3
5
2
0
.
9
7
6
0
.
9
5
1
0
.
9
0
7
0
.
9
9
6
0
.
9
8
3
0
.
9
7
5
3
0
.
9
6
5
0
.
9
5
5
0
.
9
3
6
0
.
9
7
4
0
.
9
1
3
0
.
9
8
1
4
0
.
9
7
1
0
.
9
5
9
0
.
9
3
6
0
.
9
8
2
0
.
9
4
0
0
.
9
8
1
5
0
.
9
5
2
0
.
9
2
7
0
.
8
6
5
0
.
9
8
9
0
.
9
7
0
0
.
9
4
5
M
e
a
n
0
.
9
5
6
0
.
9
3
3
0
.
8
8
7
0
.
9
7
9
0
.
9
3
7
0
.
9
6
3
T
ab
le
6
.
C
o
m
p
a
r
is
o
n
with
r
ela
ted
r
esear
ch
R
e
se
a
r
c
h
D
a
t
a
s
e
t
V
o
i
c
e
d
a
t
a
S
y
mp
t
o
m
d
a
t
a
M
o
d
e
l
A
U
C
(
%)
[
4
]
C
o
sw
a
r
a
C
o
u
g
h
so
u
n
d
-
H
G
B
o
o
st
66
[
5
]
C
o
sw
a
r
a
C
o
u
g
h
so
u
n
d
-
M
i
n
i
V
G
G
N
e
t
7
8
,
1
[
6
]
C
o
sw
a
r
a
P
a
t
i
e
n
t
's
v
o
i
c
e
-
N
e
u
r
a
l
n
e
t
w
o
r
k
82
C
o
sw
a
r
a
-
P
n
e
u
mo
n
i
a
,
a
s
t
h
m
a
,
d
i
f
f
i
c
u
l
t
y
b
r
e
a
t
h
i
n
g
,
d
i
a
r
r
h
e
a
,
f
a
t
i
g
u
e
,
mu
s
c
l
e
a
c
h
e
s,
f
e
v
e
r
,
c
o
l
d
,
a
n
d
so
r
e
t
h
r
o
a
t
78
C
o
sw
a
r
a
P
a
t
i
e
n
t
's
v
o
i
c
e
P
n
e
u
mo
n
i
a
,
a
s
t
h
m
a
,
d
i
f
f
i
c
u
l
t
y
b
r
e
a
t
h
i
n
g
,
d
i
a
r
r
h
e
a
,
f
a
t
i
g
u
e
,
mu
s
c
l
e
a
c
h
e
s,
f
e
v
e
r
,
c
o
l
d
,
a
n
d
so
r
e
t
h
r
o
a
t
88
[
7
]
C
o
u
g
h
v
i
d
C
o
u
g
h
so
u
n
d
R
e
s
p
i
r
a
t
o
r
y
c
o
n
d
i
t
i
o
n
s
a
n
d
f
e
v
e
r
s
y
m
p
t
o
ms
M
B
D
LN
91
[
8
]
C
o
sw
a
r
a
a
n
d
C
o
u
g
h
v
i
d
C
o
u
g
h
so
u
n
d
R
e
s
p
i
r
a
t
o
r
y
c
o
n
d
i
t
i
o
n
s
,
s
y
m
p
t
o
ms
o
f
f
e
v
e
r
,
a
n
d
mu
sc
l
e
p
a
i
n
H
M
T
82
P
r
o
p
o
se
d
C
o
sw
a
r
a
C
o
u
g
h
so
u
n
d
-
Li
g
h
t
G
B
M
8
2
,
7
-
D
i
f
f
i
c
u
l
t
y
b
r
e
a
t
h
i
n
g
,
c
o
l
d
,
c
o
u
g
h
,
f
e
v
e
r
,
a
n
o
smi
a
,
mu
sc
l
e
a
c
h
e
s
,
s
o
r
e
t
h
r
o
a
t
,
d
i
a
r
r
h
e
a
,
a
n
d
f
a
t
i
g
u
e
8
9
,
9
C
o
u
g
h
so
u
n
d
D
i
f
f
i
c
u
l
t
y
b
r
e
a
t
h
i
n
g
,
c
o
l
d
,
c
o
u
g
h
,
f
e
v
e
r
,
a
n
o
smi
a
,
mu
sc
l
e
a
c
h
e
s
,
s
o
r
e
t
h
r
o
a
t
,
d
i
a
r
r
h
e
a
,
a
n
d
f
a
t
i
g
u
e
93
T
h
e
f
ea
tu
r
e
im
p
o
r
tan
ce
g
r
ap
h
an
aly
s
is
o
f
th
e
5
th
iter
atio
n
o
f
m
o
d
el
3
tr
ain
in
g
,
as
s
h
o
wn
in
Fig
u
r
e
4
ca
n
p
r
o
v
id
e
co
m
p
lem
en
ta
r
y
in
s
ig
h
ts
.
T
h
e
f
ea
tu
r
es
‘
co
u
g
h
’
,
‘
f
atig
u
e’
,
‘
co
l
d
’
,
an
d
‘
f
ev
er
’
h
av
e
th
e
h
ig
h
est
g
ain
,
in
d
icatin
g
th
eir
ef
f
ec
tiv
e
n
ess
in
in
cr
ea
s
in
g
m
o
d
el
ac
cu
r
ac
y
.
Au
d
io
f
ea
tu
r
es
s
u
ch
as
‘
zc
r
’
an
d
‘
m
f
cc
_
7
’
also
h
av
e
h
ig
h
er
g
ain
v
alu
es,
i
n
d
icatin
g
th
eir
im
p
o
r
tan
ce
in
t
r
ain
in
g
a
m
o
d
el
to
d
etec
t
C
OVI
D
-
1
9
in
ter
m
s
o
f
co
u
g
h
s
o
u
n
d
c
h
ar
ac
ter
is
tics
.
On
th
e
o
th
er
h
an
d
,
f
ea
tu
r
e
im
p
o
r
tan
ce
r
a
n
k
in
g
b
ased
o
n
s
p
lit
s
h
o
ws
th
at
f
ea
tu
r
es
lik
e
‘
zc
r
’
,
‘
m
f
cc
_
1
2
’
,
‘
m
f
cc
_
1
8
’
,
an
d
‘
co
ld
’
h
av
e
t
h
e
g
r
ea
test
in
f
lu
en
ce
in
m
ak
in
g
d
ec
is
io
n
s
in
th
e
C
OVI
D
-
1
9
d
etec
tio
n
m
o
d
el.
T
h
e
s
p
lit
v
alu
e
in
d
icate
s
h
o
w
o
f
ten
th
e
f
ea
tu
r
e
is
u
s
ed
in
d
ata
s
p
litt
in
g
d
u
r
in
g
th
e
tr
ain
in
g
p
r
o
ce
s
s
.
A
co
m
p
ar
is
o
n
b
etwe
en
f
ea
tu
r
e
im
p
o
r
tan
ce
b
ased
o
n
g
ain
an
d
s
p
lit
s
h
o
ws
s
im
ilar
itie
s
in
f
ea
tu
r
es
lik
e
'
co
ld
'
,
wh
ich
ar
e
im
p
o
r
tan
t
f
o
r
d
iv
id
i
n
g
d
ata
an
d
in
c
r
ea
s
in
g
m
o
d
el
ac
cu
r
ac
y
.
Ho
wev
e
r
,
t
h
er
e
ar
e
d
if
f
er
e
n
ce
s
in
f
ea
tu
r
es,
s
u
ch
as
‘
zc
r
’
,
wh
i
ch
h
as
th
e
lar
g
est
r
o
le
b
ased
o
n
s
p
lit
b
u
t
h
as
a
lo
wer
g
ain
th
an
o
th
er
f
ea
tu
r
es.
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
ctio
n
o
f COVI
D
-
1
9
b
a
s
ed
o
n
co
u
g
h
s
o
u
n
d
a
n
d
a
cc
o
m
p
a
n
yin
g
s
ymp
to
n
u
s
in
g
…
(
Wih
a
r
to
)
947
As
f
o
r
th
e
r
elate
d
r
esear
ch
t
h
a
t
h
as
b
ee
n
lis
ted
an
d
ex
p
lain
e
d
p
r
e
v
io
u
s
ly
,
two
s
tu
d
ies
o
n
ly
u
s
e
co
u
g
h
s
o
u
n
d
s
,
th
e
wo
r
k
o
f
[
4
]
an
d
[
5
]
.
T
h
r
ee
s
tu
d
ies co
m
b
in
e
co
u
g
h
s
o
u
n
d
s
with
s
y
m
p
to
m
d
ata,
r
esear
ch
b
y
[
6
]
–
[
8
]
.
Fig
u
r
e
4
.
Featu
r
e
im
p
o
r
ta
n
ce
a
n
aly
s
is
b
ased
o
n
g
ain
an
d
s
p
l
it
R
esear
ch
[
4
]
an
d
[
5
]
u
s
ed
co
u
g
h
s
o
u
n
d
s
in
th
e
C
o
s
war
a
d
ataset
to
ex
tr
ac
t
f
ea
tu
r
es
u
s
in
g
v
ar
io
u
s
m
eth
o
d
s
.
C
h
o
wd
u
r
y
et
a
l.
[
4
]
u
s
ed
5
d
if
f
er
en
t
f
ea
tu
r
e
ex
tr
ac
tio
n
m
eth
o
d
s
to
tr
ain
H
GB
o
o
s
t
m
o
d
el
an
d
ac
h
iev
ed
a
n
AUC
v
alu
e
o
f
6
6
%.
Kh
o
et
a
l.
[
5
]
u
s
ed
MFC
C
f
ea
tu
r
e
to
tr
ain
Min
i
VGGN
et
an
d
an
AUC
v
alu
e
o
f
7
8
.
1
%.
B
o
th
m
o
d
els
wer
e
d
ef
ea
ted
b
y
m
o
d
el
1
,
wh
ich
h
ad
an
AUC
v
alu
e
o
f
8
2
.
7
%.
F
ak
h
r
y
et
a
l
.
[
7
]
u
s
ed
th
e
au
g
m
e
n
ted
C
o
u
g
h
v
id
d
at
aset
to
tr
ain
a
MBDLN
u
s
in
g
MFC
C
f
ea
tu
r
es
an
d
s
p
ec
tr
o
g
r
am
s
f
r
o
m
co
u
g
h
s
o
u
n
d
s
with
ad
d
itio
n
al
s
y
m
p
to
m
d
ata,
in
clu
d
in
g
r
esp
ir
at
o
r
y
co
n
d
itio
n
s
an
d
f
e
v
er
s
y
m
p
to
m
s
.
T
h
e
m
o
d
el
co
n
s
is
ted
o
f
two
d
ee
p
n
e
u
r
al
n
etwo
r
k
b
r
a
n
ch
es
f
o
r
MFC
C
f
ea
tu
r
es,
an
o
th
er
f
o
r
s
y
m
p
to
m
f
ea
tu
r
es,
an
d
a
co
n
v
o
l
u
tio
n
al
n
eu
r
al
n
etwo
r
k
(
C
NN
)
with
r
esid
u
al
n
etwo
r
k
(
R
esNet
)
-
5
0
ar
ch
itectu
r
e
f
o
r
s
p
ec
tr
o
g
r
am
s
.
T
h
e
m
o
d
el
ca
n
ac
h
ie
v
e
an
AUC
v
a
lu
e
o
f
9
1
%.
T
an
g
et
a
l.
[
8
]
d
e
v
elo
p
ed
a
HM
T
co
n
s
is
tin
g
o
f
th
r
ee
b
r
an
ch
es:
two
m
u
ltil
ay
er
p
er
ce
p
tr
o
n
s
(
ML
Ps
)
f
o
r
p
r
o
ce
s
s
in
g
s
y
m
p
to
m
d
at
a
an
d
th
e
av
er
ag
e
v
alu
e
o
f
ea
ch
MFC
C
f
ea
tu
r
e
co
ef
f
icien
t o
f
co
u
g
h
s
o
u
n
d
s
,
a
n
d
a
n
ested
h
ier
ar
ch
ical
tr
a
n
s
f
o
r
m
er
b
r
a
n
ch
f
o
r
ex
tr
ac
tin
g
s
p
ec
tr
o
g
r
am
f
ea
t
u
r
es.
T
h
e
HM
T
m
o
d
el
ac
h
iev
ed
an
AUC
v
alu
e
o
f
8
2
%.
T
h
o
s
e
tw
o
m
o
d
els
ca
n
b
e
o
u
tp
e
r
f
o
r
m
e
d
b
y
m
o
d
el
3
an
d
it
o
f
f
er
s
in
d
e
p
en
d
e
n
t
s
y
m
p
t
o
m
i
d
en
tific
atio
n
,
u
n
lik
e
p
r
ev
io
u
s
r
esear
ch
[
7
]
an
d
[
8
]
th
at
r
elied
o
n
ex
p
e
r
t
d
o
ct
o
r
s
d
iag
n
o
s
in
g
r
esp
ir
ato
r
y
co
n
d
itio
n
ab
n
o
r
m
alities
f
r
o
m
co
u
g
h
r
ec
o
r
d
in
g
s
.
Me
an
wh
ile,
R
ah
o
u
m
a
et
a
l.
[
6
]
co
n
d
u
cted
a
s
tu
d
y
u
s
in
g
C
o
s
war
a
d
ataset
to
ex
tr
ac
t
f
ea
t
u
r
es
f
r
o
m
p
atien
t'
s
v
o
ice,
s
u
ch
as
c
o
u
g
h
,
b
r
ea
th
,
c
o
u
n
tin
g
s
o
u
n
d
s
,
a
n
d
E
n
g
lis
h
v
o
wel
p
r
o
n
u
n
ciatio
n
.
T
h
ey
u
s
ed
1
1
m
eth
o
d
s
an
d
9
s
y
m
p
t
o
m
s
d
ata,
in
clu
d
in
g
asth
m
a
an
d
p
n
eu
m
o
n
ia
wh
ich
r
eq
u
ir
e
e
x
p
er
t m
ed
ical
d
iag
n
o
s
is
.
T
h
e
p
r
o
p
o
s
ed
m
eth
o
d
o
n
ly
u
s
es
co
u
g
h
s
o
u
n
d
s
,
ex
tr
ac
tin
g
f
ea
tu
r
es
u
s
in
g
o
n
ly
5
m
eth
o
d
s
an
d
ad
d
in
g
9
s
y
m
p
to
m
s
d
ata
with
o
u
t
i
n
clu
d
in
g
asth
m
a
an
d
p
n
e
u
m
o
n
ia
o
r
o
th
e
r
s
y
m
p
to
m
s
th
at
r
eq
u
ir
e
e
x
p
er
t
m
ed
ical
d
ia
g
n
o
s
is
.
Ho
wev
er
,
th
e
co
m
b
in
ed
m
o
d
e
l in
[
6
]
h
ad
a
n
AUC v
alu
e
o
f
8
8
% th
at
ca
n
b
e
o
u
tp
e
r
f
o
r
m
ed
b
y
th
e
p
er
f
o
r
m
a
n
ce
o
f
m
o
d
el
3
.
T
h
e
m
o
d
el
tr
ain
e
d
u
s
in
g
v
ar
i
o
u
s
ty
p
es
o
f
s
o
u
n
d
s
h
ad
an
AUC
v
alu
e
alm
o
s
t
th
e
s
am
e
as
m
o
d
el
1
,
with
an
AUC
v
alu
e
o
f
8
2
%.
T
h
e
m
o
d
el
tr
ain
ed
with
s
y
m
p
to
m
d
ata
o
b
tain
ed
a
n
AUC
v
a
lu
e
o
f
7
8
%
an
d
ca
n
b
e
o
u
tp
er
f
o
r
m
e
d
b
y
m
o
d
el
2
with
an
AUC
v
alu
e
o
f
8
9
.
9
%.
T
h
e
p
r
o
p
o
s
ed
m
o
d
el
h
as
g
o
o
d
class
if
icatio
n
ca
p
ab
ilit
ies,
with
a
h
ig
h
AUC
v
alu
e
in
d
icatin
g
b
etter
p
er
f
o
r
m
an
ce
in
d
if
f
er
e
n
tiatin
g
b
etwe
en
p
o
s
itiv
e
an
d
n
eg
ativ
e
class
es.
Ad
d
itio
n
ally
,
th
e
p
r
o
p
o
s
ed
m
eth
o
d
h
as
a
d
d
ed
v
alu
e
b
y
u
s
in
g
s
y
m
p
to
m
d
ata
th
at
ca
n
b
e
id
en
tifie
d
in
d
e
p
en
d
e
n
tly
.
4.
CO
NCLU
SI
O
N
Fro
m
th
e
r
esear
ch
th
at
h
as b
ee
n
co
n
d
u
cted
,
it c
an
b
e
co
n
clu
d
ed
th
at
m
ac
h
in
e
lear
n
in
g
m
o
d
els tr
ain
ed
o
n
ly
with
p
atien
t
s
y
m
p
to
m
d
ata
p
er
f
o
r
m
b
etter
th
an
m
o
d
els
tr
ain
ed
o
n
ly
w
ith
co
u
g
h
s
o
u
n
d
f
ea
t
u
r
es.
Ho
wev
er
,
co
m
b
in
in
g
co
u
g
h
s
o
u
n
d
f
ea
tu
r
es
a
n
d
p
atien
t
s
y
m
p
to
m
s
ca
n
im
p
r
o
v
e
m
o
d
el
p
e
r
f
o
r
m
an
ce
co
m
p
ar
ed
to
ju
s
t
u
s
in
g
o
n
e
ty
p
e
o
f
f
e
atu
r
e.
T
h
e
m
o
d
el
tr
ai
n
ed
u
s
in
g
co
u
g
h
s
o
u
n
d
f
ea
tu
r
es
an
d
p
atien
t
s
y
m
p
to
m
s
ac
h
iev
ed
an
ac
cu
r
ac
y
o
f
9
5
.
6
1
%,
AUC
o
f
9
3
.
3
3
%,
s
en
s
iti
v
ity
o
f
8
8
.
7
4
%,
s
p
ec
if
icity
o
f
9
7
.
9
1
%,
PP
V
o
f
93.
1
7
%,
an
d
NPV
o
f
9
6
.
3
3
%.
Featu
r
e
im
p
o
r
tan
ce
an
al
y
s
is
co
n
f
ir
m
e
d
th
e
im
p
o
r
tan
ce
o
f
c
o
u
g
h
,
f
atig
u
e,
co
ld
,
an
d
f
ev
er
in
im
p
r
o
v
i
n
g
th
e
m
o
d
el’
s
ac
cu
r
ac
y
.
I
n
ad
d
itio
n
,
Z
C
R
an
d
MF
C
C
ar
e
au
d
io
f
ea
tu
r
es
th
at
ar
e
o
f
ten
u
s
ed
to
s
ep
ar
ate
d
ata
d
u
r
in
g
tr
ain
in
g
.
Ov
er
all,
t
h
e
p
r
o
p
o
s
ed
co
m
b
in
e
d
m
o
d
el
was
a
b
le
to
e
x
ce
ed
t
h
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
38
,
No
.
2
,
May
20
25
:
9
4
0
-
9
4
9
948
p
er
f
o
r
m
an
ce
o
f
r
elate
d
s
tu
d
i
es
b
ased
o
n
th
e
AUC
m
etr
i
c
v
alu
e
o
f
9
3
%,
an
d
it
d
e
m
o
n
s
tr
ated
ex
ce
llen
t
class
if
icatio
n
ca
p
ab
ilit
ies.
AC
K
NO
WL
E
DG
E
M
E
NT
S
T
h
is
wo
r
k
is
p
ar
tially
s
u
p
p
o
r
ted
b
y
Un
iv
er
s
itas
Seb
elas
Ma
r
et
f
o
r
p
r
o
v
id
in
g
r
esear
ch
f
u
n
d
i
n
g
th
r
o
u
g
h
th
e
Hib
ah
R
is
et
Gr
o
u
p
s
ch
em
e
as
s
tip
u
lated
in
c
o
n
tr
ac
t
No
.
1
9
4
.
2
/UN2
7
.
2
2
/P
T
.
0
1
.
0
3
/2
0
2
4
.
T
h
e
au
th
o
r
s
also
g
r
ate
f
u
lly
ac
k
n
o
wled
g
e
th
e
h
elp
f
u
l
co
m
m
en
t
s
an
d
s
u
g
g
esti
o
n
s
o
f
th
e
r
e
v
i
ewe
r
s
,
wh
ich
h
av
e
im
p
r
o
v
e
d
th
e
p
r
esen
tatio
n
.
RE
F
E
R
E
NC
E
S
[
1
]
I
.
S
a
l
a
h
s
h
o
o
r
i
e
t
a
l
.
,
“
O
v
e
r
v
i
e
w
o
f
C
O
V
I
D
-
19
d
i
se
a
se
:
v
i
r
o
l
o
g
y
,
e
p
i
d
e
m
i
o
l
o
g
y
,
p
r
e
v
e
n
t
i
o
n
d
i
a
g
n
o
s
i
s,
t
r
e
a
t
m
e
n
t
,
a
n
d
v
a
c
c
i
n
e
s
,
”
Bi
o
l
o
g
i
c
s
,
v
o
l
.
1
,
n
o
.
1
,
p
p
.
2
–
4
0
,
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
b
i
o
l
o
g
i
c
s
1
0
1
0
0
0
2
.
[
2
]
A
.
I
mr
a
n
e
t
a
l
.
,
“
A
I
4
C
O
V
I
D
-
1
9
:
A
I
e
n
a
b
l
e
d
p
r
e
l
i
m
i
n
a
r
y
d
i
a
g
n
o
s
i
s fo
r
C
O
V
I
D
-
1
9
f
r
o
m
c
o
u
g
h
sam
p
l
e
s
v
i
a
a
n
a
p
p
,
”
I
n
f
o
rm
a
t
i
c
s
i
n
Me
d
i
c
i
n
e
U
n
l
o
c
k
e
d
,
v
o
l
.
2
0
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
mu
.
2
0
2
0
.
1
0
0
3
7
8
.
[
3
]
Y
.
B
h
a
n
u
sr
e
e
,
B
.
S
.
D
e
e
k
sh
a
,
V
.
S
o
h
a
n
,
D
.
A
j
a
y
,
a
n
d
M
.
E
.
S
.
R
a
m,
“
A
d
e
e
p
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
t
o
p
r
e
d
i
c
t
t
o
p
r
e
d
i
c
t
C
O
V
I
D
-
1
9
t
h
r
o
u
g
h
c
o
u
g
h
a
n
a
l
y
si
s
u
si
n
g
C
N
N
-
B
i
D
i
r
e
c
t
i
o
n
a
l
LST
M
,
”
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
O
N
A
T5
3
4
2
3
.
2
0
2
2
.
9
7
2
6
0
6
7
.
[
4
]
N
.
K
.
C
h
o
w
d
h
u
r
y
,
M
.
A
.
K
a
b
i
r
,
M
.
M
.
R
a
h
ma
n
,
a
n
d
S
.
M
.
S
.
I
sl
a
m,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
f
o
r
d
e
t
e
c
t
i
n
g
C
O
V
I
D
-
1
9
f
r
o
m
c
o
u
g
h
so
u
n
d
s:
a
n
e
n
sem
b
l
e
-
b
a
se
d
M
C
D
M
me
t
h
o
d
,
”
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
,
v
o
l
.
1
4
5
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
mp
b
i
o
m
e
d
.
2
0
2
2
.
1
0
5
4
0
5
.
[
5
]
S
.
J.
K
h
o
e
t
a
l
.
,
“
M
a
l
a
y
si
a
n
c
o
u
g
h
so
u
n
d
a
n
a
l
y
si
s a
n
d
C
O
V
I
D
-
1
9
c
l
a
ssi
f
i
c
a
t
i
o
n
w
i
t
h
d
e
e
p
l
e
a
r
n
i
n
g
,
”
I
n
t
e
l
l
i
g
e
n
c
e
-
Ba
s
e
d
Me
d
i
c
i
n
e
,
v
o
l
.
9
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
b
me
d
.
2
0
2
3
.
1
0
0
1
2
9
.
[
6
]
K
.
R
a
h
o
u
ma,
S
.
R
a
m
z
y
,
a
n
d
M
.
A
l
y
,
“
A
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
a
g
a
i
n
st
v
i
r
u
s
c
h
a
n
g
e
s
:
a
l
o
n
g
t
e
r
m
d
e
t
e
c
t
o
r
o
f
C
O
V
I
D
-
1
9
u
si
n
g
t
h
e
c
l
i
n
i
c
a
l
s
y
m
p
t
o
ms
a
n
d
r
e
s
p
i
r
a
t
o
r
y
so
u
n
d
s,
”
J
o
u
rn
a
l
o
f
A
d
v
a
n
c
e
d
En
g
i
n
e
e
ri
n
g
T
re
n
d
s
,
v
o
l
.
4
2
,
n
o
.
2
,
p
p
.
2
8
9
–
2
9
9
,
2
0
2
3
,
d
o
i
:
1
0
.
2
1
6
0
8
/
j
a
e
t
.
2
0
2
2
.
1
3
2
5
5
2
.
1
1
4
9
.
[
7
]
A
.
F
a
k
h
r
y
,
X
.
J
i
a
n
g
,
J
.
X
i
a
o
,
G
.
C
h
a
u
d
h
a
r
i
,
A
.
H
a
n
,
a
n
d
A
.
K
h
a
n
z
a
d
a
,
“
V
i
r
u
f
y
:
a
mu
l
t
i
-
b
r
a
n
c
h
d
e
e
p
l
e
a
r
n
i
n
g
n
e
t
w
o
r
k
f
o
r
a
u
t
o
m
a
t
e
d
d
e
t
e
c
t
i
o
n
o
f
C
O
V
I
D
-
1
9
,
”
2
0
2
1
.
[
8
]
S
.
Ta
n
g
,
X
.
H
u
,
L.
A
t
l
a
s,
A
.
K
h
a
n
z
a
d
a
,
a
n
d
M
.
P
i
l
a
n
c
i
,
“
H
i
e
r
a
r
c
h
i
c
a
l
mu
l
t
i
-
mo
d
a
l
t
r
a
n
sf
o
r
mer
f
o
r
a
u
t
o
m
a
t
i
c
d
e
t
e
c
t
i
o
n
o
f
C
O
V
I
D
-
19,
”
i
n
AC
M
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
Pro
c
e
e
d
i
n
g
S
e
ri
e
s
,
2
0
2
2
,
p
p
.
1
9
7
–
2
0
2
,
d
o
i
:
1
0
.
1
1
4
5
/
3
5
5
6
3
8
4
.
3
5
5
6
4
1
4
.
[
9
]
Y
.
M
a
r
u
sh
k
o
,
A
.
A
b
a
t
u
r
o
v
,
H
.
B
e
k
e
t
o
v
a
,
V
.
B
e
r
e
z
e
n
k
o
,
T
.
P
o
c
h
y
n
o
k
,
a
n
d
A
.
C
h
u
r
y
l
i
n
a
,
“
N
e
w
v
i
e
w
s
o
n
t
h
e
d
i
a
g
n
o
s
i
s
a
n
d
t
r
e
a
t
me
n
t
o
f
a
st
h
m
a
i
n
c
h
i
l
d
r
e
n
,
”
C
h
i
l
d
’
s He
a
l
t
h
,
v
o
l
.
1
7
,
n
o
.
2
,
p
p
.
1
0
7
–
1
1
3
,
2
0
2
2
,
d
o
i
:
1
0
.
2
2
1
4
1
/
2
2
2
4
-
0
5
5
1
.
1
7
.
2
.
2
0
2
2
.
1
5
0
3
.
[
1
0
]
L.
O
r
l
a
n
d
i
c
,
T
.
Te
i
j
e
i
r
o
,
a
n
d
D
.
A
t
i
e
n
z
a
,
“
T
h
e
C
O
U
G
H
V
I
D
c
r
o
w
d
s
o
u
r
c
i
n
g
d
a
t
a
se
t
,
a
c
o
r
p
u
s
f
o
r
t
h
e
s
t
u
d
y
o
f
l
a
r
g
e
-
sca
l
e
c
o
u
g
h
a
n
a
l
y
si
s
a
l
g
o
r
i
t
h
ms
,
”
S
c
i
e
n
t
i
f
i
c
D
a
t
a
,
v
o
l
.
8
,
n
o
.
1
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
5
9
7
-
0
2
1
-
0
0
9
3
7
-
4.
[
1
1
]
N
.
S
h
a
r
m
a
e
t
a
l
.
,
“
C
o
sw
a
r
a
-
A
d
a
t
a
b
a
se
o
f
b
r
e
a
t
h
i
n
g
,
c
o
u
g
h
,
a
n
d
v
o
i
c
e
s
o
u
n
d
s
f
o
r
C
O
V
I
D
-
1
9
d
i
a
g
n
o
si
s
,
”
i
n
P
ro
c
e
e
d
i
n
g
s
o
f
t
h
e
An
n
u
a
l
C
o
n
f
e
r
e
n
c
e
o
f
t
h
e
I
n
t
e
r
n
a
t
i
o
n
a
l
S
p
e
e
c
h
C
o
m
m
u
n
i
c
a
t
i
o
n
Ass
o
c
i
a
t
i
o
n
,
I
N
T
ER
S
P
EEC
H
,
2
0
2
0
,
p
p
.
4
8
1
1
–
4
8
1
5
,
d
o
i
:
1
0
.
2
1
4
3
7
/
I
n
t
e
r
sp
e
e
c
h
.
2
0
2
0
-
2
7
6
8
.
[
1
2
]
T.
N
.
M
.
A
r
i
s,
A
.
A
.
B
.
U
.
B
a
k
a
r
,
N
.
M
a
h
i
d
d
i
n
,
a
n
d
M
.
Zo
l
k
e
p
l
i
,
“
A
f
u
z
z
y
i
n
f
e
r
e
n
c
e
m
o
d
e
l
f
o
r
d
i
a
g
n
o
si
s
o
f
d
i
a
b
e
t
e
s
a
n
d
l
e
v
e
l
o
f
c
a
r
e
,
”
J
o
u
r
n
a
l
o
f
T
h
e
o
r
e
t
i
c
a
l
a
n
d
A
p
p
l
i
e
d
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
1
0
1
,
n
o
.
1
5
,
p
p
.
5
9
6
2
–
5
9
7
5
,
2
0
2
3
.
[
1
3
]
B
.
M
.
K
o
g
a
n
,
L.
E.
K
u
z
’
mi
s
h
i
n
,
a
n
d
A
.
A
.
La
v
r
o
v
,
“
I
mp
o
r
t
a
n
c
e
o
f
u
l
t
r
a
so
n
i
c
d
i
a
g
n
o
si
s
t
o
me
d
i
c
a
l
e
x
p
e
r
t
e
v
a
l
u
a
t
i
o
n
o
f
t
h
e
w
o
r
k
c
a
p
a
c
i
t
y
o
f
i
sc
h
e
m
i
c
h
e
a
r
t
d
i
se
a
se
p
a
t
i
e
n
t
s,
”
v
o
l
.
2
4
,
n
o
.
8
,
p
p
.
3
8
–
4
1
,
1
9
8
4
.
[
1
4
]
J.
L.
M
u
l
s
h
i
n
e
,
“
O
n
e
scr
e
e
n
i
n
g
f
o
r
i
sch
e
mi
c
h
e
a
r
t
d
i
se
a
se
,
l
u
n
g
c
a
n
c
e
r
,
a
n
d
c
h
r
o
n
i
c
o
b
s
t
r
u
c
t
i
v
e
p
u
l
m
o
n
a
r
y
d
i
sea
se
:
a
sy
st
e
ms
b
i
o
l
o
g
y
b
r
i
d
g
e
f
o
r
t
o
b
a
c
c
o
a
n
d
r
a
d
i
a
t
i
o
n
e
x
p
o
s
u
r
e
,
”
Am
e
r
i
c
a
n
J
o
u
r
n
a
l
o
f
Pu
b
l
i
c
H
e
a
l
t
h
,
v
o
l
.
1
0
8
,
n
o
.
1
0
,
p
p
.
1
2
9
4
–
1
2
9
5
,
2
0
1
8
,
d
o
i
:
1
0
.
2
1
0
5
/
A
JP
H
.
2
0
1
8
.
3
0
4
6
5
5
.
[
1
5
]
A
.
F
u
l
z
e
l
e
,
P
.
P
a
t
i
l
,
A
.
T
h
a
k
r
e
,
A
.
M
a
h
a
l
e
,
S
.
S
h
e
l
k
e
,
a
n
d
C
.
E
n
g
i
n
e
e
r
i
n
g
,
“
A
m
o
b
i
l
e
a
p
p
l
i
c
a
t
i
o
n
f
o
r
e
a
r
l
y
d
i
a
g
n
o
s
i
s
o
f
p
n
e
u
mo
n
i
a
,
”
2
0
2
2
.
[
1
6
]
A
.
A
.
A
b
d
e
l
h
a
mi
d
e
t
a
l
.
,
“
R
o
b
u
s
t
sp
e
e
c
h
e
mo
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
u
si
n
g
C
N
N
+
LSTM
b
a
se
d
o
n
st
o
c
h
a
s
t
i
c
f
r
a
c
t
a
l
sea
r
c
h
o
p
t
i
mi
z
a
t
i
o
n
a
l
g
o
r
i
t
h
m,
”
I
EEE
Ac
c
e
ss
,
v
o
l
.
1
0
,
p
p
.
4
9
2
6
5
–
4
9
2
8
4
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
2
.
3
1
7
2
9
5
4
.
[
1
7
]
N
.
S
e
n
g
u
p
t
a
,
M
.
S
a
h
i
d
u
l
l
a
h
,
a
n
d
G
.
S
a
h
a
,
“
L
u
n
g
so
u
n
d
c
l
a
ss
i
f
i
c
a
t
i
o
n
u
s
i
n
g
c
e
p
s
t
r
a
l
-
b
a
s
e
d
st
a
t
i
st
i
c
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
,
v
o
l
.
7
5
,
p
p
.
1
1
8
–
1
2
9
,
2
0
1
6
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
mp
b
i
o
med
.
2
0
1
6
.
0
5
.
0
1
3
.
[
1
8
]
Z.
M
u
sh
t
a
q
a
n
d
S
.
F
.
S
u
,
“
Ef
f
i
c
i
e
n
t
c
l
a
ssi
f
i
c
a
t
i
o
n
o
f
e
n
v
i
r
o
n
me
n
t
a
l
s
o
u
n
d
s
t
h
r
o
u
g
h
m
u
l
t
i
p
l
e
f
e
a
t
u
r
e
s
a
g
g
r
e
g
a
t
i
o
n
a
n
d
d
a
t
a
e
n
h
a
n
c
e
me
n
t
t
e
c
h
n
i
q
u
e
s fo
r
sp
e
c
t
r
o
g
r
a
m i
m
a
g
e
s,
”
S
y
m
m
e
t
ry
,
v
o
l
.
1
2
,
n
o
.
1
1
,
p
p
.
1
–
3
4
,
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
s
y
m
1
2
1
1
1
8
2
2
.
[
1
9
]
T.
A
.
A
d
e
s
u
y
i
,
B
.
M
.
K
i
m,
a
n
d
J.
K
i
m,
“
S
n
o
r
i
n
g
s
o
u
n
d
c
l
a
ssi
f
i
c
a
t
i
o
n
u
si
n
g
1
D
-
C
N
N
m
o
d
e
l
b
a
se
d
o
n
mu
l
t
i
-
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
F
u
zzy
L
o
g
i
c
a
n
d
I
n
t
e
l
l
i
g
e
n
t
S
y
st
e
m
s
,
v
o
l
.
2
2
,
n
o
.
1
,
p
p
.
1
–
10
,
2
0
2
2
,
d
o
i
:
1
0
.
5
3
9
1
/
I
JF
I
S
.
2
0
2
2
.
2
2
.
1
.
1
.
[
2
0
]
S
.
P
r
u
st
y
,
S
.
P
a
t
n
a
i
k
,
a
n
d
S
.
K
.
D
a
sh
,
“
S
K
C
V
:
s
t
r
a
t
i
f
i
e
d
k
-
f
o
l
d
c
r
o
ss
-
v
a
l
i
d
a
t
i
o
n
o
n
M
L
c
l
a
ssi
f
i
e
r
s
f
o
r
p
r
e
d
i
c
t
i
n
g
c
e
r
v
i
c
a
l
c
a
n
c
e
r
,
”
Fro
n
t
i
e
rs
i
n
N
a
n
o
t
e
c
h
n
o
l
o
g
y
,
v
o
l
.
4
,
2
0
2
2
,
d
o
i
:
1
0
.
3
3
8
9
/
f
n
a
n
o
.
2
0
2
2
.
9
7
2
4
2
1
.
[
2
1
]
H
.
M
.
N
g
u
y
e
n
,
E
.
W
.
C
o
o
p
e
r
,
a
n
d
K
.
K
a
me
i
,
“
B
o
r
d
e
r
l
i
n
e
o
v
e
r
-
s
a
mp
l
i
n
g
f
o
r
i
mb
a
l
a
n
c
e
d
d
a
t
a
c
l
a
ss
i
f
i
c
a
t
i
o
n
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
K
n
o
w
l
e
d
g
e
En
g
i
n
e
e
r
i
n
g
a
n
d
S
o
f
t
D
a
t
a
Pa
ra
d
i
g
m
s
,
v
o
l
.
3
,
n
o
.
1
,
p
p
.
4
–
2
1
,
2
0
1
1
,
d
o
i
:
1
0
.
1
5
0
4
/
i
j
k
e
sd
p
.
2
0
1
1
.
0
3
9
8
7
5
.
[
2
2
]
G
.
K
e
e
t
a
l
.
,
“
L
i
g
h
t
G
B
M
:
a
h
i
g
h
l
y
e
f
f
i
c
i
e
n
t
g
r
a
d
i
e
n
t
b
o
o
s
t
i
n
g
d
e
c
i
si
o
n
t
r
e
e
,
”
Ad
v
a
n
c
e
s i
n
N
e
u
r
a
l
I
n
f
o
rm
a
t
i
o
n
Pr
o
c
e
ssi
n
g
S
y
s
t
e
m
s
,
p
p
.
3
1
4
7
–
3
1
5
5
,
2
0
1
7
.
[
2
3
]
N
.
D
u
n
b
r
a
y
,
R
.
R
a
n
e
,
S
.
N
i
m
j
e
,
J
.
K
a
t
a
d
e
,
a
n
d
S
.
M
a
v
a
l
e
,
“
A
N
o
v
e
l
n
o
v
e
l
p
r
e
d
i
c
t
i
o
n
m
o
d
e
l
f
o
r
d
i
a
b
e
t
e
s
d
e
t
e
c
t
i
o
n
u
s
i
n
g
gr
i
d
sea
r
c
h
a
n
d
a
v
o
t
i
n
g
c
l
a
ssi
f
i
e
r
b
e
t
w
e
e
n
Li
g
h
t
G
B
M
a
n
d
K
N
N
,
”
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
G
C
A
T
5
2
1
8
2
.
2
0
2
1
.
9
5
8
7
5
5
1
.
[
2
4
]
M
.
S
o
k
o
l
o
v
a
a
n
d
G
.
L
a
p
a
l
me,
“
A
sy
st
e
ma
t
i
c
a
n
a
l
y
s
i
s
o
f
p
e
r
f
o
r
m
a
n
c
e
me
a
su
r
e
s
f
o
r
c
l
a
ssi
f
i
c
a
t
i
o
n
t
a
s
k
s,”
I
n
f
o
rm
a
t
i
o
n
Pro
c
e
ss
i
n
g
a
n
d
Ma
n
a
g
e
m
e
n
t
,
v
o
l
.
4
5
,
n
o
.
4
,
p
p
.
4
2
7
–
4
3
7
,
2
0
0
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
p
m
.
2
0
0
9
.
0
3
.
0
0
2
.
[
2
5
]
Z.
Zh
a
n
g
,
T.
Z
h
a
n
g
,
a
n
d
J
.
Li
,
“
U
n
b
i
a
s
e
d
g
r
a
d
i
e
n
t
b
o
o
st
i
n
g
d
e
c
i
si
o
n
t
r
e
e
w
i
t
h
u
n
b
i
a
se
d
f
e
a
t
u
r
e
i
m
p
o
r
t
a
n
c
e
,
”
i
n
I
J
C
AI
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
i
n
t
C
o
n
f
e
r
e
n
c
e
o
n
A
rt
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
2
0
2
3
,
p
p
.
4
6
2
9
–
4
6
3
7
,
d
o
i
:
1
0
.
2
4
9
6
3
/
i
j
c
a
i
.
2
0
2
3
/
5
1
5
.
[
2
6
]
B
.
M
c
F
e
e
e
t
a
l
.
,
“
Li
b
r
o
s
a
:
A
u
d
i
o
a
n
d
mu
s
i
c
s
i
g
n
a
l
a
n
a
l
y
si
s
i
n
i
n
P
y
t
h
o
n
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
1
4
t
h
P
y
t
h
o
n
i
n
S
c
i
e
n
c
e
C
o
n
f
e
re
n
c
e
,
2
0
1
5
,
p
p
.
1
8
–
2
4
,
d
o
i
:
1
0
.
2
5
0
8
0
/
ma
j
o
r
a
-
7
b
9
8
e
3
e
d
-
0
0
3
.
[
2
7
]
G
.
Le
ma
,
F
e
r
n
a
n
d
o
N
o
g
u
e
i
r
a
,
a
n
d
C
h
r
i
st
o
s
K
.
A
r
i
d
a
s,
“
I
mb
a
l
a
n
c
e
d
-
l
e
a
r
n
:
a
P
y
t
h
o
n
t
o
o
l
b
o
x
t
o
t
a
c
k
l
e
t
h
e
c
u
r
s
e
o
f
i
mb
a
l
a
n
c
e
d
d
a
t
a
se
t
s
i
n
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
J
o
u
rn
a
l
o
f
Ma
c
h
i
n
e
L
e
a
r
n
i
n
g
R
e
se
a
rc
h
,
v
o
l
.
1
8
,
n
o
.
1
7
,
p
p
.
1
–
5
,
2
0
1
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
ctio
n
o
f COVI
D
-
1
9
b
a
s
ed
o
n
co
u
g
h
s
o
u
n
d
a
n
d
a
cc
o
m
p
a
n
yin
g
s
ymp
to
n
u
s
in
g
…
(
Wih
a
r
to
)
949
[
2
8
]
T.
H
o
a
n
g
,
L
.
P
h
a
m
,
D
.
N
g
o
,
a
n
d
H
.
D
.
N
g
u
y
e
n
,
“
A
c
o
u
g
h
-
b
a
se
d
d
e
e
p
l
e
a
r
n
i
n
g
f
r
a
mew
o
r
k
f
o
r
d
e
t
e
c
t
i
n
g
C
O
V
I
D
-
1
9
,
”
i
n
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
A
n
n
u
a
l
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
f
t
h
e
I
E
EE
E
n
g
i
n
e
e
r
i
n
g
i
n
Me
d
i
c
i
n
e
a
n
d
B
i
o
l
o
g
y
S
o
c
i
e
t
y
,
EM
B
S
,
2
0
2
2
,
p
p
.
3
4
2
2
–
3
4
2
5
,
d
o
i
:
1
0
.
1
1
0
9
/
E
M
B
C
4
8
2
2
9
.
2
0
2
2
.
9
8
7
1
1
7
9
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Wih
a
r
to
re
c
e
iv
e
d
o
b
tai
n
e
d
a
b
a
c
h
e
lo
r’s
d
e
g
re
e
i
n
e
lec
tri
c
a
l
e
n
g
i
n
e
e
rin
g
(B.
E.
)
fro
m
Un
iv
e
rsitas
Telk
o
m
,
I
n
d
o
n
e
sia
,
in
1
9
9
9
.
He
o
b
tain
e
d
a
m
a
ste
r’s
d
e
g
re
e
in
c
o
m
p
u
ter
sc
ien
c
e
fro
m
Un
iv
e
rsitas
G
a
d
jah
M
a
d
a
,
In
d
o
n
e
sia
,
in
2
0
0
4
a
n
d
a
Do
c
to
ra
l
d
e
g
re
e
fro
m
th
e
sa
m
e
Un
iv
e
rsity
,
i
n
2
0
1
7
.
C
u
rre
n
tl
y
h
e
w
o
rk
s
a
s
a
lec
tu
re
r
i
n
t
h
e
In
f
o
rm
a
ti
c
s
De
p
a
rtme
n
t,
F
a
c
u
lt
y
o
f
In
f
o
rm
a
ti
o
n
Tec
h
n
o
l
o
g
y
a
n
d
Da
ta
S
c
ien
c
e
,
Un
i
v
e
rsitas
S
e
b
e
las
M
a
re
t,
S
u
ra
k
a
rta,
In
d
o
n
e
sia
.
His
e
x
p
e
rien
c
e
a
n
d
a
r
e
a
s
o
f
in
tere
st
fo
c
u
s
o
n
a
rti
ficia
l
in
telli
g
e
n
c
e
,
c
o
m
p
u
tati
o
n
a
l
in
telli
g
e
n
c
e
,
b
i
o
m
e
d
ica
l
c
o
m
p
u
t
a
ti
o
n
,
a
n
d
c
li
n
ica
l
d
e
c
isio
n
s
u
p
p
o
rt
sy
ste
m
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
wih
a
rt
o
@s
taff.u
n
s.a
c
.
i
d
.
Ann
a
s
Abd
u
r
r
a
h
m
a
n
re
c
e
i
v
e
d
th
e
b
a
c
h
e
lo
r’s
d
e
g
re
e
in
in
f
o
rm
a
ti
c
s
fro
m
th
e
F
a
c
u
lt
y
o
f
In
f
o
rm
a
ti
o
n
Tec
h
n
o
l
o
g
y
a
n
d
Da
ta
S
c
ien
c
e
,
Un
i
v
e
rsitas
S
e
b
e
las
M
a
re
t,
S
u
ra
k
a
rta,
In
d
o
n
e
sia
,
2
0
2
3
.
His
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
so
f
t
c
o
m
p
u
ti
n
g
,
m
a
c
h
in
e
lea
rn
in
g
,
a
n
d
in
telli
g
e
n
t
sy
ste
m
s.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
a
n
n
a
sa
b
d
u
rra
h
m
a
n
3
5
4
@s
tu
d
e
n
t.
u
n
s.a
c
.
i
d
.
Um
i
S
a
l
a
m
a
h
re
c
e
iv
e
d
h
e
r
b
a
c
h
e
lo
r’s
d
e
g
re
e
fro
m
th
e
De
p
a
rtme
n
t
o
f
M
a
th
e
m
a
ti
c
s,
Un
iv
e
rsitas
S
e
b
e
la
s
M
a
re
t,
I
n
d
o
n
e
sia
,
in
1
9
9
4
.
S
h
e
re
c
e
iv
e
d
h
e
r
m
a
ste
r’s
a
n
d
Do
c
to
ra
l
d
e
g
re
e
s
fro
m
t
h
e
De
p
a
rt
m
e
n
t
o
f
I
n
fo
rm
a
ti
c
s
E
n
g
i
n
e
e
rin
g
,
In
stit
u
t
Te
k
n
o
lo
g
i
S
e
p
u
lu
h
No
p
e
m
b
e
r,
I
n
d
o
n
e
sia
,
i
n
2
0
0
2
a
n
d
2
0
1
8
,
re
sp
e
c
ti
v
e
l
y
.
He
r
re
se
a
rc
h
in
tere
sts
i
n
c
lu
d
e
fu
z
z
y
lo
g
ic
a
n
d
sy
ste
m
s,
ima
g
e
p
ro
c
e
s
sin
g
,
a
p
p
li
e
d
m
a
th
e
m
a
ti
c
s,
a
n
d
c
o
m
p
u
tat
i
o
n
a
l
sc
ien
c
e
s.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
u
m
isa
lam
a
h
@s
taff.u
n
s.a
c
.
id
.
Evaluation Warning : The document was created with Spire.PDF for Python.