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.
39
,
No
.
1
,
J
u
l
y
2
0
2
5
,
p
p
.
669
~
6
8
0
I
SS
N:
2
5
0
2
-
4
7
5
2
,
DOI
: 1
0
.
1
1
5
9
1
/ijeecs.v
39
.i
1
.
pp
669
-
6
8
0
669
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs.ia
esco
r
e.
co
m
No
n
-
co
ntact
brea
thing ra
te
mo
nito
ring
using
inf
ra
r
e
d
thermog
ra
phy
and ma
chine l
ea
rni
ng
Ana
dy
a
G
hin
a
Sa
ls
a
bil
a
1
,
Ra
chm
a
d Set
ia
wa
n
1
,
Na
da
F
it
riey
a
t
ul H
ikm
a
h
1
,
Z
a
in B
ud
i
Sy
ultho
ni
2
1
D
e
p
a
r
t
me
n
t
o
f
B
i
o
m
e
d
i
c
a
l
En
g
i
n
e
e
r
i
n
g
,
F
a
c
u
l
t
y
o
f
I
n
t
e
l
l
i
g
e
n
t
El
e
c
t
r
i
c
a
l
Te
c
h
n
o
l
o
g
y
a
n
d
I
n
f
o
r
m
a
t
i
c
s,
I
n
st
i
t
u
t
Te
k
n
o
l
o
g
i
S
e
p
u
l
u
h
N
o
p
e
m
b
e
r
(
I
TS)
,
S
u
r
a
b
a
y
a
,
I
n
d
o
n
e
s
i
a
2
M
e
d
i
c
a
l
P
r
o
f
e
s
si
o
n
S
t
u
d
y
P
r
o
g
r
a
m,
F
a
c
u
l
t
y
o
f
M
e
d
i
c
i
n
e
a
n
d
H
e
a
l
t
h
,
I
n
st
i
t
u
t
Te
k
n
o
l
o
g
i
S
e
p
u
l
u
h
N
o
p
e
m
b
e
r
(
I
TS)
,
S
u
r
a
b
a
y
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
Au
g
9
,
2
0
2
4
R
ev
is
ed
Mar
13
,
2
0
2
5
Acc
ep
ted
Mar
26
,
2
0
2
5
M
o
n
i
t
o
r
i
n
g
v
i
ta
l
p
h
y
si
o
l
o
g
ic
a
l
p
a
ra
m
e
t
e
rs
s
u
c
h
a
s
b
re
a
t
h
i
n
g
ra
t
e
(B
R)
is
c
ru
c
ia
l
f
o
r
a
s
se
ss
i
n
g
p
a
t
ie
n
t
h
e
a
lt
h
.
H
o
w
e
v
e
r
,
c
u
r
re
n
t
c
o
n
t
a
c
t
-
b
a
se
d
m
e
a
su
re
m
e
n
t
m
e
t
h
o
d
s
o
f
te
n
c
a
u
s
e
d
i
sc
o
m
f
o
rt
,
p
a
r
ti
c
u
lar
l
y
i
n
in
fa
n
ts
o
r
b
u
r
n
p
a
ti
e
n
ts
.
T
h
is
s
t
u
d
y
a
im
s
t
o
d
e
v
e
l
o
p
a
non
-
c
o
n
tac
t
s
y
s
tem
f
o
r
m
o
n
i
to
r
in
g
BR
u
s
i
n
g
i
n
f
ra
r
e
d
t
h
e
r
m
o
g
ra
p
h
y
(
IR
T)
.
T
h
is
a
p
p
r
o
a
c
h
p
e
rm
i
ts
t
o
d
e
tec
t
s
a
n
d
trac
k
s
t
h
e
n
o
s
e
f
r
o
m
t
h
e
rm
a
l
v
i
d
e
o
,
e
x
t
ra
c
ts
tem
p
e
r
a
t
u
r
e
v
a
r
ia
ti
o
n
s
i
n
t
o
a
b
re
a
t
h
i
n
g
s
i
g
n
a
l
,
a
n
d
p
r
o
c
e
s
se
s
t
h
is
s
i
g
n
a
l
to
e
s
ti
m
a
te
B
R.
T
h
e
e
s
ti
m
a
t
e
d
BR
is
th
e
n
c
la
ss
if
ie
d
i
n
t
o
t
h
re
e
h
e
a
l
t
h
c
a
te
g
o
r
ies
(
b
ra
d
y
p
n
e
a
/
n
o
rm
a
l/
t
a
c
h
y
p
n
e
a
)
u
s
i
n
g
k
-
n
e
a
re
s
t
n
e
i
g
h
b
o
rs
(
k
-
NN
)
.
T
o
e
v
a
l
u
a
te
s
y
ste
m
a
c
c
u
ra
c
y
a
n
d
ro
b
u
s
t
n
e
ss
,
e
x
p
e
rime
n
ts
we
re
c
o
n
d
u
c
te
d
u
n
d
e
r
t
h
re
e
c
o
n
d
i
ti
o
n
s
:
(
i
)
sta
ti
o
n
a
r
y
b
re
a
t
h
i
n
g
,
(
ii
)
b
re
a
t
h
i
n
g
w
it
h
h
e
a
d
m
o
v
e
m
e
n
t
s,
a
n
d
(
ii
i
)
s
p
e
c
if
ic
b
re
a
t
h
i
n
g
p
a
tt
e
r
n
s
.
Re
s
u
lt
s
d
e
m
o
n
st
ra
te
d
h
ig
h
c
o
n
sis
te
n
c
y
w
it
h
c
o
n
tac
t
-
b
a
se
d
p
h
o
t
o
p
let
h
y
s
m
o
g
ra
p
h
y
(
P
P
G
)
m
e
a
su
re
m
e
n
ts
,
a
c
h
ie
v
i
n
g
c
o
m
p
lem
e
n
t
o
f
t
h
e
a
b
s
o
l
u
te
n
o
rm
a
l
ize
d
d
if
fe
re
n
c
e
(
CAN
D
)
i
n
d
e
x
v
a
l
u
e
s
o
f
9
4
.
5
7
%
,
9
3
.
7
1
%
,
a
n
d
9
6
.
0
6
%
a
c
r
o
ss
t
h
e
t
h
r
e
e
c
o
n
d
i
ti
o
n
s
a
n
d
m
e
a
n
a
b
s
o
l
u
te BR
e
r
ro
r
s o
f
1
.
0
4
5
b
p
m
,
1
.
2
5
9
b
p
m
,
a
n
d
0
.
6
0
7
b
p
m
.
T
h
e
k
-
N
N
c
las
si
fie
r
d
e
m
o
n
st
ra
te
d
h
i
g
h
p
e
r
f
o
rm
a
n
c
e
wi
t
h
tr
a
i
n
i
n
g
,
v
a
li
d
a
t
io
n
,
a
n
d
tes
t
i
n
g
a
c
c
u
ra
c
ies
o
f
1
0
0
%
,
1
0
0
%
,
a
n
d
9
9
.
2
%
,
re
s
p
e
c
t
iv
e
l
y
.
S
e
n
s
i
ti
v
i
t
y
,
s
p
e
c
i
fic
i
t
y
,
p
re
c
is
i
o
n
,
a
n
d
F
-
m
e
a
s
u
re
re
s
u
l
ts
c
o
n
fi
rm
sy
ste
m
re
l
ia
b
i
li
t
y
f
o
r
n
o
n
-
c
o
n
ta
c
t
BR
m
o
n
i
t
o
r
i
n
g
in
c
li
n
ica
l
a
n
d
p
ra
c
ti
c
a
l
se
tt
i
n
g
s
.
K
ey
w
o
r
d
s
:
B
r
ea
th
in
g
r
ate
Hea
lth
I
n
f
r
ar
e
d
th
er
m
o
g
r
a
p
h
y
Ma
ch
in
e
lear
n
in
g
No
n
-
co
n
tact
m
ea
s
u
r
em
en
t
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
:
Nad
a
Fit
r
iey
atu
l H
ik
m
ah
Dep
ar
tm
en
t o
f
B
io
m
ed
ical
E
n
g
in
ee
r
in
g
,
Facu
lty
o
f
I
n
tellig
e
n
t E
lectr
ical
an
d
I
n
f
o
r
m
atics T
ec
h
n
o
lo
g
y
I
n
s
titu
t T
ek
n
o
lo
g
i Sep
u
lu
h
No
p
em
b
er
(
I
T
S)
Su
r
ab
ay
a,
I
n
d
o
n
esia
E
m
ail: n
ad
af
h
@
b
m
e.
its
.
ac
.
id
1.
I
NT
RO
D
UCT
I
O
N
Mo
n
ito
r
in
g
v
ital p
h
y
s
io
lo
g
ical
p
ar
am
eter
s
s
u
ch
as b
r
ea
th
in
g
r
ate
(
B
R
)
is
cr
u
cial
f
o
r
ass
ess
i
n
g
p
atien
t
h
ea
lth
.
B
R
,
d
ef
i
n
ed
as
th
e
n
u
m
b
er
o
f
b
r
ea
th
i
n
g
cy
cles
p
e
r
m
in
u
te,
i
n
clu
d
es
in
s
p
ir
atio
n
(
i
n
h
alin
g
o
x
y
g
en
)
a
n
d
ex
p
ir
atio
n
(
ex
h
alin
g
ca
r
b
o
n
d
io
x
id
e)
[
1
]
.
Ab
n
o
r
m
al
B
R
(
ta
ch
y
p
n
ea
,
b
r
ad
y
p
n
ea
,
o
r
ap
n
e
a)
ca
n
s
er
v
e
as
an
ea
r
ly
in
d
icato
r
o
f
v
a
r
io
u
s
r
e
s
p
ir
ato
r
y
d
is
ea
s
es,
in
clu
d
in
g
asth
m
a,
ch
r
o
n
ic
o
b
s
tr
u
ctiv
e
p
u
lm
o
n
ar
y
d
is
ea
s
e
(
C
OPD)
,
an
d
p
u
lm
o
n
ar
y
t
h
r
o
m
b
o
em
b
o
lis
m
[
2
]
,
[
3
]
.
Desp
ite
its
im
p
o
r
tan
ce
,
B
R
is
o
f
ten
u
n
d
o
cu
m
en
ted
d
u
e
to
th
e
lack
o
f
ac
ce
s
s
ib
le
m
o
n
ito
r
in
g
m
eth
o
d
s
[
4
]
.
C
u
r
r
e
n
t
tech
n
iq
u
es
ty
p
ically
r
eq
u
ir
e
th
e
att
ac
h
m
en
t
o
f
s
en
s
o
r
s
to
th
e
p
atien
t
’
s
b
o
d
y
,
wh
ich
ca
n
ca
u
s
e
d
is
co
m
f
o
r
t,
s
tr
ess
,
an
d
ev
e
n
p
ain
,
p
ar
tic
u
lar
ly
in
ch
ild
r
en
an
d
b
u
r
n
p
atien
ts
[
5
]
.
T
r
ad
itio
n
al
B
R
m
o
n
ito
r
in
g
m
eth
o
d
s
in
v
o
lv
e
ass
ess
in
g
ch
est
m
o
v
em
en
ts
with
r
esp
ir
ato
r
y
b
elt
tr
an
s
d
u
ce
r
s
,
elec
tr
ical
im
p
ed
a
n
ce
,
E
C
G,
PP
G
m
o
r
p
h
o
lo
g
y
,
ca
p
n
o
g
r
ap
h
y
,
o
r
s
p
ir
o
m
etr
y
[
6
]
-
[
1
0
]
.
W
h
ile
th
ese
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
39
,
No
.
1
,
J
u
ly
20
25
:
669
-
6
8
0
670
m
eth
o
d
s
ar
e
r
eliab
le,
th
e
y
a
r
e
in
tr
u
s
iv
e
an
d
m
a
y
lead
t
o
s
en
s
o
r
d
is
lo
ca
tio
n
,
wh
ich
co
u
ld
co
m
p
r
o
m
is
e
m
ea
s
u
r
em
en
t
ac
cu
r
ac
y
o
r
,
in
in
d
iv
id
u
als
with
s
en
s
itiv
e
s
k
in
lik
e
in
f
a
n
ts
o
r
b
u
r
n
v
ictim
s
,
ca
u
s
e
ir
r
itatio
n
o
r
ev
en
s
k
in
d
am
ag
e
.
Ad
d
itio
n
ally
,
u
s
in
g
d
is
p
o
s
ab
le
s
en
s
o
r
s
,
s
u
ch
as e
lectr
o
d
es,
in
cr
ea
s
es c
o
m
p
lex
ity
an
d
co
s
ts
,
p
r
esen
ts
ch
allen
g
es
in
h
an
d
lin
g
an
d
h
y
g
ien
e,
an
d
co
n
tr
i
b
u
te
s
to
m
ed
ical
waste
[
1
1
]
.
C
o
n
s
eq
u
en
tly
,
th
er
e
is
a
g
r
o
win
g
d
em
an
d
f
o
r
n
o
n
-
co
n
tact
B
R
m
o
n
ito
r
in
g
alter
n
at
iv
es
th
at
im
p
r
o
v
e
p
atien
t
co
m
f
o
r
t
an
d
o
p
tim
ize
m
ed
ical
r
eso
u
r
ce
s
[
1
2
]
.
Sev
er
al
n
o
n
-
co
n
tact
tech
n
iq
u
e
s
h
av
e
b
ee
n
p
r
o
p
o
s
ed
,
s
u
ch
as
au
d
io
a
n
aly
s
is
,
d
o
p
p
ler
r
a
d
ar
,
m
ag
n
etic
in
d
u
ctio
n
,
an
d
im
ag
in
g
m
eth
o
d
s
u
s
in
g
R
GB
ca
m
er
as
an
t
h
er
m
al
im
ag
in
g
[
1
3
]
-
[
1
6
]
.
E
a
ch
m
eth
o
d
h
as
its
lim
itatio
n
s
,
in
clu
d
in
g
s
en
s
itiv
ity
to
am
b
ien
t
n
o
is
e,
s
u
b
ject
p
o
s
itio
n
co
n
s
tr
ain
ts
,
h
ig
h
s
en
s
itiv
ity
to
m
o
tio
n
ar
tifa
cts,
an
d
lig
h
tin
g
co
n
d
iti
o
n
s
[
1
7
]
.
T
h
er
m
al
im
ag
i
n
g
,
o
r
in
f
r
ar
ed
th
er
m
o
g
r
a
p
h
y
(
I
R
T
)
,
o
f
f
er
s
s
ig
n
if
ica
n
t
ad
v
an
tag
es
d
u
e
t
o
its
n
o
n
-
co
n
tact,
n
o
n
-
in
v
asiv
e,
a
n
d
n
o
n
-
r
a
d
iativ
e
n
atu
r
e
,
an
d
d
o
es
n
o
t
r
e
q
u
ir
e
lig
h
t,
m
a
k
in
g
it
u
s
ab
le
d
ay
an
d
n
ig
h
t
[
1
1
]
,
[
1
2
]
.
I
R
T
is
a
tech
n
o
lo
g
y
th
a
t
d
etec
ts
in
f
r
ar
ed
r
ad
iatio
n
e
m
itted
b
y
an
o
b
ject,
co
n
v
er
ts
it
in
to
tem
p
e
r
atu
r
e
v
alu
es,
an
d
g
en
er
ates
a
th
er
m
a
l
im
ag
e
r
e
p
r
esen
ti
n
g
t
h
e
tem
p
er
atu
r
e
d
is
tr
ib
u
tio
n
[
1
8
]
.
Sh
aik
h
et
a
l.
[
1
9
]
d
em
o
n
s
tr
ated
th
at
r
es
p
ir
atio
n
d
ata
o
b
tain
ed
v
ia
I
R
T
s
h
o
ws
n
o
s
ig
n
if
ican
t
d
if
f
er
e
n
ce
co
m
p
ar
ed
to
d
ata
f
r
o
m
r
esp
ir
a
to
r
y
in
d
u
ctan
ce
p
leth
y
s
m
o
g
r
a
p
h
y
,
h
ig
h
lig
h
tin
g
I
R
T
as a
n
ef
f
ec
tiv
e,
n
o
n
-
co
n
tac
t
m
eth
o
d
f
o
r
m
o
n
ito
r
in
g
h
u
m
an
r
esp
ir
atio
n
.
I
R
T
-
b
ased
b
r
ea
th
i
n
g
f
u
n
ctio
n
m
ea
s
u
r
em
en
t
r
e
lies
o
n
tem
p
e
r
atu
r
e
d
i
f
f
er
en
ce
s
o
b
s
er
v
e
d
in
th
e
n
asal
ar
ea
d
u
r
in
g
b
r
ea
th
in
g
cy
cles
[
1
9
]
.
Ab
b
as
et
a
l.
[
1
6
]
d
ev
elo
p
ed
an
alg
o
r
ith
m
to
m
o
n
ito
r
th
e
B
R
b
y
a
n
aly
zin
g
tem
p
er
atu
r
e
f
lu
ctu
atio
n
s
ar
o
u
n
d
th
e
n
o
s
tr
ils
[
1
6
]
.
L
ewis
et
a
l.
[
2
0
]
em
p
lo
y
ed
I
R
T
to
o
b
s
er
v
e
tem
p
er
at
u
r
e
v
ar
iatio
n
s
ac
r
o
s
s
th
e
n
o
s
tr
ils
,
ac
co
u
n
tin
g
f
o
r
d
if
f
e
r
en
t
b
r
ea
th
in
g
p
atter
n
s
,
in
clu
d
i
n
g
s
p
o
n
tan
eo
u
s
,
s
lo
w,
an
d
r
ap
id
b
r
ea
t
h
in
g
.
T
h
e
d
ata
c
o
llected
f
r
o
m
th
e
t
h
er
m
al
c
am
er
a
wer
e
p
r
im
ar
ily
o
b
tai
n
ed
u
n
d
er
o
p
tim
al
co
n
d
itio
n
s
,
ch
ar
a
cter
ized
b
y
m
in
im
al
h
ea
d
m
o
v
em
en
ts
an
d
n
o
r
m
al
b
r
ea
t
h
in
g
[
1
6
]
,
[
1
9
]
,
[
2
0
]
.
I
n
co
n
tr
ast,
th
is
s
tu
d
y
ev
alu
ates
th
e
ef
f
ec
tiv
en
ess
o
f
o
u
r
m
eth
o
d
in
m
o
r
e
ch
allen
g
in
g
s
ce
n
ar
io
s
,
s
u
ch
as
h
ea
d
m
o
v
em
en
ts
an
d
b
r
ea
th
in
g
d
is
o
r
d
er
s
.
W
e
ev
al
u
ated
th
e
r
o
b
u
s
tn
ess
o
f
o
u
r
a
p
p
r
o
ac
h
in
th
e
p
r
esen
ce
o
f
m
o
tio
n
ar
tifa
cts
an
d
ass
es
s
ed
its
ac
cu
r
ac
y
an
d
r
elia
b
ilit
y
ac
r
o
s
s
d
if
f
er
en
t
b
r
ea
th
in
g
p
atter
n
s
.
L
ewis
et
a
l.
[2
0]
s
ig
n
if
ica
n
tly
ad
v
an
ce
d
th
e
u
s
e
o
f
I
R
T
f
o
r
o
b
tain
in
g
th
e
B
R
b
y
tr
ac
k
in
g
t
h
e
n
o
s
tr
ils
with
a
Piecew
is
e
B
ez
ier
Vo
lu
m
e
Def
o
r
m
atio
n
m
o
d
el
,
wh
ile
J
in
Fei
an
d
I
o
an
n
is
Pav
lid
is
e
m
p
lo
y
ed
a
n
etwo
r
k
o
f
p
r
o
b
ab
ilis
tic
tr
ac
k
er
s
to
s
eg
m
en
t
an
d
tr
ac
k
th
e
n
o
s
tr
ils
[
7
]
.
Ho
wev
e
r
,
th
ese
m
eth
o
d
s
r
eq
u
ir
ed
m
an
u
al
s
elec
tio
n
o
f
th
e
r
eg
io
n
o
f
in
t
er
est
(
R
OI
)
in
th
e
in
itial
f
r
am
e
[
7
]
,
[
2
0
]
,
[
2
1
]
.
Mo
r
e
o
v
er
,
tr
ac
k
in
g
alg
o
r
ith
m
s
f
ac
ed
v
ar
io
u
s
ch
allen
g
es
,
s
u
ch
as
f
ailu
r
es
d
u
r
in
g
s
u
d
d
e
n
o
r
lar
g
e
h
ea
d
m
o
v
em
en
ts
o
r
wh
en
th
e
s
u
b
ject
o
p
en
ed
t
h
eir
m
o
u
th
,
wh
ich
o
f
t
en
ca
u
s
ed
th
e
b
r
ea
th
in
g
s
ig
n
al
to
h
av
e
ze
r
o
v
alu
es
[
1
9
]
,
[
2
0
]
.
T
o
ad
d
r
ess
th
ese
ch
allen
g
es,
th
is
s
tu
d
y
u
tili
ze
s
a
Haa
r
C
ascad
e
clas
s
if
ier
to
a
u
to
m
atica
lly
d
etec
t
an
d
tr
ac
k
th
e
n
o
s
e
r
eg
io
n
in
th
er
m
al
v
i
d
eo
,
co
m
b
in
ed
with
a
ca
n
n
y
e
d
g
e
d
etec
to
r
f
o
r
n
o
s
tr
il
d
etec
tio
n
to
en
h
a
n
ce
ac
cu
r
ac
y
.
An
in
ter
p
o
latio
n
alg
o
r
ith
m
was
also
ap
p
lied
to
p
r
ev
e
n
t
s
ig
n
al
lo
s
s
d
u
r
in
g
tr
ac
k
in
g
f
ailu
r
es,
wh
ich
wo
u
l
d
o
th
er
wis
e
r
esu
lt
in
ze
r
o
-
v
alu
e
s
ig
n
als.
T
h
is
in
ter
p
o
latio
n
m
et
h
o
d
r
e
p
air
s
th
e
ex
t
r
ac
ted
s
ig
n
a
l
s
,
r
ep
r
esen
tin
g
an
in
n
o
v
ativ
e
a
p
p
r
o
ac
h
th
at
h
as n
o
t b
ee
n
a
d
d
r
ess
ed
in
p
r
io
r
s
tu
d
ies.
Per
eir
a
et
a
l.
[
1
2
]
ap
p
lied
a
b
a
n
d
p
ass
B
u
tter
wo
r
th
f
ilter
to
en
h
an
ce
th
e
s
ig
n
al
-
to
-
n
o
is
e
r
atio
(
S
NR
)
o
f
th
e
b
r
ea
th
i
n
g
s
ig
n
al
.
Similar
ly
,
I
o
a
n
n
is
Pav
lid
is
em
p
l
o
y
ed
a
lo
wp
as
s
B
u
tter
wo
r
th
f
ilter
to
im
p
r
o
v
e
SNR
an
d
in
tr
o
d
u
ce
d
a
m
eth
o
d
f
o
r
ch
ar
ac
ter
izin
g
b
r
ea
th
in
g
p
atter
n
s
b
y
ca
lcu
latin
g
th
e
m
ea
n
d
y
n
a
m
ic
b
r
ea
th
in
g
s
ig
n
al
an
d
id
en
tify
i
n
g
b
r
ea
th
in
g
c
y
cles
u
d
in
g
ze
r
o
-
c
r
o
s
s
th
r
esh
o
ld
in
g
[
7
]
.
J
ag
ad
ev
a
n
d
Gir
i
m
ad
e
a
s
ig
n
if
ican
t
co
n
tr
ib
u
tio
n
in
class
if
y
in
g
th
e
b
r
ea
th
in
g
s
ig
n
al
u
s
in
g
m
a
ch
in
e
lear
n
in
g
b
y
u
s
in
g
a
k
-
n
ea
r
est
n
eig
h
b
o
u
r
(k
-
NN)
class
if
ier
to
d
eter
m
in
e
wh
eth
er
th
e
s
u
b
ject
ex
h
ib
it
n
o
r
m
al
o
r
a
b
n
o
r
m
al
r
esp
ir
atio
n
o
r
is
s
p
ec
if
ically
ex
p
er
ien
cin
g
B
r
ad
y
p
n
ea
o
r
T
a
ch
y
p
n
ea
[
2
]
.
I
n
th
is
s
tu
d
y
,
we
ap
p
lied
th
e
B
u
tter
wo
r
th
b
a
n
d
p
ass
f
ilter
to
r
ed
u
c
e
n
o
is
e
an
d
en
h
an
ce
th
e
SNR
o
f
th
e
o
b
tain
e
d
b
r
ea
th
in
g
s
ig
n
a
l.
Af
ter
t
h
at,
we
im
p
lem
en
ted
p
ea
k
d
etec
tio
n
t
o
au
to
m
atica
lly
id
en
tify
th
e
b
r
ea
th
in
g
cy
cles
in
th
e
f
ilter
ed
b
r
ea
th
in
g
s
ig
n
als
an
d
ca
lcu
l
at
e
th
e
b
r
ea
th
s
p
er
m
in
u
te
(
B
PM)
v
alu
e,
th
er
eb
y
o
v
er
co
m
i
n
g
th
e
lim
itatio
n
s
p
r
esen
t
in
p
r
io
r
s
tu
d
ies
[
7
]
,
[
1
6
]
,
[
1
9
]
,
[
2
0
]
,
wh
ich
n
ec
ess
itated
m
an
u
al
in
ter
v
en
t
io
n
f
o
r
th
e
d
eter
m
in
atio
n
o
f
B
PM.
Fu
th
er
m
o
r
e,
we
class
i
f
ied
th
e
b
r
ea
th
in
g
s
ig
n
als in
to
th
r
ee
ca
teg
o
r
ies:
b
r
ad
y
p
n
ea
,
n
o
r
m
al,
a
n
d
tach
y
p
n
ea
,
u
s
in
g
th
e
k
-
NN
alg
o
r
ith
m
.
T
h
is
s
tu
d
y
in
tr
o
d
u
ce
s
a
n
o
v
el
an
d
r
eliab
le
ap
p
r
o
ac
h
f
o
r
co
n
t
ac
tles
s
m
o
n
ito
r
in
g
o
f
BRs
u
s
i
n
g
th
er
m
a
l
im
ag
in
g
.
I
n
co
n
tr
ast to
o
th
er
tech
n
iq
u
es th
at
r
eq
u
ir
e
m
an
u
al
s
elec
tio
n
o
f
th
e
R
OI
[
7
]
,
[
2
0
]
,
[
2
1
]
,
th
is
ap
p
r
o
ac
h
au
to
m
atica
lly
d
etec
ts
th
e
n
o
s
e
in
th
e
in
itial
f
r
am
e.
W
e
also
u
s
e
a
ca
n
n
y
ed
g
e
d
etec
to
r
t
o
d
etec
t
n
o
s
tr
ils
to
m
ak
e
a
m
o
r
e
ac
cu
r
ate
an
d
a
p
p
lied
in
ter
p
o
lat
io
n
alg
o
r
ith
m
to
p
r
ev
en
t
th
e
ze
r
o
v
alu
e
o
f
b
r
ea
th
in
g
s
ig
n
al
ca
u
s
ed
b
y
m
is
s
in
g
R
OI
.
W
h
i
le
p
r
ev
io
u
s
r
esear
ch
v
alid
ate
d
th
eir
alg
o
r
ith
m
s
u
n
d
er
o
p
ti
m
al
co
n
d
itio
n
s
with
m
in
im
al
h
ea
d
m
o
v
em
e
n
ts
an
d
n
o
r
m
al
b
r
ea
t
h
in
g
[
1
6
]
,
[
1
9
]
,
[
2
0
]
,
we
ev
alu
ate
o
u
r
s
in
m
o
r
e
ch
all
en
g
in
g
s
itu
atio
n
s
,
s
u
ch
as
h
ea
d
m
o
v
e
m
en
ts
an
d
b
r
ea
t
h
in
g
d
is
o
r
d
e
r
s
.
Ad
d
itio
n
ally
,
we
e
m
p
lo
y
e
d
m
ac
h
in
e
lear
n
i
n
g
,
u
s
in
g
a
1
0
-
f
o
ld
c
r
o
s
s
-
v
alid
atio
n
k
-
NN
class
if
ier
,
to
class
if
y
b
r
ea
th
in
g
c
o
n
d
itio
n
s
an
d
d
et
er
m
in
e
wh
eth
er
t
h
e
p
er
s
o
n
h
as n
o
r
m
al
b
r
ea
th
in
g
o
r
co
n
d
i
tio
n
s
lik
e
b
r
a
d
y
p
n
ea
(
s
lo
w
b
r
ea
th
in
g
)
o
r
tach
y
p
n
ea
(
f
ast b
r
ea
th
in
g
)
.
T
h
is
s
y
s
tem
is
ex
p
ec
ted
to
y
ield
v
alu
ab
le
in
s
ig
h
ts
in
to
th
e
a
p
p
li
ca
tio
n
o
f
th
er
m
al
im
ag
in
g
f
o
r
B
R
d
etec
tio
n
an
d
p
r
esen
t a
p
r
o
m
is
in
g
n
o
n
-
co
n
ta
ct
alter
n
ativ
e
f
o
r
h
ea
lth
ca
r
e
p
r
o
f
ess
io
n
als
.
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:
2502
-
4
7
5
2
N
o
n
-
co
n
ta
ct
b
r
ea
th
in
g
r
a
te
m
o
n
ito
r
in
g
u
s
in
g
i
n
fr
a
r
ed
t
h
ermo
g
r
a
p
h
y
a
n
d
…
(
A
n
a
d
ya
G
h
in
a
S
a
ls
a
b
ila
)
671
2.
M
E
T
H
O
D
T
h
is
s
ec
tio
n
o
f
f
er
s
a
d
etailed
o
v
er
v
iew
o
f
th
e
s
eq
u
e
n
tial
s
tep
s
in
v
o
lv
ed
i
n
th
e
ef
f
ec
tiv
e
m
o
n
ito
r
in
g
o
f
B
R
,
as
illu
s
tr
ated
in
Fig
u
r
e
1
.
T
h
e
p
r
o
ce
s
s
b
eg
in
s
with
d
ata
ac
q
u
is
itio
n
u
s
in
g
an
in
f
r
ar
ed
th
er
m
al
ca
m
er
a
,
f
o
llo
wed
b
y
R
OI
d
etec
tio
n
an
d
tr
ac
k
in
g
.
Su
b
s
eq
u
en
t
s
tep
s
in
clu
d
e
R
OM
d
etec
tio
n
,
b
r
ea
th
in
g
s
ig
n
al
ex
tr
ac
tio
n
,
an
d
f
ilter
in
g
.
T
h
e
ex
tr
ac
ted
B
R
v
alu
es
ar
e
th
en
class
if
ied
in
to
b
r
ad
y
p
n
ea
,
n
o
r
m
al,
an
d
tach
y
p
n
ea
u
s
in
g
a
k
-
NN
class
if
ier
.
Fig
u
r
e
1
.
Ov
e
r
v
iew
o
f
th
e
s
y
s
tem
d
esig
n
2
.
1
.
Da
t
a
a
cquis
it
io
n
T
h
e
ex
p
e
r
im
en
ts
wer
e
co
n
d
u
c
ted
in
th
e
lab
o
r
ato
r
i
u
m
r
o
o
m
,
wh
er
e
th
e
tem
p
e
r
atu
r
e
was
co
n
tr
o
lled
at
2
4
°C
.
T
h
e
s
tu
d
y
in
v
o
lv
ed
ten
v
o
lu
n
teer
p
a
r
ticip
an
ts
,
co
m
p
r
is
in
g
m
ales
an
d
f
em
ales
ag
ed
1
8
–
2
5
y
ea
r
s
.
T
h
e
y
wer
e
s
ea
ted
co
m
f
o
r
tab
l
y
an
d
t
h
e
I
R
ca
m
er
a
co
n
n
ec
ted
to
a
l
ap
to
p
was
p
o
s
itio
n
ed
p
a
r
allel
to
th
eir
f
ac
es.
T
h
e
d
ata
ac
q
u
is
itio
n
p
r
o
c
ess
is
illu
s
tr
ated
in
Fig
u
r
e
2
,
s
h
o
win
g
Fig
u
r
e
2
(
a
)
th
e
th
er
m
al
im
ag
er
an
d
Fig
u
r
e
2
(
b
)
t
h
e
ex
p
er
im
en
tal
s
etu
p
.
T
h
e
th
e
r
m
al
im
ag
er
u
s
ed
was th
e
UT
i2
6
0
B
m
o
d
el
[
2
2
]
.
T
h
e
ca
m
er
a
was
p
lace
d
0
.
2
5
m
eter
s
f
r
o
m
th
e
s
u
b
ject,
f
o
c
u
s
in
g
ex
clu
s
iv
ely
o
n
th
e
f
ac
ial
ar
ea
.
Data
was
co
llected
u
n
d
er
th
r
ee
d
if
f
er
en
t
co
n
d
itio
n
s
:
(
1
)
th
e
s
u
b
ject
was
in
s
tr
u
cted
to
r
em
ain
s
till
an
d
b
r
ea
th
e
n
o
r
m
ally
,
(
2
)
th
e
s
u
b
ject
b
r
e
ath
ed
n
o
r
m
all
y
wh
ile
p
er
f
o
r
m
in
g
s
o
m
e
h
ea
d
m
o
v
em
en
ts
,
an
d
(
3
)
th
e
s
u
b
ject
s
im
u
lated
d
ee
p
,
s
lo
w
b
r
ea
th
in
g
(
b
r
a
d
y
p
n
ea
)
o
r
s
h
allo
w,
r
ap
i
d
b
r
ea
th
in
g
(
tach
y
p
n
ea
)
.
Vid
e
o
s
wer
e
r
ec
o
r
d
e
d
at
a
f
r
am
e
r
ate
o
f
1
0
Hz
f
o
r
6
0
s
ec
o
n
d
s
p
er
c
o
n
d
itio
n
.
(
a)
(
b
)
Fig
u
r
e
2
.
Data
ac
q
u
is
itio
n
(
a)
t
h
er
m
al
im
ag
er
u
s
ed
an
d
(
b
)
ex
p
er
im
en
tal
s
etu
p
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
39
,
No
.
1
,
J
u
ly
20
25
:
669
-
6
8
0
672
2
.
2
.
Det
ec
t
io
n a
nd
t
ra
c
k
ing
o
f
RO
I
T
h
is
ap
p
r
o
ac
h
r
elies
o
n
th
e
tem
p
er
atu
r
e
ch
an
g
es
ar
o
u
n
d
th
e
n
o
s
tr
ils
d
u
r
in
g
th
e
b
r
ea
t
h
in
g
c
y
cle
(
in
s
p
ir
atio
n
an
d
ex
p
ir
atio
n
)
.
As
co
o
l
air
is
in
s
p
ir
ed
f
r
o
m
t
h
e
en
v
ir
o
n
m
e
n
t
an
d
war
m
air
is
ex
p
ir
ed
f
r
o
m
th
e
lu
n
g
s
,
I
R
T
ca
n
p
r
ec
is
ely
d
etec
t
th
ese
tem
p
er
atu
r
e
v
ar
iatio
n
s
,
as
s
h
o
wn
in
Fig
u
r
e
3
.
T
o
ca
lcu
late
th
e
B
R
f
r
o
m
th
e
th
er
m
al
v
id
e
o
,
th
e
n
o
s
e
(
R
OI
)
m
u
s
t b
e
au
t
o
m
atica
lly
d
et
ec
ted
in
th
e
in
itial f
r
am
e.
T
h
e
f
ir
s
t
s
tep
was
f
ac
e
s
eg
m
e
n
tatio
n
u
s
in
g
th
e
m
u
lti
-
lev
el
Ots
u
’
s
m
eth
o
d
[
2
3
]
.
I
n
1
9
7
9
,
No
b
u
y
u
k
i
Ots
u
[
2
4
]
in
tr
o
d
u
ce
d
a
n
im
a
g
e
th
r
esh
o
l
d
in
g
tech
n
iq
u
e
b
ased
o
n
cl
u
s
ter
in
g
,
allo
win
g
th
e
d
iv
is
io
n
o
f
a
n
im
a
g
e
in
to
two
ca
teg
o
r
ies:
b
ac
k
g
r
o
u
n
d
an
d
f
o
r
eg
r
o
u
n
d
.
T
h
is
alg
o
r
ith
m
em
p
lo
y
s
d
is
cr
im
in
an
t
an
aly
s
is
to
d
eter
m
in
e
th
e
o
p
tim
al
th
r
esh
o
ld
v
alu
e
(
T*
)
b
y
m
in
im
izin
g
w
ith
in
-
cl
a
s
s
va
r
ia
n
ce
(
2
)
o
r
,
alter
n
ativ
ely
,
m
ax
im
izin
g
b
etw
ee
n
-
cla
s
s
va
r
ia
n
ce
(
2
)
,
as d
ef
in
ed
b
y
(
1
)
,
∗
=
1
≤
<
{
2
(
)
=
2
(
)
−
2
(
)
}
,
(
1
)
wh
er
e
2
d
en
o
tes
th
e
to
tal
v
ar
ian
ce
,
T
r
ep
r
esen
ts
th
e
th
r
esh
o
ld
v
alu
e,
an
d
L
co
r
r
esp
o
n
d
s
to
th
e
g
r
ay
lev
els.
T
h
is
eq
u
atio
n
ca
n
b
e
f
u
r
th
er
elab
o
r
ated
in
t
o
(
2
)
,
2
(
)
=
1
(
)
[
1
(
)
−
]
2
+
2
(
)
[
2
(
)
−
]
2
.
(
2
)
h
er
e,
r
ep
r
esen
ts
th
e
p
r
o
b
ab
il
ities
o
f
th
e
two
clas
s
es
(
b
ac
k
g
r
o
u
n
d
an
d
f
o
r
e
g
r
o
u
n
d
)
,
µ
d
e
n
o
tes
th
e
m
ea
n
in
ten
s
ity
o
f
th
e
o
r
ig
i
n
al
im
ag
e
,
an
d
µ
r
ef
er
s
to
th
e
m
ea
n
in
ten
s
ity
o
f
ea
ch
r
esp
ec
tiv
e
class
.
Sp
ec
if
ically
,
1
an
d
2
co
r
r
esp
o
n
d
t
o
class
es C
1
an
d
C
2
,
r
esp
ec
ti
v
ely
.
Mu
lti
-
lev
el
Ots
u
’
s
m
eth
o
d
was
ap
p
lied
f
o
r
f
ac
e
s
eg
m
e
n
tatio
n
to
ef
f
ec
tiv
ely
s
ep
a
r
ate
th
e
s
u
b
ject
’
s
f
ac
e
f
r
o
m
th
e
b
ac
k
g
r
o
u
n
d
,
m
in
im
izin
g
b
a
ck
g
r
o
u
n
d
n
o
is
e
th
at
ca
n
af
f
ec
t
d
etec
tio
n
a
cc
u
r
ac
y
i
n
th
er
m
al
im
ag
in
g
.
T
h
is
s
tep
en
s
u
r
es
th
at
o
n
ly
t
h
e
lar
g
est
r
e
g
io
n
in
t
h
e
b
in
ar
y
im
a
g
e
co
r
r
esp
o
n
d
s
to
th
e
f
ac
e.
Af
ter
s
eg
m
en
tatio
n
,
th
e
Haa
r
C
ascad
e
class
if
ier
was
u
s
ed
to
d
etec
t
th
e
n
o
s
e
r
e
g
io
n
with
in
th
e
s
e
g
m
en
ted
f
ac
e.
Haa
r
C
ascad
e
is
well
-
k
n
o
wn
f
o
r
its
ef
f
icien
cy
in
d
etec
tin
g
f
ac
ial
f
ea
tu
r
es
in
d
ig
ital
im
ag
es,
ev
e
n
wh
en
o
b
jects
ar
e
at
d
if
f
er
en
t
s
ca
les
an
d
o
r
ien
ta
tio
n
s
,
m
ak
in
g
it
s
u
itab
le
f
o
r
th
is
task
[
2
5
]
.
Pre
v
io
u
s
s
tu
d
ie
s
,
s
u
ch
as
th
o
s
e
b
y
Setjo
an
d
Far
id
ah
[
2
6
]
,
h
av
e
also
d
em
o
n
s
tr
ated
th
e
ef
f
ec
tiv
en
ess
o
f
th
is
m
eth
o
d
in
th
er
m
al
im
ag
in
g
.
B
y
co
m
b
in
in
g
Ots
u
’
s
s
eg
m
e
n
tat
io
n
an
d
Haa
r
C
ascad
e,
o
u
r
ap
p
r
o
ac
h
aim
ed
t
o
im
p
r
o
v
e
th
e
ac
cu
r
ac
y
an
d
r
eliab
ilit
y
o
f
n
o
s
e
d
etec
tio
n
in
th
er
m
al
v
id
eo
s
.
2
.
3
.
I
dentif
ica
t
io
n o
f
re
g
io
n
o
f
m
e
a
s
urem
ent
I
n
o
r
d
er
to
im
p
r
o
v
e
th
e
SNR
,
a
s
ec
o
n
d
an
d
s
m
aller
R
OI
th
at
f
o
cu
s
es
o
n
th
e
ar
ea
a
r
o
u
n
d
t
h
e
n
o
s
tr
ils
,
n
am
ely
th
e
R
eg
io
n
o
f
Me
asu
r
em
en
t
(
R
OM
)
,
is
d
eter
m
i
n
ed
.
R
OM
is
id
en
tifie
d
f
o
r
ea
ch
tr
ac
k
e
d
R
OI
b
y
co
n
s
id
er
in
g
th
e
n
o
s
e
ed
g
es
an
d
is
f
o
u
n
d
u
s
in
g
th
e
ca
n
n
y
ed
g
e
d
etec
to
r
[
2
6
]
.
T
h
e
n
o
s
tr
il
r
eg
io
n
,
wh
er
e
tem
p
er
atu
r
e
f
lu
ct
u
atio
n
s
o
cc
u
r
d
u
r
in
g
b
r
ea
th
in
g
,
was
th
en
s
eg
m
en
ted
.
T
h
ese
tem
p
er
atu
r
e
v
alu
es
wer
e
tr
ac
k
ed
o
v
er
tim
e,
allo
win
g
u
s
to
ex
tr
ac
t
th
e
b
r
ea
th
in
g
s
ig
n
al
b
ased
o
n
th
e
tem
p
er
atu
r
e
c
h
an
g
es
ass
o
ciate
d
with
in
s
p
ir
atio
n
an
d
ex
p
ir
atio
n
.
2
.
4
.
E
x
t
r
a
ct
io
n o
f
brea
t
hin
g
s
ig
na
l a
nd
s
ig
na
l
pro
ce
s
s
ing
T
h
e
b
r
ea
th
in
g
s
ig
n
al
ex
tr
ac
tio
n
ac
co
r
d
i
n
g
to
th
e
av
er
a
g
e
tem
p
er
atu
r
e
v
al
u
e
̅
(
)
o
f
th
e
R
OM
f
o
r
ea
ch
f
r
am
e
is
g
iv
e
n
b
y
(
3
)
,
̅
(
)
=
1
∑
∑
(
,
,
)
−
1
=
0
−
1
=
0
,
(
3
)
wh
er
e
(
,
,
)
r
ep
r
esen
ts
th
e
tem
p
er
atu
r
e
at
p
ix
el
(
,
)
at
tim
e
t,
m
is
th
e
wid
th
o
f
th
e
R
OM
,
an
d
n
is
its
len
g
th
.
In
(
3
)
d
escr
ib
es
th
e
p
r
o
ce
s
s
o
f
ex
tr
ac
tin
g
th
e
b
r
e
ath
in
g
s
ig
n
al
f
r
o
m
th
e
r
m
al
i
m
ag
es
b
y
u
s
in
g
th
e
av
er
ag
e
tem
p
e
r
atu
r
e
in
th
e
R
OM
f
o
r
ea
ch
im
ag
e
f
r
am
e.
T
h
e
av
er
ag
e
tem
p
e
r
atu
r
e
̅
(
)
at
tim
e
t
is
ca
lcu
lated
b
y
s
u
m
m
in
g
th
e
tem
p
e
r
atu
r
es
at
ea
ch
p
ix
el
(
,
,
)
with
in
th
e
R
OM
an
d
d
iv
id
in
g
b
y
th
e
to
tal
n
u
m
b
er
o
f
p
ix
els (
).
T
h
e
ex
tr
ac
ted
b
r
ea
t
h
in
g
s
ig
n
a
l
u
n
d
er
g
o
es
p
o
s
t
-
p
r
o
ce
s
s
in
g
t
o
im
p
r
o
v
e
its
q
u
ality
an
d
r
ed
u
ce
n
o
is
e.
Du
e
to
d
if
f
icu
lties
in
tr
ac
k
in
g
th
e
R
OI
i
n
th
e
r
m
al
v
id
eo
,
n
o
t
all
ac
q
u
ir
ed
b
r
ea
t
h
in
g
s
ig
n
als
d
is
p
lay
o
p
tim
al
m
o
r
p
h
o
lo
g
y
.
W
h
en
th
e
n
o
s
tr
i
ls
ar
e
u
n
d
etec
ted
,
th
e
s
ig
n
al
m
ay
r
eg
is
ter
as
ze
r
o
,
lead
in
g
to
d
is
co
n
tin
u
ities
.
T
o
r
eso
lv
e
th
is
is
s
u
e,
a
n
in
ter
p
o
latio
n
alg
o
r
ith
m
r
ep
lace
s
ze
r
o
v
alu
es b
y
av
e
r
ag
in
g
th
e
im
m
ed
iate
n
eig
h
b
o
r
in
g
v
alu
es,
ef
f
ec
tiv
ely
r
esto
r
in
g
c
o
n
tin
u
ity
in
th
e
s
ig
n
al.
Sin
ce
th
e
b
r
ea
th
in
g
s
ig
n
al
ty
p
ically
h
as
a
lo
w
SNR
-
af
f
ec
ted
b
y
f
ac
to
r
s
s
u
c
h
as
em
is
s
iv
ity
v
ar
iatio
n
s
,
ca
m
er
a
r
esp
o
n
s
e,
tem
p
er
atu
r
e
ca
lib
r
atio
n
,
atm
o
s
p
h
er
ic
co
n
d
itio
n
s
,
an
d
en
v
ir
o
n
m
en
ta
l
r
ef
lectio
n
s
-
a
s
ec
o
n
d
-
o
r
d
e
r
B
u
tter
wo
r
th
b
a
n
d
-
p
ass
f
ilter
is
ap
p
lied
,
with
3
d
B
cu
to
f
f
f
r
eq
u
e
n
cies
b
etwe
en
0
.
1
Hz
an
d
0
.
5
Hz,
to
is
o
late
th
e
r
esp
ir
ato
r
y
s
ig
n
al
r
an
g
e
an
d
en
h
an
ce
cla
r
ity
b
y
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:
2502
-
4
7
5
2
N
o
n
-
co
n
ta
ct
b
r
ea
th
in
g
r
a
te
m
o
n
ito
r
in
g
u
s
in
g
i
n
fr
a
r
ed
t
h
ermo
g
r
a
p
h
y
a
n
d
…
(
A
n
a
d
ya
G
h
in
a
S
a
ls
a
b
ila
)
673
atten
u
atin
g
b
ac
k
g
r
o
u
n
d
n
o
is
e
.
Af
ter
f
ilter
in
g
,
p
ea
k
d
etec
ti
o
n
is
p
e
r
f
o
r
m
ed
to
id
e
n
tify
th
e
b
r
ea
t
h
in
g
cy
cles
with
in
th
e
s
ig
n
al,
wh
ich
e
n
ab
l
es th
e
ca
lcu
latio
n
o
f
B
R
in
s
u
b
s
eq
u
en
t step
s
.
2
.
5
.
B
re
a
t
hin
g
ra
t
e
ca
lcula
t
i
o
n
T
h
e
B
R
is
ca
lcu
lated
f
r
o
m
t
h
e
f
ilter
ed
b
r
ea
th
i
n
g
s
ig
n
al
b
y
co
u
n
tin
g
th
e
n
u
m
b
e
r
o
f
p
e
ak
s
in
th
e
s
ig
n
al
p
r
o
f
ile,
wh
er
e
th
e
p
ea
k
s
co
r
r
esp
o
n
d
to
e
x
p
ir
atio
n
s
an
d
th
e
cr
ests
in
d
icate
in
s
p
ir
atio
n
s
.
A
co
m
p
lete
b
r
ea
th
cy
cle
co
n
s
is
ts
o
f
o
n
e
p
ea
k
an
d
o
n
e
cr
est,
an
d
t
h
e
to
tal
n
u
m
b
er
o
f
th
ese
cy
cles
in
a
m
in
u
te
g
iv
es
th
e
B
R
.
T
o
ev
alu
ate
th
e
ac
cu
r
ac
y
o
f
th
e
d
etec
ted
B
R
in
c
o
m
p
ar
i
s
o
n
to
th
e
p
h
o
to
p
leth
y
s
m
o
g
r
a
p
h
y
(
PP
G)
g
r
o
u
n
d
tr
u
th
,
th
e
c
o
m
p
lem
e
n
t
o
f
th
e
ab
s
o
lu
te
n
o
r
m
alize
d
d
i
f
f
er
e
n
ce
(
C
AND)
in
d
ex
is
co
m
p
u
ted
,
with
a
h
ig
h
er
C
AND
v
alu
e
s
ig
n
if
y
in
g
b
etter
d
etec
tio
n
o
f
v
ital sig
n
s
.
T
h
e
C
AND
v
alu
e
is
d
eter
m
in
ed
u
s
in
g
(
4
)
:
=
1
−
|
−
|
,
(
4
)
wh
er
e
r
ep
r
esen
ts
th
e
ac
tu
al
B
R
v
alu
es
o
b
tain
ed
f
r
o
m
PP
G
an
d
r
ep
r
esen
ts
th
e
r
esu
lt
o
b
tain
ed
u
s
in
g
th
e
th
er
m
al
im
ag
in
g
-
b
ased
B
R
d
etec
tio
n
s
y
s
tem
.
2
.
6
.
Cla
s
s
if
ica
t
io
n us
ing
k
-
NN
T
h
e
k
-
NN
class
if
ier
,
a
n
o
n
-
li
n
ea
r
s
u
p
e
r
v
is
ed
lear
n
in
g
m
et
h
o
d
,
ca
teg
o
r
izes
b
r
ea
th
in
g
s
i
g
n
als
in
to
tach
y
p
n
ea
,
n
o
r
m
al,
an
d
b
r
a
d
y
p
n
ea
with
o
u
t
ass
u
m
in
g
d
at
a
d
is
tr
ib
u
tio
n
.
Usi
n
g
m
ajo
r
it
y
v
o
tin
g
am
o
n
g
its
k
-
NN
,
it
ass
ig
n
s
u
n
k
n
o
wn
at
tr
ib
u
tes
to
th
e
d
o
m
i
n
an
t
clas
s
[
2
7
]
.
T
h
e
f
o
r
m
u
latio
n
o
f
th
is
alg
o
r
ith
m
in
th
e
tr
ain
in
g
p
h
ase
is
d
ef
in
ed
b
y
(
5
)
:
=
(
)
,
(
5
)
w
h
e
r
e
i
s
a
v
e
c
t
o
r
c
o
n
t
a
i
n
i
n
g
t
h
e
e
x
t
r
a
c
t
e
d
f
e
a
t
u
r
e
s
,
a
n
d
r
e
p
r
e
s
e
n
t
s
t
h
e
c
l
a
s
s
(
N
o
r
m
a
l
,
T
a
c
h
y
p
n
e
a
,
o
r
B
r
a
d
y
p
n
e
a
)
t
h
a
t
b
e
l
o
n
g
s
t
o
.
I
n
t
h
e
t
e
s
t
i
n
g
p
h
a
s
e
,
t
h
e
c
l
a
s
s
i
f
i
e
r
a
s
s
i
g
n
s
c
l
a
s
s
e
s
t
o
n
e
w
i
n
s
t
a
n
c
e
s
a
c
c
o
r
d
i
n
g
t
o
(
6
)
:
=
(
)
,
(
6
)
wh
er
e
r
ep
r
es
en
ts
th
e
v
ec
to
r
o
f
q
u
er
y
f
ea
tu
r
es,
a
n
d
is
t
h
e
p
r
e
d
icted
class
(
No
r
m
al,
T
ac
h
y
p
n
ea
,
o
r
B
r
ad
y
p
n
ea
)
f
o
r
.
T
h
e
k
in
k
-
NN
r
ef
er
s
to
t
h
e
n
u
m
b
er
o
f
n
ea
r
est
n
eig
h
b
o
r
s
u
s
ed
t
o
class
if
y
a
test
s
am
p
le.
C
h
o
o
s
in
g
th
e
r
ig
h
t
v
alu
e
f
o
r
k
is
cr
u
cial,
as
i
t
s
ig
n
if
ic
an
tly
im
p
ac
ts
th
e
p
er
f
o
r
m
an
ce
o
f
t
h
e
k
-
NN
class
if
ier
.
T
h
e
g
o
al
is
to
f
i
n
d
a
b
alan
ce
b
etwe
en
o
v
er
f
itti
n
g
an
d
u
n
d
e
r
f
i
ttin
g
.
A
to
tal
o
f
4
1
6
6
0
-
s
ec
o
n
d
b
r
ea
th
in
g
s
ig
n
als
wer
e
s
o
u
r
ce
d
f
r
o
m
th
e
B
I
DM
C
PP
G
an
d
r
esp
ir
atio
n
d
ataset
[
2
8
]
an
d
an
SQLite
-
d
r
iv
en
d
atab
ase
[
2
9
]
f
o
r
tr
ain
i
n
g
th
e
k
-
NN
class
if
ier
,
co
m
p
r
is
in
g
9
0
b
r
ad
y
p
n
ea
s
ig
n
als,
2
0
0
n
o
r
m
al
b
r
ea
th
in
g
s
ig
n
als,
an
d
1
2
6
tach
y
p
n
ea
s
ig
n
als.
T
h
e
ex
tr
ac
ted
f
ea
tu
r
es
f
r
o
m
th
ese
b
r
ea
th
in
g
s
ig
n
als
in
clu
d
ed
B
PM
an
d
th
e
co
u
n
t
o
f
n
o
r
m
al
an
d
ab
n
o
r
m
al
b
r
ea
th
s
with
in
ea
ch
s
ig
n
al,
wh
ich
wer
e
th
en
in
p
u
t
in
to
th
e
k
-
NN
class
if
ier
.
T
h
e
d
ataset,
co
n
tain
in
g
b
o
th
n
o
r
m
al
an
d
ab
n
o
r
m
al
b
r
ea
th
in
g
s
ig
n
als,
is
m
ath
em
atica
lly
r
ep
r
esen
ted
as sh
o
wn
in
(
7
)
:
=
{
(
,
)
=
1
|
∈
ℝ
,
∈
{
,
ℎ
,
}
}
,
(
7
)
wh
er
e
r
ep
r
esen
ts
th
e
d
ataset
co
m
p
r
is
in
g
o
f
v
ec
to
r
s
an
d
,
wh
er
ein
co
n
tain
s
th
e
B
PM,
n
u
m
b
er
o
f
n
o
r
m
al
an
d
ab
n
o
r
m
al
b
r
ea
th
c
y
cles in
ea
ch
s
ig
n
al,
an
d
id
en
tifie
s
th
e
class
to
wh
ich
b
elo
n
g
s
.
T
h
e
d
ataset
was
in
itially
s
p
lit
7
:3
f
o
r
tr
ain
i
n
g
a
n
d
test
in
g
.
T
h
e
tr
ain
in
g
d
ataset
was
f
u
r
th
er
d
iv
id
e
d
in
to
a
tr
ain
in
g
s
et
an
d
a
v
ali
d
atio
n
s
et
u
s
in
g
th
e
cr
o
s
s
-
v
a
lid
atio
n
m
eth
o
d
.
T
h
e
tr
ain
in
g
s
et
co
n
tain
s
d
ata
s
am
p
les
u
s
ed
f
o
r
b
u
ild
in
g
th
e
m
o
d
el,
wh
ile
t
h
e
v
al
id
atio
n
s
et
h
o
ld
s
b
ac
k
s
am
p
les
to
e
v
alu
ate
th
e
m
o
d
el
’
s
p
er
f
o
r
m
an
ce
.
C
r
o
s
s
-
v
alid
atio
n
,
a
s
tatis
tical
m
eth
o
d
to
ass
ess
a
m
ac
h
i
n
e
lear
n
i
n
g
m
o
d
el
’
s
a
cc
u
r
ac
y
o
n
u
n
s
ee
n
d
ata,
ty
p
ically
in
v
o
lv
es th
e
f
o
l
lo
win
g
s
tep
s
:
a)
R
an
d
o
m
ly
s
h
u
f
f
le
th
e
d
ataset.
b)
Sp
lit th
e
d
ataset
in
to
n
g
r
o
u
p
s
,
co
m
m
o
n
ly
5
o
r
1
0
.
c)
E
ac
h
s
am
p
le
is
u
s
ed
o
n
ce
an
d
f
o
r
m
o
d
el
tr
ain
in
g
n
-
1
tim
es in
th
e
v
alid
atio
n
s
et.
I
n
th
is
s
t
u
d
y
,
n
w
as
s
et
to
1
0
.
T
h
e
t
r
ai
n
i
n
g
d
at
a
was
r
a
n
d
o
m
l
y
d
iv
id
e
d
i
n
t
o
1
0
f
o
ld
s
o
f
a
p
p
r
o
x
im
ate
ly
eq
u
a
l
s
iz
e.
T
h
e
f
ir
s
t
f
o
l
d
was
u
s
e
d
as
t
h
e
v
ali
d
at
i
o
n
s
et,
w
h
i
l
e
th
e
m
o
d
el
w
as
t
r
ai
n
ed
o
n
t
h
e
r
e
m
ai
n
i
n
g
9
f
o
l
d
s
.
T
h
is
1
0
-
f
o
ld
c
r
o
s
s
-
v
a
li
d
at
io
n
p
r
o
ce
s
s
g
e
n
e
r
at
ed
1
0
r
es
u
lts
,
wi
th
th
e
f
i
n
a
l r
es
u
lt
b
ei
n
g
t
h
e
ir
a
v
e
r
a
g
e
.
T
h
e
test
in
g
d
at
ase
t,
co
n
s
is
ti
n
g
o
f
b
r
e
at
h
i
n
g
s
i
g
n
als
,
was
u
s
e
d
t
o
ev
al
u
a
te
t
h
e
f
i
n
al
m
o
d
el
’
s
p
e
r
f
o
r
m
a
n
c
e
a
n
d
was
k
e
p
t
s
ep
ar
ate
u
n
til
t
h
e
m
o
d
e
l w
as
f
u
ll
y
d
e
v
el
o
p
e
d
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
39
,
No
.
1
,
J
u
ly
20
25
:
669
-
6
8
0
674
T
h
e
r
o
b
u
s
t
n
ess
an
d
e
f
f
ec
ti
v
e
n
ess
o
f
t
h
e
k
-
NN
cl
ass
if
ie
r
wer
e
ass
ess
ed
b
y
ca
l
cu
lat
in
g
its
t
r
a
i
n
i
n
g
,
v
al
id
ati
o
n
,
an
d
tes
ti
n
g
ac
c
u
r
a
c
ies.
F
u
r
th
e
r
m
o
r
e
,
p
e
r
f
o
r
m
a
n
c
e
m
et
r
ics
s
u
c
h
as
s
e
n
s
it
iv
it
y
,
s
p
ec
i
f
ic
it
y
,
p
r
ec
is
i
o
n
,
an
d
F
-
m
ea
s
u
r
e
we
r
e
ca
lc
u
la
t
ed
f
o
r
e
ac
h
class
in
d
i
v
id
u
a
ll
y
.
T
h
e
m
at
h
e
m
at
ica
l
e
x
p
r
ess
i
o
n
s
u
s
e
d
f
o
r
th
ese
ca
l
cu
lat
io
n
s
a
r
e
p
r
o
v
i
d
e
d
in
(
8
)
to
(
1
1
)
,
=
+
,
(
8
)
=
+
,
(
9
)
=
+
,
(
1
0
)
−
=
2
×
×
+
,
(
1
1
)
wh
e
r
e
tr
u
e
p
o
s
i
ti
v
e
(
T
P
)
r
e
f
e
r
s
t
o
w
h
en
s
u
b
j
ec
ts
w
it
h
n
o
r
m
al
b
r
ea
t
h
i
n
g
w
er
e
c
o
r
r
ec
t
ly
cl
ass
if
ie
d
as
n
o
r
m
a
l,
f
als
e
p
o
s
i
ti
v
e
(
FP
)
r
e
f
e
r
s
t
o
w
h
e
n
s
u
b
j
ec
ts
wit
h
n
o
r
m
al
b
r
e
at
h
i
n
g
w
er
e
w
r
o
n
g
ly
class
i
f
i
e
d
as
tac
h
y
p
n
ea
/
b
r
a
d
y
p
n
e
a,
t
r
u
e
n
e
g
at
iv
e
(
T
N)
r
ef
er
s
to
w
h
e
n
n
o
r
m
al
s
u
b
j
ec
ts
we
r
e
c
o
r
r
ec
t
ly
class
if
ie
d
as
n
o
t
h
a
v
i
n
g
t
ac
h
y
p
n
e
a/
b
r
a
d
y
p
n
e
a,
a
n
d
f
alse
n
e
g
at
iv
e
(
FN
)
r
e
f
e
r
s
t
o
w
h
e
n
u
n
h
ea
lt
h
y
s
u
b
j
ec
ts
(
tac
h
y
p
n
e
a/
b
r
a
d
y
p
n
e
a)
wer
e
wr
o
n
g
ly
c
lass
i
f
i
e
d
as
h
a
v
in
g
n
o
r
m
al
b
r
e
at
h
i
n
g
.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
is
s
ec
t
io
n
p
r
o
v
i
d
es
a
s
u
m
m
a
r
y
o
f
all
t
h
e
e
x
p
e
r
i
m
e
n
t
al
a
n
d
n
u
m
er
ic
al
test
s
p
e
r
f
o
r
m
ed
.
T
h
e
I
R
ca
m
e
r
a
c
ap
tu
r
e
d
t
h
e
t
em
p
er
at
u
r
e
c
h
a
n
g
es
ar
o
u
n
d
t
h
e
n
o
s
t
r
ils
d
u
r
i
n
g
b
r
ea
t
h
i
n
g
.
T
h
e
f
l
u
ct
u
at
i
o
n
s
in
t
em
p
er
at
u
r
e
ca
u
s
e
d
b
y
in
s
p
i
r
a
ti
o
n
a
n
d
e
x
p
ir
a
ti
o
n
ar
e
il
lu
s
tr
ate
d
in
F
ig
u
r
es
3
(
a
)
a
n
d
3
(
b
)
,
r
es
p
ec
t
iv
el
y
.
T
h
e
Ha
ar
C
asc
ad
e
alg
o
r
it
h
m
w
as
i
m
p
le
m
e
n
te
d
t
o
a
u
t
o
m
at
e
t
h
e
n
asa
l
R
OI
d
et
ec
ti
o
n
a
n
d
t
r
ac
k
i
n
g
i
n
t
h
e
s
u
b
ject
’
s
t
h
er
m
a
l
v
i
d
e
o
.
On
c
e
th
e
n
as
al
R
OI
was
d
et
ec
ted
,
th
e
ca
n
n
y
e
d
g
e
d
et
ec
t
o
r
was
em
p
l
o
y
e
d
to
i
d
e
n
ti
f
y
th
e
R
OM
.
T
h
e
R
OM
,
a
s
ec
o
n
d
ar
y
R
OI
wi
th
in
t
h
e
n
a
s
al
R
O
I
,
f
o
c
u
s
es
o
n
t
h
e
n
o
s
t
r
il
t
o
en
h
an
ce
t
h
e
a
cc
u
r
ac
y
o
f
b
r
ea
t
h
in
g
s
i
g
n
al
ex
t
r
ac
ti
o
n
.
Fi
g
u
r
e
4
p
r
es
en
ts
e
x
am
p
l
es
o
f
t
h
e
d
ete
ct
ed
R
OI
a
n
d
R
OM
,
as
well
as
t
h
e
s
y
s
t
em
’
s
t
r
a
c
k
i
n
g
p
e
r
f
o
r
m
a
n
c
e
u
n
d
er
v
a
r
i
o
u
s
h
e
a
d
m
o
v
em
e
n
ts
.
Sp
ec
if
ically
,
Fig
u
r
e
4
(
a)
s
h
o
ws
an
ex
am
p
le
o
f
th
e
d
e
tecte
d
R
OI
an
d
R
OM
o
n
th
e
f
ac
e.
Fig
u
r
es
4
(
b
)
-
4
(
d
)
d
em
o
n
s
tr
ate
th
e
s
y
s
tem
’
s
ab
ilit
y
to
tr
ac
k
th
e
R
OI
an
d
R
OM
u
n
d
er
v
a
r
io
u
s
h
ea
d
m
o
v
em
en
ts
.
I
n
Fig
u
r
e
4
(
b
)
,
a
cc
u
r
ate
tr
ac
k
in
g
is
o
b
s
er
v
ed
wh
en
th
e
s
u
b
ject
’
s
h
ea
d
is
in
a
n
eu
tr
al
p
o
s
itio
n
.
I
n
Fig
u
r
e
4
(
c)
,
th
e
s
y
s
tem
s
u
cc
ess
f
u
lly
ad
ju
s
ts
an
d
co
n
tin
u
es
tr
ac
k
in
g
d
esp
ite
an
u
p
war
d
m
o
v
em
en
t.
Fig
u
r
e
4
(
d
)
s
h
o
ws
th
e
s
y
s
tem
m
ain
tain
in
g
f
o
c
u
s
o
n
th
e
n
o
s
e
ev
e
n
d
u
r
in
g
a
h
ea
d
tilt
,
d
em
o
n
s
tr
atin
g
r
o
b
u
s
tn
ess
in
ch
a
llen
g
in
g
o
r
ien
tatio
n
s
.
T
h
e
s
e
r
esu
lts
h
ig
h
lig
h
t
th
e
s
y
s
te
m
’
s
ad
ap
tab
ilit
y
to
h
ea
d
m
o
v
em
en
ts
,
en
s
u
r
in
g
r
eliab
le
d
etec
tio
n
an
d
tr
ac
k
in
g
o
f
b
r
ea
th
in
g
s
ig
n
als,
wh
ich
is
ess
en
tia
l
f
o
r
ac
cu
r
ate
n
o
n
-
co
n
tact
BR
m
o
n
ito
r
in
g
.
T
h
ese
f
in
d
in
g
s
d
ir
ec
tly
ad
d
r
es
s
g
ap
s
id
en
t
if
ied
in
p
r
ev
io
u
s
r
esear
ch
.
Prio
r
s
tu
d
ies
[
7
]
-
[
2
1
]
,
r
eq
u
i
r
ed
m
an
u
al
s
elec
tio
n
o
f
th
e
R
OI
i
n
th
e
in
itial
f
r
a
m
e
an
d
f
ac
e
d
c
h
allen
g
es
d
u
r
i
n
g
lar
g
e
o
r
ab
r
u
p
t
h
ea
d
m
o
v
em
e
n
ts
,
o
f
ten
r
esu
ltin
g
in
ze
r
o
-
v
al
u
e
b
r
ea
th
in
g
s
ig
n
als.
Mo
r
e
o
v
er
,
tr
ac
k
in
g
alg
o
r
ith
m
s
f
r
o
m
ea
r
l
ier
wo
r
k
s
s
tr
u
g
g
led
with
m
o
tio
n
a
r
tifa
cts,
wh
ich
co
m
p
r
o
m
is
ed
th
e
c
o
n
tin
u
ity
a
n
d
r
eliab
ilit
y
o
f
th
e
b
r
ea
t
h
in
g
s
ig
n
al.
I
n
co
n
tr
ast,
th
is
s
tu
d
y
im
p
lem
en
ts
a
f
u
lly
au
to
m
ated
a
p
p
r
o
ac
h
u
s
in
g
th
e
Haa
r
C
ascad
e
class
if
ier
f
o
r
n
asal
R
OI
d
etec
tio
n
an
d
th
e
ca
n
n
y
ed
g
e
d
etec
t
o
r
f
o
r
n
o
s
tr
il
s
eg
m
en
tatio
n
,
en
h
an
cin
g
ac
c
u
r
ac
y
a
n
d
r
o
b
u
s
tn
ess
.
T
h
ese
im
p
r
o
v
em
e
n
ts
en
s
u
r
e
co
n
s
is
ten
t
p
er
f
o
r
m
an
ce
d
esp
ite
h
ea
d
m
o
v
em
e
n
ts
,
o
v
er
co
m
in
g
k
ey
lim
itatio
n
s
o
f
p
r
ev
io
u
s
m
et
h
o
d
s
.
(
a)
(
b
)
Fig
u
r
e
3
.
T
e
m
p
er
atu
r
e
v
ar
iatio
n
ar
o
u
n
d
th
e
n
o
s
tr
ils
d
u
r
in
g
(
a
)
in
s
p
ir
atio
n
an
d
(
b
)
ex
p
ir
atio
n
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:
2502
-
4
7
5
2
N
o
n
-
co
n
ta
ct
b
r
ea
th
in
g
r
a
te
m
o
n
ito
r
in
g
u
s
in
g
i
n
fr
a
r
ed
t
h
ermo
g
r
a
p
h
y
a
n
d
…
(
A
n
a
d
ya
G
h
in
a
S
a
ls
a
b
ila
)
675
(
a)
(
b
)
(
c)
(
d
)
Fig
u
r
e
4
.
R
OI
an
d
R
OM
tr
ac
k
in
g
:
(
a)
d
etec
ted
in
th
e
r
m
al
v
i
d
eo
,
(
b
)
in
a
n
eu
tr
al
h
ea
d
p
o
s
itio
n
,
(
c)
d
u
r
i
n
g
s
lig
h
t u
p
war
d
h
e
ad
m
o
v
em
en
t
,
an
d
(
d
)
d
u
r
in
g
h
ea
d
tilt
to
th
e
s
id
e
W
h
ile
n
o
s
t
r
ils
d
i
d
n
o
t
m
o
v
e
o
u
t
o
f
t
h
e
ca
m
e
r
a
’
s
v
iew
in
t
h
is
s
t
u
d
y
,
we
in
c
o
r
p
o
r
ate
d
a
p
r
e
v
e
n
ti
v
e
in
t
er
p
o
l
ati
o
n
s
te
p
t
o
ad
d
r
ess
p
o
te
n
t
ial
ze
r
o
-
v
a
lu
e
b
r
ea
t
h
i
n
g
s
i
g
n
als
t
h
at
c
o
u
l
d
a
r
is
e
i
n
c
li
n
ic
al
s
e
tti
n
g
s
.
I
f
n
o
s
t
r
il
tr
ac
k
i
n
g
w
er
e
t
o
f
ai
l,
r
es
u
l
t
i
n
g
in
ze
r
o
v
al
u
es,
th
is
a
lg
o
r
it
h
m
wo
u
l
d
r
e
p
l
ac
e
t
h
e
m
wit
h
t
h
e
av
e
r
a
g
e
o
f
s
u
r
r
o
u
n
d
i
n
g
d
at
a
p
o
i
n
ts
.
T
h
i
s
a
p
p
r
o
ac
h
f
ills
i
n
d
at
a
g
a
p
s
a
n
d
s
m
o
o
t
h
s
o
u
t
a
b
r
u
p
t
s
i
g
n
al
ju
m
p
s
,
h
e
lp
in
g
m
ai
n
t
ai
n
a
co
n
t
in
u
o
u
s
an
d
c
o
n
s
is
t
en
t
s
i
g
n
a
l
m
o
r
p
h
o
lo
g
y
.
C
o
n
s
e
q
u
e
n
tl
y
,
t
h
e
b
r
ea
t
h
i
n
g
s
ig
n
al
r
e
m
ai
n
s
r
eli
ab
le
f
o
r
f
u
r
t
h
e
r
an
al
y
s
is
,
r
e
d
u
ci
n
g
t
h
e
r
is
k
o
f
m
is
d
ete
cti
o
n
f
r
o
m
s
u
d
d
en
z
er
o
-
v
al
u
e
i
n
t
er
r
u
p
ti
o
n
s
.
T
h
is
i
n
t
er
p
o
l
ati
o
n
m
et
h
o
d
r
ep
r
ese
n
ts
a
n
in
n
o
v
a
tiv
e
a
p
p
r
o
ac
h
n
o
t
a
d
d
r
ess
e
d
in
p
r
i
o
r
s
tu
d
i
es,
f
u
r
th
e
r
b
r
i
d
g
i
n
g
t
h
e
i
d
en
ti
f
ie
d
r
es
ea
r
c
h
g
ap
.
T
h
e
e
x
t
r
ac
t
ed
b
r
ea
t
h
i
n
g
s
i
g
n
a
ls
g
en
e
r
al
ly
e
x
h
i
b
it
lo
w
SNR
.
He
n
c
e,
th
e
s
i
g
n
a
l
w
as
f
ilt
er
e
d
u
s
i
n
g
a
s
ec
o
n
d
-
o
r
d
e
r
B
u
tt
er
w
o
r
t
h
b
a
n
d
p
ass
f
ilt
er
,
wi
th
a
l
o
w
er
cu
to
f
f
f
r
e
q
u
e
n
cy
s
et
a
t
0
.
1
Hz
an
d
a
n
u
p
p
e
r
c
u
t
o
f
f
o
f
a
t
0
.
5
H
z.
Fi
g
u
r
e
5
p
r
es
en
ts
a
c
o
m
p
ar
is
o
n
b
et
we
en
t
h
e
r
a
w
a
n
d
f
ilt
er
e
d
b
r
e
at
h
i
n
g
s
ig
n
a
ls
e
x
t
r
ac
t
ed
f
r
o
m
t
h
e
r
m
al
v
i
d
e
o
s
.
Sp
ec
i
f
i
ca
l
ly
,
Fi
g
u
r
e
5
(
a)
s
h
o
ws
t
h
e
r
a
w
b
r
e
at
h
i
n
g
s
i
g
n
als
,
w
h
il
e
Fi
g
u
r
e
5
(
b
)
d
is
p
l
ay
s
t
h
e
s
i
g
n
als
a
f
t
er
f
ilt
e
r
i
n
g
.
T
h
e
B
u
tt
e
r
wo
r
t
h
b
a
n
d
p
ass
f
ilt
er
ef
f
e
cti
v
e
l
y
r
e
d
u
c
e
d
n
o
is
e,
r
es
u
l
ti
n
g
i
n
s
m
o
o
t
h
er
s
i
g
n
als
w
it
h
m
o
r
e
ap
p
a
r
e
n
t
p
er
i
o
d
i
c
p
att
er
n
s
,
wh
er
e
in
s
p
i
r
a
t
o
r
y
p
ea
k
s
a
n
d
e
x
p
i
r
at
o
r
y
tr
o
u
g
h
s
ar
e
m
o
r
e
e
asil
y
i
d
e
n
t
if
ie
d
.
W
h
il
e
th
e
r
e
w
as
a
s
li
g
h
t
a
m
p
lit
u
d
e
s
h
i
f
t
b
etw
ee
n
t
h
e
r
aw
a
n
d
f
il
te
r
ed
s
i
g
n
als
,
t
h
is
d
i
d
n
o
t
af
f
e
ct
t
h
e
a
cc
u
r
ac
y
o
f
BR
d
et
ec
ti
o
n
,
as
t
h
e
f
i
lte
r
p
r
es
er
v
e
d
t
h
e
s
i
g
n
al
m
o
r
p
h
o
l
o
g
y
,
e
n
s
u
r
i
n
g
p
e
a
k
a
n
d
t
r
o
u
g
h
i
d
en
tifi
ca
ti
o
n
r
em
ai
n
e
d
r
el
ia
b
le
.
A
f
t
er
t
h
at
,
p
e
ak
d
ete
cti
o
n
al
g
o
r
it
h
m
s
we
r
e
a
p
p
lie
d
to
id
e
n
ti
f
y
t
h
e
p
e
a
k
a
n
d
v
all
ey
in
t
h
e
b
r
ea
th
in
g
s
ig
n
al
,
i
n
d
ica
ti
n
g
t
h
e
b
r
ea
th
in
g
cy
cl
e
’
s
i
n
s
p
i
r
ati
o
n
a
n
d
e
x
p
i
r
ati
o
n
p
h
ases
.
On
e
b
r
e
at
h
i
n
g
c
y
cl
e
c
o
n
s
is
ts
o
f
o
n
e
in
s
p
i
r
at
io
n
p
h
as
e
a
n
d
o
n
e
e
x
p
i
r
at
io
n
p
h
as
e,
d
e
f
i
n
ed
as
t
h
e
d
i
s
tan
ce
b
etw
ee
n
c
o
n
s
e
cu
ti
v
e
p
e
ak
s
o
r
c
o
n
s
e
cu
ti
v
e
v
al
le
y
s
.
T
h
u
s
,
t
h
e
B
R
ca
n
b
e
c
alc
u
l
ate
d
b
y
o
n
e
m
i
n
u
te
’
s
to
tal
n
u
m
b
e
r
o
f
b
r
ea
th
c
y
cles
.
(
a)
(
b
)
Fig
u
r
e
5
.
E
x
tr
ac
ted
b
r
ea
th
in
g
s
ig
n
al
(
a)
b
ef
o
r
e
f
i
lter
in
g
an
d
(
b
)
af
ter
f
ilter
in
g
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
39
,
No
.
1
,
J
u
ly
20
25
:
669
-
6
8
0
676
3
.
1
.
B
re
a
t
hin
g
ra
t
e
ca
lcula
t
i
o
n
T
h
is
s
tu
d
y
e
v
alu
ates
r
esp
ir
ato
r
y
r
ate
esti
m
atio
n
f
r
o
m
th
er
m
al
v
id
eo
r
ec
o
r
d
in
g
s
u
n
d
er
t
h
r
e
e
d
if
f
er
e
n
t
co
n
d
itio
n
s
:
(
i
)
s
tatio
n
ar
y
n
o
r
m
al
b
r
ea
th
i
n
g
,
(
ii
)
h
ea
d
m
o
v
em
en
t
with
n
o
r
m
al
b
r
ea
t
h
in
g
,
an
d
(
iii
)
a
b
n
o
r
m
al
b
r
ea
th
in
g
p
atter
n
s
s
u
ch
as b
r
a
d
y
p
n
ea
o
r
tach
y
p
n
ea
.
T
a
b
l
e
1
p
r
e
s
e
n
t
s
t
h
e
p
e
r
f
o
r
m
an
c
e
o
f
t
h
e
p
r
o
p
o
s
e
d
a
l
g
o
r
i
t
h
m
a
c
r
o
s
s
t
h
es
e
c
o
n
d
i
t
i
o
n
s
.
I
n
c
o
n
d
i
t
i
o
n
1
(
C
1
)
,
w
h
e
r
e
s
u
b
j
e
ct
s
m
a
i
n
t
a
i
n
e
d
a
s
t
a
t
i
o
n
a
r
y
p
o
s
t
u
r
e
w
h
il
e
b
r
e
a
t
h
i
n
g
n
o
r
m
a
l
l
y
,
t
h
e
a
l
g
o
r
i
th
m
d
e
m
o
n
s
t
r
a
t
e
d
a
h
i
g
h
c
a
n
d
i
d
a
t
e
i
n
d
e
x
(
C
A
ND
)
o
f
9
4
.
5
7
%
o
n
a
v
e
r
a
g
e
,
w
i
t
h
v
a
l
u
es
r
a
n
g
i
n
g
f
r
o
m
9
1
.
0
3
%
t
o
9
9
.
6
5
%
.
T
h
e
m
e
a
n
a
b
s
o
l
u
t
e
e
r
r
o
r
(
M
A
E
)
i
n
r
e
s
p
i
r
a
t
o
r
y
r
a
t
e
e
s
ti
m
a
t
i
o
n
w
a
s
1
.
0
4
5
b
p
m
,
w
i
t
h
t
h
e
h
i
g
h
e
s
t
o
b
s
e
r
v
e
d
e
r
r
o
r
a
t
1
.
7
7
b
p
m
a
n
d
t
h
e
l
o
w
e
s
t
at
0
.
0
7
b
p
m
.
T
h
e
s
e
r
e
s
u
lt
s
i
n
d
i
c
a
t
e
th
a
t
t
h
e
a
l
g
o
r
i
t
h
m
p
e
r
f
o
r
m
s
a
c
cu
r
a
t
e
l
y
u
n
d
e
r
s
t
at
i
c
c
o
n
d
i
t
i
o
n
s
.
I
n
c
o
n
d
itio
n
2
(
C
2
)
,
wh
er
e
s
u
b
jects
p
er
f
o
r
m
e
d
h
ea
d
m
o
v
em
en
ts
wh
ile
m
ain
tain
in
g
a
n
o
r
m
a
l
b
r
ea
th
in
g
p
atter
n
,
th
e
alg
o
r
ith
m
r
em
ain
ed
r
o
b
u
s
t,
ac
h
iev
in
g
an
av
er
ag
e
C
AND
in
d
ex
o
f
9
3
.
7
1
%,
with
v
alu
es
r
an
g
in
g
f
r
o
m
8
7
.
3
1
%
to
9
9
.
7
7
%.
Ho
wev
er
,
d
u
e
to
m
o
tio
n
ar
tifa
cts
in
tr
o
d
u
ce
d
b
y
h
ea
d
m
o
v
em
en
ts
,
th
er
e
was
a
s
lig
h
t
in
cr
ea
s
e
in
th
e
MA
E
t
o
1
.
2
5
9
b
p
m
.
T
h
e
h
ig
h
est
in
d
iv
id
u
al
er
r
o
r
r
ec
o
r
d
ed
in
th
is
co
n
d
itio
n
was
2
.
7
3
b
p
m
,
wh
ile
th
e
lo
west
was
0
.
0
4
b
p
m
.
T
h
is
s
u
g
g
ests
th
at
wh
ile
th
e
m
eth
o
d
r
em
ai
n
s
ef
f
ec
tiv
e
in
d
y
n
a
m
ic
s
ettin
g
s
,
ad
d
itio
n
al
m
o
tio
n
co
m
p
en
s
atio
n
tech
n
i
q
u
es m
ay
b
e
r
eq
u
ir
e
d
to
en
h
an
ce
ac
c
u
r
ac
y
.
I
n
c
o
n
d
itio
n
3
(
C
3
)
,
wh
ic
h
in
v
o
lv
ed
ab
n
o
r
m
al
b
r
ea
th
in
g
p
a
tter
n
s
s
u
ch
as
b
r
ad
y
p
n
ea
a
n
d
t
ac
h
y
p
n
ea
,
th
e
alg
o
r
ith
m
m
ain
tain
e
d
s
tr
o
n
g
p
e
r
f
o
r
m
an
ce
,
a
ch
iev
in
g
a
n
av
er
a
g
e
C
AND
in
d
ex
o
f
9
6
.
0
6
%,
with
v
alu
es
r
an
g
in
g
f
r
o
m
9
1
.
3
0
%
to
9
9
.
7
7
%.
T
h
e
MA
E
was
r
ed
u
ce
d
to
0
.
6
0
7
b
p
m
,
with
th
e
h
ig
h
es
t
er
r
o
r
r
ec
o
r
d
ed
at
1
.
2
3
b
p
m
an
d
th
e
lo
west
at
0
.
0
4
b
p
m
.
T
h
ese
f
in
d
in
g
s
in
d
i
ca
te
th
at
th
e
p
r
o
p
o
s
ed
m
eth
o
d
is
well
-
s
u
ited
f
o
r
d
etec
tin
g
ir
r
eg
u
lar
r
esp
ir
ato
r
y
p
atter
n
s
with
h
ig
h
p
r
ec
is
io
n
.
O
v
e
r
a
l
l
,
t
h
e
r
es
u
l
ts
c
o
n
f
i
r
m
t
h
a
t
t
h
e
p
r
o
p
o
s
e
d
a
l
g
o
r
it
h
m
p
r
o
v
i
d
e
s
a
cc
u
r
a
t
e
r
e
s
p
i
r
at
o
r
y
r
a
t
e
e
s
ti
m
a
ti
o
n
e
v
e
n
u
n
d
e
r
c
o
n
d
i
t
i
o
n
s
i
n
v
o
l
v
i
n
g
m
o
t
i
o
n
a
r
t
i
f
a
c
t
s
a
n
d
a
b
n
o
r
m
a
l
b
r
e
a
t
h
i
n
g
p
a
t
t
e
r
n
s
.
T
h
e
s
l
i
g
h
t
p
e
r
f
o
r
m
a
n
c
e
d
e
g
r
a
d
a
t
i
o
n
o
b
s
e
r
v
e
d
i
n
c
o
n
d
i
t
i
o
n
2
(
C
2
)
s
u
g
g
es
t
s
t
h
a
t
f
u
r
t
h
e
r
i
m
p
r
o
v
e
m
e
n
t
s
i
n
n
as
a
l
tr
a
c
k
i
n
g
a
l
g
o
r
i
t
h
m
s
a
n
d
m
o
t
i
o
n
c
o
m
p
e
n
s
a
t
i
o
n
t
ec
h
n
i
q
u
e
s
c
o
u
l
d
e
n
h
a
n
c
e
r
o
b
u
s
t
n
es
s
i
n
d
y
n
a
m
i
c
e
n
v
i
r
o
n
m
en
t
s
.
F
u
t
u
r
e
s
t
u
d
ie
s
s
h
o
u
l
d
f
o
c
u
s
o
n
v
a
l
i
d
a
t
i
n
g
th
e
m
e
t
h
o
d
w
i
t
h
a
l
a
r
g
e
r
a
n
d
m
o
r
e
d
i
v
e
r
s
e
d
a
t
a
s
e
t
t
o
s
tr
e
n
g
t
h
e
n
i
t
s
c
l
i
n
i
c
a
l
a
p
p
l
i
c
a
b
i
li
t
y
.
T
ab
le
1
.
Per
f
o
r
m
an
ce
ev
alu
ati
o
n
o
f
s
y
s
tem
u
s
in
g
C
AND
in
d
ex
an
d
MA
E
S
u
b
j
e
c
t
C1
C2
C3
(
b
p
m)
(
b
p
m)
Er
r
o
r
(
b
p
m)
(
%)
(
b
p
m)
(
b
p
m)
Er
r
o
r
(
b
p
m)
(
%)
(
b
p
m)
(
b
p
m)
Er
r
o
r
(
b
p
m)
(
%)
S1
2
1
.
9
3
2
3
.
3
6
1
.
4
3
9
3
.
4
8
1
7
.
1
3
1
8
.
4
7
1
.
3
4
9
2
.
1
8
2
4
.
8
3
2
5
.
6
4
0
.
8
1
9
6
.
7
4
S2
1
9
.
7
3
2
1
.
5
0
1
.
7
7
9
1
.
0
3
2
1
.
5
6
2
3
.
8
3
2
.
2
7
8
9
.
4
7
2
4
.
5
6
2
4
.
0
0
0
.
5
6
9
7
.
7
2
S3
1
7
.
5
0
1
7
.
0
5
0
.
4
5
9
7
.
4
3
1
7
.
8
3
1
9
.
5
2
1
.
6
9
9
0
.
5
2
9
.
4
8
9
.
0
0
0
.
4
8
9
4
.
9
4
S4
1
8
.
7
8
1
9
.
8
9
1
.
1
1
9
4
.
0
9
2
1
.
5
2
2
4
.
2
5
2
.
7
3
8
7
.
3
1
2
7
.
5
2
2
6
.
4
8
1
.
0
4
9
6
.
2
2
S5
2
1
.
8
7
2
3
.
0
7
1
.
2
0
9
4
.
5
1
2
0
.
4
3
2
1
.
3
5
0
.
9
2
9
5
.
4
9
1
0
.
9
5
1
1
.
0
0
0
.
0
5
9
9
.
5
4
S6
1
7
.
5
6
1
9
.
0
4
1
.
4
8
9
1
.
5
7
2
0
.
6
3
2
1
.
0
0
0
.
3
7
9
8
.
2
1
2
1
.
5
6
2
1
.
6
1
0
.
0
5
9
9
.
7
7
S7
2
0
.
1
3
2
1
.
2
0
0
.
0
7
9
9
.
6
5
2
0
.
5
2
2
1
.
4
2
0
.
9
0
9
5
.
6
1
1
0
.
1
2
1
1
.
0
0
0
.
8
8
9
1
.
3
0
S8
1
7
.
8
3
1
6
.
9
6
0
.
8
7
9
5
.
1
2
2
1
.
1
0
2
0
.
1
1
.
0
0
9
5
.
2
6
1
0
.
7
7
1
2
.
0
0
1
.
2
3
8
8
.
5
8
S9
1
8
.
9
8
2
0
.
5
8
1
.
6
0
9
1
.
5
7
1
9
.
8
5
1
8
.
5
2
1
.
3
3
9
3
.
2
9
1
0
.
1
6
1
0
.
3
3
0
.
1
7
9
8
.
3
3
S
1
0
1
6
.
9
5
1
7
.
4
2
0
.
4
7
9
7
.
2
3
1
7
.
1
2
1
7
.
0
8
0
.
0
4
9
9
.
7
7
3
1
.
5
1
3
0
.
7
1
0
.
8
0
9
7
.
4
6
M
E
A
N
-
-
1
.
0
4
5
9
4
.
5
7
-
-
1
.
2
5
9
9
3
.
7
1
-
-
0
.
6
0
7
9
6
.
0
6
3
.
2
.
Cla
s
s
if
ica
t
io
n us
ing
k
-
NN
Af
ter
ca
lcu
latin
g
th
e
BR
,
th
e
k
-
NN
class
if
ier
was
em
p
lo
y
ed
to
ca
teg
o
r
ize
th
e
b
r
ea
th
in
g
s
ig
n
als
in
to
th
r
ee
co
n
d
itio
n
s
:
tach
y
p
n
ea
,
n
o
r
m
al,
o
r
b
r
ad
y
p
n
ea
.
Key
f
ea
t
u
r
es
u
s
ed
f
o
r
class
if
icatio
n
in
clu
d
ed
th
e
n
u
m
b
e
r
o
f
n
o
r
m
al
an
d
a
b
n
o
r
m
al
cy
cl
es,
as
well
as
th
e
ca
lcu
lated
B
R
v
alu
es.
B
r
ea
th
in
g
cy
cles
wer
e
class
if
ied
as
n
o
r
m
al
if
th
eir
d
u
r
atio
n
r
an
g
e
d
f
r
o
m
2
.
5
to
5
s
ec
o
n
d
s
p
er
cy
cle;
d
u
r
atio
n
s
o
u
ts
id
e
th
is
r
an
g
e
wer
e
co
n
s
id
er
ed
ab
n
o
r
m
al.
T
h
e
k
-
NN
class
if
ie
r
was
tr
ain
ed
u
s
in
g
4
1
6
b
r
ea
th
in
g
s
ig
n
als
co
m
p
r
is
ed
9
0
b
r
ad
y
p
n
ea
,
2
0
0
n
o
r
m
al
b
r
ea
th
in
g
,
an
d
1
2
6
tac
h
y
p
n
e
a
s
ig
n
als.
T
h
e
d
ata
was
s
p
lit
in
to
tr
ain
in
g
a
n
d
test
in
g
s
ets
with
a
7
:3
r
atio
.
T
o
d
eter
m
in
e
th
e
o
p
tim
al
k
v
a
lu
e,
v
alid
atio
n
ac
cu
r
ac
y
was
ca
lcu
lated
f
o
r
k
v
alu
es
b
etwe
en
1
an
d
9
,
as
s
h
o
wn
in
Fig
u
r
e
6
.
B
ased
o
n
Fig
u
r
e
6
(
a)
,
th
e
m
o
s
t
ef
f
ec
t
iv
e
k
v
a
lu
e
is
k
=1
,
with
th
e
b
est
v
alid
atio
n
ac
cu
r
ac
y
o
f
1
0
0
%
an
d
tr
ain
in
g
ac
cu
r
ac
y
o
f
1
0
0
%.
T
h
is
in
d
icate
s
th
at
t
h
e
m
o
d
el
ca
n
co
r
r
ec
tly
class
if
y
th
e
tr
ain
i
n
g
d
ata
u
s
in
g
th
e
n
ea
r
est n
eig
h
b
o
r
.
W
ith
k
=1
s
elec
ted
a
s
th
e
o
p
tim
al
v
alu
e,
th
e
test
in
g
ac
cu
r
ac
y
o
f
th
e
tr
ain
e
d
k
-
NN
m
o
d
el
was
ass
es
s
ed
,
r
esu
ltin
g
in
a
test
in
g
ac
cu
r
ac
y
o
f
9
9
.
2
%.
T
h
ese
r
e
s
u
lts
d
em
o
n
s
tr
ate
th
e
m
o
d
el
’
s
ab
ilit
y
to
m
ain
tain
h
ig
h
ac
c
u
r
ac
y
o
n
u
n
s
ee
n
d
at
a
T
h
e
c
o
n
f
u
s
io
n
m
atr
i
x
g
e
n
er
ated
b
y
th
e
k
-
NN
class
if
ier
d
u
r
in
g
test
in
g
is
illu
s
tr
ated
in
Fig
u
r
e
6
(
b
)
.
T
h
e
class
if
ier
’
s
p
er
f
o
r
m
an
ce
i
s
f
u
r
th
er
ass
ess
ed
b
y
ca
lcu
latin
g
ea
ch
class
’
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:
2502
-
4
7
5
2
N
o
n
-
co
n
ta
ct
b
r
ea
th
in
g
r
a
te
m
o
n
ito
r
in
g
u
s
in
g
i
n
fr
a
r
ed
t
h
ermo
g
r
a
p
h
y
a
n
d
…
(
A
n
a
d
ya
G
h
in
a
S
a
ls
a
b
ila
)
677
s
p
ec
if
icity
,
s
en
s
itiv
ity
,
p
r
ec
is
i
o
n
,
a
n
d
F1
-
s
co
r
e,
as
d
etailed
in
T
ab
le
2
.
T
h
ese
m
etr
ics
o
f
f
er
in
s
ig
h
t
i
n
to
t
h
e
m
o
d
el
’
s
ac
cu
r
ac
y
in
co
r
r
ec
tly
id
en
tify
in
g
p
o
s
itiv
e
an
d
n
e
g
ativ
e
class
e
s
.
T
h
e
r
esu
lts
in
d
icate
th
at
th
e
k
-
NN
m
o
d
el
with
th
e
o
p
tim
al
k
v
alu
e
is
r
eliab
le
f
o
r
clas
s
if
icatio
n
ap
p
licatio
n
s
,
d
em
o
n
s
tr
atin
g
ex
ce
llen
t
p
er
f
o
r
m
an
ce
in
d
etec
tin
g
a
n
d
class
if
y
in
g
d
ata.
Ou
r
s
tu
d
y
f
o
c
u
s
ed
o
n
class
if
y
in
g
t
h
r
ee
r
esp
ir
ato
r
y
co
n
d
iti
ons
-
n
o
r
m
al,
b
r
ad
y
p
n
ea
,
an
d
t
ac
h
y
p
n
ea
-
ac
h
iev
in
g
h
ig
h
er
ac
cu
r
ac
y
th
an
p
r
ev
io
u
s
r
esear
ch
,
with
1
0
0
%
f
o
r
tr
ain
in
g
an
d
v
alid
atio
n
,
an
d
9
9
.
2
%
f
o
r
test
in
g
.
I
n
co
n
tr
ast,
p
r
io
r
wo
r
k
class
if
ied
f
o
u
r
co
n
d
itio
n
s
an
d
r
ep
o
r
ted
ac
c
u
r
ac
ies
o
f
9
8
.
5
9
%
(
tr
ain
in
g
)
,
9
9
.
5
%
(
v
al
id
atio
n
)
,
a
n
d
9
8
%
(
test
in
g
)
.
Fu
r
th
er
m
o
r
e,
o
u
r
s
y
s
tem
was
test
ed
u
n
d
er
th
r
ee
v
id
eo
d
ata
v
ar
iatio
n
s
,
in
clu
d
in
g
m
o
v
em
en
t
s
ce
n
ar
i
o
s
,
d
em
o
n
s
tr
atin
g
its
r
o
b
u
s
tn
ess
in
d
y
n
am
ic
e
n
v
ir
o
n
m
e
n
ts
.
T
h
ese
r
esu
lts
h
ig
h
lig
h
t th
e
r
eliab
ilit
y
an
d
p
r
ac
tical
ap
p
licab
ilit
y
o
f
o
u
r
n
o
n
-
co
n
tact
BR
m
o
n
ito
r
in
g
ap
p
r
o
ac
h
.
(
a)
(
b
)
Fig
u
r
e
6
.
R
esu
lts
s
h
o
win
g
(
a)
ac
cu
r
ac
y
v
al
u
es f
r
o
m
1
0
-
f
o
ld
cr
o
s
s
-
v
alid
atio
n
o
f
th
e
k
-
NN
class
if
ier
ac
r
o
s
s
v
ar
io
u
s
k
v
alu
es,
an
d
(
b
)
th
e
c
o
n
f
u
s
io
n
m
atr
ix
g
e
n
er
ated
b
y
t
h
e
k
-
NN
cla
s
s
if
ier
d
u
r
in
g
test
in
g
with
k
=1
T
ab
le
2
.
Statis
tical
ev
alu
atio
n
o
f
th
e
1
0
-
f
o
ld
cr
o
s
s
v
alid
atio
n
k
-
NN
c
lass
if
ier
f
o
r
ea
ch
class
at
k
=1
C
l
a
s
s
S
p
e
s
i
f
i
c
i
t
y
S
e
n
s
i
t
i
v
i
t
y
P
r
e
c
i
s
i
o
n
F1
-
s
c
o
r
e
B
r
a
d
y
p
n
e
a
1
.
0
0
1
.
0
0
1
.
0
0
1
.
0
0
N
o
r
mal
1
.
0
0
0
.
9
8
7
2
1
.
0
0
0
.
9
9
3
6
Ta
c
h
y
p
n
e
a
0
.
9
8
8
2
1
.
0
0
0
.
9
7
5
6
0
.
9
8
7
6
4.
CO
NCLU
SI
O
N
T
h
is
s
tu
d
y
p
r
esen
ts
a
r
eliab
le
n
o
n
-
co
n
tact
s
y
s
tem
f
o
r
m
o
n
ito
r
in
g
r
esp
ir
ato
r
y
r
ate
u
s
in
g
I
R
T
.
B
y
tr
ac
k
in
g
n
asal
tem
p
er
atu
r
e
f
lu
ctu
atio
n
s
d
u
r
in
g
i
n
s
p
ir
atio
n
an
d
e
x
p
ir
atio
n
,
th
e
p
r
o
p
o
s
ed
m
eth
o
d
e
f
f
ec
tiv
ely
esti
m
ates
BR
with
h
ig
h
ac
cu
r
ac
y
ac
r
o
s
s
d
if
f
er
e
n
t
co
n
d
itio
n
s
.
T
h
e
in
teg
r
atio
n
o
f
Haa
r
C
ascad
e,
C
an
n
y
ed
g
e
d
etec
tio
n
,
an
d
a
B
u
tter
wo
r
th
b
an
d
p
ass
f
ilter
en
h
an
ce
s
s
ig
n
a
l
q
u
ality
,
wh
ile
a
k
-
NN
class
if
ier
en
ab
les
r
eliab
le
class
if
icatio
n
o
f
b
r
ea
th
i
n
g
p
atter
n
s
.
E
x
p
er
im
e
n
tal
r
esu
lts
d
em
o
n
s
tr
ate
th
e
s
y
s
tem
’
s
s
tr
o
n
g
p
er
f
o
r
m
an
ce
,
ac
h
iev
in
g
C
AND
in
d
ices
o
f
9
4
.
5
7
%,
9
3
.
7
1
%,
an
d
9
6
.
0
6
%
f
o
r
s
tatio
n
ar
y
,
m
o
v
in
g
,
a
n
d
ab
n
o
r
m
al
b
r
ea
th
in
g
co
n
d
itio
n
s
,
r
esp
ec
tiv
ely
,
with
lo
w
MA
E
.
T
h
e
k
-
NN
class
if
ier
f
u
r
th
e
r
v
alid
ated
its
ef
f
ec
tiv
en
ess
with
9
9
.
2
%
ac
cu
r
ac
y
in
test
in
g
.
T
h
ese
f
in
d
in
g
s
h
ig
h
lig
h
t
th
e
p
o
ten
tial
o
f
I
R
T
f
o
r
n
o
n
-
in
v
asiv
e
r
esp
ir
a
to
r
y
m
o
n
ito
r
in
g
i
n
clin
ical
an
d
h
o
m
e
s
ettin
g
s
.
Fu
tu
r
e
wo
r
k
s
h
o
u
ld
f
o
cu
s
o
n
o
p
tim
izin
g
th
e
alg
o
r
ith
m
f
o
r
d
iv
er
s
e
p
atie
n
t
p
o
p
u
latio
n
s
an
d
in
teg
r
atin
g
th
e
s
y
s
tem
in
to
r
ea
l
-
tim
e
h
ea
lth
ca
r
e
f
r
am
ewo
r
k
s
f
o
r
ea
r
ly
d
et
ec
tio
n
o
f
r
esp
ir
ato
r
y
d
is
o
r
d
er
s
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
T
h
is
r
esear
ch
was
s
u
p
p
o
r
ted
b
y
th
e
Dep
ar
tm
en
t
o
f
B
io
m
ed
ical
E
n
g
in
ee
r
in
g
,
I
n
s
titu
t
T
ek
n
o
lo
g
i
Sep
u
lu
h
No
p
em
b
er
(
I
T
S),
th
r
o
u
g
h
th
e
B
io
m
ed
ical
E
n
g
in
ee
r
in
g
I
T
S
2
0
2
4
R
esear
ch
Fu
n
d
in
g
(
No
.
9
6
9
/PKS
/I
T
S/2
0
2
4
)
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
39
,
No
.
1
,
J
u
ly
20
25
:
669
-
6
8
0
678
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
An
ad
y
a
Gh
in
a
Sals
ab
ila
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
R
ac
h
m
ad
Setiawan
✓
✓
✓
✓
✓
✓
✓
Nad
a
Fit
r
iey
atu
l
Hik
m
ah
✓
✓
✓
✓
✓
✓
✓
✓
✓
Z
ain
B
u
d
i Sy
u
lth
o
n
i
✓
✓
✓
✓
C
:
C
o
n
c
e
p
tu
a
li
z
a
ti
o
n
M
:
M
e
th
o
d
o
l
o
g
y
So
:
So
ftwa
re
Va
:
Va
li
d
a
ti
o
n
Fo
:
Fo
rm
a
l
a
n
a
ly
sis
I
:
I
n
v
e
stig
a
ti
o
n
R
:
R
e
so
u
rc
e
s
D
:
D
a
ta Cu
ra
ti
o
n
O
:
Wr
it
in
g
-
O
ri
g
in
a
l
Dra
ft
E
:
Wr
it
in
g
-
Re
v
iew
&
E
d
it
i
n
g
Vi
:
Vi
su
a
li
z
a
ti
o
n
Su
:
Su
p
e
rv
isi
o
n
P
:
P
ro
jec
t
a
d
m
in
istrati
o
n
Fu
:
Fu
n
d
in
g
a
c
q
u
isi
ti
o
n
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
Au
th
o
r
s
s
tate
n
o
co
n
f
lict o
f
in
t
er
est
.
I
NF
O
RM
E
D
CO
NS
E
N
T
W
e
h
av
e
o
b
tain
ed
in
f
o
r
m
ed
c
o
n
s
en
t
f
r
o
m
all
in
d
iv
id
u
als in
c
lu
d
ed
in
t
h
is
s
tu
d
y
.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
ata
th
at
s
u
p
p
o
r
t
th
e
f
in
d
in
g
s
o
f
th
is
s
tu
d
y
ar
e
av
aila
b
le
o
n
r
eq
u
est
f
r
o
m
th
e
co
r
r
esp
o
n
d
in
g
au
th
o
r
,
N.
F.H
.
T
h
e
d
ata,
w
h
ich
co
n
tain
in
f
o
r
m
atio
n
th
at
co
u
ld
c
o
m
p
r
o
m
is
e
th
e
p
r
iv
ac
y
o
f
r
esear
ch
p
ar
ticip
an
ts
,
ar
e
n
o
t p
u
b
licly
a
v
ailab
le
d
u
e
to
ce
r
tain
r
estri
ctio
n
s
.
RE
F
E
R
E
NC
E
S
[
1
]
D
.
D
.
Ta
r
a
l
u
n
g
a
,
B
.
M
o
n
a
c
u
,
a
n
d
R
.
Ta
p
u
,
“
A
u
t
o
ma
t
i
c
r
e
a
l
t
i
m
e
d
e
r
i
v
a
t
i
o
n
o
f
b
r
e
a
t
h
i
n
g
r
a
t
e
f
r
o
m
t
h
e
r
m
a
l
v
i
d
e
o
s
e
q
u
e
n
c
e
s,
”
I
FM
BE
Pro
c
e
e
d
i
n
g
s
,
v
o
l
.
6
5
,
p
p
.
8
1
-
8
4
,
2
0
1
7
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
981
-
10
-
5
1
2
2
-
7
_
2
1
.
[
2
]
P
.
Ja
g
a
d
e
v
a
n
d
L
.
I
.
G
i
r
i
,
“
N
o
n
-
c
o
n
t
a
c
t
m
o
n
i
t
o
r
i
n
g
o
f
h
u
ma
n
r
e
s
p
i
r
a
t
i
o
n
u
si
n
g
i
n
f
r
a
r
e
d
t
h
e
r
m
o
g
r
a
p
h
y
a
n
d
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
I
n
f
r
a
re
d
P
h
y
si
c
s
and
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
1
0
4
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
n
f
r
a
r
e
d
.
2
0
1
9
.
1
0
3
1
1
7
.
[
3
]
D
.
C
.
J.
H
o
w
e
l
l
a
n
d
L.
F
l
o
w
e
r
,
“
S
i
g
n
s
o
f
r
e
s
p
i
r
a
t
o
r
y
d
i
sea
s
e
:
B
r
e
a
t
h
i
n
g
p
a
t
t
e
r
n
s
,
”
E
n
c
y
c
l
o
p
e
d
i
a
o
f
R
e
s
p
i
ra
t
o
ry
Me
d
i
c
i
n
e
,
p
p
.
5
3
–
5
6
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
B
0
-
12
-
3
7
0
8
7
9
-
6
%
2
F
0
0
3
5
2
-
5.
[
4
]
C
.
B
.
P
e
r
e
i
r
a
,
X
.
Y
u
1
,
M
.
C
z
a
p
l
i
k
,
V
.
B
l
a
z
e
k
,
B
.
V
e
n
e
ma,
a
n
d
S
.
Le
o
n
h
a
r
d
t
,
“
Est
i
ma
t
i
o
n
o
f
b
r
e
a
t
h
i
n
g
r
a
t
e
i
n
t
h
e
r
ma
l
i
ma
g
i
n
g
v
i
d
e
o
s:
a
p
i
l
o
t
s
t
u
d
y
o
n
h
e
a
l
t
h
y
h
u
m
a
n
s
u
b
j
e
c
t
s
,
”
J
o
u
r
n
a
l
o
f
C
l
i
n
i
c
a
l
M
o
n
i
t
o
r
i
n
g
a
n
d
C
o
m
p
u
t
i
n
g
,
v
o
l
.
3
1
,
p
p
.
1
2
4
1
-
1
2
5
4
,
2
0
1
7
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
0
8
7
7
-
016
-
9
9
4
9
-
y.
[
5
]
C
.
B
.
P
e
r
e
i
r
a
,
X
.
Y
u
1
,
M
.
C
z
a
p
l
i
k
,
V
.
B
l
a
z
e
k
,
B
.
V
e
n
e
m
a
,
S
.
L
e
o
n
h
a
r
d
t
,
a
n
d
D
.
T
e
i
c
h
m
a
n
n
,
“
M
o
n
i
t
o
r
i
n
g
o
f
c
a
r
d
i
o
r
e
s
p
i
r
a
t
o
r
y
si
g
n
a
l
s
u
si
n
g
t
h
e
r
mal
i
m
a
g
i
n
g
:
a
p
i
l
o
t
st
u
d
y
o
n
h
e
a
l
t
h
y
h
u
ma
n
su
b
j
e
c
t
s,
”
S
e
n
so
rs
,
v
o
l
.
2
8
,
2
0
1
8
,
d
o
i
:
1
0
.
3
3
9
0
/
s
1
8
0
5
1
5
4
1
.
[
6
]
F
.
S
.
A
.
R
e
st
a
,
R
.
S
e
t
i
a
w
a
n
,
N
.
F
.
H
i
k
m
a
h
,
a
n
d
R
.
A
m
a
l
i
a
,
“
N
o
n
c
o
n
t
a
c
t
e
l
e
c
t
r
o
c
a
r
d
i
o
g
r
a
m
sy
s
t
e
m
f
o
r
ma
t
t
r
e
sses
u
si
n
g
si
l
v
e
r
c
o
n
d
u
c
t
i
v
e
f
a
b
r
i
c
,
”
i
n
1
1
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
El
e
c
t
ri
c
a
l
E
n
g
i
n
e
e
ri
n
g
,
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
I
n
f
o
r
m
a
t
i
c
s
,
p
p
.
3
3
-
3
8
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
EE
C
S
I
6
3
4
4
2
.
2
0
2
4
.
1
0
7
7
6
1
6
2
.
[
7
]
J.
F
e
i
a
n
d
I
.
P
a
v
l
i
d
i
s,
“
Th
e
r
mi
s
t
o
r
a
t
a
d
i
s
t
a
n
c
e
:
u
n
o
b
t
r
u
si
v
e
mea
s
u
r
e
m
e
n
t
o
f
b
r
e
a
t
h
i
n
g
,
”
I
EEE
T
ra
n
s
a
c
t
i
o
n
s
o
n
Bi
o
m
e
d
i
c
a
l
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
5
7
,
n
o
.
4
,
p
p
.
9
8
8
–
9
9
8
,
2
0
1
0
,
d
o
i
:
1
0
.
1
1
0
9
/
T
B
M
E.
2
0
0
9
.
2
0
3
2
4
1
5
.
[
8
]
N
.
F
.
H
i
k
ma
h
,
R
.
S
e
t
i
a
w
a
n
,
a
n
d
M
.
D
.
G
u
n
a
w
a
n
,
“
S
l
e
e
p
q
u
a
l
i
t
y
a
sse
ssm
e
n
t
f
r
o
m ro
b
u
s
t
h
e
a
r
t
a
n
d
mu
s
c
l
e
f
a
t
i
g
u
e
e
st
i
mat
i
o
n
u
si
n
g
su
p
e
r
v
i
se
d
mac
h
i
n
e
l
e
a
r
n
i
n
g
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
I
n
t
e
l
l
i
g
e
n
t
E
n
g
i
n
e
e
ri
n
g
a
n
d
S
y
s
t
e
m
s
,
v
o
l
.
1
6
,
n
o
.
2
,
p
p
.
3
1
9
-
3
3
1
,
2
0
2
3
,
d
o
i
:
1
0
.
2
2
2
6
6
/
i
j
i
e
s2
0
2
3
.
0
4
3
0
.
2
6
.
[
9
]
R
.
M
u
r
t
h
y
,
I
.
P
a
v
l
i
d
i
s,
a
n
d
P
.
Ts
i
a
m
y
r
t
z
i
s
,
“
T
o
u
c
h
l
e
ss
m
o
n
i
t
o
r
i
n
g
o
f
b
r
e
a
t
h
i
n
g
f
u
n
c
t
i
o
n
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
I
EE
E
En
g
i
n
e
e
r
i
n
g
i
n
Me
d
i
c
i
n
e
a
n
d
Bi
o
l
o
g
y
S
o
c
i
e
t
y
(
I
EEE,
2
0
0
4
)
,
p
p
.
1
1
9
6
–
1
1
9
9
,
d
o
i
:
1
0
.
1
1
0
9
/
I
EM
B
S
.
2
0
0
4
.
1
4
0
3
3
8
2
.
[
1
0
]
R
.
G
.
S
o
t
o
,
E.
S
.
F
u
,
H
.
V
i
l
a
,
a
n
d
R
.
V
.
M
i
g
u
e
l
,
“
C
a
p
n
o
g
r
a
p
h
y
a
c
c
u
r
a
t
e
l
y
d
e
t
e
c
t
s
a
p
n
e
a
d
u
r
i
n
g
m
o
n
i
t
o
r
e
d
a
n
e
s
t
h
e
si
a
c
a
r
e
,
”
An
e
s
t
h
.
A
n
a
l
g
.
,
v
o
l
.
9
9
,
n
o
.
2
,
p
p
.
3
7
9
–
3
8
2
,
2
0
0
4
,
d
o
i
:
1
0
.
1
2
1
3
/
0
1
.
A
N
E.
0
0
0
0
1
3
1
9
6
4
.
6
7
5
2
4
.
E7
.
[
1
1
]
L.
M
a
u
r
y
a
a
,
P
.
M
a
h
a
p
a
t
r
a
b
,
a
n
d
D
.
C
h
a
w
l
a
,
“
N
o
n
-
c
o
n
t
a
c
t
b
r
e
a
t
h
i
n
g
m
o
n
i
t
o
r
i
n
g
b
y
i
n
t
e
g
r
a
t
i
n
g
R
G
B
a
n
d
t
h
e
r
mal
i
m
a
g
i
n
g
v
i
a
R
G
B
-
t
h
e
r
m
a
l
i
ma
g
e
r
e
g
i
st
r
a
t
i
o
n
,
”
Bi
o
c
y
b
e
r
n
e
t
i
c
s
a
n
d
B
i
o
m
e
d
i
c
a
l
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
4
1
,
p
p
.
1
1
0
7
-
1
1
2
2
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
b
b
e
.
2
0
2
1
.
0
7
.
0
0
2
.
[
1
2
]
C
.
B
.
P
e
r
e
i
r
a
,
X
.
Y
u
1
,
M
.
C
z
a
p
l
i
k
,
V
.
B
l
a
z
e
k
,
B
.
V
e
n
e
ma,
a
n
d
S
.
L
e
o
n
h
a
r
d
t
,
“
R
e
m
o
t
e
m
o
n
i
t
o
r
i
n
g
o
f
b
r
e
a
t
h
i
n
g
d
y
n
a
m
i
c
s
u
s
i
n
g
i
n
f
r
a
r
e
d
t
h
e
r
mo
g
r
a
p
h
y
,
”
Bi
o
m
e
d
i
c
a
l
O
p
t
i
c
s
Ex
p
ress
,
v
o
l
.
6
,
p
p
.
4
3
7
8
–
4
3
9
4
,
2
0
1
5
,
d
o
i
:
1
0
.
1
3
6
4
/
B
O
E.
6
.
0
0
4
3
7
8
.
[
1
3
]
A
.
D
.
D
r
o
i
t
c
o
u
r
e
t
a
l
.
,
“
N
o
n
-
c
o
n
t
a
c
t
r
e
sp
i
r
a
t
o
r
y
r
a
t
e
m
e
a
s
u
r
e
m
e
n
t
v
a
l
i
d
a
t
i
o
n
f
o
r
h
o
sp
i
t
a
l
i
z
e
d
p
a
t
i
e
n
t
s,
”
I
n
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
I
EEE
En
g
i
n
e
e
r
i
n
g
i
n
Me
d
i
c
i
n
e
a
n
d
Bi
o
l
o
g
y
S
o
c
i
e
t
y
,
M
i
n
n
e
a
p
o
l
i
s
,
M
N
,
U
S
A
,
2
–
6
S
e
p
t
e
m
b
e
r
2
0
0
9
;
p
p
.
4
8
1
2
–
4
8
1
5
,
d
o
i
:
1
0
.
1
1
0
9
/
I
EM
B
S
.
2
0
0
9
.
5
3
3
2
6
3
5
.
Evaluation Warning : The document was created with Spire.PDF for Python.