I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
p
ute
r
E
ng
in
ee
ring
(
I
J
E
CE
)
Vo
l.
8
,
No
.
5
,
Octo
b
e
r
2
0
1
8
,
p
p
.
3
9
40
~3
9
4
8
I
SS
N:
2
0
8
8
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v8
i
5
.
p
p
3
9
3
7
-
394
8
3940
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
co
r
e
.
co
m/
jo
u
r
n
a
ls
/in
d
ex
.
p
h
p
/
I
JE
C
E
Sleep A
pnea
Iden
tif
ica
tion
u
sing
HRV F
ea
tures of
E
CG
Sig
na
ls
B
illy
Su
lis
t
y
o
,
Nico
Su
ra
ntha
,
Sa
ni
M
.
I
s
a
Co
m
p
u
ter S
c
ien
c
e
De
p
a
rtm
e
n
t,
Bin
u
s G
ra
d
u
a
te
P
ro
g
ra
m
–
M
a
ste
r
o
f
Co
m
p
u
ter S
c
ien
c
e
,
Bin
a
Nu
sa
n
tara
Un
iv
e
rsity
,
Ja
k
a
rta,
In
d
o
n
e
sia
1
1
4
8
0
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
A
p
r
10
,
2
0
1
8
R
ev
i
s
ed
J
u
n
2
1
,
2
0
1
8
A
cc
ep
ted
J
u
l
1
0
,
2
0
1
8
S
lee
p
a
p
n
e
a
is
a
c
o
m
m
o
n
sle
e
p
d
i
so
rd
e
r
th
a
t
in
terf
e
re
s
w
it
h
th
e
b
re
a
th
in
g
o
f
a
p
e
rso
n
.
Du
ri
n
g
sle
e
p
,
p
e
o
p
le
c
a
n
sto
p
b
re
a
th
in
g
f
o
r
a
m
o
m
e
n
t
th
a
t
c
a
u
se
s
th
e
b
o
d
y
lac
k
o
f
o
x
y
g
e
n
th
a
t
las
ts
f
o
r
se
v
e
ra
l
s
e
c
o
n
d
s
to
m
in
u
tes
e
v
e
n
u
n
ti
l
t
h
e
ra
n
g
e
o
f
h
o
u
rs.
If
it
h
a
p
p
e
n
s
f
o
r
a
lo
n
g
p
e
rio
d
,
it
c
a
n
re
su
lt
in
m
o
re
se
rio
u
s
d
ise
a
se
s
,
e
.
g
.
h
ig
h
b
lo
o
d
p
re
ss
u
re
,
h
e
a
rt
fa
il
u
re
,
stro
k
e
,
d
i
a
b
e
tes
,
e
tc
.
S
lee
p
a
p
n
e
a
c
a
n
b
e
p
re
v
e
n
ted
b
y
id
e
n
ti
fy
in
g
th
e
i
n
d
ica
ti
o
n
o
f
s
lee
p
a
p
n
e
a
it
se
lf
f
ro
m
EC
G
,
EE
G
,
o
r
o
th
e
r
sig
n
a
l
s
to
p
e
rf
o
rm
e
a
rl
y
p
re
v
e
n
ti
o
n
.
T
h
e
p
u
r
p
o
se
o
f
th
is
stu
d
y
is
to
b
u
il
d
a
c
las
si
f
i
c
a
ti
o
n
m
o
d
e
l
to
id
e
n
ti
f
y
sle
e
p
d
iso
rd
e
rs f
ro
m
th
e
He
a
rt
Ra
te
V
a
riab
i
li
ty
(HRV
)
f
e
a
tu
re
s
th
a
t
c
a
n
b
e
o
b
t
a
in
e
d
w
it
h
El
e
c
tro
c
a
rd
i
o
g
ra
m
(EC
G
)
sig
n
a
ls.
In
t
h
is
st
u
d
y
,
HRV
f
e
a
tu
re
s
w
e
r
e
p
ro
c
e
ss
e
d
u
sin
g
se
v
e
ra
l
c
l
a
ss
i
f
ic
a
ti
o
n
m
e
th
o
d
s,
i.
e
.
A
N
N,
KN
N,
N
-
Ba
y
e
s
a
n
d
S
V
M
li
n
e
a
r
M
e
th
o
d
s.
T
h
e
c
las
si
f
ica
ti
o
n
is
p
e
rf
o
r
m
e
d
u
sin
g
su
b
jec
t
-
sp
e
c
if
ic
sc
h
e
m
e
a
n
d
su
b
jec
t
-
in
d
e
p
e
n
d
e
n
t
sc
h
e
m
e
.
T
h
e
si
m
u
latio
n
re
su
lt
s
sh
o
w
th
a
t
th
e
S
V
M
m
e
th
o
d
a
c
h
i
e
v
e
s
h
ig
h
e
r
a
c
c
u
ra
c
y
o
th
e
r
th
a
n
th
re
e
o
th
e
r
m
e
th
o
d
s
i
n
id
e
n
t
ify
in
g
sle
e
p
a
p
n
e
a
.
W
h
il
e
,
ti
m
e
d
o
m
a
in
f
e
a
tu
re
s
sh
o
w
s
th
e
m
o
st d
o
m
in
a
n
t
p
e
rf
o
rm
a
n
c
e
a
m
o
n
g
th
e
HRV
f
e
a
tu
re
s.
K
ey
w
o
r
d
:
E
C
G
Featu
r
e
e
x
tr
ac
tio
n
HR
V
Sleep
a
p
n
ea
Co
p
y
rig
h
t
©
2
0
1
8
In
stit
u
te o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts
re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Nico
Su
r
an
t
h
a
,
C
o
m
p
u
ter
Scien
ce
Dep
ar
t
m
en
t,
B
in
u
s
Gr
ad
u
ate
P
r
o
g
r
a
m
–
Ma
s
ter
o
f
C
o
m
p
u
ter
Scie
n
ce
,
B
in
a
Nu
s
an
tar
a
U
n
i
v
er
s
it
y
,
J
ak
ar
ta,
I
n
d
o
n
esia 1
1
4
8
0
.
E
m
ail:
n
s
u
r
an
t
h
a
@
b
in
u
s
.
ed
u
1.
I
NT
RO
D
UCT
I
O
N
Sleep
is
v
er
y
i
m
p
o
r
ta
n
t
f
o
r
th
e
h
u
m
an
b
o
d
y
to
p
er
f
o
r
m
o
p
ti
m
al
ly
.
Du
r
i
n
g
s
leep
,
th
e
b
o
d
y
w
ill
f
o
r
m
an
d
r
eg
en
er
ate
ce
ll
s
,
s
u
p
p
o
r
t
b
r
ain
f
u
n
ctio
n
,
an
d
r
ec
h
ar
g
e
t
h
e
b
o
d
y
's
en
er
g
y
.
Fo
r
ch
ild
r
e
n
an
d
ad
o
lescen
t
s
,
s
leep
is
r
eq
u
ir
ed
to
h
elp
t
h
e
g
r
o
w
th
p
r
o
ce
s
s
.
Sleep
ca
n
b
e
d
iv
id
ed
in
to
t
w
o
p
h
a
s
es,
i
.
e
.
r
a
p
id
ey
e
m
o
v
e
m
en
t
(
R
E
M)
an
d
n
o
n
-
R
ap
id
E
y
e
M
o
v
e
m
e
n
t
(
NR
E
M)
w
h
er
e
b
o
th
ar
e
alw
a
y
s
r
ep
ea
ted
in
s
leep
[
1
]
.
W
h
en
a
p
er
s
o
n
d
o
es
n
o
t
ex
p
er
ien
ce
n
o
r
m
al
R
E
M
an
d
n
o
n
-
R
E
M
c
y
cles,
t
h
e
b
o
d
y
w
i
ll
e
x
p
er
ien
ce
v
ar
i
o
u
s
ad
v
er
s
e
e
f
f
ec
t
s
s
u
c
h
as
f
ati
g
u
e,
d
ec
r
ea
s
i
n
g
ab
i
lit
y
to
co
n
ce
n
tr
ate,
d
is
r
u
p
ted
b
o
d
y
m
etab
o
lis
m
,
an
d
s
o
o
n
[
2
]
.
T
h
er
e
ar
e
v
ar
io
u
s
t
y
p
es
o
f
s
l
ee
p
in
g
d
is
o
r
d
er
,
e.
g
.
in
s
o
m
n
i
a,
n
ar
co
lep
s
y
,
s
leep
ap
n
ea
,
p
ar
aso
m
n
ia,
h
y
p
er
s
o
m
n
ia,
r
estl
ess
le
g
s
y
n
d
r
o
m
e,
etc
[
3
]
.
Sleep
a
p
n
ea
is
a
d
is
tu
r
b
an
ce
to
th
e
b
r
ea
th
in
g
p
r
o
ce
s
s
b
ec
au
s
e
th
e
w
al
l
o
f
t
h
e
t
h
r
o
at
is
r
elax
ed
an
d
n
ar
r
o
w
ed
w
h
i
le
s
leep
i
n
g
[
4
]
.
W
h
ile
s
leep
in
g
,
t
h
e
m
u
s
cles
o
f
t
h
e
t
h
r
o
at
b
ec
o
m
e
r
ela
x
ed
an
d
w
ea
k
.
W
h
en
t
h
e
m
u
s
c
les
ar
e
to
o
w
ea
k
an
d
n
o
t
tr
ea
ted
i
m
m
ed
iatel
y
,
it
m
a
y
ca
u
s
e
co
n
s
tr
ictio
n
o
r
ev
e
n
b
lo
ck
th
e
air
w
a
y
s
t
h
at
p
o
ten
tiall
y
ca
u
s
e
h
ea
lt
h
p
r
o
b
lem
s
,
ac
cid
en
t
s
,
an
d
p
r
em
atu
r
e
d
ea
th
.
T
h
er
e
ar
e
3
ty
p
es
o
f
s
leep
ap
n
ea
,
i.e
.
o
b
s
tr
u
ctiv
e
s
leep
ap
n
ea
ca
u
s
ed
b
y
o
b
s
tr
u
ctio
n
o
f
th
e
r
esp
ir
ato
r
y
tr
ac
t
,
ce
n
tr
al
s
leep
ap
n
ea
ca
u
s
ed
b
y
th
e
u
n
s
tab
le
r
esp
ir
ato
r
y
co
n
tr
o
l
ce
n
ter
s
th
at
r
esu
l
t
in
th
e
b
r
ain
f
ail
in
g
to
s
ig
n
al
th
e
b
r
e
ath
i
n
g
m
u
s
c
les
[
4
]
,
[
5
]
,
an
d
m
i
x
ed
co
m
p
lex
w
h
ic
h
i
s
a
co
m
b
in
at
io
n
o
f
o
b
s
tr
u
cti
v
e
an
d
ce
n
tr
al
ap
n
ea
Sleep
ap
n
ea
is
v
er
y
co
m
m
o
n
,
u
s
u
all
y
f
o
u
n
d
m
o
r
e
in
m
en
t
h
an
in
w
o
m
e
n
.
T
h
is
co
n
d
itio
n
c
an
o
cc
u
r
in
p
atien
t
s
o
f
an
y
a
g
e,
b
u
t
m
o
r
e
co
m
m
o
n
in
m
id
d
le
-
a
g
ed
ad
u
lts
.
Sleep
a
p
n
ea
ca
n
b
e
tr
ea
ted
b
y
k
n
o
w
i
n
g
th
e
s
y
m
p
to
m
s
o
r
s
ig
n
s
o
f
s
leep
ap
n
ea
,
r
ed
u
cin
g
r
is
k
f
ac
to
r
s
a
n
d
b
ein
g
d
is
c
u
s
s
ed
w
it
h
th
e
d
o
cto
r
f
o
r
f
u
r
t
h
er
ac
tio
n
.
C
o
m
m
o
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2
0
8
8
-
8708
S
leep
A
p
n
e
a
I
d
en
tifi
ca
tio
n
u
s
i
n
g
HR
V
F
ea
t
u
r
es o
f E
C
G
S
ig
n
a
ls
(
B
illy S
u
lis
tyo
)
3941
s
y
m
p
to
m
s
ar
e
s
n
o
r
i
n
g
,
o
t
h
er
s
n
o
tice
s
o
m
e
b
r
ea
th
i
n
g
i
n
ter
r
u
p
tio
n
s
d
u
r
i
n
g
s
leep
,
s
u
d
d
en
wak
e
w
i
th
s
h
o
r
tn
es
s
o
f
b
r
ea
th
,
h
ea
d
ac
h
e
in
t
h
e
m
o
r
n
in
g
,
i
n
s
o
m
n
ia,
atte
n
tio
n
p
r
o
b
le
m
s
,
ir
r
itab
ilit
y
,
an
d
h
y
p
er
s
o
m
n
ia
.
S
leep
ap
n
ea
d
is
o
r
d
er
ca
n
ca
u
s
e
h
y
p
er
ten
s
i
o
n
,
h
i
g
h
b
lo
o
d
p
r
ess
u
r
e,
s
tr
o
k
e,
o
b
esit
y
,
a
n
d
d
iab
etes.
S
leep
ap
n
ea
c
o
u
ld
n
o
t
b
e
tr
ea
ted
,
b
u
t
ca
n
b
e
d
i
m
i
n
i
s
h
e
d
b
y
d
o
in
g
tr
ea
t
m
en
t
s
s
u
c
h
a
s
b
eh
a
v
io
r
al
t
h
er
ap
y
,
p
o
s
iti
v
e
p
r
ess
u
r
e
t
h
er
ap
y
,
in
s
ta
llatio
n
o
f
o
r
al
b
r
ea
th
in
g
ap
p
ar
atu
s
,
an
d
o
p
er
atio
n
[
6
]
,
[
7
]
.
T
h
er
e
ar
e
s
o
m
e
r
esear
c
h
es
h
a
v
e
b
ee
n
p
er
f
o
r
m
ed
i
n
s
leep
a
p
n
ea
id
en
ti
f
icatio
n
.
A
l
m
az
a
y
d
eh
,
et
a
l
.,
p
er
f
o
r
m
s
o
b
s
tr
u
cti
v
e
s
leep
ap
n
ea
d
etec
tio
n
u
s
i
n
g
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
i
n
e
(
S
V
M)
m
eth
o
d
[
8
]
.
T
h
e
f
ea
t
u
r
e
u
s
ed
i
n
th
e
p
ap
er
ar
e
m
ea
n
e
p
o
ch
,
s
ta
n
d
ar
d
d
ev
iatio
n
ep
o
ch
,
NN5
0
(
v
ar
ia
n
t
1
)
,
NN5
0
(
v
ar
ian
t
2
)
,
p
NN5
0
,
etc.
T
h
ey
u
s
ed
E
C
G
s
i
g
n
al
d
atab
ase
f
r
o
m
p
h
y
s
io
n
et.
o
r
g
as
th
eir
d
ata
s
et.
On
th
e
o
t
h
er
h
an
d
,
Yil
m
az
,
et.
al.
h
av
e
p
r
o
p
o
s
ed
s
leep
s
ta
g
e
a
n
d
o
b
s
tr
u
ctiv
e
ap
n
ea
ic
ep
o
ch
class
i
f
icatio
n
u
s
i
n
g
s
in
g
le
-
lea
d
E
C
G
i
n
o
r
d
er
to
class
i
f
y
s
leep
s
tag
e
a
n
d
s
lee
p
ap
n
ea
au
to
m
a
ticall
y
u
s
i
n
g
s
in
g
le
-
lead
E
C
G
[
9
]
.
I
n
th
i
s
r
esear
ch
,
Yil
m
a
z
p
er
f
o
r
m
d
ata
p
r
ep
r
o
ce
s
s
in
g
a
n
d
f
ea
tu
r
e
e
x
tr
ac
tio
n
b
ef
o
r
e
th
e
cla
s
s
i
f
icat
io
n
.
An
o
th
er
p
ap
er
f
r
o
m
C
ar
o
lin
a
Var
o
n
,
et
a
l
.,
p
er
f
o
r
m
s
s
leep
ap
n
ea
clas
s
i
f
icatio
n
u
s
in
g
f
o
u
r
ea
s
il
y
co
m
p
u
tab
le
f
ea
tu
r
es,
th
r
ee
g
e
n
er
all
y
kn
o
w
n
o
n
es
an
d
a
n
e
w
l
y
p
r
o
p
o
s
ed
f
ea
tu
r
e
[
1
0
]
.
T
h
ey
p
er
f
o
r
m
class
i
f
ica
tio
n
u
s
i
n
g
lea
s
t
s
q
u
ar
es
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
i
n
es
(
L
S
-
SVM)
with
R
B
F
k
er
n
e
l.
Fi
n
all
y
,
San
i
M.
I
s
a,
et
a
l
l
p
r
o
p
o
s
ed
th
e
i
m
p
le
m
en
ta
tio
n
o
f
th
e
p
r
in
cip
al
co
m
p
o
n
e
n
t
an
a
l
y
s
is
(
P
C
A
)
i
n
s
leep
ap
n
ea
id
en
t
i
f
icatio
n
i
n
o
r
d
er
to
i
m
p
r
o
v
e
t
h
e
t
h
e
ac
cu
r
ac
y
o
f
class
i
f
icatio
n
p
r
o
ce
s
s
[
1
1
]
.
A
cc
o
r
d
in
g
to
th
e
s
tu
d
y
t
h
a
t
h
av
e
b
ee
n
p
er
f
o
r
m
ed
in
t
h
is
ar
ea
,
it
i
s
in
ter
e
s
ti
n
g
t
o
co
n
d
u
ct
p
er
f
o
r
m
a
n
ce
ev
al
u
atio
n
a
m
o
n
g
w
e
ll
k
n
o
w
n
clas
s
if
icatio
n
m
eth
o
d
in
t
h
e
s
i
m
ilar
s
i
m
u
la
tio
n
co
n
d
it
io
n
.
I
n
t
h
i
s
r
esear
ch
w
e
e
v
alu
a
te
th
e
p
er
f
o
r
m
a
n
ce
o
f
ANN,
KNN,
N
-
b
ay
e
s
,
an
d
s
u
p
p
o
r
t
v
ec
to
r
m
a
ch
in
e
i
n
clas
s
if
y
i
n
g
s
leep
ap
n
ea
.
T
h
en
,
m
o
s
tl
y
i
n
p
r
ev
io
u
s
s
t
u
d
y
,
th
e
y
p
er
f
o
r
m
clas
s
icatio
n
f
o
r
2
class
o
f
s
leep
ap
n
ea
.
I
n
th
i
s
s
tu
d
y
,
w
e
p
er
f
o
r
m
cla
s
s
i
f
icat
i
o
n
o
f
2
,
3
,
an
d
4
cla
s
s
o
f
s
lee
p
ap
n
ea
.
I
n
th
i
s
r
esear
c
h
w
e
a
ls
o
p
er
f
o
r
m
f
ea
t
u
r
e
ex
tr
ac
tio
n
w
it
h
f
o
u
r
tec
h
n
iq
u
es,
i.e
.
ti
m
e
d
o
m
ai
n
,
g
eo
m
etr
ical
w
it
h
h
is
to
g
r
a
m
,
p
o
i
n
c
ar
e
an
d
f
r
eq
u
en
c
y
d
o
m
ai
n
.
W
e
ev
alu
ate
w
h
ic
h
f
e
at
u
r
e
ac
h
ie
v
e
th
e
b
est
p
er
f
o
r
m
an
ce
f
o
r
s
leep
ap
n
ea
id
en
ti
f
ica
tio
n
.
I
n
th
e
en
d
o
f
s
tu
d
y
w
e
e
x
p
ec
t
to
ac
h
iev
e
th
e
b
est
ac
cu
r
ac
y
o
f
s
leep
ap
n
ea
id
en
tif
icat
io
n
w
it
h
m
ac
h
i
n
e
lear
n
in
g
m
e
th
o
d
.
W
e
also
p
er
f
o
r
m
t
w
o
m
eth
o
d
s
o
f
class
i
f
icatio
n
,
i.e
.
s
u
b
j
ec
t
-
s
p
ec
if
ic
s
c
h
e
m
e
a
n
d
s
u
b
j
ec
t
-
i
n
d
ep
en
d
en
t
s
c
h
e
m
e.
T
h
is
is
p
ap
er
is
o
r
g
an
ized
as
f
o
llo
w
.
R
esear
c
h
m
e
th
o
d
o
lo
g
y
is
ex
p
lain
ed
i
n
S
ec
tio
n
2
.
T
h
e
s
i
m
u
latio
n
r
esu
l
ts
an
d
d
is
cu
s
s
io
n
ar
e
e
x
p
lain
ed
i
n
s
ec
tio
n
3
,
w
h
ile
t
h
e
r
esu
l
t o
f
th
e
p
ap
er
is
co
n
clu
d
ed
in
S
ec
t
io
n
4
.
2.
RE
S
E
ARCH
M
E
T
H
O
D
T
h
is
r
esear
ch
f
o
cu
s
es
o
n
H
R
V
Fea
tu
r
es
o
f
E
C
G
s
i
g
n
al
i
n
g
to
id
en
t
if
y
s
lee
p
ap
n
ea
.
W
e
cr
ea
te
class
i
f
icatio
n
m
o
d
el
b
ased
o
n
t
h
e
d
ata
o
b
tain
ed
f
r
o
m
E
C
G
s
i
g
n
al.
I
n
t
h
is
r
esear
ch
,
we
id
en
ti
f
y
th
e
s
leep
ap
n
ea
u
n
ti
l
4
class
es,
i.e
.
n
o
n
-
s
leep
ap
n
ea
,
h
y
p
o
ap
n
e
a,
o
b
s
tr
u
cti
v
e
ap
n
ea
,
an
d
ce
n
tr
al
ap
n
ea
.
Fig
u
r
e
1
s
h
o
ws
th
e
m
eth
o
d
o
lo
g
y
f
lo
w
c
h
ar
t
o
f
th
e
r
esear
ch
.
T
h
e
n
e
x
t
s
u
b
s
ec
tio
n
p
r
esen
t
s
ab
o
u
t
th
e
d
etail
o
f
ev
er
y
s
tep
in
t
h
e
f
lo
w
c
h
ar
t,
s
tar
ted
f
r
o
m
d
a
ta
co
llectio
n
,
d
ata
p
r
e
-
p
r
o
ce
s
s
i
n
g
,
f
ea
tu
r
e
e
x
tr
ac
tio
n
,
cl
ass
i
f
icatio
n
m
o
d
el
d
ev
elo
p
m
en
t a
n
d
p
er
f
o
r
m
a
n
ce
ev
alu
at
io
n
.
Fig
u
r
e
1
.
R
esear
ch
m
et
h
o
d
o
lo
g
y
2
.
1
.
Da
t
a
co
llect
io
n
A
t
t
h
is
s
tag
e
t
h
e
d
ata
co
llected
w
h
er
e
th
e
d
ata
u
s
ed
is
MI
T
-
B
I
H
P
o
ly
s
o
m
n
o
g
r
ap
h
ic
Data
b
ase
(
s
lp
d
b
)
[
1
2
]
o
b
tain
ed
f
r
o
m
h
ttp
s
:/
/
p
h
y
s
io
n
et.
o
r
g
.
T
h
is
d
ata
co
n
tai
n
s
a
co
llectio
n
o
f
r
ec
o
r
d
in
g
s
o
f
s
e
v
er
al
p
h
y
s
io
lo
g
ical
s
i
g
n
als
o
f
o
b
j
ec
ts
d
u
r
in
g
s
leep
,
ie
E
C
G,
E
E
G,
b
lo
o
d
p
r
ess
u
r
e
an
d
r
esp
ir
ato
r
y
s
i
g
n
als,
a
n
d
ca
lib
r
atio
n
co
n
s
ta
n
ts
,
t
h
e
len
g
th
o
f
th
e
r
ec
o
r
d
in
g
,
a
g
e,
g
en
d
er
,
an
d
w
e
ig
h
t.
T
h
e
d
ata
u
s
ed
co
m
e
s
f
r
o
m
m
ale
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
8
,
No
.
5
,
Octo
b
er
2
0
1
8
:
3
9
40
–
3
9
4
8
3942
s
leep
r
ec
o
r
d
s
,
ag
ed
3
2
-
5
6
y
e
ar
s
o
ld
(
av
er
ag
e
4
3
y
ea
r
s
o
ld
)
,
w
ei
g
h
t
8
9
-
1
5
2
k
g
(
av
er
a
g
e
1
1
9
k
g
)
.
T
h
e
d
ata
co
n
s
is
ts
o
f
1
8
r
ec
o
r
d
in
g
s
o
f
1
6
p
eo
p
le
w
h
o
h
a
v
e
d
if
f
er
e
n
t
d
u
r
atio
n
s
o
f
m
ea
s
u
r
e
m
en
t
.
T
h
en
,
ev
er
y
3
0
s
ec
o
n
d
s
o
f
d
u
r
atio
n
,
it
w
as
m
ad
e
i
n
to
1
s
a
m
p
le
d
ata
th
a
t
w
il
l p
r
o
ce
ed
to
th
e
p
r
e
-
p
r
o
ce
s
s
in
g
p
h
ase
o
f
t
h
e
d
ata.
T
h
e
d
ata
is
ab
o
u
t
t
h
e
R
R
i
n
ter
v
a
l
an
d
S
leep
ap
n
ea
an
n
o
tatio
n
s
.
T
ab
le
1
s
h
o
w
s
a
m
p
les
o
f
d
ata
w
h
ic
h
h
ad
b
ee
n
d
iv
id
ed
in
to
3
0
s
ec
o
n
d
s
an
d
as
d
ata
u
s
ed
to
o
b
tain
HR
V
f
ea
t
u
r
es
.
Fig
u
r
e
2
s
h
o
w
s
o
n
e
o
f
t
h
e
s
i
g
n
als
f
r
o
m
t
h
e
MI
T
-
B
I
H
Po
ly
s
o
m
n
o
g
r
ap
h
ic
Da
tab
ase
(
s
lp
0
1
a)
d
ata
to
b
e
s
ep
ar
at
ed
ev
er
y
3
0
s
ec
o
n
d
s
.
T
ab
le
1
.
Sleep
A
p
n
ea
Data
s
et
s
D
a
t
a
D
u
r
a
t
i
o
n
N
u
mb
e
r
o
f
samp
l
e
s
(
h
o
u
r
-
mi
n
u
t
e
s)
sl
p
0
1
a
2
H
2
4
0
sl
p
0
1
b
3
H
3
6
0
sl
p
0
2
a
3
H
3
6
0
sl
p
0
2
b
2
H
1
5
M
2
7
0
sl
p
0
3
6
H
7
2
0
sl
p
0
4
6
H
7
2
0
sl
p
1
4
6
H
7
2
0
sl
p
1
6
6
H
7
2
0
sl
p
3
2
5
H
2
0
M
6
4
0
sl
p
3
7
5
H
5
0
M
7
0
0
sl
p
4
1
6
H
3
0
M
7
8
0
sl
p
4
5
6
H
2
0
M
7
6
0
sl
p
4
8
6
H
2
0
M
7
6
0
sl
p
5
9
4
H
4
8
0
sl
p
6
0
5
H
5
5
M
7
1
0
sl
p
6
1
6
H
1
0
M
7
4
0
sl
p
6
6
3
H
4
0
M
4
4
0
sl
p
6
7
x
1
H
1
7
M
1
5
4
T
o
t
a
l
o
f
S
a
mp
l
e
1
0
2
7
4
Fig
u
r
e
2
.
Sa
m
p
le
o
f
E
C
G
s
i
g
n
al
u
s
ed
f
o
r
s
leep
ap
n
ea
id
en
t
if
i
ca
tio
n
2
.
2
.
Da
t
a
pre
-
pro
ce
s
s
ing
T
h
e
p
r
e
-
p
r
o
ce
s
s
in
g
s
ta
g
e
i
s
t
h
e
d
is
p
o
s
al
s
ta
g
e
o
f
E
C
G
r
ec
o
r
d
in
g
d
ata
(
R
R
in
ter
v
als
an
d
s
l
ee
p
ap
n
ea
an
n
o
tatio
n
s
)
t
h
at
ar
e
o
u
t
o
f
s
y
n
c
in
o
r
d
er
to
o
b
tain
th
e
v
al
id
d
ata
.
I
n
th
i
s
s
tag
e,
w
e
r
e
m
o
v
e
d
ata
s
lp
0
3
an
d
s
lp
6
0
b
ec
au
s
e
th
e
d
ata
ar
e
o
u
t
o
f
s
y
n
c.
T
h
en
all
d
ata
f
r
o
m
t
h
e
p
r
e
-
p
r
o
ce
s
s
in
g
r
es
u
lt
s
is
en
ter
ed
in
to
th
e
f
o
r
m
u
las to
g
e
t th
e
H
R
V
f
ea
tu
r
e
s.
2
.
3
.
F
ea
t
ure
ex
t
ra
ct
io
n
I
n
th
i
s
p
r
o
ce
s
s
,
d
ata
f
r
o
m
p
r
e
-
p
r
o
ce
s
s
i
n
g
r
es
u
lt
is
p
r
o
ce
s
s
ed
to
o
b
tain
HR
V
f
ea
t
u
r
es.
W
e
em
p
lo
y
f
o
u
r
tec
h
n
iq
u
e
s
i
n
t
h
i
s
p
ap
er
,
i.e
.
ti
m
e
d
o
m
ai
n
,
g
eo
m
etr
ical,
p
o
in
ca
r
e,
an
d
f
r
eq
u
e
n
c
y
d
o
m
ain
[
1
3
]
,
[
1
4
]
.
T
h
e
f
ea
t
u
r
es
co
n
tai
n
SD
NN,
R
MS
DD,
NN5
0
,
p
NN5
0
,
Me
an
R
R
,
HR
V
I
n
d
ex
,
SD1
,
SD2
,
S
D1
/
SD2
,
T
P
,
VL
F,
L
F,
HF,
L
F
/
H
F,
L
F
n
o
r
m
,
H
F
n
o
r
m
.
T
im
e
Do
m
a
in
is
d
e
r
iv
ed
f
r
o
m
E
C
G
Si
g
n
al
Data
in
th
e
f
o
r
m
o
f
R
R
in
ter
v
a
l,
f
r
eq
u
e
n
c
y
Do
m
ain
o
f
to
tal
s
p
ec
tr
u
m
o
f
ea
ch
b
ea
t
s
ep
ar
ated
in
in
d
ex
to
g
en
er
ate
P
SD
.
T
h
er
e
ar
e
1
8
f
ea
t
u
r
es
u
s
ed
in
t
h
is
r
esear
c
h
as
s
h
o
w
n
b
y
T
ab
le
2
.
W
e
p
er
f
o
r
m
f
ea
t
u
r
e
ex
tr
ac
tio
n
u
s
i
n
g
m
at
lab
.
Fig
u
r
e
3
s
h
o
w
s
t
h
e
v
al
u
e
o
f
f
ea
t
u
r
e
ex
tr
ac
tio
n
w
it
h
ti
m
e
d
o
m
ai
n
m
e
th
o
d
.
Fig
u
r
e
4
s
h
o
w
s
th
e
r
esu
lts
o
f
f
ea
t
u
r
e
ex
tr
ac
tio
n
w
it
h
f
r
eq
u
en
c
y
d
o
m
ai
n
tec
h
n
iq
u
es,
w
h
ile
Fi
g
u
r
e
5
s
h
o
w
s
th
e
f
ea
t
u
r
e
ex
tr
ac
tio
n
r
es
u
lts
w
it
h
p
o
in
ca
r
e
tech
n
iq
u
es.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2
0
8
8
-
8708
S
leep
A
p
n
e
a
I
d
en
tifi
ca
tio
n
u
s
i
n
g
HR
V
F
ea
t
u
r
es o
f E
C
G
S
ig
n
a
ls
(
B
illy S
u
lis
tyo
)
3943
T
ab
le
2
.
HR
V
Featu
r
es
L
is
t
N
o
F
e
a
t
u
r
e
M
e
t
h
o
d
D
e
scri
p
t
i
o
n
Eq
u
a
t
i
o
n
1
A
V
N
N
T
i
me
D
o
mai
n
T
h
e
a
v
e
r
a
g
e
o
f
a
l
l
N
N
(
o
r
RR
)
i
n
t
e
r
v
a
l
s
,
∑
2
S
D
N
N
T
i
me
D
o
mai
n
T
h
e
st
a
n
d
a
r
d
d
e
v
i
a
t
i
o
n
o
f
a
l
l
N
N
(
o
r
RR
)
i
n
t
e
r
v
a
l
s
√
∑
(
̅
̅
̅
̅
)
3
R
M
S
S
D
T
i
me
D
o
mai
n
T
h
e
sq
u
a
r
e
r
o
o
t
o
f
t
h
e
a
v
e
r
a
g
e
o
f
t
h
e
su
m o
f
t
h
e
s
q
u
a
r
e
s o
f
d
i
f
f
e
r
e
n
c
e
s b
e
t
w
e
e
n
a
d
j
a
c
e
n
t
R
R
i
n
t
e
r
v
a
l
s
√
∑
(
)
4
S
D
S
D
T
i
me
D
o
mai
n
S
t
a
n
d
a
r
d
d
e
v
i
a
t
i
o
n
o
f
d
i
f
f
e
r
e
n
c
e
s b
e
t
w
e
e
n
a
d
j
a
c
e
n
t
R
R
i
n
t
e
r
v
a
l
s
-
5
N
N
5
0
T
i
me
D
o
mai
n
T
h
e
c
o
u
n
t
o
f
a
d
j
a
c
e
n
t
N
N
(
o
r
RR
)
i
n
t
e
r
v
a
l
s
d
i
f
f
e
r
e
n
c
e
s t
h
a
t
a
r
e
mo
r
e
t
h
a
n
5
0
ms
(
)
6
p
N
N
5
0
T
i
me
D
o
mai
n
T
h
e
d
i
v
i
si
o
n
o
f
N
N
5
0
b
y
t
o
t
a
l
o
f
a
l
l
R
R
i
n
t
e
r
v
a
l
s mi
n
u
s o
n
e
t
i
me
s
1
0
0
7
H
R
V
T
r
i
a
n
g
u
l
a
r
I
n
d
e
x
G
e
o
m
e
t
r
i
c
a
l
T
h
e
t
o
t
a
l
n
u
m
b
e
r
o
f
R
R
i
n
t
e
r
v
a
l
s d
i
v
i
d
e
d
b
y
t
h
e
p
e
a
k
o
f
h
i
s
t
o
g
r
a
m c
r
e
a
t
e
d
f
r
o
m R
R
i
n
t
e
r
v
a
l
s d
a
t
a
w
i
t
h
7
.
8
1
2
5
b
i
n
si
z
e
-
8
S
D
1
P
o
i
n
c
a
r
e
T
h
e
st
a
n
d
a
r
d
d
e
v
i
a
t
i
o
n
o
f
p
o
i
n
t
s
p
e
r
p
e
n
d
i
c
u
l
a
r
t
o
t
h
e
a
x
i
s o
f
l
i
n
e
-
of
-
i
d
e
n
t
i
t
y
9
S
D
2
P
o
i
n
c
a
r
e
T
h
e
st
a
n
d
a
r
d
d
e
v
i
a
t
i
o
n
o
f
p
o
i
n
t
s
a
l
o
n
g
t
h
e
a
x
i
s o
f
l
i
n
e
-
of
-
i
d
e
n
t
i
t
y
10
S
D
1
S
D
2
R
a
t
i
o
P
o
i
n
c
a
r
e
R
a
t
i
o
o
f
S
D
1
a
n
d
S
D
2
,
11
S
P
o
i
n
c
a
r
e
A
r
e
a
o
f
e
l
l
i
p
se
12
TP
F
r
e
q
u
e
n
c
y
D
o
mai
n
T
o
t
a
l
p
o
w
e
r
-
13
V
L
F
F
r
e
q
u
e
n
c
y
D
o
mai
n
T
o
t
a
l
p
o
w
e
r
o
f
0
t
o
0
.
0
4
H
z
-
14
LF
F
r
e
q
u
e
n
c
y
D
o
mai
n
T
o
t
a
l
p
o
w
e
r
o
f
0
.
0
4
t
o
0
.
1
5
H
z
-
15
HF
F
r
e
q
u
e
n
c
y
D
o
mai
n
T
o
t
a
l
p
o
w
e
r
o
f
0
.
1
5
t
o
0
.
4
H
z
-
16
L
F
H
F
R
a
t
i
o
F
r
e
q
u
e
n
c
y
D
o
mai
n
R
a
t
i
o
o
f
L
F
a
n
d
H
F
-
17
L
F
n
o
r
m
F
r
e
q
u
e
n
c
y
D
o
mai
n
N
o
r
mal
i
z
e
d
L
F
1
1
8
H
F
n
o
r
m
F
r
e
q
u
e
n
c
y
D
o
mai
n
N
o
r
mal
i
z
e
d
H
F
Fig
u
r
e
3
.
R
esu
lt
o
f
ti
m
e
d
o
m
ai
n
&
g
eo
m
etr
ica
l
f
ea
t
u
r
es
Fig
u
r
e
4
.
R
esu
lt o
f
f
r
eq
u
en
c
y
d
o
m
ai
n
tec
h
n
iq
u
es
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
8
,
No
.
5
,
Octo
b
er
2
0
1
8
:
3
9
40
–
3
9
4
8
3944
Fig
u
r
e
5
.
Featu
r
e
E
x
tr
ac
tio
n
with
p
o
in
ca
r
e
tech
n
iq
u
es
2
.
4
.
Cla
s
s
if
ica
t
io
n
p
ro
ce
s
s
I
n
th
i
s
p
ap
er
,
w
e
ev
al
u
ate
f
o
llo
w
i
n
g
f
o
u
r
cla
s
s
i
f
icatio
n
m
e
th
o
d
s
in
cla
s
s
i
f
y
i
n
g
s
leep
ap
n
ea
.
A
ll
o
f
th
ese
m
et
h
o
d
ar
e
th
e
m
o
s
t
w
el
l
-
k
n
o
w
n
clas
s
i
f
icatio
n
m
et
h
o
d
[
1
5
]
,
i.e
.
:
a.
A
r
ti
f
icial
Ne
u
r
al
Net
w
o
r
k
(
ANN)
is
an
alg
o
r
ith
m
w
h
er
e
th
er
e
is
a
n
et
w
o
r
k
o
f
s
m
all
p
r
o
ce
s
s
u
n
it
s
th
at
ar
e
m
o
d
eled
o
r
co
n
s
tr
u
cted
b
ased
o
n
th
e
b
eh
av
io
r
o
f
h
u
m
a
n
n
e
u
r
al
n
et
w
o
r
k
s
[
1
6
]
.
T
h
e
f
u
n
c
ti
o
n
o
f
th
e
n
e
u
r
al
n
et
w
o
r
k
is
t
h
e
clas
s
i
f
icatio
n
o
f
p
atter
n
s
,
p
atter
n
m
ap
p
in
g
o
b
tain
ed
f
r
o
m
i
n
p
u
t
s
in
to
n
e
w
p
atter
n
s
o
f
o
u
tp
u
t,
m
ap
p
in
g
o
f
s
i
m
i
lar
p
atter
n
s
,
a
n
d
p
r
o
b
le
m
s
o
l
v
er
s
[
1
7
]
.
T
h
is
A
N
N
is
co
m
m
o
n
l
y
a
p
p
lied
f
o
r
n
o
is
e
id
en
ti
f
icatio
n
,
w
a
v
e
an
al
y
s
is
,
s
p
ee
d
an
al
y
s
is
,
r
eser
v
o
ir
ch
ar
a
cter
izatio
n
an
d
etc
.
b.
T
h
e
Naiv
e
B
a
y
es
C
lass
if
ier
i
s
a
s
i
m
p
le
p
r
o
b
ab
ilit
y
class
if
ic
atio
n
w
h
ich
u
s
e
s
B
a
y
es
's
th
e
o
r
em
w
i
th
h
i
g
h
in
d
ep
en
d
en
cy
as
s
u
m
p
tio
n
s
[
1
8
]
.
Sin
ce
v
ar
iab
les
ar
e
as
s
u
m
ed
to
b
e
in
d
ep
en
d
en
t
s
o
t
h
at
t
h
e
v
ar
ian
ce
o
f
a
v
ar
iab
le
i
n
a
c
lass
is
r
eq
u
ir
ed
t
o
d
eter
m
in
e
th
e
clas
s
i
f
icatio
n
.
T
h
e
ad
v
an
tag
e
o
f
u
s
in
g
th
i
s
m
et
h
o
d
is
th
at
i
t
r
eq
u
ir
es
o
n
l
y
a
f
e
w
a
m
o
u
n
t
o
f
tr
ai
n
i
n
g
d
ata
to
d
eter
m
i
n
e
t
h
e
r
eq
u
ir
ed
e
s
ti
m
at
io
n
p
ar
a
m
eter
s
i
n
th
e
class
i
f
icatio
n
p
r
o
ce
s
s
.
c.
K
-
Nea
r
est
Ne
ig
h
b
o
r
(
K
-
NN)
i
s
o
n
e
o
f
a
s
u
p
er
v
is
ed
al
g
o
r
ith
m
w
h
er
e
g
r
o
u
p
in
g
o
f
a
n
o
b
j
ec
t
is
class
if
ied
b
y
th
e
m
aj
o
r
ity
o
f
th
e
n
ea
r
est
c
ateg
o
r
y
.
T
h
e
g
o
al
is
to
class
if
y
n
e
w
o
b
j
ec
ts
b
ased
o
n
t
h
e
attr
ib
u
tes
an
d
s
a
m
p
les
o
f
th
e
d
ata
[
1
9
]
.
T
h
e
K
-
NN
alg
o
r
it
h
m
w
o
r
k
s
b
ased
o
n
th
e
m
in
i
m
u
m
d
is
ta
n
ce
f
r
o
m
t
h
e
n
e
w
d
ata
to
th
e
s
a
m
p
les
d
ata
to
d
eter
m
in
e
th
e
K
n
u
m
b
er
o
f
n
ea
r
est
n
ei
g
h
b
o
r
s
.
Fro
m
h
er
e
w
e
o
b
tain
t
h
e
m
aj
o
r
ity
v
alu
e
u
s
ed
as t
h
e
p
r
ed
icted
r
esu
lt o
f
th
e
n
e
w
d
ata.
d.
Su
p
p
o
r
t
Vec
to
r
Ma
ch
in
e
(
SVM)
is
a
tech
n
iq
u
e
f
o
r
m
a
k
in
g
p
r
ed
ictio
n
s
in
b
o
th
cla
s
s
i
f
icatio
n
an
d
r
eg
r
ess
io
n
ca
s
e
s
.
T
h
e
i
n
te
n
tio
n
o
f
S
VM
i
s
to
f
i
n
d
a
n
o
p
ti
m
al
s
ep
ar
atin
g
h
y
p
er
p
lan
e
(
O
S
H)
,
w
h
ic
h
is
th
e
lar
g
est
m
ar
g
i
n
b
et
w
ee
n
t
h
e
t
wo
d
atasets
.
I
t
ca
n
b
e
f
o
u
n
d
b
y
m
a
x
i
m
izi
n
g
t
h
e
m
ar
g
i
n
b
et
wee
n
t
h
e
cla
s
s
e
s
.
Firstl
y
,
SV
M
tr
a
n
s
f
o
r
m
s
i
n
p
u
t
d
ata
i
n
to
a
h
i
g
h
er
d
i
m
e
n
s
io
n
al
s
p
ac
e
b
y
u
s
in
g
a
k
er
n
el
f
u
n
ct
io
n
.
T
h
en
,
SVM
co
n
s
tr
u
c
ts
a
li
n
ea
r
O
SH
b
et
w
ee
n
th
e
t
w
o
cla
s
s
e
s
i
n
th
e
tr
an
s
f
o
r
m
ed
s
p
ac
e.
T
h
e
n
ea
r
est
d
ata
v
ec
to
r
s
to
th
e
co
n
s
tr
u
cted
lin
e
i
n
t
h
e
tr
an
s
f
o
r
m
ed
s
p
ac
e
ar
e
ca
lled
as th
e
s
u
p
p
o
r
t v
ec
to
r
s
[
1
0
]
.
2
.
5
.
P
er
f
o
r
m
a
nce
e
v
a
lua
t
io
n
T
h
e
d
ata
is
d
iv
id
ed
in
to
2
:
7
0
%
tr
ain
in
g
d
ata
an
d
3
0
%
d
ata
test
in
g
to
b
u
ild
th
e
m
o
d
el
o
f
th
e
class
i
f
icatio
n
to
b
e
test
ed
.
T
h
e
r
esu
lt
d
ata
o
f
th
e
e
x
tr
ac
t
f
e
atu
r
e
w
ill
b
e
r
an
d
o
m
ized
to
class
i
f
y
t
h
e
A
NN,
KNN,
N
-
B
a
y
e
s
an
d
lin
ea
r
SV
M
class
i
f
icatio
n
m
et
h
o
d
s.
W
e
p
er
f
o
r
m
th
e
cla
s
s
i
f
icatio
n
w
it
h
r
ap
id
m
i
n
er
.
T
h
e
ex
p
er
i
m
e
n
ts
ar
e
co
n
d
u
c
ted
s
ev
er
al
ti
m
es
f
o
r
ea
ch
o
f
th
e
f
o
ll
o
w
i
n
g
cla
s
s
e
s
:
a.
2
class
es: Sleep
ap
n
ea
a
n
d
n
o
n
-
s
leep
ap
n
ea
b.
3
class
es:
n
o
n
-
s
leep
ap
n
ea
/
h
y
p
o
-
ap
n
ea
/o
b
s
tr
u
cti
v
e
-
ap
n
ea
c.
4
class
es:
n
o
n
-
s
leep
ap
n
ea
/
h
y
p
o
-
ap
n
ea
/o
b
s
tr
u
cti
v
e
-
ap
n
ea
/ce
n
tr
al
-
ap
n
ea
W
e
p
er
f
o
r
m
clas
s
i
f
icatio
n
u
s
i
n
g
s
u
b
j
ec
t
-
s
p
ec
i
f
ic
s
c
h
e
m
e
an
d
s
u
b
j
ec
t
-
in
d
ep
en
d
e
n
t
s
c
h
e
m
e
[
2
0
]
.
T
h
e
d
if
f
er
e
n
ce
b
et
w
ee
n
th
e
m
is
a
b
o
u
t
th
e
s
elec
tio
n
o
f
tr
ai
n
i
n
g
an
d
test
in
g
s
ets.
I
n
s
u
b
j
ec
t
-
s
p
ec
if
ic
s
ch
e
m
e,
th
e
tr
ain
i
n
g
an
d
te
s
ti
n
g
s
et
s
ar
e
s
el
ec
ted
f
r
o
m
th
e
s
a
m
e
r
ec
o
r
d
b
ef
o
r
e
b
ein
g
in
p
u
tted
to
cla
s
s
if
ier
m
o
d
el.
On
t
h
e
o
th
er
h
an
d
,
in
s
u
b
j
ec
t
-
i
n
d
ep
en
d
en
t
s
c
h
e
m
e,
th
e
tr
ai
n
i
n
g
a
n
d
test
in
g
s
ets
ar
e
co
m
b
i
n
ed
f
r
o
m
al
l
r
ec
o
r
d
s
.
T
h
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2
0
8
8
-
8708
S
leep
A
p
n
e
a
I
d
en
tifi
ca
tio
n
u
s
i
n
g
HR
V
F
ea
t
u
r
es o
f E
C
G
S
ig
n
a
ls
(
B
illy S
u
lis
tyo
)
3945
s
u
b
j
ec
t
in
d
ep
en
d
e
n
t
s
ch
e
m
e
i
s
m
o
r
e
p
r
ac
tical
[
2
0
]
.
Ho
w
ev
er
s
u
b
j
ec
t
s
p
ec
i
f
ic
s
c
h
e
m
e
m
o
r
e
u
s
e
f
u
l
f
o
r
m
u
lt
i
-
n
ig
h
t i
n
v
esti
g
atio
n
s
a
n
d
ev
al
u
atin
g
th
e
i
m
p
o
r
tan
ce
o
f
ea
c
h
f
ea
tu
r
e
f
o
r
s
leep
s
ta
g
i
n
g
.
3.
RE
SU
L
T
S
A
ND
D
I
SCU
SS
I
O
N
Firstl
y
,
w
e
p
er
f
o
r
m
clas
s
i
f
ica
tio
n
o
f
s
leep
ap
n
ea
f
o
r
2
class
es
o
f
class
if
ica
tio
n
.
A
s
m
e
n
tio
n
ed
i
n
S
ec
tio
n
2
,
w
e
e
v
al
u
ate
t
h
e
p
er
f
o
r
m
an
ce
o
f
4
clas
s
i
f
icatio
n
m
et
h
o
d
,
i.e
.
A
NN,
KNN,
N
-
B
ay
e
s
,
li
n
ea
r
SVM.
T
ab
le
3
s
h
o
w
s
th
e
r
esu
lt
o
f
2
class
es
o
f
clas
s
i
f
icatio
n
w
i
th
s
u
b
j
ec
t
-
s
p
ec
if
ic
s
ch
e
m
e.
Firstl
y
,
w
e
ca
lcu
late
th
e
ac
cu
r
ac
y
f
o
r
ev
er
y
s
u
b
j
ec
t
(
to
tal
1
6
s
u
b
j
ec
ts
u
s
ed
i
n
t
h
i
s
e
x
p
er
im
e
n
t)
a
n
d
p
er
f
o
r
m
m
ea
n
o
p
er
atio
n
at
th
e
en
d
to
co
m
p
u
te
th
e
a
v
er
ag
e
ac
c
u
r
ac
y
.
T
ab
le
3
s
h
o
w
s
th
at
t
h
e
S
VM
lin
ea
r
s
h
o
w
s
t
h
e
m
o
s
t
s
u
p
er
io
r
p
er
f
o
r
m
a
n
c
e
a
m
o
n
g
th
e
m
.
S
VM
lin
ea
r
ac
h
i
ev
es 7
5
.
8
% a
cc
u
r
ac
y
,
al
m
o
s
t
3
%
m
o
r
e
th
an
t
h
e
s
ec
o
n
d
o
n
e,
i.e
.
A
NN.
T
ab
le
3
.
A
cc
u
r
ac
y
f
o
r
2
C
lass
es C
las
s
i
f
icatio
n
w
it
h
Su
b
j
ec
t
-
s
p
ec
if
ic
Sc
h
e
m
e
D
a
t
a
M
e
t
h
o
d
AN
N
K
N
N
N
-
Ba
y
e
s
S
VM
(
l
i
n
e
a
r)
S
l
p
0
1
a
7
7
.
7
8
%
7
7
,
7
8
%
7
6
,
3
9
%
8
3
,
3
3
%
S
l
p
0
1
b
8
6
,
1
1
%
7
9
,
6
3
%
8
7
,
9
6
%
8
6
,
1
1
%
S
l
p
0
2
a
8
2
,
4
1
%
6
9
,
4
4
%
6
4
,
8
1
%
8
2
,
4
1
%
S
l
p
0
2
b
8
5
,
0
0
%
8
0
,
0
0
%
7
2
,
5
0
%
9
1
,
2
5
%
S
l
p
0
3
8
0
,
0
0
%
6
4
,
2
9
%
8
1
,
9
0
%
7
6
,
6
7
%
S
l
p
0
4
8
1
,
9
4
%
7
1
,
3
0
%
8
4
,
7
2
%
8
5
,
6
5
%
S
l
p
1
4
7
1
,
0
3
%
6
1
,
2
1
%
6
7
,
2
9
%
7
2
,
9
0
%
S
l
p
1
6
6
2
,
0
2
%
5
3
,
3
7
%
6
6
,
3
5
%
6
4
,
9
0
%
S
l
p
3
2
8
2
,
8
1
%
7
3
,
9
6
%
7
2
,
4
0
%
8
3
,
3
3
%
S
l
p
3
7
8
4
,
6
9
%
7
9
,
9
0
%
7
7
,
9
9
%
8
5
,
1
7
%
S
l
p
4
8
7
3
,
2
5
%
6
2
,
7
2
%
7
1
,
0
5
%
7
3
,
6
8
%
S
l
p
5
9
5
6
,
7
2
%
4
9
,
6
4
%
4
7
,
4
5
%
4
8
,
1
8
%
S
l
p
6
0
6
5
,
2
4
%
5
6
,
6
7
%
6
0
,
4
8
%
6
3
,
3
3
%
S
l
p
6
1
6
0
,
1
9
%
6
0
,
6
5
%
7
3
,
1
5
%
6
8
,
5
2
%
S
l
p
6
6
6
8
,
9
4
%
6
4
,
3
9
%
7
5
,
7
6
%
8
1
,
0
6
%
S
l
p
6
7
x
6
5
,
2
2
%
4
7
,
8
3
%
7
3
,
9
1
%
6
7
,
3
9
%
M
e
a
n
7
3
,
9
6
%
6
5
,
8
0
%
7
2
,
1
3
%
7
5
,
8
7
%
Fig
u
r
e
6
a
n
d
Fi
g
u
r
e
7
s
h
o
w
s
t
h
e
r
es
u
lt
o
f
c
lass
if
icatio
n
f
o
r
2
,
3
,
an
d
4
clas
s
es
w
it
h
s
u
b
j
ec
t
-
s
p
ec
i
f
ic
s
ch
e
m
e
an
d
s
u
b
j
ec
t
-
i
n
d
ep
en
d
en
t
s
c
h
e
m
e,
r
esp
ec
tiv
el
y
.
W
e
ca
n
o
b
s
er
v
e
in
F
i
g
u
r
e
6
th
at
SVM
ac
h
ie
v
es
t
h
e
b
est
p
er
f
o
r
m
a
n
ce
a
m
o
n
g
all
m
et
h
o
d
w
ith
7
5
.
8
7
%,
7
3
.
5
8
%,
an
d
7
1
.
5
8
%
f
o
r
2
,
3
,
an
d
4
c
lass
s
e
s
,
r
esp
ec
ti
v
el
y
.
W
h
ile
A
NN
b
ec
o
m
es
t
h
e
s
ec
o
n
d
b
est
w
it
h
p
er
f
o
r
m
a
n
c
e
lo
w
er
ab
o
u
t
1
-
2
%
co
m
p
a
r
ed
to
th
e
SVM.
I
n
ter
esti
n
g
l
y
,
as
s
h
o
w
n
b
y
F
i
g
u
r
e
7
,
it
s
h
o
w
s
th
a
t
th
e
p
er
f
o
r
m
a
n
ce
o
f
A
NN
s
li
g
h
tl
y
b
et
ter
th
an
SVM
f
o
r
3
an
d
4
c
lass
es
clas
s
i
f
icatio
n
.
B
ased
o
n
th
is
r
es
u
lt
it
s
h
o
w
s
t
h
at
in
o
v
er
all,
f
o
r
s
u
b
j
ec
t
-
in
d
ep
en
d
en
t
s
c
h
e
m
e
an
d
s
u
b
j
ec
t
-
s
p
ec
i
f
ic
s
c
h
e
m
e,
SVM
s
h
o
w
s
t
h
e
b
est
p
er
f
o
r
m
a
n
ce
a
m
o
n
g
t
h
e
m
.
T
h
e
r
ea
s
o
n
m
a
y
b
e
d
u
e
to
th
e
n
at
u
r
e
o
f
SVM
th
at
p
er
f
o
r
m
s
d
ata
s
elec
tio
n
b
ef
o
r
e
d
o
in
g
class
if
ica
tio
n
.
T
h
er
e
it
r
esu
lts
in
b
etter
ac
cu
r
ac
y
p
er
f
o
r
m
a
n
ce
.
Ho
w
e
v
er
,
th
e
an
o
m
a
l
y
i
n
s
u
b
j
ec
t
in
d
ep
en
d
en
t
s
ch
e
m
e
w
it
h
3
an
d
4
class
es
class
i
f
icatio
n
s
h
o
ws
th
e
ac
cu
r
ac
y
r
esu
lt so
m
e
ti
m
es
also
in
f
lu
e
n
ce
d
b
y
t
h
e
d
is
tr
ib
u
tio
n
o
f
d
ata
tr
ain
i
n
g
an
d
test
i
n
g
.
Fro
m
Fi
g
u
r
e
6
an
d
Fi
g
u
r
e
7
,
w
e
ca
n
also
ev
a
lu
ate
h
o
w
g
o
o
d
th
e
g
en
er
aliza
t
io
n
ca
p
ab
ili
t
y
o
f
ea
c
h
m
et
h
o
d
is
.
Fo
r
ex
a
m
p
le,
th
e
s
e
r
esu
lts
s
h
o
w
s
th
at
ANN
al
g
o
r
ith
m
h
as
g
o
o
d
g
en
er
aliza
t
io
n
ca
p
ab
ilit
y
b
ec
a
u
s
e
th
e
d
ec
r
ea
s
e
o
f
ac
cu
r
ac
y
b
et
w
ee
n
s
u
b
j
ec
t
-
s
p
ec
i
f
ic
a
n
d
s
u
b
j
ec
t
in
d
ep
en
d
en
t
s
c
h
e
m
e
is
t
h
e
lo
w
est
an
d
m
o
s
t
co
n
s
ta
n
t
a
m
o
n
g
all
m
et
h
o
d
,
i.e
.
ar
o
u
n
d
4
%
f
o
r
2
,
3
,
4
class
es
o
f
class
i
f
icat
io
n
.
SVM
e
v
en
th
o
u
g
h
s
h
o
w
s
t
h
e
b
est
p
er
f
o
r
m
a
n
ce
i
n
o
v
er
all
a
s
e
x
p
lain
ed
i
n
th
e
p
r
ev
io
u
s
p
ar
ag
r
ap
h
,
it
s
u
f
f
er
s
8
%
d
ec
r
e
ase
o
f
ac
cu
r
a
c
y
i
n
3
an
d
4
class
es
o
f
class
if
ica
tio
n
.
W
h
ile
N
-
B
a
y
es
s
h
o
w
s
t
h
e
w
o
r
s
t
g
en
er
aliza
tio
n
ca
p
ab
ilit
y
b
y
s
u
f
f
er
s
al
m
o
s
t
2
0
% o
f
d
ec
r
ea
s
e
in
4
class
es o
f
clas
s
if
icatio
n
ac
c
u
r
ac
y
.
On
t
h
e
o
th
er
e
x
p
er
i
m
e
n
t
s
,
w
e
ev
al
u
ate
w
h
ic
h
f
ea
t
u
r
es
ex
tr
ac
tio
n
tec
h
n
iq
u
es
h
as
b
ette
r
p
er
f
o
r
m
an
c
e
f
o
r
clas
s
if
icatio
n
in
ev
er
y
cla
s
s
if
ica
tio
n
m
et
h
o
d
.
T
h
e
r
esu
lt
is
s
h
o
w
n
b
y
Fi
g
u
r
e
8
.
T
h
e
ti
m
e
d
o
m
ai
n
f
ea
t
u
r
es
s
h
o
w
s
d
o
m
in
a
n
t
p
er
f
o
r
m
an
ce
w
i
th
ANN
an
d
S
VM
m
eth
o
d
.
W
h
ile,
p
o
in
ca
r
e
tech
n
iq
u
es
an
d
f
r
eq
u
en
c
y
-
d
o
m
ai
n
tech
n
iq
u
e
s
s
h
o
w
s
th
e
b
est
p
er
f
o
r
m
an
ce
w
it
h
N
-
b
ay
es
m
e
th
o
d
an
d
KNN
m
et
h
o
d
,
r
esp
ec
tiv
el
y
.
T
h
is
r
esu
lt
s
m
ea
n
s
e
v
er
y
f
ea
tu
r
e
ex
tr
ac
tio
n
m
et
h
o
d
h
as
d
if
f
er
en
t
p
er
f
o
r
m
a
n
ce
in
ev
er
y
cla
s
s
i
f
icatio
n
m
et
h
o
d
.
Ho
w
e
v
er
y
,
f
o
r
s
leep
ap
n
ea
ca
s
e,
T
h
e
tim
e
d
o
m
ai
n
f
ea
tu
r
e
s
s
h
o
w
s
t
h
e
b
est p
er
f
o
r
m
a
n
ce
s
i
n
o
v
e
r
all.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
8
,
No
.
5
,
Octo
b
er
2
0
1
8
:
3
9
40
–
3
9
4
8
3946
Fig
u
r
e
6
.
A
cc
u
r
ac
y
p
er
f
o
r
m
a
n
ce
ev
alu
at
io
n
w
it
h
s
u
b
j
ec
t
-
s
p
ec
i
f
ic
s
c
h
e
m
e
Fig
u
r
e
7
.
A
cc
u
r
ac
y
p
er
f
o
r
m
a
n
ce
ev
alu
at
io
n
w
it
h
s
u
b
j
ec
t
-
i
n
d
ep
en
d
en
t
s
c
h
e
m
e
Fig
u
r
e
8
.
Featu
r
e
ex
tr
ac
tio
n
m
eth
o
d
co
m
p
ar
is
o
n
Fin
all
y
,
w
e
p
er
f
o
r
m
a
co
m
p
a
r
is
o
n
w
it
h
t
h
e
ex
i
s
ti
n
g
p
ap
er
an
d
ca
n
b
e
s
ee
n
th
r
o
u
g
h
T
a
b
le
4
.
T
h
e
co
m
p
ar
is
o
n
is
p
er
f
o
r
m
ed
f
o
r
class
i
f
icatio
n
w
ith
2
class
e
s
.
T
ab
le
4
s
h
o
w
s
th
a
t
o
u
r
r
esu
l
ts
o
u
tp
er
f
o
r
m
s
th
e
r
esu
lt
o
f
o
th
er
w
o
r
k
b
y
T
ilm
az
an
d
E
r
az
o
w
ith
a
n
ac
cu
r
ac
y
o
f
7
5
.
8
9
%.
Fo
r
th
e
f
u
t
u
r
e,
th
e
s
leep
ap
n
ea
class
i
f
icatio
n
m
o
d
el
th
at
u
s
es
th
e
HR
V
f
ea
t
u
r
e
o
f
E
C
G
s
i
g
n
al
f
o
r
ti
m
e
d
o
m
ai
n
,
p
o
in
ca
r
e,
g
eo
m
etr
ical,
an
d
f
r
eq
u
en
c
y
d
o
m
ai
n
ca
n
p
r
o
d
u
ce
b
etter
ac
cu
r
ac
y
.
T
h
en
it
ca
n
p
r
o
d
u
ce
r
ea
l
-
ti
m
e
s
leep
aid
s
f
r
o
m
th
e
E
C
G
s
i
g
n
al
r
esu
lt
s
w
h
e
n
a
p
er
s
o
n
s
leep
s
.
T
ab
le
4
.
C
o
m
p
ar
is
o
n
w
i
th
o
t
h
er
W
o
r
k
s
A
u
t
h
o
r
Y
e
a
r
A
p
p
r
o
a
c
h
A
c
c
u
r
a
c
y
R
e
su
l
t
Y
i
l
maz
[
2
1
]
2
0
1
0
k
N
N
,
Q
D
A
,
S
V
M
7
4
.
4
%
Er
a
z
o
[
2
2
]
2
0
1
4
A
N
N
&
S
V
M
5
5
.
9
4
%
P
r
o
p
o
se
d
2
0
1
7
A
N
N
&
S
V
M
L
i
n
e
a
r
7
4
.
8
5
%
4.
CO
NCLU
SI
O
N
I
n
th
i
s
p
ap
er
,
w
e
h
av
e
p
er
f
o
r
m
ed
ev
al
u
atio
n
o
f
s
leep
ap
n
e
a
id
en
ti
f
icatio
n
u
s
in
g
H
R
V
f
ea
tu
r
es
o
f
E
C
G
s
ig
n
al.
W
e
h
a
v
e
p
er
f
o
r
m
ed
co
m
p
ar
is
o
n
o
f
w
h
ich
cla
s
s
i
f
icatio
n
m
et
h
o
d
p
er
f
o
r
m
s
b
etter
an
d
w
h
at
HR
V
f
ea
t
u
r
es s
h
o
w
s
t
h
e
b
est p
er
f
o
r
m
an
ce
f
o
r
s
leep
ap
n
ea
id
en
ti
f
i
ca
tio
n
.
W
e
p
er
f
o
r
m
th
e
clas
s
if
icatio
n
f
o
r
2
,
3
,
an
d
4
class
es
o
f
s
leep
ap
n
ea
.
Ou
r
s
i
m
u
latio
n
r
es
u
lts
s
h
o
w
s
t
h
at
th
e
li
n
ea
r
SV
M
ac
h
ie
v
e
s
th
e
b
est
ac
c
u
r
ac
y
co
m
p
ar
ed
to
t
h
e
th
r
ee
o
t
h
er
m
et
h
o
d
s
.
W
h
ile,
th
e
A
NN
m
et
h
o
d
s
h
o
w
s
t
h
e
b
e
s
t
g
en
e
r
aliza
tio
n
ca
p
ab
ilit
y
a
m
o
n
g
all
m
et
h
o
d
.
On
t
h
e
o
t
h
er
r
esu
l
ts
,
t
h
e
ti
m
e
d
o
m
ai
n
f
ea
t
u
r
es
s
h
o
w
s
t
h
e
m
o
s
t
d
o
m
in
an
t
p
er
f
o
r
m
a
n
ce
a
m
o
n
g
t
h
e
H
R
V
f
ea
tu
r
es.
At
t
h
e
en
d
,
w
e
s
h
o
w
s
h
o
w
o
u
r
w
o
r
k
s
s
h
o
w
s
s
lig
h
tl
y
b
etter
p
er
f
o
r
m
a
n
ce
co
m
p
ar
ed
to
th
e
o
t
h
er
r
ef
er
en
ce
s
.
Fo
r
t
h
e
f
u
t
u
r
e
r
esear
c
h
,
w
e
ar
e
g
o
in
g
to
e
m
p
lo
y
clas
s
i
f
icatio
n
m
eth
o
d
d
ev
elo
p
ed
i
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2
0
8
8
-
8708
S
leep
A
p
n
e
a
I
d
en
tifi
ca
tio
n
u
s
i
n
g
HR
V
F
ea
t
u
r
es o
f E
C
G
S
ig
n
a
ls
(
B
illy S
u
lis
tyo
)
3947
th
is
p
ap
er
in
to
s
leep
ap
n
ea
m
o
n
ito
r
i
n
g
p
r
o
to
t
y
p
e.
W
e
ar
e
g
o
in
g
to
b
u
i
ld
th
e
p
o
r
tab
le
an
d
co
n
tactle
s
s
p
r
o
to
ty
p
e
th
at
w
e
h
o
p
e
ca
n
h
e
lp
p
eo
p
le
t
o
d
o
s
elf
m
o
n
ito
r
in
g
o
f
s
leep
ap
n
ea
s
y
m
p
to
m
s
at
h
o
m
e.
ACK
NO
WL
E
D
G
E
M
E
NT
S
T
h
is
r
esear
ch
w
as s
u
p
p
o
r
ted
b
y
B
in
a
N
u
s
a
n
tar
a
Un
i
v
er
s
i
t
y
.
RE
F
E
R
E
NC
E
S
[1
]
W
u
e
n
KC
b
in
M
o
h
d
S
a
a
d
W
H,
e
t
a
l
.
,
“
S
tu
d
y
o
n
th
e
Eff
e
c
t
o
f
t
h
e
Am
b
ien
t
T
e
m
p
e
ra
tu
re
to
wa
rd
th
e
Qu
a
li
t
y
o
f
S
lee
p
”
,
In
t
J
El
e
c
tr
Co
mp
u
t
E
n
g
.
,
v
o
l
.
7
,
n
o
.
6
,
p
p
.
2
9
8
6
-
92
,
2
0
1
7
.
[2
]
S
u
ra
n
t
h
a
N
.
,
e
t
a
l
.
,
“
In
tern
e
t
o
f
th
in
g
s
f
o
r
S
lee
p
Qu
a
l
it
y
M
o
n
it
o
ri
n
g
S
y
ste
m
:
A
su
rv
e
y
”
,
Kn
o
wled
g
e
,
In
fo
rm
a
ti
o
n
a
n
d
Cre
a
ti
v
it
y
S
u
p
p
o
rt S
y
ste
ms
(
KICS
S
),
2
0
1
6
1
1
th
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
.
,
p
p
.
1
-
6
,
2
0
1
6
.
[3
]
M
o
rto
n
A
.
J.
,
“
Circa
d
ian
a
n
d
S
lee
p
Diso
r
d
e
r
in
H
u
n
t
in
g
to
n
’s
D
ise
a
se
”
,
Exp
Ne
u
ro
l
.
,
v
o
l.
2
4
3
,
p
p
.
34
-
44
,
2
0
1
3
.
[4
]
Qa
se
e
m
A
.
,
e
t
a
l
.
,
“
Dia
g
n
o
sis
o
f
Ob
stru
c
ti
v
e
S
lee
p
A
p
n
e
a
in
A
d
u
lt
s:
A
Cli
n
ica
l
P
ra
c
ti
c
e
G
u
id
e
li
n
e
f
ro
m
th
e
Am
e
rica
n
Co
ll
e
g
e
o
f
P
h
y
sic
ian
s
”
,
An
n
In
ter
n
M
e
d
.
,
v
o
l
.
1
6
1
,
n
o
.
3
,
p
p
.
2
1
0
-
20
,
2
0
1
4
.
[5
]
Co
w
ie M
.
R
.
,
e
t
a
l
.
,
“
A
d
a
p
ti
v
e
S
e
rv
o
-
v
e
n
ti
latio
n
f
o
r
Ce
n
tral
S
lee
p
A
p
n
e
a
in
S
y
sto
li
c
He
a
rt
F
a
il
u
re
”
,
N
En
g
l
J
M
e
d
.
,
v
o
l
.
3
7
3
,
n
o
.
1
2
,
p
p
.
1
0
9
5
-
1
0
5
,
2
0
1
5
.
[6
]
M
c
Ev
o
y
R
.
D
.
,
e
t
a
l
.
,
“
CP
A
P
f
o
r
Pr
e
v
e
n
ti
o
n
o
f
Ca
rd
io
v
a
sc
u
lar E
v
e
n
ts
in
Ob
str
u
c
ti
v
e
S
lee
p
A
p
n
ea
”
,
N
En
g
l
J
M
e
d
.
,
v
o
l
.
3
7
5
,
n
o
.
1
0
,
p
p
.
9
1
9
-
31
,
2
0
1
6
.
[7
]
Ch
iri
n
o
s
J
.
A
.
,
e
t
a
l
.
,
“
C
P
A
P
,
w
e
ig
h
t
lo
ss
,
o
r
b
o
th
f
o
r
Ob
stru
c
ti
v
e
S
lee
p
A
p
n
e
a
”
,
N
En
g
l
J
M
e
d
.
,
v
o
l
.
3
7
0
,
n
o
.
2
4
,
p
p
.
2
2
6
5
-
75
,
2
0
1
4
.
[8
]
A
l
m
a
z
a
y
d
e
h
L
.
,
e
t
a
l
.
,
“
Ob
stru
c
ti
v
e
S
lee
p
A
p
n
e
a
De
t
e
c
ti
o
n
u
s
in
g
S
V
M
-
b
a
se
d
C
las
si
f
ica
ti
o
n
o
f
EC
G
S
ig
n
a
l
F
e
a
tu
re
s
”
,
En
g
i
n
e
e
rin
g
i
n
M
e
d
icin
e
a
n
d
Bi
o
lo
g
y
S
o
c
iety
(
EM
BC
),
2
0
1
2
A
n
n
u
a
l
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
f
th
e
IEE
E
,
p
p
.
4
9
3
8
-
41
,
2
0
1
2
.
[9
]
Yilm
a
z
B
.
,
e
t
a
l
.
,
“
S
lee
p
St
a
g
e
a
n
d
Ob
stru
c
ti
v
e
A
p
n
e
a
ic
Ep
o
c
h
Clas
s
if
ic
a
ti
o
n
u
sin
g
S
in
g
le
-
lea
d
ECG
”
,
Bi
o
me
d
En
g
On
li
n
e
,
vol
.
9
,
n
o
.
1
,
p
.
39
,
2
0
1
0
.
[1
0
]
V
a
ro
n
C
.
,
e
t
a
l
.
,
“
S
lee
p
A
p
n
e
a
Clas
sif
i
c
a
ti
o
n
u
si
n
g
Le
a
st
-
sq
u
a
re
s
S
u
p
p
o
rt
V
e
c
t
o
r
M
a
c
h
i
n
e
s
o
n
S
i
n
g
le
L
e
a
d
EC
G
”
,
p
p
.
5
0
2
9
-
32
,
2
0
1
3
.
[1
1
]
Isa
S
.
M
.
,
e
t
a
l
.
,
“
S
lee
p
A
p
n
e
a
De
tec
ti
o
n
f
ro
m
EC
G
sig
n
a
l:
a
n
a
l
y
s
is
o
n
o
p
ti
m
a
l
fe
a
tu
re
s,
p
rin
c
ip
a
l
c
o
m
p
o
n
e
n
ts,
a
n
d
n
o
n
li
n
e
a
rit
y
,”
Bi
o
in
f
o
rm
a
ti
c
s
a
n
d
Bi
o
me
d
ica
l
E
n
g
i
n
e
e
rin
g
,
(
iCB
BE
)
5
th
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
,
p
p
.
1
-
4
,
2
0
1
1
.
[1
2
]
G
o
ld
b
e
rg
e
r
A
.
L
.
,
e
t
a
l
.
,
“
P
h
y
sio
Ba
n
k
,
P
h
y
sio
T
o
o
lk
it
,
a
n
d
P
h
y
sio
Ne
t:
Co
m
p
o
n
e
n
ts
o
f
a
n
e
w
Re
se
a
rc
h
Re
so
u
rc
e
f
o
r
Co
m
p
lex
P
h
y
sio
lo
g
ic S
ig
n
a
ls
”
,
C
irc
u
la
ti
o
n
,
v
o
l
.
1
0
1
,
n
o
.
2
3
,
p
p
.
E
2
1
5
-
20
,
2
0
0
0
.
[1
3
]
T
a
r
v
a
in
e
n
M
.
P
.
,
e
t
a
l
.
,
“
Ku
b
i
o
s
HRV
--
He
a
rt
Ra
te
V
a
riab
il
it
y
An
a
ly
sis
S
o
f
t
w
a
re
”
,
Co
mp
u
t
M
e
th
o
d
s
Pr
o
g
r
a
ms
Bi
o
me
d
.
,
v
o
l
.
1
1
3
,
n
o
.
1
,
p
p
.
2
1
0
-
20
,
2
0
1
4
.
[1
4
]
G
o
d
o
y
E
.
,
e
t
a
l
.
,
“
T
i
m
e
-
Do
m
a
in
,
F
re
q
u
e
n
c
y
Do
m
a
in
a
n
d
No
n
-
L
in
e
a
r
M
e
a
su
re
m
e
n
ts
in
Ne
o
n
a
tes
窶
He
a
rt
Ra
te
V
a
riab
il
i
ty
w
it
h
Cli
n
ica
l
S
e
p
sis
S
e
p
sis,
a
Crit
ica
l
Ba
c
teri
a
l
In
f
e
c
ti
o
n
o
f
th
e
Blo
o
d
stre
am
,
is
a
S
e
rio
u
s
Ca
u
se
o
f
Ill
n
e
ss
in
Ne
o
n
a
tal
P
e
ri
o
d
in
b
o
t
h
P
re
m
a
tu
re
a
n
d
a
t
ter
”
,
Co
mp
u
ti
n
g
in
Ca
r
d
io
l
o
g
y
Co
n
fer
e
n
c
e
(
Cin
C)
,
p
p
.
4
2
9
-
32
,
2
0
1
4
.
[1
5
]
A
b
d
a
r
M
.
,
e
t
a
l
.
,
“
Co
m
p
a
rin
g
P
e
rf
o
r
m
a
n
c
e
o
f
Da
ta
M
in
in
g
A
lg
o
ri
th
m
s
in
P
re
d
ictio
n
He
a
rt
Dise
a
se
s
”
,
In
t
J
El
e
c
tr
Co
mp
u
t
En
g
.
,
v
o
l
.
5
,
n
o
.
6
,
p
p
.
1
5
6
9
-
76
,
2
0
1
5
.
[1
6
]
M
o
ra
e
s
R
.
,
e
t
a
l
.
,
“
Do
c
u
m
e
n
t
-
lev
e
l
S
e
n
ti
m
e
n
t
Cla
ss
i
f
ica
ti
o
n
:
A
n
E
m
p
iri
c
a
l
Co
m
p
a
riso
n
b
e
twe
e
n
S
V
M
a
n
d
A
NN
”
,
Exp
e
rt S
y
st A
p
p
l
.
,
v
o
l
.
4
0
,
n
o
.
2
,
p
p
.
6
2
1
-
33
,
2
0
1
3
.
[1
7
]
P
ra
sa
d
S
.
V
.
S
.
,
e
t
a
l
.
,
“
Co
m
p
a
riso
n
o
f
A
c
c
u
ra
c
y
M
e
a
su
re
s
f
o
r
RS
Im
a
g
e
Clas
sif
i
c
a
ti
o
n
u
sin
g
S
V
M
a
n
d
A
NN
Clas
sif
ier
s
”
,
In
t
J
El
e
c
tr
Co
mp
u
t
En
g
.
,
v
o
l
.
7
,
n
o
.
3
,
p
p
.
1
1
8
0
-
7
,
2
0
1
7
.
[1
8
]
Zh
o
u
X
.
,
e
t
a
l
.
,
“
De
tec
ti
o
n
o
f
P
a
th
o
l
o
g
ica
l
Bra
in
in
M
RI
Sc
a
n
n
in
g
b
a
se
d
o
n
Wa
v
e
let
-
e
n
tro
p
y
a
n
d
Na
iv
e
Ba
y
e
s
C
las
sif
ier
”
,
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
Bi
o
i
n
f
o
rm
a
ti
c
s a
n
d
Bi
o
me
d
ica
l
E
n
g
in
e
e
rin
g
,
p
p
.
2
0
1
-
9
,
2
0
1
5
.
[1
9
]
S
u
tt
o
n
O.
,
“
In
tro
d
u
c
ti
o
n
t
o
k
n
e
a
re
st
Ne
ig
h
b
o
u
r
Clas
sif
ica
ti
o
n
a
n
d
Co
n
d
e
n
se
d
n
e
a
re
st
Ne
ig
h
b
o
u
r
Da
ta
Re
d
u
c
ti
o
n
t
he
k
n
e
a
re
st Ne
ig
h
b
o
u
rs A
lg
o
rit
h
m
”
,
p
p
.
1
-
10
,
2
0
1
2
.
[2
0
]
X
iao
M
.
,
e
t
a
l
.
,
“
S
lee
p
S
tag
e
s
Clas
sif
i
c
a
ti
o
n
b
a
se
d
o
n
He
a
rt
Ra
te
V
a
riab
il
i
ty
a
n
d
Ra
n
d
o
m
F
o
re
st
”
,
Bi
o
me
d
S
ig
n
a
l
Pro
c
e
ss
Co
n
tro
l
,
v
o
l
.
8
,
n
o
.
6
,
p
p
.
6
2
4
-
33
,
2
0
1
3
.
[2
1
]
Yılm
a
z
B
.
,
e
t
a
l
.
,
“
S
lee
p
sta
g
e
a
n
d
o
b
str
u
c
ti
v
e
a
p
n
e
a
ic
e
p
o
c
h
c
la
ss
if
ic
a
ti
o
n
u
sin
g
sin
g
le
-
lea
d
EC
G
”
,
Bi
o
me
d
En
g
On
li
n
e
,
vol
.
9
,
n
o
.
1
,
p
.
39
,
2
0
1
0
.
[2
2
]
Río
s
S
.
A
.
a
n
d
Eraz
o
L
.
,
“
A
n
Au
to
m
a
ti
c
A
p
n
e
a
S
c
re
e
n
in
g
A
l
g
o
r
it
h
m
f
o
r
C
h
il
d
re
n
”
,
Exp
e
rt
S
y
st
Ap
p
l
.
,
v
o
l
.
48
,
p
p
.
42
-
54
,
2
0
1
6
.
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
B
il
l
y
S
u
li
sty
o
re
c
e
iv
e
d
th
e
b
a
c
h
e
lo
r
d
e
g
re
e
in
Co
m
p
u
ter
En
g
in
e
e
ri
n
g
in
2
0
1
3
.
F
r
o
m
2
0
1
5
u
n
t
il
n
o
w
,
h
e
is
g
ra
d
u
a
te
stu
d
e
n
t
o
f
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
l
o
g
y
in
Bin
a
Nu
sa
n
tara
Un
iv
e
rsit
y
.
His
re
se
a
rc
h
in
tere
st
is
n
e
tw
o
rk
d
e
sig
n
,
n
e
tw
o
rk
p
e
rf
o
r
m
a
n
c
e
a
n
a
l
y
sis,
a
n
d
m
a
c
h
in
e
lea
rn
in
g
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
8
,
No
.
5
,
Octo
b
er
2
0
1
8
:
3
9
40
–
3
9
4
8
3948
Nic
o
S
u
r
a
n
th
a
re
c
e
iv
e
d
h
is
B.
En
g
(2
0
0
7
)
a
n
d
M
.
En
g
.
(2
0
0
9
)
f
ro
m
In
stit
u
t
T
e
k
n
o
lo
g
i
Ba
n
d
u
n
g
,
In
d
o
n
e
sia
.
He
re
c
e
i
v
e
d
h
is
P
h
D
d
e
g
re
e
f
ro
m
K
y
u
sh
u
I
n
stit
u
te
o
f
Tec
h
n
o
l
o
g
y
,
Ja
p
a
n
,
in
2
0
1
3
.
Cu
rre
n
tl
y
,
h
e
se
rv
e
s
a
s
a
n
a
ss
istan
t
p
ro
f
e
ss
o
r
in
C
o
m
p
u
ter
S
c
ien
c
e
De
p
a
rtme
n
t,
Bin
u
s
G
ra
d
u
a
te
P
r
o
g
ra
m
,
Bin
a
Nu
sa
n
tara
Un
iv
e
rsity
.
His
re
se
a
rc
h
in
tere
st
i
n
c
lu
d
e
s
w
irele
ss
c
o
m
m
u
n
ica
ti
o
n
,
h
e
a
lt
h
m
o
n
it
o
rin
g
,
n
e
tw
o
rk
d
e
sig
n
,
d
ig
it
a
l
sig
n
a
l
p
r
o
c
e
ss
in
g
,
s
y
ste
m
o
n
c
h
ip
d
e
sig
n
,
a
n
d
m
a
c
h
in
e
lea
rn
in
g
.
He
is
a
n
IEE
E
m
e
m
b
e
r
.
S
a
n
i
M
.
Is
a
is
a
lec
tu
re
r
a
n
d
re
s
e
a
rc
h
e
r
in
Co
m
p
u
ter
S
c
ien
c
e
De
p
a
rtm
e
n
t,
BINU
S
G
ra
d
u
a
te
P
ro
g
r
a
m
-
M
a
ste
r
o
f
Co
m
p
u
ter
S
c
ien
c
e
.
He
h
a
s
so
m
e
e
x
p
e
rien
c
e
s
in
tea
c
h
in
g
a
n
d
re
se
a
rc
h
in
re
m
o
te
s
e
n
sin
g
a
n
d
b
io
m
e
d
ica
l
e
n
g
in
e
e
rin
g
a
re
a
s.
H
e
g
o
t
h
is
d
o
c
to
ra
l
d
e
g
re
e
in
Co
m
p
u
ter
S
c
ien
c
e
f
ro
m
Un
iv
e
rsit
y
o
f
In
d
o
n
e
sia
.
He
is
a
lso
re
c
e
i
v
e
d
h
is
m
a
ste
r
d
e
g
re
e
in
Co
m
p
u
ter
S
c
ien
c
e
f
ro
m
Un
iv
e
rsit
y
o
f
In
d
o
n
e
sia
a
s
w
e
ll
a
s b
a
c
h
e
lo
r
d
e
g
re
e
f
ro
m
P
a
d
jad
jar
a
n
Un
iv
e
rsity
,
Ba
n
d
u
n
g
,
I
n
d
o
n
e
s
i
a.
Evaluation Warning : The document was created with Spire.PDF for Python.