I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
pu
t
er
Science
Vo
l.
3
8
,
No
.
2
,
Ma
y
20
2
5
,
p
p
.
767
~
7
7
3
I
SS
N:
2
502
-
4
7
52
,
DOI
: 1
0
.
1
1
5
9
1
/ijee
cs
.v
3
8
.
i
2
.
pp
767
-
7
7
3
767
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs
.
ia
esco
r
e.
co
m
An
em
bedd
ed
s
ystem
f
or
t
he
clas
sific
ation
o
f
sl
ee
p
dis
order
s us
ing ECG
s
ignals
L
a
v
u
V
enk
a
t
a
Ra
j
a
ni K
um
a
ri
,
B
a
bis
ha
m
ili Da
ra
v
a
t
h,
Y
a
rla
g
a
dd
a
P
a
d
m
a
Sa
i
De
p
a
rtme
n
t
o
f
ECE
,
VN
R
Vig
n
a
n
a
Jy
o
t
h
i
I
n
stit
u
te o
f
En
g
in
e
e
rin
g
a
n
d
Tec
h
n
o
l
o
g
y
,
Tela
n
g
a
n
a
,
I
n
d
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
l
19
,
2
0
2
4
R
ev
is
ed
No
v
1
,
2
0
2
4
Acc
ep
ted
No
v
11
,
2
0
2
4
S
lee
p
a
p
n
e
a
(S
A)
is
a
we
ll
-
k
n
o
w
n
sle
e
p
d
iso
r
d
e
r.
It
p
re
d
o
m
in
a
n
tl
y
a
p
p
e
a
rs
d
u
e
to
lac
k
o
f
o
x
y
g
e
n
i
n
h
u
m
a
n
s.
Id
e
n
ti
f
y
in
g
S
A
a
t
a
n
e
a
rly
sta
g
e
c
a
n
h
e
lp
e
a
rly
d
iag
n
o
sis.
Th
e
p
r
ima
ry
m
o
tt
o
o
f
o
u
r
re
se
a
rc
h
is
to
i
d
e
n
ti
fy
S
A
u
sin
g
e
lec
tro
c
a
rd
io
g
ra
m
(ECG
)
sig
n
a
l
s.
He
re
,
th
re
e
c
las
se
s
a
re
c
o
n
si
d
e
re
d
fo
r
c
las
sifica
ti
o
n
.
On
e
is
n
o
rm
a
l
(N),
a
n
d
th
e
o
th
e
r
tw
o
a
re
S
A
c
las
se
s
o
b
stru
c
t
iv
e
sle
e
p
a
p
n
e
a
(OA
)
a
n
d
c
e
n
tral
sle
e
p
a
p
n
e
a
(CA).
ECG
s
ig
n
a
ls
a
re
a
c
c
u
m
u
late
d
fo
r
M
IT
-
BIH
p
o
ly
s
o
m
n
o
g
ra
p
h
ic d
a
tas
e
t.
T
h
e
ECG
d
a
t
a
d
iv
id
e
d
in
to
ECG
se
g
m
e
n
ts
a
n
d
lab
e
ll
e
d
u
si
n
g
a
n
n
o
tati
o
n
fil
e
.
T
h
e
p
ro
p
o
se
d
d
eep
lo
n
g
sh
o
rt
-
term
m
e
m
o
ry
(
LS
TM
)
m
o
d
e
l
is
t
h
e
n
trai
n
e
d
u
sin
g
ECG
se
g
m
e
n
ts
a
n
d
fu
rth
e
r
tes
ted
.
Th
e
m
o
d
e
l
is
th
e
n
fi
n
e
tu
n
e
d
a
n
d
o
p
ti
m
ize
d
to
o
b
tai
n
th
e
b
e
st
a
c
c
u
ra
c
y
.
An
a
c
c
u
ra
c
y
o
f
9
8
.
5
1
%
is
o
b
tain
e
d
.
I
n
a
d
d
i
ti
o
n
,
p
e
r
fo
rm
a
n
c
e
m
e
a
su
re
s
li
k
e
p
re
c
isio
n
,
se
n
siti
v
i
ty
,
s
p
e
c
ifi
c
it
y
,
F
-
sc
o
re
a
re
a
lso
e
v
a
lu
a
ted
.
Th
e
m
o
d
e
l
is
t
h
e
n
d
e
p
lo
y
e
d
o
n
NV
IDIA
’s
Je
tso
n
n
a
n
o
b
o
a
rd
t
o
b
u
i
ld
a
p
ro
t
o
ty
p
e
.
Ou
r
m
o
d
e
l
is
e
ffe
c
ti
v
e
,
p
ro
m
isi
n
g
a
n
d
o
u
t
p
e
rfo
rm
e
d
e
x
isti
n
g
sta
te
o
f
a
rt
tec
h
n
iq
u
e
s
.
K
ey
w
o
r
d
s
:
Dee
p
l
ea
r
n
in
g
Deep
L
STM
E
lectr
o
ca
r
d
io
g
r
am
Sleep
ap
n
ea
T
im
e
-
s
er
ies d
ata
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
:
L
av
u
Ven
k
ata
R
ajan
i K
u
m
a
r
i
De
p
a
rtme
n
t
o
f
ECE
,
VN
R
Vig
n
a
n
a
Jy
o
t
h
i
I
n
stit
u
te o
f
En
g
in
e
e
rin
g
a
n
d
Tec
h
n
o
l
o
g
y
Tela
n
g
a
n
a
,
I
n
d
ia
E
m
ail:
r
ajan
ik
u
m
ar
i
_
lv
@
v
n
r
v
jiet.in
1.
I
NT
RO
D
UCT
I
O
N
Sleep
ap
n
ea
(
SA)
b
ec
o
m
es
a
m
ajo
r
p
r
o
b
lem
w
h
ile
h
u
m
a
n
b
r
ea
th
in
g
is
in
ter
r
u
p
te
d
[
1
]
.
P
er
s
o
n
s
with
SA
o
f
ten
f
ee
ls
tire
d
ev
en
a
f
te
r
h
av
in
g
a
p
r
o
p
er
s
leep
.
SA
i
s
m
ain
ly
ca
teg
o
r
ized
as
o
b
s
tr
u
ctiv
e
s
leep
ap
n
ea
(
OA)
an
d
ce
n
tr
al
s
leep
ap
n
e
a
(
C
A)
[
2
]
.
Ob
s
tr
u
ctiv
e
ap
n
ea
o
cc
u
r
s
wh
en
th
e
u
p
p
er
ai
r
way
is
r
ep
ea
ted
l
y
b
lo
ck
ed
d
u
r
in
g
s
leep
,
lead
in
g
to
a
d
ec
r
ea
s
e
o
r
ce
s
s
atio
n
o
f
air
f
lo
w.
C
A
o
cc
u
r
s
wh
en
th
e
b
r
ain
d
o
es
n
o
t
s
en
d
b
r
ea
th
in
g
s
ig
n
als,
wh
ic
h
m
ak
es
it
d
if
f
icu
lt
f
o
r
a
p
er
s
o
n
to
b
r
ea
th
e
.
T
h
e
s
tan
d
ar
d
way
t
o
d
iag
n
o
s
e
SA
is
p
o
ly
s
o
m
n
o
g
r
ap
h
y
(
PS
G)
,
wh
ich
n
ee
d
s
an
aly
zi
n
g
th
e
p
atien
ts
’
p
h
y
s
io
lo
g
ical
d
ata
w
h
ile
s
leep
in
g
.
C
o
llectin
g
d
ata
u
s
in
g
PS
G
i
s
co
s
t
ly
an
d
tim
e
-
co
n
s
u
m
in
g
.
Sev
er
al
co
s
t
-
ef
f
ec
tiv
e
m
e
th
o
d
s
h
av
e
b
ee
n
p
r
o
p
o
s
ed
to
d
etec
t
SA
[
3
]
-
[
6
]
.
So
m
e
r
esear
c
h
er
s
co
n
ten
d
t
h
at
SA
co
n
s
titu
tes
a
p
r
ed
ictab
le
r
is
k
f
ac
to
r
f
o
r
s
tr
o
k
e,
lead
in
g
to
in
d
iv
id
u
als
af
f
ec
ted
b
y
SA
h
av
in
g
a
n
a
p
p
r
o
x
im
ate
two
f
o
l
d
in
cr
ea
s
ed
r
is
k
o
f
s
tr
o
k
e
w
h
en
co
n
tr
asted
with
th
o
s
e
u
n
af
f
e
cted
b
y
th
e
co
n
d
it
io
n
[
7
]
.
I
t
is
ev
id
en
t
th
at
SA
p
o
s
es
a
s
ig
n
if
ican
t
r
is
k
to
th
e
o
v
er
all
p
h
y
s
ical
an
d
m
en
tal
well
-
b
ein
g
o
f
in
d
i
v
id
u
als
wo
r
ld
wid
e,
as
ap
p
r
o
x
i
m
ately
9
3
6
m
illi
o
n
ad
u
lts
b
etwe
en
ag
e
3
0
-
6
9
ex
p
er
ien
ce
m
ild
to
s
ev
er
e
OA
wh
ile
4
2
5
m
illi
o
n
ad
u
lts
in
th
e
s
am
e
ag
e
g
r
o
u
p
en
d
u
r
e
m
o
d
er
ate
to
s
ev
er
e
OA
[
8
]
.
H
ig
h
p
r
ev
alen
ce
o
f
SA,
it
is
cr
u
cial
to
co
n
d
u
ct
s
cr
ee
n
in
g
s
f
o
r
in
d
iv
id
u
als
with
th
is
d
is
o
r
d
er
an
d
im
p
lem
en
t
p
r
o
m
p
t
in
ter
v
en
tio
n
s
.
T
h
e
s
ig
n
if
ican
ce
o
f
o
u
r
r
esear
ch
is
to
d
etec
t
S
A
u
s
in
g
e
lectr
o
ca
r
d
io
g
r
a
m
(
E
C
G)
s
ig
n
als.
T
h
e
d
ataset
u
s
ed
in
th
is
s
tu
d
y
is
MI
T
-
B
I
H
p
o
ly
s
o
m
n
o
g
r
ap
h
ic
d
ataset
[
9
].
C
o
llectio
n
o
f
E
C
G
d
ata
is
h
ig
h
ly
co
s
t
ef
f
ec
tiv
e
[
1
0
]
,
[
1
1
]
.
Hen
ce
,
th
e
m
o
d
els
d
ev
el
o
p
ed
u
s
in
g
E
C
G
d
ata
ar
e
lo
west
co
s
t
m
o
d
els
th
at
ca
n
id
en
tify
SA
o
v
er
a
p
er
i
o
d
.
Var
io
u
s
ac
ad
em
ic
s
tu
d
ies
h
av
e
ex
am
in
e
d
th
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
8
,
No
.
2
,
May
20
2
5
:
7
6
7
-
7
7
3
768
ef
f
icac
y
o
f
id
e
n
tify
in
g
SA
th
r
o
u
g
h
th
e
a
n
aly
s
is
o
f
E
C
G
s
ig
n
als [
11]
-
[
2
5
]
.
Kay
a
an
d
Yilm
az
[1
2
]
tr
ied
f
in
d
th
e
r
elatio
n
b
etwe
en
SA
an
d
E
C
G
s
ig
n
als.
T
h
e
r
elatio
n
s
h
ip
b
e
twee
n
s
leep
ap
n
ea
an
d
v
en
tr
ic
u
lar
r
e
-
p
o
lar
izatio
n
was
ex
am
in
ed
.
T
h
e
s
ig
n
if
ica
n
ce
o
f
ex
a
m
in
in
g
t
h
e
E
C
G
s
ig
n
als
to
d
etec
t
th
e
o
cc
u
r
r
en
ce
o
f
SA
[
1
2
]
was
n
o
ted
.
Xie
an
d
Min
n
[
1
4
]
u
s
e
d
an
ad
ap
tiv
e
b
o
o
s
ted
d
ec
is
io
n
tr
ee
alg
o
r
ith
m
[
1
3
]
alo
n
g
with
d
ec
is
io
n
s
tu
m
p
to
id
en
tify
s
leep
ap
n
ea
.
R
o
d
r
i
g
u
es
et
a
l
.
[
16
]
ex
am
i
n
ed
v
ar
io
u
s
class
if
icatio
n
m
o
d
els
f
o
r
p
r
ed
ictin
g
a
p
n
ea
-
h
y
p
o
p
n
ea
in
d
ex
(
AHI
)
.
Nis
h
a
d
et
a
l
.
[
1
7
]
o
f
f
e
r
s
a
s
tr
aig
h
tf
o
r
war
d
m
et
h
o
d
f
o
r
d
etec
tin
g
s
leep
ap
n
ea
in
a
d
u
lt
p
atien
ts
,
with
th
e
ab
ilit
y
to
d
is
ce
r
n
its
p
r
esen
ce
th
r
o
u
g
h
v
is
u
al
e
x
am
in
atio
n
o
f
E
C
G
u
s
in
g
f
ilter
b
an
k
s
.
C
h
en
et
a
l
.
[
1
8
]
co
n
s
id
er
ed
b
id
ir
ec
tio
n
al
g
ate
d
r
ec
u
r
r
e
n
t
u
n
its
(
B
i
-
GR
Us)
as
b
u
ild
in
g
b
l
o
ck
s
o
f
th
e
m
o
d
el.
No
v
el
m
o
d
el
was
p
r
o
p
o
s
ed
b
y
ad
d
i
n
g
B
i
-
GR
U
lay
er
to
1
-
D
C
NN.
Uzn
ań
s
k
a
et
a
l
.
[
1
9
]
id
en
tifie
d
a
s
tr
o
n
g
ass
o
ciatio
n
b
etwe
en
s
leep
a
p
n
ea
an
d
ca
r
d
i
o
v
ascu
lar
illn
ess
.
L
iu
et
a
l
.
[
2
0
]
c
o
n
s
id
e
r
ed
th
e
p
r
etr
ain
e
d
E
f
f
icien
tNet
m
o
d
el
as
b
ac
k
b
o
n
e
an
d
u
tili
ze
d
XGb
o
o
s
t
to
u
p
d
ate
th
e
s
am
p
le
weig
h
ts
.
Var
o
n
et
a
l
.
[
2
1
]
in
tr
o
d
u
ce
d
a
n
in
n
o
v
ativ
e
au
t
o
m
ated
ap
p
r
o
ac
h
f
o
r
d
etec
tin
g
s
leep
ap
n
ea
u
s
in
g
wid
e
n
eu
r
al
n
etwo
r
k
s
.
I
n
th
eir
s
tu
d
y
,
f
o
r
d
ec
o
m
p
o
s
iti
o
n
o
f
n
o
n
s
tatio
n
ar
y
d
ata,
n
o
n
p
ar
am
etize
d
tech
n
i
q
u
es
wer
e
u
s
ed
.
L
i
et
a
l
.
[
2
2]
in
tr
o
d
u
ce
d
a
n
o
v
el
ap
p
r
o
ac
h
c
o
m
b
in
in
g
n
eu
r
al
n
etwo
r
k
s
an
d
h
id
d
e
n
m
ar
k
o
v
m
o
d
els
(
HM
M)
to
id
en
t
if
y
SA.
C
h
an
g
et
a
l
.
[
2
3
]
d
ev
elo
p
ed
o
n
e
d
im
e
n
s
io
n
al
C
NN
f
o
r
d
etec
tin
g
s
leep
a
p
n
ea
u
s
in
g
E
C
G
s
ig
n
al.
S
h
eta
et
a
l
.
[
2
4
]
co
n
s
id
er
e
d
tim
e
s
er
ies
d
ata
to
d
ev
elo
p
a
DL
m
o
d
el.
An
lo
n
g
s
h
o
r
t
-
ter
m
m
em
o
r
y
(
L
STM
)
lay
er
alo
n
g
with
C
NN
was
u
s
ed
.
M
a
s
h
r
u
r
e
t
a
l
.
[
2
5
]
p
r
o
p
o
s
e
d
a
n
e
n
d
t
o
e
n
d
a
p
p
r
o
a
c
h
u
s
i
n
g
w
a
v
e
l
e
t
t
r
a
n
s
f
o
r
m
s
a
n
d
e
m
p
i
r
i
c
a
l
m
o
d
e
d
e
c
o
m
p
o
s
i
t
i
o
n
(
E
M
D
)
a
l
o
n
g
w
i
t
h
2
-
D
C
N
N
.
E
C
G
s
e
g
m
e
n
t
s
w
e
r
e
c
o
n
v
e
r
t
e
d
i
n
t
o
s
c
a
l
o
g
r
a
m
s
a
n
d
c
o
n
s
i
d
e
r
e
d
a
s
i
n
p
u
t
.
Var
io
u
s
h
ar
d
war
e
b
o
ar
d
s
with
in
teg
r
ated
C
PU
alo
n
g
with
g
r
ap
h
ic
ca
r
ds
ca
n
b
e
f
o
u
n
d
f
o
r
p
r
o
to
ty
p
in
g
n
ee
d
s
,
in
clu
d
i
n
g
J
etso
n
Nan
o
/
AGX/
T
X1
/
T
X2
/Xav
ier
,
R
asp
b
er
r
y
Pi,
B
ea
g
l
e
B
o
ar
d
,
an
d
Asu
s
T
in
k
er
B
o
ar
d
[
10
]
.
T
h
e
NVI
DI
A
J
etso
n
p
latf
o
r
m
s
,
ex
h
ib
it
s
u
p
er
io
r
f
u
n
ctio
n
in
g
ca
p
ab
ilit
ies
attr
ib
u
ted
to
th
ei
r
h
ig
h
-
s
p
ee
d
GPUs
.
As
a
r
e
s
u
l
t
,
th
e
J
etso
n
s
er
ie
s
s
tan
d
s
at
th
e
f
o
r
ef
r
o
n
t
o
f
s
in
g
le
-
b
o
a
r
d
co
m
p
u
tin
g
with
in
th
e
r
ea
lm
o
f
d
ee
p
lear
n
in
g
ap
p
lic
atio
n
s
b
y
p
r
o
v
id
in
g
d
ev
elo
p
er
k
its
with
d
iv
er
s
e
f
ea
tu
r
es.
T
h
e
u
s
e
o
f
t
h
e
Nv
i
d
ia
J
e
t
s
o
n
N
a
n
o
d
e
v
e
l
o
p
e
r
k
i
t
i
n
t
h
e
c
r
e
a
t
i
o
n
o
f
a
p
r
o
t
o
t
y
p
e
e
x
e
m
p
l
i
f
i
e
s
i
t
s
e
f
f
i
c
a
c
y
i
n
f
a
c
i
l
i
t
a
t
i
n
g
i
n
n
o
v
a
t
i
v
e
p
r
o
j
e
c
ts
a
n
d
t
e
c
h
n
o
l
o
g
i
c
a
l
a
d
v
a
n
c
e
m
e
n
t
s
.
H
e
n
c
e
,
i
n
t
h
i
s
r
e
s
e
a
r
c
h
j
e
t
s
o
n
n
a
n
o
k
i
t
i
s
u
s
e
d
t
o
b
u
i
l
d
h
a
r
d
w
a
r
e
p
r
o
t
o
t
y
p
e
.
T
h
e
in
ten
t o
f
th
is
s
tu
d
y
is
to
d
ev
elo
p
a
d
eep
L
STM
m
o
d
el
u
s
in
g
L
STM
b
lo
ck
s
.
T
h
r
ee
class
es
n
o
r
m
al
(
N)
,
OA
a
n
d
C
A
ar
e
c
o
n
s
id
er
ed
f
o
r
class
if
icatio
n
.
T
h
is
wo
r
k
m
ain
l
y
em
p
h
ases
o
n
d
etec
ti
n
g
SA
u
s
in
g
tim
e
-
s
er
ies
d
ata.
E
C
G
S
ig
n
als
ar
e
co
llected
f
r
o
m
MI
T
-
B
I
H
p
o
ly
s
o
m
n
o
g
r
a
p
h
y
d
ataset
an
d
s
eg
m
en
ted
to
o
b
tain
E
C
G
s
eg
m
en
ts
.
T
h
ese
s
eg
m
en
ts
ar
e
lab
elled
v
ia
an
n
o
tatio
n
s
f
ile
g
iv
en
in
d
atab
ase.
Dee
p
n
etwo
r
k
s
ar
e
d
ev
elo
p
e
d
u
s
in
g
L
STM
b
u
il
d
in
g
b
l
o
ck
s
with
3
0
0
h
id
d
e
n
u
n
it.
T
h
is
d
ev
elo
p
e
d
n
etw
o
r
k
is
tr
ain
ed
a
n
d
o
p
tim
ized
.
T
h
e
n
it is
test
ed
f
o
r
d
etec
tin
g
SA u
s
in
g
NVI
DI
A
j
etso
n
b
o
ar
d
.
T
h
e
r
em
ain
in
g
p
a
r
t
o
f
th
e
p
a
p
er
is
s
tr
u
ctu
r
ed
as
f
o
llo
ws.
S
ec
tio
n
2
d
ep
icts
o
u
r
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
,
in
clu
d
in
g
t
h
e
d
etails
o
n
d
at
aset,
s
eg
m
en
tatio
n
an
d
d
ee
p
lear
n
in
g
f
r
am
ewo
r
k
.
Sectio
n
3
d
escr
ib
es
th
e
ex
p
er
im
en
tal
s
etu
p
u
s
ed
f
o
r
cl
ass
if
icatio
n
.
I
n
s
e
ctio
n
4
,
i
n
v
esti
g
ativ
e
f
in
d
in
g
s
ar
e
d
etailed
an
d
co
m
p
a
r
ed
with
liter
atu
r
e.
Sectio
n
5
d
escr
ib
es th
e
co
n
clu
s
io
n
o
f
o
u
r
r
esear
ch
.
2.
M
E
T
H
O
D
T
h
e
o
b
jectiv
e
o
f
o
u
r
r
esear
ch
is
to
id
en
tify
SA
f
r
o
m
E
C
G
s
ig
n
als.
T
h
e
Data
is
co
llected
f
r
o
m
MI
T
-
B
I
H
p
o
ly
s
o
m
n
o
g
r
a
p
h
ic
d
a
taset
an
d
s
eg
m
en
ted
in
to
E
C
G
s
eg
m
en
ts
.
T
h
ese
E
C
G
s
eg
m
en
t
s
ar
e
lab
elled
u
s
in
g
th
e
an
n
o
tatio
n
s
m
en
tio
n
ed
in
d
atab
ase.
T
h
e
la
b
elled
d
at
aset
is
co
n
s
id
er
ed
f
o
r
tr
ain
i
n
g
an
d
test
in
g
t
h
e
p
r
o
p
o
s
ed
Dee
p
L
STM
m
o
d
el.
Fig
u
r
e
1
s
ig
n
if
ies th
e
p
r
o
p
o
s
ed
m
eth
o
d
o
lo
g
y
.
2
.
1
.
MIT
-
B
I
H
P
o
ly
s
o
m
no
g
r
a
ph
ic
da
t
a
s
et
MI
T
-
B
I
H
p
o
ly
s
o
m
n
o
g
r
a
p
h
ic
d
ataset
[
8
]
co
n
tain
s
1
8
r
ec
o
r
d
s
.
Data
s
et
co
n
s
id
er
ed
in
th
is
r
esear
ch
is
an
im
b
alan
ce
d
ataset.
T
o
co
n
s
id
er
b
alan
ce
d
d
ata,
we
h
av
e
c
o
n
s
id
er
ed
7
r
ec
o
r
d
s
-
Slp
0
1
a
m
,
Slp
0
1
b
m
,
Slp
0
4
m
,
Slp
1
6
m
,
Slp
3
7
m
,
Slp
6
0
m
,
Slp
6
7
x
m
in
th
is
r
esear
ch
.
T
h
e
s
eg
m
en
ts
in
th
ese
r
ec
o
r
d
s
a
r
e
lab
elled
as
p
er
th
e
an
n
o
tio
n
s
g
iv
en
in
d
ataset.
T
h
e
r
em
ain
i
n
g
r
ec
o
r
d
s
h
av
e
a
m
ajo
r
ity
o
f
n
o
r
m
al
s
ig
n
als
a
n
d
o
n
ly
f
ew
ap
n
ea
s
ig
n
als.
Hen
ce
,
th
e
r
em
ain
in
g
s
ig
n
als ar
e
ig
n
o
r
e
d
.
T
h
e
s
u
m
m
ar
y
o
f
b
ea
ts
co
n
s
id
er
e
d
is
s
h
o
wn
in
T
ab
le
1
.
T
h
e
No
r
m
al
class
is
n
o
ted
as
‘
N’
,
o
b
s
tr
u
ctiv
e
s
leep
ap
n
ea
c
lass
is
n
o
tes
as
‘
OA’
,
an
d
ce
n
tr
al
s
leep
ap
n
ea
class
is
n
o
ted
as
‘
C
A’
.
T
h
ese
th
r
ee
co
n
s
id
er
e
d
class
es
ar
e
s
h
o
wn
in
F
ig
u
r
e
2
.
T
h
e
lab
elled
d
ata
is
f
u
r
th
er
d
i
v
id
ed
in
to
tr
ain
i
n
g
,
t
esti
n
g
an
d
v
alid
atio
n
d
ata.
Su
m
m
ar
y
o
f
b
ea
ts
co
n
s
id
er
ed
f
o
r
tr
ain
in
g
,
test
in
g
,
an
d
v
alid
atio
n
is
g
iv
en
in
T
ab
l
e
2
.
2
.
2
.
Dee
p L
ST
M
f
ra
m
ewo
rk
L
STM
is
a
ty
p
e
o
f
r
ec
u
r
r
en
t
n
etwo
r
k
u
s
ed
f
o
r
p
r
o
ce
s
s
in
g
tim
e
-
s
er
ies
d
ata.
I
n
th
is
s
tu
d
y
we
h
a
v
e
co
n
s
id
er
ed
L
STM
b
lo
c
k
s
to
b
u
ild
a
L
STM
lay
er
.
3
0
0
h
id
d
en
L
STM
b
lo
ck
s
ar
e
u
s
ed
t
o
d
ev
elo
p
a
L
STM
lay
er
.
L
ab
elled
E
C
G
s
eg
m
en
t
s
ar
e
g
iv
e
n
as
in
p
u
ts
to
d
esig
n
ed
L
STM
lay
er
.
T
h
e
o
u
tp
u
t
is
co
n
n
ec
te
d
to
f
u
lly
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
A
n
emb
ed
d
e
d
s
ystem
fo
r
th
e
cla
s
s
ifica
tio
n
o
f sleep
d
is
o
r
d
ers
u
s
in
g
…
(
La
vu
V
e
n
ka
ta
R
a
ja
n
i Ku
ma
r
i
)
769
co
n
n
ec
ted
lay
er
f
o
llo
wed
b
y
So
f
tMa
x
ac
tiv
atio
n
.
T
h
e
lay
er
ed
ar
ch
itectu
r
e
o
f
p
r
o
p
o
s
ed
Dee
p
L
STM
f
r
am
ewo
r
k
is
d
is
p
lay
ed
in
F
ig
u
r
e
3
.
Fig
u
r
e
1
.
Pro
p
o
s
ed
m
et
h
o
d
o
lo
g
y
T
ab
le
1
.
Deta
ils
o
f
co
n
s
id
er
ed
E
C
G
s
eg
m
en
ts
f
o
r
m
d
ataset
R
e
c
o
r
d
N
o
r
mal
(
N
)
O
b
st
r
u
c
t
i
v
e
s
l
e
e
p
a
p
n
e
a
(
O
A
)
C
e
n
t
r
a
l
s
l
e
e
p
A
p
n
e
a
(
C
A
)
S
l
p
0
1
a
m
5
6
4
-
-
S
l
p
0
1
b
m
3
3
6
-
-
S
l
p
0
4
m
-
1
6
5
-
S
l
p
1
6
m
-
2
1
0
-
S
l
p
3
7
m
-
5
2
5
-
S
l
p
6
0
m
-
-
1
4
7
S
l
p
6
7
x
m
-
-
7
5
3
To
t
a
l
9
0
0
9
0
0
9
0
0
(
a)
(
b
)
(
c)
Fig
u
r
e
2
.
E
C
G
s
ig
n
als
co
n
s
id
e
r
ed
f
r
o
m
d
ataset
,
(
a)
n
o
r
m
al
E
C
G
,
(
b
)
o
b
s
tr
u
ctiv
e
s
leep
a
p
n
e
a
class
,
an
d
(
c)
c
en
tr
al
s
leep
ap
n
ea
class
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
8
,
No
.
2
,
May
20
2
5
:
7
6
7
-
7
7
3
770
T
ab
le
2
.
Deta
ils
o
f
E
C
G
s
eg
m
en
ts
co
n
s
id
er
ed
f
o
r
tr
ain
i
n
g
,
v
alid
atio
n
an
d
test
in
g
C
l
a
s
s
Tr
a
i
n
i
n
g
V
a
l
i
d
a
t
i
o
n
Te
st
i
n
g
To
t
a
l
N
6
3
0
90
1
8
0
9
0
0
OA
6
3
0
90
1
8
0
9
0
0
CA
6
3
0
90
1
8
0
9
0
0
To
t
a
l
1
8
9
0
2
7
0
5
4
0
2
7
0
0
Fig
u
r
e
3
.
L
a
y
er
ed
a
r
ch
itectu
r
e
o
f
p
r
o
p
o
s
ed
D
ee
p
L
STM
f
r
am
ewo
r
k
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
NS
NVI
DI
A
J
etso
n
n
an
o
b
o
ar
d
i
s
u
tili
ze
d
f
o
r
d
ev
elo
p
i
n
g
h
ar
d
war
e
p
r
o
to
ty
p
e.
I
ts
f
u
n
ctio
n
ality
af
f
o
r
d
s
u
s
th
e
o
p
p
o
r
tu
n
ity
to
co
n
d
u
ct
th
e
tr
ain
in
g
o
f
a
d
esig
n
ated
D
NN
with
a
p
o
wer
co
n
s
u
m
p
tio
n
lim
ited
to
5
watts.
T
h
is
b
o
ar
d
is
eq
u
ip
p
ed
with
a
6
4
-
b
it q
u
ad
-
co
r
e
Ar
m
C
o
r
tex
A5
7
C
PU o
p
er
ated
at
1
.
4
3
Gig
ah
er
tz
,
p
air
ed
with
a
NVI
DI
A
Ma
x
well
GPU
co
n
tain
in
g
1
2
8
C
UDA
co
r
es
ca
p
a
b
le
o
f
4
7
2
GFLO
Ps
(
FP
1
6
)
,
a
n
d
is
s
u
p
p
o
r
ted
b
y
4
GB
o
f
6
4
-
b
it
L
PDDR
4
R
A
M.
T
eg
r
astats
was
u
tili
ze
d
f
o
r
th
e
p
u
r
p
o
s
e
o
f
p
e
r
f
o
r
m
an
ce
a
n
aly
s
is
an
d
tr
ain
in
g
Dee
p
Neu
r
al
Netwo
r
k
s
.
I
t
is
a
to
o
l
o
f
f
er
ed
b
y
NVI
DI
A
f
o
r
co
llectin
g
d
ata
o
n
h
ar
d
wa
r
e
u
tili
za
tio
n
,
m
em
o
r
y
u
s
ag
e,
an
d
p
o
wer
co
n
s
u
m
p
tio
n
o
f
b
o
th
th
e
C
PU
an
d
GPU.
NVI
DI
A
J
et
s
o
n
n
an
o
d
ev
elo
p
er
k
it
is
s
h
o
wn
in
F
ig
u
r
e
4
.
A
to
tal
o
f
2
7
0
0
E
C
G
s
eg
m
en
ts
as
g
iv
en
in
T
ab
le
1
ar
e
co
n
s
id
er
ed
f
o
r
tr
ain
i
n
g
,
te
s
tin
g
an
d
v
alid
atio
n
.
T
h
e
s
tep
-
by
-
s
tep
e
v
alu
atio
n
o
f
th
e
r
esu
lt
o
b
tain
s
d
u
r
in
g
th
e
tr
ai
n
in
g
p
r
o
ce
s
s
is
s
h
o
wn
in
Fig
u
r
e
5
.
On
ce
th
e
tr
ain
in
g
is
co
m
p
leted
,
b
u
ild
th
e
e
x
ec
u
tab
le
f
ile.
I
n
itialize
th
e
lib
r
ar
ies
C
u
DN
N,
T
en
s
o
r
R
T
alo
n
g
with
n
v
cc
p
ath
an
d
ch
ec
k
C
UDA
av
ailab
ilit
y
.
No
w,
lau
n
ch
th
e
ex
ec
u
tab
le
f
ile
o
n
tar
g
et.
Fig
u
r
e
6
s
h
o
ws
th
e
r
esu
lts
wh
en
th
e
ex
ec
u
tab
le
f
ile
is
lau
n
ch
ed
o
n
h
ar
d
war
e
an
d
test
ed
with
test
d
ata.
T
h
e
co
n
f
u
s
io
n
m
atr
ix
o
b
tain
ed
wh
e
n
test
ed
with
5
4
0
E
C
G
s
eg
m
en
ts
is
s
h
o
wn
in
Fig
u
r
e
6
.
I
t
is
o
b
s
er
v
e
d
th
at
f
o
r
C
lass
‘
N’
,
all
th
e
1
8
0
E
C
G
s
eg
m
en
ts
ar
e
co
r
r
ec
tly
class
if
ied
as
class
‘
N’
.
Ou
t
o
f
1
8
0
‘
OA’
.
1
7
4
s
eg
m
en
ts
ar
e
c
o
r
r
ec
tly
class
if
ied
as
‘
OA’
an
d
6
s
eg
m
en
ts
ar
e
m
is
class
if
ied
as
‘
C
A’
.
Similar
ly
,
am
o
n
g
1
8
0
‘
C
A’
s
eg
m
en
ts
1
7
8
a
r
e
co
r
r
ec
tly
id
e
n
tifie
d
as ‘
C
A’
an
d
2
s
eg
m
en
ts
ar
e
m
is
class
if
ied
as ‘
OA’
.
T
o
v
er
if
y
th
e
ef
f
icac
y
o
f
d
e
v
e
lo
p
ed
m
o
d
el
,
p
r
ec
is
io
n
,
s
p
ec
if
icity
,
s
en
s
itiv
ity
,
F
-
s
co
r
e,
an
d
a
cc
u
r
ac
y
ar
e
ev
alu
ated
u
s
in
g
f
o
r
m
u
lae
l
is
ted
[
2
6
]
-
[
2
8
]
.
=
+
(1
)
=
+
(2
)
=
+
(3
)
−
=
+
0
.
5
(
+
)
(4
)
=
+
+
+
+
(5
)
W
h
er
e
-
T
r
u
e
p
o
s
itiv
es,
-
T
r
u
e
n
eg
ativ
es,
-
Fals
e
p
o
s
itiv
es
an
d
-
Fals
e
n
eg
ativ
es.
T
h
e
p
er
f
o
r
m
an
ce
p
ar
m
eter
s
o
f
o
u
r
p
r
o
p
o
s
ed
D
ee
p
L
ST
M
f
r
am
ew
o
r
k
is
s
u
m
m
ar
ized
in
T
ab
le
3
.
I
t
ca
n
b
e
o
b
s
er
v
ed
th
at
th
er
e
is
n
o
m
is
clas
s
if
icati
o
n
o
f
‘
N’
ty
p
e
s
eg
m
e
n
ts
.
All
o
f
th
e
m
is
class
if
ied
s
eg
m
en
ts
ar
e
f
r
o
m
‘
OA’
an
d
‘
C
A’
ty
p
e
E
C
G
s
eg
m
en
ts
.
Nu
m
er
o
u
s
f
i
n
d
in
g
s
o
b
s
er
v
e
d
b
y
r
esear
c
h
er
s
ar
e
lis
ted
i
n
T
a
b
le
4
.
Ka
y
a
an
d
Yilm
az
[
1
2
]
d
ev
elo
p
ed
a
ML
alg
o
r
ith
m
u
s
in
g
d
ec
is
io
n
tr
ee
an
d
u
s
ed
en
s
em
b
le
m
eth
o
d
ad
ab
o
o
s
t
to
im
p
r
o
v
e
th
e
p
er
f
o
r
m
a
n
ce
.
An
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
A
n
emb
ed
d
e
d
s
ystem
fo
r
th
e
cla
s
s
ifica
tio
n
o
f sleep
d
is
o
r
d
ers
u
s
in
g
…
(
La
vu
V
e
n
ka
ta
R
a
ja
n
i Ku
ma
r
i
)
771
ac
cu
r
ac
y
o
f
8
2
%
was
o
b
tain
ed
.
Uzn
ań
s
k
a
et
a
l.
[
1
9
]
p
er
f
o
r
m
ed
HR
V
an
aly
s
is
co
n
s
id
er
in
g
E
C
G
s
ig
n
als
an
d
an
ac
cu
r
ac
y
o
f
8
5
%
was
o
b
tai
n
ed
.
L
iu
et
a
l
.
[
2
0
]
ac
h
iev
ed
an
ac
cu
r
ac
y
o
f
8
5
%
u
s
in
g
a
h
y
b
r
id
m
o
d
el
wh
ich
in
clu
d
es
DL
an
d
HM
M.
Var
o
n
et
a
l
.
[
2
1
]
im
p
lem
e
n
ted
a
D
L
m
o
d
el
u
s
in
g
1
D
C
NN
an
d
a
ch
iev
ed
a
n
ac
cu
r
ac
y
o
f
8
7
.
9
%.
L
i
et
a
l
.
[
2
2
]
a
d
d
ed
L
STM
la
y
er
al
o
n
g
with
C
NN
an
d
ac
h
iev
e
d
a
n
ac
c
u
r
ac
y
o
f
8
6
.
2
5
%.
Ou
r
p
r
o
p
o
s
ed
Dee
p
L
STM
o
u
t
p
er
f
o
r
m
ed
e
x
is
tin
g
m
eth
o
d
o
lo
g
ies
with
an
ac
cu
r
ac
y
o
f
9
8
.
51
%.
Fig
u
r
e
4
.
NVI
DI
A
J
etso
n
n
a
n
o
d
ev
elo
p
er
k
it
Fig
u
r
e
5
.
S
tep
b
y
s
tep
ev
al
u
atio
n
Fig
u
r
e
6
.
Har
d
war
e
r
esu
lts
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
8
,
No
.
2
,
May
20
2
5
:
7
6
7
-
7
7
3
772
T
ab
le
3
.
Per
f
o
r
m
an
ce
m
ea
s
u
r
e
s
C
l
a
s
s
P
r
e
c
i
s
i
o
n
(
%)
S
e
n
s
i
t
i
v
i
t
y
(
%)
S
p
e
c
i
f
i
c
i
t
y
(
%)
F
-
sco
r
e
(
%)
N
1
0
0
1
0
0
1
0
0
1
0
0
OA
9
6
.
6
6
7
9
8
.
8
6
4
9
8
.
3
5
2
9
7
.
7
5
3
CA
9
8
.
8
8
9
9
6
.
7
3
9
9
9
.
4
3
8
9
7
.
8
0
2
O
v
e
r
a
l
l
Te
s
t
a
c
c
u
r
a
c
y
:
9
8
.
5
1
%
T
ab
le
4
.
C
o
m
p
a
r
is
o
n
o
f
o
u
r
ap
p
r
o
ac
h
with
s
tate
-
of
-
th
e
-
ar
t
m
o
d
els
A
u
t
h
o
r
s
M
e
t
h
o
d
P
e
r
f
o
r
ma
n
c
e
(
%
)
X
i
e
a
n
d
M
i
n
n
e
t
a
l
.
[
1
4
]
D
e
c
i
s
i
o
n
t
r
e
e
w
i
t
h
A
d
a
b
o
o
st
82
V
a
r
o
n
e
t
a
l
.
[
2
1
]
W
i
d
e
n
e
u
r
a
l
n
e
t
w
o
r
k
s
(WNN)
9
6
.
6
0
Li
e
t
a
l
.
[
2
2
]
D
L+
H
M
M
h
y
b
r
i
d
mo
d
e
l
85
C
h
a
n
g
e
t
a
l
.
[
2
3
]
1
D
C
N
N
mo
d
e
l
8
7
.
9
S
h
e
t
a
e
t
a
l
.
[
2
4
]
C
N
N
+
LST
M
8
6
.
2
5
M
a
s
h
r
u
r
e
t
a
l
.
[
2
5
]
C
W
T+
EM
D
9
4
.
3
O
u
r
p
r
o
p
o
s
e
d
mo
d
e
l
D
e
e
p
LST
M
9
8
.
5
1
4.
CO
NCLU
SI
O
N
Dee
p
L
STM
m
o
d
el
h
as
b
ee
n
p
r
o
p
o
s
ed
to
d
etec
t
SA
f
r
o
m
E
C
G
s
ig
n
al.
T
h
e
d
ata
h
as
b
ee
n
co
llected
f
r
o
m
MI
T
-
B
I
H
p
o
l
y
s
o
m
n
o
g
r
ap
h
ic
d
atab
ase.
E
C
G
s
ig
n
als
ar
e
th
en
s
eg
m
en
ted
in
to
E
C
G
s
eg
m
en
ts
.
T
h
ese
s
eg
m
en
ts
ar
e
lab
elled
u
s
in
g
th
e
an
n
o
tatio
n
f
ile
m
en
tio
n
ed
in
d
atab
ase.
T
h
e
p
r
o
p
o
s
ed
m
o
d
el
is
th
en
tr
ain
ed
co
n
s
id
er
in
g
v
ar
io
u
s
h
y
p
er
p
ar
a
m
eter
s
.
Fu
r
th
er
,
m
o
d
el
is
s
av
ed
with
b
est
h
y
p
er
p
ar
am
eter
s
a
n
d
th
en
test
ed
.
Ou
r
m
o
d
el
r
ec
o
r
d
e
d
th
e
b
est
ac
c
u
r
ac
y
o
f
9
8
.
5
1
%
co
m
p
a
r
ed
t
o
ex
is
tin
g
liter
atu
r
e
.
I
t
is
co
n
clu
d
ed
th
at
s
leep
d
is
o
r
d
er
s
ca
n
b
e
id
en
tifie
d
u
s
in
g
s
leep
q
u
ality
f
ea
tu
r
es
f
r
o
m
a
3
0
-
s
ec
o
n
d
ep
o
ch
o
f
th
e
E
C
G
s
ig
n
al.
T
h
is
m
eth
o
d
h
as
p
r
o
v
e
n
to
b
e
r
eli
ab
le
f
o
r
m
o
d
elin
g
s
leep
d
is
o
r
d
er
s
with
o
u
t
th
e
n
ee
d
f
o
r
a
m
u
ltich
an
n
el
PS
G
s
ig
n
al.
Ad
d
itio
n
ally
,
it
is
s
tr
ai
g
h
tf
o
r
war
d
to
im
p
lem
en
t
o
n
e
m
b
ed
d
e
d
h
ar
d
war
e
d
e
v
ices.
Ou
r
p
r
o
p
o
s
ed
s
y
s
tem
is
p
o
r
tab
le
an
d
cu
s
to
m
izab
le,
m
ak
in
g
it a
n
id
ea
l so
lu
tio
n
f
o
r
co
n
tin
u
o
u
s
s
leep
ap
n
ea
m
o
n
it
o
r
in
g
.
RE
F
E
R
E
NC
E
S
[
1
]
I
.
U
mb
r
o
,
V
.
F
a
b
i
a
n
i
,
M
.
F
a
b
i
a
n
i
,
F
.
A
n
g
e
l
i
c
o
,
a
n
d
M
.
D
e
l
B
e
n
,
“
A
s
y
st
e
mat
i
c
r
e
v
i
e
w
o
n
t
h
e
a
ss
o
c
i
a
t
i
o
n
b
e
t
w
e
e
n
o
b
st
r
u
c
t
i
v
e
sl
e
e
p
a
p
n
e
a
a
n
d
c
h
r
o
n
i
c
k
i
d
n
e
y
d
i
se
a
s
e
,
”
S
l
e
e
p
Me
d
i
c
i
n
e
Re
v
i
e
w
s
,
v
o
l
.
5
3
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
smr
v
.
2
0
2
0
.
1
0
1
3
3
7
.
[
2
]
M
.
S
h
a
r
ma
,
M
.
R
a
v
a
l
,
a
n
d
U
.
R
.
A
c
h
a
r
y
a
,
“
A
n
e
w
a
p
p
r
o
a
c
h
t
o
i
d
e
n
t
i
f
y
o
b
s
t
r
u
c
t
i
v
e
sl
e
e
p
a
p
n
e
a
u
si
n
g
a
n
o
p
t
i
m
a
l
o
r
t
h
o
g
o
n
a
l
w
a
v
e
l
e
t
f
i
l
t
e
r
b
a
n
k
w
i
t
h
EC
G
s
i
g
n
a
l
s,
”
I
n
f
o
rm
a
t
i
c
s
i
n
Me
d
i
c
i
n
e
U
n
l
o
c
k
e
d
,
v
o
l
.
1
6
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
mu
.
2
0
1
9
.
1
0
0
1
7
0
.
[
3
]
S
.
Y
o
o
k
,
D
.
K
i
m,
C
.
G
u
p
t
e
,
E
.
Y
.
J
o
o
,
a
n
d
H
.
K
i
m,
“
D
e
e
p
l
e
a
r
n
i
n
g
o
f
sl
e
e
p
a
p
n
e
a
-
h
y
p
o
p
n
e
a
e
v
e
n
t
s
f
o
r
a
c
c
u
r
a
t
e
c
l
a
ssi
f
i
c
a
t
i
o
n
o
f
o
b
s
t
r
u
c
t
i
v
e
sl
e
e
p
a
p
n
e
a
a
n
d
d
e
t
e
r
mi
n
a
t
i
o
n
o
f
c
l
i
n
i
c
a
l
s
e
v
e
r
i
t
y
,
”
S
l
e
e
p
Me
d
i
c
i
n
e
,
v
o
l
.
1
1
4
,
p
p
.
2
1
1
–
2
1
9
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
sl
e
e
p
.
2
0
2
4
.
0
1
.
0
1
5
.
[
4
]
P
.
F
o
n
se
c
a
e
t
a
l
.
,
“
Est
i
ma
t
i
n
g
t
h
e
S
e
v
e
r
i
t
y
o
f
O
b
st
r
u
c
t
i
v
e
S
l
e
e
p
A
p
n
e
a
U
si
n
g
E
C
G
,
R
e
s
p
i
r
a
t
o
r
y
Ef
f
o
r
t
a
n
d
N
e
u
r
a
l
N
e
t
w
o
r
k
s,”
I
EEE
J
o
u
rn
a
l
o
f
Bi
o
m
e
d
i
c
a
l
a
n
d
H
e
a
l
t
h
I
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
2
8
,
n
o
.
7
,
p
p
.
3
8
9
5
–
3
9
0
6
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
J
B
H
I
.
2
0
2
4
.
3
3
8
3
2
4
0
.
[
5
]
A
.
Th
o
mm
a
n
d
r
a
m,
J
.
M
.
Ek
l
u
n
d
,
a
n
d
C
.
M
c
G
r
e
g
o
r
,
“
D
e
t
e
c
t
i
o
n
o
f
a
p
n
o
e
a
f
r
o
m
r
e
s
p
i
r
a
t
o
r
y
t
i
m
e
ser
i
e
s
d
a
t
a
u
s
i
n
g
c
l
i
n
i
c
a
l
l
y
r
e
c
o
g
n
i
z
a
b
l
e
f
e
a
t
u
r
e
s
a
n
d
k
N
N
c
l
a
s
si
f
i
c
a
t
i
o
n
,
”
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
A
n
n
u
a
l
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
f
t
h
e
I
EE
E
En
g
i
n
e
e
ri
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
,
EM
BS
,
p
p
.
5
0
1
3
–
5
0
1
6
,
2
0
1
3
,
d
o
i
:
1
0
.
1
1
0
9
/
E
M
B
C
.
2
0
1
3
.
6
6
1
0
6
7
4
.
[
6
]
S
.
K
i
m
e
t
a
l
.
,
“
A
C
o
m
p
r
e
h
e
n
si
v
e
S
t
u
d
y
o
n
a
D
e
e
p
-
Le
a
r
n
i
n
g
-
B
a
s
e
d
El
e
c
t
r
o
c
a
r
d
i
o
g
r
a
p
h
y
A
n
a
l
y
si
s
f
o
r
Est
i
m
a
t
i
n
g
t
h
e
A
p
n
e
a
-
H
y
p
o
p
n
e
a
I
n
d
e
x
,
”
D
i
a
g
n
o
st
i
c
s
,
v
o
l
.
1
4
,
n
o
.
1
1
,
2
0
2
4
,
d
o
i
:
1
0
.
3
3
9
0
/
d
i
a
g
n
o
st
i
c
s
1
4
1
1
1
1
3
4
.
[
7
]
O
.
D
.
L
y
o
n
s
a
n
d
C
.
M
.
R
y
a
n
,
“
S
l
e
e
p
A
p
n
e
a
a
n
d
S
t
r
o
k
e
,
”
C
a
n
a
d
i
a
n
J
o
u
r
n
a
l
o
f
C
a
r
d
i
o
l
o
g
y
,
v
o
l
.
3
1
,
n
o
.
7
,
p
p
.
9
1
8
–
9
2
7
,
J
u
l
.
2
0
1
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
j
c
a
.
2
0
1
5
.
0
3
.
0
1
4
.
[
8
]
A
.
V
.
B
e
n
j
a
f
i
e
l
d
e
t
a
l
.
,
“
Est
i
ma
t
i
o
n
o
f
t
h
e
g
l
o
b
a
l
p
r
e
v
a
l
e
n
c
e
a
n
d
b
u
r
d
e
n
o
f
o
b
st
r
u
c
t
i
v
e
sl
e
e
p
a
p
n
o
e
a
:
a
l
i
t
e
r
a
t
u
r
e
-
b
a
se
d
a
n
a
l
y
s
i
s,”
T
h
e
L
a
n
c
e
t
R
e
s
p
i
r
a
t
o
ry
M
e
d
i
c
i
n
e
,
v
o
l
.
7
,
n
o
.
8
,
p
p
.
6
8
7
–
6
9
8
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
S
2
2
1
3
-
2
6
0
0
(
1
9
)
3
0
1
9
8
-
5.
[
9
]
G
o
l
d
b
e
r
g
e
r
A
.
e
t
a
l
.
,
“
P
h
y
s
i
o
B
a
n
k
,
P
h
y
s
i
o
To
o
l
k
i
t
,
a
n
d
P
h
y
si
o
N
e
t
:
C
o
mp
o
n
e
n
t
s
o
f
a
n
e
w
r
e
s
e
a
r
c
h
r
e
s
o
u
r
c
e
f
o
r
c
o
m
p
l
e
x
p
h
y
s
i
o
l
o
g
i
c
s
i
g
n
a
l
s,
”
C
i
r
c
u
l
a
t
i
o
n
[O
n
l
i
n
e
]
,
v
o
l
.
1
0
1
,
n
o
.
2
3
,
p
p
.
E
2
1
5
–
E
2
2
0
,
2
0
2
1
.
[
1
0
]
M
o
h
e
b
b
a
n
a
a
z
,
Y
.
P
a
d
m
a
S
a
i
,
a
n
d
L
.
V
.
R
a
j
a
n
i
K
u
m
a
r
i
,
“
C
o
g
n
i
t
i
v
e
a
ssi
s
t
a
n
t
D
e
e
p
N
e
t
mo
d
e
l
f
o
r
d
e
t
e
c
t
i
o
n
o
f
c
a
r
d
i
a
c
a
r
r
h
y
t
h
mi
a
,
”
Bi
o
m
e
d
i
c
a
l
S
i
g
n
a
l
Pr
o
c
e
s
si
n
g
a
n
d
C
o
n
t
r
o
l
,
v
o
l
.
7
1
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
b
s
p
c
.
2
0
2
1
.
1
0
3
2
2
1
.
[
1
1
]
M
o
h
e
b
b
a
n
a
a
z
,
Y
.
P
a
d
m
a
S
a
i
,
a
n
d
L
.
V
.
R
a
j
a
n
i
K
u
m
a
r
i
,
“
A
R
e
v
i
e
w
o
n
A
r
r
h
y
t
h
m
i
a
C
l
a
ssi
f
i
c
a
t
i
o
n
U
si
n
g
EC
G
S
i
g
n
a
l
s,”
2
0
2
0
I
EEE
I
n
t
e
r
n
a
t
i
o
n
a
l
S
t
u
d
e
n
t
s’
C
o
n
f
e
re
n
c
e
o
n
El
e
c
t
r
i
c
a
l
,
E
l
e
c
t
r
o
n
i
c
s
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
S
C
E
EC
S
2
0
2
0
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
S
C
EEC
S
4
8
3
9
4
.
2
0
2
0
.
9
.
[
1
2
]
K
.
A
.
K
a
y
a
a
n
d
B
.
Y
i
l
ma
z
,
“
A
n
e
w
t
o
o
l
f
o
r
Q
T
i
n
t
e
r
v
a
l
a
n
a
l
y
s
i
s
d
u
r
i
n
g
sl
e
e
p
i
n
h
e
a
l
t
h
y
a
n
d
o
b
s
t
r
u
c
t
i
v
e
sl
e
e
p
a
p
n
e
a
s
u
b
j
e
c
t
s
:
A
st
u
d
y
o
n
w
o
me
n
,
”
T
u
rki
sh
J
o
u
r
n
a
l
o
f
E
l
e
c
t
r
i
c
a
l
E
n
g
i
n
e
e
r
i
n
g
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
s,
v
o
l
.
2
1
,
n
o
.
5
,
p
p
.
1
5
0
4
–
1
5
1
3
,
2
0
1
3
,
d
o
i
:
1
0
.
3
9
0
6
/
e
l
k
-
1
2
0
3
-
6
2
.
[
1
3
]
O
.
F
a
u
s
t
,
U
.
R
.
A
c
h
a
r
y
a
,
E
.
Y
.
K
.
N
g
,
a
n
d
H
.
F
u
j
i
t
a
,
“
A
r
e
v
i
e
w
o
f
EC
G
-
B
a
se
d
d
i
a
g
n
o
si
s
s
u
p
p
o
r
t
s
y
st
e
ms
f
o
r
o
b
s
t
r
u
c
t
i
v
e
sl
e
e
p
a
p
n
e
a
,
”
J
o
u
r
n
a
l
o
f
M
e
c
h
a
n
i
c
s
i
n
M
e
d
i
c
i
n
e
a
n
d
Bi
o
l
o
g
y
,
v
o
l
.
1
6
,
n
o
.
1
,
2
0
1
6
,
d
o
i
:
1
0
.
1
1
4
2
/
S
0
2
1
9
5
1
9
4
1
6
4
0
0
0
4
2
.
[
1
4
]
B
.
X
i
e
a
n
d
H
.
M
i
n
n
,
“
R
e
a
l
-
t
i
me
sl
e
e
p
a
p
n
e
a
d
e
t
e
c
t
i
o
n
b
y
c
l
a
ssi
f
i
e
r
c
o
m
b
i
n
a
t
i
o
n
,
”
I
EEE
T
ra
n
s
a
c
t
i
o
n
s
o
n
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
i
n
B
i
o
m
e
d
i
c
i
n
e
,
v
o
l
.
1
6
,
n
o
.
3
,
p
p
.
4
6
9
–
4
7
7
,
2
0
1
2
,
d
o
i
:
1
0
.
1
1
0
9
/
TI
TB
.
2
0
1
2
.
2
1
8
8
2
9
9
.
[
1
5
]
L.
V
K
u
mar
i
,
Y
.
P
.
S
a
i
,
a
n
d
o
t
h
e
r
s,
“
C
l
a
ssi
f
i
c
a
t
i
o
n
o
f
E
C
G
b
e
a
t
s
u
s
i
n
g
o
p
t
i
mi
z
e
d
d
e
c
i
s
i
o
n
t
r
e
e
a
n
d
a
d
a
p
t
i
v
e
b
o
o
s
t
e
d
o
p
t
i
mi
z
e
d
d
e
c
i
si
o
n
t
r
e
e
,
”
S
i
g
n
a
l
,
I
m
a
g
e
a
n
d
Vi
d
e
o
Pro
c
e
s
s
i
n
g
,
v
o
l
.
1
6
,
n
o
.
3
,
p
p
.
6
9
5
–
7
0
3
,
2
0
2
2
.
[
1
6
]
J.
F
.
R
o
d
r
i
g
u
e
s
,
J
.
L.
P
e
p
i
n
,
L.
G
o
e
u
r
i
o
t
,
a
n
d
S
.
A
m
e
r
-
Y
a
h
i
a
,
“
A
n
E
x
t
e
n
s
i
v
e
I
n
v
e
st
i
g
a
t
i
o
n
o
f
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
Te
c
h
n
i
q
u
e
s
f
o
r
S
l
e
e
p
A
p
n
e
a
S
c
r
e
e
n
i
n
g
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
I
n
f
o
rm
a
t
i
o
n
a
n
d
K
n
o
w
l
e
d
g
e
Ma
n
a
g
e
m
e
n
t
,
Pro
c
e
e
d
i
n
g
s
,
p
p
.
2
7
0
9
–
2
7
1
6
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
4
5
/
3
3
4
0
5
3
1
.
3
4
1
2
6
8
6
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
A
n
emb
ed
d
e
d
s
ystem
fo
r
th
e
cla
s
s
ifica
tio
n
o
f sleep
d
is
o
r
d
ers
u
s
in
g
…
(
La
vu
V
e
n
ka
ta
R
a
ja
n
i Ku
ma
r
i
)
773
[
1
7
]
A
.
N
i
sh
a
d
,
R
.
B
.
P
a
c
h
o
r
i
,
a
n
d
U
.
R
.
A
c
h
a
r
y
a
,
“
A
p
p
l
i
c
a
t
i
o
n
o
f
TQ
W
T
b
a
se
d
f
i
l
t
e
r
-
b
a
n
k
f
o
r
s
l
e
e
p
a
p
n
e
a
s
c
r
e
e
n
i
n
g
u
s
i
n
g
E
C
G
si
g
n
a
l
s,
”
J
o
u
r
n
a
l
o
f
Am
b
i
e
n
t
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
H
u
m
a
n
i
ze
d
C
o
m
p
u
t
i
n
g
,
v
o
l
.
1
5
,
n
o
.
1
,
p
p
.
8
9
3
–
9
0
4
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
2
6
5
2
-
0
1
8
-
0
8
6
7
-
3.
[
1
8
]
J.
C
h
e
n
,
M
.
S
h
e
n
,
W
.
M
a
,
a
n
d
W
.
Z
h
e
n
g
,
“
A
s
p
a
t
i
o
-
t
e
mp
o
r
a
l
l
e
a
r
n
i
n
g
-
b
a
sed
m
o
d
e
l
f
o
r
sl
e
e
p
a
p
n
e
a
d
e
t
e
c
t
i
o
n
u
si
n
g
s
i
n
g
l
e
-
l
e
a
d
EC
G
s
i
g
n
a
l
s,
”
Fr
o
n
t
i
e
rs
i
n
N
e
u
r
o
s
c
i
e
n
c
e
,
v
o
l
.
1
6
,
2
0
2
2
,
d
o
i
:
1
0
.
3
3
8
9
/
f
n
i
n
s.
2
0
2
2
.
9
7
2
5
8
1
.
[
1
9
]
B
.
U
z
n
a
ń
sk
a
,
E
.
Tr
z
o
s,
T.
R
e
c
h
c
i
ń
sk
i
,
J
.
D
.
K
a
sp
r
z
a
k
,
a
n
d
M
.
K
u
r
p
e
s
a
,
“
R
e
p
e
a
t
a
b
i
l
i
t
y
o
f
s
l
e
e
p
a
p
n
e
a
d
e
t
e
c
t
i
o
n
i
n
4
8
-
h
o
u
r
h
o
l
t
e
r
EC
G
m
o
n
i
t
o
r
i
n
g
,
”
A
n
n
a
l
s
o
f
N
o
n
i
n
v
a
si
v
e
El
e
c
t
ro
c
a
rd
i
o
l
o
g
y
,
v
o
l
.
1
5
,
n
o
.
3
,
p
p
.
2
1
8
–
2
2
2
,
2
0
1
0
,
d
o
i
:
1
0
.
1
1
1
1
/
j
.
1
5
4
2
-
4
7
4
X
.
2
0
1
0
.
0
0
3
6
7
.
x
.
[
2
0
]
M
.
H
.
L
i
u
e
t
a
l
.
,
“
Ef
f
i
c
i
e
n
t
N
e
t
-
b
a
se
d
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
r
c
h
i
t
e
c
t
u
r
e
f
o
r
sl
e
e
p
a
p
n
e
a
i
d
e
n
t
i
f
i
c
a
t
i
o
n
i
n
c
l
i
n
i
c
a
l
si
n
g
l
e
-
l
e
a
d
E
C
G
si
g
n
a
l
d
a
t
a
s
e
t
s
,
”
Bi
o
M
e
d
i
c
a
l
E
n
g
i
n
e
e
ri
n
g
O
n
l
i
n
e
,
v
o
l
.
2
3
,
n
o
.
1
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
8
6
/
s
1
2
9
3
8
-
0
2
4
-
0
1
2
5
2
-
w.
[
2
1
]
C
.
V
a
r
o
n
,
A
.
C
a
i
c
e
d
o
,
D
.
Te
s
t
e
l
ma
n
s
,
B
.
B
u
y
s
e
,
a
n
d
S
.
V
a
n
H
u
f
f
e
l
,
“
A
N
o
v
e
l
A
l
g
o
r
i
t
h
m
f
o
r
t
h
e
A
u
t
o
ma
t
i
c
D
e
t
e
c
t
i
o
n
o
f
S
l
e
e
p
A
p
n
e
a
f
r
o
m
S
i
n
g
l
e
-
L
e
a
d
E
C
G
,
”
I
E
EE
T
ra
n
s
a
c
t
i
o
n
s
o
n
B
i
o
m
e
d
i
c
a
l
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
6
2
,
n
o
.
9
,
p
p
.
2
2
6
9
–
2
2
7
8
,
2
0
1
5
,
d
o
i
:
1
0
.
1
1
0
9
/
T
B
M
E.
2
0
1
5
.
2
4
2
2
3
7
8
.
[
2
2
]
K
.
Li
,
W
.
P
a
n
,
Y
.
L
i
,
Q
.
J
i
a
n
g
,
a
n
d
G
.
Li
u
,
“
A
me
t
h
o
d
t
o
d
e
t
e
c
t
sl
e
e
p
a
p
n
e
a
b
a
s
e
d
o
n
d
e
e
p
n
e
u
r
a
l
n
e
t
w
o
r
k
a
n
d
h
i
d
d
e
n
M
a
r
k
o
v
mo
d
e
l
u
s
i
n
g
si
n
g
l
e
-
l
e
a
d
EC
G
s
i
g
n
a
l
,
”
N
e
u
r
o
c
o
m
p
u
t
i
n
g
,
v
o
l
.
2
9
4
,
p
p
.
9
4
–
1
0
1
,
2
0
1
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
n
e
u
c
o
m.
2
0
1
8
.
0
3
.
0
1
1
.
[
2
3
]
H
.
Y
.
C
h
a
n
g
,
C
.
Y
.
Y
e
h
,
C
.
Te
L
e
e
,
a
n
d
C
.
C
.
L
i
n
,
“
A
sl
e
e
p
a
p
n
e
a
d
e
t
e
c
t
i
o
n
s
y
s
t
e
m
b
a
se
d
o
n
a
o
n
e
-
d
i
me
n
si
o
n
a
l
d
e
e
p
c
o
n
v
o
l
u
t
i
o
n
n
e
u
r
a
l
n
e
t
w
o
r
k
mo
d
e
l
u
si
n
g
s
i
n
g
l
e
-
l
e
a
d
e
l
e
c
t
r
o
c
a
r
d
i
o
g
r
a
m,
”
S
e
n
s
o
rs
(
S
w
i
t
zerl
a
n
d
)
,
v
o
l
.
2
0
,
n
o
.
1
5
,
p
p
.
1
–
1
5
,
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
s
2
0
1
5
4
1
5
7
.
[
2
4
]
A
.
S
h
e
t
a
e
t
a
l
.
,
“
D
i
a
g
n
o
s
i
s
o
f
o
b
st
r
u
c
t
i
v
e
sl
e
e
p
a
p
n
e
a
f
r
o
m
E
C
G
si
g
n
a
l
s
u
si
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
c
l
a
ss
i
f
i
e
r
s,
”
Ap
p
l
i
e
d
S
c
i
e
n
c
e
s
(
S
w
i
t
zer
l
a
n
d
)
,
v
o
l
.
1
1
,
n
o
.
1
4
,
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
1
1
4
6
6
2
2
.
[
2
5
]
F
.
R
.
M
a
s
h
r
u
r
,
M
.
S
.
I
sl
a
m,
D
.
K
.
S
a
h
a
,
S
.
M
.
R
.
I
sl
a
m,
a
n
d
M
.
A
.
M
o
n
i
,
“
S
C
N
N
:
S
c
a
l
o
g
r
a
m
-
b
a
se
d
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
t
o
d
e
t
e
c
t
o
b
st
r
u
c
t
i
v
e
sl
e
e
p
a
p
n
e
a
u
si
n
g
si
n
g
l
e
-
l
e
a
d
e
l
e
c
t
r
o
c
a
r
d
i
o
g
r
a
m
si
g
n
a
l
s,”
C
o
m
p
u
t
e
rs
i
n
Bi
o
l
o
g
y
a
n
d
Me
d
i
c
i
n
e
,
v
o
l
.
1
3
4
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
mp
b
i
o
m
e
d
.
2
0
2
1
.
1
0
4
5
3
2
.
[
2
6
]
L.
V
.
R
a
j
a
n
i
K
u
mar
i
a
n
d
Y
.
C
h
a
l
a
p
a
t
h
i
R
a
o
,
“
EC
G
b
e
a
t
c
l
a
ssi
f
i
c
a
t
i
o
n
u
si
n
g
p
r
o
p
o
se
d
p
a
t
t
e
r
n
a
d
a
p
t
i
v
e
w
a
v
e
l
e
t
-
b
a
s
e
d
h
y
b
r
i
d
c
l
a
ss
i
f
i
e
r
s,”
S
i
g
n
a
l
,
I
m
a
g
e
a
n
d
V
i
d
e
o
Pro
c
e
ssi
n
g
,
v
o
l
.
1
7
,
n
o
.
6
,
p
p
.
2
8
2
7
–
2
8
3
5
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
7
6
0
-
023
-
0
2
5
0
1
-
6.
[
2
7
]
L.
V
.
R
.
K
u
m
a
r
i
,
A
.
Lo
h
i
t
h
a
,
A
.
K
a
v
y
a
,
a
n
d
N
.
T
a
r
a
k
e
sw
a
r
,
“
A
u
t
o
m
a
t
e
d
sl
e
e
p
a
p
n
e
a
c
l
a
ssi
f
i
c
a
t
i
o
n
b
a
s
e
d
o
n
st
a
t
i
st
i
c
a
l
a
n
d
sp
e
c
t
r
a
l
a
n
a
l
y
s
i
s
o
f
e
l
e
c
t
r
o
c
a
r
d
i
o
g
r
a
m
si
g
n
a
l
s,”
I
n
d
o
n
e
s
i
a
n
J
o
u
rn
a
l
o
f
El
e
c
t
ri
c
a
l
E
n
g
i
n
e
e
ri
n
g
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
2
5
,
n
o
.
3
,
p
p
.
1
4
5
0
–
1
4
5
7
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s
.
v
2
5
.
i
3
.
p
p
1
4
5
0
-
1
4
5
7
.
[
2
8
]
M
o
h
e
b
b
a
n
a
a
z
,
Y
.
P
a
d
ma
S
a
i
,
a
n
d
L.
V
.
R
a
j
a
n
i
K
u
m
a
r
i
,
“
D
e
t
e
c
t
i
o
n
o
f
c
a
r
d
i
a
c
a
r
r
h
y
t
h
m
i
a
u
si
n
g
d
e
e
p
C
N
N
a
n
d
o
p
t
i
m
i
z
e
d
S
V
M
,
”
I
n
d
o
n
e
si
a
n
J
o
u
r
n
a
l
o
f
El
e
c
t
ri
c
a
l
E
n
g
i
n
e
e
r
i
n
g
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
2
4
,
n
o
.
1
,
p
p
.
2
1
7
–
2
2
5
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s.
v
2
4
.
i
1
.
p
p
2
1
7
-
2
2
5
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
La
v
u
V
e
n
k
a
ta
R
a
ja
n
i
K
u
m
a
r
i
Hy
d
e
ra
b
a
d
h
a
s c
o
m
p
lete
d
BTec
h
in
EC
E,
M
Tec
h
in
Emb
e
d
d
e
d
S
y
ste
m
s,
a
n
d
P
h
D d
e
g
re
e
in
b
io
m
e
d
ica
l
si
g
n
a
l
p
ro
c
e
ss
in
g
fr
o
m
JN
TUH.
S
h
e
h
a
s
p
re
se
n
ted
4
5
re
se
a
rc
h
p
a
p
e
rs
in
in
tern
a
ti
o
n
a
l
jo
u
rn
a
ls/co
n
fe
re
n
c
e
s
a
n
d
th
re
e
p
a
ten
ts.
S
h
e
is
a
S
e
n
io
r
m
e
m
b
e
r
o
f
IEE
E
,
Li
fe
m
e
m
b
e
r
o
f
IS
TE
a
n
d
M
e
m
b
e
r
o
f
I
ET
E.
He
r
a
re
a
s
o
f
re
se
a
r
c
h
in
tere
st
a
re
Bio
-
M
e
d
ica
l,
S
ig
n
a
l
a
n
d
Im
a
g
e
P
r
o
c
e
ss
in
g
,
Emb
e
d
d
e
d
sy
ste
m
s,
IOT,
M
a
c
h
i
n
e
Lea
rn
in
g
a
n
d
d
e
e
p
lea
rn
i
n
g
to
c
re
a
te
so
c
ieta
l
imp
a
c
t.
S
h
e
h
a
s
re
c
e
iv
e
d
a
n
AICT
E
-
RP
S
with
a
n
a
m
o
u
n
t
o
f
8
.
2
5
lak
h
s.
S
h
e
is
th
e
Co
o
rd
in
a
t
o
r
o
f
QS
a
n
d
UG
C
a
n
d
a
c
ti
v
e
ly
in
v
o
l
v
e
d
in
NBA
,
NA
AC
a
n
d
JN
TUH
wo
rk
s
a
t
in
stit
u
te
le
v
e
l.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
ra
jan
ik
u
m
a
ri_
l
v
@v
n
rv
ji
e
t.
in
.
Ba
b
ish
a
m
il
i
Da
r
a
v
a
t
h
Hy
d
e
ra
b
a
d
c
o
m
p
lete
d
B.
Tec
h
in
ECE
.
S
h
e
is
p
re
se
n
tl
y
p
u
rsu
i
n
g
M
.
Tec
h
i
n
VN
R
VJ
IET
,
Hy
d
e
ra
b
a
d
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
b
a
b
y
d
a
ra
v
a
th
0
6
@g
m
a
il
.
c
o
m
.
Ya
r
la
g
a
d
d
a
Pa
d
m
a
S
a
i
is
p
ro
fe
ss
o
r
a
n
d
De
a
n
-
S
t
u
d
e
n
t
P
ro
g
re
ss
io
n
ECE
,
VN
RVJ
IET
,
Hy
d
e
ra
b
a
d
h
a
s
re
c
e
iv
e
d
P
h
.
D
.
in
B
io
-
m
e
d
ica
l
S
i
g
n
a
l
p
ro
c
e
ss
in
g
fro
m
Os
m
a
n
ia
Un
iv
e
rsity
.
S
h
e
is
a
se
n
io
r
m
e
m
b
e
r
o
f
IEE
E,
Li
fe
m
e
m
b
e
r
o
f
IS
TE
,
IS
OI,
ASCI
a
n
d
F
e
ll
o
w o
f
IET
E,
IEI
,
C
h
a
irma
n
fo
r
WI
E
Aff
in
it
y
G
ro
u
p
IEE
E
Hy
d
e
ra
b
a
d
S
e
c
ti
o
n
.
S
h
e
h
a
s p
re
se
n
ted
a
n
d
p
u
b
li
sh
e
d
8
0
re
se
a
rc
h
p
a
p
e
rs
i
n
Na
ti
o
n
a
l
a
n
d
I
n
tern
a
ti
o
n
a
l
Co
n
fe
re
n
c
e
s/Jo
u
rn
a
ls
.
On
e
o
f
th
e
in
v
e
n
to
rs
o
f
th
e
p
a
ten
t
a
n
d
p
u
b
li
s
h
e
d
b
y
In
d
ian
P
a
te
n
t
o
ffice
Ti
t
led
a
M
e
th
o
d
a
n
d
S
y
ste
m
fo
r
An
a
ly
z
in
g
Risk
As
so
c
iate
d
with
Re
sp
irato
ry
S
o
u
n
d
s.
S
h
e
h
a
s
re
c
e
iv
e
d
2
a
wa
rd
s
(o
n
e
G
o
ld
a
n
d
sp
e
c
ial
p
r
ize
)
fro
m
Ko
re
a
In
tern
a
ti
o
n
a
l
Wo
m
e
n
I
n
v
e
n
ti
o
n
E
x
p
o
si
ti
o
n
(KIWIE
-
2
0
1
9
)
a
s
wo
m
e
n
e
n
trep
re
n
e
u
r
o
f
S
a
lcit
Te
c
h
n
o
l
o
g
ies
P
riv
a
te
Li
m
it
e
d
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
p
a
d
m
a
sa
i_
y
@v
n
rv
j
iet.
in
.
Evaluation Warning : The document was created with Spire.PDF for Python.