I
nte
rna
t
io
na
l J
o
urna
l o
f
I
nfo
rm
a
t
ics a
nd
Co
m
m
un
ica
t
io
n T
ec
hn
o
lo
g
y
(
I
J
-
I
CT
)
Vo
l.
1
5
,
No
.
1
,
M
ar
ch
20
2
6
,
p
p
.
21
7
~
22
7
I
SS
N:
2252
-
8
7
7
6
,
DOI
:
1
0
.
1
1
5
9
1
/iji
ct
.
v
1
5
i
1
.
pp
21
7
-
22
7
217
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ict.
ia
esco
r
e.
co
m
Fet
a
l el
ectr
o
ca
rdi
o
g
ra
m ex
traction
a
nd sig
na
l qual
ity
a
ss
ess
ment using
sta
tistical me
thod
L
i M
un
Ng
1
,
Nur
Ani
da
J
um
a
di
1,
2
,
F
a
ra
h Na
j
ida
h No
o
riza
n
1
1
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
o
n
i
c
E
n
g
i
n
e
e
r
i
n
g
,
F
a
c
u
l
t
y
o
f
El
e
c
t
r
i
c
a
l
a
n
d
El
e
c
t
r
o
n
i
c
En
g
i
n
e
e
r
i
n
g
,
U
n
i
v
e
r
s
i
t
i
T
u
n
H
u
ss
e
i
n
O
n
n
M
a
l
a
y
s
i
a
,
B
a
t
u
P
a
h
a
t
,
M
a
l
a
y
si
a
2
P
r
i
n
c
i
p
al
R
e
se
a
r
c
h
e
r
i
n
A
d
v
a
n
c
e
d
M
e
d
i
c
a
l
I
mag
i
n
g
a
n
d
O
p
t
i
c
s
(
A
d
M
e
d
i
c
)
,
U
n
i
v
e
r
si
t
i
Tu
n
H
u
sse
i
n
O
n
n
M
a
l
a
y
si
a
,
B
a
t
u
P
a
h
a
t
,
M
a
l
a
y
si
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
an
2
2
,
2
0
2
5
R
ev
is
ed
Oct
2
9
,
2
0
2
5
Acc
ep
ted
No
v
5
,
2
0
2
5
Ab
d
o
m
i
n
a
l
e
lec
tro
c
a
rd
i
o
g
ra
m
(a
ECG
)
c
a
n
b
e
u
se
d
to
m
o
n
it
o
r
fe
tal
h
e
a
rt
ra
te
(fHR),
p
ro
v
id
i
n
g
c
ri
ti
c
a
l
in
sig
h
ts
in
t
o
fe
tal
h
e
a
lt
h
d
u
r
in
g
p
re
g
n
a
n
c
y
.
Ho
we
v
e
r,
se
p
a
ra
ti
n
g
t
h
e
m
ix
e
d
sig
n
a
ls
o
f
fe
tal
ECG
(fE
CG
)
a
n
d
m
a
tern
a
l
ECG
(m
EC
G
)
with
in
th
e
a
ECG
re
m
a
in
s
a
c
rit
ica
l
c
h
a
ll
e
n
g
e
.
T
h
is
p
a
p
e
r
in
v
e
stig
a
tes
t
h
e
in
te
g
ra
ti
o
n
o
f
st
a
ti
stica
l
m
e
tri
c
s,
in
c
lu
d
i
n
g
si
g
n
a
l
-
to
-
n
o
ise
ra
ti
o
(S
NR),
sk
e
wn
e
ss
,
k
u
rt
o
sis,
sta
n
d
a
rd
d
e
v
iati
o
n
,
a
n
d
v
a
rian
c
e
to
a
ss
e
ss
fECG
sig
n
a
l
q
u
a
li
t
y
d
u
ri
n
g
e
x
tra
c
ti
o
n
u
sin
g
t
h
re
e
a
d
a
p
ti
v
e
fi
lt
e
ri
n
g
m
e
to
d
s
(
(
L
e
a
st
m
e
a
n
sq
u
a
re
(LM
S
),
n
o
r
m
a
li
z
e
d
LM
S
(NLM
S
)
,
a
n
d
re
c
u
rsiv
e
lea
st
sq
u
a
re
(RLS
))
a
n
d
i
n
d
e
p
e
n
d
e
n
t
c
o
m
p
o
n
e
n
t
a
n
a
ly
sis
(
ICA
)
.
Th
e
fin
d
in
g
s
re
v
e
a
l
th
a
t
RLS
a
c
h
ie
v
e
s
th
e
b
e
st p
e
rfo
rm
a
n
c
e
a
m
o
n
g
t
h
e
t
h
re
e
AF
m
e
th
o
d
s
,
with
th
e
h
i
g
h
e
st
S
NR
o
f
5
.
6
d
B
a
t
th
e
ste
p
siz
e
,
µ
o
f
0
.
9
.
F
o
r
IC
A
with
a
b
a
n
d
p
a
ss
Ch
e
b
y
s
h
e
v
fil
ter
(l
o
w
-
c
u
t
fre
q
u
e
n
c
y
=
1
Hz
,
h
ig
h
-
c
u
t
fre
q
u
e
n
c
y
=
5
0
Hz
)
p
r
o
d
u
c
e
s
a
n
S
NR
o
f
0
.
8
6
d
B.
Ad
d
it
i
o
n
a
ll
y
,
b
o
t
h
RLS
a
n
d
I
CA
y
iel
d
sim
il
a
r
fHR
v
a
lu
e
s
o
f
1
3
3
b
p
m
with
a
P
E
m
e
a
su
re
m
e
n
t
o
f
0
.
9
%
.
In
c
o
n
c
lu
si
o
n
,
i
n
teg
ra
ti
n
g
sta
ti
stica
l
m
e
tri
c
s
with
ICA
a
n
d
RLS
e
ffe
c
ti
v
e
ly
e
x
trac
ts
fECG
with
g
o
o
d
sig
n
a
l
q
u
a
li
ty
.
F
u
tu
re
re
se
a
rc
h
c
o
u
ld
e
x
p
l
o
re
o
t
h
e
r
ECG
d
a
tas
e
ts
a
n
d
i
n
c
o
r
p
o
ra
te
m
a
c
h
in
e
lea
rn
in
g
to
fu
r
th
e
r
imp
ro
v
e
f
ECG
e
x
trac
ti
o
n
a
n
d
si
g
n
a
l
q
u
a
li
ty
a
ss
e
ss
m
e
n
t.
K
ey
w
o
r
d
s
:
Ad
ap
tiv
e
f
ilter
in
g
E
lectr
o
ca
r
d
io
g
r
am
Fetal
I
n
d
ep
e
n
d
en
t c
o
m
p
o
n
en
t
an
aly
s
is
Sig
n
al
ex
tr
ac
tio
n
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
:
Nu
r
An
id
a
J
u
m
ad
i
Dep
ar
tm
en
t o
f
E
lectr
o
n
ic
E
n
g
in
ee
r
in
g
,
Facu
lty
o
f
E
lectr
ical
an
d
E
lectr
o
n
ic
E
n
g
in
ee
r
in
g
Un
iv
er
s
iti T
u
n
Hu
s
s
ein
On
n
Ma
lay
s
ia
B
atu
Pah
at,
Ma
lay
s
ia
E
m
ail:
an
id
a@
u
th
m
.
ed
u
.
m
y
1.
I
NT
RO
D
UCT
I
O
N
An
elec
tr
o
ca
r
d
io
g
r
am
(
E
C
G)
is
b
est
k
n
o
wn
f
o
r
its
ap
p
licab
ilit
y
in
r
ec
o
r
d
in
g
th
e
elec
tr
ical
ac
tiv
ity
o
f
ca
r
d
iac
[
1]
.
I
t
tr
ac
es
th
e
en
tir
e
cy
cle
o
f
elec
tr
ical
im
p
u
ls
es
as
th
ey
tr
av
el
th
r
o
u
g
h
th
e
ca
r
d
iac
m
u
s
cle
d
u
r
in
g
co
n
tr
ac
tio
n
a
n
d
r
elax
atio
n
.
T
h
e
illu
s
tr
atio
n
in
Fig
u
r
e
1
d
is
p
lay
s
th
e
E
C
G
s
ig
n
al
wav
ef
o
r
m
g
en
e
r
ated
b
y
a
s
in
g
le
h
ea
r
tb
ea
t,
h
ig
h
lig
h
ti
n
g
its
d
is
tin
ct
c
o
m
p
o
n
en
ts
:
th
e
P
wav
e,
QR
S
co
m
p
lex
,
T
wav
e,
an
d
ST
s
eg
m
en
t.
E
ac
h
o
f
th
ese
elem
en
ts
r
ep
r
esen
ts
a
s
p
ec
if
ic
p
h
ase
o
f
c
ar
d
iac
ac
tiv
ity
,
an
d
a
d
etaile
d
an
aly
s
is
o
f
th
eir
v
ar
iatio
n
s
p
r
o
v
id
es
cr
u
cial
in
s
ig
h
ts
in
to
th
e
h
ea
r
t'
s
h
ea
l
th
[
2
]
.
B
y
ex
am
in
i
n
g
th
e
a
lter
atio
n
s
in
th
ese
wav
ef
o
r
m
s
,
h
ea
lth
ca
r
e
p
r
o
f
es
s
io
n
als
ca
n
u
n
co
v
e
r
p
o
te
n
tial
ca
r
d
io
v
ascu
lar
is
s
u
es
an
d
b
e
tter
u
n
d
er
s
tan
d
th
e
f
u
n
ctio
n
i
n
g
o
f
th
e
h
ea
r
t d
u
r
in
g
d
if
f
er
en
t stag
es o
f
its
r
h
y
th
m
.
T
h
e
E
C
G
is
a
cr
u
cial
to
o
l
in
m
o
n
ito
r
in
g
th
e
h
ea
lth
s
tatu
s
o
f
a
d
ev
elo
p
in
g
f
et
u
s
.
R
ec
en
t
r
esear
ch
h
as
f
o
cu
s
ed
o
n
th
e
ch
allen
g
in
g
ta
s
k
o
f
is
o
latin
g
th
e
f
etal
E
C
G
(
f
E
C
G)
s
ig
n
al
f
r
o
m
th
e
a
b
d
o
m
in
al
E
C
G
(
aE
C
G)
s
ig
n
al,
wh
ich
in
clu
d
es
co
n
tr
i
b
u
tio
n
s
f
r
o
m
b
o
th
th
e
m
ate
r
n
al
E
C
G
(
m
E
C
G)
an
d
th
e
f
etu
s
.
T
h
is
p
r
o
ce
d
u
r
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
7
6
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
,
Vo
l.
1
5
,
No
.
1
,
Ma
r
ch
20
2
6
:
21
7
-
2
2
7
218
h
o
ld
s
s
ig
n
if
ican
t
im
p
o
r
tan
ce
a
s
th
e
ex
tr
ac
ted
f
E
C
G
s
ig
n
al
ca
n
b
e
p
r
o
ce
s
s
ed
an
d
an
aly
ze
d
to
ass
e
s
s
th
e
we
ll
-
b
ein
g
o
f
th
e
f
etu
s
d
u
r
in
g
p
r
eg
n
an
cy
.
T
h
e
ch
a
llen
g
e
lies
in
t
h
e
f
ac
t
th
at
th
e
f
E
C
G
s
ig
n
al
o
f
ten
r
esem
b
les
th
e
m
E
C
G
s
ig
n
al
d
u
e
to
its
o
v
er
l
ap
p
in
g
ch
ar
ac
ter
is
tics
in
b
o
th
f
r
eq
u
en
cy
an
d
tem
p
o
r
al
d
o
m
ain
s
.
T
h
is
o
v
er
la
p
lead
s
to
th
e
p
r
o
d
u
ctio
n
o
f
s
tr
ik
in
g
ly
s
im
ilar
wav
ef
o
r
m
s
,
m
ak
in
g
it
d
if
f
icu
lt
to
d
is
tin
g
u
is
h
b
etwe
en
th
e
two
s
ig
n
als.
As
a
r
esu
lt,
ac
cu
r
ately
r
ec
o
g
n
izin
g
an
d
is
o
latin
g
th
e
f
E
C
G
f
r
o
m
th
e
m
E
C
G
b
ec
o
m
es
a
co
m
p
lex
task
,
co
m
p
licatin
g
an
aly
s
is
an
d
in
t
er
p
r
etatio
n
in
clin
ical
s
ettin
g
s
[
3
]
.
Du
r
in
g
p
r
eg
n
an
cy
,
th
e
f
etal’
s
h
ea
r
t
b
ea
ts
s
ig
n
if
ican
tly
f
aster
th
an
th
e
m
o
th
er
’
s
h
ea
r
t.
T
y
p
ically
,
th
e
f
e
tal
h
ea
r
t
r
ate
(
f
HR
)
r
an
g
es
f
r
o
m
1
1
0
to
1
6
0
b
ea
t
-
p
er
-
m
in
u
te
(
b
p
m
)
[
4
]
,
wh
er
e
as
m
ater
n
al
h
ea
r
t
r
ate
(
m
HR
)
g
en
er
ally
f
alls
b
etwe
en
7
0
an
d
9
0
b
p
m
[
5
]
.
T
h
er
ef
o
r
e,
s
u
itab
le
tech
n
iq
u
es
an
d
s
tr
ateg
ies
m
u
s
t
b
e
em
p
lo
y
ed
to
s
u
cc
ess
f
u
lly
is
o
late
a
n
d
s
ep
ar
ate
th
e
f
etal
s
ig
n
al
f
r
o
m
m
ate
r
n
al
in
ter
f
e
r
e
n
ce
.
Fig
u
r
e
1
.
An
E
C
G
s
ig
n
al
wav
ef
o
r
m
o
f
o
n
e
h
ea
r
t
b
ea
t
[
1
]
T
h
e
s
tu
d
y
b
y
S
iew
et
a
l
.
[
7
]
d
em
o
n
s
tr
ated
t
h
at
th
e
e
n
s
e
m
b
le
Kalm
an
f
ilter
(
E
n
KF)
ef
f
ec
tiv
ely
ex
tr
ac
ts
f
E
C
G
f
r
o
m
s
in
g
le
-
ch
a
n
n
el
E
C
G,
o
u
tp
er
f
o
r
m
in
g
th
e
e
x
ten
d
ed
Kalm
an
f
ilter
(
E
KF)
in
ac
cu
r
ac
y
[
6
]
.
I
n
an
o
th
er
s
tu
d
y
,
a
co
m
b
in
atio
n
o
f
B
u
t
ter
wo
r
th
an
d
Sav
itzk
y
-
Go
lay
f
ilter
s
was
u
s
ed
f
o
r
m
E
C
G
ex
tr
ac
tio
n
,
with
th
e
Sav
itzk
y
-
Go
lay
f
ilter
al
s
o
ap
p
lied
f
o
r
f
E
C
G
ex
tr
ac
tio
n
.
A
co
m
p
ar
ativ
e
s
tu
d
y
b
y
Gan
et
a
l
.
[
8
]
co
m
p
ar
ativ
e
s
tu
d
y
o
n
th
e
u
s
e
o
f
C
h
eb
y
s
h
ev
T
y
p
e
1
an
d
B
u
tter
wo
r
th
f
ilter
s
s
h
o
wed
th
at
C
h
eb
y
s
h
ev
T
y
p
e
1
p
r
o
v
e
d
m
o
r
e
ef
f
ec
tiv
e
in
ex
tr
ac
tin
g
th
e
f
E
C
G
s
ig
n
al.
R
ec
en
t
f
in
d
i
n
g
s
o
f
J
eb
a
et
a
l
.
[
9
]
in
tr
o
d
u
ce
d
a
tim
e
-
f
r
eq
u
e
n
cy
a
n
aly
s
is
alg
o
r
ith
m
t
h
at
em
p
lo
y
ed
th
e
Sto
ck
well
tr
an
s
f
o
r
m
an
d
S
h
an
n
o
n
E
n
er
g
y
E
n
tr
o
p
y
to
id
en
tif
y
m
ater
n
al
p
ea
k
s
.
T
h
is
ap
p
r
o
ac
h
allo
ws
f
o
r
f
E
C
G
s
ig
n
al
ex
tr
ac
tio
n
ev
en
in
ca
s
es
o
f
o
v
er
la
p
p
in
g
b
ea
ts
with
o
u
t
ex
ten
s
iv
e
p
r
ep
r
o
ce
s
s
in
g
.
T
h
e
alg
o
r
ith
m
ap
p
lied
t
h
e
Sto
ck
well
tr
an
s
f
o
r
m
as
a
tim
e
-
f
r
eq
u
e
n
cy
to
o
l
alo
n
g
with
Sh
an
n
o
n
E
n
er
g
y
E
n
tr
o
p
y
to
i
d
en
tify
m
ate
r
n
al
p
ea
k
s
,
wh
ile
th
e
S
-
tr
an
s
f
o
r
m
was
u
s
ed
t
o
id
en
tify
f
etal
p
ea
k
s
.
T
h
is
m
eth
o
d
en
h
an
ce
d
p
er
f
o
r
m
an
ce
in
th
e
tim
e
-
f
r
eq
u
e
n
cy
d
o
m
ain
,
ef
f
ec
tiv
ely
id
en
tif
y
in
g
b
o
th
m
ate
r
n
al
an
d
f
etal
p
ea
k
s
,
an
d
elim
in
ated
th
e
n
ee
d
f
o
r
ex
p
licit p
r
ep
r
o
ce
s
s
in
g
.
B
lin
d
s
o
u
r
ce
s
ep
ar
atio
n
(
B
SS
)
is
a
co
m
p
u
tatio
n
al
tech
n
iq
u
e
th
at
is
o
lates
th
e
m
ix
ed
s
ig
n
als
with
o
u
t
h
av
in
g
to
ac
q
u
ir
e
p
r
io
r
k
n
o
wl
ed
g
e
o
f
th
e
o
r
ig
in
al
s
ig
n
als
[
1
0
]
.
I
n
d
ep
e
n
d
en
t
c
o
m
p
o
n
en
t
an
aly
s
is
(
I
C
A)
an
d
p
r
in
cip
al
co
m
p
o
n
e
n
t a
n
aly
s
is
(
PC
A)
ar
e
th
e
two
m
o
s
t p
o
p
u
l
ar
m
eth
o
d
s
o
f
B
SS
in
ex
tr
a
ctin
g
m
ix
ed
s
ig
n
als.
I
n
a
m
ajo
r
s
tu
d
y
b
y
T
ah
a
an
d
R
ah
ee
m
[
1
1
]
,
a
n
o
v
el
al
g
o
r
ith
m
k
n
o
wn
as
th
e
n
u
ll
s
p
ac
e
id
em
p
o
te
n
t
tr
an
s
f
o
r
m
atio
n
m
atr
ix
(
NSI
T
M)
was
d
ev
el
o
p
ed
to
ex
tr
ac
t
f
etal
elec
tr
o
ca
r
d
io
g
r
am
(
f
E
C
G)
s
ig
n
als
f
r
o
m
m
ater
n
al
ab
d
o
m
in
al
r
ec
o
r
d
in
g
s
u
s
in
g
th
e
B
SS
ap
p
r
o
ac
h
.
T
h
is
alg
o
r
ith
m
ca
lc
u
lated
an
in
tr
in
s
ic
tem
p
o
r
al
m
atr
ix
(
W
)
f
r
o
m
th
e
in
itial
E
C
G
in
p
u
t
an
d
esti
m
ated
th
e
r
aw
f
E
C
G
an
d
m
E
C
G
s
ig
n
als
f
r
o
m
th
e
n
u
ll
s
p
ac
e
o
f
W
.
T
h
e
clea
n
f
E
C
G
s
ig
n
al
was
o
b
tain
ed
b
y
elim
i
n
atin
g
th
e
i
n
ter
f
er
in
g
m
E
C
G
co
m
p
o
n
e
n
t
f
r
o
m
th
e
r
aw
f
E
C
G
s
ig
n
al.
Similar
ly
,
R
am
li
et
a
l
.
[
1
2
]
c
o
n
d
u
cted
a
co
m
p
ar
ativ
e
s
tu
d
y
to
ass
ess
th
e
ef
f
ec
tiv
en
ess
o
f
v
ar
io
u
s
B
SS
alg
o
r
ith
m
s
,
in
clu
d
in
g
f
ast
f
i
x
ed
-
p
o
in
t
f
o
r
I
C
A
(
Fas
tI
C
A)
,
jo
in
t
ap
p
r
o
x
im
ate
d
iag
o
n
ali
za
tio
n
eig
en
m
atr
ix
(
J
ADE
)
,
an
d
PC
A,
f
o
r
ex
tr
ac
tin
g
f
E
C
G
s
i
g
n
als
f
r
o
m
m
ater
n
al
ab
d
o
m
in
al
r
ec
o
r
d
in
g
s
.
Desp
ite
r
eq
u
ir
in
g
f
in
e
-
tu
n
in
g
,
Fas
tI
C
A
ac
h
iev
ed
co
m
p
ar
ab
le
ac
c
u
r
ac
y
to
J
ADE
an
d
e
x
h
ib
ited
g
r
ea
ter
f
lex
ib
ili
ty
in
h
an
d
lin
g
lo
w
-
q
u
ality
in
p
u
t sig
n
als.
I
n
an
o
th
e
r
ap
p
r
o
ac
h
,
I
C
A
was
co
m
b
in
ed
with
s
in
g
u
lar
v
al
u
e
d
ec
o
m
p
o
s
itio
n
(
SVD)
f
o
r
f
E
C
G
s
ig
n
al
ex
tr
ac
tio
n
[
1
3
]
.
I
n
itially
,
SVD
p
r
o
v
i
d
ed
a
p
p
r
o
x
im
atio
n
s
o
f
f
E
C
G
esti
m
ates,
b
u
t
th
ese
co
n
tain
ed
n
o
is
e
an
d
m
is
s
in
g
wav
ef
o
r
m
s
.
Fas
tI
C
A
th
en
u
tili
ze
d
m
E
C
G
s
ig
n
als
to
s
ep
ar
ate
n
o
is
e
f
r
o
m
th
e
f
E
C
G,
ef
f
ec
tiv
ely
r
ed
u
cin
g
r
esid
u
al
n
o
is
e
in
t
h
e
f
E
C
G
s
ig
n
als
an
d
ad
d
r
es
s
in
g
th
e
is
s
u
e
o
f
m
is
s
in
g
w
av
ef
o
r
m
s
.
Sev
er
al
r
esear
ch
er
s
h
av
e
ex
p
lo
r
ed
a
d
ap
tiv
e
f
ilter
-
b
ased
(
AF)
ap
p
r
o
ac
h
es
f
o
r
e
x
tr
ac
tin
g
th
e
f
E
C
G
s
ig
n
al
[
1
4
]
.
R
an
jan
ik
ar
et
a
l
.
[
1
5
]
p
r
o
p
o
s
ed
a
co
m
p
r
eh
en
s
iv
e
m
o
d
el
t
h
at
u
s
ed
ad
ap
tiv
e
n
o
is
e
ca
n
c
ellatio
n
to
r
em
o
v
e
b
ac
k
g
r
o
u
n
d
ar
tef
ac
ts
an
d
n
o
is
e
f
r
o
m
f
E
C
G
s
ig
n
als,
en
ab
lin
g
th
e
ex
tr
ac
tio
n
o
f
f
E
C
G
a
n
d
th
e
co
m
p
u
tatio
n
o
f
f
HR
.
Kah
an
k
o
v
a
et
a
l.
[
1
6
]
f
o
cu
s
ed
o
n
o
p
tim
izin
g
AF
c
o
n
tr
o
l
p
ar
am
eter
s
to
ac
h
iev
e
m
o
r
e
ef
f
icien
t
an
d
ac
cu
r
ate
n
o
n
-
in
v
asiv
e
e
x
tr
ac
tio
n
o
f
th
e
f
E
C
G
s
ig
n
al
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
I
SS
N:
2252
-
8
7
7
6
F
eta
l e
lectro
ca
r
d
io
g
r
a
m
ex
tr
a
ctio
n
a
n
d
s
ig
n
a
l q
u
a
lity a
s
s
ess
men
t u
s
in
g
s
ta
tis
tica
l m
eth
o
d
(
Li Mu
n
N
g
)
219
On
th
e
o
th
er
h
an
d
,
Al
-
Sh
eik
h
et
a
l
.
[
1
7
]
p
r
o
p
o
s
ed
a
n
ew
A
F
alg
o
r
ith
m
n
am
e
d
th
e
d
is
cr
et
e
wav
elet
tr
an
s
f
o
r
m
r
ec
u
r
s
iv
e
i
n
v
er
s
e
(
DW
T
-
R
I
)
f
o
r
f
E
C
G
s
ig
n
al
e
x
tr
ac
tio
n
f
r
o
m
th
e
aE
C
G
s
ig
n
al
.
T
h
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
ef
f
ec
tiv
ely
s
u
p
p
r
ess
ed
m
E
C
G
p
r
o
jectio
n
s
an
d
ex
tr
ac
ted
f
E
C
G
co
m
p
o
n
en
ts
f
r
o
m
th
e
aE
C
G
s
ig
n
al.
T
h
e
p
er
f
o
r
m
an
ce
o
f
th
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
was
ev
alu
ated
a
g
ain
s
t
o
th
er
tr
ad
itio
n
al
AF
alg
o
r
ith
m
s
,
in
clu
d
in
g
least
m
ea
n
s
q
u
ar
e
(
L
MS)
,
r
ec
u
r
s
iv
e
least
s
q
u
ar
e
(
R
L
S),
an
d
R
I
,
u
s
in
g
b
o
th
s
y
n
th
etic
a
n
d
ac
tu
al
clin
ical
d
ata.
T
h
e
r
esu
lts
d
em
o
n
s
tr
ate
th
at
t
h
e
DW
T
-
R
I
AF
alg
o
r
ith
m
o
u
t
p
er
f
o
r
m
s
o
th
er
alg
o
r
ith
m
s
'
ac
cu
r
ac
y
a
n
d
p
o
s
itiv
e
p
r
ed
ictiv
ity
,
m
ak
in
g
it
a
p
r
o
m
is
in
g
to
o
l
f
o
r
f
E
C
G
ex
tr
ac
tio
n
.
Usi
n
g
th
is
a
p
p
r
o
ac
h
,
r
esear
c
h
er
s
h
av
e
b
ee
n
a
b
le
to
p
er
f
o
r
m
th
e
f
E
C
G
s
ig
n
al
ex
tr
ac
tio
n
ef
f
icien
tly
,
d
e
m
o
n
s
tr
a
tin
g
its
v
er
s
atility
an
d
r
o
b
u
s
tn
ess
ac
r
o
s
s
d
if
f
er
en
t
r
esear
ch
co
n
tex
ts
[
1
8
]
–
[
2
0
]
.
W
h
ile
th
ese
tech
n
iq
u
es
h
av
e
d
em
o
n
s
tr
ated
p
o
te
n
tial,
th
ey
o
f
ten
r
ely
o
n
s
p
ec
if
ic
alg
o
r
ith
m
ic
ass
u
m
p
tio
n
s
an
d
d
o
n
o
t
f
u
ll
y
u
tili
ze
s
tatis
t
ical
m
ea
s
u
r
es
lik
e
s
ig
n
al
-
to
-
n
o
is
e
r
atio
(
S
NR
)
,
k
u
r
to
s
is
,
an
d
v
ar
ian
ce
,
wh
ich
c
o
u
ld
o
f
f
er
d
ee
p
er
in
s
ig
h
ts
in
to
s
ig
n
al
q
u
ality
an
d
s
tab
ilit
y
.
T
h
is
g
ap
h
ig
h
lig
h
ts
th
e
n
ee
d
f
o
r
m
eth
o
d
o
l
o
g
ies
th
at
s
y
s
tem
ati
ca
lly
in
teg
r
ate
s
tatis
t
ical
m
etr
ics
with
ad
v
an
ce
d
s
ig
n
al
p
r
o
ce
s
s
in
g
to
o
p
tim
ize
th
e
s
ep
ar
atio
n
o
f
f
E
C
G
f
r
o
m
m
E
C
G,
p
ar
ticu
lar
ly
in
n
o
is
y
o
r
lo
w
-
q
u
ality
d
atasets
.
T
h
is
s
tu
d
y
ai
m
s
t
o
b
r
id
g
e
th
is
g
ap
b
y
co
m
p
a
r
in
g
two
p
r
o
m
in
en
t
m
eth
o
d
o
l
o
g
ies,
n
am
ely
ad
ap
tiv
e
f
ilter
in
g
(
AF)
a
n
d
I
C
A,
th
r
o
u
g
h
a
s
tatis
t
ical
an
aly
s
is
f
r
am
ewo
r
k
.
AF
is
v
alu
ed
f
o
r
its
co
m
p
u
tatio
n
al
s
im
p
licity
,
an
d
its
p
e
r
f
o
r
m
a
n
ce
will
b
e
ass
es
s
ed
u
s
in
g
th
r
ee
alg
o
r
ith
m
s
:
L
M
S,
No
r
m
alize
d
L
MS
(
NL
MS)
,
an
d
R
L
S.
On
t
h
e
o
t
h
er
h
an
d
,
I
C
A
ex
ce
ls
at
s
ep
ar
atin
g
in
d
ep
en
d
en
t
co
m
p
o
n
e
n
ts
f
r
o
m
m
ix
ed
s
ig
n
al
s
.
B
y
in
co
r
p
o
r
atin
g
s
tatis
tical
m
ea
s
u
r
es
s
u
ch
as
SNR
,
k
u
r
to
s
is
,
an
d
v
ar
ian
ce
,
t
h
is
s
tu
d
y
s
ee
k
s
to
ev
alu
ate
a
n
d
en
h
a
n
ce
th
e
ef
f
ec
tiv
en
ess
o
f
th
ese
m
eth
o
d
s
f
o
r
f
E
C
G
ex
tr
ac
tio
n
.
T
h
e
f
E
C
G
s
i
g
n
als an
aly
ze
d
in
th
is
s
tu
d
y
ar
e
s
o
u
r
ce
d
f
r
o
m
th
e
d
atab
ase
f
o
r
th
e
id
en
tific
atio
n
o
f
s
y
s
tem
s
(
DAI
SY)
an
d
p
r
o
c
ess
ed
u
s
in
g
Py
th
o
n
a
n
d
MA
T
L
AB
s
o
f
twar
e.
B
r
ief
ly
,
Sectio
n
1
p
r
o
v
id
es
a
n
o
v
er
v
iew
o
f
th
e
to
p
ic
an
d
r
ev
iews
r
ec
en
t
ad
v
an
ce
s
in
f
E
C
G
s
ig
n
al
ex
tr
ac
tio
n
m
et
h
o
d
o
lo
g
ies.
Sec
tio
n
2
d
etails
th
e
m
ate
r
ials
an
d
m
eth
o
d
o
lo
g
y
,
s
ec
tio
n
3
p
r
es
en
ts
th
e
r
esu
lts
an
d
d
is
cu
s
s
io
n
o
f
th
e
s
ig
n
al
q
u
ality
an
aly
s
is
,
an
d
s
ec
tio
n
4
co
n
clu
d
es
th
e
s
tu
d
y
with
k
ey
f
in
d
in
g
s
an
d
r
ec
o
m
m
en
d
atio
n
s
f
o
r
f
u
tu
r
e
r
esear
ch
.
B
y
co
m
b
in
in
g
s
tatis
tical
in
s
ig
h
ts
with
p
r
o
v
e
n
s
ig
n
al
p
r
o
ce
s
s
in
g
m
eth
o
d
s
,
th
is
r
esear
ch
aim
s
to
im
p
r
o
v
e
th
e
r
eliab
ilit
y
,
ac
cu
r
ac
y
,
an
d
clin
ical
ap
p
licab
ilit
y
o
f
f
E
C
G
ex
tr
ac
tio
n
tech
n
iq
u
es.
2.
RE
S
E
ARCH
M
E
T
H
O
D
T
h
e
m
eth
o
d
o
lo
g
y
ad
o
p
t
ed
in
t
h
is
s
tu
d
y
f
o
llo
ws
a
s
eq
u
e
n
tial
an
d
s
tr
u
ctu
r
ed
o
r
d
er
.
First,
th
e
DAI
SY
E
C
G
d
ataset
u
s
ed
f
o
r
t
h
e
e
x
p
er
im
en
ts
is
d
escr
ib
ed
in
s
ec
tio
n
2
.
1
.
Sectio
n
2
.
2
o
u
tlin
es
t
h
e
s
im
u
latio
n
to
o
ls
an
d
p
r
e
p
r
o
ce
s
s
in
g
tech
n
iq
u
es a
p
p
lied
to
p
r
ep
ar
e
th
e
E
C
G
d
a
ta
f
o
r
an
al
y
s
is
.
Fo
llo
win
g
th
is
,
s
ec
tio
n
2
.
3
d
etails
th
e
ap
p
licatio
n
o
f
AF
an
d
I
C
A
to
s
ep
ar
ate
th
e
f
E
C
G
an
d
m
E
C
G
s
ig
n
als
f
r
o
m
th
e
aE
C
G
r
ec
o
r
d
i
n
g
s
.
Fin
ally
,
s
ec
tio
n
2
.
4
p
r
esen
ts
th
e
s
tatis
ti
ca
l m
eth
o
d
s
u
s
ed
to
ass
ess
th
e
q
u
ality
o
f
th
e
ex
tr
ac
te
d
f
E
C
G
s
ig
n
als.
2
.
1
.
Da
t
a
ba
s
e
s
elec
t
io
n
DAI
SY
d
at
ab
ase
was
c
h
o
s
e
n
f
o
r
t
h
is
s
t
u
d
y
[
2
1
]
.
I
t
is
a
n
o
n
li
n
e
d
at
aset
c
o
m
p
r
is
i
n
g
v
ar
i
o
u
s
d
a
ta
ca
t
eg
o
r
ies
s
u
c
h
as
b
io
m
e
d
i
ca
l
s
y
s
te
m
s
,
ele
ct
r
ic
al
a
n
d
ele
ct
r
o
n
ic
s
y
s
te
m
s
,
b
i
o
c
h
em
i
ca
l
s
y
s
t
e
m
s
,
a
n
d
m
e
ch
a
n
ic
al
s
y
s
te
m
s
t
h
at
a
r
e
a
v
ail
ab
le
t
o
b
e
u
s
e
d
b
y
r
ese
ar
ch
er
s
.
T
h
is
s
t
u
d
y
o
b
ta
in
ed
a
s
e
t o
f
E
C
G
r
ec
o
r
d
in
g
s
f
o
r
th
e
f
E
C
G
s
ig
n
al
s
e
p
a
r
a
ti
o
n
.
I
t
is
a
1
0
-
s
ec
o
n
d
c
u
ta
n
e
o
u
s
p
o
te
n
t
ial
r
ec
o
r
d
i
n
g
o
f
a
p
r
eg
n
an
t
w
o
m
a
n
co
n
s
is
t
in
g
o
f
ei
g
h
t
ch
an
n
els,
w
h
e
r
e
c
h
a
n
n
els
A
1
t
o
A
5
a
r
e
aE
C
G
s
i
g
n
als
a
n
d
c
h
an
n
e
ls
T
6
t
o
T
8
a
r
e
t
h
o
r
a
ci
c
E
C
G
(
t
E
C
G
)
s
i
g
n
als
.
T
h
e
n
u
m
b
e
r
o
f
s
am
p
l
es
f
o
r
t
h
i
s
E
C
G
d
at
ase
t
is
2
5
0
0
,
wh
ic
h
g
i
v
es
th
e
s
a
m
p
li
n
g
f
r
e
q
u
e
n
cy
at
2
5
0
H
z.
Fi
g
u
r
e
2
d
is
p
la
y
s
t
h
e
p
l
o
t
te
d
E
C
G
c
h
a
n
n
els
f
r
o
m
t
h
e
DA
I
SY
d
atas
et.
F
o
r
t
h
e
AF
m
et
h
o
d
,
o
n
ly
ch
a
n
n
els
A
1
(
r
e
p
r
ese
n
ti
n
g
a
E
C
G
)
a
n
d
T
8
(
r
ep
r
es
en
ti
n
g
tECG
)
we
r
e
u
s
e
d
f
o
r
an
al
y
s
is
,
as
th
is
c
o
m
b
in
ati
o
n
y
iel
d
ed
th
e
m
o
s
t
s
ig
n
i
f
ic
a
n
t
r
es
u
l
ts
.
O
n
th
e
o
t
h
e
r
h
a
n
d
,
all
c
h
a
n
n
els
w
er
e
em
p
l
o
y
e
d
in
t
h
e
I
C
A
an
al
y
s
is
.
2
.
2
.
Sim
ula
t
i
o
n t
o
o
ls
a
nd
da
t
a
pre
-
pro
ce
s
s
ing
T
h
is
s
tu
d
y
e
m
p
lo
y
e
d
Py
t
h
o
n
a
n
d
MA
T
L
AB
as
s
im
u
latio
n
to
o
ls
to
r
u
n
th
e
e
x
p
er
im
e
n
ts
.
T
h
e
p
u
r
p
o
s
e
o
f
u
tili
zin
g
two
d
if
f
er
e
n
t
to
o
ls
is
to
ex
p
lo
r
e
th
eir
ca
p
ab
ilit
ies
f
o
r
s
im
u
latin
g
b
io
m
ed
ical
en
g
in
ee
r
in
g
ap
p
licatio
n
s
.
Py
C
h
ar
m
2
0
2
2
.
3
.
1
(
C
o
m
m
u
n
ity
e
d
itio
n
)
[
2
2
]
an
d
MA
T
L
AB
2
0
2
4
b
[
2
3
]
we
r
e
u
s
ed
t
o
co
n
d
u
c
t
th
e
s
tatis
tical
an
aly
s
i
s
f
o
r
th
e
f
E
C
G
s
ig
n
al
ex
tr
ac
tio
n
.
T
h
e
AF
m
eth
o
d
was
p
er
f
o
r
m
ed
u
s
in
g
Py
th
o
n
,
wh
er
ea
s
th
e
I
C
A
ap
p
r
o
ac
h
was c
ar
r
ied
o
u
t u
s
in
g
MA
T
L
AB
2
0
2
4
b
.
Prio
r
to
ex
tr
ac
tin
g
th
e
f
E
C
G
s
ig
n
al,
th
e
aE
C
G
d
ata
wer
e
p
r
ep
r
o
ce
s
s
ed
with
th
e
u
s
e
o
f
v
ar
i
o
u
s
f
ilter
s
an
d
f
r
e
q
u
en
cies
f
o
r
d
ata
clea
n
in
g
.
Fiv
e
b
an
d
p
ass
f
ilter
s
,
n
a
m
ely
B
u
tter
wo
r
th
,
C
h
eb
y
s
h
e
v
T
y
p
e
I
a
n
d
T
y
p
e
I
I
,
E
llip
tic,
an
d
B
ess
el,
wer
e
tr
ie
d
o
u
t
u
s
in
g
two
lo
w
-
c
u
t
f
r
eq
u
en
cies
(
f
Low
)
,
0
.
5
Hz
an
d
1
Hz,
an
d
two
h
ig
h
-
cu
t
f
r
eq
u
e
n
cies
(
f
High
)
,
4
5
Hz
an
d
5
0
Hz.
T
o
id
en
tif
y
th
e
b
est
f
ilter
,
th
e
SNR
an
aly
s
is
wa
s
im
p
l
em
en
ted
.
Fro
m
th
e
co
m
b
in
atio
n
o
f
f
ilter
test
in
g
s
(
th
e
co
m
p
lete
r
esu
lts
ar
e
n
o
t
s
h
o
wn
h
er
e)
,
th
e
f
in
al
ch
o
s
en
f
ilter
was
th
e
b
an
d
p
ass
C
h
eb
y
s
h
e
v
T
y
p
e
I
I
with
f
Low
=1
Hz
an
d
f
High
=
5
0
Hz.
T
h
is
i
s
b
ec
a
u
s
e
it
s
h
o
ws
th
e
m
o
s
t
o
p
tim
al
SNR
r
esu
lt
s
co
m
p
ar
ed
to
o
th
e
r
f
ilter
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
7
6
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
,
Vo
l.
1
5
,
No
.
1
,
Ma
r
ch
20
2
6
:
21
7
-
2
2
7
220
Fig
u
r
e
2
.
T
h
e
p
lo
ttin
g
o
f
all
th
e
E
C
G
ch
an
n
els f
r
o
m
t
h
e
DAI
SY d
atab
ase
with
f
=2
5
0
Hz
2
.
3
.
AF
a
nd
I
CA
im
plem
ent
a
t
io
n
AF
is
a
d
ig
ital
f
ilter
with
s
elf
-
ad
ju
s
tin
g
p
r
o
p
er
ties
[
2
4
]
.
Fig
u
r
e
3
illu
s
tr
ates
th
e
g
en
er
al
b
lo
ck
d
iag
r
am
o
f
an
AF c
o
n
tain
in
g
a
p
r
im
ar
y
s
ig
n
al
(
aE
C
G
s
ig
n
al)
,
d
,
an
d
a
r
ef
er
en
ce
s
ig
n
al
(
tE
C
G
s
ig
n
al)
,
u
,
as a
n
in
p
u
t
to
b
e
p
r
o
ce
s
s
ed
b
y
th
e
AF,
wh
ich
y
ield
s
an
esti
m
ate
o
f
o
u
tp
u
t
(
m
E
C
G
s
ig
n
al)
,
y
.
An
esti
m
atio
n
er
r
o
r
(
f
E
C
G
s
ig
n
al)
,
e,
will
b
e
o
b
t
ain
ed
af
ter
th
e
s
u
b
tr
ac
tio
n
o
f
d
an
d
y,
g
iv
in
g
th
e
s
y
s
tem
o
u
tp
u
t.
T
h
e
g
en
er
al
eq
u
atio
n
o
f
th
e
AF
is
ex
p
r
es
s
ed
in
(
1
)
.
T
h
r
ee
AF
alg
o
r
i
th
m
s
will
b
e
co
m
p
ar
e
d
,
n
am
el
y
L
MS,
n
o
r
m
alize
d
L
MS
(
NL
MS)
,
an
d
R
L
S,
to
i
m
p
r
o
v
e
th
e
p
e
r
f
o
r
m
an
ce
o
f
s
ig
n
al
ex
tr
ac
tio
n
.
Step
s
ize,
µ,
is
a
cr
u
cial
p
ar
a
m
eter
th
at
co
n
tr
o
ls
th
e
r
ate
at
wh
ich
th
e
f
ilter
co
e
f
f
icien
ts
ar
e
u
p
d
ate
d
[
2
5
]
.
I
t
d
eter
m
i
n
es
h
o
w
m
u
c
h
o
f
th
e
n
ew
in
f
o
r
m
atio
n
is
in
co
r
p
o
r
ated
in
to
th
e
f
ilter
'
s
r
esp
o
n
s
e
an
d
h
o
w
q
u
ick
ly
t
h
e
f
ilter
a
d
ap
ts
to
ch
a
n
g
es
in
th
e
in
p
u
t
s
ig
n
al.
A
m
o
r
e
s
ig
n
if
ican
t
s
tep
s
ize
lead
s
t
o
f
aster
ad
a
p
tatio
n
,
m
ea
n
in
g
t
h
e
f
ilter
r
esp
o
n
d
s
m
o
r
e
r
a
p
id
ly
t
o
ch
a
n
g
es
in
th
e
i
n
p
u
t
s
ig
n
al.
Ho
wev
er
,
a
m
o
r
e
s
ig
n
if
ican
t
s
tep
s
ize
ca
n
also
lead
to
in
s
tab
ilit
y
a
n
d
o
s
cillatio
n
s
in
th
e
f
ilter
'
s
o
u
tp
u
t.
C
o
n
v
e
r
s
ely
,
a
s
m
aller
s
tep
s
ize
lead
s
t
o
s
lo
wer
ad
ap
tatio
n
,
p
r
o
v
id
in
g
m
o
r
e
ex
ce
llen
t stab
ilit
y
an
d
r
e
d
u
cin
g
th
e
r
is
k
o
f
o
s
cillatio
n
s
.
Dif
f
er
en
t step
s
ize
s
wer
e
in
v
esti
g
ated
in
th
is
s
tu
d
y
wh
en
ap
p
l
y
in
g
AF f
o
r
f
E
C
G
s
ig
n
al
ex
tr
ac
tio
n
.
(
)
=
(
)
−
(
)
(
1
)
Fig
u
r
e
3
.
Ad
a
p
tiv
e
f
ilter
b
l
o
ck
d
iag
r
am
[
2
6
]
L
MS,
NL
MS,
an
d
R
L
S
ar
e
th
e
co
n
v
en
tio
n
al
AFs
co
m
m
o
n
l
y
u
s
ed
in
s
ig
n
al
s
ep
ar
atio
n
p
r
o
ce
d
u
r
e
s
to
m
in
im
ize
th
e
er
r
o
r
b
etwe
en
t
h
e
d
esire
d
o
u
tp
u
t
an
d
th
e
ac
t
u
al
o
u
tp
u
t
[
2
6
]
.
T
h
e
L
MS
alg
o
r
ith
m
is
o
n
e
o
f
th
e
m
o
s
t
wid
ely
u
s
ed
an
d
s
tu
d
i
ed
AFs
,
p
r
im
ar
il
y
d
u
e
to
i
ts
s
im
p
licity
,
lo
w
m
em
o
r
y
r
eq
u
ir
em
e
n
ts
,
an
d
co
m
p
u
tatio
n
al
ef
f
icien
cy
.
I
ts
u
p
d
ate
r
u
le
f
o
llo
ws
a
g
r
ad
ien
t
-
d
escen
t
ap
p
r
o
ac
h
,
ad
ju
s
tin
g
f
ilter
co
ef
f
icien
ts
b
ased
o
n
th
e
er
r
o
r
b
etwe
en
t
h
e
d
esire
d
s
ig
n
al
an
d
th
e
ac
t
u
al
o
u
tp
u
t
as
f
o
r
m
u
lated
in
(
2
)
.
i
r
ep
r
esen
ts
th
e
n
u
m
b
er
o
f
iter
atio
n
s
.
w
(
i+1
)
i
s
th
e
esti
m
ate
o
f
tap
-
weig
h
t
v
ec
to
r
(
at
tim
e
n
+1
)
w
h
er
ea
s
w
(
i
)
is
th
e
tap
-
weig
h
t
v
ec
to
r
.
T
h
e
esti
m
atio
n
e
r
r
o
r
s
ig
n
al
with
co
m
p
lex
c
o
n
ju
g
atio
n
is
d
e
n
o
ted
as
*
,
an
d
last
ly
,
d
(
i
)
is
th
e
i
n
p
u
t
s
ig
n
al.
(
+
1
)
=
(
)
+
∗
(
)
(
)
(
2
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
I
SS
N:
2252
-
8
7
7
6
F
eta
l e
lectro
ca
r
d
io
g
r
a
m
ex
tr
a
ctio
n
a
n
d
s
ig
n
a
l q
u
a
lity a
s
s
ess
men
t u
s
in
g
s
ta
tis
tica
l m
eth
o
d
(
Li Mu
n
N
g
)
221
NL
MS
is
an
ex
ten
s
io
n
o
f
L
M
S
th
at
n
o
r
m
alize
s
th
e
s
tep
s
ize
to
im
p
r
o
v
e
co
n
v
er
g
en
ce
s
ta
b
ilit
y
f
ac
ed
b
y
L
MS
[
2
7
]
.
B
y
n
o
r
m
alizin
g
,
th
e
alg
o
r
ith
m
ad
a
p
ts
to
v
a
r
iatio
n
s
in
th
e
p
o
wer
o
f
th
e
in
p
u
t
s
ig
n
al,
wh
ic
h
im
p
r
o
v
es
p
e
r
f
o
r
m
an
ce
in
ca
s
es
o
f
n
o
n
-
s
tatio
n
ar
y
s
ig
n
als
as
p
r
esen
ted
in
(
3
)
,
w
h
er
e
̃
m
ea
n
s
th
e
p
o
s
itiv
e
r
ea
l
s
ca
lin
g
f
ac
to
r
an
d
|
|
d
(
i
)
|
|
i
s
th
e
E
u
clid
ea
n
n
o
r
m
o
f
th
e
a
d
ap
tiv
e
tap
-
in
p
u
t
v
ec
to
r
,
d
(
i
).
(
+
1
)
=
(
)
+
̃
‖
(
)
‖
2
∗
(
)
(
)
(
3
)
Me
an
wh
ile
,
R
L
S
i
s
a
m
o
r
e
ad
v
an
ce
d
AF
alg
o
r
ith
m
th
at
r
ec
u
r
s
iv
ely
m
in
im
izes
th
e
least
s
q
u
ar
es
er
r
o
r
.
U
n
lik
e
L
MS
an
d
NL
MS,
R
L
S
tak
es
in
to
ac
co
u
n
t
all
p
r
ev
io
u
s
er
r
o
r
v
alu
es
(
n
o
t
ju
s
t
th
e
cu
r
r
en
t
o
n
e)
,
wh
ich
allo
ws
f
o
r
f
aster
co
n
v
er
g
en
ce
an
d
b
etter
p
er
f
o
r
m
a
n
ce
with
n
o
n
-
s
tatio
n
ar
y
s
ig
n
al
s
.
T
h
e
u
p
d
ate
r
u
le
in
v
o
lv
es
an
in
v
er
s
e
co
r
r
elati
o
n
m
atr
ix
as
p
r
o
v
id
e
d
in
(
4
)
,
wh
er
e
k
(
i
)
is
th
e
g
ain
v
ec
to
r
an
d
ξ
*(
i
)
is
th
e
esti
m
atio
n
er
r
o
r
o
f
R
L
S.
(
)
=
(
−
1
)
+
(
)
ξ
∗
(
)
(
4
)
Fig
u
r
e
4
s
h
o
ws
th
e
o
v
er
all
f
r
am
ewo
r
k
o
f
f
E
C
G
s
ig
n
al
ex
tr
ac
tio
n
with
s
tati
s
tical
an
aly
s
i
s
u
s
in
g
AF
(
Fig
u
r
e
4
(
a)
)
a
n
d
I
C
A
(
Fig
u
r
e
4
(
b
)
)
.
First,
th
e
o
p
er
atio
n
o
f
AF
is
in
itiated
b
y
lo
ad
in
g
th
e
DAI
SY
E
C
G
d
ataset,
co
n
s
is
tin
g
o
f
b
o
th
aE
C
G
an
d
tECG
s
ig
n
als
as
in
p
u
ts
.
T
h
ese
E
C
G
s
ig
n
als
h
ad
b
e
en
p
r
e
-
p
r
o
ce
s
s
ed
as
m
en
tio
n
ed
in
s
ec
tio
n
2
.
2
.
Nex
t,
th
e
L
MS
AF
was
in
itialized
,
an
d
µ
was
s
et
to
0
.
1
.
T
h
e
AF w
o
u
ld
r
u
n
with
th
e
aE
C
G
s
ig
n
al
as
th
e
p
r
im
a
r
y
s
ig
n
al,
d,
a
n
d
th
e
tECG
s
ig
n
al
(
r
ef
er
e
n
ce
s
ig
n
al)
as
u
.
T
h
e
esti
m
ated
m
E
C
G
s
ig
n
al,
y,
wo
u
l
d
b
e
g
en
e
r
ated
af
ter
g
o
i
n
g
th
r
o
u
g
h
t
h
e
AF
m
ec
h
an
is
m
.
T
h
e
n
,
a
d
ed
u
ctio
n
o
cc
u
r
r
e
d
b
etwe
en
d
an
d
y
th
at
w
o
u
ld
p
r
o
d
u
ce
th
e
e
s
ig
n
al,
th
e
d
esire
d
f
E
C
G
s
ig
n
al
ex
tr
ac
ted
as
th
e
s
y
s
tem
o
u
tp
u
t
at
t
h
e
en
d
o
f
th
e
p
r
o
c
ess
.
T
o
en
h
an
ce
t
h
e
es
tim
ated
e
s
ig
n
al
,
a
p
o
s
t
-
p
r
o
ce
s
s
in
g
s
tep
was
p
er
f
o
r
m
ed
,
wh
ic
h
in
v
o
lv
ed
t
h
e
u
s
e
o
f
a
h
ig
h
-
p
ass
B
u
tter
wo
r
th
f
i
lter
f
o
llo
wed
b
y
wa
v
elet
d
en
o
is
in
g
u
s
in
g
a
Dau
b
ec
h
ies
-
6
(
d
b
6
)
wav
elet.
T
h
e
f
in
al
s
tep
wo
u
ld
b
e
th
e
ca
lcu
latio
n
o
f
th
e
f
ilter
ed
f
HR
a
n
d
its
s
tati
s
tical
m
etr
ic
s
.
T
h
is
p
r
o
ce
s
s
was
th
en
r
ep
ea
ted
f
o
r
v
ar
io
u
s
s
tep
s
izes
,
r
an
g
in
g
f
r
o
m
µ
=
0
.
0
0
1
to
0
.
9
.
Ad
d
itio
n
ally
,
t
h
e
s
am
e
p
r
o
c
ed
u
r
e
was
ap
p
lied
to
two
o
th
er
AF a
lg
o
r
ith
m
s
,
N
L
MS
an
d
R
L
S,
r
esp
ec
tiv
ely
.
(
a)
(
b
)
Fig
u
r
e
4
.
Pro
ce
s
s
o
f
f
E
C
G
s
ig
n
al
ex
tr
ac
tio
n
(
a)
u
s
in
g
AF in
Py
C
h
ar
m
an
d
(
b
)
u
s
in
g
I
C
A
in
MA
T
L
AB
2
0
2
4
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
7
6
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
,
Vo
l.
1
5
,
No
.
1
,
Ma
r
ch
20
2
6
:
21
7
-
2
2
7
222
I
n
co
n
tr
ast
to
AF,
I
C
A
i
s
a
s
tatis
tical
tech
n
iq
u
e
th
at
s
ee
k
s
to
u
n
co
v
er
th
e
u
n
d
er
l
y
in
g
s
tr
u
ctu
r
e
o
f
co
m
p
lex
d
ata
b
y
d
ec
o
m
p
o
s
in
g
it
in
to
a
s
et
o
f
s
tatis
tically
in
d
ep
en
d
en
t
c
o
m
p
o
n
en
ts
[
2
8
]
.
T
h
e
f
o
r
m
u
la
f
o
r
I
C
A
is
ex
p
r
ess
ed
in
(
5
)
,
wh
er
e
Z
is
th
e
m
atr
ix
o
f
I
C
A
co
m
p
o
n
en
ts
,
A
is
th
e
I
C
A
m
ix
in
g
m
atr
ix
,
an
d
X
is
th
e
m
atr
ix
o
f
E
C
G
s
ig
n
als
(
aE
C
G
s
ig
n
al)
.
T
h
is
eq
u
atio
n
r
ep
r
esen
ts
th
e
co
r
e
o
p
er
atio
n
o
f
I
C
A;
th
e
in
p
u
t
aE
C
G
s
ig
n
als,
X
,
ar
e
f
ir
s
t
tr
a
n
s
f
o
r
m
ed
in
to
in
d
e
p
en
d
e
n
t
co
m
p
o
n
en
ts
,
Z
,
u
s
in
g
th
e
I
C
A
m
ix
in
g
m
atr
ix
,
A
.
T
h
e
in
d
ep
en
d
en
t c
o
m
p
o
n
e
n
ts
ar
e
t
h
en
s
ep
ar
ated
,
g
en
er
atin
g
th
e
f
in
al
o
u
tp
u
t,
th
e
ex
tr
ac
te
d
f
E
C
G
s
ig
n
al,
Z
.
=
∗
(
5
)
T
h
e
p
r
o
ce
s
s
o
f
th
e
I
C
A
ap
p
l
icatio
n
in
MA
T
L
AB
is
s
h
o
wn
in
Fig
u
r
e
4
(
b
)
.
T
h
e
p
r
o
ce
s
s
o
f
f
E
C
G
s
ig
n
al
ex
tr
ac
tio
n
b
e
g
an
with
t
h
e
u
s
e
o
f
th
e
DAI
SY
E
C
G
d
a
taset
th
at
h
ad
b
ee
n
p
r
ep
r
o
ce
s
s
ed
as
in
p
u
t
X
.
T
h
e
I
C
A
was
th
en
in
itialized
to
in
p
u
t
X
.
Mix
in
g
m
atr
ix
A
wo
u
l
d
b
e
esti
m
ated
an
d
u
p
d
ated
,
l
ea
d
in
g
to
Z
as
th
e
o
v
er
all
o
u
tp
u
t,
r
ep
r
esen
tin
g
th
e
f
E
C
G
s
ig
n
al
ex
tr
ac
ted
.
T
h
e
n
ex
t
s
tep
was
ca
lcu
lati
n
g
th
e
f
HR
an
d
its
s
tatis
t
ical
m
ea
s
u
r
em
en
ts
.
HR
i
s
ca
lcu
lated
b
y
u
s
in
g
th
e
f
o
r
m
u
la
p
r
esen
ted
in
(
6
)
.
T
h
e
f
in
al
s
tep
was
to
o
b
tain
th
e
s
tatis
tical
an
aly
s
i
s
af
ter
ea
ch
iter
atio
n
p
e
r
f
o
r
m
ed
b
y
I
C
A.
,
(
)
=
60
−
(
)
(
6
)
2
.
4
.
St
a
t
is
t
ica
l
m
et
ho
ds
f
o
r
s
ig
na
l qua
lity
I
n
s
ig
n
al
p
r
o
ce
s
s
in
g
,
SNR
m
ea
s
u
r
es
th
e
lev
el
o
f
th
e
d
esire
d
s
ig
n
al
r
elativ
e
to
th
e
b
ac
k
g
r
o
u
n
d
n
o
is
e.
A
h
ig
h
er
SNR
in
d
icate
s
a
clea
r
er
an
d
m
o
r
e
d
is
tin
ct
s
ig
n
al,
wh
ile
a
lo
wer
SNR
s
u
g
g
ests
th
a
t th
e
s
ig
n
al
is
m
o
r
e
o
b
s
cu
r
ed
b
y
n
o
is
e.
Stan
d
ar
d
d
ev
iatio
n
,
σ
q
u
an
tifie
s
th
e
s
p
r
e
ad
o
f
d
ata
ar
o
u
n
d
th
e
m
ea
n
,
̅
.
A
lo
wer
σ
,
m
ea
n
s
th
e
d
ata
p
o
in
ts
ar
e
cl
o
s
er
to
th
e
̅
,
wh
ile
a
h
ig
h
er
v
alu
e
in
d
icate
s
g
r
ea
ter
d
is
p
er
s
io
n
.
W
h
en
s
q
u
a
r
in
g
t
h
e
s
tan
d
ar
d
d
ev
iatio
n
a
n
d
it
b
ec
o
m
es
v
ar
ian
ce
,
2
.
Me
an
wh
ile,
2
p
lay
s
a
cr
u
cial
r
o
le
in
ass
es
s
in
g
th
e
s
p
r
ea
d
o
r
d
is
p
er
s
io
n
o
f
a
s
ig
n
al'
s
am
p
litu
d
e
ar
o
u
n
d
its
v
alu
e.
I
t
is
a
s
tatis
tical
m
ea
s
u
r
e
th
at
q
u
an
tifie
s
th
e
s
ig
n
al’
s
en
er
g
y
d
is
tr
ib
u
tio
n
an
d
p
r
o
v
id
es
in
s
ig
h
ts
in
to
th
e
s
ig
n
al’
s
ch
ar
ac
ter
is
tics
.
Sk
ewn
ess
,
1
m
ea
s
u
r
es
th
e
asy
m
m
etr
ical
d
ata.
A
p
o
s
itiv
e
s
k
ewn
ess
in
d
icate
s
th
at
th
e
E
C
G
s
ig
n
al'
s
tail i
s
lo
n
g
er
o
n
th
e
r
ig
h
t sid
e
th
an
th
e
lef
t,
wh
ile
a
s
k
ewn
es
s
o
f
ze
r
o
r
ep
r
esen
ts
a
s
y
m
m
etr
ic
s
ig
n
a
l.
Ku
r
to
s
is
,
2
d
escr
ib
es
h
o
w
p
ea
k
ed
o
r
f
lat
th
e
d
ata
d
is
tr
ib
u
tio
n
is
co
m
p
ar
e
d
to
a
n
o
r
m
al
d
is
tr
ib
u
ti
o
n
.
Hig
h
k
u
r
to
s
is
s
ig
n
als
h
av
e
a
s
h
ar
p
p
ea
k
n
ea
r
th
e
m
ea
n
with
h
ea
v
y
tails
,
wh
ile
lo
w
k
u
r
to
s
is
s
ig
n
als
ar
e
f
latter
a
n
d
le
s
s
p
ea
k
ed
.
L
et
E
C
G
s
ig
n
als
b
e
d
en
o
ted
b
y
x
with
N
as sam
p
le
p
o
in
ts
,
an
d
th
ese
s
tatis
t
ical
m
ea
s
u
r
em
en
ts
wer
e
ex
p
r
ess
ed
in
(
7
)
to
(
1
1
)
,
r
esp
e
ctiv
ely
.
−
−
,
=
10
.
l
og
10
(
2
2
)
(
7
)
,
=
√
1
−
1
∑
|
−
̅
|
2
=
1
(
8
)
,
2
=
1
∑
(
−
̅
)
2
=
1
(
9
)
,
1
=
1
∑
(
−
̅
σ
)
3
=
1
(
1
0
)
,
2
=
1
∑
(
−
̅
σ
)
4
=
1
(
1
1
)
Sin
ce
th
e
DAI
SY
d
atab
ase
d
id
n
o
t
p
r
o
v
i
d
e
th
e
r
ea
l
v
alu
es
o
f
f
HR
an
d
m
HR
,
th
e
r
esu
lts
f
r
o
m
t
h
is
s
tu
d
y
wer
e
co
m
p
ar
e
d
with
th
e
esti
m
ated
f
HR
(
1
3
5
b
p
m
)
r
etr
iev
ed
f
r
o
m
[
2
9
]
u
s
in
g
p
er
ce
n
tag
e
er
r
o
r
(
PE)
an
aly
s
is
.
T
h
e
co
r
r
esp
o
n
d
i
n
g
f
o
r
m
u
la
is
ex
p
r
ess
ed
in
(
12
)
,
w
h
er
e
ca
lcu
lated
HR
r
ep
r
esen
ts
th
e
ex
tr
ac
ted
f
E
C
G
h
ea
r
t r
ate
o
b
tain
ed
f
r
o
m
th
is
s
tu
d
y
,
wh
e
r
ea
s
r
ef
er
e
n
ce
HR
is
o
b
tain
ed
f
r
o
m
[
1
0
]
.
=
|
−
×
100
%
|
(
1
2
)
3.
RE
SU
L
T
S
AND
D
I
SCU
SS
I
O
N
T
h
is
s
tu
d
y
in
v
esti
g
ated
th
e
ef
f
ec
ts
o
f
co
m
p
ar
in
g
two
m
eth
o
d
o
lo
g
ies,
n
am
ely
AF
a
n
d
I
C
A,
with
in
a
s
tatis
t
ical
an
aly
s
is
f
r
am
ewo
r
k
to
ex
tr
ac
t
th
e
f
E
C
G
s
ig
n
als.
W
h
ile
ea
r
lier
s
tu
d
ies
h
av
e
ex
p
lo
r
ed
th
e
ap
p
licatio
n
o
f
v
ar
io
u
s
s
ig
n
al
s
ep
ar
atio
n
a
lg
o
r
ith
m
s
,
th
ey
o
f
ten
r
el
y
o
n
s
p
ec
if
ic
alg
o
r
ith
m
ic
ass
u
m
p
tio
n
s
.
Ho
wev
er
,
th
ey
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
I
SS
N:
2252
-
8
7
7
6
F
eta
l e
lectro
ca
r
d
io
g
r
a
m
ex
tr
a
ctio
n
a
n
d
s
ig
n
a
l q
u
a
lity a
s
s
ess
men
t u
s
in
g
s
ta
tis
tica
l m
eth
o
d
(
Li Mu
n
N
g
)
223
h
av
e
n
o
t
ex
p
licitly
ad
d
r
ess
ed
th
e
in
f
lu
en
ce
o
f
s
tatis
tical
m
ea
s
u
r
es
s
u
ch
as
SN
R
,
k
u
r
to
s
is
,
a
n
d
v
ar
ian
ce
,
wh
ich
ca
n
p
r
o
v
id
e
m
o
r
e
o
b
jectiv
e
an
d
q
u
an
titativ
e
in
s
ig
h
ts
in
to
s
ig
n
al
q
u
ality
an
d
s
tab
ilit
y
.
T
o
b
e
g
in
with
,
th
e
s
ig
n
al
ex
t
r
ac
tio
n
r
esu
lts
ar
e
d
is
p
lay
ed
i
n
Fig
u
r
e
5
f
o
r
t
h
e
f
ir
s
t
(
A1
)
an
d
eig
h
th
(
T
8
)
ch
an
n
els
o
f
th
e
DAI
SY
E
C
G
d
ataset
af
ter
em
p
lo
y
in
g
th
e
AF.
T
h
e
A1
a
n
d
T
8
ch
a
n
n
els
r
ep
r
esen
t
th
e
p
r
im
ar
y
s
ig
n
al,
d,
a
n
d
r
ef
e
r
en
ce
s
ig
n
al,
u
.
Af
ter
ev
alu
atin
g
o
th
er
ch
an
n
els’
co
m
b
in
atio
n
s
,
o
n
ly
th
is
p
air
o
f
ch
an
n
els
co
u
ld
o
u
t
p
u
t
a
s
atis
f
ac
to
r
y
r
esu
lt
(
in
ter
m
s
o
f
f
etal
b
p
m
)
.
Fig
u
r
e
5
(
a)
d
is
p
lay
s
th
e
esti
m
atio
n
o
f
th
e
m
E
C
G
s
ig
n
al
af
ter
p
ass
in
g
th
e
R
L
S,
wh
er
ea
s
Fig
u
r
e
5
(
b
)
d
ep
icts
th
e
ex
tr
ac
ted
f
E
C
G
s
ig
n
al,
wh
ich
h
as
b
ee
n
p
o
s
t
-
p
r
o
ce
s
s
ed
u
s
in
g
a
h
ig
h
-
p
ass
f
ilter
an
d
wa
v
elet
d
e
n
o
is
e
to
r
em
o
v
e
t
h
e
r
esid
u
al
n
o
is
e
t
o
en
h
an
ce
t
h
e
f
E
C
G
s
ig
n
al
wav
ef
o
r
m
.
Fu
r
th
e
r
m
o
r
e,
in
co
r
p
o
r
atin
g
a
p
o
s
t
-
p
r
o
ce
s
s
in
g
s
tag
e
f
o
r
s
ig
n
al
en
h
an
ce
m
en
t
wo
u
ld
f
u
r
t
h
er
r
ef
in
e
th
e
e
x
tr
ac
ted
f
E
C
G
s
ig
n
al
q
u
ality
,
e
n
ab
le
m
o
r
e
ac
cu
r
ate
in
ter
p
r
etatio
n
s
,
a
n
d
e
n
h
a
n
ce
f
etal
well
-
b
ein
g
m
o
n
ito
r
in
g
.
(
a)
(
b
)
Fig
u
r
e
5
.
Sig
n
al
e
x
tr
ac
tio
n
r
esu
lts
f
o
r
(
a)
t
h
e
esti
m
ated
m
E
C
G
(
T
8
)
s
ig
n
al,
y
,
af
ter
g
o
in
g
th
r
o
u
g
h
AF a
n
d
(
b
)
th
e
p
o
s
t
-
p
r
o
ce
s
s
in
g
o
f
th
e
ex
tr
ac
ted
f
E
C
G
s
ig
n
al,
e
(
A1
)
T
h
e
AF
r
esu
lts
ar
e
s
u
m
m
ar
ize
d
in
T
ab
le
1
,
s
h
o
wca
s
in
g
th
e
e
x
tr
ac
tio
n
o
f
f
E
C
G
s
ig
n
als
u
s
in
g
v
ar
i
o
u
s
s
tep
s
izes
(
µ
=
0
.
0
0
1
to
0
.
9
)
.
T
h
e
tab
le
also
p
r
esen
ts
s
tatis
tical
m
ea
s
u
r
em
en
ts
,
esti
m
ated
f
HR
r
ea
d
in
g
s
,
a
n
d
th
e
an
aly
s
is
o
f
h
ea
r
t r
ate
d
is
cr
ep
an
cies u
s
in
g
th
e
PE
f
o
r
m
u
la
.
T
h
e
s
ig
n
al
q
u
ality
ass
es
s
m
en
t f
o
r
L
MS,
NL
MS,
an
d
R
L
S
f
ilter
s
was
e
v
alu
ated
u
s
in
g
SNR
,
s
k
ewn
ess
,
k
u
r
to
s
is
,
v
ar
ian
ce
,
s
tan
d
ar
d
d
e
v
iatio
n
,
R
-
p
ea
k
d
etec
tio
n
,
an
d
f
HR
.
T
h
e
SNR
o
f
th
e
L
M
S f
ilter
im
p
r
o
v
e
d
to
4
.
6
1
d
B
at
a
s
tep
s
ize
o
f
0
.
0
1
,
wh
ile
th
e
R
L
S f
ilter
ac
h
iev
ed
th
e
h
ig
h
est
SNR
o
f
5
.
6
d
B
at
0
.
9
,
s
h
o
win
g
its
s
u
p
er
io
r
n
o
is
e
r
ed
u
ctio
n
.
Sk
ewn
ess
an
d
k
u
r
to
s
is
v
ar
ied
ac
r
o
s
s
f
ilter
s
,
with
th
e
R
L
S
f
ilter
p
r
o
v
id
in
g
s
tab
le
r
esu
lts
an
d
m
i
n
im
al
wav
ef
o
r
m
d
is
to
r
tio
n
at
lar
g
er
s
tep
s
izes.
Alth
o
u
g
h
th
e
L
MS
f
i
lter
co
n
s
is
ten
tly
d
etec
ted
all
R
-
p
ea
k
s
with
m
in
im
al
PE
(
1
.
6
4
%),
it
co
u
ld
n
o
t
co
m
p
u
te
an
y
h
ea
r
t
b
ea
t
wh
en
u
s
in
g
a
b
ig
g
er
s
tep
s
ize
(
µ
=
0
.
9
)
,
th
u
s
r
esu
ltin
g
in
a
n
u
ll
r
esu
lt.
M
ea
n
wh
ile,
th
e
R
L
S
f
ilter
at
s
tep
s
ize
0
.
9
ac
h
iev
e
d
th
e
lo
west
PE
(
0
.
9
2
%),
s
h
o
wc
asi
n
g
a
r
o
b
u
s
t
R
-
p
ea
k
d
etec
tio
n
.
On
th
e
co
n
tr
a
r
y
,
th
e
NL
MS
f
ilter
s
h
o
wed
r
ed
u
ce
d
ac
cu
r
ac
y
an
d
in
cr
ea
s
in
g
s
ig
n
al
d
is
to
r
tio
n
at
h
ig
h
er
s
tep
s
izes.
Ov
er
all,
f
r
o
m
th
e
s
ig
n
al
q
u
ality
ass
es
s
m
en
t,
th
e
R
L
S
f
il
ter
d
em
o
n
s
tr
ated
th
e
b
est
b
alan
ce
b
etwe
en
n
o
is
e
r
ed
u
ctio
n
an
d
f
E
C
G
s
ig
n
al
p
r
eser
v
atio
n
,
esp
ec
ially
wh
en
th
e
s
tep
s
ize
is
lar
g
e.
On
th
e
o
th
er
h
a
n
d
,
Fig
u
r
e
6
s
h
o
ws
th
e
ex
t
r
ac
tio
n
r
esu
lts
o
f
I
C
A
f
r
o
m
th
e
DAI
SY
E
C
G
d
ataset.
Sig
n
al
q
u
ality
ass
ess
m
en
t
-
b
as
ed
s
tatis
tical
m
ea
s
u
r
em
en
ts
an
d
th
e
f
HR
co
m
p
u
tatio
n
r
esu
l
ts
wer
e
tab
u
lated
in
T
ab
le
2
.
T
h
e
tab
le
h
ig
h
lig
h
ts
th
e
ef
f
ec
ts
o
f
v
ar
y
in
g
f
Low
an
d
f
High
f
ilter
s
ettin
g
s
o
n
E
C
G
C
h
an
n
el
A2
b
ef
o
r
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
7
6
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
,
Vo
l.
1
5
,
No
.
1
,
Ma
r
ch
20
2
6
:
21
7
-
2
2
7
224
an
d
af
ter
ap
p
ly
in
g
I
C
A.
T
h
e
HR
b
ef
o
r
e
I
C
A
was c
o
n
s
is
ten
t
at
8
1
.
7
3
b
p
m
,
with
2
2
R
-
p
ea
k
s
d
etec
ted
ac
r
o
s
s
all
s
ettin
g
s
,
r
esu
ltin
g
in
a
s
tab
le
m
ea
n
f
HR
o
f
1
3
3
.
7
7
b
p
m
an
d
m
in
im
al
PE
(
0
.
9
1
%).
T
h
e
SN
R
im
p
r
o
v
ed
s
lig
h
tly
af
ter
I
C
A,
r
ea
ch
i
n
g
a
m
ax
im
u
m
o
f
0
.
8
6
d
B
with
f
ilter
s
s
e
t
to
0
.
5
to
5
0
Hz
o
r
1
to
5
0
Hz.
Sk
ewn
ess
an
d
k
u
r
to
s
is
v
alu
es
s
h
o
wed
m
o
d
er
ate
d
ev
iatio
n
s
,
with
s
k
ewn
ess
p
ea
k
in
g
at
1
.
3
5
(
1
to
4
5
Hz)
a
n
d
k
u
r
to
s
is
r
an
g
in
g
f
r
o
m
9
.
4
2
to
1
0
.
3
6
.
Var
ian
ce
an
d
s
tan
d
ar
d
d
e
v
iatio
n
r
em
ai
n
ed
s
tab
le,
s
u
g
g
esti
n
g
m
in
im
al
im
p
ac
t
o
n
s
ig
n
al
am
p
litu
d
e.
Ov
er
all,
f
ilter
s
with
h
ig
h
e
r
f
High
(
5
0
Hz)
p
r
o
v
id
e
d
o
p
tim
al
n
o
is
e
r
ed
u
ctio
n
an
d
s
ig
n
al
p
r
eser
v
atio
n
,
co
n
f
ir
m
in
g
th
e
ef
f
ec
tiv
en
ess
o
f
I
C
A
in
f
E
C
G
s
ig
n
al
ex
tr
ac
tio
n
.
T
ab
le
1
.
Sig
n
al
q
u
ality
ass
ess
m
en
t u
s
in
g
AF.
No
te:
Prim
ar
y
s
ig
n
al,
d
=A
1
,
r
e
f
er
en
ce
s
ig
n
a
l,
y
=T
8
A
F
f
i
l
t
e
r
LM
S
N
LM
S
R
LS
S
t
e
p
si
z
e
(
µ
)
0
.
0
0
1
0
.
0
1
0
.
9
0
.
1
0
.
5
0
.
9
0
.
1
0
.
5
0
.
9
H
R
b
e
f
o
r
e
A
F
(
b
p
m)
84
S
N
R
b
e
f
o
r
e
A
F
(
d
B
)
-
5
.
7
4
S
N
R
a
f
t
e
r
A
F
(
d
B
)
2
.
9
3
4
.
6
1
N
/
A
-
1
.
1
5
-
3
.
6
2
-
5
.
2
7
-
4
.
1
3
1
.
4
1
5
.
6
1
-
2
.
0
1
2
.
3
5
N
/
A
3
.
8
9
2
.
7
4
3
.
1
7
-
4
.
1
7
0
.
3
6
0
.
2
5
2
3
8
.
7
0
4
8
.
2
5
N
/
A
6
1
.
6
4
7
0
.
3
5
7
8
.
1
1
1
7
7
.
4
3
4
7
.
7
6
1
2
.
0
6
2
0
.
2
9
0
.
1
8
N
/
A
0
.
9
8
1
.
7
0
2
.
4
2
1
.
2
3
0
.
2
7
0
.
0
8
0
.
5
4
0
.
4
2
N
/
A
0
.
9
9
1
.
3
0
1
.
5
6
1
.
1
1
0
.
5
2
0
.
2
9
F
e
t
a
l
R
-
p
e
a
k
23
23
0
20
14
9
19
22
22
f
H
R
a
f
t
e
r
A
F
(
b
p
m)
1
3
7
.
2
1
1
3
7
.
2
7
N
/
A
1
1
9
.
5
5
8
1
.
5
9
6
0
.
3
0
1
1
5
.
7
8
1
3
1
.
1
4
1
3
3
.
7
6
PE
(
%)
1
.
6
4
1
.
6
8
N
/
A
1
1
.
4
4
3
9
.
5
6
5
5
.
3
3
1
4
.
2
4
2
.
8
6
0
.
9
2
I
t
was
o
b
s
er
v
e
d
t
h
at
th
e
s
ig
n
al
q
u
ality
ass
ess
m
en
t
r
esu
lts
co
r
r
elate
d
well
with
th
e
ac
cu
r
ac
y
o
f
th
e
ex
tr
ac
ted
f
E
C
G
s
ig
n
als
wh
en
co
m
p
ar
ed
t
o
th
e
r
ef
e
r
en
ce
f
HR
.
B
o
th
m
eth
o
d
s
d
em
o
n
s
tr
a
ted
th
e
ca
p
ab
ilit
y
to
ex
tr
ac
t
f
E
C
G
s
ig
n
als,
y
ield
i
n
g
s
im
ilar
p
er
ce
n
ta
g
es
o
f
er
r
o
r
i
n
f
HR
v
alu
es.
Ho
wev
er
,
th
e
A
F
m
eth
o
d
p
r
o
d
u
ce
d
s
lig
h
tly
h
ig
h
er
SNR
v
alu
es,
in
d
icatin
g
m
a
r
g
in
ally
b
etter
s
i
g
n
al
clar
ity
u
n
d
e
r
th
e
e
v
alu
at
ed
co
n
d
itio
n
s
.
T
h
e
im
p
o
r
tan
ce
o
f
ass
ess
in
g
s
ig
n
al
q
u
ality
is
wo
r
th
n
o
tin
g
to
av
o
id
m
ea
n
in
g
less
in
ter
p
r
etatio
n
o
f
t
h
e
r
esu
lts
in
v
o
lv
in
g
AF
tech
n
iq
u
es.
T
h
is
was
p
r
o
v
en
w
h
en
o
n
ly
o
n
e
co
m
b
in
atio
n
o
f
ch
a
n
n
els
(
A1
an
d
T
8
)
was
p
o
s
s
ib
le
wh
en
ex
tr
ac
tin
g
th
e
f
E
C
G
s
ig
n
al
u
s
in
g
th
e
AF
ap
p
r
o
ac
h
.
L
ik
ewise,
ev
en
th
o
u
g
h
th
e
I
C
A
m
eth
o
d
co
u
ld
p
er
f
o
r
m
s
ig
n
al
e
x
tr
ac
tio
n
f
o
r
all
ch
an
n
els
,
o
n
ly
c
h
an
n
el
A
2
ex
h
ib
ited
th
e
b
est
r
esu
lt
f
o
r
f
HR
,
wh
ich
is
clo
s
e
to
th
e
r
ef
er
e
n
ce
HR
.
Fig
u
r
e
6
.
T
h
e
ex
tr
ac
ted
f
E
C
G
s
ig
n
al
af
ter
ap
p
ly
i
n
g
I
C
A
f
r
o
m
th
e
A2
ch
a
n
n
el,
with
r
-
p
ea
k
s
d
etec
ted
T
ab
le
2
.
Sig
n
al
q
u
ality
ass
ess
m
en
t
-
b
ased
s
tatis
tical
m
ea
s
u
r
em
en
ts
u
s
in
g
I
C
A
EC
G
C
h
a
n
n
e
l
Lo
w
-
C
u
t
O
f
f
(
f
L
ow
)
a
n
d
H
i
g
h
C
u
t
o
f
f
F
r
e
q
u
e
n
c
y
(
f
H
i
gh
)
(
H
z
)
B
e
f
o
r
e
I
C
A
H
R
(
b
p
m)
S
N
R
(
d
B
)
A
f
t
e
r
I
C
A
S
N
R
(
d
B
)
1
2
2
F
e
t
a
l
R
-
P
e
a
k
M
e
a
n
f
H
R
(
b
p
m)
A2
0
.
5
a
n
d
4
5
8
1
.
7
3
0
.
7
1
0
.
7
9
1
.
2
4
9
.
4
2
1
.
3
1
0
.
1
6
22
1
3
3
.
7
7
1
a
n
d
4
5
8
1
.
7
3
0
.
7
1
0
.
8
5
1
.
3
5
1
0
.
3
6
1
.
3
1
0
.
1
5
22
1
3
3
.
7
7
0
.
5
a
n
d
5
0
8
1
.
7
3
0
.
7
1
0
.
8
6
1
.
2
7
1
0
.
2
9
1
.
3
2
0
.
1
8
22
1
3
3
.
7
7
1
a
n
d
5
0
8
1
.
7
3
0
.
7
0
0
.
8
6
1
.
2
7
1
0
.
3
1
.
3
1
0
.
1
8
22
1
3
3
.
7
7
P
E
(
%)
0
.
9
1
A
d
etailed
ex
am
in
atio
n
o
f
th
e
r
esu
lts
f
r
o
m
b
o
th
AF
an
d
I
C
A
s
u
g
g
ests
s
ig
n
if
ican
t
d
if
f
er
en
c
es
in
th
eir
ef
f
ec
tiv
en
ess
f
o
r
f
E
C
G
ex
tr
ac
t
io
n
,
p
ar
ticu
la
r
ly
wh
en
s
u
p
p
o
r
ted
b
y
in
te
g
r
ated
s
tatis
tical
an
aly
s
is
.
AF
r
elies
o
n
th
e
r
ef
er
e
n
ce
c
h
an
n
el,
T
8
,
wh
ich
is
u
tili
ze
d
in
an
iter
ativ
e
n
o
is
e
-
r
ed
u
ctio
n
p
r
o
ce
s
s
.
T
h
is
a
p
p
r
o
ac
h
is
n
o
tab
ly
ef
f
ec
tiv
e
f
o
r
e
x
tr
ac
tin
g
f
E
C
G
wh
en
th
e
r
ef
er
e
n
ce
ch
an
n
el
s
tr
o
n
g
ly
co
r
r
elate
s
with
th
e
tar
g
et
f
etal
s
ig
n
al.
I
n
co
n
tr
ast,
I
C
A
ad
o
p
ts
a
d
if
f
e
r
e
n
t
s
tr
ateg
y
b
y
im
p
lem
en
ti
n
g
B
SS
,
wh
ich
o
p
er
ates
o
n
th
e
p
r
in
cip
le
o
f
s
tatis
tical
in
d
ep
en
d
en
ce
r
ath
e
r
th
an
u
tili
zin
g
a
r
ef
e
r
en
ce
ch
a
n
n
el.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
I
SS
N:
2252
-
8
7
7
6
F
eta
l e
lectro
ca
r
d
io
g
r
a
m
ex
tr
a
ctio
n
a
n
d
s
ig
n
a
l q
u
a
lity a
s
s
ess
men
t u
s
in
g
s
ta
tis
tica
l m
eth
o
d
(
Li Mu
n
N
g
)
225
T
h
is
s
tu
d
y
ex
p
lo
r
ed
a
c
o
m
p
r
eh
en
s
iv
e
m
eth
o
d
o
f
in
teg
r
at
in
g
s
tatis
tical
m
ea
s
u
r
es
s
u
ch
as
SNR
,
k
u
r
to
s
is
,
an
d
v
a
r
ian
ce
f
u
r
th
er
en
h
an
ce
s
th
e
s
elec
tio
n
o
f
th
e
o
p
tim
al
m
eth
o
d
an
d
c
h
an
n
el
f
o
r
f
E
C
G
ex
tr
ac
tio
n
.
Fo
r
ex
am
p
le,
th
e
SNR
h
elp
s
id
en
tify
ch
a
n
n
els
with
h
ig
h
er
s
ig
n
al
clar
ity
an
d
lo
wer
n
o
is
e
in
ter
f
er
en
ce
,
w
h
ile
k
u
r
to
s
is
an
d
v
ar
ian
ce
p
r
o
v
i
d
e
in
s
ig
h
ts
in
to
s
ig
n
al
d
is
tr
ib
u
tio
n
an
d
s
tab
ilit
y
,
en
ab
lin
g
t
h
e
id
en
tific
atio
n
o
f
ch
an
n
els
with
u
n
i
q
u
e
an
d
d
is
tin
g
u
is
h
ab
le
s
ig
n
al
c
h
ar
ac
ter
is
tics
.
B
y
ap
p
ly
in
g
t
h
ese
s
tatis
tic
al
ass
es
s
m
en
ts
,
th
e
s
u
itab
ilit
y
o
f
ch
a
n
n
els
lik
e
T
8
an
d
A1
f
o
r
AF
o
r
A2
f
o
r
I
C
A
ca
n
b
e
s
y
s
tem
atica
lly
v
alid
ated
.
Ho
wev
er
,
f
u
r
th
er
a
n
d
in
-
d
ep
th
s
tu
d
ies
m
ay
b
e
n
ee
d
ed
to
en
s
u
r
e
a
m
o
r
e
ac
cu
r
ate
an
d
r
eliab
le
f
E
C
G
ex
tr
ac
tio
n
p
r
o
ce
s
s
tailo
r
ed
to
th
e
s
p
ec
if
ic
c
h
ar
ac
t
er
is
tics
o
f
th
e
d
ata.
T
h
is
s
tu
d
y
d
e
m
o
n
s
tr
ates
th
e
a
p
p
licab
ilit
y
o
f
b
o
t
h
AF
an
d
I
C
A
f
o
r
f
E
C
G
s
ig
n
al
ex
tr
ac
tio
n
.
Ho
wev
er
,
th
e
d
ataset
u
s
ed
in
v
o
lv
ed
o
n
ly
a
s
in
g
le
s
u
b
j
ec
t
a
n
d
lack
e
d
a
r
ef
er
e
n
ce
f
HR
,
lim
itin
g
i
ts
u
s
e
f
o
r
clin
ical
v
alid
atio
n
.
T
h
ese
f
ac
to
r
s
s
u
g
g
est
th
at
th
e
d
ataset
is
m
o
r
e
s
u
itab
le
f
o
r
s
im
u
latio
n
p
u
r
p
o
s
es
r
ath
er
th
a
n
a
r
o
b
u
s
t
co
m
p
ar
is
o
n
an
al
y
s
is
.
An
o
th
er
lim
itatio
n
f
o
u
n
d
is
th
e
co
n
tr
ib
u
tio
n
o
f
f
etal
s
ig
n
al
s
in
th
e
th
o
r
ac
ic
ch
an
n
el.
Alth
o
u
g
h
n
o
t
d
ir
ec
tly
v
is
ib
le,
th
e
f
etal
s
ig
n
als
ca
n
s
till
b
e
d
etec
ted
in
tECGs
d
u
e
to
th
e
ir
p
r
o
x
im
ity
to
th
e
ab
d
o
m
in
al
r
e
g
io
n
,
d
esp
ite
b
ei
n
g
wea
k
er
.
Fu
tu
r
e
s
tu
d
ies
m
a
y
ex
p
lo
r
e
th
e
p
e
r
f
o
r
m
an
ce
o
f
t
h
ese
m
eth
o
d
s
u
s
in
g
lar
g
er
,
m
u
lti
-
s
u
b
ject
d
atasets
with
an
n
o
tated
r
ef
er
en
ce
s
ig
n
als,
as
well
as
in
v
esti
g
ate
f
ea
s
ib
le
way
s
o
f
im
p
r
o
v
in
g
s
im
u
latio
n
-
b
ased
e
v
alu
atio
n
f
r
am
ewo
r
k
s
wh
e
n
r
e
al
clin
ical
r
ef
er
en
ce
s
ar
e
u
n
av
ailab
le.
4.
CO
NCLU
SI
O
N
I
n
co
n
clu
s
io
n
,
th
e
in
teg
r
atio
n
o
f
s
tatis
tical
an
aly
s
i
s
with
AF
an
d
I
C
A
en
ab
led
th
e
s
u
cc
ess
f
u
l
ex
tr
ac
tio
n
o
f
t
h
e
f
E
C
G
s
ig
n
al
with
o
p
tim
al
q
u
ality
,
s
h
o
wca
s
in
g
th
e
ef
f
ec
tiv
en
ess
o
f
th
is
ap
p
r
o
ac
h
in
en
h
an
cin
g
s
ig
n
al
clar
ity
.
T
h
is
s
tu
d
y
h
as
d
em
o
n
s
tr
ated
th
at
th
e
R
L
S
alg
o
r
ith
m
o
u
tp
e
r
f
o
r
m
ed
th
e
L
MS
an
d
NL
MS
alg
o
r
ith
m
s
in
f
E
C
G
ex
tr
ac
tio
n
,
ac
h
iev
i
n
g
th
e
o
p
t
im
al
r
esu
lts
f
o
r
AF.
Giv
en
th
e
im
p
o
r
tan
ce
o
f
ac
cu
r
ate
HR
m
ea
s
u
r
em
en
t
i
n
m
ed
ical
s
ettin
g
s
,
th
e
lo
we
r
er
r
o
r
r
ate
o
f
I
C
A
an
d
R
L
S
o
f
AF
m
ak
es
it
a
n
ap
p
r
o
p
r
iate
ch
o
ice
f
o
r
clin
ic
al
ap
p
licatio
n
s
,
th
u
s
m
a
k
in
g
th
e
f
E
C
G
s
ig
n
al
ac
h
ie
v
ab
le
.
I
t
is
ess
en
tial
to
u
n
d
er
s
tan
d
th
at
th
er
e
ar
e
n
o
o
n
e
-
s
ize
-
f
its
-
all
s
o
lu
tio
n
s
,
as
n
o
t
all
th
e
E
C
G
ch
a
n
n
els
f
r
o
m
th
e
DAI
SY
d
ataset
ca
n
u
s
e
th
e
s
am
e
f
ilter
s
p
ec
if
i
ca
tio
n
s
f
o
r
f
E
C
G
s
ig
n
al
s
ep
ar
atio
n
.
T
h
is
is
ev
id
e
n
t
in
t
h
e
A
F
ap
p
r
o
ac
h
,
wh
e
r
e
an
ad
d
itio
n
al
s
tep
was
n
ec
ess
ar
y
to
p
o
s
t
-
p
r
o
ce
s
s
th
e
esti
m
ated
f
E
C
G
s
ig
n
al
af
ter
ex
tr
ac
tio
n
to
en
h
a
n
ce
t
h
e
s
ig
n
al
q
u
ality
.
E
x
p
a
n
d
in
g
th
e
cu
r
r
en
t
s
tu
d
y
b
y
co
m
p
a
r
in
g
th
e
o
b
tai
n
ed
r
esu
lts
with
a
b
r
o
ad
er
r
a
n
g
e
o
f
E
C
G
d
atasets
is
h
ig
h
ly
r
ec
o
m
m
en
d
ed
f
o
r
f
u
tu
r
e
r
esear
c
h
.
Ad
d
iti
o
n
ally
,
in
v
esti
g
atin
g
th
e
p
er
f
o
r
m
an
ce
o
f
AF
a
n
d
I
C
A
in
f
E
C
G
s
ig
n
al
s
ep
ar
atio
n
u
s
in
g
s
in
g
le
-
ch
a
n
n
el
an
d
m
u
lti
-
ch
an
n
el
ap
p
r
o
ac
h
es
wo
u
ld
p
r
o
v
id
e
v
alu
a
b
le
in
s
ig
h
ts
.
Fu
tu
r
e
r
esear
ch
co
u
l
d
also
e
x
p
lo
r
e
em
e
r
g
in
g
s
ig
n
al
s
ep
ar
atio
n
tech
n
iq
u
es
with
a
c
o
m
b
in
atio
n
o
f
m
ac
h
in
e
-
lear
n
i
n
g
ap
p
r
o
ac
h
es f
o
r
r
o
b
u
s
t f
etal
ex
tr
ac
tio
n
an
d
s
ig
n
al
q
u
ality
ass
ess
m
en
t.
ACK
NO
WL
E
DG
E
M
E
NT
S
T
h
is
r
esear
ch
was
s
u
p
p
o
r
ted
b
y
Min
is
tr
y
o
f
Hig
h
e
r
E
d
u
ca
tio
n
(
MO
HE
)
th
r
o
u
g
h
Fu
n
d
am
en
tal
R
esear
ch
Gr
an
t
Sch
em
e
(
FR
GS)
(
FR
GS/1
/2
0
2
3
/TK
0
7
/
UT
HM
/0
2
/1
3
)
an
d
Un
iv
e
r
s
iti
T
u
n
Hu
s
s
ein
On
n
Ma
lay
s
ia
(
UT
HM
)
th
r
o
u
g
h
T
I
E
R
1
(
v
o
t Q
5
4
5
)
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
T
h
e
f
u
n
d
in
g
in
f
o
r
m
atio
n
ca
n
b
e
r
ef
er
r
e
d
to
in
t
h
e
ac
k
n
o
wled
g
m
en
t sectio
n
.
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
T
h
is
jo
u
r
n
al
u
s
es
th
e
C
o
n
t
r
ib
u
to
r
R
o
les
T
a
x
o
n
o
m
y
(
C
R
ed
iT)
to
r
ec
o
g
n
ize
in
d
iv
i
d
u
al
au
th
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
th
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
llab
o
r
atio
n
.
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
L
i M
u
n
Ng
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Nu
r
An
id
a
J
u
m
ad
i
✓
✓
✓
✓
✓
✓
✓
Far
ah
Najid
ah
No
o
r
izan
✓
✓
C
:
C
o
n
ce
p
tu
aliza
tio
n
M
:
M
eth
o
d
o
lo
g
y
So
:
So
f
twar
e
Va
:
Va
lid
atio
n
Fo
:
Fo
r
m
al
an
aly
s
is
I
:
I
n
v
esti
g
atio
n
R
:
R
eso
u
r
ce
s
D
:
D
ata
C
u
r
atio
n
O
:
W
r
itin
g
-
O
r
ig
in
al
Dr
af
t
E
:
W
r
itin
g
-
R
ev
iew
&
E
d
itin
g
Vi
:
Vi
s
u
aliza
tio
n
Su
:
Su
p
er
v
is
io
n
P
:
P
r
o
ject
ad
m
in
is
tr
atio
n
Fu
:
Fu
n
d
in
g
ac
q
u
is
itio
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
7
6
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
,
Vo
l.
1
5
,
No
.
1
,
Ma
r
ch
20
2
6
:
21
7
-
2
2
7
226
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
T
h
e
au
th
o
r
s
co
n
f
ir
m
th
at
th
er
e
is
n
o
co
n
f
lict
o
f
in
ter
est r
elate
d
to
th
e
m
a
n
u
s
cr
ip
t.
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
o
p
en
l
y
av
ailab
le
in
DAI
SY
at
h
ttp
s
://ftp
.
esat.k
u
leu
v
en
.
b
e/p
u
b
/SIST
A/d
ata/b
io
m
ed
ical/f
o
et
al_
ec
g
.
tx
t,
r
e
f
er
en
ce
n
u
m
b
er
[
6
]
.
RE
F
E
R
E
NC
E
S
[
1
]
J.
H
a
m
p
t
o
n
a
n
d
J.
H
a
m
p
t
o
n
,
T
h
e
EC
G
Ma
d
e
E
a
sy
,
9
t
h
e
d
.
2
0
1
9
.
[
2
]
K
.
A
m
i
n
i
,
A
.
M
i
r
z
a
e
i
,
M
.
H
o
sse
i
n
i
,
H
.
Za
n
d
i
a
n
,
I
.
A
z
i
z
p
o
u
r
,
a
n
d
Y
.
H
a
g
h
i
,
“
A
sse
ssm
e
n
t
o
f
e
l
e
c
t
r
o
c
a
r
d
i
o
g
r
a
m
i
n
t
e
r
p
r
e
t
a
t
i
o
n
c
o
m
p
e
t
e
n
c
y
a
m
o
n
g
h
e
a
l
t
h
c
a
r
e
p
r
o
f
e
s
si
o
n
a
l
s
a
n
d
st
u
d
e
n
t
s
o
f
A
r
d
a
b
i
l
U
n
i
v
e
r
si
t
y
o
f
M
e
d
i
c
a
l
S
c
i
e
n
c
e
s:
a
m
u
l
t
i
d
i
sci
p
l
i
n
a
r
y
st
u
d
y
,
”
BM
C
Me
d
i
c
a
l
Ed
u
c
a
t
i
o
n
,
v
o
l
.
2
2
,
n
o
.
1
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
8
6
/
s
1
2
9
0
9
-
0
2
2
-
0
3
5
1
8
-
0.
[
3
]
G
.
D
.
C
l
i
f
f
o
r
d
,
I
.
S
i
l
v
a
,
J
.
B
e
h
a
r
,
a
n
d
G
.
B
.
M
o
o
d
y
,
“
N
o
n
-
i
n
v
a
si
v
e
f
e
t
a
l
E
C
G
a
n
a
l
y
si
s
,
”
P
h
y
s
i
o
l
o
g
i
c
a
l
Me
a
su
r
e
m
e
n
t
,
v
o
l
.
3
5
,
n
o
.
8
,
p
p
.
1
5
2
1
–
1
5
3
6
,
2
0
1
4
,
d
o
i
:
1
0
.
1
0
8
8
/
0
9
6
7
-
3
3
3
4
/
3
5
/
8
/
1
5
2
1
.
[
4
]
T.
G
h
i
e
t
a
l
.
,
“
I
n
t
r
a
p
a
r
t
u
m
f
e
t
a
l
h
e
a
r
t
r
a
t
e
b
e
t
w
e
e
n
1
5
0
a
n
d
1
6
0
b
p
m
a
t
o
r
a
f
t
e
r
4
0
w
e
e
k
s
a
n
d
l
a
b
o
r
o
u
t
c
o
m
e
,
”
A
c
t
a
O
b
s
t
e
t
ri
c
i
a
e
t
G
y
n
e
c
o
l
o
g
i
c
a
S
c
a
n
d
i
n
a
v
i
c
a
,
v
o
l
.
1
0
0
,
n
o
.
3
,
p
p
.
5
4
8
–
55
4
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
1
1
/
a
o
g
s.
1
4
0
2
4
.
[
5
]
J.
L.
M
u
ñ
o
z
,
“
P
h
y
si
c
a
l
c
h
a
n
g
e
s
d
u
r
i
n
g
p
r
e
g
n
a
n
c
y
,”
MS
D
M
a
n
u
a
l
C
o
n
s
u
m
e
r
Ve
rs
i
o
n
,
2
0
2
4
.
h
t
t
p
s
:
/
/
w
w
w
.
ms
d
ma
n
u
a
l
s
.
c
o
m/
h
o
me
/
w
o
me
n
-
s
-
h
e
a
l
t
h
-
i
ss
u
e
s/
n
o
r
ma
l
-
p
r
e
g
n
a
n
c
y
/
p
h
y
s
i
c
a
l
-
c
h
a
n
g
e
s
-
d
u
r
i
n
g
-
p
r
e
g
n
a
n
c
y
(
a
c
c
e
sse
d
Ja
n
.
1
8
,
2
0
2
5
)
.
[6
]
S
.
S
a
r
a
f
a
n
,
T.
L
e
,
M
.
P
.
H
.
La
u
,
A
.
H
a
m
e
e
d
,
T.
G
h
i
r
m
a
i
,
a
n
d
H
.
C
a
o
,
“
F
e
t
a
l
e
l
e
c
t
r
o
c
a
r
d
i
o
g
r
a
m
e
x
t
r
a
c
t
i
o
n
f
r
o
m
t
h
e
m
o
t
h
e
r
’
s
a
b
d
o
mi
n
a
l
si
g
n
a
l
u
si
n
g
t
h
e
e
n
sem
b
l
e
k
a
l
ma
n
f
i
l
t
e
r
,
”
S
e
n
s
o
rs
,
v
o
l
.
2
2
,
n
o
.
7
,
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
s
2
2
0
7
2
7
8
8
.
[
7
]
H
.
S
.
H
.
S
i
e
w
,
Y
.
S
.
A
l
s
h
e
b
l
y
,
a
n
d
M
.
N
a
f
e
a
,
“
F
e
t
a
l
EC
G
e
x
t
r
a
c
t
i
o
n
u
s
i
n
g
S
a
v
i
t
z
k
y
-
G
o
l
a
y
a
n
d
B
u
t
t
e
r
w
o
r
t
h
f
i
l
t
e
r
s,”
i
n
2
0
2
2
I
EEE
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
A
u
t
o
m
a
t
i
c
C
o
n
t
r
o
l
a
n
d
I
n
t
e
l
l
i
g
e
n
t
S
y
s
t
e
m
s,
I
2
C
A
C
I
S
2
0
2
2
-
Pr
o
c
e
e
d
i
n
g
s
,
2
0
2
2
,
p
p
.
2
1
5
–
2
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
I
2
C
A
C
I
S
5
4
6
7
9
.
2
0
2
2
.
9
8
1
5
4
6
9
.
[
8
]
S
.
E
.
S
.
G
a
n
,
S
.
K
.
D
e
b
n
a
t
h
,
Y
.
S
.
A
l
sh
e
b
l
y
,
H
.
N
u
g
r
o
h
o
,
S
.
B
a
g
c
h
i
,
a
n
d
M
.
N
a
f
e
a
,
“
F
e
t
a
l
E
C
G
e
x
t
r
a
c
t
i
o
n
f
r
o
m
a
b
d
o
mi
n
a
l
EC
G
u
si
n
g
C
h
e
b
y
s
h
e
v
a
n
d
B
u
t
t
e
r
w
o
r
t
h
f
i
l
t
e
r
s,”
I
S
C
I
2
0
2
1
-
2
0
2
1
I
EEE
S
y
m
p
o
s
i
u
m
o
n
C
o
m
p
u
t
e
rs
a
n
d
I
n
f
o
rm
a
t
i
c
s
,
p
p
.
2
5
–
3
0
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
I
S
C
I
5
1
9
2
5
.
2
0
2
1
.
9
6
3
3
5
9
5
.
[
9
]
A
.
Ja
b
a
D
e
v
a
K
r
u
p
a
,
S
.
D
h
a
n
a
l
a
k
s
h
mi
,
a
n
d
R
.
K
u
mar
,
“
J
o
i
n
t
t
i
me
-
f
r
e
q
u
e
n
c
y
a
n
a
l
y
s
i
s
a
n
d
n
o
n
-
l
i
n
e
a
r
e
st
i
ma
t
i
o
n
f
o
r
f
e
t
a
l
E
C
G
e
x
t
r
a
c
t
i
o
n
,
”
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
5
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
b
s
p
c
.
2
0
2
2
.
1
0
3
5
6
9
.
[
1
0
]
S
.
S
e
n
a
y
,
“
T
i
me
-
f
r
e
q
u
e
n
c
y
B
S
S
o
f
b
i
o
s
i
g
n
a
l
s,
”
H
e
a
l
t
h
c
a
re
T
e
c
h
n
o
l
o
g
y
L
e
t
t
e
rs
,
v
o
l
.
5
,
n
o
.
6
,
p
p
.
2
4
2
–
2
4
6
,
2
0
1
8
,
d
o
i
:
1
0
.
1
0
4
9
/
h
t
l
.
2
0
1
8
.
5
0
2
9
.
[
1
1
]
L.
Ta
h
a
a
n
d
E.
A
b
d
e
l
-
R
a
h
e
e
m,
“
A
n
u
l
l
s
p
a
c
e
-
b
a
se
d
b
l
i
n
d
s
o
u
r
c
e
se
p
a
r
a
t
i
o
n
f
o
r
f
e
t
a
l
e
l
e
c
t
r
o
c
a
r
d
i
o
g
r
a
m
si
g
n
a
l
s,
”
S
e
n
s
o
r
s
(
S
w
i
t
zer
l
a
n
d
)
,
v
o
l
.
2
0
,
n
o
.
1
2
,
p
p
.
1
–
2
8
,
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
s
2
0
1
2
3
5
3
6
.
[
1
2
]
D
.
A
.
R
a
ml
i
,
Y
.
H
.
S
h
i
o
n
g
,
a
n
d
N
.
H
a
ssa
n
,
“
B
l
i
n
d
so
u
r
c
e
s
e
p
a
r
a
t
i
o
n
(
B
S
S
)
o
f
mi
x
e
d
ma
t
e
r
n
a
l
a
n
d
f
e
t
a
l
e
l
e
c
t
r
o
c
a
r
d
i
o
g
r
a
m
(
E
C
G
)
si
g
n
a
l
:
A
c
o
m
p
a
r
a
t
i
v
e
S
t
u
d
y
,
”
Pr
o
c
e
d
i
a
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
1
7
6
,
p
p
.
5
8
2
–
5
9
1
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
r
o
c
s.
2
0
2
0
.
0
8
.
0
6
0
.
[
1
3
]
J.
H
a
o
,
Y
.
Y
a
n
g
,
Z
.
Zh
o
u
,
a
n
d
S
.
W
u
,
“
F
e
t
a
l
e
l
e
c
t
r
o
c
a
r
d
i
o
g
r
a
m
si
g
n
a
l
e
x
t
r
a
c
t
i
o
n
b
a
s
e
d
o
n
f
a
st
i
n
d
e
p
e
n
d
e
n
t
c
o
mp
o
n
e
n
t
a
n
a
l
y
si
s
a
n
d
s
i
n
g
u
l
a
r
v
a
l
u
e
d
e
c
o
m
p
o
s
i
t
i
o
n
,
”
S
e
n
s
o
rs
,
v
o
l
.
2
2
,
n
o
.
1
0
,
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
s
2
2
1
0
3
7
0
5
.
[
1
4
]
A
.
A
l
-
S
a
f
i
,
“
E
C
G
si
g
n
a
l
d
e
n
o
i
s
i
n
g
u
si
n
g
a
n
o
v
e
l
a
p
p
r
o
a
c
h
o
f
a
d
a
p
t
i
v
e
f
i
l
t
e
r
s
f
o
r
r
e
a
l
-
t
i
me
p
r
o
c
e
ss
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
El
e
c
t
r
i
c
a
l
a
n
d
C
o
m
p
u
t
e
r
En
g
i
n
e
e
r
i
n
g
,
v
o
l
.
1
1
,
n
o
.
2
,
p
p
.
1
2
4
3
–
1
2
4
9
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
c
e
.
v
1
1
i
2
.
p
p
1
2
4
3
-
1
2
4
9
.
[
1
5
]
M
.
A
.
R
a
n
j
a
n
i
k
a
r
,
S
.
V
.
J
o
s
h
i
,
J
.
M
.
W
a
g
h
mar
e
,
S
.
V
.
S
h
i
n
d
e
,
a
n
d
R
.
Y
.
P
a
t
i
l
,
“
F
e
t
a
l
e
l
e
c
t
r
o
c
a
r
d
i
o
g
r
a
m
e
x
t
r
a
c
t
i
o
n
u
si
n
g
a
d
a
p
t
i
v
e
f
i
l
t
e
r
s a
p
p
r
o
a
c
h
,
”
D
i
sr
u
p
t
i
v
e
D
e
v
e
l
o
p
m
e
n
t
s
i
n
Bi
o
m
e
d
i
c
a
l
A
p
p
l
i
c
a
t
i
o
n
s
,
p
p
.
2
0
3
–
2
2
8
,
2
0
2
2
,
d
o
i
:
1
0
.
1
2
0
1
/
9
7
8
1
0
0
3
2
7
2
6
9
4
-
1
7
.
[
1
6
]
R
.
K
a
h
a
n
k
o
v
a
,
M
.
M
i
k
o
l
a
so
v
a
,
a
n
d
R
.
M
a
r
t
i
n
e
k
,
“
O
p
t
i
m
i
z
a
t
i
o
n
o
f
a
d
a
p
t
i
v
e
f
i
l
t
e
r
c
o
n
t
r
o
l
p
a
r
a
m
e
t
e
r
s
f
o
r
n
o
n
-
i
n
v
a
s
i
v
e
f
e
t
a
l
e
l
e
c
t
r
o
c
a
r
d
i
o
g
r
a
m
e
x
t
r
a
c
t
i
o
n
,
”
PL
o
S
O
N
E
,
v
o
l
.
1
7
,
n
o
.
4
A
p
r
i
l
,
2
0
2
2
,
d
o
i
:
1
0
.
1
3
7
1
/
j
o
u
r
n
a
l
.
p
o
n
e
.
0
2
6
6
8
0
7
.
[
1
7
]
B
.
A
l
-
S
h
e
i
k
h
,
M
.
S
.
S
a
l
ma
n
,
A
.
E
l
e
y
a
n
,
a
n
d
S
.
A
l
b
o
o
n
,
“
N
o
n
-
i
n
v
a
s
i
v
e
f
e
t
a
l
EC
G
e
x
t
r
a
c
t
i
o
n
u
s
i
n
g
d
i
scr
e
t
e
w
a
v
e
l
e
t
t
r
a
n
sf
o
r
m
r
e
c
u
r
s
i
v
e
i
n
v
e
r
se
a
d
a
p
t
i
v
e
a
l
g
o
r
i
t
h
m
,
”
T
e
c
h
n
o
l
o
g
y
a
n
d
H
e
a
l
t
h
C
a
r
e
,
v
o
l
.
2
8
,
n
o
.
5
,
p
p
.
5
0
7
–
5
2
0
,
2
0
2
0
,
d
o
i
:
1
0
.
3
2
3
3
/
TH
C
-
1
9
1
9
4
8
.
[
1
8
]
M
.
A
q
i
l
a
n
d
A
.
J
b
a
r
i
,
“
El
e
c
t
r
o
c
a
r
d
i
o
g
r
a
m
f
e
a
t
u
r
e
s
d
e
t
e
c
t
i
o
n
u
si
n
g
st
a
t
i
o
n
a
r
y
w
a
v
e
l
e
t
t
r
a
n
sf
o
r
m,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
t
r
i
c
a
l
a
n
d
C
o
m
p
u
t
e
r
En
g
i
n
e
e
r
i
n
g
,
v
o
l
.
1
5
,
n
o
.
1
,
p
p
.
3
7
4
–
3
8
5
,
2
0
2
5
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
c
e
.
v
1
5
i
1
.
p
p
3
7
4
-
3
8
5
.
[
1
9
]
I
.
K
a
o
u
l
a
,
A
.
G
u
e
ss
o
u
m,
a
n
d
B
.
K
a
z
e
d
,
“
G
e
n
e
r
a
l
i
z
e
d
r
e
c
u
r
si
v
e
a
l
g
o
r
i
t
h
m
f
o
r
f
e
t
a
l
e
l
e
c
t
r
o
c
a
r
d
i
o
g
r
a
m
i
so
l
a
t
i
o
n
f
r
o
m
n
o
n
-
i
n
v
a
si
v
e
mat
e
r
n
a
l
e
l
e
c
t
r
o
c
a
r
d
i
o
g
r
a
m
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
E
l
e
c
t
ri
c
a
l
a
n
d
C
o
m
p
u
t
e
r
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
1
3
,
n
o
.
6
,
p
p
.
6
3
1
2
–
6
3
2
3
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
c
e
.
v
1
3
i
6
.
p
p
6
3
1
2
-
6
3
2
3
.
[
2
0
]
A
.
P
h
u
p
h
a
n
i
n
,
M
.
T
a
sa
k
o
r
n
,
a
n
d
J.
S
r
i
v
i
c
h
a
i
,
“
El
e
c
t
r
o
c
a
r
d
i
o
g
r
a
m
si
g
n
a
l
p
r
o
c
e
ss
i
n
g
a
l
g
o
r
i
t
h
m
o
n
m
i
c
r
o
c
o
n
t
r
o
l
l
e
r
u
s
i
n
g
w
a
v
e
l
e
t
t
r
a
n
sf
o
r
m
me
t
h
o
d
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
E
l
e
c
t
r
i
c
a
l
a
n
d
C
o
m
p
u
t
e
r
E
n
g
i
n
e
e
r
i
n
g
,
v
o
l
.
1
4
,
n
o
.
2
,
p
p
.
1
5
3
0
–
1
5
4
3
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
c
e
.
v
1
4
i
2
.
p
p
1
5
3
0
-
1
5
4
3
.
[
2
1
]
B
.
D
e
M
o
o
r
,
“
D
a
I
S
y
:
D
a
t
a
b
a
s
e
f
o
r
t
h
e
i
d
e
n
t
i
f
i
c
a
t
i
o
n
o
f
sy
st
e
ms
,”
D
e
p
t
.
EE
a
n
d
K
.
U
.
L
e
u
v
e
n
,
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
:
/
/
h
o
m
e
s.e
s
a
t
.
k
u
l
e
u
v
e
n
.
b
e
/
~
sm
c
/
d
a
i
s
y
/
%5
C
n
w
w
w
.
e
sa
t
.
k
u
l
e
u
v
e
n
.
b
e
/
si
s
t
a
/
d
a
i
s
y
/
.
[
2
2
]
Jet
B
r
a
i
n
s,
“
P
y
C
h
a
r
m:
T
h
e
P
y
t
h
o
n
I
D
E
f
o
r
p
r
o
f
e
ssi
o
n
a
l
d
e
v
e
l
o
p
e
r
s
b
y
Je
t
B
r
a
i
n
s,”
J
e
t
Br
a
i
n
s
,
2
0
2
3
,
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s
:
/
/
w
w
w
.
j
e
t
b
r
a
i
n
s.
c
o
m/
p
y
c
h
a
r
m/
.
[
2
3
]
T.
M
.
I
n
c
.
,
“
M
A
T
LA
B
v
e
r
s
i
o
n
:
2
4
.
2
.
0
.
2
7
7
3
1
4
2
(
R
2
0
2
4
b
)
,
”
T
h
e
M
a
t
h
W
o
r
k
s
I
n
c
.
,
2
0
2
4
,
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s
:
/
/
w
w
w
.
ma
t
h
w
o
r
k
s
.
c
o
m.
[
2
4
]
L.
T
a
n
a
n
d
J.
J
i
a
n
g
,
D
i
g
i
t
a
l
si
g
n
a
l
p
ro
c
e
ssi
n
g
:
F
u
n
d
a
m
e
n
t
a
l
s
a
n
d
a
p
p
l
i
c
a
t
i
o
n
s
,
3
r
d
e
d
.
A
c
a
d
e
m
i
c
P
r
e
ss,
2
0
1
3
.
[
2
5
]
N
.
J.
B
e
r
s
h
a
d
a
n
d
J
.
C
.
M
.
B
e
r
m
u
d
e
z
,
“
A
sw
i
t
c
h
e
d
v
a
r
i
a
b
l
e
st
e
p
si
z
e
N
LM
S
a
d
a
p
t
i
v
e
f
i
l
t
e
r
,
”
D
i
g
i
t
a
l
S
i
g
n
a
l
Pr
o
c
e
ssi
n
g
:
A
R
e
v
i
e
w
J
o
u
rn
a
l
,
v
o
l
.
1
0
1
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
d
sp
.
2
0
2
0
.
1
0
2
7
3
0
.
[
2
6
]
S
.
S
.
H
a
y
k
i
n
,
Ad
a
p
t
i
v
e
f
i
l
t
e
r
t
h
e
o
ry
,
5
t
h
e
d
.
2
0
1
4
.
[
2
7
]
D
.
N
i
l
a
y
,
P
.
U
t
p
a
l
,
a
n
d
D
.
C
h
i
n
t
a
n
,
“
A
c
t
i
v
e
n
o
i
s
e
c
o
n
t
r
o
l
u
s
i
n
g
L
M
S
&
N
L
M
S
a
l
g
o
r
i
t
h
m,
”
J
o
u
r
n
a
l
o
f
En
g
i
n
e
e
ri
n
g
a
n
d
T
e
c
h
n
o
l
o
g
y
(
J
ET)
,
v
o
l
.
1
,
n
o
.
1
,
p
p
.
1
–
8.
[
2
8
]
A
.
T
h
a
r
w
a
t
,
“
I
n
d
e
p
e
n
d
e
n
t
c
o
m
p
o
n
e
n
t
a
n
a
l
y
s
i
s:
A
n
i
n
t
r
o
d
u
c
t
i
o
n
,
”
A
p
p
l
i
e
d
c
o
m
p
u
t
i
n
g
a
n
d
i
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
1
7
,
n
o
.
2
,
p
p
.
2
2
2
–
2
4
9
,
2
0
1
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
c
i
.
2
0
1
8
.
0
8
.
0
0
6
.
[
2
9
]
Y
.
S
.
A
l
sh
e
b
l
y
a
n
d
M
.
N
a
f
e
a
,
“
I
so
l
a
t
i
o
n
o
f
f
e
t
a
l
EC
G
si
g
n
a
l
s
f
r
o
m
a
b
d
o
mi
n
a
l
EC
G
u
si
n
g
w
a
v
e
l
e
t
a
n
a
l
y
si
s
,”
I
r
b
m
,
v
o
l
.
4
1
,
n
o
.
5
,
p
p
.
2
5
2
–
2
6
0
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
r
b
m.2
0
1
9
.
1
2
.
0
0
2
.
Evaluation Warning : The document was created with Spire.PDF for Python.