Co
m
pu
t
er
Science
a
n
d In
f
o
r
m
a
t
io
n T
ec
hn
o
lo
g
ies
Vo
l.
2
,
No
.
3
,
No
v
em
b
er
202
1
,
p
p
.
1
13
~
1
20
I
SS
N:
2722
-
3221
,
DOI
: 1
0
.
1
1
5
9
1
/
csit
.
v
2
i
3
.p
1
13
-
1
20
113
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
p
r
ime.
co
m/in
d
ex
.
p
h
p
/csi
t
Les
s
co
m
pu
tatio
n
a
l appro
a
ch t
o
de
tect Q
RS co
m
plex
es in EC
G
rhy
th
m
s
T
a
riq M
.
Yo
un
es
1
,
M
o
ha
m
m
a
d A
l
k
he
dh
er
2
,
M
o
ha
m
a
d Al
K
ha
w
a
ldeh
3
,
J
a
la
l N
a
wa
s
h
4
,
I
bra
hi
m
A
l
-
Abba
s
5
1,
3,
5
De
p
a
rtm
e
n
t
o
f
M
e
c
h
a
tro
n
ics
En
g
in
e
e
rin
g
,
A
l
Ba
lq
a
A
p
p
li
e
d
U
n
iv
e
rsity
,
A
l
-
S
a
lt
,
Jo
rd
a
n
2
M
e
c
h
a
n
ica
l
En
g
in
e
e
rin
g
De
p
a
rt
m
e
n
t,
A
b
u
Dh
a
b
i
Un
iv
e
rsity
,
A
b
u
Dh
a
b
i,
U
n
it
e
d
A
ra
b
Em
irat
e
s
4
P
h
y
sic
s De
p
a
rt
m
e
n
t,
Un
iv
e
rsity
o
f
W
isc
o
n
sin
-
W
h
it
e
w
a
ter,
W
h
it
e
wa
ter,
USA
A
rt
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
A
ug
1
8
,
2
0
2
0
R
ev
i
s
ed
M
ar
8
,
2
0
2
1
A
cc
ep
ted
M
ar
13
,
2
0
2
1
El
e
c
tro
c
a
rd
io
g
ra
m
(EC
G
)
sig
n
a
ls
a
re
n
o
rm
a
ll
y
a
ff
e
c
ted
b
y
a
rti
f
a
c
ts
th
a
t
re
q
u
ire
m
a
n
u
a
l
a
ss
e
ss
m
e
n
t
o
r
u
se
o
f
o
t
h
e
r
re
f
e
re
n
c
e
sig
n
a
ls.
Cu
rre
n
tl
y
,
Ca
rd
io
g
ra
p
h
s
a
re
u
se
d
to
a
c
h
iev
e
b
a
sic
n
e
c
e
ss
a
r
y
h
e
a
rt
ra
te m
o
n
it
o
rin
g
in
re
a
l
c
o
n
d
i
ti
o
n
s.
T
h
is
w
o
rk
a
i
m
s
to
stu
d
y
a
n
d
id
e
n
t
ify
m
a
in
EC
G
f
e
a
t
u
re
s,
QRS
c
o
m
p
lex
e
s,
a
s
o
n
e
o
f
th
e
ste
p
s
o
f
a
c
o
m
p
re
h
e
n
siv
e
EC
G
sig
n
a
l
a
n
a
l
y
sis.
T
h
e
p
ro
p
o
se
d
a
lg
o
rit
h
m
su
g
g
e
ste
d
a
n
a
u
to
m
a
ti
c
re
c
o
g
n
it
io
n
o
f
QRS
c
o
m
p
lex
e
s
in
ECG
rh
y
th
m
.
T
h
is
m
e
th
o
d
is
d
e
sig
n
e
d
b
a
se
d
o
n
se
v
e
ra
l
f
il
te
r
stru
c
tu
re
c
o
m
p
o
se
s
lo
w
p
a
ss
,
d
iff
e
r
e
n
c
e
a
n
d
su
m
m
a
ti
o
n
f
il
ters
.
T
h
e
f
il
tere
d
s
ig
n
a
l
is
fe
d
to
a
n
a
d
a
p
ti
v
e
t
h
re
sh
o
l
d
f
u
n
c
ti
o
n
t
o
d
e
tec
t
QRS
c
o
m
p
lex
e
s.
T
h
e
a
lg
o
rit
h
m
w
a
s
v
a
li
d
a
ted
a
n
d
re
su
lt
s
w
e
re
c
h
e
c
k
e
d
w
it
h
e
x
p
e
rim
e
n
tal
d
a
ta
b
a
se
d
o
n
se
n
siti
v
it
y
tes
t.
K
ey
w
o
r
d
s
:
Au
to
m
a
tic
r
ec
o
g
n
itio
n
E
C
G
No
is
e
r
e
m
o
v
al
QR
S d
etec
tio
n
Sig
n
al
p
r
o
ce
s
s
i
n
g
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
:
Mo
h
a
m
m
ad
A
l
k
h
ed
h
er
Me
ch
an
ical
E
n
g
i
n
ee
r
in
g
Dep
a
r
t
m
en
t
A
b
u
Dh
ab
i U
n
i
v
er
s
it
y
A
b
u
Dh
ab
i,
5
9
9
1
1
Un
ited
A
r
ab
E
m
ir
ate
s
E
m
ail:
m
o
h
a
m
m
ad
.
alk
h
ed
h
er
@
ad
u
.
ac
.
ae
1.
I
NT
RO
D
UCT
I
O
N
No
w
ad
a
y
s
,
o
n
e
o
f
th
e
m
o
s
t
co
m
m
o
n
m
et
h
o
d
s
f
o
r
d
iag
n
o
s
is
a
n
d
r
ec
o
g
n
it
io
n
o
f
ca
r
d
io
v
a
s
cu
l
ar
d
is
ea
s
es
is
elec
tr
o
ca
r
d
io
g
r
ap
h
y
(
E
C
G)
.
T
h
e
E
C
G
s
ig
n
al
is
ch
ar
ac
ter
i
ze
d
b
y
a
s
et
o
f
p
ea
k
s
.
I
n
th
ese
p
ea
k
s
,
th
e
ti
m
e
an
d
a
m
p
lit
u
d
e
p
ar
am
eter
s
ar
e
d
iag
n
o
s
ed
[
1
]
.
A
s
a
n
o
r
m
al
p
r
ac
tice
b
y
ca
r
d
io
lo
g
is
t
s
,
th
e
p
r
o
ce
d
u
r
e
o
f
f
in
d
i
n
g
t
h
e
ch
ar
ac
ter
is
tic
s
o
f
E
C
G
p
ea
k
s
is
p
er
f
o
r
m
ed
u
s
in
g
d
r
a
w
i
n
g
ac
ce
s
s
o
r
ies.
Su
c
h
a
s
ch
e
m
e
i
s
q
u
ite
s
i
m
p
le
an
d
r
eliab
le,
b
u
t
it
is
ti
m
e
-
co
n
s
u
m
i
n
g
a
n
d
r
eq
u
ir
es
an
e
x
p
er
t.
Du
e
to
th
e
lack
o
f
al
ter
n
ati
v
e
ap
p
r
o
ac
h
es,
d
iag
n
o
s
i
n
g
E
C
G
p
atter
n
s
u
s
i
n
g
t
h
is
m
et
h
o
d
h
as
b
ee
n
i
m
p
le
m
e
n
ted
f
o
r
s
ev
er
al
d
ec
ad
es
[
2
]
.
Mo
s
t
o
f
t
h
e
h
ea
r
t
d
is
ea
s
e
s
ar
e
d
iag
n
o
s
ed
u
s
i
n
g
E
lectr
o
ca
r
d
io
g
r
a
m
s
i
g
n
a
ls
.
T
h
e
ac
c
u
r
ate
an
al
y
s
e
s
o
f
th
e
s
e
b
io
lo
g
ic
s
i
g
n
a
l
s
m
ak
e
it e
x
tr
e
m
e
l
y
i
m
p
o
r
tan
t
in
d
etec
tin
g
h
ea
r
t
r
h
y
th
m
ir
r
eg
u
lar
itie
s
an
d
th
e
d
iag
n
o
s
is
o
f
Hea
r
t
R
ate
Var
iab
ilit
y
(
H
R
V)
.
E
x
tr
ac
tio
n
o
f
th
e
Q
R
S
co
m
p
le
x
an
d
o
b
tain
i
n
g
i
ts
ch
ar
ac
ter
i
s
tics
i
s
o
n
e
o
f
th
e
m
o
s
t
i
m
p
o
r
ta
n
t
p
ar
ts
in
E
C
G
s
ig
n
al
p
r
o
ce
s
s
in
g
an
d
a
n
al
y
s
i
s
,
esp
e
ciall
y
t
h
e
w
a
v
e
k
n
o
w
n
a
s
R
.
R
ec
en
t
ad
v
a
n
ce
s
i
n
elec
tr
o
n
ic
m
ed
ical
eq
u
ip
m
e
n
t
m
ad
e
it
p
o
s
s
ib
le
f
o
r
ex
p
er
i
m
en
tal,
cli
n
ical,
an
d
p
r
ev
en
tiv
e
m
ed
icin
e
to
u
tili
ze
en
g
i
n
ee
r
i
n
g
e
x
p
er
tis
e
i
n
th
e
d
esig
n
o
f
co
m
p
lex
co
n
tr
o
l
s
y
s
te
m
s
t
h
at
ar
e
r
elate
d
to
th
e
d
iag
n
o
s
is
o
f
th
e
s
ta
te
o
f
th
e
h
u
m
an
b
o
d
y
[
3
]
.
T
h
ese
tech
n
o
lo
g
ical
d
ev
elo
p
m
e
n
ts
al
lo
w
ed
th
e
au
to
m
atic
d
iag
n
o
s
is
o
f
f
etal
h
ea
r
t r
ate
u
s
in
g
d
if
f
er
en
t
m
et
h
o
d
o
lo
g
ical
ap
p
r
o
ac
h
es
[
4
]
.
I
n
v
esti
g
ati
n
g
v
ar
io
u
s
d
iag
n
o
s
tic
m
e
th
o
d
s
s
h
o
w
s
th
a
t
t
h
e
m
o
s
t
u
s
e
f
u
l
i
n
f
o
r
m
atio
n
o
n
t
h
e
f
u
n
ctio
n
i
n
g
o
f
i
n
te
r
n
al
o
r
g
a
n
s
an
d
p
h
y
s
io
lo
g
ical
s
y
s
te
m
s
o
f
h
u
m
an
b
o
d
y
is
co
n
tai
n
ed
in
b
io
elec
tr
ic
s
ig
n
al
s
.
T
h
ese
s
ig
n
a
ls
ar
e
tak
en
f
r
o
m
v
ar
io
u
s
ar
ea
s
p
ar
ts
,
u
n
d
er
th
e
s
k
in
o
r
f
r
o
m
t
h
e
s
u
r
f
ac
e
o
f
th
e
b
o
d
y
[
5
]
.
T
h
is
r
ef
er
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2722
-
3221
C
o
m
p
u
t.
Sci.
I
n
f
.
T
ec
h
n
o
l.
,
Vo
l.
2
,
No
.
3
,
No
v
em
b
er
20
2
1
:
1
13
–
1
20
114
to
th
e
elec
tr
ical
ac
ti
v
it
y
o
f
th
e
h
ea
r
t,
th
e
elec
tr
ic
f
ie
ld
o
f
t
h
e
b
r
ain
,
an
d
t
h
e
elec
tr
ical
p
o
ten
t
ia
ls
o
f
b
o
d
y
m
u
s
cles
[
6
]
.
I
n
g
en
er
al,
a
n
y
elec
tr
o
p
h
y
s
io
lo
g
ical
s
t
u
d
y
i
s
r
ep
r
esen
ted
b
y
t
h
r
ee
s
u
cc
es
s
i
v
e
s
tag
e
s
:
r
e
m
o
v
al,
r
e
g
is
tr
atio
n
an
d
p
r
o
ce
s
s
in
g
o
f
b
io
elec
tr
ic
ac
tiv
it
y
s
i
g
n
al
s
[
7
]
.
T
h
e
s
p
ec
if
ic
f
ea
tu
r
es
i
n
h
er
ited
in
a
p
ar
ticu
lar
m
et
h
o
d
o
f
i
m
p
le
m
en
t
in
g
ea
c
h
o
f
th
e
s
e
s
tag
es
ab
o
v
e
d
eter
m
i
n
e
t
h
e
s
et
o
f
r
eq
u
ir
e
m
e
n
t
s
a
n
d
r
estricti
o
n
s
o
n
th
e
p
o
s
s
ib
le
i
m
p
le
m
en
ta
tio
n
o
f
th
e
o
th
er
s
t
ag
es
[
8
]
.
Fo
r
s
ev
er
al
d
ec
ad
es,
t
h
e
r
eliab
ilit
y
o
f
b
io
elec
tr
ic
s
tu
d
ies w
as
li
m
ited
b
y
th
e
tec
h
n
ica
l
ca
p
ab
ilit
ies
o
f
r
e
co
r
d
in
g
an
d
d
is
p
la
y
in
g
i
n
f
o
r
m
atio
n
.
T
h
is
h
i
n
d
er
ed
th
e
d
ev
el
o
p
m
e
n
t
o
f
m
et
h
o
d
s
f
o
r
th
e
a
u
to
m
a
tic
p
r
o
ce
s
s
i
n
g
o
f
elec
tr
o
ca
r
d
io
g
r
am
s
i
g
n
als.
Du
r
i
n
g
th
e
last
d
ec
ad
e
,
d
ev
elo
p
m
en
t
in
m
icr
o
elec
tr
o
n
ics
an
d
co
m
p
u
t
er
tech
n
o
lo
g
y
a
llo
w
ed
th
e
e
li
m
i
n
atio
n
o
f
in
s
tr
u
m
e
n
tal
d
i
s
to
r
tio
n
s
,
a
n
d
th
e
ap
p
licatio
n
o
f
d
i
g
ital
s
i
g
n
a
l
p
r
o
ce
s
s
in
g
m
et
h
o
d
s
,
t
h
e
i
m
p
le
m
en
tatio
n
o
f
w
h
ic
h
w
as
p
r
ev
io
u
s
l
y
i
m
p
o
s
s
ib
le.
A
s
p
ec
ial
p
o
in
t
a
m
o
n
g
elec
tr
o
p
h
y
s
io
lo
g
ical
d
iag
n
o
s
tic
m
et
h
o
d
s
is
m
ea
s
u
r
i
n
g
a
n
d
p
r
o
ce
s
s
in
g
o
f
a
n
el
ec
tr
o
ca
r
d
io
g
r
am
.
Si
n
ce
th
e
elec
tr
o
ca
r
d
io
g
r
am
is
th
e
m
ain
i
n
d
icato
r
th
at
cu
r
r
en
tl
y
allo
w
s
t
h
e
p
r
o
p
h
y
lact
ic
an
d
th
er
ap
eu
tic
co
n
tr
o
l
o
f
ca
r
d
io
v
ascu
lar
d
is
ea
s
e
s
;
t
h
e
ef
f
ec
ti
v
e
n
es
s
o
f
elec
tr
o
ca
r
d
io
g
r
ap
h
ic
d
iag
n
o
s
t
ic
m
et
h
o
d
s
ca
n
b
e
f
ac
ili
tated
b
y
t
h
e
w
ell
-
estab
l
i
s
h
ed
lead
s
y
s
te
m
a
n
d
w
id
esp
r
ea
d
u
s
e
o
f
q
u
a
n
tita
tiv
e
E
C
G
in
d
icato
r
s
.
Dete
ctio
n
a
n
d
id
en
tific
atio
n
o
f
Q
R
S
co
m
p
lex
e
s
ar
e
o
n
e
o
f
t
h
e
m
ai
n
ta
s
k
s
i
n
t
h
e
a
n
al
y
s
i
s
o
f
a
ca
r
d
io
g
r
a
m
[
9
]
.
T
h
e
s
ep
ar
atio
n
o
f
QR
S
co
m
p
l
ex
es h
elp
s
to
s
o
lv
e
p
r
o
b
le
m
s
s
u
ch
a
s
an
al
y
s
i
s
o
f
t
h
e
E
C
G
r
h
y
th
m
,
r
ec
o
g
n
itio
n
o
f
P
,
QR
S,
T
f
ea
tu
r
es,
an
d
co
m
p
r
ess
io
n
o
f
t
h
e
ca
r
d
io
g
r
a
m
.
I
n
o
r
d
er
to
co
m
p
lete
th
e
s
i
g
n
a
l
av
er
ag
i
n
g
p
r
o
ce
s
s
,
r
ef
er
en
ce
p
o
in
ts
m
u
s
t b
e
d
ef
in
ed
in
ea
ch
c
y
cle.
P
ea
k
lo
ca
tio
n
s
o
f
R
w
a
v
es a
r
e
u
s
ed
as r
ef
e
r
en
ce
p
o
in
ts
.
Fig
u
r
e
1
(
a)
s
h
o
w
s
a
p
ar
t o
f
a
ca
r
d
io
g
r
a
m
w
it
h
a
n
o
r
m
a
l h
ea
r
t r
h
y
t
h
m
.
Fi
g
u
r
e
1
(
b
)
ca
r
d
io
g
r
am
k
e
y
f
ea
t
u
r
es.
(
a)
E
C
G
s
a
m
p
le
s
i
g
n
al
(
b
)
E
C
G
em
b
ed
d
ed
co
m
p
le
x
e
s
Fig
u
r
e
1
.
T
h
ese
f
ig
u
r
es a
r
e;
(
a)
Sa
m
p
le
o
f
r
etr
iev
ed
ca
r
d
io
g
r
a
m
s
i
g
n
al
w
it
h
n
o
r
m
a
l h
ea
r
t r
h
y
t
h
m
(
b
)
E
C
G
m
ai
n
ch
ar
ac
ter
is
t
ics
f
ea
tu
r
e
s
,
in
clu
d
i
n
g
P
,
T
,
an
d
QR
S c
o
m
p
lex
es.
Sev
er
al
ap
p
r
o
ac
h
es su
g
g
e
s
ted
alg
o
r
ith
m
s
as
h
id
d
en
Ma
r
k
o
v
m
o
d
el
s
[
1
0
]
f
o
r
o
n
lin
e
r
h
y
th
m
r
ec
o
r
d
in
g
o
f
an
E
C
G
s
i
g
n
a
l.
Fo
r
s
u
ch
ap
p
r
o
ac
h
es,
t
w
o
lead
s
o
f
a
c
ar
d
io
g
r
am
ar
e
u
s
ed
s
i
m
u
lta
n
e
o
u
s
l
y
,
alt
h
o
u
g
h
th
i
s
m
et
h
o
d
p
r
o
v
id
es
s
o
m
e
ad
v
an
tag
es,
ti
m
es
o
f
h
ea
r
tb
ea
ts
g
i
v
en
b
y
th
e
s
e
lead
s
m
a
y
n
o
t
co
in
cid
e
[
1
1
]
.
T
h
e
alg
o
r
ith
m
u
s
i
n
g
o
n
e
E
C
G
ch
a
n
n
el
i
s
p
ar
ticu
lar
l
y
co
n
v
e
n
ie
n
t
f
o
r
s
tan
d
-
alo
n
e
m
o
n
ito
r
s
.
I
t
is
also
u
s
ed
in
m
an
y
o
th
er
d
ev
ices
s
u
c
h
as
h
o
m
e
a
p
p
lian
ce
s
,
d
ef
ib
r
illato
r
s
,
an
d
i
n
tele
m
etr
y
f
o
r
d
ev
ices
w
it
h
l
i
m
ited
b
an
d
w
id
t
h
.
A
l
g
o
r
ith
m
s
w
er
e
e
m
p
lo
y
ed
to
an
al
y
ze
E
C
G
s
u
c
h
as
th
e
Ha
m
ilto
n
-
T
o
m
p
k
i
n
s
(
H
-
T
)
alg
o
r
ith
m
a
s
w
ell
as
th
e
Hilb
er
t
tr
an
s
f
o
r
m
-
b
ased
alg
o
r
ith
m
s
[
1
2
]
.
Ma
n
y
o
th
er
alg
o
r
i
th
m
s
ex
i
s
t,
an
d
th
e
co
m
b
in
at
i
o
n
o
f
u
s
i
n
g
t
w
o
o
f
th
e
m
o
r
m
o
r
e
d
ee
m
ed
to
b
e
b
e
n
ef
icial
in
b
etter
p
in
p
o
in
ti
n
g
th
e
lo
ca
tio
n
o
f
Q,
R
,
an
d
S
p
ea
k
s
[
1
3
]
.
Fo
r
ex
am
p
le
.
th
e
H
-
T
alg
o
r
ith
m
ac
c
u
r
ac
y
w
a
s
test
ed
o
n
g
e
n
er
ated
M
AT
L
A
B
E
C
G
s
i
g
n
a
ls
a
n
d
f
o
u
n
d
a
r
eliab
le
ac
cu
r
ac
y
ev
en
th
o
u
g
h
m
o
d
er
ate
to
h
ig
h
n
o
i
s
es
w
er
e
p
r
ese
n
t
[
1
4
]
.
T
h
ese
r
es
u
lt
s
w
er
e
v
er
y
e
n
co
u
r
ag
in
g
to
t
h
e
u
s
e
o
f
h
an
d
h
eld
d
ev
ices
w
ith
m
o
s
t
l
y
u
s
e
t
h
is
m
eth
o
d
.
T
h
e
Hi
lb
er
t
tr
an
s
f
o
r
m
-
b
ased
alg
o
r
it
h
m
s
f
o
u
n
d
b
etter
ap
p
licatio
n
s
in
tr
a
n
s
f
o
r
m
ed
s
i
g
n
al
s
w
h
er
e
it is
u
s
ed
to
s
u
p
p
r
ess
u
n
w
a
n
ted
w
av
e
f
o
r
m
s
o
r
s
ig
n
a
l
s
[
1
5
]
.
Ma
th
e
m
atica
l
an
d
s
tat
is
tical
m
o
d
el
s
[
1
6
]
w
er
e
u
s
ed
to
h
el
p
ex
tr
ac
t
ac
cu
r
ate
r
esu
lts
.
Ne
v
er
th
e
less
,
d
ep
en
d
in
g
o
n
th
e
q
u
alit
y
lev
e
l
o
f
th
e
d
atab
ase,
t
h
e
ac
cu
r
ac
y
r
an
g
ed
f
r
o
m
7
8
.
9
9
%
to
9
9
%
[
1
7
]
.
B
esid
es
th
e
p
r
esen
ce
o
f
f
al
lacio
u
s
s
i
g
n
als
an
d
n
o
is
e,
t
h
e
m
ai
n
p
r
o
b
le
m
in
d
etec
t
in
g
Q
R
S
o
cc
u
r
s
f
o
r
elec
tr
o
ca
r
d
io
g
r
am
s
w
it
h
a
v
ar
iab
le
r
h
y
th
m
,
w
h
er
e
P
an
d
T
w
av
e
s
h
a
v
e
s
i
g
n
i
f
ica
n
t v
alu
e
s
.
T
h
e
g
en
er
al
s
tr
u
ct
u
r
e
o
f
a
QR
S d
etec
to
r
co
n
s
is
ts
o
f
t
w
o
s
tag
e
s
[
18
]
:
i
n
s
ta
g
e
o
n
e;
th
e
d
ig
itized
ca
r
d
io
g
r
a
m
d
ata
is
f
ilter
ed
to
elim
i
n
ate
n
o
is
e
a
n
d
to
eli
m
i
n
ate
P
an
d
T
w
a
v
es.
F
u
r
t
h
er
,
in
o
r
d
er
to
am
p
li
f
y
t
h
e
R
w
a
v
e,
th
e
o
u
tp
u
t s
ig
n
al
i
s
p
r
o
ce
s
s
ed
b
y
n
o
n
-
l
in
ea
r
tr
an
s
f
o
r
m
atio
n
s
,
s
u
c
h
as
a
q
u
a
d
r
atic
f
u
n
ctio
n
.
Seco
n
d
l
y
,
to
o
b
tain
t
h
e
b
o
u
n
d
ar
y
p
o
in
ts
o
f
t
h
e
QR
S
co
m
p
lex
,
a
n
alg
o
r
i
th
m
w
it
h
a
th
r
esh
o
l
d
f
u
n
ctio
n
(
T
o
m
p
k
i
n
s
alg
o
r
ith
m
)
is
u
s
ed
.
A
s
an
alter
n
ati
v
e
to
th
e
T
o
m
p
k
i
n
s
’
al
g
o
r
ith
m
,
Z
i
g
el
’
s
alg
o
r
ith
m
[
18
]
ca
n
b
e
u
tili
ze
d
w
i
th
s
o
m
e
m
o
d
if
icatio
n
.
Z
i
g
el
’
s
alg
o
r
it
h
m
als
o
co
n
s
is
ts
o
f
t
w
o
s
ta
g
es,
b
u
t
it
h
as
a
d
i
f
f
er
en
t
ap
p
r
o
ac
h
i
n
d
eter
m
i
n
in
g
t
h
e
r
e
f
r
ac
to
r
y
p
er
io
d
(
p
er
i
o
d
o
f
n
o
n
-
Evaluation Warning : The document was created with Spire.PDF for Python.
C
o
m
p
u
t.
Sci.
I
n
f
.
T
ec
h
n
o
l.
Les
s
co
mp
u
ta
tio
n
a
l a
p
p
r
o
a
ch
to
d
etec
t Q
R
S
co
mp
lexe
s
in
E
C
G
r
h
yth
ms
(
Ta
r
iq
M.
Yo
u
n
es
)
115
ex
citab
ilit
y
)
in
th
e
s
i
g
n
a
l.
I
n
th
e
f
ir
s
t
s
ta
g
e,
p
er
io
d
s
o
f
n
o
n
-
e
x
citab
ilit
y
ar
e
d
eter
m
i
n
ed
w
h
e
r
e
th
er
e
is
n
o
QR
S,
an
d
th
u
s
Q
R
S c
o
m
p
le
x
es
ar
e
a
p
p
r
o
x
im
a
tel
y
d
eter
m
in
ed
.
2.
RE
S
E
ARCH
M
E
T
H
O
D
T
h
e
d
esire
d
QR
S
w
a
v
e
f
o
r
m
s
ar
e
d
eter
m
in
ed
u
s
i
n
g
a
“L
o
w
P
ass
”
Fil
ter
(
L
P
F),
a
d
if
f
er
en
c
e
f
ilter
i
n
g
,
an
d
m
o
v
i
n
g
av
er
a
g
e
f
ilter
i
n
g
.
T
h
is
p
r
o
ce
d
u
r
e,
d
em
o
n
s
tr
ated
in
Fig
u
r
e
2
,
allo
w
s
f
o
r
th
e
esti
m
atio
n
o
f
an
ap
p
r
o
x
im
a
te
r
an
g
e
o
f
Q
R
S
co
m
p
lex
e
s
v
al
u
es.
T
h
is
f
ilter
in
g
also
d
is
ca
r
d
s
f
allac
io
u
s
s
i
g
n
al
s
ca
u
s
ed
b
y
T
w
a
v
e
s
an
d
n
o
is
e.
A
f
ilter
d
esi
g
n
co
n
s
tr
ai
n
w
h
e
n
u
s
i
n
g
a
co
n
s
tan
t
th
r
es
h
o
ld
f
u
n
ctio
n
is
th
e
p
r
o
ce
d
u
r
e
ac
cu
r
ac
y
,
esp
ec
iall
y
w
i
th
s
ig
n
al
s
co
n
tai
n
in
g
a
lar
g
e
ad
m
i
x
t
u
r
e
o
f
E
MG
n
o
is
e
o
r
ar
tif
ac
ts
o
f
m
o
tio
n
[
1
9
]
.
(
a)
(
b
)
(
c)
Fig
u
r
e
2
.
E
C
G
f
iltra
t
io
n
p
r
o
ce
d
u
r
e:
L
o
w
P
ass
FIR
Fil
ter
,
d
if
f
er
en
ce
f
ilter
i
n
g
,
m
o
v
i
n
g
av
er
ag
e
f
i
lter
;
(
a
)
Step
1
: L
o
w
p
ass
FI
R
,
(
b
)
Step
2
: D
if
f
er
en
ce
f
ilter
,
(
c
)
Step
3
: M
o
v
in
g
a
v
er
ag
e
f
ilter
I
n
th
e
s
ec
o
n
d
s
tag
e,
th
e
th
r
e
s
h
o
ld
f
u
n
ctio
n
is
u
s
ed
.
Ho
w
ev
er
,
th
e
alg
o
r
ith
m
f
a
ils
w
h
e
n
t
h
e
s
ig
n
al
co
n
tain
s
a
lo
t
o
f
h
i
g
h
-
f
r
eq
u
e
n
c
y
n
o
i
s
e
[
2
0
]
.
T
h
is
is
b
ec
a
u
s
e
th
e
t
h
r
es
h
o
ld
d
ep
en
d
s
o
n
th
e
d
er
iv
ativ
e
v
al
u
es
o
f
th
e
s
i
g
n
al.
I
n
t
h
is
p
ap
er
,
it
is
p
r
o
p
o
s
ed
th
at
th
e
th
r
e
s
h
o
ld
is
s
e
t
as
a
v
ar
iab
le
f
u
n
c
tio
n
t
h
a
t
is
a
d
j
u
s
ted
ea
ch
p
er
io
d
u
n
t
il
it
r
ea
ch
e
s
a
p
ar
a
m
eter
d
ef
in
ed
b
y
th
e
u
s
er
.
T
h
e
p
r
o
p
o
s
ed
m
et
h
o
d
in
clu
d
es
s
i
g
n
al
p
r
e
-
p
r
o
ce
s
s
in
g
,
f
iltra
tio
n
s
eq
u
en
ce
,
r
o
b
u
s
t
th
r
es
h
o
ld
an
al
y
s
i
s
an
d
s
u
b
s
eq
u
e
n
tl
y
,
QR
S
d
etec
tio
n
f
o
r
E
C
G
is
d
escr
ib
ed
in
th
e
b
elo
w
s
ec
tio
n
s
.
2
.
1
.
Appl
y
ing
l
ow
-
pa
s
s
f
ilte
r
t
o
c
a
rdio
g
ra
m
s
ig
na
l
F
ir
s
t,
th
e
ca
r
d
io
g
r
a
m
s
ig
n
al
is
f
ed
th
r
o
u
g
h
a
lo
w
-
p
a
s
s
FIR
f
il
ter
w
it
h
p
ass
b
an
d
u
p
p
er
f
r
eq
u
en
c
y
1
Hz,
s
to
p
b
an
d
lo
w
er
f
r
eq
u
en
c
y
4
5
Hz.
A
s
s
tated
i
n
th
e
liter
at
u
r
e,
m
o
s
t
ca
r
d
io
g
r
a
m
en
er
g
y
i
s
in
a
r
an
g
e
o
f
1
Hz
-
45
Hz
[
2
1
]
.
T
h
er
ef
o
r
e,
th
e
cu
to
f
f
f
r
eq
u
en
c
y
f
o
r
th
is
f
ilter
is
4
5
Hz.
T
h
e
f
ilter
ed
s
ig
n
al
k
ee
p
s
m
o
s
t
o
f
th
e
e
n
er
g
y
f
o
r
th
e
o
r
ig
in
a
l
s
i
g
n
al,
r
estra
i
n
in
g
h
ig
h
-
f
r
eq
u
en
c
y
n
o
i
s
e
[
2
2
]
.
T
h
is
in
clu
d
e
s
th
e
5
0
Hz
in
ter
f
er
e
n
ce
o
f
th
e
elec
tr
ical
n
et
w
o
r
k
[
2
3
]
.
I
n
s
o
m
e
ca
s
es,
it
m
a
y
b
e
p
o
s
s
ib
le
to
ap
p
ly
m
o
r
e
t
h
o
r
o
u
g
h
f
ilter
in
g
t
o
im
p
r
o
v
e
t
h
e
r
esu
lt
b
y
u
s
i
n
g
o
th
er
t
y
p
e
s
o
f
f
ilter
s
as
a
n
o
tch
f
ilter
o
r
w
a
v
elet
d
o
m
a
in
[
2
4
]
.
Ho
w
ev
er
,
t
h
e
g
o
a
l
o
f
th
i
s
s
ta
g
e
is
to
d
eter
m
in
e
t
h
e
ap
p
r
o
x
i
m
ate
in
t
er
v
als
o
f
t
h
e
Q
R
S
co
m
p
le
x
e
s
.
T
h
is
p
r
o
ce
s
s
is
b
ar
el
y
d
ep
en
d
en
t
o
n
t
h
e
f
allac
io
u
s
s
ig
n
al
f
ilter
ed
b
y
L
P
F.
Fi
g
u
r
e
3
s
h
o
w
s
d
etails o
f
th
e
u
s
ed
L
P
F.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2722
-
3221
C
o
m
p
u
t.
Sci.
I
n
f
.
T
ec
h
n
o
l.
,
Vo
l.
2
,
No
.
3
,
No
v
em
b
er
20
2
1
:
1
13
–
1
20
116
Fig
u
r
e
3
.
T
h
e
am
p
lit
u
d
e
r
esp
o
n
s
e
o
f
t
h
e
L
P
F tr
an
s
f
er
f
u
n
ctio
n
.
x
-
ax
is
i
n
X/1
0
0
Hz
As
ca
n
b
e
s
ee
n
i
n
Fi
g
u
r
e
4
,
th
e
f
il
ter
ed
o
u
tp
u
t
s
i
g
n
a
l
is
s
m
o
o
t
h
er
an
d
co
n
tai
n
s
le
s
s
n
o
i
s
e
th
a
n
th
e
o
r
ig
in
al
s
ig
n
al.
I
t c
o
m
p
ar
es t
h
e
in
itial c
ar
d
io
g
r
a
m
s
i
g
n
al
w
i
t
h
its
f
ilter
ed
lo
w
p
a
s
s
o
u
tp
u
t.
(
a)
I
n
itial r
a
w
E
C
G
s
i
g
n
a
l.
x
-
a
x
is
i
s
ti
m
e
s
a
m
p
les
(
b
)
Fil
ter
ed
E
C
G
s
ig
n
al.
x
-
ax
i
s
is
ti
m
e
s
a
m
p
les
Fig
u
r
e
4
.
C
o
m
p
ar
is
o
n
b
et
w
ee
n
th
e
i
n
itia
l si
g
n
al
(
a)
an
d
f
ilte
r
ed
s
ig
n
al
(
b
)
.
Af
ter
f
ilter
i
n
g
,
t
h
e
i
n
ter
v
al
s
b
e
ca
m
e
s
m
o
o
t
h
er
.
A
s
in
FIR
f
i
lte
r
s
,
th
e
d
i
f
f
er
en
ce
f
i
lter
a
m
p
l
if
i
es
R
w
av
e
s
an
d
r
ed
u
ce
s
th
e
P
an
d
T
w
a
v
es
.
I
t
also
r
ed
u
ce
s
th
e
b
ac
k
g
r
o
u
n
d
n
o
is
e
o
f
th
e
w
a
v
e
f
o
r
m
.
T
h
e
d
if
f
er
e
n
ce
f
i
lter
h
a
s
th
e
f
o
r
m
[
2
5
]
,
[
2
6
]
:
[
]
=
[
]
−
[
−
1
]
2
(
1
)
W
h
er
e:
x
[
n
]
is
th
e
o
u
tp
u
t
s
ig
n
al
o
f
t
h
e
lo
w
p
as
s
f
ilter
.
d
[
n
]
is
th
e
o
u
tp
u
t
s
i
g
n
al
o
f
t
h
e
d
i
f
f
er
en
ce
f
ilter
.
F
ig
u
r
e
5
s
h
o
w
s
t
h
e
c
h
ar
ac
ter
is
tics
o
f
th
e
ap
p
lied
d
if
f
er
en
ce
f
i
lter
.
(
a)
Dif
f
er
e
n
ce
f
il
ter
d
B
(
b
)
Dif
f
er
en
ce
f
ilter
P
h
ase
a
n
g
le
Fig
u
r
e
5
.
The
se
fi
g
ure
s
a
re
;
(
a)
Am
p
lit
u
d
e
an
d
(
b
)
p
h
ase
p
lo
ts
o
f
d
if
f
er
en
ce
f
ilter
.
x
-
ax
i
s
in
X/1
0
0
Hz
Evaluation Warning : The document was created with Spire.PDF for Python.
C
o
m
p
u
t.
Sci.
I
n
f
.
T
ec
h
n
o
l.
Les
s
co
mp
u
ta
tio
n
a
l a
p
p
r
o
a
ch
to
d
etec
t Q
R
S
co
mp
lexe
s
in
E
C
G
r
h
yth
ms
(
Ta
r
iq
M.
Yo
u
n
es
)
117
2
.
2
.
M
o
v
ing
a
v
er
a
g
e
f
ilte
r
T
h
e
d
if
f
er
en
ce
f
i
lter
w
as
f
o
u
n
d
to
r
ed
u
ce
th
e
n
o
n
-
QR
S
f
ea
t
u
r
es;
h
o
w
ev
er
,
it
a
ls
o
i
n
cr
ea
s
e
s
th
e
h
i
g
h
-
f
r
eq
u
en
c
y
n
o
i
s
e
th
at
r
e
m
ai
n
s
a
f
ter
th
e
L
P
F.
T
o
r
ed
u
ce
s
h
o
r
t
-
t
er
m
in
ter
f
er
en
ce
,
it
is
n
ec
es
s
ar
y
to
ap
p
l
y
a
m
o
v
i
n
g
av
er
ag
e
f
ilter
as
in
(
2
)
.
T
h
e
f
ilter
s
ize
is
tak
en
to
m
atc
h
t
h
e
ap
p
r
o
x
i
m
ate
w
id
t
h
o
f
th
e
Q
R
S
co
m
p
le
x
es
[
2
7
]
,
[
2
8
]
.
[
]
=
∑
|
[
+
]
|
16
=
−
16
(
2
)
2
.
3
.
T
hres
ho
ld f
un
ct
io
n
T
h
e
ap
p
r
o
x
im
a
te
in
ter
v
als
o
f
th
e
QR
S
co
m
p
lex
e
s
ca
n
b
e
d
eter
m
in
ed
u
s
in
g
th
e
t
h
r
esh
o
l
d
m
o
v
in
g
av
er
ag
e
v
alu
e
o
f
th
e
o
u
tp
u
t
f
il
ter
:
ℎ
[
0
]
=
[
]
+
[
]
−
[
]
2
.
4
(
3
)
I
t
is
also
p
o
s
s
ib
le
to
u
s
e
an
a
d
ap
tiv
e
th
r
es
h
o
ld
f
u
n
ctio
n
w
h
en
th
e
d
etec
tio
n
o
f
lo
w
er
in
te
r
v
als
f
ai
ls
.
T
h
is
tak
es
p
lace
w
h
en
a
lar
g
e
n
u
m
b
er
o
f
h
i
g
h
-
f
r
eq
u
e
n
c
y
n
o
is
e
o
r
s
ig
n
al
d
i
s
to
r
tio
n
s
ar
e
g
en
er
ated
w
h
en
t
h
e
p
atien
t
m
o
v
es:
ℎ
[
]
=
ℎ
[
−
1
]
+
[
]
+
[
]
−
[
]
2
.
8
2
(
4
)
3.
AL
G
O
RI
T
H
M
VALI
DAT
I
O
N
I
n
Fig
u
r
e
6
,
a
s
a
m
p
le
o
f
b
o
u
n
d
ar
y
d
eter
m
i
n
atio
n
p
r
o
ce
s
s
u
s
in
g
t
h
e
t
h
r
esh
o
ld
f
u
n
ctio
n
i
s
s
h
o
w
n
.
A
s
d
em
o
n
s
tr
atio
n
s
a
m
p
les
f
o
r
d
if
f
er
en
t
E
C
G
r
etr
iev
ed
w
i
th
d
i
f
f
er
en
t
co
n
d
itio
n
s
,
th
e
d
e
v
elo
p
ed
QR
S
al
g
o
r
it
hm
w
a
s
test
ed
w
it
h
t
h
r
ee
ca
r
d
io
g
r
a
m
s
i
g
n
als (
E
C
G3
.
d
at,
E
C
G4
.
d
at,
an
d
E
C
G5
.
d
at)
.
I
n
th
e
E
C
G3
s
ig
n
al.
d
at,
th
er
e
is
a
m
o
d
er
ate
a
m
o
u
n
t
o
f
n
o
n
d
eter
m
i
n
is
tic
g
r
o
u
n
d
n
o
is
e
t
h
at
ca
n
b
e
p
r
o
d
u
ce
d
b
y
t
h
e
p
atien
t
'
s
b
r
ea
t
h
i
n
g
.
B
o
u
n
d
ar
y
o
f
Q
R
S
w
as
s
u
cc
e
s
s
f
u
l a
s
s
h
o
w
n
i
n
Fi
g
u
r
e
7
.
Fig
u
r
e
6
.
T
h
e
r
esu
lt o
f
th
e
b
o
u
n
d
ar
y
d
eter
m
i
n
atio
n
p
r
o
ce
s
s
u
s
in
g
t
h
e
th
r
es
h
o
ld
f
u
n
ctio
n
.
x
-
ax
is
i
s
ti
m
e
s
a
m
p
les
Fig
u
r
e
7
.
QR
S d
etec
tio
n
r
es
u
lt
f
o
r
E
C
G3
.
d
at
s
ig
n
al.
x
-
a
x
is
i
s
ti
m
e
s
a
m
p
les
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2722
-
3221
C
o
m
p
u
t.
Sci.
I
n
f
.
T
ec
h
n
o
l.
,
Vo
l.
2
,
No
.
3
,
No
v
em
b
er
20
2
1
:
1
13
–
1
20
118
Fig
u
r
e
8
s
h
o
w
s
t
h
e
E
C
G4
.
d
at
s
ig
n
al
w
h
ic
h
is
a
f
f
ec
ted
b
y
a
b
ase
ch
a
n
g
e
at
t
h
e
en
d
.
T
h
is
ca
n
b
e
ca
u
s
ed
b
y
th
e
m
o
v
e
m
en
t o
f
th
e
p
atien
t a
n
d
b
y
h
ig
h
-
f
r
eq
u
e
n
c
y
n
o
is
e.
T
h
e
in
f
l
u
en
ce
o
f
t
h
o
s
e
e
f
f
ec
ts
is
clea
r
l
y
n
o
ticed
,
as th
e
i
n
ter
v
al
s
b
ec
o
m
e
w
id
er
.
Fig
u
r
e
8
.
QR
S d
etec
tio
n
r
es
u
lt
f
o
r
E
C
G4
.
d
at
s
ig
n
al.
x
-
a
x
is
i
s
ti
m
e
s
a
m
p
les
Fig
u
r
e
9
s
h
o
w
s
s
i
g
n
al
(
E
C
G5
.
d
at)
w
h
ich
is
ex
tr
e
m
el
y
d
is
to
r
ted
.
A
ls
o
w
it
h
i
n
7
s
ec
o
n
d
s
,
a
s
h
ar
p
ed
m
o
tio
n
s
i
g
n
a
l
ap
p
ea
r
s
s
i
m
u
lati
n
g
th
e
Q
R
S
co
m
p
lex
.
T
h
is
f
all
ac
io
u
s
m
o
tio
n
s
i
g
n
al
m
a
k
es
t
h
e
d
etec
tio
n
o
f
Q
R
S
co
m
p
le
x
a
ch
al
len
g
i
n
g
ta
s
k
.
Fig
u
r
e
9
.
QR
S d
etec
tio
n
r
es
u
lt
f
o
r
E
C
G5
.
d
at
s
ig
n
al.
x
-
a
x
is
i
s
ti
m
e
s
a
m
p
les
T
h
e
p
r
o
p
o
s
ed
QR
S
d
etec
tio
n
a
lg
o
r
ith
m
is
test
ed
u
s
in
g
th
r
ee
ca
r
d
io
g
r
am
s
p
atter
n
s
,
ea
ch
co
n
s
is
ts
o
f
2
0
s
a
m
p
les
a
s
d
e
m
o
n
s
tr
ated
in
t
h
e
p
r
ev
io
u
s
s
ec
tio
n
[
2
9
]
.
T
h
e
d
u
r
atio
n
o
f
t
h
e
s
i
g
n
als
i
s
2
0
s
ec
o
n
d
s
an
d
th
e
y
ar
e
d
is
to
r
ted
b
y
t
h
e
n
o
is
e
o
f
v
ar
io
u
s
t
y
p
e
s
(
FS
=
2
0
0
Hz)
.
Sen
s
it
iv
it
y
(
Se)
,
th
e
r
es
u
lts
ar
e
ill
u
s
t
r
ated
in
T
ab
le
1
,
is
ca
lcu
lated
u
s
i
n
g
t
h
e
f
o
llo
w
i
n
g
f
o
r
m
u
las:
=
(
1
−
+
)
%
=
+
%
(
5
)
W
h
er
e:
T
P
(
T
r
u
e
P
o
s
itiv
e)
is
th
e
n
u
m
b
er
o
f
Q
R
S
co
m
p
le
x
es
f
o
u
n
d
,
FN
(
Fals
e
Ne
g
ati
v
e)
-
t
h
e
n
u
m
b
er
o
f
in
co
r
r
ec
tl
y
d
ef
in
ed
QR
S
co
m
p
lex
e
s
.
I
f
t
h
er
e
w
a
s
an
er
r
o
r
in
th
e
lo
ca
tio
n
o
f
th
e
s
tr
ik
e
e
v
en
at
o
n
e
s
elec
ted
p
o
in
t,
th
e
FN i
n
cr
ea
s
es.
Evaluation Warning : The document was created with Spire.PDF for Python.
C
o
m
p
u
t.
Sci.
I
n
f
.
T
ec
h
n
o
l.
Les
s
co
mp
u
ta
tio
n
a
l a
p
p
r
o
a
ch
to
d
etec
t Q
R
S
co
mp
lexe
s
in
E
C
G
r
h
yth
ms
(
Ta
r
iq
M.
Yo
u
n
es
)
119
T
ab
le
1
.
Sen
s
itiv
it
y
c
alc
u
lat
io
n
S
a
mp
le
S
e
%
S
i
g
n
a
l
E
C
G
3
.
d
a
t
,
91
S
i
g
n
a
l
E
C
G
4
.
d
a
t
88
S
i
g
n
a
l
E
C
G
5
.
d
a
t
85
T
h
e
r
esu
lts
s
h
o
w
s
at
is
f
ac
to
r
y
d
etec
tio
n
o
f
QR
S
co
m
p
le
x
es
f
o
r
th
e
p
r
o
p
o
s
ed
s
tr
aig
h
t
f
o
r
w
ar
d
alg
o
r
ith
m
th
at
d
o
es
n
o
t
r
eq
u
ir
e
an
y
r
ef
er
en
ce
s
i
g
n
als.
T
h
e
s
e
n
s
i
tiv
it
y
c
an
b
e
i
m
p
r
o
v
ed
u
s
ed
a
co
r
r
ec
tio
n
alg
o
r
it
h
m
an
d
co
m
p
ar
ati
v
e
p
er
io
d
ic
p
r
o
ce
d
u
r
e.
4.
CO
NCLU
SI
O
N
T
h
e
d
ev
elo
p
m
e
n
t
o
f
ad
v
a
n
ce
d
p
r
o
ce
s
s
in
g
s
y
s
te
m
s
h
as
r
es
u
lte
d
in
r
ea
lizin
g
s
p
ec
i
f
ic
co
m
p
le
x
es
in
E
C
G
r
h
y
t
h
m
t
h
at
al
lo
w
s
d
etec
ti
n
g
h
ea
r
t
d
is
ea
s
es.
C
u
r
r
en
tl
y
,
i
n
s
tr
u
m
en
tatio
n
s
ar
e
u
s
ed
to
r
e
co
r
d
C
ar
d
io
g
r
ap
h
s
p
r
o
v
id
in
g
s
i
g
n
al
f
ilter
i
n
g
,
d
ata
an
al
y
s
is
,
an
d
d
iag
n
o
s
is
b
ased
o
n
E
C
G
ti
m
i
n
g
.
I
n
th
is
p
ap
er
,
au
to
m
at
ic
d
etec
tio
n
an
d
r
ec
o
g
n
itio
n
o
f
Q
R
S
co
m
p
l
ex
es
f
o
r
E
C
G
r
h
y
t
h
m
ar
e
p
r
o
p
o
s
ed
.
T
h
e
p
r
esen
ted
alg
o
r
it
h
m
is
s
tr
u
ct
u
r
ed
b
ased
o
n
a
s
er
ies
o
f
f
i
lter
s
th
at
co
m
p
o
s
es
L
P
F,
d
if
f
er
en
ce
a
n
d
s
u
m
m
atio
n
f
ilter
s
.
A
f
ter
w
ar
d
,
a
th
r
es
h
o
ld
f
u
n
ctio
n
i
s
ap
p
lied
to
d
etec
t
QR
S
co
m
p
le
x
es.
T
h
e
al
g
o
r
ith
m
h
as
s
u
cc
es
s
f
u
ll
y
lo
ca
ted
th
e
QR
S
co
m
p
le
x
es.
A
n
ap
p
r
o
x
i
m
ate
d
ef
in
i
tio
n
o
f
b
o
u
n
d
ar
ies
ca
n
b
e
ch
alle
n
g
in
g
w
h
e
n
t
h
ese
b
o
u
n
d
ar
ies
ar
e
d
is
to
r
ted
b
y
h
ig
h
-
f
r
e
q
u
en
c
y
E
MG
n
o
is
e
an
d
b
y
t
h
e
n
o
is
e
f
r
o
m
p
atien
t
m
o
v
e
m
e
n
t.
T
h
is
lead
s
to
th
e
o
m
is
s
io
n
o
f
s
e
v
er
al
b
ea
ts
.
I
n
s
u
ch
ca
s
es,
in
s
tead
o
f
u
s
i
n
g
a
co
n
s
tan
t
th
r
es
h
o
ld
f
u
n
ctio
n
,
it
is
n
ec
ess
ar
y
to
u
s
e
an
ad
ap
tiv
e
th
r
esh
o
ld
f
u
n
ctio
n
,
w
h
ic
h
ca
n
i
m
p
r
o
v
e
th
e
o
p
er
atio
n
o
f
th
e
alg
o
r
it
h
m
u
s
i
n
g
v
ar
iab
le
t
h
r
es
h
o
ld
v
ar
ia
b
les.
T
h
e
r
esu
lt
s
ar
e
f
o
u
n
d
s
at
is
f
ac
to
r
y
f
o
r
s
u
c
h
a
r
o
b
u
s
t d
ir
ec
t a
lg
o
r
ith
m
.
RE
F
E
R
E
NC
E
S
[1
]
J.
A
sp
u
ru
e
t
a
l
.
,
"
S
e
g
m
e
n
tatio
n
o
f
th
e
ECG
S
ig
n
a
l
b
y
M
e
a
n
s
o
f
a
L
in
e
a
r
Re
g
r
e
ss
io
n
A
lg
o
r
it
h
m
"
,
S
e
n
so
rs
,
v
o
l.
1
9
,
n
o
.
4
,
p
.
7
7
5
,
2
0
1
9
.
[2
]
I.
Be
ra
z
a
a
n
d
I.
Ro
m
e
ro
,
"
Co
m
p
a
ra
ti
v
e
stu
d
y
o
f
a
lg
o
rit
h
m
s
f
o
r
ECG
s
e
g
m
e
n
tatio
n
"
,
Bi
o
me
d
ica
l
S
ig
n
a
l
Pr
o
c
e
ss
in
g
a
n
d
Co
n
tro
l
,
v
o
l.
3
4
,
p
p
.
1
6
6
-
1
7
3
,
2
0
1
7
.
[3
]
K.
M
a
e
d
a
,
Y.
No
g
u
c
h
i,
M
.
Utsu
a
n
d
T
.
Na
g
a
ss
a
wa
,
"
A
lg
o
rit
h
m
s
f
o
r
Co
m
p
u
teriz
e
d
F
e
tal
He
a
rt
Ra
te Diag
n
o
sis w
it
h
Dire
c
t
Re
p
o
rti
n
g
"
,
Al
g
o
rit
h
ms
,
v
o
l.
8
,
n
o
.
3
,
p
p
.
3
9
5
-
4
0
6
,
2
0
1
5
.
[4
]
G
.
M
a
g
e
n
e
s,
M
.
G
.
S
ig
n
o
rin
i
a
n
d
R.
S
a
ss
i,
"
A
u
to
m
a
ti
c
d
iag
n
o
sis
o
f
f
e
tal
h
e
a
rt
ra
te:
c
o
m
p
a
ris
o
n
o
f
d
if
f
e
re
n
t
m
e
th
o
d
o
lo
g
ica
l
a
p
p
ro
a
c
h
e
s,"
20
0
1
Co
n
fer
e
n
c
e
Pro
c
e
e
d
i
n
g
s
o
f
th
e
2
3
rd
An
n
u
a
l
I
n
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
f
th
e
IEE
E
En
g
i
n
e
e
rin
g
in
M
e
d
icin
e
a
n
d
Bi
o
lo
g
y
S
o
c
iety
,
Ista
n
b
u
l,
T
u
rk
e
y
,
2
0
0
1
,
p
p
.
1
6
0
4
-
1
6
0
7
v
o
l
.
2
,
d
o
i:
1
0
.
1
1
0
9
/I
EM
BS
.
2
0
0
1
.
1
0
2
0
5
1
9
.
[5
]
E.
F
ra
n
k
,
"
A
n
e
q
u
iv
a
len
t
c
ircu
it
f
o
r
t
h
e
h
u
m
a
n
h
e
a
rt
-
b
o
d
y
e
lec
tri
c
a
l
sy
ste
m
"
,
Ame
ric
a
n
He
a
rt
J
o
u
r
n
a
l
,
v
o
l.
4
8
,
n
o
.
5
,
p
p
.
7
3
8
-
7
4
5
,
1
9
5
4
.
[6
]
L
.
M
o
n
teiro
,
F
.
V
a
sq
u
e
s
-
Nó
v
o
a
,
L
.
F
e
rre
ira,
P
.
P
in
t
o
-
do
-
Ó
a
n
d
D.
Na
sc
i
m
e
n
to
,
"
Re
sto
rin
g
h
e
a
rt
f
u
n
c
ti
o
n
a
n
d
e
lec
tri
c
a
l
in
teg
rit
y
:
c
lo
sin
g
th
e
c
ir
c
u
it
"
,
n
p
j
Re
g
e
n
e
ra
ti
v
e
M
e
d
icin
e
,
v
o
l.
2
,
n
o
.
9
,
p
p
.
1
-
13
,
2
0
1
7
.
[7
]
J.
A
lu
n
a
n
d
B
.
M
u
r
p
h
y
,
"
L
o
n
e
li
n
e
ss
,
so
c
ial
iso
lati
o
n
a
n
d
c
a
rd
i
o
v
a
sc
u
lar
risk
"
,
Brit
ish
J
o
u
r
n
a
l
o
f
C
a
rd
ia
c
Nu
rs
in
g
,
v
o
l.
1
4
,
n
o
.
1
0
,
p
p
.
1
-
8
,
2
0
1
9
.
[8
]
A
.
W
in
terto
n
,
L
.
R
ø
d
e
v
a
n
d
,
L
.
W
e
stl
y
e
,
N.
S
tee
n
,
O.
A
n
d
re
a
ss
e
n
a
n
d
D.
Q
u
in
ta
n
a
,
A
ss
o
c
iatio
n
s
o
f
L
o
n
e
li
n
e
ss
a
n
d
S
o
c
ial
Iso
lati
o
n
w
it
h
Ca
rd
io
v
a
sc
u
lar an
d
M
e
tab
o
li
c
He
a
lt
h
:
a
S
y
ste
m
a
ti
c
Re
v
ie
w
a
n
d
M
e
ta
-
a
n
a
ly
sis
p
ro
t
o
c
o
l,
2
0
1
9
.
[9
]
S
.
S
a
ra
sw
a
t,
G
.
S
riv
a
sta
v
a
a
n
d
S
.
S
h
u
k
la,
"
Re
v
i
e
w
:
Co
m
p
a
riso
n
o
f
QRS
d
e
tec
ti
o
n
a
lg
o
rit
h
m
s,"
In
ter
n
a
t
io
n
a
l
Co
n
fer
e
n
c
e
o
n
Co
m
p
u
t
in
g
,
C
o
mm
u
n
ica
ti
o
n
&
Au
to
ma
ti
o
n
,
G
re
a
ter
No
id
a
,
I
n
d
ia,
2
0
1
5
,
p
p
.
3
5
4
-
3
5
9
,
d
o
i
:
1
0
.
1
1
0
9
/CCA
A
.
2
0
1
5
.
7
1
4
8
4
4
3
.
[1
0
]
M
.
A
.
Be
lk
a
d
i
a
n
d
A
.
Da
a
m
o
u
c
h
e
,
"
A
n
i
m
p
ro
v
e
d
QRS
d
e
tec
ti
o
n
m
e
th
o
d
u
sin
g
Hi
d
d
e
n
M
a
rk
o
v
M
o
d
e
ls,"
2
0
1
7
6
th
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
S
y
ste
ms
a
n
d
C
o
n
tro
l
(
ICS
C)
,
Ba
tn
a
,
2
0
1
7
,
p
p
.
8
1
-
8
4
,
d
o
i:
1
0
.
1
1
0
9
/IC
o
S
C.
2
0
1
7
.
7
9
5
8
6
9
6
.
[1
1
]
S
.
S
o
tel
o
,
W
.
A
re
n
a
s
a
n
d
M
.
A
lt
u
v
e
,
"
QRS
c
o
m
p
lex
d
e
tec
ti
o
n
b
a
se
d
o
n
c
o
n
ti
n
u
o
u
s
d
e
n
sity
h
id
d
e
n
M
a
rk
o
v
m
o
d
e
ls
u
sin
g
u
n
iv
a
riate
o
b
se
rv
a
ti
o
n
s"
,
J
o
u
rn
a
l
o
f
Ph
y
sic
s: Co
n
fer
e
n
c
e
S
e
rie
s,
v
o
l.
1
0
0
2
,
p
.
0
1
2
0
0
9
,
2
0
1
8
.
[1
2
]
N.
M
.
A
rz
e
n
o
,
Z.
-
D.
De
n
g
a
n
d
C.
-
S
.
P
o
o
n
,
"
A
n
a
l
y
sis
o
f
F
irst
-
De
riv
a
ti
v
e
Ba
se
d
QRS
D
e
tec
ti
o
n
A
l
g
o
rit
h
m
s,"
in
IEE
E
T
r
a
n
sa
c
ti
o
n
s
o
n
Bi
o
m
e
d
ica
l
En
g
in
e
e
rin
g
,
v
o
l.
5
5
,
n
o
.
2
,
p
p
.
4
7
8
-
4
8
4
,
F
e
b
.
2
0
0
8
,
d
o
i
:
1
0
.
1
1
0
9
/T
BM
E.
2
0
0
7
.
9
1
2
6
5
8
.
[1
3
]
G
.
M
.
F
ries
e
n
,
T
.
C.
Ja
n
n
e
tt
,
M
.
A
.
Ja
d
a
ll
a
h
,
S
.
L
.
Ya
tes
,
S
.
R.
Qu
in
t
a
n
d
H
.
T
.
Na
g
le,
"
A
c
o
m
p
a
ris
o
n
o
f
th
e
n
o
ise
se
n
siti
v
it
y
o
f
n
in
e
QRS
d
e
tec
ti
o
n
a
lg
o
rit
h
m
s,"
in
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
Bio
m
e
d
ica
l
En
g
in
e
e
rin
g
,
v
o
l
.
3
7
,
n
o
.
1
,
p
p
.
85
-
9
8
,
Ja
n
.
1
9
9
0
,
d
o
i:
1
0
.
1
1
0
9
/
1
0
.
4
3
6
2
0
.
[1
4
]
P
.
S
.
Ha
m
il
to
n
a
n
d
W
.
J.
T
o
m
p
k
in
s,
"
Co
m
p
re
ss
io
n
o
f
th
e
a
m
b
u
lato
ry
EC
G
b
y
a
v
e
ra
g
e
b
e
a
t
su
b
trac
ti
o
n
a
n
d
re
si
d
u
a
l
d
if
fe
re
n
c
in
g
,
"
in
I
EE
E
T
ra
n
sa
c
ti
o
n
s
o
n
Bi
o
m
e
d
ica
l
En
g
in
e
e
rin
g
,
v
o
l.
3
8
,
n
o
.
3
,
p
p
.
2
5
3
-
2
5
9
,
M
a
rc
h
1
9
9
1
,
d
o
i
:
1
0
.
1
1
0
9
/
1
0
.
1
3
3
2
0
6
.
[1
5
]
F
.
Zh
a
n
g
a
n
d
Y.
L
ian
,
"
QRS
De
te
c
ti
o
n
Ba
se
d
o
n
M
u
lt
isc
a
le M
a
th
e
m
a
ti
c
a
l
M
o
rp
h
o
lo
g
y
f
o
r
W
e
a
r
a
b
le E
C
G
De
v
ice
s
in
B
o
d
y
A
re
a
Ne
t
w
o
rk
s,"
in
IEE
E
T
ra
n
sa
c
t
io
n
s
o
n
Bi
o
me
d
ica
l
Circ
u
it
s
a
n
d
S
y
ste
ms
,
v
o
l.
3
,
n
o
.
4
,
p
p
.
2
2
0
-
2
2
8
,
A
u
g
.
2
0
0
9
,
d
o
i:
1
0
.
1
1
0
9
/T
BCA
S
.
2
0
0
9
.
2
0
2
0
0
9
3
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2722
-
3221
C
o
m
p
u
t.
Sci.
I
n
f
.
T
ec
h
n
o
l.
,
Vo
l.
2
,
No
.
3
,
No
v
em
b
er
20
2
1
:
1
13
–
1
20
120
[1
6
]
M
.
El
g
e
n
d
i,
"
F
a
st
QRS
De
tec
ti
o
n
w
it
h
a
n
Op
ti
m
iz
e
d
Kn
o
w
led
g
e
-
Ba
se
d
M
e
th
o
d
:
Ev
a
lu
a
ti
o
n
o
n
1
1
S
tan
d
a
rd
ECG
Da
tab
a
se
s
"
,
PL
o
S
ONE
,
v
o
l.
8
,
n
o
.
9
,
p
.
e
7
3
5
5
7
,
2
0
1
3
.
[1
7
]
F
.
L
iu
e
t
a
l.
,
"
P
e
rf
o
rm
a
n
c
e
A
n
a
l
y
sis
o
f
T
e
n
Co
m
m
o
n
QRS
De
tec
to
rs
o
n
Dif
f
e
re
n
t
ECG
A
p
p
li
c
a
ti
o
n
Ca
se
s
"
,
J
o
u
rn
a
l
o
f
He
a
lt
h
c
a
re
En
g
i
n
e
e
rin
g
,
v
o
l.
2
0
1
8
,
p
p
.
1
-
8
,
2
0
1
8
.
[1
8
]
M
.
El
g
e
n
d
i,
B.
Esk
o
f
ier,
S
.
Do
k
o
s
a
n
d
D.
A
b
b
o
tt
,
"
Re
v
isit
in
g
QRS
De
tec
ti
o
n
M
e
th
o
d
o
lo
g
ies
f
o
r
P
o
r
t
a
b
le,
W
e
a
ra
b
le,
Ba
tt
e
r
y
-
Op
e
ra
ted
,
a
n
d
W
irele
ss
ECG
S
y
ste
m
s
"
,
PL
o
S
ONE
,
v
o
l.
9
,
n
o
.
1
,
p
.
e
8
4
0
1
8
,
2
0
1
4
.
[1
9
]
T
.
S
h
a
rm
a
a
n
d
K.
S
h
a
rm
a
,
"
A
n
e
w
m
e
th
o
d
f
o
r
QRS
d
e
tec
ti
o
n
in
ECG
sig
n
a
ls
u
sin
g
QRS
-
p
re
s
e
rv
in
g
f
il
terin
g
tec
h
n
iq
u
e
s
"
,
B
io
me
d
ica
l
E
n
g
i
n
e
e
rin
g
/
Bi
o
me
d
izin
isc
h
e
T
e
c
h
n
ik,
v
o
l.
6
3
,
n
o
.
2
,
p
p
.
2
0
7
-
2
1
7
,
2
0
1
8
.
[2
0
]
S
.
Bil
g
i
n
a
n
d
Z.
A
k
in
,
“
A
Ne
w
Ro
b
u
st
QRS
De
tec
ti
o
n
A
lg
o
rit
h
m
in
A
rrh
y
th
m
ic
ECG
S
ig
n
a
ls”
,
J
E
n
g
S
c
i
De
sig
n
,
v
o
l.
6
,
n
o
.
1
,
p
p
.
6
4
-
7
3
,
2
0
1
8
.
[2
1
]
O.
Kw
o
n
e
t
a
l.
,
"
El
e
c
tro
c
a
rd
io
g
r
a
m
S
a
m
p
li
n
g
F
re
q
u
e
n
c
y
Ra
n
g
e
A
c
c
e
p
tab
le
f
o
r
He
a
rt
Ra
te
V
a
ria
b
il
it
y
A
n
a
l
y
sis"
,
He
a
lt
h
c
a
re
In
fo
rm
a
ti
c
s R
e
se
a
rc
h
,
v
o
l.
2
4
,
n
o
.
3
,
p
.
1
9
8
,
2
0
1
8
.
[2
2
]
M
.
M
e
rri,
D.
C.
F
a
rd
e
n
,
J.
G
.
M
o
tt
le
y
a
n
d
E.
L
.
T
it
leb
a
u
m
,
"
S
a
m
p
li
n
g
f
r
e
q
u
e
n
c
y
o
f
th
e
e
lec
tro
c
a
rd
io
g
ra
m
f
o
r
sp
e
c
tral
a
n
a
ly
sis
o
f
th
e
h
e
a
rt
ra
te
v
a
riab
il
it
y
,
"
in
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
Bi
o
me
d
ica
l
En
g
in
e
e
rin
g
,
v
o
l.
3
7
,
n
o
.
1
,
p
p
.
9
9
-
1
0
6
,
Ja
n
.
1
9
9
0
,
d
o
i:
1
0
.
1
1
0
9
/1
0
.
4
3
6
2
1
.
[2
3
]
K.
Ra
h
u
l,
“
S
ig
n
a
l
P
r
o
c
e
ss
in
g
T
e
c
h
n
i
q
u
e
s
f
o
r
Re
m
o
v
in
g
No
ise
f
ro
m
EC
G
S
ig
n
a
ls”
,
J
Bi
o
me
d
En
g
.
,
v
o
l.
3
.
n
o
.
1
,
p
p
.
1
-
9
,
2
0
1
9
.
[2
4
]
M
.
Ka
b
ir
a
n
d
C.
S
h
a
h
n
a
z
,
"
De
n
o
isin
g
o
f
ECG
sig
n
a
ls
b
a
se
d
o
n
n
o
ise
re
d
u
c
ti
o
n
a
lg
o
ri
th
m
s
in
E
M
D
a
n
d
w
a
v
e
l
e
t
d
o
m
a
in
s"
,
Bi
o
me
d
ica
l
S
i
g
n
a
l
Pro
c
e
ss
in
g
a
n
d
C
o
n
tr
o
l
,
v
o
l
.
7
,
n
o
.
5
,
p
p
.
4
8
1
-
4
8
9
,
2
0
1
2
.
[2
5
]
N.
Da
s a
n
d
M
.
C
h
a
k
ra
b
o
rty
,
"
P
e
r
f
o
r
m
a
n
c
e
a
n
a
l
y
sis o
f
F
IR
a
n
d
IIR
f
il
ters
f
o
r
ECG
sig
n
a
l
d
e
n
o
isi
n
g
b
a
se
d
o
n
S
NR"
,
2
0
1
7
T
h
ir
d
I
n
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Res
e
a
rc
h
i
n
C
o
mp
u
ta
ti
o
n
a
l
In
tell
ig
e
n
c
e
a
n
d
C
o
mm
u
n
ic
a
ti
o
n
Ne
two
rk
s
(
ICRCICN)
,
2
0
1
7
.
[2
6
]
S
.
Bh
o
g
e
sh
w
a
r,
M
.
S
o
n
i
a
n
d
D.
Ba
n
sa
l,
"
T
o
v
e
ri
fy
a
n
d
c
o
m
p
a
re
d
e
n
o
isi
n
g
o
f
ECG
sig
n
a
l
u
sin
g
v
a
rio
u
s
d
e
n
o
isin
g
a
lg
o
rit
h
m
s o
f
IIR
a
n
d
F
IR
f
il
ters
"
,
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
Bi
o
me
d
ica
l
En
g
in
e
e
rin
g
a
n
d
T
e
c
h
n
o
lo
g
y
,
v
o
l.
1
6
,
n
o
.
3
,
p
.
2
4
4
,
2
0
1
4
.
[2
7
]
S
.
L
e
e
,
Y.
Je
o
n
g
,
D.
P
a
rk
,
B.
Yu
n
a
n
d
K.
P
a
rk
,
"
Ef
f
icie
n
t
F
id
u
c
ial
P
o
in
t
De
tec
ti
o
n
o
f
ECG
QRS
Co
m
p
lex
Ba
se
d
o
n
P
o
ly
g
o
n
a
l
A
p
p
ro
x
ima
ti
o
n
"
,
S
e
n
s
o
rs
,
v
o
l.
1
8
,
n
o
.
1
2
,
p
.
4
5
0
2
,
2
0
1
8
.
[2
8
]
M
.
A
k
h
b
a
ri,
M
.
S
h
a
m
so
ll
a
h
i
a
n
d
C.
Ju
tt
e
n
,
"
Co
m
p
a
riso
n
o
f
ECG
f
i
d
u
c
ial
p
o
in
t
e
x
trac
ti
o
n
m
e
th
o
d
s
b
a
s
e
d
o
n
d
y
n
a
m
i
c
Ba
y
e
sia
n
n
e
tw
o
rk
"
,
2
0
1
7
Ira
n
ia
n
Co
n
fer
e
n
c
e
o
n
El
e
c
trica
l
E
n
g
in
e
e
rin
g
(
ICEE
)
,
2
0
1
7
.
[2
9
]
M
.
S
y
b
u
rra
,
N.
G
u
e
tt
ler,
J.
D’A
rc
y
a
n
d
E.
Nic
o
l,
"
Cli
n
ica
l
o
c
c
u
p
a
ti
o
n
a
l
a
ss
e
ss
m
e
n
t
p
re
-
a
n
d
p
o
st
-
c
a
rd
iac
su
rg
e
ry
"
,
Eu
ro
p
e
a
n
He
a
rt
J
o
u
r
n
a
l
,
v
o
l.
4
0
,
n
o
.
4
0
,
p
p
.
3
2
8
3
-
3
2
8
6
,
2
0
1
9
.
Evaluation Warning : The document was created with Spire.PDF for Python.