I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
p
u
t
er
Science
Vo
l.
22
,
No
.
3
,
J
u
n
e
2
0
2
1
,
p
p
.
1520
~
1
5
2
8
I
SS
N:
2
5
02
-
4
7
5
2
,
DOI
: 1
0
.
1
1
5
9
1
/i
j
ee
cs.v
2
2
.i
3
.
pp
1
5
2
0
-
1
5
2
8
1520
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs.ia
esco
r
e.
co
m
Cla
ss
ificatio
n of
ECG
sig
na
ls for
d
etec
tion
of arrhy
t
h
m
ia
and
co
ng
estiv
e heart
f
a
ilure bas
ed on
c
o
ntinuou
s w
a
v
elet
trans
for
m
a
nd deep
neura
l
netw
o
rk
s
Ra
s
hid
a
h F
u
n
k
e
O
la
nrew
a
j
u,
S.
No
o
rj
a
nn
a
h Ib
ra
hi
m
,
Ani L
iza
As
na
w
i,
H
un
a
in Alt
a
f
Dep
ar
t
m
en
t o
f
E
lectr
ical
an
d
C
o
m
p
u
ter
E
n
g
in
ee
r
i
n
g
,
I
n
ter
n
atio
n
al
I
s
la
m
ic
U
n
iv
er
s
it
y
Ma
l
a
y
s
ia,
Ma
la
y
s
ia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Oct
1
6
,
2
0
2
0
R
ev
i
s
ed
J
u
n
6
,
2
0
2
1
A
cc
ep
ted
J
u
n
1
0
,
202
1
A
c
c
o
rd
in
g
to
W
o
rld
He
a
lt
h
Org
a
n
iza
ti
o
n
(
W
HO
)
re
p
o
r
t
a
n
e
sti
m
a
ted
1
7
.
9
m
il
li
o
n
li
v
e
s
a
re
b
e
in
g
lo
st
e
a
c
h
y
e
a
r
d
u
e
to
c
a
rd
io
v
a
sc
u
lar
d
ise
a
se
s
(CV
Ds
)
a
n
d
is
th
e
to
p
c
o
n
tri
b
u
t
o
r
to
t
h
e
d
e
a
th
c
a
u
se
s.
8
0
%
o
f
th
e
c
a
r
d
io
v
a
sc
u
lar
c
a
se
s
in
c
lu
d
e
h
e
a
rt
a
tt
a
c
k
s
a
n
d
stro
k
e
s.
T
h
is
w
o
rk
is
a
n
e
ff
o
rt
to
a
c
c
u
ra
tel
y
p
re
d
ict
th
e
c
o
m
m
o
n
h
e
a
rt
d
ise
a
se
s
su
c
h
a
s
a
rrh
y
th
m
ia
(
A
RR)
a
n
d
c
o
n
g
e
stiv
e
h
e
a
rt
f
a
il
u
re
(CHF)
a
lo
n
g
w
it
h
t
h
e
n
o
rm
a
l
sin
u
s
rh
y
th
m
(NSR)
b
a
se
d
o
n
t
h
e
in
teg
ra
ted
m
o
d
e
l
d
e
v
e
lo
p
e
d
u
sin
g
c
o
n
ti
n
u
o
u
s
w
a
v
e
let
tran
sf
o
r
m
(CWT
)
a
n
d
d
e
e
p
n
e
u
ra
l
n
e
tw
o
rk
s
.
T
h
e
p
ro
p
o
se
d
m
e
th
o
d
u
se
d
in
t
h
is
re
se
a
rc
h
a
n
a
ly
se
s
th
e
ti
m
e
-
f
re
q
u
e
n
c
y
fe
a
tu
re
s
o
f
a
n
e
lec
tro
c
a
rd
i
o
g
ra
m
(
EC
G
)
sig
n
a
l
b
y
f
irst
c
o
n
v
e
rti
n
g
th
e
1
D
ECG
sig
n
a
ls
to
t
h
e
2
D
S
c
a
lo
g
ra
m
i
m
a
g
e
s
a
n
d
su
b
se
q
u
e
n
tl
y
th
e
2
D
im
a
g
e
s
a
re
b
e
in
g
u
se
d
a
s
a
n
i
n
p
u
t
t
o
t
h
e
2
D
d
e
e
p
n
e
u
ra
l
n
e
tw
o
rk
m
o
d
e
l
-
A
lex
Ne
t.
T
h
e
re
a
so
n
b
e
h
i
n
d
c
o
n
v
e
rti
n
g
th
e
ECG
sig
n
a
ls
t
o
2
D
im
a
g
e
s
is
th
a
t
it
is
e
a
sie
r
to
e
x
trac
t
d
e
e
p
fe
a
tu
re
s
f
ro
m
i
m
a
g
e
s
ra
th
e
r
th
a
n
f
ro
m
th
e
ra
w
d
a
ta
f
o
r
train
in
g
p
u
rp
o
se
s
in
A
lex
Ne
t.
T
h
e
d
a
tas
e
t
u
se
d
f
o
r
th
is
re
se
a
rc
h
w
a
s
o
b
tain
e
d
f
ro
m
M
a
s
sa
c
h
u
s
e
tt
s
In
stit
u
te
o
f
T
e
c
h
n
o
lo
g
y
-
Bo
sto
n
'
s
Be
th
Isra
e
l
Ho
s
p
it
a
l
(
M
IT
-
BIH
)
a
rrh
y
th
m
ia
d
a
tab
a
se
,
M
IT
-
BIH
n
o
rm
a
l
sin
u
s
rh
y
th
m
d
a
tab
a
se
a
n
d
Be
th
Isr
a
e
l
De
a
c
o
n
e
ss
M
e
d
ica
l
Ce
n
ter
(
BIDMC
)
c
o
n
g
e
stiv
e
h
e
a
rt
f
a
il
u
re
d
a
tab
a
se
.
In
t
h
is
w
o
rk
,
w
e
h
a
v
e
id
e
n
ti
f
ied
th
e
b
e
st
f
it
p
a
ra
m
e
ters
f
o
r
th
e
A
lex
Ne
t
m
o
d
e
l
th
a
t
c
o
u
l
d
s
u
c
c
e
ss
f
u
ll
y
p
re
d
ict
th
e
c
o
m
m
o
n
h
e
a
rt
d
ise
a
se
s
w
it
h
a
n
a
c
c
u
ra
c
y
o
f
9
8
.
7
%
.
T
h
is
w
o
rk
is
a
lso
b
e
i
n
g
c
o
m
p
a
re
d
w
it
h
th
e
re
c
e
n
t
re
se
a
rc
h
d
o
n
e
i
n
t
h
e
f
ield
o
f
ECG
Clas
sif
ica
ti
o
n
f
o
r
d
e
tec
ti
o
n
o
f
h
e
a
rt
c
o
n
d
i
ti
o
n
s
a
n
d
p
ro
v
e
s
to
b
e
a
n
e
ffe
c
ti
v
e
tec
h
n
iq
u
e
f
o
r
th
e
c
las
si
f
ica
ti
o
n
.
K
ey
w
o
r
d
s
:
C
o
n
v
o
lu
tio
n
Dee
p
lear
n
in
g
Neu
r
al
n
et
w
o
r
k
s
W
av
elet
tr
an
s
f
o
r
m
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
:
Sit
i N
o
o
r
j
an
n
ah
I
b
r
ah
i
m
Dep
ar
t
m
en
t o
f
E
lectr
ical
an
d
C
o
m
p
u
ter
E
n
g
in
ee
r
i
n
g
I
n
ter
n
atio
n
al
I
s
la
m
ic
U
n
iv
er
s
it
y
Ma
la
y
s
ia
J
alan
Go
m
b
ak
,
5
3
1
0
0
,
Selan
g
o
r
,
Ma
lay
s
ia
E
m
ail:
n
o
o
r
j
an
n
ah
@
ii
u
m
.
ed
u
.
m
y
1.
I
NT
RO
D
UCT
I
O
N
An
elec
tr
o
ca
r
d
io
g
r
a
m
also
k
n
o
w
n
as
elec
tr
o
ca
r
d
io
g
r
a
m
(
E
C
G
)
is
a
test
t
h
at
m
ea
s
u
r
es
t
h
e
elec
tr
ical
ac
tiv
it
y
o
f
t
h
e
h
ea
r
tb
ea
t.
W
ith
ea
ch
b
ea
t,
an
elec
tr
ical
i
m
p
u
l
s
e
tr
av
el
t
h
r
o
u
g
h
t
h
e
h
ea
r
t.
T
h
is
w
av
e
ca
u
s
e
s
th
e
m
u
s
cle
to
s
q
u
ee
ze
an
d
r
ela
x
a
n
d
h
e
n
ce
p
u
m
p
i
n
g
b
lo
o
d
f
r
o
m
th
e
h
ea
r
t
to
th
e
w
h
o
le
b
o
d
y
.
A
n
o
r
m
a
l
h
ea
r
tb
ea
t
o
n
E
C
G
as
s
h
o
w
n
i
n
Fi
g
u
r
e
1
w
il
l s
h
o
w
th
e
t
i
m
in
g
o
f
t
h
e
to
p
an
d
lo
w
er
ch
a
m
b
er
s
.
T
h
er
e
is
a
“
P
w
av
e”
w
h
ic
h
y
ield
s
f
r
o
m
a
r
ig
h
t
an
d
lef
t
a
tr
ia
o
r
u
p
p
er
ch
a
m
b
er
s
.
T
h
en
it
is
f
o
llo
w
ed
b
y
a
f
lat
li
n
e
w
h
e
n
th
e
elec
tr
ica
l
i
m
p
u
l
s
e
g
o
es
to
t
h
e
b
o
tto
m
o
f
ch
a
m
b
er
s
.
T
h
e
“
Q
R
S
co
m
p
le
x
”
is
t
h
e
n
e
x
t
w
a
v
e
th
at
i
s
p
r
o
d
u
ce
d
b
y
r
ig
h
t
a
n
d
lef
t
b
o
tto
m
ch
a
m
b
er
s
.
T
h
e
f
in
al
w
a
v
e
o
r
“
T
w
a
v
e”
r
ep
r
ese
n
ts
e
lectr
ical
r
ec
o
v
er
y
o
r
r
etu
r
n
to
a
r
esti
n
g
s
tate
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
C
la
s
s
i
fica
tio
n
o
f E
C
G
s
ig
n
a
ls
fo
r
d
etec
tio
n
o
f
a
r
r
h
yth
mia
a
n
d
co
n
g
esti
ve
…
(
R
a
s
h
id
a
h
F
u
n
ke
Ola
n
r
ewa
ju
)
1521
f
o
r
th
e
v
en
tr
ic
les.
E
C
G
s
er
v
es
as
th
e
b
asic
an
d
ea
s
y
to
i
m
p
le
m
en
t
m
et
h
o
d
f
o
r
th
e
d
i
ag
n
o
s
is
o
f
ca
r
d
iac
m
al
f
u
n
ctio
n
i
n
g
(
o
r
h
ea
r
t
r
h
y
t
h
m
d
is
o
r
d
er
s
)
.
T
h
is
is
d
u
e
to
its
n
o
n
-
in
v
as
iv
e
a
n
d
s
i
m
p
le
tec
h
n
iq
u
e
o
f
r
ec
o
r
d
in
g
th
e
s
i
g
n
als
w
h
il
s
t p
r
o
v
id
in
g
v
i
tal
in
f
o
r
m
atio
n
o
n
h
ea
r
t c
o
n
d
it
io
n
s
.
A
r
o
u
n
d
1
7
.
3
m
illi
o
n
p
eo
p
le
d
ie
ea
ch
y
ea
r
g
lo
b
all
y
d
u
e
to
c
ar
d
iac
d
is
e
ases
w
h
ic
h
ac
co
u
n
t
s
f
o
r
o
v
er
37
%
o
f
th
e
to
tal
w
o
r
ld
d
ea
th
s
[
1
]
an
d
it
h
as
also
b
ee
n
p
r
ed
icted
th
at
ab
o
u
t
2
3
.
6
m
illi
o
n
m
i
g
h
t
d
ie
d
u
e
to
h
ea
r
t
d
is
ea
s
es
a
n
d
f
ail
u
r
es
[
2
]
.
T
h
e
ad
v
an
ce
m
e
n
ts
in
d
ata
m
in
i
n
g
an
d
clo
u
d
co
m
p
u
t
in
g
allo
w
h
u
g
e
a
m
o
u
n
ts
o
f
m
ed
ical
d
ata
to
b
e
ex
te
n
s
i
v
el
y
an
al
y
ze
d
w
i
th
o
u
t
co
m
p
r
o
m
i
s
i
n
g
th
e
p
r
ec
is
io
n
o
f
it
s
r
es
u
lt
s
.
T
h
is
is
co
n
s
id
er
ed
as
a
m
o
ti
v
atio
n
to
co
n
d
u
ct
a
d
ata
d
r
iv
en
r
esear
ch
to
p
r
e
d
ict,
d
eter
m
i
n
e
an
d
d
etec
t
th
e
d
is
ea
s
es
at
an
ea
r
l
y
s
tag
e.
L
i
k
e
w
is
e,
E
C
G
s
i
g
n
al
s
g
en
er
ate
h
u
g
e
ch
u
n
k
s
o
f
d
ata
th
at
h
a
s
b
ee
n
u
s
ed
b
y
r
es
e
ar
ch
er
s
to
d
ev
elo
p
p
r
ed
ictio
n
m
o
d
els b
ased
o
n
m
ac
h
in
e
lear
n
i
n
g
a
n
d
co
n
v
o
l
u
ti
o
n
al
n
e
u
r
al
n
et
w
o
r
k
s
[
3
]
.
Fig
u
r
e
1
.
E
lectr
o
ca
r
d
io
g
r
ap
h
y
w
a
v
e
[
4
]
Hea
lth
ca
r
e
r
esear
ch
h
a
s
al
w
a
y
s
ai
m
ed
to
id
en
tify
th
e
tec
h
n
i
q
u
es
to
r
ed
u
ce
th
e
m
o
r
talit
y
r
ates
in
o
n
e
f
o
r
m
o
r
an
o
th
er
.
A
p
p
r
o
p
r
iate
d
ata
m
i
n
i
n
g
an
d
m
ac
h
i
n
e
le
ar
n
in
g
al
g
o
r
ith
m
s
h
av
e
p
la
y
e
d
a
p
iv
o
tal
r
o
le
in
d
ev
elo
p
in
g
t
h
e
h
ig
h
l
y
ef
f
ic
ien
t p
r
ed
ictio
n
m
o
d
els f
o
r
d
etec
ti
o
n
o
f
d
is
ea
s
e
a
n
d
o
n
e
a
m
o
n
g
t
h
o
s
e
d
is
ea
s
e
s
is
t
h
e
h
ea
r
t
d
is
ea
s
e
[
2
]
.
I
n
r
etr
o
s
p
ec
t,
th
er
e
ar
e
m
a
n
y
t
y
p
es
o
f
h
ea
r
t
d
is
ea
s
e
s
a
n
d
t
h
e
m
o
s
t
co
m
m
o
n
o
f
h
ea
r
t
co
n
d
itio
n
s
ar
e
a
r
r
h
y
t
h
m
ia
(
AR
R
)
a
n
d
co
n
g
esti
v
e
h
ea
r
t
f
ail
u
r
e
(
C
H
F)
[
5
]
.
W
h
at
d
if
f
er
en
tiates
b
et
w
ee
n
o
n
e
h
ea
r
t
d
is
o
r
d
er
s
f
r
o
m
an
o
t
h
er
is
th
e
elec
tr
ical
ac
tiv
itie
s
w
h
ich
r
ef
lect
in
its
E
C
G
s
ig
n
a
ls
.
A
no
r
m
a
l
s
in
u
s
r
h
y
t
h
m
(
NS
R
)
r
ep
r
esen
ts
a
p
r
o
p
er
tr
an
s
m
is
s
io
n
o
f
elec
tr
ical
s
ig
n
als
f
r
o
m
o
n
e
’
s
s
i
n
u
s
n
o
d
es
an
d
is
an
in
d
icatio
n
o
f
a
n
o
r
m
al
h
ea
r
t [
5
]
.
T
h
is
r
esear
ch
m
ak
e
s
u
s
e
o
f
th
e
NSR
,
AR
R
,
an
d
C
H
F
E
C
G
d
ata
f
r
o
m
t
h
e
v
er
if
ied
d
atab
ases
in
o
r
d
er
to
b
u
ild
a
p
r
e
d
ictio
n
m
o
d
el
b
ased
o
n
co
n
v
o
lu
tio
n
al
n
eu
r
al
n
et
w
o
r
k
s
.
T
h
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
w
o
u
ld
b
e
ab
le
to
d
eter
m
i
n
e
w
h
et
h
er
a
p
er
s
o
n
h
as
an
y
o
f
th
e
m
e
n
tio
n
ed
d
is
o
r
d
er
s
o
r
p
o
s
s
ess
e
s
a
h
e
alth
y
h
ea
r
t
r
h
y
th
m
.
A
cc
u
r
ate
d
iag
n
o
s
i
s
an
d
p
r
ed
ictio
n
o
f
a
n
y
d
i
s
ea
s
e
i
s
an
ex
ten
s
i
v
e
an
d
c
h
alle
n
g
i
n
g
ta
s
k
a
n
d
n
ee
d
s
m
o
r
e
ac
cu
r
ate
class
if
ica
tio
n
.
A
l
g
o
r
ith
m
s
d
o
ex
i
s
t
f
o
r
E
C
G
b
ased
au
to
m
a
tic
ca
r
d
iac
d
is
o
r
d
er
d
etec
tio
n
w
h
ic
h
m
ai
n
l
y
r
el
y
o
n
th
e
m
o
r
p
h
o
lo
g
ical
f
ea
t
u
r
es
o
f
QR
S
co
m
p
le
x
es
o
r
h
ea
r
tb
ea
ts
.
B
u
t
th
e
an
al
y
s
is
o
f
QR
S
co
m
p
lex
es
is
m
o
r
e
p
o
p
u
lar
in
t
h
e
s
cie
n
ti
f
ic
liter
at
u
r
e
th
a
n
th
e
E
C
G
s
ig
n
al
f
r
ag
m
e
n
ts
o
f
lo
n
g
d
u
r
atio
n
s
[
6
]
.
T
h
e
p
r
o
b
lem
w
it
h
s
u
c
h
m
et
h
o
d
s
ar
is
es
d
u
e
to
th
e
v
a
r
ied
b
ea
t
-
to
-
b
ea
t
v
ar
iab
ilit
y
a
m
o
n
g
i
n
d
iv
id
u
als
a
n
d
th
i
s
p
r
o
m
p
ted
u
s
to
lo
o
k
b
ey
o
n
d
th
e
s
e
m
o
r
p
h
o
lo
g
ical
f
ea
tu
r
es
a
n
d
p
er
f
o
r
m
t
h
at
a
n
al
y
s
i
s
o
f
lo
n
g
d
u
r
atio
n
E
C
G
s
i
g
n
als
w
it
h
m
o
r
e
d
ata
an
d
f
ea
t
u
r
es u
s
i
n
g
d
ee
p
n
e
u
r
al
n
et
w
o
r
k
s
.
Dee
p
l
ea
r
n
in
g
,
a
t
y
p
e
o
f
m
ac
h
in
e
lear
n
in
g
m
e
th
o
d
,
co
m
p
r
i
s
es
a
h
ier
ar
ch
ica
l
ar
ch
it
ec
tu
r
e
th
at
in
cl
u
d
es
m
u
ltip
le
la
y
er
s
an
d
s
tag
es
f
o
r
in
f
o
r
m
atio
n
p
r
o
ce
s
s
in
g
[
7
]
.
T
h
e
in
n
er
lay
er
s
ar
e
u
tili
ze
d
to
ex
tr
ac
t
th
e
d
ee
p
f
ea
tu
r
es
w
h
er
ea
s
th
e
o
u
ter
la
y
er
s
h
elp
in
p
er
f
o
r
m
i
n
g
t
h
e
an
al
y
s
i
s
an
d
class
if
ica
tio
n
[
8
]
.
T
h
e
class
i
f
icatio
n
o
f
d
ee
p
lea
r
n
in
g
ca
n
b
e
d
o
n
e
b
ased
o
n
th
e
tr
ain
in
g
m
et
h
o
d
s
in
v
o
l
v
ed
in
b
u
ild
in
g
u
p
th
e
n
et
w
o
r
k
s
an
d
s
o
m
e
o
f
i
ts
p
r
o
m
i
n
en
t
s
u
b
t
y
p
es
ar
e:
i)
C
o
n
v
o
l
u
tio
n
al
n
e
u
r
al
n
et
w
o
r
k
s
(
C
NNs)
,
ii)
R
ec
u
r
r
en
t
n
eu
r
al
n
et
w
o
r
k
s
(
R
NN
s
)
,
iii)
Dee
p
n
eu
r
al
n
e
t
w
o
r
k
s
(
DNN
s
)
T
h
ese
s
u
b
t
y
p
es
f
al
l
in
th
e
ca
teg
o
r
y
o
f
d
ee
p
d
is
cr
i
m
in
a
to
r
y
m
o
d
el
s
.
An
o
th
er
s
u
ch
ca
teg
o
r
y
o
f
d
ee
p
lear
n
in
g
i
n
cl
u
d
es
u
n
s
u
p
er
v
i
s
ed
/g
e
n
er
ativ
e
m
o
d
els
s
u
c
h
as
d
ee
p
b
elief
n
et
w
o
r
k
s
(
DB
Ns),
r
estricte
d
B
o
ltzm
a
n
n
m
ac
h
i
n
es
(
R
B
Ms
)
,
d
ee
p
B
o
ltzm
a
n
n
m
ac
h
i
n
es
(
DB
Ms)
,
an
d
r
eg
u
lar
ized
a
u
to
en
co
d
er
s
.
Dee
p
l
ea
r
n
in
g
h
as
g
a
in
ed
p
ac
e
f
r
o
m
t
h
e
p
as
t
1
0
y
ea
r
s
d
u
e
to
its
ab
ilit
y
to
p
r
o
ce
s
s
h
u
g
e
c
h
u
n
k
s
o
f
p
r
o
ce
s
s
ed
d
at
a
in
cl
u
d
in
g
2
D
im
a
g
e
s
w
it
h
h
i
g
h
ef
f
icie
n
c
y
.
W
e
w
ill
b
e
u
s
i
n
g
th
is
f
ea
tu
r
e
o
f
d
ee
p
lear
n
in
g
to
tr
ain
th
e
m
o
d
el
w
it
h
2
D
Scalo
g
r
a
m
i
m
ag
e
s
w
h
ic
h
h
a
v
e
b
ee
n
d
er
iv
ed
f
r
o
m
1
D
E
C
G
s
i
g
n
al
d
atasets
.
T
h
e
g
o
al
is
to
tr
ain
a
co
n
v
o
lu
tio
n
al
n
e
u
r
al
n
et
w
o
r
k
(
C
NN)
s
o
th
at
i
t
w
ill
b
e
ab
le
to
d
is
tin
g
u
i
s
h
b
et
w
ee
n
t
h
e
s
e
t
h
r
ee
t
y
p
es
o
f
E
C
G
s
ig
n
al
s
-
N
SR
,
AR
R
a
n
d
C
H
F.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2502
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
22
,
No
.
3
,
J
u
n
e
2
0
2
1
:
1
5
2
0
-
1
5
2
8
1522
2.
RE
L
AT
E
D
WO
RK
Hea
r
tb
ea
t
s
eg
m
en
ta
tio
n
i
s
ess
en
tial
f
o
r
class
i
f
ica
tio
n
o
f
h
e
ar
t
d
is
ea
s
es
as
f
e
w
er
r
o
r
s
m
i
g
h
t
h
a
v
e
a
d
ef
in
i
te
i
m
p
ac
t
o
n
th
e
cla
s
s
i
f
icatio
n
r
esu
l
ts
o
f
E
C
G
s
ig
n
al
s
.
Seg
m
en
tatio
n
m
ain
l
y
i
n
v
o
l
v
es
d
etec
tio
n
o
f
P
-
QR
S
-
T
w
a
v
es.
R
esear
ch
in
to
th
e
d
etec
tio
n
o
f
Q
R
S
co
m
p
le
x
es
i
n
E
C
G
s
i
g
n
als
h
as
b
ee
n
ca
r
r
ied
f
o
r
y
ea
r
s
b
y
v
ir
tu
e
o
f
f
r
eq
u
e
n
tl
y
u
s
ed
m
et
h
o
d
s
s
u
c
h
te
m
p
late
m
atc
h
i
n
g
m
et
h
o
d
[
9
]
,
d
if
f
er
en
tial
th
r
es
h
o
ld
m
eth
o
d
[
4
]
an
d
w
a
v
elet
tr
a
n
s
f
o
r
m
[
1
0
]
.
So
m
e
alg
o
r
ith
m
s
w
er
e
also
d
ev
elo
p
ed
to
ex
tr
ac
t
f
ea
tu
r
es
f
r
o
m
P
an
d
T
w
a
v
es
[
1
1
]
.
R
R
in
ter
v
al
s
ar
e
o
n
e
o
f
th
e
m
o
s
t
s
o
u
g
h
t
o
u
t
f
ea
t
u
r
es
o
f
E
C
G
s
ig
n
als
th
a
t
h
a
v
e
b
ee
n
u
s
ed
f
o
r
class
i
f
icatio
n
[
1
2
]
.
I
n
ad
d
itio
n
to
R
R
in
ter
v
als,
m
o
r
p
h
o
lo
g
ic
al
f
ea
tu
r
es
s
u
c
h
as
w
a
v
e
a
m
p
l
itu
d
e
an
d
p
o
s
itiv
e
n
eg
at
iv
e
ar
ea
s
h
a
v
e
b
ee
n
u
s
e
d
.
A
p
ar
t
f
r
o
m
t
h
e
m
o
r
p
h
o
lo
g
ical
f
ea
t
u
r
es
o
b
tain
ed
f
r
o
m
P
-
Q
R
S
-
T
w
av
e
s
o
f
E
C
G
s
i
g
n
als,
s
ig
n
al
p
r
o
ce
s
s
i
n
g
m
et
h
o
d
s
s
u
c
h
as
h
i
g
h
er
o
r
d
er
s
p
ec
tr
al
cu
m
u
lan
ts
[
1
3
]
,
w
a
v
elet
tr
a
n
s
f
o
r
m
s
b
o
th
d
is
cr
ete
an
d
co
n
tin
u
o
u
s
an
d
in
d
ep
en
d
en
t
co
m
p
o
n
en
t
an
al
y
s
is
(
I
C
A
)
h
av
e
b
ee
n
w
i
d
ely
u
s
ed
f
o
r
E
C
G
class
i
f
icatio
n
f
o
r
h
ea
r
t
d
is
ea
s
e
s
.
A
lt
h
o
u
g
h
,
th
ese
f
ea
tu
r
es
f
o
llo
w
a
p
ar
ticu
lar
m
ath
e
m
at
ical
in
ter
p
r
etatio
n
,
th
e
y
ce
r
tain
l
y
d
o
lack
th
e
p
h
y
s
io
lo
g
ical
m
ea
n
i
n
g
m
ak
in
g
it
d
if
f
i
cu
lt
f
o
r
m
ed
ical
p
r
ac
titi
o
n
er
s
to
u
n
d
er
s
tan
d
p
lu
s
co
m
p
u
tatio
n
al
co
s
t to
i
m
p
le
m
en
t th
e
s
e
m
eth
o
d
s
.
T
h
e
w
o
r
k
p
r
o
p
o
s
ed
Ku
m
ar
et
a
l
.
i
n
[
1
4
]
f
o
r
ar
r
h
y
t
h
m
ic
b
ea
t
class
i
f
icat
io
n
u
s
i
n
g
t
h
e
E
C
G
d
ataset
i
s
b
ased
o
n
d
is
cr
ete
co
s
in
e
tr
an
s
f
o
r
m
(
DC
T
)
w
h
er
e
th
e
DC
T
co
n
v
er
ts
ti
m
e
s
er
ie
s
p
lo
t
o
f
an
E
C
G
d
ata
in
to
th
e
co
r
r
esp
o
n
d
in
g
f
r
eq
u
e
n
c
y
co
m
p
o
n
en
ts
.
I
n
t
h
is
m
eth
o
d
o
lo
g
y
th
e
QR
S
c
o
m
p
le
x
o
f
an
E
C
G
s
i
g
n
al
alo
n
g
w
ith
th
e
R
R
in
ter
v
al
ar
e
u
s
ed
to
d
i
s
tin
g
u
is
h
s
i
g
n
al
s
f
r
o
m
o
n
e
a
n
o
th
er
f
o
llo
w
ed
b
y
t
h
e
cla
s
s
i
f
ic
atio
n
u
s
i
n
g
r
an
d
o
m
tr
ee
tech
n
iq
u
e.
Data
w
as
o
b
tain
ed
f
r
o
m
t
h
e
p
h
y
s
io
b
an
k
w
e
b
s
ite
an
d
p
ap
er
claim
s
to
ac
h
i
ev
e
an
ac
c
u
r
ac
y
o
f
9
0
%.
On
e
o
f
th
e
b
ac
k
d
r
o
p
s
o
f
th
e
p
r
o
p
o
s
ed
s
tr
ateg
y
is
th
at
t
h
e
class
i
f
icat
io
n
h
a
s
b
ee
n
d
o
n
e
u
s
in
g
th
e
r
an
d
o
m
f
o
r
est
w
h
ich
w
o
r
k
s
w
ell
f
o
r
th
e
li
m
ited
d
ataset
o
n
l
y
a
n
d
s
lo
w
s
d
o
w
n
f
o
r
h
u
g
e
ch
u
n
k
s
o
f
d
ata.
T
h
o
m
as
e
t
a
l
.
[
1
5
]
,
th
e
w
o
r
k
p
r
o
p
o
s
ed
ex
tr
ac
ts
th
e
f
ea
t
u
r
es
b
ased
o
n
th
e
d
u
al
t
r
ee
co
m
p
l
ex
w
av
e
let
tr
an
s
f
o
r
m
(
DT
C
W
T
)
an
d
r
es
u
lts
i
n
th
e
au
to
m
a
tic
class
i
f
ic
atio
n
o
f
ca
r
d
iac
a
r
r
h
y
th
m
ia
s
.
DT
C
W
T
tech
n
iq
u
e
w
a
s
p
r
ef
er
r
ed
o
v
er
DW
T
d
u
e
to
th
e
p
r
o
p
er
ty
o
f
s
h
i
f
t
i
n
v
ar
ian
ce
p
r
ese
n
t
i
n
f
o
r
m
er
.
DW
T
is
n
o
d
o
u
b
t
a
p
o
w
er
f
u
l
to
o
l
f
o
r
E
C
G
s
i
g
n
al
an
al
y
s
is
b
u
t
s
u
f
f
er
s
f
r
o
m
p
r
o
b
le
m
s
l
ik
e
alia
s
i
n
g
a
n
d
o
s
cillati
o
n
ap
ar
t
f
r
o
m
s
h
i
f
t
v
ar
ian
ce
.
DT
C
W
T
tech
n
iq
u
e
p
r
o
p
o
s
ed
Ma
n
u
et
a
l
.
in
[
1
5
]
s
im
p
l
y
o
v
er
co
m
es
t
h
e
li
m
itatio
n
s
o
f
DW
T
tech
n
iq
u
e
b
y
i
m
p
le
m
en
tin
g
F
o
u
r
ier
tr
an
s
f
o
r
m
as
t
h
e
m
a
g
n
itu
d
es
d
o
n
o
t
o
s
cillate
f
r
o
m
p
o
s
itiv
e
to
n
eg
at
iv
e
an
d
ar
e
p
er
f
ec
tl
y
s
h
i
f
t
i
n
v
ar
ian
t.
Ho
w
e
v
er
,
li
m
itat
io
n
o
f
s
u
ch
a
s
tr
ateg
y
i
s
th
at
th
e
r
e
is
n
o
m
ea
n
s
o
f
id
en
ti
f
y
i
n
g
w
h
er
e
a
n
ev
e
n
t h
a
s
o
cc
u
r
r
ed
as th
e
ti
m
e
i
n
f
o
r
m
at
io
n
is
m
is
s
in
g
.
Z
h
u
et
a
l
.
[
1
6
]
p
r
o
p
o
s
es
a
m
et
h
o
d
f
o
r
ar
r
h
y
t
h
m
ia
r
ec
o
g
n
itio
n
a
n
d
clas
s
i
f
icatio
n
u
s
in
g
E
C
G
m
o
r
p
h
o
lo
g
y
a
n
d
Seg
m
e
n
t
Fea
tu
r
e
An
al
y
s
i
s
.
I
t
b
eg
in
s
w
ith
t
h
e
ex
tr
ac
tio
n
o
f
m
o
r
p
h
o
lo
g
ic
al
f
ea
tu
r
e
s
f
r
o
m
P
-
QR
S
-
T
w
a
v
e
s
f
o
llo
w
ed
b
y
p
r
in
cip
al
co
m
p
o
n
en
t
a
n
al
y
s
is
(
P
C
A
)
an
d
d
y
n
a
m
ic
ti
m
e
w
ar
p
in
g
(
DT
W
)
to
ex
tr
ac
t
E
C
G
s
eg
m
e
n
t
f
ea
t
u
r
es.
I
n
th
e
last
s
ec
tio
n
o
f
th
e
ir
p
r
o
p
o
s
ed
m
et
h
o
d
o
lo
g
y
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
s
(
SVM)
h
as
b
ee
n
ap
p
lied
to
th
e
f
ea
tu
r
es
ex
tr
ac
ted
an
d
th
e
class
i
f
icat
io
n
r
esu
lt
s
ar
e
o
b
tain
ed
.
T
h
o
u
g
h
th
e
e
f
f
icien
c
y
o
b
tain
ed
is
h
ig
h
er
t
h
an
th
e
o
th
er
p
r
o
p
o
s
ed
m
et
h
o
d
o
lo
g
ies,
h
o
w
e
v
er
,
it
is
a
k
n
o
w
n
f
ac
t
th
at
SVM
h
a
s
li
m
ita
tio
n
s
w
h
en
it
co
m
es
to
th
e
s
ize
o
f
th
e
d
ataset
an
d
is
s
im
p
l
y
n
o
t
s
u
itab
le
f
o
r
lar
g
e
d
at
asets
.
SVMs
d
o
n
o
t
p
er
f
o
r
m
at
p
ar
w
it
h
o
th
er
h
i
g
h
l
y
ef
f
icie
n
t
clas
s
if
ier
s
w
h
e
n
th
e
n
o
is
e
in
th
e
s
i
g
n
al
is
h
i
g
h
.
T
h
er
e
is
n
o
m
e
n
tio
n
o
f
t
h
e
s
ize
o
f
th
e
d
ataset
e
v
en
tu
a
ll
y
u
s
ed
f
o
r
tr
ain
i
n
g
a
n
d
test
i
n
g
u
s
in
g
SVM
c
lass
if
i
er
s
.
W
o
r
k
p
r
o
p
o
s
ed
Sain
i
et
a
l
.
[
1
7
]
also
u
s
es
P
C
A
to
co
m
p
u
te
t
h
e
s
tatis
tical
f
e
atu
r
es
d
ir
ec
tl
y
f
r
o
m
E
C
G
s
i
g
n
als
f
o
llo
w
ed
b
y
t
h
e
u
s
e
o
f
s
u
p
er
v
i
s
ed
m
ac
h
i
n
e
lea
r
n
in
g
cla
s
s
i
f
ier
k
-
n
ea
r
es
t
n
e
ig
h
b
o
r
s
(
KNN)
r
esu
lti
n
g
in
an
o
v
er
all
ac
cu
r
ac
y
o
f
8
7
.
5
% f
o
r
1
0
d
if
f
er
en
t c
la
s
s
es.
F
r
o
m
t
h
e
p
a
s
t
f
ew
y
e
a
r
s
,
d
e
e
p
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s
h
a
v
e
s
h
o
w
n
a
p
o
s
i
t
i
v
e
t
r
e
n
d
a
n
d
o
u
t
p
e
r
f
o
r
m
e
d
t
h
e
t
r
a
d
i
t
i
o
n
a
l
E
C
G
c
l
a
s
s
i
f
i
c
a
t
i
o
n
m
e
t
h
o
d
s
f
o
r
p
a
t
t
e
r
n
r
e
c
o
g
n
i
t
i
o
n
a
p
p
l
i
c
a
t
i
o
n
s
[
1
8
]
a
n
d
a
s
a
r
e
s
u
l
t
,
r
e
s
e
a
r
c
h
e
r
s
a
r
e
f
o
c
u
s
i
n
g
m
o
r
e
o
n
t
h
e
d
e
e
p
l
e
a
r
n
i
n
g
m
o
d
e
l
s
f
o
r
E
C
G
c
l
a
s
s
i
f
i
c
a
t
i
o
n
p
r
o
b
l
e
m
s
f
o
r
s
e
v
e
r
a
l
h
e
a
r
t
d
i
s
e
a
s
e
s
.
R
e
c
u
r
r
e
n
t
n
e
u
r
a
l
n
e
t
w
o
r
k
s
(
R
N
N
s
)
w
e
r
e
p
r
o
p
o
s
e
d
b
y
S
a
l
l
o
u
m
a
n
d
K
u
o
[
1
9
]
f
o
r
t
h
e
i
d
e
n
t
i
f
i
c
a
t
i
o
n
a
n
d
a
u
t
h
e
n
t
i
c
a
t
i
o
n
p
r
o
b
l
e
m
i
n
E
C
G
-
b
a
s
e
d
b
i
o
m
e
t
r
i
c
s
.
M
o
s
t
a
y
e
d
a
l
s
o
u
s
e
d
R
N
N
f
o
r
t
h
e
d
e
t
e
c
t
i
o
n
o
f
p
a
t
h
o
l
o
g
i
e
s
i
n
1
2
-
l
e
a
d
e
l
e
c
t
r
o
c
a
r
d
i
o
g
r
a
m
s
i
g
n
a
l
s
t
h
a
t
c
o
n
s
i
s
t
e
d
o
f
b
i
-
d
i
r
e
c
t
i
o
n
a
l
s
h
o
r
t
-
l
o
n
g
-
t
e
r
m
-
m
em
o
r
y
l
a
y
e
r
s
[
2
0
]
.
1
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
s
(
C
N
N
s
)
w
e
r
e
u
s
e
d
t
o
p
r
o
p
o
s
e
a
r
e
a
l
t
i
m
e
p
a
t
i
e
n
t
s
p
e
c
i
f
i
c
e
l
e
c
t
r
o
c
a
r
d
i
o
g
r
a
m
c
l
a
s
s
i
f
i
c
a
t
i
o
n
t
e
c
h
n
i
q
u
e
f
o
r
c
l
a
s
s
i
f
y
i
n
g
l
o
n
g
E
C
G
s
i
g
n
a
l
r
e
c
o
r
d
s
o
f
p
a
t
i
e
n
t
s
[
2
1
]
.
L
i
a
l
s
o
p
r
o
p
o
s
e
d
a
m
o
d
e
l
f
o
r
t
h
e
c
l
a
s
s
i
f
i
c
a
t
i
o
n
o
f
5
t
y
p
e
s
o
f
a
r
r
h
y
t
h
m
i
a
s
b
a
s
e
d
o
n
t
h
e
1
D
-
C
N
N
m
e
t
h
o
d
[
2
2
]
.
I
m
p
u
l
s
e
r
a
d
i
o
u
l
t
r
a
-
w
i
d
e
b
a
n
d
(
I
R
-
U
W
B
)
r
a
d
a
r
i
n
t
e
g
r
a
t
e
d
w
i
t
h
E
C
G
m
o
n
i
t
o
r
i
n
g
w
a
s
p
r
o
p
o
s
e
d
b
y
Y
i
n
e
t
a
l
.
[
2
3
]
a
n
d
i
m
p
l
e
m
e
n
t
s
a
c
a
s
c
a
d
e
C
N
N
f
o
r
a
n
a
l
y
s
i
s
o
f
E
C
G
s
i
g
n
a
l
s
a
n
d
r
a
d
a
r
d
a
t
a
.
T
h
e
o
v
e
r
a
l
l
a
c
c
u
r
a
c
y
a
c
h
i
e
v
e
d
w
a
s
8
8
.
8
9
%
a
n
d
t
h
e
p
r
o
p
o
s
e
d
m
o
d
e
l
m
a
i
n
t
a
i
n
s
a
s
t
a
b
l
e
a
c
c
u
r
a
c
y
i
n
c
l
a
s
s
i
f
y
i
n
g
n
o
r
m
a
l
a
n
d
a
b
n
o
r
m
a
l
h
e
a
r
t
s
i
g
n
a
l
s
i
n
t
h
e
s
l
i
g
h
t
m
o
t
i
o
n
s
t
a
t
e
.
A
r
ec
e
n
t
tr
e
n
d
in
th
e
cla
s
s
i
f
ic
atio
n
o
f
E
C
G
s
ig
n
al
s
h
a
s
b
ee
n
t
h
e
u
s
e
o
f
2
D
C
N
N
ar
ch
ite
ctu
r
es
t
h
a
t
h
av
e
s
h
o
w
n
p
r
o
m
is
i
n
g
r
esu
lts
w
h
e
n
co
m
p
ar
ed
w
it
h
th
e
r
es
u
lts
f
r
o
m
1
-
D
C
N
N.
On
e
s
u
c
h
m
et
h
o
d
h
as
b
ee
n
p
r
o
p
o
s
ed
E
lif
et
a
l
.
i
n
[
2
4
]
w
h
er
e
a
d
ee
p
lear
n
i
n
g
b
ased
2
-
D
C
NN
m
o
d
el
clas
s
i
f
ies
f
i
v
e
d
is
tin
ct
ar
r
h
y
th
m
ia
t
y
p
es.
I
n
th
i
s
ap
p
r
o
ac
h
ea
c
h
o
f
th
e
h
ea
r
tb
ea
ts
th
a
t
w
er
e
co
llected
f
r
o
m
Ma
s
s
ac
h
u
s
ett
s
I
n
s
ti
tu
te
o
f
T
ec
h
n
o
lo
g
y
-
B
o
s
to
n
'
s
B
eth
I
s
r
ae
l
Ho
s
p
ital
(
MI
T
-
B
I
H
)
d
atab
ase
w
er
e
co
n
v
er
ted
to
2
-
D
g
r
a
y
s
ca
le
i
m
ag
e
s
as
an
in
p
u
t
to
th
e
C
NN
m
o
d
el
an
d
th
e
m
o
d
el
co
u
ld
r
ea
ch
to
an
o
v
er
all
ac
cu
r
ac
y
o
f
9
7
.
4
2
%
o
n
th
e
tr
ain
i
n
g
r
es
u
lts
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
C
la
s
s
i
fica
tio
n
o
f E
C
G
s
ig
n
a
ls
fo
r
d
etec
tio
n
o
f
a
r
r
h
yth
mia
a
n
d
co
n
g
esti
ve
…
(
R
a
s
h
id
a
h
F
u
n
ke
Ola
n
r
ewa
ju
)
1523
T
h
e
p
r
o
p
o
s
ed
C
NN
ar
ch
itectu
r
e
in
clu
d
ed
2
c
o
n
v
o
lu
tio
n
al
la
y
er
s
,
2
p
o
o
lin
g
la
y
er
s
an
d
a
f
u
ll
y
co
n
n
ec
ted
lay
er
in
w
h
ich
t
h
e
f
ir
s
t
t
w
o
la
y
er
s
(
co
n
v
o
lu
tio
n
al
a
n
d
p
o
o
lin
g
)
ar
e
r
esp
o
n
s
ib
le
f
o
r
f
ea
t
u
r
e
ex
tr
a
ctio
n
w
h
er
ea
s
f
u
ll
y
co
n
n
ec
ted
la
y
er
h
elp
s
in
th
e
class
i
f
icatio
n
s
tep
s
.
So
,
th
i
s
w
a
y
2
-
D
i
m
ag
e
s
ar
e
d
ir
ec
tl
y
u
s
ed
as
a
n
i
n
p
u
t
a
n
d
th
er
eb
y
d
o
n
o
t
r
eq
u
ir
e
s
ep
ar
ate
f
ea
t
u
r
e
e
x
tr
ac
tio
n
m
et
h
o
d
s
f
o
r
v
ar
ied
f
ea
tu
r
es
o
f
E
C
G
Si
g
n
al
s
.
An
o
th
er
s
tu
d
y
[
2
5
]
p
r
o
p
o
s
es
a
ten
-
la
y
er
m
o
d
el
co
n
s
is
tin
g
o
f
f
o
u
r
c
o
n
v
o
l
u
tio
n
al
la
y
er
s
,
f
o
u
r
p
o
o
lin
g
la
y
er
s
f
o
llo
w
ed
b
y
a
s
i
n
g
le
f
u
ll
y
co
n
n
ec
ted
la
y
er
an
d
an
o
u
tp
u
t
la
y
er
to
tr
an
s
f
o
r
m
t
h
e
E
C
G
s
i
g
n
als
i
n
to
2
-
D
s
p
ec
tr
o
g
r
a
m
s
.
T
h
is
tr
an
s
f
o
r
m
atio
n
is
d
o
n
e
u
s
in
g
a
s
h
o
r
t
-
ti
m
e
Fo
u
r
ier
T
r
an
s
f
o
r
m
a
n
d
th
e
cla
s
s
i
f
icatio
n
a
cc
u
r
ac
y
o
b
tain
ed
is
also
v
er
y
h
i
g
h
.
T
h
o
u
g
h
th
e
f
i
n
al
av
er
a
g
e
ac
c
u
r
ac
y
as
c
lai
m
ed
in
t
h
i
s
r
esear
ch
is
ab
o
v
e
9
9
%
b
u
t
th
er
e
t
w
o
class
es
w
i
th
i
n
d
i
v
id
u
al
f
r
eq
u
e
n
cies o
f
le
s
s
t
h
a
n
9
0
% a
n
d
o
n
e
class
ac
cu
r
ac
y
r
ea
ch
i
n
g
a
s
lo
w
as 7
7
.
6
%.
3.
M
AT
E
RIAL
A
ND
M
E
T
H
O
DS
3
.
1
.
E
CG
s
ig
na
l da
t
a
s
et
a
nd
da
t
a
ba
s
e
pro
ce
s
s
ing
H
er
e,
w
e
u
s
ed
th
r
ee
ca
teg
o
r
i
es
o
f
E
C
G
s
ig
n
al
s
f
o
r
m
o
d
ellin
g
a
d
ee
p
C
NN:
i)
C
ar
d
iac
a
r
r
h
y
t
h
m
ia
(
AR
R
)
,
ii)
C
o
n
g
e
s
ti
v
e
h
ea
r
t
f
ailu
r
e
(
C
H
F),
iii)
No
r
m
al
s
i
n
u
s
r
h
y
th
m
(
NS
R
)
.
T
h
ese
s
i
g
n
al
s
ar
e
o
b
tain
ed
f
r
o
m
1
6
2
E
C
G
r
ec
o
r
d
in
g
s
f
r
o
m
th
r
ee
P
h
y
s
io
n
et
d
atab
ases
:
MI
T
-
B
I
H
ar
r
h
y
th
m
ia
d
atab
ase
(
9
6
r
ec
o
r
d
in
g
s
o
f
AR
R
s
ig
n
al
s
)
,
MI
T
-
B
I
H
n
o
r
m
al
s
i
n
u
s
r
h
y
t
h
m
d
atab
ase
(
3
0
R
ec
o
r
d
in
g
s
o
f
NS
R
s
i
g
n
al
s
a
n
d
B
I
DM
C
co
n
g
e
s
ti
v
e
h
ea
r
t
f
ail
u
r
e
d
atab
ase
(
3
6
r
ec
o
r
d
in
g
s
o
f
C
HF
s
ig
n
al
s
)
.
T
h
e
d
ata
m
atr
i
x
i
s
o
f
s
ize
1
6
*
6
5
5
3
6
w
h
ic
h
m
ea
n
s
i
t
ca
r
r
ies
a
to
tal
o
f
1
6
2
E
C
G
s
ig
n
als
o
f
s
ize
6
5
5
3
6
s
am
p
les
ea
ch
.
E
ac
h
s
ig
n
al
h
a
s
b
ee
n
lab
elled
f
r
o
m
w
h
ic
h
th
e
in
f
o
r
m
atio
n
ab
o
u
t
t
h
e
t
y
p
e
o
f
th
e
E
C
G
s
ig
n
al
i
s
g
at
h
er
ed
.
R
o
w
s
1
:9
6
o
f
th
e
d
atab
ase
ar
e
AR
R
s
i
g
n
als,
r
o
w
s
9
7
:1
2
6
o
f
th
e
d
atab
ase
ar
e
C
HF sig
n
al
s
an
d
r
o
w
s
1
2
7
:1
6
2
o
f
th
e
d
atab
ase
ar
e
NSR
s
i
g
n
als.
Data
p
r
ep
r
o
ce
s
s
in
g
f
o
r
o
u
r
p
r
o
b
lem
s
ta
te
m
e
n
t
is
f
ir
s
t
s
tar
te
d
at
th
e
d
atab
ase
lev
el.
E
ac
h
r
ec
o
r
d
is
o
f
len
g
th
6
5
5
3
6
s
am
p
les
o
r
s
i
m
p
l
y
d
ata
p
o
in
ts
an
d
is
th
er
eb
y
b
r
o
k
en
in
to
s
m
all
s
i
g
n
a
ls
o
f
l
en
g
t
h
s
5
0
0
s
am
p
les
to
in
cr
ea
s
e
th
e
s
ize
o
f
th
e
d
at
ab
ase
to
m
a
k
e
it
ap
p
r
o
p
r
iate
t
o
tr
a
in
a
co
n
v
o
lu
t
io
n
n
e
u
r
al
n
et
w
o
r
k
-
i
n
o
u
r
ca
s
e
A
le
x
Net.
W
e
also
tak
e
3
0
r
ec
o
r
d
in
g
s
o
f
ea
ch
t
y
p
e
(
AR
R
,
C
HF,
an
d
NSR
)
to
h
av
e
eq
u
al
d
is
tr
ib
u
tio
n
.
E
ac
h
r
ec
o
r
d
in
g
h
as
b
ee
n
b
r
o
k
en
in
t
o
2
0
p
iece
s
o
f
len
g
t
h
5
0
0
s
a
m
p
les
an
d
th
er
ef
o
r
e
ea
ch
ca
teg
o
r
y
w
ill
p
r
o
v
id
e
6
0
0
(
3
0
*
2
0
)
r
ec
o
r
d
in
g
s
o
f
s
ize
5
0
0
s
a
m
p
les a
n
d
th
u
s
t
h
e
to
tal
w
il
l b
e
1
8
0
0
r
ec
o
r
d
in
g
s
.
3
.
2
.
E
CG
s
ig
na
l t
o
i
m
a
g
e
co
nv
er
s
io
n us
i
ng
co
ntinuo
us
w
a
v
elet
t
r
a
ns
f
o
r
m
Her
e
w
e
w
er
e
ab
le
to
co
n
v
er
t
o
n
e
-
d
i
m
en
s
io
n
al
E
C
G
s
i
g
n
al
i
n
to
a
n
e
w
t
w
o
-
d
i
m
e
n
s
io
n
al
R
GB
im
a
g
e
b
y
ex
tr
ac
tin
g
E
C
G
s
i
g
n
a
l
f
e
atu
r
es
th
at
ap
p
ea
r
ed
in
a
ce
r
tain
f
r
eq
u
e
n
c
y
b
an
d
.
T
h
e
r
es
u
lta
n
t
i
m
a
g
es
w
er
e
o
b
tain
ed
v
ia
ti
m
e
-
f
r
eq
u
en
c
y
r
ep
r
esen
tatio
n
o
f
t
h
eir
co
r
r
esp
o
n
d
in
g
E
C
G
s
i
g
n
al
s
.
Sh
o
r
t
ti
m
e
f
o
u
r
ier
tr
a
n
s
f
o
r
m
(
ST
F
T
)
w
h
ich
h
as
b
ee
n
co
m
m
o
n
l
y
u
s
ed
f
o
r
th
e
ti
m
e
-
f
r
eq
u
en
c
y
r
ep
r
esen
tatio
n
is
les
s
ef
f
ec
tiv
e
f
o
r
E
C
G
s
ig
n
al
s
d
u
e
to
ti
m
e
a
n
d
f
r
eq
u
en
c
y
tr
ad
e
-
o
f
f
i
n
r
eso
lu
tio
n
[
2
6
]
.
Sm
all
w
in
d
o
w
s
ize
in
S
T
F
T
r
esu
lts
i
n
g
o
o
d
ti
m
e
b
u
t p
o
o
r
f
r
eq
u
e
n
c
y
a
n
d
t
h
e
r
es
u
lts
ar
e
q
u
ite
o
p
p
o
s
ite
w
h
en
th
e
w
i
n
d
o
w
is
w
id
e.
T
o
r
eso
lv
e
t
h
i
s
is
s
u
e,
w
e
m
ak
e
u
s
e
o
f
co
n
t
in
u
o
u
s
w
a
v
el
et
tr
an
s
f
o
r
m
(
C
W
T
)
[
2
7
]
to
d
e
v
elo
p
a
t
w
o
-
d
i
m
e
n
s
io
n
al
R
GB
i
m
a
g
e
o
f
a
n
E
C
G
s
ig
n
al.
Fo
u
r
ier
t
r
an
s
f
o
r
m
(
FT
)
an
d
co
n
ti
n
u
o
u
s
w
av
e
let
tr
a
n
s
f
o
r
m
(
C
W
T
)
h
av
e
s
i
m
ilar
m
eth
o
d
o
lo
g
ies
w
h
er
e
FT
g
en
er
ates
co
r
r
elatio
n
co
e
f
f
icie
n
ts
b
et
w
ee
n
t
h
e
s
i
n
u
s
o
id
al
s
i
g
n
al
an
d
t
h
e
o
r
ig
i
n
al
s
i
g
n
al.
Si
m
ilar
l
y
,
C
W
T
also
g
en
er
ates
co
ef
f
icie
n
ts
li
k
e
FT
,
h
o
w
e
v
er
,
th
e
d
if
f
er
en
ce
b
etw
ee
n
t
w
o
tr
an
s
f
o
r
m
s
is
t
h
e
d
o
m
ain
s
in
w
h
ich
th
o
s
e
co
r
r
elatio
n
co
e
f
f
ic
ien
ts
ar
e
g
en
er
ated
.
W
h
i
le
FT
d
ea
ls
w
ith
f
r
eq
u
e
n
c
y
d
o
m
ai
n
,
co
ef
f
icien
t
s
i
n
C
W
T
ar
e
g
en
er
ated
in
ti
m
e
d
o
m
ain
.
W
e
ch
o
s
e
C
W
T
d
u
e
to
th
e
r
ea
s
o
n
s
m
an
y
r
elev
a
n
t
u
s
ef
u
l
d
etails
co
u
ld
b
e
ex
tr
ac
ted
f
r
o
m
t
h
e
s
i
g
n
als
i
n
t
h
e
ti
m
e
d
o
m
a
in
.
T
h
e
s
h
ap
e
o
f
th
e
C
W
T
w
a
v
ef
o
r
m
ca
n
b
e
ea
s
i
l
y
co
n
tr
o
lled
b
y
s
h
if
tin
g
an
d
s
ca
li
n
g
p
ar
a
m
eter
s
.
T
h
e
m
ath
e
m
atica
l
f
o
r
m
u
la
o
f
C
W
T
f
o
r
a
f
u
n
ctio
n
x
(
t)
h
a
s
b
ee
n
g
iv
en
in
(
1
)
:
C
W
T
(
s
,
ω
)
=
(
1
/
√
s
)
∫
x
(
t)
.
Ψ
(
(
t
-
ω
)
/s
)
.
d
t
(
1
)
Her
e
s
a
n
d
ω
a
r
e
ca
lled
d
ilat
io
n
(
s
ca
le)
a
n
d
t
r
an
s
latio
n
(
p
o
s
itio
n
)
p
ar
a
m
eter
s
,
r
esp
ec
tiv
el
y
.
Sca
l
e
p
ar
am
eter
s
ar
e
r
esp
o
n
s
ib
le
f
o
r
eith
er
s
tr
etch
i
n
g
t
h
e
w
a
v
e
let
o
r
co
m
p
r
ess
i
n
g
th
e
w
a
v
e
let.
Ψ
r
ep
r
esen
ts
a
w
a
v
elet
f
u
n
ctio
n
an
d
in
o
u
r
ex
p
er
i
m
e
n
t,
w
e
ar
e
u
s
i
n
g
Mo
r
l
et
w
av
e
let
as
g
iv
e
n
in
(
2
)
.
x
(
t)
r
ep
r
esen
ts
th
e
E
C
G
si
g
n
al
i
n
th
is
p
ap
er
an
d
C
W
T
(
s
,
ω
)
d
en
o
tes
th
e
co
ef
f
ici
en
ts
o
b
tain
ed
b
y
p
er
f
o
r
m
in
g
co
n
tin
u
o
u
s
w
av
e
let
tr
an
s
f
o
r
m
.
(
)
=
.
2
/
2
(
2
)
T
h
e
r
esu
lts
o
f
C
W
T
ar
e
m
a
n
y
w
av
elet
co
ef
f
icie
n
ts
,
w
h
ich
a
r
e
a
f
u
n
c
tio
n
o
f
s
(
s
ca
le)
a
n
d
ω
(
p
o
s
itio
n
)
.
E
C
G
s
ig
n
al
x
(
t)
ca
n
b
e
r
ec
o
v
er
ed
b
y
p
er
f
o
r
m
i
n
g
a
n
i
n
v
er
s
e
C
W
T
,
as sh
o
w
n
in
(
3
)
.
(
)
=
1
∫
(
,
)
,
(
)
|
|
3
/
2
.
(
3
)
w
h
er
e
C
r
ep
r
esen
t
s
th
e
n
o
r
m
al
izatio
n
co
n
s
tan
t t
h
at
e
n
tire
l
y
d
ep
en
d
s
u
p
o
n
t
h
e
w
av
ele
t selec
ted
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2502
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
22
,
No
.
3
,
J
u
n
e
2
0
2
1
:
1
5
2
0
-
1
5
2
8
1524
C
W
T
,
w
it
h
a
s
m
o
o
th
w
a
v
elet,
h
as
th
e
ca
p
ab
ilit
y
o
f
e
x
tr
ac
ti
n
g
o
r
r
ep
r
esen
ti
n
g
t
h
e
d
y
n
a
m
ic
f
r
eq
u
en
c
y
p
r
o
p
er
ties
o
f
an
y
s
i
g
n
al
ap
p
lied
u
p
o
n
an
d
w
e
w
ill
b
e
u
s
in
g
t
h
is
p
r
o
p
er
t
y
o
f
C
W
T
to
o
b
tain
i
n
f
o
r
m
atio
n
f
r
o
m
E
C
G
s
i
g
n
als.
Her
e
w
e
w
ill
u
s
e
Mo
r
let
w
a
v
elet
b
y
ap
p
l
y
i
n
g
v
ar
io
u
s
s
ca
les
a
n
d
tr
an
s
latio
n
s
o
n
to
p
o
f
Mo
r
let.
Mo
r
let
w
a
v
elet
h
as
b
ee
n
o
b
tain
ed
o
r
d
er
iv
ed
f
r
o
m
a
Ga
u
s
s
ia
n
f
u
n
ctio
n
an
d
is
r
ep
r
esen
ted
b
y
(
4
)
.
P
ar
am
e
ter
σ
p
lay
s
a
p
iv
o
tal
r
o
le
in
s
h
ap
i
n
g
th
e
m
o
t
h
er
w
av
e
let.
(
)
=
2
−
2
2
2
=
(
2
+
2
)
−
2
2
2
(4
)
A
t
t
h
is
s
ta
g
e
o
f
p
r
ep
r
o
ce
s
s
in
g
all
th
e
o
n
e
-
d
i
m
e
n
s
io
n
al
(
1
D)
s
ig
n
a
ls
ar
e
co
n
v
er
ted
in
to
i
m
ag
es
u
s
i
n
g
co
n
tin
u
o
u
s
w
a
v
elet
tr
an
s
f
o
r
m
(
C
W
T
)
s
o
th
at
t
h
ese
i
m
a
g
es
c
o
u
ld
later
b
e
f
ed
to
a
d
ee
p
C
NN
-
A
le
x
Net.
T
h
e
c
o
ef
f
icie
n
t
s
o
f
a
C
W
T
o
f
ea
c
h
1
D
s
i
g
n
a
l
ar
e
ar
r
an
g
ed
to
f
o
r
m
a
C
W
T
Scalo
g
r
a
m
an
d
ea
ch
Scalo
g
r
a
m
i
s
r
ep
r
esen
ted
as
a
co
lo
r
m
ap
o
f
t
y
p
e
“
j
et”
o
f
1
2
8
co
lo
r
s
.
C
o
n
v
er
s
io
n
o
f
Scalo
g
r
a
m
in
to
i
m
a
g
es
is
s
to
r
ed
in
t
h
eir
r
esp
ec
tiv
e
f
o
ld
er
s
(
AR
R
,
NS
R
,
an
d
C
HF
)
.
E
ac
h
I
m
ag
e
is
r
esized
to
2
2
7
*
2
2
7
as
th
ese
im
ag
e
s
ar
e
f
ed
to
a
d
ee
p
C
NN
m
o
d
el
A
le
x
Net
t
h
at
ca
n
o
n
l
y
ac
ce
p
t
i
m
a
g
es
o
f
th
e
m
e
n
tio
n
ed
s
ize.
B
y
th
e
e
n
d
o
f
th
is
ac
ti
v
it
y
,
a
to
tal
o
f
1
8
0
0
Scalo
g
r
a
m
i
m
ag
es a
r
e
p
r
o
d
u
ce
d
f
o
r
co
r
r
esp
o
n
d
in
g
1
8
0
0
E
C
G
s
i
g
n
als
-
6
0
0
f
r
o
m
ea
ch
ca
te
g
o
r
y
i
n
th
eir
r
esp
ec
tiv
e
f
o
ld
er
s
.
C
W
T
m
e
t
h
o
d
o
l
o
g
y
a
p
p
l
i
e
d
f
o
r
t
h
e
c
o
n
v
e
r
s
i
o
n
o
f
s
i
g
n
a
l
s
t
o
i
m
a
g
e
s
b
y
v
i
r
t
u
e
o
f
a
c
a
r
e
f
u
l
l
y
c
h
o
s
e
n
w
a
v
e
l
e
t
a
n
a
l
y
t
i
c
a
l
m
o
r
l
e
t
(
a
m
o
r
)
d
u
e
t
o
i
t
s
e
q
u
a
l
v
a
r
i
a
n
c
e
i
n
t
i
m
e
a
n
d
f
r
e
q
u
e
n
cy
.
T
h
e
s
e
w
av
e
l
e
t
s
m
a
k
e
a
g
o
o
d
c
h
o
i
c
e
f
o
r
o
b
t
a
i
n
i
n
g
a
t
im
e
-
f
r
e
q
u
e
n
c
y
a
n
a
l
y
s
i
s
u
s
i
n
g
C
W
T
.
1
2
w
a
v
e
l
e
t
b
a
n
d
p
a
s
s
f
i
l
t
e
r
s
a
r
e
u
s
e
d
f
o
r
C
W
T
t
h
a
t
a
l
l
o
w
s
o
n
l
y
a
c
e
r
t
a
i
n
r
a
n
g
e
o
f
f
r
e
q
u
e
n
c
i
e
s
t
o
p
a
s
s
t
h
r
o
u
g
h
w
h
i
l
e
b
l
o
c
k
i
n
g
e
x
t
r
e
m
e
l
y
h
i
g
h
a
n
d
e
x
t
r
e
m
e
l
y
l
o
w
f
r
e
q
u
e
n
c
i
e
s
.
T
h
e
r
e
s
u
l
t
o
f
c
o
n
v
e
r
s
i
o
n
p
r
o
c
e
d
u
r
e
s
o
n
o
n
e
o
f
t
h
e
t
h
r
e
e
d
i
f
f
e
r
e
n
t
c
a
t
e
g
o
r
i
e
s
f
o
r
a
s
i
n
g
l
e
s
i
g
n
a
l
h
a
s
b
e
e
n
s
h
o
w
n
i
n
F
i
g
u
r
e
2
.
T
h
i
s
c
o
n
v
e
r
s
i
o
n
w
a
s
d
o
n
e
f
o
r
a
l
l
t
h
o
s
e
1
8
0
0
s
i
g
n
a
l
s
p
r
e
s
e
n
t
i
n
o
u
r
d
a
t
a
b
a
s
e
.
Fig
u
r
e
2
.
C
o
n
v
er
s
io
n
o
f
1
D
E
C
G
s
i
g
n
al
in
to
it
s
co
r
r
esp
o
n
d
in
g
2
D
s
ca
lo
g
r
a
m
i
m
a
g
e
[
2
2
7
*
2
2
7
]
3
.
3
.
Appl
y
t
ra
ns
f
er
lea
rning
m
ec
ha
nis
m
A
p
r
e
-
tr
ai
n
ed
d
ee
p
n
eu
r
al
n
e
t
w
o
r
k
-
Alex
Ne
t
h
as
b
ee
n
u
s
e
d
.
A
lex
Ne
t
h
as
b
ee
n
tr
ai
n
ed
o
n
o
v
er
a
m
illi
o
n
i
m
a
g
es
a
n
d
ca
n
class
i
f
y
i
m
a
g
es
in
to
1
0
0
0
d
if
f
er
en
t
o
b
j
ec
t
ca
teg
o
r
ies.
So
b
asically
,
w
e
w
ill
b
e
f
i
n
e
tu
n
in
g
a
p
r
e
-
tr
ain
ed
C
NN
to
p
er
f
o
r
m
t
h
e
clas
s
i
f
icatio
n
o
n
a
n
e
w
co
llectio
n
o
f
i
m
a
g
es.
T
h
i
s
m
e
th
o
d
o
f
tr
a
n
s
f
er
lear
n
in
g
i
s
q
u
ick
er
th
a
n
tr
ai
n
i
n
g
a
C
NN
f
r
o
m
s
cr
atch
w
h
ic
h
r
eq
u
ir
es
a
lo
t
o
f
tr
ai
n
in
g
t
i
m
e
a
n
d
t
h
o
u
s
a
n
d
s
o
f
in
p
u
t
i
m
a
g
es.
A
le
x
Net
ar
ch
it
ec
tu
r
e
is
s
h
o
w
n
i
n
Fig
u
r
e
3
w
h
ic
h
co
n
s
i
s
ts
o
f
8
la
y
er
s
o
u
t
o
f
w
h
ich
5
ar
e
co
n
v
o
lu
tio
n
al
la
y
er
s
an
d
w
e
h
av
e
3
f
u
ll
y
co
n
n
ec
ted
la
y
er
s
.
T
h
e
in
p
u
t
s
ize
w
h
ic
h
A
le
x
Net
ac
ce
p
ts
i
s
2
2
7
*
2
2
7
*
3
w
h
er
e
3
r
ef
er
s
to
a
co
lo
r
i
m
ag
e.
So
,
th
e
i
n
p
u
t
t
o
th
e
f
ir
s
t
co
n
v
o
l
u
tio
n
a
l
is
2
2
7
*
2
2
7
*
3
w
h
ic
h
t
h
en
ap
p
lies
9
6
f
ilter
s
o
f
s
ize
1
1
*
1
1
w
it
h
a
s
tr
id
e
o
f
4
p
ix
el
s
f
o
llo
w
ed
b
y
p
o
o
lin
g
la
y
er
o
f
w
i
n
d
o
w
s
ize
3
*
3
t
h
a
t
ap
p
lies
a
s
tr
id
e
o
f
2
.
T
h
e
o
u
tp
u
t
o
f
f
ir
s
t
co
n
v
o
lu
tio
n
al
la
y
er
b
ec
o
m
e
s
t
h
e
in
p
u
t
o
f
s
ec
o
n
d
c
o
n
v
o
l
u
tio
n
al
la
y
er
an
d
s
o
o
n
till
co
n
v
o
l
u
tio
n
al
la
y
er
5
.
T
h
e
o
u
tp
u
t
ten
s
o
r
at
t
h
e
co
n
v
o
l
u
tio
n
a
l
la
y
er
5
is
(
1
3
*
1
3
*
2
5
6
)
af
ter
g
o
in
g
th
r
o
u
g
h
a
m
a
x
p
o
o
lin
g
la
y
er
p
er
f
o
r
m
ed
ze
r
o
p
ad
d
ed
s
am
p
lin
g
o
p
er
atio
n
w
ith
a
s
tr
id
e
o
f
2
an
d
a
w
in
d
o
w
r
eg
io
n
o
f
(
3
*
3
)
an
d
t
h
is
s
u
b
s
a
m
p
li
n
g
o
p
er
atio
n
p
r
o
d
u
ce
d
a
ten
s
o
r
o
u
t
p
u
t
o
f
s
ize
(
6
*
6
*
2
5
6
)
.
First
F
u
ll
y
C
o
n
n
ec
ted
la
y
er
o
f
t
h
e
ar
ch
ite
ctu
r
e
s
h
o
w
n
i
n
Fi
g
u
r
e
3
is
r
ep
r
esen
ted
as
F
C
6
w
h
ic
h
ac
ce
p
ts
(
6
*
6
*
2
5
6
)
ten
s
o
r
f
r
o
m
t
h
e
p
r
ev
io
u
s
la
y
er
an
d
p
er
f
o
r
m
ed
w
eig
h
ted
s
u
m
o
p
er
atio
n
r
esu
lti
n
g
i
n
(
4
0
9
6
*
1
)
ten
s
o
r
o
u
tp
u
t.
F
C
7
is
y
et
an
o
t
h
er
f
u
l
l
y
co
n
n
ec
ted
la
y
er
th
at
ac
ce
p
ts
th
e
4
0
9
1
*
1
ten
s
o
r
as
an
in
p
u
t
an
d
af
ter
p
ass
i
n
g
t
h
r
o
u
g
h
t
h
e
r
ec
tif
ied
lin
ea
r
ac
tiv
at
io
n
f
u
n
ctio
n
(
R
eL
u
)
p
r
o
d
u
ce
s
th
e
o
u
tp
u
t
w
i
th
t
h
e
s
a
m
e
d
i
m
e
n
s
io
n
s
(
4
0
9
1
*
1
)
an
d
th
i
s
l
a
y
e
r
s
i
m
p
l
y
r
e
s
u
l
t
s
i
n
t
h
e
g
r
e
a
t
e
r
n
u
m
b
e
r
o
f
t
r
a
i
n
a
b
l
e
p
a
r
a
m
e
t
e
r
s
w
h
e
n
c
o
m
p
a
r
e
d
w
i
t
h
t
h
e
p
r
e
v
i
o
u
s
l
a
y
e
r
(
F
C
6
)
.
F
C
8
i
s
t
h
e
l
a
s
t
l
a
y
e
r
r
e
p
r
e
s
e
n
t
s
t
h
e
o
u
t
p
u
t
c
l
a
s
s
t
h
a
t
u
s
e
s
t
h
e
S
o
f
t
M
a
x
a
c
t
i
v
a
t
i
o
n
f
u
n
c
t
i
o
n
f
o
r
c
l
a
s
s
i
f
i
c
a
t
i
o
n
a
n
d
p
e
r
f
o
r
m
s
t
h
e
s
a
m
e
f
u
n
c
t
i
o
n
a
s
t
h
a
t
o
f
F
C
6
a
n
d
F
C
7
a
n
d
h
a
s
b
e
e
n
m
o
d
i
f
i
e
d
t
o
3
f
o
r
t
h
e
m
o
d
e
l
a
s
w
e
a
r
e
t
r
y
i
n
g
t
o
c
l
a
s
s
i
f
y
o
n
t
h
r
e
e
d
i
f
f
e
r
e
n
t
c
l
a
s
s
e
s
s
u
c
h
a
s
A
R
R
,
C
H
F
a
n
d
N
S
R
.
A
s
f
a
r
as
t
h
e
m
a
t
h
e
m
a
t
i
c
s
f
o
r
e
a
c
h
l
a
y
e
r
o
f
A
l
e
x
N
e
t
i
s
c
o
n
c
e
r
n
e
d
t
h
e
r
e
a
r
e
t
w
o
d
i
s
t
i
n
c
t
c
a
s
e
s
,
o
n
e
f
o
r
w
i
t
h
o
u
t
p
a
d
d
i
n
g
w
h
i
c
h
i
s
r
e
p
r
e
s
e
n
t
e
d
b
y
(
5
)
a
n
d
o
n
e
w
i
t
h
p
a
d
d
i
n
g
h
a
s
b
e
e
n
p
u
t
i
n
(
6
)
.
T
h
e
s
i
z
e
o
f
t
h
e
i
m
a
g
e
(
I
m
S)
i
s
c
a
l
c
u
l
a
t
e
d
a
f
t
e
r
p
a
s
s
i
n
g
t
h
r
o
u
g
h
e
a
c
h
l
a
y
e
r
a
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
C
la
s
s
i
fica
tio
n
o
f E
C
G
s
ig
n
a
ls
fo
r
d
etec
tio
n
o
f
a
r
r
h
yth
mia
a
n
d
co
n
g
esti
ve
…
(
R
a
s
h
id
a
h
F
u
n
ke
Ola
n
r
ewa
ju
)
1525
s
h
o
w
n
b
y
(
5
)
a
n
d
(
6
)
,
w
h
e
r
e
n
r
e
p
r
e
s
e
n
t
s
t
h
e
n
u
m
b
e
r
o
f
s
i
z
e
s
o
f
t
h
e
i
m
a
g
e
,
f
r
e
f
e
r
s
t
o
t
h
e
f
i
l
t
e
r
s
i
z
e
a
n
d
s
s
t
a
n
d
s
f
o
r
t
h
e
s
t
r
i
d
e
.
F
o
r
P
a
d
d
i
n
g
w
e
h
a
v
e
a
n
e
x
t
r
a
t
e
r
m
P
a
s
s
h
o
w
n
i
n
(
6
)
.
Fig
u
r
e
3
.
A
le
x
Net
a
r
ch
i
tectu
r
e
(
)
=
−
∗
−
+
1
(
5
)
(
)
=
+
2
−
∗
+
2
−
+1
(
6
)
W
e
ch
an
g
ed
th
e
last
la
y
er
b
e
ca
u
s
e
Alex
Ne
t
is
tr
ain
ed
f
o
r
1
0
0
0
d
if
f
er
en
t
o
b
j
ec
ts
b
u
t
f
o
r
o
u
r
cu
r
r
en
t
p
r
o
b
lem
,
th
e
to
tal
class
i
f
icatio
n
o
b
j
ec
ts
o
r
class
es
ar
e
o
n
ly
t
h
r
ee
.
T
h
at
m
ea
n
s
o
n
l
y
th
r
ee
t
y
p
e
s
o
f
s
ig
n
al
s
m
u
s
t
b
e
d
is
tin
g
u
i
s
h
ed
f
r
o
m
o
n
e
a
n
o
th
er
.
Af
ter
t
h
is
s
tep
,
th
e
d
ee
p
n
eu
r
al
n
e
t
w
o
r
k
is
tr
ai
n
ed
b
y
f
ee
d
in
g
t
h
e
s
y
s
te
m
w
it
h
t
h
e
n
e
w
s
et
o
f
Scalo
g
r
a
m
i
m
a
g
es.
I
n
o
u
r
ex
p
er
i
m
en
t
w
e
h
a
v
e
ch
o
s
en
1
5
0
0
i
m
a
g
es
o
f
tr
ain
in
g
p
u
r
p
o
s
e
an
d
r
est
3
0
0
im
ag
e
s
to
tes
t
th
e
s
y
s
te
m
f
o
r
its
ac
cu
r
ac
y
an
d
ef
f
icie
n
c
y
.
T
h
at
m
ea
n
s
ea
ch
ca
teg
o
r
y
o
f
6
0
0
i
m
a
g
es
w
ill
b
e
s
u
p
p
l
y
i
n
g
5
0
0
i
m
ag
e
s
f
o
r
tr
ain
i
n
g
an
d
1
0
0
im
ag
e
s
f
o
r
test
in
g
.
T
h
ese
la
y
er
s
ar
e
f
in
e
-
t
u
n
ed
as
p
er
s
tep
s
m
e
n
tio
n
ed
b
elo
w
a
n
d
th
u
s
t
h
e
u
s
e
o
f
ap
p
r
o
p
r
iate
o
p
ti
m
izatio
n
p
ar
a
m
eter
s
i
n
t
h
e
C
NN
m
o
d
el
f
o
r
t
h
e
class
i
f
icatio
n
o
f
s
i
g
n
als
i
n
to
t
h
r
ee
d
if
f
er
en
t c
a
teg
o
r
ies
-
AR
R
,
C
HF
,
an
d
N
SR
.
Step
w
i
s
e
p
r
o
ce
d
u
r
e
f
o
r
ap
p
ly
i
n
g
th
e
d
ee
p
C
NN
n
et
w
o
r
k
A
le
x
Net
is
s
u
m
m
ar
ized
as
s
h
o
w
n
in
:
i)
R
ea
d
i
m
a
g
es
f
r
o
m
d
ata
b
ase
f
o
ld
er
u
s
i
n
g
a
MA
T
L
A
B
f
u
n
ctio
n
i
m
ag
eDa
tast
o
r
e
;
ii)
Sp
lit
i
m
ag
e
s
i
n
to
test
i
n
g
a
n
d
tr
ain
i
n
g
s
et
s
;
ii
i)
L
o
ad
p
r
etr
ain
ed
n
et
w
o
r
k
-
A
le
x
Net
;
i
v
)
P
r
eser
v
e
all
lay
er
s
o
f
A
le
x
Net
e
x
ce
p
t
last
3
-
s
in
ce
w
e
w
ill
b
e
u
s
in
g
3
class
e
s
o
n
l
y
;
v
)
Def
i
n
e
t
h
e
th
r
ee
la
y
er
s
;
v
i
)
Set
th
e
tr
ain
i
n
g
o
p
tio
n
s
u
c
h
as
B
atch
Size,
Ma
x
E
p
o
ch
s
,
L
ea
r
n
i
n
g
R
ate,
a
n
d
Valid
atio
n
R
a
te
; v
ii)
T
r
ain
th
e
C
NN
f
o
llo
w
ed
b
y
cla
s
s
i
f
icatio
n
o
f
i
m
ag
e
s
an
d
p
lo
t th
e
co
n
f
u
s
io
n
m
atr
ix
.
A
ca
r
e
f
u
l
s
elec
tio
n
o
f
t
h
e
t
w
o
o
p
tim
izatio
n
p
ar
a
m
eter
s
s
u
c
h
as
b
atch
s
ize
an
d
lea
r
n
in
g
r
at
e
p
lay
s
a
k
e
y
r
o
le
in
th
e
clas
s
i
f
icatio
n
ac
cu
r
ac
ies.
Dif
f
er
e
n
t
v
al
u
es
o
f
th
e
s
e
p
ar
am
eter
s
w
er
e
s
et,
a
n
d
it
w
as
o
b
s
er
v
ed
th
at
a
lear
n
i
n
g
r
ate
p
ar
am
e
ter
h
ad
a
d
ir
ec
t
im
p
ac
t
o
n
t
h
e
s
p
e
ed
o
f
co
n
v
er
g
e
n
ce
an
d
t
h
e
lea
r
n
in
g
r
ate
o
f
0
.
0
0
1
p
r
o
v
ed
to
b
e
id
ea
l
f
o
r
class
if
icatio
n
.
Af
ter
test
i
n
g
th
e
v
ar
i
o
u
s
b
atch
s
ize
p
ar
a
m
eter
s
at
a
f
ix
ed
lear
n
i
n
g
o
f
0
.
0
0
1
,
a
b
atch
s
ize
o
f
2
0
alo
n
g
w
it
h
t
h
e
v
alid
atio
n
f
r
eq
u
e
n
c
y
o
f
1
0
p
r
o
d
u
ce
d
th
e
h
ig
h
cla
s
s
i
f
icatio
n
ac
cu
r
ac
y
.
4.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
Fig
u
r
e
4
(
a)
r
ep
r
esen
ts
th
e
ac
c
u
r
ac
y
p
lo
t
b
ased
o
n
t
h
e
n
u
m
b
er
o
f
iter
atio
n
s
.
Her
e,
ac
cu
r
ac
y
b
asicall
y
r
ep
r
esen
ts
th
e
n
u
m
b
er
o
f
s
u
cc
ess
f
u
l
p
r
ed
ictio
n
s
cla
s
s
i
f
ied
b
y
C
NN.
As
ev
id
en
t
f
r
o
m
t
h
e
g
r
ap
h
th
e
ac
c
u
r
ac
y
s
tar
ts
w
i
th
t
h
e
m
o
d
es
t
v
alu
e
o
f
ab
o
u
t
3
8
%
at
t
h
e
s
tar
t
o
f
t
h
e
iter
atio
n
s
a
n
d
r
ea
ch
e
s
a
v
al
u
e
s
h
o
w
s
a
n
in
cr
ea
s
i
n
g
tr
en
d
w
it
h
m
o
r
e
a
n
d
m
o
r
e
iter
atio
n
s
an
d
r
ea
ch
e
s
a
p
r
o
m
is
i
n
g
v
al
u
e
o
f
9
8
.
7
%
at
th
e
e
n
d
o
f
6
0
0
iter
atio
n
s
d
u
r
in
g
8
th
ep
o
ch
.
T
h
is
tr
en
d
i
n
i
n
cr
ea
s
e
o
f
th
e
ac
c
u
r
ac
y
v
al
u
e
is
b
ec
a
u
s
e
t
h
e
C
N
N
m
o
d
el
is
g
etti
n
g
tr
ain
ed
w
it
h
a
g
r
ea
ter
n
u
m
b
er
o
f
s
ca
lo
g
r
a
m
i
m
a
g
es a
n
d
th
er
e
b
y
th
e
cla
s
s
i
f
icat
io
n
b
ec
o
m
e
s
ea
s
ier
an
d
ac
cu
r
ate
d
u
r
in
g
th
e
co
u
r
s
e
o
f
ti
m
e
o
r
iter
atio
n
s
.
L
o
s
s
p
lo
t
s
h
o
w
n
in
Fi
g
u
r
e
4
(
b
)
as
ex
p
ec
ted
,
s
h
o
w
s
e
x
ac
tl
y
th
e
o
p
p
o
s
ite
tr
en
d
w
h
en
co
m
p
ar
ed
w
it
h
t
h
e
ac
cu
r
ac
y
p
lo
t.
I
n
it
i
all
y
r
ate
i
s
m
u
c
h
h
ig
h
er
a
n
d
g
r
ad
u
all
y
d
ec
r
ea
s
e
s
w
it
h
t
h
e
in
cr
ea
s
e
in
t
h
e
n
u
m
b
e
r
o
f
iter
atio
n
s
(
tr
ain
i
n
g
)
.
F
i
g
u
r
e
5
r
e
p
r
e
s
e
n
t
s
t
h
e
c
o
n
f
u
s
i
o
n
m
a
t
r
i
x
t
h
a
t
w
e
h
a
v
e
a
c
h
i
e
v
e
d
t
h
r
o
u
g
h
t
h
i
s
r
e
s
e
a
r
c
h
.
H
e
r
e
w
e
c
a
n
s
e
e
t
h
e
t
h
r
e
e
c
l
a
s
s
e
s
s
u
c
h
a
s
a
r
r
,
c
h
f
a
n
d
n
s
r
.
F
o
r
A
R
R
c
l
a
s
s
,
9
8
o
u
t
o
f
1
0
0
a
r
e
s
u
c
c
e
s
s
f
u
l
l
y
c
l
a
s
s
i
f
i
e
d
a
s
a
r
r
w
h
i
c
h
m
a
k
es
a
n
a
c
c
u
r
a
c
y
p
e
r
c
e
n
t
a
g
e
o
f
9
8
%
w
h
e
r
e
a
s
t
h
e
tw
o
c
a
s
e
s
o
f
a
r
r
w
e
r
e
m
i
s
i
n
t
e
r
p
r
e
t
e
d
b
y
t
h
e
c
l
a
s
s
i
f
i
e
r
a
s
n
s
r
.
F
o
r
t
h
e
n
s
r
c
l
a
s
s
,
9
8
o
u
t
1
0
0
c
a
s
e
s
w
e
r
e
s
u
c
c
e
s
s
f
u
l
l
y
c
l
a
s
s
i
f
i
e
d
b
y
t
h
e
C
N
N
m
o
d
e
l
w
h
i
c
h
c
o
n
t
r
i
b
u
t
e
s
t
o
t
h
e
s
u
c
c
e
s
s
p
e
r
c
e
n
t
a
g
e
o
f
9
8
%
.
R
e
s
u
l
t
s
o
b
t
a
i
n
e
d
f
o
r
n
s
r
w
e
r
e
p
r
o
m
i
s
i
n
g
a
n
d
t
h
e
c
l
a
s
s
i
f
i
e
r
c
o
u
l
d
i
d
e
n
t
i
f
y
a
l
l
t
h
e
1
0
0
c
a
s
e
s
a
s
a
r
r
w
h
i
c
h
m
a
k
e
s
a
s
u
c
c
e
s
s
p
e
r
c
e
n
t
a
g
e
o
f
1
0
0
%
.
O
v
e
r
a
l
l
a
v
e
r
a
g
e
s
u
c
c
e
s
s
p
e
r
c
e
n
t
a
g
e
o
f
t
h
e
m
o
d
e
l
u
s
e
d
t
h
u
s
s
t
a
n
d
s
a
t
9
8
.
7
%
.
T
a
b
l
e
1
s
h
o
w
s
t
h
e
c
o
m
p
a
r
i
s
o
n
o
u
r
p
r
o
p
o
s
e
d
s
t
r
a
t
e
g
y
o
f
c
l
a
s
s
i
f
y
i
n
g
t
h
e
E
C
G
s
i
g
n
a
l
s
w
i
t
h
t
h
e
w
o
r
k
d
o
n
e
b
y
o
t
h
e
r
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2502
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
22
,
No
.
3
,
J
u
n
e
2
0
2
1
:
1
5
2
0
-
1
5
2
8
1526
r
e
s
e
a
r
c
h
e
r
s
a
n
d
t
h
e
a
c
c
u
r
a
c
y
r
e
s
u
l
t
o
f
9
8
.
7
%
t
e
s
t
i
f
i
e
s
t
h
e
f
a
c
t
t
h
a
t
c
o
n
v
e
r
s
i
o
n
o
f
1
D
s
i
g
n
a
l
s
t
o
2
D
s
c
a
l
o
g
r
am
i
m
a
g
e
s
u
s
i
n
g
c
o
n
v
o
l
u
t
i
o
n
a
l
w
a
v
e
l
e
t
t
r
a
n
s
f
o
r
m
(
C
W
T
)
p
l
a
y
s
a
p
i
v
o
t
a
l
r
o
l
e
i
n
f
u
r
t
h
e
r
e
x
t
r
a
c
t
i
n
g
t
h
e
f
e
a
t
u
r
e
s
a
n
d
c
l
a
s
s
i
f
y
i
n
g
t
h
e
im
a
g
e
s
a
c
c
u
r
a
t
e
l
y
u
s
i
n
g
t
r
a
n
s
f
e
r
l
e
a
r
n
i
n
g
m
o
d
e
l
.
(
a)
(
b
)
Fig
u
r
e
4
.
Th
ese
f
ig
u
r
e
s
ar
e
:
(
a)
ac
cu
r
ac
y
(
%
)
Vs.
n
u
m
b
er
o
f
iter
atio
n
s
p
lo
t
an
d
(
b
)
l
o
s
s
p
lo
t b
a
s
ed
o
n
th
e
n
u
m
b
er
o
f
iter
atio
n
s
Fig
u
r
e
5
.
C
o
n
f
u
s
io
n
m
atr
ix
o
f
th
e
C
N
N
n
et
w
o
r
k
r
ep
r
ese
n
ti
n
g
s
u
cc
ess
a
n
d
f
ail
u
r
e
r
ates
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
C
la
s
s
i
fica
tio
n
o
f E
C
G
s
ig
n
a
ls
fo
r
d
etec
tio
n
o
f
a
r
r
h
yth
mia
a
n
d
co
n
g
esti
ve
…
(
R
a
s
h
id
a
h
F
u
n
ke
Ola
n
r
ewa
ju
)
1527
T
ab
le
1
.
C
o
m
p
ar
is
o
n
w
i
th
o
t
h
er
ex
is
ti
n
g
ap
p
r
o
ac
h
es
L
i
t
e
r
a
t
u
r
e
P
r
e
p
r
o
c
e
ssi
n
g
F
e
a
t
u
r
e
Ex
t
r
a
c
t
i
o
n
C
l
a
ssi
f
i
c
a
t
i
o
n
A
c
c
u
r
a
c
y
Jo
sh
i
e
t
a
l
.
[
2
8
]
W
a
v
e
l
e
t
P
C
A
+
W
a
v
e
l
e
t
S
V
M
8
6
.
4
%
Z
h
u
e
t
a
l
.
[
1
6
]
M
o
r
p
h
o
l
o
g
i
c
a
l
F
i
l
t
e
r
P
C
A
S
V
M
8
7
.
5
%
Y
i
n
g
e
t
a
l
[
2
9
]
M
o
v
i
n
g
a
v
e
r
a
g
e
me
t
h
o
d
w
i
t
h
p
r
e
d
e
t
e
r
mi
n
e
d
w
i
n
d
o
w
G
i
b
b
s Sa
mp
l
i
n
g
A
l
g
o
r
i
t
h
m
H
i
d
d
e
n
M
a
r
k
o
v
M
o
d
e
l
8
8
.
3
3
%
Jo
se
e
t
a
l
.
[
3
0
]
W
a
v
e
l
e
t
W
a
v
e
l
e
t
P
N
N
9
2
.
7
%
Z
u
b
a
i
r
e
t
a
l
.
[
3
1
]
B
a
n
d
p
a
ss
F
i
l
t
e
r
C
N
N
S
o
f
t
M
a
x
9
2
.
7
%
A
c
h
a
r
y
a
e
t
a
l
.
[
3
2
]
D
a
u
b
e
c
h
i
e
s w
a
v
e
l
e
t
P
a
n
T
o
mp
k
i
n
s
9
-
L
a
y
e
r
C
N
N
9
3
.
4
7
%
I
smai
e
l
e
t
a
l
.
[
3
3
]
D
i
g
i
t
a
l
F
i
l
t
e
r
s
D
i
scre
t
e
W
a
v
e
l
e
t
N
N
W
s
9
4
%
Ö
z
a
l
e
t
a
l
.
[
3
4
]
C
o
n
st
a
n
t
C
o
mp
o
n
e
n
t
R
e
d
u
c
t
i
o
n
R
e
sca
l
e
d
R
a
w
D
a
t
a
1
-
D
C
N
N
9
5
.
2
0
%
El
i
f
,
e
t
a
l
.
[
2
4
]
1
D
t
o
2
D
T
r
a
n
sf
o
r
ma
t
i
o
n
C
o
n
v
o
l
u
t
i
o
n
C
N
N
M
o
d
e
l
9
7
.
2
4
%
P
r
o
p
o
se
d
A
n
a
l
y
t
i
c
a
l
M
o
r
l
e
t
(
a
mo
r
)
C
W
T
C
N
N
-
A
l
e
x
N
e
t
9
8
.
7
%
5.
CO
NCLU
SI
O
N
I
n
t
h
i
s
w
o
r
k
,
w
e
p
r
o
p
o
s
e
d
a
c
l
a
s
s
i
f
i
c
a
t
i
o
n
m
o
d
e
l
b
a
s
e
d
o
n
c
o
n
t
i
n
u
o
u
s
w
a
v
e
l
e
t
t
r
a
n
s
f
o
r
m
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
n
e
t
w
o
r
k
t
h
a
t
c
o
u
l
d
c
l
a
s
s
i
f
y
E
C
G
s
i
g
n
a
l
s
i
n
t
o
t
h
r
e
e
d
i
s
t
i
n
c
t
c
l
a
s
s
e
s
s
u
c
h
a
s
N
S
R
,
C
H
F
a
n
d
A
R
R
.
E
C
G
s
i
g
n
a
l
s
w
e
r
e
o
b
t
a
i
n
e
d
f
r
o
m
M
I
T
-
B
I
H
a
n
d
B
M
D
M
C
d
a
t
a
b
a
s
e
s
a
v
a
i
l
a
b
l
e
o
n
l
i
n
e
a
n
d
p
r
e
p
r
o
c
e
s
s
e
d
u
s
i
n
g
A
n
a
l
y
t
i
c
a
l
M
o
r
l
e
t
f
i
l
t
e
r
f
o
l
l
o
w
e
d
b
y
c
o
n
v
e
r
s
i
o
n
o
f
a
l
l
9
0
0
o
n
e
d
i
m
e
n
s
i
o
n
a
l
r
e
c
o
r
d
i
n
g
s
i
n
t
o
2
D
R
G
B
s
c
a
l
o
g
r
a
m
s
.
T
h
e
s
e
r
e
s
u
l
t
a
n
t
im
a
g
e
s
w
e
r
e
p
a
s
s
e
d
t
h
r
o
u
g
h
a
s
e
r
i
e
s
o
f
c
o
n
v
o
l
u
t
i
o
n
a
l
l
a
y
e
r
s
o
f
a
d
e
e
p
n
e
u
r
a
l
n
e
tw
o
r
k
f
o
l
l
o
w
e
d
b
y
t
e
s
t
i
n
g
a
n
d
t
r
a
i
n
i
n
g
t
h
e
d
a
t
a
s
e
t
.
R
e
s
u
l
t
s
s
h
o
w
t
h
a
t
t
h
e
d
e
t
e
c
t
i
o
n
o
f
h
e
a
r
t
c
o
n
d
i
t
i
o
n
s
f
r
o
m
a
n
E
C
G
s
i
g
n
a
l
s
b
y
v
i
r
t
u
e
o
f
C
W
T
f
o
l
l
o
w
e
d
b
y
d
e
e
p
n
e
u
r
a
l
n
e
tw
o
r
k
s
m
o
d
e
l
c
a
n
r
e
a
c
h
a
n
a
v
e
r
a
g
e
a
c
c
u
r
a
c
y
o
f
9
8
.
7
%
a
t
a
l
e
a
r
n
i
n
g
r
a
t
e
o
f
0
.
0
0
1
.
W
e
h
a
v
e
a
l
s
o
c
o
m
p
a
r
e
d
o
u
r
r
e
s
u
l
t
s
w
i
t
h
o
t
h
e
r
r
e
s
e
a
r
c
h
e
r
s
a
n
d
t
h
e
c
o
m
p
a
r
i
s
o
n
t
a
b
l
e
s
i
g
n
i
f
i
e
s
t
h
a
t
t
h
e
f
a
c
t
t
h
a
t
c
o
n
v
e
r
s
i
o
n
o
f
1
D
i
m
a
g
e
s
i
n
t
o
2
D
s
c
a
l
o
g
r
a
m
s
d
u
r
i
n
g
t
h
e
p
r
e
p
r
o
c
e
s
s
i
n
g
s
t
a
g
e
y
i
e
l
d
s
b
e
t
t
e
r
r
e
s
u
l
t
s
t
h
a
n
t
h
e
c
o
n
v
e
n
t
i
o
n
a
l
w
a
y
o
f
e
x
t
r
a
c
t
i
n
g
t
h
e
m
o
r
p
h
o
l
o
g
i
c
a
l
f
e
a
t
u
r
e
s
f
r
o
m
E
C
G
s
i
g
n
a
l
s
.
T
h
e
o
v
e
r
a
l
l
2
-
D
C
N
N
d
e
e
p
l
e
a
r
n
i
n
g
m
o
d
e
l
s
h
a
v
e
h
i
g
h
c
l
a
s
s
i
f
i
c
a
t
i
o
n
a
c
c
u
r
a
c
i
e
s
t
h
e
r
e
b
y
c
a
n
b
e
s
a
f
e
l
y
u
s
e
d
f
o
r
d
i
a
g
n
o
s
i
s
o
f
a
r
r
h
y
t
h
m
i
a
a
n
d
a
u
t
o
m
a
t
i
c
c
l
a
s
s
i
f
i
c
a
t
i
o
n
i
n
t
h
e
m
e
d
i
c
a
l
a
p
p
l
i
c
a
t
i
o
n
s
i
n
g
e
n
e
r
a
l
.
ACK
NO
WL
E
D
G
E
M
E
NT
S
W
e
w
o
u
ld
li
k
e
to
ac
k
n
o
w
led
g
e
th
e
s
u
p
p
o
r
t
g
iv
e
n
b
y
t
h
e
Min
i
s
tr
y
o
f
H
ig
h
er
E
d
u
ca
tio
n
Ma
la
y
s
ia
(
K
eme
n
teri
a
n
P
en
d
id
ika
n
Tin
g
g
i
)
th
r
o
u
g
h
F
u
n
d
a
m
e
n
tal
R
esear
ch
Gr
an
t
Sc
h
e
m
e.
T
h
is
r
esear
ch
is
m
ad
e
p
o
s
s
ib
le
an
d
f
u
n
d
ed
u
n
d
er
t
h
e
FR
G
S1
9
-
150
-
0
7
5
9
(
FR
GS/
1
/2
0
1
9
/
T
K
0
4
/UI
A
M/0
2
/8
)
en
t
itled
th
e
Ne
w
No
n
-
I
n
v
a
s
iv
e
T
ec
h
n
iq
u
e
v
ia
P
h
y
s
i
o
lo
g
ical
Sig
n
al
s
an
d
I
n
telli
g
e
n
ce
Ma
ch
i
n
e
L
ea
r
n
i
n
g
f
o
r
R
a
p
id
C
lass
i
f
icatio
n
o
f
Stre
s
s
L
e
v
el
lead
b
y
P
r
in
cip
al
I
n
v
e
s
tig
a
to
r
,
S.
No
o
r
j
an
n
ah
I
b
r
ah
i
m
.
RE
F
E
R
E
NC
E
S
[1
]
S
.
P
.
Ra
jam
h
o
a
n
a
,
C
.
A
.
De
v
i,
K.
Um
a
m
a
h
e
s
w
a
ri,
R.
Kiru
b
a
,
K.
Ka
ru
n
y
a
,
a
n
d
R.
De
e
p
ik
a
,
“
A
n
a
l
y
sis
o
f
Ne
u
ra
l
Ne
tw
o
rk
s
Ba
se
d
He
a
rt
Dise
a
s
e
P
re
d
icti
o
n
S
y
ste
m
,
”
2
0
1
8
1
1
t
h
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
Hu
ma
n
S
y
ste
m
In
ter
a
c
ti
o
n
(
HS
I)
,
2
0
1
8
,
p
p
.
2
3
3
-
2
3
9
,
d
o
i:
1
0
.
1
1
0
9
/HS
I.
2
0
1
8
.
8
4
3
1
1
5
3
.
[2
]
S
.
Ro
o
sta
e
e
a
n
d
H.
R.
G
h
a
ff
a
r
y
,
“
Dia
g
n
o
sis
o
f
h
e
a
rt
d
ise
a
se
b
a
se
d
o
n
m
e
ta
h
e
u
risti
c
a
lg
o
rit
h
m
s
a
n
d
c
l
u
ste
rin
g
m
e
th
o
d
s,
”
J
o
u
r
n
a
l
o
f
El
e
c
trica
l
a
n
d
Co
m
p
u
ter
En
g
in
e
e
rin
g
In
n
o
v
a
ti
o
n
s
(
J
ECE
I)
,
v
o
l.
4
,
n
o
.
2
,
p
p
.
1
0
5
-
1
1
0
,
2
0
1
6
,
d
o
i:
1
0
.
2
2
0
6
1
/JEC
EI.
2
0
1
6
.
5
7
0
.
[3
]
U.
R.
A
c
h
a
r
y
a
,
H.
F
u
ji
ta,
S
.
L
.
O
h
,
Y.
Ha
g
iw
a
ra
,
J.
H.
T
a
n
,
M
.
A
d
a
m
,
a
n
d
R.
S
.
T
a
n
,
“
De
e
p
c
o
n
v
o
lu
ti
o
n
a
l
n
e
u
ra
l
n
e
tw
o
rk
f
o
r
th
e
a
u
to
m
a
ted
d
iag
n
o
sis
o
f
c
o
n
g
e
stiv
e
h
e
a
rt
f
a
il
u
re
u
sin
g
ECG
sig
n
a
ls,
”
Ap
p
li
e
d
In
tell
ig
e
n
c
e
,
v
o
l.
4
9
,
n
o
.
1
,
p
p
.
16
-
27
,
2
0
1
9
,
d
o
i:
1
0
.
1
0
0
7
/s1
0
4
8
9
-
0
1
8
-
1
1
7
9
-
1
.
[4
]
D.
P
a
n
d
it
,
Z.
L
i,
L
.
Ch
e
n
g
y
u
,
S
.
Ch
a
tt
o
p
a
d
h
y
a
y
,
N.
A
sl
a
m
,
a
n
d
L
.
C.
P
e
n
g
,
“
A
li
g
h
twe
ig
h
t
QRS
d
e
tec
to
r
f
o
r
sin
g
le
lea
d
ECG
sig
n
a
ls
u
sin
g
a
m
a
x
-
m
in
d
iff
e
re
n
c
e
a
lg
o
rit
h
m
,
”
Co
mp
u
ter
me
th
o
d
s
a
n
d
p
ro
g
ra
ms
i
n
b
i
o
me
d
icin
e
,
v
o
l.
1
4
4
,
p
p
.
61
-
75
,
2
0
1
7
,
d
o
i:
1
0
.
1
0
1
6
/
j.
c
m
p
b
.
2
0
1
7
.
0
2
.
0
2
8
.
[5
]
S
.
N
a
h
a
k
a
n
d
G
.
S
a
h
a
,
“
A
F
u
s
i
o
n
B
a
s
e
d
C
l
a
ss
if
i
c
a
t
i
o
n
o
f
N
o
rm
a
l
,
A
r
r
h
y
t
h
m
i
a
a
n
d
C
o
n
g
e
s
t
i
v
e
H
e
a
r
t
F
a
i
l
u
r
e
i
n
E
CG
,
”
2
0
2
0
N
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
C
o
m
m
u
n
i
c
a
t
i
o
n
s
(
N
C
C)
,
2
0
2
0
,
p
p
.
1
-
6
,
d
o
i
:
1
0
.
1
1
0
9
/
N
C
C
4
8
6
4
3
.
2
0
2
0
.
9
0
5
6
0
9
5
.
[6
]
V
.
G
u
p
ta
a
n
d
M
.
M
i
tt
a
l,
“
QRS
c
o
m
p
lex
d
e
tec
ti
o
n
u
si
n
g
S
T
F
T
,
c
h
a
o
s
a
n
a
ly
sis,
a
n
d
P
CA
in
sta
n
d
a
r
d
a
n
d
re
a
l
-
ti
m
e
ECG
d
a
tab
a
se
s,
”
J
o
u
rn
a
l
o
f
th
e
In
stit
u
ti
o
n
o
f
E
n
g
in
e
e
rs
(
In
d
i
a
)
:
S
e
rie
s
B
,
v
o
l
.
1
0
0
,
n
o
.
5
,
p
p
.
489
-
4
9
7
,
2
0
1
9
,
d
o
i:
1
0
.
1
0
0
7
/s4
0
0
3
1
-
0
1
9
-
0
0
3
9
8
-
9.
[7
]
J.
M
.
Jo
h
n
so
n
a
n
d
T
.
M
.
K
h
o
sh
g
o
f
taa
r,
“
S
u
rv
e
y
o
n
d
e
e
p
lea
rn
i
n
g
w
it
h
c
las
s
im
b
a
lan
c
e
,
”
J
o
u
rn
a
l
o
f
Bi
g
Da
ta
,
v
o
l.
6
,
n
o
.
1
,
p
p
.
1
-
54
,
2
0
1
9
,
d
o
i:
1
0
.
1
1
8
6
/s
4
0
5
3
7
-
0
1
9
-
0
1
9
2
-
5.
[8
]
U.
R.
A
c
h
a
r
y
a
,
H.
F
u
ji
ta,
S.
L
.
Oh
a
,
Y.
Ha
g
i
w
a
ra
,
J.
H.
T
a
n
,
a
n
d
M
.
A
d
a
m
,
“
A
p
p
li
c
a
ti
o
n
o
f
d
e
e
p
c
o
n
v
o
l
u
ti
o
n
a
l
n
e
u
ra
l
n
e
tw
o
rk
f
o
r
a
u
to
m
a
ted
d
e
tec
ti
o
n
o
f
m
y
o
c
a
rd
i
a
l
in
f
a
rc
ti
o
n
u
si
n
g
ECG
sig
n
a
ls,
”
In
fo
rm
a
ti
o
n
S
c
ien
c
e
s
415
-
4
1
6
,
1
9
0
-
1
9
8
,
No
v
e
m
b
e
r
2
0
1
7
,
d
o
i:
1
0
.
1
0
1
6
/j
.
in
s.
2
0
1
7
.
0
6
.
0
2
7
.
[9
]
H.
L
iu
,
D.
Ch
e
n
,
a
n
d
G
.
S
u
n
,
“
De
tec
ti
o
n
o
f
F
e
tal
EC
G
R
W
a
v
e
f
ro
m
S
in
g
le
-
Lea
d
A
b
d
o
m
in
a
l
ECG
Us
in
g
a
Co
m
b
in
a
ti
o
n
o
f
RR
T
i
m
e
-
S
e
r
ies
S
m
o
o
th
in
g
a
n
d
T
e
m
p
late
-
M
a
tch
in
g
A
p
p
ro
a
c
h
,
”
IEE
E
A
c
c
e
ss
,
v
o
l.
7
,
p
p
.
6
6
6
3
3
-
6
6
6
4
3
,
2
0
1
9
,
d
o
i:
1
0
.
1
1
0
9
/A
CCES
S
.
2
0
1
9
.
2
9
1
7
8
2
6
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2502
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
22
,
No
.
3
,
J
u
n
e
2
0
2
1
:
1
5
2
0
-
1
5
2
8
1528
[1
0
]
T
.
T
u
n
c
e
r,
S
.
Do
g
a
n
,
P
.
P
ław
iak
,
a
n
d
U.
R.
A
c
h
a
r
y
a
,
“
A
u
to
m
a
te
d
a
rrh
y
t
h
m
ia
d
e
tec
ti
o
n
u
sin
g
n
o
v
e
l
h
e
x
a
d
e
c
i
m
a
l
lo
c
a
l
p
a
tt
e
rn
a
n
d
m
u
lt
il
e
v
e
l
w
a
v
e
let
tran
sf
o
rm
w
it
h
ECG
sig
n
a
ls,
”
Kn
o
wled
g
e
-
Ba
se
d
S
y
ste
ms
,
v
o
l.
1
8
6
,
p
.
1
0
4
9
2
3
,
De
c
.
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/j
.
k
n
o
sy
s.
2
0
1
9
.
1
0
4
9
2
3
.
[1
1
]
J.
P
.
V.
M
a
d
e
iro
,
E.
M
.
B.
S
a
n
t
o
s,
P
.
C.
Co
rtez
,
J.
H.
S
.
F
e
li
x
,
a
n
d
F
.
S
.
S
c
h
li
n
d
w
e
in
,
“
Ev
a
lu
a
ti
n
g
Ga
u
ss
ian
a
n
d
Ra
y
leig
h
-
Ba
s
e
d
M
a
th
e
m
a
ti
c
a
l
M
o
d
e
ls
f
o
r
T
a
n
d
P
-
w
a
v
e
s
in
ECG,
”
in
IEE
E
L
a
ti
n
Ame
ric
a
T
ra
n
sa
c
ti
o
n
s
,
v
o
l
.
1
5
,
n
o
.
5
,
p
p
.
8
4
3
-
8
5
3
,
M
a
y
2
0
1
7
,
d
o
i:
1
0
.
1
1
0
9
/T
LA
.
2
0
1
7
.
7
9
1
0
1
9
7
.
[1
2
]
A
.
Ke
n
n
e
d
y
,
D.
D.
F
in
lay
,
D.
Gu
ld
e
n
r
in
g
,
R.
R.
Bo
n
d
,
K.
M
o
ra
n
,
a
n
d
J.
M
c
L
a
u
g
h
li
n
,
“
A
u
to
m
a
t
e
d
d
e
tec
ti
o
n
o
f
a
tri
a
l
f
ib
ril
latio
n
u
sin
g
RR
i
n
terv
a
ls
a
n
d
m
u
lt
iv
a
riate
-
b
a
se
d
c
las
si
fica
ti
o
n
,
”
J
o
u
rn
a
l
o
f
e
lec
tro
c
a
rd
i
o
lo
g
y
,
v
o
l.
4
9
,
n
o
.
6
,
p
p
.
8
7
1
-
8
7
6
,
De
c
.
2
0
1
6
,
d
o
i:
1
0
.
1
0
1
6
/j
.
jele
c
tro
c
a
rd
.
2
0
1
6
.
0
7
.
0
3
3
.
[1
3
]
H.
A
lq
u
ra
a
n
,
A
.
M
.
A
lq
u
d
a
h
,
A
b
u
-
Qa
sm
ieh
,
A
.
A
l
-
Ba
d
a
rn
e
h
,
a
n
d
S
.
A
lm
a
sh
a
q
b
e
h
,
“
ECG
c
las
sif
ica
ti
o
n
u
sin
g
h
ig
h
e
r
o
r
d
e
r
sp
e
c
tral
e
stim
a
ti
o
n
a
n
d
d
e
e
p
lea
rn
i
n
g
tec
h
n
i
q
u
e
s,
”
Ne
u
ra
l
Ne
tw
o
rk
W
o
rld
,
v
o
l.
2
9
,
n
o
.
4
,
p
p
.
2
0
7
-
2
1
9
,
2
0
1
9
,
d
o
i:
1
0
.
1
4
3
1
1
/NNW
.
2
0
1
9
.
2
9
.
0
1
4
.
[1
4
]
R.
G
.
Ku
m
a
r
a
n
d
Y.
S
.
K
u
m
a
ra
s
wa
m
y
,
“
In
v
e
sti
g
a
ti
n
g
c
a
r
d
iac
a
rrh
y
th
m
ia
in
ECG
u
si
n
g
ra
n
d
o
m
f
o
re
st
c
las
si
f
ica
ti
o
n
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
C
o
mp
u
ter
A
p
p
li
c
a
ti
o
n
s
,
v
o
l.
37
,
n
o
.
4
,
p
p
.
31
-
34
,
Ja
n
.
2
0
1
2
.
[1
5
]
M
.
T
h
o
m
a
s,
M
.
Kr.
Da
s,
a
n
d
S
.
A
ri
,
“
A
u
to
m
a
ti
c
EC
G
a
rrh
y
th
m
ia
c
las
si
f
ica
ti
o
n
u
sin
g
d
u
a
l
tree
c
o
m
p
lex
w
a
v
e
let
-
b
a
se
d
f
e
a
tu
re
s,
”
AEU
-
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
tro
n
ics
a
n
d
Co
mm
u
n
ica
ti
o
n
s
,
v
o
l.
6
9
,
n
o
.
4
,
p
p
.
7
1
5
-
7
2
1
,
A
p
r
.
2
0
1
5
,
d
o
i:
1
0
.
1
0
1
6
/
j.
a
e
u
e
.
2
0
1
4
.
1
2
.
0
1
3
.
[1
6
]
W
.
Zh
u
,
X
.
C
h
e
n
,
Y.
W
a
n
g
,
a
n
d
L
.
Wan
g
,
“
A
rrh
y
th
m
ia
R
e
c
o
g
n
it
io
n
a
n
d
Clas
sif
ica
ti
o
n
Us
in
g
EC
G
M
o
rp
h
o
l
o
g
y
a
n
d
S
e
g
m
e
n
t
F
e
a
tu
re
A
n
a
l
y
sis,
”
IEE
E/
ACM
T
ra
n
sa
c
ti
o
n
s
o
n
C
o
mp
u
ta
ti
o
n
a
l
Bi
o
lo
g
y
a
n
d
Bi
o
i
n
f
o
rm
a
ti
c
s
,
v
o
l.
1
6
,
n
o
.
1
,
p
p
.
1
3
1
-
1
3
8
,
1
Ja
n
.
-
F
e
b
.
2
0
1
9
,
d
o
i:
1
0
.
1
1
0
9
/T
CBB.2
0
1
8
.
2
8
4
6
6
1
1
.
[1
7
]
R.
S
a
in
i,
N
.
Bin
d
a
l,
a
n
d
P
.
Ba
n
sa
l,
“
Clas
sif
ic
a
ti
o
n
o
f
h
e
a
rt
d
ise
a
se
s
f
ro
m
EC
G
sig
n
a
ls
u
sin
g
w
a
v
e
le
t
tran
sf
o
rm
a
n
d
k
NN
c
las
si
f
ier,
”
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
C
o
mp
u
ti
n
g
,
Co
mm
u
n
ica
ti
o
n
&
Au
to
ma
ti
o
n
,
2
0
1
5
,
p
p
.
1
2
0
8
-
1
2
1
5
,
d
o
i:
1
0
.
1
1
0
9
/CCA
A
.
2
0
1
5
.
7
1
4
8
5
6
1
.
[1
8
]
X
in
-
Ch
e
n
g
Ca
o
,
Bin
-
Qia
n
g
Ch
e
n
,
B.
Ya
o
,
a
n
d
W
a
n
g
-
P
e
n
g
He
,
“
Co
m
b
in
in
g
tran
sla
ti
o
n
-
i
n
v
a
rian
t
w
a
v
e
let
f
ra
m
e
s
a
n
d
c
o
n
v
o
l
u
ti
o
n
a
l
n
e
u
ra
l
n
e
tw
o
rk
f
o
r
in
telli
g
e
n
t
to
o
l
w
e
a
r
sta
te
id
e
n
ti
f
ica
ti
o
n
,
”
C
o
mp
u
ter
s
in
In
d
u
stry
,
v
o
l.
1
0
6
,
pp.
71
-
84
,
A
p
ril
2
0
1
9
,
d
o
i:
1
0
.
1
0
1
6
/j
.
c
o
m
p
in
d
.
2
0
1
8
.
1
2
.
0
1
8
.
[1
9
]
R.
S
a
ll
o
u
m
a
n
d
C
.
J.
Ku
o
,
“
EC
G
-
b
a
se
d
b
io
m
e
tri
c
s
u
sin
g
re
c
u
rre
n
t
n
e
u
ra
l
n
e
tw
o
rk
s,
”
2
0
1
7
IEE
E
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Aco
u
stics
,
S
p
e
e
c
h
a
n
d
S
i
g
n
a
l
Pr
o
c
e
ss
in
g
(
ICAS
S
P)
,
2
0
1
7
,
p
p
.
2
0
6
2
-
2
0
6
6
,
d
o
i:
1
0
.
1
1
0
9
/ICA
S
S
P
.
2
0
1
7
.
7
9
5
2
5
1
9
.
[2
0
]
A
.
M
o
sta
y
e
d
,
J.
L
u
o
,
X
.
S
h
u
,
a
n
d
W
.
W
e
e
,
“
Clas
sif
ic
a
ti
o
n
o
f
1
2
-
lea
d
ECG
sig
n
a
ls
w
it
h
Bi
-
d
ir
e
c
ti
o
n
a
l
L
S
T
M
n
e
tw
o
rk
,
”
a
rXiv p
re
p
rin
t
a
rXiv:1
8
1
1
.
0
2
0
9
0
,
No
v
.
2
0
1
8
.
[2
1
]
S
.
Kira
n
y
a
z
,
T
.
In
c
e
,
a
n
d
M
.
Ga
b
b
o
u
j,
“
Re
a
l
-
T
i
m
e
P
a
ti
e
n
t
-
S
p
e
c
if
ic
EC
G
Cla
ss
i
f
ica
ti
o
n
b
y
1
-
D
Co
n
v
o
l
u
t
io
n
a
l
Ne
u
ra
l
Ne
tw
o
rk
s,
”
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.
6
3
,
n
o
.
3
,
p
p
.
6
6
4
-
6
7
5
,
M
a
r
.
2
0
1
6
,
d
o
i:
1
0
.
1
1
0
9
/T
BM
E.
2
0
1
5
.
2
4
6
8
5
8
9
.
[2
2
]
D.
L
i,
J.
Zh
a
n
g
,
Q.
Z
h
a
n
g
,
a
n
d
X.
W
e
i,
“
Clas
si
f
ica
ti
o
n
o
f
ECG
si
g
n
a
ls
b
a
se
d
o
n
1
D
c
o
n
v
o
l
u
ti
o
n
n
e
u
ra
l
n
e
tw
o
rk
,
”
2
0
1
7
I
EE
E
1
9
th
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
e
-
He
a
lt
h
Ne
two
rk
in
g
,
Ap
p
li
c
a
ti
o
n
s
a
n
d
S
e
rv
ice
s
(
He
a
lt
h
c
o
m)
,
2
0
1
7
,
p
p
.
1
-
6
,
d
o
i:
1
0
.
1
1
0
9
/He
a
lt
h
C
o
m
.
2
0
1
7
.
8
2
1
0
7
8
4
.
[2
3
]
W
.
Yin
,
X
.
Ya
n
g
,
L
.
Z
h
a
n
g
,
a
n
d
E.
Ok
i,
“
ECG
M
o
n
it
o
rin
g
S
y
ste
m
In
teg
ra
ted
w
it
h
IR
-
UW
B
Ra
d
a
r
Ba
se
d
o
n
C
NN,
”
IEE
E
Acc
e
ss
,
v
o
l.
4
,
p
p
.
6
3
4
4
-
6
3
5
1
,
2
0
1
6
,
d
o
i:
1
0
.
1
1
0
9
/A
CCES
S
.
2
0
1
6
.
2
6
0
8
7
7
7
.
[2
4
]
E.
Iz
c
i,
M
.
A
.
Oz
d
e
m
ir,
M
.
De
g
irme
n
c
i
,
a
n
d
A
.
Ak
a
n
,
“
Ca
rd
iac
A
rrh
y
th
m
ia
De
te
c
ti
o
n
f
ro
m
2
D
ECG
I
m
a
g
e
s
b
y
Us
in
g
De
e
p
L
e
a
rn
in
g
Tec
h
n
iq
u
e
,
”
2
0
1
9
T
IPT
EKNO
,
2
0
1
9
,
p
p
.
1
-
4
,
d
o
i:
1
0
.
1
1
0
9
/T
I
P
T
EKNO
.
2
0
1
9
.
8
8
9
5
0
1
1
.
[2
5
]
A
.
Ullah
,
S.
M
.
A
n
w
a
r
,
M
.
Bil
a
l,
a
n
d
R.
M
.
M
e
h
m
o
o
d
,
“
Clas
sif
ica
t
io
n
o
f
a
rrh
y
th
m
ia b
y
u
sin
g
d
e
e
p
lea
rn
in
g
w
it
h
2
-
D E
C
G
sp
e
c
tral
i
m
a
g
e
re
p
re
se
n
ta
ti
o
n
,
”
Rem
o
te S
e
n
sin
g
,
v
o
l.
1
2
,
n
o
.
10
,
p
.
1
6
8
5
,
2
0
2
0
,
d
o
i:
1
0
.
3
3
9
0
/
rs1
2
1
0
1
6
8
5
.
[2
6
]
C.
M
a
teo
a
n
d
J.
A
.
T
a
lav
e
r
a
,
“
S
h
o
rt
-
ti
m
e
F
o
u
rier
tran
sf
o
rm
w
it
h
t
h
e
w
in
d
o
w
siz
e
f
ix
e
d
in
th
e
f
re
q
u
e
n
c
y
d
o
m
a
in
,
”
Dig
it
a
l
S
i
g
n
a
l
Pr
o
c
e
ss
in
g
,
v
o
l.
77
,
p
p
.
1
3
-
2
1
,
J
u
n
.
2
0
1
8
,
d
o
i
:
1
0
.
1
0
1
6
/j
.
d
sp
.
2
0
1
7
.
1
1
.
0
0
3
.
[2
7
]
L
.
Zh
a
o
,
Q.
L
i
,
Y.
Zh
a
n
g
,
H.
W
a
n
g
,
a
n
d
X
.
Du
,
“
In
teg
ra
ti
n
g
th
e
Co
n
ti
n
u
o
u
s
W
a
v
e
let
T
r
a
n
sf
o
r
m
a
n
d
a
Co
n
v
o
l
u
ti
o
n
a
l
Ne
u
ra
l
Ne
tw
o
rk
to
Id
e
n
ti
f
y
V
in
e
y
a
rd
Us
in
g
T
i
m
e
S
e
ries
S
a
telli
te
I
m
a
g
e
s
,
”
Rem
o
te
S
e
n
sin
g
,
v
o
l.
1
1
,
n
o
.
2
2
,
p
.
2
6
4
1
,
2
0
1
9
,
d
o
i:
1
0
.
3
3
9
0
/rs1
1
2
2
2
6
4
1
.
[2
8
]
N.
P
.
Jo
sh
i
a
n
d
P
.
S
.
T
o
p
a
n
n
a
v
a
r,
“
S
u
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
-
b
a
se
d
h
e
a
rtb
e
a
t
c
las
sif
ica
ti
o
n
,
”
Pro
c
.
o
f
4
t
h
IRF
In
t
.
Co
n
f
,
2
0
1
4
,
p
p
.
1
4
0
-
1
4
4
.
[2
9
]
Y.
L
iao
,
Y.
X
ian
g
,
a
n
d
D.
D
u
,
“
A
u
to
m
a
ti
c
Clas
si
f
ica
ti
o
n
o
f
He
a
rtb
e
a
ts
Us
in
g
ECG
S
ig
n
a
ls
v
ia
Hig
h
e
r
Ord
e
r
Hid
d
e
n
M
a
rk
o
v
M
o
d
e
l
,
”
2
0
2
0
IEE
E
1
6
th
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
A
u
to
m
a
ti
o
n
S
c
ien
c
e
a
n
d
En
g
i
n
e
e
rin
g
(
CAS
E)
,
2
0
2
0
,
p
p
.
6
9
-
7
4
,
d
o
i:
1
0
.
1
1
0
9
/CA
S
E4
8
3
0
5
.
2
0
2
0
.
9
2
1
6
9
5
6
.
[
3
0
]
J
.
A
.
G
u
t
i
é
r
r
e
z
-
G
n
e
c
c
h
i
,
e
t
a
l
.
“
D
S
P
-
b
a
s
e
d
a
r
r
h
y
t
h
m
i
a
c
l
a
s
s
i
f
i
c
a
t
i
o
n
u
s
i
n
g
w
a
v
e
l
e
t
t
r
a
n
s
f
o
r
m
a
n
d
p
r
o
b
a
b
i
l
i
s
t
i
c
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
B
i
o
m
e
d
i
c
a
l
S
i
g
n
a
l
P
r
o
c
e
s
s
i
n
g
a
n
d
C
o
n
t
r
o
l
,
v
o
l
.
32
,
p
p
.
44
-
56
,
F
e
b
r
u
a
r
y
2
0
1
7
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
b
s
p
c
.
2
0
1
6
.
1
0
.
0
0
5
.
[3
1
]
M
.
Z
u
b
a
ir,
J.
Kim
,
a
n
d
C
.
Y
o
o
n
,
“
A
n
A
u
to
m
a
ted
ECG
Be
a
t
Cla
ss
if
ic
a
ti
o
n
S
y
ste
m
Us
in
g
Co
n
v
o
lu
ti
o
n
a
l
Ne
u
ra
l
Ne
tw
o
rk
s,
”
2
0
1
6
6
th
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
IT
Co
n
v
e
rg
e
n
c
e
a
n
d
S
e
c
u
rity
(
ICIT
CS
)
,
2
0
1
6
,
p
p
.
1
-
5
,
d
o
i:
1
0
.
1
1
0
9
/ICIT
CS
.
2
0
1
6
.
7
7
4
0
3
1
0
.
[3
2
]
U.
R.
A
c
h
a
r
y
a
,
e
t
a
l
.
,
“
A
d
e
e
p
c
o
n
v
o
l
u
ti
o
n
a
l
n
e
u
ra
l
n
e
tw
o
rk
m
o
d
e
l
to
c
las
sify
h
e
a
rtb
e
a
ts,
”
Co
mp
u
ter
s
in
b
io
l
o
g
y
a
n
d
me
d
icin
e
,
v
o
l.
8
9
,
p
p
.
3
8
9
-
3
9
6
,
Oc
t
.
2
0
1
7
,
d
o
i:
1
0
.
1
0
1
6
/j
.
c
o
m
p
b
io
m
e
d
.
2
0
1
7
.
0
8
.
0
2
2
.
[3
3
]
F
.
O.
M
.
Ism
a
iel,
“
Clas
si
f
ica
ti
o
n
o
f
Ca
rd
iac
A
rrh
y
th
m
ia
s
Ba
se
d
o
n
W
a
v
e
let
T
ra
n
sf
o
r
m
a
n
d
Ne
u
ra
l
Ne
tw
o
rk
s
,
”
P
h
D
T
h
e
sis
,
S
u
d
a
n
U
n
iv
e
rsity
o
f
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
lo
g
y
,
2
0
1
5
.
[3
4
]
Ö.
Yıld
ır
ım
,
P
.
P
ław
iak
,
Ru
-
S
a
n
T
a
n
,
a
n
d
U.
R.
A
c
h
a
ry
a
,
“
A
rrh
y
t
h
m
ia
d
e
tec
ti
o
n
u
sin
g
d
e
e
p
c
o
n
v
o
lu
ti
o
n
a
l
n
e
u
ra
l
n
e
tw
o
rk
w
it
h
lo
n
g
d
u
ra
ti
o
n
ECG
sig
n
a
ls,
”
Co
mp
u
ter
s
in
b
io
l
o
g
y
a
n
d
m
e
d
icin
e
,
v
o
l.
1
0
2
,
p
p
.
4
1
1
-
4
2
0
,
No
v
.
2
0
1
8
,
d
o
i:
1
0
.
1
0
1
6
/j
.
c
o
m
p
b
io
m
e
d
.
2
0
1
8
.
0
9
.
0
0
9
.
Evaluation Warning : The document was created with Spire.PDF for Python.