T
E
L
KOM
N
I
KA
T
e
le
c
o
m
m
u
n
ic
a
t
io
n
,
C
o
m
p
u
t
i
n
g
,
E
l
ect
ro
n
i
cs
a
n
d
C
o
n
t
ro
l
Vo
l
.
1
9
, N
o
.
5
,
O
ct
o
b
er
202
1
, p
p
.
1
697
~
17
06
I
S
S
N
:
1693
-
6930,
a
c
c
r
e
di
t
e
d F
i
r
s
t
G
r
a
de
by K
e
m
e
nr
i
s
t
e
kdi
kt
i
,
D
e
c
r
e
e
N
o:
21/
E
/
K
P
T
/
2018
D
O
I
:
10.
12928/
T
E
L
K
O
M
N
I
K
A
.
v1
9
i
5
.
20486
1697
Jou
r
n
al
h
om
e
page
:
ht
t
p:
/
/
j
our
nal
.
uad
.
ac
.
i
d/
i
nde
x
.
php/
T
E
L
K
O
M
N
I
K
A
C
l
a
s
s
i
f
i
ca
t
i
o
n o
f
h
ea
rt
di
s
ea
s
e
ba
s
ed o
n P
C
G
s
i
g
na
l
u
s
i
ng
C
N
N
A
d
i
t
ya Wi
s
n
u
gr
ah
a
S
u
gi
yar
t
o
1
,
A
gu
s
M
am
an
A
b
ad
i
2
,
S
um
a
r
na
3
1,
2
De
pa
r
tm
e
nt of
M
a
the
m
a
tic
s,
Un
ive
r
si
ta
s Ne
ge
r
i Yo
gy
a
ka
r
ta
,
Y
og
ya
ka
r
ta
,
I
nd
one
sia
3
De
pa
r
tm
e
n
t of
P
h
ys
ic
s,
U
ni
ve
r
s
ita
s
Ne
ge
r
i
Y
og
ya
ka
r
ta
,
Yog
ya
ka
r
ta
,
I
nd
one
sia
A
rt
i
cl
e I
n
f
o
AB
S
T
RACT
A
r
tic
le
h
is
to
r
y
:
R
ecei
v
ed
J
ul
14
,
2020
R
ev
i
s
ed
J
ul
14
,
2021
A
ccep
t
ed
J
ul
28
,
2021
C
a
r
di
ova
sc
u
la
r
di
se
a
se
i
s t
he
le
a
d
in
g c
a
u
se
of
de
a
t
h i
n the
w
or
l
d,
so e
a
r
l
y
de
te
c
ti
on of
he
a
r
t c
o
nd
it
io
ns i
s ve
r
y im
p
or
ta
nt.
De
te
c
ti
on r
e
la
te
d
to
c
a
r
di
ova
sc
u
la
r
di
se
a
se
c
a
n be
c
o
nd
uc
te
d
thr
ou
gh
t
h
e
de
te
c
t
io
n
of
he
a
r
t
sig
na
ls in
te
r
f
e
r
e
nc
e
,
on
e
of
whic
h is c
a
lle
d ph
on
oc
a
r
d
iog
r
a
p
hy.
Th
is st
ud
y
a
im
s
to
c
la
ss
if
y
he
a
r
t
dise
a
se
ba
se
d
on
ph
on
oc
a
r
di
ogr
a
m
(
P
C
G
)
signa
ls
us
in
g
the
c
o
nv
ol
ut
io
na
l
ne
ur
a
l ne
t
wo
r
ks (
C
N
N
)
.
T
he
s
tu
d
y wa
s
in
it
ia
te
d wi
th
sig
na
l pr
e
p
r
oc
e
ss
in
g by c
ut
ti
ng a
nd
nor
m
a
liz
in
g t
he
s
ign
a
l,
f
o
ll
owe
d b
y a
c
on
ti
nu
ou
s wa
ve
le
t tr
a
n
sf
or
m
a
ti
on
pr
oc
e
ss
us
in
g a
m
o
the
r
wa
ve
le
t
a
na
ly
tic
m
or
le
t.
The
de
c
om
po
si
ti
on r
e
su
lt
s a
r
e
vis
ua
l
iz
e
d u
si
ng
a
sc
a
lo
gr
a
m
,
the
n the
r
e
su
lt
s a
r
e
u
se
d a
s C
N
N i
np
ut.
I
n t
hi
s s
tu
dy,
the
P
C
G
sig
na
l
s u
se
d
we
r
e
c
la
s
sif
ie
d i
nt
o
nor
m
a
l,
a
ngi
na
pe
c
to
r
is
(A
P
),
c
on
ge
s
ti
ve
he
a
r
t f
a
il
u
re (CH
F),
a
nd
hy
pe
r
te
ns
ive
he
a
r
t di
se
a
s
e
(
H
HD)
.
The
to
ta
l da
ta
us
e
d,
c
la
s
sif
ie
d
i
nt
o
8
0
tr
a
i
ni
ng
da
ta
a
nd
2
0 te
st
in
g da
ta
.
T
he
ob
ta
i
ne
d m
ode
l s
ho
ws
the
le
ve
l
of
a
c
c
ur
a
c
y,
se
ns
it
iv
it
y,
a
nd
dia
gn
os
tic
spe
c
if
ic
it
y of
1
00
%,
1
00
%
,
a
nd
10
0%
f
or
tr
a
in
in
g da
ta
,
r
e
s
pe
c
t
ive
ly,
w
hi
le
the
pr
e
d
ic
t
io
n r
e
sul
ts
f
or
te
s
ti
ng
da
ta
ind
ic
a
te
the
le
ve
l of
a
c
c
ur
a
c
y,
se
ns
it
iv
it
y,
a
nd
spe
c
if
ic
i
ty of
85
%,
80
%,
a
nd
100
%,
r
e
spe
c
ti
ve
l
y.
Th
is r
e
s
ul
t pr
ove
d to be
be
tte
r
tha
n the
m
o
the
r
wa
ve
le
t
or
oth
e
r
c
la
s
sif
ie
r
m
e
th
od
s,
the
n t
he
m
ode
l wa
s de
pl
oy
e
d in
to th
e
gr
a
p
hic
a
l
u
s
e
r
i
n
t
e
r
f
a
c
e
(G
U
I).
Ke
y
wo
r
d
s
:
C
ont
i
nuous
w
a
ve
l
e
t
t
r
a
ns
f
or
m
C
onvol
ut
i
ona
l
ne
ur
a
l
ne
t
w
or
k
H
ear
t
d
i
s
eas
e
P
honoc
a
r
di
ogr
a
m
T
his
is
a
n
o
pe
n
ac
c
e
s
s
ar
tic
le
u
nde
r
the
CC
B
Y
-
SA
lic
e
n
se
.
C
or
r
e
s
pon
di
n
g A
u
t
h
or
:
A
di
t
ya
W
i
s
nugr
a
ha
S
ugi
ya
r
t
o
D
ep
ar
t
m
en
t
o
f
M
at
h
em
at
i
cs
U
ni
ve
r
s
i
t
a
s
N
e
ge
r
i
Y
ogya
ka
r
t
a
C
ol
om
bo S
t
.
N
o.
1,
Y
ogya
ka
r
t
a
55281,
I
ndone
s
i
a
E
ma
il:
a
di
t
ya
.
w
i
s
nugr
a
ha
2016@
s
t
ude
nt
.
uny.
a
c
.
i
d
1.
I
NT
RO
DUC
T
I
O
N
T
he
he
a
r
t
i
s
one
of
t
he
m
os
t
i
m
por
t
a
nt
o
r
ga
ns
i
n hum
a
ns
be
c
a
us
e
i
t
ha
s
a
vi
t
a
l
r
ol
e
,
pum
pi
ng b
l
ood
t
hr
oughout
t
he
body ke
e
pi
ng
t
he
b
l
ood
f
l
ow
.
O
ne
of
t
he
di
s
e
a
s
e
s
c
a
us
e
d by i
t
s
m
a
l
f
unc
t
i
on
i
s
c
a
r
d
i
o
va
s
c
ul
a
r
di
s
e
a
s
e
.
A
c
c
or
di
ng t
o
da
t
a
f
r
om
t
he
w
o
r
ld
h
e
a
lth
or
ga
ni
z
a
t
i
on
(
WH
O
)
,
car
d
i
o
v
as
cu
l
ar
d
i
s
eas
e i
s
t
h
e
n
u
m
b
er
one
c
a
us
e
of
de
a
t
h i
n t
he
w
or
l
d
.
A
n e
s
t
i
m
a
t
e
d 17
.
9 m
i
l
l
i
on pe
opl
e
ha
ve
di
e
d
f
r
om
c
a
r
di
ova
s
c
ul
a
r
di
s
e
a
s
e
.
I
n
201
6
,
an
es
t
i
m
at
ed
3
1
%
o
f
g
l
o
b
al
d
eat
h
s
ar
e d
u
e t
o
car
d
i
o
v
as
cu
l
ar
cau
s
es
.
O
f
t
h
es
e 3
1
%
,
8
5
%
w
a
s
a
ppr
ove
d
c
a
us
e
d by a
he
a
r
t
a
t
t
a
c
k a
nd s
t
r
oke
[
1]
.
S
ym
pt
om
s
of
c
a
r
di
ova
s
c
ul
a
r
di
s
e
a
s
e
c
a
n of
t
e
n
go unde
t
e
c
t
e
d,
but
t
o
i
de
nt
i
f
y
t
he
m
e
a
r
l
y,
he
a
r
t
a
t
t
a
c
ks
a
nd s
t
r
oke
s
m
a
y be
t
he
f
i
r
s
t
w
a
r
ni
ng of
t
he
di
s
e
a
s
e
.
S
ym
pt
om
s
of
a
he
a
r
t
a
t
t
a
c
k i
nc
l
ude
pa
i
n or
di
s
c
om
f
or
t
i
n t
he
c
e
nt
e
r
o
f
t
he
c
he
s
t
,
pa
i
n
or
di
s
c
o
m
f
or
t
i
n
t
he
a
r
m
,
l
e
f
t
s
houl
de
r
,
e
l
bow
,
j
a
w
,
o
r
ba
c
k.
A
l
s
o,
t
he
pe
r
s
on m
a
y ha
ve
br
e
a
t
hi
ng di
f
f
i
c
ul
t
y or
s
hor
t
ne
s
s
of
br
e
a
t
h,
na
us
e
a
or
vom
i
t
i
ng,
di
z
z
i
ne
s
s
or
f
a
i
nt
,
c
ol
d
s
w
e
a
t
s
,
a
nd pa
l
e
ne
s
s
[
1]
.
I
n
I
ndone
s
i
a,
h
ear
t
d
i
s
eas
e i
s
s
t
i
l
l
a
v
er
y
d
an
g
er
o
u
s
t
h
r
eat
.
A
cco
r
d
i
n
g
t
o
t
h
e
s
am
p
l
e
r
e
g
is
tr
a
tio
n
s
y
s
t
em
(
S
R
S
)
,
h
ear
t
d
i
s
eas
e i
s
t
h
e s
ec
o
n
d
l
ead
i
n
g
cau
s
e o
f
d
eat
h
,
af
t
er
s
t
r
o
k
e.
A
s
a r
es
u
l
t
o
f
t
h
i
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SSN
:
1693
-
6930
T
E
L
KOM
NI
KA
T
el
eco
m
m
u
n
C
om
put
E
l
C
ont
r
o
l
,
Vo
l
.
1
9
, N
o
.
5
,
O
ct
o
b
er
2021
:
1
697
-
1706
1698
d
i
s
eas
e,
t
h
e co
u
n
t
r
y
s
u
f
f
er
ed
eco
n
o
m
i
c l
o
s
s
es
.
E
ach
y
ear
,
t
h
e d
at
a
f
r
o
m
th
e
S
o
c
ia
l
S
e
c
u
r
ity
A
d
min
is
t
r
a
to
r
f
o
r
H
e
a
l
t
h (
B
P
J
S
)
s
how
s
a
n i
nc
r
e
a
s
e
i
n he
a
l
t
h e
xpe
ns
e
s
f
or
he
a
r
t
di
s
e
a
s
e
.
I
n 2014,
he
a
r
t
di
s
e
a
s
e
c
o
ns
um
e
d
a
r
ound 4.
4 t
r
i
l
l
i
on of
B
P
J
S
f
unds
,
f
ol
l
ow
e
d by a
n i
nc
r
e
a
s
e
t
o 7.
4 t
r
i
l
l
i
on i
n 2016
,
a
nd i
nc
r
e
a
s
e
d f
ur
t
he
r
i
n
201
8 a
m
ount
i
ng t
o 9.
3
t
r
i
l
l
i
on
[
2]
.
T
hi
s
pr
ove
s
t
h
a
t
t
he
r
e
i
s
a
ve
r
y s
i
gni
f
i
c
a
nt
i
nc
r
e
a
s
e
e
ve
r
y ye
a
r
i
n pa
t
i
e
nt
s
w
i
t
h
h
ear
t
d
i
s
eas
e.
T
h
e
r
ef
o
r
e,
d
i
s
eas
e p
r
ev
en
t
i
o
n
e
f
f
o
r
t
s
ar
e n
eed
ed
t
o
r
ed
u
ce
t
h
e b
u
r
d
en
o
f
s
t
at
e ex
p
en
s
es
i
n
ta
c
k
lin
g
th
e
d
is
e
a
s
e
.
P
e
o
p
le
w
ith
c
ar
d
i
o
v
as
cu
l
ar
d
i
s
eas
e o
r
w
h
o
ar
e
at
h
i
g
h
r
i
s
k
f
o
r
car
d
i
o
v
as
cu
l
ar
d
i
s
eas
e
n
eed
ear
l
y
d
et
ect
i
o
n
.
H
ear
t
d
i
s
eas
e h
as
m
an
y
t
y
p
e
s
,
s
o
m
e o
f
w
h
i
ch
a
r
e an
g
i
n
a p
ect
o
r
i
s
(
A
P
)
,
co
n
g
es
t
i
v
e h
ear
t
f
ai
l
u
r
e
(
C
H
F
)
,
an
d
h
y
p
e
r
t
en
s
i
v
e h
ear
t
d
i
s
eas
e (
H
H
D
)
.
E
ach
o
f
t
h
es
e d
i
s
eas
e
s
i
s
ch
ar
act
er
i
zed
b
y
t
h
ei
r
r
e
s
p
ect
i
v
e
he
a
r
t
s
i
gna
l
s
.
A
t
pr
e
s
e
nt
,
t
he
r
e
ha
ve
be
e
n m
a
ny de
ve
l
opm
e
nt
s
i
n t
he
a
na
l
ys
i
s
of
he
a
r
t
s
i
gna
l
s
or
s
ou
nds
.
T
he
m
os
t
c
om
m
onl
y
us
e
d m
e
t
hod
ba
s
e
d on
he
a
r
t
s
i
gna
l
i
s
t
he
e
l
e
c
t
r
oc
a
r
di
og
r
a
m
(
E
C
G
)
s
i
gna
l
,
w
hi
l
e
t
he
phonoc
a
r
di
o
gr
a
m
(
P
C
G
)
s
i
gna
l
i
s
of
t
e
n
us
e
d t
o
a
na
l
yz
e
t
he
he
a
r
t
s
ound.
A
n
E
C
G
i
s
a
r
e
c
or
di
ng
of
he
a
r
t
s
i
gna
l
a
c
t
i
vi
t
y
[
3]
.
M
e
a
nw
hi
l
e
,
P
C
G
r
e
c
or
ds
t
he
s
ound o
f
t
he
he
a
r
t
r
e
s
ul
t
i
ng
f
r
om
t
he
be
a
t
i
ng
o
f
va
r
i
ous
s
t
r
uc
t
ur
e
s
of
t
he
he
a
r
t
a
nd c
i
r
c
ul
a
t
i
ng bl
ood
[
4]
.
E
C
G
i
s
r
e
c
or
de
d by pl
a
c
i
ng t
he
e
l
e
c
t
r
ode
s
on t
he
s
ki
n,
w
he
r
e
a
s
P
C
G
i
s
r
e
c
or
de
d t
hr
ough
a
n e
l
e
c
t
r
oni
c
s
t
e
t
hos
c
ope
[
5
]
,
[
6
].
R
es
ear
ch
o
n
h
ear
t
d
i
s
e
as
e an
al
y
s
i
s
u
s
i
n
g
E
C
G
h
as
b
een
w
i
d
el
y
u
s
ed
[
7
]
-
[
11]
.
P
C
G
s
i
gna
l
s
c
ons
i
s
t
of
t
w
o m
a
i
n s
ounds
na
m
e
l
y
t
he
f
i
r
s
t
s
ound
(
S
1)
a
nd t
he
s
e
c
ond s
ound (
S
2)
[
12
]
.
A
s
f
or
t
he
a
bnor
m
a
l
he
a
r
t
P
C
G
s
i
gna
l
s
,
i
t
c
ons
i
s
t
s
of
m
or
e
t
ha
n t
w
o s
ounds
a
nd
m
ur
m
ur
s
[
13]
.
A
m
ur
m
u
r
i
s
a
t
ur
bul
e
nt
s
ound
of
bl
ood
f
l
ow
i
ng t
h
r
ough t
he
he
a
r
t
due
t
o
a
phys
i
ol
ogi
c
a
l
a
bnor
m
a
l
i
t
y.
M
ur
m
ur
s
c
a
n
oc
c
ur
a
s
a
r
e
s
ul
t
o
f
h
ear
t
v
al
v
e
d
y
s
f
u
n
ct
i
o
n
,
s
ep
t
al
d
ef
ect
,
an
d
co
ar
ct
at
i
o
n
o
f
t
h
e
ao
r
t
a
[
1
4
]
.
T
h
e ch
ar
act
er
i
s
t
i
cs
o
f
t
h
e
P
C
G
s
i
g
n
a
l
can
b
e
a
na
l
yz
e
d us
i
ng di
gi
t
a
l
s
i
gna
l
de
c
om
pos
i
t
i
on [
15]
.
T
he
de
c
om
pos
i
t
i
on of
di
gi
t
a
l
s
i
gna
l
s
c
a
n be
done
by us
i
ng
m
a
ny m
e
t
hods
,
i
nc
l
udi
ng
t
he
F
our
i
e
r
t
r
a
ns
f
or
m
a
t
i
on or
w
a
ve
l
e
t
t
r
a
ns
f
or
m
a
t
i
on.
W
a
ve
l
e
t
t
r
a
ns
f
or
m
i
s
a
ma
th
e
ma
tic
a
l me
th
o
d
th
a
t is
a
lmo
s
t s
imila
r
to
F
o
u
r
ie
r
tr
a
n
s
f
o
r
m
.
H
o
w
e
v
e
r
,
th
e
d
e
c
o
mp
o
s
itio
n
p
r
o
c
e
s
s
is
l
oc
a
l
i
z
e
d bot
h i
n t
he
t
i
m
e
a
nd f
r
e
que
nc
y dom
a
i
ns
,
a
s
oppos
e
d t
o t
he
F
our
i
e
r
t
r
a
ns
f
or
m
,
w
hi
c
h
i
s
onl
y
l
oc
a
l
i
z
e
d i
n t
he
f
r
e
que
nc
y dom
a
i
n [
16
]
.
T
he
w
a
ve
l
e
t
t
r
a
ns
f
or
m
s
a
r
e
m
or
e
va
l
i
d t
ha
n
F
our
i
e
r
t
r
a
ns
f
or
m
be
c
a
us
e
t
he
w
a
ve
l
e
t
t
r
a
ns
f
or
m
de
pe
nds
on w
a
ve
l
e
t
s
i
f
t
he
f
r
e
que
nc
y va
r
i
e
s
i
n a
l
i
m
i
t
e
d dur
a
t
i
on
.
T
he
r
e
f
or
e
,
t
he
r
e
s
ul
t
s
of
us
i
ng w
av
el
et
t
r
an
s
f
o
r
m
s
h
av
e m
o
r
e
d
et
ai
l
ed
r
es
u
l
t
s
[
1
7
]
.
I
n a
c
c
or
da
nc
e
w
i
t
h t
he
w
or
l
d a
gr
e
e
m
e
nt
on s
us
t
a
i
n
a
bl
e
de
ve
l
opm
e
nt
goa
l
s
(
S
D
G
s
)
,
t
he
de
ve
l
opm
e
nt
of
i
nf
o
r
m
a
t
i
on a
nd c
om
m
uni
c
a
t
i
on t
e
c
hnol
ogy
(
I
C
T
)
i
s
one
of
t
he
S
D
G
s
goa
l
s
[
18]
.
O
ne
pr
oo
f
of
t
he
de
ve
l
opm
e
nt
of
I
C
T
i
s
t
he
ve
r
y
r
a
pi
d de
ve
l
op
m
e
nt
of
p
r
e
di
c
t
i
ve
o
r
c
l
a
s
s
i
f
i
c
a
t
i
on m
e
t
hods
[
1
9
]
,
[
2
0]
.
C
ur
r
e
nt
l
y know
n a
s
a
r
t
i
f
i
c
i
a
l
i
nt
e
l
l
i
ge
nc
e
(
A
I
)
,
a
m
e
c
ha
ni
c
a
l
s
i
m
ul
a
t
i
on s
ys
t
e
m
f
or
ga
t
he
r
i
ng
know
l
e
dge
a
nd
in
f
o
r
ma
tio
n
d
is
tr
ib
u
te
th
e
m to
p
a
r
t
ie
s
w
h
o
me
e
t th
e
r
e
q
u
ir
e
m
e
nt
s
i
n t
he
f
o
r
m
of
a
c
t
i
ona
bl
e
i
nt
e
l
l
i
ge
nc
e
[
21]
.
M
a
c
hi
ne
l
e
a
r
ni
ng (
M
L
)
i
s
pa
r
t
of
A
I
,
w
hi
c
h
i
s
us
e
d t
o de
s
i
gn
a
l
gor
i
t
hm
s
ba
s
e
d on da
t
a
t
r
e
nds
a
nd
hi
s
t
or
i
c
a
l
r
e
l
a
t
i
ons
hi
ps
be
t
w
e
e
n da
t
a
[
22
]
,
[
23
]
.
I
n
M
L
,
m
a
n
y m
e
t
hods
c
a
n be
us
e
d,
i
nc
l
udi
ng
f
uz
z
y s
ys
t
e
m
s
,
a
r
tif
ic
ia
l
ne
ur
a
l
ne
t
w
or
ks
,
de
e
p l
e
a
r
ni
ng,
a
nd e
vol
ut
i
ona
r
y
a
l
gor
i
t
hm
s
[
2
4
]
,
[
25
]
.
D
e
e
p l
e
a
r
ni
ng
i
s
a
n a
l
gor
i
t
hm
f
r
om
M
L
t
h
at
u
s
es
s
ev
er
al
l
ay
er
s
i
n
t
h
e l
ear
n
i
n
g
p
r
o
ces
s
[
2
6
]
,
[
27
].
R
es
ear
ch
r
el
at
ed
t
o
t
h
e
an
al
y
s
i
s
o
f
h
ear
t
d
i
s
eas
e b
as
ed
o
n
t
h
e P
C
G
s
i
g
n
al
ha
s
be
e
n us
e
d
[
2
8
]
-
[
31
].
T
he
a
na
l
ys
i
s
us
i
ng w
a
ve
l
e
t
t
r
a
ns
f
or
m
s
a
nd t
he
M
L
m
e
t
hod f
or
c
l
a
s
s
i
f
i
c
a
t
i
on a
l
s
o ha
s
be
e
n us
e
d
e
xt
e
ns
i
ve
l
y [
32
]
-
[
3
6
]
.
C
ur
r
e
nt
l
y,
i
t
i
s
w
i
de
l
y
a
c
c
e
pt
e
d t
ha
t
t
he
c
ont
i
nuous
w
a
ve
l
e
t
t
r
a
ns
f
or
m
(
C
W
T
)
m
e
t
hod
i
s
t
he
m
os
t
a
ppr
opr
i
a
t
e
f
or
a
na
l
yz
i
ng non
-
s
t
a
t
i
ona
r
y P
C
G
s
i
gna
l
s
(
ha
vi
ng va
r
i
ous
f
r
e
que
nc
i
e
s
a
nd i
n
time
)
[
3
7
]
,
[
38
]
.
R
es
ear
ch
r
el
at
ed
t
o
t
h
e cl
as
s
i
f
i
cat
i
o
n
o
f
P
C
G
s
i
g
n
a
l
s
w
i
t
h C
W
T
ha
s
a
l
s
o be
e
n c
a
r
r
i
e
d out
by
s
ev
er
al
r
es
ear
ch
er
s
[
39
]
.
T
he
s
i
gna
l
a
na
l
ys
i
s
pr
oc
e
s
s
doe
s
not
onl
y us
e
f
e
a
t
u
r
e
e
xt
r
a
c
t
i
on but
t
h
r
ough s
c
a
l
ogr
a
m
a
na
l
ys
i
s
[
4
0
].
S
i
g
n
al
an
al
y
s
i
s
u
s
i
n
g
a
s
cal
o
g
r
am
i
s
m
o
r
e u
s
ef
u
l
t
h
an
a s
p
ect
r
o
g
r
am
b
ecau
s
e a s
cal
o
g
r
a
m
c
on
s
i
s
t
s
n
ot
onl
y of
t
i
m
e
a
nd
f
r
e
que
nc
y but
a
l
s
o t
he
m
a
gni
t
ude
or
s
t
r
e
ngt
h of
t
he
s
i
gna
l
i
t
s
e
l
f
[
4
1
]
.
I
n
s
ev
er
al
s
t
u
d
i
es
,
t
h
e m
et
h
o
d
u
s
e
d
f
o
r
c
la
s
s
if
ic
a
tio
n
o
r
c
la
s
s
if
ie
r
is
c
onvol
ut
i
ona
l
ne
ur
a
l
ne
t
w
or
ks
(
C
N
N
)
.
C
N
N
is
a
ty
p
e
o
f
a
r
tif
ic
ia
l n
e
u
r
a
l
ne
t
w
or
k (
A
N
N
)
w
hi
c
h ha
s
a
de
e
p l
e
a
r
ni
ng
p
r
in
c
ip
le
in
i
t.
I
t
c
o
n
s
is
ts
o
f
s
e
v
e
r
a
l la
y
e
r
s
s
p
e
c
if
ic
a
lly
d
e
s
ig
n
e
d
to
p
r
o
c
e
ss t
w
o
-
di
m
e
ns
i
ona
l
da
t
a
[
4
2
]
.
H
ow
e
ve
r
,
t
he
c
ons
t
r
uc
t
i
on of
C
N
N
a
nd C
W
T
i
n
P
C
G
s
i
gna
l
a
na
l
ys
i
s
ha
s
ne
ve
r
be
e
n
us
e
d i
n
pr
e
vi
ous
s
t
udi
e
s
.
T
he
r
e
f
or
e
,
t
h
e
pr
oc
e
s
s
of
c
l
a
s
s
i
f
i
c
a
t
i
on o
f
he
a
r
t
di
s
e
a
s
e
i
n t
hi
s
s
t
udy i
s
ba
s
e
d on P
C
G
s
i
gna
l
s
us
i
ng C
W
T
a
nd C
N
N
(
C
W
T
-
C
N
N
)
.
T
he
r
e
a
s
on f
o
r
us
i
ng
C
W
T
-
C
N
N
i
s
t
h
at
C
WT
h
as
c
a
pa
bi
l
i
t
y t
o e
l
i
m
i
na
t
e
t
he
s
i
gna
l
noi
s
e
a
nd t
he
n
a
na
l
yz
e
i
t
i
n t
he
f
r
e
que
nc
y,
t
i
m
e
,
a
nd m
a
gni
t
ude
dom
a
i
n
w
hi
c
h i
s
i
nt
e
r
pr
e
t
e
d i
nt
o a
s
c
a
l
ogr
a
m
i
n t
he
f
or
m
of
a
t
w
o
-
d
i
m
en
s
i
o
n
al
i
m
ag
e,
w
h
er
eas
C
N
N
i
s
a v
er
y
s
u
i
t
ab
l
e m
et
h
o
d
t
o
b
e u
s
ed
as
a cl
as
s
i
f
i
er
.
2.
R
ES
EA
R
C
H
M
ETH
O
D
T
he
da
t
a
us
e
d i
n
t
hi
s
s
t
udy
a
r
e
s
e
c
onda
r
y da
t
a
obt
a
i
ne
d
f
r
om
t
he
obs
e
r
va
t
i
on o
f
he
a
r
t
di
s
e
a
s
e
pa
t
i
e
nt
s
a
nd he
a
l
t
hy pe
o
pl
e
a
t
P
K
U
M
uha
m
m
a
di
y
a
h Y
ogya
ka
r
t
a
H
os
pi
t
a
l
c
onduc
t
e
d by a
nd [
3
6
]
on F
e
br
ua
r
y
24,
2017,
t
o A
p
r
i
l
18,
2017
.
T
he
da
t
a
w
e
r
e
c
ol
l
e
c
t
e
d i
n t
he
f
or
m
of
he
a
r
t
r
a
t
e
s
i
gna
l
r
e
c
or
di
ngs
i
n .
w
a
v f
i
l
e
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
KA
T
el
eco
m
m
u
n
C
om
put
E
l
C
ont
r
o
l
C
l
as
s
i
f
i
c
at
i
on of
he
ar
t
di
s
e
as
e
bas
e
d on P
C
G
s
i
gnal
us
i
ng C
N
N
(
A
di
t
y
a
W
i
s
nugr
aha Sugi
y
ar
t
o
)
1699
f
or
m
a
t
f
r
om
75
vol
unt
e
e
r
s
w
i
t
h he
a
r
t
di
s
e
a
s
e
a
nd 25 nor
m
a
l
pe
opl
e
.
T
he
da
t
a
r
e
c
or
di
ng p
r
oc
e
s
s
i
s
ba
s
e
d on
r
e
s
e
a
r
c
h c
onduc
t
e
d by [
4
3
].
T
hi
s
s
t
udy a
i
m
s
t
o c
l
a
s
s
i
f
y t
he
t
ype
s
of
he
a
r
t
di
s
e
a
s
e
ba
s
e
d on P
C
G
s
i
gna
l
pa
t
t
e
r
n
s
.
T
he
da
t
a
w
e
r
e
a
na
l
yz
e
d us
i
ng
c
ont
i
nuous
w
a
ve
l
e
t
-
c
onvol
ut
i
ona
l
ne
ur
a
l
ne
t
w
or
k
(
CW
-
C
N
N
)
,
w
hi
c
h i
s
a
c
om
bi
ne
d m
ode
l
of
c
ont
i
nuous
w
a
ve
l
e
t
t
r
a
ns
f
or
m
a
t
i
on a
nd
c
onvol
ut
i
o
na
l
ne
ur
a
l
ne
t
w
or
k
(
C
N
N
)
a
s
a
c
la
s
s
if
ie
r
.
I
n
p
r
in
c
ip
le
,
th
e
c
ont
i
nuous
w
a
ve
l
e
t
t
r
a
ns
f
or
m
i
s
us
e
d
t
o a
na
l
yz
e
da
t
a
by
e
xt
r
a
c
t
i
ng
a
nd de
c
om
pos
i
ng
P
C
G
s
i
g
na
l
s
i
nt
o
s
ev
er
al
co
m
p
o
n
en
t
s
,
an
d
l
at
er
,
t
h
e
r
e
s
ul
t
w
i
l
l
be
us
e
d a
s
i
nput
on
C
N
N
.
I
n
b
r
i
e
f
,
t
he
pr
oc
e
s
s
of
c
l
a
s
s
i
f
yi
ng
h
ear
t
d
i
s
eas
e b
y
t
h
e C
W
-
C
N
N
m
e
t
hod i
s
e
xpl
a
i
ne
d i
n F
i
gu
r
e
1
.
A
f
te
r
o
b
ta
in
in
g
th
e
C
N
N
mo
d
e
l w
ith
th
e
mo
s
t o
p
tima
l c
la
s
s
if
ic
a
tio
n
o
f
h
e
a
r
t d
is
e
a
s
e
,
th
e
n
e
x
t s
te
p
is
t
o a
ppl
y
t
hi
s
C
N
N
m
ode
l
i
nt
o
a
n
a
ppl
i
c
a
t
i
on
ba
s
e
d on
M
A
T
L
A
B
or
know
n
g
r
ap
h
i
cal
u
s
er
i
n
t
er
f
ace
(
GUI
)
,
s
o
t
h
at
i
t
can
b
e u
s
ed
eas
i
l
y
an
d
p
o
s
s
es
s
a m
o
r
e at
t
r
a
c
t
i
ve
a
ppe
a
r
a
nc
e
.
T
he
de
s
i
gn of
t
he
G
U
I
di
s
pl
a
y f
or
t
he
c
l
a
s
s
i
f
i
c
a
t
i
on of
he
a
r
t
di
s
e
a
s
e
i
s
s
how
n i
n F
i
gu
r
e
2.
F
i
gur
e
1.
R
es
ear
ch
d
i
ag
r
am
F
i
gur
e
2
.
G
U
I
di
s
pl
a
y de
s
i
gn
3.
R
ES
U
LTS
A
ND ANAL
YS
I
S
3.
1.
P
rep
ro
ces
s
i
n
g
s
i
gn
al
I
n t
hi
s
s
t
udy
,
t
he
da
t
a
us
e
d a
r
e
i
n
t
he
f
o
r
m
of
c
a
r
di
a
c
P
C
G
s
i
gna
l
r
e
c
or
di
ngs
c
ons
i
s
t
i
ng of
75
r
e
c
or
di
ngs
of
he
a
r
t
di
s
e
a
s
e
pa
t
i
e
nt
s
f
r
om
P
K
U
M
u
ha
m
m
a
di
ya
h H
os
pi
t
a
l
Y
ogya
ka
r
t
a
a
nd 25 r
e
c
or
di
ngs
of
t
he
he
a
r
t
of
a
nor
m
a
l
pe
r
s
on.
T
he
r
e
c
or
di
ng da
t
a
w
e
r
e
s
t
or
e
d
i
n t
he
.
w
a
v e
xt
e
ns
i
on.
T
he
f
i
r
s
t
s
t
e
p t
o a
na
l
yz
e
t
he
he
a
r
t
r
a
t
e
r
e
c
or
di
ng da
t
a
w
a
s
s
i
gna
l
pr
e
pr
oc
e
s
s
i
n
g.
T
he
s
i
gna
l
pr
e
pr
oc
e
s
s
i
ng w
a
s
c
onduc
t
e
d by c
u
t
t
i
ng t
he
he
a
r
t
be
a
t
s
ound s
i
gna
l
a
nd
nor
m
a
l
i
z
i
ng
t
he
s
i
gna
l
.
E
ve
r
y
s
i
ngl
e
he
a
r
t
r
a
t
e
r
e
c
or
d w
a
s
c
ut
i
nt
o
s
e
v
er
al
p
i
eces
of
s
i
gna
l
w
i
t
h t
he
s
a
m
e
s
i
gna
l
l
e
ngt
h
.
N
or
m
a
l
i
z
a
t
i
on pr
oc
e
s
s
i
s
br
i
ngi
ng da
t
a
t
o s
t
a
nda
r
d no
r
m
a
l
f
or
m
(
m
ean
=0
,
s
t
an
d
ar
d
d
ev
i
at
i
o
n
=1
)
.
N
o
r
m
al
i
zat
i
o
n
i
s
n
eces
s
ar
y
s
o
t
h
at
t
h
e d
at
a i
s
i
n
t
h
e s
am
e r
an
g
e.
T
h
e s
t
ep
s
f
o
r
p
r
ep
r
o
ces
s
i
n
g
P
C
G
d
at
a ar
e a
s f
o
l
l
o
w
s:
3.
1.
1.
S
i
gn
a
l
cu
t
t
i
n
g
p
ro
ces
s
E
ach
h
ear
t
P
C
G
s
i
g
n
al
d
at
a
r
eco
r
d
w
as
cu
t
i
n
t
o
s
ev
er
al
p
i
eces
o
f
s
i
g
n
al
w
i
t
h
t
h
e s
am
e cu
t
l
en
g
t
h
.
O
ne
pi
e
c
e
of
P
C
G
s
i
gna
l
c
ons
i
s
t
s
of
f
i
r
s
t
he
a
r
t
s
ound (
S
1)
a
nd s
e
c
ond he
a
r
t
s
ound
(
S
2)
.
T
he
p
r
oc
e
s
s
of
c
u
t
t
i
ng
t
he
s
i
gn
a
l
w
a
s
d
on
e
by
t
he
r
e
c
t
a
ng
l
e
m
e
t
h
od
a
nd
t
he
n
f
ol
l
o
w
e
d by
t
h
e
ha
m
m
i
ng
w
i
n
do
w
m
e
t
ho
d.
A
n
e
x
a
m
pl
e
o
f
a
nor
m
a
l
P
C
G
s
i
g
n
a
l
c
u
t
t
i
ng
pr
oc
e
s
s
i
n t
he
he
a
r
t
w
i
t
h t
h
e
f
i
l
e
n
a
m
e
n
1.
w
a
v i
s
pr
e
s
e
nt
e
d
i
n F
i
gur
e
3.
3.
1.
2.
S
i
gn
a
l
n
or
m
a
l
i
z
at
i
on
p
r
oc
e
s
s
T
he
P
C
G
s
i
gna
l
t
ha
t
ha
s
be
e
n c
ut
w
a
s
t
he
n nor
m
a
l
i
z
e
d.
T
he
n
o
r
m
al
i
zat
i
o
n
p
r
o
ces
s
w
as
car
r
i
ed
o
u
t
s
o t
ha
t
t
he
da
t
a
doe
s
not
a
f
f
e
c
t
t
he
s
i
z
e
of
t
he
r
e
c
or
di
ng s
i
gna
l
a
m
pl
i
t
ude
.
T
hi
s
pr
oc
e
s
s
doe
s
not
c
ha
nge
t
he
i
nf
or
m
a
t
i
on c
ont
a
i
ne
d
i
n t
he
P
C
G
s
i
gna
l
.
A
n
e
xa
m
pl
e
of
a
c
a
r
di
a
c
P
C
G
s
i
gna
l
f
o
r
nor
m
a
l
da
t
a
w
i
t
h t
he
n
o
r
ma
liz
e
d f
i
l
e
na
m
e
n1.
w
a
v
i
s
s
how
n i
n F
i
gu
r
e
4
.
3.
2.
D
e
c
om
p
os
i
t
i
on
of
P
C
G
s
i
gn
al
T
he
ne
xt
s
t
e
p a
f
t
e
r
da
t
a
nor
m
a
l
i
z
a
t
i
on w
a
s
de
c
om
pos
i
ng t
he
s
i
gna
l
w
i
t
h c
ont
i
nuous
w
a
ve
l
e
t
t
r
a
ns
f
or
m
a
t
i
on.
I
n t
hi
s
s
t
udy,
t
he
m
ot
he
r
w
a
ve
l
e
t
us
e
d i
s
t
he
m
ot
he
r
w
a
ve
l
e
t
a
na
l
yt
i
c
m
or
l
et
.
Wav
el
et
t
r
a
ns
f
or
m
a
t
i
on f
unc
t
i
on a
c
c
or
di
ng
t
o [
4
4
]
i
s
de
f
i
ne
d a
s
(
1)
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SSN
:
1693-
6930
T
E
L
KOM
NI
KA
T
el
eco
m
m
u
n
C
om
put
E
l
C
ont
r
o
l
,
Vo
l
.
19
, N
o
.
5
,
O
ct
o
b
er
2021:
1697
-
1706
1700
(
,
)
=
∫
(
)
∞
−
∞
ψ
(
,
)
∗
(
)
(
1)
an
d
m
o
t
h
er
w
av
el
et
an
al
y
t
i
c
m
o
r
l
et
i
s
d
ef
i
n
ed
as
(2
)
.
ψ
(
t
)
=
−
1
/
4
−
(
t
−
t
0
)
2
/
2
(
t
)
(
2)
A
f
t
er
t
h
e t
r
an
s
f
o
r
m
at
i
o
n
,
t
h
e
r
es
u
l
t
s
w
er
e
vi
s
ua
l
i
z
e
d i
n t
he
f
or
m
of
a
s
c
a
l
ogr
a
m
.
T
he
f
o
l
l
ow
i
ng i
s
a
n
e
xa
m
pl
e
of
t
he
w
a
ve
l
e
t
t
r
a
ns
f
or
m
a
t
i
on pr
oc
e
s
s
us
i
ng a
m
ot
he
r
w
a
ve
l
e
t
a
na
l
yt
i
c
m
or
l
e
t
vi
s
ua
l
i
z
e
d i
n t
he
f
or
m
of
a
s
c
a
l
ogr
a
m
us
i
ng t
he
f
i
l
e
na
m
e
d
n1.
w
a
v,
a
s
s
how
n i
n F
i
gu
r
e
5
.
I
n
F
i
g
u
r
e 5
,
i
t
can
b
e
obs
e
r
ve
d
t
ha
t
not
onl
y f
r
e
que
nc
y a
nd t
i
m
e
a
r
e
v
i
s
ua
l
i
z
e
d i
n t
he
f
or
m
of
c
ol
or
,
but
t
he
m
a
gni
t
ude
or
s
t
r
e
ngt
h
of
t
he
s
i
gn
a
l
i
s
a
l
s
o
p
r
es
en
t
ed
.
F
r
o
m
t
h
i
s
r
ep
r
es
en
t
at
i
o
n
,
t
h
e d
at
a i
n
t
h
e f
o
r
m
o
f
s
cal
o
g
r
am
i
m
ag
es
ar
e r
i
ch
i
n
p
ar
am
et
er
f
eat
u
r
es
t
h
at
can
b
e u
s
ed
to
a
n
a
ly
z
e
d
ig
ita
l s
ig
n
a
ls
.
T
h
e
r
e
s
u
lts
o
f
th
e
s
c
a
lo
g
r
a
m w
ill th
e
n
a
c
t a
s
a
n
in
p
u
t f
o
r
th
e
C
NN m
o
d
e
l
.
(
a)
(
b)
(
c)
(
d)
F
i
gur
e
3
.
P
C
G
s
i
gna
l
s
:
(
a
)
be
f
or
e
c
ut
t
i
ng
,
(
b
)
c
ut
t
i
ng pr
oc
e
s
s
,
(
c
)
c
u
ttin
g
r
e
s
u
lt o
f
th
e
r
e
c
ta
n
g
le
me
th
o
d
,
(
d)
c
ut
t
i
ng
r
e
s
ul
t
o
f
t
he
ha
m
m
i
ng w
i
ndow
m
e
t
hod
(
a)
(
b)
F
i
gur
e
4
.
P
C
G
s
i
gna
l
s
:
(
a)
b
ef
o
r
e
n
o
r
m
al
i
zat
i
o
n
,
(
b
)
a
f
te
r
n
o
r
ma
liz
a
tio
n
F
i
gur
e
5
.
V
i
s
ua
l
i
z
a
t
i
on of
w
a
ve
l
e
t
t
r
a
ns
f
or
m
r
e
s
ul
t
s
on a
s
c
a
l
ogr
a
m
i
n
t
he
t
i
m
e
a
nd f
r
e
que
nc
y dom
a
i
n
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
KA
T
el
eco
m
m
u
n
C
om
put
E
l
C
ont
r
o
l
C
l
as
s
i
f
i
c
at
i
on of
he
ar
t
di
s
e
as
e
bas
e
d on P
C
G
s
i
gnal
us
i
ng C
N
N
(
A
di
t
y
a
W
i
s
nugr
aha Sugi
y
ar
t
o
)
1701
3.
3
.
CNN
T
he
f
i
r
s
t
t
hi
ng
t
o
do
a
t
t
hi
s
s
t
a
ge
i
s
i
m
a
ge
l
a
be
l
i
ng.
T
hi
s
l
a
be
l
i
ng
w
a
s
done
by
t
r
a
i
ni
ng t
he
m
ode
l
w
i
t
h t
r
a
i
ni
ng da
t
a
t
ha
t
ha
s
be
e
n l
a
be
l
e
d a
c
c
or
di
ng
t
o t
he
i
m
a
ge
cl
as
s
i
f
i
cat
i
o
n
.
T
h
e
r
e ar
e 4
cl
as
s
es
,
n
am
el
y
0
f
or
nor
m
a
l
s
c
a
l
ogr
a
m
i
m
a
ge
s
,
1
f
o
r
A
P
di
a
gnos
e
d
s
c
a
l
ogr
a
m
i
m
a
ge
s
,
2
f
o
r
C
H
F
di
a
gnos
e
d s
c
a
l
ogr
a
m
s
,
a
nd
3
f
or
H
H
D
di
a
gnos
e
d s
c
a
l
ogr
a
m
s
.
T
he
l
a
be
l
i
ng w
a
s
us
e
d t
o t
r
a
i
n da
t
a
ba
s
e
d on t
he
pr
e
de
t
e
r
m
i
ne
d c
a
t
e
gor
i
e
s
.
T
hi
s
,
t
he
n
,
w
oul
d
be
ut
i
l
i
z
e
d a
s
a
r
e
f
e
r
e
nc
e
on
t
he
c
l
a
s
s
pr
e
di
c
t
i
ons
,
s
o t
he
p
r
ogr
a
m
c
oul
d
c
l
a
s
s
i
f
y a
c
c
or
di
ng
to
s
imila
r
itie
s
a
n
d
c
a
te
g
o
r
iz
e
th
e
m
a
p
p
r
o
p
r
ia
te
ly
.
T
he
a
r
c
hi
t
e
c
t
ur
e
i
n t
hi
s
s
t
udy w
a
s
i
ns
pi
r
e
d by t
he
V
G
G
N
e
t
a
r
c
hi
t
e
c
t
ur
e
m
ode
l
,
but
t
he
r
e
w
e
r
e
s
l
i
ght
m
odi
f
i
c
a
t
i
ons
i
n t
he
num
be
r
of
c
onvol
ut
i
on
l
a
ye
r
s
,
pool
i
ng
,
a
nd
r
ect
i
f
i
ed
l
i
n
ear
u
n
i
t
(
R
e
Lu
)
l
ay
er
s
.
T
h
en
an
a
ppr
opr
i
a
t
e
a
r
c
hi
t
e
c
t
ur
e
f
o
r
t
he
he
a
r
t
P
C
G
s
i
gna
l
s
c
a
l
ogr
a
m
da
t
a
w
a
s
obt
a
i
ne
d us
i
ng t
he
t
r
i
a
l
a
nd e
r
r
or
m
e
t
hod,
a
s
pr
e
s
e
nt
e
d i
n
F
i
gur
e
6
.
T
h
e
i
nput
us
e
d w
a
s
m
a
t
r
i
x
i
n
f
or
m
a
t
i
on
of
ima
g
e
f
r
o
m th
e
s
c
a
lo
g
r
a
m.
T
h
e
s
te
p
w
a
s
in
itia
te
d
b
y
e
nt
e
r
i
ng t
he
i
nput
i
nt
o
t
he
f
i
r
s
t
s
t
a
ge
of
t
he
c
onvol
ut
i
on l
a
ye
r
,
f
ol
l
ow
e
d by
t
he
R
e
L
u a
c
t
i
va
t
i
on l
a
ye
r
,
a
nd t
he
n
t
h
e m
ax
-
pool
i
ng l
a
ye
r
.
T
hi
s
s
e
que
nc
e
w
a
s
r
e
pe
a
t
ed
t
h
r
ee t
i
m
es
.
T
h
e r
es
u
l
t
t
h
en
en
t
er
ed
b
ack
t
o
t
h
e f
i
r
s
t
c
onvol
ut
i
on l
a
ye
r
f
o
l
l
ow
e
d by t
he
R
e
L
u a
c
t
i
va
t
i
on l
a
ye
r
.
A
f
t
e
r
t
ha
t
,
t
he
r
e
s
ul
t
e
nt
e
r
e
d
t
he
f
ul
l
y
c
o
nne
c
t
e
d
l
a
ye
r
s
t
a
ge
a
nd t
he
n t
he
s
of
t
m
a
x l
a
ye
r
.
F
r
om
t
hi
s
p
r
oc
e
s
s
,
t
he
f
i
na
l
out
put
w
a
s
ge
ne
r
a
t
e
d
i
n t
he
f
or
m
of
i
m
a
ge
c
la
s
s
if
ic
a
tio
n
in
to
c
la
s
s
e
s
.
B
a
s
e
d on t
he
t
r
a
i
ni
ng r
e
s
ul
t
s
of
t
he
t
r
a
i
ni
ng da
t
a
a
nd a
r
c
hi
t
e
c
t
ur
e
us
e
d i
n t
hi
s
s
t
udy,
t
he
r
e
s
ul
t
i
ng
m
ode
l
i
s
p
r
e
s
e
nt
e
d i
n F
i
gur
e
7
.
B
e
f
or
e
c
onduc
t
i
ng t
r
a
i
ni
ng t
o
ge
t
t
he
m
ode
l
,
t
he
f
i
r
s
t
t
hi
ng t
o do w
a
s
da
t
a
a
ugm
e
nt
a
t
i
on i
n w
hi
c
h t
he
s
cal
o
g
r
am
i
m
ag
e d
at
a i
s
r
es
i
zed
t
o
f
aci
l
i
t
at
e
t
h
e l
ea
r
n
i
n
g
p
r
o
ces
s
.
T
h
i
s
s
t
ep
i
s
n
eces
s
ar
y
b
ecau
s
e b
y
u
s
i
n
g
d
at
a
au
g
m
en
t
at
i
o
n
,
t
h
e
l
ear
n
i
n
g
p
r
o
ces
s
w
i
l
l
b
e
f
as
t
er
,
b
et
t
er
,
an
d
h
av
e b
et
t
er
accu
r
acy
[
4
5
]
.
T
a
b
l
e 1
p
r
e
se
n
t
s t
h
e
r
e
s
ul
t
s
of
s
e
ve
r
a
l
s
c
a
l
i
ng e
xpe
r
i
m
e
nt
s
c
onduc
t
e
d f
or
da
t
a
a
ugm
e
nt
a
t
i
on.
F
r
o
m
T
ab
l
e
1
i
t
can
b
e s
een
t
h
at
t
h
e
pr
oc
e
s
s
of
da
t
a
a
ugm
e
nt
a
t
i
on
by
s
c
a
l
i
ng t
he
s
i
z
e
t
o 10%
ha
s
t
he
be
s
t
r
e
s
ul
t
s
bot
h
i
n
t
e
r
m
s
of
C
N
N
t
r
a
i
ni
ng
t
i
m
e an
d
accu
r
acy
.
T
h
er
ef
o
r
e,
t
h
e r
es
u
l
t
s
of
da
t
a
a
ugm
e
nt
a
t
i
on a
r
e
s
c
a
l
ogr
a
m
i
m
a
ge
s
m
e
a
s
ur
i
ng 35x39x3
R
G
B
ch
an
n
el
s
.
F
i
gur
e
6
.
C
N
N
mo
d
e
l a
r
c
h
ite
c
tu
r
e
F
i
gur
e
7
.
C
N
N
m
ode
l
f
or
m
e
d
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SSN
:
1693
-
6930
T
E
L
KOM
NI
KA
T
el
eco
m
m
u
n
C
om
put
E
l
C
ont
r
o
l
,
Vo
l
.
1
9
, N
o
.
5
,
O
ct
o
b
er
2021
:
1
697
-
1706
1702
T
ab
l
e 1
.
R
es
u
l
t
s
o
f
s
ev
er
al
s
cal
i
n
g
ex
p
er
i
m
en
t
s
S
cal
e
T
r
a
in
in
g
T
ime
A
ccu
r
acy
T
r
a
in
in
g
T
e
s
tin
g
100%
6
hour
s
80%
40%
70%
4 hour
s
80%
50%
50%
1 hour
90%
50%
30%
20 m
i
nut
e
s
100%
60%
10%
5
min
u
te
s
100%
85%
3.
4
.
D
a
t
a
m
o
d
el
res
u
l
t
T
he
e
xpe
r
i
m
e
nt
s
f
o
r
m
ode
l
l
e
a
r
ni
ng w
e
r
e
c
onduc
t
e
d i
n a
m
a
xi
m
um
o
f
200
e
poc
hs
by va
r
yi
ng
t
he
num
be
r
of
c
onvol
ut
i
on l
a
ye
r
s
us
i
ng 4x4 ke
r
ne
l
a
nd 8 f
i
l
t
e
r
s
i
n e
a
c
h c
onvol
ut
i
on pa
r
a
m
e
t
e
r
.
M
or
e
ov
e
r
,
2x2
-
s
i
zed
p
o
o
l
i
n
g
an
d
s
t
r
i
d
e
2
w
er
e u
t
i
l
i
zed
.
T
h
e
accu
r
acy
r
es
u
l
t
s
o
f
t
r
a
i
ni
ng
a
nd
t
e
s
t
i
ng da
t
a
obt
a
i
ne
d t
hr
ough
t
r
i
al
an
d
er
r
o
r
ar
e p
r
es
en
t
ed
i
n
T
ab
l
e 2
.
F
r
o
m
T
ab
l
e
2
i
t
c
a
n be
obs
e
r
ve
d t
ha
t
t
he
be
s
t
m
ode
l
w
i
t
h 4
c
onvol
ut
i
on l
a
ye
r
s
r
e
s
ul
t
e
d i
n
100%
a
c
c
ur
a
c
y
f
or
t
r
a
i
ni
ng da
t
a
a
nd 85
%
a
c
c
ur
a
c
y f
o
r
t
e
s
t
i
ng
da
t
a
.
T
he
m
ode
l
,
w
hi
c
h
ha
d be
e
n
f
o
r
m
e
d
f
r
om
t
he
t
r
a
i
n
i
ng da
t
a
,
w
a
s
t
he
n t
e
s
t
e
d
on
a
l
l
da
t
a
,
bot
h
t
r
a
i
ni
ng
da
t
a
a
nd t
e
s
t
i
ng
da
t
a
,
t
o
de
t
e
r
m
i
ne
t
he
a
c
c
ur
a
c
y
of
t
he
m
ode
l
.
M
ode
l
t
e
s
t
i
ng w
a
s
done
by
c
a
l
c
ul
a
t
i
ng t
he
accu
r
acy
,
s
en
s
i
t
i
v
i
t
y
,
an
d
s
p
eci
f
i
ci
t
y
.
T
h
e r
es
u
l
t
s
of
t
he
out
put
m
ode
l
f
o
r
t
r
a
i
ni
ng da
t
a
a
r
e
:
T
P
=
60,
T
N
=
20,
F
P
=
0,
a
nd
F
N
=
0.
T
hus
,
t
he
obt
a
i
ne
d va
l
ue
o
f
a
c
c
u
r
a
c
y,
s
e
ns
i
t
i
vi
t
y,
a
nd
s
pe
c
i
f
i
c
i
t
y a
r
e
a
s
f
ol
l
ow
s
:
=
+
+
+
+
100%
=
80
80
100%
=
100%
=
+
100%
=
60
60
100%
=
100%
=
+
100%
=
20
20
100%
=
100%
T
h
e p
er
f
o
r
m
an
ce o
f
t
h
e m
o
d
el
o
n
t
r
ai
n
i
n
g
d
at
a h
as
a h
i
g
h
d
eg
r
ee o
f
accu
r
acy
b
ecau
s
e t
h
e p
r
o
ces
s
o
f
f
or
m
i
ng t
he
m
ode
l
i
s
ba
s
e
d on t
he
t
r
a
i
ni
ng da
t
a
.
T
h
e
r
e
f
o
r
e
,
it is
s
till n
e
c
e
s
s
a
r
y
to
te
s
t th
e
mo
d
e
l o
n
te
s
tin
g
da
t
a
.
T
he
p
r
e
di
c
t
i
on r
e
s
ul
t
s
of
t
he
m
ode
l
on t
he
t
e
s
t
i
ng da
t
a
a
r
e
:
T
P
=
12
,
T
N
=
5
,
F
P
=
0
,
a
nd F
N
=
3.
T
hus
,
t
he
obt
a
i
ne
d va
l
ue
of
a
c
c
ur
a
c
y,
s
e
ns
i
t
i
vi
t
y,
a
nd
s
pe
c
i
f
i
c
i
t
y w
i
t
h r
e
ga
r
ds
t
o t
he
t
e
s
t
i
ng da
t
a ar
e as
f
o
l
l
o
w
s
:
=
+
+
+
+
100%
=
17
20
100%
=
85%
=
+
100%
=
12
12
+
3
100%
=
12
15
100%
=
80%
=
+
100
%
=
5
5
100%
=
100%
F
r
om
t
he
c
a
l
c
ul
a
t
i
on a
bove
,
i
t
w
a
s
f
oun
d
t
h
at
t
h
e t
r
ai
n
i
n
g
d
at
a h
as
an
accu
r
acy
,
s
en
s
i
t
i
v
i
t
y
,
an
d
s
pe
c
i
f
i
c
i
t
y of
100%
,
100%
,
a
nd 100
%
,
r
e
s
pe
c
t
i
ve
l
y.
T
hi
s
r
e
s
ul
t
s
how
s
t
ha
t
t
he
C
N
N
m
ode
l
ha
s
be
e
n bui
l
t
ve
r
y w
e
l
l
ba
s
e
d on t
r
a
i
ni
ng da
t
a
,
bot
h
on
t
he
P
C
G
s
i
gna
l
di
a
gnos
e
d w
i
t
h
t
he
d
i
s
e
a
s
e
or
not
.
A
s
f
o
r
te
s
tin
g
da
t
a
,
t
he
r
e
s
ul
t
s
how
e
d t
ha
t
t
he
di
a
gnos
t
i
c
a
c
c
ur
a
c
y i
s
85
%
,
w
he
r
e
a
s
t
he
s
e
ns
i
t
i
vi
t
y i
s
80%
,
a
nd
t
he
s
pe
c
i
f
i
c
i
t
y i
s
100%
.
T
he
s
e
r
e
s
ul
t
s
i
ndi
c
a
t
e
t
ha
t
t
h
e
m
ode
l
,
w
hi
c
h
w
a
s
bui
l
t
ba
s
e
d on
t
r
a
i
ni
ng
da
t
a
,
c
a
n ve
r
y
w
e
l
l
di
a
gnos
e
P
C
G
s
i
gna
l
s
t
ha
t
a
r
e
not
di
s
e
a
s
e
d or
nor
m
a
l
.
T
hi
s
i
s
i
ndi
c
a
t
e
d
by
t
he
r
e
s
ul
t
s
of
t
he
s
p
e
c
i
f
i
c
i
t
y
of
100%
.
H
ow
e
ve
r
,
t
he
s
e
ns
i
t
i
vi
t
y
of
80%
i
n
t
e
s
t
i
ng da
t
a
i
nd
i
c
a
t
e
s
t
ha
t
t
he
m
ode
l
i
s
l
e
s
s
a
bl
e
t
o
di
a
gnos
e
di
s
e
a
s
e
d P
C
G
s
i
gn
a
l
s
.
F
ur
t
he
r
m
or
e
,
t
he
a
c
c
ur
a
c
y o
f
85%
on
t
he
t
e
s
t
i
ng d
a
ta
s
h
o
w
s
th
a
t th
e
C
N
N
mo
d
e
l is
n
o
t
ab
l
e t
o
d
i
ag
n
o
s
e P
C
G
s
i
g
n
al
s
accu
r
at
el
y
.
M
o
d
e
l te
s
t r
e
s
u
lts
f
o
r
mo
th
e
r
w
a
v
e
le
t a
n
a
ly
tic
mo
r
le
t (
a
m
o
r
)
w
e
r
e
al
s
o
co
m
p
ar
ed
w
i
t
h
o
t
h
er
m
o
t
h
e
r
w
av
el
et
s
s
u
ch
as
b
u
m
p
an
d
g
en
er
al
i
zed
m
o
r
s
e w
av
el
et
(
m
o
r
s
e)
.
T
h
e
c
om
pa
r
i
s
on i
s
pr
es
en
t
ed
i
n
T
ab
l
e
3
.
A
ddi
t
i
ona
l
y,
t
he
r
e
s
ul
t
s
o
f
t
he
m
ode
l
t
e
s
t
i
ng
w
e
r
e
a
l
s
o c
om
pa
r
e
d
w
i
t
h
t
he
ot
he
r
m
e
t
hods
be
s
i
de
s
C
N
N
,
s
uc
h a
s
m
e
t
hods
us
i
ng ot
he
r
c
l
a
s
s
i
f
i
e
r
s
na
m
e
l
y f
uz
z
y s
ys
t
e
m
s
or
w
i
t
h ot
he
r
de
e
p
l
e
a
r
ni
ng
m
e
t
hods
.
T
he
c
om
pa
r
i
s
on of
t
he
s
e
di
f
f
e
r
e
nt
m
e
t
hods
i
n t
e
r
m
s
of
a
c
c
ur
a
c
y a
r
e
pr
e
s
e
nt
e
d i
n T
a
bl
e
4
.
F
r
o
m
th
e
r
e
s
u
lts
in
T
ab
l
e 4
i
t
can
b
e
s
een
t
h
at
t
h
e
C
N
N
m
et
h
o
d
h
as
t
h
e b
es
t
accu
r
acy
w
h
en
co
m
p
ar
ed
t
o
F
C
M
-
M
am
d
an
i
,
F
CM
-
S
uge
no O
r
de
r
0,
B
a
c
kpr
opa
ga
t
i
on N
e
ur
a
l
N
e
t
w
or
k,
o
r
L
S
T
M
-
RN
N
.
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
KA
T
el
eco
m
m
u
n
C
om
put
E
l
C
ont
r
o
l
C
l
as
s
i
f
i
c
at
i
on of
he
ar
t
di
s
e
as
e
bas
e
d on P
C
G
s
i
gnal
us
i
ng C
N
N
(
A
di
t
y
a
W
i
s
nugr
aha Sugi
y
ar
t
o
)
1703
T
ab
l
e
2
.
T
h
e
r
e
s
ul
t
s
of
t
r
a
i
ni
ng a
nd
t
e
s
t
i
ng da
t
a
a
c
c
ur
a
c
y
(%)
T
he
N
um
be
r
of
C
onvol
ut
i
on L
a
ye
r
s
A
ccu
r
acy
(
%
)
T
r
a
in
in
g
T
e
s
tin
g
1
100
50
2
100
60
3
100
60
4
100
80
5
100
75
T
ab
l
e
3
.
T
h
e
r
e
s
u
l
t
s
o
f
t
h
e c
o
m
p
ar
i
s
o
n
o
f
t
h
e ac
cu
r
a
cy
,
s
en
s
i
t
i
v
i
t
y
,
an
d
s
p
e
ci
f
i
c
at
i
o
n
s
o
f
s
e
v
er
a
l
mo
th
e
r
w
av
el
e
t
s
M
o
t
h
er
Wav
el
et
A
n
a
ly
tic
M
o
r
le
t
B
u
mp
Mo
r
se
A
ccu
r
acy
T
r
a
in
in
g
100%
100%
100%
T
e
s
tin
g
85%
75%
70%
S
e
n
s
itiv
ity
T
r
a
in
in
g
100%
100%
100%
T
e
s
tin
g
80%
75%
70%
S
p
e
c
if
ic
ity
T
r
a
in
in
g
100%
100%
100%
T
e
s
tin
g
100%
100%
100%
T
ab
l
e
4
.
T
he
c
om
pa
r
i
s
on w
i
t
h ot
he
r
m
e
t
hods
(
%
)
A
ccu
r
acy
(
%
)
T
r
a
in
in
g
T
e
s
tin
g
FC
M
-
M
a
m
da
ni
57.5
20
FC
M
-
0 O
r
de
r
S
uge
no
73.75
35
C
NN
100
80
B
PN
N
80
60
LS
T
M
-
R
NN
70
60
3.
5
.
D
is
p
la
y
o
f
GU
I
A
f
t
e
r
t
he
m
ode
l
ha
s
pa
s
s
e
d t
he
t
e
s
t
i
ng s
t
a
ge
,
t
he
ne
xt
s
t
e
p w
a
s
t
o c
ons
t
r
uc
t
t
he
C
N
N
m
ode
l
i
nt
o
a
G
U
I
.
T
h
e
ma
in
p
u
r
p
o
s
e
is
to
ma
k
e
it lo
o
k
s
imp
l
e
r
,
mo
r
e
a
tt
r
a
c
tiv
e
,
a
n
d
e
a
s
ie
r
f
o
r
u
s
e
r
s
to
u
s
e
it.
F
ig
u
r
e
8
p
r
es
en
t
s
t
h
e u
s
er
i
n
t
er
f
ace o
f
t
h
e h
ear
t
d
i
s
eas
e c
la
s
s
if
ic
a
tio
n
s
y
s
te
m w
ith
a
G
U
I
.
T
he
G
U
I
di
s
pl
a
y c
a
n be
us
e
d
di
r
e
c
t
l
y t
o c
l
a
s
s
i
f
y he
a
r
t
di
s
e
a
s
e
f
r
om
a
P
C
G
s
i
gna
l
i
nput
.
F
i
r
s
t
,
t
he
P
C
G
s
i
gna
l
i
nput
i
s
s
e
l
e
c
t
e
d by u
s
i
ng t
he
S
e
l
e
c
t
S
i
gna
l
but
t
on.
A
s
a
n
e
xa
m
pl
e
,
t
he
pi
c
t
ur
e
a
bove
us
e
s
P
C
G
s
i
gna
l
i
nput
f
r
om
tr
a
in
in
g
d
a
ta
w
ith
C
H
F
di
a
gnos
i
s
.
T
he
P
C
G
s
i
gna
l
i
s
t
he
n
e
nt
e
r
e
d i
n
t
o
t
he
G
U
I
.
T
he
n
t
hr
ough
t
he
pr
e
pr
oc
e
s
s
i
ng s
t
a
ge
,
na
m
e
l
y
nor
m
a
l
i
z
a
t
i
on,
a
nd by pe
r
f
or
m
i
ng
a
c
ont
i
nuous
w
a
ve
l
e
t
t
r
a
ns
f
or
m
a
t
i
on,
a
s
c
a
l
ogr
a
m
pl
ot
i
s
obt
a
i
ne
d.
T
hi
s
,
t
he
n,
w
i
l
l
be
us
e
d t
o
i
npu
t
t
he
C
N
N
m
ode
l
.
A
f
t
e
r
w
a
r
d,
t
he
pr
oc
e
s
s
i
ng i
s
done
by us
i
ng
C
N
N
t
ha
t
ha
s
be
e
n
bui
l
t
,
a
nd t
he
r
e
s
ul
t
s
obt
a
i
ne
d a
r
e
s
uc
c
e
s
s
f
ul
l
y di
a
gnos
e
d w
i
t
h C
H
F
.
T
he
r
e
s
ul
t
s
of
t
he
G
U
I
de
s
i
g
n a
r
e
i
n
a
c
c
or
da
nc
e
w
i
t
h t
he
i
ni
t
i
a
l
de
s
i
gn us
i
ng t
he
C
N
N
m
ode
l
w
hi
c
h ha
s
be
e
n t
e
s
t
ed
i
n
t
e
r
m
s
o
f
accu
r
acy
.
F
i
gur
e
8
.
G
U
I
d
i
s
p
l
ay
f
o
r
cl
as
s
i
f
i
cat
i
o
n
o
f
h
ear
t
d
i
s
eas
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SSN
:
1693
-
6930
T
E
L
KOM
NI
KA
T
el
eco
m
m
u
n
C
om
put
E
l
C
ont
r
o
l
,
Vo
l
.
1
9
, N
o
.
5
,
O
ct
o
b
er
2021
:
1
697
-
1706
1704
4.
CO
NCL
US
I
O
N
AND
RE
CO
M
M
E
NDAT
I
O
N
4
.1
.
C
on
c
l
u
s
i
on
T
h
i
s
r
es
ear
ch
w
as
i
n
i
t
i
at
ed
w
i
t
h
d
at
a p
r
ep
r
o
ces
s
i
n
g
,
i
n
w
h
i
ch
each
h
ear
t
b
eat
r
eco
r
d
i
n
g
(
P
C
G
s
i
g
n
al
)
w
a
s
c
ut
i
nt
o
s
e
ve
r
a
l
pi
e
c
e
s
of
s
i
gna
l
s
,
f
ol
l
ow
e
d by t
he
nor
m
a
l
i
z
a
t
i
on of
e
a
c
h pi
e
c
e
of
t
he
s
i
gna
l
.
T
he
da
t
a
t
ha
t
ha
d be
e
n c
ut
a
nd nor
m
a
l
i
z
e
d
w
a
s
t
he
n de
s
c
r
i
be
d by us
i
ng c
ont
i
nuous
w
a
ve
l
e
t
t
r
a
ns
f
o
r
m
s
w
i
t
h a
m
ot
he
r
l
y
w
a
v
e
le
t a
n
a
ly
tic
mo
r
le
t.
T
h
e
r
e
s
u
lts
o
f
th
e
tr
a
n
s
f
o
r
ma
t
i
on w
e
r
e
pl
ot
t
e
d
i
nt
o a
s
c
a
l
ogr
a
m
,
w
hi
c
h t
he
n
be
c
a
m
e
t
he
i
nput
f
or
t
he
C
N
N
m
e
t
hod.
T
he
s
c
a
l
ogr
a
m
i
m
a
ge
t
ha
t
ha
d be
e
n ge
ne
r
a
t
e
d w
a
s
t
he
n a
ugm
e
nt
e
d a
g
a
i
ns
t
t
he
da
t
a
s
o t
ha
t
i
t
c
oul
d f
a
c
i
l
i
t
a
t
e
t
he
l
e
a
r
ni
ng pr
oc
e
s
s
of
t
he
C
N
N
m
ode
l
.
E
nt
e
r
i
ng t
he
s
t
a
ge
of
d
a
t
a t
y
p
es
d
iv
is
io
n
,
i
ma
g
e
d
a
ta
w
a
s
d
iv
id
e
d
b
a
s
e
d
o
n
tr
a
in
in
g
d
a
ta
a
n
d
te
s
tin
g
d
a
ta
w
ith
a
r
a
tio
o
f
3
:1
.
A
f
te
r
th
a
t,
th
e
c
l
a
s
s
i
f
i
c
a
t
i
on s
t
a
ge
w
a
s
done
by t
he
C
N
N
m
e
t
hod
.
T
hi
s
m
e
t
hod us
e
d 4 c
onvol
ut
i
on l
a
ye
r
s
,
3 pool
i
n
g l
a
ye
r
s
a
l
ong w
i
t
h t
he
R
e
L
u a
c
t
i
va
t
i
on f
u
nc
t
i
on,
a
f
ul
l
y c
onne
c
t
e
d l
a
ye
r
,
a
nd
w
a
s
e
nde
d w
i
t
h t
he
S
of
t
m
a
x
a
c
t
i
va
t
i
on
f
unc
t
i
on t
o c
r
e
a
t
e
i
m
a
ge
pr
oba
bi
l
i
t
i
e
s
ba
s
e
d on t
h
e
c
or
r
e
s
pondi
ng c
l
a
s
s
s
i
m
i
l
a
r
i
t
y.
T
he
a
c
c
ur
a
c
y,
s
e
ns
i
t
i
vi
t
y,
an
d
s
p
eci
f
i
ci
t
y
w
er
e t
h
en
cal
cu
l
at
ed
f
r
o
m
t
r
ai
n
i
n
g
an
d
t
es
t
i
n
g
d
at
a.
T
h
e
f
in
a
l s
te
p
w
a
s
imp
le
me
n
tin
g
t
h
e
C
N
N
mo
d
e
l w
ith
a
G
U
I
.
P
C
G
s
i
gna
l
pa
t
t
e
r
ns
c
a
n be
br
oke
n dow
n ba
s
e
d o
n t
he
t
ype
of
m
ot
he
r
w
a
ve
l
e
t
us
e
d.
T
he
a
c
c
ur
a
c
y,
s
e
ns
i
t
i
vi
t
y,
a
nd s
pe
c
i
f
i
c
i
t
y obt
a
i
ne
d by us
i
ng t
he
C
N
N
m
e
t
hod a
s
t
he
c
l
a
s
s
i
f
i
e
r
w
e
r
e
100%
,
100%
,
a
n
d 100
%
f
or
t
r
a
i
ni
ng
da
t
a
,
r
e
s
pe
c
t
i
ve
l
y,
a
nd 85%
,
80%
,
a
nd
100%
f
o
r
t
e
s
t
i
ng da
t
a
,
r
e
s
pe
c
t
i
ve
l
y.
B
a
s
e
d on t
he
l
e
ve
l
of
a
c
c
ur
a
c
y,
s
e
ns
i
t
i
vi
t
y,
a
nd s
pe
c
i
f
i
c
i
t
y o
f
t
r
a
i
ni
ng a
nd t
e
s
t
i
ng da
t
a
c
om
pa
r
e
d w
i
t
h
ot
he
r
m
ot
he
r
w
a
ve
l
e
t
s
a
nd
ot
he
r
m
e
t
hods
,
i
t
c
a
n be
c
onc
l
ude
d t
h
at
t
h
e m
o
t
h
e
r
w
av
el
et
an
al
y
t
i
c m
o
r
l
et
can
d
eci
p
h
er
P
C
G
s
i
g
n
a
l
s
b
et
t
er
t
ha
n ot
he
r
m
ot
he
r
w
a
ve
l
e
t
s
.
F
ur
t
he
r
m
o
r
e
,
f
r
o
m
t
he
a
s
pe
c
t
s
of
a
c
c
ur
a
c
y,
s
e
ns
i
t
i
vi
t
y,
a
nd s
pe
c
i
f
i
c
i
t
y us
i
ng
t
r
a
i
ni
ng a
nd t
e
s
t
i
ng da
t
a
of
t
he
C
N
N
m
ode
l
t
ha
t
w
a
s
bui
l
t
,
i
t
c
a
n be
c
onc
l
ude
d
t
ha
t
t
he
C
N
N
m
ode
l
i
s
a
good
m
et
h
o
d
t
o
cl
as
s
i
f
y
h
ear
t
d
i
s
eas
e as
co
m
p
ar
ed
t
o
t
h
e o
t
h
er
m
et
h
o
d
s
.
4
.
2
.
R
eco
m
m
en
d
a
t
i
o
n
F
o
r
f
u
r
t
h
er
r
es
ear
ch
,
w
e r
eco
m
m
en
d
i
n
cr
eas
i
n
g
t
h
e d
at
as
et
s
i
ze,
s
o
p
o
t
en
t
i
al
o
v
er
f
i
t
t
i
n
g
p
r
o
b
l
em
can
be
i
de
nt
i
f
i
e
d.
M
or
e
ove
r
,
upda
t
i
ng
t
he
P
C
G
d
at
a
w
i
t
h
n
ew
an
d
p
r
eci
s
e P
C
G
r
eco
r
d
i
n
g
s
can
b
et
t
er
i
n
t
e
r
p
r
et
t
h
e
ci
r
cu
m
s
t
an
ces
t
h
at
o
ccu
r
i
n
acco
r
d
an
ce w
i
t
h
t
h
e
i
l
l
n
es
s
s
u
f
f
er
ed
.
A
nd a
l
s
o,
f
i
ndi
ng t
he
b
e
s
t
m
e
t
h
od i
n c
u
t
t
i
ng
t
h
e
s
i
g
na
l
a
s
a
n
a
t
t
e
m
p
t
t
o f
r
e
e
t
he
i
n
pu
t
d
a
t
a
f
r
o
m
hum
a
n e
r
r
or
s
i
s
a
l
s
o
a
dv
i
s
a
bl
e
.
L
a
s
t
l
y,
w
e
a
l
s
o r
e
c
om
m
e
n
d
opt
i
m
i
z
i
n
g or
m
a
n
i
p
ul
a
t
i
n
g t
h
e
m
e
t
ho
d
s
t
o
ge
t
a
m
or
e
op
t
i
m
a
l
m
o
de
l
,
s
u
c
h
a
s
by
u
s
i
n
g g
e
n
e
t
i
c
a
l
go
r
i
t
hm
s
,
a
n
t
c
o
lo
n
y
a
l
g
o
r
it
h
m
s
,
p
a
r
ti
c
le
s
w
a
r
m o
p
ti
mi
z
a
ti
o
n
,
o
r
o
th
e
r
o
p
tim
i
z
a
tio
n
me
th
o
d
s
in
th
e
f
o
r
m
a
t
io
n
o
f
n
e
u
r
a
l
ne
t
w
o
r
k w
e
i
ght
s
t
o m
i
ni
m
i
z
e
t
r
i
a
l
a
n
d e
r
r
or
i
n t
h
e
m
od
e
l
s
e
a
r
c
h
pr
o
c
e
s
s
.
A
C
K
N
O
W
LED
G
EM
EN
TS
We w
o
u
l
d
l
i
k
e
t
o
t
h
an
k
D
i
r
ect
o
r
at
e
o
f
R
es
ear
ch
an
d
C
o
m
m
u
n
i
t
y
S
er
v
i
ce,
M
i
n
i
s
t
r
y
o
f
R
es
ear
ch
,
T
e
c
hnol
ogy,
a
nd H
i
ghe
r
E
duc
a
t
i
on of
t
he
R
e
publ
i
c
o
f
I
ndone
s
i
a
unde
r
gr
a
nt
N
o
.
82/
P
e
ne
l
i
t
i
a
n/
P
D
/
U
N
.
34
.
21/
2019.
R
EF
ER
EN
C
ES
[1
]
Am
e
r
ic
a
n He
a
r
t As
soc
ia
t
io
n,
“
He
a
r
t
D
i
s
e
a
s
e
a
n
d
S
tr
o
ke
S
ta
ti
st
ic
s
-
20
17
U
pda
te
:
A
R
e
por
t f
r
om
the
Am
e
r
ic
a
n
He
a
r
t A
ss
oc
ia
ti
on,
”
C
i
rc
u
la
ti
on,
v
ol.
1
35,
n
o.
10,
2
01
7
,
doi
:
1
0.
11
61
/C
I
R
.
0
00
00
00
00
00
00
48
5.
[2
]
A.
M
a
ha
r
a
ni,
S
u
ja
r
w
ot
o,
D.
P
r
a
ve
e
n,
D.
Oc
e
a
nd
y,
G
.
Ta
m
p
ub
ol
on,
A.
P
a
te
l,
“
C
a
r
di
ova
sc
u
la
r
di
se
a
se
r
is
k f
a
c
to
r
pr
e
va
le
nc
e
a
n
d e
st
im
a
te
d 10
-
ye
a
r
c
a
r
d
io
va
sc
ula
r
r
i
sk sc
or
e
s i
n I
nd
one
sia
: The
S
M
AR
The
a
lt
h E
xte
nd s
tu
dy,
”
PL
oS
ON
E,
vo
l.
14
,
no
.
4
,
20
19,
d
oi
: 1
0.
13
71
/j
ou
r
na
l.
po
ne
.
0
2
152
19.
[3
]
J
.
R
.
Ha
m
pto
n,
T
he
EC
G ma
de
e
a
sy
.
L
ond
on
: C
h
ur
c
h
il
l L
ivi
ngs
to
ne
E
lse
ive
r
.
2
01
3.
[4
]
G G
ood
m
a
n
,
“9
4
-
C
a
r
diov
a
sc
ul
a
r
Te
c
hnique
s
a
nd
Te
c
hnology,
”
C
lini
c
al
Engine
e
ring
Handboo
k
:
Biom
e
di
c
al
Engine
e
ring
,
M
a
ss
a
c
hus
e
tts:
Else
iv
e
r
Ac
a
de
m
ic
P
r
e
s
s
,
pp
.
417
-
420
,
2014
,
doi:
10.
1016/
B
978
-
012226570
-
9/50103
-
4
.
[5
]
M
S
a
m
pso
n a
nd
A M
c
gr
a
t
h,
“
Un
de
r
s
ta
n
di
ng t
he
EC
G
P
a
r
t 1: Ana
tom
y a
nd p
hy
si
ol
og
y,
”
B
ri
ti
sh
J
ou
rn
al o
f
C
ard
iac
N
ur
si
ng
,
vo
l
.
10
, n
o
.
1
1,
pp.
5
48
-
55
4,
20
15,
d
oi
:
10.
1
29
68
/b
jc
a
.
2
01
5.
1
0.
11.
54
8
.
[6
]
A.
J.
P
a
ppa
no a
n
d W
.
G
.
W
ie
r
,
“
4
-
T
h
e
C
a
r
d
i
a
c
P
u
m
p
,
”
C
ardi
ov
asc
ul
ar P
hy
s
io
lo
gy
.
Te
nt
h Ed
it
io
n.
P
hi
la
de
lp
h
ia
:
Els
e
i
ve
r
M
os
by,
p
p.
55
-
90,
2
01
5,
do
i:
10.
1
01
6/B
97
8
-
0
-
323
-
08
69
7
-
4.
00
00
4
-
6
.
[7
]
A.
Tur
ni
p,
M
.
I
.
R
iz
q
ywa
n,
D.
E.
K
us
um
a
n
da
r
i,
M
.
T
ur
n
ip,
P
.
S
i
hom
bin
g,
“
C
la
ss
if
ic
a
ti
on
of
EC
G
S
i
gna
l
wit
h
S
upp
or
t Ve
c
tor
M
a
c
h
ine
M
e
t
ho
d f
or
Ar
r
yt
hm
ia
De
te
c
t
i
on,
”
I
OP C
on
f.
Se
r
ie
s:
J
ou
rn
al o
f Phy
sic
s,
vol.
97
0,
20
18,
doi
:
10
.
1
08
8/
17
42
-
65
96
/9
70
/1/
01
20
12
.
[8
]
A.
E.
Z
a
de
h,
A.
Kha
z
a
e
e
,
V.
R
a
na
e
e
,
“
C
la
ss
if
ic
a
ti
on o
f
the
e
le
c
t
r
oc
a
r
di
ogr
a
m
s
ig
na
l
s us
in
g s
upe
r
vi
se
d c
la
ss
if
i
e
r
s
a
nd e
f
f
ic
ie
n
t f
e
a
tur
e
s,
”
C
omp
ute
r Me
t
ho
ds a
nd P
ro
gr
ams i
n Bi
ome
dic
ine
,
v
ol.
99
,
n
o
.
2,
pp.
17
9
-
1
94,
2
0
10,
doi
:
1
0.
10
16
/j.
c
m
pb.
20
10.
0
4.
0
13
.
[9
]
J.
He
,
L
.
S
un,
J.
R
on
g,
H.
Wa
ng,
Y.
Z
ha
n
g,
“
A
py
r
a
m
id
-
li
ke
m
o
de
l f
or
he
a
r
tbe
a
t c
la
s
sif
ic
a
t
io
n f
r
om
E
C
G
r
e
c
or
d
in
gs,
”
PL
oS ON
E
,
vo
l.
13
,
no
.
11,
2
01
8,
do
i:
10.
1
371
/j
ou
r
na
l.
po
ne
.
0
20
65
93
.
[1
0
]
S
.
M
.
Anwa
r
,
M
.
G
u
l,
M
.
M
a
ji
d,
M
.
A
ln
owa
m
i,
“
Ar
r
yt
h
m
ia
C
la
ss
if
ic
a
ti
on
of
EC
G
S
ig
na
l
s U
si
ng
H
ybr
id F
e
a
tur
e
s,
”
C
omp
ut
at
io
na
l a
nd M
at
he
ma
tic
al Me
th
od
s i
n Me
d
ic
i
ne
,
pp.
1
-
8,
2
01
8,
do
i:
10.
1
15
5/
20
18
/1
38
03
48
.
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
KA
T
el
eco
m
m
u
n
C
om
put
E
l
C
ont
r
o
l
C
l
as
s
i
f
i
c
at
i
on of
he
ar
t
di
s
e
as
e
bas
e
d on P
C
G
s
i
gnal
us
i
ng C
N
N
(
A
di
t
y
a
W
i
s
nugr
aha Sugi
y
ar
t
o
)
1705
[1
1
]
R.
G
.
Kum
a
r
a
nd
Y.
S
.
Kum
a
r
a
s
wa
m
y,
“
P
e
r
f
or
m
a
nc
e
a
na
l
ys
is of
s
of
t c
om
p
ut
in
g te
c
hn
iq
ue
s f
or
c
la
s
sif
yi
ng c
a
r
dia
c
a
r
r
hy
thm
ia
,
”
In
d
ia
n J
ou
rn
al
of C
o
mp
ute
r Sc
ie
nc
e
a
nd
E
ngi
ne
e
ri
ng (
I
J
C
S
E)
,
v
o
l
.
4
,
no.
6,
p
p.
45
9
-
4
65,
2
01
4.
[1
2
]
N.
G
ior
da
no,
M
.
Kna
f
li
tz
,
“
A n
ove
l m
e
t
ho
d f
or
m
e
a
su
r
in
g the
tim
in
g of
he
a
r
t s
ou
nd c
om
p
one
nt
s t
hr
o
ug
h di
g
ita
l
pho
no
c
a
r
d
io
gr
a
p
hy,
”
Se
ns
or
s
,
vo
l.
19
, n
o
.
8
,
pp.
18
68
-
(1
-
9)
,
2
01
9,
do
i:
10
.
33
90
/s
19
08
18
68
.
[1
3
]
J.
E.
Ha
ll a
nd A.
C
.
G
uyto
n,
Guy
to
n
an
d
Ha
ll
T
e
x
tb
oo
k
of
Me
dic
al
P
hy
s
io
lo
gy
.
12t
h
Ed
it
io
n
.
P
hila
de
l
ph
ia
: E
lse
i
ve
r
He
a
l
th S
c
ie
nc
e
s.
2
01
1.
[1
4
]
J.
Wr
i
gh
t,
“
M
ur
m
ur
s: A F
o
c
us
e
d A
sse
ssm
e
nt,
”
I
n
te
r
n
ati
on
al J
ou
rn
al o
f N
u
rs
in
g &
C
li
nic
al P
rac
tic
e
s
,
vo
l.
3,
pp.
1
-
2,
20
16,
d
oi
:
10.
15
34
4/
23
94
-
4
97
8/
20
16
/1
70
.
[1
5
]
A.
K.
B
ho
i,
K.
S
.
S
he
r
p
a
,
B
.
Kha
n
de
l
wa
l,
“
M
ul
ti
dim
e
ns
ion
a
l A
na
lyt
ic
a
l S
tu
dy
of
He
a
r
t S
o
un
ds,
”
A R
e
v
ie
w.
I
n
t
. J
.
B
io
au
to
ma
ti
on
, v
o
l
. 9
, n
o
.
3,
p
p.
35
1
-
3
76,
2
01
5.
[1
6
]
G.
K.
R
a
jin
i,
“
A c
om
pr
e
he
ns
ive
r
e
v
ie
w o
n wa
v
e
le
t tr
a
n
sf
or
m
a
n
d it
s a
pp
lic
a
ti
on
s,
”
ARPN
J
o
ur
na
l of E
ng
ine
e
ri
n
g
and Ap
pl
ie
d Sc
ie
nc
e
s
,
vo
l
.
11
, n
o
.
1
9,
pp.
1
17
13
-
11
72
3,
201
6.
[1
7
]
C
.
Z
.
B
as
h
a,
K
.
M.
S
ri
c
h
aran
,
C
.
K
.
D
h
eera
j
,
R
.
R
.
S
r
i,
“
A
st
ud
y o
n wa
ve
le
t
tr
a
n
sf
or
m
us
in
g im
a
ge
a
na
l
y
sis,
”
I
nte
rn
at
io
na
l J
ou
rn
al
of E
ng
ine
e
ri
ng &
T
e
c
h
no
lo
gy
, v
o
l
. 7
,
no.
2.
32,
p
p.
94
-
9
6,
20
18
,
d
oi
: 10.
14
419
/i
je
t.
v7
i2.
32.
1
35
35
.
[1
8
]
J.
W
u,
S
.
G
uo,
H.
H
ua
n
g,
W
.
L
iu a
nd
Y.
Xia
ng,
"
I
nf
or
m
a
ti
on a
n
d C
om
m
un
ic
a
t
io
ns
Te
c
h
no
lo
gie
s f
or
S
us
ta
i
na
ble
De
ve
lo
pm
e
n
t G
oa
ls: S
ta
te
-
of
-
the
-
Ar
t,
Ne
e
ds a
nd P
e
r
s
pe
c
t
ive
s,
"
in
I
EEE C
om
m
uni
c
a
ti
on
s Surv
e
y
s &
T
uto
ri
als
,
vol.
2
0,
no.
3,
p
p.
23
89
-
2
40
6,
th
ir
d
qua
r
te
r
20
18,
d
oi
: 1
0.
110
9/C
OM
S
T.
20
18.
2
81
23
01.
[1
9
]
J.
Wu,
S
.
G
uo,
J.
L
i a
nd D.
Z
e
ng,
"
B
ig Da
ta
M
e
e
t G
r
e
e
n C
ha
ll
e
n
ge
s
: B
ig Da
ta
T
owa
r
d G
r
e
e
n App
lic
a
ti
on
s,
"
in
I
EE
E Sy
s
te
m
s J
o
ur
na
l
,
vo
l.
10,
n
o.
3,
pp.
8
88
-
90
0,
S
e
pt.
201
6,
do
i: 1
0.
1
1
0
9/
JS
YS
T.
20
16.
25
50
53
0.
[2
0
]
S
.
Yu,
L
.
Xu,
Y.
Z
ha
ng,
J.
Wu,
Z
.
L
ia
o a
nd Y.
L
i,
"
NB
S
L
:
A S
upe
r
vi
se
d C
la
ss
if
ic
a
ti
on M
o
de
l of
P
ul
l R
e
que
st i
n G
ith
u
b,
"
201
8 I
E
EE I
nte
rn
at
io
na
l C
on
fe
re
nc
e
o
n C
om
mu
nic
at
io
ns (
I
C
C
)
,
2018,
p
p.
1
-
6,
do
i
: 1
0.
1
10
9/I
C
C
.
2
01
8.
84
22
10
3.
[2
1
]
D.
S
.
G
r
e
wa
l,
“
A c
r
itic
a
l c
onc
e
pt
ua
l a
na
ly
si
s of
de
f
i
n
iti
on
s of
a
r
t
if
ic
ia
l i
nte
ll
ige
nc
e
a
s a
pp
lic
a
ble
to c
om
pu
te
r
e
ng
ine
e
r
in
g,
”
I
OS
R J
o
ur
na
l o
f C
o
mp
ute
r E
ng
ine
e
ri
ng (
I
OS
R
-
JCE
),
vo
l
.
16
,
n
o
.
2,
p
p.
9
-
1
3,
2
014
,
doi
:
10
.
9
79
0/
06
61
-
1
62
10
91
3
.
[2
2
]
S
.
Angr
a
a
nd S
.
Ahuja
,
"
M
a
c
hine
le
a
r
ni
ng a
nd i
ts a
pp
lic
a
t
ion
s: A r
e
v
ie
w,
"
201
7 I
nte
r
na
ti
on
al C
o
nfe
re
nc
e
o
n Big D
at
a
An
aly
tic
s an
d C
o
mp
ut
at
io
na
l I
nte
ll
ige
nc
e
(
I
C
B
DAC
)
,
2
01
7,
pp.
57
-
60,
d
oi
: 1
0.
11
09
/I
C
B
D
AC
I
.
20
17.
80
70
80
9.
[2
3
]
A.
W.
S
u
gi
ya
r
t
o,
D.
Ur
wa
tu
l
Wu
ts
qa
,
N.
He
n
di
ya
n
i a
n
d A.
R
.
R
a
sja
va
,
"
Op
tim
iz
a
t
io
n of
G
e
ne
t
ic
A
lg
or
i
thm
s
o
n
B
a
c
kpr
opa
ga
t
io
n Ne
ur
a
l Ne
t
wor
k to P
r
e
d
ic
t Na
ti
ona
l R
ic
e
P
r
oduc
ti
on L
e
ve
l
s,
"
2019 2
nd I
n
te
r
na
ti
on
al C
o
nfe
re
nc
e
on
Ap
pl
ie
d I
n
fo
rm
at
io
n T
e
c
h
no
lo
gy
an
d I
n
nov
at
io
n (
I
C
AI
T
I
)
,
201
9,
pp
.
77
-
81,
d
oi
: 10.
11
09/
I
C
AI
TI
4
84
42.
2
01
9.
8
98
21
18.
[2
4
]
M
.
R
igla
,
G
.
G
a
r
c
ia
-
S
a
e
z
,
B
.
P
o
n
s
,
M
.
E.
He
r
na
nd
o,
“
A
r
tif
ic
ia
l int
e
l
lig
e
nc
e
m
e
t
ho
do
lo
gie
s a
nd the
ir
a
pp
lic
a
ti
on
to
dia
be
te
s,
”
J
ou
rn
al of Di
abe
te
s Sc
ie
nc
e
a
nd T
e
c
hn
ol
ogy
,
v
ol.
12
,
no
.
2,
p
p.
3
03
-
31
0,
2
018
,
doi
:
10
.
1
17
7/
19
32
29
68
17
71
04
75
.
[2
5
]
A.
M
.
Aba
d
i,
A.
H.
L
u
km
a
na
,
A.
W
.
S
ug
iya
r
to,
H.
V.
Am
a
l
ia
,
“
De
te
r
m
in
in
g of
wa
te
r
sa
t
ur
a
t
io
n u
si
ng f
uz
z
y
l
ogi
c
m
e
th
od in
M
i
r
a
h
-
1 we
ll,
C
e
n
tr
a
l S
um
a
tr
a
ba
s
in
of
I
n
do
ne
s
ia
,
”
J
ou
rn
al of Adv
anc
e
d
Re
se
a
rc
h in Fl
ui
d
M
e
c
h
an
ic
s
and T
he
r
ma
l Sc
ie
nc
e
s,
vo
l.
73
, n
o
.
1,
p
p.
46
-
58,
2
02
0,
d
oi:
10.
3
79
34
/a
r
f
m
ts.
7
3.
1.
4
65
8
.
[2
6
]
L
.
De
ng a
nd
D.
Yu,
“
De
e
p
le
a
r
ni
ng
: m
e
t
ho
ds a
nd a
p
pli
c
a
t
io
ns,
”
F
ou
nd
at
io
n
an
d T
re
nd
s i
n S
ig
na
l P
roc
e
ss
i
ng
,
vol.
7,
no
. 3
-
4
,
pp
.
1
99
-
2
00,
2
01
3,
do
i:
10.
1
56
1/
20
00
00
003
9
.
[2
7
]
A.
W.
S
ug
iya
r
to a
nd A.
M
.
A
ba
d
i,
"
P
r
e
dic
t
io
n of
I
ndo
ne
sia
n P
a
lm
O
il P
r
o
du
c
t
io
n Us
in
g L
on
g S
hor
t
-
T
erm
M
e
m
or
y
R
e
c
ur
r
e
n
t Ne
ur
a
l
Ne
t
wor
k (
L
S
TM
-
RN
N
),
"
2
019
1
st I
nte
rn
at
io
na
l C
o
nfe
re
nc
e
on
Ar
ti
fic
ia
l
I
n
te
l
li
ge
n
c
e
and
Da
ta S
c
ie
nc
e
s (
A
iD
AS)
,
2
01
9,
pp.
5
3
-
5
7,
do
i: 10.
1
1
09/
Ai
D
AS
47
88
8.
2
01
9.
89
70
73
5.
[2
8
]
S
.
I
.
Kha
n
a
n
d V.
Ahm
e
d,
"
I
n
ve
s
ti
ga
t
io
n of
s
om
e
f
e
a
tur
e
s f
or
pr
e
lim
ina
r
y de
te
c
t
io
n
of
c
or
ona
r
y a
r
te
r
y
d
ise
a
se
usi
ng e
le
c
tr
on
ic
ste
th
osc
ope
,
"
20
16 I
nte
rn
at
io
na
l C
on
fe
re
nc
e
o
n
Eme
rg
in
g
T
re
n
ds
in
C
o
mm
un
ic
a
ti
on
T
e
c
h
no
lo
gie
s
(
E
TC
T
)
,
201
6,
pp.
1
-
4,
do
i: 10.
1
10
9/
E
TC
T.
2
01
6.
7
88
29
5
6.
[2
9
]
S
.
E.
S
c
hm
idt,
C
.
Holst
-
Ha
n
se
n,
J.
Ha
nse
n,
E.
Tof
t a
n
d J.
J.
S
tr
uijk
,
"
Ac
o
us
tic
F
e
a
tur
e
s f
or
the
I
de
n
tif
ic
a
t
io
n
of
C
or
on
a
r
y Ar
te
r
y D
ise
a
se
,
"
in
I
EE
E T
ran
sa
c
ti
on
s on B
io
me
d
ic
a
l En
gi
ne
e
r
in
g,
vol.
6
2,
no.
11,
pp.
2
61
1
-
2
61
9,
Nov
.
201
5,
do
i: 10.
1
10
9/
TB
M
E.
20
15.
2
43
21
29.
[3
0
]
S
.
E.
S
c
hm
idt,
C
.
Holst
-
Ha
nse
n,
C
.
G
r
a
f
f
,
E.
Tof
t a
nd J.
J.
S
tr
uij
k,
"
De
te
c
t
io
n of
c
or
ona
r
y a
r
te
r
y d
ise
a
se
wi
th
a
n
e
le
c
tr
on
ic
ste
th
osc
ope
,
"
2
00
7 C
om
pu
te
r
s i
n C
ar
di
ol
ogy
,
200
7,
pp.
7
57
-
7
60,
d
oi
:
10.
11
09
/C
I
C
.
20
07.
4
74
55
96.
[3
1
]
S
.
I
.
Kha
n a
nd
V.
Ahm
e
d,
"
S
tud
y of
e
f
f
e
c
ti
ve
ne
ss of
st
oc
k
we
l
l tr
a
n
sf
or
m
f
or
de
t
e
c
t
io
n of
c
or
ona
r
y a
r
te
r
y di
se
a
se
f
r
om
he
a
r
t s
ou
nd
s,
"
201
6 2
nd I
n
te
r
na
ti
on
al C
on
fe
re
n
c
e
on C
on
te
m
po
ra
ry
C
o
mp
ut
in
g an
d I
nf
or
ma
tic
s (
I
C
3I
)
,
201
6,
pp.
7
25
-
7
28,
d
oi
: 10.
11
09
/I
C
3I
.
2
01
6.
7
91
80
56.
[3
2
]
N.
K.
De
wa
n
ga
n,
S
.
P
.
S
hu
k
la
,
K.
De
wa
nga
n,
“
P
C
G
si
gn
a
l a
na
ly
si
s u
si
ng
dis
c
r
e
te
wa
ve
le
t
tr
a
n
sf
or
m
,
”
I
nt
e
rn
at
ion
al
J
ou
rn
al o
f A
dv
a
nc
e
d i
n M
an
age
me
n
t,
T
e
c
hn
ol
ogy
,
a
nd
En
gi
ne
e
r
in
g Sc
ie
nc
e
s
,
v
o
l
.
8
,
n
o
.
3,
pp.
4
12
-
41
7,
20
18.
[3
3
]
T.
T.
M
un
ia
,
e
t
al
.
,
“
He
a
r
t
so
un
d
c
la
ss
if
ic
a
ti
on
f
r
om
wa
ve
le
t
d
e
c
om
po
se
d
si
gna
l us
in
g m
or
ph
ol
og
ic
a
l a
n
d s
ta
t
is
t
ic
a
l
f
e
a
t
u
r
e
s
,
”
C
om
pu
ti
ng i
n C
a
rd
io
lo
gy
,
vo
l.
43,
pp
.
1
-
4
,
2
0
16,
do
i:
10.
2
24
89
/C
i
nC
.
2
01
6.
17
2
-
31
8
.
[3
4
]
F
.
S
a
f
a
r
a
,
S
.
Dor
a
isa
m
y,
A.
Az
m
a
n,
A.
Ja
nta
n,
S
.
R
a
nga
,
“
W
a
ve
le
t pa
c
ke
t e
n
tr
o
py f
or
he
a
r
t m
ur
m
ur
s
c
l
a
s
s
i
f
i
c
a
t
io
n,
”
Adv
anc
e
s
in Bi
oi
nf
or
ma
tic
s
,
vo
l.
20
12,
2
012,
d
oi
:
1
0.
11
55
/2
01
2/
32
72
69
.
[3
5
]
V.
Niv
it
ha
Va
r
ghe
e
s
a
n
d K.
I
.
R
a
m
a
c
ha
ndr
a
n,
"
Ef
f
e
c
t
i
ve
He
a
r
t
S
o
un
d
S
e
gm
e
nta
ti
on a
nd M
ur
m
ur
C
la
s
sif
ic
a
t
i
on
Usi
ng
Em
pir
ic
a
l
Wa
ve
le
t Tr
a
nsf
or
m
a
nd I
ns
ta
n
ta
ne
o
us P
ha
se
f
or
Ele
c
tr
o
nic
S
te
t
ho
sc
o
pe
,
"
i
n
I
EE
E S
e
n
so
rs
J
ou
rn
al
,
v
ol.
1
7,
no.
1
2,
pp.
3
86
1
-
3
87
2,
15 J
une
15,
2
01
7,
doi
: 1
0.
11
09
/JS
EN.
20
17.
2
69
49
70.
[3
6
]
A.
M
.
Aba
di a
n
d
S
um
a
r
na
,
"
C
ons
tr
uc
ti
on
of
F
uz
z
y
S
yste
m
f
or
C
la
ss
if
ic
a
t
io
n of
He
a
r
t
Di
se
a
se
B
a
se
d
o
n
P
hon
oc
a
r
di
ogr
a
m
S
i
gna
l,
"
201
9 1s
t I
nte
rn
at
io
na
l C
o
nfe
re
nc
e
o
n Ar
ti
fic
ia
l I
nte
ll
ig
e
nc
e
a
nd D
at
a Sc
ie
nc
e
s (
Ai
D
AS)
,
201
9,
pp.
6
4
-
69,
d
oi
: 10.
11
09
/A
iD
AS
47
88
8.
2
01
9.
89
70
9
75.
[3
7
]
B
.
Er
ge
n,
Y
.
Ta
ta
r
,
H.
O.
G
ulc
ur
,
“
Tim
e
-
f
r
e
que
nc
y a
na
l
ysi
s of
ph
on
oc
a
r
d
io
gr
a
m
si
gna
ls
us
in
g wa
ve
le
t
tr
a
n
sf
or
m
: a
c
om
pa
r
a
ti
ve
st
ud
y,
”
C
om
pu
te
r Me
th
od
s i
n Bi
ome
c
ha
nic
s an
d Bi
ome
dic
al
En
gi
ne
e
r
in
g
,
vo
l.
15,
no.
4,
pp
.
3
71
-
38
1,
201
0,
do
i:
10.
1
08
0/
10
25
58
42.
20
10.
5
38
38
6
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SSN
:
1693
-
6930
T
E
L
KOM
NI
KA
T
el
eco
m
m
u
n
C
om
put
E
l
C
ont
r
o
l
,
Vo
l
.
1
9
, N
o
.
5
,
O
ct
o
b
er
2021
:
1
697
-
1706
1706
[3
8
]
A
.
Al
tu
nka
yn
a
k a
nd
M
.
Oz
g
e
r
,
“
C
om
pa
r
i
so
n of
d
isc
r
e
te
a
n
d c
o
nt
in
uo
us
wa
v
e
le
t
-
m
u
lt
ila
ye
r
pe
r
c
e
ptr
on
m
e
t
ho
ds f
or
da
il
y
pr
e
c
i
pi
ta
t
io
n pr
e
d
ic
t
io
n,
”
J
our
na
l of H
id
ro
lo
gic
E
ng
ine
e
rin
g
,
vo
l.
21
, n
o
.
7,
20
16,
do
i:
1
0.
1
06
1/(
AS
C
E)
HE.
1
9
43
-
558
4.
0
00
13
76
.
[3
9
]
S
.
P
a
tida
r
a
nd R
.
B
.
P
a
c
hor
i,
“
A c
ont
in
uo
us wa
ve
le
t tr
a
nsf
or
m
s
-
ba
se
d m
e
tho
d f
or
de
te
c
ti
ng he
a
r
t va
lve
d
is
or
d
e
r
s
usi
ng
p
ho
noc
a
r
di
ogr
a
m
si
gna
ls,
”
I
C
HI
T
20
12:
C
onv
e
rge
nc
e
a
nd
Hy
b
ri
d I
n
fo
rm
at
io
n
T
e
c
h
no
lo
gy
,
vo
l
.
31
0,
pp.
51
3
-
52
0,
20
12
,
do
i:
10.
10
07
/9
78
-
3
-
64
2
-
3
26
92
-
9_
64
.
[4
0
]
Z
.
P
e
ng,
F
.
C
hu,
Y.
He
,
“
V
ibr
a
ti
on
si
gna
l a
na
ly
si
s a
nd
f
e
a
tur
e
e
xtr
a
c
ti
on
ba
se
d
on r
e
a
ss
ig
ne
d
wa
ve
le
t
sc
a
lo
gr
a
m
,
”
J
ou
rn
al o
f S
ou
nd a
nd
Vi
br
at
io
n
,
vol.
2
53
,
n
o
.
5,
pp.
1
0
87
-
11
00,
2
00
2,
do
i:
1
0.
1
00
6/
jsv
i.
2
00
1.
40
85
.
[4
1
]
R
.
R
om
ulu
s,
M
.
L
uc
ia
n,
“
I
f
e
stim
a
t
io
n us
i
n
g spe
c
tr
o
gr
a
m
a
nd sc
a
lo
gr
a
m
,
”
J
ou
rn
al of E
le
c
t
ric
al a
nd E
le
c
t
ro
n
ic
s
E
ng
in
e
e
ri
ng
, v
o
l
. 6
, n
o
.
2,
p
p.
25
-
28,
2
01
3.
[4
2
]
X.
Ha
n a
n
d Y.
L
i,
“
The
a
pp
lic
a
ti
on of
c
on
vo
lu
ti
ona
l ne
ur
a
l ne
t
wor
ks i
n ha
n
dwr
it
te
n
num
e
r
a
l r
e
c
og
ni
ti
on,
”
I
nt
e
rn
at
i
on
al
J
ou
rn
al o
f D
at
ab
ase
T
he
ory
an
d
Ap
pl
ic
a
ti
on,
v
ol.
8
, n
o
.
3,
pp.
36
7
-
37
6,
20
15,
d
oi
:
10.
14
25
7/i
jd
ta
.
2
01
5.
8.
3.
32
.
[4
3
]
S
um
a
r
na
,
J.
A
st
on
o,
A.
P
ur
wa
nt
o a
n
d D.
K.
A
gu
st
ik
a
,
"
The
im
pr
ove
m
e
nt of
ph
on
oc
a
r
d
io
gr
a
p
h s
ig
na
l (
P
C
G
)
r
e
pr
e
se
nta
ti
on t
hr
o
ug
h the
e
le
c
tr
on
ic
ste
th
osc
ope
,
"
20
1
7 4t
h I
nte
rn
at
io
na
l C
on
fe
re
nc
e
o
n Ele
c
tr
ic
a
l En
gi
ne
e
r
i
ng,
C
omp
ut
e
r Sc
ie
nc
e
an
d I
nf
or
ma
tic
s (
E
EC
SI
)
,
2
01
7,
pp.
1
-
5,
do
i: 1
0.
1
10
9/
EEC
S
I
.
2
01
7.
8
23
90
99.
[4
4
]
C
.
S
hor
te
n a
nd
T.
M
.
Kho
sh
gof
ta
a
r
,
“
A s
ur
ve
y o
n im
a
ge
da
ta
a
ugm
e
nta
ti
on f
or
de
e
p
le
a
r
n
in
g,
”
J
ou
rn
al of Bi
g
Dat
a
,
vo
l.
6,
no.
6
0,
pp.
1
-
4
8,
20
19,
d
oi
:
10.
11
86
/s4
05
3
7
-
01
9
-
01
97
-
0
.
[4
5
]
P
.
S
.
Addi
so
n,
“
I
nt
od
uc
t
io
n
to
r
e
d
un
da
nc
y r
u
le
s
:
the
c
o
nti
nu
ou
s
wa
ve
le
t tr
a
n
sf
or
m
c
om
e
s
of
a
g
e
,
”
P
h
il
os
op
hic
a
l
T
ran
sac
ti
on
s o
f T
he
Ro
y
a
l S
oc
ie
ty
A
Ma
the
ma
tic
al,
P
hy
sic
al,
a
nd
En
gi
ne
e
r
in
g Sc
ie
nc
e
s
,
v
ol.
3
76
,
n
o
.
21
26
,
201
8
,
doi
:
10
.
1
09
8/
r
st
a
.
20
17
.
02
58
.
B
I
OGR
A
P
HI
E
S
OF
A
U
T
HOR
S
Ad
it
y
a W
i
sn
u
gr
ah
a S
u
g
iy
ar
t
o
r
e
c
e
ive
d h
is B
a
c
he
lor
De
gr
e
e
of
M
a
t
he
m
a
t
ic
s (
B
.
S
c
.
)
f
r
o
m
Uni
ve
r
si
ta
s Ne
ge
r
i Yo
gya
ka
r
ta
,
I
n
do
ne
s
ia
in 20
20.
C
ur
r
e
n
tl
y,
he
is stu
de
n
t of
G
r
a
dua
t
e
P
r
ogr
a
m
of
M
a
t
he
m
a
t
ic
s (
M
.
S
c
.
)
i
n I
n
st
it
ut
Te
k
no
l
ogi
B
a
n
du
ng,
I
n
do
ne
s
ia
.
H
is c
ur
r
e
n
t
r
e
se
a
r
c
h
in
te
r
e
s
ts i
nc
l
ude
tim
e
se
r
ie
s
m
o
de
l,
f
uz
z
y
sys
te
m
,
ne
ur
a
l
ne
t
wor
k
m
o
de
l,
de
e
p
le
a
r
n
in
g,
a
nd e
x
pe
r
t
sy
ste
m
.
Agu
s
M
am
an
Ab
ad
i
r
e
c
e
ive
d h
is
Doc
tor
a
l De
gr
e
e
(
Dr
.
)
f
r
om
G
a
dja
h M
a
da
Un
iv
e
r
si
ty
,
I
nd
one
sia
i
n 20
10.
P
r
e
se
n
tl
y,
he
is a
n a
s
soc
ia
te
pr
of
e
s
sor
of
M
a
t
he
m
a
t
ic
s De
pa
r
tm
e
nt
,
Yo
gya
ka
r
ta
S
ta
t
e
Uni
ve
r
s
it
y,
I
nd
one
sia
.
Hi
s
c
ur
r
e
n
t
r
e
se
a
r
c
h
inte
r
e
s
ts
inc
lu
de
f
uz
z
y
t
im
e
se
r
ie
s
m
ode
l,
f
uz
z
y s
ys
te
m
s,
ne
ur
a
l
ne
t
wor
k m
ode
l,
im
a
g
e
pr
o
c
e
ss
in
g
,
a
nd f
uz
z
y de
c
is
io
n m
a
ki
ng.
S
um
a
r
n
a
r
e
c
e
ive
d h
is M
a
s
te
r
De
gr
e
e
(
M
.
S
c
.
)
f
r
om
De
pa
r
tm
e
nt of
P
h
ys
ic
s,
I
n
st
it
ut
Te
k
no
lo
g
i
B
a
nd
un
g,
I
ndo
ne
s
ia
i
n
19
93.
He
a
l
so
r
e
c
e
ive
d
hi
s
M
a
ste
r
De
gr
e
e
(
M
.
En
g.
)
f
r
om
De
pa
r
tm
e
n
t
o
f
Ele
c
tr
o
nic
s En
gi
ne
e
r
i
ng,
G
a
dja
h M
a
da
U
ni
ve
r
s
it
y,
I
nd
o
ne
s
ia
in 2
01
5.
P
r
e
se
n
tl
y,
he
i
s a
le
c
t
ur
e
of
P
hy
sic
s De
pa
r
tm
e
n
t,
Yo
gya
ka
r
ta
S
ta
te
U
ni
ve
r
s
it
y,
I
ndo
ne
sia
.
Hi
s c
u
r
r
e
nt r
e
se
a
r
c
h in
te
r
e
st
s
inc
lu
de
ph
ys
ic
s
in
str
um
e
n
ta
t
io
n,
m
e
dic
a
l i
ns
tr
um
e
nta
ti
on (
e
s
pe
c
ia
ll
y i
n ph
on
oc
a
r
di
ogr
a
ph
y)
,
sig
na
l pr
oc
e
ss
in
g,
a
nd
se
n
sor
s.
Evaluation Warning : The document was created with Spire.PDF for Python.