I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
p
ute
r
E
ng
in
ee
ring
(
I
J
E
CE
)
Vo
l.
9
,
No
.
6
,
Dec
em
b
er
201
9
,
p
p
.
5
0
0
6
~5
0
1
5
I
SS
N:
2
0
8
8
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v9
i
6
.
p
p
5
0
0
6
-
5015
5006
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
co
r
e
.
co
m/
jo
u
r
n
a
ls
/in
d
ex
.
p
h
p
/
I
JE
C
E
O
n
t
he
c
la
ss
ificati
o
n
o
f
a
rrhy
th
m
ia
u
sing
supp
le
m
en
t
a
ry
f
ea
tures
fro
m
t
etr
o
let
t
ra
nsfo
r
m
s
G
.
J
a
y
a
g
o
pi
1
,
S.
P
us
hp
a
2
1
S
t.
P
e
ter’s
In
stit
u
te
o
f
Hig
h
e
r
E
d
u
c
a
ti
o
n
a
n
d
Re
se
a
rc
h
,
I
n
d
ia
2
De
p
a
rtm
e
n
t
o
f
Co
m
p
u
ter S
c
ien
c
e
,
S
t.
P
e
ter’s
In
st
it
u
te
o
f
Hig
h
e
r
E
d
u
c
a
ti
o
n
a
n
d
Re
se
a
rc
h
,
In
d
i
a
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
No
v
16
,
2
0
1
8
R
ev
i
s
ed
A
p
r
1
2
,
2
0
1
9
A
cc
ep
ted
J
u
n
27
,
2
0
1
9
He
a
rt
d
ise
a
se
s
h
a
d
b
e
e
n
m
o
ld
e
d
a
s
p
o
ten
ti
a
l
t
h
re
a
ts
to
h
u
m
a
n
li
v
e
s,
e
sp
e
c
iall
y
to
e
ld
e
rly
p
e
o
p
le
in
r
e
c
e
n
t
d
a
y
s
d
u
e
to
t
h
e
d
y
n
a
m
ic
a
l
ly
v
a
r
y
in
g
f
o
o
d
h
a
b
it
s
a
m
o
n
g
th
e
p
e
o
p
le.
Ho
we
v
e
r,
th
e
se
d
ise
a
se
s
c
o
u
ld
b
e
e
a
sil
y
c
a
u
g
h
t
b
y
p
ro
p
e
r
a
n
a
ly
sis
o
f
El
e
c
tro
c
a
rd
io
g
ra
m
(EC
G
)
sig
n
a
ls
a
c
q
u
ired
f
ro
m
in
d
iv
id
u
a
ls.
T
h
is
p
a
p
e
r
p
ro
p
o
se
s
a
b
e
tt
e
r
m
e
th
o
d
t
o
d
e
tec
t
a
n
d
c
las
sify
th
e
a
rrh
y
th
m
ia
u
sin
g
1
5
f
e
a
tu
re
s
w
h
ich
i
n
c
lu
d
e
4
R
-
R
in
terv
a
l
fe
a
tu
re
s,
3
sta
ti
stica
l
a
n
d
6
c
h
a
o
ti
c
f
e
a
tu
re
s
e
sti
m
a
ted
f
ro
m
EC
G
sig
n
a
ls.
A
d
d
it
io
n
a
ll
y
,
En
tro
p
y
a
n
d
En
e
rg
y
f
e
a
tu
re
s
h
a
d
b
e
e
n
g
a
in
e
d
a
f
ter
c
o
n
v
e
rti
n
g
o
n
e
d
im
e
n
sio
n
a
l
ECG
sig
n
a
ls
to
tw
o
d
ime
n
sio
n
a
l
d
a
ta
a
n
d
a
p
p
l
i
e
d
T
e
tr
o
let
tran
sf
o
r
m
s o
n
th
a
t
. T
o
tal
n
u
m
b
e
r
s o
f
1
5
f
e
a
tu
re
s h
a
d
b
e
e
n
u
ti
li
z
e
d
to
c
las
sify
th
e
h
e
a
rt
b
e
a
ts
f
ro
m
th
e
b
e
n
c
h
m
a
rk
M
IT
-
A
rrh
y
th
m
i
a
d
a
tab
a
se
u
sin
g
S
u
p
p
o
rt
V
e
c
to
r
M
a
c
h
i
n
e
s
(S
V
M
).
T
h
e
c
las
sif
ic
a
ti
o
n
p
e
rf
o
rm
a
n
c
e
wa
s
a
n
a
l
y
z
e
d
u
n
d
e
r
v
a
rio
u
s
k
e
rn
e
l
f
u
n
c
ti
o
n
s
a
n
d
d
if
f
e
r
e
n
t
T
e
tro
let
d
e
c
o
m
p
o
siti
o
n
le
v
e
ls.
It
i
s
f
o
u
n
d
th
a
t
Ra
d
ial
Ba
sis
F
u
n
c
ti
o
n
(RBF
)
k
e
rn
e
l
c
o
u
ld
p
e
rf
o
rm
b
e
tt
e
r
th
a
n
li
n
e
a
r
a
n
d
p
o
ly
n
o
m
ial
k
e
rn
e
ls.
Th
is
re
se
a
rc
h
a
tt
e
m
p
t
y
ield
e
d
a
n
a
c
c
u
ra
c
y
o
f
9
9
.
3
5
%
a
g
a
in
st
th
e
e
x
isti
n
g
w
o
rk
s.
M
o
re
o
v
e
r,
a
d
d
it
i
o
n
o
f
tw
o
m
o
re
f
e
a
tu
re
s
h
a
d
i
n
tro
d
u
c
e
d
a
n
e
g
li
g
ib
le
o
v
e
r
h
e
a
d
o
f
ti
m
e
.
He
n
c
e
,
th
is
m
e
th
o
d
is
b
e
tt
e
r
su
it
a
b
le t
o
d
e
tec
t
a
n
d
c
las
sify
th
e
A
rrh
y
th
m
ia i
n
b
o
t
h
o
n
li
n
e
a
n
d
o
f
fli
n
e
.
K
ey
w
o
r
d
s
:
A
r
r
h
y
t
h
m
ia
E
n
er
g
y
E
n
tr
o
p
y
SVM
T
etr
o
let
tr
an
s
f
o
r
m
s
Co
p
y
rig
h
t
©
2
0
1
9
In
st
it
u
te o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
G.
J
ay
a
g
o
p
i
,
St.P
eter
‟s I
n
s
tit
u
te
o
f
Hi
g
h
er
E
d
u
ca
tio
n
an
d
R
e
s
ea
r
ch
,
C
h
e
n
n
ai
,
I
n
d
ia
.
E
-
m
a
il: j
a
y
ag
o
p
ip
h
d
@
g
m
ail.
c
o
m
1.
I
NT
RO
D
UCT
I
O
N
I
t
is
v
er
y
u
n
f
o
r
t
u
n
ate
t
h
at
t
h
e
C
ar
d
io
v
ascu
lar
Dis
ea
s
e
(
C
V
D)
is
e
m
er
g
in
g
i
n
h
i
g
h
er
r
ates.
C
ar
d
iac
is
s
u
es
ar
e
ex
p
a
n
d
in
g
s
tep
-
by
-
s
tep
i
n
t
h
e
w
o
r
ld
.
T
h
o
u
g
h
s
ev
er
al
d
ata
s
o
u
r
ce
s
i
n
cl
u
d
in
g
au
d
ib
le
h
ea
r
tb
ea
t,
b
lo
o
d
p
r
ess
u
r
e,
b
lo
o
d
s
u
g
ar
l
ev
el
etc.
ar
e
a
v
ailab
le,
E
C
G
s
ig
n
al
s
p
la
y
v
ita
l
r
o
le
in
r
ev
ea
lin
g
t
h
e
ca
r
d
iac
d
is
o
r
d
er
.
A
b
n
o
r
m
alit
y
d
etec
ti
o
n
is
j
u
s
t
b
ased
o
n
t
h
e
ti
m
e,
f
r
eq
u
en
c
y
,
a
m
p
lit
u
d
e
,
s
tat
is
tic
al
in
f
o
r
m
atio
n
a
n
d
o
th
er
d
er
iv
ed
f
ea
t
u
r
es
f
r
o
m
a
n
E
C
G
w
a
v
e.
Hen
ce
,
a
n
a
u
to
m
atic
m
et
h
o
d
o
f
E
C
G
w
av
e
f
o
r
m
a
n
al
y
s
is
w
o
u
ld
b
e
h
ig
h
l
y
u
s
ef
u
l
to
th
e
h
u
m
an
s
o
ciet
y
to
d
etec
t
th
e
h
ea
r
t
d
is
ea
s
es
ea
r
lier
an
d
h
en
ce
th
e
ap
p
r
o
p
r
iate
th
er
ap
y
co
u
ld
b
e
em
p
lo
y
ed
.
W
h
ile
ca
u
tio
u
s
l
y
o
b
s
er
v
in
g
th
e
ea
r
lier
liter
at
u
r
es
in
ar
r
h
y
t
h
m
ia
clas
s
if
icatio
n
,
it
w
a
s
p
er
ce
iv
ed
th
at
t
h
e
f
o
r
e
m
o
s
t
p
r
o
b
lem
i
s
to
o
b
tain
b
etter
class
if
ica
tio
n
ac
cu
r
ac
y
w
h
e
n
m
o
r
e
n
u
m
b
er
o
f
class
es
ar
e
ac
co
u
n
ted
.
Si
n
ce
ac
c
u
r
ac
y
is
in
v
er
s
el
y
p
r
o
p
o
r
tio
n
al
to
t
h
e
n
u
m
b
er
o
f
clas
s
es
o
f
ab
n
o
r
m
a
liti
es
in
E
C
G,
it
i
s
th
e
tas
k
o
f
t
h
e
r
esear
ch
er
to
ch
o
o
s
e
a
s
u
itab
le
f
ea
t
u
r
e
ex
tr
ac
tio
n
m
et
h
o
d
w
h
ic
h
w
o
u
ld
r
ep
r
esen
t
t
h
e
co
m
p
lete
m
o
r
p
h
o
lo
g
ical
c
h
ar
ac
ter
is
tic
s
o
f
v
ar
io
u
s
cla
s
s
e
s
o
f
E
C
G
s
ig
n
al.
A
s
a
n
o
v
el
ap
p
r
o
ac
h
,
alo
n
g
w
it
h
tr
ad
itio
n
a
l
R
-
R
i
n
ter
v
al
d
ata,
f
e
w
o
th
er
f
ea
tu
r
es
i
n
cl
u
d
in
g
s
tat
is
tical
,
c
h
ao
tic
m
e
tr
ics
an
d
s
u
p
p
le
m
e
n
tar
y
f
ea
t
u
r
es
f
r
o
m
T
etr
o
let
tr
an
s
f
o
r
m
s
h
a
v
e
b
ee
n
co
n
ca
te
n
ated
i
n
f
ea
t
u
r
e
s
e
ts
b
ased
o
n
w
h
ic
h
t
h
e
cla
s
s
i
f
ic
atio
n
i
s
d
o
n
e
u
s
i
n
g
Su
p
p
o
r
t
Vec
to
r
Ma
ch
in
e
s
(
S
VM
).
T
h
e
f
o
llo
w
i
n
g
p
r
ese
n
t
atio
n
s
ar
e
ab
o
u
t
t
h
e
p
er
f
o
r
m
an
ce
s
o
b
tain
ed
i
n
v
ar
io
u
s
ea
r
lier
w
o
r
k
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2
0
8
8
-
8708
On
th
e
cla
s
s
ifica
tio
n
o
f a
r
r
h
yth
mia
u
s
in
g
s
u
p
p
leme
n
ta
r
y
fea
tu
r
es fr
o
m
tet
r
o
let
tr
a
n
s
fo
r
m
s
(
G.
Ja
ya
g
o
p
i)
5007
M
y
o
ca
r
d
ial
in
f
ar
ct
io
n
,
ca
r
d
io
m
y
o
p
at
h
y
,
a
n
d
m
y
o
ca
r
d
itis
h
a
d
b
ee
n
class
if
ied
in
[
1
]
,
w
it
h
an
ac
cu
r
ac
y
o
f
9
5
%
w
h
i
le
class
i
f
y
i
n
g
t
h
e
ca
r
d
iac
ar
r
h
y
t
h
m
ia.
T
h
e
w
o
r
k
s
u
f
f
er
s
f
r
o
m
a
d
r
a
w
b
ac
k
th
a
t
o
n
l
y
3
class
es
ca
s
e
w
a
s
i
m
p
le
m
e
n
ted
u
s
i
n
g
Gen
er
al
R
eg
r
e
s
s
io
n
Neu
r
al
Net
w
o
r
k
(
GR
NN)
.
T
h
e
w
o
r
k
p
r
ese
n
ted
in
[
2
]
,
w
a
s
ab
le
to
class
i
f
y
n
o
r
m
a
l
b
ea
t,
s
u
p
r
av
e
n
tr
icu
lar
ec
to
p
ic
b
ea
t,
b
u
n
d
le
b
r
an
ch
ec
to
p
ic
b
ea
t,
v
en
tr
ic
u
lar
ec
to
p
ic
b
ea
t,
f
u
s
io
n
b
ea
t
a
n
d
u
n
k
n
o
w
n
b
e
at
f
r
o
m
L
o
n
g
ter
m
ac
c
u
m
u
l
ated
p
atien
t
E
C
G
d
ata.
T
h
is
co
u
ld
p
r
o
d
u
ce
8
8
%
ac
cu
r
ac
y
b
u
t
th
is
w
o
r
k
is
n
o
t
p
o
p
u
lar
d
u
e
to
v
er
y
le
s
s
n
u
m
b
er
o
f
class
e
s
.
T
im
e
s
eq
u
e
n
ce
s
o
f
QR
S
co
m
p
le
x
es
o
f
th
e
E
C
G
w
av
e
f
o
r
m
w
er
e
c
o
n
v
er
ted
in
to
Fo
u
r
ier
s
p
e
ctr
u
m
an
d
f
r
eq
u
en
c
y
co
m
p
o
n
e
n
t
s
w
er
e
o
b
s
er
v
ed
w
it
h
r
esp
ec
t
to
p
o
w
er
w
it
h
i
n
0
-
2
0
Hz
s
p
ec
tr
u
m
.
Gr
e
y
R
ela
ti
o
n
al
An
al
y
s
is
(
GR
A
)
w
as
p
er
f
o
r
m
ed
to
clas
s
i
f
y
th
e
ab
o
v
e
m
en
t
io
n
ed
ab
n
o
r
m
alitie
s
b
ased
o
n
MI
T
-
B
I
H
ar
r
h
y
th
m
i
a
b
en
c
h
m
ar
k
d
atab
ase.
Ho
w
ev
er
,
th
is
n
o
n
i
n
v
asi
v
e
m
eth
o
d
is
li
m
ited
o
n
l
y
to
6
class
es
i
n
cl
u
d
in
g
t
h
e
n
o
r
m
al
b
ea
t.
T
h
is
m
aj
o
r
d
r
aw
b
ac
k
i
s
d
u
e
th
e
f
ac
t th
at
f
ea
t
u
r
e
u
s
ed
is
b
a
s
ed
o
n
l
y
o
n
t
h
e
p
o
w
er
s
p
ec
tr
u
m
o
f
t
h
e
f
r
eq
u
e
n
c
y
d
o
m
ai
n
s
i
g
n
al.
T
h
e
r
ec
o
m
m
e
n
d
atio
n
s
s
u
g
g
es
ted
in
[
3
]
co
u
ld
class
if
y
7
ar
r
h
y
t
h
m
ia
clas
s
es
i
n
clu
d
i
n
g
P
VC
,
A
tr
ial
Fib
r
illatio
n
(
A
F),
C
o
m
p
lete
H
ea
r
t
B
lo
ck
(
C
HB
)
,
L
e
f
t
B
u
n
d
l
e
B
r
an
ch
B
lo
ck
(
L
B
B
B
)
,
No
r
m
al
S
in
u
s
R
h
y
th
m
(
NSR
)
,
Ven
tr
ic
u
lar
Fib
r
illati
o
n
(
VF)
an
d
Ven
tr
ic
u
lar
T
a
ch
y
ca
r
d
ia
(
VT
)
.
T
o
tall
y
,
1
4
f
ea
t
u
r
es
f
r
o
m
t
i
m
e
d
o
m
ai
n
,
f
r
eq
u
en
c
y
d
o
m
ai
n
,
n
o
n
lin
ea
r
a
n
d
ch
ao
tic
f
ea
tu
r
es
w
er
e
ex
tr
ac
ted
to
tr
ain
Mu
lt
i
-
L
a
y
er
P
er
ce
p
tr
o
n
(
ML
P
)
n
eu
r
al
n
et
w
o
r
k
s
af
ter
co
m
p
u
tin
g
Hea
r
t
R
ate
Var
i
ab
ilit
y
(
HR
V)
.
I
n
o
r
d
er
to
r
ed
u
ce
th
e
o
v
er
all
class
i
f
icatio
n
ti
m
e,
Gen
er
aliz
ed
Dis
cr
i
m
i
n
ate
An
al
y
s
i
s
(
GDA
)
h
as
b
ee
n
u
s
ed
as
a
d
i
m
en
s
io
n
r
ed
u
c
tio
n
m
et
h
o
d
p
r
io
r
to
tr
ain
th
e
n
eu
r
al
n
et
w
o
r
k
.
T
h
o
u
g
h
th
e
tr
ai
n
i
n
g
s
et
w
as
f
ilter
ed
b
y
d
eleti
n
g
th
e
co
n
f
u
s
in
g
d
ata,
o
v
er
all
p
er
f
o
r
m
a
n
ce
o
f
9
5
%
t
o
1
0
0
%
ac
cu
r
ac
y
i
n
c
lass
if
ica
tio
n
i
s
li
m
ited
o
n
l
y
to
7
cla
s
s
es
o
f
ar
r
h
y
th
m
ia
o
n
MI
T
-
B
I
H
d
ata
b
ase.
No
n
-
l
in
ea
r
d
y
n
a
m
ic
L
y
ap
u
n
o
v
ex
p
o
n
en
t
s
h
ad
b
ee
n
in
tr
o
d
u
ce
d
in
[
4
]
f
o
r
th
e
an
al
y
s
i
s
o
f
E
C
G
s
ig
n
al
s
.
No
r
m
al
b
ea
t,
co
n
g
e
s
t
iv
e
h
ea
r
t
f
a
ilu
r
e
b
ea
t,
v
e
n
tr
ic
u
lar
tac
h
y
ar
r
h
y
t
h
m
ia
b
ea
t,
atr
ial
f
ib
r
illat
io
n
b
ea
t
av
ailab
le
in
P
h
y
s
io
B
an
k
d
atab
ase
w
er
e
class
i
f
ied
u
s
in
g
th
e
R
ec
u
r
r
en
t
Neu
r
al
Net
w
o
r
k
s
(
R
NN)
.
L
ev
e
n
b
er
g
-
Ma
r
q
u
ar
d
t
alg
o
r
ith
m
w
as
u
s
ed
as
a
tr
ai
n
i
n
g
alg
o
r
it
h
m
b
ased
o
n
t
h
e
Ma
x
i
m
u
m
,
M
i
n
i
m
u
m
,
Me
a
n
a
n
d
Stan
d
ar
d
d
ev
iatio
n
o
f
th
e
L
y
ap
u
n
o
v
E
x
p
o
n
en
t
s
(
L
E
)
o
f
ea
ch
E
C
G
b
ea
t.
T
o
th
e
b
est
o
f
th
e
k
n
o
w
led
g
e
o
f
th
e
au
th
o
r
,
t
h
i
s
is
[
4
]
th
e
f
ir
s
t
v
alid
E
C
G
cla
s
s
i
f
icat
io
n
b
ase
d
o
n
ch
ao
tic
m
etr
ic
s
.
T
h
e
clas
s
if
ica
tio
n
ac
c
u
r
ac
y
o
b
tain
ed
w
as
9
4
.
7
2
%.
Ho
w
e
v
er
,
th
e
m
aj
o
r
d
r
aw
b
ac
k
is
li
m
ited
n
u
m
b
er
o
f
clas
s
es
(
f
o
u
r
)
an
d
th
is
w
o
r
k
h
a
s
u
tili
ze
d
o
n
l
y
L
y
ap
u
n
o
v
e
x
p
o
n
en
t
an
d
d
is
ca
r
d
ed
o
th
er
c
h
ao
tic
m
etr
ics
w
h
ic
h
w
o
u
ld
h
av
e
b
ee
n
u
s
ed
as
ef
f
icien
t f
ea
t
u
r
e
s
.
Mo
s
t
s
u
itab
le
State
-
Of
-
A
r
t
co
m
p
ar
i
s
o
n
in
ar
r
h
y
th
m
ia
clas
s
i
f
icatio
n
w
o
u
ld
b
e
t
h
e
liter
at
u
r
e
[
5
]
,
as
it
d
ea
ls
all
th
e
1
6
clas
s
es
as
a
v
ailab
le
i
n
MI
T
-
B
I
H
d
atab
ase.
T
h
is
cr
itical
w
o
r
k
r
esu
lted
i
n
a
cla
s
s
i
f
ica
tio
n
ac
cu
r
ac
y
o
f
9
8
.
8
2
%.
R
elev
a
n
t
r
esear
ch
er
s
co
u
ld
g
et
t
h
i
s
b
etter
ac
cu
r
ac
y
t
h
r
o
u
g
h
D
is
cr
ete
Or
th
o
g
o
n
al
Sto
ck
w
ell
T
r
an
s
f
o
r
m
(
DOST
)
u
s
in
g
Dis
cr
ete
C
o
s
i
n
e
T
r
an
s
f
o
r
m
(
DC
T
)
f
o
r
b
etter
r
ep
r
esen
tatio
n
o
f
t
h
e
E
C
G
s
ig
n
al
i
n
T
im
e
-
Fre
q
u
en
c
y
s
p
a
ce
.
T
o
elim
i
n
ate
t
h
e
r
ed
u
n
d
a
n
t
f
ea
t
u
r
es,
a
d
i
m
e
n
s
io
n
r
ed
u
c
t
io
n
h
ad
b
ee
n
d
o
n
e
w
it
h
P
r
in
cip
al
C
o
m
p
o
n
e
n
t
An
al
y
s
i
s
(
P
C
A
)
,
co
n
s
id
er
in
g
a
ll
th
e
m
o
r
p
h
o
lo
g
ical
c
h
ar
ac
te
r
is
tics
o
f
th
e
E
C
G
s
ig
n
al.
B
esid
es,
d
y
n
a
m
ic
R
-
R
in
ter
v
al
f
ea
tu
r
e
w
as
al
s
o
co
m
p
u
ted
an
d
co
n
ca
te
n
ated
to
co
n
s
tit
u
te
th
e
f
i
n
al
f
ea
t
u
r
e
s
et
co
n
s
is
t
in
g
2
0
f
ea
t
u
r
es.
Fu
r
t
h
er
o
p
ti
m
izatio
n
h
ad
b
ee
n
in
v
o
lv
ed
i
n
SVM
c
lass
if
ier
th
r
o
u
g
h
P
ar
ticle
S
w
ar
m
Op
ti
m
izatio
n
(
P
SO)
w
h
ile
u
s
i
n
g
MI
T
-
B
I
H
ar
r
h
y
t
h
m
ia
b
en
c
h
m
ar
k
d
atab
as
e
f
o
r
A
r
r
h
y
t
h
m
ia
class
i
f
icatio
n
.
As
m
e
n
tio
n
ed
ea
r
lie
r
,
t
h
e
ex
p
er
i
m
en
tal
r
es
u
lts
g
e
n
er
ated
an
i
m
p
r
o
v
ed
o
v
er
all
ac
cu
r
ac
y
o
f
9
8
.
8
2
% in
co
m
p
ar
is
o
n
w
i
th
t
h
e
co
n
v
en
tio
n
al
ap
p
r
o
ac
h
es a
v
a
ilab
le
p
r
io
r
to
th
is
r
esear
ch
li
te
r
atu
r
e.
T
h
e
n
o
v
el
id
ea
in
tr
o
d
u
ce
d
in
th
is
r
esear
c
h
is
to
ex
tr
ac
t
e
n
e
r
g
y
a
n
d
en
tr
o
p
y
f
r
o
m
t
h
e
E
C
G
s
ig
n
als.
Sin
ce
,
E
C
G
s
ig
n
als
ar
e
o
f
o
n
e
d
i
m
en
s
io
n
i
n
n
at
u
r
e,
it
is
to
co
n
v
er
t
it
to
2
d
im
en
s
io
n
al
s
i
g
n
al
s
as
a
p
r
ep
r
o
ce
s
s
in
g
s
tep
.
A
f
ter
o
b
tain
i
n
g
T
etr
o
let
tr
an
s
f
o
r
m
s
f
o
r
th
e
2
-
D
co
n
v
er
ted
E
C
G
s
ig
n
al,
en
er
g
y
a
n
d
en
tr
o
p
y
f
ea
t
u
r
es
ar
e
co
n
ca
te
n
ated
w
it
h
alr
e
ad
y
a
v
ailab
le
s
t
atis
tical
a
n
d
ch
ao
tic
f
ea
t
u
r
es.
Ho
w
e
v
er
,
th
e
to
ta
l
n
u
m
b
er
s
o
f
f
ea
t
u
r
es a
r
e
less
er
th
an
t
h
e
2
0
f
ea
t
u
r
es a
s
s
ee
n
i
n
ex
is
t
in
g
State
-
Of
-
T
h
e
-
A
r
t W
o
r
k
s
.
T
h
is
p
ap
er
h
as
b
ee
n
o
r
g
a
n
i
ze
d
as
f
o
llo
w
s
.
Sectio
n
1
d
is
p
la
y
s
t
h
e
r
ec
e
n
t
r
esear
ch
w
o
r
k
s
o
n
th
e
al
g
o
r
ith
m
u
s
ed
alo
n
g
w
it
h
t
h
e
s
u
f
f
er
i
n
g
s
i
n
t
h
o
s
e
w
o
r
k
s
.
S
ec
tio
n
2
d
escr
ib
es
th
e
MI
T
-
B
I
H
ar
r
h
y
t
h
m
ia
d
atab
ase,
1
-
D
to
2
-
D
co
n
v
er
s
io
n
o
f
E
C
G
s
i
g
n
a
ls
,
T
etr
o
let
tr
an
s
f
o
r
m
s
,
C
alc
u
latio
n
o
f
E
n
er
g
y
a
n
d
E
n
tr
o
p
y
f
ea
t
u
r
es
f
r
o
m
2
-
D
g
r
a
y
s
ca
le
i
m
a
g
es
a
n
d
o
v
er
all
tr
ai
n
in
g
a
n
d
test
i
n
g
b
ased
o
n
SVM
u
n
d
er
d
if
f
er
en
t
k
er
n
e
l
f
u
n
ctio
n
s
.
Sec
tio
n
3
p
r
esen
ts
p
er
f
o
r
m
a
n
ce
m
etr
ic
s
in
c
lu
d
i
n
g
s
e
n
s
iti
v
it
y
,
s
p
ec
i
f
icit
y
a
n
d
ac
cu
r
ac
y
b
ased
o
n
v
ar
io
u
s
T
etr
o
let
d
ec
o
m
p
o
s
itio
n
lev
el
s
an
d
d
if
f
er
e
n
t k
er
n
el
f
u
n
ct
io
n
s
i
n
SV
M
.
2.
RE
S
E
ARCH
M
E
T
H
O
D
2
.
1
.
Cha
ra
ct
er
iza
t
io
n o
f
E
CG
E
C
G
s
i
g
n
al
s
ar
e
f
u
n
d
a
m
en
ta
ll
y
w
ea
k
s
i
g
n
al
ac
q
u
ir
ed
f
r
o
m
e
lectr
o
d
es
af
ter
p
r
o
p
e
r
am
p
li
f
ic
atio
n
an
d
de
-
n
o
is
i
n
g
.
T
h
e
s
i
g
n
al
i
s
d
is
m
an
tled
i
n
to
P
,
Q,
R
,
S
a
n
d
T
w
a
v
es
g
lo
b
all
y
a
s
s
ee
n
i
n
Fig
u
r
e
1
.
T
h
e
ti
m
e
in
ter
v
a
l
b
et
w
ee
n
R
o
f
t
w
o
s
u
cc
es
s
iv
e
E
C
G
w
a
v
es
r
e
v
ea
l
s
th
e
h
ea
r
t
r
ate
[6
-
8]
.
T
h
e
h
ig
h
e
s
t
a
m
p
lit
u
d
e
is
o
b
tain
ed
f
r
o
m
QR
S c
o
m
p
le
x
w
h
ic
h
g
i
v
es
m
o
r
e
in
f
o
r
m
atio
n
o
n
th
e
h
ea
l
th
co
n
d
it
io
n
o
f
t
h
e
h
ea
r
t
[
9
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
6
,
Dec
em
b
er
2
0
1
9
:
5
0
0
6
-
50
1
5
5008
Fig
u
r
e
1
.
A
p
p
ea
r
an
ce
o
f
E
C
G
A
ll
b
io
m
ed
ical
s
i
g
n
als
i
n
cl
u
d
in
g
E
C
G
ar
e
v
er
y
d
i
f
f
ic
u
l
t
to
ac
q
u
ir
e
id
ea
ll
y
w
it
h
o
u
t
n
o
i
s
e.
Du
e
to
th
e
f
ea
t
u
r
es
o
f
f
ee
b
le
a
m
p
lit
u
d
e
an
d
f
r
eq
u
e
n
c
y
,
E
C
G
s
ig
n
als
ar
e
u
s
u
all
y
co
r
r
u
p
ted
b
y
d
if
f
er
en
t
k
i
n
d
s
o
f
n
o
is
es,
i
n
cl
u
d
in
g
th
e
p
o
w
er
lin
e
in
ter
f
er
en
ce
s
,
b
aselin
e
d
r
if
t
an
d
m
o
tio
n
ar
ti
f
ac
ts
[
1
0
]
.
Mo
s
t
o
f
th
e
r
esear
c
h
es
h
av
e
b
ee
n
d
o
n
e
b
ased
o
n
MI
T
-
B
I
H
ar
r
h
y
t
h
m
ia
d
atab
ase
w
h
ic
h
co
n
s
is
t
s
o
f
E
C
G
s
i
g
n
a
ls
in
th
e
f
o
llo
w
i
n
g
f
o
r
m
at
as
g
i
v
en
i
n
[
5
]
.
2
.
2
.
M
I
T
-
B
I
H
a
rr
hy
t
hm
ia
da
t
a
b
a
s
e
Fo
r
all
th
e
ex
p
er
i
m
e
n
ts
co
n
d
u
cted
,
E
C
G
r
ec
o
r
d
in
g
s
o
f
4
7
d
if
f
er
en
t
s
u
b
j
ec
ts
co
m
p
r
is
in
g
4
8
r
ec
o
r
d
s
st
u
d
ied
b
y
B
I
H
A
r
r
h
y
t
h
m
ia
la
b
o
r
ato
r
y
h
as
b
ee
n
u
s
ed
[
1
1
]
.
T
h
e
MI
T
-
B
I
H
d
atab
ase
c
o
v
er
s
1
1
0
1
0
9
b
ea
t
lab
els
w
h
ile
t
h
e
s
i
g
n
a
ls
ar
e
p
ass
ed
th
r
o
u
g
h
a
B
an
d
P
ass
Fil
ter
(
B
P
F)
w
h
en
t
h
e
cu
t
-
o
f
f
f
r
eq
u
en
cies
f
1
a
n
d
f
2
s
et
b
et
w
ee
n
0
.
1
Hz
an
d
1
0
0
Hz.
T
h
e
d
ig
itized
o
u
tp
u
ts
ar
e
o
b
ta
in
ed
af
ter
s
a
m
p
li
n
g
th
e
B
P
F
f
ilter
ed
s
ig
n
al
w
i
th
s
a
m
p
li
n
g
f
r
eq
u
en
c
y
o
f
3
6
0
s
a
m
p
les
p
er
s
ec
o
n
d
.
E
ac
h
s
a
m
p
le
ar
o
u
n
d
t
h
e
r
an
g
e
1
0
m
V
is
r
ep
r
ese
n
ted
b
y
d
ig
ital
d
ata
w
it
h
1
1
b
it
r
eso
lu
t
io
n
.
Mo
d
if
ied
li
m
b
lead
f
r
o
m
th
e
d
atab
ase
h
a
s
b
ee
n
u
s
ed
p
ar
ticu
lar
l
y
h
ea
r
t
b
ea
t
s
eg
m
e
n
ts
o
b
tain
ed
u
s
i
n
g
a
win
d
o
w
ac
r
o
s
s
ea
ch
R
-
p
ea
k
.
G
r
o
u
n
d
tr
u
t
h
o
b
tain
ed
f
r
o
m
th
e
class
a
n
n
o
tatio
n
s
p
r
o
v
id
ed
b
y
t
h
e
b
en
c
h
m
ar
k
d
atab
ase
is
u
s
ed
to
cr
o
s
s
co
n
f
ir
m
t
h
e
clas
s
i
f
icatio
n
p
er
f
o
r
m
an
ce
.
T
h
e
s
u
m
m
ar
y
o
f
th
e
d
ata
s
ets
a
n
d
th
e
d
eta
ils
o
f
1
6
E
C
G
s
i
g
n
al
c
lass
e
s
ar
e
p
r
o
v
id
ed
i
n
T
a
b
le
1
.
I
n
o
r
d
er
to
m
ain
tain
th
e
g
e
n
er
aliza
tio
n
,
as
s
elec
te
d
in
th
e
Sta
te
-
of
-
T
h
e
-
A
r
t
w
o
r
k
,
E
C
G
s
i
g
n
als
f
r
o
m
ea
c
h
o
f
th
e
1
6
clas
s
es
ar
e
ch
o
s
en
r
a
n
d
o
m
l
y
to
co
n
s
ti
tu
t
e
th
e
tr
ain
i
n
g
an
d
tes
tin
g
d
a
ta
s
ets
b
y
d
i
v
id
in
g
t
h
e
w
h
o
l
e
d
ata
s
et
in
to
1
6
b
u
n
c
h
es,
w
h
er
e
ea
c
h
g
r
o
u
p
r
e
p
r
esen
ts
th
eir
ca
teg
o
r
y
.
P
ar
ticu
lar
l
y
,
1
5
%
f
r
o
m
n
o
r
m
al
ca
te
g
o
r
y
,
3
5
%
f
r
o
m
‘
P
’
,
‘
A’
,
‘
V
’
,
‘
R
’
,
an
d
‘
L
’
ca
teg
o
r
y
,
an
d
4
0
%
f
r
o
m
ea
c
h
o
f
t
h
e
r
e
m
ai
n
in
g
te
n
clas
s
es
o
f
E
C
G
s
ig
n
al
s
ar
e
s
elec
ted
r
an
d
o
m
l
y
f
o
r
th
e
tr
a
i
n
i
n
g
d
ata
s
et,
i.e
.
,
a
to
tal
o
f
2
1
.
7
9
%
(
less
p
r
o
p
o
r
tio
n
f
o
r
tr
ain
in
g
)
e
v
en
t
s
o
f
t
h
e
w
h
o
le
d
ata
s
et
ar
e
s
elec
ted
f
o
r
th
e
tr
ain
i
n
g
d
ata
s
et
w
h
i
le
th
e
r
e
m
a
in
i
n
g
7
8
.
2
1
%
o
f
E
C
G
s
ig
n
als
ar
e
u
s
ed
f
o
r
test
in
g
th
e
p
r
o
p
o
s
ed
m
et
h
o
d
.
As
an
atte
m
p
t
to
i
m
p
r
o
v
e
t
h
e
r
esu
lts
o
b
tai
n
ed
in
[
5
]
ch
ao
ti
c
f
ea
tu
r
e
s
ets
h
av
e
b
ee
n
esti
m
ated
an
d
test
ed
in
[
1
2
]
.
I
n
o
r
d
er
to
s
till
i
m
p
r
o
v
e
th
e
ac
c
u
r
ac
y
p
er
f
o
r
m
an
ce
,
E
n
er
g
y
an
d
E
n
tr
o
p
y
f
ea
t
u
r
es
o
b
tain
ed
f
r
o
m
T
etr
o
let
tr
an
s
f
o
r
m
s
h
a
v
e
b
ee
n
ad
d
ed
to
th
e
ex
i
s
ti
n
g
[
1
2
]
f
ea
tu
r
e
s
et
s
.
I
t
h
a
s
b
ee
n
a
n
o
v
el
m
et
h
o
d
,
f
o
u
n
d
in
[
1
3
]
w
h
er
e
m
u
lt
ich
an
n
el
1
-
D
E
E
G
s
ig
n
al
s
h
ad
b
ee
n
tr
an
s
f
o
r
m
ed
to
v
o
lu
m
e
o
f
d
ata.
On
e
d
i
m
e
n
s
io
n
al
s
i
g
n
al
f
r
o
m
m
u
lti
-
elec
tr
o
d
es
f
ir
s
t
co
n
v
er
te
d
to
tw
o
d
i
m
en
s
io
n
al
m
atr
i
x
an
d
th
e
m
atr
ice
s
ar
e
co
n
ca
ten
ated
to
f
o
r
m
a
v
o
l
u
m
e
b
y
co
n
ca
te
n
ati
n
g
t
h
e
t
wo
d
im
e
n
s
io
n
al
m
atr
ice
s
.
Af
o
r
e
m
en
t
io
n
ed
w
o
r
k
co
n
f
ir
m
s
t
h
e
p
o
s
s
ib
ilit
y
th
at
wav
e
an
al
y
s
i
s
co
u
ld
b
e
d
o
n
e
in
2
-
D
an
d
3
-
D
s
p
ac
e.
W
av
elet
b
ased
E
C
G
an
al
y
s
i
s
h
ad
b
ee
n
d
o
n
e
i
n
[
1
4
]
,
w
h
er
e
f
ea
tu
r
e
s
f
r
o
m
w
av
e
let
c
o
ef
f
icie
n
t
s
w
er
e
u
s
ed
to
cla
s
s
i
f
y
Dex
tr
o
c
ar
d
ia,
T
ac
h
y
ca
r
d
ia,
B
r
ad
y
ca
r
d
ia,
Hy
p
er
k
ale
m
ia,
M
y
o
ca
r
d
i
al,
is
c
h
ae
m
ia,
H
y
p
er
ca
lcae
m
ia,
Si
n
o
atr
ial
b
lo
ck
an
d
Su
d
d
en
ca
r
d
iac
d
ea
th
.
C
e
y
la
n
an
d
C
a
n
b
ilen
h
a
v
e
f
o
u
n
d
i
n
[
1
5
]
,
T
etr
o
let
tr
an
s
f
o
r
m
s
co
u
ld
b
e
u
s
ed
i
n
m
ed
ical
i
m
a
g
e
p
r
o
ce
s
s
in
g
.
Si
n
ce
T
etr
o
let
tr
an
s
f
o
r
m
s
ar
e
ef
f
icie
n
t
t
o
d
escr
ib
e
th
e
g
eo
m
etr
ical
f
e
atu
r
es,
it
is
h
i
g
h
l
y
p
o
s
s
ib
le
to
ca
tch
t
h
e
f
ea
tu
r
e
s
b
ased
o
n
v
i
s
u
al
ap
p
ea
r
an
ce
.
T
h
e
s
ig
n
als
o
b
tai
n
ed
f
r
o
m
t
h
e
E
C
G
m
o
n
ito
r
i
n
g
d
ev
ice
o
r
w
a
v
e
f
o
r
m
s
o
b
tai
n
ed
f
r
o
m
MI
T
-
B
I
H
d
atab
ase
ar
e
o
f
o
n
e
d
i
m
e
n
s
io
n
r
ep
r
ese
n
ted
a
s
eith
er
r
o
w
m
atr
ix
o
r
co
lu
m
n
m
atr
i
x
.
A
za
d
et
a
l
,
in
[
1
6
]
h
av
e
g
r
ea
tl
y
in
s
p
ir
ed
a
w
a
y
o
f
co
n
v
er
t
in
g
1
-
D
s
i
g
n
al
i
n
to
2
-
D
s
ig
n
al
b
ased
o
n
en
er
g
y
v
al
u
es
f
r
o
m
t
h
e
ti
m
e
d
o
m
ain
s
i
g
n
al
s
.
T
h
e
o
v
er
all
f
lo
w
o
f
th
e
p
r
o
p
o
s
ed
A
r
r
h
y
th
m
ia
clas
s
i
f
icatio
n
s
y
s
te
m
i
s
s
h
o
w
n
i
n
F
ig
u
r
e
2
.
I
n
th
is
w
o
r
k
,
a
n
a
u
to
m
atic
A
r
r
h
y
th
m
ia
class
if
icatio
n
s
y
s
te
m
i
s
i
m
p
le
m
e
n
ted
f
o
r
th
e
E
C
G
s
i
g
n
al
s
av
ailab
le
in
MI
T
-
B
I
H
d
atab
ase.
T
h
e
co
m
p
let
e
i
m
p
le
m
e
n
tat
io
n
o
f
t
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
co
n
s
i
s
ts
o
f
b
o
th
1
-
D
an
d
2
-
D
p
r
o
ce
s
s
in
g
.
E
x
ce
p
t th
e
T
etr
o
let
tr
an
s
f
o
r
m
s
,
all
o
t
h
er
p
r
o
ce
s
s
in
g
ar
e
d
o
n
e
in
o
n
e
d
i
m
e
n
s
io
n
a
l sp
ac
e.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2
0
8
8
-
8708
On
th
e
cla
s
s
ifica
tio
n
o
f a
r
r
h
yth
mia
u
s
in
g
s
u
p
p
leme
n
ta
r
y
fea
tu
r
es fr
o
m
tet
r
o
let
tr
a
n
s
fo
r
m
s
(
G.
Ja
ya
g
o
p
i)
5009
T
ab
le
1
.
Data
s
ets p
r
esen
ted
in
[
1
1
]
EC
G
si
g
n
a
l
f
o
r
m
C
l
a
ss
A
n
n
o
t
a
t
i
o
n
T
o
t
a
l
T
r
a
i
n
i
n
g
se
t
s a
n
d
(
%)
T
e
st
se
t
s a
n
d
(
%)
N
o
r
mal
(
N
O
R
)
N
7
5
0
1
7
1
1
2
5
3
(
1
5
)
6
3
7
6
4
(
8
5
)
L
e
f
t
B
u
n
d
l
e
B
r
a
n
c
h
B
l
o
c
k
(
L
B
B
B
)
L
8
0
7
2
2
8
2
5
(
3
5
)
5
2
4
7
(
6
5
)
R
i
g
h
t
B
u
n
d
l
e
B
r
a
n
c
h
B
l
o
c
k
(
L
B
B
B
)
R
7
2
5
5
2
5
3
9
(
3
5
)
4
7
1
6
(
6
5
)
A
t
r
i
a
l
P
r
e
mat
u
r
e
C
o
n
t
r
a
c
t
i
o
n
(
A
P
C
)
A
2
5
4
6
8
9
1
(
3
5
)
1
6
5
5
(
6
5
)
P
r
e
v
e
n
t
r
i
c
u
l
a
r
C
o
n
t
r
a
c
t
i
o
n
(
P
V
C
)
V
7
1
2
9
2
4
9
5
(
3
5
)
4
6
3
4
(
6
5
)
P
a
c
e
d
b
e
a
t
(
P
A
C
E)
P
7
0
2
4
2
4
5
8
(
3
5
)
4
5
6
6
(
6
5
)
A
b
e
r
r
a
t
e
d
a
t
r
i
a
l
P
r
e
mat
u
r
e
b
e
a
t
(
A
P
)
a
1
5
0
7
5
(
4
0
)
7
5
(
6
0
)
V
e
n
t
r
i
c
u
l
a
r
F
l
u
t
t
e
r
(
V
F
)
!
4
7
2
2
3
6
(
4
0
)
2
3
6
(
6
0
)
F
u
si
o
n
o
f
v
e
n
t
r
i
c
u
l
a
r
a
n
d
n
o
r
mal
b
e
a
t
(
V
F
N
)
F
8
0
2
4
0
1
(
4
0
)
4
0
1
(
6
0
)
B
l
o
c
k
e
d
a
t
r
i
a
l
P
r
e
mat
u
r
e
b
e
a
t
(
B
A
P
)
x
1
9
3
9
7
(
4
0
)
9
6
(
6
0
)
N
o
d
a
l
(
Ju
n
c
t
i
o
n
a
l
Esc
a
p
e
B
e
a
t
)
j
2
2
9
1
1
5
(
4
0
)
1
1
4
(
6
0
)
F
u
si
o
n
o
f
P
a
c
e
d
a
n
d
N
o
r
mal
b
e
a
t
(
F
P
N
)
f
9
8
2
4
9
1
(
4
0
)
4
9
1
(
6
0
)
V
e
n
t
r
i
c
u
l
a
r
Esc
a
p
e
b
e
a
t
(
V
E)
E
1
0
6
5
3
(
4
0
)
5
3
(
6
0
)
N
o
d
a
l
(
Ju
n
c
t
i
o
n
a
l
)
P
r
e
mat
u
r
e
B
e
a
t
(
N
P
)
J
83
4
2
(
4
0
)
4
1
(
6
0
)
A
t
r
i
a
l
Esc
a
p
e
b
e
a
t
(
A
E)
e
16
8
(
4
0
)
8
(
6
0
)
U
n
c
l
a
ssi
f
i
a
b
l
e
b
e
a
t
(
U
N
)
Q
33
1
7
(
4
0
)
1
6
(
6
0
)
T
o
t
a
l
1
1
0
1
0
9
2
3
9
9
6
(
2
1
.
7
9
)
8
6
1
1
3
(
7
8
.
2
1
)
Fig
u
r
e
2
.
B
lo
ck
d
iag
r
a
m
o
f
t
h
e
p
r
o
p
o
s
ed
a
r
r
h
y
t
h
m
ia
clas
s
i
f
i
ca
tio
n
s
y
s
te
m
C
o
n
v
er
tin
g
1
-
D
to
2
-
D
s
ig
n
a
l
is
a
s
tr
aig
h
t
f
o
r
w
ar
d
p
r
o
ce
s
s
w
h
er
e,
ea
ch
ti
m
e
s
a
m
p
le
o
f
th
e
E
C
G
w
a
v
e
is
m
ap
p
ed
to
an
elem
en
t
in
t
h
e
m
atr
i
x
o
f
s
ize
M
x
N
.
A
ll
th
e
lo
ca
tio
n
s
ar
e
f
i
lled
b
y
co
n
s
u
m
i
n
g
th
e
s
u
cc
e
s
s
i
v
e
ti
m
e
s
a
m
p
les
f
r
o
m
th
e
E
C
G
s
i
g
n
a
l
as
g
i
v
e
n
in
Fi
g
u
r
e
3
.
B
y
th
e
n
at
u
r
e
o
f
E
C
G
s
ig
n
al
s
,
it
i
s
o
b
v
io
u
s
t
h
at
n
e
g
ati
v
e
s
a
m
p
les
also
w
o
u
ld
b
e
p
r
esen
t d
u
e
to
th
e
v
o
lta
g
e
alter
n
a
tio
n
s
.
B
u
t,
n
eg
ati
v
e
ele
m
e
n
t
s
i
n
2
-
D
m
atr
ix
ar
e
n
o
t
p
er
m
itted
i
n
a
d
i
g
ital
i
m
a
g
e
a
s
t
h
e
g
r
a
y
s
ca
le
is
f
r
o
m
0
to
2
5
5
.
T
h
er
ef
o
r
e,
n
o
r
m
aliza
tio
n
i
s
d
o
n
e
o
n
th
e
2
-
D
m
atr
i
x
y
ield
i
n
g
a
g
r
a
y
s
ca
le
i
m
a
g
e
as s
h
o
wn
in
Fig
u
r
e
4.
Fig
u
r
e
3
.
T
r
an
s
f
o
r
m
atio
n
o
f
t
i
m
e
s
a
m
p
les to
2
-
D
m
atr
i
x
[
1
6
]
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
6
,
Dec
em
b
er
2
0
1
9
:
5
0
0
6
-
50
1
5
5010
Fig
u
r
e
4
.
2
-
D
m
atr
i
x
to
g
r
a
y
s
ca
le
i
m
a
g
e
co
n
v
er
s
io
n
2
.
3
.
T
et
ro
let
t
ra
ns
f
o
r
m
Haa
r
w
a
v
elet
d
ec
o
m
p
o
s
itio
n
(
HW
D)
ef
f
ec
t
iv
el
y
u
tili
ze
s
t
h
e
s
q
u
ar
e
s
h
ap
ed
m
o
th
er
w
a
v
ele
t
f
u
n
ct
io
n
w
h
ile
e
x
a
m
i
n
i
n
g
th
e
s
i
g
n
a
ls
.
B
esid
es,
th
e
m
et
h
o
d
an
al
y
s
es
th
e
s
i
g
n
al
i
n
ter
m
s
o
f
o
r
th
o
n
o
r
m
al
b
asis
w
h
ic
h
s
u
cc
e
s
s
f
u
ll
y
d
ec
o
m
p
o
s
es t
h
e
1
-
D
a
n
d
2
-
D
s
i
g
n
al
s
i
n
to
d
if
f
er
en
t p
ar
ts
b
ased
o
n
its
d
i
f
f
er
en
t
p
r
o
p
er
ties
s
u
ch
a
s
:
s
h
i
f
ted
f
u
n
c
tio
n
,
l
in
ea
r
co
m
b
in
atio
n
an
d
o
r
t
h
o
g
o
n
al
i
ties
.
Du
e
to
t
h
e
e
f
f
ec
ti
v
e
d
ec
o
m
p
o
s
in
g
p
r
o
ce
s
s
,
Haa
r
w
a
v
elet
is
co
n
s
id
er
ed
to
b
e
a
f
air
to
o
l
f
o
r
s
ig
n
al
a
n
al
y
s
is
[
1
7
]
.
T
h
e
u
n
d
er
l
y
i
n
g
co
n
ce
p
t
o
f
th
is
al
g
o
r
ith
m
is
s
i
m
p
le
b
u
t
e
n
o
r
m
o
u
s
l
y
e
f
f
e
ctiv
e.
T
h
e
al
g
o
r
ith
m
co
n
s
tr
u
ct
io
n
is
s
i
m
ilar
to
th
a
t
o
f
t
h
e
d
i
g
ital
w
ed
g
elet
s
[
1
8
]
in
w
h
ich
o
n
l
y
t
h
e
Haa
r
f
u
n
cti
o
n
s
o
n
w
ed
g
e
p
ar
titi
o
n
s
ar
e
u
s
ed
.
Usi
n
g
th
i
s
alg
o
r
it
h
m
,
w
e
d
iv
id
e
ea
ch
i
m
a
g
e
in
to
4
x
4
b
lo
ck
s
an
d
d
eter
m
i
n
e
d
th
at
in
ea
ch
b
lo
ck
,
a
T
etr
o
m
in
o
p
ar
titi
o
n
is
ad
ap
ted
to
th
e
i
m
a
g
e
g
eo
m
etr
y
o
f
ea
ch
b
lo
ck
s
.
Usi
n
g
t
h
is
g
eo
m
e
tr
ical
s
h
ap
e,
a
Haa
r
w
a
v
elet
t
y
p
e
ca
lled
th
e
T
etr
o
let
is
d
ef
in
e
d
.
T
h
is
f
ilter
b
an
k
alg
o
r
ith
m
is
u
s
ed
to
d
ec
o
m
p
o
s
e
an
i
m
a
g
e
an
d
o
b
tain
T
etr
o
let
co
ef
f
icie
n
t
s
o
f
d
ec
o
m
p
o
s
ed
s
u
b
b
an
d
s
.
T
h
e
T
etr
o
m
i
n
o
es
b
lo
ck
s
ar
e
m
ad
e
b
y
t
h
e
co
m
b
i
n
atio
n
o
f
f
o
u
r
eq
u
al
-
s
ized
s
q
u
ar
es
t
h
at
ar
e
co
n
n
ec
ted
to
ea
ch
o
th
er
w
it
h
at
least
o
n
e
s
q
u
ar
e
i
s
j
o
in
ed
alo
n
g
w
it
h
a
n
ed
g
e.
T
h
er
e
ar
e
f
i
v
e
b
asic
T
etr
o
m
in
o
es
s
h
ap
es
ar
e
av
ailab
le
as s
h
o
w
n
i
n
Fi
g
u
r
e
5
.
Fig
u
r
e
5
.
B
asic f
iv
e
s
h
ap
es o
f
t
etr
o
m
in
o
es
T
h
e
co
n
ce
p
t
o
f
th
e
T
etr
o
let
tr
an
s
f
o
r
m
ca
n
b
e
u
n
d
er
s
to
o
d
m
o
r
e
clea
r
ly
b
y
elab
o
r
atin
g
it
with
s
u
itab
le
n
o
tatio
n
s
an
d
ter
m
i
n
o
lo
g
ie
s
.
T
h
e
alg
o
r
it
h
m
ca
n
b
e
u
s
ed
o
n
a
2
-
D
d
ata
b
y
f
ir
s
t id
en
ti
f
y
in
g
it
s
in
d
ex
s
ets a
n
d
it
s
co
r
r
esp
o
n
d
in
g
n
e
ig
h
b
o
r
h
o
o
d
v
alu
e
s
.
Fo
r
ex
a
m
p
le,
let
I
={
(
m,
n
)
:
m,
n
=0
,
1
,
2
…,
M
-
1
}
b
e
th
e
s
et
o
f
i
n
d
ex
o
f
a
n
i
m
a
g
e
I
=f
(
m,
n
)
w
h
er
e
M
=
2
J
,
an
d
th
e
n
eig
h
b
o
r
h
o
o
d
n
~
o
f
in
d
ex
(
m,
n
)
is
ei
th
er
at
th
e
v
er
tex
o
r
at
t
h
e
b
o
u
n
d
ar
ies.
T
h
e
eq
u
atio
n
ca
n
b
e
d
ef
in
ed
as:
1
,
,
1
,
,
,
1
,
,
1
,
~
n
m
n
m
n
m
n
m
n
m
n
(1
)
2
.
4
.
F
ea
t
ures f
ro
m
2
-
D
g
ra
y
s
ca
l
e
i
m
a
g
e
Fro
m
th
e
T
etr
o
let
s
u
b
-
b
an
d
s
co
ef
f
icie
n
t
s
,
th
e
f
ea
t
u
r
es
lik
e
en
er
g
y
an
d
en
tr
o
p
y
v
al
u
es
ar
e
o
b
tain
ed
w
h
ic
h
ar
e
v
er
y
u
s
e
f
u
l
i
n
an
y
class
i
f
icatio
n
s
y
s
te
m
.
I
n
g
e
n
er
al,
th
e
en
er
g
y
s
i
g
n
at
u
r
es
w
il
l
af
f
o
r
d
a
g
o
o
d
in
d
icatio
n
ab
o
u
t
t
h
e
to
tal
e
n
er
g
y
p
r
ese
n
t
s
p
ec
i
f
icall
y
at
a
n
y
s
p
atial
o
r
f
r
eq
u
en
c
y
le
v
els
a
n
d
o
r
ien
tatio
n
s
[
1
9
]
.
I
t is ass
u
m
ed
th
at,
i
n
th
e
e
n
er
g
y
b
ased
ap
p
r
o
ac
h
es,
d
if
f
er
en
t
en
er
g
y
d
is
tr
ib
u
t
io
n
s
ar
e
p
r
ese
n
t a
t v
ar
io
u
s
te
x
t
u
r
e
p
atter
n
s
o
f
a
n
y
s
p
atial
o
r
f
r
eq
u
en
c
y
d
o
m
ai
n
s
.
L
et
en
er
g
y
(
E
)
is
an
ex
ten
t
o
f
p
ix
el
p
air
r
ep
etitio
n
s
th
at
m
ea
s
u
r
es t
h
e
u
n
i
f
o
r
m
it
y
o
f
a
n
i
m
a
g
e.
T
h
e
T
etr
o
let
b
ased
en
er
g
y
f
ea
tu
r
e
i
s
d
ef
i
n
ed
as
(
)
=
√
∑
∑
,
−
1
=
0
−
1
=
0
(
2
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2
0
8
8
-
8708
On
th
e
cla
s
s
ifica
tio
n
o
f a
r
r
h
yth
mia
u
s
in
g
s
u
p
p
leme
n
ta
r
y
fea
tu
r
es fr
o
m
tet
r
o
let
tr
a
n
s
fo
r
m
s
(
G.
Ja
ya
g
o
p
i)
5011
w
h
er
e,
E
(
I
)
b
e
t
h
e
e
n
er
g
y
o
f
in
p
u
t
i
m
ag
e
I
,
M
i,
j
b
e
t
h
e
s
u
b
-
b
an
d
co
e
f
f
ic
ien
t
s
at
lo
ca
tio
n
(
i,
j
)
a
n
d
N
b
e
th
e
s
ize
o
f
th
e
s
u
b
-
b
an
d
s
.
E
n
tr
o
p
y
i
s
d
ef
in
ed
a
s
t
h
e
s
ta
tis
tical
m
ea
s
u
r
e
m
e
n
t
o
f
t
h
e
u
n
ce
r
tai
n
t
y
d
e
g
r
ee
an
d
th
e
i
n
f
o
r
m
atio
n
co
n
ten
t
o
f
a
m
ess
a
g
e
ex
is
t
s
in
a
s
y
s
te
m
[
2
0
]
.
T
h
e
en
tr
o
p
y
g
iv
es
a
m
ea
s
u
r
e
m
e
n
t
o
f
i
n
f
o
r
m
atio
n
an
d
th
er
e
f
o
r
e
it
is
ad
o
p
ted
to
ch
ar
ac
ter
ize
an
i
m
ag
e
ea
c
h
o
f
w
h
ic
h
i
s
co
n
s
id
er
ed
as
a
s
p
ec
if
ic
f
ea
t
u
r
e.
T
h
e
T
etr
o
let
b
ased
en
tr
o
p
y
f
e
at
u
r
e
is
d
ef
in
ed
as:
=
−
∑
(
)
2
(
)
=
1
(
3
)
w
h
er
e,
P
(
x
j
)
is
t
h
e
p
r
o
b
ab
ilit
y
d
is
tr
ib
u
tio
n
.
2
.
5
.
F
ea
t
ures f
ro
m
1
-
D
E
C
G
Sig
na
l
B
y
n
at
u
r
e,
th
e
r
h
y
th
m
o
f
t
h
e
h
ea
r
t
is
n
o
t
s
y
n
ch
r
o
n
ized
to
an
y
co
m
m
o
n
clo
c
k
an
d
v
ar
i
es
a
m
o
n
g
in
d
iv
id
u
als
b
ased
o
n
t
h
e
b
ea
t
co
u
n
t
p
er
m
i
n
u
te.
A
ls
o
,
it
d
ep
en
d
s
o
n
cu
r
r
e
n
t
p
h
y
s
ical
a
n
d
n
atu
r
al
co
n
d
itio
n
s
o
f
th
e
test
s
p
ec
i
m
e
n
.
T
h
e
r
h
y
t
h
m
v
ar
iatio
n
i
s
u
s
u
all
y
ca
u
g
h
t
f
r
o
m
th
e
R
-
R
i
n
ter
v
al
b
et
w
ee
n
t
w
o
h
ea
r
t
b
ea
ts
a
n
d
th
is
f
ea
t
u
r
e
is
a
g
o
o
d
r
ep
r
es
en
tati
v
e
o
f
t
h
e
d
y
n
a
m
ic
ch
ar
ac
ter
is
tic
o
f
t
h
e
E
C
G
s
i
g
n
al
s
.
Af
o
r
e
m
e
n
tio
n
ed
T
ab
le
2
clea
r
ly
s
tate
s
th
e
li
s
t
o
f
f
ea
t
u
r
es
w
h
ich
ar
e
u
s
ed
in
th
i
s
p
r
o
p
o
s
al
an
d
co
r
r
esp
o
n
d
in
g
f
o
r
m
u
la
to
esti
m
ate
th
e
m
.
T
h
e
co
m
b
in
at
io
n
o
f
th
e
p
r
e
an
d
p
o
s
t
R
-
R
in
ter
v
al
f
ea
t
u
r
e
o
f
th
e
E
C
G
s
i
g
n
al
co
r
r
esp
o
n
d
s
to
an
in
s
ta
n
ta
n
eo
u
s
r
h
y
t
h
m
c
h
ar
ac
te
r
is
tic.
T
h
e
m
ea
n
R
-
R
in
ter
v
al
f
ea
t
u
r
e
is
d
er
iv
ed
b
y
a
v
er
ag
in
g
t
h
e
R
-
R
in
ter
v
al
s
o
f
t
h
e
ea
r
lier
3
m
in
u
tes
d
at
a
o
f
a
p
ar
ticu
lar
s
p
ec
i
m
en
.
L
i
k
e
w
is
e,
t
h
e
lo
ca
l
-
R
-
R
f
ea
t
u
r
e
is
d
er
iv
ed
b
y
ca
lcu
lati
n
g
t
h
e
m
ea
n
o
f
all
t
h
e
R
-
R
in
ter
v
al
s
o
f
th
e
ea
r
lier
8
s
ec
o
n
d
s
d
ata
o
f
a
p
ar
tic
u
lar
e
v
en
t.
I
n
s
tan
ta
n
eo
u
s
in
ter
v
a
l
m
a
y
n
o
t
b
e
tr
u
s
tab
le
in
f
o
r
m
atio
n
f
o
r
d
ec
id
in
g
ab
n
o
r
m
alit
y
.
T
h
er
ef
o
r
e,
lo
ca
l
an
d
m
ea
n
R
-
R
f
ea
t
u
r
es
ar
e
also
co
n
s
id
er
ed
w
h
ich
r
ep
r
esen
t
th
e
a
v
er
ag
e
ch
ar
ac
ter
is
t
ics
o
f
a
s
er
ies
o
f
E
C
G
s
ig
n
als
.
Fu
r
th
er
,
k
u
r
to
s
is
,
s
k
e
w
n
es
s
a
n
d
s
ta
n
d
ar
d
d
ev
iatio
n
ar
e
ca
lcu
lated
f
r
o
m
t
h
e
o
b
tain
ed
R
-
R
in
ter
v
al
[
1
2
]
.
Fin
a
ll
y
,
all
t
h
e
f
ea
t
u
r
e
s
alo
n
g
w
i
th
e
n
er
g
y
a
n
d
en
tr
o
p
y
f
ea
t
u
r
es
ar
e
co
n
ca
ten
ated
.
As
a
r
es
u
lt,
1
5
h
y
b
r
id
f
ea
t
u
r
es
(
i.e
.
,
f
o
u
r
R
-
R
in
ter
v
a
l
f
ea
t
u
r
es,
s
ix
c
h
ao
tic
f
ea
tu
r
es
(
Ma
x
i
m
u
m
L
E
,
Mi
n
i
m
u
m
L
E
,
Av
er
ag
e
L
E
,
Sta
n
d
ar
d
d
ev
iatio
n
o
f
L
E
,
KSE
d
en
s
it
y
an
d
KSE
g
e
n
er
a
lit
y
)
,
th
r
ee
s
tati
s
tical
f
ea
t
u
r
es
an
d
t
w
o
T
etr
o
let
f
ea
tu
r
es
(
E
n
er
g
y
an
d
E
n
tr
o
p
y
)
ar
e
d
eter
m
i
n
ed
to
r
ep
r
esen
t
ea
ch
d
en
o
is
ed
in
p
u
t
E
C
G
a
n
d
ar
e
f
u
r
t
h
er
p
r
o
ce
s
s
e
d
f
o
r
class
if
ica
tio
n
.
P
r
io
r
to
th
e
e
x
tr
ac
tio
n
o
f
af
o
r
e
m
en
tio
n
ed
f
ea
t
u
r
es,
E
C
G
d
ata
is
f
i
lt
er
ed
u
s
in
g
a
r
ele
v
an
t
L
o
w
P
ass
Fi
lter
(
L
P
F)
w
it
h
cu
t
-
o
f
f
f
r
eq
u
e
n
c
y
4
0
0
Hz
to
r
e
m
o
v
e
t
h
e
in
ter
f
er
i
n
g
lo
w
f
r
eq
u
en
c
y
n
o
i
s
e.
T
ab
le
2
.
L
is
t o
f
1
-
D
a
n
d
2
-
D
f
ea
tu
r
es
C
i
t
a
t
i
o
n
N
a
me
o
f
t
h
e
f
e
a
t
u
r
e
M
e
t
h
o
d
o
r
E
q
u
a
t
i
o
n
u
se
d
1
[
5
]
P
r
e
R
-
R
T
i
me
i
n
t
e
r
v
a
l
b
e
t
w
e
e
n
P
r
e
v
i
o
u
s a
n
d
C
u
r
r
e
n
t
R
-
p
e
a
k
2
[
5
]
P
o
st
R
-
R
T
i
me
i
n
t
e
r
v
a
l
b
e
t
w
e
e
n
C
u
r
r
e
n
t
a
n
d
f
o
l
l
o
w
e
d
R
-
p
e
a
k
3
[
5
]
L
o
c
a
l
R
-
R
A
v
e
r
a
g
e
o
f
R
-
R
i
n
t
e
r
v
a
l
s o
f
p
a
s
t
8
se
c
o
n
d
s e
p
i
so
d
e
4
[
5
]
A
v
e
r
a
g
e
R
-
R
A
v
e
r
a
g
e
o
f
R
-
R
i
n
t
e
r
v
a
l
s o
f
p
a
s
t
3
m
i
n
u
t
e
e
p
i
so
d
e
5
[
4
]
M
a
x
i
m
u
m
L
E
M
a
x
(
li
m
→
∞
log
|
(
)
|
)
6
[
4
]
M
i
n
i
m
u
m
L
E
M
i
n
(
li
m
→
∞
log
|
(
)
|
)
7
[
4
]
A
v
e
r
a
g
e
L
E
M
e
a
n
(
li
m
→
∞
log
|
(
)
|
)
8
[
4
]
S
t
a
n
d
a
r
d
d
e
v
i
a
t
i
o
n
o
f
L
E
=
√
(
)
2
−
[
(
)
]
2
w
h
e
r
e
,
E(
X)
i
s
t
h
e
e
x
p
e
c
t
e
d
v
a
l
u
e
o
f
L
E
s
e
r
i
e
s
9
[
1
2
]
K
S
E
d
e
n
si
t
y
∑
+
(
)
=
1
10
[
1
2
]
K
S
E
g
e
n
e
r
a
l
i
t
y
′
11
[
1
2
]
K
u
r
t
o
si
s
=
{
(
+
1
)
(
−
1
)
(
−
2
)
(
−
3
)
×
∑
(
−
4
)
4
=
1
}
−
3
(
−
1
)
2
(
−
2
)
(
−
3
)
W
h
e
r
e
,
n
=
s
a
mp
l
e
si
z
e
,
s=st
a
n
d
a
r
d
d
e
v
i
a
t
i
o
n
12
[
1
2
]
S
k
e
w
n
e
ss
=
(
−
1
)
(
−
2
)
∑
(
−
)
3
=
1
3
W
he
r
e
,
n
=
sa
m
p
le
si
z
e
,
s
=
st
a
n
dar
d
dev
i
a
t
i
o
n
13
[
1
2
]
S
t
a
n
d
a
r
d
d
e
v
i
a
t
i
o
n
o
f
t
i
me
se
r
i
e
s
=
√
(
)
2
−
[
(
)
]
2
w
h
e
r
e
,
E(
X)
i
s
t
h
e
e
x
p
e
c
t
e
d
v
a
l
u
e
o
f
t
i
me
se
r
i
e
s
14
[
1
5
,
19]
En
e
r
g
y
√
∑
∑
,
−
1
=
0
−
1
=
0
W
h
e
r
e
,
,
=
su
b
-
b
a
n
d
c
o
e
f
f
i
c
i
e
n
t
s
a
t
l
o
c
a
t
i
o
n
(
i
,
j
)
an
d
N
=
si
z
e
o
f
t
h
e
s
u
b
-
b
a
n
d
s.
15
[
1
5
,
19]
En
t
r
o
p
y
−
∑
(
)
2
(
)
=
1
W
h
e
r
e
,
P(
x
j
)
i
s
t
h
e
p
r
o
b
a
b
i
l
i
t
y
d
i
s
t
r
i
b
u
t
i
o
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
6
,
Dec
em
b
er
2
0
1
9
:
5
0
0
6
-
50
1
5
5012
2
.
6
.
S
VM
c
la
s
s
if
ica
t
io
n
T
h
e
SVM
class
if
ier
ca
n
b
e
u
s
ed
as
a
to
o
l
f
o
r
t
h
e
r
ec
o
g
n
it
io
n
an
d
cla
s
s
i
f
icatio
n
p
r
o
ce
s
s
in
m
a
ny
m
ac
h
in
e
lear
n
i
n
g
ap
p
licatio
n
s
[
2
1
]
.
SVM
is
v
er
y
u
s
ef
u
l
in
b
i
n
ar
y
cla
s
s
if
ica
tio
n
a
n
d
also
as
m
u
lticla
s
s
class
i
f
icatio
n
in
v
ar
io
u
s
ap
p
lic
atio
n
s
.
I
t
is
m
o
s
t
p
o
p
u
lar
f
o
r
its
o
n
e
v
er
s
u
s
o
n
e
a
n
d
th
e
o
n
e
v
er
s
u
s
all
ap
p
r
o
ac
h
m
ea
n
s
.
T
h
e
alg
o
r
ith
m
ca
n
b
e
u
n
d
er
s
to
o
d
as
f
o
llo
w
s
.
L
et
{
x
1
,x
2
,
x
3
….x
n
}
b
e
th
e
tr
ain
in
g
s
ets
o
f
a
class
X
,
w
h
er
e
X
⊂
R
n
.
I
f
th
e
m
ap
p
in
g
s
f
u
n
ctio
n
i
s
th
en
:
X
⟶
H
i
s
t
h
e
f
ea
t
u
r
e
s
p
ac
e.
T
h
en
th
e
eq
u
atio
n
ca
n
b
e
d
er
iv
ed
as
[
1
2
‖
‖
2
+
1
∑
−
=
1
]
(
4
)
w
it
h
s
u
b
j
ec
t
to
w
.(
x
i
)
⩾
p
-
ξ
,
let
i=1
,
2
,
.
.
n
an
d
ξ
i
⩾
0
,
T
h
en
,
b
e
th
e
s
lack
v
ar
iab
le
to
p
en
alize
m
is
c
lass
if
ica
tio
n
,
p
is
th
e
b
ias an
d
n
is
t
h
e
n
u
m
b
er
o
f
ex
a
m
p
le
s
.
3.
RE
SU
L
T
S
A
ND
AN
AL
Y
SI
S
3
.
1
.
P
er
f
o
r
m
a
nce
m
et
rics
T
h
e
p
er
f
o
r
m
a
n
ce
an
al
y
s
is
f
o
r
ea
ch
clas
s
o
f
e
v
en
t
i
s
est
i
m
ated
b
y
co
m
p
u
ti
n
g
T
r
u
e
p
o
s
itiv
e
(
T
P
),
T
r
u
e
n
eg
at
iv
e
(
T
N
)
,
F
alse
p
o
s
itiv
e
(
F
P
)
an
d
F
alse
n
e
g
ati
v
e
(
F
N
)
p
ar
am
eter
s
,
w
h
er
e
(
T
P
)
an
d
(
T
N
)
r
ep
r
esen
t
th
e
co
r
r
ec
t
class
if
icat
io
n
o
f
th
e
n
o
r
m
al
an
d
ab
n
o
r
m
al
E
C
G
s
ig
n
als.
On
t
h
e
b
asis
o
f
t
h
ese
T
P
,
T
N
,
F
P
,
F
N
p
ar
am
eter
s
,
th
e
p
er
f
o
r
m
an
ce
m
etr
ics
f
o
r
ea
ch
class
o
f
s
i
g
n
al
ar
e
ca
lcu
lated
n
a
m
el
y
,
s
en
s
iti
v
it
y
,
s
p
ec
i
f
icit
y
an
d
p
o
s
itiv
e
p
r
ed
ictiv
i
t
y
w
h
er
e
,
s
en
s
i
tiv
it
y
i
s
t
h
e
r
ate
o
f
co
r
r
ec
tl
y
clas
s
i
f
ied
ev
e
n
ts
a
m
o
n
g
th
e
to
tal
n
u
m
b
er
o
f
ev
en
t
s
,
w
h
er
ea
s
p
o
s
iti
v
e
p
r
ed
ictiv
it
y
r
ef
er
s
to
th
e
r
ate
o
f
co
r
r
ec
tly
clas
s
i
f
ied
ev
en
t
s
i
n
a
ll
d
etec
ted
ev
en
ts
.
Usi
n
g
t
h
ese
d
ef
in
i
tio
n
s
,
s
en
s
iti
v
it
y
a
n
d
s
p
ec
i
f
icit
y
ca
n
b
e
d
ef
in
ed
as
=
+
×
100
,
=
+
×
100
(
5
)
T
h
e
o
v
er
all
ac
cu
r
ac
y
an
d
er
r
o
r
r
ate
ca
n
b
e
d
ef
in
ed
as g
i
v
e
n
i
n
E
q
u
atio
n
s
(
6
)
an
d
(
7
)
r
esp
ec
tiv
el
y
.
(
%
)
=
×
100
(
6
)
(
%
)
=
×
100
(
7
)
A
ll
th
e
s
e
m
en
tio
n
ed
p
ar
a
m
et
er
s
ar
e
co
m
p
u
ted
a
n
d
h
i
g
h
li
g
h
ted
b
ased
o
n
th
e
s
i
m
u
latio
n
ca
r
r
ied
o
u
t
u
s
i
n
g
MI
T
-
B
I
H
d
ata
b
ase.
3
.
2
.
Ana
ly
s
is
T
h
e
p
r
o
p
o
s
ed
f
ea
tu
r
e
e
x
tr
ac
ti
o
n
an
d
cla
s
s
i
f
icat
io
n
m
et
h
o
d
s
ar
e
i
m
p
le
m
e
n
ted
u
s
i
n
g
m
at
h
e
m
a
tical,
s
tatis
t
ical,
i
m
a
g
e
p
r
o
ce
s
s
in
g
an
d
w
a
v
elet
to
o
l
b
o
x
es
av
ailab
l
e
in
MA
T
L
A
B
s
o
f
t
w
ar
e
(
v
er
s
i
o
n
2
0
1
8
a
)
p
ac
k
ag
e
in
s
ta
lled
o
n
W
in
d
o
w
s
8
.
1
o
p
e
r
atin
g
s
y
s
te
m
(
i.e
.
,
A
M
D
E
1
-
2
1
0
0
p
r
o
ce
s
s
o
r
,
1
GHz
,
4
G
B
R
AM
)
.
MI
T
-
B
I
H
ar
r
h
y
t
h
m
ia
b
en
c
h
m
ar
k
d
atab
ase
w
as
u
s
ed
to
v
al
id
ate
th
e
p
r
o
p
o
s
ed
m
eth
o
d
.
T
h
e
SV
M
class
i
f
ier
i
s
tr
ai
n
ed
w
it
h
2
1
.
8
% tr
ain
i
n
g
d
ata
s
et
m
en
tio
n
ed
i
n
T
ab
le
1
an
d
its
p
er
f
o
r
m
an
ce
is
a
n
al
y
ze
d
f
o
r
ea
ch
test
ed
E
C
G
s
i
g
n
al
u
n
d
er
L
i
n
ea
r
,
2
nd
o
r
d
er
p
o
ly
n
o
m
ial,
5
th
o
r
d
er
p
o
ly
n
o
m
i
al
an
d
R
B
F
k
er
n
el
f
u
n
ctio
n
s
.
T
h
e
p
r
ed
ictio
n
p
er
f
o
r
m
a
n
ce
o
f
t
h
e
test
ed
E
C
G
s
i
g
n
al
s
i
n
to
t
h
eir
1
6
ca
teg
o
r
ies
u
s
in
g
t
h
e
p
r
o
p
o
s
ed
R
B
F
-
SVM
clas
s
i
f
icatio
n
m
et
h
o
d
is
p
r
esen
ted
in
t
h
e
f
o
r
m
o
f
co
n
f
u
s
io
n
m
atr
i
x
s
h
o
w
n
in
T
ab
le
3
.
A
b
r
ie
f
d
is
c
u
s
s
io
n
o
n
t
h
e
co
n
f
u
s
io
n
m
atr
ix
is
p
r
ese
n
ted
b
elo
w
.
T
h
e
b
o
ld
v
al
u
es
s
h
o
w
n
d
ia
g
o
n
al
w
is
e
in
d
icate
s
t
h
at
n
u
m
b
er
o
f
in
s
ta
n
ce
s
co
r
r
ec
tl
y
clas
s
i
f
ie
d
.
I
t
co
u
ld
b
e
n
o
ted
th
at
6
3
3
7
1
s
ig
n
a
ls
ar
e
class
i
f
ied
as
n
o
r
m
al
ca
teg
o
r
y
f
r
o
m
to
tal
6
3
7
6
4
s
ig
n
als
o
f
n
o
r
m
al
cla
s
s
.
R
e
m
ai
n
i
n
g
ele
m
e
n
ts
in
t
h
e
f
ir
s
t
r
o
w
s
h
o
w
s
th
e
n
u
m
b
er
o
f
in
s
ta
n
ce
s
cla
s
s
if
ied
w
r
o
n
g
l
y
i
n
o
th
er
ca
te
g
o
r
ies.
I
n
co
lu
m
n
1
,
6
3
4
3
1
n
o
r
m
al
s
ig
n
als
ar
e
d
etec
ted
in
th
e
‘
n
o
r
m
al
’
clas
s
th
at
i
n
clu
d
es
s
i
g
n
al
s
f
r
o
m
t
h
e
o
th
er
ca
teg
o
r
ies,
i.e
.
,
6
3
3
7
1
‘
n
o
r
m
al
’
s
i
g
n
als
ar
e
co
r
r
ec
tly
c
lass
if
ied
.
So
T
P
in
th
is
ca
s
e
is
6
3
3
7
1
s
ig
n
al
s
a
n
d
T
P
+F
N
eq
u
a
ls
6
3
7
6
4
s
ig
n
al
s
.
I
n
th
e
id
en
t
ical
p
r
o
ce
d
u
r
e,
th
e
class
i
f
ica
tio
n
r
esu
lt
s
f
o
r
th
e
o
th
er
1
5
clas
s
es
o
f
E
C
G
s
i
g
n
als
ar
e
ca
lcu
late
d
an
d
p
r
esen
ted
i
n
T
ab
le
3
.
A
s
an
o
v
er
all
p
er
f
o
r
m
an
ce
,
o
u
t
o
f
8
6
1
1
3
test
s
ig
n
als
in
to
tal,
8
5
5
5
4
s
ig
n
al
s
ar
e
co
r
r
ec
tly
cla
s
s
i
f
ied
an
d
5
5
9
s
ig
n
al
s
ar
e
m
is
c
lass
i
f
ied
f
o
r
all
1
6
class
es
o
f
E
C
G
s
ig
n
al
s
.
T
h
e
a
cc
u
r
ac
y
an
d
er
r
o
r
o
b
tain
ed
f
r
o
m
th
e
p
r
o
p
o
s
ed
m
et
h
o
d
is
ev
al
u
a
ted
f
r
o
m
E
q
u
atio
n
s
(
6
)
an
d
(
7
)
,
w
h
ich
i
s
9
9
.
3
5
% a
n
d
0
.
6
5
% r
esp
ec
tiv
el
y
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2
0
8
8
-
8708
On
th
e
cla
s
s
ifica
tio
n
o
f a
r
r
h
yth
mia
u
s
in
g
s
u
p
p
leme
n
ta
r
y
fea
tu
r
es fr
o
m
tet
r
o
let
tr
a
n
s
fo
r
m
s
(
G.
Ja
ya
g
o
p
i)
5013
T
ab
le
3
.
C
o
n
f
u
s
io
n
m
atr
i
x
f
o
r
R
B
F
-
SVM
m
o
d
el
C
o
r
r
e
c
t
l
y
c
l
a
ssi
f
i
e
d
i
n
s
t
a
n
c
e
s:
8
5
5
5
4
,
M
i
s
c
l
a
ssi
f
i
e
d
i
n
s
t
a
n
c
e
s:
5
5
9
,
Er
r
o
r
:
0
.
6
5
%,
A
c
c
u
r
a
c
y
:
9
9
.
3
5
%
G
r
o
u
n
d
T
r
u
t
h
C
l
a
ss
N
L
R
A
V
P
a
!
F
x
J
f
E
J
e
Q
T
o
t
a
l
N
6
3
3
7
1
32
0
2
0
6
61
0
23
0
51
0
15
5
0
0
0
0
6
3
7
6
4
L
9
5
2
3
0
0
0
8
0
0
0
0
0
0
0
0
0
0
0
5
2
4
7
R
16
0
4
6
9
5
0
5
0
0
0
0
0
0
0
0
0
0
0
4
7
1
6
A
0
0
0
1
6
5
1
0
0
0
2
2
0
0
0
0
0
0
0
1
6
5
5
V
11
1
0
0
4
6
1
9
0
0
1
2
0
0
0
0
0
0
0
4
6
3
4
P
0
0
18
0
0
4
5
3
8
0
0
0
0
0
10
0
0
0
0
4
5
6
6
a
0
0
1
1
3
0
70
0
0
0
0
0
0
0
0
0
75
!
0
0
0
1
20
0
0
2
1
5
0
0
0
0
0
0
0
0
2
3
6
F
6
0
0
0
4
0
0
0
3
9
1
0
0
0
0
0
0
0
4
0
1
x
8
0
0
0
1
0
0
0
0
87
0
0
0
0
0
0
96
j
0
0
0
1
1
1
0
0
0
0
1
1
0
0
0
1
0
0
1
1
4
f
1
1
1
2
0
5
0
1
0
0
0
4
8
0
0
0
0
0
4
9
1
E
4
1
0
0
0
0
0
1
0
0
0
0
47
0
0
0
53
J
1
0
1
0
0
0
0
0
0
0
0
0
0
39
0
0
41
e
3
1
0
0
0
0
0
0
0
0
0
0
0
0
4
0
8
Q
1
1
1
0
2
0
0
0
0
0
0
4
0
0
0
7
16
T
o
t
a
l
6
3
4
3
1
5
2
6
7
4
7
1
7
1
8
6
2
4
7
2
4
4
5
4
4
93
2
2
0
4
4
6
87
1
2
5
4
9
9
47
40
4
7
8
6
1
1
3
T
h
e
p
er
f
o
r
m
an
ce
a
s
s
e
s
s
m
en
t
o
f
th
e
p
r
o
p
o
s
ed
m
et
h
o
d
o
l
o
g
y
is
ca
r
r
ied
o
u
t
b
y
c
o
m
p
u
ti
n
g
th
e
p
ar
a
m
eter
s
s
u
c
h
as
T
P
,
F
P
,
an
d
F
N
f
r
o
m
T
ab
le
3
,
u
s
in
g
(
5
)
to
ev
alu
ate
th
e
s
e
n
s
itiv
it
y
an
d
p
o
s
iti
v
e
p
r
ed
ictiv
it
y
a
n
al
y
s
i
s
f
o
r
ea
ch
c
lass
o
f
E
C
G
s
i
g
n
al,
w
h
ich
i
s
p
r
esen
ted
in
T
ab
le
4
.
I
t is seen
t
h
at
s
u
p
p
le
m
e
n
tar
y
f
ea
t
u
r
es
E
n
tr
o
p
y
a
n
d
E
n
er
g
y
v
al
u
es
e
x
tr
ac
ted
f
r
o
m
t
h
e
2
-
D
g
r
a
y
s
ca
le
i
m
a
g
e
h
a
s
s
i
g
n
i
f
ican
tl
y
i
m
p
r
o
v
ed
th
e
class
if
ica
tio
n
ac
cu
r
ac
y
to
9
9
.
3
5
%
f
o
r
4
lev
els
o
f
T
etr
o
le
t
d
ec
o
m
p
o
s
itio
n
s
.
Mo
r
eo
v
er
,
t
h
e
to
tal
n
u
m
b
er
o
f
f
ea
t
u
r
es
i
s
s
till
1
5
,
w
h
ic
h
ar
e
less
th
a
n
2
0
f
ea
t
u
r
es
a
s
s
ee
n
i
n
[
5
]
.
W
h
ile
f
o
c
u
s
i
n
g
o
n
ac
cu
r
ac
y
i
m
p
r
o
v
e
m
e
n
t,
s
lig
h
t i
n
cr
ea
s
e
i
n
th
e
ti
m
e
o
v
e
r
h
ea
d
is
n
e
g
li
g
ib
le.
As
p
er
t
h
e
p
r
o
p
o
s
ed
m
et
h
o
d
o
lo
g
y
th
e
T
etr
o
let
tr
an
s
f
o
r
m
is
ap
p
lied
an
d
th
e
f
ea
tu
r
e
s
li
k
e
e
n
er
g
y
a
n
d
en
tr
o
p
y
f
ea
t
u
r
es
ar
e
e
x
tr
ac
te
d
an
d
co
n
ca
ten
ated
to
t
h
e
ex
is
ti
n
g
1
3
f
ea
t
u
r
es
f
o
u
n
d
i
n
[
1
2
]
class
if
ied
u
s
i
n
g
th
e
SVM
cla
s
s
i
f
ier
.
I
n
o
r
d
er
t
o
m
ai
n
tai
n
t
h
e
g
e
n
er
alit
y
,
t
h
e
p
er
ce
n
tag
e
o
f
tr
ai
n
in
g
d
ata
is
m
ai
n
tai
n
ed
s
a
m
e
as
n
o
ted
in
[
5
]
an
d
[
1
2
]
.
T
h
e
p
r
o
p
o
s
ed
tech
n
iq
u
e
i
s
v
a
lid
ated
o
n
all
t
h
e
E
C
G
d
ata
(
i.e
.
,
w
it
h
o
u
t
e
x
cl
u
d
in
g
a
n
y
s
eg
m
e
n
t)
o
f
b
en
ch
m
ar
k
MI
T
-
B
I
H
ar
r
h
y
t
h
m
ia
d
atab
ase
w
it
h
2
1
.
8
%
tr
ain
in
g
d
ata
(
2
3
9
9
6
b
ea
ts
f
r
o
m
1
1
0
1
0
9
to
tal
b
ea
ts
)
f
a
v
o
r
in
g
a
le
s
s
t
r
ain
in
g
ti
m
e
a
n
d
m
e
m
o
r
y
co
n
s
u
m
p
t
io
n
w
h
e
n
i
m
p
le
m
en
te
d
in
r
ea
l
ti
m
e
as
an
e
m
b
ed
d
ed
s
y
s
te
m
.
T
h
e
p
er
f
o
r
m
an
ce
o
f
th
e
s
y
s
te
m
is
e
v
al
u
at
ed
b
y
v
ar
y
i
n
g
SVM
k
er
n
els
s
u
ch
as
R
B
F,
L
i
n
ea
r
,
an
d
P
o
ly
n
o
m
ial
k
er
n
e
ls
f
o
r
all
th
e
f
o
u
r
d
ec
o
m
p
o
s
it
io
n
le
v
els
o
f
th
e
T
etr
o
let
tr
an
s
f
o
r
m
.
T
ab
le
4
.
P
er
f
o
r
m
a
n
ce
o
f
ea
ch
class
o
f
E
C
G
EC
G
c
l
a
ss
T
r
a
i
n
e
d
b
e
a
t
s
T
e
st
b
e
a
t
s
F
N
T
P
F
P
S
e
(
%)
P
P
(
%)
A
c
c
u
r
a
c
y
(
%)
N
1
1
2
5
3
6
3
7
6
4
3
9
3
6
3
3
7
1
60
9
9
.
3
8
9
9
.
9
0
9
9
.
3
8
L
2
8
2
5
5
2
4
7
17
5
2
3
0
37
9
9
.
6
7
9
9
.
3
0
9
9
.
6
7
R
2
5
3
9
4
7
1
6
21
4
6
9
5
22
9
9
.
5
5
9
9
.
5
4
9
9
.
5
5
A
8
9
1
1
6
5
5
4
1
6
5
1
2
1
1
9
9
.
7
6
8
8
.
6
7
9
9
.
7
6
V
2
4
9
5
4
6
3
4
15
4
6
1
9
1
0
5
9
9
.
6
8
9
7
.
7
7
9
9
.
6
8
P
2
4
5
8
4
5
6
6
28
4
5
3
8
6
9
9
.
3
8
9
9
.
8
7
9
9
.
3
8
a
75
75
5
70
23
9
3
.
3
3
7
5
.
2
7
9
3
.
3
3
!
2
3
6
2
3
6
21
2
1
5
5
9
1
.
1
0
9
7
.
7
3
9
1
.
1
0
F
4
0
1
4
0
1
10
3
9
1
55
9
7
.
5
0
8
7
.
6
7
9
7
.
5
0
x
97
96
9
87
0
9
0
.
6
3
1
0
0
9
0
.
6
3
j
1
1
5
1
1
4
4
1
1
0
15
9
6
.
4
9
8
8
.
0
0
9
6
.
4
9
f
4
9
1
4
9
1
11
4
8
0
19
9
7
.
7
6
9
6
.
1
9
9
7
.
7
6
E
53
53
6
47
0
8
8
.
6
8
1
0
0
8
8
.
6
8
J
42
41
2
39
1
9
5
.
1
3
9
7
.
5
0
9
5
.
1
3
e
8
8
4
4
0
5
0
.
0
0
1
0
0
5
0
.
0
0
Q
17
16
9
7
0
7
7
.
7
8
1
0
0
7
7
.
7
8
T
o
t
a
l
2
3
9
9
6
8
6
1
1
3
5
5
9
8
5
5
5
4
5
5
9
9
9
.
3
5
9
9
.
3
5
9
9
.
3
5
I
n
T
ab
le
5
,
th
e
e
v
alu
a
tio
n
is
d
o
n
e
b
et
w
ee
n
t
h
e
4
le
v
els
o
f
th
e
T
etr
o
let
co
ef
f
icie
n
ts
w
it
h
t
h
e
d
if
f
er
en
t
SVM
k
er
n
el
s
f
u
n
ctio
n
u
s
i
n
g
1
5
f
ea
tu
r
es
i
n
c
lu
d
i
n
g
en
er
g
y
an
d
en
tr
o
p
y
.
I
t
is
o
b
s
er
v
ed
t
h
at
t
h
e
R
B
F
k
er
n
el
g
iv
e
s
th
e
b
etter
ac
cu
r
ac
y
th
a
n
th
e
li
n
ea
r
,
2
nd
o
r
d
er
p
o
ly
n
o
m
ial
(
q
u
ad
r
atic)
an
d
5
th
o
r
d
er
o
ly
n
o
m
ial
k
er
n
els.
A
l
s
o
,
th
e
h
ig
h
es
t
ac
cu
r
ac
y
i
s
o
b
tain
ed
at
4
th
lev
el
o
f
th
e
T
etr
o
let
co
-
ef
f
icie
n
t.
T
h
e
co
m
p
ar
ativ
e
an
al
y
s
is
o
f
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
w
it
h
o
th
er
A
r
r
h
y
th
m
ia
s
clas
s
i
f
icatio
n
s
y
s
te
m
i
n
i
n
cr
e
m
e
n
tal
o
r
d
er
b
ased
o
n
th
e
n
u
m
b
er
o
f
class
e
s
is
s
h
o
w
n
in
T
ab
le
6
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
6
,
Dec
em
b
er
2
0
1
9
:
5
0
0
6
-
50
1
5
5014
T
ab
le
5
.
Ou
tp
u
t a
cc
u
r
ac
y
f
o
r
ea
ch
t
etr
o
let
lev
el
f
o
r
4
d
if
f
er
en
t SVM
k
er
n
els
K
e
r
n
e
l
s s
e
t
i
n
S
V
M
T
e
t
r
o
l
e
t
d
e
c
o
mp
o
si
t
i
o
n
l
e
v
e
l
s
L
e
v
e
l
1
L
e
v
e
l
2
L
e
v
e
l
3
L
e
v
e
l
4
L
i
n
e
a
r
9
4
.
1
9
5
.
3
3
9
8
.
7
6
9
9
.
1
5
2
nd
o
r
d
e
r
p
o
l
y
n
o
mi
a
l
96
9
8
.
3
3
9
9
.
1
6
9
8
.
3
3
5
th
o
r
d
e
r
p
o
l
y
n
o
mi
a
l
9
4
.
1
9
4
.
1
9
9
.
1
6
9
8
.
3
3
P
r
o
p
o
se
d
R
B
F
9
6
.
6
6
9
9
.
1
4
9
9
.
1
2
9
9
.
3
5
Fro
m
t
h
e
T
ab
le
6
,
it
i
s
c
lear
t
h
at
o
u
r
p
r
o
p
o
s
ed
s
y
s
te
m
is
co
m
p
ar
ed
w
i
th
o
th
er
State
-
of
-
Ar
t
m
et
h
o
d
s
[
5
,
22
-
2
7
]
w
it
h
d
i
f
f
er
e
n
t
n
u
m
b
er
o
f
cla
s
s
e
s
,
d
is
s
i
m
ilar
f
ea
t
u
r
es
an
d
d
i
v
er
g
e
n
t
cla
s
s
i
f
ier
s
u
s
ed
i
n
it.
W
h
en
co
m
p
ar
ed
to
th
e
o
th
er
m
et
h
o
d
,
o
u
r
s
y
s
te
m
p
r
o
v
id
es
th
e
b
etter
class
i
f
icatio
n
ac
c
u
r
ac
y
o
f
9
9
.
3
5
%
o
n
MI
T
-
B
I
H
A
r
r
h
y
t
h
m
ia
d
ata
b
ase.
T
ab
le
6
.
C
o
m
p
ar
is
o
n
o
f
p
r
o
p
o
s
ed
a
r
r
h
y
t
h
m
ia
class
if
ica
tio
n
w
it
h
o
th
er
m
et
h
o
d
s
L
i
t
e
r
a
t
u
r
e
A
p
p
r
o
a
c
h
C
l
a
sse
s
A
c
c
u
r
a
c
y
(
%)
[
2
7
]
P
C
A
+
k
-
I
C
A
+
S
V
M
5
9
7
.
7
8
[
2
5
]
P
C
A
+
L
S
-
S
V
M
5
9
3
.
4
8
[
2
4
]
M
o
r
p
h
o
l
o
g
y
+
P
C
A
+
S
V
M
6
9
1
.
6
7
[
2
6
]
W
a
v
e
l
e
t
+
B
P
N
N
8
9
7
.
4
0
[
2
3
]
H
i
g
h
e
r
o
r
d
e
r
st
a
t
i
st
i
c
s
+
H
e
r
mi
t
e
+
S
V
M
13
9
5
.
9
1
[
2
2
]
M
o
r
p
h
o
l
o
g
y
+
D
e
c
i
si
o
n
16
9
6
.
1
3
[
5
]
D
C
T
b
a
se
d
D
O
S
T
+
S
V
M
-
PSO
16
9
8
.
8
2
[
1
2
]
C
h
a
o
t
i
c
+
S
t
a
t
i
st
i
c
a
l
me
t
r
i
c
s
+
R
R
+
S
V
M
16
9
8
.
9
5
P
r
o
p
o
se
d
T
e
t
r
o
l
e
t
(
4
l
e
v
e
l
)
+
C
h
a
o
t
i
c
+
S
t
a
t
i
st
i
c
a
l
+
R
R
+
S
V
M
(
R
B
F
k
e
r
n
e
l
)
16
9
9
.
3
5
T
h
o
u
g
h
n
o
is
e
i
m
m
u
n
it
y
w
a
s
b
etter
,
Hilb
er
t tr
an
s
f
o
r
m
u
s
ed
i
n
[
2
8
]
co
u
ld
n
o
t
y
ield
e
x
ac
t
R
-
R
in
ter
v
al
d
u
e
to
v
ar
iatio
n
i
n
R
-
R
in
ter
v
al
b
et
w
ee
n
t
h
e
b
ea
ts
.
U
n
li
k
e
th
e
d
etec
tio
n
o
f
o
n
l
y
o
n
e
c
lass
o
f
A
r
r
h
y
t
h
m
ia
in
[
2
9
]
,
p
r
o
p
o
s
ed
m
et
h
o
d
clas
s
if
ie
s
1
6
class
e
s
o
f
E
C
G
s
i
g
n
a
l
w
ith
s
i
g
n
i
f
ica
n
tl
y
b
etter
clas
s
if
ica
tio
n
ac
c
u
r
ac
y
co
m
p
ar
ed
to
o
th
er
r
ep
o
r
ted
w
o
r
k
s
in
t
h
e
liter
at
u
r
e
.
A
ll
t
h
e
l
iter
atu
r
e
tak
e
n
f
o
r
co
m
p
ar
is
o
n
s
u
f
f
er
s
eith
er
w
it
h
in
s
u
f
f
icien
t
ac
c
u
r
ac
y
o
r
le
s
s
n
u
m
b
er
o
f
cla
s
s
e
s
.
I
n
[
2
2
]
,
th
o
u
g
h
a
f
air
le
v
el
o
f
ac
c
u
r
ac
y
is
o
b
tain
ed
f
o
r
all
1
6
A
r
r
h
y
t
h
m
ia
class
e
s
,
th
e
ex
p
er
i
m
e
n
ts
w
er
e
co
n
d
u
cted
u
s
in
g
6
6
%
o
f
tr
ain
in
g
s
et
an
d
o
n
l
y
3
3
%
o
f
test
in
g
s
ets.
I
t
is
m
er
ito
r
io
u
s
to
u
s
e
less
er
n
u
m
b
er
o
f
tr
ai
n
i
n
g
s
e
t
in
c
lass
if
icatio
n
w
h
ile
s
i
m
u
l
tan
eo
u
s
l
y
g
ai
n
in
g
m
a
x
i
m
u
m
class
i
f
icatio
n
ac
cu
r
ac
y
.
I
n
t
h
e
p
r
o
p
o
s
ed
w
o
r
k
,
o
n
l
y
2
1
.
8
%
tr
ain
in
g
d
ata
ar
e
co
n
s
u
m
ed
an
d
class
i
f
icatio
n
h
a
s
b
ee
n
d
o
n
e
w
it
h
o
n
l
y
1
5
f
ea
t
u
r
es.
4.
CO
NCLU
SI
O
N
T
h
is
p
ap
er
h
as
o
f
f
er
ed
an
au
t
o
m
a
ted
E
C
G
s
ig
n
al
an
a
l
y
s
is
s
ch
e
m
e
a
n
d
p
er
f
o
r
m
ed
th
e
cla
s
s
i
f
icatio
n
o
f
A
r
r
h
y
t
h
m
ia
co
n
s
is
t
in
g
o
f
1
6
class
es
i
n
clu
d
i
n
g
n
o
r
m
al
a
n
d
u
n
clas
s
i
f
iab
le
b
ea
t.
T
h
is
m
e
th
o
d
is
v
er
y
u
s
e
f
u
l
f
o
r
lo
n
g
-
ter
m
m
o
n
ito
r
i
n
g
a
n
d
an
al
y
z
in
g
t
h
e
n
o
n
-
s
tatio
n
ar
y
b
eh
av
io
r
o
f
th
e
ca
r
d
iac
s
i
g
n
als.
A
co
m
b
in
at
io
n
o
f
R
-
R
i
n
ter
v
al,
s
tat
is
tical
,
c
h
ao
ti
c
an
d
T
etr
o
let
tr
an
s
f
o
r
m
b
ase
d
f
ea
tu
r
e
s
w
it
h
SVM
cla
s
s
i
f
ie
r
u
n
d
er
R
B
F
k
er
n
el
co
u
ld
p
er
f
o
r
m
b
etter
th
a
n
t
h
e
State
-
of
-
T
h
e
-
A
r
t
m
et
h
o
d
s
.
W
i
th
t
h
e
h
elp
o
f
1
5
f
ea
tu
r
es
a
n
d
o
n
l
y
w
it
h
2
1
.
8
%
o
f
th
e
tr
ain
in
g
d
ata
s
et
s
,
th
e
p
r
o
p
o
s
ed
m
et
h
o
d
co
u
ld
y
ield
a
n
i
m
p
r
o
v
ed
ac
cu
r
ac
y
o
f
9
9
.
3
5
%
o
n
th
e
b
en
c
h
m
ar
k
MI
T
-
B
I
H
ar
r
h
y
t
h
m
ia
d
atab
a
s
e.
T
h
is
r
esear
ch
w
o
r
k
h
a
s
a
s
co
p
e
o
f
e
x
ten
d
in
g
f
u
r
t
h
er
to
in
co
r
p
o
r
ate
th
e
cla
s
s
i
f
icatio
n
w
it
h
d
i
m
e
n
s
i
o
n
r
ed
u
ctio
n
an
d
o
p
ti
m
izatio
n
in
SVM
cla
s
s
i
f
icat
io
n
.
F
u
r
t
h
e
r
r
esear
ch
co
u
ld
b
e
ex
ten
d
ed
to
w
ar
d
s
r
ed
u
cin
g
t
h
e
tr
ain
in
g
d
ata
s
et
s
.
ACK
NO
WL
E
D
G
E
M
E
NT
S
W
e
ar
e
th
an
k
f
u
l
to
th
e
a
u
t
h
o
r
ities
o
f
MI
T
-
B
I
H
A
r
r
h
y
t
h
m
i
a
d
atab
ase
f
o
r
p
r
o
v
id
in
g
th
e
d
atasets
to
co
n
d
u
ct
th
is
r
esear
ch
o
n
E
C
G
class
i
f
icatio
n
.
A
l
s
o
,
w
e
w
o
u
l
d
lik
e
t
o
th
an
k
C
h
a
n
ce
llo
r
,
St.
P
eter
’
s
I
n
s
tit
u
te
o
f
Hig
h
er
E
d
u
ca
tio
n
a
n
d
R
e
s
e
ar
ch
,
C
h
en
n
ai,
f
o
r
h
is
co
n
s
tan
t
s
u
p
p
o
r
t
an
d
t
h
a
n
k
f
u
l
t
o
th
e
Me
m
b
er
s
o
f
th
e
Fac
u
lt
y
o
f
C
o
m
p
u
ter
Scie
n
ce
f
o
r
th
eir
co
n
s
ta
n
t e
n
co
u
r
ag
e
m
en
t.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2
0
8
8
-
8708
On
th
e
cla
s
s
ifica
tio
n
o
f a
r
r
h
yth
mia
u
s
in
g
s
u
p
p
leme
n
ta
r
y
fea
tu
r
es fr
o
m
tet
r
o
let
tr
a
n
s
fo
r
m
s
(
G.
Ja
ya
g
o
p
i)
5015
RE
F
E
R
E
NC
E
S
[1
]
L
.
P
e
n
g
f
e
i,
e
t
a
l
.,
“
Hig
h
P
e
rf
o
rm
a
n
c
e
P
e
rso
n
a
li
z
e
d
He
a
r
Be
a
t
Clas
s
i
f
ic
a
ti
o
n
m
o
d
e
l
f
o
r
L
o
n
g
-
te
rm
EC
G
sig
n
a
l,
”
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
4
,
p
p
.
7
8
-
8
6
,
2
0
1
7
.
[2
]
C.
H.
L
in
,
“
F
re
q
u
e
n
c
y
Do
m
a
in
F
e
a
tu
re
s
F
o
r
ECG
Be
a
t
Dis
c
ri
m
in
a
ti
o
n
Us
in
g
G
ra
y
Re
latio
n
a
l
A
n
a
l
y
si
s
Ba
se
d
Clas
sif
i
e
r,
”
Co
mp
u
ter
s a
n
d
M
a
th
e
ma
ti
c
s wit
h
A
p
p
li
c
a
ti
o
n
s
,
v
o
l.
5
5
,
p
p
.
6
8
0
-
6
9
0
,
2
0
0
8
.
[3
]
R.
M
o
d
j
tab
a
a
n
d
S
.
Re
z
a
,
“
Ne
u
ra
l
Ne
t
w
o
rk
s
b
a
se
d
Dia
g
n
o
sis
o
f
He
a
rt
A
rrh
y
th
m
ia
u
sin
g
Ch
a
o
ti
c
a
n
d
No
n
l
in
e
a
r
F
e
a
tu
re
s
o
f
HRV
sig
n
a
ls,”
In
ter
n
a
ti
o
n
a
l
Ass
o
c
ia
ti
o
n
o
f
Co
mp
u
ter
S
c
ien
c
e
a
n
d
I
n
fo
rm
a
t
io
n
T
e
c
h
n
o
l
o
g
y
,
S
i
n
g
a
p
o
re
-
2
0
0
9
,
p
p
.
5
4
5
-
5
4
9
,
2
0
0
9
.
[4
]
E.
D.
Ub
e
y
li
,
“
Re
c
u
rre
n
t
Ne
u
ra
l
Ne
tw
o
rk
s
E
m
p
lo
y
in
g
Ly
a
p
u
n
o
v
Ex
p
o
n
e
n
ts
f
o
r
A
n
a
l
y
sis
o
f
EC
G
s
ig
n
a
ls,”
Exp
e
rt
S
y
ste
ms
wih
Ap
p
li
c
a
ti
o
n
s
,
v
o
l.
3
7
,
p
p
.
1
1
9
2
-
1
1
9
9
,
2
0
1
0
.
[5
]
S
.
Ra
j
a
n
d
K.
C
.
Ra
y
,
“
EC
G
S
ig
n
a
l
A
n
a
l
y
sis
Us
in
g
DC
T
Ba
se
d
DO
S
T
a
n
d
P
S
O
Op
ti
m
ize
d
S
V
M
,
”
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
In
str
u
me
n
ta
t
io
n
a
n
d
M
e
a
su
re
me
n
t
,
v
o
l.
6
6
,
p
p
.
4
7
0
-
4
7
8
,
2
0
1
7
.
[6
]
V
.
Oc
tav
ian
i,
e
t
a
l
.,
“
A
lertin
g
s
y
ste
m
f
o
r
S
p
o
rt
A
c
ti
v
it
y
B
a
se
d
o
n
ECG
sig
n
a
ls
Us
in
g
P
ro
p
o
rti
o
n
a
l
In
teg
ra
l
Driv
a
ti
v
e
,
”
Pro
c
.
o
f
EE
CS
I
,
Y
o
g
y
a
k
a
rta
,
In
d
o
n
e
sia
,
2
0
1
7
.
[7
]
N.
A
.
Na
y
a
n
,
e
t
a
l
.,
“
De
v
e
lo
p
m
e
n
t
o
f
Re
sp
irato
ry
Ra
te
Esti
m
a
ti
o
n
T
e
c
h
n
i
q
u
e
Us
i
n
g
El
e
c
tro
g
c
a
rd
io
g
ra
m
a
n
d
P
h
o
t
o
p
leth
y
s
m
o
g
ra
m
f
o
r
c
o
n
ti
n
o
u
s
He
a
lt
h
M
o
n
it
o
ri
n
g
,
”
Bu
ll
e
ti
n
o
f
El
e
c
trica
l
E
n
g
i
n
e
e
rin
g
a
n
d
In
f
o
rm
a
ti
c
s,
v
o
l.
3
,
p
p
.
4
8
7
-
4
9
4
,
2
0
1
8
.
[8
]
R.
E.
Kle
ig
e
r
,
e
t
a
l
.,
“
He
a
rt
Ra
te
V
a
riab
il
i
ty
:
M
e
a
su
re
m
e
n
t
a
n
d
Cli
n
ica
l
Util
it
y
,
”
ANN
No
n
in
v
El
e
c
tro
c
a
rd
io
l
,
v
o
l
.
1
0
,
p
p
.
8
8
-
1
0
1
,
2
0
0
5
.
[9
]
B.
U.
Ko
h
ler,
e
t
a
l
.
,
“
T
h
e
P
ri
n
c
ip
les
o
f
S
o
f
t
w
a
r
e
QRS
D
e
tec
ti
o
n
,
”
IEE
E
En
g
M
e
d
Bi
o
l
M
a
g
,
v
o
l.
2
1
,
p
p
.
4
2
-
5
7
,
2
0
0
2
.
[1
0
]
Z.
Yu
e
,
e
t
a
l
.
,
“
A
d
a
p
ti
v
e
R
-
wa
v
e
D
e
tec
ti
o
n
M
e
th
o
d
in
Dy
n
a
m
ic
EC
G
w
it
h
He
a
v
y
EM
G
Artif
a
c
t,
”
IEE
E
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
I
n
fo
r
ma
ti
o
n
a
n
d
Au
t
o
ma
t
io
n
,
S
h
e
n
y
a
n
g
,
2
0
1
2
,
p
p
.
8
3
-
8
7
,
2
0
1
2
.
[1
1
]
G
.
B.
M
o
o
d
y
a
n
d
R.
G
.
M
a
rk
,
“
Th
e
Im
p
a
c
t
o
f
th
e
M
IT
-
BI
H
A
rrh
y
t
h
m
ia D
a
tab
a
se
,
”
IEE
E
En
g
.
M
e
d
.
Bi
o
l.
M
a
g
,
v
o
l
.
2
0
,
p
p
.
4
5
-
5
0
,
2
0
0
1
.
[1
2
]
G
.
J
a
y
a
g
o
p
i
a
n
d
S
.
P
u
sh
p
a
,
“
A
rrh
y
th
m
ia
Cla
ss
i
f
ica
ti
o
n
Ba
se
d
o
n
Co
m
b
in
e
d
Ch
a
o
ti
c
a
n
d
S
tatisti
c
a
l
F
e
a
tu
re
Ex
trac
ti
o
n
,
”
In
d
o
n
e
sia
n
J
o
u
r
n
a
l
o
f
El
e
c
trica
l
En
g
in
e
e
rin
g
a
n
d
Co
mp
u
ter
S
c
ien
c
e
,
v
o
l
.
1
2
,
p
p
.
1
2
7
-
1
3
6
,
2
0
1
8
.
[1
3
]
K.
S
rin
iv
a
sa
n
,
e
t
a
l
.
,
“
M
u
lt
ich
a
n
n
e
l
EE
G
Co
m
p
re
ss
io
n
:
W
a
v
e
let
Ba
se
d
I
m
a
g
e
a
n
d
V
o
l
u
m
e
tri
c
Co
d
in
g
A
p
p
ro
a
c
h
,
”
IEE
E
J
o
u
rn
a
l
o
f
Bi
o
me
d
ica
l
A
n
d
He
a
lt
h
I
n
fo
rm
a
ti
c
s
,
v
o
l.
1
7
,
p
p
.
1
13
-
1
2
0
,
2
0
1
3
.
[1
4
]
C.
S
a
rit
h
a
,
e
t
a
l
.
,
“
ECG
S
ig
n
a
l
An
a
ly
sis Us
in
g
W
a
v
e
let
T
r
a
n
sf
o
r
m
s,”
Bu
lg
.
J
.
P
h
y
s.
v
o
l.
3
5
,
p
p
.
6
8
-
7
7
,
2
0
0
8
.
[1
5
]
M
.
Ce
y
lan
a
n
d
A
.
E.
Ca
n
b
il
e
n
,
“
P
e
rf
o
rm
a
n
c
e
Co
m
p
a
riso
n
o
f
Tetro
let
T
ra
n
sf
o
r
m
a
n
d
Wav
e
let
B
a
s
e
d
T
ra
n
s
f
o
rm
s
f
o
r
M
e
d
ica
l
I
m
a
g
e
De
n
o
isin
g
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
In
telli
g
e
n
t
S
y
ste
ms
a
n
d
Ap
p
li
c
a
ti
o
n
s
in
E
n
g
in
e
e
rin
g
,
v
o
l.
5
,
p
p
.
2
2
2
-
2
3
1
,
2
0
1
7
.
[1
6
]
M
.
A
z
a
d
,
e
t
a
l
.
,
“
A
n
Eff
i
c
ien
t
W
a
y
to
Co
n
v
e
rt
1
D
S
ig
n
a
l
to
2
D
Dig
it
a
l
I
m
a
g
e
U
sin
g
En
e
rg
y
V
a
lu
e
s,”
T
h
e
sis
su
b
mitt
e
d
to
De
p
a
rtme
n
t
o
f
C
o
mp
u
ter
S
c
ien
c
e
a
n
d
En
g
in
e
e
rin
g
,
BR
AC
Un
ive
rs
it
y
,
Ba
n
g
lad
e
sh
,
2
0
1
8
.
[1
7
]
P
.
P
o
rw
ik
a
n
d
A
.
L
iso
w
s
k
a
,
“
T
h
e
Ha
a
r
W
a
v
e
let
T
ra
n
sf
o
r
m
in
Dig
it
a
l
Im
a
g
e
P
ro
c
e
ss
in
g
:
Its
S
tatu
s
a
n
d
A
c
h
ie
v
e
m
e
n
ts,”
M
a
c
h
in
e
Gr
a
p
h
i
c
s a
n
d
Vi
sio
n
,
v
o
l
.
1
3
,
p
p
.
7
9
-
9
8
,
2
0
0
4
.
[1
8
]
S
.
M
.
V
a
li
,
e
t
a
l
.
,
“
Ro
b
u
st
Im
a
g
e
W
a
ter
m
a
r
k
i
n
g
u
sin
g
T
e
tro
let
T
r
a
n
sf
o
r
m
,
”
IEE
E
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
El
e
c
trica
l,
El
e
c
tro
n
ics
,
S
i
g
n
a
ls,
C
o
mm
u
n
ic
a
ti
o
n
a
n
d
Op
ti
miz
a
ti
o
n
,
p
p
.
1
-
5
,
2
0
1
5
.
[1
9
]
A
.
I
y
y
a
n
a
ra
p
p
a
n
a
n
d
G
.
Ta
m
il
p
a
v
a
i,
“
G
lau
c
o
m
a
to
u
s
Im
a
g
e
Clas
s
if
ica
ti
o
n
Us
in
g
W
a
v
e
let
b
a
se
d
E
n
e
rg
y
F
e
a
tu
re
s
a
n
d
P
NN
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
T
e
c
h
n
o
lo
g
y
En
h
a
n
c
e
me
n
ts
a
n
d
Eme
rg
in
g
En
g
in
e
e
rin
g
Res
e
a
rc
h
,
p
p
.
2
-
4
,
2
0
1
4
.
[2
0
]
T
.
W
.
Ch
a
n
g
,
e
t
a
l
.
,
“
Eff
ici
e
n
t
En
tro
p
y
b
a
s
e
d
F
e
a
tu
re
s
S
e
lec
t
io
n
f
o
r
Im
a
g
e
Re
tri
e
v
a
l,
”
IEE
E
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
S
y
ste
ms
,
M
a
n
,
a
n
d
Cy
b
e
r
n
e
ti
c
s
,
p
p
.
2
9
4
1
-
2
9
4
6
,
2
0
0
9
.
[2
1
]
N.
E.
M
d
.
Isa
,
e
t
a
l
.
,
“
M
o
t
o
r
ima
g
e
r
y
c
la
ss
i
f
ica
ti
o
n
in
Bra
in
c
o
m
p
u
ter
In
terfa
c
e
(BCI)
b
a
se
d
o
n
EE
G
sig
n
a
l
b
y
u
sin
g
m
a
c
h
in
e
lea
rn
in
g
tec
h
n
i
q
u
e
,
”
Bu
ll
e
ti
n
o
f
El
e
c
trica
l
En
g
in
e
e
ri
n
g
a
n
d
I
n
fo
rm
a
t
ics
,
v
o
l.
8
,
p
p
.
2
6
9
-
2
7
5
,
2
0
1
9
.
[2
2
]
J.
Ro
d
r
ig
u
e
z
,
e
t
a
l
.
,
“
Re
a
l
-
ti
m
e
Clas
sif
ic
a
ti
o
n
o
f
ECG
s
o
n
a
P
DA
,
”
IEE
E
T
ra
n
s
a
c
ti
o
n
s
o
n
I
n
f
o
rm
a
ti
o
n
T
e
c
h
n
o
lo
g
y
Bi
o
me
d
ica
l
,
v
o
l.
9
,
p
p
.
2
3
-
3
4
,
2
0
0
5
.
[2
3
]
S
.
Os
o
w
s
k
i,
e
t
a
l
.
,
“
S
u
p
p
o
rt
V
e
c
to
r
M
a
c
h
in
e
b
a
se
d
Ex
p
e
rt
S
y
st
e
m
f
o
r
Re
li
a
b
le
H
e
a
rt
B
e
a
t
Re
c
o
g
n
it
io
n
,
”
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
Bi
o
me
d
ica
l
En
g
i
n
e
e
rin
g
,
v
o
l.
5
1
,
p
p
.
5
8
2
-
5
8
9
,
2
0
0
4
.
[2
4
]
F
.
M
e
lg
a
n
i
a
n
d
Y.
Ba
z
i,
“
”
Clas
si
f
ica
ti
o
n
o
f
El
e
c
tro
c
a
rd
io
g
ra
m
S
ig
n
a
ls
w
it
h
S
u
p
p
o
rt
V
e
c
to
r
M
a
c
h
i
n
e
s
a
n
d
P
a
rti
c
le
S
w
a
r
m
Op
ti
m
iza
ti
o
n
,
”
IEE
E
T
r
a
n
sa
c
ti
o
n
s o
n
I
n
fo
rm
a
ti
o
n
T
e
c
h
n
o
l
o
g
y
Bi
o
me
d
ica
l
,
v
o
l
.
1
2
,
p
p
.
6
6
7
-
6
7
7
,
2
0
0
8
.
[2
5
]
R.
J.
M
a
rti
s,
e
t
a
l
.
,
“
Ca
rd
iac
De
c
i
sio
n
M
a
k
in
g
u
sin
g
Hig
h
e
r
Ord
e
r
S
p
e
c
tra,”
Bi
o
me
d
ic
a
l
S
ig
n
a
l
Pro
c
e
ss
in
g
Co
n
tro
l
,
v
o
l.
8
,
p
p
.
1
9
3
-
2
0
3
,
2
0
1
3
.
[2
6
]
S
.
Ra
j,
e
t
a
l
.
,
“
A
RM
b
a
se
d
A
rrh
y
th
m
ia
Be
a
t
M
o
n
it
o
ri
n
g
S
y
ste
m
,
”
M
icr
o
p
ro
c
e
ss
o
r,
M
icr
o
sy
ste
m
,
v
o
l
.
3
9
,
p
p
.
5
0
4
-
5
1
1
,
2
0
1
5
.
[2
7
]
H.
L
i,
e
t
a
l
.
,
“
No
v
e
l
ECG
S
ig
n
a
l
Clas
sif
ic
a
ti
o
n
b
a
se
d
o
n
KICA
No
n
li
n
e
a
r
F
e
a
tu
re
Ex
trac
ti
o
n
,
”
C
irc
u
it
s,
S
y
ste
m,
S
ig
n
a
l
Pro
c
e
ss
in
g
,
v
o
l.
3
5
,
p
p
.
1
1
8
7
-
1
1
9
7
,
2
0
1
6
.
[2
8
]
S
.
S
.
Ko
h
li
,
e
t
a
l
.
,
“
Hilb
e
rt
T
ra
n
sfo
rm
Ba
s
e
d
A
d
a
p
ti
v
e
EC
G
R
-
P
e
a
k
De
tec
ti
o
n
T
e
c
h
n
iq
u
e
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
El
e
c
trica
l
a
n
d
C
o
mp
u
ter
En
g
in
e
e
rin
g
,
v
o
l.
2
,
p
p
.
6
3
9
-
6
4
3
,
2
0
1
2
.
[2
9
]
K.
P
a
d
m
a
v
a
th
i
a
n
d
K.
S
.
Ra
m
a
k
rish
n
a
,
“
De
tec
ti
o
n
o
f
A
tri
a
l
F
ib
r
il
latio
n
u
sin
g
A
u
to
re
g
re
ss
iv
e
m
o
d
e
li
n
g
,
”
In
ter
n
a
t
io
n
a
l
jo
u
rn
a
l
o
f
El
e
c
trica
l
a
n
d
C
o
mp
u
ter
En
g
in
e
e
rin
g
,
v
o
l.
5
,
p
p
.
6
4
-
7
0
,
2
0
1
5
.
Evaluation Warning : The document was created with Spire.PDF for Python.