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.
8
,
No
.
2
,
A
p
r
il
201
8
,
p
p
.
658
~
6
6
5
I
SS
N:
2088
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v
8
i
2
.
p
p
6
5
8
-
6
6
5
658
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
U
tili
z
ing
EC
G
W
a
v
efor
m
Feature
s
a
s New
Bio
m
e
tri
c
Authen
ticatio
n
M
ethod
Ah
m
ed
Yo
u
nes
S
hd
ef
a
t
1
,
M
oo
n
-
I
l J
o
o
2
,
Sung
-
H
o
o
n Cho
i
3
,
H
ee
-
Cheo
l K
i
m
4
1
De
p
a
rt
m
e
n
t
o
f
In
f
o
rm
a
ti
o
n
S
y
ste
m
a
n
d
T
e
c
h
n
o
l
o
g
y
/
T
e
le
c
m
u
n
ica
ti
o
n
s an
d
Ne
tw
o
rk
T
e
c
h
n
o
l
o
g
y
(IS
T
/T
NT
),
Am
e
rica
n
Un
iv
e
rsit
y
o
f
M
id
d
le E
a
st,
Ku
w
a
it
2,
3,
4
I
n
stit
u
te
o
f
Dig
it
a
l
A
n
ti
-
Ag
in
g
He
a
lt
h
c
a
re
/
De
p
a
rt
m
e
n
t
o
f
Co
m
p
u
ter E
n
g
in
e
e
ri
n
g
/S
m
a
rt
Welln
e
ss
L
a
b
,
In
je Un
iv
e
rsity
,
G
i
m
h
a
e
,
Re
p
.
o
f
Ko
re
a
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Dec
9
,
2
0
1
7
R
ev
i
s
ed
Mar
2
,
2
0
1
8
A
cc
ep
ted
Ma
r
1
6
,
2
0
1
8
In
th
is
stu
d
y
,
we
a
re
p
ro
p
o
si
n
g
a
p
ra
c
ti
c
a
l
w
a
y
f
o
r
h
u
m
a
n
id
e
n
ti
f
ica
ti
o
n
b
a
se
d
o
n
a
n
e
w
b
io
m
e
tri
c
m
e
th
o
d
.
T
h
e
n
e
w
m
e
th
o
d
is
b
u
il
t
o
n
th
e
u
se
o
f
th
e
e
lec
tro
c
a
rd
io
g
ra
m
(ECG
)
si
g
n
a
l
w
a
v
e
f
o
r
m
f
e
a
tu
re
s,
w
h
ich
a
re
p
ro
d
u
c
e
d
f
ro
m
th
e
p
ro
c
e
ss
o
f
a
c
q
u
iri
n
g
e
lec
tri
c
a
l
a
c
ti
v
it
ies
o
f
th
e
h
e
a
rt
b
y
u
sin
g
e
lec
tro
d
e
s
p
lac
e
d
o
n
t
h
e
b
o
d
y
.
T
h
is
p
ro
c
e
ss
is
l
a
u
n
c
h
e
d
o
v
e
r
a
p
e
rio
d
o
f
ti
m
e
b
y
u
sin
g
a
re
c
o
rd
in
g
d
e
v
ice
to
re
a
d
a
n
d
sto
re
th
e
ECG
si
g
n
a
l.
On
th
e
c
o
n
trary
o
f
o
th
e
r
b
io
m
e
tri
c
s
m
e
th
o
d
li
k
e
v
o
ice
,
f
in
g
e
rp
rin
t
a
n
d
iri
s
sc
a
n
,
ECG
sig
n
a
l
c
a
n
n
o
t
b
e
c
o
p
ied
o
r
m
a
n
ip
u
late
d
.
T
h
e
f
irst
o
p
e
ra
ti
o
n
f
o
r
o
u
r
s
y
ste
m
is
to
re
c
o
rd
a
p
o
r
ti
o
n
o
f
3
0
se
c
o
n
d
s
o
u
t
o
f
w
h
o
le
ECG
s
ig
n
a
l
o
f
a
c
e
rtain
u
se
r
in
o
r
d
e
r
to
re
g
ister
it
a
s
u
se
r
te
m
p
late
in
th
e
s
y
s
te
m
.
T
h
e
n
th
e
s
y
ste
m
w
il
l
ta
k
e
7
to
9
se
c
o
n
d
s
in
a
u
th
e
n
ti
c
a
ti
n
g
th
e
te
m
p
late
u
sin
g
te
m
p
late
m
a
tch
in
g
tec
h
n
iq
u
e
s.
4
4
su
b
jec
ts‟
ra
w
EC
G
d
a
ta
we
re
d
o
w
n
lo
a
d
e
d
f
ro
m
P
h
y
sio
n
e
t
w
e
b
site
re
p
o
sito
ry
.
W
e
u
se
d
a
te
m
p
late
m
a
tch
in
g
tec
h
n
iq
u
e
f
o
r
th
e
a
u
th
e
n
ti
c
a
ti
o
n
p
r
o
c
e
ss
a
n
d
L
in
e
a
r
S
V
M
a
lg
o
rit
h
m
f
o
r
th
e
c
las
si
f
ic
a
ti
o
n
tas
k
.
T
h
e
a
c
c
u
ra
c
y
ra
te
wa
s
9
7
.
2
%
f
o
r
th
e
a
u
th
e
n
ti
c
a
ti
o
n
p
r
o
c
e
ss
a
n
d
9
8
.
6
%
f
o
r
th
e
c
las
sif
ica
ti
o
n
tas
k
;
w
it
h
fa
lse
a
c
c
e
p
tan
c
e
ra
te 1
.
2
1
%
.
K
ey
w
o
r
d
:
B
io
m
etr
ic
a
u
t
h
en
t
if
ica
tio
n
E
C
G
P
atter
n
r
ec
o
g
n
itio
n
Secu
r
it
y
Co
p
y
rig
h
t
©
2
0
1
8
In
stit
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
:
Hee
-
C
h
eo
l K
i
m
,
I
n
s
tit
u
te
o
f
An
ti
-
Ag
i
n
g
Hea
lth
ca
r
e/
Dep
ar
t
m
e
n
t o
f
C
o
m
p
u
ter
E
n
g
i
n
ee
r
i
n
g
/
S
m
ar
t W
elln
es
s
L
ab
,
I
n
j
e
Un
iv
er
s
i
t
y
,
1
9
7
,
I
n
j
e
-
r
o
,
Gim
h
ae
-
s
i,
G
y
eo
n
g
s
an
g
n
a
m
-
d
o
,
5
0
8
3
4
,
R
ep
.
o
f
Ko
r
ea
.
E
m
ail:
h
ee
k
i
@
i
n
j
e.
ac
.
k
r
1.
I
NT
RO
D
UCT
I
O
N
R
ec
en
t
l
y
,
b
io
m
e
tr
ics
a
u
th
e
n
ti
ca
tio
n
h
a
s
b
ee
n
w
id
el
y
r
esear
ch
ed
an
d
ap
p
lied
to
en
h
a
n
ce
t
h
e
s
ec
u
r
it
y
lev
el
o
f
t
h
e
cu
r
r
en
t
s
y
s
te
m
s
.
T
h
e
s
ec
u
r
it
y
le
v
el
at
a
s
y
s
te
m
is
m
ea
s
u
r
ed
b
y
t
h
e
s
y
s
te
m
i
m
m
u
n
it
y
a
g
ai
n
s
t
in
tr
u
s
io
n
an
d
f
a
k
e
s
i
g
n
a
tu
r
e
t
o
id
en
ti
f
y
t
h
e
p
er
s
o
n
d
u
r
i
n
g
t
h
e
a
u
t
h
en
t
icatio
n
p
r
o
ce
s
s
[
1
]
.
T
ec
h
n
icall
y
,
s
o
m
e
b
io
m
etr
ic
m
et
h
o
d
s
h
av
e
s
tr
o
n
g
u
n
iq
u
e
n
es
s
s
u
c
h
as
s
ca
n
n
in
g
ir
is
an
d
r
etin
a.
B
u
t
t
h
e
y
r
eq
u
ir
e
ex
p
en
s
iv
e
a
n
d
s
p
ec
ial
eq
u
ip
m
e
n
t
to
in
s
tall
t
h
e
m
.
Ot
h
er
b
io
m
e
tr
ic
m
et
h
o
d
s
s
u
c
h
a
s
v
o
ice,
f
ac
e
a
n
d
f
in
g
er
p
r
in
t
r
ec
o
g
n
it
io
n
h
av
e
a
s
tr
o
n
g
u
n
iq
u
e
n
es
s
to
o
.
B
u
t
ev
e
n
s
o
;
t
h
ese
f
ea
t
u
r
es
s
t
ill
ea
s
y
to
b
e
o
b
tain
ed
,
s
in
ce
t
h
e
y
ar
e
ea
s
y
to
b
e
m
an
ip
u
lated
.
B
eh
a
v
io
r
al
b
io
m
etr
ics
m
e
th
o
d
s
,
l
ik
e
g
ai
t
a
n
d
h
an
d
w
r
iti
n
g
a
n
al
y
s
i
s
f
o
r
in
s
ta
n
ce
,
h
a
v
e
a
v
er
y
w
ea
k
u
n
iq
u
e
n
es
s
in
co
m
p
ar
is
o
n
w
it
h
t
h
e
p
r
ev
io
u
s
b
io
m
etr
i
cs
m
et
h
o
d
s
.
E
C
G
h
as
b
ee
n
u
s
ed
to
d
iag
n
o
s
e
h
ea
r
t
d
is
ea
s
es
an
d
ap
p
lied
in
o
th
er
m
ed
ical
f
ield
s
f
o
r
a
lo
n
g
ti
m
e.
Ma
n
y
r
ec
en
t
s
t
u
d
ies
co
n
f
ir
m
th
at
it
is
p
o
s
s
ib
le
to
u
s
e
E
C
G
as
o
n
e
o
f
th
e
b
io
m
etr
ic
f
ea
t
u
r
es
[
2
]
.
A
cc
o
r
d
in
g
to
[
3]
,
[4
]
,
E
C
G
is
d
if
f
ic
u
lt
to
b
e
clo
n
ed
o
r
m
an
ip
u
lated
b
ec
au
s
e
E
C
G
s
i
g
n
al
is
u
n
iq
u
e
f
o
r
ea
c
h
s
in
g
le
p
er
s
o
n
an
d
n
o
t
r
ea
d
il
y
a
v
ailab
le
to
o
t
h
er
s
.
Mo
r
eo
v
er
,
it h
a
s
a
s
m
all
co
m
p
u
tatio
n
a
l a
n
d
s
to
r
a
g
e
o
v
er
h
ea
d
as E
C
G
is
a
o
n
e
-
d
i
m
en
s
io
n
al
s
ig
n
al;
s
o
,
r
elati
v
e
alg
o
r
ith
m
s
ca
n
b
e
d
ep
lo
y
ed
i
n
s
m
ar
t p
h
o
n
es,
s
m
ar
t
w
atc
h
es
an
d
m
a
n
y
n
e
w
s
m
ar
t d
ev
ice
s
.
Fo
r
co
llectin
g
E
C
G
r
a
w
d
ata,
w
e
n
ee
d
at
least t
w
o
lo
ca
tio
n
s
i
n
h
u
m
an
b
o
d
y
to
p
lace
th
e
elec
tr
o
d
es [
5
]
.
I
t
is
p
iv
o
tal
to
e
x
tr
ac
t
t
h
e
E
C
G
s
ig
n
al
f
ea
t
u
r
es
t
h
at
r
ep
r
ese
n
t
a
v
ital
i
n
f
o
r
m
atio
n
co
u
ld
b
e
u
s
ed
to
i
m
p
r
o
v
e
th
e
a
u
t
h
e
n
ticatio
n
a
n
d
class
if
icatio
n
p
er
f
o
r
m
an
ce
.
T
h
er
e
ar
e
s
ev
er
al
tech
n
iq
u
es
f
o
r
ex
tr
ac
ti
n
g
E
C
G
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:
2088
-
8708
Utiliz
in
g
E
C
G
W
a
ve
fo
r
m
F
ea
tu
r
es
a
s
N
ew B
io
met
r
ic
A
u
th
en
tica
tio
n
Meth
o
d
(
A
h
med
Yo
u
n
es S
h
d
efa
t)
659
s
ig
n
al
s
f
ea
tu
r
es,
w
h
ich
ar
e
c
l
ass
i
f
ied
i
n
to
ti
m
e,
f
r
eq
u
en
c
y
an
d
ti
m
e
–
f
r
eq
u
e
n
c
y
e
x
tr
ac
tio
n
tec
h
n
iq
u
es.
T
h
e
ex
tr
ac
ted
ti
m
e
d
o
m
ai
n
f
ea
t
u
r
es
ar
e
th
e
am
p
li
tu
d
e
p
ar
a
m
eter
s
(
QR
S,
ST
)
,
d
u
r
atio
n
p
ar
am
e
ter
s
(
QR
S,
QT
,
an
d
P
R
)
an
d
h
ea
r
tb
ea
t
in
ter
v
al
[
2
].
T
im
e
ex
tr
ac
tio
n
tec
h
n
iq
u
e
d
o
n
o
t
p
r
o
v
id
e
g
o
o
d
r
ec
o
g
n
itio
n
;
an
d
th
at
is
d
u
e
to
th
e
f
r
eq
u
e
n
t
c
h
a
n
g
e
s
i
n
th
e
a
m
p
lit
u
d
e
an
d
d
u
r
atio
n
i
n
t
h
e
E
C
G
S
ig
n
al
w
av
e
s
[
3
].
O
n
t
h
e
o
t
h
er
h
a
n
d
,
t
h
e
f
r
eq
u
en
c
y
d
o
m
ai
n
e
x
tr
ac
tio
n
tech
n
iq
u
e
d
o
n
o
t
p
r
o
v
id
e
in
t
er
i
m
i
n
f
o
r
m
atio
n
ab
o
u
t
t
h
e
E
C
G
s
i
g
n
als
w
a
v
e
s
.
A
p
p
l
y
in
g
s
u
itab
le
ti
m
e
–
f
r
eq
u
e
n
c
y
tec
h
n
iq
u
e
ca
n
o
v
er
co
m
e
t
h
is
i
s
s
u
e
.
I
n
th
e
cu
r
r
e
n
t
b
io
m
etr
ic
au
th
e
n
ticatio
n
u
s
in
g
E
C
G
s
i
g
n
a
l
w
a
v
es
r
elate
d
w
o
r
k
s
,
m
an
y
r
esea
r
ch
es
h
ad
b
ee
n
p
er
f
o
r
m
ed
;
lik
e
in
[
1
]
,
th
e
r
esear
ch
er
s
h
a
v
e
p
r
o
p
u
s
ed
m
o
b
ile
b
io
m
etr
ic
au
th
e
n
ticati
o
n
alg
o
r
it
h
m
b
ase
d
o
n
E
C
G
s
i
g
n
al.
T
h
e
y
h
a
v
e
c
o
n
d
u
cted
t
w
o
e
x
p
er
i
m
e
n
t
t
y
p
es;
e
x
p
er
i
m
e
n
t
u
s
i
n
g
p
h
y
s
io
n
et
E
C
G
r
ec
o
r
d
s
a
n
d
lab
o
r
ato
r
y
ex
p
er
i
m
e
n
t
.
T
h
e
f
ir
s
t e
x
p
er
i
m
en
t t
y
p
e
f
r
o
m
th
eir
w
o
r
k
i
s
r
elate
d
d
ir
ec
tl
y
to
o
u
r
w
o
r
k
.
So
ac
co
r
d
in
g
to
th
e
m
,
7
3
r
ec
o
r
d
s
o
b
tain
ed
f
r
o
m
t
h
e
P
h
y
s
io
n
et
d
atab
ase
.
T
h
e
E
C
G
ti
m
e
len
g
t
h
f
o
r
th
e
o
b
tain
ed
r
ec
o
r
d
s
s
co
p
e
b
et
w
ee
n
3
0
m
i
n
t
u
tes
t
o
2
4
h
o
u
r
s
.
T
h
eir
m
et
h
o
d
ha
d
s
co
r
d
1.
29
%
f
alse
ac
ce
p
ta
n
ce
r
ate
an
d
8
1
.
8
2
%
ac
cu
r
ac
y
r
ate
o
v
er
4
s
o
f
s
i
g
n
al
len
g
h
t
.
I
n
th
e
w
o
r
k
[
6
]
,
th
ey
h
ad
a
s
tr
atig
y
to
ex
to
r
t
f
r
eq
u
en
c
y
d
o
i
m
an
f
ea
tu
r
e
s
u
s
i
n
g
Fo
u
r
ier
tr
an
s
f
o
r
m
m
et
h
o
d
.
T
h
ey
w
er
e
s
ee
k
in
g
f
o
r
ce
r
tain
f
ea
t
u
r
es
a
m
o
n
g
th
e
f
r
eq
u
e
n
c
y
d
o
i
m
a
n
f
ea
tu
r
es
;
l
ik
e
s
lo
p
e,
h
ar
m
o
n
ic
n
u
m
b
er
,
th
e
m
a
g
n
it
u
d
e
g
ap
an
d
r
atio
o
f
d
if
f
er
en
t
f
r
eq
u
e
n
c
y
en
er
g
y
to
to
tal
en
er
g
y
.
Fo
r
th
e
class
i
f
icatio
n
p
r
o
ce
s
s
th
e
y
h
ad
u
s
ed
co
r
r
elatio
n
an
al
y
s
i
s
an
d
n
e
u
r
al
n
e
t
wo
r
k
w
er
e
u
s
ed
in
id
en
ti
f
icat
io
n
p
h
ase.
T
h
e
y
h
a
v
e
s
co
r
ed
lo
w
r
ec
o
g
n
itio
n
r
ate,
th
e
y
b
elie
v
ed
th
e
r
ea
s
o
n
w
a
s
i
n
f
ea
t
u
r
e
s
elec
tio
n
m
e
th
o
d
;
b
u
t
f
r
o
m
o
u
r
r
esear
ch
p
o
in
t
o
f
v
ie
w
w
e
b
eli
v
e
th
a
t
th
e
r
ea
s
o
n
is
i
n
t
h
e
f
ea
t
u
r
e
ex
tr
ac
tio
n
t
y
p
e
d
u
e
to
i
n
s
u
f
f
icie
n
t
in
f
o
r
m
a
tio
n
p
r
o
v
ed
e
b
y
th
i
s
t
y
p
e
o
f
f
ea
t
u
r
e
.
T
h
ey
h
a
v
e
s
co
r
ed
9
6
.
4
% o
f
ac
cu
r
ac
y
r
ate
w
it
h
3
.
6
1
f
alse a
cc
ep
t r
ate.
W
e
h
av
e
co
n
tr
ib
u
ted
to
b
io
m
etr
ic
au
th
e
n
ticat
io
n
f
iled
b
y
in
cr
ea
s
in
g
t
h
e
ac
cu
r
ac
y
r
at
e
lev
el
f
o
r
au
th
e
n
tica
tio
n
a
n
d
class
i
f
icat
i
o
n
p
h
ases
;
at
th
e
s
a
m
e
t
i
m
e,
w
e
h
av
e
r
ed
u
ce
d
t
h
e
f
al
s
e
ac
ce
p
tan
ce
r
ate.
W
e
h
av
e
s
co
r
ed
a
s
ig
n
i
f
ica
n
t
a
u
th
en
ticatio
n
ac
c
u
r
ac
y
r
ate
b
y
f
o
llo
w
i
n
g
ce
r
tain
p
r
o
p
er
s
tep
s
;
s
tar
ti
n
g
f
r
o
m
p
r
ep
r
o
ce
s
s
in
g
t
h
e
r
a
w
E
C
G
s
ig
n
a
l
d
ata,
f
ea
tu
r
e
s
elec
tio
n
,
s
eg
m
e
n
tatio
n
an
d
e
x
tr
ac
tio
n
t
ec
h
n
iq
u
e.
A
l
s
o
,
w
e
h
av
e
u
s
ed
th
e
b
es
t
clas
s
i
f
icati
o
n
m
et
h
o
d
in
E
C
G
s
i
g
n
a
l
ca
s
e
u
i
n
s
g
li
n
ea
r
SVM
clas
s
if
ier
a
n
d
at
t
h
e
s
a
m
e
ti
m
e
w
e
h
av
e
u
s
ed
te
m
p
late
m
atc
h
i
n
g
tec
h
n
iq
u
e
f
o
r
au
th
e
n
tica
tio
n
p
r
o
ce
s
s
.
2.
E
C
G
SI
G
NA
L
P
H
YS
I
O
L
O
G
Y
W
h
en
th
e
h
ea
r
t
ce
lls
ar
e
in
r
es
t
s
itu
atio
n
th
e
y
co
n
s
id
er
ed
as
in
p
o
lar
ized
ca
s
e
w
h
ic
h
m
ea
n
s
th
at
th
er
e
is
n
o
elec
tr
ical
ac
tiv
i
t
y
is
ta
k
i
n
g
p
lace
at
th
e
m
o
m
e
n
t.
B
asic
all
y
,
th
e
h
ea
r
t
is
d
ep
o
lar
ized
w
h
e
n
it
is
in
s
y
s
to
le
s
tate
a
n
d
r
ep
o
lar
ized
w
h
en
it
is
at
d
i
a
s
to
le
s
tate.
T
h
e
d
ep
o
lar
izatio
n
ca
s
e
in
n
o
r
m
al
E
C
G
w
av
e
tak
e
s
p
lace
f
r
o
m
th
e
b
eg
i
n
n
i
n
g
t
h
e
P
w
a
v
e
u
n
til
t
h
e
m
id
d
le
o
f
ST
s
eg
m
en
t
as
s
h
o
w
n
in
F
ig
u
r
e
1
,
w
h
il
e
th
e
r
ep
o
lar
izatio
n
ca
s
e
s
tar
ts
f
r
o
m
t
h
e
T
w
a
v
e
[
7]
,
[8
].
Fig
u
r
e
1
.
E
C
G
s
i
g
n
al
p
h
y
s
io
lo
g
y
.
B
r
o
ad
ly
,
E
C
G
ti
m
e
–
f
r
eq
u
en
c
y
f
ea
t
u
r
es
ar
e
class
i
f
ied
as
eith
er
w
a
v
e
f
o
r
m
o
r
ch
ar
ac
ter
is
tic
b
ased
f
ea
t
u
r
es.
T
h
e
s
i
m
p
le
s
t
o
n
e
to
o
b
tain
a
m
o
n
g
t
h
e
f
ea
t
u
r
es
is
ch
ar
ac
ter
is
tic
b
ased
,
b
ec
au
s
e
i
n
o
r
d
er
to
s
tar
t
th
e
ex
tr
ac
tio
n
p
r
o
ce
s
s
;
it
j
u
s
t
r
eq
u
ir
e
th
e
E
C
G
f
id
u
cial
p
o
in
ts
in
f
o
r
m
a
tio
n
ab
o
u
t
o
n
e
o
f
E
C
G
co
m
p
lex
.
I
n
F
ig
u
r
e
1
P
S,
P
,
P
E
,
Q,
R
,
S,
T
S,
T
,
T
E
ar
e
th
e
f
id
u
cial
p
o
in
ts
o
f
t
h
e
g
i
v
en
p
o
r
tio
n
f
r
o
m
t
h
e
E
C
G
s
ig
n
al.
F
id
u
cial
p
o
in
t
s
r
ep
r
esen
t
t
h
e
co
r
r
esp
o
n
d
en
ce
p
o
in
ts
th
a
t
in
ter
s
ec
t
w
it
h
th
e
p
ea
k
s
a
n
d
b
o
u
n
d
ar
ies
o
f
P
,
QR
S
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.
8
,
No
.
2
,
A
p
r
il
201
8
:
6
5
8
–
6
6
5
660
an
d
T
w
a
v
e
s
.
I
n
id
ea
l
E
C
G
c
o
m
p
le
x
,
th
er
e
ar
e
s
ix
b
o
u
n
d
ar
ies
an
d
th
r
ee
p
ea
k
s
(
P
,
R
,
an
d
T
)
as
illu
s
tr
ated
in
F
ig
u
r
e
1
[
9
].
T
h
e
m
a
in
f
ea
t
u
r
es
t
h
at
ai
m
ed
to
b
e
ex
tr
ac
ted
ar
e
an
g
le,
s
l
o
p
e,
am
p
lit
u
d
e
an
d
d
u
r
atio
n
(
te
m
p
o
r
al)
.
Dis
cr
i
m
in
at
iv
e
c
h
a
r
ac
ter
is
tics
m
u
s
t
b
e
s
elec
ted
f
r
o
m
t
h
ese
f
ea
t
u
r
es
b
y
ap
p
ly
in
g
ex
tr
a
p
r
o
ce
s
s
in
g
o
v
er
th
e
m
[
10
]
.
T
h
e
p
r
o
b
lem
o
f
e
x
tr
ac
ti
n
g
ch
ar
ac
ter
i
s
tic
b
ased
f
ea
t
u
r
es
is
w
h
en
w
e
u
s
e
f
id
u
cial
p
o
in
ts
t
h
at
m
a
y
ca
u
s
e
d
if
f
ic
u
lt
ies i
n
d
etec
tin
g
t
h
e
b
o
u
n
d
ar
ies e
s
p
ec
iall
y
i
n
t
h
e
p
r
esen
ce
o
f
n
o
i
s
e.
On
t
h
e
o
t
h
er
h
an
d
,
W
a
v
ef
o
r
m
b
ased
f
ea
t
u
r
es
p
r
o
ce
s
s
ed
b
y
u
s
i
n
g
t
h
e
w
a
v
e
f
o
r
m
p
r
o
ce
s
s
co
ef
f
icien
t
v
alu
e
s
s
u
c
h
as
au
to
co
r
r
elatio
n
,
f
o
u
r
ier
co
ef
f
icien
t,
p
h
ase
s
p
ac
e
r
ec
o
n
s
tr
u
ctio
n
,
an
d
w
av
el
et
co
ef
f
icie
n
t.
I
t
i
s
w
o
r
th
m
en
tio
n
i
n
g
th
at
m
o
s
t
o
f
th
e
E
C
G
co
m
p
le
x
es
ar
e
u
s
e
d
in
w
av
e
f
o
r
m
tec
h
n
iq
u
e
f
o
r
f
ea
t
u
r
e
ex
tr
ac
tio
n
.
T
h
e
tech
n
iq
u
e
h
as
an
ad
v
a
n
tag
e
o
f
n
o
t
r
eq
u
ir
i
n
g
d
etec
ti
o
n
o
f
th
e
f
id
u
cial
p
o
i
n
ts
wh
ich
m
a
y
g
e
n
er
ate
b
o
u
n
d
ar
y
d
etec
tio
n
d
if
f
icu
lt
ie
s
in
th
e
p
r
esen
ce
o
f
n
o
i
s
e
[
1
1
].
T
h
er
ef
o
r
e,
in
o
r
d
er
t
o
av
o
id
b
o
u
n
d
ar
y
d
etec
tio
n
d
if
f
ic
u
lt
ies
is
s
u
e,
w
e
h
a
v
e
ex
t
o
r
ted
w
a
v
e
f
o
r
m
b
ased
f
ea
t
u
r
e
o
u
t o
f
th
e
E
C
G
s
i
g
n
al.
3.
RE
S
E
ARCH
M
E
T
H
O
D
O
u
r
m
et
h
o
d
s
tr
u
ct
u
r
e
is
o
r
g
an
ized
b
y
a
s
eq
u
e
n
ce
o
f
p
r
o
ce
s
s
in
g
s
tep
s
;
s
tar
t
in
g
w
it
h
E
C
G
p
r
ep
r
o
ce
s
s
in
g
,
E
C
G
f
ea
t
u
r
e
s
elec
tio
n
,
Seg
m
a
n
taio
n
,
E
C
G
f
ea
t
u
r
e
ex
tr
ac
tio
n
,
I
n
ter
-
B
ea
t
-
I
n
ter
v
al
(
I
B
I
)
p
r
ep
r
o
ce
s
s
in
g
an
d
I
B
I
ex
tr
ac
ti
o
n
.
T
h
e
f
ir
s
t
s
tep
i
n
E
C
G
p
r
ep
r
o
ce
s
s
i
n
g
,
i
s
t
h
at
w
e
s
h
o
u
ld
f
il
t
er
th
e
E
C
G
to
m
a
x
i
m
ize
b
ea
t
d
etec
tio
n
ef
f
icien
c
y
.
Hi
g
h
-
p
as
s
f
i
lter
in
g
w
as
u
s
ed
to
r
e
m
o
v
e
t
h
e
b
ase
lin
e
w
a
n
d
er
,
w
h
ich
i
s
ac
h
ie
v
e
d
b
y
s
u
b
tr
ac
tin
g
a
lo
w
f
r
eq
u
e
n
c
y
tr
e
n
d
li
n
e
f
r
o
m
th
e
E
C
G
[
12
]
.
T
h
is
tr
en
d
li
n
e
w
as
f
o
r
m
ed
b
y
ap
p
l
y
in
g
a
tr
i
an
g
u
lar
(
t
w
o
-
p
ass
)
m
o
v
i
n
g
av
er
a
g
e
f
ilter
w
it
h
a
w
i
n
d
o
w
s
ize
o
f
512
p
o
in
ts
a
n
d
co
n
s
ten
t
r
ate
o
f
5
0
HZ
to
th
e
E
C
G
s
i
g
n
al.
On
t
h
e
o
th
er
h
an
d
,
L
o
w
-
p
as
s
f
i
lter
in
g
is
u
s
ed
to
r
e
m
o
v
e
h
ig
h
f
r
eq
u
en
c
y
n
o
is
e
b
y
u
s
i
n
g
a
tr
ian
g
u
l
ar
m
o
v
i
n
g
a
v
er
ag
e
f
ilter
w
it
h
a
w
i
n
d
o
w
s
ize
o
f
3
p
o
in
ts
.
Mo
v
in
g
av
er
ag
e
f
ilter
s
p
r
o
v
id
ed
a
s
i
m
p
le,
v
alu
ab
le,
an
d
f
ast
m
et
h
o
d
to
f
ilte
r
E
C
G
[
13]
,
[
1
4
].
W
e
h
av
e
ap
p
l
ied
f
ea
tu
r
e
s
elec
tio
n
p
h
as
e
b
y
u
s
i
n
g
a
b
s
(
)
Ma
tlab
b
u
ilt
-
i
n
f
u
n
ctio
n
to
ap
p
l
y
th
e
ab
s
o
lu
te
v
al
u
e
o
v
er
th
e
w
h
o
le
E
C
G
s
ig
n
al
d
ata.
R
ig
h
t
a
f
ter
t
h
e
p
r
ep
r
o
ce
s
s
in
g
co
m
es
t
h
e
s
e
g
m
en
tatio
n
,
E
C
G
s
eg
m
e
n
ts
w
er
e
p
r
o
ce
s
s
ed
f
o
r
3
0
s
ec
o
n
d
s
.
T
h
is
p
r
o
ce
s
s
s
tar
ts
b
y
p
ass
i
n
g
a
m
o
v
in
g
w
i
n
d
o
w
o
v
er
th
e
e
n
tire
E
C
G
d
ata
f
o
r
5
m
i
n
u
tes
[
15
]
.
T
h
en
,
f
ig
u
r
es
o
v
er
E
C
G
w
er
e
co
llected
f
o
r
ea
ch
w
i
n
d
o
w
o
n
ti
m
e.
A
cc
o
r
d
in
g
to
t
h
e
o
u
tp
u
t,
a
lis
t
o
f
f
u
n
ctio
n
a
l
E
C
G
s
eg
m
e
n
ts
w
a
s
cr
ea
ted
.
T
h
e
s
elec
tio
n
cr
iter
ia
f
o
r
th
e
ap
p
licab
le
5
m
in
u
te
s
e
g
m
en
t
h
av
e
b
ee
n
ac
h
iev
ed
b
y
th
e
f
o
llo
w
i
n
g
:
a.
Hea
r
t r
ate
(
HR
)
m
ea
n
w
a
s
m
o
r
e
th
an
2
5
0
b
ea
ts
/
m
i
n
b.
T
h
e
o
v
er
all
n
u
m
b
er
o
f
ec
to
p
ic
b
ea
ts
w
er
e
les
s
th
a
n
1
% o
f
to
t
al
b
ea
ts
c.
T
h
e
n
o
n
ex
i
s
ten
ce
o
f
s
i
g
n
if
ica
n
t
m
is
s
in
g
d
ata,
an
d
th
e
v
is
u
al
in
s
p
ec
tio
n
o
f
n
o
is
e
a
n
d
ec
o
t
y
p
e.
d.
Sig
n
i
f
ica
n
t
m
is
s
in
g
d
ata
w
a
s
d
ef
i
n
ed
as h
a
v
i
n
g
m
o
r
e
t
h
an
1
5
0
co
n
s
e
cu
ti
v
e
m
i
s
s
i
n
g
d
ata
v
al
u
es o
r
m
is
s
i
n
g
m
o
r
e
th
a
n
1
5
0
m
s
co
n
s
ec
u
ti
v
el
y
.
e.
Seg
m
en
ts
w
it
h
les
s
t
h
an
1
5
0
co
n
s
ec
u
tiv
e
m
i
s
s
i
n
g
d
ata
v
al
u
e
s
w
er
e
i
n
ter
p
o
lated
u
s
i
n
g
c
u
b
i
c
s
p
li
e.
Fig
u
r
e
2
.
T
em
p
late
m
atc
h
i
n
g
f
o
r
QR
S d
etec
tio
n
As a
r
esu
lt,
t
h
e
ap
p
licab
le
5
m
in
u
te
s
e
g
m
e
n
t
w
i
th
t
h
e
lo
w
est
HR
w
as c
h
o
s
en
f
o
r
an
al
y
s
i
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:
2088
-
8708
Utiliz
in
g
E
C
G
W
a
ve
fo
r
m
F
ea
tu
r
es
a
s
N
ew B
io
met
r
ic
A
u
th
en
tica
tio
n
Meth
o
d
(
A
h
med
Yo
u
n
es S
h
d
efa
t)
661
Fo
r
th
e
E
C
G
f
ea
t
u
r
e
e
x
tr
ac
tio
n
,
C
o
r
r
elatio
n
b
ased
te
m
p
late
m
atc
h
i
n
g
al
g
o
r
ith
m
w
a
s
u
s
e
d
to
lo
ca
te
QR
S c
o
m
p
le
x
es [
1
6
]
.
Ho
w
e
v
e
r
,
t
w
o
QR
S
t
y
p
es
o
f
te
m
p
late
s
w
er
e
i
m
p
le
m
e
n
ted
to
ac
h
ie
v
e
te
m
p
late
m
atch
in
g
an
d
t
h
e
y
w
er
e
cr
ea
ted
b
y
a
v
e
r
ag
in
g
m
o
r
e
t
h
a
n
2
0
Q
R
S
co
m
p
lex
e
s
[
1
7
]
.
T
h
e
f
ir
s
t
t
y
p
e
o
f
te
m
p
late
w
a
s
th
e
Glo
b
al
te
m
p
late;
g
lo
b
al
i
n
th
e
s
en
s
e
th
at
o
n
e
te
m
p
lat
e
w
a
s
s
u
itab
le
f
o
r
all
s
u
b
j
ec
ts
as s
h
o
wn
in
Fi
g
u
r
e
2
.
I
n
I
B
I
p
r
ep
r
o
ce
s
s
in
g
an
d
b
e
f
o
r
e
in
itiati
n
g
t
h
e
co
r
r
ec
tio
n
p
r
o
ce
s
s
o
v
er
t
h
e
ec
to
p
ic
in
t
er
v
als,
w
e
s
h
o
u
ld
b
e
ac
q
u
ain
ted
w
it
h
t
h
e
m
.
T
o
ac
h
iev
e
th
e
p
r
o
p
er
d
etec
tio
n
tech
n
iq
u
es,
w
e
h
a
v
e
u
s
ed
p
er
ce
n
tag
e,
s
tan
d
ar
d
d
ev
iatio
n
an
d
m
ed
ia
n
f
ilter
s
.
T
h
e
m
ed
ian
f
ilter
ac
ts
as
a
n
i
m
p
u
l
s
e
r
ej
ec
tio
n
f
ilt
er
w
it
h
t
h
r
es
h
o
ld
t
o
d
elin
ea
te
ec
to
p
ic
in
ter
v
als
[
18
,
19
]
.
A
len
g
th
o
f
N
w
it
h
r
an
d
o
m
v
ar
iab
le
x
u
s
in
g
a
t
h
r
es
h
o
ld
o
f
τ
f
o
r
m
ed
ia
n
f
ilter
eq
u
atio
n
is
g
i
v
en
b
y
t
h
e
f
o
llo
w
in
g
eq
u
at
io
n
:
(
)
|
(
)
(
)
|
*
|
(
)
(
)
|
+
(
1
)
I
f
D
(
n
)
≤
,
th
en
n
o
t e
cto
p
ic;
else e
cto
p
ic
T
h
e
co
r
r
ec
tio
n
p
r
o
ce
s
s
is
esta
b
lis
h
ed
af
ter
d
etec
tin
g
t
h
e
ec
t
o
p
ic
in
ter
v
al
b
y
ap
p
l
y
in
g
f
o
u
r
co
r
r
ec
tio
n
tech
n
iq
u
es.
T
h
e
co
r
r
ec
tio
n
p
r
o
ce
s
s
is
es
tab
lis
h
ed
af
ter
d
etec
tin
g
t
h
e
ec
to
p
ic
in
ter
v
al
b
y
ap
p
l
y
in
g
f
o
u
r
co
r
r
ec
tio
n
tech
n
iq
u
es
[
20
]
.
T
h
e
f
ir
s
t
o
n
e
ai
m
s
to
eli
m
i
n
ate
a
n
y
ec
to
p
ic
in
ter
v
als
co
u
ld
b
e
f
o
u
n
d
.
T
h
e
s
ec
o
n
d
tech
n
iq
u
e
i
s
u
s
ed
to
r
ep
lace
a
n
y
ec
to
p
ic
in
ter
v
al
w
i
th
th
e
m
ea
n
v
alu
e
o
f
w
n
ea
r
t
h
e
I
B
I
in
ter
v
als
ce
n
ter
ed
o
n
th
e
ec
to
p
ic
i
n
ter
v
al
as
s
h
o
w
n
in
E
q
u
atio
n
(
2
)
.
Me
d
ian
tec
h
n
iq
u
e
i
s
r
elate
d
to
t
h
e
r
ep
la
ce
m
en
t
o
f
ec
to
p
ic
in
ter
v
a
ls
w
it
h
th
e
m
ed
ia
n
v
al
u
e
o
f
w
n
eig
h
b
o
r
in
g
th
e
I
B
I
i
n
ter
v
al
s
ce
n
ter
ed
o
n
th
e
ec
to
p
ic
in
ter
v
al
as
s
h
o
wn
in
E
q
u
atio
n
(
3
)
.
Fin
all
y
,
c
u
b
ic
s
p
lin
e
r
ep
lace
s
ec
to
p
ic
in
ter
v
als b
y
u
s
i
n
g
c
u
b
ic
s
p
lin
e
i
n
ter
p
o
latio
n
.
(
)
*
(
)
|
|
(
2
)
(
)
*
(
)
|
|
(
3
)
T
h
er
e
ar
e
m
u
ltip
le
m
ec
h
a
n
is
m
s
o
f
s
i
g
n
al
d
etr
en
d
in
g
(
n
o
r
m
alizi
n
g
)
to
r
e
m
o
v
e
lo
w
f
r
eq
u
en
c
y
,
s
o
m
e
o
f
th
e
s
e
m
ec
h
a
n
is
m
s
ar
e:
li
n
e
ar
d
etr
en
d
in
g
,
p
o
l
y
n
o
m
ia
l
d
etr
en
d
in
g
,
w
av
ele
t
d
etr
en
d
in
g
a
n
d
w
av
elet
p
ac
k
et
d
etr
en
d
in
g
.
I
n
th
e
I
B
I
ex
tr
ac
tio
n
s
tep
,
th
e
d
ata
co
n
tain
b
ea
t
-
to
-
b
ea
t
i
n
ter
v
als
t
h
at
w
er
e
b
asicall
y
elicite
d
f
r
o
m
th
e
E
C
G
s
i
g
n
a
ls
.
C
o
m
m
o
n
l
y
,
w
e
r
el
y
o
n
R
-
w
a
v
e
to
f
i
n
d
th
e
te
m
p
o
r
al
lo
ca
tio
n
s
o
f
b
ea
ts
a
s
it
is
o
f
te
n
th
e
ea
s
iest
w
a
v
e
to
d
i
s
ti
n
g
u
i
s
h
.
Mo
r
eo
v
er
,
R
w
av
e
s
t
y
p
icall
y
h
a
v
e
th
e
lar
g
e
s
t
a
m
p
lit
u
d
es
i
n
co
m
p
ar
is
o
n
w
it
h
s
u
r
r
o
u
n
d
in
g
P
,
Q,
S,
an
d
T
w
a
v
ef
o
r
m
s
[
21
].
T
h
e
f
o
llo
w
in
g
eq
u
atio
n
clar
if
i
es
h
o
w
to
ca
lc
u
late
t
i
m
e
s
er
ie
s
I
B
I
o
f
a
n
E
C
G
s
e
g
m
e
n
t
co
n
tain
i
n
g
N
b
ea
ts
,
w
h
er
e
b
ea
t (
n
)
is
th
e
ti
m
e
lo
ca
tio
n
o
f
t
h
e
n
th
b
ea
t:
(
)
(
)
(
)
(
4
)
T
h
e
s
y
s
te
m
m
o
d
el
co
n
s
i
s
ts
o
f
a
s
er
ies
o
f
p
r
o
ce
s
s
s
tar
t
f
r
o
m
r
ec
o
r
d
in
g
a
p
o
r
tio
n
o
f
3
0
s
ec
o
n
d
f
r
o
m
th
e
r
a
w
s
i
g
n
a
l
f
o
r
th
e
f
ir
s
t
ti
m
e,
P
r
e
-
p
r
o
ce
s
s
th
e
r
a
w
s
i
g
n
al
,
E
x
to
r
t
th
e
f
ea
tu
r
e
o
u
t
o
f
i
t
t
h
en
i
n
t
h
e
au
th
e
n
tica
tio
n
p
r
o
ce
s
s
th
e
s
y
s
te
m
w
ill
ap
p
l
y
te
m
p
late
m
a
tc
h
in
g
tec
h
n
iq
u
e
as
s
h
o
w
n
i
n
F
ig
u
r
e
3
.
Af
ter
th
e
s
y
s
te
m
w
i
ll
s
u
cc
e
s
s
f
u
ll
y
r
ec
o
g
n
ized
th
e
u
s
er
;
th
e
L
i
n
ea
r
SVM
class
i
f
ier
w
i
ll
class
i
f
y
th
e
u
s
er
s
ac
co
r
d
in
g
to
au
th
o
r
izatio
n
lev
el
a
s
s
o
ciate
d
w
it
h
all
g
r
a
n
ted
p
r
iv
ileg
e
s
t
o
ea
ch
lev
el
s
u
ch
as
“
ad
m
in
”
o
r
“
r
eg
u
lar
u
s
er
”
lev
el.
T
h
e
s
y
s
te
m
w
i
ll
d
is
p
la
y
th
e
u
s
er
n
a
m
e,
a
g
e,
g
en
d
er
,
E
C
G
s
i
g
n
al,
s
p
ec
tr
u
m
,
Q
R
S
c
o
m
p
le
x
,
h
ea
r
t
b
ea
t
b
ased
o
n
s
ig
n
al
an
d
h
ea
r
t b
ea
t b
ased
o
n
s
p
ec
tr
u
m
[
22
-
24
].
We
h
av
e
u
s
ed
L
I
B
L
I
NE
A
R
[
2
5
]
,
[
2
6
]
o
v
er
8
s
u
b
j
ec
ts
‟
E
C
G
r
ec
o
r
d
s
f
o
r
tr
ain
in
g
s
et
a
n
d
36
s
u
b
j
ec
ts
‟
E
C
G
r
ec
o
r
d
s
f
o
r
test
in
g
s
et.
W
e
h
av
e
ap
p
lied
lin
ea
r
SVM
ac
co
r
d
in
g
to
[
2
7
]
r
ec
o
m
a
n
d
at
io
n
;
af
ter
th
e
y
h
a
v
e
d
o
n
e
a
co
m
p
ar
s
io
n
i
n
th
eir
w
o
r
k
b
et
w
ee
n
th
e
li
n
ea
r
an
d
n
o
n
-
lin
ea
r
SVM
p
er
f
o
r
m
a
n
c
e.
T
h
e
s
u
b
j
ec
t
ca
n
p
r
o
v
id
e
th
e
E
C
G
s
ig
n
al
to
o
u
r
s
y
s
te
m
in
m
a
n
y
w
a
y
s
,
o
n
e
o
f
th
e
w
a
y
s
i
s
b
y
to
u
c
h
i
n
g
th
e
m
o
b
ile
a
n
d
b
r
ac
elet
elec
tr
o
d
es
w
it
h
t
h
e
f
i
n
g
er
t
ip
s
f
o
r
f
ir
s
t
-
t
i
m
e
en
r
o
ll
m
en
t
an
d
te
m
p
late
cr
ea
tio
n
o
r
b
y
j
u
s
t
t
o
ch
in
g
t
h
e
b
r
ac
elet
th
at
co
n
tai
n
s
t
w
o
elec
tr
o
d
es
th
at
lo
ca
ted
in
th
e
u
p
p
er
s
id
e
an
d
u
n
d
er
th
e
b
r
ac
elet
lik
e
in
Ny
m
i
b
a
n
d
ca
s
e
.
T
h
e
o
th
er
w
a
y
i
s
b
y
d
o
in
g
t
h
e
E
C
G
r
ec
o
r
d
in
g
in
clin
ic
o
r
h
o
s
p
ital
b
u
t
it
is
n
o
t
co
n
v
i
n
ea
n
t
o
n
e
b
ec
au
s
e
it
is
n
o
t
p
r
ac
tical
d
u
e
to
s
o
m
e
l
i
m
itiati
o
n
s
li
k
e
it
w
ill
n
o
t b
e
av
ialab
e
all
o
f
th
e
ti
m
e
to
ap
p
l
y
it.
W
e
u
s
ed
th
e
f
o
llo
w
in
g
eq
u
atio
n
to
ass
e
s
s
ac
cu
r
ac
y
r
ate
(
A
R
)
o
v
er
th
e
clas
s
i
f
ic
atio
n
an
d
au
th
e
n
tica
tio
n
p
h
a
s
e
s
o
f
o
u
r
ex
p
er
i
m
e
n
t:
(
5
)
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.
8
,
No
.
2
,
A
p
r
il
201
8
:
6
5
8
–
6
6
5
662
W
h
er
e
v
ar
iab
le
r
ep
r
esen
t
t
h
e
n
u
m
b
er
o
f
t
h
e
s
a
m
p
les
th
a
t
h
av
e
test
ed
co
r
r
ec
tl
y
d
u
r
i
n
g
t
h
e
class
i
f
icatio
n
an
d
a
u
t
h
en
t
icati
o
n
p
h
ase
s
.
T
h
e
v
ar
iab
le
r
ep
r
esen
t
t
h
e
to
tal
n
u
m
b
er
o
f
4
4
s
u
b
j
ec
ts
'
test
s
a
m
p
les.
Fo
r
th
e
p
u
r
p
o
s
e
o
f
ev
al
u
ati
n
g
t
h
e
a
u
th
e
n
tica
tio
n
p
h
a
s
e
o
f
o
u
r
ex
p
er
i
m
e
n
t,
w
e
h
av
e
u
s
ed
th
e
f
o
llo
w
in
g
eq
u
at
io
n
s
w
h
er
e
E
q
u
atio
n
(
6
)
is
to
o
b
tain
f
al
s
e
ac
ce
p
t r
ate
(
FA
R
)
:
F
A
R
=
(
6
)
I
n
f
ac
t
,
i
n
eq
u
atio
n
n
u
m
b
er
6
;
FP
S
r
ep
r
esen
t
th
e
n
u
m
b
er
o
f
f
alse
p
o
s
iti
v
e
s
a
m
p
les
an
d
AN
S
r
ep
r
esen
t th
e
n
u
m
b
er
o
f
ac
tu
a
l
n
eg
ati
v
e
s
a
m
p
les.
Fig
u
r
e
3
.
E
C
G
Au
t
h
e
n
tic
atio
n
S
y
s
te
m
T
ec
h
n
ica
l
A
p
p
r
o
ac
h
4.
RE
SU
L
T
S
A
ND
AN
AL
Y
SI
S
We
h
av
e
test
ed
44
s
u
b
j
ec
ts
‟
E
C
G
r
a
w
r
ec
o
r
d
s
w
it
h
t
h
e
ex
ten
s
io
n
s
(
*
.
m
a
t,
*
.
t
x
t,
*
.
d
at)
;
22
o
f
th
e
s
u
b
j
ec
ts
‟
s
a
m
p
les
w
er
e
a
u
t
h
o
r
ized
in
s
id
e
o
u
r
s
y
s
te
m
a
s
1
1
m
ales
an
d
1
1
f
e
m
ele
s
as
s
h
o
w
n
i
n
F
ig
u
r
e
3
w
h
il
e
th
e
o
th
er
22
as
1
1
m
ales
an
d
1
1
f
e
m
eles
ar
e
n
o
t
au
t
h
o
r
ized
u
s
er
s
as
sh
o
w
n
i
n
F
i
g
u
r
e
4
.
T
h
e
ac
cu
r
ac
y
r
ate
w
a
s
9
7
.
2
%
f
o
r
t
h
e
au
t
h
e
n
ticatio
n
p
r
o
ce
s
s
an
d
9
8
.
6
%
f
o
r
t
h
e
cla
s
s
if
icatio
n
ta
s
k
o
v
er
a
ll
t
h
e
s
e
g
m
en
ts
o
f
th
e
w
h
o
le
s
ig
n
al
.
Fig
u
r
e
4
.
E
C
G
Au
t
h
e
n
ticatio
n
S
y
s
te
m
r
es
u
lt
f
o
r
au
th
o
r
ized
u
s
er
Fig
u
r
e
5
.
E
C
G
Au
t
h
e
n
ticatio
n
S
y
s
te
m
r
es
u
lt
f
o
r
u
n
a
u
t
h
o
r
ized
u
s
er
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:
2088
-
8708
Utiliz
in
g
E
C
G
W
a
ve
fo
r
m
F
ea
tu
r
es
a
s
N
ew B
io
met
r
ic
A
u
th
en
tica
tio
n
Meth
o
d
(
A
h
med
Yo
u
n
es S
h
d
efa
t)
663
I
n
ti
m
e,
w
h
e
n
w
e
ap
p
lied
th
e
SVM
clas
s
i
f
er
o
v
er
a
p
o
r
tio
n
o
f
t
h
e
s
i
g
n
a
l
w
h
ich
tec
h
n
icil
y
o
n
e
s
eg
m
e
n
t
o
u
t
o
f
th
e
s
ig
n
al,
w
e
f
o
u
n
d
th
a
t
th
e
clas
s
i
f
i
ca
tio
n
ac
cu
r
ac
y
a
v
er
ag
e
w
a
s
9
5
.
8
%
an
d
w
i
th
au
th
e
n
tica
tio
n
ac
c
u
r
ac
y
av
er
a
g
e
o
f
9
6
.
9
%.
R
eg
ar
d
i
n
g
s
e
g
m
en
t
p
r
o
ce
s
s
i
n
g
ca
s
e,
t
h
e
ac
cu
r
ac
y
is
n
ea
r
l
y
t
h
e
s
a
m
e
to
th
e
p
r
o
ce
s
s
i
n
g
o
f
th
e
w
h
o
le
s
ig
n
al
ca
s
e;
b
u
t
th
e
ti
m
e
r
eq
u
ir
ed
f
o
r
a
u
t
h
en
t
icatio
n
w
as
f
a
s
ter
i
n
t
h
e
s
eg
m
a
n
tio
n
s
it
u
atio
n
.
T
o
o
v
er
co
m
e
th
is
i
s
s
u
e,
w
e
h
av
e
p
r
o
c
ess
ed
th
e
w
h
o
le
s
i
g
n
al
as a
s
er
ies o
f
s
eg
m
e
n
ts
; so
w
e
g
ain
t
h
e
h
ig
h
ac
c
u
r
ac
y
r
ate
alo
n
g
w
it
h
s
p
ee
d
in
p
er
f
o
r
m
a
n
ce
.
W
e
h
av
e
d
o
n
e
a
co
m
p
er
s
io
n
b
et
w
ee
n
o
u
r
m
et
h
o
d
an
d
p
r
ev
io
u
s
r
elate
d
w
r
o
k
s
i
n
ter
m
o
f
n
u
m
b
er
o
f
s
u
b
j
ec
ts
,
f
a
ls
e
ac
ce
p
ted
r
ate
a
n
d
ac
cu
r
ac
y
m
att
er
s
li
k
e
i
n
T
ab
le
1
.
I
t
is
o
b
v
io
u
s
th
a
t
w
e
h
av
e
i
n
cr
ea
s
ed
t
h
e
au
th
e
n
tica
tio
n
ac
c
u
r
ac
y
r
ate
a
n
d
d
ec
r
ea
s
ed
th
e
f
alse a
cc
ep
ta
n
ce
r
ate.
T
ab
le
1
.
A
u
t
h
en
t
icatio
n
R
es
u
lt
o
f
Mo
th
o
d
s
R
e
c
e
r
c
h
N
o
.
S
u
b
j
e
c
t
s
Y
e
a
r
F
A
R
A
c
c
u
r
a
c
y
W
.
Y
a
r
o
n
g
e
t
a
l
.
[
6
]
15
2
0
1
5
3
.
6
1
%
9
6
.
4
%
J.
S
.
A
r
t
e
a
g
a
-
F
a
l
c
o
n
i
e
t
a
l
.
[
1
]
73
2
0
1
6
1
.
2
9
%
8
4
.
9
3
%
O
u
r
p
r
o
p
o
u
se
d
me
t
h
o
d
44
2
0
1
7
1
.
2
1
%
9
7
.
2
%
5.
CO
NCLU
SI
O
N
Ou
r
d
esig
n
p
av
es
t
h
e
w
a
y
to
war
d
s
a
co
m
p
r
eh
en
s
i
v
e
s
ec
u
r
e
s
y
s
te
m
t
h
at
is
u
s
i
n
g
a
n
e
w
f
ea
t
u
r
e
w
h
ic
h
is
E
C
G
s
ig
n
al
a
n
al
y
s
is
a
s
o
n
e
o
f
th
e
b
io
m
etr
ic
m
et
h
o
d
s
.
B
y
u
s
i
n
g
E
C
G
s
ig
n
al
w
a
v
e
f
o
r
m
f
ea
tu
r
es a
s
b
io
m
e
tr
ic
au
th
e
n
tica
tio
n
w
e
h
a
v
e
co
n
cl
u
d
ed
th
at
th
ese
f
ea
tu
r
es
ca
n
n
o
t
b
e
co
p
ied
o
r
m
a
n
ip
u
lated
.
T
h
er
ef
o
r
e,
s
y
s
te
m
s
i
m
m
u
n
it
y
ag
ai
n
s
t
in
tr
u
s
io
n
an
d
f
ak
e
s
ig
n
at
u
r
e
to
id
en
tify
th
e
p
er
s
o
n
d
u
r
in
g
th
e
au
th
e
n
tica
tio
n
p
r
o
ce
s
s
w
ill
b
e
i
m
p
er
v
io
u
s
.
W
e
h
av
e
i
n
cr
ea
s
ed
t
h
e
ac
c
u
r
a
c
y
r
ate
an
d
r
ed
u
ce
d
th
e
f
alse
ac
ce
p
t
r
ate
s
i
g
n
if
ican
t
l
y
,
co
m
p
ar
in
g
w
it
h
p
r
ev
io
u
es
r
elate
d
w
o
r
k
l
ik
e
in
[
1
,
6
]
ca
s
es.
B
y
r
ed
u
ci
n
g
t
h
e
f
al
s
e
ac
ce
p
ted
r
ate,
t
h
e
a
u
t
h
e
n
ticatio
n
ac
c
u
r
ac
y
w
il
l
b
e
s
tead
il
y
i
n
cr
ea
s
ed
.
W
e
h
av
e
s
u
cc
ess
f
u
ll
y
r
ea
ch
ed
a
h
i
g
h
ac
c
u
r
ac
y
le
v
el
i
n
au
t
h
en
ticatio
n
an
d
class
i
f
icatio
n
w
is
e
o
f
E
C
G
r
a
w
s
ig
n
al.
W
e
ar
e
lo
o
k
in
g
f
o
r
w
ar
d
to
d
ep
lo
y
m
y
s
y
s
te
m
ef
f
ec
tiv
el
y
in
m
a
n
y
lif
e
asp
ec
ts
lik
e
h
ea
lt
h
m
o
n
ito
r
in
g
; n
o
t j
u
s
t r
eg
ar
d
in
g
s
y
s
te
m
s
s
e
cu
r
it
y
m
atter
s
.
RE
F
E
R
E
NC
E
S
[1
]
J.
S
.
A
rtea
g
a
-
F
a
lco
n
i,
H.
A
l
O
s
m
a
n
a
n
d
A
.
El
S
a
d
d
ik
,
"
ECG
A
u
th
e
n
ti
c
a
ti
o
n
f
o
r
M
o
b
il
e
De
v
ice
s,"
in
IEE
E
T
ra
n
sa
c
ti
o
n
s o
n
I
n
stru
m
e
n
tatio
n
a
n
d
M
e
a
su
re
m
e
n
t,
v
o
l.
6
5
,
n
o
.
3
,
p
p
.
5
9
1
-
6
0
0
,
M
a
rc
h
2
0
1
6
.
[2
]
M
.
K.
Ba
sh
a
r,
Y.
O
h
ta
a
n
d
H.
Y
o
sh
id
a
,
"
ECG
-
b
a
se
d
b
io
me
tric
a
u
th
e
n
ti
c
a
ti
o
n
u
sin
g
mu
lsc
a
le
d
e
s
c
rip
to
rs
:
ECG
-
b
a
se
d
b
i
o
me
tric a
u
th
e
n
ti
c
a
ti
o
n
,
"
2
0
1
5
In
tern
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
o
n
In
te
ll
ig
e
n
t
In
f
o
rm
a
ti
c
s
a
n
d
Bio
m
e
d
ica
l
S
c
ien
c
e
s
(ICIIBM
S
),
Ok
in
a
w
a
,
2
0
1
5
,
p
p
.
1
-
4.
[3
]
S
.
Š
p
ra
g
e
r,
R.
T
ro
b
e
c
a
n
d
M
.
B.
Ju
rič,
"
Fea
si
b
il
i
ty
o
f
b
io
me
tric
a
u
t
h
e
n
ti
c
a
ti
o
n
u
si
n
g
we
a
r
a
b
le
E
CG
b
o
d
y
se
n
so
r
b
a
se
d
o
n
h
ig
h
e
r
-
o
rd
e
r
sta
ti
stic
s,"
2
0
1
7
4
0
th
In
ter
n
a
ti
o
n
a
l
Co
n
v
e
n
t
io
n
o
n
In
f
o
rm
a
ti
o
n
a
n
d
Co
m
m
u
n
ica
ti
o
n
T
e
c
h
n
o
lo
g
y
,
El
e
c
tro
n
ics
a
n
d
M
icro
e
lec
tro
n
ics
(M
I
P
RO)
,
Op
a
ti
ja,
2
0
1
7
,
p
p
.
2
6
4
-
2
6
9
.
[4
]
N.
Ka
ri
m
ian
,
P
.
A
.
W
o
rtma
n
a
n
d
F
.
T
e
h
ra
n
ip
o
o
r
,
"
Evo
lvi
n
g
a
u
th
e
n
ti
c
a
ti
o
n
d
e
sig
n
c
o
n
sid
e
ra
ti
o
n
s fo
r
th
e
In
ter
n
e
t
o
f
b
io
me
tric
th
i
n
g
s
(
Io
BT
)
,"
2
0
1
6
I
n
tern
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
o
n
Ha
rd
w
a
r
e
/S
o
f
t
w
a
re
Co
d
e
sig
n
a
n
d
S
y
ste
m
S
y
n
th
e
sis
(COD
ES
+
IS
S
S
),
P
it
tsb
u
rg
h
,
P
A
,
2
0
1
6
,
p
p
.
1
-
1
0
.
[5
]
S
.
J.
Ka
n
g
,
S
.
Y.
L
e
e
,
H.
I.
Ch
o
a
n
d
H.
P
a
rk
,
"
ECG
A
u
th
e
n
ti
c
a
ti
o
n
S
y
ste
m
De
sig
n
Ba
se
d
o
n
S
ig
n
a
l
A
n
a
l
y
sis
in
M
o
b
i
le an
d
W
e
a
ra
b
le De
v
i
c
e
s,"
i
n
IEE
E
S
i
g
n
a
l
Pr
o
c
e
ss
in
g
L
e
tt
e
rs
,
v
o
l.
2
3
,
n
o
.
6
,
p
p
.
8
0
5
-
8
0
8
,
Ju
n
e
2
0
1
6
.
[6
]
W
.
Ya
ro
n
g
a
n
d
Z.
G
a
n
g
,
"
S
tu
d
y
o
f
h
u
m
a
n
id
e
n
ti
f
ica
ti
o
n
b
y
El
e
c
tr
o
c
a
rd
io
g
ra
p
h
y
f
re
q
u
e
n
c
y
f
e
a
tu
re
s
"
2
0
1
5
.
[7
]
K.
S
.
S
.
S
u
jan
,
R.
S
.
P
rid
h
v
i,
K.
P
.
P
riy
a
a
n
d
R.
V
.
Ra
m
a
n
a
,
"
P
e
rf
o
rm
a
n
c
e
a
n
a
l
y
sis
f
o
r
th
e
F
e
a
tu
re
Ex
trac
ti
o
n
a
lg
o
rit
h
m
o
f
a
n
ECG
si
g
n
a
l,
"
In
n
o
v
a
ti
o
n
s
i
n
In
fo
rm
a
ti
o
n
,
Emb
e
d
d
e
d
a
n
d
C
o
mm
u
n
ic
a
ti
o
n
S
y
ste
ms
(ICIIE
CS
),
2
0
1
5
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
,
C
o
i
m
b
a
to
re
,
2
0
1
5
,
p
p
.
1
-
5.
[8
]
D.
Aw
a
sth
i
a
n
d
S
.
M
a
d
h
e
,
"
An
a
lys
is
o
f
e
n
c
ry
p
ted
ECG
sig
n
a
l
in
ste
g
a
n
o
g
r
a
p
h
y
u
sin
g
w
a
v
e
le
t
tra
n
sfo
rm
s,
"
El
e
c
tro
n
ics
a
n
d
C
o
m
m
u
n
ica
ti
o
n
S
y
ste
m
s
(ICECS
),
2
0
1
5
2
n
d
I
n
tern
a
ti
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
,
Co
im
b
a
to
re
,
2
0
1
5
,
p
p
.
7
1
8
-
7
2
3
.
[9
]
P
.
V
a
ll
u
ra
iah
a
n
d
B.
Bisw
a
l,
"
ECG
sig
n
a
l
a
n
a
lys
is
u
si
n
g
Hilb
e
rt
tra
n
sfo
rm
,
"
2
0
1
5
IEE
E
P
o
w
e
r,
Co
m
m
u
n
ica
ti
o
n
a
n
d
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
l
o
g
y
Co
n
f
e
r
e
n
c
e
(P
CIT
C)
,
Bh
u
b
a
n
e
sw
a
r,
In
d
ia,
2
0
1
5
,
p
p
.
4
6
5
-
4
6
9
.
[1
0
]
R.
M
a
rti
n
e
k
e
t
a
l
.
,
"
E
n
h
a
n
c
e
d
p
ro
c
e
ss
in
g
a
n
d
a
n
a
l
y
sis
o
f
m
u
lt
i
-
c
h
a
n
n
e
l
n
o
n
-
i
n
v
a
siv
e
a
b
d
o
m
in
a
l
f
o
e
tal
ECG
sig
n
a
ls
d
u
ri
n
g
lab
o
r
a
n
d
d
e
li
v
e
ry
,
"
in
El
e
c
tro
n
ics
L
e
tt
e
rs
,
v
o
l.
5
1
,
n
o
.
2
2
,
p
p
.
1
7
4
4
-
1
7
4
6
,
2
0
1
5
.
[1
1
]
E.
Be
n
m
a
le
k
a
n
d
J.
El
m
h
a
m
d
i,
"
Arrh
y
th
mi
a
ECG
sig
n
a
l
a
n
a
lys
is
u
sin
g
n
o
n
p
a
r
a
me
tric
ti
me
-
fre
q
u
e
n
c
y
tec
h
n
iq
u
e
,
"
El
e
c
tri
c
a
l
a
n
d
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
l
o
g
ies
(ICEI
T
),
2
0
1
5
In
tern
a
ti
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
,
M
a
rra
k
e
c
h
,
2
0
1
5
,
p
p
.
2
8
1
-
2
8
5
.
[1
2
]
K.
S
.
S
.
S
u
jan
,
R.
S
.
P
rid
h
v
i,
K.
P
.
P
riy
a
a
n
d
R.
V
.
Ra
m
a
n
a
,
"
P
e
rf
o
rm
a
n
c
e
a
n
a
l
y
sis
f
o
r
th
e
F
e
a
tu
re
Ex
trac
ti
o
n
a
lg
o
rit
h
m
o
f
a
n
ECG
si
g
n
a
l,
"
In
n
o
v
a
ti
o
n
s
i
n
In
fo
rm
a
ti
o
n
,
Emb
e
d
d
e
d
a
n
d
C
o
mm
u
n
ic
a
ti
o
n
S
y
ste
ms
(ICIIE
CS
),
2
0
1
5
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
,
C
o
i
m
b
a
to
re
,
2
0
1
5
,
p
p
.
1
-
5.
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.
8
,
No
.
2
,
A
p
r
il
201
8
:
6
5
8
–
6
6
5
664
[1
3
]
D.
Aw
a
sth
i
a
n
d
S
.
M
a
d
h
e
,
"
A
n
a
l
y
sis
o
f
e
n
c
r
y
p
ted
ECG
sig
n
a
l
in
ste
g
a
n
o
g
ra
p
h
y
u
sin
g
w
a
v
e
let
t
ra
n
sf
o
r
m
s,"
El
e
c
tro
n
ics
a
n
d
C
o
mm
u
n
ic
a
ti
o
n
S
y
ste
ms
(
ICECS
),
2
0
1
5
2
n
d
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
,
Co
im
b
a
to
re
,
2
0
1
5
,
p
p
.
7
1
8
-
7
2
3
.
[1
4
]
E.
Be
n
m
a
le
k
a
n
d
J.
El
m
h
a
m
d
i,
"
Arrh
y
th
mi
a
ECG
sig
n
a
l
a
n
a
lys
is
u
sin
g
n
o
n
p
a
r
a
me
tric
ti
me
-
fre
q
u
e
n
c
y
tec
h
n
iq
u
e
,
"
El
e
c
tri
c
a
l
a
n
d
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
l
o
g
ies
(ICEI
T
),
2
0
1
5
In
tern
a
ti
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
,
M
a
rra
k
e
c
h
,
2
0
1
5
,
p
p
.
2
8
1
-
2
8
5
.
[1
5
]
P
.
V
a
ll
u
ra
iah
a
n
d
B.
Bisw
a
l,
"
ECG
sig
n
a
l
a
n
a
lys
is
u
si
n
g
Hilb
e
rt
tra
n
sfo
rm
,
"
2
0
1
5
IEE
E
P
o
w
e
r,
Co
m
m
u
n
ica
ti
o
n
a
n
d
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
l
o
g
y
Co
n
f
e
r
e
n
c
e
(P
CIT
C)
,
Bh
u
b
a
n
e
s
w
a
r,
In
d
ia,
2
0
1
5
,
p
p
.
4
6
5
-
4
6
9
.
[1
6
]
S
.
Ja
in
,
A
.
Ku
m
a
r
a
n
d
V
.
Ba
jaj,
"
T
e
c
h
n
iq
u
e
f
o
r
QRS
c
o
m
p
lex
d
e
tec
ti
o
n
u
sin
g
p
a
rti
c
le
sw
a
r
m
o
p
ti
m
i
sa
ti
o
n
,
"
i
n
IE
T
S
c
ien
c
e
,
M
e
a
su
re
me
n
t
&
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
1
0
,
n
o
.
6
,
p
p
.
6
2
6
-
6
3
6
,
9
2
0
1
6
.
[1
7
]
E.
A
rra
is
Ju
n
io
r,
R.
A
.
d
e
M
e
d
e
iro
s
V
a
len
t
im
a
n
d
G
.
Be
z
e
rra
Bra
n
d
a
o
,
"
Re
a
l
T
i
m
e
QRS
De
te
c
ti
o
n
Ba
se
d
o
n
Re
d
u
n
d
a
n
t
Disc
re
te W
a
v
e
let
T
ra
n
sf
o
r
m
,
"
in
IEE
E
L
a
ti
n
Ame
ric
a
T
r
a
n
sa
c
ti
o
n
s
,
v
o
l.
1
4
,
n
o
.
4
,
p
p
.
1
6
6
2
-
1
6
6
8
,
[1
8
]
A
p
ril
2
0
1
6
.
[1
9
]
S
.
H.
F
a
n
,
C.
C.
Ch
o
u
,
W
.
C.
Ch
e
n
a
n
d
W
.
C.
F
a
n
g
,
"
Rea
l
-
ti
me
o
b
stru
c
ti
v
e
sl
e
e
p
a
p
n
e
a
d
e
tec
ti
o
n
f
ro
m
fre
q
u
e
n
c
y
a
n
a
lys
is
o
f
EDR
a
n
d
HRV
u
sin
g
L
o
mb
Per
io
d
o
g
r
a
m,"
En
g
in
e
e
r
in
g
in
M
e
d
icin
e
a
n
d
Bio
l
o
g
y
S
o
c
iety
(EM
BC),
2
0
1
5
3
7
t
h
A
n
n
u
a
l
In
tern
a
t
io
n
a
l
C
o
n
f
e
re
n
c
e
o
f
th
e
IEE
E
,
M
il
a
n
,
2
0
1
5
,
p
p
.
5
9
8
9
-
5
9
9
2
.
[2
0
]
M
.
G
.
P
o
d
d
a
r,
V
.
Ku
m
a
r
a
n
d
Y.
P
.
S
h
a
r
m
a
,
"
He
a
rt
ra
te
v
a
ri
a
b
il
it
y
:
An
a
lys
is
a
n
d
c
l
a
ss
if
ica
ti
o
n
o
f
h
e
a
lt
h
y
su
b
jec
ts
fo
r
d
i
ff
e
re
n
t
a
g
e
g
r
o
u
p
s,"
C
o
m
p
u
ti
n
g
f
o
r
S
u
sta
in
a
b
le
G
lo
b
a
l
De
v
e
lo
p
m
e
n
t
(IND
I
A
Co
m
),
2
0
1
5
2
n
d
I
n
tern
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
o
n
,
Ne
w
De
lh
i,
2
0
1
5
,
p
p
.
1
9
0
8
-
1
9
1
3
.
[2
1
]
R.
Ca
sta
ld
o
,
P
.
M
e
li
ll
o
,
R.
Iz
z
o
,
N.
De
L
u
c
a
a
n
d
L
.
P
e
c
c
h
ia,
"
F
a
ll
P
re
d
ictio
n
in
Hy
p
e
rten
siv
e
P
a
ti
e
n
ts
v
ia
S
h
o
rt
-
T
e
r
m
HRV
A
n
a
l
y
sis,"
in
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.
2
1
,
n
o
.
2
,
p
p
.
3
9
9
-
4
0
6
,
M
a
rc
h
2
0
1
7
.
[2
2
]
V
.
T
im
o
th
y
,
A
.
S
.
P
ri
h
a
tm
a
n
to
a
n
d
K.
H.
R
h
e
e
,
"
Da
t
a
p
re
p
a
ra
ti
o
n
ste
p
f
o
r
a
u
to
m
a
ted
d
ia
g
n
o
sis
b
a
se
d
o
n
HR
V
a
n
a
lys
is
a
n
d
ma
c
h
i
n
e
lea
rn
in
g
,
"
2
0
1
6
6
th
In
tern
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
o
n
S
y
ste
m
En
g
in
e
e
rin
g
a
n
d
T
e
c
h
n
o
lo
g
y
(ICS
ET
),
Ba
n
d
u
n
g
,
2
0
1
6
,
p
p
.
1
4
2
-
1
4
8
.
[2
3
]
S
.
Ke
sh
ish
z
a
d
e
h
a
n
d
S
.
Ra
sh
id
i,
"
S
in
g
le
lea
d
El
e
c
tro
c
a
rd
i
o
g
ra
m
fea
tu
re
e
x
tra
c
ti
o
n
fo
r
th
e
h
u
m
a
n
v
e
rifi
c
a
ti
o
n
,
"
2
0
1
5
5
th
In
ter
n
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
o
n
C
o
m
p
u
ter
a
n
d
Kn
o
w
led
g
e
En
g
in
e
e
rin
g
(ICCKE),
M
a
sh
h
a
d
,
2
0
1
5
,
p
p
.
1
1
8
-
1
2
2
.
[2
4
]
K.
S
in
g
h
,
A
.
S
in
g
h
v
i
a
n
d
V
.
P
a
th
a
n
g
a
y
,
"
Dr
y
c
o
n
ta
c
t
fi
n
g
e
rti
p
ECG
-
b
a
se
d
a
u
th
e
n
ti
c
a
ti
o
n
sy
st
e
m
u
si
n
g
ti
me
,
fre
q
u
e
n
c
y
d
o
ma
in
fea
t
u
re
s
a
n
d
s
u
p
p
o
rt
v
e
c
to
r
ma
c
h
in
e
,
"
2
0
1
5
3
7
th
A
n
n
u
a
l
In
tern
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
o
f
th
e
IEE
E
En
g
in
e
e
rin
g
in
M
e
d
ici
n
e
a
n
d
Bio
l
o
g
y
S
o
c
iety
(EM
BC),
M
il
a
n
,
2
0
1
5
,
p
p
.
5
2
6
-
5
2
9
[2
5
]
Ch
u
n
-
C
h
ieh
Hs
iao
,
S
h
e
i
-
W
e
i
Wan
g
,
R.
L
in
a
n
d
Re
n
-
G
u
e
y
L
e
e
,
"
M
u
lt
ip
le
b
io
me
tric
a
u
th
e
n
ti
c
a
ti
o
n
f
o
r
p
e
rs
o
n
a
l
id
e
n
ti
ty
u
si
n
g
we
a
r
a
b
le
d
e
v
ice
,
"
2
0
1
6
IEE
E
I
n
tern
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
o
n
S
y
ste
m
s,
M
a
n
,
a
n
d
Cy
b
e
rn
e
ti
c
s
(S
M
C),
Bu
d
a
p
e
st,
2
0
1
6
,
p
p
.
0
0
0
6
7
3
-
0
0
0
6
7
8
.
[2
6
]
C.
Ca
tal
a
n
d
S
.
G
u
ld
a
n
,
"
P
r
o
d
u
c
t
re
v
ie
w
m
a
n
a
g
e
m
e
n
t
so
f
t
w
a
r
e
b
a
se
d
o
n
m
u
lt
ip
le
c
las
sif
ier
s,"
in
IET
S
o
ft
w
a
re
,
v
o
l.
1
1
,
n
o
.
3
,
p
p
.
8
9
-
9
2
,
6
2
0
1
7
.
[2
7
]
L
IB
L
INE
A
R
--
A
L
ib
ra
r
y
f
o
r
S
u
p
p
o
rt
V
e
c
to
r
M
a
c
h
in
e
s,
URL
:
h
tt
p
s://
ww
w
.
c
si
e
.
n
tu
.
e
d
u
.
tw
/~
c
jl
in
/
li
b
li
n
e
a
r/
[2
8
]
Y.
Zh
a
n
g
a
n
d
Ju
n
ji
e
W
u
,
"
Pra
c
ti
c
a
l
h
u
ma
n
a
u
th
e
n
ti
c
a
ti
o
n
me
th
o
d
b
a
se
d
o
n
p
iec
e
wise
c
o
rr
e
c
ted
El
e
c
tro
c
a
rd
io
g
ra
m,
"
2
0
1
6
7
th
I
EE
E
In
tern
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
o
n
S
o
f
tw
a
re
En
g
in
e
e
rin
g
a
n
d
S
e
rv
ice
S
c
ien
c
e
(ICS
ES
S
),
Be
ij
in
g
,
2
0
1
6
,
p
p
.
3
0
0
-
3
0
3
.
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
Ahm
e
d
Yo
u
n
e
s
S
h
d
e
f
a
t
re
c
e
iv
e
d
th
e
B.
E
.
d
e
g
re
e
in
c
o
m
p
u
ter
in
f
o
r
m
a
ti
o
n
sy
ste
m
f
ro
m
Ya
r
m
o
u
k
Un
iv
e
rsit
y
,
Jo
rd
a
n
,
in
2
0
0
8
a
n
d
th
e
M
.
E.
d
e
g
re
e
in
in
f
o
r
m
a
ti
o
n
tec
h
n
o
l
o
g
y
f
ro
m
u
n
iv
e
rsit
y
Uta
ra
M
a
la
y
sia
(UU
M
),
M
a
la
y
si
a
,
in
2
0
1
0
.
His
p
re
v
io
u
s
p
o
sit
io
n
w
a
s
a
u
n
iv
e
rsity
le
c
tu
re
r
a
t
Co
m
p
u
ter
De
p
a
rtme
n
t
–
Co
ll
e
g
e
o
f
c
o
m
m
u
n
it
y
se
rv
ic
e
–
Taib
a
h
Un
iv
e
rsity
,
KSA
a
n
d
n
o
w
a
lec
tu
re
r
a
t
th
e
De
p
a
rtme
n
t
o
f
In
f
o
rm
a
ti
o
n
S
y
ste
m
a
n
d
T
e
c
h
n
o
lo
g
y
,
Am
e
rica
n
U
n
iv
e
rsity
o
f
M
id
d
le
Eas
t,
K
u
w
a
it
.
He
a
lso
p
u
rsu
e
s
f
o
r
P
h
.
D.
a
t
De
p
a
rtm
e
n
t
o
f
Co
m
p
u
ter
En
g
in
e
e
ri
n
g
,
In
je
Un
iv
e
rsity
,
Ko
re
a
.
He
h
a
s
in
tere
sts
in
th
e
a
re
a
s
o
f
b
io
-
sig
n
a
l
s,
so
f
twa
re
e
n
g
in
e
e
rin
g
,
a
n
d
d
a
ta
m
in
in
g
.
He
h
a
s
p
u
b
li
sh
e
d
se
v
e
ra
l
p
a
p
e
rs i
n
b
i
o
-
sig
n
a
ls.
M
o
o
n
-
Il
J
o
o
re
c
e
i
v
e
d
th
e
M
S
d
e
g
re
e
in
c
o
m
p
u
ter
e
n
g
in
e
e
rin
g
f
ro
m
In
je
Un
iv
e
rsit
y
,
Ko
re
a
,
in
2
0
12
.
He
c
u
rre
n
tl
y
stu
d
ies
f
o
r
P
h
D
a
t
t
h
e
d
e
p
a
rtm
e
n
t
o
f
c
o
m
p
u
ter
sc
ien
c
e
,
In
je
Un
iv
e
rsit
y
,
Ko
re
a
H
e
h
a
s
in
tere
sts
in
th
e
a
re
a
s
o
f
so
f
t
w
a
r
e
e
n
g
in
e
e
rin
g
,
h
u
m
a
n
c
o
m
p
u
ter
i
n
tera
c
ti
o
n
,
sm
a
rt
p
h
o
n
e
p
ro
g
ra
m
m
in
g
,
a
n
d
c
o
m
p
o
n
e
n
t
b
a
se
d
d
e
v
e
lo
p
m
e
n
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:
2088
-
8708
Utiliz
in
g
E
C
G
W
a
ve
fo
r
m
F
ea
tu
r
es
a
s
N
ew B
io
met
r
ic
A
u
th
en
tica
tio
n
Meth
o
d
(
A
h
med
Yo
u
n
es S
h
d
efa
t)
665
S
u
n
g
-
H
o
o
n
C
h
o
i
r
e
c
e
i
v
e
d
th
e
BS
d
e
g
re
e
in
c
o
m
p
u
ter
sc
ien
c
e
f
ro
m
In
je
Un
iv
e
rsit
y
,
Ko
re
a
,
in
2
0
1
6
.
He
is
c
u
rre
n
tl
y
a
g
ra
d
u
a
te
stu
d
e
n
t
a
t
th
e
I
n
stit
u
te
o
f
Dig
it
a
l
An
ti
-
A
g
in
g
He
a
lt
h
c
a
re
(ID
A
),
In
je
Un
iv
e
rsit
y
,
Ko
re
a
.
H
e
h
a
s
in
tere
sts
in
th
e
a
re
a
s
o
f
so
f
t
wa
re
e
n
g
in
e
e
rin
g
,
a
rti
f
icia
l
in
telli
g
e
n
c
e
a
n
d
h
e
a
lt
h
c
a
re
so
f
t
w
a
re
.
Hee
-
C
h
e
o
l
K
i
m
re
c
e
iv
e
d
th
e
M
S
d
e
g
re
e
in
c
o
m
p
u
ter
sc
ien
c
e
f
r
o
m
S
o
G
a
n
g
Un
iv
e
rsit
y
,
Ko
re
a
,
in
1
9
9
1
,
a
n
d
th
e
P
h
D
i
n
c
o
m
p
u
ter
s
c
ien
c
e
f
ro
m
S
to
c
k
h
o
lm
Un
iv
e
rsit
y
/
Ro
y
a
l
In
stit
u
te
o
f
T
e
c
h
n
o
l
o
g
y
,
S
w
e
d
e
n
in
2
0
0
1
.
He
is
a
p
r
o
f
e
ss
o
r
a
t
In
stit
u
te
o
f
Dig
it
a
l
A
n
ti
-
Ag
in
g
He
a
lt
h
c
a
re
(ID
A
)
/
De
p
a
rt
m
e
n
t
o
f
Co
m
p
u
ter
En
g
in
e
e
rin
g
/
S
m
a
r
t
W
e
ll
n
e
ss
L
a
b
,
In
je
Un
iv
e
rsit
y
,
Ko
re
a
.
He
h
a
s
b
e
e
n
i
n
v
o
lv
e
d
a
s
c
o
o
rd
i
n
a
to
r/
d
irec
to
r
in
re
se
a
rc
h
p
ro
jec
ts
in
c
lu
d
in
g
th
e
p
ro
je
c
t
o
f
„De
v
e
lo
p
m
e
n
t
o
f
n
a
n
o
f
ib
e
r
-
b
a
se
d
w
e
ll
n
e
ss
w
e
a
r
s
y
ste
m
‟
f
u
n
d
e
d
b
y
th
e
m
in
istry
o
f
k
n
o
w
led
g
e
a
n
d
e
c
o
n
o
m
y
($
2
m
il
li
o
n
,
2
0
0
9
.
6
.
–
2
0
1
4
.
5
.
)
He
h
a
s
in
tere
sts
in
t
h
e
a
re
a
s
o
f
h
u
m
a
n
c
o
m
p
u
ter
in
tera
c
ti
o
n
,
so
f
tw
a
re
e
n
g
in
e
e
rin
g
,
a
n
d
d
ig
it
a
l
h
e
a
lt
h
c
a
re
.
He
h
a
s
a
lso
p
u
b
li
sh
e
d
m
o
re
th
a
n
10
0
p
a
p
e
rs i
n
t
h
e
se
a
re
a
s.
Evaluation Warning : The document was created with Spire.PDF for Python.