I
AE
S In
t
er
na
t
io
na
l J
o
urna
l o
f
Art
if
icia
l In
t
ellig
ence
(
I
J
-
AI
)
Vo
l.
1
5
,
No
.
4
,
A
u
g
u
s
t 2
0
2
6
,
p
p
.
3
8
7
8
~
3
8
8
7
I
SS
N:
2
2
5
2
-
8
9
3
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijai.v
15
.i
4
.
p
p
3
8
7
8
-
3
8
8
7
3878
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
i
.
ia
esco
r
e.
co
m
M
etaheuris
tic
opt
imiza
tion for a
t
ri
a
l f
ibrilla
tion d
ete
ction:
feature
extractio
n
,
selec
tion, and
hy
perpa
ra
meter
t
un
ing
Z
a
id
No
un
a
1
,
H
a
m
id
B
o
uy
g
hf
1
,
M
o
ha
m
m
ed
Na
hid
1
,
I
s
s
a
Sa
biri
2
1
La
b
o
r
a
t
o
r
y
o
f
E
n
g
i
n
e
e
r
i
n
g
S
c
i
e
n
c
e
s
a
n
d
B
i
o
sc
i
e
n
c
e
s,
F
a
c
u
l
t
y
o
f
S
c
i
e
n
c
e
s
a
n
d
T
e
c
h
n
i
q
u
e
s,
H
a
ssa
n
I
I
U
n
i
v
e
r
s
i
t
y
,
M
o
h
a
mm
e
d
i
a
,
M
o
r
o
c
c
o
2
La
b
o
r
a
t
o
r
y
o
f
S
y
st
e
ms,
S
i
g
n
a
l
s
a
n
d
A
r
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
EN
S
E
T,
H
a
ssa
n
I
I
U
n
i
v
e
r
si
t
y
,
M
o
h
a
mm
e
d
i
a
,
M
o
r
o
c
c
o
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Au
g
1
0
,
2
0
2
5
R
ev
is
ed
J
u
l 1
2
,
2
0
2
6
Acc
ep
ted
J
u
l 2
1
,
2
0
2
6
Atrial
fib
ril
lati
o
n
(AF)
d
e
tec
ti
o
n
fro
m
e
lec
tro
c
a
rd
io
g
ra
m
(ECG
)
sig
n
a
ls
is
c
ru
c
ial
fo
r
e
a
rly
d
ia
g
n
o
sis
a
n
d
in
terv
e
n
t
io
n
.
Th
is
stu
d
y
p
re
se
n
t
s
a
m
u
lt
i
-
o
b
jec
ti
v
e
o
p
ti
m
iza
ti
o
n
a
p
p
ro
a
c
h
fo
r
AF
d
e
tec
ti
o
n
,
f
o
c
u
sin
g
o
n
fe
a
tu
re
e
x
trac
ti
o
n
,
se
lec
ti
o
n
,
a
n
d
n
e
u
r
a
l
n
e
two
rk
h
y
p
e
rp
a
ra
m
e
ter
tu
n
in
g
.
Th
e
m
e
th
o
d
o
lo
g
y
u
se
s
c
ro
ss
-
v
a
li
d
a
ti
o
n
d
u
ri
n
g
th
e
train
i
n
g
o
f
th
e
two
c
o
n
c
a
ten
a
ted
ECG
d
a
tas
e
t
fe
a
tu
r
e
s
a
n
d
sim
u
lt
a
n
e
o
u
sly
m
in
imiz
e
s
th
e
e
rro
r
ra
te
o
n
t
h
e
se
p
a
ra
te
v
a
li
d
a
ti
o
n
f
o
l
d
s
o
f
e
a
c
h
d
a
tas
e
t
a
n
d
re
d
u
c
e
s
th
e
n
u
m
b
e
r
o
f
se
lec
ted
fe
a
tu
re
s,
e
n
h
a
n
c
in
g
m
o
d
e
l
g
e
n
e
ra
li
z
a
ti
o
n
a
n
d
e
fficie
n
c
y
.
P
a
rti
c
le
sw
a
rm
o
p
ti
m
iza
ti
o
n
(
P
S
O),
g
re
y
wo
lf
o
p
ti
m
iza
ti
o
n
(G
WO),
a
n
d
d
iffere
n
ti
a
l
e
v
o
lu
ti
o
n
(DE)
a
lg
o
rit
h
m
s
we
re
imp
lem
e
n
ted
t
o
n
a
v
i
g
a
te
t
h
is
m
u
lt
i
-
o
b
jec
ti
v
e
sp
a
c
e
.
W
h
il
e
a
ll
th
re
e
a
lg
o
rit
h
m
s
we
re
e
x
p
lo
re
d
,
th
e
fi
n
a
l
so
lu
ti
o
n
,
d
e
m
o
n
stra
ti
n
g
a
su
p
e
rio
r
trad
e
-
o
ff
b
e
twe
e
n
a
c
c
u
ra
c
y
a
n
d
fe
a
tu
re
re
d
u
c
ti
o
n
,
wa
s
o
b
tain
e
d
u
si
n
g
DE
.
T
h
is
a
p
p
ro
a
c
h
e
ffe
c
ti
v
e
ly
i
d
e
n
ti
fies
o
p
ti
m
a
l
fe
a
tu
re
su
b
se
ts
a
n
d
n
e
u
ra
l
n
e
two
r
k
c
o
n
f
ig
u
ra
ti
o
n
s,
y
iel
d
in
g
a
r
o
b
u
st
a
n
d
c
o
m
p
a
c
t
AF
d
e
tec
ti
o
n
m
o
d
e
l.
T
h
e
p
ro
p
o
s
e
d
a
p
p
r
o
a
c
h
h
a
s
sh
o
w
n
p
ro
m
isi
n
g
re
su
lt
s,
with
th
e
m
o
d
e
l
a
c
h
iev
i
n
g
a
c
c
u
ra
c
ies
o
f
9
6
.
3
8
%
a
n
d
9
0
.
6
9
%
,
a
n
d
c
o
rre
sp
o
n
d
in
g
a
re
a
u
n
d
e
r
t
h
e
c
u
rv
e
(
AUC
)
v
a
lu
e
s
o
f
0
.
9
9
a
n
d
0
.
9
6
,
fo
r
t
h
e
first
a
n
d
se
c
o
n
d
d
a
tas
e
ts,
re
sp
e
c
ti
v
e
ly
,
u
sin
g
1
0
o
p
t
ima
ll
y
se
lec
ted
fe
a
tu
re
s.
K
ey
w
o
r
d
s
:
Atr
ial
f
ib
r
illatio
n
E
lectr
o
ca
r
d
io
g
r
am
s
ig
n
al
Featu
r
e
ex
tr
ac
tio
n
Featu
r
e
s
elec
tio
n
Hy
p
er
p
ar
a
m
eter
tu
n
in
g
Me
tah
eu
r
is
tic
o
p
tim
izatio
n
Neu
r
al
n
etwo
r
k
s
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Z
aid
No
u
n
a
L
ab
o
r
ato
r
y
o
f
E
n
g
i
n
ee
r
in
g
Scien
ce
s
an
d
B
io
s
cien
ce
s
,
Facu
lty
o
f
Scien
ce
s
an
d
T
ec
h
n
i
q
u
es
Hass
an
I
I
Un
iv
er
s
ity
Mo
h
am
m
ed
ia,
M
o
r
o
cc
o
E
m
ail:
za
id
.
n
o
u
n
a
-
etu
@
etu
.
u
n
iv
h
2
c.
m
a
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
p
r
ev
alen
ce
o
f
atr
ial
f
ib
r
ill
atio
n
(
AF)
is
ex
p
ec
ted
to
in
cr
e
ase
d
r
am
atica
lly
in
th
e
n
ea
r
f
u
tu
r
e
[
1
]
,
it
is
th
e
m
o
s
t
p
r
ev
alen
t
ty
p
e
o
f
ca
r
d
iac
ar
r
h
y
th
m
ia
an
d
is
li
n
k
ed
to
a
f
iv
e
tim
es
g
r
ea
ter
r
is
k
o
f
s
tr
o
k
e
if
lef
t
u
n
tr
ea
ted
[
2
]
.
T
h
e
ea
r
l
y
an
d
a
cc
u
r
ate
p
r
e
d
ictio
n
,
s
cr
ee
n
i
n
g
,
an
d
tim
ely
in
te
r
v
en
tio
n
ar
e
o
f
s
u
b
s
tan
tial
clin
ical
im
p
o
r
tan
ce
[
3
]
.
W
h
ile
clin
ical
r
is
k
s
co
r
es
ca
n
h
elp
id
en
tify
s
u
s
ce
p
tib
le
in
d
iv
id
u
als,
th
eir
p
r
ed
ictiv
e
ac
cu
r
ac
y
is
lim
ited
[
4
]
.
T
h
e
elec
tr
o
ca
r
d
io
g
r
am
(
E
C
G)
is
a
wid
ely
u
s
ed
to
o
l
f
o
r
d
iag
n
o
s
in
g
ca
r
d
io
-
v
ascu
lar
c
o
n
d
itio
n
s
.
I
t c
ap
tu
r
es th
e
elec
tr
ical
ac
tiv
i
ty
o
f
th
e
h
ea
r
t th
r
o
u
g
h
s
u
r
f
ac
e
elec
tr
o
d
es p
lace
d
o
n
th
e
lim
b
s
o
r
ch
est.
I
n
ter
v
als
b
etwe
en
d
if
f
er
e
n
t
wav
es
co
n
tain
d
iag
n
o
s
tic
in
f
o
r
m
atio
n
ab
o
u
t
h
ea
r
t
d
is
ea
s
es.
T
h
e
P
wav
e
co
r
r
esp
o
n
d
s
to
atr
ial
d
ep
o
lar
izatio
n
,
t
h
e
Q
R
S
co
m
p
lex
in
d
icate
s
v
en
tr
icu
lar
d
ep
o
lar
izatio
n
,
an
d
th
e
T
wav
e
r
ef
lects
v
en
tr
icu
lar
r
ep
o
lar
izatio
n
[
5
]
.
T
h
e
ef
f
icac
y
o
f
au
to
m
ated
E
C
G
in
ter
p
r
etatio
n
co
u
l
d
b
e
s
ig
n
if
ican
tly
in
cr
ea
s
ed
b
y
th
e
co
m
b
i
n
atio
n
o
f
th
e
i
n
cr
ea
s
in
g
av
ailab
ilit
y
o
f
d
ig
i
tal
E
C
G
r
ec
o
r
d
s
an
d
th
e
cr
ea
tio
n
o
f
ad
v
a
n
ce
d
alg
o
r
ith
m
s
d
esig
n
ed
to
an
al
y
ze
lar
g
e
am
o
u
n
ts
o
f
d
ata
[
6
]
.
B
y
an
aly
zin
g
th
e
f
ea
t
u
r
e
s
o
f
th
ese
wav
es,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
Meta
h
eu
r
is
tic
o
p
timiz
a
tio
n
fo
r
a
tr
ia
l fib
r
illa
tio
n
d
etec
tio
n
:
fe
a
tu
r
e
ex
tr
a
ctio
n
,
s
elec
tio
n
…
(
Za
id
N
o
u
n
a
)
3879
ab
n
o
r
m
alities
in
a
p
er
s
o
n
’
s
h
ea
r
t
f
u
n
ctio
n
ca
n
b
e
d
etec
ted
[
7
]
.
I
r
r
e
g
u
lar
R
-
R
in
ter
v
als,
th
e
lack
o
f
clea
r
ly
d
ef
in
ed
,
r
ep
ea
tin
g
P
wav
es,
d
is
o
r
g
an
ized
an
d
ir
r
eg
u
lar
atr
ial
ac
tiv
ity
ar
e
a
m
o
n
g
t
h
e
k
ey
f
ea
tu
r
es
o
f
AF
d
etec
tio
n
[
8
]
.
T
h
e
u
s
e
o
f
m
ac
h
in
e
lear
n
in
g
(
ML
)
an
d
d
ee
p
lear
n
in
g
(
DL
)
f
o
r
AF
d
etec
tio
n
b
ased
o
n
E
C
G
s
ig
n
als
is
a
f
ield
o
f
g
r
o
win
g
in
ter
est.
A
n
u
m
b
er
o
f
s
tu
d
ies
h
av
e
e
x
p
l
o
r
ed
th
is
d
o
m
ai
n
,
L
ag
h
ar
i
et
a
l.
[
9
]
d
ev
elo
p
e
d
a
d
ee
p
r
esid
u
al
-
d
en
s
e
n
etwo
r
k
with
a
b
i
d
ir
ec
tio
n
al
r
ec
u
r
r
en
t
n
eu
r
al
n
etwo
r
k
(
R
NN)
,
an
d
ac
h
iev
e
d
9
7
.
7
2
%
ac
cu
r
ac
y
,
s
en
s
itiv
ity
was
9
3
.
0
9
%,
an
d
s
p
ec
if
icity
was
9
8
.
7
1
%.
I
n
,
R
ad
et
a
l.
[
1
0
]
in
t
r
o
d
u
c
e
a
s
y
s
tem
th
at
u
s
es
a
“
v
o
tin
g
”
ap
p
r
o
ac
h
,
wh
e
r
e
th
e
r
esu
lts
o
f
s
ix
d
if
f
e
r
en
t
AF
d
etec
tio
n
alg
o
r
ith
m
s
ar
e
c
o
m
b
i
n
ed
to
m
ak
e
a
m
o
r
e
ac
cu
r
ate
f
in
al
d
ec
is
io
n
in
m
o
b
ile
E
C
G
d
ev
ices,
a
n
d
is
e
v
a
lu
ated
ac
r
o
s
s
d
i
v
er
s
e
d
atasets
.
Z
h
ao
et
a
l.
[
1
1
]
p
r
o
p
o
s
e
a
s
in
g
le
-
lea
d
E
C
Gs
AF
class
if
icatio
n
ap
p
r
o
ac
h
,
wh
ich
c
o
n
s
is
ts
o
f
u
s
in
g
c
o
m
b
in
ed
tem
p
o
r
al
co
n
v
o
l
u
tio
n
al
n
etwo
r
k
(
T
C
N)
an
d
r
esid
u
al
n
etwo
r
k
ar
ch
itect
u
r
e.
T
h
e
m
o
d
el
ac
h
iev
e
d
a
9
7
%
ac
cu
r
ac
y
an
d
an
8
7
% F1
-
s
co
r
e
o
n
th
e
2
0
1
7
Ph
y
s
io
Net/C
in
C
d
atase
t.
J
ah
an
et
a
l.
[
1
2
]
e
v
alu
atin
g
s
ev
er
al
ML
alg
o
r
ith
m
s
as
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
(
SVM
)
,
d
ec
is
io
n
tr
ee
(
DT
)
,
a
n
d
r
an
d
o
m
f
o
r
est
(
RF
)
f
o
r
AF
u
s
in
g
s
tatis
tical
f
ea
tu
r
es
ex
tr
ac
ted
f
r
o
m
E
C
G
s
ig
n
al
s
.
T
h
e
u
s
ed
d
ataset
f
o
r
tr
ain
in
g
co
n
s
is
ts
o
f
2
3
ten
-
h
o
u
r
E
C
G
r
ec
o
r
d
s
u
s
in
g
lea
v
e
o
n
e
g
r
o
u
p
o
u
t
cr
o
s
s
-
v
alid
a
tio
n
tech
n
iq
u
e
,
an
d
th
e
b
est
p
er
f
o
r
m
in
g
m
o
d
el
ac
h
iev
ed
a
s
en
s
itiv
ity
o
f
8
5
.
6
7
%,
s
p
ec
if
icity
o
f
8
1
.
2
5
%,
p
o
s
itiv
e
p
r
ed
ictiv
e
v
al
u
e
o
f
9
0
.
8
5
%,
f
alse
p
o
s
itiv
e
r
ate
o
f
1
8
.
7
5
%,
an
d
F1
-
s
co
r
e
o
f
8
8
.
1
8
%.
Du
r
an
ta
et
a
l.
[
1
3
]
p
r
es
en
t
a
n
o
v
el
m
eth
o
d
f
o
r
AF
d
etec
tio
n
co
m
b
in
in
g
wav
elet
tr
an
s
f
o
r
m
-
b
ased
f
ilter
in
g
an
d
2
4
E
C
G
ex
tr
ac
ted
f
ea
tu
r
es
as
in
p
u
t
to
th
e
n
eu
r
al
n
etwo
r
k
class
if
ier
.
R
es
u
lts
d
em
o
n
s
tr
ate
p
r
o
m
is
in
g
p
e
r
f
o
r
m
a
n
ce
,
ac
h
iev
in
g
ac
cu
r
ac
i
es
o
f
9
6
%
(
r
ec
eiv
e
r
o
p
er
atin
g
c
h
ar
ac
ter
is
tic
(
R
OC
)
0
.
9
5
)
an
d
8
6
%
(
R
OC
0
.
8
4
)
o
n
p
u
b
licly
av
ailab
le
E
C
G
d
at
asets
.
Fu
r
th
er
m
o
r
e,
5
-
f
o
ld
c
r
o
s
s
-
v
alid
atio
n
was
em
p
lo
y
ed
t
o
en
h
a
n
ce
m
o
d
el
r
o
b
u
s
tn
ess
,
r
esu
ltin
g
in
ac
cu
r
ac
i
es
o
f
9
9
%
an
d
9
0
%
f
o
r
th
e
two
d
atasets
.
Me
tah
eu
r
is
tics
o
f
f
er
r
o
b
u
s
t
s
o
lu
tio
n
s
to
c
o
m
p
le
x
o
p
tim
izatio
n
p
r
o
b
lem
s
in
ar
tific
ial
i
n
tellig
en
ce
(
AI
)
.
S
p
ec
if
ically
,
th
is
s
tu
d
y
ap
p
ly
m
etah
eu
r
is
tics
to
o
p
ti
m
ize
n
eu
r
al
n
etwo
r
k
p
e
r
f
o
r
m
an
ce
b
y
ef
f
icien
tly
s
elec
tin
g
f
ea
tu
r
es
an
d
tu
n
in
g
h
y
p
er
p
ar
am
eter
s
.
W
ith
in
wr
ap
p
er
m
eth
o
d
s
,
th
ey
ca
n
b
e
u
s
ed
in
s
elec
tin
g
f
ea
tu
r
es
b
ased
o
n
th
e
a
ctu
al
p
er
f
o
r
m
an
ce
o
f
a
class
if
ier
,
d
is
tin
g
u
is
h
in
g
it
f
r
o
m
f
ilter
m
eth
o
d
s
th
at
u
tili
ze
s
tatis
t
ical
m
ea
s
u
r
es
[
1
4
]
.
T
h
is
s
tu
d
y
aim
s
to
p
er
f
o
r
m
m
etah
eu
r
is
tic
alg
o
r
ith
m
o
p
tim
izatio
n
,
in
clu
d
in
g
n
u
m
b
er
o
f
f
ea
tu
r
es
m
in
im
izatio
n
an
d
ac
c
u
r
ac
y
m
ax
im
izatio
n
o
f
two
d
if
f
e
r
e
n
t
d
atasets
u
s
in
g
p
r
o
p
e
r
E
C
G
s
ig
n
al
f
ea
tu
r
es
ex
tr
ac
to
r
,
h
y
p
er
-
p
ar
am
eter
s
tu
n
in
g
an
d
f
ea
tu
r
es selectio
n
tech
n
iq
u
es,
to
en
h
an
ce
AF d
etec
tio
n
.
T
h
e
r
em
ain
d
er
o
f
th
is
p
a
p
er
is
s
tr
u
ctu
r
e
d
a
s
f
o
llo
ws:
s
ec
tio
n
2
p
r
o
v
id
e
s
an
o
v
e
r
v
iew
o
f
th
e
u
s
ed
d
atasets
,
d
etails
th
e
p
r
ep
r
o
ce
s
s
in
g
tech
n
iq
u
es,
an
d
th
e
o
p
tim
izatio
n
p
r
o
ce
s
s
s
tep
s
.
Sectio
n
3
ex
p
o
s
es
th
e
ex
p
e
r
im
en
tal
s
etu
p
,
th
e
co
m
p
ar
is
o
n
b
etwe
en
r
esu
lts
o
f
th
e
th
r
ee
alg
o
r
ith
m
s
in
ter
m
s
o
f
co
m
p
u
tatio
n
s
an
d
q
u
ality
o
f
s
o
lu
tio
n
,
an
d
th
en
th
e
f
in
al
c
h
o
s
en
m
o
d
el’
s
p
er
f
o
r
m
an
ce
.
Sectio
n
4
co
n
clu
d
es
th
e
p
a
p
er
with
a
s
u
m
m
ar
y
an
d
o
u
tlin
es
p
o
ten
tial
d
ir
ec
tio
n
s
f
o
r
f
u
tu
r
e
r
esear
ch
.
2.
M
E
T
H
O
D
2
.
1
.
Da
t
a
s
et
s
Fig
u
r
e
1
r
ep
r
esen
ts
th
e
d
ata
s
p
litt
in
g
,
r
esp
ec
tin
g
r
an
d
o
m
n
e
s
s
to
en
s
u
r
e
r
ep
r
esen
tativ
e
s
am
p
les
an
d
r
ed
u
ce
b
ias,
s
tr
atif
icatio
n
to
m
ain
tain
class
d
is
tr
ib
u
tio
n
s
,
a
n
d
a
h
o
ld
o
u
t
test
s
et
f
o
r
an
u
n
b
iased
ev
alu
atio
n
o
f
th
e
m
o
d
el’
s
f
in
al
p
er
f
o
r
m
a
n
c
e.
T
wo
p
u
b
licly
av
ailab
le
s
in
g
le
-
lead
E
C
G
d
atasets
ar
e
u
s
ed
,
th
e
f
ir
s
t
o
n
e
is
co
llected
f
r
o
m
th
e
web
s
ite
M
en
d
eley
d
ata
[
1
5
]
,
co
r
r
esp
o
n
d
in
g
to
E
C
G
s
ig
n
als
f
r
o
m
4
5
p
atien
ts
,
class
if
ied
in
to
1
5
class
es
o
f
C
VD
with
a
s
am
p
lin
g
f
r
eq
u
en
cy
o
f
3
6
0
a
n
d
1
0
s
as
th
e
tim
e
o
f
th
e
s
ig
n
al.
T
h
e
s
ec
o
n
d
o
n
e
is
‘
T
h
e
Ph
y
s
io
Net
in
ca
r
d
io
lo
g
y
c
h
allen
g
e
2
0
1
7
’
[
1
6
]
,
an
d
co
n
s
is
t
o
f
8
,
5
2
8
s
in
g
le
lead
d
ata
d
iv
id
ed
in
to
AF,
n
o
r
m
al
r
h
y
th
m
an
d
o
th
e
r
r
h
y
t
h
m
with
a
s
am
p
lin
g
f
r
eq
u
e
n
c
y
o
f
3
0
0
.
B
o
th
d
atasets
ar
e
u
n
b
alan
ce
d
;
th
e
y
wer
e
ad
ap
ted
b
y
Du
r
a
n
ta
et
a
l.
[
1
3
]
to
g
en
er
ate
n
ew
d
atasets
r
ep
r
esen
tin
g
two
class
es
o
n
ly
(
AF
an
d
n
o
r
m
al
d
ata
)
.
W
ith
th
e
au
th
o
r
s
'
p
er
m
is
s
io
n
,
th
ese
ad
ap
ted
d
atasets
wer
e
u
s
ed
in
th
is
s
tu
d
y
a
n
d
r
em
ain
p
u
b
licly
a
v
ailab
le
th
r
o
u
g
h
th
e
s
o
u
r
ce
lin
k
p
r
o
v
id
ed
in
th
eir
o
r
ig
in
al
p
ap
er
.
2
.
2
.
P
re
pro
ce
s
s
ing
No
is
e
d
u
r
in
g
ac
q
u
is
itio
n
an
d
tr
an
s
m
is
s
io
n
f
r
eq
u
en
tly
co
m
p
r
o
m
is
es
th
e
in
teg
r
ity
o
f
E
C
G
s
ig
n
als.
T
h
is
in
clu
d
es
b
aselin
e
wan
d
er
r
esu
ltin
g
f
r
o
m
p
atien
t
r
esp
ir
a
tio
n
,
p
o
wer
lin
e
in
ter
f
e
r
en
ce
c
au
s
ed
b
y
elec
tr
ical
p
o
wer
s
o
u
r
ce
s
,
m
u
s
cle
ar
tifa
cts
g
en
er
ated
b
y
m
u
s
cle
m
o
v
e
m
en
ts
,
an
d
Gau
s
s
ian
n
o
is
e
r
is
in
g
f
r
o
m
p
o
o
r
s
ig
n
al
tr
an
s
m
is
s
io
n
,
all
o
f
wh
ic
h
ar
e
d
ev
iatio
n
s
f
r
o
m
th
e
id
ea
l
o
f
h
i
g
h
-
q
u
ality
,
n
o
is
e
-
f
r
ee
s
i
g
n
al
[
1
7
]
.
W
av
elet
tr
an
s
f
o
r
m
d
en
o
is
in
g
is
a
c
o
m
m
o
n
tec
h
n
iq
u
e
u
s
ed
in
E
C
G
s
ig
n
al
p
r
o
ce
s
s
in
g
to
im
p
r
o
v
e
s
ig
n
al
q
u
ality
.
T
h
e
Sy
m
let
-
4
(
S
ym4
)
wav
elet
was
s
elec
ted
b
ec
au
s
e
its
n
ea
r
-
s
y
m
m
etr
ical
s
h
ap
e
clo
s
ely
m
ir
r
o
r
th
e
m
o
r
p
h
o
lo
g
ical
p
ea
k
s
o
f
an
E
C
G
s
ig
n
al.
Ar
tifa
ct
r
em
o
v
al
was
ac
h
iev
ed
b
y
d
is
ca
r
d
i
n
g
th
e
h
ig
h
est
f
r
eq
u
en
cy
d
etail
co
ef
f
icien
ts
(
lev
el
0
)
to
elim
i
n
ate
m
u
s
cle
ar
tifa
cts
an
d
p
o
wer
-
lin
e
in
ter
f
e
r
en
ce
,
wh
ile
t
h
e
lo
west
f
r
e
q
u
en
c
y
co
ef
f
icien
ts
(
lev
els
3
an
d
4
)
wer
e
r
em
o
v
e
d
to
elim
in
ate
l
o
w
-
f
r
eq
u
en
cy
a
r
tifa
cts
s
u
ch
as
r
esp
ir
ato
r
y
d
r
if
t.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2252
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
4
,
Au
g
u
s
t 2
0
2
6
:
3
8
7
8
-
3
8
8
7
3880
On
ly
th
e
in
ter
m
ed
iate
co
e
f
f
ici
en
ts
(
lev
els
1
an
d
2
)
,
wh
ich
c
ap
tu
r
e
th
e
ess
en
tial
m
o
r
p
h
o
lo
g
ical
f
ea
tu
r
es
o
f
th
e
E
C
G,
wer
e
r
etain
ed
f
o
r
r
ec
o
n
s
tr
u
ctio
n
.
Fo
llo
win
g
E
C
G
s
ig
n
al
f
ilter
in
g
,
P,
QR
S,
an
d
R
-
p
e
ak
s
wer
e
id
en
tifie
d
,
f
r
o
m
wh
ich
1
5
f
ea
tu
r
es
wer
e
d
er
iv
ed
.
Su
b
s
eq
u
en
tly
,
s
tan
d
a
r
d
izatio
n
was
ap
p
lied
to
th
ese
f
ea
tu
r
es
to
en
s
u
r
e
u
n
if
o
r
m
s
ca
lin
g
,
en
h
an
cin
g
m
o
d
el
p
er
f
o
r
m
an
ce
b
y
allo
win
g
ea
ch
f
ea
tu
r
e
to
co
n
t
r
ib
u
te
eq
u
ally
.
Nex
t
s
tep
is
t
o
s
elec
t f
r
o
m
th
ese
f
ea
tu
r
es,
th
e
o
n
es th
at
ch
ar
ac
ter
ize
th
e
AF
,
th
is
s
tep
is
ca
lled
f
ea
tu
r
es sele
ctio
n
.
T
h
is
p
r
o
c
ess
h
as
b
ec
o
m
e
ess
en
tial
f
o
r
th
e
d
ev
elo
p
m
e
n
t
o
f
ef
f
icien
t
d
ata
m
in
in
g
a
n
d
ML
alg
o
r
ith
m
s
[
1
8
]
.
Af
ter
ex
tr
ac
tin
g
f
ea
tu
r
es
f
r
o
m
th
e
tr
ain
i
n
g
d
ata,
an
d
p
er
f
o
r
m
in
g
th
e
s
elec
tio
n
,
th
e
r
esu
ltin
g
f
ea
tu
r
e
s
et
(
s
am
e
f
o
r
b
o
th
d
atasets
)
is
co
n
ca
ten
ated
in
to
a
s
in
g
le
d
ataset
f
o
r
m
o
d
el
tr
ai
n
in
g
as
s
h
o
wn
in
Fig
u
r
e
2
.
T
h
is
ap
p
r
o
ac
h
aim
s
to
en
h
a
n
ce
th
e
m
o
d
el’
s
g
e
n
er
aliza
tio
n
ca
p
ab
ilit
ies.
Fig
u
r
e
1
.
Data
s
p
litt
in
g
Fig
u
r
e
2
.
Data
s
ets
co
n
ca
ten
ati
o
n
2
.
3
.
F
e
a
t
ures
ex
t
ra
c
t
io
n
I
n
th
e
c
o
n
tex
t
o
f
E
C
G
s
ig
n
als
,
f
ea
tu
r
e
e
x
tr
ac
tio
n
in
v
o
l
v
es
d
i
s
till
in
g
th
e
s
ig
n
al
in
to
a
s
et
o
f
clin
ically
r
elev
an
t
ch
ar
ac
ter
is
tics
th
at
ca
n
b
e
u
s
ed
f
o
r
v
ar
io
u
s
d
iag
n
o
s
tic
an
d
an
aly
tical
p
u
r
p
o
s
es.
Fo
r
th
e
ca
s
e
s
tu
d
y
,
we’
ll
f
o
cu
s
o
n
ex
tr
ac
tin
g
ea
c
h
o
f
th
e
P
-
wav
e,
R
-
p
ea
k
,
an
d
QR
S
co
m
p
lex
es
as
s
h
o
wn
i
n
Fig
u
r
e
3
,
an
d
th
ese
wav
ef
o
r
m
s
s
er
v
ed
as
th
e
f
o
u
n
d
atio
n
f
o
r
d
er
iv
i
n
g
th
e
f
ea
tu
r
e
s
u
s
ed
in
m
o
d
el
an
al
y
s
is
.
R
-
p
ea
k
s
wer
e
d
etec
ted
u
s
in
g
th
e
“
f
in
d
p
ea
k
s
”
f
u
n
ctio
n
f
r
o
m
th
e
SciPy
lib
r
ar
y
an
d
th
eir
n
u
m
b
er
ca
lcu
lated
.
A
m
i
n
im
u
m
d
is
tan
ce
o
f
5
0
s
am
p
les
b
etwe
en
d
etec
ted
p
ea
k
s
was
im
p
lem
en
ted
to
av
o
id
th
e
d
etec
tio
n
o
f
ad
jace
n
t
p
ea
k
s
.
T
h
is
f
u
n
ctio
n
r
etu
r
n
s
th
e
p
ea
k
h
eig
h
ts
,
f
r
o
m
wh
ich
th
e
m
ea
n
an
d
s
tan
d
ar
d
d
ev
iatio
n
wer
e
ca
lcu
lated
.
Nex
t
wo
u
ld
b
e
th
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
Meta
h
eu
r
is
tic
o
p
timiz
a
tio
n
fo
r
a
tr
ia
l fib
r
illa
tio
n
d
etec
tio
n
:
fe
a
tu
r
e
ex
tr
a
ctio
n
,
s
elec
tio
n
…
(
Za
id
N
o
u
n
a
)
3881
R
-
R
in
ter
v
als
ca
lcu
latio
n
in
t
h
e
E
C
G
s
ig
n
al,
f
r
o
m
wh
ich
th
e
m
ea
n
,
s
tan
d
ar
d
d
ev
iatio
n
,
r
o
o
t
m
ea
n
s
q
u
a
r
e
o
f
s
u
cc
ess
iv
e
d
if
f
er
en
ce
s
(
R
MSSD)
o
f
th
e
R
-
R
in
ter
v
als,
an
d
th
e
p
er
ce
n
tag
e
o
f
s
u
cc
ess
iv
e
R
-
R
in
ter
v
als
th
at
d
if
f
er
b
y
m
o
r
e
th
an
5
0
m
illi
s
e
co
n
d
s
wer
e
o
b
tain
ed
.
Fig
u
r
e
3
.
E
C
G
s
ig
n
al
P
-
p
ea
k
s
ar
e
d
etec
ted
u
s
in
g
t
h
e
s
am
e
f
u
n
ctio
n
,
i
n
a
0
.
1
s
win
d
o
w
b
e
f
o
r
e
R
-
p
ea
k
.
T
h
e
m
ea
n
a
n
d
s
tan
d
ar
d
d
ev
iatio
n
ar
e
d
ete
r
m
in
ed
f
o
r
ea
ch
o
f
th
e
P
-
wav
e
d
u
r
atio
n
a
n
d
P
-
wav
e
wid
t
h
,
in
ad
d
itio
n
t
o
th
e
P
-
wav
e
m
ea
n
ar
ea
.
Fo
r
th
e
QR
S
co
m
p
lex
,
th
is
s
tu
d
y
f
o
c
u
s
o
n
th
e
ch
ar
ac
ter
is
tic
QR
S
in
t
er
v
als
,
f
r
o
m
w
h
ich
th
e
m
ea
n
an
d
s
tan
d
ar
d
d
ev
iati
o
n
ar
e
e
x
tr
ac
ted
as f
ea
tu
r
es.
2
.
4
.
M
et
a
heuris
t
ics
T
h
r
ee
d
if
f
er
en
t
m
eta
h
eu
r
is
tics
ar
e
u
s
ed
d
u
r
in
g
th
is
s
tu
d
y
,
Fig
u
r
e
4
r
ep
r
esen
ts
th
e
g
en
e
r
al
p
r
o
ce
s
s
o
f
th
o
s
e
alg
o
r
ith
m
s
.
I
n
th
e
p
a
r
ticle
s
war
m
o
p
tim
izatio
n
(
PS
O)
alg
o
r
ith
m
,
p
ar
ticle
m
o
v
em
e
n
t
is
g
o
v
er
n
e
d
b
y
v
elo
city
u
p
d
ates,
wh
ich
ar
e
c
alcu
lated
b
ased
o
n
a
p
ar
ticle’
s
cu
r
r
en
t
s
p
ee
d
,
its
p
er
s
o
n
al
b
e
s
t
p
o
s
itio
n
,
an
d
th
e
s
war
m
’
s
g
lo
b
al
b
est
p
o
s
itio
n
.
T
h
is
d
y
n
am
ic
ad
ju
s
tm
en
t
en
ab
les
th
e
s
war
m
to
ef
f
ec
tiv
ely
b
alan
ce
ex
p
l
o
r
in
g
th
e
s
ea
r
ch
s
p
ac
e
a
n
d
ex
p
lo
it
in
g
p
r
o
m
is
in
g
ar
ea
s
[
1
9
]
.
Di
f
f
er
en
tial
e
v
o
lu
tio
n
(
DE
)
is
a
p
o
p
u
latio
n
-
b
ased
o
p
tim
izatio
n
alg
o
r
ith
m
in
tr
o
d
u
ce
d
b
y
Sto
r
n
an
d
Pric
e
[
2
0
]
,
th
at
g
en
er
ates
n
ew
ca
n
d
id
ate
s
o
lu
tio
n
s
b
y
co
m
b
in
in
g
ex
is
tin
g
o
n
es.
I
t
cr
ea
tes
’
m
u
tan
t’
v
ec
to
r
s
f
r
o
m
v
ec
to
r
d
if
f
er
en
ce
s
,
b
le
n
d
s
th
em
with
‘
tar
g
et’
v
ec
to
r
s
v
ia
cr
o
s
s
o
v
er
t
o
f
o
r
m
‘
tr
ial’
v
ec
to
r
s
,
an
d
s
elec
ts
th
e
f
ittes
t
f
o
r
th
e
n
ex
t
g
en
er
ati
o
n
.
T
h
e
g
r
ey
w
o
lf
o
p
tim
izatio
n
(
GW
O)
em
u
lates
th
e
h
ier
ar
ch
ical
h
u
n
tin
g
s
tr
ateg
y
o
f
g
r
ay
wo
lv
es,
u
tili
zin
g
alp
h
a,
b
eta,
an
d
d
elta
wo
lv
es
to
g
u
id
e
t
h
e
s
ea
r
ch
.
Om
eg
a
wo
lv
es
u
p
d
ate
th
ei
r
p
o
s
itio
n
s
b
ased
o
n
th
e
lead
e
r
s
,
s
im
u
latin
g
p
r
e
y
en
cir
clin
g
a
n
d
attac
k
in
g
b
eh
a
v
io
r
s
.
T
h
is
p
r
o
ce
s
s
b
ala
n
ce
s
ex
p
lo
r
atio
n
an
d
e
x
p
lo
itatio
n
,
en
ab
lin
g
ef
f
icien
t
n
av
ig
atio
n
o
f
co
m
p
lex
s
ea
r
ch
s
p
ac
es
b
y
iter
ativ
ely
ad
ju
s
tin
g
wo
lf
p
o
s
itio
n
s
to
war
d
s
p
r
o
m
is
in
g
r
eg
io
n
s
[
2
1
]
.
E
lectr
o
n
ic
cir
cu
it
d
esig
n
o
p
ti
m
izatio
n
[
2
2
]
–
[
2
5
]
,
m
etah
e
u
r
i
s
tic
-
o
p
tim
ized
ML
to
id
en
tify
s
ec
u
r
ity
b
r
ea
c
h
es
in
Hea
lth
ca
r
e
4
.
0
[
2
6
]
,
o
r
e
v
en
m
etah
eu
r
is
tic
alg
o
r
ith
m
s
th
at
cr
ea
te
o
p
tim
al
d
aily
s
ch
ed
u
l
es
f
o
r
h
o
m
e
h
ea
lth
ca
r
e
wo
r
k
er
s
b
y
f
ig
u
r
i
n
g
o
u
t
th
e
b
est
r
o
u
tes
a
n
d
tim
es
f
o
r
th
eir
p
atien
t
v
is
its
[
2
7
]
,
ar
e
a
f
ew
e
x
am
p
les
o
f
m
etah
eu
r
is
tic
u
s
e
ca
s
es in
th
e
liter
atu
r
e.
Fig
u
r
e
4
.
Gen
e
r
al
m
etah
eu
r
is
tic
o
p
tim
izatio
n
f
l
o
wch
ar
t
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2252
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
4
,
Au
g
u
s
t 2
0
2
6
:
3
8
7
8
-
3
8
8
7
3882
2
.
5
.
O
pti
m
iza
t
io
n
pro
ce
s
s
As
s
h
o
wn
in
Fig
u
r
e
5
,
th
is
s
tu
d
y
o
p
ted
f
o
r
s
im
u
ltan
eo
u
s
f
ea
tu
r
es
s
elec
tio
n
an
d
h
y
p
er
p
ar
am
eter
tu
n
i
n
g
s
in
ce
th
e
o
p
tim
al
s
et
o
f
f
ea
tu
r
es
o
f
ten
d
e
p
en
d
s
o
n
th
e
ch
o
s
en
h
y
p
er
p
ar
a
m
eter
s
,
an
d
v
ice
v
er
s
a.
B
y
o
p
tim
izin
g
th
ese
asp
ec
ts
co
n
cu
r
r
en
tly
,
th
e
p
o
ten
tial
f
o
r
i
d
en
tify
in
g
th
e
g
l
o
b
ally
o
p
ti
m
al
co
m
b
in
atio
n
is
en
h
an
ce
d
.
E
ac
h
in
d
iv
id
u
al
o
f
th
e
p
o
p
u
latio
n
is
d
iv
id
ed
in
t
o
a
f
ea
tu
r
e
s
elec
tio
n
p
ar
t
an
d
a
h
y
p
er
p
ar
am
ete
r
s
elec
tio
n
p
ar
t.
O
n
ce
th
e
f
ea
tu
r
es
an
d
t
h
e
h
y
p
er
p
ar
am
eter
s
ar
e
s
elec
ted
u
s
in
g
a
m
eta
h
eu
r
is
tic
alg
o
r
ith
m
,
th
e
n
eu
r
al
n
etwo
r
k
m
o
d
el
is
b
u
ilt
.
T
h
is
s
tu
d
y
em
p
lo
y
e
d
5
-
f
o
ld
cr
o
s
s
-
v
alid
atio
n
to
en
s
u
r
e
a
r
o
b
u
s
t
ev
alu
atio
n
o
f
th
e
m
o
d
el’
s
p
er
f
o
r
m
an
ce
a
n
d
to
m
itig
ate
th
e
r
is
k
o
f
o
v
er
f
itti
n
g
.
Fo
r
ea
ch
d
ataset,
th
e
av
er
ag
e
p
er
f
o
r
m
an
ce
is
ca
lcu
lated
to
en
ab
le
m
o
d
el
e
v
alu
atio
n
d
u
r
in
g
th
e
iter
atio
n
s
o
f
th
e
o
p
tim
izatio
n
p
r
o
ce
s
s
an
d
to
en
a
b
le
th
e
m
etah
eu
r
is
tics
to
ex
p
lo
r
e
th
e
s
o
lu
tio
n
s
s
p
ac
e
ef
f
ec
tiv
ely
.
T
o
b
alan
ce
p
er
f
o
r
m
an
ce
with
clin
ical
u
tili
ty
,
th
is
s
tu
d
y
ass
ig
n
ed
a
lo
wer
weig
h
t
to
f
ea
tu
r
e
r
ed
u
ctio
n
(
0
.
1
)
co
m
p
ar
e
d
to
ac
cu
r
ac
y
(
0
.
4
5
)
with
in
th
e
co
s
t
f
u
n
ctio
n
.
T
h
is
d
elib
er
ate
co
n
s
tr
ain
t
p
r
ev
en
ts
ag
g
r
ess
iv
e
f
ea
tu
r
e
r
ed
u
ctio
n
,
e
n
s
u
r
in
g
th
e
m
o
d
el
r
etai
n
s
a
r
esp
ec
tab
le
n
u
m
b
er
o
f
m
o
r
p
h
o
lo
g
ical
b
io
m
ar
k
er
s
ess
en
tial
f
o
r
in
ter
p
r
etab
ilit
y
.
B
y
a
v
o
id
in
g
an
o
v
er
ly
m
in
im
alis
t
f
ea
tu
r
e
s
et,
th
e
f
r
am
ewo
r
k
m
ain
tain
s
th
e
tr
an
s
p
a
r
en
cy
an
d
d
iv
er
s
ity
o
f
d
ata
n
e
ed
ed
to
g
en
e
r
alize
ef
f
ec
tiv
ely
ac
r
o
s
s
d
if
f
er
en
t p
atien
t
p
o
p
u
latio
n
s
with
o
u
t
s
ac
r
if
icin
g
cr
itical
d
iag
n
o
s
tic
d
etails.
T
h
e
ex
p
er
im
en
ts
ar
e
co
n
d
u
cted
o
n
a
s
y
s
tem
wi
th
an
ASUS
Prim
e
H6
1
0
M
-
K
m
o
th
er
b
o
ar
d
,
f
ea
tu
r
in
g
an
I
n
tel
1
2
th
Gen
C
o
r
e
i5
-
1
2
4
0
0
F
p
r
o
ce
s
s
o
r
(
6
c
o
r
es/1
2
th
r
ea
d
s
,
2
.
5
GHz
)
,
1
6
GB
DDR5
-
4
8
0
0
R
AM
,
a
n
d
W
in
d
o
ws
1
0
Pr
o
f
ess
io
n
al
64
-
b
it a
s
th
e
o
p
er
atin
g
s
y
s
tem
.
Fig
u
r
e
5
.
So
lu
tio
n
g
e
n
er
atio
n
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
3
.
1
.
E
x
perim
ent
a
l
s
et
up
W
h
ile
th
e
n
eu
r
al
n
etwo
r
k
’
s
o
p
tim
izer
,
n
u
m
b
er
o
f
ep
o
c
h
s
,
a
n
d
lo
s
s
f
u
n
ctio
n
ar
e
f
i
x
ed
at
Ad
am
,
2
0
,
an
d
b
in
ar
y
cr
o
s
s
-
en
tr
o
p
y
,
r
es
p
ec
tiv
ely
,
o
th
er
o
p
tim
ized
h
y
p
er
p
ar
am
eter
r
an
g
es
ar
e
ex
p
o
s
ed
in
T
ab
le
1
.
T
h
e
in
p
u
t
lay
er
is
s
et
as
th
e
n
u
m
b
er
o
f
f
ea
tu
r
es
s
in
ce
it
is
ch
an
g
in
g
th
r
o
u
g
h
iter
atio
n
s
,
an
d
th
e
o
u
tp
u
t
lay
er
is
a
o
n
e
n
eu
r
o
n
u
s
in
g
s
ig
m
o
id
ac
t
iv
atio
n
f
u
n
ctio
n
.
R
eg
ar
d
in
g
th
e
m
etah
eu
r
is
tic
alg
o
r
ith
m
s
,
T
ab
le
2
r
esu
m
es
th
e
p
ar
am
eter
v
alu
es,
a
n
d
GW
O
’
s
co
r
e
m
ec
h
an
is
m
au
to
m
ati
ca
lly
h
an
d
les
th
e
c
o
n
v
e
r
g
en
ce
f
ac
to
r
an
d
th
e
ca
lcu
latio
n
o
f
“A”
a
n
d
“C” v
e
cto
r
s
,
wh
ich
ar
e
c
r
u
cial
f
o
r
th
e
en
cir
clin
g
an
d
h
u
n
tin
g
b
eh
av
i
o
r
.
3
.
2
.
M
et
a
heuris
t
ic
s
o
lutio
ns
co
m
pa
riso
n
On
ce
all
p
ar
am
eter
s
ar
e
s
et
u
p
,
t
h
e
s
ea
r
ch
f
o
r
t
h
e
o
p
tim
al
s
o
lu
tio
n
s
tar
ts
.
T
ab
le
3
r
ep
r
esen
ts
co
m
p
u
tatio
n
tim
e
f
o
r
ea
ch
alg
o
r
ith
m
.
T
h
e
c
o
m
p
u
tatio
n
tim
e
is
g
en
er
ally
n
o
t
ch
a
n
g
i
n
g
m
u
c
h
b
etwe
e
n
p
r
o
g
r
a
m
r
u
n
s
,
wh
ich
s
h
o
ws th
at
b
o
th
GW
O
an
d
PS
O
h
av
e
b
ee
n
ab
o
u
t 3
tim
es f
aster
th
an
DE
.
T
ab
le
1
.
Hy
p
er
p
ar
a
m
eter
r
an
g
es a
n
d
ty
p
es
H
y
p
e
r
p
a
r
a
me
t
e
r
R
a
n
g
e
Ty
p
e
Le
a
r
n
i
n
g
r
a
t
e
(
1
e
-
4
,
1
e
-
1)
C
o
n
t
i
n
u
o
u
s
N
u
mb
e
r
o
f
l
a
y
e
r
s
(
2
,
5
)
I
n
t
e
g
e
r
N
u
mb
e
r
o
f
n
e
u
r
o
n
s
[
8
,
1
6
,
2
4
,
3
2
]
C
a
t
e
g
o
r
i
c
a
l
A
c
t
i
v
a
t
i
o
n
[
’
r
e
l
u
’
,
’
s
i
g
mo
i
d
’
,
’
t
a
n
h
’
]
C
a
t
e
g
o
r
i
c
a
l
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
Meta
h
eu
r
is
tic
o
p
timiz
a
tio
n
fo
r
a
tr
ia
l fib
r
illa
tio
n
d
etec
tio
n
:
fe
a
tu
r
e
ex
tr
a
ctio
n
,
s
elec
tio
n
…
(
Za
id
N
o
u
n
a
)
3883
T
ab
le
2
.
Me
tah
e
u
r
is
tics
p
ar
am
eter
s
A
l
g
o
r
i
t
h
m
P
a
r
a
me
t
e
r
V
a
l
u
e
G
e
n
e
r
a
l
p
a
r
a
me
t
e
r
s
N
u
mb
e
r
o
f
I
t
e
r
a
t
i
o
n
s
10
P
o
p
u
l
a
t
i
o
n
S
i
z
e
10
PSO
w
(
I
n
e
r
t
i
a
)
1
W
d
a
m
p
(
D
a
m
p
i
n
g
f
a
c
t
o
r
)
0
.
8
c
1
(
P
e
r
so
n
a
l
c
o
e
f
f
i
c
i
e
n
t
)
2
c
2
(
S
o
c
i
a
l
c
o
e
f
f
i
c
i
e
n
t
)
2
DE
C
R
(
C
r
o
ss
o
v
e
r
r
a
t
e
)
0
.
5
F
(
S
c
a
l
i
n
g
f
a
c
t
o
r
)
0
.
8
T
ab
le
3
.
C
o
m
p
u
tatio
n
tim
e
co
m
p
ar
is
o
n
A
l
g
o
r
i
t
h
m
G
W
O
PSO
DE
C
o
m
p
u
t
a
t
i
o
n
t
i
m
e
(
s)
6
2
9
.
7
7
1
1
7
1
0
.
6
2
7
8
2
0
1
7
.
6
1
3
4
T
h
e
co
n
v
er
g
en
ce
cu
r
v
es
o
f
th
e
th
r
ee
m
etah
eu
r
is
tic
al
g
o
r
ith
m
s
ar
e
illu
s
tr
ated
in
Fig
u
r
e
6
.
Nu
m
er
ically
,
PS
O
an
d
GW
O
ex
h
ib
it
s
u
p
e
r
io
r
co
n
v
er
g
en
ce
s
p
ee
d
,
r
ea
c
h
in
g
a
lo
wer
g
lo
b
a
l
m
in
im
u
m
with
in
th
e
f
ir
s
t
iter
atio
n
s
,
wh
ich
s
u
g
g
ests
h
ig
h
ef
f
icien
cy
in
m
i
n
im
izin
g
th
e
m
ath
em
atica
l
co
s
t
f
u
n
ctio
n
.
C
o
n
v
er
s
ely
,
DE
d
is
p
lay
s
a
s
lo
wer
d
escen
t.
W
h
ile
th
is
m
ig
h
t
in
itially
im
p
ly
lo
wer
o
p
tim
izatio
n
ef
f
icien
cy
,
it
s
u
g
g
ests
th
at
DE
av
o
id
s
p
r
em
at
u
r
e
co
n
v
er
g
en
ce
b
y
p
er
f
o
r
m
in
g
a
m
o
r
e
ex
h
au
s
tiv
e
ex
p
lo
r
atio
n
o
f
th
e
s
ea
r
ch
s
p
ac
e.
Fig
u
r
e
6
.
Glo
b
al
m
in
im
u
m
co
n
v
er
g
e
n
ce
PS
O
b
est
s
o
lu
tio
n
ac
c
u
r
ac
ies
h
av
e
ac
h
iev
e
d
9
5
.
1
8
%
an
d
8
8
.
6
6
%,
ar
ea
u
n
d
er
th
e
c
u
r
v
e
(
AUC)
o
f
0
.
9
9
a
n
d
0
.
9
4
,
f
o
r
d
ataset
s
1
an
d
2
s
u
cc
ess
iv
ely
,
u
s
in
g
6
f
e
atu
r
es.
GW
O
b
est
s
o
lu
tio
n
h
a
s
ac
h
iev
ed
9
5
.
1
8
%
an
d
8
7
.
5
%
ac
cu
r
ac
ies
with
an
AUC
o
f
0
.
9
8
an
d
0
.
9
3
,
u
s
in
g
5
f
ea
tu
r
es.
DE
b
est
s
o
lu
tio
n
h
as
ac
h
iev
ed
9
6
.
3
8
%
an
d
9
0
.
6
9
%
ac
c
u
r
ac
ies
with
an
AUC
o
f
0
.
9
9
an
d
0
.
9
6
,
f
o
r
d
atasets
1
an
d
2
s
u
cc
ess
iv
ely
,
u
s
in
g
1
0
f
ea
tu
r
es
,
d
em
o
n
s
tr
atin
g
t
h
e
b
est o
v
e
r
all
b
alan
ce
ac
r
o
s
s
all
p
er
f
o
r
m
a
n
c
e
in
d
icato
r
s
.
3
.
3
.
O
pti
m
a
l
m
o
del
T
h
e
1
0
s
elec
ted
f
ea
t
u
r
es
d
u
r
in
g
th
e
o
p
tim
izatio
n
p
r
o
c
ess
ar
e
d
etailed
in
T
ab
le
4
,
an
d
th
e
co
r
r
esp
o
n
d
in
g
m
o
d
el
is
a
n
eu
r
al
n
etwo
r
k
with
a
ten
-
n
o
d
e
in
p
u
t
lay
er
co
r
r
esp
o
n
d
in
g
to
th
e
n
u
m
b
er
o
f
f
ea
tu
r
es
an
d
a
s
in
g
le
-
n
e
u
r
o
n
o
u
tp
u
t
la
y
er
,
u
tili
zin
g
a
s
ig
m
o
id
ac
tiv
a
tio
n
f
u
n
ctio
n
,
wh
ich
was
im
p
lem
en
ted
to
p
r
o
d
u
ce
a
p
r
o
b
ab
ilit
y
s
co
r
e
f
o
r
b
in
ar
y
class
if
icatio
n
.
T
ab
le
5
s
h
o
ws
t
h
e
s
elec
ted
h
y
p
er
p
ar
a
m
eter
s
in
th
e
h
id
d
en
lay
er
s
u
s
in
g
DE
alg
o
r
ith
m
.
Fo
r
ea
c
h
lay
er
,
th
e
s
am
e
ac
tiv
atio
n
f
u
n
c
tio
n
is
u
s
ed
in
all
th
e
n
e
u
r
o
n
s
.
Usi
n
g
th
e
s
elec
ted
f
ea
tu
r
es
an
d
th
e
d
is
cu
s
s
ed
h
y
p
er
p
ar
am
et
er
s
,
th
e
n
eu
r
al
n
etwo
r
k
m
o
d
el
ac
h
iev
e
d
h
ig
h
p
er
f
o
r
m
an
ce
ac
r
o
s
s
b
o
t
h
ev
alu
ate
d
d
atasets
,
as
illu
s
tr
ated
in
th
e
co
n
f
u
s
io
n
m
at
r
ices
in
Fig
u
r
e
7
.
Sp
ec
if
ically
,
Fig
u
r
e
7
(
a
)
illu
s
t
r
ates
m
o
d
el’
s
p
er
f
o
r
m
an
ce
o
n
d
ataset
1
,
wh
ile
Fig
u
r
e
7
(
b
)
s
h
o
ws
p
er
f
o
r
m
a
n
ce
on
d
ataset
2
.
Alth
o
u
g
h
t
h
e
n
u
m
b
er
o
f
test
s
am
p
les
in
th
ese
s
u
b
s
ets
is
s
m
aller
co
m
p
ar
ed
t
o
th
e
to
tal
t
r
ain
in
g
p
o
o
l,
th
e
co
n
s
is
ten
cy
o
f
th
e
r
e
s
u
lts
ac
r
o
s
s
b
o
th
d
atasets
co
n
f
ir
m
s
th
e
m
o
d
el'
s
r
o
b
u
s
tn
ess
an
d
g
en
er
aliza
b
ilit
y
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2252
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
4
,
Au
g
u
s
t 2
0
2
6
:
3
8
7
8
-
3
8
8
7
3884
T
ab
le
4
.
DE
s
elec
ted
f
ea
tu
r
es
A
l
g
o
r
i
t
h
m
S
e
l
e
c
t
e
d
f
e
a
t
u
r
e
s
D
i
f
f
e
r
e
n
t
i
a
l
e
v
o
l
u
t
i
o
n
M
e
a
n
R
-
R
i
n
t
e
r
v
a
l
s
R
-
R
s
t
a
n
d
a
r
d
d
e
v
i
a
t
i
o
n
R
M
S
S
D
O
F
R
-
R
i
n
t
e
r
v
a
l
s
P
e
r
c
e
n
t
a
g
e
o
f
su
c
c
e
ssi
v
e
R
-
R
i
n
t
e
r
v
a
l
s t
h
a
t
d
i
f
f
e
r
b
y
mo
r
e
t
h
a
n
5
0
ms
R
me
a
n
h
e
i
g
h
t
R
h
e
i
g
h
t
st
a
n
d
a
r
d
d
e
v
i
a
t
i
o
n
P
w
a
v
e
d
u
r
a
t
i
o
n
s
t
a
n
d
a
r
d
d
e
v
i
a
t
i
o
n
P
-
w
a
v
e
me
a
n
a
r
e
a
P
w
a
v
e
w
i
d
t
h
s
t
a
n
d
a
r
d
d
e
v
i
a
t
i
o
n
Q
R
S
me
a
n
i
n
t
e
r
v
a
l
T
ab
le
5
.
Hy
p
er
p
ar
a
m
eter
v
alu
es
H
y
p
e
r
p
a
r
a
me
t
e
r
s
V
a
l
u
e
s
Le
a
r
n
i
n
g
r
a
t
e
0
.
0
1
7
4
N
u
mb
e
r
o
f
h
i
d
d
e
n
l
a
y
e
r
s
3
N
u
mb
e
r
s
o
f
n
e
u
r
o
n
s
[
3
2
,
2
4
,
1
6
]
A
c
t
i
v
a
t
i
o
n
f
u
n
c
t
i
o
n
[
’
t
a
n
h
’
,
’
t
a
n
h
’
,
’
si
g
m
o
i
d
’
]
(
a)
(
b
)
Fig
u
r
e
7
.
C
o
n
f
u
s
io
n
m
atr
ices
of
(
a)
d
ataset
1
an
d
(
b
)
d
ataset
2
T
o
p
r
o
v
id
e
a
c
o
n
cise
o
v
er
v
ie
w
o
f
t
h
e
m
o
d
els'
o
v
er
all
p
e
r
f
o
r
m
an
ce
,
T
ab
le
6
p
r
esen
ts
th
e
ac
cu
r
ac
y
,
F1
-
s
co
r
e,
p
r
ec
is
io
n
,
an
d
r
ec
all
f
o
r
ea
ch
class
,
wh
ile
F
ig
u
r
e
8
d
is
p
lay
s
th
e
R
OC
cu
r
v
es
ev
alu
atin
g
class
if
icatio
n
p
er
f
o
r
m
a
n
ce
.
Sp
ec
if
ically
,
Fig
u
r
e
s
8
(
a)
an
d
8
(
b
)
p
r
esen
t
th
e
R
OC
cu
r
v
es
f
o
r
d
ataset
1
an
d
d
ataset
2
,
r
esp
ec
tiv
ely
.
T
h
e
m
o
d
el
d
em
o
n
s
tr
ates
h
ig
h
d
iag
n
o
s
tic
ef
f
icac
y
,
with
a
co
n
s
is
ten
t
AF
p
r
ec
is
io
n
o
f
9
0
to
9
2
% a
n
d
h
ig
h
F1
-
s
co
r
es
(
u
p
to
9
7
%),
en
s
u
r
in
g
r
eliab
le
class
if
icatio
n
with
f
ew
f
alse a
l
ar
m
s
.
I
n
d
ataset
1
,
th
e
s
y
s
tem
ac
h
iev
ed
a
p
er
f
e
ct
1
0
0
%
r
ec
all
f
o
r
AF,
th
o
u
g
h
th
is
s
en
s
itiv
ity
s
lig
h
tly
d
ec
r
ea
s
ed
to
8
7
%
in
d
ataset
2
.
T
h
ese
m
etr
ics
ar
e
f
u
r
th
er
s
u
p
p
o
r
te
d
b
y
th
e
r
ap
id
r
is
e
o
f
b
o
th
R
OC
cu
r
v
es
to
war
d
th
e
u
p
p
er
-
lef
t
co
o
r
d
in
ate,
r
ef
lectin
g
h
ig
h
d
is
cr
im
in
ativ
e
p
o
wer
,
m
ax
im
izin
g
s
en
s
itiv
ity
wh
ile
m
in
im
izin
g
f
alse p
o
s
itiv
es.
T
ab
le
6
.
Per
f
o
r
m
an
ce
o
f
th
e
m
o
d
el
D
a
t
a
s
e
t
A
c
c
u
r
a
c
y
(
%)
P
r
e
c
i
s
i
o
n
(
%)
R
e
c
a
l
l
(
%)
F1
-
sc
o
r
e
(
%)
N
o
r
mal
AF
N
o
r
mal
AF
N
o
r
mal
AF
D
a
t
a
s
e
t
1
9
6
.
3
8
1
0
0
90
95
1
0
0
97
95
D
a
t
a
s
e
t
2
9
0
.
6
9
90
92
94
87
92
89
T
ab
les
7
a
n
d
8
,
ad
a
p
ted
f
r
o
m
[
1
3
]
,
p
r
esen
t
a
c
o
m
p
ar
ati
v
e
an
aly
s
is
o
f
AF
d
etec
tio
n
m
o
d
els
o
n
d
atasets
1
an
d
2
,
r
esp
ec
tiv
el
y
.
T
h
is
s
tu
d
y
h
as
ex
ten
d
ed
th
ese
tab
les
to
in
clu
d
e
th
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
p
r
o
p
o
s
ed
m
o
d
el.
As
s
h
o
w
n
,
th
e
m
o
d
el
ac
h
iev
es
a
n
ac
cu
r
ac
y
o
f
9
6
.
3
8
%
o
n
d
ataset
1
an
d
9
0
.
6
9
%
o
n
d
ataset
2
,
o
u
tp
er
f
o
r
m
in
g
th
e
o
th
er
m
o
d
els.
T
h
e
s
u
p
er
io
r
p
er
f
o
r
m
an
c
e
o
f
th
e
p
r
o
p
o
s
ed
m
o
d
el
is
p
r
im
ar
ily
d
u
e
to
th
e
elim
in
atio
n
o
f
m
an
u
al
o
r
s
ta
n
d
ar
d
h
y
p
er
p
ar
am
eter
tu
n
i
n
g
an
d
f
ix
ed
f
ea
tu
r
e
s
ets,
a
co
m
m
o
n
lim
itatio
n
in
ex
is
tin
g
s
tu
d
ies.
I
n
s
tead
o
f
r
e
ly
in
g
o
n
h
u
m
an
-
b
iased
s
elec
tio
n
,
th
is
s
tu
d
y
u
tili
ze
d
DE
to
p
er
f
o
r
m
a
g
lo
b
al
s
ea
r
ch
f
o
r
a
u
n
if
ied
o
p
tim
al
c
o
n
f
ig
u
r
atio
n
o
f
b
o
th
f
ea
tu
r
es a
n
d
h
y
p
e
r
p
ar
am
eter
s
.
B
y
id
en
tif
y
in
g
a
s
in
g
le
s
et
o
f
p
ar
am
eter
s
th
at
r
em
ain
s
h
ig
h
ly
ef
f
ec
tiv
e
ac
r
o
s
s
two
in
d
ep
en
d
en
t
d
atasets
,
th
is
s
tu
d
y
d
em
o
n
s
tr
ate
th
at
th
e
m
o
d
el
ca
p
tu
r
es
f
u
n
d
a
m
en
tal
p
h
y
s
io
lo
g
ical
m
ar
k
er
s
o
f
AF
r
ath
er
th
an
d
ataset
-
s
p
ec
if
ic
n
o
is
e.
T
h
is
d
u
al
-
o
p
tim
izatio
n
ap
p
r
o
ac
h
e
n
s
u
r
es a
m
o
r
e
o
b
jectiv
e,
r
o
b
u
s
t,
an
d
g
e
n
er
aliza
b
le
d
ia
g
n
o
s
tic
to
o
l.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
Meta
h
eu
r
is
tic
o
p
timiz
a
tio
n
fo
r
a
tr
ia
l fib
r
illa
tio
n
d
etec
tio
n
:
fe
a
tu
r
e
ex
tr
a
ctio
n
,
s
elec
tio
n
…
(
Za
id
N
o
u
n
a
)
3885
(
a)
(
b
)
Fig
u
r
e
8
.
R
OC
’
s
of
(
a)
d
ataset
1
an
d
(
b
)
d
ataset
T
ab
le
7
.
Mo
d
el
co
m
p
ar
is
o
n
(
d
ataset
1
)
M
o
d
e
l
Y
e
a
r
A
c
c
u
r
a
c
y
(
%)
D
e
e
p
A
N
N
[
2
8
]
2
0
2
0
9
3
.
0
0
F
e
e
d
f
o
r
w
a
r
d
N
N
[
2
9
]
2
0
2
2
8
4
.
0
0
11
-
l
a
y
e
r
C
N
N
[
3
0
]
2
0
1
7
9
4
.
9
0
24
-
F
e
a
t
u
r
e
s
A
N
N
[
1
3
]
2
0
2
3
9
6
.
0
0
P
r
o
p
o
se
d
m
o
d
e
l
2
0
2
5
9
6
.
3
8
T
ab
le
8
.
Mo
d
el
co
m
p
ar
is
o
n
(
d
ataset
2
)
M
o
d
e
l
Y
e
a
r
A
c
c
u
r
a
c
y
(
%)
1
6
l
a
y
e
r
1
-
D
C
N
N
[
3
1
]
2
0
1
7
8
2
.
0
0
LSTM
[
3
2
]
2
0
2
0
7
8
.
3
5
D
C
N
N
[
3
3
]
2
0
1
8
7
1
.
0
0
24
-
F
e
a
t
u
r
e
s
A
N
N
[
1
3
]
2
0
2
3
8
6
.
0
0
P
r
o
p
o
se
d
m
o
d
e
l
2
0
2
5
9
0
.
6
9
4.
CO
NCLU
SI
O
N
T
h
e
m
ain
o
b
jectiv
e
o
f
th
is
s
tu
d
y
is
to
en
h
an
ce
AF
d
etec
tio
n
b
ased
o
n
E
C
G
r
ec
o
r
d
in
g
s
,
b
y
d
ev
elo
p
in
g
a
n
o
v
el
d
etec
tio
n
m
o
d
el
tr
ain
ed
o
n
a
co
n
ca
ten
at
ed
d
ataset,
a
n
d
e
v
alu
ated
o
n
h
o
ld
o
u
t,
r
a
n
d
o
m
a
n
d
s
tr
atif
ied
test
s
et
s
.
T
h
e
o
p
ti
m
izatio
n
p
r
o
ce
s
s
h
as
b
ee
n
co
n
d
u
cte
d
u
s
in
g
t
h
r
ee
d
if
f
e
r
en
t
m
etah
eu
r
is
tic
alg
o
r
ith
m
s
,
PS
O,
GW
O
an
d
DE
,
th
at
h
av
e
b
ee
n
co
m
p
ar
e
d
in
ter
m
s
o
f
s
o
lu
tio
n
q
u
ality
an
d
co
m
p
u
tatio
n
tim
e.
T
h
e
f
in
al
s
elec
ted
m
o
d
el
d
e
m
o
n
s
tr
ated
in
te
r
esti
n
g
p
e
r
f
o
r
m
an
ce
s
,
ac
h
iev
i
n
g
ac
cu
r
ac
ie
s
o
f
9
6
.
3
8
%
an
d
9
0
.
6
9
%,
AUC
s
co
r
es
o
f
0
.
9
9
an
d
0
.
9
6
,
o
n
b
o
th
d
atasets
,
s
u
r
p
ass
in
g
th
e
r
esu
lts
r
ep
o
r
ted
i
n
p
r
ev
i
o
u
s
s
tu
d
ies.
T
h
is
im
p
r
o
v
e
m
en
t
h
ig
h
lig
h
ts
th
e
ef
f
ec
tiv
en
ess
o
f
th
e
f
ea
tu
r
e
ex
tr
ac
tio
n
an
d
o
p
tim
izatio
n
m
eth
o
d
o
l
o
g
y
.
T
h
e
s
u
cc
ess
f
u
l
ap
p
licatio
n
o
f
m
et
ah
eu
r
is
tic
o
p
tim
izatio
n
u
n
d
er
s
co
r
es
its
p
o
ten
tial
to
en
h
an
ce
th
e
ac
cu
r
ac
y
an
d
r
eliab
ilit
y
o
f
AF
d
etec
tio
n
s
y
s
tem
s
.
A
p
r
o
m
is
in
g
d
ir
ec
tio
n
f
o
r
f
u
tu
r
e
r
esear
ch
is
t
o
e
x
p
lo
r
e
th
e
m
o
d
el’
s
r
o
b
u
s
tn
ess
to
n
o
is
e
an
d
ar
tifa
cts
in
E
C
G
r
ec
o
r
d
in
g
s
,
as
we
ll
as
its
p
er
f
o
r
m
an
ce
o
n
lar
g
e
r
an
d
m
o
r
e
d
iv
er
s
e
d
atasets
.
T
h
is
wo
r
k
co
n
tr
ib
u
te
s
v
alu
ab
le
in
s
ig
h
ts
to
war
d
s
th
e
d
ev
elo
p
m
en
t
o
f
m
o
r
e
p
r
ec
is
e
an
d
ef
f
icien
t
AF
d
etec
tio
n
tech
n
o
lo
g
ies.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
Au
th
o
r
s
s
tate
n
o
f
u
n
d
in
g
in
v
o
lv
ed
.
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
T
h
is
jo
u
r
n
al
u
s
es
th
e
C
o
n
tr
ib
u
to
r
R
o
les
T
ax
o
n
o
m
y
(
C
R
ed
iT)
to
r
ec
o
g
n
ize
in
d
iv
id
u
al
au
th
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
th
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
llab
o
r
atio
n
.
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
Z
aid
No
u
n
a
✓
✓
✓
✓
✓
✓
✓
✓
✓
Ham
id
B
o
u
y
g
h
f
✓
✓
✓
✓
✓
✓
✓
Mo
h
am
m
ed
Na
h
id
✓
✓
✓
✓
✓
✓
✓
I
s
s
a
Sab
ir
i
✓
✓
✓
✓
✓
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2252
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
4
,
Au
g
u
s
t 2
0
2
6
:
3
8
7
8
-
3
8
8
7
3886
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
Au
th
o
r
s
s
tate
n
o
co
n
f
lict o
f
in
t
er
est.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
ad
ap
ted
d
ata
th
at
s
u
p
p
o
r
t
th
e
f
in
d
in
g
s
o
f
th
is
s
tu
d
y
a
r
e
a
v
ailab
le
v
ia
th
e
o
r
ig
in
al
s
o
u
r
c
e
lin
k
r
ef
er
en
ce
d
in
th
e
m
ai
n
tex
t
.
RE
F
E
R
E
NC
E
S
[
1
]
P
.
K
i
r
c
h
h
o
f
e
t
a
l
.
,
“
2
0
1
6
ES
C
g
u
i
d
e
l
i
n
e
s
f
o
r
t
h
e
ma
n
a
g
e
me
n
t
o
f
a
t
r
i
a
l
f
i
b
r
i
l
l
a
t
i
o
n
d
e
v
e
l
o
p
e
d
i
n
c
o
l
l
a
b
o
r
a
t
i
o
n
w
i
t
h
EA
C
TS,
”
Eu
r
o
p
e
a
n
H
e
a
r
t
J
o
u
r
n
a
l
,
v
o
l
.
3
7
,
n
o
.
3
8
,
p
p
.
2
8
9
3
–
2
9
6
2
,
2
0
1
6
,
d
o
i
:
1
0
.
1
0
9
3
/
e
u
r
h
e
a
r
t
j
/
e
h
w
2
1
0
.
[
2
]
T.
H
y
g
r
e
l
l
e
t
a
l
.
,
“
A
n
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
–
b
a
s
e
d
m
o
d
e
l
f
o
r
p
r
e
d
i
c
t
i
o
n
o
f
a
t
r
i
a
l
f
i
b
r
i
l
l
a
t
i
o
n
f
r
o
m
s
i
n
g
l
e
-
l
e
a
d
s
i
n
u
s
r
h
y
t
h
m
e
l
e
c
t
r
o
c
a
r
d
i
o
g
r
a
ms f
a
c
i
l
i
t
a
t
i
n
g
scr
e
e
n
i
n
g
,
”
Eu
r
o
p
a
c
e
,
v
o
l
.
2
5
,
n
o
.
4
,
p
p
.
1
3
3
2
–
1
3
3
8
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
9
3
/
e
u
r
o
p
a
c
e
/
e
u
a
d
0
3
6
.
[
3
]
B
.
Ji
a
,
J.
C
h
e
n
,
Y
.
L
u
a
n
,
H
.
W
a
n
g
,
Y
.
W
e
i
,
a
n
d
Y
.
H
u
,
“
A
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
a
n
d
a
t
r
i
a
l
f
i
b
r
i
l
l
a
t
i
o
n
:
a
b
i
b
l
i
o
m
e
t
r
i
c
a
n
a
l
y
s
i
s
f
r
o
m
2
0
1
3
t
o
2
0
2
3
,
”
H
e
l
i
y
o
n
,
v
o
l
.
1
0
,
n
o
.
1
5
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
h
e
l
i
y
o
n
.
2
0
2
4
.
e
3
5
0
6
7
.
[
4
]
Z.
I
.
A
t
t
i
a
e
t
a
l
.
,
“
A
n
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
-
e
n
a
b
l
e
d
E
C
G
a
l
g
o
r
i
t
h
m
f
o
r
t
h
e
i
d
e
n
t
i
f
i
c
a
t
i
o
n
o
f
p
a
t
i
e
n
t
s
w
i
t
h
a
t
r
i
a
l
f
i
b
r
i
l
l
a
t
i
o
n
d
u
r
i
n
g
si
n
u
s
r
h
y
t
h
m:
a
r
e
t
r
o
s
p
e
c
t
i
v
e
a
n
a
l
y
si
s
o
f
o
u
t
c
o
me
p
r
e
d
i
c
t
i
o
n
,
”
T
h
e
L
a
n
c
e
t
,
v
o
l
.
3
9
4
,
n
o
.
1
0
2
0
1
,
p
p
.
8
6
1
–
8
6
7
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
S
0
1
4
0
-
6
7
3
6
(
1
9
)
3
1
7
2
1
-
0.
[
5
]
T.
A
n
b
a
l
a
g
a
n
,
M
.
K
.
N
a
t
h
,
D
.
V
i
j
a
y
a
l
a
k
sh
m
i
,
a
n
d
A
.
A
n
b
a
l
a
g
a
n
,
“
A
n
a
l
y
si
s
o
f
v
a
r
i
o
u
s
t
e
c
h
n
i
q
u
e
s
f
o
r
EC
G
si
g
n
a
l
i
n
h
e
a
l
t
h
c
a
r
e
,
p
a
s
t
,
p
r
e
s
e
n
t
,
a
n
d
f
u
t
u
r
e
,
”
Bi
o
m
e
d
i
c
a
l
En
g
i
n
e
e
ri
n
g
A
d
v
a
n
c
e
s
,
v
o
l
.
6
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
b
e
a
.
2
0
2
3
.
1
0
0
0
8
9
.
[
6
]
A
.
Y
.
H
a
n
n
u
n
e
t
a
l
.
,
“
C
a
r
d
i
o
l
o
g
i
s
t
-
l
e
v
e
l
a
r
r
h
y
t
h
mi
a
d
e
t
e
c
t
i
o
n
a
n
d
c
l
a
ssi
f
i
c
a
t
i
o
n
i
n
a
m
b
u
l
a
t
o
r
y
e
l
e
c
t
r
o
c
a
r
d
i
o
g
r
a
ms
u
si
n
g
a
d
e
e
p
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
N
a
t
u
re
Me
d
i
c
i
n
e
,
v
o
l
.
2
5
,
n
o
.
1
,
p
p
.
6
5
–
6
9
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
3
8
/
s4
1
5
9
1
-
018
-
0
2
6
8
-
3.
[
7
]
A
.
A
z
z
o
u
z
e
t
a
l
.
,
“
A
n
e
f
f
i
c
i
e
n
t
E
C
G
si
g
n
a
l
s
d
e
n
o
i
s
i
n
g
t
e
c
h
n
i
q
u
e
b
a
se
d
o
n
t
h
e
c
o
m
b
i
n
a
t
i
o
n
o
f
p
a
r
t
i
c
l
e
sw
a
r
m
o
p
t
i
m
i
sa
t
i
o
n
a
n
d
w
a
v
e
l
e
t
t
r
a
n
sf
o
r
m,
”
H
e
l
i
y
o
n
,
v
o
l
.
1
0
,
n
o
.
5
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
h
e
l
i
y
o
n
.
2
0
2
4
.
e
2
6
1
7
1
.
[
8
]
C
.
T.
Ja
n
u
a
r
y
e
t
a
l
.
,
“
2
0
1
4
A
H
A
/
A
C
C
/
H
R
S
g
u
i
d
e
l
i
n
e
f
o
r
t
h
e
m
a
n
a
g
e
m
e
n
t
o
f
p
a
t
i
e
n
t
s
w
i
t
h
a
t
r
i
a
l
f
i
b
r
i
l
l
a
t
i
o
n
:
a
r
e
p
o
r
t
o
f
t
h
e
A
meric
a
n
C
o
l
l
e
g
e
o
f
C
a
r
d
i
o
l
o
g
y
/
A
m
e
r
i
c
a
n
H
e
a
r
t
A
ss
o
c
i
a
t
i
o
n
t
a
s
k
f
o
r
c
e
o
n
p
r
a
c
t
i
c
e
g
u
i
d
e
l
i
n
e
s
a
n
d
t
h
e
h
e
a
r
t
r
h
y
t
h
m
s
o
c
i
e
t
y
,
”
J
o
u
rn
a
l
o
f
t
h
e
Am
e
ri
c
a
n
C
o
l
l
e
g
e
o
f
C
a
rd
i
o
l
o
g
y
,
v
o
l
.
6
4
,
n
o
.
2
1
,
p
p
.
e
1
–
e
7
6
,
2
0
1
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
a
c
c
.
2
0
1
4
.
0
3
.
0
2
2
.
[
9
]
A
.
A
.
L
a
g
h
a
r
i
,
Y
.
S
u
n
,
M
.
A
l
h
u
s
s
e
i
n
,
K
.
A
u
r
a
n
g
z
e
b
,
M
.
S
.
A
n
w
a
r
,
a
n
d
M
.
R
a
s
h
i
d
,
“
D
e
e
p
r
e
s
i
d
u
a
l
-
d
e
n
s
e
n
e
t
w
o
r
k
b
a
s
e
d
o
n
b
i
d
i
r
e
c
t
i
o
n
a
l
r
e
c
u
r
r
e
n
t
n
e
u
r
a
l
n
e
t
w
o
r
k
f
o
r
a
t
r
i
a
l
f
i
b
r
i
l
l
a
t
i
o
n
d
e
t
e
c
t
i
o
n
,
”
S
c
i
e
n
t
i
f
i
c
R
e
p
o
r
t
s
,
v
o
l
.
1
3
,
n
o
.
1
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
5
9
8
-
023
-
4
0
3
4
3
-
x.
[
1
0
]
A
.
B
.
R
a
d
e
t
a
l
.
,
“
A
c
r
o
w
d
so
u
r
c
e
d
A
I
f
r
a
mew
o
r
k
f
o
r
a
t
r
i
a
l
f
i
b
r
i
l
l
a
t
i
o
n
d
e
t
e
c
t
i
o
n
i
n
A
p
p
l
e
W
a
t
c
h
a
n
d
K
a
r
d
i
a
M
o
b
i
l
e
E
C
G
s,”
S
e
n
so
rs
,
v
o
l
.
2
4
,
n
o
.
1
7
,
2
0
2
4
,
d
o
i
:
1
0
.
3
3
9
0
/
s2
4
1
7
5
7
0
8
.
[
1
1
]
X
.
Zh
a
o
,
R
.
Z
h
o
u
,
L.
N
i
n
g
,
Q
.
G
u
o
,
Y
.
Li
a
n
g
,
a
n
d
J
.
Y
a
n
g
,
“
A
t
r
i
a
l
f
i
b
r
i
l
l
a
t
i
o
n
d
e
t
e
c
t
i
o
n
w
i
t
h
si
n
g
l
e
-
l
e
a
d
e
l
e
c
t
r
o
c
a
r
d
i
o
g
r
a
m b
a
s
e
d
o
n
t
e
mp
o
r
a
l
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
t
w
o
r
k
–
R
e
sN
e
t
,
”
S
e
n
s
o
rs
,
v
o
l
.
2
4
,
n
o
.
2
,
2
0
2
4
,
d
o
i
:
1
0
.
3
3
9
0
/
s
2
4
0
2
0
3
9
8
.
[
1
2
]
M
.
S
.
Ja
h
a
n
,
M
.
M
a
n
s
o
u
r
v
a
r
,
S
.
P
u
t
h
u
ss
e
r
y
p
a
d
y
,
U
.
K
.
W
i
i
l
,
a
n
d
A
.
P
e
i
man
k
a
r
,
“
S
h
o
r
t
-
t
e
r
m
a
t
r
i
a
l
f
i
b
r
i
l
l
a
t
i
o
n
d
e
t
e
c
t
i
o
n
u
s
i
n
g
e
l
e
c
t
r
o
c
a
r
d
i
o
g
r
a
ms
:
a
c
o
m
p
a
r
i
s
o
n
o
f
mac
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
e
s,”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
M
e
d
i
c
a
l
I
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
1
6
3
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
j
m
e
d
i
n
f
.
2
0
2
2
.
1
0
4
7
9
0
.
[
1
3
]
D
.
U
.
S
.
D
u
r
a
n
t
a
e
t
a
l
.
,
“
E
n
h
a
n
c
i
n
g
a
t
r
i
a
l
f
i
b
r
i
l
l
a
t
i
o
n
d
e
t
e
c
t
i
o
n
a
c
c
u
r
a
c
y
:
a
w
a
v
e
l
e
t
t
r
a
n
sf
o
r
m
f
i
l
t
e
r
e
d
si
n
g
l
e
l
e
a
d
E
C
G
si
g
n
a
l
a
n
a
l
y
si
s
w
i
t
h
a
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s
a
n
d
n
o
v
e
l
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
,
”
Ma
c
h
i
n
e
L
e
a
r
n
i
n
g
w
i
t
h
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
2
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
m
l
w
a
.
2
0
2
3
.
1
0
0
4
7
2
.
[
1
4
]
Z.
O
.
H
a
m
a
d
,
“
R
e
v
i
e
w
o
f
f
e
a
t
u
r
e
se
l
e
c
t
i
o
n
m
e
t
h
o
d
s
u
s
i
n
g
o
p
t
i
m
i
z
a
t
i
o
n
a
l
g
o
r
i
t
h
m
(
r
e
v
i
e
w
p
a
p
e
r
f
o
r
o
p
t
i
mi
z
a
t
i
o
n
a
l
g
o
r
i
t
h
m)
,
”
Po
l
y
t
e
c
h
n
i
c
J
o
u
r
n
a
l
,
v
o
l
.
1
2
,
n
o
.
2
,
p
p
.
2
0
3
–
2
1
4
,
2
0
2
2
,
d
o
i
:
1
0
.
2
5
1
5
6
/
p
t
j
.
v
1
2
n
2
y
2
0
2
2
.
p
p
2
0
3
-
2
1
4
.
[
1
5
]
P
.
P
ł
a
w
i
a
k
,
“
N
o
v
e
l
me
t
h
o
d
o
l
o
g
y
o
f
c
a
r
d
i
a
c
h
e
a
l
t
h
r
e
c
o
g
n
i
t
i
o
n
b
a
se
d
o
n
EC
G
si
g
n
a
l
s
a
n
d
e
v
o
l
u
t
i
o
n
a
r
y
-
n
e
u
r
a
l
sy
st
e
m,
”
E
x
p
e
rt
S
y
s
t
e
m
s
w
i
t
h
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
9
2
,
p
p
.
3
3
4
-
3
4
9
,
2
0
1
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
sw
a
.
2
0
1
7
.
0
9
.
0
2
2
.
[
1
6
]
G
.
C
l
i
f
f
o
r
d
e
t
a
l
.
,
“
A
F
c
l
a
ssi
f
i
c
a
t
i
o
n
f
r
o
m
a
s
h
o
r
t
si
n
g
l
e
l
e
a
d
EC
G
r
e
c
o
r
d
i
n
g
:
t
h
e
P
h
y
si
o
n
e
t
c
o
mp
u
t
i
n
g
i
n
c
a
r
d
i
o
l
o
g
y
c
h
a
l
l
e
n
g
e
2
0
1
7
,
”
2
0
1
7
C
o
m
p
u
t
i
n
g
i
n
C
a
r
d
i
o
l
o
g
y
(
C
i
n
C
)
,
R
e
n
n
e
s,
F
r
a
n
c
e
,
2
0
1
7
,
p
p
.
1
-
4
,
d
o
i
:
1
0
.
2
2
4
8
9
/
C
i
n
C
.
2
0
1
7
.
0
6
5
-
4
6
9
.
[
1
7
]
A
.
F
.
H
u
ss
e
i
n
,
W
.
R
.
M
o
h
a
mm
e
d
,
M
.
M
u
sa
Ja
b
e
r
,
a
n
d
O
.
I
.
K
h
a
l
a
f
,
“
A
n
a
d
a
p
t
i
v
e
E
C
G
n
o
i
se
r
e
mo
v
a
l
p
r
o
c
e
ss b
a
sed
o
n
e
m
p
i
r
i
c
a
l
mo
d
e
d
e
c
o
m
p
o
si
t
i
o
n
(
E
M
D
)
,
”
C
o
n
t
r
a
st
M
e
d
i
a
a
n
d
Mo
l
e
c
u
l
a
r
I
m
a
g
i
n
g
,
v
o
l
.
2
0
2
2
,
n
o
.
1
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
2
/
3
3
4
6
0
5
5
.
[1
8
]
T.
D
o
k
e
r
o
g
l
u
,
A
.
D
e
n
i
z
,
a
n
d
H
.
E.
K
i
z
i
l
o
z
,
“
A
c
o
m
p
r
e
h
e
n
si
v
e
s
u
r
v
e
y
o
n
r
e
c
e
n
t
met
a
h
e
u
r
i
st
i
c
s
f
o
r
f
e
a
t
u
r
e
sel
e
c
t
i
o
n
,
”
N
e
u
ro
c
o
m
p
u
t
i
n
g
,
v
o
l
.
4
9
4
,
p
p
.
2
6
9
–
2
9
6
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
n
e
u
c
o
m
.
2
0
2
2
.
0
4
.
0
8
3
.
[1
9
]
A
.
G
.
G
a
d
,
“
P
a
r
t
i
c
l
e
sw
a
r
m
o
p
t
i
mi
z
a
t
i
o
n
a
l
g
o
r
i
t
h
m
a
n
d
i
t
s
a
p
p
l
i
c
a
t
i
o
n
s:
a
sy
st
e
ma
t
i
c
r
e
v
i
e
w
,
”
Ar
c
h
i
v
e
s
o
f
C
o
m
p
u
t
a
t
i
o
n
a
l
Me
t
h
o
d
s
i
n
En
g
i
n
e
e
r
i
n
g
,
v
o
l
.
2
9
,
n
o
.
5
,
p
p
.
2
5
3
1
–
2
5
6
1
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
8
3
1
-
0
2
1
-
0
9
6
9
4
-
4.
[
20
]
R
.
S
t
o
r
n
a
n
d
K
.
P
r
i
c
e
,
“
D
i
f
f
e
r
e
n
t
i
a
l
e
v
o
l
u
t
i
o
n
-
a
s
i
m
p
l
e
a
n
d
e
f
f
i
c
i
e
n
t
h
e
u
r
i
st
i
c
f
o
r
g
l
o
b
a
l
o
p
t
i
m
i
z
a
t
i
o
n
o
v
e
r
c
o
n
t
i
n
u
o
u
s
sp
a
c
e
s
,
”
J
o
u
rn
a
l
o
f
G
l
o
b
a
l
O
p
t
i
m
i
z
a
t
i
o
n
,
v
o
l
.
1
1
,
n
o
.
4
,
p
p
.
3
4
1
–
3
5
9
,
1
9
9
7
,
d
o
i
:
1
0
.
1
0
2
3
/
A
:
1
0
0
8
2
0
2
8
2
1
3
2
8
.
[
21
]
S
.
M
i
r
j
a
l
i
l
i
,
S
.
M
.
M
i
r
j
a
l
i
l
i
,
a
n
d
A
.
L
e
w
i
s,
“
G
r
e
y
w
o
l
f
o
p
t
i
mi
z
e
r
,
”
Ad
v
a
n
c
e
s
i
n
E
n
g
i
n
e
e
ri
n
g
S
o
f
t
w
a
re
,
v
o
l
.
6
9
,
p
p
.
4
6
–
6
1
,
2
0
1
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
d
v
e
n
g
so
f
t
.
2
0
1
3
.
1
2
.
0
0
7
.
[2
2
]
K
.
G
.
S
h
r
e
e
h
a
r
sh
a
,
R
.
K
.
S
i
d
d
h
a
r
t
h
,
M
.
H
.
V
a
sa
n
t
h
a
,
a
n
d
Y
.
B
.
N
.
K
u
mar,
“
A
n
e
r
r
o
r
b
o
u
n
d
p
a
r
t
i
c
l
e
sw
a
r
m
o
p
t
i
mi
z
a
t
i
o
n
f
o
r
a
n
a
l
o
g
c
i
r
c
u
i
t
si
z
i
n
g
,
”
I
EEE
Ac
c
e
ss
,
v
o
l
.
1
2
,
p
p
.
5
0
1
2
6
–
5
0
1
3
6
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
4
.
3
3
8
5
4
9
1
.
[2
3
]
I
.
S
a
b
i
r
i
,
H
.
B
o
u
y
g
h
f
,
a
n
d
A
.
R
a
i
h
a
n
i
,
“
O
p
t
i
ma
l
i
n
t
e
r
d
i
g
i
t
a
t
e
d
e
l
e
c
t
r
o
d
e
se
n
so
r
d
e
si
g
n
f
o
r
b
i
o
se
n
s
o
r
s
u
s
i
n
g
d
i
f
f
e
r
e
n
t
i
a
l
e
v
o
l
u
t
i
o
n
a
l
g
o
r
i
t
h
m,
”
E
3
S
W
e
b
o
f
C
o
n
f
e
re
n
c
e
s
,
v
o
l
.
3
5
1
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
5
1
/
e
3
sc
o
n
f
/
2
0
2
2
3
5
1
0
1
0
3
1
.
[2
4
]
K
.
G
.
S
h
r
e
e
h
a
r
sh
a
,
R
.
K
.
S
i
d
d
h
a
r
t
h
,
M
.
H
.
V
a
sa
n
t
h
a
,
a
n
d
Y
.
B
.
N
.
K
u
mar,
“
P
a
r
t
i
t
i
o
n
b
o
u
n
d
r
a
n
d
o
m
n
u
m
b
e
r
-
b
a
s
e
d
p
a
r
t
i
c
l
e
sw
a
r
m
o
p
t
i
m
i
z
a
t
i
o
n
f
o
r
a
n
a
l
o
g
c
i
r
c
u
i
t
si
z
i
n
g
,
”
I
EEE
Ac
c
e
ss
,
v
o
l
.
1
1
,
p
p
.
1
2
3
5
7
7
–
1
2
3
5
8
8
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
3
.
3
3
2
9
6
9
8
.
[2
5
]
H
.
B
o
u
y
g
h
f
,
B
.
B
e
n
h
a
l
a
,
a
n
d
A
.
R
a
i
h
a
n
i
,
“
A
n
a
l
y
s
i
s
o
f
t
h
e
i
m
p
a
c
t
o
f
m
e
t
a
l
t
h
i
c
k
n
e
ss
a
n
d
g
e
o
me
t
r
i
c
p
a
r
a
me
t
e
r
s
o
n
t
h
e
q
u
a
l
i
t
y
f
a
c
t
o
r
-
Q
i
n
i
n
t
e
g
r
a
t
e
d
s
p
i
r
a
l
i
n
d
u
c
t
o
r
s
b
y
m
e
a
n
s
o
f
a
r
t
i
f
i
c
i
a
l
b
e
e
c
o
l
o
n
y
t
e
c
h
n
i
q
u
e
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
E
l
e
c
t
r
i
c
a
l
a
n
d
C
o
m
p
u
t
e
r
E
n
g
i
n
e
e
r
i
n
g
,
v
o
l
.
9
,
n
o
.
4
,
p
p
.
2
9
1
8
–
2
9
3
1
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
c
e
.
v
9
i
4
.
p
p
2
9
1
8
-
2
9
3
1
.
[2
6
]
N
.
S
a
v
a
n
o
v
i
ć
e
t
a
l
.
,
“
I
n
t
r
u
s
i
o
n
d
e
t
e
c
t
i
o
n
i
n
H
e
a
l
t
h
c
a
r
e
4
.
0
i
n
t
e
r
n
e
t
o
f
t
h
i
n
g
s
sy
s
t
e
ms
v
i
a
m
e
t
a
h
e
u
r
i
st
i
c
s
o
p
t
i
m
i
z
e
d
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
S
u
st
a
i
n
a
b
i
l
i
t
y
,
v
o
l
.
1
5
,
n
o
.
1
6
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
su
1
5
1
6
1
2
5
6
3
.
[2
7
]
L.
Z
h
a
n
g
e
t
a
l
.
,
“
B
LPA
D
.
C
o
r
e
:
a
m
u
l
t
i
-
f
u
n
c
t
i
o
n
s
o
p
t
i
mi
z
e
r
t
o
w
a
r
d
s
d
a
i
l
y
p
l
a
n
n
i
n
g
g
e
n
e
r
a
t
i
o
n
i
n
h
o
me
h
e
a
l
t
h
c
a
r
e
,
”
i
n
2
0
2
0
I
EEE/
A
C
S
1
7
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
C
o
m
p
u
t
e
r
S
y
st
e
m
s
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
(
AI
C
C
S
A)
,
A
n
t
a
l
y
a
,
T
u
r
k
e
y
,
2
0
2
0
,
p
p
.
1
-
6
,
d
o
i
:
1
0
.
1
1
0
9
/
A
I
C
C
S
A
5
0
4
9
9
.
2
0
2
0
.
9
3
1
6
5
2
2
.
[2
8
]
L.
K
h
r
i
j
i
,
M
.
F
r
a
d
i
,
M
.
M
a
c
h
h
o
u
t
,
a
n
d
A
.
H
o
sse
n
,
“
D
e
e
p
l
e
a
r
n
i
n
g
-
b
a
se
d
a
p
p
r
o
a
c
h
f
o
r
a
t
r
i
a
l
f
i
b
r
i
l
l
a
t
i
o
n
d
e
t
e
c
t
i
o
n
,
”
i
n
T
h
e
I
m
p
a
c
t
o
f
D
i
g
i
t
a
l
T
e
c
h
n
o
l
o
g
i
e
s
o
n
Pu
b
l
i
c
H
e
a
l
t
h
i
n
D
e
v
e
l
o
p
e
d
a
n
d
D
e
v
e
l
o
p
i
n
g
C
o
u
n
t
ri
e
s
,
C
h
a
m
:
S
p
r
i
n
g
e
r
,
2
0
2
0
,
p
p
.
1
0
0
–
1
1
3
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
030
-
5
1
5
1
7
-
1
_
9
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
Meta
h
eu
r
is
tic
o
p
timiz
a
tio
n
fo
r
a
tr
ia
l fib
r
illa
tio
n
d
etec
tio
n
:
fe
a
tu
r
e
ex
tr
a
ctio
n
,
s
elec
tio
n
…
(
Za
id
N
o
u
n
a
)
3887
[2
9
]
Y
.
C
h
e
n
,
C
.
Zh
a
n
g
,
C
.
L
i
u
,
Y
.
W
a
n
g
,
a
n
d
X
.
W
a
n
,
“
A
t
r
i
a
l
f
i
b
r
i
l
l
a
t
i
o
n
d
e
t
e
c
t
i
o
n
u
si
n
g
a
f
e
e
d
f
o
r
w
a
r
d
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
J
o
u
rn
a
l
o
f
Me
d
i
c
a
l
a
n
d
B
i
o
l
o
g
i
c
a
l
E
n
g
i
n
e
e
r
i
n
g
,
v
o
l
.
4
2
,
n
o
.
1
,
p
p
.
6
3
–
7
3
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s
4
0
8
4
6
-
0
2
2
-
0
0
6
8
1
-
z.
[
30
]
U
.
R
.
A
c
h
a
r
y
a
,
H
.
F
u
j
i
t
a
,
O
.
S
.
L
i
h
,
Y
.
H
a
g
i
w
a
r
a
,
J.
H
.
Ta
n
,
a
n
d
M
.
A
d
a
m,
“
A
u
t
o
ma
t
e
d
d
e
t
e
c
t
i
o
n
o
f
a
r
r
h
y
t
h
m
i
a
s
u
si
n
g
d
i
f
f
e
r
e
n
t
i
n
t
e
r
v
a
l
s
o
f
t
a
c
h
y
c
a
r
d
i
a
E
C
G
s
e
g
m
e
n
t
s
w
i
t
h
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
I
n
f
o
rm
a
t
i
o
n
S
c
i
e
n
c
e
s
,
v
o
l
.
4
0
5
,
p
p
.
8
1
–
9
0
,
2
0
1
7
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
n
s
.
2
0
1
7
.
0
4
.
0
1
2
.
[
31
]
Z.
X
i
o
n
g
,
M
.
K
.
S
t
i
l
e
s
,
a
n
d
J.
Z
h
a
o
,
“
R
o
b
u
s
t
E
C
G
si
g
n
a
l
c
l
a
ss
i
f
i
c
a
t
i
o
n
f
o
r
d
e
t
e
c
t
i
o
n
o
f
a
t
r
i
a
l
f
i
b
r
i
l
l
a
t
i
o
n
u
si
n
g
a
n
o
v
e
l
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
i
n
2
0
1
7
C
o
m
p
u
t
i
n
g
i
n
C
a
rd
i
o
l
o
g
y
(
C
i
n
C
)
,
R
e
n
n
e
s,
F
r
a
n
c
e
,
2
0
1
7
,
p
p
.
1
-
4,
d
o
i
:
1
0
.
2
2
4
8
9
/
C
i
n
C
.
2
0
1
7
.
0
6
6
-
1
3
8
.
[3
2
]
P
.
C
a
o
e
t
a
l
.
,
“
A
n
o
v
e
l
d
a
t
a
a
u
g
m
e
n
t
a
t
i
o
n
me
t
h
o
d
t
o
e
n
h
a
n
c
e
d
e
e
p
n
e
u
r
a
l
n
e
t
w
o
r
k
s
f
o
r
d
e
t
e
c
t
i
o
n
o
f
a
t
r
i
a
l
f
i
b
r
i
l
l
a
t
i
o
n
,
”
B
i
o
m
e
d
i
c
a
l
S
i
g
n
a
l
Pr
o
c
e
ssi
n
g
a
n
d
C
o
n
t
ro
l
,
v
o
l
.
5
6
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
b
sp
c
.
2
0
1
9
.
1
0
1
6
7
5
.
[3
3
]
S
.
G
h
i
a
si
,
M
.
A
b
d
o
l
l
a
h
p
u
r
,
N
.
M
a
d
a
n
i
,
K
.
K
i
a
n
i
,
a
n
d
A
.
G
h
a
f
f
a
r
i
,
“
A
t
r
i
a
l
f
i
b
r
i
l
l
a
t
i
o
n
d
e
t
e
c
t
i
o
n
u
si
n
g
f
e
a
t
u
r
e
-
b
a
s
e
d
a
l
g
o
r
i
t
h
m
a
n
d
d
e
e
p
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
i
n
2
0
1
7
C
o
m
p
u
t
i
n
g
i
n
C
a
r
d
i
o
l
o
g
y
(
C
i
n
C
)
,
R
e
n
n
e
s
,
F
r
a
n
c
e
,
2
0
1
7
,
p
p
.
1
–
4
,
d
o
i
:
1
0
.
2
2
4
8
9
/
C
i
n
C
.
2
0
1
7
.
1
5
9
-
3
2
7
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Za
id
No
u
n
a
g
o
t
h
is
b
a
c
h
e
lo
r’s
d
e
g
re
e
in
El
e
c
tri
c
a
l
En
g
in
e
e
r
in
g
a
n
d
In
d
u
str
ial
Co
m
p
u
ti
n
g
i
n
2
0
2
0
,
a
n
d
t
h
e
n
a
n
e
n
g
in
e
e
rin
g
d
e
g
re
e
in
El
e
c
tri
c
a
l
a
n
d
Tele
c
o
m
m
u
n
ica
ti
o
n
s
i
n
2
0
2
3
,
b
o
th
a
t
t
h
e
Un
i
v
e
rsity
Ha
ss
a
n
II
M
o
h
a
m
m
e
d
ia
,
M
o
ro
c
c
o
.
He
is
c
u
rre
n
t
ly
a
P
h
.
D
.
st
u
d
e
n
t
a
t
M
o
h
a
m
m
e
d
ia
-
F
a
c
u
lt
y
o
f
S
c
ien
c
e
a
n
d
Tec
h
n
iq
u
e
s
,
Ha
ss
a
n
II
Un
iv
e
rsity
o
f
Ca
sa
b
lan
c
a
,
i
n
th
e
Lab
o
ra
t
o
ry
o
f
E
n
g
in
e
e
rin
g
S
c
ien
c
e
s
a
n
d
Bio
sc
ien
c
e
s
(LS
IB).
His
re
se
a
rc
h
a
n
d
in
tere
sts
a
re
c
e
n
tere
d
o
n
th
e
d
e
v
e
lo
p
m
e
n
t
a
n
d
o
p
t
imiz
a
ti
o
n
o
f
e
lec
tro
n
ic
sy
ste
m
s
fo
r
b
i
o
m
e
d
ica
l
e
n
g
in
e
e
rin
g
a
n
d
d
a
ta
sc
ien
c
e
tec
h
n
iq
u
e
s
fo
r
m
e
d
ica
l
a
p
p
li
c
a
ti
o
n
s.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
z
a
id
.
n
o
u
n
a
-
e
tu
@e
t
u
.
u
n
iv
h
2
c
.
m
a
.
H
a
m
id
B
o
u
y
g
h
f
g
o
t
h
is
B.
S
.
a
n
d
M
.
S
.
d
e
g
re
e
s
in
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
a
n
d
Tele
c
o
m
fro
m
t
h
e
Un
iv
e
rsit
y
o
f
S
c
ien
c
e
a
n
d
Tec
h
n
o
l
o
g
y
i
n
F
e
z
,
M
o
ro
c
c
o
,
i
n
2
0
0
7
,
a
n
d
h
i
s
P
h
.
D.
i
n
E
lec
tri
c
a
l
En
g
i
n
e
e
rin
g
a
n
d
Tele
c
o
m
fro
m
Ha
ss
a
n
II
Un
i
v
e
rsity
o
f
Ca
sa
b
lan
c
a
,
M
o
ro
c
c
o
,
i
n
2
0
1
9
.
F
ro
m
2
0
1
5
u
n
ti
l
2
0
1
9
,
h
e
w
o
rk
e
d
a
s
a
re
se
a
rc
h
a
ss
istan
t
a
t
t
h
e
P
ri
n
c
e
to
n
P
las
m
a
P
h
y
sic
s
Lab
o
ra
t
o
ry
.
S
i
n
c
e
2
0
1
9
,
h
e
h
a
s
wo
rk
e
d
a
s
a
n
a
ss
istan
t
p
ro
fe
ss
o
r
a
t
t
h
e
De
p
a
rtme
n
t
o
f
El
e
c
tri
c
a
l
E
n
g
i
n
e
e
rin
g
at
Ha
ss
a
n
II
Un
iv
e
rsit
y
’s
F
S
T
M
o
h
a
m
m
e
d
ia
in
Ca
sa
b
lan
c
a
,
M
o
ro
c
c
o
,
a
n
d
h
a
s
re
c
e
iv
e
d
h
is
h
a
b
il
i
tatio
n
in
El
e
c
tri
c
a
l
En
g
in
e
e
ri
n
g
a
n
d
Artifi
c
ial
In
telli
g
e
n
c
e
in
2
0
2
3
.
He
c
o
n
d
u
c
ts
re
se
a
rc
h
with
in
t
h
e
Lab
o
ra
to
r
y
o
f
En
g
in
e
e
rin
g
S
c
ien
c
e
s
a
n
d
Bio
sc
ien
c
e
s
(LS
IB),
lea
d
in
g
th
e
"
c
ircu
it
s
a
n
d
s
y
ste
m
s"
tea
m
.
In
th
e
to
p
ic
o
f
IC
o
p
ti
m
iza
ti
o
n
,
h
e
h
a
s
writt
e
n
n
u
m
e
ro
u
s
a
rti
c
les
.
His
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
b
i
o
m
e
d
ica
l
e
lec
tro
n
ics
,
a
n
a
lo
g
IC
d
e
sig
n
,
e
lec
tro
m
a
g
n
e
ti
c
fiel
d
s,
l
o
w
p
o
we
r
d
e
sig
n
,
a
n
d
B
L
E
a
p
p
li
c
a
ti
o
n
s
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
h
a
m
id
.
b
o
u
y
g
h
f@g
m
a
il
.
c
o
m
.
Mo
h
a
m
m
e
d
Na
h
i
d
stu
d
ied
e
lec
tro
n
ics
a
n
d
re
c
e
iv
e
d
th
e
B.
S
.
d
i
p
l
o
m
a
in
El
e
c
tro
n
ics
a
t
EN
S
ET
I
n
stit
u
te,
M
o
h
a
m
m
e
d
ia,
M
o
ro
c
c
o
in
1
9
9
4
,
re
c
e
iv
e
d
t
h
e
Ag
g
re
g
a
ti
o
n
d
ip
l
o
m
a
o
f
e
lec
tro
n
ics
a
n
d
e
lec
tri
c
a
l
e
n
g
in
e
e
rin
g
fr
o
m
ENS
E
T
i
n
st
it
u
te
o
f
Ra
b
a
t,
M
o
ro
c
c
o
in
2
0
0
0
.
He
re
c
e
iv
e
d
th
e
DES
A
d
i
p
lo
m
a
in
c
o
m
p
u
ter
e
n
g
i
n
e
e
rin
g
,
tele
c
o
m
s
a
n
d
m
u
lt
ime
d
ia
in
2
0
0
4
.
He
c
o
n
d
u
c
ted
d
o
c
t
o
ra
l
re
s
e
a
rc
h
a
t
ima
g
e
s,
v
id
e
o
s
c
o
d
in
g
a
n
d
q
u
a
li
ty
a
ss
e
ss
m
e
n
t
u
n
d
e
r
p
sy
c
h
o
v
isu
a
l
q
u
a
li
t
y
c
rit
e
ria
sin
c
e
2
0
0
4
a
t
M
o
h
a
m
e
d
V
u
n
iv
e
rsit
y
o
f
Ra
b
a
t,
M
o
r
o
c
c
o
,
wh
e
re
h
e
re
c
e
iv
e
d
h
is
P
h
.
D.
in
2
0
1
0
.
He
is
re
se
a
r
c
h
p
ro
fe
ss
o
r
in
t
h
e
F
a
c
u
lt
y
o
f
S
c
ien
c
e
a
n
d
Tec
h
n
iq
u
e
s
o
f
Ha
ss
a
n
II
Un
i
v
e
rsity
,
M
o
h
a
m
m
e
d
ia
sin
c
e
2
0
1
1
,
sp
e
c
ifi
c
a
ll
y
a
ffil
iate
d
with
th
e
Lab
o
ra
to
r
y
o
f
En
g
in
e
e
rin
g
S
c
ien
c
e
s
a
n
d
Bio
sc
ien
c
e
s
lo
c
a
ted
a
t
th
e
F
a
c
u
lt
y
o
f
S
c
ien
c
e
s
a
n
d
Tec
h
n
iq
u
e
s
(F
S
T),
c
o
n
d
u
c
ts
re
s
e
a
rc
h
o
n
v
is
u
a
l
p
e
rc
e
p
ti
o
n
a
n
d
it
s
a
p
p
li
c
a
ti
o
n
t
o
c
o
d
i
n
g
,
u
n
d
e
rsta
n
d
i
n
g
,
a
n
d
d
is
p
lay
o
f
v
isu
a
l
in
f
o
rm
a
ti
o
n
a
n
d
t
o
h
u
m
a
n
v
isi
o
n
,
ima
g
e
q
u
a
li
ty
,
a
n
d
d
ig
it
a
l
ima
g
i
n
g
.
Re
se
a
rc
h
a
n
d
p
r
o
jec
ts
a
re
a
lso
fo
c
u
se
d
o
n
a
rti
fi
c
ial
in
telli
g
e
n
c
e
,
e
m
b
e
d
d
e
d
sy
ste
m
s,
b
io
m
e
d
ica
l
sy
ste
m
s,
sm
a
rt
g
rid
s,
a
n
d
d
ig
it
a
l
a
n
d
a
n
a
lo
g
IC
d
e
sig
n
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
m
o
h
a
m
m
e
d
.
n
a
h
id
@g
m
a
il
.
c
o
m
.
Issa
S
a
b
iri
g
o
t
a
P
h
.
D.
d
e
g
re
e
in
El
e
c
tri
c
a
l
En
g
i
n
e
e
rin
g
a
n
d
Arti
ficia
l
In
telli
g
e
n
c
e
fro
m
ENS
ET
M
o
h
a
m
m
e
d
ia
-
F
a
c
u
lt
y
o
f
S
c
ien
c
e
a
n
d
Tec
h
n
iq
u
e
,
Ha
ss
a
n
II
Un
iv
e
rsity
o
f
Ca
sa
b
lan
c
a
,
M
o
r
o
c
c
o
,
a
ffil
iate
d
with
t
h
e
La
b
o
ra
to
r
y
o
f
S
i
g
n
a
l
s,
Distrib
u
ted
S
y
ste
m
s
a
n
d
Artifi
c
ial
In
telli
g
e
n
c
e
(LS
S
DIA
)
.
His
li
c
e
n
se
d
e
g
re
e
in
b
i
o
m
e
d
ica
l
in
stru
m
e
n
tat
io
n
a
n
d
m
a
in
ten
a
n
c
e
,
a
t
t
h
e
In
stit
u
te
o
f
He
a
lt
h
S
c
ien
c
e
sSettat
-
M
o
r
o
c
c
o
(IS
S
S
)
a
t
t
h
e
Un
i
v
e
rsity
Ha
ss
a
n
I,
S
e
tt
a
t
-
M
o
r
o
c
c
o
.
He
a
lso
g
o
t
a
m
a
ste
r’s
d
e
g
re
e
i
n
B
io
m
e
d
ica
l
E
n
g
i
n
e
e
rin
g
fr
o
m
F
S
T
S
e
tt
a
t
in
2
0
1
8
.
His
wo
r
k
,
stu
d
ies
,
a
n
d
i
n
tere
sts
a
re
fo
c
u
se
d
o
n
t
h
e
d
e
v
e
lo
p
m
e
n
t
,
d
e
sig
n
,
a
n
d
o
p
ti
m
iza
ti
o
n
o
f
e
lec
tro
n
ic
sy
ste
m
s
fo
r
b
i
o
m
e
d
ica
l
e
n
g
in
e
e
rin
g
,
a
n
d
h
e
a
lt
h
sc
ien
c
e
s.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
issa
.
sa
b
iri
@e
t
u
.
fstm
.
a
c
.
m
a
.
Evaluation Warning : The document was created with Spire.PDF for Python.