I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
p
u
t
er
Science
Vo
l.
21
,
No
.
3
,
Ma
r
ch
2
0
2
1
,
p
p
.
1
5
3
0
~
1
5
3
9
I
SS
N:
2
5
02
-
4
7
5
2
,
DOI
: 1
0
.
1
1
5
9
1
/i
j
ee
cs.v
2
1
.i
3
.
pp
1
5
3
0
-
1
5
3
9
1530
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs.ia
esco
r
e.
co
m
Predic
ting hea
rt
f
a
ilure using
a w
r
a
pper
-
ba
sed
feat
ure selec
tion
M
inh
T
ua
n L
e
1
,
M
inh
T
ha
n
h Vo
2
,
Nha
t
T
a
n P
ha
m
3
,
So
n
V.
T
Da
o
4
1,
2
S
EE
,
In
ter
n
a
ti
o
n
a
l
Un
iv
e
rsity
,
V
ietn
a
m
Na
ti
o
n
a
l
Un
iv
e
rsity
Ho
Ch
i
M
i
n
h
Cit
y
,
Ho
Ch
i
M
in
h
Cit
y
,
V
iet
Na
m
3,
4
S
IEM
,
V
NU
-
In
te
rn
a
ti
o
n
a
l
U
n
iv
e
rsit
y
,
V
ietn
a
m
Na
ti
o
n
a
l
Un
iv
e
rsi
ty
Ho
Ch
i
M
in
h
Cit
y
,
Ho
Ch
i
M
i
n
h
Ci
ty
,
V
iet
Na
m
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Oct
3
0
,
2
0
2
0
R
ev
i
s
ed
Dec
7
,
2
0
2
0
A
cc
ep
ted
Dec
2
3
,
2
0
2
0
In
th
e
c
u
rre
n
t
h
e
a
lt
h
sy
st
e
m
,
it
is
v
e
r
y
d
iff
i
c
u
lt
f
o
r
m
e
d
ica
l
p
ra
c
ti
ti
o
n
e
rs/
p
h
y
sic
ian
s
to
d
iag
n
o
se
th
e
e
f
f
e
c
ti
v
e
n
e
ss
o
f
h
e
a
rt
c
o
n
trac
ti
o
n
.
In
th
i
s
re
se
a
rc
h
,
w
e
p
ro
p
o
se
d
a
m
a
c
h
in
e
lea
rn
in
g
m
o
d
e
l
to
p
re
d
ict
h
e
a
rt
c
o
n
trac
ti
o
n
u
si
n
g
a
n
a
rti
f
icia
l
n
e
u
ra
l
n
e
t
w
o
rk
(
A
NN
).
W
e
a
lso
p
ro
p
o
se
d
a
n
o
v
e
l
w
r
a
p
p
e
r
-
b
a
se
d
fe
a
tu
re
se
lec
ti
o
n
u
ti
li
z
i
n
g
a
g
re
y
w
o
lf
o
p
ti
m
iza
ti
o
n
(
GW
O)
to
re
d
u
c
e
th
e
n
u
m
b
e
r
o
f
r
e
q
u
ired
in
p
u
t
a
tt
rib
u
tes
.
In
th
is
w
o
rk
,
w
e
c
o
m
p
a
re
d
th
e
re
su
lt
s
a
c
h
iev
e
d
u
sin
g
o
u
r
m
e
th
o
d
a
n
d
se
v
e
ra
l
c
o
n
v
e
n
ti
o
n
a
l
m
a
c
h
in
e
lea
rn
in
g
a
lg
o
rit
h
m
s
a
p
p
ro
a
c
h
e
s
su
c
h
a
s
su
p
p
o
rt
v
e
c
t
o
r
m
a
c
h
in
e
,
d
e
c
isio
n
tree
,
K
-
n
e
a
re
st
n
e
ig
h
b
o
r,
n
a
ïv
e
b
a
y
e
s,
ra
n
d
o
m
f
o
re
st,
a
n
d
lo
g
isti
c
re
g
re
ss
io
n
.
Co
m
p
u
tatio
n
a
l
re
su
lt
s
sh
o
w
n
o
t
o
n
ly
th
a
t
m
u
c
h
fe
w
e
r
fe
a
tu
re
s
a
re
n
e
e
d
e
d
,
b
u
t
a
lso
h
ig
h
e
r
p
re
d
ictio
n
a
c
c
u
ra
c
y
c
a
n
b
e
a
c
h
iev
e
d
a
ro
u
n
d
8
7
%
.
T
h
is
w
o
r
k
h
a
s th
e
p
o
te
n
ti
a
l
to
b
e
a
p
p
li
c
a
b
le t
o
c
li
n
ica
l
p
ra
c
ti
c
e
a
n
d
b
e
c
o
m
e
a
su
p
p
o
rti
n
g
to
o
l
f
o
r
d
o
c
t
o
rs/p
h
y
sic
ian
s.
K
ey
w
o
r
d
s
:
Featu
r
e
s
elec
t
io
n
Gr
e
y
w
o
l
f
o
p
ti
m
izatio
n
Hea
r
t f
ail
u
r
e
Mu
ltil
a
y
er
p
er
ce
p
tr
o
n
Neu
r
al
n
et
w
o
r
k
T
h
is
is
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
:
So
n
V.
T
Dao
Sch
o
o
l o
f
I
n
d
u
s
tr
ial
an
d
Ma
n
a
g
e
m
e
n
t
I
n
ter
n
atio
n
al
Un
iv
er
s
it
y
Vi
etn
a
m
Natio
n
al
Un
iv
er
s
it
y
HC
MC
Ho
C
h
i M
i
n
h
C
it
y
,
Viet
Na
m
E
m
ail: d
v
ts
o
n
@
h
c
m
iu
.
ed
u
.
vn
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
ter
m
"
h
ea
r
t
f
ail
u
r
e"
r
ef
er
r
in
g
to
a
co
n
d
itio
n
i
n
w
h
ic
h
th
e
h
ea
r
t's
co
n
tr
ac
tio
n
is
n
o
t
as
ef
f
ec
ti
v
e
as
it
s
h
o
u
ld
b
e.
T
h
e
h
ea
r
t
is
a
v
i
tal
o
r
g
an
in
th
e
h
u
m
an
b
o
d
y
b
ec
au
s
e
it
p
u
m
p
s
b
lo
o
d
to
ev
er
y
o
th
er
o
r
g
a
n
.
A
p
atien
t
w
h
o
i
s
li
v
i
n
g
v
e
g
etati
v
e
s
tates
s
till
n
ee
d
s
t
h
e
h
ea
r
t to
s
u
r
v
iv
e.
Hea
r
t
f
ail
u
r
e
(
HF)
is
a
ch
r
o
n
ic
co
n
d
itio
n
in
w
h
ich
o
n
e
o
f
th
e
v
e
n
tr
icles
o
r
atr
iu
m
s
o
n
b
o
th
s
id
es is
n
o
t
ab
le
to
p
u
m
p
r
ich
o
x
y
g
e
n
in
to
th
e
b
o
d
y
a
n
d
p
o
o
r
o
x
y
g
en
in
to
t
h
e
l
u
n
g
s
.
T
h
er
e
ar
e
s
ev
er
al
co
m
m
o
n
r
ea
s
o
n
s
c
au
s
e
h
ea
r
t
f
ail
u
r
e.
T
h
e
m
aj
o
r
i
t
y
o
f
(
H
F)
p
atien
t
s
ar
e
eld
er
ly
.
C
ar
d
iac
ar
r
est
o
f
t
en
g
r
ad
u
all
y
an
d
d
elib
er
atel
y
d
ev
elo
p
s
af
ter
p
ar
ts
o
f
a
h
ea
r
t
g
o
t
w
ea
k
en
a
n
d
m
ak
e
s
o
t
h
er
s
s
u
c
h
as
v
e
n
tr
icl
es
an
d
atr
i
u
m
s
d
o
ex
tr
a
w
o
r
k
l
o
ad
s
to
p
r
o
v
id
e
en
o
u
g
h
b
lo
o
d
an
d
o
x
y
g
e
n
to
t
h
e
b
o
d
y
[
1
-
2
]
.
W
ith
t
h
e
u
b
iq
u
ito
u
s
ap
p
licatio
n
o
f
tec
h
n
o
lo
g
y
i
n
t
h
e
m
ed
ical
f
ield
,
i
t
h
elp
s
t
h
e
co
s
t
o
f
d
iag
n
o
s
i
s
to
b
e
in
ex
p
en
s
i
v
e.
U
n
f
o
r
t
u
n
a
tel
y
,
n
o
w
ad
a
y
s
t
h
e
n
u
m
b
er
o
f
p
atien
ts
w
h
o
h
a
v
e
b
ee
n
d
iag
n
o
s
e
s
w
it
h
h
ea
r
t
f
ail
u
r
e
is
g
r
ad
u
all
y
i
n
cr
ea
s
i
n
g
i
n
s
u
b
u
r
b
s
a
n
d
d
r
a
m
atica
ll
y
in
cr
ea
s
in
g
i
n
u
r
b
an
ar
ea
s
.
T
h
er
ef
o
r
e,
th
e
ea
r
lier
f
o
r
g
etti
n
g
d
iag
n
o
s
ed
,
t
h
e
b
etter
o
f
f
it
w
ill
b
e
f
o
r
th
e
p
atien
t
s
.
B
ec
au
s
e
o
f
t
h
e
d
if
f
ic
u
lt
y
o
f
d
ia
g
n
o
s
in
g
th
e
p
r
o
ce
s
s
o
f
a
h
ea
r
t
f
ail
u
r
e
co
n
d
itio
n
,
it
m
i
g
h
t
ca
u
s
e
a
p
o
s
tp
o
n
e
m
en
t
in
tr
ea
t
m
e
n
t
o
p
er
atio
n
.
T
h
er
ef
o
r
e,
it
is
cr
u
cial
to
d
ev
elo
p
a
h
ea
r
t
d
is
ea
s
e
p
r
ed
ictio
n
s
y
s
te
m
f
o
r
h
ea
r
t
f
a
il
u
r
e
to
s
u
p
p
o
r
t
w
h
o
e
v
er
w
o
r
k
s
in
t
h
e
m
ed
ical
p
r
o
f
ess
io
n
al
f
ield
to
d
iag
n
o
s
e
p
atien
ts
w
i
th
co
n
d
itio
n
s
m
o
r
e
r
ap
id
an
d
ac
cu
r
ate.
Dee
p
lear
n
in
g
a
n
d
Ma
ch
i
n
e
lear
n
in
g
al
g
o
r
ith
m
s
h
a
v
e
b
ee
n
s
u
cc
e
s
s
f
u
ll
y
ap
p
lied
to
v
ar
io
u
s
f
ield
[
3
-
4
]
,
esp
ec
iall
y
m
ed
i
ca
l
f
ield
to
s
u
p
p
o
r
t
d
o
cto
r
/p
h
y
s
ician
to
d
iag
n
o
s
e
v
ar
io
u
s
d
is
ea
s
e
s
s
u
c
h
as
h
ea
r
t
f
ail
u
r
e,
d
iab
etes.
A
N
N
h
as
al
s
o
b
ee
n
ap
p
lied
b
y
r
esear
ch
er
s
in
t
h
e
m
ed
ical
f
ie
l
d
[5
-
7]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
P
r
ed
ictin
g
h
ea
r
t fa
ilu
r
e
u
s
in
g
a
w
r
a
p
p
er
-
b
a
s
ed
fea
tu
r
e
s
elec
tio
n
(
Min
h
Tu
a
n
Le
)
1531
I
n
th
i
s
s
t
u
d
y
,
w
e
w
i
ll
u
s
e
a
m
u
l
tila
y
er
p
er
ce
p
tr
o
n
m
o
d
e
ls
(
ML
P
)
to
g
et
h
er
w
ith
p
r
ep
r
o
ce
s
s
in
g
m
et
h
o
d
s
f
o
r
p
r
ed
ictin
g
h
ea
r
t
f
ailu
r
e
p
atien
t.
B
esid
es,
a
m
eta
h
eu
r
i
s
tics
-
b
as
ed
f
ea
tu
r
e
s
elec
t
io
n
alg
o
r
ith
m
g
r
e
y
w
o
l
f
o
p
ti
m
iza
tio
n
(
GW
O)
als
o
ap
p
lied
to
ML
P
m
o
d
els
to
e
n
h
a
n
ce
t
h
e
p
er
f
o
r
m
a
n
ce
a
n
d
r
ed
u
ce
tr
ain
i
n
g
ti
m
e
.
T
h
e
r
esu
lt
is
a
b
en
c
h
m
ar
k
w
i
th
o
th
er
co
m
m
o
n
m
ac
h
in
e
le
ar
n
in
g
/
d
ee
p
lear
n
i
n
g
al
g
o
r
ith
m
s
i
n
t
h
e
f
o
llo
w
i
n
g
s
u
c
h
as
lo
g
i
s
tic
r
e
g
r
ess
io
n
(
L
R
)
[
8
]
,
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
i
n
e
(
SVM)
[
9
]
,
k
-
n
ea
r
est
n
ei
g
h
b
o
r
class
i
f
ier
(
KNN)
[
1
0
]
,
n
aiv
e
b
a
y
e
s
ian
clas
s
i
f
ier
(
NB
C
)
[
1
1
-
12]
,
d
ec
is
io
n
tr
ee
(
DT
)
[
1
3
]
,
an
d
r
an
d
o
m
f
o
r
est
class
if
ier
(
R
F
C
)
[
1
4
]
b
ased
o
n
th
e
o
r
ig
in
al
s
et
o
f
av
ailab
le
m
ed
ical
f
ea
t
u
r
es.
Sev
er
al
d
ata
m
i
n
i
n
g
m
et
h
o
d
s
h
a
v
e
b
ee
n
s
u
cc
es
s
f
u
ll
y
ap
p
li
ed
to
d
iag
n
o
s
in
g
h
ea
r
t
f
ail
u
r
e
(
HF)
.
I
n
[
1
0
]
,
Dav
id
e
C
h
ic
co
r
ep
r
esen
ts
a
m
o
d
el
to
d
iag
n
o
s
tic
t
h
e
s
u
r
v
i
v
al
r
ate
o
f
p
atie
n
ts
wh
o
h
av
e
b
ee
n
u
s
in
g
clin
ical
r
ec
o
r
d
HF
d
ata.
I
n
th
e
r
esear
ch
[
1
5
]
,
a
lis
t
o
f
th
e
m
ac
h
in
e
lear
n
in
g
m
e
th
o
d
s
w
a
s
u
s
ed
f
o
r
th
e
b
in
ar
y
class
i
f
icatio
n
o
f
s
u
r
v
i
v
al.
A
r
an
d
o
m
f
o
r
est
clas
s
i
f
ier
o
u
tp
e
r
f
o
r
m
ed
all
o
th
er
m
et
h
o
d
s
co
m
p
ar
ed
to
th
e
o
th
er
m
o
d
el
s
,
w
h
ic
h
is
v
er
y
i
m
p
r
es
s
iv
e
in
t
h
is
a
g
e
[
1
6
]
.
Gu
id
i
e
t
a
l
.
(
2
0
1
3
)
r
ep
r
esen
t
a
cli
n
ica
l
d
ec
is
io
n
s
u
p
p
o
r
t
s
y
s
te
m
(
C
DS
S)
f
o
r
an
al
y
zi
n
g
HF
p
atien
t
s
an
d
co
m
p
ar
i
n
g
th
e
p
er
f
o
r
m
a
n
ce
o
f
n
e
u
r
al
n
e
t
wo
r
k
,
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e,
f
u
zz
y
-
g
e
n
etic,
r
an
d
o
m
f
o
r
est.
I
n
[
1
7
]
,
th
e
au
th
o
r
s
u
s
ed
th
e
d
etailed
clin
ica
l
d
ata
o
n
p
atien
ts
h
o
s
p
italized
w
it
h
HF
i
n
O
n
tar
io
,
C
an
ad
a.
I
n
th
e
m
ac
h
in
e
lea
r
n
in
g
liter
at
u
r
e,
alter
n
ate
cla
s
s
i
f
icatio
n
s
c
h
e
m
e
s
h
av
e
b
ee
n
d
ev
elo
p
ed
s
u
c
h
as
b
o
o
ts
tr
ap
ag
g
r
eg
atio
n
(
b
a
g
g
i
n
g
)
,
b
o
o
s
tin
g
,
r
an
d
o
m
f
o
r
est
s
,
an
d
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
s
.
T
h
e
y
al
s
o
co
m
p
ar
ed
th
e
ab
ilit
y
o
f
t
h
ese
m
et
h
o
d
s
to
p
r
ed
ict
th
e
p
r
o
b
ab
ilit
y
o
f
th
e
p
r
esen
c
e
o
f
h
ea
r
t
f
ail
u
r
e
w
ith
p
r
eser
v
ed
ej
ec
tio
n
f
r
ac
tio
n
(
HFP
E
F).
Featu
r
e
s
e
lectio
n
(
F
S)
is
a
p
r
o
ce
s
s
th
at
co
m
m
o
n
l
y
s
elec
ts
in
m
ac
h
in
e
lear
n
i
n
g
to
s
o
lv
e
th
e
h
ig
h
d
i
m
en
s
io
n
al
it
y
p
r
o
b
le
m
.
I
n
F
S,
w
e
c
h
o
o
s
e
a
s
m
al
l
n
u
m
b
er
o
f
f
ea
t
u
r
es
b
u
t
i
m
p
o
r
tan
t
an
d
u
s
u
all
y
ig
n
o
r
e
th
e
ir
r
elev
an
t
a
n
d
n
o
is
y
f
ea
tu
r
e
s
,
in
o
r
d
er
to
m
a
k
e
t
h
e
s
u
b
s
eq
u
en
t
a
n
al
y
s
i
s
ea
s
ier
.
A
cc
o
r
d
in
g
to
th
e
r
ed
u
n
d
an
c
y
an
d
r
elev
an
ce
.
Y
u
et
a
l
.,
[
1
8
]
h
av
e
class
i
f
ied
th
o
s
e
f
ea
t
u
r
e
s
u
b
s
et
s
in
to
f
o
u
r
d
if
f
er
en
t
t
y
p
es
:
n
o
is
y
an
d
ir
r
elev
an
t;
r
ed
u
n
d
an
t
a
n
d
w
e
ak
l
y
r
ele
v
an
t,
w
ea
k
l
y
r
ele
v
an
t
an
d
n
o
n
-
r
ed
u
n
d
a
n
t,
an
d
s
tr
o
n
g
l
y
r
ele
v
a
n
t.
A
n
ir
r
elev
an
t
f
ea
tu
r
e
d
o
es
n
o
t
r
eq
u
ir
e
p
r
ed
ictin
g
ac
cu
r
ac
y
.
F
u
r
th
er
m
o
r
e,
m
a
n
y
ap
p
r
o
ac
h
es
ca
n
i
m
p
le
m
e
n
t
w
it
h
f
ilter
an
d
w
r
ap
p
er
m
e
th
o
d
s
s
u
c
h
as
m
o
d
els,
s
ea
r
c
h
s
t
r
ateg
ies,
f
ea
tu
r
e
q
u
ali
t
y
m
e
asu
r
es,
a
n
d
f
ea
tu
r
e
ev
alu
a
tio
n
.
A
ll
f
ea
t
u
r
es
p
la
y
a
s
k
e
y
f
ac
to
r
s
f
o
r
d
eter
m
i
n
i
n
g
th
e
h
y
p
o
th
e
s
is
o
f
t
h
e
p
r
ed
ictin
g
m
o
d
els.
B
esid
es
th
at,
t
h
e
n
u
m
b
er
o
f
f
ea
t
u
r
es
a
n
d
th
e
s
ize
o
f
t
h
e
h
y
p
o
th
e
s
is
s
p
ac
es
ar
e
d
ir
ec
tly
p
r
o
p
o
r
tio
n
al
to
ea
ch
o
th
er
,
an
d
s
o
o
n
.
W
h
e
n
t
h
e
n
u
m
b
er
o
f
f
ea
t
u
r
es
i
n
cr
ea
s
es,
th
e
s
ize
o
f
t
h
e
s
ea
r
ch
i
n
g
s
p
ac
e
al
s
o
i
n
cr
ea
s
ed
.
On
e
s
u
c
h
o
u
ts
ta
n
d
in
g
ca
s
e
i
s
t
h
at
i
f
th
er
e
ar
e
M
f
ea
tu
r
e
s
w
it
h
th
e
b
i
n
a
r
y
clas
s
lab
el
in
a
d
ataset,
it
h
as
co
m
b
i
n
atio
n
in
th
e
s
ea
r
ch
s
p
ac
e.
T
h
er
e
ar
e
th
r
ee
t
y
p
es
o
f
F
S
m
et
h
o
d
s
,
w
h
ic
h
ar
e
d
ef
i
n
ed
b
ased
o
n
th
e
i
n
ter
ac
tio
n
w
it
h
t
h
e
lear
n
i
n
g
m
o
d
el,
n
a
m
e
l
y
f
ilter
,
w
r
ap
p
er
,
an
d
e
m
b
ed
d
ed
m
et
h
o
d
s
.
T
h
e
Fil
ter
m
et
h
o
d
s
elec
ts
s
tatis
t
ic
s
-
b
ased
f
ea
tu
r
es.
I
t
is
i
n
d
ep
en
d
en
t
o
f
t
h
e
lear
n
i
n
g
alg
o
r
it
h
m
an
d
th
u
s
r
eq
u
ir
es
l
ess
co
m
p
u
tatio
n
al
t
i
m
e.
Stati
s
tical
m
ea
s
u
r
es
s
u
c
h
as
in
f
o
r
m
atio
n
g
ai
n
,
ch
i
-
s
q
u
ar
e
test
[
1
9
]
,
Fis
h
er
s
co
r
e,
co
r
r
elatio
n
co
ef
f
icien
t,
a
n
d
v
ar
ian
ce
th
r
esh
o
ld
ar
e
u
s
ed
to
u
n
d
er
s
ta
n
d
t
h
e
i
m
p
o
r
tan
ce
o
f
th
e
f
ea
tu
r
es.
I
n
co
n
tr
ast,
t
h
e
w
r
ap
p
er
m
et
h
o
d
’
s
p
er
f
o
r
m
a
n
ce
h
ig
h
l
y
d
ep
en
d
s
o
n
th
e
clas
s
if
ier
.
T
h
e
b
est
s
u
b
s
et
o
f
f
ea
tu
r
es
is
s
elec
ted
b
ased
o
n
th
e
r
esu
lts
o
f
t
h
e
class
i
f
ier
.
W
r
ap
p
er
m
et
h
o
d
s
ar
e
m
u
ch
m
o
r
e
co
m
p
u
tat
io
n
all
y
ex
p
e
n
s
i
v
e
t
h
a
n
f
i
lter
m
e
th
o
d
s
s
i
n
ce
it
n
ee
d
s
to
r
u
n
s
i
m
u
lta
n
eo
u
s
l
y
w
it
h
t
h
e
clas
s
i
f
ier
m
a
n
y
ti
m
es.
Ho
w
e
v
er
,
th
ese
m
et
h
o
d
s
ar
e
m
o
r
e
ac
c
u
r
ate
th
a
n
t
h
e
f
ilter
m
et
h
o
d
.
So
m
e
o
f
t
h
e
w
r
ap
p
er
ex
a
m
p
les
ar
e
r
ec
u
r
s
i
v
e
f
ea
t
u
r
e
eli
m
in
a
tio
n
[
2
0
]
,
S
eq
u
en
tial
f
ea
t
u
r
e
s
elec
tio
n
al
g
o
r
ith
m
s
[
2
1
]
,
an
d
g
en
et
ic
alg
o
r
it
h
m
s
[
2
2
]
.
T
h
ir
d
l
y
,
th
e
e
m
b
ed
d
ed
m
et
h
o
d
w
h
i
ch
u
ti
lizes
e
n
s
e
m
b
le
lear
n
i
n
g
an
d
h
y
b
r
id
lear
n
i
n
g
m
et
h
o
d
s
f
o
r
f
ea
tu
r
e
s
elec
tio
n
.
T
h
is
m
eth
o
d
h
as
a
co
llectiv
e
d
ec
is
io
n
;
th
er
e
f
o
r
e,
its
p
er
f
o
r
m
an
ce
i
s
b
etter
th
an
th
e
p
r
ev
io
u
s
o
n
e.
O
n
e
e
x
a
m
p
le
is
t
h
e
r
an
d
o
m
f
o
r
est
w
h
ic
h
is
les
s
co
m
p
u
tat
io
n
a
ll
y
in
te
n
s
iv
e
t
h
a
n
w
r
ap
p
er
m
et
h
o
d
s
.
On
e
d
r
a
w
b
ac
k
o
f
t
h
e
e
m
b
ed
d
ed
m
et
h
o
d
is
th
at
it i
s
s
p
ec
if
ic
to
a
lear
n
i
n
g
m
o
d
el.
Ma
n
y
ev
o
l
u
tio
n
ar
y
m
etah
e
u
r
i
s
tics
-
b
ased
f
ea
tu
r
e
s
elec
tio
n
m
et
h
o
d
s
ar
e
also
p
r
o
p
o
s
ed
,
m
an
y
o
f
t
h
e
m
ar
e
w
r
ap
p
er
t
y
p
e
s
in
ce
it
h
as
b
ee
n
p
r
o
v
en
th
at
w
r
ap
p
er
p
r
o
v
id
es
b
etter
p
er
f
o
r
m
a
n
ce
[
2
3
]
.
T
o
o
et
a
l
.,
[
2
4
]
p
r
o
p
o
s
ed
a
co
m
p
etit
iv
e
b
i
n
ar
y
g
r
e
y
w
o
l
f
o
p
ti
m
izer
(
C
B
G
W
O)
,
w
h
ich
is
b
ased
o
n
th
e
g
r
e
y
w
o
l
f
o
p
ti
m
izer
(
GW
O)
p
r
o
p
o
s
ed
b
y
Mir
j
alili
et
a
l
.
[
2
5
]
,
f
o
r
f
ea
tu
r
e
s
elec
t
io
n
p
r
o
b
lem
i
n
E
MG
s
i
g
n
al
class
i
f
icatio
n
.
T
h
e
r
esu
lt
s
s
h
o
w
ed
th
at
C
B
GW
O
o
u
tr
an
k
ed
o
th
er
al
g
o
r
ith
m
s
i
n
ter
m
s
o
f
p
er
f
o
r
m
a
n
ce
f
o
r
th
a
t
ca
s
e
s
t
u
d
y
.
Ma
n
y
o
th
er
w
r
ap
p
er
-
b
ased
f
ea
t
u
r
e
s
elec
tio
n
alg
o
r
it
h
m
s
w
er
e
also
in
tr
o
d
u
ce
d
in
m
a
n
y
p
r
ev
io
u
s
w
o
r
k
s
to
s
elec
t
a
s
u
b
s
et
o
f
f
ea
tu
r
e
s
,
in
cl
u
d
i
n
g
b
in
ar
y
g
r
e
y
w
o
l
f
o
p
ti
m
izatio
n
(
B
GW
O)
[
2
6
]
,
b
in
ar
y
p
ar
ticle
s
w
ar
m
o
p
ti
m
iza
tio
n
(
B
P
SO)
[
2
7
]
,
an
t c
o
lo
n
y
o
p
tim
izatio
n
(
AC
O)
[
2
8
]
,
an
d
b
in
ar
y
d
i
f
f
er
en
tial e
v
o
lu
tio
n
(
B
DE
)
[
2
9
]
.
2.
RE
S
E
ARCH
M
E
T
H
O
D
T
h
is
s
y
s
te
m
i
n
cl
u
d
es t
w
o
s
tep
s
: d
ata
p
r
e
-
p
r
o
ce
s
s
i
n
g
w
h
ic
h
i
n
v
o
l
v
ed
o
u
tlier
d
etec
tio
n
.
T
h
en
f
o
llo
w
e
d
b
y
a
m
u
lt
ila
y
er
p
er
ce
p
tr
o
n
(
ML
P
)
.
T
h
e
o
u
tlier
d
etec
tio
n
i
n
t
h
is
r
e
s
ea
r
ch
i
s
u
s
i
n
g
i
n
ter
q
u
ar
tile
r
an
g
e
(
I
Q
R
)
m
et
h
o
d
an
d
th
e
n
ap
p
l
y
i
n
g
g
r
e
y
w
o
l
f
o
p
ti
m
izer
to
o
p
ti
m
iz
e
th
e
ar
ch
itect
u
r
e
o
f
m
u
ltil
a
y
er
p
er
ce
p
tr
o
n
f
o
r
cla
s
s
i
f
y
in
g
t
h
e
h
ea
r
t
f
ail
u
r
e
p
atien
t
s
.
T
h
e
d
etail
o
f
th
is
m
et
h
o
d
is
d
escr
ib
ed
in
th
is
s
ec
tio
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
21
,
No
.
3
,
Ma
r
ch
2
0
2
1
:
1
5
3
0
-
1
5
3
9
1532
2
.
1
.
D
a
t
a
C
o
llect
io
n
Hea
r
t
f
ail
u
r
e
clin
ical
r
ec
o
r
d
s
d
ata
s
et
h
as
b
ee
n
u
s
ed
in
t
h
is
r
esear
ch
,
w
h
ic
h
is
r
ec
o
r
d
s
h
ea
r
t
f
ailu
r
e
p
atien
ts
f
r
o
m
t
h
e
Fais
a
lab
ad
I
n
s
ti
tu
te
o
f
C
ar
d
io
lo
g
y
a
n
d
th
e
A
llied
Ho
s
p
ital
i
n
Fai
s
alab
ad
(
P
u
n
j
ab
,
P
ak
is
tan
)
.
T
h
e
d
ataset
is
a
v
ailab
le
o
n
t
h
e
U
C
I
r
ep
o
s
ito
r
y
.
T
h
e
tar
g
e
t
o
f
t
h
is
b
in
ar
y
clas
s
i
f
icatio
n
h
as
t
w
o
ca
teg
o
r
ial
v
alu
e
:
1
-
y
es
(
p
atien
t
is
s
ick
)
a
n
d
0
-
n
o
(
p
atien
t
is
h
ea
lt
h
y
)
.
T
h
e
attr
ib
u
te
f
o
r
p
r
ed
ictin
g
i
s
“DE
A
T
H_
E
VE
NT
”
w
h
ic
h
co
n
tai
n
s
t
w
o
ca
te
g
o
r
ic
al
v
al
u
es
a
n
d
is
co
n
s
id
er
ed
as
a
b
in
ar
y
clas
s
i
f
icatio
n
p
r
o
b
le
m
.
T
ab
le
1
lis
t
th
e
n
u
m
b
er
o
f
in
s
ta
n
ce
n
u
m
b
er
o
f
attr
ib
u
te
an
d
f
ea
t
u
r
es o
f
th
e
d
ataset
.
T
h
e
d
ataset
co
n
tai
n
s
2
9
9
in
s
tan
ce
s
a
n
d
1
2
at
tr
ib
u
tes.
E
ac
h
o
f
th
e
s
e
attr
ib
u
tes
is
p
h
y
s
io
lo
g
ical
m
ea
s
u
r
e
m
e
n
t
s
.
T
h
e
p
atien
ts
i
n
th
is
d
ataset
i
n
cl
u
d
e
1
9
4
m
en
an
d
1
0
5
w
o
m
en
a
n
d
th
e
r
an
g
e
o
f
th
e
ir
ag
e
s
b
et
w
ee
n
4
0
an
d
9
5
y
ea
r
s
o
ld
.
Featu
r
es,
m
ea
s
u
r
e
m
e
n
t
s
,
an
d
r
an
g
e
ar
e
lis
ted
in
T
ab
le
1
.
T
ab
le
1
.
Featu
r
es,
m
ea
s
u
r
e
m
e
n
t,
m
ea
n
i
n
g
,
a
n
d
r
an
g
e
o
f
th
e
d
ataset
F
e
a
t
u
r
e
Ex
p
l
a
n
a
t
i
o
n
M
e
a
su
r
e
me
n
t
R
a
n
g
e
A
g
e
A
g
e
o
f
t
h
e
p
a
t
i
e
n
t
y
e
a
r
s
[
4
0
,
…,
9
5
]
A
n
a
e
mi
a
D
e
c
r
e
a
se
o
f
r
e
d
b
l
o
o
d
c
e
l
l
s o
r
h
e
mo
g
l
o
b
i
n
B
o
o
l
e
a
n
0
,
1
H
i
g
h
b
l
o
o
d
p
r
e
ssu
r
e
I
f
t
h
e
p
a
t
i
e
n
t
h
a
s
h
y
p
e
r
t
e
n
si
o
n
B
o
o
l
e
a
n
0,
1
C
r
e
a
t
i
n
i
n
e
p
h
o
sp
h
o
k
i
n
a
se
(
C
P
K
)
L
e
v
e
l
o
f
t
h
e
C
P
K
e
n
z
y
me
i
n
t
h
e
b
l
o
o
d
mcg
/
L
[
2
3
,
.
.
.
.
,
7
8
6
1
]
D
i
a
b
e
t
e
s
I
f
t
h
e
p
a
t
i
e
n
t
h
a
s
d
i
a
b
e
t
e
s
B
o
o
l
e
a
n
0
,
1
Ej
e
c
t
i
o
n
f
r
a
c
t
i
o
n
P
e
r
c
e
n
t
a
g
e
o
f
b
l
o
o
d
l
e
a
v
i
n
g
t
h
e
h
e
a
r
t
a
t
e
a
c
h
c
o
n
t
r
a
c
t
i
o
n
%
[
1
4
,
.
.
.
,
8
0
]
S
e
x
P
l
a
t
e
l
e
t
s i
n
t
h
e
b
l
o
o
d
b
i
n
a
r
y
0
,
1
P
l
a
t
e
l
e
t
s
w
o
man
o
r
man
k
i
l
o
p
l
a
t
e
l
e
t
s/
mL
[
2
5
.
0
1
,
.
.
.
,
8
5
0
.
0
0
]
S
e
r
u
m c
r
e
a
t
i
n
i
n
e
L
e
v
e
l
o
f
se
r
u
m c
r
e
a
t
i
n
i
n
e
i
n
t
h
e
b
l
o
o
d
mg
/
d
L
[
0
.
5
0
,
…
9
.
4
0
]
S
e
r
u
m so
d
i
u
m
L
e
v
e
l
o
f
se
r
u
m so
d
i
u
m
i
n
t
h
e
b
l
o
o
d
mEq
/
L
[
1
1
4
,
.
.
.
,
1
4
8
]
S
mo
k
i
n
g
I
f
t
h
e
p
a
t
i
e
n
t
smo
k
e
s o
r
n
o
t
B
o
o
l
e
a
n
0
,
1
T
i
me
F
o
l
l
o
w
-
u
p
p
e
r
i
o
d
d
a
y
s
[
4
,
.
.
.
,
2
8
5
]
[
t
a
r
g
e
t
]
d
e
a
t
h
e
v
e
n
t
I
f
t
h
e
p
a
t
i
e
n
t
d
e
c
e
a
se
d
d
u
r
i
n
g
t
h
e
f
o
l
l
o
w
-
u
p
p
e
r
i
o
d
B
o
o
l
e
a
n
0
,
1
2
.
2
.
D
a
t
a
P
re
pro
ce
s
s
ing
Fo
r
p
r
ep
r
o
ce
s
s
in
g
d
ata,
w
e
u
s
e
t
h
e
n
o
r
m
al
izatio
n
a
n
d
I
QR
m
et
h
o
d
o
f
o
u
tl
ier
d
etec
t
io
n
.
B
ef
o
r
e
tr
ain
i
n
g
d
ata,
w
e
n
o
r
m
alize
t
h
is
d
ataset
s
i
n
ce
t
h
e
g
r
ad
ien
t
d
escen
t
w
ill
b
e
e
f
f
ec
ti
v
e
w
it
h
n
o
r
m
alize
d
(
s
ca
led
)
v
alu
e
s
.
W
e
m
a
y
g
et
t
h
e
v
al
u
e
s
in
t
h
e
d
if
f
er
en
t
s
ca
les
i
f
w
e
w
o
u
ld
n
o
t
n
o
r
m
al
ize
th
e
d
ata.
T
o
ad
j
u
s
t
w
ei
g
h
ts
,
o
u
r
m
o
d
el
w
o
u
ld
ta
k
e
m
o
r
e
ti
m
e
to
tr
ai
n
o
n
t
h
is
d
ata.
Ho
w
e
v
er
,
if
w
e
n
o
r
m
al
ize
o
u
r
d
ata
b
y
u
s
i
n
g
n
o
r
m
aliza
t
io
n
tech
n
iq
u
e
s
,
w
e
w
il
l
h
a
v
e
n
u
m
b
er
s
o
n
th
e
s
a
m
e
s
ca
le
w
h
ic
h
w
ill
m
ak
e
o
u
r
m
o
d
el
tr
ain
m
u
c
h
f
aster
an
d
g
r
ad
ien
t
d
esce
n
t
w
i
ll
b
e
ef
f
ec
tiv
e
i
n
th
i
s
ca
s
e.
I
QR
Me
th
o
d
o
f
o
u
tlier
d
etec
tio
n
,
w
h
ic
h
is
u
s
ed
f
o
r
p
r
e
-
p
r
o
ce
s
s
in
g
d
ata
I
QR
(
s
h
o
r
t
f
o
r
“
in
ter
q
u
ar
tile
r
an
g
e”
)
in
th
e
m
id
d
le
s
p
r
ea
d
,
is
also
k
n
o
w
n
as
th
e
q
u
ar
tile
r
an
g
e
o
f
t
h
e
d
ataset.
T
h
is
co
n
c
ep
t is u
s
ed
in
s
tati
s
tical
a
n
al
y
s
is
to
h
elp
co
n
clu
d
e
a
s
et
o
f
n
u
m
b
er
s
.
I
QR
i
s
u
s
ed
f
o
r
th
e
r
an
g
e
o
f
v
ar
ia
tio
n
b
ec
a
u
s
e
it e
x
cl
u
d
es
m
o
s
t o
u
tlier
s
o
f
d
ata.
I
n
Fi
g
u
r
e
1
,
th
e
m
i
n
i
m
u
m
,
m
ax
i
m
u
m
i
s
t
h
e
m
i
n
i
m
u
m
a
n
d
m
a
x
i
m
u
m
v
a
lu
e
in
th
e
d
ataset.
T
h
e
m
ed
ian
i
s
also
ca
lled
th
e
s
ec
o
n
d
q
u
ar
tile
o
f
t
h
e
d
ata.
Q1
is
th
e
f
ir
s
t
q
u
ar
tile
o
f
t
h
e
d
ata,
it
m
ea
n
s
t
h
at
2
5
%
o
f
th
e
d
ata
is
lie
s
b
et
w
ee
n
m
i
n
i
m
u
m
a
n
d
Q1
.
A
n
d
Q3
is
t
h
e
t
h
ir
d
q
u
ar
tile o
f
th
e
d
ata,
it
s
a
y
s
t
h
at
7
5
% o
f
t
h
e
d
ata
lies
b
et
w
ee
n
m
ax
i
m
u
m
a
n
d
Q3
.
T
h
e
eq
u
atio
n
b
elo
w
i
s
t
h
e
I
n
ter
-
Q
u
ar
tile
R
a
n
g
e
o
r
I
QR
,
w
h
ic
h
is
th
e
d
if
f
er
e
n
ce
b
et
w
ee
n
Q3
an
d
Q1
.
Fig
u
r
e
1
.
A
b
o
x
-
w
h
is
k
er
p
lo
t
(
1
)
Fo
r
d
etec
tin
g
th
e
o
u
tl
ier
s
w
it
h
th
i
s
tech
n
iq
u
e,
w
e
h
a
v
e
to
d
ef
in
e
a
n
e
w
r
a
n
g
e,
w
h
ic
h
is
ca
lled
a
d
ec
is
io
n
r
an
g
e.
I
f
an
y
p
o
in
t lie
s
o
u
ts
id
e
t
h
is
r
a
n
g
e,
it i
s
co
n
s
i
d
er
ed
an
o
u
tlier
.
T
h
is
r
an
g
e
is
(
2
)
,
(
3
)
:
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
P
r
ed
ictin
g
h
ea
r
t fa
ilu
r
e
u
s
in
g
a
w
r
a
p
p
er
-
b
a
s
ed
fea
tu
r
e
s
elec
tio
n
(
Min
h
Tu
a
n
Le
)
1533
(
2
)
(
3
)
2
.
3
.
Resea
rc
h
M
e
t
ho
do
lo
g
y
2
.
3
.
1
.
G
re
y
w
o
l
f
o
pti
m
izer
(
G
WO
)
S
w
ar
m
in
telli
g
en
ce
is
t
h
e
w
a
y
o
f
co
m
m
u
n
icatio
n
b
etw
ee
n
an
in
d
i
v
id
u
al
a
n
d
a
g
r
o
u
p
.
T
h
e
ap
p
licatio
n
o
f
h
er
d
i
n
telli
g
e
n
c
e
in
t
h
e
f
ield
s
o
f
i
n
d
u
s
tr
y
,
s
cie
n
ce
,
an
d
co
m
m
er
ce
h
as
m
a
n
y
u
n
iq
u
e
a
n
d
d
iv
er
s
e
ap
p
licatio
n
s
.
R
e
s
ea
r
ch
i
n
h
er
d
in
telli
g
en
ce
ca
n
h
elp
p
eo
p
le
m
a
n
ag
e
co
m
p
lex
s
y
s
te
m
s
.
GW
O
s
i
m
u
late
s
t
h
e
w
a
y
t
h
at
t
h
e
w
o
l
v
es
lo
o
k
f
o
r
f
o
o
d
an
d
s
u
r
v
i
v
e
b
y
av
o
id
in
g
t
h
eir
en
e
m
ie
s
(
Fi
g
u
r
e
2
)
.
GW
O
w
as
f
ir
s
t
l
y
in
tr
o
d
u
ce
d
b
y
Mir
j
alili
et
a
l
.
,
2
0
1
4
[
2
5
]
.
A
lp
h
a
m
ea
n
s
t
h
at
t
h
e
lead
er
g
i
v
es
th
e
d
ec
is
io
n
f
o
r
a
s
leep
in
g
p
lace
,
h
u
n
ti
n
g
g
r
e
y
,
ti
m
e
to
w
a
k
e
u
p
.
T
h
e
s
ec
o
n
d
lev
e
l
o
f
g
r
a
y
w
o
l
v
es
is
b
eta.
T
h
e
b
etas
ar
e
th
e
w
o
lv
e
s
i
n
h
er
d
s
u
n
d
er
alp
h
a
b
u
t
al
s
o
co
m
m
a
n
d
ed
an
o
th
er
lo
w
-
lev
el
w
o
l
f
.
T
h
e
lo
w
e
s
t
r
an
k
a
m
o
n
g
t
h
e
g
r
a
y
w
o
l
v
e
s
is
O
m
eg
a.
T
h
ey
ar
e
w
ea
k
w
o
l
v
es
a
n
d
h
a
v
e
to
r
el
y
o
n
o
th
er
w
o
lv
e
s
in
t
h
e
p
ac
k
.
Delta
o
n
es
ar
e
d
ep
en
d
en
t
o
n
alp
h
as
a
n
d
b
etas,
b
u
t
t
h
e
y
ar
e
m
o
r
e
e
f
f
ec
t
iv
e
t
h
a
n
o
m
e
g
a.
T
h
e
y
ar
e
r
esp
o
n
s
ib
le
f
o
r
m
o
n
ito
r
in
g
ter
r
ito
r
ial
b
o
u
n
d
ar
ies
a
n
d
w
ar
n
in
g
in
s
id
e
i
n
ca
s
e
o
f
d
an
g
er
,
p
r
o
tect
a
n
d
en
s
u
r
e
s
a
f
e
t
y
f
o
r
h
er
d
s
,
tak
e
ca
r
e
o
f
th
e
w
ea
k
,
a
n
d
il
ln
e
s
s
w
o
l
v
es i
n
th
e
p
ac
k
.
Fig
u
r
e
2
.
P
o
s
itio
n
u
p
d
atin
g
in
GW
O
T
o
d
ev
elo
p
th
e
m
at
h
e
m
atica
l
m
o
d
el,
t
h
e
b
est
s
o
lu
tio
n
is
co
n
s
id
er
ed
as
alp
h
a.
B
eta
an
d
d
elta
ar
e
th
e
s
ec
o
n
d
an
d
th
e
t
h
ir
d
s
o
lu
t
io
n
,
r
esp
ec
tiv
el
y
.
T
h
e
s
tep
o
f
GW
O
is
en
cir
cli
n
g
p
r
e
y
is
s
h
o
w
n
(
4
)
,
(
5
)
:
)
(
4
)
(
5
)
w
h
er
e
t
s
h
o
w
s
t
h
e
c
u
r
r
en
t iter
atio
n
,
an
d
ar
e
co
ef
f
icie
n
t
v
ec
to
r
s
,
is
t
h
e
p
o
s
itio
n
v
ec
to
r
o
f
a
g
r
e
y
w
o
l
f
an
d
is
th
e
p
o
s
itio
n
v
ec
to
r
o
f
th
e
p
r
e
y
.
T
h
e
co
ef
f
i
cie
n
t i
s
in
d
icate
d
in
t
h
e
(
6
)
,
(
7
)
:
)
(
6
)
(
7
)
w
h
er
e
is
li
n
ea
r
l
y
d
ec
r
ea
s
ed
f
r
o
m
2
to
0
,
an
d
ar
e
r
an
d
o
m
v
e
cto
r
in
[
0
,
1
]
.
T
h
ese
eq
u
atio
n
s
b
elo
w
d
ef
i
n
e
th
e
f
in
al
p
o
s
itio
n
o
f
t
h
e
w
o
lf
:
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
21
,
No
.
3
,
Ma
r
ch
2
0
2
1
:
1
5
3
0
-
1
5
3
9
1534
(
8
)
(
9
)
(
1
0
)
(
1
1
)
(
1
2
)
(
1
3
)
(
1
4
)
2
.
3
.
2
.
M
ultila
y
er
p
er
ce
ptr
o
n
(
M
L
P
)
T
h
e
s
in
g
le
-
la
y
er
p
er
ce
p
tr
o
n
s
o
lv
es
o
n
l
y
li
n
ea
r
l
y
s
ep
ar
ab
le
p
r
o
b
lem
s
,
b
u
t
s
o
m
e
co
m
p
le
x
p
r
o
b
lem
s
ar
e
n
o
t
li
n
ea
r
l
y
s
ep
ar
ab
le.
T
h
er
ef
o
r
e,
in
o
r
d
er
to
s
o
lv
e
s
o
m
e
co
m
p
le
x
p
r
o
b
le
m
s
,
o
n
e
o
r
m
o
r
e
la
y
er
s
ar
e
ad
d
ed
in
a
s
i
n
g
le
la
y
er
p
er
ce
p
tr
o
n
,
s
o
it
is
k
n
o
w
n
as
a
m
u
lti
la
y
er
p
er
ce
p
tr
o
n
(
ML
P
)
[
3
0
-
3
3
]
.
T
h
e
ML
P
n
et
w
o
r
k
is
also
k
n
o
w
n
as a
f
ee
d
-
f
o
r
w
ar
d
n
eu
r
al
n
et
w
o
r
k
h
av
i
n
g
o
n
e
o
r
m
o
r
e
h
id
d
en
la
y
er
s
as c
an
b
e
s
ee
n
in
F
ig
u
r
e
3
.
F
ig
u
r
e
3
.
T
h
e
A
r
ch
itect
u
r
e
o
f
a
m
u
l
tila
y
er
p
er
ce
p
tr
o
n
I
n
F
i
g
u
r
e
3
,
th
e
n
eu
r
al
n
et
w
o
r
k
h
as
an
in
p
u
t
la
y
er
w
i
th
n
n
e
u
r
o
n
s
,
o
n
e
h
id
d
en
la
y
er
w
i
th
n
n
eu
r
o
n
s
,
an
d
an
o
u
tp
u
t la
y
er
I
n
p
u
t la
y
er
: c
all
in
p
u
t v
ar
iab
le
(
x
1
,
…,
x
n
)
,
also
ca
lled
th
e
v
is
ib
le
la
y
er
Hid
d
e
n
la
y
er
: t
h
e
la
y
er
o
f
t
h
e
n
o
d
e
lies
b
et
w
ee
n
t
h
e
in
p
u
t a
n
d
o
u
tp
u
t la
y
er
.
Ou
tp
u
t la
y
er
: t
h
is
la
y
er
p
r
o
d
u
ce
s
th
e
o
u
tp
u
t v
ar
iab
le
s
T
h
e
f
o
llo
w
in
g
s
tep
s
b
elo
w
s
h
o
w
t
h
e
ca
lcu
latio
n
o
f
th
e
M
L
P
o
u
tp
u
t
a
f
ter
g
i
v
i
n
g
t
h
e
w
ei
g
h
ts
,
in
p
u
ts
,
an
d
b
iases
:
T
h
e
w
eig
h
ted
s
u
m
s
o
f
i
n
p
u
t
s
a
r
e
ca
lcu
lated
as f
o
llo
w
:
(
1
5
)
w
h
er
e
s
h
o
w
s
th
e
th
in
p
u
t,
r
ep
r
esen
t
th
e
n
u
m
b
er
o
f
n
o
d
es,
is
th
e
co
n
n
ec
tio
n
w
ei
g
h
t
f
r
o
m
th
e
th
n
o
d
e
to
th
e
th
n
o
d
e
an
d
is
th
e
t
h
r
es
h
o
ld
o
f
th
e
h
id
d
en
n
o
d
e.
T
h
e
ca
lcu
latio
n
o
f
t
h
e
o
u
tp
u
t
o
f
ea
ch
h
id
d
en
n
o
d
e:
(
1
6
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
P
r
ed
ictin
g
h
ea
r
t fa
ilu
r
e
u
s
in
g
a
w
r
a
p
p
er
-
b
a
s
ed
fea
tu
r
e
s
elec
tio
n
(
Min
h
Tu
a
n
Le
)
1535
T
h
e
f
in
al
o
u
tp
u
ts
ar
e
b
ased
o
n
th
e
ca
lcu
la
tio
n
o
f
t
h
e
o
u
tp
u
t o
f
h
id
d
en
n
o
d
es:
(
1
7
)
(
1
8
)
w
h
er
e
is
t
h
e
co
n
n
ec
t
io
n
w
ei
g
h
t f
r
o
m
to
an
d
is
th
e
t
h
r
es
h
o
l
d
o
f
th
e
o
u
tp
u
t
n
o
d
e.
Fo
r
th
e
d
ef
i
n
it
io
n
o
f
t
h
e
f
in
al
o
u
tp
u
t,
t
h
e
w
ei
g
h
ts
a
n
d
b
iase
s
ar
e
u
s
ed
.
W
e
f
in
d
t
h
e
v
al
u
es
f
o
r
w
ei
g
h
t
s
an
d
b
iases
to
ac
h
ie
v
e
a
r
elati
o
n
s
h
ip
b
et
w
ee
n
th
e
in
p
u
ts
an
d
o
u
tp
u
ts
.
I
n
t
h
i
s
al
g
o
r
ith
m
,
w
ei
g
h
ts
an
d
b
iase
s
h
av
e
b
ee
n
ad
j
u
s
ted
r
ep
ea
ted
l
y
f
o
r
m
i
n
i
m
izi
n
g
t
h
e
ac
t
u
al
o
u
tp
u
t v
ec
to
r
o
f
t
h
e
n
et
w
o
r
k
an
d
o
u
tp
u
t
v
ec
to
r
.
3.
RE
SU
L
T
S
A
ND
AN
AL
Y
SI
S
3
.
1
.
P
er
f
o
rm
a
nce
E
v
a
lua
t
io
n
I
n
th
i
s
s
y
s
te
m
,
th
e
p
er
f
o
r
m
an
c
e
o
f
th
ese
al
g
o
r
ith
m
s
i
s
s
t
u
d
ie
d
b
ased
o
n
p
er
f
o
r
m
an
ce
m
etr
i
cs
s
u
c
h
as
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
F1
s
co
r
e,
w
h
ich
ar
e
g
i
v
e
n
in
t
h
es
e
(
1
9
-
22)
:
(
1
9
)
(
2
0
)
(
2
1
)
(
2
2
)
W
h
er
e:
a
tr
u
e
p
o
s
itiv
e
(
T
P
)
: th
e
s
a
m
p
les ar
e
clas
s
i
f
ied
as tr
u
e
(
T
)
w
h
ile
t
h
e
y
ar
e
(
T
)
; a
t
r
u
e
n
eg
at
iv
e
(
T
N)
: th
e
s
a
m
p
les
ar
e
cla
s
s
i
f
ied
as
f
alse
(
F)
w
h
ile
t
h
e
y
ar
e
(
F);
a
f
als
e
p
o
s
itiv
e
(
FP
)
:
th
e
s
a
m
p
les
a
r
e
class
i
f
ied
a
s
(
T
)
w
h
ile
t
h
e
y
ar
e
(
F);
A
f
a
ls
e
n
eg
ativ
e
(
FN)
: t
h
e
s
a
m
p
les ar
e
cla
s
s
i
f
ied
as (
F)
w
h
i
le
th
e
y
ar
e
(
T
)
.
3
.
2
.
Ana
ly
s
is
Resul
t
s
Usi
ng
Va
rio
us
M
a
chine Lea
rning
M
o
dels
I
n
th
i
s
r
esear
ch
,
s
i
x
class
i
f
ie
r
m
o
d
els
L
R
,
KNN,
SV
M,
NB
,
D
T
,
R
FC
ar
e
u
s
ed
.
T
h
e
d
ataset
is
d
iv
id
ed
in
to
8
0
:2
0
,
w
h
ic
h
is
8
0
%
o
f
d
ata
f
o
r
tr
ain
i
n
g
t
h
e
m
o
d
els
an
d
2
0
%
is
u
s
ed
f
o
r
tes
t
in
g
t
h
e
ac
cu
r
ac
y
o
f
th
e
m
o
d
els.
I
n
t
h
i
s
r
esear
ch
,
we
ap
p
ly
t
h
e
r
e
m
o
v
a
l o
f
th
e
o
u
tl
ier
d
ataset
f
o
r
tr
ain
i
n
g
.
T
h
e
b
ar
ch
ar
t
in
th
e
F
i
g
u
r
e
4
in
d
icate
s
t
h
e
ac
cu
r
ac
y
o
f
m
ac
h
in
e
lear
n
i
n
g
alg
o
r
ith
m
s
.
As
ca
n
b
e
s
ee
n
f
r
o
m
t
h
e
f
ig
u
r
e
t
h
at
t
h
e
r
an
d
o
m
f
o
r
est
cla
s
s
i
f
ier
i
s
h
a
v
i
n
g
th
e
h
ig
h
es
t
ac
cu
r
ac
y
w
it
h
8
5
%
co
m
p
ar
ed
to
th
e
o
th
er
alg
o
r
ith
m
s
.
L
R
also
ac
h
i
ev
es
g
o
o
d
ac
cu
r
ac
y
a
s
co
m
p
ar
ed
to
SVM.
Fig
u
r
e
4
.
C
lass
if
ica
tio
n
ac
c
u
r
ac
y
w
it
h
d
if
f
er
en
t
m
o
d
els
T
ab
le
2
in
d
icate
s
th
e
class
i
f
ic
atio
n
r
esu
lt
s
o
f
t
h
e
s
ix
m
o
d
els
b
ased
o
n
ac
cu
r
ac
y
,
r
ec
all,
p
r
ec
is
io
n
,
F
1
s
co
r
e
o
n
th
e
h
ea
r
t
f
ai
lu
r
e
d
ata
s
et.
I
t
ca
n
b
e
s
ee
n
o
n
t
h
e
tab
l
e
th
at,
a
m
o
n
g
th
e
s
i
x
m
eth
o
d
s
,
th
e
R
F
C
m
e
th
o
d
p
er
f
o
r
m
s
t
h
e
b
est
p
er
f
o
r
m
a
n
c
e,
w
it
h
t
h
e
h
ig
h
es
t
ac
cu
r
ac
y
8
5
%,
6
5
.
2
1
%
r
ec
all,
9
3
.
7
5
%
p
r
ec
is
io
n
,
a
n
d
7
6
%
F
1
s
co
r
e
th
an
t
h
e
o
th
er
m
ac
h
i
n
e
l
ea
r
n
in
g
m
o
d
els.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
21
,
No
.
3
,
Ma
r
ch
2
0
2
1
:
1
5
3
0
-
1
5
3
9
1536
T
ab
le
2
.
T
h
e
p
r
e
d
ictio
n
r
esu
l
t
s
ID
M
e
t
h
o
d
A
c
c
u
r
a
c
y
R
e
c
a
l
l
P
r
e
c
i
si
o
n
F
1
sco
r
e
1
LR
0
.
8
0
0
.
4
7
8
2
1
0
.
6
4
7
0
2
K
N
N
0
.
7
5
0
.
4
7
8
2
0
.
7
8
5
7
0
.
5
9
4
5
3
S
V
M
0
.
8
0
0
.
4
7
8
2
1
0
.
6
4
7
0
4
N
B
C
0
.
6
8
3
3
0
.
3
0
4
3
0
.
7
0
.
4
2
4
2
5
DT
0
.
7
6
6
7
0
.
6
0
8
6
0
.
7
3
6
8
0
.
6
6
6
6
6
R
F
C
0
.
8
5
0
.
6
5
2
1
0
.
9
3
7
5
0
.
7
6
9
2
Fig
u
r
e
5
s
h
o
w
s
t
h
e
co
n
f
u
s
io
n
m
atr
ix
o
f
all
al
g
o
r
ith
m
s
.
T
h
e
d
iag
o
n
al
ele
m
e
n
t
s
o
f
th
e
m
at
r
ix
ar
e
th
e
co
r
r
ec
tly
clas
s
i
f
ied
n
u
m
b
er
o
f
p
o
in
ts
f
o
r
ea
c
h
d
ata
la
y
er
.
Fr
o
m
h
er
e,
t
h
e
ac
c
u
r
ac
y
ca
n
b
e
in
f
er
r
ed
b
y
t
h
e
s
u
m
o
f
th
e
ele
m
e
n
ts
o
n
t
h
e
d
iag
o
n
al
d
iv
id
ed
b
y
t
h
e
s
u
m
o
f
th
e
e
le
m
e
n
ts
o
f
t
h
e
e
n
tire
m
atr
i
x
.
A
g
o
o
d
m
o
d
el
w
ill
g
iv
e
a
co
n
f
u
s
io
n
m
atr
i
x
w
it
h
th
e
ele
m
en
t
s
o
n
th
e
m
ai
n
d
iag
o
n
al
h
a
v
i
n
g
a
b
ig
v
a
lu
e
an
d
th
e
r
e
m
ain
in
g
ele
m
e
n
ts
h
a
v
i
n
g
a
s
m
all
v
al
u
e.
I
t
ca
n
b
e
s
ee
n
f
r
o
m
t
h
e
co
n
f
u
s
io
n
m
atr
i
x
t
h
at
t
h
e
m
ai
n
d
i
ag
o
n
al
ele
m
e
n
t
s
o
f
th
e
m
a
tr
ix
o
f
L
R
,
SV
M,
an
d
R
FC
h
a
v
e
a
h
ig
h
er
v
al
u
e.
Fig
u
r
e
5
.
C
o
n
f
u
s
io
n
m
atr
ix
o
f
all
alg
o
r
ith
m
s
T
h
e
r
ec
eiv
er
o
p
e
r
atin
g
ch
ar
a
cter
is
tic
(
R
O
C
)
p
lo
t
is
a
m
e
asu
r
e
m
en
t
f
o
r
ev
al
u
ati
n
g
t
h
e
class
i
f
ier
p
er
f
o
r
m
a
n
ce
o
f
ea
c
h
alg
o
r
it
h
m
,
as s
h
o
w
n
i
n
Fi
g
u
r
e
6
.
Fig
u
r
e
6
.
R
ec
eiv
er
o
p
er
atin
g
c
h
ar
ac
ter
is
tic
(
R
OC
)
o
f
all
al
g
o
r
ith
m
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
P
r
ed
ictin
g
h
ea
r
t fa
ilu
r
e
u
s
in
g
a
w
r
a
p
p
er
-
b
a
s
ed
fea
tu
r
e
s
elec
tio
n
(
Min
h
Tu
a
n
Le
)
1537
3
.
3
.
E
x
peri
m
ent
a
l R
es
ults o
f
G
WO
-
M
L
P
I
n
th
i
s
w
o
r
k
,
w
e
s
h
o
w
t
h
e
ex
p
er
im
e
n
tal
r
es
u
lt
w
h
e
n
g
r
e
y
w
o
l
f
o
p
ti
m
izat
io
n
is
ap
p
lied
t
o
m
u
lt
ila
y
er
p
er
ce
p
tr
o
n
(
GW
O
-
ML
P
)
.
T
h
e
T
ab
le
3
s
h
o
w
s
th
e
s
a
m
p
les o
f
th
e
s
elec
ted
f
ea
tu
r
e
u
s
in
g
g
r
ey
w
o
l
f
o
p
ti
m
iza
tio
n
an
d
Fig
u
r
e
7
s
h
o
w
s
C
o
n
v
er
g
e
n
ce
cu
r
v
e
o
f
th
e
f
it
n
es
s
f
u
n
cti
o
n
.
T
ab
le
3
.
Sam
p
les o
f
f
ea
t
u
r
e
s
e
lectio
n
ID
F
e
a
t
u
r
e
F
e
a
t
u
r
e
se
l
e
c
t
i
o
n
1
a
g
e
S
e
l
e
c
t
e
d
2
a
n
a
e
m
i
a
S
e
l
e
c
t
e
d
3
c
r
e
a
t
i
n
i
n
e
_
p
h
o
s
p
h
o
k
i
n
a
se
x
4
d
i
a
b
e
t
e
s
x
5
e
j
e
c
t
i
o
n
_
f
r
a
c
t
i
o
n
S
e
l
e
c
t
e
d
6
h
i
g
h
_
b
l
o
o
d
_
p
r
e
ssu
r
e
S
e
l
e
c
t
e
d
7
p
l
a
t
e
l
e
t
s
x
8
se
r
u
m_
c
r
e
a
t
i
n
i
n
e
x
9
se
r
u
m_
so
d
i
u
m
x
10
se
x
S
e
l
e
c
t
e
d
11
smo
k
i
n
g
x
12
t
i
me
S
e
l
e
c
t
e
d
Fig
u
r
e
7
.
C
o
n
v
er
g
en
ce
c
u
r
v
e
o
f
th
e
f
it
n
ess
f
u
n
c
tio
n
W
e
ca
n
s
ee
th
at
6
o
f
th
e
1
2
f
ea
tu
r
es
ar
e
s
elec
ted
.
Af
ter
th
at,
th
is
s
u
b
s
et
o
f
f
ea
tu
r
es
i
s
tr
ain
ed
o
n
th
e
ML
P
w
it
h
1
0
0
ep
o
ch
s
,
w
h
ic
h
y
ield
s
th
e
f
o
llo
w
in
g
r
es
u
lt
in
Fig
u
r
e
8
.
I
n
t
h
is
ap
p
r
o
ac
h
,
t
h
e
p
er
f
o
r
m
a
n
ce
o
f
GW
O
-
M
L
P
ac
h
ie
v
ed
8
7
%
o
f
ac
cu
r
ac
y
,
7
4
%
r
ec
all,
7
7
%
p
r
ec
is
io
n
,
an
d
7
6
%
F1
s
co
r
e.
W
ith
th
is
ap
p
r
o
ac
h
,
o
n
l
y
s
ix
o
u
t
o
f
t
h
e
o
r
ig
i
n
al
t
welv
e
f
ea
tu
r
e
s
w
er
e
s
elec
ted
,
th
e
ac
cu
r
ac
y
o
f
th
e
GW
O
-
M
L
P
m
o
d
el
w
a
s
h
ig
h
er
th
an
t
h
e
o
th
er
m
et
h
o
d
s
,
in
d
i
ca
tin
g
t
h
er
e
w
er
e
u
n
u
s
e
f
u
l
f
ea
t
u
r
es
in
th
e
d
ata.
Fu
r
t
h
er
m
o
r
e,
t
h
e
tr
ai
n
in
g
t
i
m
e
o
f
th
is
d
ata
is
lo
w
er
t
h
an
t
h
e
o
th
e
r
m
o
d
els.
(
a)
(
b
)
Fig
u
r
e
8
.
(
a)
T
r
ain
in
g
a
n
d
Valid
atio
n
ac
cu
r
ac
y
r
es
u
lt,
(
b
)
T
r
ain
i
n
g
a
n
d
Valid
atio
n
lo
s
s
r
es
u
lt
4.
CO
NCLU
SI
O
N
I
n
th
is
p
ap
er
,
w
e
p
r
o
p
o
s
e
a
m
ac
h
in
e
lear
n
in
g
m
o
d
el
to
p
r
ed
i
ct
h
ea
r
t
f
ail
u
r
e
u
s
i
n
g
a
n
ANN.
A
t
f
ir
s
t,
a
w
r
ap
p
er
-
b
ased
f
ea
t
u
r
e
s
e
lecti
o
n
ap
p
r
o
ac
h
u
s
i
n
g
a
m
etah
e
u
r
is
tic
ca
lled
GW
O
to
s
elec
t
6
f
ea
t
u
r
es
o
u
t
o
f
t
h
e
o
r
ig
in
al
1
2
f
ea
tu
r
e
s
.
T
h
ese
f
e
atu
r
es
ar
e
u
s
ed
as
in
p
u
ts
f
o
r
th
e
M
L
P
f
o
r
t
h
e
p
r
ed
ictio
n
t
ask
.
O
u
r
p
r
o
p
o
s
ed
r
esu
lt
s
ac
h
iev
e
an
ac
cu
r
ac
y
o
f
8
7
%,
w
h
ic
h
s
h
o
w
s
t
h
at
o
u
r
ap
p
r
o
ac
h
o
u
tp
er
f
o
r
m
ed
o
th
e
r
m
ac
h
in
e
lear
n
i
n
g
m
o
d
el
s
s
u
c
h
a
s
SV
M,
L
R
,
K
NN,
NB
C
,
DT
,
R
F
C
.
F
u
r
t
h
er
m
o
r
e,
w
it
h
f
e
w
er
f
ea
tu
r
e
s
,
o
u
r
m
ac
h
in
e
lear
n
i
n
g
m
o
d
el
is
m
u
c
h
s
i
m
p
ler
an
d
r
eq
u
ir
es
m
u
c
h
le
s
s
co
m
p
u
tati
o
n
al
e
f
f
o
r
t.
P
o
ten
tial
f
u
t
u
r
e
w
o
r
k
s
ar
e
l
is
ted
a
s
f
o
llo
w
s
:
f
in
e
-
t
u
n
in
g
th
e
M
L
P
ar
ch
itect
u
r
e,
i.e
th
e
n
u
m
b
er
o
f
h
id
d
en
la
y
er
s
an
d
h
id
d
en
n
o
d
es,
as
w
ell
as
th
e
ac
tiv
atio
n
f
u
n
ctio
n
s
;
o
r
o
p
tim
izin
g
th
e
p
ar
a
m
eter
s
o
f
t
h
e
f
ea
tu
r
e
s
elec
tio
n
alg
o
r
it
h
m
f
o
r
ac
h
iev
i
n
g
a
b
etter
p
er
f
o
r
m
a
n
ce
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
21
,
No
.
3
,
Ma
r
ch
2
0
2
1
:
1
5
3
0
-
1
5
3
9
1538
RE
F
E
R
E
NC
E
S
[1
]
T
.
Ee,
P
.
T
g
,
K.
G
s,
N.
Kk
,
a
n
d
F
.
Di,
“
He
a
rt
F
a
il
u
re
:
Dia
g
n
o
sis,
S
e
v
e
rit
y
Esti
m
a
ti
o
n
a
n
d
P
r
e
d
icti
o
n
o
f
A
d
v
e
rse
Ev
e
n
ts
T
h
ro
u
g
h
M
a
c
h
in
e
L
e
a
rn
in
g
Tec
h
n
iq
u
e
s.,
”
Co
mp
u
t
S
tr
u
c
t
Bi
o
tec
h
n
o
l
J
,
v
o
l.
1
5
,
p
p
.
2
6
–
4
7
,
No
v
.
2
0
1
6
,
d
o
i:
1
0
.
1
0
1
6
/
j.
c
sb
j.
2
0
1
6
.
1
1
.
0
0
1
.
[2
]
L
.
Hu
ss
a
in
,
I.
A
.
Aw
a
n
,
W
.
Az
iz,
S
.
S
a
e
e
d
,
a
n
d
A
.
A
li
,
“
De
t
e
c
ti
n
g
Co
n
g
e
stiv
e
He
a
rt
F
a
il
u
re
b
y
Ex
tr
a
c
ti
n
g
M
u
lt
im
o
d
a
l
F
e
a
tu
re
s
a
n
d
Em
p
lo
y
in
g
M
a
c
h
in
e
L
e
a
rn
in
g
T
e
c
h
n
iq
u
e
s,”
Bi
o
M
e
d
Res
e
a
rc
h
In
ter
n
a
ti
o
n
a
l
,
v
o
l.
2
0
2
0
,
p
p
.
1
–
1
9
,
2
0
2
0
,
d
o
i:
h
tt
p
s:/
/d
o
i.
o
r
g
/1
0
.
1
1
5
5
/
2
0
2
0
/
4
2
8
1
2
4
3
.
[3
]
Y.
L
e
Cu
n
,
Y.
Be
n
g
io
,
a
n
d
G
.
Hin
to
n
,
“
De
e
p
lea
rn
in
g
,
”
Na
tu
re
,
v
o
l.
5
2
1
,
n
o
.
7
5
5
3
,
A
rt
.
n
o
.
7
5
5
3
,
M
a
y
2
0
1
5
,
d
o
i
:
1
0
.
1
0
3
8
/
n
a
tu
re
1
4
5
3
9
.
[4
]
M
.
Ru
n
g
ru
a
n
g
a
n
u
k
u
l
a
n
d
T
.
S
ir
i
b
o
rv
o
r
n
ra
tan
a
k
u
l,
“
De
e
p
L
e
a
rn
in
g
Ba
se
d
G
e
stu
re
Clas
si
f
ica
ti
o
n
f
o
r
Ha
n
d
P
h
y
sic
a
l
T
h
e
ra
p
y
In
tera
c
ti
v
e
P
ro
g
ra
m
,
”
in
Dig
it
a
l
Hu
m
a
n
M
o
d
e
li
n
g
a
n
d
A
p
p
li
c
a
ti
o
n
s
i
n
He
a
lt
h
,
S
a
f
e
ty
,
Erg
o
n
o
m
ics
a
n
d
Risk
M
a
n
a
g
e
m
e
n
t.
P
o
st
u
re
,
M
o
ti
o
n
a
n
d
He
a
lt
h
,
Ju
l.
2
0
2
0
,
p
p
.
3
4
9
–
3
5
8
,
d
o
i:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
0
3
0
-
4
9
9
0
4
-
4
_
2
6
.
[5
]
C.
S
.
Da
n
g
a
re
a
n
d
S
.
S
.
A
p
te,
“
A
Da
ta
M
in
in
g
A
p
p
ro
a
c
h
f
o
r
P
re
d
i
c
ti
o
n
o
f
He
a
rt
Dise
a
se
Us
in
g
N
e
u
ra
l
Ne
tw
o
rk
s”
,
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
C
o
mp
u
ter
En
g
i
n
e
e
rin
g
a
n
d
T
e
c
h
n
o
lo
g
y
(
IJ
CET
)
,
v
o
l.
3
,
n
o
.
3
,
p
p
.
3
0
–
4
0
,
Oc
t.
2
0
1
2
.
[6
]
S
.
S
m
il
e
y
,
“
Dia
g
n
o
stic
f
o
r
He
a
rt
Dise
a
s
e
w
it
h
M
a
c
h
in
e
L
e
a
rn
in
g
,
”
M
e
d
iu
m
,
J
a
n
.
1
2
,
2
0
2
0
.
h
tt
p
s:/
/t
o
w
a
rd
sd
a
tas
c
ien
c
e
.
c
o
m
/d
i
a
g
n
o
stic
-
f
o
r
-
h
e
a
rt
-
d
ise
a
se
-
w
it
h
-
m
a
c
h
in
e
-
lea
rn
in
g
-
8
1
b
0
6
4
a
3
c
1
d
d
(
a
c
c
e
s
se
d
S
e
p
.
1
9
,
2
0
2
0
).
[7
]
D.
S
h
e
n
,
G
.
W
u
,
a
n
d
H.
-
I
.
S
u
k
,
“
De
e
p
L
e
a
rn
in
g
in
M
e
d
ica
l
I
m
a
g
e
A
n
a
l
y
sis,”
An
n
u
a
l
Rev
iew
o
f
B
io
me
d
ica
l
En
g
i
n
e
e
rin
g
,
v
o
l.
1
9
,
n
o
.
1
,
p
p
.
2
2
1
–
2
4
8
,
2
0
1
7
,
d
o
i:
1
0
.
1
1
4
6
/an
n
u
r
e
v
-
b
io
e
n
g
-
0
7
1
5
1
6
-
0
4
4
4
4
2
.
[8
]
R.
E.
W
rig
h
t,
“
L
o
g
isti
c
re
g
r
e
ss
i
o
n
,
”
in
Rea
d
in
g
a
n
d
u
n
d
e
rs
ta
n
d
i
n
g
mu
lt
iv
a
ria
te
sta
ti
stics
,
W
a
sh
in
g
to
n
,
DC,
US:
Am
e
rica
n
P
sy
c
h
o
lo
g
ica
l
A
s
so
c
iatio
n
,
1
9
9
5
,
p
p
.
2
1
7
–
2
4
4
.
[9
]
V
lad
im
ir
N.
V
a
p
n
ik
,
"
S
tatisti
c
a
l
L
e
a
rn
in
g
T
h
e
o
r
y
"
,
Ca
n
a
d
a
,
A
W
il
e
y
-
In
ters
c
ien
c
e
P
u
b
li
c
a
ti
o
n
,
S
e
p
.
1
9
9
8
[1
0
]
N.
S
.
A
lt
m
a
n
,
“
A
n
In
tro
d
u
c
ti
o
n
t
o
Ke
rn
e
l
a
n
d
Ne
a
re
st
-
Ne
ig
h
b
o
r
N
o
n
p
a
ra
m
e
tri
c
Re
g
re
ss
io
n
:
T
h
e
Am
e
rica
n
S
tatisti
c
ian
"
T
h
e
Ame
ric
a
n
S
t
a
ti
sticia
n
:
V
o
l
4
6
,
No
3
,
p
p
.
1
7
5
-
1
8
5
,
A
u
g
.
1
9
9
2
,
[
O
n
li
n
e
]
.
A
v
a
il
a
b
le:
h
tt
p
s:/
/d
o
i.
o
rg
/1
0
.
2
3
0
7
/2
6
8
5
2
0
9
.
[1
1
]
K.
M
.
T
in
g
a
n
d
Z.
Z
h
e
n
g
,
“
I
m
p
ro
v
in
g
th
e
P
e
rf
o
r
m
a
n
c
e
o
f
Bo
o
sti
n
g
f
o
r
Na
iv
e
Ba
y
e
sia
n
Clas
sif
ic
a
ti
o
n
,
”
i
n
M
e
th
o
d
o
lo
g
ies
fo
r
Kn
o
wled
g
e
Disc
o
v
e
ry
a
n
d
Da
ta
M
in
in
g
,
Be
rli
n
,
He
id
e
lb
e
rg
,
1
9
9
9
,
p
p
.
2
9
6
–
3
0
5
,
[
O
n
li
n
e
].
Av
a
il
a
b
le:
h
tt
p
s://
d
o
i.
o
rg
/
1
0
.
1
0
0
7
/3
-
5
4
0
-
4
8
9
1
2
-
6
_
4
1
.
[1
2
]
C.
Ke
rd
v
ib
u
lv
e
c
h
,
“
Hu
m
a
n
Ha
n
d
M
o
ti
o
n
Re
c
o
g
n
it
io
n
Us
in
g
a
n
Ex
ten
d
e
d
P
a
rti
c
le
F
il
ter,”
in
A
rti
c
u
late
d
M
o
ti
o
n
a
n
d
De
f
o
rm
a
b
le Ob
jec
ts,
Ch
a
m
,
2
0
1
4
,
p
p
.
7
1
–
8
0
,
d
o
i:
1
0
.
1
0
0
7
/9
7
8
-
3
-
3
1
9
-
0
8
8
4
9
-
5
_
8
.
[1
3
]
J.
R.
Qu
in
lan
,
“
In
d
u
c
ti
o
n
o
f
d
e
c
isio
n
tree
s”
M
a
c
h
L
e
a
rn
1
,
v
o
l.
1
,
n
o
.
1
,
p
p
.
8
1
–
1
0
6
,
M
a
r.
1
9
8
6
,
[
On
li
n
e
].
Av
a
il
a
b
le:
h
tt
p
s://
d
o
i.
o
rg
/
1
0
.
1
0
0
7
/BF
0
0
1
1
6
2
5
1
.
[1
4
]
L
.
Bre
i
m
a
n
,
“
Ra
n
d
o
m
F
o
re
s
ts,
”
M
a
c
h
in
e
L
e
a
rn
in
g
,
v
o
l.
4
5
,
n
o
.
1
,
p
p
.
5
–
3
2
,
Oc
t.
2
0
0
1
,
d
o
i:
1
0
.
1
0
2
3
/A
:1
0
1
0
9
3
3
4
0
4
3
2
4
[1
5
]
S
.
A
n
g
ra
a
l
e
t
a
l.
,
“
M
a
c
h
in
e
L
e
a
r
n
in
g
P
re
d
icti
o
n
o
f
M
o
rtalit
y
a
n
d
Ho
sp
it
a
li
z
a
ti
o
n
in
He
a
rt
F
a
il
u
re
w
it
h
P
re
se
rv
e
d
Ej
e
c
ti
o
n
F
ra
c
ti
o
n
,
”
J
ACC:
He
a
rt
Fa
il
u
re
,
v
o
l.
8
,
n
o
.
1
,
p
p
.
1
2
–
2
1
,
Ja
n
.
2
0
2
0
,
[
O
n
li
n
e
]
.
A
v
a
il
a
b
le:
h
tt
p
s:/
/d
o
i.
o
rg
/1
0
.
1
0
1
6
/j
.
jch
f
.
2
0
1
9
.
0
6
.
0
1
3
.
[1
6
]
D.
Ch
icc
o
a
n
d
G
.
Ju
rm
a
n
,
“
M
a
c
h
in
e
lea
rn
in
g
c
a
n
p
re
d
ict
su
rv
i
v
a
l
o
f
p
a
ti
e
n
ts
w
it
h
h
e
a
rt
f
a
il
u
re
f
ro
m
se
ru
m
c
re
a
ti
n
in
e
a
n
d
e
jec
ti
o
n
f
ra
c
ti
o
n
a
lo
n
e
,
”
BM
C
M
e
d
ica
l
In
fo
rm
a
ti
c
s
a
n
d
De
c
isio
n
M
a
k
in
g
,
v
o
l
.
2
0
,
n
o
.
1
,
p
.
1
6
,
F
e
b
.
2
0
2
0
,
[
O
n
li
n
e
].
A
v
a
il
a
b
le:
h
tt
p
s://
d
o
i.
o
rg
/1
0
.
1
1
8
6
/s1
2
9
1
1
-
0
2
0
-
1
0
2
3
-
5.
[1
7
]
P
.
C.
A
u
stin
,
J.
V
.
T
u
,
J.
E.
Ho
,
D.
Lev
y
,
a
n
d
D.
S
.
L
e
e
,
“
Us
in
g
m
e
th
o
d
s
f
ro
m
th
e
d
a
ta
-
m
in
in
g
a
n
d
m
a
c
h
in
e
-
lea
rn
in
g
li
tera
tu
re
f
o
r
d
ise
a
se
c
las
sif
ic
a
ti
o
n
a
n
d
p
re
d
ictio
n
:
a
c
a
se
stu
d
y
e
x
a
m
in
in
g
c
las
si
f
ic
a
ti
o
n
o
f
h
e
a
rt
f
a
il
u
re
su
b
ty
p
e
s,”
Jo
u
rn
a
l
o
f
Cli
n
i
c
a
l
Ep
id
e
m
io
lo
g
y
,
v
o
l.
6
6
,
n
o
.
4
,
p
p
.
3
9
8
–
4
0
7
,
A
p
r.
2
0
1
3
,
d
o
i:
1
0
.
1
0
1
6
/
j.
jclin
e
p
i.
2
0
1
2
.
1
1
.
0
0
8
.
[1
8
]
L
.
Yu
a
n
d
H.
L
iu
,
“
Ef
f
icie
n
t
F
e
a
tu
re
S
e
lec
ti
o
n
v
ia
A
n
a
ly
sis
o
f
Re
lev
a
n
c
e
a
n
d
Re
d
u
n
d
a
n
c
y
,
”
T
h
e
J
o
u
r
n
a
l
o
f
M
a
c
h
in
e
L
e
a
r
n
in
g
Res
e
a
rc
h
,
v
o
l.
5
,
p
p
.
1
2
0
5
–
1
2
2
4
,
De
c
.
2
0
0
4
.
[1
9
]
Y.
Ya
n
g
a
n
d
J.
P
e
d
e
rse
n
,
“
A
Co
m
p
a
ra
ti
v
e
S
tu
d
y
o
n
F
e
a
tu
re
S
e
lec
ti
o
n
in
T
e
x
t
Ca
teg
o
riza
ti
o
n
,
”
1
9
9
7
.
[2
0
]
K.
Ya
n
a
n
d
D.
Zh
a
n
g
,
“
F
e
a
tu
re
se
lec
ti
o
n
a
n
d
a
n
a
ly
sis
o
n
c
o
rre
late
d
g
a
s
se
n
so
r
d
a
ta
w
it
h
re
c
u
rsiv
e
f
e
a
tu
re
e
li
m
in
a
ti
o
n
,
”
S
e
n
so
rs
a
n
d
Act
u
a
to
rs
B:
Ch
e
mic
a
l
,
v
o
l.
2
1
2
,
p
p
.
3
5
3
–
3
6
3
,
Ju
n
.
2
0
1
5
,
[
O
n
li
n
e
]
.
A
v
a
il
a
b
le:
h
tt
p
s:/
/d
o
i.
o
rg
/1
0
.
1
0
1
6
/j
.
sn
b
.
2
0
1
5
.
0
2
.
0
2
5
.
[2
1
]
A
.
Ja
in
a
n
d
D.
Zo
n
g
k
e
r,
“
F
e
a
t
u
re
se
lec
ti
o
n
:
e
v
a
lu
a
ti
o
n
,
a
p
p
li
c
a
ti
o
n
,
a
n
d
sm
a
ll
sa
m
p
le
p
e
rf
o
r
m
a
n
c
e
,
”
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
Pa
t
ter
n
An
a
lys
is
a
n
d
M
a
c
h
i
n
e
In
telli
g
e
n
c
e
,
v
o
l.
1
9
,
n
o
.
2
,
p
p
.
1
5
3
–
1
5
8
,
F
e
b
.
1
9
9
7
,
[
O
n
li
n
e
].
Av
a
il
a
b
le:
h
tt
p
s://
d
o
i.
o
rg
/
1
0
.
1
1
0
9
/3
4
.
5
7
4
7
9
7
.
[2
2
]
C.
De
S
tefa
n
o
,
F
.
F
o
n
tan
e
ll
a
,
C.
M
a
rro
c
c
o
,
a
n
d
A
.
S
c
o
tt
o
d
i
F
re
c
a
,
“
A
GA
-
b
a
se
d
f
e
a
tu
re
s
e
lec
ti
o
n
a
p
p
r
o
a
c
h
w
it
h
a
n
a
p
p
li
c
a
ti
o
n
to
h
a
n
d
w
rit
ten
c
h
a
ra
c
ter
re
c
o
g
n
i
ti
o
n
,
”
Pa
tt
e
rn
Rec
o
g
n
it
io
n
L
e
tt
e
rs
,
v
o
l.
3
5
,
p
p
.
1
3
0
–
1
4
1
,
Ja
n
.
2
0
1
4
,
[
On
li
n
e
]
.
A
v
a
il
a
b
le:
h
tt
p
s://
d
o
i.
o
r
g
/1
0
.
1
0
1
6
/j
.
p
a
trec
.
2
0
1
3
.
0
1
.
0
2
6
.
[2
3
]
E.
Zo
ra
r
p
a
c
ı
a
n
d
S
.
A
.
Öz
e
l,
“
A
h
y
b
rid
a
p
p
r
o
a
c
h
o
f
d
if
f
e
re
n
ti
a
l
e
v
o
lu
ti
o
n
a
n
d
a
rti
f
icia
l
b
e
e
c
o
l
o
n
y
f
o
r
fe
a
tu
re
se
lec
ti
o
n
,
”
Exp
e
rt
S
y
ste
ms
wi
th
A
p
p
li
c
a
ti
o
n
s
,
v
o
l
.
6
2
,
p
p
.
9
1
–
1
0
3
,
No
v
.
2
0
1
6
,
[
O
n
li
n
e
]
.
A
v
a
il
a
b
le:
h
tt
p
s:/
/d
o
i.
o
rg
/1
0
.
1
0
1
6
/j
.
e
sw
a
.
2
0
1
6
.
0
6
.
0
0
4
.
[2
4
]
J
.
T
o
o
,
A
.
R.
A
b
d
u
ll
a
h
,
N.
M
o
h
d
S
a
a
d
,
N.
M
o
h
d
A
li
,
a
n
d
W
.
T
e
e
,
“
A
Ne
w
Co
m
p
e
ti
ti
v
e
Bin
a
r
y
G
r
e
y
W
o
lf
Op
ti
m
ize
r
to
S
o
lv
e
th
e
F
e
a
tu
re
S
e
lec
ti
o
n
P
ro
b
lem
in
EM
G
S
ig
n
a
l
s
Clas
si
f
ica
ti
o
n
,
”
Co
mp
u
ter
s
,
v
o
l
.
7
,
n
o
.
4
,
A
rt.
n
o
.
4
,
De
c
.
2
0
1
8
,
[
On
li
n
e
]
.
A
v
a
il
a
b
le:
h
tt
p
s:/
/
d
o
i.
o
rg
/1
0
.
3
3
9
0
/co
m
p
u
ters
7
0
4
0
0
5
8
.
[2
5
]
S
.
M
irj
a
li
li
,
S
.
M
.
M
irj
a
li
li
,
a
n
d
A
.
L
e
w
is,
“
G
re
y
W
o
l
f
Op
ti
m
ize
r,
”
Ad
v
a
n
c
e
s
in
En
g
in
e
e
rin
g
S
o
ft
w
a
re
,
v
o
l.
6
9
,
p
p
.
46
–
6
1
,
M
a
r.
2
0
1
4
,
[
On
li
n
e
]
.
A
v
a
il
a
b
le:
h
tt
p
s://
d
o
i
.
o
rg
/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
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
P
r
ed
ictin
g
h
ea
r
t fa
ilu
r
e
u
s
in
g
a
w
r
a
p
p
er
-
b
a
s
ed
fea
tu
r
e
s
elec
tio
n
(
Min
h
Tu
a
n
Le
)
1539
[2
6
]
E.
Em
a
r
y
,
Ho
ss
a
m
M
.
Za
w
b
a
a
,
“
Bin
a
r
y
G
re
y
W
o
lf
Op
ti
m
iz
a
ti
o
n
A
p
p
ro
a
c
h
e
s
f
o
r
F
e
a
t
u
re
S
e
lec
ti
o
n
”
Ne
u
ro
c
o
mp
u
ti
n
g
,
v
o
l.
1
7
2
,
p
p
.
3
7
1
-
3
8
1
,
Ja
n
.
2
0
1
6
,
[
O
n
li
n
e
]
.
A
v
a
il
a
b
le:
h
tt
p
s:/
/d
o
i.
o
rg
/1
0
.
1
0
1
6
/j
.
n
e
u
c
o
m
.
2
0
1
5
.
0
6
.
0
8
3
.
[2
7
]
L.
-
Y.
Ch
u
a
n
g
,
H.
-
W
.
Ch
a
n
g
,
C.
-
J.
T
u
,
a
n
d
C.
-
H.
Ya
n
g
,
“
Im
p
ro
v
e
d
b
in
a
ry
P
S
O
f
o
r
f
e
a
tu
re
se
lec
t
io
n
u
sin
g
g
e
n
e
e
x
p
re
ss
io
n
d
a
ta”
Co
m
p
u
t
a
ti
o
n
a
l
Bi
o
lo
g
y
a
n
d
Ch
e
mistry
,
v
o
l.
3
2
,
n
o
.
1
,
p
p
.
2
9
–
3
8
,
F
e
b
.
2
0
0
8
,
[
O
n
l
in
e
].
A
v
a
il
a
b
le:
h
tt
p
s:/
/d
o
i.
o
rg
/1
0
.
1
0
1
6
/j
.
c
o
m
p
b
i
o
lch
e
m
.
2
0
0
7
.
0
9
.
0
0
5
.
[2
8
]
M
.
H.
A
g
h
d
a
m
,
N.
G
.
Ag
h
a
e
e
,
M
.
Eh
sa
n
Ba
siri
“
T
e
x
t
fe
a
tu
re
s
e
lec
ti
o
n
u
si
n
g
a
n
t
c
o
l
o
n
y
o
p
ti
m
iza
ti
o
n
"
Exp
e
rt
sy
ste
ms
wit
h
a
p
p
l
ica
ti
o
n
s,
v
o
l.
3
6
,
p
p
.
6
8
4
3
-
6
8
5
3
,
A
p
ril
.
2
0
0
9
,
[
On
li
n
e
]
.
A
v
a
il
a
b
le:
h
tt
p
s:/
/d
o
i.
o
rg
/1
0
.
1
0
1
6
/j
.
e
sw
a
.
2
0
0
8
.
0
8
.
0
2
2
.
[2
9
]
X
.
He
,
Q.
Zh
a
n
g
,
N.
S
u
n
a
n
d
Y.
Do
n
g
,
"
F
e
a
tu
re
S
e
lec
ti
o
n
w
it
h
Disc
re
te
Bin
a
r
y
Di
ff
e
r
e
n
ti
a
l
Ev
o
lu
ti
o
n
,
"
2
0
0
9
In
ter
n
a
t
io
n
a
l
Co
n
fer
e
n
c
e
o
n
Arti
fi
c
ia
l
I
n
telli
g
e
n
c
e
a
n
d
Co
mp
u
ta
ti
o
n
a
l
I
n
telli
g
e
n
c
e
,
p
p
.
3
2
7
-
3
3
0
,
2
0
0
9
,
[
On
li
n
e
].
Av
a
il
a
b
le:
h
tt
p
s://
d
o
i.
o
rg
/
1
0
.
1
1
0
9
/A
ICI.
2
0
0
9
.
4
3
8
.
[3
0
]
M
.
Ja
h
a
n
g
ir,
H.
A
f
z
a
l,
M
.
A
h
m
e
d
,
K.
Kh
u
rs
h
id
a
n
d
R
.
Na
w
a
z
,
"
A
n
e
x
p
e
rt
s
y
ste
m
f
o
r
d
iab
e
tes
p
re
d
ictio
n
u
sin
g
a
u
t
o
tu
n
e
d
m
u
lt
i
-
lay
e
r
p
e
r
c
e
p
tro
n
,
"
2
0
1
7
I
n
telli
g
e
n
t
S
y
ste
ms
Co
n
fer
e
n
c
e
(
In
telli
S
y
s)
,
p
p
.
7
2
2
-
7
2
8
,
2
0
1
7
,
[
O
n
li
n
e
].
Av
a
il
a
b
le:
h
tt
p
s://
d
o
i.
o
rg
/
1
0
.
1
1
0
9
/In
telli
S
y
s.2
0
1
7
.
8
3
2
4
2
0
9
.
[3
1
]
Ja
h
a
n
g
ir,
M
.
,
Af
z
a
l,
H.,
A
h
m
e
d
,
M
.
e
t
a
l
,
"
A
u
to
-
M
e
DiS
in
e
:
a
n
a
u
t
o
-
tu
n
a
b
le
m
e
d
ica
l
d
e
c
isio
n
su
p
p
o
rt
e
n
g
in
e
u
sin
g
a
n
a
u
to
m
a
ted
c
las
s
o
u
tl
ier
d
e
tec
ti
o
n
m
e
th
o
d
a
n
d
A
u
to
M
L
P
,
"
Ne
u
ra
l
Co
mp
u
ti
n
g
a
n
d
A
p
p
li
c
a
ti
o
n
s
,
p
p
.
2
6
2
1
–
2
6
3
3
(2
0
2
0
),
[
On
li
n
e
].
A
v
a
il
a
b
le:
h
tt
p
s
:/
/d
o
i.
o
rg
/
1
0
.
1
0
0
7
/s
0
0
5
2
1
-
0
1
9
-
0
4
1
3
7
-
5
.
[3
2
]
Ch
a
u
d
h
u
ri
,
B.
B.
,
a
n
d
U.
Bh
a
tt
a
c
h
a
ry
a
.
“
E
ff
icie
n
t
T
r
a
in
in
g
a
n
d
Im
p
ro
v
e
d
P
e
rf
o
rm
a
n
c
e
o
f
M
u
lt
il
a
y
e
r
P
e
rc
e
p
tro
n
in
P
a
tt
e
r
n
Clas
sif
ica
ti
o
n
.
”
Ne
u
ro
c
o
mp
u
ti
n
g
,
3
4
,
n
o
.
1
(
S
e
p
tem
b
e
r
1
,
2
0
0
0
):
1
1
–
2
7
.
h
tt
p
s://
d
o
i
.
o
rg
/
1
0
.
1
0
1
6
/
S
0
9
2
5
-
2
3
1
2
(
0
0
)
0
0
3
0
5
-
2
.
[3
3
]
Orh
a
n
,
Um
u
t,
M
a
h
m
u
t
He
k
i
m
,
a
n
d
M
a
h
m
u
t
Oz
e
r.
“
EE
G
S
ig
n
a
ls
Clas
sif
ic
a
ti
o
n
Us
in
g
t
h
e
K
-
M
e
a
n
s
Clu
ste
rin
g
a
n
d
a
M
u
lt
i
lay
e
r
P
e
rc
e
p
tro
n
Ne
u
ra
l
Ne
tw
o
rk
M
o
d
e
l.
”
Exp
e
rt
S
y
ste
m
s
wit
h
Ap
p
li
c
a
ti
o
n
s
,
3
8
,
n
o
.
1
0
(S
e
p
tem
b
e
r
1
5
,
2
0
1
1
):
1
3
4
7
5
–
8
1
.
h
tt
p
s:/
/d
o
i.
o
rg
/
1
0
.
1
0
1
6
/
j.
e
sw
a
.
2
0
1
1
.
0
4
.
1
4
9
.
Evaluation Warning : The document was created with Spire.PDF for Python.