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
.
3
,
J
u
n
e
2
0
2
6
,
p
p
.
2290
~
2
2
9
9
I
SS
N:
2
2
5
2
-
8
9
3
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijai.v
15
.i
3
.
p
p
2
2
9
0
-
2
2
9
9
2290
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
i
.
ia
esco
r
e.
co
m
Co
mbina
tion o
f
b
ina
ry
particle swa
rm o
ptimiza
tion a
nd
ra
ndo
m forest
for
stroke disea
se
pr
ediction
Su
t
ik
no
1
,
Ris
m
iy
a
t
i
1
,
K
ha
dij
a
h
1
,
Abdu
l K
a
rim
2
1
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
mat
i
c
s
,
F
a
c
u
l
t
y
o
f
S
c
i
e
n
c
e
a
n
d
M
a
t
h
e
ma
t
i
c
s,
D
i
p
o
n
e
g
o
r
o
U
n
i
v
e
r
si
t
y
,
S
e
m
a
r
a
n
g
,
I
n
d
o
n
e
si
a
2
C
e
r
e
b
r
o
v
a
sc
u
l
a
r
D
i
se
a
se
R
e
sea
r
c
h
C
e
n
t
e
r
,
H
a
l
l
y
m
U
n
i
v
e
r
si
t
y
,
C
h
u
n
c
h
e
o
n
,
S
o
u
t
h
K
o
r
e
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Sep
1
9
,
2
0
2
4
R
ev
is
ed
Feb
1
2
,
2
0
2
6
Acc
ep
ted
Ap
r
2
0
,
2
0
2
6
S
tro
k
e
is
a
lea
d
in
g
c
a
u
se
o
f
d
e
a
th
a
n
d
d
isa
b
i
li
ty
wo
rl
d
wid
e
,
m
a
k
in
g
e
a
rly
risk
p
re
d
ictio
n
c
rit
ica
l
f
o
r
p
re
v
e
n
ti
o
n
.
M
a
c
h
in
e
lea
rn
in
g
m
e
th
o
d
s
su
c
h
a
s
ra
n
d
o
m
fo
re
st
(RF
)
h
a
v
e
sh
o
wn
s
tro
n
g
p
re
d
icti
v
e
p
e
rfo
rm
a
n
c
e
,
b
u
t
a
c
c
u
ra
c
y
c
a
n
b
e
fu
rt
h
e
r
imp
ro
v
e
d
t
h
ro
u
g
h
e
ffe
c
ti
v
e
fe
a
tu
re
se
lec
ti
o
n
.
Th
is
re
se
a
rc
h
p
ro
p
o
se
s
a
n
in
te
g
ra
ted
m
o
d
e
l
th
a
t
c
o
m
b
i
n
e
s
b
i
n
a
ry
p
a
rti
c
l
e
sw
a
rm
o
p
ti
m
iza
ti
o
n
(BP
S
O)
fo
r
fe
a
t
u
re
se
lec
ti
o
n
wit
h
RF
f
o
r
st
ro
k
e
risk
c
las
sifica
ti
o
n
.
Ex
p
e
rime
n
ts
we
re
c
o
n
d
u
c
ted
o
n
tw
o
p
u
b
l
ic
d
a
t
a
se
ts:
th
e
stro
k
e
p
re
d
ic
ti
o
n
d
a
tas
e
t
(S
P
D)
a
n
d
th
e
b
ra
i
n
stro
k
e
d
a
tas
e
t
(BS
D).
Da
ta
p
re
p
ro
c
e
ss
in
g
in
c
l
u
d
e
d
h
a
n
d
li
n
g
m
issin
g
v
a
l
u
e
s,
n
o
rm
a
li
z
a
ti
o
n
,
a
n
d
t
h
e
sy
n
th
e
ti
c
m
in
o
rit
y
o
v
e
rsa
m
p
li
n
g
tec
h
n
iq
u
e
(
S
M
OTE)
to
m
it
ig
a
te
th
e
m
in
o
rit
y
a
n
d
m
a
jo
rit
y
c
las
se
s.
BP
S
O
wa
s
e
m
p
lo
y
e
d
to
se
lec
t
th
e
m
o
st
in
fo
rm
a
ti
v
e
fe
a
tu
re
s,
f
o
ll
o
we
d
b
y
RF
fo
r
c
las
sifica
ti
o
n
.
T
h
e
BP
S
O
-
RF
m
o
d
e
l
d
e
li
v
e
re
d
su
p
e
ri
o
r
a
c
c
u
ra
c
ies
o
f
9
6
.
1
3
%
o
n
t
h
e
S
P
D
a
n
d
9
6
.
0
7
%
o
n
th
e
BS
D,
o
u
tp
e
rfo
rm
i
n
g
c
o
m
p
e
ti
n
g
c
las
sifiers
a
n
d
fe
a
tu
re
se
lec
ti
o
n
tec
h
n
iq
u
e
s.
Im
p
o
r
tan
t
fe
a
tu
re
s
s
u
c
h
a
s
g
e
n
d
e
r,
a
g
e
,
w
o
rk
t
y
p
e
,
re
sid
e
n
c
e
ty
p
e
,
a
v
e
ra
g
e
g
l
u
c
o
se
lev
e
l,
b
o
d
y
m
a
ss
in
d
e
x
(BM
I)
,
a
n
d
sm
o
k
i
n
g
sta
t
u
s
we
re
c
o
n
siste
n
tl
y
id
e
n
ti
fied
a
s
k
e
y
p
re
d
icto
rs.
T
h
e
se
re
su
lt
s
in
d
ica
te
th
a
t
in
teg
ra
ti
n
g
sw
a
rm
in
tel
li
g
e
n
c
e
with
e
n
se
m
b
le
lea
rn
in
g
c
a
n
e
ffe
c
ti
v
e
ly
imp
ro
v
e
str
o
k
e
ris
k
p
re
d
ictio
n
a
n
d
su
p
p
o
rt
c
li
n
ica
l
d
e
c
isio
n
-
m
a
k
in
g
.
K
ey
w
o
r
d
s
:
B
i
n
a
r
y
p
a
r
t
i
c
l
e
s
w
a
r
m
o
p
t
i
m
i
z
a
t
i
o
n
I
n
teg
r
ated
m
o
d
el
Pre
d
ictio
n
R
an
d
o
m
f
o
r
est
Stro
k
e
d
is
ea
s
e
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
:
Su
tik
n
o
Dep
ar
tm
en
t o
f
I
n
f
o
r
m
atics,
Facu
lty
o
f
Scien
ce
a
n
d
Ma
th
em
a
tics
,
Dip
o
n
eg
o
r
o
Un
iv
er
s
ity
Pro
f
.
J
ac
o
b
R
ais Stre
et,
Sem
ar
an
g
,
C
en
tr
al
J
av
a,
I
n
d
o
n
esia
E
m
ail:
s
u
tik
n
o
@
lectu
r
er
.
u
n
d
ip
.
ac
.
id
1.
I
NT
RO
D
UCT
I
O
N
Stro
k
e
is
d
ea
d
ly
d
is
ea
s
e
th
at
s
ig
n
if
ican
tly
af
f
ec
ts
th
e
q
u
ality
o
f
life
b
y
im
p
air
in
g
p
h
y
s
ical,
co
g
n
itiv
e,
an
d
em
o
tio
n
al
well
-
b
ein
g
.
T
h
e
W
o
r
ld
Hea
lth
Or
g
an
izatio
n
(
W
HO)
r
ep
o
r
ted
th
at
s
tr
o
k
e
r
ep
r
esen
ts
th
e
m
ain
ca
u
s
e
o
f
m
o
r
tality
an
d
d
is
ab
il
ity
g
lo
b
ally
[
1
]
.
I
n
p
r
ev
e
n
tio
n
ef
f
o
r
ts
,
s
tr
o
k
e
r
is
k
p
r
ed
ictio
n
p
lay
s
an
im
p
o
r
tan
t
r
o
le
an
d
h
as b
ee
n
s
u
cc
ess
f
u
lly
im
p
lem
en
ted
u
s
in
g
m
ac
h
i
n
e
l
ea
r
n
in
g
alg
o
r
ith
m
s
o
v
er
th
e
p
a
s
t f
ew
d
ec
ad
es.
P
r
e
v
i
o
u
s
r
e
s
ea
r
c
h
p
r
o
p
o
s
e
d
t
h
e
s
u
p
p
o
r
t
v
e
c
t
o
r
m
a
c
h
i
n
e
(
S
V
M
)
[
2
]
–
[
5
]
f
o
r
s
t
r
o
k
e
p
r
e
d
i
c
t
i
o
n
.
C
o
m
p
a
r
e
d
w
i
t
h
s
e
v
e
r
a
l
m
a
c
h
in
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
m
s
,
i
n
c
l
u
d
in
g
n
a
i
v
e
B
a
y
e
s
(
NB
)
,
l
o
g
i
s
ti
c
r
e
g
r
e
s
s
i
o
n
(
L
R
)
,
a
n
d
d
e
c
i
s
i
o
n
t
r
e
e
(
D
T
)
,
t
h
e
p
r
o
p
o
s
e
d
m
e
t
h
o
d
a
c
h
i
e
v
e
d
h
i
g
h
e
r
a
cc
u
r
a
c
y
.
T
h
e
r
a
n
d
o
m
f
o
r
e
s
t
(
R
F
)
a
l
g
o
r
i
t
h
m
[
6
]
,
[
7
]
w
a
s
a
ls
o
d
e
v
e
l
o
p
e
d
a
n
d
s
h
o
w
e
d
s
u
p
e
r
i
o
r
p
e
r
f
o
r
m
a
n
c
e
c
o
m
p
a
r
e
d
t
o
L
R
,
k
-
n
e
a
r
e
s
t
n
e
i
g
h
b
o
r
(
K
N
N
)
,
S
V
M
,
e
x
t
r
e
m
e
g
r
a
d
i
e
n
t
b
o
o
s
t
i
n
g
(
XG
B
o
o
s
t
)
,
a
d
a
p
ti
v
e
b
o
o
s
ti
n
g
(
Ad
a
B
o
o
s
t
)
,
D
T
,
a
n
d
l
i
g
h
t
g
r
a
d
i
en
t
-
b
o
o
s
t
i
n
g
m
a
c
h
i
n
e
(
L
i
g
h
t
G
B
M
)
.
F
u
r
t
h
e
r
m
o
r
e
,
t
h
e
u
s
e
o
f
a
r
t
i
f
i
ci
a
l
n
e
u
r
al
n
e
tw
o
r
k
(
A
N
N
)
[
6
]
,
a
d
a
p
t
i
v
e
n
eu
r
o
-
f
u
z
z
y
i
n
f
e
r
e
n
c
e
s
y
s
te
m
(
A
NF
I
S
)
[
7
]
,
a
n
d
c
o
n
v
o
l
u
t
i
o
n
n
e
u
r
a
l
n
e
t
w
o
r
k
(
C
N
N
)
h
a
s
b
e
e
n
r
e
p
o
r
t
e
d
i
n
s
t
r
o
k
e
p
r
e
d
i
c
t
i
o
n
e
f
f
o
r
t
s
[
8
]
.
Sev
er
al
m
eth
o
d
s
h
av
e
b
ee
n
u
s
ed
to
im
p
r
o
v
e
ac
cu
r
ac
y
,
in
clu
d
in
g
en
s
em
b
lin
g
,
o
v
er
s
am
p
lin
g
,
an
d
f
ea
tu
r
e
s
elec
tio
n
.
E
n
s
em
b
lin
g
m
eth
o
d
s
ap
p
lied
in
cl
u
d
e
XGBo
o
s
t
[
9
]
–
[
1
1
]
,
Ad
aBo
o
s
t
[
1
2
]
,
an
d
s
tack
in
g
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
C
o
mb
in
a
tio
n
o
f
b
in
a
r
y
p
a
r
ticl
e
s
w
a
r
m
o
p
timiz
a
tio
n
a
n
d
r
a
n
d
o
m
fo
r
est fo
r
s
tr
o
ke
d
is
ea
s
e
…
(
S
u
tikn
o
)
2291
[
1
3
]
–
[
1
5
]
,
with
r
esu
lts
s
h
o
win
g
s
ig
n
if
ican
t
im
p
r
o
v
em
en
ts
in
ac
cu
r
ac
y
.
T
h
e
o
v
e
r
s
am
p
lin
g
m
eth
o
d
ca
n
also
im
p
r
o
v
e
ac
c
u
r
ac
y
o
n
u
n
b
alan
ce
d
d
atasets
.
Srin
iv
asu
et
a
l.
[
1
6
]
ap
p
lied
th
e
s
y
n
th
etic
m
i
n
o
r
ity
o
v
e
r
s
am
p
lin
g
tech
n
iq
u
e
(
SMOT
E
)
to
b
alan
ce
th
e
class
d
is
tr
ib
u
tio
n
an
d
u
s
ed
an
ANN
as
th
e
class
if
ie
r
.
T
h
is
m
eth
o
d
was
also
u
s
ed
in
[
1
7
]
,
wh
o
r
ep
o
r
t
ed
s
ig
n
if
ican
tly
s
u
p
er
io
r
p
er
f
o
r
m
an
ce
.
Me
an
w
h
ile,
B
is
wa
s
et
a
l
.
[
1
8
]
u
s
ed
th
e
r
an
d
o
m
o
v
e
r
s
am
p
lin
g
(
R
OS)
m
eth
o
d
a
n
d
an
SVM
class
if
ier
,
r
esu
ltin
g
in
a
s
u
b
s
tan
tial in
cr
ea
s
e
in
ac
cu
r
ac
y
.
An
o
th
er
m
eth
o
d
to
in
cr
ea
s
e
ac
cu
r
ac
y
is
to
ad
d
a
f
ea
tu
r
e
s
elec
tio
n
p
r
o
ce
s
s
to
id
en
tif
y
th
e
b
est
f
ea
tu
r
es
in
th
e
d
ataset
[
1
9
]
.
L
ee
et
a
l
.
[
2
0
]
p
r
o
p
o
s
ed
p
r
in
ci
p
al
co
m
p
o
n
en
t
an
aly
s
is
(
PC
A
)
f
ea
tu
r
e
s
elec
tio
n
an
d
o
v
er
s
am
p
lin
g
f
o
r
s
tr
o
k
e
p
r
e
d
ictio
n
.
Me
an
wh
ile,
Vic
to
r
et
a
l.
[
2
1
]
p
r
o
p
o
s
ed
u
s
in
g
p
ar
ticle
s
war
m
o
p
tim
izatio
n
(
PS
O)
f
o
r
f
ea
tu
r
e
s
elec
tio
n
an
d
f
e
d
er
ated
lear
n
in
g
(
FL)
as
a
class
if
ier
.
T
h
e
r
esu
lts
s
h
o
wed
th
at
th
ese
m
eth
o
d
s
co
u
ld
in
cr
ea
s
e
ac
cu
r
ac
y
,
with
PS
O
as
th
e
wr
ap
p
er
f
ea
tu
r
e
s
elec
tio
n
m
eth
o
d
p
r
o
d
u
cin
g
r
elativ
ely
s
u
p
er
i
o
r
p
er
f
o
r
m
an
ce
.
I
n
s
o
m
e
r
ep
o
r
ts
,
R
F
[
2
2
]
,
[
2
3
]
an
d
PS
O
[
2
1
]
ac
h
iev
ed
b
etter
ac
cu
r
ac
y
th
a
n
o
th
er
m
eth
o
d
s
.
T
h
er
ef
o
r
e,
th
i
s
r
esear
ch
p
r
o
p
o
s
es
a
n
o
v
el
h
y
b
r
id
B
PS
O
–
R
F
ap
p
r
o
ac
h
,
t
h
e
f
ir
s
t
in
teg
r
atin
g
b
in
ar
y
p
ar
ticle
s
war
m
o
p
tim
iz
atio
n
(
B
PS
O)
an
d
RF
f
o
r
s
tr
o
k
e
p
r
ed
ictio
n
,
to
e
n
h
an
ce
clas
s
if
icatio
n
ac
cu
r
ac
y
an
d
f
ea
tu
r
e
r
elev
an
ce
.
T
h
e
r
e
s
u
lts
wer
e
ex
p
ec
ted
to
p
r
o
v
id
e
v
alu
ab
le
in
f
o
r
m
atio
n
o
n
p
r
ed
ictio
n
ef
f
o
r
ts
f
o
r
f
aster
an
d
m
o
r
e
ef
f
ec
tiv
e
ca
r
e
to
b
e
p
r
o
v
id
e
d
to
p
atien
ts
at
in
cr
ea
s
ed
r
is
k
o
f
s
tr
o
k
e.
2.
M
E
T
H
O
D
T
h
e
p
r
o
p
o
s
ed
r
esear
ch
s
tep
s
i
n
s
tr
o
k
e
p
r
ed
ictio
n
ar
e
d
ep
icte
d
in
Fig
u
r
e
1
.
T
h
e
i
n
p
u
t
o
f
th
i
s
r
esear
ch
is
th
e
d
atasets
an
d
th
e
o
u
t
p
u
t
is
m
o
d
el
e
v
alu
atio
n
.
T
h
e
m
ain
p
r
o
ce
s
s
es
ar
e
p
r
ep
r
o
ce
s
s
in
g
,
o
v
e
r
s
am
p
lin
g
,
s
p
litt
in
g
d
ata,
f
ea
tu
r
e
s
elec
tio
n
,
an
d
class
if
icatio
n
.
Fig
u
r
e
1
.
T
h
e
p
r
o
p
o
s
ed
r
esear
ch
s
tep
s
in
s
tr
o
k
e
p
r
e
d
ictio
n
2
.
1
.
Da
t
a
s
et
T
h
is
r
esear
ch
u
s
ed
two
p
u
b
li
c
d
atasets
:
th
e
s
tr
o
k
e
p
r
ed
icti
o
n
d
ataset
(
SP
D)
an
d
th
e
b
r
ain
s
tr
o
k
e
d
ataset
(
B
S
D)
,
av
ailab
le
o
n
Kag
g
le
[
2
4
]
,
[
2
5
]
.
B
o
th
d
atasets
co
n
tain
d
ata
o
n
s
tr
o
k
e
an
d
n
o
n
-
s
tr
o
k
e
p
atien
ts
,
ea
ch
with
1
2
attr
ib
u
tes.
T
h
e
s
tr
o
k
e
attr
ib
u
tes,
wh
ich
tak
e
v
alu
es
0
o
r
1
,
ar
e
th
e
tar
g
ets,
wh
ile
th
e
o
th
er
s
ar
e
f
ea
tu
r
es.
A
v
alu
e
o
f
0
in
d
icate
s
th
e
p
atien
t
d
id
n
o
t
h
av
e
a
s
tr
o
k
e,
wh
ile
a
v
alu
e
o
f
1
i
n
d
ica
tes
th
e
p
atien
t
d
id
.
T
h
e
SP
D
d
ataset
co
n
tain
s
5
,
1
1
0
r
o
ws,
with
4
.
8
7
%
s
tr
o
k
e
p
atien
ts
an
d
9
5
.
1
3
%
n
o
n
-
s
tr
o
k
e
p
atien
ts
.
Me
an
wh
ile,
th
e
B
SD
d
ataset
co
n
tain
s
4
,
9
8
1
r
o
ws,
with
4
.
9
8
%
s
tr
o
k
e
p
atien
ts
an
d
9
5
.
0
2
%
n
o
n
-
s
tr
o
k
e
p
atien
ts
.
I
t
ap
p
ea
r
s
th
at
th
e
cl
ass
es
in
b
o
th
d
atasets
ar
e
im
b
alan
ce
d
.
T
h
e
d
ata
im
b
alan
ce
was
a
ch
allen
g
e
f
o
r
th
is
r
esear
ch
,
alo
n
g
s
id
e
m
is
s
in
g
v
alu
es in
s
ev
er
al
attr
ib
u
tes,
u
n
d
er
s
co
r
i
n
g
th
e
n
ee
d
f
o
r
s
p
ec
ial
h
an
d
lin
g
.
2
.
2
.
P
re
pro
ce
s
s
ing
Pre
p
r
o
ce
s
s
in
g
f
u
n
ctio
n
s
to
p
r
ep
ar
e
d
ata
an
d
f
ac
ilit
ate
th
e
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
s
,
th
er
eb
y
im
p
r
o
v
in
g
d
ata
q
u
ality
an
d
e
n
h
an
cin
g
m
o
d
el
p
e
r
f
o
r
m
an
ce
.
I
n
t
h
is
r
esear
ch
,
p
r
ep
r
o
ce
s
s
in
g
co
m
p
r
is
ed
t
h
r
ee
s
tag
es:
h
an
d
lin
g
m
is
s
in
g
v
alu
es,
tr
an
s
f
o
r
m
in
g
attr
ib
u
tes,
an
d
n
o
r
m
aliza
tio
n
.
Me
an
im
p
u
ta
tio
n
is
u
s
ed
h
an
d
le
m
is
s
in
g
v
alu
es.
T
h
e
f
ea
t
u
r
es
th
at
h
av
e
th
is
is
s
u
e
ar
e
g
e
n
d
e
r
,
b
o
d
y
m
ass
in
d
e
x
(
B
MI
)
,
a
n
d
s
m
o
k
in
g
s
tatu
s
.
Af
ter
th
at,
t
h
e
I
D
co
lu
m
n
was
r
em
o
v
ed
b
ec
au
s
e
it
d
id
n
o
t
a
f
f
ec
t
th
e
m
o
d
el'
s
r
esu
lts
.
Su
b
s
eq
u
en
tly
,
attr
ib
u
te
tr
an
s
f
o
r
m
in
g
was
p
er
f
o
r
m
ed
b
y
ch
an
g
in
g
th
e
s
tr
in
g
v
alu
e
to
an
in
teg
er
.
T
h
e
f
iv
e
-
s
tr
i
n
g
attr
ib
u
tes
wer
e
g
en
d
er
,
ev
er
m
ar
r
ied
,
wo
r
k
t
y
p
e,
r
esid
en
ce
ty
p
e,
an
d
s
m
o
k
in
g
s
tatu
s
.
T
h
e
last
s
tep
in
p
r
ep
r
o
ce
s
s
in
g
was
n
o
r
m
aliza
tio
n
to
p
r
o
d
u
ce
n
u
m
er
ic
v
alu
es
i
n
th
e
r
an
g
e
0
to
1
,
ca
lcu
lated
u
s
in
g
(
1
)
.
W
h
er
e
is
th
e
n
o
r
m
alize
d
f
ea
tu
r
e
v
alu
e,
is
th
e
ac
tu
al
v
alu
e
o
f
th
e
f
ea
tu
r
e,
is
lo
west v
alu
e,
an
d
is
h
ig
h
est v
alu
e.
=
−
−
(
1
)
2
.
3
.
O
v
er
s
a
m
pli
ng
T
h
e
im
b
alan
ce
in
p
o
s
itiv
e
s
am
p
les
b
iases
th
e
m
o
d
el
to
war
d
th
e
m
ajo
r
ity
class
an
d
d
eg
r
ad
es
d
etec
tio
n
p
er
f
o
r
m
an
ce
,
n
ec
e
s
s
itatin
g
cla
s
s
-
b
alan
cin
g
tech
n
iq
u
es
s
u
ch
as
SMOT
E
to
g
en
er
ate
s
y
n
th
etic
m
in
o
r
ity
s
am
p
les.
SMOT
E
g
en
er
ates
s
y
n
th
etic
d
ata
p
o
in
ts
b
y
in
ter
p
o
latin
g
am
o
n
g
s
am
p
les
o
f
th
e
m
i
n
o
r
it
y
class
.
Giv
en
two
s
am
p
les,
a
n
d
,
f
r
o
m
t
h
e
m
in
o
r
ity
class
,
a
n
ew
s
y
n
t
h
etic
in
s
tan
ce
is
g
en
er
ated
as
(
2
)
.
W
h
er
e
is
th
e
n
ew
ar
tific
ial
s
am
p
le,
an
d
ar
e
two
r
an
d
o
m
ly
s
elec
ted
m
in
o
r
ity
-
class
s
am
p
les.
D
a
t
a
s
e
t
P
r
e
p
r
o
c
e
s
s
i
n
g
-
H
a
n
d
l
i
n
g
m
i
s
s
i
n
g
v
a
l
u
e
-
T
r
a
n
s
f
o
r
m
i
n
g
a
t
t
r
i
b
u
t
e
s
-
N
o
r
m
a
l
i
z
a
t
i
o
n
F
e
a
t
u
r
e
S
e
l
e
c
t
i
o
n
(
B
P
S
O
+
R
F
)
C
l
a
s
s
i
f
i
c
a
t
i
o
n
(
R
F
)
M
o
d
e
l
E
v
a
l
u
a
t
i
o
n
(
A
c
c
,
P
r
e
,
R
e
c
,
F
1
-
S
)
O
v
e
r
s
a
m
p
l
i
n
g
(
S
M
O
T
E
)
S
p
l
i
t
t
i
n
g
d
a
t
a
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
3
,
J
u
n
e
2
0
2
6
:
2
2
9
0
-
2
2
9
9
2292
T
h
e
v
ar
iab
le
d
en
o
tes
a
r
an
d
o
m
ly
s
am
p
led
v
alu
e
in
th
e
in
te
r
v
al
[
0
,
1
]
th
at
co
n
tr
o
ls
th
e
in
ter
p
o
latio
n
.
T
h
is
p
r
o
ce
s
s
h
elp
s
th
e
m
o
d
el
lear
n
f
r
o
m
u
n
d
er
r
ep
r
esen
ted
class
es
b
y
g
en
er
atin
g
ad
d
itio
n
al
tr
ain
in
g
d
ata,
t
h
u
s
im
p
r
o
v
in
g
th
e
b
alan
ce
b
etwe
en
th
e
p
o
s
itiv
e
an
d
n
eg
ativ
e
class
es.
R
esam
p
lin
g
tech
n
iq
u
es
h
av
e
b
ee
n
wid
ely
u
s
ed
to
ad
d
r
ess
class
im
b
ala
n
ce
an
d
h
a
v
e
b
ee
n
em
p
ir
ically
s
h
o
wn
to
im
p
r
o
v
e
th
e
m
o
d
el's
ab
ilit
y
to
lear
n
u
n
d
er
r
ep
r
esen
ted
m
in
o
r
ity
cla
s
s
es
[
2
6
]
.
=
+
×
(
−
)
(
2
)
2
.
4
.
Da
t
a
s
pli
t
t
ing
Data
s
p
litt
in
g
was
p
er
f
o
r
m
e
d
af
ter
o
v
er
s
am
p
lin
g
.
Data
s
p
litt
in
g
was
p
er
f
o
r
m
e
d
u
s
i
n
g
5
-
f
o
ld
cr
o
s
s
-
v
alid
atio
n
.
T
h
e
f
in
al
r
es
u
lt wa
s
th
e
av
er
ag
e.
2
.
5
.
F
e
a
t
ure
s
elec
t
io
n
T
h
is
r
esear
ch
u
s
ed
B
PS
O
f
ea
t
u
r
e
s
elec
tio
n
to
s
o
lv
e
b
in
ar
y
o
p
tim
izatio
n
p
r
o
b
lem
s
.
T
h
e
alg
o
r
ith
m
is
a
d
ev
elo
p
m
e
n
t
o
f
PS
O
in
tr
o
d
u
ce
d
b
y
Ken
n
ed
y
an
d
E
b
er
h
a
r
t
[
2
7
]
.
I
n
B
PS
O,
ea
ch
p
ar
ticl
e
is
ex
p
r
ess
ed
as
a
s
eq
u
en
ce
o
f
b
in
ar
y
b
its
.
T
h
e
m
o
v
em
en
t
o
f
p
a
r
ticles
is
in
f
lu
en
ce
d
b
y
in
d
i
v
id
u
al
ex
p
er
ien
ce
an
d
th
e
b
est
ex
p
er
ien
ce
o
f
th
eir
n
eig
h
b
o
r
s
i
n
f
in
d
in
g
th
e
o
p
tim
al
s
o
lu
tio
n
.
B
PS
O
in
clu
d
es
s
tep
s
to
r
ea
ch
an
o
p
tim
al
s
o
lu
tio
n
in
a
b
in
ar
y
s
ea
r
ch
s
p
ac
e.
I
n
itially
,
a
p
o
p
u
latio
n
o
f
p
ar
ticles
is
r
an
d
o
m
ly
estab
lis
h
ed
.
T
h
is
s
tep
is
f
o
llo
wed
b
y
ev
alu
atin
g
ea
ch
p
ar
ticle'
s
f
it
n
ess
v
alu
e
u
s
in
g
th
e
o
b
jectiv
e
f
u
n
ctio
n
to
b
e
o
p
tim
ized
.
Fu
r
th
er
m
o
r
e,
th
e
p
a
r
t
icle
in
th
e
p
o
p
u
latio
n
u
p
d
ate
s
its
v
elo
city
an
d
p
o
s
itio
n
.
T
h
e
v
elo
city
is
i
n
f
lu
en
ce
d
b
y
th
e
p
r
ev
i
o
u
s
r
es
u
lts
,
in
d
iv
id
u
al
ex
p
er
ien
ce
(
p
b
est),
an
d
g
lo
b
al
ex
p
er
ien
ce
(
g
b
est).
T
h
e
v
elo
c
ity
u
p
d
ate
m
o
v
es
th
e
p
ar
ticle
in
th
e
b
in
ar
y
s
o
lu
tio
n
s
p
ac
e.
Su
b
s
eq
u
en
tly
,
th
e
f
itn
ess
v
alu
e
o
f
t
h
e
n
ew
p
a
r
ticle
is
ev
alu
ated
,
an
d
wh
e
n
t
h
e
n
ew
p
o
s
itio
n
p
r
o
v
id
es
b
etter
f
itn
ess
,
th
e
p
a
r
ticle
p
b
est is
u
p
d
ated
.
W
h
en
th
e
s
ea
r
ch
s
p
ac
e
is
=
{
0
,
1
}
an
d
th
e
o
b
jectiv
e
f
u
n
ctio
n
aim
s
to
m
ax
im
ize,
(
)
,
p
ar
ticle
ca
n
b
e
f
o
r
m
u
lated
as
a
-
d
im
en
s
io
n
al
v
ec
to
r
,
=
(
1
,
2
,
.
.
.
,
)
,
with
∈
{
0
,
1
}
,
=
1
,
2
,
.
.
.
,
.
T
h
e
v
el
o
city
is
g
iv
e
n
b
y
=
(
1
,
2
,
.
.
.
,
)
,
with
∈
[
−
,
]
,
wh
er
e
is
th
e
h
ig
h
est
v
elo
city
v
alu
e.
T
h
e
b
est
p
o
s
itio
n
th
at
p
ar
ticle
h
as
ev
er
v
is
ited
is
r
ep
r
esen
ted
b
y
=
(
1
,
2
,
.
.
.
,
)
,
wh
er
e
∈
{
0
,
1
}
.
W
h
en
is
d
ef
in
ed
as
th
e
b
est
in
d
ex
in
th
e
s
war
m
a
n
d
is
th
e
b
est
p
o
s
itio
n
,
th
e
v
elo
city
u
p
d
ate
is
ca
lcu
lated
u
s
in
g
(
3
)
,
wh
er
e
is
a
p
ar
am
eter
th
at
co
n
tr
o
ls
th
e
s
teep
n
es
s
o
f
th
e
s
ig
m
o
id
f
u
n
ctio
n
.
T
h
e
p
o
s
itio
n
u
p
d
ate
is
th
en
f
o
r
m
u
lated
b
y
(
4
)
.
=
+
1
1
(
−
)
+
2
2
(
−
)
(
3
)
=
{
1
(
0
,
1
)
<
(
)
,
2
ℎ
,
(
4
)
T
h
e
f
ea
tu
r
e
s
elec
tio
n
p
r
o
ce
s
s
is
in
m
u
ltip
le
s
tag
es,
as
illu
s
tr
ated
in
Fig
u
r
e
2
.
T
h
is
p
r
o
ce
s
s
co
m
b
in
e
d
two
alg
o
r
ith
m
s
:
B
PS
O,
u
s
ed
t
o
s
elec
t
th
e
o
p
tim
al
f
ea
tu
r
e
s
u
b
s
et
;
an
d
R
F,
u
s
ed
to
co
m
p
u
t
e
th
e
f
it
n
ess
v
alu
e.
T
h
e
r
esu
lts
o
f
th
is
p
r
o
ce
s
s
ar
e
th
e
b
est f
ea
tu
r
e
s
u
b
s
et
an
d
th
e
h
ig
h
est ac
cu
r
ac
y
.
Fig
u
r
e
2
.
Featu
r
e
s
elec
tio
n
p
r
o
ce
s
s
u
s
in
g
B
PS
O
an
d
R
F
T
h
e
in
itial
s
tag
e
in
v
o
lv
es
d
ete
r
m
in
in
g
th
e
n
u
m
b
e
r
o
f
p
ar
ticles
(
N
)
an
d
th
e
n
u
m
b
e
r
o
f
d
im
en
s
io
n
s
p
er
p
ar
ticle
(
D
)
.
I
n
th
is
r
esear
ch
,
D
is
eq
u
al
to
th
e
n
u
m
b
er
o
f
f
e
atu
r
es.
T
h
er
e
ar
e
1
1
f
ea
tu
r
es,
with
ea
ch
d
im
en
s
io
n
tak
in
g
v
al
u
es
0
o
r
1
.
Sp
ec
if
ica
lly
,
0
co
r
r
esp
o
n
d
s
to
a
n
o
n
-
s
elec
ted
f
ea
tu
r
e,
an
d
1
to
a
s
elec
ted
f
ea
tu
r
e
.
Du
r
in
g
in
itializatio
n
,
th
ese
b
in
ar
y
v
alu
es a
r
e
r
an
d
o
m
ly
d
eter
m
in
ed
.
R
a
n
d
o
m
l
y
i
n
i
t
i
a
l
i
z
e
t
h
e
p
o
p
u
l
a
t
i
o
n
o
f
p
a
r
t
i
c
l
e
s
S
e
t
t
h
e
i
n
i
t
i
a
l
v
a
l
u
e
s
f
o
r
p
e
r
s
o
n
a
l
b
e
s
t
a
n
d
g
l
o
b
a
l
b
e
s
t
M
o
d
i
f
y
t
h
e
p
a
r
t
i
c
l
e
'
s
v
e
l
o
c
i
t
y
M
o
d
i
f
y
t
h
e
p
a
r
t
i
c
l
e
'
s
p
o
s
i
t
i
o
n
F
i
t
n
e
s
s
e
v
a
l
u
a
t
i
o
n
(
R
F
)
U
p
d
a
t
e
t
h
e
g
l
o
b
a
l
b
e
s
t
i
f
t
h
e
f
i
t
n
e
s
s
v
a
l
u
e
i
n
c
r
e
a
s
e
s
U
p
d
a
t
e
t
h
e
p
e
r
s
o
n
a
l
b
e
s
t
i
f
t
h
e
f
i
t
n
e
s
s
v
a
l
u
e
i
n
c
r
e
a
s
e
s
O
u
t
p
u
t
:
S
u
b
s
e
t
f
e
a
t
u
r
e
a
n
d
t
h
e
b
e
s
t
a
c
c
u
r
a
c
y
I
t
e
r
a
t
i
o
n
l
i
m
i
t
r
e
a
c
h
e
d
?
Y
e
s
N
o
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
C
o
mb
in
a
tio
n
o
f
b
in
a
r
y
p
a
r
ticl
e
s
w
a
r
m
o
p
timiz
a
tio
n
a
n
d
r
a
n
d
o
m
fo
r
est fo
r
s
tr
o
ke
d
is
ea
s
e
…
(
S
u
tikn
o
)
2293
A
p
er
s
o
n
al
b
est
is
a
p
ar
ticle
th
at
alr
ea
d
y
ex
is
ts
,
wh
ile
a
g
lo
b
al
b
est
h
as
th
e
b
est
f
itn
ess
v
al
u
e.
Fit
n
ess
is
ca
lcu
lated
u
s
in
g
(
5
)
[
2
8
]
.
W
h
er
e
is
th
e
av
er
a
g
e
class
if
icatio
n
er
r
o
r
,
|
|
r
ep
r
esen
ts
th
e
n
u
m
b
er
o
f
s
elec
ted
f
ea
tu
r
es,
|
|
d
en
o
tes th
e
co
m
p
lete
s
et
o
f
f
ea
tu
r
es,
is
th
e
weig
h
t f
o
r
class
if
icatio
n
ac
cu
r
ac
y
,
a
n
d
is
th
e
weig
h
t f
o
r
th
e
s
elec
ted
f
ea
tu
r
es.
KNN
is
o
f
ten
u
s
ed
as a
class
if
ier
[
2
9
]
.
T
h
is
r
esear
ch
u
s
es a
n
R
F c
la
s
s
if
ier
with
=
0
.
99
an
d
=
0
.
01
[
2
8
]
.
=
(
)
+
|
|
|
|
(
5
)
2
.
6
.
Cla
s
s
if
ica
t
io
n
R
F
i
s
a
tr
ee
-
b
ased
en
s
em
b
le
a
lg
o
r
ith
m
th
at
f
o
r
m
s
m
u
ltip
le
DT
f
r
o
m
r
an
d
o
m
ly
s
elec
ted
s
am
p
les
an
d
co
m
b
in
es
th
eir
p
r
e
d
ictio
n
s
th
r
o
u
g
h
m
ajo
r
ity
v
o
tin
g
.
I
ts
m
a
in
ad
v
an
tag
es
ar
e
r
o
b
u
s
tn
ess
ag
ain
s
t
o
v
er
f
itti
n
g
,
s
tr
o
n
g
g
e
n
er
aliza
tio
n
p
er
f
o
r
m
an
ce
,
an
d
th
e
ab
ilit
y
to
id
en
ti
f
y
im
p
o
r
tan
t
f
ea
tu
r
es
[
3
0
]
.
R
F
ap
p
lies
b
o
o
ts
tr
ap
s
am
p
lin
g
to
g
en
e
r
ate
m
u
ltip
le
d
atasets
an
d
r
an
d
o
m
ly
s
elec
ts
f
ea
tu
r
e
s
u
b
s
ets
at
ea
ch
n
o
d
e,
wh
er
e
s
p
lits
ar
e
d
eter
m
in
ed
u
s
in
g
c
r
iter
ia
s
u
ch
as
Gin
i
im
p
u
r
ity
o
r
en
tr
o
p
y
.
Gin
i
im
p
u
r
ity
m
ea
s
u
r
es
th
e
im
p
er
f
ec
tio
n
o
f
a
s
p
lit
at
a
p
ar
ticu
lar
n
o
d
e
u
s
in
g
(
6
)
.
T
h
e
v
a
r
iab
le
o
f
is
p
r
o
p
o
r
ti
o
n
o
f
s
am
p
les
with
class
at
th
at
n
o
d
e,
an
d
is
n
u
m
b
er
o
f
class
es.
An
o
th
er
alt
er
n
ativ
e
f
o
r
m
ea
s
u
r
in
g
ir
r
eg
u
l
ar
ity
at
a
n
o
d
e
is
en
tr
o
p
y
,
as d
ef
in
ed
in
(
7
)
.
(
)
=
1
−
∑
2
=
1
(
6
)
(
)
=
−
∑
2
(
)
=
1
(
7
)
T
h
e
s
p
litt
in
g
p
r
o
ce
s
s
co
n
tin
u
e
s
u
n
til
it
m
ee
ts
a
s
p
ec
if
ic
s
to
p
co
n
d
itio
n
.
Af
ter
all
tr
ee
s
ar
e
f
o
r
m
ed
,
th
e
f
in
al
s
tep
is
v
o
tin
g
.
E
ac
h
tr
ee
p
r
o
v
id
es a
class
p
r
ed
ictio
n
,
an
d
th
e
f
in
al
p
r
ed
ictio
n
r
esu
lts
f
r
o
m
m
ajo
r
ity
v
o
tin
g
ac
r
o
s
s
all
tr
ee
s
,
as
in
(
8
)
.
W
h
er
e
ℎ
(
)
is
th
e
p
r
ed
ictio
n
f
r
o
m
tr
e
e
f
o
r
s
am
p
le
,
an
d
m
o
d
e
r
etu
r
n
s
th
e
m
o
s
t
f
r
eq
u
e
n
t c
lass
am
o
n
g
all
tr
ee
s
.
̂
=
{
ℎ
(
)
}
=
1
(
8
)
2
.
7
.
M
o
del e
v
a
lua
t
i
o
n
T
h
e
p
e
r
f
o
r
m
an
ce
e
v
alu
atio
n
was
co
n
d
u
cted
u
s
in
g
th
e
m
et
r
ics
o
f
ac
c
u
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
-
s
co
r
e,
ca
lcu
lated
s
eq
u
en
tia
lly
with
(
9
)
to
(
1
2
)
[
3
0
]
.
T
h
e
v
alu
es o
f
tr
u
e
p
o
s
itiv
e
(
)
,
tr
u
e
n
eg
ativ
e
(
)
,
f
alse p
o
s
itiv
e
(
)
,
an
d
f
alse n
eg
ativ
e
(
)
wer
e
d
e
r
iv
ed
f
r
o
m
co
n
f
u
s
io
n
m
atr
ix
,
as illu
s
tr
ated
in
T
ab
le
1
.
=
+
+
+
+
(
9
)
=
+
(
1
0
)
=
+
(
1
1
)
1
−
=
2
×
×
+
(
1
2
)
T
ab
le
1
.
C
o
n
f
u
s
io
n
m
atr
ix
o
f
s
tr
o
k
e
p
r
ed
ictio
n
A
c
t
u
a
l
v
a
l
u
e
s
S
t
r
o
k
e
N
o
n
-
st
r
o
k
e
P
r
e
d
i
c
t
e
d
v
a
l
u
e
s
S
t
r
o
k
e
T
pos
F
pos
N
o
n
-
s
t
r
o
k
e
F
ne
g
T
ne
g
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
esti
n
g
was
co
n
d
u
cted
u
s
in
g
s
ev
er
al
s
ce
n
ar
io
s
.
I
n
th
e
f
ir
s
t
s
ce
n
ar
io
,
we
test
ed
th
e
R
F
clas
s
if
ier
with
o
u
t
f
ea
tu
r
e
s
elec
tio
n
a
n
d
th
en
c
o
m
p
a
r
ed
it
with
o
th
e
r
class
if
ier
s
,
n
am
ely
XGBo
o
s
t,
L
ig
h
tGB
M,
an
d
ca
teg
o
r
ical
b
o
o
s
tin
g
(
C
atB
o
o
s
t
)
.
All
te
s
ts
wer
e
p
er
f
o
r
m
ed
with
h
y
p
er
p
ar
am
eter
tu
n
in
g
to
ac
h
iev
e
th
e
b
est
ac
cu
r
ac
y
.
T
h
e
r
an
g
e
o
f
v
alu
e
s
f
o
r
th
e
tu
n
e
d
p
ar
am
eter
is
s
h
o
wn
in
T
ab
le
2
.
I
n
th
e
f
o
llo
win
g
s
ce
n
ar
io
,
we
test
ed
B
P
SO
f
ea
tu
r
e
s
elec
tio
n
with
th
e
R
F
clas
s
if
ier
an
d
c
o
m
p
ar
ed
it
with
o
th
er
f
ea
t
u
r
e
s
elec
tio
n
m
eth
o
d
s
,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
3
,
J
u
n
e
2
0
2
6
:
2
2
9
0
-
2
2
9
9
2294
in
clu
d
in
g
m
u
tu
al
in
f
o
r
m
atio
n
(
MI
)
,
g
en
etic
alg
o
r
ith
m
s
(
GA)
,
an
d
B
o
r
u
ta.
T
h
e
p
ar
a
m
et
er
s
u
s
ed
f
r
o
m
th
e
f
ea
tu
r
e
s
elec
tio
n
ar
e
s
h
o
w
n
in
T
ab
le
3
.
T
ab
le
2
.
R
an
g
e
v
alu
e
o
f
th
e
p
a
r
am
eter
tu
n
in
g
ex
p
er
im
en
t in
th
e
class
if
ier
C
l
a
s
si
f
i
e
r
R
a
n
g
e
v
a
l
u
e
o
f
t
h
e
p
a
r
a
me
t
e
r
RF
N
u
mb
e
r
o
f
t
r
e
e
s:
5
0
,
1
0
0
,
a
n
d
1
5
0
M
i
n
i
m
u
m
sam
p
l
e
s
p
e
r
l
e
a
f
:
1
,
2
,
3
,
a
n
d
4
N
u
mb
e
r
o
f
f
e
a
t
u
r
e
s
p
e
r
s
p
l
i
t
:
2
t
o
1
0
X
G
B
o
o
st
Tr
e
e
c
o
u
n
t
:
5
0
,
1
0
0
,
a
n
d
1
5
0
Th
e
d
e
p
t
h
l
i
mi
t
o
f
e
a
c
h
t
r
e
e
:
3
,
4
,
a
n
d
5
Li
g
t
G
B
M
Tr
e
e
c
o
u
n
t
:
5
0
,
1
0
0
,
a
n
d
1
5
0
Th
e
d
e
p
t
h
l
i
mi
t
o
f
e
a
c
h
t
r
e
e
:
3
,
4
,
a
n
d
5
C
a
t
B
o
o
s
t
Tr
e
e
c
o
u
n
t
:
5
0
,
1
0
0
,
1
5
0
Th
e
d
e
p
t
h
l
i
mi
t
o
f
e
a
c
h
t
r
e
e
:
3
,
4
,
a
n
d
5
T
ab
le
3
.
T
h
e
s
et
o
f
p
a
r
am
eter
r
an
g
es c
o
n
s
id
er
e
d
f
o
r
tu
n
i
n
g
i
n
th
e
f
ea
tu
r
e
s
elec
tio
n
s
tag
e
F
e
a
t
u
r
e
s
e
l
e
c
t
i
o
n
R
a
n
g
e
v
a
l
u
e
o
f
t
h
e
p
a
r
a
me
t
e
r
PSO
N
u
mb
e
r
o
f
p
a
r
t
i
c
l
e
s:
1
2
M
a
x
i
m
u
m
i
t
e
r
a
t
i
o
n
:
5
0
MI
F
e
a
t
u
r
e
:
1
0
%
t
o
1
0
0
%
(
i
n
c
r
e
a
m
e
n
t
:
1
0
%)
GA
P
o
p
u
l
a
t
i
o
n
s
i
z
e
:
1
2
N
u
mb
e
r
o
f
g
e
n
e
r
a
t
i
o
n
s
:
5
0
C
r
o
ss
o
v
e
r
r
a
t
e
:
0
.
8
M
u
t
a
t
i
o
n
r
a
t
e
:
0
.
0
5
T
h
e
r
esu
lts
o
f
t
h
e
f
ir
s
t
test
u
s
e
d
R
F
f
o
r
class
if
icatio
n
with
o
u
t
f
ea
tu
r
e
s
elec
tio
n
.
I
t
was
th
en
co
m
p
ar
ed
with
class
if
ier
s
XGBo
o
s
t,
L
ig
h
tGB
M,
an
d
C
atB
o
o
s
t.
T
h
e
co
m
p
ar
is
o
n
r
esu
lts
o
f
th
ese
class
if
ier
s
ar
e
s
h
o
wn
in
T
ab
le
4
.
R
F
ac
h
iev
es
h
i
g
h
er
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
-
s
co
r
e
th
an
t
h
e
o
th
e
r
class
if
ier
s
o
n
b
o
th
d
atasets
.
T
h
er
ef
o
r
e,
R
F is
m
o
r
e
s
u
itab
le
f
o
r
s
tr
o
k
e
d
is
ea
s
e
class
if
icatio
n
th
an
th
e
o
th
er
th
r
e
e
class
if
ier
s
.
T
h
e
n
ex
t
test
in
v
o
lv
ed
a
d
d
in
g
a
f
ea
tu
r
e
s
elec
tio
n
p
r
o
ce
s
s
.
T
h
e
p
r
o
p
o
s
ed
f
ea
tu
r
e
s
elec
tio
n
m
eth
o
d
is
B
PS
O.
T
h
e
r
esu
lts
o
f
th
is
test
ar
e
s
h
o
wn
in
T
ab
le
5
.
T
h
e
p
r
o
p
o
s
ed
m
et
h
o
d
ac
h
iev
e
d
a
n
ac
c
u
r
ac
y
o
f
0
.
9
6
1
3
o
n
th
e
SP
D
d
ataset
an
d
0
.
9
6
0
7
o
n
th
e
B
SD d
ataset.
Ad
d
in
g
f
ea
t
u
r
e
s
elec
tio
n
in
cr
ea
s
ed
ac
cu
r
a
cy
b
y
0
.
0
8
% o
n
th
e
SP
D
d
ataset
an
d
0
.
0
1
%
o
n
th
e
B
SD
d
ata
s
et.
T
h
e
n
u
m
b
er
o
f
f
ea
tu
r
es
in
b
o
th
d
atasets
is
1
0
.
T
h
e
B
PS
O
f
ea
tu
r
e
s
elec
tio
n
y
ield
ed
s
ev
en
d
o
m
i
n
an
t
f
ea
tu
r
es
in
th
e
SP
D
d
ataset
:
g
en
d
e
r
,
ag
e,
wo
r
k
ty
p
e,
r
esid
en
ce
ty
p
e,
a
v
er
ag
e
g
lu
co
s
e
lev
el,
B
MI
,
an
d
s
m
o
k
in
g
s
tatu
s
.
Me
an
wh
ile,
in
th
e
B
SD
d
ataset,
eig
h
t
d
o
m
in
an
t
f
ea
tu
r
es
wer
e
id
en
tifie
d
:
g
en
d
er
,
ag
e,
e
v
er
m
ar
r
ied
,
w
o
r
k
t
y
p
e,
r
esid
en
ce
ty
p
e,
a
v
er
ag
e
g
lu
co
s
e
le
v
el,
B
MI
,
an
d
s
m
o
k
i
n
g
s
tatu
s
.
T
wo
f
ea
tu
r
es we
r
e
n
o
t
s
elec
ted
in
th
e
test
s
f
o
r
b
o
th
d
atasets
,
n
am
ely
h
y
p
er
ten
s
io
n
a
n
d
h
ea
r
t
d
is
ea
s
e.
T
ab
le
4
.
C
o
m
p
a
r
is
o
n
o
f
R
F c
lass
if
ier
with
XGBo
o
s
t,
L
ig
h
t
GB
M,
an
d
C
atB
o
o
s
t
M
e
t
h
o
d
S
P
D
d
a
t
a
se
t
B
S
D
d
a
t
a
se
t
A
c
c
u
r
a
c
y
Pre
c
i
s
i
o
n
Rec
a
l
l
F1
-
s
c
o
r
e
A
c
c
u
r
a
c
y
Pre
c
i
s
i
o
n
Rec
a
l
l
F1
-
s
c
o
r
e
X
G
B
o
o
st
0
.
9
0
7
4
0
.
9
2
1
8
0
.
8
9
0
3
0
.
9
0
5
7
0
.
9
1
8
0
0
.
9
2
4
7
0
.
9
1
0
2
0
.
9
1
7
4
Li
g
t
G
B
M
0
.
9
2
1
2
0
.
9
4
5
6
0
.
8
9
4
0
0
.
9
1
9
0
0
.
9
2
7
5
0
.
9
4
4
3
0
.
9
0
8
7
0
.
9
2
6
2
C
a
t
B
o
o
s
t
0
.
8
5
8
2
0
.
8
6
7
7
0
.
8
4
5
4
0
.
8
5
6
4
0
.
8
6
7
9
0
.
8
7
5
7
0
.
8
5
7
8
0
.
8
6
6
6
RF
0
.
9
6
0
5
0
.
9
5
3
8
0
.
9
6
7
9
0
.
9
6
0
7
0
.
9
6
0
6
0
.
9
5
5
3
0
.
9
6
6
4
0
.
9
6
0
8
T
ab
le
5
.
R
esu
lts
o
f
th
e
p
r
o
p
o
s
ed
m
eth
o
d
u
s
in
g
B
PS
O
f
ea
tu
r
e
s
elec
tio
n
an
d
R
F c
lass
if
ier
F
o
l
d
n
u
mb
e
r
S
P
D
d
a
t
a
se
t
B
S
D
d
a
t
a
se
t
A
c
c
u
r
a
c
y
Pre
c
i
s
i
o
n
Rec
a
l
l
F1
-
s
c
o
r
e
Ti
me
(
s)
A
c
c
u
r
a
c
y
Pre
c
i
s
i
o
n
Rec
a
l
l
F1
-
s
c
o
r
e
Ti
me
(
s)
1
0
.
9
6
7
1
0
.
9
6
3
3
0
.
9
7
1
2
0
.
9
6
7
2
6
4
7
0
.
9
5
7
2
0
.
9
4
8
2
0
.
9
6
7
2
0
.
9
5
7
6
2
3
7
7
2
0
.
9
6
1
9
0
.
9
5
9
1
0
.
9
6
5
0
0
.
9
6
2
0
6
6
2
0
.
9
6
7
7
0
.
9
5
9
5
0
.
9
7
6
7
0
.
9
6
8
0
2
3
9
6
3
0
.
9
6
2
4
0
.
9
5
7
2
0
.
9
6
8
1
0
.
9
6
2
6
6
5
8
0
.
9
6
2
5
0
.
9
5
5
3
0
.
9
7
0
4
0
.
9
6
2
8
2
3
5
7
4
0
.
9
5
9
9
0
.
9
4
3
4
0
.
9
7
8
4
0
.
9
6
0
6
6
5
4
0
.
9
6
3
5
0
.
9
5
9
2
0
.
9
6
8
3
0
.
9
6
3
7
2
4
1
9
5
0
.
9
5
5
3
0
.
9
5
1
1
0
.
9
5
9
9
0
.
9
5
5
5
6
5
4
0
.
9
5
6
2
0
.
9
4
8
2
0
.
9
6
5
2
0
.
9
5
6
7
2
4
3
4
A
v
e
r
a
g
e
0
.
9
6
1
3
0
.
9
5
4
8
0
.
9
6
8
3
0
.
9
6
1
5
6
5
5
0
.
9
6
0
7
0
.
9
5
3
8
0
.
9
6
8
3
0
.
9
6
1
0
2
3
9
7
T
h
e
co
n
f
u
s
io
n
m
atr
ix
o
f
th
e
ex
p
er
im
en
t
is
s
h
o
wn
in
Fig
u
r
e
3
,
wh
er
e
Fig
u
r
e
3
(
a
)
s
h
o
ws
r
esu
lt
s
f
o
r
th
e
SP
D
d
ataset
an
d
Fig
u
r
e
3
(
b
)
s
h
o
ws
r
esu
lts
f
o
r
th
e
B
SD
d
ataset.
E
v
alu
atio
n
r
esu
lts
o
n
th
e
b
est
n
u
m
b
er
o
f
f
o
ld
s
in
d
icate
d
th
at,
f
o
r
th
e
SP
D
d
ataset,
th
e
m
o
d
el
m
ad
e
6
4
class
if
icatio
n
er
r
o
r
s
(
3
.
2
9
%),
co
n
s
is
tin
g
o
f
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
C
o
mb
in
a
tio
n
o
f
b
in
a
r
y
p
a
r
ticl
e
s
w
a
r
m
o
p
timiz
a
tio
n
a
n
d
r
a
n
d
o
m
fo
r
est fo
r
s
tr
o
ke
d
is
ea
s
e
…
(
S
u
tikn
o
)
2295
3
6
f
alse
p
o
s
itiv
es
(
1
.
8
5
%)
an
d
2
8
f
alse
n
eg
ativ
es
(
1
.
4
4
%).
Fo
r
th
e
B
SD
d
ata
s
et,
th
er
e
we
r
e
6
1
class
if
icatio
n
er
r
o
r
s
(
3
.
2
3
%),
in
clu
d
i
n
g
3
9
f
alse
p
o
s
itiv
es
(
2
.
0
6
%)
an
d
2
2
f
alse
n
eg
ativ
es
(
1
.
1
6
%).
Fi
g
u
r
e
4
p
r
esen
ts
th
e
r
esu
lts
o
f
th
e
f
itn
ess
f
u
n
ctio
n
f
o
r
f
ea
tu
r
e
s
elec
tio
n
.
Fig
u
r
e
4
(
a)
p
r
esen
ts
th
e
f
itn
ess
o
b
tain
ed
f
r
o
m
th
e
SP
D
d
ataset,
wh
ile
Fig
u
r
e
4
(
b
)
s
h
o
ws
th
e
f
itn
ess
f
o
r
th
e
B
SD
d
at
aset.
T
h
e
p
er
f
o
r
m
a
n
ce
im
p
r
o
v
em
en
t
o
b
tain
ed
b
y
in
teg
r
atin
g
B
PS
O
with
R
F
is
m
ain
ly
d
u
e
to
B
PS
O's
ab
ilit
y
to
s
elec
t
a
m
o
r
e
in
f
o
r
m
ativ
e
f
ea
tu
r
e
s
u
b
s
et
wh
ile
elim
in
atin
g
r
ed
u
n
d
a
n
t
an
d
ir
r
elev
an
t
f
ea
tu
r
es.
T
h
is
f
ea
tu
r
e
r
ed
u
ctio
n
r
ed
u
ce
s
n
o
is
e
an
d
o
v
er
f
itti
n
g
,
e
n
ab
lin
g
th
e
R
F to
u
n
d
er
s
tan
d
d
is
cr
im
in
ativ
e
p
atter
n
s
b
etter
a
n
d
im
p
r
o
v
e
g
e
n
er
aliza
tio
n
.
(
a)
(
b
)
Fig
u
r
e
3
.
C
o
n
f
u
s
io
n
m
atr
i
x
o
f
th
e
p
r
o
p
o
s
ed
m
eth
o
d
r
esu
lts
f
o
r
(
a)
SP
D
d
ataset
an
d
(
b
)
B
SD d
ataset
(
a)
(
b
)
Fig
u
r
e
4
.
C
o
n
v
er
g
e
n
ce
cu
r
v
e
o
f
B
P
SO f
ea
tu
r
e
s
elec
tio
n
f
o
r
(
a)
SP
D
d
ataset
an
d
(
b
)
B
SD d
ataset
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
3
,
J
u
n
e
2
0
2
6
:
2
2
9
0
-
2
2
9
9
2296
T
h
e
p
r
o
p
o
s
ed
f
ea
tu
r
e
s
elec
tio
n
was
th
en
co
m
p
ar
ed
with
o
th
er
f
ea
tu
r
e
s
elec
tio
n
m
eth
o
d
s
,
n
am
ely
B
o
r
u
ta,
MI
,
an
d
GA.
T
h
e
r
es
u
lts
o
f
th
is
c
o
m
p
ar
is
o
n
ar
e
s
h
o
wn
in
T
ab
le
6
.
I
n
th
e
SP
D
d
ataset,
th
e
p
r
o
p
o
s
ed
m
eth
o
d
o
u
tp
e
r
f
o
r
m
s
th
e
o
th
er
s
in
r
elatio
n
to
ac
c
u
r
ac
y
,
r
ec
al
l,
an
d
F1
-
s
co
r
e.
Me
an
wh
ile,
i
n
th
e
B
SD
d
ataset,
MI
p
er
f
o
r
m
s
b
etter
th
an
th
e
o
th
er
s
,
with
th
e
p
r
o
p
o
s
ed
m
eth
o
d
s
lig
h
tly
b
elo
w
it.
B
o
r
u
ta
an
d
MI
r
eq
u
ir
e
less
tim
e
co
m
p
ar
ed
t
o
GA
an
d
PS
O.
B
o
r
u
ta
an
d
MI
ar
e
f
ilter
-
b
ased
f
ea
tu
r
e
s
elec
tio
n
m
eth
o
d
s
,
wh
er
ea
s
GA
an
d
PS
O
ar
e
wr
ap
p
er
-
b
ased
a
p
p
r
o
ac
h
es th
at
g
en
er
ally
r
eq
u
ir
e
lo
n
g
er
co
m
p
u
tatio
n
al
tim
e
.
T
ab
le
6
.
Per
f
o
r
m
an
ce
co
m
p
a
r
is
o
n
o
f
th
e
p
r
o
p
o
s
ed
m
eth
o
d
w
ith
o
th
er
f
ea
t
u
r
e
s
elec
tio
n
m
et
h
o
d
s
M
e
t
h
o
d
S
P
D
d
a
t
a
se
t
B
S
D
d
a
t
a
se
t
A
c
c
u
r
a
c
y
Pre
c
i
s
i
o
n
Rec
a
l
l
F1
-
s
c
o
r
e
Ti
me
(
s)
A
c
c
u
r
a
c
y
Pre
c
i
s
i
o
n
Rec
a
l
l
F1
-
s
c
o
r
e
Ti
me
(
s)
B
o
r
u
t
a
0
.
9
3
0
5
0
.
9
2
9
5
0
.
9
3
1
9
0
.
9
3
0
6
12
0
.
9
3
0
8
0
.
9
2
8
0
0
.
9
3
4
1
0
.
9
3
1
0
10
MI
0
.
9
5
6
6
0
.
9
5
9
3
0
.
9
5
3
7
0
.
9
5
6
3
31
0
.
9
6
1
4
0
.
9
5
3
5
0
.
9
7
0
2
0
.
9
6
1
8
32
GA
0
.
9
5
8
7
0
.
9
5
2
2
0
.
9
6
6
0
0
.
9
5
9
0
1
6
4
1
0
.
9
6
0
0
0
.
9
5
4
1
0
.
9
6
6
6
0
.
9
6
0
3
1
6
2
4
P
r
o
p
o
se
d
0
.
9
6
1
3
0
.
9
5
4
8
0
.
9
6
8
3
0
.
9
6
1
5
6
5
5
0
.
9
6
0
7
0
.
9
5
3
8
0
.
9
6
8
3
0
.
9
6
1
0
2
3
9
7
A
co
m
p
ar
ativ
e
an
al
y
s
is
is
co
n
d
u
cted
b
etwe
en
th
e
p
r
o
p
o
s
e
d
m
eth
o
d
,
p
r
e
v
io
u
s
r
esear
ch
ap
p
r
o
ac
h
es,
an
d
d
ee
p
lear
n
in
g
m
o
d
els.
T
h
ese
m
o
d
els
ar
e
SVM
[
3
]
–
[
5
]
,
DT
[
2
3
]
,
KNN
[
2
3
]
,
NB
[
3
]
,
an
d
C
NN,
as
s
u
m
m
ar
ized
in
T
ab
le
7
.
T
h
e
o
u
tco
m
es
in
d
icate
th
at
th
e
p
r
o
p
o
s
ed
m
eth
o
d
y
ield
s
b
etter
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
an
d
F1
-
s
co
r
e
th
a
n
th
e
o
th
e
r
s
,
alth
o
u
g
h
its
r
ec
all
is
lo
wer
th
an
th
at
o
f
th
e
KNN
m
eth
o
d
.
C
o
m
p
ar
is
o
n
o
f
ac
cu
r
ac
y
r
esu
lts
b
etwe
en
th
e
p
r
o
p
o
s
ed
m
et
h
o
d
an
d
o
th
er
m
et
h
o
d
s
is
s
h
o
wn
in
Fig
u
r
e
5
.
T
h
e
s
tu
d
y
s
u
g
g
ests
th
at
th
e
p
r
o
p
o
s
ed
B
PS
O
-
R
F
m
o
d
el
ca
n
s
u
p
p
o
r
t
ea
r
ly
s
tr
o
k
e
s
cr
ee
n
in
g
b
y
id
en
tify
in
g
h
i
g
h
-
r
is
k
in
d
iv
i
d
u
als
an
d
en
ab
lin
g
p
r
e
v
en
tiv
e
s
tr
ateg
ies
th
r
o
u
g
h
life
s
ty
le
m
o
n
ito
r
in
g
an
d
in
ter
v
en
tio
n
s
b
ased
o
n
k
ey
r
i
s
k
f
ac
to
r
s
.
Ho
wev
e
r
,
th
is
s
tu
d
y
h
as
s
ev
er
al
lim
itatio
n
s
,
in
clu
d
in
g
t
h
e
u
s
e
o
f
a
r
elativ
ely
s
m
all
d
ata
s
et.
Fu
r
th
er
m
o
r
e
,
s
tr
o
k
e
p
r
e
d
ictio
n
was
s
im
p
lifie
d
as
a
b
in
ar
y
class
if
icatio
n
task
,
wh
er
ea
s
r
ea
l
-
wo
r
l
d
clin
ical
s
ettin
g
s
in
v
o
lv
e
a
v
ar
iety
o
f
s
tr
o
k
e
s
u
b
ty
p
es
a
n
d
s
ev
er
it
y
lev
els
th
at
wer
e
n
o
t c
o
n
s
id
er
e
d
.
T
ab
le
7
.
C
o
m
p
a
r
ativ
e
ass
ess
m
en
t o
f
th
e
p
r
o
p
o
s
ed
m
eth
o
d
a
n
d
r
elate
d
s
tu
d
ies
M
e
t
h
o
d
S
P
D
d
a
t
a
se
t
B
S
D
d
a
t
a
se
t
A
c
c
u
r
a
c
y
Pre
c
i
s
i
o
n
Rec
a
l
l
F1
-
s
c
o
r
e
A
c
c
u
r
a
c
y
Pre
c
i
s
i
o
n
Rec
a
l
l
F1
-
s
c
o
r
e
S
V
M
[
3
]
–
[
5
]
0
.
8
3
2
9
0
.
8
1
1
6
0
.
8
6
7
0
0
.
8
3
8
4
0
.
8
4
1
2
0
.
8
1
7
4
0
.
8
7
9
3
0
.
8
4
7
1
D
T
[
2
3
]
0
.
9
2
5
1
0
.
9
1
4
8
0
.
9
3
7
6
0
.
9
2
6
0
0
.
9
2
5
3
0
.
9
1
4
4
0
.
9
3
8
7
0
.
9
2
6
3
K
N
N
[
2
3
]
0
.
9
1
3
0
0
.
8
5
6
2
0
.
9
9
3
0
0
.
9
1
9
5
0
.
9
1
8
6
0
.
8
6
3
1
0
.
9
9
5
1
0
.
9
2
4
4
N
B
[
3
]
0
.
7
4
3
0
0
.
7
5
0
3
0
.
7
2
8
2
0
.
7
3
9
0
0
.
7
2
4
2
0
.
7
4
3
9
0
.
6
8
4
1
0
.
7
1
2
6
C
N
N
0
.
8
6
1
3
0
.
8
2
5
9
0
.
9
1
6
4
0
.
8
6
8
6
0
.
8
7
3
1
0
.
8
3
9
4
0
.
9
2
3
3
0
.
8
7
9
3
P
r
o
p
o
se
d
0
.
9
6
1
3
0
.
9
5
4
8
0
.
9
6
8
3
0
.
9
6
1
5
0
.
9
6
0
7
0
.
9
5
3
8
0
.
9
6
8
3
0
.
9
6
1
0
Fig
u
r
e
5
.
C
o
m
p
a
r
is
o
n
o
f
ac
cu
r
ac
y
b
etwe
en
th
e
p
r
o
p
o
s
ed
m
et
h
o
d
an
d
o
th
er
m
eth
o
d
s
0.83
29
0.92
51
0.91
30
0.74
30
0.90
74
0.92
12
0.85
82
0.96
05
0.93
05
0.95
66
0.95
87
0.86
13
0.96
13
0.84
12
0.92
53
0.91
86
0.72
42
0.91
80
0.92
75
0.86
79
0.96
06
0.93
08
0.96
14
0.96
00
0.87
31
0.960
7
0.7
0
0.7
5
0.8
0
0.8
5
0.9
0
0.9
5
1.0
0
S
V
M
DT
KNN
NB
X
G
B
o
o
st
Li
g
t
G
B
M
C
a
t
B
o
o
st
RF
B
o
r
ut
a+
R
F
M
I+
R
F
G
A
+
R
F
C
N
N
P
r
o
po
se
d
A
ccur
acy
M
e
t
hod
S
P
D da
t
as
e
t
B
S
D
d
at
as
e
t
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
C
o
mb
in
a
tio
n
o
f
b
in
a
r
y
p
a
r
ticl
e
s
w
a
r
m
o
p
timiz
a
tio
n
a
n
d
r
a
n
d
o
m
fo
r
est fo
r
s
tr
o
ke
d
is
ea
s
e
…
(
S
u
tikn
o
)
2297
4.
CO
NCLU
SI
O
N
T
h
is
s
tu
d
y
p
r
o
p
o
s
ed
co
m
b
in
i
n
g
B
PS
O
an
d
R
F
to
p
r
e
d
ict
s
tr
o
k
e,
r
ep
r
esen
tin
g
th
e
f
ir
s
t
s
y
s
tem
ati
c
in
teg
r
atio
n
o
f
B
PS
O
with
R
F.
T
h
e
B
PS
O
m
eth
o
d
s
elec
ted
f
e
atu
r
es,
an
d
R
F
was
ap
p
lied
to
class
if
y
th
em
.
T
h
e
r
esu
lts
s
h
o
wed
th
at
ad
d
in
g
B
PS
O
co
u
ld
im
p
r
o
v
e
ac
c
u
r
ac
y
,
ac
h
iev
in
g
b
etter
r
esu
lts
th
an
p
r
ev
io
u
s
r
esear
ch
.
T
h
e
B
PS
O
m
eth
o
d
id
en
tifie
d
im
p
o
r
tan
t
f
ea
tu
r
es
th
at
s
ig
n
i
f
ican
tly
af
f
ec
ted
s
tr
o
k
e
d
is
ea
s
e.
T
h
ese
f
ea
tu
r
es
wer
e
g
en
d
er
,
ag
e,
w
o
r
k
t
y
p
e,
r
esid
en
ce
ty
p
e,
av
er
ag
e
g
lu
c
o
s
e
lev
el,
B
MI
,
an
d
s
m
o
k
in
g
s
tatu
s
f
o
r
th
e
SP
D
d
ataset;
an
d
g
e
n
d
er
,
ag
e,
ev
e
r
m
ar
r
ied
,
wo
r
k
ty
p
e,
r
esid
en
c
e
ty
p
e,
av
er
a
g
e
g
l
u
co
s
e
lev
el,
B
MI
,
an
d
s
m
o
k
in
g
s
tatu
s
f
o
r
th
e
B
SD
d
ataset.
F
u
tu
r
e
s
tu
d
ies
s
h
o
u
ld
e
x
p
lo
r
e
th
e
u
s
e
o
f
lar
g
e
r
an
d
m
o
r
e
d
iv
er
s
e
d
atasets
,
th
e
in
teg
r
atio
n
o
f
m
u
ltimo
d
al
clin
ical
d
ata,
an
d
th
e
ad
o
p
tio
n
o
f
ex
p
lain
ab
le
AI
tech
n
iq
u
es
to
f
u
r
th
er
en
h
a
n
ce
m
o
d
el
r
o
b
u
s
tn
ess
,
clin
ical
r
el
ev
an
ce
,
a
n
d
in
te
r
p
r
etab
ilit
y
.
I
n
ad
d
itio
n
,
th
e
p
r
o
p
o
s
ed
m
o
d
el
ca
n
b
e
ex
ten
d
ed
to
war
d
in
teg
r
ati
o
n
in
t
o
r
ea
l
-
t
im
e
h
o
s
p
ital
ap
p
licatio
n
s
a
n
d
clin
ical
d
ec
is
io
n
s
u
p
p
o
r
t
s
y
s
tem
s
to
s
u
p
p
o
r
t
h
ea
lth
ca
r
e
p
r
o
f
ess
io
n
als in
ea
r
ly
s
tr
o
k
e
r
is
k
ass
ess
m
en
t a
n
d
tim
ely
in
ter
v
en
tio
n
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
T
h
is
r
esear
ch
was
f
u
n
d
e
d
f
r
o
m
Facu
lty
o
f
Scien
ce
an
d
Ma
th
em
atics
at
Dip
o
n
eg
o
r
o
Un
iv
er
s
ity
th
r
o
u
g
h
f
u
n
d
in
g
Dea
n
'
s
Dec
r
ee
Nu
m
b
er
2
0
/UN7
.
F8
/HK/I
I
/2
0
2
4
.
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
Su
tik
n
o
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
R
is
m
iy
ati
✓
✓
✓
✓
✓
✓
✓
Kh
ad
ijah
✓
✓
✓
✓
✓
✓
✓
Ab
d
u
l K
ar
im
✓
✓
✓
✓
✓
✓
✓
✓
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
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
T
h
e
au
th
o
r
s
s
tate
n
o
co
n
f
lict o
f
in
ter
est.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
is
p
ap
er
p
r
esen
ts
two
d
atasets
th
at
h
av
e
b
ee
n
u
s
ed
an
d
a
r
e
av
ailab
le
f
r
o
m
Kag
g
le
in
t
h
e
s
tr
o
k
e
p
r
ed
ictio
n
d
ataset
,
r
ef
er
en
ce
n
u
m
b
er
[
2
4
]
an
d
i
n
th
e
b
r
ain
s
tr
o
k
e
d
ataset
,
r
ef
e
r
en
ce
n
u
m
b
er
[
2
5
]
.
RE
F
E
R
E
NC
E
S
[
1
]
V
.
L
.
F
e
i
g
i
n
e
t
a
l
.
,
“
W
o
r
l
d
st
r
o
k
e
o
r
g
a
n
i
z
a
t
i
o
n
(
W
S
O
)
:
g
l
o
b
a
l
st
r
o
k
e
f
a
c
t
s
h
e
e
t
2
0
2
2
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
S
t
r
o
k
e
,
v
o
l
.
1
7
,
n
o
.
1
,
p
p
.
1
8
–
2
9
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
7
7
/
1
7
4
7
4
9
3
0
2
1
1
0
6
5
9
1
7
.
[
2
]
M
.
A
l
t
a
y
e
b
a
n
d
A
.
A
r
a
b
i
a
t
,
“
E
n
h
a
n
c
i
n
g
st
r
o
k
e
p
r
e
d
i
c
t
i
o
n
u
s
i
n
g
t
h
e
w
a
i
k
a
t
o
e
n
v
i
r
o
n
m
e
n
t
f
o
r
k
n
o
w
l
e
d
g
e
a
n
a
l
y
si
s
,
”
I
AE
S
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
1
3
,
n
o
.
3
,
p
p
.
3
0
1
0
–
3
0
1
7
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
a
i
.
v
1
3
.
i
3
.
p
p
3
0
1
0
-
3
0
1
7
.
[
3
]
I
.
M
i
sh
r
a
a
n
d
S
.
M
o
h
a
p
a
t
r
a
,
“
A
n
e
n
h
a
n
c
e
d
a
p
p
r
o
a
c
h
f
o
r
a
n
a
l
y
z
i
n
g
t
h
e
p
e
r
f
o
r
ma
n
c
e
o
f
h
e
a
r
t
st
r
o
k
e
p
r
e
d
i
c
t
i
o
n
w
i
t
h
mac
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
1
5
,
n
o
.
6
,
p
p
.
3
2
5
7
–
3
2
7
0
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s
4
1
8
7
0
-
023
-
0
1
3
2
1
-
8.
[
4
]
S
.
M
u
s
h
t
a
q
,
K
.
S
.
S
a
i
n
i
,
a
n
d
S
.
B
a
s
h
i
r
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
f
o
r
b
r
a
i
n
st
r
o
k
e
p
r
e
d
i
c
t
i
o
n
,
”
i
n
2
0
2
3
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
D
i
sru
p
t
i
v
e
T
e
c
h
n
o
l
o
g
i
e
s
(
I
C
D
T
)
,
2
0
2
3
,
p
p
.
4
0
1
–
4
0
8
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
D
T5
7
9
2
9
.
2
0
2
3
.
1
0
1
5
1
1
4
8
.
[
5
]
I
.
G
.
I
v
a
n
o
v
,
Y
.
K
u
m
c
h
e
v
,
a
n
d
V
.
J.
H
o
o
p
e
r
,
“
A
n
o
p
t
i
m
i
z
a
t
i
o
n
p
r
e
c
i
se
mo
d
e
l
o
f
st
r
o
k
e
d
a
t
a
t
o
i
mp
r
o
v
e
s
t
r
o
k
e
p
r
e
d
i
c
t
i
o
n
,
”
Al
g
o
r
i
t
h
m
s
,
v
o
l
.
1
6
,
n
o
.
9
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
a
1
6
0
9
0
4
1
7
.
[
6
]
G
.
F
.
I
ssa,
K
.
S
h
a
a
l
a
n
,
Y
.
S
h
a
a
l
a
n
,
H
.
A
.
S
a
e
e
d
,
N
.
F
a
t
i
ma,
a
n
d
A
.
U
.
R
e
h
m
a
n
,
“
B
r
a
i
n
s
t
r
o
k
e
p
r
e
d
i
c
t
i
o
n
u
si
n
g
A
N
N
,
”
i
n
2
0
2
2
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
y
b
e
r
R
e
si
l
i
e
n
c
e
(
I
C
C
R)
,
2
0
2
2
,
p
p
.
1
–
9
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
C
R
5
6
2
5
4
.
2
0
2
2
.
9
9
9
5
8
8
5
.
[
7
]
A
.
La
k
k
sh
m
a
n
a
n
,
S
.
R
.
A
d
a
l
i
n
e
,
N
.
P
r
i
y
a
n
k
a
,
D
.
B
.
A
n
a
n
d
,
K
.
N
a
g
a
r
a
j
u
,
a
n
d
U
.
G
.
N
a
i
d
u
,
“
A
n
o
v
e
l
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
b
a
se
d
st
r
o
k
e
p
r
e
d
i
c
t
i
o
n
s
y
st
e
m
u
s
i
n
g
ma
g
n
e
t
i
c
r
e
so
n
a
n
c
e
i
m
a
g
i
n
g
a
n
d
a
d
a
p
t
i
v
e
n
e
w
f
u
z
z
y
i
n
f
e
r
e
n
c
e
s
y
st
e
m,”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
I
n
t
e
l
l
i
g
e
n
t
S
y
s
t
e
m
s
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
i
n
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
1
2
,
n
o
.
1
0
s,
p
p
.
5
7
6
–
5
8
5
,
2
0
2
4
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
3
,
J
u
n
e
2
0
2
6
:
2
2
9
0
-
2
2
9
9
2298
[
8
]
M
.
A
s
h
r
a
f
u
z
z
a
ma
n
,
S
.
S
a
h
a
,
a
n
d
K
.
N
u
r
,
“
P
r
e
d
i
c
t
i
o
n
o
f
st
r
o
k
e
d
i
s
e
a
s
e
u
si
n
g
d
e
e
p
C
N
N
-
b
a
s
e
d
a
p
p
r
o
a
c
h
,
”
J
o
u
r
n
a
l
o
f
A
d
v
a
n
c
e
s
i
n
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
1
3
,
n
o
.
6
,
2
0
2
2
,
d
o
i
:
1
0
.
1
2
7
2
0
/
j
a
i
t
.
1
3
.
6
.
6
0
4
-
6
1
3
.
[
9
]
X
.
Y
e
,
W
.
X
u
,
X
.
Y
e
,
D
.
L
o
n
g
,
Q
.
Y
i
n
,
a
n
d
B
.
H
u
a
n
g
,
“
S
t
r
o
k
e
p
r
e
d
i
c
t
i
o
n
u
si
n
g
t
h
e
t
r
u
st
e
v
a
l
u
a
t
i
o
n
w
i
t
h
d
a
t
a
l
e
a
k
a
g
e
a
v
o
i
d
i
n
g
,
”
J
o
u
rn
a
l
o
f
Ph
y
si
c
s:
C
o
n
f
e
re
n
c
e
S
e
ri
e
s
,
v
o
l
.
2
5
6
0
,
n
o
.
1
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
8
8
/
1
7
4
2
-
6
5
9
6
/
2
5
6
0
/
1
/
0
1
2
0
5
1
.
[
1
0
]
M
.
G
.
R
a
o
,
K
.
P
,
K
.
R
.
K
o
t
i
a
n
,
a
n
d
D
.
P
.
H
e
g
d
e
,
“
M
u
l
t
i
m
o
d
a
l
a
p
p
r
o
a
c
h
f
o
r
p
r
e
d
i
c
t
i
n
g
t
h
e
b
r
a
i
n
st
r
o
k
e
u
si
n
g
t
h
e
mac
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s,
”
i
n
2
0
2
2
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
D
a
t
a
E
n
g
i
n
e
e
ri
n
g
(
AI
D
E)
,
2
0
2
2
,
p
p
.
2
4
2
–
2
4
7
,
d
o
i
:
1
0
.
1
1
0
9
/
A
I
D
E5
7
1
8
0
.
2
0
2
2
.
1
0
0
6
0
4
2
4
.
[
1
1
]
U
.
S
i
n
g
h
,
A
.
K
.
Je
n
a
,
a
n
d
M
.
T.
H
a
q
u
e
,
“
A
n
e
n
s
e
m
b
l
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
a
n
d
a
n
a
l
y
s
i
s
f
o
r
s
t
r
o
k
e
p
r
e
d
i
c
t
i
o
n
d
a
t
a
se
t
,
”
i
n
2
0
2
2
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
A
d
v
a
n
c
e
m
e
n
t
s
i
n
S
m
a
rt
,
S
e
c
u
r
e
a
n
d
I
n
t
e
l
l
i
g
e
n
t
C
o
m
p
u
t
i
n
g
(
A
S
S
I
C
)
,
2
0
2
2
,
p
p
.
1
–
8
,
d
o
i
:
1
0
.
1
1
0
9
/
A
S
S
I
C
5
5
2
1
8
.
2
0
2
2
.
1
0
0
8
8
3
6
3
.
[
1
2
]
P
.
P
a
l
,
M
.
N
a
n
d
a
l
,
S
.
D
i
k
s
h
i
t
,
A
.
T
h
u
su
,
a
n
d
H
.
V
.
S
i
n
g
h
,
“
H
a
r
n
e
ssi
n
g
t
h
e
p
o
w
e
r
o
f
e
n
s
e
m
b
l
e
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
f
o
r
t
h
e
h
e
a
r
t
st
r
o
k
e
c
l
a
ss
i
f
i
c
a
t
i
o
n
,
”
EAI
E
n
d
o
r
sed
T
r
a
n
s
a
c
t
i
o
n
s
o
n
Pe
rv
a
si
v
e
H
e
a
l
t
h
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
9
,
n
o
.
1
,
2
0
2
3
,
d
o
i
:
1
0
.
4
1
0
8
/
e
e
t
p
h
t
.
9
.
4
6
1
7
.
[
1
3
]
E.
D
r
i
t
s
a
s
a
n
d
M
.
Tr
i
g
k
a
,
“
S
t
r
o
k
e
r
i
sk
p
r
e
d
i
c
t
i
o
n
w
i
t
h
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s,”
S
e
n
s
o
rs
,
v
o
l
.
2
2
,
n
o
.
1
3
,
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
s
2
2
1
3
4
6
7
0
.
[
1
4
]
S
.
A
.
M
o
st
a
f
a
,
D
.
S
.
E
l
z
a
n
f
a
l
y
,
a
n
d
A
.
E
.
Y
a
k
o
u
b
,
“
A
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
e
n
s
e
mb
l
e
c
l
a
ss
i
f
i
e
r
f
o
r
p
r
e
d
i
c
t
i
o
n
o
f
b
r
a
i
n
st
r
o
k
e
s,”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
A
d
v
a
n
c
e
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
3
,
n
o
.
1
2
,
2
0
2
2
,
d
o
i
:
1
0
.
1
4
5
6
9
/
I
JA
C
S
A
.
2
0
2
2
.
0
1
3
1
2
3
2
.
[
1
5
]
A
.
R
e
h
ma
n
,
T
.
A
l
a
m
,
M
.
M
u
j
a
h
i
d
,
F
.
S
.
A
l
a
mr
i
,
B
.
A
l
G
h
o
f
a
i
l
y
,
a
n
d
T.
S
a
b
a
,
“
R
D
E
T
s
t
a
c
k
i
n
g
c
l
a
ssi
f
i
e
r
:
a
n
o
v
e
l
mac
h
i
n
e
l
e
a
r
n
i
n
g
b
a
s
e
d
a
p
p
r
o
a
c
h
f
o
r
st
r
o
k
e
p
r
e
d
i
c
t
i
o
n
u
s
i
n
g
i
mb
a
l
a
n
c
e
d
a
t
a
,
”
Pe
e
rJ
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
9
,
2
0
2
3
,
d
o
i
:
1
0
.
7
7
1
7
/
p
e
e
r
j
-
c
s
.
1
6
8
4
.
[
1
6
]
P
.
N
.
S
r
i
n
i
v
a
s
u
,
U
.
S
i
r
i
s
h
a
,
K
.
S
a
n
d
e
e
p
,
S
.
P
.
P
r
a
v
e
e
n
,
L.
P
.
M
a
g
u
l
u
r
i
,
a
n
d
T.
B
i
k
k
u
,
“
A
n
i
n
t
e
r
p
r
e
t
a
b
l
e
a
p
p
r
o
a
c
h
w
i
t
h
e
x
p
l
a
i
n
a
b
l
e
A
I
f
o
r
h
e
a
r
t
st
r
o
k
e
p
r
e
d
i
c
t
i
o
n
,
”
D
i
a
g
n
o
st
i
c
s
,
v
o
l
.
1
4
,
n
o
.
2
,
2
0
2
4
,
d
o
i
:
1
0
.
3
3
9
0
/
d
i
a
g
n
o
s
t
i
c
s1
4
0
2
0
1
2
8
.
[
1
7
]
H
.
M
.
-
S
o
l
i
s
,
R
.
P
.
-
S
i
g
u
a
s
,
E
.
M
.
-
S
o
l
i
s,
L.
M
.
-
Z
a
m
u
d
i
o
,
S
.
M
.
-
G
o
me
z
,
a
n
d
J.
F
.
V
.
-
M
o
l
i
n
a
,
“
A
p
p
l
i
c
a
t
i
o
n
o
f
mac
h
i
n
e
l
e
a
r
n
i
n
g
f
o
r
t
h
e
p
r
e
d
i
c
t
i
o
n
o
f
s
t
r
o
k
e
s
i
n
P
e
r
u
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
En
g
i
n
e
e
ri
n
g
T
r
e
n
d
s
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
7
0
,
n
o
.
1
0
,
p
p
.
5
4
–
6
0
,
2
0
2
2
,
d
o
i
:
1
0
.
1
4
4
4
5
/
2
2
3
1
5
3
8
1
/
I
JETT
-
V
7
0
I
1
0
P
2
0
7
.
[
1
8
]
N
.
B
i
sw
a
s,
K
.
M
.
M
.
U
d
d
i
n
,
S
.
T.
R
i
k
t
a
,
a
n
d
S
.
K
.
D
e
y
,
“
A
c
o
m
p
a
r
a
t
i
v
e
a
n
a
l
y
si
s
o
f
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
c
l
a
s
si
f
i
e
r
s
f
o
r
st
r
o
k
e
p
r
e
d
i
c
t
i
o
n
:
a
p
r
e
d
i
c
t
i
v
e
a
n
a
l
y
t
i
c
s
a
p
p
r
o
a
c
h
,
”
H
e
a
l
t
h
c
a
re
A
n
a
l
y
t
i
c
s
,
v
o
l
.
2
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
h
e
a
l
t
h
.
2
0
2
2
.
1
0
0
1
1
6
.
[
1
9
]
E.
S
t
e
n
w
i
g
,
P
.
S
.
R
o
ss
i
,
G
.
S
a
l
v
i
,
a
n
d
N
.
K
.
S
k
j
æ
r
v
o
l
d
,
“
T
h
e
i
m
p
a
c
t
o
f
f
e
a
t
u
r
e
c
o
mb
i
n
a
t
i
o
n
s
o
n
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
m
o
d
e
l
s
f
o
r
i
n
-
h
o
s
p
i
t
a
l
m
o
r
t
a
l
i
t
y
p
r
e
d
i
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
5
,
n
o
.
1
,
2
0
2
5
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
5
9
8
-
0
2
5
-
2
6
6
1
1
-
y.
[
2
0
]
J.
L
e
e
e
t
a
l
.
,
“
C
o
m
p
a
r
a
t
i
v
e
a
n
a
l
y
si
s
o
f
n
e
u
r
a
l
n
e
t
w
o
r
k
m
e
t
h
o
d
o
n
st
r
o
k
e
p
r
e
d
i
c
t
i
o
n
,
”
i
n
2
0
2
3
1
0
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
I
C
T
f
o
r
S
m
a
r
t
S
o
c
i
e
t
y
(
I
C
I
S
S
)
,
2
0
2
3
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
I
S
S
5
9
1
2
9
.
2
0
2
3
.
1
0
2
9
1
4
0
4
.
[
2
1
]
N
.
V
i
c
t
o
r
,
S
.
B
h
a
t
t
a
c
h
a
r
y
a
,
P
.
K
.
R
.
M
a
d
d
i
k
u
n
t
a
,
F
.
M
.
A
l
o
t
a
i
b
i
,
T.
R
.
G
a
d
e
k
a
l
l
u
,
a
n
d
R
.
H
.
J
h
a
v
e
r
i
,
“
F
L
-
P
S
O
:
a
f
e
d
e
r
a
t
e
d
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
w
i
t
h
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
b
r
a
i
n
st
r
o
k
e
p
r
e
d
i
c
t
i
o
n
,
”
i
n
2
0
2
3
I
E
EE/
AC
M
2
3
rd
I
n
t
e
r
n
a
t
i
o
n
a
l
S
y
m
p
o
s
i
u
m
o
n
C
l
u
st
e
r,
C
l
o
u
d
a
n
d
I
n
t
e
rn
e
t
C
o
m
p
u
t
i
n
g
Wo
r
k
s
h
o
p
s
(
C
C
G
ri
d
W)
,
2
0
2
3
,
p
p
.
3
3
–
3
8
,
d
o
i
:
1
0
.
1
1
0
9
/
C
C
G
r
i
d
W
5
9
1
9
1
.
2
0
2
3
.
0
0
0
2
0
.
[
2
2
]
Y
.
M
i
a
o
,
“
U
si
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
m
e
t
h
o
d
t
o
p
r
e
d
i
c
t
s
t
r
o
k
e
r
i
s
k
,
”
i
n
2
0
2
1
2
n
d
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
I
n
f
o
rm
a
t
i
o
n
S
c
i
e
n
c
e
a
n
d
Ed
u
c
a
t
i
o
n
(
I
C
I
S
E
-
I
E)
,
2
0
2
1
,
p
p
.
6
6
5
–
6
6
8
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
I
S
E
-
I
E5
3
9
2
2
.
2
0
2
1
.
0
0
1
5
6
.
[
2
3
]
M
.
C
.
D
a
s
e
t
a
l
.
,
“
A
c
o
m
p
a
r
a
t
i
v
e
s
t
u
d
y
o
f
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
e
s
f
o
r
h
e
a
r
t
st
r
o
k
e
p
r
e
d
i
c
t
i
o
n
,
”
i
n
2
0
2
3
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
S
m
a
r
t
A
p
p
l
i
c
a
t
i
o
n
s,
C
o
m
m
u
n
i
c
a
t
i
o
n
s
a
n
d
N
e
t
w
o
r
k
i
n
g
(
S
m
a
rt
N
e
t
s)
,
2
0
2
3
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
S
m
a
r
t
N
e
t
s
5
8
7
0
6
.
2
0
2
3
.
1
0
2
1
6
0
4
9
.
[
2
4
]
F
.
S
.
P
a
l
a
c
i
o
s,
“
S
t
r
o
k
e
p
r
e
d
i
c
t
i
o
n
d
a
t
a
s
e
t
,
”
K
a
g
g
l
e
.
2
0
2
1
.
A
c
c
e
ss
e
d
:
A
u
g
.
3
0
,
2
0
2
4
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s
:
/
/
w
w
w
.
k
a
g
g
l
e
.
c
o
m
/
d
a
t
a
se
t
s/
f
e
d
e
so
r
i
a
n
o
/
s
t
r
o
k
e
-
p
r
e
d
i
c
t
i
o
n
-
d
a
t
a
set
[
2
5
]
G
.
Ji
l
l
a
n
i
,
“
B
r
a
i
n
st
r
o
k
e
d
a
t
a
s
e
t
,
”
K
a
g
g
l
e
,
2
0
2
2
.
A
c
c
e
s
sed
:
A
u
g
.
3
0
,
2
0
2
4
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s
:
/
/
w
w
w
.
k
a
g
g
l
e
.
c
o
m
/
d
a
t
a
se
t
s/
j
i
l
l
a
n
i
s
o
f
t
t
e
c
h
/
b
r
a
i
n
-
st
r
o
k
e
-
d
a
t
a
s
e
t
[
2
6
]
Z.
Z
h
a
o
,
T
.
C
u
i
,
S
.
D
i
n
g
,
J.
L
i
,
a
n
d
A
.
G
.
B
e
l
l
o
t
t
i
,
“
R
e
sam
p
l
i
n
g
t
e
c
h
n
i
q
u
e
s
st
u
d
y
o
n
c
l
a
ss
i
m
b
a
l
a
n
c
e
p
r
o
b
l
e
m
i
n
c
r
e
d
i
t
r
i
sk
p
r
e
d
i
c
t
i
o
n
,
”
M
a
t
h
e
m
a
t
i
c
s
,
v
o
l
.
1
2
,
n
o
.
5
,
2
0
2
4
,
d
o
i
:
1
0
.
3
3
9
0
/
mat
h
1
2
0
5
0
7
0
1
.
[
2
7
]
J.
K
e
n
n
e
d
y
a
n
d
R
.
E
b
e
r
h
a
r
t
,
“
P
a
r
t
i
c
l
e
sw
a
r
m
o
p
t
i
mi
z
a
t
i
o
n
,
”
i
n
Pro
c
e
e
d
i
n
g
s
o
f
I
C
N
N
’
9
5
-
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
ren
c
e
o
n
N
e
u
r
a
l
N
e
t
w
o
rks
,
1
9
9
5
,
v
o
l
.
4
,
p
p
.
1
9
4
2
–
1
9
4
8
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
N
N
.
1
9
9
5
.
4
8
8
9
6
8
.
[
2
8
]
W.
-
L.
C
h
e
n
g
e
t
a
l
.
,
“
A
n
a
d
a
p
t
i
v
e
a
n
d
p
a
r
a
l
l
e
l
me
t
a
h
e
u
r
i
s
t
i
c
f
r
a
m
e
w
o
r
k
f
o
r
w
r
a
p
p
e
r
-
b
a
se
d
f
e
a
t
u
r
e
se
l
e
c
t
i
o
n
u
si
n
g
a
r
c
t
i
c
p
u
f
f
i
n
o
p
t
i
m
i
z
a
t
i
o
n
,
”
C
o
m
p
u
t
e
rs
,
Ma
t
e
r
i
a
l
s
& C
o
n
t
i
n
u
a
,
v
o
l
.
8
5
,
n
o
.
1
,
p
p
.
2
0
2
1
–
2
0
5
0
,
2
0
2
5
,
d
o
i
:
1
0
.
3
2
6
0
4
/
c
m
c
.
2
0
2
5
.
0
6
4
2
4
3
.
[
2
9
]
M
.
A
l
G
h
a
mr
i
,
D
.
I
b
r
a
h
i
m,
R
.
S
i
h
w
a
i
l
,
a
n
d
M
.
S
h
e
h
a
b
,
“
W
h
a
l
e
o
p
t
i
m
i
z
a
t
i
o
n
a
l
g
o
r
i
t
h
m
f
o
r
f
e
a
t
u
r
e
s
e
l
e
c
t
i
o
n
e
n
h
a
n
c
e
s
c
l
a
ss
i
f
i
c
a
t
i
o
n
i
n
ma
l
w
a
r
e
d
a
t
a
set
s
,
”
J
o
u
rn
a
l
o
f
C
o
m
p
u
t
a
t
i
o
n
a
l
a
n
d
C
o
g
n
i
t
i
v
e
En
g
i
n
e
e
r
i
n
g
,
v
o
l
.
4
,
n
o
.
3
,
p
p
.
3
8
7
–
3
9
6
,
2
0
2
4
,
d
o
i
:
1
0
.
4
7
8
5
2
/
b
o
n
v
i
e
w
JC
C
E
4
2
0
2
4
2
3
3
.
[
3
0
]
A
.
G
u
mm
a
r
a
j
u
,
A
.
K
.
B
.
S
h
e
n
o
y
,
a
n
d
S
.
N
.
P
a
i
,
“
P
e
r
f
o
r
m
a
n
c
e
c
o
mp
a
r
i
so
n
o
f
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
m
o
d
e
l
s
f
o
r
h
a
n
d
w
r
i
t
t
e
n
D
e
v
a
n
a
g
a
r
i
n
u
mera
l
s c
l
a
ss
i
f
i
c
a
t
i
o
n
,
”
I
EEE
A
c
c
e
ss
,
v
o
l
.
1
1
,
p
p
.
1
3
3
3
6
3
–
1
3
3
3
7
1
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
3
.
3
3
3
6
9
1
2
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Dr
.
S
u
tik
n
o
re
c
e
iv
e
d
a
Do
c
to
r
o
f
P
h
il
o
s
o
p
h
y
(
P
h
.
D.
)
d
e
g
re
e
i
n
C
o
m
p
u
ter
S
c
ien
c
e
fro
m
t
h
e
F
a
c
u
lt
y
o
f
M
a
th
e
m
a
ti
c
s
a
n
d
Na
tu
ra
l
S
c
ien
c
e
s
a
t
t
h
e
Un
i
v
e
rsitas
G
a
d
jah
M
a
d
a
,
In
d
o
n
e
sia
.
No
w
,
h
e
is
a
n
a
ss
istan
t
p
r
o
fe
ss
o
r
a
t
th
e
De
p
a
rtme
n
t
o
f
In
f
o
rm
a
ti
c
s,
F
a
c
u
lt
y
o
f
S
c
ien
c
e
s
a
n
d
M
a
t
h
e
m
a
ti
c
s,
Un
iv
e
rsitas
Dip
o
n
e
g
o
r
o
.
His
re
se
a
rc
h
in
tere
sts
i
n
c
lu
d
e
m
a
c
h
in
e
lea
rn
in
g
,
c
o
m
p
u
ter
v
isio
n
,
a
n
d
a
rti
ficia
l
i
n
telli
g
e
n
c
e
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
su
ti
k
n
o
@le
c
tu
re
r.
u
n
d
ip
.
a
c
.
id
.
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
C
o
mb
in
a
tio
n
o
f
b
in
a
r
y
p
a
r
ticl
e
s
w
a
r
m
o
p
timiz
a
tio
n
a
n
d
r
a
n
d
o
m
fo
r
est fo
r
s
tr
o
ke
d
is
ea
s
e
…
(
S
u
tikn
o
)
2299
Rism
iy
a
ti
re
c
e
iv
e
d
a
Ba
c
h
e
lo
r
o
f
En
g
i
n
e
e
rin
g
(B.
E
n
g
.
)
fr
o
m
th
e
S
c
h
o
o
l
o
f
El
e
c
tri
c
a
l
a
n
d
El
e
c
tro
n
ics
En
g
in
e
e
rin
g
,
Na
n
y
a
n
g
Tec
h
n
o
l
o
g
ica
l
Un
iv
e
rsity
(NTU),
in
2
0
0
7
a
n
d
a
M
a
ste
r
o
f
C
o
m
p
u
ter
S
c
ien
c
e
(M
.
Cs
.
)
fr
o
m
t
h
e
U
n
iv
e
rsitas
G
a
d
jah
M
a
d
a
,
I
n
d
o
n
e
sia
,
i
n
2
0
1
6
.
S
h
e
h
a
s
b
e
e
n
a
lec
tu
re
r
i
n
t
h
e
De
p
a
rtme
n
t
o
f
In
f
o
rm
a
ti
c
s
a
t
Un
i
v
e
rsitas
Dip
o
n
e
g
o
r
o
sin
c
e
2
0
1
7
.
He
r
m
a
in
re
se
a
rc
h
in
tere
sts
a
re
a
rti
ficia
l
in
telli
g
e
n
c
e
,
ima
g
e
p
ro
c
e
ss
in
g
,
a
n
d
m
a
c
h
in
e
lea
rn
in
g
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
rism
iy
a
ti
@liv
e
.
u
n
d
ip
.
a
c
.
i
d
.
K
h
a
d
ija
h
re
c
e
iv
e
d
a
Ba
c
h
e
l
o
r
o
f
In
f
o
rm
a
ti
c
s
En
g
i
n
e
e
rin
g
(
S
.
Ko
m
.
)
fro
m
th
e
Un
iv
e
rsitas
Dip
o
n
e
g
o
ro
,
I
n
d
o
n
e
s
ia,
in
2
0
1
1
a
n
d
a
M
a
ste
r
o
f
Co
m
p
u
ter
S
c
ien
c
e
(M
.
Cs
.
)
fro
m
th
e
Un
iv
e
rsitas
G
a
d
jah
M
a
d
a
,
I
n
d
o
n
e
sia
,
i
n
2
0
1
4
.
S
h
e
h
a
s b
e
e
n
a
le
c
tu
re
r
in
t
h
e
De
p
a
rtme
n
t
o
f
In
fo
rm
a
ti
c
s
a
t
Un
iv
e
rsitas
Dip
o
n
e
g
o
ro
si
n
c
e
2
0
1
4
.
He
r
m
a
in
re
se
a
rc
h
in
tere
sts
a
re
a
rti
ficia
l
in
telli
g
e
n
c
e
a
n
d
m
a
c
h
i
n
e
lea
rn
in
g
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
k
h
a
d
ij
a
h
@li
v
e
.
u
n
d
ip
.
a
c
.
i
d
.
Dr
.
Abd
u
l
K
a
r
i
m
re
c
e
iv
e
d
h
is
P
h
.
D.
fro
m
U
n
iv
e
rsita
s
G
a
d
jah
M
a
d
a
,
Yo
g
y
a
k
a
rta,
I
n
d
o
n
e
sia
.
He
is
c
u
rre
n
tl
y
a
r
e
se
a
rc
h
p
r
o
fe
ss
o
r
a
t
Ha
ll
y
m
U
n
iv
e
rsit
y
,
S
o
u
t
h
Ko
re
a
.
His
re
se
a
rc
h
in
tere
sts
sp
a
n
a
wid
e
ra
n
g
e
o
f
to
p
ics
,
i
n
c
lu
d
in
g
n
a
t
u
ra
l
lan
g
u
a
g
e
p
ro
c
e
ss
in
g
,
a
rti
ficia
l
in
telli
g
e
n
c
e
,
m
a
c
h
in
e
lea
rn
in
g
,
d
e
e
p
lea
rn
in
g
,
so
ftwa
re
e
n
g
i
n
e
e
rin
g
,
a
n
d
c
o
m
p
u
ter
v
isi
o
n
.
He
is
a
c
ti
v
e
l
y
w
o
rk
i
n
g
o
n
larg
e
lan
g
u
a
g
e
m
o
d
e
ls
(LL
M
s)
a
n
d
th
e
i
r
a
p
p
li
c
a
ti
o
n
s
t
o
v
a
rio
u
s
re
a
l
-
wo
rld
p
ro
b
lem
s,
a
d
v
a
n
c
in
g
AI
tec
h
n
o
l
o
g
ies
i
n
b
o
t
h
a
c
a
d
e
m
ic
a
n
d
p
ra
c
ti
c
a
l
d
o
m
a
in
s.
He
c
a
n
b
e
c
o
n
t
a
c
ted
a
t
e
m
a
il
:
a
b
d
u
ll
k
a
rim@
h
o
t
m
a
il
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.