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.
14
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
5
,
p
p
.
473
~
481
I
SS
N:
2
2
5
2
-
8
9
3
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijai.v
14
.i
1
.
p
p
4
7
3
-
4
8
1
473
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
i
.
ia
esco
r
e.
co
m
Ba
la
ncing
and meta
heuristic
t
ec
hni
ques for im
pro
v
ing
ma
chine
lea
rning
mo
dels i
n brain st
ro
ke pr
ediction
A
bd
Alla
h Ao
ura
g
h
1
,
M
o
ha
m
ed
B
a
ha
j
1
,
F
o
ua
d T
o
ufik
2
1
M
I
ET
La
b
o
r
a
t
o
r
y
,
F
a
c
u
l
t
y
o
f
S
c
i
e
n
c
e
s a
n
d
T
e
c
h
n
i
q
u
e
s,
H
a
ssa
n
1
st
U
n
i
v
e
r
si
t
y
,
S
e
t
t
a
t
,
M
o
r
o
c
c
o
2
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
s L
a
b
o
r
a
t
o
r
y
,
H
i
g
h
e
r
S
c
h
o
o
l
o
f
Te
c
h
n
o
l
o
g
y
,
M
o
h
a
mm
e
d
V
U
n
i
v
e
r
si
t
y
,
S
a
l
e
,
M
o
r
o
c
c
o
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Mar
19
,
2
0
2
4
R
ev
is
ed
Oct
19
,
2
0
2
4
Acc
ep
ted
Oct
23
,
2
0
2
4
A
b
ra
in
stro
k
e
,
m
e
d
ica
ll
y
re
fe
rre
d
to
a
s
a
str
o
k
e
,
re
p
re
se
n
ts
a
c
rit
ica
l
c
o
n
d
i
ti
o
n
tri
g
g
e
re
d
b
y
t
h
e
d
isru
p
ti
o
n
o
f
b
lo
o
d
flo
w
t
o
a
re
g
io
n
o
f
th
e
b
r
a
in
.
Earl
y
d
e
tec
ti
o
n
o
f
stro
k
e
is
c
ru
c
ial
t
o
p
r
e
v
e
n
t
fa
tal
c
o
m
p
li
c
a
ti
o
n
s.
In
th
is
stu
d
y
,
we
wo
rk
e
d
with
a
n
u
n
b
a
lan
c
e
d
d
a
t
a
se
t
o
f
4
9
8
1
e
n
tri
e
s
o
n
stro
k
e
,
wh
ich
we
b
a
lan
c
e
d
u
si
n
g
th
e
K
-
m
e
a
n
s
sy
n
th
e
ti
c
m
i
n
o
rit
y
o
v
e
r
-
sa
m
p
li
n
g
tec
h
n
iq
u
e
(
KMea
n
sSM
OTE
)
a
lg
o
rit
h
m
.
We
th
e
n
e
m
p
lo
y
e
d
fiv
e
m
a
c
h
i
n
e
lea
rn
in
g
a
lg
o
rit
h
m
s:
d
e
c
isio
n
tree
,
ra
n
d
o
m
fo
re
st,
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
,
K
-
ne
a
re
st
n
e
ig
h
b
o
rs,
a
n
d
g
ra
d
ie
n
t
b
o
o
st
in
g
.
We
c
o
m
p
a
re
d
th
e
h
y
p
e
r
p
a
ra
m
e
ter
o
p
ti
m
iza
ti
o
n
o
f
t
h
e
se
a
lg
o
rit
h
m
s
u
sin
g
f
o
u
r
m
e
tah
e
u
rist
ic
tec
h
n
i
q
u
e
s:
g
ra
y
wo
lf
o
p
ti
m
iza
ti
o
n
,
p
a
rti
c
le
sw
a
rm
o
p
ti
m
iza
ti
o
n
,
g
e
n
e
ti
c
a
lg
o
ri
th
m
,
a
n
d
a
rti
ficia
l
b
e
e
c
o
lo
n
y
.
T
h
e
m
o
d
e
ls'
e
ffe
c
ti
v
e
n
e
ss
wa
s
e
v
a
lu
a
ted
u
sin
g
m
u
lt
i
p
le
m
e
tri
c
s,
su
c
h
a
s
a
c
c
u
ra
c
y
,
re
c
a
l
l,
p
re
c
isio
n
,
F
1
-
sc
o
re
,
a
n
d
a
re
a
u
n
d
e
r
th
e
re
c
e
iv
e
r
o
p
e
ra
ti
n
g
c
h
a
ra
c
teristic
c
u
rv
e
.
Ou
r
fi
n
d
i
n
g
s i
n
d
ica
te t
h
a
t
th
e
ra
n
d
o
m
fo
re
st
o
p
t
imiz
e
d
b
y
t
h
e
g
e
n
e
ti
c
a
l
g
o
rit
h
m
a
c
h
iev
e
d
t
h
e
b
e
st
p
e
r
fo
rm
a
n
c
e
,
with
a
n
a
c
c
u
ra
c
y
o
f
9
7
.
3
9
%
a
n
d
a
n
F
1
-
sc
o
re
o
f
9
7
.
3
5
%
.
Th
is
stu
d
y
h
ig
h
li
g
h
ts
th
e
e
ffe
c
ti
v
e
n
e
ss
o
f
b
a
lan
c
in
g
a
n
d
m
e
tah
e
u
risti
c
s
tec
h
n
iq
u
e
s
i
n
o
p
ti
m
izi
n
g
m
a
c
h
in
e
lea
rn
in
g
m
o
d
e
ls f
o
r
str
o
k
e
fo
re
c
a
stin
g
.
K
ey
w
o
r
d
s
:
B
r
ain
s
tr
o
k
e
Gen
etic
alg
o
r
ith
m
Hy
p
er
p
ar
a
m
eter
o
p
tim
izatio
n
KM
ea
n
s
SMOT
E
Ma
ch
in
e
lear
n
in
g
Ov
er
s
am
p
lin
g
R
an
d
o
m
f
o
r
est
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
:
Ab
d
Allah
Ao
u
r
a
g
h
MI
E
T
L
ab
o
r
ato
r
y
,
Facu
lty
o
f
Scien
ce
s
an
d
T
ec
h
n
iq
u
es,
Hass
an
1
s
t U
n
iv
er
s
ity
Settat,
Mo
r
o
cc
o
E
m
ail:
ab
d
allah
ao
u
r
ag
h
@
g
m
a
il.c
o
m
1.
I
NT
RO
D
UCT
I
O
N
B
r
ain
s
tr
o
k
e,
also
k
n
o
wn
as
s
tr
o
k
e,
is
a
c
r
itical
h
ea
lth
p
r
o
b
lem
wo
r
ld
wid
e,
c
o
n
s
titu
tin
g
o
n
e
o
f
th
e
f
o
r
em
o
s
t
ca
u
s
es
o
f
m
o
r
tality
a
n
d
lo
n
g
-
ter
m
h
an
d
icap
[
1
]
.
W
h
en
a
s
tr
o
k
e
o
cc
u
r
s
,
th
e
r
is
k
o
f
d
ea
th
is
h
ig
h
.
I
f
n
o
t
f
atal,
a
s
tr
o
k
e
ca
n
ca
u
s
e
v
is
io
n
o
r
s
p
ee
ch
im
p
air
m
en
t,
p
ar
aly
s
is
,
an
d
co
n
f
u
s
io
n
.
E
v
er
y
y
ea
r
,
1
5
m
illi
o
n
p
eo
p
le
ar
e
r
ep
o
r
ted
t
o
h
a
v
e
a
s
tr
o
k
e:
5
m
illi
o
n
d
ie,
an
d
5
m
illi
o
n
a
r
e
l
ef
t
p
er
m
a
n
en
tly
d
is
ab
l
ed
,
b
u
r
d
en
in
g
f
am
ilies
an
d
s
o
cieties
[
1
]
,
[
2
]
.
A
s
tr
o
k
e
h
a
p
p
en
s
wh
en
b
l
o
o
d
f
l
o
w
to
a
s
ec
tio
n
o
f
th
e
b
r
ain
is
d
is
r
u
p
te
d
,
lead
in
g
to
o
x
y
g
en
d
ep
r
iv
atio
n
,
an
d
s
u
b
s
eq
u
en
tly
,
tis
s
u
e
d
am
ag
e.
Pro
m
p
t
r
ec
o
g
n
itio
n
a
n
d
ea
r
ly
i
n
ter
v
en
tio
n
ar
e
p
ar
am
o
u
n
t
i
n
m
itig
atin
g
th
e
d
e
v
astatin
g
co
n
s
eq
u
en
ce
s
o
f
th
is
c
o
n
d
itio
n
[
3
]
.
W
h
ile
th
er
e
ar
e
m
a
n
y
tr
ea
tm
en
ts
av
ailab
le
f
o
r
s
tr
o
k
e,
in
clu
d
in
g
s
u
r
g
er
y
,
r
ad
iatio
n
th
er
ap
y
,
c
h
em
o
th
e
r
ap
y
,
an
d
tar
g
eted
th
er
ap
e
u
tic
ap
p
r
o
ac
h
es
[
4
]
,
t
h
ese
in
ter
v
en
tio
n
s
ca
n
b
e
c
o
s
tly
,
an
d
th
eir
ef
f
ec
tiv
en
ess
o
f
ten
d
ep
en
d
s
o
n
h
o
w
q
u
ick
ly
t
h
e
s
tr
o
k
e
is
d
iag
n
o
s
ed
a
n
d
tr
ea
ted
.
T
h
er
ef
o
r
e,
ea
r
ly
d
iag
n
o
s
is
o
f
s
tr
o
k
e
is
o
f
u
tm
o
s
t
im
p
o
r
tan
ce
,
as
it
n
o
t
o
n
ly
im
p
r
o
v
e
s
th
e
h
ea
lth
s
itu
atio
n
o
f
p
atien
ts
b
u
t a
ls
o
r
ed
u
ce
s
th
e
co
s
ts
ass
o
ciate
d
with
th
eir
r
eh
ab
ilit
atio
n
[
5
]
.
Alth
o
u
g
h
p
o
ten
tially
s
er
io
u
s
,
s
tr
o
k
e
r
em
ain
s
a
ch
allen
g
in
g
co
n
d
itio
n
to
p
r
e
d
ict
an
d
m
an
a
g
e
ef
f
ec
tiv
ely
[
3
]
,
[
4
]
.
Ma
ch
in
e
lear
n
i
n
g
tech
n
iq
u
es
h
av
e
b
ec
o
m
e
p
r
o
m
is
in
g
in
s
tr
u
m
en
ts
in
th
e
h
ea
lth
ca
r
e
f
ield
,
f
ac
ilit
atin
g
th
e
an
aly
s
is
o
f
co
m
p
lex
m
e
d
ical
d
ata
an
d
aid
in
g
clin
ical
d
ec
is
io
n
-
m
ak
in
g
[
6
]
.
T
h
ese
ad
v
a
n
ce
m
en
ts
h
av
e
also
im
p
r
o
v
e
d
th
e
p
r
e
d
ictio
n
o
f
v
ar
i
o
u
s
d
is
ea
s
es,
in
clu
d
in
g
b
r
ain
t
u
m
o
r
s
[
7
]
,
liv
er
d
is
ea
s
e
[
8
]
,
a
n
d
o
th
er
s
[
9
]
,
n
o
ta
b
ly
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.
14
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
5
:
473
-
4
8
1
474
th
r
o
u
g
h
th
e
u
tili
za
tio
n
o
f
d
ataset
b
alan
cin
g
an
d
h
y
p
er
p
ar
a
m
eter
o
p
tim
izatio
n
tec
h
n
iq
u
e
s
[
1
0
]
,
[
1
1
]
.
I
n
t
h
e
co
n
tex
t o
f
s
tr
o
k
e,
th
e
u
tili
za
tio
n
o
f
m
ac
h
in
e
lea
r
n
in
g
alg
o
r
ith
m
s
an
d
d
iv
er
s
e
o
p
tim
izatio
n
t
ec
h
n
iq
u
es f
o
r
ea
r
ly
p
r
ed
ictio
n
h
o
ld
s
s
ig
n
if
ican
t
p
r
o
m
is
e
f
o
r
im
p
r
o
v
in
g
p
atie
n
t
ca
r
e
o
u
tc
o
m
es
an
d
allev
ia
tin
g
th
e
b
u
r
d
en
o
n
h
ea
lth
ca
r
e
s
y
s
tem
s
.
T
h
ese
in
n
o
v
ativ
e
ap
p
r
o
ac
h
es
en
ab
le
p
r
ed
ictiv
e
m
o
d
els
to
b
e
tailo
r
e
d
to
th
e
n
u
an
ce
s
o
f
m
ed
ical
d
ata,
th
er
e
b
y
e
n
h
an
ci
n
g
th
eir
ac
c
u
r
ac
y
a
n
d
r
elia
b
ilit
y
[
1
2
]
.
I
n
th
is
co
n
tex
t,
Daid
o
n
e
et
a
l.
[
1
3
]
ex
am
i
n
ed
th
e
u
s
e
o
f
m
ac
h
in
e
lear
n
i
n
g
tech
n
iq
u
es
in
s
tr
o
k
e
p
r
ed
ictio
n
.
T
h
ey
em
p
h
asized
th
e
im
p
o
r
tan
ce
o
f
d
e
v
elo
p
i
n
g
s
o
p
h
is
ticated
tech
n
o
lo
g
ies
to
en
h
an
ce
d
iag
n
o
s
is
,
tr
ea
tm
en
t,
an
d
p
atien
t
r
esu
lts
.
T
h
eir
f
in
d
i
n
g
s
d
em
o
n
s
tr
ate
th
at
em
er
g
in
g
m
ac
h
in
e
lear
n
in
g
t
ec
h
n
iq
u
es
h
a
v
e
s
h
o
wn
ex
ce
p
tio
n
al
p
r
ec
is
io
n
in
a
n
aly
zin
g
im
ag
es,
d
iag
n
o
s
in
g
s
u
b
ty
p
es
o
f
s
tr
o
k
e
,
a
n
d
p
r
ed
ictin
g
p
atien
t
p
r
o
g
n
o
s
is
.
Ho
wev
er
,
s
ev
er
al
ch
allen
g
es
p
er
s
is
t,
in
clu
d
in
g
d
ata
s
tan
d
ar
d
izatio
n
an
d
m
o
d
el
v
alid
atio
n
.
Sirsat
et
a
l.
[
1
4
]
co
n
d
u
cted
a
s
tu
d
y
o
n
th
e
u
s
e
o
f
m
ac
h
i
n
e
lear
n
in
g
f
o
r
ac
cu
r
ate
s
tr
o
k
e
p
r
ed
ictio
n
.
T
h
ey
co
n
clu
d
e
d
th
at
m
ac
h
in
e
lear
n
i
n
g
is
a
p
o
ten
t
in
s
tr
u
m
en
t
in
h
e
alth
ca
r
e,
p
r
o
v
id
i
n
g
tailo
r
e
d
cli
n
ical
ca
r
e
to
s
tr
o
k
e
p
atien
ts
.
T
h
ey
id
en
tifie
d
a
n
e
ed
f
o
r
r
esear
ch
i
n
ce
r
tain
u
n
d
er
ex
p
lo
r
e
d
a
r
ea
s
,
p
a
r
ticu
lar
ly
in
s
tr
o
k
e
tr
ea
tm
en
t
.
T
h
e
s
tu
d
y
h
ig
h
lig
h
ted
th
e
ef
f
icac
y
o
f
r
an
d
o
m
f
o
r
est
(
R
F)
an
d
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
i
n
e
(
SVM)
in
s
tr
o
k
e
f
o
r
ec
asti
n
g
.
E
m
o
n
et
a
l
.
[
1
5
]
b
u
ilt
a
m
o
d
el
f
o
r
th
e
ea
r
ly
f
o
r
ec
asti
n
g
o
f
s
tr
o
k
e
-
r
elate
d
d
is
ea
s
es
u
s
in
g
v
ar
io
u
s
m
ac
h
in
e
lear
n
in
g
tech
n
i
q
u
es.
T
h
ey
id
en
tifie
d
s
ev
er
al
f
ac
t
o
r
s
,
in
clu
d
in
g
h
ea
r
t
d
is
ea
s
e,
b
o
d
y
m
ass
in
d
e
x
,
h
y
p
er
ten
s
io
n
,
s
tr
o
k
e
h
is
to
r
y
,
a
n
d
ag
e,
as
s
ig
n
if
ican
t
p
r
ed
icto
r
s
.
T
h
ei
r
m
o
d
el
in
v
o
lv
ed
tr
ain
in
g
ten
class
if
ier
s
,
th
e
r
esu
lts
o
f
wh
ich
wer
e
co
m
b
in
ed
v
ia
weig
h
ted
v
o
tin
g
,
r
esu
ltin
g
in
9
7
%
ac
cu
r
ac
y
.
T
h
e
weig
h
ted
v
o
tin
g
class
if
ier
p
r
o
v
ed
to
b
e
th
e
b
es
t
p
er
f
o
r
m
e
r
f
o
r
p
r
ed
ictin
g
s
tr
o
k
e,
ex
h
ib
itin
g
t
h
e
lo
west
f
alse
p
o
s
itiv
e
an
d
f
al
s
e
n
eg
ativ
e
r
ates.
T
az
in
et
a
l.
[
1
6
]
d
ev
el
o
p
ed
s
tr
o
k
e
p
r
ed
ictio
n
m
o
d
els
u
tili
zin
g
a
v
ar
iety
o
f
m
ac
h
in
e
lea
r
n
in
g
m
eth
o
d
s
.
T
h
eir
r
esear
ch
in
c
o
r
p
o
r
ated
p
h
y
s
io
lo
g
ical
d
ata
a
n
d
alg
o
r
ith
m
s
,
i
n
clu
d
in
g
lo
g
is
tic
r
eg
r
ess
io
n
,
RF
class
if
icatio
n
,
d
ec
is
io
n
tr
ee
(
DT
)
class
if
icatio
n
,
an
d
v
o
tin
g
class
if
ier
s
,
to
tr
ain
f
o
u
r
d
is
tin
ct
m
o
d
els.
Am
o
n
g
th
ese
alg
o
r
ith
m
s
,
RF
em
er
g
ed
as
th
e
m
o
s
t
ef
f
ec
tiv
e,
ac
h
iev
in
g
an
ac
cu
r
ac
y
o
f
a
p
p
r
o
x
im
atel
y
9
6
%.
T
h
ese
r
esu
lts
s
h
o
wca
s
ed
n
o
tab
ly
h
ig
h
er
ac
c
u
r
ac
y
co
m
p
a
r
ed
to
p
r
e
v
io
u
s
s
tu
d
ies,
af
f
ir
m
in
g
th
e
r
eliab
ilit
y
o
f
th
e
d
ev
elo
p
e
d
m
o
d
els.
Ak
ter
et
a
l.
[
1
7
]
d
ev
elo
p
ed
a
p
r
ec
is
e
m
o
d
el
f
o
r
p
r
ed
ic
tin
g
s
tr
o
k
es
u
tili
zin
g
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
s
.
T
h
ey
e
v
alu
ated
DT
,
SVM
,
an
d
RF
m
o
d
els
d
u
r
in
g
tr
ain
in
g
a
n
d
test
in
g
.
T
h
e
ef
f
icien
cy
o
f
ea
c
h
class
if
ier
was a
s
s
es
s
ed
u
s
in
g
v
ar
io
u
s
ev
alu
atio
n
m
etr
ics s
u
ch
as a
cc
u
r
ac
y
,
s
en
s
itiv
ity
,
f
alse
n
eg
ativ
e
r
ate,
f
alse
p
o
s
itiv
e
r
ate,
a
n
d
er
r
o
r
r
ate.
T
h
e
p
r
o
p
o
s
ed
m
o
d
el
attain
ed
a
m
a
x
im
u
m
ac
cu
r
ac
y
o
f
9
5
.
3
0
%
with
th
e
RF
class
if
ier
,
d
em
o
n
s
tr
atin
g
its
e
f
f
ec
tiv
en
ess
in
ac
cu
r
ate
s
tr
o
k
e
p
r
ed
ictio
n
.
Paliwal
et
a
l
.
[
1
8
]
in
v
esti
g
ated
th
e
s
u
b
s
tan
tial
in
f
lu
en
ce
o
f
ea
r
ly
d
etec
tio
n
an
d
s
wif
t
in
ter
v
en
t
io
n
in
m
itig
atin
g
s
tr
o
k
e
d
am
ag
e
an
d
en
h
a
n
cin
g
s
u
r
v
iv
o
r
s
'
q
u
ality
o
f
life
.
E
m
p
l
o
y
in
g
a
v
a
r
iety
o
f
m
ac
h
i
n
e
lear
n
in
g
m
eth
o
d
s
,
in
clu
d
in
g
DT
,
lo
g
is
tic
r
eg
r
ess
io
n
,
SVM
,
an
d
RF
,
th
ey
d
ev
is
ed
a
m
o
d
el
tar
g
etin
g
s
tr
o
k
e
p
r
ed
ict
io
n
.
T
h
e
em
p
h
asis
was
o
n
ass
ess
in
g
th
e
ef
f
icac
y
o
f
o
v
e
r
s
am
p
lin
g
tec
h
n
iq
u
es
f
o
r
m
an
ag
i
n
g
u
n
b
alan
ce
d
d
ata.
T
h
eir
r
esu
lts
r
ev
ea
led
t
h
at
th
e
K
-
m
ea
n
s
s
y
n
th
etic
m
in
o
r
ity
o
v
er
-
s
am
p
lin
g
tech
n
iq
u
e
(
KM
ea
n
s
SMOT
E
)
tech
n
iq
u
e
y
ield
e
d
th
e
h
ig
h
est
ac
cu
r
ac
y
o
f
9
6
%,
with
m
in
im
al
f
alse
p
o
s
itiv
es
a
n
d
f
alse
n
e
g
ativ
es,
s
h
o
wc
asin
g
its
ef
f
ec
tiv
en
ess
in
s
tr
o
k
e
p
r
ed
ictio
n
.
Sriv
astav
et
a
l.
[
1
9
]
h
av
e
cr
ea
ted
a
m
o
d
el
aim
ed
at
p
r
e
d
ictin
g
s
tr
o
k
e
o
cc
u
r
r
e
n
ce
th
r
o
u
g
h
d
if
f
er
en
t
m
ea
s
u
r
es
s
u
ch
as
p
r
ec
is
io
n
,
r
ec
all,
F1
-
s
co
r
e,
an
d
r
o
o
t
m
ea
n
s
q
u
ar
e
er
r
o
r
(
R
MSE
)
.
An
an
aly
tical
co
m
p
ar
is
o
n
o
f
p
r
e
d
ictio
n
p
er
f
o
r
m
an
ce
was
co
n
d
u
cted
u
s
in
g
s
ev
er
al
m
ac
h
in
e
lear
n
i
n
g
a
lg
o
r
ith
m
s
,
an
d
it
was
f
o
u
n
d
t
h
at
lo
g
is
tic
r
eg
r
ess
io
n
y
ield
ed
t
h
e
b
est
p
e
r
f
o
r
m
a
n
ce
with
an
ac
c
u
r
ac
y
o
f
9
5
.
0
2
%.
Srin
iv
as
an
d
Mo
s
ig
an
ti
[
2
0
]
d
ev
elo
p
ed
an
en
s
em
b
le
lear
n
in
g
m
o
d
el
f
o
r
s
tr
o
k
e
p
r
ed
ictio
n
,
c
o
m
b
in
i
n
g
f
o
r
ec
asts
f
r
o
m
e
x
tr
em
ely
r
a
n
d
o
m
ized
tr
ee
s
,
RF
,
an
d
h
is
to
g
r
a
m
-
b
ased
g
r
ad
ien
t
b
o
o
s
tin
g
(
GB
)
.
T
h
is
s
o
f
t
v
o
tin
g
m
o
d
el
im
p
r
o
v
ed
p
r
ec
is
io
n
an
d
r
eliab
ilit
y
,
ac
h
iev
in
g
9
6
.
8
8
% a
cc
u
r
ac
y
.
I
n
o
u
r
s
tu
d
y
,
we
ex
ten
d
p
r
ev
io
u
s
r
esear
ch
o
n
m
ac
h
in
e
lea
r
n
in
g
ap
p
licatio
n
s
f
o
r
p
r
e
d
ictin
g
b
r
ain
s
tr
o
k
es.
E
x
is
tin
g
s
tu
d
ies
h
av
e
ex
p
lo
r
ed
v
a
r
io
u
s
tech
n
iq
u
es,
b
u
t
n
o
u
n
iv
er
s
ally
a
p
p
licab
le
m
eth
o
d
h
as
em
er
g
ed
.
Pre
v
io
u
s
r
esear
ch
p
r
im
ar
ily
f
o
cu
s
ed
o
n
d
e
v
elo
p
in
g
an
d
e
v
alu
atin
g
m
ac
h
in
e
lear
n
in
g
m
o
d
els
u
s
in
g
d
iv
er
s
e
d
atasets
,
o
f
ten
o
v
er
lo
o
k
in
g
th
e
cr
itical
im
p
o
r
tan
ce
o
f
d
a
ta
b
alan
cin
g
an
d
h
y
p
er
p
ar
a
m
eter
o
p
tim
izatio
n
tech
n
iq
u
es.
Ou
r
s
tu
d
y
ad
d
r
ess
es
th
ese
g
ap
s
in
th
e
li
ter
atu
r
e
b
y
in
tr
o
d
u
cin
g
a
co
m
p
r
e
h
e
n
s
iv
e
ap
p
r
o
ac
h
th
at
ev
alu
ates
th
e
ef
f
ec
tiv
en
ess
o
f
KM
ea
n
s
SMOT
E
,
a
p
o
wer
f
u
l
d
ata
b
alan
cin
g
tech
n
iq
u
e,
i
n
co
n
ju
n
ctio
n
with
ad
v
an
ce
d
m
etah
eu
r
is
tic
o
p
ti
m
izatio
n
tech
n
iq
u
es
f
o
r
h
y
p
er
p
ar
am
eter
s
,
in
cl
u
d
in
g
g
r
a
y
wo
lf
o
p
tim
izatio
n
(
GW
O)
,
p
ar
ticle
s
war
m
o
p
tim
izatio
n
(
PS
O)
,
g
en
etic
alg
o
r
ith
m
(
GA)
,
an
d
ar
tific
ial
b
ee
co
lo
n
y
(
AB
C
)
.
W
e
r
ig
o
r
o
u
s
ly
ass
es
s
th
e
co
m
b
in
ed
im
p
ac
t
o
f
th
ese
tech
n
iq
u
es
o
n
m
o
d
el
p
er
f
o
r
m
an
ce
u
s
in
g
f
iv
e
d
if
f
er
en
t
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
s
:
DT
,
SV
M
,
K
-
n
ea
r
est
n
eig
h
b
o
r
s
(
KNN)
,
GB
,
an
d
RF
.
I
m
p
o
r
tan
tly
,
o
u
r
m
eth
o
d
o
lo
g
y
d
em
o
n
s
tr
ates
s
u
p
er
io
r
e
f
f
ec
ti
v
en
ess
co
m
p
ar
ed
t
o
p
r
e
v
io
u
s
r
esear
ch
en
d
ea
v
o
r
s
,
p
ar
tic
u
lar
ly
in
ter
m
s
o
f
ac
h
iev
in
g
b
alan
ce
d
d
atasets
an
d
o
p
tim
ized
h
y
p
er
p
ar
am
eter
s
,
wh
ich
ar
e
cr
u
cial
f
o
r
e
n
h
an
ci
n
g
m
o
d
el
ac
cu
r
ac
y
an
d
r
o
b
u
s
tn
ess
.
T
h
is
s
tu
d
y
n
o
t
o
n
ly
f
ills
a
s
ig
n
if
ican
t
g
ap
in
th
e
ex
is
tin
g
liter
atu
r
e
b
u
t
also
o
f
f
er
s
a
n
o
v
e
l
co
n
tr
ib
u
tio
n
to
th
e
f
ield
o
f
s
tr
o
k
e
p
r
ed
ictio
n
th
r
o
u
g
h
a
well
-
r
o
u
n
d
ed
a
n
d
in
n
o
v
ativ
e
m
eth
o
d
o
lo
g
ical
f
r
am
ewo
r
k
.
T
h
e
f
o
llo
win
g
s
ec
tio
n
s
o
f
t
h
is
s
tu
d
y
ar
e
s
tr
u
ctu
r
e
d
as
f
o
llo
ws:
s
ec
tio
n
2
p
r
o
v
i
d
es
an
in
-
d
ep
t
h
ex
p
lan
atio
n
o
f
th
e
m
ater
ials
a
n
d
m
eth
o
d
s
u
tili
ze
d
.
Sectio
n
3
p
r
esen
ts
an
d
d
is
cu
s
s
es
th
e
r
esu
lts
,
in
clu
d
in
g
an
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
B
a
la
n
cin
g
a
n
d
meta
h
eu
r
is
tic
tech
n
iq
u
es fo
r
imp
r
o
vin
g
m
a
ch
in
e
lea
r
n
in
g
mo
d
els in
…
(
A
b
d
A
lla
h
A
o
u
r
a
g
h
)
475
an
aly
s
is
o
f
th
e
e
f
f
ec
ts
o
f
th
e
te
ch
n
iq
u
es
em
p
lo
y
ed
.
L
astl
y
,
s
e
ctio
n
4
o
f
f
er
s
a
s
u
m
m
ar
y
o
f
th
e
k
ey
f
in
d
in
g
s
an
d
p
r
o
p
o
s
es p
o
ten
tial a
v
en
u
es f
o
r
f
u
tu
r
e
i
n
v
esti
g
atio
n
s
.
2.
M
AT
E
R
I
AL
A
ND
M
E
T
H
O
D
2
.
1
.
P
r
o
po
s
ed
m
et
ho
do
lo
g
y
I
n
o
u
r
s
tu
d
y
f
o
cu
s
ed
o
n
p
r
ed
ictin
g
s
tr
o
k
es
u
s
in
g
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
s
,
we
d
ev
is
ed
a
m
eth
o
d
o
l
o
g
y
e
n
co
m
p
ass
in
g
s
ev
er
al
cr
u
cial
s
tep
s
.
I
n
itially
,
we
ac
q
u
ir
ed
th
e
s
tr
o
k
e
d
atas
et,
wh
ich
p
r
o
v
id
es
co
m
p
r
eh
e
n
s
iv
e
in
f
o
r
m
atio
n
a
b
o
u
t
p
atien
ts
af
f
licted
b
y
th
is
m
ed
ical
co
n
d
itio
n
.
Su
b
s
eq
u
e
n
tly
,
we
c
o
n
d
u
cted
a
d
ata
p
r
ep
r
o
ce
s
s
in
g
p
h
ase,
in
v
o
lv
i
n
g
o
p
er
atio
n
s
lik
e
en
co
d
in
g
,
d
ata
p
ar
titi
o
n
in
g
,
an
d
n
o
r
m
aliza
tio
n
,
to
en
s
u
r
e
u
n
if
o
r
m
d
ata
s
ca
lin
g
.
Fu
r
th
er
m
o
r
e,
we
ad
d
r
ess
ed
th
e
ch
allen
g
e
o
f
d
ata
im
b
alan
ce
b
y
ass
es
s
in
g
v
ar
io
u
s
b
alan
cin
g
tech
n
i
q
u
es,
with
KM
ea
n
s
SMOT
E
id
en
tifie
d
as
t
h
e
o
p
tim
al
s
o
lu
tio
n
.
Su
b
s
eq
u
en
tly
,
we
ass
es
s
ed
a
v
ar
iety
o
f
m
ac
h
in
e
lear
n
in
g
m
eth
o
d
s
,
s
u
ch
as
DT
,
KNN,
SV
M,
R
F,
an
d
GB
.
T
o
im
p
r
o
v
e
t
h
e
ef
f
icac
y
o
f
t
h
ese
m
o
d
els,
we
co
n
d
u
cted
h
y
p
e
r
p
ar
am
eter
o
p
tim
izatio
n
f
o
r
ea
ch
u
s
in
g
m
etah
e
u
r
is
tic
o
p
tim
izatio
n
tech
n
iq
u
es
s
u
ch
as GWO,
PS
O,
GA,
an
d
AB
C
.
Fin
ally
,
Fig
u
r
e
1
illu
s
tr
ates th
e
m
eth
o
d
o
lo
g
ical
a
p
p
r
o
ac
h
ad
o
p
ted
in
th
is
s
tu
d
y
.
Fig
u
r
e
1
.
Su
g
g
ested
m
eth
o
d
o
l
o
g
y
2
.
2
.
Da
t
a
s
et
I
n
o
u
r
b
r
ain
s
tr
o
k
e
p
r
ed
ictio
n
p
r
o
ject,
we
u
tili
ze
th
e
d
ataset
s
o
u
r
ce
d
f
r
o
m
Kag
g
le
[
2
1
]
,
wh
ich
s
er
v
es
as
a
v
alu
a
b
le
ass
et
in
th
e
m
ed
i
ca
l
d
o
m
ai
n
.
T
h
is
d
ataset
o
f
f
er
s
a
r
o
b
u
s
t
f
o
u
n
d
atio
n
f
o
r
r
esear
ch
er
s
an
d
h
ea
lth
c
ar
e
p
r
ac
titi
o
n
er
s
in
ter
ested
in
ex
p
lo
r
in
g
th
e
c
o
r
r
elatio
n
b
etwe
en
clin
ical
attr
ib
u
tes
an
d
b
r
ain
s
tr
o
k
es.
C
o
m
p
r
is
in
g
1
1
an
th
r
o
p
o
m
etr
ic
an
d
b
io
lo
g
ical
ch
ar
ac
ter
is
tics
,
th
e
b
r
ain
s
t
r
o
k
e
d
ataset
en
co
m
p
ass
es
4
9
8
1
r
ec
o
r
d
s
,
p
r
o
v
id
in
g
a
co
m
p
r
eh
en
s
iv
e
b
asis
f
o
r
b
r
a
in
s
tr
o
k
e
an
aly
s
is
an
d
p
r
ed
icti
o
n
.
T
h
e
b
r
ain
s
tr
o
k
e
d
ataset
i
s
d
iv
id
ed
in
to
two
class
es
:
s
tr
o
k
e
p
atien
ts
(
4
.
9
7
%)
an
d
n
o
n
-
s
tr
o
k
e
p
at
ien
ts
(
9
5
.
0
3
%).
T
h
is
s
ig
n
if
ican
t
class
im
b
alan
ce
ca
n
p
r
esen
t
ch
allen
g
es
d
u
r
i
n
g
th
e
t
r
ain
in
g
o
f
m
a
ch
in
e
lear
n
in
g
m
o
d
e
ls
,
lead
in
g
to
b
iased
p
er
f
o
r
m
an
ce
ass
ess
m
en
ts
.
T
h
er
ef
o
r
e,
ad
d
r
ess
in
g
u
n
b
ala
n
ce
d
class
es
is
cr
u
cial
to
en
s
u
r
e
ac
cu
r
ate
an
d
b
alan
ce
d
p
r
ed
icti
o
n
s
.
Fu
r
th
er
d
etails
r
eg
ar
d
in
g
th
e
d
ataset
co
m
p
o
s
itio
n
ar
e
o
u
tlin
ed
in
T
ab
le
1
.
T
ab
le
1
.
Data
s
et
c
o
m
p
o
s
itio
n
A
t
t
r
i
b
u
t
e
D
e
scri
p
t
i
o
n
G
e
n
d
e
r
G
e
n
d
e
r
o
f
p
a
t
i
e
n
t
A
g
e
P
a
t
i
e
n
t
's
a
g
e
H
y
p
e
r
t
e
n
si
o
n
0
f
o
r
n
o
h
y
p
e
r
t
e
n
s
i
o
n
,
1
f
o
r
h
y
p
e
r
t
e
n
s
i
o
n
H
e
a
r
t
_
d
i
se
a
se
0
f
o
r
n
o
h
e
a
r
t
d
i
sea
s
e
,
1
f
o
r
h
e
a
r
t
d
i
s
e
a
se
Ev
e
r
_
marr
i
e
d
"
N
o
"
o
r
"
Y
e
s"
W
o
r
k
_
t
y
p
e
"
c
h
i
l
d
r
e
n
"
,
"
G
o
v
t
_
j
o
v
"
,
"
N
e
v
e
r
_
w
o
r
k
e
d
"
,
"
P
r
i
v
a
t
e
"
o
r
"
S
e
l
f
-
e
m
p
l
o
y
e
d
"
R
e
si
d
e
n
c
e
_
t
y
p
e
"
R
u
r
a
l
"
o
r
"
U
r
b
a
n
"
A
v
g
_
g
l
u
c
o
se
_
l
e
v
e
l
A
v
e
r
a
g
e
b
l
o
o
d
g
l
u
c
o
se
l
e
v
e
l
B
M
I
B
o
d
y
M
a
ss I
n
d
e
x
S
mo
k
i
n
g
_
st
a
t
u
s
"
f
o
r
merl
y
sm
o
k
e
d
"
,
"
n
e
v
e
r
sm
o
k
e
d
"
o
r
"
smo
k
e
s"
S
t
r
o
k
e
Ta
r
g
e
t
v
a
r
i
a
b
l
e
,
0
:
H
e
a
l
t
h
y
,
1
:
A
f
f
e
c
t
e
d
2
.
3
.
B
a
la
ncing
da
t
a
s
et
Data
s
et
b
alan
cin
g
is
cr
u
cial
in
o
u
r
s
tu
d
y
to
en
s
u
r
e
ac
cu
r
ate
an
d
b
alan
ce
d
p
r
ed
ictio
n
s
,
p
a
r
t
icu
lar
ly
in
th
e
p
r
esen
ce
o
f
u
n
b
ala
n
ce
d
cl
ass
es
l
ik
e
s
tr
o
k
e
an
d
n
o
n
-
s
tr
o
k
e
p
atien
ts
.
I
n
o
u
r
r
esear
ch
,
w
e
ev
alu
ated
m
u
ltip
le
d
ata
b
alan
cin
g
tech
n
iq
u
es,
in
clu
d
in
g
SMOT
E
,
a
d
ap
tiv
e
s
y
n
th
etic
s
am
p
lin
g
(
ADASYN
)
,
SVMSMO
T
E
,
an
d
KM
ea
n
s
SMOT
E
[
8
]
,
[
2
2
]
–
[
2
4
]
.
W
e
s
elec
ted
th
ese
tech
n
iq
u
es
d
u
e
to
th
eir
wid
esp
r
ea
d
ad
o
p
tio
n
an
d
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.
14
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
5
:
473
-
4
8
1
476
d
em
o
n
s
tr
ated
ef
f
ec
tiv
e
n
ess
in
m
ed
ical
r
esear
ch
,
wh
er
e
class
im
b
alan
ce
s
ar
e
p
r
ev
alen
t
[
8
]
,
[
2
2
]
–
[
2
4
]
.
Am
o
n
g
th
ese
tech
n
iq
u
es,
KM
ea
n
s
SM
OT
E
em
er
g
ed
as
th
e
b
est
-
p
er
f
o
r
m
in
g
o
p
tio
n
.
T
h
e
KM
ea
n
s
a
lg
o
r
ith
m
is
u
tili
ze
d
to
id
en
tify
clu
s
ter
s
in
th
e
o
r
ig
in
al
d
ata,
f
o
llo
wed
b
y
a
s
ep
ar
at
e
ap
p
licatio
n
o
f
SMOT
E
to
ea
ch
g
r
o
u
p
to
g
en
er
ate
s
y
n
th
etic
d
ata
p
o
in
ts
th
at
clo
s
e
ly
r
esem
b
le
ex
am
p
les
f
r
o
m
th
e
m
in
o
r
ity
class
[
2
5
]
.
T
h
is
ap
p
r
o
ac
h
en
a
b
led
u
s
t
o
g
en
er
ate
a
s
y
n
th
etic
d
ataset
th
at
b
etter
r
ep
r
esen
ts
th
e
m
in
o
r
ity
class
,
en
h
an
cin
g
o
u
r
m
o
d
el'
s
a
b
ilit
y
to
g
en
er
alize
an
d
p
r
o
d
u
ce
ex
ac
t p
r
ed
ictio
n
s
f
o
r
s
tr
o
k
e
p
atien
ts
.
2
.
4
.
M
a
chine le
a
rning
a
lg
o
ri
t
hm
s
I
n
o
u
r
s
tu
d
y
,
we
ev
alu
ated
s
ev
er
al
m
ac
h
in
e
lear
n
in
g
al
g
o
r
ith
m
s
f
o
r
s
tr
o
k
e
p
r
ed
ictio
n
.
T
h
ese
alg
o
r
ith
m
s
wer
e
s
elec
ted
f
o
r
th
eir
ef
f
icien
cy
in
m
o
d
elin
g
class
if
icatio
n
p
r
o
b
lem
s
an
d
h
a
v
e
b
ee
n
wid
ely
u
s
ed
in
s
im
ilar
m
ed
ical
f
ield
s
to
p
r
e
d
ict
clin
ical
o
u
tco
m
es
[
8
]
,
[
2
3
]
,
[
2
6
]
–
[
2
8
]
.
T
h
e
ev
alu
ated
al
g
o
r
ith
m
s
i
n
clu
d
e
as f
o
llo
ws.
2
.
4
.
1
.
Dec
is
io
n t
re
e
T
h
e
DT
is
a
s
im
p
le
an
d
in
ter
p
r
etab
le
alg
o
r
ith
m
wid
el
y
u
s
ed
f
o
r
class
if
icatio
n
task
s
.
I
t c
an
ef
f
ec
tiv
ely
ca
p
tu
r
e
n
o
n
-
tr
iv
ial
co
r
r
elatio
n
s
b
etwe
en
p
r
ed
icto
r
s
an
d
th
e
o
u
tco
m
e
v
ar
iab
le
wh
ile
also
h
a
n
d
lin
g
m
is
s
in
g
d
ata
an
d
o
u
tlier
s
ef
f
icien
tly
.
T
h
e
d
ec
is
io
n
r
u
l
es
it
g
en
er
ates
ar
e
e
x
p
lain
ab
le,
m
a
k
in
g
it
p
ar
ticu
l
ar
ly
u
s
ef
u
l
in
f
ield
s
s
u
ch
as m
ed
icin
e
[
2
6
]
–
[
2
8
]
.
2
.
4
.
2
.
K
-
nea
re
s
t
neig
hb
o
rs
KNN
is
a
b
asic
class
if
icat
io
n
tech
n
iq
u
e
t
h
at
ass
ig
n
s
d
ata
p
o
i
n
ts
to
th
e
m
o
s
t
co
m
m
o
n
class
am
o
n
g
t
h
eir
n
ea
r
est n
eig
h
b
o
r
s
.
I
t'
s
s
tr
aig
h
tf
o
r
war
d
t
o
im
p
lem
en
t a
n
d
d
o
e
s
n
'
t a
s
s
u
m
e
an
y
s
p
ec
if
ic
d
ata
d
is
tr
ib
u
tio
n
,
m
ak
in
g
it
r
o
b
u
s
t
to
n
o
is
y
d
ata.
H
o
wev
er
,
it
m
ay
in
c
u
r
s
ig
n
if
ican
t
co
m
p
u
tatio
n
al
co
s
ts
,
p
ar
ticu
lar
ly
with
h
ig
h
-
d
im
e
n
s
io
n
al
d
atasets
[
2
3
]
,
[
2
6
]
–
[
2
8
]
.
2
.
4
.
3
.
Su
pp
o
rt
v
ec
t
o
r
m
a
chi
ne
SVM
is
k
n
o
wn
f
o
r
its
ef
f
ec
tiv
e
n
ess
in
h
an
d
lin
g
h
ig
h
-
d
im
en
s
i
o
n
al
d
ata
an
d
f
in
d
i
n
g
n
o
n
-
lin
e
ar
d
ec
is
io
n
b
o
u
n
d
ar
ies.
I
t
wo
r
k
s
b
y
f
in
d
in
g
th
e
d
ec
is
io
n
b
o
u
n
d
a
r
y
th
at
o
p
tim
ally
s
eg
r
eg
ates
d
is
tin
ct
class
e
s
wh
il
e
m
ax
im
izin
g
th
e
m
ar
g
i
n
b
etwe
en
th
em
.
SVM
is
p
ar
ticu
la
r
l
y
u
s
ef
u
l
in
s
ce
n
ar
io
s
with
co
m
p
le
x
d
ata
r
elatio
n
s
h
ip
s
b
u
t m
ay
r
eq
u
ir
e
ca
r
ef
u
l t
u
n
in
g
f
o
r
o
p
tim
al
p
er
f
o
r
m
a
n
ce
[
2
6
]
–
[
2
8
]
.
2
.
4
.
4
.
Ra
nd
o
m
f
o
re
s
t
R
F
i
s
a
v
er
s
ati
le
en
s
em
b
le
lea
r
n
in
g
alg
o
r
ith
m
k
n
o
wn
f
o
r
its
r
o
b
u
s
tn
ess
an
d
h
ig
h
ac
cu
r
ac
y
.
I
t
b
u
ild
s
n
u
m
er
o
u
s
DT
d
u
r
in
g
th
e
tr
ain
in
g
p
h
ase
an
d
i
n
teg
r
ates
th
eir
r
esu
lts
to
f
o
r
m
u
late
p
r
ed
ictio
n
s
.
RF
i
s
r
esil
ien
t
to
o
v
er
f
itti
n
g
,
p
er
f
o
r
m
s
well
with
h
ig
h
-
d
im
en
s
io
n
al
d
ata,
an
d
p
r
o
v
id
es
v
al
u
ab
le
in
s
ig
h
ts
in
to
f
ea
t
u
r
e
im
p
o
r
tan
ce
[
7
]
,
[
2
6
]
–
[
2
8
]
.
2
.
4
.
5
.
G
ra
dient
bo
o
s
t
ing
GB
i
s
a
r
o
b
u
s
t
en
s
em
b
le
lear
n
in
g
m
eth
o
d
th
at
co
n
s
tr
u
cts
a
p
o
ten
t
p
r
ed
ictiv
e
m
o
d
el
b
y
i
ter
ativ
ely
in
co
r
p
o
r
atin
g
wea
k
lear
n
er
s
.
O
f
ten
DT
s
,
to
m
in
im
ize
th
e
lo
s
s
f
u
n
ctio
n
.
I
t
ef
f
ec
tiv
ely
h
an
d
les
co
m
p
lex
d
atasets
,
r
ed
u
ce
s
b
ias
an
d
v
ar
ian
ce
,
an
d
ca
n
m
o
d
el
co
m
p
lex
in
t
er
ac
tio
n
s
b
etwe
en
p
r
ed
icto
r
s
an
d
th
e
r
esp
o
n
s
e
v
ar
iab
le
[
2
3
]
,
[
2
6
]
–
[
2
8
]
.
2
.
5
.
H
y
perpa
ra
m
e
t
er
o
ptim
i
za
t
io
n wit
h m
et
a
heuris
t
ics
Op
tim
izin
g
h
y
p
er
p
a
r
am
eter
s
i
s
cr
u
cial
f
o
r
f
i
n
e
-
tu
n
i
n
g
th
e
ef
f
ec
tiv
en
ess
o
f
m
ac
h
in
e
lear
n
i
n
g
m
o
d
els.
T
r
ad
itio
n
ally
,
th
is
o
p
tim
izatio
n
is
p
er
f
o
r
m
e
d
u
s
in
g
m
eth
o
d
s
s
u
ch
as
g
r
id
s
ea
r
ch
,
wh
ich
ev
alu
ates
ev
er
y
p
o
ten
tial
co
m
b
in
atio
n
o
f
p
a
r
a
m
eter
s
to
d
etec
t
th
e
b
es
t
co
n
f
ig
u
r
atio
n
[
8
]
.
Ho
wev
e
r
,
th
is
ap
p
r
o
ac
h
m
ay
b
e
in
ef
f
icien
t
f
o
r
lar
g
e
o
r
co
m
p
lex
p
a
r
am
eter
s
p
ac
es.
Me
t
ah
eu
r
is
tic
tech
n
iq
u
es
p
r
o
v
id
e
a
m
o
r
e
ef
f
ec
tiv
e
alter
n
ativ
e,
ef
f
icien
tly
ex
p
l
o
r
i
n
g
th
e
s
o
lu
tio
n
s
p
ac
e
to
d
is
co
v
er
o
p
tim
al
co
n
f
ig
u
r
atio
n
s
with
in
r
ea
s
o
n
a
b
le
tim
e
f
r
am
es.
Un
l
ik
e
g
r
id
s
ea
r
ch
,
t
h
ey
o
f
f
er
g
r
ea
ter
f
lex
ib
ilit
y
,
r
ed
u
ce
d
s
u
s
ce
p
tib
ilit
y
to
lo
ca
l m
i
n
im
a,
an
d
en
h
an
ce
d
s
u
itab
ilit
y
f
o
r
ad
d
r
ess
in
g
th
e
c
o
m
p
lex
ities
o
f
h
y
p
er
p
a
r
am
eter
o
p
tim
izatio
n
[
2
9
]
,
[
3
0
]
.
I
n
o
u
r
s
tu
d
y
,
we
o
p
ted
to
u
tili
ze
th
e
f
o
llo
win
g
f
o
u
r
tech
n
iq
u
es,
wid
ely
r
e
co
g
n
ize
d
an
d
ex
ten
s
iv
ely
em
p
l
o
y
ed
in
th
e
r
esear
ch
co
m
m
u
n
ity
:
2
.
5
.
1
.
G
ra
y
wo
lf
o
pti
m
iza
t
io
n
GW
O
i
s
a
m
etah
eu
r
is
tic
ap
p
r
o
ac
h
in
f
lu
en
ce
d
b
y
th
e
s
o
cial
o
r
g
an
izatio
n
an
d
h
u
n
tin
g
b
e
h
av
i
o
r
o
f
g
r
ay
wo
lv
es.
T
h
e
alg
o
r
ith
m
o
p
er
ate
s
b
y
e
m
u
latin
g
th
e
h
u
n
tin
g
s
tr
a
teg
ies
o
f
g
r
ay
wo
lv
es,
in
wh
ic
h
th
e
p
ac
k
m
em
b
er
s
co
llab
o
r
ate
to
tr
ac
k
a
n
d
ca
p
tu
r
e
p
r
ey
.
I
n
itially
,
th
e
lo
ca
tio
n
s
o
f
th
e
alp
h
a,
b
eta,
d
elta,
an
d
o
m
eg
a
wo
lv
es
ar
e
r
an
d
o
m
l
y
in
itialized
with
in
th
e
ex
p
lo
r
atio
n
s
p
ac
e.
T
h
e
n
,
th
e
a
lg
o
r
ith
m
co
n
tin
u
ally
m
o
d
if
ies
th
e
lo
ca
tio
n
s
o
f
th
e
wo
lv
es
d
ep
en
d
i
n
g
o
n
p
r
ed
ef
in
ed
eq
u
atio
n
s
,
in
co
r
p
o
r
atin
g
th
e
alp
h
a,
b
eta,
d
elta,
an
d
o
m
e
g
a
wo
lv
es'
p
o
s
itio
n
s
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
B
a
la
n
cin
g
a
n
d
meta
h
eu
r
is
tic
tech
n
iq
u
es fo
r
imp
r
o
vin
g
m
a
ch
in
e
lea
r
n
in
g
mo
d
els in
…
(
A
b
d
A
lla
h
A
o
u
r
a
g
h
)
477
to
g
u
id
e
th
e
s
ea
r
ch
to
war
d
o
p
tim
al
s
o
lu
tio
n
s
.
GW
O
i
s
ad
v
an
tag
e
o
u
s
b
ec
au
s
e
it
r
eq
u
ir
es
f
ewe
r
co
n
tr
o
l
p
ar
am
eter
s
,
is
ea
s
y
to
im
p
lem
en
t,
an
d
e
x
h
ib
its
f
ast co
n
v
e
r
g
e
n
ce
[
2
9
]
,
[
3
0
]
.
2
.
5
.
2
.
G
enet
ic
a
lg
o
rit
hm
GA
is
a
m
etah
eu
r
is
tic
alg
o
r
it
h
m
in
s
p
ir
ed
b
y
n
atu
r
al
s
elec
tio
n
an
d
ev
o
lu
tio
n
,
em
p
l
o
y
in
g
p
r
in
cip
les
s
u
ch
as
s
elec
tio
n
,
cr
o
s
s
o
v
er
,
an
d
m
u
tatio
n
to
s
ee
k
o
p
tim
al
s
o
lu
tio
n
s
with
in
a
d
ef
in
ed
p
r
o
b
lem
s
p
ac
e.
Star
tin
g
with
an
in
itial
p
o
p
u
latio
n
o
f
p
o
ten
tial
s
o
lu
tio
n
s
,
r
ep
r
esen
ted
as
ch
r
o
m
o
s
o
m
es,
th
e
alg
o
r
ith
m
s
elec
ts
in
d
iv
id
u
als
with
h
ig
h
er
f
itn
ess
s
co
r
es
f
o
r
r
ep
r
o
d
u
ctio
n
.
T
h
r
o
u
g
h
cr
o
s
s
o
v
er
,
s
elec
ted
p
air
s
ex
ch
an
g
e
g
e
n
etic
in
f
o
r
m
atio
n
to
g
en
er
ate
o
f
f
s
p
r
in
g
,
wh
ile
m
u
t
atio
n
in
tr
o
d
u
ce
s
s
m
all
c
h
an
g
e
s
to
m
ain
tain
p
o
p
u
lati
o
n
d
iv
e
r
s
ity
.
T
h
is
iter
ativ
e
p
r
o
ce
s
s
co
n
tin
u
es u
n
til co
n
v
e
r
g
en
ce
to
a
n
id
ea
l o
r
q
u
asi
-
o
p
tim
al
s
o
lu
tio
n
[
2
9
]
,
[
3
0
]
.
2
.
5
.
3
.
P
a
rt
icle
s
wa
r
m
o
ptim
i
za
t
io
n
PS
O
is
a
m
etah
eu
r
is
tic
alg
o
r
ith
m
g
u
i
d
ed
b
y
s
o
cial
b
ir
d
f
lo
c
k
in
g
o
r
f
is
h
s
ch
o
o
lin
g
b
e
h
av
io
r
.
I
n
PS
O,
a
p
o
p
u
latio
n
o
f
p
o
s
s
ib
le
s
o
lu
ti
o
n
s
,
r
ep
r
esen
ted
as
p
ar
ticles,
m
o
v
es
ac
r
o
s
s
th
e
s
ea
r
ch
s
p
ac
e
to
f
in
d
o
p
tim
al
s
o
lu
tio
n
s
.
E
ac
h
p
ar
ticle
a
d
ap
t
s
its
lo
ca
tio
n
u
s
i
n
g
its
in
d
i
v
id
u
al
h
is
to
r
y
an
d
t
h
e
co
llectiv
e
ac
tio
n
s
o
f
n
ea
r
b
y
p
ar
ticles.
T
h
e
alg
o
r
ith
m
iter
ativ
ely
ad
ju
s
ts
th
e
v
elo
city
an
d
p
o
s
itio
n
o
f
p
ar
ticles
b
ased
o
n
th
e
m
o
s
t
o
p
tim
al
p
o
s
itio
n
s
f
o
u
n
d
b
y
in
d
iv
id
u
a
l
p
ar
ticles
an
d
th
e
en
tire
s
w
ar
m
.
T
h
is
co
o
p
er
ativ
e
b
e
h
a
v
io
r
allo
ws
PS
O
to
ef
f
icien
tly
n
av
i
g
ate
th
r
o
u
g
h
th
e
s
ea
r
ch
s
p
ac
e
an
d
c
o
n
v
e
r
g
e
t
o
war
d
s
th
e
b
est s
o
lu
tio
n
s
[
2
9
]
,
[
3
0
]
.
2
.
5
.
4
.
Art
if
icia
l bee
co
lo
ny
AB
C
i
s
a
m
etah
eu
r
is
tic
o
p
tim
izatio
n
alg
o
r
ith
m
in
s
p
ir
ed
b
y
th
e
h
u
n
tin
g
ac
tiv
ity
o
f
h
o
n
ey
b
ee
s
.
I
t
in
v
o
lv
es
th
r
ee
p
r
im
ar
y
elem
e
n
ts
:
wo
r
k
in
g
b
ee
s
,
o
b
s
er
v
er
b
ee
s
,
an
d
s
co
u
t
b
ee
s
.
W
o
r
k
i
n
g
b
ee
s
s
ee
k
o
u
t
f
o
o
d
s
o
u
r
ce
s
an
d
co
m
m
u
n
icate
th
eir
f
in
d
in
g
s
to
o
b
s
er
v
e
r
b
ee
s
,
wh
o
th
e
n
s
elec
t
f
o
o
d
s
o
u
r
ce
s
b
ased
o
n
th
is
in
f
o
r
m
atio
n
,
wh
ile
s
co
u
t
b
ee
s
ex
p
lo
r
e
n
ew
f
o
o
d
s
o
u
r
ce
s
.
T
h
e
alg
o
r
ith
m
em
u
lates
th
e
co
o
p
er
ativ
e
attitu
d
e
o
f
b
ee
s
in
lo
ca
tin
g
an
d
e
x
p
lo
itin
g
f
o
o
d
s
o
u
r
ce
s
,
f
ac
ilit
atin
g
ef
f
icien
t
ex
p
lo
r
atio
n
a
n
d
ex
p
lo
itatio
n
o
f
th
e
s
o
lu
tio
n
s
p
ac
e.
AB
C
is
k
n
o
wn
f
o
r
its
s
im
p
licity
,
f
ew
co
n
tr
o
l
p
ar
am
et
er
s
,
an
d
ef
f
ec
tiv
en
ess
in
ex
p
lo
r
in
g
s
ea
r
ch
s
p
ac
es,
m
ak
in
g
it a
c
o
m
m
o
n
ly
ch
o
s
en
o
p
tio
n
i
n
v
ar
io
u
s
o
p
tim
izatio
n
p
r
o
b
lem
s
[
2
9
]
,
[
3
0
]
.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
I
n
th
is
s
ec
tio
n
,
we
d
elv
e
in
to
th
e
o
u
tco
m
es
an
d
d
is
cu
s
s
io
n
s
s
te
m
m
in
g
f
r
o
m
o
u
r
in
v
esti
g
atio
n
in
to
b
r
ain
s
tr
o
k
e
p
r
ed
ictio
n
.
T
h
e
ex
p
e
r
im
en
ts
wer
e
co
n
d
u
cted
o
n
a
c
o
m
p
u
tin
g
s
y
s
tem
p
o
wer
ed
b
y
an
AM
D
R
y
ze
n
7
5
7
0
0
G
p
r
o
ce
s
s
o
r
with
R
ad
eo
n
g
r
ap
h
ics.
Ou
r
s
o
f
twar
e
en
v
i
r
o
n
m
en
t
was
co
n
f
ig
u
r
e
d
with
th
e
Py
th
o
n
lan
g
u
a
g
e
o
p
er
atin
g
with
in
J
u
p
y
ter
No
teb
o
o
k
,
s
u
p
p
lem
en
ted
b
y
es
s
en
tial
lib
r
ar
ies
lik
e
Pan
d
as,
Scik
it
-
lear
n
,
an
d
Hy
p
ONI
C
.
T
o
ev
alu
ate
th
e
e
f
f
icien
cy
o
f
o
u
r
m
ac
h
in
e
lear
n
in
g
m
o
d
els,
w
e
u
tili
ze
d
a
v
ar
iety
o
f
ass
ess
m
e
n
t
m
etr
ics,
in
clu
d
in
g
ac
cu
r
ac
y
,
r
ec
all,
p
r
ec
is
io
n
,
F1
-
s
co
r
e,
an
d
ar
ea
u
n
d
er
th
e
r
ec
eiv
er
o
p
er
atin
g
c
h
ar
ac
ter
is
tic
cu
r
v
e
(
AUC
-
R
O
C
)
.
T
h
ese
m
ea
s
u
r
es
s
er
v
e
as
ess
en
tial
in
d
icato
r
s
o
f
o
u
r
m
o
d
els'
p
r
ed
ictiv
e
p
r
o
wess
an
d
th
eir
ca
p
ac
ity
to
g
en
er
alize
to
n
ew
d
ata.
W
e
s
elec
ted
th
ese
ev
alu
atio
n
m
etr
ics
d
u
e
to
th
eir
ab
ilit
y
to
o
f
f
er
a
th
o
r
o
u
g
h
in
s
ig
h
t
in
to
o
u
r
m
o
d
els'
p
er
f
o
r
m
an
c
e
[
3
1
]
,
[
3
2
]
.
T
h
e
r
esu
lts
ac
r
o
s
s
d
if
f
er
en
t
s
tag
es
o
f
th
e
s
tu
d
y
a
r
e
o
u
tlin
e
d
i
n
T
ab
les
2
–
7
.
T
h
ese
r
esu
lts
o
f
f
er
v
alu
ab
le
i
n
s
ig
h
ts
in
to
th
e
co
m
p
ar
ativ
e
e
f
f
ec
tiv
en
ess
o
f
th
e
alg
o
r
ith
m
s
in
p
r
ed
ictin
g
b
r
ain
s
tr
o
k
es,
co
n
s
i
d
er
in
g
b
o
th
th
e
d
ata
b
alan
ci
n
g
an
d
th
e
h
y
p
er
p
a
r
am
eter
o
p
tim
izatio
n
s
tr
ateg
ies
em
p
lo
y
ed
.
I
n
T
ab
le
2
,
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
m
o
d
els
o
n
th
e
o
r
ig
in
al
d
ataset,
wh
ich
is
h
ig
h
l
y
im
b
alan
ce
d
,
is
p
r
esen
ted
.
Alth
o
u
g
h
s
o
m
e
m
o
d
els
ac
h
iev
ed
h
i
g
h
o
v
er
all
ac
c
u
r
ac
y
,
with
t
h
e
b
est
v
alu
e
r
ea
c
h
in
g
u
p
to
9
5
.
7
9
%
f
o
r
th
e
SVM
m
o
d
el,
it
is
cr
u
cial
to
m
en
tio
n
th
at
th
e
s
e
m
o
d
els
ar
e
n
o
t
co
n
s
id
er
ed
ef
f
ec
tiv
e
d
u
e
to
th
eir
p
o
o
r
p
er
f
o
r
m
an
ce
o
n
o
th
er
m
etr
ics
s
u
ch
as
p
r
ec
is
io
n
,
r
ec
all,
an
d
AUC
-
R
O
C
,
wh
ich
d
o
n
o
t
ex
c
ee
d
2
8
%,
1
5
%,
a
n
d
5
5
%,
r
esp
ec
tiv
ely
.
T
h
ese
r
esu
lts
in
d
icate
th
at
th
ese
m
o
d
els
ar
e
n
o
t
s
u
itab
le
f
o
r
th
e
task
o
f
s
tr
o
k
e
p
r
ed
ictio
n
d
u
e
to
th
eir
in
ab
ilit
y
to
g
e
n
er
al
ize
well
an
d
ef
f
ec
tiv
ely
ca
p
tu
r
e
p
o
s
itiv
e
in
s
tan
ce
s
.
Af
ter
b
alan
cin
g
with
KM
ea
n
s
SMOT
E
,
th
e
m
o
d
el
p
er
f
o
r
m
an
ce
s
ar
e
s
ig
n
if
ican
tly
im
p
r
o
v
e
d
,
as
s
h
o
wn
in
T
ab
le
3
.
T
h
er
e
is
a
s
ig
n
if
ican
t
in
cr
ea
s
e
in
all
ev
al
u
atio
n
m
etr
ics
co
m
p
ar
ed
t
o
th
e
h
ig
h
ly
im
b
alan
ce
d
o
r
ig
in
al
d
ataset.
Par
ticu
lar
ly
,
GB
s
tan
d
s
o
u
t
b
y
ac
h
iev
in
g
th
e
h
ig
h
est
v
alu
es
o
f
ac
c
u
r
ac
y
(
9
5
.
5
6
%),
p
r
ec
is
io
n
(
9
4
.
3
0
%),
F1
-
s
co
r
e
(
9
5
.
5
6
%),
an
d
AUC
-
R
OC
(
9
5
.
5
8
%).
Ad
d
itio
n
ally
,
KNN
an
d
RF
p
er
f
o
r
m
well,
with
th
e
h
ig
h
est
r
ec
a
ll
o
f
9
7
.
2
9
%.
Af
ter
ap
p
ly
in
g
GW
O
to
th
e
d
atas
et
b
alan
ce
d
b
y
KM
ea
n
s
SMOT
E
,
T
ab
le
4
h
ig
h
lig
h
ts
a
clea
r
p
er
f
o
r
m
an
ce
im
p
r
o
v
em
e
n
t.
On
ce
ag
ain
,
GB
s
tan
d
s
o
u
t
b
y
ac
h
iev
in
g
th
e
h
ig
h
est
v
alu
es
o
f
ac
cu
r
ac
y
(
9
7
.
3
2
%),
p
r
ec
is
io
n
(
9
7
.
4
9
%),
F1
-
s
co
r
e
(
9
7
.
2
8
%)
,
an
d
AUC
-
R
OC
(
9
7
.
3
2
%).
Me
an
wh
ile,
SVM
ac
h
iev
es
t
h
e
h
ig
h
est
r
ec
all
o
f
9
7
.
2
9
%.
Af
ter
ap
p
ly
in
g
GA
to
th
e
d
a
taset
b
alan
ce
d
b
y
KM
ea
n
s
SMOT
E
,
T
ab
le
5
d
em
o
n
s
tr
ate
s
a
n
o
tab
le
p
er
f
o
r
m
an
ce
im
p
r
o
v
em
e
n
t.
T
h
is
tim
e,
RF
s
tan
d
s
o
u
t
b
y
ac
h
iev
in
g
th
e
h
ig
h
est
v
alu
es
o
f
ac
cu
r
ac
y
(
9
7
.
3
9
%),
p
r
ec
is
io
n
(
9
7
.
6
3
%),
F1
-
s
co
r
e
(
9
7
.
3
5
%),
an
d
AUC
-
R
OC
(
9
7
.
3
9
%).
Ad
d
itio
n
ally
,
SVM
a
ch
iev
es
th
e
h
ig
h
est
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.
14
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
5
:
473
-
4
8
1
478
r
ec
all
o
f
9
7
.
2
1
%.
Af
ter
ap
p
ly
i
n
g
PS
O
to
th
e
d
ataset
b
alan
ce
d
b
y
KM
ea
n
s
SMOT
E
,
T
ab
le
6
r
ev
ea
ls
a
s
ig
n
if
ican
t
p
er
f
o
r
m
an
ce
im
p
r
o
v
em
e
n
t.
I
n
th
is
ca
s
e,
GB
s
tan
d
s
o
u
t
b
y
ac
h
iev
in
g
th
e
h
ig
h
est
v
alu
es
o
f
a
cc
u
r
ac
y
(
9
7
.
2
2
%),
p
r
ec
is
io
n
(
9
7
.
3
5
%),
F1
-
s
co
r
e
(
9
7
.
1
7
%),
an
d
AUC
-
R
OC
(
9
7
.
2
2
%).
Ad
d
itio
n
ally
,
SVM
a
ch
iev
es
th
e
h
ig
h
est
r
ec
all
o
f
9
7
.
2
9
%.
Af
ter
a
p
p
l
y
in
g
AB
C
to
th
e
d
ataset
b
al
an
ce
d
b
y
KM
ea
n
s
SMOT
E
,
T
ab
le
7
illu
s
tr
ates
a
s
ig
n
if
ican
t
p
er
f
o
r
m
an
ce
im
p
r
o
v
em
en
t.
T
h
is
tim
e,
GB
s
tan
d
s
o
u
t
b
y
ac
h
iev
in
g
th
e
h
i
g
h
est
v
alu
es
o
f
ac
cu
r
ac
y
(
9
7
.
3
2
%),
p
r
ec
is
io
n
(
9
7
.
2
9
%)
,
r
ec
all
(
9
7
.
2
9
%),
F1
-
s
co
r
e
(
9
7
.
2
9
%),
an
d
AUC
-
R
OC
(
9
7
.
3
2
%).
Ad
d
itio
n
ally
,
SVM
also
ac
h
iev
es th
e
h
ig
h
est r
ec
all
o
f
9
7
.
2
9
%.
T
ab
le
2
.
Or
ig
i
n
al
d
ataset
A
c
c
u
r
a
c
y
(
%)
P
r
e
c
i
s
i
o
n
(
%)
R
e
c
a
l
l
(
%)
F1
-
S
c
o
r
e
(
%)
AUC
-
R
O
C
(
%)
DT
9
1
.
0
4
1
0
.
9
9
1
5
.
8
7
1
2
.
9
9
5
5
.
1
1
K
N
N
9
5
.
3
8
2
5
.
0
0
4
.
7
6
8
.
0
0
5
2
.
0
7
S
V
M
9
5
.
7
9
0
.
0
0
0
.
0
0
0
.
0
0
5
0
.
0
0
RF
9
5
.
5
9
2
0
.
0
0
1
.
5
9
2
.
9
4
5
0
.
6
5
GB
9
5
.
5
9
2
8
.
5
7
3
.
1
7
5
.
7
1
5
1
.
4
1
T
ab
le
3
.
B
alan
ce
d
KM
ea
n
s
S
MO
T
E
d
ataset
A
c
c
u
r
a
c
y
(
%)
P
r
e
c
i
s
i
o
n
(
%)
R
e
c
a
l
l
(
%)
F1
-
S
c
o
r
e
(
%)
AUC
-
R
O
C
(
%)
DT
9
4
.
1
5
9
2
.
7
9
9
5
.
5
7
9
4
.
1
6
9
4
.
1
7
K
N
N
9
4
.
1
5
9
1
.
4
1
9
7
.
2
9
9
4
.
2
6
9
4
.
2
0
S
V
M
9
5
.
0
4
9
2
.
9
7
9
7
.
2
9
9
5
.
0
8
9
5
.
0
7
RF
9
4
.
8
2
9
2
.
8
2
9
7
.
0
0
9
4
.
8
7
9
4
.
8
5
GB
9
5
.
5
6
9
4
.
3
0
9
6
.
8
6
9
5
.
5
6
9
5
.
5
8
T
ab
le
4
.
B
alan
ce
d
d
ataset
+
GW
O
Op
tim
izatio
n
A
c
c
u
r
a
c
y
(
%)
P
r
e
c
i
s
i
o
n
(
%)
R
e
c
a
l
l
(
%)
F1
-
S
c
o
r
e
(
%)
AUC
-
R
O
C
(
%)
DT
9
4
.
4
0
9
3
.
6
7
9
5
.
0
7
9
4
.
3
6
9
4
.
4
1
K
N
N
9
4
.
2
6
9
1
.
6
5
9
7
.
2
1
9
4
.
3
5
9
4
.
3
0
S
V
M
9
7
.
1
1
9
6
.
8
7
9
7
.
2
9
9
7
.
0
8
9
7
.
1
2
RF
9
5
.
0
4
9
3
.
5
6
9
6
.
5
7
9
5
.
0
4
9
5
.
0
6
GB
9
7
.
3
2
9
7
.
4
9
9
7
.
0
7
9
7
.
2
8
9
7
.
3
2
T
ab
le
5
.
B
alan
ce
d
d
ataset
+
G
A
Op
tim
izatio
n
A
c
c
u
r
a
c
y
(
%)
P
r
e
c
i
s
i
o
n
(
%)
R
e
c
a
l
l
(
%)
F1
-
S
c
o
r
e
(
%)
AUC
-
R
O
C
(
%)
DT
9
5
.
6
7
9
4
.
8
1
9
6
.
5
0
9
5
.
6
5
9
5
.
6
8
K
N
N
9
4
.
4
4
9
1
.
9
6
9
7
.
2
1
9
4
.
5
1
9
4
.
4
8
S
V
M
9
7
.
2
5
9
7
.
2
8
9
7
.
1
4
9
7
.
2
1
9
7
.
2
5
RF
9
7
.
3
9
9
7
.
6
3
9
7
.
0
7
9
7
.
3
5
9
7
.
3
9
GB
9
6
.
6
9
9
6
.
3
1
9
7
.
0
0
9
6
.
6
5
9
6
.
6
9
T
ab
le
6
.
B
alan
ce
d
d
ataset
+
PSO
Op
tim
izatio
n
A
c
c
u
r
a
c
y
(
%)
P
r
e
c
i
s
i
o
n
(
%)
R
e
c
a
l
l
(
%)
F1
-
S
c
o
r
e
(
%)
AUC
-
R
O
C
(
%)
DT
9
4
.
7
2
9
4
.
0
1
9
5
.
3
6
9
4
.
6
8
9
4
.
7
3
K
N
N
9
4
.
7
2
9
2
.
4
6
9
7
.
2
1
9
4
.
7
8
9
4
.
7
5
S
V
M
9
7
.
1
1
9
6
.
8
7
9
7
.
2
9
9
7
.
0
8
9
7
.
1
2
RF
9
5
.
2
1
9
3
.
8
3
9
6
.
6
4
9
5
.
2
1
9
5
.
2
3
GB
9
7
.
2
2
9
7
.
3
5
9
7
.
0
0
9
7
.
1
7
9
7
.
2
2
T
ab
le
7
.
B
alan
ce
d
d
ataset
+
AB
C
Op
tim
izatio
n
A
c
c
u
r
a
c
y
(
%)
P
r
e
c
i
s
i
o
n
(
%)
R
e
c
a
l
l
(
%)
F1
-
S
c
o
r
e
(
%)
AUC
-
R
O
C
(
%)
DT
9
4
.
4
4
9
3
.
7
9
9
5
.
0
0
9
4
.
3
9
9
4
.
4
4
K
N
N
9
4
.
6
5
9
2
.
3
3
9
7
.
2
1
9
4
.
7
1
9
4
.
6
8
S
V
M
9
7
.
1
1
9
6
.
8
7
9
7
.
2
9
9
7
.
0
8
9
7
.
1
2
RF
9
4
.
9
6
9
3
.
3
7
9
6
.
6
4
9
4
.
9
8
9
4
.
9
9
GB
9
7
.
3
2
9
7
.
2
9
9
7
.
2
9
9
7
.
2
9
9
7
.
3
2
T
h
e
r
esu
lts
h
ig
h
lig
h
t
th
e
b
en
ef
its
o
f
d
ata
b
alan
cin
g
an
d
h
y
p
er
p
a
r
am
eter
o
p
tim
izatio
n
in
s
tr
o
k
e
p
r
ed
ictio
n
.
B
y
c
o
m
b
in
in
g
t
h
e
KM
ea
n
s
SMOT
E
m
eth
o
d
with
th
e
GA
an
d
th
e
RF
m
o
d
el,
we
r
ea
ch
ed
th
e
h
ig
h
est
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
B
a
la
n
cin
g
a
n
d
meta
h
eu
r
is
tic
tech
n
iq
u
es fo
r
imp
r
o
vin
g
m
a
ch
in
e
lea
r
n
in
g
mo
d
els in
…
(
A
b
d
A
lla
h
A
o
u
r
a
g
h
)
479
p
er
f
o
r
m
an
ce
,
with
a
n
ac
cu
r
ac
y
r
ate
o
f
9
7
.
3
9
%
an
d
an
F1
-
s
co
r
e
o
f
9
7
.
3
5
%.
T
h
e
m
ea
s
u
r
em
en
ts
f
o
r
th
e
d
if
f
er
e
n
t
m
o
d
els
o
f
th
e
b
est
co
m
b
i
n
atio
n
ar
e
illu
s
tr
ated
in
Fig
u
r
e
2
.
T
h
is
ap
p
r
o
ac
h
p
r
o
v
e
d
to
b
e
ef
f
e
ctiv
e
in
en
h
an
cin
g
th
e
o
v
er
all
p
r
ed
ictiv
e
ca
p
ab
il
ity
o
f
th
e
m
o
d
els.
T
h
e
GB
a
n
d
RF
m
o
d
els
ex
h
ib
ited
o
p
tim
al
p
er
f
o
r
m
an
ce
in
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
F1
-
s
co
r
e,
an
d
AUC
-
R
OC
d
u
e
to
th
eir
in
tr
in
s
ic
ab
ilit
y
to
ca
p
tu
r
e
co
m
p
lex
r
elatio
n
s
h
ip
s
b
etwe
en
v
a
r
iab
les an
d
p
r
o
v
id
e
ac
cu
r
ate
p
r
e
d
ictio
n
s
.
T
h
eir
ca
p
ab
ilit
y
to
tr
ain
wea
k
m
o
d
els
an
d
a
g
g
r
e
g
ate
th
e
m
s
ig
n
if
ican
tly
im
p
r
o
v
e
d
th
e
o
v
er
all
m
o
d
el
p
er
f
o
r
m
a
n
ce
.
C
o
n
v
er
s
ely
,
th
e
SVM
s
to
o
d
o
u
t
f
o
r
r
ec
all
d
u
e
to
its
u
tili
za
tio
n
o
f
d
ec
is
io
n
h
y
p
er
p
lan
es
th
at
m
ax
im
ize
th
e
m
ar
g
in
b
etwe
en
d
if
f
er
en
t
class
es,
en
ab
lin
g
it
to
m
o
r
e
ea
s
ily
id
en
tify
p
o
s
itiv
e
ex
am
p
l
es.
T
h
e
GA
o
u
tp
e
r
f
o
r
m
ed
o
th
e
r
m
etah
eu
r
is
tics
b
ec
au
s
e
o
f
its
ab
ilit
y
to
ef
f
icien
tly
ex
p
lo
r
e
s
o
lu
tio
n
s
p
ac
es
an
d
i
d
en
tify
s
ets
o
f
o
p
tim
al
p
a
r
am
eter
s
f
o
r
th
e
m
o
d
els.
B
y
em
p
lo
y
in
g
co
n
ce
p
ts
o
f
n
atu
r
al
s
elec
tio
n
an
d
cr
o
s
s
o
v
er
,
th
e
GA
co
u
ld
a
v
o
id
lo
c
al
m
in
im
a
an
d
co
n
v
er
g
e
to
war
d
s
m
o
r
e
p
er
f
o
r
m
a
n
t
s
o
lu
tio
n
s
with
in
r
ea
s
o
n
ab
le
ti
m
ef
r
am
es.
Fig
u
r
e
2
.
Me
tr
ics o
f
th
e
b
est c
o
m
b
in
atio
n
C
o
m
p
ar
in
g
o
u
r
r
esu
lts
to
p
r
ev
io
u
s
s
tu
d
ies,
we
o
b
s
er
v
e
th
at
m
eth
o
d
s
s
u
ch
as
GB
an
d
RF
c
o
n
s
is
ten
tly
p
er
f
o
r
m
well,
alig
n
in
g
with
f
in
d
in
g
s
f
r
o
m
o
th
er
r
esear
ch
.
Ou
r
s
tu
d
y
ex
ten
d
s
th
ese
f
i
n
d
i
n
g
s
b
y
s
p
ec
if
ically
h
ig
h
lig
h
tin
g
th
e
im
p
ac
t
o
f
d
if
f
er
en
t
h
y
p
er
p
ar
a
m
eter
o
p
tim
i
za
tio
n
tech
n
iq
u
es
o
n
m
o
d
el
p
er
f
o
r
m
a
n
ce
.
Un
lik
e
p
r
ev
io
u
s
wo
r
k
,
we
em
p
l
o
y
ed
KM
e
an
s
SMOT
E
f
o
r
d
ata
b
al
an
cin
g
in
c
o
n
ju
n
ctio
n
with
v
ar
io
u
s
o
p
tim
izatio
n
alg
o
r
ith
m
s
,
in
clu
d
in
g
GW
O
,
PSO
,
an
d
GA
.
No
tab
l
y
,
th
e
co
m
b
in
atio
n
o
f
KM
ea
n
s
SMOT
E
with
th
e
GA
an
d
RF
y
iel
d
ed
th
e
h
i
g
h
est ac
cu
r
ac
y
a
n
d
F1
-
s
co
r
e,
s
ig
n
if
ican
tly
o
u
tp
er
f
o
r
m
in
g
p
r
e
v
io
u
s
m
o
d
els.
T
h
is
u
n
d
er
s
co
r
es th
e
cr
itical
r
o
le
o
f
d
ata
b
alan
cin
g
an
d
h
y
p
er
p
a
r
am
eter
o
p
ti
m
izatio
n
in
en
h
an
cin
g
p
r
ed
i
ctio
n
ac
cu
r
ac
y
an
d
r
o
b
u
s
tn
ess
.
Ou
r
f
in
d
in
g
s
d
em
o
n
s
tr
ate
th
at
th
ese
te
ch
n
iq
u
es
ca
n
s
ig
n
if
ican
tly
im
p
r
o
v
e
m
o
d
el
p
er
f
o
r
m
an
ce
co
m
p
ar
ed
to
p
r
io
r
s
tu
d
ies
th
at
d
id
n
o
t
u
tili
ze
s
u
ch
co
m
p
r
eh
en
s
iv
e
o
p
tim
izatio
n
s
tr
ateg
ies.
B
y
s
y
s
tem
atica
lly
ad
d
r
ess
in
g
th
e
ch
allen
g
es
o
f
d
ata
im
b
alan
ce
a
n
d
o
p
tim
izin
g
h
y
p
er
p
ar
am
eter
s
,
o
u
r
ap
p
r
o
ac
h
p
r
o
v
i
d
es
a
m
o
r
e
r
o
b
u
s
t
f
r
am
ewo
r
k
f
o
r
s
tr
o
k
e
p
r
ed
ictio
n
,
o
f
f
er
in
g
im
p
r
o
v
ed
a
cc
u
r
ac
y
an
d
r
eliab
ilit
y
.
Desp
ite
th
ese
en
co
u
r
ag
in
g
f
in
d
in
g
s
,
it
is
im
p
o
r
ta
n
t
to
ac
k
n
o
wled
g
e
ce
r
tain
r
estrictio
n
s
o
f
o
u
r
s
tu
d
y
.
Ou
r
d
ataset
m
ay
b
e
lim
ited
in
ter
m
s
o
f
r
ep
r
esen
tativ
en
ess
,
p
o
ten
t
ially
r
estrictin
g
th
e
g
e
n
er
ali
za
b
ilit
y
o
f
o
u
r
f
in
d
in
g
s
to
o
th
er
p
o
p
u
latio
n
s
.
Ad
d
itio
n
ally
,
s
o
m
e
im
p
o
r
tan
t
v
ar
iab
les
m
ay
n
o
t
h
a
v
e
b
ee
n
ac
co
u
n
ted
f
o
r
in
o
u
r
an
aly
s
is
,
wh
ich
co
u
ld
af
f
ec
t
th
e
v
alid
ity
o
f
o
u
r
r
esu
lts
.
Fo
r
f
u
tu
r
e
r
esear
ch
,
it
wo
u
ld
b
e
a
d
v
a
n
tag
e
o
u
s
to
f
u
r
t
h
er
e
x
am
i
n
e
th
e
u
s
e
o
f
th
ese
tech
n
iq
u
es
in
o
t
h
er
ar
ea
s
o
f
p
r
ed
ictiv
e
m
e
d
icin
e,
as
well
as
th
eir
in
teg
r
atio
n
in
t
o
r
e
al
clin
ical
s
ettin
g
s
.
Ad
d
itio
n
al
s
tu
d
ies
co
u
ld
also
d
elv
e
in
to
th
e
im
p
ac
t
o
f
t
h
e
s
e
tech
n
iq
u
es
o
n
tr
ea
tm
e
n
t
d
ec
is
io
n
s
an
d
p
ati
en
t
o
u
tco
m
es to
b
etter
u
n
d
er
s
tan
d
th
eir
p
o
ten
tial in
a
clin
ical
co
n
tex
t.
4.
CO
NCLU
SI
O
N
I
n
co
n
clu
s
io
n
,
th
is
s
tu
d
y
s
h
e
d
s
lig
h
t
o
n
t
h
e
s
ig
n
if
ican
ce
o
f
d
ata
b
alan
ci
n
g
a
n
d
h
y
p
er
p
ar
am
eter
o
p
tim
izatio
n
tech
n
iq
u
es
in
s
tr
o
k
e
p
r
ed
ictio
n
.
T
h
e
f
i
n
d
in
g
s
d
em
o
n
s
tr
ate
th
at
th
e
i
n
teg
r
atio
n
o
f
KM
ea
n
s
SMOT
E
with
th
e
GA
a
n
d
th
e
RF
m
o
d
el
y
ield
ed
th
e
h
ig
h
est
p
r
ed
icti
v
e
p
e
r
f
o
r
m
an
ce
,
s
h
o
wca
s
in
g
an
ac
cu
r
ac
y
r
ate
o
f
95.
67%
94.
44%
97.
25%
97.
39%
96.
69%
94.
81%
91.
96%
97.
28%
97.
63%
96.
31%
96.
50%
97.
21%
97.
14%
97.
07%
97.
00%
95.
65%
94.
51%
97.
21%
97.
35%
96.
65%
95.
68%
94.
48%
97.
25%
97.
39%
96.
69
%
9
1
%
9
2
%
9
3
%
9
4
%
9
5
%
9
6
%
9
7
%
9
8
%
D
e
c
i
si
o
n
T
r
e
e
KNN
S
V
M
R
a
n
d
o
m Fo
r
e
st
G
r
a
d
i
e
n
t
B
o
o
st
i
n
g
K
mea
n
s
S
M
O
TE
+
G
e
n
e
t
i
c
A
l
g
o
r
i
t
h
m
S
C
O
R
ES
a
c
c
u
ra
c
y
p
r
e
c
isio
n
re
c
all
F1
-s
c
o
re
au
c-
ro
c
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.
14
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
5
:
473
-
4
8
1
480
9
7
.
3
9
%
a
n
d
a
n
F1
-
s
co
r
e
o
f
9
7
.
3
5
%.
T
h
ese
r
esu
lts
u
n
d
e
r
s
co
r
e
th
e
ca
p
ab
ilit
y
o
f
ad
v
an
ce
d
m
ac
h
in
e
lear
n
in
g
m
eth
o
d
s
to
im
p
r
o
v
e
s
tr
o
k
e
p
r
e
d
ictio
n
ac
cu
r
ac
y
.
Mo
v
in
g
f
o
r
w
ar
d
,
th
e
s
u
cc
ess
f
u
l
ap
p
licatio
n
o
f
th
ese
tech
n
iq
u
es
o
p
en
s
a
v
en
u
es
f
o
r
en
h
an
ce
d
s
tr
o
k
e
r
is
k
ass
e
s
s
m
en
t
an
d
ea
r
ly
in
ter
v
en
tio
n
s
tr
ateg
ies
i
n
clin
ical
s
ettin
g
s
.
Mo
r
eo
v
er
,
th
e
r
o
b
u
s
t
p
er
f
o
r
m
an
ce
o
f
th
e
GB
an
d
RF
m
o
d
els
s
u
g
g
ests
th
eir
s
u
itab
ilit
y
f
o
r
r
ea
l
-
wo
r
l
d
d
ep
lo
y
m
e
n
t
in
h
ea
lth
ca
r
e
s
y
s
t
em
s
,
wh
er
e
ac
cu
r
ate
s
tr
o
k
e
p
r
e
d
ictio
n
ca
n
s
ig
n
if
ican
tly
im
p
a
ct
p
a
tien
t
o
u
tco
m
es.
Fu
r
th
er
m
o
r
e
,
th
is
s
tu
d
y
p
r
o
m
p
ts
f
u
r
th
er
ex
p
l
o
r
atio
n
in
t
o
th
e
in
te
g
r
atio
n
o
f
a
d
v
an
ce
d
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
s
with
d
o
m
ain
-
s
p
ec
if
ic
k
n
o
wled
g
e
a
n
d
ad
d
itio
n
al
p
atien
t
d
ata
s
o
u
r
ce
s
,
s
u
ch
as
g
en
etic
m
ar
k
er
s
o
r
life
s
ty
le
f
ac
to
r
s
.
Su
ch
in
ter
d
i
s
cip
lin
ar
y
ap
p
r
o
ac
h
es
h
o
ld
p
r
o
m
is
e
f
o
r
r
ef
in
i
n
g
s
tr
o
k
e
p
r
e
d
ictio
n
m
o
d
els
an
d
tailo
r
in
g
in
ter
v
en
tio
n
s
to
in
d
iv
id
u
al
p
atien
t
p
r
o
f
iles
.
Ultim
ately
,
th
e
f
in
d
in
g
s
p
r
esen
ted
in
th
is
s
tu
d
y
co
n
tr
ib
u
te
to
th
e
o
n
g
o
in
g
r
esear
ch
ef
f
o
r
ts
aim
ed
at
lev
er
a
g
in
g
m
ac
h
in
e
l
ea
r
n
in
g
f
o
r
p
r
o
ac
tiv
e
h
ea
lth
ca
r
e
m
an
ag
em
e
n
t.
B
y
elu
cid
atin
g
th
e
e
f
f
ec
tiv
en
ess
o
f
d
ata
b
ala
n
cin
g
a
n
d
h
y
p
er
p
ar
am
eter
o
p
tim
izatio
n
tech
n
i
q
u
es,
th
is
r
esear
ch
ad
v
an
ce
s
o
u
r
u
n
d
er
s
tan
d
in
g
o
f
s
tr
o
k
e
p
r
e
d
ictio
n
an
d
p
av
es th
e
way
f
o
r
f
u
tu
r
e
in
n
o
v
atio
n
s
i
n
clin
ical
p
r
ac
tice.
RE
F
E
R
E
NC
E
S
[
1
]
S
.
J.
M
u
r
p
h
y
a
n
d
D
.
J.
W
e
r
r
i
n
g
,
“
S
t
r
o
k
e
:
c
a
u
s
e
s
a
n
d
c
l
i
n
i
c
a
l
f
e
a
t
u
r
e
s,
”
M
e
d
i
c
i
n
e
,
v
o
l
.
4
8
,
n
o
.
9
,
p
p
.
5
6
1
–
5
6
6
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
mp
me
d
.
2
0
2
0
.
0
6
.
0
0
2
.
[
2
]
W
H
O
,
“
S
t
r
o
k
e
,
c
e
r
e
b
r
o
v
a
sc
u
l
a
r
a
c
c
i
d
e
n
t
,
”
H
e
a
l
t
h
T
o
p
i
c
,
W
o
r
l
d
H
e
a
l
t
h
O
r
g
a
n
i
z
a
t
i
o
n
,
2
0
2
1
.
A
c
c
e
ss
e
d
:
J
u
n
.
2
5
,
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
.
e
mr
o
.
w
h
o
.
i
n
t
/
h
e
a
l
t
h
-
t
o
p
i
c
s/
s
t
r
o
k
e
-
c
e
r
e
b
r
o
v
a
s
c
u
l
a
r
-
a
c
c
i
d
e
n
t
/
i
n
d
e
x
.
h
t
m
l
[
3
]
D
.
K
u
r
i
a
k
o
s
e
a
n
d
Z
.
X
i
a
o
,
“
P
a
t
h
o
p
h
y
s
i
o
l
o
g
y
a
n
d
t
r
e
a
t
me
n
t
o
f
s
t
r
o
k
e
:
P
r
e
s
e
n
t
s
t
a
t
u
s
a
n
d
f
u
t
u
r
e
p
e
r
s
p
e
c
t
i
v
e
s,”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
M
o
l
e
c
u
l
a
r
S
c
i
e
n
c
e
s
,
v
o
l
.
2
1
,
n
o
.
2
0
,
p
p
.
1
–
2
4
,
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
i
j
ms
2
1
2
0
7
6
0
9
.
[
4
]
M
.
O
.
O
w
o
l
a
b
i
e
t
a
l
.
,
“
P
r
i
m
a
r
y
st
r
o
k
e
p
r
e
v
e
n
t
i
o
n
w
o
r
l
d
w
i
d
e
:
t
r
a
n
s
l
a
t
i
n
g
e
v
i
d
e
n
c
e
i
n
t
o
a
c
t
i
o
n
,
”
T
h
e
L
a
n
c
e
t
P
u
b
l
i
c
H
e
a
l
t
h
,
v
o
l
.
7
,
n
o
.
1
,
p
p
.
e
7
4
–
e
8
5
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
S
2
4
6
8
-
2
6
6
7
(
2
1
)
0
0
2
3
0
-
9.
[
5
]
T.
N
.
R
o
c
h
m
a
h
,
I
.
T.
R
a
h
maw
a
t
i
,
M
.
D
a
h
l
u
i
,
W
.
B
u
d
i
a
r
t
o
,
a
n
d
N
.
B
i
l
q
i
s,
“
E
c
o
n
o
mi
c
b
u
r
d
e
n
o
f
st
r
o
k
e
d
i
se
a
se
:
A
sy
st
e
ma
t
i
c
r
e
v
i
e
w
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
E
n
v
i
ro
n
m
e
n
t
a
l
Re
s
e
a
r
c
h
a
n
d
P
u
b
l
i
c
H
e
a
l
t
h
,
v
o
l
.
1
8
,
n
o
.
1
4
,
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
i
j
e
r
p
h
1
8
1
4
7
5
5
2
.
[
6
]
M
.
J
a
v
a
i
d
,
A
.
H
a
l
e
e
m,
R
.
P
r
a
t
a
p
S
i
n
g
h
,
R
.
S
u
ma
n
,
a
n
d
S
.
R
a
b
,
“
S
i
g
n
i
f
i
c
a
n
c
e
o
f
mac
h
i
n
e
l
e
a
r
n
i
n
g
i
n
h
e
a
l
t
h
c
a
r
e
:
F
e
a
t
u
r
e
s,
p
i
l
l
a
r
s
a
n
d
a
p
p
l
i
c
a
t
i
o
n
s,
”
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
N
e
t
w
o
rks
,
v
o
l
.
3
,
p
p
.
5
8
–
7
3
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
j
i
n
.
2
0
2
2
.
0
5
.
0
0
2
.
[
7
]
A
.
A
.
A
o
u
r
a
g
h
a
n
d
M
.
B
a
h
a
j
,
“
C
o
m
b
i
n
i
n
g
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
w
i
t
h
C
N
N
s
a
n
d
mac
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms
f
o
r
i
m
p
r
o
v
e
d
b
r
a
i
n
t
u
m
o
r
c
l
a
ss
i
f
i
c
a
t
i
o
n
f
r
o
m
M
R
I
,
”
i
n
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
D
a
t
a
S
c
i
e
n
c
e
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
,
2
0
2
4
,
p
p
.
3
9
1
–
3
9
7
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
0
3
1
-
4
8
5
7
3
-
2
_
5
6
.
[
8
]
A
.
A
.
A
o
u
r
a
g
h
a
n
d
M
.
B
a
h
a
j
,
“
F
e
a
t
u
r
e
se
l
e
c
t
i
o
n
a
n
d
d
i
me
n
s
i
o
n
a
l
i
t
y
r
e
d
u
c
t
i
o
n
f
o
r
u
n
b
a
l
a
n
c
e
d
l
i
v
e
r
d
i
se
a
se
c
l
a
ssi
f
i
c
a
t
i
o
n
w
i
t
h
o
p
t
i
m
i
z
e
d
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
m
s,”
i
n
2
0
2
3
7
t
h
I
EEE
C
o
n
g
re
ss
o
n
I
n
f
o
rm
a
t
i
o
n
S
c
i
e
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
(
C
i
S
t
)
,
2
0
2
3
,
p
p
.
5
4
7
–
5
5
2
,
d
o
i
:
1
0
.
1
1
0
9
/
C
i
S
t
5
6
0
8
4
.
2
0
2
3
.
1
0
4
0
9
9
6
7
.
[
9
]
M
.
M
.
A
h
sa
n
,
S
.
A
.
L
u
n
a
,
a
n
d
Z.
S
i
d
d
i
q
u
e
,
“
M
a
c
h
i
n
e
-
l
e
a
r
n
i
n
g
-
b
a
se
d
d
i
s
e
a
s
e
d
i
a
g
n
o
si
s
:
a
c
o
m
p
r
e
h
e
n
s
i
v
e
r
e
v
i
e
w
,
”
H
e
a
l
t
h
c
a
r
e
,
v
o
l
.
1
0
,
n
o
.
3
,
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
h
e
a
l
t
h
c
a
r
e
1
0
0
3
0
5
4
1
.
[
1
0
]
K
.
M
.
H
a
s
i
b
e
t
a
l
.
,
“
A
s
u
r
v
e
y
o
f
me
t
h
o
d
s
f
o
r
m
a
n
a
g
i
n
g
t
h
e
c
l
a
ssi
f
i
c
a
t
i
o
n
a
n
d
s
o
l
u
t
i
o
n
o
f
d
a
t
a
i
mb
a
l
a
n
c
e
p
r
o
b
l
e
m,
”
J
o
u
r
n
a
l
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
1
6
,
n
o
.
1
1
,
p
p
.
1
5
4
6
–
1
5
5
7
,
2
0
2
0
,
d
o
i
:
1
0
.
3
8
4
4
/
JC
S
S
P
.
2
0
2
0
.
1
5
4
6
.
1
5
5
7
.
[
1
1
]
J.
K
o
n
g
,
W
.
K
o
w
a
l
c
z
y
k
,
D
.
A
.
N
g
u
y
e
n
,
T
.
B
a
c
k
,
a
n
d
S
.
M
e
n
z
e
l
,
“
H
y
p
e
r
p
a
r
a
met
e
r
o
p
t
i
m
i
sa
t
i
o
n
f
o
r
i
mp
r
o
v
i
n
g
c
l
a
ssi
f
i
c
a
t
i
o
n
u
n
d
e
r
c
l
a
ss
i
mb
a
l
a
n
c
e
,
”
i
n
2
0
1
9
I
EE
E
S
y
m
p
o
s
i
u
m
S
e
ri
e
s
o
n
C
o
m
p
u
t
a
t
i
o
n
a
l
I
n
t
e
l
l
i
g
e
n
c
e
(
S
S
C
I
)
,
2
0
1
9
,
p
p
.
3
0
7
2
–
3
0
7
8
,
d
o
i
:
1
0
.
1
1
0
9
/
S
S
C
I
4
4
8
1
7
.
2
0
1
9
.
9
0
0
2
6
7
9
.
[
1
2
]
C
.
H
.
L
i
n
e
t
a
l
.
,
“
Ev
a
l
u
a
t
i
o
n
o
f
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
me
t
h
o
d
s
t
o
st
r
o
k
e
o
u
t
c
o
me
p
r
e
d
i
c
t
i
o
n
u
s
i
n
g
a
n
a
t
i
o
n
w
i
d
e
d
i
sea
s
e
r
e
g
i
st
r
y
,
”
C
o
m
p
u
t
e
r
M
e
t
h
o
d
s
a
n
d
Pr
o
g
r
a
m
s
i
n
Bi
o
m
e
d
i
c
i
n
e
,
v
o
l
.
1
9
0
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
mp
b
.
2
0
2
0
.
1
0
5
3
8
1
.
[
1
3
]
M
.
D
a
i
d
o
n
e
,
S
.
F
e
r
r
a
n
t
e
l
l
i
,
a
n
d
A
.
T
u
t
t
o
l
o
m
o
n
d
o
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
l
i
c
a
t
i
o
n
s
i
n
s
t
r
o
k
e
m
e
d
i
c
i
n
e
:
A
d
v
a
n
c
e
men
t
s,
c
h
a
l
l
e
n
g
e
s
,
a
n
d
f
u
t
u
r
e
p
r
o
s
p
e
c
t
i
v
e
,
”
N
e
u
ra
l
R
e
g
e
n
e
r
a
t
i
o
n
Re
s
e
a
r
c
h
,
v
o
l
.
1
9
,
n
o
.
4
,
p
p
.
7
6
9
–
7
7
3
,
2
0
2
4
,
d
o
i
:
1
0
.
4
1
0
3
/
1
6
7
3
-
5
3
7
4
.
3
8
2
2
2
8
.
[
1
4
]
M
.
S
.
S
i
r
sa
t
,
E.
F
e
r
m
é
,
a
n
d
J.
C
â
ma
r
a
,
“
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
:
a
r
e
v
i
e
w
,
”
J
o
u
r
n
a
l
o
f
S
t
ro
k
e
a
n
d
C
e
re
b
r
o
v
a
sc
u
l
a
r
D
i
sea
ses
,
v
o
l
.
2
9
,
n
o
.
1
0
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
s
t
r
o
k
e
c
e
r
e
b
r
o
v
a
sd
i
s.
2
0
2
0
.
1
0
5
1
6
2
.
[
1
5
]
M
.
U
.
Emo
n
,
M
.
S
.
K
e
y
a
,
T.
I
.
M
e
g
h
l
a
,
M
.
M
.
R
a
h
ma
n
,
M
.
S
.
A
l
M
a
m
u
n
,
a
n
d
M
.
S
.
K
a
i
s
e
r
,
“
P
e
r
f
o
r
m
a
n
c
e
a
n
a
l
y
si
s
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
i
n
s
t
r
o
k
e
p
r
e
d
i
c
t
i
o
n
,
”
i
n
2
0
2
0
4
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
El
e
c
t
r
o
n
i
c
s,
C
o
m
m
u
n
i
c
a
t
i
o
n
a
n
d
A
e
ro
s
p
a
c
e
T
e
c
h
n
o
l
o
g
y
(
I
C
EC
A)
,
2
0
2
0
,
p
p
.
1
4
6
4
–
1
4
6
9
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
E
C
A
4
9
3
1
3
.
2
0
2
0
.
9
2
9
7
5
2
5
.
[
1
6
]
T.
Ta
z
i
n
,
M
.
N
.
A
l
a
m
,
N
.
N
.
D
o
l
a
,
M
.
S
.
B
a
r
i
,
S
.
B
o
u
r
o
u
i
s,
a
n
d
M
.
M
.
K
h
a
n
,
“
S
t
r
o
k
e
d
i
s
e
a
s
e
d
e
t
e
c
t
i
o
n
a
n
d
p
r
e
d
i
c
t
i
o
n
u
s
i
n
g
r
o
b
u
s
t
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
e
s,
”
J
o
u
r
n
a
l
o
f
H
e
a
l
t
h
c
a
r
e
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
2
0
2
1
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
1
/
7
6
3
3
3
8
1
.
[
1
7
]
B
.
A
k
t
e
r
,
A
.
R
a
j
b
o
n
g
sh
i
,
S
.
S
a
z
z
a
d
,
R
.
S
h
a
k
i
l
,
J
.
B
i
sw
a
s,
a
n
d
U
.
S
a
r
a
,
“
A
mac
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
t
o
d
e
t
e
c
t
t
h
e
b
r
a
i
n
s
t
r
o
k
e
d
i
s
e
a
se
,
”
i
n
2
0
2
2
4
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
S
m
a
r
t
S
y
s
t
e
m
s
a
n
d
I
n
v
e
n
t
i
v
e
T
e
c
h
n
o
l
o
g
y
(
I
C
S
S
I
T
)
,
2
0
2
2
,
p
p
.
8
9
7
–
9
0
1
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
S
S
I
T5
3
2
6
4
.
2
0
2
2
.
9
7
1
6
3
4
5
.
[
1
8
]
S
.
P
a
l
i
w
a
l
,
S
.
P
a
r
v
e
e
n
,
M
.
A
.
A
l
a
m
,
a
n
d
J.
A
h
m
e
d
,
“
I
mp
r
o
v
i
n
g
b
r
a
i
n
s
t
r
o
k
e
p
r
e
d
i
c
t
i
o
n
t
h
r
o
u
g
h
o
v
e
r
sa
mp
l
i
n
g
t
e
c
h
n
i
q
u
e
s:
a
c
o
m
p
a
r
a
t
i
v
e
e
v
a
l
u
a
t
i
o
n
o
f
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms,
”
Pr
e
p
r
i
n
t
s
,
p
p
.
1
–
1
8
,
2
0
2
3
,
d
o
i
:
1
0
.
2
0
9
4
4
/
p
r
e
p
r
i
n
t
s2
0
2
3
0
6
.
1
4
4
4
.
v
1
.
[
1
9
]
S
.
S
r
i
v
a
s
t
a
v
,
K
.
G
u
l
e
r
i
a
,
a
n
d
S
.
S
h
a
r
ma,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
m
o
d
e
l
s
f
o
r
e
a
r
l
y
b
r
a
i
n
s
t
r
o
k
e
p
r
e
d
i
c
t
i
o
n
:
a
p
e
r
f
o
r
man
c
e
a
n
a
l
o
g
y
,
”
i
n
2
0
2
3
Wo
rl
d
C
o
n
f
e
r
e
n
c
e
o
n
C
o
m
m
u
n
i
c
a
t
i
o
n
&
C
o
m
p
u
t
i
n
g
(
WC
O
N
F)
,
2
0
2
3
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
W
C
O
N
F
5
8
2
7
0
.
2
0
2
3
.
1
0
2
3
5
0
7
0
.
[
2
0
]
A
.
S
r
i
n
i
v
a
s
a
n
d
J.
P
.
M
o
s
i
g
a
n
t
i
,
“
A
b
r
a
i
n
s
t
r
o
k
e
d
e
t
e
c
t
i
o
n
m
o
d
e
l
u
si
n
g
so
f
t
v
o
t
i
n
g
b
a
se
d
e
n
sem
b
l
e
mac
h
i
n
e
l
e
a
r
n
i
n
g
c
l
a
ss
i
f
i
e
r
,
”
Me
a
su
r
e
m
e
n
t
:
S
e
n
s
o
rs
,
v
o
l
.
2
9
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
me
a
se
n
.
2
0
2
3
.
1
0
0
8
7
1
.
[
2
1
]
F
.
S
o
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
se
t
,
”
K
a
g
g
l
e
.
2
0
2
0
.
A
c
c
e
sse
d
:
J
u
n
.
2
5
,
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
2
]
T.
D
.
P
i
y
a
d
a
s
a
a
n
d
K
.
G
u
n
a
w
a
r
d
a
n
a
,
“
A
r
e
v
i
e
w
o
n
o
v
e
r
sam
p
l
i
n
g
t
e
c
h
n
i
q
u
e
s
f
o
r
so
l
v
i
n
g
t
h
e
d
a
t
a
i
m
b
a
l
a
n
c
e
p
r
o
b
l
e
m
i
n
c
l
a
ss
i
f
i
c
a
t
i
o
n
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
n
A
d
v
a
n
c
e
s
i
n
I
C
T
f
o
r
Em
e
r
g
i
n
g
Re
g
i
o
n
s
(
I
C
T
e
r)
,
v
o
l
.
1
6
,
n
o
.
1
,
p
p
.
2
2
–
3
1
,
2
0
2
3
,
d
o
i
:
1
0
.
4
0
3
8
/
i
c
t
e
r
.
v
1
6
i
1
.
7
2
6
0
.
[
2
3
]
A
.
A
.
A
o
u
r
a
g
h
a
n
d
M
.
B
a
h
a
j
,
“
A
d
v
a
n
c
i
n
g
b
r
e
a
s
t
c
a
n
c
e
r
d
i
a
g
n
o
si
s
w
i
t
h
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
:
e
x
p
l
o
r
i
n
g
d
a
t
a
b
a
l
a
n
c
i
n
g
,
f
e
a
t
u
r
e
sel
e
c
t
i
o
n
,
a
n
d
b
a
y
e
s
i
a
n
o
p
t
i
m
i
z
a
t
i
o
n
,
”
i
n
2
0
2
3
I
EEE
6
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
ren
c
e
o
n
C
l
o
u
d
C
o
m
p
u
t
i
n
g
a
n
d
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
:
T
e
c
h
n
o
l
o
g
i
e
s
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s (
C
l
o
u
d
T
e
c
h
)
,
2
0
2
3
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
C
l
o
u
d
Te
c
h
5
8
7
3
7
.
2
0
2
3
.
1
0
3
6
6
0
5
8
.
[
2
4
]
L.
W
a
n
g
,
M
.
H
a
n
,
X
.
Li
,
N
.
Z
h
a
n
g
,
a
n
d
H
.
C
h
e
n
g
,
“
R
e
v
i
e
w
o
f
c
l
a
s
si
f
i
c
a
t
i
o
n
m
e
t
h
o
d
s
o
n
u
n
b
a
l
a
n
c
e
d
d
a
t
a
se
t
s,”
I
EEE
Ac
c
e
ss
,
v
o
l
.
9
,
p
p
.
6
4
6
0
6
–
6
4
6
2
8
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
1
.
3
0
7
4
2
4
3
.
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
B
a
la
n
cin
g
a
n
d
meta
h
eu
r
is
tic
tech
n
iq
u
es fo
r
imp
r
o
vin
g
m
a
ch
in
e
lea
r
n
in
g
mo
d
els in
…
(
A
b
d
A
lla
h
A
o
u
r
a
g
h
)
481
[
2
5
]
W
.
Li
,
“
I
mb
a
l
a
n
c
e
d
d
a
t
a
o
p
t
i
mi
z
a
t
i
o
n
c
o
m
b
i
n
i
n
g
K
-
me
a
n
s
a
n
d
S
M
O
TE
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
Pe
rf
o
rm
a
b
i
l
i
t
y
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
1
5
,
n
o
.
8
,
p
p
.
2
1
7
3
–
2
1
8
1
,
2
0
1
9
,
d
o
i
:
1
0
.
2
3
9
4
0
/
i
j
p
e
.
1
9
.
0
8
.
p
1
7
.
2
1
7
3
2
1
8
1
.
[
2
6
]
A
.
A
.
A
o
u
r
a
g
h
,
M
.
B
a
h
a
j
,
a
n
d
N
.
G
h
e
r
a
b
i
,
“
C
o
m
p
a
r
a
t
i
v
e
st
u
d
y
o
f
d
i
me
n
si
o
n
a
l
i
t
y
r
e
d
u
c
t
i
o
n
t
e
c
h
n
i
q
u
e
s
a
n
d
mac
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms
f
o
r
a
l
z
h
e
i
mer’
s
d
i
se
a
se
c
l
a
ssi
f
i
c
a
t
i
o
n
a
n
d
p
r
e
d
i
c
t
i
o
n
,
”
i
n
2
0
2
2
I
E
EE
3
r
d
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
El
e
c
t
ro
n
i
c
s,
C
o
n
t
r
o
l
,
O
p
t
i
m
i
z
a
t
i
o
n
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
(
I
C
E
C
O
C
S
)
,
2
0
2
2
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
EC
O
C
S
5
5
1
4
8
.
2
0
2
2
.
9
9
8
3
2
1
1
.
[
2
7
]
S
.
U
d
d
i
n
,
A
.
K
h
a
n
,
M
.
E
.
H
o
ss
a
i
n
,
a
n
d
M
.
A
.
M
o
n
i
,
“
C
o
m
p
a
r
i
n
g
d
i
f
f
e
r
e
n
t
s
u
p
e
r
v
i
se
d
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms
f
o
r
d
i
s
e
a
se
p
r
e
d
i
c
t
i
o
n
,
”
B
MC
Me
d
i
c
a
l
I
n
f
o
rm
a
t
i
c
s a
n
d
D
e
c
i
si
o
n
Ma
k
i
n
g
,
v
o
l
.
1
9
,
n
o
.
1
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
8
6
/
s
1
2
9
1
1
-
0
1
9
-
1
0
0
4
-
8.
[
2
8
]
D
.
P
a
u
l
,
G
.
G
a
i
n
,
a
n
d
S
.
O
r
a
n
g
,
“
A
d
v
a
n
c
e
d
r
a
n
d
o
m
f
o
r
e
st
e
n
se
mb
l
e
f
o
r
s
t
r
o
k
e
p
r
e
d
i
c
t
i
o
n
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
A
d
v
a
n
c
e
d
Re
se
a
rc
h
i
n
C
o
m
p
u
t
e
r
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
1
1
,
n
o
.
3
,
2
0
2
2
,
d
o
i
:
1
0
.
1
7
1
4
8
/
i
j
a
r
c
c
e
.
2
0
2
2
.
1
1
3
4
3
.
[
2
9
]
S
.
Y
a
r
a
t
,
S
.
S
e
n
a
n
,
a
n
d
Z.
O
r
man
,
“
A
c
o
mp
a
r
a
t
i
v
e
s
t
u
d
y
o
n
P
S
O
w
i
t
h
o
t
h
e
r
m
e
t
a
h
e
u
r
i
st
i
c
m
e
t
h
o
d
s
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
S
e
r
i
e
s
i
n
O
p
e
r
a
t
i
o
n
s
Re
se
a
r
c
h
a
n
d
M
a
n
a
g
e
m
e
n
t
S
c
i
e
n
c
e
,
v
o
l
.
3
0
6
,
p
p
.
4
9
–
7
2
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
0
3
0
-
7
0
2
8
1
-
6
_
4
.
[
3
0
]
T.
D
o
k
e
r
o
g
l
u
,
E.
S
e
v
i
n
c
,
T.
K
u
c
u
k
y
i
l
maz
,
a
n
d
A
.
C
o
sar,
“
A
su
r
v
e
y
o
n
n
e
w
g
e
n
e
r
a
t
i
o
n
me
t
a
h
e
u
r
i
s
t
i
c
a
l
g
o
r
i
t
h
ms
,
”
C
o
m
p
u
t
e
rs a
n
d
I
n
d
u
st
r
i
a
l
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
1
3
7
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
i
e
.
2
0
1
9
.
1
0
6
0
4
0
.
[
3
1
]
S
.
A
.
H
i
c
k
s
e
t
a
l
.
,
“
O
n
e
v
a
l
u
a
t
i
o
n
m
e
t
r
i
c
s
f
o
r
me
d
i
c
a
l
a
p
p
l
i
c
a
t
i
o
n
s
o
f
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
,
”
S
c
i
e
n
t
i
f
i
c
Re
p
o
r
t
s
,
v
o
l
.
1
2
,
n
o
.
1
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
5
9
8
-
022
-
0
9
9
5
4
-
8.
[
3
2
]
J.
Le
v
e
r
,
M
.
K
r
z
y
w
i
n
s
k
i
,
a
n
d
N
.
A
l
t
m
a
n
,
“
C
l
a
ssi
f
i
c
a
t
i
o
n
e
v
a
l
u
a
t
i
o
n
,
”
N
a
t
u
r
e
M
e
t
h
o
d
s
,
v
o
l
.
1
3
,
n
o
.
8
,
p
p
.
6
0
3
–
6
0
4
,
2
0
1
6
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Abd
Alla
h
A
o
u
r
a
g
h
is
c
u
rr
e
n
tl
y
p
u
rsu
in
g
h
is
P
h
.
D.
a
t
t
h
e
M
IET
Lab
o
ra
to
r
y
,
F
a
c
u
lt
y
o
f
S
c
ien
c
e
s
a
n
d
Tec
h
n
i
q
u
e
s,
Ha
ss
a
n
F
irst
U
n
iv
e
rsit
y
,
S
e
t
t
a
t,
M
o
r
o
c
c
o
.
His
re
se
a
rc
h
is
fo
c
u
se
d
o
n
a
d
v
a
n
c
in
g
m
e
d
ica
l
d
iag
n
o
sis
su
p
p
o
rt
sy
ste
m
s,
with
a
p
a
rti
c
u
lar
e
m
p
h
a
sis
o
n
lev
e
ra
g
in
g
m
a
c
h
in
e
l
e
a
rn
i
n
g
,
d
e
e
p
lea
rn
in
g
,
a
n
d
c
o
m
p
u
ter
v
isio
n
tec
h
n
iq
u
e
s
to
d
e
v
e
lo
p
in
n
o
v
a
ti
v
e
so
l
u
ti
o
n
s.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
a
b
d
a
ll
a
h
a
o
u
ra
g
h
@g
m
a
il
.
c
o
m
.
Mo
h
a
m
e
d
B
a
h
a
j
re
c
e
iv
e
d
h
is
P
h
.
D.
in
M
a
th
e
m
a
ti
c
s
a
n
d
C
o
m
p
u
ter
S
c
ien
c
e
fro
m
th
e
Un
i
v
e
rsity
Ha
ss
a
n
1
st,
M
o
r
o
c
c
o
,
a
n
d
c
u
rre
n
tl
y
se
rv
e
s a
s a
F
u
ll
P
ro
fe
ss
o
r
i
n
th
e
De
p
a
rtme
n
t
o
f
M
a
th
e
m
a
ti
c
s
a
n
d
Co
m
p
u
ter
S
c
ien
c
e
s
a
t
th
e
Un
iv
e
rsity
Ha
ss
a
n
1
st,
F
a
c
u
lt
y
o
f
S
c
ien
c
e
s
&
Tec
h
n
o
l
o
g
y
,
S
e
tt
a
t,
M
o
r
o
c
c
o
.
Wi
th
a
ro
b
u
st
a
c
a
d
e
m
ic
b
a
c
k
g
ro
u
n
d
,
h
e
h
a
s
c
o
n
tri
b
u
ted
o
v
e
r
6
0
p
e
e
r
-
re
v
iew
e
d
p
a
p
e
rs,
sp
a
n
n
in
g
a
r
e
a
s
su
c
h
a
s
in
telli
g
e
n
t
s
y
ste
m
s,
o
n
to
lo
g
ies
e
n
g
i
n
e
e
rin
g
,
p
a
rti
a
l
a
n
d
d
iffere
n
ti
a
l
e
q
u
a
ti
o
n
s,
n
u
m
e
rica
l
a
n
a
ly
sis,
a
n
d
sc
ien
ti
fic
c
o
m
p
u
ti
n
g
.
He
h
a
s
p
ro
v
id
e
d
v
a
lu
a
b
le
p
e
e
r
re
v
iew
se
rv
ice
s
fo
r
v
a
rio
u
s
jo
u
rn
a
ls
a
n
d
m
e
n
t
o
re
d
se
v
e
ra
l
P
h
.
D.
stu
d
e
n
ts
i
n
c
o
m
p
u
ter
sc
ien
c
e
s
a
n
d
m
a
th
e
m
a
ti
c
s.
He
a
c
ti
v
e
ly
e
n
g
a
g
e
s
in
wo
rk
s
h
o
p
s,
se
m
in
a
rs,
a
n
d
a
c
a
d
e
m
ic
fo
ru
m
s
to
e
n
h
a
n
c
e
tea
c
h
in
g
m
e
th
o
d
o
l
o
g
ies
a
n
d
re
se
a
rc
h
p
r
a
c
ti
c
e
s
.
H
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
m
o
h
a
m
e
d
b
a
h
a
j@g
m
a
il
.
c
o
m
.
Fo
u
a
d
To
u
f
ik
re
c
e
iv
e
d
h
is
P
h
.
D.
in
Co
m
p
u
ter
S
c
ien
c
e
fro
m
th
e
Un
iv
e
rsity
Ha
ss
a
n
1
st,
S
e
tt
a
t
,
M
o
r
o
c
c
o
.
He
c
u
rre
n
t
l
y
h
o
l
d
s
t
h
e
p
o
sit
io
n
o
f
P
ro
fe
ss
o
r
o
f
C
o
m
p
u
ter
S
c
ien
c
e
s
a
t
th
e
Hig
h
e
r
S
c
h
o
o
l
o
f
Tec
h
n
o
lo
g
y
S
ALE,
M
o
h
a
m
m
e
d
V
Un
i
v
e
rsity
,
M
o
ro
c
c
o
.
Wi
th
e
x
p
e
rti
se
in
a
rti
ficia
l
in
telli
g
e
n
c
e
,
b
ig
d
a
ta,
a
n
d
d
a
tab
a
se
a
rc
h
it
e
c
tu
re
s,
h
is
r
e
se
a
rc
h
in
tere
sts
li
e
a
t
th
e
in
ters
e
c
ti
o
n
o
f
t
h
e
se
field
s.
His a
c
a
d
e
m
ic p
u
rsu
it
s a
im t
o
a
d
v
a
n
c
e
k
n
o
wle
d
g
e
a
n
d
in
n
o
v
a
ti
o
n
in
th
e
se
a
re
a
s,
c
o
n
tri
b
u
t
in
g
to
th
e
d
e
v
e
lo
p
m
e
n
t
o
f
c
u
t
ti
n
g
-
e
d
g
e
tec
h
n
o
lo
g
ies
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
to
u
fi
k
.
f
o
u
a
d
@
g
m
a
il
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.