I
A
E
S
I
n
t
e
r
n
at
io
n
al
Jou
r
n
al
of
A
r
t
if
ic
ia
l
I
n
t
e
ll
ig
e
n
c
e
(
I
J
-
AI
)
V
ol
.
14
, N
o.
2
,
A
pr
il
2025
, pp.
1
140
~
1
149
I
S
S
N
:
2252
-
8938
,
D
O
I
:
10.11591/
ij
a
i.
v
14
.i
2
.pp
1
140
-
1
149
1140
Jou
r
n
al
h
om
e
page
:
ht
tp
:
//
ij
ai
.
ia
e
s
c
or
e
.c
om
D
i
ab
e
t
e
s m
e
l
l
i
t
u
s d
i
ag
n
osi
s
m
e
t
h
od
b
ase
d
r
an
d
om
f
or
e
st
w
i
t
h
b
at
al
gor
i
t
h
m
S
yai
f
u
l
A
n
am
1
, F
id
ia
D
e
n
y T
is
n
a A
m
ij
aya
2
, S
at
r
io
H
ad
i
Wi
j
oyo
3
, D
ia
n
E
k
a R
at
n
aw
at
i
4
,
C
yn
t
h
ia
A
yu
D
w
i
L
e
s
t
ar
i
1
, M
u
h
ai
m
in
I
ly
as
1
1
D
e
pa
r
t
m
e
nt
of
M
a
t
he
m
a
t
i
c
s
, F
a
c
ul
t
y of
M
a
t
he
m
a
t
i
c
s
of
N
a
t
ur
a
l
S
c
i
e
nc
e
, B
r
a
w
i
j
a
ya
U
ni
ve
r
s
i
t
y, M
a
l
a
ng, I
ndone
s
i
a
2
D
e
pa
r
t
m
e
nt
of
M
a
t
he
m
a
t
i
c
s
, F
a
c
ul
t
y of
M
a
t
he
m
a
t
i
c
s
of
N
a
t
ur
a
l
S
c
i
e
nc
e
, M
ul
a
w
a
r
m
a
n U
ni
ve
r
s
i
t
y, S
a
m
a
r
i
nda
, I
ndone
s
i
a
3
D
e
pa
r
t
m
e
nt
of
I
nf
or
m
a
t
i
c
s
E
ngi
ne
e
r
i
ng,
F
a
c
ul
t
y of
C
om
put
e
r
S
c
i
e
nc
e
, B
r
a
w
i
j
a
ya
U
ni
ve
r
s
i
t
y, M
a
l
a
ng, I
ndone
s
i
a
4
D
e
pa
r
t
m
e
nt
of
I
nf
or
m
a
t
i
on
S
ys
t
e
m
, F
a
c
ul
t
y of
C
om
put
e
r
S
c
i
e
nc
e
, B
r
a
w
i
j
a
ya
U
ni
ve
r
s
i
t
y, M
a
l
a
ng, I
ndone
s
i
a
A
r
t
ic
le
I
n
f
o
A
B
S
T
R
A
C
T
A
r
ti
c
le
h
is
to
r
y
:
R
e
c
e
iv
e
d
F
e
b 1, 2024
R
e
vi
s
e
d
N
ov 5, 2024
A
c
c
e
pt
e
d
N
ov 14, 2024
Diabetes
mellitus
(DM)
is
a
very
dangerous
disease
and
can
cause
various
problems.
Early
diagnosis
of
DM
is
essential
to
avoid
seve
re
effec
ts
and
complicat
ions.
An
affordable
DM
diagnosi
s
method
can
be
develo
ped
by
applyin
g
machine
learning.
Random
forest
(RF)
is
a
machine
le
arning
technique
that
is
applied
to
develop
a
DM
diagnosis
method.
Howev
er,
the
optimization
of
RF
hyperparameters
determines
the
performance
of
RF
approach. S
warm int
elligence
(SI) coul
d be used
to so
lve the
hyperparamet
er
optimization
problem
on
RF.
It
is
robust
and
simple
to
be
applied
and
doesn’t
require
derivatives.
Bat
algorithm
(BA)
is
one
of
SI
techniqu
es
that
gives a balance betwe
en exploration and exploitation to find a glob
al opti
mal
solution.
This
article
proposes
developing
an
RF
-
BA
-
based
technique
for
diagnosing
DM.
The
results
of
the
experiment
demonstrate
that
RF
-
BA
can
diagnose
DM
more
accurately
than
conventional
RF.
RF
-
BA
has
higher
performance
compared
to
RF
-
particle
swarm
optimization
(PSO)
in
te
rms
of
computat
ional
time.
The
RF
-
BA
also
are
able
to
solve
the
over
fitting
problem
in
the
conventional
RF.
In
the
future,
the
proposed
method
has
a
high
chance
of
being
implemented
for
helping
people
with
earl
y
DM
diagnosis
with high accuracy, low
cost, and high
-
speed proce
ss.
K
e
y
w
o
r
d
s
:
B
a
t
a
lg
or
it
hm
D
ia
be
te
s
m
e
ll
it
us
D
ia
gnos
is
H
ype
r
pa
r
a
m
e
te
r
opt
im
iz
a
ti
on
R
a
ndom f
or
e
s
t
This is an
open
acce
ss artic
le unde
r the
CC BY
-
SA
license.
C
or
r
e
s
pon
di
n
g A
u
th
or
:
S
ya
if
ul
A
na
m
D
e
pa
r
tm
e
nt
of
M
a
th
e
m
a
ti
c
s
, F
a
c
ul
ty
of
M
a
th
e
m
a
ti
c
s
of
N
a
tu
r
a
l
S
c
ie
nc
e
, B
r
a
w
ij
a
ya
U
ni
ve
r
s
it
y
V
e
te
r
a
n S
tr
e
e
t,
M
a
la
ng, I
ndone
s
ia
E
m
a
il
:
s
ya
if
ul
@
ub.a
c
.i
d
1.
I
N
T
R
O
D
U
C
T
I
O
N
A
s
e
ve
r
e
m
e
ta
bol
i
s
m
th
a
t
e
le
va
t
e
s
bl
ood
s
ug
a
r
le
ve
ls
i
s
a
ha
ll
m
a
r
k
of
di
a
be
te
s
m
e
ll
it
us
(
D
M
)
[
1]
.
I
ndone
s
ia
is
r
a
te
d
s
e
ve
nt
h
out
of
te
n
c
ount
r
ie
s
in
th
e
w
or
ld
f
or
th
e
ove
r
a
ll
num
be
r
of
D
M
pa
ti
e
nt
s
.
T
e
n
poi
nt
e
ig
ht
m
il
li
on pe
opl
e
i
n I
ndone
s
ia
w
il
l
ha
ve
D
M
i
n 2020, r
e
pr
e
s
e
nt
in
g 6.2 pe
r
c
e
nt
of
t
he
c
ount
r
y'
s
t
ot
a
l
pa
ti
e
nt
popula
ti
on
[
2]
.
V
a
r
io
us
c
om
pl
ic
a
ti
ons
a
r
e
br
ought
on
by
D
M
[
3]
,
[
4]
.
P
e
r
s
ons
w
ho
ha
ve
ty
pe
1
or
ty
pe
2
di
a
be
te
s
f
r
e
que
nt
ly
e
xpe
r
ie
nc
e
c
om
pl
ic
a
ti
ons
a
nd
th
e
y
a
ls
o
dr
a
m
a
ti
c
a
ll
y
r
a
is
e
m
or
ta
li
ty
a
s
w
e
ll
a
s
m
or
bi
di
ty
[
5]
–
[
7]
.
T
he
r
e
a
r
e
two
m
a
in
c
a
te
gor
ie
s
of
c
om
pl
ic
a
ti
ons
a
s
s
o
c
ia
te
d
w
it
h
di
a
be
te
s
w
hi
c
h
a
r
e
m
ic
r
ova
s
c
ul
a
r
a
nd
m
a
c
r
ova
s
c
ul
a
r
.
T
he
m
ic
r
ova
s
c
ul
a
r
c
om
pl
ic
a
ti
ons
ha
ve
a
s
ig
ni
f
ic
a
nt
ly
gr
e
a
te
r
f
r
e
que
nc
y
th
a
n
th
e
m
a
c
r
ova
s
c
ul
a
r
c
om
pl
ic
a
ti
ons
[
8]
.
M
ic
r
ova
s
c
ul
a
r
pr
obl
e
m
s
in
c
l
ude
r
e
ti
nopa
th
y,
ne
ur
opa
th
y,
a
nd
ne
phr
opa
th
y,
w
he
r
e
a
s
m
a
c
r
ova
s
c
ul
a
r
c
om
pl
ic
a
ti
ons
in
c
lu
de
pe
r
ip
he
r
a
l
a
r
te
r
y
di
s
e
a
s
e
,
s
tr
oke
,
a
nd
c
a
r
di
ova
s
c
ul
a
r
di
s
e
a
s
e
[
3]
,
[
9]
,
[
10]
.
W
it
h
236
th
ous
a
nd
D
M
-
r
e
la
te
d
de
a
th
s
in
2021,
I
n
done
s
ia
r
a
nk
s
a
s
ha
vi
ng
th
e
s
ix
th
-
hi
ghe
s
t
D
M
m
or
ta
li
ty
r
a
te
, a
c
c
or
di
ng t
o t
he
I
nt
e
r
na
ti
ona
l
D
ia
be
te
s
F
e
de
r
a
ti
on (
I
D
F
)
[
11
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
r
ti
f
I
nt
e
ll
I
S
S
N
:
2252
-
8938
D
ia
be
te
s
m
e
ll
it
us
di
agnos
i
s
m
e
th
od bas
e
d r
andom fo
r
e
s
t
w
it
h b
at
al
gor
it
hm
(
Sy
ai
fu
l
A
nam
)
1141
E
a
r
ly
id
e
nt
if
ic
a
ti
on
of
D
M
is
c
r
uc
ia
l
to
pr
e
ve
nt
it
s
s
e
ve
r
it
y
s
ym
pt
om
s
a
nd
c
om
pl
ic
a
ti
ons
.
D
ia
gnos
is
of
D
M
is
ty
pi
c
a
ll
y
pe
r
f
o
r
m
e
d
by
a
hi
gh
ly
s
ki
ll
e
d
phys
ic
ia
n
a
nd
ne
e
ds
hi
gh
e
xpe
ns
e
[
12]
,
[
13]
.
T
he
r
e
s
ul
ts
of
th
e
di
a
gnos
is
by
th
e
phys
i
c
ia
ns
a
r
e
of
te
n
bi
a
s
e
d
a
m
ongs
t
s
pe
c
ia
li
s
ts
[
14]
.
A
r
e
li
a
bl
e
a
nd
r
e
a
s
ona
bl
y
pr
ic
e
d
m
e
th
od f
or
di
a
gnos
in
g D
M
i
s
pos
s
ib
le
t
o be
done
by e
m
pl
oyi
ng
a
c
la
s
s
if
ic
a
ti
on t
e
c
hni
que
. O
ne
of
t
he
popula
r
a
nd
r
obus
t
c
la
s
s
if
ic
a
ti
on
m
e
th
ods
is
m
a
c
hi
ne
le
a
r
ni
ng.
M
a
c
hi
n
e
le
a
r
ni
ng
m
e
th
od
ha
s
m
a
ny
a
dva
nt
a
ge
s
ove
r
tr
a
di
ti
ona
l
m
e
th
ods
.
T
he
ir
a
dva
nt
a
ge
s
ha
ve
be
e
n
e
xt
e
ns
iv
e
l
y
s
tu
di
e
d
a
nd
doc
um
e
nt
e
d
in
va
r
io
us
f
ie
ld
s
.
M
a
c
hi
ne
le
a
r
ni
ng
m
e
th
ods
ha
ve
de
m
ons
tr
a
te
d
s
e
v
e
r
a
l
be
ne
f
it
s
ove
r
tr
a
di
ti
ona
l
a
pp
r
oa
c
he
s
,
in
c
lu
di
ng
im
pr
ove
d
pe
r
f
or
m
a
nc
e
,
e
nha
nc
e
d
pr
e
di
c
ti
ve
c
a
pa
bi
li
ti
e
s
,
a
nd
th
e
a
bi
li
ty
to
ha
ndl
e
c
om
pl
e
x
da
ta
s
tr
uc
tu
r
e
s
[
15]
.
T
he
m
a
c
hi
ne
le
a
r
ni
ng
a
ls
o
no
n
e
e
d
s
tr
ong
a
s
s
um
pt
io
ns
a
bout
th
e
ty
pe
of
e
r
r
or
di
s
tr
ib
ut
io
n,
m
uc
h
m
or
e
f
le
xi
bl
e
a
nd
do
not
r
e
qui
r
e
a
ny
a
pr
io
r
i
a
s
s
um
pt
io
n
s
[
16]
.
M
a
c
hi
ne
le
a
r
ni
ng
ha
s
be
e
n
a
ppl
ie
d
s
uc
c
e
s
f
ul
ly
in
m
a
ny
f
ie
ld
s
,
s
uc
h
a
s
ve
hi
c
ul
a
r
ne
twor
ks
[
17]
,
[
18]
,
m
e
di
c
a
l
di
a
gnos
is
[
19]
,
[
20]
,
s
pe
e
c
h
r
e
c
ogni
ti
on
[
21]
,
c
om
put
a
ti
ona
l
im
a
gi
ng
[
15]
,
m
e
di
c
a
l
he
a
lt
hc
a
r
e
[
22]
,
s
ig
na
l
p
r
oc
e
s
s
in
g
[
23]
,
a
nd
a
ut
onomous
dr
iv
in
g
[
24]
.
T
he
m
a
c
hi
ne
l
e
a
r
ni
ng
te
c
hni
que
known a
s
r
a
ndom
f
or
e
s
t
(
R
F
)
ha
s
num
e
r
ous
be
n
e
f
it
s
,
s
uc
h a
s
th
e
c
a
pa
c
it
y
to
m
a
na
ge
bi
g
da
ta
s
e
ts
w
it
h
hi
gh
di
m
e
ns
io
n
a
li
ty
,
e
a
s
e
of
u
s
e
,
r
e
s
is
ta
nc
e
to
out
li
e
r
s
a
nd
noi
s
y
da
t
a
,
e
a
s
y
pa
r
a
ll
e
li
z
a
ti
on,
good
a
voi
da
nc
e
of
ove
r
f
it
ti
ng,
r
a
pi
d
pr
oc
e
s
s
in
g,
e
xc
e
ll
e
nt
pr
e
c
is
io
n,
r
obus
tn
e
s
s
,
a
nd
a
w
id
e
va
r
ie
ty
of
va
r
ia
bl
e
s
[
25]
–
[
28]
.
T
he
R
F
a
ppr
oa
c
h
ha
s
be
e
n
ut
il
iz
e
d
to
s
om
e
a
ppl
ic
a
ti
ons
,
i
nc
lu
di
ng
pr
e
di
c
ti
ng
c
ons
um
e
r
c
hur
n
[
29]
–
[
31]
,
de
te
c
ti
on
of
he
a
r
t
di
s
e
a
s
e
[
32]
,
in
s
ur
a
nc
e
a
c
c
e
pt
a
n
c
e
pr
e
di
c
ti
on
[
33]
,
id
e
nt
if
yi
ng
f
r
a
ud
[
34]
,
lo
a
n
f
or
e
c
a
s
ti
ng
[
27]
,
a
nd
br
e
a
s
t
c
a
nc
e
r
de
te
c
ti
on
[
35]
.
H
ow
e
ve
r
,
th
e
c
a
pa
bi
li
ty
of
th
e
R
F
te
c
hni
qu
e
is
gr
e
a
tl
y
im
pa
c
te
d
by
th
e
c
hoi
c
e
of
hyp
e
r
pa
r
a
m
e
te
r
s
.
W
h
e
n
th
e
hyp
e
r
pa
r
a
m
e
te
r
s
a
r
e
s
e
le
c
t
e
d
in
c
or
r
e
c
tl
y,
th
e
lo
s
s
of
f
unc
ti
on
c
a
nnot
be
e
f
f
ic
ie
nt
ly
r
e
duc
e
d,
w
hi
c
h
le
a
d
s
to
im
pr
e
c
is
e
f
in
di
ngs
f
r
om
th
e
R
F
a
ppr
oa
c
h.
T
he
r
e
f
or
e
,
th
e
r
ig
ht
R
F
hype
r
pa
r
a
m
e
te
r
m
us
t
be
c
hos
e
n
or
opt
im
iz
e
d
to
m
a
xi
m
iz
e
th
e
e
f
f
ic
a
c
y
of
th
e
R
F
a
ppr
oa
c
h.
S
e
ve
r
a
l
in
ve
s
ti
ga
ti
ons
ha
v
e
s
how
n
th
a
t
hyp
e
r
pa
r
a
m
e
te
r
a
dj
us
t
m
e
nt
s
ig
ni
f
ic
a
nt
ly
im
pr
ove
s
R
F
pe
r
f
or
m
a
nc
e
[
36]
.
I
n
s
tu
dy
by
Z
hu
e
t
al
.
[
36]
,
th
e
gr
id
s
e
a
r
c
h
is
us
e
d
to
s
e
le
c
t
th
e
R
F
hype
r
pa
r
a
m
e
te
r
s
.
H
ow
e
ve
r
,
th
is
m
e
th
od
ne
e
ds
a
hi
gh
c
om
put
a
ti
ona
l
c
os
t,
s
in
c
e
a
ll
c
om
bi
na
ti
o
ns
of
R
F
hype
r
pa
r
a
m
e
te
r
s
ha
ve
to
be
tr
ie
d
to
f
in
d
th
e
be
s
t
hype
r
pa
r
a
m
e
te
r
s
.
T
he
s
e
le
c
ti
on
of
hype
r
pa
r
a
m
e
te
r
s
of
th
e
R
F
pr
obl
e
m
c
a
n
be
r
e
pr
e
s
e
nt
e
d
in
th
e
opt
im
iz
a
ti
on f
or
m
ul
a
ti
on.
F
or
t
hi
s
r
e
a
s
on, R
F
c
a
n be
c
om
bi
ne
d w
it
h gl
oba
l
opt
im
iz
a
ti
on me
th
ods
, s
uc
h a
s
t
he
s
w
a
r
m
in
te
ll
ig
e
nc
e
(
S
I
)
te
c
hni
que
,
to
s
ol
ve
th
e
is
s
ue
of
c
hoos
in
g
hype
r
pa
r
a
m
e
te
r
s
in
th
e
R
F
m
e
th
od.
T
he
R
F
hype
r
pa
r
a
m
e
te
r
s
opt
im
iz
a
ti
on
by
us
in
g
S
I
doe
s
n’
t
ha
ve
to
tr
y
a
ll
c
om
bi
na
ti
ons
of
R
F
hype
r
pa
r
a
m
e
te
r
s
in
th
e
s
e
a
r
c
h
dom
a
in
,
w
hi
c
h
m
e
a
n
s
th
a
t
th
e
R
F
hyp
e
r
pa
r
a
m
e
te
r
s
opt
im
iz
a
ti
on
by
us
in
g
S
I
m
a
y
r
e
s
ul
t
in
a
s
hor
te
r
c
om
put
a
ti
ona
l
ti
m
e
t
ha
n t
he
gr
id
s
e
a
r
c
h m
e
th
od.
I
n
a
ddi
ti
on,
th
e
S
I
a
lg
or
it
hm
o
f
f
e
r
s
a
num
be
r
of
be
ne
f
it
s
.
T
he
S
I
a
ppr
oa
c
h
ha
s
a
bi
li
ty
to
s
e
a
r
c
h
a
gl
oba
l
opt
im
um
in
m
ul
ti
m
oda
l
f
unc
ti
ons
,
is
r
e
s
il
ie
nt
,
e
a
s
y
to
im
pl
e
m
e
nt
,
a
nd
doe
s
n'
t
ne
e
d
d
e
r
iv
a
ti
ve
[
37]
.
N
um
e
r
ous
S
I
te
c
hni
que
s
ha
ve
be
e
n
put
f
or
th
.
B
a
t
a
lg
or
it
hm
(
B
A
)
,
a
r
ti
f
ic
ia
l
be
e
c
ol
ony
(
A
B
C
)
a
lg
o
r
it
hm
,
pa
r
ti
c
le
s
w
a
r
m
opt
im
iz
a
ti
on
(
P
S
O
)
,
a
nd
f
ir
e
f
ly
a
lg
or
it
hm
(
F
A
)
a
r
e
s
om
e
S
I
e
xa
m
pl
e
s
.
A
c
c
or
di
ng
to
c
e
r
ta
in
r
e
s
e
a
r
c
h,
P
S
O
a
nd
B
A
pr
ovi
de
a
dva
nt
a
ge
s
in
th
e
b
a
la
nc
e
be
t
w
e
e
n
e
xpl
or
a
ti
on
a
nd
e
xpl
oi
ta
ti
on.
B
A
ha
s
a
num
be
r
of
be
ne
f
it
s
,
in
c
lu
di
ng
qui
c
k
c
onv
e
r
ge
nc
e
a
nd
th
e
r
e
qui
r
e
m
e
nt
f
or
f
e
w
pa
r
a
m
e
te
r
s
[
38]
.
A
ddi
ti
ona
ll
y,
one
s
tu
dy
de
m
ons
tr
a
te
s
th
a
t
th
e
c
onve
r
ge
nc
e
of
B
A
is
be
tt
e
r
t
ha
n
th
e
ge
ne
ti
c
a
lg
or
it
hm
(
G
A
)
a
nd
P
S
O
[
39
]
.
F
or
th
e
di
a
gnos
is
of
D
M
,
th
e
K
-
m
e
a
ns
a
lg
or
it
hm
,
w
hi
c
h
B
A
opt
im
iz
e
d,
ha
s
be
e
n
us
e
d
[
40]
.
R
e
s
e
a
r
c
h
in
di
c
a
te
s
th
a
t
th
e
K
-
m
e
a
ns
a
lg
or
it
hm
'
s
pe
r
f
or
m
a
nc
e
c
a
n
be
c
ons
id
e
r
a
bl
y
e
nha
nc
e
d
by
th
e
B
A
a
ppr
oa
c
h
e
s
;
ne
ve
r
th
e
le
s
s
,
ot
he
r
s
tu
di
e
s
'
f
in
di
ngs
in
di
c
a
te
th
a
t
th
e
R
F
m
e
th
od
out
pe
r
f
or
m
s
th
e
K
-
m
e
a
ns
m
e
th
od
[
41]
.
B
A
a
ls
o
ha
s
be
e
n
a
ppl
ie
d
s
u
c
c
e
s
s
f
ul
ly
to
m
a
ny
f
ie
ld
s
s
uc
h
a
s
tr
a
ns
por
t
ne
twor
k
de
s
ig
n
pr
obl
e
m
[
42]
,
jo
b
s
c
he
dul
in
g pr
obl
e
m
[
43]
, i
m
a
ge
e
nha
nc
e
m
e
nt
[
44]
,
a
nd
di
s
e
a
s
e
c
la
s
s
if
ic
a
ti
on
[
45]
.
B
a
s
e
d
on
th
e
pr
obl
e
m
th
a
t
ha
s
be
e
n
de
s
c
r
ib
e
d,
th
is
a
r
ti
c
le
s
ugge
s
t
s
de
v
e
lo
pi
ng
a
n
R
F
w
it
h
a
hype
r
pa
r
a
m
e
te
r
B
a
t
a
lg
or
it
hm
op
ti
m
iz
e
r
(
R
F
-
B
A
)
f
or
D
M
di
a
gnos
is
.
B
A
is
e
m
pl
oye
d
to
opt
im
iz
e
th
e
R
F
hype
r
pa
r
a
m
e
te
r
s
.
T
hi
s
a
r
ti
c
le
h
a
s
c
ont
r
ib
ut
e
d
to
c
r
e
a
ti
ng
a
D
M
di
a
gnos
i
s
m
e
th
od
w
it
h
hi
gh
a
c
c
ur
a
c
y
a
nd
a
c
c
e
pt
a
bl
e
c
om
put
a
ti
ona
l
ti
m
e
.
T
hi
s
a
r
ti
c
le
a
ls
o
h
a
s
a
c
ont
r
ib
ut
io
n
to
s
e
le
c
ti
ng
th
e
R
F
hype
r
pa
r
a
m
e
te
r
s
f
or
in
c
r
e
a
s
in
g
th
e
p
e
r
f
or
m
a
nc
e
of
R
F
by
ut
il
iz
in
g B
A
w
it
h s
hor
te
r
c
om
put
a
ti
on
ti
m
e
th
a
n
th
e
c
om
put
a
ti
ona
l
ti
m
e
of
th
e
pr
e
vi
ous
m
e
th
od
in
[
36]
.
T
he
s
ugge
s
te
d
a
ppr
oa
c
h
is
a
s
s
e
s
s
e
d
u
s
in
g
a
num
be
r
of
pe
r
f
o
r
m
a
nc
e
c
r
it
e
r
ia
,
in
c
lu
di
ng
c
om
put
a
ti
on
ti
m
e
,
f
1
s
c
or
e
,
a
c
c
ur
a
c
y,
r
e
c
a
ll
,
a
nd
pr
e
c
is
io
n
.
T
he
s
ugge
s
te
d
a
ppr
oa
c
h
is
c
ont
r
a
s
te
d
w
it
h R
F
-
P
S
O
a
nd t
r
a
di
ti
ona
l
R
F
.
2.
M
E
T
H
O
D
T
he
de
ve
lo
pm
e
nt
of
t
he
pr
opos
e
d m
e
th
od w
il
l
be
c
ove
r
e
d i
n t
hi
s
pa
r
t.
T
he
r
e
a
r
e
m
ul
ti
pl
e
s
te
ps
i
n t
he
pr
oc
e
s
s
,
in
c
lu
di
ng:
i)
ga
th
e
r
da
ta
,
ii
)
pr
e
-
p
r
oc
e
s
s
in
g
da
ta
,
ii
i)
de
ve
lo
p
RF
-
B
A
m
e
th
od,
iv
)
s
e
t
pa
r
a
m
e
te
r
s
of
th
e
pr
opos
e
d m
e
th
od, v)
a
s
s
e
s
s
t
h
e
pr
opos
e
d m
e
th
od, a
nd vi)
dr
a
w
c
onc
lu
s
io
n.
2.1.
D
at
as
e
t
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8938
I
nt
J
A
r
ti
f
I
nt
e
ll
,
V
ol
. 14, No. 2, A
pr
il
202
5
:
1
140
-
1
149
1142
T
he
da
ta
s
e
t
c
a
m
e
f
r
om
t
he
ka
ggl
e
.c
om
. T
he
R
F
-
B
A
a
ppr
oa
c
h f
or
di
a
gnos
in
g D
M
i
s
de
ve
lo
pe
d us
in
g
c
e
r
ta
in
f
e
a
tu
r
e
s
.
T
he
f
e
a
tu
r
e
s
u
s
e
d
in
th
e
c
la
s
s
if
ic
a
ti
on
m
ode
l
f
or
th
e
di
a
gnos
is
of
D
M
in
c
lu
de
hi
gh
bl
ood
pr
e
s
s
ur
e
(
hbp
)
,
hi
gh
c
hol
e
s
te
r
ol
(
hc
)
,
no
c
hol
e
s
te
r
ol
c
he
c
k
i
n
f
iv
e
ye
a
r
s
(
c
hol
)
,
body
m
a
s
s
in
de
x
(
bm
i
)
,
s
m
oke
r
(
s
m
k
)
,
s
tr
oke
(
s
tr
)
,
di
s
e
a
s
e
or
he
a
r
t
a
tt
a
c
k
(
ha
)
,
phys
i
c
a
l
a
c
ti
vi
ty
(
pa
)
,
f
r
ui
ts
(
fr
t
)
,
ve
ge
ta
bl
e
s
(
v
gt
)
,
he
a
vy
dr
in
ke
r
s
(
hd
)
,
ne
e
d
to
s
e
e
a
doc
to
r
(
ns
d
)
,
ge
ne
r
a
l
he
a
lt
h
(
gh
)
,
m
e
nt
a
l
he
a
lt
h
(
mh
)
,
phys
ic
a
l
he
a
lt
h
(
ph
)
,
di
f
f
ic
ul
t
w
a
lk
(
dw
)
,
s
e
x
(
sx
)
,
a
g
e
(
ag
)
,
e
du
c
a
ti
on
(
ed
)
,
in
c
o
m
e
(
in
c
)
,
a
nd
di
a
b
e
te
s
(
D
)
.
N
e
xt
,
it
w
il
l
be
di
s
c
us
s
e
d
a
n
e
xpl
a
na
ti
on
of
e
a
c
h
va
r
ia
bl
e
.
hpb
in
di
c
a
te
s
pa
ti
e
nt
w
it
h
hype
r
te
ns
io
n
a
nd
hc
r
e
pr
e
s
e
nt
s
f
or
pa
ti
e
nt
c
hol
e
s
te
r
ol
le
v
e
l.
T
h
e
pa
ti
e
nt
h
a
s
s
m
oke
d
a
t
le
a
s
t
100
c
i
ga
r
e
tt
e
s
dur
in
g
th
e
ir
li
f
e
ti
m
e
,
a
c
c
or
di
ng
to
th
e
s
m
k
.
s
tr
d
e
f
in
e
s
th
e
pa
ti
e
nt
w
it
h
s
tr
oke
.
P
a
ti
e
nt
s
w
it
h
m
yoc
a
r
di
a
l
in
f
a
r
c
ti
on
(
M
I
)
o
r
c
or
ona
r
y
he
a
r
t
di
s
e
a
s
e
(
C
H
D
)
a
r
e
de
f
in
e
d
by
ha.
pa
r
e
pr
e
s
e
nt
s
th
e
a
c
ti
vi
ty
of
pa
ti
e
nt
in
pa
s
t
30
da
ys
,
not
in
c
lu
di
ng
jo
b.
fr
t
a
r
e
de
f
in
e
d
a
s
th
os
e
th
a
t
a
r
e
c
ons
um
e
d
a
t
le
a
s
t
on
c
e
e
ve
r
y
da
y
a
nd
v
gt
a
r
e
de
f
in
e
d
a
s
th
os
e
th
a
t
a
r
e
c
on
s
um
e
d
a
t
a
t
le
a
s
t
on
c
e
e
ve
r
y
d
a
y.
W
hi
le
, a
dul
t
m
e
n
w
ho c
ons
um
e
m
or
e
t
ha
n
14
dr
in
ks
pe
r
w
e
e
k
a
nd a
dul
t
w
om
e
n
w
ho
c
ons
um
e
m
or
e
th
a
n
s
e
ve
n
dr
in
ks
p
e
r
w
e
e
k
a
r
e
c
on
s
id
e
r
e
d
hd.
ns
d
de
not
e
s
a
pe
r
io
d
w
it
hi
n
th
e
pr
e
vi
ous
12
m
ont
hs
w
he
n
a
pa
ti
e
nt
ne
e
de
d
to
s
e
e
a
doc
to
r
but
w
a
s
una
bl
e
to
do
s
o
due
to
f
in
a
nc
ia
l
c
ons
tr
a
in
ts
.
gh
is
m
e
a
s
ur
e
d
on a
s
c
a
le
of
1
f
or
e
xc
e
ll
e
nt
,
2
f
or
ve
r
y
good,
3
f
or
g
ood,
4
f
or
f
a
ir
,
a
nd
5
f
or
poor
a
nd
m
h
in
c
lu
de
s
s
tr
e
s
s
,
d
e
pr
e
s
s
io
n,
a
nd
e
m
ot
io
na
l
is
s
u
e
s
,
a
s
w
e
ll
a
s
th
e
num
be
r
of
da
ys
in
th
e
pr
e
vi
ous
30
da
y
s
th
a
t
w
e
r
e
not
good
f
or
m
e
nt
a
l
he
a
lt
h.
P
hys
ic
a
l
di
s
e
a
s
e
a
nd
in
ju
r
y
a
r
e
in
c
lu
de
d
in
ph
,
a
s
is
th
e
num
be
r
of
da
ys
in
th
e
la
s
t
30
da
ys
w
he
r
e
phys
ic
a
l
he
a
lt
h
w
a
s
poor
or
none
xi
s
te
nt
.
T
he
dw
s
ym
bol
iz
e
s
th
e
e
xt
r
e
m
e
di
f
f
ic
ul
ty
of
a
s
c
e
ndi
ng
s
ta
ir
s
or
w
a
lk
in
g. T
he
13
-
le
ve
l
a
ge
c
a
te
gor
y i
s
de
te
r
m
in
e
d by
ag
. O
n a
r
a
nki
ng s
ys
te
m
of
1 t
o 6,
ed
r
e
pr
e
s
e
nt
s
e
duc
a
ti
ona
l
le
ve
l.
V
a
lu
e
of
1
r
e
pr
e
s
e
nt
s
onl
y
a
tt
e
ndi
ng
pr
e
s
c
hool
or
ne
ve
r
a
tt
e
ndi
ng
s
c
hool
,
2
r
e
pr
e
s
e
nt
s
c
om
pl
e
ti
ng
e
le
m
e
nt
a
r
y
s
c
hool
gr
a
de
s
1
th
r
ough
8,
3
in
di
c
a
te
s
s
om
e
of
th
e
hi
gh
s
c
hool
gr
a
de
s
9
th
r
ough
11,
4
in
di
c
a
te
s
gr
a
de
12 or
hi
gh s
c
hool
g
r
a
dua
te
(
G
E
D
)
,
5 r
e
pr
e
s
e
nt
s
one
t
o t
hr
e
e
ye
a
r
s
of
c
ol
le
ge
, a
nd 6 r
e
pr
e
s
e
nt
s
f
our
ye
a
r
s
or
m
or
e
o
f
c
ol
le
ge
(
c
ol
le
ge
gr
a
dua
te
)
.
A
c
c
or
di
ng
t
o
th
e
in
c
om
e
s
c
a
le
,
a
va
lu
e
of
1
de
not
e
s
le
s
s
th
a
n
$10,000,
a
va
lu
e
of
5
de
not
e
s
unde
r
th
a
n
$35,000,
a
nd
a
va
lu
e
of
8
de
not
e
s
gr
e
a
te
r
th
a
n
$75,000.
D
r
e
pr
e
s
e
nt
s
t
he
D
M
s
ta
te
.
2.2.
D
at
a p
r
e
-
p
r
oc
e
s
s
in
g
P
r
e
pa
r
in
g
r
a
w
da
ta
in
to
a
us
e
f
ul
f
or
m
a
t
is
th
e
a
im
of
da
ta
pr
e
-
pr
oc
e
s
s
in
g.
S
e
ve
r
a
l
da
ta
pr
e
-
pr
oc
e
s
s
in
g m
e
th
ods
w
e
r
e
us
e
d i
n t
hi
s
w
or
k, s
uc
h a
s
da
ta
t
r
a
ns
f
or
m
a
ti
on, de
a
li
ng w
it
h m
is
s
in
g va
lu
e
s
, a
nd
m
is
s
in
g
va
lu
e
in
s
pe
c
ti
on.
I
na
de
qua
t
e
ha
ndl
in
g
of
th
e
s
e
m
is
s
in
g
va
lu
e
s
w
il
l
li
ke
ly
m
a
ke
it
di
f
f
ic
ul
t
to
dr
a
w
a
tr
us
twor
th
y
c
onc
lu
s
io
n.
T
he
da
ta
in
th
is
s
tu
dy
is
tr
a
ns
f
or
m
e
d
us
in
g
m
in
-
m
a
x
nor
m
a
li
z
a
ti
on.
D
a
ta
tr
a
ns
f
or
m
a
ti
on'
s
m
a
in
obj
e
c
ti
ve
is
to
c
ha
nge
th
e
s
c
a
le
of
m
e
a
s
u
r
e
m
e
nt
of
th
e
r
a
w
da
ta
in
to
a
di
f
f
e
r
e
nt
f
or
m
a
t
s
o t
ha
t
it
c
a
n be
pr
oc
e
s
s
e
d e
f
f
e
c
ti
ve
ly
a
nd
s
a
ti
s
f
y t
he
s
pe
c
if
ic
a
ti
ons
of
t
he
s
e
le
c
te
d pr
oc
e
s
s
in
g m
e
th
od.
2.3.
D
e
ve
lo
p
in
g t
h
e
al
gor
it
h
m
of
t
h
e
D
M
d
ia
gn
os
is
m
e
t
h
od
b
as
e
d
R
F
-
BA
T
he
de
v
e
lo
pm
e
nt
of
th
e
a
lg
or
it
hm
f
or
th
e
R
F
-
B
A
ba
s
e
d
on
th
e
D
M
di
a
gno
s
is
a
ppr
oa
c
h
w
il
l
be
di
s
c
us
s
e
d
in
th
is
pa
r
t.
T
h
e
R
F
hype
r
pa
r
a
m
e
te
r
s
a
r
e
opt
im
iz
e
d
to
c
r
e
a
te
th
e
R
F
-
B
A
b
a
s
e
d
on
th
e
D
M
di
a
gnos
is
m
e
th
od
.
R
F
is
de
vi
s
e
d
by
B
r
e
im
a
n
a
nd
C
ut
le
r
.
F
ir
s
t,
th
e
w
a
y
of
R
F
w
or
ks
w
il
l
be
de
s
c
r
ib
e
d
he
r
e
.
T
he
w
or
ki
ngs
of
th
e
R
F
to
s
ol
v
e
c
la
s
s
if
ic
a
ti
on
pr
obl
e
m
s
c
a
n
be
s
e
e
n
in
F
ig
ur
e
1.
T
h
e
R
F
is
m
a
d
e
up
of
m
ul
ti
pl
e
de
c
is
io
n
tr
e
e
s
th
a
t
w
e
r
e
c
ons
tr
uc
te
d
w
it
h
r
a
ndom
ve
c
to
r
s
.
T
he
R
F
a
lg
or
it
hm
c
a
n
be
e
xpr
e
s
s
e
d
s
im
pl
y
a
s
f
ol
lo
w
s
:
le
t
u
s
a
s
s
um
e
th
a
t
th
e
tr
a
in
in
g
da
ta
s
e
t
c
om
pr
is
e
s
p
pr
e
di
c
to
r
va
r
ia
bl
e
s
a
nd
h
a
s
a
s
iz
e
of
n
obs
e
r
va
ti
ons
.
T
he
s
te
p
s
in
vol
ve
d
in
R
F
e
s
ti
m
a
ti
on
a
nd
pr
e
pa
r
a
ti
on
a
r
e
[
4
6]
:
i)
th
e
boot
s
tr
a
p
s
ta
ge
is
to
dr
a
w
r
a
ndom
s
a
m
pl
e
s
of
s
i
z
e
n
f
r
om
h
tr
a
in
in
g
da
ta
;
ii
)
ut
il
iz
in
g
a
b
oot
s
tr
a
p
da
ta
s
e
t,
th
e
tr
e
e
is
c
on
s
tr
uc
te
d
unt
il
it
a
c
hi
e
ve
s
it
s
opt
im
um
s
iz
e
(
w
it
hout
pr
uni
ng)
in
th
e
r
a
ndom
s
ub
-
s
e
tt
in
g
s
te
p.
T
h
e
s
or
te
r
is
s
e
le
c
te
d
a
t
e
a
c
h
node
by
s
e
le
c
ti
ng
m
pr
e
di
c
ti
ve
va
r
ia
bl
e
s
a
t
r
a
ndom,
w
he
r
e
m
<
p
.
T
he
be
s
t
s
or
te
r
is
th
e
n
s
e
le
c
te
d
ba
s
e
d
on
th
e
m
pr
e
di
c
to
r
va
r
ia
bl
e
s
;
ii
i)
to
c
r
e
a
te
a
f
or
e
s
t
m
a
de
up
of
k
R
F
,
r
e
pe
a
t
th
e
pr
oc
e
dur
e
1
-
3
k
ti
m
e
s
;
iv
)
vot
in
g
s
ta
ge
s
:
t
he
vot
in
g
s
ta
ge
is
c
a
r
r
ie
d
out
f
or
e
a
c
h
pr
e
di
c
ti
on
r
e
s
ul
t,
f
or
c
la
s
s
if
ic
a
ti
on
pr
obl
e
m
s
th
e
m
ode
w
il
l
be
us
e
d,
a
nd
f
or
r
e
gr
e
s
s
io
n
pr
obl
e
m
s
th
e
m
e
a
n
w
il
l
be
us
e
d
;
a
nd
v)
th
e
f
in
a
l
s
te
p
is
th
a
t
th
e
a
lg
or
it
hm
w
il
l
s
e
le
c
t
th
e
m
os
t
f
r
e
que
nt
ly
s
e
le
c
te
d pr
e
di
c
ti
on r
e
s
ul
ts
a
s
t
he
f
in
a
l
pr
e
di
c
ti
on.
I
n
th
is
w
or
k,
th
e
s
e
tt
in
gs
in
th
e
R
F
a
r
e
opt
im
iz
e
d
us
in
g
B
A
. R
F
pe
r
f
or
m
a
nc
e
is
e
nha
nc
e
d
by
pr
e
c
is
e
s
e
tt
in
gs
.
T
he
f
lo
w
c
ha
r
t
f
or
th
e
D
M
di
a
gnos
is
m
e
th
od
ba
s
e
d
RF
-
B
A
is
di
s
pl
a
ye
d
in
F
ig
ur
e
2.
T
he
r
e
a
r
e
s
e
ve
r
a
l
pha
s
e
s
in
th
e
s
ugge
s
te
d
m
e
th
od.
I
n
th
e
in
it
ia
l
s
te
p,
th
e
da
ta
s
e
t
is
e
nt
e
r
e
d
a
nd
di
vi
de
d
in
to
da
ta
f
or
tr
a
in
in
g a
nd t
e
s
ti
ng. Additi
ona
ll
y, t
he
pa
r
a
m
e
te
r
s
of
B
A
a
ls
o s
h
oul
d be
e
nt
e
r
e
d, s
uc
h a
s
numb
e
r
of
ba
t
(
N
bat
)
,
th
e
m
a
xi
m
um
num
be
r
i
te
r
a
ti
on
(
t
m
a
x
)
, l
oudne
s
s
of
ba
t
(
A
)
,
pul
s
e
r
at
e
(
r
0
)
,
,
,
m
a
xi
m
um
f
r
e
que
nc
y (
f
m
a
x
)
a
nd
m
in
im
um
f
r
e
que
nc
y (
f
min
).
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
r
ti
f
I
nt
e
ll
I
S
S
N
:
2252
-
8938
D
ia
be
te
s
m
e
ll
it
us
di
agnos
i
s
m
e
th
od bas
e
d r
andom fo
r
e
s
t
w
it
h b
at
al
gor
it
hm
(
Sy
ai
fu
l
A
nam
)
1143
F
ig
ur
e
1. I
ll
us
tr
a
ti
on of
R
F
F
ig
ur
e
2. F
lo
w
c
ha
r
t
of
R
F
-
BA
S
tart
In
p
u
t
Da
taSet,
BA P
a
ra
m
e
ters
(Nb
a
t,
f
i
,
A
i,
r
i
, A
i
)
G
e
n
e
r
a
tes
th
e
lo
c
a
ti
o
n
a
n
d
v
e
lo
c
i
t
y
o
f
th
e
b
a
ts r
a
n
d
o
m
ly
.
Term
in
a
ti
o
n
Ch
e
c
k
Ou
tp
u
t
RF
C
M
o
d
e
l
wit
h
Op
ti
m
a
l
Hy
p
e
r
p
a
ra
m
e
ters
No
En
d
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8938
I
nt
J
A
r
ti
f
I
nt
e
ll
,
V
ol
. 14, No. 2, A
pr
il
202
5
:
1
140
-
1
149
1144
A
s
a
r
e
s
ul
t,
ba
t
pos
it
io
ns
a
nd ve
lo
c
it
ie
s
a
r
e
de
te
r
m
in
e
d a
t
r
a
ndo
m
. E
a
c
h ba
t'
s
pos
it
io
n de
te
r
m
in
e
s
t
he
R
F
hype
r
pa
r
a
m
e
te
r
.
T
he
R
F
pa
r
a
m
e
te
r
s
a
r
e
m
in
im
a
l
s
a
m
pl
e
s
pl
it
(
m
ax
_de
pt
h
)
,
m
a
xi
m
um
de
pt
h
(
m
ax
_f
e
at
)
,
m
in
im
um
s
a
m
pl
e
s
pl
it
le
a
f
(
m
ax
_Sam_Split
)
,
a
nd
th
e
num
be
r
of
e
s
ti
m
a
to
r
s
(
n_e
s
t
)
.
T
he
num
be
r
of
tr
e
e
s
in
R
F
de
f
in
e
s
th
e
num
be
r
of
e
s
ti
m
a
to
r
s
.
T
h
e
to
ta
l
num
b
e
r
of
node
s
on
th
e
lo
nge
s
t
pa
th
f
r
om
th
e
r
oot
node
to
th
e
le
a
f
node
is
known
a
s
th
e
m
a
xi
m
um
de
pt
h.
T
he
ba
r
e
m
in
im
um
of
s
a
m
pl
e
s
ne
e
de
d
to
s
pl
it
a
n
in
te
r
na
l
node
is
known
a
s
th
e
m
in
im
a
l
s
a
m
pl
e
s
s
pl
it
.
T
he
m
in
im
a
l
num
be
r
of
s
a
m
pl
e
s
ne
e
de
d
a
t
a
le
a
f
node
is
known
a
s
th
e
m
in
im
um
s
a
m
pl
e
s
pl
it
l
e
a
f
. T
he
ba
t'
s
po
s
it
io
n i
s
s
p
e
c
if
ie
d i
n (
1)
.
=
(
,
1
,
,
2
,
…
,
,
4
)
,
=
1
,
.
.
.
,
(
1)
T
he
num
be
r
of
pa
r
ti
c
le
s
is
de
f
in
e
d
by
N
bat
.
T
he
i
-
th
ba
t,
de
not
e
d
by
,
is
th
e
R
F
pa
r
a
m
e
te
r
c
a
ndi
da
te
.
T
he
num
be
r
of
e
s
ti
m
a
to
r
s
is
r
e
pr
e
s
e
nt
e
d
by
x
i
,
1
,
th
e
m
a
xi
m
um
de
pt
h
by
x
i
,
2
,
th
e
m
in
im
a
l
s
a
m
pl
e
s
pl
it
by
x
i
,
3
,
a
nd
th
e
m
in
im
um
s
a
m
pl
e
s
pl
it
le
a
f
by
x
i
,
4
.
E
ve
r
y
pa
r
a
m
e
te
r
ha
s
a
r
a
nge
of
di
f
f
e
r
e
nc
e
s
.
T
he
f
ol
lo
w
in
g
s
e
c
ti
on
w
il
l
pr
ov
id
e
a
de
s
c
r
ip
ti
on
o
f
th
e
r
a
nge
o
f
pa
r
a
m
e
te
r
s
.
T
he
f
ol
lo
w
in
g
s
ta
ge
is
a
dj
us
ti
ng
e
a
c
h ba
t'
s
f
r
e
que
nc
y va
lu
e
us
in
g (
2)
.
=
+
(
−
)
(
2)
F
ol
lo
w
in
g
e
a
c
h
ba
t'
s
f
r
e
que
nc
y
a
dj
u
s
tm
e
nt
,
th
e
ba
ts
'
po
s
it
io
n
a
nd
ve
lo
c
it
y
a
r
e
upda
te
d,
a
nd
n
e
w
s
ol
ut
io
ns
a
r
e
pr
oduc
e
d us
in
g (
3)
, (
4)
, a
nd (
5)
,
r
e
s
pe
c
ti
ve
ly
.
+
1
=
+
(
−
∗
)
(
3)
+
1
=
+
+
1
(
4)
A
num
be
r
a
t
r
a
ndom
w
it
h
a
uni
f
or
m
di
s
tr
ib
ut
io
n
(
0
,
1
)
is
ut
il
iz
e
d
to
pr
oduc
e
th
e
opt
im
a
l
s
ol
ut
io
ns
.
U
s
in
g
th
e
f
it
ne
s
s
f
unc
ti
on
in
P
s
e
udo
c
ode
1,
th
e
opt
im
a
l
s
ol
ut
io
n
de
te
r
m
in
e
s
e
a
c
h
ba
t'
s
f
it
ne
s
s
va
lu
e
.
I
f
(
<
)
, t
he
n (
5)
ge
ne
r
a
te
s
t
he
l
oc
a
l
s
ol
ut
io
ns
a
t
r
a
ndom.
=
+
(
)
(
5)
(
)
is
th
e
m
e
a
n
of
ba
t
lo
udne
s
s
ove
r
ti
m
e
,
is
th
e
s
c
a
li
ng
f
a
c
to
r
,
a
nd
di
s
pl
a
ys
r
a
ndom
va
lu
e
s
obt
a
in
e
d
f
r
om
a
di
s
tr
ib
ut
io
n
th
a
t
is
nor
m
a
l
th
a
t
ha
s
th
e
G
a
us
s
ia
n
s
h
a
pe
(
0
,
1
)
.
is
e
qua
l
to
0
.
01
w
hi
c
h
c
oul
d
pos
s
ib
ly
be
us
e
d f
or
pr
a
c
ti
c
a
li
ty
.
P
s
e
udoc
ode
1. F
it
ne
s
s
f
unc
ti
on
F
u
n
c
t
i
o
n
f
i
t
n
e
s
s
(
x
,
X
_
t
r
a
i
n
i
n
g
,
y
_
t
r
a
i
n
i
n
g
,
X
_
t
e
s
t
i
n
g
,
y
_
t
e
s
t
i
n
g
)
_
=x[1]
_
=x[2]
_
ℎ
= x[3]
_
_
= x[4]
r
f
c
=
R
F
C
l
a
s
s
i
f
i
e
r
(
n
_
e
s
t
,
m
a
x
_
f
e
a
t
,
m
a
x
_
d
e
p
t
h
,
m
a
x
_
s
a
m
_
s
p
l
i
t
)
r
f
c
.
f
i
t
(
X
_
t
r
a
i
n
i
n
g
,
y
_
t
r
a
i
n
i
n
g
)
y
_
p
r
e
d
i
c
t
i
o
n
=
r
f
_
c
l
a
s
s
i
f
i
e
r
.
p
r
e
d
i
c
t
(
X
_
t
e
s
t
i
n
g
)
f
1
=
f
1
_
s
c
o
r
e
(
y
_
t
e
s
t
i
n
g
,
y
_
p
r
e
d
i
c
t
i
o
n
)
fit=1
-
f
1
r
e
t
u
r
n
f
i
t
T
he
ne
xt
s
te
ps
a
r
e
a
c
he
c
ki
ng
of
a
c
c
e
pt
a
nc
e
of
ne
w
s
ol
ut
io
n,
in
c
r
e
a
s
in
g
a
nd
r
e
duc
in
g
.
If
(
>
a
nd
(
)
<
ℱ
(
∗
)
)
th
e
n t
he
c
ur
r
e
nt
s
ol
ut
io
n ne
e
ds
t
o be
upda
t
e
d us
in
g t
he
s
ol
ut
io
ns
f
ound by
us
in
g (
5)
a
nd (
6)
,
is
i
nc
r
e
a
s
e
d a
nd
is
r
e
duc
e
d.
+
1
=
,
(
6)
+
1
=
0
[
1
−
e
x
p
(
−
)
]
,
(
7)
T
he
r
a
nge
of
α
is
0<
α<
1,
w
he
r
e
a
s
γ
>
0.
I
ts
va
lu
e
is
α,
a
nd
γ
c
oul
d
be
a
dj
us
te
d
w
it
h
α=
γ
=
0.9
to
f
a
c
il
it
a
te
th
e
s
e
a
r
c
h
pr
oc
e
s
s
.
A
c
c
or
di
ng
to
Y
a
ng
[
39]
,
th
e
pr
oc
e
dur
e
f
or
s
e
a
r
c
hi
ng
c
oul
d
be
m
a
de
s
im
pl
e
r
by
us
in
g
a
nd
to
de
not
e
th
e
va
lu
e
s
of
1
a
nd
1,
w
it
h
α=
γ
=
0.9.
T
he
ba
ts
a
r
e
s
or
te
d
in
th
e
f
in
a
l
s
ta
ge
to
obt
a
i
n
th
e
be
s
t
s
ol
ut
io
n
(
∗
)
.
I
f
one
of
th
e
te
r
m
in
a
ti
on
c
ondi
ti
ons
,
th
e
m
a
xi
m
um
num
be
r
of
it
e
r
a
ti
ons
or
th
e
f
it
ne
s
s
im
pr
ove
m
e
nt
,
is
s
a
ti
s
f
ie
d,
th
e
pr
opos
e
d
m
e
th
od'
s
pr
ogr
a
m
w
il
l
be
te
r
m
in
a
te
d.
A
pr
e
s
um
pt
io
n
is
m
a
de
.
W
he
n
th
e
gl
oba
l
be
s
t'
s
f
it
ne
s
s
doe
s
not
in
c
r
e
a
s
e
a
f
te
r
20
r
ounds
,
th
e
gl
oba
l
opt
im
a
l
poi
nt
ha
s
b
e
e
n
id
e
nt
if
ie
d.
A
f
te
r
B
A
de
te
r
m
in
e
s
th
e
R
F
pa
r
a
m
e
te
r
s
,
th
e
c
la
s
s
if
ic
a
ti
on
m
ode
l
is
ut
il
iz
e
d.
T
he
lo
opi
ng
pr
oc
e
s
s
w
il
l
be
s
to
ppe
d
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
r
ti
f
I
nt
e
ll
I
S
S
N
:
2252
-
8938
D
ia
be
te
s
m
e
ll
it
us
di
agnos
i
s
m
e
th
od bas
e
d r
andom fo
r
e
s
t
w
it
h b
at
al
gor
it
hm
(
Sy
ai
fu
l
A
nam
)
1145
a
nd
th
e
pr
ogr
a
m
'
s
out
put
w
il
l
be
s
a
ve
d
if
th
e
te
r
m
in
a
ti
on
c
ondi
ti
on
is
s
a
ti
s
f
ie
d.
T
he
R
F
m
ode
l
w
it
h
th
e
a
ppr
opr
ia
te
pa
r
a
m
e
te
r
s
is
th
e
r
e
s
ul
t
of
th
is
pr
oc
e
s
s
.
E
va
lu
a
ti
on
of
c
la
s
s
if
ic
a
ti
on
m
ode
ls
f
or
D
M
di
a
gno
s
is
us
in
g
R
F
-
B
A
on
tr
a
in
in
g
da
ta
a
s
s
how
n
in
A
lg
or
it
hm
1
a
nd
e
va
lu
a
ti
on
of
c
la
s
s
if
ic
a
ti
on
m
ode
l
s
f
or
D
M
di
a
gnos
is
us
in
g
R
F
-
B
A
on t
e
s
ti
ng da
ta
a
s
s
how
n i
n A
lg
or
it
hm
2.
A
lg
or
it
hm
1. E
va
lu
a
ti
on of
a
c
la
s
s
if
ic
a
ti
on mode
l
f
or
D
M
di
a
gnos
is
us
in
g R
F
-
B
A
on t
r
a
in
in
g da
ta
.
I
n
p
u
t
:
t
h
e
t
r
a
i
n
i
n
g
d
a
t
a
(
X
train
)
w
i
t
h
s
i
z
e
o
f
n
×
m
,
h
y
p
e
r
p
a
r
a
m
e
t
e
r
s
o
f
R
F
,
y
train
(
T
r
a
i
n
i
n
g
d
a
t
a
s
e
t
'
s
c
l
a
s
s
l
a
b
e
l
)
O
u
t
p
u
t
:
a
c
c
u
r
a
c
y
,
r
e
c
a
l
l
,
p
r
e
c
i
s
i
o
n
,
f
1
s
c
o
r
e
.
1.
T
r
a
i
n
R
F
M
o
d
e
l
u
s
i
n
g
t
r
a
i
n
i
n
g
d
a
t
a
.
2.
C
o
m
p
u
t
e
t
h
e
l
a
b
e
l
p
r
e
d
i
c
t
i
o
n
y
pred
b
a
s
e
d
o
n
R
F
-
BA.
3.
C
o
m
p
u
t
e
A
c
c
u
r
a
c
y
,
R
e
c
a
l
l
,
P
r
e
c
i
s
i
o
n
a
n
d
f
1
S
c
o
r
e
.
A
lg
or
it
hm
2. E
va
lu
a
ti
on of
a
c
la
s
s
if
ic
a
ti
on mode
l
f
or
D
M
di
a
gnos
is
us
in
g R
F
-
B
A
on t
e
s
ti
ng da
ta
.
I
n
p
u
t
:
t
h
e
t
e
s
t
i
n
g
d
a
t
a
,
R
F
m
o
d
e
l
,
y
testing
(
e
a
c
h
t
e
s
t
i
n
g
d
a
t
a
'
s
c
l
a
s
s
l
a
b
e
l
s
)
O
u
t
p
u
t
:
a
c
c
u
r
a
c
y
,
r
e
c
a
l
l
,
p
r
e
c
i
s
i
o
n
,
f
1
s
c
o
r
e
.
1.
C
o
m
p
u
t
e
t
h
e
l
a
b
e
l
p
r
e
d
i
c
t
i
o
n
y
pred
b
a
s
e
d
o
n
R
F
-
BA.
2.
C
o
m
p
u
t
e
A
c
c
u
r
a
c
y
,
R
e
c
a
l
l
,
P
r
e
c
i
s
i
o
n
a
n
d
f
1
S
c
o
r
e
.
2.4.
S
e
t
t
in
g t
h
e
p
ar
am
e
t
e
r
s
o
f
t
h
e
p
r
op
os
e
d
m
e
t
h
od
T
he
f
ol
lo
w
in
g
li
s
ts
th
e
r
a
ng
e
of
R
F
pa
r
a
m
e
te
r
s
th
a
t
a
r
e
pe
r
m
it
te
d
in
th
is
s
tu
dy:
T
he
m
a
xi
m
um
de
pt
h
is
[
1,10]
,
th
e
lo
w
e
s
t
s
a
m
pl
e
s
pl
it
is
[
1,20]
,
th
e
m
in
im
um
s
a
m
pl
e
s
pl
it
le
a
f
is
[
1,20
]
,
a
nd
th
e
num
be
r
o
f
e
s
ti
m
a
to
r
s
is
[
10,100]
.
T
he
s
e
pa
r
a
m
e
te
r
s
a
r
e
de
r
iv
e
d
f
r
o
m
e
a
r
li
e
r
s
tu
di
e
s
[
20]
.
B
a
t
lo
udne
s
s
(
A
)
,
m
a
xi
m
um
it
e
r
a
ti
on
(
t
m
a
x
)
,
num
be
r
of
ba
ts
(
N
bat
)
,
pu
ls
e
r
a
te
(
r
0
)
,
,
,
m
a
xi
m
um
f
r
e
que
nc
y
(
f
m
a
x
)
,
a
nd
m
in
im
um
f
r
e
que
nc
y
(
f
min
)
a
r
e
a
m
ong
th
e
B
A
c
ha
r
a
c
te
r
is
ti
c
s
t
ha
t
a
r
e
e
m
pl
oye
d.
T
h
e
B
A
u
s
e
d'
s
pa
r
a
m
e
te
r
s
e
tt
in
gs
a
r
e
a
s
f
ol
lo
w
s
:
f
min
=
0,
f
m
a
x
=
2,
N
bat
=
100,
t
m
a
x
=
500,
A
=
1,
r
0
=
1,
=
0.97, a
nd
=
0.1.
2.5.
E
val
u
at
in
g t
h
e
p
r
op
os
e
d
m
e
t
h
od
T
h
e
m
e
tr
ic
s
a
s
s
e
s
s
m
e
n
t
m
u
s
t
b
e
c
om
put
e
d
to
e
v
a
l
ua
te
th
e
c
la
s
s
if
ic
a
t
io
n
m
o
de
l
.
T
h
e
R
F
-
B
A
hyp
e
r
p
a
r
a
m
e
t
e
r
s
o
pt
i
m
i
z
a
t
io
n
i
s
u
s
e
d
to
bui
ld
th
e
c
l
a
s
s
if
i
c
a
ti
o
n
m
od
e
l.
C
on
s
e
q
ue
nt
l
y,
th
e
m
od
e
l
i
s
a
s
s
e
s
s
e
d
us
in
g
th
e
t
e
s
t
in
g
d
a
t
a
.
T
h
e
a
c
c
ur
a
c
y,
r
e
c
a
ll
, pr
e
c
i
s
i
on
, a
nd
f
1
s
c
or
e
of
t
he
tr
a
in
in
g
a
nd t
e
s
ti
n
g
d
a
t
a
a
r
e
c
a
lc
ul
a
t
e
d
to
e
v
a
lu
a
t
e
th
e
c
l
a
s
s
if
i
c
a
ti
o
n m
od
e
l'
s
e
f
f
ic
a
c
y.
T
h
e
f
ol
l
ow
in
g
i
s
a
de
s
c
r
ip
ti
o
n o
f
e
a
c
h
e
va
lu
a
ti
on
m
e
tr
i
c
.
‒
In
(
8)
i
s
us
e
d t
o c
a
lc
ul
a
te
t
he
a
c
c
ur
a
c
y.
=
+
+
+
+
(
8)
P
os
it
iv
e
da
ta
th
a
t
is
c
or
r
e
c
tl
y
in
te
r
pr
e
te
d
is
r
e
f
e
r
r
e
d
to
a
s
a
t
r
ue
pos
it
iv
e
(
T
P
)
.
T
r
ue
ne
ga
ti
ve
(
T
N
)
is
th
e
qua
nt
it
y of
t
up
le
s
c
or
r
e
c
tl
y c
la
s
s
if
ie
d a
s
ne
ga
ti
ve
. T
he
a
m
ount
of
e
r
r
one
ous
ly
i
de
nt
i
f
ie
d t
upl
e
s
i
n
th
e
ne
ga
ti
ve
c
la
s
s
i
s
known a
s
f
a
l
s
e
pos
it
iv
e
s
(
F
P
)
. F
a
ls
e
ne
ga
ti
ve
(
F
N
)
r
e
f
e
r
s
t
o t
he
qua
nt
it
y of
t
upl
e
s
t
ha
t
a
r
e
c
la
s
s
if
ie
d a
s
ne
ga
ti
ve
. T
he
r
a
ti
o of
a
c
c
ur
a
te
pr
e
di
c
ti
ons
t
o t
ot
a
l
tu
pl
e
s
i
s
kno
w
n a
s
a
c
c
ur
a
c
y.
‒
In
(
9)
i
ndi
c
a
te
s
r
e
c
a
ll
t
ha
t
is
us
e
d t
o m
e
a
s
ur
e
t
he
pr
opor
ti
on of
c
or
r
e
c
tl
y r
e
c
ogni
z
e
d pos
it
iv
e
pa
tt
e
r
ns
.
R
e
c
a
l
l
=
TP
TP
+
FN
(
9)
‒
T
he
de
f
in
it
io
n
of
pr
e
c
is
io
n
is
gi
ve
n
by
(
10)
.
I
t
is
c
om
put
e
d
a
s
th
e
r
a
ti
o
of
a
ll
th
e
tu
pl
e
s
in
th
e
pos
it
iv
e
c
a
te
gor
y t
o t
he
c
or
r
e
c
tl
y pr
e
di
c
te
d pos
it
iv
e
c
la
s
s
.
P
r
e
c
is
io
n
=
TP
TP
+
FP
(
10)
‒
In
(
11)
is
ut
il
iz
e
d
to
c
om
put
e
th
e
f
1
s
c
or
e
.
I
t
is
c
om
put
e
d
by
us
in
g
th
e
ha
r
m
oni
c
m
e
a
n
of
r
e
c
a
ll
a
nd
pr
e
c
is
io
n.
1
=
2
×
∙
+
(
11)
3.
R
E
S
U
L
T
S
A
N
D
D
I
S
C
U
S
S
I
O
N
T
he
a
c
c
ur
a
c
y,
pr
e
c
i
s
io
n,
r
e
c
a
ll
,
a
nd
f
1
s
c
or
e
a
r
e
us
e
d
to
a
s
s
e
s
s
th
e
pr
opos
e
d
a
ppr
oa
c
h.
T
he
da
ta
s
e
t
s
houl
d
be
e
xa
m
in
e
d
f
or
m
is
s
in
g
va
lu
e
s
a
s
th
e
in
it
ia
l
s
te
p.
T
he
f
in
di
ngs
in
di
c
a
te
th
a
t
th
e
r
e
a
r
e
no
m
is
s
in
g
va
lu
e
s
in
th
e
d
a
ta
s
e
t.
T
h
e
m
in
-
m
a
x
nor
m
a
li
z
a
ti
on a
ppr
oa
c
h
i
s
t
he
n
us
e
d
to
c
onve
r
t
th
e
d
a
ta
s
e
t.
A
ll
of
th
e
da
ta
ha
s
th
e
s
a
m
e
r
a
nge
[
0,1]
,
a
c
c
or
di
ng
to
th
e
nor
m
a
li
z
a
ti
on
r
e
s
ul
t
s
.
T
h
e
goa
l
of
th
is
pr
oc
e
s
s
is
to
m
a
ke
th
e
R
F
a
ppr
oa
c
h
m
or
e
e
f
f
e
c
ti
ve
.
A
s
a
r
e
s
ul
t,
th
e
da
ta
s
e
t
is
s
e
pa
r
a
te
d
in
to
tr
a
in
in
g
a
nd
te
s
ti
ng
da
ta
s
ubs
e
ts
.
T
he
pe
r
c
e
nt
a
ge
s
of
te
s
ti
ng
a
nd
tr
a
in
in
g
da
ta
a
r
e
30
a
nd
70%
,
a
c
c
or
di
ngl
y
T
a
bl
e
s
1
to
4
s
how
th
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8938
I
nt
J
A
r
ti
f
I
nt
e
ll
,
V
ol
. 14, No. 2, A
pr
il
202
5
:
1
140
-
1
149
1146
e
f
f
e
c
ti
ve
ne
s
s
of
th
e
R
F
-
PSO
-
ba
s
e
d
a
nd
R
F
-
BA
-
ba
s
e
d
D
M
di
a
gnos
is
te
c
hni
que
s
.
T
he
a
ve
r
a
ge
pe
r
f
or
m
a
nc
e
m
e
tr
ic
s
of
R
F
,
P
S
O
-
R
F
,
a
nd
B
A
-
R
F
to
di
a
gnos
e
D
M
f
or
da
ta
tr
a
in
in
g
a
nd
te
s
ti
ng
a
r
e
di
s
pl
a
ye
d
in
T
a
bl
e
s
1
a
nd
3,
r
e
s
pe
c
ti
ve
ly
.
T
he
e
xpe
r
im
e
nt
us
e
s
s
e
ve
r
a
l
t
he
num
be
r
of
ba
ts
w
hi
c
h
a
r
e
5,
10,
20
,
a
nd
50
ba
ts
.
R
F
-
B
A
5
m
e
a
ns
th
a
t
B
A
us
e
s
5
ba
ts
,
a
nd
R
F
-
B
A
5
m
e
a
ns
th
a
t
B
A
us
e
s
10
ba
ts
.
T
he
R
F
-
B
A
pr
oduc
e
d
r
e
s
ul
ts
f
or
a
c
c
ur
a
c
y,
pr
e
c
is
io
n,
r
e
c
a
ll
,
a
nd
f
1
s
c
o
r
e
of
0.7861,
0.7668,
0.8315,
a
nd
0.7978
,
r
e
s
pe
c
ti
ve
ly
,
w
he
r
e
a
s
th
e
R
F
-
P
S
O
pr
oduc
e
d
r
e
s
ul
ts
f
or
a
c
c
ur
a
c
y,
pr
e
c
is
io
n,
r
e
c
a
ll
,
a
nd
f
1
s
c
or
e
of
0.7516,
0.7346,
0.7738,
a
nd
0.7536.
T
he
tr
a
di
ti
ona
l
R
F
f
or
tr
a
in
in
g
da
ta
yi
e
ld
e
d
th
e
f
ol
lo
w
in
g
r
e
s
ul
ts
a
c
c
ur
a
c
y,
pr
e
c
is
io
n, r
e
c
a
ll
,
a
nd f
1
s
c
or
e
:
0.9953, 0.9942, 0.9964, a
nd 0.99
52, r
e
s
pe
c
ti
ve
ly
.
T
a
bl
e
1.
T
he
pe
r
f
or
m
a
nc
e
m
e
tr
ic
s
a
ve
r
a
g
e
f
or
D
M
di
a
gnos
is
u
s
in
g R
F
, R
F
-
P
S
O
, a
nd R
F
-
B
A
(
tr
a
in
in
g da
ta
)
M
e
t
hods
t
A
c
c
ur
a
c
y
P
r
e
c
i
s
i
on
R
e
c
a
l
l
f
1
S
c
or
e
C
om
put
a
t
i
ona
l
t
ime
F
i
t
ne
s
s
RF
-
B
A
5
50
0.7894
0.7688
0.8370
0.8014
16.2429
0.2275
RF
-
B
A
10
50
0.7807
0.7611
0.8275
0.7929
16.2546
0.2265
RF
-
B
A
20
60
0.7879
0.7699
0.8298
0.7987
20.0742
0.2277
RF
-
B
A
50
50
0.7865
0.7672
0.8317
0.7981
15.8187
0.2268
RF
-
BA
52.5
0.7861
0.7668
0.8315
0.7978
17.0976
0.2271
RF
-
P
S
O
5
28.12
0.7521
0.7356
0.7719
0.7533
49.0971
0.2259
RF
-
P
S
O
10
46.44
0.7475
0.7314
0.7664
0.7485
179.6955
0.2277
RF
-
P
S
O
20
41.36
0.7567
0.7383
0.7859
0.7613
918.0722
0.2315
RF
-
P
S
O
50
41.52
0.7501
0.7332
0.7709
0.7515
640.1197
0.2297
RF
-
PSO
39.36
0.7516
0.7346
0.7738
0.7536
446.7461
0.22869
RF
-
0.9953
0.9942
0.9964
0.9952
5.9194
-
T
a
b
l
e
2
.
T
h
e
p
e
r
f
or
m
a
n
c
e
m
e
t
r
i
c
s
s
t
a
n
d
a
r
d
d
e
vi
a
t
i
on
of
R
F
,
R
F
-
P
S
O
a
n
d
R
F
-
B
A
f
or
D
M
d
i
a
gn
o
s
i
s
(
t
r
a
i
n
i
n
g
d
a
t
a
)
M
e
t
hods
t
A
c
c
ur
a
c
y
P
r
e
c
i
s
i
on
R
e
c
a
l
l
f
1
S
c
or
e
C
om
put
a
t
i
ona
l
t
ime
F
i
t
ne
s
s
RF
-
B
A
5
0.0000
0.0396
0.0384
0.0356
0.0365
6.1681
0.0118
RF
-
B
A
10
0.0000
0.0185
0.0189
0.0169
0.0167
5.5662
0.0081
RF
-
B
A
20
0.0000
0.0253
0.0235
0.0256
0.0240
8.1078
0.0098
RF
-
B
A
50
0.0000
0.0324
0.0319
0.0279
0.0295
4.0908
0.0092
RF
-
BA
0
0.02895
0.02818
0.0265
0.02668
5.98323
0.0097
RF
-
P
S
O
5
7.6829
0.0074
0.0068
0.0100
0.0079
23.4423
0.0098
RF
-
P
S
O
10
11.2475
0.0087
0.0069
0.0140
0.0098
80.6586
0.0102
RF
-
P
S
O
20
10.0825
0.0120
0.0101
0.0234
0.0156
905.5180
0.0099
RF
-
P
S
O
50
10.6031
0.0151
0.0129
0.0201
0.0158
310.5717
0.0144
RF
-
PSO
9.904
0.0108
0.009175
0.016875
0.012275
330.0476
0.0110
RF
0
1.744
10
-
5
0.000184
0.00018
1.735
10
-
5
0.11033
-
T
a
bl
e
3.
T
he
pe
r
f
or
m
a
nc
e
m
e
tr
ic
s
a
ve
r
a
g
e
of
R
F
, R
F
-
P
S
O
a
nd R
F
-
B
A
f
or
D
M
di
a
gnos
is
(
te
s
ti
ng da
ta
)
M
e
t
hods
A
c
c
ur
a
c
y
P
r
e
c
i
s
i
on
R
e
c
a
l
l
f
1
s
c
or
e
RF
-
B
A
5
0.7686
0.7688
0.7796
0.7740
RF
-
B
A
10
0.7666
0.7685
0.7742
0.7713
RF
-
B
A
20
0.7688
0.7717
0.7747
0.7730
RF
-
B
A
50
0.7679
0.7724
0.7707
0.7715
RF
-
BA
0.7680
0.7703
0.7748
0.7725
RF
-
P
S
O
5
0.7695
0.7718
0.7683
0.7717
RF
-
P
S
O
10
0.7689
0.7711
0.7664
0.7710
RF
-
P
S
O
20
0.7642
0.7668
0.7715
0.7663
RF
-
P
S
O
50
0.7708
0.7731
0.7698
0.7730
RF
-
PSO
0.7684
0.7707
0.7690
0.7705
RF
0.7371
0.7181
0.7783
0.7470
T
a
b
l
e
4
.
T
h
e
p
e
r
f
or
m
a
n
c
e
m
e
t
r
i
c
s
s
t
a
n
d
a
r
d
d
e
vi
a
t
i
on
of
R
F
,
R
F
-
P
S
O
,
a
n
d
R
F
-
B
A
f
or
D
M
di
a
g
n
o
s
i
s
(
t
e
s
t
i
ng
d
a
t
a
)
M
e
t
hods
A
c
c
ur
a
c
y
P
r
e
c
i
s
i
on
R
e
c
a
l
l
f
1
s
c
or
e
RF
-
B
A
5
0.0089
0.0106
0.01349
0.0087
RF
-
B
A
10
0.0070
0.0090
0.01311
0.0073
RF
-
B
A
20
0.0076
0.0089
0.01556
0.0085
RF
-
B
A
50
0.0085
0.0069
0.01600
0.0098
RF
-
BA
0.0080
0.0089
0.01454
0.0086
RF
-
P
S
O
5
0.0100
0.0113
0.01542
0.0102
RF
-
P
S
O
10
0.0083
0.0080
0.01154
0.0085
RF
-
P
S
O
20
0.0070
0.0071
0.01266
0.0077
RF
-
P
S
O
50
0.0152
0.0261
0.02838
0.0162
RF
-
PSO
0.0101
0.01314
0.01700
0.0106
RF
0.0014
0.00156
0.00198
0.00134
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
r
ti
f
I
nt
e
ll
I
S
S
N
:
2252
-
8938
D
ia
be
te
s
m
e
ll
it
us
di
agnos
i
s
m
e
th
od bas
e
d r
andom fo
r
e
s
t
w
it
h b
at
al
gor
it
hm
(
Sy
ai
fu
l
A
nam
)
1147
F
or
t
e
s
ti
ng
d
a
t
a
,
th
e
a
c
c
ur
a
c
y,
pr
e
c
is
io
n
,
r
e
c
a
ll
,
a
nd
f
1
s
c
or
e
o
bt
a
in
e
d
f
r
om
t
he
R
F
-
B
A
a
r
e
0.
768
0,
0.7
703
,
0.
77
48,
a
nd
0.7
72
5,
r
e
s
pe
c
ti
v
e
ly
.
S
im
i
la
r
ly
,
t
he
a
c
c
ur
a
c
y,
pr
e
c
is
io
n
,
r
e
c
a
ll
a
nd
f
1
s
c
or
e
ob
ta
in
e
d
f
r
o
m
th
e
R
F
-
P
S
O
a
r
e
0.
76
841
, 0.
770
7,
0
.76
90
, a
n
d 0.
770
5,
r
e
s
p
e
c
t
iv
e
ly
.
U
s
i
ng
t
he
tr
a
d
it
i
on
a
l
R
F
f
or
t
e
s
t
in
g da
ta
, t
h
e
c
or
r
e
s
po
nd
in
g
a
c
c
ur
a
c
y
, pr
e
c
i
s
i
on
,
r
e
c
a
l
l
,
a
nd
f
1
s
c
or
e
a
r
e
0.7
37
2
,
0
.7
181
, 0.
778
3,
a
nd
0
.7
470
. A
s
de
m
o
ns
tr
a
te
d
by
th
e
r
e
s
ul
ts
,
R
F
-
B
A
a
n
d
R
F
-
P
S
O
out
pe
r
f
or
m
c
o
nv
e
nt
io
na
l
R
F
a
n
d
c
a
n
r
e
s
o
lv
e
th
e
o
ve
r
f
it
t
in
g
i
s
s
ue
of
R
F
.
R
e
ga
r
di
ng
a
c
c
ur
a
c
y
,
pr
e
c
i
s
i
on
, r
e
c
a
l
l
,
a
nd f
1
s
c
or
e
,
R
F
-
B
A
a
n
d
R
F
-
P
S
O
do
no
t
di
f
f
e
r
m
uc
h
in
pe
r
f
or
m
a
n
c
e
.
T
he
e
xpe
r
im
e
nt
a
l
f
in
di
ngs
a
ls
o
de
m
ons
tr
a
te
th
a
t
th
e
P
S
O
a
nd
BA
f
unc
ti
on
id
e
nt
ic
a
ll
y
r
e
ga
r
dl
e
s
s
of
th
e
num
be
r
of
pa
r
ti
c
le
s
or
ba
ts
w
hi
c
h
is
5,
10,
20,
a
nd
50.
N
e
ve
r
th
e
le
s
s
,
R
F
-
B
A
'
s
c
om
put
a
ti
on
ti
m
e
is
s
ubs
ta
nt
ia
ll
y
qui
c
k
e
r
th
a
n R
F
-
P
S
O
'
s
.
T
he
gr
id
s
e
a
r
c
h
a
ppr
oa
c
h
t
a
ke
s
lo
nge
r
to
c
om
put
e
th
a
n
th
e
R
F
-
P
S
O
a
nd
RF
-
B
A
m
e
th
ods
.
T
he
R
F
-
P
S
O
is
to
bl
a
m
e
,
a
nd
th
e
R
F
-
B
A
do
e
s
not
ha
ve
to
e
xpe
r
im
e
nt
w
it
h
e
ve
r
y
pos
s
ib
le
c
om
bi
na
ti
on
of
R
F
hyp
e
r
pa
r
a
m
e
te
r
s
.
T
he
f
it
ne
s
s
va
lu
e
s
th
a
t
R
F
-
P
S
O
a
nd
R
F
-
B
A
pr
oduc
e
a
r
e
v
e
r
y
s
im
il
a
r
.
T
a
bl
e
s
2
a
nd
4
de
m
ons
tr
a
te
th
a
t
R
F
-
P
S
O
a
nd
R
F
-
B
A
pr
oduc
e
d
good
va
r
ia
nc
e
s
f
or
a
ll
ba
t/
pa
r
ti
c
le
c
ount
s
.
C
ons
e
que
nt
ly
,
f
iv
e
pa
r
ti
c
le
s
or
ba
ts
is
th
e
s
ugge
s
te
d
qua
nt
it
y.
G
e
ne
r
a
ll
y,
R
F
us
in
g
th
e
S
I
te
c
hni
que
(
B
A
a
nd
P
S
O
)
pe
r
f
or
m
s
f
a
r
be
tt
e
r
th
a
n
tr
a
di
ti
ona
l
R
F
.
T
o
i
nc
r
e
a
s
e
p
e
r
f
or
m
a
nc
e
,
th
e
R
F
-
B
A
m
e
th
od
of
di
a
gnos
in
g
DM
m
us
t
s
ti
ll
be
us
e
d.
O
pt
im
iz
in
g
th
e
da
ta
pr
e
p
r
oc
e
s
s
in
g
s
ta
ge
s
,
in
c
lu
di
ng
f
e
a
tu
r
e
s
e
le
c
ti
on,
c
a
n
he
lp
a
c
hi
e
ve
th
e
im
pr
ove
m
e
nt
.
P
r
oc
e
s
s
opt
im
iz
a
ti
on
on
B
A
,
s
uc
h
a
s
a
r
obus
t
popula
ti
on
in
it
ia
ti
on
to
in
c
r
e
a
s
e
t
he
gl
oba
l
opt
im
a
s
e
a
r
c
h, c
a
n
a
ls
o be
u
s
e
d t
o i
m
pr
ove
.
4.
C
O
N
C
L
U
S
I
O
N
T
he
c
onc
lu
s
io
n
dr
a
w
n
f
r
om
th
e
e
xa
m
in
a
ti
on
of
th
e
e
xpe
r
im
e
nt
a
l
r
e
s
ul
ts
is
th
e
R
F
-
B
A
is
b
e
tt
e
r
th
a
n
th
e
tr
a
di
ti
ona
l
R
F
a
nd
th
e
R
F
-
P
S
O
f
or
th
e
D
M
di
a
gnos
i
s
.
T
h
e
ove
r
-
f
it
ti
ng
s
it
ua
ti
ons
on
th
e
c
onve
nt
io
na
l
R
F
f
or
di
a
gnos
in
g
D
M
c
a
n
be
a
voi
de
d
ba
s
e
d
on
th
e
R
F
-
B
A
a
nd
R
F
-
P
S
O
.
C
om
pa
r
e
d
to
R
F
-
P
S
O
,
R
F
-
B
A
ha
s
a
f
a
s
te
r
c
om
put
a
ti
on
ti
m
e
.
C
om
pa
r
e
d
to
th
e
g
r
id
s
e
a
r
c
h
a
ppr
oa
c
h,
th
e
R
F
-
P
S
O
a
nd
R
F
-
B
A
a
ls
o
yi
e
ld
s
hor
te
r
c
om
put
a
ti
on
ti
m
e
s
.
F
or
e
ve
r
y
ba
t
or
pa
r
ti
c
le
c
ount
,
bot
h
R
F
-
P
S
O
a
nd
R
F
-
B
A
p
r
oduc
e
d
good
va
r
ia
nc
e
s
.
C
ons
e
que
nt
ly
,
it
is
a
dvi
s
e
d
th
a
t
th
e
r
e
be
f
iv
e
p
a
r
ti
c
le
s
in
e
a
c
h
ba
t.
E
ve
n
th
ough
R
F
-
B
A
ta
k
e
s
le
s
s
ti
m
e
to
c
om
put
e
th
a
n
R
F
-
P
S
O
,
a
f
a
s
te
r
B
A
pr
oc
e
dur
e
is
s
ti
ll
r
e
qui
r
e
d.
I
n
a
ddi
ti
on,
th
e
R
F
-
B
A
m
e
th
od
o
f
di
a
gnos
in
g
DM
is
s
ti
ll
ne
e
de
d.
O
pt
im
iz
in
g
th
e
da
ta
pr
e
pr
oc
e
s
s
in
g
s
ta
ge
s
,
in
c
lu
di
ng
f
e
a
tu
r
e
s
e
le
c
ti
on,
c
a
n
he
lp
it
ge
t
be
tt
e
r
.
A
ddi
ti
ona
ll
y,
th
e
B
A
pr
oc
e
s
s
s
ti
ll
ha
s
to
be
e
nha
n
c
e
d
i
n
or
de
r
to
in
c
r
e
a
s
e
th
e
w
or
ld
w
id
e
s
e
a
r
c
h
f
or
opt
im
a
l
r
e
s
ul
ts
.
T
h
e
s
ugg
e
s
te
d
a
ppr
oa
c
h
ha
s
a
c
ons
id
e
r
a
bl
e
p
ot
e
nt
ia
l
of
be
in
g
us
e
d
in
th
e
f
ut
ur
e
to
a
s
s
is
t
in
di
vi
dua
ls
w
it
h e
a
r
ly
di
a
be
te
s
di
a
gno
s
is
i
n a
f
a
s
t,
l
ow
-
c
o
s
t,
a
nd
hi
ghl
y a
c
c
ur
a
te
m
a
nne
r
.
A
C
K
N
O
WL
E
D
G
E
M
E
N
T
S
A
ll
a
ut
hor
s
w
oul
d
l
ik
e
to
s
a
y
th
e
ir
gr
a
ti
tu
de
to
th
e
M
in
is
tr
y
of
E
duc
a
ti
on,
C
ul
tu
r
e
,
R
e
s
e
a
r
c
h,
a
nd
T
e
c
hnol
ogy
of
th
e
R
e
publ
i
c
of
I
ndone
s
ia
'
s
,
D
I
K
T
I
f
or
s
uppor
t
th
e
r
e
s
e
a
r
c
h
th
r
ough
C
oope
r
a
ti
ve
R
e
s
e
a
r
c
h
G
r
a
nt
-
D
om
e
s
ti
c
2023
(
H
ib
ah
P
e
ne
li
ti
an
K
e
r
ja
s
am
a
-
D
al
am
N
e
ge
r
i
2023
)
,
unde
r
c
ont
r
a
c
t
num
be
r
199/
E
5/
P
G
.020.00.P
L
/2
023.
R
E
F
E
R
E
N
C
E
S
[
1]
S
.
F
a
t
t
a
he
i
a
n
-
D
e
hkor
di
,
R
.
H
oj
j
a
t
i
f
a
r
d,
M
.
S
a
e
e
di
,
a
nd
M
.
K
ha
n
a
vi
,
“
A
r
e
vi
e
w
on
a
nt
i
di
a
be
t
i
c
a
c
t
i
vi
t
y
of
c
e
nt
a
ur
e
a
s
pp.:
a
n
e
w
a
ppr
oa
c
h
f
or
de
ve
l
opi
ng
he
r
ba
l
r
e
m
e
di
e
s
,”
E
v
i
de
nc
e
-
B
as
e
d
C
om
pl
e
m
e
nt
ar
y
an
d
A
l
t
e
r
nat
i
v
e
M
e
di
c
i
ne
,
vol
.
2021,
pp.
1
–
23,
2021,
doi
:
10.1155/
2021/
5587938.
[
2]
A
.
M
.
H
ut
a
pe
a
a
nd
C
.
S
us
a
nt
o,
“
H
ypogl
yc
e
m
i
c
pot
e
nt
i
a
l
of
A
l
oe
ve
r
a
i
n
di
a
be
t
e
s
m
e
l
l
i
t
us
i
nduc
e
d
by
di
a
be
t
oge
ni
c
s
ub
s
t
a
nc
e
s
a
nd
hi
gh
f
a
t
di
e
t
:
A
s
ys
t
e
m
a
t
i
c
m
e
t
a
-
a
na
l
ys
i
s
r
e
vi
e
w
,”
I
nt
e
r
nat
i
onal
J
ou
r
nal
of
A
ppl
i
e
d
D
e
nt
al
Sc
i
e
nc
e
s
,
vol
.
7,
no.
3,
pp.
360
–
368, 2021, doi
:
10.22271/
or
a
l
.2021.v7.i
3f
.1322.
[
3]
K
.
P
a
pa
t
he
odor
ou,
M
.
B
a
na
c
h,
E
.
B
e
ki
a
r
i
,
M
.
R
i
z
z
o,
a
nd
M
.
E
dm
onds
,
“
C
o
m
pl
i
c
a
t
i
ons
of
di
a
be
t
e
s
2017,”
J
our
nal
of
D
i
abe
t
e
s
R
e
s
e
ar
c
h
, vol
. 2018, pp. 1
–
4, 2018, doi
:
10.1155/
2018/
3086167.
[
4]
D
.
T
om
i
c
,
J
.
E
.
S
ha
w
,
a
nd
D
.
J
.
M
a
gl
i
a
no,
“
T
he
bur
de
n
a
nd
r
i
s
ks
of
e
m
e
r
gi
ng
c
om
pl
i
c
a
t
i
ons
of
di
a
be
t
e
s
m
e
l
l
i
t
us
,”
N
at
ur
e
R
e
v
i
e
w
s
E
ndoc
r
i
nol
ogy
, vol
. 18, no. 9, pp. 525
–
539, 2022, doi
:
10.1038/
s
41574
-
022
-
00690
-
7.
[
5]
K
.
J
.
B
r
a
hm
bha
t
t
e
t
al
.
,
“
A
s
s
o
c
i
a
t
i
on
of
m
e
a
n
pl
a
t
e
l
e
t
vol
um
e
w
i
t
h
v
a
s
c
ul
a
r
c
om
pl
i
c
a
t
i
ons
i
n
t
he
p
a
t
i
e
nt
s
w
i
t
h
t
ype
2
di
a
b
e
t
e
s
m
e
l
l
i
t
us
,”
C
ur
e
u
s
, vol
. 14, no. 9, 2022, doi
:
10.7759/
c
ur
e
us
.29316.
[
6]
J
.
C
.
H
a
r
t
z
,
S
.
D.
F
e
r
r
a
nt
i
,
a
nd
S
.
G
i
ddi
ng,
“
H
ype
r
t
r
i
gl
yc
e
r
i
de
m
i
a
i
n
di
a
be
t
e
s
m
e
l
l
i
t
us
:
i
m
pl
i
c
a
t
i
ons
f
or
pe
di
a
t
r
i
c
c
a
r
e
,”
J
our
nal
of
t
he
E
ndoc
r
i
ne
Soc
i
e
t
y
, vol
. 2, no. 6, pp. 497
–
512, 2018, doi
:
10.1210/
j
s
.2018
-
00079.
[
7]
H
.
A
r
ya
n,
A
.
N
a
j
m
a
l
di
n,
a
nd
A
.
G
oh
a
r
i
,
“
M
or
t
a
l
i
t
y
r
a
t
e
a
nd
r
e
l
a
t
e
d
r
i
s
k
f
a
c
t
or
s
i
n
hos
pi
t
a
l
i
z
e
d
c
or
ona
vi
r
us
di
s
e
a
s
e
2019
pa
t
i
e
nt
s
w
i
t
h di
a
be
t
e
s
:
a
s
i
ngl
e
-
c
e
nt
e
r
s
t
udy,”
G
al
e
n M
e
di
c
al
J
our
nal
, vol
. 11, 2022, doi
:
10.31661/
gm
j
.v11i
.2590.
[
8]
A
.
D
.
D
e
s
hpa
nde
,
M
.
H
a
r
r
i
s
-
H
a
ye
s
,
a
nd
M
.
S
c
hoot
m
a
n,
“
E
pi
de
m
i
ol
ogy
of
di
a
be
t
e
s
a
nd
di
a
be
t
e
s
-
r
e
l
a
t
e
d
c
om
pl
i
c
a
t
i
ons
,
”
P
hy
s
i
c
al
T
he
r
apy
, vol
. 88, no. 11, pp. 1254
–
1264, 2008, doi
:
10.2522/
pt
j
.20080020.
[
9]
M
.
G
r
uj
i
c
i
c
,
A
. S
a
l
a
p
u
r
a
, G
.
J
o
va
n
o
vi
c
,
A
.
F
i
gu
r
e
k
,
D
.
Z
r
n
i
c
,
a
n
d
A
. G
r
b
i
c
,
“
N
o
n
-
di
a
b
e
t
i
c
k
i
dn
e
y
d
i
s
e
a
s
e
i
n
pa
t
i
e
n
t
s
w
i
t
h
t
y
p
e
2
d
i
a
b
e
t
e
s
m
e
l
l
i
t
us
-
11
-
y
e
a
r
e
xp
e
r
i
e
n
c
e
f
r
o
m
a
s
i
ng
l
e
c
e
n
t
e
r
,
”
M
e
d
i
c
a
l
A
r
c
h
i
v
e
s
,
v
o
l
.
7
3
,
n
o
.
2
,
p
p
.
8
7
–
9
1
,
20
1
9
,
d
o
i
:
10
.
5
4
55
/
m
e
da
r
h
.
2
01
9
.
7
3.
8
7
-
91.
[
10]
S
. K
a
m
l
e
, M
.
H
ol
a
y, P
.
P
a
t
i
l
, a
nd P
.
T
a
yde
, “
C
l
i
ni
c
a
l
pr
of
i
l
e
a
nd out
c
om
e
of
di
a
be
t
i
c
ke
t
oa
c
i
do
s
i
s
i
n
t
ype
1
a
nd t
ype
2 di
a
b
e
t
e
s
:
a
c
om
pa
r
a
t
i
ve
s
t
udy,”
V
i
dar
bha J
our
nal
of
I
nt
e
r
nal
M
e
di
c
i
ne
, vol
. 32, 2022, doi
:
10.25259/
V
J
I
M
_11_2021.
[
11]
A
. A
r
m
a
ya
ni
e
t
al
.
, “
E
f
f
e
c
t
of
hydr
oge
l
us
e
on he
a
l
i
ng di
a
be
t
i
c
f
oot
ul
c
e
r
s
:
s
y
s
t
e
m
a
t
i
c
r
e
vi
e
w
,”
O
pe
n
A
c
c
e
s
s
M
ac
e
doni
an
J
our
na
l
of
M
e
di
c
al
Sc
i
e
nc
e
s
, vol
. 10, no. F
, pp. 448
–
453, 2022, doi
:
10.3889/
oa
m
j
m
s
.2
022.9835.
[
12]
B
.
H
i
da
ya
t
,
R
.
V
.
R
a
m
a
da
ni
,
A
.
R
udi
j
a
nt
o,
P
.
S
oe
w
ondo,
K
.
S
ua
s
t
i
ka
,
a
nd
J
.
Y
.
S
i
u
N
g,
“
D
i
r
e
c
t
m
e
di
c
a
l
c
os
t
of
t
ype
2
di
a
be
t
e
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8938
I
nt
J
A
r
ti
f
I
nt
e
ll
,
V
ol
. 14, No. 2, A
pr
il
202
5
:
1
140
-
1
149
1148
m
e
l
l
i
t
us
a
nd
i
t
s
a
s
s
oc
i
a
t
e
d
c
om
pl
i
c
a
t
i
ons
i
n
I
ndone
s
i
a
,”
V
al
ue
i
n
H
e
al
t
h
R
e
gi
onal
I
s
s
ue
s
,
vol
.
28,
pp.
82
–
89,
2022,
doi
:
10.1016/
j
.vhr
i
.2021.04.006.
[
13]
V
.
K
a
vur
u,
R
.
S
.
S
e
nge
r
,
J
.
L
.
R
obe
r
t
s
on,
a
nd
D
.
C
houdhur
y,
“
A
na
l
ys
i
s
of
u
r
i
ne
R
a
m
a
n
s
pe
c
t
r
a
di
f
f
e
r
e
nc
e
s
f
r
om
pa
t
i
e
nt
s
w
i
t
h
di
a
be
t
e
s
m
e
l
l
i
t
us
a
nd r
e
na
l
pa
t
hol
ogi
e
s
,”
P
e
e
r
J
, vol
. 11, p.
e
14879, 2023, doi
:
10.7717/
pe
e
r
j
.14879.
[
14]
R
.
P
.
S
.
M
a
kk
a
r
,
A
.
M
onga
,
A
.
A
r
or
a
,
S
.
M
ukhopa
dhya
y,
a
nd
A
.
K
.
G
upt
a
,
“
S
e
l
f
‐
r
e
f
e
r
r
a
l
t
o
s
pe
c
i
a
l
i
s
t
s
–
a
dodgy
pr
opos
i
t
i
on,”
I
nt
e
r
nat
i
onal
J
our
nal
of
H
e
al
t
h C
ar
e
Q
ual
i
t
y
A
s
s
ur
an
c
e
, vol
. 16, no. 2, pp. 87
–
89, 2003, doi
:
10.1108/
09526860310465591.
[
15]
A
.
S
.
L
und
e
r
vol
d
a
nd
A
.
L
und
e
r
vol
d,
“
A
n
ov
e
r
vi
e
w
of
de
e
p
l
e
a
r
ni
ng
i
n
m
e
di
c
a
l
i
m
a
gi
ng
f
oc
u
s
i
ng
on
M
R
I
,”
Z
e
i
t
s
c
hr
i
f
t
f
ür
M
e
di
z
i
ni
s
c
he
P
hy
s
i
k
, vol
. 29, no. 2, pp. 102
–
127, 2019, doi
:
10.1016/
j
.z
e
m
e
di
.2
018.11.002.
[
16]
H
. S
.
R
.
R
a
j
ul
a
,
G
.
V
e
r
l
a
t
o,
M
.
M
a
nc
h
i
a
, N
.
A
nt
o
nuc
c
i
, a
nd
V
.
F
a
nos
, “
C
o
m
pa
r
i
s
on
o
f
c
o
nve
nt
i
on
a
l
s
t
a
t
i
s
t
i
c
a
l
m
e
t
ho
ds
w
i
t
h
m
a
c
h
i
ne
l
e
a
r
n
i
ng
i
n
m
e
d
i
c
i
ne
:
d
i
a
g
nos
i
s
,
d
r
ug
de
ve
l
op
m
e
n
t
,
a
n
d
t
r
e
a
t
m
e
n
t
,”
M
e
d
i
c
i
na
, v
ol
.
56
, n
o.
9,
2
020
,
do
i
:
10
.33
90
/
m
e
di
c
i
n
a
56
09
045
5.
[
17]
A
.
M
e
kr
a
c
he
,
A
.
B
r
a
da
i
,
E
.
M
oul
a
y,
a
nd
S
.
D
a
w
a
l
i
by,
“
D
e
e
p
r
e
i
nf
or
c
e
m
e
nt
l
e
a
r
ni
ng
t
e
c
hni
que
s
f
or
ve
hi
c
ul
a
r
ne
t
w
or
ks
:
R
e
c
e
nt
a
dva
nc
e
s
a
nd f
ut
ur
e
t
r
e
nds
t
ow
a
r
ds
6
G
,”
V
e
hi
c
ul
ar
C
om
m
uni
c
at
i
ons
, vol
. 33, 2
022, doi
:
10.1016/
j
.ve
hc
om
.2021.100398.
[
18]
K
.
T
a
n,
D
.
B
r
e
m
ne
r
,
J
.
L
.
K
e
r
ne
c
,
L
.
Z
ha
ng,
a
nd
M
.
I
m
r
a
n,
“
M
a
c
hi
n
e
l
e
a
r
ni
ng
i
n
ve
hi
c
ul
a
r
n
e
t
w
or
ki
ng:
A
n
ove
r
vi
e
w
,”
D
i
gi
t
al
C
om
m
uni
c
at
i
ons
and N
e
t
w
or
k
s
, vol
. 8, no. 1, pp. 18
–
24, 2022, doi
:
10.1016/
j
.dc
a
n.2021.10.007.
[
19]
Z
.
Q
i
a
o
e
t
al
.
,
“
A
n
e
nha
n
c
e
d
R
ung
e
K
ut
t
a
boos
t
e
d
m
a
c
hi
ne
l
e
a
r
ni
ng
f
r
a
m
e
w
or
k
f
or
m
e
di
c
a
l
di
a
gnos
i
s
,”
C
o
m
put
e
r
s
i
n
B
i
ol
ogy
and M
e
di
c
i
ne
, vol
. 160, 2023, doi
:
10.1016/
j
.c
om
pbi
om
e
d.2023.106949.
[
20]
X
.
C
he
n,
X
.
L
i
u,
Y
.
W
u
, Z
.
W
a
ng
,
a
n
d
S
.
H
. W
a
n
g,
“
R
e
s
e
a
r
c
h r
e
l
a
t
e
d t
o
t
he
d
i
a
gnos
i
s
o
f
p
r
os
t
a
t
e
c
a
nc
e
r
ba
s
e
d
o
n
m
a
c
hi
ne
l
e
a
r
n
i
ng
m
e
d
i
c
a
l
i
m
a
ge
s
:
A
r
e
vi
e
w
,”
I
nt
e
r
na
t
i
ona
l
J
our
na
l
o
f
M
e
di
c
al
I
nf
or
m
a
t
i
c
s
,
vo
l
.
18
1,
202
4,
do
i
:
1
0.1
01
6/
j
.
i
j
m
e
d
i
n
f
.
202
3.
105
27
9.
[
21]
S
.
M
a
da
ni
a
n
e
t
al
.
,
“
S
pe
e
c
h
e
m
ot
i
on
r
e
c
ogni
t
i
on
us
i
ng
m
a
c
hi
ne
l
e
a
r
ni
ng
—
A
s
ys
t
e
m
a
t
i
c
r
e
vi
e
w
,”
I
nt
e
l
l
i
ge
nt
Sy
s
t
e
m
s
w
i
t
h
A
ppl
i
c
at
i
ons
, vol
. 20, 2023, doi
:
10.1016/
j
.i
s
w
a
.2023.200266.
[
22]
E
.
C
.
P
.
N
e
t
o
,
S
.
D
a
d
kha
h, S
. S
a
de
g
hi
, H
.
M
ol
y
ne
a
ux, a
nd A
.
A
.
G
ho
r
ba
ni
,
“
A
r
e
vi
e
w
o
f
m
a
c
h
i
ne
l
e
a
r
n
i
n
g
(
M
L
)
-
ba
s
e
d I
o
T
s
e
c
ur
i
t
y
i
n
he
a
l
t
hc
a
r
e
:
A
da
t
a
s
e
t
pe
r
s
pe
c
t
i
v
e
,”
C
om
pu
t
e
r
C
om
m
uni
c
a
t
i
o
ns
,
vo
l
.
2
13,
p
p.
61
–
77
, 2
02
4,
do
i
:
10
.1
016
/
j
.c
o
m
c
om
.
20
23.
11
.00
2.
[
23]
D
.
R
.
W
i
j
a
ya
,
F
.
A
f
i
a
nt
i
,
A
.
A
r
i
f
i
a
nt
o,
D
.
R
a
hm
a
w
a
t
i
,
a
nd
V
.
S
.
K
odogi
a
nni
s
,
“
E
ns
e
m
bl
e
m
a
c
hi
ne
l
e
a
r
ni
ng
a
ppr
oa
c
h
f
or
e
l
e
c
t
r
oni
c
nos
e
s
i
gna
l
pr
oc
e
s
s
i
ng,”
S
e
ns
i
ng and B
i
o
-
Se
ns
i
ng R
e
s
e
ar
c
h
, vol
. 36, 2022, doi
:
10.1016/
j
.s
bs
r
.2022.100495.
[
24]
V
.
B
ha
r
i
l
ya
a
nd
N
.
K
um
a
r
,
“
M
a
c
hi
ne
l
e
a
r
ni
ng
f
o
r
a
ut
onom
ous
ve
hi
c
l
e
’
s
t
r
a
j
e
c
t
or
y
p
r
e
di
c
t
i
on:
A
c
om
pr
e
he
ns
i
ve
s
ur
ve
y,
c
ha
l
l
e
nge
s
, a
nd f
ut
ur
e
r
e
s
e
a
r
c
h di
r
e
c
t
i
ons
,
”
V
e
hi
c
ul
ar
C
om
m
uni
c
at
i
on
s
, vol
. 46
, 2024, doi
:
10.1016/
j
.ve
hc
om
.2024.100733.
[
25]
V
.
F
.
R
odr
i
gue
z
-
G
a
l
i
a
no,
B
.
G
hi
m
i
r
e
,
J
.
R
oga
n,
M
.
C
hi
c
a
-
O
l
m
o,
a
nd
J
.
P
.
R
i
g
ol
-
S
a
nc
he
z
,
“
A
n
a
s
s
e
s
s
m
e
nt
of
t
he
e
f
f
e
c
t
i
ve
ne
s
s
of
a
r
a
ndom
f
or
e
s
t
c
l
a
s
s
i
f
i
e
r
f
or
l
a
nd
-
c
ove
r
c
l
a
s
s
i
f
i
c
a
t
i
on,”
I
SP
R
S
J
our
nal
of
P
hot
ogr
am
m
e
t
r
y
and
R
e
m
ot
e
Se
ns
i
ng
,
vol
.
67,
pp. 93
–
104, 2012, doi
:
10.1016/
j
.i
s
pr
s
j
pr
s
.2011.11.002.
[
26]
M
. S
ha
t
na
w
i
, N
. Z
a
ki
, a
nd
P
. D
. Y
oo,
“
P
r
ot
e
i
n i
nt
e
r
-
dom
a
i
n l
i
nke
r
pr
e
di
c
t
i
on us
i
ng r
a
ndom
f
or
e
s
t
a
nd a
m
i
no
a
c
i
d phys
i
oc
h
e
m
i
c
a
l
pr
ope
r
t
i
e
s
,”
B
M
C
B
i
oi
nf
or
m
at
i
c
s
, vol
. 15, no. S
8, 2014, doi
:
10.1186/
1471
-
210
5
-
15
-
S
16
-
S
8.
[
27]
Z
.
Y
i
k
un,
H
.
Y
i
ng
j
i
e
,
Z
.
H
a
i
x
i
a
o
,
L
.
J
i
a
ha
o
,
L
.
Y
i
j
i
n,
a
nd
L
.
J
i
nj
un
, “
C
l
a
s
s
i
f
i
c
a
t
i
o
n m
e
t
ho
d o
f
vo
l
t
a
ge
s
a
g
s
ou
r
c
e
s
ba
s
e
d
o
n
s
e
qu
e
n
t
i
a
l
t
r
a
j
e
c
t
o
r
y
f
e
a
t
u
r
e
l
e
a
r
n
i
n
g a
l
go
r
i
t
hm
,”
I
E
E
E
A
c
c
e
s
s
, v
ol
. 1
0,
pp
.
38
502
–
3
851
0,
20
22,
do
i
:
1
0.1
10
9/
A
C
C
E
S
S
.2
02
2.3
16
467
5.
[
28]
N
.
K
.
M
i
s
hr
a
e
t
al
.
,
“
A
ut
om
a
t
i
c
l
e
s
i
on
bor
de
r
s
e
l
e
c
t
i
on
i
n
d
e
r
m
os
c
opy
i
m
a
ge
s
u
s
i
ng
m
or
phol
ogy
a
nd
c
ol
or
f
e
a
t
ur
e
s
,”
Sk
i
n
R
e
s
e
ar
c
h and T
e
c
hnol
ogy
, vol
. 25, no. 4, pp. 544
–
552, 2019, doi
:
10.1111/
s
r
t
.1
2685.
[
29]
I
.
U
l
l
a
h
,
B
.
R
a
z
a
,
A
.
K
.
M
a
l
i
k
,
M
.
I
m
r
a
n,
S
.
U
.
I
s
l
a
m
,
a
n
d
S
.
W
.
K
i
m
,
“
A
c
hu
r
n
p
r
e
d
i
c
t
i
o
n
m
ode
l
us
i
n
g
r
a
nd
om
f
or
e
s
t
:
a
na
l
ys
i
s
o
f
m
a
c
h
i
ne
l
e
a
r
ni
n
g t
e
c
h
ni
que
s
f
o
r
c
hu
r
n
p
r
e
d
i
c
t
i
o
n
a
nd f
a
c
t
o
r
i
de
n
t
i
f
i
c
a
t
i
on i
n t
e
l
e
c
om
s
e
c
t
o
r
,”
I
E
E
E
A
c
c
e
s
s
, vo
l
.
7
,
p
p. 601
34
–
60
14
9,
201
9,
do
i
:
10
.1
109
/
A
C
C
E
S
S
.2
019
.2
914
99
9.
[
30]
A
.
M
une
e
r
,
R
.
F
.
A
l
i
,
A
.
A
l
gha
m
di
,
S
.
M
.
T
a
i
b,
A
.
A
l
m
a
ght
ha
w
i
,
a
nd
E
.
A
.
A
.
G
h
a
l
e
b,
“
P
r
e
di
c
t
i
ng
c
us
t
om
e
r
s
c
hur
ni
ng
i
n
ba
nki
ng
i
ndus
t
r
y:
A
m
a
c
hi
ne
l
e
a
r
ni
ng
a
ppr
oa
c
h,”
I
ndone
s
i
an
J
our
nal
of
E
l
e
c
t
r
i
c
al
E
ngi
ne
e
r
i
ng
and
C
om
put
e
r
Sc
i
e
nc
e
,
vol
.
26,
no. 1, pp. 539
–
549, 2022, doi
:
10.11591/
i
j
e
e
c
s
.v26.i
1.pp539
-
549.
[
31]
Z
.
Z
h
a
o
,
W
.
Z
h
o
u,
Z
.
Q
i
u
,
A
.
L
i
,
a
n
d
J
.
W
a
n
g
,
“
R
e
s
e
a
r
c
h
o
n
c
t
r
i
p
c
us
t
o
m
e
r
c
h
u
r
n
p
r
e
d
i
c
t
i
o
n
m
o
de
l
ba
s
e
d
on
r
a
nd
o
m
f
o
r
e
s
t
,”
i
n
I
n
t
e
r
na
t
i
o
n
a
l
C
on
f
e
r
e
nc
e
o
n
B
us
i
n
e
s
s
I
n
t
e
l
l
i
g
e
nc
e
a
n
d
I
n
f
o
r
m
a
t
i
o
n
T
e
c
h
n
o
l
o
gy
,
20
22
,
p
p
.
5
1
1
–
52
3
.
do
i
:
1
0.
1
0
0
7
/
9
7
8
-
3
-
0
30
-
92632
-
8_48.
[
32]
M
.
P
a
l
a
nd
S
.
P
a
r
i
j
a
,
“
P
r
e
di
c
t
i
on
of
he
a
r
t
di
s
e
a
s
e
s
us
i
ng
r
a
ndom
f
or
e
s
t
,”
J
our
n
al
of
P
hy
s
i
c
s
:
C
onf
e
r
e
nc
e
Se
r
i
e
s
,
vol
.
1817,
no.
1
,
2021, doi
:
10.1088/
1742
-
6596/
1817/
1/
012009.
[
33]
N
.
K
.
Y
e
go,
J
.
K
a
s
oz
i
,
a
nd
J
.
N
kur
unz
i
z
a
,
“
A
c
om
pa
r
a
t
i
ve
a
na
l
ys
i
s
of
m
a
c
hi
ne
l
e
a
r
ni
ng
m
ode
l
s
f
or
t
he
pr
e
di
c
t
i
on
of
i
ns
ur
a
nc
e
upt
a
ke
i
n K
e
nya
,”
D
at
a
, vol
. 6, no. 11, 2021, doi
:
10.3390/
da
t
a
6110116.
[
34]
V
.
G
.
K
r
i
s
hna
n,
S
.
D
.
R
a
j
,
S
.
L
oke
s
h,
a
nd
S
.
S
udha
r
s
ha
n,
“
C
r
e
di
t
c
a
r
d
f
r
a
ud
de
t
e
c
t
i
on
us
i
ng
r
a
ndom
f
o
r
e
s
t
a
l
gor
i
t
hm
,”
I
nt
e
r
nat
i
onal
J
our
nal
f
o
r
R
e
s
e
a
r
c
h
i
n
A
ppl
i
e
d
Sc
i
e
nc
e
and
E
ngi
ne
e
r
i
ng
T
e
c
hnol
ogy
,
vol
.
7,
no.
3,
pp.
1199
–
1202,
2019,
doi
:
10.22214/
i
j
r
a
s
e
t
.2019.3215.
[
35]
M
. M
i
nnoor
a
nd V
.
B
a
t
hs
,
“
D
i
a
gnos
i
s
of
br
e
a
s
t
c
a
n
c
e
r
us
i
ng r
a
ndom
f
or
e
s
t
s
,
”
P
r
oc
e
di
a C
om
put
e
r
Sc
i
e
nc
e
, vol
. 218,
pp. 429
–
437,
2023, doi
:
10.1016/
j
.pr
oc
s
.2023.01.025.
[
36]
N
.
Z
h
u
, C
.
Z
hu
,
L
.
Z
h
o
u
,
Y
.
Z
h
u,
a
n
d
X
.
Z
h
a
n
g,
“
O
p
t
i
m
i
z
a
t
i
o
n
o
f
t
he
r
a
n
d
o
m
f
o
r
e
s
t
h
y
pe
r
p
a
r
a
m
e
t
e
r
s
f
o
r
p
ow
e
r
i
n
d
us
t
r
i
a
l
c
o
n
t
r
o
l
s
ys
t
e
m
s
i
n
t
r
u
s
i
on
d
e
t
e
c
t
i
o
n
us
i
n
g
a
n
i
m
p
r
o
v
e
d
g
r
i
d
s
e
a
r
c
h
a
l
g
o
r
i
t
h
m
,
”
A
p
p
l
i
e
d
S
c
i
e
n
c
e
s
,
v
o
l
.
1
2
,
n
o
.
2
0
,
2
0
2
2
,
d
o
i
:
1
0
.
3
39
0
/
a
pp
1
2
2
01
0
4
5
6.
[
37]
A
.
K
.
K
or
don,
“
S
w
a
r
m
i
nt
e
l
l
i
ge
nc
e
:
t
he
be
ne
f
i
t
s
of
s
w
a
r
m
s
,”
i
n
A
ppl
y
i
ng
C
om
put
at
i
onal
I
nt
e
l
l
i
ge
nc
e
,
B
e
r
l
i
n,
H
e
i
de
l
be
r
g:
S
pr
i
nge
r
, 2010, pp. 145
–
174. doi
:
10.1007/
978
-
3
-
540
-
69913
-
2_6.
[
38]
W
. Y
a
ng, R
.
L
i
, Y
. Y
ua
n, a
nd
X
. M
ou, “
E
c
onom
i
c
di
s
pa
t
c
h us
i
ng m
odi
f
i
e
d ba
t
a
l
gor
i
t
hm
,”
F
r
ont
i
e
r
s
i
n E
ne
r
gy
R
e
s
e
ar
c
h
, vol
. 10
,
2022, doi
:
10.3389/
f
e
nr
g.2022.977883.
[
39]
X.
-
S
. Y
a
ng, “
A
ne
w
m
e
t
a
he
ur
i
s
t
i
c
ba
t
-
i
ns
pi
r
e
d a
l
gor
i
t
hm
,”
ar
X
i
v
-
M
at
he
m
at
i
c
s
, pp. 1
–
10, 2010.
[
40]
S
.
A
na
m
,
Z
.
F
i
t
r
i
a
h,
N
.
H
i
da
ya
t
,
a
nd
M
.
H
.
A
.
A
.
M
a
ul
a
na
,
“
C
l
a
s
s
i
f
i
c
a
t
i
on
m
ode
l
f
or
di
a
be
t
e
s
m
e
l
l
i
t
us
di
a
gnos
i
s
ba
s
e
d
on
k
-
m
e
a
ns
c
l
u
s
t
e
r
i
ng
a
l
gor
i
t
hm
opt
i
m
i
z
e
d
w
i
t
h
ba
t
a
l
gor
i
t
hm
,”
I
nt
e
r
nat
i
onal
J
our
nal
of
A
dv
anc
e
d
C
om
put
e
r
Sc
i
e
nc
e
and
A
ppl
i
c
at
i
ons
, vol
. 14, no. 1, 2023, doi
:
10.14569/
I
J
A
C
S
A
.2023.0140172.
[
41]
N
.
V
a
ni
a
nd
D
.
V
i
nod,
“
A
c
om
pa
r
a
t
i
ve
a
na
l
ys
i
s
on
r
a
ndom
f
or
e
s
t
a
l
gor
i
t
h
m
ove
r
k
-
m
e
a
ns
f
o
r
i
de
nt
i
f
yi
ng
t
he
br
a
i
n
t
um
or
a
nom
a
l
i
e
s
us
i
ng
nove
l
C
T
s
c
a
n
w
i
t
h
M
R
I
s
c
a
n,”
i
n
2022
I
nt
e
r
nat
i
onal
C
onf
e
r
e
nc
e
on
B
us
i
ne
s
s
A
nal
y
t
i
c
s
f
or
T
e
c
hnol
ogy
an
d
Se
c
ur
i
t
y
(
I
C
B
A
T
S)
, 2022, pp. 1
–
6. doi
:
10.1109/
I
C
B
A
T
S
54253.2022.9759036.
[
42]
S
.
S
r
i
va
s
t
a
va
a
nd
S
.
K
.
S
a
ha
na
,
“
A
ppl
i
c
a
t
i
on
of
ba
t
a
l
gor
i
t
hm
f
or
t
r
a
ns
por
t
ne
t
w
or
k
de
s
i
gn
pr
obl
e
m
,”
A
ppl
i
e
d
C
om
put
at
i
onal
I
nt
e
l
l
i
ge
nc
e
and Sof
t
C
om
put
i
ng
, vol
. 2019, pp. 1
–
12, 2019, doi
:
10.1155/
2019/
9864090.
[
43]
A
.
A
s
oka
n,
D
.
E
.
P
ope
s
c
u,
J
.
A
ni
t
ha
,
a
nd
D
.
J
.
H
e
m
a
nt
h,
“
B
a
t
a
l
gor
i
t
hm
ba
s
e
d
non
-
l
i
ne
a
r
c
ont
r
a
s
t
s
t
r
e
t
c
hi
ng
f
or
s
a
t
e
l
l
i
t
e
i
m
a
g
e
e
nha
nc
e
m
e
nt
,”
G
e
o
s
c
i
e
nc
e
s
, vol
. 10, no. 2, 2020, doi
:
10.3390/
ge
os
c
i
e
n
c
e
s
100
20078.
[
44]
T
.
A
.
R
a
s
hi
d
e
t
al
.
,
“
A
n
i
m
pr
ove
d
B
A
T
a
l
gor
i
t
hm
f
o
r
s
ol
vi
ng
j
ob
s
c
he
dul
i
ng
pr
obl
e
m
s
i
n
hot
e
l
s
a
nd
r
e
s
t
a
ur
a
nt
s
,”
i
n
St
udi
e
s
i
n
C
om
put
at
i
onal
I
nt
e
l
l
i
ge
nc
e
, S
pr
i
nge
r
, C
ha
m
, 2021, pp. 155
–
171. doi
:
10.1007/
978
-
3
-
030
-
72711
-
6_9.
[
45]
S
.
A
na
m
a
nd
Z
.
F
i
t
r
i
a
h,
“
E
a
r
l
y
bl
i
ght
di
s
e
a
s
e
s
e
gm
e
nt
a
t
i
on
on
t
om
a
t
o
pl
a
nt
us
i
ng
k
-
m
e
a
ns
a
l
gor
i
t
hm
w
i
t
h
s
w
a
r
m
i
nt
e
l
l
i
ge
nc
e
-
ba
s
e
d a
l
gor
i
t
hm
,”
I
nt
e
r
nat
i
onal
J
our
nal
of
M
at
he
m
at
i
c
s
and C
o
m
put
e
r
Sc
i
e
n
c
e
, vol
. 16, no. 4, pp. 1217
–
1228, 2021.
[
46]
L
. B
r
e
i
m
a
n, “
R
a
ndom
f
or
e
s
t
s
,”
i
n
M
ac
hi
ne
L
e
ar
ni
ng
, S
pr
i
nge
r
, 2001, pp. 5
–
32
, doi
:
10.1023/
A
:
1010933404324
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
r
ti
f
I
nt
e
ll
I
S
S
N
:
2252
-
8938
D
ia
be
te
s
m
e
ll
it
us
di
agnos
i
s
m
e
th
od bas
e
d r
andom fo
r
e
s
t
w
it
h b
at
al
gor
it
hm
(
Sy
ai
fu
l
A
nam
)
1149
B
I
O
G
R
A
P
H
I
E
S
O
F
A
U
T
H
O
R
S
Syaiful
Anam
received
a
Do
ctor
of
Natural
Science
and
Mathem
atics
degree
from
Yamaguchi
University,
Japan
in
2015.
He
also
received
his
Bachel
or
Degree
in
Mathematics
from
Brawijaya
University,
Indonesia
in
2001
and
his
Master
Degre
e
from
Sepuluh
Nopember
Institut
e
of
Technology,
Indonesia
in
2006.
He
is
currently
an
Assista
nt
Professor
at
Department
of
Mathematics,
Brawijaya
University,
Malang,
Indonesia.
His
rese
arch
includes
data
science,
computat
ional
intell
igence,
machine
learning,
digital
image
processin
g,
and
computer
vision
.
He
has
published
over
35
papers
in
international
jo
urnals
and
conferenc
es.
He
can
be
contacted
at
email:
syaiful@
ub.ac.id.
Fidia
Deny
Tisna
Amijaya
holds
the
Master
D
egree
in
Math
ematics
from
the
Brawijay
a
University,
Malang,
Indonesia,
with
the
master
thesis
“
Hybrid
greedy
algorithm
-
particle
swarm
optimization
-
genetic
algorithm
(Hybrid
GPSOG
A)”.
He
also
received
his
Bachelo
r
Degre
e
in
Mathema
tics
from
Brawijay
a
Universi
ty,
Ind
onesia
in
2011
.
He
is
an
Assistant P
rofessor in
Department of
Mathematics,
Faculty of Mathem
atics and Natur
al Sciences,
Mulawarman
University,
Samarinda,
Indonesia.
His
researc
h
interests
are
in
applied
mathematics,
data
mining,
and
computationa
l
intelligence
.
He
ca
n
be
contacted
a
t
email
:
fidiadta@
fmipa.unmu
l.ac.id.
Satrio
Hadi
Wijoyo
holds
the
Master
D
egree
in
Informatics
Engi
neering
from
the
Sepuluh
Nopemb
er
Inst
i
tute
of
Technology,
Surabaya,
Indonesia.
He
also
received
his
Bachelor
Degree
in
Mathematics
from
Brawijaya
University,
Indonesia
in
2013.
He
is
an
Assistant
Profes
sor
in
Department
of
Information
System,
Faculty
of
Co
mputer
Science,
Malang,
Indonesia.
His
research
interests
are
Ed
ucation,
learning,
evaluation,
learning
media,
intelligent
computi
ng,
and
data
&
informat
ion
man
agement.
He
can
be
contacted
at
email:
satriohadi@ub.ac.id
.
Dian
Eka
Ratnawati
holds
a
Bachelor
of
Science
in
Mathe
matics,
Master
in
Informatics
Engineering
and
Doctor
in
Mathematics.
She
is
cur
rently
lecturing
with
the
D
epartment
of
Informati
cs
Engineeri
ng
at
Faculty
of
Science,
Bra
wijaya
Universi
ty,
Malang,
Indonesia.
Her
research
areas
of
interest
include
computat
ional
intell
ig
ence
.
She
can
be
contacted
at email
:
dian_ilkom@
ub.ac.id
.
Cynthia
Ayu
Dwi
Lestari
is
a
student
of
the
Master
Degree
in
Mathematics
Brawijay
a
Universi
ty,
Malang,
Indones
ia.
She
also
recei
ved
his
Bach
elor
Degre
e
in
Mathema
tics
from
Brawijaya
University,
Indonesia
in
2019.
Her
research
interests
are
computational
intelligence
and data
science
. She can
be contac
ted at ema
il: cynthiaay
u@
student.ub.a
c.id
.
Muhaimi
n
Ilyas
is
a
student
of
the
Master
Degree
in
Mathe
matics
Brawijaya
University,
Malang,
Indonesia.
He
also
received
his
Bachelor
De
gree
in
Mathematics
from
Brawijay
a
Universi
ty,
Indones
ia
in
2023.
His
resea
rch
interes
ts
are
computatio
nal
intelligen
ce
and data s
cience. He can
be contact
ed at emai
l: chaim
in@
student
.ub.ac.id
.
Evaluation Warning : The document was created with Spire.PDF for Python.