I
n
d
on
e
s
ian
Jou
r
n
al
o
f
E
lec
t
r
ica
l
E
n
gin
e
e
r
in
g
a
n
d
Com
p
u
t
e
r
S
c
ience
Vo
l
.
3
8
,
N
o
.
1
,
A
pr
i
l
20
2
5
,
pp.
569
~
57
7
I
S
S
N:
2
502
-
4
7
52
,
DO
I
:
10
.
11591/i
j
e
e
cs
.v
3
8
.
i
1
.
pp
569
-
57
7
569
Jou
r
n
al
h
o
m
e
page
:
ht
tp:
//
ij
e
e
cs
.
iaes
c
or
e
.
c
om
T
r
e
e
-
b
ase
d
m
od
e
ls
a
n
d
h
y
p
e
r
p
ar
a
m
e
t
e
r
op
t
im
i
z
at
io
n
f
or
asse
ssi
n
g e
m
p
lo
y
e
e
p
e
r
f
o
r
m
a
n
c
e
Re
n
d
r
a
Gu
s
t
r
ian
s
yah
1
,
S
h
in
t
a
P
u
s
p
as
a
r
i
1
,
Ahm
ad
S
an
m
or
in
o
2
,
Naz
or
i
S
u
h
an
d
i
1
,
De
wi
S
ar
t
ik
a
3
1
D
e
pa
r
tm
e
nt
of
I
n
f
or
ma
ti
c
s
E
ng
in
e
e
r
in
g,
F
a
c
ul
t
y
of
C
omput
e
r
a
nd N
a
tu
r
a
l
S
c
i
e
nc
e
, U
ni
ve
r
s
it
a
s
I
nd
o
G
l
o
ba
l
M
a
ndi
r
i,
P
a
le
mba
ng, I
nd
o
n
e
s
ia
2
D
e
pa
r
tm
e
nt
of
I
n
f
or
ma
ti
o
n S
y
s
te
m,
F
a
c
ul
t
y
of
C
omput
e
r
a
nd
N
a
tu
r
a
l
S
c
i
e
n
c
e
, U
ni
ve
r
s
it
a
s
I
nd
o
G
l
o
ba
l
M
a
ndi
r
i,
P
a
le
mba
ng, I
ndo
n
e
s
ia
3
D
e
pa
r
tm
e
nt
of
I
n
f
or
ma
ti
c
s
E
ng
in
e
e
r
in
g,
F
a
c
ul
t
y
of
C
omput
e
r
S
c
i
e
n
c
e
, U
ni
ve
r
s
it
a
s
S
r
iwi
ja
y
a
,
P
a
l
e
mba
ng,
I
nd
o
n
e
s
ia
Ar
t
ic
l
e
I
n
f
o
AB
S
T
RA
CT
A
r
ti
c
le
h
is
tor
y
:
R
e
c
e
i
ve
d
M
a
y
8
,
202
4
R
e
vi
s
e
d
Oc
t
14
,
202
4
A
c
c
e
pt
e
d
Oc
t
30
,
202
4
T
h
e
Pal
em
b
an
g
ci
t
y
fi
r
e
an
d
r
e
s
c
u
e
s
e
rv
i
c
e
(FRS)
i
s
e
n
co
u
n
t
e
ri
n
g
ch
al
l
e
n
g
e
s
i
n
a
d
h
e
r
i
n
g
t
o
n
at
i
o
n
al
s
t
an
d
ar
d
s
fo
r
f
i
r
e
r
e
s
p
o
n
s
e
t
i
me
.
H
en
ce
,
t
h
e
Pal
em
b
an
g
c
i
t
y
FRS
i
s
co
mm
i
t
t
ed
t
o
e
n
h
an
ci
n
g
emp
l
o
y
ee
p
e
rf
o
r
m
an
ce
t
h
ro
u
g
h
q
u
art
e
r
l
y
p
e
rf
o
r
m
an
ce
as
s
e
s
s
me
n
t
s
b
as
ed
o
n
v
a
ri
o
u
s
c
ri
t
e
ri
a
s
u
c
h
as
at
t
e
n
d
an
ce,
w
o
rk
t
arg
e
t
s
,
b
e
h
a
v
i
o
r,
ed
u
c
at
i
o
n
,
an
d
p
e
rfo
rm
an
ce
r
e
p
o
rt
s
.
T
h
i
s
s
t
u
d
y
p
ro
p
o
s
e
s
t
ree
-
b
as
e
d
mo
d
el
s
i
n
m
a
ch
i
n
e
l
e
arn
i
n
g
(ML
)
a
n
d
h
y
p
e
rp
ara
me
t
e
r
o
p
t
i
m
i
zat
i
o
n
t
o
as
s
e
s
s
t
h
e
p
e
rf
o
r
m
an
ce
o
f
Pa
l
em
b
an
g
c
i
t
y
FRS
em
p
l
o
y
ee
s
.
T
ree
-
b
as
ed
m
o
d
e
l
s
e
n
co
m
p
as
s
d
ec
i
s
i
o
n
t
ree
s
(D
T
),
ran
d
o
m
fo
re
s
t
s
(RF),
an
d
e
x
t
reme
g
rad
i
e
n
t
b
o
o
s
t
i
n
g
(X
G
B).
T
h
e
p
red
i
c
t
i
v
e
p
e
rfo
r
m
an
ce
o
f
e
ach
m
o
d
e
l
w
as
e
v
a
l
u
at
e
d
u
s
i
n
g
t
h
e
co
n
fu
s
i
o
n
m
at
ri
x
(CM)
,
t
h
e
ar
e
a
u
n
d
e
r
t
h
e
r
ece
i
v
e
r
o
p
e
rat
i
n
g
c
h
ara
c
t
e
ri
s
t
i
c
(A
U
RO
C),
an
d
t
h
e
k
ap
p
a
c
o
e
ff
i
c
i
en
t
(
K
C).
T
h
e
re
s
u
l
t
s
i
n
d
i
c
at
e
t
h
at
RF
p
e
rfo
r
m
s
b
e
t
t
e
r
t
h
an
D
T
an
d
X
G
B
i
n
t
h
e
s
e
n
s
i
t
i
v
i
t
y
,
A
U
RO
C,
an
d
K
C
me
t
ri
c
s
b
y
1
.
0
0
0
0
,
0
.
9
8
7
4
,
an
d
0
.
8
5
8
4
,
re
s
p
e
c
t
i
v
e
l
y
.
K
e
y
w
o
r
d
s
:
De
c
i
s
i
o
n
t
r
e
e
E
m
p
l
o
y
e
e
pe
r
f
o
r
m
a
nc
e
E
x
t
r
e
m
e
gr
a
d
i
e
n
t
b
oo
s
t
i
n
g
H
y
pe
r
pa
r
a
m
e
t
e
r
o
p
t
i
mi
z
a
t
i
o
n
M
a
c
hi
ne
l
e
a
r
ni
ng
R
a
n
do
m
f
o
r
e
s
t
Th
i
s
i
s
a
n
o
p
en
a
c
ces
s
a
r
t
i
c
l
e
u
n
d
e
r
t
h
e
CC
B
Y
-
SA
l
i
cen
s
e.
C
or
r
e
s
pon
din
g
A
u
th
or
:
R
e
n
dr
a
Gus
t
r
i
a
ns
y
a
h
De
pa
r
t
m
e
n
t
o
f
I
nf
o
r
m
a
t
i
c
s
E
n
g
i
ne
e
r
i
ng,
F
a
c
u
l
t
y
o
f
C
o
m
put
e
r
a
n
d
Na
t
ur
a
l
S
c
i
e
n
c
e
Uni
ve
r
s
i
t
a
s
I
n
do
Gl
o
ba
l
M
a
n
d
i
r
i
S
tr
e
e
t
o
f
J
e
n
de
r
a
l
S
ud
i
r
m
a
n
No
.
629,
P
a
l
e
m
ba
ng,
30129,
I
n
do
n
e
s
i
a
E
m
a
i
l
:
r
e
n
dr
a
@
u
i
g
m
.
a
c
.
i
d
1.
I
NT
RODU
C
T
I
ON
A
c
c
o
r
d
i
n
g
to
P
e
r
m
e
n
da
gr
i
86
o
f
2017,
t
h
e
n
a
t
i
o
na
l
s
t
a
n
da
r
d
f
o
r
t
h
e
f
i
r
e
a
n
d
r
e
s
c
ue
s
e
r
vi
c
e
(
F
R
S
)
pe
r
f
o
r
m
a
n
c
e
i
s
t
h
a
t
t
h
e
F
R
S
m
u
s
t
b
e
a
bl
e
to
h
a
n
d
l
e
a
f
i
r
e
m
a
n
a
ge
m
e
n
t
a
r
e
a
w
i
t
h
a
m
a
xi
m
u
m
r
e
s
po
n
s
e
t
i
m
e
o
f
15
m
i
nut
e
s
.
Ho
we
v
e
r
,
t
h
e
P
a
l
e
m
ba
n
g
c
i
t
y
F
R
S
i
s
n
o
t
m
e
e
t
i
n
g
t
hi
s
t
a
r
ge
t
.
I
t
i
s
s
h
o
wn
f
r
o
m
t
h
e
pe
r
f
o
r
m
a
n
c
e
i
nd
i
c
a
t
o
r
t
h
a
t
f
i
r
e
r
e
s
p
o
n
s
e
t
i
m
e
i
n
2022
w
i
ll
o
nly
r
e
a
c
h
80
pe
r
c
e
n
t
[
1]
.
T
h
e
r
e
f
o
r
e
,
t
h
e
P
a
l
e
m
ba
n
g
c
i
t
y
F
R
S
i
s
c
o
m
mi
t
t
e
d
to
i
m
pr
o
vi
n
g
i
t
s
pe
r
f
o
r
m
a
n
c
e
i
n
t
h
e
ne
xt
t
h
r
e
e
y
e
a
r
s
.
On
e
wa
y
i
s
to
e
n
h
a
n
c
e
e
m
p
l
o
y
e
e
pe
r
f
o
r
m
a
n
c
e
.
T
h
e
P
a
l
e
m
ba
n
g
c
i
t
y
F
R
S
h
a
s
i
n
i
t
i
a
t
e
d
e
m
p
l
o
y
e
e
pe
r
f
o
r
m
a
n
c
e
a
s
s
e
s
s
m
e
n
t
s
e
v
e
r
y
qua
r
t
e
r
.
T
o
e
n
s
ur
e
a
f
a
i
r
a
n
d
o
bj
e
c
t
i
v
e
a
s
s
e
s
s
m
e
n
t
,
F
R
S
ut
i
l
i
z
e
s
m
u
l
t
i
p
l
e
c
r
i
t
e
r
i
a
,
i
n
c
l
ud
i
ng
a
tt
e
n
da
n
c
e
,
wo
r
k
t
a
r
ge
t
s
,
b
e
h
a
vi
o
r
,
e
duc
a
t
i
o
n
,
a
n
d
pe
r
f
o
r
m
a
n
c
e
r
e
po
r
t
s
.
T
h
e
r
e
s
ul
t
s
o
f
t
h
e
pe
r
f
o
r
m
a
n
c
e
a
s
s
e
s
s
m
e
n
t
a
r
e
t
h
e
b
a
s
i
s
f
o
r
de
t
e
r
m
i
ni
ng
a
l
l
o
wa
n
c
e
s
.
T
h
e
r
e
f
o
r
e
,
a
n
o
bj
e
c
t
i
v
e
a
ppr
a
i
s
a
l
i
s
n
e
e
de
d
to
e
n
s
ur
e
t
h
e
a
s
s
e
s
s
m
e
n
t
t
e
a
m
’
s
f
i
nd
i
ngs
a
li
g
n
w
i
t
h
e
a
c
h
e
m
p
l
o
y
e
e
’
s
a
c
c
o
m
p
li
s
hm
e
n
t
s
.
M
a
c
hi
ne
l
e
a
r
ni
ng
(
M
L
)
m
e
t
h
o
ds
c
a
n
b
e
a
pp
li
e
d
a
s
t
h
e
r
i
g
h
t
s
o
l
ut
i
o
n
to
r
e
duc
e
bi
a
s
i
n
pe
r
f
o
r
m
a
n
c
e
a
s
s
e
s
s
m
e
n
t
.
M
L
c
a
n
b
u
il
d
m
o
de
l
s
t
o
i
de
n
t
i
f
y
s
pe
c
i
f
i
c
pa
tt
e
r
n
s
i
n
a
da
t
a
s
e
t
,
a
n
d
m
o
de
l
s
c
a
n
b
e
ut
i
li
z
e
d
to
e
v
a
l
ua
t
e
/pr
e
d
i
c
t
n
e
w
da
t
a
.
Ho
we
v
e
r
,
t
h
e
r
e
a
r
e
o
nl
y
a
f
e
w
i
m
p
l
e
m
e
n
t
a
t
i
o
n
s
o
f
M
L
to
a
s
s
e
s
s
e
m
p
l
o
y
e
e
pe
r
f
o
r
m
a
n
c
e
.
S
o
m
e
s
t
ud
i
e
s
us
e
m
e
t
h
o
ds
s
uc
h
a
s
th
e
Na
ï
ve
B
a
y
e
s
(
NB
)
[
2]
-
[
4]
,
de
c
i
s
i
o
n
t
r
e
e
(
DT
)
[
2]
,
[
5
]
,
a
n
d
K
-
n
e
a
r
e
s
t
n
e
i
g
hb
o
r
(
K
NN
)
[
3]
.
Ga
l
i
h
a
n
d
E
r
iy
a
d
i
[
6]
a
n
d
S
a
r
t
i
k
a
a
n
d
Gus
t
r
i
a
n
s
y
a
h
[
5]
s
h
o
w
t
h
a
t
t
h
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2
5
0
2
-
4
7
52
In
do
n
e
s
i
a
n
J
E
l
e
c
E
n
g
&
C
o
m
p
S
c
i
,
Vo
l
.
3
8
,
N
o
.
1
,
A
pr
i
l
20
2
5
:
569
-
57
7
570
pe
r
f
o
r
m
a
n
c
e
o
f
t
h
e
DT
m
e
t
h
o
d
o
u
t
pe
r
f
o
r
m
s
t
h
e
NB
.
M
e
a
nw
hi
l
e
,
o
t
h
e
r
s
t
udi
e
s
ge
n
e
r
a
ll
y
u
s
e
m
u
l
t
i
-
c
r
i
t
e
r
i
a
de
c
i
s
i
o
n
-
m
a
k
i
ng
m
e
t
h
o
ds
,
i
n
c
l
ud
i
ng
t
h
e
a
n
a
l
y
t
i
c
a
l
hi
e
r
a
r
c
hy
pr
o
c
e
s
s
[
7]
,
[
8]
,
s
i
m
p
l
e
a
dd
i
t
i
v
e
w
e
i
g
h
t
i
ng
[
9]
,
[
10]
,
t
e
c
h
ni
qu
e
f
o
r
or
de
r
pr
e
f
e
r
e
n
c
e
by
s
i
mi
l
a
r
i
t
y
to
i
de
a
l
s
o
l
ut
i
o
n
[
11]
,
[
12
]
,
pr
o
f
i
l
e
m
a
t
c
hi
ng
[
13]
,
[
14]
,
we
i
g
h
t
e
d
pr
o
duc
t
[
15]
,
a
n
d
ot
h
e
r
s
t
h
a
t
m
u
s
t
i
nv
o
l
v
e
e
x
pe
r
t
s
to
a
s
s
e
s
s
e
m
p
l
o
y
e
e
pe
r
f
o
r
m
a
n
c
e
.
B
e
s
i
de
s
t
h
a
t,
t
h
e
r
e
a
r
e
s
e
ve
r
a
l
s
im
il
a
r
s
t
udi
e
s
b
ut
f
o
r
t
h
e
c
a
s
e
o
f
s
t
ude
n
t
/ac
a
de
m
i
c
pe
r
f
o
r
m
a
n
c
e
a
s
s
e
s
s
m
e
n
t
w
i
t
h
nu
m
e
r
i
c
a
l
[
16]
-
[
18
]
a
n
d
c
a
t
e
g
o
r
i
c
a
l
da
t
a
[
19]
-
[
21
]
.
T
h
e
r
e
f
o
r
e
,
t
h
i
s
s
t
udy
pr
o
p
o
s
e
s
tr
e
e
-
b
a
s
e
d
m
o
de
l
s
i
n
M
L
to
a
s
s
e
s
s
t
h
e
P
a
l
e
m
ba
n
g
c
i
t
y
F
R
S
e
m
p
l
o
y
e
e
s
’
pe
r
f
o
r
m
a
n
c
e
.
T
r
e
e
-
b
a
s
e
d
m
o
de
l
s
i
n
M
L
i
n
c
l
ude
DT
,
r
a
n
do
m
f
o
r
e
s
t
(
R
F
)
,
a
n
d
e
x
t
r
e
m
e
gr
a
di
e
n
t
b
o
o
s
t
i
n
g
(
XG
B
)
.
DT
i
n
M
L
i
s
l
i
ke
a
f
l
o
wc
h
a
r
t
t
h
a
t
m
a
ke
s
de
c
i
s
i
o
ns
b
a
s
e
d
o
n
da
t
a
a
tt
r
i
b
ut
e
s
a
n
d
l
e
a
ds
to
a
de
c
i
s
i
o
n
[
5]
.
I
t
i
s
be
n
e
f
i
c
i
a
l
i
n
s
i
t
ua
t
i
o
ns
t
h
a
t
r
e
qu
i
r
e
s
t
r
a
i
g
h
t
f
o
r
wa
r
d
a
n
d
l
o
g
i
c
a
l
j
udg
m
e
n
t
s
.
M
e
a
n
w
hil
e
,
pr
uni
ng
t
e
c
h
ni
que
s
a
r
e
e
s
s
e
n
t
i
a
l
t
o
e
n
s
ur
e
t
h
e
DT
m
o
de
l
’
s
a
c
c
ur
a
c
y
.
T
h
e
r
e
f
o
r
e
,
t
h
e
y
h
e
l
p
de
c
r
e
a
s
e
m
o
de
l
c
o
m
p
l
e
xi
t
y
a
n
d
pr
e
v
e
n
t
o
v
e
r
f
i
t
t
i
n
g
to
a
c
hi
e
v
e
o
pt
i
m
a
l
p
e
r
f
o
r
m
a
n
c
e
.
R
F
i
s
a
n
e
n
s
e
m
bl
e
l
e
a
r
ni
ng
m
e
t
h
o
d
t
h
a
t
c
o
m
bi
ne
s
s
e
v
e
r
a
l
DT
s
to
p
r
o
duc
e
m
o
r
e
a
c
c
ur
a
t
e
pr
e
di
c
t
i
o
n
s
[
22]
.
I
n
h
a
n
d
li
ng
c
o
m
p
l
e
x
da
t
a
s
e
t
s
,
t
hi
s
m
e
t
h
o
d
ge
n
e
r
a
ll
y
o
ut
pe
r
f
o
r
m
s
DT
[
23]
.
XG
B
,
o
n
t
h
e
ot
h
e
r
h
a
n
d,
i
s
a
n
o
t
h
e
r
e
n
s
e
m
b
l
e
l
e
a
r
ni
ng
m
e
t
h
o
d
wi
t
h
a
d
i
f
f
e
r
e
n
t
a
ppr
o
a
c
h
t
h
a
n
R
F
[
24]
.
R
F
b
u
il
d
s
t
r
e
e
s
i
n
de
p
e
n
de
n
t
l
y
,
whil
e
XG
B
b
u
il
ds
t
r
e
e
s
s
e
que
n
t
i
a
ll
y
.
E
a
c
h
n
e
w
tr
e
e
h
e
l
p
s
c
o
r
r
e
c
t
t
h
e
m
i
s
t
a
ke
s
m
a
de
by
t
he
pr
e
vio
us
tr
e
e
.
It
’
s
a
s
i
f
e
a
c
h
t
r
e
e
i
n
t
h
e
s
e
que
n
c
e
l
e
a
r
ns
f
r
o
m
th
e
pr
e
vi
o
us
t
r
e
e
’
s
m
i
s
t
a
ke
s
,
r
e
s
u
l
t
i
n
g
i
n
a
m
o
r
e
a
c
c
ur
a
t
e
m
o
de
l
.
A
dd
i
t
i
o
n
a
ll
y
,
hy
p
e
r
pa
r
a
m
e
t
e
r
s
w
i
ll
b
e
f
i
n
e
-
tu
n
e
d
to
b
e
o
p
t
i
m
a
l
[
25]
,
a
n
d
e
a
c
h
m
o
de
l
’
s
pr
e
d
i
c
t
i
v
e
pe
r
f
o
r
m
a
n
c
e
i
s
e
v
a
l
ua
t
e
d
us
i
n
g
m
e
t
r
i
c
s
s
uc
h
a
s
a
c
c
ur
a
c
y
,
s
e
ns
i
t
i
vi
t
y
,
pr
e
c
i
s
i
o
n
,
s
pe
c
i
f
i
c
i
t
y
,
a
r
e
a
un
de
r
r
e
c
e
i
v
e
r
o
pe
r
a
t
i
n
g
c
h
a
r
a
c
t
e
r
i
s
t
i
c
,
a
n
d
k
a
ppa
c
o
e
f
f
i
c
i
e
n
t
(
K
C
)
.
2.
M
E
T
HO
D
T
h
e
s
t
ud
y
’
s
a
ppr
o
a
c
h
i
s
b
a
s
e
d
o
n
t
h
e
m
o
d
i
f
i
e
d
c
r
o
s
s
-
i
n
du
s
t
r
y
s
t
a
n
da
r
d
pr
o
c
e
s
s
f
o
r
da
t
a
m
i
ni
ng
[
26]
.
T
hi
s
m
o
de
l
c
o
m
pr
i
s
e
s
f
i
ve
s
e
que
n
t
i
a
l
pr
o
c
e
s
s
e
s
,
a
s
de
p
i
c
t
e
d
i
n
F
i
gur
e
1.
T
h
e
i
ni
t
i
a
l
p
h
a
s
e
o
f
t
hi
s
m
o
de
l
is
B
us
i
ne
s
s
U
n
de
r
s
t
a
n
d
i
ng.
T
hi
s
p
h
a
s
e
c
o
m
pr
e
he
n
ds
t
h
e
b
us
i
ne
s
s
f
r
o
m
v
a
r
i
o
us
pe
r
s
pe
c
t
i
ve
s
,
s
uc
h
a
s
a
p
p
l
i
c
a
t
i
o
n
fi
e
l
d,
pr
o
j
e
c
t
g
o
a
l
s
,
r
e
qu
i
r
e
m
e
n
t
s
,
a
n
d
m
a
n
a
g
e
m
e
nt
r
e
gul
a
t
i
o
ns
.
D
a
t
a
U
n
d
e
r
s
t
a
n
d
i
n
g
E
v
a
l
u
a
t
i
o
n
B
u
s
i
n
e
s
s
U
n
d
e
r
s
t
a
n
d
i
n
g
D
a
t
a
P
r
e
p
a
r
a
t
i
o
n
M
o
d
e
l
i
n
g
F
i
gur
e
1.
R
e
s
e
a
r
c
h
p
h
a
s
e
s
2.
1.
Dat
a
u
n
d
e
r
s
t
an
d
in
g
T
h
e
s
e
c
o
n
d
p
ha
s
e
i
nv
o
l
ve
s
c
o
l
l
e
c
t
i
n
g,
de
s
c
r
i
bi
ng
,
a
n
a
ly
z
i
ng,
a
n
d
m
a
ni
pu
l
a
t
i
n
g
da
t
a
us
i
n
g
va
r
i
o
us
t
e
c
h
ni
que
s
t
o
f
a
m
il
i
a
r
i
z
e
u
s
e
r
s
w
i
t
h
t
h
e
da
t
a
.
T
h
e
P
a
l
e
m
ba
n
g
c
i
t
y
F
R
S
da
t
a
s
e
t
f
r
o
m
t
h
e
f
i
r
s
t
qua
r
t
e
r
o
f
2023
(
J
a
n
ua
r
y
t
o
M
a
r
c
h
)
wi
ll
b
e
ut
i
li
z
e
d
f
o
r
t
hi
s
s
t
ud
y
.
T
h
e
da
t
a
s
e
t
h
a
s
218
e
m
p
l
o
y
e
e
r
e
c
o
r
ds
,
e
a
c
h
c
o
n
t
a
i
n
i
ng
s
i
x
a
tt
r
i
b
ut
e
s
wi
t
h
v
a
l
ue
s
a
s
pr
e
s
e
n
t
e
d
i
n
T
a
bl
e
1.
F
ur
t
h
e
r
m
o
r
e
,
t
h
e
c
o
r
r
e
l
a
t
i
o
n
be
t
we
e
n
v
a
r
i
a
bl
e
s
i
s
v
e
r
i
f
i
e
d
us
i
n
g
t
h
e
r
a
n
k
c
o
r
r
e
l
a
t
i
o
n
c
o
e
f
f
i
c
i
e
n
t
.
T
a
bl
e
1.
A
tt
r
i
b
ut
e
s
de
s
c
r
i
pt
i
o
n
A
tt
r
ib
ut
e
s
V
a
lu
es
T
y
p
e
A
tt
e
nda
nc
e
D
is
c
ip
li
ne
/
undi
s
c
i
pl
in
e
d
C
a
te
gor
ic
a
l
P
e
r
f
or
ma
n
c
e
_
r
e
p
or
t
S
a
ti
s
f
i
e
d
/d
is
s
a
ti
s
f
i
e
d
C
a
te
gor
ic
a
l
W
o
r
k_t
a
r
g
e
t
N
e
e
ds
i
mp
r
ov
e
m
e
nt
/g
oo
d/
ve
r
y
g
oo
d
C
a
te
gor
ic
a
l
W
o
r
k_b
e
ha
v
i
o
r
N
e
e
ds
i
mp
r
ov
e
m
e
nt
/g
oo
d/
ve
r
y
g
oo
d
C
a
te
gor
ic
a
l
E
duc
a
ti
o
n
S
M
P
/S
M
A
(
S
M
K
)
/D3/
S
1/
S
2
C
a
te
gor
ic
a
l
R
e
s
ul
t
W
o
r
th
y
/
u
nw
or
th
y
C
a
te
gor
ic
a
l
2.
2.
Dat
a
p
r
e
p
ar
at
ion
All
a
c
t
i
vi
t
i
e
s
r
e
qu
i
r
e
d
to
c
o
n
s
t
r
uc
t
t
h
e
f
i
na
l
da
t
a
s
e
t
to
b
e
us
e
d
i
n
t
h
e
m
o
de
l
i
ng
pha
s
e
a
r
e
c
o
v
e
r
e
d
i
n
t
hi
s
p
h
a
s
e
.
Da
t
a
pr
e
pa
r
a
t
i
o
n
i
s
a
c
r
uc
i
a
l
p
ha
s
e
i
n
e
nh
a
n
c
i
ng
m
o
de
l
pe
r
f
o
r
m
a
n
c
e
.
Dur
i
n
g
t
hi
s
pr
o
c
e
s
s
,
i
nv
a
li
d
da
t
a
,
i
n
c
l
ud
i
ng
e
m
pt
y
,
i
n
c
o
m
p
l
e
t
e
,
o
r
n
u
l
l
da
t
a
i
s
r
e
m
o
v
e
d
f
r
o
m
t
h
e
da
t
a
s
e
t
[
27
]
.
A
dd
i
t
i
o
n
a
ll
y
,
a
l
l
va
r
i
a
bl
e
s
a
r
e
c
o
n
v
e
r
t
e
d
to
n
u
m
e
r
i
c
v
a
l
ue
s
t
o
f
a
c
il
i
t
a
t
e
c
a
l
c
u
l
a
t
i
o
ns
a
n
d
t
h
e
n
e
n
c
o
de
d
a
s
c
a
t
e
gor
i
c
a
l
.
Af
t
e
r
t
hi
s
,
t
h
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
do
n
e
s
i
a
n
J
E
l
e
c
E
n
g
&
C
o
m
p
S
c
i
I
S
S
N:
2
5
0
2
-
4
7
52
T
r
e
e
-
bas
e
d
mode
ls
and
hy
pe
r
par
a
me
ter
opti
miz
ati
on
…
(
R
e
ndr
a
Gus
tr
ians
y
ah
)
571
da
t
a
s
e
t
i
s
r
a
n
do
m
ly
pa
r
t
i
t
i
o
n
e
d
i
n
t
o
t
w
o
pa
r
t
s
,
wi
t
h
80%
o
f
t
h
e
da
t
a
a
l
l
o
c
a
t
e
d
f
o
r
t
r
a
i
ni
ng
a
n
d
t
h
e
r
e
m
a
i
n
i
ng
20%
f
o
r
t
e
s
t
i
n
g.
T
h
e
da
t
a
b
a
l
a
n
c
e
a
c
r
o
s
s
e
a
c
h
c
l
a
s
s
i
n
t
he
t
a
r
ge
t
v
a
r
i
a
bl
e
(
r
e
s
u
l
t
)
i
s
c
a
r
e
f
u
ll
y
c
o
n
s
ider
e
d
f
o
r
t
h
e
t
r
a
i
ni
ng
a
n
d
t
e
s
t
da
t
a
.
2.
3.
M
od
e
l
in
g
2.
3.
1.
De
c
is
ion
t
r
e
e
DT
i
s
a
m
e
t
h
o
d
us
e
d
f
o
r
c
l
a
s
s
if
i
c
a
t
i
o
n
t
h
a
t
r
e
pr
e
s
e
n
t
s
da
t
a
i
n
a
t
r
e
e
s
t
r
uc
t
u
r
e
.
E
a
c
h
a
t
tr
i
b
ut
e
(
p
)
i
s
a
n
o
de
i
n
t
h
e
t
r
e
e
,
r
e
pr
e
s
e
n
t
e
d
by
b
r
a
n
c
h
e
s
f
o
r
i
t
s
v
a
l
ue
a
n
d
l
e
a
v
e
s
f
o
r
t
h
e
c
l
a
s
s
[
5]
.
DT
w
o
r
ks
by
d
i
vi
d
i
ng
da
t
a
i
n
t
o
s
m
a
ll
e
r
gr
o
ups
b
a
s
e
d
o
n
a
t
t
r
i
b
ut
e
va
l
ue
s
.
E
n
t
r
o
py
i
s
us
e
d
t
o
m
e
a
s
ur
e
t
h
e
u
n
c
e
r
t
a
i
n
t
y
o
f
da
t
a
(
j
)
a
t
e
a
c
h
b
r
a
n
c
h
d
i
vi
s
i
o
n
(
s
)
.
T
hi
s
pr
o
c
e
s
s
i
s
r
e
pe
a
t
e
d
r
e
c
ur
s
i
ve
l
y
by
d
i
v
i
d
i
ng
t
h
e
gr
o
ups
i
n
t
o
s
m
a
ll
e
r
gr
o
ups
.
T
h
e
pr
o
c
e
s
s
s
t
o
ps
wh
e
n
a
l
l
gr
o
ups
ha
v
e
hi
g
h
h
o
m
o
ge
n
e
i
t
y
.
W
h
e
n
t
h
e
r
e
a
r
e
n
o
m
o
r
e
a
tt
r
i
b
ut
e
s
t
h
a
t
c
a
n
be
us
e
d
to
di
vi
de
t
h
e
gr
o
ups
.
I
n
a
dd
i
t
i
o
n
t
o
e
n
t
r
o
py
(
E
)
,
i
nf
o
r
m
a
t
i
o
n
ga
i
n
(
IG
)
i
s
a
l
s
o
c
a
l
c
u
l
a
t
e
d.
IG
m
e
a
s
ur
e
s
t
h
e
di
f
f
e
r
e
n
c
e
i
n
t
h
e
e
n
t
r
o
py
o
f
da
t
a
b
e
f
o
r
e
a
n
d
a
f
t
e
r
di
vi
d
i
ng
i
t
b
a
s
e
d
o
n
a
f
e
a
t
ur
e
or
a
tt
r
i
b
ut
e
.
A
high
e
r
IG
i
nd
i
c
a
t
e
s
b
e
t
t
e
r
a
n
d
m
o
r
e
i
nf
o
r
m
a
t
i
v
e
s
e
pa
r
a
t
i
o
n
.
(
)
=
∑
log
2
=
1
(
1)
(
)
=
(
)
−
∑
|
|
|
|
=
1
(
)
(
2)
2.
3.
2.
Rand
om
f
or
e
s
t
R
F
i
s
a
s
upe
r
vi
s
e
d
M
L
m
e
t
h
o
d
t
h
a
t
us
e
s
DT
tec
hni
que
s
t
o
c
a
t
e
g
o
r
i
z
e
da
t
a
[
22]
.
T
hi
s
m
e
t
h
o
d
co
n
s
i
s
t
s
o
f
a
c
o
l
l
e
c
t
i
o
n
o
f
DT
s
t
h
a
t
a
r
e
t
r
a
i
n
e
d
r
a
ndo
m
ly
a
n
d
a
s
s
i
g
n
l
a
b
e
l
s
t
o
e
a
c
h
l
e
a
f
n
o
de
.
E
a
c
h
DT
i
n
t
h
e
s
e
t
i
s
b
u
il
t
us
i
ng
d
if
f
e
r
e
n
t
da
t
a
f
r
o
m
t
h
e
o
r
i
g
i
na
l
d
a
t
a
s
e
t.
R
F
us
e
s
a
m
a
j
o
r
i
t
y
v
o
t
e
to
de
t
e
r
m
i
ne
t
h
e
f
in
a
l
l
a
b
e
l
.
T
h
e
t
w
o
m
o
s
t
c
r
uc
i
a
l
pa
r
a
m
e
t
e
r
s
i
n
R
F
a
r
e
n
t
r
e
e
a
n
d
m
t
r
y
.
“
n
t
r
e
e
”
de
f
i
ne
s
t
h
e
n
u
m
be
r
o
f
t
r
e
e
s
i
n
t
he
m
o
de
l
,
a
n
d
“
m
t
r
y
”
de
f
i
ne
s
h
o
w
m
a
ny
l
a
b
e
l
s
a
r
e
r
e
qu
i
r
e
d
i
n
e
a
c
h
s
t
e
p.
T
h
e
s
e
t
wo
pa
r
a
m
e
t
e
r
s
pr
o
duc
e
t
h
e
e
x
p
l
a
i
ne
d
v
a
r
i
a
n
c
e
a
n
d
p
e
r
c
e
n
t
a
ge
e
r
r
o
r
r
a
t
e
.
T
hi
s
m
e
t
h
o
d
ha
s
s
e
v
e
r
a
l
a
d
va
n
t
a
ge
s
,
i
n
c
l
ud
i
ng
hi
g
h
a
c
c
ur
a
c
y
,
r
e
s
i
s
t
a
n
c
e
to
o
v
e
r
f
i
t
t
i
n
g,
a
n
d
e
f
f
o
r
t
l
e
s
s
i
n
t
e
r
pr
e
t
a
t
i
o
n
.
T
h
e
pr
o
c
e
s
s
o
f
h
o
w
R
F
wo
r
ks
c
a
n
b
e
e
x
p
l
a
i
ne
d
i
n
t
h
e
f
o
l
l
o
w
i
ng
s
t
e
ps
:
S
t
e
p
1:
r
a
n
do
m
l
y
s
e
l
e
c
t
j
s
a
m
p
l
e
s
f
r
o
m
t
h
e
t
r
a
i
ni
ng
da
t
a
s
e
t
us
i
n
g
b
o
ot
s
t
r
a
p
r
e
s
a
m
p
l
i
ng
w
i
t
h
r
e
p
l
a
c
e
men
t
.
S
t
e
p
2:
r
a
n
do
m
l
y
s
e
l
e
c
t
m
a
tt
r
i
b
ut
e
s
f
r
o
m
p
a
tt
r
i
b
ut
e
s
(
wh
e
r
e
m
p
).
S
t
e
p
3:
c
o
n
s
t
r
uc
t
a
DT
a
n
d
t
h
e
n
s
p
li
t
t
h
e
b
e
s
t
n
o
de
(
s
)
f
r
o
m
t
h
e
DT
us
i
n
g
t
h
e
G
i
ni
i
n
d
e
x
:
(
)
=
1
−
∑
2
=
1
(
3)
S
t
e
p
4:
r
e
pe
a
t
s
t
e
ps
1
-
3
un
t
i
l
a
f
o
r
e
s
t
o
f
n
t
r
e
e
s
(
n
t
r
e
e
)
i
s
f
o
r
m
e
d
a
n
d
t
h
e
o
p
t
i
m
a
l
m
t
r
y
i
s
o
b
t
a
i
n
e
d.
S
t
e
p
5:
u
s
e
a
m
a
j
o
r
i
t
y
v
ot
e
to
de
t
e
r
m
i
ne
t
h
e
l
a
b
e
l
o
f
a
l
e
a
f
n
o
de
(
c
l
a
s
s
)
.
2.
3.
3.
E
x
t
r
e
m
e
g
r
ad
ient
b
oos
t
in
g
XG
B
i
s
a
n
e
ns
e
m
b
l
e
M
L
m
e
t
h
o
d
us
e
d
f
o
r
c
l
a
s
s
i
f
ica
t
i
o
n
a
n
d
r
e
gr
e
s
s
i
o
n
t
a
s
ks
.
I
t
u
t
i
l
i
z
e
s
t
h
e
o
u
t
pu
t
s
o
f
m
u
l
t
i
p
l
e
DT
t
o
c
r
e
a
t
e
a
m
o
r
e
pr
e
c
i
s
e
a
n
d
r
o
b
us
t
m
o
de
l
[
24]
.
I
n
t
h
e
XG
B
m
e
t
h
o
d,
e
a
c
h
DT
i
s
t
r
a
i
n
e
d
t
o
r
e
duc
e
t
h
e
pr
e
di
c
t
i
o
n
e
r
r
o
r
o
f
t
h
e
pr
e
vi
o
us
m
o
de
l
.
T
h
e
n
e
w
ly
a
dde
d
DT
l
e
a
r
ns
f
r
o
m
t
h
e
pr
e
di
c
t
i
o
n
e
r
r
or
s
i
nc
ur
r
e
d
by
t
h
e
pr
e
vi
o
u
s
m
o
de
l
a
n
d
t
r
i
e
s
to
m
i
n
im
i
z
e
t
h
o
s
e
e
r
r
o
r
s
.
XG
B
h
a
s
s
e
v
e
r
a
l
a
d
va
n
t
a
ge
s
,
i
n
c
l
ud
i
ng
hi
g
h
e
f
f
i
c
i
e
n
c
y
,
a
c
c
ur
a
c
y
,
a
n
d
s
t
a
bil
i
t
y
.
T
h
e
s
e
a
r
e
t
h
e
s
t
e
ps
f
o
r
b
u
i
l
d
i
ng
a
n
XG
B
m
o
de
l
:
S
t
e
p
1:
s
e
t
t
h
e
i
ni
t
i
a
l
pr
e
d
i
c
t
i
o
n
pr
o
b
a
bi
li
t
y
(
Pr
i
)
a
s
t
h
e
b
a
s
e
o
u
t
pu
t
,
wi
t
h
i
=
1,
2
,
…
,
n
.
S
t
e
p
2:
c
o
m
put
e
t
h
e
r
e
s
i
dua
l
e
r
r
o
r
(
RE
)
b
a
s
e
d
o
n
th
e
a
c
t
ua
l
o
u
t
pu
t
(
Y
i
).
=
−
(
4)
S
t
e
p
3:
c
o
n
s
t
r
uc
t
a
bi
n
a
r
y
DT
.
S
t
e
p
4:
e
v
a
l
ua
t
e
t
h
e
s
i
mi
l
a
r
i
t
y
s
c
o
r
e
(
SS
).
=
(
∑
=
1
)
2
∑
(
1
−
)
=
1
+
(
5)
S
t
e
p
5:
d
e
t
e
r
m
i
ne
t
h
e
Gain
f
o
r
e
a
c
h
a
tt
r
i
b
ut
e
.
S
e
l
e
c
t
t
h
e
a
tt
r
i
b
ut
e
wi
t
h
t
h
e
hi
g
h
e
s
t
Gain
to
b
u
i
l
d
t
h
e
DT
.
(
)
=
+
ℎ
−
(
6)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2
5
0
2
-
4
7
52
In
do
n
e
s
i
a
n
J
E
l
e
c
E
n
g
&
C
o
m
p
S
c
i
,
Vo
l
.
3
8
,
N
o
.
1
,
A
pr
i
l
20
2
5
:
569
-
57
7
572
S
t
e
p
6:
e
x
pa
n
d
t
h
e
DT
a
n
d
de
t
e
r
m
i
ne
t
h
e
l
e
a
f
o
u
t
p
ut
(
Lo
)
by
a
pp
ly
i
ng
o
pt
i
mi
z
a
t
i
o
n
pa
r
a
m
e
t
e
r
s
(
).
=
∑
=
1
∑
(
1
−
)
=
1
+
(
7)
S
t
e
p
7:
c
a
l
c
u
l
a
t
e
t
h
e
l
o
g
o
dds
v
a
l
ue
o
f
t
h
e
ba
s
e
m
o
de
l
.
log
=
log
(
1
−
)
(
8)
S
t
e
p
8:
c
o
m
put
e
n
e
w
pr
o
b
a
bil
i
t
i
e
s
f
o
r
e
a
c
h
r
e
c
o
r
d
a
n
d
n
o
r
m
a
li
z
e
t
h
e
m
us
i
ng
t
h
e
l
e
a
r
ni
ng
r
a
t
e
(
).
+
1
=
log
+
.
(
9)
S
t
e
p
9:
s
t
a
n
da
r
d
i
z
e
t
h
e
pr
o
b
a
bil
i
t
y
va
l
ue
us
i
ng
t
h
e
bi
na
r
y
s
i
g
m
o
i
d
f
u
n
c
t
i
o
n
(
Sig
).
(
+
1
)
=
+
1
1
+
+
1
(
10)
S
t
e
p
10:
r
e
c
a
l
c
u
l
a
t
e
t
h
e
R
E
us
i
n
g
t
h
e
n
e
w
+
1
a
n
d
r
e
pe
a
t
t
h
e
pr
o
c
e
s
s
f
r
o
m
s
t
e
p
2
to
s
t
e
p
9
to
c
r
e
a
t
e
a
n
e
w
DT
.
2.
3.
4.
H
yp
e
r
p
ar
a
m
e
t
e
r
T
h
e
hy
pe
r
pa
r
a
m
e
t
e
r
f
i
ne
-
t
uni
n
g
p
h
a
s
e
i
s
c
r
uc
i
a
l
i
n
de
t
e
r
m
i
ni
ng
t
h
e
o
pt
i
m
a
l
m
o
de
l
pa
r
a
m
e
t
e
r
s
b
e
f
o
r
e
t
h
e
t
r
a
i
ni
ng
pr
o
c
e
s
s
b
e
g
i
ns
[
25]
.
E
a
c
h
m
o
de
l
i
nv
o
lv
e
s
uni
que
s
e
t
s
o
f
hy
pe
r
pa
r
a
m
e
t
e
r
s
[
28
]
.
T
h
e
‘
m
l
r
’
l
i
b
r
a
r
y
i
n
R
wa
s
us
e
d
t
o
o
p
t
i
mi
z
e
t
h
e
s
e
hy
pe
r
pa
r
a
m
e
t
e
r
s
.
2.
4.
E
val
u
at
ion
2.
4.
1.
Conf
u
s
ion
m
at
r
ix
Co
nf
us
i
o
n
m
a
t
r
i
x
(
CM
)
c
o
n
s
i
s
t
s
o
f
f
o
ur
c
a
t
e
g
o
r
i
e
s
:
t
r
ue
p
o
s
i
t
i
v
e
(
T
P
)
,
f
a
l
s
e
po
s
i
t
i
v
e
(
F
P
)
,
tr
ue
n
e
ga
t
i
v
e
(
T
N)
,
a
n
d
f
a
l
s
e
n
e
ga
t
i
v
e
(
F
N)
a
s
pr
e
s
e
nt
e
d
i
n
T
a
bl
e
2
[
22]
.
C
M
i
s
t
h
e
b
a
s
i
s
f
o
r
a
s
s
e
s
s
i
ng
s
e
v
e
r
a
l
v
a
l
i
da
t
i
o
n
m
e
tr
i
c
s
a
s
pr
e
s
e
n
t
e
d
i
n
T
a
bl
e
3
,
s
uc
h
a
s
a
c
c
u
r
a
c
y
(
1
)
,
p
r
e
c
i
s
i
o
n
(
2
)
,
s
e
n
s
i
t
i
vi
t
y
(
3
)
,
a
n
d
s
pe
c
i
f
i
c
i
t
y
(
4
)
,
t
h
a
t
a
r
e
us
e
d
to
e
v
a
l
u
a
t
e
m
o
de
l
s
[
29]
.
P
r
e
c
i
s
i
o
n
i
s
a
m
e
t
r
i
c
t
o
m
e
a
s
ur
e
t
h
e
r
a
t
i
o
o
f
c
o
r
r
e
c
t
po
s
i
t
i
v
e
pr
e
d
i
c
t
i
o
n
s
.
M
e
a
n
w
hil
e
,
s
e
n
s
i
t
i
v
i
t
y
m
e
a
s
ur
e
s
t
h
e
m
o
de
l
’
s
a
bil
i
t
y
t
o
i
de
n
t
i
f
y
a
ll
po
s
i
t
i
v
e
c
a
s
e
s
.
S
pe
c
i
f
i
c
i
t
y
,
o
n
t
h
e
ot
h
e
r
h
a
n
d,
i
d
e
n
t
i
f
i
e
s
t
r
ue
n
e
ga
t
i
v
e
r
e
s
u
l
t
s
.
A
c
c
ur
a
c
y
m
e
a
s
ur
e
s
t
h
e
r
a
t
i
o
o
f
c
o
r
r
e
c
t
pr
e
di
c
t
i
o
n
s
,
b
o
t
h
po
s
i
t
i
v
e
a
n
d
n
e
ga
t
i
v
e
,
o
u
t
o
f
a
l
l
t
he
da
t
a
.
I
t
i
s
i
m
po
r
t
a
n
t
to
s
e
l
e
c
t
a
ppr
o
p
r
i
a
t
e
m
e
t
r
i
c
s
b
a
s
e
d
o
n
s
pe
c
i
f
ic
s
c
e
n
a
r
i
o
s
to
e
v
a
l
ua
t
e
t
h
e
m
o
de
l
’
s
pe
r
f
o
r
m
a
nc
e
a
c
c
ur
a
t
e
l
y
.
T
a
bl
e
2.
T
h
e
c
o
n
f
u
s
i
o
n
m
a
t
r
i
x
A
c
tu
a
l
“
W
o
r
th
y
”
A
c
tu
a
l
“
U
nw
o
r
th
y
”
P
r
e
di
c
t
e
d
“
W
o
r
th
y
”
TP
FP
P
r
e
di
c
t
e
d
“
U
nw
o
r
th
y
”
FN
TN
T
a
bl
e
3.
T
h
e
v
a
li
da
t
i
o
n
m
e
t
r
i
c
s
M
e
tr
i
c
s
E
qua
ti
o
n
A
c
c
u
r
a
c
y
+
/
(
+
+
+
)
(
1)
P
r
e
c
is
i
o
n
/
(
+
)
(
2)
S
e
ns
it
i
v
it
y
/
(
+
)
(
3)
S
pe
c
i
f
i
c
it
y
/
(
+
)
(
4)
2.
4.
2.
Ar
e
a
u
n
d
e
r
t
h
e
r
e
c
e
ive
r
op
e
r
at
in
g
c
h
ar
ac
t
e
r
is
t
ic
s
c
u
r
ve
a
r
e
a
un
de
r
t
h
e
r
e
c
e
i
v
e
r
o
pe
r
a
t
i
n
g
c
h
a
r
a
c
t
e
r
i
s
t
i
c
(
A
U
R
OC
)
i
s
a
m
e
t
r
i
c
us
e
d
to
e
v
a
l
ua
t
e
t
h
e
o
v
e
r
a
l
l
pe
r
f
o
r
m
a
n
c
e
o
f
a
c
l
a
s
s
if
i
c
a
t
i
o
n
s
y
s
t
e
m
.
I
t
de
t
e
r
m
in
e
s
a
t
h
r
e
s
h
o
l
d
v
a
l
u
e
a
n
d
m
e
a
s
ur
e
s
t
h
e
m
o
de
l
’
s
a
bil
i
t
y
t
o
d
i
f
f
e
r
e
n
t
i
a
t
e
b
e
t
we
e
n
t
w
o
c
l
a
s
s
e
s
o
r
gr
o
ups
a
c
c
ur
a
te
l
y
.
I
n
a
m
u
l
t
i
-
c
l
a
s
s
s
t
ud
y
,
a
“
po
s
i
t
i
ve
”
c
l
a
s
s
i
s
de
s
i
g
n
a
t
e
d,
a
n
d
t
h
e
r
e
m
a
i
n
i
ng
c
l
a
s
s
e
s
a
r
e
de
f
i
ne
d
a
s
“
n
e
ga
t
i
v
e
.
”
T
h
e
A
UR
OC
va
l
ue
o
f
a
m
o
de
l
i
nc
r
e
a
s
e
s
a
s
i
t
s
a
c
c
ur
a
c
y
i
n
pr
e
d
i
c
t
i
n
g
t
h
e
c
l
a
s
s
im
pr
o
v
e
s
,
w
i
t
h
a
v
a
l
ue
c
l
o
s
e
r
to
1
i
n
d
i
c
a
t
i
n
g
be
tt
e
r
a
c
c
ur
a
c
y
[
30]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
do
n
e
s
i
a
n
J
E
l
e
c
E
n
g
&
C
o
m
p
S
c
i
I
S
S
N:
2
5
0
2
-
4
7
52
T
r
e
e
-
bas
e
d
mode
ls
and
hy
pe
r
par
a
me
ter
opti
miz
ati
on
…
(
R
e
ndr
a
Gus
tr
ians
y
ah
)
573
2.
4.
3.
K
ap
p
a
c
oe
f
f
icie
n
t
KC
i
s
u
s
e
d
to
qua
n
t
i
f
y
i
n
t
e
r
-
r
a
t
e
r
r
e
l
i
a
bi
li
t
y
o
r
a
gr
e
e
m
e
n
t
b
e
t
we
e
n
a
nn
o
t
a
to
r
s
wh
e
n
pe
r
f
o
r
m
i
ng
a
c
l
a
s
s
if
i
c
a
t
i
o
n
t
a
s
k.
K
C
c
a
n
be
ut
i
l
i
z
e
d
f
o
r
c
l
a
s
s
i
f
ica
t
i
o
n
t
a
s
ks
i
nv
o
l
vi
ng
s
e
v
e
r
a
l
c
l
a
s
s
e
s
o
r
i
m
ba
l
a
n
c
e
d
c
l
a
s
s
d
i
s
t
r
i
b
ut
i
o
n
s
.
T
h
e
c
o
e
f
f
i
c
i
e
n
t
v
a
l
ue
s
a
r
e
0
f
o
r
l
o
w
a
gr
e
e
m
e
n
t
a
n
d
1
f
o
r
pe
r
f
e
c
t
a
gr
e
e
m
e
n
t
[
31]
.
I
t
i
s
im
p
o
r
t
a
n
t
to
n
ot
e
t
h
a
t
t
h
e
K
C
s
h
o
u
l
d
o
nly
b
e
us
e
d
to
m
e
a
s
ur
e
o
u
t
c
o
m
e
s
t
h
a
t
i
nv
o
l
v
e
qua
li
t
a
t
i
ve
(
c
a
t
e
g
o
r
i
c
a
l
)
da
ta.
3.
RE
S
UL
T
S
AN
D
DI
S
CU
S
S
I
ON
3.
1.
Dat
a
u
n
d
e
r
s
t
an
d
in
g
I
n
t
hi
s
ph
a
s
e
,
t
h
e
c
l
a
s
s
c
o
m
po
s
i
t
i
o
n
o
f
t
h
e
t
a
r
ge
t
v
a
r
i
a
bl
e
(
r
e
s
u
l
t
)
i
s
pr
e
s
e
n
t
e
d
f
o
r
t
h
e
218
e
m
p
l
o
y
e
e
s
i
n
t
h
e
da
t
a
s
e
t
i
n
T
a
bl
e
4.
T
h
e
r
e
s
ul
t
s
i
n
d
i
c
a
t
e
t
h
a
t
t
h
e
c
l
a
s
s
c
o
m
po
s
i
t
i
o
n
i
s
r
e
l
a
t
i
v
e
ly
b
a
l
a
nc
e
d
a
m
o
n
g
t
h
e
d
i
f
f
e
r
e
n
t
c
l
a
s
s
e
s
.
B
e
s
i
de
s
,
t
h
e
r
e
l
a
t
i
o
n
s
hi
p
s
b
e
t
we
e
n
v
a
r
i
a
bl
e
s
a
r
e
s
h
o
wn
i
n
F
i
gur
e
2.
T
h
e
r
e
s
u
l
t
s
de
m
o
n
s
t
r
a
t
e
t
h
a
t
t
h
e
e
duc
a
t
i
o
n
va
r
i
a
bl
e
m
o
s
t
do
m
i
na
n
t
l
y
i
n
f
l
u
e
n
c
e
s
t
h
e
r
e
s
u
l
t
v
a
r
i
a
bl
e
.
I
t
c
a
n
a
s
s
i
s
t
i
n
de
t
e
r
m
ini
ng
t
h
e
r
oot
v
a
r
i
a
bl
e
f
o
r
t
h
e
DT
a
n
d
R
F
m
e
t
h
o
ds
.
T
a
bl
e
4.
T
h
e
c
l
a
s
s
c
o
m
po
s
i
t
i
o
n
o
f
t
h
e
r
e
s
u
l
t
v
a
r
i
a
bl
e
W
o
r
th
y
U
nw
o
r
th
y
N
o
of
e
mpl
oy
e
e
128
90
F
i
gur
e
2.
T
h
e
r
e
l
a
t
i
o
n
s
hi
p
s
b
e
t
we
e
n
va
r
i
a
bl
e
s
3.
2.
Dat
a
p
r
e
p
ar
at
ion
I
n
t
hi
s
p
h
a
s
e
,
ve
r
i
f
i
c
a
t
i
o
n
i
s
pe
r
f
o
r
m
e
d
f
o
r
e
m
pt
y
a
n
d
n
u
ll
da
t
a
.
T
h
e
r
e
i
s
n
o
da
t
a
r
e
duc
t
i
o
n
i
n
t
hi
s
ph
a
s
e
.
F
ur
t
h
e
r
m
o
r
e
,
t
h
e
da
t
a
s
e
t
i
s
r
a
n
do
m
ly
pa
r
t
i
t
i
o
n
e
d
i
n
t
o
t
r
a
i
ni
ng
a
n
d
t
e
s
t
i
n
g
d
a
t
a
i
n
a
r
a
t
i
o
of
80:20.
T
h
e
c
l
a
s
s
b
a
l
a
n
c
e
f
o
r
e
a
c
h
da
t
a
s
e
t
i
s
v
e
r
i
f
i
e
d
t
o
m
i
n
im
i
z
e
a
ny
bi
a
s
.
F
i
gur
e
3
i
ll
us
t
r
a
t
e
s
t
h
e
c
l
a
s
s
c
om
po
s
i
t
i
o
n
o
f
t
h
e
r
e
s
u
l
t
v
a
r
i
a
bl
e
f
o
r
b
ot
h
t
h
e
tr
a
i
ni
n
g
a
n
d
t
e
s
ti
ng
da
t
a
.
F
i
gur
e
3(
a
)
de
p
i
c
t
s
a
c
l
a
s
s
c
o
m
po
s
i
t
i
o
n
o
f
59:41
f
o
r
t
h
e
t
r
a
i
ni
ng
da
t
a
,
whi
l
e
F
i
gur
e
3(
b
)
s
h
o
ws
a
s
l
i
g
h
t
l
y
im
pr
o
v
e
d
c
l
a
s
s
c
o
m
po
s
i
t
i
o
n
f
o
r
t
h
e
t
e
s
t
i
n
g
da
t
a
.
Ho
we
v
e
r
,
b
ot
h
c
o
m
po
s
i
t
i
o
n
s
i
nd
i
c
a
t
e
t
h
a
t
t
h
e
c
l
a
s
s
c
o
m
po
s
i
t
i
o
n
i
s
r
e
l
a
t
i
v
e
ly
ba
l
a
n
c
e
d.
(
a
)
(
b
)
F
i
gur
e
3.
T
h
e
c
l
a
s
s
c
o
m
po
s
i
t
i
o
n
o
f
t
h
e
r
e
s
u
l
t
v
a
r
i
a
bl
e
f
o
r
(
a
)
t
r
a
i
ni
ng
da
t
a
a
n
d
(
b
)
t
e
s
t
da
t
a
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2
5
0
2
-
4
7
52
In
do
n
e
s
i
a
n
J
E
l
e
c
E
n
g
&
C
o
m
p
S
c
i
,
Vo
l
.
3
8
,
N
o
.
1
,
A
pr
i
l
20
2
5
:
569
-
57
7
574
3.
3.
Hyp
e
r
p
ar
a
m
e
t
e
r
o
p
t
im
i
z
at
ion
T
h
e
o
p
t
i
m
a
l
hy
pe
r
pa
r
a
m
e
t
e
r
c
o
nf
i
gur
a
t
i
o
ns
o
b
t
a
i
n
e
d
us
i
ng
t
h
e
‘
ml
r
’
l
i
br
a
r
y
f
o
r
e
a
c
h
m
o
de
l
a
r
e
li
s
t
e
d
i
n
T
a
bl
e
5.
T
h
e
hy
pe
r
pa
r
a
m
e
t
e
r
s
f
i
ne
-
t
uni
n
g
f
o
r
t
h
e
D
T
a
n
d
R
F
m
e
t
h
o
ds
i
s
s
t
r
a
i
g
h
t
f
o
r
wa
r
d.
I
n
c
o
n
t
r
a
s
t
,
t
h
e
XG
B
m
e
t
h
o
d
’
s
hy
pe
r
pa
r
a
m
e
t
e
r
f
i
ne
-
t
uni
ng
i
s
m
o
r
e
c
o
m
pr
e
h
e
ns
i
ve
.
T
a
bl
e
5.
T
h
e
hy
pe
r
pa
r
a
m
e
t
e
r
s
f
i
ne
-
t
uni
n
g
i
n
ML
m
e
t
h
o
ds
M
e
th
o
d
H
y
p
e
r
pa
r
a
m
e
t
e
r
s
DT
M
a
x
de
pt
h=
23,
c
p=
0.009, mi
ns
pl
it
=
8
RF
N
tr
e
e
=
10, mt
r
y
=
2
X
G
B
E
ta
=
0.379, ma
x
_de
p
th
=
3, mi
n_c
hi
ld
_w
e
ig
ht
=
2.59,
c
o
ls
a
mpl
e
_
b
y
tr
e
e
=
0.969,
c
o
ls
a
mpl
e
_b
y
l
e
ve
l=
0.863, s
ubs
a
mpl
e
=
0.966, nr
o
unds
=
139, boo
s
te
r
=
gbt
r
e
e
3.
4.
E
val
u
at
ion
W
e
e
m
p
l
o
y
e
d
C
M
,
A
UC
R
OC
,
a
n
d
KC
to
a
s
s
e
s
s
t
h
e
pe
r
f
o
r
m
a
n
c
e
o
f
t
h
e
c
l
a
s
s
i
f
i
c
a
t
i
o
n
m
o
de
l
s
.
T
h
e
C
M
d
e
l
i
ne
a
t
e
s
t
h
e
c
l
a
s
s
if
i
c
a
t
i
o
n
pe
r
f
o
r
m
a
n
c
e
o
f
e
a
c
h
m
o
de
l
us
i
ng
t
h
e
t
e
s
t
da
t
a
,
a
s
de
p
i
c
t
e
d
i
n
F
i
gur
e
4.
F
i
gur
e
s
4(
a
)
a
n
d
4(
b
)
e
x
e
m
p
l
if
y
t
h
e
C
M
r
e
s
u
l
t
s
f
o
r
t
h
e
DT
a
n
d
R
F
m
o
de
l
s
;
c
o
nv
e
r
s
e
ly
,
F
i
gur
e
4(
c
)
i
l
lus
t
r
a
t
e
s
t
h
e
m
a
r
g
i
n
a
ll
y
d
i
f
f
e
r
e
n
t
C
M
y
i
e
l
de
d
by
t
h
e
X
GB
m
o
de
l
.
I
n
a
dd
i
t
i
o
n
,
t
h
e
A
UR
O
C
r
e
s
u
l
t
s
f
o
r
e
a
c
h
m
o
de
l
a
r
e
de
pi
c
t
e
d
i
n
F
i
gur
e
5.
F
i
gur
e
s
5(
a
)
-
5(
c
)
p
r
e
s
e
n
t
t
h
e
A
UR
O
C
v
a
l
ue
s
f
o
r
t
h
e
DT
,
R
F
,
a
n
d
XG
B
m
o
de
l
s
,
a
l
l
o
f
whi
c
h
a
r
e
n
o
t
a
bl
y
hi
g
h
(
a
b
o
v
e
90%
)
.
Ho
we
v
e
r
,
t
h
e
A
UR
O
C
a
c
hi
e
ve
d
by
t
h
e
R
F
m
o
de
l
o
u
t
pe
r
f
o
r
m
s
t
h
e
ot
h
e
r
t
w
o
m
o
de
l
s
.
(
a
)
(
b
)
(
c
)
F
i
gur
e
4.
T
h
e
C
M
f
o
r
:
(
a
)
DT
,
(
b
)
R
F
,
a
n
d
(
b
)
XG
B
m
o
de
l
s
(
a
)
(
b
)
(
c
)
F
i
gur
e
5.
T
h
e
A
UR
OC
f
o
r
:
(
a
)
DT
,
(
b
)
R
F
,
a
n
d
(
b
)
XG
B
m
o
de
l
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
do
n
e
s
i
a
n
J
E
l
e
c
E
n
g
&
C
o
m
p
S
c
i
I
S
S
N:
2
5
0
2
-
4
7
52
T
r
e
e
-
bas
e
d
mode
ls
and
hy
pe
r
par
a
me
ter
opti
miz
ati
on
…
(
R
e
ndr
a
Gus
tr
ians
y
ah
)
575
B
a
s
e
d
o
n
C
M
,
a
c
c
ur
a
c
y
,
pr
e
c
i
s
i
o
n
,
s
e
ns
i
t
i
vi
t
y
,
a
nd
s
pe
c
i
f
i
c
i
t
y
m
e
t
r
i
c
s
c
a
n
b
e
de
t
e
r
m
i
ne
d
f
o
r
e
a
c
h
m
o
de
l
.
F
ur
t
h
e
r
m
o
r
e
,
t
h
e
e
v
a
l
u
a
t
i
o
n
r
e
s
u
l
t
s
b
a
s
e
d
o
n
m
e
t
r
i
c
s
f
o
r
e
a
c
h
m
o
de
l
a
r
e
s
h
o
wn
i
n
T
a
bl
e
6.
T
h
e
s
e
r
e
s
u
l
t
s
pr
o
v
e
t
h
a
t
R
F
h
a
s
b
e
t
t
e
r
pe
r
f
o
r
m
a
n
c
e
t
h
a
n
DT
a
n
d
XG
B
.
B
e
c
a
us
e
i
t
g
ot
t
h
e
b
e
s
t
s
c
o
r
e
s
o
n
t
h
r
e
e
m
e
t
r
i
c
s
:
s
e
ns
i
t
i
vi
t
y
,
A
U
R
OC
,
a
n
d
K
C
.
M
e
a
n
w
hil
e
,
DT
a
n
d
XG
B
a
r
e
o
nl
y
s
upe
r
i
o
r
i
n
t
w
o
m
e
t
r
i
c
s
.
T
a
bl
e
6.
T
h
e
e
v
a
l
ua
t
i
o
n
r
e
s
u
l
t
s
M
e
tr
i
c
s
DT
RF
X
G
B
A
c
c
u
r
a
c
y
0.9318
0.9318
0.9318
S
e
ns
it
i
v
it
y
1.0000
1.0000
0.9000
P
r
e
c
is
i
o
n
0.8929
0.8929
1.0000
S
pe
c
i
f
i
c
it
y
0.8421
0.8421
1.0000
A
U
R
O
C
0.9211
0.9874
0.9500
KC
0.8584
0.8584
0.8514
I
f
o
b
s
e
r
v
e
d,
t
h
e
a
c
c
ur
a
c
y
l
e
ve
l
f
o
r
a
l
l
t
h
r
e
e
t
r
e
e
-
b
a
s
e
d
m
o
de
l
s
i
s
t
h
e
s
a
m
e
,
i
n
d
i
c
a
t
i
n
g
t
h
a
t
t
h
e
a
c
c
ur
a
c
y
m
e
t
r
i
c
c
a
nn
o
t
b
e
ut
i
li
z
e
d
t
o
m
e
a
s
ur
e
m
o
de
l
pe
r
f
o
r
m
a
n
c
e
.
I
n
a
dd
i
t
i
o
n
,
t
h
e
C
M
a
ppr
o
a
c
h
us
e
d
i
s
n
o
t
a
ppr
o
p
r
i
a
t
e
i
f
we
c
o
m
pa
r
e
t
h
e
DT
a
n
d
R
F
a
s
t
h
e
y
b
ot
h
pr
o
duc
e
t
h
e
s
a
m
e
pe
r
f
o
r
m
a
n
c
e
.
Ho
we
v
e
r
,
a
dd
i
t
i
o
n
a
l
s
t
udi
e
s
w
i
t
h
v
a
r
i
o
us
da
t
a
s
e
t
s
a
r
e
n
e
e
de
d
t
o
s
uppor
t
t
hi
s
c
o
n
c
l
u
s
i
o
n
.
I
n
t
hi
s
c
a
s
e
,
t
h
e
A
U
R
OC
m
e
t
r
i
c
i
s
t
h
e
m
o
s
t
a
ppr
o
p
r
i
a
t
e
f
o
r
m
e
a
s
ur
i
ng
m
o
de
l
pe
r
f
o
r
m
a
n
c
e
a
s
i
t
s
h
o
ws
t
h
e
r
e
s
u
l
t
s
’
d
i
f
f
e
r
e
n
t
i
a
t
i
o
n
.
T
h
e
pr
o
p
o
s
e
d
m
e
t
h
o
d
i
n
t
hi
s
s
t
ud
y
s
h
o
ws
s
upe
r
i
o
r
pe
r
f
o
r
m
a
n
c
e
(
a
c
c
ur
a
c
y
)
c
o
m
pa
r
e
d
to
p
r
e
vi
o
us
s
t
ud
i
e
s
[
5]
,
[
6
]
.
T
hi
s
s
t
ud
y
a
l
s
o
f
o
un
d
t
h
a
t
R
F
a
s
a
t
r
e
e
-
b
a
s
e
d
m
o
de
l
i
n
M
L
h
a
s
wo
r
ke
d
b
e
tt
e
r
to
s
o
l
v
e
e
m
p
l
o
y
e
e
pe
r
f
o
r
m
a
n
c
e
a
s
s
e
s
s
m
e
n
t
i
s
s
ue
s
.
T
h
e
R
F
m
o
de
l
u
s
e
s
a
c
o
m
bi
na
t
i
o
n
o
f
m
a
ny
t
r
e
e
s
t
o
pr
o
duc
e
m
o
r
e
a
c
c
ur
a
t
e
a
n
d
r
o
b
us
t
r
e
s
u
l
t
s
c
o
m
pa
r
e
d
t
o
t
h
e
DT
m
e
t
h
o
d.
M
e
a
n
w
hil
e
,
t
h
e
XG
B
m
e
t
h
o
d
b
u
il
ds
t
r
e
e
s
o
n
e
by
o
n
e
a
n
d
us
e
s
e
a
c
h
n
e
w
t
r
e
e
to
c
o
r
r
e
c
t
m
i
s
t
a
ke
s
m
a
de
by
t
h
e
pr
e
vi
o
u
s
t
r
e
e
,
r
e
s
u
l
t
i
n
g
i
n
hi
g
hly
a
c
c
ur
a
t
e
m
o
de
l
s
.
Ho
we
v
e
r
,
XG
B
m
a
y
r
e
qu
i
r
e
m
o
r
e
s
e
n
s
i
t
i
v
i
t
y
a
n
d
a
d
j
us
t
m
e
n
t
c
o
m
pa
r
e
d
to
R
F
.
T
r
e
e
-
b
a
s
e
d
m
o
de
l
s
i
n
ML
w
i
t
h
hy
pe
r
pa
r
a
m
e
t
e
r
opt
i
mi
z
a
t
i
o
n
h
a
v
e
pr
o
duc
e
d
e
x
c
e
ll
e
n
t
pe
r
f
o
r
m
a
n
c
e
i
n
a
s
s
e
s
s
i
ng
t
h
e
pe
r
f
o
r
m
a
n
c
e
o
f
D
K
P
e
m
p
l
o
y
e
e
s
in
P
a
l
e
m
ba
n
g
c
i
t
y
.
T
h
e
s
e
f
i
nd
i
ngs
c
o
u
l
d
b
e
a
f
o
u
nda
t
i
o
n
a
l
s
t
e
p
f
o
r
f
ut
ur
e
r
e
s
e
a
r
c
h
.
Ho
we
v
e
r
,
t
hi
s
s
t
ud
y
ha
s
l
im
i
t
a
t
i
o
ns
a
s
i
t
i
s
a
s
pe
c
i
f
i
c
c
a
s
e
s
t
udy
.
T
h
e
r
e
f
o
r
e
,
t
h
e
r
e
s
u
l
t
s
m
u
s
t
b
e
ge
n
e
r
a
li
z
e
d
by
im
p
l
e
m
e
n
t
i
n
g
t
h
e
m
i
n
v
a
r
i
o
us
o
t
h
e
r
c
a
s
e
s
.
I
n
a
dd
i
t
i
o
n
,
v
a
r
i
a
bl
e
s
e
l
e
c
t
i
o
n
m
e
t
h
o
ds
c
a
n
a
l
s
o
b
e
t
r
i
e
d
t
o
e
n
h
a
nc
e
t
h
e
m
o
de
l
’
s
r
e
s
u
l
t
s
a
n
d
ga
i
n
a
be
tt
e
r
pe
r
s
pe
c
t
i
v
e
o
n
c
r
uc
i
a
l
v
a
r
i
a
bl
e
s
.
4.
CONC
L
USI
ON
T
hi
s
s
t
ud
y
hi
g
hl
i
g
h
t
s
t
h
e
s
i
g
n
i
f
i
c
a
nc
e
o
f
us
i
ng
t
r
e
e
-
b
a
s
e
d
m
o
de
l
s
i
n
M
L
t
e
c
hni
que
s
s
uc
h
a
s
DT
,
R
F
,
a
n
d
XG
B
i
n
e
va
l
ua
t
i
n
g
e
m
p
l
o
y
e
e
pe
r
f
o
r
m
a
nc
e
f
o
r
t
h
e
P
a
l
e
m
ba
n
g
c
i
t
y
F
R
S
.
T
h
e
r
e
s
e
a
r
c
h
f
i
nd
i
n
g
s
i
nd
i
c
a
t
e
t
h
a
t
tr
e
e
-
b
a
s
e
d
m
o
de
l
s
i
n
M
L
e
xhi
b
i
t
hi
g
h
pe
r
f
o
r
m
a
n
c
e
i
n
r
e
s
o
l
vi
ng
e
m
p
l
o
y
e
e
pe
r
f
o
r
m
a
n
c
e
a
s
s
e
s
s
m
e
n
t
i
s
s
ue
s
.
T
h
e
g
r
a
dua
t
e
v
a
r
i
a
bl
e
i
s
t
h
e
m
o
s
t
s
i
g
ni
f
i
c
a
n
t
f
a
c
t
or
i
nf
l
ue
n
c
i
ng
t
h
e
r
e
s
ul
t
v
a
r
i
a
bl
e
.
O
f
t
h
e
t
h
r
e
e
t
r
e
e
-
b
a
s
e
d
m
o
de
l
s
,
t
h
e
R
F
m
o
de
l
pe
r
f
o
r
m
s
be
tt
e
r
t
h
a
n
DT
a
n
d
XG
B
i
n
a
ddr
e
s
s
i
ng
e
m
p
l
o
y
e
e
pe
r
f
o
r
m
a
n
c
e
e
v
a
l
ua
t
i
o
n
i
s
s
ue
s
.
R
F
’
s
s
upe
r
i
o
r
i
t
y
i
s
de
m
o
ns
t
r
a
ted
i
n
t
h
e
s
e
n
s
i
t
i
v
i
t
y
,
A
U
R
OC
,
a
n
d
K
C
v
a
l
ue
s
by
1.
0000,
0.
9874,
a
n
d
0.
8584
,
r
e
s
pe
c
t
i
v
e
ly
.
T
h
e
s
e
f
i
nd
i
n
g
s
c
o
ul
d
s
e
r
ve
a
s
a
c
r
uc
i
a
l
s
t
e
p
f
o
r
i
n
s
p
i
r
i
ng
f
ut
ur
e
r
e
s
e
a
r
c
h
.
Ho
we
v
e
r
,
to
a
c
hi
e
ve
ge
n
e
r
a
li
z
a
bil
i
t
y
,
i
t
i
s
n
e
c
e
s
s
a
r
y
to
a
ppl
y
t
h
e
s
e
m
o
de
l
s
to
v
a
r
i
o
us
ot
h
e
r
c
a
s
e
s
.
F
i
n
a
ll
y
,
n
e
w
e
n
s
e
m
bl
e
a
n
d
hy
b
r
i
d
m
o
de
l
s
c
a
n
b
e
i
n
t
r
o
duc
e
d
to
a
c
hi
e
ve
hi
g
h
e
r
pe
r
f
o
r
m
a
n
c
e
.
AC
K
NOWL
E
DGE
M
E
NT
S
T
h
e
a
ut
h
o
r
s
w
o
ul
d
l
i
k
e
to
e
x
t
e
n
d
m
y
he
a
r
t
f
e
l
t
a
ppr
e
c
i
a
t
i
o
n
to
t
h
e
h
e
a
d
o
f
t
h
e
P
a
l
e
m
ba
n
g
c
i
t
y
F
R
S
f
o
r
hi
s
v
a
l
ua
bl
e
c
o
o
pe
r
a
t
i
o
n
,
e
s
pe
c
i
a
l
ly
i
n
pr
o
vi
d
in
g
t
h
e
da
t
a
s
e
t
f
o
r
t
hi
s
s
t
ud
y
.
T
h
e
a
ut
h
o
r
s
a
l
s
o
e
x
ten
d
t
h
e
i
r
a
ppr
e
c
i
a
t
i
o
n
f
o
r
t
h
e
i
nv
a
l
ua
bl
e
s
uppo
r
t
r
e
c
e
i
ve
d
f
r
o
m
U
ni
ve
r
s
i
t
a
s
I
n
do
G
l
o
b
a
l
M
a
n
d
i
r
i
.
RE
F
E
R
E
NC
E
S
[
1]
P
e
m
e
r
in
ta
h
-
K
o
ta
-
P
a
le
mba
ng,
“
D
P
K
s
tr
a
te
gi
c
pl
a
n
a
nd
s
a
v
in
g
th
e
c
i
t
y
of
P
a
l
e
mba
ng
f
o
r
2024
-
2026
(
I
n
I
nd
o
n
e
s
ia
n:
r
e
ns
tr
a
D
P
K
da
n
pe
n
y
e
la
ma
ta
n
K
o
ta
P
a
le
mba
ng
t
a
h
un
2024
-
2026)
,”
2023.
[
O
nl
in
e
]
.
A
v
a
il
a
bl
e
:
ht
tp
:/
/e
s
a
ki
p.pa
le
mba
ng.g
o
.i
d/
1823
/d
o
kume
n
/1
16/
202
3/
f
117
c
b
7d5b411d63656a
5c
465e
f
01047.pd
f
[
2]
A
.
S
.
D
e
O
li
ve
ir
a
G
oe
s
a
nd
R
.
C
.
L
.
D
e
O
li
ve
i
r
a
,
“
A
P
r
oc
e
s
s
f
o
r
huma
n
r
e
s
o
ur
c
e
p
e
r
f
or
ma
n
c
e
e
v
a
lu
a
ti
o
n
us
in
g
c
o
mput
a
ti
ona
l
in
te
ll
ig
e
n
c
e
:
a
n
a
ppr
o
a
c
h
us
in
g
a
c
o
mbi
na
ti
o
n
of
r
ul
e
-
ba
s
e
d
c
l
a
s
s
if
ie
r
s
a
nd
s
upe
r
v
is
e
d
le
a
r
ni
ng
a
lg
o
r
i
th
ms
,”
I
E
E
E
A
c
c
e
s
s
,
v
ol
.
8,
pp. 39403
–
39419, 2020, do
i:
10.1109/AC
C
E
S
S
.2020.2975485.
[
3]
K
.
G
.
A
y
u
e
t
al
.
,
“
C
la
s
s
if
i
c
a
ti
o
n
of
e
mpl
oy
e
e
c
o
mp
e
t
e
nc
y
a
s
s
e
s
s
me
nt
us
in
g
N
a
ïv
e
B
a
y
e
s
a
nd
K
-
n
e
a
r
e
s
t
n
e
ig
hb
o
r
(
K
N
N
)
a
lg
o
r
it
h
ms
,”
J
our
nal
o
f
A
dv
anc
e
s
i
n I
n
f
or
m
at
io
n T
e
c
hnol
ogy
, v
o
l.
15, n
o
. 7, pp. 879
–
885, 2024, d
o
i:
10.12720/
ja
it
.15.7.879
-
88
5.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2
5
0
2
-
4
7
52
In
do
n
e
s
i
a
n
J
E
l
e
c
E
n
g
&
C
o
m
p
S
c
i
,
Vo
l
.
3
8
,
N
o
.
1
,
A
pr
i
l
20
2
5
:
569
-
57
7
576
[
4]
H
.
H
in
da
y
a
nt
i,
W
.
S
e
pt
ia
ni
,
a
nd
R
.
M
a
ul
id
y
a
,
“
E
mpl
oy
e
e
p
e
r
f
or
ma
nc
e
a
s
s
e
s
s
me
nt
mo
d
e
l
in
s
ur
ve
y
s
e
r
v
i
c
e
c
o
mpa
ni
e
s
us
in
g
a
na
l
y
ti
c
a
l
hi
e
r
a
r
c
h
y
pr
oc
e
s
s
a
nd
N
a
iv
e
B
a
y
e
s
,”
Spe
k
tr
um
I
ndus
tr
i
,
v
o
l.
22,
no
.
1,
pp.
36
–
50,
M
a
y
2024,
do
i:
10.12928/s
i.
v
22i
1.150.
[
5]
D
.
S
a
r
ti
ka
a
nd
R
.
G
us
tr
ia
ns
y
a
h,
“
C
o
mpa
r
is
o
n
of
na
i
ve
B
a
y
e
s
a
nd
d
e
c
is
io
n
t
r
e
e
a
lg
o
r
it
hms
to
a
s
s
e
s
s
th
e
p
e
r
f
or
ma
nc
e
of
P
a
le
mba
ng
C
it
y
f
i
r
e
a
nd
D
is
a
s
te
r
ma
na
ge
me
nt
e
mpl
oy
e
e
s
,”
T
E
K
N
O
SA
I
N
S:
J
ur
nal
Sai
ns
,
T
e
k
nol
ogi
dan
I
n
f
or
m
at
ik
a
,
v
o
l.
11,
no
. 1, pp. 132
–
138, 202
4, d
o
i:
10.37373/t
e
kn
o
.
v
11i
1.843.
[
6]
G
.
G
a
li
h
a
nd M
. E
r
i
y
a
di
, “
C
o
mpa
r
is
o
n
of
t
h
e
N
B
C
, S
V
M
, a
nd
C
4.5 mo
d
e
ls
i
n
m
e
a
s
ur
in
g
o
ut
s
ta
ndi
ng
e
mpl
oy
e
e
p
e
r
f
or
ma
nc
e
po
s
t
th
e
C
ov
id
-
19
pa
nde
mi
c
(
I
n
I
nd
o
n
e
s
ia
n:
P
e
r
bandingan
m
ode
l
N
B
C
,
SV
M
,
dan
C
4.5
dal
am
m
e
nguk
ur
k
in
e
r
j
a
k
ar
y
aw
an
be
r
p
r
e
s
ta
s
i
pas
c
a
pande
m
i
C
O
V
I
D
-
19
)
,”
J
ur
nal
I
nf
or
m
at
ik
a
,
v
o
l.
9,
no
.
2,
pp.
123
–
130,
O
c
t.
2
022,
do
i:
10.31294/i
n
f
.
v
9i
2.13772.
[
7]
S
.
G
.
F
a
s
ho
t
o
,
O
.
A
ma
o
nw
u,
a
nd
A
.
A
f
o
l
o
r
uns
h
o
,
“
D
e
v
e
l
opme
nt
of
a
de
c
is
i
o
n
s
upp
o
r
t
s
y
s
t
e
m
o
n
e
mpl
oy
e
e
p
e
r
f
or
ma
nc
e
a
ppr
a
is
a
l
us
in
g
A
H
P
m
o
d
e
l,
”
J
O
I
V
:
I
nt
e
r
nat
io
nal
J
our
nal
on
I
nf
or
m
at
ic
s
V
is
ual
iz
at
io
n
,
v
o
l.
2,
n
o
.
4,
pp.
262
–
267,
A
ug.
2
018,
do
i:
10.30630/j
oi
v
.2.4.160.
[
8]
B
.
L
a
ia
a
nd
B
.
S
in
a
ga
,
“
D
e
c
is
i
o
n
s
upp
o
r
t
s
y
s
t
e
m
f
or
e
mpl
oy
e
e
pe
r
f
or
ma
nc
e
us
in
g
A
H
P
m
e
th
o
d
(
c
a
s
e
s
tu
d
y
:
P
T
.
A
ndh
y
P
ut
r
a
)
,”
I
nt
e
r
nat
io
nal
J
our
nal
of
B
as
ic
and A
ppl
ie
d Sc
ie
n
c
e
, v
o
l.
10, n
o
.
3, pp. 107
–
116, De
c
. 2021, d
oi
:
10.35335/i
j
o
ba
s
.v
10i
3.33.
[
9]
R
. G
us
tr
ia
ns
y
a
h, J
. A
li
e
, a
nd N
. S
uha
ndi
, “
P
e
r
f
or
ma
n
c
e
e
v
a
lu
a
t
io
n
of
c
o
nt
r
a
c
t
e
mpl
oy
e
e
s
us
in
g t
h
e
b
e
s
t
-
w
o
r
s
t
a
nd s
im
pl
e
a
ddi
t
iv
e
w
e
ig
ht
in
g m
e
th
o
ds
,”
J
U
I
T
A
:
J
ur
nal
I
nf
or
m
at
ik
a
, vo
l.
9, n
o
. 2,
pp. 219
–
227, Nov
. 2021, d
o
i:
10.30595/j
ui
ta
.v
9i
2.11989.
[
10]
Y
.
P
.
S
upr
a
pt
o
,
H
.
H
a
e
r
udi
n,
a
nd
A
.
D
a
nuw
id
o
do
,
“
D
e
c
is
io
n
s
uppor
t
s
y
s
te
m
f
or
e
mpl
oy
e
e
p
e
r
f
or
ma
n
c
e
a
s
s
e
s
s
me
nt
us
in
g
a
na
l
y
ti
c
a
l
hi
e
r
a
r
c
h
y
pr
oc
e
s
s
a
nd
s
im
pl
e
a
ddi
ti
ve
w
e
ig
h
ti
ng
m
e
t
ho
d
s
,”
J
our
nal
of
I
nf
o
r
m
at
io
n
Sy
s
te
m
s
and
I
nf
or
m
at
i
c
s
,
v
o
l.
6,
no
.
2, pp. 766
–
780, J
un. 2024, do
i:
10.51519/j
o
ur
na
li
s
i.
v
6i
2.721.
[
11]
T
.
B
.
F
e
b
r
ia
n
a
nd
A
.
S
im
a
nguns
o
ng,
“
D
e
c
is
i
o
n
su
ppor
t
s
y
s
t
e
m
e
mpl
oy
e
e
p
e
r
f
or
ma
nc
e
a
ppr
a
is
a
l
me
th
o
d
us
in
g
T
O
P
S
I
S
,”
J
our
nal
O
f
C
om
put
e
r
N
e
tw
or
k
s
,
A
r
c
hi
te
c
tu
r
e
and
H
ig
h
P
e
r
f
or
m
a
nc
e
C
om
put
in
g
,
vo
l.
2,
n
o
.
2,
pp.
307
–
312,
J
un.
2020,
do
i:
10.47709/c
na
pc
.
v
2i
2.412.
[
12]
M
.
L
in
gga
,
“
E
v
a
lu
a
ti
ng
th
e
p
e
r
f
or
ma
nc
e
e
m
pl
oy
e
e
us
i
ng
T
O
P
S
I
S
,”
I
O
P
C
onf
e
r
e
nc
e
Se
r
ie
s
:
M
at
e
r
ia
l
s
Sc
ie
nc
e
and
E
ngi
ne
e
r
in
g
,
vo
l.
662, n
o
. 6, pp. 1
–
8, N
ov
. 2019, d
o
i:
10.1088/1757
-
899X/6
62/
6/
062018.
[
13]
N
.
P
.
D
e
w
i,
N
.
R
a
ma
dha
ni
,
I
.
D
a
r
ma
w
a
n,
U
.
U
ba
id
i,
a
nd
A
.
W
.
S
y
a
hr
o
ni
,
“
A
ppl
i
c
a
ti
o
n
of
p
r
of
il
e
ma
t
c
hi
ng
in
d
e
t
e
r
mi
n
in
g
e
mpl
oy
e
e
a
nnua
l
b
o
nus
e
s
,”
J
ur
nal
I
nf
or
m
as
i
dan T
e
k
nol
ogi
, v
ol
. 6, no
. 2, pp. 133
–
140, J
un. 2024, d
o
i:
10.60083/j
id
t.
v
6i
2.542.
[
14]
S
a
f
r
i
z
a
l,
L
.
T
a
nt
i,
R
.
P
us
pa
s
a
r
i,
a
nd
B
.
T
r
ia
ndi
,
“
E
mpl
oy
e
e
p
e
r
f
o
r
ma
n
c
e
a
s
s
e
s
s
me
nt
w
it
h
pr
of
il
e
ma
t
c
hi
ng
me
th
o
d,”
in
2018
6t
h
I
nt
e
r
nat
io
nal
C
onf
e
r
e
nc
e
on
C
y
b
e
r
and
I
T
Se
r
v
ic
e
M
anage
m
e
nt
(
C
I
T
SM
)
,
I
E
E
E
,
A
ug.
2018,
pp.
1
–
6.
do
i:
10.1109/C
I
T
S
M
.2018.8674256.
[
15]
R
.
T
.
A
.
A
gus
,
M
.
A
.
S
e
mb
ir
in
g,
M
.
F
.
L
.
S
ib
u
e
a
,
M
a
r
da
li
us
,
a
nd
A
.
N
a
ta
,
“
E
mpl
oy
e
e
p
e
r
f
or
ma
nc
e
a
na
l
y
s
is
us
in
g
a
na
l
yt
ic
a
l
hi
e
r
a
r
c
h
y
pr
oc
e
s
s
a
nd
w
e
ig
ht
e
d
pr
o
du
c
t
c
o
mbi
na
ti
o
ns
a
lg
o
r
i
th
m,”
J
our
nal
o
f
P
hy
s
ic
s
:
C
on
f
e
r
e
n
c
e
S
e
r
ie
s
,
v
o
l.
1783,
n
o.
1,
pp. 1
–
4, F
e
b. 2021, d
o
i:
10.1088/1742
-
6596/1783/
1/
012010.
[
16]
B
.
S
e
k
e
r
o
gl
u,
K
.
D
im
il
il
e
r
,
a
nd
K
.
T
un
c
a
l,
“
S
tu
d
e
nt
pe
r
f
o
r
ma
n
c
e
pr
e
di
c
ti
o
n
a
nd
c
la
s
s
if
i
c
a
ti
o
n
us
in
g
ma
c
hi
n
e
le
a
r
n
in
g
a
lg
o
r
it
h
ms
,”
in
P
r
oc
e
e
di
ngs
o
f
th
e
2019
8t
h
I
nt
e
r
nat
io
nal
C
o
nf
e
r
e
nc
e
on
E
duc
at
io
nal
and
I
nf
o
r
m
at
io
n
T
e
c
hnol
ogy
,
N
e
w
Y
o
r
k,
N
Y
, U
S
A
:
A
C
M
, M
a
r
. 2019, pp. 7
–
11. do
i:
10.1145/3318396.3
318419.
[
17]
A
.
Q
a
z
da
r
,
B
.
E
r
-
R
a
ha
,
C
.
C
he
r
ka
o
ui
,
a
nd
D
.
M
a
mm
a
s
s
,
“
A
ma
c
hi
n
e
l
e
a
r
ni
ng
a
lg
or
it
hm
f
r
a
m
e
w
o
r
k
f
or
p
r
e
di
c
ti
ng
s
tu
de
nt
s
pe
r
f
or
ma
nc
e
:
A
c
a
s
e
s
tu
d
y
of
ba
c
c
a
la
ur
e
a
te
s
tu
de
nt
s
in
M
o
r
oc
c
o
,”
E
duc
at
io
n
and
I
nf
or
m
at
io
n
T
e
c
hnol
ogi
e
s
,
vo
l.
24,
n
o.
6,
pp. 3577
–
358
9, N
ov
. 2019, d
o
i:
10.1007/s
10639
-
019
-
09946
-
8.
[
18]
X
.
X
u,
J
.
W
a
ng,
H
.
P
e
ng,
a
nd
R
.
W
u,
“
P
r
e
di
c
ti
o
n
of
a
c
a
d
e
mi
c
p
e
r
f
or
ma
n
c
e
a
s
s
o
c
ia
t
e
d
w
it
h
in
t
e
r
n
e
t
us
a
ge
b
e
ha
v
i
o
r
s
us
in
g
ma
c
hi
ne
le
a
r
n
in
g a
lg
or
it
hms
,”
C
om
put
e
r
s
i
n H
um
an B
e
hav
io
r
,
vo
l.
98, pp. 166
–
173, S
e
p.
2019, d
o
i:
10.1016/
j.
c
hb.2019.04.01
5.
[
19]
A
.
S
.
H
a
s
hi
m,
W
.
A
.
A
w
a
dh,
a
nd
A
.
K
.
H
a
mo
ud,
“
S
tu
d
e
nt
pe
r
f
or
ma
nc
e
pr
e
di
c
ti
o
n
m
o
d
e
l
ba
s
e
d
o
n
s
upe
r
v
is
e
d
ma
c
hi
n
e
l
e
a
r
n
in
g
a
lg
o
r
it
h
ms
,”
in
I
O
P
C
onf
e
r
e
nc
e
Se
r
ie
s
:
M
at
e
r
ia
ls
Sc
ie
nc
e
and
E
ngi
ne
e
r
in
g
,
I
O
P
P
ubl
is
hi
ng,
N
o
v
.
2
020,
pp. 1
–
18. do
i:
10.1088/1757
-
899X/928/3/
032019.
[
20]
R
.
G
h
o
r
ba
ni
a
nd
R
.
G
h
o
us
i,
“
C
o
mpa
r
in
g
di
f
f
e
r
e
nt
r
e
s
a
mpl
i
ng
me
th
o
ds
in
pr
e
di
c
ti
ng
s
tu
de
nt
s
’
p
e
r
f
or
ma
n
c
e
us
in
g
ma
c
hi
ne
le
a
r
ni
ng t
e
c
hni
qu
e
s
,”
I
E
E
E
A
c
c
e
s
s
, v
o
l.
8, pp. 67899
–
6791
1, 2
020, do
i:
10.1109/AC
C
E
S
S
.2020.2986809.
[
21]
B
.
A
lb
r
e
ik
i,
N
.
Z
a
ki
,
a
nd
H
.
A
la
s
hw
a
l,
“
A
s
y
s
te
ma
ti
c
li
t
e
r
a
tu
r
e
r
e
v
i
e
w
of
s
tu
d
e
nt
’
p
e
r
f
or
ma
nc
e
pr
e
di
c
ti
o
n
us
in
g
ma
c
hi
ne
l
e
a
r
n
in
g
te
c
hni
que
s
,
”
E
duc
at
io
n Sc
ie
nc
e
s
, vo
l.
11, n
o
. 9, pp. 1
–
27, S
e
p.
2021, do
i:
10.3
390/
e
du
c
s
c
i1
1090552.
[
22]
R
.
G
us
tr
ia
ns
y
a
h,
N
.
S
uha
ndi
,
S
.
P
us
pa
s
a
r
i,
a
nd
A
.
S
a
nmo
r
in
o
,
“
M
a
c
hi
ne
l
e
a
r
ni
ng
m
e
th
o
d
to
pr
e
di
c
t
th
e
to
dd
le
r
s
’
nut
r
it
i
ona
l
s
ta
t
us
,”
I
N
F
O
T
E
L
,
vo
l.
16, n
o
. 1, pp. 1
–
6, 2024, d
o
i:
10.20895
/
in
f
ot
e
l.
v
15
i4
.988.
[
23]
V
.
K
.
G
upt
a
,
A
.
G
up
t
a
,
D
.
K
uma
r
,
a
nd
A
.
S
a
r
da
na
,
“
P
r
e
d
ic
t
i
on
of
C
O
V
I
D
-
19
c
o
n
f
i
r
me
d,
d
e
a
th
,
a
nd
c
u
r
e
d
c
a
s
e
s
in
I
ndi
a
us
in
g
r
a
ndo
m
f
or
e
s
t
m
o
de
l,
”
B
ig
D
at
a
M
in
in
g
and
A
na
ly
ti
c
s
,
vo
l.
4,
n
o
.
2,
pp.
116
–
123,
J
un.
2021,
do
i:
10.26599/B
D
M
A
.2020.9020016.
[
24]
V
.
P
r
a
de
e
p,
R
.
K
h
e
mm
a
r
,
a
nd
F
.
J
e
nd
o
ubi
,
“
V
is
ua
l
e
c
o
-
r
o
u
ti
n
g
(
V
E
R
)
:
X
G
B
oo
s
t
ba
s
e
d
e
c
o
-
r
o
ut
e
s
e
le
c
ti
o
n
f
r
o
m
r
o
a
d
s
c
e
n
e
s
a
nd
ve
hi
c
le
e
mi
s
s
i
o
ns
,”
I
E
E
E
A
c
c
e
s
s
, v
ol
. 12, pp. 9669
–
9681, 2024
, do
i:
10.1109/AC
C
E
S
S
.2024.3353036.
[
25]
E
.
E
l
v
in
a
nd
A
.
W
ib
o
w
o
,
“
F
o
r
e
c
a
s
ti
ng
w
a
te
r
qua
li
t
y
th
r
o
ugh
ma
c
hi
n
e
l
e
a
r
ni
ng
a
nd
h
y
p
e
r
pa
r
a
m
e
t
e
r
o
p
ti
mi
z
a
ti
o
n,”
I
ndone
s
ia
n
J
our
nal
of
E
le
c
tr
ic
al
E
ngi
ne
e
r
in
g
and
C
om
put
e
r
Sc
ie
nc
e
,
vo
l.
33,
n
o
.
1,
pp.
496
–
506,
J
a
n.
2024,
do
i:
10.11591/i
je
e
c
s
.v
33.i
1.pp496
-
506.
[
26]
J
.
S
a
lt
z
,
I
.
S
ha
ms
hur
in
,
a
nd
K
.
C
r
o
w
s
t
o
n,
“
C
o
mpa
r
i
ng
da
t
a
s
c
ie
nc
e
pr
o
j
e
c
t
ma
na
ge
m
e
nt
m
e
th
o
d
o
l
o
gi
e
s
v
ia
a
c
o
nt
r
o
l
le
d
e
x
p
e
r
im
e
nt
,”
in
P
r
oc
e
e
di
ngs
o
f
th
e
50t
h
H
aw
ai
i
I
nt
e
r
nat
io
nal
C
onf
e
r
e
n
c
e
on
Sy
s
te
m
S
c
ie
nc
e
s
,
2017,
pp.
1013
–
1022.
do
i:
10.24251/H
I
C
S
S
.2017.120.
[
27]
R
.
G
us
tr
ia
ns
y
a
h,
E
.
E
r
ma
ti
ta
,
a
nd
D
.
P
.
R
i
ni
,
“
A
n
a
ppr
o
a
c
h
f
o
r
s
a
l
e
s
f
o
r
e
c
a
s
ti
ng,”
E
x
pe
r
t
Sy
s
te
m
s
w
it
h
A
ppl
ic
at
io
ns
,
vo
l.
207,
pp. 1
–
8, N
ov
. 2022, d
o
i:
10.1016/j
.
e
s
w
a
.2022.118043.
[
28]
R
.
H
.
H
r
id
oy
,
A
.
D
.
A
r
n
i,
S
.
K
.
G
h
o
s
h,
N
.
R
.
C
ha
kr
a
bo
r
t
y
,
a
nd
I
.
M
a
hmud,
“
P
e
r
f
o
r
ma
n
c
e
e
nha
nc
e
m
e
nt
of
ma
c
h
in
e
le
a
r
ni
ng
a
lg
o
r
it
h
m
f
or
br
e
a
s
t
c
a
n
c
e
r
di
a
gn
o
s
is
us
in
g
h
y
p
e
r
pa
r
a
m
e
te
r
o
pt
im
i
z
a
ti
o
n,”
I
nt
e
r
nat
io
nal
J
our
nal
of
E
le
c
tr
ic
al
and
C
om
put
e
r
E
ngi
ne
e
r
in
g (
I
J
E
C
E
)
,
vo
l.
14, n
o
. 2, pp. 2181
–
2190, Apr
. 2024
, do
i:
10.11591/i
je
c
e
.
v
14i
2.pp2181
-
2190.
[
29]
A
.
S
a
nmor
in
o
a
nd
H
.
D
i
K
e
s
uma
,
“
F
in
e
-
tu
n
in
g
a
pr
e
-
tr
a
in
e
d
R
e
s
N
e
t5
0
m
o
de
l
t
o
d
e
t
e
c
t
di
s
tr
ib
ut
e
d
d
e
ni
a
l
of
s
e
r
v
i
c
e
a
tt
a
c
k,”
B
ul
le
ti
n of
E
le
c
tr
ic
al
E
ngi
ne
e
r
in
g and I
nf
o
r
m
at
ic
s
, v
o
l.
13, n
o
.
2, pp. 1362
–
1370, Apr
. 2024, do
i:
10.11591
/e
e
i.
v
13i
2.7014.
[
30]
T
.
K
im
a
nd
J
.
-
S
.
L
e
e
,
“
M
a
x
im
iz
in
g
A
U
C
to
le
a
r
n
w
e
ig
ht
e
d
na
iv
e
B
a
y
e
s
f
o
r
im
ba
la
nc
e
d
da
ta
c
la
s
s
if
i
c
a
ti
o
n,”
E
x
pe
r
t
Sy
s
te
m
s
w
it
h
A
ppl
ic
at
io
ns
, vo
l.
217, pp. 1
–
17, M
a
y
2023, d
o
i:
10.1016/j
.
e
s
w
a
.2023.119564.
[
31]
S
. R
a
f
i
e
y
a
n, E
. V
a
s
he
gha
ni
-
F
a
r
a
ha
ni
, N
. B
a
he
i
r
a
e
i,
a
nd
H
.
K
e
s
ha
v
a
r
z
, “
M
L
A
T
E
:
ma
c
hi
n
e
l
e
a
r
ni
ng
f
o
r
p
r
e
di
c
t
in
g c
e
ll
b
e
ha
v
i
or
o
n
c
a
r
di
a
c
ti
s
s
ue
e
ngi
n
e
e
r
in
g
s
c
a
f
f
o
ld
s
,”
C
om
put
e
r
s
in
B
io
lo
gy
and
M
e
di
c
in
e
,
v
o
l.
158,
pp.
1
–
11,
M
a
y
2023,
do
i:
10.1016/j
.c
o
mpbi
o
m
e
d.2023.106804.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
do
n
e
s
i
a
n
J
E
l
e
c
E
n
g
&
C
o
m
p
S
c
i
I
S
S
N:
2
5
0
2
-
4
7
52
T
r
e
e
-
bas
e
d
mode
ls
and
hy
pe
r
par
a
me
ter
opti
miz
ati
on
…
(
R
e
ndr
a
Gus
tr
ians
y
ah
)
577
B
I
OG
RA
P
HI
E
S
OF
AU
T
HO
RS
R
endra
Gu
s
tri
a
n
s
y
a
h
i
s
an
as
s
o
c
i
at
e
p
ro
f
e
s
s
o
r
at
U
n
i
v
e
rs
i
t
as
In
d
o
G
l
o
b
al
Man
d
i
r
i
,
In
d
o
n
e
s
i
a
.
H
e
co
m
p
l
e
t
ed
h
i
s
m
as
t
e
r’s
a
n
d
d
o
c
t
o
ra
l
d
eg
r
ee
s
w
i
t
h
BPP
D
N
Sch
o
l
ars
h
i
p
s
fro
m
t
h
e
M
i
n
i
s
t
ry
o
f
R
e
s
e
ar
ch
,
T
ech
n
o
l
o
g
y
,
an
d
H
i
g
h
e
r
E
d
u
c
at
i
o
n
fo
r
Mas
t
e
r
’
s
i
n
co
m
p
u
t
e
r
s
c
i
en
ce
fro
m
t
h
e
U
n
i
v
e
rs
i
t
y
o
f
I
n
d
o
n
e
s
i
a
an
d
a
d
o
c
t
o
ra
l
i
n
i
n
fo
r
m
at
i
c
s
e
n
g
i
n
ee
ri
n
g
fro
m
Sr
i
w
i
j
a
y
a
U
n
i
v
e
rs
i
t
y
.
H
i
s
r
e
s
e
ar
ch
ar
eas
are
m
a
c
h
i
n
e
l
e
arn
i
n
g
,
d
at
a
mi
n
i
n
g
,
d
eci
s
i
o
n
-
m
ak
i
n
g
,
a
n
d
b
u
s
i
n
e
s
s
i
n
t
e
l
l
i
g
e
n
ce.
H
e
c
an
b
e
co
n
t
ac
t
e
d
at
em
a
i
l
:
r
en
d
ra@
u
i
g
m
.
a
c
.
i
d
.
Shi
n
ta
P
u
s
pa
s
a
ri
recei
v
ed
t
h
e
S.
S
i
.
d
e
g
r
ee
i
n
m
at
h
em
at
i
c
s
fro
m
t
h
e
U
n
i
v
e
rs
i
t
as
Sri
w
i
j
a
y
a
,
t
h
e
M.
K
o
m
.
d
e
g
r
ee
i
n
c
o
m
p
u
t
i
n
g
fr
o
m
t
h
e
U
n
i
v
e
rs
i
t
as
In
d
o
n
e
s
i
a
,
an
d
t
h
e
d
o
c
t
o
rat
e
i
n
i
n
f
o
r
m
at
i
c
s
en
g
i
n
ee
r
i
n
g
fro
m
t
h
e
U
n
i
v
e
rs
i
t
as
Sri
w
i
j
a
y
a
,
I
n
d
o
n
e
s
i
a.
S
h
e
h
o
l
d
s
t
h
e
H
e
ad
o
f
I
n
s
t
i
t
u
t
e
s
fo
r
R
e
s
e
ar
c
h
a
n
d
C
o
mm
u
n
i
t
y
S
e
r
v
i
ce,
U
n
i
v
e
rs
i
t
as
In
d
o
G
l
o
b
al
Ma
n
d
i
ri
.
Sh
e
i
s
c
u
rr
en
t
l
y
a
n
as
s
o
ci
at
e
p
ro
f
e
s
s
o
r
w
i
t
h
t
h
e
D
e
p
art
men
t
o
f
I
n
f
o
r
m
at
i
c
s
E
n
g
i
n
ee
ri
n
g
,
U
n
i
v
e
rs
i
t
as
I
n
d
o
G
l
o
b
al
Man
d
i
r
i
(U
I
G
M).
H
e
r
r
e
s
e
ar
c
h
i
n
t
e
r
e
s
t
s
i
n
c
l
u
d
e
co
m
p
u
t
e
r
v
i
s
i
o
n
a
n
d
i
n
t
e
l
l
i
g
e
n
t
s
y
s
t
em
s
.
S
h
e
c
an
b
e
co
n
t
a
c
t
ed
at
em
ai
l
:
s
h
i
n
t
a@
u
i
g
m
.
a
c.
i
d
.
A
hm
a
d
Sa
nm
o
r
i
n
o
i
s
an
as
s
o
c
i
at
e
p
ro
f
e
s
s
o
r
at
t
h
e
Fa
cu
l
t
y
o
f
C
o
m
p
u
t
e
r
an
d
Sci
en
ce
,
U
n
i
v
e
rs
i
t
as
I
n
d
o
G
l
o
b
al
Ma
n
d
i
ri
,
In
d
o
n
e
s
i
a
.
H
e
r
ece
i
v
e
d
a
d
o
c
t
o
rat
e
i
n
i
n
f
o
r
m
at
i
c
s
e
n
g
i
n
ee
ri
n
g
fro
m
U
n
i
v
e
rs
i
t
as
Sri
w
i
j
a
y
a.
H
i
s
r
e
s
e
ar
c
h
i
n
t
e
r
e
s
t
s
i
n
c
l
u
d
e
art
i
fi
ci
al
i
n
t
el
l
i
g
en
ce
are
a
i
n
cl
u
d
i
n
g
ap
p
l
i
e
d
m
ach
i
n
e
l
e
arn
i
n
g
,
cy
b
e
r
s
ecu
ri
t
y
,
an
d
i
n
fo
r
m
at
i
o
n
s
ecu
ri
t
y
.
H
e
c
an
b
e
c
o
n
t
ac
t
e
d
at
em
a
i
l
:
s
an
mo
ri
n
o
@
u
i
g
m
.
a
c
.
i
d
.
N
a
z
o
ri
S
uh
a
n
d
i
i
s
a
s
e
n
i
o
r
l
ec
t
u
r
e
r
at
t
h
e
Fa
c
u
l
t
y
o
f
C
o
m
p
u
t
e
r
an
d
S
ci
e
n
ce
,
U
n
i
v
e
rs
i
t
as
In
d
o
G
l
o
b
al
Ma
n
d
i
ri
.
H
e
r
ecei
v
ed
a
mas
t
e
r
’
s
d
eg
r
e
e
i
n
m
an
a
g
eme
n
t
fro
m
U
n
i
v
e
rs
i
t
as
Sri
w
i
j
a
y
a.
H
e
h
as
r
e
s
e
ar
ch
i
n
t
e
r
e
s
t
s
i
n
b
u
s
i
n
e
s
s
i
n
t
el
l
i
g
en
ce
a
n
d
e
n
t
r
e
p
ren
e
u
rs
h
i
p
.
H
e
c
an
b
e
co
n
t
a
c
t
ed
at
em
a
i
l
:
n
azo
r
i
@
u
i
g
m
.
a
c
.
i
d
.
D
ew
i
Sa
rti
k
a
i
s
c
u
rr
e
n
t
l
y
a
l
ec
t
u
r
e
r
at
t
h
e
Facu
l
t
y
o
f
C
o
m
p
u
t
e
r
S
c
i
en
ce,
Sri
w
i
j
a
y
a
U
n
i
v
e
rs
i
t
y
,
I
n
d
o
n
e
s
i
a.
S
h
e
c
o
m
p
l
e
t
e
d
h
e
r
d
e
g
r
ee
f
o
r
b
ach
e
l
o
r
o
f
i
n
f
o
r
m
at
i
c
s
e
n
g
i
n
ee
ri
n
g
at
Sri
w
i
j
a
y
a
U
n
i
v
e
rs
i
t
y
an
d
m
as
t
e
r
o
f
c
o
mp
u
t
e
r
s
ci
e
n
ce
at
U
n
i
v
e
rs
i
t
as
I
n
d
o
n
e
s
i
a.
Sh
e
h
as
r
e
s
e
ar
ch
i
n
t
e
r
e
s
t
s
i
n
s
o
ft
w
ar
e
en
g
i
n
ee
ri
n
g
an
d
co
m
p
u
t
at
i
o
n
al
i
n
t
el
l
i
g
en
c
e.
Sh
e
c
a
n
b
e
c
o
n
t
ac
t
e
d
at
em
a
i
l
:
d
ew
i
s
art
i
k
a@
u
n
s
ri
.
a
c
.
i
d
.
Evaluation Warning : The document was created with Spire.PDF for Python.