I
n
t
e
r
n
at
ion
al
Jou
r
n
a
l
of
I
n
f
o
r
m
at
ics
an
d
Com
m
u
n
icat
ion
T
e
c
h
n
ol
ogy
(
I
J
-
I
CT
)
Vo
l
.
14
,
N
o
.
2
,
A
ugus
t
20
25
,
pp.
446
~
456
I
S
S
N:
2252
-
8
776
,
DO
I
:
10
.
11591/i
ji
c
t
.
v
14
i
2
.
pp
44
6
-
456
446
Jou
r
n
al
h
o
m
e
page
:
ht
tp:
//
ij
ict
.
iaes
c
or
e
.
c
om
M
ac
h
in
e
l
e
ar
n
in
g i
n
d
e
t
e
c
t
in
g an
d
i
n
t
e
r
p
r
e
t
in
g b
u
si
n
e
ss
in
c
u
b
at
or
su
c
c
e
ss d
at
a an
d
d
a
t
ase
t
s
M
oc
h
am
m
ad
Hal
d
i
Wid
ian
t
o
1
,
P
u
j
i
P
r
ab
owo
2
1
C
o
mput
e
r
S
c
ie
n
c
e
D
e
pa
r
tm
e
nt
,
S
c
h
oo
l
of
C
o
mput
e
r
S
c
i
e
n
c
e
,
B
in
a
N
us
a
nt
a
r
a
U
ni
v
e
r
s
it
y
, J
a
ka
r
ta
,
I
ndo
n
e
s
ia
2
E
nt
r
e
pr
e
n
e
ur
s
hi
p
D
e
pa
r
tm
e
nt
, B
in
a
N
us
a
nt
a
r
a
U
ni
v
e
r
s
it
y
, J
a
k
a
r
ta
, I
ndo
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
J
u
l
26,
2024
R
e
vi
s
e
d
De
c
6
,
2024
A
c
c
e
pt
e
d
De
c
15
,
2024
T
h
i
s
r
e
s
e
ar
ch
co
n
t
ri
b
u
t
e
s
t
o
c
r
e
at
i
n
g
a
p
ro
p
o
s
ed
ar
ch
i
t
ec
t
u
ra
l
m
o
d
e
l
b
y
u
t
i
l
i
zi
n
g
s
ev
e
ra
l
m
a
c
h
i
n
e
l
e
arn
i
n
g
(ML
)
al
g
o
r
i
t
h
m
s
,
h
e
at
m
ap
co
rr
e
l
at
i
o
n
,
an
d
ML
i
n
t
e
rp
re
t
at
i
o
n
.
S
e
v
e
ra
l
al
g
o
ri
t
h
m
s
ar
e
u
s
e
d
,
s
u
c
h
as
K
-
n
e
ar
e
s
t
n
ei
g
h
b
o
rs
(
KNN
)
t
o
t
h
e
a
d
ap
t
i
v
e
b
o
o
s
t
i
n
g
(
Ada
B
o
o
s
t
)
al
g
o
r
i
t
h
m
,
a
n
d
h
e
at
m
ap
c
o
rr
el
at
i
o
n
i
s
u
s
ed
t
o
s
ee
t
h
e
r
e
l
at
i
o
n
s
h
i
p
b
e
t
w
ee
n
v
a
r
i
ab
l
e
s
.
Fi
n
a
l
l
y
,
s
el
ec
t
K
-
b
e
s
t
i
s
u
s
e
d
i
n
t
h
e
re
s
u
l
t
s
,
s
h
o
w
i
n
g
t
h
at
s
e
v
e
ral
p
ro
p
o
s
ed
mo
d
e
l
ML
a
l
g
o
ri
t
h
m
s
s
u
c
h
as
A
d
aBo
o
s
t
,
Cat
Bo
o
s
t
,
an
d
X
G
Bo
o
s
t
h
av
e
acc
u
ra
cy
,
p
reci
s
i
o
n
,
an
d
r
ec
al
l
o
f
9
4
%
an
d
a
n
F
1
-
s
c
o
r
e
o
f
9
3
%
.
H
o
w
ev
e
r,
t
h
e
co
m
p
u
t
i
n
g
t
i
me
t
h
e
b
e
s
t
ML
i
s
A
d
a
B
o
o
s
t
w
i
t
h
0
.
0
8
1
s
.
T
h
e
n
,
fi
n
al
l
y
,
t
h
e
p
ro
p
o
s
e
d
mo
d
el
r
e
s
u
l
t
s
o
f
t
h
e
i
n
t
e
rp
r
e
t
at
i
o
n
o
f
A
d
a
B
o
o
s
t
u
s
i
n
g
s
el
ec
t
K
-
b
e
s
t
are
t
h
e
b
e
s
t
fe
at
u
r
e
s
“
l
as
t
re
v
e
n
u
e
”
an
d
“
fi
rs
t
re
v
e
n
u
e
”
w
i
t
h
k
f
e
at
u
r
e
v
a
l
u
e
s
o
f
0
.
5
8
an
d
0
.
1
9
6
,
t
h
e
s
e
f
e
at
u
r
e
s
i
n
f
l
u
en
ce
t
h
e
s
u
cce
s
s
o
f
t
h
e
b
u
s
i
n
e
s
s
.
T
h
e
re
s
u
l
t
s
s
h
o
w
t
h
at
t
h
e
p
ro
p
o
s
ed
m
o
d
e
l
s
u
cce
s
s
fu
l
l
y
u
t
i
l
i
z
e
d
m
o
d
e
l
c
l
as
s
i
fi
c
at
i
o
n
,
co
rr
e
l
at
i
o
n
,
a
n
d
i
n
t
e
rp
r
e
t
at
i
o
n
.
T
h
e
p
ro
p
o
s
e
d
mo
d
el
s
t
i
l
l
h
as
w
e
a
k
n
e
s
s
e
s
,
s
u
ch
as
t
h
e
M
L
m
o
d
e
l
b
e
i
n
g
o
u
t
d
at
e
d
a
n
d
n
o
t
h
av
i
n
g
t
o
o
m
an
y
i
n
t
e
rp
r
e
t
at
i
o
n
f
e
at
u
r
e
s
.
T
h
e
fu
t
u
r
e
r
e
s
e
ar
ch
mi
g
h
t
m
ax
i
mi
ze
w
i
t
h
M
L
mo
d
el
s
an
d
t
h
e
l
at
e
s
t
i
n
t
e
rp
re
t
at
i
o
n
s
.
T
h
e
s
e
i
m
p
ro
v
eme
n
t
s
c
o
u
l
d
b
e
i
n
t
h
e
f
o
r
m
o
f
ML
a
l
g
o
ri
t
h
m
s
t
h
at
ar
e
m
o
r
e
i
mm
u
n
e
t
o
d
at
a
u
n
ce
rt
ai
n
t
y
,
a
n
d
i
n
t
e
rp
r
e
t
at
i
o
n
o
f
r
e
s
u
l
t
s
w
i
t
h
w
i
d
e
r
d
at
a
.
K
e
y
w
o
r
d
s
:
A
da
B
o
o
s
t
F
e
a
t
u
re
I
n
t
e
r
pr
e
t
a
t
i
o
n
M
a
c
hi
ne
l
e
a
r
ni
ng
M
o
de
l
a
r
c
hi
t
e
c
t
ur
e
S
e
l
e
c
t
K
-
b
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
:
M
o
c
h
a
mm
a
d
Ha
l
d
i
W
i
d
i
a
n
t
o
C
o
m
put
e
r
S
c
i
e
n
c
e
De
pa
r
t
m
e
n
t
,
S
c
h
oo
l
o
f
C
o
m
put
e
r
S
c
i
e
nc
e
,
B
i
n
a
Nus
a
n
t
a
r
a
Uni
v
e
r
s
i
t
y
B
a
n
du
n
g
C
a
m
pu
s
,
J
a
ka
r
t
a
,
11480
,
I
n
do
n
e
s
i
a
E
m
a
i
l
:
m
o
c
h
a
m
a
d.
w
i
d
i
a
n
t
o
@
bi
nus
.
a
c
.
i
d
1.
I
NT
RODU
C
T
I
ON
E
n
t
r
e
pr
e
n
e
ur
s
hi
p
e
duc
a
t
i
o
n
c
o
n
t
i
n
u
e
s
to
g
r
o
w
b
e
c
a
us
e
o
f
i
t
s
b
e
ne
f
i
t
s
i
n
de
ve
l
o
p
i
n
g
s
t
ud
e
n
t
s
’
c
o
m
pe
t
e
nc
i
e
s
a
n
d
e
n
t
r
e
pr
e
n
e
ur
i
a
l
s
k
il
l
s
t
h
a
t
t
h
e
mi
nds
e
t
a
n
d
i
n
t
e
n
t
i
o
n
to
b
e
c
o
m
e
e
n
t
r
e
pr
e
n
e
ur
s
c
o
n
t
i
n
ue
to
gr
o
w
f
r
o
m
t
hi
s
a
c
t
i
vi
t
y
[
1]
.
A
c
t
i
vi
t
i
e
s
t
h
a
t
s
upp
o
r
t
s
t
ude
n
t
s
to
l
e
a
r
n
d
i
r
e
c
t
l
y
i
n
t
h
e
f
i
e
l
d
a
n
d
s
uppo
r
t
p
r
o
g
r
a
ms
c
a
n
im
pr
o
v
e
t
e
c
h
ni
c
a
l
s
k
il
l
s
a
s
e
n
t
r
e
pr
e
n
e
ur
s
[
2]
,
[
3]
.
I
n
a
dd
i
t
i
o
n
,
t
hi
s
e
n
t
r
e
pr
e
n
e
ur
s
hi
p
e
duc
a
t
i
o
n
c
a
n
h
e
lp
de
v
e
l
o
p
b
us
i
ne
s
s
pe
r
f
o
r
m
a
nc
e
[
4]
.
A
c
t
i
vi
t
i
e
s
t
h
a
t
a
r
e
s
upp
o
r
t
e
d
by
d
i
r
e
c
t
a
ppl
i
c
a
t
i
o
n
i
n
t
h
e
f
i
e
l
d,
a
n
e
c
o
s
y
s
t
e
m
t
h
a
t
e
n
c
o
ur
a
ge
s
s
t
ude
n
t
s
to
b
e
e
n
t
h
us
i
a
s
t
i
c
a
b
o
ut
s
o
l
vi
ng
pr
o
b
l
e
m
s
,
c
a
n
e
n
c
o
ur
a
ge
i
nn
o
v
a
t
i
ve
i
de
a
s
[
5]
W
i
t
h
uni
ve
r
s
i
t
i
e
s
be
i
n
g
a
bl
e
to
pl
a
y
a
r
o
l
e
i
n
b
us
i
ne
s
s
a
n
d
e
c
o
n
o
m
i
c
gr
o
w
t
h
,
e
n
t
r
e
p
r
e
n
e
ur
s
hi
p
e
duc
a
t
i
o
n
c
a
n
e
n
c
o
ur
a
ge
t
h
e
bi
r
t
h
o
f
i
nn
o
v
a
t
i
o
n
f
r
o
m
ne
w
b
u
s
i
ne
s
s
e
s
[
4]
.
Uni
ve
r
s
i
t
i
e
s
t
h
a
t
f
o
c
us
o
n
de
v
e
l
o
p
i
ng
e
n
t
r
e
pr
e
n
e
u
r
s
hi
p,
i
n
t
h
i
s
c
a
s
e
,
f
u
ll
y
s
uppo
r
t
t
h
e
bi
r
t
h
o
f
n
e
w
e
n
t
r
e
pr
e
n
e
ur
s
t
h
r
o
ugh
t
h
e
a
pp
l
i
c
a
t
i
o
n
o
f
e
n
t
r
e
pr
e
n
e
ur
s
hi
p
i
n
v
a
r
i
o
us
c
o
ur
s
e
s
,
c
r
e
a
t
i
v
e
pr
o
gr
a
m
s
,
uni
ve
r
s
i
t
y
-
b
a
s
e
d
b
us
i
ne
s
s
i
nc
u
b
a
t
or
s
,
a
n
d
ot
h
e
r
s
upp
o
r
t
i
n
g
f
a
c
il
i
t
i
e
s
t
h
a
t
c
a
n
b
e
a
goo
d
e
c
o
s
y
s
t
e
m
f
o
r
g
r
o
w
i
ng
n
e
w
e
n
t
r
e
pr
e
n
e
ur
s
[
6]
,
[
7
]
.
T
h
e
de
v
e
l
o
p
m
e
n
t
o
f
s
e
r
vice
s
,
t
e
a
c
hi
ng,
a
n
d
t
h
e
i
r
i
nf
l
ue
n
c
e
o
n
t
h
e
c
ur
r
i
c
u
l
u
m
a
r
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t
J
I
n
f
&
C
o
m
m
u
n
T
e
c
hn
o
l
I
S
S
N:
2252
-
8776
M
ac
hine
lear
ning
in
de
tec
ti
ng
and
int
e
r
pr
e
ti
ng
bu
s
ines
s
incubator
s
u
c
c
e
s
…
(
M
oc
ham
mad
Haldi
W
idi
anto
)
447
r
e
qu
i
r
e
d
to
m
e
e
t
s
t
ude
n
t
c
o
m
pe
t
e
n
c
i
e
s
t
o
o
b
t
a
i
n
t
h
e
b
e
s
t
r
e
s
u
l
t
s
[
8]
,
[
9]
.
I
n
a
dd
i
t
i
o
n
,
t
h
e
e
xi
s
t
e
n
c
e
o
f
a
s
y
s
t
e
m
a
n
d
pe
r
i
o
d
i
c
e
v
a
l
ua
t
i
o
n
a
r
e
e
s
s
e
n
t
i
a
l
i
n
u
n
d
e
r
s
t
a
n
d
i
ng
t
h
e
n
e
e
d
s
o
f
b
us
i
ne
s
s
s
t
ude
n
t
s
t
h
a
t
t
h
e
pe
r
f
o
r
m
a
n
c
e
o
f
s
e
r
vi
c
e
s
a
n
d
f
a
c
il
i
t
i
e
s
c
a
n
b
e
m
e
a
s
ur
e
d
[
10]
.
T
h
e
e
xi
s
t
e
n
c
e
o
f
s
o
un
d
s
y
s
t
e
m
a
n
d
s
e
r
vi
c
e
i
n
t
e
gr
a
t
i
o
n
b
e
t
we
e
n
u
ni
ve
r
s
i
t
i
e
s
a
n
d
b
us
i
ne
s
s
i
nc
u
b
a
t
o
r
s
c
a
n
a
f
f
e
c
t
t
h
e
de
v
e
l
o
p
m
e
n
t
o
f
b
us
i
ne
s
s
e
s
b
e
i
ng
m
a
n
a
ge
d
[
11]
.
C
ur
r
e
n
t
l
y
,
n
ot
m
a
ny
b
us
i
ne
s
s
e
s
in
c
u
b
a
t
o
r
s
m
e
a
s
ur
e
a
n
d
un
d
e
r
s
t
a
n
d
t
h
e
i
r
pa
r
t
i
c
i
pa
n
t
s
’
n
e
e
d
s
i
n
de
pt
h
.
T
hi
s
c
a
n
he
l
p
i
nc
u
ba
to
r
s
de
v
e
l
o
p
s
u
ppo
r
t
i
ng
f
a
c
il
i
t
i
e
s
s
uc
h
a
s
a
c
t
i
vi
t
i
e
s
a
n
d
m
e
n
t
or
i
n
g
[
12]
,
[
1
3]
.
T
h
e
s
uc
c
e
s
s
o
f
a
uni
ve
r
s
i
t
y
-
b
a
s
e
d
i
n
c
u
b
a
t
o
r
i
s
gr
e
a
t
ly
i
n
f
l
u
e
n
c
e
d
by
m
a
ny
f
a
c
to
r
s
t
h
a
t
wi
ll
a
f
f
e
c
t
i
t
s
pe
r
f
o
r
m
a
nc
e
.
S
t
a
r
t
i
n
g
f
r
o
m
i
n
t
e
r
n
a
l
u
ni
ve
r
s
i
t
y
s
uppor
t
,
f
a
c
il
i
t
i
e
s
i
n
t
h
e
i
nc
u
b
a
t
o
r
,
e
n
t
r
a
n
c
e
s
e
l
e
c
t
i
o
n
,
h
u
m
a
n
r
e
s
o
ur
c
e
c
a
pa
bil
i
t
i
e
s
,
kn
o
w
l
e
dge
o
f
t
e
c
hn
o
l
o
gy
a
n
d
f
i
na
n
c
e
,
a
n
d
m
a
n
a
g
e
r
i
a
l
.
T
h
e
n
,
e
x
t
e
r
n
a
l
s
uppo
r
t
,
s
uc
h
a
s
f
u
n
d
i
ng
s
uppo
r
t
,
b
us
i
n
e
s
s
n
e
t
wo
r
ks
,
a
n
d
gov
e
r
nm
e
n
t
po
l
i
c
i
e
s
[
14]
,
[
15]
.
T
h
e
r
e
f
o
r
e
,
a
m
a
na
ge
r
i
s
n
e
e
de
d,
a
s
we
l
l
a
s
goo
d
m
a
na
ge
m
e
n
t
a
n
d
m
e
a
s
ur
a
bl
e
e
v
a
l
ua
t
i
o
n
a
n
d
m
e
a
s
ur
e
m
e
n
t
f
o
r
s
uc
c
e
s
s
i
n
a
b
u
s
i
ne
s
s
i
n
c
u
b
a
t
o
r
[
16
].
P
r
e
d
i
c
t
i
n
g,
c
l
a
s
s
if
i
c
a
t
i
o
n
,
c
l
u
s
t
e
r
i
n
g,
a
n
d
i
n
t
e
r
pr
e
t
a
t
i
o
n
a
r
e
n
e
c
e
s
s
a
r
y
,
e
s
p
e
c
i
a
ll
y
w
h
e
n
b
u
il
d
i
ng
a
s
us
t
a
i
n
a
bl
e
b
us
i
ne
s
s
.
O
n
e
wa
y
i
s
by
ut
i
l
i
z
i
ng
a
r
t
i
f
ic
i
a
l
i
n
t
e
ll
i
g
e
n
c
e
(
A
I
)
[
17]
,
[
18]
,
H
o
we
v
e
r
,
i
t
s
us
e
n
e
e
d
s
to
b
e
pa
i
d
a
t
t
e
n
t
i
o
n
to,
e
s
pe
c
i
a
l
ly
f
o
r
i
t
s
b
us
i
ne
s
s
pur
po
s
e
s
[
19]
,
[
20]
A
I
a
l
s
o
do
e
s
n
ot
s
t
a
n
d
a
l
o
n
e
b
e
c
a
us
e
i
t
h
a
s
ot
h
e
r
r
e
s
e
a
r
c
h
b
r
a
n
c
h
e
s
,
s
uc
h
a
s
m
a
c
hi
ne
l
e
a
r
ni
ng
(
M
L
)
[
21]
,
de
e
p
l
e
a
r
ni
ng
(
D
L
)
[
22]
,
a
n
d
t
r
a
n
s
f
e
r
l
e
a
r
ni
ng
(
T
L
)
.
On
t
h
e
ot
h
e
r
h
a
n
d,
t
h
e
i
r
us
e
s
a
r
e
d
i
f
f
e
r
e
nt.
H
o
we
v
e
r
,
i
n
b
u
s
i
ne
s
s
c
a
s
e
s
,
i
t
i
s
e
x
pe
c
t
e
d
to
us
e
ML
b
e
c
a
us
e
t
h
e
da
t
a
us
e
d
i
s
us
ua
ll
y
a
l
o
t
a
n
d
c
a
n
b
e
us
e
d
a
s
tr
a
i
ni
ng
da
t
a
[
23]
,
[
24
]
.
T
hi
s
A
I
t
e
c
h
n
o
l
o
g
y
a
l
s
o
c
h
a
n
g
e
s
h
o
w
c
o
m
pa
ni
e
s
do
b
us
i
ne
s
s
,
a
l
l
o
w
i
ng
t
h
e
m
t
o
a
n
a
l
y
z
e
da
t
a
a
nd
a
uto
m
a
t
e
de
c
i
s
i
o
n
-
m
a
k
i
ng
pr
o
c
e
s
s
e
s
.
B
y
l
o
o
k
i
ng
a
t
hi
s
t
or
i
c
a
l
da
t
a
,
M
L
a
l
go
r
i
t
hm
s
c
a
n
pr
e
d
i
c
t
f
ut
ur
e
po
s
s
i
bil
i
t
i
e
s
,
whi
c
h
i
s
i
nva
l
ua
bl
e
f
o
r
i
nv
e
n
t
o
r
y
m
a
n
a
ge
m
e
n
t
,
de
m
a
n
d
f
o
r
e
c
a
s
t
i
n
g,
a
n
d
f
i
na
n
c
i
a
l
p
l
a
nni
ng.
B
us
i
ne
s
s
e
s
a
r
e
us
i
n
g
M
L
to
ga
i
n
de
e
pe
r
i
n
s
i
g
h
t
s
i
n
to
c
us
to
m
e
r
b
e
ha
vi
o
r
,
pr
e
f
e
r
e
nc
e
s
,
a
n
d
e
n
ga
ge
m
e
n
t
,
r
e
s
u
l
t
i
n
g
i
n
m
o
r
e
pe
r
s
o
n
a
li
z
e
d
s
e
r
vi
c
e
s
a
n
d
pr
o
duc
t
s
[
25
]
.
H
o
we
v
e
r
,
s
e
v
e
r
a
l
que
s
t
i
o
ns
a
r
i
s
e
a
b
o
ut
h
ow
to
us
e
i
t
o
r
c
o
l
l
a
b
o
r
a
t
e
wi
t
h
i
t
,
wh
e
r
e
s
o
m
e
r
e
s
e
a
r
c
h
m
a
y
o
nl
y
us
e
M
L
a
l
o
n
e
w
i
t
h
o
ut
c
r
e
a
t
i
n
g
a
s
t
a
r
t
o
r
a
r
c
hi
t
e
c
t
ur
e
f
o
r
i
t
s
c
r
e
a
t
i
o
n
.
S
o
,
i
t
i
s
f
e
l
t
t
h
a
t
t
h
e
us
e
o
f
M
L
i
s
not
o
p
t
i
m
a
l
[
26]
,
[
27
]
.
P
r
e
vi
o
us
r
e
s
e
a
r
c
h
ha
s
n
o
t
us
e
d
M
L
a
s
m
uc
h
f
o
r
b
us
i
ne
s
s
c
l
a
s
s
i
f
i
c
a
t
i
o
n
a
n
d
i
n
t
e
r
pr
e
t
a
t
i
o
n
.
M
a
r
t
í
n
e
z
e
t
al.
[
28]
,
u
t
i
li
z
e
gr
a
d
i
e
n
t
b
oo
s
t
i
n
g
i
n
i
t
s
us
e
i
n
b
us
i
ne
s
s
.
K
r
a
u
s
e
t
al.
[
29
]
,
u
t
i
li
z
e
DL
i
n
b
us
i
ne
s
s
c
o
n
d
i
t
i
o
n
s
.
Na
k
h
a
l
e
t
al.
[
30]
,
l
i
ke
o
t
h
e
r
s
,
t
h
e
y
a
l
s
o
us
e
M
L
i
n
b
u
s
i
ne
s
s
.
Ho
we
v
e
r
,
t
h
e
r
e
i
s
s
t
i
ll
not
m
uc
h
r
e
s
e
a
r
c
h
th
a
t
e
m
ph
a
s
i
z
e
s
a
r
c
hi
t
e
c
tu
r
a
l
c
r
e
a
t
i
o
n
i
n
c
l
a
s
s
i
f
y
i
n
g
a
n
d
i
n
te
r
p
r
e
t
i
n
g
i
t.
H
owe
v
e
r
,
s
o
m
e
a
pp
r
oa
c
h
e
s
r
a
r
e
l
y
di
s
c
us
s
h
ow
to
i
n
te
r
p
r
e
t
th
e
a
l
g
or
i
t
h
m
’
s
r
e
s
u
l
t
s
.
T
h
e
r
e
f
o
r
e
,
t
h
i
s
wa
s
a
d
i
s
a
dv
a
n
t
a
ge
i
n
t
h
e
p
r
e
vi
ou
s
s
tu
d
y
[
31
]
.
T
hi
s
r
e
s
e
a
r
c
h
c
o
n
t
r
i
b
ut
e
s
a
n
d
i
nve
s
t
i
ga
t
e
s
by
t
a
ki
ng
a
d
v
a
n
t
a
ge
o
f
pr
e
vi
o
u
s
r
e
s
e
a
r
c
h
’
s
l
im
i
t
a
t
i
o
n
s
.
P
r
e
vi
o
us
r
e
s
e
a
r
c
h
o
nly
d
i
s
c
us
s
e
d
pr
e
d
i
c
t
i
o
n
a
n
d
c
l
a
s
s
if
i
c
a
t
i
o
n
.
T
hi
s
h
a
s
be
e
n
c
l
a
r
i
f
i
e
d
by
t
h
e
n
e
e
d
f
o
r
a
wa
y
to
f
i
n
d
t
h
e
i
n
t
e
r
pr
e
t
a
t
i
o
n
o
f
t
h
e
M
L
r
e
s
u
l
t
s
.
M
e
a
n
w
hil
e
,
t
h
e
r
e
i
s
n
o
t
m
uc
h
c
l
a
r
if
i
c
a
t
i
o
n
r
e
ga
r
d
i
n
g
t
he
i
n
t
e
r
pr
e
t
a
t
i
o
n
o
f
t
h
e
da
t
a
b
e
c
a
us
e
t
hi
s
e
x
p
l
a
n
a
t
i
o
n
i
s
n
e
e
de
d
t
o
un
de
r
s
t
a
n
d
h
o
w
t
h
e
M
L
l
e
a
r
ni
n
g
a
l
go
r
i
t
h
m
wo
r
ks
.
I
n
t
e
r
p
r
e
t
a
t
i
o
n
o
f
r
e
s
u
l
t
s
i
s
us
ua
ll
y
us
e
d
s
o
t
h
a
t
h
u
m
a
ns
be
tt
e
r
un
de
r
s
t
a
n
d
t
h
e
i
nf
l
ue
n
c
e
o
f
pr
e
d
i
c
t
i
o
n
r
e
s
u
l
t
s
o
n
e
xi
s
t
i
n
g
f
e
a
t
ur
e
s
.
T
h
e
r
e
f
o
r
e
,
t
hi
s
r
e
s
e
a
r
c
h
w
i
ll
f
il
l
t
h
e
ga
ps
i
n
pr
e
vi
o
us
r
e
s
e
a
r
c
h
by
pr
o
po
s
i
n
g
s
e
v
e
r
a
l
M
L
m
o
de
l
a
r
c
hi
t
e
c
t
ur
e
s
i
n
t
hi
s
s
t
udy
to
pr
o
vi
de
ne
w
s
o
l
ut
i
o
n
s
f
o
r
i
n
t
e
r
pr
e
t
i
n
g
M
L
r
e
s
u
l
t
s
a
n
d
c
a
n
a
l
s
o
i
m
pr
o
v
e
M
L
pe
r
f
o
r
m
a
n
c
e
.
T
hi
s
r
e
s
e
a
r
c
h
a
im
s
t
o
c
r
e
a
t
e
a
n
A
I
m
o
de
l
a
r
c
hi
t
e
c
t
ur
e
to
h
e
l
p
s
e
e
t
h
e
s
uc
c
e
s
s
a
n
d
i
n
t
e
r
p
r
e
t
a
t
i
o
n
o
f
t
h
e
s
uc
c
e
s
s
o
f
t
h
e
i
n
c
u
b
a
t
o
r
b
us
i
ne
s
s
.
T
h
e
f
o
l
l
o
w
i
n
g
a
r
e
hi
s
m
a
i
n
c
o
n
t
r
i
b
ut
i
o
n
s
:
a)
T
hi
s
s
t
ud
y
b
u
il
ds
a
m
o
de
l
a
r
c
hi
t
e
c
t
ur
e
b
a
s
e
d
o
n
M
L
a
l
go
r
i
t
hm
a
n
d
l
o
o
ks
f
o
r
a
goo
d
a
l
go
r
i
t
hm
b
a
s
e
d
o
n
i
t
s
c
l
a
s
s
i
f
i
c
a
t
i
o
n
.
b)
T
h
e
pr
o
p
o
s
e
d
m
o
de
l
a
r
c
hi
t
e
c
t
ur
e
i
s
us
e
d
t
o
c
l
a
s
s
i
f
y
i
nc
u
b
a
t
or
b
us
i
n
e
s
s
e
s
ba
s
e
d
o
n
e
xi
s
t
i
ng
da
t
a
.
c)
T
h
e
r
e
s
u
l
t
s
o
f
t
h
e
b
e
s
t
M
L
m
o
de
l
n
e
e
d
t
o
b
e
i
n
t
e
r
pr
e
t
e
d
f
r
o
m
pr
o
p
o
s
e
d
m
o
de
l
us
i
ng
s
e
v
e
r
a
l
goo
d
a
l
go
r
i
t
hm
s
to
f
i
n
d
do
m
i
na
n
t
f
e
a
t
ur
e
s
.
d)
P
r
e
s
e
n
t
c
o
m
p
l
e
t
e
da
t
a
s
e
t
s
i
n
t
h
e
f
o
r
m
o
f
i
n
c
u
b
a
t
o
r
b
us
i
ne
s
s
da
t
a
.
T
h
e
a
r
t
i
c
l
e
h
a
s
f
o
ur
s
e
c
t
i
o
ns
i
n
t
h
e
l
a
s
t
s
e
c
t
i
o
n
.
S
e
c
t
i
o
n
1
e
x
p
l
a
i
ns
t
h
e
pr
o
bl
e
m
de
s
c
r
i
pt
i
o
n
a
n
d
i
n
t
r
o
duc
t
i
o
n
.
S
e
c
t
i
o
n
2
e
x
p
l
a
i
ns
t
h
e
pr
o
p
o
s
e
d
m
o
de
l
.
S
e
c
t
i
o
n
3
e
x
p
l
a
i
ns
t
h
e
i
m
p
l
e
m
e
n
t
a
t
i
o
n
a
n
d
t
r
i
a
l
r
e
s
u
l
t
s
.
F
i
na
ll
y
,
s
e
c
t
i
o
n
4
i
s
f
o
l
l
o
we
d
by
c
o
n
c
l
u
s
i
o
n
s
a
n
d
s
ugge
s
t
i
o
ns
f
o
r
f
ur
t
h
e
r
r
e
s
e
a
r
c
h
.
2.
RE
S
E
AR
CH
M
E
T
HO
D
T
hi
s
s
e
c
t
i
o
n
w
il
l
e
x
p
l
a
i
n
t
h
e
s
t
a
ge
s
o
f
f
o
r
m
i
ng
a
n
m
o
de
l
a
r
c
hi
t
e
c
t
ur
e
f
o
r
a
n
i
nc
u
b
a
t
o
r
b
us
i
ne
s
s
.
P
r
e
vi
o
us
r
e
s
e
a
r
c
h
e
r
s
h
a
v
e
us
e
d
m
a
ny
ge
n
e
r
a
l
m
o
d
e
l
s
,
b
ut
t
h
e
b
e
s
t
M
L
a
l
go
r
i
t
hm
s
m
u
s
t
b
e
f
o
un
d
whe
n
us
i
ng
c
l
a
s
s
if
i
c
a
t
i
o
n
i
n
i
nc
u
b
a
t
or
b
us
i
n
e
s
s
e
s
.
T
h
e
n
,
t
h
e
b
e
s
t
M
L
a
l
go
r
i
t
hm
m
us
t
b
e
i
n
t
e
r
pr
e
t
e
d
to
ob
t
a
i
n
t
h
e
do
m
i
na
n
t
f
e
a
t
ur
e
s
.
F
i
gur
e
1
s
h
o
ws
t
h
e
r
e
s
e
a
r
c
h
pr
o
c
e
s
s
f
l
o
w
f
o
r
c
l
a
s
s
i
f
yi
ng
b
us
i
ne
s
s
s
uc
c
e
s
s
a
n
d
i
n
t
e
r
pr
e
t
i
ng
t
h
e
s
uc
c
e
s
s
r
e
s
u
l
t
s
,
s
t
a
r
t
i
n
g
f
r
o
m
“
s
t
a
r
t
”
to
“
F
i
n
i
s
h
.
”
T
h
e
f
o
l
l
o
w
i
ng
a
r
e
t
h
e
s
t
a
ge
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8776
I
n
t
J
I
n
f
&
C
o
m
m
u
n
T
e
c
hn
o
l
,
Vo
l
.
14
,
N
o.
2
,
A
ugus
t
20
25
:
446
-
456
448
a)
T
h
e
f
i
r
s
t
ph
a
s
e
i
s
t
h
e
da
t
a
i
n
t
r
o
duc
t
i
o
n
p
h
a
s
e
.
I
nf
o
r
m
a
t
i
o
n
c
o
m
e
s
f
r
o
m
pr
i
m
a
r
y
da
t
a
,
n
a
m
e
ly
t
h
e
B
a
n
du
n
g
bi
nus
b
us
i
ne
s
s
i
nc
u
b
a
t
or
.
T
hi
s
da
t
a
c
o
l
l
e
c
t
i
o
n
wa
s
c
o
l
l
e
c
t
e
d
by
B
a
n
du
n
g
bi
nus
i
n
c
u
b
a
t
o
r
b
us
i
ne
s
s
e
s
.
T
h
e
da
t
a
s
e
t
c
o
n
t
a
i
n
s
151
da
t
a
wi
t
h
17
f
e
a
t
ur
e
s
.
W
i
t
h
t
h
e
de
t
e
c
t
e
d
v
a
r
i
a
bl
e
b
e
i
ng
“
T
a
r
ge
t
”
.
b)
Ne
x
t
,
we
s
t
a
r
t
by
h
a
n
d
li
ng
t
h
e
da
t
a
b
e
c
a
us
e
i
t
w
il
l
b
e
pr
o
c
e
s
s
e
d.
T
h
e
a
ut
h
o
r
wi
ll
l
o
o
k
f
o
r
s
e
v
e
r
a
l
f
e
a
tur
e
s
t
h
a
t
d
o
n
ot
a
f
f
e
c
t
t
h
e
c
l
a
s
s
if
i
c
a
t
i
o
n
r
e
s
u
l
t
s
.
T
h
e
r
e
f
o
r
e
,
t
h
e
s
e
l
e
c
t
i
o
n
i
s
c
a
r
r
i
e
d
o
u
t
to
m
a
xi
mi
z
e
t
h
e
r
e
s
u
l
t
s
o
f
c
l
a
s
s
if
i
c
a
t
i
o
n
a
n
d
i
n
t
e
r
pr
e
t
a
t
i
o
n
.
T
h
e
f
e
a
t
ur
e
r
e
s
u
l
t
s
a
f
t
e
r
e
l
im
i
na
t
i
o
n
a
r
e
15
f
e
a
t
ur
e
s
.
c)
T
h
e
n
e
x
t
s
t
a
ge
,
t
h
e
f
i
xe
d
da
t
a
,
i
s
c
a
r
r
i
e
d
o
u
t
b
y
P
e
a
r
s
o
n
c
o
r
r
e
l
a
t
i
o
n
by
l
o
o
k
i
n
g
f
o
r
a
h
e
a
t
m
a
p
a
n
d
e
x
a
mi
n
i
ng
t
h
e
c
o
r
r
e
l
a
t
i
o
n
r
e
s
u
l
t
s
o
f
e
a
c
h
va
r
i
a
bl
e
,
e
s
pe
c
i
a
ll
y
t
h
e
pr
i
m
a
r
y
v
a
r
i
a
bl
e
,
“
T
ar
ge
t
”
.
d)
t
h
e
da
t
a
wa
s
a
l
s
o
t
r
e
a
t
e
d
to
c
o
nf
o
r
m
t
o
a
n
or
m
a
l
d
i
s
t
r
i
b
ut
i
o
n
b
e
c
a
us
e
a
l
l
da
t
a
wa
s
n
o
t
n
or
m
a
l
l
y
d
i
s
t
r
i
b
ut
e
d.
A
t
t
hi
s
s
t
a
ge
,
t
h
e
r
e
s
u
l
t
r
a
n
ge
i
s
[
0
to
1]
.
T
h
e
r
e
f
o
r
e
,
i
t
i
s
us
ua
ll
y
d
i
s
t
r
i
b
ut
e
d.
A
t
t
hi
s
p
ha
s
e
,
d
i
vi
de
d
i
n
t
o
2
wi
t
h
a
c
o
m
p
a
r
i
s
o
n
b
e
t
we
e
n
t
r
a
i
ni
ng
da
t
a
a
n
d
t
e
s
t
da
t
a
,
n
a
m
e
ly
90/10
f
o
r
t
r
a
i
ni
ng
da
t
a
.
e)
A
t
t
hi
s
s
t
a
ge
,
v
a
r
i
o
us
s
u
i
t
a
bl
e
ML
a
l
go
r
i
t
hm
s
a
r
e
us
e
d,
whi
c
h
w
i
ll
b
e
c
o
m
e
a
b
e
n
c
hm
a
r
k
i
n
t
h
e
n
e
x
t
s
tage
o
f
t
h
e
i
n
t
e
r
pr
e
t
a
t
i
o
n
pr
o
c
e
s
s
.
f)
A
t
t
hi
s
s
t
a
ge
,
t
h
e
t
e
s
t
r
e
s
u
l
t
s
a
r
e
t
h
e
pe
r
f
o
r
m
a
n
c
e
o
f
a
ll
t
h
e
s
e
l
e
c
t
e
d
M
L
a
l
go
r
i
t
h
m
s
.
g)
Af
t
e
r
l
o
o
ki
n
g
f
o
r
pe
r
f
o
r
m
a
n
c
e
,
s
e
v
e
r
a
l
pa
r
a
m
e
t
e
r
s
a
r
e
e
v
a
l
ua
t
e
d,
i
n
c
l
ud
i
ng
a
c
c
ur
a
c
y
,
r
e
c
a
l
l
,
F
1
-
s
c
o
r
e
,
pr
e
c
i
s
i
o
n
,
a
n
d
c
o
m
put
i
n
g
t
i
m
e
.
T
hi
s
a
im
s
to
ge
t
r
e
s
u
l
t
s
f
r
o
m
a
r
c
hi
t
e
c
t
ur
e
.
h)
Af
t
e
r
t
h
a
t,
t
h
e
r
e
s
u
l
t
s
o
f
t
h
e
b
e
s
t
M
L
m
o
de
l
w
i
ll
be
i
n
t
e
r
pr
e
t
e
d
f
o
r
d
o
m
i
n
a
n
t
f
e
a
t
ur
e
s
us
i
n
g
s
e
l
e
c
t
K
-
b
e
s
t
.
T
hi
s
f
i
na
l
r
e
s
u
l
t
i
s
h
e
l
p
f
u
l
f
o
r
de
t
e
r
m
i
n
i
ng
w
hi
c
h
f
e
a
t
ur
e
s
a
r
e
pa
r
a
m
e
t
e
r
s
i
n
t
h
e
i
n
c
u
b
a
t
o
r
b
us
i
n
e
s
s
’
s
s
uc
c
e
s
s
.
F
i
gur
e
1
.
R
e
s
e
a
r
c
h
pr
o
p
o
s
e
d
m
o
de
l
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t
J
I
n
f
&
C
o
m
m
u
n
T
e
c
hn
o
l
I
S
S
N:
2252
-
8776
M
ac
hine
lear
ning
in
de
tec
ti
ng
and
int
e
r
pr
e
ti
ng
bu
s
ines
s
incubator
s
u
c
c
e
s
…
(
M
oc
ham
mad
Haldi
W
idi
anto
)
449
T
h
e
pr
o
p
o
s
e
d
m
o
de
l
f
l
o
w
i
s
us
e
d
to
i
nc
u
b
a
t
e
a
s
uc
c
e
s
s
f
u
l
pr
o
c
e
s
s
a
s
s
h
o
wn
i
n
F
i
gur
e
1.
T
h
e
da
t
a
us
e
d
i
n
t
hi
s
s
t
ud
y
ut
i
li
z
e
s
pr
i
m
a
r
y
da
t
a
f
r
o
m
[
32]
.
I
n
F
i
gur
e
1
t
h
e
a
ut
h
or
o
nl
y
us
e
s
a
f
e
w
a
l
go
r
i
t
hms
us
e
d
in
t
h
e
pr
o
p
o
s
e
d
m
o
de
l
,
b
e
c
a
us
e
t
h
e
s
e
M
L
a
l
go
r
i
t
hm
s
a
r
e
v
e
r
y
c
o
m
m
o
nly
us
e
d
i
n
r
e
s
e
a
r
c
h
.
I
n
s
p
i
r
e
d
by
t
his
w
i
de
ly
us
e
d
m
o
de
l
,
t
h
e
M
L
a
l
go
r
i
t
hm
i
n
F
i
gur
e
1
i
s
us
e
d.
2.
1.
Dat
a
in
f
or
m
at
ion
A
c
c
o
r
d
i
n
g
t
o
t
h
e
a
u
t
h
o
r
,
t
h
e
da
t
a
us
e
d
i
s
a
n
i
nc
u
ba
to
r
f
r
o
m
B
i
nus
B
a
n
du
n
g,
whi
c
h
wa
s
pr
o
c
e
s
s
e
d
to
r
e
m
o
v
e
us
e
l
e
s
s
da
t
a
a
n
d
pr
o
duc
e
pr
o
c
e
s
s
e
d
da
t
a
a
s
s
h
o
wn
i
n
T
a
bl
e
1.
T
a
bl
e
1
e
x
p
l
a
i
ns
t
h
e
da
t
a
us
e
d
i
n
t
his
s
t
udy
ba
s
e
d
o
n
a
b
us
i
ne
s
s
i
nc
u
b
a
t
or
.
F
e
a
t
ur
e
n
o
16
’
s
pr
e
d
i
c
t
i
o
n
t
a
r
ge
t
i
s
“
T
ar
ge
t
.
”
T
h
e
da
t
a
t
a
ke
n
r
e
s
u
l
t
s
f
r
o
m
a
n
i
n
c
u
b
a
t
o
r
b
us
i
ne
s
s
,
whi
c
h
h
a
s
a
t
a
r
ge
t
w
h
e
n
t
h
e
f
i
na
l
r
e
v
e
n
ue
c
a
n
e
xc
e
e
d
20
m
i
ll
i
o
n
r
up
i
a
h
s
.
T
h
e
n
,
t
h
e
t
a
r
ge
t
wi
ll
be
“
1,
”
whe
r
e
a
s
if
i
t
do
e
s
n
o
t
m
e
e
t
t
h
e
t
a
r
ge
t,
i
t
w
i
ll
be
“
0
”
.
T
h
e
im
ba
l
a
n
c
e
i
s
s
ue
t
a
r
ge
t
h
a
s
b
e
e
n
a
c
hi
e
ve
d
f
o
r
e
a
c
h
f
e
a
t
ur
e
s
o
t
h
a
t
n
o
m
o
r
e
i
n
-
de
pt
h
m
a
n
a
ge
m
e
n
t
i
s
ne
e
de
d
to
ge
t
m
a
xi
m
u
m
r
e
s
u
l
t
s
.
T
a
bl
e
1.
Da
t
a
i
nf
o
r
m
a
t
i
o
n
No
F
e
a
tu
r
e
N
umbe
r
of
da
ta
s
e
ts
D
a
ta
t
y
pe
1
B
us
i
ne
s
s
n
a
me
151
S
tr
in
g
2
B
us
in
e
s
s
c
a
t
e
g
o
r
y
151
S
tr
in
g
3
B
us
in
e
s
s
te
a
m m
e
mb
e
r
151
N
ume
r
i
c
4
F
ir
s
t
r
e
ve
nu
e
151
N
ume
r
i
c
5
L
a
s
t
r
e
ve
nue
151
N
ume
r
i
c
6
N
umbe
r
of
e
mpl
oy
e
e
s
151
N
ume
r
i
c
7
E
xt
e
r
na
l
c
o
ll
a
b
or
a
ti
o
n
151
N
ume
r
i
c
8
T
ot
a
l
f
o
ll
o
w
s
t
he
ba
z
a
a
r
151
N
ume
r
ic
9
N
umbe
r
of
o
n
li
ne
a
d
ve
r
ti
s
e
m
e
nt
s
151
N
ume
r
i
c
10
U
s
in
g T
ik
T
ok
l
i
ve
151
S
tr
in
g
11
A
ddi
ti
o
na
l
in
ve
s
tm
e
nt
f
r
o
m
e
x
t
e
r
na
l
151
S
tr
in
g
12
c
ove
r
e
d b
y
t
he
me
di
a
151
S
tr
in
g
13
o
w
n t
r
a
d
e
ma
r
k r
ig
h
ts
151
S
tr
in
g
14
ha
ve
a
ha
la
l
c
e
r
ti
f
i
c
a
t
e
151
S
tr
in
g
15
N
umbe
r
of
t
y
pe
s
of
s
a
le
s
m
e
th
o
ds
151
S
tr
in
g
16
T
a
r
ge
t
151
N
ume
r
i
c
All
t
h
e
f
e
a
t
ur
e
s
i
n
T
a
bl
e
1
a
r
e
s
e
l
e
c
t
e
d
a
n
d
pr
o
c
e
s
s
e
d
i
n
t
h
e
d
a
t
a
h
a
n
d
li
ng
s
e
c
t
i
o
n
a
s
s
h
o
w
n
in
F
i
gur
e
1
,
b
e
c
a
u
s
e
t
h
e
r
e
i
s
n
o
t
too
m
uc
h
da
t
a
,
t
h
e
r
e
i
s
n
o
s
p
l
i
t
t
i
n
g
o
f
s
m
a
l
l
da
t
a
.
B
e
c
a
us
e
t
h
e
da
t
a
us
e
d
i
s
n
o
t
too
m
uc
h
,
t
h
e
c
h
a
l
l
e
n
g
e
i
n
t
h
e
pr
o
p
o
s
e
d
m
o
de
l
i
s
m
a
n
a
g
i
ng
t
h
e
l
i
mi
t
e
d
da
t
a
i
n
o
r
de
r
to
ge
t
g
oo
d
c
o
nf
us
i
o
n
m
a
t
r
i
x
r
e
s
u
l
t
s
.
2.
2.
Cor
r
e
l
at
ion
A
t
t
hi
s
ph
a
s
e
,
a
c
o
r
r
e
l
a
t
i
o
n
t
e
s
t
(
,
)
is
c
a
r
r
i
e
d
o
u
t
o
n
t
h
e
da
t
a
s
e
t
.
In
(
1
)
t
h
e
c
o
r
r
e
l
a
t
i
o
n
f
o
r
m
u
la
i
t
s
e
lf
[
33]
.
C
o
r
r
e
l
a
t
i
o
n
i
s
u
s
e
d
t
o
s
e
e
h
o
w
v
a
r
i
a
bles
r
e
l
a
t
e
to
e
a
c
h
ot
h
e
r
,
a
n
d
a
c
c
o
r
d
i
n
g
t
o
t
h
e
a
ut
h
o
r
t
h
i
s
is
v
e
r
y
im
po
r
t
a
n
t
to
u
t
i
l
i
z
e
:
(
,
)
=
∑
(
−
_
)
(
−
_
)
=
1
√
∑
(
−
_
)
2
=
1
√
∑
(
−
_
)
2
=
1
(
1)
w
hi
c
h
:
r
(
,
)
:
c
or
r
e
l
a
t
i
o
n
c
o
e
f
f
i
c
i
e
n
t
.
x
:
x
to
-
i
.
_
:
x
da
t
a
m
e
a
n
.
y
:
y
t
o
-
i
.
2.
3.
L
ogis
t
ic
r
e
g
r
e
s
s
ion
L
o
gi
s
t
i
c
r
e
gr
e
s
s
i
o
n
(
L
R
)
i
s
us
e
d
i
n
da
t
a
a
n
a
l
y
s
i
s
t
e
c
hni
que
s
,
e
s
pe
c
i
a
ll
y
i
n
t
h
e
r
e
l
a
t
i
o
ns
hi
p
o
f
s
e
ve
r
a
l
v
a
r
i
a
bl
e
s
u
s
e
d
f
o
r
c
l
a
s
s
i
f
i
c
a
t
i
o
n
a
l
go
r
i
t
hm
s
.
T
hi
s
v
a
r
i
a
bl
e
i
s
u
s
e
d
i
n
gr
o
upi
n
g
c
l
a
s
s
i
f
i
c
a
t
i
o
n
b
a
s
e
d
o
n
t
h
e
i
n
f
l
u
e
n
c
e
a
n
d
r
e
l
a
t
i
o
n
s
hi
p
o
f
s
e
v
e
r
a
l
v
a
r
i
a
bl
e
s
[
34]
.
T
h
e
f
o
r
m
u
l
a
f
o
u
n
d
i
n
(
2)
:
(
1
−
)
=
0
+
1
1
+
2
2
+
⋯
+
(
2)
whi
c
h
:
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8776
I
n
t
J
I
n
f
&
C
o
m
m
u
n
T
e
c
hn
o
l
,
Vo
l
.
14
,
N
o.
2
,
A
ugus
t
20
25
:
446
-
456
450
(p
)
:
t
h
e
pr
o
b
a
bil
i
t
y
o
f
t
h
e
de
s
i
r
e
d
e
v
e
n
t
.
(
)
:
i
n
t
e
r
c
e
pt
.
(
1
.
.
.
)
:
i
s
t
h
e
c
o
e
f
f
i
c
i
e
n
t
f
o
r
t
h
e
pr
e
di
c
t
o
r
v
a
r
i
a
bl
e
(
1
…
)
.
2.
4.
S
V
M
c
l
as
s
if
icat
ion
S
uppor
t
v
e
c
to
r
m
a
c
hi
ne
(
S
VM
)
c
l
a
s
s
if
i
c
a
t
i
o
n
i
s
a
t
m
o
de
l
f
o
r
f
i
n
d
i
ng
t
h
e
b
e
s
t
hy
pe
r
p
l
a
ne
to
di
vi
d
e
c
l
a
s
s
e
s
li
ne
a
r
ly
.
I
n
S
VM
,
t
h
e
go
a
l
is
to
l
o
o
ki
n
g
f
o
r
a
hy
pe
r
p
l
a
n
e
i
n
N
-
d
i
m
e
ns
i
o
na
l
s
p
a
c
e
(N
-
n
u
m
b
e
r
o
f
f
e
a
t
ur
e
s
)
t
h
a
t
un
a
m
bi
guo
us
l
y
c
las
s
if
i
e
s
da
t
a
p
o
i
n
t
s
.
I
t
i
s
us
e
d
to
i
de
n
t
i
f
y
da
t
a
wi
t
h
s
i
mi
l
a
r
pa
t
t
e
r
n
s
a
c
r
o
s
s
t
h
e
r
e
by
m
a
xim
i
z
i
ng
t
h
e
m
a
r
g
i
n
b
e
t
we
e
n
c
l
a
s
s
e
s
.
T
h
e
f
o
r
m
u
l
a
f
o
r
S
VM
i
s
a
s
(
3)
[
35]
:
.
−
(
3)
w
hi
c
h
:
(
w)
:
t
h
e
we
i
g
h
t
v
e
c
t
or
i
s
a
v
e
r
a
ge
t
o
t
h
e
hy
pe
r
p
l
a
n
e
.
(
x
)
:
a
f
e
a
t
ur
e
v
e
c
t
or
(
b
)
:
bi
a
s
2.
5.
De
c
is
ion
t
r
e
e
M
L
a
l
go
r
i
t
hm
t
h
a
t
us
e
s
a
t
r
e
e
s
tr
uc
t
ur
e
o
r
de
c
i
s
i
o
n
hi
e
r
a
r
c
hy
.
W
h
e
r
e
t
h
e
n
o
de
s
i
n
t
h
e
t
r
e
e
r
e
pr
e
s
e
n
t
f
e
a
t
ur
e
s
,
t
h
e
de
c
i
s
i
o
n
b
r
a
nc
h
e
s
a
n
d
e
a
c
h
l
e
a
f
r
e
pr
e
s
e
n
t
t
h
e
o
u
t
c
o
m
e
.
T
h
e
f
o
r
m
u
l
a
f
o
r
t
h
e
de
c
i
s
i
o
n
tr
e
e
(
D
T
)
a
ppr
o
a
c
h
i
s
(
4)
[
36]
:
ℎ
(
)
=
−
∑
2
=
1
(
4)
w
hi
c
h
p
i
:
t
h
e
s
a
m
p
l
e
pr
o
p
or
t
i
o
n
f
r
o
m
c
l
a
s
s
-
i
.
2.
6.
Rand
om
f
or
e
s
t
M
L
m
e
t
h
o
d
t
h
a
t
s
t
a
r
t
s
f
r
o
m
DT
c
h
a
n
g
e
s
a
n
d
b
e
c
o
m
e
s
a
f
a
m
o
us
c
l
a
s
s
if
i
c
a
t
i
o
n
(
r
a
n
do
m
f
o
r
e
s
t
(
R
F
)
)
.
T
h
e
f
o
l
l
o
w
i
n
g
i
s
t
h
e
b
a
s
i
c
f
o
r
m
u
l
a
us
e
d
i
n
RF
f
o
r
c
l
a
s
s
if
i
c
a
t
i
o
n
pr
e
s
e
n
t
e
d
i
n
(
5)
.
T
h
i
s
e
qua
t
i
o
n
i
s
a
de
r
i
v
a
t
i
v
e
o
f
t
h
e
pr
e
vi
o
us
us
e
o
f
DT
,
b
e
c
a
us
e
R
F
s
a
r
e
de
r
i
va
t
i
ve
s
o
f
DT
[
37]
.
̂
=
{
ℎ
(
,
)
,
=
1
,
…
,
}
(
5)
W
hi
c
h
:
(
̂
)
:
t
h
e
pr
e
d
i
c
t
e
d
c
l
a
s
s
(
ℎ
(
,
)
)
:
a
c
l
a
s
s
if
i
c
a
t
i
o
n
f
u
n
c
t
i
o
n
a
pp
l
i
e
d
to
t
h
e
i
n
put
v
e
c
t
o
r
(
x
)
,
wi
t
h
pa
r
a
m
e
t
e
r
s
(
)
whi
c
h
i
s
u
ni
que
to
t
h
e
ke
t
r
e
e
-
(
k)
.
(
K
)
:
n
u
m
b
e
r
o
f
t
r
e
e
s
i
n
t
h
e
f
o
r
e
s
t
2.
7.
XG
B
oos
t
c
l
as
s
i
f
icat
ion
T
h
e
XG
B
o
o
s
t
c
l
a
s
s
i
f
i
c
a
t
i
o
n
i
s
a
l
s
o
a
de
r
i
v
a
t
i
v
e
o
f
t
h
e
DT
.
T
hi
s
M
L
m
o
de
l
i
s
m
o
r
e
f
o
c
us
e
d
o
n
t
h
e
c
a
s
e
o
f
gr
a
d
i
e
n
t
b
oo
s
t
i
n
g
a
l
go
r
i
t
hm
s
w
i
t
h
a
DT
m
o
de
l
a
s
t
h
e
b
a
s
i
s
f
o
r
t
h
e
c
l
a
s
s
if
i
e
r
.
T
hi
s
m
o
de
l
c
a
n
b
e
e
x
p
l
a
i
ne
d
w
i
t
h
a
(
6)
.
W
h
e
r
e
r
e
pr
e
s
e
n
t
s
da
t
a
c
o
n
t
a
i
ni
ng
n
o
b
s
e
r
v
a
t
i
o
n
s
.
x
i
s
t
h
e
i
nde
pe
n
de
n
t
v
a
r
i
a
bl
e
,
a
n
d
y
i
s
t
h
e
de
pe
n
de
n
t
v
a
r
i
a
bl
e
[
38]
.
=
[
,
]
(
6)
2.
8.
Cat
B
oos
t
c
l
as
s
if
icat
ion
C
a
t
b
oo
s
t
i
s
a
r
o
b
us
t
M
L
a
l
go
r
i
t
hm
f
o
r
c
l
a
s
s
i
f
ica
t
i
o
n
.
I
t
i
s
a
t
y
pe
o
f
b
o
o
s
t
i
n
g
a
l
go
r
i
t
hm
t
h
a
t
o
p
t
i
mi
z
e
s
gr
a
d
i
e
n
t
-
b
o
o
s
t
i
n
g
ML
.
C
a
t
b
oo
s
t
i
s
a
s
y
mm
e
t
r
i
c
DT
t
e
c
hni
qu
e
t
h
a
t
c
a
n
s
o
l
v
e
t
h
e
pr
obl
e
m
s
o
f
pr
e
d
i
c
t
i
o
n
dr
i
f
t
a
n
d
gr
a
d
i
e
n
t
b
i
a
s
a
n
d
r
e
duc
e
o
v
e
r
f
i
t
t
i
n
g
w
i
t
h
s
t
a
bl
e
a
n
d
hi
g
h
a
c
c
ur
a
c
y
a
n
d
r
e
s
ul
t
s
[
39]
.
In
us
e
d
(
7)
:
̂
=
∑
=
1
(
)
(
7)
whi
c
h
:
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t
J
I
n
f
&
C
o
m
m
u
n
T
e
c
hn
o
l
I
S
S
N:
2252
-
8776
M
ac
hine
lear
ning
in
de
tec
ti
ng
and
int
e
r
pr
e
ti
ng
bu
s
ines
s
incubator
s
u
c
c
e
s
…
(
M
oc
ham
mad
Haldi
W
idi
anto
)
451
(
̂
)
:
t
h
e
pr
e
d
i
c
t
e
d
c
l
a
s
s
(f
K
(
)
)
:
t
h
e
s
c
o
r
e
i
s
g
i
ve
n
by
t
h
e
(
t
)
t
h
DT
f
o
r
t
h
e
(
k)
t
h
c
l
a
s
s
.
(
T
)
:
i
s
t
h
e
tot
a
l
n
u
m
be
r
o
f
t
r
e
e
s
i
n
t
h
e
m
o
de
l
.
2.
9.
K
-
n
e
ar
e
s
t
n
e
igh
b
or
s
I
n
t
h
e
K
NN
a
l
go
r
i
t
hm
l
e
a
r
ni
ng.
T
h
e
m
o
de
l
us
i
ng
M
a
nh
a
t
t
a
n
a
s
t
h
e
di
s
t
a
n
c
e
a
l
g
o
r
i
t
hm
i
s
s
h
o
wn
in
(
8)
[
40
]
.
I
n
(
8)
a
r
e
us
e
d
to
f
i
n
d
t
h
e
c
l
o
s
e
s
t
pa
s
t
c
a
s
e
s
.
T
hi
s
e
qua
t
i
o
n
i
s
b
e
n
e
f
i
c
i
a
l
i
n
d
e
t
e
r
m
i
n
i
ng
p
r
e
d
i
c
t
i
v
e
v
a
l
ue
s
.
T
h
e
v
a
r
i
a
b
l
e
s
X
a
n
d
y
f
r
o
m
(
1)
r
e
pr
e
s
e
n
t
only
t
wo
v
e
c
to
r
s
i
n
t
h
e
f
e
a
t
ur
e
s
pa
c
e
,
a
n
d
xi
a
n
d
y
i
a
r
e
t
h
e
i
r
c
oo
r
di
n
a
t
e
s
e
a
c
h
[
40]
.
M
a
nh
a
t
t
a
n
di
s
t
a
n
c
e
:
(
,
)
=
∑
|
−
|
=
1
(
8)
W
hi
c
h
:
i
=
1
to
n
p
=
p
o
s
i
t
i
ve
i
n
t
e
ge
r
2.
10.
Ada
B
oos
t
A
da
B
o
o
s
t
,
i
s
a
n
M
L
a
l
go
r
i
t
hm
u
s
e
d
a
s
a
n
e
n
s
e
m
b
l
e
o
r
c
o
m
bi
na
t
i
o
n
t
e
c
hni
que
a
n
d
i
s
a
l
s
o
t
h
e
b
a
s
is
f
o
r
de
r
i
vi
ng
DT
.
I
t
w
o
r
ks
by
c
o
m
bi
n
i
ng
s
e
v
e
r
a
l
we
a
k
l
e
a
r
ne
r
s
to
c
r
e
a
t
e
a
s
t
r
o
n
g
l
e
a
r
n
e
r
.
E
a
c
h
we
a
k
l
e
a
r
n
e
r
us
ua
l
ly
c
o
ns
i
s
t
s
o
f
a
s
i
m
p
l
e
DT
.
T
h
e
f
o
l
l
o
w
i
ng
i
s
th
e
f
o
r
m
u
l
a
f
o
r
A
da
B
o
o
s
t
[
41]
,
[
42
]
(
9
)
:
+
1
=
e
xp
(
ℎ
(
)
)
(
9)
w
h
e
r
e
:
(
)
:
t
h
e
we
i
g
h
t
o
f
t
h
e
(
i
)
-
t
h
o
b
s
e
r
v
a
t
i
o
n
.
(
)
:
t
h
e
we
i
g
h
t
o
f
t
h
e
(
i
)
-
t
h
c
l
a
s
s
i
f
i
e
r
,
c
a
l
c
u
l
a
t
e
d
b
a
s
e
d
o
n
i
t
s
e
r
r
o
r
r
a
t
e
.
(
)
:
t
h
e
a
c
t
ua
l
l
a
b
e
l
o
f
t
h
e
(
i
)
-
t
h
o
b
s
e
r
v
a
t
i
o
n
.
(
ℎ
(
)
)
:
t
h
e
pr
e
d
i
c
t
i
o
n
o
f
t
h
e
(
i
)
-
t
h
c
l
a
s
s
if
i
e
r
f
o
r
t
h
e
(
i
)
-
t
h
o
b
s
e
r
v
a
t
i
o
n
.
2.
11.
S
e
l
e
c
t
K
-
b
e
s
t
T
hi
s
m
e
t
h
o
d
i
s
u
s
e
d
t
o
r
e
m
o
ve
l
e
s
s
c
o
n
t
r
i
b
ut
i
n
g
pa
r
t
s
f
r
o
m
t
h
e
a
t
t
r
i
b
ut
e
s
o
r
f
e
a
t
ur
e
s
i
n
t
h
e
da
t
a
s
e
t
s
o
t
h
a
t
i
t
c
a
n
r
e
duc
e
t
r
a
i
ni
ng
t
i
m
e
by
c
a
l
c
u
l
a
t
i
n
g
v
a
r
i
a
bl
e
s
b
a
s
e
d
o
n
t
h
e
hi
g
h
e
s
t
c
o
r
r
e
l
a
t
i
o
n
b
e
t
we
e
n
th
e
s
c
o
r
e
f
u
n
c
t
i
o
n
pr
o
vi
de
d
a
n
d
t
h
e
a
tt
r
i
b
ut
e
or
f
e
a
t
ur
e
i
t
s
e
l
f
(
10)
[
43]
.
2
(
)
=
∑
(
−
)
2
(
10)
W
hi
c
h
:
(
)
:
Ob
s
e
r
v
a
t
i
o
n
f
r
e
que
n
c
y
o
f
c
l
a
s
s
(
j
)
w
i
t
h
f
e
a
t
ur
e
(
i
)
.
(
)
:
i
s
t
h
e
e
x
pe
c
t
e
d
f
r
e
que
n
c
y
o
f
c
l
a
s
s
(
j
)
w
i
t
h
f
e
a
t
ur
e
(
i
)
i
f
t
h
e
r
e
i
s
n
o
r
e
l
a
t
i
o
n
s
hi
p
b
e
t
we
e
n
t
h
e
f
e
a
t
ur
es
.
3.
RE
S
UL
T
S
AN
D
DI
S
CU
S
S
I
ON
T
hi
s
s
e
c
t
i
o
n
w
il
l
d
i
s
c
u
s
s
t
h
e
r
e
s
u
l
t
s
o
f
t
wo
e
x
pe
r
i
m
e
n
t
a
l
pr
o
po
s
e
d
m
o
de
l
s
.
T
h
e
pr
o
p
o
s
e
d
m
o
de
l
wa
s
e
v
a
l
ua
t
e
d
by
l
o
o
k
i
n
g
a
t
t
h
e
da
t
a
s
e
t
r
e
s
u
l
t
s
b
a
s
e
d
o
n
p
e
a
r
s
o
n
c
o
r
r
e
l
a
t
i
o
n
.
T
h
e
n
,
t
h
e
M
L
r
e
s
ul
t
s
will
s
h
o
w
whi
c
h
i
s
t
h
e
b
e
s
t
a
n
d
wh
i
c
h
w
i
ll
b
e
us
e
d.
F
i
na
l
ly
,
t
h
e
r
e
s
u
l
t
s
o
f
t
h
e
b
e
s
t
M
L
w
i
ll
b
e
i
n
t
e
r
pr
e
t
e
d
us
i
n
g
s
e
l
e
c
t
K
-
b
e
s
t
to
s
e
e
t
h
e
i
n
t
e
r
pr
e
t
a
t
i
o
n
o
f
t
h
e
M
L
.
3.
1.
Cor
r
e
l
at
ion
r
e
s
u
l
t
T
h
e
a
ut
h
o
r
s
f
o
un
d
t
h
a
t
t
h
e
c
o
r
r
e
l
a
t
i
o
n
o
f
a
l
l
d
a
t
a
us
i
n
g
(
1)
a
s
s
h
o
wn
i
n
F
i
gur
e
1,
wh
e
r
e
n
o
c
o
r
r
e
l
a
t
i
o
n
e
x
c
e
e
ds
0.
5.
I
t
c
a
n
b
e
s
a
i
d
t
h
a
t
a
l
l
d
a
t
a
i
s
n
o
t
c
o
r
r
e
l
a
t
e
d
wi
t
h
e
a
c
h
ot
h
e
r
.
Ho
we
v
e
r
,
t
h
e
b
e
s
t
c
o
r
r
e
l
a
t
i
o
n
i
s
f
o
un
d
i
n
3
f
e
a
t
ur
e
s
,
n
a
m
e
ly
“
f
i
r
s
t
i
n
c
o
m
e
,
”
“
l
a
s
t
i
n
c
o
m
e
,
”
a
n
d
“
n
u
m
be
r
o
f
e
m
p
l
o
y
e
e
s
.
”
T
his
t
hi
r
d
a
tt
r
i
b
ut
e
i
s
c
o
m
pa
r
e
d
w
i
t
h
t
h
e
t
a
r
ge
t
a
tt
r
i
but
e
,
whi
c
h
c
o
r
r
e
l
a
t
e
s
a
r
o
un
d
“
0.
23
”
,
“
0.
28
”
,
a
n
d
“
0.
34
”
.
W
h
e
r
e
t
h
e
a
t
tr
i
b
ut
e
“
n
u
m
be
r
o
f
e
m
p
l
o
y
e
e
s
”
ha
s
t
h
e
hi
g
h
e
s
t
c
o
r
r
e
l
a
t
i
o
n
v
a
l
ue
.
W
e
a
k
c
o
r
r
e
l
a
t
i
o
n
a
f
f
e
c
t
s
t
h
e
c
o
n
t
r
i
b
ut
i
o
n
o
f
f
e
a
t
ur
e
s
to
t
h
e
a
l
go
r
i
t
hm
,
i
t
i
s
wr
o
ng
b
ut
t
h
e
a
ut
h
o
r
s
t
i
ll
us
e
s
a
ll
f
e
a
t
ur
e
s
b
e
c
a
u
s
e
i
t
s
t
i
ll
a
ll
o
ws
f
o
r
a
c
o
n
tr
i
b
ut
i
o
n
b
e
t
we
e
n
a
l
l
f
e
a
t
ur
e
s
to
t
h
e
pe
r
f
o
r
m
a
n
c
e
o
f
t
h
e
M
L
a
l
go
r
i
t
hm
i
n
t
h
e
pr
o
p
o
s
e
d
m
o
de
l
.
T
h
e
r
e
f
o
r
e
,
t
h
e
a
ut
h
or
s
ugge
s
t
s
t
h
a
t
i
n
t
e
r
pr
e
t
a
t
i
o
n
i
s
n
e
c
e
s
s
a
r
y
t
o
s
e
e
t
h
e
i
nf
l
u
e
n
c
e
o
f
c
l
a
s
s
i
f
i
c
a
t
i
o
n
o
n
t
h
e
i
n
t
e
r
pr
e
t
a
t
i
o
n
o
f
t
h
e
da
t
a
.
T
h
e
a
ut
h
o
r
’
s
s
ugge
s
t
i
o
ns
w
i
ll
a
l
s
o
b
e
pr
e
s
e
n
t
e
d
i
n
a
n
ot
h
e
r
s
e
c
t
i
o
n
s
o
t
h
a
t
y
o
u
c
a
n
s
e
e
t
h
e
r
e
s
u
l
t
s
o
f
M
L
a
n
d
i
n
t
e
r
pr
e
t
t
h
e
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8776
I
n
t
J
I
n
f
&
C
o
m
m
u
n
T
e
c
hn
o
l
,
Vo
l
.
14
,
N
o.
2
,
A
ugus
t
20
25
:
446
-
456
452
3.
2.
M
ac
h
in
e
l
e
ar
n
in
g
r
e
s
u
l
t
T
hi
s
s
e
c
t
i
o
n
w
i
ll
e
x
p
l
a
i
n
t
h
e
pr
o
po
s
e
d
ML
m
o
de
l
’
s
r
e
s
u
l
t
s
i
n
a
ll
a
s
p
e
c
t
s
,
s
uc
h
a
s
F
1
-
s
c
o
r
e
,
a
c
c
ur
a
c
y
,
pr
e
c
i
s
i
o
n
,
a
n
d
r
e
c
a
l
l
.
T
h
e
s
e
r
e
s
u
l
t
s
a
r
e
pr
e
s
e
n
t
e
d
i
n
T
a
bl
e
2.
T
h
e
s
e
r
e
s
u
l
t
s
a
r
e
us
e
f
u
l
i
n
s
e
e
i
ng
t
h
e
q
ua
l
i
t
y
o
f
t
h
e
M
L
a
l
go
r
i
t
hm
g
i
ve
n
by
t
h
e
pr
o
p
o
s
e
d
m
o
de
l
.
T
a
bl
e
2.
ML
r
e
s
u
l
t
No
M
L
a
lg
o
r
it
h
m
A
c
ur
a
c
c
y
P
r
e
c
is
i
o
n
R
e
c
a
ll
F1
-
s
c
o
r
e
T
im
e
c
o
mput
a
ti
on
1
K
N
N
88%
77%
88%
82%
0.1s
2
DT
93%
93%
93%
92%
0.1s
3
LR
88%
77%
88%
82%
0.023
4
S
V
M
88%
77%
88%
82%
0.021s
5
RF
93%
93%
93%
92%
0.44s
6
X
G
B
oo
s
t
94%
94%
94%
93%
0.61s
7
C
a
tB
oo
s
t
94%
94%
94%
93%
1.49s
8
A
da
B
oo
s
t
94%
94%
94%
93%
0.081s
T
a
bl
e
2
e
x
p
l
a
i
ns
t
h
e
r
e
s
u
l
t
s
o
f
t
h
e
pr
o
p
o
s
e
d
m
o
de
l
pr
o
vi
de
d
by
XG
B
o
o
s
t
,
C
a
t
B
oo
s
t
,
a
n
d
A
da
B
o
o
s
t.
T
h
e
r
e
s
u
l
t
s
we
r
e
94%
a
c
c
ur
a
c
y
,
94%
pr
e
c
i
s
i
o
n
,
9
4%
r
e
c
a
l
l
,
a
n
d
93%
F
1
-
s
c
o
r
e
.
H
o
we
v
e
r
,
i
f
t
h
e
a
uth
o
r
l
o
o
ks
a
t
t
h
e
c
o
m
put
i
n
g
t
i
m
e
b
e
t
we
e
n
t
h
e
t
h
r
e
e
a
l
go
r
i
t
hm
s
.
T
h
e
a
ut
h
o
r
pr
e
f
e
r
s
A
da
B
o
o
s
t
wi
t
h
a
c
o
m
put
i
ng
t
i
m
e
o
f
o
nl
y
0.
081s
.
M
e
a
n
w
hil
e
,
C
a
t
b
o
o
s
t
a
n
d
XG
b
o
o
s
t
h
a
v
e
c
o
m
put
i
n
g
t
i
m
e
s
o
f
1.
49s
a
n
d
0.
61s
.
T
hi
s
c
o
m
put
i
n
g
t
i
m
e
wa
s
c
h
o
s
e
n
b
e
c
a
us
e
i
t
i
s
i
m
po
r
t
a
n
t
to
s
e
e
t
h
e
s
upe
r
i
o
r
i
t
y
o
f
t
h
e
M
L
a
l
go
r
i
t
hm
i
n
t
he
pr
o
p
o
s
e
d
m
o
de
l
.
C
o
m
put
a
t
i
o
n
t
i
m
e
a
l
s
o
a
f
f
e
c
t
s
h
o
w
f
a
s
t
pr
o
c
e
s
s
i
n
g
i
m
pr
o
v
e
s
a
c
c
ur
a
c
y
.
T
h
e
r
e
f
o
r
e
,
t
h
e
a
l
go
r
i
t
hm
c
h
o
s
e
n
i
s
t
h
e
b
e
s
t
,
n
a
m
e
ly
A
d
a
B
o
o
s
t
.
T
h
e
A
da
B
o
o
s
t
a
l
go
r
i
t
hm
pr
o
duc
e
s
t
h
e
b
e
s
t
r
e
s
u
l
t
s
c
o
m
pa
r
e
d
t
o
t
h
e
ot
h
e
r
s
.
T
hi
s
h
a
ppe
ns
b
e
c
a
u
s
e
t
h
e
t
h
r
e
e
o
f
t
h
e
m
a
r
e
o
n
e
o
f
t
h
e
e
ns
e
m
b
l
e
t
e
c
hni
que
s
t
h
a
t
a
r
e
g
oo
d
f
o
r
c
l
a
s
s
i
f
i
c
a
t
i
o
n
.
A
s
f
o
r
t
h
o
s
e
wh
o
s
a
y
t
ha
t
t
h
e
a
s
s
e
m
b
l
a
ge
t
e
c
hni
que
c
a
n
m
a
xim
i
z
e
t
h
e
a
l
go
r
i
t
hm
i
n
m
a
ny
w
a
y
s
,
e
s
pe
c
i
a
ll
y
i
n
i
t
s
a
ppr
o
a
c
h
to
d
e
t
e
c
t
i
o
n
[
44]
,
[
45]
.
A
n
d
s
o
m
e
r
e
a
s
o
n
s
w
hy
t
h
e
s
e
t
h
r
e
e
t
e
c
h
ni
que
s
a
r
e
b
e
t
t
e
r
i
n
t
e
r
m
s
o
f
:
B
i
a
s
a
n
d
v
a
r
i
a
n
c
e
r
e
duc
t
i
o
n
F
o
c
us
o
n
m
i
s
t
a
ke
s
R
e
gu
l
a
r
i
z
a
t
i
o
n
C
a
t
e
gor
i
c
a
l
f
e
a
t
ur
e
pr
o
c
e
s
s
i
n
g
C
o
m
put
a
t
i
o
n
a
l
e
f
f
i
c
i
e
nc
y
L
a
r
ge
s
c
a
l
e
da
t
a
h
a
n
d
li
ng
F
l
e
xi
b
l
e
pa
r
a
m
e
t
e
r
t
uni
n
g
I
n
t
h
e
r
e
a
l
wo
r
l
d,
t
h
e
a
dv
a
n
t
a
ge
s
o
f
c
o
m
put
i
ng
t
i
m
e
a
n
d
a
s
u
i
t
a
bl
e
c
o
nf
u
s
i
o
n
m
a
t
r
i
x
a
f
f
e
c
t
pr
o
c
e
s
s
i
n
g
t
i
m
e
i
n
t
h
e
b
us
i
ne
s
s
wo
r
l
d
b
e
c
a
us
e
t
i
m
e
a
n
d
a
c
c
ur
a
c
y
a
r
e
t
h
e
o
n
e
s
t
h
a
t
i
nf
l
ue
n
c
e
c
o
m
pa
n
y
o
pe
r
a
t
i
o
n
s
.
S
e
v
e
r
a
l
a
d
v
a
n
t
a
ge
s
m
a
k
e
t
h
i
s
t
e
c
h
ni
qu
e
b
e
tt
e
r
.
T
h
e
t
h
r
e
e
M
L
t
e
c
h
ni
que
s
w
i
ll
b
e
t
r
i
e
d
to
i
n
t
e
r
pr
e
t
t
h
e
r
e
s
u
l
t
s
i
n
t
h
e
n
e
x
t
c
h
a
pt
e
r
.
3.
3.
I
n
t
e
r
p
r
e
t
at
ion
r
e
s
u
l
t
T
hi
s
s
e
c
t
i
o
n
w
i
ll
e
x
p
l
a
i
n
t
h
e
be
s
t
r
e
s
u
l
t
s
pr
o
p
o
s
e
d
by
t
h
e
m
o
de
l
f
r
o
m
ML
a
n
d
A
da
B
o
o
s
t
.
T
h
i
s
i
s
us
e
d
to
i
n
t
e
r
pr
e
t
M
L
r
e
s
ul
t
s
,
or
wh
a
t
i
t
i
s
us
ua
ll
y
c
a
l
l
e
d,
to
s
e
e
h
o
w
ML
wo
r
ks
,
u
t
i
li
z
i
ng
(
10)
,
n
a
m
e
ly
t
h
e
s
e
l
e
c
t
K
-
b
e
s
t
f
o
r
m
u
l
a
.
T
h
e
s
e
r
e
s
u
l
t
s
a
r
e
pr
e
s
e
n
t
e
d
i
n
T
a
bl
e
3.
T
a
bl
e
3.
S
e
l
e
c
t
K
-
b
e
s
t
r
e
s
u
l
t
N
o
.
A
tt
r
ib
ut
e
K
-
v
a
lu
e
1
L
a
s
t
r
e
ve
nue
0.58
2
F
ir
s
t
r
e
ve
nu
e
0.196
3
N
umbe
r
e
mpl
oy
e
e
s
0.077
4
I
nt
e
r
na
l
c
o
ll
a
b
o
r
a
ti
o
n
0.0242
5
N
umbe
r
of
o
n
li
ne
a
d
ve
r
ti
s
e
m
e
nt
s
0.024
6
T
ot
a
l
f
o
ll
o
w
s
t
he
b
a
z
a
a
r
0.026
7
E
xt
e
r
na
l
c
o
ll
a
b
or
a
ti
o
n
0.022
8
B
us
in
e
s
s
te
a
m m
e
mb
e
r
0.016
9
A
ddi
ti
o
na
l
in
ve
s
tm
e
nt
f
r
o
m
e
x
t
e
r
na
l
0.01
10
o
w
n t
r
a
d
e
ma
r
k r
ig
h
ts
0.009
11
c
ove
r
e
d b
y
t
he
me
di
a
0.008
12
H
a
v
e
ha
la
l
c
e
r
i
f
ie
d
0.005
13
U
s
in
g T
ik
T
ok
l
i
ve
0.004
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t
J
I
n
f
&
C
o
m
m
u
n
T
e
c
hn
o
l
I
S
S
N:
2252
-
8776
M
ac
hine
lear
ning
in
de
tec
ti
ng
and
int
e
r
pr
e
ti
ng
bu
s
ines
s
incubator
s
u
c
c
e
s
…
(
M
oc
ham
mad
Haldi
W
idi
anto
)
453
T
h
e
r
e
s
u
l
t
s
o
f
t
h
e
pr
o
p
o
s
e
d
m
o
de
l
i
n
t
e
r
pr
e
t
a
t
i
o
n
o
f
t
h
e
A
da
B
o
o
s
t
a
l
go
r
i
t
hm
s
h
o
w
t
h
a
t
t
h
e
m
o
s
t
do
m
i
na
n
t
f
e
a
t
ur
e
s
de
t
e
r
m
i
ni
ng
a
n
i
n
c
u
b
a
t
o
r
b
us
i
ne
s
s
’
s
s
uc
c
e
s
s
qua
li
f
i
c
a
t
i
o
ns
a
r
e
l
a
s
t
r
e
v
e
n
ue
a
n
d
f
i
r
s
t
r
e
v
e
n
ue
,
w
i
t
h
v
a
l
ue
s
o
f
0.
58
a
n
d
0.
196.
H
o
we
v
e
r
,
t
hi
s
c
o
n
t
r
a
s
t
s
wi
t
h
t
h
e
r
e
s
u
l
t
s
i
n
F
i
gur
e
2
whi
c
h
s
t
a
t
e
s
t
h
a
t
t
h
e
n
u
m
be
r
o
f
e
m
p
l
o
y
e
e
s
r
e
a
ll
y
i
nf
l
ue
nc
e
s
t
h
e
t
a
r
ge
t
.
T
h
e
K
-
v
a
l
ue
i
s
i
n
t
e
r
pr
e
t
e
d
b
a
s
e
d
o
n
t
h
e
t
a
r
ge
t
f
e
a
t
ur
e
s
i
n
t
h
e
M
L
a
l
go
r
i
t
hm
a
n
d
l
o
o
ks
a
t
t
h
e
i
nf
l
ue
n
c
e
o
n
th
e
b
us
i
ne
s
s
’
s
s
uc
c
e
s
s
.
T
h
e
r
e
s
u
l
t
s
o
f
t
hi
s
i
n
t
e
r
pr
e
t
a
t
i
o
n
o
nly
l
o
o
k
a
t
whi
c
h
f
e
a
t
ur
e
s
a
r
e
m
o
r
e
d
o
m
i
na
n
t
i
n
t
h
e
c
l
a
s
s
i
f
i
c
a
t
i
o
n
.
I
n
t
h
e
c
o
n
t
e
x
t
o
f
b
us
i
ne
s
s
s
uc
c
e
s
s
,
i
t
c
a
n
b
e
s
e
e
n
t
h
a
t
wh
e
n
t
h
e
f
i
r
s
t
r
e
v
e
n
ue
a
n
d
l
a
s
t
r
e
v
e
n
ue
i
n
c
r
e
a
s
e
,
t
h
i
s
m
e
a
ns
t
h
a
t
i
t
i
n
d
i
c
a
t
e
s
t
h
e
s
uc
c
e
s
s
o
f
t
h
e
b
us
i
ne
s
s
,
b
ut
n
ot
o
n
l
y
t
h
a
t
,
a
n
ot
h
e
r
a
s
pe
c
t
,
n
a
m
e
ly
t
h
e
nu
m
b
e
r
o
f
e
m
p
l
o
y
e
e
s
,
a
l
s
o
i
nf
l
ue
nc
e
s
t
h
e
s
uc
c
e
s
s
o
f
t
h
e
b
us
i
n
e
s
s
.
F
i
gur
e
2
.
P
e
r
f
o
r
m
a
n
c
e
o
f
h
e
a
t
m
a
p
c
o
r
r
e
l
a
t
i
o
n
i
n
c
u
b
a
t
o
r
da
t
a
s
e
t
s
4.
CONC
L
USI
ON
T
h
e
r
e
s
u
l
t
s
o
f
t
hi
s
r
e
s
e
a
r
c
h
a
r
e
i
n
s
e
a
r
c
h
o
f
i
nc
u
b
a
t
o
r
b
us
i
n
e
s
s
s
u
c
c
e
s
s
;
i
n
t
hi
s
c
a
s
e
,
t
h
e
r
e
s
e
a
r
c
h
pr
e
s
e
n
t
s
a
pr
o
po
s
e
d
m
o
de
l
a
r
c
hi
t
e
c
t
ur
e
f
o
r
c
l
a
s
s
if
yi
ng
b
us
i
ne
s
s
s
u
c
c
e
s
s
;
i
n
t
hi
s
c
a
s
e
,
t
h
e
pr
o
p
o
s
e
d
m
o
de
l
a
r
c
hi
t
e
c
t
ur
e
c
o
m
e
s
f
r
o
m
pr
e
pr
o
c
e
s
s
i
n
g,
M
L
m
o
de
l
s
,
a
n
d
m
o
de
l
i
n
t
e
r
pr
e
t
a
t
i
o
n
.
T
h
e
f
i
r
s
t
r
e
s
u
l
t
i
s
t
h
a
t
t
h
e
b
e
s
t
c
o
r
r
e
l
a
t
i
o
n
ba
s
e
d
o
n
t
h
e
h
e
a
t
m
a
p
i
s
t
he
“
n
u
m
be
r
o
f
e
m
p
l
o
y
e
e
s
,
”
w
i
t
h
a
c
o
r
r
e
l
a
t
i
o
n
v
a
l
ue
o
f
0.
34.
T
h
e
n
,
s
e
v
e
r
a
l
M
L
a
l
go
r
i
t
hm
s
s
uc
h
a
s
A
d
a
B
o
o
s
t
,
C
a
t
B
oos
t
,
a
n
d
XG
B
oo
s
t
wi
t
h
a
c
c
ur
a
c
y
,
pr
e
c
i
s
i
o
n
,
r
e
c
a
l
l
va
l
ue
s
o
f
94%
,
a
n
d
F
1
-
s
c
o
r
e
o
f
93%
.
B
u
t
i
f
t
h
e
a
ut
h
or
l
o
oks
a
t
t
h
e
c
o
m
put
i
n
g
t
i
m
e
,
t
h
e
b
e
s
t
M
L
i
s
0.
081s
,
n
a
m
e
ly
A
da
B
o
o
s
t
.
T
h
e
n
,
f
i
na
ll
y
,
t
h
e
i
n
t
e
r
pr
e
t
a
t
i
o
n
r
e
s
u
l
t
s
f
r
o
m
A
da
B
o
o
s
t
us
i
n
g
s
e
l
e
c
t
K
-
b
e
s
t
a
r
e
t
h
e
b
e
s
t
f
e
a
t
ur
e
s
“
l
a
s
t
r
e
v
e
n
ue
”
a
n
d
“
f
i
r
s
t
r
e
v
e
n
ue
,
”
w
i
t
h
f
e
a
t
ur
e
K
-
v
a
l
ue
s
o
f
0.
58
a
n
d
0.
196;
t
h
e
s
e
f
e
a
t
ur
e
s
i
nf
l
u
e
n
c
e
t
h
e
s
uc
c
e
s
s
o
f
t
h
e
b
us
i
ne
s
s
.
T
h
e
r
e
f
o
r
e
,
i
n
t
hi
s
da
t
a
,
th
e
l
e
v
e
l
o
f
s
uc
c
e
s
s
c
a
n
b
e
a
s
s
e
s
s
e
d
f
r
o
m
t
h
e
c
o
r
r
e
l
a
t
i
o
n
r
e
s
u
l
t
s
,
c
l
a
s
s
i
f
i
c
a
t
i
o
n
,
a
n
d
i
n
t
e
r
pr
e
t
a
t
i
o
n
r
e
s
u
l
t
s
.
F
ut
ur
e
r
e
s
e
a
r
c
h
,
s
uc
h
a
s
us
i
ng
i
m
pr
o
v
e
m
e
n
t
s
i
n
hyb
r
i
d
M
L
a
l
go
r
i
t
hm
s
a
n
d
ot
h
e
r
m
o
de
l
i
n
t
e
r
pr
e
t
a
t
i
o
n
s
,
i
s
i
m
po
r
t
a
n
t.
T
h
e
s
e
im
pr
o
v
e
m
e
n
t
s
c
o
u
l
d
b
e
i
n
t
he
f
o
r
m
o
f
M
L
a
l
go
r
i
t
hm
s
t
h
a
t
a
r
e
m
o
r
e
i
m
m
u
n
e
t
o
da
t
a
un
c
e
r
t
a
i
nt
y
,
a
n
d
i
n
t
e
r
pr
e
t
a
t
i
o
n
o
f
r
e
s
u
l
t
s
w
i
t
h
w
i
de
r
da
t
a
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8776
I
n
t
J
I
n
f
&
C
o
m
m
u
n
T
e
c
hn
o
l
,
Vo
l
.
14
,
N
o.
2
,
A
ugus
t
20
25
:
446
-
456
454
F
UN
DI
NG
I
N
F
ORM
AT
I
ON
B
i
n
a
Nu
s
a
n
t
a
r
a
Uni
ve
r
s
i
t
y
f
u
n
ds
r
e
s
e
a
r
c
h
,
e
s
pe
c
i
a
ll
y
t
h
e
R
T
T
O
(
R
e
s
e
a
r
c
h
a
n
d
T
e
c
h
n
o
l
o
g
y
T
r
a
ns
f
e
r
O
f
f
i
c
e
)
uni
t
,
whi
c
h
ha
s
f
u
n
de
d
t
hi
s
r
e
s
e
a
r
c
h
f
o
r
j
o
ur
n
a
l
r
e
g
i
s
t
r
a
t
i
o
n
.
AU
T
HO
R
CONT
RI
B
UT
I
ONS
S
T
AT
E
M
E
NT
P
u
j
i
P
r
a
b
o
wo
pr
o
vi
de
s
da
t
a
s
e
t
s
a
n
d
da
t
a
m
a
n
a
g
e
m
e
n
t
t
h
a
t
c
a
n
b
e
ut
i
l
i
z
e
d.
M
o
c
h
a
m
m
a
d
Ha
l
d
i
W
i
d
i
a
n
t
o
c
o
m
p
l
e
t
e
d
t
h
e
s
c
i
e
n
t
i
f
i
c
pa
pe
r
by
c
o
n
s
i
d
e
r
i
n
g
r
e
vi
s
i
o
n
s
f
r
o
m
r
e
vi
e
we
r
s
u
n
t
i
l
c
o
m
p
l
e
t
i
o
n
.
T
h
e
r
e
f
o
r
e
,
a
l
l
a
ut
h
o
r
s
c
o
n
t
r
i
b
ut
e
d
to
t
hi
s
s
c
i
e
n
t
i
f
i
c
a
r
t
i
c
l
e
.
Nam
e
of
Aut
h
or
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
M
o
c
h
a
mm
a
d
Ha
l
d
i
W
i
d
i
a
n
t
o
P
u
j
i
P
r
a
b
o
wo
C
:
C
o
n
c
e
pt
ua
li
z
a
ti
o
n
M
:
M
e
th
o
d
o
l
o
g
y
So
:
So
f
twa
r
e
Va
:
Va
li
da
ti
o
n
Fo
:
Fo
r
ma
l
a
na
l
y
s
is
I
:
I
nve
s
ti
ga
ti
o
n
R
:
R
e
s
o
u
r
c
e
s
D
:
D
a
ta
C
ur
a
ti
o
n
O
:
W
r
it
in
g
-
O
r
ig
in
a
l
D
r
a
f
t
E
:
W
r
it
in
g
-
R
e
v
i
e
w
&
E
di
ti
ng
Vi
:
Vi
s
ua
li
z
a
ti
o
n
Su
:
Su
pe
r
v
is
io
n
P
:
P
r
o
j
e
c
t
a
dmi
n
is
tr
a
ti
o
n
Fu
:
Fu
ndi
ng a
c
qui
s
it
i
o
n
CONF
L
I
CT
OF
I
NT
E
RE
S
T
S
T
AT
E
M
E
NT
A
ut
h
o
r
s
s
t
a
t
e
n
o
c
o
nf
li
c
t
o
f
i
n
t
e
r
e
s
t
.
I
NF
ORM
E
D
CONSE
NT
W
e
h
a
v
e
o
b
t
a
i
n
e
d
i
nf
o
r
m
e
d
c
o
n
s
e
n
t
f
r
o
m
a
l
l
i
nd
i
vidua
l
s
i
n
c
l
ude
d
i
n
t
hi
s
s
t
ud
y
.
DA
T
A
AV
AI
L
AB
I
L
I
T
Y
T
h
e
da
t
a
t
h
a
t
s
uppo
r
t
t
h
e
f
i
nd
i
ngs
o
f
t
hi
s
s
t
ud
y
a
r
e
o
pe
nl
y
a
v
a
il
a
bl
e
i
n
t
h
e
m
e
n
de
l
e
y
r
e
po
s
i
t
o
r
y
a
t
:
h
t
t
ps
:/
/da
t
a
.
m
e
n
de
l
e
y
.
c
o
m
/dat
a
s
e
t
s
/dd9
j
v
5pw3
n
/1
.
RE
F
E
R
E
NC
E
S
[
1]
D
.
L
uk
e
ti
ć
,
“
E
nt
r
e
pr
e
n
e
ur
s
hi
p
e
duc
a
ti
o
n
in
c
ompul
s
or
y
e
du
c
a
ti
o
n
:
l
e
s
s
o
ns
w
e
l
e
a
r
n
f
r
o
m
r
e
c
e
nt
r
e
s
e
a
r
c
h
pr
a
c
ti
c
e
,
”
A
c
ta
I
ade
r
ti
na
, vo
l.
18, n
o
. 2, pp. 255
–
284, J
a
n. 2022, d
o
i:
10.1
5291/a
i.
3607.
[
2]
G
.
E
li
a
,
A
.
M
a
r
ghe
r
it
a
,
E
.
C
ia
vo
li
n
o
,
a
nd
K
.
M
o
us
ta
gh
f
ir
,
“
D
ig
it
a
l
s
oc
i
e
t
y
in
c
uba
t
o
r
:
c
o
mbi
ni
ng
e
x
p
o
n
e
nt
ia
l
te
c
hn
o
l
o
g
y
a
nd
huma
n
po
t
e
nt
ia
l
t
o
bui
ld
r
e
s
il
ie
nt
e
nt
r
e
pr
e
n
e
ur
ia
l
e
c
o
s
y
s
t
e
ms
,
”
A
dm
in
is
tr
at
iv
e
S
c
ie
nc
e
s
,
v
o
l.
11,
n
o
.
3,
p.
96,
S
e
p.
2021,
do
i:
10.3390/adms
c
i1
1030096.
[
3]
M
.
G
ue
r
r
e
r
o
a
nd
J
.
E
s
pi
noz
a
-
B
e
na
v
id
e
s
,
“
D
oe
s
e
nt
r
e
p
r
e
n
e
ur
s
hi
p
e
c
o
s
y
s
te
m
in
f
lu
e
n
c
e
bus
in
e
s
s
r
e
-
e
nt
r
i
e
s
a
f
t
e
r
f
a
il
ur
e
?
,
”
I
nt
e
r
nat
io
nal
E
nt
r
e
pr
e
ne
ur
s
hi
p
and
M
anage
m
e
nt
J
o
ur
nal
,
vo
l.
17,
n
o
.
1,
pp.
211
–
227,
M
a
r
.
2
021,
do
i:
10.1007/s
11365
-
020
-
00694
-
7.
[
4]
R
.
M
a
hmo
o
d,
A
.
S
.
M
.
Z
a
ha
r
i,
N
.
I
br
a
hi
m,
N
.
F
.
H
.
N
.
J
a
a
f
a
r
,
a
nd
N
.
M
.
Y
a
a
c
o
b,
“
T
h
e
im
pa
c
t
of
e
nt
r
e
pr
e
ne
u
r
e
du
c
a
ti
on
o
n
bus
in
e
s
s
pe
r
f
o
r
ma
n
c
e
,
”
A
s
ia
n J
our
nal
of
U
ni
v
e
r
s
it
y
E
duc
at
io
n
,
vo
l.
16, n
o
. 4, p. 171, J
a
n. 2021, doi:
10.24191/ajue
.
v
16
i4
.1194
7.
[
5]
Y
.
K
h
o
dk
ov
s
ka
y
a
a
nd
O
.
M
a
l
y
kh,
“
P
r
o
j
e
c
t
-
ba
s
e
d
l
e
a
r
ni
ng
a
s
a
n
e
le
m
e
nt
of
th
e
uni
ve
r
s
it
y
in
n
ov
a
ti
o
n
e
c
o
s
y
s
t
e
m,
”
SH
S W
e
b of
C
onf
e
r
e
nc
e
s
, v
o
l.
116, p. 00069
, J
ul
. 2021, d
o
i:
10.
1051/s
hs
c
o
n
f
/2
02111600069.
[
6]
M
.
G
ue
r
r
e
r
o
,
D
.
U
r
ba
no
,
a
nd
E
.
G
a
jó
n,
“
E
nt
r
e
pr
e
n
e
ur
i
a
l
uni
v
e
r
s
it
y
e
c
o
s
y
s
te
ms
a
nd
gr
a
dua
te
s
’
c
a
r
e
e
r
pa
tt
e
r
ns
:
do
e
nt
r
e
pr
e
n
e
ur
s
hi
p
e
du
c
a
ti
o
n
pr
o
g
r
a
mm
e
s
a
nd
uni
v
e
r
s
it
y
bus
i
ne
s
s
in
c
uba
t
o
r
s
ma
tt
e
r
?
,
”
J
our
nal
o
f
M
anage
m
e
nt
D
e
v
e
lo
pm
e
nt
,
vo
l.
39, n
o
. 5, pp. 753
–
775, Apr
. 2020, d
o
i
:
10.1108/J
M
D
-
10
-
2019
-
0439.
[
7]
J
.
M
.
L
o
pe
s
,
M
.
O
li
v
e
i
r
a
,
J
.
O
li
v
e
ir
a
,
M
.
S
o
us
a
,
T
.
S
a
nt
o
s
,
a
nd
S
.
G
o
m
e
s
,
“
D
e
te
r
mi
na
nt
s
of
th
e
e
nt
r
e
pr
e
n
e
ur
ia
l
I
n
f
lu
e
n
c
e
o
n
a
c
a
de
mi
c
e
nt
r
e
pr
e
n
e
ur
s
hi
p
—
l
e
s
s
o
ns
le
a
r
n
e
d
f
r
om
hi
ghe
r
e
du
c
a
ti
o
n
s
tu
de
nt
s
in
P
o
r
tu
ga
l,
”
E
duc
Sc
i
(
B
as
e
l)
,
vol
.
11,
no
.
12,
p. 771, Nov
. 2021, d
o
i:
10.3390/
e
du
c
s
c
i1
1120771.
[
8]
T
.
A
hm
e
d,
V
.
G
.
R
.
C
ha
ndr
a
n,
J
.
E
.
K
l
o
ba
s
,
F
.
L
iñ
á
n,
a
nd
P
.
K
o
kka
li
s
,
“
E
nt
r
e
pr
e
n
e
ur
s
hi
p
e
du
c
a
ti
o
n
pr
o
g
r
a
mm
e
s
:
h
o
w
l
e
a
r
n
in
g,
in
s
pi
r
a
ti
o
n
a
nd
r
e
s
o
ur
c
e
s
a
f
f
e
c
t
in
t
e
nt
i
o
ns
f
o
r
n
e
w
ve
nt
ur
e
c
r
e
a
ti
o
n
in
a
d
e
ve
l
o
pi
ng
e
c
o
n
o
m
y
,
”
T
he
I
nt
e
r
nat
io
nal
J
our
nal
o
f
M
anage
m
e
nt
E
duc
at
io
n
, vo
l.
18, n
o
. 1, p. 100327, M
a
r
. 2020, d
o
i:
10.1016/j
.
ij
m
e
.2019.100327.
[
9]
E
.
M
.
S
w
a
r
tz
,
C
.
B
.
S
c
he
e
p
e
r
s
,
a
nd
T
.
T
o
e
f
y
,
“
W
o
m
e
n
e
nt
r
e
pr
e
n
e
ur
s
’
o
pp
or
tu
ni
t
y
id
e
n
ti
f
i
c
a
ti
o
n
of
di
g
it
a
l
pl
a
tf
or
m
s
ta
r
t
-
ups
:
e
m
e
r
gi
ng
e
vi
de
n
c
e
f
r
o
m
S
o
ut
h
A
f
r
ic
a
,
”
I
nt
e
r
nat
io
nal
J
our
nal
of
G
e
nde
r
and
E
nt
r
e
p
r
e
ne
u
r
s
hi
p
,
v
o
l.
14,
no
.
3,
pp.
352
–
374,
A
ug. 2022, do
i:
10.1108/
I
J
G
E
-
0
6
-
2021
-
0096.
[
10]
G
.
G
a
br
i
e
la
,
S
.
E
.
C
e
r
a
s
e
la
,
S
.
C
.
O
c
ta
v
ia
n
,
S
.
M
a
r
c
e
la
,
a
nd
B
.
C
.
L
a
r
is
a
,
“
C
r
e
a
ti
ng
a
s
us
ta
in
a
bl
e
e
nt
r
e
p
r
e
ne
u
r
ia
l
e
c
o
s
y
s
t
e
m
a
t
hi
ghe
r
e
du
c
a
ti
o
n
in
s
ti
tu
ti
o
n
l
e
v
e
l,
”
E
c
onomic
C
om
put
at
io
n
and
E
c
onomic
C
y
be
r
ne
ti
c
s
St
udi
e
s
and
R
e
s
e
a
r
c
h
,
vo
l.
55, n
o
. 2/
2021, pp. 265
–
280, J
un. 2021, d
o
i:
10.24818/184
23264/55.2.21.16.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t
J
I
n
f
&
C
o
m
m
u
n
T
e
c
hn
o
l
I
S
S
N:
2252
-
8776
M
ac
hine
lear
ning
in
de
tec
ti
ng
and
int
e
r
pr
e
ti
ng
bu
s
ines
s
incubator
s
u
c
c
e
s
…
(
M
oc
ham
mad
Haldi
W
idi
anto
)
455
[
11]
M
.
L
o
ga
na
th
a
n
a
nd
M
.
H
.
B
.
S
ubr
a
hma
n
y
a
,
“
T
e
c
hn
o
l
o
gi
c
a
l
o
u
tc
o
m
e
a
c
hi
e
v
e
me
nt
s
b
y
s
ta
r
t
-
ups
a
t
uni
ve
r
s
it
y
-
ba
s
e
d
in
c
uba
t
o
r
s
:
a
n
e
mpi
r
i
c
a
l
a
na
l
y
s
is
in
th
e
I
ndi
a
n
c
o
nt
e
x
t,
”
T
e
c
hnol
o
gy
A
nal
y
s
is
and
St
r
at
e
gi
c
M
anage
m
e
nt
,
v
o
l.
34,
n
o
.
9,
pp.
1004
–
10
19,
S
e
p. 2022, d
o
i:
10.1080/09537325.
2021.1940921.
[
12]
K
.
L
uk
o
s
iu
t
e
,
S
.
J
e
ns
e
n,
a
nd
S
.
T
a
n
e
v
,
“
I
s
jo
in
in
g
a
bus
in
e
s
s
in
c
uba
to
r
or
a
c
c
e
le
r
a
to
r
a
lwa
y
s
a
goo
d
th
in
g
?,
”
T
e
c
hno
lo
gy
I
nnov
at
io
n M
a
nage
m
e
nt
R
e
v
ie
w
,
vo
l.
7, n
o
. 10, pp. 5
–
15, J
ul
. 2019, do
i:
10.22215/t
im
r
e
v
i
e
w
/1
251.
[
13]
A
.
R
o
s
a
do
-
C
ube
r
o
,
T
.
F
r
e
ir
e
-
R
ubi
o
,
a
nd
A
.
H
e
r
ná
nde
z
,
“
E
nt
r
e
pr
e
n
e
ur
s
hi
p:
W
ha
t
ma
tt
e
r
s
mo
s
t,
”
J
our
nal
o
f
B
us
in
e
s
s
R
e
s
e
a
r
c
h
,
vo
l.
144, pp. 250
–
263, M
a
y
2022, d
oi
:
10.1016
/j
.j
bus
r
e
s
.2022.01.087.
[
14]
L
.
G
oz
a
li
e
t
al
.
,
“
P
e
r
f
or
ma
n
c
e
f
a
c
t
or
s
f
or
s
uc
c
e
s
s
f
ul
bus
in
e
s
s
in
c
uba
t
o
r
s
in
I
nd
o
ne
s
ia
n
publ
i
c
U
ni
ve
r
s
it
i
e
s
,
”
I
nt
e
r
nat
io
nal
J
our
nal
of
T
e
c
hnol
ogy
, v
o
l.
11, n
o
. 1, p. 155, J
a
n. 2020, do
i:
10.14716
/i
jt
e
c
h.
v
11i
1.2464.
[
15]
S
.
Y
.
N
a
s
ut
io
n
a
nd
A
.
S
uz
ia
nt
i,
“
D
e
ve
l
o
pm
e
nt
of
a
n
in
c
ub
a
to
r
p
e
r
f
or
ma
nc
e
m
o
d
e
l
ba
s
e
d
o
n
us
e
r
pe
r
c
e
pt
i
o
ns
:
a
P
L
S
-
S
E
M
a
ppr
o
a
c
h
,
”
in
4t
h
A
s
ia
P
ac
if
ic
C
onf
e
r
e
nc
e
on R
e
s
e
ar
c
h i
n I
ndus
tr
ia
l
and Sy
s
te
m
s
E
ngi
ne
e
r
in
g 2021
, N
e
w
Y
o
r
k,
N
Y
, U
S
A
:
A
C
M
,
M
a
y
2021, pp. 61
–
67
,
d
o
i
:
10.1145/3468013.34
68310.
[
16]
R
.
K
.
M
a
v
i,
H
.
G
h
e
ib
d
o
us
t,
A
.
A
.
K
ha
nf
a
r
,
a
nd
N
.
K
.
M
a
v
i,
“
R
a
nki
ng
f
a
c
t
or
s
in
f
lu
e
n
c
in
g
s
tr
a
te
gi
c
ma
na
ge
m
e
nt
of
uni
ve
r
s
it
y
bus
in
e
s
s
in
c
uba
to
r
s
w
it
h
A
N
P
,
”
M
anage
m
e
nt
D
e
c
i
s
io
n
,
v
o
l.
57,
n
o
.
12,
pp.
3492
–
3510,
D
e
c
.
2
019,
do
i:
10
.1108/M
D
-
06
-
2018
-
0688.
[
17]
M
.
M
a
da
na
n,
N
.
A
.
M
.
Z
ul
ke
f
li
,
a
nd
N
.
C
.
V
e
la
y
udha
n,
“
D
e
s
ig
ni
ng
a
h
y
b
r
id
a
r
t
i
f
i
c
ia
l
in
t
e
ll
ig
e
nt
c
li
n
ic
a
l
d
e
c
is
i
o
n
s
upp
o
r
t
s
ys
te
m
us
in
g
a
r
ti
f
i
c
ia
l
n
e
ur
a
l
ne
twor
k
a
nd
a
r
ti
f
i
c
ia
l
be
e
c
o
l
o
n
y
f
o
r
p
r
e
di
c
ti
ng
h
e
a
r
t
f
a
il
ur
e
r
a
t
e
,
”
in
20
21
I
nt
e
r
nat
io
nal
C
onf
e
r
e
nc
e
on
C
om
put
e
r
C
om
m
uni
c
at
io
n and I
nf
or
m
at
ic
s
(
I
C
C
C
I
)
, J
a
n. 2021,
pp. 1
–
7,
do
i:
10.1109/
I
C
C
C
I
50826.2021.9457007.
[
18]
R
.
S
ha
r
ma
,
“
A
r
ti
f
ic
ia
l
in
te
ll
ig
e
n
c
e
in
a
gr
ic
ul
tu
r
e
:
a
r
e
v
i
e
w
,
”
in
2021
5t
h
I
nt
e
r
nat
io
nal
C
on
f
e
r
e
nc
e
on
I
nt
e
ll
ig
e
nt
C
om
put
in
g
and
C
ont
r
ol
Sy
s
te
m
s
(
I
C
I
C
C
S)
, M
a
y
2021, pp. 937
–
942
,
d
o
i:
10.11
09/
I
C
I
C
C
S
51141.2021.9432187.
[
19]
S
.
Z
e
l
a
nd
E
.
K
o
nga
r
,
“
T
r
a
ns
f
or
mi
ng
di
gi
ta
l
e
mpl
oy
e
e
e
x
p
e
r
i
e
nc
e
w
it
h
a
r
t
i
f
i
c
ia
l
in
t
e
ll
ig
e
n
c
e
,
”
in
2020
I
E
E
E
/
I
T
U
I
nt
e
r
nat
io
nal
C
onf
e
r
e
nc
e
on A
r
ti
f
i
c
ia
l
I
nt
e
ll
ig
e
nc
e
f
o
r
G
ood (
A
I
4G
)
, S
e
p. 20
20, pp. 176
–
179,
do
i:
10.1109/A
I
4G
50087.2020.9311088.
[
20]
S
. J
. R
us
s
e
ll
a
nd P
. N
o
r
v
ig
,
A
r
ti
f
ic
ia
l
I
nt
e
ll
ig
e
nc
e
A
M
ode
r
n A
p
pr
oac
h T
hi
r
d E
di
ti
on
, T
h
ir
d. 2021.
[
21]
I
.
P
r
i
y
a
da
r
s
hi
ni
,
S
.
S
a
hu,
R
.
K
uma
r
,
a
nd
D
.
T
a
ni
a
r
,
“
A
ma
c
h
i
ne
-
l
e
a
r
ni
ng
e
ns
e
mbl
e
m
o
d
e
l
f
or
pr
e
di
c
ti
ng
e
n
e
r
g
y
c
o
ns
umpt
i
on
in
s
ma
r
t
ho
m
e
s
,
”
I
nt
e
r
ne
t
of
T
hi
ngs
, v
o
l.
20, p. 100636, 2022, d
o
i:
10.1016/j
.i
o
t.
2022.100636.
[
22]
K
.
A
r
ul
kuma
r
a
n,
M
.
P
.
D
e
is
e
n
r
o
th
,
M
.
B
r
unda
ge
,
a
nd
A
.
A
.
B
ha
r
a
th
,
“
D
e
e
p
r
e
in
f
or
c
e
me
nt
le
a
r
n
in
g:
a
br
i
e
f
s
ur
ve
y
,
”
I
E
E
E
Si
gnal
P
r
oc
e
s
s
M
ag
, vo
l.
34, n
o
. 6, pp. 26
–
38, N
ov
. 2017
, do
i:
10.1109/M
S
P
.2017.2743240.
[
23]
M
.
H
.
W
id
ia
nt
o
,
V
.
H
.
C
.
P
ut
r
a
,
a
nd
M
.
P
.
K
e
na
r
di
,
“
I
nt
e
r
pr
e
ta
ti
o
n
a
nd
pe
r
f
o
r
ma
n
c
e
ma
c
hi
n
e
le
a
r
ni
ng
m
o
d
e
l
f
o
r
de
t
e
c
ti
on
of
br
a
in
s
tr
o
ke
ba
s
e
d
o
n
c
la
s
s
i
f
i
e
r
,
”
in
2023
6t
h
I
nt
e
r
nat
io
na
l
C
on
f
e
r
e
nc
e
on
I
n
f
or
m
at
io
n
and
C
om
m
uni
c
at
io
ns
T
e
c
hnol
ogy
(
I
C
O
I
A
C
T
)
, N
ov
. 2023, pp. 183
–
188
,
d
o
i:
10.1109/
I
C
O
I
A
C
T
5
9844.2023.10455892.
[
24]
J
.
A
udr
e
y
a
nd
M
.
H
.
W
id
ia
nt
o
,
“
H
e
a
r
t
a
tt
a
c
k
p
r
e
di
c
ti
o
n
us
in
g
ma
c
hi
ne
l
e
a
r
ni
ng
c
la
s
s
i
f
ic
a
ti
o
n
m
o
d
e
ls
,
”
in
2023
3r
d
I
nt
e
r
nat
i
onal
C
onf
e
r
e
nc
e
on
E
le
c
tr
oni
c
and
E
le
c
tr
ic
al
E
ngi
ne
e
r
in
g
a
nd
I
nt
e
ll
ig
e
nt
Sy
s
te
m
(
I
C
E
3I
S)
,
A
ug.
2023,
pp.
201
–
2
06,
do
i:
10.1109/
I
C
E
3I
S
59323.2023.10335233.
[
25]
A
.
I
.
C
a
nho
t
o
a
nd
F
.
C
l
e
a
r
,
“
A
r
ti
f
i
c
i
a
l
in
t
e
ll
ig
e
n
c
e
a
nd
ma
c
h
in
e
l
e
a
r
ni
ng
a
s
bus
in
e
s
s
to
o
ls
:
a
f
r
a
me
w
o
r
k
f
or
di
a
gn
o
s
in
g
va
lu
e
de
s
tr
u
c
ti
o
n p
o
t
e
nt
ia
l,
”
B
us
H
or
iz
, vo
l.
63, n
o
. 2, pp. 183
–
193, 2
020, do
i:
10.1016/j
.bus
h
o
r
.2019.11.003.
[
26]
W
.
K
r
a
ts
c
h,
J
.
M
a
nde
r
s
c
he
id
,
M
.
R
ögl
in
ge
r
,
a
nd
J
.
S
e
y
f
r
i
e
d,
“
M
a
c
hi
ne
l
e
a
r
ni
ng
in
bus
in
e
s
s
pr
oc
e
s
s
mo
ni
t
o
r
in
g:
a
c
ompa
r
is
on
of
de
e
p
le
a
r
ni
ng
a
nd
c
la
s
s
ic
a
l
a
ppr
o
a
c
h
e
s
us
e
d
f
o
r
o
ut
c
ome
p
r
e
di
c
ti
o
n
,
”
B
us
in
e
s
s
and
I
nf
or
m
at
io
n
Sy
s
te
m
s
E
ngi
ne
e
r
in
g
,
v
o
l.
63,
no
. 3, pp. 261
–
276, 2021, d
o
i:
10.1007/s
12599
-
020
-
00645
-
0.
[
27
]
M
.
A
.
K
ha
n
e
t
al
.
,
“
E
f
f
e
c
ti
ve
de
ma
nd
f
o
r
e
c
a
s
ti
ng
mo
d
e
l
us
in
g
bus
in
e
s
s
in
te
ll
ig
e
nc
e
e
mp
o
w
e
r
e
d
w
it
h
ma
c
hi
ne
l
e
a
r
ni
ng
,
”
I
E
E
E
A
c
c
e
s
s
, v
ol
. 8, pp. 116013
–
116023, J
un. 2020, do
i:
10.11
09/
A
C
C
E
S
S
.2020.3003790.
[
28]
A
.
M
a
r
tí
ne
z
,
C
.
S
c
hmu
c
k,
S
.
P
e
r
e
ve
r
z
y
e
v,
C
.
P
i
r
k
e
r
,
a
nd
M
.
H
a
lt
m
e
i
e
r
,
“
A
ma
c
hi
n
e
l
e
a
r
ni
ng
f
r
a
me
w
o
r
k
f
or
c
us
to
me
r
pur
c
ha
s
e
pr
e
di
c
ti
o
n
in
th
e
n
o
n
-
c
o
n
tr
a
c
tu
a
l
s
e
tt
in
g,
”
E
ur
ope
an
J
our
nal
of
O
pe
r
at
io
nal
R
e
s
e
ar
c
h
,
v
o
l.
281,
n
o
.
3,
pp.
588
–
596,
20
20,
do
i:
10.1016/j
.
e
j
or
.2018.04.034.
[
29]
M
.
K
r
a
us
,
S
.
F
e
ue
r
r
i
e
g
e
l,
a
nd
A
.
O
z
te
ki
n,
“
D
e
e
p
le
a
r
n
in
g
in
b
us
in
e
s
s
a
na
l
y
ti
c
s
a
nd
o
p
e
r
a
ti
o
ns
r
e
s
e
a
r
c
h:
m
o
d
e
ls
,
a
ppl
ic
a
ti
o
ns
a
nd
ma
na
ge
r
ia
l
im
pl
i
c
a
ti
o
ns
,
”
E
ur
ope
an
J
our
nal
o
f
O
pe
r
a
ti
onal
R
e
s
e
ar
c
h
,
v
o
l.
281,
n
o
.
3,
pp.
628
–
641,
20
20,
do
i:
10.1016/j
.
e
j
or
.2019.09.018.
[
30]
A
.
J
.
N
a
kha
l
,
R
.
P
a
tr
ia
r
c
a
,
G
.
D
i
G
r
a
v
i
o
,
G
.
A
nt
o
ni
o
ni
,
a
nd
N
.
P
a
lt
r
in
ie
r
i,
“
I
nve
s
ti
ga
ti
ng
oc
c
upa
ti
o
na
l
a
nd
o
p
e
r
a
ti
o
na
l
in
dus
tr
ia
l
s
a
f
e
t
y
da
ta
th
r
o
ugh
bus
in
e
s
s
in
te
ll
ig
e
n
c
e
a
nd
ma
c
hi
n
e
l
e
a
r
ni
n
g
,
”
J
our
nal
o
f
L
os
s
P
r
e
v
e
nt
io
n
in
th
e
P
r
oc
e
s
s
I
ndus
t
r
ie
s
,
v
o
l.
73,
p. 104608, 2021, do
i:
10.1016/j
.
jl
p.2021.104608.
[
31]
M
.
H
.
W
id
ia
nt
o
,
A
.
A
.
S
.
G
una
w
a
n,
Y
.
H
e
r
y
a
di
,
a
nd
W
.
B
u
di
ha
r
to
,
“
I
nt
e
r
p
r
e
ta
ti
o
n
of
th
e
d
o
mi
na
nt
f
e
a
tu
r
e
s
in
th
e
pr
e
di
c
ti
o
n
r
e
s
ul
ts
of
e
l
e
c
t
r
i
c
a
l
e
n
e
r
g
y
c
o
ns
umpt
i
o
n
us
in
g
s
ma
r
t
h
o
m
e
da
ta
s
e
ts
ba
s
e
d
o
n
KN
N
ma
c
hi
n
e
l
e
a
r
ni
ng
,
”
I
C
I
C
E
x
pr
e
s
s
L
e
tt
e
r
s
, P
ar
t
B
:
A
ppl
ic
at
io
ns
,
vo
l.
15, n
o
. 4, 2024.
[
32]
M
.
H
.
w
id
ia
nt
o
,
“
I
nc
uba
t
o
r
da
ta
s
e
ts
,
”
D
a
ta
s
e
t.
A
c
c
e
s
s
e
d:
J
un.
12,
2024.
[
O
nl
in
e
]
.
A
v
a
il
a
bl
e
:
ht
tp
s
:/
/d
oc
s
.goo
g
le
.
c
o
m/
s
pr
e
a
ds
he
e
ts
/d
/1
F
V
o
C
gD
B
r
e
m
B
b0R
S
c
i
z
y
7w
F
14u1
-
a
A
S
V
k/
e
di
t
?
us
p=
s
ha
r
in
g&o
ui
d=
100964609793302912523&
r
tp
of
=
tr
u
e
&s
d=
tr
ue
[
33]
E
.
S
a
c
c
e
nt
i
, M
.
H
.
W
.
B
.
H
e
n
dr
i
k
s
,
a
n
d
A
.
K
.
S
mi
l
de
,
“
C
o
r
r
up
ti
o
n
o
f
t
he
p
e
a
r
s
o
n
c
o
r
r
e
la
ti
o
n
c
o
e
f
f
ic
ie
nt
b
y
me
a
s
ur
e
me
n
t
e
r
r
o
r
a
n
d i
t
s
e
s
ti
m
a
ti
o
n
,
bi
a
s
,
a
n
d c
o
r
r
e
c
ti
o
n
u
nde
r
di
f
f
e
r
e
nt
e
r
r
o
r
mo
de
l
s
,
”
S
c
i
R
e
p
,
v
o
l.
10
,
no
.
1,
p
.
43
8,
2
02
0,
do
i:
1
0.
10
38
/
s
4
15
98
-
0
19
-
57
247
-
4.
[
34]
D
. M
e
nu
f
a
ndu, R
. F
it
r
ia
ni
, a
nd E
. S
u
ma
r
mi
ni
ngs
ih
,
“
e
s
ti
ma
ti
o
n
of
ma
x
im
um l
ik
e
li
h
oo
d
w
e
ig
ht
e
d
l
o
gi
s
ti
c
r
e
gr
e
s
s
io
n us
in
g g
e
n
e
ti
c
a
lg
o
r
it
h
m
(
c
a
s
e
s
tu
d
y
:
in
di
v
id
ua
l
w
or
k
s
ta
tu
s
in
ma
l
a
ng
c
it
y
),
”
B
A
R
E
K
E
N
G
:
J
ur
nal
I
lmu
M
at
e
m
at
ik
a
dan
T
e
r
apan
,
v
o
l.
17,
pp. 487
–
494, Apr
. 2023, do
i:
10.30598
/b
a
r
e
k
e
ng
vo
l1
7i
s
s
1pp048
7
-
0494.
[
35]
A
.
M
.
A
bdul
a
z
e
e
z
,
“
M
a
c
hi
ne
l
e
a
r
ni
ng
a
ppl
ic
a
ti
o
ns
ba
s
e
d
o
n
S
V
M
c
la
s
s
if
i
c
a
ti
o
n:
a
r
e
v
i
e
w
,
”
M
a
y
2021,
do
i:
10.48161/qaj.
v
1n2a
50.
[
36]
L
.
C
a
ñe
te
-
S
i
f
u
e
nt
e
s
,
R
.
M
o
nr
oy
,
a
nd
M
.
A
.
M
e
di
na
-
P
é
r
e
z
,
“
A
r
e
v
i
e
w
a
nd
e
x
pe
r
im
e
nt
a
l
c
o
mpa
r
is
o
n
of
mul
ti
v
a
r
ia
te
d
e
c
is
io
n
tr
e
e
s
,
”
I
E
E
E
A
c
c
e
s
s
, vo
l.
9, pp. 110451
–
110479, 2021, d
o
i:
10.
1109/AC
C
E
S
S
.2021.3102239.
[
37]
M
.
J
e
o
ng,
J
.
N
a
m,
a
nd
B
.
C
.
K
o
,
“
L
ig
ht
w
e
ig
ht
mul
ti
la
y
e
r
r
a
nd
o
m
f
or
e
s
ts
f
or
m
o
ni
t
or
in
g
dr
i
ve
r
e
m
o
ti
o
na
l
s
ta
t
us
,
”
I
E
E
E
A
c
c
e
s
s
, v
ol
. 8, pp. 60344
–
60354, 2020
, d
o
i:
10.1109/AC
C
E
S
S
.2020.2983202.
[
38]
G
.
M
us
ta
f
a
e
t
al
.
,
“
H
y
p
e
r
s
p
e
c
tr
a
l
r
e
f
le
c
ta
n
c
e
pr
ox
i
e
s
t
o
di
a
gn
o
s
e
in
-
f
ie
ld
f
us
a
r
iu
m
he
a
d
bl
ig
ht
in
w
he
a
t
w
it
h
ma
c
hi
n
e
l
e
a
r
ni
ng,
”
R
e
m
ot
e
Se
ns
(
B
as
e
l)
, vo
l.
14, n
o
. 12, p. 2784, 2022, d
o
i:
10.339
0/
r
s
14122784.
[
39]
W
.
C
ha
ng,
X
.
W
a
ng,
J
.
Y
a
ng,
a
nd
T
.
Q
in
,
“
A
n
im
pr
ove
d
c
a
tb
oo
s
t
-
ba
s
e
d
c
la
s
s
if
i
c
a
ti
o
n
m
o
d
e
l
f
or
e
c
o
l
o
gi
c
a
l
s
ui
ta
bi
li
t
y
of
bl
ue
b
e
r
r
i
e
s
,
”
Se
ns
or
s
, v
o
l.
23, p. 1811, F
e
b. 2023, d
o
i:
10.3390
/s
23041811.
[
40]
X
.
G
a
o
a
nd
G
.
L
i,
“
A
K
N
N
mo
d
e
l
ba
s
e
d
o
n
ma
nha
tt
a
n
d
is
ta
nc
e
t
o
id
e
nt
i
f
y
th
e
S
N
A
R
E
pr
o
t
e
in
s
,
”
I
E
E
E
A
c
c
e
s
s
,
v
o
l
.
8,
pp. 112922
–
112931, 2020, do
i:
10.1109/AC
C
E
S
S
.2020.30030
86.
[
41]
J
.
L
i,
G
.
L
i,
C
.
H
a
i,
a
nd
M
.
G
uo
,
“
T
r
a
ns
f
or
m
e
r
f
a
ul
t
di
a
gn
o
s
i
s
ba
s
e
d
o
n
mul
ti
-
c
la
s
s
a
da
bo
o
s
t
a
lg
o
r
it
hm
,
”
I
E
E
E
A
c
c
e
s
s
,
v
o
l.
10,
pp. 1522
–
1
532, 2022, do
i:
10.1109/AC
C
E
S
S
.2021.3135467.
Evaluation Warning : The document was created with Spire.PDF for Python.