I
A
E
S
I
n
t
e
r
n
at
io
n
al
Jou
r
n
al
of
A
r
t
if
ic
ia
l
I
n
t
e
ll
ig
e
n
c
e
(
I
J
-
A
I
)
V
ol
. 13, No.
4
,
D
e
c
e
m
be
r
2024, pp.
4537
~
4543
I
S
S
N
:
2252
-
8938
,
D
O
I
:
10.11591/
ij
a
i.
v13.i
4
.pp
4537
-
4543
4537
Jou
r
n
al
h
om
e
page
:
ht
tp
:
//
ij
ai
.
ia
e
s
c
or
e
.c
om
M
u
l
t
i
-
l
ab
e
l
f
e
at
u
r
e
aw
a
r
e
X
G
B
oost
m
od
e
l
f
or
st
u
d
e
n
t
p
e
r
f
or
m
an
c
e
ass
e
ss
m
e
n
t
u
si
n
g b
e
h
av
i
or
d
at
a i
n
on
l
i
n
e
l
e
ar
n
i
n
g
e
n
vi
r
on
m
e
n
t
S
h
as
h
ir
e
k
h
a H
an
u
m
an
t
h
ap
p
a
1
, C
h
e
t
an
a
P
r
ak
as
h
2
1
D
e
pa
r
t
m
e
nt
of
C
om
put
e
r
S
c
i
e
nc
e
a
nd
E
ngi
ne
e
r
i
ng,
V
i
s
ve
s
va
r
a
ya
T
e
c
hnol
ogi
c
a
l
U
ni
ve
r
s
i
t
y
, M
ys
or
e
, I
ndi
a
2
D
e
pa
r
t
m
e
nt
of
C
om
put
e
r
S
c
i
e
nc
e
a
nd
E
ngi
ne
e
r
i
ng,
B
a
puj
i
I
ns
t
i
t
ut
e
of
E
ngi
ne
e
r
i
ng a
nd T
e
c
hnol
ogy
, D
a
va
na
ge
r
e
, I
ndi
a
A
r
t
ic
le
I
n
f
o
A
B
S
T
R
A
C
T
A
r
ti
c
le
h
is
to
r
y
:
R
e
c
e
iv
e
d
N
ov 24, 202
3
R
e
vi
s
e
d
M
a
r
11, 2024
A
c
c
e
pt
e
d
M
a
r
21, 2024
In
light
of
recent
outbreaks
like
COVID19,
the
use
of
online
-
based
learning
streams
(i.e.,
e
-
Learning
systems)
has
increased
significantly.
Instit
utional
efforts
to
boost
student
achievement
have
made
precise
predicti
ons
of
academic
success
a
priorit
y.
To
analyze
student
session
s
-
stream
s
and
anticipat
e
academic
success,
e
-
l
earning
platform
s
are
startin
g
to
co
mbine
data
mining
(DM)
with
machine
-
learning
(ML)
techniques.
Recent
re
search
highlights
the
difficulties
that
ML
-
based
methods
have
while
dealing
with
unbalanced
data.
In
tackling
ensemble
-
learning,
we
combine
several
ML
algorit
hms
to
select
the
most
appropriat
e
approach
for
the
given
data.
Current
ensemble
-
based
approaches
for
predicting
student
achiev
ement,
nevertheless,
don'
t
do
exceptionally
well,
particularly
when
it
co
mes
to
multi
-
label
classification,
because
they
don'
t
factor
the
relevance
of
features
into
their
approaches.
This
study
presents
multi
-
label
feature
aware
XGBoost
(MLFA
-
XGB)
method
that
improves
upon
the
previousl
y
used
ensemble
-
lear
ning
technique.
The
MLFA
-
XGB
makes
use
of
a
robust
cross
-
validation
approach
for
gaining
a
deeper
understanding
of
feature
relationshi
ps.
The
experimental
results
demonstrate
that
in
compariso
n
with
the
state
-
of
-
the
-
art
ensemble
-
based
student
achievement
pre
dictive
approach,
this
suggest
ed
MLFA
-
XGB
based
approach
provides
much higher
accuracy for pr
ediction
.
K
e
y
w
o
r
ds
:
E
ns
e
m
bl
e
l
e
a
r
ni
ng
F
e
a
tu
r
e
e
xt
r
a
c
ti
on
F
e
a
tu
r
e
s
e
le
c
ti
on
M
a
c
hi
ne
l
e
a
r
ni
ng
M
ul
ti
-
la
be
l
c
la
s
s
if
ic
a
ti
on
S
tu
de
nt
pe
r
f
or
m
a
nc
e
This is an
open
acce
ss artic
le unde
r the
CC BY
-
SA
license.
C
or
r
e
s
pon
di
n
g A
u
th
or
:
S
ha
s
hi
r
e
kha
H
a
num
a
nt
ha
ppa
D
e
pa
r
tm
e
nt
of
C
om
put
e
r
S
c
ie
nc
e
a
nd
E
ngi
ne
e
r
in
g,
V
is
ve
s
v
a
r
a
ya
T
e
c
hnol
ogi
c
a
l
U
ni
ve
r
s
it
y
M
ys
or
e
, I
ndi
a
E
m
a
il
:
s
ha
s
hi
r
e
kha
_h2k22@
r
e
di
f
f
m
a
il
.c
om
1.
I
N
T
R
O
D
U
C
T
I
O
N
E
duc
a
t
io
n
a
l
a
n
d
in
d
u
s
tr
i
a
l
tr
a
i
ni
n
g
h
a
s
s
hi
f
t
e
d
b
e
y
on
d
th
e
tr
a
di
t
i
ona
l
of
f
l
in
e
m
e
th
o
d
to
w
a
r
d
s
a
d
ig
i
ta
l
onl
i
ne
-
m
o
de
,
k
no
w
n
a
s
a
n
e
-
l
e
a
r
n
in
g
e
nv
ir
on
m
e
nt
[
1]
,
b
e
c
a
u
s
e
of
t
he
pr
o
li
f
e
r
a
ti
o
n
o
f
i
nt
e
r
n
e
t
a
c
c
e
s
s
a
lo
ng
s
i
de
th
e
d
e
v
e
lo
pm
e
nt
of
t
e
c
hno
lo
gi
c
a
l
d
e
vi
c
e
s
.
T
he
im
por
t
a
n
c
e
w
it
h
in
a
n
e
-
l
e
a
r
ni
n
g
e
n
vi
r
o
nm
e
nt
w
a
s
d
r
iv
e
n
s
tr
ong
ly
t
hr
o
ugh
ou
t
th
e
C
O
V
I
D
-
19
out
br
e
a
k
w
h
e
n
e
ve
r
y
s
c
ho
ol
w
a
s
s
w
i
tc
he
d
to
a
f
ul
l
y
on
li
n
e
i
n
s
tr
u
c
t
io
n
a
l
m
e
t
hod
.
A
t
r
u
s
t
w
or
t
hy
a
n
d
pr
e
c
i
s
e
a
ppr
oa
c
h
f
or
pr
e
d
ic
ti
n
g
p
e
r
f
or
m
a
nc
e
a
m
o
ng
l
e
a
r
n
e
r
s
[
2]
i
s
d
if
f
i
c
ul
t
to
pr
ov
id
e
.
A
c
a
d
e
m
i
c
a
c
hi
e
v
e
m
e
nt
f
or
l
e
a
r
n
e
r
s
c
a
n
b
e
e
nh
a
n
c
e
d
us
in
g
in
d
iv
i
du
a
li
z
e
d
c
ur
r
ic
ul
u
m
if
a
n
e
f
f
i
c
i
e
n
t
e
v
a
lu
a
t
io
n
a
ppr
oa
c
h
i
s
de
ve
lo
pe
d b
y
a
n
a
l
yz
i
ng
s
e
s
s
i
on r
e
c
or
di
n
g
s
f
r
om
a
n o
nl
i
ne
l
e
a
r
ni
n
g
e
n
vi
r
onm
e
n
t.
T
he
bi
gge
s
t
pr
obl
e
m
s
w
it
h
to
da
y'
s
e
-
l
e
a
r
ni
ng
s
y
s
te
m
s
[
3]
or
i
gi
na
te
f
r
om
th
e
f
a
c
t
th
a
t
th
e
y
don'
t
a
ll
ow
f
or
th
e
s
ha
r
in
g
of
m
a
te
r
ia
l
th
a
t
c
a
n
be
c
us
to
m
iz
e
d
to
e
a
c
h
s
tu
de
nt
'
s
uni
que
pr
e
f
e
r
e
nc
e
s
a
nd
le
a
r
ni
ng
a
ppr
oa
c
h.
I
n
or
de
r
to
be
tt
e
r
unde
r
s
ta
nd
e
a
c
h
s
tu
de
nt
,
e
duc
a
to
r
s
ha
ve
pl
a
c
e
d
a
n
e
m
ph
a
s
is
on
us
in
g
a
da
pt
iv
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8938
I
nt
J
A
r
ti
f
I
nt
e
ll
, V
ol
. 13, No.
4
,
D
e
c
e
m
be
r
2024:
4537
-
4543
4538
pe
r
s
ona
li
z
a
ti
on
s
tr
a
te
gi
e
s
[
4]
.
M
a
c
hi
ne
-
le
a
r
ni
ng
(
M
L
)
a
nd
da
ta
-
m
in
in
g
(
D
M
)
te
c
hni
que
s
w
e
r
e
ju
s
t
r
e
c
e
nt
ly
put
to
th
e
m
is
s
io
n
of
pr
e
di
c
ti
ng
a
c
a
de
m
ic
s
uc
c
e
s
s
f
or
in
di
vi
dua
l
s
tu
de
nt
s
.
A
s
il
lu
s
tr
a
te
d
in
F
ig
ur
e
1,
D
M
h
a
s
be
e
n
e
m
pl
oye
d
to
ga
in
va
lu
a
bl
e
in
f
or
m
a
ti
on
th
r
ough
th
e
s
e
s
s
io
n
-
s
tr
e
a
m
s
in
f
or
m
a
ti
on
of
a
pa
r
ti
c
ul
a
r
e
-
l
e
a
r
ni
ng
pl
a
tf
or
m
'
s
le
a
r
ne
r
s
,
w
hi
c
h
in
tu
r
n
ha
s
im
pr
ove
d
de
c
i
s
i
on
-
m
a
ki
ng
a
nd
in
c
r
e
a
s
e
d
pr
oduc
ti
vi
ty
[
5]
.
T
he
a
ppl
ic
a
ti
ons
of
D
M
a
nd
M
L
in
a
va
r
ie
ty
of
s
e
c
to
r
s
,
li
ke
or
ga
ni
z
a
ti
on,
in
f
or
m
a
ti
on
s
e
c
ur
it
y,
a
nd
e
duc
a
ti
ona
l
oppor
tu
ni
ti
e
s
[
6]
s
how
gr
e
a
t
pr
om
is
e
.
E
duc
a
ti
on
da
ta
-
m
in
in
g
(
E
D
M
)
[
7
]
is
a
r
e
la
ti
ve
ly
ne
w
di
s
c
ip
li
ne
th
a
t
a
im
s
to
im
pr
ove
te
a
c
hi
ng
m
e
th
ods
,
le
a
r
ne
r
pr
o
f
il
e
s
a
nd
a
c
a
de
m
ic
out
c
om
e
s
[
8]
.
V
a
r
io
us
ki
nds
of
da
ta
m
a
ke
up
th
e
E
D
M
,
in
c
lu
di
ng
r
e
c
or
ds
of
a
dm
in
is
tr
a
ti
ve
a
c
ti
ons
,
r
e
c
or
ds
of
le
a
r
ne
r
s
e
s
s
io
n
-
s
tr
e
a
m
s
ope
r
a
ti
on,
a
nd
r
e
c
or
ds
of
le
a
r
ne
r
a
c
a
de
m
ic
a
c
hi
e
ve
m
e
nt
.
E
D
M
da
ta
s
e
ts
w
e
r
e
m
a
de
a
va
il
a
bl
e
in
[
9]
,
[
10]
,
w
hi
c
h
ga
th
e
r
e
d
in
f
or
m
a
ti
on
f
r
om
s
e
ve
r
a
l
onl
in
e
r
e
s
our
c
e
s
.
T
he
y
u
s
e
d
s
e
ve
r
a
l
M
L
m
ode
ls
a
lo
ng
w
it
h
a
n
e
ns
e
m
bl
e
-
le
a
r
ni
ng
te
c
hni
que
to
f
or
e
c
a
s
t
how
w
e
ll
s
tu
de
nt
s
w
il
l
do
th
r
oughout
th
e
c
our
s
e
of
s
tu
dy.
T
he
r
e
s
ul
ts
de
m
ons
tr
a
te
th
a
t
th
e
e
ns
e
m
bl
e
a
ppr
oa
c
h
pr
ovi
de
s
th
e
m
os
t
a
c
c
ur
a
te
pr
e
di
c
ti
o
ns
.
N
e
ve
r
th
e
le
s
s
,
th
e
s
e
a
ppr
oa
c
he
s
f
a
il
e
d
to
c
r
e
a
te
a
f
e
a
tu
r
e
a
f
f
e
c
ti
ng
pr
e
di
c
ti
on
a
ppr
oa
c
h,
le
a
di
ng
to
lo
w
a
c
c
ur
a
c
y
in
c
la
s
s
if
yi
ng
w
he
ne
ve
r
th
e
in
f
or
m
a
ti
on c
ons
id
e
r
in
g m
ul
ti
-
la
be
l
c
la
s
s
if
ic
a
ti
on a
nd i
m
ba
la
nc
e
d da
ta
pr
obl
e
m
.
F
ig
ur
e
1. A
r
c
hi
te
c
tu
r
e
of
pr
opos
e
d
T
he
pr
im
a
r
y
a
im
of
th
is
s
tu
dy
is
to
de
ve
lo
p
a
r
obus
t
le
a
r
ne
r
pr
e
di
c
ti
on
a
ppr
oa
c
h
w
hi
c
h
pr
e
di
c
ts
a
c
c
ur
a
te
ly
s
tu
d
e
nt
gr
a
de
s
th
r
oughout
a
gi
ve
n
c
our
s
e
by
de
v
e
lo
pi
ng
m
ul
ti
-
la
be
l
f
e
a
tu
r
e
a
w
a
r
e
(
M
L
F
A
)
-
X
G
B
to
e
f
f
e
c
ti
ve
ly
a
na
ly
z
e
le
a
r
ne
r
s
e
s
s
io
n
-
s
tr
e
a
m
s
e
-
le
a
r
ni
ng
in
f
or
m
a
ti
on.
T
he
m
ode
l
is
ve
r
y
e
f
f
e
c
ti
ve
i
n
c
la
s
s
if
yi
ng
th
e
pe
r
f
or
m
a
nc
e
of
s
tu
de
nt
s
c
ons
id
e
r
in
g
th
r
e
e
di
f
f
e
r
e
nt
c
la
s
s
e
s
s
uc
h
a
s
w
e
a
k,
a
ve
r
a
ge
,
a
nd
good.
T
he
pr
opos
e
d m
ode
l
a
c
hi
e
ve
s
m
u
c
h hi
ghe
r
a
c
c
ur
a
c
y t
ha
n
c
ur
r
e
nt
M
L
a
nd e
ns
e
m
bl
e
-
ba
s
e
d a
ppr
oa
c
he
s
.
M
a
nus
c
r
ip
t
or
ga
ni
z
a
ti
on.
I
n
s
e
c
ti
on
2
th
e
de
ta
il
e
d
s
ur
ve
y
of
va
r
io
us
e
xi
s
ti
ng
m
e
th
odol
ogi
e
s
a
nd
th
e
ir
li
m
it
a
ti
ons
ha
ve
be
e
n
hi
ghl
ig
ht
e
d.
T
he
pr
opos
e
d
m
e
th
odo
lo
gy
is
di
s
c
us
s
e
d
in
s
e
c
ti
on
3.
T
he
e
xpe
r
im
e
nt
s
tu
dy
us
in
g
s
tu
de
nt
s
e
s
s
io
n
s
tr
e
a
m
da
ta
is
gi
v
e
n
in
s
e
c
ti
on
4.
T
he
la
s
t
s
e
c
ti
on
s
ig
ni
f
ic
a
nc
e
of
w
or
k
is
gi
ve
n
a
nd f
ut
ur
e
r
e
s
e
a
r
c
h di
r
e
c
ti
on f
or
e
nha
nc
in
g s
tu
de
nt
pe
r
f
or
m
a
nc
e
pr
e
di
c
ti
on outc
om
e
s
.
2.
L
I
T
E
R
A
T
U
R
E
S
U
R
V
E
Y
I
n
th
e
li
te
r
a
tu
r
e
s
ur
ve
y
s
e
c
ti
on,
s
e
v
e
r
a
l
s
tu
di
e
s
ha
ve
b
e
e
n
di
s
c
us
s
e
d,
e
a
c
h
f
oc
us
in
g
on
pr
e
di
c
ti
ng
s
tu
de
nt
pe
r
f
or
m
a
nc
e
us
in
g
M
L
a
lg
or
it
hm
s
in
va
r
io
us
e
duc
a
ti
o
na
l
s
e
tt
in
gs
.
T
he
s
e
s
tu
di
e
s
le
v
e
r
a
ge
di
f
f
e
r
e
nt
da
ta
s
e
ts
,
f
e
a
tu
r
e
s
e
le
c
ti
on
te
c
hni
que
s
,
a
nd
M
L
a
lg
or
it
hm
s
to
f
o
r
e
c
a
s
t
a
c
a
de
m
ic
a
c
hi
e
v
e
m
e
nt
a
nd
e
nha
nc
e
th
e
qua
li
ty
of
e
duc
a
ti
on.
I
n
[
11]
,
[
12]
,
th
e
pr
im
a
r
y
obj
e
c
ti
ve
w
a
s
to
pr
e
di
c
t
s
tu
de
nt
pe
r
f
or
m
a
nc
e
a
t
di
f
f
e
r
e
nt
s
ta
ge
s
of
c
our
s
e
de
li
ve
r
y
u
s
in
g
M
L
.
T
w
o
s
e
pa
r
a
te
da
ta
s
e
ts
r
e
pr
e
s
e
nt
in
g
c
our
s
e
de
li
ve
r
y
a
t
20%
a
nd
50%
c
om
pl
e
ti
on
s
ta
ge
s
w
e
r
e
m
e
ti
c
ul
ous
ly
a
na
ly
z
e
d.
T
he
s
tu
dy
b
e
gi
ns
w
it
h
a
f
e
a
tu
r
e
a
na
ly
s
is
to
ga
in
in
s
ig
ht
s
in
to
th
e
da
ta
s
e
t'
s
n
a
tu
r
e
,
w
hi
c
h
in
f
or
m
s
th
e
s
e
le
c
ti
on
of
M
L
a
lg
or
it
hm
s
a
nd
th
e
ir
pa
r
a
m
e
te
r
s
.
A
s
y
s
te
m
a
ti
c
a
ppr
oa
c
h
ba
s
e
d
on
th
e
G
in
i
in
de
x
a
nd
p
-
va
lu
e
is
pr
opos
e
d
to
c
hoos
e
a
s
ui
ta
bl
e
e
n
s
e
m
bl
e
l
e
a
r
ne
r
f
r
om
s
ix
pot
e
nt
ia
l
M
L
a
lg
or
it
hm
s
.
T
he
e
xpe
r
im
e
nt
a
l
r
e
s
ul
ts
in
di
c
a
te
th
a
t
th
e
pr
opos
e
d
e
ns
e
m
bl
e
m
ode
ls
a
c
hi
e
ve
hi
gh
a
c
c
ur
a
c
y a
nd l
ow
f
a
ls
e
pos
it
iv
e
r
a
te
s
f
or
bot
h da
ta
s
e
ts
a
t
a
ll
s
ta
ge
s
.
I
n
[
13]
–
[
15]
,
th
is
r
e
s
e
a
r
c
h
f
oc
us
e
s
on
unde
r
gr
a
dua
te
da
ta
s
e
ts
f
r
om
two
di
s
ti
nc
t
uni
v
e
r
s
it
ie
s
a
nd
a
im
s
to
pr
e
di
c
t
s
tu
de
nt
a
c
hi
e
ve
m
e
nt
a
t
two
poi
nt
s
dur
in
g
c
our
s
e
d
e
li
ve
r
y.
I
t
f
ol
lo
w
s
a
s
im
il
a
r
a
ppr
oa
c
h
to
[
16]
,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
r
ti
f
I
nt
e
ll
I
S
S
N
:
2252
-
8938
M
ul
ti
-
la
be
l
fe
at
ur
e
aw
ar
e
x
gboos
t
m
od
e
l
fo
r
s
tu
de
nt
p
e
r
fo
r
m
an
c
e
…
(
Shas
hi
r
e
k
ha
H
anumanthappa
)
4539
w
it
h
th
e
s
e
le
c
ti
on
of
M
L
a
lg
or
i
th
m
s
a
nd
pa
r
a
m
e
te
r
opt
im
iz
a
t
io
n.
A
m
ul
ti
-
s
pl
it
m
e
th
odol
ogy
ba
s
e
d
on
th
e
G
in
i
in
de
x
a
nd
p
-
va
lu
e
is
e
m
pl
oye
d
to
opt
im
iz
e
a
b
a
ggi
ng
e
ns
e
m
bl
e
le
a
r
ne
r
f
r
om
s
ix
f
ounda
ti
on
M
L
a
lg
or
it
hm
s
.
T
he
e
xp
e
r
im
e
nt
a
l
f
in
di
ngs
s
how
th
a
t
th
e
s
ugge
s
te
d
ba
ggi
ng
e
n
s
e
m
bl
e
m
od
e
ls
de
li
ve
r
good
a
c
c
ur
a
c
y f
or
t
he
t
a
r
ge
t
gr
oup in bot
h da
ta
s
e
ts
. F
ig
ur
e
1 s
how
s
t
he
pr
opos
e
d a
r
c
hi
te
c
tu
r
e
.
T
he
c
e
nt
r
a
l
f
oc
u
s
of
S
ha
hz
a
d
e
t
al
.
[
17]
w
a
s
on
pr
e
di
c
ti
ng
s
tu
de
nt
pe
r
f
or
m
a
nc
e
dur
in
g
onl
in
e
in
te
r
a
c
ti
ve
s
e
s
s
io
ns
u
s
in
g
a
da
ta
s
e
t
c
ol
le
c
te
d
f
r
om
di
gi
ta
l
e
le
c
tr
oni
c
s
e
duc
a
ti
on a
nd
de
s
ig
n s
ui
te
s
. T
he
da
t
a
s
e
t
c
a
pt
ur
e
s
s
tu
de
nt
in
te
r
a
c
ti
ons
dur
in
g
onl
in
e
la
b
w
or
k,
in
c
lu
di
ng
te
xt
e
di
ti
ng,
ke
ys
tr
oke
s
,
ti
m
e
s
pe
nt
in
a
c
ti
vi
ti
e
s
, a
nd e
xa
m
s
c
or
e
s
pe
r
s
e
s
s
io
n. T
he
r
e
s
e
a
r
c
h i
nt
r
oduc
e
s
a
pr
e
di
c
ti
on mode
l
c
ons
is
ti
ng of
86 s
ta
ti
s
ti
c
a
l
f
e
a
tu
r
e
s
,
c
a
te
gor
iz
e
d
in
to
th
r
e
e
br
oa
d
gr
oups
:
a
c
ti
vi
ty
ty
pe
,
ti
m
in
g
s
ta
ti
s
ti
c
s
,
a
nd
pe
r
ip
he
r
a
l
a
c
ti
vi
ty
c
ount
.
F
e
a
tu
r
e
s
e
le
c
ti
on
is
u
s
e
d
to
r
e
ta
in
in
f
lu
e
nt
ia
l
f
e
a
tu
r
e
s
,
a
nd
f
iv
e
popula
r
c
la
s
s
if
ie
r
s
,
in
c
lu
di
ng
r
a
ndom
f
or
e
s
t
(
R
F
)
a
nd
s
uppor
t
ve
c
to
r
m
a
c
hi
ne
(
S
V
M
)
,
a
r
e
e
m
pl
oye
d.
T
h
e
m
ode
l
a
im
s
to
pr
e
di
c
t
w
he
th
e
r
a
s
tu
de
nt
'
s
pe
r
f
or
m
a
nc
e
w
il
l
be
lo
w
or
hi
gh.
T
hr
e
e
di
f
f
e
r
e
nt
s
c
e
n
a
r
io
s
f
or
m
ode
l
e
va
lu
a
ti
on
a
r
e
c
ons
id
e
r
e
d,
a
nd
th
e
r
e
s
ul
ts
de
m
ons
tr
a
te
e
xc
e
pt
io
na
l
c
la
s
s
if
ic
a
ti
on
a
c
c
ur
a
c
y,
w
it
h
R
F
a
c
hi
e
vi
ng
th
e
be
s
t
pe
r
f
or
m
a
nc
e
a
t
97.4%
.
I
n
[
18]
–
[
20]
,
th
is
s
tu
dy
f
oc
us
e
s
on
pr
e
di
c
ti
ng
f
in
a
l
e
xa
m
gr
a
de
s
of
unde
r
gr
a
dua
te
s
tu
de
nt
s
us
in
g
th
e
ir
m
id
te
r
m
e
xa
m
gr
a
de
s
a
s
s
our
c
e
da
ta
.
I
t
e
m
pl
oys
va
r
io
us
ML
a
lg
or
it
hm
s
,
in
c
lu
di
ng
K
-
ne
a
r
e
s
t
ne
ig
hbor
s
(
K
N
N
)
,
R
F
,
S
V
M
,
na
ïv
e
B
a
ye
s
(
N
B
)
,
a
nd
lo
gi
s
ti
c
r
e
gr
e
s
s
io
n
(
L
R
)
,
to
m
a
k
e
pr
e
di
c
ti
ons
.
T
he
da
ta
s
e
t
c
om
pr
is
e
s
a
c
a
de
m
ic
a
c
hi
e
ve
m
e
nt
gr
a
de
s
of
1854
s
tu
de
nt
s
in
a
T
ur
ki
s
h
L
a
ngua
ge
-
I
c
our
s
e
.
T
he
pr
opos
e
d
m
ode
l,
ba
s
e
d
on
onl
y
th
r
e
e
pa
r
a
m
e
te
r
s
(
m
id
te
r
m
e
xa
m
gr
a
de
s
,
de
pa
r
tm
e
nt
da
ta
,
a
nd
f
a
c
ul
ty
da
ta
)
,
a
c
hi
e
ve
d
a
c
la
s
s
if
ic
a
ti
on
a
c
c
ur
a
c
y
of
70
-
75%
.
T
hi
s
s
tu
dy
is
e
s
s
e
nt
ia
l
f
or
e
s
ta
bl
is
hi
ng
a
le
a
r
ni
ng
a
na
ly
s
is
f
r
a
m
e
w
or
k
in
h
ig
he
r
e
duc
a
ti
on
a
nd
a
id
in
g
in
de
c
is
io
n
-
m
a
ki
ng
pr
oc
e
s
s
e
s
,
pa
r
ti
c
ul
a
r
ly
f
or
id
e
nt
if
yi
ng
s
tu
de
nt
s
a
t
hi
gh
r
is
k
o
f
f
a
il
ur
e
.
P
ongpa
ic
he
t
e
t
al
.
[
21]
in
tr
oduc
e
s
a
M
L
a
ppr
oa
c
h
to
pr
e
di
c
t
s
tu
de
nt
p
e
r
f
or
m
a
nc
e
in
a
n
onl
in
e
le
a
r
ni
ng
e
nvi
r
onm
e
nt
vi
a
th
e
M
a
ha
r
a
t
pl
a
tf
or
m
a
t
T
a
if
U
ni
ve
r
s
it
y,
f
ol
lo
w
in
g
onl
in
e
le
a
r
ni
ng
tr
a
in
in
g
s
ta
nda
r
ds
i
n S
a
udi
A
r
a
bi
a
. F
e
a
tu
r
e
e
xt
r
a
c
ti
on i
s
pe
r
f
or
m
e
d us
in
g hybr
id
opt
im
iz
a
ti
on, a
nd t
he
S
V
M
t
e
c
hni
que
is
a
ppl
ie
d
f
or
pr
e
di
c
ti
ons
.
T
he
pr
im
a
r
y
obj
e
c
ti
ve
is
to
f
or
e
c
a
s
t
a
c
a
de
m
ic
a
c
hi
e
ve
m
e
nt
a
nd
a
s
s
e
s
s
th
e
qu
a
li
ty
a
s
s
ur
a
nc
e
of
onl
in
e
tr
a
in
in
g
pr
ogr
a
m
s
.
D
e
s
c
r
ip
ti
ve
-
a
na
ly
ti
c
a
l
m
e
th
ods
a
r
e
us
e
d
to
a
n
a
ly
z
e
s
a
m
pl
e
opi
ni
ons
a
bout
qua
li
ty
a
s
s
ur
a
nc
e
.
T
hi
s
s
tu
dy
br
id
ge
s
th
e
ga
p
be
tw
e
e
n
onl
in
e
le
a
r
ni
ng
s
ta
nda
r
ds
a
nd
s
tu
d
e
nt
pe
r
f
or
m
a
nc
e
pr
e
di
c
ti
on,
c
ont
r
ib
ut
in
g
to
e
nha
nc
in
g
th
e
qua
li
ty
of
onl
in
e
e
duc
a
ti
on.
S
e
ve
r
a
l
r
e
s
e
a
r
c
he
r
s
[
22]
,
[
23]
pr
opos
e
s
a
m
ul
t
i
-
out
put
hybr
id
e
ns
e
m
bl
e
m
ode
l
th
a
t
ut
il
iz
e
s
da
ta
f
r
om
th
e
s
upe
r
s
ta
r
le
a
r
ni
n
g
c
om
m
uni
c
a
ti
on
pl
a
tf
or
m
(
S
L
C
P
)
to
pr
e
di
c
t
gr
a
de
s
.
I
t
us
e
s
th
e
X
G
B
m
ode
l
to
p
r
e
di
c
t
m
id
-
te
r
m
a
nd
f
in
a
l
gr
a
de
s
,
a
c
hi
e
vi
ng
a
n a
c
c
ur
a
c
y
of
78.37%
,
s
ur
pa
s
s
in
g c
om
pa
r
is
on
m
ode
ls
.
A
ddi
ti
ona
ll
y,
th
e
gr
a
di
e
nt
-
boos
ti
ng
m
ode
l
is
e
m
pl
oye
d
to
pr
e
di
c
t
hom
e
w
or
k
a
nd
e
xpe
r
im
e
nt
gr
a
de
s
,
out
pe
r
f
or
m
in
g
c
om
pa
r
is
on
m
ode
ls
in
m
e
a
n
s
qua
r
e
d
e
r
r
or
.
T
hi
s
m
ul
ti
-
out
put
hybr
id
e
ns
e
m
bl
e
m
od
e
l
pr
ovi
de
s
in
s
ig
ht
s
in
to
how
gr
a
d
e
pr
e
di
c
ti
ons
c
a
n
im
pr
ove
bot
h s
tu
de
nt
l
e
a
r
ni
ng qua
li
ty
a
nd t
e
a
c
he
r
t
e
a
c
hi
ng e
f
f
e
c
ti
ve
ne
s
s
[
24]
.
I
n
s
um
m
a
r
y,
th
e
s
e
s
tu
di
e
s
c
ol
le
c
ti
ve
ly
e
m
pl
oy
M
L
a
lg
or
it
hm
s
to
pr
e
di
c
t
s
tu
de
nt
pe
r
f
o
r
m
a
nc
e
a
nd
e
nha
nc
e
th
e
qua
li
ty
of
e
duc
a
ti
on.
T
he
y
le
ve
r
a
ge
v
a
r
io
us
da
ta
s
e
ts
,
f
e
a
tu
r
e
s
e
l
e
c
ti
on
te
c
hni
que
s
,
a
nd
e
ns
e
m
bl
e
le
a
r
ni
ng
m
e
th
ods
to
a
c
hi
e
ve
hi
gh
a
c
c
ur
a
c
y
in
pr
e
di
c
ti
ng
a
c
a
d
e
m
ic
a
c
hi
e
ve
m
e
nt
s
,
ul
ti
m
a
te
ly
c
ont
r
ib
ut
in
g
to
th
e
im
pr
ove
m
e
nt
of
e
duc
a
ti
ona
l
pr
oc
e
s
s
e
s
a
nd
out
c
om
e
s
.
E
a
c
h
s
tu
dy
of
f
e
r
s
uni
que
in
s
ig
ht
s
a
nd
m
e
th
odol
ogi
e
s
,
c
a
te
r
in
g
to
di
f
f
e
r
e
nt
e
duc
a
ti
ona
l
s
e
tt
in
gs
a
nd
obj
e
c
ti
ve
s
.
H
ow
e
v
e
r
,
c
ons
id
e
r
in
g
m
ul
ti
-
la
be
l
c
la
s
s
if
ic
a
ti
on
th
e
c
ur
r
e
nt
m
e
th
od
e
xhi
bi
ts
poor
a
c
c
ur
a
c
i
e
s
.
T
he
pr
opos
e
d
w
or
k
is
a
im
e
d
a
t
de
s
ig
ni
ng
a
n
e
f
f
e
c
ti
ve
m
e
th
od f
or
i
m
pr
ovi
ng a
c
c
ur
a
c
ie
s
i
n pe
r
f
or
m
in
g m
ul
ti
-
la
be
l
c
la
s
s
if
ic
a
ti
on.
3.
M
U
L
T
I
-
L
A
B
E
L
F
E
A
T
U
R
E
A
W
A
R
E
X
G
B
O
O
S
T
M
O
D
E
L
F
O
R
S
T
U
D
E
N
T
P
E
R
F
O
R
M
A
N
C
E
A
S
S
E
S
S
M
E
N
T
H
e
r
e
,
w
e
in
tr
oduc
e
a
n
e
nha
nc
e
d
M
L
a
ppr
oa
c
h
c
a
ll
e
d
M
L
F
A
-
X
G
B
.
W
hi
c
h
ha
s
be
e
n
de
ve
lo
pe
d
s
pe
c
if
ic
a
ll
y
f
or
th
e
pur
pos
e
of
E
D
M
in
th
e
c
ont
e
xt
of
le
a
r
ne
r
s
e
s
s
io
n
-
s
tr
e
a
m
s
a
s
de
s
c
r
ib
e
d
in
F
ig
ur
e
2
.
T
he
M
L
F
A
-
X
G
B
a
lg
or
it
hm
r
e
pr
e
s
e
nt
s
a
n
a
dva
nc
e
m
e
nt
ove
r
th
e
c
onve
nt
io
na
l
M
L
F
A
-
X
G
B
a
ppr
oa
c
h
by
in
c
or
por
a
ti
ng a
m
or
e
e
f
f
ic
ie
nt
s
e
le
c
ti
ng f
e
a
tu
r
e
s
pr
oc
e
s
s
.
T
he
X
G
B
a
ppr
oa
c
h
r
e
pr
e
s
e
nt
s
a
n
e
nha
nc
e
d
it
e
r
a
ti
on
of
th
e
pr
e
vi
ous
gr
a
di
e
nt
-
boos
ti
ng
a
ppr
oa
c
h
[
25]
.
I
t
in
vol
ve
s
th
e
a
ggr
e
ga
ti
on
of
le
s
s
e
f
f
e
c
ti
ve
c
la
s
s
if
ie
r
s
to
f
or
m
a
r
obus
t
c
la
s
s
if
ie
r
,
r
e
s
ul
ti
ng
in
im
pr
ove
d
c
la
s
s
if
ic
a
ti
on
r
e
s
ul
ts
.
L
e
t
u
s
c
ons
id
e
r
a
da
t
a
s
e
t
de
not
e
d
a
s
,
th
a
t
r
e
pr
e
s
e
nt
s
a
n
ongoing
s
tr
e
a
m
of
le
a
r
ni
ng
s
e
s
s
io
n
in
f
or
m
a
ti
on.
T
hi
s
da
ta
s
e
t
c
ons
is
t
s
of
e
xa
m
pl
e
s
,
w
he
r
e
e
a
c
h
s
a
m
pl
e
is
r
e
pr
e
s
e
nt
e
d
by
a
pa
ir
(
,
)
.
H
e
r
e
,
r
e
pr
e
s
e
nt
s
a
ve
c
to
r
of
f
e
a
tu
r
e
s
,
a
nd
r
e
pr
e
s
e
nt
s
a
la
be
l
a
s
s
oc
ia
te
d
w
it
h
th
e
e
xa
m
pl
e
.
T
h
e
va
r
ia
bl
e
̂
is
ut
il
iz
e
d t
o de
not
e
t
he
e
xpe
c
t
e
d r
e
s
ul
t
ge
ne
r
a
te
d by the
a
ppr
oa
c
h i
n t
he
f
ol
lo
w
in
g m
a
nne
r
.
̂
=
∑
−
1
(
)
,
∈
(
1)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8938
I
nt
J
A
r
ti
f
I
nt
e
ll
, V
ol
. 13, No.
4
,
D
e
c
e
m
be
r
2024:
4537
-
4543
4540
F
ig
ur
e
2. A
r
c
hi
te
c
tu
r
e
of
pr
opos
e
d
T
he
te
r
m
r
e
f
e
r
s
to
a
n
in
de
pe
nde
nt
r
e
gr
e
s
s
io
n
-
tr
e
e
,
w
hi
le
(
)
de
not
e
s
th
e
c
or
r
e
s
ponding
pr
e
di
c
ti
on
r
e
s
ul
ts
ge
ne
r
a
te
d
by
th
e
ℎ
tr
e
e
f
or
th
e
ℎ
s
a
m
pl
e
a
s
s
how
n
in
(
2
)
.
T
he
c
ons
tr
uc
ti
on
of
a
ny
e
ns
e
m
bl
e
-
tr
e
e
i
s
a
c
hi
e
ve
d by me
a
n
s
of
a
s
um
m
a
ti
on me
th
od. T
he
a
nt
ic
ip
a
te
d r
e
s
ul
ts
f
or
t
he
ℎ
s
a
m
pl
e
dur
in
g
th
e
ℎ
it
e
r
a
ti
on,
de
not
e
d
a
s
̂
(
)
,
ne
c
e
s
s
it
a
te
s
th
e
in
c
lu
s
io
n
of
in
or
de
r
to
m
in
im
iz
e
th
e
s
p
e
c
if
ie
d
f
unc
ti
on.
T
he
e
va
lu
a
ti
on of
is
gi
ve
n a
s
gi
ve
n i
n (
4)
.
=
{
(
)
=
(
)
}
(
2)
(
)
=
∑
=
1
(
,
̂
(
−
1
)
+
(
)
)
+
(
)
(
3)
(
)
=
+
1
2
‖
‖
2
(
4)
T
he
r
e
gul
a
r
iz
a
ti
on
-
va
r
ia
bl
e
is
de
not
e
d
by
a
nd
,
w
hi
le
th
e
le
a
f
'
s
-
s
iz
e
is
r
e
pr
e
s
e
nt
e
d
by
.
A
ddi
ti
ona
ll
y,
th
e
r
a
nki
ng
f
or
va
r
io
us
le
a
v
e
s
is
de
not
e
d
by
.
T
he
(
3)
c
a
n
be
r
e
duc
e
d
by
e
m
pl
oyi
ng
th
e
te
c
hni
que
of
r
e
m
ovi
ng t
he
s
ta
bl
e
va
r
ia
bl
e
us
in
g t
he
s
e
c
ond
-
or
de
r
T
a
yl
or
'
s
e
xpa
ndi
ng, whic
h c
a
n be
e
xpr
e
s
s
e
d
in
t
he
f
ol
lo
w
in
g m
a
nne
r
.
(
)
=
∑
=
1
[
ℎ
(
)
+
1
2
(
)
2
]
+
(
)
(
5)
T
he
va
r
i
a
bl
e
ℎ
is
us
e
d t
o de
not
e
th
e
i
ni
ti
a
l
or
de
r
-
gr
a
di
e
nt
w
it
h
r
e
g
a
r
d t
o
, a
nd
t
he
va
r
ia
bl
e
is
us
e
d
to
de
not
e
t
h
e
ne
xt
or
de
r
-
gr
a
di
e
nt
w
it
h r
e
ga
r
d
to
. I
n a
tt
a
i
ni
ng mo
r
e
opt
im
a
l
pe
r
f
or
m
a
nc
e
w
it
h
le
s
s
f
lu
c
tu
a
ti
on
th
e
w
or
k i
nt
r
odu
c
e
s
a
c
r
os
s
-
e
nt
r
opy lo
s
s
f
u
nc
ti
o
n a
w
a
r
e
gr
a
di
e
n
t
boos
ti
ng t
r
e
e
a
s
de
f
i
ne
d i
n (
6)
. T
h
e
p
a
r
a
m
e
t
e
r
̂
is
c
a
l
c
ul
a
te
d
in
(
7)
,
a
nd
f
or
a
c
t
iv
a
ti
on
s
ig
m
oi
d
ope
r
a
ti
on
is
c
om
put
e
d
a
s
gi
ve
n
in
(
8)
.
T
h
e
n,
th
e
w
or
k
in
tr
oduc
e
s
a
K
-
f
ol
d c
r
os
s
v
a
li
da
ti
on f
or
s
e
le
c
ti
ng
a
nd r
a
nki
ng
f
e
a
tu
r
e
w
it
h l
e
s
s
t
r
a
in
in
g
e
r
r
or
u
s
in
g
(
9)
.
=
−
∑
=
1
[
(
̂
)
+
(
1
−
)
(
1
−
̂
)
]
(
6)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
r
ti
f
I
nt
e
ll
I
S
S
N
:
2252
-
8938
M
ul
ti
-
la
be
l
fe
at
ur
e
aw
ar
e
x
gboos
t
m
od
e
l
fo
r
s
tu
de
nt
p
e
r
fo
r
m
an
c
e
…
(
Shas
hi
r
e
k
ha
H
anumanthappa
)
4541
̂
=
1
[
1
+
(
−
)
]
,
(
7)
̂
=
̂
(
1
−
̂
)
(
8)
(
)
=
1
∑
=
1
∑
=
1
∑
∈
−
(
,
̂
−
(
)
(
,
)
)
(
9)
I
n
(
9)
,
to
s
e
le
c
t
id
e
a
l
̂
f
or
opt
im
i
z
in
g
th
e
s
tu
de
nt
pr
e
d
ic
ti
o
n
m
o
de
l
is
a
tt
a
in
e
d
a
s
f
ol
lo
w
s
.
W
he
r
e
de
f
in
e
s
s
i
z
e
of
tr
a
in
in
g
da
t
a
s
e
t
c
on
s
id
e
r
e
d,
(
∙
)
de
f
in
e
s
lo
s
s
f
unc
ti
on,
a
nd
̂
−
(
)
(
∙
)
de
f
in
e
s
a
f
u
nc
ti
o
n
to
c
om
put
e
c
oe
f
f
i
c
ie
n
ts
. T
h
e
pr
opo
s
e
d M
L
F
A
-
X
G
B
ba
s
e
d s
tu
d
e
nt
pe
r
f
or
m
a
nc
e
pr
e
di
c
ti
on
m
o
de
l
a
c
hi
e
ve
s
be
tt
e
r
c
la
s
s
if
i
c
a
ti
on a
c
c
ur
a
c
y
i
n
c
om
p
a
r
is
o
n w
it
h
e
xi
s
ti
n
g e
n
s
e
m
bl
e
-
b
a
s
e
d
c
la
s
s
if
ie
r
a
s
s
h
ow
n i
n r
e
s
ul
t
s
e
c
ti
on
.
̂
=
(
)
(
10)
4.
R
E
S
U
L
T
A
N
D
A
N
A
L
Y
S
I
S
T
hi
s
s
e
c
ti
on
de
lv
e
s
in
to
th
e
e
xa
m
in
a
ti
on
of
s
tu
de
nt
pe
r
f
or
m
a
nc
e
pr
e
di
c
ti
on
by
e
m
pl
oyi
ng
th
e
pr
e
s
e
nt
e
d
M
L
F
A
-
X
G
B
a
ppr
oa
c
h
a
lo
ngs
id
e
a
ddi
ti
ona
l
e
s
t
a
bl
is
he
d
M
L
-
ba
s
e
d
a
ppr
oa
c
he
s
f
or
le
a
r
ne
r
pr
e
di
c
ti
on
[
10]
,
[
15]
.
T
he
e
va
lu
a
ti
on
of
pe
r
f
o
r
m
a
nc
e
in
th
is
s
tu
dy
ut
il
iz
e
s
th
e
e
-
le
a
r
ni
ng
da
ta
s
e
t
obt
a
in
e
d
us
in
g
[
10]
.
T
he
da
ta
s
e
t
pr
e
f
e
r
e
nc
e
is
pr
e
di
c
a
te
d
upon
th
e
f
in
di
ngs
pr
e
s
e
nt
e
d
in
a
c
om
pa
r
a
ti
ve
s
tu
dy
[
9]
,
[
10]
,
[
15]
.
T
he
M
L
a
ppr
oa
c
h
ut
il
iz
e
d
in
th
is
s
tu
dy
f
or
th
e
pur
pos
e
of
pr
e
di
c
ti
ng
s
tu
de
nt
pe
r
f
or
m
a
nc
e
ha
s
be
e
n
de
ve
lo
pe
d
w
it
h
th
e
P
yt
hon
3
f
r
a
m
e
w
or
k.
T
h
e
a
c
c
ur
a
c
y,
s
p
e
c
if
ic
it
y,
s
e
ns
it
iv
it
y,
a
nd
F
1
-
s
c
or
e
a
r
e
m
e
tr
ic
s
u
s
e
d
f
or
va
li
da
ti
ng
m
ode
ls
.
T
he
pr
opos
e
d
w
or
k
na
m
e
ly
M
L
F
A
-
X
G
B
is
c
om
pa
r
e
d
w
it
h
e
xi
s
ti
ng
m
e
th
odol
ogi
e
s
na
m
e
ly
m
ul
ti
-
s
pl
it
opt
im
iz
a
ti
on ba
ggi
ng e
ns
e
m
bl
e
(
M
S
O
B
E
)
[
10]
, R
F
-
e
ns
e
m
bl
e
[
15]
,
a
nd
X
G
B
[
9]
, [
10
]
.
T
he
s
p
e
c
if
ic
it
y
pe
r
f
or
m
a
nc
e
is
gi
ve
n
in
F
ig
ur
e
3.
T
he
r
e
s
ul
ts
s
how
th
a
t
th
e
M
S
O
B
E
a
c
hi
e
ve
s
m
uc
h
le
s
s
s
pe
c
if
ic
it
y,
th
e
X
G
B
m
ode
l
a
c
hi
e
ve
s
b
e
tt
e
r
pe
r
f
or
m
a
nc
e
t
ha
n
R
F
-
e
ns
e
m
bl
e
a
nd
M
S
O
B
E
.
O
n
th
e
ot
he
r
s
id
e
,
th
e
pr
opos
e
d
M
L
F
A
-
X
G
B
a
c
hi
e
ve
s
m
u
c
h
be
tt
e
r
s
pe
c
if
i
c
it
y
pe
r
f
or
m
a
nc
e
th
a
n
ot
he
r
e
xi
s
ti
ng
s
tu
de
nt
pe
r
f
or
m
a
nc
e
c
la
s
s
if
ic
a
ti
on
m
e
th
ods
.
T
he
s
e
ns
it
iv
it
y
pe
r
f
or
m
a
n
c
e
is
gi
v
e
n
in
F
ig
ur
e
4.
T
he
r
e
s
ul
ts
s
ho
w
th
a
t
th
e
M
S
O
B
E
a
c
hi
e
ve
s
m
uc
h
l
e
s
s
s
e
ns
it
iv
it
y,
th
e
X
G
B
m
ode
l
a
c
hi
e
ve
s
b
e
tt
e
r
pe
r
f
or
m
a
nc
e
th
a
n
R
F
-
e
ns
e
m
bl
e
a
nd M
S
O
B
E
. O
n t
he
ot
he
r
s
id
e
, t
he
pr
opos
e
d
M
L
F
A
-
X
G
B
a
c
hi
e
ve
s
m
uc
h be
tt
e
r
s
e
ns
it
iv
it
y pe
r
f
or
m
a
nc
e
t
ha
n
ot
he
r
e
xi
s
ti
ng s
tu
de
nt
pe
r
f
or
m
a
nc
e
c
la
s
s
if
ic
a
ti
on me
th
ods
.
F
ig
ur
e
3. S
pe
c
if
ic
it
y pe
r
f
or
m
a
nc
e
F
ig
ur
e
4. S
e
ns
it
iv
it
y pe
r
f
or
m
a
nc
e
T
he
a
c
c
ur
a
c
y
pe
r
f
or
m
a
nc
e
is
gi
ve
n
in
F
ig
ur
e
5.
T
he
r
e
s
ul
ts
s
how
th
a
t
th
e
M
S
O
B
E
a
c
hi
e
ve
s
m
uc
h
le
s
s
a
c
c
ur
a
c
y,
th
e
X
G
B
m
ode
l
a
c
hi
e
ve
s
be
tt
e
r
pe
r
f
or
m
a
nc
e
th
a
n
R
F
-
e
ns
e
m
bl
e
a
nd
M
S
O
B
E
.
O
n
th
e
ot
he
r
s
id
e
,
th
e
pr
opo
s
e
d
M
L
F
A
-
X
G
B
a
c
hi
e
ve
s
m
uc
h
be
tt
e
r
a
c
c
ur
a
c
y
pe
r
f
or
m
a
nc
e
th
a
n
ot
he
r
e
xi
s
ti
ng
s
tu
de
nt
pe
r
f
or
m
a
nc
e
c
la
s
s
if
ic
a
ti
on me
th
ods
.
T
he
F
1
-
s
c
or
e
pe
r
f
or
m
a
nc
e
is
gi
ve
n
in
F
ig
ur
e
6.
T
h
e
r
e
s
ul
t
s
s
h
ow
th
a
t
th
e
M
S
O
B
E
a
c
hi
e
ve
s
m
uc
h
le
s
s
F
1
-
s
c
or
e
,
th
e
X
G
B
m
ode
l
a
c
hi
e
ve
s
be
tt
e
r
pe
r
f
o
r
m
a
nc
e
t
ha
n
R
F
-
e
ns
e
m
bl
e
a
nd
M
S
O
B
E
.
O
n
th
e
ot
he
r
s
id
e
,
th
e
pr
opo
s
e
d
M
L
F
A
-
X
G
B
a
c
hi
e
ve
s
m
uc
h
be
tt
e
r
a
c
c
ur
a
c
y
pe
r
f
or
m
a
nc
e
th
a
n
ot
he
r
e
xi
s
ti
ng
s
tu
de
nt
pe
r
f
or
m
a
nc
e
c
la
s
s
if
ic
a
ti
on me
th
ods
.
0
0.2
0.4
0.6
0.8
1
1.2
R
F
-
E
ns
e
m
bl
e
M
S
O
B
E
XGB
M
L
F
A
-
X
G
B
S
pe
c
i
f
i
c
i
t
y
P
r
e
di
c
t
i
on M
ode
l
s
Speci
f
i
ci
t
y
R
F
-
E
ns
e
m
bl
e
M
S
O
B
E
XGB
M
L
F
A
-
X
G
B
0
0.2
0.4
0.6
0.8
1
1.2
R
F
-
E
ns
e
m
bl
e
M
S
O
B
E
XGB
M
L
F
A
-
X
G
B
S
e
ns
i
t
i
v
i
t
y
P
r
e
di
c
t
i
on M
ode
l
s
Sen
s
i
t
i
v
i
t
y
R
F
-
E
ns
e
m
bl
e
M
S
O
B
E
XGB
M
L
F
A
-
X
G
B
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8938
I
nt
J
A
r
ti
f
I
nt
e
ll
, V
ol
. 13, No.
4
,
D
e
c
e
m
be
r
2024:
4537
-
4543
4542
F
ig
ur
e
5. A
c
c
ur
a
c
y pe
r
f
or
m
a
nc
e
F
ig
ur
e
6. F
-
m
e
a
s
ur
e
pe
r
f
or
m
a
nc
e
5.
C
O
N
C
L
U
S
I
O
N
T
he
pr
e
s
e
nt
s
tu
dy
in
tr
oduc
e
s
a
nove
l
e
ns
e
m
bl
e
M
L
a
ppr
oa
c
h
w
hi
c
h
de
m
ons
tr
a
te
s
e
nh
a
nc
e
d
e
f
f
ic
ie
nc
y
th
r
ough
th
e
m
odi
f
ic
a
ti
on
o
f
th
e
X
G
B
oos
t
a
lg
or
it
hm
.
N
ot
a
bl
y,
th
is
m
e
th
od
e
xhi
bi
ts
r
obus
t
pe
r
f
or
m
a
nc
e
e
ve
n
in
s
c
e
n
a
r
io
s
w
he
r
e
th
e
tr
a
in
in
g
in
f
or
m
a
ti
on
s
uf
f
e
r
s
f
r
om
im
ba
la
nc
e
d
c
la
s
s
di
s
tr
ib
ut
io
n.
I
n
th
is
s
tu
dy,
w
e
of
f
e
r
a
nove
l
a
nd
e
f
f
ic
ie
nt
c
r
os
s
-
va
li
da
ti
on
m
e
th
od
th
a
t
a
im
s
to
de
te
r
m
in
e
th
e
s
pe
c
if
ic
f
e
a
tu
r
e
s
th
a
t
ha
ve
s
ig
ni
f
ic
a
nt
e
f
f
e
c
ts
on
th
e
c
or
r
e
c
tn
e
s
s
of
a
pr
e
di
c
ti
on
a
ppr
oa
c
h.
T
he
ut
il
iz
a
ti
on
of
th
e
C
V
m
e
th
od
in
vol
ve
s
th
e
im
pl
e
m
e
nt
a
ti
on
of
a
pr
of
ic
ie
nt
f
e
a
tu
r
e
r
a
nki
ng
m
e
th
od,
w
hi
c
h
a
im
s
to
e
nha
nc
e
th
e
a
c
c
ur
a
c
y
of
pr
e
di
c
ti
ons
by
m
in
im
iz
in
g
th
e
pr
e
di
c
ti
on
-
e
r
r
o
r
.
T
he
r
e
s
e
a
r
c
h
s
tu
dy
w
a
s
c
a
r
r
ie
d
out
ut
il
iz
in
g
a
da
ta
s
e
t
c
ons
is
ti
ng
of
c
onve
nt
io
na
l
s
tu
de
nt
-
s
e
s
s
io
n
s
tr
e
a
m
in
g
in
f
or
m
a
ti
on.
T
he
M
L
F
A
-
X
G
B
m
e
th
od
e
xhi
bi
ts
not
a
bl
e
e
nha
nc
e
m
e
nt
s
in
te
r
m
s
of
pr
e
c
is
io
n,
a
c
c
ur
a
c
y,
s
pe
c
if
ic
it
y,
s
e
ns
it
iv
it
y,
a
nd
F
-
m
e
a
s
ur
e
pe
r
f
or
m
a
nc
e
w
he
n
c
om
pa
r
e
d
to
e
xi
s
ti
ng
s
tu
de
nt
pe
r
f
or
m
a
nc
e
pr
e
di
c
ti
ve
a
ppr
oa
c
he
s
u
s
in
g
R
F
-
e
ns
e
m
bl
e
,
M
S
O
B
E
,
a
nd
X
G
B
-
ba
s
e
d a
ppr
oa
c
he
s
. T
he
f
ut
ur
e
w
or
k w
oul
d be
f
oc
us
e
d i
n e
nha
nc
in
g t
he
m
ode
l
f
ur
th
e
r
a
nd a
ls
o f
ur
th
e
r
va
li
da
te
th
e
m
ode
l
unde
r
m
or
e
di
ve
r
s
e
da
ta
s
e
t.
R
E
F
E
R
E
N
C
E
S
[
1]
A
.
E
.
T
a
t
a
r
a
nd
D
.
D
üş
t
e
gör
,
“
P
r
e
di
c
t
i
on
o
f
a
c
a
de
m
i
c
pe
r
f
or
m
a
nc
e
a
t
unde
r
gr
a
dua
t
e
gr
a
dua
t
i
on:
C
our
s
e
gr
a
de
s
or
gr
a
de
poi
nt
a
ve
r
a
ge
?
,”
A
ppl
i
e
d Sc
i
e
nc
e
s
, vol
. 10, no. 14, 2020, doi
:
10.3390/
a
pp10144967.
[
2]
A
.
M
ouba
ye
d,
M
.
I
nj
a
da
t
,
A
.
S
ha
m
i
,
a
nd
H
.
L
ut
f
i
yya
,
“
S
t
ude
nt
e
nga
ge
m
e
nt
l
e
ve
l
i
n
a
n
e
-
l
e
a
r
ni
ng
e
nvi
r
onm
e
nt
:
c
l
us
t
e
r
i
ng
us
i
ng
k
-
m
e
a
ns
,”
A
m
e
r
i
c
an J
ou
r
nal
of
D
i
s
t
anc
e
E
duc
at
i
on
, vol
. 34, no. 2, pp. 137
–
15
6, 2020, doi
:
10.1080/
08923647.2020.1696140.
[
3]
S
. A
. P
r
i
ya
m
ba
da
, T
. U
s
a
ga
w
a
, a
nd M
. E
R
, “
T
w
o
-
l
a
ye
r
e
ns
e
m
bl
e
pr
e
di
c
t
i
on of
s
t
ude
nt
s
’
pe
r
f
or
m
a
nc
e
us
i
ng l
e
a
r
ni
ng be
ha
vi
or
a
nd
dom
a
i
n know
l
e
dge
,”
C
om
put
e
r
s
and E
duc
at
i
on:
A
r
t
i
f
i
c
i
al
I
nt
e
l
l
i
ge
nc
e
, vol
. 5, 2023, doi
:
10.1016/
j
.c
a
e
a
i
.2023.100149.
[
4]
A
.
K
um
a
r
,
A
.
K
a
ur
,
P
.
S
i
ngh,
M
.
D
r
i
s
s
,
a
nd
W
.
B
oul
i
l
a
,
“
E
f
f
i
c
i
e
nt
m
ul
t
i
c
l
a
s
s
c
l
a
s
s
i
f
i
c
a
t
i
on
us
i
ng
f
e
a
t
ur
e
s
e
l
e
c
t
i
on
i
n
hi
gh
-
di
m
e
ns
i
ona
l
da
t
a
s
e
t
s
,”
E
l
e
c
t
r
oni
c
s
, vol
. 12, no. 10, 2023, doi
:
10.3390/
e
l
e
c
t
r
oni
c
s
12102290.
[
5]
A
.
A
l
-
Z
a
w
qa
r
i
,
D
.
P
e
um
a
ns
,
a
nd
G
.
V
a
nde
r
s
t
e
e
n,
“
A
f
l
e
xi
bl
e
f
e
a
t
ur
e
s
e
l
e
c
t
i
on
a
ppr
oa
c
h
f
or
pr
e
di
c
t
i
ng
s
t
ude
nt
s
’
a
c
a
de
m
i
c
pe
r
f
or
m
a
nc
e
i
n onl
i
ne
c
our
s
e
s
,”
C
om
put
e
r
s
and E
duc
at
i
on:
A
r
t
i
f
i
c
i
al
I
nt
e
l
l
i
ge
nc
e
, vol
. 3, 2022, doi
:
10.1016/
j
.c
a
e
a
i
.2022.100103.
[
6]
K
.
J
a
w
a
d,
M
.
A
.
S
ha
h,
a
nd
M
.
T
a
hi
r
,
“
S
t
ude
nt
s
’
a
c
a
de
m
i
c
pe
r
f
or
m
a
nc
e
a
nd
e
nga
ge
m
e
nt
pr
e
di
c
t
i
on
i
n
a
vi
r
t
ua
l
l
e
a
r
ni
ng
e
nvi
r
onm
e
nt
us
i
ng r
a
ndom
f
or
e
s
t
w
i
t
h da
t
a
ba
l
a
nc
i
ng,”
Sus
t
ai
nabi
l
i
t
y
, vol
. 14, no. 22, 2022, doi
:
10.3390/
s
u142214795.
0
0.2
0.4
0.6
0.8
1
1.2
R
F
-
E
ns
e
m
bl
e
M
S
O
B
E
XGB
M
L
F
A
-
X
G
B
A
c
c
u
r
a
c
y
P
r
e
d
i
c
i
t
ve
M
od
e
l
A
c
c
u
r
ac
y
R
F
-
E
ns
e
m
bl
e
M
S
O
B
E
XGB
M
L
F
A
-
X
G
B
0
0.2
0.4
0.6
0.8
1
1.2
R
F
-
E
ns
e
m
bl
e
M
S
O
B
E
XGB
M
L
F
A
-
X
G
B
F1
-
S
c
or
e
P
r
e
d
i
c
i
t
ve
M
od
e
l
F1
-
S
c
or
e
R
F
-
E
ns
e
m
bl
e
M
S
O
B
E
XGB
M
L
F
A
-
X
G
B
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
r
ti
f
I
nt
e
ll
I
S
S
N
:
2252
-
8938
M
ul
ti
-
la
be
l
fe
at
ur
e
aw
ar
e
x
gboos
t
m
od
e
l
fo
r
s
tu
de
nt
p
e
r
fo
r
m
an
c
e
…
(
Shas
hi
r
e
k
ha
H
anumanthappa
)
4543
[
7]
P
.
P
uj
a
r
,
A
.
K
um
a
r
,
a
nd
V
.
K
um
a
r
,
“
P
l
a
nt
l
e
a
f
de
t
e
c
t
i
on
t
hr
ough
m
a
c
hi
ne
l
e
a
r
ni
ng
ba
s
e
d
i
m
a
ge
c
l
a
s
s
i
f
i
c
a
t
i
on
a
ppr
oa
c
h,”
I
A
E
S
I
nt
e
r
nat
i
onal
J
our
nal
of
A
r
t
i
f
i
c
i
al
I
nt
e
l
l
i
ge
nc
e
, vol
. 13, no. 1, pp. 1139
–
1148, 2024, doi
:
10.11591/
i
j
a
i
.v13.i
1.pp1139
-
1148.
[
8]
S
.
H
.
S
r
e
e
dha
r
a
,
V
.
K
um
a
r
,
a
nd
S
.
S
a
l
m
a
,
“
E
f
f
i
c
i
e
nt
bi
g
da
t
a
c
l
us
t
e
r
i
ng
us
i
ng
a
dhoc
f
uz
z
y
c
m
e
a
n
s
a
nd
a
ut
o
-
e
nc
ode
r
C
N
N
,
”
L
e
c
t
ur
e
N
ot
e
s
i
n N
e
t
w
o
r
k
s
and S
y
s
t
e
m
s
, vol
. 563, pp. 353
–
368, 2023, doi
:
10.1007/
978
-
981
-
19
-
7402
-
1_25.
[
9]
M
.
N
.
I
nj
a
da
t
,
A
.
M
ouba
ye
d,
A
.
B
.
N
a
s
s
i
f
,
a
nd
A
.
S
ha
m
i
,
“
S
ys
t
e
m
a
t
i
c
e
ns
e
m
bl
e
m
ode
l
s
e
l
e
c
t
i
on
a
ppr
oa
c
h
f
or
e
duc
a
t
i
ona
l
da
t
a
m
i
ni
ng,”
K
now
l
e
dge
-
B
as
e
d Sy
s
t
e
m
s
, vol
. 200, 2020, doi
:
10.1016/
j
.knos
ys
.202
0.105992.
[
10]
M
.
N
.
I
nj
a
da
t
,
A
.
M
ouba
ye
d,
A
.
B
.
N
a
s
s
i
f
,
a
nd
A
.
S
ha
m
i
,
“
M
ul
t
i
-
s
pl
i
t
opt
i
m
i
z
e
d
ba
ggi
ng
e
n
s
e
m
bl
e
m
ode
l
s
e
l
e
c
t
i
on
f
or
m
ul
t
i
-
c
l
a
s
s
e
du
c
a
t
i
ona
l
da
t
a
m
i
ni
ng,”
A
ppl
i
e
d I
nt
e
l
l
i
ge
nc
e
, vol
. 50, no. 12, pp. 4506
–
4528, 2020, doi
:
10.1007/
s
10489
-
020
-
01776
-
3.
[
11]
M
.
L
.
N
i
s
t
a
l
,
“
A
n
e
xp
e
r
i
e
nc
e
of
c
ont
i
nuous
a
s
s
e
s
s
m
e
nt
i
n
t
e
l
e
c
om
m
uni
c
a
t
i
on
t
e
c
hnol
ogi
e
s
e
ngi
ne
e
r
i
ng:
N
e
w
c
os
t
s
f
or
t
he
t
e
a
c
he
r
,”
R
e
v
i
s
t
a
I
be
r
oam
e
r
i
c
ana
d
e
T
e
c
nol
ogi
as
de
l
A
pr
e
ndi
z
aj
e
,
vol
.
8,
no.
2,
pp.
90
–
95,
2013,
doi
:
10.1109/
R
I
T
A
.2013.2258225.
[
12]
M
.
Y
a
ğc
ı
,
“
E
duc
a
t
i
ona
l
da
t
a
m
i
ni
ng:
pr
e
di
c
t
i
on
of
s
t
ude
nt
s
’
a
c
a
de
m
i
c
pe
r
f
or
m
a
nc
e
us
i
ng
m
a
c
hi
ne
l
e
a
r
ni
ng
a
l
gor
i
t
hm
s
,”
Sm
a
r
t
L
e
ar
ni
ng E
nv
i
r
onm
e
nt
s
, vol
. 9, no. 1, 2022, doi
:
10.1186/
s
40561
-
022
-
00192
-
z.
[
13]
M
.
N
.
A
l
s
ub
a
i
e
,
“
P
r
e
di
c
t
i
ng
s
t
ude
nt
p
e
r
f
or
m
a
nc
e
us
i
ng
m
a
c
hi
ne
l
e
a
r
ni
ng
t
o
e
nha
nc
e
t
he
qua
l
i
t
y
a
s
s
ur
a
nc
e
of
onl
i
ne
t
r
a
i
ni
ng
vi
a
M
a
ha
r
a
t
pl
a
t
f
or
m
,”
A
l
e
x
andr
i
a E
ngi
ne
e
r
i
ng J
our
nal
, vol
. 69, pp. 323
–
339, 202
3, doi
:
10.1016/
j
.a
e
j
.2023.02.004.
[
14]
H
.
X
ue
a
nd
Y
.
N
i
u,
“
M
ul
t
i
-
out
put
-
ba
s
e
d
hybr
i
d i
nt
e
gr
a
t
e
d
m
ode
l
s
f
or
s
t
ude
nt
pe
r
f
or
m
a
nc
e
pr
e
di
c
t
i
on,”
A
pp
l
i
e
d
Sc
i
e
nc
e
s
,
vol
.
13,
no. 9, 2023, doi
:
10.3390/
a
pp13095384.
[
15]
G
.
B
.
B
r
a
hi
m
,
“
P
r
e
di
c
t
i
ng
s
t
ude
nt
pe
r
f
o
r
m
a
nc
e
f
r
om
on
l
i
ne
e
nga
ge
m
e
nt
a
c
t
i
vi
t
i
e
s
us
i
ng
nove
l
s
t
a
t
i
s
t
i
c
a
l
f
e
a
t
ur
e
s
,”
A
r
abi
an
J
our
nal
f
or
Sc
i
e
nc
e
and E
ngi
ne
e
r
i
ng
, vol
. 47, no. 8, pp. 10225
–
10243, 2022, d
oi
:
10.1007/
s
13369
-
021
-
06548
-
w.
[
16]
E
. A
l
ha
z
m
i
a
nd A
. S
he
ne
a
m
e
r
, “
E
a
r
l
y pr
e
di
c
t
i
ng of
s
t
ude
nt
’
s
p
e
r
f
or
m
a
nc
e
i
n hi
ghe
r
e
duc
a
t
i
on,”
I
E
E
E
A
c
c
e
s
s
, vol
. 11, pp. 27579
–
27589, 2023, doi
:
10.1109/
A
C
C
E
S
S
.2023.3250702.
[
17]
R
.
S
ha
hz
a
d
e
t
al
.
,
“
M
ul
t
i
-
a
ge
nt
s
ys
t
e
m
f
or
s
t
ude
nt
’
s
c
ogni
t
i
ve
a
s
s
e
s
s
m
e
nt
i
n
e
-
l
e
a
r
ni
ng
e
nvi
r
onm
e
nt
,”
I
E
E
E
A
c
c
e
s
s
,
vol
.
12,
pp
.
15458
–
15467, 2024, doi
:
10.1109/
A
C
C
E
S
S
.2024.3356613.
[
18]
Z
.
X
u,
H
.
Y
ua
n,
a
nd
Q
.
L
i
u,
“
S
t
ude
nt
pe
r
f
or
m
a
nc
e
pr
e
di
c
t
i
on
ba
s
e
d
on
bl
e
nde
d
l
e
a
r
ni
ng,”
I
E
E
E
T
r
ans
ac
t
i
ons
on
E
duc
at
i
on
,
vol
.
64, no. 1, pp. 66
–
73, 2021, doi
:
10.1109/
T
E
.2020.3008751.
[
19]
P
.
J
i
a
ng
a
nd
X
.
W
a
ng,
“
P
r
e
f
e
r
e
nc
e
c
ogni
t
i
ve
di
a
gnos
i
s
f
or
s
t
ude
nt
pe
r
f
or
m
a
nc
e
pr
e
di
c
t
i
on,”
I
E
E
E
A
c
c
e
s
s
,
vol
.
8,
pp.
219775
–
219787, 2020, doi
:
10.1109/
A
C
C
E
S
S
.2020.3042775.
[
20]
N
.
A
.
B
ut
t
,
Z
.
M
a
hm
ood,
K
.
S
ha
ke
e
l
,
S
.
A
l
f
a
r
hood,
M
.
S
a
f
r
a
n,
a
nd
I
.
A
s
hr
a
f
,
“
P
e
r
f
or
m
a
nc
e
pr
e
di
c
t
i
on
of
s
t
ude
nt
s
i
n
hi
ghe
r
e
duc
a
t
i
on
us
i
ng
m
ul
t
i
-
m
ode
l
e
ns
e
m
bl
e
a
ppr
oa
c
h,”
I
E
E
E
A
c
c
e
s
s
,
vol
.
11,
pp.
136091
–
136108,
2023,
doi
:
10.1109/
A
C
C
E
S
S
.2023.3336987.
[
21]
S
.
P
ongpa
i
c
he
t
,
K
.
N
i
r
unw
i
r
oj
,
a
nd
S
.
T
ua
r
ob,
“
A
ut
om
a
t
i
c
a
s
s
e
s
s
m
e
nt
a
nd
i
de
nt
i
f
i
c
a
t
i
on
of
l
e
a
de
r
s
hi
p
i
n
c
ol
l
e
ge
s
t
ude
nt
s
,”
I
E
E
E
A
c
c
e
s
s
, vol
. 10, pp. 79041
–
79060, 2022, doi
:
10.1109/
A
C
C
E
S
S
.2022.3193935.
[
22]
J
.
F
i
gue
r
oa
-
C
a
na
s
a
nd
T
.
S
a
nc
ho
-
V
i
nue
s
a
,
“
E
a
r
l
y
pr
e
di
c
t
i
on
o
f
dr
opout
a
nd
f
i
na
l
e
xa
m
pe
r
f
or
m
a
nc
e
i
n
a
n
onl
i
ne
s
t
a
t
i
s
t
i
c
s
c
our
s
e
,”
R
e
v
i
s
t
a
I
be
r
oam
e
r
i
c
ana
de
T
e
c
nol
ogi
a
s
de
l
A
pr
e
ndi
z
aj
e
,
vol
.
15,
no.
2,
pp.
86
–
94,
2020,
doi
:
10.1109/
R
I
T
A
.2020.2987727.
[
23]
J
.
L
.
P
.
-
L
uj
a
n,
C
.
T
.
C
a
l
a
f
a
t
e
,
J
.
L
.
P
.
-
Y
a
gue
,
a
nd
J
.
C
.
C
a
no,
“
A
s
s
e
s
s
i
ng
t
he
i
m
pa
c
t
of
c
ont
i
nuous
e
v
a
l
ua
t
i
on
s
t
r
a
t
e
gi
e
s
:
t
r
a
de
of
f
be
t
w
e
e
n
s
t
ude
nt
pe
r
f
or
m
a
nc
e
a
nd
i
ns
t
r
uc
t
or
e
f
f
or
t
,”
I
E
E
E
T
r
ans
ac
t
i
ons
on
E
duc
at
i
on
,
vol
.
59,
no.
1,
pp.
17
–
23,
2016,
doi
:
10.1109/
T
E
.2015.2418740.
[
24]
A
.
S
m
i
t
h, S
.
L
.
-
M
unk,
A
.
S
he
l
t
on,
B
.
M
ot
t
, E
.
W
i
e
be
,
a
nd J
.
L
e
s
t
e
r
,
“
A
m
ul
t
i
m
oda
l
a
s
s
e
s
s
m
e
nt
f
r
a
m
e
w
or
k
f
or
i
nt
e
gr
a
t
i
ng
s
t
ude
nt
w
r
i
t
i
ng
a
nd
dr
a
w
i
ng
i
n
e
l
e
m
e
nt
a
r
y
s
c
i
e
n
c
e
l
e
a
r
ni
ng,”
I
E
E
E
T
r
ans
ac
t
i
ons
on
L
e
ar
ni
ng
T
e
c
hnol
ogi
e
s
,
vol
.
12,
no.
1,
pp.
3
–
15
,
2019, doi
:
10.1109/
T
L
T
.2018.2799871.
[
25]
T
.
C
he
n
a
nd
C
.
G
ue
s
t
r
i
n,
“
X
G
B
oos
t
:
a
s
c
a
l
a
bl
e
t
r
e
e
boos
t
i
ng
s
ys
t
e
m
,”
P
r
oc
e
e
di
ngs
of
t
he
A
C
M
SI
G
K
D
D
I
nt
e
r
nat
i
onal
C
onf
e
r
e
nc
e
on K
now
l
e
dge
D
i
s
c
ov
e
r
y
and D
at
a M
i
ni
ng
, vol
. 13
-
17
-
A
ugu, pp. 785
–
794, 2016, doi
:
10.1145/
2939672.2939785.
B
I
O
G
R
A
P
H
I
E
S
O
F
A
U
T
H
O
R
S
Mrs.
Shashirekha
Hanumanthappa
currently
working
as
Asst.
P
rofessor
in
the
Department
of
Computer
Science
and
Engineering
,
Visvesvaraya
T
echnological
University
Centre
for
Post
Graduation
Studies,
Mysuru.
She
has
completed
M.Te
ch
.
in
Computer
Scienc
e
and
Engineering
from
UBDT
College
of
Engineering
(Kuvempu
University
),
Davanagere,
Karnataka,
India
in
the
year
2008.
Her
field
of
interest
is
big
data,
a
rtificial
intelligence,
and
machine le
a
rning.
She ca
n be c
ontact
ed at
email:
shashivtu@
gmail.com.
Dr.
Chetana
Prakash
holds
Doctor
of
Philosophy
(Ph.D
.
)
in
Co
mputer
Science
and
Engineering
and
she
is
curre
ntly
working
as
Professor
in
the
Department
of
Computer
Scienc
e
and
Engineering
, Bapuji Institute of Engineering
and
Technol
ogy, Davangere. She has
teaching
experience
of
more
than
30
Years.
Her
field
of
interest
is
s
peech
signal
processing,
data mining, image processing, fuzzy tec
hniques
, IoT
, and data
analyti
cs
.
She ca
n be c
ontact
ed
at email
:
chetana.p.m
@
gmail.co
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.