I
n
t
e
r
n
at
ion
al
Jou
r
n
al
of
E
lec
t
r
ical
an
d
Com
p
u
t
e
r
E
n
gin
e
e
r
in
g
(
I
JE
CE
)
Vol.
15
,
No.
1
,
F
e
br
ua
r
y
20
25
,
pp.
645
~
653
I
S
S
N:
2088
-
8708
,
DO
I
:
10
.
11591/i
jec
e
.
v
15
i
1
.
pp
6
45
-
653
645
Jou
r
n
al
h
omepage
:
ht
tp:
//
ij
e
c
e
.
iaes
c
or
e
.
c
om
Pr
e
d
ic
t
i
n
g
ac
a
d
e
m
i
c
p
e
r
f
o
r
m
an
c
e
:
t
ow
a
r
d
a
m
od
e
l
b
ase
d
o
n
m
ac
h
i
n
e
l
e
a
r
n
i
n
g an
d
l
e
ar
n
e
r
’
s i
n
t
e
ll
ig
e
n
c
e
s
Jam
al
E
d
d
in
e
Raf
iq
1
,
Z
ak
r
an
i
Ab
d
e
lal
i
1
,
M
oh
a
m
m
e
d
Am
r
aou
y
2
,
S
ai
d
Nouh
3
,
Abd
e
l
lah
B
e
n
n
a
n
e
4
1
L
a
bor
a
to
r
y of
A
r
ti
f
ic
ia
l
I
n
te
ll
ig
e
nc
e
a
nd
C
ompl
e
x
S
ys
te
ms
E
n
gi
ne
e
r
in
g, H
a
s
s
a
n I
I
U
ni
ve
r
s
it
y, C
a
s
a
bl
a
n
c
a
, M
or
oc
c
o
2
N
a
ti
ona
l
I
ns
ti
tu
te
of
P
os
ts
a
nd
T
e
le
c
omm
uni
c
a
ti
on
s
,
M
oha
mm
e
d V
U
ni
ve
r
s
it
y,
R
a
ba
t,
M
or
oc
c
o
3
I
nf
or
ma
ti
on T
e
c
hnol
ogy a
nd M
ode
li
ng
, H
a
s
s
a
n I
I
U
ni
ve
r
s
it
y, C
a
s
a
bl
a
n
c
a
, M
or
oc
c
o
4
I
ns
pe
c
to
r
s
T
r
a
in
in
g C
e
nt
e
r
f
or
E
duc
a
ti
on
,
M
oha
mm
e
d V
U
ni
v
e
r
s
it
y, R
a
ba
t,
M
or
oc
c
o
Ar
t
icle
I
n
f
o
AB
S
T
RA
CT
A
r
ti
c
le
h
is
tor
y
:
R
e
c
e
ived
M
a
y
19,
2024
R
e
vis
e
d
Aug
20,
2024
Ac
c
e
pted
S
e
p
3,
2024
W
i
t
h
t
h
e
rap
i
d
ev
o
l
u
t
i
o
n
o
f
o
n
l
i
n
e
l
earn
i
n
g
en
v
i
r
o
n
men
t
s
,
t
h
e
ab
i
l
i
t
y
t
o
p
red
i
ct
s
t
u
d
e
n
t
s
'
acad
em
i
c
p
erfo
rma
n
ce
h
a
s
b
eco
me
cr
u
ci
al
f
o
r
p
er
s
o
n
al
i
zi
n
g
an
d
en
h
an
c
i
n
g
t
h
e
ed
u
ca
t
i
o
n
a
l
ex
p
eri
e
n
ce.
In
t
h
i
s
a
rt
i
c
l
e,
w
e
p
res
e
n
t
a
p
red
i
ct
i
v
e
mo
d
el
b
as
e
d
o
n
mach
i
n
e
l
ear
n
i
n
g
t
ech
n
i
q
u
es
,
d
e
s
i
g
n
e
d
t
o
b
e
i
n
t
eg
ra
t
ed
i
n
t
o
o
n
l
i
n
e
l
earn
i
n
g
p
l
a
t
fo
rm
s
u
s
i
n
g
t
h
e
co
mp
et
e
n
cy
-
b
as
e
d
ap
p
r
o
ach
.
T
h
i
s
mo
d
el
l
ev
era
g
e
s
feat
u
res
fr
o
m
fo
u
r
k
e
y
d
i
men
s
i
o
n
s
:
d
emo
g
rap
h
i
c,
s
o
ci
a
l
,
emo
t
i
o
n
al
,
a
n
d
co
g
n
i
t
i
v
e,
t
o
accu
ra
t
el
y
p
red
i
ct
l
earn
er
s
'
acad
emi
c
p
erfo
rma
n
ce.
W
e
d
et
a
i
l
t
h
e
me
t
h
o
d
o
l
o
g
y
fo
r
co
l
l
ec
t
i
n
g
a
n
d
p
ro
ce
s
s
i
n
g
l
earn
i
n
g
t
race
s
,
d
i
s
t
i
n
g
u
i
s
h
i
n
g
b
et
w
een
ex
p
l
i
ci
t
t
races
,
s
u
ch
as
d
emo
g
rap
h
i
c
d
at
a,
an
d
i
m
p
l
i
ci
t
t
race
s
,
w
h
i
ch
ca
p
t
u
re
l
earn
er
s
'
i
n
t
eract
i
o
n
s
an
d
b
e
h
av
i
o
r
s
d
u
ri
n
g
t
h
ei
r
l
earn
i
n
g
p
ro
ce
s
s
.
T
h
e
an
a
l
y
s
i
s
o
f
t
h
e
s
e
d
a
t
a
n
o
t
o
n
l
y
i
mp
r
o
v
e
s
t
h
e
accu
racy
o
f
p
erf
o
rman
ce
p
red
i
ct
i
o
n
s
b
u
t
al
s
o
p
ro
v
i
d
e
s
v
al
u
ab
l
e
i
n
s
i
g
h
t
s
i
n
t
o
s
k
i
l
l
acq
u
i
s
i
t
i
o
n
an
d
l
earn
er
s
'
p
ers
o
n
al
d
ev
e
l
o
p
me
n
t
.
T
h
e
res
u
l
t
s
o
f
t
h
i
s
s
t
u
d
y
d
emo
n
s
t
rat
e
t
h
e
p
o
t
en
t
i
a
l
o
f
t
h
i
s
mo
d
e
l
t
o
t
ra
n
s
f
o
rm
o
n
l
i
n
e
ed
u
cat
i
o
n
b
y
mak
i
n
g
i
t
mo
re
a
d
ap
t
i
v
e
an
d
fo
cu
s
e
d
o
n
i
n
d
i
v
i
d
u
al
l
earn
er
s
'
n
eed
s
.
K
e
y
w
o
r
d
s
:
C
ompete
nc
y
-
b
a
s
e
d
l
e
a
r
ning
Digit
a
l
lea
r
ning
L
e
a
r
ning
tr
a
c
e
s
M
a
c
hine
lea
r
ning
P
r
e
dicting
a
c
a
de
mi
c
P
e
r
f
or
manc
e
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
ce
n
s
e.
C
or
r
e
s
pon
din
g
A
u
th
or
:
J
a
mal
E
ddine
R
a
f
iq
L
a
bor
a
tor
y
of
Ar
ti
f
icia
l
I
ntelli
ge
nc
e
a
nd
C
ompl
e
x
S
ys
tems
E
nginee
r
ing,
Ha
s
s
a
n
I
I
Unive
r
s
it
y
150
Ave
nue
Nile
S
idi
Othman,
C
a
s
a
blanc
a
20670,
M
or
oc
c
o
E
mail:
jama
l
.
r
a
f
iq
-
e
tu@e
tu.
univh2c.
ma
1.
I
NT
RODU
C
T
I
ON
Digit
a
l
lea
r
ning
ha
s
r
e
volut
ion
ize
d
e
duc
a
ti
on
by
of
f
e
r
ing
ne
w
modalit
ies
,
including
onli
ne
ins
tr
uc
ti
on.
De
s
pit
e
thes
e
a
dva
nc
e
s
,
it
r
e
mains
a
c
r
uc
ial
c
ha
ll
e
nge
to
a
nti
c
ipate
a
nd
e
f
f
e
c
ti
ve
ly
im
pr
ove
lea
r
ne
r
s
'
a
c
a
de
mi
c
pe
r
f
or
manc
e
us
ing
da
ta
ge
ne
r
a
ted
by
onli
ne
lea
r
ning
platf
or
ms
.
Ac
c
ur
a
te
pr
e
d
iction
of
a
c
a
de
mi
c
pe
r
f
or
manc
e
is
e
s
s
e
nti
a
l
to
mee
t
indi
vidual
e
duc
a
ti
ona
l
ne
e
ds
a
nd
to
a
da
pt
pe
da
gogica
l
s
tr
a
tegie
s
[
1]
,
[
2
]
.
P
r
e
vious
r
e
s
e
a
r
c
h
ha
s
e
xplo
r
e
d
va
r
ious
methods
to
p
r
e
dict
a
c
a
de
mi
c
pe
r
f
or
manc
e
.
T
r
a
dit
ional
a
ppr
oa
c
he
s
,
s
uc
h
a
s
thos
e
de
s
c
r
ibed
in
s
tudi
e
s
[
3]
,
[
4]
,
[
5]
,
pr
im
a
r
i
ly
f
oc
us
on
qua
nti
tative
mea
s
ur
e
s
li
ke
tes
t
s
c
or
e
s
.
Although
thes
e
methods
ha
ve
pr
ovided
va
luable
ins
ight
s
,
they
of
ten
ove
r
look
the
br
oa
de
r
c
ontext
of
lea
r
ning,
including
knowle
dge
a
c
quis
it
ion
a
nd
s
kil
l
de
ve
lopm
e
nt
.
T
he
main
c
ontr
ibut
o
r
s
in
thi
s
f
i
e
ld
ha
ve
e
s
tablis
he
d
f
unda
menta
l
tec
hnique
s
,
but
ha
ve
not
f
ull
y
a
ddr
e
s
s
e
d
the
c
ompl
e
xit
ies
of
int
e
gr
a
ti
ng
mul
ti
modal
da
ta
in
onli
ne
lea
r
n
ing
e
nvir
onments
.
C
ur
r
e
nt
mod
e
l
s
of
ten
s
tr
ug
gle
to
pr
ovid
e
a
c
ompr
e
he
n
s
iv
e
pr
e
di
c
ti
on
of
a
c
a
de
mi
c
pe
r
f
or
ma
nc
e
by
ne
gl
e
c
ti
ng
th
e
mul
ti
dim
e
ns
i
ona
l
na
t
ur
e
of
on
li
ne
lea
r
ni
ng.
I
n
pa
r
ti
c
ul
a
r
,
ther
e
is
a
ga
p
in
th
e
u
s
e
of
da
t
a
f
r
om
va
r
iou
s
dim
e
ns
i
on
s
s
u
c
h
a
s
de
mogr
a
phi
c
,
s
oc
ial,
e
m
oti
on
a
l,
a
nd
be
ha
v
ior
a
l
f
a
c
tor
s
,
whic
h
a
r
e
c
r
uc
i
a
l
f
or
a
ho
li
s
ti
c
und
e
r
s
t
a
ndi
ng
of
lea
r
ne
r
s
'
pr
o
gr
e
s
s
.
Addr
e
s
s
in
g
thi
s
ga
p
c
ou
ld
s
igni
f
i
c
a
ntl
y
e
nh
a
nc
e
th
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2088
-
8708
I
nt
J
E
lec
&
C
omp
E
ng
,
Vol
.
15
,
No.
1
,
F
e
br
ua
r
y
20
25
:
645
-
653
646
a
c
c
ur
a
c
y
of
pr
e
dic
ti
on
s
a
nd
pr
o
vid
e
mor
e
pe
r
s
on
a
li
z
e
d
s
upp
or
t
f
or
l
e
a
r
n
e
r
s
,
th
us
f
os
t
e
r
ing
be
t
ter
a
c
a
d
e
mi
c
outcom
e
s
.
I
n
thi
s
s
tudy,
we
p
r
opos
e
the
a
c
a
de
mi
c
pe
r
f
or
ma
nc
e
pr
e
diction
model
ba
s
e
d
on
c
ompete
nc
y
-
ba
s
e
d
lea
r
ning
t
r
a
c
e
s
(
4I
-
C
B
T
)
.
Unlike
tr
a
dit
ional
met
hods
,
4I
-
C
B
T
uti
li
z
e
s
mul
ti
modal
da
ta
to
pr
ovid
e
a
mor
e
pr
e
c
is
e
a
nd
nua
nc
e
d
pr
e
diction
of
lea
r
ne
r
s
'
a
c
a
de
mi
c
pe
r
f
o
r
manc
e
.
Ou
r
model
in
tegr
a
tes
a
na
lys
is
a
c
r
os
s
f
our
dim
e
ns
ions
of
digi
tal
t
r
a
c
e
s
,
of
f
e
r
ing
a
mor
e
c
omp
r
e
he
ns
ive
a
ppr
oa
c
h
c
ompar
e
d
to
e
xis
ti
ng
s
olut
ions
.
T
he
f
oll
owing
s
e
c
ti
ons
will
de
tail
the
4I
-
C
B
T
model,
including
it
s
ke
y
c
omponents
a
nd
da
ta
c
oll
e
c
ti
on
methodology.
W
e
will
s
how
how
o
ur
model
im
p
r
ove
s
e
xis
ti
ng
a
ppr
oa
c
he
s
a
nd
dis
c
us
s
it
s
e
f
f
e
c
ti
ve
ne
s
s
in
pr
e
dicting
a
c
a
de
mi
c
pe
r
f
or
manc
e
.
Additi
ona
ll
y
,
the
r
e
leva
nc
e
o
f
ou
r
r
e
s
ult
s
f
or
e
n
ha
nc
ing
onli
ne
tea
c
hing
a
nd
pe
r
s
ona
li
z
e
d
lea
r
ning
wi
ll
be
h
ighl
ight
e
d.
2.
M
E
T
HO
D
T
his
wor
k
is
e
xplor
a
tor
y
r
e
s
e
a
r
c
h
a
bout
how
to
p
r
e
dict
a
c
a
de
mi
c
pe
r
f
or
manc
e
in
a
c
ompl
e
x
onli
ne
e
nvir
onment
.
T
he
methodology
a
dopted
by
our
s
tudy,
a
s
il
lus
tr
a
ted
in
F
igu
r
e
1
.
E
nc
ompas
s
e
s
f
our
pr
im
a
r
y
s
teps
:
li
ter
a
tur
e
r
e
view
,
model
c
onc
e
pti
on,
s
olut
ion
de
ve
lopm
e
nt
,
a
nd
r
e
leva
nc
e
e
va
luation.
F
igur
e
1.
M
e
thodol
ogy
a
dopted
2.
1.
L
it
e
r
at
u
r
e
r
e
view
an
a
lys
is
2.
1.
1.
Re
s
e
ar
c
h
q
u
e
s
t
ion
s
T
his
s
tudy
ini
ti
a
ll
y
a
im
s
to
pr
ovide
a
c
ompr
e
he
ns
ive
ove
r
view
of
r
e
s
e
a
r
c
h
publi
s
he
d
f
r
om
2019
to
2024
on
pr
e
dicting
a
c
a
de
mi
c
pe
r
f
o
r
manc
e
ba
s
e
d
on
c
ompete
nc
y
-
ba
s
e
d
lea
r
ning
tr
a
c
e
s
.
T
he
a
na
lys
is
of
thes
e
s
tudi
e
s
is
guided
by
the
f
our
ke
y
r
e
s
e
a
r
c
h
que
s
ti
ons
pr
e
s
e
nted
in
T
a
ble
1.
B
y
f
oc
us
ing
on
thes
e
que
s
ti
ons
,
the
s
tudy
s
e
e
k
s
to
highl
ight
tr
e
nds
,
g
a
ps
,
a
nd
e
mer
ging
methodologi
e
s
in
the
f
ield,
p
r
ovidi
ng
va
luable
ins
ight
s
f
or
f
utur
e
r
e
s
e
a
r
c
h.
T
a
ble
1.
R
e
s
e
a
r
c
h
que
s
ti
ons
ID
R
e
vi
e
w
que
s
ti
on
M
a
in
mot
iv
a
ti
on
R
Q
1
W
ha
t
a
r
e
t
he
ma
in
f
a
c
to
r
s
i
nf
lu
e
nc
in
g t
he
a
c
a
de
mi
c
pe
r
f
or
ma
nc
e
of
onl
in
e
l
e
a
r
ne
r
s
?
I
de
nt
if
y a
nd unde
r
s
ta
nd t
he
ke
y va
r
ia
bl
e
s
t
ha
t
a
f
f
e
c
t
th
e
s
uc
c
e
s
s
of
onl
in
e
l
e
a
r
ne
r
s
i
n or
de
r
t
o de
ve
lo
p
ta
r
ge
te
d i
nt
e
r
ve
nt
io
ns
a
nd
im
pr
ove
a
c
a
de
mi
c
out
c
ome
s
.
R
Q
2
W
ha
t
mode
ls
f
or
pr
e
di
c
ti
ng a
c
a
de
mi
c
pe
r
f
or
ma
nc
e
ha
ve
be
e
n pr
opos
e
d i
n t
he
e
xi
s
ti
ng l
it
e
r
a
tu
r
e
?
E
va
lu
a
te
t
he
c
ur
r
e
nt
a
ppr
oa
c
he
s
a
nd t
e
c
hni
que
s
f
or
pr
e
di
c
ti
ng
a
c
a
de
mi
c
pe
r
f
or
ma
nc
e
t
o i
de
nt
if
y e
f
f
e
c
ti
ve
pr
a
c
ti
c
e
s
a
nd
pot
e
nt
ia
l
ga
ps
i
n t
he
l
it
e
r
a
tu
r
e
.
R
Q
3
W
ha
t
a
r
e
t
he
a
dva
nt
a
g
e
s
a
nd l
im
it
a
ti
ons
of
t
he
di
f
f
e
r
e
nt
pr
e
di
c
ti
on mode
ls
?
A
na
ly
z
e
t
he
s
tr
e
ngt
hs
a
nd w
e
a
kn
e
s
s
e
s
of
va
r
io
us
mode
ls
t
o
in
f
or
m t
he
de
ve
lo
pme
nt
of
ne
w
, mor
e
a
c
c
ur
a
te
, a
nd r
obus
t
mode
ls
s
ui
te
d t
o t
he
c
ur
r
e
nt
ne
e
d
s
of
e
duc
a
ti
on.
R
Q
4
H
ow
a
r
e
c
ompe
te
nc
y
-
ba
s
e
d l
e
a
r
ni
ng t
r
a
c
e
s
c
ol
le
c
te
d a
nd a
na
ly
z
e
d i
n e
xi
s
ti
ng s
tu
di
e
s
, a
nd w
ha
t
is
t
he
ir
r
ol
e
i
n pr
e
di
c
ti
ng a
c
a
de
mi
c
pe
r
f
or
ma
nc
e
?
U
nde
r
s
ta
nd t
he
me
th
ods
of
c
ol
le
c
ti
ng a
nd
a
na
ly
z
in
g l
e
a
r
ni
ng
tr
a
c
e
s
t
o de
te
r
mi
ne
t
he
ir
e
f
f
e
c
ti
ve
ne
s
s
a
nd uti
li
ty
i
n i
mpr
ovi
ng
mode
ls
f
or
pr
e
di
c
ti
ng a
c
a
de
mi
c
pe
r
f
or
ma
nc
e
.
2.
1.
2.
S
e
ar
c
h
q
u
e
r
y
I
n
or
de
r
to
obtain
the
lar
ge
s
t
number
of
a
r
ti
c
les
a
ddr
e
s
s
ing
que
s
ti
ons
r
e
late
d
to
our
s
tudy
topi
c
,
we
ha
ve
us
e
d
the
ke
ywor
ds
e
xplaine
d
in
T
a
ble
2
.
T
he
s
e
ke
ywor
ds
we
r
e
c
a
r
e
f
ul
ly
s
e
lec
ted
to
c
ove
r
a
b
r
o
a
d
r
a
nge
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
E
lec
&
C
omp
E
ng
I
S
S
N:
2088
-
8708
P
r
e
dicting
ac
ade
mic
pe
r
for
manc
e
:
tow
ar
d
a
mode
l
bas
e
d
on
…
(
J
amal
E
ddine
R
afi
q
)
647
of
r
e
leva
nt
theme
s
a
nd
e
ns
ur
e
c
ompr
e
he
ns
ive
s
e
a
r
c
h
r
e
s
ult
s
.
T
his
a
ppr
oa
c
h
maximi
z
e
s
the
r
e
leva
nc
e
a
nd
s
c
ope
of
the
a
r
ti
c
les
include
d
in
the
a
na
lys
is
,
c
ont
r
i
buti
ng
to
the
ove
r
a
ll
r
igor
of
the
s
tudy.
2.
1.
3.
S
c
ient
if
ic
d
at
ab
as
e
s
Us
ing
the
pr
e
vious
ly
e
s
tablis
he
d
s
e
a
r
c
h
s
tr
ing,
we
s
e
a
r
c
he
d
thr
e
e
major
s
c
ientif
ic
da
taba
s
e
s
:
S
c
opu
s
,
W
e
b
of
S
c
ienc
e
,
a
nd
S
c
ienc
e
Dir
e
c
t.
T
his
yielde
d
a
tot
a
l
of
185
pa
pe
r
s
:
61
f
r
om
S
c
opus
,
71
f
r
om
W
e
b
of
S
c
ienc
e
,
a
nd
53
f
r
om
S
c
ienc
e
Dir
e
c
t.
T
he
inclus
io
n
of
thes
e
mul
ti
ple
da
taba
s
e
s
e
ns
ur
e
d
a
c
ompr
e
he
ns
ive
a
nd
diver
s
e
c
oll
e
c
ti
on
of
s
tudi
e
s
,
e
nha
nc
ing
the
r
obus
t
ne
s
s
of
our
li
te
r
a
tur
e
r
e
view
.
T
a
ble
2.
I
nit
ial
s
e
a
r
c
h
s
tr
ing
T
opi
c
S
e
a
r
c
h t
e
r
ms
P
r
e
di
c
ti
ng a
c
a
de
mi
c
pe
r
f
or
ma
nc
e
“
P
r
e
di
c
ti
ng
a
c
a
de
mi
c
pe
r
f
or
ma
nc
e
”
O
R
“
a
c
a
d
e
mi
c
pe
r
f
or
ma
nc
e
pr
e
di
c
ti
on
”
A
dva
nc
e
d t
e
c
hni
que
s
AND
“
ma
c
hi
ne
l
e
a
r
ni
ng
”
O
R
“
a
r
ti
f
ic
ia
l
in
te
ll
ig
e
nc
e
”
L
e
a
r
ne
r
i
nt
e
ll
ig
e
nc
e
s
a
nd
e
nvi
r
onme
nt
a
l
in
di
c
a
to
r
s
AND
“
le
a
r
ni
ng t
r
a
c
e
s
”
O
R
“
c
ogni
ti
ve
”
O
R
“
s
oc
ia
l
”
O
R
“
e
mot
i
ona
l
”
O
R
“
de
mogr
a
phi
c
”
O
nl
in
e
l
e
a
r
ni
ng
AND
“
onl
in
e
l
e
a
r
ni
ng
”
O
R
“
e
-
le
a
r
ni
ng
”
C
ompe
te
nc
y
-
ba
s
e
d l
e
a
r
ni
ng
AND
“
C
ompe
te
nc
y
-
B
a
s
e
d L
e
a
r
ni
ng
T
r
a
c
e
s
”
O
R
“
c
ompe
te
nc
y
-
ba
s
e
d e
duc
a
ti
on
”
I
nt
e
r
a
c
ti
ons
i
n l
e
a
r
ni
ng
A
N
D
“
i
nt
er
a
ct
i
ons
”
O
R
“
t
eacher
-
s
t
udent
i
nt
er
a
ct
i
ons
”
2.
1.
4.
S
t
u
d
y
s
e
lec
t
ion
I
n
thi
s
p
ivot
a
l
s
tep,
our
pr
i
mar
y
ob
jec
ti
ve
wa
s
t
o
c
hoos
e
r
e
leva
nt
s
tudi
e
s
that
s
he
d
li
ght
on
the
r
e
s
e
a
r
c
h
que
s
ti
ons
(
R
Qs
)
a
t
ha
nd.
I
n
s
e
ns
e
,
ha
v
e
a
ppli
e
d
the
inclus
ion
a
nd
e
xc
lus
ion
c
r
it
e
r
ia
ou
tl
ined
in
T
a
ble
3.
B
a
s
e
d
on
thes
e
c
r
i
ter
ia,
we
ha
ve
s
e
lec
ted
18
r
e
leva
nt
s
tudi
e
s
in
our
r
e
s
e
a
r
c
h
f
ield
f
r
om
the
ini
ti
a
ll
y
c
oll
e
c
ted
185
a
r
ti
c
les
.
T
a
ble
4
pr
e
s
e
nts
the
li
s
t
o
f
s
e
lec
ted
a
r
ti
c
les
,
c
a
tegor
ize
d
by
type
o
f
indi
c
a
tor
s
a
nd
by
a
lgor
it
hm
us
e
d
f
o
r
pr
e
dicting
a
c
a
de
mi
c
pe
r
f
o
r
manc
e
.
T
a
ble
3.
I
nc
lus
ion
a
nd
e
xc
lus
ion
c
r
it
e
r
ia
I
nc
lu
s
io
n c
r
it
e
r
ia
E
xc
lu
s
io
n c
r
it
e
r
ia
P
ubl
is
he
d 2019
–
2024
E
ngl
is
h
E
mpi
r
ic
a
l,
pr
im
a
r
y
r
e
s
e
a
r
c
h I
nde
xe
d
I
nde
xe
d i
n W
e
b of
S
c
ie
nc
e
or
S
c
opus
J
our
na
l
or
C
onf
e
r
e
nc
e
P
r
oc
e
e
di
ngs
U
s
e
c
a
s
e
of
pr
e
di
c
ti
ng a
c
a
de
mi
c
p
e
r
f
or
ma
nc
e
P
ubl
is
he
d be
f
or
e
2019
N
ot
i
n E
ngl
is
h
N
ot
pr
im
a
r
y r
e
s
e
a
r
c
h (
e
.g.
, r
e
vi
e
w
)
N
ot
in
de
xe
d
W
oS
or
S
c
opus
N
ot
a
j
our
na
l
a
r
ti
c
le
N
o I
T
of
pr
e
di
c
ti
ng a
c
a
de
mi
c
pe
r
f
or
ma
nc
e
D
upl
ic
a
te
pa
pe
r
s
P
a
pe
r
s
a
va
il
a
bl
e
onl
y a
s
a
bs
tr
a
c
t
s
or
P
ow
e
r
P
oi
nt
pr
e
s
e
nt
a
ti
ons
T
a
ble
4.
R
e
leva
nt
s
tudi
e
s
c
las
s
if
ied
by
type
of
indi
c
a
tor
s
a
nd
pr
e
dictive
a
lgor
i
thm
us
e
d
T
ype
of
in
di
c
a
to
r
s
A
lg
or
it
hms
S
tu
di
e
s
C
ogni
ti
ve
L
R
, R
F
, S
V
M
, N
B
, K
N
N
, S
V
R
,
C
N
N
, R
L
, A
N
N
, F
D
N
, D
T
, S
V
M
[
6]
,
[
7]
,
[
8]
,
[
9
]
,
[
10]
,
[
11]
,
[
12]
,
[
13]
S
oc
ia
l
S
V
R
, C
N
N
, A
N
N
, K
N
N
,
D
T
, R
F
, S
V
M
,
M
R
, D
T
, N
B
[
11]
,
[
14]
,
[
15]
,
[
16
]
,
[
17]
,
[
18]
,
[
19]
E
mot
io
na
l
C
N
N
, F
D
N
, R
F
, D
T
, K
N
N
[
14]
,
[
18]
,
[
20]
,
[
21
]
D
e
mogr
a
phi
c
D
T
,
V
S
M
,
N
B
,
K
N
N
, R
F
[
17]
,
[
8]
,
[
22]
,
[
23
]
2.
2.
Conce
p
t
io
n
an
d
m
od
e
li
z
a
t
ion
T
he
a
na
lys
is
of
the
s
tudi
e
s
s
e
lec
ted
in
the
pr
e
vious
s
tage
a
ll
owe
d
us
to
pr
opos
e
a
model
f
or
pr
e
dicting
a
c
a
de
mi
c
pe
r
f
or
manc
e
in
li
ne
with
the
pr
inciples
of
e
xplor
a
ti
on
theor
y
a
nd
the
f
ou
r
c
a
te
gor
ies
of
lea
r
ning
tr
a
c
e
s
:
s
oc
ial,
c
ognit
ive,
e
mot
ional,
a
n
d
de
mogr
a
phic
d
im
e
ns
ions
.
T
his
model
int
e
gr
a
t
e
s
thes
e
dim
e
ns
ions
to
pr
ovide
a
mor
e
holi
s
ti
c
a
nd
a
c
c
ur
a
te
pr
e
diction
of
lea
r
ne
r
s
'
a
c
a
de
mi
c
s
uc
c
e
s
s
.
T
he
de
tailed
de
s
c
r
ipt
ion
a
nd
a
na
lys
is
of
the
pr
opos
e
d
model
will
be
pr
e
s
e
nted
in
the
a
na
lys
is
a
nd
dis
c
us
s
ion
s
e
c
ti
on
,
of
f
e
r
ing
f
ur
ther
ins
ight
s
int
o
it
s
s
tr
uc
tur
e
a
nd
e
f
f
e
c
ti
ve
ne
s
s
.
2.
3.
S
olu
t
ion
d
e
ve
lop
m
e
n
t
T
he
hybr
id
pr
e
dictive
model
we
de
ve
loped
c
ombi
ne
s
mul
ti
ple
r
e
gr
e
s
s
ion
(
M
L
)
,
a
r
ti
f
icia
l
ne
ur
a
l
ne
twor
ks
(
AN
N)
,
a
nd
r
a
ndom
f
o
r
e
s
t
(
R
F
)
to
maximi
z
e
the
a
c
c
ur
a
c
y
of
a
c
a
de
mi
c
pe
r
f
or
manc
e
pr
e
dictions
.
T
his
model
ha
s
be
e
n
e
nc
a
ps
ulate
d
in
a
plugi
n
s
pe
c
if
ica
ll
y
de
s
igned
f
or
the
M
oodle
onli
ne
lea
r
ning
platf
or
m.
T
he
int
e
gr
a
ti
on
of
th
is
plugi
n
int
o
M
oodle
wa
s
a
c
hieve
d
us
ing
the
platf
or
m's
API
s
a
nd
pr
og
r
a
mm
ing
int
e
r
f
a
c
e
s
,
a
ll
owing
s
e
a
ml
e
s
s
int
e
r
a
c
ti
on
be
twe
e
n
the
pr
e
dictive
model
a
nd
c
ou
r
s
e
da
ta.
S
pe
c
if
i
c
a
ll
y,
the
plugi
n
c
a
n
r
e
tr
ieve
lea
r
ne
r
da
ta,
s
uc
h
a
s
their
s
c
or
e
s
,
f
or
um
pa
r
ti
c
ipation
,
a
nd
a
s
s
ignm
e
nt
s
ub
mi
s
s
ion
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2088
-
8708
I
nt
J
E
lec
&
C
omp
E
ng
,
Vol
.
15
,
No.
1
,
F
e
br
ua
r
y
20
25
:
645
-
653
648
a
c
ti
vit
ies
,
to
pr
oc
e
s
s
a
nd
p
r
ovide
r
e
a
l
-
ti
me
pr
e
dict
ions
of
their
f
utu
r
e
pe
r
f
or
manc
e
.
T
he
p
r
e
diction
r
e
s
ult
s
a
r
e
then
a
c
c
e
s
s
ibl
e
to
ins
tr
uc
tor
s
via
the
M
oodle
da
s
hboa
r
d,
ther
e
by
f
a
c
il
it
a
ti
ng
pe
da
gogica
l
de
c
is
ion
-
making
a
nd
pe
r
s
ona
li
z
e
d
lea
r
ne
r
s
uppor
t
.
T
his
int
e
g
r
a
ti
o
n
a
ls
o
e
ns
ur
e
s
c
onti
nuous
upda
ti
ng
o
f
p
r
e
diction
s
a
s
ne
w
da
ta
be
c
omes
a
va
il
a
ble,
thus
maintaining
the
r
e
lev
a
nc
e
a
nd
a
c
c
ur
a
c
y
of
the
a
na
lys
e
s
pr
ovided
by
the
model.
2.
4.
Re
levance
e
valu
at
io
n
Dur
ing
the
c
ode
de
ve
lopm
e
nt
a
nd
thr
oughout
the
va
li
da
ti
on
pha
s
e
s
,
tes
t
s
we
r
e
s
c
h
e
duled
to
e
ns
ur
e
pr
oduc
t
qua
li
ty
c
ontr
o
l.
I
n
thi
s
r
e
ga
r
d
,
we
a
im
e
d
to
a
s
s
e
s
s
the
pe
da
gogica
l
a
nd
tec
hnica
l
r
e
leva
nc
e
of
the
pr
opos
e
d
s
olut
ion.
T
he
a
na
lys
is
a
nd
dis
c
us
s
ion
s
e
c
ti
on
highl
ight
s
the
pe
da
gogica
l
qua
li
ty
of
our
mod
e
l,
while
the
tec
hnica
l
r
e
leva
nc
e
will
be
a
dd
r
e
s
s
e
d
in
a
nother
pa
pe
r
.
2.
5.
E
xp
loi
t
a
t
ion
an
d
m
ain
t
e
n
a
n
c
e
T
his
pha
s
e
a
ll
owe
d
us
to
e
f
f
e
c
ti
ve
ly
moni
to
r
the
ope
r
a
ti
on
o
f
our
pr
e
dictive
model
ba
s
e
d
on
the
tr
a
c
e
s
c
oll
e
c
ted
f
r
om
int
e
r
a
c
ti
ons
o
f
lea
r
ne
r
s
with
the
c
ou
r
s
e
their
tea
c
he
r
s
de
ployed
on
the
M
oodle
onli
ne
platf
or
m.
C
ons
e
que
ntl
y,
we
we
r
e
a
ble
to
c
or
r
e
c
t
de
ve
lopm
e
nt
bugs
,
f
ine
-
tune
it
s
ope
r
a
ti
ons
,
a
n
d
a
djus
t
pa
r
a
mete
r
s
.
Ongoing
us
e
o
f
the
plugi
n
a
ls
o
in
volved
r
e
gular
pe
r
f
or
manc
e
moni
tor
ing
,
ga
ther
i
ng
us
e
r
f
e
e
dba
c
k,
a
nd
c
onti
nuous
ly
im
pleme
nti
ng
e
nha
nc
e
ments
to
e
ns
ur
e
it
s
e
f
f
e
c
ti
ve
ne
s
s
a
nd
r
obus
tnes
s
.
3.
RE
S
UL
T
S
AN
D
DI
S
CU
S
S
I
ON
T
h
e
a
na
lys
is
of
p
r
e
vi
ous
s
t
ud
ies
,
pa
r
ti
c
u
la
r
ly
th
a
t
o
f
V
i
ma
r
s
ha
e
t
al
.
[
8
]
,
u
nd
e
r
s
c
o
r
e
s
t
he
c
o
mp
le
xi
t
y
o
f
h
u
man
in
te
ll
i
ge
n
c
e
a
nd
it
s
di
r
e
c
t
im
pa
c
t
o
n
a
c
a
de
mi
c
a
c
hi
e
v
e
m
e
n
t
,
e
s
p
e
c
ial
l
y
in
th
e
c
o
nt
e
x
t
o
f
o
n
li
ne
le
a
r
n
in
g
.
T
h
e
s
e
w
o
r
ks
c
on
ve
r
ge
o
n
t
he
r
e
c
og
ni
t
io
n
o
f
t
he
i
m
po
r
tan
c
e
n
ot
on
ly
o
f
c
o
gn
it
i
ve
d
im
e
ns
io
ns
b
ut
a
ls
o
o
f
s
oc
i
o
-
e
mo
ti
on
a
l
a
nd
de
mo
gr
a
p
hi
c
f
a
c
to
r
s
.
T
he
s
tu
d
ies
i
n
[
24
]
ha
v
e
e
l
uc
id
a
te
d
t
he
e
vo
lu
t
io
n
o
f
i
nte
l
li
ge
n
c
e
c
ons
t
r
u
c
ts
,
e
m
ph
a
s
i
z
i
ng
t
he
pl
u
r
a
l
i
ty
o
f
i
n
te
ll
ig
e
nc
e
f
o
r
ms
a
n
d
the
i
r
r
o
le
i
n
p
r
e
d
ic
ti
ng
a
c
a
de
mi
c
a
c
h
ie
ve
me
nt
.
M
or
e
s
p
e
c
i
f
ic
a
l
ly
,
s
tu
d
ies
[
2
5
]
a
nd
[
2
6
]
h
a
ve
de
mon
s
t
r
a
te
d
t
he
c
r
i
ti
c
a
l
i
mp
o
r
ta
nc
e
o
f
e
mo
t
io
na
l
i
nt
e
l
li
ge
nc
e
a
n
d
s
oc
i
a
l
s
up
po
r
t
f
o
r
the
a
c
a
d
e
m
ic
s
u
c
c
e
s
s
of
s
e
c
o
nd
a
r
y
s
c
ho
o
l
s
tu
de
nts
,
the
r
e
b
y
c
o
r
r
o
bo
r
a
t
in
g
th
e
f
in
di
ngs
o
f
[
24
]
.
T
h
e
a
n
a
l
ys
i
s
o
f
o
nl
in
e
le
a
r
n
in
g
t
r
a
c
e
s
[
2
7]
r
e
ve
a
ls
a
s
ig
ni
f
ica
n
t
po
te
nt
ia
l
f
o
r
p
r
e
d
ic
ti
ng
a
c
a
d
e
m
ic
pe
r
f
o
r
ma
nc
e
.
B
y
c
o
mb
in
in
g
c
o
gn
it
iv
e
mea
s
u
r
e
s
a
n
d
in
no
va
ti
ve
pe
da
go
gi
c
a
l
s
tr
a
t
e
g
ies
[
28
]
,
s
u
c
h
a
s
c
o
ll
a
b
o
r
a
t
i
ve
le
a
r
n
i
ng
,
we
c
a
n
r
e
f
ine
ou
r
p
r
e
d
ic
t
io
n
m
ode
ls
.
O
u
r
m
od
e
l
in
F
ig
u
r
e
2
i
nt
e
g
r
a
tes
a
m
ul
ti
di
me
ns
io
na
l
a
p
p
r
oa
c
h
,
dyn
a
m
ic
a
l
ly
a
na
ly
z
i
ng
le
a
r
ne
r
s
'
s
ki
ll
d
e
ve
lo
p
men
t
in
a
r
ic
h
a
nd
in
te
r
a
c
t
i
ve
lea
r
ni
ng
e
nv
ir
on
me
n
t
.
T
h
is
a
p
pr
oa
c
h
a
l
lows
f
o
r
a
b
e
t
te
r
un
de
r
s
t
a
n
di
ng
o
f
t
he
f
a
c
t
or
s
in
f
lu
e
n
c
i
ng
on
l
in
e
s
uc
c
e
s
s
.
F
i
r
s
tl
y
,
w
e
c
o
ll
e
c
t
l
e
a
r
n
e
r
s
'
l
e
a
r
n
i
ng
t
r
a
c
e
s
,
i
nc
l
ud
in
g
b
ot
h
e
x
pl
ic
i
t
t
r
a
c
e
s
(
r
e
v
e
a
l
i
ng
c
og
ni
t
ive
,
s
oc
i
a
l
,
a
n
d
e
m
ot
i
ona
l
p
r
oc
e
s
s
e
s
)
a
n
d
i
mp
l
ic
it
tr
a
c
e
s
(
s
u
c
h
a
s
d
e
m
og
r
a
p
hic
da
ta
)
.
T
h
is
he
t
e
r
o
ge
n
e
o
us
da
ta
is
th
e
n
p
r
oc
e
s
s
e
d
t
o
f
e
e
d
a
h
yb
r
id
p
r
e
d
ic
ti
on
m
ode
l,
t
he
r
e
by
e
na
bl
in
g
t
he
e
s
t
im
a
t
io
n
o
f
e
a
c
h
l
e
a
r
n
e
r
's
a
c
a
d
e
m
ic
pe
r
f
or
ma
nc
e
.
F
igur
e
2.
Ac
a
de
mi
c
pe
r
f
o
r
manc
e
pr
e
diction
model
ba
s
e
d
on
c
ompete
nc
y
-
ba
s
e
d
lea
r
ning
tr
a
c
e
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
E
lec
&
C
omp
E
ng
I
S
S
N:
2088
-
8708
P
r
e
dicting
ac
ade
mic
pe
r
for
manc
e
:
tow
ar
d
a
mode
l
bas
e
d
on
…
(
J
amal
E
ddine
R
afi
q
)
649
3.
1.
Com
p
e
t
e
n
c
y
-
b
as
e
d
lear
n
in
g
as
p
e
d
agogical
f
r
am
e
wor
k
Ac
c
or
ding
to
W
e
iner
t
[
29]
,
c
ompete
nc
e
is
a
n
i
ntegr
a
ted
c
ombi
na
ti
on
of
knowle
dge
,
s
kil
ls
,
a
nd
mot
ivations
,
a
da
pted
to
s
it
ua
ti
ons
.
De
L
a
nds
he
e
r
e
e
mphas
ize
s
that
it
goe
s
b
e
yond
the
is
olate
d
a
ppli
c
a
ti
on
of
a
bil
it
ies
[
30]
.
C
ompete
nc
y
-
ba
s
e
d
lea
r
ning,
whic
h
f
oc
us
e
s
on
pr
a
c
ti
c
a
l
a
ppli
c
a
ti
on
a
nd
pr
oblem
-
s
olvi
ng,
pr
omot
e
s
a
de
e
pe
r
unde
r
s
tanding
a
nd
be
tt
e
r
p
r
e
pa
r
a
ti
on
f
or
r
e
a
l
-
wor
ld
c
ha
ll
e
nge
s
[
31]
.
I
t
e
n
c
our
a
ge
s
a
utonom
y,
r
e
s
pons
ibi
li
ty,
a
nd
the
de
ve
lopm
e
nt
of
t
r
a
ns
ve
r
s
a
l
s
kil
ls
s
uc
h
a
s
c
r
i
ti
c
a
l
th
inki
ng
a
nd
c
oll
a
bor
a
ti
on
[
32]
.
Online
lea
r
n
ing,
in
th
is
pe
r
s
pe
c
ti
ve
,
of
f
e
r
s
a
f
lexible
a
nd
pe
r
s
ona
li
z
e
d
platf
or
m,
a
ll
owing
le
a
r
ne
r
s
to
pr
ogr
e
s
s
a
t
their
own
pa
c
e
a
nd
de
ve
lop
the
ne
c
e
s
s
a
r
y
s
kil
ls
[
33]
.
3.
2.
Com
p
e
t
e
n
c
ies
d
e
ve
lop
m
e
n
t
p
r
oc
e
s
s
T
he
de
ve
lopm
e
nt
of
a
c
ompete
nc
y,
ini
ti
a
ll
y
in
a
n
e
mbr
yonic
s
tate
(
C
0)
,
is
a
dyna
mi
c
pr
oc
e
s
s
inf
luenc
e
d
by
a
c
on
f
luenc
e
of
f
a
c
tor
s
.
R
e
s
our
c
e
s
,
e
nc
ompas
s
ing
both
ha
r
d
a
nd
s
of
t
s
kil
ls
,
s
e
r
ve
a
s
the
be
dr
oc
k
f
or
thi
s
de
ve
lopm
e
nt.
T
he
tut
or
plays
a
pivot
a
l
r
ole
in
f
a
c
il
it
a
ti
ng
lea
r
ne
r
pr
og
r
e
s
s
,
a
da
pti
ng
ins
tr
uc
ti
on
ba
s
e
d
on
the
a
na
lys
is
of
lea
r
ning
tr
a
c
e
s
.
C
ons
e
que
ntl
y,
the
c
ompete
nc
y
e
volves
to
wa
r
ds
a
de
ve
loped
s
tate
(
DC
)
,
a
s
e
videnc
e
d
by
a
c
a
de
mi
c
p
e
r
f
or
manc
e
,
with
in
a
f
r
a
mew
or
k
of
a
da
pti
ve
s
ys
tems
.
3.
3.
Ac
ad
e
m
ic
p
e
r
f
or
m
an
c
e
Ac
a
de
mi
c
pe
r
f
or
manc
e
,
of
ten
ope
r
a
ti
ona
li
z
e
d
a
s
a
pr
oxy
f
o
r
c
ompete
nc
y,
is
de
r
ived
f
r
om
a
mul
ti
f
a
c
tor
ial
a
s
s
e
s
s
ment
of
s
tudent
outcome
s
[
34]
.
I
t
e
nc
ompas
s
e
s
both
qua
nti
tative
mea
s
ur
e
s
(
gr
a
de
s
,
e
xa
mi
na
ti
ons
)
a
nd
qua
li
tative
indi
c
a
tor
s
s
uc
h
a
s
pa
r
ti
c
ipation
a
nd
qua
li
ty
of
wor
k.
T
his
mul
ti
f
a
c
e
ted
a
s
s
e
s
s
ment
e
n
a
bles
the
e
v
a
luation
of
a
s
tudent's
c
a
pa
c
it
y
to
mobi
li
z
e
the
r
e
quis
it
e
knowle
dge
a
nd
s
kil
ls
withi
n
their
s
pe
c
if
ic
domain
of
s
tudy
[
35
]
.
3.
4.
P
r
e
d
ic
t
ion
algori
t
h
m
s
M
a
c
hine
lea
r
ning
pr
ovides
a
diver
s
e
r
a
nge
of
me
thodol
ogies
f
or
pr
e
dicting
a
c
a
de
mi
c
pe
r
f
o
r
manc
e
[
36]
,
[
37
]
.
As
pe
r
the
r
e
s
e
a
r
c
h
c
onduc
ted
by
Al
br
e
iki
e
t
al
.
[
38]
,
M
ode
ls
including
r
a
ndom
f
o
r
e
s
ts
(
R
F
)
,
a
r
ti
f
icia
l
ne
ur
a
l
ne
twor
ks
(
AN
N)
,
a
nd
mul
ti
p
le
r
e
gr
e
s
s
ion
(
M
R
)
a
r
e
f
r
e
que
ntl
y
uti
li
z
e
d.
T
he
s
e
models
leve
r
a
ge
s
ophis
ti
c
a
ted
a
lgor
it
hms
to
a
na
lyze
e
xtens
ive
da
tas
e
t
s
a
nd
unc
ove
r
pa
tt
e
r
ns
a
s
s
oc
ia
ted
with
a
c
a
de
mi
c
a
c
hieve
ment.
T
he
M
R
a
lgor
it
hm
us
e
s
t
he
f
or
mul
a
=
0
+
1
1
+
2
2
+
.
.
.
+
+
to
e
va
luate
the
in
f
luenc
e
of
e
a
c
h
indepe
nde
nt
va
r
i
a
ble
on
the
de
pe
nde
nt
va
r
iable
.
R
a
ndom
f
or
e
s
t
pr
e
dicts
a
c
a
de
mi
c
pe
r
f
or
manc
e
by
a
ve
r
a
ging
the
pr
e
diction
s
of
mul
ti
ple
de
c
is
ion
tr
e
e
s
a
c
c
or
ding
to
̂
=
1
∑
(
)
=
1
.
Ar
ti
f
icia
l
ne
ur
a
l
ne
twor
ks
(
AN
N)
us
e
the
f
or
m
ula
̂
=
(
∑
.
+
)
=
1
to
tr
a
ns
f
or
m
we
ight
e
d
input
f
e
a
tur
e
s
thr
ough
a
n
a
c
ti
va
ti
on
f
unc
ti
on
to
obtain
th
e
f
inal
p
r
e
diction.
3.
5.
T
h
e
4I
I
n
thi
s
s
e
c
ti
on,
we
e
xplor
e
the
f
our
types
of
indi
c
a
tor
s
(
4I
)
that
ha
ve
a
s
igni
f
ica
nt
im
pa
c
t
on
onli
ne
a
c
a
de
mi
c
pe
r
f
or
manc
e
.
T
he
s
e
indi
c
a
tor
s
a
r
e
de
r
ived
f
r
om
e
xpli
c
it
tr
a
c
e
s
(
de
mogr
a
phic
indi
c
a
t
or
s
)
a
nd
im
pli
c
it
one
s
(
e
mot
ional,
s
oc
ial,
a
nd
c
ognit
iv
e
int
e
ll
igenc
e
)
.
C
ognit
ive
int
e
ll
igenc
e
is
e
s
s
e
nti
a
l
f
o
r
unde
r
s
tanding
c
onc
e
pts
,
s
olvi
ng
pr
oblems
,
a
nd
a
c
quir
ing
ne
w
knowle
dge
thr
ough
d
igi
tal
r
e
s
our
c
e
s
[
39]
.
S
im
il
a
r
ly,
s
oc
ial
int
e
ll
igenc
e
is
ke
y
f
or
int
e
r
a
c
ti
ng
with
pe
e
r
s
a
nd
tea
c
he
r
s
via
onli
ne
tool
s
,
f
a
c
il
it
a
ti
ng
c
oll
a
bor
a
ti
on
a
nd
c
oope
r
a
ti
ve
lea
r
ning
[
40
]
.
E
mot
i
ona
l
int
e
ll
igenc
e
is
c
r
uc
ial
onli
ne
,
he
lpi
ng
lea
r
ne
r
s
mana
ge
their
e
mot
ions
in
the
f
a
c
e
o
f
e
duc
a
ti
ona
l
c
ha
ll
e
ng
e
s
[
41]
.
F
inally
,
de
mog
r
a
phic
c
ha
r
a
c
ter
is
ti
c
s
play
a
c
r
uc
ial
r
ole
in
lea
r
ne
r
s
'
a
c
a
de
mi
c
pe
r
f
or
manc
e
,
dir
e
c
tl
y
inf
luenc
ing
their
s
uc
c
e
s
s
in
onli
ne
lea
r
ning
[
42]
.
B
y
c
ombi
ning
thes
e
f
our
types
of
indi
c
a
tor
s
,
our
mod
e
l
e
nha
nc
e
s
the
a
c
c
ur
a
c
y
of
onli
ne
a
c
a
de
mi
c
pe
r
f
or
manc
e
pr
e
dictions
,
e
na
bli
ng
mo
r
e
pe
r
s
ona
li
z
e
d
a
nd
tar
ge
t
e
d
int
e
r
ve
nti
ons
to
s
uppor
t
e
a
c
h
lea
r
ne
r
.
3.
6.
Digit
a
l
lear
n
in
g
t
r
ac
e
s
A
digi
tal
lea
r
ning
tr
a
c
e
,
a
s
de
f
ined
by
[
43]
,
is
a
s
e
que
nc
e
of
a
c
ti
ons
pe
r
f
or
med
by
a
lea
r
ne
r
withi
n
a
c
omput
e
r
-
ba
s
e
d
lea
r
ning
e
nvir
onment
(
C
B
L
E
)
.
A
f
ter
c
lea
ning
a
nd
tr
a
ns
f
or
mation
,
thes
e
tr
a
c
e
s
a
ll
ow
f
or
the
e
xtr
a
c
ti
on
of
ke
y
indi
c
a
tor
s
that
c
a
n
be
us
e
d
to
pe
r
s
ona
li
z
e
the
lea
r
ning
e
xpe
r
ienc
e
.
F
igu
r
e
3
il
lus
tr
a
tes
how
thes
e
indi
c
a
tor
s
a
r
e
uti
li
z
e
d
to
tailor
e
duc
a
ti
ona
l
in
ter
ve
nti
ons
ba
s
e
d
on
indi
vidual
lea
r
ne
r
be
ha
vior
s
.
T
he
pr
oc
e
s
s
ing
of
onli
ne
lea
r
ning
tr
a
c
e
s
f
oll
ow
s
a
r
igo
r
ous
mul
t
i
-
s
tep
pr
oc
e
s
s
.
F
ir
s
tl
y,
da
ta
is
c
oll
e
c
ted
f
r
om
lea
r
ne
r
int
e
r
a
c
ti
ons
with
the
lea
r
ning
platf
o
r
m,
including
both
e
xpli
c
it
a
c
ti
ons
(
logi
ns
,
s
ubmi
s
s
ion
s
)
a
nd
im
pli
c
it
a
c
ti
ons
(
ti
me
s
pe
nt
o
n
tas
ks
,
na
vigation
pa
ths
)
.
T
his
da
ta
is
then
c
lea
ne
d
a
nd
s
tr
uc
tur
e
d
to
f
a
c
il
it
a
te
a
na
lys
is
.
Onc
e
pr
e
pa
r
e
d
,
the
da
ta
is
a
na
lyze
d
us
ing
s
tatis
ti
c
a
l
tool
s
a
nd
mac
hine
lea
r
ning
tec
hniques
to
identif
y
pa
tt
e
r
ns
a
nd
t
r
e
nds
in
lea
r
ning
be
ha
vior
s
.
T
he
r
e
s
ult
s
o
f
thi
s
a
na
lys
is
a
r
e
s
umm
a
r
ize
d
in
r
e
por
ts
that
a
s
s
e
s
s
lea
r
ne
r
s
'
pr
ogr
e
s
s
,
identif
y
their
s
tr
e
ngths
a
nd
we
a
kne
s
s
e
s
,
a
nd
highl
ight
a
r
e
a
s
f
or
im
pr
ove
ment
.
T
his
in
f
or
mation
s
e
r
ve
s
a
s
the
ba
s
is
f
or
pe
r
s
ona
li
z
ing
lea
r
ning
pa
ths
by
of
f
e
r
ing
a
c
ti
vit
ies
tailor
e
d
to
indi
vidual
lea
r
ne
r
ne
e
ds
a
nd
a
djus
ti
ng
pe
da
gogica
l
s
tr
a
tegie
s
a
c
c
or
dingl
y.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2088
-
8708
I
nt
J
E
lec
&
C
omp
E
ng
,
Vol
.
15
,
No.
1
,
F
e
br
ua
r
y
20
25
:
645
-
653
650
F
igur
e
3.
L
if
e
c
yc
le
of
lea
r
ning
t
r
a
c
e
s
3.
7.
Ac
ad
e
m
ic
p
e
r
f
or
m
an
c
e
p
r
e
d
ict
io
n
ap
p
r
oac
h
I
n
thi
s
s
tudy
,
we
e
xplor
e
the
f
a
c
tor
s
inf
luenc
i
ng
onli
ne
a
c
a
de
mi
c
pe
r
f
or
manc
e
by
int
e
gr
a
ti
ng
indi
c
a
tor
s
de
r
ived
f
r
om
lea
r
ne
r
s
'
e
xpli
c
it
a
nd
i
mpl
icit
t
r
a
c
e
s
.
W
e
c
ons
ider
a
s
e
t
of
va
r
iable
s
,
including
pr
e
vious
a
c
a
de
mi
c
r
e
s
ult
s
,
e
nga
ge
ment
in
lea
r
ning
a
c
ti
vit
ies
(
dis
c
us
s
ion
f
or
ums
,
onl
ine
r
e
s
our
c
e
s
)
,
de
mogr
a
phic
c
ha
r
a
c
ter
is
ti
c
s
,
a
nd
dim
e
ns
ions
r
e
late
d
to
the
thr
e
e
int
e
ll
igenc
e
s
.
T
his
c
ompr
e
he
ns
ive
a
ppr
oa
c
h
a
ll
ows
us
to
a
na
lyze
the
mul
ti
f
a
c
e
ted
na
tur
e
of
onli
ne
lea
r
ning
a
nd
identi
f
y
the
ke
y
e
leme
nts
th
a
t
im
pa
c
t
lea
r
ne
r
s
'
s
uc
c
e
s
s
.
T
o
a
s
s
e
s
s
c
ognit
ive
int
e
ll
igenc
e
in
onli
ne
lea
r
ni
ng,
we
c
a
n
a
na
lyze
lea
r
ne
r
s
'
c
ognit
ive
a
c
ti
vit
ies
.
P
r
oblem
s
olvi
ng,
knowle
dge
a
c
quis
it
ion,
a
nd
pa
r
ti
c
ipation
in
on
li
ne
dis
c
us
s
ions
a
r
e
ke
y
in
dica
tor
s
.
Onditi
e
t
al
.
[
44]
s
howe
d
that
a
na
lyzing
f
o
r
um
c
ontent
c
a
n
e
va
luate
lea
r
ning
outcome
s
.
T
e
xt
a
na
lys
is
methods
c
a
n
mea
s
ur
e
how
we
ll
lea
r
ne
r
s
'
c
ontr
ibut
ions
a
li
gn
with
lea
r
ning
objec
ti
ve
s
.
S
oc
ial
int
e
ll
igenc
e
,
c
r
uc
ial
f
or
onl
ine
c
oll
a
bor
a
ti
on
[
45]
,
is
mea
s
ur
e
d
by
the
s
oc
ial
int
e
ll
igenc
e
s
c
or
e
(
S
I
S
)
.
T
his
s
c
or
e
i
ntegr
a
tes
the
number
of
pos
ts
(
NPD
)
,
r
e
pli
e
s
(
NPR
)
,
a
n
d
view
s
(
NV
)
.
T
he
f
or
mul
a
=
(
+
)
×
a
s
s
e
s
s
e
s
a
lea
r
ne
r
's
s
oc
ial
e
nga
ge
ment.
T
o
e
va
lu
a
te
e
mot
ional
int
e
ll
igenc
e
,
e
s
s
e
nti
a
l
f
or
on
li
ne
m
oti
va
ti
on
[
46]
,
we
a
na
lyze
e
mot
ions
e
xp
r
e
s
s
e
d
in
mes
s
a
ge
s
.
W
e
us
e
the
b
idi
r
e
c
ti
ona
l
e
nc
ode
r
r
e
pr
e
s
e
ntations
f
r
om
tr
a
ns
f
or
mer
s
(
B
E
R
T
)
model
,
a
s
in
R
a
f
iq
e
t
al
.
[
47]
,
f
or
s
e
nti
ment
a
na
lys
is
.
M
e
s
s
a
ge
s
a
r
e
pr
e
pr
oc
e
s
s
e
d.
M
e
s
s
a
ge
s
a
r
e
pr
e
pr
oc
e
s
s
e
d
be
f
or
e
a
na
lys
is
.
T
o
c
a
lcula
te
the
de
mogr
a
phic
s
c
or
e
,
we
in
tegr
a
te
s
e
ve
r
a
l
s
igni
f
ica
nt
e
nvir
onmenta
l
c
ha
r
a
c
ter
is
ti
c
s
:
ge
ogr
a
phic
r
e
gion,
ne
ighbo
r
hood
pove
r
ty
leve
l,
pr
ior
e
duc
a
ti
on,
a
ge
,
ge
nde
r
,
a
nd
dis
a
bil
it
y
s
tatus
.
T
he
s
e
indi
c
a
tor
s
a
r
e
c
ombi
ne
d
to
a
s
s
e
s
s
the
ove
r
a
ll
im
pa
c
t
of
the
s
oc
io
-
e
c
onomi
c
e
nvir
onment
on
lea
r
ne
r
s
'
a
c
a
de
mi
c
pe
r
f
o
r
manc
e
.
T
he
pr
opos
e
d
f
o
r
mul
a
is
:
ℎ
=
1
×
+
2
×
+
3
×
+
4
×
+
5
×
+
6
×
T
his
a
ppr
oa
c
h
is
gr
ounde
d
in
r
e
c
e
nt
r
e
s
e
a
r
c
h
in
dica
ti
ng
that
thes
e
c
ha
r
a
c
ter
is
ti
c
s
s
igni
f
ica
ntl
y
inf
luenc
e
e
duc
a
ti
ona
l
oppor
tuni
ti
e
s
a
nd
r
e
s
our
c
e
s
,
ther
e
by
i
mpac
ti
ng
a
c
a
de
mi
c
pe
r
f
or
manc
e
[
48
]
.
F
inally
,
the
lea
r
ne
r
's
ove
r
a
ll
s
c
or
e
is
c
a
lcula
ted
us
ing
the
we
ight
e
d
a
ve
r
a
ge
of
the
s
c
or
e
s
of
the
5
I
.
E
a
c
h
s
c
or
e
is
we
ight
e
d
a
c
c
or
ding
to
it
s
r
e
lative
im
po
r
tanc
e
in
the
c
ontex
t
of
onli
ne
lea
r
ning
.
T
his
ove
r
a
ll
s
c
or
e
is
us
e
d
to
pr
e
dict
lea
r
ne
r
pe
r
f
o
r
manc
e
.
=
1
+
2
+
3
+
4
ℎ
T
o
e
nr
ich
ou
r
model,
we
s
uppleme
nt
lea
r
ning
tr
a
c
e
s
with
lea
r
ne
r
s
’
de
mogr
a
phic
da
ta.
W
e
c
oll
e
c
t
in
f
or
mation
on
their
a
c
a
de
mi
c
ba
c
kgr
ound,
int
e
r
a
c
ti
ons
,
e
mot
i
ona
l
s
tate
s
,
s
ubmi
tt
e
d
a
c
ti
vit
ies
,
s
uc
c
e
s
s
e
s
/f
a
il
ur
e
s
,
a
s
we
ll
a
s
other
s
pe
c
if
ic
f
a
c
tor
s
s
uc
h
a
s
the
r
e
s
our
c
e
s
c
ons
ult
e
d,
c
onne
c
ti
on
dur
a
ti
on,
a
nd
lea
r
ning
p
r
e
f
e
r
e
n
c
e
s
.
Our
onli
ne
a
c
a
de
mi
c
pe
r
f
or
manc
e
pr
e
diction
model
i
s
gr
ounde
d
in
thi
s
s
ys
temic
a
ppr
oa
c
h
that
int
e
gr
a
tes
the
c
ognit
ive,
s
oc
ial,
e
mot
ional,
a
nd
de
mogr
a
phic
in
dica
tor
s
.
I
n
ter
ms
of
the
s
oc
ial
di
mens
ion,
B
ona
f
ini
e
t
al
.
[
49]
de
mons
tr
a
ted
that
e
nga
ge
ment
in
dis
c
us
s
ion
f
or
ums
wa
s
a
s
s
oc
iate
d
with
higher
s
c
or
e
s
a
nd
gr
e
a
ter
r
e
tention
in
mas
s
ive
ope
n
onli
ne
c
our
s
e
s
(
M
OO
C
s
)
.
Additi
ona
ll
y,
the
da
ta
a
na
lyze
d
in
r
e
s
e
a
r
c
h
[
50]
include
d
thr
e
e
types
of
a
c
ti
vit
ies
(
videos
wa
tche
d,
a
s
s
ignm
e
nts
s
ubmi
tt
e
d,
a
nd
mes
s
a
ge
s
wr
it
ten)
a
s
indi
c
a
tor
s
of
lea
r
ne
r
e
nga
ge
ment
in
onli
ne
tas
ks
.
T
he
r
e
s
ult
s
of
the
lea
r
ning
a
na
lyt
ics
a
ppr
oa
c
h
f
r
om
[
50]
s
howe
d
that
a
ll
thr
e
e
indi
c
a
tor
s
(
videos
wa
tche
d
a
s
c
ontextua
l
dim
e
ns
ion,
a
s
s
ignm
e
nts
s
ubmi
tt
e
d
a
s
c
ognit
ive
dim
e
ns
ion,
a
nd
mes
s
a
ge
s
pos
ted
a
s
s
oc
ial
dim
e
n
s
ion)
of
e
nga
ge
ment
in
onli
ne
tas
ks
s
igni
f
ica
ntl
y
pr
e
dicte
d
a
c
a
de
mi
c
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
E
lec
&
C
omp
E
ng
I
S
S
N:
2088
-
8708
P
r
e
dicting
ac
ade
mic
pe
r
for
manc
e
:
tow
ar
d
a
mode
l
bas
e
d
on
…
(
J
amal
E
ddine
R
afi
q
)
651
pe
r
f
or
manc
e
,
with
s
c
or
e
s
on
the
f
inal
e
xa
m
s
e
r
ving
a
s
a
mea
s
ur
e
of
their
a
c
a
de
mi
c
pe
r
f
o
r
ma
nc
e
.
B
y
int
e
gr
a
ti
ng
thes
e
dif
f
e
r
e
nt
dim
e
ns
ions
of
int
e
l
li
ge
nc
e
,
our
model
a
im
s
to
pr
ovide
a
n
a
c
c
ur
a
te
a
nd
c
ompr
e
he
ns
ive
pr
e
diction
of
onl
ine
a
c
a
de
mi
c
pe
r
f
or
manc
e
,
c
ons
ider
ing
the
d
iver
s
it
y
of
lea
r
ne
r
s
'
a
bil
it
ies
a
nd
s
kil
ls
in
a
digi
tal
lea
r
ning
e
nvi
r
onment.
4.
CONC
L
USI
ON
E
duc
a
ti
on
is
unde
r
going
a
pr
o
f
ound
tr
a
ns
f
or
mati
on
with
the
r
is
e
of
digi
tal
lea
r
ning
,
pa
r
ti
c
ular
ly
onli
ne
e
duc
a
ti
on.
T
his
pa
pe
r
int
r
oduc
e
s
the
4I
-
C
B
T
c
onc
e
ptual
model,
de
s
igned
to
pr
e
dict
a
nd
e
nha
nc
e
lea
r
ne
r
s
'
a
c
a
de
mi
c
pe
r
f
o
r
manc
e
in
onli
ne
e
nvir
on
ments
.
T
he
model
leve
r
a
ge
s
a
r
ti
f
icia
l
int
e
ll
igenc
e
,
uti
li
z
ing
tec
hniques
s
uc
h
a
s
mul
ti
ple
r
e
gr
e
s
s
ion,
a
r
ti
f
icia
l
ne
ur
a
l
ne
twor
ks
,
a
nd
r
a
ndom
f
o
r
e
s
ts
,
while
int
e
gr
a
ti
ng
c
ognit
ive,
s
oc
ial,
e
mot
ional,
a
nd
de
mogr
a
phic
ind
ica
tor
s
.
Unlike
pr
e
vious
s
tudi
e
s
that
of
ten
f
oc
us
e
d
on
one
to
thr
e
e
dim
e
ns
ions
to
pr
e
dict
a
c
a
de
mi
c
pe
r
f
or
manc
e
,
ne
glec
ti
ng
the
c
ompl
e
xit
y
of
f
a
c
tor
s
inf
luenc
ing
lea
r
ne
r
outcome
s
,
our
mul
ti
modal
model
int
e
gr
a
te
s
f
our
dim
e
ns
ions
a
nd
17
dis
ti
nc
t
c
ha
r
a
c
ter
is
ti
c
s
,
o
f
f
e
r
ing
a
mor
e
c
ompr
e
he
ns
ive
a
nd
a
c
c
ur
a
te
e
va
luation.
T
h
is
model
is
de
s
igned
to
e
nr
ich
the
onli
ne
lea
r
ning
e
x
pe
r
ienc
e
by
c
ons
ider
ing
thes
e
diver
s
e
dim
e
ns
ion
s
.
I
t
a
ls
o
pr
ovides
a
f
ounda
ti
on
f
or
unde
r
s
tanding
c
ompete
n
c
y
-
ba
s
e
d
onli
ne
lea
r
ning
pr
oc
e
s
s
e
s
,
of
f
e
r
ing
numer
ous
r
e
s
e
a
r
c
h
oppor
tuni
ti
e
s
to
va
li
da
te
or
r
e
f
u
te
it
s
pr
opos
i
ti
ons
.
I
n
the
f
utur
e
,
we
plan
to
e
nha
nc
e
our
model
by
e
xplo
r
ing
ne
w
de
e
p
lea
r
ning
tec
hniques
a
nd
r
e
f
ini
ng
th
e
c
r
it
e
r
ia
f
or
e
va
luating
pr
e
dictive
pe
r
f
or
manc
e
.
W
e
a
ls
o
e
nvis
ion
e
xpa
nding
our
model
to
s
uppor
t
pe
r
s
ona
li
z
e
d
onli
ne
lea
r
ning,
p
r
ovidi
ng
tailo
r
e
d
pe
da
gogica
l
r
e
c
omm
e
nda
ti
ons
ba
s
e
d
on
pr
e
dicte
d
a
c
a
de
mi
c
pe
r
f
or
manc
e
.
RE
F
E
RE
NC
E
S
[
1]
S
.
L
a
r
a
bi
-
M
a
r
ie
-
S
a
in
te
,
R
.
J
a
n,
A
.
A
l
-
M
a
to
uq,
a
nd
S
.
A
la
bduha
di
,
“
T
he
im
pa
c
t
of
ti
me
ta
bl
e
on
s
tu
de
nt
’
s
a
b
s
e
nc
e
s
a
nd
pe
r
f
or
ma
nc
e
,”
P
L
oS O
N
E
, vol
. 16, no. 6 J
une
, pp. 1
–
22, 2021, doi:
10.1371/j
our
na
l.
pone
.0253256.
[
2]
K
.
F
a
hd,
S
.
J
.
M
ia
h,
a
nd
K
.
A
hme
d,
“
P
r
e
di
c
ti
ng
s
tu
de
nt
pe
r
f
or
ma
nc
e
in
a
bl
e
nde
d
le
a
r
ni
ng
e
nvi
r
onme
nt
us
in
g
le
a
r
ni
ng
ma
na
ge
me
nt
s
y
s
te
m i
nt
e
r
a
c
ti
on da
ta
,”
A
ppl
ie
d C
om
put
in
g and
I
nf
or
m
at
ic
s
, 2021, doi:
10.1108/AC
I
-
06
-
2021
-
0150.
[
3]
S
.
H
a
s
e
e
na
a
nd
S
.
P
e
te
r
,
“
D
a
ta
mi
ni
ng
te
c
hni
que
s
:
e
duc
a
ti
ona
l
s
ys
te
m,”
I
nt
e
r
nat
io
nal
J
our
nal
of
A
dv
anc
e
d
R
e
s
e
ar
c
h
T
r
e
nd
s
in
E
ngi
ne
e
r
in
g and T
e
c
hnol
ogy
(
I
J
A
R
T
E
T
)
, vol
. 4, no. 4, pp. 41
–
4
3, 2017.
[
4]
X
.
X
u
,
J
.
W
a
ng
,
H
.
P
e
n
g,
a
nd
R
.
W
u,
“
P
r
e
d
i
c
ti
on
of
a
c
a
de
mi
c
p
e
r
f
or
ma
n
c
e
a
s
s
o
c
ia
te
d
w
it
h
i
nt
e
r
n
e
t
u
s
a
g
e
b
e
ha
vi
or
s
u
s
in
g
m
a
c
h
in
e
l
e
a
r
ni
n
g
a
lg
or
i
th
m
s
,
”
C
o
m
put
e
r
s
i
n
H
u
m
a
n B
e
h
a
v
i
o
r
,
v
ol
.
9
8,
n
o.
J
a
nu
a
r
y,
p
p.
1
66
–
1
73
,
20
19
,
do
i:
10
.1
01
6/
j.
c
h
b.
20
19
.0
4.
01
5.
[
5]
R
. T
or
mon, B
. L
. L
in
ds
a
y, R
. M
. P
a
ul
, M
. A
. B
oyc
e
, a
nd K
. J
ohns
to
n, “
P
r
e
di
c
ti
ng a
c
a
de
mi
c
pe
r
f
or
ma
nc
e
i
n f
ir
s
t
-
ye
a
r
e
ngi
ne
e
r
in
g
s
tu
de
nt
s
:
T
he
r
ol
e
of
s
tr
e
s
s
,
r
e
s
il
ie
nc
y,
s
tu
de
nt
e
ng
a
ge
me
nt
,
a
n
d
gr
ow
th
mi
nds
e
t,
”
L
e
ar
ni
ng
and
I
ndi
v
id
ual
D
if
fe
r
e
n
c
e
s
,
vol
.
108,
2023, doi:
10.1016/j
.l
in
di
f
.2023.102383.
[
6]
P
.
X
ua
n
L
a
m,
P
.
Q
.
H
.
M
a
i,
Q
.
H
.
N
guye
n,
T
.
P
ha
m,
T
.
H
.
H
.
N
guye
n,
a
nd
T
.
H
.
N
guye
n,
“
E
nha
nc
in
g
e
duc
a
ti
ona
l
e
va
lu
a
ti
on
th
r
ough
pr
e
di
c
ti
ve
s
tu
de
nt
a
s
s
e
s
s
me
nt
mode
li
ng,”
C
om
put
e
r
s
and
E
duc
at
io
n:
A
r
ti
fi
c
ia
l
I
nt
e
ll
ig
e
nc
e
,
vol
.
6,
2024,
doi
:
10.1016/j
.c
a
e
a
i.
2024.100244.
[
7]
X
.
W
a
ng,
Y
.
Z
ha
o,
C
.
L
i,
a
nd
P
.
R
e
n,
“
P
r
obS
A
P
:
A
c
o
mpr
e
he
ns
iv
e
a
nd
hi
gh
-
pe
r
f
or
ma
nc
e
s
ys
te
m
f
or
s
tu
de
nt
a
c
a
d
e
mi
c
pe
r
f
or
ma
nc
e
pr
e
di
c
ti
on,”
P
at
te
r
n R
e
c
ogni
ti
on
, vol
. 137, 2023, doi:
10.1016/j
.pa
tc
og.2023.109309.
[
8]
K
.
V
im
a
r
s
ha
,
S
.
P
.
S
.
P
r
a
ka
s
h,
K
.
K
r
in
ki
n,
a
nd
Y
.
A
.
S
hi
c
h
ki
na
,
“
S
tu
de
nt
pe
r
f
or
ma
nc
e
pr
e
di
c
ti
on:
a
c
o
-
e
vol
ut
io
na
r
y
hy
br
id
in
te
ll
ig
e
nc
e
mode
l,
”
P
r
oc
e
di
a C
om
put
e
r
Sc
ie
n
c
e
, vol
. 235, pp.
436
–
446, 2024, doi:
10.1016/j
.pr
oc
s
.2024.04.043.
[
9]
C
.
F
.
R
odr
íg
ue
z
-
H
e
r
ná
nde
z
,
M
.
M
us
s
o,
E
.
K
yndt
,
a
nd
E
.
C
a
s
c
a
ll
a
r
,
“
A
r
ti
f
ic
ia
l
ne
ur
a
l
ne
twor
ks
in
a
c
a
de
mi
c
pe
r
f
or
ma
nc
e
pr
e
di
c
ti
on:
S
ys
te
ma
ti
c
im
pl
e
me
nt
a
ti
on
a
nd
pr
e
di
c
to
r
e
va
lu
a
ti
on,”
C
om
put
e
r
s
and
E
duc
at
io
n:
A
r
ti
fi
c
ia
l
I
nt
e
ll
ig
e
nc
e
,
vol
.
2,
2
021,
doi
:
10.1016/j
.c
a
e
a
i.
2021.100018.
[
10]
E
.
M
ur
a
to
v,
M
.
L
e
w
is
,
D
.
F
our
c
he
s
,
A
.
T
r
ops
ha
,
a
nd
W
.
C
.
C
ox,
“
C
omput
e
r
-
a
s
s
is
te
d
de
c
is
io
n
s
uppor
t
f
or
s
tu
de
nt
a
dmi
s
s
i
ons
ba
s
e
d
on
th
e
ir
pr
e
di
c
te
d
a
c
a
de
mi
c
pe
r
f
or
ma
nc
e
,”
A
m
e
r
ic
an
J
our
nal
of
P
har
m
ac
e
ut
ic
al
E
duc
at
io
n
,
vol
.
81,
no.
3,
2017,
doi
:
10.5688/a
jp
e
81346.
[
11]
J
.
M
a
li
ni
a
nd
Y
.
K
a
lp
a
na
,
“
I
nve
s
ti
ga
ti
on
of
f
a
c
to
r
s
a
f
f
e
c
ti
ng
s
tu
de
nt
pe
r
f
or
ma
nc
e
e
va
lu
a
ti
on
u
s
in
g
e
duc
a
ti
on
ma
te
r
ia
ls
da
ta
mi
ni
ng t
e
c
hni
que
,”
M
at
e
r
ia
ls
T
oday
:
P
r
oc
e
e
di
ng
s
, vol
. 47, pp. 6105
–
6110, 2021, doi:
10.1016/j
.ma
tp
r
.2021.05.026.
[
12]
P
a
r
ka
vi
R
.
,
K
a
r
th
ik
e
ya
n
P
.
,
a
nd
S
.
A
bdul
la
h
A
.
,
“
P
r
e
di
c
ti
ng
a
c
a
de
mi
c
pe
r
f
or
ma
nc
e
of
le
a
r
ne
r
s
w
it
h
th
e
th
r
e
e
doma
in
s
of
le
a
r
ni
ng
da
ta
us
in
g
ne
ur
o
-
f
uz
z
y
mode
l
a
nd
ma
c
hi
ne
le
a
r
ni
ng
a
lg
or
it
hms
,”
J
our
nal
of
E
ngi
ne
e
r
in
g
R
e
s
e
ar
c
h
,
2023,
doi
:
10.1016/j
.j
e
r
.2023.09.006.
[
13]
M
.
C
he
n
a
nd
Z
.
L
iu
,
“
P
r
e
di
c
ti
ng
pe
r
f
or
ma
nc
e
of
s
tu
de
nt
s
by
opt
im
iz
in
g
tr
e
e
c
ompone
nt
s
of
r
a
ndom
f
or
e
s
t
us
in
g
ge
n
e
ti
c
a
lg
or
it
hm,”
H
e
li
y
on
, vol
. 10, no. 12, 2024, doi
:
10.1016/j
.he
li
yon.2024.e
32570.
[
14]
G
.
W
a
ng
a
nd
T
.
R
e
n,
“
D
e
s
ig
n
of
s
por
ts
a
c
hi
e
ve
me
nt
pr
e
di
c
ti
on
s
ys
te
m
ba
s
e
d
on
U
-
ne
t
c
onvolut
io
na
l
ne
ur
a
l
ne
twor
k
in
th
e
c
ont
e
xt
of
ma
c
hi
ne
l
e
a
r
ni
ng,”
H
e
li
y
on
, vol
. 10, no. 10, 2024, do
i:
10.1016/j
.he
li
yon.2024.e
30055.
[
15]
H
.
W
a
he
e
d,
S
.
U
.
H
a
s
s
a
n,
R
.
N
a
w
a
z
,
N
.
R
.
A
lj
oha
ni
,
G
.
C
he
n,
a
nd
D
.
G
a
s
e
vi
c
,
“
E
a
r
ly
pr
e
di
c
ti
on
of
le
a
r
ne
r
s
a
t
r
is
k
in
s
e
lf
-
pa
c
e
d
e
duc
a
ti
on:
a
ne
ur
a
l
ne
twor
k a
ppr
oa
c
h,”
E
x
pe
r
t
Sy
s
te
m
s
w
it
h A
p
pl
ic
at
io
ns
, vol
. 213, 2023, doi:
10.1016/j
.e
s
w
a
.2022.118868.
[
16]
K
.
S
ur
e
s
h
M
a
ni
c
,
A
.
S
.
A
l
-
B
e
ma
ni
,
A
.
A
.
N
iz
a
mudi
n,
G
.
B
a
la
ji
,
a
nd
A
.
A
.
A
ma
l,
“
O
pt
im
iz
in
g
a
c
a
de
mi
c
jo
ur
ne
y
f
or
hi
gh
s
c
hool
e
r
s
in
O
ma
n:
a
ma
c
hi
ne
le
a
r
ni
ng
-
e
na
bl
e
d
A
I
mode
l,
”
P
r
oc
e
di
a
C
om
put
e
r
Sc
ie
nc
e
,
vol
.
235,
pp.
2716
–
2729,
2024,
doi
:
10.1016/j
.pr
oc
s
.2024.04.256.
[
17]
S
.
R
iz
vi
,
B
.
R
ie
nt
ie
s
,
a
nd
S
.
A
.
K
hoj
a
,
“
T
he
r
ol
e
of
de
mogr
a
phi
c
s
in
onl
in
e
le
a
r
ni
ng:
a
de
c
is
io
n
tr
e
e
ba
s
e
d a
ppr
oa
c
h,”
C
om
put
e
r
s
and E
duc
at
io
n
, vol
. 137, pp. 32
–
47, 2019, doi:
10.1016/j
.c
omp
e
du.2019.04.001.
[
18]
G
.
A
l
-
ta
me
e
mi
,
“
A
hybr
id
ma
c
hi
ne
l
e
a
r
ni
ng
a
ppr
oa
c
h
f
or
pr
e
di
c
ti
ng
s
tu
de
nt
a
hybr
id
ma
c
hi
ne
le
a
r
ni
ng
a
ppr
oa
c
h
f
or
pr
e
di
c
ti
ng
s
tu
de
nt
pe
r
f
or
ma
nc
e
us
in
g
mul
ti
-
c
la
s
s
e
duc
a
ti
ona
l
da
ta
s
e
ts
,”
P
r
oc
e
di
a
C
om
put
e
r
Sc
ie
nc
e
,
vol
.
238,
no.
2019,
pp.
888
–
895,
2
024,
doi
:
10.1016/j
.pr
oc
s
.2024.06.108.
[
19]
Á
.
H
e
r
ná
nde
z
-
G
a
r
c
ía
,
C
.
C
ue
nc
a
-
E
nr
iq
ue
,
L
.
D
e
l
-
R
ío
-
C
a
r
a
z
o,
a
nd
S
.
I
gl
e
s
ia
s
-
P
r
a
da
s
,
“
E
xpl
or
in
g
th
e
r
e
la
ti
ons
hi
p
be
twe
e
n
L
M
S
in
te
r
a
c
ti
ons
a
nd
a
c
a
de
mi
c
pe
r
f
or
ma
nc
e
:
a
le
a
r
ni
ng
c
yc
le
a
ppr
oa
c
h,”
C
om
put
e
r
s
in
H
um
an
B
e
hav
io
r
,
vol
.
155,
2024,
doi
:
10.1016/j
.c
hb.2024.108183.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2088
-
8708
I
nt
J
E
lec
&
C
omp
E
ng
,
Vol
.
15
,
No.
1
,
F
e
br
ua
r
y
20
25
:
645
-
653
652
[
20]
B
.
C
he
ng,
Y
.
L
iu
,
a
nd
Y
.
J
ia
,
“
E
va
lu
a
ti
on
of
s
tu
de
nt
s
’
pe
r
f
or
ma
nc
e
dur
in
g
th
e
a
c
a
de
mi
c
pe
r
io
d
us
in
g
th
e
X
G
-
boos
t
c
la
s
s
if
ie
r
-
e
nha
nc
e
d A
E
O
hybr
id
mode
l,
”
E
x
pe
r
t
Sy
s
te
m
s
w
it
h A
ppl
ic
at
io
ns
, vol
. 238, 2024, doi:
10.1016/j
.e
s
w
a
.2023.122136.
[
21]
M
.
A
mr
a
ouy,
M
.
B
e
ll
a
f
ki
h,
A
.
B
e
nna
n
e
,
a
nd
J
.
T
a
la
ghz
i,
“
S
e
n
ti
me
nt
a
na
ly
s
is
f
or
c
ompe
te
nc
e
-
ba
s
e
d
e
-
a
s
s
e
s
s
me
nt
us
in
g
ma
c
hi
ne
le
a
r
ni
ng
a
nd
le
xi
c
on
a
ppr
oa
c
h,”
in
T
he
3r
d
I
nt
e
r
nat
io
nal
C
onf
e
r
e
nc
e
on
A
r
ti
fi
c
ia
l
I
nt
e
ll
ig
e
nc
e
and
C
om
put
e
r
V
is
io
n
(
A
I
C
V
2023)
,
M
ar
c
h 5
–
7, 2023. A
I
C
V
2023
, 2023, pp. 327
–
336. doi:
10.1007
/9
78
-
3
-
031
-
27762
-
7_31.
[
22]
A
.
S
.
H
a
s
hi
m,
W
.
A
.
A
w
a
dh,
a
nd
A
.
K
.
H
a
moud,
“
S
tu
de
nt
pe
r
f
or
ma
nc
e
pr
e
di
c
ti
on
mode
l
ba
s
e
d
on
s
upe
r
vi
s
e
d
ma
c
hi
ne
le
a
r
ni
ng
a
lg
or
it
hms
,”
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
,
vol
.
928,
no.
3,
N
ov.
2020,
doi
:
10.1088
/1
7
57
-
899X/928/3/
032019.
[
23]
B
.
O
w
us
u
-
B
o
a
du,
I
.
K
.
N
ti
,
O
.
N
ya
r
ko
-
B
oa
te
ng,
J
.
A
ni
ng,
a
nd
V
.
B
o
a
f
o,
“
A
c
a
d
e
mi
c
pe
r
f
or
ma
nc
e
mode
ll
in
g
w
it
h
m
a
c
hi
ne
le
a
r
ni
ng
ba
s
e
d
on
c
ogni
ti
ve
a
nd
non
-
c
ogni
ti
ve
f
e
a
tu
r
e
s
,
”
A
p
pl
ie
d
C
om
put
e
r
Sy
s
te
m
s
,
vol
.
26,
no.
2,
pp.
122
–
131,
2021,
doi
:
10.2478/a
c
s
s
-
2021
-
0015.
[
24]
A
.
Q
uí
le
z
-
R
obr
e
s
,
P
.
U
s
á
n,
R
.
L
oz
a
no
-
B
l
a
s
c
o,
a
nd
C
.
S
a
la
ve
r
a
,
“
T
ype
s
of
in
te
ll
ig
e
nc
e
a
nd
a
c
a
de
mi
c
pe
r
f
or
ma
nc
e
:
a
s
y
s
te
m
a
ti
c
r
e
vi
e
w
a
nd me
ta
-
a
na
ly
s
is
,
”
J
our
nal
of
I
nt
e
ll
ig
e
nc
e
10:
, vol
. 10,
2022, doi:
10.3390/j
in
te
ll
ig
e
nc
e
10040123.
[
25]
N
.
S
á
nc
he
z
-
Á
lv
a
r
e
z
,
M
.
P
.
B
e
r
r
io
s
M
a
r
to
s
,
a
nd
N
.
E
xt
r
e
me
r
a
,
“
A
me
ta
-
a
na
ly
s
is
of
th
e
r
e
la
ti
ons
hi
p
be
tw
e
e
n
e
mot
i
ona
l
in
te
ll
ig
e
nc
e
a
nd
a
c
a
de
mi
c
pe
r
f
or
ma
nc
e
in
s
e
c
onda
r
y
e
duc
a
ti
o
n:
a
mul
ti
-
s
tr
e
a
m
c
ompa
r
is
on,”
F
r
ont
ie
r
s
in
P
s
y
c
hol
ogy
,
vol
.
11,
no. J
ul
y, pp. 1
–
11, 2020, doi:
10.3389/f
ps
yg.2020.01517.
[
26]
I
.
A
nt
oni
o
-
A
gi
r
r
e
,
A
.
R
odr
íg
ue
z
-
F
e
r
ná
nde
z
,
a
nd
L
.
R
e
vu
e
lt
a
,
“
S
oc
ia
l
s
uppor
t,
e
mot
io
na
l
in
te
ll
ig
e
nc
e
a
nd
a
c
a
de
mi
c
pe
r
f
or
ma
nc
e
in
s
e
c
onda
r
y
e
duc
a
ti
on.,”
E
ur
ope
an
J
our
nal
of
I
nv
e
s
ti
gat
io
n
i
n
H
e
al
th
,
P
s
y
c
hol
ogy
and
E
duc
at
io
n
,
vol
.
9,
no.
2,
pp.
109
–
1
18,
2019, doi:
10.30552/ejihpe.v9i2.324.
[
27]
I
.
O
te
r
o,
J
.
F
.
S
a
lg
a
do,
a
nd
S
.
M
os
c
os
o,
“
C
ogni
ti
ve
r
e
f
le
c
ti
on,
c
ogni
ti
ve
in
te
ll
ig
e
nc
e
,
a
nd
c
ogni
ti
ve
a
bi
li
t
ie
s
:
a
me
ta
-
a
na
ly
s
is
,”
I
nt
e
ll
ig
e
nc
e
, vol
. 90, 2022, doi:
10.1016/j
.i
nt
e
ll
.2021.101614.
[
28]
P
.
A
r
na
iz
-
S
á
nc
he
z
,
R
.
de
H
a
r
o,
S
.
A
l
c
a
r
a
z
,
a
nd
A
.
B
.
M
ir
e
te
R
ui
z
,
“
S
c
hool
s
th
a
t
pr
omot
e
th
e
im
pr
ove
me
nt
of
a
c
a
de
mi
c
pe
r
f
or
ma
nc
e
a
nd t
he
s
uc
c
e
s
s
of
a
ll
s
tu
d
e
nt
s
,”
F
r
ont
ie
r
s
i
n P
s
y
c
hol
ogy
, vol
. 10, pp. 1
–
8, 2020, doi:
10.3389/f
ps
yg.2019.02920.
[
29]
F
.
E
.
W
e
in
e
r
t,
“
C
onc
e
pt
s
of
c
ompe
te
nc
e
.
C
ont
r
ib
ut
io
n
w
it
h
in
th
e
O
E
C
D
pr
o
je
c
t
de
f
in
it
io
n
a
nd
s
e
le
c
ti
on
of
c
ompe
te
nc
ie
s
:
th
e
or
e
ti
c
a
l
a
nd c
onc
e
pt
ua
l
f
ounda
ti
ons
,
”
A
m
e
r
ic
an P
s
y
c
hol
ogi
c
al
A
s
s
oc
ia
ti
on
, pp. 45
–
65, 2001.
[
30]
V
.
D
e
L
a
nd
s
he
e
r
e
,
“
M
in
im
um
c
omp
e
te
nc
y
in
s
e
c
onda
r
y
e
d
uc
a
ti
on,”
P
r
os
p
e
c
ts
,
vol
.
17,
no.
1,
pp.
38
–
48,
M
a
r
.
1987,
doi
:
10.1007/B
F
02195157.
[
31]
P
.
P
e
r
r
e
noud,
“
S
ki
ll
s
,
ha
bi
tu
s
a
nd
pr
of
e
s
s
io
na
l
knowle
dg
e
,”
E
u
r
ope
an
J
ou
r
nal
of
T
e
ac
he
r
E
duc
at
io
n
,
vol
.
17,
no.
1
–
2,
pp.
45
–
48,
1994, doi:
10.1080/026197694
0170108.
[
32]
M
.
A
.
M
or
e
ir
a
e
t
al
.
,
“
T
e
a
c
h
e
r
s
’
pe
da
gogi
c
a
l
c
omp
e
te
nc
e
s
in
hi
ghe
r
e
duc
a
ti
on:
A
s
ys
te
ma
ti
c
li
te
r
a
tu
r
e
r
e
vi
e
w
,”
J
our
na
l
of
U
ni
v
e
r
s
it
y
T
e
a
c
hi
ng and L
e
ar
ni
ng P
r
ac
ti
c
e
, vol
. 20, no. 1, pp.
90
–
123, J
a
n. 2023, doi:
10.53761/1.20.01.0
7.
[
33]
B
.
J
a
c
ob
s
e
t
al
.
,
“
P
r
e
pa
r
in
g
s
tu
de
nt
s
f
or
th
e
f
ut
ur
e
w
or
kpl
a
c
e
:
how
onl
in
e
te
a
c
hi
ng
a
nd
le
a
r
ni
ng
dur
in
g
th
e
C
O
V
I
D
-
19
pa
nde
mi
c
hone
r
e
qui
r
e
d t
r
a
ns
f
e
r
a
bl
e
s
ki
ll
s
,”
E
duc
at
io
n and T
r
ai
ni
ng
, vol
. 65, no. 10, pp. 81
–
97, 2023, doi:
10.1108/E
T
-
09
-
2022
-
0371.
[
34]
N
.
R
a
c
hbur
e
e
a
nd
W
.
P
unl
umj
e
a
k,
“
O
ve
r
s
a
mpl
in
g
te
c
hni
que
in
s
tu
de
nt
pe
r
f
or
ma
nc
e
c
la
s
s
if
ic
a
ti
on
f
r
om
e
ngi
ne
e
r
in
g
c
our
s
e
,
”
I
nt
e
r
nat
io
nal
J
our
nal
of
E
le
c
t
r
ic
al
and
C
om
put
e
r
E
ngi
ne
e
r
in
g
,
vol
.
11,
no.
4,
pp.
3567
–
3574,
2021,
doi
:
10.11591/i
je
c
e
.v11i4.pp3567
-
3574.
[
35]
H
.
D
.
M
a
s
on,
“
S
e
n
s
e
of
me
a
ni
ng
a
nd
a
c
a
de
mi
c
pe
r
f
or
ma
nc
e
:
a
br
ie
f
r
e
por
t,
”
J
our
nal
of
P
s
y
c
hol
ogy
in
A
fr
ic
a
,
vol
.
27,
no.
3,
pp. 282
–
285, 2017, doi:
10.1080/14330237.
2017.1321860.
[
36]
I
.
I
s
s
a
h,
O
.
A
ppi
a
h,
P
.
A
ppi
a
he
n
e
,
a
nd
F
.
I
nus
a
h,
“
A
s
y
s
te
ma
ti
c
r
e
vi
e
w
of
th
e
li
te
r
a
tu
r
e
on
m
a
c
hi
ne
le
a
r
ni
ng
a
ppl
ic
a
ti
o
n
of
de
te
r
mi
ni
ng
th
e
a
tt
r
ib
ut
e
s
in
f
lu
e
nc
in
g
a
c
a
de
mi
c
pe
r
f
or
ma
nc
e
,”
D
e
c
is
io
n
A
nal
y
ti
c
s
J
ou
r
nal
,
vol
.
7,
2023,
doi
:
10.1016/j
.da
jo
ur
.2023.100204.
[
37]
S
.
B
a
to
ol
,
J
.
R
a
s
hi
d,
M
.
W
.
N
is
a
r
,
J
.
K
im
,
H
.
Y
.
K
w
on,
a
nd
A
.
H
us
s
a
in
,
“
E
duc
a
ti
ona
l
da
ta
mi
ni
ng
to
pr
e
di
c
t
s
tu
de
nt
s
’
a
c
a
de
mi
c
pe
r
f
or
ma
nc
e
:
a
s
ur
ve
y
s
tu
dy,”
E
duc
at
io
n
and
I
nf
or
m
at
io
n
T
e
c
hnol
ogi
e
s
,
vol
.
28,
no.
1,
pp.
905
–
971,
2023,
doi
:
10.1007/
s
10
639
-
022
-
11152
-
y.
[
38]
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
te
r
a
tu
r
e
r
e
vi
e
w
of
s
tu
de
nt
’
pe
r
f
or
ma
nc
e
pr
e
di
c
ti
on
u
s
in
g
ma
c
hi
n
e
le
a
r
n
in
g
te
c
hni
que
s
,”
E
duc
at
io
n Sc
ie
nc
e
s
, vol
. 11, no. 9, 2021, doi
:
10.3
390/
e
duc
s
c
i1
1090552.
[
39]
J
.
V
a
lv
e
r
d
e
-
B
e
r
r
o
c
os
o,
M
.
d
e
l
C
.
G
a
r
r
i
do
-
A
r
r
oy
o,
C
.
B
ur
g
o
s
-
V
i
d
e
l
a
,
a
n
d
M
.
B
.
M
o
r
a
l
e
s
-
C
e
va
ll
o
s
,
“
T
r
e
n
d
s
in
e
d
u
c
a
ti
on
a
l
r
e
s
e
a
r
c
h
a
b
ou
t
e
-
l
e
a
r
ni
ng:
a
s
y
s
t
e
m
a
t
ic
l
it
e
r
a
t
ur
e
r
e
v
i
e
w
(
2
00
9
–
20
18)
,
”
Sus
t
ai
na
bi
l
it
y
,
vol
.
12
,
no
.
12
,
J
un
.
20
20
,
do
i:
1
0.
33
90
/s
u1
21
25
15
3.
[
40]
R
.
A
.
R
a
mi
r
e
z
-
M
e
ndoz
a
,
R
.
M
or
a
le
s
-
M
e
ne
nde
z
,
H
.
I
qba
l,
a
nd
R
.
P
a
r
r
a
-
S
a
ld
iv
a
r
,
“
E
ngi
ne
e
r
in
g
e
duc
a
ti
on
4.0:
-
pr
opos
a
l
f
or
a
n
e
w
c
ur
r
ic
ul
a
,”
I
E
E
E
G
lo
bal
E
ngi
ne
e
r
in
g
E
duc
at
io
n
C
onf
e
r
e
nc
e
,
E
D
U
C
O
N
,
vol
.
2018
-
A
pr
il
,
pp.
1273
–
1282,
2018,
doi
:
10.1109/E
D
U
C
O
N
.2018.8363376.
[
41]
C
.
M
a
c
C
a
nn,
Y
.
J
ia
ng,
L
.
E
.
R
.
B
r
ow
n,
K
.
S
.
D
oubl
e
,
M
.
B
uc
i
c
h,
a
nd
A
.
M
in
ba
s
hi
a
n,
“
E
mot
io
na
l
in
te
ll
ig
e
nc
e
pr
e
di
c
ts
a
c
a
d
e
mi
c
pe
r
f
or
ma
nc
e
:
a
me
ta
-
a
na
ly
s
is
,”
P
s
y
c
hol
ogi
c
al
B
ul
le
ti
n
, vol
. 146(
2)
, 15, 2019, doi:
10.1037/bul
0000219.
[
42]
R
.
U
me
r
,
T
.
S
us
nj
a
k,
A
.
M
a
th
r
a
ni
,
a
nd
S
.
S
ur
ia
di
,
“
O
n
pr
e
di
c
ti
ng
a
c
a
de
mi
c
p
e
r
f
or
ma
nc
e
w
it
h
pr
oc
e
s
s
mi
ni
ng
in
le
a
r
ni
ng
a
na
ly
ti
c
s
,”
J
ou
r
nal
of
R
e
s
e
ar
c
h
in
I
nnov
at
iv
e
T
e
ac
hi
ng
&
L
e
a
r
ni
ng
,
vol
.
10,
no.
2,
pp.
160
–
176,
2017,
doi
:
10.1108/j
r
it
-
09
-
20
17
-
0022.
[
43]
T
.
D
jo
ua
d,
A
.
M
il
le
,
C
. R
e
f
f
a
y,
a
nd
M
. B
e
nmoha
mm
e
d, “
A
ne
w
a
ppr
oa
c
h
ba
s
e
d
on
mode
ll
e
d
tr
a
c
e
s
to
c
omput
e
c
ol
la
bor
a
ti
ve
a
nd
in
di
vi
dua
l
in
di
c
a
to
r
s
’
huma
n
in
te
r
a
c
ti
on,”
in
P
r
oc
e
e
di
ng
s
-
10t
h
I
E
E
E
I
nt
e
r
nat
io
nal
C
onf
e
r
e
nc
e
on
A
dv
an
c
e
d
L
e
a
r
ni
ng
T
e
c
hnol
ogi
e
s
, I
C
A
L
T
2010
, 2010, pp. 53
–
54. doi:
10.1109/I
C
A
L
T
.2010.21.
[
44]
W
.
O
.
O
ndi
ti
,
S
.
N
z
io
ki
,
a
nd
S
.
M
ur
it
hi
,
“
E
f
f
e
c
t
of
knowle
d
ge
s
ha
r
in
g
on
a
c
a
d
e
mi
c
pe
r
f
or
ma
nc
e
of
po
s
tg
r
a
dua
te
s
tu
de
nt
s
of
pr
iv
a
te
U
ni
ve
r
s
it
ie
s
i
n K
e
nya
,”
I
nt
e
r
nat
io
nal
J
our
nal
of
P
r
of
e
s
s
io
nal
P
r
ac
ti
c
e
, no. 2, 2023.
[
45]
M
.
N
e
o
e
t
al
.
,
“
E
nha
nc
in
g
s
tu
de
nt
s
’
onl
in
e
le
a
r
ni
ng
e
xpe
r
ie
nc
e
s
w
it
h
a
r
ti
f
ic
ia
l
in
te
ll
ig
e
nc
e
(
A
I
)
:
th
e
M
E
R
L
I
N
pr
oj
e
c
t,
”
I
nt
e
r
nat
io
nal
J
our
nal
of
T
e
c
hnol
ogy
, vol
. 13, no. 5, pp. 1023
–
1
034, 2022, doi:
10.14716/i
jt
e
c
h.v13i5.5843.
[
46]
R
.
R
e
hma
n,
S
.
T
a
r
iq
,
a
nd
S
.
T
a
r
iq
,
“
E
mot
io
na
l
in
te
ll
ig
e
nc
e
a
nd
a
c
a
de
mi
c
pe
r
f
or
ma
nc
e
of
s
tu
de
nt
s
,”
J
our
nal
of
th
e
P
ak
is
ta
n
M
e
di
c
al
A
s
s
oc
ia
ti
on
, vol
. 71, no. 12, pp. 2777
–
2781, 2017, doi:
10.29086/2519
-
5476/2017/
s
p20a
9.
[
47]
J
.
E
.
R
a
f
iq
,
A
.
Z
a
kr
a
ni
,
M
.
A
mr
a
ouy,
A
.
N
a
mi
r
,
a
nd
A
.
B
e
nna
ne
,
“
O
pt
im
iz
in
g
le
a
r
ni
ng
pe
r
f
or
ma
nc
e
th
r
ough
A
I
-
e
nha
nc
e
d
di
s
c
us
s
io
n
f
or
ums
,”
in
2023
14t
h
I
nt
e
r
nat
io
nal
C
onf
e
r
e
nc
e
on
I
nt
e
ll
ig
e
nt
Sy
s
te
m
s
:
T
he
or
ie
s
and
A
ppl
ic
at
io
ns
(
SI
T
A
)
,
2
023,
pp. 1
–
6. doi:
10.1109/S
I
T
A
60746.2023.10373689.
[
48]
L
.
O
.
L
.
B
a
nda
,
J
.
L
iu
,
J
. T
.
B
a
nd
a
,
a
nd W
.
Z
hou,
“
I
mpa
c
t
of
e
th
ni
c
id
e
nt
it
y
a
nd
ge
ogr
a
phi
c
a
l
hom
e
lo
c
a
ti
on
on s
tu
de
nt
a
c
a
de
m
ic
pe
r
f
or
ma
nc
e
,”
H
e
li
y
on
, vol
. 9, no. 6, 2023, doi:
10.1016/j
.he
li
yon.2023.e
16767.
[
49]
F
.
C
.
B
ona
f
in
i,
C
.
C
ha
e
,
E
.
P
a
r
k,
a
nd
K
.
W
. J
a
bl
okow,
“
H
o
w
muc
h
doe
s
s
tu
de
nt
e
ng
a
ge
me
nt
w
it
h
vi
d
e
os
a
nd
f
or
ums
in
a
M
O
O
C
a
f
f
e
c
t
th
e
ir
a
c
hi
e
ve
me
nt
?
,”
O
nl
in
e
L
e
a
r
ni
ng J
our
nal
, vol
. 21, n
o. 4, pp. 223
–
240, 2017, doi:
10.24059/ol
j.
v21i
4.1270.
[
50]
Y
.
J
ia
ng
a
nd
J
.
E
.
P
e
ng,
“
E
xpl
or
in
g
th
e
r
e
la
ti
ons
hi
ps
be
twe
e
n
le
a
r
ne
r
s
’
e
nga
ge
me
nt
,
a
ut
onomy,
a
nd
a
c
a
d
e
mi
c
pe
r
f
or
ma
nc
e
i
n
a
n
E
ngl
is
h l
a
ngua
ge
M
O
O
C
,
”
C
om
put
e
r
A
s
s
is
t
e
d L
anguage
L
e
ar
n
in
g
, pp. 1
–
26, 2023, doi:
10.1080/09588221.
2022.2164777.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
E
lec
&
C
omp
E
ng
I
S
S
N:
2088
-
8708
P
r
e
dicting
ac
ade
mic
pe
r
for
manc
e
:
tow
ar
d
a
mode
l
bas
e
d
on
…
(
J
amal
E
ddine
R
afi
q
)
653
B
I
OG
RA
P
HI
E
S
OF
AU
T
HO
RS
J
a
m
a
l
Eddi
ne
R
a
fi
q
i
s
a
p
ed
ag
o
g
i
ca
l
i
n
s
p
ec
t
o
r
i
n
co
mp
u
t
er
s
ci
en
ce
Marrak
ec
h
,
Mo
ro
cc
o
,
an
d
a
cu
rren
t
Ph
.
D
.
s
t
u
d
en
t
,
L
ab
o
rat
o
ry
o
f
A
rt
i
f
i
ci
a
l
In
t
e
l
l
i
g
e
n
ce
an
d
Co
mp
l
e
x
Sy
s
t
em
s
E
n
g
i
n
eer
i
n
g
,
H
as
s
a
n
II
U
n
i
v
er
s
i
t
y
.
H
i
s
res
ear
ch
i
n
t
eres
t
s
fo
c
u
s
o
n
h
u
ma
n
co
m
p
u
t
er
i
n
t
eract
i
o
n
,
art
i
fi
c
i
al
i
n
t
el
l
i
g
en
ce
,
a
n
d
d
i
g
i
t
a
l
l
ear
n
i
n
g
t
races
.
H
e
can
b
e
c
o
n
t
act
e
d
a
t
emai
l
:
j
amal
.
rafi
q
-
et
u
@
et
u
.
u
n
i
v
h
2
c.
ma
.
Za
kra
ni
A
bdel
a
l
i
h
o
l
d
s
a
Ph
.
D
.
i
n
c
o
mp
u
t
er
s
ci
e
n
ces
a
t
Mo
h
amm
ed
V
U
n
i
v
er
s
i
t
y
,
Rab
at
,
Mo
r
o
cco
,
i
n
2
0
1
2
.
H
e
i
s
cu
rre
n
t
l
y
p
ro
fes
s
o
r
(
H
i
g
h
er
D
e
g
ree
Res
earc
h
(H
D
R))
at
E
N
S
A
M
,
H
as
s
a
n
II
U
n
i
v
er
s
i
t
y
,
Cas
ab
l
a
n
ca,
Mo
ro
cco
.
H
i
s
cu
rren
t
res
earch
i
n
t
eres
t
s
’
ar
t
i
f
i
ci
a
l
n
eu
ra
l
n
e
t
w
o
rk
,
d
at
a
m
i
n
i
n
g
,
an
d
s
o
ft
w
are
en
g
i
n
eer
i
n
g
.
H
e
ca
n
b
e
co
n
t
act
e
d
at
emai
l
:
ab
d
el
a
l
i
.
za
k
ran
i
@
u
n
i
v
h
2
c.
ma.
M
o
ha
m
m
ed
A
m
r
a
o
u
y
h
o
l
d
s
a
Ph
.
D
.
i
n
co
m
p
u
t
er
s
ci
en
ce
s
at
N
at
i
o
n
al
In
s
t
i
t
u
t
e
o
f
Po
s
t
s
an
d
T
el
ec
o
mmu
n
i
ca
t
i
o
n
s
,
Rab
a
t
,
Mo
r
o
cco
i
n
2
0
2
3
.
H
e
i
s
cu
r
ren
t
l
y
a
p
e
d
ag
o
g
i
ca
l
i
n
s
p
ec
t
o
r
i
n
co
mp
u
t
er
s
c
i
en
ce
a
n
d
p
ar
t
-
t
i
me
t
rai
n
er
a
t
Reg
i
o
n
a
l
Cen
t
er
fo
r
E
d
u
cat
i
o
n
an
d
T
rai
n
i
n
g
Pro
fe
s
s
i
o
n
O
u
j
d
a,
Mo
ro
cc
o
.
H
i
s
res
earc
h
i
n
t
eres
t
s
fo
c
u
s
o
n
h
u
man
c
o
mp
u
t
e
r
i
n
t
eract
i
o
n
,
art
i
f
i
ci
a
l
i
n
t
el
l
i
g
en
ce
,
an
d
o
n
l
i
n
e
l
earn
i
n
g
as
s
es
s
men
t
.
H
e
can
b
e
c
o
n
t
act
e
d
at
emai
l
:
amrao
u
y
.
mo
h
amed
1
@
g
mai
l
.
co
m
.
Sa
i
d
N
o
uh
h
o
l
d
s
a
Ph
.
D
.
i
n
co
mp
u
t
er
s
c
i
en
ce
s
at
N
at
i
o
n
a
l
Sch
o
o
l
o
f
Co
mp
u
t
er
Sci
en
ce
an
d
Sy
s
t
em
s
A
n
a
l
y
s
i
s
(E
N
SIA
S),
Rab
a
t
,
Mo
ro
cco
i
n
2
0
1
4
.
H
e
i
s
cu
rre
n
t
l
y
p
ro
fe
s
s
o
r
(
H
i
g
h
er
D
eg
ree
Re
s
earch
(
H
D
R))
a
t
Facu
l
t
y
o
f
Sc
i
en
c
es
Ben
M’Si
c
k
,
H
a
s
s
a
n
II
U
n
i
v
ers
i
t
y
,
Cas
ab
l
an
ca,
Mo
ro
cc
o
.
H
i
s
cu
rre
n
t
res
earc
h
i
n
t
eres
t
s
are
art
i
fi
ci
al
i
n
t
e
l
l
i
g
e
n
ce,
mach
i
n
e
l
earn
i
n
g
,
d
ee
p
l
ear
n
i
n
g
,
t
el
ec
o
mmu
n
i
ca
t
i
o
n
s
,
i
n
fo
rma
t
i
o
n
,
an
d
c
o
d
i
n
g
t
h
eo
r
y
.
H
e
ca
n
b
e
co
n
t
act
e
d
at
emai
l
:
s
a
i
d
.
n
o
u
h
@
u
n
i
v
h
2
m.
ma.
A
bdel
l
a
h
Benna
ne
i
s
a
p
ro
fes
s
o
r
at
t
h
e
T
rai
n
i
n
g
Ce
n
t
er
o
f
T
each
i
n
g
In
s
p
ect
o
rs
,
an
d
mem
b
er
o
f
In
t
ern
a
t
i
o
n
a
l
Cen
t
er
o
f
A
ca
d
emi
c
s
Pe
d
ag
o
g
y
an
d
Man
a
g
emen
t
(Fac
u
l
t
y
o
f
E
d
u
cat
i
o
n
Sci
en
ce
s
,
U
n
i
v
er
s
i
t
y
Mo
h
amed
V
So
u
i
s
s
i
),
Rab
at
,
Mo
ro
cc
o
.
H
e
i
s
p
r
o
fes
s
i
o
n
al
i
n
ap
p
l
i
e
d
i
n
fo
rma
t
i
c
s
i
n
e
d
u
ca
t
i
o
n
s
ci
e
n
ce
s
.
H
i
s
rece
n
t
r
es
earch
i
s
e
-
l
ear
n
i
n
g
,
d
ev
e
l
o
p
men
t
o
f
the
t
each
i
n
g
s
o
f
t
w
are
an
d
u
s
e
o
f
mach
i
n
e
l
ear
n
i
n
g
t
ec
h
n
i
q
u
e
s
.
H
e
can
b
e
co
n
t
act
e
d
at
emai
l
:
ab
d
e
l
l
a
h
.
b
en
n
an
e@
g
ma
i
l
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.