T
E
L
KO
M
N
I
KA
T
e
lec
om
m
u
n
icat
ion
,
Com
p
u
t
i
n
g,
E
lec
t
r
on
ics
an
d
Cont
r
ol
Vol.
18
,
No.
3
,
J
une
2020
,
pp.
13
54
~
13
60
I
S
S
N:
1693
-
6930,
a
c
c
r
e
dit
e
d
F
ir
s
t
G
r
a
de
by
Ke
me
nr
is
tekdikti
,
De
c
r
e
e
No:
21/E
/KP
T
/2018
DO
I
:
10.
12928/
T
E
L
KO
M
NI
KA
.
v18i3.
14802
1354
Jou
r
n
al
h
omepage
:
ht
tp:
//
jour
nal.
uad
.
ac
.
id/
index
.
php/T
E
L
K
OM
N
I
K
A
Pr
e
d
ic
t
i
n
g
st
u
d
e
n
t
p
e
r
f
or
m
an
c
e
i
n
h
ig
h
e
r
e
d
u
c
at
io
n
u
si
n
g m
u
lti
-
r
e
gr
e
ssi
on
m
o
d
e
ls
L
e
o
Wil
lyan
t
o
S
an
t
os
o,
Yul
ia
I
nf
or
matics
De
pa
r
tm
e
nt
,
P
e
tr
a
C
hr
is
ti
a
n
Unive
r
s
it
y
S
ur
a
ba
ya
,
I
ndone
s
ia
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
J
ul
23
,
2019
R
e
vis
e
d
J
a
n
21
,
2020
Ac
c
e
pted
F
e
b
24
,
2020
Su
p
p
o
rt
i
n
g
t
h
e
g
o
al
o
f
h
i
g
h
er
ed
u
cat
i
o
n
t
o
p
r
o
d
u
ce
g
r
ad
u
a
t
i
o
n
w
h
o
w
i
l
l
b
e
a
p
ro
fes
s
i
o
n
a
l
l
ea
d
er
i
s
a
cru
c
i
al
.
Mo
s
t
o
f
u
n
i
v
er
s
i
t
i
e
s
i
mp
l
eme
n
t
i
n
t
e
l
l
i
g
e
n
t
i
n
f
o
rmat
i
o
n
s
y
s
t
em
(IIS)
t
o
s
u
p
p
o
rt
i
n
ach
i
ev
i
n
g
t
h
e
i
r
v
i
s
i
o
n
a
n
d
mi
s
s
i
o
n
.
O
n
e
o
f
t
h
e
feat
u
res
o
f
IIS
i
s
s
t
u
d
en
t
p
erfo
rma
n
ce
p
re
d
i
c
t
i
o
n
.
By
i
m
p
l
eme
n
t
i
n
g
d
at
a
m
i
n
i
n
g
mo
d
el
i
n
II
S,
t
h
i
s
fea
t
u
re
c
o
u
l
d
p
rec
i
s
e
l
y
p
re
d
i
c
t
t
h
e
s
t
u
d
en
t
’
g
rad
e
fo
r
t
h
e
i
r
en
r
o
l
l
ed
s
u
b
j
ec
t
s
.
Mo
re
o
v
er,
i
t
can
reco
g
n
i
ze
at
-
ri
s
k
s
t
u
d
en
t
s
an
d
al
l
o
w
t
o
p
e
d
u
ca
t
i
o
n
a
l
man
a
g
emen
t
t
o
t
ak
e
e
d
u
ca
t
i
v
e
i
n
t
erv
en
t
i
o
n
s
i
n
o
rd
er
t
o
s
u
ccee
d
acad
emi
cal
l
y
.
In
t
h
i
s
res
earc
h
,
mu
l
ti
-
reg
re
s
s
i
o
n
mo
d
el
w
as
p
ro
p
o
s
ed
t
o
b
u
i
l
d
mo
d
el
f
o
r
ev
ery
s
t
u
d
e
n
t
.
I
n
o
u
r
mo
d
el
,
l
earn
i
n
g
man
ag
eme
n
t
s
y
s
t
em
(L
MS)
act
i
v
i
t
y
l
o
g
s
w
ere
c
o
mp
u
t
e
d
.
Bas
ed
o
n
t
h
e
t
e
s
t
i
n
g
res
u
l
t
o
n
b
i
g
s
t
u
d
en
t
s
d
at
a
s
et
s
,
co
u
r
s
es
,
an
d
act
i
v
i
t
i
es
i
n
d
i
ca
t
es
t
h
a
t
t
h
es
e
m
o
d
e
l
s
co
u
l
d
i
m
p
ro
v
e
t
h
e
accu
rac
y
o
f
p
re
d
i
ct
i
o
n
m
o
d
e
l
b
y
o
v
er
1
5
%
.
K
e
y
w
o
r
d
s
:
Da
ta
mi
ning
E
duc
a
ti
on
M
ult
i
-
r
e
gr
e
s
s
ion
P
r
e
diction
S
tudent
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
:
L
e
o
W
il
lyanto
S
a
ntos
o
,
I
nf
or
matics
De
pa
r
tm
e
nt
,
P
e
tr
a
C
hr
is
ti
a
n
Unive
r
s
it
y
S
ur
a
ba
ya
,
121
-
131
S
iwa
lanke
r
to
S
t.
,
S
ur
a
ba
ya
,
E
a
s
t
J
a
va
60236
,
I
ndone
s
ia.
E
mail:
leow
@pe
tr
a
.
a
c
.
id
1.
I
NT
RODU
C
T
I
ON
E
duc
a
ti
on
is
a
ke
y
to
e
nding
the
pove
r
ty
in
de
ve
lopi
ng
c
ountr
ies
.
E
duc
a
ti
on
ha
s
powe
r
to
c
ha
nge
the
pe
ople,
c
omm
unit
ies
,
na
ti
on
a
nd
human
li
f
e
.
T
he
gove
r
nment
s
hould
pa
y
mor
e
a
tt
e
nti
on
to
the
q
ua
li
ty
of
e
duc
a
ti
on.
E
duc
a
ti
on
is
the
r
e
s
pons
ibi
li
ty
o
f
t
he
st
a
ke
holder
s
including
gove
r
nment
o
f
f
icia
l,
pa
r
e
nt,
a
nd
tea
c
he
r
.
E
duc
a
ti
on
s
hould
be
mana
ge
d
thr
o
ugh
na
ti
ona
l
r
e
s
our
c
e
s
.
F
ur
ther
mo
r
e
,
higher
e
duc
a
ti
on
is
im
por
tant
f
or
s
oc
ial
a
nd
e
c
onomi
c
im
pa
c
ts
in
s
oc
iety.
T
he
ge
ne
r
a
l
mi
s
s
ion
of
higher
e
duc
a
ti
on
ins
ti
tut
ion
is
to
pr
oduc
e
s
tudent
gr
a
dua
ti
on
who
will
be
a
pr
o
f
e
s
s
ional
lea
de
r
s
in
their
f
ield
a
nd
va
luable
f
o
r
their
c
om
muni
ti
e
s
a
nd
c
ountr
y.
T
o
a
c
hieve
thi
s
mi
s
s
ion,
higher
e
duc
a
ti
on
ins
ti
tut
ion
s
hould
im
pr
ove
their
qua
li
ty
of
e
duc
a
ti
on.
T
he
r
e
a
r
e
s
e
ve
r
a
l
f
a
c
tor
s
a
f
f
e
c
ted
the
qua
li
ty
of
e
duc
a
ti
on.
T
he
high
leve
l
of
s
tudent
s
uc
c
e
s
s
a
nd
lo
w
f
a
il
ur
e
r
a
te
s
tudents
c
an
r
e
f
lec
t
the
qua
li
ty
of
e
duc
a
ti
on
.
One
of
the
major
pr
oblems
of
h
igher
e
duc
a
ti
on
in
the
de
ve
lopi
ng
c
ountr
y
,
li
ke
I
ndone
s
ia
is
the
hi
gh
r
a
tes
o
f
s
tudent
dr
op
out
that
ha
s
r
e
a
c
he
d
10%
.
Anothe
r
r
e
late
d
pr
oblem
is
the
long
ti
me
t
ha
t
a
s
tudent
take
s
to
c
ompl
e
te
their
de
gr
e
e
.
Now
a
da
ys
,
inf
or
mation
tec
hnology
is
c
ons
ider
e
d
a
s
im
por
tant
f
a
c
tor
to
im
pr
ove
the
qua
li
ty
of
e
duc
a
ti
on.
T
h
i
s
i
s
t
h
e
r
e
a
s
o
n
w
h
y
m
a
n
y
u
n
i
v
e
r
s
i
t
i
e
s
a
r
e
i
n
v
e
s
t
i
n
g
a
l
o
t
o
f
b
u
d
g
e
t
t
o
i
m
p
r
o
v
e
t
h
e
i
r
a
c
a
d
e
m
i
c
i
n
f
o
r
m
a
t
i
o
n
s
y
s
t
e
m
[
1
].
E
duc
a
ti
ona
l
da
ta
mi
ning
(
E
DM
)
ha
s
e
mer
ge
d
i
n
the
las
t
de
c
a
de
s
due
to
the
la
r
ge
volum
e
of
e
duc
a
ti
ona
l
da
ta
that
wa
s
made
a
va
il
a
ble
[
2,
3]
.
I
t
is
c
onc
e
r
ne
d
with
de
ve
lopi
ng
a
nd
a
pplyi
ng
da
ta
mi
ning
a
lgor
it
hms
to
identif
y
pa
tt
e
r
ns
in
lar
ge
a
moun
ts
o
f
e
duc
a
ti
ona
l
da
ta,
a
nd
to
be
tt
e
r
unde
r
s
tand
s
tudents
a
nd
their
lea
r
ning
e
nvir
onments
[
4
-
7]
.
M
or
e
ove
r
,
da
ta
mi
ni
ng
a
nd
da
ta
wa
r
e
hous
ing
tec
hnique
ha
ve
be
e
n
incr
e
a
s
ingl
y
im
pleme
nted
in
the
a
c
a
de
mi
c
inf
o
r
mation
s
ys
tem
to
a
na
lyze
the
va
s
t
a
mount
s
of
s
tude
nt
da
ta
[
8
,
9]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KO
M
NI
KA
T
e
lec
omm
un
C
omput
E
l
C
ontr
o
l
P
r
e
dicting
s
tudent
pe
r
for
manc
e
in
higher
e
duc
ati
on
…
(
L
e
o
W
il
lyanto
Santos
o
)
1355
Da
ta
mi
ning
is
a
tool
to
im
pr
ove
the
qua
li
ty
of
e
d
uc
a
ti
on
by
identif
ying
the
s
tudents
who
a
r
e
a
t
r
is
k
in
their
s
tudy
[
10
-
1
2
]
.
T
his
in
f
or
mation
is
ve
r
y
us
e
f
ul
f
or
t
op
leve
l
mana
ge
ment
to
take
a
ppr
opr
iate
a
c
ti
on
f
or
s
tudents
who
a
r
e
c
ons
ider
e
d
to
ha
ve
a
higher
pr
oba
bil
it
y
of
f
a
il
ing
a
c
a
de
mi
c
a
ll
y
or
d
r
opping
out
of
u
niver
s
it
y.
T
he
univer
s
it
y
c
ould
pr
ovide
a
ddit
ional
s
e
r
vice
s
a
n
d
r
e
s
our
c
e
s
to
the
at
-
r
is
k
s
tudents
[
1
3,
14
]
.
I
n
a
ddit
i
on,
they
ne
e
d
to
de
ve
lop
innovative
a
pp
r
oa
c
he
s
to
r
e
tain
s
t
ude
nts
,
e
ns
ur
e
that
they
g
r
a
dua
te
on
a
ti
mely
mann
e
r
[
15]
.
S
ome
tec
hniques
ha
ve
be
e
n
de
ve
loped
to
a
ddr
e
s
s
thi
s
is
s
ue
.
How
e
ve
r
,
thes
e
a
ppr
oa
c
he
s
ignor
e
the
dif
f
e
r
e
nt
f
e
a
tur
e
s
of
how
s
tudents
wor
k
togethe
r
with
the
mate
r
ial/
L
M
S
’
pr
ovided
inf
o
r
mation,
whi
c
h
c
ould
pos
s
ibl
y
be
us
e
d
to
incr
e
a
s
e
ove
r
a
ll
a
c
c
ur
a
tene
s
s
of
p
r
e
diction
.
I
n
th
is
r
e
s
e
a
r
c
h,
s
ingl
e
r
e
gr
e
s
s
ion
m
ode
l
a
nd
mul
ti
r
e
gr
e
s
s
ion
model
w
e
r
e
im
pleme
nted
a
nd
inv
e
s
ti
ga
ted.
T
his
model
c
ould
pr
e
dict
the
s
tudents
’
gr
a
de
by
mi
ning
dif
f
e
r
e
nt
c
our
s
e
a
c
ti
vit
ies
log
(
e
.
g
.
,
tes
ts
a
nd
a
s
s
ignm
e
nts
)
in
lea
r
ning
mana
ge
ment
s
ys
tem.
An
e
a
r
ly
wa
r
ning
s
ys
tem
ge
ne
r
a
tes
e
a
r
ly
wa
r
nings
a
bout
s
t
r
uggli
ng
s
tudents
who
a
r
e
mos
t
li
ke
ly
to
f
a
il
e
d
a
c
our
s
e
or
dr
op
out
of
univer
s
it
y
.
I
t
is
s
uppos
e
d
to
ge
ne
r
a
te
th
e
s
e
wa
r
nings
e
a
r
l
y
e
nough
in
or
de
r
to
a
ll
ow
f
or
int
e
r
ve
nti
on
by
of
f
e
r
ing
s
uit
a
ble
a
s
s
is
tanc
e
f
or
the
s
tudents
that
a
r
e
a
t
r
is
k.
T
his
s
ys
tem
wor
ks
by
p
r
e
dicting
a
s
tudent’
s
pe
r
f
or
manc
e
in
the
lea
r
ning
a
c
ti
vit
ies
(
e
.
g.
,
a
s
s
ignm
e
nts
)
withi
n
a
c
our
s
e
that
they
a
r
e
e
nr
oll
e
d
in
.
T
he
y
a
ls
o
pr
e
dict
the
s
tudent’
s
fi
na
l
g
r
a
de
in
a
c
our
s
e
that
the
y
a
r
e
e
nr
o
ll
e
d
in
,
o
r
in
c
our
s
e
s
that
they
wil
l
take
in
the
ne
xt
s
e
mes
ter
to
f
ulfi
ll
their
p
r
ogr
a
m
r
e
quir
e
ments
.
W
he
n
s
tudents
fi
r
s
t
e
nr
oll
in
a
un
iver
s
it
y,
their
u
niver
s
it
y
ge
t
the
da
ta
a
bout
t
he
ir
pe
r
f
or
manc
e
in
va
r
ious
high
s
c
hool
s
ubjec
ts
,
tes
t
a
c
a
de
mi
c
po
tential,
a
nd
de
mogr
a
phics
.
As
the
s
tudents
pr
oc
e
e
d
w
it
h
their
a
c
a
de
mi
c
s
tudi
e
s
,
mor
e
da
ta
a
r
e
c
oll
e
c
ted.
T
he
c
oll
e
c
ted
da
ta
li
ke
the
s
tudent
tr
a
ns
c
r
ipt
a
nd
e
nr
oll
e
d
c
our
s
e
s
.
T
he
s
tudents
c
a
n
a
ls
o
a
c
c
e
s
s
onli
ne
lea
r
ning
mana
ge
ment
s
ys
tem
(
L
M
S
)
,
s
uc
h
a
s
M
oodle,
E
dmodo,
E
li
a
de
mi
,
AT
utor
or
B
lac
kB
oa
r
d,
a
t
whic
h
they
ge
t
a
c
c
e
s
s
to
the
c
our
s
e
mate
r
ials
.
T
hr
ough
the
L
M
S
,
s
tudents
c
a
n
a
ls
o
e
nga
ge
in
f
or
um
dis
c
us
s
ions
,
c
ontr
ibut
e
to
the
c
our
s
e
c
ontent
,
e
nga
ge
in
c
our
s
e
a
c
ti
vit
ies
s
uc
h
a
s
onli
ne
quizz
e
s
,
a
nd
do
o
ther
tas
ks
.
I
n
thi
s
r
e
s
e
a
r
c
h,
lar
ge
da
tas
e
t
wa
s
e
xtr
a
c
ted
f
r
om
the
P
e
tr
a
C
hr
is
ti
a
n
Uni
ve
r
s
it
y’
s
L
M
S
.
T
he
na
me
of
P
e
tr
a
C
hr
is
ti
a
n
Unive
r
s
it
y
L
M
S
is
L
e
nter
a
,
ba
s
e
d
on
M
oodle
[
1
6
]
.
T
his
da
tas
e
t
c
on
tains
486
c
our
s
e
s
,
7,
563
s
tudents
,
a
nd
109,
231
a
c
ti
vit
ies
.
T
he
im
por
tant
c
ontr
ibut
ions
of
thi
s
pa
pe
r
a
r
e
a
s
f
oll
ows
:
(
1)
T
he
de
s
igned
s
ys
tem
c
a
n
c
lus
ter
/s
e
gment
the
s
tudents
int
o
gr
oups
whos
e
pr
e
diction
models
a
r
e
r
e
latively
s
im
il
a
r
.
B
y
e
xplor
ing
thes
e
s
tudent’
gr
oups
,
knowle
dge
on
the
f
a
c
tor
s
that
de
ter
m
ine
the
s
tuden
ts
’
pe
r
f
or
manc
e
a
r
e
ga
ined.
(
2)
T
he
pr
opos
e
d
r
e
c
o
mm
e
nde
r
s
ys
tem
pr
ovides
s
olut
ion
to
im
pr
ove
the
e
duc
a
ti
on
qua
li
ty
us
ing
c
utt
ing
e
dge
tec
hnology
.
T
he
r
e
s
t
of
t
he
pa
pe
r
is
or
ga
nize
d
a
s
f
oll
ows
:
s
e
c
ti
on
2
de
s
c
r
ibes
the
li
ter
a
tur
e
r
e
view
.
S
e
c
ti
on
2
de
s
c
r
ibes
the
mul
ti
-
r
e
gr
e
s
s
ion
model
t
h
a
t
w
e
u
s
e
d
.
S
e
c
t
i
o
n
2
d
e
s
c
r
i
b
e
s
t
h
e
d
a
t
a
s
e
t
t
h
a
t
w
e
u
s
e
d
a
l
o
n
g
w
i
t
h
t
h
e
v
a
r
i
o
u
s
f
e
a
t
u
r
e
s
t
h
a
t
w
e
e
x
t
r
a
c
t
e
d
.
S
e
c
t
i
o
n
3
p
r
o
v
i
d
e
s
t
h
e
i
n
v
e
s
t
i
g
a
t
i
o
n
a
l
e
v
a
l
u
a
t
i
o
n
a
n
d
a
n
a
l
y
s
i
s
o
f
t
h
e
r
e
s
u
l
t
s
.
F
i
n
a
l
l
y
,
s
e
c
t
i
o
n
4
c
o
n
c
l
u
d
e
s
t
h
i
s
r
e
s
e
a
r
c
h
.
2.
RE
S
E
AR
CH
M
E
T
HO
D
I
de
nti
f
ying
a
t
-
r
is
k
s
tudents
f
or
taking
a
ppr
opr
ia
te
a
c
ti
ons
c
a
n
be
a
ddr
e
s
s
e
d
thr
ough
e
va
luating
c
oll
e
c
ted
s
tudents
’
a
c
a
de
mi
c
pe
r
f
or
manc
e
da
ta.
De
c
is
ion
tr
e
e
tec
hnique
wa
s
im
pleme
nted
to
e
xplain
the
pr
ope
r
ti
e
s
int
e
r
de
pe
nde
nc
ies
of
d
r
op
out
s
tudents
[
1
7
]
.
T
his
s
tudy
a
ls
o
o
f
f
e
r
s
an
e
xa
mpl
e
of
h
ow
da
ta
mi
ning
tec
hnique
c
a
n
be
us
e
d
to
incr
e
a
s
e
the
e
f
f
e
c
ti
ve
ne
s
s
a
nd
e
f
f
icie
nc
y
o
f
the
modeling
pr
oc
e
s
s
es
.
De
kke
r
e
xplaine
d
a
da
ta
-
mi
ning
c
a
s
e
s
tudy
de
mons
tr
a
ti
ng
the
us
e
f
ulnes
s
of
s
e
ve
r
a
l
c
las
s
if
ica
ti
on
methods
a
nd
the
c
os
t
-
s
e
n
s
it
ive
lea
r
ning
a
ppr
oa
c
h
[
1
8
]
.
I
n
thi
s
s
ys
tem,
c
os
t
-
s
e
n
s
it
ive
lea
r
ning
doe
s
he
lp
to
b
ias
c
las
s
if
ica
ti
on
e
r
r
or
s
towa
r
ds
p
r
e
f
e
r
r
ing
f
a
ls
e
pos
it
ives
to
f
a
ls
e
ne
ga
ti
ve
s
.
Optim
iza
ti
on
s
hould
be
done
to
im
p
r
ove
th
e
s
ys
tem.
P
r
e
dictive
a
na
lyt
ic
tec
hnique
c
ould
be
int
e
gr
a
ted
with
lea
r
ning
mana
ge
ment
s
ys
tem
(
L
M
S
)
to
identi
f
y
s
tudents
who
a
r
e
in
da
nge
r
of
f
a
il
ing
the
c
our
s
e
in
whic
h
they
a
r
e
c
ur
r
e
ntl
y
e
nr
oll
e
d
[
1
9
]
.
L
e
a
r
ning
a
na
lyt
ic
is
c
ons
ider
e
d
c
a
n
s
uppor
t
s
tudent
s
,
lec
tur
e
r
s
a
nd
e
duc
a
ti
ona
l
mana
ge
r
s
to
pr
e
dict
c
our
s
e
f
a
il
ur
e
[
20
]
.
L
e
a
r
ning
a
na
lyt
ic
be
a
ble
to
s
uppor
t
ins
tr
uc
ti
ona
l
mate
r
ial
de
s
igner
s
to
be
tt
e
r
mea
s
ur
e
the
qua
li
ty
of
a
c
our
s
e
de
s
ign
a
nd
unde
r
s
tand
wha
t
wor
ks
a
nd
wha
t
doe
s
not
wo
r
k
[
2
1,
22
]
.
M
or
e
ove
r
,
l
e
a
r
ning
a
na
lyt
ic
c
a
n
incr
e
a
s
e
e
va
luation
of
s
tudent
pe
r
f
or
manc
e
by
inves
ti
ga
ti
ng
va
r
ious
ind
ica
tor
s
s
uc
h
a
s
s
tudent
a
c
ti
vit
ies
a
nd
gr
a
de
s
on
a
s
s
ig
nments
.
Da
ta
mi
ning
tec
hniques
f
or
c
a
tegor
izing
univer
s
it
y
s
tudents
ba
s
e
d
on
M
oodle’
us
a
ge
da
ta
in
a
l
e
a
r
ni
ng
mana
ge
ment
s
ys
tem
a
nd
the
f
inal
mar
ks
a
c
hieve
d
in
the
c
our
s
e
wa
s
im
pleme
nted
[
23
]
.
T
he
pr
opos
e
d
s
ys
tem
us
e
s
pr
e
pr
oc
e
s
s
ing
tas
ks
a
s
dis
c
r
e
ti
z
a
ti
on
a
nd
r
e
ba
lanc
ing
da
ta.
T
he
a
uthor
s
hould
c
ons
ider
how
the
da
ta
qua
nti
ty
a
nd
da
ta
qua
li
ty
c
a
n
i
mpac
t
the
pe
r
f
or
man
c
e
of
the
a
lgor
it
hms
.
I
n
f
or
mation
with
mo
r
e
e
viden
c
e
a
bout
the
s
tudents
,
li
ke
s
tudent
pr
o
f
il
e
a
nd
s
e
t
of
c
ou
r
s
e
s
s
hould
be
incor
por
a
ted.
T
e
ns
or
f
a
c
tor
iza
ti
on
tec
hniques
f
or
pr
e
dicting
s
tudent
pe
r
f
or
manc
e
wa
s
pr
opos
e
d
[
24
]
.
T
he
a
utho
r
int
r
oduc
e
s
a
nove
l
r
e
c
omm
e
nde
r
s
ys
tem
whic
h
c
a
n
be
us
e
d
not
only
f
or
r
e
c
omm
e
nding
obj
e
c
ts
li
ke
tas
ks
/exe
r
c
is
e
s
to
the
s
tudents
but
a
ls
o
f
or
pr
e
dic
ti
ng
s
tudent
pe
r
f
or
manc
e
.
T
he
pr
e
diction
r
e
s
ult
s
c
ould
be
im
pr
ove
d
by
a
pplyi
ng
mor
e
s
ophis
ti
c
a
ted
methods
to
de
a
l
with
the
c
old
-
s
tar
t
pr
ob
lems
a
nd
buil
d
ing
e
ns
e
mbl
e
methods
on
dif
f
e
r
e
nt
models
ge
ne
r
a
ted
f
r
om
matr
i
x
a
nd
tens
or
f
a
c
to
r
iza
ti
on.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
1693
-
6930
T
E
L
KO
M
NI
KA
T
e
lec
omm
un
C
omput
E
l
C
ontr
o
l
,
Vol.
18
,
No
.
3
,
J
une
2020:
13
54
-
13
60
1356
S
e
v
e
r
a
l
f
a
c
t
o
r
s
e
f
f
e
c
t
i
n
g
t
h
e
a
c
c
o
m
p
l
i
s
h
m
e
n
t
o
f
t
h
e
f
r
e
s
h
m
a
n
s
t
u
d
e
n
t
s
w
a
s
d
e
t
e
r
m
i
n
e
d
[
2
5
].
T
he
de
ve
loped
s
ys
tem
c
a
n
c
la
s
s
if
y
s
tudent
s
int
o
thr
e
e
gr
oups
:
‘
low
-
r
is
k’
s
tudents
,
with
a
high
pr
ob
a
bil
it
y
of
s
uc
c
e
e
ding;
‘
medium
-
r
is
k’
s
tudents
,
who
may
s
uc
c
e
e
d;
a
nd
‘
high
-
r
is
k’
s
tudents
,
who
ha
ve
a
high
pr
oba
bil
it
y
of
dr
opping
out
.
How
e
ve
r
,
the
c
omb
ination
of
dif
f
e
r
e
nt
pr
e
diction
methods
ha
ve
n
ot
be
e
n
a
ddr
e
s
s
e
d.
T
his
c
ombi
na
ti
on
may
lea
d
to
the
im
pr
ove
ment
of
the
ove
r
a
ll
r
e
s
ult
.
W
it
h
lar
ge
volum
e
s
of
s
tudent
da
ta,
including
e
nr
oll
ment,
a
c
a
de
mi
c
a
nd
dis
c
ipl
inar
y
r
e
c
or
ds
,
higher
e
duc
a
ti
on
ins
ti
tut
ion
c
ould
buil
d
big
da
ta
a
nd
a
na
lyt
ics
s
ys
tem
[
26]
.
B
ig
d
a
ta
c
a
n
pr
ovide
top
leve
l
man
a
ge
ment
the
ne
e
de
d
a
na
lyt
ica
l
tool
s
to
im
pr
ove
lea
r
ning
output
f
or
indi
v
idual
s
tudents
a
s
we
ll
wa
ys
gua
r
a
ntee
ing
a
c
a
de
mi
c
pr
ogr
a
mm
e
s
a
r
e
of
high‐
qua
li
ty
s
tanda
r
ds
[
2
7
]
.
B
y
de
s
igni
ng
a
ppli
c
a
ti
ons
that
ga
ther
da
ta
a
t
e
ve
r
y
pha
s
e
of
the
s
tudents
lea
r
ning
pr
oc
e
s
s
e
s
,
univer
s
it
ies
c
a
n
a
ddr
e
s
s
s
tudent
ne
e
ds
with
c
us
tom
ize
d
modul
e
s
,
f
e
e
dba
c
k,
a
nd
a
s
s
ignm
e
nts
in
the
s
yll
a
bus
that
will
s
ti
mul
a
te
be
tt
e
r
a
nd
r
iche
r
lea
r
ning
.
I
n
thi
s
r
e
s
e
a
r
c
h,
we
inves
ti
ga
te
the
li
ne
a
r
mul
ti
-
r
e
gr
e
s
s
i
on
models
to
f
or
e
c
a
s
t
the
s
tudents
’
pe
r
f
or
manc
e
a
t
va
r
iou
s
c
our
s
e
a
c
ti
vit
ies
in
L
M
S
.
2.
1
.
De
s
ign
I
n
thi
s
pa
r
t,
the
pr
opos
e
d
model
f
o
r
p
r
e
diction
s
tude
nt
pe
r
f
o
r
manc
e
will
be
dis
c
us
s
e
d.
T
his
model
us
e
s
mul
ti
-
r
e
gr
e
s
s
ion
model
[
2
8
,
2
9]
.
M
ult
i
-
r
e
gr
e
s
s
ion
is
a
n
e
xtens
ion
of
s
im
ple
li
ne
a
r
r
e
gr
e
s
s
ion.
As
a
p
r
e
dictive
a
na
lys
is
,
the
mul
ti
-
r
e
gr
e
s
s
ion
is
us
e
d
to
e
xplain
th
e
r
e
lations
hip
be
twe
e
n
de
pe
nde
nt
va
r
iable
a
n
d
t
w
o
o
r
m
o
r
e
i
n
d
e
p
e
n
d
e
n
t
v
a
r
i
a
b
l
e
s
.
I
n
t
h
i
s
m
o
d
e
l
,
t
h
e
g
r
a
d
e
g
s
,
a
f
o
r
s
t
u
d
e
n
t
s
i
n
a
c
t
i
v
i
t
i
e
s
a
i
s
f
o
r
m
u
l
a
t
e
d
as
(
1
)
.
=
=
+
+
=
+
+
=
t
d
k
d
n
k
k
sa
d
s
c
s
sa
t
s
c
s
sa
w
f
p
b
b
Wf
b
b
g
f
p
1
,
1
,
,
)
(
(
1)
whe
r
e
:
b
s
=
s
tudent
bias
ter
ms
b
c
=
c
our
s
e
bias
ter
ms
f
sa
=
ve
c
tor
that
s
tor
e
s
the
input
f
e
a
tur
e
s
l
=
tot
a
l
of
li
ne
a
r
r
e
gr
e
s
s
ion
models
W
=
matr
ix
that
s
tor
e
s
the
c
oe
ffi
c
ients
of
li
ne
a
r
r
e
gr
e
s
s
ion
p
s
=
ve
c
tor
that
s
tor
e
s
the
membe
r
s
hips
of
s
tudent
s
w
d
,
k
=
we
ight
ed
f
e
a
tur
e
k
unde
r
the
d
th
r
e
gr
e
s
s
ion
mode
l
p
s
,
d
=
s
tudent
membe
r
s
hip
s
in
the
d
th
r
e
gr
e
s
s
ion
model
T
he
pe
r
f
or
manc
e
c
ompar
is
on
be
twe
e
n
a
mul
ti
-
r
e
gr
e
s
s
ion
model
a
c
r
os
s
a
li
ne
a
r
r
e
gr
e
s
s
ion
model
wa
s
pr
e
s
e
nted
.
T
he
a
ppr
oxi
mation
of
univer
s
it
y
s
tudent
gr
a
de
us
ing
li
ne
a
r
r
e
gr
e
s
s
ion
model
as
;
=
+
=
f
n
k
k
k
sa
f
w
w
g
1
0
(
2)
whe
r
e
f
k
is
the
r
a
te
of
k
a
nd
the
w
k
’
s
a
r
e
the
r
e
g
r
e
s
s
ion
c
oe
ffi
c
ients
.
I
n
F
ig
ur
e
1
c
a
n
be
s
e
e
n
the
f
low
diagr
a
m
of
a
ppli
c
a
ti
on
de
s
ign
pr
oc
e
s
s
.
T
he
ini
t
ial
s
tage
is
c
oll
e
c
ti
ng
da
ta
,
then
s
e
lec
ti
ng
da
ta.
S
e
lec
ti
on
of
da
ta
is
ne
e
de
d
,
i
f
ther
e
is
mi
s
s
ing
va
lue
da
ta,
the
da
ta
will
be
dis
c
a
r
de
d.
Af
ter
doing
da
ta
c
lea
ns
ing,
then
the
da
ta
is
divi
de
d
int
o
two
na
mely
the
t
r
a
ini
ng
da
ta
a
nd
tes
t
d
a
ta
with
the
pe
r
c
e
ntage
of
e
a
c
h
70%
f
o
r
t
r
a
ini
ng
da
ta
a
nd
30
%
f
o
r
the
tes
t
da
ta.
T
he
tr
a
ini
ng
da
ta
c
ons
is
ts
of
pr
e
r
e
quis
it
e
va
lue
a
s
a
p
r
e
dictor
va
r
iable
a
nd
p
r
e
de
ter
mi
ne
d
va
l
ue
a
s
a
r
e
s
pons
e
va
r
iable
.
T
e
s
t
da
ta
jus
t
a
s
the
tr
a
in
ing
da
ta
c
ontains
s
o
me
pr
e
r
e
quis
it
e
a
nd
pr
e
de
ter
mi
ne
d
va
lu
e
.
W
e
us
e
d
a
da
tas
e
t
e
xtr
a
c
ted
f
r
o
m
the
P
e
tr
a
C
hr
is
ti
a
n
Unive
r
s
it
y’
M
oodle.
T
he
main
pa
ge
of
P
e
tr
a
C
hr
is
ti
a
n
Unive
r
s
it
y’
M
oodle
c
a
n
be
s
e
e
n
in
F
i
g
ur
e
2.
T
he
da
tas
e
t
s
pa
ns
f
our
s
e
mes
ter
s
a
nd
it
c
ontains
486
c
our
s
e
s
,
7
,
563
s
tudents
,
a
nd
109
,
231
a
c
ti
vit
ies
.
T
he
c
our
s
e
s
be
long
to
21
diffe
r
e
nt
s
c
hools
;
e
a
c
h
u
niver
s
it
y
s
tudent
ha
s
r
e
gis
ter
e
d
in
a
r
ound
5
c
our
s
e
s
.
I
n
thi
s
r
e
s
e
a
r
c
h,
the
a
c
ti
vit
ies
r
e
f
e
r
to
the
a
s
s
ignm
e
nts
a
n
d
quizz
e
s
i
n
L
e
nter
a
.
F
or
e
a
c
h
s
tudent
-
a
c
ti
vit
y
pa
ir
(
s
,
a
)
,
f
e
a
tur
e
ve
c
tor
f
sa
is
c
ons
tr
uc
ted.
T
he
r
e
a
r
e
th
r
e
e
c
a
tegor
ies
:
s
tudent
-
c
e
nt
e
r
e
d
f
e
a
tur
e
s
,
a
c
ti
vit
y
-
c
e
nter
e
d
f
e
a
tur
e
s
a
nd
L
e
nter
a
int
e
r
a
c
ti
on
f
e
a
tur
e
s
.
S
tudent
-
c
e
nter
e
d
f
e
a
tur
e
s
a
r
e
f
e
a
tur
e
s
r
e
late
d
to
the
s
tudent.
T
he
r
e
a
r
e
two
c
a
tegor
ies
:
-
GPA_tot
a
l:
T
he
nu
mber
o
f
gr
a
de
s
point
s
a
s
tudent
e
a
r
ne
d
in
a
given
pe
r
iod
o
f
ti
me.
-
Gr
a
de
_tot
a
l:
T
he
a
ve
r
a
ge
g
r
a
de
a
c
c
ompl
is
he
d
ove
r
the
e
nti
r
e
ly
of
the
pa
s
t
e
xe
r
c
is
e
in
the
c
our
s
e
.
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KO
M
NI
KA
T
e
lec
omm
un
C
omput
E
l
C
ontr
o
l
P
r
e
dicting
s
tudent
pe
r
for
manc
e
in
higher
e
duc
ati
on
…
(
L
e
o
W
il
lyanto
Santos
o
)
1357
F
igur
e
1.
T
he
F
low
d
iagr
a
m
of
a
ppli
c
a
ti
on
de
s
ign
F
igur
e
2
.
T
he
main
pa
ge
o
f
L
e
nter
a
Ac
ti
vit
y
-
c
e
nter
e
d
f
e
a
tur
e
s
a
r
e
f
e
a
tur
e
s
that
r
e
late
to
the
a
c
ti
vit
y
o
f
s
tudent
in
the
L
e
nter
a
L
M
S
.
F
ig
ur
e
3
de
s
c
r
ibes
the
l
is
t
of
a
c
ti
vit
ies
in
L
e
nter
a
.
T
he
r
e
a
r
e
th
r
e
e
c
a
tegor
ies
:
-
Ac
ti
vit
y_type
:
a
c
ti
vit
y
of
s
tudent
in
or
de
r
to
int
e
r
a
c
t
with
other
s
tudent
or
tea
c
he
r
in
L
e
nter
a
,
T
his
c
a
n
e
it
he
r
be
quiz
or
a
s
s
ignm
e
nt.
-
C
our
s
e
_leve
l:
T
he
dif
f
iculty
leve
l
of
c
our
s
e
.
T
he
r
a
nge
of
va
lue
is
1,
2,
3
a
nd
4.
Va
lue
1
mea
ns
the
dif
f
iculty
of
c
our
s
e
is
ve
r
y
l
ow.
-
De
pa
r
tm
e
nt:
T
he
de
pa
r
t
ment
who
o
f
f
e
r
the
c
our
s
e
.
L
e
nter
a
-
c
e
nter
e
d
f
e
a
tur
e
s
de
s
c
r
ibe
the
s
tudent’
s
i
nter
a
c
ti
on
with
L
e
nter
a
pr
io
r
to
the
due
da
te
o
f
the
quizz
e
s
a
nd
a
s
s
ignm
e
nts
.
T
he
s
e
f
e
a
tur
e
s
we
r
e
e
xtr
a
c
ted
f
r
om
L
e
nter
a
’
s
log
fi
les
a
nd
a
r
e
the
f
oll
o
win
g:
-
D
is
c
us
s
_tot
a
l
:
the
number
o
f
dis
c
us
s
ion
that
pos
ted
by
s
tudent.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
1693
-
6930
T
E
L
KO
M
NI
KA
T
e
lec
omm
un
C
omput
E
l
C
ontr
o
l
,
Vol.
18
,
No
.
3
,
J
une
2020:
13
54
-
13
60
1358
-
log_t
otal:
f
r
e
que
nc
y
of
the
s
tudent
logi
n
to
the
L
e
nter
a
-
ti
me_total:
tot
a
l
a
mount
of
ti
me
s
pe
nt
be
twe
e
n
logi
n
a
nd
logout
-
r
e
a
d
_to
t
a
l:
t
he
number
of
dis
c
us
s
ions
’
f
or
um
that
a
r
e
de
li
ve
r
e
d
by
the
s
tudent.
-
view
e
d
_tot
a
l
:
t
he
number
of
t
im
e
s
the
s
tudent
vie
we
d
r
e
late
d
mate
r
ial.
T
he
da
tas
e
t
wa
s
divi
de
d
int
o
two
s
ubs
e
ts
,
na
mely
tr
a
ini
ng
a
nd
tes
t
ing
s
ubs
e
ts
c
ompr
is
ing
7
0%
a
nd
30%
of
the
da
tas
e
t
r
e
s
pe
c
ti
ve
ly.
T
he
pr
opos
e
d
mo
de
l
wa
s
tr
a
ined
on
the
tr
a
ini
ng
da
ta
s
e
t
s
a
nd
then
e
va
luate
d
on
the
tes
t
ing
da
ta
s
e
t
s
.
T
his
e
va
luation
pr
oc
e
s
s
wa
s
r
e
it
e
r
a
ted
5
ti
mes
a
nd
the
a
c
quir
e
d
r
e
s
ult
s
on
the
tes
t
da
ta
s
e
t
s
we
r
e
c
a
lcula
ted.
T
he
r
o
ot
mea
n
s
qua
r
e
d
e
r
r
or
(
R
M
S
E
)
wa
s
us
e
d
to
a
s
s
e
s
s
the
pr
opos
e
d
model.
I
t
mea
s
ur
e
s
the
dif
f
e
r
e
nc
e
be
twe
e
n
the
a
c
tual
a
nd
pr
e
dicte
d
gr
a
de
s
on
the
tes
t
da
ta
s
e
t
s
.
F
igur
e
3.
Ac
ti
vit
ies
in
L
e
nter
a
3.
RE
S
E
AR
CH
F
I
ND
I
NGS
A
ND
AN
AL
YSI
S
Th
is
s
e
c
ti
on
pr
e
s
e
nts
the
r
e
s
e
a
r
c
h
f
indi
ngs
a
nd
a
na
lys
is
.
M
or
e
ove
r
,
the
pe
r
f
or
manc
e
c
ompar
is
on
be
twe
e
n
mul
ti
-
r
e
gr
e
s
s
ion
model
a
nd
s
ingl
e
r
e
gr
e
s
s
ion
a
r
e
dis
c
us
s
e
d.
F
ig
ur
e
4
s
hows
the
s
tatis
ti
c
s
in
L
e
nter
a
.
I
t
s
hows
the
number
of
a
c
ti
ve
c
ou
r
s
e
s
,
s
tudents
a
n
d
a
c
ti
vit
ies
i
n
L
e
nter
a
.
T
he
c
or
r
e
lation
be
twe
e
n
a
c
ti
vit
ies
in
L
e
nter
a
(
int
e
r
a
c
ti
on
be
twe
e
n
s
tudents
with
the
L
e
nter
a
f
e
a
tur
e
s
)
a
nd
the
pr
e
dicte
d
gr
a
de
s
is
dis
c
us
s
e
d
.
T
o
ge
t
the
be
tt
e
r
r
e
s
ult
,
the
mul
ti
-
r
e
gr
e
s
s
ion
models
a
nd
t
he
ba
s
e
li
ne
model
we
r
e
tr
a
ined
2
ti
mes
.
F
ig
u
re
5
s
hows
the
gr
a
phic
of
the
s
ingl
e
r
e
gr
e
s
s
ion
a
nd
the
mul
ti
-
r
e
gr
e
s
s
ion
models
with
a
nd
without
us
ing
L
e
nter
a
-
int
e
r
a
c
ti
on
f
e
a
tur
e
s
.
I
t
c
a
n
be
s
e
e
n
f
r
om
thi
s
f
igur
e
,
the
va
lue
of
R
M
S
E
wa
s
c
ha
nge
a
l
ong
thi
s
e
xpe
r
im
e
nts
.
I
t
is
c
lea
r
f
r
om
F
ig
u
r
e
5
that
the
R
M
S
E
of
mul
ti
r
e
gr
e
s
s
ion
model
with
L
e
nter
a
f
e
a
tur
e
s
with
one
li
ne
a
r
model
is
0
.
17.
On
the
other
ha
nd,
the
R
M
S
E
of
s
ingl
e
r
e
gr
e
s
s
ion
model
is
0
.
3.
B
y
a
c
c
o
mpanying
s
tudent
-
bia
s
ter
m
a
nd
c
our
s
e
-
bi
a
s
ter
m,
mul
ti
-
r
e
gr
e
s
s
ion
model
c
ould
be
tt
e
r
c
a
ptur
e
s
tudent
pe
r
f
or
manc
e
s
in
their
c
our
s
e
.
F
ig
ur
e
5
il
lus
tr
a
tes
that
ther
e
is
a
de
c
r
e
ment
o
f
ob
taine
d
R
M
S
E
by
the
mul
ti
r
e
gr
e
s
s
ion
model
wi
th
incr
e
a
s
ing
number
of
li
ne
a
r
models
.
Us
ing
t
we
lve
pr
opos
e
d
r
e
gr
e
s
s
ion
models
,
the
a
c
quir
e
d
R
M
S
E
dr
ops
to
0
.
12.
C
ompar
ing
the
pe
r
f
or
manc
e
of
the
two
mul
t
i
-
r
e
gr
e
s
s
ion
models
in
F
ig
ur
e
5
,
we
c
a
n
s
e
e
that
t
he
model
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KO
M
NI
KA
T
e
lec
omm
un
C
omput
E
l
C
ontr
o
l
P
r
e
dicting
s
tudent
pe
r
for
manc
e
in
higher
e
duc
ati
on
…
(
L
e
o
W
il
lyanto
Santos
o
)
1359
that
us
e
s
the
L
e
nter
a
f
e
a
tur
e
s
pe
r
f
or
ms
be
tt
e
r
than
the
one
that
doe
s
not
us
e
them.
A
mul
ti
-
r
e
gr
e
s
s
ion
model
with
ten
li
ne
a
r
models
gives
a
nd
a
n
R
M
S
E
of
0
.
14
3
withou
t
us
ing
the
L
e
nter
a
f
e
a
tur
e
s
a
nd
gives
a
n
R
M
S
E
of
0
.
12
us
ing
the
L
e
nter
a
f
e
a
tur
e
s
.
T
he
us
e
of
L
e
nter
a
f
e
a
tur
e
s
lea
d
to
mor
e
dr
op
in
R
M
S
E
with
incr
e
a
s
ing
number
of
r
e
gr
e
s
s
ion
models
.
F
r
om
the
e
va
luation,
it
c
a
n
be
c
onc
luded
that
it
is
be
c
a
us
e
the
pr
opos
e
d
m
o
de
l
that
pr
a
c
ti
c
e
s
the
L
e
nter
a
f
e
a
tur
e
s
ha
ve
e
xtr
a
s
tudent
L
e
nter
a
c
oll
a
bor
a
ti
on
inf
or
mation
to
s
tudy
f
r
om
a
s
the
number
of
r
e
gr
e
s
s
ion
models
incr
e
a
s
e
.
F
igur
e
4
.
S
tatis
ti
c
s
in
L
e
nter
a
F
igur
e
5.
T
he
gr
a
phic
o
f
r
e
g
r
e
s
s
ion
model
vs
R
M
S
E
4.
CONC
L
USI
ON
I
n
thi
s
r
e
s
e
a
r
c
h,
mul
ti
-
r
e
gr
e
s
s
ion
model
to
f
o
r
e
c
a
s
t
the
pe
r
f
or
manc
e
of
univer
s
it
y
s
tudent
wa
s
im
pleme
nted.
Ac
c
or
ding
to
the
tes
ti
ng
r
e
s
ult
,
mul
t
i
-
r
e
gr
e
s
s
ion
model
pe
r
f
or
ms
be
tt
e
r
in
e
xplaining
d
e
pe
nde
nt
va
r
iable
s
than
s
ingl
e
l
inea
r
r
e
gr
e
s
s
ion.
M
or
e
ove
r
,
by
incr
e
a
s
ing
the
nu
mber
o
f
li
ne
a
r
r
e
gr
e
s
s
ion
model,
the
R
M
S
E
tends
to
de
c
r
e
a
s
e
gr
a
dua
ll
y.
F
inally
,
L
e
nter
a
int
e
r
a
c
ti
on
f
e
a
tu
r
e
s
c
ould
im
pr
ove
the
a
c
c
ur
a
c
y
of
pr
e
diction
of
s
tudent
pe
r
f
o
r
manc
e
.
AC
KNOWL
E
DGM
E
N
T
T
his
r
e
s
e
a
r
c
h
wa
s
s
uppor
ted
by
T
he
M
ini
s
tr
y
o
f
R
e
s
e
a
r
c
h,
T
e
c
hnology
a
nd
Highe
r
E
duc
a
ti
on
of
the
R
e
publi
c
of
I
ndone
s
ia.
R
e
s
e
a
r
c
h
Gr
a
nt
S
c
he
me
(
No:
002/
S
P
2H/L
T
/K7/KM
/2017)
.
RE
F
E
RE
NC
E
S
[1
]
San
t
o
s
o
.
L.
W
.
,
“
A
n
al
y
s
i
s
o
f
t
h
e
i
mp
ac
t
o
f
i
n
fo
rma
t
i
o
n
t
e
ch
n
o
l
o
g
y
i
n
v
e
s
t
me
n
t
s
–
a
s
u
rv
e
y
o
f
i
n
d
o
n
es
i
an
u
n
i
v
er
s
i
t
i
es
,
”
A
R
P
N
JE
A
S
,
v
o
l
.
9
,
n
o
.
12
,
p
p
.
2
4
0
4
-
2
4
1
0
,
2
0
1
4
.
[2
]
Bak
e
r
R
.
an
d
In
v
en
t
ad
o
.
P
, “
E
d
u
ca
t
i
o
n
a
l
d
at
a
mi
n
i
n
g
an
d
l
earn
i
n
g
an
a
l
y
t
i
cs
,
”
Lea
r
n
i
n
g
A
n
a
l
yt
i
cs
,
p
p
.
61
-
75
,
2
0
1
4
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
1693
-
6930
T
E
L
KO
M
NI
KA
T
e
lec
omm
un
C
omput
E
l
C
ontr
o
l
,
Vol.
18
,
No
.
3
,
J
une
2020:
13
54
-
13
60
1360
[3
]
A
n
d
ers
o
n
J
.
R
.
,
Bo
y
l
e
C.
F
.
,
an
d
Rei
s
er
B.
J
.
,
“
In
t
el
l
i
g
e
n
t
t
u
t
o
r
i
n
g
s
y
s
t
em
s
,
”
S
ci
en
ce
,
v
o
l
.
2
2
8
,
n
o
.
4
6
9
8
,
p
p
.
4
5
6
-
4
6
2
,
1
9
8
5
.
[
4
]
M
j
h
o
o
l
A
.
Y
.
,
A
l
h
i
l
a
l
i
A
.
a
n
d
H
,
A
l
-
A
u
g
b
y
S
,
“
A
P
r
o
p
o
s
e
d
a
r
c
h
i
t
e
c
t
u
r
e
o
f
b
i
g
e
d
u
c
a
t
i
o
n
a
l
d
a
t
a
u
s
i
n
g
h
a
d
o
o
p
a
t
t
h
e
u
n
i
v
e
r
s
i
t
y
o
f
k
u
f
a
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
E
l
e
c
t
r
i
c
a
l
a
n
d
C
o
m
p
u
t
e
r
E
n
g
i
n
e
e
r
i
n
g
,
v
o
l
.
9
,
n
o
.
6
,
p
p
.
4
9
7
0
-
4
9
7
8
,
2
0
1
9
.
[5
]
Ro
mero
C
.
,
an
d
V
e
n
t
u
ra
S
.
, “
E
d
u
ca
t
i
o
n
al
d
a
t
a
mi
n
i
n
g
:
A
rev
i
e
w
o
f
t
h
e
s
t
at
e
o
f
t
h
e
ar
t
,”
Tr
a
n
s
.
S
y
s
.
M
a
n
Cyb
er
P
a
r
t
C
,
v
o
l
.
40
,
n
o
.
6
,
p
p
.
6
0
1
-
6
1
8
,
2
0
1
0
.
[6
]
San
t
o
s
o
L
.
W
.
,
Y
u
l
i
a
,
“
T
h
e
an
a
l
y
s
i
s
o
f
s
t
u
d
en
t
p
erfo
rma
n
ce
u
s
i
n
g
d
a
t
a
m
i
n
i
n
g
,
”
A
d
va
n
ces
i
n
In
t
e
l
l
i
g
e
n
t
S
y
s
t
e
m
s
a
n
d
Co
m
p
u
t
a
t
i
o
n
a
l
S
c
i
en
ce
s
,
p
p
.
5
5
9
-
5
7
3
,
2
0
1
9
.
[7
]
San
t
o
s
o
L.
W
,
“
E
arl
y
w
ar
n
i
n
g
s
y
s
t
em
fo
r
aca
d
emi
c
u
s
i
n
g
d
at
a
m
i
n
i
n
g
,
”
F
o
u
r
t
h
In
t
er
n
a
t
i
o
n
a
l
C
o
n
f
er
e
n
ce
o
n
A
d
v
a
n
ce
s
i
n
C
o
m
p
u
t
i
n
g
,
Co
m
m
u
n
i
ca
t
i
o
n
&
A
u
t
o
m
a
t
i
o
n
,
p
p
.
1
-
4
,
2
0
1
9
.
[8
]
San
t
o
s
o
L
.
W
.
,
“
D
a
t
a
w
are
h
o
u
s
e
w
i
t
h
b
i
g
d
at
a
t
ech
n
o
l
o
g
y
f
o
r
h
i
g
h
er
e
d
u
cat
i
o
n
,
”
P
r
o
ce
d
i
a
Co
m
p
u
t
er
S
ci
e
n
ce
,
v
o
l
.
1
2
4
,
n
o
.
1
,
p
p
.
93
-
99
,
2
0
1
7
.
[9
]
Barb
er
R
.
,
Sh
ark
ey
M
.
, “
Co
u
rs
e
co
rr
ect
i
o
n
:
U
s
i
n
g
an
al
y
t
i
c
s
t
o
p
red
i
ct
co
u
rs
e
s
u
cces
s
,”
In
t
e
r
n
a
t
i
o
n
a
l
Co
n
f
e
r
en
ce
o
n
Lea
r
n
i
n
g
A
n
a
l
yt
i
cs
a
n
d
Kn
o
w
l
ed
g
e
,
p
p
.
2
5
9
-
2
6
2
,
2
0
1
2
.
[1
0
]
W
an
g
J
.
,
an
d
K
ary
p
i
s
G
.
,
“
H
armo
n
y
:
E
ffici
e
n
t
l
y
mi
n
i
n
g
t
h
e
b
es
t
ru
l
es
fo
r
cl
a
s
s
i
ficat
i
o
n
,
”
D
a
t
a
M
i
n
i
n
g
Co
n
f
e
r
en
ce
,
p
p
.
2
0
5
-
2
1
6
,
2
0
0
5
.
[1
1
]
H
an
J
.
,
Pei
J
.
,
Y
i
n
Y
.
,
“
Mi
n
i
n
g
fre
q
u
e
n
t
p
at
t
ern
s
w
i
t
h
o
u
t
ca
n
d
i
d
a
t
e
g
e
n
erat
i
o
n
,
”
A
CM
S
IG
M
O
D
In
t
’l
Co
n
f
.
o
n
M
a
n
a
g
em
e
n
t
o
f
D
a
t
a
,
v
o
l
.
2
9
,
n
o
.
2
,
p
p
.
1
-
12
,
2
0
0
0
.
[1
2
]
Frad
k
i
n
D
.
an
d
Mo
rch
e
n
F
.
,
“
Mi
n
i
n
g
s
e
q
u
e
n
t
i
al
p
a
t
t
ern
s
fo
r
cl
as
s
i
fica
t
i
o
n
,”
Kn
o
w
l
.
In
f
.
S
ys
t
,
v
o
l
.
45
,
no
.
3
,
p
p
.
7
3
1
-
7
4
9
,
2
0
1
5
.
[1
3
]
A
g
ra
w
al
R
.
,
G
o
l
s
h
a
n
B
.
,
an
d
Pa
p
al
e
x
ak
i
s
E.
E
.
,
“
T
o
w
a
rd
d
a
t
a
-
d
r
i
v
e
n
d
e
s
i
g
n
o
f
ed
u
cat
i
o
n
al
c
o
u
r
s
es
:
A
fea
s
i
b
i
l
i
t
y
St
u
d
y
,
”
Jo
u
r
n
a
l
o
f
E
d
u
ca
t
i
o
n
a
l
D
a
t
a
M
i
n
i
n
g
(JE
D
M
)
,
v
o
l
.
8
,
n
o
.
1
,
p
p
.
1
-
21
,
2
0
1
6
.
[1
4
]
J
i
t
t
a
w
i
r
i
y
a
n
u
k
o
o
n
C
.
,
“
Pro
p
o
s
e
d
cl
a
s
s
i
fi
ca
t
i
o
n
f
o
r
el
ea
rn
i
n
g
d
a
t
a
an
al
y
t
i
cs
w
i
t
h
MO
A
,”
In
t
er
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
E
l
ec
t
r
i
ca
l
a
n
d
Co
m
p
u
t
e
r
E
n
g
i
n
eer
i
n
g
,
v
o
l
.
9
,
n
o
.
5
,
p
p
.
3
5
6
9
-
3
5
7
5
,
2
0
1
9
.
[1
5
]
A
n
d
ay
a
n
i
S
.
,
et
a
l
,
“
D
ec
i
s
i
o
n
-
mak
i
n
g
mo
d
el
f
o
r
s
t
u
d
e
n
t
a
s
s
e
s
s
me
n
t
b
y
u
n
i
fy
i
n
g
n
u
meri
ca
l
a
n
d
l
i
n
g
u
i
s
t
i
c
d
a
t
a
,
”
In
t
e
r
n
a
t
i
o
n
a
l
Jo
u
r
n
a
l
o
f
E
l
ect
r
i
c
a
l
a
n
d
Co
m
p
u
t
er
E
n
g
i
n
eer
i
n
g
,
v
o
l
.
7
,
n
o
.
1
,
p
p
.
3
6
3
-
3
7
3
,
2
0
1
7
.
[1
6
]
San
t
o
s
o
L.
W
.
, “
IT
IL
s
erv
i
ce
man
ag
eme
n
t
mo
d
el
fo
r
e
-
l
earn
i
n
g
,
”
Jo
u
r
n
a
l
o
f
A
d
v
R
es
e
a
r
c
h
i
n
D
y
n
a
m
i
c
a
l
&
Co
n
t
r
o
l
S
ys
t
em
s
,
v
o
l
.
1
1
,
n
o
.
6
,
p
p
.
1
9
0
-
1
9
7
,
2
0
1
9
.
[1
7
]
Q
u
a
d
ri
M.
N
,
an
d
K
a
l
y
a
n
k
ar
N.
V
.
,
“
D
ro
p
o
u
t
fea
t
u
re
o
f
s
t
u
d
en
t
d
a
t
a
fo
r
aca
d
emi
c
p
erfo
rma
n
ce
u
s
i
n
g
d
eci
s
i
o
n
t
ree
t
ech
n
i
q
u
es
,
”
G
l
o
b
.
J.
Co
m
p
u
t
.
S
ci
.
Tech
n
o
l
o
g
y
,
v
o
l
.
10
,
n
o
.
2
,
p
p
.
2
-
5
,
2
0
1
0
.
[1
8
]
D
ek
k
er
G.
W
.
,
Pech
en
i
zk
i
y
M
.
,
an
d
V
l
ees
h
o
u
w
er
s
J.
M
.
,
“
Pred
i
ct
i
o
n
s
t
u
d
e
n
t
d
r
o
p
o
u
t
:
A
cas
e
s
t
u
d
y
,”
2
n
d
I
n
t
e
r
n
a
t
i
o
n
a
l
Co
n
f
e
r
en
ce
o
n
E
d
u
c
a
t
i
o
n
a
l
D
a
t
a
M
i
n
i
n
g
,
p
p
.
41
-
50
,
2
0
0
9
.
[1
9
]
Barb
er
R
.
,
an
d
Sh
ark
e
y
M
.
,
“
Co
u
rs
e
c
o
rrect
i
o
n:
U
s
i
n
g
a
n
a
l
y
t
i
c
s
t
o
p
red
i
ct
c
o
u
r
s
e
s
u
cces
s
,”
2
nd
In
t
e
r
n
a
t
i
o
n
a
l
Co
n
f
er
e
n
ce
o
n
Le
a
r
n
i
n
g
A
n
a
l
yt
i
cs
a
n
d
Kn
o
w
l
ed
g
e
,
p
p
.
259
-
2
6
2
,
2
0
1
2
.
[2
0
]
L
ei
t
n
er
P
.
,
K
h
al
i
l
M
.
,
an
d
E
b
n
er
M
.
,
“
L
earn
i
n
g
an
al
y
t
i
c
s
i
n
h
i
g
h
e
r
ed
u
ca
t
i
o
n
ð
a
l
i
t
erat
u
re
rev
i
e
w
,
”
Lea
r
n
i
n
g
A
n
a
l
y
t
i
c
s
:
F
u
n
d
a
m
e
n
t
s
,
A
p
p
l
i
ca
t
i
o
n
s
,
a
n
d
Tr
e
n
d
s
.
S
p
r
i
n
g
er
In
t
er
n
a
t
i
o
n
a
l
P
u
b
l
i
s
h
i
n
g
,
p
p
.
1
-
23
,
2
0
1
7
.
[2
1
]
L
ee
Y
.
,
an
d
Ch
o
J
.
,
“
An
i
n
t
el
l
i
g
en
t
co
u
r
s
e
reco
mme
n
d
a
t
i
o
n
s
y
s
t
em
,
”
S
m
a
r
t
C
R
,
v
o
l
.
1
,
n
o
.
1
,
p
p
.
69
-
84
,
2
0
1
1
.
[2
2
]
Y
u
n
i
a
n
t
a
A
.
,
et
a
l
.
,
“
So
l
v
i
n
g
t
h
e
co
m
p
l
e
x
i
t
y
o
f
h
et
e
ro
g
e
n
ei
t
y
d
at
a
o
n
l
ear
n
i
n
g
e
n
v
i
ro
n
men
t
u
s
i
n
g
o
n
t
o
l
o
g
y
,
TE
LKO
M
NIK
A
Tel
ec
o
m
m
u
n
i
c
a
t
i
o
n
Co
m
p
u
t
i
n
g
E
l
ec
t
r
o
n
i
c
s
a
n
d
Co
n
t
r
o
l
,
v
o
l
.
13
,
n
o
.
1
,
p
p
.
3
4
1
-
3
4
8
,
2
0
1
5
,
[2
3
]
V
en
t
u
ra
C
.
S
.
,
E
s
p
e
j
o
P
.
G
.
,
an
d
H
er
v
ás
C
.
,
“
D
at
a
mi
n
i
n
g
al
g
o
r
i
t
h
ms
t
o
c
l
a
s
s
i
fy
s
t
u
d
e
n
t
s
,”
1
st
In
t
.
C
o
n
f
.
o
n
E
d
u
ca
t
i
o
n
a
l
D
a
t
a
M
i
n
i
n
g
.
M
o
n
t
r
ea
l
,
p
p
.
1
87
-
1
9
1
,
2
0
0
8
.
[2
4
]
T
h
a
i
-
N
g
h
e
N
g
,
et
al
.
,
“
Fact
o
r
i
zat
i
o
n
t
ec
h
n
i
q
u
es
f
o
r
p
red
i
c
t
i
n
g
s
t
u
d
en
t
p
erf
o
rman
ce
.
ed
u
cat
i
o
n
al
rec
o
mmen
d
er
s
y
s
t
ems
a
n
d
t
ech
n
o
l
o
g
i
e
s
:
Pract
i
ces
a
n
d
ch
a
l
l
en
g
es
,”
O
I
G
I
G
l
o
b
a
l
,
p
p
.
1
2
9
-
1
5
3
,
2
0
1
1
.
[2
5
]
Su
p
er
b
y
J
.
F,
V
an
d
amme
J.
P
.
,
an
d
Me
s
k
e
n
s
N
,
“
D
et
erm
i
n
a
t
i
o
n
o
f
fact
o
rs
i
n
f
l
u
en
c
i
n
g
t
h
e
ach
i
ev
eme
n
t
o
f
t
h
e
fi
r
s
t
-
y
ear
u
n
i
v
ers
i
t
y
s
t
u
d
e
n
t
s
u
s
i
n
g
d
a
t
a
mi
n
i
n
g
met
h
o
d
s
,
”
W
o
r
ks
h
o
p
o
n
e
d
u
c
a
t
i
o
n
a
l
d
a
t
a
m
i
n
i
n
g
,
v
o
l
.
3
2
,
2
0
0
6
.
[2
6
]
L
aman
i
A
.
,
et
al
.
,
“
D
at
a
mi
n
i
n
g
t
ec
h
n
i
q
u
es
a
p
p
l
i
ca
t
i
o
n
fo
r
p
red
i
ct
i
o
n
i
n
O
L
A
P
Cu
b
e
,”
In
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
E
l
ec
t
r
i
ca
l
a
n
d
Co
m
p
u
t
e
r
E
n
g
i
n
eer
i
n
g
,
v
o
l
.
9
,
n
o
.
3
,
p
p
.
2
0
9
4
-
2
1
0
2
,
2
0
1
9
.
[2
7
]
D
an
i
el
B
.
,
“
Bi
g
d
at
a
an
d
a
n
al
y
t
i
cs
i
n
h
i
g
h
er
e
d
u
cat
i
o
n
:
O
p
p
o
rt
u
n
i
t
i
es
an
d
c
h
a
l
l
e
n
g
e
s
,
”
B
r
i
t
i
s
h
Jo
u
r
n
a
l
o
f
E
d
u
c
a
t
i
o
n
a
l
Tech
n
o
l
o
g
y
,
v
o
l
.
46
,
n
o
.
5
,
p
p
.
9
0
4
-
9
2
0
,
2
0
1
4
.
[
2
8
]
E
l
b
a
d
r
a
w
y
A
.
,
S
t
u
d
h
a
m
R
.
S
.
,
a
n
d
K
a
r
y
p
i
s
G
.
,
“
P
e
r
s
o
n
a
l
i
z
e
d
m
u
l
t
i
-
r
e
g
r
e
s
s
i
o
n
m
o
d
e
l
s
f
o
r
p
r
e
d
i
c
t
i
n
g
s
t
u
d
e
n
t
s
’
p
e
r
f
o
r
m
a
n
c
e
i
n
c
o
u
r
s
e
a
c
t
i
v
i
t
i
e
s
,”
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
L
e
a
r
n
i
n
g
A
n
a
l
y
t
i
c
s
a
n
d
K
n
o
w
l
e
d
g
e
,
p
p
.
1
0
3
-
1
0
7
,
2
0
1
5
.
[2
9
]
A
g
ar
w
al
D
.
,
an
d
C
h
en
B.
C
.
,
“
R
eg
res
s
i
o
n
-
b
as
e
d
l
a
t
en
t
fact
o
r
m
o
d
e
l
s
,
”
A
CM
S
IG
K
D
D
C
o
n
f
er
e
n
ce
o
n
K
n
o
w
l
e
d
g
e
D
i
s
co
ve
r
y
a
n
d
D
a
t
a
M
i
n
i
n
g
,
p
p
.
19
-
27
,
2
0
0
9
.
Evaluation Warning : The document was created with Spire.PDF for Python.