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.
1
,
F
e
br
ua
r
y
2020
,
pp.
199
~
207
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
.
v18i1.
14922
199
Jou
r
n
al
h
omepage
:
ht
tp:
//
jour
nal.
uad
.
ac
.
id/
index
.
php/T
E
L
K
OM
N
I
K
A
D
e
ve
lo
p
m
e
n
t
o
f
on
li
n
e
l
e
ar
n
i
n
g gr
o
u
p
s
b
ase
d
o
n
M
B
T
I l
e
ar
n
in
g st
yl
e
an
d
f
u
z
z
y al
gor
ith
m
B
u
d
i
L
ak
s
on
o
P
u
t
r
o
,
Yus
e
p
Ros
m
an
s
yah
,
S
u
h
a
r
d
i
Sch
o
o
l
o
f
E
l
ec
t
ri
ca
l
E
n
g
i
n
eeri
n
g
a
n
d
I
n
fo
rma
t
i
c
s
,
Ban
d
u
n
g
In
s
t
i
t
u
t
e
o
f
T
ech
n
o
l
o
g
y
,
Ban
d
u
n
g
,
In
d
o
n
es
i
a
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
Aug
30
,
2019
R
e
vis
e
d
Nov
2
9
,
20
19
Ac
c
e
pted
De
c
21
,
20
19
G
ro
u
p
d
e
v
el
o
p
me
n
t
i
s
an
i
n
i
t
i
al
s
t
ep
an
d
an
i
mp
o
rt
a
n
t
i
n
fl
u
en
ce
o
n
l
earn
i
n
g
co
l
l
ab
o
rat
i
v
e
p
ro
b
l
em
s
o
l
v
i
n
g
(CPS)
b
as
e
d
o
n
t
h
e
d
i
g
i
t
al
l
earn
i
n
g
en
v
i
r
o
n
me
n
t
(D
L
E
).
G
ro
u
p
d
e
v
el
o
p
me
n
t
b
a
s
ed
o
n
t
h
e
My
er
s
-
Bri
g
g
s
t
y
p
e
s
i
n
d
i
ca
t
o
r
s
(MBT
I)
ru
l
e
p
r
o
v
ed
s
u
cce
s
s
f
u
l
f
o
r
t
h
e
e
d
u
c
at
i
o
n
al
a
n
d
i
n
d
u
s
t
ri
al
e
n
v
i
ro
n
men
t
.
T
h
e
MBT
I
i
d
ea
l
g
ro
u
p
ru
l
es
are
reach
ed
w
h
e
n
a
g
ro
u
p
l
ead
er
h
as
t
h
e
h
i
g
h
es
t
l
ev
e
l
o
f
l
ead
ers
h
i
p
an
d
co
m
p
at
i
b
i
l
i
t
y
b
et
w
een
g
ro
u
p
m
emb
ers
.
T
h
e
l
ev
e
l
o
f
l
ead
er
s
h
i
p
an
d
s
u
i
t
a
b
i
l
i
t
y
o
f
g
ro
u
p
memb
er
s
i
s
d
e
t
ermi
n
e
d
b
as
e
d
o
n
t
h
e
MBT
I
l
earn
i
n
g
s
t
y
l
e
(L
S).
Pro
b
l
em
s
ari
s
e
w
h
e
n
t
h
e
p
o
p
u
l
at
i
o
n
o
f
MBT
I
L
S
w
i
t
h
t
h
e
h
i
g
h
e
s
t
l
e
v
el
o
f
l
ead
er
s
h
i
p
i
s
o
v
er.
T
h
i
s
w
i
l
l
l
ead
t
o
d
u
al
l
ead
ers
h
i
p
p
ro
b
l
em
s
an
d
h
a
v
e
an
i
mp
ac
t
o
n
g
r
o
u
p
d
i
s
h
arm
o
n
y
.
T
h
i
s
s
t
u
d
y
p
ro
p
o
s
e
s
an
i
n
t
el
l
i
g
en
t
ag
en
t
s
o
f
t
w
a
re
fo
r
t
h
e
d
e
v
el
o
p
me
n
t
o
f
t
h
e
i
d
eal
g
ro
u
p
o
f
MBT
I,
u
s
i
n
g
t
h
e
Fu
zzy
al
g
o
ri
t
h
m.
T
h
e
i
n
t
e
l
l
i
g
e
n
t
ag
e
n
t
w
a
s
d
ev
el
o
p
e
d
o
n
t
h
e
SK
A
CI
p
l
at
f
o
rm.
SK
A
CI
i
s
a
D
L
E
fo
r
CPS
l
earn
i
n
g
.
Fu
zzy
al
g
o
r
i
t
h
m
fo
r
s
o
l
v
i
n
g
d
u
a
l
l
ead
er
s
h
i
p
p
ro
b
l
em
s
i
n
a
g
r
o
u
p
.
Fu
zzy
al
g
o
r
i
t
h
m
i
s
u
s
e
d
t
o
i
n
cre
as
e
t
h
e
p
o
p
u
l
at
i
o
n
o
f
MBT
I
L
S
t
o
3
l
e
v
el
s
,
n
amel
y
l
o
w
,
med
i
u
m
an
d
h
i
g
h
.
In
cr
eas
i
n
g
t
h
e
p
o
p
u
l
a
t
i
o
n
o
f
MBT
I
L
S
can
i
n
crea
s
e
t
h
e
p
r
o
b
a
b
i
l
i
t
y
o
f
fo
rmi
n
g
a
n
i
d
eal
g
ro
u
p
o
f
MBT
I.
In
t
e
l
l
i
g
e
n
t
ag
e
n
t
s
are
t
es
t
ed
b
a
s
ed
o
n
a
q
u
a
n
t
i
t
a
t
i
v
e
an
al
y
s
i
s
b
e
t
w
ee
n
e
x
p
er
i
men
t
al
cl
as
s
es
(ap
p
l
y
i
n
g
i
n
t
el
l
i
g
en
t
ag
e
n
t
s
),
an
d
c
o
n
t
r
o
l
cl
a
s
s
e
s
(w
i
t
h
o
u
t
i
n
t
el
l
i
g
en
t
ag
e
n
t
s
).
E
x
p
eri
me
n
t
re
s
u
l
t
s
s
h
o
w
an
i
n
crea
s
e
i
n
p
erf
o
rman
c
e
an
d
p
ro
d
u
c
t
i
v
i
t
y
i
s
b
et
t
er
i
n
t
h
e
ex
p
eri
me
n
t
a
l
cl
a
s
s
t
h
a
n
i
n
t
h
e
co
n
t
ro
l
cl
a
s
s
.
It
w
as
co
n
c
l
u
d
ed
t
h
a
t
t
h
e
d
ev
e
l
o
p
men
t
o
f
i
n
t
e
l
l
i
g
e
n
t
ag
e
n
t
s
h
a
d
a
p
o
s
i
t
i
v
e
i
mp
ac
t
o
n
g
ro
u
p
d
e
v
el
o
p
me
n
t
b
as
e
d
o
n
t
h
e
MBT
I
L
S
.
K
e
y
w
o
r
d
s
:
21
s
t
c
e
ntur
y
s
kil
ls
C
ol
labor
a
ti
ve
pr
oblem
s
olvi
ng
D
igi
tal
l
e
a
r
ning
e
nvi
r
onment
Gr
oup
de
ve
lopm
e
nt
I
ntelli
ge
nt
ag
e
nt
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
:
B
udi
L
a
ks
ono
P
utr
o,
S
c
hool
of
E
lec
tr
ica
l
E
nginee
r
ing
a
nd
I
n
f
or
matics
,
B
a
ndung
I
ns
ti
tut
e
of
T
e
c
hnology,
B
a
ndung,
I
ndone
s
ia
.
E
mail:
blput
r
o@gmail.
c
om
1.
I
NT
RODU
C
T
I
ON
C
oll
a
bor
a
ti
ve
pr
oblem
s
olvi
ng
(
C
P
S
)
lea
r
ning
b
a
s
e
d
on
digi
tal
lea
r
ning
e
nvir
onment
(
DL
E
)
is
a
n
e
f
f
or
t
to
r
e
a
li
z
e
21
st
c
e
ntu
r
y
s
kil
ls
[1
-
6]
.
G
r
ou
p
de
ve
lopm
e
nt
is
a
f
ir
s
t
s
tep
a
nd
s
igni
f
ica
nt
inf
luenc
e
on
the
e
f
f
e
c
ti
ve
ne
s
s
of
C
P
S
lea
r
ning
ba
s
e
d
on
DL
E
[
4
,
7
-
13]
.
T
he
r
e
a
r
e
many
a
lt
e
r
na
t
ive
methods
f
or
de
ve
lopi
ng
gr
oups
,
a
nd
e
a
c
h
a
lt
e
r
na
ti
ve
method
of
gr
oup
f
o
r
m
a
ti
on
ha
s
a
dva
ntage
s
a
nd
dis
a
dva
ntage
s
[
14]
.
T
he
c
r
it
e
r
ia
o
f
the
be
s
t
gr
oup
a
r
e
a
s
f
oll
ows
:
(
1)
a
ppr
op
r
iate
indi
vi
dua
l
c
ompos
it
ion,
(
2)
e
a
c
h
indi
v
idual
plays
a
good
f
unc
ti
on,
(
3)
incr
e
a
s
e
d
indi
vidual
pr
oduc
ti
vi
ty,
(
4
)
incr
e
a
s
e
d
gr
oup
p
r
oduc
ti
vit
y,
a
nd
(
5
)
e
njoyable
lea
r
ning
e
xp
e
r
ienc
e
s
f
or
both
indi
viduals
a
nd
a
s
a
gr
oup
[1
4]
.
Gr
oup
de
ve
lopm
e
nt
ba
s
e
d
on
the
M
ye
r
s
-
B
r
iggs
ty
pe
s
indi
c
a
tor
s
r
ule
(
M
B
T
I
)
ha
s
pr
ove
n
s
uc
c
e
s
s
f
ul
f
or
the
e
duc
a
ti
ona
l
a
nd
indus
tr
ial
e
nvir
onment
[
14
]
.
T
he
M
B
T
I
idea
l
gr
oup
r
ule
is
r
e
a
c
he
d
whe
n
a
gr
oup
lea
de
r
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
.
1
,
F
e
br
ua
r
y
2020
:
199
-
207
200
ha
s
the
highes
t
leve
l
of
lea
de
r
s
hip
a
nd
c
ompatibi
li
ty
be
twe
e
n
gr
oup
membe
r
s
.
T
he
leve
l
of
lea
de
r
s
hip
a
nd
s
uit
a
bil
it
y
of
g
r
oup
membe
r
s
is
de
ter
mi
ne
d
ba
s
e
d
on
the
M
B
T
I
lea
r
ning
s
tyl
e
(
L
S
)
.
P
r
oblems
a
r
i
s
e
whe
n
the
population
of
M
B
T
I
L
S
with
the
highes
t
lev
e
l
of
lea
de
r
s
hip
is
ove
r
.
T
his
will
lea
d
to
dua
l
lea
de
r
s
hip
pr
oblems
a
nd
ha
ve
a
n
im
pa
c
t
on
gr
oup
dis
ha
r
mony.
T
he
r
e
is
no
int
e
ll
igent
a
ge
nt
r
e
s
e
a
r
c
h
f
or
gr
oup
de
ve
lopm
e
nt
that
a
ddr
e
s
s
e
s
the
is
s
ue
of
the
pos
s
ibi
li
ty
of
dua
l
lea
r
de
r
s
hip
in
M
B
T
I
.
T
his
s
tudy
pr
opos
e
s
a
n
int
e
ll
igent
a
ge
nt
s
of
twa
r
e
f
or
the
de
ve
lopm
e
nt
of
the
idea
l
gr
oup
of
M
B
T
I
,
us
ing
the
F
uz
z
y
a
lgor
it
hm.
T
he
i
ntelli
ge
nt
a
ge
nt
w
a
s
de
ve
loped
on
the
S
KA
C
I
platf
or
m.
S
KA
C
I
is
a
DL
E
f
or
C
P
S
lea
r
ning.
T
he
us
e
of
f
uz
z
y
a
lgor
it
h
ms
to
s
olve
the
pr
oblem
of
dua
l
lea
de
r
s
hip.
F
uz
z
y
c
lus
ter
ing
m
e
thod
to
c
r
e
a
te
homogenous
c
lus
ter
s
ba
s
e
d
on
we
ight
ing
the
s
pe
c
if
ied
c
r
it
e
r
ia
[
15
-
18]
.
T
he
dua
l
lea
de
r
s
hip
pr
oblem
is
s
olved
by
gr
ouping
e
a
c
h
leve
l
o
f
lea
de
r
s
hip
int
o
s
e
ve
r
a
l
homogene
ous
c
lus
ter
leve
ls
[
12,
15]
.
E
a
c
h
leve
l
of
lea
de
r
s
hip
of
the
M
B
T
I
L
S
is
made
int
o
a
hom
oge
ne
ous
c
lus
ter
ba
s
e
d
on
high,
medium,
a
nd
lo
w
leve
ls
.
T
he
M
B
T
I
L
S
lea
de
r
s
hip
leve
l
wa
s
or
igi
na
ll
y
4
(
f
o
ur
)
leve
ls
,
with
a
f
uz
z
y
a
lgor
it
hm
c
lus
ter
ing
int
o
12
(
twe
lve)
leve
ls
.
I
nc
r
e
a
s
ing
the
leve
l
of
lea
de
r
s
hip
of
the
M
B
T
I
L
S
c
a
n
inc
r
e
a
s
e
the
pr
oba
bil
it
y
o
f
f
o
r
mi
ng
a
n
id
e
a
l
gr
oup
of
M
B
T
I
.
T
he
int
e
ll
igent
a
ge
nt
de
ve
lopm
e
n
t
method
f
or
gr
ou
p
de
ve
lopm
e
nt
us
e
s
c
ons
tr
a
int
pr
ogr
a
mm
ing
(
C
P
)
modeling
[
19
,
20
]
na
mely
f
lowc
ha
r
t
diagr
a
ms
,
a
nd
P
HP
pr
ogr
a
mm
ing
s
c
r
ipt
s
.
T
he
int
e
ll
igent
a
ge
nt
tes
t
is
ba
s
e
d
on
the
int
e
ll
igent
a
ge
nt
pe
r
f
o
r
manc
e
metr
ic
f
or
g
r
oup
de
ve
lopm
e
nt
on
C
P
S
lea
r
ning.
T
he
pe
r
f
or
manc
e
metr
ics
a
r
e
ba
s
e
d
on
5
(
f
ive)
mea
s
ur
ing
tool
s
na
m
e
ly
[
21
,
22
]
:
Gr
oup
f
or
mation
ti
me,
opti
mi
z
a
ti
on
o
f
s
tudent
dis
tr
ibut
ion
to
gr
oups
,
C
oll
a
bo
r
a
ti
on
pe
r
f
o
r
m
a
nc
e
(
C
O)
,
Know
ledge
,
a
nd
s
kil
ls
.
I
t
is
hope
d
that
the
im
pleme
ntation
o
f
int
e
ll
igent
a
ge
nts
c
a
n
i
nc
r
e
a
s
e
the
e
f
f
icie
nc
y
of
gr
oup
f
o
r
mation
ti
m
e
,
gr
oup
pe
r
f
or
manc
e
,
a
nd
inc
r
e
a
s
e
the
pr
oduc
ti
vit
y
of
C
P
S
lea
r
ning
(
knowle
dge
,
s
kil
ls
)
.
I
ntelli
ge
nt
a
ge
nt
tes
ti
ng
ba
s
e
d
on
qua
nti
tative
a
na
lys
is
c
ompar
is
on
be
twe
e
n
e
xpe
r
im
e
ntal
c
las
s
(
a
pplyi
ng
int
e
ll
igent
a
ge
nt)
,
a
nd
c
ont
r
ol
c
las
s
(
without
a
n
in
telli
ge
nt
a
ge
nt)
.
I
mpr
ove
d
pe
r
f
o
r
ma
nc
e
a
nd
p
r
oduc
ti
vit
y
of
C
P
S
lea
r
ning
in
the
e
xpe
r
im
e
ntal
c
las
s
is
be
tt
e
r
than
the
c
ontr
ol
c
las
s
.
I
t
wa
s
c
onc
lud
e
d
that
the
de
ve
lopm
e
nt
o
f
in
telli
ge
nt
a
ge
nts
ha
d
a
pos
it
ive
i
mpac
t
on
gr
oup
de
ve
lopm
e
nt
ba
s
e
d
on
the
M
B
T
I
L
S
.
T
his
pa
pe
r
c
ons
is
ts
of
4
S
e
c
ti
ons
.
B
a
c
kgr
ound
r
e
s
e
a
r
c
h,
is
s
ue
s
,
goa
l
s
e
tt
ing,
a
nd
ge
ne
r
a
l
ove
r
view
a
r
e
e
xplaine
d
in
s
e
c
ti
on
1;
r
e
s
e
a
r
c
h
method
r
e
s
e
a
r
c
h
is
dis
c
us
s
e
d
in
s
e
c
ti
on
2;
s
e
c
ti
on
3
dis
c
us
s
e
s
r
e
s
ult
s
a
nd
a
na
lys
is
;
de
ve
lo
pment
of
int
e
ll
igent
a
ge
nts
o
n
the
S
KA
C
I
platf
or
m
is
dis
c
us
s
e
d
in
s
e
c
ti
on
3.
1;
e
xpe
r
im
e
nts
a
nd
a
na
lyze
s
of
int
e
ll
igent
a
ge
nts
f
or
gr
oup
de
ve
lopm
e
nt
C
P
S
lea
r
ning
on
the
S
KA
C
I
plat
f
or
m
a
r
e
dis
c
us
s
e
d
in
se
c
ti
on
3.
2;
a
nd
c
onc
lus
ions
a
nd
s
ugge
s
ti
ons
r
e
s
e
a
r
c
h
oppor
tuni
ti
e
s
a
r
e
f
ur
ther
dis
c
u
s
s
e
d
in
s
e
c
ti
on
4.
2.
RE
S
E
AR
CH
M
E
T
HO
D
T
his
c
ha
pter
dis
c
us
s
e
s
r
e
s
e
a
r
c
h
methodology
whic
h
c
ons
is
ts
of
s
tag
e
s
of
r
e
s
e
a
r
c
h
a
nd
de
t
a
il
e
d
s
teps
of
e
a
c
h
s
tage
of
r
e
s
e
a
r
c
h.
T
his
r
e
s
e
a
r
c
h
c
ons
is
ts
of
2
main
s
tage
s
,
na
mely:
−
De
ve
lopm
e
nt
of
int
e
ll
igent
a
ge
nts
f
or
gr
ou
p
f
o
r
mation
ba
s
e
d
on
M
B
T
I
L
S
,
a
nd
f
uz
z
y
a
lgor
it
hms
.
I
ntelli
ge
nt
a
ge
nts
a
r
e
de
ve
loped
on
the
S
KA
C
I
pla
tf
or
m.
S
KA
C
I
is
a
DL
E
f
o
r
C
P
S
lea
r
ning
.
T
he
out
put
is
a
n
int
e
ll
igent
a
ge
nt
f
or
gr
oup
de
ve
lopm
e
nt
ba
s
e
d
on
the
M
B
T
I
L
S
a
nd
f
uz
z
y
a
lgor
it
hms
.
−
Ana
lys
is
of
the
pe
r
f
or
manc
e
of
int
e
ll
igent
a
g
e
nts
f
or
gr
oup
de
ve
lopm
e
nt
on
C
P
S
lea
r
ning
on
the
S
KA
C
I
platf
o
r
m.
2
.
1.
I
n
t
e
ll
igent
age
n
t
f
or
gr
ou
p
d
e
ve
lop
m
e
n
t
T
he
de
ve
lopm
e
nt
o
f
int
e
ll
igent
a
ge
nts
on
the
S
K
AC
I
platf
or
m
[
23
,
24]
is
il
lus
tr
a
ted
in
F
igur
e
1.
S
KA
C
I
is
a
DL
E
f
or
C
P
S
lea
r
ning.
S
KA
C
I
f
unc
ti
o
na
li
ti
e
s
include
indi
vidual
lea
r
ning
e
nvir
onments
[
25]
,
a
nd
c
oll
a
bor
a
ti
ve
lea
r
ning
e
nvir
onments
or
of
ten
r
e
f
e
r
r
e
d
to
a
s
C
omput
e
r
-
s
uppor
ted
c
oll
a
bor
a
ti
ve
lea
r
ning
(
C
S
C
L
)
[
23,
26
,
27]
.
De
ve
lopm
e
nt
of
int
e
ll
igent
a
ge
nts
f
or
gr
oup
de
ve
lopm
e
nt
us
ing
c
ons
tr
a
int
p
r
og
r
a
mm
ing
(
C
P
)
modeling
[
19,
20]
na
mely
f
lowc
ha
r
t
diag
r
a
ms
a
nd
P
HP
pr
ogr
a
m
mi
ng
s
c
r
ipt
s
.
T
he
s
tage
s
of
the
f
r
a
mew
or
k
f
or
de
ve
lopi
ng
int
e
ll
igent
a
ge
nts
f
or
mi
ng
gr
oups
on
the
S
KA
C
I
platf
or
m
a
r
e
:
(
a
)
S
L
E
-
int
e
r
f
a
c
e
,
(
b)
gr
oup
f
or
mation
-
int
e
ll
igent
a
ge
nt,
(
c
)
C
oll
a
bor
a
ti
ve
pr
obl
e
m
s
olvi
ng
(
C
P
S
)
-
Ac
ti
vit
y.
S
L
E
-
int
e
r
f
a
c
e
in
F
igur
e
1
pa
r
t
(
a
)
a
s
a
C
P
S
lea
r
n
ing
int
e
r
f
a
c
e
f
o
r
s
tu
de
nt
p
r
of
il
e
,
que
s
ti
onna
ir
e
(
M
B
T
I
lea
r
ning
s
tyl
e
)
,
a
nd
c
ou
r
s
e
a
s
s
ignm
e
nt.
T
he
int
e
ll
igent
a
ge
nt
im
pleme
ntation
on
the
S
KA
C
I
plat
f
or
m
in
F
igur
e
1
pa
r
t
(
b
)
.
T
his
s
tage
c
ons
is
ts
of
3
(
th
r
e
e
)
m
a
in
f
unc
ti
ona
li
ti
e
s
,
na
mely:
(
1)
C
las
s
if
ying
a
nd
R
a
nking
of
M
B
T
I
L
S
Attr
ibut
e
s
,
(
2
)
I
nc
r
e
a
s
ing
L
S
of
M
B
T
I
P
opulation
with
F
uz
z
y
Algor
it
hm,
a
nd
(
3)
Gr
oup
f
or
mation
a
lgor
it
hms
ba
s
e
d
on
M
B
T
I
tea
m
lea
de
r
r
ules
.
M
e
a
s
ur
e
ment
of
the
e
f
f
e
c
ti
ve
ne
s
s
of
int
e
l
li
ge
nt
a
ge
nts
f
or
mi
ng
gr
oups
in
F
igur
e
1
pa
r
t
(
b
)
,
na
mely:
the
e
f
f
icie
nc
y
of
gr
oup
f
or
mation
ti
me,
a
nd
opti
m
izing
the
dis
tr
i
buti
on
of
s
tudents
in
gr
oups
.
C
P
S
lea
r
ning
on
the
S
KA
C
I
P
lat
f
or
m
is
il
lus
tr
a
ted
i
n
F
igur
e
1
pa
r
t
(
c
)
[
28
]
.
T
he
s
tage
s
of
C
P
S
lea
r
ning
a
c
ti
vit
ies
include
(
1)
c
oll
a
bor
a
ti
ve
lea
r
ning
,
a
nd
(
2
)
indi
vidual
lea
r
ning
.
T
he
pe
r
f
o
r
manc
e
of
gr
oup
f
o
r
mation
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
De
v
e
lopme
nt
of
onli
ne
lear
ning
gr
oups
bas
e
d
on
M
B
T
I
lear
ning
s
tyle
…
(
B
udi
L
ak
s
ono
P
utr
o
)
201
on
C
P
S
lea
r
ning
is
mea
s
ur
e
d
by
indi
vidual
lea
r
ni
ng
outc
omes
a
nd
c
oll
a
bor
a
ti
ve
lea
r
ning
.
DL
E
-
ba
s
e
d
C
P
S
lea
r
ning
is
an
e
f
f
or
t
to
r
e
a
li
z
e
21
st
cen
tur
y
s
kil
ls
(
2
1
st
c
e
ntur
y
S
kil
l
)
[
2]
.
21
st
c
e
ntur
y
s
kil
ls
a
r
e
the
s
kil
ls
ne
e
de
d
to
de
a
l
with
21
st
c
e
ntur
y
pr
oblems
[
2]
.
F
igur
e
1.
I
ntell
igent
a
ge
nts
f
or
the
de
ve
lopm
e
nt
of
C
P
S
lea
r
ning
g
r
oups
on
the
S
KA
C
I
platf
o
r
m
[
2,
1
1,
29]
2
.2
.
I
n
t
e
ll
igent
age
n
t
p
e
r
f
or
m
an
c
e
m
e
t
r
ics
I
ntelli
ge
nt
a
ge
nt
pe
r
f
o
r
manc
e
mea
s
ur
e
ment
ba
s
e
d
on
mea
s
ur
e
ment
metr
ics
in
T
a
ble
1.
I
ntell
igent
a
ge
nt
pe
r
f
or
manc
e
metr
ics
c
ons
is
t
[
21
,
22
]
:
gr
ou
p
f
or
mat
ion
ti
me,
opti
mi
z
a
ti
on
o
f
s
tudent
dis
tr
ib
uti
on
to
gr
oups
,
c
oll
a
bor
a
ti
on
pe
r
f
or
manc
e
(
C
O)
,
k
nowle
d
ge
,
a
nd
s
kil
ls
.
M
e
a
s
ur
e
ment
of
g
r
oup
f
or
mation
t
im
e
a
nd
opti
mi
z
a
ti
on
of
s
tudent
dis
tr
ibut
ion
in
gr
oups
is
c
a
r
r
ied
out
a
t
the
f
or
mation
s
tage
.
C
oll
a
bor
a
ti
on
pe
r
f
or
manc
e
(
C
O)
,
kn
owle
dge
,
a
nd
s
kil
l
m
e
a
s
ur
e
ments
a
r
e
pe
r
f
or
med
a
t
the
pe
r
f
or
mi
ng
s
tage
[
2
,
11
,
29
]
.
Qua
nti
tative
a
na
lys
is
of
int
e
ll
igent
a
ge
nts
ba
s
e
d
on
c
ompar
is
on
of
pe
r
f
or
manc
e
mea
s
ur
e
ments
be
twe
e
n
the
e
xpe
r
im
e
ntal
c
las
s
(
a
pplyi
ng
int
e
ll
igent
a
ge
nts
)
a
nd
the
c
ontr
ol
c
las
s
(
without
a
pplyi
ng
i
ntelli
ge
nt
a
ge
nts
)
on
C
P
S
l
e
a
r
n
ing.
T
he
im
pleme
ntation
of
int
e
l
li
ge
nt
a
ge
nts
is
s
uc
c
e
s
s
f
ul
whe
n
the
r
e
s
ult
s
of
the
e
xpe
r
im
e
ntal
c
las
s
(
a
pplyi
ng
int
e
ll
igent
a
ge
nt
s
)
mea
s
ur
e
ment
a
r
e
be
tt
e
r
than
the
c
ontr
ol
c
las
s
(
without
a
pplyi
ng
int
e
ll
igent
a
ge
nts
)
.
T
a
ble
1.
M
e
tr
ics
p
e
r
f
or
manc
e
o
f
int
e
ll
igent
a
ge
nts
f
or
g
r
oup
de
ve
l
opment
on
C
P
S
lea
r
n
ing
S
ta
ge
of
gr
oup
f
or
ma
t
io
n
M
e
tr
ic
s
pe
r
f
or
ma
nc
e
of
gr
oup
f
or
ma
ti
on
[
21, 22]
M
e
a
s
ur
e
me
nt
S
tu
de
nt
G
r
oup
C
la
s
s
F
or
ma
ti
on S
ta
ge
G
r
oup
f
or
ma
ti
on t
im
e
E
f
f
ic
ie
nc
y t
im
e
opt
im
iz
a
ti
on of
s
tu
de
nt
di
s
tr
ib
ut
io
n
in
gr
oups
P
e
r
c
e
nt
a
ge
of
s
tu
de
nt
di
s
tr
ib
ut
io
n
P
e
r
f
or
mi
ng S
ta
ge
C
ol
la
bor
a
ti
on pe
r
f
or
ma
nc
e
(
C
O
)
P
e
e
r
gr
oup me
mbe
r
a
s
s
e
s
s
me
nt
que
s
ti
onna
ir
e
.
K
now
le
dge
P
r
e
-
T
e
s
t
& P
os
t
-
T
e
s
t
S
ki
ll
s
P
r
oj
e
c
t
t
a
s
k
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
.
1
,
F
e
br
ua
r
y
2020
:
199
-
207
202
3.
RE
S
UL
T
S
A
ND
AN
AL
YSI
S
T
his
c
ha
pter
dis
c
us
s
e
s
the
de
ve
lopm
e
nt
of
in
telli
g
e
nt
a
ge
nts
f
o
r
gr
oup
de
ve
lopm
e
nt
on
the
S
KA
C
I
platf
or
m
in
c
ha
pter
3
.
1,
a
nd
the
Ana
lys
is
of
I
ntel
li
ge
nt
a
ge
nt
I
mpl
e
menta
ti
on
in
c
ha
pter
3.
2
.
T
he
s
teps
f
or
de
ve
lopi
ng
a
n
int
e
ll
igent
a
ge
nt
f
or
gr
oup
de
ve
lopm
e
nt
a
r
e
il
lus
tr
a
ted
in
F
igu
r
e
2
.
3.
1.
I
n
t
e
ll
igen
t
age
n
t
f
or
gr
ou
p
d
e
ve
lop
m
e
n
t
T
he
pr
oc
e
s
s
s
tage
s
of
int
e
ll
igent
a
ge
nt
s
of
twa
r
e
f
or
g
r
oup
de
ve
lopm
e
nt
a
r
e
de
picte
d
in
F
igu
r
e
2
.
I
ntelli
ge
nt
a
ge
nts
f
or
gr
oup
de
ve
lopm
e
nt
a
r
e
im
pleme
nted
a
t
the
f
o
r
mation
S
tage
,
in
F
igu
r
e
1
pa
r
t
(
b
)
.
I
ntelli
ge
nt
a
ge
nts
f
or
gr
oup
de
ve
lopm
e
nt
c
ons
is
t
of
3
(
thr
e
e
)
main
f
unc
ti
ona
l
g
r
oups
,
na
mely:
(
1)
c
las
s
if
ying
a
nd
r
a
nking
o
f
M
B
T
I
L
S
a
tt
r
ibu
tes
,
(
2
)
i
nc
r
e
a
s
ing
L
S
M
B
T
I
P
opulation
with
f
uz
z
y
a
lgor
it
hm
,
a
nd
(
3)
gr
oup
f
or
mation
a
lgor
it
h
ms
ba
s
e
d
on
M
B
T
I
r
ules
.
A
de
tailed
e
xplana
ti
on
of
e
a
c
h
s
e
c
ti
on
is
e
xp
laine
d
in
the
s
ub
-
c
ha
pter
be
low.
F
igur
e
2.
P
r
oc
e
s
s
f
lo
w
of
I
ntelli
ge
nt
a
ge
nt
s
of
twa
r
e
3.
1.
1.
Cla
s
s
if
yin
g
a
n
d
r
an
k
in
g
L
S
M
B
T
I
a
t
t
r
ib
u
t
e
s
T
he
M
B
T
I
L
S
da
ta
wa
s
obtaine
d
by
us
ing
the
onli
ne
que
s
ti
onna
ir
e
on
the
S
KA
C
I
i
nter
f
a
c
e
.
C
las
s
if
ying
a
nd
r
a
nking
M
B
T
I
L
S
is
the
f
ir
s
t
s
te
p
to
s
or
t
the
highes
t
leve
l
of
lea
de
r
s
hip
to
the
lo
we
s
t
[
14]
.
T
he
M
B
T
I
L
S
lea
de
r
s
hip
leve
l
is
de
picte
d
in
T
a
ble
2.
T
ier
0
is
the
h
ighes
t
lea
de
r
s
hip
leve
l,
a
nd
ti
e
r
4
is
the
lowe
s
t
lea
de
r
s
hip
leve
l
.
T
he
M
B
T
I
L
S
c
las
s
if
ica
ti
on
a
lgor
it
hm
pr
oc
e
s
s
is
il
lus
tr
a
ted
in
F
igur
e
3
.
T
he
pur
pos
e
of
thi
s
s
t
a
ge
is
to
r
a
nk
lea
de
r
s
hip
f
r
om
highes
t
to
lowe
s
t.
T
he
highes
t
leve
l
of
lea
de
r
s
hip
is
a
pr
ior
it
y
f
or
c
a
ndidate
s
to
be
c
ome
gr
oup
lea
de
r
s
.
F
igur
e
3.
C
las
s
if
ying
a
nd
r
a
nking
of
M
B
T
I
L
S
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
De
v
e
lopme
nt
of
onli
ne
lear
ning
gr
oups
bas
e
d
on
M
B
T
I
lear
ning
s
tyle
…
(
B
udi
L
ak
s
ono
P
utr
o
)
203
3.
1.
2.
I
n
c
r
e
as
in
g
L
S
M
B
T
I
p
op
u
lat
ion
wit
h
f
u
z
z
y
algorit
h
m
An
incr
e
a
s
e
d
population
of
L
S
M
B
T
I
f
or
s
olut
ions
to
dua
l
lea
de
r
s
hip
p
r
oblems
in
g
r
oup
de
ve
lopm
e
nt.
An
incr
e
a
s
e
d
population
of
L
S
M
B
T
I
us
ing
the
f
u
z
z
y
a
lgor
it
hm.
T
he
de
ter
mi
na
ti
on
o
f
the
gr
oup
lea
de
r
us
ing
the
M
B
T
I
r
ules
is
il
lus
tr
a
ted
in
T
a
ble
3
.
I
nc
r
e
a
s
in
g
the
number
of
M
B
T
I
L
S
populations
us
ing
f
uz
z
y
a
lg
or
it
hms
,
il
lus
tr
a
ted
in
F
igu
r
e
4
.
Util
iza
ti
on
of
f
uz
z
y
a
lgor
it
hms
by
c
r
e
a
ti
ng
3
leve
ls
of
M
B
T
I
L
S
leve
ls
:
1
(
h
igh
)
,
2
(
m
e
dium
)
a
nd
3
(
l
ow)
.
T
he
population
leve
l
of
L
S
M
B
T
I
with
the
a
ppli
c
a
ti
on
of
the
f
uz
z
y
a
lgor
it
hm
to
15
leve
ls
a
s
s
hown
in
T
a
ble
3
,
inc
r
e
a
s
ing
the
c
ha
nc
e
s
f
or
the
f
or
mation
of
the
c
ompos
it
ion
of
the
C
P
S
lea
r
ning
gr
oup
.
T
he
f
i
r
s
t
s
tep
is
to
de
ter
mi
ne
the
number
o
f
g
r
o
up
lea
de
r
s
.
T
he
g
r
oup
lea
de
r
is
c
hos
e
n
ba
s
e
d
on
the
highes
t
lea
de
r
s
hip
p
r
ior
it
y
(
T
ier
0
or
ti
e
r
1)
.
T
ier
0
(
E
S
T
J
,
xor
,
I
S
T
J
)
is
the
p
r
ior
it
y
to
be
c
om
e
a
gr
oup
lea
de
r
a
nd
may
not
ha
ve
gr
oup
membe
r
s
with
the
s
a
me
lea
de
r
s
hip
lev
e
l
(
T
ier
0
ie
E
S
T
J
,
xor
I
S
T
J
)
.
T
ie
r
1
(
I
NT
J
,
xor
E
NT
J
)
is
the
s
e
c
ond
pr
io
r
it
y
f
or
be
ing
a
gr
oup
lea
de
r
a
nd
may
not
ha
ve
gr
oup
membe
r
s
wit
h
higher
or
e
qua
l
lea
de
r
s
hip
leve
ls
.
T
a
ble
2.
M
B
T
I
tea
m
lea
de
r
r
ole
[
14]
T
e
a
m
L
e
a
de
r
R
ol
e
G
ua
r
di
a
ns
A
r
ti
s
a
ns
I
de
a
li
s
ts
R
a
ti
ona
ls
T
ie
r
0
I
S
T
J
, E
S
T
J
T
ie
r
1
I
S
T
P
,
E
S
T
P
I
nT
J
, I
nT
P
,
E
nT
P
,
E
nT
J
T
ie
r
2
I
S
F
J
, E
S
F
J
I
nF
P
,
E
nF
P
T
ie
r
3
I
nF
J
,
E
nF
J
T
ie
r
4
I
S
F
P
,
E
S
F
P
F
igur
e
4.
I
nc
r
e
a
s
e
d
population
of
L
S
M
B
T
I
us
ing
f
uz
z
y
a
lgor
it
hm
T
a
ble
3.
I
nc
r
e
a
s
e
d
population
o
f
M
B
T
I
L
S
L
e
ve
l
G
ua
r
di
a
ns
A
r
ti
s
a
ns
I
de
a
li
s
ts
R
a
ti
ona
ls
1
I
S
T
J
, E
S
T
J
2
I
S
T
J
, E
S
T
J
3
I
S
T
J
, E
S
T
J
1
I
S
T
P
,
E
S
T
P
I
nT
J
, I
nT
P
, E
nT
P
, E
nT
J
2
I
S
T
P
,
E
S
T
P
I
nT
J
, I
nT
P
, E
nT
P
, E
nT
J
3
I
S
T
P
,
E
S
T
P
I
nT
J
, I
nT
P
, E
nT
P
, E
nT
J
1
I
S
F
J
, E
S
F
J
I
nF
P
, E
nF
P
2
I
S
F
J
, E
S
F
J
I
nF
P
, E
nF
P
3
I
S
F
J
, E
S
F
J
I
nF
P
, E
nF
P
1
I
nF
J
, E
nF
J
2
I
nF
J
, E
nF
J
3
I
nF
J
, E
nF
J
1
I
S
F
P
,
E
S
F
P
2
I
S
F
P
,
E
S
F
P
3
I
S
F
P
,
E
S
F
P
3.
1.
3.
Group
f
or
m
a
t
ion
a
lgorit
h
m
s
b
as
e
d
on
M
B
T
I
r
u
les
Gr
oup
f
or
mation
a
lgor
i
thm
s
ba
s
e
d
on
M
B
T
I
r
ules
a
r
e
r
ules
of
gr
oup
de
ve
lopm
e
nt
ba
s
e
d
on
the
leve
l
of
lea
de
r
s
hip
of
M
B
T
I
L
S
,
a
nd
r
ules
of
c
ompatibi
li
ty
be
twe
e
n
gr
oup
membe
r
s
ba
s
e
d
on
M
B
T
I
L
S
[
14
]
.
S
tage
s
of
s
tudent
dis
tr
ibut
ion
in
gr
oups
ba
s
e
d
on
the
M
B
T
I
e
nne
a
gr
a
m
matr
ix
is
to
de
ter
mi
ne
the
number
of
gr
oup
lea
de
r
s
,
a
nd
the
dis
tr
ibut
ion
of
gr
oup
membe
r
s
.
3.
2.
A
n
alys
is
of
i
m
p
lem
e
n
t
a
t
ion
of
in
t
e
ll
igen
t
a
ge
n
t
Ana
lys
is
of
int
e
ll
igent
a
ge
nt
im
p
leme
ntation
is
ba
s
e
d
on
a
c
ompar
is
on
be
twe
e
n
the
e
xpe
r
im
e
ntal
c
las
s
(
a
pplyi
ng
int
e
ll
igent
a
ge
nt
)
,
a
nd
the
c
ont
r
ol
c
las
s
(
without
int
e
ll
igent
a
ge
nt)
.
T
he
ob
jec
ts
of
thi
s
s
tu
dy
we
r
e
-
2
c
las
s
e
s
of
Da
tab
a
s
e
of
2016
C
omput
e
r
S
c
ienc
e
E
duc
a
ti
on
s
tudy
pr
ogr
a
ms
a
t
UPI
.
One
e
xpe
r
im
e
n
tal
c
las
s
a
nd
one
c
ont
r
ol
c
las
s
,
a
nd
e
a
c
h
c
las
s
c
ons
is
ts
of
36
s
tudents
.
E
a
c
h
c
las
s
is
made
up
of
9
gr
oups
f
or
e
a
c
h
gr
oup
of
4
pe
ople
.
Da
ta
p
r
oc
e
s
s
ing
us
ing
I
B
M
S
P
S
S
S
tat
is
ti
c
s
s
of
twa
r
e
.
T
he
gr
oup
f
o
r
mation
o
f
e
a
c
h
c
las
s
is
s
tatic
a
nd
is
d
one
onc
e
a
t
the
be
ginni
ng
o
f
C
P
S
le
a
r
ning
.
T
e
s
ti
ng
of
int
e
ll
igent
a
ge
nts
f
or
g
r
oup
f
or
mation
us
ing
s
tatis
ti
c
a
l
method
s
pa
ir
e
d
S
a
mpl
e
T
-
T
e
s
t
that
c
ompar
e
s
gr
oups
be
twe
e
n
the
e
xpe
r
im
e
ntal
c
las
s
a
nd
the
c
ontr
ol
c
las
s
.
Qua
nti
tative
a
na
lys
is
of
int
e
ll
igent
a
ge
nts
f
o
r
mi
n
g
gr
oups
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
.
1
,
F
e
br
ua
r
y
2020
:
199
-
207
204
ba
s
e
d
on
the
pe
r
f
or
manc
e
o
f
int
e
ll
igent
a
ge
nts
in
T
a
ble
1.
T
he
r
e
s
ult
s
of
the
pe
r
f
or
manc
e
o
f
int
e
ll
igen
t
a
ge
nts
f
or
g
r
oup
f
o
r
mation
ba
s
e
d
on
5
(
f
ive)
metr
ic
mea
s
ur
e
ments
a
r
e
[
21
,
22]
:
3.
2.
1.
Group
f
or
m
a
t
ion
t
im
e
T
he
e
f
f
e
c
ti
ve
ne
s
s
of
gr
oup
f
or
mation
ti
me
is
c
ompa
r
e
d
be
twe
e
n
the
e
xpe
r
im
e
ntal
c
las
s
a
nd
the
c
ontr
ol
c
las
s
.
T
he
mea
s
ur
e
ment
of
gr
oup
f
or
mation
ti
me
i
s
il
lus
tr
a
ted
in
T
a
ble
4.
T
he
ti
me
f
or
the
e
xpe
r
im
e
ntal
c
las
s
is
15
mi
nutes
,
a
nd
the
c
ontr
ol
c
las
s
is
27
mi
nutes
.
Une
ve
n
gr
oup
c
ompos
it
ion
oc
c
ur
s
in
the
c
ontr
ol
c
l
a
s
s
,
s
o
it
is
ne
c
e
s
s
a
r
y
to
r
e
-
f
or
m
the
g
r
oup.
W
he
r
e
a
s
in
the
e
xpe
r
im
e
ntal
c
las
s
gr
oup
f
o
r
mation
is
only
done
on
c
e
.
T
a
ble
4.
G
r
oup
f
or
mation
ti
me
E
xpe
r
im
e
nt
c
la
s
s
C
ont
r
ol
C
la
s
s
C
ompone
nt
of
gr
oup f
or
ma
ti
on t
im
e
Q
ua
nt
it
y
C
ompone
nt
of
gr
oup f
or
ma
ti
on t
im
e
Q
ua
nt
it
y
O
nl
in
e
que
s
ti
onna
ir
e
M
B
T
I
15 mi
nut
e
s
N
e
got
ia
ti
on be
twe
e
n s
tu
de
nt
s
15 mi
nut
e
s
P
r
oc
e
s
s
in
g of
L
S
M
B
T
I
0
.
564 s
e
c
onds
G
r
oup
f
or
ma
ti
on
12 mi
nut
e
s
G
r
oup
f
or
ma
ti
on by
in
te
ll
ig
e
nt
a
ge
nt
0.596 s
e
c
onds
T
ot
a
l
T
im
e
15 mi
nut
e
s
, 1,133 s
e
c
ond
s
.
T
ot
a
l
T
im
e
27 mi
nut
e
s
3.
2.
2.
Op
t
im
izin
g
t
h
e
d
is
t
r
ib
u
t
ion
o
f
s
t
u
d
e
n
t
s
in
gr
ou
p
s
Optim
izing
the
dis
tr
ibut
ion
of
s
tudents
in
gr
oup
s
f
or
the
e
xpe
r
im
e
ntal
c
las
s
is
100%
,
while
f
or
the
c
ontr
ol
c
las
s
is
90%
.
T
he
c
las
s
e
xpe
r
im
e
nt
is
mor
e
opti
mal
be
c
a
us
e
of
the
c
e
r
tainty
of
t
he
gr
oup
de
ve
lopm
e
nt
r
ules
of
the
M
B
T
I
.
W
hil
e
the
c
ont
r
ol
c
las
s
lea
ve
s
10%
of
s
tudents
who
ha
ve
n’
t
go
tt
e
n
a
gr
oup,
thi
s
is
due
to
the
indi
vidual
matc
h
f
a
c
tor
be
twe
e
n
s
tudents
.
A
r
e
ne
goti
a
ti
on
pr
oc
e
s
s
is
ne
e
de
d
to
dis
tr
ibut
e
the
r
e
maining
10
%
of
s
tudents
.
3.
2.
3.
Collab
or
at
ion
p
e
r
f
or
m
an
c
e
(
C
P
)
C
oll
a
bor
a
ti
on
pe
r
f
or
manc
e
(
C
P
)
is
mea
s
ur
e
d
by
pe
e
r
a
s
s
e
s
s
ment
onli
ne
be
twe
e
n
membe
r
s
in
one
gr
oup.
C
P
is
done
e
ve
r
y
ti
me
a
f
ter
wo
r
king
on
a
c
oll
a
bor
a
ti
ve
pr
ojec
t
a
nd
is
done
3
ti
mes
.
T
he
que
s
ti
onna
ir
e
a
im
s
to
f
ind
out
thr
e
e
C
P
va
lues
,
na
mely
:
pa
r
ti
c
ipati
on
,
pe
r
s
pe
c
ti
ve
thi
nking,
a
nd
s
oc
ial
r
e
gulation.
T
he
a
ve
r
a
ge
C
P
va
lue
in
e
xpe
r
im
e
nt
c
las
s
a
nd
c
ontr
ol
c
las
s
is
il
lus
tr
a
ted
in
F
igu
r
e
5.
C
P
va
lue
in
e
xpe
r
im
e
nt
c
las
s
is
be
tt
e
r
than
c
ontr
ol
c
las
s
.
G
r
oup
c
oll
a
bor
a
ti
on
in
the
e
xpe
r
im
e
ntal
c
las
s
is
be
tt
e
r
than
th
e
c
ontr
ol
c
las
s
.
Gr
oup
c
ompos
it
ion
ba
s
e
d
on
M
B
T
I
r
ules
ha
s
pr
ove
n
to
b
e
a
ble
to
incr
e
a
s
e
gr
oup
c
oll
a
bor
a
ti
on.
F
igur
e
5.
C
oll
a
bor
a
ti
ve
pe
r
f
or
manc
e
(
C
O)
3.
2.
4.
Kn
owle
d
ge
Know
ledge
is
take
n
f
r
om
the
a
ve
r
a
ge
s
c
or
e
of
the
pr
e
-
tes
t
a
nd
pos
t
-
tes
t
f
or
e
a
c
h
s
tudent
c
onduc
ted
onli
ne
on
the
S
KA
C
I
platf
o
r
m.
T
he
c
ompar
is
on
of
p
re
-
tes
t
a
nd
p
os
t
-
t
e
s
t
va
lues
be
twe
e
n
the
e
xpe
r
im
e
ntal
c
las
s
a
nd
the
c
ontr
ol
c
las
s
is
il
lus
tr
a
ted
in
F
igu
r
e
6.
T
he
a
ve
r
a
ge
va
lue
in
the
e
xpe
r
i
menta
l
c
las
s
is
be
tt
e
r
than
the
c
ontr
ol
c
las
s
.
T
he
s
uit
a
bil
it
y
o
f
indi
viduals
in
gr
oups
is
pr
ove
n
to
incr
e
a
s
e
gr
oup
c
oll
a
bor
a
ti
on
a
n
d
knowle
dge
of
e
a
c
h
indi
vidual
.
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
De
v
e
lopme
nt
of
onli
ne
lear
ning
gr
oups
bas
e
d
on
M
B
T
I
lear
ning
s
tyle
…
(
B
udi
L
ak
s
ono
P
utr
o
)
205
F
igur
e
6.
Know
ledge
va
lue
o
f
C
P
S
lea
r
ning
3.
2.
5.
S
k
i
ll
S
kil
ls
a
r
e
take
n
f
r
om
the
va
lue
o
f
s
tudent
pr
o
jec
t
a
s
s
ignm
e
nts
a
s
a
gr
oup.
P
r
ojec
t
tas
ks
a
r
e
pe
r
f
or
med
3
ti
mes
e
it
he
r
in
the
e
xpe
r
im
e
nt
c
las
s
or
in
the
c
on
tr
ol
c
las
s
.
Good
gr
oup
c
oll
a
bor
a
ti
on
will
a
f
f
e
c
t
the
qua
li
ty
of
pr
ojec
t
tas
ks
f
or
e
a
c
h
gr
oup.
T
he
a
ve
r
a
ge
s
kil
l
s
c
or
e
in
the
e
xpe
r
im
e
ntal
c
las
s
is
b
e
tt
e
r
than
the
c
ontr
ol
c
las
s
,
s
hown
in
F
igur
e
7.
T
he
s
kil
l
va
lue
in
the
e
xpe
r
im
e
n
tal
c
las
s
is
s
tr
ongly
inf
luenc
e
d
by
good
g
r
oup
c
oll
a
bor
a
ti
on.
T
he
r
e
s
ult
s
of
the
e
xpe
r
im
e
nt
ba
s
e
d
on
pe
r
f
or
manc
e
metr
ics
on
int
e
ll
igent
a
ge
nts
f
or
gr
oup
de
ve
lopm
e
nt
s
how
that
the
e
xpe
r
i
menta
l
c
las
s
is
mor
e
e
f
f
e
c
ti
ve
than
the
c
ont
r
ol
c
las
s
.
T
he
a
ppli
c
a
ti
on
of
int
e
ll
igent
a
ge
nts
f
o
r
gr
oup
de
ve
lopm
e
nt
ba
s
e
d
o
n
M
B
T
I
r
ules
ha
s
a
pos
it
ive
e
f
f
e
c
t
on
gr
oup
c
oll
a
bor
a
ti
on.
I
nc
r
e
a
s
e
d
gr
oup
c
oll
a
bor
a
ti
on
ha
s
a
pos
it
ive
e
f
f
e
c
t
on
the
va
lue
of
s
kil
ls
a
nd
knowle
dge
both
f
o
r
ind
ivi
dua
ls
a
nd
gr
oups
.
F
igur
e
7.
S
kil
ls
in
C
P
S
lea
r
ning
4.
CONC
L
USI
ON
Gr
oup
de
ve
lopm
e
nt
ba
s
e
d
on
M
B
T
I
r
ules
ha
s
p
r
ov
e
n
s
uc
c
e
s
s
f
ul
f
or
the
e
duc
a
ti
on
a
nd
indus
tr
y
e
nvir
onment.
M
B
T
I
idea
l
g
r
oup
r
ules
a
r
e
a
c
hieve
d
whe
n
a
gr
oup
lea
de
r
with
the
highes
t
leve
l
of
le
a
de
r
s
hip,
a
nd
c
ompatibi
li
ty
be
twe
e
n
g
r
oup
membe
r
s
.
T
he
leve
l
of
lea
de
r
s
hip
a
nd
s
uit
a
bil
it
y
of
gr
oup
me
mber
s
is
de
t
e
r
mi
ne
d
ba
s
e
d
on
the
M
B
T
I
L
S
.
P
r
oblems
a
r
is
e
whe
n
the
population
o
f
M
B
T
I
L
S
with
the
h
ighes
t
leve
l
of
lea
de
r
s
hip
is
ove
r
.
T
his
will
lea
d
to
dua
l
lea
de
r
s
hip
pr
oblems
a
nd
ha
ve
a
n
im
pa
c
t
on
gr
oup
dis
ha
r
mony.
T
his
s
tudy
pr
opos
e
s
a
n
int
e
ll
igent
a
ge
nt
s
of
twa
r
e
f
or
th
e
de
ve
lopm
e
nt
of
the
idea
l
gr
oup
of
M
B
T
I
,
us
ing
t
he
f
uz
z
y
a
lgor
it
hm.
F
uz
z
y
a
lgor
it
hm
f
or
s
olvi
ng
dua
l
lea
de
r
s
hip
pr
oblems
in
a
gr
oup
.
F
uz
z
y
a
lgor
it
hm
is
us
e
d
to
incr
e
a
s
e
the
population
of
M
B
T
I
L
S
to
3
leve
ls
,
na
mely
low
,
medium,
a
nd
high.
I
nc
r
e
a
s
ing
t
he
population
o
f
M
B
T
I
L
S
c
a
n
incr
e
a
s
e
the
pr
oba
bil
it
y
o
f
f
or
mi
ng
a
n
idea
l
g
r
oup
of
M
B
T
I
.
I
ntelli
ge
nt
a
ge
nt
is
s
uc
c
e
s
s
f
ul
in
s
olvi
ng
dua
l
lea
de
r
s
hip
pr
oblems
.
T
he
tes
t
r
e
s
ult
s
in
the
e
xpe
r
im
e
ntal
c
las
s
(
a
pplyi
ng
int
e
ll
igent
a
ge
nts
)
a
r
e
be
tt
e
r
than
th
e
c
ontr
ol
c
las
s
(
without
int
e
ll
igent
a
ge
nts
)
.
I
ntelli
g
e
nt
a
ge
nt
pe
r
f
or
manc
e
mea
s
ur
e
ment
ba
s
e
d
on
5
(
f
ive)
mea
s
ur
e
ment
metr
ics
,
na
mely:
g
r
oup
f
o
r
mation
ti
me,
opti
mi
z
a
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
.
1
,
F
e
br
ua
r
y
2020
:
199
-
207
206
of
s
tudent
dis
tr
ibut
ion
to
gr
oups
,
c
oll
a
bor
a
ti
on
pe
r
f
or
manc
e
(
C
O)
,
k
nowle
dge
,
a
nd
s
kil
ls
.
I
t
wa
s
c
onc
luded
that
the
de
ve
lopm
e
nt
of
int
e
ll
igent
a
ge
nts
ha
d
a
pos
it
ive
e
f
f
e
c
t
f
or
gr
oup
de
ve
lopm
e
nt
b
a
s
e
d
on
the
M
B
T
I
L
S
.
AC
KNOWL
E
DGE
M
E
NT
S
P
r
a
is
e
Allah
f
or
a
ll
the
bles
s
ings
that
He
ha
s
give
n.
T
ha
nks
a
ls
o
to
our
pa
r
e
nts
,
wif
e
,
c
hil
dr
e
n
a
nd
f
r
iends
f
or
their
pa
r
t
icipa
ti
on
a
nd
s
uppor
t,
a
nd
to
t
he
I
ndone
s
ian
M
ini
s
tr
y
of
E
duc
a
ti
on
a
nd
F
inanc
e
M
ini
s
tr
y
f
or
the
f
unding
of
the
B
UD
I
-
DN
s
c
holar
s
hip
.
RE
F
E
RE
NC
E
S
[1
]
M.
E
.
W
eb
b
et
al
.
,
“Ch
al
l
en
g
es
fo
r
IT
‑
E
n
a
b
l
e
d
Fo
rmat
i
v
e
A
s
s
e
s
s
me
n
t
o
f
Co
m
p
l
e
x
2
1
s
t
Cen
t
u
r
y
Sk
i
l
l
s
,
”
Tech
n
o
l
.
Kn
o
wl
.
Lea
r
n
.
,
v
o
l
.
2
3
,
n
o
.
3
,
p
p
.
4
4
1
–
4
5
6
,
A
u
g
2
0
1
8
.
[2
]
P.
G
ri
ffi
n
an
d
E
.
Care,
“A
s
s
es
s
men
t
an
d
t
each
i
n
g
o
f
2
1
s
t
ce
n
t
u
ry
s
k
i
l
l
s
,
”
B
r
.
J.
E
d
u
c.
Tech
n
o
l
.
,
v
o
l
.
4
6
,
n
o
.
4
,
p
p
.
E
1
5
–
E
1
6
,
2
0
1
5
.
[3
]
J
.
K
h
l
ai
s
an
g
an
d
N
.
So
n
g
k
ram,
“D
e
s
i
g
n
i
n
g
a
V
i
r
t
u
a
l
L
earn
i
n
g
E
n
v
i
r
o
n
me
n
t
S
y
s
t
em
fo
r
T
eac
h
i
n
g
T
w
e
n
t
y
-
F
i
rs
t
Cen
t
u
ry
Sk
i
l
l
s
t
o
H
i
g
h
er
E
d
u
ca
t
i
o
n
St
u
d
e
n
t
s
i
n
A
SE
A
N
,
”
Tech
n
o
l
.
Kn
o
w
l
.
Lea
r
n
.
,
v
o
l
.
2
4
,
n
o
.
1
,
p
p
.
4
1
-
6
3
,
2
0
1
9
.
[4
]
A.
T
ri
ay
u
d
i
an
d
I.
Fi
t
ri
,
“A
n
ew
a
g
g
l
o
mera
t
i
v
e
h
i
erarc
h
i
cal
cl
u
s
t
er
i
n
g
t
o
mo
d
el
s
t
u
d
en
t
act
i
v
i
t
y
i
n
o
n
l
i
n
e
l
ear
n
i
n
g
,
”
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
.
1
7
,
n
o
.
3
,
p
p
.
1
2
2
6
-
1
2
3
5
,
J
u
n
e
2
0
1
9
.
[5
]
Ras
i
m
Ras
i
m,
Y
.
Ro
s
man
s
y
a
h
,
A
.
Z
.
R
.
L
an
g
i
,
an
d
Mu
n
i
r
Mu
n
i
r
,
“Sel
ect
i
o
n
o
f
L
earn
i
n
g
Mat
er
i
al
s
Bas
ed
o
n
St
u
d
e
n
t
s
'
Beh
av
i
o
r
s
i
n
3
D
M
U
V
L
E
,
”
T
E
LKO
M
NIKA
Te
l
eco
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
cs
a
n
d
C
o
n
t
r
o
l
,
v
o
l
.
1
6
,
n
o
.
5
,
p
p
.
2
1
2
7
–
2
1
3
6
,
2
0
1
8
.
[6
]
T
.
O
k
t
a
v
i
a,
H
.
L
.
H
.
S.
W
arn
ars
,
an
d
S.
A
d
i
,
“
Co
n
cep
t
u
al
Mo
d
el
o
f
K
n
o
w
l
e
d
g
e
Man
a
g
emen
t
an
d
So
c
i
al
Me
d
i
a
t
o
Su
p
p
o
rt
L
earn
i
n
g
Pro
ce
s
s
i
n
H
i
g
h
er
E
d
u
cat
i
o
n
In
s
t
i
t
u
t
i
o
n
,
”
TE
LK
O
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
cs
a
n
d
C
o
n
t
r
o
l
,
v
o
l
.
1
5
,
n
o
.
2
,
p
p
.
6
7
8
-
6
8
5
,
J
u
n
e
201
7
.
[7
]
S.
Is
o
t
an
i
,
A
.
In
ab
a,
M.
Ik
ed
a,
an
d
R.
Mi
zo
g
u
ch
i
,
“A
n
o
n
t
o
l
o
g
y
en
g
i
n
eeri
n
g
ap
p
ro
ac
h
t
o
t
h
e
real
i
za
t
i
o
n
o
f
t
h
e
o
ry
-
d
ri
v
en
g
r
o
u
p
fo
rma
t
i
o
n
,
”
In
t
.
J.
Co
m
p
u
t
.
Co
l
l
a
b
.
Lea
r
n
.
,
v
o
l
.
4
,
n
o
.
4
,
p
p
.
4
4
5
–
4
7
8
,
A
u
g
.
2
0
0
9
.
[8
]
N
.
Maq
t
ar
y
,
A
.
M
o
h
s
en
,
a
n
d
K
.
Bech
k
o
u
m,
“G
ro
u
p
F
o
rmat
i
o
n
T
ec
h
n
i
q
u
es
i
n
Co
mp
u
t
er
-
Su
p
p
o
rt
e
d
Co
l
l
a
b
o
ra
t
i
v
e
L
earn
i
n
g
:
A
S
y
s
t
emat
i
c
L
i
t
erat
u
re
Rev
i
ew
,
”
Tech
n
o
l
.
Kn
o
wl
.
Lea
r
n
.
,
v
ol.
2
4
,
n
o
.
2
,
p
p
.
1
–
2
2
,
J
u
n
e
2
0
1
9
.
[9
]
I.
Srb
a
an
d
M.
Bi
el
i
k
o
v
a,
“D
y
n
am
i
c
G
ro
u
p
Fo
rmat
i
o
n
as
an
A
p
p
r
o
ach
t
o
Co
l
l
a
b
o
rat
i
v
e
L
earn
i
n
g
Su
p
p
o
r
t
,
”
in
I
E
E
E
Tr
a
n
s
a
c
t
i
o
n
s
o
n
Lea
r
n
i
n
g
Tec
h
n
o
l
o
g
i
es
,
v
o
l
.
8
,
n
o
.
2
,
p
p
.
1
7
3
-
1
8
6
,
1
A
p
ri
l
-
J
u
n
e
2
0
1
5
.
[1
0
]
R.
C.
D
.
Rei
s
,
S.
Is
o
t
an
i
,
C.
L
.
Ro
d
ri
g
u
ez,
K
.
T
.
L
y
r
a,
P.
A
.
J
aq
u
e
s
,
an
d
I.
I.
Bi
t
t
e
n
c
o
u
r
t
,
“A
ffect
i
v
e
s
t
a
t
e
s
i
n
co
mp
u
t
er
-
s
u
p
p
o
rt
e
d
co
l
l
ab
o
rat
i
v
e
l
ear
n
i
n
g
:
St
u
d
y
i
n
g
t
h
e
p
a
s
t
t
o
d
r
i
v
e
t
h
e
fu
t
u
re,
”
Co
m
p
u
t
.
E
d
u
c.
,
v
o
l
.
1
2
0
,
n
o
.
May
,
p
p
.
2
9
–
5
0
,
2
0
1
8
.
[1
1
]
A
.
A
.
v
o
n
D
a
v
i
er,
J
.
H
a
o
,
L
.
L
i
u
,
an
d
P.
K
y
l
l
o
n
e
n
,
“In
t
erd
i
s
ci
p
l
i
n
ar
y
res
earc
h
ag
en
d
a
i
n
s
u
p
p
o
r
t
o
f
as
s
es
s
men
t
o
f
co
l
l
ab
o
rat
i
v
e
p
ro
b
l
em
s
o
l
v
i
n
g
:
l
es
s
o
n
s
l
earn
e
d
fro
m
d
ev
el
o
p
i
n
g
a
Co
l
l
a
b
o
ra
t
i
v
e
Sci
e
n
ce
A
s
s
e
s
s
me
n
t
Pr
o
t
o
t
y
p
e,
”
Co
m
p
u
t
.
H
u
m
a
n
B
eh
a
v.
,
v
o
l
.
7
6
,
p
p
.
6
3
1
–
6
4
0
,
N
o
v
emb
er
2
0
1
7
.
[1
2
]
S.
L
ai
l
i
y
a
h
,
E
.
Y
u
l
s
i
l
v
i
a
n
a,
an
d
R.
A
n
d
rea,
“Cl
u
s
t
er
i
n
g
an
al
y
s
i
s
o
f
l
earn
i
n
g
s
t
y
l
e
o
n
an
g
g
a
n
a
h
i
g
h
s
ch
o
o
l
s
t
u
d
e
n
t
,
”
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
.
1
7
,
n
o
.
3
,
p
p
.
1
4
0
9
-
1
4
1
6
,
J
u
n
e
2
0
1
9
.
[1
3
]
S.
Mi
rza
ei
an
d
A
.
F.
H
ay
at
i
,
“E
ffect
s
o
f
t
h
e
co
mp
u
t
er
med
i
a
t
ed
co
mm
u
n
i
cat
i
o
n
i
n
t
eract
i
o
n
o
n
v
o
ca
b
u
l
ary
i
mp
r
o
v
eme
n
t
,
”
TE
LKO
M
NIKA
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
cs
a
n
d
Co
n
t
r
o
l
,
v
o
l
.
1
6
,
n
o
.
5
,
p
p
.
2
2
1
7
–
2
2
2
5
,
2
0
1
8
.
[1
4
]
S.
T
.
Sh
en
,
S.
D
.
Pri
o
r,
A
.
S.
W
h
i
t
e,
an
d
M.
K
arama
n
o
g
l
u
,
“U
s
i
n
g
p
er
s
o
n
al
i
t
y
t
y
p
e
d
i
ffere
n
ces
t
o
fo
rm
e
n
g
i
n
eer
i
n
g
d
es
i
g
n
t
eams
,
”
E
n
g
.
E
d
u
c.
,
v
o
l
.
2
,
n
o
.
2
,
p
p
.
5
4
–
6
6
,
2
0
0
7
.
[1
5
]
D
.
N
u
rj
a
n
a
h
,
K
.
D
ew
an
t
o
,
an
d
F.
D
.
Sari
,
“H
o
mo
g
en
e
o
u
s
g
ro
u
p
fo
rma
t
i
o
n
i
n
co
l
l
a
b
o
ra
t
i
v
e
l
ear
n
i
n
g
u
s
i
n
g
f
u
zzy
C
-
mean
s
,
”
2
0
1
7
I
E
E
E
6
th
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
er
e
n
ce
o
n
T
ea
ch
i
n
g
,
A
s
s
e
s
s
m
en
t
,
a
n
d
Le
a
r
n
i
n
g
f
o
r
E
n
g
i
n
eer
i
n
g
(TA
LE
)
,
H
o
n
g
K
o
n
g
,
n
o
.
9
7
8
,
p
p
.
7
4
–
79
,
2
0
1
7
.
[1
6
]
S.
G
h
o
s
h
an
d
S.
K
.
D
u
b
e
y
,
“Co
mp
ara
t
i
v
e
A
n
a
l
y
s
i
s
o
f
K
-
Mean
s
an
d
Fu
zzy
C
-
Mean
s
A
l
g
o
r
i
t
h
ms
,
”
In
t
.
J.
A
d
v.
Co
m
p
u
t
.
S
ci
.
A
p
p
l
.
,
v
o
l
.
4
,
n
o
.
4
,
p
p
.
3
5
–
3
9
,
May
2
0
1
3
.
[1
7
]
C.
E
.
Ch
ri
s
t
o
d
o
u
l
o
p
o
u
l
o
s
an
d
K
.
A
.
Pap
a
n
i
k
o
l
ao
u
,
“A
g
ro
u
p
f
o
rmat
i
o
n
t
o
o
l
i
n
a
E
-
L
earn
i
n
g
c
o
n
t
ex
t
,
”
19
th
IE
E
E
In
t
e
r
n
a
t
i
o
n
a
l
Co
n
f
er
e
n
ce
o
n
To
o
l
s
w
i
t
h
A
r
t
i
f
i
c
i
a
l
In
t
el
l
i
g
en
ce
(ICTA
I
2
0
0
7
)
,
Pat
ra
s
,
p
p
.
1
1
7
-
1
2
3
,
2
0
0
7
.
[1
8
]
Y
.
A
.
Po
l
l
al
i
s
an
d
G
.
Mav
ro
mmat
i
s
,
“U
s
i
n
g
s
i
mi
l
ar
i
t
y
meas
u
re
s
fo
r
co
l
l
a
b
o
ra
t
i
n
g
g
ro
u
p
s
fo
rmat
i
o
n
:
A
mo
d
e
l
fo
r
d
i
s
t
a
n
ce
l
earn
i
n
g
en
v
i
r
o
n
me
n
t
s
,
”
E
u
r
.
J.
O
p
er
.
R
e
s
.
,
v
o
l
.
1
9
3
,
n
o
.
2
,
p
p
.
6
2
6
–
6
3
6
,
Mar
2
0
0
9
.
[1
9
]
K
rzy
s
zt
o
f
A
p
t
,
"
Pri
n
ci
p
l
e
s
o
f
c
o
n
s
t
ra
i
n
t
p
ro
g
rammi
n
g
,
"
Camb
ri
d
g
e
:
Camb
ri
d
g
e
U
n
i
v
er
s
i
t
y
Pres
s
,
2
0
0
3
.
[2
0
]
F.
Ro
s
s
i
,
P.
V
an
Beek
,
an
d
T
.
W
a
l
s
h
,
"
H
an
d
b
o
o
k
o
f
Co
n
s
t
ra
i
n
t
Pro
g
rammi
n
g
(F
o
u
n
d
a
t
i
o
n
s
o
f
A
r
t
i
f
i
ci
al
I
n
t
e
l
l
i
g
e
n
ce)
,
"
2
0
0
6
.
[2
1
]
A
.
O
u
n
n
a
s
,
D
.
E
.
Mi
l
l
ard
,
an
d
H
.
C.
D
av
i
s
,
“A
me
t
ri
c
s
f
ramew
o
r
k
fo
r
ev
a
l
u
a
t
i
n
g
g
ro
u
p
fo
rma
t
i
o
n
,
”
P
r
o
ceed
i
n
g
s
o
f
t
h
e
2
0
0
7
i
n
t
e
r
n
a
t
i
o
n
a
l
A
CM
c
o
n
f
er
e
n
ce
o
n
S
u
p
p
o
r
t
i
n
g
g
r
o
u
p
wo
r
k
,
p
p
.
2
2
1
–
2
2
4
,
N
o
v
.
2
0
0
7
.
[2
2
]
I.
W
u
an
d
W
.
Ch
en
,
“E
v
al
u
at
i
n
g
t
h
e
e
-
l
earn
i
n
g
p
l
a
t
fo
rm
f
ro
m
t
h
e
p
ers
p
ect
i
v
e
o
f
k
n
o
w
l
ed
g
e
man
ag
eme
n
t
:
T
h
e
A
H
P
ap
p
r
o
ach
,
”
J.
Li
b
r
.
In
f
.
S
t
u
d
.
,
v
o
l
.
1
1
,
n
o
.
1
,
p
p
.
1
–
2
4
,
J
u
n
e
2
0
1
3
.
[2
3
]
G
.
St
ah
l
,
T
.
K
o
s
ch
ma
n
n
,
a
n
d
D
.
S
u
t
h
ers
,
“C
o
mp
u
t
er
-
s
u
p
p
o
r
t
ed
c
o
l
l
ab
o
rat
i
v
e
l
ear
n
i
n
g
:
A
n
h
i
s
t
o
ri
ca
l
p
er
s
p
ec
t
i
v
e,
”
Camb
ri
d
g
e
H
a
n
d
b
.
L
earn
.
Sci
.
,
p
p
.
4
0
9
–
4
2
6
,
J
an
2
0
0
6
.
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
De
v
e
lopme
nt
of
onli
ne
lear
ning
gr
oups
bas
e
d
on
M
B
T
I
lear
ning
s
tyle
…
(
B
udi
L
ak
s
ono
P
utr
o
)
207
[2
4
]
K
.
H
.
A
l
l
e
h
ai
b
i
an
d
N
.
N
.
A
l
b
aq
am
i
,
“A
U
n
i
fi
e
d
Q
u
a
l
i
t
y
C
o
n
t
ro
l
Mo
d
e
l
fo
r
E
-
L
earn
i
n
g
Sy
s
t
ems
,
”
In
t
.
J.
E
l
e
ct
r
.
Co
m
p
u
t
.
E
n
g
.
,
v
o
l
.
7
,
n
o
.
3
,
p
p
.
1
3
5
5
–
1
3
6
6
,
J
u
n
e
2
0
1
7
.
[2
5
]
A
.
H
i
d
a
y
at
an
d
V
.
G
.
U
t
o
mo
,
“A
d
ap
t
i
v
e
O
n
l
i
n
e
Mo
d
u
l
e
Pro
t
o
t
y
p
e
fo
r
L
earn
i
n
g
U
n
i
f
i
ed
Mo
d
el
l
i
n
g
L
an
g
u
ag
e
(U
ML
),
”
In
t
.
J.
E
l
ect
r
.
Co
m
p
u
t
.
E
n
g
.
,
v
o
l
.
6
,
n
o
.
6
,
p
p
.
2
9
3
1
–
2
9
3
8
,
D
ecem
b
er
2
0
1
6
.
[2
6
]
P.
T
ch
o
u
n
i
k
i
n
e,
N
.
Ru
mmel
,
an
d
B.
M.
Mc
L
aren
,
“C
o
mp
u
t
er
Su
p
p
o
r
t
ed
Co
l
l
a
b
o
ra
t
i
v
e
L
earn
i
n
g
an
d
In
t
e
l
l
i
g
en
t
T
u
t
o
r
i
n
g
Sy
s
t
ems
,
”
A
d
v.
In
t
e
l
l
.
Tu
t
o
r
i
n
g
S
ys
t
.
,
p
p
.
4
4
7
–
4
6
3
,
2
0
1
0
.
[2
7
]
M.
R.
M.
V
eeraman
i
ck
am
an
d
N
.
Rad
h
i
k
a,
“A
Smar
t
E
-
L
earn
i
n
g
Sy
s
t
em
f
o
r
So
ci
a
l
N
e
t
w
o
rk
i
n
g
,
”
In
t
.
J.
E
l
e
ct
r
.
Co
m
p
u
t
.
E
n
g
.
,
v
o
l
.
4
,
n
o
.
3
,
p
p
.
4
4
7
–
4
5
5
,
J
u
n
e
20
14.
[2
8
]
P.
G
ri
ffi
n
,
“A
s
s
es
s
i
n
g
c
o
l
l
ab
o
rat
i
v
e
p
ro
b
l
em
s
o
l
v
i
n
g
,
"
[O
n
l
i
n
e],
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s
:
/
/
i
n
s
e
g
n
an
t
i
d
u
e
p
u
n
t
o
zero
.
fi
l
es
.
w
o
r
d
p
re
s
s
.
co
m
/
2
0
1
7
/
0
1
/
as
s
es
s
i
n
g
-
c
o
l
l
ab
o
rat
i
v
e
-
p
ro
b
l
em
s
o
l
v
i
n
g
_
p
_
g
ri
ff
i
n
.
p
d
f
,
2
0
1
7
.
[2
9
]
F.
K
o
ch
an
d
D
.
B.
E
d
s
,
"
A
d
v
an
ce
s
i
n
S
o
ci
a
l
Co
mp
u
t
i
n
g
an
d
Mu
l
t
i
ag
e
n
t
S
y
s
t
ems
,
"
6
th
In
t
er
n
a
t
i
o
n
a
l
W
o
r
ks
h
o
p
o
n
Co
l
l
a
b
o
r
a
t
i
ve
A
g
en
t
s
R
e
s
ea
r
ch
a
n
d
D
evel
o
p
m
en
t
,
CA
R
E
2
0
1
5
a
n
d
S
eco
n
d
In
t
er
n
a
t
i
o
n
a
l
W
o
r
k
s
h
o
p
o
n
M
u
l
t
i
a
g
en
t
F
o
u
n
d
a
t
i
o
n
s
o
f
S
o
c
i
a
l
Co
m
p
u
t
i
n
g
,
M
F
S
C
2
0
1
5
,
v
o
l
.
5
4
1
,
May
2
0
1
5
.
B
I
OG
RA
P
HI
E
S
OF
AU
T
HO
RS
Budi
La
ks
o
no
P
utro
rece
i
v
e
d
h
i
s
b
ach
e
l
o
r
d
e
g
ree
i
n
co
mp
u
t
er
s
ci
e
n
ce
fro
m
U
n
i
v
er
s
i
t
as
Pad
j
a
d
j
ara
n
,
Ban
d
u
n
g
,
In
d
o
n
es
i
a,
i
n
2
0
0
2
,
an
d
h
i
s
mas
t
er
d
eg
ree
at
t
h
e
Sch
o
o
l
o
f
E
l
ec
t
ri
ca
l
E
n
g
i
n
eeri
n
g
an
d
In
f
o
rmat
i
cs
(S
T
E
I),
IT
B,
Ban
d
u
n
g
,
I
n
d
o
n
e
s
i
a,
i
n
2
0
1
0
.
H
e
i
s
c
u
rren
t
l
y
w
o
r
k
i
n
g
t
o
w
ard
a
d
o
c
t
o
ra
l
d
eg
ree
at
t
h
e
Sch
o
o
l
o
f
E
l
e
ct
ri
ca
l
E
n
g
i
n
eeri
n
g
an
d
In
fo
rmat
i
cs
,
IT
B.
H
e
w
o
rk
s
fo
r
In
d
o
n
es
i
a
U
n
i
v
er
s
i
t
y
o
f
E
d
u
ca
t
i
o
n
i
n
t
h
e
Co
m
p
u
t
er
Sci
en
ce
E
d
u
ca
t
i
o
n
fi
el
d
.
H
e
i
s
cu
rren
t
l
y
a
memb
er
o
f
t
h
e
Serv
i
ce
s
Co
mp
u
t
i
n
g
Res
earc
h
G
ro
u
p
(SCRG
)
o
f
SE
E
I
IT
B.
H
i
s
cu
rren
t
res
earch
i
n
t
ere
s
t
i
n
cl
u
d
e
s
mo
b
i
l
e
l
earn
i
n
g
t
ech
n
o
l
o
g
i
e
s
,
s
erv
i
ce
co
m
p
u
t
i
n
g
,
s
o
ft
w
are
en
g
i
n
eeri
n
g
,
an
d
i
n
fo
rma
t
i
o
n
s
y
s
t
ems
.
Y
us
ep
R
o
s
m
a
n
s
y
a
h
recei
v
e
d
t
h
e
B.
S.
d
eg
ree
fro
m
Ban
d
u
n
g
In
s
t
i
t
u
t
e
o
f
T
ec
h
n
o
l
o
g
y
,
In
d
o
n
e
s
i
a,
i
n
1
9
9
3
,
an
d
b
o
t
h
t
h
e
M.
Sc.
an
d
P
h
.
D
.
d
e
g
ree
s
fro
m
t
h
e
U
n
i
v
ers
i
t
y
o
f
Su
rr
ey
,
U
.
K
.
H
e
h
a
s
b
ee
n
a
re
s
earch
e
r
an
d
an
as
s
o
c
i
at
e
p
ro
fe
s
s
o
r
a
t
t
h
e
Sch
o
o
l
o
f
E
l
ect
r
i
cal
E
n
g
i
n
eeri
n
g
an
d
In
f
o
rm
at
i
cs
,
Ban
d
u
n
g
In
s
t
i
t
u
t
e
o
f
T
ech
n
o
l
o
g
y
(SE
E
I
IT
B),
In
d
o
n
es
i
a.
H
i
s
cu
rre
n
t
res
earc
h
i
n
t
eres
t
i
n
c
l
u
d
es
m
o
b
i
l
e
l
ear
n
i
n
g
t
ech
n
o
l
o
g
i
e
s
an
d
cy
b
er
s
ecu
ri
t
y
.
Suha
rdi
recei
v
ed
t
h
e
b
ac
h
el
o
r
d
eg
ree
i
n
el
ec
t
ri
ca
l
en
g
i
n
eeri
n
g
fro
m
t
h
e
Ba
n
d
u
n
g
In
s
t
i
t
u
t
e
o
f
T
ech
n
o
l
o
g
y
,
Ban
d
u
n
g
,
In
d
o
n
es
i
a,
i
n
1
9
8
8
,
t
h
e
mas
t
er
d
eg
ree
i
n
man
ag
em
en
t
fro
m
Parah
y
a
n
g
a
n
Cat
h
o
l
i
c
U
n
i
v
er
s
i
t
y
,
Ban
d
u
n
g
,
In
d
o
n
e
s
i
a,
i
n
2
0
1
2
,
an
d
t
h
e
D
o
c
t
o
r
o
f
E
n
g
i
n
eeri
n
g
d
eg
ree
i
n
t
e
l
eco
mm
u
n
i
ca
t
i
o
n
e
n
g
i
n
eer
i
n
g
fro
m
t
h
e
T
ech
n
i
ca
l
U
n
i
v
er
s
i
t
y
o
f
Berl
i
n
,
Berl
i
n
,
G
erman
y
,
i
n
1
9
9
7
.
H
e
i
s
cu
rre
n
t
l
y
a
n
A
s
s
o
c
i
at
e
Pro
f
es
s
o
r
w
i
t
h
t
h
e
Sch
o
o
l
o
f
E
l
ec
t
ri
ca
l
E
n
g
i
n
eeri
n
g
a
n
d
In
f
o
rmat
i
cs
,
SE
E
I
IT
B.
H
e
i
s
t
h
e
H
ead
o
f
Serv
i
ce
s
Co
m
p
u
t
i
n
g
Res
earch
G
ro
u
p
(SCRG
),
SE
E
I
IT
B.
H
i
s
res
earch
i
n
t
ere
s
t
s
i
n
c
l
u
d
e
s
er
v
i
ce
c
o
mp
u
t
i
n
g
,
IT
v
al
u
e
a
n
d
ri
s
k
,
s
erv
i
ce
s
y
s
t
em
s
en
g
i
n
eer
i
n
g
,
i
n
fo
rmat
i
o
n
an
d
s
o
c
i
al
n
e
t
w
o
rk
s
,
i
n
f
o
rmat
i
o
n
an
d
s
o
ci
a
l
n
e
t
w
o
rk
s
,
i
n
f
o
rmat
i
o
n
g
o
v
ern
a
n
ce
an
d
man
a
g
emen
t
,
an
d
i
n
t
ern
e
t
s
o
ci
e
t
y
an
d
l
a
w
.
Evaluation Warning : The document was created with Spire.PDF for Python.