I
A
E
S
I
n
t
e
r
n
at
io
n
al
Jou
r
n
al
of
A
r
t
if
ic
ia
l
I
n
t
e
ll
ig
e
n
c
e
(
I
J
-
AI
)
V
ol
.
13
, N
o.
4
,
D
e
c
e
m
be
r
2024
, pp.
4334
~
4343
I
S
S
N
:
2252
-
8938
,
D
O
I
:
10.11591/
ij
a
i.
v
13
.i
4
.pp
4334
-
4343
4334
Jou
r
n
al
h
om
e
page
:
ht
tp
:
//
ij
ai
.
ia
e
s
c
or
e
.c
om
E
l
i
gi
b
i
l
i
t
y r
at
e
of
ap
p
l
i
c
an
t
’
s L
i
n
k
e
d
I
n
ac
c
ou
n
t
:
a
n
aï
ve
b
aye
s
c
l
ass
i
f
i
c
at
i
on
an
d
vi
s
u
al
i
z
at
i
on
K
h
yr
in
a A
ir
in
F
ar
i
z
a A
b
u
S
am
ah
1
,
N
u
r
u
l
A
t
h
ir
ah
A
h
m
ad
1
,
A
n
is
A
m
il
ah
S
h
ar
i
1
,
H
an
a F
ak
h
ir
a
A
lm
ar
z
u
k
i
2
,
Z
u
h
r
i
A
r
af
ah
1
,
L
al
a S
e
p
t
e
m
R
iz
a
3
,
A
m
ir
H
ai
k
al
A
b
d
u
l
H
al
im
1
1
C
ol
l
e
ge
of
C
om
put
i
ng, I
nf
or
m
a
t
i
c
s
a
nd M
a
t
he
m
a
t
i
c
s
, U
ni
ve
r
s
i
t
i
T
e
knol
ogi
M
A
R
A
M
e
l
a
k
a
B
r
a
nc
h,
M
e
l
a
ka
, M
a
l
a
ys
i
a
2
C
ol
l
e
ge
of
C
om
put
i
ng, I
nf
or
m
a
t
i
c
s
a
nd
M
a
t
he
m
a
t
i
c
s
, U
ni
ve
r
s
i
t
i
T
e
knol
ogi
M
A
R
A
S
ha
h A
l
a
m
, S
e
l
a
ngor
,
M
a
l
a
y
s
i
a
3
D
e
pa
r
t
m
e
nt
of
C
om
put
e
r
S
c
i
e
nc
e
E
duc
a
t
i
on, U
ni
ve
r
s
i
t
a
s
P
e
ndi
di
ka
n I
ndone
s
i
a
, B
a
ndung, I
ndone
s
i
a
A
r
t
ic
le
I
n
f
o
A
B
S
T
R
A
C
T
A
r
ti
c
le
h
is
to
r
y
:
R
e
c
e
iv
e
d
D
e
c
22
,
2023
R
e
vi
s
e
d
M
a
r
13
,
2024
A
c
c
e
pt
e
d
M
a
r
21
,
2024
In
the
digital
era,
social
media
platforms
like
LinkedIn
have
become
f
amous
for
recruitment,
and
recruiters
widely
use
them
to
find
potential
empl
oyees.
The
recruitment
process
is
crucial
in
organizations,
as
it
involves
se
lecting
qualified applicants from a diverse pool. How
ever, the scree
ning
proce
ss
and
manual
recruitment
process
entail
significant
time,
high
costs,
and
po
tential
bias.
Consequently,
it
may
cause
recruiting
unqualified
applicants
an
d
may
affect
the
organizations.
Thus,
this
study
aims
to
classify
and
generate
a
list
of
potential
job
ap
plicants
by
analyzing
seven
attributes
of
their
Li
nkedIn
accounts:
title,
location
,
skills
,
education
,
language,
certificati
on,
and
years
of
experience.
Data
are
collected
from
LinkedIn
profiles
and
then
under
go
data
pre
-
processing.
The
n
aive
Bayes
(NB)
algorithm
is
implemented
as
the
classifi
cation
algorit
hm
and
sets
the
classifi
cation
as
“
eligibl
e
”
or
“
ineli
gible
”.
The
NB
model
achieved
an
accuracy
testing
of
89.8%,
indicating
good
performance
in
classifying
potential
job
applicants.
At
the
same
time,
we
measure
the
similarity
cosine
score
to
set
the
mean
of
the
eligibilit
y.
The
classifi
cation
results
are
visuali
z
ed
for
the
suitable
applicants
in
desc
ending
rank, allowi
ng users t
o choose th
e applicants
’ classificat
ion statu
s effic
iently
.
For
the
sys
tem
usability,
we
managed
to
get
9
0%
from
the
recruitment
expert.
K
e
y
w
o
r
d
s
:
C
la
s
s
if
ic
a
ti
on
L
in
ke
dI
n
N
a
ïv
e
B
a
ye
s
R
e
c
r
ui
tm
e
nt
V
is
ua
li
z
a
ti
on
This is an
open
acce
ss artic
le unde
r the
CC BY
-
SA
license.
C
or
r
e
s
pon
di
n
g A
u
th
or
:
K
hyr
in
a
A
ir
in
F
a
r
iz
a
A
bu S
a
m
a
h
C
ol
le
ge
of
C
om
put
in
g, I
nf
or
m
a
ti
c
s
a
nd M
a
th
e
m
a
ti
c
s
U
ni
ve
r
s
it
i
T
e
knol
ogi
M
A
R
A
M
e
la
k
a
B
r
a
nc
h,
J
a
s
in
C
a
m
pus
, M
e
r
li
m
a
u, 77300, M
e
la
ka
, M
a
la
ys
ia
E
m
a
il
:
khyr
in
a
783@
ui
tm
.e
du.my
1.
I
N
T
R
O
D
U
C
T
I
O
N
R
e
c
r
ui
tm
e
nt
is
a
c
r
uc
ia
l
a
s
pe
c
t
of
th
e
hum
a
n
r
e
s
our
c
e
s
(
H
R
)
D
e
pa
r
tm
e
nt
a
s
it
in
vol
ve
s
s
e
le
c
ti
ng
e
li
gi
bl
e
c
a
ndi
da
te
s
f
r
om
a
va
s
t
a
ppl
ic
a
nt
pool
[
1]
.
E
m
pl
oyi
ng
a
va
r
ie
ty
of
s
tr
a
te
gi
e
s
is
ne
c
e
s
s
a
r
y
to
lo
c
a
te
,
in
te
r
vi
e
w
,
a
nd
r
e
c
r
ui
t
in
di
vi
dua
ls
f
or
th
e
pos
it
io
n.
T
he
H
R
D
e
pa
r
tm
e
nt
’
s
in
it
ia
l
ta
s
k
is
r
e
c
r
ui
tm
e
nt
to
e
ns
ur
e
e
a
c
h
e
m
pl
oye
e
i
s
c
om
pe
ti
ti
ve
a
nd
c
ont
r
ib
ut
e
s
to
s
o
c
ie
ty
[
2]
.
I
nt
e
r
vi
e
w
e
r
s
a
im
to
id
e
nt
if
y
th
e
m
os
t
s
ui
ta
bl
e
c
a
ndi
da
te
w
ho
f
ul
f
il
s
th
e
e
m
pl
oym
e
nt
r
e
qui
r
e
m
e
nt
s
dur
in
g
th
is
pr
oc
e
s
s
.
A
bba
s
e
t
al
.
[
3]
e
m
pha
s
iz
e
d
th
e
s
ig
ni
f
ic
a
nc
e
of
s
e
le
c
ti
ng
th
e
a
ppr
opr
ia
te
c
a
ndi
da
te
in
c
om
pa
ny
ope
r
a
ti
ons
,
s
ta
ti
ng
th
a
t
c
om
pe
te
nt
e
m
pl
oye
e
s
c
a
n
s
ig
ni
f
ic
a
nt
ly
im
pa
c
t
th
e
s
uc
c
e
s
s
or
f
a
il
ur
e
of
a
n
or
ga
ni
z
a
ti
on
.
L
a
w
ong
e
t
al
.
[
4]
s
ta
te
d
th
a
t
bot
h
th
e
or
ga
ni
z
a
ti
on
a
nd
th
e
a
ge
nt
s
s
ha
r
e
r
e
s
pons
ib
il
it
y
f
or
th
e
e
f
f
e
c
ti
ve
ne
s
s
of
th
e
hi
r
in
g
pr
oc
e
s
s
.
R
e
c
r
ui
te
r
s
pl
a
y
a
c
r
uc
ia
l
r
ol
e
i
n a
n or
ga
ni
z
a
ti
on
’
s
pe
r
f
or
m
a
nc
e
by i
m
pl
e
m
e
nt
in
g
e
f
f
e
c
ti
ve
hi
r
in
g a
nd r
e
c
r
ui
ti
ng
ta
c
ti
c
s
t
o a
tt
r
a
c
t
qua
li
f
ie
d
a
nd
c
om
pe
te
nt
in
di
vi
dua
ls
.
T
h
e
y
a
c
c
om
pl
is
h
th
i
s
by
c
onduc
ti
ng
r
e
s
e
a
r
c
h,
de
s
ig
ni
ng,
a
nd
im
pl
e
m
e
nt
in
g t
he
s
e
t
a
c
ti
c
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
r
ti
f
I
nt
e
ll
I
S
S
N
:
2252
-
8938
E
li
gi
bi
li
ty
r
at
e
of
appli
c
ant
’
s
L
in
k
e
dI
n ac
c
ount
:
a naïv
e
bay
e
s
…
(
K
hy
r
in
a A
ir
in
F
ar
iz
a
A
bu Samah
)
4335
I
n
m
ode
r
n
ti
m
e
s
,
th
e
w
or
ld
ha
s
unde
r
gone
a
di
gi
ta
l
tr
a
n
s
f
or
m
a
ti
on
[
5]
,
in
c
lu
di
ng
s
oc
ia
l
m
e
di
a
pl
a
tf
or
m
s
s
uc
h
a
s
F
a
c
e
book,
L
in
ke
dI
n,
a
nd
T
w
it
te
r
,
w
hi
c
h
a
r
e
m
or
e
popula
r
f
or
r
e
c
r
ui
tm
e
nt
pr
oc
e
s
s
e
s
[
6]
.
L
in
ke
dI
n
is
th
e
pr
im
a
r
y
s
it
e
f
or
c
om
pa
ni
e
s
to
r
e
c
r
ui
t
a
ppl
ic
a
nt
s
a
nd
e
m
pha
s
iz
e
s
c
ul
ti
va
ti
ng
pr
of
e
s
s
io
na
l
c
onne
c
ti
ons
[
7]
,
[
8]
w
it
h
a
us
a
ge
r
a
te
of
77%
c
om
pa
r
e
d
to
ot
he
r
pl
a
tf
or
m
s
[
9]
.
I
t
is
th
e
bi
gge
s
t
onl
in
e
ne
twor
ki
ng
s
it
e
f
or
pr
of
e
s
s
io
na
ls
,
li
nki
ng
m
or
e
th
a
n
900
m
i
ll
io
n
in
di
vi
dua
ls
in
ove
r
200
c
ount
r
ie
s
.
I
t
e
na
bl
e
s
us
e
r
s
to
di
s
c
ove
r
jo
b
ope
ni
ngs
,
br
oa
d
e
n
th
e
ir
pr
of
e
s
s
io
na
l
c
o
nne
c
ti
ons
,
a
nd
a
c
qui
r
e
ne
w
s
ki
ll
s
to
a
c
hi
e
v
e
s
uc
c
e
s
s
in
th
e
ir
c
a
r
e
e
r
s
.
A
c
c
or
di
ng
to
Wei
[
10]
,
M
a
la
ys
ia
ha
s
a
r
ound
5.79
m
il
li
on
L
in
ke
d
I
n
us
e
r
s
,
a
nd
num
e
r
ous
r
e
c
r
ui
te
r
s
pr
e
f
e
r
i
t
f
or
r
e
c
r
ui
t
m
e
nt
pur
pos
e
s
[
11]
.
O
ne
s
te
p
in
th
e
r
e
c
r
ui
tm
e
nt
pr
oc
e
s
s
i
s
th
e
s
c
r
e
e
ni
ng
of
a
ppl
ic
a
ti
ons
[
12]
.
I
t
in
vol
ve
s
e
va
lu
a
ti
ng
jo
b
c
a
ndi
da
te
s
to
a
s
s
e
s
s
th
e
ir
s
ui
ta
bi
li
ty
f
or
a
pos
it
io
n.
H
ow
e
ve
r
,
S
iv
a
na
nda
m
a
nd
M
uda
li
a
r
[
13]
hi
ghl
ig
ht
e
d
th
a
t
r
e
c
r
ui
te
r
s
f
in
d
it
c
ha
ll
e
ngi
ng
to
go
th
r
ough
num
e
r
ous
r
e
s
um
e
s
.
E
xa
m
in
in
g
th
e
a
ppl
ic
a
nt
’
s
r
e
s
um
e
is
a
ti
m
e
-
c
ons
um
in
g
pr
oc
e
s
s
,
le
a
di
ng
to
de
la
ys
a
nd
in
e
f
f
e
c
ti
ve
ti
m
e
m
a
na
ge
m
e
nt
[
14]
.
R
e
c
r
ui
te
r
s
m
us
t
ve
r
if
y
a
nd
e
va
lu
a
te
th
e
m
in
im
a
l
c
r
e
de
nt
ia
l
s
f
or
th
e
jo
b
to
gu
a
r
a
nt
e
e
a
s
u
c
c
e
s
s
f
ul
r
e
c
r
ui
tm
e
nt
pr
oc
e
s
s
a
nd
m
a
ke
a
n
in
f
or
m
e
d
s
e
le
c
ti
on.
A
bba
s
e
t
al
.
[
3]
s
ta
te
d
th
a
t
a
s
c
r
e
e
ni
ng
pr
oc
e
s
s
th
a
t
is
not
e
f
f
e
c
ti
ve
c
oul
d
r
e
s
ul
t
in
ge
ne
r
a
ti
ng
a
r
os
te
r
of
i
na
de
qua
te
ly
qua
li
f
ie
d c
a
ndi
da
te
s
.
M
or
e
ove
r
,
a
m
a
nua
l
r
e
c
r
ui
tm
e
nt
m
e
th
od
ne
c
e
s
s
it
a
te
s
s
ubs
t
a
nt
ia
l
e
xpe
ns
e
s
[
15]
,
[
16]
.
C
os
ts
a
nd
e
xpe
ns
e
s
r
e
la
te
d t
o r
e
c
r
ui
tm
e
nt
m
us
t
be
c
ons
id
e
r
e
d
, s
uc
h a
s
t
im
e
t
o hi
r
e
, r
e
s
um
e
s
c
r
e
e
ni
ng, a
nd r
e
c
r
ui
te
r
f
e
e
s
.
F
ur
th
e
r
m
or
e
,
th
e
e
xpe
ns
e
s
w
oul
d
be
a
t
th
e
ir
hi
ghe
s
t
if
unqua
li
f
ie
d
c
a
ndi
da
te
s
w
e
r
e
s
e
l
e
c
te
d
f
or
th
e
pos
it
io
n.
U
ti
li
z
in
g
in
e
xpe
ns
iv
e
r
e
c
r
ui
tm
e
nt
pr
oc
e
s
s
e
s
m
a
y
r
e
s
ul
t
in
e
r
r
one
ous
s
hor
tl
is
te
d
c
a
ndi
da
te
s
a
s
th
e
y
do
not
a
lwa
ys
e
ns
ur
e
th
e
m
os
t
e
li
gi
bl
e
a
ppl
ic
a
ti
ons
[
17]
.
A
m
a
nua
l
r
e
c
r
ui
tm
e
nt
pr
oc
e
dur
e
m
ig
ht
le
a
d
to
bi
a
s
e
d
out
c
om
e
s
i
nf
lu
e
nc
e
d
by g
e
nde
r
or
huma
n
pe
r
c
e
pt
io
n,
a
f
f
e
c
ti
ng t
he
de
c
i
s
io
n
-
m
a
ki
ng i
n t
he
r
e
c
r
ui
tm
e
nt
pr
oc
e
s
s
[
18]
,
[
19]
.
R
e
c
r
ui
tm
e
nt
bi
a
s
oc
c
ur
s
w
he
n
th
e
r
e
c
r
ui
te
r
a
s
s
e
s
s
e
s
th
e
a
ppl
ic
a
nt
onl
y
ba
s
e
d
on
th
e
ir
in
it
ia
l
im
pr
e
s
s
io
n.
I
t
is
in
f
lu
e
nc
e
d
by
hum
a
n
p
e
r
c
e
pt
io
n,
m
a
ki
ng
in
di
vi
dua
ls
m
or
e
in
c
li
ne
d
to
f
a
vour
a
r
e
s
um
e
w
it
h
a
n a
ppe
a
li
ng pr
of
il
e
i
m
a
ge
.
E
ig
ht
hi
gh
-
de
m
a
nd
voc
a
ti
ons
in
M
a
la
ys
ia
f
or
2022
ha
ve
be
e
n
d
e
te
r
m
in
e
d
ba
s
e
d
on
c
ur
r
e
nt
tr
e
nds
a
nd
in
dus
tr
y
e
s
ti
m
a
te
s
[
20]
.
T
he
li
s
t
c
om
pr
is
e
s
in
f
or
m
a
ti
on
te
c
hnol
ogy
(
I
T
)
,
s
of
twa
r
e
de
ve
lo
pm
e
nt
,
di
gi
ta
l
m
a
r
ke
ti
ng,
f
in
a
nc
e
pos
it
io
n
s
,
pr
oj
e
c
t
m
a
na
ge
m
e
nt
r
ol
e
s
,
bu
s
in
e
s
s
d
e
ve
lo
pm
e
nt
a
nd
s
a
le
s
e
xe
c
ut
iv
e
s
,
m
e
di
c
a
l
pr
of
e
s
s
io
na
ls
,
e
du
c
a
to
r
s
,
a
nd
c
us
to
m
e
r
s
e
r
vi
c
e
e
xe
c
ut
iv
e
s
.
I
T
a
nd
s
of
twa
r
e
de
ve
lo
pm
e
nt
,
di
gi
ta
l
m
a
r
ke
ti
ng,
a
nd f
in
a
nc
e
j
obs
a
r
e
t
he
t
op t
hr
e
e
jo
bs
i
de
nt
if
ie
d by J
obS
tr
e
e
t
a
nd
c
hos
e
n f
or
t
hi
s
r
e
s
e
a
r
c
h
.
J
ob
s
e
e
ke
r
s
s
houl
d
pr
io
r
it
i
z
e
r
e
vi
e
w
in
g
th
e
jo
b
r
e
qui
r
e
m
e
nt
s
in
f
or
m
a
ti
on
th
a
t
c
a
n
pr
ovi
de
in
s
ig
ht
in
to
th
e
s
pe
c
if
ic
jo
b
r
e
qui
r
e
m
e
nt
s
f
or
r
e
c
r
ui
te
r
s
[
21
]
,
[
22
]
.
A
tt
r
ib
u
te
s
li
s
te
d
in
jo
b
li
s
ti
ngs
a
r
e
c
r
uc
ia
l
f
or
r
e
c
r
ui
ti
ng
a
ppr
opr
ia
te
c
a
ndi
da
te
s
.
R
e
s
e
a
r
c
h
e
r
s
id
e
nt
if
ie
d
10
ke
y
f
a
c
to
r
s
f
or
r
e
c
r
ui
te
r
s
to
c
ons
id
e
r
w
he
n
e
va
lu
a
ti
ng
a
jo
b
oppor
tu
ni
ty
:
pos
it
io
n,
s
ki
ll
s
,
e
duc
a
ti
on
le
ve
l
a
nd
hi
s
to
r
y,
la
ngu
a
ge
s
,
ye
a
r
s
of
e
xp
e
r
ie
n
c
e
,
c
e
r
ti
f
ic
a
ti
on,
s
a
la
r
y,
be
ne
f
it
s
,
lo
c
a
ti
on,
a
nd
w
or
ki
ng
hour
s
[
23]
,
[
24
]
.
H
ow
e
ve
r
,
t
hi
s
r
e
s
e
a
r
c
h
f
oc
us
e
s
on
s
e
ve
n
a
tt
r
ib
ut
e
s
f
or
c
la
s
s
if
ic
a
ti
on:
ti
tl
e
,
lo
c
a
ti
on,
e
duc
a
ti
on, ye
a
r
s
of
pr
of
e
s
s
io
na
l
e
xpe
r
ie
nc
e
,
s
ki
ll
s
, l
a
ngua
ge
s
, a
nd c
e
r
ti
f
ic
a
te
s
[
25]
,
[
26]
.
A
w
e
b
-
ba
s
e
d
da
s
hbo
a
r
d
w
a
s
c
r
e
a
te
d
ut
il
i
z
in
g
da
ta
e
xt
r
a
c
t
e
d
f
r
om
L
in
ke
dI
n
pr
o
f
il
e
s
th
a
t
w
e
r
e
s
c
r
a
pe
d
f
r
om
t
he
pl
a
tf
or
m
i
n r
e
s
pons
e
t
o
t
he
i
de
nt
if
ie
d i
s
s
ue
s
.
T
he
n
a
ïv
e
B
a
ye
s
(
N
B
)
a
lg
or
it
hm
w
a
s
ut
il
i
z
e
d
t
o c
la
s
s
if
y
a
nd
vi
s
ua
li
z
e
th
e
L
in
ke
dI
n
a
c
c
ount
s
of
a
ppl
ic
a
nt
s
w
ho
m
e
e
t
th
e
c
om
pa
ny
’
s
jo
b
r
e
qui
r
e
m
e
nt
s
.
T
he
s
ys
t
e
m
ut
il
i
z
e
s
ba
r
c
ha
r
ts
a
nd
pi
e
c
h
a
r
ts
f
or
vi
s
ua
li
z
a
ti
on.
It
a
ll
ow
s
u
s
e
r
s
to
s
e
e
w
hi
c
h
a
ppl
ic
a
ti
ons
f
r
om
th
e
ir
L
in
ke
dI
n
acc
ount
s
m
e
e
t
th
e
r
e
qui
r
e
m
e
nt
s
f
or
th
e
jo
b.
I
t
a
s
s
is
ts
r
e
c
r
ui
te
r
s
i
n
id
e
nt
if
yi
ng
th
e
m
os
t
s
ui
ta
bl
e
c
a
ndi
da
t
e
w
ho
m
e
e
ts
th
e
jo
b
’
s
c
r
it
e
r
ia
.
T
he
pa
p
e
r
is
s
tr
uc
tu
r
e
d
a
s
f
ol
lo
w
s
:
s
e
c
t
io
n
1
c
om
m
e
nc
e
s
w
it
h
a
c
onc
i
s
e
in
tr
oduc
ti
on.
S
e
c
ti
on
2
de
ta
il
s
th
e
a
ppr
oa
c
h,
w
hi
le
s
e
c
ti
on
3
pr
e
s
e
nt
s
th
e
r
e
s
ul
ts
a
nd
di
s
c
u
s
s
io
n.
S
e
c
ti
on
4
e
nds
th
e
s
tu
dy
a
nd
of
f
e
r
s
a
br
ie
f
r
e
vi
e
w
of
pot
e
nt
ia
l
f
ut
ur
e
i
m
p
r
ove
m
e
nt
s
.
2.
R
E
S
E
A
R
C
H
M
E
T
H
O
D
2
.1.
D
e
s
ig
n
of
t
h
e
s
y
s
t
e
m
S
ys
te
m
de
s
ig
n
in
r
e
s
e
a
r
c
h
in
vol
ve
s
de
ve
lo
pi
ng
a
f
r
a
m
e
w
or
k
or
s
tr
uc
tu
r
e
to
in
ve
s
ti
ga
te
a
nd
s
ol
ve
a
s
pe
c
if
ic
r
e
s
e
a
r
c
h
i
s
s
ue
.
W
e
de
li
be
r
a
te
d
on
th
e
c
om
pr
e
he
ns
iv
e
s
y
s
te
m
a
r
c
hi
te
c
tu
r
e
,
s
ys
te
m
f
lo
w
,
in
te
r
f
a
c
e
s
,
a
nd
th
e
da
ta
pe
r
ta
in
in
g
to
th
e
s
y
s
te
m
ne
e
d
s
.
D
ur
in
g
th
is
s
ta
ge
,
w
e
ut
il
i
z
e
a
u
s
e
c
a
s
e
di
a
gr
a
m
a
nd
a
f
lo
w
c
ha
r
t
di
a
gr
a
m
to
il
lu
s
tr
a
te
th
e
w
or
kf
lo
w
.
U
s
e
r
in
te
r
f
a
c
e
(
U
I
)
is
th
e
ul
ti
m
a
te
s
t
a
ge
in
th
e
de
s
ig
n
pr
oc
e
s
s
.
T
h
e
te
r
m
pe
r
ta
in
s
to
th
e
vi
s
ua
l
a
r
r
a
nge
m
e
nt
of
th
e
s
ys
te
m
c
om
pone
nt
s
th
a
t
a
us
e
r
c
a
n
e
nga
ge
w
it
h
on
a
w
e
bs
it
e
.
U
I
de
s
ig
n
s
houl
d
be
e
f
f
e
c
ti
ve
a
nd
us
e
r
-
c
e
nt
r
ic
to
gua
r
a
nt
e
e
us
e
r
-
f
r
ie
ndl
in
e
s
s
a
nd
a
ppe
a
l
to
pot
e
nt
ia
l
us
e
r
s
.
I
t
s
tr
iv
e
s
to
s
tr
e
a
m
li
ne
th
e
us
e
r
’
s
i
nt
e
r
a
c
ti
on t
o e
f
f
ic
ie
nt
ly
a
c
hi
e
ve
t
he
ir
goa
ls
w
it
hi
n t
h
e
s
ys
te
m
.
2
.
2
.
B
ac
k
-
e
n
d
d
e
ve
lo
p
m
e
n
t
B
a
c
k
-
e
nd
de
v
e
lo
pm
e
nt
in
c
lu
de
s
ga
th
e
r
in
g,
pr
e
pa
r
in
g,
a
nd
a
ppl
yi
ng
th
e
N
B
m
ode
l,
a
s
s
e
e
n
in
F
ig
ur
e
1.
T
he
di
a
gr
a
m
i
ll
us
tr
a
te
s
th
e
s
ys
te
m
’
s
ope
r
a
ti
on
f
r
om
da
ta
c
ol
le
c
ti
ng
in
it
ia
ti
on
to
vi
s
ua
li
z
a
ti
on
c
om
pl
e
ti
on.
D
a
ta
pr
e
pa
r
a
ti
on
in
c
lu
de
s
c
ol
le
c
ti
ng
a
nd
pr
e
-
pr
oc
e
s
s
in
g
da
ta
to
gua
r
a
nt
e
e
it
s
r
e
li
a
bi
li
ty
,
a
nd
th
e
n
us
in
g a
n N
B
c
la
s
s
if
ie
r
f
or
c
a
te
gor
iz
a
ti
on. T
he
out
put
c
on
s
is
ts
of
bot
h vi
s
ua
li
z
e
d a
nd r
e
por
te
d da
ta
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8938
I
nt
J
A
r
ti
f
I
nt
e
ll
, V
ol
.
13
, N
o.
4
,
D
e
c
e
m
be
r
2024
:
4334
-
4343
4336
F
ig
ur
e
1.
R
e
s
e
a
r
c
h de
s
ig
n f
lo
w
di
a
gr
a
m
f
or
L
in
ke
dI
n e
li
gi
bi
l
it
y
2
.2.1.
D
at
a
c
ol
le
c
t
io
n
an
d
p
r
e
-
p
r
oc
e
s
s
in
g
D
a
ta
w
a
s
c
ol
l
e
c
te
d
by
w
e
b
s
c
r
a
pi
ng
f
r
om
S
e
pt
e
m
be
r
1,
202
2,
to
M
a
r
c
h
31,
2023,
ut
il
i
z
in
g
th
e
s
e
le
ni
um
a
nd be
a
ut
if
ul
s
oup pa
c
ka
ge
s
in
P
yt
hon. S
e
le
ni
um
i
s
a
pot
e
nt
i
ns
tr
um
e
nt
f
or
m
a
na
gi
ng w
e
b br
ow
s
e
r
s
a
nd e
xe
c
ut
in
g br
ow
s
e
r
a
ut
om
a
ti
on
[
27]
. T
hi
s
s
tu
dy i
nvol
ve
s
us
in
g
s
e
le
ni
um
t
o a
ut
om
a
te
t
he
L
in
ke
dI
n pa
ge
t
o
e
xt
r
a
c
t
a
ppl
ic
a
nt
da
ta
.
S
ubs
e
que
nt
ly
,
be
a
ut
if
ul
s
oup
w
a
s
ut
il
i
z
e
d
to
r
e
tr
ie
ve
th
e
L
in
ke
dI
n
pr
of
il
e
in
f
or
m
a
ti
on.
T
he
s
c
r
a
pe
r
n
a
vi
ga
te
s
th
r
ough
a
ll
pr
of
il
e
pa
g
e
s
of
th
e
c
or
r
e
s
po
ndi
ng
U
R
L
s
on
th
e
L
in
ke
dI
n
w
e
bs
it
e
.
T
he
to
ol
r
e
tr
ie
ve
s
L
in
ke
dI
n
pr
o
f
il
e
in
f
o
r
m
a
ti
on
us
in
g
s
pe
c
if
ic
pa
r
a
m
e
te
r
s
,
in
c
lu
di
ng
ti
tl
e
,
lo
c
a
ti
on,
e
duc
a
ti
on,
e
xpe
r
ie
nc
e
s
,
c
e
r
ti
f
ic
a
ti
ons
,
s
ki
ll
s
,
a
nd
la
ngua
ge
s
.
T
h
e
e
xt
r
a
c
te
d
da
ta
w
a
s
s
a
ve
d
in
a
C
S
V
f
or
m
a
t
,
a
nd
2006
pr
of
il
e
s
w
e
r
e
ga
th
e
r
e
d f
or
t
hi
s
i
nve
s
ti
ga
ti
on us
in
g s
c
r
a
pi
ng
.
T
he
da
ta
th
a
t
w
a
s
ga
th
e
r
e
d
w
a
s
th
e
n c
le
a
ne
d
up
to
m
a
ke
hi
gh
-
qua
li
ty
da
ta
f
or
te
s
ti
ng
a
nd
tr
a
in
in
g.
I
t
w
a
s
pr
oc
e
s
s
e
d
to
r
e
m
ove
s
ym
bol
s
,
f
il
l
in
m
is
s
in
g
num
be
r
s
,
a
nd
lo
w
e
r
c
a
s
e
a
ll
th
e
le
tt
e
r
s
in
th
e
da
ta
s
e
t.
I
t
w
a
s
c
ha
nge
d
to
th
e
w
or
d
“
none
”
in
th
e
in
f
or
m
a
ti
on
w
he
r
e
th
e
e
m
pt
y
li
s
t
w
it
h
th
e
s
ym
bol
“
[]
”
us
e
d
to
b
e
.
A
f
te
r
th
a
t,
a
s
im
il
a
r
it
y
s
c
or
e
m
e
th
od
w
a
s
us
e
d
to
f
ig
ur
e
out
how
s
im
il
a
r
th
e
a
ppl
ic
a
nt
’
s
pe
r
s
ona
l
d
a
ta
w
a
s
to
th
e
jo
b
de
s
c
r
ip
ti
on da
ta
. T
he
c
o
s
in
e
s
im
il
a
r
it
y f
unc
ti
on w
a
s
us
e
d t
o f
ig
ur
e
out
t
he
c
lo
s
e
ne
s
s
s
c
or
e
.
T
hi
s
s
tu
dy l
ooks
a
t
ti
tl
e
s
,
s
ki
ll
s
,
a
nd
la
ngua
g
e
s
a
nd
ge
ts
th
e
s
im
il
a
r
it
y
s
c
or
e
be
twe
e
n
th
e
m
.
T
he
e
qua
ti
on
f
or
c
o
s
in
e
s
im
il
a
r
it
y
s
c
or
e
is
r
e
pr
e
s
e
nt
e
d a
s
in
(
1)
[
28]
.
=
(
⋅
)
(
|
|
|
|
⋅
|
|
|
|
)
(
1)
N
e
xt
,
f
or
e
duc
a
ti
on
a
tt
r
ib
ut
e
s
,
th
e
e
duc
a
ti
on
le
ve
l
w
a
s
e
xt
r
a
c
te
d
us
in
g
r
e
ge
x
to
m
a
tc
h
th
e
e
duc
a
ti
on
le
ve
l
in
th
a
t
jo
b’
s
r
e
qui
r
e
m
e
nt
s
.
I
f
a
m
a
tc
h
w
a
s
f
ound,
it
w
a
s
a
s
s
ig
ne
d
a
va
lu
e
of
“
1”
to
in
di
c
a
te
a
s
uc
c
e
s
s
f
ul
m
a
tc
h
in
te
r
m
s
of
e
duc
a
ti
on
le
v
e
l.
A
f
te
r
w
a
r
d
s
,
th
e
dur
a
ti
on
of
th
e
a
ppl
ic
a
nt
’
s
L
in
ke
dI
n
pr
of
il
e
e
xpe
r
ie
nc
e
s
w
a
s
c
om
put
e
d
in
m
ont
hs
to
f
a
c
il
it
a
te
be
tt
e
r
c
om
pa
r
is
ons
w
it
h
th
e
m
in
im
um
dur
a
ti
on
of
e
xpe
r
ie
nc
e
s
r
e
qui
r
e
d
by
e
a
c
h j
ob’
s
s
pe
c
if
ic
a
ti
ons
.
A
f
te
r
a
ll
th
e
a
tt
r
ib
ut
e
s
w
e
r
e
pr
oc
e
s
s
e
d,
a
f
e
w
c
ondi
ti
ons
w
e
r
e
a
ppl
ie
d
to
th
e
da
ta
la
be
l
le
d.
A
ne
w
c
ol
um
n
c
a
ll
e
d
“
e
li
gi
bi
li
ty
s
ta
tu
s
”
h
a
s
be
e
n
a
dde
d
to
th
e
d
a
ta
s
e
t.
T
he
s
e
e
li
gi
bi
li
ty
s
ta
tu
s
a
tt
r
ib
ut
e
s
h
a
ve
“
e
li
gi
bl
e
”
a
nd
“
in
e
li
gi
bl
e
”
s
ta
tu
s
e
s
. T
he
L
in
ke
dI
n
pr
of
il
e
w
a
s
c
la
s
s
if
ie
d
a
s
ha
vi
ng
“
E
li
gi
bi
li
ty
”
s
ta
tu
s
if
it
f
ul
f
il
le
d
th
e
s
e
th
r
e
e
c
ondi
ti
ons
.
F
ir
s
t,
th
e
s
im
il
a
r
it
y
s
c
or
e
be
twe
e
n
ti
tl
e
,
s
ki
ll
s
a
nd
la
ngua
ge
s
is
hi
ghe
r
th
a
n
th
e
m
e
a
n
of
th
e
s
im
il
a
r
it
y
s
c
or
e
be
twe
e
n
ti
tl
e
,
s
ki
ll
s
,
a
nd
la
ngu
a
ge
s
.
F
unc
ti
on
m
e
a
n(
)
c
a
lc
ul
a
te
d
th
e
a
ve
r
a
g
e
of
th
e
to
ta
l
s
im
il
a
r
it
y
s
c
or
e
f
or
th
e
a
ppl
ic
a
nt
s
a
nd
w
a
s
c
om
m
onl
y
c
a
lc
ul
a
te
d
a
s
in
(
2)
.
T
he
s
e
c
ond
c
ondi
ti
on
i
s
if
th
e
e
duc
a
ti
on
le
ve
l
th
a
t
w
a
s
e
xt
r
a
c
te
d
e
a
r
li
e
r
m
a
tc
he
s
th
e
e
duc
a
ti
o
n
le
ve
l
r
e
qui
r
e
d
by
th
e
jo
b’
s
de
s
c
r
ip
ti
on.
T
he
la
s
t
c
ondi
ti
on
is
th
a
t
th
e
dur
a
ti
on
o
f
th
e
L
in
ke
dI
n
pr
of
il
e
e
xpe
r
ie
nc
e
s
in
a
m
ont
h
s
houl
d
be
hi
ghe
r
th
a
n
th
e
d
ur
a
ti
on
of
th
e
jo
b
e
xpe
r
ie
nc
e
s
in
a
m
ont
h.
O
th
e
r
w
is
e
,
if
th
e
d
a
ta
doe
s
not
m
e
e
t
th
os
e
c
ondi
ti
ons
,
it
w
il
l
f
a
ll
unde
r
t
he
“
in
e
li
gi
bl
e
”
c
a
te
gor
y.
=
(
_
(
1
,
1
)
+
_
(
2
,
2
)
+
…
+
_
(
,
)
)
(
2)
T
he
f
in
a
l
da
ta
s
e
t
ha
s
a
to
ta
l
of
14
c
ol
um
ns
f
or
L
in
ke
dI
n
p
r
of
i
le
:
na
m
e
,
ti
tl
e
,
lo
c
a
ti
on,
e
xpe
r
ie
nc
e
s
,
e
duc
a
ti
on,
c
e
r
ti
f
ic
a
ti
ons
,
s
ki
ll
s
,
l
a
ngua
ge
s
,
s
im
il
a
r
it
ys
c
or
e
s
_t
it
le
_s
ki
ll
s
_l
a
ng,
e
duc
a
ti
on
le
v
e
l,
e
duc
a
ti
on
m
a
tc
h,
to
ta
l
dur
a
ti
on
in
m
ont
hs
,
ha
s
c
e
r
ti
f
ic
a
ti
on,
a
nd
e
li
gi
bi
li
ty
.
F
in
a
ll
y,
th
e
da
ta
s
e
t
i
s
s
a
v
e
d
in
a
C
S
V
f
il
e
f
or
th
e
ne
xt
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
r
ti
f
I
nt
e
ll
I
S
S
N
:
2252
-
8938
E
li
gi
bi
li
ty
r
at
e
of
appli
c
ant
’
s
L
in
k
e
dI
n ac
c
ount
:
a naïv
e
bay
e
s
…
(
K
hy
r
in
a A
ir
in
F
ar
iz
a
A
bu Samah
)
4337
tr
a
in
in
g
a
nd
te
s
ti
ng
to
de
ve
lo
p
th
e
m
ode
l
a
nd
u
s
e
d
f
or
d
a
ta
vi
s
ua
li
z
a
ti
on.
O
n
c
e
th
e
pr
e
-
pr
oc
e
s
s
in
g
pha
s
e
is
f
in
is
he
d, t
he
f
in
a
l
da
ta
s
e
t
is
pr
e
pa
r
e
d f
or
t
he
c
la
s
s
if
ic
a
ti
on me
th
od us
in
g m
a
c
hi
ne
l
e
a
r
ni
ng
.
2
.2.
2
.
N
aï
ve
B
aye
s
c
la
s
s
i
f
ic
at
io
n
m
od
e
l
T
he
N
B
c
la
s
s
if
ie
r
i
s
a
w
id
e
ly
us
e
d a
lg
or
it
hm
f
or
c
la
s
s
if
ic
a
ti
on a
nd pr
e
di
c
ti
on a
na
ly
s
is
[
29]
–
[
31]
. N
B
c
la
s
s
if
ie
r
i
s
pe
r
f
or
m
e
d ba
s
e
d on the
B
a
ye
s
t
he
or
e
m
. I
t
a
s
s
um
e
s
th
a
t
th
e
f
e
a
tu
r
e
s
a
r
e
c
ondi
ti
ona
ll
y i
nde
pe
nde
nt
gi
ve
n
th
e
c
la
s
s
la
be
l.
T
h
e
N
B
c
la
s
s
if
ie
r
c
a
lc
ul
a
te
s
th
e
pr
oba
bi
li
ty
of
e
a
c
h
c
la
s
s
la
be
l
gi
ve
n
th
e
in
put
f
e
a
tu
r
e
s
.
It
a
s
s
um
e
s
th
a
t
th
e
f
e
a
tu
r
e
s
w
it
hi
n
th
e
in
put
f
e
a
tu
r
e
s
a
r
e
c
ondi
ti
ona
ll
y
in
de
pe
nde
nt
gi
ve
n
th
e
c
la
s
s
.
B
y
le
ve
r
a
gi
ng
th
is
a
s
s
um
pt
io
n,
th
e
N
B
a
lg
or
it
hm
c
a
n
m
a
ke
pr
e
di
c
ti
ons
a
c
c
ur
a
te
ly
a
nd
qui
c
kl
y.
B
a
ye
s
’
t
he
or
e
m
c
a
lc
ul
a
te
s
th
e
pr
oba
bi
li
ty
of
a
n
e
ve
nt
ha
ppe
ni
ng
ba
s
e
d
on
th
e
pr
oba
bi
li
t
y
of
a
not
he
r
e
ve
nt
th
a
t
ha
s
a
lr
e
a
dy
oc
c
ur
r
e
d. A
c
c
or
di
ng t
o B
r
ow
nl
e
e
[
32]
, t
he
B
a
ye
s
t
h
e
or
e
m
w
a
s
de
pi
c
t
ed
a
s
in
(
3)
.
(
|
)
=
(
|
)
(
)
(
)
(
3)
D
ur
in
g
tr
a
in
in
g
da
ta
,
th
e
N
B
c
la
s
s
if
ie
r
c
a
lc
ul
a
te
s
th
e
pr
io
r
pr
oba
bi
li
ty
,
w
hi
c
h
is
P
(
A
)
f
r
om
(
3)
o
f
e
a
c
h
c
la
s
s
,
by
c
ount
in
g
th
e
num
be
r
of
in
s
ta
nc
e
s
.
I
t
a
ls
o
e
s
ti
m
a
te
s
th
e
c
ondi
ti
ona
l
pr
oba
bi
li
ti
e
s
by
c
a
lc
ul
a
ti
ng
th
e
li
ke
li
hood, P
(
B
│
A
)
,
of
obs
e
r
vi
ng e
a
c
h
f
e
a
tu
r
e
va
lu
e
gi
ve
n
t
he
c
la
s
s
l
a
be
l.
T
hus
,
dur
in
g t
e
s
ti
ng d
a
ta
, t
he
B
a
y
e
s
th
e
or
e
m
w
a
s
a
ppl
ie
d
to
c
a
lc
ul
a
t
e
th
e
pos
te
r
io
r
pr
oba
bi
li
ti
e
s
of
e
a
c
h
c
la
s
s
gi
ve
n
th
e
in
put
f
e
a
tu
r
e
s
,
w
hi
c
h
is
P
(
A
│
B
)
f
r
om
th
e
e
qua
ti
on.
T
he
c
la
s
s
w
it
h
th
e
gr
e
a
te
s
t
pos
te
r
io
r
pr
oba
bi
li
t
y
is
s
ubs
e
que
nt
ly
c
ho
s
e
n
a
s
th
e
pr
e
di
c
te
d
c
la
s
s
.
T
he
da
t
a
s
e
t
is
l
a
be
l
le
d
ba
s
e
d
on
it
s
c
ondi
ti
ons
, w
he
r
e
w
e
us
e
a
r
a
ti
o
of
80:
20
to
s
pl
it
th
e
da
ta
in
to
2
pa
r
ts
:
tr
a
in
in
g
a
nd
te
s
ti
n
g
.
F
our
f
e
a
tu
r
e
c
ol
um
ns
w
e
r
e
s
e
le
c
te
d
f
or
tr
a
in
in
g
s
e
ts
,
s
uc
h
a
s
s
im
il
a
r
it
y
s
c
or
e
s
title
s
ki
ll
s
la
ng,
e
duc
a
ti
on
m
a
tc
h,
to
ta
l
dur
a
ti
on
in
m
ont
hs
,
a
nd
ha
s
c
e
r
ti
f
ic
a
ti
on.
A
f
te
r
de
ve
lo
pi
ng
th
e
N
B
m
ode
l,
t
he
e
li
gi
bi
li
ty
r
a
te
w
a
s
pr
oduc
e
d us
in
g
B
a
ye
s
’
s
t
he
or
e
m
pr
oba
bi
li
ty
.
2.
3
.
F
r
on
t
-
e
n
d
d
e
ve
lo
p
m
e
n
t
H
T
M
L
,
C
S
S
,
a
nd
J
a
v
a
S
c
r
ip
t
a
r
e
th
r
e
e
c
or
e
te
c
hnol
ogi
e
s
f
or
de
ve
lo
pi
ng
a
nd
de
s
ig
ni
ng
w
e
bs
it
e
s
a
nd
w
e
b a
ppl
ic
a
ti
ons
.
A
w
e
bs
it
e
ha
s
b
e
e
n c
r
e
a
te
d f
or
us
e
r
s
t
o i
nt
e
r
a
c
t
w
it
h, a
nd t
he
s
y
s
te
m
c
a
n be
a
c
c
e
s
s
e
d
e
a
s
il
y.
T
he
w
e
b
a
ppl
ic
a
ti
on
c
onne
c
t
s
th
e
in
te
r
f
a
c
e
a
nd
t
he
P
yt
hon
c
o
de
us
in
g
th
e
F
la
s
k
a
ppl
ic
a
ti
on.
I
t
di
s
pl
a
ys
th
e
r
e
s
ul
t
of
th
e
pr
e
di
c
ti
on
a
nd
o
f
f
e
r
s
to
ol
s
f
o
r
da
ta
vi
s
ua
li
z
a
ti
on,
a
ll
ow
in
g
th
e
c
r
e
a
ti
on
of
c
ha
r
ts
a
nd
gr
a
phs
to
r
e
pr
e
s
e
nt
da
ta
vi
s
ua
ll
y.
2.4.
T
e
s
t
in
g d
e
ve
lo
p
m
e
n
t
U
pon
c
om
pl
e
ti
on
of
a
ll
pha
s
e
s
,
th
e
f
in
a
l
pha
s
e
is
te
s
ti
ng,
w
hi
c
h
in
vol
ve
s
e
xe
c
ut
in
g
te
s
t
c
a
s
e
s
on
th
e
s
ys
te
m
.
T
he
ve
r
if
ic
a
ti
on
a
nd
va
li
da
ti
on
pr
oc
e
s
s
e
ns
ur
e
s
th
a
t
t
he
s
ys
te
m
f
ul
f
il
s
th
e
in
it
ia
l
r
e
qui
r
e
m
e
nt
s
a
nd
s
a
ti
s
f
ie
s
it
s
a
im
s
.
V
e
r
if
ic
a
ti
on
e
va
lu
a
te
s
th
e
s
ys
t
e
m
’
s
de
ve
lo
p
m
e
nt
pr
oduc
t,
w
h
e
r
e
a
s
va
li
da
ti
on
a
s
s
e
s
s
e
s
th
e
f
in
a
l
pr
oduc
t.
T
he
te
s
ti
ng
pha
s
e
is
in
te
nde
d
to
e
ns
ur
e
th
e
s
ys
te
m
’
s
f
unc
ti
ona
li
ty
a
nd
a
ddr
e
s
s
a
ny
pr
obl
e
m
s
or
c
onc
e
r
ns
.
I
n
th
is
s
tu
dy
,
th
e
obj
e
c
ti
ve
s
f
oc
us
on
da
s
hboa
r
d
f
u
nc
ti
ona
li
ty
ba
s
e
d
on
th
e
de
f
in
e
d
us
e
c
a
s
e
a
nd
s
ys
te
m
us
a
bi
li
ty
s
c
a
le
(
S
U
S
)
by
H
R
r
e
c
r
ui
tm
e
nt
pr
of
e
s
s
io
na
ls
.
3.
R
E
S
U
L
T
S
A
ND
D
I
S
C
U
S
S
I
O
N
3
.1.
M
od
e
l
a
c
c
u
r
ac
y
E
va
lu
a
ti
ng t
he
N
B
c
la
s
s
if
ie
r
m
ode
l
in
vol
ve
s
c
om
pa
r
in
g t
he
pr
e
di
c
te
d va
lu
e
s
w
it
h t
he
a
c
tu
a
l
va
lu
e
s
i
n
a
te
s
t
d
a
ta
s
e
t
to
de
te
r
m
in
e
a
c
c
ur
a
c
y.
F
ig
ur
e
2
di
s
pl
a
y
s
th
e
a
c
c
ur
a
c
y
te
s
ti
ng
r
e
s
ul
ts
of
th
e
N
B
m
ode
l
in
th
is
s
tu
dy. T
he
a
c
c
ur
a
c
y r
e
s
ul
t
is
89.8%
. A
n a
c
c
ur
a
c
y s
c
or
e
a
bove
90%
i
s
c
ons
id
e
r
e
d
“
e
xc
e
ll
e
nt
”
in
[
33]
, w
he
r
e
a
s
a
s
c
or
e
b
e
twe
e
n
70%
a
nd
90%
is
c
la
s
s
if
ie
d
a
s
“
good
.
”
A
n
a
c
c
ur
a
c
y
s
c
or
e
r
a
ngi
ng
f
r
om
60
%
to
70
%
is
c
ons
id
e
r
e
d
“
ok
a
y
,
”
w
hi
le
a
s
c
or
e
be
lo
w
60
%
i
s
l
a
b
e
ll
e
d a
s
“
poo
r
.
”
T
he
s
ys
t
e
m
’
s
a
c
c
ur
a
c
y r
a
ng
e
s
f
r
om
70
%
to
90
%
,
w
hi
c
h
is
c
ons
id
e
r
e
d
“
good
.
”
T
h
e
m
ode
l
a
c
hi
e
v
e
d
a
n
a
c
c
u
r
a
c
y
r
a
te
of
a
bout
89.8%
in
c
la
s
s
if
yi
ng
e
ve
nt
s
w
it
hi
n
th
e
te
s
t
da
ta
s
e
t.
T
he
c
onf
us
io
n
m
a
tr
ix
pr
ovi
de
s
a
de
ta
il
e
d
br
e
a
kdown
of
th
e
tr
ue
va
lu
e
s
th
a
t
a
li
gn
w
it
h
th
e
m
ode
l
’
s
pr
e
di
c
ti
ons
. T
he
c
onf
us
io
n m
a
tr
ix
i
n
t
hi
s
s
tu
dy us
e
s
t
he
c
la
s
s
e
s
“
in
e
li
gi
bl
e
”
a
nd
“
e
li
gi
bl
e
”
, w
hi
c
h
a
r
e
de
not
e
d by
“
0
”
a
nd
“
1
”
c
or
r
e
s
pondingl
y.
3.2.
C
os
in
e
s
im
il
ar
it
y s
c
or
e
s
r
e
s
u
lt
W
e
us
e
a
n
e
x
a
m
pl
e
us
in
g
th
e
jo
b’
s
f
ie
ld
,
“
f
in
a
nc
e
,”
a
nd
th
e
jo
b
’
s
ti
tl
e
,
“
a
c
c
ount
a
nt
,
”
to
il
lu
s
tr
a
te
th
e
r
e
s
ul
t.
W
e
obs
c
ur
e
d
th
e
or
ig
in
a
l
na
m
e
s
w
it
h
bl
a
c
k
m
a
r
ki
ngs
.
T
he
n
w
e
r
e
na
m
e
d
th
e
m
us
in
g
a
c
om
pa
r
a
bl
e
a
lp
ha
be
t
to
pr
e
ve
nt
a
ny
e
th
ic
a
l
c
onc
e
r
ns
.
W
e
a
r
e
de
vi
a
ti
ng
f
r
om
th
e
c
onve
nt
io
na
l
a
lp
ha
b
e
ti
c
a
l
s
e
que
nc
e
be
c
a
us
e
th
e
vi
s
ua
li
z
a
ti
on
is
a
r
r
a
nge
d
a
c
c
or
di
ng
to
th
e
de
s
c
e
ndi
ng
r
a
te
out
c
om
e
.
C
os
in
e
s
im
il
a
r
it
y
s
c
or
e
s
a
r
e
c
om
put
e
d
us
in
g
th
e
ti
tl
e
s
,
a
bi
li
ti
e
s
,
a
nd
la
ngua
ge
s
of
s
e
ve
n
a
ppl
ic
a
nt
s
.
A
ppl
ic
a
nt
s
w
ho
e
xc
e
e
d
th
e
a
ve
r
a
ge
s
im
il
a
r
it
y
s
c
or
e
a
r
e
de
e
m
e
d
to
ha
ve
m
e
t
one
of
th
e
e
li
gi
bi
li
ty
c
r
it
e
r
ia
w
he
n
th
e
r
ul
e
s
a
r
e
a
ppl
ie
d.
T
hus
,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8938
I
nt
J
A
r
ti
f
I
nt
e
ll
, V
ol
.
13
, N
o.
4
,
D
e
c
e
m
be
r
2024
:
4334
-
4343
4338
F
ig
ur
e
3
s
how
s
th
e
ba
r
c
ha
r
t
of
c
os
in
e
s
im
il
a
r
it
y
s
c
or
e
c
om
pa
r
is
ons
w
he
r
e
e
a
c
h
ba
r
r
e
pr
e
s
e
nt
s
a
n
a
ppl
ic
a
nt
’
s
s
im
il
a
r
it
y
s
c
or
e
.
A
li
ne
w
it
h
a
dot
te
d
poi
nt
r
e
pr
e
s
e
nt
s
th
e
m
e
a
n
of
th
e
c
os
in
e
s
im
il
a
r
it
y
s
c
or
e
of
0.26,
w
hi
c
h
in
di
c
a
te
s
th
e
m
e
a
n of
t
he
s
im
il
a
r
it
y s
c
or
e
a
c
r
os
s
a
ll
a
ppl
ic
a
nt
s
.
I
n c
onc
lu
s
io
n, only f
our
c
a
ndi
d
a
te
s
a
r
e
e
li
gi
bl
e
s
in
c
e
t
he
y s
ur
pa
s
s
t
he
m
e
a
n ba
s
e
d on the
ove
r
a
ll
a
ppl
ic
a
nt
’
s
s
c
or
e
.
F
ig
ur
e
2.
N
a
ïv
e
B
a
ye
s
m
ode
l
a
c
c
ur
a
c
y r
e
s
ul
t
s
F
ig
ur
e
3.
B
a
r
gr
a
ph
of
s
im
il
a
r
it
y c
os
in
e
s
c
or
e
of
a
ppl
ic
a
nt
s
w
it
h
m
e
a
n s
c
or
e
3.3.
F
u
n
c
t
io
n
al
it
y t
e
s
t
in
g of
d
as
h
b
oar
d
vi
s
u
al
i
z
at
io
n
T
he
da
s
hboa
r
d vi
s
ua
li
z
a
ti
on i
s
r
e
la
te
d t
o
f
unc
ti
ona
li
ty
te
s
ti
ng
. I
t
is
t
he
pr
oc
e
s
s
w
he
r
e
th
e
U
I
is
te
s
te
d
by
pr
ovi
di
ng
a
ppr
opr
ia
te
te
s
t
in
put
.
T
he
out
put
is
c
om
pa
r
e
d
w
it
h
th
e
e
xpe
c
te
d
out
put
.
T
he
s
ys
te
m
’
s
out
put
w
il
l
be
e
va
lu
a
te
d
w
h
e
th
e
r
it
is
s
u
c
c
e
s
s
f
ul
or
not
a
t
th
e
e
nd
of
th
e
t
e
s
t.
T
hi
s
te
s
ti
ng
i
s
m
a
in
ly
c
onc
e
r
ne
d
w
it
h
th
e
pr
oc
e
s
s
in
g r
e
s
ul
ts
.
T
he
goa
ls
a
r
e
t
o t
e
s
t
a
nd r
un t
hr
ough a
ll
t
he
s
ys
te
m
f
unc
ti
ons
f
r
om
t
he
f
ir
s
t
to
t
he
l
a
s
t
pa
ge
of
t
he
a
ppl
ic
a
ti
on. I
t
e
ns
ur
e
s
t
he
a
ppl
ic
a
ti
on r
uns
, f
ol
lo
w
s
t
he
r
e
qui
r
e
m
e
nt
s
, a
nd dis
pl
a
y
s
t
he
de
s
ir
e
d outc
om
e
.
I
t
pe
r
f
or
m
s
a
s
e
r
ie
s
of
te
s
t
c
a
s
e
s
c
ove
r
in
g
th
e
a
ppl
ic
a
ti
on’
s
va
r
i
ous
f
unc
ti
ona
li
ti
e
s
.
T
hu
s
,
f
unc
ti
ona
li
ty
te
s
ti
ng
he
lp
s
i
de
nt
if
y bugs
, e
r
r
or
s
, or
de
vi
a
ti
ons
f
r
om
t
he
i
nt
e
nde
d be
ha
vi
o
u
r
.
F
ig
ur
e
4
s
how
s
th
e
“
upl
oa
d
f
il
e
”
pa
ge
w
he
r
e
us
e
r
s
c
a
n
s
e
le
c
t
th
e
jo
b’
s
f
ie
ld
a
nd
ti
tl
e
a
nd
upl
oa
d
a
C
S
V
f
il
e
c
ont
a
in
in
g
a
li
s
t
of
U
R
L
s
of
th
e
L
in
ke
dI
n
a
ppl
ic
a
nt
’
s
a
c
c
ount
th
a
t
th
e
us
e
r
w
a
nt
s
to
pe
r
f
or
m
th
e
c
la
s
s
if
ic
a
ti
on.
U
s
in
g
th
e
s
a
m
e
e
xa
m
pl
e
f
or
th
e
s
im
il
a
r
it
y
c
oe
f
f
ic
i
e
nt
s
c
or
e
,
w
e
c
h
os
e
th
e
jo
b’
s
f
ie
ld
a
s
“
f
in
a
nc
e
”
a
nd t
he
j
ob’
s
t
it
le
a
s
“
a
c
c
ount
a
nt
”
.
O
nc
e
t
he
but
to
n
“
upl
oa
d
”
i
s
c
li
c
ke
d, t
he
s
c
r
a
pi
ng
pr
oc
e
s
s
w
il
l
s
t
a
r
t
,
a
nd t
he
jo
b
r
e
qui
r
e
m
e
nt
s
s
e
le
c
te
d
a
nd
th
e
a
ppl
ic
a
nt
’
s
in
f
or
m
a
ti
on
w
il
l
be
di
s
pl
a
ye
d
on
th
e
ne
xt
pa
ge
,
a
s
il
lu
s
tr
a
te
d
in
F
ig
ur
e
5.
O
n
to
p
of
th
e
da
s
hboa
r
d,
th
e
jo
b’
s
r
e
qui
r
e
m
e
nt
is
li
s
t
e
d
a
c
c
or
di
ng
to
th
e
s
e
ve
n
a
tt
r
ib
ut
e
s
c
hos
e
n
f
or
th
is
s
tu
dy. T
he
r
e
i
s
a
ls
o i
nf
or
m
a
ti
on on the
t
ot
a
l
of
a
ppl
ic
a
nt
s
t
ha
t
m
a
tc
h t
he
r
e
qui
r
e
m
e
nt
s
.
F
ig
ur
e
4
.
“
U
pl
oa
d
f
il
e
”
pa
ge
F
ig
ur
e
5. V
ie
w
t
he
“
di
s
pl
a
y i
nf
or
m
a
ti
on
”
pa
ge
T
he
s
ys
t
e
m
a
ll
ow
s
th
e
us
e
r
to
c
li
c
k
th
e
“
c
la
s
s
if
ic
a
ti
on
”
but
to
n
to
s
how
th
e
a
ppl
ic
a
nt
’
s
in
f
or
m
a
ti
on
w
it
h
it
s
e
li
gi
bi
li
ty
s
ta
tu
s
,
e
it
he
r
“
e
li
gi
bl
e
”
or
“
in
e
li
gi
bl
e
”
on
th
e
r
ig
ht
r
ow
,
a
s
de
pi
c
t
e
d
in
F
ig
ur
e
6.
T
h
e
us
e
r
m
a
y
c
hoos
e
to
c
li
c
k
“
dow
nl
oa
d
a
ll
a
ppl
ic
a
nt
s
”
to
s
e
e
th
e
de
ta
i
ls
.
T
he
s
ys
t
e
m
e
xhi
bi
ts
th
e
e
li
gi
bl
e
a
ppl
ic
a
nt
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
r
ti
f
I
nt
e
ll
I
S
S
N
:
2252
-
8938
E
li
gi
bi
li
ty
r
at
e
of
appli
c
ant
’
s
L
in
k
e
dI
n ac
c
ount
:
a naïv
e
bay
e
s
…
(
K
hy
r
in
a A
ir
in
F
ar
iz
a
A
bu Samah
)
4339
a
lo
ng w
it
h t
he
ir
c
or
r
e
s
ponding e
li
gi
bi
li
ty
r
a
te
s
onc
e
t
he
“
vi
e
w
e
li
gi
bl
e
a
ppl
ic
a
nt
s
”
but
to
n i
s
s
e
le
c
te
d
a
s
s
how
n
in
F
ig
ur
e
7.
A
t
th
e
t
op of
t
he
pa
ge
,
t
he
da
s
hboa
r
d vi
s
ua
li
z
e
s
t
he
to
ta
l
num
be
r
of
e
li
gi
bl
e
a
ppl
ic
a
nt
s
,
w
hi
c
h i
s
4.
F
ig
ur
e
6
.
V
ie
w
t
he
“
a
ppl
ic
a
nt
’
s
e
l
i
gi
bi
l
i
t
y
s
ta
tu
s
”
pa
ge
F
ig
ur
e
7
.
V
ie
w
t
he
“
e
li
gi
bl
e
a
ppl
ic
a
nt
s
”
p
a
ge
T
he
us
e
r
ha
s
th
e
c
hoi
c
e
to
c
li
c
k
th
e
“
dow
nl
oa
d
li
s
t
”
but
to
n
to
r
e
f
e
r
to
th
e
de
ta
il
e
d
in
f
or
m
a
ti
on.
T
he
a
na
ly
s
is
p
a
ge
w
a
s
di
s
pl
a
ye
d
a
f
te
r
th
e
us
e
r
c
li
c
ke
d
th
e
“
ove
r
vi
e
w
of
a
ppl
ic
a
nt
s
a
na
ly
s
i
s
”
but
to
n.
F
ig
ur
e
8
s
how
s
a
pi
e
c
ha
r
t
of
th
e
to
ta
l
e
li
gi
bl
e
a
nd
in
e
li
gi
bl
e
a
ppl
ic
a
nt
s
. T
he
r
e
a
r
e
f
our
e
li
gi
bl
e
a
ppl
ic
a
nt
s
a
t
57.1%
a
nd
th
r
e
e
in
e
li
gi
bl
e
a
ppl
ic
a
nt
s
a
t
a
pe
r
c
e
nt
a
ge
of
42.9%
.
F
ol
lo
w
in
g t
he
pi
e
c
ha
r
t,
F
ig
ur
e
9
s
how
s
t
he
ba
r
c
h
a
r
t
of
t
he
e
li
g
ib
il
it
y r
a
te
of
t
he
a
ppl
ic
a
nt
s
pl
ot
te
d i
n
de
c
r
e
a
s
in
g
or
de
r
to
e
a
s
e
th
e
a
na
ly
s
i
s
.
T
he
y
-
a
xi
s
de
not
e
s
th
e
e
li
gi
bi
li
ty
r
a
te
,
w
he
r
e
a
s
th
e
x
-
a
xi
s
s
ig
ni
f
ie
s
th
e
a
ppl
ic
a
nt
’
s
na
m
e
.
T
he
c
ha
r
t
is
c
om
po
s
e
d
of
ba
r
s
,
w
it
h
e
a
c
h
ba
r
r
e
pr
e
s
e
nt
in
g
a
n
a
ppl
ic
a
nt
a
nd
it
s
he
ig
ht
c
or
r
e
s
ponding
to
th
a
t
a
ppl
ic
a
nt
’
s
e
li
gi
bi
li
ty
r
a
te
.
W
it
h
th
a
t,
th
e
us
e
r
c
a
n
qui
c
kl
y
id
e
nt
if
y
a
nd
a
na
ly
z
e
th
e
to
p
a
ppl
ic
a
nt
s
w
it
h t
he
hi
ghe
s
t
e
li
gi
bi
li
ty
r
a
te
.
F
ig
ur
e
8. P
ie
c
ha
r
t
of
e
li
gi
bl
e
a
ppl
ic
a
nt
(
s
)
vs
.
in
e
li
gi
bl
e
a
ppl
ic
a
nt
(
s
)
F
ig
ur
e
9. B
a
r
c
ha
r
t
of
t
he
e
li
gi
bi
li
ty
r
a
te
of
a
ppl
ic
a
nt
(
s
)
9
4
.
5
8
9
2
.
9
8
8
7
.
3
0
8
5
.
2
3
0
.
5
0
0
0
0
20
40
60
80
1
0
0
R
a
t
e
(
%
)
N
a
m
e
E
l
i
g
i
b
i
l
i
t
y
R
a
t
e
o
f
t
h
e
A
p
p
l
i
ca
n
t
(
s)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8938
I
nt
J
A
r
ti
f
I
nt
e
ll
, V
ol
.
13
, N
o.
4
,
D
e
c
e
m
be
r
2024
:
4334
-
4343
4340
T
he
ne
xt
pa
ge
i
s
th
e
“
a
tt
r
ib
ut
e
a
na
ly
s
is
”
pa
ge
.
T
hi
s
pa
ge
vi
s
ua
li
z
e
s
th
r
e
e
pr
opor
ti
ons
of
to
ta
l
a
ppl
ic
a
nt
s
:
e
li
gi
bl
e
a
ppl
ic
a
nt
s
a
nd
in
e
li
gi
bl
e
a
ppl
ic
a
nt
s
.
F
or
e
a
c
h
pr
opor
ti
on,
it
a
na
ly
s
e
s
s
e
ve
n
a
tt
r
ib
ut
e
s
us
e
d
f
or
th
e
c
la
s
s
if
ic
a
ti
on
in
th
is
r
e
s
e
a
r
c
h.
T
he
r
e
w
il
l
be
two
vi
s
ua
li
z
a
ti
ons
in
to
ta
l
to
di
f
f
e
r
e
nt
ia
te
th
e
c
la
s
s
if
ic
a
ti
on.
T
he
f
ir
s
t
a
na
ly
s
is
w
a
s
vi
s
u
a
li
z
e
d
us
in
g
a
s
t
a
c
ke
d
ba
r
c
ha
r
t,
w
he
r
e
e
a
c
h
a
ppl
ic
a
nt
’
s
na
m
e
a
nd
s
a
ti
s
f
a
c
ti
on
s
ta
tu
s
f
or
e
a
c
h
a
tt
r
ib
ut
e
w
e
r
e
di
s
pl
a
ye
d.
F
ig
ur
e
10
s
h
ow
s
th
a
t
out
of
f
our
e
li
gi
bl
e
c
a
ndi
da
te
s
,
W
in
da
f
ul
f
il
s
th
e
a
tt
r
ib
u
te
s
of
c
e
r
ti
f
ic
a
ti
on,
e
xpe
r
ie
nc
e
,
a
nd
e
duc
a
ti
o
n.
C
a
tr
io
na
a
nd
K
ir
os
hi
ni
f
ul
f
il
a
tt
r
ib
ut
e
s
f
or
c
e
r
ti
f
ic
a
ti
on a
nd e
duc
a
ti
on, while
H
a
r
s
hi
m
a
h only f
ul
f
il
s
e
duc
a
t
io
n a
tt
r
ib
ut
e
s
.
T
he
s
e
c
ond
a
na
ly
s
i
s
w
a
s
vi
s
ua
li
z
e
d
ba
s
e
d
on
s
ta
te
s
in
M
a
la
y
s
ia
,
a
s
in
F
ig
ur
e
11.
F
ig
ur
e
11(
a
)
us
in
g
th
e
pi
e
c
ha
r
t
of
th
e
to
ta
l
a
ppl
ic
a
nt
s
ba
s
e
d
on
th
e
ge
ogr
a
phi
c
a
l
d
is
tr
ib
ut
io
n
of
a
ppl
ic
a
nt
s
a
c
r
o
s
s
di
f
f
e
r
e
nt
s
ta
t
e
s
in
M
a
la
ys
ia
:
W
P
K
ua
la
L
um
pur
,
W
P
P
ut
r
a
ja
ya
,
S
e
la
ngor
,
a
nd N
e
ge
r
i
S
e
m
bi
la
n.
I
t
gi
ve
s
a
n
ove
r
vi
e
w
of
w
hi
c
h
s
ta
te
s
ha
ve
a
hi
ghe
r
num
be
r
of
a
ppl
ic
a
nt
s
.
T
he
n,
w
e
s
pl
it
th
e
pi
e
c
ha
r
t
in
F
ig
u
r
e
11(
b)
t
o
de
te
r
m
in
e
w
hi
c
h
s
ta
te
th
e
f
our
e
li
gi
bl
e
c
a
ndi
da
te
s
a
r
e
.
A
s
c
a
n
be
s
e
e
n,
th
e
r
e
a
r
e
two
e
li
gi
bl
e
c
a
ndi
da
te
s
f
r
om
S
e
la
ngor
a
nd
W
P
K
ua
la
L
um
pur
. F
ig
u
r
e
11(
c
)
de
pi
c
ts
t
he
pi
e
c
ha
r
t
b
r
e
a
kdown of
t
he
nu
m
be
r
s
of
i
ne
li
gi
bl
e
c
a
ndi
da
te
s
t
ha
t
c
om
e
f
r
om
W
P
K
ua
la
L
um
pur
, W
P
P
ut
r
a
ja
ya
, a
nd N
e
ge
r
i
S
e
m
bi
la
n.
F
ig
ur
e
10. S
ta
c
ke
d ba
r
c
ha
r
t
of
a
tt
r
ib
ut
e
s
s
a
ti
s
f
ie
d by
e
li
gi
bl
e
a
ppl
ic
a
nt
(
s
)
F
ig
ur
e
11. P
ie
c
ha
r
t
of
:
(
a
)
t
o
ta
l
a
ppl
ic
a
nt
s
ba
s
e
d on
s
ta
te
di
s
tr
i
but
io
n i
n M
a
la
ys
ia
,
(
b)
s
ta
te
of
f
our
e
li
gi
bl
e
c
a
ndi
da
te
s
,
a
nd (
c
)
br
e
a
kdown of
t
he
numbe
r
s
of
i
ne
li
gi
bl
e
c
a
n
di
da
te
s
3.4.
U
s
ab
il
it
y t
e
s
t
in
g
I
n
c
a
lc
ul
a
ti
ng
th
e
S
U
S
s
c
or
e
,
th
e
r
e
s
pons
e
s
pr
ovi
de
d
by
pa
r
ti
c
i
pa
nt
s
to
th
e
S
U
S
que
s
ti
onna
ir
e
w
e
r
e
us
e
d.
F
or
th
is
s
tu
dy
f
oc
us
,
w
e
c
onduc
t
e
d
in
te
r
vi
e
w
s
w
it
h
th
r
e
e
H
R
e
xpe
r
t
pe
r
s
onne
l
w
ho
w
e
r
e
a
va
il
a
bl
e
f
or
th
e
us
a
bi
li
ty
te
s
ti
ng
due
to
th
e
ti
m
e
c
ons
tr
a
in
ts
a
v
a
il
a
bl
e
to
c
om
pl
e
te
th
e
s
tu
dy.
T
he
que
s
ti
ons
w
e
r
e
di
vi
d
e
d
in
to
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
r
ti
f
I
nt
e
ll
I
S
S
N
:
2252
-
8938
E
li
gi
bi
li
ty
r
at
e
of
appli
c
ant
’
s
L
in
k
e
dI
n ac
c
ount
:
a naïv
e
bay
e
s
…
(
K
hy
r
in
a A
ir
in
F
ar
iz
a
A
bu Samah
)
4341
two type
s
of
s
ta
te
m
e
nt
s
,
w
he
r
e
qu
e
s
ti
ons
w
it
h odd number
s
(
1,
3,
5,
7,
9)
a
r
e
phr
a
s
e
d
pos
it
iv
e
ly
. F
or
t
hi
s
t
yp
e
,
th
e
r
e
s
ponde
nt
’
s
r
e
s
pon
s
e
s
c
or
e
f
r
om
1
to
5
w
a
s
de
duc
te
d
by
one
.
T
he
qu
e
s
ti
ons
w
it
h
e
v
e
n
num
be
r
s
(
2,
4,
6,
8,
10)
a
r
e
phr
a
s
e
d
ne
ga
ti
ve
ly
.
F
iv
e
poi
nt
s
w
il
l
be
de
du
c
t
e
d
f
r
om
th
e
r
e
s
pons
e
s
c
or
e
f
or
th
e
s
e
que
s
ti
ons
.
T
he
poi
nt
s
w
e
r
e
ta
ll
ie
d
to
ge
th
e
r
onc
e
th
e
a
dj
u
s
tm
e
nt
s
w
e
r
e
m
a
de
f
or
a
ll
th
e
que
s
ti
on
s
.
T
he
f
in
a
l
s
c
or
e
w
a
s
m
ul
ti
pl
ie
d
by
2.5
to
c
onve
r
t
th
e
to
ta
l
poi
nt
s
in
to
a
S
U
S
s
c
or
e
o
n
a
s
c
a
le
of
0
to
100.
T
hi
s
c
a
lc
ul
a
ti
on
m
e
th
od
a
ll
ow
s
f
or
a
s
ta
nda
r
di
z
e
d
a
s
s
e
s
s
m
e
nt
of
th
e
s
y
s
te
m
’
s
pe
r
c
e
iv
e
d
us
a
bi
li
ty
,
w
it
h
hi
ghe
r
S
U
S
s
c
or
e
s
in
di
c
a
ti
ng
be
tt
e
r
us
a
bi
li
ty
.
T
a
bl
e
1
s
how
s
th
e
f
in
di
ngs
of
th
e
S
U
S
w
it
h
th
e
r
a
w
a
nd
f
in
a
l
s
c
or
e
.
T
he
r
e
s
ponde
nt
s
pr
e
dom
in
a
nt
ly
s
e
le
c
te
d
a
s
c
a
le
of
4,
r
e
pr
e
s
e
nt
in
g
“
a
gr
e
e
”
,
f
or
th
e
pos
it
iv
e
ly
phr
a
s
e
d
qu
e
s
ti
ons
.
C
onve
r
s
e
ly
,
th
e
r
e
s
ponde
nt
s
m
a
in
ly
s
e
le
c
te
d a
s
c
a
le
of
1 f
or
t
he
ne
ga
ti
ve
ly
phr
a
s
e
d que
s
ti
on
s
.
T
a
bl
e
1
.
S
U
S
s
c
or
e
s
f
in
di
ngs
Q
ue
s
t
i
on N
o.
1
2
3
4
5
6
7
8
9
10
S
U
S
r
a
w
s
c
or
e
S
U
S
f
i
na
l
s
c
or
e
E
xpe
r
t
A
4
1
5
1
4
2
4
1
4
1
35
87.50
E
xpe
r
t
B
5
2
4
1
4
1
5
2
5
1
36
90.00
E
xpe
r
t
C
4
1
4
1
5
1
5
1
4
1
37
92.50
A
ve
r
a
ge
90.00
T
he
ove
r
a
ll
pe
r
c
e
nt
a
ge
f
or
S
U
S
in
th
is
s
tu
dy
is
9
0%
,
w
hi
c
h
in
di
c
a
te
s
th
a
t
th
e
s
ys
te
m
is
c
ons
id
e
r
e
d
good.
A
c
c
or
di
ng
to
M
is
da
n
e
t
al
.
[
33
]
,
th
e
a
ve
r
a
ge
S
U
S
s
c
or
e
is
68,
a
nd
s
c
or
e
s
a
bove
85
a
r
e
a
s
s
oc
ia
te
d
w
it
h
“
e
xc
e
ll
e
nt
”
.
S
c
or
e
s
a
bove
a
ve
r
a
ge
a
t
71 a
r
e
pr
e
s
e
nt
e
d
a
s
“
good
”
,
a
nd s
c
or
e
s
a
t
51
a
r
e
c
ons
id
e
r
e
d
“
ok
”
.
B
a
s
e
d
on
th
e
s
e
c
r
it
e
r
ia
,
w
it
h
a
S
U
S
s
c
or
e
of
9
0%
,
th
e
s
ys
te
m
in
th
is
s
tu
dy
f
a
ll
s
w
it
hi
n
th
e
e
xc
e
ll
e
nt
r
a
ti
ng
r
a
nge
,
in
di
c
a
ti
ng pos
it
iv
e
f
e
e
dba
c
k f
r
om
t
he
pa
r
ti
c
ip
a
nt
s
.
4.
C
O
N
C
L
U
S
I
O
N
T
hi
s
s
tu
dy
a
im
s
t
o he
lp
r
e
c
r
ui
te
r
s
id
e
nt
if
y
a
nd s
e
le
c
t
th
e
m
os
t
s
ui
ta
bl
e
c
a
ndi
da
te
w
ho me
e
t
s
t
he
j
ob
’
s
r
e
qui
r
e
m
e
nt
s
.
B
a
s
e
d on th
e
i
nf
or
m
a
ti
on ga
th
e
r
e
d, w
e
c
la
s
s
if
y a
nd vis
ua
li
z
e
t
he
e
li
gi
bi
li
ty
r
a
te
t
o f
in
d t
he
m
os
t
s
ui
ta
bl
e
a
ppl
ic
a
nt
s
th
a
t
f
it
th
e
jo
b
of
f
e
r
e
d.
T
he
N
B
m
ode
l
th
a
t
w
a
s
a
ppl
ie
d
in
th
i
s
s
tu
dy
e
na
bl
e
s
th
e
s
y
s
te
m
to
do
th
e
c
la
s
s
if
ic
a
ti
on
ta
s
k
s
.
I
n
a
ddi
ti
on,
th
e
di
ve
r
s
e
vi
s
ua
li
z
a
ti
ons
w
e
r
e
a
na
ly
z
e
d
f
r
om
th
e
in
f
or
m
a
ti
on
ga
in
e
d
in
th
e
s
ys
te
m
a
ppl
ic
a
ti
on,
e
na
bl
in
g
th
e
m
to
m
a
ke
in
f
or
m
e
d
de
c
is
io
ns
dur
in
g
th
e
hi
r
in
g
pr
oc
e
s
s
.
C
le
a
r
a
nd
in
tu
it
iv
e
vi
s
ua
li
z
a
ti
on
e
na
bl
e
s
th
e
r
e
c
r
ui
te
r
s
to
r
e
tr
ie
ve
a
nd
s
um
m
a
r
i
z
e
in
f
or
m
a
ti
on
a
bout
e
li
gi
bl
e
a
nd
in
e
li
gi
bl
e
a
ppl
ic
a
nt
s
.
T
he
e
li
gi
bi
li
ty
r
a
te
a
ll
ow
s
r
e
c
r
ui
te
r
s
to
e
f
f
ic
ie
nt
ly
ha
ndl
e
a
nd
g
a
in
a
c
om
pr
e
he
ns
iv
e
unde
r
s
ta
ndi
ng
of
a
ll
a
ppl
ic
a
nt
s
w
ho
m
e
e
t
th
e
ir
c
r
it
e
r
ia
in
a
s
hor
te
r
a
m
ount
of
ti
m
e
.
T
he
le
ve
r
a
gi
ng
pow
e
r
of
N
B
s
or
t
s
th
e
m
os
t
qua
li
f
ie
d
c
a
ndi
da
te
s
f
or
a
pos
it
io
n
a
nd
vi
s
ua
li
z
a
ti
on
te
c
hni
que
s
ba
s
e
d
on
th
e
s
e
ve
n
a
tt
r
ib
ut
e
s
f
or
c
la
s
s
if
ic
a
ti
on:
ti
tl
e
,
lo
c
a
ti
on,
e
duc
a
ti
on,
ye
a
r
s
of
pr
of
e
s
s
io
na
l
e
xpe
r
ie
nc
e
,
s
ki
ll
s
,
la
ngua
ge
s
,
a
nd
c
e
r
ti
f
ic
a
te
s
.
F
or
f
ur
th
e
r
s
tu
dy,
w
e
r
e
c
om
m
e
n
d
a
ddi
ng
m
or
e
f
unc
ti
ons
f
o
r
c
ont
a
c
ti
ng
th
e
s
hor
tl
is
te
d
a
ppl
ic
a
nt
s
f
r
om
th
e
s
ys
te
m
a
nd
a
ddi
ng
m
or
e
j
ob f
ie
ld
s
.
A
C
K
N
O
WL
E
D
G
E
M
E
N
T
S
T
hi
s
r
e
s
e
a
r
c
h
w
a
s
f
unde
d
by
a
gr
a
nt
f
r
om
U
ni
ve
r
s
it
i
T
e
knol
o
gi
M
A
R
A
C
a
w
a
ng
a
n
M
e
la
ka
(
T
E
J
A
G
r
a
nt
2023
G
D
T
2023/1
-
14)
.
R
E
F
E
R
E
N
C
E
S
[
1]
N
.
S
.
G
i
l
l
,
“
R
e
c
r
ui
t
m
e
nt
a
nd
s
e
l
e
c
t
i
on
pr
oc
e
dur
e
s
i
n
hum
a
n
r
e
s
our
c
e
m
a
na
ge
m
e
nt
,”
I
nt
e
r
nat
i
onal
J
our
nal
of
C
om
put
e
r
S
c
i
e
nc
e
an
d
M
obi
l
e
C
om
put
i
ng
, vol
. 10, no. 2, pp. 45
–
49, 2021, doi
:
10.47760/
i
j
c
s
m
c
.2021.v10i
02.006.
[
2]
P
.
A
.
H
a
m
z
a
e
t
al
.
,
“
R
e
c
r
ui
t
m
e
nt
a
nd
s
e
l
e
c
t
i
on:
T
he
r
e
l
a
t
i
ons
hi
p
be
t
w
e
e
n
r
e
c
r
ui
t
m
e
nt
a
nd
s
e
l
e
c
t
i
on
w
i
t
h
o
r
ga
ni
z
a
t
i
ona
l
pe
r
f
or
m
a
nc
e
,”
I
nt
e
r
nat
i
onal
J
our
nal
of
E
ngi
ne
e
r
i
ng, B
us
i
ne
s
s
and M
anage
m
e
n
t
, vol
. 5, no. 3, 2021, doi
:
10.22161/
i
j
e
bm
.5.3.1.
[
3]
S
.
I
.
A
bba
s
,
M
.
H
.
S
ha
h,
a
nd
Y
.
H
.
O
t
hm
a
n,
“
C
r
i
t
i
c
a
l
r
e
vi
e
w
of
r
e
c
r
ui
t
m
e
nt
a
nd
s
e
l
e
c
t
i
on
m
e
t
hod
s
:
U
nde
r
s
t
a
ndi
ng
t
he
c
ur
r
e
nt
pr
a
c
t
i
c
e
s
,”
A
nnal
s
of
C
ont
e
m
po
r
ar
y
D
e
v
e
l
opm
e
nt
s
i
n M
anage
m
e
nt
&
H
R
, vol
. 3, no. 3, 2021, doi
:
10.33166/
a
c
dm
hr
.2021.03.005.
[
4]
D
.
L
a
w
ong,
G
.
R
.
F
e
r
r
i
s
,
W
.
H
oc
hw
a
r
t
e
r
,
a
nd
L
.
M
a
he
r
,
“
R
e
c
r
ui
t
e
r
pol
i
t
i
c
a
l
s
ki
l
l
a
nd
or
ga
ni
z
a
t
i
on
r
e
put
a
t
i
on
e
f
f
e
c
t
s
on
j
ob
a
ppl
i
c
a
nt
a
t
t
r
a
c
t
i
on
i
n
t
he
r
e
c
r
ui
t
m
e
nt
pr
oc
e
s
s
:
A
m
ul
t
i
-
s
t
udy
i
nve
s
t
i
ga
t
i
on,”
C
ar
e
e
r
D
e
v
e
l
opm
e
nt
I
nt
e
r
nat
i
onal
,
vol
.
24,
no.
4,
2019,
doi
:
10.1108/
C
D
I
-
01
-
2019
-
0007.
[
5]
G
.
D
a
s
h
a
nd
D
.
C
ha
kr
a
bor
t
y,
“
D
i
gi
t
a
l
t
r
a
ns
f
or
m
a
t
i
on
of
m
a
r
ke
t
i
ng
s
t
r
a
t
e
gi
e
s
dur
i
ng
a
pa
nde
m
i
c
:
E
vi
de
nc
e
f
r
om
a
n
e
m
e
r
gi
ng
e
c
onom
y dur
i
ng c
ovi
d
-
19,”
Sus
t
ai
nabi
l
i
t
y
, vol
. 13, no. 12, 2021, doi
:
10.3390/
s
u13126735.
[
6]
M
.
S
.
H
os
a
i
n
a
nd
P
.
L
i
u,
“
L
i
nke
d
i
n
f
or
s
e
a
r
c
hi
ng
be
t
t
e
r
j
ob
oppo
r
t
uni
t
y:
P
a
s
s
i
ve
j
obs
e
e
ke
r
s
’
pe
r
c
e
i
ve
d
e
xpe
r
i
e
nc
e
,”
Q
ual
i
t
at
i
v
e
R
e
por
t
, vol
. 25, no. 10, 2020, doi
:
10.46743/
2160
-
3715/
2020.4449.
[
7]
R
.
T
ha
kka
r
,
“
T
op
100
hi
r
i
ng
s
t
a
t
i
s
t
i
c
s
f
or
2022,”
L
i
nk
e
dI
n
,
2022.
A
c
c
e
s
s
e
d:
N
ov.
24,
2022.
[
O
nl
i
ne
]
.
A
va
i
l
a
bl
e
:
ht
t
ps
:
/
/
w
w
w
.l
i
nke
di
n.c
om
/
pul
s
e
/
t
op
-
100
-
hi
r
i
ng
-
s
t
a
t
i
s
t
i
c
s
-
2022
-
r
i
nku
-
t
ha
kka
r
/
[
8]
B
.
T
.
J
a
ni
gová
,
“
T
he
ge
nr
e
a
n
a
l
ys
i
s
of
j
ob
a
dve
r
t
s
po
s
t
e
d
on
l
i
nke
dI
n,”
M
.Sc
.
T
h
e
s
i
s
,
D
e
pa
r
t
m
e
nt
of
E
ngl
i
s
h
a
nd
A
m
e
r
i
c
a
n
S
t
udi
e
s
,
M
a
s
a
r
yk U
ni
ve
r
s
i
t
y, B
r
no,
C
z
e
c
h R
e
publ
i
c
, 2023.
[
9]
S
. L
.
-
C
a
r
r
i
l
, C
. A
na
gnos
t
opoul
os
, a
nd P
.
P
a
r
ga
na
s
, “
S
oc
i
a
l
m
e
di
a
i
n s
por
t
m
a
n
a
ge
m
e
nt
e
duc
a
t
i
on:
I
nt
r
oduc
i
ng L
i
nke
dI
n,”
J
our
nal
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8938
I
nt
J
A
r
ti
f
I
nt
e
ll
, V
ol
.
13
, N
o.
4
,
D
e
c
e
m
be
r
2024
:
4334
-
4343
4342
of
H
os
pi
t
al
i
t
y
, L
e
i
s
ur
e
, Spo
r
t
and T
our
i
s
m
E
duc
at
i
on
, vol
. 27, 2020, doi
:
10.1016/
j
.j
hl
s
t
e
.2020.100262.
[
10]
K
.
S
.
W
e
i
,
“
L
i
nke
dI
n
i
n
M
a
l
a
ys
i
a
:
a
c
om
pr
e
he
ns
i
v
e
ove
r
vi
e
w
of
t
he
gr
ow
i
n
g
pr
of
e
s
s
i
ona
l
ne
t
w
or
k
i
n
2023,”
L
i
nk
e
dI
n.
2023.
A
c
c
e
s
s
e
d:
M
a
y
04,
2023.
[
O
nl
i
ne
]
.
A
va
i
l
a
bl
e
:
ht
t
ps
:
/
/
w
w
w
.l
i
nke
di
n.c
om
/
pul
s
e
/
l
i
nke
di
n
-
m
a
l
a
ys
i
a
-
c
om
pr
e
he
ns
i
ve
-
ove
r
vi
e
w
-
gr
ow
i
ng
-
ne
t
w
or
k
-
s
hoo/
[
11]
G
.
D
.
M
a
r
i
n
a
nd
C
.
N
i
l
ă
,
“
B
r
a
ndi
ng
i
n
s
oc
i
a
l
m
e
di
a
us
i
ng
L
i
nke
dI
n
i
n
pe
r
s
ona
l
br
a
nd
c
om
m
uni
c
a
t
i
on:
A
s
t
udy
on
c
om
m
uni
c
a
t
i
ons
/
m
a
r
ke
t
i
ng
a
nd
r
e
c
r
ui
t
m
e
nt
/
hum
a
n
r
e
s
our
c
e
s
s
pe
c
i
a
l
i
s
t
s
pe
r
c
e
p
t
i
on,”
Soc
i
al
Sc
i
e
nc
e
s
&
H
um
ani
t
i
e
s
O
pe
n
,
vol
.
4
,
no. 1, pp. 1
–
8, 2021, doi
:
10.1016/
j
.s
s
a
ho.2021.100174.
[
12]
B
. H
m
oud a
nd V
. L
a
s
z
l
o, “
W
i
l
l
a
r
t
i
f
i
c
i
a
l
i
nt
e
l
l
i
ge
nc
e
t
a
ke
ove
r
hum
a
n r
e
s
our
c
e
s
r
e
c
r
ui
t
m
e
nt
a
nd s
e
l
e
c
t
i
on?
,”
N
e
t
w
or
k
I
nt
e
l
l
i
ge
nc
e
St
udi
e
s
, vol
. 7, no. 13, pp. 31
–
30, 2019.
[
13]
D
.
P
.
S
i
va
na
nda
m
a
nd
M
.
P
.
M
uda
l
i
a
r
,
“
A
s
t
udy
on
s
c
i
e
nt
i
f
i
c
s
c
r
e
e
ni
ng
pr
oc
e
s
s
i
n
a
r
e
c
r
ui
t
m
e
nt
c
ons
ul
t
a
nc
y
f
i
r
m
,”
J
our
nal
of
C
ont
e
m
por
ar
y
I
s
s
ue
s
i
n B
us
i
ne
s
s
and G
ov
e
r
nm
e
nt
, vol
. 26, no. 2, 2021, doi
:
10
.47750/
c
i
bg.2020.26.02.053.
[
14]
E
.
F
i
s
he
r
,
R
.
S
.
T
hom
a
s
,
M
.
K
.
H
i
ggi
ns
,
C
.
J
.
W
i
l
l
i
a
m
s
,
I
.
C
hoi
,
a
nd
L
.
A
.
M
c
C
a
ul
e
y,
“
F
i
ndi
ng
t
he
r
i
ght
c
a
ndi
da
t
e
:
D
e
ve
l
opi
ng
hi
r
i
ng
gui
de
l
i
ne
s
f
or
s
c
r
e
e
ni
ng
a
ppl
i
c
a
nt
s
f
or
c
l
i
ni
c
a
l
r
e
s
e
a
r
c
h
c
oor
di
na
t
or
pos
i
t
i
ons
,”
J
ou
r
nal
of
C
l
i
ni
c
al
and
T
r
an
s
l
at
i
onal
Sc
i
e
nc
e
,
vol
. 6, no. 1, 2022, doi
:
10.1017/
c
t
s
.2021.853.
[
15]
I
.
N
i
kol
a
ou,
“
W
ha
t
i
s
t
he
r
ol
e
o
f
t
e
c
hnol
ogy
i
n
r
e
c
r
ui
t
m
e
nt
a
nd
s
e
l
e
c
t
i
on?
,”
S
pani
s
h
J
our
nal
of
P
s
y
c
hol
ogy
,
vol
.
24,
2021,
doi
:
10.1017/
S
J
P
.2021.6.
[
16]
J
.
L
.
R
.
-
S
á
nc
he
z
,
T
.
G
.
-
T
or
r
e
s
,
A
.
M
.
-
N
a
va
r
r
o,
a
nd
R
.
G
.
-
L
os
a
da
,
“
I
nve
s
t
i
ng t
i
m
e
a
nd
r
e
s
our
c
e
s
f
or
w
or
k
–
l
i
f
e
ba
l
a
nc
e
:
t
he
e
f
f
e
c
t
on
t
a
l
e
nt
r
e
t
e
nt
i
on,”
I
nt
e
r
nat
i
onal
J
our
nal
of
E
nv
i
r
onm
e
nt
al
R
e
s
e
ar
c
h
and
P
ubl
i
c
H
e
al
t
h
,
vol
.
17,
no.
6,
2020,
doi
:
10.3390/
i
j
e
r
ph17061920.
[
17]
H
.
S
.
-
S
z
c
z
a
pa
,
“
R
e
c
r
ui
t
m
e
nt
of
e
m
pl
oye
e
s
—
a
s
s
um
pt
i
ons
of
t
he
r
i
s
k
m
ode
l
,”
R
i
s
k
s
,
vol
.
9,
no.
3,
2021,
doi
:
10.3390/
r
i
s
k
s
9030055.
[
18]
G
.
E
r
doğa
n,
“
T
he
e
t
hi
c
a
l
s
hor
t
l
i
s
t
i
ng
pr
obl
e
m
,”
C
om
put
e
r
s
and
O
pe
r
at
i
ons
R
e
s
e
a
r
c
h
,
vol
.
138,
2022,
doi
:
10.1016/
j
.c
or
.2021.105593.
[
19]
J
.
H
.
H
a
r
dy,
K
.
S
.
T
e
y,
W
. C
.
-
L
a
i
,
R
.
F
. M
a
r
t
e
l
l
,
A
.
O
l
s
t
a
d,
a
nd
E
. L
.
U
hl
m
a
nn, “
B
i
a
s
i
n
c
ont
e
xt
:
S
m
a
l
l
bi
a
s
e
s
i
n
hi
r
i
ng
e
va
l
ua
t
i
on
s
ha
ve
bi
g c
ons
e
que
n
c
e
s
,”
J
our
nal
of
M
anage
m
e
nt
, vol
. 48, no. 3, 2022, doi
:
10.
1177/
0149206320982654.
[
20]
K
. A
. F
. A
. S
a
m
a
h, N
. S
. D
. W
i
r
a
ka
r
na
i
n, R
. H
a
m
z
a
h, N
. A
. M
oke
t
a
r
, L
. S
. R
i
z
a
, a
nd Z
. O
t
hm
a
n, “
A
l
i
ne
a
r
r
e
gr
e
s
s
i
on a
ppr
oa
c
h t
o
pr
e
di
c
t
i
ng
s
a
l
a
r
i
e
s
w
i
t
h
vi
s
ua
l
i
z
a
t
i
on
s
of
j
ob
va
c
a
nc
i
e
s
:
a
c
a
s
e
s
t
udy
of
J
obs
t
r
e
e
t
M
a
l
a
ys
i
a
,
”
I
A
E
S
I
nt
e
r
nat
i
onal
J
our
nal
of
A
r
t
i
f
i
c
i
al
I
nt
e
l
l
i
ge
nc
e
, vol
. 11, no. 3, pp. 1130
–
1142, 2022, doi
:
10.11591/
i
j
a
i
.v11.i
3.pp1
130
-
1142.
[
21]
M
.
G
.
R
obi
ns
on,
“
S
ki
l
l
s
a
nd
qua
l
i
f
i
c
a
t
i
ons
f
or
t
he
s
pe
c
i
a
l
l
i
br
a
r
y
e
nvi
r
onm
e
nt
i
n
J
a
m
a
i
c
a
:
a
j
ob
a
dve
r
t
i
s
e
m
e
nt
a
na
l
ys
i
s
,”
L
i
br
a
r
y
M
anage
m
e
nt
, vol
. 42, no. 1
–
2, 2021, doi
:
10.1108/
L
M
-
07
-
2020
-
0109.
[
22]
M
. H
a
l
i
ns
ki
a
nd J
. A
. H
a
r
r
i
s
on, “
T
he
j
ob r
e
s
our
c
e
s
-
e
nga
ge
m
e
nt
r
e
l
a
t
i
on
s
hi
p:
t
he
r
ol
e
of
l
oc
a
t
i
on,”
I
nt
e
r
nat
i
onal
J
our
nal
of
P
ubl
i
c
Se
c
t
or
M
anage
m
e
nt
, vol
. 33, no. 6
–
7, 2020, doi
:
10.1108/
I
J
P
S
M
-
12
-
2019
-
0303
.
[
23]
L
.
R
onda
,
C
.
A
br
i
l
,
a
nd
C
.
V
a
l
or
,
“
J
ob
c
hoi
c
e
de
c
i
s
i
ons
:
unde
r
s
t
a
ndi
ng
t
he
r
ol
e
o
f
nonne
got
i
a
bl
e
a
t
t
r
i
but
e
s
a
nd
t
r
a
de
-
of
f
s
i
n
e
f
f
e
c
t
i
ve
s
e
gm
e
nt
a
t
i
on,”
M
anage
m
e
nt
D
e
c
i
s
i
on
, vol
. 59, no. 6, pp. 1546
–
1561, 2020, doi
:
10.1108/
M
D
-
10
-
2019
-
1472.
[
24]
M
. I
z
ve
r
c
i
a
n, S
. P
ot
r
a
, a
nd
L
.
I
va
s
c
u,
“
J
ob s
a
t
i
s
f
a
c
t
i
on
va
r
i
a
bl
e
s
:
A
gr
ounde
d t
he
or
y a
ppr
oa
c
h,”
P
r
oc
e
di
a
-
Soc
i
al
and B
e
hav
i
o
r
al
Sc
i
e
nc
e
s
, vol
. 221, 2016, doi
:
10.1016/
j
.s
b
s
pr
o.2016.05.093.
[
25]
M
. K
a
ya
a
nd T
. B
oge
r
s
, “
E
f
f
e
c
t
i
ve
ne
s
s
of
j
ob t
i
t
l
e
ba
s
e
d e
m
be
ddi
ngs
on r
e
s
um
e
t
o j
ob a
d r
e
c
om
m
e
nda
t
i
on,”
i
n
2021 W
or
k
s
hop on
R
e
c
om
m
e
nde
r
Sy
s
t
e
m
s
f
o
r
H
um
an R
e
s
ou
r
c
e
s
, R
E
C
SY
S I
N
H
R
2021
, A
m
s
t
e
r
da
m
, N
e
t
he
r
l
a
nds
, 2021, pp. 1
–
7.
[
26]
N
.
C
ha
i
ya
m
a
a
nd
N
.
K
a
e
w
pi
l
a
,
“
T
he
de
ve
l
opm
e
nt
of
l
i
f
e
a
nd
c
a
r
e
e
r
s
ki
l
l
s
i
n
21s
t
c
e
nt
ur
y
t
e
s
t
f
or
unde
r
gr
a
dua
t
e
s
t
ude
nt
s
,
”
E
ur
ope
a
n
J
our
nal
of
E
duc
at
i
onal
R
e
s
e
ar
c
h
, vol
. 11, no. 1, 2022, doi
:
10.12973/
e
u
-
j
e
r
.11.1.51.
[
27]
A
. T
a
ha
e
t
al
.
, “
R
obot
i
c
c
ol
or
e
c
t
a
l
s
ur
ge
r
y:
qua
l
i
t
y a
s
s
e
s
s
m
e
nt
of
pa
t
i
e
nt
i
nf
or
m
a
t
i
on a
va
i
l
a
bl
e
on t
he
i
nt
e
r
ne
t
us
i
ng w
e
bs
c
r
a
pi
ng,”
C
om
put
e
r
A
s
s
i
s
t
e
d Sur
g
e
r
y
, vol
. 28, no. 1, 2023, doi
:
10.1080/
24699322.2023.
2187275.
[
28]
M
. M
. Ö
z
t
ür
k, “
C
os
i
ne
s
i
m
i
l
a
r
i
t
y
-
ba
s
e
d c
r
os
s
-
pr
oj
e
c
t
de
f
e
c
t
pr
e
di
c
t
i
on,”
B
i
l
i
ş
i
m
T
e
k
nol
oj
i
l
e
r
i
D
e
r
gi
s
i
, vol
. 12, no. 3, pp. 159
–
167,
2019, doi
:
10.17671/
ga
z
i
bt
d.453436.
[
29]
L
.
K
.
F
oo,
S
.
L
.
C
hua
,
a
nd
N
.
I
br
a
hi
m
,
“
A
t
t
r
i
but
e
w
e
i
ght
e
d
na
ï
v
e
ba
ye
s
c
l
a
s
s
i
f
i
e
r
,”
C
om
put
e
r
s
,
M
at
e
r
i
al
s
and
C
ont
i
nua
,
vol
.
71
,
no. 1, 2022, doi
:
10.32604/
c
m
c
.2022.022011.
[
30]
K
.
A
.
F
.
A
.
S
a
m
a
h,
N
.
M
.
N
.
A
z
ha
r
l
udi
n,
L
.
S
.
R
i
z
a
,
M
.
N
.
H
.
H
.
J
ono,
a
nd
N
.
A
.
M
oke
t
a
r
,
“
C
l
a
s
s
i
f
i
c
a
t
i
on
a
nd
vi
s
ua
l
i
z
a
t
i
on:
T
w
i
t
t
e
r
s
e
nt
i
m
e
nt
a
na
l
ys
i
s
of
M
a
l
a
ys
i
a
’
s
pr
i
va
t
e
ho
s
pi
t
a
l
s
,”
I
A
E
S I
nt
e
r
nat
i
onal
J
our
nal
of
A
r
t
i
f
i
c
i
al
I
nt
e
l
l
i
ge
nc
e
(
I
J
-
A
I
)
, vol
. 12, no. 4, pp.
1793
–
1802, 2023, doi
:
10.11591/
i
j
a
i
.v12.i
4.pp1793
-
1802.
[
31]
P
.
N
.
M
w
a
r
o,
D
.
K
.
O
ga
da
,
a
nd
P
.
W
.
C
he
r
ui
yot
,
“
A
ppl
i
c
a
bi
l
i
t
y
of
N
a
ï
ve
B
a
ye
s
m
ode
l
f
or
a
ut
om
a
t
i
c
r
e
s
um
e
c
l
a
s
s
i
f
i
c
a
t
i
on,
”
I
nt
e
r
nat
i
onal
J
our
nal
of
C
om
put
e
r
A
ppl
i
c
at
i
ons
T
e
c
hnol
ogy
and
R
e
s
e
a
r
c
h
,
vol
.
9,
no.
9,
pp.
257
–
264,
2020,
doi
:
10.7753/
i
j
c
a
t
r
0909.1002.
[
32]
Y
.
L
i
u
a
nd A
.
I
.
A
be
yr
a
t
ne
,
P
r
ac
t
i
c
al
appl
i
c
at
i
ons
of
B
ay
e
s
i
an
r
e
l
i
abi
l
i
t
y
.
H
obo
ke
n,
U
ni
t
e
d
S
t
a
t
e
s
of
A
m
e
r
i
c
a
:
J
ohn
W
i
l
e
y
&
S
ons
,
2019.
[
33]
K
.
A
.
F
.
A
.
S
a
m
a
h,
N
.
F
.
A
. M
i
s
da
n, M
.
N
.
H
.
H
.
J
ono,
a
nd
L
.
S
. R
i
z
a
,
“
T
he
be
s
t
M
a
l
a
ys
i
a
n
a
i
r
l
i
ne
c
om
pa
ni
e
s
vi
s
ua
l
i
z
a
t
i
on
t
hr
ough
bi
l
i
ngua
l
t
w
i
t
t
e
r
s
e
nt
i
m
e
nt
a
na
l
ys
i
s
:
A
m
a
c
hi
ne
l
e
a
r
ni
ng
c
l
a
s
s
i
f
i
c
a
t
i
on,”
J
O
I
V
:
I
nt
e
r
nat
i
onal
J
our
nal
on I
nf
or
m
at
i
c
s
V
i
s
ual
i
z
at
i
on
,
vol
. 6, no. 1, pp. 130
–
137, 2022, doi
:
10.30630/
j
oi
v.6.1.879.
B
I
O
G
R
A
P
H
I
E
S
O
F
A
U
T
H
O
R
S
Khyrina
Airin
Fariza
Abu
Samah
is
a
senior
lecturer
at
the
College
of
Computing
,
Informatics
and
Mathematics
in
Universiti
Teknologi
MARA
(UiT
M)
Melaka
Branch,
Jasin
Campus.
Before
joining
UiTM,
she
had
13
years
of
working
experie
nce
in
the
semicondu
ctor
industry. She h
as a Diploma
, Bac
helor’s Degree a
nd Master’s Degree in Computer Scienc
e and
Ph
.
D
.
in
Information
Technology.
Her
research
interests
a
re
in
artifici
al
intelligence,
algorithm
analysis
,
machine
learning,
dat
a
science,
optimi
zation,
and
eva
cuatio
n
algorit
hms.
She
can
be
contacted
at email
: khyri
na783@
uitm.ed
u.my.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
r
ti
f
I
nt
e
ll
I
S
S
N
:
2252
-
8938
E
li
gi
bi
li
ty
r
at
e
of
appli
c
ant
’
s
L
in
k
e
dI
n ac
c
ount
:
a naïv
e
bay
e
s
…
(
K
hy
r
in
a A
ir
in
F
ar
iz
a
A
bu Samah
)
4343
Nurul
Atirah
Ahmad
is
a
Bachelor’s
student
in
Computer
Sci
ence
currently
undergoing her internship programme. He
r research inter
ests are data
mining, machine learning
algorit
hms,
data
analysis
and
visuali
zation.
She
is
actively
involv
ed
in
the
research
group
at
UiTM. Curren
tly, she is pur
suing an inte
rnship at Ama
st Sdn Bhd, Sel
angor, Ma
laysia. She
can
be contacted at email: 2020482848@student.uitm
.edu.my.
Anis
Amilah
is
a
lecturer
at
the
College
of
Computing,
Informatic
s
an
d
Mathematic
s
in
Universiti
Teknologi
MARA
(UiTM)
Melaka
Branch,
Jasin
Camp
us.
She
has
a
Master
of
Scienc
es
degre
e
from
UiTM
Shah
Alam.
With
a
solid
educa
tional
backg
round,
she
brings
expertise
and
knowledg
e
to
her
role,
contribu
ting
to
the
academic
en
vironmen
t.
Her
resear
ch
interests
revolve
around
artificia
l
intelligence
and
emergen
ce
algorit
hms.
Her
focus
on
these
cutting
-
edge
fields
underscores
a
commitment
to
exploring
in
novative
solutions
and
understanding
the
dynamic
interplay
between
intelligence
and
emergent
phenom
ena.
She
can
be
contacted
at email
: anisam
ilah@
uitm.ed
u.my.
Hana
Fakhira
Almarzuki
is
a
lecturer
at
the
College
of
Computi
ng,
Informatics
and
Mathematics
at
Universiti
Teknologi
MARA
(UiTM)
Shah
Alam,
Selangor.
She
is
currently
a
Ph
.
D
.
candidate
in
the
College
of
Comput
ing,
Informati
cs
and
Mathemati
cs,
Universi
ti
Teknologi
MARA,
Melaka,
Jasin
Campus,
Malaysia.
Her
research
interests
are
intelligent
tutoring
systems,
artificia
l
intelligence
,
and
machine
learning.
She
ca
n
be
contacte
d
at
email
:
hanaalira97@gmail.com
.
Zuhri
Arafah
Zulkifli
is
lecturer
at
College
of
Computing,
Informatics
and
Mathematics
in
Universiti
Teknologi
MARA
(UiTM)
Melaka
Branch,
Jasin
Campus.
Before
joining
UiTM,
she
has
been
working
with
HSBC
GLC
Malaysia.
She
ha
s
a
Diploma
in
Computer
Scienc
es,
a
Degre
e
in
Intelli
gent
Systems
from
UiTM
and
a
Master
of Man
ageme
nt
Infor
mation
Systems
from
UKM.
She
has
a
passion
ate
intere
st
in
educa
tional
techno
logy,
knowle
dge
manageme
nt,
intelligent
systems
,
and
big
data.
She
can
b
e
contacted
at
email
:
zuhrizulk
ifli@
uitm.ed
u.m
y.
Lala
Septem
Riza
received
Ph
.
D
.
in
Computer
Science
from
Universidad
de
Granada,
Spain,
in
2015.
He
works
in
the
Department
of
Comp
uter
Science
Education,
Universitas
Pendidikan
Indonesia,
Indonesia.
He
teaches
machine
lear
ning,
big
data
platforms,
and
statistical
data
science.
His
rese
arch
interests
are
in
machine
lea
rning,
data
science,
an
d
education
. He can be
contacted
at lala.s
.riza@
upi.edu.
Amir Haikal Ab
dul Hal
im
received a Master’s
Degree in
Comput
e
r Science from
Universiti
Teknologi
MARA.
He
is
currently
a
research
assistant
and
intends
to
be
a
Ph.D.
candidate
in
the
College
of
Comput
ing,
Informati
cs,
and
Mathemati
cs,
Universi
ti
Teknolog
i
MARA,
Melaka,
Jasin
Camp
us,
Malaysia.
He
has
a
Diploma
and
a
Deg
ree
in
Computer
Science
.
His
research
interests
are
evacuation
algorithms,
algorithm
analysis,
a
rtificial
intelligence,
and
machine le
arning. He
can be
contacte
d
at
email:
ameerhaical@
gmail.co
m.
Evaluation Warning : The document was created with Spire.PDF for Python.