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
.
14
, N
o.
3
,
J
une
2025
, pp.
1940
~
1950
I
S
S
N
:
2252
-
8938
,
D
O
I
:
10.11591/
ij
a
i.
v
14
.i
3
.pp
1940
-
1950
1940
Jou
r
n
al
h
om
e
page
:
ht
tp
:
//
ij
ai
.
ia
e
s
c
or
e
.c
om
E
n
h
a
n
c
i
n
g p
l
ag
i
ar
i
sm
d
e
t
e
c
t
i
on
u
si
n
g d
at
a p
r
e
-
p
r
oc
e
ss
i
n
g an
d
m
ac
h
i
n
e
l
e
ar
n
i
n
g a
p
p
r
oac
h
V
r
u
s
h
al
i
B
h
u
yar
1
, S
ac
h
in
N
.
D
e
s
h
m
u
k
h
2
1
D
e
pa
r
t
m
e
nt
of
C
om
put
e
r
A
ppl
i
c
a
t
i
ons
,
M
a
ha
r
a
s
ht
r
a
I
ns
t
i
t
ut
e
of
T
e
c
hnol
ogy
,
D
r
. B
a
ba
s
a
he
b A
m
b
e
dka
r
M
a
r
a
t
hw
a
da
U
ni
v
e
r
s
i
t
y,
C
hh. S
a
m
bha
j
i
na
ga
r
, I
ndi
a
2
D
e
pa
r
t
m
e
nt
of
C
om
put
e
r
S
c
i
e
nc
e
a
nd I
T
,
D
r
. B
a
ba
s
a
he
b A
m
be
dka
r
M
a
r
a
t
hw
a
da
U
ni
ve
r
s
i
t
y, C
hh. S
a
m
bha
j
i
na
ga
r
, I
ndi
a
A
r
t
ic
le
I
n
f
o
A
B
S
T
R
A
C
T
A
r
ti
c
le
h
is
to
r
y
:
R
e
c
e
iv
e
d
F
e
b 2, 2024
R
e
vi
s
e
d
N
ov 19, 2024
A
c
c
e
pt
e
d
J
a
n 27, 2025
Modern
technology
and
the
internet
have
enhanced
academic
infor
mation
accessibil
ity,
but
this
has
led
to
a
rising
global
concern
about
plagi
arism.
Resear
chers
are
activel
y
exploring
machine
learnin
g
as
a
promising
s
olution
for
detection.
This
study
underscores
the
importance
of
robus
t
data
preprocessing
for
optimal
machine
learning
algorithm
performance.
Using
a
dataset
of
67
research
papers,
big
five
factors
(OCEAN),
and
plagiaris
m
rates,
the
study
employed
machine
learning
to
detect
plagiarism.
The
tr
aining
process involved exposing algori
thms to an 80%
training subs
et, follo
wed by
evaluatin
g
their
performance
on
the
remainin
g
20%
in
the
testing
phase,
assessin
g
generalizat
ion
capabilit
ies.
For
the
random
forest
regressor,
b
agging
regressor,
gradient
boosting
regressor
,
XGB
regressor
,
and
AdaBoost
regressor
,
corresponding
root
mean
squared
error
(
RMSE
)
are
9.48,
10.66,
11.79,
12.53
,
and
12.79,
respectively.
This
research
contributes
novel
i
nsights
to
existing
literature
by
introducing
a
plagiarism
detection
mod
el
that
innovatively
integrates
outlier
detection,
normaliza
tion,
missing
value
imputation,
and
feature
selection.
The
unique
aspect
lies
in
the
ef
fective
combinat
ion
of
feature
selectio
n
and
missi
ng
value
imputat
ion,
surp
assing
previous
benchmarks
and
optimizing
precisi
on
and
efficiency.
The
ap
proach
is
metaphorically
likened
to
assembling
puzzle
pieces,
highlighti
ng
the
distinctive
methodology
employed
in
enhancing
the
performance
of
the
plagiarism detection model using data preproce
ssing.
K
e
y
w
o
r
d
s
:
D
a
ta
pr
e
pr
oc
e
s
s
in
g
M
a
c
hi
ne
l
e
a
r
ni
ng
M
is
s
in
g va
lu
e
i
m
put
a
ti
on
P
la
gi
a
r
is
m
de
te
c
ti
on
R
e
gr
e
s
s
io
n
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
:
V
r
us
ha
li
B
huya
r
D
e
pa
r
tm
e
nt
of
C
om
put
e
r
A
ppl
ic
a
ti
ons
, M
a
ha
r
a
s
ht
r
a
I
ns
ti
tu
te
of
T
e
c
hnol
ogy
D
r
. B
a
ba
s
a
h
e
b A
m
be
dka
r
M
a
r
a
th
w
a
da
U
ni
ve
r
s
it
y
C
hh. S
a
m
bha
ji
na
ga
r
, I
ndi
a
E
m
a
il
:
vr
us
ha
li
.bhuya
r
@
gm
a
il
.c
om
1.
I
N
T
R
O
D
U
C
T
I
O
N
I
n
th
e
e
ve
r
-
e
vol
vi
ng
la
nd
s
c
a
pe
of
a
c
a
d
e
m
ic
a
nd
di
gi
ta
l
c
ont
e
nt
,
th
e
is
s
ue
of
pl
a
gi
a
r
is
m
r
e
m
a
in
s
a
s
ig
ni
f
ic
a
nt
c
onc
e
r
n.
A
s
th
e
vol
um
e
of
in
f
or
m
a
ti
on
a
va
il
a
bl
e
onl
i
ne
c
ont
in
ue
s
to
gr
ow
e
xpone
nt
ia
ll
y,
tr
a
di
ti
ona
l
m
e
th
ods
of
de
te
c
ti
ng
a
nd
pr
e
ve
nt
in
g
pl
a
gi
a
r
is
m
a
r
e
pr
ovi
ng
to
be
in
s
uf
f
ic
ie
nt
.
T
hi
s
r
e
s
e
a
r
c
h
a
im
s
to
a
ddr
e
s
s
th
is
c
ha
ll
e
nge
by
pr
opos
in
g
a
n
in
nova
ti
ve
a
ppr
oa
c
h
th
a
t
c
om
bi
ne
s
a
dva
nc
e
d
d
a
ta
pr
e
pr
oc
e
s
s
in
g
te
c
hni
que
s
w
it
h s
ta
te
-
of
-
th
e
-
a
r
t
m
a
c
hi
ne
l
e
a
r
ni
ng a
lg
or
it
hm
s
t
o e
nha
nc
e
pl
a
gi
a
r
is
m
de
te
c
ti
on.
T
o
e
xt
r
a
c
t
r
e
le
va
nt
f
e
a
tu
r
e
s
f
r
om
th
e
r
a
w
te
xt
ua
l
da
t
a
,
our
a
ppr
oa
c
h
be
gi
ns
w
it
h
th
or
ough
da
ta
pr
e
pr
oc
e
s
s
in
g.
T
o
do
th
is
,
th
e
te
xt
m
us
t
be
tr
a
ns
f
or
m
e
d
us
in
g
m
e
th
ods
li
ke
m
is
s
in
g
va
lu
e
im
put
a
ti
on,
r
e
m
ove
d
unw
a
nt
e
d
a
tt
r
ib
ut
e
s
,
out
li
e
r
de
te
c
ti
on,
a
nd
nor
m
a
li
z
a
ti
on
in
to
a
f
or
m
a
t
th
a
t
is
c
ons
is
te
nt
a
nd
a
ppr
opr
ia
te
f
or
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
nhanc
in
g pl
agi
ar
is
m
de
te
c
ti
on us
in
g data pr
e
-
pr
oc
e
s
s
in
g and
m
ac
hi
ne
l
e
ar
ni
ng
…
(
V
r
us
hal
i
B
huy
a
r
)
1941
m
a
c
hi
ne
le
a
r
ni
ng
a
n
a
ly
s
is
.
T
hi
s
th
or
ough
pr
e
pr
oc
e
s
s
in
g
c
r
e
a
te
s
th
e
f
ounda
ti
on
f
or
m
a
c
hi
ne
le
a
r
ni
ng
m
ode
ls
th
a
t
a
r
e
m
or
e
pr
e
c
is
e
a
nd c
om
pl
e
x.
T
he
us
e
of
m
a
c
hi
ne
le
a
r
ni
ng
a
lg
or
it
hm
s
th
a
t
c
a
n
id
e
nt
if
y
pa
tt
e
r
ns
a
nd
a
bnor
m
a
li
ti
e
s
in
th
e
pr
e
pr
oc
e
s
s
e
d
da
ta
i
s
t
he
s
e
c
ond
e
s
s
e
nt
ia
l
e
le
m
e
nt
of
our
m
e
th
od
ol
ogy. W
e
t
r
a
in
t
h
e
m
ode
l
on l
a
be
ll
e
d
da
ta
s
e
ts
us
in
g
s
upe
r
vi
s
e
d
le
a
r
ni
ng
a
ppr
oa
c
h
e
s
,
in
c
lu
di
ng
r
e
gr
e
s
s
io
n
te
c
h
ni
que
s
,
s
o
th
a
t
it
c
a
n
id
e
nt
if
y
pa
tt
e
r
ns
li
nke
d
to
pl
a
gi
a
r
is
m
.
O
ur
m
e
th
od
s
e
e
ks
to
gr
e
a
tl
y
im
pr
ove
th
e
e
f
f
e
c
ti
ve
ne
s
s
of
pl
a
gi
a
r
is
m
de
te
c
ti
on
s
ys
t
e
m
s
by
m
e
r
gi
ng
th
e
be
s
t
f
e
a
tu
r
e
s
of
m
a
c
hi
ne
l
e
a
r
ni
ng a
nd da
ta
pr
e
pr
oc
e
s
s
in
g, t
he
r
e
by e
nha
nc
in
g t
he
i
nt
e
gr
it
y of
a
c
a
de
m
ic
a
nd
di
gi
ta
l
c
ont
e
nt
gl
oba
ll
y.
H
e
lg
e
s
s
on
a
nd
E
r
ik
s
s
on
[
1]
,
publ
is
he
r
s
,
a
nd
e
duc
a
ti
ona
l
in
s
ti
tu
ti
ons
m
us
t
c
ope
w
it
h
th
e
s
e
r
io
us
gl
oba
l
pr
obl
e
m
of
pl
a
gi
a
r
is
m
.
E
ve
n
th
ough
it
'
s
ha
r
d
to
de
f
in
e
,
w
e
f
r
e
qu
e
nt
ly
r
e
f
e
r
to
pl
a
gi
a
r
is
m
a
s
"
f
ic
ti
ona
l
s
te
a
li
ng."
I
t'
s
th
e
s
a
m
e
a
s
s
te
a
li
ng
ot
he
r
pe
opl
e
'
s
c
onc
e
pt
s
,
c
r
e
de
nt
ia
ls
,
c
ode
,
a
nd
vi
s
ua
ls
a
nd
pa
s
s
in
g
th
e
m
of
f
a
s
one
'
s
ow
n.
B
e
c
a
us
e
di
f
f
e
r
e
nt
or
ga
ni
z
a
ti
ons
a
nd
f
ie
ld
s
ha
ve
va
r
ie
d
vi
e
w
s
on
pl
a
gi
a
r
is
m
,
it
doe
s
n'
t
ne
e
d
to
be
r
e
por
te
d
by
a
s
ubj
e
c
t
e
xpe
r
t.
I
t
ha
s
a
ls
o
be
e
n
s
how
n
to
be
a
r
us
e
in
a
c
a
de
m
ic
[
2]
a
nd
li
te
r
a
r
y
c
ir
c
le
s
.
T
h
e
y
m
us
t
be
f
ound
a
s
a
r
e
s
ul
t.
P
la
gi
a
r
is
m
ha
s
be
e
n
th
e
s
ubj
e
c
t
of
num
e
r
ous
s
tu
di
e
s
,
w
hi
c
h
ha
ve
pr
oduc
e
d
a
num
be
r
of
de
f
in
it
io
ns
[
3]
.
A
c
c
or
di
ng
to
[
4
]
“
P
la
gi
a
r
is
m
oc
c
ur
s
w
he
n
s
om
e
one
us
e
s
w
or
ds
,
id
e
a
s
,
or
w
or
k
p
r
oduc
ts
,
a
tt
r
ib
ut
a
bl
e
t
o
a
not
he
r
id
e
nt
if
ia
bl
e
pe
r
s
on
or
s
our
c
e
,
w
it
hout
a
tt
r
ib
ut
in
g t
he
w
or
k
to
th
e
s
our
c
e
f
r
om
w
hi
c
h
it
w
a
s
obt
a
in
e
d,
in
a
s
it
ua
ti
on
in
w
hi
c
h
th
e
r
e
i
s
a
le
gi
ti
m
a
te
e
xpe
c
t
a
ti
on
of
or
ig
in
a
l
a
ut
hor
s
hi
p,
in
or
de
r
to
obt
a
in
s
om
e
b
e
ne
f
it
,
c
r
e
di
t,
or
ga
in
w
hi
c
h
ne
e
d
not
be
m
on
e
ta
r
y
”
.
T
h
e
f
a
s
t
gr
ow
th
of
w
e
b
c
ont
e
nt
ha
s
in
c
r
e
a
s
e
d
th
e
r
is
k
of
pl
a
gi
a
r
is
m
in
a
c
a
de
m
ic
r
e
s
e
a
r
c
h.
P
la
gi
a
r
is
m
is
a
c
r
im
e
in
th
e
U
ni
te
d
S
ta
te
s
,
but
vi
ol
a
ti
ons
of
th
e
a
ut
hor
'
s
r
ig
ht
to
c
r
e
di
t
a
nd c
opyr
ig
ht
i
nf
r
in
ge
m
e
nt
a
r
e
a
ls
o c
iv
il
w
r
ongs
f
or
w
hi
c
h t
he
of
f
e
nde
r
m
a
y a
ls
o be
punis
he
d.
F
or
th
e
pu
r
pos
e
of
pr
e
ve
nt
in
g
p
la
gi
a
r
is
m
a
nd
pr
e
s
e
r
vi
ng
th
e
o
r
ig
in
a
li
ty
of
th
e
in
f
or
m
a
ti
on
s
our
c
e
,
it
is
e
s
s
e
nt
ia
l
to
unde
r
ta
ke
pl
a
gi
a
r
is
m
de
te
c
ti
on
a
t
va
r
io
us
s
ta
ge
s
.
T
o
do
th
is
,
r
e
s
e
a
r
c
h
ha
s
be
e
n
goi
ng
on
f
or
a
w
hi
le
.
O
ve
r
ti
m
e
,
a
va
r
ie
ty
of
te
c
hni
que
s
a
nd
te
c
hnol
ogi
e
s
ha
v
e
be
e
n
c
r
e
a
te
d
to
de
te
c
t
pl
a
gi
a
r
is
m
a
t
va
r
io
us
le
ve
ls
[
5]
–
[
7]
.
T
he
r
e
a
r
e
num
e
r
ous
m
e
th
od
s
f
or
s
pot
ti
ng
pl
a
gi
a
r
is
m
;
how
e
ve
r
,
it
is
ye
t
un
c
e
r
ta
in
how
th
e
s
e
te
c
hnol
ogi
e
s
w
il
l
a
dva
nc
e
t
o of
f
e
r
a
hi
gh l
e
ve
l
of
a
c
c
ur
a
c
y.
M
a
c
hi
ne
le
a
r
ni
ng
a
lg
or
it
hm
s
[
8]
–
[
10]
pl
a
y
a
vi
ta
l
r
ol
e
in
s
c
i
e
nt
if
ic
c
om
put
in
g,
a
s
w
e
ll
a
s
in
da
ta
a
nd
te
xt
m
in
in
g.
A
c
c
or
di
ng
to
r
e
c
e
nt
s
tu
di
e
s
,
it
is
c
r
uc
ia
l
to
us
e
da
ta
p
r
e
pr
oc
e
s
s
in
g
a
nd
m
a
c
hi
n
e
le
a
r
ni
ng
a
ppr
oa
c
he
s
[
11]
–
[
13]
to
s
pe
e
d
up a
nd
e
nh
a
nc
e
th
e
p
e
r
f
or
m
a
nc
e
of
th
e
m
od
e
ls
.
A
s
a
r
e
s
ul
t,
th
e
s
ugg
e
s
te
d
s
y
s
te
m
r
e
li
e
s
on
m
a
c
hi
ne
l
e
a
r
ni
ng a
nd da
ta
pr
e
pr
oc
e
s
s
in
g m
e
th
ods
.
V
a
r
ga
s
e
t
al
.
[
14]
pr
e
s
e
nt
s
a
c
om
pr
e
he
ns
iv
e
te
c
hni
que
f
or
pr
e
pr
oc
e
s
s
in
g
im
ba
la
nc
e
d
da
ta
s
e
ts
in
m
a
c
hi
ne
le
a
r
ni
ng,
a
ddr
e
s
s
in
g
th
e
c
ha
ll
e
nge
po
s
e
d
by
s
k
e
w
e
d
c
la
s
s
di
s
tr
ib
ut
io
ns
f
a
vor
in
g
th
e
m
a
jo
r
it
y
c
la
s
s
.
T
he
a
ut
hor
s
s
ys
te
m
a
ti
c
a
ll
y
r
e
vi
e
w
a
va
il
a
bl
e
m
e
th
odol
ogi
e
s
,
a
i
m
in
g
to
pr
ovi
de
a
c
om
pr
e
he
ns
iv
e
ove
r
vi
e
w
of
r
e
c
e
nt
s
tr
a
te
gi
e
s
f
or
m
it
ig
a
ti
ng
c
la
s
s
im
ba
la
n
c
e
a
nd
im
pr
ovi
ng
m
ode
l
pe
r
f
or
m
a
nc
e
.
S
tr
a
te
gi
e
s
s
uc
h
a
s
c
o
s
t
-
s
e
ns
it
iv
e
le
a
r
ni
ng,
hybr
id
a
ppr
oa
c
he
s
,
ove
r
s
a
m
pl
in
g,
a
nd
unde
r
s
a
m
pl
in
g
a
r
e
li
ke
ly
in
ve
s
ti
ga
te
d
a
nd
c
a
te
gor
iz
e
d
ba
s
e
d
on
th
e
ir
e
f
f
ic
a
c
y
w
it
h
di
f
f
e
r
e
nt
da
ta
s
e
ts
a
nd
a
lg
or
it
hm
s
.
T
he
s
ur
ve
y
of
f
e
r
s
in
s
ig
ht
s
in
to
th
e
a
dva
nt
a
ge
s
a
nd
di
s
a
dva
nt
a
ge
s
of
e
a
c
h
m
e
th
od,
f
ur
ni
s
hi
ng
a
c
a
de
m
ic
s
a
nd
pr
a
c
ti
ti
one
r
s
w
it
h
a
va
lu
a
bl
e
r
e
s
our
c
e
f
or
i
nf
or
m
e
d de
c
is
io
n
-
m
a
ki
ng i
n m
a
c
hi
ne
l
e
a
r
ni
ng pr
oj
e
c
ts
de
a
l
in
g w
it
h i
m
ba
la
nc
e
d da
ta
.
A
lf
ik
r
i
a
nd
P
ur
w
a
r
ia
nt
i
[
15]
c
onduc
t
a
th
or
ough
li
te
r
a
tu
r
e
s
ur
ve
y
on
e
xt
r
in
s
ic
pl
a
gi
a
r
is
m
de
te
c
ti
on
s
ys
te
m
s
,
f
oc
us
in
g
on
m
a
c
hi
ne
l
e
a
r
ni
ng
te
c
hni
que
s
li
ke
n
a
iv
e
B
a
ye
s
a
nd
S
V
M
.
T
he
y
e
va
lu
a
te
di
v
e
r
s
e
li
te
r
a
tu
r
e
,
e
m
pha
s
iz
in
g m
e
th
ods
be
yond te
xt
ua
l
a
na
ly
s
is
, s
u
c
h a
s
m
e
ta
da
t
a
e
xa
m
in
a
ti
on. T
hr
ough a
s
s
e
s
s
in
g
n
a
iv
e
B
a
ye
s
a
nd
S
V
M
a
c
r
os
s
da
ta
s
e
ts
a
nd
s
e
tu
ps
,
th
e
y
pr
ovi
de
in
s
ig
ht
s
i
nt
o
th
e
ir
e
f
f
e
c
ti
ve
ne
s
s
.
T
he
s
ur
ve
y
not
onl
y
s
um
m
a
r
iz
e
s
e
xi
s
ti
ng
knowle
dge
but
a
ls
o
hi
ghl
ig
ht
s
e
vol
vi
ng
m
e
th
odol
ogi
e
s
a
nd
th
e
pot
e
nt
ia
l
f
or
m
a
c
hi
ne
le
a
r
ni
ng
to
im
pr
ove
de
te
c
ti
on.
B
y
id
e
nt
if
yi
ng
c
om
m
on
pa
tt
e
r
ns
a
nd
unr
e
s
ol
ve
d
que
s
ti
ons
,
th
e
a
ut
hor
s
pa
ve
th
e
w
a
y
f
or
f
ur
th
e
r
a
na
ly
s
is
a
nd
te
s
ti
ng,
a
dv
a
nc
in
g
our
unde
r
s
ta
ndi
ng
of
m
a
c
hi
ne
le
a
r
ni
ng
-
ba
s
e
d
pl
a
gi
a
r
is
m
de
te
c
ti
on s
ys
te
m
s
.
N
e
nnur
i
e
t
al
.
[
16]
a
im
s
to
a
ddr
e
s
s
th
e
gr
ow
in
g
c
on
c
e
r
n
of
pl
a
g
ia
r
is
m
us
in
g
da
ta
m
in
in
g
te
c
hni
que
s
.
T
he
a
ut
hor
s
pr
e
s
e
nt
a
c
om
pr
e
he
n
s
iv
e
li
te
r
a
tu
r
e
s
ur
ve
y
e
xpl
or
in
g
r
e
s
e
a
r
c
h
in
pl
a
gi
a
r
is
m
de
te
c
ti
on
a
nd
da
ta
m
in
in
g.
T
he
y
li
ke
ly
c
ove
r
va
r
io
us
a
ppr
oa
c
he
s
,
m
e
th
odol
ogi
e
s
,
a
nd
a
lg
o
r
it
hm
s
us
e
d
to
c
om
ba
t
pl
a
gi
a
r
is
m
in
a
c
a
de
m
ic
a
nd
te
xt
ua
l
c
ont
e
nt
.
T
h
e
s
tu
dy
m
a
y
di
s
c
u
s
s
s
tr
e
ng
th
s
a
nd
dr
a
w
ba
c
ks
of
di
f
f
e
r
e
nt
da
ta
m
in
in
g
te
c
hni
que
s
in
pl
a
gi
a
r
is
m
d
e
te
c
ti
on,
in
c
lu
di
ng
te
xt
ua
l
s
im
il
a
r
it
y
a
na
ly
s
is
a
nd
m
a
c
hi
n
e
le
a
r
ni
ng.
C
ha
ll
e
nge
s
s
uc
h
a
s
m
a
na
gi
ng
pa
r
a
phr
a
s
e
d
c
ont
e
nt
a
nd
e
va
di
ng
de
te
c
ti
on
s
ys
te
m
s
m
a
y
be
hi
ghl
ig
ht
e
d.
T
he
s
ur
ve
y
li
ke
ly
s
how
c
a
s
e
s
th
e
e
vol
vi
ng
la
nd
s
c
a
pe
of
d
a
ta
m
in
in
g
te
c
hnol
ogi
e
s
f
or
pl
a
gi
a
r
is
m
de
te
c
ti
on.
S
ubs
e
que
nt
s
e
c
ti
on
s
li
ke
ly
di
s
c
us
s
th
e
de
ve
lo
pm
e
nt
of
a
n
e
f
f
ic
ie
nt
a
nd
r
e
li
a
bl
e
pl
a
gi
a
r
is
m
de
te
c
ti
on
s
ys
te
m
,
bui
ld
in
g
upon
s
ynt
he
s
iz
e
d r
e
s
e
a
r
c
h t
o a
dv
a
nc
e
unde
r
s
t
a
ndi
ng of
c
ut
ti
ng
-
e
dge
m
e
th
ods
.
P
e
tr
id
e
s
e
t
al
.
[
17]
in
ve
s
ti
ga
te
s
t
he
r
e
la
ti
ons
hi
ps
be
twe
e
n t
r
a
it
e
m
ot
io
na
l
in
te
ll
ig
e
nc
e
a
nd t
he
bi
g f
iv
e
pe
r
s
ona
li
ty
tr
a
it
s
in
th
e
N
e
th
e
r
la
nds
.
T
he
a
ut
hor
s
in
ve
s
ti
ga
t
e
h
ow
th
e
bi
g
f
iv
e
pe
r
s
ona
li
ty
tr
a
it
s
r
e
la
te
to
tr
a
it
e
m
ot
io
na
l
in
te
ll
ig
e
nc
e
i
n a
D
ut
c
h
popula
ti
on. T
he
ir
s
tu
dy l
ik
e
ly
r
e
vi
e
w
s
e
xi
s
ti
ng r
e
s
e
a
r
c
h on thi
s
r
e
la
ti
ons
hi
p,
c
ons
id
e
r
in
g
c
ul
tu
r
a
l
in
f
lu
e
nc
e
s
on
e
m
ot
io
na
l
in
te
ll
ig
e
nc
e
a
nd
pe
r
s
ona
li
ty
tr
a
it
s
.
P
e
tr
id
e
s
e
t
al
.
[
17]
w
or
k
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
.
14
, N
o.
3
,
J
une
2025
:
1940
-
1950
1942
a
dva
nc
e
s
our
unde
r
s
ta
ndi
ng
of
in
di
vi
dua
l
di
f
f
e
r
e
nc
e
s
in
pe
r
s
ona
li
ty
a
nd
e
m
ot
io
na
l
in
te
ll
ig
e
nc
e
w
it
hi
n
th
e
N
e
th
e
r
la
nds
.
P
onoma
r
e
va
e
t
al
.
[
18]
pr
e
s
e
nt
s
a
nov
e
l
a
ppr
oa
c
h
f
or
pr
e
di
c
ti
ng
t
he
f
or
m
a
ti
on
pr
e
s
s
ur
e
in
th
e
S
ukha
r
e
v
oi
l
f
ie
ld
r
e
s
e
r
voi
r
in
R
us
s
ia
,
ut
il
iz
in
g
m
ul
ti
pl
e
r
e
gr
e
s
s
io
n
a
na
ly
s
is
.
T
h
e
a
ut
hor
s
de
ve
lo
p a
pr
e
di
c
ti
on
m
ode
l
to
unde
r
s
ta
nd
f
or
m
a
ti
on
pr
e
s
s
ur
e
dyna
m
ic
s
,
c
r
uc
ia
l
f
or
r
e
s
e
r
voi
r
m
a
na
ge
m
e
nt
.
U
s
in
g
m
ul
ti
pl
e
r
e
gr
e
s
s
io
n
a
n
a
ly
s
is
,
th
e
y
c
ons
id
e
r
va
r
io
us
va
r
ia
bl
e
s
to
im
pr
ove
pr
e
di
c
ti
on
a
c
c
ur
a
c
y.
A
ppl
ie
d
to
th
e
S
ukha
r
e
v
oi
l
f
ie
ld
,
th
e
s
tu
dy
a
dva
nc
e
s
knowle
dge
a
nd
of
f
e
r
s
va
lu
a
bl
e
in
s
ig
ht
s
f
or
r
e
s
e
r
v
oi
r
e
ngi
ne
e
r
s
.
T
he
li
te
r
a
tu
r
e
r
e
vi
e
w
e
xpl
o
r
e
s
e
xi
s
ti
ng me
th
ods
a
nd s
e
ts
t
he
c
ont
e
xt
f
or
t
he
a
ut
hor
s
'
i
nnova
ti
ve
a
ppr
oa
c
h.
El
-
R
a
s
hi
dy
e
t
al
.
[
19
]
a
ddr
e
s
s
e
s
th
e
gr
ow
in
g
is
s
ue
of
s
c
ie
nt
if
ic
pl
a
gi
a
r
is
m
us
in
g
a
dva
nc
e
d
s
of
twa
r
e
.
I
t
in
tr
oduc
e
s
a
ne
w
da
ta
ba
s
e
w
it
h
42
f
e
a
tu
r
e
s
f
or
e
a
c
h
s
im
il
a
r
it
y
c
a
s
e
,
c
om
put
e
d
us
in
g
le
xi
c
a
l,
s
ynt
a
c
ti
c
,
a
nd
s
e
m
a
nt
ic
m
e
tr
ic
s
.
T
he
pr
opos
e
d
in
te
ll
ig
e
nt
s
ys
te
m
,
ba
s
e
d
on
lo
ng
s
hor
t
-
te
r
m
m
e
m
or
y
(
L
S
T
M
)
a
r
c
hi
te
c
tu
r
e
,
out
pe
r
f
or
m
s
c
ont
e
m
por
a
r
y
s
ys
te
m
s
in
de
te
c
ti
ng
te
xt
pl
a
gi
a
r
i
s
m
on
be
nc
hm
a
r
k
da
ta
s
e
ts
(
P
A
N
2013
a
nd
P
A
N
2014)
.
T
he
s
y
s
te
m
ut
il
iz
e
s
in
nov
a
ti
ve
m
e
th
ods
,
in
c
lu
di
ng
3
D
im
a
ge
a
nd
s
ig
n
a
l
c
onve
r
s
io
n,
pr
e
pr
oc
e
s
s
in
g,
a
nd
de
e
p
le
a
r
ni
ng
c
la
s
s
if
ic
a
ti
on,
s
how
c
a
s
in
g
s
upe
r
io
r
a
c
c
ur
a
c
y
in
na
vi
ga
ti
ng
le
xi
c
a
l,
s
ynt
a
c
ti
c
,
a
nd
s
e
m
a
nt
ic
f
lu
c
tu
a
ti
ons
in
s
us
pi
c
io
u
s
c
a
s
e
s
.
O
ve
r
a
ll
,
th
e
f
in
di
ngs
pos
it
io
n
th
e
pr
opos
e
d
s
y
s
te
m
a
s
a
le
a
di
ng
s
ol
ut
io
n
in
te
xt
pl
a
gi
a
r
is
m
de
te
c
ti
on.
M
a
ha
r
a
na
e
t
al
.
[
20]
unde
r
s
c
or
e
s
th
e
c
r
uc
ia
l
r
ol
e
of
da
ta
pr
e
-
pr
oc
e
s
s
in
g
in
m
a
c
hi
ne
le
a
r
ni
ng,
a
ddr
e
s
s
in
g
c
ha
ll
e
nge
s
li
ke
noi
s
e
,
m
is
s
in
g
da
ta
,
a
nd
in
c
on
s
is
t
e
nc
y.
I
t
a
dvoc
a
te
s
f
or
va
r
io
us
pr
e
-
pr
oc
e
s
s
in
g
te
c
hni
que
s
,
e
m
pha
s
i
z
in
g
th
e
im
por
ta
nc
e
of
c
le
a
ni
ng,
in
te
gr
a
ti
on,
a
nd
tr
a
ns
f
or
m
a
ti
on
to
e
xt
r
a
c
t
m
e
a
ni
ngf
ul
in
f
or
m
a
ti
on. T
he
pa
pe
r
i
nt
r
oduc
e
s
d
a
ta
a
ugm
e
nt
a
ti
on t
o ha
ndl
e
m
is
s
in
g da
ta
a
nd e
nha
n
c
e
m
ode
l
p
e
r
f
or
m
a
nc
e
.
K
e
y
poi
nt
s
in
c
lu
de
di
s
c
us
s
io
ns
on
im
a
ge
d
a
ta
a
ugm
e
nt
a
ti
on
te
c
hni
que
s
to
m
it
ig
a
te
ove
r
f
it
ti
ng,
e
s
s
e
nt
ia
l
da
ta
pr
e
-
pr
oc
e
s
s
in
g
s
te
ps
,
a
nd
c
ha
ll
e
nge
s
in
a
ut
om
a
ti
ng
da
ta
pr
e
tr
e
a
tm
e
nt
.
G
ui
de
li
ne
s
f
or
bui
ld
in
g
m
ode
ls
s
tr
e
s
s
th
e
im
por
ta
nc
e
of
w
or
ki
ng
w
it
h
c
or
r
e
c
t
d
a
ta
,
unde
r
s
t
a
ndi
ng
f
e
a
tu
r
e
s
,
a
nd
c
he
c
ki
ng
di
s
tr
ib
ut
io
n.
O
ve
r
a
ll
,
th
e
f
in
di
ngs
pr
ovi
de
va
lu
a
bl
e
in
s
ig
ht
s
f
or
p
r
a
c
ti
ti
on
e
r
s
s
e
e
ki
ng
to
opt
im
iz
e
m
a
c
hi
ne
le
a
r
ni
ng
m
ode
ls
th
r
ough
e
f
f
e
c
ti
ve
da
ta
pr
e
-
pr
oc
e
s
s
in
g a
nd
a
ugm
e
nt
a
ti
on s
tr
a
te
gi
e
s
.
B
ohr
a
a
nd
B
a
r
w
a
r
[
21]
e
xpl
or
e
s
th
e
im
pa
c
t
of
de
e
p
le
a
r
ni
ng
o
n
na
tu
r
a
l
la
ngua
ge
pr
oc
e
s
s
in
g
(
N
L
P
)
a
nd
f
oc
us
e
s
on
a
ut
hor
s
hi
p
a
tt
r
ib
ut
io
n
a
nd
pl
a
gi
a
r
is
m
de
te
c
ti
on.
I
t
in
tr
oduc
e
s
a
f
r
a
m
e
w
or
k
in
vol
vi
ng
two
la
ye
r
s
of
pr
oc
e
s
s
in
g
f
or
a
ut
hor
s
hi
p
a
tt
r
ib
ut
io
n,
e
m
pha
s
i
z
in
g
th
e
im
por
ta
nc
e
of
obt
a
in
in
g
a
s
im
il
a
r
it
y
s
c
or
e
.
T
h
e
pr
opos
e
d
pl
a
gi
a
r
is
m
de
te
c
ti
on
a
lg
or
it
hm
e
m
pl
oys
e
xpl
ic
it
s
e
m
a
nt
ic
de
te
c
ti
on
a
nd
c
ont
e
xt
ua
li
z
e
d
w
or
d
e
m
be
ddi
ngs
f
r
om
a
B
E
R
T
pr
e
-
tr
a
in
e
d
m
ode
l.
E
xpe
r
im
e
nt
s
c
on
duc
te
d
us
in
g
P
yt
hon
a
nd
th
e
K
e
r
a
s
f
r
a
m
e
w
or
k
de
m
ons
tr
a
te
in
c
r
e
a
s
e
d
e
f
f
ic
ie
nc
y
c
om
pa
r
e
d
to
e
xi
s
ti
ng
s
ys
te
m
s
,
s
how
c
a
s
in
g
th
e
a
lg
or
it
hm
'
s
im
pr
ove
d
a
c
c
ur
a
c
y
in
i
de
nt
if
yi
ng pla
gi
a
r
is
m
i
n N
L
P
t
a
s
k.
S
in
gh
a
nd
G
upt
a
[
22]
di
s
c
us
s
e
s
va
r
io
us
e
xt
r
in
s
ic
pl
a
gi
a
r
is
m
de
te
c
ti
on
te
c
hni
que
s
,
in
c
lu
di
ng
li
ngui
s
ti
c
,
s
e
m
a
nt
ic
, a
nd c
ont
e
xt
ua
l
a
ppr
oa
c
he
s
, a
s
w
e
ll
a
s
m
a
c
hi
ne
l
e
a
r
ni
ng a
nd de
e
p l
e
a
r
ni
ng me
th
ods
. T
he
t
e
c
hni
que
s
w
e
r
e
im
pl
e
m
e
nt
e
d
on
di
ve
r
s
e
da
ta
s
e
ts
,
a
nd
th
e
ir
e
f
f
e
c
ti
ve
ne
s
s
w
a
s
c
om
pa
r
e
d
us
in
g
s
ta
nda
r
d
m
e
a
s
ur
e
s
li
ke
pr
e
c
is
io
n,
r
e
c
a
ll
,
F
1
S
c
or
e
,
P
la
gD
e
t,
a
nd
gr
a
nul
a
r
it
y
.
T
he
s
tu
dy
a
ls
o
pr
ovi
de
s
a
di
s
c
us
s
io
n
on
th
e
pr
os
a
nd
c
on
s
of
e
a
c
h pl
a
gi
a
r
is
m
de
te
c
ti
on t
e
c
hni
que
, of
f
e
r
in
g i
ns
ig
ht
s
i
nt
o t
h
e
ir
s
tr
e
ngt
hs
a
nd l
im
it
a
ti
ons
.
2.
M
E
T
H
O
D
T
hi
s
m
a
nus
c
r
ip
t
in
tr
oduc
e
s
a
m
e
th
odol
ogy
f
or
de
te
c
ti
ng
pl
a
gi
a
r
i
s
m
in
te
c
hni
c
a
l
r
e
s
e
a
r
c
h
pa
pe
r
s
u
s
in
g
th
e
bi
g
f
iv
e
pe
r
s
ona
li
ty
tr
a
it
s
(
O
C
E
A
N
)
.
T
he
da
ta
s
e
t
f
or
th
is
s
tu
dy
w
a
s
a
s
s
e
m
bl
e
d
by
ga
th
e
r
in
g
67
te
c
hni
c
a
l
pa
pe
r
s
th
r
ough
U
R
K
U
N
D
,
a
w
id
e
ly
a
dopt
e
d
pl
a
gi
a
r
is
m
de
te
c
ti
on
s
of
twa
r
e
known
f
or
it
s
s
im
il
a
r
it
y
m
e
a
s
ur
e
m
e
nt
.
U
R
K
U
N
D
is
e
xt
e
ns
iv
e
ly
ut
il
iz
e
d
by
a
c
a
de
m
ic
s
to
id
e
nt
if
y
pl
a
gi
a
r
is
m
e
f
f
e
c
ti
ve
ly
[
23]
.
T
o
e
xt
r
a
c
t
th
e
bi
g
f
iv
e
pe
r
s
ona
li
ty
f
a
c
to
r
s
f
r
om
te
c
hni
c
a
l
pa
pe
r
s
,
w
e
e
m
pl
oye
d
th
e
I
B
M
W
a
t
s
on
pe
r
s
ona
li
ty
in
s
ig
ht
s
a
ppl
ic
a
ti
on
pr
ogr
a
m
m
in
g
in
te
r
f
a
c
e
(
A
P
I
)
[
24]
,
[
25]
,
a
w
e
ll
-
r
e
ga
r
de
d
to
ol
in
th
e
in
dus
tr
y
known
f
or
de
li
ve
r
in
g
pr
om
is
in
g r
e
s
ul
ts
i
n pe
r
s
ona
li
ty
a
na
ly
s
i
s
.
F
r
om
th
e
I
B
M
W
a
ts
on
A
P
I
,
w
e
c
ol
le
c
te
d
21
f
e
a
tu
r
e
s
,
c
om
pl
e
m
e
nt
e
d
by
two
a
ddi
ti
ona
l
f
e
a
tu
r
e
s
-
w
or
ds
a
nd
pl
a
gi
a
r
is
m
pe
r
c
e
nt
a
ge
-
e
xt
r
a
c
te
d
f
r
om
U
R
K
U
N
D
s
of
twa
r
e
.
T
he
da
ta
s
e
t
s
w
e
r
e
th
e
n
m
e
r
ge
d,
r
e
s
ul
ti
ng
in
a
c
om
pr
e
he
ns
iv
e
da
t
a
s
e
t
c
om
pr
is
in
g
67
in
s
t
a
nc
e
s
:
40
c
la
s
s
if
ie
d
a
s
pl
a
gi
a
r
iz
e
d
a
nd
27
a
s
unpl
a
gi
a
r
iz
e
d.
T
he
pr
opos
e
d s
ys
te
m
i
nvol
ve
s
t
w
o ke
y s
t
e
ps
:
da
ta
pr
e
pr
oc
e
s
s
in
g a
n
d m
ode
l
bui
l
di
ng, a
s
i
ll
us
tr
a
te
d i
n F
ig
ur
e
1.
2.1. Dat
a p
r
e
p
r
oc
e
s
s
in
g
D
a
ta
pr
e
pr
oc
e
s
s
in
g
on
te
xt
do
c
um
e
nt
s
is
e
s
s
e
nt
ia
l
f
or
c
le
a
ni
ng
a
nd
tr
a
ns
f
or
m
in
g
r
a
w
te
xt
da
ta
in
to
a
s
ui
ta
bl
e
f
or
m
a
t
f
or
a
na
ly
s
is
a
nd
m
ode
l
tr
a
in
in
g.
I
t
he
lp
s
im
p
r
ove
th
e
qua
li
ty
of
th
e
da
t
a
,
e
nha
n
c
e
s
m
ode
l
pe
r
f
or
m
a
nc
e
,
a
nd
e
n
s
ur
e
s
th
a
t
th
e
r
e
s
ul
ti
ng
in
s
ig
ht
s
a
r
e
m
e
a
ni
ngf
ul
a
nd
a
c
c
ur
a
te
.
D
a
ta
c
le
a
ni
ng
in
vol
ve
s
a
ddr
e
s
s
in
g
c
om
m
on
i
s
s
ue
s
s
uc
h
a
s
m
is
s
in
g
va
lu
e
s
,
out
li
e
r
s
,
a
nd
unw
a
nt
e
d
a
tt
r
ib
ut
e
s
.
T
e
c
hni
que
s
li
ke
im
put
a
ti
on (
f
il
l
in
g i
n m
is
s
in
g da
ta
)
, out
li
e
r
de
te
c
ti
on (
id
e
nt
if
y
in
g a
nd r
e
m
ovi
ng e
xt
r
e
m
e
va
lu
e
s
)
, a
nd a
tt
r
ib
ut
e
r
e
m
ova
l
(
r
e
m
ovi
ng i
r
r
e
le
va
nt
or
r
e
dunda
nt
f
e
a
tu
r
e
s
)
a
r
e
e
s
s
e
nt
i
a
l
f
or
e
ns
ur
in
g da
ta
qua
li
ty
.
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
nhanc
in
g pl
agi
ar
is
m
de
te
c
ti
on us
in
g data pr
e
-
pr
oc
e
s
s
in
g and
m
ac
hi
ne
l
e
ar
ni
ng
…
(
V
r
us
hal
i
B
huy
a
r
)
1943
F
ig
ur
e
1. F
r
a
m
e
w
or
k f
or
p
la
gi
a
r
is
m
de
te
c
ti
on s
ys
te
m
us
in
g d
a
ta
pr
e
-
pr
oc
e
s
s
in
g a
nd ma
c
hi
n
e
l
e
a
r
ni
ng
2.1.1. M
is
s
in
g valu
e
i
m
p
u
t
at
io
n
T
h
e
m
is
s
in
g
va
lu
e
s
a
r
e
i
ndi
c
a
t
e
d f
or
e
a
c
h f
e
a
t
ur
e
, w
it
h
va
r
yi
ng d
e
gr
e
e
s
of
m
i
s
s
i
ng d
a
t
a
.
T
o a
ddr
e
s
s
t
h
e
m
is
s
in
g va
lu
e
s
,
t
he
f
r
a
m
e
w
or
k
e
m
pl
oy
s
t
h
e
m
e
di
a
n i
m
p
ut
a
ti
on me
t
hod
,
w
hi
c
h
r
e
p
la
c
e
s
th
e
m
is
s
in
g va
lu
e
s
w
it
h
th
e
m
e
di
a
n
v
a
l
ue
of
th
e
r
e
s
pe
c
ti
ve
f
e
a
tu
r
e
.
T
hi
s
e
ns
ur
e
s
t
ha
t
t
he
d
a
t
a
s
e
t
i
s
c
o
m
pl
e
t
e
a
nd
r
e
a
d
y
f
or
f
ur
th
e
r
a
na
ly
s
i
s
.
2.1.2. F
e
at
u
r
e
s
e
le
c
t
io
n
F
e
a
tu
r
e
s
e
le
c
ti
on i
s
a
c
r
it
ic
a
l
a
s
pe
c
t
of
da
ta
pr
e
pr
oc
e
s
s
in
g t
ha
t
i
m
pr
ove
s
m
ode
l
pe
r
f
or
m
a
nc
e
, r
e
duc
e
s
ove
r
f
it
ti
ng,
e
nha
nc
e
s
in
te
r
pr
e
ta
bi
li
ty
,
a
nd
s
im
pl
if
ie
s
th
e
ove
r
a
ll
a
na
ly
s
is
pr
oc
e
s
s
.
I
t
is
a
n
e
s
s
e
nt
ia
l
s
te
p
to
e
ns
ur
e
th
a
t
th
e
da
ta
us
e
d
f
or
a
na
ly
s
is
is
r
e
le
va
nt
,
c
onc
i
s
e
,
a
nd
c
onduc
iv
e
to
bui
ld
in
g
e
f
f
e
c
ti
ve
a
nd
e
f
f
ic
ie
nt
m
ode
ls
.
D
a
ta
s
e
t
c
ons
i
s
ts
of
two
a
tt
r
ib
ut
e
s
,
"
P
a
pe
r
N
a
m
e
"
a
nd
"
D
oc
_i
d
,"
w
hi
c
h
a
r
e
not
r
e
qui
r
e
d
f
or
th
e
s
ubs
e
que
nt
a
na
ly
s
is
a
nd h
e
nc
e
r
e
m
ove
d.
2.1.3.
O
u
t
li
e
r
d
e
t
e
c
t
io
n
an
d
r
e
p
la
c
e
d
b
y w
i
n
s
or
iz
at
io
n
T
he
ne
xt
s
te
p
in
th
e
f
r
a
m
e
w
or
k
in
vol
ve
s
out
li
e
r
de
te
c
ti
on
us
in
g
boxplot
s
.
A
ny
out
li
e
r
s
id
e
nt
if
ie
d
in
th
e
da
ta
s
e
t
a
r
e
th
e
n
r
e
pl
a
c
e
d
us
in
g
th
e
W
in
s
or
iz
e
r
m
e
th
od.
W
in
s
or
iz
a
ti
on
r
e
pl
a
c
e
s
e
xt
r
e
m
e
va
lu
e
s
w
it
h
th
e
95
th
pe
r
c
e
nt
il
e
f
or
uppe
r
out
li
e
r
s
a
nd
th
e
5
th
pe
r
c
e
nt
il
e
f
or
lo
w
e
r
ou
tl
i
e
r
s
.
B
y
a
ppl
yi
ng
th
is
te
c
hni
que
,
th
e
f
r
a
m
e
w
or
k
e
ns
ur
e
s
t
ha
t
th
e
da
t
a
s
e
t
is
m
or
e
r
obus
t
a
nd r
e
pr
e
s
e
nt
a
ti
ve
of
t
he
da
ta
di
s
tr
ib
ut
io
n.
2.1.4.
S
t
an
d
ar
d
i
z
at
io
n
or
s
c
al
in
g
S
c
a
li
ng
us
in
g
th
e
Z
-
s
c
or
e
,
a
ls
o
known
a
s
s
ta
nda
r
di
z
a
ti
on,
is
a
c
om
m
on
pr
e
pr
oc
e
s
s
in
g
te
c
hni
que
in
m
a
c
hi
ne
l
e
a
r
ni
ng t
o t
r
a
ns
f
or
m
nume
r
ic
a
l
f
e
a
tu
r
e
s
s
o t
ha
t
th
e
y h
a
ve
a
m
e
a
n of
0 a
nd a
s
ta
nda
r
d de
vi
a
ti
on o
f
1
.
T
hi
s
pr
oc
e
s
s
h
e
lp
s
in
m
a
ki
ng
di
f
f
e
r
e
nt
f
e
a
tu
r
e
s
c
om
pa
r
a
bl
e
a
nd
e
ns
ur
e
s
th
a
t
th
e
da
ta
a
dhe
r
e
s
to
a
s
ta
nda
r
d
nor
m
a
l
di
s
tr
ib
ut
io
n
(
m
e
a
n=
0,
s
ta
nda
r
d
de
vi
a
ti
on=
1)
.
T
he
f
or
m
ul
a
f
or
c
a
lc
ul
a
ti
ng
th
e
Z
-
s
c
or
e
f
or
a
pa
r
t
ic
ul
a
r
da
ta
poi
nt
x i
n a
f
e
a
tu
r
e
i
s
gi
ve
n i
n
(
1
)
,
Z
=
(
x
-
µ)
/
σ
(
1)
W
he
r
e
Z
i
s
Z
s
c
or
e
, X
i
s
i
ndi
vi
s
ua
l
da
t
a
poi
nt
, µ i
s
m
e
a
n of
f
e
a
t
ur
e
a
nd σ
i
s
s
ta
nd
a
r
d de
vi
a
ti
on of
t
he
f
e
a
tu
r
e
.
2.1.5. Hi
s
t
ogr
am
an
d
c
or
r
e
la
t
io
n
an
al
ys
is
H
is
to
gr
a
m
s
a
r
e
va
lu
a
bl
e
to
ol
s
f
or
vi
s
ua
li
z
in
g
da
ta
di
s
tr
ib
ut
io
ns
.
B
y
gr
oupi
ng
da
ta
in
to
bi
ns
a
nd
r
e
pr
e
s
e
nt
in
g
th
e
f
r
e
que
nc
y
of
oc
c
ur
r
e
nc
e
s
w
it
hi
n
e
a
c
h
bi
n
a
s
a
ba
r
,
hi
s
to
gr
a
m
s
pr
ovi
de
a
c
le
a
r
vi
s
u
a
l
r
e
pr
e
s
e
nt
a
ti
on
of
th
e
da
ta
'
s
s
pr
e
a
d
a
nd
s
ha
pe
.
T
hi
s
vi
s
ua
l
r
e
pr
e
s
e
nt
a
ti
on
a
ll
ow
s
f
or
e
a
s
y
id
e
nt
if
ic
a
ti
on
of
ke
y
c
ha
r
a
c
te
r
is
ti
c
s
s
uc
h a
s
s
ke
w
n
e
s
s
, m
oda
li
ty
(
num
be
r
of
pe
a
ks
)
, a
nd t
he
pr
e
s
e
nc
e
of
out
li
e
r
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
.
14
, N
o.
3
,
J
une
2025
:
1940
-
1950
1944
H
e
a
tm
a
ps
a
r
e
a
pow
e
r
f
ul
vi
s
u
a
li
z
a
ti
on t
e
c
hni
qu
e
f
or
e
xpl
or
in
g
c
or
r
e
la
ti
ons
be
twe
e
n
f
e
a
tu
r
e
s
w
it
hi
n a
da
ta
s
e
t.
B
y
r
e
pr
e
s
e
nt
in
g
th
e
s
tr
e
ngt
h
of
th
e
r
e
la
ti
ons
hi
p
b
e
tw
e
e
n
va
r
ia
bl
e
s
us
in
g
c
ol
or
gr
a
di
e
nt
s
,
he
a
tm
a
p
s
pr
ovi
de
a
c
onc
is
e
a
nd
in
tu
it
iv
e
vi
s
ua
l
s
um
m
a
r
y
of
th
e
da
t
a
.
T
hi
s
vi
s
ua
l
r
e
pr
e
s
e
nt
a
ti
on
f
a
c
il
it
a
te
s
th
e
id
e
nt
if
ic
a
ti
on
of
pot
e
nt
ia
l
r
e
la
ti
ons
hi
ps
,
de
pe
nd
e
nc
ie
s
,
a
nd
r
e
dun
da
nc
ie
s
a
m
ong
f
e
a
tu
r
e
s
,
w
hi
c
h
c
a
n
be
v
a
lu
a
bl
e
f
or
f
e
a
tu
r
e
s
e
le
c
ti
on, mode
l
bui
ld
in
g, a
nd ove
r
a
ll
da
ta
unde
r
s
ta
ndi
ng.
2.2. M
od
e
l
b
u
il
d
in
g
T
he
f
r
a
m
e
w
or
k
a
ppl
ie
s
r
e
gr
e
s
s
io
n
m
ode
ls
to
th
e
pr
e
pr
oc
e
s
s
e
d
da
ta
s
e
t
f
or
th
e
ta
s
k
of
pl
a
gi
a
r
is
m
de
te
c
ti
on. Va
r
io
us
r
e
gr
e
s
s
io
n m
ode
ls
, i
nc
lu
di
ng
r
a
ndom f
or
e
s
t
r
e
gr
e
s
s
or
, ba
ggi
ng r
e
gr
e
s
s
or
, gr
a
di
e
nt
boos
ti
ng
r
e
gr
e
s
s
or
,
X
G
B
r
e
gr
e
s
s
or
,
a
nd
A
da
B
oo
s
t
r
e
gr
e
s
s
or
,
a
r
e
e
m
p
lo
ye
d
a
nd
e
va
lu
a
te
d
ba
s
e
d
on
th
e
ir
a
dj
us
te
d
R
-
s
qua
r
e
d,
R
-
s
qua
r
e
d,
r
oot
m
e
a
n
s
qua
r
e
d
e
r
r
or
(
R
M
S
E
)
,
a
nd
th
e
ti
m
e
ta
ke
n
f
or
t
r
a
in
in
g.
O
ve
r
a
ll
,
th
e
f
r
a
m
e
w
or
k
s
how
c
a
s
e
s
a
c
om
pr
e
he
ns
iv
e
a
ppr
oa
c
h
to
pl
a
gi
a
r
is
m
de
te
c
ti
on,
s
ta
r
ti
ng
f
r
om
da
ta
pr
e
pr
oc
e
s
s
in
g
a
nd
ha
ndl
in
g
m
is
s
in
g
va
lu
e
s
,
out
li
e
r
s
,
a
nd
da
ta
tr
a
ns
f
or
m
a
ti
on,
to
ut
il
iz
in
g
r
e
gr
e
s
s
io
n
m
ode
ls
f
or
pr
e
di
c
ti
on.
B
y
f
ol
lo
w
in
g
th
is
f
r
a
m
e
w
or
k,
r
e
s
e
a
r
c
he
r
s
a
nd
pr
a
c
ti
ti
one
r
s
c
a
n
e
f
f
e
c
ti
ve
ly
de
te
c
t
in
s
ta
nc
e
s
of
pl
a
gi
a
r
is
m
a
nd
e
nha
nc
e
t
he
i
nt
e
gr
it
y of
a
c
a
de
m
ic
r
e
s
e
a
r
c
h.
R
e
gr
e
s
s
io
n
m
ode
ls
a
nd
s
ophi
s
ti
c
a
te
d
d
a
ta
pr
e
pr
oc
e
s
s
in
g
te
c
hni
que
s
a
r
e
c
om
bi
ne
d
in
a
nove
l
w
a
y
in
our
s
ugge
s
te
d m
e
th
od t
o i
m
pr
ove
pl
a
gi
a
r
is
m
de
te
c
ti
on. Our
a
p
pr
oa
c
h gr
e
a
tl
y r
e
f
in
e
s
t
he
i
nput
da
ta
by us
in
g a
m
ul
ti
di
m
e
ns
io
na
l
da
ta
pr
e
pr
oc
e
s
s
in
g s
tr
a
te
gy
th
a
t
in
c
lu
de
s
f
e
a
t
ur
e
s
e
le
c
ti
on
a
nd
m
is
s
in
g
va
lu
e
im
put
a
ti
on,
in
c
ont
r
a
s
t
to
tr
a
di
ti
ona
l
m
e
th
ods
th
a
t
f
r
e
que
nt
ly
r
e
ly
on
s
im
pl
e
pr
e
pr
oc
e
s
s
in
g
or
lo
w
m
od
e
l
s
ophi
s
ti
c
a
ti
on.
O
ur
m
e
th
od
is
uni
que
be
c
a
us
e
it
c
om
bi
ne
s
c
ut
ti
ng
-
e
dge
r
e
gr
e
s
s
io
n
m
ode
ls
w
it
h
th
is
c
om
pl
e
x
pr
e
pr
oc
e
s
s
in
g.
U
nl
ik
e
pr
e
vi
ous
r
e
s
e
a
r
c
h
th
a
t
m
ig
ht
c
onc
e
nt
r
a
te
on
s
pe
c
if
ic
e
le
m
e
nt
s
or
ne
gl
e
c
t
to
us
e
s
ta
te
-
of
-
th
e
-
a
r
t
pr
e
pr
oc
e
s
s
in
g m
e
th
ods
,
our
m
ode
l
ta
ke
s
a
c
om
pl
e
te
a
ppr
oa
c
h t
o t
he
c
om
pl
e
xi
ti
e
s
of
pl
a
gi
a
r
is
m
de
t
e
c
ti
on. T
h
e
c
om
bi
na
ti
on
of
s
ophi
s
ti
c
a
te
d
r
e
gr
e
s
s
io
n
m
ode
ls
a
nd
c
a
r
e
f
ul
da
ta
pr
e
pa
r
a
ti
on
pr
oduc
e
s
a
s
tr
onge
r
s
ys
te
m
,
w
hi
c
h
is
a
s
ig
ni
f
ic
a
nt
i
m
pr
ove
m
e
nt
ove
r
c
onve
nt
io
na
l
m
e
th
od.
3.
R
E
S
U
L
T
S
A
N
D
D
I
S
C
U
S
S
I
O
N
3.1
.
D
at
as
e
t
c
r
e
at
io
n
I
n
th
is
r
e
s
e
a
r
c
h,
w
e
c
ur
a
te
d
a
d
a
ta
s
e
t
by
ga
th
e
r
in
g
67
te
c
hni
c
a
l
r
e
s
e
a
r
c
h
p
a
pe
r
s
th
r
ough
U
R
K
U
N
D
pl
a
gi
a
r
is
m
de
te
c
ti
on
s
of
twa
r
e
.
U
R
K
U
N
D
,
a
r
e
li
a
bl
e
s
of
twa
r
e
w
id
e
ly
ut
il
iz
e
d
by
m
a
ny
a
c
a
de
m
ic
s
,
w
a
s
in
s
tr
um
e
nt
a
l
in
th
is
da
ta
c
ol
le
c
ti
on.
F
or
f
e
a
tu
r
e
e
xt
r
a
c
ti
on,
we
ut
il
iz
e
d
th
e
I
B
M
W
a
ts
on
pe
r
s
ona
li
ty
in
s
ig
ht
s
A
P
I
,
known
f
or
pr
ovi
di
ng
r
obus
t
r
e
s
ul
ts
a
nd
c
om
m
onl
y
e
m
pl
oye
d
by
in
dus
tr
y
pr
of
e
s
s
io
na
l
s
.
T
h
e
in
it
ia
l
21
f
e
a
tu
r
e
s
w
e
r
e
e
xt
r
a
c
te
d
f
r
om
I
B
M
W
a
ts
on
pe
r
s
ona
li
ty
t
r
a
it
s
(
O
-
ope
nne
s
s
,
C
-
c
on
s
c
ie
nt
io
us
ne
s
s
,
E
-
e
xt
r
a
ve
r
s
io
n
,
A
-
a
gr
e
e
a
bl
e
ne
s
s
,
N
-
ne
ur
ot
ic
is
m
or
e
m
ot
io
na
l
r
a
nge
)
,
w
hi
le
th
e
r
e
m
a
in
in
g
2
f
e
a
tu
r
e
s
w
e
r
e
obt
a
in
e
d
f
r
om
U
R
K
U
N
D
s
of
twa
r
e
,
na
m
e
ly
,
w
o
r
ds
a
nd
pl
a
gi
a
r
is
m
pe
r
c
e
nt
a
ge
.
S
ubs
e
que
nt
ly
,
w
e
m
e
r
ge
d
th
e
s
e
f
e
a
tu
r
e
s
to
c
r
e
a
te
a
da
ta
s
e
t
c
om
pr
is
in
g
23
di
s
ti
nc
t
f
e
a
tu
r
e
s
.
D
e
s
c
r
ip
ti
on
of
pl
a
gi
a
r
is
m
de
te
c
ti
on
da
ta
s
e
t
is
pr
e
s
e
n
te
d i
n
T
a
bl
e
1 a
nd s
ta
ti
s
ti
c
a
l
a
na
ly
s
is
i
s
gi
ve
n i
n
T
a
bl
e
2.
T
a
bl
e
1. D
e
s
c
r
ip
ti
on of
pl
a
gi
a
r
is
m
de
te
c
ti
on da
ta
s
e
t
S
.N
.
F
e
a
t
ur
e
D
e
s
c
r
i
pt
i
on
M
i
s
s
i
ng
v
a
l
ue
1
O
V
a
l
ue
of
ope
nne
s
s
a
s
pe
r
a
ut
hor
0
2
C
V
a
l
ue
of
c
ons
c
i
e
nt
i
ous
ne
s
s
a
s
pe
r
a
ut
hor
0
3
I
/
E
I
nt
r
ove
r
t
/
e
xt
r
ove
r
t
va
l
ue
0
4
E
m
ot
i
ona
l
r
a
nge
E
m
ot
i
ona
l
r
a
nge
a
s
pe
r
a
ut
hor
0
5
A
A
gr
e
e
a
bl
e
ne
s
s
a
s
pe
r
a
ut
hor
0
6
C
ur
i
os
i
t
y
V
a
l
ue
of
c
ur
i
os
i
t
y a
s
pe
r
a
ut
hor
1
7
P
r
a
c
t
i
c
a
l
i
t
y
V
a
l
ue
of
pr
a
c
t
i
c
a
l
i
t
y a
s
pe
r
a
ut
hor
2
8
L
i
be
r
t
y
L
i
be
r
t
y va
l
ue
a
s
pe
r
a
ut
hor
17
9
I
de
a
l
V
a
l
ue
of
i
de
a
l
a
s
pe
r
a
ut
hor
50
10
S
t
r
uc
t
ur
e
V
a
l
ue
of
s
t
r
uc
t
ur
e
a
s
pe
r
a
ut
hor
34
11
C
ha
l
l
e
nge
V
a
l
ue
of
c
ha
l
l
e
nge
a
s
p
e
r
a
ut
hor
38
12
L
ove
V
a
l
ue
of
l
ove
a
s
pe
r
a
ut
hor
46
13
S
e
l
f
e
xpr
e
s
s
i
on
V
a
l
ue
of
s
e
l
f
e
xpr
e
s
s
i
on
42
14
H
a
r
m
ony
V
a
l
ue
of
ha
r
m
ony
66
15
E
xc
i
t
e
m
e
nt
V
a
l
ue
of
e
xc
i
t
e
m
e
nt
49
16
S
t
a
bi
l
i
t
y
V
a
l
ue
of
s
t
a
bi
l
i
t
y
57
17
S
t
i
m
ul
a
t
i
on
V
a
l
ue
of
s
t
i
m
ul
a
t
i
on
0
18
A
c
hi
e
ve
m
e
nt
V
a
l
ue
of
a
c
hi
e
ve
m
e
nt
0
19
H
e
l
pi
ng
ot
he
r
s
V
a
l
ue
of
he
l
pi
ng ot
he
r
s
0
20
T
a
ki
ng
pl
e
a
s
ur
e
i
n l
i
f
e
V
a
l
ue
of
t
a
ki
ng
pl
e
a
s
ur
e
i
n l
i
f
e
0
21
T
r
a
di
t
i
on
V
a
l
ue
of
t
r
a
di
t
i
on
0
22
W
or
ds
V
a
l
ue
of
w
or
ds
0
23
P
l
a
gi
a
r
i
s
m
%
P
l
a
gi
a
r
i
s
m
pe
r
c
e
nt
a
ge
0
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
nhanc
in
g pl
agi
ar
is
m
de
te
c
ti
on us
in
g data pr
e
-
pr
oc
e
s
s
in
g and
m
ac
hi
ne
l
e
ar
ni
ng
…
(
V
r
us
hal
i
B
huy
a
r
)
1945
T
a
bl
e
2. S
ta
ti
s
ti
c
a
l
d
e
s
c
r
ip
ti
on of
da
ta
s
e
t
C
ount
M
e
a
n
S
t
d
M
i
n
25%
50%
O
67.00
97.73
7.83
40.00
98.00
100.00
C
67.00
46.01
14.08
10.00
36.50
46.00
I
_E
67.00
42.30
16.00
7.00
31.00
41.00
E
m
ot
i
ona
l
_r
a
nge
67.00
47.81
28.45
0.00
25.50
49.00
A
67.00
2.03
3.28
0.00
0.00
1.00
P
l
a
gi
a
r
i
s
m
%
67.00
21.22
27.78
0.00
3.00
8.00
3.2. Dat
a p
r
e
p
r
oc
e
s
s
in
g
T
hi
s
r
e
s
e
a
r
c
h
e
xa
m
in
e
d
a
pl
a
gi
a
r
is
m
de
te
c
ti
on
da
t
a
s
e
t,
in
c
or
po
r
a
ti
ng
f
e
a
tu
r
e
s
r
e
la
te
d
to
th
e
a
ut
hor
'
s
c
ha
r
a
c
te
r
is
ti
c
s
,
s
pe
c
if
ic
a
ll
y
th
e
bi
g
f
iv
e
pe
r
s
ona
li
ty
tr
a
it
s
,
a
nd
t
he
pe
r
c
e
nt
a
g
e
of
pl
a
gi
a
r
is
m
.
A
r
ig
or
ous
s
e
t
of
pr
e
pr
oc
e
s
s
in
g s
te
p
s
w
a
s
e
m
pl
oye
d t
o e
ns
ur
e
t
he
da
ta
s
e
t'
s
s
ui
ta
b
il
it
y f
or
s
ubs
e
que
nt
r
e
gr
e
s
s
io
n m
ode
l
tr
a
in
in
g.
T
o
ga
in
in
s
ig
ht
s
in
to
th
e
di
s
tr
ib
ut
io
n
of
th
e
da
ta
,
hi
s
to
gr
a
m
s
w
e
r
e
ge
ne
r
a
te
d,
of
f
e
r
in
g
a
v
is
ua
l
r
e
pr
e
s
e
nt
a
ti
on
of
t
he
s
pr
e
a
d a
nd
f
r
e
que
nc
y of
t
he
f
e
a
tu
r
e
s
.
T
he
vi
s
ua
li
z
a
ti
on t
h
r
ough h
is
to
gr
a
m
s
pr
ovi
de
d a
di
s
ti
nc
t
por
tr
a
ya
l
of
t
he
da
ta
'
s
di
s
pe
r
s
io
n a
nd c
on
c
e
nt
r
a
ti
on. F
ig
ur
e
2 i
ll
us
tr
a
te
s
t
hi
s
t
hr
ough the
de
pi
c
te
d hi
s
to
gr
a
m
.
F
ig
ur
e
2. H
is
to
gr
a
m
f
or
ope
nne
s
s
(
O
)
,
c
ons
c
ie
nt
io
us
ne
s
s
(
c
)
,
e
x
tr
a
ve
r
s
io
n
(
I
_E
)
,
e
m
ot
io
na
l
_
r
a
nge
,
a
gr
e
e
a
bl
e
ne
s
s
(
A
)
,
a
nd
pl
a
gi
a
r
is
m
%
3.2.1. Han
d
li
n
g m
is
s
in
g valu
e
s
T
a
bl
e
1
r
e
ve
a
ls
a
s
ig
ni
f
ic
a
nt
num
be
r
of
m
is
s
in
g
va
lu
e
s
in
t
he
da
ta
s
e
t.
B
ot
h
m
e
a
n
a
nd
m
e
di
a
n
im
put
a
ti
on
w
e
r
e
c
ons
id
e
r
e
d
f
or
f
il
li
ng
th
e
s
e
ga
ps
.
H
ow
e
ve
r
,
m
e
a
n
im
put
a
ti
on
c
a
n
be
in
f
lu
e
nc
e
d
by
out
li
e
r
s
,
le
a
di
ng
to
le
s
s
a
c
c
ur
a
te
r
e
s
ul
ts
.
T
o
m
it
ig
a
te
th
i
s
is
s
ue
,
w
e
c
hos
e
m
e
di
a
n
im
put
a
ti
on,
w
hi
c
h
i
s
le
s
s
s
e
ns
it
iv
e
to
out
li
e
r
s
. T
hi
s
a
ppr
oa
c
h
s
uc
c
e
s
s
f
ul
ly
f
il
le
d a
ll
m
is
s
in
g va
lu
e
s
, c
r
e
a
ti
ng a
c
om
pl
e
te
da
ta
s
e
t
f
or
f
ur
th
e
r
a
na
ly
s
is
.
3.2.2. F
e
at
u
r
e
s
e
le
c
t
io
n
F
e
a
tu
r
e
s
e
le
c
ti
on
is
c
r
uc
ia
l
s
te
p
in
m
a
c
hi
ne
le
a
r
ni
ng
a
nd
da
ta
a
na
ly
s
i
s
in
vol
vi
ng
th
e
pr
oc
e
s
s
of
s
e
le
c
ti
ng
a
s
ub
s
e
t
of
r
e
le
va
nt
f
e
a
tu
r
e
s
f
or
u
s
e
in
m
ode
l
c
on
s
tr
uc
ti
on.
T
he
a
im
i
s
to
im
pr
ove
m
ode
l
pe
r
f
or
m
a
nc
e
,
r
e
duc
e
c
om
put
a
ti
ona
l
c
om
pl
e
xi
ty
,
a
nd
e
nha
n
c
e
in
te
r
pr
e
ta
bi
li
ty
.
U
nne
c
e
s
s
a
r
y
a
tt
r
ib
ut
e
s
,
s
u
c
h
a
s
"
D
oc
_i
d,"
w
e
r
e
e
li
m
in
a
te
d f
r
om
t
he
da
ta
s
e
t,
s
tr
e
a
m
li
ni
ng t
he
a
na
ly
s
i
s
.
3.2.3. Ou
t
li
e
r
d
e
t
e
c
t
io
n
an
d
r
e
p
la
c
e
d
b
y w
i
n
s
or
iz
at
io
n
U
ti
li
z
in
g
a
boxplot
f
o
r
out
li
e
r
de
te
c
ti
on
(
de
pi
c
te
d
in
F
ig
ur
e
3
)
,
w
e
id
e
nt
if
ie
d
out
li
e
r
s
in
th
e
da
ta
.
S
ubs
e
que
nt
ly
,
w
e
a
ppl
ie
d
w
in
s
or
iz
a
ti
on,
a
te
c
hni
que
th
a
t
r
e
pl
a
c
e
d
uppe
r
-
s
id
e
out
li
e
r
s
w
it
h
th
e
95
th
pe
r
c
e
nt
il
e
of
th
e
da
ta
a
nd
lo
w
e
r
-
s
id
e
out
li
e
r
s
w
it
h
th
e
5
th
pe
r
c
e
nt
il
e
of
th
e
da
ta
.
F
ol
lo
w
in
g
th
e
w
in
s
or
iz
a
ti
on
pr
oc
e
s
s
,
a
ll
out
li
e
r
s
w
e
r
e
r
e
pl
a
c
e
d
w
it
h
a
ppr
opr
ia
te
va
lu
e
s
,
a
s
il
lu
s
tr
a
te
d
in
F
ig
ur
e
4.
I
n
bot
h
boxplot
F
ig
ur
e
s
3
a
nd
4,
th
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8938
I
nt
J
A
r
ti
f
I
nt
e
ll
, V
ol
.
14
, N
o.
3
,
J
une
2025
:
1940
-
1950
1946
x
-
a
xi
s
r
e
pr
e
s
e
nt
s
th
e
c
om
bi
na
ti
on
of
pe
r
s
ona
li
ty
t
r
a
it
s
(
O
C
E
A
N
)
a
nd
pl
a
gi
a
r
is
m
pe
r
c
e
nt
a
ge
,
w
hi
le
th
e
y
-
a
xi
s
de
pi
c
ts
t
he
s
c
or
e
s
or
va
lu
e
s
a
s
s
o
c
ia
te
d w
it
h e
a
c
h c
om
bi
na
ti
on.
F
ig
ur
e
3. B
oxpl
ot
w
it
h outl
ie
r
f
o
r
ope
nne
s
s
(
O
)
,
c
ons
c
ie
nt
io
u
s
n
e
s
s
(
c
)
,
e
xt
r
a
ve
r
s
io
n
(
I
_E
)
,
e
m
ot
io
na
l
_r
a
nge
,
a
gr
e
e
a
bl
e
ne
s
s
(
A
)
,
a
nd
pl
a
gi
a
r
is
m
%
F
ig
ur
e
4. B
oxpl
ot
w
it
hout
out
li
e
r
f
o
r
ope
nne
s
s
(
O
)
,
c
ons
c
ie
nt
io
us
ne
s
s
(
c
)
,
e
xt
r
a
ve
r
s
io
n
(
I
_E
)
,
e
m
ot
io
na
l
_r
a
nge
,
a
nd
a
gr
e
e
a
bl
e
ne
s
s
(
A
)
3.2.4. S
t
an
d
ar
d
i
z
at
io
n
or
s
c
al
in
g
B
y
e
m
pl
oyi
ng
Z
-
s
c
or
e
no
r
m
a
li
z
a
ti
on
to
e
ns
ur
e
a
nor
m
a
l
di
s
tr
i
but
io
n
a
nd
s
ta
nda
r
di
z
e
a
ll
a
tt
r
ib
u
te
s
.
T
hi
s
tr
a
ns
f
or
m
a
ti
on
is
e
s
s
e
nt
ia
l
f
or
m
a
ny
m
a
c
hi
ne
le
a
r
ni
ng
a
l
gor
it
hm
s
.
B
y
us
in
g
Z
-
s
c
or
e
nor
m
a
li
z
a
ti
on,
w
e
c
onve
r
te
d
a
ll
va
lu
e
s
f
r
om
a
0
-
100
r
a
nge
to
a
+
1
to
-
1
r
a
nge
.
T
hi
s
s
ta
nda
r
di
z
a
ti
on
he
lp
s
to
pr
e
ve
nt
f
e
a
tu
r
e
s
w
it
h
la
r
ge
r
m
a
gni
tu
de
s
f
r
om
dom
in
a
ti
ng
th
e
le
a
r
ni
ng
pr
oc
e
s
s
.
T
he
s
ta
nda
r
di
z
e
d
va
lu
e
s
r
e
s
ul
ti
ng
f
r
om
th
is
p
r
oc
e
s
s
a
r
e
di
s
pl
a
ye
d i
n T
a
bl
e
3.
V
a
l
ue
s
V
a
l
ue
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
nhanc
in
g pl
agi
ar
is
m
de
te
c
ti
on us
in
g data pr
e
-
pr
oc
e
s
s
in
g and
m
ac
hi
ne
l
e
ar
ni
ng
…
(
V
r
us
hal
i
B
huy
a
r
)
1947
T
a
bl
e
3. A
f
te
r
Z
s
c
or
e
nor
m
a
li
z
a
ti
on
S
r
. N
o.
O
C
I
_E
E
m
ot
i
ona
l
_r
a
nge
A
P
l
a
gi
a
r
i
s
m
0
0.78
-
0.79
0.18
0.82
0.21
5
1
0.78
1.72
0.61
-
0.57
0.21
9
2
0.78
0.21
-
0.07
-
1.35
-
1.10
1
3
0.78
0.36
-
0.20
-
0.53
-
1.10
1
4
0.78
1.00
0.18
1.29
0.79
0
...
...
...
...
...
...
...
62
-
1.17
0.07
1.42
0.97
0.79
99
63
0.78
-
0.72
-
0.01
1.08
-
1.10
8
64
0.78
-
0.15
-
0.64
-
0.76
-
1.10
99
65
0.78
-
1.01
-
0.71
0.94
-
1.10
39
66
-
0.51
-
0.15
-
0.64
-
0.42
-
1.10
18
3.2.5. Cor
r
e
la
t
io
n
an
al
ys
is
A
he
a
tm
a
p
w
a
s
e
m
pl
oye
d
to
r
e
ve
a
l
pot
e
nt
ia
l
c
o
r
r
e
la
ti
ons
be
tw
e
e
n
th
e
bi
g
f
iv
e
pe
r
s
ona
li
ty
tr
a
it
s
a
nd
th
e
pl
a
gi
a
r
is
m
pe
r
c
e
nt
a
ge
.
T
he
a
na
ly
s
is
of
th
e
he
a
tm
a
p
in
di
c
a
t
e
s
th
a
t
no
a
tt
r
ib
ut
e
e
xhi
bi
ts
a
hi
gh
c
or
r
e
la
ti
o
n
w
it
h a
not
he
r
a
tt
r
ib
ut
e
,
a
s
t
he
ir
c
or
r
e
la
ti
on
c
oe
f
f
ic
ie
nt
s
a
r
e
a
ll
be
lo
w
0.50. T
he
r
e
f
or
e
, a
ll
a
tt
r
ib
ut
e
s
a
r
e
r
e
ta
in
e
d
f
or
f
ur
th
e
r
a
na
ly
s
is
. F
ig
ur
e
5 vi
s
ua
ll
y r
e
pr
e
s
e
nt
s
t
he
he
a
tm
a
p us
e
d f
or
c
or
r
e
la
ti
on a
na
ly
s
is
.
F
ig
ur
e
5. H
e
a
tm
a
p f
or
c
or
r
e
la
ti
on a
na
ly
s
is
3.3.
R
e
gr
e
s
s
io
n
m
od
e
ls
e
val
u
at
io
n
F
ol
lo
w
in
g
pr
e
pr
oc
e
s
s
in
g,
va
r
io
us
r
e
gr
e
s
s
io
n
m
od
e
ls
unde
r
w
e
nt
tr
a
in
in
g
a
nd
e
va
lu
a
ti
on
ut
il
iz
in
g
m
ul
ti
pl
e
m
e
tr
ic
s
.
I
n
th
is
s
tu
dy,
w
e
pa
r
ti
ti
one
d
th
e
da
ta
s
e
t
in
to
80
%
f
or
t
r
a
in
in
g
a
nd
20%
f
or
te
s
ti
ng.
L
a
z
ypr
e
di
c
t
te
c
hni
que
s
w
e
r
e
e
m
pl
oye
d
to
id
e
nt
if
y
th
e
to
p
5
r
e
gr
e
s
s
io
n
m
ode
ls
.
T
he
r
e
gr
e
s
s
io
n
m
ode
ls
w
e
r
e
a
ppl
ie
d
to
bot
h
da
ta
s
e
ts
:
one
w
it
hout
pr
e
pr
oc
e
s
s
in
g
a
nd
a
not
he
r
w
it
h
pr
e
pr
oc
e
s
s
in
g.
f
iv
e
r
e
gr
e
s
s
io
n
m
ode
l
us
e
d
w
hi
c
h
w
e
r
e
r
a
ndom
-
f
or
e
s
t
r
e
gr
e
s
s
or
,
ba
ggi
ng r
e
gr
e
s
s
or
,
gr
a
di
e
nt
boos
ti
ng r
e
gr
e
s
s
or
,
X
G
B
r
e
gr
e
s
s
or
,
A
da
boos
t
r
e
gr
e
s
s
io
n
.
E
va
lu
a
ti
on
m
e
tr
ic
s
in
c
lu
de
d
a
dj
us
te
d
R
-
s
qua
r
e
d,
R
-
s
qua
r
e
d,
R
M
S
E
,
a
nd
tr
a
in
in
g
ti
m
e
.
T
he
pe
r
f
or
m
a
nc
e
of
th
e
m
ode
ls
w
a
s
s
c
r
ut
in
iz
e
d
to
a
s
s
e
s
s
th
e
ir
pr
e
di
c
ti
ve
c
a
pa
bi
li
ti
e
s
c
onc
e
r
ni
ng
pl
a
gi
a
r
is
m
pe
r
c
e
nt
a
ge
s
ba
s
e
d
on
a
ut
hor
t
r
a
it
s
. R
e
s
ul
ts
f
r
om
T
a
bl
e
s
4 a
nd 5 indi
c
a
te
i
m
pr
ove
d pe
r
f
or
m
a
nc
e
us
in
g pr
e
pr
oc
e
s
s
in
g t
e
c
hni
que
s
.
T
a
bl
e
4. R
e
gr
e
s
s
io
n
m
ode
l
w
it
hout
pr
e
pr
oc
e
s
s
in
g
M
ode
l
A
dj
us
t
e
d R
-
S
qua
r
e
d
R
-
s
qua
r
e
d
R
M
S
E
T
i
m
e
t
a
ke
n
R
a
ndom
F
or
e
s
t
R
e
gr
e
s
s
or
-
0.41
-
0.06
34.07
0.05
B
a
ggi
ng
R
e
gr
e
s
s
or
-
0.31
0.01
32.90
0.01
G
r
a
di
e
nt
B
oos
t
i
ng
R
e
gr
e
s
s
or
-
0.66
-
0.25
37.00
0.01
XGB
R
e
gr
e
s
s
or
-
0.68
-
0.26
37.25
0.05
A
da
B
oos
t
R
e
gr
e
s
s
or
-
0.36
-
0.02
33.48
0.03
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
.
14
, N
o.
3
,
J
une
2025
:
1940
-
1950
1948
T
a
bl
e
5.
R
e
gr
e
s
s
io
n m
ode
l
w
it
h pr
e
pr
oc
e
s
s
in
g
M
ode
l
A
dj
us
t
e
d R
-
s
qua
r
e
d
R
-
s
qua
r
e
d
R
M
S
E
T
i
m
e
t
a
ke
n
R
a
ndom
f
or
e
s
t
r
e
gr
e
s
s
or
0.76
0.85
9.84
0.13
B
a
ggi
ng
r
e
gr
e
s
s
or
0.72
0.83
10.66
0.03
G
r
a
di
e
nt
boos
t
i
ng r
e
gr
e
s
s
or
0.66
0.79
11.79
0.03
XGB
r
e
gr
e
s
s
or
0.61
0.76
12.53
0.04
A
da
B
oos
t
r
e
gr
e
s
s
or
0.60
0.75
12.79
0.11
T
hi
s
th
or
ough
a
na
ly
s
i
s
yi
e
ld
s
va
lu
a
bl
e
in
s
ig
ht
s
in
to
pr
e
pr
oc
e
s
s
in
g
e
f
f
ic
a
c
y,
da
t
a
s
e
t
di
s
tr
ib
ut
io
n,
c
or
r
e
la
ti
ons
,
a
nd
th
e
r
e
la
ti
ve
pe
r
f
or
m
a
nc
e
of
r
e
gr
e
s
s
io
n
m
ode
ls
.
F
ig
ur
e
6
s
how
s
c
om
pa
r
a
ti
ve
a
na
ly
s
is
of
r
e
gr
e
s
s
io
n m
ode
l
w
it
h
a
nd w
it
hout
pr
e
pr
oc
e
s
s
in
g
on pla
gi
a
r
is
m
de
te
c
ti
on da
ta
s
e
t.
S
uc
h i
n
s
ig
ht
s
a
r
e
c
r
uc
ia
l
f
or
unde
r
s
ta
ndi
ng
th
e
s
e
m
ode
l
s
'
r
e
li
a
bi
li
ty
in
e
s
ti
m
a
ti
ng
pl
a
gi
a
r
is
m
pe
r
c
e
nt
a
ge
s
ba
s
e
d
on
a
ut
hor
c
ha
r
a
c
t
e
r
is
ti
c
s
.
T
he
c
om
bi
na
ti
on of
m
e
ti
c
ul
ou
s
pr
e
pr
oc
e
s
s
in
g a
nd r
ig
or
ous
m
o
de
l
e
va
lu
a
ti
on e
nha
n
c
e
s
t
he
f
in
di
ngs
'
r
e
li
a
bi
li
ty
a
nd a
ppl
ic
a
bi
li
ty
i
n r
e
a
l
-
w
or
ld
c
ont
e
xt
s
.
F
ig
ur
e
6. C
om
pa
r
is
on of
r
e
gr
e
s
s
io
n m
ode
l
w
it
h a
nd w
it
hout
pr
e
pr
oc
e
s
s
in
g
4.
C
O
N
C
L
U
S
I
O
N
T
he
r
e
ha
s
be
e
n
a
w
or
r
yi
ng
r
is
e
in
pl
a
gi
a
r
is
m
w
or
ld
w
id
e
a
s
a
r
e
s
ul
t
of
th
e
r
e
c
e
nt
e
xpl
os
io
n
in
th
e
a
va
il
a
bi
li
ty
of
s
c
hol
a
r
ly
c
ont
e
nt
vi
a
m
ode
r
n
te
c
hnol
ogy
a
nd
th
e
in
te
r
ne
t.
A
s
a
r
e
s
ul
t
of
r
e
s
e
a
r
c
he
r
s
'
pe
r
s
is
te
nt
s
e
a
r
c
h
f
or
w
or
ka
bl
e
s
ol
ut
io
ns
,
m
a
c
hi
ne
le
a
r
ni
n
g
ha
s
be
e
n
in
ve
s
ti
ga
te
d
a
s
a
pot
e
nt
ia
l
pl
a
gi
a
r
is
m
de
te
c
ti
on
m
e
th
od.
T
hi
s
w
or
k
hi
ghl
ig
ht
s
th
e
c
r
uc
ia
l
r
ol
e
th
a
t
da
ta
pr
e
pa
r
a
ti
on
ha
s
in
opt
im
iz
in
g
th
e
c
a
pa
bi
li
ti
e
s
of
m
a
c
hi
ne
le
a
r
ni
ng
a
lg
or
it
hm
s
a
nd
s
ugge
s
t
s
a
uni
que
m
e
th
od
th
a
t
c
om
bi
ne
s
f
e
a
tu
r
e
s
e
l
e
c
ti
on
a
nd
m
is
s
in
g
v
a
lu
e
im
put
a
ti
on
to
im
pr
ove
th
e
de
te
c
ti
on
of
pl
a
gi
a
r
is
m
us
in
g
r
e
gr
e
s
s
io
n
m
ode
l
s
.
O
ur
r
e
s
e
a
r
c
h
is
unus
u
a
l
in
th
a
t
it
bui
ld
s
a
s
tr
ong
a
r
c
hi
te
c
tu
r
e
f
or
a
pl
a
gi
a
r
is
m
d
e
te
c
ti
on
m
ode
l
th
a
t
in
c
lu
de
s
ne
c
e
s
s
a
r
y
s
te
ps
in
c
lu
di
ng
out
li
e
r
de
te
c
ti
on,
nor
m
a
li
z
a
ti
on
m
e
th
ods
,
a
nd
th
or
ough
da
ta
pr
e
tr
e
a
tm
e
nt
.
O
ur
m
e
th
od
a
dds
nove
l
in
s
ig
ht
s
to
th
e
body
of
li
te
r
a
tu
r
e
by
e
xa
m
in
in
g
th
e
jo
in
t
e
f
f
e
c
ts
of
f
e
a
tu
r
e
s
e
le
c
ti
on
a
nd
m
is
s
in
g
va
lu
e
im
put
a
ti
on.
O
ur
s
ugge
s
te
d
m
e
th
odol
ogy
pr
oduc
e
d
r
e
m
a
r
ka
bl
e
r
e
s
ul
ts
a
f
te
r
th
or
ough
t
e
s
ti
ng
on
a
pl
a
gi
a
r
is
m
da
t
a
s
e
t,
w
it
h
R
M
S
E
f
or
s
e
ve
r
a
l
r
e
gr
e
s
s
io
n
m
ode
l
s
of
9.48,
10.66,
11.79,
12.53
a
n
d
12.79.
O
ur
c
ont
r
ib
ut
io
n
i
s
e
s
s
e
nt
ia
ll
y
th
e
de
ve
lo
pm
e
nt
of
a
pl
a
gi
a
r
is
m
de
te
c
ti
on t
e
c
hnol
ogy tha
t
is
i
nc
r
e
di
bl
y e
f
f
ic
ie
nt
c
om
pa
r
e
d t
o c
ur
r
e
nt
a
ppr
oa
c
he
s
.
T
he
to
ta
l
a
c
c
ur
a
c
y
a
nd
pr
oduc
ti
vi
ty
of
our
pl
a
gi
a
r
is
m
d
e
te
c
ti
on
pr
oc
e
s
s
a
r
e
m
a
xi
m
iz
e
d
by
th
e
s
m
oot
h
in
te
gr
a
ti
on
of
c
ut
ti
ng
-
e
dge
m
a
c
hi
ne
le
a
r
ni
ng
te
c
hni
que
s
w
it
h
c
le
ve
r
da
ta
pr
e
pa
r
a
ti
on
s
tr
a
te
gi
e
s
,
s
uc
h
a
s
pr
io
r
it
iz
in
g i
m
por
ta
nt
c
om
pone
nt
s
a
nd
f
il
li
ng
in
in
f
or
m
a
ti
on
ga
ps
.
I
n
c
onc
lu
s
io
n,
our
m
e
th
od
r
a
is
e
s
th
e
ba
r
f
o
r
our
pl
a
gi
a
r
is
m
de
te
c
ti
on t
ool
'
s
pe
r
f
or
m
a
nc
e
, m
uc
h l
ik
e
put
ti
ng t
oge
th
e
r
a
puz
z
le
.
F
U
N
D
I
N
G
I
N
F
O
R
M
A
T
I
O
N
N
o f
undi
ng w
a
s
i
nvol
ve
d.
3
4
.0
7
3
2
.9
37
3
7
.2
5
33.48
9
.8
4
1
0
.6
6
1
1
.7
9
1
2
.5
3
1
2
.7
9
0
5
10
15
20
25
30
35
40
R
a
n
d
o
m
F
o
r
es
t
R
eg
r
es
so
r
B
a
g
g
i
n
g
R
eg
r
es
so
r
G
r
a
d
i
en
t
B
o
o
st
i
n
g
R
eg
r
es
so
r
X
G
B
R
eg
r
e
ss
o
r
A
d
a
B
o
o
st
R
eg
r
es
so
r
R
MS
E
R
e
g
r
e
s
s
i
o
n
M
o
d
e
l
R
MS
E
Wi
t
h
o
u
t
P
r
ep
r
o
c
es
si
n
g
R
M
S
E
W
i
t
h
P
r
ep
r
o
c
es
si
n
g
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
nhanc
in
g pl
agi
ar
is
m
de
te
c
ti
on us
in
g data pr
e
-
pr
oc
e
s
s
in
g and
m
ac
hi
ne
l
e
ar
ni
ng
…
(
V
r
us
hal
i
B
huy
a
r
)
1949
A
U
T
H
O
R
C
O
N
T
R
I
B
U
T
I
O
N
S
S
T
A
T
E
M
E
N
T
T
hi
s
jo
ur
na
l
us
e
s
th
e
C
ont
r
ib
ut
or
R
ol
e
s
T
a
xonomy
(
C
R
e
di
T
)
to
r
e
c
ogni
z
e
in
di
vi
dua
l
a
ut
hor
c
ont
r
ib
ut
io
ns
, r
e
duc
e
a
ut
hor
s
hi
p di
s
put
e
s
,
a
nd f
a
c
il
it
a
te
c
ol
la
bo
r
a
ti
on.
N
am
e
o
f
A
u
t
h
or
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
V
r
us
ha
li
B
huya
r
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
S
a
c
hi
n D
e
s
hm
ukh
✓
✓
✓
✓
✓
✓
✓
C
:
C
onc
e
pt
ua
li
z
a
ti
on
M
:
M
e
th
odol
ogy
So
:
So
f
twa
r
e
Va
:
Va
li
da
ti
on
Fo
:
Fo
r
m
a
l
a
na
ly
s
is
I
:
I
nve
s
ti
ga
ti
on
R
:
R
e
s
our
c
e
s
D
:
D
a
ta
C
ur
a
ti
on
O
:
W
r
it
in
g
-
O
r
ig
in
a
l
D
r
a
f
t
E
:
W
r
it
in
g
-
R
e
vi
e
w
&
E
di
ti
ng
Vi
:
Vi
s
ua
li
z
a
ti
on
Su
:
Su
pe
r
vi
s
io
n
P
:
P
r
oj
e
c
t
a
dm
in
is
tr
a
ti
on
Fu
:
Fu
ndi
ng a
c
qui
s
it
io
n
C
O
N
F
L
I
C
T
O
F
I
N
T
E
R
E
S
T
S
T
A
T
E
M
E
N
T
T
he
a
ut
hor
s
de
c
la
r
e
no c
onf
li
c
t
of
i
nt
e
r
e
s
t
.
I
N
F
O
R
M
E
D
C
O
N
S
E
N
T
W
e
ha
ve
obt
a
in
e
d i
nf
or
m
e
d c
ons
e
nt
f
r
om
a
ll
i
ndi
vi
dua
ls
i
nc
lu
de
d i
n t
hi
s
s
tu
dy.
D
A
T
A
A
V
A
I
L
A
B
I
L
I
T
Y
T
he
da
ta
th
a
t
s
uppor
t
th
e
f
in
di
ngs
of
th
is
s
tu
dy
a
r
e
a
va
il
a
bl
e
f
r
om
th
e
c
or
r
e
s
ponding
a
ut
hor
,
[
VAB
]
,
upon r
e
a
s
ona
bl
e
r
e
que
s
t.
R
E
F
E
R
E
N
C
E
S
[
1]
G
.
H
e
l
ge
s
s
on
a
nd
S
.
E
r
i
ks
s
on,
“
P
l
a
gi
a
r
i
s
m
i
n
r
e
s
e
a
r
c
h,”
M
e
di
c
i
ne
,
H
e
al
t
h
C
ar
e
and
P
hi
l
os
ophy
,
pp.
91
–
101
,
2015
,
doi
:
10.1007/
s
11019
-
014
-
9583
-
8.
[
2]
Q
.
G
u
a
nd
J
.
B
r
ooks
,
“
B
e
yond
t
he
a
c
c
us
a
t
i
on
of
pl
a
gi
a
r
i
s
m
,”
Sy
s
t
e
m
,
vol
.
36,
no.
3,
pp.
337
–
352,
2008,
doi
:
10.1016/
j
.s
ys
t
e
m
.2008.01.004.
[
3]
H
. M
a
ur
e
r
, F
.
K
a
ppe
, a
nd B
.
Z
a
ka
, “
P
l
a
gi
a
r
i
s
m
-
a
s
ur
ve
y,”
J
our
nal
of
U
ni
v
e
r
s
al
C
om
put
e
r
Sc
i
e
nc
e
, vol
. 12, no. 8, pp. 1050
–
1084,
2017
,
doi
:
10.3217/
j
uc
s
-
012
-
08
-
1050
.
[
4]
T
.
F
i
s
hm
a
n,
“
W
e
kno
w
i
t
w
he
n
w
e
s
e
e
i
t
i
s
not
good
e
nough:
t
ow
a
r
d
a
s
t
a
nda
r
d de
f
i
ni
t
i
on
of
pl
a
gi
a
r
i
s
m
t
ha
t
t
r
a
ns
c
e
nd
s
t
he
f
t
,
f
r
a
ud,
a
nd c
opyr
i
ght
,
”
F
our
t
h A
s
i
a P
ac
i
f
i
c
C
onf
e
r
e
nc
e
on E
duc
at
i
onal
I
nt
e
gr
i
t
y
(
4A
P
C
E
I
)
, 2009,
pp. 1
-
5.
[
5]
K
.
V
a
ni
a
nd
D
.
G
upt
a
,
“
S
t
udy
on
e
xt
r
i
ns
i
c
t
e
xt
pl
a
gi
a
r
i
s
m
de
t
e
c
t
i
on
t
e
c
hni
qu
e
s
a
nd
t
ool
s
,”
J
our
nal
of
E
ngi
ne
e
r
i
ng
Sc
i
e
nc
e
and
T
e
c
hnol
ogy
R
e
v
i
e
w
, vol
. 9, no. 5, pp. 9
–
23, 2016, doi
:
10.25103/
j
e
s
t
r
.095.02.
[
6]
F
.
K
ha
l
e
d
a
nd
M
.
S
.
H
.
A
l
-
T
a
m
i
m
i
,
“
P
l
a
gi
a
r
i
s
m
de
t
e
c
t
i
on
m
e
t
hods
a
nd
t
ool
s
:
a
n
ove
r
vi
e
w
,”
I
r
aqi
J
our
nal
of
S
c
i
e
nc
e
,
vol
.
62,
no. 8, pp. 2771
–
2783, 2021, doi
:
10.24996/
i
j
s
.2021.62.8.30.
[
7]
M
.
N
.
M
a
n
s
oor
a
nd
M
.
S
.
H
.
A
l
-
T
a
m
i
m
i
,
“
C
om
put
e
r
-
ba
s
e
d
pl
a
gi
a
r
i
s
m
de
t
e
c
t
i
on
t
e
c
hni
que
s
:
A
c
om
pa
r
a
t
i
ve
s
t
udy,”
I
nt
e
r
nat
i
ona
l
J
our
nal
of
N
onl
i
ne
ar
A
nal
y
s
i
s
and A
ppl
i
c
at
i
ons
, vol
. 13,
no. 1,
pp.
3599
-
3611
, 2022,
doi
:
10.22075/
i
j
na
a
.2022.6140.
[
8]
W
.
A
nw
a
r
,
I
.
S
.
B
a
j
w
a
,
a
nd
S
.
R
a
m
z
a
n,
“
D
e
s
i
gn
a
nd
i
m
pl
e
m
e
nt
a
t
i
on
of
a
m
a
c
hi
ne
l
e
a
r
ni
ng
-
ba
s
e
d
a
ut
hor
s
hi
p
i
de
nt
i
f
i
c
a
t
i
on
m
ode
l
,
”
Sc
i
e
nt
i
f
i
c
P
r
ogr
am
m
i
ng
, vol
. 2019,
no. 1,
2019, doi
:
10.1155/
2019/
9431073.
[
9]
J
.
B
ur
da
c
k,
F
.
H
or
s
t
,
S
.
G
i
e
s
s
e
l
ba
c
h,
I
.
H
a
s
s
a
n,
S
.
D
a
f
f
ne
r
,
a
nd
W
.
I
.
S
c
höl
l
hor
n,
“
S
ys
t
e
m
a
t
i
c
c
om
pa
r
i
s
on
of
t
he
i
nf
l
ue
nc
e
of
di
f
f
e
r
e
nt
da
t
a
pr
e
pr
oc
e
s
s
i
ng
m
e
t
hods
on
t
he
pe
r
f
or
m
a
nc
e
of
ga
i
t
c
l
a
s
s
i
f
i
c
a
t
i
ons
us
i
ng
m
a
c
hi
ne
l
e
a
r
ni
ng,”
F
r
ont
i
e
r
s
i
n
B
i
oe
ngi
ne
e
r
i
ng and B
i
ot
e
c
hnol
ogy
, vol
. 8, 2020, doi
:
10.3389/
f
bi
oe
.2020.0026
0.
[
10]
M
. M
.
Z
a
hi
d, K
.
A
bi
d, A
.
R
e
hm
a
n,
M
.
F
uz
a
i
l
, a
nd
N
.
A
s
l
a
m
,
“
A
n
e
f
f
i
c
i
e
nt
m
a
c
hi
ne
l
e
a
r
ni
ng a
ppr
oa
c
h
f
or
pl
a
gi
a
r
i
s
m
de
t
e
c
t
i
on i
n
t
e
xt
doc
um
e
nt
s
,”
J
our
nal
of
C
om
put
i
ng &
B
i
om
e
di
c
al
I
nf
or
m
at
i
c
s
, vol
. 4, no. 2
, pp. 241
–
248, 2023.
[
11]
T
.
F
ol
t
ýne
k,
N
.
M
e
us
c
hke
,
a
nd
B
.
G
i
pp,
“
A
c
a
de
m
i
c
pl
a
gi
a
r
i
s
m
de
t
e
c
t
i
on:
a
s
ys
t
e
m
a
t
i
c
l
i
t
e
r
a
t
ur
e
r
e
vi
e
w
,”
A
C
M
C
om
put
i
ng
Sur
v
e
y
s
,
vol
. 52, no. 6,
pp. 1
-
42,
2019, doi
:
10.1145/
3345317.
[
12]
C
. C
. O
l
i
s
a
h, L
. S
m
i
t
h, a
nd M
. S
m
i
t
h, “
D
i
a
be
t
e
s
m
e
l
l
i
t
us
pr
e
di
c
t
i
on a
nd di
a
gnos
i
s
f
r
om
a
da
t
a
pr
e
pr
oc
e
s
s
i
ng a
nd m
a
c
hi
ne
l
e
a
r
n
i
n
g
pe
r
s
pe
c
t
i
ve
,”
C
om
put
e
r
M
e
t
hods
and P
r
og
r
am
s
i
n B
i
om
e
di
c
i
ne
, vol
. 220,
pp. 1
-
12,
2022, doi
:
10.1016/
j
.c
m
pb.2022.106773.
[
13]
M
.
A
.
E
l
-
R
a
s
hi
dy,
R
.
G
.
M
oha
m
e
d,
N
.
A
.
E
l
-
F
i
s
ha
w
y,
a
nd
M
.
A
.
S
houm
a
n,
“
A
n
e
f
f
e
c
t
i
ve
t
e
xt
pl
a
gi
a
r
i
s
m
de
t
e
c
t
i
on
s
ys
t
e
m
ba
s
e
d
on
f
e
a
t
ur
e
s
e
l
e
c
t
i
on
a
nd
S
V
M
t
e
c
hni
que
s
,
”
M
ul
t
i
m
e
di
a
T
ool
s
and
A
ppl
i
c
at
i
ons
,
vol
.
83,
no.
1,
pp.
2609
–
2646,
2024,
doi
:
10.1007/
s
11042
-
023
-
15703
-
4.
[
14]
V
.
W
.
D
.
V
a
r
ga
s
,
J
.
A
.
S
.
A
r
a
nda
,
R
.
D.
S
.
C
os
t
a
,
P
.
R
.
S
.
P
e
r
e
i
r
a
,
a
nd
J
. L
.
V
.
B
a
r
bos
a
,
“
I
m
ba
l
a
nc
e
d
da
t
a
pr
e
pr
oc
e
s
s
i
ng
t
e
c
hni
que
s
f
or
m
a
c
hi
ne
l
e
a
r
ni
ng:
a
s
y
s
t
e
m
a
t
i
c
m
a
ppi
ng
s
t
udy,”
K
now
l
e
dge
and
I
nf
or
m
at
i
on
Sy
s
t
e
m
s
,
vol
.
65,
no.
1,
pp.
31
–
57,
2023,
doi
:
10.1007/
s
10115
-
022
-
01772
-
8.
[
15]
Z
.
F
.
A
l
f
i
kr
i
a
nd
A
.
P
ur
w
a
r
i
a
nt
i
,
“
D
e
t
a
i
l
e
d
a
na
l
ys
i
s
of
e
xt
r
i
ns
i
c
pl
a
gi
a
r
i
s
m
de
t
e
c
t
i
on
s
ys
t
e
m
us
i
ng
m
a
c
hi
ne
l
e
a
r
ni
ng
a
ppr
oa
c
h
(
na
i
ve
B
a
ye
s
a
nd
S
V
M
)
,”
T
E
L
K
O
M
N
I
K
A
I
ndone
s
i
an
J
our
nal
of
E
l
e
c
t
r
i
c
al
E
ngi
ne
e
r
i
ng
,
vol
.
12,
no.
11,
2014,
doi
:
10.11591/
t
e
l
kom
ni
ka
.v12i
11.6652.
[
16]
R
.
N
e
nnur
i
,
M
.
G
.
Y
a
da
v,
M
.
S
a
m
hi
t
ha
,
S
.
S
.
K
um
a
r
,
a
nd
G
.
R
o
s
hi
ni
,
“
P
l
a
g
i
a
r
i
s
m
de
t
e
c
t
i
on
t
hr
ough
da
t
a
m
i
ni
ng
t
e
c
hni
que
s
,”
J
our
nal
of
P
hy
s
i
c
s
:
C
onf
e
r
e
nc
e
S
e
r
i
e
s
, vol
. 1979, no. 1, 2021, doi
:
10.1088/
1742
-
6596/
1979/
1/
012070.
[
17]
K
.
V
.
P
e
t
r
i
de
s
,
P
.
A
.
V
e
r
non,
J
.
A
.
S
c
he
r
m
e
r
,
L
.
L
i
gt
ha
r
t
,
D
.
I
.
B
oom
s
m
a
,
a
nd L
.
V
e
s
e
l
ka
,
“
R
e
l
a
t
i
ons
hi
ps
be
t
w
e
e
n
t
r
a
i
t
e
m
ot
i
o
na
l
i
nt
e
l
l
i
ge
nc
e
a
nd
t
he
bi
g
f
i
ve
i
n
t
he
N
e
t
he
r
l
a
nds
,”
P
e
r
s
onal
i
t
y
and
I
ndi
v
i
dual
D
i
f
f
e
r
e
nc
e
s
,
vol
.
48,
no.
8,
pp.
906
–
910,
2010,
doi
:
10.1016/
j
.pa
i
d.2010.02.019.
Evaluation Warning : The document was created with Spire.PDF for Python.