Co
m
pu
t
er
Science
a
nd
I
nfo
r
m
a
t
io
n T
ec
hn
o
lo
g
ies
Vo
l.
6
,
No
.
2
,
J
u
ly
20
25
,
p
p
.
1
4
7
~
1
5
8
I
SS
N:
2722
-
3
2
2
1
,
DOI
:
1
0
.
1
1
5
9
1
/csi
t
.
v6
i
2
.
p
p
1
4
7
-
1
5
8
147
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
p
r
ime.
co
m/in
d
ex
.
p
h
p
/csi
t
Cla
ss
ificatio
n and
sim
ila
rity de
tect
i
o
n of Indo
nesia
n
scientifi
c
journa
l articles
Ny
im
a
s
Sa
bil
ina
Ca
hy
a
ni
1
,
Der
is
Stia
wa
n
2
,
Abd
ia
ns
a
h
Abdi
a
ns
a
h
1
,
Nurul Af
if
a
h
3
,
Dendi Re
na
l
do
P
er
m
a
na
1
1
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
U
n
i
v
e
r
s
i
t
y
o
f
S
r
i
w
i
j
a
y
a
,
P
a
l
e
m
b
a
n
g
,
I
n
d
o
n
e
s
i
a
2
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
En
g
i
n
e
e
r
i
n
g
,
U
n
i
v
e
r
s
i
t
y
o
f
S
r
i
w
i
j
a
y
a
,
P
a
l
e
m
b
a
n
g
,
I
n
d
o
n
e
si
a
3
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
mat
i
c
s
E
n
g
i
n
e
e
r
i
n
g
,
U
n
i
v
e
r
si
t
y
o
f
S
r
i
w
i
j
a
y
a
,
P
a
l
e
m
b
a
n
g
,
I
n
d
o
n
e
s
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Feb
20
,
2
0
2
5
R
ev
is
ed
Mar
24
,
2
0
2
5
Acc
ep
ted
May
23
,
2
0
2
5
Th
e
d
e
v
e
lo
p
m
e
n
t
o
f
tec
h
n
o
lo
g
y
is
a
c
c
e
lera
ti
n
g
in
fi
n
d
i
n
g
re
fe
re
n
c
e
s
to
sc
ien
ti
fic
a
rti
c
les
o
r
j
o
u
r
n
a
ls
re
lat
e
d
t
o
re
se
a
rc
h
t
o
p
ics
.
On
e
o
f
th
e
so
u
rc
e
s
o
f
n
a
ti
o
n
a
l
a
g
g
re
g
a
to
r
se
r
v
ice
s
to
fin
d
re
fe
re
n
c
e
s
is
G
a
rb
a
Ru
ju
k
a
n
Dig
it
a
l
(G
AR
UD
A),
d
e
v
e
lo
p
e
d
b
y
th
e
M
in
istr
y
o
f
Ed
u
c
a
ti
o
n
,
Cu
lt
u
re
,
Re
se
a
rc
h
,
a
n
d
Tec
h
n
o
l
o
g
y
(
Ke
m
e
n
d
i
k
b
u
d
r
istek
)
o
f
th
e
Re
p
u
b
li
c
o
f
I
n
d
o
n
e
sia
.
Th
e
n
a
ïv
e
Ba
y
e
s
m
e
th
o
d
c
las
sifies
a
rti
c
les
in
to
se
v
e
ra
l
c
a
teg
o
ries
b
a
se
d
o
n
ti
tl
e
s
a
n
d
a
b
stra
c
ts
.
Th
e
sy
ste
m
a
c
h
iev
e
s a
n
F
1
-
sc
o
re
o
f
9
8
%
,
wh
ich
in
d
i
c
a
tes
h
ig
h
c
las
sifica
ti
o
n
a
c
c
u
ra
c
y
,
a
n
d
th
e
c
las
sifica
ti
o
n
p
ro
c
e
ss
tak
e
s
les
s
th
a
n
6
0
m
i
n
u
tes
.
Article
sim
il
a
rit
y
d
e
tec
ti
o
n
is
d
o
n
e
u
s
in
g
th
e
c
o
si
n
e
sim
il
a
rit
y
m
e
th
o
d
,
a
n
d
a
sim
il
a
rit
y
sc
o
re
o
f
0
.
0
7
1
re
flec
ts
th
e
d
e
g
re
e
o
f
sim
il
a
rit
y
b
e
twe
e
n
th
e
ti
tl
e
a
n
d
th
e
a
b
stra
c
t
th
a
t
h
a
s
b
e
e
n
c
o
n
c
a
ten
a
ted
,
wh
i
le
a
sc
o
re
c
lo
se
to
1
in
d
ica
tes
a
h
ig
h
e
r
sim
il
a
rit
y
.
S
e
a
rc
h
i
n
g
f
o
r
sim
il
a
r
sc
ien
ti
fic
a
rti
c
les
b
a
se
d
o
n
ti
tl
e
a
n
d
a
b
stra
c
t,
so
rt
a
rti
c
les
b
a
se
d
o
n
th
e
re
s
u
lt
s
o
f
th
e
h
ig
h
e
st
sim
il
a
rit
y
sc
o
re
a
re
th
e
m
o
st
sim
il
a
r
a
rti
c
les
,
a
n
d
g
e
n
e
ra
ti
n
g
a
rti
c
le
c
a
teg
o
ries
.
Th
e
re
su
lt
s
o
f
th
e
r
e
se
a
rc
h
sh
o
w
th
a
t
t
h
e
p
r
o
p
o
se
d
m
e
th
o
d
sig
n
ifi
c
a
n
t
ly
im
p
ro
v
e
s
th
e
c
las
sifica
ti
o
n
a
n
d
se
a
rc
h
p
r
o
c
e
ss
e
s
in
G
ARU
DA
,
a
s we
ll
a
s a
c
c
u
ra
te an
d
e
fficie
n
t
sim
il
a
rit
y
d
e
tec
ti
o
n
.
K
ey
w
o
r
d
s
:
C
las
s
if
icatio
n
C
o
s
in
e
s
im
ilar
ity
GARUD
A
Naïv
e
B
ay
es
Similar
ity
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Der
is
Sti
awa
n
Dep
ar
tm
en
t o
f
C
o
m
p
u
ter
E
n
g
i
n
ee
r
in
g
,
U
n
iv
er
s
ity
o
f
Sriwijay
a
I
n
d
r
alay
a
,
Og
an
I
lir
3
0
6
6
2
,
Palem
b
an
g
,
I
n
d
o
n
esia
E
m
ail:
d
er
is
@
u
n
s
r
i.a
c.
id
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
d
e
v
elo
p
m
e
n
t
o
f
tech
n
o
lo
g
y
is
ac
ce
ler
atin
g
in
ag
g
r
eg
at
o
r
s
er
v
ices
f
o
r
s
cien
tific
jo
u
r
n
al
s
ea
r
ch
es
as
a
r
ef
er
en
ce
o
r
b
ib
lio
g
r
a
p
h
y
in
d
eter
m
in
in
g
ar
ticle
wr
itin
g
to
p
ics.
T
h
e
ag
g
r
eg
ato
r
s
er
v
ice
is
a
p
latf
o
r
m
th
at
co
llects
an
d
co
m
p
iles
in
f
o
r
m
a
tio
n
f
r
o
m
v
ar
i
o
u
s
s
o
u
r
ce
s
to
p
r
o
v
id
e
ea
s
ier
an
d
m
o
r
e
o
r
g
a
n
ized
ac
ce
s
s
f
o
r
its
u
s
er
s
,
o
n
e
o
f
wh
ich
is
th
e
n
ati
o
n
al
a
g
g
r
eg
at
o
r
Gar
b
a
R
u
ju
k
a
n
Dig
ital
(
GARUDA)
d
e
v
elo
p
ed
b
y
t
h
e
Min
is
tr
y
o
f
E
d
u
ca
tio
n
,
C
u
ltu
r
e,
R
esear
ch
,
an
d
T
ec
h
n
o
lo
g
y
(
Kem
e
n
d
i
k
b
u
d
r
is
tek
)
o
f
th
e
R
ep
u
b
lic
o
f
I
n
d
o
n
esia.
Als
o
,
it
h
as
a
d
atab
ase
an
d
n
etwo
r
k
co
n
n
ec
ted
to
SIN
T
A,
B
im
a,
Ar
ju
n
a,
PDDI
KT
I
,
R
is
b
an
g
,
Sco
p
u
s
,
an
d
R
am
a.
R
es
e
a
r
c
h
f
r
o
m
a
ll
l
e
ct
u
r
e
r
s
i
n
I
n
d
o
n
e
s
i
a
is
c
o
ll
e
c
t
e
d
a
n
d
e
n
t
e
r
e
d
i
n
t
o
t
h
e
s
c
ie
n
c
e
a
n
d
t
ec
h
n
o
l
o
g
y
i
n
d
e
x
(
S
I
N
T
A
)
p
o
r
t
a
l
u
s
e
d
t
o
m
e
as
u
r
e
a
n
d
m
o
n
i
t
o
r
t
h
e
p
e
r
f
o
r
m
a
n
c
e
o
f
s
c
i
e
n
ti
f
i
c
r
e
s
e
a
r
c
h
c
o
n
d
u
c
t
e
d
b
y
r
e
s
ea
r
c
h
e
r
s
[
1
]
.
Naiv
e
B
ay
es
i
s
an
alg
o
r
ith
m
u
s
ed
f
o
r
class
if
icatio
n
b
ased
o
n
B
ay
es
t
h
eo
r
em
[
2
]
.
C
lass
if
icatio
n
is
a
tech
n
iq
u
e
to
g
r
o
u
p
d
ata
s
ets
in
to
m
u
lti
-
class
es
to
o
b
tain
co
r
r
ec
t
p
r
ed
ictio
n
an
d
a
n
aly
s
is
r
esu
lts
[
3
]
.
C
las
s
if
icatio
n
with
th
e
s
u
p
p
o
r
t
v
ec
to
r
m
a
ch
in
e
L
i
n
ea
r
Ker
n
el
m
eth
o
d
u
s
in
g
2
0
5
f
ea
tu
r
es
o
b
tain
ed
a
p
o
o
r
ac
cu
r
ac
y
r
ate
o
f
5
8
.
3
%
[
4
]
.
C
lass
if
icatio
n
b
ased
o
n
jo
u
r
n
al
ab
s
tr
ac
ts
u
s
in
g
th
e
n
aiv
e
B
ay
es
an
d
n
aiv
e
B
ay
es
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
7
2
2
-
3
2
2
1
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
,
Vo
l.
6
,
No
.
2
,
J
u
ly
20
25
:
147
-
1
5
8
148
m
u
ltin
o
m
ial
m
eth
o
d
s
p
r
o
v
i
d
es
m
o
r
e
ac
cu
r
ate
class
if
icati
o
n
p
er
f
o
r
m
a
n
ce
with
f
aster
an
d
m
o
r
e
e
f
f
icien
t
co
m
p
u
tin
g
tim
e
co
m
p
ar
ed
t
o
o
th
er
class
if
icatio
n
m
eth
o
d
s
[
5
]
,
[
6
]
.
Natu
r
al
lan
g
u
ag
e
p
r
o
ce
s
s
in
g
(
NL
P)
to
u
n
d
er
s
tan
d
h
u
m
an
lan
g
u
ag
e
ef
f
ec
tiv
ely
an
d
p
r
o
v
id
e
tech
n
iq
u
es
f
o
r
m
a
n
ag
in
g
t
h
e
class
if
icatio
n
o
f
lar
g
e
am
o
u
n
ts
o
f
tex
t
o
r
d
o
cu
m
en
ts
with
ac
cu
r
ate
r
esu
lts
[
7
]
,
[
8
]
.
T
e
x
t
class
if
icatio
n
u
s
in
g
NL
P
ca
n
au
t
o
m
atica
lly
lear
n
f
r
o
m
tex
t
,
s
o
t
h
at
it
ca
n
p
r
o
v
i
d
e
in
f
o
r
m
atio
n
f
r
o
m
th
e
tex
t
in
an
o
r
g
an
ize
d
m
an
n
e
r
with
th
e
co
r
r
ec
t
class
if
icatio
n
[
9
]
,
[
1
0
]
.
NL
P
co
m
b
in
es
co
m
p
u
ter
s
cien
ce
,
lin
g
u
is
tics
,
an
d
m
ath
em
atics
[
1
1
]
,
NL
P
ca
n
b
e
u
s
ed
f
o
r
p
lag
iar
is
m
d
etec
tio
n
[
1
2
]
.
T
h
is
r
esear
ch
u
s
es
tex
t
p
r
o
ce
s
s
in
g
to
class
if
y
ar
ticles
an
d
d
ete
ct
s
im
ilar
ities
b
ased
o
n
titl
es
an
d
ab
s
tr
ac
ts
in
to
s
p
ec
if
ic
ca
teg
o
r
ies
.
T
e
x
t
is
co
n
v
er
ted
to
n
u
m
e
r
ical
f
o
r
m
u
s
in
g
th
e
ter
m
f
r
eq
u
e
n
c
y
-
in
v
er
s
e
d
o
cu
m
en
t
f
r
eq
u
e
n
cy
(TF
-
I
DF)
tec
h
n
iq
u
e
[
1
3
]
.
C
o
s
in
e
s
im
ilar
ity
in
m
ea
s
u
r
in
g
th
e
d
eg
r
ee
o
f
s
im
ilar
i
ty
o
f
s
cien
tific
ar
ticle
citat
io
n
s
with
r
ef
er
en
ce
s
o
u
r
ce
s
g
iv
es
q
u
ite
g
o
o
d
r
esu
lts
o
f
7
0
%
,
an
d
citat
io
n
s
with
n
o
r
elatio
n
s
h
ip
with
r
ef
er
e
n
ce
s
o
u
r
ce
s
b
y
3
0
%
[
1
4
]
.
C
o
s
in
e
s
im
ilar
it
y
to
d
etec
t
p
lag
iar
is
m
i
n
B
en
g
ali
tex
t
co
n
ten
t
s
u
cc
ess
f
u
lly
d
eter
m
in
es
s
im
ilar
ity
b
y
co
m
p
ar
in
g
v
ec
t
o
r
s
in
n
u
m
er
ical
v
alu
es
[
1
5
]
.
Me
asu
r
e
m
en
t
u
s
in
g
co
s
in
e
s
im
ilar
ity
b
y
m
ea
s
u
r
in
g
two
v
ec
to
r
s
an
d
ca
lcu
latin
g
th
e
s
ize
o
f
th
e
c
o
s
in
e
an
g
le
b
etwe
en
th
em
[
1
6
]
.
Ma
tch
in
g
s
cie
n
tific
ar
ticle
titl
es
u
s
in
g
th
e
co
s
in
e
s
im
ilar
ity
an
d
J
ac
ca
r
d
s
im
ilar
ity
m
eth
o
d
s
p
r
o
v
i
d
es
b
etter
co
s
in
e
s
im
ilar
ity
p
er
f
o
r
m
a
n
ce
r
esu
lts
th
an
J
ac
ca
r
d
s
im
ilar
ity
in
s
p
ec
if
ic
s
ce
n
ar
io
s
[
1
7
]
.
C
o
s
in
e
s
im
ilar
ity
i
s
u
s
ed
f
o
r
a
b
o
o
k
r
ec
o
m
m
en
d
atio
n
s
y
s
tem
to
p
r
o
v
id
e
r
esu
lts
r
el
ev
an
t
to
th
e
co
u
r
s
e
to
p
ic
wit
h
a
p
r
ec
is
io
n
o
f
0
.
7
an
d
a
r
ec
all
o
f
0
.
7
3
[
1
8
]
.
C
o
m
p
ar
in
g
th
r
ee
d
if
f
e
r
en
t
m
eth
o
d
s
,
n
am
ely
co
s
in
e
s
im
ilar
ity
,
J
ac
ca
r
d
s
im
ilar
i
ty
,
an
d
E
u
clid
ea
n
d
is
tan
ce
,
to
m
ea
s
u
r
e
th
e
s
im
ilar
ity
o
f
two
n
ews
ar
ticles
in
Hin
d
i
a
n
d
E
n
g
lis
h
b
ased
o
n
to
p
ic.
T
h
e
m
o
s
t
ac
cu
r
ate
co
s
in
e
s
im
ilar
ity
r
esu
lts
co
m
p
ar
ed
to
th
e
o
th
e
r
two
m
eth
o
d
s
,
with
an
ac
cu
r
ac
y
o
f
8
1
.
2
5
%,
r
ec
all
o
f
1
0
0
%,
an
d
F
-
m
ea
s
u
r
e
o
f
7
6
.
9
2
%
[
1
9
]
.
T
h
e
m
ap
p
in
g
r
elate
d
to
th
e
p
r
ev
io
u
s
r
esear
ch
b
ased
o
n
th
e
r
esu
lts
o
f
th
e
liter
atu
r
e
r
esear
ch
co
llec
tio
n
is
illu
s
tr
ated
in
Fig
u
r
e
1
VOS
Viewe
r
n
aiv
e
B
ay
es
an
d
Fig
u
r
e
2
VOS
V
iewe
r
c
o
s
in
e
s
im
ilar
ity
.
Fig
u
r
e
1
is
th
e
VOS
V
iewe
r
f
o
r
m
eth
o
d
s
r
elate
d
to
n
aiv
e
B
ay
es
an
d
p
r
ev
io
u
s
r
esear
ch
.
F
ig
u
r
e
2
is
th
e
VOS
V
iewe
r
f
o
r
m
eth
o
d
s
r
elate
d
to
co
s
in
e
s
im
ilar
ity
an
d
p
r
ev
io
u
s
r
esear
ch
.
VOS
Viewe
r
is
u
s
ed
f
o
r
m
ap
p
i
n
g
th
e
r
elatio
n
s
h
ip
s
b
etwe
en
k
ey
w
o
r
d
s
,
p
r
ev
i
o
u
s
au
th
o
r
s
,
an
d
j
o
u
r
n
als
u
s
e
d
in
r
esear
ch
.
R
e
s
ea
r
ch
er
s
u
s
e
it
to
id
en
tify
e
m
er
g
in
g
f
ield
s
an
d
l
o
o
k
at
in
ter
r
elate
d
s
cien
tific
c
o
n
ce
p
ts
.
T
h
is
r
esear
ch
co
n
tr
i
b
u
tes
to
e
v
alu
atin
g
th
e
class
if
icatio
n
o
f
p
u
b
lis
h
ed
ar
ticles
in
GA
R
UDA
b
y
ap
p
ly
in
g
th
e
n
ai
v
e
B
ay
es
m
et
h
o
d
,
an
d
d
etec
tin
g
s
im
ilar
ities
u
s
in
g
th
e
co
s
in
e
s
im
ilar
ity
ap
p
r
o
ac
h
.
T
h
e
cl
ass
if
icatio
n
m
eth
o
d
u
s
in
g
n
a
iv
e
B
ay
es
an
d
th
e
s
im
ilar
ity
d
etec
tio
n
m
eth
o
d
u
s
in
g
co
s
in
e
s
im
ilar
ity
,
in
th
is
r
esear
ch
p
r
o
d
u
ce
an
ac
c
u
r
ate
an
d
g
o
o
d
m
o
d
el
in
class
if
y
in
g
ar
ticles
an
d
m
ea
s
u
r
in
g
ar
ticle
s
im
ilar
it
y
.
T
h
is
r
esear
ch
aim
s
to
d
eter
m
in
e
th
e
p
er
f
o
r
m
an
ce
o
f
class
if
ier
s
u
s
in
g
th
e
n
aïv
e
B
a
y
es
m
eth
o
d
an
d
to
d
eter
m
in
e
th
e
p
er
f
o
r
m
an
ce
o
f
s
im
ilar
ity
d
etec
tio
n
u
s
in
g
th
e
co
s
in
e
s
im
ilar
ity
m
eth
o
d
.
T
h
e
d
is
cu
s
s
io
n
in
th
is
r
esear
ch
is
as
f
o
llo
ws:
s
ec
tio
n
2
d
is
cu
s
s
es
t
h
e
m
eth
o
d
s
u
s
ed
in
d
eter
m
in
in
g
r
e
f
er
en
ce
s
an
d
d
atasets
.
Sectio
n
3
p
r
o
v
id
es
th
e
r
esu
lts
o
f
class
if
icatio
n
,
s
im
ilar
ity
d
etec
tio
n
,
an
d
s
ea
r
ch
o
f
ar
ticles
.
Sectio
n
4
p
r
o
v
id
es c
o
n
cl
u
s
io
n
s
an
d
s
u
g
g
esti
o
n
s
f
o
r
f
u
r
th
e
r
r
esear
ch
.
Fig
u
r
e
1
.
VOS
Viewe
r
f
o
r
n
aï
v
e
B
ay
es
Evaluation Warning : The document was created with Spire.PDF for Python.
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
I
SS
N:
2722
-
3
2
2
1
C
la
s
s
i
fica
tio
n
a
n
d
s
imila
r
ity
d
etec
tio
n
o
f I
n
d
o
n
esia
n
s
cien
tifi
c
jo
u
r
n
a
l
…
(
N
yima
s
S
a
b
ilin
a
C
a
h
ya
n
i
)
149
Fig
u
r
e
2
.
VOS
Viewe
r
f
o
r
C
o
s
in
e
S
im
ilar
ity
2.
M
E
T
H
O
D
2.
1
.
Resea
rc
h
f
ra
m
ewo
r
k
T
h
is
r
esear
ch
r
eq
u
ir
es
a
f
r
am
ewo
r
k
,
r
esear
c
h
f
lo
w,
a
n
d
s
ev
er
al
s
tag
es.
T
h
e
th
eo
r
y
u
s
ed
b
y
p
r
ev
i
o
u
s
r
esear
ch
,
th
e
ap
p
r
o
p
r
iate
m
eth
o
d
o
lo
g
y
to
s
o
lv
e
th
e
m
a
in
p
r
o
b
lem
u
s
in
g
th
e
n
aiv
e
B
ay
es
m
eth
o
d
in
class
if
icatio
n
,
th
e
co
s
in
e
s
im
ilar
ity
m
eth
o
d
in
s
im
ilar
ity
d
e
te
ctio
n
,
an
d
th
e
co
s
in
e
s
im
ilar
it
y
m
eth
o
d
in
ar
ticle
s
ea
r
ch
,
th
e
r
esear
ch
f
r
a
m
ewo
r
k
is
d
r
awn
in
Fig
u
r
e
3
.
T
h
e
r
esear
ch
f
r
am
ew
o
r
k
in
Fig
u
r
e
3
d
escr
ib
es
t
h
e
p
r
o
ce
s
s
,
s
tar
tin
g
with
d
ata
co
l
lectio
n
,
d
ata
e
n
g
in
ee
r
i
n
g
,
lab
e
lin
g
u
s
in
g
r
u
le
-
b
ased
au
to
lab
elin
g
,
cl
ass
if
icatio
n
u
s
in
g
n
aiv
e
B
ay
es,
s
im
ilar
ity
d
etec
tio
n
u
s
in
g
co
s
in
e
s
im
ilar
ity
,
an
d
ar
ticle
s
ea
r
ch
u
s
in
g
co
s
in
e
s
im
ilar
ity
.
Data
en
g
in
ee
r
in
g
is
ca
r
r
ied
o
u
t
to
clea
n
u
p
d
u
p
licate
d
a
ta
an
d
co
n
s
is
ts
o
f
s
ev
er
al
s
t
ag
es:
to
k
en
izatio
n
,
co
n
ca
ten
atio
n
,
b
alan
cin
g
,
f
la
tten
in
g
d
ata,
a
n
d
s
p
litt
in
g
.
R
u
le
-
b
ased
au
to
-
lab
elin
g
is
d
o
n
e
b
y
m
atch
i
n
g
k
ey
wo
r
d
s
in
th
e
tex
t
with
p
r
e
d
eter
m
in
ed
ca
te
g
o
r
ies.
C
lass
if
icatio
n
was
ca
r
r
ied
o
u
t
to
d
ete
r
m
in
e
th
e
ca
te
g
o
r
y
o
f
tex
t
b
ased
o
n
th
e
p
r
o
b
ab
i
lity
o
f
wo
r
d
s
,
i
f
th
e
class
if
icatio
n
r
esu
lts
ar
e
i
n
co
r
r
ec
t,
g
o
b
ac
k
to
t
h
e
d
at
a
en
g
in
ee
r
in
g
p
r
o
ce
s
s
.
Me
an
w
h
ile,
th
e
c
o
r
r
ec
t
class
if
icatio
n
r
esu
lts
will
p
r
o
ce
e
d
to
th
e
s
im
ilar
ity
d
etec
tio
n
p
r
o
ce
s
s
.
Similar
ity
d
etec
tio
n
an
d
s
cien
tific
ar
ticle
s
ea
r
ch
es
wer
e
ca
r
r
ied
o
u
t
to
an
al
y
ze
t
h
e
r
esu
lts
o
f
c
o
s
in
e
s
im
ilar
it
y
to
ass
es
s
th
e
s
im
ila
r
ity
o
f
ar
ticles
b
ased
o
n
th
e
s
im
ilar
ity
s
co
r
e
.
T
h
e
c
l
a
s
s
i
f
i
ca
t
i
o
n
m
e
t
h
o
d
u
s
i
n
g
n
a
i
v
e
B
a
y
e
s
a
n
d
t
h
e
s
i
m
il
a
r
i
t
y
d
e
t
e
c
t
i
o
n
m
e
t
h
o
d
u
s
i
n
g
C
o
s
i
n
e
S
i
m
i
l
a
r
it
y
p
r
o
d
u
c
e
a
n
a
c
c
u
r
a
t
e
a
n
d
g
o
o
d
m
o
d
e
l
i
n
c
l
a
s
s
i
f
y
i
n
g
a
r
ti
c
l
es
a
n
d
m
e
as
u
r
in
g
a
r
t
i
c
l
e
s
i
m
il
a
r
i
t
y
.
2.
1
.
1.
Da
t
a
c
o
llect
io
n
T
h
e
d
ataset
co
llectio
n
tech
n
iq
u
e
o
b
tain
e
d
f
r
o
m
GARUDA
in
th
e
f
o
r
m
o
f
E
x
ce
l
is
s
ec
o
n
d
ar
y
d
ata.
T
h
er
e
ar
e
3
5
,
9
0
8
r
o
ws
an
d
1
3
co
l
u
m
n
s
o
f
Au
th
o
r
I
D,
GARUDA_
I
D,
OJS
_
I
DE
NT
I
FIE
R
,
an
d
GARUD
A_
DOI
.
AKREDI
T
ASI
,
GARUDA_
T
I
T
L
E
,
GARUDA_
A
B
ST
R
AC
T
,
GA
R
UDA
J
OU
R
NAL
,
GARUD
A_
YE
AR
_
PU
B
L
I
SH
,
GARUDA_
DAT
E
_
PU
B
L
I
SH,
GARUDA_
C
I
T
E
,
GARUDA_
U
R
L
,
OR
I
GI
NAL
_
UR
L
.
T
h
is
r
esea
r
ch
u
s
ed
th
e
titl
e
an
d
a
b
s
tr
ac
t
to
class
if
y
,
d
etec
t
s
im
ilar
ities
an
d
s
ea
r
ch
f
o
r
s
cien
tific
ar
ticles.
T
h
e
d
ata
wa
s
p
r
o
ce
s
s
ed
b
y
d
eletin
g
d
u
p
lic
ate
d
ata
in
to
2
9
,
2
3
9
r
o
ws
an
d
1
3
c
o
lu
m
n
s
.
G
o
o
d
class
if
icatio
n
r
esu
lts
u
s
in
g
n
aiv
e
B
ay
es,
ar
ticle
s
im
ilar
ity
d
etec
tio
n
u
s
in
g
co
s
in
e
s
im
il
ar
ity
,
ar
ticle
s
ea
r
ch
u
s
in
g
co
s
in
e
s
im
ilar
ity
,
an
d
r
e
s
ea
r
ch
d
ata
ar
e
o
b
tain
ed
a
n
d
d
ep
icted
in
Fig
u
r
e
4
.
2
.
1
.
2
.
Da
t
a
eng
ineering
Data
en
g
in
ee
r
in
g
is
co
llectin
g
an
d
p
r
ep
ar
i
n
g
d
atasets
f
r
o
m
t
h
e
Min
is
tr
y
o
f
E
d
u
ca
tio
n
an
d
C
u
ltu
r
e's
GARUD
A,
clea
n
in
g
d
u
p
licate
d
ata
,
an
d
lab
elin
g
.
T
h
e
s
tag
es
ca
r
r
ied
o
u
t
in
d
ata
en
g
i
n
ee
r
in
g
ar
e
illu
s
tr
ated
in
Fig
u
r
e
5
.
T
h
e
s
tag
es
o
f
d
ata
e
n
g
in
ee
r
in
g
ar
e
s
h
o
w
n
in
Fig
u
r
e
5
.
T
h
e
f
ir
s
t
s
tag
e
is
to
k
en
izin
g
,
th
e
s
ec
o
n
d
s
tag
e
is
co
n
ca
t
th
e
d
ata
to
c
o
m
b
in
e
th
e
tex
t
d
ata
b
etwe
en
th
e
titl
e
an
d
a
b
s
tr
ac
t
co
lu
m
n
s
to
g
e
n
e
r
ate
a
n
ew
c
o
lu
m
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
7
2
2
-
3
2
2
1
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
,
Vo
l.
6
,
No
.
2
,
J
u
ly
20
25
:
147
-
1
5
8
150
with
th
e
n
am
e
C
ONCAT_
D
AT
A.
T
h
e
th
ir
d
s
tag
e
is
b
ala
n
cin
g
d
ata
to
b
alan
ce
d
ata
b
e
twee
n
m
in
o
r
ity
an
d
m
ajo
r
ity
class
es.
W
e
alr
ea
d
y
tr
ied
to
u
s
e
a
n
u
n
b
alan
ce
d
d
ataset,
b
u
t
we
g
o
t
u
n
s
atis
f
ac
to
r
y
r
esu
lts
an
d
n
eg
ativ
ely
im
p
ac
te
d
th
e
p
e
r
f
o
r
m
an
ce
o
f
m
ac
h
in
e
lea
r
n
in
g
a
lg
o
r
ith
m
s
[
2
0
]
,
[
2
1
]
.
T
h
e
f
o
u
r
th
s
tag
e
f
latten
s
th
e
d
ata
to
ch
an
g
e
th
e
s
tr
u
ctu
r
e
o
f
a
m
u
lti
-
d
im
en
s
io
n
al
ar
r
a
y
in
to
a
o
n
e
-
d
im
e
n
s
io
n
al
ar
r
ay
.
T
h
e
last
s
tag
e
s
p
li
ts
th
e
d
ata
to
s
ep
ar
ate
th
e
d
ataset
in
to
two
s
u
b
s
ets:
tr
ain
in
g
an
d
test
d
ata.
I
n
th
is
s
tu
d
y
,
a
r
an
d
o
m
s
p
lit
m
eth
o
d
is
u
s
ed
b
y
s
am
p
lin
g
d
ata
to
en
s
u
r
e
th
at
r
ef
r
ac
tio
n
ag
ain
s
t
d
if
f
er
en
t
d
ata
ch
ar
ac
te
r
is
tics
d
o
es
n
o
t
af
f
ec
t
th
e
d
ata
m
o
d
elin
g
p
r
o
ce
s
s
.
Af
ter
p
e
r
f
o
r
m
in
g
th
e
d
ata
en
g
i
n
ee
r
in
g
s
tag
e,
lab
elin
g
is
d
e
p
icted
in
Fig
u
r
e
6
.
T
h
e
ca
teg
o
r
y
lab
elin
g
in
Fig
u
r
e
6
d
escr
ib
es
th
e
r
esu
lts
o
f
th
e
au
to
lab
el
u
s
e
r
u
le
-
b
ased
a
u
to
.
T
h
er
e
is
a
n
ew
co
lu
m
n
with
th
e
n
a
m
e
o
f
th
e
ca
teg
o
r
y
.
T
h
e
ca
teg
o
r
ie
s
th
at
h
av
e
b
ee
n
d
eter
m
in
e
d
i
n
th
is
s
tu
d
y
ar
e
n
in
e
ca
teg
o
r
ies,
n
am
el
y
o
th
er
,
m
a
n
ag
em
en
t
in
f
o
r
m
atio
n
s
y
s
tem
s
,
d
ec
is
io
n
s
u
p
p
o
r
t
s
y
s
tem
s
,
s
ales
in
f
o
r
m
atio
n
s
y
s
tem
s
,
cu
s
to
m
er
r
elatio
n
s
h
i
p
m
an
ag
em
en
t,
m
a
r
k
etin
g
in
f
o
r
m
atio
n
s
y
s
tem
s
,
f
in
an
cial
in
f
o
r
m
atio
n
s
y
s
tem
s
,
ex
ec
u
tiv
e
in
f
o
r
m
atio
n
s
y
s
tem
s
,
an
d
h
u
m
an
r
eso
u
r
ce
s
in
f
o
r
m
atio
n
s
y
s
tem
s
.
Fig
u
r
e
3
.
R
esear
ch
f
r
am
ewo
r
k
Fig
u
r
e
4
.
R
esear
ch
d
ataset
Evaluation Warning : The document was created with Spire.PDF for Python.
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
I
SS
N:
2722
-
3
2
2
1
C
la
s
s
i
fica
tio
n
a
n
d
s
imila
r
ity
d
etec
tio
n
o
f I
n
d
o
n
esia
n
s
cien
tifi
c
jo
u
r
n
a
l
…
(
N
yima
s
S
a
b
ilin
a
C
a
h
ya
n
i
)
151
Fig
u
r
e
5
.
Stag
es o
f
d
ata
en
g
in
ee
r
in
g
Fig
u
r
e
6
.
C
ateg
o
r
y
l
ab
elin
g
2.
1
.
3.
L
a
belin
g
L
ab
elin
g
in
th
is
r
esear
ch
u
s
in
g
a
r
u
le
-
b
ased
m
eth
o
d
is
ca
r
r
ied
o
u
t b
ased
o
n
p
r
ed
eter
m
i
n
e
d
k
ey
wo
r
d
s
.
T
h
is
m
eth
o
d
ca
teg
o
r
izes
th
e
l
ab
els
au
to
m
atica
lly
,
th
e
s
p
ec
if
ied
k
ey
wo
r
d
s
m
u
s
t
b
e
r
elev
a
n
t
to
th
e
titl
e
an
d
ab
s
tr
ac
t
o
f
th
e
ar
ticle
.
T
h
e
lab
elin
g
p
r
o
ce
s
s
in
th
is
s
tu
d
y
c
h
a
n
g
es
wo
r
d
s
to
lo
we
r
ca
s
e
letter
s
.
L
ab
els
b
ased
o
n
p
r
ed
ef
in
e
d
k
ey
wo
r
d
s
,
th
e
r
esu
lt
is
th
at
if
th
er
e
ar
e
k
ey
wo
r
d
s
,
th
ey
will
au
to
m
atica
lly
en
ter
th
e
ca
teg
o
r
y
lab
els
th
at
h
av
e
b
ee
n
d
eter
m
in
ed
,
if
th
er
e
ar
e
n
o
k
e
y
wo
r
d
s
,
th
e
y
wi
ll a
u
to
m
atica
lly
en
t
er
o
t
h
er
lab
els.
2.
1
.
4.
Cla
s
s
if
ica
t
io
n us
ing
n
a
iv
e
B
a
y
es
C
las
s
if
icatio
n
is
ca
r
r
ied
o
u
t
af
ter
th
e
d
ataset
p
r
e
-
p
r
o
ce
s
s
in
g
s
tag
e
is
co
m
p
leted
,
an
d
a
clas
s
if
icatio
n
m
o
d
el
is
ca
r
r
ied
out
u
s
in
g
t
h
e
n
aïv
e
B
ay
es
m
eth
o
d
.
Pr
o
ce
s
s
s
tep
s
to
m
ea
s
u
r
e
class
if
icatio
n
p
er
f
o
r
m
a
n
ce
b
y
ca
lcu
latin
g
ac
cu
r
ac
y
,
r
ec
all,
p
r
ec
is
io
n
,
an
d
F
1
-
s
co
r
e
[
2
2
]
.
C
a
lcu
latin
g
ac
cu
r
ac
y
ca
n
u
s
e
(
1
)
.
=
+
+
+
+
100%
(
1
)
C
alcu
latin
g
th
e
p
r
ec
is
io
n
ca
n
b
e
d
o
n
e
u
s
in
g
(
2
)
.
=
+
(
2
)
C
alcu
l
atin
g
r
ec
alls
ca
n
b
e
d
o
n
e
u
s
in
g
(
3
)
.
=
+
(
3
)
C
alcu
latin
g
th
e
F1
-
s
co
r
e
ca
n
b
e
d
o
n
e
u
s
in
g
(
4
)
.
F1
−
=
2
∗
+
(
4
)
I
n
f
o
r
m
atio
n
:
T
r
u
e
p
o
s
itiv
e
:
t
h
e
am
o
u
n
t
o
f
c
o
r
r
ec
tly
class
if
ied
p
o
s
itiv
e
d
at
a
.
T
r
u
e
n
e
g
ativ
e
:
t
h
e
am
o
u
n
t o
f
co
r
r
ec
tly
class
if
ied
n
eg
ativ
e
d
ata
.
Fals
e
p
o
s
itiv
e
:
t
h
e
am
o
u
n
t o
f
n
eg
ativ
e
d
ata
th
at
is
in
c
o
r
r
ec
tl
y
class
if
ied
as p
o
s
itiv
e
.
Fals
e
n
eg
ativ
e
:
t
h
e
am
o
u
n
t
o
f
p
o
s
itiv
e
d
ata
th
at
is
in
co
r
r
ec
tl
y
class
if
ied
as n
eg
ativ
e
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
7
2
2
-
3
2
2
1
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
,
Vo
l.
6
,
No
.
2
,
J
u
ly
20
25
:
147
-
1
5
8
152
2.
1
.
5.
Art
icle
s
im
ila
rit
y
d
et
ec
t
io
n us
ing
c
o
s
ine
s
im
ila
rit
y
T
h
e
d
etec
tio
n
o
f
s
im
ilar
ity
in
ar
ticles
u
s
in
g
th
e
co
s
in
e
s
i
m
ilar
ity
m
eth
o
d
is
v
er
y
ap
p
r
o
p
r
iate
to
ev
alu
ate
h
o
w
m
u
c
h
s
im
ilar
ity
b
etwe
en
class
es
an
d
th
e
r
e
s
u
lt
is
in
th
e
f
o
r
m
o
f
v
ec
to
r
an
g
le
p
ar
am
ete
r
s
.
C
alcu
latin
g
s
im
ilar
ity
h
as a
r
an
g
e
v
alu
e
f
r
o
m
0
-
1
.
T
h
e
ca
lcu
latio
n
f
o
r
m
u
la
f
o
r
th
e
s
im
ilar
ity
r
es
u
lts
u
s
es
(
5
)
.
=
∑
.
.
1
√
∑
2
1
√
∑
2
1
(
5
)
I
n
f
o
r
m
atio
n
:
a
i
an
d
b
i
:
c
o
m
p
o
n
en
ts
o
f
two
v
ec
to
r
s
A
a
n
d
B
.
Σa
i
b
i
:
d
o
t p
r
o
d
u
ct
(
m
u
ltip
licatio
n
o
f
d
o
ts
)
b
etwe
en
two
v
ec
to
r
s
.
2
an
d
2
:
t
h
e
len
g
th
(
m
ag
n
itu
d
e)
o
f
ea
ch
v
ec
to
r
.
n
:
u
n
iq
u
e
wo
r
d
co
u
n
t
.
T
h
is
r
esear
ch
u
s
es
v
ec
to
r
we
ig
h
tin
g
to
ca
lcu
late
c
o
s
in
e
s
im
ilar
ity
in
v
ec
to
r
f
o
r
m
u
s
in
g
T
F
-
I
DF.
TF
-
I
DF
is
a
s
tatis
tical
m
eth
o
d
u
s
ed
to
m
ea
s
u
r
e
th
e
lev
el
o
f
im
p
o
r
tan
ce
o
f
a
ter
m
in
a
d
o
c
u
m
en
t
[
2
3
]
.
T
F
in
d
icate
s
th
e
f
r
eq
u
en
c
y
o
f
th
e
wo
r
d
ap
p
ea
r
i
n
g
in
th
e
d
o
cu
m
en
t;
th
e
h
ig
h
er
th
e
T
F
v
alu
e
is
co
n
s
id
er
ed
th
e
m
o
r
e
r
elev
an
t
th
e
wo
r
d
is
in
th
e
d
o
cu
m
e
n
t
[
2
4
]
.
T
h
e
wo
r
d
weig
h
t
is
o
b
tain
ed
f
r
o
m
th
e
m
u
ltip
licatio
n
o
f
T
F
an
d
I
DF
[
2
5
]
.
T
h
is
ca
lcu
lati
o
n
b
e
g
in
s
b
y
d
eter
m
i
n
in
g
two
v
ec
to
r
s
,
n
am
ely
ar
ticle
1
a
n
d
ar
ticle
2
,
wh
ich
r
ep
r
esen
t
th
e
o
b
ject
b
ein
g
c
o
m
p
ar
ed
,
in
th
is
r
esear
ch
,
b
ased
o
n
th
e
titl
e
an
d
ab
s
tr
a
ct
th
at
h
av
e
b
ee
n
co
n
ca
ten
ated
.
T
h
e
f
ir
s
t
s
tep
i
n
th
e
ca
lcu
latio
n
p
r
o
ce
s
s
is
t
o
d
eter
m
i
n
e
th
e
d
o
t
p
r
o
d
u
ct
o
f
th
e
two
v
ec
to
r
s
,
wh
ich
is
o
b
tain
e
d
b
y
ad
d
in
g
th
e
r
esu
lt
o
f
th
e
m
u
ltip
licatio
n
o
f
ea
ch
co
r
r
esp
o
n
d
i
n
g
elem
e
n
t
in
ea
ch
v
ec
to
r
.
I
n
th
e
s
ec
o
n
d
s
tep
,
th
e
len
g
th
o
r
m
ag
n
itu
d
e
o
f
ea
c
h
v
ec
t
o
r
is
c
alcu
lated
b
y
tak
in
g
th
e
s
q
u
ar
e
r
o
o
t
o
f
th
e
s
u
m
o
f
th
e
s
q
u
ar
es
o
f
ea
ch
elem
en
t
in
th
at
v
ec
to
r
.
T
h
e
co
s
in
e
s
im
ilar
ity
v
alu
e
is
th
en
o
b
tain
ed
b
y
d
iv
id
in
g
th
e
d
o
t
p
r
o
d
u
ct
r
esu
lt
b
y
th
e
p
r
o
d
u
ct
m
u
ltip
licatio
n
o
f
th
e
len
g
th
s
o
f
th
e
two
v
ec
to
r
s
,
ac
co
r
d
in
g
t
o
th
e
eq
u
atio
n
.
T
h
e
r
esu
lts
o
f
th
is
ca
lcu
lat
io
n
ar
e
in
th
e
r
an
g
e
o
f
0
to
1
,
wh
e
r
e
v
alu
es
clo
s
e
to
1
in
d
icate
a
h
ig
h
d
eg
r
ee
o
f
s
im
ilar
ity
,
v
alu
es
clo
s
e
to
0
in
d
icate
th
e
ab
s
en
ce
o
f
a
s
ig
n
if
i
ca
n
t
r
elatio
n
s
h
ip
,
an
d
v
alu
es
clo
s
e
to
-
1
in
d
icate
th
at
th
e
two
v
ec
to
r
s
h
av
e
o
p
p
o
s
ite
d
ir
ec
tio
n
s
.
T
h
e
s
im
ilar
ity
d
etec
tio
n
s
tag
es a
r
e
d
ep
icted
in
Fig
u
r
e
7
.
Fig
u
r
e
7
.
Stag
es o
f
co
s
in
e
s
im
ilar
ity
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
i
s
s
e
c
t
i
o
n
d
e
s
c
r
i
b
e
s
t
h
e
r
e
s
u
l
t
s
a
n
d
d
i
s
c
u
s
s
i
o
n
o
f
t
h
e
d
a
t
a
b
a
l
a
n
c
i
n
g
p
r
o
c
e
s
s
.
T
h
e
r
e
s
u
l
t
s
o
f
d
a
t
a
b
a
l
a
n
c
i
n
g
a
r
e
i
l
l
u
s
t
r
a
t
e
d
i
n
T
a
b
l
e
1
,
a
n
d
t
h
e
d
a
t
a
d
i
f
f
e
r
e
n
c
e
g
r
a
p
h
i
s
i
l
l
u
s
t
r
a
t
e
d
i
n
F
i
g
u
r
e
8
.
F
i
g
u
r
e
8
s
h
o
w
s
a
g
r
a
p
h
o
f
t
h
e
d
a
t
a
c
l
a
s
s
i
f
i
c
a
t
i
o
n
r
e
s
u
l
t
s
,
F
i
g
u
r
e
8
(
a
)
g
r
a
p
h
s
t
h
a
t
p
r
o
v
i
d
e
c
l
a
s
s
i
f
i
c
a
t
i
o
n
r
e
s
u
l
t
s
u
s
i
n
g
i
m
b
a
l
a
n
c
e
d
d
a
t
a
,
a
n
d
F
i
g
u
r
e
8
(
b
)
g
r
a
p
h
s
t
h
a
t
p
r
o
v
i
d
e
c
l
a
s
s
i
f
i
c
a
t
i
o
n
r
e
s
u
l
t
s
u
s
i
n
g
b
a
l
a
n
c
e
d
d
a
t
a
u
s
i
n
g
t
h
e
r
a
n
d
o
m
o
v
e
r
-
s
a
m
p
l
i
n
g
(
R
O
S
)
m
e
t
h
o
d
.
T
h
e
f
i
n
a
l
s
t
a
g
e
d
i
s
c
u
s
s
e
s
t
h
e
r
e
s
u
l
t
s
o
f
c
l
a
s
s
i
f
i
c
a
t
i
o
n
u
s
i
n
g
t
h
e
n
a
i
v
e
B
a
y
e
s
m
e
t
h
o
d
,
t
h
e
r
e
s
u
l
t
s
o
f
a
r
t
i
c
l
e
s
i
m
i
l
a
r
i
t
y
d
e
t
e
c
t
i
o
n
,
a
n
d
t
h
e
r
e
s
u
l
t
s
o
f
s
c
i
e
n
t
i
f
i
c
a
r
t
i
c
l
e
s
e
a
r
c
h
u
s
i
n
g
t
h
e
c
o
s
i
n
e
s
i
m
i
l
a
r
i
t
y
m
e
t
h
o
d
.
T
a
b
l
e
1
d
e
s
c
r
i
b
e
s
t
h
e
d
a
t
a
s
e
t
t
h
a
t
h
a
s
d
o
n
e
c
a
t
e
g
o
r
y
a
u
t
o
-
l
a
b
e
l
i
n
g
b
a
s
e
d
o
n
t
h
e
k
e
y
w
o
r
d
s
t
h
a
t
h
a
v
e
b
e
e
n
d
e
f
i
n
e
d
.
T
h
e
r
e
a
r
e
t
w
o
c
o
l
u
m
n
s
i
n
t
h
e
n
u
m
b
e
r
o
f
d
a
t
a
s
e
t
s
:
t
h
e
n
u
m
b
e
r
b
e
f
o
r
e
a
n
d
t
h
e
n
u
m
b
e
r
a
f
t
e
r
.
T
h
e
p
r
e
v
i
o
u
s
n
u
m
b
e
r
r
e
s
u
l
t
s
f
r
o
m
a
u
t
o
-
l
a
b
e
l
i
n
g
w
i
t
h
o
u
t
u
s
i
n
g
t
h
e
o
v
e
r
-
s
a
m
p
l
i
n
g
m
e
t
h
o
d
.
T
h
e
n
u
m
b
e
r
a
f
t
e
r
i
s
t
h
e
r
e
s
u
l
t
o
f
a
u
t
o
-
l
a
b
e
l
i
n
g
w
i
t
h
d
a
t
a
b
a
l
a
n
c
i
n
g
u
s
i
n
g
R
O
S
,
w
h
i
c
h
h
a
s
a
w
a
y
o
f
w
o
r
k
i
n
g
b
y
i
d
e
n
t
i
f
y
i
n
g
m
i
n
o
r
i
t
y
c
l
a
s
s
e
s
a
n
d
m
a
j
o
r
i
t
y
c
l
a
s
s
e
s
.
D
u
p
l
i
c
a
t
e
d
a
t
a
f
r
o
m
t
h
e
m
i
n
o
r
i
t
y
c
l
a
s
s
e
s
o
f
2
0
,
9
1
4
c
l
a
s
s
e
s
t
o
b
e
b
a
l
a
n
c
e
d
w
i
t
h
t
h
e
m
a
j
o
r
i
t
y
c
l
a
s
s
[
2
6
]
.
F
i
g
u
r
e
8
(
a
)
d
e
p
i
c
t
s
i
m
b
a
l
a
n
c
e
d
d
a
t
a
w
i
t
h
o
t
h
e
r
c
a
t
e
g
o
r
i
e
s
a
s
m
a
n
y
a
s
2
0
,
9
1
4
,
c
o
u
n
t
o
f
a
p
p
o
i
n
t
m
e
n
t
i
n
f
o
r
m
a
t
i
o
n
s
y
s
t
e
m
i
s
1
6
9
,
d
e
c
i
s
i
o
n
s
u
p
p
o
r
t
s
y
s
t
e
m
i
s
1
,
0
0
3
,
s
a
l
e
s
i
n
f
o
r
m
a
t
i
o
n
s
y
s
t
e
m
i
s
1
1
1
,
c
u
s
t
o
m
e
r
r
e
l
a
t
i
o
n
s
h
i
p
m
a
n
a
g
e
m
e
n
t
i
s
6
3
,
m
a
r
k
e
t
i
n
g
i
n
f
o
r
m
a
t
i
o
n
s
y
s
t
e
m
i
s
9
,
f
i
n
a
n
c
i
a
l
i
n
f
o
r
m
a
t
i
o
n
s
y
s
t
e
m
i
s
8
,
e
x
e
c
u
t
i
v
e
i
n
f
o
r
m
a
t
i
o
n
s
y
s
t
e
m
i
s
5
,
a
n
d
Evaluation Warning : The document was created with Spire.PDF for Python.
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
I
SS
N:
2722
-
3
2
2
1
C
la
s
s
i
fica
tio
n
a
n
d
s
imila
r
ity
d
etec
tio
n
o
f I
n
d
o
n
esia
n
s
cien
tifi
c
jo
u
r
n
a
l
…
(
N
yima
s
S
a
b
ilin
a
C
a
h
ya
n
i
)
153
h
u
m
a
n
r
e
s
o
u
r
c
e
s
i
n
f
o
r
m
a
t
i
o
n
s
y
s
t
e
m
i
s
4
.
F
i
g
u
r
e
8
(
b
)
i
l
l
u
s
t
r
a
t
e
s
t
h
e
b
a
l
a
n
c
e
d
d
a
t
a
t
h
a
t
h
a
s
b
e
e
n
c
a
r
r
i
e
d
o
u
t
u
s
i
n
g
R
O
S
,
a
n
d
a
l
l
c
a
t
e
g
o
r
i
e
s
a
r
e
b
a
l
a
n
c
e
d
a
s
m
a
n
y
a
s
2
0
,
9
1
4
i
n
e
a
c
h
c
a
t
e
g
o
r
y
.
T
ab
le
1
.
B
alan
cin
g
d
ata
u
s
in
g
R
OS
C
a
t
e
g
o
r
y
To
t
a
l
B
e
f
o
r
e
R
O
S
A
f
t
e
r
R
O
S
O
t
h
e
r
2
0
,
9
1
4
2
0
,
9
1
4
M
a
n
a
g
e
m
e
n
t
i
n
f
o
r
ma
t
i
o
n
s
y
st
e
ms
1
6
9
2
0
,
9
1
4
D
e
c
i
s
i
o
n
s
u
p
p
o
r
t
sy
s
t
e
m
1
,
0
0
3
2
0
,
9
1
4
S
a
l
e
s
i
n
f
o
r
m
a
t
i
o
n
s
y
st
e
m
1
1
1
2
0
,
9
1
4
C
u
s
t
o
mer r
e
l
a
t
i
o
n
s
h
i
p
ma
n
a
g
e
m
e
n
t
63
2
0
,
9
1
4
M
a
r
k
e
t
i
n
g
i
n
f
o
r
m
a
t
i
o
n
s
y
st
e
m
9
2
0
,
9
1
4
F
i
n
a
n
c
i
a
l
i
n
f
o
r
ma
t
i
o
n
s
y
st
e
m
8
2
0
,
9
1
4
Ex
e
c
u
t
i
v
e
i
n
f
o
r
m
a
t
i
o
n
s
y
s
t
e
ms
5
2
0
,
9
1
4
H
u
ma
n
r
e
s
o
u
r
c
e
i
n
f
o
r
m
a
t
i
o
n
s
y
st
e
ms
4
2
0
,
9
1
4
(
a)
(
b
)
Fig
u
r
e
8
.
Gr
a
p
h
o
f
th
e
d
ata
class
if
icatio
n
r
esu
lts
:
(
a)
im
b
alan
ce
d
d
ata
an
d
(
b
)
b
alan
ce
d
d
ata
3.
1
.
Cla
s
s
if
ica
t
io
n us
ing
n
a
iv
e
B
a
y
es
T
h
is
class
if
icatio
n
co
n
d
u
cted
o
n
e
ex
p
er
im
e
n
t
with
8
0
%
o
f
th
e
tr
ain
in
g
d
ata
an
d
2
0
%
o
f
th
e
test
d
at
a
f
r
o
m
2
9
,
2
3
9
r
o
ws.
T
h
e
r
esu
lts
o
f
th
e
n
aiv
e
B
ay
es
class
if
icati
o
n
m
o
d
el
test
ca
n
b
e
s
ee
n
in
T
ab
le
2
,
wh
ich
u
s
es
im
b
alan
ce
d
d
ata
,
an
d
T
ab
le
3
,
wh
ich
u
s
es
b
alan
ce
d
d
ata.
T
h
e
r
esu
lts
o
f
two
test
s
with
d
if
f
er
en
t
d
ata
g
a
v
e
ex
ce
llen
t
F1
-
s
co
r
e
ac
cu
r
ac
y
r
e
s
u
lts
.
T
h
e
test
r
esu
lt
s
u
s
in
g
im
b
alan
ce
d
d
ata
d
id
n
o
t p
r
o
v
id
e
g
o
o
d
class
if
icatio
n
r
esu
lts
,
an
d
n
o
ca
teg
o
r
y
lab
els
wer
e
d
etec
ted
c
o
r
r
ec
tly
.
T
h
e
test
r
esu
lt
u
s
in
g
b
alan
c
ed
d
ata
g
iv
es
g
o
o
d
class
if
icatio
n
r
esu
lts
an
d
co
r
r
e
ctly
d
etec
ts
ca
teg
o
r
y
lab
els
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
7
2
2
-
3
2
2
1
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
,
Vo
l.
6
,
No
.
2
,
J
u
ly
20
25
:
147
-
1
5
8
154
T
h
e
class
if
icatio
n
r
esu
lts
in
T
ab
le
2
s
h
o
w
th
e
im
p
ac
t
o
f
i
m
b
alan
ce
d
d
ata
o
n
m
o
d
el
p
e
r
f
o
r
m
a
n
ce
.
B
ased
o
n
th
e
class
if
icatio
n
r
e
s
u
lts
,
th
e
o
th
er
ca
teg
o
r
y
h
as
a
p
r
ec
is
io
n
v
al
u
e
o
f
0
.
9
4
,
a
r
ec
all
o
f
1
.
0
0
,
a
n
d
a
n
F1
-
s
co
r
e
o
f
0
.
9
6
,
with
th
e
to
t
al
d
ata
r
ea
ch
in
g
4
,
1
9
7
s
am
p
les.
T
h
is
s
u
g
g
ests
th
at
th
e
m
o
d
el
ten
d
s
to
class
if
y
m
o
s
t
o
f
th
e
d
ata
in
to
o
th
er
ca
teg
o
r
ies
ca
u
s
ed
b
y
u
n
b
ala
n
ce
d
d
ata.
I
n
co
n
tr
ast,
o
th
er
ca
teg
o
r
ies,
s
u
ch
as
m
an
ag
em
en
t
in
f
o
r
m
atio
n
s
y
s
tem
s
,
m
ar
k
etin
g
in
f
o
r
m
atio
n
s
y
s
tem
s
,
an
d
d
ec
is
io
n
s
u
p
p
o
r
t
s
y
s
tem
s
,
h
av
e
an
F1
s
co
r
e
o
f
0
.
0
0
,
in
d
icatin
g
th
at
th
e
m
o
d
el
ca
n
n
o
t
ea
s
ily
r
ec
o
g
n
ize
d
ata
i
n
th
o
s
e
ca
te
g
o
r
ies.
L
o
w
m
ac
r
o
av
er
ag
e
v
alu
es
in
clu
d
e
p
r
ec
is
i
o
n
0
.
1
1
,
r
ec
all
0
.
1
2
,
an
d
F1
-
s
co
r
e
0
.
1
2
.
I
t
s
h
o
ws
th
at
t
h
e
m
o
d
el
is
in
ac
cu
r
ate
in
class
if
y
in
g
class
es
with
a
f
e
w
s
am
p
les.
T
h
e
weig
h
ted
av
er
a
g
e
is
h
ig
h
er
b
ec
au
s
e
th
e
m
ajo
r
i
ty
class
in
f
lu
en
ce
s
it
.
Alth
o
u
g
h
t
h
e
m
o
d
el
h
as
a
n
o
v
er
all
ac
c
u
r
ac
y
o
f
0
.
9
4
,
th
is
v
alu
e
ca
n
n
o
t
i
n
d
icate
th
at
t
h
e
m
o
d
el
class
if
ies
well
d
u
e
to
r
ef
r
ac
tio
n
to
war
d
s
th
e
m
ajo
r
ity
class
.
T
o
im
p
r
o
v
e
th
e
m
o
d
el'
s
p
er
f
o
r
m
an
ce
in
cl
ass
if
y
in
g
m
in
o
r
ity
class
es,
s
tr
ateg
ies
s
u
ch
as
o
v
er
s
am
p
lin
g
ar
e
n
ee
d
ed
s
o
th
at
th
e
lab
els
o
f
class
ca
teg
o
r
ies
ar
e
m
o
r
e
b
ala
n
ce
d
an
d
th
e
class
if
icatio
n
r
esu
lts
ar
e
m
o
r
e
a
p
p
r
o
p
r
iate
.
T
ab
le
2
.
C
lass
if
icatio
n
r
esu
lts
u
s
in
g
im
b
alan
ce
d
d
ata
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
F1
-
s
c
o
r
e
S
u
p
p
o
r
t
O
t
h
e
r
0
.
9
4
1
.
0
0
0
.
9
6
4
,
1
9
7
C
u
s
t
o
mer r
e
l
a
t
i
o
n
s
h
i
p
ma
n
a
g
e
m
e
n
t
0
.
0
0
0
.
0
0
0
.
0
0
10
Ex
e
c
u
t
i
v
e
i
n
f
o
r
m
a
t
i
o
n
s
y
s
t
e
ms
0
.
0
0
0
.
0
0
0
.
0
0
3
F
i
n
a
n
c
i
a
l
i
n
f
o
r
ma
t
i
o
n
s
y
st
e
m
-
-
-
-
M
a
n
a
g
e
m
e
n
t
i
n
f
o
r
ma
t
i
o
n
s
y
st
e
ms
0
.
0
0
0
.
0
0
0
.
0
0
36
M
a
r
k
e
t
i
n
g
i
n
f
o
r
m
a
t
i
o
n
s
y
st
e
m
0
.
0
0
0
.
0
0
0
.
0
0
1
S
a
l
e
s
i
n
f
o
r
m
a
t
i
o
n
s
y
st
e
m
0
.
0
0
0
.
0
0
0
.
0
0
21
H
u
ma
n
r
e
s
o
u
r
c
e
i
n
f
o
r
m
a
t
i
o
n
s
y
st
e
ms
0
.
0
0
0
.
0
0
0
.
0
0
3
D
e
c
i
s
i
o
n
s
u
p
p
o
r
t
sy
s
t
e
m
0
.
0
0
0
.
0
0
0
.
0
0
1
8
7
A
c
c
u
r
a
c
y
0
.
9
4
4
,
4
5
8
M
a
c
r
o
a
v
g
0
.
1
1
0
.
1
2
0
.
1
2
4
,
4
5
8
W
e
i
g
h
t
e
d
a
v
g
0
.
8
8
0
.
9
4
0
.
9
1
4
,
4
5
8
T
ab
le
3
.
C
lass
if
icatio
n
r
esu
lts
u
s
in
g
b
alan
ce
d
d
ata
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
F1
-
s
c
o
r
e
S
u
p
p
o
r
t
O
t
h
e
r
0
.
9
8
0
.
8
5
0
.
9
1
4
,
1
2
5
C
u
s
t
o
mer r
e
l
a
t
i
o
n
s
h
i
p
ma
n
a
g
e
m
e
n
t
0
.
9
9
1
.
0
0
1
.
0
0
4
,
2
1
1
Ex
e
c
u
t
i
v
e
i
n
f
o
r
m
a
t
i
o
n
s
y
s
t
e
ms
1
.
0
0
1
.
0
0
1
.
0
0
4
,
1
0
2
F
i
n
a
n
c
i
a
l
i
n
f
o
r
ma
t
i
o
n
s
y
st
e
m
1
.
0
0
1
.
0
0
1
.
0
0
4
,
2
3
5
M
a
n
a
g
e
m
e
n
t
i
n
f
o
r
ma
t
i
o
n
s
y
st
e
ms
0
.
9
4
1
.
0
0
0
.
9
7
4
,
2
0
7
M
a
r
k
e
t
i
n
g
i
n
f
o
r
m
a
t
i
o
n
s
y
st
e
m
1
.
0
0
1
.
0
0
1
.
0
0
4
,
1
2
4
S
a
l
e
s
i
n
f
o
r
m
a
t
i
o
n
s
y
st
e
m
0
.
9
7
1
.
0
0
0
.
9
9
4
,
2
0
6
H
u
ma
n
r
e
s
o
u
r
c
e
i
n
f
o
r
m
a
t
i
o
n
s
y
st
e
ms
1
.
0
0
1
.
0
0
1
.
0
0
4
,
2
4
8
D
e
c
i
s
i
o
n
s
u
p
p
o
r
t
sy
s
t
e
m
0
.
9
5
0
.
9
8
0
.
9
6
4
,
1
8
8
A
c
c
u
r
a
c
y
0
.
9
8
3
7
,
6
4
6
M
a
c
r
o
a
v
g
0
.
9
8
0
.
9
8
0
.
9
8
3
7
,
6
4
6
W
e
i
g
h
t
e
d
a
v
g
0
.
9
8
0
.
9
8
0
.
9
8
3
7
,
6
4
6
T
h
e
class
if
icatio
n
r
esu
lts
ill
u
s
tr
ated
in
T
ab
le
3
s
h
o
w
th
e
class
if
icatio
n
r
esu
lts
o
b
tain
ed
u
s
in
g
b
alan
ce
d
d
ata,
n
a
m
ely
ca
teg
o
r
y
lab
el
d
ata
th
at
h
as
b
ee
n
b
al
an
ce
d
u
s
in
g
R
OS.
T
h
e
m
o
d
el'
s
p
er
f
o
r
m
an
ce
was
ev
alu
ated
b
ased
o
n
t
h
r
ee
p
r
im
ar
y
m
ea
s
u
r
em
en
ts
:
p
r
ec
is
io
n
,
r
ec
all
,
an
d
F1
-
Sco
r
e
,
wh
ic
h
s
h
o
wed
t
h
e
ac
c
u
r
ac
y
an
d
co
n
s
is
ten
cy
o
f
th
e
m
o
d
e
l
in
class
if
y
in
g
d
ata.
T
h
e
an
aly
s
is
r
esu
lts
s
h
o
w
th
at
alm
o
s
t
all
cla
s
s
es
h
av
e
p
r
ec
is
io
n
an
d
r
ec
all
ab
o
v
e
0
.
9
4
,
a
n
d
t
h
e
m
o
d
el
ca
n
p
e
r
f
o
r
m
class
if
icatio
n
with
m
in
im
al
er
r
o
r
r
ate,
w
ith
o
u
t
r
ef
r
ac
tio
n
th
at
im
p
ac
ts
ce
r
tain
class
es.
T
h
e
o
v
er
all
Acc
u
r
a
cy
v
alu
e
r
ea
ch
e
d
0
.
9
8
,
in
d
icatin
g
th
e
m
o
d
el
h
as
ex
ce
llen
t
p
r
e
d
ictio
n
p
er
f
o
r
m
a
n
ce
.
T
h
e
m
ac
r
o
av
e
r
ag
e
a
n
d
weig
h
ted
av
e
r
ag
e
v
alu
es,
ea
ch
v
alu
ed
at
0
.
9
8
,
also
in
d
icate
th
e
m
o
d
el
h
as
a
b
ala
n
ce
d
p
er
f
o
r
m
a
n
ce
ac
r
o
s
s
ca
teg
o
r
ies.
T
h
u
s
,
c
o
r
r
ec
tly
ap
p
l
y
in
g
d
ata
b
ala
n
cin
g
c
an
im
p
r
o
v
e
th
e
m
o
d
el'
s
p
er
f
o
r
m
an
ce
co
m
p
ar
ed
to
th
e
im
b
alan
ce
d
d
ata
co
n
d
itio
n
,
w
h
e
r
e
s
o
m
e
ca
teg
o
r
ies
p
r
ev
io
u
s
ly
h
ad
a
lo
wer
F1
-
s
co
r
e.
T
h
ese
r
esu
lts
s
h
o
w
th
at
th
e
d
ata
b
alan
ci
n
g
s
tr
ateg
y
ca
n
r
ed
u
ce
r
e
f
r
ac
tio
n
in
class
if
icatio
n
an
d
im
p
r
o
v
e
ac
c
u
r
ac
y
.
T
h
e
co
n
f
u
s
io
n
m
atr
ix
r
esu
lts
f
r
o
m
th
e
class
if
icatio
n
m
o
d
el
test
u
s
in
g
n
aiv
e
B
ay
es
ar
e
s
h
o
wn
in
Fig
u
r
e
9
(
a)
co
n
f
u
s
io
n
m
atr
ix
with
im
b
alan
ce
d
d
ata
an
d
Fig
u
r
e
9
(
b
)
co
n
f
u
s
io
n
m
atr
ix
with
b
alan
ce
d
d
a
ta
.
Fig
u
r
e
9
(
a)
s
h
o
ws
th
at
th
e
m
o
d
el
ten
d
s
to
class
if
y
d
ata
in
t
o
o
n
ly
o
n
e
d
o
m
in
a
n
t
ca
teg
o
r
y
,
with
m
an
y
o
th
er
class
es
h
av
in
g
a
n
ea
r
-
ze
r
o
p
r
e
d
ictio
n
co
u
n
t.
T
h
is
s
h
o
ws
th
at
th
e
m
o
d
el
is
b
iased
to
war
d
s
th
e
m
ajo
r
ity
class
,
s
o
it
ca
n
n
o
t
r
ec
o
g
n
ize
th
e
p
atter
n
s
o
f
th
e
m
in
o
r
it
y
class
es
well.
Fig
u
r
e
9
(
b
)
o
f
th
e
co
n
f
u
s
io
n
m
atr
ix
f
o
r
b
alan
ce
d
d
ata
s
h
o
ws
a
m
o
r
e
e
v
en
d
is
tr
ib
u
tio
n
o
f
p
r
e
d
ictio
n
s
alo
n
g
th
e
d
iag
o
n
al
o
f
t
h
e
m
at
r
ix
.
T
h
e
m
o
d
el
ca
n
class
if
y
s
am
p
les
in
to
ap
p
r
o
p
r
i
ate
class
es
with
f
ewe
r
er
r
o
r
s
.
A
co
m
p
ar
is
o
n
o
f
th
ese
two
m
atr
i
ce
s
s
h
o
ws
th
at
Evaluation Warning : The document was created with Spire.PDF for Python.
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
I
SS
N:
2722
-
3
2
2
1
C
la
s
s
i
fica
tio
n
a
n
d
s
imila
r
ity
d
etec
tio
n
o
f I
n
d
o
n
esia
n
s
cien
tifi
c
jo
u
r
n
a
l
…
(
N
yima
s
S
a
b
ilin
a
C
a
h
ya
n
i
)
155
r
elev
an
t
d
ata
b
alan
ci
n
g
im
p
r
o
v
es
m
o
d
el
p
er
f
o
r
m
a
n
ce
b
y
r
e
d
u
cin
g
b
ias
ag
ain
s
t
m
ajo
r
ity
c
lass
es
an
d
en
ab
lin
g
m
o
r
e
ac
cu
r
ate
class
if
icatio
n
ac
r
o
s
s
ca
teg
o
r
ies
.
(
a)
(
b
)
Fig
u
r
e
9
.
C
o
n
f
u
s
io
n
m
atr
i
x
f
o
r
(
a)
im
b
ala
n
ce
d
d
ata
an
d
(
b
)
b
alan
ce
d
d
ata
3.
2.
Art
icle
s
im
ila
rit
y
det
ec
t
io
n us
in
g
C
o
s
i
ne
Sim
ila
rit
y
T
h
is
p
r
o
ce
s
s
d
etec
ts
s
im
ilar
it
ies
u
s
in
g
th
e
titl
e
an
d
ab
s
tr
a
ct
o
f
Ar
ticle
1
a
n
d
Ar
ticle
2
.
Af
ter
th
e
ex
p
er
im
en
t,
th
e
s
im
ilar
ity
d
ete
ctio
n
s
co
r
e
was
o
b
tain
ed
as
0
.
0
7
1
,
s
h
o
wn
i
n
T
ab
le
4
.
T
ab
le
4
s
h
o
ws
th
e
r
esu
lts
o
f
th
e
s
im
ilar
ity
d
etec
tio
n
an
aly
s
is
b
etwe
en
two
ar
tic
les
b
as
ed
o
n
th
e
ca
lcu
latio
n
o
f
s
im
ilar
ity
s
co
r
es.
Ar
ticle
1
is
titl
ed
"
W
eb
-
b
ased
d
ec
is
i
o
n
s
u
p
p
o
r
t
s
y
s
tem
ass
es
s
m
en
t
.
.
.
"
wh
ich
f
o
c
u
s
es
o
n
th
e
im
p
lem
en
tatio
n
o
f
a
d
ec
is
io
n
s
u
p
p
o
r
t sy
s
tem
in
th
e
co
n
tex
t o
f
ass
ess
m
en
t in
a
v
illag
e,
wh
ile
Ar
ticle
2
is
en
titl
ed
"De
s
ig
n
an
d
b
u
ild
au
to
m
atic
b
o
ttle
f
illi
n
g
an
d
ca
p
p
in
g
s
y
s
tem
b
ased
o
n
b
o
ttle
h
eig
h
t
.
.
.
"
wh
ich
d
is
cu
s
s
es
au
to
m
atio
n
s
y
s
tem
s
in
th
e
m
an
u
f
ac
tu
r
in
g
in
d
u
s
tr
y
.
T
h
e
ca
lcu
l
atio
n
r
esu
lts
s
h
o
wed
th
at
th
e
s
im
ilar
ity
s
co
r
e
b
etwe
en
th
e
two
a
r
ticles
was
0
.
0
7
1
,
wh
ich
in
d
icate
s
a
v
er
y
lo
w
lev
el
o
f
s
im
ilar
i
ty
.
T
h
is
v
alu
e
in
d
icate
s
th
at
th
e
two
ar
ticles
s
ig
n
if
ican
tly
d
if
f
er
in
to
p
ic,
ter
m
in
o
lo
g
y
,
an
d
co
n
ten
t.
T
h
u
s
,
th
e
s
im
ilar
ity
d
ete
ctio
n
m
eth
o
d
is
p
r
o
v
e
n
to
d
is
tin
g
u
is
h
ar
ticles
with
d
if
f
er
en
t
to
p
ics
well.
B
ased
o
n
a
s
im
ilar
ity
s
co
r
e
r
an
g
e
o
f
0
to
1
,
p
r
o
v
id
e
a
g
o
o
d
s
co
r
e
to
d
etec
t
a
r
ticle
s
im
ilar
ities
.
I
n
th
is
r
esear
ch
,
th
e
h
i
g
h
est
s
co
r
e
was
u
s
ed
t
o
o
b
ta
in
an
ac
cu
r
ate
an
d
r
elev
an
t a
r
t
icle
ac
co
r
d
in
g
t
o
th
e
r
esear
ch
to
p
ic
.
T
ab
le
4
.
Similar
ity
d
etec
tio
n
r
esu
lts
A
r
t
i
c
l
e
Ti
t
l
e
B
r
i
e
f
a
b
s
t
r
a
c
t
1
W
e
b
-
b
a
se
d
d
e
c
i
s
i
o
n
su
p
p
o
r
t
s
y
st
e
m a
ssessme
n
t
.
.
.
P
r
i
n
g
sari
V
i
l
l
a
g
e
i
s
o
n
e
o
f
t
h
e
v
i
l
l
a
g
e
s
i
n
t
h
e
su
b
-
d
i
s
t
r
i
c
t
.
.
.
.
W
h
e
r
e
i
s
e
a
c
h
v
i
l
l
a
g
e
...
2
D
e
si
g
n
a
n
d
b
u
i
l
d
a
u
t
o
ma
t
i
c
b
o
t
t
l
e
f
i
l
l
i
n
g
a
n
d
c
a
p
p
i
n
g
s
y
s
t
e
ms
b
a
se
d
o
n
b
o
t
t
l
e
h
e
i
g
h
t
.
.
.
To
d
a
y
's
i
n
d
u
st
r
i
a
l
w
o
r
l
d
c
a
n
n
o
l
o
n
g
e
r
b
e
s
e
p
a
r
a
t
e
d
b
y
t
h
e
p
r
o
b
l
e
m
o
f
a
u
t
o
ma
t
i
o
n
f
o
r
v
a
r
i
o
u
s
p
r
o
d
u
c
t
i
o
n
f
a
c
i
l
i
t
i
e
s
. …
S
c
o
r
e
c
o
si
n
e
si
m
i
l
a
r
i
t
y
0
.
0
7
1
3.
3.
Art
icle
s
ea
rc
h us
ing
c
o
s
ine
s
im
ila
rit
y
T
h
is
p
r
o
ce
s
s
s
ea
r
ch
es
f
o
r
s
cien
tific
ar
ticles
th
at
ar
e
s
im
ilar
t
o
th
e
m
ai
n
ar
ticle
b
ased
o
n
th
e
titl
e
an
d
ab
s
tr
ac
t
th
at
h
a
v
e
b
ee
n
c
o
n
ca
ten
ated
.
T
h
e
v
al
u
e
r
a
n
g
e
is
0
to
1
.
T
h
e
r
esu
lts
o
f
th
e
s
ea
r
ch
d
is
p
lay
a
tab
le
co
n
tain
in
g
th
e
c
o
lu
m
n
s
g
a
r
u
d
a
titl
e,
g
ar
u
d
a
ab
s
tr
ac
t,
s
im
ilar
ity
s
co
r
e,
ca
teg
o
r
y
,
an
d
p
r
e
d
icted
ca
teg
o
r
y
.
T
h
e
p
r
ed
icted
ca
teg
o
r
y
is
th
e
wr
o
n
g
ca
teg
o
r
y
lab
el
co
lu
m
n
in
class
if
y
in
g
th
e
ca
teg
o
r
y
,
as sh
o
w
n
in
Fig
u
r
e
10
.
T
h
e
s
ea
r
ch
r
esu
lts
o
f
ar
ticles
i
n
Fig
u
r
e
10
s
h
o
w
th
e
r
esu
lts
o
f
th
e
s
im
ilar
ity
s
co
r
e
ca
lcu
latio
n
,
w
h
er
e
th
e
ar
ticle
with
th
e
h
ig
h
est
s
co
r
e
h
as
t
h
e
m
o
s
t
s
ig
n
if
ica
n
t
le
v
el
o
f
s
im
ilar
ity
with
th
e
m
ain
ar
ticle.
T
h
e
ar
ticle
with
th
e
h
ig
h
est
s
im
ilar
ity
s
c
o
r
e
is
p
lace
d
f
ir
s
t
in
th
e
s
ea
r
ch
r
esu
lts
.
T
h
is
p
r
o
ce
s
s
co
m
p
ar
es
th
e
s
ea
r
ch
tex
t
with
th
e
titl
e
an
d
a
b
s
tr
ac
t
f
r
o
m
th
e
a
v
ailab
le
d
ataset.
Nex
t,
th
e
s
ea
r
ch
r
esu
lts
ar
e
s
o
r
te
d
b
y
s
im
ilar
ity
s
co
r
e
i
n
d
escen
d
in
g
o
r
d
e
r
s
o
th
at
th
e
m
o
s
t
co
m
m
o
n
d
o
c
u
m
en
ts
ap
p
ea
r
f
ir
s
t.
T
h
e
r
esu
lts
o
f
th
is
s
tu
d
y
s
h
o
w
th
at
t
h
e
to
p
f
iv
e
d
o
c
u
m
en
ts
h
av
e
th
e
h
ig
h
e
s
t le
v
el
o
f
s
im
ilar
ity
to
th
e
k
e
y
wo
r
d
s
o
f
web
-
b
ased
d
ec
is
io
n
s
u
p
p
o
r
t sy
s
tem
s
.
T
h
ese
r
esu
lts
ar
e
d
is
p
lay
ed
i
n
a
tab
le
t
h
at
in
clu
d
es
th
e
ti
tle
co
lu
m
n
s
,
a
b
s
tr
ac
t,
s
im
ilar
ity
s
co
r
e,
o
r
ig
in
al
ca
teg
o
r
y
,
an
d
p
r
e
d
icted
ca
teg
o
r
y
.
T
h
e
s
im
ilar
ity
s
co
r
e
o
b
tain
e
d
r
an
g
ed
f
r
o
m
0
.
3
9
to
0
.
2
6
,
wh
ic
h
in
d
icate
s
a
d
i
f
f
er
en
ce
in
th
e
le
v
el
o
f
s
im
ilar
ity
o
f
d
o
cu
m
en
ts
.
T
h
e
o
r
i
g
in
al
a
n
d
p
r
e
d
icted
c
ateg
o
r
ies
s
h
o
wed
a
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
7
2
2
-
3
2
2
1
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
,
Vo
l.
6
,
No
.
2
,
J
u
ly
20
25
:
147
-
1
5
8
156
r
ea
s
o
n
ab
ly
h
ig
h
m
atch
,
in
d
icat
in
g
th
at
th
e
m
o
d
el
ca
n
r
ec
o
g
n
i
ze
an
d
g
r
o
u
p
d
o
cu
m
e
n
ts
q
u
ite
well
b
ased
o
n
tex
t
s
im
ilar
ity
an
aly
s
is
.
Fig
u
r
e
10
.
Ar
ticle
s
ea
r
ch
r
esu
l
ts
T
ab
le
5
.
Ar
ticle
s
ea
r
ch
r
esu
lts
G
A
R
U
D
A
_
TI
TLE
G
A
R
U
D
A
_
A
B
S
T
R
A
C
T
S
I
M
I
LA
R
I
TY
_
S
C
O
R
E
C
A
TEG
O
R
Y
C
A
TEG
O
R
Y
_
P
R
ED
I
C
TED
0
D
e
c
i
s
i
o
n
s
u
p
p
o
r
t
sy
s
t
e
m
f
o
r
r
e
c
i
p
i
e
n
t
s
e
l
e
c
t
i
o
n
…
D
e
c
i
s
i
o
n
s
u
p
p
o
r
t
sy
s
t
e
m
a
s
a
sy
st
e
m…
0.
3
9
1
5
9
6
D
e
c
i
s
i
o
n
s
u
p
p
o
r
t
sy
st
e
m
D
e
c
i
s
i
o
n
s
u
p
p
o
r
t
sy
st
e
m
1
D
e
c
i
s
i
o
n
s
u
p
p
o
r
t
sy
s
t
e
m
f
o
r
n
e
w
s
t
u
d
e
n
t
a
d
m
i
ssi
o
n
…
A
d
e
c
i
s
i
o
n
s
u
p
p
o
r
t
sy
s
t
e
m
i
s
a
sy
st
e
m…
0.
2
9
5
9
6
7
D
e
c
i
s
i
o
n
s
u
p
p
o
r
t
sy
st
e
m
D
e
c
i
s
i
o
n
s
u
p
p
o
r
t
sy
st
e
m
2
D
e
c
i
s
i
o
n
s
u
p
p
o
r
t
sy
s
t
e
m
f
o
r
e
mp
l
o
y
e
e
r
e
c
r
u
i
t
m
e
n
t
…
C
u
r
r
e
n
t
i
n
f
o
r
m
a
t
i
o
n
t
e
c
h
n
o
l
o
g
y
d
e
v
e
l
o
p
m
e
n
t
s…
0.
2
7
5
6
7
9
D
e
c
i
s
i
o
n
s
u
p
p
o
r
t
sy
st
e
m
D
e
c
i
s
i
o
n
s
u
p
p
o
r
t
sy
st
e
m
3
D
e
c
i
s
i
o
n
s
u
p
p
o
r
t
sy
s
t
e
m
f
o
r
r
e
st
a
u
r
a
n
t
sel
e
c
t
i
o
n
…
Th
e
a
b
st
r
a
c
t
o
f
t
h
i
s r
e
se
a
r
c
h
a
i
ms
t
o
h
e
l
p
…
0.
2
6
9
3
1
4
D
e
c
i
s
i
o
n
s
u
p
p
o
r
t
sy
st
e
m
D
e
c
i
s
i
o
n
s
u
p
p
o
r
t
sy
st
e
m
4
D
e
c
i
s
i
o
n
s
u
p
p
o
r
t
sy
s
t
e
m
f
o
r
e
mp
l
o
y
e
e
p
e
r
f
o
r
m
a
n
c
e
e
v
a
l
u
a
t
i
o
n
…
Emp
l
o
y
e
e
p
e
r
f
o
r
m
a
n
c
e
e
v
a
l
u
a
t
i
o
n
d
e
c
i
si
o
n
s
u
p
p
o
r
t
sy
st
e
m…
0.
2
6
7
9
5
9
D
e
c
i
s
i
o
n
s
u
p
p
o
r
t
sy
st
e
m
D
e
c
i
s
i
o
n
s
u
p
p
o
r
t
sy
st
e
m
4.
CO
NCLU
SI
O
N
T
h
e
n
aiv
e
B
ay
es
m
eth
o
d
u
s
ed
f
o
r
class
if
icatio
n
p
r
o
v
i
d
es
a
g
o
o
d
le
v
el
o
f
F1
-
s
co
r
e
ac
c
u
r
ac
y
b
y
u
s
in
g
b
alan
ce
d
d
ata
o
f
9
8
%
an
d
im
b
alan
ce
d
d
ata
o
f
9
4
%.
T
h
e
cl
ass
if
icatio
n
p
r
o
ce
s
s
tak
es
les
s
th
an
6
0
m
in
u
tes
to
p
r
o
ce
s
s
an
d
class
if
y
th
e
ar
ticle
ca
teg
o
r
ies.
T
h
e
co
s
in
e
s
im
ilar
ity
m
eth
o
d
u
s
ed
f
o
r
s
im
ilar
ity
d
etec
tio
n
an
d
s
ea
r
ch
f
o
r
th
e
m
ain
ar
ticle
with
o
th
er
ar
ticles
g
av
e
a
g
o
o
d
s
im
ilar
ity
d
etec
tio
n
s
co
r
e
o
f
0
.
0
7
1
.
I
n
co
n
tr
ast,
a
s
im
ilar
ity
s
co
r
e
clo
s
e
t
o
1
in
d
icate
s
a
h
ig
h
er
s
im
ilar
ity
in
s
ea
r
ch
in
g
f
o
r
a
r
ticles
r
elev
a
n
t
to
th
e
s
p
ec
if
ie
d
r
esear
ch
to
p
ic
.
Sear
ch
es
f
o
r
s
cien
tific
ar
ticles
th
at
ar
e
s
im
i
lar
to
th
e
m
ain
ar
ticle
p
r
o
v
id
e
ex
ce
llen
t
s
ea
r
ch
r
esu
lts
.
T
h
e
r
esear
ch
r
esu
lts
s
h
o
w
th
at
th
e
p
r
o
p
o
s
ed
m
eth
o
d
s
ig
n
if
ican
tly
im
p
r
o
v
es
th
e
class
if
icatio
n
an
d
s
ea
r
ch
p
r
o
ce
s
s
es
in
GARUDA,
an
d
p
r
o
v
id
es
ac
cu
r
ate
an
d
ef
f
icien
t
s
im
ilar
ity
d
etec
tio
n
.
Fu
r
th
er
r
esear
ch
ca
n
b
e
d
ev
el
o
p
ed
b
y
ad
d
in
g
m
o
r
e
d
atasets
in
th
e
s
cien
tific
f
ie
ld
,
n
o
t
o
n
ly
in
t
h
e
I
n
d
o
n
esia
n
lan
g
u
ag
e,
a
n
d
b
y
ap
p
ly
in
g
f
ea
tu
r
es
to
f
in
d
ar
ticl
es si
m
ilar
to
th
e
GARUDA
.
ACK
NO
WL
E
DG
M
E
N
T
S
T
h
e
au
th
o
r
s
wo
u
ld
lik
e
to
th
a
n
k
th
e
C
o
m
n
ets
R
esear
ch
Gr
o
u
p
,
Un
iv
er
s
ity
o
f
Sriwijay
a,
I
n
d
o
n
esia
f
o
r
p
r
o
v
id
i
n
g
f
u
ll su
p
p
o
r
t f
o
r
th
eir
r
esear
ch
n
ec
ess
ar
y
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
Au
th
o
r
s
s
tate
n
o
f
u
n
d
in
g
in
v
o
lv
ed
.
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
T
h
is
jo
u
r
n
al
u
s
es
th
e
C
o
n
t
r
ib
u
to
r
R
o
les
T
a
x
o
n
o
m
y
(
C
R
ed
iT)
to
r
ec
o
g
n
ize
in
d
iv
i
d
u
al
au
th
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
th
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
llab
o
r
atio
n
.
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
Ny
im
as Sab
ilin
a
C
ah
y
an
i
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Der
is
Sti
awa
n
✓
✓
✓
✓
✓
✓
Ab
d
ian
s
ah
Ab
d
ian
s
ah
✓
✓
✓
✓
✓
✓
Nu
r
u
l A
f
if
ah
✓
✓
✓
✓
✓
✓
Den
d
i Ren
ald
o
Per
m
an
a
✓
✓
✓
✓
✓
✓
Evaluation Warning : The document was created with Spire.PDF for Python.