I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
p
u
t
er
Science
Vo
l.
1
2
,
No
.
1
,
Octo
b
er
201
8
,
p
p
.
1
5
5
~
1
6
0
I
SS
N:
2502
-
4752
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ee
cs
.
v
1
2
.i
1
.
p
p
155
-
1
6
0
155
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
co
r
e.
co
m/jo
u
r
n
a
ls
/in
d
ex
.
p
h
p
/
ijeec
s
Neig
hbo
r Weigh
t
ed K
-
Nea
res
t
Nei
g
hbo
r f
o
r Sa
m
ba
t
O
nlin
e
Cla
ss
ificatio
n
Anni
s
y
a
April
ia
P
ra
s
a
nti,
M
.
Ali F
a
uzi,
M
.
T
a
nzil F
urqo
n
F
a
c
u
lt
y
o
f
Co
m
p
u
ter S
c
ien
c
e
,
Bra
w
ij
a
y
a
Un
iv
e
rsit
y
,
M
a
lan
g
,
In
d
o
n
e
sia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Ma
y
6
,
2
0
1
8
R
ev
i
s
ed
Ma
y
2
9
,
2
0
1
8
A
cc
ep
ted
J
u
n
1
6
,
2
0
1
8
S
a
m
b
a
t
On
li
n
e
is
o
n
e
o
f
th
e
i
m
p
l
e
m
e
n
tatio
n
o
f
E
-
G
o
v
e
rn
m
e
n
t
f
o
r
c
o
m
p
lain
ts
m
a
n
a
g
e
m
e
n
t
p
ro
v
id
e
d
b
y
M
a
lan
g
Cit
y
G
o
v
e
rn
m
e
n
t.
A
ll
o
f
th
e
c
o
m
p
lain
ts
w
il
l
b
e
c
las
sif
ied
in
to
it
s
in
ten
d
e
d
d
e
p
a
rtm
e
n
t.
In
th
is
stu
d
y
,
a
u
to
m
a
ti
c
c
o
m
p
lain
t
c
las
sif
ic
a
ti
o
n
sy
ste
m
u
sin
g
Ne
ig
h
b
o
r
W
e
ig
h
ted
K
-
Ne
a
re
st
Ne
ig
h
b
o
r
(NW
-
KN
N)
is
p
o
p
o
se
d
b
e
c
a
u
se
S
a
m
b
a
t
On
li
n
e
h
a
s
im
b
a
lan
c
e
d
d
a
ta.
T
h
e
s
y
ste
m
d
e
v
e
lo
p
e
d
is
c
o
m
p
o
se
d
o
f
th
re
e
m
a
jo
r
p
h
a
se
s
in
c
lu
d
i
n
g
p
re
p
ro
c
e
ss
in
g
,
N
-
G
ra
m
f
e
a
tu
re
e
x
trac
ti
o
n
,
a
n
d
c
las
sif
ic
a
ti
o
n
u
s
in
g
NW
-
KN
N.
Ba
se
d
o
n
t
h
e
e
x
p
e
rim
e
n
t
r
e
su
lt
s,
it
c
a
n
b
e
re
su
m
e
d
th
a
t
th
e
NW
-
KN
N
a
lg
o
rit
h
m
is
a
b
le
to
c
las
sify
th
e
i
m
b
a
lan
c
e
d
d
a
ta
w
e
ll
w
it
h
th
e
m
o
st
o
p
ti
m
a
l
k
-
n
e
ig
h
b
o
r
v
a
lu
e
is
3
a
n
d
u
n
ig
ra
m
a
s
th
e
b
e
st
f
e
a
tu
re
s
b
y
7
7
.
8
5
%
p
re
c
isio
n
,
7
4
.
1
8
%
re
c
a
ll
,
a
n
d
7
5
.
2
5
%
f
-
m
e
a
su
re
v
a
lu
e
.
Co
m
p
a
re
d
to
th
e
c
o
n
v
e
n
ti
o
n
a
l
KN
N,
NW
-
KN
N
a
lg
o
rit
h
m
a
lso
p
ro
v
e
d
to
b
e
b
e
tt
e
r
f
o
r
im
b
a
lan
c
e
d
d
a
ta
p
ro
b
lem
s
w
it
h
v
e
r
y
slig
h
t
d
iff
e
re
n
c
e
s.
K
ey
w
o
r
d
s
:
T
ex
t Cl
ass
i
f
icat
io
n
Sa
m
b
at
O
n
li
n
e
N
-
Gr
a
m
NW
-
KNN
Neig
h
b
o
r
W
eig
h
ted
K
-
Nea
r
e
s
t
Neig
h
b
o
r
.
Co
p
y
rig
h
t
©
2
0
1
8
In
stit
u
te o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts
re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
M.
A
li Fa
u
zi
Facu
lt
y
o
f
C
o
m
p
u
ter
Scien
ce
,
B
r
a
w
ij
ay
a
U
n
i
v
er
s
it
y
,
Ma
lan
g
,
I
n
d
o
n
esia.
E
-
m
a
il:
m
o
c
h
.
ali.
f
au
zi
@
u
b
.
ac
.
id
1.
I
NT
RO
D
UCT
I
O
N
E
lectr
o
n
ic
g
o
v
er
n
m
e
n
t
(
e
-
g
o
v
er
n
m
e
n
t)
h
as
b
ec
o
m
e
a
n
e
m
er
g
i
n
g
tr
e
n
d
f
o
r
th
e
p
ast
t
w
o
d
ec
ad
es.
No
w
ad
a
y
s
,
e
-
g
o
v
er
n
m
e
n
t
is
n
o
t
li
m
ited
to
th
e
d
ev
elo
p
ed
co
u
n
tr
ie
s
.
T
h
er
e
ar
e
s
o
m
e
i
n
n
o
v
ativ
e
e
-
g
o
v
er
n
m
en
t
ap
p
licatio
n
in
th
e
d
ev
elo
p
in
g
co
u
n
tr
ies,
as
I
C
T
s
ar
e
b
ein
g
g
r
o
w
i
n
g
l
y
u
s
ed
b
y
g
o
v
er
n
m
en
t
an
d
co
n
n
ec
t
it
m
o
r
e
c
l
o
s
el
y
w
it
h
t
h
eir
cit
ize
n
s
.
W
it
h
t
h
e
ap
p
licatio
n
o
f
e
-
g
o
v
er
n
m
e
n
t,
t
w
o
-
w
a
y
co
m
m
u
n
ica
tio
n
b
et
w
ee
n
citizen
s
an
d
g
o
v
er
n
m
e
n
t
ca
n
b
e
d
ev
elo
p
ed
ea
s
il
y
.
C
itizen
s
ca
n
co
n
v
e
y
th
e
ir
asp
ir
atio
n
,
c
r
itics
,
o
r
o
p
in
io
n
to
th
e
g
o
v
er
n
m
en
t
w
ith
o
u
t
an
y
d
if
f
icu
lties
[
1
]
.
SA
MB
A
T
On
li
n
e
is
o
n
e
o
f
t
h
e
i
m
p
le
m
en
tati
o
n
o
f
e
-
g
o
v
er
n
m
e
n
t
p
r
o
v
id
ed
b
y
Di
s
k
o
m
i
n
f
o
(
C
o
m
m
u
n
icatio
n
an
d
I
n
f
o
r
m
ati
o
n
Dep
ar
t
m
e
n
t)
o
f
Ma
lan
g
cit
y
g
o
v
er
n
m
en
t.
S
A
MB
A
T
On
li
n
e
is
an
ap
p
licatio
n
f
o
r
co
m
p
lai
n
t
s
y
s
te
m
th
at
en
ab
le
p
eo
p
le
o
f
Ma
lan
g
cit
y
to
ex
p
r
ess
th
ei
r
o
p
in
io
n
s
,
s
u
g
g
esti
o
n
s
,
cr
itic
i
s
m
s
,
q
u
e
s
tio
n
s
o
r
co
m
p
lai
n
t
s
ab
o
u
t
t
h
e
p
er
f
o
r
m
an
ce
o
f
p
u
b
lic
f
ac
i
liti
e
s
o
r
s
er
v
ices
h
eld
b
y
t
h
e
g
o
v
er
n
m
en
t.
F
u
r
th
er
m
o
r
e,
Di
s
k
o
m
i
n
f
o
w
il
l
v
er
i
f
y
an
d
ac
ce
p
t
all
i
n
c
o
m
in
g
co
m
p
lai
n
t
s
.
T
h
ey
al
s
o
h
av
e
to
s
o
r
t
an
d
cl
ass
i
f
y
t
h
e
co
m
p
lai
n
ts
b
ased
o
n
th
e
i
n
te
n
d
ed
d
ep
ar
tm
en
t
m
a
n
u
al
l
y
.
Ob
v
io
u
s
l
y
,
w
it
h
th
e
lar
g
e
n
u
m
b
er
o
f
in
co
m
i
n
g
co
m
p
lai
n
ts
,
t
h
is
p
r
o
ce
s
s
is
e
x
p
en
s
i
v
e
a
n
d
ta
k
es
a
lo
t
o
f
ti
m
e.
He
n
ce
,
a
n
au
to
m
at
ic
co
m
p
lai
n
ts
cla
s
s
i
f
ic
atio
n
is
r
eq
u
ir
ed
.
Sa
m
b
at
On
lin
e
clas
s
i
f
icatio
n
ca
n
b
e
co
n
s
id
er
ed
as
to
p
ica
l
tex
t
class
i
f
icat
io
n
.
Var
io
u
s
tr
ad
itio
n
al
m
ac
h
in
e
lear
n
in
g
m
e
th
o
d
s
h
av
e
b
ee
n
ap
p
lied
to
s
o
lv
e
th
is
p
r
o
b
lem
s
u
ch
as
Naï
v
e
B
a
y
es
[
2
-
6
]
,
Su
p
p
o
r
t
Vec
to
r
Ma
ch
in
e
s
[
7
-
8
]
.
K
-
N
ea
r
est
Neig
h
b
o
r
s
[
9
-
1
2
]
,
Neu
r
al
Net
w
o
r
k
[
1
3
-
1
4
]
.
T
h
ese
m
et
h
o
d
s
h
a
v
e
b
ee
n
s
h
o
w
n
to
p
r
o
v
id
e
e
x
ce
lle
n
t
p
er
f
o
r
m
a
n
ce
in
tex
t
clas
s
i
f
ic
atio
n
.
Ho
w
e
v
er
,
Sa
m
b
at
o
n
l
in
e
d
atase
t
is
a
n
i
m
b
alan
ce
d
d
ata.
T
h
e
p
er
f
o
r
m
an
ce
o
f
th
e
s
e
m
e
th
o
d
s
h
a
s
en
co
u
n
ter
ed
a
s
ig
n
i
f
ican
t
d
r
aw
b
ac
k
w
h
e
n
d
ea
lin
g
w
it
h
i
m
b
ala
n
ce
d
d
ata
[
1
5
-
1
6
]
.
T
h
e
i
m
b
ala
n
ce
d
ata
is
s
u
e
r
is
e
s
f
r
eq
u
en
t
l
y
i
n
cl
u
s
ter
i
n
g
an
d
class
i
f
ica
tio
n
s
ce
n
ar
io
s
w
h
e
n
th
e
a
m
o
u
n
t o
f
d
ata
w
it
h
a
p
ar
ticu
lar
cla
s
s
i
s
m
u
c
h
m
o
r
e
th
a
n
t
h
e
d
ata
in
t
h
e
o
th
er
class
e
s
[
1
7
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l
.
1
2
,
No
.
1
,
Octo
b
er
201
8
:
1
5
5
–
160
156
T
r
a
d
itio
n
al
m
ac
h
in
e
lear
n
in
g
m
et
h
o
d
s
ten
d
to
b
e
f
lo
o
d
ed
b
y
t
h
e
m
aj
o
r
class
an
d
n
eg
lect
th
e
m
i
n
o
r
o
n
es
as
th
e
y
ar
e
ap
p
lied
to
s
u
ch
s
k
e
w
e
d
d
ata
[
1
8
]
.
On
e
o
f
th
e
i
m
p
r
o
v
ed
m
ac
h
i
n
e
lear
n
in
g
m
et
h
o
d
s
d
ev
o
ted
t
o
tack
le
t
h
e
is
s
u
e
o
f
i
m
b
a
lan
ce
d
d
ata
is
Neig
h
b
o
r
W
eig
h
ted
K
-
Nea
r
es
t
Neig
h
b
o
r
(
NW
-
KNN)
.
NW
-
KNN
is
an
i
m
p
r
o
v
ed
K
-
Nea
r
est
Neig
h
b
o
r
(
KNN)
m
et
h
o
d
p
r
o
p
o
s
ed
b
y
T
an
[
1
9
]
th
at
ad
d
in
g
a
w
ei
g
h
ti
n
g
s
tag
e
to
s
o
lv
e
i
m
b
a
lan
ce
d
d
ata
p
r
o
b
le
m
s
.
T
h
is
m
et
h
o
d
ass
i
g
n
s
a
s
m
all
w
ei
g
h
t
v
al
u
e
to
th
e
n
ei
g
h
b
o
r
s
co
m
i
n
g
f
r
o
m
th
e
m
aj
o
r
it
y
class
a
n
d
ass
i
g
n
s
a
lar
g
er
w
eig
h
t
v
alu
e
to
t
h
e
n
ei
g
h
b
o
r
s
f
r
o
m
m
i
n
o
r
it
y
cla
s
s
e
s
.
T
h
is
m
et
h
o
d
p
r
o
v
e
n
to
o
b
tain
s
ig
n
if
ican
t
i
m
p
r
o
v
ed
p
er
f
o
r
m
a
n
ce
o
n
i
m
b
ala
n
ce
d
d
ata.
I
n
th
is
s
tu
d
y
,
w
e
i
m
p
le
m
e
n
t
t
h
e
NW
-
KNN
m
et
h
o
d
f
o
r
Sam
b
at
On
lin
e
clas
s
i
f
icatio
n
.
W
e
u
s
e
co
s
i
n
e
s
i
m
ilar
it
y
f
o
r
m
ea
s
u
r
i
n
g
te
x
t
p
r
o
x
i
m
it
y
to
d
eter
m
i
n
e
n
ei
g
h
b
o
r
s
in
NW
-
KNN.
W
e
al
s
o
u
s
e
N
-
g
r
a
m
f
ea
t
u
r
es
to
i
m
p
r
o
v
e
t
h
e
p
er
f
o
r
m
a
n
ce
o
f
t
h
is
clas
s
i
f
icatio
n
m
et
h
o
d
d
u
e
to
it
s
p
r
o
m
is
in
g
p
er
f
o
r
m
a
n
ce
as
co
m
b
in
ed
w
it
h
co
s
in
e
s
i
m
ilar
it
y
[
2
0
]
.
B
y
ap
p
ly
in
g
th
e
NW
-
K
NN
m
et
h
o
d
s
u
p
p
o
r
ted
b
y
N
-
g
r
a
m
f
ea
t
u
r
e
ex
tr
ac
tio
n
,
i
t
i
s
ex
p
ec
ted
th
at
t
h
e
class
if
ica
tio
n
s
y
s
te
m
ca
n
h
a
n
d
le
th
e
i
m
b
al
an
ce
d
ata
class
i
f
icatio
n
p
r
o
b
lem
w
ell.
2.
RE
S
E
ARCH
M
E
T
H
O
D
As
d
ep
icted
in
Fi
g
u
r
e
1
,
Sa
m
b
at
On
li
n
e
clas
s
i
f
icatio
n
in
t
h
i
s
s
tu
d
y
is
co
m
p
s
ed
o
f
th
r
ee
m
aj
ir
p
h
ases
:
1
)
p
r
e
p
r
o
ce
s
s
in
g
; 2
)
N
-
g
r
a
m
f
ea
tu
r
e
ex
tr
ac
tio
n
; a
n
d
3
)
class
i
f
icatio
n
u
s
in
g
NW
-
KNN.
Fig
u
r
e
1
.
Sa
m
b
at
On
lin
e
C
las
s
if
icatio
n
S
y
s
te
m
Ma
i
n
Flo
w
c
h
ar
t
2
.
1
.
Do
cu
m
ent
P
re
pro
ce
s
s
i
ng
P
r
ep
r
o
ce
s
s
in
g
i
s
a
p
r
o
ce
s
s
t
h
a
t
ai
m
s
to
p
r
ep
ar
e
r
a
w
d
o
cu
m
e
n
ts
b
ef
o
r
e
b
ein
g
p
r
o
ce
s
s
ed
,
ei
th
er
f
r
o
m
tr
ain
i
n
g
d
o
cu
m
e
n
ts
o
r
test
d
o
cu
m
e
n
ts
.
T
h
er
e
ar
e
s
o
m
e
s
tep
s
in
cl
u
d
ed
in
d
o
cu
m
e
n
t
p
r
ep
r
o
ce
s
s
in
g
s
ta
g
e
in
cu
d
i
n
g
to
k
e
n
izatio
n
,
f
il
ter
in
g
,
a
n
d
s
te
m
m
i
n
g
.
I
n
th
e
f
ir
s
t
s
tep
,
th
e
d
o
cu
m
en
t
is
s
p
li
tted
in
to
s
m
aller
u
n
it
s
ca
lled
to
k
en
s
o
r
ter
m
s
[
2
1
-
2
2
]
.
I
n
th
is
s
tep
,
all
o
f
ch
ar
ac
ter
s
ar
e
co
n
v
er
ted
in
to
lo
w
er
ca
s
e
an
d
p
u
n
ctu
at
io
n
,
n
u
m
b
er
s
,
h
t
m
l
ta
g
a
n
d
ch
ar
a
cter
s
o
u
ts
id
e
o
f
t
h
e
alp
h
ab
et
ar
e
also
r
e
m
o
v
ed
.
T
h
e
n
ex
t
s
tep
is
f
il
ter
in
g
o
r
r
e
m
o
v
i
n
g
u
n
i
n
f
o
r
m
ati
v
e
w
o
r
d
s
ca
lled
s
to
p
lis
t
b
ased
o
n
a
n
ex
is
tin
g
s
to
p
lis
t
d
ictio
n
ar
y
b
y
T
ala
[
2
3
]
.
T
h
e
f
o
u
r
t
h
s
tep
is
s
te
m
m
i
n
g
.
I
n
s
t
e
m
m
in
g
,
ev
er
y
w
o
r
d
s
is
co
n
v
er
ted
to
its
r
o
o
t
[
2
4
-
25]
.
Fo
r
ex
a
m
p
le,
t
h
e
w
o
r
d
s
„
j
alan
‟
,
„
d
ij
alan
k
a
n
‟
,
an
d
„
p
er
j
alan
an
‟
w
i
ll b
e
co
n
v
er
ted
to
th
e
s
a
m
e
w
o
r
d
„
j
alan
‟
.
2
.
2
.
N
-
G
ra
m
F
ea
t
ures E
x
t
ra
ct
io
n
N
-
Gr
a
m
is
a
s
lice
o
f
n
-
w
o
r
d
o
b
tain
ed
f
r
o
m
a
d
o
cu
m
e
n
t
[
2
6
]
.
T
h
e
n
ca
n
v
ar
ies
f
r
o
m
1
(
u
n
i
g
r
a
m
)
,
2
(
b
ig
r
a
m
)
,
3
(
tig
r
a
m
)
,
4
,
an
d
s
o
o
n
.
I
n
t
h
i
s
w
o
r
k
,
w
e
u
s
e
u
n
i
g
r
a
m
,
b
ig
r
a
m
,
a
n
d
co
m
b
i
n
atio
n
o
f
t
h
e
m
.
Fo
r
ex
a
m
p
le,
if
w
e
h
av
e
a
d
o
cu
m
en
t
t
h
at
co
n
tain
a
s
e
n
te
n
ce
:
“w
e
ea
t
r
ice”
,
t
h
en
t
h
e
N
-
g
r
a
m
f
ea
t
u
r
es
o
f
t
h
is
d
o
cu
m
en
t is p
r
esen
ted
in
T
ab
l
e
1
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
N
eig
h
b
o
r
W
eig
h
ted
K
-
N
ea
r
e
s
t
N
eig
h
b
o
r
fo
r
S
a
mb
a
t O
n
lin
e
C
la
s
s
i
fica
tio
n
(
M.
A
li F
a
u
z
i
)
157
T
ab
le
1
.
N
-
Gr
a
m
Feat
u
r
e
E
x
tr
ac
tio
n
R
es
u
lt
U
n
i
g
r
a
m
B
i
g
r
a
m
C
o
mb
i
n
a
t
i
o
n
o
f
U
n
i
g
r
a
m
a
n
d
B
i
g
r
a
m
we
e
a
t
w
e
e
a
t
e
a
t
r
i
c
e
we
e
a
t
r
i
c
e
r
i
c
e
w
e
e
a
t
e
a
t
r
i
c
e
Fu
r
t
h
er
m
o
r
e,
w
e
r
ep
r
esen
t
th
e
f
ea
t
u
r
es
w
i
th
T
F.I
DF
w
ei
g
h
ti
n
g
.
T
F.I
DF
is
th
e
m
o
s
t
h
ig
h
l
y
e
m
p
lo
y
ed
ter
m
w
ei
g
h
tin
g
al
g
o
r
ith
m
i
n
d
o
cu
m
e
n
t
clas
s
i
f
icatio
n
[
2
7
]
.
T
F.
I
DF
in
co
r
p
o
r
ate
ter
m
f
r
eq
u
en
c
y
(
T
F)
an
d
in
v
er
s
e
d
o
cu
m
e
n
t
f
r
eq
u
e
n
c
y
(
I
DF)
.
T
h
e
T
F.I
DF
w
eig
h
t
o
f
ter
m
f
ea
tu
r
e
t
in
d
o
cu
m
e
n
t
d
is
f
o
r
m
u
lated
a
s
f
o
llo
w
s
:
)
l
o
g
1
(
)
l
o
g
1
(
)
,
(
,
t
d
d
t
df
N
f
d
t
I
D
F
TF
W
h
er
e
d
t
f
,
is
t
h
e
n
u
m
b
er
o
f
o
cc
u
r
r
en
ce
s
o
f
f
ea
t
u
r
e
t
i
n
d
o
cu
m
en
t
d
an
d
d
N
is
t
h
e
n
u
m
b
er
o
f
d
o
cu
m
en
t
i
n
d
ataset
.
an
d
t
df
is
th
e
n
u
m
b
er
o
f
d
o
cu
m
e
n
t
in
d
ataset
t
h
at
co
n
tai
n
s
f
ea
t
u
r
e
t.
T
h
is
f
ea
tu
r
e
r
ep
r
esen
tati
o
n
w
il
l
b
e
u
s
ed
in
th
e
cla
s
s
i
f
ica
tio
n
s
ta
g
e.
2
.
3
.
Cla
s
s
if
ica
t
io
n us
i
ng
NW
-
K
NN
T
h
e
last
s
tag
e
is
d
o
cu
m
en
t
class
i
f
icatio
n
u
s
i
n
g
Ne
ig
h
b
o
r
W
eig
h
ted
K
-
Nea
r
est
Ne
ig
h
b
o
r
(
NW
-
KNN)
.
E
ac
h
co
m
p
lain
t
w
ill
b
e
class
i
f
ied
b
ased
o
n
th
e
i
n
te
n
d
ed
d
ep
ar
tm
e
n
t.
NW
-
KN
N
is
a
m
o
d
if
icat
io
n
o
f
KNN
alg
o
r
it
h
m
to
s
o
lv
e
th
e
p
r
o
b
lem
o
f
i
m
b
ala
n
ce
d
d
ata.
T
h
e
i
n
itia
l
s
tag
e
is
f
i
n
d
in
g
k
n
e
ar
est
n
ei
g
h
b
o
r
s
b
y
ca
lcu
lati
n
g
th
e
d
i
s
tan
ce
o
r
s
i
m
ilar
it
y
b
et
w
ee
n
th
e
te
s
ti
n
g
a
n
d
tr
ain
i
n
g
d
ata.
C
o
s
i
n
e
s
i
m
il
ar
it
y
is
u
s
ed
i
n
t
h
i
s
s
tu
d
y
f
o
r
th
o
s
e
tas
k
.
T
h
e
ap
p
licatio
n
o
f
NW
-
KNN
al
g
o
r
it
h
m
is
n
o
t
m
u
ch
d
i
f
f
er
en
t
f
r
o
m
tr
ad
itio
n
al
K
NN
a
lg
o
r
ith
m
.
T
h
e
o
n
l
y
d
if
f
er
e
n
c
e
b
et
w
ee
n
t
h
e
t
w
o
alg
o
r
it
h
m
s
lies
in
t
h
e
ca
lcu
latio
n
clas
s
weig
h
t.
I
n
tr
ad
itio
n
al
KNN,
ea
ch
c
lass
h
a
s
t
h
e
s
a
m
e
w
ei
g
h
t.
O
n
t
h
e
o
th
er
h
a
n
d
,
N
W
-
KNN
g
i
v
e
t
h
e
m
in
o
r
it
y
cla
s
s
a
g
r
ea
ter
w
ei
g
h
t,
w
h
ile
t
h
e
m
aj
o
r
it
y
clas
s
w
ill b
e
g
iv
e
n
s
m
aller
w
ei
g
h
t.
T
h
e
w
eig
h
t o
f
ea
ch
cla
s
s
i
s
ca
lcu
la
te
d
as f
o
llo
w
s
:
(
(
)
(
{
(
)
}
)
)
W
h
er
e
is
t
h
e
w
ei
g
h
t
o
f
class
,
(
)
is
t
h
e
n
u
m
b
er
o
f
tr
ain
in
g
d
ata
i
n
clas
s
,
{
(
)
}
is
t
h
e
least
n
u
m
b
er
o
f
d
ata
tr
ain
i
n
g
i
n
ea
c
h
cla
s
s
,
an
d
is
a
co
n
s
ta
n
t
m
ag
i
c
n
u
m
b
er
th
at
i
ts
v
a
lu
e
u
s
u
all
y
m
o
r
e
t
h
a
n
1
.
I
n
th
is
s
tu
d
y
,
w
e
u
s
e
2
as t
h
e
v
al
u
e.
T
h
is
w
ei
g
h
t,
alo
n
g
s
id
e
w
it
h
t
h
e
k
n
ea
r
est
n
eig
h
b
o
r
s
,
w
il
l
b
e
u
s
ed
to
ca
lcu
late
th
e
s
co
r
e
f
o
r
ea
ch
class
.
T
h
e
clas
s
w
i
th
h
i
g
h
est
s
co
r
e
w
ill b
e
t
h
e
c
lass
o
f
t
h
e
te
s
t d
ata.
T
h
e
ca
lcu
la
tio
n
o
f
t
h
e
s
co
r
es o
f
ea
c
h
cla
s
s
ca
n
b
e
ca
lcu
lated
as
f
o
llo
w
s
:
(
)
(
∑
(
)
(
)
(
)
)
w
h
er
e
(
)
is
t
h
e
s
co
r
e
o
f
clas
s
f
o
r
test
i
n
g
d
ata
,
i
s
th
e
w
ei
g
h
t
o
f
cla
s
s
,
(
)
is
a
s
e
t
o
f
tr
ai
n
i
n
g
d
ata
th
at
l
o
ca
ted
th
e
k
n
ea
r
est
n
ei
g
h
b
o
r
o
f
th
e
test
d
ata
,
an
d
(
)
is
th
e
s
i
m
ilar
it
y
b
et
w
ee
n
tr
ain
i
n
g
d
ata
an
d
test
in
g
d
ata
.
W
e
em
p
lo
y
co
s
i
n
e
s
i
m
ilar
it
y
f
o
r
th
is
m
ea
s
u
r
e.
Me
an
w
h
ile,
(
)
is
th
e
b
in
ar
y
w
ei
g
h
t
th
at
h
as
v
al
u
e
o
f
1
if
tr
ain
i
n
g
d
ata
is
b
elo
n
g
to
class
.
Oth
er
w
h
is
e,
its
w
eig
h
t
w
ill
b
e
0
.
B
y
u
s
i
n
g
t
h
is
f
o
r
m
u
la,
N
W
-
KNN
ca
n
h
a
n
d
le
m
aj
o
r
ity
class
d
o
m
in
a
n
ce
in
i
m
b
alan
ce
d
d
ata
b
ec
au
s
e
it
g
i
v
e
lo
w
er
w
eig
h
t
f
o
r
m
aj
o
r
ity
cl
ass
an
d
h
ig
h
er
clas
s
f
o
r
th
e
m
i
n
o
r
it
y
o
n
e.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l
.
1
2
,
No
.
1
,
Octo
b
er
201
8
:
1
5
5
–
160
158
3.
RE
SU
L
T
S AN
D
AN
AL
Y
SI
S
T
h
e
d
ata
u
s
ed
in
th
is
s
t
u
d
y
is
tak
en
f
r
o
m
S
A
MB
A
T
On
lin
e.
T
h
e
tex
t
o
f
th
e
co
m
p
lai
n
t
is
t
ak
en
f
r
o
m
3
d
ep
a
r
tm
e
n
t
s
in
cl
u
d
in
g
Dep
ar
t
m
en
t
o
f
T
r
an
s
p
o
r
tatio
n
o
r
Din
as
P
er
h
u
b
u
n
g
an
(
DI
SHU
B
)
,
Dep
a
r
tm
e
n
t
o
f
San
itat
io
n
a
n
d
P
ar
k
s
o
r
Di
n
as
Keb
er
s
ih
a
n
d
an
P
er
ta
m
a
n
a
n
(
DKP
)
,
an
d
Dep
ar
t
m
en
t
o
f
P
u
b
lic
W
o
r
k
s
,
Ho
u
s
in
g
an
d
B
u
ild
in
g
Su
p
er
v
is
io
n
o
r
Din
as
P
ek
er
j
aa
n
U
m
u
m
,
P
er
u
m
a
h
a
n
d
an
P
en
g
a
w
a
s
an
B
a
n
g
u
n
an
(
DP
UP
P
B
)
.
T
o
tal
d
ata
u
s
ed
is
3
1
0
d
iv
id
ed
in
t
o
2
3
7
tr
ain
in
g
d
ata
an
d
7
3
test
d
ata.
T
h
e
tr
ain
in
g
d
at
a
co
n
s
is
t
o
f
2
7
d
ata
f
o
r
m
DKP
class
,
4
9
d
ata
f
o
r
m
DP
UP
P
B
class
an
d
1
6
1
d
a
ta
f
r
o
m
DI
SHUB
.
Me
an
w
h
i
le
,
th
e
test
d
ata
u
s
ed
co
n
s
is
t o
f
1
3
d
ata
f
r
o
m
a
D
KP
class
,
2
1
d
ata
f
r
o
m
DP
UP
PB
a
n
d
3
9
d
ata
f
r
o
m
DI
SHUB
cla
s
s
.
T
h
er
e
ar
e
th
r
ee
ex
p
er
im
e
n
t
s
c
en
ar
io
s
p
er
f
o
r
m
ed
o
n
t
h
is
s
tu
d
y
.
F
ir
s
tl
y
,
th
e
e
x
p
er
i
m
e
n
t
i
s
f
o
cu
s
ed
o
n
th
e
ef
f
ec
t
o
f
k
v
al
u
es
o
f
NW
-
KNN
a
n
d
f
i
n
d
i
n
g
t
h
e
m
o
s
t
o
p
ti
m
al
v
alu
e
o
f
k
.
h
e
f
o
llo
w
i
n
g
e
x
p
er
i
m
e
n
t
i
s
i
s
f
o
cu
s
ed
o
n
th
e
e
f
f
ec
t
o
f
N
-
Gr
a
m
as
f
ea
t
u
r
es
f
o
r
clas
s
f
ic
itio
n
u
s
i
n
g
NW
-
KNN.
I
n
th
e
last
o
n
e,
w
e
w
ill
co
m
p
ar
e
th
e
p
er
f
o
r
m
a
n
ce
o
f
NW
-
KNN
an
d
co
n
v
en
tio
n
al
KNN
m
et
h
o
d
.
W
e
u
s
e
p
r
ec
is
io
n
,
r
ec
all,
an
d
f
-
m
ea
s
u
r
e
f
o
r
ev
al
u
atio
n
in
all
o
f
th
e
s
e
ex
p
er
i
m
en
ts
.
3
.
1
.
K
Va
lue V
a
ria
t
io
n E
x
peri
ment
I
n
th
is
e
x
p
er
i
m
e
n
t,
w
e
p
er
f
o
r
m
ed
a
co
m
p
ar
is
o
n
o
f
k
v
al
u
es
v
ar
iatio
n
s
o
f
1
,
3
,
5
,
7
an
d
1
5
.
Un
ig
r
a
m
(
B
ag
o
f
W
o
r
d
)
is
u
s
ed
f
o
r
th
is
ex
p
er
i
m
e
n
t.
T
ab
le
2
s
h
o
w
s
th
e
r
esu
l
t
o
f
th
is
e
x
p
er
i
m
e
n
t.
T
h
e
r
esu
lts
d
ep
icts
th
at
g
e
n
er
all
y
th
e
p
er
f
o
r
m
a
n
c
e
o
f
t
h
is
clas
s
i
f
icatio
n
s
y
s
te
m
is
d
ec
r
ea
s
i
n
g
as
th
e
v
a
lu
e
o
f
k
i
s
g
etti
n
g
h
ig
h
er
.
T
h
is
is
b
ec
au
s
e
t
h
e
h
ig
h
er
t
h
e
v
al
u
e
o
f
k
,
t
h
e
h
ig
h
er
t
h
e
p
r
o
b
ab
ilit
y
o
f
n
ei
g
h
b
o
r
s
t
h
at
h
a
v
e
f
u
r
th
er
d
is
ta
n
ce
s
ar
e
also
co
n
s
id
er
ab
ly
ta
k
en
i
n
to
co
n
s
id
er
atio
n
.
T
h
is
f
ar
n
eig
h
b
o
r
s
ca
n
b
e
th
e
ir
r
elev
an
t
f
o
r
ch
o
o
s
in
g
th
e
r
i
g
h
t
class
.
T
h
e
v
alu
e
o
f
k
=3
h
as
t
h
e
m
o
s
t
o
p
ti
m
al
p
er
f
o
r
m
a
n
ce
with
7
7
.
8
5
%
p
r
ec
is
io
n
,
7
4
.
1
8
% r
ec
all,
an
d
7
5
.
2
5
%
f
-
m
ea
s
u
r
e
v
al
u
e.
Ho
w
e
v
er
,
th
e
v
alu
e
o
f
k
=1
h
a
s
t
h
e
m
o
s
t
in
f
er
io
r
p
er
f
o
r
m
a
n
ce
w
it
h
f
-
m
ea
s
u
r
e
v
al
u
e
o
n
l
y
6
5
.
5
1
%
b
ec
au
s
e
it o
n
l
y
co
n
s
id
er
o
n
e
n
eig
h
b
o
r
th
at
ca
n
b
e
v
e
r
y
b
ia
s
ed
.
T
ab
le
2
.
K
Valu
e
Var
iatio
n
E
x
p
er
im
e
n
t
R
es
u
lt.
K
V
a
l
u
e
P
r
e
c
i
so
n
R
e
c
a
l
l
F
-
M
e
a
su
r
e
1
6
9
.
6
0
%
6
3
.
5
1
%
6
5
.
5
1
%
3
7
7
.
8
5
%
7
4
.
1
8
%
7
5
.
2
5
%
5
7
5
.
1
3
%
6
8
.
3
1
%
7
0
.
6
0
%
7
7
6
.
5
1
%
6
8
.
3
1
%
7
0
.
9
5
%
15
7
4
.
0
2
%
6
4
.
5
0
%
6
7
.
0
2
%
3
.
2
.
N
-
G
ra
m
Va
ria
t
io
n
E
x
peri
ment
I
n
th
is
e
x
p
er
i
m
e
n
t,
t
h
e
v
ar
iet
y
o
f
N
-
Gr
a
m
u
s
ed
w
er
e
u
n
i
g
r
a
m
,
b
ig
r
a
m
a
n
d
co
m
b
i
n
atio
n
o
f
b
o
th
a
s
f
ea
u
r
e
s
.
T
h
is
ex
p
er
i
m
en
t
is
co
n
d
u
ce
ted
u
s
in
g
k
=3
as
T
ab
le
3
s
h
o
w
s
th
e
r
esu
lt.
As
s
ee
n
o
n
T
ab
le
3
,
u
n
ig
r
a
m
f
ea
t
u
r
e
s
h
o
w
s
th
e
b
est
p
er
f
o
r
m
an
ce
co
m
p
ar
ed
to
t
h
e
o
t
h
er
s
w
it
h
7
7
.
8
5
%
p
r
ec
is
io
n
,
7
4
.
1
8
%
r
ec
all,
an
d
7
5
.
2
5
%
f
-
m
ea
s
u
r
e
v
al
u
e.
Me
an
w
h
ile,
th
e
w
o
r
s
t
p
er
f
o
r
m
a
n
ce
is
o
b
tain
ed
w
h
e
n
b
ig
r
a
m
i
s
e
m
p
lo
y
ed
w
i
th
f
-
m
ea
s
u
r
e
v
al
u
e
o
n
l
y
4
8
.
5
1
%.
T
h
is
is
b
ec
au
s
e
m
an
y
o
f
B
ig
r
a
m
'
s
ter
m
s
,
w
h
ich
i
s
a
co
m
b
i
n
atio
n
o
f
t
w
o
w
o
r
d
s
,
r
ar
ely
ap
p
ea
r
o
n
m
o
r
e
th
a
n
o
n
e
d
o
cu
m
e
n
t.
I
t
is
o
f
te
n
o
n
l
y
o
cc
u
r
s
i
n
th
e
d
o
cu
m
en
t
w
h
er
e
t
h
e
ter
m
i
s
lo
ca
ted
.
I
t
is
v
er
y
d
if
f
er
en
t
f
r
o
m
u
n
ig
r
a
m
f
ea
t
u
r
e
th
at
o
n
l
y
co
n
s
i
s
t
o
n
e
w
o
r
d
.
I
t
m
a
k
es
t
h
is
f
e
tau
r
e
s
ca
n
b
e
o
cc
u
r
s
in
a
lo
t o
f
d
o
cu
m
e
n
ts
.
T
ab
le
3
.
N
-
G
r
a
m
Var
iatio
n
E
x
p
er
im
e
n
t
R
es
u
lt.
K
V
a
l
u
e
P
r
e
c
i
so
n
R
e
c
a
l
l
F
-
M
e
a
su
r
e
U
n
i
g
r
a
m
7
7
.
8
5
%
7
4
.
1
8
%
7
5
.
2
5
%
B
i
g
r
a
m
5
5
.
8
5
%
4
6
.
4
4
%
4
8
.
5
1
%
C
o
mb
i
n
a
t
i
o
n
o
f
U
n
i
g
r
a
m
a
n
d
B
i
g
r
a
m
7
0
.
5
1
%
6
9
.
5
7
%
6
9
.
5
7
%
3
.
3
.
NW
-
K
NN
a
nd
K
NN
Co
m
pa
riso
n E
x
peri
m
ent
A
co
m
p
ar
i
s
o
n
o
f
KNN
a
n
d
NW
-
KNN
al
g
o
r
ith
m
i
s
p
er
f
o
r
m
ed
in
t
h
is
e
x
p
er
i
m
e
n
t.
T
h
e
u
n
i
g
r
a
m
f
ea
t
u
r
e
is
u
s
ed
in
t
h
is
e
x
p
er
im
en
t
w
it
h
v
ar
iatio
n
s
o
f
k
n
ei
g
h
b
o
r
in
g
v
a
lu
e
s
u
s
ed
in
cl
u
d
e
1
,
3
,
5
,
7
,
an
d
1
5
as
F
ig
u
r
e
2
s
h
o
w
s
t
h
e
r
es
u
lt.
T
h
e
r
esu
lt
d
ep
icts
t
h
at
g
e
n
er
al
l
y
NW
-
KNN
al
g
o
r
ith
m
s
h
o
w
s
a
b
etter
p
er
f
o
r
m
a
n
ce
th
an
co
n
v
e
n
tio
n
al
KNN
al
g
o
r
ith
m
s
a
s
th
e
k
v
a
lu
e
g
e
tti
n
g
b
ig
g
er
.
T
h
is
i
s
b
ec
a
u
s
e
th
e
d
is
tr
ib
u
tio
n
o
f
th
e
a
m
o
u
n
t
o
f
tr
ai
n
in
g
d
ata
in
e
ac
h
class
is
im
b
ala
n
ce
d
.
As
th
e
n
ei
g
h
b
o
r
in
g
v
al
u
e
of
k
g
r
o
w
s
b
ig
g
er
,
KNN
alg
o
r
ith
m
te
n
d
to
co
n
s
id
er
f
ar
n
eig
h
b
o
r
s
th
at
o
f
te
n
b
elo
n
g
to
th
e
class
th
at
h
as
th
e
h
ig
h
e
s
t
a
m
o
u
n
t
o
f
tr
ain
i
n
g
d
ata.
A
s
th
e
r
esu
lt,
b
y
u
s
i
n
g
KNN,
w
il
l
b
e
a
lo
t
o
f
test
in
g
d
ata
th
at
class
i
f
ied
in
to
m
aj
o
r
it
y
class
e
v
en
t
h
o
u
g
h
it
s
h
o
u
ld
n
o
t.
Me
an
w
h
i
le,
th
is
p
r
o
b
l
em
ca
n
b
e
av
o
id
ed
b
y
NW
-
KNN
al
g
o
r
it
h
m
b
ec
au
s
e
it
g
i
v
es
lo
w
er
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
N
eig
h
b
o
r
W
eig
h
ted
K
-
N
ea
r
e
s
t
N
eig
h
b
o
r
fo
r
S
a
mb
a
t O
n
lin
e
C
la
s
s
i
fica
tio
n
(
M.
A
li F
a
u
z
i
)
159
w
ei
g
h
ts
f
o
r
m
aj
o
r
ity
c
lass
an
d
h
i
g
h
er
w
eig
h
t
f
o
r
t
h
e
m
i
n
o
r
ity
o
n
e.
T
h
e
b
est
p
er
f
o
r
m
a
n
ce
i
s
s
h
o
w
ed
b
y
NW
-
KNN
w
h
e
n
u
s
in
g
k
v
al
u
e
o
f
2
w
it
h
7
5
.
2
5
%
f
-
m
ea
s
u
r
e
v
al
u
e
,
w
h
ile
KNN
also
s
h
o
w
s
it
s
b
est
p
er
f
o
r
m
an
ce
at
th
e
s
a
m
e
k
v
al
u
e
w
it
h
s
li
g
h
t d
if
f
er
en
ce
v
a
lu
e
o
f
f
-
m
ea
u
s
r
e
o
f
7
5
.
2
1
%.
Fig
u
r
e
2
.
KNN
an
d
NW
-
KNN
C
o
m
p
ar
is
o
n
R
es
u
lt
4.
CO
NCLU
SI
O
N
I
n
t
h
is
w
o
r
k
,
Nei
g
h
b
o
r
W
eig
h
ted
K
-
Nea
r
es
t
Nei
g
h
b
o
r
(
NW
-
KNN)
w
as
u
s
ed
f
o
r
i
m
b
ala
n
ce
d
Sa
m
b
at
On
li
n
e
clas
s
i
f
icatio
n
.
T
h
e
s
y
s
te
m
d
ev
elo
p
ed
is
co
m
p
o
s
ed
o
f
t
h
r
ee
m
aj
o
r
p
h
ases
i
n
cl
u
d
in
g
p
r
ep
r
o
ce
s
s
in
g
,
N
-
Gr
a
m
f
ea
t
u
r
e
ex
tr
ac
tio
n
,
a
n
d
class
i
f
icat
io
n
u
s
i
n
g
NW
-
KN
N.
B
ased
o
n
t
h
e
e
x
p
er
i
m
e
n
t
r
esu
lt
s
,
it
ca
n
b
e
r
esu
m
ed
th
a
t
t
h
e
NW
-
KNN
a
lg
o
r
ith
m
i
s
ab
le
to
cla
s
s
i
f
y
t
h
e
i
m
b
ala
n
ce
d
d
ata
w
ell
w
it
h
t
h
e
m
o
s
t
o
p
ti
m
al
k
-
n
eig
h
b
o
r
v
al
u
e
is
3
an
d
u
n
i
g
r
a
m
as
t
h
e
b
est
f
ea
t
u
r
es
b
y
7
7
.
8
5
%
p
r
ec
is
io
n
,
7
4
.
1
8
%
r
ec
all,
an
d
7
5
.
2
5
%
f
-
m
ea
s
u
r
e
v
al
u
e.
T
h
is
s
t
u
d
y
s
h
o
w
t
h
at
g
r
ea
ter
v
al
u
e
o
f
k
d
ec
r
ea
s
e
th
e
f
-
m
ea
s
u
r
e
v
al
u
e
o
f
cl
ass
i
f
icatio
n
s
y
s
te
m
.
T
h
is
s
tu
d
y
al
s
o
d
ep
ict
th
at
th
e
b
ig
r
a
m
a
n
d
co
m
b
i
n
atio
n
o
f
b
o
th
u
n
i
g
r
a
m
a
n
d
b
ig
r
a
m
f
ail
to
i
m
p
r
o
v
e
th
e
s
y
s
te
m
p
er
f
o
r
m
a
n
ce
.
C
o
m
p
ar
ed
to
th
e
co
n
v
e
n
tio
n
al
KNN
,
NW
-
KNN
a
lg
o
r
it
h
m
p
r
o
v
ed
to
b
e
b
etter
f
o
r
i
m
b
alan
ce
d
d
ata
p
r
o
b
lem
s
as
th
e
v
al
u
e
o
f
k
n
eig
h
b
o
r
s
g
e
ttin
g
g
r
ea
ter
b
ec
au
s
e
it
g
iv
e
s
lo
w
er
w
ei
g
h
t
s
f
o
r
m
aj
o
r
ity
clas
s
a
n
d
h
ig
h
er
w
e
ig
h
t
f
o
r
th
e
m
in
o
r
it
y
o
n
e.
S
o
m
e
f
u
t
u
r
e
w
o
r
k
s
th
at
ca
n
b
e
co
n
d
u
cted
i
s
t
h
e
d
etec
tio
n
o
f
ab
b
r
ev
iated
w
o
r
d
s
an
d
s
la
n
g
w
o
r
d
s
b
ec
au
s
e
m
a
n
y
co
m
p
lai
n
ts
i
n
Sa
m
b
at
O
n
li
n
e
ar
e
w
r
itte
n
u
s
in
g
th
at
k
in
d
o
f
w
o
r
d
s
.
RE
F
E
R
E
NC
E
S
[1
]
A
n
a
n
d
it
a
N.
“
El
e
m
e
n
S
u
k
se
s
E
–
G
o
v
e
rn
m
e
n
t:
S
tu
d
i
Ka
su
s
L
a
y
a
n
a
n
A
sp
iras
i
Da
n
P
e
n
g
a
d
u
a
n
On
li
n
e
Ra
k
y
a
t
(L
a
p
o
r!
)
Ko
ta Ba
n
d
u
n
g
”
.
Un
iv
e
rsitas
Ka
to
li
k
P
a
ra
h
y
a
n
g
a
n
,
Ba
n
d
u
n
g
.
2
0
1
6
.
[2
]
F
a
u
z
i
M
A
,
A
ri
f
in
A
Z,
G
o
sa
ria
S
C.
“
In
d
o
n
e
sia
n
Ne
w
s
Clas
sif
i
c
a
ti
o
n
Us
in
g
Na
ïv
e
Ba
y
e
s
a
n
d
Tw
o
-
P
h
a
se
F
e
a
tu
re
S
e
lec
ti
o
n
M
o
d
e
l.
In
d
o
n
e
sia
n
”.
J
o
u
rn
a
l
o
f
El
e
c
trica
l
E
n
g
i
n
e
e
rin
g
a
n
d
Co
mp
u
ter
S
c
ien
c
e
(
IJ
EE
CS
)
.
2
0
1
7
De
c
1
;8
(
3
):6
1
0
-
5.
[3
]
A
n
ti
n
a
sa
ri
P
,
P
e
r
d
a
n
a
RS
,
F
a
u
z
i
M
A
.
“
A
n
a
li
sis
S
e
n
ti
m
e
n
Ten
tan
g
Op
in
i
F
il
m
P
a
d
a
D
o
k
u
m
e
n
Tw
it
ter
Be
rb
a
h
a
sa
In
d
o
n
e
sia
M
e
n
g
g
u
n
a
k
a
n
Na
iv
e
Ba
y
e
s
De
n
g
a
n
P
e
rb
a
ik
a
n
Ka
ta
T
id
a
k
Ba
k
u
”
.
J
u
rn
a
l
Pe
n
g
e
mb
a
n
g
a
n
T
e
k
n
o
l
o
g
i
In
fo
rm
a
si
d
a
n
Ilm
u
K
o
mp
u
ter
.
2
0
1
7
;
1
(1
2
):
1
7
3
3
-
41.
[4
]
G
u
n
a
w
a
n
F
,
F
a
u
z
i
M
A
,
A
d
ik
a
r
a
P
P
.
“
A
n
a
li
sis
S
e
n
ti
m
e
n
P
a
d
a
Ula
sa
n
A
p
li
k
a
si
M
o
b
il
e
M
e
n
g
g
u
n
a
k
a
n
Na
iv
e
B
a
y
e
s
Da
n
No
rm
a
li
sa
si
Ka
t
a
Be
rb
a
sis
Lev
e
n
sh
tein
Dista
n
c
e
(S
tu
d
i
Ka
su
s
A
p
li
k
a
si
BC
A
M
o
b
il
e
)
”
.
S
y
ste
mic
:
In
fo
rm
a
ti
o
n
S
y
ste
m a
n
d
In
f
o
rm
a
ti
c
s Jo
u
rn
a
l
.
2
0
1
7
De
s 3
1
;
3
(2
):
1
-
6.
[5
]
F
a
u
z
i
M
A
,
Af
iri
a
n
to
T
.
“
I
m
p
ro
v
in
g
S
e
n
ti
m
e
n
t
A
n
a
l
y
sis
o
f
S
h
o
rt
In
f
o
rm
a
l
In
d
o
n
e
sia
n
P
r
o
d
u
c
t
Re
v
ie
w
s
u
sin
g
S
y
n
o
n
y
m
Ba
se
d
F
e
a
tu
re
Ex
p
a
n
s
io
n
”
.
T
E
L
KOM
NIKA
(
T
e
lec
o
mm
u
n
ica
ti
o
n
Co
mp
u
ti
n
g
El
e
c
tro
n
ics
a
n
d
C
o
n
tr
o
l)
.
2
0
1
8
J
u
n
1
;1
6
(3
)
.
[6
]
F
a
n
issa
S
,
F
a
u
z
i
M
A
,
A
d
in
u
g
ro
h
o
S
.
“
A
n
a
li
sis
S
e
n
ti
m
e
n
P
a
riw
is
a
ta
d
i
Ko
ta
M
a
lan
g
M
e
n
g
g
u
n
a
k
a
n
M
e
to
d
e
Na
iv
e
Ba
y
e
s
d
a
n
S
e
le
k
si
F
it
u
r
Qu
e
ry
Ex
p
a
n
sio
n
Ra
n
k
in
g
”
.
J
u
rn
a
l
Pen
g
e
mb
a
n
g
a
n
T
e
k
n
o
l
o
g
i
I
n
fo
r
ma
si
d
a
n
Ilmu
Ko
mp
u
ter
.
2
0
1
8
;
2
(
8
):2
7
6
6
-
7
0
.
[7
]
Ro
f
iq
o
h
U,
P
e
r
d
a
n
a
RS
,
F
a
u
z
i
M
A
.
“
A
n
a
li
sis
S
e
n
ti
m
e
n
T
in
g
k
a
t
K
e
p
u
a
sa
n
P
e
n
g
g
u
n
a
P
e
n
y
e
d
ia
L
a
y
a
n
a
n
T
e
le
k
o
m
u
n
ik
a
si
S
e
lu
ler
I
n
d
o
n
e
si
a
P
a
d
a
T
w
it
ter
De
n
g
a
n
M
e
to
d
e
S
u
p
p
o
rt
V
e
c
to
r
M
a
c
h
in
e
d
a
n
L
e
x
ico
n
Ba
se
d
F
e
a
tu
re
s
”
.
J
u
rn
a
l
Pen
g
e
mb
a
n
g
a
n
T
e
k
n
o
l
o
g
i
In
f
o
rm
a
si
d
a
n
Ilmu
Ko
mp
u
ter
.
2
0
1
7
;
1
(1
2
):
1
7
2
5
-
32.
[8
]
Jo
a
c
h
im
s
T
.
“
T
e
x
t
c
a
te
g
o
riza
ti
o
n
w
it
h
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
s:
L
e
a
rn
in
g
w
it
h
m
a
n
y
re
l
e
v
a
n
t
f
e
a
tu
re
s
”
.
In
Eu
ro
p
e
a
n
c
o
n
fer
e
n
c
e
o
n
ma
c
h
in
e
lea
rn
i
n
g
1
9
9
8
A
p
r
2
1
(
p
p
.
1
3
7
-
1
4
2
).
S
p
ri
n
g
e
r,
Be
rli
n
,
He
id
e
lb
e
rg
.
1
2
3
4
5
KNN
6
5
.
5
1
7
5
.
2
1
7
0
.
8
3
6
2
.
5
1
6
2
.
1
5
N
W
-
K
N
N
6
5
.
5
1
7
5
.
2
5
7
0
.
6
7
0
.
9
5
6
7
.
0
2
0
20
40
60
80
F
-
M
e
a
su
r
e
K N
e
a
r
e
st
N
e
i
g
h
b
o
r
s
K
NN
v
s
NW
-
K
NN
Com
p
ar
is
on
KNN
N
W
-
K
N
N
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l
.
1
2
,
No
.
1
,
Octo
b
er
201
8
:
1
5
5
–
160
160
[9
]
Nu
rjan
a
h
W
E,
P
e
rd
a
n
a
RS
,
F
a
u
z
i
M
A
.
“
A
n
a
li
sis
S
e
n
ti
m
e
n
Terh
a
d
a
p
T
a
y
a
n
g
a
n
T
e
le
v
isi
Be
r
d
a
sa
rk
a
n
Op
in
i
M
a
s
y
a
ra
k
a
t
p
a
d
a
M
e
d
ia
S
o
sia
l
Tw
it
ter
m
e
n
g
g
u
n
a
k
a
n
M
e
to
d
e
K
-
Ne
a
re
st
Ne
ig
h
b
o
r
d
a
n
P
e
m
b
o
b
o
tan
Ju
m
lah
Re
twe
e
t
”
.
J
u
rn
a
l
Pen
g
e
mb
a
n
g
a
n
T
e
k
n
o
lo
g
i
I
n
fo
rm
a
si d
a
n
Ilmu
K
o
mp
u
ter
.
2
0
1
7
;
1
(
1
2
),
1
7
5
0
-
5
7
.
[1
0
]
S
u
h
a
r
n
o
CF
,
F
a
u
z
i
M
A
,
P
e
rd
a
n
a
RS
.
“
Kla
si
f
i
k
a
si
T
e
k
s
Ba
h
a
sa
In
d
o
n
e
sia
P
a
d
a
Do
k
u
m
e
n
P
e
n
g
a
d
u
a
n
S
a
m
b
a
t
On
li
n
e
M
e
n
g
g
u
n
a
k
a
n
M
e
to
d
e
K
-
Ne
a
re
st
Ne
ig
h
b
o
rs
d
a
n
Ch
i
-
S
q
u
a
re
”
.
S
y
ste
mic
:
In
fo
rm
a
ti
o
n
S
y
ste
m
a
n
d
In
fo
rm
a
t
ics
J
o
u
rn
a
l
.
2
0
1
7
De
c
7
;
3
(1
):
2
5
-
32.
[1
1
]
M
e
n
tari
ND
,
F
a
u
z
i
M
A
,
M
u
f
li
k
h
a
h
L
.
“
A
n
a
li
sis
S
e
n
ti
m
e
n
Ku
rik
u
lu
m
2
0
1
3
P
a
d
a
S
o
sia
l
M
e
d
ia
Tw
it
ter
M
e
n
g
g
u
n
a
k
a
n
M
e
to
d
e
K
-
Ne
a
re
st
Ne
i
g
h
b
o
r
d
a
n
F
e
a
t
u
re
S
e
lec
ti
o
n
Q
u
e
ry
Ex
p
a
n
sio
n
Ra
n
k
in
g
”
.
J
u
rn
a
l
Pen
g
e
mb
a
n
g
a
n
T
e
k
n
o
lo
g
i
In
fo
rm
a
si d
a
n
I
lmu
K
o
mp
u
ter
.
2
0
1
8
;
2
(
8
):2
7
3
9
-
4
3
.
[1
2
]
Clau
d
y
YI,
P
e
rd
a
n
a
RS
,
F
a
u
z
i
M
A
.
“
Kla
si
f
ik
a
si
Do
k
u
m
e
n
Tw
it
ter
Un
tu
k
M
e
n
g
e
tah
u
i
Ka
ra
k
ter
Ca
lo
n
Ka
r
y
a
w
a
n
M
e
n
g
g
u
n
a
k
a
n
A
lg
o
rit
m
e
K
-
Ne
a
re
st
Ne
ig
h
b
o
r
(KN
N)
”
.
J
u
rn
a
l
Pen
g
e
mb
a
n
g
a
n
T
e
k
n
o
lo
g
i
I
n
fo
r
ma
si
d
a
n
I
lm
u
Ko
mp
u
ter
.
2
0
1
8
;
2
(
8
):
2
7
6
1
-
65.
[1
3
]
M
u
n
ir
M
M
,
F
a
u
z
i
M
A
,
P
e
rd
a
n
a
RS
.
“
Im
p
le
m
e
n
tas
i
M
e
to
d
e
Ba
c
k
p
ro
p
a
g
a
ti
o
n
Ne
u
ra
l
Ne
tw
o
rk
b
e
rb
a
sis
L
e
x
ico
n
Ba
se
d
F
e
a
tu
re
s
d
a
n
Ba
g
o
f
W
o
rd
s
Un
t
u
k
Id
e
n
ti
f
i
k
a
si
Uja
ra
n
Ke
b
e
n
c
ian
P
a
d
a
T
w
it
ter
”
.
J
u
rn
a
l
P
e
n
g
e
mb
a
n
g
a
n
T
e
k
n
o
lo
g
i
I
n
fo
rm
a
si d
a
n
Ilmu
K
o
mp
u
ter
e
-
IS
S
N.
2
0
1
7
;2
5
4
8
:9
6
4
X
.
[1
4
]
L
a
m
S
L
,
Lee
D
L
.
“
F
e
a
tu
re
re
d
u
c
ti
o
n
f
o
r
n
e
u
ra
l
n
e
tw
o
rk
b
a
se
d
tex
t
c
a
teg
o
riza
ti
o
n
”
.
In
Da
t
a
b
a
se
S
y
ste
ms
fo
r
Ad
v
a
n
c
e
d
Ap
p
li
c
a
t
io
n
s,
1
9
9
9
.
Pro
c
e
e
d
in
g
s.
,
6
t
h
I
n
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
1
9
9
9
(
p
p
.
1
9
5
-
2
0
2
).
IE
EE
.
[1
5
]
S
u
n
Y,
W
o
n
g
A
K,
K
a
m
e
l
M
S
.
“
Clas
si
f
ica
ti
o
n
o
f
i
m
b
a
lan
c
e
d
d
a
ta:
A
re
v
ie
w
”
.
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
P
a
tt
e
r
n
Rec
o
g
n
it
io
n
a
n
d
Arti
fi
c
i
a
l
In
telli
g
e
n
c
e
.
2
0
0
9
J
u
n
;
2
3
(
0
4
)
:6
8
7
-
7
1
9
.
[1
6
]
F
ra
n
k
E,
Bo
u
c
k
a
e
rt
RR.
“
Na
i
v
e
b
a
y
e
s
f
o
r
te
x
t
c
l
a
ss
i
f
ica
ti
o
n
w
it
h
u
n
b
a
la
n
c
e
d
c
las
se
s
”
.
In
Eu
ro
p
e
a
n
Co
n
fer
e
n
c
e
o
n
Prin
c
ip
les
o
f
Da
t
a
M
in
i
n
g
a
n
d
K
n
o
wled
g
e
Disc
o
v
e
ry
2
0
0
6
S
e
p
1
8
(p
p
.
5
0
3
-
5
1
0
).
S
p
ri
n
g
e
r,
Be
rli
n
,
He
id
e
lb
e
rg
.
[1
7
]
L
iu
Y,
L
o
h
HT
,
S
u
n
A
.
“
I
m
b
a
lan
c
e
d
tex
t
c
las
sif
ic
a
ti
o
n
:
A
term
w
e
i
g
h
ti
n
g
a
p
p
r
o
a
c
h
”
.
Exp
e
r
t
sy
ste
ms
wit
h
Ap
p
li
c
a
ti
o
n
s
.
2
0
0
9
Ja
n
1
;
3
6
(1
):
6
9
0
-
7
0
1
.
[1
8
]
Ch
a
w
la
NV
,
Ja
p
k
o
w
icz
N,
Ko
t
c
z
A
.
“
S
p
e
c
ial
issu
e
o
n
lea
rn
i
n
g
f
ro
m
i
m
b
a
lan
c
e
d
d
a
ta
se
ts
”
.
ACM
S
i
g
k
d
d
Exp
lo
ra
ti
o
n
s Ne
wsle
tt
e
r
.
2
0
0
4
Ju
n
1
;
6
(1
)
:1
-
6.
[1
9
]
T
a
n
S
.
“
Ne
ig
h
b
o
r
-
w
e
ig
h
ted
k
-
n
e
a
re
st
n
e
ig
h
b
o
r
f
o
r
u
n
b
a
la
n
c
e
d
te
x
t
c
o
rp
u
s
”
.
Exp
e
rt
S
y
ste
ms
wit
h
Ap
p
li
c
a
ti
o
n
s
.
2
0
0
5
M
a
y
1
;2
8
(4
):
6
6
7
-
7
1
.
[2
0
]
Ro
si
F
,
F
a
u
z
i
M
A
,
P
e
rd
a
n
a
RS
.
“
P
re
d
ik
si
Ra
ti
n
g
P
a
d
a
Re
v
ie
w
P
ro
d
u
k
Ke
c
a
n
ti
k
a
n
M
e
n
g
g
u
n
a
k
a
n
M
e
to
d
e
Na
ïv
e
Ba
y
e
s
d
a
n
Ca
teg
o
rica
l
P
ro
p
o
r
t
i
o
n
a
l
Diff
e
re
n
c
e
(CP
D)
”
.
J
u
rn
a
l
Pen
g
e
mb
a
n
g
a
n
T
e
k
n
o
l
o
g
i
In
fo
r
ma
si
d
a
n
Ilm
u
Ko
mp
u
ter
.
2
0
1
8
;
2
(
5
):
1
9
9
1
-
97.
[2
1
]
L
e
sta
ri
A
R,
P
e
rd
a
n
a
RS
,
F
a
u
z
i
M
A
.
“
A
n
a
li
sis
S
e
n
ti
m
e
n
T
e
n
tan
g
Op
in
i
P
il
k
a
d
a
Dk
i
2
0
1
7
P
a
d
a
D
o
k
u
m
e
n
Tw
it
ter
Be
rb
a
h
a
sa
In
d
o
n
e
sia
M
e
n
g
g
u
n
a
k
a
n
Nä
iv
e
Ba
y
e
s
d
a
n
P
e
m
b
o
b
o
tan
Em
o
ji
”
.
J
u
rn
a
l
Pen
g
e
mb
a
n
g
a
n
T
e
k
n
o
lo
g
i
In
fo
rm
a
si
d
a
n
Ilm
u
K
o
mp
u
ter
.
2
0
1
7
;
1
(1
2
):
1
7
1
8
-
24.
[2
2
]
F
a
u
z
i
M
A
,
A
ri
f
in
A
,
Yu
n
iarti
A
.
“
T
e
r
m
Weig
h
ti
n
g
Be
rb
a
sis
In
d
e
k
s
Bu
k
u
d
a
n
Ke
las
u
n
tu
k
P
e
ra
n
g
k
in
g
a
n
Do
k
u
m
e
n
Be
rb
a
h
a
sa
A
r
a
b
”
.
L
o
n
ta
r K
o
mp
u
t
e
r: Ju
rn
a
l
Ilmi
a
h
T
e
k
n
o
l
o
g
i
In
fo
r
ma
si
.
2
0
1
3
.
[2
3
]
T
a
la F
Z.
“
A
stu
d
y
o
f
ste
m
m
in
g
e
ff
e
c
ts
o
n
in
f
o
rm
a
ti
o
n
re
tri
e
v
a
l
in
Ba
h
a
sa
In
d
o
n
e
sia
”
.
In
stit
u
te f
o
r L
o
g
ic,
L
a
n
g
u
a
g
e
a
n
d
Co
m
p
u
t
a
ti
o
n
,
Un
ive
rs
it
e
it
v
a
n
Amste
rd
a
m
,
T
h
e
Ne
th
e
rlan
d
s.
2
0
0
3
Ju
l.
[2
4
]
P
ra
m
u
k
a
n
to
ro
ES
,
F
a
u
z
i
M
A
.
“
C
o
m
p
a
ra
ti
v
e
a
n
a
l
y
sis
o
f
strin
g
si
m
il
a
rit
y
a
n
d
c
o
rp
u
s
-
b
a
se
d
sim
il
a
rit
y
f
o
r
a
u
to
m
a
ti
c
e
ss
a
y
sc
o
rin
g
s
y
ste
m
o
n
e
-
lea
r
n
in
g
g
a
m
i
f
ica
ti
o
n
”
.
In
Ad
v
a
n
c
e
d
Co
mp
u
ter
S
c
ien
c
e
a
n
d
In
fo
rm
a
ti
o
n
S
y
ste
ms
(
ICACS
IS
),
2
0
1
6
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
2
0
1
6
Oc
t
1
5
(
p
p
.
1
4
9
-
1
5
5
).
IEE
E.
[2
5
]
F
a
u
z
i
M
A
,
Yu
n
iarti
A
.
“
En
se
m
b
le
M
e
th
o
d
f
o
r
In
d
o
n
e
sia
n
T
w
it
ter
Ha
te
S
p
e
e
c
h
De
tec
ti
o
n
”
.
In
d
o
n
e
sia
n
J
o
u
rn
a
l
o
f
El
e
c
trica
l
En
g
in
e
e
rin
g
a
n
d
Co
m
p
u
ter
S
c
ien
c
e
(
IJ
EE
CS
)
.
2
0
1
8
Ju
l
1
;1
1
(1
).
[2
6
]
F
a
u
z
i
M
A
,
Uto
m
o
DC,
S
e
ti
a
wa
n
BD,
P
ra
m
u
k
a
n
to
ro
ES
.
“
A
u
to
m
a
ti
c
Essa
y
S
c
o
rin
g
S
y
ste
m
Us
i
n
g
N
-
G
r
a
m
a
n
d
Co
sin
e
S
im
il
a
rit
y
f
o
r
G
a
m
i
f
i
c
a
ti
o
n
Ba
se
d
E
-
L
e
a
rn
in
g
”
.
In
Pr
o
c
e
e
d
in
g
s
o
f
t
h
e
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Ad
v
a
n
c
e
s i
n
Ima
g
e
Pro
c
e
ss
in
g
2
0
1
7
A
u
g
2
5
(p
p
.
1
5
1
-
1
5
5
).
A
CM
.
[2
7
]
F
a
u
z
i
M
A
,
A
ri
f
in
A
Z,
Yu
n
iarti
A
.
“
Ara
b
ic
Bo
o
k
Re
tri
e
v
a
l
u
sin
g
Clas
s
a
n
d
Bo
o
k
In
d
e
x
Ba
se
d
T
e
rm
Weig
h
ti
n
g
”
.
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
E
lec
trica
l
a
n
d
C
o
mp
u
ter
En
g
in
e
e
rin
g
(
IJ
ECE
)
.
2
0
1
7
De
c
1
;
7
(6
):
3
7
0
5
-
1
0
.
Evaluation Warning : The document was created with Spire.PDF for Python.