T
E
L
K
O
M
N
I
K
A
T
elec
o
m
m
un
ica
t
io
n,
Co
m
pu
t
ing
,
E
lect
ro
ni
cs a
nd
Co
ntr
o
l
Vo
l.
18
,
No
.
5
,
Octo
b
er
2
0
2
0
,
p
p
.
2
4
8
0
~
2
4
8
7
I
SS
N:
1
6
9
3
-
6
9
3
0
,
ac
cr
ed
ited
First Gr
ad
e
b
y
Kem
en
r
is
tek
d
i
k
ti,
Dec
r
ee
No
: 2
1
/E/KPT
/2
0
1
8
DOI
: 1
0
.
1
2
9
2
8
/TE
L
KOM
NI
K
A.
v
1
8
i5
.
1
4
0
2
7
2480
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//jo
u
r
n
a
l.u
a
d
.
a
c.
id
/in
d
ex
.
p
h
p
/TELK
OM
N
I
K
A
Dete
c
ting
Indo
ne
sia
n am
big
uo
us sentences
using
Bo
y
er
-
M
o
o
re
a
lg
o
rithm
Ris
k
y
Aswi Ra
m
a
dh
a
ni
,
I
K
et
ut
G
ede
Da
rm
a
P
utr
a
,
M
a
de
Su
da
rm
a
,
I
.
A.
D
.
G
iria
nt
a
ri
Ud
a
y
a
n
a
Un
i
v
e
rsity
,
In
d
o
n
e
sia
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Sep
2
,
2
0
1
9
R
ev
is
ed
Ap
r
2
,
2
0
2
0
Acc
ep
ted
May
1
,
2
0
2
0
Am
b
ig
u
o
u
s
se
n
ten
c
e
s
a
re
d
iv
i
d
e
d
in
t
o
3
t
y
p
e
s
n
a
m
e
ly
p
h
o
n
e
ti
c
,
l
e
x
ica
l,
a
n
d
g
ra
m
m
a
ti
c
a
l.
Th
is
st
u
d
y
f
o
c
u
s
e
s
o
n
g
ra
m
m
a
ti
c
a
l
a
m
b
ig
u
o
u
s
se
n
ten
c
e
s,
g
ra
m
m
a
ti
c
a
l
a
m
b
ig
u
o
u
s
se
n
ten
c
e
s
a
re
a
m
b
ig
u
it
ies
t
h
a
t
o
c
c
u
r
d
u
e
t
o
in
c
o
rre
c
t
g
ra
m
m
a
r,
b
u
t
th
is
a
m
b
i
g
u
it
y
wi
ll
d
isa
p
p
e
a
r
o
n
c
e
it
is
u
se
d
with
i
n
a
se
n
ten
c
e
.
Am
b
ig
u
o
u
s
se
n
te
n
c
e
s
b
e
c
o
m
e
a
b
ig
p
r
o
b
lem
wh
e
n
th
e
y
a
re
p
r
o
c
e
ss
e
d
b
y
a
c
o
m
p
u
ter.
In
o
r
d
e
r
f
o
r
t
h
e
c
o
m
p
u
ter t
o
i
n
terp
re
t
a
m
b
ig
u
o
u
s wo
r
d
s
c
o
rre
c
tl
y
,
th
is
stu
d
y
se
e
k
s
to
d
e
v
e
lo
p
d
e
te
c
ti
o
n
o
f
In
d
o
n
e
sia
n
a
m
m
b
i
g
u
o
u
s
se
n
ten
c
e
s
u
sin
g
Bo
y
e
r
M
o
o
re
a
lg
o
r
it
h
m
.
T
h
is
a
lg
o
rit
h
m
m
a
tch
e
s
a
m
b
ig
u
o
u
s
se
n
ten
c
e
s
th
a
t
a
re
in
se
rted
a
s
in
p
u
t
wit
h
th
e
d
a
ta
se
t.
Th
e
n
t
h
e
se
n
ten
c
e
is
b
e
in
g
d
e
tec
ted
wh
e
th
e
r
it
c
o
n
tai
n
s
a
m
b
ig
u
o
u
s
s
e
n
ten
c
e
s,
b
y
c
a
lcu
latin
g
th
e
p
e
r
c
e
n
tag
e
o
f
sim
il
a
rit
y
u
sin
g
c
o
sin
e
sim
il
a
rit
y
m
e
th
o
d
.
C
o
sin
e
s
imilarity
sy
ste
m
is
a
b
le
to
fin
d
o
u
t
t
h
e
m
e
a
n
in
g
o
f
t
h
e
se
n
ten
c
e
.
In
th
e
d
a
ta
se
t,
th
e
n
u
m
b
e
r
o
f
a
m
b
ig
u
o
u
s
se
n
ten
c
e
s
th
a
t
c
a
n
b
e
c
o
ll
e
c
ted
is
5
0
wo
rd
s.
T
h
e
5
0
wo
r
d
s
c
o
n
sist
o
f
a
m
b
ig
u
o
u
s
wo
rd
s
d
a
ta,
a
m
b
i
g
u
o
u
s
se
n
ten
c
e
s,
a
n
d
a
m
b
i
g
u
o
u
s
se
n
ten
c
e
m
e
a
n
in
g
s.
T
h
is
sy
ste
m
tri
a
l
wa
s
c
a
rried
o
u
t
fo
r
2
0
0
ti
m
e
s
a
n
d
t
h
e
a
c
c
u
ra
c
y
lev
e
l
wa
s
0
.
9
3
5
,
p
re
c
isio
n
wa
s
0
.
9
3
2
0
,
a
n
d
Re
c
a
ll
wa
s
0
.
8
.
Wh
il
e
th
e
F
-
M
e
a
su
re
wa
s
0
.
8
0
6
1
.
Wh
il
e
t
h
e
sp
e
e
d
f
o
r
wo
r
d
se
a
rc
h
0
.
0
0
3
2
7
5
se
c
o
n
d
s
K
ey
w
o
r
d
s
:
Am
b
ig
u
o
u
s
B
o
y
er
-
Mo
o
r
e
Gr
am
m
atica
l
I
n
d
o
n
esian
s
en
ten
ce
s
Strin
g
T
ex
t
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
:
I
Ketu
t G
ed
e
Dar
m
a
Pu
tr
a
,
Ud
ay
an
a
Un
iv
e
r
s
ity
,
P.
B
.
Su
d
ir
m
an
St.
,
Den
p
asar
,
B
ali,
I
n
d
o
n
esia
.
E
m
ail:
ik
g
d
ar
m
a
p
u
tr
a@
u
n
u
d
.
ac
.
id
1.
I
NT
RO
D
UCT
I
O
N
Am
b
ig
u
o
u
s
s
en
ten
ce
s
ar
e
s
en
ten
ce
s
th
at
h
av
e
m
o
r
e
th
a
n
o
n
e
m
ea
n
i
n
g
.
Am
b
ig
u
o
u
s
s
en
t
en
ce
s
ar
e
d
iv
id
ed
in
to
3
ty
p
es,
n
a
m
ely
p
h
o
n
etic,
lex
ical,
an
d
g
r
am
m
atica
l.
T
h
is
r
esear
ch
will
f
o
cu
s
o
n
g
r
am
m
atica
l
am
b
ig
u
ity
.
Gr
am
m
atica
l
am
b
i
g
u
ity
o
cc
u
r
s
d
u
e
to
in
c
o
r
r
ec
t
g
r
am
m
ar
u
s
ag
e.
Ho
wev
e
r
,
th
i
s
am
b
ig
u
ity
wo
u
ld
d
is
ap
p
ea
r
o
n
ce
it
is
u
s
ed
with
in
a
s
en
ten
ce
[
1
-
4
]
.
I
n
I
n
d
o
n
esian
,
th
e
u
n
a
b
ilit
y
to
u
n
d
er
s
tan
d
am
b
ig
u
o
u
s
s
en
ten
ce
s
o
f
ten
o
cc
u
r
s
d
u
e
to
d
if
f
er
e
n
t
lev
els
o
f
lan
g
u
ag
e
u
s
e,
d
i
f
f
er
en
t
lev
els
o
f
ed
u
ca
tio
n
,
a
n
d
cu
ltu
r
e
[
5
]
.
A
m
b
i
g
u
o
u
s
w
o
r
d
i
s
a
w
o
r
d
h
a
t
h
a
s
a
v
a
g
u
e
(
u
n
c
l
e
a
r
)
n
a
t
u
r
e
,
i
n
I
n
d
o
n
e
s
i
a
n
,
t
h
e
r
e
a
r
e
a
n
u
m
b
e
r
o
f
g
r
a
m
m
a
t
i
c
a
l
a
m
b
i
g
u
o
u
s
w
o
r
d
s
s
u
c
h
a
s
"
b
u
l
a
n
(
m
o
o
n
/
m
o
n
t
h
)
"
.
“
B
u
l
a
n
”
h
a
s
t
w
o
m
e
a
n
i
n
g
s
,
t
h
e
f
i
r
s
t
m
e
a
n
i
n
g
i
s
"
a
n
a
s
t
r
o
n
o
m
i
c
a
l
o
b
j
e
c
t
o
r
b
i
t
t
i
n
g
t
h
e
e
a
r
t
h
"
,
a
n
d
t
h
e
s
e
c
o
n
d
m
e
a
n
i
n
g
m
e
a
n
s
"
a
p
e
r
i
o
d
o
f
t
i
m
e
"
[
6
,
7
]
.
Gr
am
m
atica
l
am
b
ig
u
o
u
s
s
en
ten
ce
s
wo
u
ld
n
o
t
p
o
s
e
a
b
ig
p
r
o
b
lem
w
h
en
u
s
ed
in
d
ir
ec
t
co
n
v
er
s
atio
n
,
d
ir
e
ct
d
ialo
g
u
e
b
etwe
en
h
u
m
an
s
,
an
d
s
en
ten
ce
s
r
ea
d
b
y
h
u
m
a
n
s
[
8
]
.
B
ec
au
s
e
h
u
m
a
n
s
h
av
e
in
tellig
e
n
ce
th
at
ca
n
p
r
o
ce
s
s
,
an
d
a
b
s
o
r
b
am
b
ig
u
o
u
s
wo
r
d
s
in
ac
co
r
d
an
ce
with
th
e
to
p
ic
o
f
c
o
n
v
er
s
ati
o
n
,
an
d
wo
r
d
s
r
elate
d
to
t
h
e
a
m
b
ig
u
o
u
s
s
en
ten
ce
.
T
h
is
is
v
er
y
d
if
f
er
e
n
t
f
r
o
m
c
o
m
p
u
ter
s
,
co
m
p
u
ter
s
d
o
n
o
t
h
a
v
e
th
e
i
n
tellig
en
ce
to
d
etec
t
a
m
b
ig
u
o
u
s
s
en
ten
ce
s
.
B
y
u
s
in
g
t
h
e
g
r
am
m
atica
l
am
b
ig
u
o
u
s
s
en
ten
ce
d
etec
tio
n
s
y
s
tem
,
th
e
s
y
s
tem
is
a
b
le
to
f
in
d
o
u
t
th
e
m
ea
n
i
n
g
o
f
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
Dete
ctin
g
I
n
d
o
n
esia
a
mb
ig
u
o
u
s
s
en
ten
ce
s
u
s
in
g
B
o
ye
r
-
Mo
o
r
e
a
lg
o
r
ith
m
(
I
K
etu
t G
ed
e
Da
r
ma
P
u
tr
a
)
2481
an
am
b
ig
u
o
u
s
s
en
ten
ce
,
an
d
tr
an
s
late
it
ac
co
r
d
in
g
to
th
e
m
ea
n
in
g
[
9
]
.
T
h
is
s
y
s
tem
is
aim
ed
to
en
ab
le
co
m
p
u
ter
to
u
n
d
e
r
s
tan
d
am
b
i
g
u
o
u
s
s
en
ten
ce
s
in
I
n
d
o
n
esian
p
r
o
p
er
l
y
.
R
esear
ch
o
n
g
r
am
m
atica
l
am
b
ig
u
o
u
s
s
en
ten
ce
s
h
as
n
o
t
b
ee
n
wid
ely
d
ev
elo
p
e
d
,
esp
ec
ially
r
eg
ar
d
in
g
th
e
d
etec
tio
n
o
f
I
n
d
o
n
esian
g
r
am
m
atica
l
am
b
ig
u
o
u
s
s
en
ten
ce
s
.
C
u
r
r
en
tly
,
r
esear
ch
es
r
elate
d
to
am
b
ig
u
o
u
s
s
en
ten
ce
s
wer
e
o
n
ly
ab
le
to
f
in
d
am
b
ig
u
o
u
s
s
en
ten
ce
s
b
u
t
wer
e
n
o
t
ab
le
to
u
n
d
er
s
tan
d
th
e
m
ea
n
in
g
o
f
am
b
ig
u
o
u
s
s
en
ten
ce
s
[
1
0
]
.
So
f
ar
,
th
e
d
ata
s
ets
co
v
er
i
n
g
I
n
d
o
n
esian
am
b
ig
u
o
u
s
g
r
am
m
atica
l
s
en
ten
ce
s
ar
e
s
till
n
o
t
av
ailab
le
y
et.
W
h
ile
th
e
a
v
ailab
ilit
y
o
f
g
r
am
m
atica
l
am
b
ig
u
o
u
s
s
en
ten
ce
s
d
etec
to
r
is
h
ig
h
ly
n
ee
d
e
d
.
Fro
in
s
tan
ce
,
in
o
r
d
er
to
im
p
r
o
v
e
th
e
ac
cu
r
ac
y
o
f
a
tr
an
s
lato
r
s
y
s
tem
,
an
d
to
m
ak
e
it
ea
s
ie
r
f
o
r
co
m
p
u
ter
s
to
u
n
d
er
s
tan
d
a
tex
t.
So
,
in
th
is
r
esear
ch
,
th
e
ex
p
ec
ted
n
o
v
elt
y
th
at
will
b
e
ac
h
iev
ed
is
to
c
r
ea
te
a
g
r
am
m
atica
l
am
b
ig
u
o
u
s
s
en
ten
ce
d
etec
tio
n
s
y
s
tem
in
I
n
d
o
n
esian
,
u
s
in
g
th
e
B
o
y
er
-
Mo
o
r
e
alg
o
r
it
h
m
2.
RE
S
E
ARCH
M
E
T
H
O
D
F
i
g
u
r
e
1
e
x
p
l
a
i
n
s
t
h
e
p
r
o
c
e
s
s
e
s
i
n
v
o
l
v
e
d
i
n
t
h
e
a
m
b
i
g
u
o
u
s
s
e
n
t
e
n
c
e
d
e
t
e
c
t
i
o
n
s
y
s
t
e
m
u
s
i
n
g
B
o
y
e
r
-
M
o
o
r
e
a
l
g
o
r
i
t
h
m
.
T
h
i
s
f
l
o
w
c
h
a
r
t
e
x
p
l
a
i
n
s
t
h
e
s
e
n
t
e
n
c
e
b
e
i
n
g
e
n
t
e
r
e
d
,
t
h
e
n
t
h
e
s
e
n
t
e
n
c
e
i
s
c
h
e
c
k
e
d
u
s
i
n
g
B
o
y
e
r
-
M
o
o
r
e
a
l
g
o
r
i
t
h
m
,
s
o
t
h
a
t
i
t
c
a
n
b
e
s
e
l
e
c
t
e
d
w
e
t
h
e
r
t
h
e
s
e
n
t
e
n
c
e
c
o
n
t
a
i
n
s
a
n
y
a
m
b
i
g
u
o
u
s
w
o
r
d
s
.
I
f
t
h
e
s
e
n
t
e
n
c
e
i
s
s
t
a
t
e
d
t
o
c
o
n
t
a
i
n
a
m
b
i
g
u
o
u
s
w
o
r
d
s
,
t
h
e
n
t
h
e
m
e
a
n
i
n
g
o
f
t
h
e
s
e
n
t
e
n
c
e
w
o
u
l
d
b
e
s
e
a
r
c
h
e
d
u
s
i
n
g
C
o
s
i
n
e
S
i
m
i
l
a
r
i
t
y
m
e
t
h
o
d
.
S
e
v
e
r
a
l
s
t
e
p
s
a
r
e
n
e
e
d
e
d
t
o
b
u
i
l
d
t
h
i
s
r
e
s
e
a
r
c
h
;
t
h
e
f
o
l
l
o
w
i
n
g
i
s
t
h
e
r
e
s
e
a
r
c
h
m
e
t
h
o
d
u
s
e
d
.
Fig
u
r
e
1
.
Flo
wch
ar
t
d
etec
tio
n
o
f
am
b
ig
u
o
u
s
I
n
d
o
n
esian
s
en
ten
ce
s
with
B
o
y
er
-
Mo
o
r
e
alg
o
r
ith
m
2
.
1
.
Sente
nce
input
Sen
ten
ce
in
p
u
t
c
o
n
s
is
ts
o
f
s
en
ten
ce
s
wh
ich
ar
e
s
till
u
n
k
n
o
wn
wh
et
h
er
it
co
n
tain
s
am
b
ig
u
ity
.
T
h
e
s
en
ten
ce
s
ar
e
co
n
v
er
s
atio
n
al
s
en
ten
ce
s
in
I
n
d
o
n
esian
.
I
n
I
n
d
o
n
esian
,
th
er
e
ar
e
s
ev
er
al
t
y
p
es
o
f
am
b
ig
u
o
u
s
s
en
ten
ce
s
,
n
am
ely
g
r
am
m
atica
l,
lex
ical,
an
d
p
h
o
n
etic
[
1
1
]
.
T
h
is
r
esear
ch
will
f
o
cu
s
o
n
g
r
a
m
m
atica
l
am
b
ig
u
ity
.
Gr
am
m
atica
l
am
b
ig
u
o
u
s
s
en
te
n
ce
s
ar
e
am
b
ig
u
o
u
s
s
en
ten
ce
s
th
at
o
cc
u
r
d
u
e
t
o
in
co
r
r
ec
t
g
r
a
m
m
ar
u
s
e,
b
u
t
th
is
am
b
ig
u
ity
will d
is
ap
p
ea
r
o
n
ce
it is
u
s
ed
in
a
s
en
ten
ce
.
T
h
e
f
o
llo
win
g
ar
e
e
x
am
p
les o
f
a
m
b
ig
u
o
u
s
s
en
ten
ce
s
“S
etia
p
a
w
a
l b
u
la
n
ka
mi
g
a
jia
n
(
W
e
ar
e
p
aid
at
t
h
e
b
eg
i
n
n
in
g
o
f
ea
c
h
m
o
n
th
)
”
T
h
e
s
en
ten
ce
a
b
o
v
e
c
o
n
tain
s
a
n
am
b
ig
u
o
u
s
wo
r
d
th
at
is
"
b
u
l
a
n
(
m
o
n
th
)
"
,
th
e
w
o
r
d
“
b
u
la
n
"
h
as
two
m
ea
n
i
n
g
s
,
wh
ich
ar
e
;
-
B
u
la
n
(
m
o
n
th
)
=
a
p
e
r
io
d
o
f
ti
m
e
-
B
u
la
n
(
m
o
o
n
)
=
s
k
y
o
b
ject
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6
9
3
0
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
,
Vo
l.
18
,
No
.
5
,
Octo
b
e
r
2
0
2
0
:
2
4
8
0
-
2487
2482
I
n
Fig
u
r
e
2
,
it
is
ex
p
lain
e
d
th
a
t
th
e
wo
r
d
“
b
u
la
n
”
h
as
two
m
ea
n
in
g
s
,
in
wh
ich
o
n
e
r
e
f
er
s
t
o
a
p
ar
ticu
lar
u
n
it
o
f
tim
e
(
m
o
n
th
)
,
an
d
th
e
“b
u
la
n
”
wh
ich
s
h
o
ws
th
e
ea
r
th
'
s
s
atellites
(
m
o
o
n
--
an
o
b
ject
i
n
th
e
s
k
y
)
.
At
th
is
s
tag
e
th
e
m
ea
n
in
g
o
f
th
e
wo
r
d
is
u
n
k
n
o
wn
.
T
h
e
f
o
llo
win
g
is
a
s
im
p
le
d
escr
ip
tio
n
o
f
an
a
m
b
ig
u
o
u
s
wo
r
d
.
Fig
u
r
e
2
.
Gr
am
m
atica
l a
m
b
ig
u
o
u
s
wo
r
d
d
escr
ip
tio
n
2
.
2
.
A
m
big
uo
us
wo
rd
s
ea
rc
h us
ing
B
o
y
er
-
M
o
o
re
B
o
y
er
-
Mo
o
r
e
alg
o
r
ith
m
is
an
alg
o
r
ith
m
u
s
ed
f
o
r
s
tr
in
g
s
ea
r
ch
in
g
[
1
2
-
20
]
.
I
n
co
n
d
u
c
tin
g
s
tr
in
g
s
ea
r
ch
in
g
,
th
e
B
o
y
er
-
Mo
o
r
e
al
g
o
r
ith
m
is
h
ig
h
ly
ac
c
u
r
ate
.
Fo
llo
win
g
ar
e
th
e
s
tep
s
co
n
d
u
cte
d
by
B
o
y
er
-
Mo
o
r
e
alg
o
r
ith
m
to
f
in
d
a
m
b
ig
u
o
u
s
s
en
ten
ce
s
.
2
.
2
.
1
.
1
st
s
t
ep
Fig
u
r
e
3
ex
p
lain
s
th
e
p
r
o
ce
s
s
o
f
s
ea
r
ch
in
g
f
o
r
th
e
am
b
ig
u
o
u
s
wo
r
d
"
b
u
l
a
n
"
in
th
e
s
en
te
n
ce
"
s
etia
p
a
w
a
l
b
u
la
n
ka
mi
g
a
jia
n
(
at
th
e
b
eg
in
n
in
g
o
f
ea
c
h
m
o
n
th
we
a
r
e
p
aid
)
.
"
T
h
is
s
ea
r
ch
is
ca
r
r
ied
o
u
t
f
r
o
m
th
e
f
ir
s
t
s
tr
in
g
,
th
e
s
ea
r
ch
is
ca
r
r
ied
o
u
t
f
r
o
m
t
h
e
lef
t
s
id
e
to
th
e
r
i
g
h
t
s
id
e.
I
f
th
e
wo
r
d
h
as
n
o
t
b
ee
n
f
o
u
n
d
,
th
e
s
ea
r
ch
wo
u
ld
b
e
r
ep
ea
ted
a
g
ain
,
s
tar
tin
g
with
th
e
s
ec
o
n
d
s
tr
in
g
.
Fig
u
r
e
3
.
Am
b
ig
u
o
u
s
wo
r
d
s
e
ar
ch
s
tep
1
2
.
2
.
2
.
2
nd
s
t
ep
Fig
u
r
e
4
ex
p
lain
s
th
e
p
r
o
ce
s
s
o
f
s
ea
r
ch
in
g
f
o
r
th
e
am
b
ig
u
o
u
s
wo
r
d
"
b
u
l
a
n
"
in
th
e
s
en
te
n
ce
"
s
etia
p
a
w
a
l
b
u
la
n
k
a
mi
g
a
jia
n
(
at
th
e
b
eg
in
n
in
g
o
f
ea
ch
m
o
n
th
we
ar
e
p
aid
)
".
T
h
is
p
r
o
ce
s
s
is
a
co
n
tin
u
atio
n
o
f
th
e
f
ir
s
t p
r
o
ce
s
s
,
th
e
s
ea
r
ch
s
tr
in
g
s
tar
ts
f
r
o
m
th
e
s
ec
o
n
d
s
tr
i
n
g
.
Fig
u
r
e
4
.
Am
b
ig
u
o
u
s
wo
r
d
s
e
ar
ch
s
tep
2
2
.
2
.
3
.
1
3
th
s
t
ep
Fig
u
r
e
5
s
h
o
ws
th
at
th
e
p
r
o
ce
s
s
o
f
s
ea
r
ch
in
g
f
o
r
th
e
am
b
ig
u
o
u
s
wo
r
d
“b
u
la
n
”
in
th
e
s
en
ten
ce
"
s
etia
p
a
w
a
l b
u
la
n
ka
mi
g
a
jia
n
(
at
th
e
b
eg
in
n
in
g
o
f
ea
ch
m
o
n
t
h
we
ar
e
p
aid
)
"
h
as b
ee
n
s
u
cc
ess
f
u
l.
T
h
e
wo
r
d
"m
o
o
n
"
is
f
o
u
n
d
o
n
th
e
1
3
th
p
r
o
ce
s
s
,
th
e
wo
r
d
“b
u
la
n
”
was
f
o
u
n
d
i
n
th
e
1
3
th
s
tr
in
g
.
On
th
e
1
3
th
s
tep
,
a
g
r
am
m
atica
l
am
b
ig
u
o
u
s
wo
r
d
was
f
o
u
n
d
;
t
h
e
wo
r
d
is
th
e
wo
r
d
“
b
u
la
n
”
.
I
n
th
is
s
tu
d
y
,
th
e
B
o
y
er
-
Mo
o
r
e
alg
o
r
ith
m
is
u
s
ed
to
ch
ec
k
s
tr
in
g
s
.
I
n
p
u
ts
(
s
en
te
n
ce
s
th
at
ar
e
n
o
t
y
et
k
n
o
wn
to
b
e
g
r
am
m
atica
lly
am
b
ig
u
o
u
s
)
ar
e
b
ein
g
m
atch
ed
with
d
ata
s
ets
o
f
wo
r
d
s
th
at
h
av
e
b
ee
n
id
en
tifie
d
as
g
r
am
m
atica
l
am
b
ig
u
o
u
s
.
At
p
r
esen
t,
th
e
n
u
m
b
er
o
f
d
ata
s
ets
th
at
ca
n
b
e
s
to
r
ed
is
o
n
ly
5
0
;
t
h
is
h
ap
p
e
n
s
b
ec
au
s
e
th
er
e
ar
e
n
o
r
esear
c
h
er
s
wh
o
h
a
v
e
d
ev
el
o
p
ed
ap
p
licatio
n
s
r
elate
d
to
g
r
am
m
atica
l a
m
b
ig
u
o
u
s
s
en
ten
ce
s
in
I
n
d
o
n
esian
.
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
Dete
ctin
g
I
n
d
o
n
esia
a
mb
ig
u
o
u
s
s
en
ten
ce
s
u
s
in
g
B
o
ye
r
-
Mo
o
r
e
a
lg
o
r
ith
m
(
I
K
etu
t G
ed
e
Da
r
ma
P
u
tr
a
)
2483
Fig
u
r
e
5
.
Am
b
ig
u
o
u
s
wo
r
d
s
e
ar
ch
s
tep
13
Fig
u
r
e
6
ex
p
lain
s
th
e
Flo
wch
ar
t
wh
er
e
th
e
am
b
ig
u
o
u
s
wo
r
d
in
a
s
en
ten
ce
is
s
ea
r
ch
ed
,
on
th
e
Flo
wch
ar
t
it
is
s
h
o
wn
th
a
t
if
th
e
am
b
i
g
u
o
u
s
wo
r
d
h
as
n
o
t
b
ee
n
f
o
u
n
d
,
th
en
a
s
ea
r
c
h
is
ca
r
r
ie
d
o
u
t
o
n
th
e
n
ex
t
s
tr
in
g
,
u
n
til
th
e
wo
r
d
is
f
o
u
n
d
o
r
d
ec
lar
e
d
to
b
e
m
is
s
in
g
.
I
f
th
e
wo
r
d
is
f
o
u
n
d
f
r
o
m
th
e
b
e
g
in
n
in
g
,
th
e
s
y
s
tem
will
im
m
ed
iately
b
e
ter
m
in
ate
d
a
n
d
it
ca
n
b
e
d
ec
i
d
ed
th
at
th
e
am
b
ig
u
o
u
s
wo
r
d
e
x
is
ts
.
T
h
e
f
o
llo
win
g
is
a
f
lo
wch
ar
t d
escr
ib
in
g
th
e
B
o
y
er
-
Mo
o
r
e
s
tr
in
g
s
ea
r
c
h
in
g
p
r
o
ce
s
s
.
Fig
u
r
e
6
.
S
tr
in
g
s
ea
r
ch
in
g
f
lo
wch
ar
t
u
s
in
g
b
o
y
er
-
m
o
o
r
e
alg
o
r
ith
m
2
.
3
.
A
m
big
uo
us
s
ent
ence
s
d
a
t
a
SE
T
Gr
am
m
atica
l
am
b
ig
u
o
u
s
s
en
te
n
ce
d
ataset
is
a
co
llectio
n
o
f
a
m
b
ig
u
o
u
s
wo
r
d
s
an
d
s
en
ten
ce
s
u
s
ed
as
a
b
en
ch
m
ar
k
[
2
1
-
2
3
]
.
Sin
ce
u
p
to
th
is
s
tag
e,
th
er
e
was
n
o
am
b
ig
u
o
u
s
s
en
ten
ce
s
f
o
u
n
d
,
th
is
r
esear
ch
h
a
s
co
llected
d
ata
o
n
am
b
ig
u
o
u
s
wo
r
d
s
an
d
s
en
ten
ce
s
f
r
o
m
I
n
d
o
n
esian
lin
g
u
is
ts
.
I
n
th
is
r
es
ea
r
ch
,
th
e
r
eso
u
r
ce
p
er
s
o
n
is
an
I
n
d
o
n
esian
lan
g
u
a
g
e
lectu
r
er
,
E
n
cil
Pu
s
p
ito
n
in
g
r
u
m
,
M.
Pd
.
T
h
e
f
o
llo
win
g
is
a
tab
le
o
f
am
b
ig
u
o
u
s
wo
r
d
s
an
d
s
en
ten
ce
s
o
b
tain
e
d
f
r
o
m
h
er
.
T
ab
le
1
co
n
s
is
ts
o
f
3
r
o
ws,
lin
e
1
is
"Am
b
ig
u
o
u
s
W
o
r
d
s
"
w
h
ich
co
n
tain
s
th
e
lis
t
o
f
am
b
ig
u
o
u
s
wo
r
d
s
.
L
in
e
2
"Sen
ten
ce
s
"
c
o
n
tain
s
s
en
ten
ce
s
th
at
u
s
u
ally
u
s
e
am
b
ig
u
o
u
s
w
o
r
d
s
.
L
in
e
3
is
th
e
“M
ea
n
in
g
”
ea
n
w
h
ich
co
n
tain
s
th
e
m
ea
n
in
g
o
f
t
h
e
am
b
ig
u
o
u
s
s
en
ten
ce
s
.
T
ab
le
1
.
Am
b
i
g
u
o
u
s
wo
r
d
s
an
d
s
en
ten
ce
s
A
mb
i
g
u
o
u
s w
o
r
d
s
S
e
n
t
e
n
c
e
M
e
a
n
i
n
g
Bu
d
i
(
M
i
n
d
)
Ak
u
m
e
n
g
e
n
a
n
g
b
u
d
i
b
a
i
k
m
u
(
I
r
e
memb
e
r
y
o
u
r
k
i
n
d
n
e
ss)
K
e
b
a
i
k
a
n
(
K
i
n
d
n
e
ss)
S
a
l
a
m
(
R
e
g
a
r
d
s
)
G
u
s k
a
m
u
k
e
m
a
r
i
n
m
e
n
d
a
p
a
t
k
a
n
s
a
l
a
m
d
a
ri
a
n
g
g
i
(
G
u
s
,
A
n
g
g
i
se
n
t
y
o
u
r
e
g
a
r
d
s
y
e
s
t
e
r
d
a
y
)
S
a
p
a
a
n
(
G
r
e
e
t
i
n
g
s)
T
a
h
u
(
T
o
f
u
)
Ag
u
s k
e
si
n
i
t
a
d
i
m
e
m
b
e
ri
t
a
h
u
(
A
g
u
s
c
a
me
h
e
r
e
t
o
g
i
v
e
u
s
t
o
f
u
)
Ma
k
a
n
a
n
(
F
o
o
d
)
Bu
n
g
a
(
I
n
t
e
r
e
st
)
Bu
n
g
a
d
e
p
o
si
t
o
d
i
b
a
n
k
j
a
t
i
m
l
u
m
a
y
a
n
t
i
n
g
g
i
(
Th
e
d
e
p
o
s
i
t
i
n
t
e
r
e
st
r
a
t
e
i
n
B
a
n
k
Ja
t
i
m
i
s
q
u
i
t
e
h
i
g
h
)
K
e
u
n
t
u
n
g
a
n
(
P
r
o
f
i
t
)
Ba
n
g
k
u
(
B
e
n
c
h
)
D
i
a
t
i
d
a
k
p
e
r
n
a
h
m
a
k
a
n
b
a
n
g
k
u
s
e
k
o
l
a
h
(
H
e
n
e
v
e
r
w
e
n
t
t
o
sc
h
o
o
l
)
Pe
n
d
i
d
i
k
a
n
(
Ed
u
c
a
t
i
o
n
)
K
e
m
a
s
(
O
r
g
a
n
i
z
e
d
)
Ac
a
r
a
i
n
i
d
i
k
e
m
a
s
d
e
n
g
a
n
s
a
n
g
a
t
b
a
i
k
(
Th
i
s
e
v
e
n
t
i
s
v
e
r
y
w
e
l
l
o
r
g
a
n
i
z
e
d
)
Me
l
a
k
u
k
a
n
p
e
k
e
r
j
a
a
n
(
D
o
i
n
g
w
o
r
k
)
Bu
l
a
n
(
M
o
n
t
h
)
Aw
a
l
Bu
l
a
n
K
a
m
u
g
a
j
i
a
n
(
Y
o
u
a
r
e
p
a
i
d
a
t
t
h
e
b
e
i
n
n
i
n
g
o
f
t
h
e
m
o
n
t
h
)
Wa
k
t
u
(
T
i
me)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6
9
3
0
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
,
Vo
l.
18
,
No
.
5
,
Octo
b
e
r
2
0
2
0
:
2
4
8
0
-
2487
2484
2
.
4
.
Co
s
ine sim
ila
rit
y
T
h
e
s
en
ten
ce
s
in
p
u
tted
ar
e
ca
lcu
lated
in
ter
m
s
o
f
th
eir
r
ese
m
b
lan
ce
to
th
e
s
en
ten
ce
s
in
t
h
e
d
ata
s
et.
I
n
o
r
d
er
to
ca
lcu
late
s
im
ilar
ities
b
etwe
en
s
en
ten
ce
s
,
co
s
i
n
e
s
im
ilar
ity
is
u
s
ed
[
2
4
-
2
8
]
.
I
n
th
is
r
esear
ch
,
th
e
s
en
ten
ce
to
b
e
u
s
ed
as
in
p
u
t
is
"
s
etia
p
a
w
a
l
b
u
la
n
ka
mi
g
a
jia
n
".
T
h
e
s
en
ten
ce
h
as
b
ee
n
i
d
en
tifie
d
to
co
n
tain
a
g
r
am
m
atica
l a
m
b
i
g
u
o
u
s
wo
r
d
,
"
b
u
la
n
(
m
o
n
th
)
"
.
Sen
ten
ce
s
r
elate
d
to
"
b
u
la
n
(
m
o
n
t
h
)
"
ar
e:
-
A
w
a
l b
u
la
n
ka
mi
g
a
jia
n
(
W
e
ar
e
p
aid
at
th
e
b
eg
in
n
in
g
o
f
th
e
m
o
n
th
).
-
B
u
mi
d
a
n
b
u
l
a
n
meru
p
a
ka
n
b
e
n
d
a
l
a
n
g
it
(
T
h
e
E
ar
t
h
an
d
T
h
e
Mo
o
n
ar
e
s
k
y
o
b
jects).
B
y
u
s
in
g
co
s
in
e
s
im
ilar
ity
,
we
ca
n
f
in
d
t
h
e
s
im
ilar
ity
o
f
a
s
tr
in
g
.
Af
ter
th
e
s
tr
in
g
s
im
ilar
ity
is
k
n
o
wn
,
th
e
s
y
s
tem
is
ab
le
to
s
h
o
w
th
e
m
ea
n
in
g
o
f
t
h
e
s
en
ten
ce
.
T
h
e
f
o
llo
win
g
is
th
e
co
s
in
e
s
im
ilar
ity
al
g
o
r
ith
m
p
r
o
ce
s
s
in
g
.
I
n
a
m
o
r
e
d
etaile
d
ex
p
lan
atio
n
,
th
e
ex
a
m
p
le
u
s
ed
is
th
e
clo
s
en
ess
b
etwe
en
"
a
w
a
l
b
u
la
n
ka
mi
g
a
jia
n
”
(
W
e
a
r
e
p
ai
d
at
t
h
e
b
eg
in
n
in
g
o
f
ea
c
h
m
o
n
th
)
an
d
“a
w
a
l
b
u
la
n
ka
mu
g
a
jia
n
”
(
Y
o
u
ar
e
p
aid
at
th
e
b
eg
in
n
in
g
o
f
ea
ch
m
o
n
th
)
".
-
S1
=
a
w
a
l b
u
l
a
n
ka
mi
g
a
jia
n
(
W
e
ar
e
ap
id
at
th
e
b
eg
in
n
in
g
o
f
th
e
m
o
n
th
)
.
-
S2
=
a
w
a
l b
u
l
a
n
ka
m
u
g
a
jia
n
(
Yo
u
a
r
e
p
aid
at
th
e
b
e
g
in
n
i
n
g
o
f
th
e
m
o
n
th
)
.
T
ab
le
2
ex
p
lain
s
th
e
ex
is
ten
ce
o
f
ea
ch
wo
r
d
in
a
s
en
ten
ce
.
I
f
th
e
wo
r
d
is
co
n
tain
ed
in
th
e
s
e
n
ten
ce
,
co
d
e
1
will
b
e
g
iv
en
in
lin
e
A.
C
o
n
v
er
s
ely
,
co
d
e
0
will b
e
g
iv
e
n
wh
en
t
h
e
wo
r
d
is
n
o
t
f
o
u
n
d
in
t
h
e
s
en
ten
ce
.
T
ab
le
2
.
Am
b
i
g
u
o
u
s
wo
r
d
s
an
d
s
en
ten
ce
s
W
o
r
d
C
o
u
n
t
A
B
A
.
B
A
2
B
2
Aw
a
l
(
b
e
g
i
n
n
i
n
g
)
1
1
1
1
1
Bu
l
a
n
(
m
o
n
t
h
)
1
1
1
1
1
K
a
m
i
(
w
e
)
1
0
0
1
0
K
a
m
u
(
y
o
u
)
0
1
0
0
1
G
a
j
i
a
n
(
p
a
i
d
)
1
0
0
1
0
2
4
3
C
o
s
in
e
Similar
ity
is
a
m
eth
o
d
u
s
ed
to
ca
lcu
late
th
e
d
e
g
r
ee
o
f
s
im
ilar
ity
b
etwe
en
tw
o
o
b
jects.
Fo
r
th
e
p
u
r
p
o
s
e
o
f
d
ata
clu
s
t
er
in
g
,
a
g
o
o
d
f
u
n
ctio
n
is
th
e
C
o
s
in
e
Similar
ity
f
u
n
ctio
n
.
Fo
r
th
e
s
et
n
o
tatio
n
th
e
f
o
r
m
u
la
as sh
o
wn
in
(
1
)
:
=
c
os
(
)
=
A
.
B
|
|
A
|
|
B
|
|
(
1
)
=
2
(
4
x
3
)
=
0
.
166
Af
ter
b
ein
g
ca
lcu
lated
u
s
in
g
th
e
C
o
s
in
e
Similar
i
ty
m
eth
o
d
,
th
e
h
ig
h
est
clo
s
en
ess
i
s
0
.
1
6
6
.
Mo
r
e
d
etailed
ex
p
lan
atio
n
is
s
h
o
wn
in
T
ab
l
e
3
.
I
n
T
ab
le
3
two
v
alu
es
ap
p
ea
r
,
wh
ich
a
r
e
0
.
1
6
an
d
0
.
0
5
.
Giv
en
th
e
h
i
g
h
s
im
ilar
ity
v
alu
e
o
f
th
e
s
en
ten
c
es
“s
et
ia
p
a
w
a
l
b
u
la
n
ka
mi
g
a
jia
n
”
an
d
“s
etia
p
a
w
a
l
b
u
la
n
k
a
mu
g
a
jia
n
”
.
I
t
ca
n
b
e
co
n
d
lu
d
ed
th
at
th
e
wo
r
d
“b
u
la
n
”
in
th
e
s
en
ten
ce
m
ea
n
s
“
a
p
er
io
d
o
f
tim
e”
.
T
ab
le
3
.
T
h
e
r
esu
lts
o
f
an
a
y
zi
n
g
th
e
m
ea
n
in
g
o
f
s
en
ten
ce
s
u
s
in
g
c
o
n
f
u
s
io
n
m
atr
ix
m
eth
o
d
Id
I
n
p
u
t
S
e
n
t
e
n
c
e
s
D
a
t
a
S
e
t
V
a
l
u
e
o
f
S
i
mi
l
a
r
i
t
y
1
S
e
t
i
a
p
a
w
a
l
b
u
l
a
n
k
a
m
i
g
a
j
i
a
n
(
W
e
a
r
e
p
a
i
d
a
t
t
h
e
b
e
g
i
n
n
i
n
g
o
f
e
a
c
h
m
o
n
t
h
)
S
e
t
i
a
p
a
w
a
l
b
u
l
a
n
k
a
m
u
g
a
j
i
a
n
(
Y
o
u
a
r
e
p
a
i
d
a
t
t
h
e
b
e
g
i
n
n
i
n
g
o
f
e
a
c
h
mo
n
t
h
)
0
.
16
2
S
e
t
i
a
p
a
w
a
l
b
u
l
a
n
k
a
m
i
g
a
j
i
a
n
(
W
e
a
r
e
p
a
i
d
a
t
t
h
e
b
e
g
i
n
n
i
n
g
o
f
e
a
c
h
m
o
n
t
h
)
Bu
m
i
d
a
n
b
u
l
a
n
m
e
ru
p
a
k
a
n
b
e
n
d
a
l
a
n
g
i
t
(
Ea
r
t
h
a
n
d
mo
o
n
a
r
e
s
k
y
o
b
j
e
c
t
s)
0
.
05
2
.
5
.
Det
er
m
ini
ng
t
he
m
ea
ni
ng
o
f
s
ent
ence
s
when bei
ng
p
ro
ce
s
s
ed
in t
he
pro
g
ra
m
Fro
m
th
e
B
o
y
er
-
Mo
o
r
e
Alg
o
r
i
th
m
an
d
C
o
s
in
e
Similar
ity
p
r
o
ce
s
s
es
s
o
m
e
r
esu
lts
ar
e
o
b
tain
e
d
[
2
9
,
3
0
]
.
T
h
ese
r
esu
lts
s
tated
th
at
“
b
u
la
n
”
in
th
e
in
p
u
t
s
en
ten
ce
m
ea
n
s
a
p
er
io
d
o
f
tim
e
(
m
o
n
th
)
.
Fo
llo
win
g
ar
e
th
e
r
esu
lts
o
b
tain
ed
,
t
h
e
r
esu
lts
ar
e
also
i
m
p
lem
en
ted
o
n
th
e
web
.
Fig
u
r
e
7
d
is
cu
s
s
es
th
e
r
esu
lts
o
f
ca
l
cu
latio
n
s
p
er
f
o
r
m
ed
b
y
u
s
in
g
C
o
s
in
e
Similiar
ity
m
eth
o
d
.
At
th
is
s
tag
e
th
e
s
en
ten
ce
“
S
etia
p
a
w
a
l
b
u
l
a
n
ka
mi
g
a
jia
n
(
we
ar
e
p
ai
d
at
th
e
b
eg
in
n
in
g
o
f
ea
ch
wee
k
)
“
h
ad
b
ee
n
test
ed
f
o
r
th
e
s
m
i
liar
ity
with
th
e
s
en
ten
ce
"
S
etia
p
a
w
a
l b
u
la
n
ka
mu
g
a
jia
n
(
y
o
u
ar
e
p
aid
at
th
e
b
e
g
in
n
in
g
o
f
ea
c
h
m
o
n
th
)
an
d
"
B
u
mi
d
a
n
B
u
la
n
meru
p
a
k
a
n
b
en
d
a
la
n
g
it
(
T
h
e
E
ar
th
an
d
T
h
e
Mo
o
n
ar
e
s
k
y
o
b
jects)"
.
Af
ter
b
ein
g
ca
lcu
late
d
u
s
in
g
C
o
s
in
e
Similar
ity
m
eth
o
d
,
th
e
s
en
ten
ce
h
as
b
ee
n
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
Dete
ctin
g
I
n
d
o
n
esia
a
mb
ig
u
o
u
s
s
en
ten
ce
s
u
s
in
g
B
o
ye
r
-
Mo
o
r
e
a
lg
o
r
ith
m
(
I
K
etu
t G
ed
e
Da
r
ma
P
u
tr
a
)
2485
p
r
o
v
e
n
to
h
a
v
e
clo
s
en
ess
in
m
ea
n
in
g
with
th
e
s
en
ten
ce
"
S
etia
p
a
w
a
l
b
u
la
n
ka
mi
g
a
jia
n
(
W
e
a
r
e
p
aid
at
th
e
b
eg
in
n
in
g
o
f
ea
ch
m
o
n
t
h
)
"
th
is
s
en
ten
ce
co
n
tais
w
o
r
d
”b
u
la
n
”
wh
ich
m
ea
n
s
a
p
er
io
d
o
f
tim
e
(
m
o
n
th
)
with
th
e
v
alu
e
o
f
s
im
ilar
ity
+
o
f
0
.
1
6
.
Fig
u
r
e
7
.
T
h
e
r
esu
lts
o
f
d
etec
ti
n
g
g
r
a
m
m
atica
l a
m
b
ig
u
o
u
s
s
en
ten
ce
s
u
s
in
g
co
s
in
e
s
im
ilar
ity
3.
RE
SU
L
T
S
A
ND
AN
AL
Y
SI
S
3
.
1
.
Acc
ura
cy
,
prec
is
io
n,
re
ca
ll a
nd
F
-
m
ea
s
ure
t
est
At
th
is
s
tag
e,
th
e
s
y
s
tem
is
tes
ted
u
s
in
g
a
co
n
f
u
s
io
n
m
atr
ix
,
wh
ich
is
o
f
ten
u
s
ed
to
f
in
d
o
u
t
p
r
ec
is
io
n
,
ac
cu
r
ac
y
,
a
n
d
r
ec
all
[
3
1
-
3
3
]
.
W
ith
th
e
co
n
f
u
s
io
n
m
atr
ix
,
it
c
an
b
e
s
ee
n
h
o
w
well
th
e
s
y
s
tem
is
ab
le
to
u
n
d
er
s
tan
d
g
r
am
m
atica
lly
am
b
ig
u
o
u
s
s
en
ten
ce
s
.
T
h
is
s
y
s
tem
ex
p
e
r
im
e
n
t
h
as
b
ee
n
ca
r
r
ied
o
u
t
2
0
0
tim
es.
W
h
ile
th
er
e
ar
e
5
0
wo
r
d
s
in
t
h
e
d
atab
ase
wh
ic
h
ar
e
am
b
ig
u
o
u
s
wo
r
d
s
,
th
is
wo
r
d
is
ca
lled
T
r
u
e
Po
s
itiv
e
(
T
P
)
.
W
h
en
s
ep
ar
atin
g
am
b
ig
u
o
u
s
wo
r
d
s
th
er
e
is
also
an
er
r
o
r
,
wh
ich
is
an
u
n
am
b
ig
u
o
u
s
w
o
r
d
b
u
t
an
am
b
i
g
u
o
u
s
wo
r
d
is
ca
p
tu
r
e
d
,
th
is
wo
r
d
is
ca
lled
f
alse p
o
s
itiv
e
(
FP
)
.
I
n
s
o
m
e
ca
s
es,
th
e
r
e
a
r
e
am
b
ig
u
o
u
s
wo
r
d
s
b
u
t
ca
n
n
o
t
b
e
r
e
co
g
n
ize
d
b
y
th
e
s
y
s
tem
,
th
is
wo
r
d
is
ca
lle
d
f
alse
n
eg
ativ
e
(
FN)
.
W
h
er
ea
s
wo
r
d
s
th
at
ar
e
n
o
t
am
b
ig
u
o
u
s
ar
e
ca
lled
tr
u
e
n
eg
ativ
es (
T
N
).
T
h
e
ca
lcu
latio
n
s
ca
n
b
e
s
ee
n
in
T
ab
le
4
.
T
ab
le
4
.
C
o
n
f
u
s
io
n
m
atr
ix
v
al
u
e
TP=
40
F
P
=
3
FN
=
1
0
TN
=
1
4
7
=
40
+
187
40
+
147
+
3
+
10
=
0
.
935
(
2
)
=
40
40
+
3
=
0
.
9302
(
3
)
40
40
+
3
=
0
.
8
(
4
)
T
h
e
v
alu
e
s
ca
le
o
f
m
atr
ix
c
o
n
f
u
s
io
n
r
a
n
g
es
f
r
o
m
0
-
1
.
F
r
o
m
th
e
ab
o
v
e
ca
lcu
latio
n
it
is
o
b
tain
ed
th
e
v
alu
e
o
f
ac
c
u
r
ac
y
w
h
ich
i
s
0
.
9
3
5
,
Pre
cisi
o
n
is
0
.
9
3
2
0
,
an
d
R
ec
all
is
0
.
8
.
J
u
d
g
in
g
f
r
o
m
th
e
r
ec
all
v
alu
e,
th
e
s
y
s
tem
is
ab
le
to
r
ec
o
g
n
iz
e
am
b
ig
u
o
u
s
wo
r
d
s
as
m
u
ch
a
s
8
0
%.
Me
an
wh
ile,
th
e
l
ac
k
o
f
d
ata
s
ets
h
as
m
ad
e
th
e
s
y
s
tem
u
n
ab
le
to
r
ec
o
g
n
iz
e
am
b
ig
u
o
u
s
wo
r
d
s
.
F
-
Me
asu
r
e
is
o
n
e
o
f
th
e
ev
al
u
atio
n
ca
lc
u
latio
n
s
m
eth
o
d
in
r
etr
iev
in
g
in
f
o
r
m
atio
n
th
at
c
o
m
b
in
es
r
ec
all
a
n
d
p
r
ec
is
io
n
.
T
h
e
v
alu
e
s
o
f
r
ec
all
a
n
d
p
r
ec
is
io
n
in
a
s
itu
atio
n
m
ig
h
t
b
ea
r
d
if
f
er
e
n
t
weig
h
ts
.
T
h
e
m
ea
s
u
r
em
en
t
th
at
d
is
p
lay
s
th
e
r
ec
ip
r
o
city
b
etwe
en
r
ec
al
l
an
d
p
r
ec
is
io
n
is
th
e
F
-
Me
asu
r
e,
wh
ich
is
t
h
e
w
eig
h
t
o
f
th
e
h
a
r
m
o
n
ic
m
ea
n
o
f
th
e
R
ec
all
an
d
P
r
ec
is
io
n
.
T
h
e
f
-
m
ea
s
u
r
e
r
a
n
g
e
is
b
etwe
en
0
-
1
.
F
r
o
m
th
e
ab
o
v
e
ca
lcu
latio
n
,
th
e
F
-
m
ea
s
u
r
e
v
al
u
e
is
0
.
8
6
.
1
=
2
∗
0
.
93
0
2
∗
0
,
8
0
.
93
0
2
+
0
,
8
=
2
∗
0
.
744
1
.
73
=
0
.
8601
(
5
)
3
.
2
.
T
he
s
peed
in det
ec
t
ing
a
m
big
uo
us
wo
rds
I
n
u
n
d
e
r
s
tan
d
in
g
g
r
am
m
atica
l
am
b
ig
u
o
u
s
s
en
ten
ce
s
,
th
e
s
y
s
te
m
r
eq
u
ir
es
d
if
f
er
e
n
t
tim
e
to
p
r
o
ce
s
s
ea
ch
s
en
ten
ce
;
th
e
p
r
o
ce
s
s
in
g
o
f
th
is
s
en
ten
ce
d
ep
en
d
s
o
n
th
e
n
u
m
b
er
o
f
ch
ar
ac
ter
s
u
n
d
er
s
to
o
d
[
3
4
]
.
T
h
e
av
er
ag
e
s
en
ten
ce
s
ea
r
ch
v
alu
e
is
0
.
0
0
3
2
7
5
.
T
h
er
e
is
a
n
e
e
d
f
o
r
s
p
ee
d
ca
lcu
latio
n
s
to
a
n
aly
ze
s
y
s
tem
p
er
f
o
r
m
an
ce
.
Am
b
ig
u
o
u
s
s
en
ten
ce
d
etec
tio
n
s
p
ee
d
is
p
r
esen
ted
in
T
ab
le
5
.
T
h
e
h
ig
h
est
s
p
ee
d
in
th
is
s
p
ee
d
d
etec
to
r
is
0
.
0
0
2
4
to
d
etec
t
th
e
s
en
ten
ce
"
Dia
b
a
g
a
i
ku
d
a
h
ita
m
(
He
is
lik
e
a
d
ar
k
h
o
r
s
e
)
"
.
W
h
ile
th
e
lo
w
est
s
p
ee
d
is
0
.
0
0
4
2
in
th
e
s
en
ten
ce
"
A
c
a
r
a
in
i
d
ikem
a
s
d
en
g
a
n
s
a
n
g
a
t
b
a
ik
(
T
h
is
ev
en
t
is
v
er
y
well
o
r
g
a
n
ized
)
”.
T
h
e
f
o
llo
win
g
tab
le
s
h
o
ws th
e
r
ate
o
f
s
p
ee
d
i
n
d
etec
tin
g
am
b
ig
u
o
u
s
wo
r
d
s
:
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6
9
3
0
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
,
Vo
l.
18
,
No
.
5
,
Octo
b
e
r
2
0
2
0
:
2
4
8
0
-
2487
2486
T
ab
le
5
.
Sp
ee
d
in
d
etec
tin
g
a
m
b
ig
u
o
u
s
wo
r
d
s
A
mb
i
g
u
o
u
s w
o
r
d
s
S
e
n
t
e
n
ces
S
p
e
e
d
K
e
m
a
s
(
o
r
g
a
n
i
z
e
d
)
Ac
a
r
a
i
n
i
d
i
k
e
m
a
s
d
e
n
g
a
n
s
a
n
g
a
t
b
a
i
k
(
Th
i
s
e
v
e
n
t
i
s
v
e
r
y
w
e
l
l
o
r
g
a
n
i
z
e
d
)
0
.
0
0
4
2
Bu
d
i
(
M
i
n
d
)
Ak
u
m
e
n
g
e
n
a
n
g
b
u
d
i
b
a
i
k
m
u
Ak
u
m
e
n
g
e
n
a
n
g
b
u
d
i
b
a
i
k
m
u
(
I
r
e
memb
e
r
i
y
o
u
r
k
i
n
d
n
e
ss)
0
.
0
0
3
6
S
a
l
a
m
(
R
e
g
a
r
d
s
)
G
u
s k
a
m
u
k
e
m
a
r
i
n
m
e
n
d
a
p
a
t
k
a
n
s
a
l
a
m
d
a
ri
a
n
g
g
i
(
G
u
s
,
A
n
g
g
i
se
n
t
y
o
u
r
e
g
a
r
d
s
y
e
st
e
r
d
a
y
)
0
.
0
0
3
9
T
a
h
u
(
T
o
f
u
)
Ag
u
s k
e
si
n
i
t
a
d
i
m
e
m
b
e
ri
t
a
h
u
(
A
g
u
s
c
a
me
h
e
r
e
t
o
g
i
v
e
u
s
t
o
f
u
)
0
.
0
0
3
9
Bu
n
g
a
(
I
n
t
e
r
e
st
)
Bu
n
g
a
d
e
p
o
si
t
o
d
i
b
a
n
k
j
a
t
i
m
l
u
m
a
y
a
n
t
i
n
g
g
i
(
Th
e
d
e
p
o
si
t
i
n
t
e
r
e
s
t
r
a
t
e
i
n
B
a
n
k
Jat
i
m
i
s
q
u
i
t
e
h
i
g
h
)
0
.
0
0
3
7
Ba
n
g
k
u
(
B
e
n
c
h
)
D
i
a
t
i
d
a
k
p
e
r
n
a
h
m
a
k
a
n
b
a
n
g
k
u
s
e
k
o
l
a
h
(
h
e
n
e
v
e
r
w
e
n
t
t
o
s
c
h
o
o
l
)
0
.
0
0
4
3
K
u
d
a
(
H
o
r
se)
D
i
a
b
a
g
a
i
k
u
d
a
h
i
t
a
m
(
H
e
i
s
l
i
k
e
a
d
a
r
k
h
o
r
se)
0
.
0
0
2
4
4.
CO
NCLU
SI
O
N
Gr
am
m
atica
l
am
b
ig
u
o
u
s
s
en
ten
ce
s
in
I
n
d
o
n
esian
ar
e
s
en
ten
ce
s
th
at
h
av
e
two
m
ea
n
in
g
s
.
T
o
r
ec
o
g
n
ize
am
b
ig
u
o
u
s
s
en
ten
ce
s
,
we
n
e
ed
a
B
o
y
er
-
Mo
o
r
e
alg
o
r
ith
m
an
d
c
o
s
in
e
s
im
ilar
ity
alg
o
r
ith
m
.
B
o
y
er
-
M
o
o
r
e
alg
o
r
ith
m
is
u
s
ed
to
f
in
d
s
tr
in
g
s
(
am
b
ig
u
o
u
s
s
en
ten
ce
s
)
.
W
h
il
e
th
e
co
s
in
e
s
im
ilar
ity
a
lg
o
r
ith
m
is
u
s
ed
to
ca
lcu
late
th
e
d
e
g
r
ee
o
f
s
im
ilar
ity
b
etwe
en
two
o
b
jects.
C
o
s
in
e
si
m
ilar
ity
ca
n
b
e
u
s
ed
to
f
in
d
o
u
t
th
e
m
ea
n
in
g
o
f
a
s
en
ten
ce
,
b
y
ca
lcu
latin
g
th
e
s
im
ilar
ity
o
f
th
e
test
d
ata
to
th
e
d
ata
s
et.
T
h
e
B
o
y
er
-
M
o
o
r
e
alg
o
r
i
th
m
an
d
th
e
C
o
s
in
e
s
im
ilar
ity
alg
o
r
ith
m
ar
e
v
er
y
ef
f
ec
tiv
e
f
o
r
d
etec
tin
g
am
b
ig
u
o
u
s
wo
r
d
s
.
T
h
is
ca
n
b
e
p
r
o
v
e
n
b
y
th
e
s
u
cc
ess
r
ate
o
f
th
e
s
y
s
t
em
in
r
etr
iev
in
g
in
f
o
r
m
atio
n
(
r
ec
all)
o
f
8
0
%.
W
h
ile
th
e
av
er
ag
e
s
p
ee
d
o
f
th
e
B
o
y
er
-
Mo
o
r
e
alg
o
r
ith
m
w
h
en
d
etec
tin
g
am
b
ig
u
o
u
s
s
en
t
en
ce
s
tak
es 0
.
0
0
3
2
7
5
s
ec
o
n
d
s
.
RE
F
E
R
E
NC
E
S
[1
]
C
h
a
rin
a
I
.
N
.
,
“
Lex
ica
l
a
n
d
S
y
n
t
a
c
ti
c
Am
b
ig
u
it
y
in
H
u
m
o
r
,”
In
te
rn
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
H
u
ma
n
it
y
S
tu
d
ies
,
v
o
l
.
1
,
n
o
.
1
,
p
p
.
1
2
0
-
1
3
1
,
S
e
p
tem
b
e
r
2
0
1
7
.
[2
]
S
o
y
u
sia
wa
ty
D
.
,
Ariwi
b
o
w
o
E
.
,
“
De
sig
n
in
g
a
n
d
Im
p
lem
e
n
ti
n
g
P
a
rsin
g
f
o
r
Am
b
ig
u
o
u
s
S
e
n
ten
c
e
s
in
I
n
d
o
n
e
sia
n
Lan
g
u
a
g
e
,”
J
o
u
r
n
a
l
o
f
T
h
e
o
re
ti
c
a
l
a
n
d
A
p
p
l
ied
I
n
fo
rm
a
ti
o
n
T
e
c
h
n
o
lo
g
y
,
v
o
l.
8
4
,
n
o
.
3
,
p
p
.
3
3
9
-
3
4
7
,
2
0
1
6
.
[3
]
A
n
d
a
rin
i
S
.
R
.
P
.
,
An
u
g
e
ra
h
wa
t
i
M
.
G
.
,
“
S
tru
c
t
u
ra
l
Am
b
ig
u
it
y
in
Th
e
Ja
k
a
rta
P
o
st
Ne
ws
p
a
p
e
r’s
He
a
d
li
n
e
Ne
ws
,”
En
g
li
s
h
L
a
n
g
u
a
g
e
E
d
u
c
a
ti
o
n
U
n
i
v
e
rs
it
a
s Ne
g
e
ri M
a
l
a
n
g
,
v
o
l
.
4
,
n
o
.
2
,
p
p
.
1
-
1
5
,
2
0
1
3
.
[4
]
M
o
u
k
rim
C
.
,
e
t
a
l
.
,
“
An
in
n
o
v
a
ti
v
e
a
p
p
r
o
a
c
h
to
a
u
t
o
c
o
rre
c
ti
n
g
g
ra
m
m
a
ti
c
a
l
e
rro
rs
in
Ara
b
ic
tex
ts
,”
J
o
u
rn
a
l
o
f
Kin
g
S
a
u
d
U
n
ive
rs
it
y
-
Co
mp
u
ter
a
n
d
I
n
fo
rm
a
t
io
n
S
c
ien
c
e
s
,
F
e
b
ru
a
ry
2
0
1
9
.
[5
]
De
n
n
is
D
.
,
De
wi
I
.
I
.
,
“
S
t
u
d
e
n
ts
u
n
d
e
rsta
n
d
i
n
g
o
f
a
m
b
i
g
u
o
u
s
se
n
ten
c
e
s
in
we
b
sites
,”
H
u
m
a
n
i
o
r
a
,
v
o
l.
2
,
n
o
.
1
,
p
p
.
3
8
1
-
3
9
4
,
Ap
r
il
2
0
1
1
.
[6
]
U
li
n
ian
sy
a
h
M
.
T
.
,
e
t
a
l
.,
“
S
o
lv
i
n
g
A
m
b
ig
u
it
ies
i
n
In
d
o
n
e
sia
n
w
o
rd
s
b
y
m
o
r
p
h
o
lo
g
ica
l
a
n
a
l
y
sis
u
sin
g
m
in
imu
m
c
o
n
n
e
c
ti
v
it
y
c
o
st
,”
J
o
u
rn
a
l
o
f
n
a
t
u
ra
l
l
a
n
g
u
a
g
e
Pr
o
c
e
ss
in
g
,
v
o
l.
2
,
n
o
.
3
,
J
u
ly
1
9
9
5
.
[7
]
Clare
Q
.
C
.
,
“
Lan
g
u
a
g
e
a
m
b
i
g
u
it
y
:
A
c
u
rse
a
n
d
a
b
les
sin
g
,”
L
it
e
ra
ry
T
ra
n
sla
t
io
n
,
v
o
l
.
7
,
n
o
.
1
,
p
p
.
1
-
4
,
2
0
0
3
.
[8
]
Rit
a
n
Y
.
C
.
G
.
,
“
Am
b
ig
u
ty
a
n
d
tree
stru
c
t
u
re
o
f
se
ten
c
e
s
i
n
h
o
m
e
m
o
v
ie
,”
Th
e
sis
U
n
iv
e
rsitas
S
a
n
a
ta
Da
rm
a
Yo
g
y
a
k
a
rta
,
2
0
1
8
.
[9
]
G
a
tt
A
.
,
Kra
m
h
e
r
E
.
,
“
S
u
r
v
e
y
o
f
th
e
sta
te
o
f
th
e
a
rt
i
n
n
a
tu
ra
l
la
n
g
u
a
g
e
g
e
n
e
ra
ti
o
n
:
c
o
re
tas
k
s,
a
p
p
li
c
a
ti
o
n
s
a
n
d
e
v
a
lu
a
ti
o
n
,”
J
o
u
rn
a
l
o
f
Arti
fi
c
i
a
l
In
telli
g
e
n
c
e
Res
e
a
rc
h
,
v
o
l.
6
1
,
n
o
.
1
,
p
p
.
6
5
-
7
0
,
2
0
1
8
.
[1
0
]
Rizk
i
T
.
D.
,
Y
u
slian
i
N
.
,
“
De
sig
n
a
n
d
b
u
il
d
a
n
a
m
b
ig
u
it
y
c
h
e
c
k
i
n
g
sy
ste
m
f
o
r
I
n
d
o
n
e
sia
n
se
n
ten
c
e
s
u
sin
g
h
a
rm
o
n
y
se
a
rc
h
a
lg
o
rit
h
m
(in
Ba
h
a
sa
:
Ra
n
c
a
n
g
b
a
n
g
u
n
siste
m
p
e
n
g
e
c
e
k
a
n
a
m
b
ig
u
it
s
k
a
li
m
a
t
b
e
rb
a
h
a
sa
I
n
d
o
n
e
sia
m
e
n
g
u
n
a
k
a
n
h
a
rm
o
n
y
se
a
rc
h
a
lg
o
rit
h
m
),
”
A
n
n
u
a
l
Res
e
a
rc
h
S
e
mi
n
a
r
,
v
o
l.
2
,
n
o
.
1
,
2
0
1
6
.
[1
1
]
A
n
wa
ri
Y
.
,
e
t
a
l
.
,
“
An
a
l
y
sis
o
f
a
m
b
ig
u
o
u
s
se
n
te
n
c
e
s
in
th
e
n
o
v
e
l
o
f
a
se
m
a
n
ti
c
p
u
n
c
h
(i
n
Ba
h
a
sa
:
An
a
li
sis
k
a
li
m
a
t
a
m
b
ig
u
d
a
lam
n
o
v
e
l
su
a
t
u
ti
n
ju
a
n
se
m
a
n
ti
c
),
”
Bu
n
g
Ha
tt
a
,
v
o
l.
2
,
n
o
.
3
,
2
0
1
3
[1
2
]
L
in
Y,
e
t
a
l
.,
“
S
p
h
e
re
c
las
sifica
ti
o
n
f
o
r
a
m
b
i
g
o
u
s
d
a
ta,”
2
0
0
6
In
t
e
rn
a
ti
o
n
a
l
Co
n
fre
n
c
e
o
n
M
a
c
h
i
n
e
L
e
a
rn
i
n
g
a
n
d
Cy
b
e
rn
e
ti
c
s
,
p
p
.
2
5
7
1
-
2
5
7
4
,
2
0
1
6
.
[1
3
]
Xi
o
n
g
Y
.
,
“
A
c
o
m
p
o
site
Bo
y
e
r
-
M
o
o
re
a
lg
o
rit
h
m
fo
r
th
e
stri
n
g
-
m
a
tch
in
g
p
r
o
b
lem
,
”
In
ter
n
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
o
n
Pa
ra
rle
l
a
n
d
Distrib
u
ted
C
o
mp
u
ti
n
g
,
Ap
p
li
c
a
t
io
n
a
n
d
T
e
c
h
n
o
lo
g
ies
,
De
c
2
0
1
0
.
[1
4
]
Wan
g
Y
.
,
“
A
n
e
w
m
e
th
o
d
to
o
b
t
a
in
th
e
sh
if
t
-
tab
le
i
n
Bo
y
e
r
-
M
o
o
r
e
’s
a
lg
o
rit
h
m
,
”
19
th
I
n
ter
n
a
ti
o
n
a
l
Co
n
fre
n
c
e
o
n
Pa
tt
e
rn
Rec
o
g
n
a
ti
o
n
,
p
p
.
1
-
4
,
De
c
e
m
b
e
r
2
0
0
8
.
[1
5
]
G
o
ld
sc
h
lag
D
.
M
.
,
“
M
e
c
h
a
n
ica
ll
y
v
e
riy
in
g
c
o
n
c
u
rre
t
p
r
o
g
ra
m
s
with
th
e
B
o
y
e
r
-
M
o
o
re
p
r
o
v
e
r,
”
IEE
E
T
ra
n
sa
c
ti
o
n
o
n
S
o
ft
w
a
re
En
g
in
e
e
rin
g
,
v
o
l
.
1
6
,
n
o
.
9
,
p
p
.
1
0
0
5
-
1
0
2
3
,
S
e
p
tem
b
e
r
1
9
9
0
.
[1
6
]
Do
m
in
g
u
e
s
A
.
,
e
t
a
l
.,
“
P
ro
m
m
a
b
le
S
o
c
p
latfo
rm
f
o
r
d
e
e
p
p
a
c
k
e
t
i
n
sp
e
c
ti
o
n
u
sin
g
e
n
h
a
n
c
e
d
Bo
y
e
r
-
M
o
o
re
a
lg
o
r
it
h
m
,
”
In
ter
n
a
si
o
n
a
l
S
y
mp
o
si
u
m o
n
Rec
o
n
fi
g
u
r
a
b
le C
o
mm
ica
ti
o
n
-
Ce
n
tric
S
y
ste
m
-
on
-
C
h
ip
,
p
p
.
1
-
8
,
Ju
l
y
2
0
1
7
.
[1
7
]
Da
n
v
y
O
.
,
Ro
h
d
e
H
.
K
.
,
“
On
o
b
tai
n
in
g
th
e
B
o
y
e
r
-
M
o
o
re
S
tri
n
g
-
M
a
tch
in
g
a
lg
o
rit
h
m
b
y
p
a
rti
a
l
e
v
a
lu
a
ti
o
n
,
”
In
fo
rm
a
t
io
n
Pro
c
e
ss
in
g
L
e
tt
e
rs
,
v
o
l.
9
9
,
n
o
.
4
,
p
p
.
1
5
8
-
1
6
2
,
Au
g
u
st
2
0
0
6
.
[1
8
]
S
a
leh
A
.
Z
.
M
.
,
e
t
a
l
.
,
“
A
m
e
t
h
o
d
f
o
r
we
b
a
p
p
li
c
a
ti
o
n
v
u
l
n
e
ra
b
il
it
ies
b
y
u
sin
g
Bo
y
e
r
-
M
o
o
re
strin
g
m
a
tch
i
n
g
a
lg
o
rit
h
m
,
”
Pro
c
e
d
i
a
Co
m
p
u
ter
S
c
ien
c
e
,
v
o
l.
7
2
,
p
p
.
1
1
2
-
1
2
1
,
2
0
1
5
.
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
Dete
ctin
g
I
n
d
o
n
esia
a
mb
ig
u
o
u
s
s
en
ten
ce
s
u
s
in
g
B
o
ye
r
-
Mo
o
r
e
a
lg
o
r
ith
m
(
I
K
etu
t G
ed
e
Da
r
ma
P
u
tr
a
)
2487
[1
9
]
Watso
n
W
.
B
.
,
“
A
n
e
w
re
g
u
lar
g
ra
m
a
r
p
a
tt
e
rn
m
a
tch
in
g
a
lg
o
ri
th
m
,
”
T
h
e
o
re
ti
c
a
l
C
o
mp
u
ter
S
c
i
e
n
c
e
,
v
o
l
.
2
9
9
,
n
o
.
1
-
3
,
p
p
.
5
0
9
-
5
2
1
,
2
0
0
3
.
[2
0
]
S
a
b
riy
e
A
.
O
.
J
.
,
Zai
n
o
n
W
.
M
.
N
.
W
.
,
“
An
a
p
rr
o
c
h
fo
r
d
e
tec
ti
o
n
sy
n
tax
a
n
d
sy
n
tatic
a
m
b
i
g
u
it
y
in
so
fw
a
re
re
q
u
it
m
e
n
t
sp
e
c
ifi
c
a
ti
o
n
,
”
J
o
u
rn
a
l
o
f
T
h
e
re
ti
c
a
l
a
n
d
Ap
p
li
e
d
I
n
fo
e
m
a
ti
o
n
T
e
c
n
o
lo
g
y
,
v
o
l.
9
6
,
n
o
.
8
,
A
p
ril
2
0
1
8
.
[2
1
]
Ra
m
a
d
h
a
n
i
R
.
A
.
,
e
t
a
l
.,
“
Da
tab
a
s
e
o
f
In
d
o
n
e
sia
n
S
i
g
n
S
y
ste
m
s
,”
I
CS
GTE
IS
,
p
p
.
2
2
5
-
2
2
8
,
Oc
t
2
0
1
8
.
[2
2
]
Jia
n
g
H
.
,
“
S
t
u
d
y
o
n
i
n
fo
rm
a
ti
o
n
r
e
tri
e
v
a
l
m
o
d
e
l
b
a
se
d
o
n
r
o
u
g
h
se
t
th
e
o
r
y
,
”
In
ter
n
a
sio
n
a
l
S
y
mp
o
siu
m o
n
I
n
telli
g
e
n
t
Ub
iq
u
it
o
u
s Co
m
p
u
ti
n
g
a
n
d
Ed
u
c
a
ti
o
n
,
p
p
.
4
4
0
-
4
4
4
,
M
a
y
2
0
0
9
.
[2
3
]
Ly
n
n
T
.
,
e
t
a
l
.
,
“
Da
ta
se
t
fo
r
a
u
t
o
m
a
ti
c
o
f
o
n
li
n
e
m
iso
g
y
n
isti
c
sp
e
e
c
h
,
Da
t
a
i
n
Brief
,
v
o
l.
2
6
,
Oc
t
2
0
1
9
.
[2
4
]
G
o
k
u
l
P
.
P,
e
t
a
l
.,
“
S
e
ten
c
e
S
imilarity
d
e
tec
ti
o
n
in
M
a
lay
a
lam
lan
g
u
a
n
g
e
u
si
n
g
c
o
si
n
e
sim
il
a
rit
y
,
”
In
ter
n
a
ti
o
n
a
l
Co
n
fre
n
c
e
o
n
Rec
e
n
t
T
re
n
d
i
n
E
lec
tro
n
ics
,
In
fo
rm
a
ti
o
n
m
&
Co
mm
u
n
ica
ti
o
n
T
e
c
h
o
n
o
l
o
g
y
,
p
p
.
2
2
1
-
2
2
5
,
M
a
y
2
0
1
7
.
[2
5
]
Ak
b
a
s
C
.
E
.
,
e
t
a
l
.,
“
L1
n
o
r
m
-
b
a
se
d
m
u
lt
i
p
li
c
a
ti
o
n
-
fre
e
c
o
s
in
e
sim
il
a
rit
y
m
e
a
su
re
s
fo
r
b
ig
d
a
ta
a
n
a
ly
sis,
“
In
ter
n
a
ti
o
n
a
l
W
o
rk
sh
o
p
o
n
C
o
m
p
u
t
a
ti
o
n
a
l
In
telleg
e
n
c
e
Fo
r
M
u
lt
i
me
d
ia
Un
d
e
rs
ta
n
d
in
g
,
p
p
.
1
-
5
,
N
o
v
2
0
1
4
.
[2
6
]
Alo
d
a
d
M
.
,
Ja
n
e
ja
,
“
S
imilarity
i
n
p
a
ti
e
n
t
s
u
p
p
o
rt
f
o
ru
m
s
u
sin
g
tf
-
i
d
f
a
n
d
c
o
sin
e
sim
il
a
rit
y
m
e
tri
c
s
,”
In
ter
n
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
o
n
He
a
lt
h
c
a
re
In
f
o
rm
a
ti
c
s
,
p
p
.
5
2
1
-
5
2
2
,
Oc
t
2
0
1
5
.
[2
7
]
Zh
u
S
.
,
e
t
a
l
.
,
“
To
p
-
K
c
o
sin
e
sim
il
a
rit
y
in
ters
ti
n
g
p
a
irs
se
a
rc
h
,
”
2
0
1
0
S
e
v
e
n
t
I
n
ter
n
a
t
io
n
a
l
C
o
n
fre
n
c
e
Fu
zz
y
S
y
ste
m
a
n
d
Kn
o
wled
g
e
Disc
o
v
e
ry
,
p
p
.
1
4
7
9
-
1
4
8
3
,
Au
g
2
0
1
0
.
[2
8
]
He
rm
a
n
d
e
s
A
.
F
.
R
.
,
G
a
rc
ia
N
.
Y
.
G
.
,
“
Distrib
u
ted
p
ro
c
e
ss
in
g
u
sin
g
c
o
si
n
e
sim
il
a
rit
y
fo
r
m
a
p
p
i
n
g
b
ig
d
a
ta
i
n
h
a
d
o
o
p
,”
I
EE
E
L
a
ti
n
Ame
ric
a
T
ra
c
sa
c
ti
o
n
,
v
o
l.
1
4
,
n
o
.
6
,
p
p
.
2
8
5
7
-
2
8
6
1
,
Ju
n
e
2
0
1
6
.
[2
9
]
Ka
rim
M
.
S
.
,
e
t
a
l
.
,
“
Im
p
lem
tatio
n
a
n
d
p
e
rf
o
rm
a
n
c
e
e
v
a
lu
a
ti
o
n
o
f
se
m
a
n
ti
c
fe
a
tu
re
s
a
n
a
l
y
sis
sy
s
tem
fo
r
b
a
n
g
la
a
ss
e
rti
v
e
,
imp
p
e
ra
ti
v
e
a
n
d
i
n
terro
g
a
ti
v
e
se
n
tec
e
s,”
ICBS
L
P
,
p
p
.
1
-
5
,
S
e
p
tem
b
e
r
2
0
1
8
.
[3
0
]
Zi
tn
ick
C
.
L
.
,
e
t
a
l
.,
“
Lea
rn
in
g
t
h
e
v
isu
a
l
i
n
terp
re
tati
o
n
o
f
se
ten
c
e
,”
2
0
1
3
IEE
E
In
ter
n
a
sio
n
a
l
Co
n
fre
n
c
e
o
n
C
o
mp
u
ter
Vi
sio
n
,
p
p
.
1
6
8
1
-
1
6
8
8
,
De
c
2
0
1
3
.
[3
1
]
F
e
rg
y
a
n
t
o
E
.
,
e
t
a
l
.
,
“
A
S
imp
l
e
c
las
sifier
fo
r
d
e
tec
ti
n
g
o
n
l
in
e
c
h
il
d
g
ro
o
m
in
g
c
o
v
e
rsa
ti
o
n
,
”
T
EL
KOM
NIK
A
T
e
lec
o
mm
u
n
ica
ti
o
n
Co
mp
u
ti
n
g
E
lec
tro
n
ics
a
n
d
C
o
n
tr
o
l
,
v
o
l
.
1
6
,
n
o
.
3
,
p
p
.
1
2
3
9
-
1
2
4
8
,
Ju
n
e
2
0
1
8
.
[3
2
]
G
a
r
c
ia
-
Ba
lb
o
la
J
.
L
.
,
e
t
a
l
.
,
“
Ho
m
o
g
e
it
y
tes
t
fo
r
c
o
n
fu
si
o
n
m
a
tri
c
e
s
:
A
m
e
th
o
d
a
n
d
e
x
a
m
p
le,
”
In
ter
n
a
sio
n
a
l
Ge
o
sc
ien
c
e
a
n
d
Rem
o
te S
e
n
si
n
g
S
y
p
o
si
u
m
,
p
p
.
1
2
0
3
-
1
2
0
5
,
Ju
l
y
2
0
1
8
.
[3
3
]
Bh
a
ll
a
R
.
,
Ba
g
g
a
A
.
,
“
Op
p
i
n
i
o
n
m
in
i
n
g
fra
m
e
wo
rk
u
si
n
g
p
r
o
p
o
se
d
r
b
-
b
a
y
e
s
m
o
d
e
l
f
o
r
te
x
t
c
las
sifica
ti
o
n
,
”
In
ter
n
a
si
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
trica
l
a
n
d
Co
mp
u
ter
E
n
g
i
n
e
e
rin
g
(
IJ
ECE
)
,
v
o
l.
9
,
n
o
.
1
,
p
p
.
4
7
7
-
4
8
4
,
Ja
n
u
a
ry
2
0
1
9
.
[3
4
]
G
o
k
a
y
R
.
,
Ya
lcin
H
.
,
“
Im
p
r
o
v
i
n
g
l
o
w
Re
so
u
rc
e
T
u
rk
is
h
sp
e
e
c
h
re
c
o
g
n
it
i
o
n
with
Da
ta
Au
g
m
e
n
ta
ti
o
n
a
n
d
TT
S
,
”
In
ter
n
a
t
io
n
a
l
M
u
lt
i
-
Co
n
fre
n
c
e
o
n
S
y
tem
s,
S
i
g
n
a
ls & De
v
ice
(S
S
D)
,
p
p
.
3
5
7
-
3
6
0
,
M
a
rc
h
2
0
1
9
.
Evaluation Warning : The document was created with Spire.PDF for Python.