I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
pu
t
er
Science
Vo
l.
25
,
No
.
3
,
Ma
r
ch
20
22
,
p
p
.
1
6
7
2
~
1
6
7
8
I
SS
N:
2
5
0
2
-
4
7
5
2
,
DOI
: 1
0
.
1
1
5
9
1
/ijeecs.v
25
.i
3
.
pp
1
6
7
2
-
1
6
7
8
1672
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs.ia
esco
r
e.
co
m
Ana
ly
sis
of
na
me
d
-
enti
ty ef
fec
t
o
n
text c
la
ss
ificatio
n
o
f
traff
ic
a
ccident
da
ta usi
ng
ma
chine learni
ng
Anug
ra
h Dw
ia
t
m
a
j
a
P
utr
a
,
Abba
Su
g
a
nd
a
G
irsa
ng
D
e
p
a
r
t
me
n
t
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
B
I
N
U
S
G
r
a
d
u
a
t
e
P
r
o
g
r
a
m
–
M
a
s
t
e
r
o
f
C
o
mp
u
t
e
r
S
c
i
e
n
c
e
,
B
i
n
a
N
u
sa
n
t
a
r
a
U
n
i
v
e
r
si
t
y
,
Ja
k
a
r
t
a
,
I
n
d
o
n
e
si
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Au
g
8
,
2
0
2
1
R
ev
is
ed
Dec
9
,
2
0
2
1
Acc
ep
ted
J
an
11
,
2
0
2
2
Wi
th
th
e
risi
n
g
n
u
m
b
e
r
o
f
a
c
c
id
e
n
ts
in
In
d
o
n
e
sia
,
it
is
stil
l
n
e
c
e
ss
a
ry
to
e
v
a
lu
a
te
a
n
d
a
n
a
ly
z
e
a
c
c
id
e
n
t
d
a
ta.
Th
e
c
a
teg
o
riza
ti
o
n
o
f
traffi
c
a
c
c
id
e
n
t
d
a
ta
h
a
s
b
e
e
n
d
e
v
e
lo
p
e
d
u
sin
g
w
o
rd
e
m
b
e
d
d
in
g
,
h
o
we
v
e
r
a
d
d
i
ti
o
n
a
l
wo
rk
is
n
e
e
d
e
d
t
o
a
c
h
iev
e
b
e
tt
e
r
re
su
lt
s
.
S
e
v
e
ra
l
i
n
fo
rm
a
ti
v
e
n
a
m
e
d
e
n
ti
ti
e
s
a
re
fre
q
u
e
n
tl
y
s
u
fficie
n
t
to
d
iffere
n
ti
a
te
wh
e
th
e
r
o
r
n
o
t
in
fo
rm
a
ti
o
n
o
n
a
traffic
a
c
c
id
e
n
t
e
x
ists.
Na
m
e
d
-
e
n
ti
ti
e
s
a
re
in
fo
rm
a
ti
o
n
a
l
c
h
a
ra
c
teristics
th
a
t
c
a
n
o
ffe
r
d
e
tails
a
b
o
u
t
a
tex
t.
Th
e
i
n
flu
e
n
c
e
o
f
n
a
m
e
d
-
e
n
ti
t
ies
o
n
th
e
m
a
ti
c
tex
t
c
a
teg
o
riza
ti
o
n
is
e
x
a
m
in
e
d
i
n
t
h
is
p
a
p
e
r.
Th
e
i
n
fo
rm
a
ti
o
n
wa
s
c
o
ll
e
c
ted
u
sin
g
a
Twit
ter
so
c
ial
m
e
d
ia
c
ra
wl.
P
re
p
ro
c
e
ss
in
g
is
d
o
n
e
a
t
t
h
e
b
e
g
in
n
in
g
o
f
th
e
p
ro
c
e
ss
t
o
m
o
d
if
y
a
n
d
d
e
le
te
u
se
fu
l
tex
t
a
s
we
ll
a
s
lab
e
l
sp
e
c
ifi
e
d
e
n
ti
ti
e
s.
On
s
u
p
p
o
r
t
v
e
c
to
r
m
a
c
h
in
e
(S
VM)
,
sc
h
e
m
e
c
o
m
p
a
riso
n
s
we
re
p
e
rfo
rm
e
d
fo
r
i)
wo
r
d
e
m
b
e
d
d
in
g
,
ii
)
th
e
n
u
m
b
e
r
o
f
o
c
c
u
rre
n
c
e
s
o
f
n
a
m
e
d
e
n
ti
ti
e
s
,
a
n
d
ii
i)
t
h
e
c
o
m
b
i
n
a
ti
o
n
o
f
t
h
e
two
is
k
n
o
w
n
a
s
a
h
y
b
r
id
.
Th
e
h
y
b
ri
d
sc
h
e
m
e
p
ro
d
u
c
e
d
a
n
imp
ro
v
e
m
e
n
t
in
c
las
sifica
ti
o
n
a
c
c
u
ra
c
y
o
f
9
0
.
2
7
%
wh
e
n
c
o
m
p
a
re
d
t
o
wo
r
d
e
m
b
e
d
d
i
n
g
sc
h
e
m
e
a
n
d
o
c
c
u
rre
n
c
e
s
o
f
n
a
m
e
d
e
n
ti
ti
e
s
sc
h
e
m
e
,
a
c
c
o
rd
in
g
to
tes
ts
c
o
n
d
u
c
ted
u
sin
g
1
.
8
8
5
d
a
ta
c
o
n
sistin
g
o
f
7
8
8
a
c
c
id
e
n
t
d
a
ta an
d
1
.
0
6
7
n
o
n
-
a
c
c
id
e
n
t
d
a
ta.
K
ey
w
o
r
d
s
:
C
las
s
if
icatio
n
Ma
ch
in
e
lear
n
in
g
Nam
ed
-
en
tity
S
o
cial
m
ed
ia
T
r
af
f
ic
ac
cid
en
t a
n
aly
s
is
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
:
An
u
g
r
ah
Dwiatm
aja
Pu
tr
a
C
o
m
p
u
ter
Scien
ce
Dep
ar
tm
e
n
t,
B
I
NUS
Gr
ad
u
ate
Pro
g
r
am
–
Ma
s
ter
o
f
C
o
m
p
u
ter
Scien
ce
B
in
a
Nu
s
an
tar
a
Un
iv
er
s
ity
J
ak
ar
ta,
I
n
d
o
n
esia
E
m
ail:
an
u
g
r
a
h
.
p
u
tr
a@
b
in
u
s
.
ac
.
id
,
an
u
g
r
ah
d
p
u
tr
a@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
I
n
I
n
d
o
n
esia,
th
e
f
r
eq
u
en
cy
o
f
ac
cid
en
ts
is
ex
tr
em
ely
s
ig
n
if
ican
t,
with
all
ty
p
es
o
f
in
ju
r
ies,
in
clu
d
in
g
d
ea
th
.
Acc
o
r
d
in
g
to
W
o
r
ld
Hea
lth
Or
g
an
izatio
n
(
W
HO)
d
a
ta
[
1
]
in
2
0
1
6
,
3
1
.
2
8
2
p
e
o
p
le
d
ied
in
a
to
tal
o
f
1
0
6
.
6
4
4
r
o
a
d
ac
ci
d
en
ts
in
I
n
d
o
n
esia,
with
7
8
%
o
f
m
ales
an
d
2
2
%
o
f
wo
m
e
n
.
T
h
is
im
p
lie
s
th
at
1
2
,
2
p
er
s
o
n
s
d
ied
in
a
tr
af
f
ic
ac
cid
e
n
t
f
o
r
e
v
er
y
1
0
0
,
0
0
0
in
h
a
b
itan
ts
,
r
esu
ltin
g
in
a
m
o
r
tality
r
ate
o
f
2
9
.
3
%.
I
n
r
ec
en
t
y
ea
r
s
,
th
er
e
h
as
b
ee
n
a
s
u
r
g
e
in
th
e
r
esear
ch
o
f
tr
a
f
f
ic
ac
cid
en
ts
as
a
r
esu
lt
o
f
cr
o
wd
s
o
u
r
cin
g
d
ata
to
s
u
p
p
lem
e
n
t
co
n
v
en
tio
n
al
tech
n
iq
u
es
an
d
u
n
co
v
er
n
ew
f
ac
ts
.
T
witter
,
wh
ich
h
as
g
o
tten
a
lo
t
o
f
atten
tio
n
in
r
ec
en
t
y
ea
r
s
,
is
s
lo
wly
b
ec
o
m
in
g
ac
k
n
o
wled
g
ed
as
a
s
o
u
r
ce
o
f
in
f
o
r
m
atio
n
f
o
r
u
s
er
s
'
d
ir
ec
t
co
n
tr
ib
u
tio
n
s
to
ev
en
t
d
etec
tio
n
.
T
witter
h
as
at
least
3
0
m
ill
io
n
u
s
er
s
in
2
0
1
0
[
2
]
.
T
witter
cr
ea
tes
an
o
n
lin
e
ec
o
s
y
s
tem
in
w
h
ich
in
f
o
r
m
atio
n
is
g
en
er
ated
,
co
n
s
u
m
e
d
,
p
r
o
m
o
ted
,
d
is
s
em
in
ated
,
d
is
co
v
er
ed
,
an
d
s
h
ar
ed
f
o
r
p
a
r
ticu
lar
r
ea
s
o
n
s
,
m
o
s
t
o
f
wh
ich
ar
e
lin
k
ed
to
co
m
m
u
n
ity
an
d
s
o
cial
ac
tiv
itie
s
r
ath
er
th
an
f
u
n
ctio
n
al
task
-
o
r
ien
te
d
g
o
als.
As
a
r
e
s
u
lt,
s
o
cial
m
ed
ia
s
ites
lik
e
T
wit
ter
will
s
er
v
e
as
d
ata
s
o
u
r
ce
s
,
an
d
it
will
b
e
p
o
s
s
ib
le
to
o
b
tain
a
wid
e
r
an
g
e
o
f
in
f
o
r
m
atio
n
f
r
o
m
a
d
i
v
er
s
e
g
r
o
u
p
o
f
in
d
i
v
id
u
als in
a
tim
ely
way
.
I
n
f
o
r
m
a
t
i
o
n
m
a
y
b
e
e
as
i
l
y
c
o
l
le
c
t
e
d
a
n
d
t
h
e
n
a
n
a
l
y
z
e
d
a
n
d
ca
t
e
g
o
r
i
s
e
d
a
c
c
o
r
d
i
n
g
t
o
c
e
r
t
a
i
n
c
a
t
e
g
o
r
i
es
u
s
i
n
g
t
h
i
s
e
n
o
r
m
o
u
s
a
m
o
u
n
t
o
f
d
a
t
a
,
p
a
r
t
i
c
u
l
a
r
l
y
i
n
f
o
r
m
a
t
i
o
n
r
e
l
a
t
i
n
g
t
o
t
r
a
f
f
i
c
a
c
ci
d
e
n
t
s
s
u
ch
a
s
[
3
]
.
T
h
is
s
tu
d
y
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
A
n
a
lysi
s
o
f n
a
med
-
e
n
tity e
ffect
o
n
text
cla
s
s
ifica
tio
n
o
f tra
ffic a
cc
id
en
t d
a
ta
…
(
A
n
u
g
r
a
h
Dw
ia
tma
ja
P
u
tr
a
)
1673
u
s
es
c
r
awlin
g
to
co
llect
d
ata
o
n
tr
af
f
ic
ac
cid
e
n
ts
,
wh
ich
is
th
en
ca
teg
o
r
ize
d
in
to
two
ca
te
g
o
r
ies:
tr
u
e
o
r
f
alse
o
n
tr
af
f
ic
ac
cid
en
t
n
ews.
Face
b
o
o
k
'
s
f
astt
ex
t
tech
n
iq
u
e
is
u
s
ed
to
weig
h
t
wo
r
d
r
ep
r
esen
tatio
n
s
.
T
h
e
wo
r
d
s
i
n
th
e
d
o
cu
m
e
n
t
ar
e
u
s
ed
as
q
u
an
titativ
e
ch
ar
ac
ter
is
tics
in
s
ev
er
al
tech
n
iq
u
es
to
tex
t
ca
t
eg
o
r
izatio
n
th
at
ar
e
b
ased
o
n
th
e
m
ac
h
in
e
lear
n
in
g
(
ML
)
alg
o
r
ith
m
.
T
h
e
ass
u
m
p
t
io
n
b
eh
in
d
th
is
tech
n
iq
u
e
is
th
at
th
e
f
r
eq
u
en
cy
o
f
p
ar
ticu
lar
ter
m
s
in
a
tex
t
is
a
g
o
o
d
p
r
e
d
icto
r
o
f
a
b
r
o
ad
to
p
ic.
T
h
is
im
p
lies
th
at
n
am
ed
en
titi
es
co
u
ld
b
e
a
b
etter
f
it
f
o
r
tex
t
d
o
c
u
m
en
t
c
ateg
o
r
izatio
n
.
T
h
e
in
f
lu
en
ce
o
f
n
am
ed
-
e
n
titi
es
o
n
th
e
ca
te
g
o
r
izatio
n
o
f
tr
af
f
ic
ac
cid
en
t
in
f
o
r
m
atio
n
d
ata
tex
t
will
b
e
i
n
v
esti
g
ated
i
n
th
is
s
t
u
d
y
.
T
h
e
co
m
p
ar
is
o
n
will
b
e
d
o
n
e
in
t
h
r
ee
wa
y
s
:
u
tili
zin
g
f
u
n
d
am
en
tal
tec
h
n
iq
u
es
th
at
wo
r
d
em
b
e
d
d
in
g
(
W
o
r
d
E
m
b
ed
d
in
g
)
,
th
e
n
u
m
b
er
s
o
f
o
cc
u
r
en
cy
n
am
ed
en
titi
es
(
Nam
ed
E
n
titi
es),
an
d
a
m
ix
o
f
th
e
two
(
Hy
b
r
id
)
.
T
h
e
d
ataset
f
r
o
m
t
h
e
p
r
e
v
io
u
s
s
tu
d
y
[
3
]
will
b
e
u
tili
ze
d
an
d
co
m
b
in
e
d
with
th
e
m
o
s
t
r
ec
en
t
cr
awlin
g
d
ataset,
wh
ich
will
th
en
b
e
lab
eled
with
n
am
ed
-
en
titi
es.
I
n
ML
,
th
e
b
asic
alg
o
r
ith
m
s
t
o
b
e
u
tili
ze
d
a
r
e
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
i
n
e
(
SVM
)
.
T
h
e
f
o
llo
w
in
g
ar
e
s
o
m
e
o
f
th
e
s
tu
d
y
'
s
co
n
tr
ib
u
tio
n
s
:
i)
T
h
e
d
ataset
is
m
ad
e
u
p
o
f
p
r
ep
r
o
ce
s
s
ed
tex
t
f
r
o
m
p
r
io
r
r
esear
ch
d
atasets
an
d
n
ew
cr
awlin
g
m
eth
o
d
s
.
Fu
r
th
er
m
o
r
e,
th
e
d
ata
e
n
tity
lab
elin
g
is
d
o
n
e
with
th
e
h
elp
o
f
a
p
r
e
s
et
lab
el
;
ii)
T
ex
t
ca
teg
o
r
izatio
n
f
o
r
t
r
af
f
ic
ac
ci
d
en
t
d
ata
u
s
e
th
e
SVM
m
eth
o
d
,
w
h
ich
co
m
p
ar
es
p
r
e
d
ef
in
ed
n
am
e
d
en
titi
es
to
th
r
ee
p
r
ed
eter
m
i
n
ed
s
ch
em
as:
wo
r
d
em
b
ed
d
i
n
g
,
n
am
e
d
en
titi
es,
an
d
h
y
b
r
id
.
T
h
e
d
ata
u
tili
ze
d
in
th
is
s
tu
d
y
is
th
e
r
esu
lt
o
f
cr
awlin
g
f
r
o
m
th
e
s
o
cial
n
etwo
r
k
in
g
s
ite
T
wit
ter
,
wh
ich
y
ield
ed
1
,
8
8
5
r
esu
lts
.
T
h
e
s
tu
d
y
th
en
co
n
ce
n
tr
ates so
lely
o
n
th
e
u
s
e
o
f
I
n
d
o
n
esian
a
n
d
th
e
p
r
ev
i
o
u
s
ly
s
p
ec
if
ied
s
et
o
f
n
am
ed
th
in
g
s
.
2.
RE
S
E
ARCH
M
E
T
H
O
D
W
eb
cr
awle
r
s
h
av
e
b
ee
n
ar
o
u
n
d
alm
o
s
t a
s
lo
n
g
as th
e
wo
r
l
d
wid
e
web
.
I
n
1
9
9
3
,
th
e
f
ir
s
t c
r
awle
r
was
im
p
lem
en
ted
.
Fo
r
m
in
in
g
h
u
g
e
d
atasets
,
we
b
cr
awlin
g
i
s
u
s
ed
to
in
d
ex
in
f
o
r
m
atio
n
o
n
a
web
s
ite
u
tili
zin
g
a
u
n
if
o
r
m
r
eso
u
r
ce
lo
ca
to
r
(
UR
L
)
an
d
a
n
a
p
p
licatio
n
p
r
o
g
r
a
m
m
in
g
i
n
ter
f
ac
e
(
API
)
.
C
r
awle
r
s
lead
to
a
p
r
o
ce
s
s
o
f
d
o
cu
m
en
t
s
h
ar
in
g
,
m
o
r
e
a
b
o
u
t
in
ter
ac
tiv
e
co
n
ten
t,
an
d
ev
en
f
u
ll
-
f
le
d
g
ed
ap
p
s
as
th
e
web
ad
v
an
ce
s
[
4
]
.
Af
ter
Face
b
o
o
k
an
d
I
n
s
tag
r
am
,
T
witter
i
s
th
e
wo
r
ld
'
s
th
ir
d
m
o
s
t
p
o
p
u
la
r
o
n
lin
e
s
o
cial
n
et
wo
r
k
(
OSN)
,
with
a
s
im
p
le
d
ata
m
o
d
el
an
d
d
ir
ec
t
d
ata
ac
ce
s
s
API
.
I
t'
s
th
er
ef
o
r
e
ex
ce
llen
t
f
o
r
s
o
cial
n
etwo
r
k
r
esear
ch
in
v
o
lv
in
g
h
u
n
d
r
ed
s
o
f
m
illi
o
n
s
o
f
p
e
o
p
le
[
5
]
.
W
h
en
it
ca
m
e
to
d
a
ta
ac
ce
s
s
,
T
witter
u
s
ed
to
h
av
e
a
f
air
l
y
lib
er
al
ap
p
r
o
ac
h
[
6
]
.
T
witter
b
eg
a
n
im
p
o
s
in
g
to
u
g
h
er
lim
itatio
n
s
in
2
0
2
1
,
as
s
tated
b
y
th
e
o
f
f
icial
T
witter
b
lo
g
[
7
]
,
b
ec
au
s
e
it
was
co
n
ce
r
n
ed
th
a
t
th
ir
d
-
p
ar
ty
s
er
v
ices
wo
u
ld
ex
p
lo
it
th
e
API
an
d
d
ev
el
o
p
ap
p
s
th
at
b
asically
m
im
ick
ed
its
p
r
im
ar
y
f
ea
tu
r
e
.
T
witter
h
as
a
s
tr
aig
h
tf
o
r
war
d
d
ata
d
eliv
er
y
s
tr
ateg
y
th
at
is
s
u
p
p
o
r
ted
b
y
a
h
ig
h
ly
ef
f
icien
t
an
d
s
ca
lab
le
i
n
f
r
astru
ctu
r
e
[
8
]
.
T
h
er
e
a
r
e
n
u
m
er
o
u
s
way
s
to
ac
ce
s
s
in
f
o
r
m
atio
n
f
r
o
m
T
witter
,
o
n
e
o
f
wh
ich
is
to
u
tili
ze
th
e
T
witter
d
ev
elo
p
er
p
ag
e'
s
ap
p
licatio
n
p
r
o
g
r
am
i
n
te
r
f
ac
e
(
API
)
.
I
n
n
u
m
er
o
u
s
ap
p
licatio
n
d
o
m
ain
s
,
SVM
is
o
n
e
o
f
th
e
m
o
s
t
r
esil
ien
t
an
d
r
o
b
u
s
t
class
if
icatio
n
an
d
r
eg
r
ess
io
n
m
eth
o
d
s
.
T
h
e
b
asic
g
o
al
o
f
SVM
is
to
u
s
e
a
s
u
r
f
ac
e
th
at
o
p
tim
izes
th
e
m
ar
g
in
b
etwe
en
class
es
in
th
e
tr
ain
in
g
s
et
to
s
ep
ar
ate
t
h
e
m
[
9
]
,
[
1
0
]
.
A
s
et
o
f
n
in
s
tan
c
es
is
r
eq
u
ir
ed
to
tr
ain
an
SV
M.
E
ac
h
ex
am
p
le
is
m
ad
e
u
p
o
f
two
p
ar
ts
:
an
in
p
u
t
v
ec
to
r
x
i
an
d
a
lab
el
y
i.
Ass
u
m
e
th
at
th
e
tr
ain
in
g
s
et
X
is
(
x
1
,
y
1
)
,
(
x
2
,
y
2
)
,
.
.
.
,
(
x
n
, y
n
)
.
Fo
r
W
e'
l
l u
s
e
th
e
ex
a
m
p
le
o
f
a
two
-
d
im
en
s
io
n
al
in
p
u
t,
i.e
.
,
x
R
2
,
f
o
r
illu
s
tr
atio
n
p
u
r
p
o
s
es.
T
h
er
e
ar
e
v
ar
io
u
s
h
y
p
er
p
lan
es
th
at
ca
n
b
e
s
p
lit,
an
d
th
e
d
ata
ca
n
b
e
d
iv
id
ed
lin
ea
r
ly
.
T
h
e
g
e
n
er
aliza
b
ilit
y
,
o
n
th
e
o
t
h
e
r
h
an
d
,
is
d
e
p
en
d
e
n
t o
n
t
h
e
p
o
s
i
tio
n
o
f
th
e
s
ep
ar
ato
r
h
y
p
e
r
p
lan
e
an
d
th
e
h
y
p
e
r
p
lan
e
with
th
e
g
r
ea
test
m
ar
g
i
n
.
A
n
a
m
e
d
e
n
ti
t
y
is
a
t
e
r
m
t
h
a
t
d
e
n
o
t
e
s
t
h
at
a
n
el
e
m
e
n
t
h
a
s
p
r
o
p
e
r
t
i
e
s
w
i
t
h
a
g
r
o
u
p
o
f
o
t
h
e
r
i
t
e
m
s
[
1
1
]
.
E
n
tity
ex
tr
ac
tio
n
f
r
o
m
a
s
et
o
f
wo
r
d
s
is
a
m
eth
o
d
o
f
d
etec
tin
g
an
d
class
if
y
in
g
en
titi
es,
also
k
n
o
w
n
as
n
am
ed
en
tity
r
ec
o
g
n
itio
n
(
NE
R
)
.
NE
R
is
s
ig
n
if
ican
t
in
d
if
f
er
e
n
t
n
atu
r
al
lan
g
u
a
g
e
p
r
o
ce
s
s
in
g
(
NL
P
)
task
s
s
u
ch
as
tex
t
in
ter
p
r
etatio
n
,
in
f
o
r
m
atio
n
r
etr
iev
al,
au
to
m
atic
tex
t
s
u
m
m
ar
izatio
n
,
m
ac
h
in
e
tr
an
s
latio
n
,
a
n
d
k
n
o
wled
g
e
b
ase
d
ev
elo
p
m
e
n
t,
in
a
d
d
itio
n
to
th
e
k
e
y
s
u
b
task
o
f
in
f
o
r
m
atio
n
ex
tr
ac
tio
n
[
1
2
]
.
T
h
e
NE
R
-
b
ased
clu
s
ter
in
g
m
eth
o
d
p
u
lls
n
am
ed
item
s
f
r
o
m
g
r
o
u
p
s
b
ased
o
n
co
n
tex
tu
al
s
im
ilar
ity
.
T
h
e
u
s
e
o
f
u
n
lab
el
ed
d
ata
,
ac
co
r
d
in
g
to
C
o
llin
s
[
1
3
]
,
lo
wer
s
th
e
m
o
n
ito
r
in
g
n
ee
d
s
to
o
n
ly
s
ev
en
b
asic p
r
in
cip
les.
NE
R
is
u
s
ed
in
s
u
p
er
v
is
ed
lear
n
in
g
to
s
o
lv
e
m
u
lti
-
class
clas
s
if
icatio
n
an
d
s
eq
u
en
ce
lab
elin
g
p
r
o
b
lem
s
[
1
4
]
.
T
h
e
f
ea
tu
r
es
i
n
an
n
o
tated
d
ata
s
am
p
les
ar
e
m
eticu
lo
u
s
ly
co
n
s
tr
u
cted
to
r
ef
lect
ea
ch
tr
ain
in
g
o
cc
u
r
r
e
n
ce
.
Ma
ch
i
n
e
lear
n
i
n
g
tech
n
iq
u
es
ar
e
th
en
u
s
ed
t
o
ex
am
in
e
th
e
m
o
d
el
in
o
r
d
er
to
d
etec
t
s
im
ilar
p
atter
n
s
in
p
r
ev
io
u
s
ly
u
n
s
ee
n
d
ata.
I
n
a
s
u
p
er
v
is
ed
NE
R
s
y
s
tem
,
f
ea
tu
r
e
en
g
in
ee
r
in
g
is
cr
itical.
A
f
ea
tu
r
e
v
ec
to
r
r
ep
r
esen
tatio
n
is
a
te
x
t
ab
s
tr
ac
tio
n
in
wh
ich
o
n
e
o
r
m
o
r
e
b
o
o
lea
n
,
n
u
m
er
ic,
o
r
n
o
m
in
al
v
alu
es
r
ep
r
esen
t
a
wo
r
d
[
1
5
]
.
T
h
e
s
u
p
er
v
is
ed
NE
R
h
as
m
ad
e
ex
t
en
s
iv
e
u
s
e
o
f
th
e
wo
r
d
lev
el
f
u
n
cti
o
n
,
lis
t
s
ea
r
ch
f
ea
tu
r
e,
an
d
c
o
r
p
u
s
f
ea
tu
r
e.
M
an
y
m
ac
h
in
e
lear
n
in
g
m
et
h
o
d
s
h
av
e
b
ee
n
b
u
ilt
in
th
e
s
u
p
e
r
v
is
ed
NE
R
b
ased
o
n
th
ese
ch
ar
ac
ter
is
tics
[
1
6
]
,
[
1
7
]
.
Acc
id
en
t
-
r
elate
d
r
esear
ch
h
a
s
in
cr
ea
s
ed
in
r
ec
en
t
y
ea
r
s
as
a
r
esu
lt
o
f
cr
o
wd
s
o
u
r
cin
g
d
ata
to
s
u
p
p
l
em
en
t
estab
lis
h
ed
ap
p
r
o
ac
h
es
an
d
u
n
co
v
e
r
n
ew
f
ac
ts
.
T
witter
,
wh
ich
h
as
g
o
tten
a
lo
t
o
f
p
r
ess
in
r
ec
en
t
y
ea
r
s
,
h
as
s
tead
ily
g
ain
ed
ac
ce
p
tan
ce
as
a
s
o
u
r
ce
o
f
in
f
o
r
m
atio
n
f
o
r
u
s
er
s
d
ir
ec
t
co
n
t
r
ib
u
tio
n
s
to
ev
e
n
t
d
etec
tio
n
.
T
h
er
e
wer
e
at
least
3
0
m
illi
o
n
T
witte
r
u
s
er
s
in
2
0
1
0
,
wh
ile
th
e
r
e
wer
e
3
3
0
m
i
llio
n
in
2
0
1
9
[
1
8
]
.
T
witter
cr
ea
tes
an
o
n
lin
e
ec
o
s
y
s
tem
wh
er
e
in
f
o
r
m
atio
n
i
s
g
en
er
ated
,
co
n
s
u
m
ed
,
p
r
o
m
o
ted
,
d
is
s
em
in
ated
,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
25
,
No
.
3
,
Ma
r
ch
20
22
:
1
6
7
2
-
1
6
7
8
1674
f
o
u
n
d
,
an
d
s
h
ar
ed
f
o
r
p
ar
ticu
l
ar
co
m
m
u
n
ity
a
n
d
s
o
cial
r
ea
s
o
n
s
r
ath
er
th
an
task
-
o
r
ie
n
ted
f
u
n
ctio
n
al
o
n
es
[1
9]
.
As a
r
esu
lt,
s
o
cial
m
ed
ia
s
ites
lik
e
T
witter
will ser
v
e
as d
ata
s
o
u
r
ce
s
,
allo
win
g
f
o
r
th
e
r
a
p
id
r
etr
iev
al
o
f
a
wid
e
r
an
g
e
o
f
in
f
o
r
m
atio
n
f
r
o
m
a
l
ar
g
e
n
u
m
b
er
o
f
in
d
iv
id
u
als.
S
ep
ar
atin
g
d
ata
t
h
at
co
n
tain
s
o
r
d
o
es
n
o
t
co
n
tain
tr
af
f
ic
ac
cid
en
t
in
f
o
r
m
ati
o
n
r
e
q
u
ir
es
d
ata
p
r
o
ce
s
s
in
g
.
T
h
is
is
b
ec
au
s
e
u
tili
zin
g
th
e
k
ey
wo
r
d
"a
cc
id
en
t"
in
th
e
cr
awlin
g
tech
n
iq
u
e
will
also
r
etu
r
n
d
ata
th
at
d
o
es
n
o
t
co
n
ta
in
tr
af
f
ic
ac
cid
en
t
in
f
o
r
m
atio
n
b
u
t
h
as
th
e
s
am
e
wo
r
d
co
m
p
o
n
e
n
t.
I
n
t
h
e
p
ap
e
r
,
Sap
u
tr
o
a
n
d
Gir
s
an
g
[
3
]
,
ac
h
iev
ed
th
e
b
est
ac
cu
r
ac
y
o
f
8
8
%
in
h
is
s
tu
d
y
b
y
ca
teg
o
r
izin
g
u
tili
zin
g
th
e
SV
M
ap
p
r
o
ac
h
b
ased
o
n
Fas
tTe
x
t r
ep
r
esen
tatio
n
to
tac
k
le
th
e
p
r
o
b
lem
.
Sev
er
al
in
f
o
r
m
ativ
e
n
am
e
d
en
titi
es
ar
e
f
r
eq
u
en
tly
s
u
f
f
i
cien
t
to
d
if
f
er
en
tiate
wh
eth
er
o
r
n
o
t
in
f
o
r
m
atio
n
o
n
a
tr
af
f
ic
ac
cid
en
t
ex
is
ts
.
Fo
r
ex
am
p
le,
in
f
o
r
m
atio
n
o
n
tr
af
f
ic
ac
cid
e
n
ts
wi
ll
in
clu
d
e
ad
d
itio
n
al
d
etails
s
u
ch
as
lo
ca
tio
n
,
ca
s
u
alty
in
ju
r
y
,
an
d
tim
e.
I
n
th
e
m
ea
n
wh
ile,
d
ata
th
at
d
o
es
n
o
t
in
clu
d
e
ac
ci
d
en
t
in
f
o
r
m
atio
n
is
less
lik
ely
to
h
av
e
s
ev
er
al
s
ets
o
f
s
u
c
h
d
ata.
As
a
r
esu
lt,
we
b
eliev
e
th
at
n
am
ed
en
titi
es
ar
e
a
f
ea
tu
r
e
th
at
m
a
y
b
e
u
tili
ze
d
t
o
s
ep
ar
ate
d
ata
in
to
d
e
f
in
ed
ca
t
eg
o
r
ies.
T
h
is
is
d
u
e
to
th
e
f
ac
t
th
at
n
am
ed
e
n
titi
es
ar
e
d
is
tr
ib
u
ted
ac
r
o
s
s
t
h
e
ite
m
r
esp
o
n
s
e
th
eo
r
y
(
I
R
T
)
h
ie
r
ar
ch
y
i
n
v
ar
io
u
s
ca
te
g
o
r
ies.
On
ar
ticles
d
ata
[
2
0
]
,
th
e
u
s
ag
e
o
f
n
am
ed
e
n
titi
es
in
tex
t
class
if
icatio
n
was
u
s
ed
to
ca
teg
o
r
ize
th
e
ca
teg
o
r
ies
o
f
p
r
esid
en
tial
elec
tio
n
n
ews
d
ep
en
d
in
g
o
n
th
eir
n
ati
o
n
o
f
o
r
ig
in
,
r
esu
ltin
g
in
an
in
cr
ea
s
e
in
t
h
e
m
ic
r
o
av
er
ag
e
F1
s
co
r
e
f
o
r
t
h
e
clo
s
est ca
teg
o
r
y
to
8
1
.
4
%
.
3.
P
RO
P
O
SE
D
M
E
T
H
O
D
A
h
ier
ar
ch
ical
te
x
t
class
if
icati
o
n
aim
s
to
class
if
y
ea
ch
in
c
o
m
in
g
d
o
cu
m
e
n
t
in
to
ze
r
o
,
o
n
e
,
o
r
s
ev
er
al
ca
teg
o
r
ies
in
th
e
tex
t
h
ier
ar
ch
y
.
On
e
ap
p
r
o
ac
h
to
th
is
tech
n
o
lo
g
y
,
SVM
with
co
m
b
in
atio
n
s
ch
em
e,
h
as
d
em
o
n
s
tr
ated
s
ig
n
if
ican
t
b
en
e
f
its
in
a
v
ar
iety
o
f
tex
t
ca
te
g
o
r
izatio
n
task
s
.
SVM
'
s
p
er
f
o
r
m
an
ce
is
d
ep
en
d
e
n
t
o
n
th
e
k
er
n
el
f
u
n
ctio
n
s
an
d
s
lack
v
ar
iab
les
u
s
ed
.
T
o
p
u
t
it
an
o
th
er
way
,
o
p
tim
izin
g
th
e
two
p
ar
am
eter
s
is
cr
u
cial
f
o
r
o
p
tim
izin
g
th
e
SVM
alg
o
r
ith
m
[
2
1
]
.
T
h
e
s
tep
s
o
f
th
is
r
esear
ch
m
e
th
o
d
ar
e
d
ep
icted
in
Fig
u
r
e
1
.
T
h
is
r
esear
ch
u
s
es
a
d
ataset
g
ath
er
ed
f
r
o
m
T
witter
I
n
d
o
n
esian
lan
g
u
ag
e
an
d
k
e
y
wo
r
d
s
th
at
c
o
r
r
esp
o
n
d
to
"tr
af
f
ic
ac
cid
en
ts
"
.
T
o
s
ee
h
o
w
th
e
n
am
ed
-
en
tity
im
p
ac
ts
th
e
s
o
cial
m
ed
ia
tex
t
ca
teg
o
r
izatio
n
o
f
tr
af
f
ic
ac
cid
e
n
t
in
f
o
r
m
atio
n
,
th
e
class
if
icatio
n
tech
n
iq
u
e
will
b
e
co
u
p
led
wit
h
th
e
n
am
ed
-
e
n
tity
ap
p
r
o
ac
h
as
a
tex
t
r
ep
r
esen
tatio
n
.
T
o
cl
ea
r
d
ata
f
r
o
m
n
o
is
e,
p
r
ep
ar
atio
n
is
r
e
q
u
ir
ed
ea
r
ly
o
n
.
T
h
e
f
in
al
s
tag
e
is
to
ass
ess
th
e
m
o
d
el
to
s
ee
h
o
w
n
a
m
e
d
-
en
titi
es
af
f
ec
t
t
h
e
tex
t c
lass
if
icatio
n
m
o
d
el
an
d
wh
ich
m
o
d
el
p
r
o
d
u
ce
s
th
e
b
es
t r
esu
lts
.
Fig
u
r
e
1.
Pro
p
o
s
ed
m
et
h
o
d
T
h
e
h
y
b
r
id
s
ch
em
a
is
p
r
esen
t
ed
as
a
n
ew
s
ch
em
a
th
at
co
m
b
in
es
th
e
wo
r
d
em
b
ed
d
i
n
g
an
d
n
am
e
d
en
tity
s
ch
em
as.
As
illu
s
tr
ate
d
in
Fig
u
r
e
2
,
t
h
e
h
y
b
r
id
s
ch
em
e
is
co
n
s
tr
u
cted
b
y
i
n
t
eg
r
atin
g
s
en
ten
ce
p
r
o
b
a
b
ilit
y
ev
alu
atio
n
s
ag
ai
n
s
t
lab
els.
T
h
e
co
m
p
u
ted
r
atio
i
s
th
en
u
s
ed
to
ca
lcu
late
th
e
c
o
n
tr
ib
u
tio
n
o
f
ea
c
h
s
ch
em
e
to
th
e
h
y
b
r
i
d
s
ch
em
e,
en
s
u
r
in
g
th
at
th
e
c
o
n
tr
ib
u
tio
n
s
ar
e
b
alan
ce
d
an
d
th
at
t
h
e
d
ata
p
r
ed
ictio
n
f
in
d
in
g
s
ar
e
as a
cc
u
r
ate
as p
o
s
s
ib
le.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
A
n
a
lysi
s
o
f n
a
med
-
e
n
tity e
ffect
o
n
text
cla
s
s
ifica
tio
n
o
f tra
ffic a
cc
id
en
t d
a
ta
…
(
A
n
u
g
r
a
h
Dw
ia
tma
ja
P
u
tr
a
)
1675
Fig
u
r
e
2
.
Hy
b
r
id
s
ch
em
e
co
n
c
ep
t
4.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
4
.
1
.
Da
t
a
c
o
llect
io
n
E
n
tity
tag
g
in
g
is
th
e
in
itial
s
tep
b
ef
o
r
e
p
r
ep
r
o
ce
s
s
in
g
.
T
h
i
s
en
ab
les
th
e
cr
ea
tio
n
o
f
d
i
v
er
s
e
tex
ts
co
n
tain
in
g
th
in
g
s
th
at
h
av
e
s
ig
n
if
ica
n
ce
b
u
t
ar
e
d
elete
d
d
u
r
in
g
p
r
ep
r
o
ce
s
s
in
g
an
d
/o
r
ar
e
p
o
o
r
ly
co
m
p
r
eh
e
n
d
ed
b
y
co
m
p
u
ter
s
.
Data
f
r
o
m
cr
awl
r
esu
lts
,
as
s
h
o
wn
in
T
ab
le
1
,
will
b
e
clea
n
ed
th
r
o
u
g
h
m
a
n
y
s
tep
s
o
f
th
e
p
r
ep
r
o
ce
s
s
in
g
m
o
d
el.
T
h
e
lo
wer
(
)
m
eth
o
d
f
r
o
m
Py
th
o
n
'
s
s
tr
in
g
m
o
d
u
le
is
u
s
ed
to
f
o
ld
th
e
ca
s
es.
Usi
n
g
th
e
Py
th
o
n
s
tr
in
g
p
ac
k
ag
e
,
s
u
p
er
f
lu
o
u
s
ch
a
r
ac
ter
s
s
u
ch
as
em
o
tic
o
n
s
,
web
s
ite
UR
L
s
,
p
u
n
ctu
atio
n
m
ar
k
s
,
d
o
u
b
le
s
p
ac
es,
an
d
n
e
wlin
es
ar
e
r
em
o
v
ed
.
B
ec
au
s
e
th
e
n
atu
r
al
lan
g
u
ag
e
to
o
l
k
it
(
NL
T
K
)
lib
r
ar
y
d
o
es
n
o
t c
u
r
r
e
n
tly
s
u
p
p
o
r
t I
n
d
o
n
esi
an
,
th
e
s
tem
m
in
g
p
r
o
ce
s
s
in
I
n
d
o
n
esian
is
ca
r
r
ied
o
u
t
u
s
in
g
t
h
e
s
astra
wi
lib
r
ar
y
,
wh
ich
h
as
s
h
o
wn
to
b
e
f
air
ly
ex
ce
llen
t
at
h
an
d
lin
g
th
e
I
n
d
o
n
esian
lan
g
u
a
g
e
s
tem
m
in
g
p
r
o
ce
s
s
.
T
h
e
NL
T
K
lib
r
ar
y
is
u
s
ed
in
th
e
to
k
en
izi
n
g
p
r
o
ce
s
s
to
d
iv
id
e
s
en
te
n
ce
s
in
to
lis
ts
w
ith
a
s
p
ac
e
ch
ar
ac
ter
s
ep
ar
ato
r
.
T
h
e
NL
T
K
an
d
s
astra
wi
lib
r
ar
ies
ar
e
u
s
ed
in
th
e
s
to
p
w
o
r
d
elim
in
atio
n
p
r
o
ce
d
u
r
e.
T
h
e
s
to
p
wo
r
d
r
e
m
o
v
a
l
p
r
o
ce
d
u
r
e
will b
e
s
tr
en
g
t
h
en
e
d
b
y
u
s
in
g
two
lib
r
a
r
ies,
wh
ich
will c
o
m
p
en
s
ate
f
o
r
ea
ch
o
th
er
'
s
in
ad
eq
u
ac
ie
s.
T
ab
le
1
.
E
x
am
p
le
o
f
cr
awlin
g
p
r
o
ce
s
s
r
esu
lt
C
o
l
u
m
n
Ex
a
m
p
l
e
C
r
e
a
t
e
d
_
A
t
Th
u
F
e
b
2
2
1
8
:
0
9
:
5
7
+
0
0
0
0
2
0
2
1
Id
1
3
9
7
9
7
8
3
9
7
9
6
0
0
6
5
0
2
4
F
u
l
l
_
T
e
x
t
D
u
a
Tr
u
k
A
d
u
B
a
n
t
e
n
g
D
i
P
a
t
i
B
e
r
mu
l
a
S
a
a
t
H
i
n
o
C
o
b
a
S
a
l
i
p
M
o
t
o
r
,
B
e
g
i
n
i
K
r
o
n
o
l
o
g
i
n
y
a
.
\
N
\
N
sel
e
n
g
k
a
p
n
y
a
K
l
i
k
Ta
u
t
a
n
B
e
r
i
k
u
t
I
n
i
.
\
N
#
P
a
t
i
#
K
r
o
n
o
l
o
g
i
#
K
e
c
e
l
a
k
a
a
n
#
Tr
u
k
\
N
\
N
h
t
t
p
s:
/
/
T.
C
o
/
V
k
1
p
r
h
h
d
z
p
4
.
2
.
Na
m
ed
-
ent
it
ies t
a
g
g
ing
L
ab
elin
g
n
am
ed
en
titi
es
f
o
r
t
h
e
ter
m
s
in
th
e
d
ataset
co
m
p
letes
th
is
p
h
ase.
I
n
th
is
s
tu
d
y
[
2
2
]
,
t
h
e
s
p
ec
if
ied
en
tity
r
elate
s
to
v
ar
i
o
u
s
n
am
e
-
en
titi
es
co
n
n
ec
ted
with
tr
af
f
ic.
T
h
is
p
h
ase
is
co
m
p
leted
b
y
lab
elin
g
n
am
ed
en
titi
es
f
o
r
ter
m
s
in
th
e
d
ata
co
llectio
n
.
I
n
th
is
s
tu
d
y
[
2
2
]
,
th
e
s
p
ec
if
ied
e
n
tity
co
r
r
esp
o
n
d
s
to
v
ar
io
u
s
n
am
e
en
titi
es
th
at
ar
e
ass
o
ciat
ed
with
tr
af
f
ic.
T
ab
le
2
lis
ts
th
e
n
am
ed
en
tity
ca
teg
o
r
ies
th
at
h
av
e
b
ee
n
d
e
f
in
ed
an
d
h
a
v
e
a
s
tr
o
n
g
r
elatio
n
s
h
ip
with
th
e
ac
cid
en
t
d
ata.
W
h
en
tag
g
in
g
,
th
e
o
u
tco
m
e
o
f
t
h
is
g
r
o
u
p
is
u
tili
ze
d
to
cr
ea
te
a
n
am
ed
en
tity
lab
el
g
r
o
u
p
.
T
h
e
r
esear
ch
er
cr
ea
ted
th
e
lab
elin
g
ap
p
licatio
n
u
s
in
g
th
e
L
ar
av
el
f
r
am
ewo
r
k
[
2
3
]
an
d
th
e
Po
s
t
g
r
eSQL
d
atab
ase.
E
n
tity
tag
g
in
g
is
d
o
n
e
o
n
d
ata
th
at
h
as
b
ee
n
ac
q
u
ir
e
d
in
a
ce
r
tain
len
g
th
o
f
tim
e.
Fig
u
r
e
3
an
d
Fig
u
r
e
4
d
ep
ict
th
e
o
u
tc
o
m
es o
f
th
e
ta
g
g
in
g
p
r
o
ce
d
u
r
e
.
T
ab
le
1
.
L
is
t o
f
n
am
ed
-
e
n
titi
es a
n
n
o
tated
En
t
i
t
y
N
a
me
Ex
a
m
p
l
e
DAT
D
a
t
e
S
e
p
t
e
m
b
e
r
,
2
0
1
9
,
B
e
s
o
k
LO
C
Lo
c
a
t
i
o
n
R
a
w
a
m
a
n
g
u
n
,
J
a
k
a
r
t
a
,
C
h
i
n
a
,
C
i
p
a
l
i
,
S
e
mara
n
g
O
R
G
O
r
g
a
n
i
z
a
t
i
o
n
Li
o
n
A
i
r
,
B
U
M
N
,
P
o
l
r
i
,
K
e
m
e
n
h
u
b
TI
M
Ti
me
1
5
.
2
4
,
P
a
g
i
,
M
a
l
a
m
V
EH
V
e
h
i
c
l
e
A
v
a
n
z
a
,
I
n
n
o
v
a
,
B
o
e
i
n
g
,
M
o
b
i
l
,
B
u
s
Fig
u
r
e
1
.
E
n
tity
tag
g
in
g
p
r
o
ce
s
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
25
,
No
.
3
,
Ma
r
ch
20
22
:
1
6
7
2
-
1
6
7
8
1676
Fig
u
r
e
4
.
Am
o
u
n
ts
o
f
ea
ch
en
t
ity
4
.
3
.
Da
t
a
pre
-
pro
ce
s
s
ing
Data
p
r
o
ce
s
s
in
g
is
o
n
e
o
f
th
e
m
o
s
t
im
p
o
r
tan
t
asp
ec
ts
o
f
th
e
d
ata
an
aly
s
is
p
r
o
ce
s
s
,
an
d
it
f
r
eq
u
e
n
tly
n
ec
ess
itates
m
o
r
e
wo
r
k
an
d
t
im
e
[
2
4
]
.
I
n
th
is
p
h
ase,
we'
ll
tag
n
am
ed
en
titi
es.
T
h
is
en
a
b
les
th
e
c
r
ea
tio
n
o
f
d
iv
er
s
e
tex
ts
co
n
tain
in
g
th
in
g
s
th
at
h
av
e
s
ig
n
if
ican
ce
b
u
t
ar
e
d
elete
d
d
u
r
in
g
p
r
ep
r
o
ce
s
s
in
g
an
d
/o
r
ar
e
p
o
o
r
l
y
co
m
p
r
eh
e
n
d
ed
b
y
c
o
m
p
u
te
r
s
.
Data
will
b
e
clea
n
ed
th
r
o
u
g
h
m
an
y
s
tep
s
o
f
t
h
e
p
r
ep
r
o
c
ess
in
g
m
o
d
el.
T
h
e
lo
wer
(
)
m
eth
o
d
f
r
o
m
Py
th
o
n
'
s
Strin
g
m
o
d
u
le
is
u
s
ed
to
f
o
ld
th
e
ca
s
es.
Usi
n
g
th
e
Py
th
o
n
Strin
g
p
ac
k
ag
e,
s
u
p
er
f
lu
o
u
s
ch
ar
ac
ter
s
s
u
ch
as e
m
o
tico
n
s
,
web
s
ite
UR
L
s
,
p
u
n
ctu
atio
n
m
ar
k
s
,
d
o
u
b
le
s
p
ac
es,
an
d
n
ewlin
es a
r
e
r
em
o
v
ed
.
T
h
e
s
tem
m
in
g
p
r
o
ce
s
s
i
s
an
im
p
o
r
tan
t
p
r
e
-
p
r
o
ce
s
s
in
g
p
h
ase
th
at,
d
ep
en
d
in
g
o
n
th
e
lan
g
u
ag
e
em
p
lo
y
ed
,
m
ig
h
t
b
e
c
o
n
s
id
er
ed
a
to
u
g
h
s
tep
to
co
m
p
lete.
T
h
e
am
o
u
n
t
o
f
m
o
r
p
h
o
lo
g
ic
al
co
m
p
lex
ity
o
f
a
lan
g
u
ag
e
ca
n
im
p
ac
t
s
tem
m
in
g
o
u
tco
m
e
s
[
2
5
]
.
B
ec
au
s
e
th
e
NL
T
K
lib
r
ar
y
[
2
6
]
,
wh
i
ch
is
u
s
ed
f
o
r
th
e
s
tem
m
in
g
p
r
o
ce
s
s
,
d
o
es
n
o
t
c
u
r
r
en
tly
s
u
p
p
o
r
t
I
n
d
o
n
esian
,
t
h
e
s
tem
m
in
g
p
r
o
ce
s
s
in
I
n
d
o
n
esian
is
ca
r
r
ied
o
u
t
u
s
in
g
th
e
Sas
tr
awi
lib
r
ar
y
[
2
7
]
,
wh
ich
h
as
p
r
o
v
ed
to
b
e
f
ai
r
ly
co
m
p
eten
t
in
h
an
d
lin
g
th
e
I
n
d
o
n
esian
lan
g
u
ag
e
s
tem
m
in
g
p
r
o
ce
s
s
.
T
h
e
NL
T
K
lib
r
ar
y
is
u
s
ed
in
th
e
to
k
e
n
izin
g
p
r
o
ce
s
s
to
d
iv
id
e
s
en
ten
ce
s
in
to
lis
ts
with
a
s
p
ac
e
ch
ar
ac
ter
s
ep
ar
ato
r
.
T
h
e
NL
T
K
an
d
Sas
tr
awi
lib
r
ar
ies
ar
e
u
s
ed
in
th
e
s
to
p
wo
r
d
eli
m
in
atio
n
p
r
o
ce
d
u
r
e.
T
h
e
s
to
p
wo
r
d
r
e
m
o
v
al
p
r
o
ce
d
u
r
e
will
b
e
s
tr
en
g
th
e
n
ed
b
y
u
s
in
g
two
li
b
r
ar
ies,
wh
ich
will
c
o
m
p
en
s
ate
f
o
r
ea
c
h
o
th
er
'
s
in
ad
eq
u
ac
ies.
T
h
e
n
u
m
b
er
o
f
en
titi
es
ca
lcu
lated
in
ea
ch
r
ep
o
r
t
is
u
s
ed
as
a
p
ar
a
m
eter
in
th
e
n
am
ed
en
titi
es
an
d
h
y
b
r
i
d
s
ch
em
e
.
T
h
e
Fas
tTe
x
t
wo
r
d
em
b
e
d
d
i
n
g
p
r
o
ce
d
u
r
e
is
ca
r
r
ied
o
u
t
with
th
e
u
s
e
o
f
p
r
e
-
t
r
ain
ed
I
n
d
o
n
esian
lan
g
u
ag
e
m
o
d
els,
wh
ich
m
ay
b
e
f
o
u
n
d
at
Fas
tTe
x
t'
s
web
s
ite
[
2
8
]
.
E
m
o
ji
r
e
m
o
v
al,
p
u
n
ctu
atio
n
r
em
o
v
al,
ca
s
e
f
o
l
d
in
g
,
s
tem
m
in
g
,
s
to
p
wo
r
d
,
to
k
en
izatio
n
,
an
d
r
ep
r
esen
tatio
n
o
f
Fas
tTe
x
t
wo
r
d
s
ar
e
all
s
tep
s
o
f
d
ata
p
r
e
-
p
r
o
c
ess
in
g
th
at
ar
e
ex
ec
u
ted
u
s
in
g
th
e
W
o
r
d
2
Vec
m
o
d
el.
T
h
e
n
u
m
b
er
o
f
en
titi
es
ca
lcu
lated
in
ea
ch
r
ep
o
r
t
is
u
s
ed
as
a
p
ar
am
eter
in
th
e
NE
an
d
c
o
m
b
in
atio
n
m
o
d
elin
g
t
ec
h
n
iq
u
es.
T
a
b
le
3
s
h
o
ws th
e
o
u
tco
m
es o
f
th
e
p
r
e
-
p
r
o
ce
s
s
in
g
.
T
ab
le
3
.
T
h
e
r
esu
lts
o
f
th
e
p
r
e
-
p
r
o
ce
s
s
in
g
P
r
o
c
e
ss
e
d
Te
x
t
V
e
c
t
o
r
i
z
e
d
T
e
x
t
En
t
i
t
y
C
o
u
n
t
I
s Acc
i
d
e
n
t
[
b
r
u
k
,
k
e
c
e
l
a
k
a
a
n
,
ma
u
t
,
l
i
b
a
t
k
a
n
,
2
,
mo
b
i
l
,
1
.
.
.
[
0
.
1
1
7
5
9
9
9
0
5
,
0
.
1
7
2
6
9
9
9
6
,
0
.
9
8
9
5
,
0
.
5
1
7
8
0
0
0
3
,
.
.
.
[
2
,
0
,
0
,
0
,
1
,
3
]
1
[
1
3
,
1
4
t
e
r
j
a
d
i
,
k
e
c
e
l
a
k
a
a
n
,
b
e
r
u
n
t
u
n
,
j
l
,
m
a
y
j
.
.
.
[
-
0
.
0
6
2
5
0
0
0
1
,
0
.
3
7
5
9
,
-
0
.
0
4
5
6
0
0
0
1
2
,
-
0
.
0
9
2
6
,
0
.
.
.
[
1
,
0
,
1
,
0
,
0
,
0
]
1
[
k
e
c
e
l
a
k
a
a
n
,
s
i
a
n
g
,
j
l
,
l
a
h
o
r
,
b
a
t
u
,
k
e
j
a
d
i
a
n
,
.
.
.
[
0
.
2
0
8
3
9
9
9
8
,
-
0
.
0
7
2
9
9
9
9
9
,
-
0
.
5
5
7
1
,
0
.
7
5
3
2
,
0
.
5
.
.
.
[
1
,
0
,
1
,
0
,
0
,
1
]
1
[
k
e
c
e
l
a
k
a
a
n
,
j
l
,
r
a
y
a
,
ser
a
n
g
,
p
a
n
d
e
g
l
a
n
g
,
t
e
p
.
.
.
[
-
0
.
5
8
9
4
9
9
9
5
,
0
.
0
9
6
0
9
9
9
6
,
0
.
2
9
9
7
,
0
.
2
6
4
5
9
9
9
8
,
.
.
.
[
2
,
1
,
2
,
0
,
0
,
0
]
1
[
j
u
j
u
t
su
f
e
ss,
c
h
i
l
d
h
o
o
d
,
f
r
i
e
n
d
,
mera
n
g
k
a
p
,
c
r
.
.
.
[
1
.
8
6
8
0
9
9
8
,
-
1
.
1
4
7
7
0
0
1
,
0
.
4
4
8
8
9
9
9
8
,
1
.
4
2
0
4
,
-
0
.
.
.
[
0
,
0
,
0
,
0
,
0
,
0
]
0
4
.
4
.
T
ra
ini
ng
cla
s
s
if
ica
t
io
n us
ing
t
he
SV
M
a
lg
o
rit
hm
T
h
e
th
r
ee
tech
n
iq
u
es m
en
ti
o
n
ed
in
th
e
p
r
ec
ed
in
g
s
ec
tio
n
ar
e
u
s
ed
to
class
if
y
th
e
d
ata:
−
W
o
r
d
em
b
e
d
d
in
g
:
T
h
e
Fas
tTe
x
t
W
o
r
d
E
m
b
ed
d
in
g
m
o
d
el
is
u
s
ed
t
o
p
r
o
v
id
e
th
e
p
o
s
itio
n
v
alu
e
f
o
r
ea
c
h
tex
t w
h
en
m
o
d
elin
g
u
s
in
g
wo
r
d
r
ep
r
esen
tatio
n
.
−
Nam
ed
en
titi
es
: T
h
e
q
u
an
tity
o
f
ea
ch
n
am
e
d
en
tity
in
a
tex
t is u
s
ed
to
id
en
tify
th
e
m
ix
o
f
e
n
t
ities
in
a
tex
t
wh
en
m
o
d
eli
n
g
with
en
tity
ta
g
g
in
g
.
−
Hy
b
r
id
:
C
o
m
b
in
atio
n
is
ac
h
ie
v
ed
b
y
co
m
b
in
in
g
th
e
two
m
o
d
els
m
en
tio
n
ed
ab
o
v
e,
wh
ich
th
en
p
r
ed
icts
a
tex
t b
y
co
m
p
ar
in
g
ea
ch
m
o
d
el
'
s
co
n
tr
ib
u
tio
n
.
T
h
e
K
-
f
o
ld
cr
o
s
s
v
alid
atio
n
te
ch
n
iq
u
e
is
u
s
ed
to
v
alid
ate
th
e
tr
ain
in
g
o
u
tco
m
es.
C
r
o
s
s
v
alid
atio
n
is
a
tech
n
iq
u
e
th
at
p
r
o
v
id
es
a
s
y
s
tem
atic
way
f
o
r
ass
ess
in
g
m
o
d
el
ef
f
icac
y
an
d
co
m
p
ar
in
g
m
o
d
els
to
o
n
e
a
n
o
th
er
.
T
h
is
tech
n
iq
u
e
ass
u
m
es
th
at
th
e
m
o
d
el
was
tr
ain
ed
o
n
a
s
ep
ar
ate
d
ataset
f
r
o
m
th
e
o
n
e
th
at
was
u
s
ed
f
o
r
test
in
g
.
T
h
e
m
o
d
el
f
i
n
d
s
r
u
les
in
o
n
e
d
ataset
an
d
th
e
n
v
alu
e
s
th
em
in
a
an
o
th
er
d
ataset.
Mo
d
el
ac
cu
r
ac
y
m
ay
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
A
n
a
lysi
s
o
f n
a
med
-
e
n
tity e
ffect
o
n
text
cla
s
s
ifica
tio
n
o
f tra
ffic a
cc
id
en
t d
a
ta
…
(
A
n
u
g
r
a
h
Dw
ia
tma
ja
P
u
tr
a
)
1677
b
e
o
b
jectiv
ely
v
er
i
f
ied
u
s
in
g
th
e
v
alid
atio
n
d
ataset,
w
h
ich
p
r
o
v
id
es
in
f
o
r
m
atio
n
o
n
g
e
n
u
in
e
class
if
icatio
n
r
esu
lts
[
2
9
]
.
T
h
e
d
ataset
f
o
r
t
h
is
p
r
o
ce
d
u
r
e
will
b
e
d
e
r
iv
ed
v
ia
d
ata
v
alid
atio
n
.
T
h
is
tec
h
n
iq
u
e
d
iv
id
es
th
e
d
ataset
in
to
ten
s
ec
tio
n
s
an
d
c
h
an
g
es lo
ca
tio
n
s
ten
tim
es a
s
a
9
0
% tr
ain
in
g
f
o
ld
a
n
d
1
0
% v
alid
atio
n
f
o
ld
.
I
n
th
is
s
ch
em
e
,
we
e
x
am
in
ed
th
e
co
n
tr
ib
u
tio
n
r
atio
s
o
f
ea
c
h
s
ch
em
e,
wh
ich
r
an
g
e
d
f
r
o
m
0
.
2
to
0
.
8
.
As
a
co
n
s
eq
u
e
n
ce
,
th
e
b
est
a
cc
u
r
ac
y
c
o
m
p
a
r
is
o
n
was
ac
h
i
ev
ed
wh
e
n
th
e
wo
r
d
em
b
e
d
d
i
n
g
s
ch
em
e
an
d
th
e
n
am
ed
en
titi
es
s
ch
em
e
wer
e
co
m
b
in
ed
at
0
.
8
5
v
s
0
.
1
5
.
A
s
a
r
esu
lt
o
f
th
is
co
m
p
ar
is
o
n
,
th
e
n
am
ed
en
titi
es
s
ch
em
e
m
ay
g
iv
e
p
r
o
b
a
b
ilit
ies
as
a
s
u
p
p
lem
en
t
to
th
e
h
y
b
r
id
s
ch
em
e
wh
ile
m
ain
tain
in
g
a
b
alan
ce
d
co
n
tr
ib
u
tio
n
r
atio
v
alu
e.
T
h
e
co
m
b
in
atio
n
s
tr
ateg
y
is
s
h
o
w
n
in
T
ab
le
4
,
with
SVM
s
u
r
p
ass
in
g
th
e
o
t
h
er
two
b
y
a
s
co
r
e
o
f
9
0
.
2
7
%
.
T
h
is
d
em
o
n
s
tr
ates
th
at
u
s
in
g
n
am
ed
en
titi
es
in
th
e
tr
af
f
ic
a
cc
id
en
t
r
ep
o
r
t
d
ata
ca
teg
o
r
izatio
n
p
r
o
ce
s
s
as
a
s
u
p
p
o
r
tin
g
s
ch
em
e
f
o
r
wo
r
d
em
b
ed
d
in
g
h
as
r
esu
lted
in
a
2
.
7
0
%
in
cr
ea
s
e
in
ca
p
ab
ilit
ies.
T
h
e
h
y
b
r
id
s
ch
e
m
e
h
as
a
cr
o
s
s
-
v
alid
atio
n
s
co
r
e
o
f
8
1
.
9
8
%
.
T
h
is
d
em
o
n
s
tr
ates
th
at
th
e
h
y
b
r
id
ap
p
r
o
ac
h
wo
r
k
s
ef
f
ec
tiv
ely
wi
th
f
r
esh
d
ata.
T
ab
le
2
.
R
esu
lts
o
f
s
ch
em
a
cla
s
s
if
icatio
n
S
c
h
e
ma
A
c
c
u
r
a
c
y
S
c
o
r
e
C
r
o
ss V
a
l
i
d
a
t
i
o
n
W
o
r
d
Em
b
e
d
d
i
n
g
0.
8
7
5
6
7
6
0.
8
0
8
0
6
9
N
a
med
E
n
t
i
t
i
e
s
0.
8
1
0
8
1
1
0.
7
9
4
8
2
8
H
y
b
r
i
d
0.
9
0
2
7
0
3
0.
8
1
1
5
9
5
5.
CO
NCLU
SI
O
N
AND
F
U
T
U
RE
WO
RK
T
h
e
d
ataset
in
cl
u
d
es
o
f
d
at
a
in
its
o
r
ig
in
al
s
tate,
d
ata
lab
elin
g
r
esu
lts
f
o
r
d
ef
in
e
d
en
titi
es,
p
r
etr
ea
tm
en
t
p
r
o
ce
s
s
in
g
r
esu
lts
,
an
d
wo
r
d
em
b
e
d
d
in
g
r
ep
r
esen
tatio
n
r
esu
lts
.
An
ev
alu
atio
n
o
f
th
e
p
er
f
o
r
m
an
ce
o
f
ea
ch
s
ch
em
e
is
ca
r
r
ied
o
u
t
with
a
m
o
d
el
a
cc
u
r
ac
y
s
co
r
e
b
ased
o
n
th
e
s
u
g
g
ested
m
o
d
elin
g
s
ch
em
e
to
ex
am
in
e
th
e
in
f
lu
e
n
ce
o
f
n
am
ed
en
titi
es
o
n
th
e
c
ateg
o
r
izatio
n
o
f
tr
af
f
ic
ac
cid
e
n
t
d
ata.
W
h
en
u
s
in
g
a
h
y
b
r
id
s
tr
ateg
y
with
th
e
SVM
m
o
d
el,
t
h
e
b
est
ac
cu
r
ac
y
r
esu
lts
ar
e
o
b
tain
ed
at
9
0
.
2
7
%
.
T
h
is
ap
p
r
o
ac
h
o
u
tp
er
f
o
r
m
s
th
e
ca
teg
o
r
izatio
n
m
eth
o
d
b
ased
o
n
t
r
ad
itio
n
a
l
wo
r
d
em
b
e
d
d
in
g
,
wh
ich
s
co
r
ed
8
7
.
5
7
%
in
th
is
s
tu
d
y
'
s
co
m
p
ar
is
o
n
.
I
t'
s
lik
ely
th
at
th
e
n
am
e
d
e
n
tity
s
ch
em
e
p
r
o
v
id
es
ex
p
lan
atio
n
to
th
e
co
m
p
r
eh
en
s
io
n
o
f
s
en
ten
ce
s
th
at
ar
e
n
'
t
ef
f
ec
tiv
e
ly
r
ep
r
esen
ted
b
y
wo
r
d
em
b
e
d
d
in
g
,
allo
win
g
th
e
r
esu
lt
to
im
p
r
o
v
e.
Ho
wev
e
r
,
u
s
in
g
th
e
n
u
m
b
er
o
f
o
cc
u
r
r
en
ce
s
o
f
n
am
ed
en
titi
es
as
an
o
n
ly
in
p
u
t
f
o
r
tex
t
ca
teg
o
r
izatio
n
p
r
o
d
u
ce
d
p
o
o
r
r
esu
lts
,
with
th
e
lo
west sco
r
e
o
f
8
1
.
0
8
%
wh
en
co
m
p
a
r
ed
to
alter
n
ativ
e
tech
n
iq
u
es.
T
h
is
d
ataset
ca
n
b
e
ac
q
u
ir
ed
an
d
u
s
ed
in
th
e
f
u
tu
r
e
f
o
r
r
esear
ch
.
L
a
b
elin
g
th
e
d
ata
f
o
r
t
r
ain
in
g
is
r
eq
u
ir
ed
to
im
p
r
o
v
e
m
ac
h
in
e
lear
n
in
g
with
a
b
r
o
a
d
er
d
ata
r
an
g
e.
A
d
d
itio
n
al
m
ac
h
in
e
l
ea
r
n
in
g
ap
p
r
o
ac
h
es,
s
u
ch
as
d
ee
p
lear
n
in
g
,
ca
n
b
e
en
ab
led
b
y
in
co
r
p
o
r
atin
g
s
u
f
f
icien
t
tr
ain
in
g
d
ata
.
I
t'
s
also
p
o
s
s
ib
le
to
b
r
o
ad
e
n
th
e
lab
elin
g
o
p
tio
n
s
f
o
r
Nam
e
d
E
n
titi
es.
B
ec
au
s
e
th
e
p
r
o
p
o
s
ed
h
y
b
r
id
m
eth
o
d
lar
g
el
y
d
e
p
en
d
s
o
n
d
ata
f
r
o
m
n
am
ed
en
tity
lab
els,
ac
cu
r
ate
lab
elin
g
o
f
n
am
ed
e
n
titi
es
is
r
eq
u
ir
ed
to
o
f
f
e
r
g
o
o
d
s
en
ten
ce
in
ter
p
r
etatio
n
.
I
t
is
b
eliev
ed
th
at
th
e
c
o
m
p
u
ter
w
o
u
ld
b
e
a
b
le
to
co
m
p
r
e
h
en
d
t
h
e
m
ea
n
in
g
o
f
t
h
e
wo
r
d
in
it
s
co
n
tex
t
in
g
r
ea
te
r
d
ep
th
,
wh
ile
r
em
ain
in
g
a
s
in
g
le
en
tity
.
C
o
llectin
g
d
ata
f
r
o
m
s
o
u
r
ce
s
o
th
er
th
an
T
witter
,
o
n
th
e
o
th
er
h
an
d
,
is
ad
v
is
ed
in
o
r
d
er
to
cr
ea
te
b
ig
g
er
an
d
m
o
r
e
v
ar
ied
d
ata
b
ases
.
RE
F
E
R
E
NC
E
S
[
1
]
R
.
I
sh
r
a
t
,
“
G
l
o
b
a
l
S
t
a
t
u
s R
e
p
o
r
t
o
n
R
o
a
d
S
a
f
e
t
y
2
0
1
8
:
S
u
m
mary
,
”
Wo
r
l
d
H
e
a
l
t
h
O
rg
a
n
i
z
a
t
i
o
n
,
n
o
.
1
,
p
.
2
0
,
2
0
1
8
,
A
c
c
e
sse
d
:
Ja
n
.
1
9
,
2
0
2
2
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
:
/
/
a
p
p
s
.
w
h
o
.
i
n
t
/
b
o
o
k
o
r
d
e
r
s.
[
2
]
R
.
S
u
j
a
y
,
J.
P
u
j
a
r
i
,
V
.
S
.
B
h
a
t
,
a
n
d
A
.
D
i
x
i
t
,
“
Ti
m
e
l
i
n
e
A
n
a
l
y
si
s
o
f
T
w
i
t
t
e
r
U
ser,”
Pr
o
c
e
d
i
a
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
1
3
2
,
p
p
.
1
5
7
–
1
6
6
,
2
0
1
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
r
o
c
s.2
0
1
8
.
0
5
.
1
7
9
.
[
3
]
D
.
A
.
S
a
p
u
t
r
o
a
n
d
A
.
S
.
G
i
r
sa
n
g
,
“
C
l
a
s
si
f
i
c
a
t
i
o
n
o
f
t
r
a
f
f
i
c
a
c
c
i
d
e
n
t
i
n
f
o
r
mat
i
o
n
u
s
i
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
f
r
o
m
so
c
i
a
l
me
d
i
a
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
Em
e
r
g
i
n
g
T
ren
d
s
i
n
E
n
g
i
n
e
e
r
i
n
g
R
e
se
a
rc
h
,
v
o
l
.
8
,
n
o
.
3
,
p
p
.
6
3
0
–
6
3
7
,
M
a
r
.
2
0
2
0
,
d
o
i
:
1
0
.
3
0
5
3
4
/
i
j
e
t
e
r
/
2
0
2
0
/
0
4
8
3
2
0
2
0
.
[
4
]
A
.
V
.
D
e
u
r
se
n
,
A
.
M
e
sb
a
h
,
a
n
d
A
.
N
e
d
e
r
l
o
f
,
“
C
r
a
w
l
-
b
a
se
d
a
n
a
l
y
s
i
s
o
f
w
e
b
a
p
p
l
i
c
a
t
i
o
n
s:
P
r
o
sp
e
c
t
s
a
n
d
c
h
a
l
l
e
n
g
e
s
,
”
S
c
i
e
n
c
e
o
f
C
o
m
p
u
t
e
r
Pr
o
g
r
a
m
m
i
n
g
,
v
o
l
.
9
7
,
n
o
.
P
1
,
p
p
.
1
7
3
–
1
8
0
,
Ja
n
.
2
0
1
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
s
c
i
c
o
.
2
0
1
4
.
0
9
.
0
0
5
.
[
5
]
D
.
A
n
t
o
n
a
k
a
k
i
,
P
.
F
r
a
g
o
p
o
u
l
o
u
,
a
n
d
S
.
I
o
a
n
n
i
d
i
s,
“
A
su
r
v
e
y
o
f
Tw
i
t
t
e
r
r
e
s
e
a
r
c
h
:
D
a
t
a
m
o
d
e
l
,
g
r
a
p
h
s
t
r
u
c
t
u
r
e
,
s
e
n
t
i
m
e
n
t
a
n
a
l
y
s
i
s
a
n
d
a
t
t
a
c
k
s,
”
E
x
p
e
rt
S
y
st
e
m
s w
i
t
h
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
6
4
,
p
.
1
1
4
0
0
6
,
F
e
b
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
sw
a
.
2
0
2
0
.
1
1
4
0
0
6
.
[
6
]
“
Tw
i
t
t
e
r
’
s
1
0
Y
e
a
r
S
t
r
u
g
g
l
e
w
i
t
h
D
e
v
e
l
o
p
e
r
R
e
l
a
t
i
o
n
s
|
N
o
r
d
i
c
A
P
I
s
|
.
”
h
t
t
p
s:
/
/
n
o
r
d
i
c
a
p
i
s
.
c
o
m/
t
w
i
t
t
e
r
-
10
-
y
e
a
r
-
st
r
u
g
g
l
e
-
w
i
t
h
-
d
e
v
e
l
o
p
e
r
-
r
e
l
a
t
i
o
n
s
/
(
a
c
c
e
sse
d
A
p
r
.
2
7
,
2
0
2
1
)
.
[
7
]
“
D
e
l
i
v
e
r
i
n
g
a
c
o
n
si
s
t
e
n
t
Tw
i
t
t
e
r
e
x
p
e
r
i
e
n
c
e
.
”
h
t
t
p
s
:
/
/
b
l
o
g
.
t
w
i
t
t
e
r
.
c
o
m
/
d
e
v
e
l
o
p
e
r
/
e
n
_
u
s/
a
/
2
0
1
2
/
d
e
l
i
v
e
r
i
n
g
-
c
o
n
s
i
st
e
n
t
-
t
w
i
t
t
e
r
-
e
x
p
e
r
i
e
n
c
e
(
a
c
c
e
ss
e
d
A
p
r
.
2
7
,
2
0
2
1
)
.
[
8
]
“
Th
e
I
n
f
r
a
st
r
u
c
t
u
r
e
B
e
h
i
n
d
T
w
i
t
t
e
r
:
S
c
a
l
e
.
”
h
t
t
p
s:
/
/
b
l
o
g
.
t
w
i
t
t
e
r
.
c
o
m
/
e
n
g
i
n
e
e
r
i
n
g
/
e
n
_
u
s
/
t
o
p
i
c
s
/
i
n
f
r
a
s
t
r
u
c
t
u
r
e
/
2
0
1
7
/
t
h
e
-
i
n
f
r
a
s
t
r
u
c
t
u
r
e
-
b
e
h
i
n
d
-
t
w
i
t
t
e
r
-
sc
a
l
e
(
a
c
c
e
sse
d
A
p
r
.
2
8
,
2
0
2
1
)
.
[
9
]
K
.
Ta
k
e
u
c
h
i
a
n
d
N
.
C
o
l
l
i
e
r
,
“
B
i
o
-
me
d
i
c
a
l
e
n
t
i
t
y
e
x
t
r
a
c
t
i
o
n
u
si
n
g
S
u
p
p
o
r
t
V
e
c
t
o
r
M
a
c
h
i
n
e
s,”
i
n
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
{A
C
L
}
2
0
0
3
w
o
r
k
sh
o
p
o
n
N
a
t
u
r
a
l
l
a
n
g
u
a
g
e
p
r
o
c
e
ssi
n
g
i
n
b
i
o
m
e
d
i
c
i
n
e
-
,
2
0
0
3
,
p
p
.
5
7
–
6
4
,
d
o
i
:
1
0
.
3
1
1
5
/
1
1
1
8
9
5
8
.
1
1
1
8
9
6
6
.
[
1
0
]
J.
C
e
r
v
a
n
t
e
s,
F
.
G
a
r
c
i
a
-
La
m
o
n
t
,
L.
R
o
d
r
í
g
u
e
z
-
M
a
z
a
h
u
a
,
a
n
d
A
.
L
o
p
e
z
,
“
A
c
o
m
p
r
e
h
e
n
s
i
v
e
su
r
v
e
y
o
n
s
u
p
p
o
r
t
v
e
c
t
o
r
ma
c
h
i
n
e
c
l
a
ss
i
f
i
c
a
t
i
o
n
:
A
p
p
l
i
c
a
t
i
o
n
s,
c
h
a
l
l
e
n
g
e
s
a
n
d
t
r
e
n
d
s,
”
N
e
u
ro
c
o
m
p
u
t
i
n
g
,
v
o
l
.
4
0
8
,
p
p
.
1
8
9
–
2
1
5
,
S
e
p
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
n
e
u
c
o
m.
2
0
1
9
.
1
0
.
1
1
8
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
25
,
No
.
3
,
Ma
r
ch
20
22
:
1
6
7
2
-
1
6
7
8
1678
[
1
1
]
A
.
G
o
y
a
l
,
V
.
G
u
p
t
a
,
a
n
d
M
.
K
u
mar
,
“
R
e
c
e
n
t
N
a
me
d
En
t
i
t
y
R
e
c
o
g
n
i
t
i
o
n
a
n
d
C
l
a
ssi
f
i
c
a
t
i
o
n
t
e
c
h
n
i
q
u
e
s
:
A
s
y
s
t
e
mat
i
c
r
e
v
i
e
w
,
”
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
Re
v
i
e
w
,
v
o
l
.
2
9
,
p
p
.
2
1
–
4
3
,
A
u
g
.
2
0
1
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
sr
e
v
.
2
0
1
8
.
0
6
.
0
0
1
.
[
1
2
]
M
.
P
a
ş
c
a
,
D
.
L
i
n
,
J
.
B
i
g
h
a
m,
A
.
L
i
f
c
h
i
t
s,
a
n
d
A
.
Ja
i
n
,
“
O
r
g
a
n
i
z
i
n
g
a
n
d
s
e
a
r
c
h
i
n
g
t
h
e
W
o
r
l
d
W
i
d
e
W
e
b
o
f
f
a
c
t
s
-
S
t
e
p
o
n
e
:
T
h
e
q
u
e
-
mi
l
l
i
o
n
f
a
c
t
e
x
t
r
a
c
t
i
o
n
c
h
a
l
l
e
n
g
e
,
”
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
N
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
2
,
2
0
0
6
,
p
p
.
1
4
0
0
–
1
4
0
5
,
A
c
c
e
sse
d
:
Ja
n
.
1
9
,
2
0
2
2
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s:
/
/
r
e
s
e
a
r
c
h
.
g
o
o
g
l
e
/
p
u
b
s
/
p
u
b
6
9
/
.
[
1
3
]
J.
-
H
.
K
i
m,
I
.
-
H
.
K
a
n
g
,
a
n
d
K
.
-
S
.
C
h
o
i
,
“
U
n
s
u
p
e
r
v
i
se
d
n
a
m
e
d
e
n
t
i
t
y
c
l
a
ssi
f
i
c
a
t
i
o
n
m
o
d
e
l
s
a
n
d
t
h
e
i
r
e
n
se
mb
l
e
s,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
1
9
t
h
i
n
t
e
rn
a
t
i
o
n
a
l
c
o
n
f
e
re
n
c
e
o
n
C
o
m
p
u
t
a
t
i
o
n
a
l
l
i
n
g
u
i
st
i
c
s
-
,
2
0
0
2
,
p
p
.
1
–
7
,
d
o
i
:
1
0
.
3
1
1
5
/
1
0
7
2
2
2
8
.
1
0
7
2
3
1
6
.
[
1
4
]
D
.
M
.
B
i
k
e
l
,
S
.
M
i
l
l
e
r
,
R
.
S
c
h
w
a
r
t
z
,
a
n
d
R
.
W
e
i
sc
h
e
d
e
l
,
“
N
y
m
b
l
e
:
A
h
i
g
h
-
p
e
r
f
o
r
m
a
n
c
e
l
e
a
r
n
i
n
g
n
a
me
-
f
i
n
d
e
r
,
”
i
n
5
t
h
C
o
n
f
e
re
n
c
e
o
n
A
p
p
l
i
e
d
N
a
t
u
r
a
l
L
a
n
g
u
a
g
e
Pr
o
c
e
s
si
n
g
,
AN
L
P
1
9
9
7
-
Pr
o
c
e
e
d
i
n
g
s
,
1
9
9
7
,
p
p
.
1
9
4
–
2
0
1
,
d
o
i
:
1
0
.
3
1
1
5
/
9
7
4
5
5
7
.
9
7
4
5
8
6
.
[
1
5
]
A
.
S
u
l
t
a
n
,
A
.
-
H
.
A
mee
n
,
M
.
F
a
r
e
a
,
O
.
F
u
a
d
,
a
n
d
T.
B
a
g
a
s
h
,
“
A
B
i
o
me
d
i
c
a
l
N
a
me
d
E
n
t
i
t
y
R
e
c
o
g
n
i
t
i
o
n
U
si
n
g
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
C
l
a
s
si
f
i
e
r
s
a
n
d
R
i
c
h
F
e
a
t
u
r
e
S
e
t
,
”
I
J
C
S
N
S
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
N
e
t
w
o
rk
S
e
c
u
ri
t
y
,
v
o
l
.
1
7
,
n
o
.
1
,
p
.
1
7
0
,
2
0
1
7
.
[
1
6
]
J.
L
i
,
A
.
S
u
n
,
J
.
H
a
n
,
a
n
d
C
.
L
i
,
“
A
S
u
r
v
e
y
o
n
D
e
e
p
Le
a
r
n
i
n
g
f
o
r
N
a
me
d
E
n
t
i
t
y
R
e
c
o
g
n
i
t
i
o
n
,
”
I
EEE
T
ra
n
s
a
c
t
i
o
n
s
o
n
K
n
o
w
l
e
d
g
e
a
n
d
D
a
t
a
En
g
i
n
e
e
ri
n
g
,
p
p
.
1
–
1
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
t
k
d
e
.
2
0
2
0
.
2
9
8
1
3
1
4
.
[
1
7
]
J.
-
H
.
K
i
m
a
n
d
P
.
W
o
o
d
l
a
n
d
,
“
A
r
u
l
e
-
b
a
s
e
d
n
a
me
d
e
n
t
i
t
y
r
e
c
o
g
n
i
t
i
o
n
s
y
s
t
e
m fo
r
s
p
e
e
c
h
i
n
p
u
t
,
”
2
0
0
0
,
p
p
.
5
2
8
–
5
3
1
.
[
1
8
]
“
Tw
i
t
t
e
r
:
m
o
n
t
h
l
y
a
c
t
i
v
e
u
s
e
r
s
w
o
r
l
d
w
i
d
e
|
S
t
a
t
i
s
t
a
,
”
h
t
t
p
s
:
/
/
w
w
w
.
st
a
t
i
st
a
.
c
o
m
/
st
a
t
i
st
i
c
s
/
2
8
2
0
8
7
/
n
u
mb
e
r
-
of
-
mo
n
t
h
l
y
-
a
c
t
i
v
e
-
t
w
i
t
t
e
r
-
u
s
e
r
s/
(
a
c
c
e
sse
d
Ju
l
.
0
3
,
2
0
2
0
)
.
[
1
9
]
A
.
G
a
l
-
T
z
u
r
,
S
.
M
.
G
r
a
n
t
-
M
u
l
l
e
r
,
T
.
K
u
f
l
i
k
,
E.
M
i
n
k
o
v
,
S
.
N
o
c
e
r
a
,
a
n
d
I
.
S
h
o
o
r
,
“
T
h
e
p
o
t
e
n
t
i
a
l
o
f
s
o
c
i
a
l
me
d
i
a
i
n
d
e
l
i
v
e
r
i
n
g
t
r
a
n
s
p
o
r
t
p
o
l
i
c
y
g
o
a
l
s
,
”
T
r
a
n
sp
o
r
t
P
o
l
i
c
y
,
v
o
l
.
3
2
,
p
p
.
1
1
5
–
1
2
3
,
M
a
r
.
2
0
1
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
t
r
a
n
p
o
l
.
2
0
1
4
.
0
1
.
0
0
7
.
[
2
0
]
Y
.
G
u
i
,
Z
.
G
a
o
,
R
.
Li
,
a
n
d
X
.
Y
a
n
g
,
“
H
i
e
r
a
r
c
h
i
c
a
l
t
e
x
t
c
l
a
ss
i
f
i
c
a
t
i
o
n
f
o
r
n
e
w
s
a
r
t
i
c
l
e
s
b
a
se
d
-
o
n
n
a
me
d
e
n
t
i
t
i
e
s
,
”
i
n
L
e
c
t
u
re
N
o
t
e
s
i
n
C
o
m
p
u
t
e
r S
c
i
e
n
c
e
(
i
n
c
l
u
d
i
n
g
su
b
se
ri
e
s
L
e
c
t
u
re
N
o
t
e
s i
n
A
rt
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
L
e
c
t
u
r
e
N
o
t
e
s
i
n
Bi
o
i
n
f
o
r
m
a
t
i
c
s)
,
v
o
l
.
7
7
1
3
LN
A
I
,
S
p
r
i
n
g
e
r
B
e
r
l
i
n
H
e
i
d
e
l
b
e
r
g
,
2
0
1
2
,
p
p
.
3
1
8
–
3
2
9
.
[
2
1
]
Y
.
Ta
n
,
“
A
p
p
l
i
c
a
t
i
o
n
s
,
”
i
n
G
p
u
-
B
a
se
d
Pa
r
a
l
l
e
l
I
m
p
l
e
m
e
n
t
a
t
i
o
n
o
f
S
w
a
rm
I
n
t
e
l
l
i
g
e
n
c
e
A
l
g
o
r
i
t
h
m
s
,
El
s
e
v
i
e
r
,
2
0
1
6
,
p
p
.
1
6
7
–
1
7
7
.
[
2
2
]
M
.
S
c
h
i
e
r
s
c
h
,
V
.
M
i
r
o
n
o
v
a
,
M
.
S
c
h
mi
t
t
,
P
.
T
h
o
mas,
A
.
G
a
b
r
y
sza
k
,
a
n
d
L.
H
e
n
n
i
g
,
“
A
G
e
r
ma
n
c
o
r
p
u
s
f
o
r
f
i
n
e
-
g
r
a
i
n
e
d
n
a
m
e
d
e
n
t
i
t
y
r
e
c
o
g
n
i
t
i
o
n
a
n
d
r
e
l
a
t
i
o
n
e
x
t
r
a
c
t
i
o
n
o
f
t
r
a
f
f
i
c
a
n
d
i
n
d
u
st
r
y
e
v
e
n
t
s,”
L
R
EC
2
0
1
8
-
1
1
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
L
a
n
g
u
a
g
e
Re
s
o
u
rce
s
a
n
d
E
v
a
l
u
a
t
i
o
n
,
A
p
r
.
2
0
1
9
,
p
p
.
4
4
3
7
–
4
4
4
4
,
A
c
c
e
ss
e
d
:
J
a
n
.
1
9
,
2
0
2
2
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s
:
/
/
a
r
x
i
v
.
o
r
g
/
a
b
s/
2
0
0
4
.
0
3
2
8
3
v
1
[
2
3
]
R
.
Y
.
H
e
,
“
D
e
s
i
g
n
a
n
d
I
mp
l
e
m
e
n
t
a
t
i
o
n
o
f
W
e
b
B
a
se
d
o
n
L
a
r
a
v
e
l
F
r
a
mew
o
r
k
,
”
i
n
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
2
0
1
4
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
El
e
c
t
r
o
n
i
c
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
6
,
2
0
1
5
,
d
o
i
:
1
0
.
2
9
9
1
/
i
c
c
se
t
-
1
4
.
2
0
1
5
.
6
6
.
[
2
4
]
S
.
R
a
m
í
r
e
z
-
G
a
l
l
e
g
o
,
B
.
K
r
a
w
c
z
y
k
,
S
.
G
a
r
c
í
a
,
M
.
W
o
ź
n
i
a
k
,
a
n
d
F
.
H
e
r
r
e
r
a
,
“
A
s
u
r
v
e
y
o
n
d
a
t
a
p
r
e
p
r
o
c
e
ss
i
n
g
f
o
r
d
a
t
a
st
r
e
a
m
mi
n
i
n
g
:
C
u
r
r
e
n
t
st
a
t
u
s
a
n
d
f
u
t
u
r
e
d
i
r
e
c
t
i
o
n
s,”
N
e
u
r
o
c
o
m
p
u
t
i
n
g
,
v
o
l
.
2
3
9
,
p
p
.
3
9
–
5
7
,
M
a
y
2
0
1
7
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
n
e
u
c
o
m.
2
0
1
7
.
0
1
.
0
7
8
.
[
2
5
]
M
.
N
a
i
l
i
,
A
.
H
.
C
h
a
i
b
i
,
a
n
d
H
.
H
.
B
e
n
G
h
e
z
a
l
a
,
“
C
o
m
p
a
r
a
t
i
v
e
st
u
d
y
o
f
A
r
a
b
i
c
s
t
e
mm
i
n
g
a
l
g
o
r
i
t
h
ms
f
o
r
t
o
p
i
c
i
d
e
n
t
i
f
i
c
a
t
i
o
n
,
”
P
ro
c
e
d
i
a
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
1
5
9
,
p
p
.
7
9
4
–
8
0
2
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
r
o
c
s.
2
0
1
9
.
0
9
.
2
3
8
.
[
2
6
]
V
.
N
.
G
u
d
i
v
a
d
a
a
n
d
K
.
A
r
b
a
b
i
f
a
r
d
,
“
O
p
e
n
-
S
o
u
r
c
e
L
i
b
r
a
r
i
e
s
,
A
p
p
l
i
c
a
t
i
o
n
F
r
a
mew
o
r
k
s,
a
n
d
W
o
r
k
f
l
o
w
S
y
st
e
ms
f
o
r
N
LP,
”
i
n
H
a
n
d
b
o
o
k
o
f
S
t
a
t
i
st
i
c
s
,
v
o
l
.
3
8
,
El
s
e
v
i
e
r
,
2
0
1
8
,
p
p
.
3
1
–
5
0
.
[
2
7
]
“
sast
r
a
w
i
/
s
a
st
r
a
w
i
:
H
i
g
h
q
u
a
l
i
t
y
s
t
e
mm
e
r
l
i
b
r
a
r
y
f
o
r
I
n
d
o
n
e
s
i
a
n
L
a
n
g
u
a
g
e
(
B
a
h
a
s
a
)
,
”
h
t
t
p
s:
/
/
g
i
t
h
u
b
.
c
o
m
/
s
a
st
r
a
w
i
/
sas
t
r
a
w
i
(
a
c
c
e
s
se
d
A
p
r
.
2
8
,
2
0
2
1
)
.
[
2
8
]
P
.
B
o
j
a
n
o
w
s
k
i
,
E.
G
r
a
v
e
,
A
.
J
o
u
l
i
n
,
a
n
d
T
.
M
i
k
o
l
o
v
,
“
E
n
r
i
c
h
i
n
g
W
o
r
d
V
e
c
t
o
r
s
w
i
t
h
S
u
b
w
o
r
d
I
n
f
o
r
ma
t
i
o
n
,
”
T
r
a
n
s
a
c
t
i
o
n
s
o
f
t
h
e
Asso
c
i
a
t
i
o
n
f
o
r
C
o
m
p
u
t
a
t
i
o
n
a
l
L
i
n
g
u
i
st
i
c
s
,
v
o
l
.
5
,
p
p
.
1
3
5
–
1
4
6
,
D
e
c
.
2
0
1
7
,
d
o
i
:
1
0
.
1
1
6
2
/
t
a
c
l
_
a
_
0
0
0
5
1
.
[
2
9
]
M
.
R
a
f
a
ł
o
,
“
C
r
o
ss
v
a
l
i
d
a
t
i
o
n
m
e
t
h
o
d
s:
A
n
a
l
y
si
s
b
a
se
d
o
n
d
i
a
g
n
o
st
i
c
s
o
f
t
h
y
r
o
i
d
c
a
n
c
e
r
me
t
a
s
t
a
s
i
s,”
I
C
T
E
x
p
ress
,
M
a
y
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
c
t
e
.
2
0
2
1
.
0
5
.
0
0
1
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Anu
g
r
a
h
Dw
i
a
tm
a
ja
P
u
tr
a
is
c
u
rre
n
tl
y
a
so
ftwa
re
e
n
g
in
e
e
r
a
n
d
p
ro
jec
t
m
a
n
a
g
e
r
a
t
a
n
a
ti
o
n
a
l
c
o
m
p
a
n
y
.
He
e
a
rn
e
d
h
is
M
.
Ko
m
.
a
t
Bisa
N
u
sa
n
tara
Un
iv
e
rsit
y
,
De
p
a
rtme
n
t
o
f
In
fo
rm
a
ti
c
s
En
g
i
n
e
e
rin
g
,
Ja
k
a
rta
In
d
o
n
e
sia
,
i
n
2
0
2
1
,
a
n
d
c
o
m
p
lete
d
h
is
u
n
d
e
rg
ra
d
u
a
te
e
d
u
c
a
ti
o
n
fro
m
th
e
De
p
a
rtme
n
t
o
f
In
f
o
rm
a
ti
o
n
S
y
ste
m
s,
S
e
p
u
lu
h
N
o
p
e
m
b
e
r
In
sti
tu
te
o
f
Tec
h
n
o
l
o
g
y
,
S
u
ra
b
a
y
a
I
n
d
o
n
e
si
a
,
in
2
0
1
8
.
He
wa
s
a
F
u
ll
S
t
a
c
k
De
v
e
lo
p
e
r
a
t
Ril
iv
.
c
o
,
S
u
ra
b
a
y
a
,
in
2
0
1
6
–
2
0
1
8
a
n
d
a
ls
o
wo
r
k
e
d
a
s
a
we
b
d
e
v
e
l
o
p
e
r
in
v
a
rio
u
s
p
ro
jec
ts
in
2
0
1
5
–
2
0
1
9
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
a
n
u
g
ra
h
d
p
u
tra@g
m
a
il
.
c
o
m
.
Abb
a
S
u
g
a
n
d
a
G
irs
a
n
g
is
c
u
rre
n
tl
y
lec
tu
re
r
a
t
m
a
ste
r
in
f
o
rm
a
ti
o
n
tec
h
n
o
lo
g
y
a
t
Bin
a
Nu
sa
n
tara
Un
iv
e
rsity
Ja
k
a
rt
a
.
He
o
b
tain
e
d
P
h
.
D.
d
e
g
re
e
in
t
h
e
In
stit
u
te
o
f
Co
m
p
u
ter
a
n
d
Co
m
m
u
n
ica
ti
o
n
E
n
g
in
e
e
rin
g
,
De
p
a
rtme
n
t
o
f
El
e
c
tri
c
a
l
E
n
g
in
e
e
rin
g
a
n
d
Na
ti
o
n
a
l
Ch
e
n
g
K
u
n
g
Un
iv
e
rsity
,
Tain
a
n
,
Taiwa
n
,
in
2
0
1
4
.
He
g
ra
d
u
a
ted
b
a
c
h
e
l
o
r
fr
o
m
t
h
e
De
p
a
rtme
n
t
o
f
El
e
c
tri
c
a
l
En
g
i
n
e
e
rin
g
,
G
a
d
jah
M
a
d
a
Un
i
v
e
rsity
(UG
M
),
Yo
g
y
a
k
a
rta
In
d
o
n
e
sia
,
i
n
2
0
0
0
.
He
t
h
e
n
c
o
n
ti
n
u
e
d
h
is
m
a
ste
rs
d
e
g
re
e
in
t
h
e
De
p
a
rtme
n
t
o
f
C
o
m
p
u
ter S
c
ien
c
e
in
t
h
e
sa
m
e
u
n
iv
e
rsity
i
n
2
0
0
6
–
2
0
0
8
.
He
wa
s
a
sta
ff
c
o
n
su
lt
a
n
t
p
r
o
g
ra
m
m
e
r
in
Be
th
e
sd
a
Ho
sp
it
a
l,
Yo
g
y
a
k
a
rta,
i
n
2
0
0
1
a
n
d
a
lso
wo
rk
e
d
a
s
a
we
b
d
e
v
e
lo
p
e
r
in
2
0
0
2
–
2
0
0
3
.
He
th
e
n
jo
i
n
e
d
th
e
fa
c
u
lt
y
o
f
De
p
a
rtme
n
t
o
f
In
fo
rm
a
ti
c
s
En
g
i
n
e
e
rin
g
in
Ja
n
a
b
a
d
ra
Un
i
v
e
rsity
a
s
a
lec
tu
re
r
i
n
2
0
0
3
-
2
0
1
5
.
He
a
lso
tau
g
h
t
so
m
e
su
b
jec
ts
a
t
so
m
e
u
n
i
v
e
rsi
ti
e
s
in
2
0
0
6
–
2
0
0
8
.
His
re
se
a
rc
h
i
n
tere
sts
i
n
c
lu
d
e
sw
a
rm
in
telli
g
e
n
c
e
,
c
o
m
b
in
a
t
o
rial
o
p
ti
m
iza
ti
o
n
,
a
n
d
d
e
c
isio
n
su
p
p
o
rt
sy
st
e
m
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
a
g
irsa
n
g
@b
i
n
u
s.e
d
u
.
Evaluation Warning : The document was created with Spire.PDF for Python.