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.
3
9
,
No
.
1
,
Ju
ly
2
0
2
5
,
p
p
.
60
3
~
61
3
I
SS
N:
2
5
0
2
-
4
7
5
2
,
DOI
: 1
0
.
1
1
5
9
1
/ijeecs.v
3
9
.i
1
.
pp
60
3
-
61
3
603
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs.ia
esco
r
e.
co
m
Wo
rd embed
ding
and imba
la
nced l
ea
rning
impa
ct
o
n
I
ndo
nesia
n
Q
ura
n
o
ntolo
g
y
popu
la
tion
F
a
nd
y
Set
y
o
Ut
o
m
o
1
,
Yuli P
urwa
t
i
2
,
M
o
hd
Sa
nu
s
i A
zm
i
3
,
L
ulu
S
ha
f
ira
2
,
Nik
ma
h T
rina
rsih
2
1
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
U
n
i
v
e
r
s
i
t
a
s
A
mi
k
o
m P
u
r
w
o
k
e
r
t
o
,
P
u
r
w
o
k
e
r
t
o
,
I
n
d
o
n
e
s
i
a
2
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
mat
i
c
s
,
F
a
c
u
l
t
y
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
U
n
i
v
e
r
s
i
t
a
s
A
mi
k
o
m
P
u
r
w
o
k
e
r
t
o
,
P
u
r
w
o
k
e
r
t
o
,
I
n
d
o
n
e
si
a
3
F
a
c
u
l
t
y
o
f
I
n
f
o
r
m
a
t
i
o
n
a
n
d
C
o
mm
u
n
i
c
a
t
i
o
n
s T
e
c
h
n
o
l
o
g
y
,
U
n
i
v
e
r
s
i
t
i
T
e
k
n
i
k
a
l
M
a
l
a
y
si
a
M
e
l
a
k
a
,
M
e
l
a
k
a
,
M
a
l
a
y
s
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Oct
19
,
2
0
2
4
R
ev
is
ed
Mar
10
,
2
0
2
5
Acc
ep
ted
Mar
26
,
2
0
2
5
Th
is
re
se
a
rc
h
a
d
d
re
ss
e
s
li
m
it
a
t
io
n
s
i
n
Qu
ra
n
ic
in
sta
n
c
e
c
las
sifica
ti
o
n
,
e
x
c
e
p
ti
o
n
a
ll
y
h
ig
h
d
ime
n
sio
n
a
li
t
y
,
lac
k
o
f
se
m
a
n
ti
c
re
latio
n
s
h
ip
s
i
n
th
e
term
fre
q
u
e
n
c
y
-
i
n
v
e
rse
d
o
c
u
m
e
n
t
fre
q
u
e
n
c
y
(
TF
-
ID
F
)
tec
h
n
i
q
u
e
,
a
n
d
i
m
b
a
lan
c
e
d
d
a
ta
d
istri
b
u
t
io
n
,
w
h
ich
re
d
u
c
e
p
r
e
d
ictio
n
a
c
c
u
ra
c
y
f
o
r
m
i
n
o
ri
t
y
c
las
se
s.
Th
is
stu
d
y
i
n
v
e
sti
g
a
tes
th
e
imp
a
c
t
o
f
wo
r
d
e
m
b
e
d
d
i
n
g
a
n
d
imb
a
lan
c
e
lea
rn
in
g
tec
h
n
iq
u
e
s
o
n
in
sta
n
c
e
c
las
sifica
ti
o
n
fra
m
e
wo
rk
s
u
sin
g
I
n
d
o
n
e
sia
n
Qu
ra
n
tran
sla
ti
o
n
a
n
d
Tafs
ir
d
a
ta
se
ts
to
h
a
n
d
le
p
re
v
io
u
s
re
se
a
rc
h
li
m
it
a
ti
o
n
s.
F
o
u
r
c
las
sifica
ti
o
n
fra
m
e
wo
rk
s
w
e
re
b
u
il
t
a
n
d
e
v
a
lu
a
ted
u
sin
g
a
c
c
u
ra
c
y
a
n
d
h
a
m
m
in
g
l
o
ss
m
e
tri
c
s.
T
h
e
r
e
su
lt
s
sh
o
w
th
a
t
th
e
sy
n
th
e
ti
c
m
in
o
ri
ty
o
v
e
rsa
m
p
li
n
g
tec
h
n
i
q
u
e
(
S
M
OT
E
)
tec
h
n
iq
u
e
,
T
F
-
IDF
m
o
d
e
l,
a
n
d
lo
g
isti
c
re
g
re
ss
io
n
c
las
sifier
p
ro
v
i
d
e
th
e
b
e
st
a
c
c
u
ra
c
y
re
su
lt
s
o
f
6
2
.
7
4
%
a
n
d
a
h
a
m
m
in
g
lo
ss
sc
o
re
o
f
0
.
3
7
2
6
o
n
th
e
Qu
ra
ish
S
h
ih
a
b
Tafs
ir
d
a
tas
e
t.
Th
is
is
b
e
tt
e
r
th
a
n
th
e
p
e
rfo
rm
a
n
c
e
o
f
p
re
v
io
u
s
c
las
sifiers
b
a
c
k
p
ro
p
a
g
a
ti
o
n
n
e
u
ra
l
n
e
two
rk
(
B
P
NN
)
a
n
d
su
p
p
o
r
t
v
e
c
to
r
m
a
c
h
in
e
(
SV
M
)
u
se
d
i
n
t
h
e
p
re
v
i
o
u
s
fra
m
e
wo
rk
,
with
a
c
c
u
ra
c
ies
o
f
5
9
.
9
1
%
a
n
d
6
2
.
2
6
%
,
re
sp
e
c
ti
v
e
ly
.
Lo
g
isti
c
re
g
re
ss
io
n
c
a
n
a
lso
p
r
o
v
i
d
e
th
e
b
e
st
c
las
sifica
ti
o
n
re
su
lt
s
wit
h
a
n
a
c
c
u
ra
c
y
o
f
6
7
.
9
2
%
a
n
d
a
h
a
m
m
in
g
l
o
ss
o
f
0
.
3
2
0
8
u
si
n
g
th
e
p
re
v
i
o
u
s
fra
m
e
wo
rk
.
Th
e
se
re
su
lt
s
a
re
b
e
tt
e
r
t
h
a
n
t
h
e
p
e
rf
o
r
m
a
n
c
e
o
f
th
e
p
re
v
i
o
u
s
c
las
sifiers
BP
NN
a
n
d
S
VM
u
se
d
in
th
e
p
re
v
io
u
s
fra
m
e
wo
rk
,
wit
h
a
c
c
u
ra
c
ies
o
f
6
2
.
2
6
%
a
n
d
6
6
.
9
8
%
,
re
sp
e
c
ti
v
e
l
y
.
T
F
-
IDF
fe
a
tu
re
e
x
trac
ti
o
n
o
u
tp
e
rfo
rm
s
wo
rd
2
v
e
c
in
in
sta
n
c
e
c
las
sifica
ti
o
n
re
su
lt
s
d
u
e
to
it
s
su
p
e
ri
o
r
su
p
p
o
rt
u
n
d
e
r
li
m
it
e
d
d
a
tas
e
t
c
o
n
d
i
ti
o
n
s.
K
ey
w
o
r
d
s
:
I
n
d
o
n
esian
Qu
r
an
i
n
ter
p
r
etatio
n
Ma
ch
in
e
lear
n
in
g
On
to
lo
g
y
lear
n
in
g
Sm
o
te
W
o
r
d
2
v
ec
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
:
Yu
li Pu
r
wati
Dep
ar
tm
en
t o
f
I
n
f
o
r
m
atics,
Facu
lty
o
f
C
o
m
p
u
ter
Scien
ce
,
U
n
iv
er
s
itas
Am
ik
o
m
Pu
r
wo
k
e
r
to
5
3
1
2
7
Pu
r
wo
k
er
to
,
B
an
y
u
m
as,
I
n
d
o
n
esia
E
m
ail:
y
u
lip
u
r
wati@
am
ik
o
m
p
u
r
wo
k
er
to
.
ac
.
id
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
Qu
r
’
an
,
as
a
h
o
ly
b
o
o
k
,
c
o
n
tain
s
k
n
o
wled
g
e
an
d
s
cien
tific
f
ac
ts
.
Pre
v
io
u
s
r
esear
ch
h
a
s
en
co
d
ed
th
e
in
f
o
r
m
atio
n
f
o
u
n
d
in
th
e
Qu
r
an
in
to
an
o
n
to
lo
g
y
s
tr
u
ct
u
r
e.
Ou
r
liter
atu
r
e
r
esear
ch
in
d
icate
s
th
at
o
n
to
lo
g
y
d
ev
elo
p
m
e
n
t
ca
n
b
e
ac
h
iev
e
d
th
r
o
u
g
h
two
m
et
h
o
d
s
:
m
an
u
a
l
(
n
o
n
-
au
to
m
ate
d
)
an
d
au
to
m
atic.
T
h
is
au
to
m
ate
d
tech
n
iq
u
e
is
r
ef
er
r
ed
to
as
th
e
o
n
to
lo
g
y
p
o
p
u
latio
n
[
1
]
.
O
n
to
lo
g
y
p
o
p
u
latio
n
r
ef
e
r
s
to
ac
q
u
ir
in
g
k
n
o
wled
g
e
ab
o
u
t
c
o
n
ce
p
ts
,
r
elatio
n
s
,
an
d
in
s
tan
ce
s
f
r
o
m
te
x
t
wr
itten
in
n
atu
r
al
lan
g
u
ag
e
an
d
s
u
b
s
eq
u
en
tly
in
co
r
p
o
r
ati
n
g
th
is
k
n
o
wled
g
e
in
to
an
o
n
t
o
lo
g
y
[
2
]
-
[
5
]
.
T
h
e
Qu
r
an
o
n
to
lo
g
y
p
o
p
u
latio
n
ap
p
r
o
ac
h
ca
n
b
e
p
er
f
o
r
m
ed
u
s
in
g
s
ev
er
al
m
eth
o
d
s
:
r
u
le
-
b
ased
,
n
atu
r
al
lan
g
u
a
g
e
p
r
o
ce
s
s
in
g
(
NL
P)
,
s
tat
is
tic
s
/m
ac
h
in
e
lear
n
in
g
,
an
d
h
y
b
r
id
ap
p
r
o
ac
h
es
[
1
]
.
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.
3
9
,
No
.
1
,
Ju
ly
20
25
:
603
-
6
1
3
604
Sev
er
al
p
r
ev
io
u
s
r
esear
ch
er
s
h
av
e
co
n
d
u
cted
s
tu
d
ies
r
eg
ar
d
in
g
th
e
in
s
tan
ce
s
class
if
icati
o
n
f
o
r
t
h
e
Qu
r
’
an
b
ased
o
n
th
eir
th
em
at
ic
to
p
ics.
T
h
e
r
esear
ch
co
n
d
u
cted
b
y
[
6
]
-
[
9
]
f
o
c
u
s
es
o
n
class
if
y
in
g
in
s
tan
ce
s
with
th
e
E
n
g
lis
h
Qu
r
an
tr
a
n
s
latio
n
d
ataset.
T
h
e
tech
n
iq
u
es
em
p
lo
y
ed
f
o
r
f
ea
tu
r
e
ex
tr
ac
t
io
n
in
clu
d
e
b
ag
o
f
wo
r
d
s
(
B
o
W
)
an
d
ter
m
f
r
eq
u
e
n
cy
-
in
v
e
r
s
e
d
o
cu
m
e
n
t f
r
eq
u
e
n
cy
(TF
-
I
DF)
.
T
h
e
in
v
esti
g
atio
n
ca
r
r
ied
o
u
t b
y
[
9
]
em
p
lo
y
s
r
an
d
o
m
u
n
d
e
r
-
s
am
p
li
n
g
(
R
U
S)
an
d
s
y
n
th
etic
m
in
o
r
ity
o
v
er
s
am
p
lin
g
tech
n
iq
u
e
(
SMOT
E
)
to
ad
d
r
ess
d
ata
im
b
alan
ce
.
Fu
r
th
er
m
o
r
e,
th
e
r
esear
ch
co
n
d
u
cted
b
y
[
1
0
]
-
[
1
3
]
f
o
cu
s
es
o
n
class
if
y
in
g
in
s
tan
ce
s
in
th
e
Ar
ab
ic
Qu
r
an
d
ataset.
T
h
e
s
tu
d
y
[
1
0
]
u
s
es
th
e
d
if
f
u
s
io
n
f
r
ec
h
et
f
u
n
ctio
n
f
o
r
th
e
f
ea
tu
r
e
ex
tr
ac
tio
n
tech
n
iq
u
e
,
wh
ile
o
th
er
s
tu
d
ies
u
s
e
B
o
W
an
d
T
F
-
I
DF.
T
o
h
an
d
le
d
ata
im
b
alan
ce
in
th
e
s
tu
d
y
[
1
3
]
,
th
ey
u
s
e
SMOT
E
.
Sev
er
al
p
r
ev
io
u
s
r
esear
ch
er
s
h
av
e
r
esear
ch
e
d
th
e
in
s
tan
ce
s
class
if
icatio
n
in
th
e
I
n
d
o
n
esian
Qu
r
an
t
r
an
s
latio
n
d
ataset.
Stu
d
ies
co
n
d
u
cted
b
y
[
1
4
]
-
[
1
8
]
u
s
ed
th
e
T
F
-
I
DF
te
ch
n
iq
u
e
f
o
r
f
ea
tu
r
e
ex
tr
ac
tio
n
o
n
th
e
I
n
d
o
n
esian
Qu
r
an
tr
an
s
latio
n
with
s
in
g
le
-
l
ab
el
class
if
icatio
n
.
T
h
e
wo
r
k
p
er
f
o
r
m
ed
b
y
[
1
7
]
aim
s
to
ex
tr
ac
t
“
is
-
a
r
elati
o
n
s
”
b
etwe
en
class
es
an
d
in
s
tan
ce
s
b
y
class
if
y
in
g
in
s
tan
ce
s
ac
co
r
d
in
g
to
th
e
r
ef
er
en
ce
d
class
.
T
h
e
ev
alu
atio
n
o
f
th
e
in
s
t
an
ce
class
if
icatio
n
f
r
am
ewo
r
k
’
s
p
er
f
o
r
m
an
ce
r
ev
ea
ls
th
at
th
e
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
(
SVM)
,
em
p
lo
y
in
g
T
F
-
I
DF
an
d
s
tem
m
in
g
m
eth
o
d
s
,
attain
s
th
e
h
ig
h
est
c
lass
if
icatio
n
ac
cu
r
ac
y
o
f
7
0
.
7
5
%
o
n
th
e
I
n
d
o
n
esian
Qu
r
a
n
tr
an
s
latio
n
d
ataset
with
a
test
d
ata
r
atio
o
f
2
0
%.
T
h
e
s
u
b
s
eq
u
en
t
s
tu
d
y
b
y
[
1
8
]
f
o
cu
s
ed
o
n
en
h
an
cin
g
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
class
if
icatio
n
f
r
am
ewo
r
k
u
tili
ze
d
b
y
[
1
7
]
b
y
ap
p
ly
i
n
g
t
h
e
ch
i
-
s
q
u
ar
e
f
ea
t
u
r
e
s
elec
t
io
n
m
eth
o
d
to
m
in
im
ize
t
h
e
d
im
en
s
io
n
s
ize.
T
h
e
test
r
es
u
lts
in
d
icate
th
at
f
ea
t
u
r
e
s
el
ec
tio
n
m
eth
o
d
s
ca
n
im
p
r
o
v
e
th
e
p
r
ec
is
io
n
an
d
ac
cu
r
ac
y
o
f
i
n
s
tan
ce
class
if
ica
tio
n
o
u
tco
m
es wh
en
t
h
e
test
d
ata
s
ize
is
co
n
f
ig
u
r
ed
at
6
0
%.
T
h
e
SVM
class
if
ier
attain
ed
a
p
r
ec
i
s
io
n
o
f
6
4
.
3
6
%
wh
en
u
tili
ze
d
o
n
th
e
I
n
d
o
n
esian
T
af
s
ir
Al
-
Qu
r
an
d
ataset
s
o
u
r
ce
d
f
r
o
m
th
e
Min
is
tr
y
o
f
R
elig
io
n
o
f
t
h
e
R
e
p
u
b
lic
o
f
I
n
d
o
n
esia.
Fu
r
t
h
er
m
o
r
e,
t
h
e
b
ac
k
p
r
o
p
ag
atio
n
n
eu
r
al
n
etwo
r
k
(
B
PNN
)
class
if
ier
attain
ed
an
ac
cu
r
ac
y
o
f
6
3
.
0
9
%.
T
h
e
two
p
r
ev
i
o
u
s
s
tu
d
ies
in
[
1
7
]
,
[
1
8
]
em
p
lo
y
e
d
th
e
T
F
-
I
DF
ter
m
weig
h
tin
g
tech
n
iq
u
e
with
in
an
in
s
tan
ce
class
if
icatio
n
f
r
am
ewo
r
k
.
T
h
e
T
F
-
I
DF
ter
m
weig
h
tin
g
tech
n
iq
u
e
h
as
s
ev
er
al
lim
itatio
n
s
.
Firstl
y
,
it
is
v
u
ln
er
ab
le
to
th
e
is
s
u
e
o
f
lar
g
e
d
im
en
s
io
n
s
i
n
th
e
te
x
t
d
o
m
ain
,
ad
v
er
s
ely
af
f
ec
tin
g
clas
s
if
ier
s
’
p
er
f
o
r
m
an
ce
[
1
9
]
.
Ad
d
itio
n
ally
,
it
d
o
es
n
o
t
co
n
s
id
er
in
f
o
r
m
atio
n
ab
o
u
t
m
ea
n
in
g
,
m
em
b
e
r
s
h
ip
r
elatio
n
s
h
ip
s
,
o
r
s
em
an
tics
b
etwe
en
wo
r
d
s
/d
o
c
u
m
en
ts
in
th
e
d
ata
s
o
u
r
ce
[
2
0
]
-
[
2
2
]
.
Fu
r
th
er
,
th
is
m
eth
o
d
p
r
o
v
es
to
b
e
in
ef
f
icien
t
f
o
r
th
e
task
o
f
te
x
t
class
if
icatio
n
wh
en
d
ea
lin
g
with
i
m
b
alan
ce
d
d
ata
d
is
tr
ib
u
tio
n
[
2
3
]
.
Fu
r
th
er
m
o
r
e,
t
h
er
e
was
a
n
im
b
alan
ce
d
d
ata
d
is
tr
ib
u
tio
n
i
n
th
e
r
esear
ch
co
n
d
u
cted
b
y
[
1
7
]
,
[
1
8
]
.
B
o
th
s
tu
d
ies
p
r
o
v
id
e
th
r
ee
class
if
icatio
n
o
u
tp
u
t
tar
g
ets:
m
o
r
als,
Al
-
Qu
r
an
,
an
d
p
r
e
v
io
u
s
n
atio
n
s
.
Ne
v
er
th
eless
,
th
e
d
is
tr
ib
u
tio
n
o
f
d
ata
u
tili
ze
d
as
a
d
ataset
in
th
e
th
r
ee
class
es
is
im
b
alan
ce
d
.
T
h
e
m
o
r
als
class
h
as
2
1
8
d
ata,
t
h
e
Al
-
Qu
r
a
n
class
h
as
1
8
3
d
ata,
an
d
th
e
p
r
e
v
io
u
s
n
atio
n
s
class
h
as
1
2
7
d
ata.
T
h
is
will
lead
to
s
ig
n
if
ican
t
d
if
f
er
e
n
ce
s
in
tr
ain
in
g
an
d
test
d
ata
d
is
tr
ib
u
tio
n
in
ea
ch
class
.
Un
f
o
r
tu
n
ately
,
m
ac
h
in
e
-
lear
n
in
g
alg
o
r
ith
m
s
o
f
ten
s
h
o
w
in
ad
e
q
u
ate
r
esu
lts
wh
en
th
er
e
is
a
s
u
b
s
tan
tial
im
b
alan
c
e
in
class
o
cc
u
r
r
e
n
ce
s
.
T
h
e
p
r
esen
ce
o
f
class
im
b
alan
ce
ch
a
llen
g
es
s
u
p
er
v
is
ed
m
o
d
els
to
ac
cu
r
ately
ca
p
t
u
r
e
th
e
d
is
tr
ib
u
tio
n
p
r
o
p
er
ties
o
f
s
k
ewe
d
d
ata,
lead
in
g
to
r
ed
u
ce
d
p
r
ed
ictio
n
ac
cu
r
ac
y
f
o
r
th
e
m
in
o
r
ity
class
es
[
2
4
]
-
[
2
8
]
.
W
o
r
d
em
b
e
d
d
in
g
ef
f
ec
tiv
ely
o
v
er
co
m
es
th
e
co
n
s
tr
ain
ts
ass
o
ciate
d
with
T
F
-
I
DF.
W
o
r
d
e
m
b
ed
d
in
g
is
a
m
eth
o
d
u
tili
ze
d
in
NL
P
an
d
m
ac
h
in
e
lear
n
in
g
th
at
en
co
d
es
wo
r
d
s
as
d
en
s
e
v
ec
to
r
s
with
in
a
co
n
tin
u
o
u
s
v
ec
to
r
s
p
ac
e,
with
ea
ch
wo
r
d
ass
ig
n
ed
to
a
h
ig
h
-
d
im
en
s
io
n
al
v
ec
to
r
[
2
9
]
.
T
h
is
f
o
r
m
o
f
r
e
p
r
esen
tatio
n
ca
p
tu
r
es
th
e
s
em
an
tic
an
d
s
y
n
tactic
in
f
o
r
m
atio
n
o
f
wo
r
d
s
b
a
s
ed
o
n
th
e
co
n
tex
t
o
f
th
eir
u
s
e
f
r
o
m
lar
g
e
tex
tu
al
co
n
ten
t
[
3
0
]
,
[
3
1
]
.
Fu
r
th
er
m
o
r
e,
th
e
im
b
alan
ce
lear
n
in
g
tec
h
n
iq
u
e
ca
n
b
e
em
p
lo
y
e
d
to
a
d
d
r
ess
th
e
is
s
u
e
o
f
class
d
ata
im
b
alan
ce
[
2
4
]
,
[
3
2
]
,
[
3
3
]
.
T
h
e
r
e
ar
e
th
r
ee
ap
p
r
o
ac
h
es
in
im
b
alan
ce
lea
r
n
in
g
th
at
ca
n
b
e
u
s
ed
to
s
o
lv
e
im
b
alan
ce
d
ata
p
r
o
b
lem
s
:
d
ata
-
lev
el,
alg
o
r
ith
m
-
le
v
el,
an
d
h
y
b
r
i
d
ap
p
r
o
ac
h
es
[
3
4
]
,
[
3
5
]
.
T
h
is
r
esear
ch
f
o
cu
s
es
o
n
th
e
d
ata
-
lev
el
ap
p
r
o
ac
h
as
a
s
o
lu
tio
n
to
d
ata
im
b
alan
ce
.
T
h
is
s
tu
d
y
em
p
lo
y
s
an
d
ex
am
in
es
wo
r
d
em
b
ed
d
in
g
a
n
d
im
b
alan
ce
d
le
ar
n
in
g
to
m
itig
ate
th
e
s
h
o
r
tco
m
in
g
s
o
f
T
F
-
I
DF
an
d
d
ata
im
b
alan
ce
in
in
s
tan
ce
class
if
icatio
n
s
y
s
tem
s
,
n
o
tab
ly
u
tili
zin
g
th
e
I
n
d
o
n
esian
Qu
r
an
tr
an
s
latio
n
an
d
T
af
s
ir
d
ata
s
et
f
o
r
th
e
o
n
to
lo
g
y
p
o
p
u
latio
n
.
T
h
e
i
n
n
o
v
atio
n
r
es
id
es in
ap
p
ly
in
g
an
d
ex
am
in
in
g
th
ese
s
tr
ateg
ies to
ad
d
r
ess
b
o
th
ch
allen
g
es.
2.
M
E
T
H
O
D
T
h
is
s
ec
tio
n
is
s
tr
u
ctu
r
ed
as
f
o
llo
ws:
s
ec
tio
n
2
.
1
d
is
cu
s
s
es
ad
o
p
tin
g
th
e
f
r
am
ewo
r
k
u
s
ed
in
th
is
s
tu
d
y
.
Sectio
n
2
.
2
ex
p
lain
s
th
e
d
ataset
u
s
ed
in
th
is
r
esear
ch
.
Fin
ally
,
th
e
test
s
ce
n
ar
io
is
d
ef
in
ed
in
s
ec
tio
n
2
.
3
.
2
.
1
.
F
r
a
m
ewo
r
k
a
do
pte
d
I
n
th
is
s
tu
d
y
,
we
ad
o
p
t
th
e
in
s
tan
ce
class
if
icat
io
n
f
r
am
ewo
r
k
f
r
o
m
[
1
8
]
to
lab
el
ea
ch
v
e
r
s
e
o
f
th
e
I
n
d
o
n
esian
Qu
r
an
tr
a
n
s
latio
n
an
d
its
in
ter
p
r
etatio
n
in
t
o
a
s
in
g
le
th
em
atic
to
p
ic.
T
h
e
f
r
am
ewo
r
k
[
1
8
]
h
as
m
u
ltip
le
s
tag
es:
(
1
)
tex
t
p
r
ep
r
o
ce
s
s
in
g
:
n
u
m
b
er
an
d
p
u
n
ct
u
atio
n
r
e
m
o
v
al,
ca
s
e
f
o
ld
in
g
,
s
to
p
wo
r
d
r
em
o
v
al,
a
n
d
to
k
en
izatio
n
;
(
2
)
m
o
r
p
h
o
lo
g
ical
an
aly
s
is
:
s
tem
m
in
g
o
p
er
atio
n
;
(
3
)
f
ea
tu
r
e
ex
tr
ac
tio
n
;
(
4
)
f
ea
tu
r
e
s
elec
tio
n
;
an
d
(
5
)
i
n
s
tan
ce
cla
s
s
if
icatio
n
.
T
h
e
m
o
r
p
h
o
lo
g
ical
an
aly
s
is
tech
n
iq
u
e
(
s
tem
m
in
g
)
u
s
ed
in
th
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
Wo
r
d
emb
ed
d
in
g
a
n
d
imb
a
la
n
ce
d
lea
r
n
in
g
imp
a
ct
o
n
I
n
d
o
n
esia
n
…
(
F
a
n
d
y
S
ety
o
Uto
mo
)
605
is
th
e
s
am
e
as
th
e
tech
n
iq
u
e
ap
p
lied
b
y
[
1
8
]
u
s
in
g
th
e
Sas
tr
awi
s
tem
m
er
.
Oth
er
r
esear
ch
er
s
h
av
e
also
im
p
lem
en
ted
th
is
s
tem
m
er
,
s
u
ch
as
th
e
s
tu
d
y
co
n
d
u
cted
b
y
[
3
6
]
-
[
3
8
]
f
o
r
tex
t
p
r
o
ce
s
s
in
g
.
Fu
r
th
er
m
o
r
e,
th
is
s
tu
d
y
’
s
f
ea
tu
r
e
s
elec
tio
n
tech
n
iq
u
e
u
s
es
ch
i
-
s
q
u
ar
e
,
as im
p
le
m
en
ted
b
y
[
1
8
]
in
h
is
r
esear
ch
.
I
n
th
is
s
tu
d
y
,
we
u
s
e
w
o
r
d
2
v
e
c
to
im
p
lem
en
t th
e
wo
r
d
em
b
e
d
d
in
g
tech
n
iq
u
e
i
n
th
e
f
ea
tu
r
e
ex
tr
ac
tio
n
s
tag
e.
W
o
r
d
2
v
ec
is
a
n
e
u
r
al
n
etwo
r
k
-
d
r
iv
en
wo
r
d
em
b
e
d
d
in
g
m
eth
o
d
t
h
at
d
ep
icts
wo
r
d
s
in
a
c
o
n
tin
u
o
u
s
v
ec
to
r
s
p
ac
e,
ca
p
tu
r
i
n
g
b
o
t
h
s
em
an
tic
an
d
s
y
n
tactic
ass
o
ciat
io
n
s
.
T
h
is
r
en
d
er
s
i
t
v
er
y
ef
f
ic
ien
t
f
o
r
NL
P
task
s
an
d
tex
t f
ea
tu
r
e
ex
tr
ac
tio
n
ac
r
o
s
s
m
an
y
ap
p
licatio
n
s
[
3
9
]
-
[
4
1
]
.
C
o
n
v
e
n
tio
n
al
f
ea
tu
r
e
s
elec
tio
n
tech
n
iq
u
es,
lik
e
ch
i
-
s
q
u
ar
e,
in
f
o
r
m
atio
n
g
ain
,
an
d
d
o
cu
m
e
n
t
f
r
e
q
u
en
c
y
,
c
o
n
s
id
er
s
o
lely
th
e
f
r
eq
u
en
cy
o
f
f
ea
tu
r
e
o
cc
u
r
r
e
n
ce
s
wh
ile
n
eg
lectin
g
f
ea
tu
r
e
s
em
an
tics
an
d
p
a
rt
-
of
-
s
p
ee
ch
attr
ib
u
tes.
W
o
r
d
2
v
ec
m
o
d
els
g
en
er
ate
v
ec
to
r
r
ep
r
esen
tatio
n
s
o
f
wo
r
d
s
th
at
ca
p
tu
r
e
s
em
an
tic
m
ea
n
in
g
s
an
d
ar
e
b
en
ef
icial
f
o
r
n
u
m
er
o
u
s
NL
P
ta
s
k
s
[
4
2
]
,
[
4
3
]
.
B
ased
o
n
th
e
lim
itatio
n
s
o
f
tr
ad
itio
n
al
f
ea
tu
r
e
s
elec
tio
n
tech
n
iq
u
es,
th
e
in
s
tan
ce
class
if
icatio
n
f
r
am
ewo
r
k
ad
o
p
ted
in
th
is
s
tu
d
y
m
u
s
t
b
e
m
o
d
if
ied
.
Sectio
n
2
.
3
will
ex
p
lain
th
e
m
o
d
if
i
ca
tio
n
.
I
n
th
e
s
tu
d
y
[
1
8
]
,
th
e
y
u
s
ed
SVM
an
d
B
P
NN
clas
s
if
ier
s
f
o
r
t
ex
t
class
if
icatio
n
.
Ho
wev
er
,
in
th
is
s
tu
d
y
,
we
u
s
e
SVM
an
d
B
PNN,
an
d
also
ad
d
lo
g
is
tic
r
eg
r
ess
io
n
an
d
r
a
n
d
o
m
f
o
r
est
as c
lass
if
ier
s
.
2
.
2
.
Da
t
a
s
et
co
llect
i
o
n
T
h
e
r
esear
ch
d
ataset
was
co
m
p
iled
f
r
o
m
v
a
r
io
u
s
s
o
u
r
ce
s
,
s
u
m
m
ar
ized
in
T
ab
le
1
.
T
h
e
s
tu
d
y
u
s
ed
Qu
r
a
is
h
Sh
ih
ab
’
s
,
I
n
d
o
n
esian
Qu
r
an
tr
an
s
latio
n
,
an
d
t
h
e
Min
is
tr
y
o
f
R
elig
io
u
s
Af
f
air
s
’
T
af
s
ir
Qu
r
an
f
o
r
tr
ain
in
g
a
n
d
test
in
g
.
T
h
e
cla
s
s
if
icatio
n
tar
g
et
is
th
e
Qu
r
a
n
C
o
r
d
o
b
a
’
s
th
e
m
atic
s
u
b
ject
s
,
d
iv
id
ed
in
to
th
e
Qu
r
an
,
His
to
r
ical
Natio
n
s
,
a
n
d
Mo
r
ality
.
T
h
e
Kate
g
lo
r
o
o
t
wo
r
d
d
ictio
n
ar
y
is
s
im
u
ltan
eo
u
s
ly
em
p
l
o
y
ed
d
u
r
in
g
th
e
s
tem
m
in
g
p
r
o
ce
d
u
r
e
to
v
e
r
if
y
r
o
o
t
wo
r
d
s
.
T
h
e
t
ex
t
p
r
e
-
p
r
o
ce
s
s
in
g
p
h
ase
em
p
lo
y
s
th
e
I
n
d
o
n
esian
s
to
p
wo
r
d
lis
t
to
elim
in
ate
ter
m
s
th
at
ar
e
ir
r
elev
an
t
to
th
e
tex
t.
Up
o
n
ac
q
u
ir
in
g
th
e
d
ata
o
n
I
n
d
o
n
esian
Qu
r
an
tr
an
s
latio
n
s
an
d
T
af
s
ir
,
th
is
s
t
u
d
y
u
tili
ze
d
th
e
in
f
o
r
m
atio
n
t
o
co
n
s
tr
u
ct
a
c
o
r
p
u
s
b
ased
o
n
th
em
atic
s
u
b
jects.
T
ab
le
2
d
elin
ea
tes th
e
q
u
an
tity
o
f
Qu
r
a
n
ic
v
er
s
es p
er
tin
e
n
t to
th
e
th
em
atic
s
u
b
jects.
T
ab
le
1
.
Data
s
et
co
llectio
n
N
o
.
D
a
t
a
S
o
u
r
c
e
1
I
n
d
o
n
e
si
a
n
Q
u
r
a
n
t
r
a
n
sl
a
t
i
o
n
I
n
t
e
r
n
a
t
i
o
n
a
l
Q
u
r
a
n
i
c
p
r
o
j
e
c
t
:
T
a
n
z
i
l
(
h
t
t
p
:
/
/
t
a
n
z
i
l
.
n
e
t
)
2
Q
u
r
a
i
s
h
S
h
i
h
a
b
Ta
f
si
r
I
n
t
e
r
n
a
t
i
o
n
a
l
Q
u
r
a
n
i
c
p
r
o
j
e
c
t
:
T
a
n
z
i
l
(
h
t
t
p
:
/
/
t
a
n
z
i
l
.
n
e
t
)
3
Q
u
r
a
n
Ta
f
s
i
r
Th
e
M
i
n
i
s
t
r
y
o
f
R
e
l
i
g
i
o
u
s Af
f
a
i
r
s I
n
d
o
n
e
si
a
(
h
t
t
p
s
:
/
/
q
u
r
a
n
.
k
e
m
e
n
a
g
.
g
o
.
i
d
/
)
4
Th
e
m
a
t
i
c
su
b
j
e
c
t
s
Th
e
Q
u
r
a
n
C
o
r
d
o
b
a
t
h
e
ma
t
i
c
i
n
d
e
x
5
R
o
o
t
w
o
r
d
d
i
c
t
i
o
n
a
r
y
K
a
t
e
g
l
o
(
h
t
t
p
s
:
/
/
k
a
t
e
g
l
o
.
c
o
m
/
)
6
I
n
d
o
n
e
si
a
n
st
o
p
w
o
r
d
l
i
s
t
I
n
d
o
n
e
si
a
n
st
o
p
w
o
r
d
l
i
s
t
f
r
o
m T
a
l
a
[
4
4
]
T
ab
le
2
.
T
h
em
atic
s
u
b
jects a
n
d
n
u
m
b
er
o
f
Q
u
r
a
n
ic
v
er
s
es
I
D
.
Th
e
m
a
t
i
c
su
b
j
e
c
t
n
a
m
e
N
u
mb
e
r
o
f
Q
u
r
a
n
i
c
v
e
r
s
e
s
1
M
o
r
a
l
s
2
1
8
2
Al
-
Q
u
r
a
n
1
8
3
3
P
r
e
v
i
o
u
s
n
a
t
i
o
n
s
1
2
7
S
u
m
t
o
t
a
l
5
2
8
T
ab
le
2
illu
s
tr
ates th
at
th
is
s
tu
d
y
em
p
lo
y
s
5
2
8
Qu
r
’
an
ic
v
e
r
s
es
s
o
u
r
ce
d
f
r
o
m
th
e
I
n
d
o
n
esia
n
Min
is
tr
y
o
f
R
elig
io
u
s
Af
f
ai
r
s
,
alo
n
g
s
id
e
5
2
8
Qu
r
’
an
ic
v
er
s
es
f
r
o
m
Q
u
r
aish
Sh
ih
ab
,
an
d
5
2
8
tr
an
s
la
tio
n
s
o
f
th
e
Qu
r
’
an
in
I
n
d
o
n
esian
.
T
h
e
ch
ap
te
r
s
o
f
th
e
Qu
r
’
an
,
in
cl
u
d
in
g
Al
-
B
aq
ar
ah
,
Ali
I
m
r
a
n
,
A
n
-
Nis
a
’
,
A
l
-
An
’
am
,
Al
-
A
’
r
af
,
At
-
Ta
u
b
ah
,
An
-
Nah
l,
an
d
T
a
h
a,
ar
e
f
ea
tu
r
ed
as
p
ar
t
o
f
t
h
e
d
ataset
p
r
esen
ted
in
T
a
b
l
e
2
.
C
o
n
s
eq
u
en
tly
,
T
ab
le
3
d
elin
ea
tes
th
e
th
e
m
atic
s
u
b
jects
th
at
wer
e
em
p
lo
y
ed
to
g
en
er
ate
th
e
d
ataset,
th
e
n
u
m
b
er
o
f
v
er
s
es
with
in
ea
ch
s
u
r
ah
,
an
d
th
e
s
u
r
ah
s
o
f
th
e
Qu
r
’
an
.
T
h
i
s
r
esear
ch
u
tili
ze
d
th
e
ca
teg
o
r
izatio
n
o
f
Qu
r
an
ic
v
er
s
es
b
y
Al
-
Qu
r
an
C
o
r
d
o
b
a,
o
r
g
an
iz
in
g
th
em
in
t
o
a
co
h
esiv
e
th
em
atic
f
r
am
ewo
r
k
,
as illu
s
tr
ated
in
T
ab
le
3
.
T
ab
le
3
.
Su
r
a
h
,
n
u
m
b
er
o
f
v
er
s
es,
an
d
s
u
b
jects
S
u
r
a
h
n
a
me
M
o
r
a
l
s
Al
-
Q
u
r
a
n
P
r
e
v
.
n
a
t
i
o
n
s
To
t
a
l
Al
-
B
a
q
a
r
a
h
51
59
13
1
2
3
A
l
i
-
I
mr
a
n
40
29
28
97
An
-
N
i
sa
’
47
25
12
84
Al
-
An
’
am
13
20
10
43
Al
-
A
’
r
a
f
21
16
37
74
At
-
Ta
u
b
a
h
28
8
4
40
An
-
N
a
h
l
14
18
5
37
Ta
h
a
4
8
18
30
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.
3
9
,
No
.
1
,
Ju
ly
20
25
:
603
-
6
1
3
606
2
.
3
.
T
est
s
ce
na
rio
T
h
e
tr
ain
in
g
d
ata
s
ize
an
d
te
s
t
d
ata
s
ize
wer
e
6
0
%
an
d
4
0
%,
r
esp
ec
tiv
ely
,
in
t
h
is
in
v
esti
g
atio
n
.
T
h
e
d
ata
s
ize
o
f
ea
ch
th
e
m
atic
to
p
ic
ca
n
b
e
elu
cid
ate
d
as
f
o
ll
o
ws,
b
ased
o
n
t
h
e
4
0
%
test
d
ata
s
ize:
(
1
)
8
8
d
ata
f
o
r
th
e
m
o
r
al
to
p
ic;
(
2
)
7
3
d
at
a
f
o
r
th
e
Al
-
Qu
r
a
n
to
p
ic;
an
d
(
3
)
5
1
d
ata
f
o
r
t
h
e
to
p
ic
o
f
t
h
e
p
r
ev
io
u
s
n
atio
n
,
s
o
th
at
th
e
to
tal
tr
ain
in
g
d
ata
s
i
ze
is
2
1
2
d
ata.
Nex
t,
th
e
S
MO
T
E
tech
n
iq
u
e
is
im
p
lem
en
ted
in
o
u
r
s
tu
d
y
t
o
h
an
d
le
d
ata
im
b
ala
n
ce
.
W
e
u
s
e
a
m
o
d
el
tr
ain
ed
o
n
th
e
I
n
d
o
n
esian
W
ik
ip
ed
ia
c
o
r
p
u
s
as
a
s
o
u
r
ce
m
o
d
el
f
o
r
im
p
lem
en
tin
g
wo
r
d
em
b
e
d
d
in
g
u
s
in
g
th
e
wo
r
d
2
v
ec
tech
n
iq
u
e.
T
h
is
m
o
d
el
ca
n
b
e
d
o
wn
l
o
ad
ed
v
ia
th
e
Gith
u
b
web
s
ite
as
f
o
llo
ws:
h
ttp
s
:/
/g
it
h
u
b
.
co
m
/d
er
y
r
ah
m
a
n
/wo
r
d
2
v
ec
-
b
ah
asa
-
in
d
o
n
esia/tre
e/m
aster
.
E
ac
h
wo
r
d
will
b
e
r
ep
r
esen
ted
as a
3
0
0
-
d
im
en
s
i
o
n
al
v
ec
to
r
.
As
d
escr
ib
ed
in
s
ec
tio
n
2
.
1
,
th
e
lim
itatio
n
s
o
f
tr
ad
itio
n
al
f
ea
tu
r
e
s
elec
tio
n
tech
n
iq
u
es
to
h
an
d
le
f
ea
tu
r
e
e
x
tr
ac
tio
n
r
esu
lts
u
s
in
g
wo
r
d
2
v
ec
r
e
q
u
ir
e
m
o
d
if
icatio
n
s
to
th
e
ad
o
p
ted
i
n
s
tan
ce
class
if
icatio
n
f
r
am
ewo
r
k
.
T
h
is
r
esear
ch
in
v
esti
g
ates
th
e
im
p
ac
t
o
f
wo
r
d
em
b
ed
d
in
g
an
d
im
b
alan
ce
d
le
ar
n
in
g
o
n
in
s
tan
ce
s
class
if
icatio
n
f
r
am
ewo
r
k
s
wit
h
th
e
I
n
d
o
n
esian
Qu
r
an
tr
an
s
l
atio
n
d
ataset
f
o
r
th
e
o
n
to
lo
g
y
p
o
p
u
latio
n
.
B
ased
o
n
th
ese
co
n
d
itio
n
s
,
th
er
e
a
r
e
4
test
s
ce
n
ar
io
s
wh
ich
ca
n
b
e
ex
p
lain
ed
as f
o
llo
ws:
−
T
es
t
s
ce
n
ar
io
1
I
n
test
s
ce
n
ar
io
1
,
we
b
u
ild
a
f
r
am
ewo
r
k
f
o
r
class
if
y
in
g
in
s
tan
ce
s
f
r
o
m
r
esear
ch
[
1
8
]
.
W
e
n
am
e
it
f
r
am
ewo
r
k
1
.
T
h
e
te
x
t
p
r
e
-
p
r
o
ce
s
s
in
g
,
m
o
r
p
h
o
lo
g
ical
an
al
y
s
is
,
f
ea
tu
r
e
ex
tr
ac
tio
n
,
an
d
f
ea
tu
r
e
s
elec
tio
n
s
tag
e
u
s
e
th
e
s
am
e
tech
n
iq
u
es
as th
e
r
esear
ch
[
1
8
]
.
−
T
est
s
ce
n
ar
io
2
I
n
th
e
s
ec
o
n
d
test
s
ce
n
ar
io
,
we
m
o
d
if
ied
th
e
i
n
s
tan
ce
class
if
icatio
n
f
r
am
ewo
r
k
f
r
o
m
th
e
s
tu
d
y
[
1
8
]
.
T
h
e
m
o
d
if
icatio
n
was
m
ad
e
d
u
e
to
th
e
lim
itatio
n
s
o
f
tr
ad
iti
o
n
al
f
ea
tu
r
e
s
elec
tio
n
tech
n
iq
u
es
in
h
an
d
lin
g
th
e
r
esu
lts
o
f
wo
r
d
2
v
ec
f
ea
tu
r
e
ex
tr
ac
tio
n
.
T
h
e
r
esu
lts
o
f
th
e
f
r
am
ewo
r
k
m
o
d
if
icati
o
n
ar
e
n
am
ed
f
r
am
ewo
r
k
2
wh
ich
co
n
s
is
ts
o
f
s
ev
er
al
p
h
ases
:
(
i
)
tex
t
p
r
ep
r
o
ce
s
s
in
g
:
n
u
m
b
e
r
an
d
p
u
n
c
tu
atio
n
r
em
o
v
al,
ca
s
e
f
o
ld
in
g
,
s
to
p
wo
r
d
r
em
o
v
al,
an
d
to
k
en
izatio
n
;
(
ii)
m
o
r
p
h
o
lo
g
ical
an
aly
s
is
:
s
tem
m
in
g
o
p
er
atio
n
;
(
iii)
f
ea
tu
r
e
ex
tr
ac
tio
n
;
an
d
(
i
v
)
in
s
tan
ce
cl
ass
if
icatio
n
.
T
h
e
f
ea
tu
r
e
ex
tr
ac
tio
n
s
tag
e
u
s
e
s
th
e
wo
r
d
2
v
ec
tech
n
iq
u
e.
−
T
est
s
ce
n
ar
io
3
I
n
th
e
th
ir
d
test
s
ce
n
ar
io
,
w
e
ad
d
ed
an
im
b
alan
ce
lear
n
i
n
g
co
m
p
o
n
en
t
to
t
h
e
in
s
tan
ce
class
if
icatio
n
f
r
am
ewo
r
k
[
1
8
]
to
h
a
n
d
le
th
e
d
ata
im
b
alan
ce
f
o
r
ea
ch
d
ataset
’
s
tar
g
et
class
,
s
o
th
e
f
r
am
ewo
r
k
h
as
s
ev
er
al
wo
r
k
p
h
ases
:
(
i
)
tex
t
p
r
e
p
r
o
c
ess
in
g
:
n
u
m
b
er
an
d
p
u
n
ctu
ati
o
n
r
e
m
o
v
al,
ca
s
e
f
o
l
d
in
g
,
s
to
p
wo
r
d
r
em
o
v
al,
an
d
to
k
e
n
izatio
n
;
(
ii)
m
o
r
p
h
o
lo
g
ical
an
aly
s
is
:
s
tem
m
in
g
o
p
er
atio
n
;
(
iii)
im
b
ala
n
ce
lear
n
i
n
g
;
(
iv
)
f
ea
tu
r
e
ex
tr
ac
tio
n
;
(
v
)
f
ea
t
u
r
e
s
elec
tio
n
;
an
d
(
v
i)
in
s
tan
ce
class
if
icatio
n
.
T
h
is
wo
r
k
p
h
ase
is
ca
lled
f
r
am
ewo
r
k
3
.
W
e
ap
p
ly
th
e
SMOT
E
tech
n
iq
u
e
to
th
e
im
b
alan
ce
lear
n
in
g
co
m
p
o
n
en
t
an
d
th
e
T
F
-
I
D
F
tech
n
iq
u
e
f
o
r
f
ea
tu
r
e
ex
tr
ac
tio
n
.
−
T
est
s
ce
n
ar
io
4
Fin
ally
,
in
th
is
f
o
u
r
th
test
s
ce
n
ar
io
,
we
m
o
d
if
ie
d
th
e
i
n
s
tan
ce
class
if
icat
io
n
f
r
am
ewo
r
k
[
1
8
]
b
y
a
d
d
in
g
a
n
im
b
alan
ce
lear
n
in
g
co
m
p
o
n
e
n
t
u
s
in
g
th
e
SMOT
E
tech
n
i
q
u
e
an
d
p
er
f
o
r
m
in
g
f
ea
tu
r
e
ex
tr
ac
tio
n
u
s
in
g
wo
r
d
2
v
ec
.
W
e
d
id
n
o
t
u
s
e
th
e
tr
ad
itio
n
al
f
ea
tu
r
e
s
elec
tio
n
t
ec
h
n
iq
u
e
b
ec
au
s
e
it
is
lim
ited
in
h
an
d
lin
g
th
e
r
esu
lts
o
f
wo
r
d
2
v
ec
f
ea
tu
r
e
e
x
tr
ac
tio
n
.
T
h
is
m
o
d
if
icatio
n
r
esu
lts
,
wh
ich
we
n
a
m
ed
f
r
am
ewo
r
k
4
wh
ich
co
n
s
is
ts
o
f
s
ev
er
al
wo
r
k
s
tag
es:
(
i)
tex
t
p
r
ep
r
o
ce
s
s
in
g
:
n
u
m
b
er
an
d
p
u
n
ctu
atio
n
r
e
m
o
v
al,
ca
s
e
f
o
ld
in
g
,
s
to
p
wo
r
d
r
em
o
v
al,
an
d
to
k
e
n
izatio
n
;
(
ii)
m
o
r
p
h
o
lo
g
ical
an
aly
s
is
:
s
tem
m
in
g
o
p
er
ati
o
n
;
(
iii)
f
ea
tu
r
e
ex
tr
ac
tio
n
; (
iv
)
im
b
alan
ce
lear
n
in
g
; a
n
d
(
v
)
in
s
tan
ce
class
if
icatio
n
.
T
h
is
s
tu
d
y
u
s
es
ac
cu
r
ac
y
a
n
d
h
am
m
in
g
lo
s
s
m
etr
ics
to
ass
ess
th
e
ef
f
icac
y
o
f
th
e
in
s
tan
ce
class
if
icatio
n
s
y
s
tem
.
T
h
e
ac
c
u
r
ac
y
s
tatis
tic
is
th
e
p
r
o
p
o
r
tio
n
o
f
r
ea
l
o
u
tco
m
es
(
in
clu
d
in
g
tr
u
e
p
o
s
itiv
es
an
d
tr
u
e
n
eg
ativ
es)
r
elativ
e
to
t
h
e
to
tal
n
u
m
b
er
o
f
in
s
tan
ce
s
an
al
y
ze
d
.
I
t
is
a
f
u
n
d
am
en
tal
m
etr
ic
f
o
r
ev
alu
atin
g
a
class
if
ier
’
s
p
er
f
o
r
m
an
ce
,
clea
r
ly
in
d
icatin
g
th
e
m
o
d
el
’
s
o
v
er
all
ef
f
ec
tiv
en
ess
[
4
5
]
.
T
h
is
m
etr
ic
is
p
ar
ticu
lar
ly
b
en
ef
icial
in
b
alan
ce
d
d
atasets
,
wh
er
e
th
e
clas
s
es
ar
e
r
ep
r
e
s
en
ted
eq
u
ally
.
Ho
wev
er
,
it
m
ay
b
e
m
is
lead
in
g
wh
en
th
e
c
lass
d
is
tr
ib
u
tio
n
is
im
b
alan
ce
d
[
4
6
]
,
[
4
7
]
.
Fu
r
th
er
m
o
r
e,
th
e
h
a
m
m
in
g
lo
s
s
q
u
a
n
tifie
s
th
e
p
r
o
p
o
r
ti
o
n
o
f
in
co
r
r
ec
t
lab
els
p
r
ed
icte
d
b
y
a
class
if
ier
co
m
p
ar
ed
to
th
e
ac
tu
al
lab
els.
Sp
ec
if
ically
,
h
am
m
in
g
lo
s
s
is
d
ef
in
ed
as th
e
av
er
ag
e
n
u
m
b
e
r
o
f
m
is
class
if
ied
lab
els
p
er
in
s
tan
ce
[
4
8
]
,
[
4
9
]
.
A
lo
wer
h
a
m
m
in
g
lo
s
s
in
d
icate
s
im
p
r
o
v
e
d
p
er
f
o
r
m
a
n
ce
,
as it in
d
icate
s
a
r
ed
u
ctio
n
in
th
e
n
u
m
b
er
o
f
m
is
class
if
icatio
n
s
.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
is
s
ec
tio
n
is
o
r
g
an
ize
d
a
s
f
o
llo
ws:
s
ec
tio
n
3
.
1
ex
am
in
es
th
e
f
in
d
in
g
s
o
f
em
p
l
o
y
in
g
wo
r
d
em
b
ed
d
in
g
an
d
im
b
ala
n
ce
lear
n
in
g
in
s
id
e
th
e
in
s
tan
ce
class
if
icat
io
n
f
r
am
ewo
r
k
o
f
th
e
I
QT
d
ataset.
Su
b
s
eq
u
en
tly
,
s
ec
tio
n
3
.
2
a
n
al
y
ze
s
th
e
f
i
n
d
in
g
s
f
r
o
m
th
e
Qu
r
aish
Sh
ih
ab
d
ataset,
wh
ile
s
e
ctio
n
3
.
3
e
v
alu
ates
th
e
co
n
clu
s
io
n
s
o
f
th
e
Qu
r
an
T
af
s
ir
d
atase
t p
r
o
v
id
e
d
b
y
th
e
Min
is
tr
y
o
f
R
elig
io
u
s
Af
f
air
s
o
f
I
n
d
o
n
esia.
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
Wo
r
d
emb
ed
d
in
g
a
n
d
imb
a
la
n
ce
d
lea
r
n
in
g
imp
a
ct
o
n
I
n
d
o
n
esia
n
…
(
F
a
n
d
y
S
ety
o
Uto
mo
)
607
3
.
1
.
I
nv
estig
a
t
i
o
n r
esu
lt
s
o
n t
he
I
Q
T
da
t
a
s
et
Fig
u
r
e
1
illu
s
tr
ates
th
e
ev
alu
atio
n
r
esu
lts
o
f
th
e
o
v
er
all
f
r
am
ewo
r
k
b
ased
o
n
t
h
e
estab
lis
h
ed
test
s
ce
n
ar
io
s
,
u
tili
zin
g
ac
c
u
r
ac
y
m
ea
s
u
r
es.
R
ef
er
r
i
n
g
to
Fig
u
r
e
1
,
it
ca
n
b
e
co
n
clu
d
ed
th
at
th
e
in
s
tan
ce
class
if
icatio
n
f
r
am
ewo
r
k
f
r
o
m
r
esear
ch
[
1
8
]
with
th
e
SVM
class
if
ier
h
as
th
e
b
est
ac
cu
r
ac
y
co
m
p
ar
ed
to
o
th
er
f
r
am
ewo
r
k
s
,
with
6
4
.
6
2
%
ac
cu
r
ac
y
.
T
h
is
r
esu
lt
is
id
en
tica
l
to
th
eir
[
1
8
]
p
r
e
v
io
u
s
r
esea
r
ch
u
s
in
g
a
s
im
ilar
f
r
am
ewo
r
k
a
n
d
class
if
ier
,
wh
ich
also
h
ad
th
e
s
am
e
ac
cu
r
ac
y
r
esu
lt.
T
h
en
,
Fig
u
r
e
2
s
h
o
ws
th
e
ev
alu
atio
n
r
esu
lts
u
s
in
g
h
am
m
in
g
lo
s
s
.
R
ef
er
r
in
g
to
Fig
u
r
e
2
,
it
c
an
b
e
co
n
clu
d
e
d
th
at
th
e
in
s
tan
ce
class
if
icatio
n
f
r
am
ewo
r
k
f
r
o
m
r
esear
c
h
[
1
8
]
with
th
e
SVM
clas
s
if
ier
h
as
th
e
lo
west
h
am
m
in
g
lo
s
s
v
alu
e
o
f
0
.
3
5
3
8
co
m
p
ar
ed
to
o
th
e
r
f
r
a
m
ewo
r
k
s
.
Fig
u
r
e
1
.
Fra
m
ewo
r
k
p
er
f
o
r
m
an
ce
ev
alu
atio
n
with
ac
cu
r
ac
y
m
etr
ic
o
n
I
QT
d
ataset
Fig
u
r
e
2
.
Fra
m
ewo
r
k
p
er
f
o
r
m
an
ce
ev
alu
atio
n
with
h
am
m
in
g
lo
s
s
m
etr
ic
o
n
I
QT
d
ataset
B
ased
o
n
Fig
u
r
es
1
an
d
2
,
it
ca
n
b
e
ex
p
lain
ed
th
at
th
e
im
p
a
ct
o
f
ap
p
ly
in
g
t
h
e
SMOT
E
tech
n
iq
u
e
to
h
an
d
le
d
ata
im
b
alan
ce
,
to
g
et
h
er
with
T
F
-
I
DF
f
o
r
f
ea
tu
r
e
ex
tr
ac
tio
n
in
f
r
am
ewo
r
k
3
,
h
as
th
e
b
est
r
esu
lts
co
m
p
ar
ed
to
f
r
am
ewo
r
k
s
2
an
d
4
.
I
t
ca
n
b
e
c
o
n
clu
d
e
d
th
a
t
f
ea
tu
r
e
ex
tr
ac
tio
n
u
tili
zin
g
T
F
-
I
DF
h
as
a
m
o
r
e
f
av
o
r
a
b
le
im
p
ac
t
o
n
th
e
f
r
am
ewo
r
k
th
an
th
e
wo
r
d
2
v
ec
tec
h
n
iq
u
e,
p
ar
ticu
lar
ly
r
e
g
ar
d
i
n
g
th
e
ac
cu
r
ac
y
an
d
Ham
m
in
g
lo
s
s
ev
alu
atio
n
.
Fig
u
r
e
3
s
h
o
ws a
c
o
m
p
ar
is
o
n
b
et
wee
n
d
ata
b
ef
o
r
e
an
d
af
ter
S
MO
T
E
is
ap
p
lied
.
I
n
Fig
u
r
e
3
,
class
1
.
0
d
e
n
o
tes
th
e
m
o
r
al
class
,
class
2
.
0
r
ep
r
esen
ts
th
e
Al
-
Qu
r
an
class
,
an
d
class
3
.
0
p
er
tain
s
to
th
e
class
o
f
p
r
ev
io
u
s
n
atio
n
s
.
Fig
u
r
e
3
(
a)
illu
s
tr
ates
th
e
q
u
a
n
tity
o
f
tr
ai
n
in
g
d
at
a
allo
ca
ted
t
o
ea
c
h
tar
g
et
class
b
ef
o
r
e
th
e
ex
ec
u
ti
o
n
o
f
t
h
e
SMOT
E
o
p
er
atio
n
.
T
h
e
d
ataset
is
p
ar
titi
o
n
ed
in
to
6
0
%
f
o
r
tr
ain
in
g
p
u
r
p
o
s
es
an
d
4
0
%
d
esig
n
ated
f
o
r
test
in
g
.
T
h
e
tr
ain
in
g
d
ata
co
m
p
o
s
itio
n
f
o
r
ea
ch
tar
g
et
cl
ass
alig
n
s
with
th
e
to
tal
d
ata
p
r
esen
ted
in
T
ab
le
2
,
as
illu
s
tr
ated
in
Fig
u
r
e
3
(
a)
.
T
h
e
a
p
p
licatio
n
o
f
th
e
SMOT
E
tech
n
iq
u
e
ad
d
r
ess
es
th
e
im
b
alan
ce
in
tr
ain
in
g
d
ata
ac
r
o
s
s
class
es,
en
s
u
r
in
g
th
at
th
e
m
in
o
r
ity
class
h
as
an
eq
u
al
n
u
m
b
er
o
f
tr
ain
in
g
in
s
tan
ce
s
as th
e
m
a
jo
r
ity
class
,
to
talin
g
1
3
0
in
s
tan
ce
s
,
as illu
s
tr
ated
in
Fig
u
r
e
3
(
b
)
.
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.
3
9
,
No
.
1
,
Ju
ly
20
25
:
603
-
6
1
3
608
(
a)
(
b
)
Fi
g
u
r
e
3
.
C
o
m
p
a
r
is
o
n
o
f
d
ata
am
o
u
n
t: (
a
)
b
ef
o
r
e
SMOT
E
; a
n
d
(
b
)
af
ter
SMOT
E
3
.
2
.
I
nv
estig
a
t
io
n r
esu
lt
s
o
n t
he
Q
ura
is
h Sh
iha
b da
t
a
s
et
T
h
e
Qu
r
aish
Sh
ih
ab
d
ataset
s
h
o
ws
d
if
f
er
en
t
ev
al
u
atio
n
r
esu
lts
.
Fig
u
r
e
4
d
escr
ib
es
th
e
o
v
er
all
ev
alu
atio
n
o
f
th
e
f
r
am
ew
o
r
k
an
d
class
if
ier
u
s
in
g
th
e
ac
c
u
r
ac
y
m
etr
ic.
Acc
o
r
d
in
g
to
Fig
u
r
e
4
,
it
ca
n
b
e
co
n
clu
d
e
d
th
at
th
e
i
n
s
tan
ce
c
lass
if
icatio
n
f
r
am
ewo
r
k
3
with
th
e
lo
g
is
tic
r
eg
r
ess
io
n
class
if
ier
h
as
th
e
b
est
ac
cu
r
ac
y
co
m
p
ar
ed
to
o
th
e
r
f
r
am
ewo
r
k
s
,
with
6
2
.
7
4
%
ac
cu
r
ac
y
.
T
h
is
r
esu
lt
is
b
etter
th
an
th
e
in
s
tan
ce
class
if
icatio
n
f
r
am
ewo
r
k
1
f
r
o
m
r
esear
ch
[
1
8
]
u
s
in
g
B
PN
N
an
d
SVM
cla
s
s
if
ier
s
,
wh
ich
h
ad
ac
cu
r
ac
ies
o
f
5
9
.
9
1
% a
n
d
6
2
.
2
6
%,
r
esp
ec
tiv
ely
.
T
h
en
,
Fig
u
r
e
5
s
h
o
ws th
e
ev
alu
atio
n
r
esu
lts
u
s
in
g
h
am
m
in
g
lo
s
s
.
Fig
u
r
e
4
.
Fra
m
ewo
r
k
p
er
f
o
r
m
an
ce
ev
alu
atio
n
with
ac
cu
r
ac
y
m
etr
ic
o
n
Qu
r
aish
Sh
ih
ab
d
ataset
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
Wo
r
d
emb
ed
d
in
g
a
n
d
imb
a
la
n
ce
d
lea
r
n
in
g
imp
a
ct
o
n
I
n
d
o
n
esia
n
…
(
F
a
n
d
y
S
ety
o
Uto
mo
)
609
R
ef
er
r
in
g
to
Fig
u
r
e
5
,
it
ca
n
b
e
co
n
cl
u
d
ed
t
h
at
th
e
in
s
tan
ce
class
if
icatio
n
f
r
am
ewo
r
k
3
with
th
e
lo
g
is
tic
r
eg
r
ess
io
n
class
if
ier
h
as
th
e
lo
west
h
am
m
in
g
lo
s
s
v
alu
e
o
f
0
.
3
7
2
6
co
m
p
a
r
ed
t
o
o
th
er
f
r
a
m
ewo
r
k
s
.
B
ased
o
n
Fig
u
r
es
4
an
d
5
,
it
ca
n
b
e
e
x
p
lain
ed
th
at
th
e
im
p
ac
t
o
f
ap
p
ly
in
g
th
e
SMOT
E
t
ec
h
n
iq
u
e
to
h
a
n
d
le
d
ata
im
b
alan
ce
,
to
g
eth
er
with
T
F
-
I
DF
f
o
r
f
ea
tu
r
e
e
x
tr
ac
tio
n
in
f
r
am
ewo
r
k
3
,
h
as
th
e
b
est
r
esu
lts
co
m
p
ar
ed
to
o
th
er
f
r
am
ewo
r
k
s
.
I
t
ca
n
b
e
c
o
n
clu
d
e
d
th
at
f
ea
tu
r
e
ex
tr
ac
ti
o
n
u
tili
zin
g
T
F
-
I
DF
h
as
a
m
o
r
e
f
av
o
r
ab
le
im
p
ac
t
th
an
th
e
wo
r
d
2
v
ec
tech
n
iq
u
e
with
in
th
e
f
r
am
ewo
r
k
,
p
ar
tic
u
lar
ly
r
e
g
ar
d
in
g
th
e
ac
cu
r
ac
y
an
d
h
am
m
in
g
lo
s
s
ev
alu
atio
n
.
Fig
u
r
e
5
.
Fra
m
ewo
r
k
p
er
f
o
r
m
an
ce
ev
alu
atio
n
with
h
am
m
in
g
lo
s
s
m
etr
ic
o
n
th
e
Q
u
r
aish
Sh
ih
ab
d
ataset
3
.
3
.
I
nv
estig
a
t
i
o
n r
esu
lt
s
o
n t
he
Q
ura
n T
a
f
s
ir
da
t
a
s
et
f
ro
m
M
ini
s
t
ry
o
f
Relig
io
us
Af
f
a
irs I
n
do
nes
ia
Fig
u
r
e
6
illu
s
tr
ates
th
e
ev
alu
atio
n
o
u
tco
m
es
o
f
th
e
c
o
m
p
r
eh
en
s
iv
e
f
r
am
ewo
r
k
u
tili
zin
g
ac
cu
r
ac
y
m
etr
ics
d
er
iv
ed
f
r
o
m
th
e
estab
lis
h
e
d
test
s
ce
n
ar
io
s
.
R
ef
er
r
in
g
to
Fig
u
r
e
6
,
it
ca
n
b
e
co
n
clu
d
e
d
th
at
th
e
in
s
tan
ce
class
if
icatio
n
f
r
am
ewo
r
k
f
r
o
m
r
esear
ch
[
1
8
]
wit
h
th
e
lo
g
is
tic
r
eg
r
ess
io
n
class
if
ier
h
as
th
e
b
est
ac
cu
r
ac
y
co
m
p
ar
ed
t
o
o
th
er
f
r
am
ewo
r
k
s
.
T
h
is
class
if
ier
p
er
f
o
r
m
s
b
etter
th
an
th
e
SVM
an
d
B
PNN
p
r
ev
io
u
s
ly
u
s
e
d
b
y
[
1
8
]
in
in
s
tan
ce
s
clas
s
if
icatio
n
f
r
am
ewo
r
k
1
with
an
ac
cu
r
ac
y
o
f
6
2
.
2
6
% a
n
d
6
6
.
9
8
%,
r
esp
ec
tiv
ely
.
Fig
u
r
e
6
.
Fra
m
ewo
r
k
p
er
f
o
r
m
an
ce
ev
alu
atio
n
with
ac
cu
r
ac
y
m
etr
ic
o
n
th
e
Qu
r
an
T
af
s
ir
d
a
taset
Mo
r
eo
v
er
,
Fig
u
r
e
7
s
h
o
ws
th
e
ev
alu
atio
n
r
esu
lts
u
s
in
g
h
am
m
in
g
l
o
s
s
.
B
ased
o
n
Fig
u
r
es
6
an
d
7
,
th
e
im
p
ac
t
o
f
ap
p
l
y
in
g
t
h
e
SM
OT
E
tech
n
iq
u
e
to
h
an
d
le
d
a
ta
im
b
alan
ce
,
t
o
g
eth
er
with
T
F
-
I
DF
f
o
r
f
ea
tu
r
e
ex
tr
ac
tio
n
in
f
r
am
ewo
r
k
3
,
is
th
e
b
est
co
m
p
ar
ed
t
o
f
r
a
m
e
wo
r
k
s
2
an
d
4
.
T
h
e
f
in
d
in
g
s
in
d
icate
th
at
f
ea
tu
r
e
ex
tr
ac
tio
n
t
h
r
o
u
g
h
T
F
-
I
DF
d
em
o
n
s
tr
ates
a
s
u
p
e
r
io
r
ef
f
ec
t
co
m
p
ar
ed
to
th
e
wo
r
d
2
v
ec
tech
n
iq
u
e
with
in
t
h
e
f
r
am
ewo
r
k
,
p
ar
ticu
lar
l
y
r
eg
a
r
d
in
g
ac
cu
r
ac
y
an
d
Ham
m
in
g
l
o
s
s
ev
alu
atio
n
.
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.
3
9
,
No
.
1
,
Ju
ly
20
25
:
603
-
6
1
3
610
Fig
u
r
e
7
.
Fra
m
ewo
r
k
p
er
f
o
r
m
an
ce
ev
alu
atio
n
with
h
am
m
in
g
lo
s
s
m
etr
ic
o
n
th
e
Q
u
r
an
T
a
f
s
ir
d
ataset
4.
CO
NCLU
SI
O
N
T
h
e
ev
alu
atio
n
r
esu
lts
o
f
all
f
r
am
ewo
r
k
s
an
d
class
if
ier
s
,
ass
es
s
ed
th
r
o
u
g
h
ac
cu
r
ac
y
an
d
h
am
m
in
g
lo
s
s
m
etr
ics,
in
d
icate
th
at
th
e
im
p
lem
en
tatio
n
o
f
th
e
SMOT
E
tech
n
iq
u
e
f
o
r
im
b
alan
ce
lea
r
n
in
g
i
n
f
r
a
m
ewo
r
k
1
,
co
m
b
in
e
d
with
th
e
T
F
-
I
DF
m
o
d
el
f
o
r
f
ea
tu
r
e
ex
tr
ac
t
io
n
a
n
d
th
e
lo
g
is
tic
r
eg
r
ess
io
n
class
if
ier
,
ac
h
iev
ed
th
e
h
ig
h
est
ac
cu
r
ac
y
o
f
6
2
.
7
4
%
a
n
d
a
h
am
m
in
g
lo
s
s
s
co
r
e
o
f
0
.
3
7
2
6
o
n
th
e
Qu
r
aish
Sh
ih
ab
T
af
s
ir
d
ataset.
T
h
is
o
u
tco
m
e
s
u
r
p
ass
es
th
e
in
s
tan
ce
class
if
icatio
n
f
r
am
ewo
r
k
1
f
r
o
m
th
e
p
r
ev
io
u
s
s
tu
d
y
,
u
tili
zin
g
B
PNN
an
d
SVM
clas
s
if
ier
s
,
wh
ich
ac
h
i
ev
ed
5
9
.
9
1
%
an
d
6
2
.
2
6
%
a
cc
u
r
ac
y
.
L
o
g
is
tic
r
eg
r
ess
io
n
d
em
o
n
s
tr
ates
th
e
ca
p
ab
ilit
y
to
y
ield
o
p
tim
al
cla
s
s
if
icatio
n
o
u
tco
m
es,
ac
h
iev
in
g
an
ac
c
u
r
ac
y
o
f
6
7
.
9
2
%
an
d
a
h
am
m
in
g
lo
s
s
o
f
0
.
3
2
0
8
in
f
r
am
ew
o
r
k
1
.
T
h
e
r
esu
lts
s
u
r
p
ass
t
h
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
ea
r
lier
class
if
ier
s
,
B
PNN
an
d
SVM,
u
tili
ze
d
in
f
r
a
m
ewo
r
k
1
f
r
o
m
a
p
r
e
v
io
u
s
s
tu
d
y
,
wh
ich
ac
h
iev
ed
ac
cu
r
ac
ies
o
f
6
2
.
2
6
%
an
d
6
6
.
9
8
%,
r
esp
ec
tiv
ely
.
Ad
d
itio
n
ally
,
it
ca
n
b
e
co
n
clu
d
e
d
th
at
f
ea
tu
r
e
ex
tr
ac
tio
n
th
r
o
u
g
h
T
F
-
I
DF
p
r
o
v
id
es
a
m
o
r
e
s
ig
n
if
ican
t
co
n
tr
ib
u
ti
o
n
co
m
p
ar
ed
to
wo
r
d
2
v
ec
in
en
h
a
n
cin
g
th
e
o
u
tc
o
m
es
o
f
in
s
tan
ce
class
if
icatio
n
,
as
ev
id
en
ce
d
b
y
th
e
p
er
f
o
r
m
a
n
ce
o
f
in
s
tan
ce
class
if
icatio
n
f
r
am
ewo
r
k
s
1
an
d
3
.
I
n
th
e
o
r
y
,
wo
r
d
2
v
ec
is
a
wo
r
d
em
b
ed
d
in
g
tech
n
iq
u
e
th
at
p
r
esen
ts
ce
r
tain
ad
v
an
t
ag
es
o
v
er
th
e
T
F
-
I
DF
f
ea
tu
r
e
ex
t
r
ac
tio
n
m
o
d
el.
Ou
r
ex
p
er
im
en
ts
in
d
icate
t
h
at
th
e
T
F
-
I
DF
tech
n
iq
u
e
o
f
f
e
r
s
s
u
p
er
io
r
s
u
p
p
o
r
t
c
o
m
p
a
r
ed
t
o
wo
r
d
2
v
ec
wh
e
n
class
if
y
in
g
in
s
tan
ce
s
with
lim
i
ted
d
ataset
co
n
d
itio
n
s
.
ACK
NO
WL
E
DG
E
M
E
NT
S
T
h
e
au
th
o
r
s
ex
p
r
ess
th
eir
g
r
a
titu
d
e
to
Un
iv
er
s
itas
Am
ik
o
m
Pu
r
wo
k
er
to
f
o
r
th
e
f
in
a
n
ci
al
s
u
p
p
o
r
t
ex
ten
d
ed
t
o
o
u
r
r
esear
ch
in
2
0
2
4
,
as
o
u
tlin
ed
i
n
d
ec
r
ee
n
u
m
b
er
0
4
6
/AMI
KOM
PW
T
/
P/1
1
/VI
I
/2
0
2
4
.
W
e
wo
u
ld
also
lik
e
to
e
x
p
r
ess
o
u
r
g
r
atitu
d
e
t
o
th
e
Am
ik
o
m
P
u
r
wo
k
er
to
I
n
tellig
en
t
Sy
s
tem
(
AI
-
SYS)
r
esear
ch
g
r
o
u
p
f
o
r
th
eir
s
u
p
p
o
r
t in
ca
r
r
y
in
g
o
u
t th
is
in
v
esti
g
atio
n
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
T
h
is
r
esear
ch
was
f
u
n
d
e
d
b
y
Un
iv
er
s
itas
Am
ik
o
m
Pu
r
w
o
k
er
to
in
2
0
2
4
with
th
e
d
ec
is
io
n
letter
n
u
m
b
er
0
4
6
/AMI
KOM
PW
T
/
P/1
1
/VI
I
/2
0
2
4
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
Fan
d
y
Sety
o
Uto
m
o
✓
✓
✓
✓
✓
✓
✓
Yu
li Pu
r
wati
✓
✓
✓
✓
✓
✓
Mo
h
d
San
u
s
i A
zm
i
✓
✓
✓
✓
✓
L
u
lu
Sh
af
ir
a
✓
✓
✓
✓
✓
✓
Nik
m
ah
T
r
in
ar
s
ih
✓
✓
✓
✓
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
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
Wo
r
d
emb
ed
d
in
g
a
n
d
imb
a
la
n
ce
d
lea
r
n
in
g
imp
a
ct
o
n
I
n
d
o
n
esia
n
…
(
F
a
n
d
y
S
ety
o
Uto
mo
)
611
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
Au
th
o
r
s
s
tate
n
o
co
n
f
lict o
f
in
t
er
est.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
au
th
o
r
s
co
n
f
ir
m
th
at
th
e
d
ata
s
u
p
p
o
r
tin
g
th
e
f
in
d
in
g
s
o
f
th
is
s
tu
d
y
ar
e
av
ailab
le
with
in
th
e
ar
ticle
an
d
its
s
u
p
p
lem
en
tar
y
m
ater
ia
ls
.
RE
F
E
R
E
NC
E
S
[
1
]
N
.
S
u
r
y
a
n
a
,
F
.
S
.
U
t
o
mo
,
a
n
d
M
.
S
.
A
z
mi
,
“
Q
u
r
a
n
o
n
t
o
l
o
g
y
:
r
e
v
i
e
w
o
n
r
e
c
e
n
t
d
e
v
e
l
o
p
me
n
t
a
n
d
o
p
e
n
r
e
se
a
r
c
h
i
ssu
e
s
,
”
J
o
u
rn
a
l
o
f
T
h
e
o
re
t
i
c
a
l
a
n
d
Ap
p
l
i
e
d
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
9
6
,
n
o
.
3
,
p
p
.
5
6
8
–
5
8
1
,
2
0
1
8
.
[
2
]
P
.
C
i
mi
a
n
o
,
O
n
t
o
l
o
g
y
l
e
a
r
n
i
n
g
a
n
d
p
o
p
u
l
a
t
i
o
n
f
r
o
m
t
e
x
t
:
A
l
g
o
r
i
t
h
m
s,
e
v
a
l
u
a
t
i
o
n
a
n
d
a
p
p
l
i
c
a
t
i
o
n
s
.
S
p
r
i
n
g
e
r
U
S
,
2
0
0
6
.
[
3
]
R
.
W
i
t
t
e
,
R
.
K
r
e
st
e
l
,
T
.
K
a
p
p
l
e
r
,
a
n
d
P
.
C
.
L
o
c
k
e
m
a
n
n
,
“
C
o
n
v
e
r
t
i
n
g
a
h
i
st
o
r
i
c
a
l
a
r
c
h
i
t
e
c
t
u
r
e
e
n
c
y
c
l
o
p
e
d
i
a
i
n
t
o
a
s
e
ma
n
t
i
c
k
n
o
w
l
e
d
g
e
b
a
se
,
”
I
E
EE
I
n
t
e
l
l
i
g
e
n
t
S
y
st
e
m
s
,
v
o
l
.
2
5
,
n
o
.
1
,
p
p
.
5
8
–
6
6
,
J
a
n
.
2
0
1
0
,
d
o
i
:
1
0
.
1
1
0
9
/
M
I
S
.
2
0
1
0
.
1
7
.
[
4
]
J.
A
.
R
e
y
e
s
a
n
d
A
.
M
o
n
t
e
s,
“
Le
a
r
n
i
n
g
d
i
s
c
o
u
r
se
r
e
l
a
t
i
o
n
s
f
r
o
m
n
e
w
s
r
e
p
o
r
t
s:
a
n
e
v
e
n
t
-
d
r
i
v
e
n
a
p
p
r
o
a
c
h
,
”
I
EE
E
L
a
t
i
n
Am
e
r
i
c
a
T
ra
n
s
a
c
t
i
o
n
s
,
v
o
l
.
1
4
,
n
o
.
1
,
p
p
.
3
5
6
–
3
6
3
,
Ja
n
.
2
0
1
6
,
d
o
i
:
1
0
.
1
1
0
9
/
T
LA
.
2
0
1
6
.
7
4
3
0
1
0
1
.
[
5
]
J.
A
.
R
e
y
e
s
-
O
r
t
i
z
,
M
.
B
r
a
v
o
,
a
n
d
H
.
P
a
b
l
o
,
“
W
e
b
ser
v
i
c
e
s
o
n
t
o
l
o
g
y
p
o
p
u
l
a
t
i
o
n
t
h
r
o
u
g
h
t
e
x
t
c
l
a
ssi
f
i
c
a
t
i
o
n
,
”
i
n
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
2
0
1
6
Fe
d
e
r
a
t
e
d
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
I
n
f
o
rm
a
t
i
o
n
S
y
st
e
m
s,
F
e
d
C
S
I
S
2
0
1
6
,
O
c
t
.
2
0
1
6
,
p
p
.
4
9
1
–
4
9
5
,
d
o
i
:
1
0
.
1
5
4
3
9
/
2
0
1
6
F
3
3
2
.
[
6
]
A
.
O
.
A
d
e
l
e
k
e
,
N
.
A
.
S
a
ms
u
d
i
n
,
A
.
M
u
s
t
a
p
h
a
,
a
n
d
N
.
M
.
N
a
w
i
,
“
A
g
r
o
u
p
-
b
a
se
d
f
e
a
t
u
r
e
sel
e
c
t
i
o
n
a
p
p
r
o
a
c
h
t
o
i
m
p
r
o
v
e
c
l
a
ss
i
f
i
c
a
t
i
o
n
o
f
H
o
l
y
Q
u
r
a
n
v
e
r
ses
,
”
i
n
A
d
v
a
n
c
e
s i
n
I
n
t
e
l
l
i
g
e
n
t
S
y
st
e
m
s
a
n
d
C
o
m
p
u
t
i
n
g
,
v
o
l
.
7
0
0
,
2
0
1
8
,
p
p
.
2
8
2
–
2
9
7
.
[
7
]
G
.
I
.
U
l
u
mu
d
i
n
,
A
.
A
d
i
w
i
j
a
y
a
,
a
n
d
M
.
S
.
M
u
b
a
r
o
k
,
“
A
m
u
l
t
i
l
a
b
e
l
c
l
a
ss
i
f
i
c
a
t
i
o
n
o
n
t
o
p
i
c
s
o
f
q
u
r
’
a
n
i
c
v
e
r
se
s
i
n
E
n
g
l
i
s
h
t
r
a
n
s
l
a
t
i
o
n
u
si
n
g
K
-
N
e
a
r
e
st
N
e
i
g
h
b
o
r
met
h
o
d
w
i
t
h
W
e
i
g
h
t
e
d
TF
-
I
D
F
,
”
J
o
u
rn
a
l
o
f
Ph
y
si
c
s:
C
o
n
f
e
re
n
c
e
S
e
ri
e
s
,
v
o
l
.
1
1
9
2
,
n
o
.
1
,
p
.
0
1
2
0
2
6
,
M
a
r
.
2
0
1
9
,
d
o
i
:
1
0
.
1
0
8
8
/
1
7
4
2
-
6
5
9
6
/
1
1
9
2
/
1
/
0
1
2
0
2
6
.
[
8
]
R
.
A
.
P
a
n
e
,
M
.
S
.
M
u
b
a
r
o
k
,
N
.
S
.
H
u
d
a
,
a
n
d
A
d
i
w
i
j
a
y
a
,
“
A
mu
l
t
i
-
l
a
b
l
e
c
l
a
ss
i
f
i
c
a
t
i
o
n
o
n
t
o
p
i
c
s
o
f
Q
u
r
a
n
i
c
v
e
r
ses
i
n
E
n
g
l
i
sh
t
r
a
n
s
l
a
t
i
o
n
u
si
n
g
mu
l
t
i
n
o
m
i
a
l
n
a
i
v
e
b
a
y
e
s,
”
i
n
2
0
1
8
6
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
I
n
f
o
rm
a
t
i
o
n
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
I
C
o
I
C
T
2
0
1
8
,
M
a
y
2
0
1
8
,
p
p
.
4
8
1
–
4
8
4
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
o
I
C
T.
2
0
1
8
.
8
5
2
8
7
7
7
.
[
9
]
N
.
S
.
H
u
d
a
,
M
.
S
.
M
u
b
a
r
o
k
,
a
n
d
A
d
i
w
i
j
a
y
a
,
“
A
mu
l
t
i
-
l
a
b
e
l
c
l
a
ssi
f
i
c
a
t
i
o
n
o
n
t
o
p
i
c
s
o
f
q
u
r
a
n
i
c
v
e
r
ses
(
e
n
g
l
i
s
h
t
r
a
n
sl
a
t
i
o
n
)
u
si
n
g
b
a
c
k
p
r
o
p
a
g
a
t
i
o
n
n
e
u
r
a
l
n
e
t
w
o
r
k
w
i
t
h
st
o
c
h
a
st
i
c
g
r
a
d
i
e
n
t
d
e
s
c
e
n
t
a
n
d
a
d
a
m
o
p
t
i
m
i
z
e
r
,
”
i
n
2
0
1
9
7
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
I
n
f
o
rm
a
t
i
o
n
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
I
C
o
I
C
T
2
0
1
9
,
Ju
l
.
2
0
1
9
,
p
p
.
1
–
5
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
o
I
C
T.
2
0
1
9
.
8
8
3
5
3
6
2
.
[
1
0
]
M
.
E
.
A
k
t
a
s
a
n
d
E
.
A
k
b
a
s,
“
Te
x
t
c
l
a
s
si
f
i
c
a
t
i
o
n
v
i
a
n
e
t
w
o
r
k
t
o
p
o
l
o
g
y
:
a
c
a
s
e
st
u
d
y
o
n
t
h
e
h
o
l
y
q
u
r
a
n
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
-
1
8
t
h
I
EE
E
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
I
C
MLA
2
0
1
9
,
D
e
c
.
2
0
1
9
,
p
p
.
1
5
5
7
–
1
5
6
2
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
M
LA
.
2
0
1
9
.
0
0
2
5
7
.
[
1
1
]
M
.
M
.
C
h
o
w
d
h
u
r
y
a
n
d
A
.
R
a
h
m
a
n
,
“
P
r
e
d
i
c
t
i
n
g
p
l
a
c
e
s
o
f
r
e
v
e
l
a
t
i
o
n
o
f
Q
u
r
a
n
’
s
v
e
r
s
e
s
,
”
i
n
2
0
2
0
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
C
o
m
p
u
t
i
n
g
a
n
d
I
n
f
o
r
m
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
I
C
C
I
T
2
0
2
0
,
S
e
p
.
2
0
2
0
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
C
I
T
-
144147971.
2020
.
9213772.
[
1
2
]
B
.
A
r
k
o
k
a
n
d
A
.
M
.
Ze
k
i
,
“
C
l
a
ssi
f
i
c
a
t
i
o
n
o
f
Q
u
r
a
n
i
c
t
o
p
i
c
s
u
s
i
n
g
e
n
se
m
b
l
e
l
e
a
r
n
i
n
g
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
8
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
C
o
m
p
u
t
e
r
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
En
g
i
n
e
e
ri
n
g
,
I
C
C
C
E
2
0
2
1
,
J
u
n
.
2
0
2
1
,
p
p
.
2
4
4
–
2
4
8
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
C
C
E
5
0
0
2
9
.
2
0
2
1
.
9
4
6
7
1
7
8
.
[
1
3
]
B
.
A
r
k
o
k
a
n
d
A
.
M
.
Ze
k
i
,
“
C
l
a
ssi
f
i
c
a
t
i
o
n
o
f
Q
u
r
a
n
i
c
t
o
p
i
c
s
u
s
i
n
g
S
M
O
T
E
t
e
c
h
n
i
q
u
e
,
”
i
n
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
ren
c
e
o
f
M
o
d
e
r
n
T
ren
d
s
i
n
I
C
T
I
n
d
u
st
r
y
:
T
o
w
a
rd
s
t
h
e
E
x
c
e
l
l
e
n
c
e
i
n
t
h
e
I
C
T
I
n
d
u
st
ri
e
s,
MTI
C
T
I
2
0
2
1
,
D
e
c
.
2
0
2
1
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
M
TI
C
TI
5
3
9
2
5
.
2
0
2
1
.
9
6
6
4
7
7
4
.
[
1
4
]
R
.
H
i
d
a
y
a
t
a
n
d
S
.
M
i
n
a
t
i
,
“
C
o
m
p
a
r
a
t
i
v
e
a
n
a
l
y
si
s
o
f
t
e
x
t
mi
n
i
n
g
c
l
a
s
si
f
i
c
a
t
i
o
n
a
l
g
o
r
i
t
h
m
s
f
o
r
E
n
g
l
i
sh
a
n
d
I
n
d
o
n
e
s
i
a
n
Q
u
r
’
a
n
t
r
a
n
s
l
a
t
i
o
n
,
”
I
J
I
D
(
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
n
I
n
f
o
rm
a
t
i
c
s
f
o
r
D
e
v
e
l
o
p
m
e
n
t
)
,
v
o
l
.
8
,
n
o
.
1
,
p
.
4
7
,
Ju
n
.
2
0
1
9
,
d
o
i
:
1
0
.
1
4
4
2
1
/
i
j
i
d
.
2
0
1
9
.
0
8
1
0
8
.
[
1
5
]
S
.
J.
P
u
t
r
a
,
Y
.
S
u
g
i
a
r
t
i
,
G
.
D
i
mas
,
M
.
N
.
G
u
n
a
w
a
n
,
T.
S
u
t
a
b
r
i
,
a
n
d
A
.
S
u
r
y
a
t
n
o
,
“
D
o
c
u
m
e
n
t
c
l
a
ss
i
f
i
c
a
t
i
o
n
u
si
n
g
N
a
ï
v
e
B
a
y
e
s
f
o
r
I
n
d
o
n
e
si
a
n
t
r
a
n
sl
a
t
i
o
n
o
f
t
h
e
Q
u
r
a
n
,
”
i
n
2
0
1
9
7
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
C
y
b
e
r
a
n
d
I
T
S
e
rv
i
c
e
M
a
n
a
g
e
m
e
n
t
,
C
I
T
S
M
2
0
1
9
,
N
o
v
.
2
0
1
9
,
p
p
.
1
–
4
,
d
o
i
:
1
0
.
1
1
0
9
/
C
I
TSM
4
7
7
5
3
.
2
0
1
9
.
8
9
6
5
3
9
0
.
[
1
6
]
O
.
V
.
P
u
t
r
a
,
F
.
D
.
E
l
f
i
a
n
i
t
a
,
T.
H
a
r
mi
n
i
,
A
.
Tr
i
s
n
a
n
i
,
a
n
d
A
.
N
u
g
r
o
h
o
,
“
i
Q
u
r
N
e
t
:
a
d
e
e
p
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
f
o
r
t
e
x
t
c
l
a
ss
i
f
i
c
a
t
i
o
n
o
n
t
h
e
I
n
d
o
n
e
s
i
a
n
H
o
l
y
Q
u
r
a
n
t
r
a
n
s
l
a
t
i
o
n
,
”
i
n
2
0
2
1
I
n
t
e
r
n
a
t
i
o
n
a
l
S
e
m
i
n
a
r
o
n
Ma
c
h
i
n
e
L
e
a
r
n
i
n
g
,
O
p
t
i
m
i
z
a
t
i
o
n
,
a
n
d
D
a
t
a
S
c
i
e
n
c
e
,
I
S
MOD
E
2
0
2
1
,
Ja
n
.
2
0
2
2
,
p
p
.
8
6
–
9
1
,
d
o
i
:
1
0
.
1
1
0
9
/
I
S
M
O
D
E
5
3
5
8
4
.
2
0
2
2
.
9
7
4
3
1
3
2
.
[
1
7
]
F
.
S
.
U
t
o
m
o
,
N
.
S
u
r
y
a
n
a
,
a
n
d
M
.
S
.
A
z
m
i
,
“
S
t
e
mm
i
n
g
i
mp
a
c
t
a
n
a
l
y
si
s
o
n
I
n
d
o
n
e
s
i
a
n
Q
u
r
a
n
t
r
a
n
s
l
a
t
i
o
n
a
n
d
t
h
e
i
r
e
x
e
g
e
si
s
c
l
a
ss
i
f
i
c
a
t
i
o
n
f
o
r
o
n
t
o
l
o
g
y
i
n
s
t
a
n
c
e
s,
”
I
I
U
M
E
n
g
i
n
e
e
ri
n
g
J
o
u
rn
a
l
,
v
o
l
.
2
1
,
n
o
.
1
,
p
p
.
3
3
–
5
0
,
J
a
n
.
2
0
2
0
,
d
o
i
:
1
0
.
3
1
4
3
6
/
i
i
u
m
e
j
.
v
2
1
i
1
.
1
1
7
0
.
[
1
8
]
Y
.
P
u
r
w
a
t
i
,
F
.
S
.
U
t
o
mo
,
N
.
Tr
i
n
a
r
s
i
h
,
a
n
d
H
.
H
i
d
a
y
a
t
u
l
l
o
h
,
“
F
e
a
t
u
r
e
se
l
e
c
t
i
o
n
t
e
c
h
n
i
q
u
e
t
o
i
m
p
r
o
v
e
t
h
e
i
n
s
t
a
n
c
e
s
c
l
a
ss
i
f
i
c
a
t
i
o
n
f
r
a
mew
o
r
k
p
e
r
f
o
r
m
a
n
c
e
f
o
r
Q
u
r
a
n
o
n
t
o
l
o
g
y
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
n
I
n
f
o
rm
a
t
i
c
s
V
i
s
u
a
l
i
z
a
t
i
o
n
,
v
o
l
.
7
,
n
o
.
2
,
p
p
.
6
1
5
–
6
2
0
,
Ju
l
.
2
0
2
3
,
d
o
i
:
1
0
.
3
0
6
3
0
/
j
o
i
v
.
7
.
2
.
1
1
9
5
.
[
1
9
]
T.
T
a
n
t
i
sr
i
p
r
e
e
c
h
a
a
n
d
N
.
S
o
o
n
t
h
o
r
n
p
h
i
sa
j
,
“
A
n
o
v
e
l
t
e
r
m
w
e
i
g
h
t
i
n
g
sc
h
e
me
f
o
r
i
mb
a
l
a
n
c
e
d
t
e
x
t
c
l
a
ss
i
f
i
c
a
t
i
o
n
,
”
I
n
f
o
rm
a
t
i
c
a
(
S
l
o
v
e
n
i
a
)
,
v
o
l
.
4
6
,
n
o
.
2
,
p
p
.
2
5
9
–
2
6
8
,
J
u
n
.
2
0
2
2
,
d
o
i
:
1
0
.
3
1
4
4
9
/
i
n
f
.
v
4
6
i
2
.
3
5
2
3
.
[
2
0
]
H
.
A
r
a
b
i
a
n
d
M
.
A
k
b
a
r
i
,
“
I
mp
r
o
v
i
n
g
p
l
a
g
i
a
r
i
sm
d
e
t
e
c
t
i
o
n
i
n
t
e
x
t
d
o
c
u
m
e
n
t
u
si
n
g
h
y
b
r
i
d
w
e
i
g
h
t
e
d
s
i
mi
l
a
r
i
t
y
,
”
Ex
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
.
2
0
7
,
p
.
1
1
8
0
3
4
,
N
o
v
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
sw
a
.
2
0
2
2
.
1
1
8
0
3
4
.
[
2
1
]
J.
A
t
t
i
e
h
a
n
d
J.
T
e
k
l
i
,
“
S
u
p
e
r
v
i
s
e
d
t
e
r
m
-
c
a
t
e
g
o
r
y
f
e
a
t
u
r
e
w
e
i
g
h
t
i
n
g
f
o
r
i
mp
r
o
v
e
d
t
e
x
t
c
l
a
ss
i
f
i
c
a
t
i
o
n
,
”
K
n
o
w
l
e
d
g
e
-
Ba
se
d
S
y
st
e
m
s
,
v
o
l
.
2
6
1
,
p
.
1
1
0
2
1
5
,
F
e
b
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
k
n
o
s
y
s.
2
0
2
2
.
1
1
0
2
1
5
.
[
2
2
]
M
.
N
.
R
a
i
d
a
,
Z.
N
.
S
r
i
st
y
,
N
.
U
l
f
a
t
,
S
.
M
.
A
.
M
o
n
i
sh
a
,
M
.
J.
I
.
M
o
st
a
f
a
,
a
n
d
M
.
N
.
H
a
q
u
e
,
“
A
s
t
u
d
y
o
n
c
l
a
ssi
f
y
i
n
g
S
t
a
c
k
O
v
e
r
f
l
o
w
q
u
e
s
t
i
o
n
s
b
a
s
e
d
o
n
d
i
f
f
i
c
u
l
t
y
b
y
u
t
i
l
i
z
i
n
g
c
o
n
t
e
x
t
u
a
l
f
e
a
t
u
r
e
s,
”
J
o
u
r
n
a
l
o
f
S
y
s
t
e
m
s
a
n
d
S
o
f
t
w
a
re
,
v
o
l
.
2
0
8
,
p
.
1
1
1
8
8
4
,
F
e
b
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
ss.
2
0
2
3
.
1
1
1
8
8
4
.
[
2
3
]
Z.
Ji
a
n
g
,
B
.
G
a
o
,
Y
.
H
e
,
Y
.
H
a
n
,
P
.
D
o
y
l
e
,
a
n
d
Q
.
Z
h
u
,
“
Te
x
t
c
l
a
ssi
f
i
c
a
t
i
o
n
u
s
i
n
g
n
o
v
e
l
t
e
r
m
w
e
i
g
h
t
i
n
g
sc
h
e
m
e
-
b
a
s
e
d
i
m
p
r
o
v
e
d
TF
-
I
D
F
f
o
r
i
n
t
e
r
n
e
t
m
e
d
i
a
r
e
p
o
r
t
s,”
M
a
t
h
e
m
a
t
i
c
a
l
Pr
o
b
l
e
m
s
i
n
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
2
0
2
1
,
p
p
.
1
–
3
0
,
M
a
r
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
1
/
6
6
1
9
0
8
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.
3
9
,
No
.
1
,
Ju
ly
20
25
:
603
-
6
1
3
612
[
2
4
]
D
.
J.
B
e
n
k
e
n
d
o
r
f
,
S
.
D
.
S
c
h
w
a
r
t
z
,
D
.
R
.
C
u
t
l
e
r
,
a
n
d
C
.
P
.
H
a
w
k
i
n
s
,
“
C
o
r
r
e
c
t
i
n
g
f
o
r
t
h
e
e
f
f
e
c
t
s
o
f
c
l
a
ss
i
mb
a
l
a
n
c
e
i
mp
r
o
v
e
s
t
h
e
p
e
r
f
o
r
m
a
n
c
e
o
f
ma
c
h
i
n
e
-
l
e
a
r
n
i
n
g
b
a
s
e
d
s
p
e
c
i
e
s
d
i
st
r
i
b
u
t
i
o
n
m
o
d
e
l
s,”
Ec
o
l
o
g
i
c
a
l
Mo
d
e
l
l
i
n
g
,
v
o
l
.
4
8
3
,
p
.
1
1
0
4
1
4
,
S
e
p
.
2
0
2
3
,
d
o
i
:
10
.
1
0
1
6
/
j
.
e
c
o
l
mo
d
e
l
.
2
0
2
3
.
1
1
0
4
1
4
.
[
2
5
]
X
.
C
h
e
n
g
,
K
.
H
u
a
n
g
,
Y
.
Z
o
u
,
a
n
d
S
.
M
a
,
“
S
l
e
e
p
EG
A
N
:
a
GAN
-
e
n
h
a
n
c
e
d
e
n
s
e
m
b
l
e
d
e
e
p
l
e
a
r
n
i
n
g
mo
d
e
l
f
o
r
i
m
b
a
l
a
n
c
e
d
c
l
a
ss
i
f
i
c
a
t
i
o
n
o
f
s
l
e
e
p
s
t
a
g
e
s
,
”
B
i
o
m
e
d
i
c
a
l
S
i
g
n
a
l
Pr
o
c
e
ss
i
n
g
a
n
d
C
o
n
t
ro
l
,
v
o
l
.
9
2
,
p
.
1
0
6
0
2
0
,
Ju
n
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
b
s
p
c
.
2
0
2
4
.
1
0
6
0
2
0
.
[
2
6
]
Y
.
L
i
,
J.
Ji
n
,
H
.
Ta
o
,
Y
.
X
i
a
o
,
J
.
L
i
a
n
g
,
a
n
d
C
.
L.
P
.
C
h
e
n
,
“
C
o
mp
l
e
me
n
t
e
d
s
u
b
sp
a
c
e
-
b
a
s
e
d
w
e
i
g
h
t
e
d
c
o
l
l
a
b
o
r
a
t
i
v
e
r
e
p
r
e
s
e
n
t
a
t
i
o
n
m
o
d
e
l
f
o
r
i
m
b
a
l
a
n
c
e
d
l
e
a
r
n
i
n
g
,
”
Ap
p
l
i
e
d
S
o
f
t
C
o
m
p
u
t
i
n
g
,
v
o
l
.
1
5
3
,
p
.
1
1
1
3
1
9
,
M
a
r
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
s
o
c
.
2
0
2
4
.
1
1
1
3
1
9
.
[
2
7
]
S
.
T
a
o
,
P
.
P
e
n
g
,
Y
.
L
i
,
H
.
S
u
n
,
Q
.
L
i
,
a
n
d
H
.
W
a
n
g
,
“
S
u
p
e
r
v
i
s
e
d
c
o
n
t
r
a
st
i
v
e
r
e
p
r
e
se
n
t
a
t
i
o
n
l
e
a
r
n
i
n
g
w
i
t
h
t
r
e
e
-
st
r
u
c
t
u
r
e
d
p
a
r
z
e
n
e
st
i
mat
o
r
B
a
y
e
si
a
n
o
p
t
i
mi
z
a
t
i
o
n
f
o
r
i
mb
a
l
a
n
c
e
d
t
a
b
u
l
a
r
d
a
t
a
,
”
Ex
p
e
r
t
S
y
s
t
e
m
s
w
i
t
h
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
2
3
7
,
p
.
1
2
1
2
9
4
,
M
a
r
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
sw
a
.
2
0
2
3
.
1
2
1
2
9
4
.
[
2
8
]
X
.
W
e
n
g
e
t
a
l
.
,
“
A
j
o
i
n
t
l
e
a
r
n
i
n
g
m
e
t
h
o
d
f
o
r
i
n
c
o
m
p
l
e
t
e
a
n
d
i
m
b
a
l
a
n
c
e
d
d
a
t
a
i
n
e
l
e
c
t
r
o
n
i
c
h
e
a
l
t
h
r
e
c
o
r
d
b
a
sed
o
n
g
e
n
e
r
a
t
i
v
e
a
d
v
e
r
sar
i
a
l
n
e
t
w
o
r
k
s
,
”
C
o
m
p
u
t
e
rs
i
n
B
i
o
l
o
g
y
a
n
d
M
e
d
i
c
i
n
e
,
v
o
l
.
1
6
8
,
p
.
1
0
7
6
8
7
,
Ja
n
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
mp
b
i
o
m
e
d
.
2
0
2
3
.
1
0
7
6
8
7
.
[
2
9
]
L.
Z
h
u
,
Y
.
H
e
,
a
n
d
D
.
Z
h
o
u
,
“
A
n
e
u
r
a
l
g
e
n
e
r
a
t
i
v
e
m
o
d
e
l
f
o
r
j
o
i
n
t
l
e
a
r
n
i
n
g
t
o
p
i
c
s
a
n
d
t
o
p
i
c
-
s
p
e
c
i
f
i
c
w
o
r
d
e
mb
e
d
d
i
n
g
s,
”
T
ra
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
.
8
,
p
p
.
1
–
1
5
,
D
e
c
.
2
0
2
0
,
d
o
i
:
1
0
.
1
1
6
2
/
t
a
c
l
_
a
_
0
0
3
2
6
.
[
3
0
]
I
.
I
a
c
o
b
a
c
c
i
,
M
.
T.
P
i
l
e
h
v
a
r
,
a
n
d
R
.
N
a
v
i
g
l
i
,
“
Em
b
e
d
d
i
n
g
s
f
o
r
w
o
r
d
se
n
s
e
d
i
sa
mb
i
g
u
a
t
i
o
n
:
a
n
e
v
a
l
u
a
t
i
o
n
s
t
u
d
y
,
”
i
n
5
4
t
h
An
n
u
a
l
Me
e
t
i
n
g
o
f
t
h
e
As
so
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
,
A
C
L
2
0
1
6
-
Lo
n
g
P
a
p
e
rs
,
2
0
1
6
,
v
o
l
.
2
,
p
p
.
8
9
7
–
9
0
7
,
d
o
i
:
1
0
.
1
8
6
5
3
/
v
1
/
p
1
6
-
1
0
8
5
.
[
3
1
]
N
.
G
a
r
g
,
L.
S
c
h
i
e
b
i
n
g
e
r
,
D
.
Ju
r
a
f
s
k
y
,
a
n
d
J
.
Z
o
u
,
“
W
o
r
d
e
m
b
e
d
d
i
n
g
s
q
u
a
n
t
i
f
y
1
0
0
y
e
a
r
s
o
f
g
e
n
d
e
r
a
n
d
e
t
h
n
i
c
st
e
r
e
o
t
y
p
e
s,
”
Pro
c
e
e
d
i
n
g
s o
f
t
h
e
N
a
t
i
o
n
a
l
Ac
a
d
e
m
y
o
f
S
c
i
e
n
c
e
s
o
f
t
h
e
U
n
i
t
e
d
S
t
a
t
e
s o
f
A
m
e
ri
c
a
,
v
o
l
.
1
1
5
,
n
o
.
1
6
,
p
p
.
E
3
6
3
5
–
E3
6
4
4
,
A
p
r
.
2
0
1
8
,
d
o
i
:
1
0
.
1
0
7
3
/
p
n
a
s
.
1
7
2
0
3
4
7
1
1
5
.
[
3
2
]
S
.
F
u
,
D
.
S
u
,
S
.
Li
,
S
.
S
u
n
,
a
n
d
Y
.
Ti
a
n
,
“
Li
n
e
a
r
-
e
x
p
o
n
e
n
t
i
a
l
l
o
ss
i
n
c
o
r
p
o
r
a
t
e
d
d
e
e
p
l
e
a
r
n
i
n
g
f
o
r
i
m
b
a
l
a
n
c
e
d
c
l
a
ssi
f
i
c
a
t
i
o
n
,
”
I
S
A
T
ra
n
s
a
c
t
i
o
n
s
,
v
o
l
.
1
4
0
,
p
p
.
2
79
–
2
9
2
,
S
e
p
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
sa
t
r
a
.
2
0
2
3
.
0
6
.
0
1
6
.
[
3
3
]
S
.
R
e
z
v
a
n
i
a
n
d
X
.
W
a
n
g
,
“
A
b
r
o
a
d
r
e
v
i
e
w
o
n
c
l
a
ss i
m
b
a
l
a
n
c
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s,
”
A
p
p
l
i
e
d
S
o
f
t
C
o
m
p
u
t
i
n
g
,
v
o
l
.
1
4
3
,
p
.
1
1
0
4
1
5
,
A
u
g
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
s
o
c
.
2
0
2
3
.
1
1
0
4
1
5
.
[
3
4
]
J.
Ta
n
g
,
Z.
H
o
u
,
X
.
Y
u
,
S
.
F
u
,
a
n
d
Y
.
Ti
a
n
,
“
M
u
l
t
i
-
v
i
e
w
c
o
s
t
-
sen
si
t
i
v
e
k
e
r
n
e
l
l
e
a
r
n
i
n
g
f
o
r
i
m
b
a
l
a
n
c
e
d
c
l
a
ssi
f
i
c
a
t
i
o
n
p
r
o
b
l
e
m,
”
N
e
u
ro
c
o
m
p
u
t
i
n
g
,
v
o
l
.
5
5
2
,
p
.
1
2
6
5
6
2
,
O
c
t
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
n
e
u
c
o
m
.
2
0
2
3
.
1
2
6
5
6
2
.
[
3
5
]
W
.
C
h
e
n
,
K
.
Y
a
n
g
,
Z
.
Y
u
,
a
n
d
W
.
Z
h
a
n
g
,
“
D
o
u
b
l
e
-
k
e
r
n
e
l
b
a
s
e
d
c
l
a
ss
-
s
p
e
c
i
f
i
c
b
r
o
a
d
l
e
a
r
n
i
n
g
s
y
st
e
m
f
o
r
m
u
l
t
i
c
l
a
ss
i
m
b
a
l
a
n
c
e
l
e
a
r
n
i
n
g
,
”
K
n
o
w
l
e
d
g
e
-
Ba
s
e
d
S
y
st
e
m
s
,
v
o
l
.
2
5
3
,
p
.
1
0
9
5
3
5
,
O
c
t
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
k
n
o
s
y
s.
2
0
2
2
.
1
0
9
5
3
5
.
[
3
6
]
A
.
A
ma
l
i
a
,
M
.
S
.
Li
d
y
a
,
A
.
A
n
d
r
i
a
n
,
E.
M
.
Z
a
mz
a
mi
,
a
n
d
S
.
M
.
H
a
r
d
i
,
“
O
LC
B
o
t
:
d
i
sse
mi
n
a
t
i
o
n
o
f
i
n
t
e
r
a
c
t
i
v
e
i
n
f
o
r
ma
t
i
o
n
r
e
l
a
t
e
d
t
o
I
n
d
o
n
e
si
a
’
s
O
m
n
i
b
u
s
La
w
w
i
t
h
t
h
e
i
m
p
l
e
m
e
n
t
a
t
i
o
n
o
f
f
u
z
z
y
s
t
r
i
n
g
m
a
t
c
h
i
n
g
a
l
g
o
r
i
t
h
m
a
n
d
s
a
st
r
a
w
i
st
e
m
mer
,
”
i
n
P
ro
c
e
e
d
i
n
g
-
ELT
I
C
O
M
2
0
2
2
:
6
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
El
e
c
t
ri
c
a
l
,
T
e
l
e
c
o
m
m
u
n
i
c
a
t
i
o
n
a
n
d
C
o
m
p
u
t
e
r
E
n
g
i
n
e
e
ri
n
g
2
0
2
2
,
N
o
v
.
2
0
2
2
,
p
p
.
1
7
8
–
1
8
1
,
d
o
i
:
1
0
.
1
1
0
9
/
EL
TI
C
O
M
5
7
7
4
7
.
2
0
2
2
.
1
0
0
3
7
9
6
6
.
[
3
7
]
S
.
F
a
h
m
i
,
L.
P
u
r
n
a
maw
a
t
i
,
G
.
F
.
S
h
i
d
i
k
,
M
.
M
u
l
j
o
n
o
,
a
n
d
A
.
Z.
F
a
n
a
n
i
,
“
S
e
n
t
i
me
n
t
a
n
a
l
y
si
s
o
f
s
t
u
d
e
n
t
r
e
v
i
e
w
i
n
l
e
a
r
n
i
n
g
man
a
g
e
me
n
t
s
y
st
e
m b
a
se
d
o
n
s
a
st
r
a
w
i
st
e
m
mer
a
n
d
S
V
M
-
P
S
O
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
-
2
0
2
0
I
n
t
e
r
n
a
t
i
o
n
a
l
S
e
m
i
n
a
r o
n
Ap
p
l
i
c
a
t
i
o
n
f
o
r
T
e
c
h
n
o
l
o
g
y
o
f
I
n
f
o
rm
a
t
i
o
n
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
:
I
T
C
h
a
l
l
e
n
g
e
s
f
o
r
S
u
st
a
i
n
a
b
i
l
i
t
y
,
S
c
a
l
a
b
i
l
i
t
y
,
a
n
d
S
e
c
u
ri
t
y
i
n
t
h
e
A
g
e
o
f
D
i
g
i
t
a
l
D
i
sru
p
t
i
o
n
,
i
S
e
m
a
n
t
i
c
2
0
2
0
,
S
e
p
.
2
0
2
0
,
p
p
.
6
4
3
–
6
4
8
,
d
o
i
:
1
0
.
1
1
0
9
/
i
S
e
ma
n
t
i
c
5
0
1
6
9
.
2
0
2
0
.
9
2
3
4
2
9
1
.
[
3
8
]
B
.
S
i
sw
a
n
t
o
a
n
d
Y
.
D
a
n
i
,
“
S
e
n
t
i
m
e
n
t
a
n
a
l
y
s
i
s
a
b
o
u
t
O
x
i
m
e
t
e
r
a
s
C
O
V
I
D
-
1
9
d
e
t
e
c
t
i
o
n
t
o
o
l
s
o
n
Tw
i
t
t
e
r
u
si
n
g
S
a
st
r
a
w
i
Li
b
r
a
r
y
,
”
i
n
2
0
2
1
8
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
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
C
o
m
p
u
t
e
r
a
n
d
El
e
c
t
ri
c
a
l
E
n
g
i
n
e
e
r
i
n
g
,
I
C
I
T
A
C
EE
2
0
2
1
,
S
e
p
.
2
0
2
1
,
p
p
.
1
6
1
–
1
6
4
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
I
T
A
C
EE
5
3
1
8
4
.
2
0
2
1
.
9
6
1
7
2
1
6
.
[
3
9
]
J.
Zh
a
n
g
a
n
d
R
.
X
i
e
,
“
W
o
r
d
2
v
e
c
-
p
o
w
e
r
e
d
a
l
g
o
r
i
t
h
m
f
o
r
e
f
f
i
c
i
e
n
t
r
e
t
r
i
e
v
a
l
o
f
b
i
l
l
o
f
q
u
a
n
t
i
t
i
e
s,”
i
n
Pr
o
c
e
e
d
i
n
g
s
-
2
0
2
3
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
I
m
a
g
e
Pr
o
c
e
ssi
n
g
a
n
d
C
o
m
p
u
t
e
r
Vi
s
i
o
n
,
I
P
C
V
2
0
2
3
,
M
a
y
2
0
2
3
,
p
p
.
1
0
8
–
1
1
1
,
d
o
i
:
1
0
.
1
1
0
9
/
I
P
C
V
5
7
0
3
3
.
2
0
2
3
.
0
0
0
2
7
.
[
4
0
]
A
.
G
.
A
y
a
r
,
S
.
A
y
g
u
n
,
M
.
H
a
ss
a
n
N
a
j
a
f
i
,
a
n
d
M
.
M
a
r
g
a
l
a
,
“
W
o
r
d
2
H
y
p
e
r
V
e
c
:
f
r
o
m
w
o
r
d
e
m
b
e
d
d
i
n
g
s
t
o
h
y
p
e
r
v
e
c
t
o
r
s
f
o
r
h
y
p
e
r
d
i
m
e
n
si
o
n
a
l
c
o
m
p
u
t
i
n
g
,
”
i
n
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
A
C
M
G
re
a
t
L
a
k
e
s
S
y
m
p
o
s
i
u
m
o
n
VL
S
I
,
G
L
S
VLS
I
,
J
u
n
.
2
0
2
4
,
p
p
.
3
5
5
–
3
5
6
,
d
o
i
:
1
0
.
1
1
4
5
/
3
6
4
9
4
7
6
.
3
6
5
8
7
9
5
.
[
4
1
]
H
.
M
.
W
a
i
d
y
a
s
o
o
r
i
y
a
a
n
d
M
.
H
a
r
i
y
a
ma,
“
P
e
r
f
o
r
ma
n
c
e
e
v
a
l
u
a
t
i
o
n
o
f
w
o
r
d
2
v
e
c
a
c
c
e
l
e
r
a
t
o
r
s
e
x
p
l
o
i
t
i
n
g
s
p
a
t
i
a
l
a
n
d
t
e
mp
o
r
a
l
p
a
r
a
l
l
e
l
i
sm
o
n
D
D
R
/
H
B
M
-
b
a
s
e
d
F
P
G
A
s,”
J
o
u
r
n
a
l
o
f
S
u
p
e
r
c
o
m
p
u
t
i
n
g
,
v
o
l
.
8
0
,
n
o
.
1
2
,
p
p
.
1
7
1
9
2
–
1
7
2
1
1
,
A
u
g
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
2
2
7
-
0
2
4
-
0
6
1
2
0
-
x.
[
4
2
]
J.
F
l
i
sar
a
n
d
V
.
P
o
d
g
o
r
e
l
e
c
,
“
I
d
e
n
t
i
f
i
c
a
t
i
o
n
o
f
se
l
f
-
a
d
mi
t
t
e
d
t
e
c
h
n
i
c
a
l
d
e
b
t
u
si
n
g
e
n
h
a
n
c
e
d
f
e
a
t
u
r
e
sel
e
c
t
i
o
n
b
a
se
d
o
n
w
o
r
d
e
mb
e
d
d
i
n
g
,
”
I
EEE
Ac
c
e
ss
,
v
o
l
.
7
,
p
p
.
1
0
6
4
7
5
–
1
0
6
4
9
4
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
1
9
.
2
9
3
3
3
1
8
.
[
4
3
]
W
.
T
i
a
n
,
J
.
Li
,
a
n
d
H
.
Li
,
“
A
me
t
h
o
d
o
f
f
e
a
t
u
r
e
se
l
e
c
t
i
o
n
b
a
se
d
o
n
w
o
r
d
2
v
e
c
i
n
t
e
x
t
c
a
t
e
g
o
r
i
z
a
t
i
o
n
,
”
i
n
C
h
i
n
e
se
C
o
n
t
r
o
l
C
o
n
f
e
re
n
c
e
,
C
C
C
,
Ju
l
.
2
0
1
8
,
v
o
l
.
2
0
1
8
-
Ju
l
y
,
p
p
.
9
4
5
2
–
9
4
5
5
,
d
o
i
:
1
0
.
2
3
9
1
9
/
C
h
i
C
C
.
2
0
1
8
.
8
4
8
3
3
4
5
.
[
4
4
]
F
.
Z
.
T
a
l
a
,
“
A
s
t
u
d
y
o
f
s
t
e
m
m
i
n
g
e
f
f
e
c
t
s
o
n
i
n
f
o
r
m
a
t
i
o
n
r
e
t
r
i
e
v
a
l
i
n
B
a
h
a
s
a
I
n
d
o
n
e
s
i
a
,
”
U
n
i
v
e
r
s
i
t
e
i
t
v
a
n
A
m
s
t
e
r
d
a
m
,
2003.
[
4
5
]
A
.
F
a
b
i
j
a
n
,
B
.
P
o
l
i
s,
R
.
F
a
b
i
j
a
n
,
K
.
Z
a
k
r
z
e
w
sk
i
,
E.
N
o
w
o
s
ł
a
w
s
k
a
,
a
n
d
A
.
Za
w
a
d
z
k
a
-
F
a
b
i
j
a
n
,
“
A
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
i
n
s
c
o
l
i
o
s
i
s
c
l
a
ss
i
f
i
c
a
t
i
o
n
:
a
n
i
n
v
e
st
i
g
a
t
i
o
n
o
f
l
a
n
g
u
a
g
e
-
b
a
se
d
mo
d
e
l
s,
”
J
o
u
rn
a
l
o
f
Pe
rs
o
n
a
l
i
ze
d
Me
d
i
c
i
n
e
,
v
o
l
.
1
3
,
n
o
.
1
2
,
p
.
1
6
9
5
,
D
e
c
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
j
p
m1
3
1
2
1
6
9
5
.
[
4
6
]
G
.
S
h
a
o
,
L
.
T
a
n
g
,
a
n
d
J
.
L
i
a
o
,
“
O
v
e
r
s
e
l
l
i
n
g
o
v
e
r
a
l
l
m
a
p
a
c
c
u
r
a
c
y
m
i
si
n
f
o
r
ms
a
b
o
u
t
r
e
s
e
a
r
c
h
r
e
l
i
a
b
i
l
i
t
y
,
”
L
a
n
d
s
c
a
p
e
E
c
o
l
o
g
y
,
v
o
l
.
3
4
,
n
o
.
1
1
,
p
p
.
2
4
8
7
–
2
4
9
2
,
N
o
v
.
2
0
1
9
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
0
9
8
0
-
0
1
9
-
0
0
9
1
6
-
6.
[
4
7
]
G
.
S
h
a
o
,
H
.
Zh
a
n
g
,
J
.
S
h
a
o
,
K
.
W
o
e
s
t
e
,
a
n
d
L
.
T
a
n
g
,
“
S
t
r
e
n
g
t
h
e
n
i
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
r
e
p
r
o
d
u
c
i
b
i
l
i
t
y
f
o
r
i
m
a
g
e
c
l
a
s
si
f
i
c
a
t
i
o
n
,
”
Ad
v
a
n
c
e
s
i
n
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
Ma
c
h
i
n
e
L
e
a
rn
i
n
g
,
v
o
l
.
2
,
n
o
.
4
,
p
p
.
4
7
1
–
4
7
6
,
2
0
2
2
,
d
o
i
:
1
0
.
5
4
3
6
4
/
A
A
I
M
L.
2
0
2
2
.
1
1
3
2
.
[
4
8
]
S
.
K
a
n
j
,
F
.
A
b
d
a
l
l
a
h
,
T
.
D
e
n
œ
u
x
,
a
n
d
K
.
To
u
t
,
“
E
d
i
t
i
n
g
t
r
a
i
n
i
n
g
d
a
t
a
f
o
r
m
u
l
t
i
-
l
a
b
e
l
c
l
a
ss
i
f
i
c
a
t
i
o
n
w
i
t
h
t
h
e
k
-
n
e
a
r
e
st
n
e
i
g
h
b
o
r
r
u
l
e
,
”
Pa
t
t
e
rn
A
n
a
l
y
s
i
s
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
9
,
n
o
.
1
,
p
p
.
1
4
5
–
1
6
1
,
F
e
b
.
2
0
1
6
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
0
0
4
4
-
0
1
5
-
0
4
5
2
-
8.
[
4
9
]
C
.
Lo
u
k
a
s
a
n
d
N
.
P
.
S
g
o
u
r
o
s,
“
M
u
l
t
i
-
i
n
s
t
a
n
c
e
m
u
l
t
i
-
l
a
b
e
l
l
e
a
r
n
i
n
g
f
o
r
su
r
g
i
c
a
l
i
m
a
g
e
a
n
n
o
t
a
t
i
o
n
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
Me
d
i
c
a
l
R
o
b
o
t
i
c
s
a
n
d
C
o
m
p
u
t
e
r A
ss
i
s
t
e
d
S
u
r
g
e
r
y
,
v
o
l
.
1
6
,
n
o
.
2
,
A
p
r
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
0
2
/
r
c
s.
2
0
5
8
.
Evaluation Warning : The document was created with Spire.PDF for Python.