T
E
L
K
O
M
NIKA
T
elec
o
mm
un
ica
t
io
n Co
m
pu
t
i
ng
E
lect
ro
nics
a
nd
Co
ntr
o
l
Vo
l.
24
,
No
.
2
,
A
p
r
il
20
26
,
p
p
.
56
4
~
5
7
3
I
SS
N:
1
6
9
3
-
6
9
3
0
,
DOI
: 1
0
.
1
2
9
2
8
/
T
E
L
KOM
NI
K
A
.
v
24
i
2
.
27398
564
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//jo
u
r
n
a
l.u
a
d
.
a
c.
id
/in
d
ex
.
p
h
p
/TELK
OM
N
I
K
A
Ev
a
lua
ting lea
rning
rate e
ff
ec
ts on
lo
ng
sho
rt
-
ter
m
m
e
m
o
ry
for
I
ndo
nesia
n senti
m
en
t
cla
ss
ifi
ca
tion
S
er
ly
E
ldi
na
,
T
e
k
a
d M
a
t
ula
t
a
n
,
No
v
riza
l F
a
t
t
a
h F
a
hm
it
r
a
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
mat
i
c
s
En
g
i
n
e
e
r
i
n
g
,
S
c
h
o
o
l
o
f
El
e
c
t
r
i
c
a
l
a
n
d
I
n
f
o
r
mat
i
c
s
,
U
n
i
v
e
r
s
i
t
a
s
M
a
r
i
t
i
m
R
a
j
a
A
l
i
H
a
j
i
,
T
a
n
j
u
n
g
p
i
n
a
n
g
,
I
n
d
o
n
e
si
a
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
l
14
,
2025
R
ev
i
s
ed
J
an
12
,
2
0
2
6
A
cc
ep
ted
J
an
30
,
2
0
2
6
H
y
p
e
rp
a
ra
m
e
ter
o
p
ti
m
iza
ti
o
n
i
s
a
c
ru
c
ial
p
r
o
c
e
ss
f
o
r
e
n
h
a
n
c
in
g
t
h
e
p
e
rf
o
r
m
a
n
c
e
o
f
d
e
e
p
lea
rn
in
g
m
o
d
e
ls,
p
a
r
ti
c
u
larly
in
t
h
e
c
o
n
tex
t
o
f
In
d
o
n
e
sia
n
se
n
ti
m
e
n
t
c
las
sif
ic
a
t
io
n
.
T
h
is
st
u
d
y
e
x
a
m
in
e
s
th
e
im
p
a
c
t
o
f
v
a
r
y
in
g
lea
rn
in
g
ra
tes
o
n
a
l
o
n
g
sh
o
r
t
-
term
m
e
m
o
r
y
(
L
S
T
M
)
a
rc
h
it
e
c
tu
re
train
e
d
w
it
h
th
e
a
d
a
p
t
iv
e
m
o
m
e
n
t
e
stim
a
ti
o
n
(A
d
a
m
)
o
p
ti
m
i
z
e
r.
Th
e
d
a
tas
e
t
c
o
m
p
rise
s
9
,
2
9
5
In
d
o
n
e
sia
n
c
o
m
m
e
n
ts
a
u
to
m
a
ti
c
a
ll
y
lab
e
led
b
y
th
e
I
n
d
o
n
e
sia
n
B
id
irec
ti
o
n
a
l
E
n
c
o
d
e
r
R
e
p
re
se
n
tatio
n
s
f
ro
m
T
ra
n
sf
o
rm
e
rs
(
In
d
o
BERT
)
m
o
d
e
l.
S
tratif
ied
k
-
f
o
ld
c
ro
ss
-
v
a
li
d
a
ti
o
n
w
a
s
e
m
p
lo
y
e
d
to
m
a
in
tain
c
las
s
b
a
lan
c
e
d
u
rin
g
tr
a
in
in
g
.
L
e
a
rn
in
g
c
u
rv
e
s
w
e
r
e
a
n
a
l
y
z
e
d
to
e
v
a
lu
a
te
c
o
n
v
e
rg
e
n
c
e
a
n
d
id
e
n
ti
f
y
p
o
ten
ti
a
l
o
v
e
rf
it
ti
n
g
,
w
h
il
e
e
a
rly
sto
p
p
in
g
w
a
s
a
p
p
li
e
d
w
h
e
n
p
e
rf
o
rm
a
n
c
e
im
p
ro
v
e
m
e
n
ts
b
e
c
a
m
e
in
sig
n
ifi
c
a
n
t.
T
h
e
one
-
w
a
y
a
n
a
l
y
sis
o
f
v
a
rian
c
e
(
A
N
OV
A
)
tes
t
(
p
-
a
d
j
=
0
.
0
0
0
5
7
5
<
0
.
0
5
)
re
v
e
a
led
sig
n
i
f
ica
n
t
d
if
fe
re
n
c
e
s
a
m
o
n
g
th
e
lea
rn
in
g
ra
te
v
a
riatio
n
s
.
P
o
st
-
h
o
c
a
n
a
ly
sis
in
d
ica
ted
th
e
lea
rn
in
g
ra
tes
o
f
0
.
0
0
0
1
,
0
.
0
0
1
,
a
n
d
0
.
0
0
2
d
if
f
e
r
sig
n
if
ica
n
tl
y
f
r
o
m
0
.
0
2
.
De
sc
rip
ti
v
e
sta
ti
stics
sh
o
w
e
d
th
a
t
a
lea
rn
i
n
g
ra
te
o
f
0
.
0
0
1
w
a
s
th
e
m
o
st
o
p
ti
m
a
l,
a
c
h
i
e
v
in
g
th
e
h
ig
h
e
st
v
a
li
d
a
ti
o
n
a
c
c
u
r
a
c
y
w
h
il
e
m
a
in
tain
in
g
a
re
lativ
e
ly
lo
w
v
a
ri
a
n
c
e
.
Ev
a
lu
a
ti
o
n
a
c
ro
ss
tw
o
d
a
ta
c
a
teg
o
ries
d
e
m
o
n
stra
ted
th
a
t
lo
w
e
r
lea
rn
in
g
ra
tes
(
0
.
0
0
0
1
a
n
d
0
.
0
0
2
)
a
c
h
iev
e
d
th
e
b
e
s
t
a
c
c
u
ra
c
y
,
7
8
.
7
1
%
o
n
i
n
-
d
o
m
a
in
d
a
ta,
w
h
e
re
a
s
h
ig
h
e
r
lea
rn
i
n
g
r
a
tes
(0
.
0
1
a
n
d
0
.
0
2
)
p
e
rf
o
rm
e
d
b
e
tt
e
r
o
n
c
ro
ss
-
d
o
m
a
in
d
a
ta
w
it
h
3
6
%
a
c
c
u
ra
c
y
.
T
h
e
se
f
in
d
in
g
s
h
ig
h
li
g
h
t
th
e
c
ru
c
ial
ro
l
e
o
f
lea
rn
in
g
ra
te
se
le
c
ti
o
n
in
d
e
term
in
i
ng
m
o
d
e
l
sta
b
il
it
y
a
n
d
g
e
n
e
ra
li
z
a
ti
o
n
c
a
p
a
b
il
it
y
.
K
ey
w
o
r
d
s
:
A
d
ap
tiv
e
m
o
m
en
t e
s
ti
m
atio
n
E
ar
ly
s
to
p
p
in
g
L
ea
r
n
i
n
g
r
ate
L
o
n
g
s
h
o
rt
-
ter
m
m
e
m
o
r
y
On
e
-
w
a
y
a
n
al
y
s
i
s
o
f
v
ar
ian
ce
Sen
ti
m
e
n
t c
las
s
i
f
icatio
n
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
:
Ser
l
y
E
ld
in
a
Dep
ar
t
m
en
t o
f
I
n
f
o
r
m
atic
s
E
n
g
in
ee
r
i
n
g
,
Sch
o
o
l o
f
E
lectr
ical
an
d
I
n
f
o
r
m
a
tics
Un
i
v
er
s
ita
s
Ma
r
iti
m
R
aj
a
A
li
Haj
i
T
an
j
u
n
g
p
in
a
n
g
,
I
n
d
o
n
esia
E
m
ail:
s
er
l
y
eld
i
n
a0
3
@
g
m
ai
l.c
o
m
1.
I
NT
RO
D
UCT
I
O
N
Sen
ti
m
e
n
t
an
al
y
s
is
o
n
s
o
cial
m
ed
ia
h
as
b
ec
o
m
e
a
p
r
o
m
i
n
e
n
t
r
esear
ch
ar
ea
th
at
lev
er
a
g
e
s
n
at
u
r
al
lan
g
u
a
g
e
p
r
o
ce
s
s
in
g
(
NL
P
)
an
d
co
m
p
u
tatio
n
al
lin
g
u
is
tic
s
to
ex
tr
ac
t
s
u
b
j
ec
tiv
e
in
f
o
r
m
atio
n
f
r
o
m
te
x
tu
a
l
d
ata,
th
er
eb
y
i
m
p
r
o
v
i
n
g
th
e
u
n
d
er
s
tan
d
in
g
o
f
p
u
b
lic
o
p
in
io
n
,
b
r
an
d
p
er
ce
p
tio
n
,
an
d
s
o
cial
d
y
n
a
m
ics
[
1
]
,
[
2
]
.
I
t
is
w
id
el
y
u
s
ed
to
class
i
f
y
I
n
d
o
n
esian
te
x
t
i
n
to
t
h
r
ee
s
en
ti
m
e
n
t
ca
teg
o
r
ies:
p
o
s
iti
v
e,
n
e
g
ati
v
e,
an
d
n
eu
tr
al
[
3
]
.
On
e
o
f
t
h
e
m
o
s
t
w
id
el
y
u
s
ed
m
o
d
els
f
o
r
th
i
s
p
u
r
p
o
s
e
is
t
h
e
lo
n
g
s
h
o
r
t
-
ter
m
m
e
m
o
r
y
(
L
ST
M)
,
a
ty
p
e
o
f
r
ec
u
r
r
en
t
n
eu
r
al
n
et
w
o
r
k
(
R
N
N)
th
at
is
ca
p
ab
le
o
f
ca
p
tu
r
i
n
g
lo
n
g
-
ter
m
d
ep
en
d
en
cie
s
w
it
h
in
s
eq
u
en
tia
l
d
ata,
al
lo
w
i
n
g
it to
p
er
f
o
r
m
ef
f
ec
ti
v
el
y
ac
r
o
s
s
a
w
id
e
r
an
g
e
o
f
tex
t
p
r
o
ce
s
s
in
g
ta
s
k
s
[
4
]
-
[
6
]
.
L
ea
r
n
i
n
g
r
ate
o
p
tim
izatio
n
p
la
y
s
a
cr
u
cial
r
o
le
in
d
ee
p
le
ar
n
in
g
,
as
it
s
ig
n
if
ican
t
l
y
af
f
ec
ts
m
o
d
el
s
tab
ilit
y
a
n
d
co
n
v
er
g
e
n
ce
.
Am
o
n
g
v
ar
io
u
s
o
p
ti
m
izatio
n
al
g
o
r
ith
m
s
,
t
h
e
ad
ap
tiv
e
m
o
m
e
n
t
esti
m
at
io
n
(
A
d
a
m
)
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
E
va
lu
a
tin
g
le
a
r
n
in
g
r
a
te
effec
ts
o
n
lo
n
g
s
h
o
r
t
-
term me
mo
r
y
fo
r
I
n
d
o
n
esia
n
…
(
S
erly E
ld
in
a
)
565
o
p
tim
izer
is
o
n
e
o
f
th
e
m
o
s
t
p
o
p
u
lar
,
as
it
a
d
ap
tiv
el
y
ad
j
u
s
ts
th
e
lear
n
in
g
r
ate
u
s
i
n
g
b
o
th
m
o
m
en
t
u
m
a
n
d
g
r
ad
ien
t
m
ea
n
e
s
ti
m
atio
n
,
e
n
ab
lin
g
f
aster
a
n
d
m
o
r
e
s
tab
le
co
n
v
er
g
e
n
ce
[
7
]
-
[
9
]
.
T
h
e
lear
n
in
g
r
ate
its
el
f
i
s
a
cr
itica
l
h
y
p
er
p
ar
am
e
ter
th
at
i
n
f
lu
e
n
ce
s
th
e
s
tab
ilit
y
a
n
d
s
p
ee
d
o
f
th
e
tr
ain
i
n
g
p
r
o
ce
s
s
.
A
h
i
g
h
lear
n
i
n
g
r
ate
in
cr
ea
s
es
t
h
e
r
is
k
o
f
o
v
er
s
h
o
o
tin
g
t
h
e
o
p
ti
m
al
s
o
l
u
tio
n
,
w
h
er
ea
s
a
lo
w
lear
n
in
g
r
ate
le
ad
s
to
g
r
ad
u
al
an
d
s
lo
w
er
co
n
v
er
g
e
n
ce
[
10
]
.
P
r
o
p
er
tu
n
i
n
g
o
f
t
h
is
p
ar
a
m
eter
i
s
v
ital
to
ac
h
ie
v
i
n
g
o
p
ti
m
al
m
o
d
el
p
er
f
o
r
m
a
n
ce
an
d
to
m
iti
g
ati
n
g
o
v
er
f
it
tin
g
o
r
u
n
d
er
f
itti
n
g
.
T
h
er
ef
o
r
e,
ad
d
itio
n
al
s
tr
ateg
ie
s
s
u
ch
a
s
ea
r
ly
s
to
p
p
in
g
a
n
d
d
r
o
p
o
u
t a
r
e
o
f
ten
ap
p
lied
to
p
r
ev
en
t t
h
e
s
e
is
s
u
es [
11
].
P
r
ev
io
u
s
s
tu
d
ies
h
a
v
e
e
x
p
lo
r
ed
th
e
i
m
p
le
m
en
ta
tio
n
o
f
t
h
e
L
ST
M
m
o
d
el
[
1
2
]
,
an
d
th
e
u
s
e
o
f
t
h
e
A
d
a
m
o
p
ti
m
izer
f
o
r
I
n
d
o
n
esia
n
s
e
n
ti
m
en
t
an
al
y
s
is
[
1
3
]
.
Fo
r
ex
a
m
p
le,
a
s
t
u
d
y
a
n
al
y
zin
g
v
ar
io
u
s
lear
n
i
n
g
r
ate
co
n
f
i
g
u
r
atio
n
s
r
ep
o
r
ted
th
at
d
if
f
er
en
t
lear
n
i
n
g
r
ate
v
al
u
es
(
0
.
1
,
0
.
0
1
,
0
.
0
0
1
)
an
d
ep
o
ch
s
ettin
g
s
(
3
0
0
,
5
0
0
,
1
0
0
0
)
in
f
l
u
e
n
ce
d
m
o
d
el
s
tab
il
it
y
a
n
d
ac
cu
r
ac
y
i
n
ti
m
e
-
s
er
ie
s
p
r
ed
ictio
n
o
f
c
h
lo
r
o
p
h
y
ll
-
a
co
n
ce
n
tr
atio
n
,
w
it
h
s
u
b
o
p
ti
m
al
lear
n
i
n
g
r
ate
s
ca
u
s
i
n
g
tr
ain
i
n
g
i
n
s
tab
ilit
y
[
1
4
]
.
Si
m
ilar
l
y
,
a
s
t
u
d
y
o
n
th
e
C
I
F
A
R
-
1
0
d
ata
s
et
s
h
o
w
ed
th
at
a
lear
n
i
n
g
r
ate
o
f
0
.
0
0
1
c
o
m
b
i
n
ed
w
it
h
a
d
r
o
p
o
u
t
r
ate
o
f
0
.
5
y
ield
ed
th
e
b
est
p
er
f
o
r
m
an
ce
i
n
ad
d
r
ess
in
g
o
v
er
f
itti
n
g
a
n
d
u
n
d
er
f
itti
n
g
is
s
u
e
s
[
10
]
.
An
o
th
e
r
s
tu
d
y
o
n
th
e
I
n
d
o
n
e
s
ian
B
i
d
ir
ec
tio
n
al
E
n
co
d
er
R
ep
r
esen
tat
io
n
s
f
r
o
m
T
r
an
s
f
o
r
m
er
s
(
I
n
d
o
B
E
R
T
)
s
en
ti
m
e
n
t
an
al
y
s
i
s
m
o
d
e
l
co
n
clu
d
ed
th
at
v
ar
iatio
n
s
in
th
e
A
d
a
m
lear
n
in
g
r
ate
s
ig
n
i
f
ic
an
tl
y
i
n
f
l
u
e
n
ce
d
s
tab
ilit
y
a
n
d
ac
cu
r
ac
y
.
T
h
e
o
p
ti
m
al
lea
r
n
in
g
r
ate
o
f
2
e
-
5
ac
h
iev
ed
a
n
ac
c
u
r
ac
y
o
f
9
4
.
1
4
%,
w
h
ile
a
n
e
x
ce
s
s
i
v
el
y
l
o
w
v
al
u
e
o
f
1
e
-
7
ca
u
s
ed
i
n
s
t
ab
ilit
y
a
n
d
r
ed
u
ce
d
ac
cu
r
ac
y
to
6
9
.
7
6
% [
1
5
].
A
lt
h
o
u
g
h
p
r
ev
io
u
s
s
t
u
d
ies
h
a
v
e
ex
a
m
in
ed
th
e
i
m
p
ac
t
o
f
l
ea
r
n
in
g
r
ate
v
ar
iatio
n
s
,
th
er
e
r
em
ai
n
s
a
r
esear
ch
g
ap
.
B
ased
o
n
o
u
r
c
u
r
r
en
t
k
n
o
w
led
g
e,
n
o
s
tu
d
y
h
as
s
p
ec
if
icall
y
in
v
es
tig
ated
th
e
ef
f
ec
t
o
f
lear
n
i
n
g
r
ate
v
ar
iatio
n
s
o
n
th
e
L
ST
M
m
o
d
el
f
o
r
I
n
d
o
n
e
s
ia
n
tex
t
class
if
icatio
n
u
s
i
n
g
au
to
m
a
ticall
y
lab
eled
d
ata
g
en
er
ated
b
y
a
f
i
n
e
-
tu
n
ed
I
n
d
o
B
E
R
T
m
o
d
el.
Mo
s
t
p
r
io
r
wo
r
k
s
f
o
cu
s
ed
o
n
ti
m
e
-
s
er
ie
s
,
i
m
ag
e,
o
r
s
en
ti
m
en
t
d
atasets
w
it
h
o
u
t
p
er
f
o
r
m
i
n
g
s
t
atis
tical
s
i
g
n
i
f
ican
ce
tes
ts
o
n
t
h
e
r
esu
lt
s
.
T
h
er
ef
o
r
e,
th
is
s
tu
d
y
ai
m
s
to
ev
al
u
ate
th
e
ef
f
ec
t o
f
d
if
f
er
en
t
A
d
a
m
le
ar
n
in
g
r
ate
co
n
f
ig
u
r
atio
n
s
o
n
t
h
e
p
er
f
o
r
m
a
n
ce
o
f
a
tex
t c
la
s
s
i
f
icatio
n
m
o
d
el.
T
h
e
m
o
d
el
w
as
tr
ai
n
ed
u
s
i
n
g
9
,
2
9
5
I
n
d
o
n
esian
co
m
m
e
n
t
s
,
an
d
Stra
tif
ied
k
-
f
o
ld
cr
o
s
s
-
v
al
i
d
atio
n
w
as
a
p
p
lied
to
en
s
u
r
e
r
esu
lt
r
eli
ab
ilit
y
an
d
to
ad
d
r
ess
class
im
b
ala
n
ce
b
y
m
ai
n
tai
n
i
n
g
p
r
o
p
o
r
tio
n
al
class
d
is
tr
ib
u
tio
n
s
in
ea
c
h
f
o
ld
[
1
6
]
.
Fu
r
th
er
m
o
r
e,
a
o
n
e
-
w
a
y
a
n
al
y
s
i
s
o
f
v
ar
ia
n
ce
(
AN
OV
A
)
test
w
ith
a
s
ig
n
i
f
ica
n
ce
lev
el
o
f
(
p
-
ad
j
<
0
.
0
5
)
w
as
co
n
d
u
c
ted
to
d
ete
r
m
i
n
e
s
tati
s
tical
s
ig
n
i
f
ica
n
ce
,
f
o
llo
w
ed
b
y
a
p
o
s
t
-
h
o
c
test
to
ass
es
s
d
if
f
er
en
ce
s
a
m
o
n
g
lear
n
i
n
g
r
ate
v
ar
iatio
n
s
[
1
7
]
,
[
1
8
]
.
T
h
e
ev
alu
atio
n
w
a
s
co
n
d
u
cted
u
s
i
n
g
a
co
n
f
u
s
io
n
m
atr
i
x
u
n
d
er
t
w
o
d
ata
s
ce
n
ar
io
s
to
ass
ess
t
h
e
m
o
d
el
’
s
g
e
n
er
aliza
tio
n
ab
ilit
y
:
in
-
d
o
m
ai
n
(
co
m
m
e
n
t
s
f
r
o
m
th
e
Sire
k
ap
ap
p
licatio
n
o
n
th
e
P
lay
Sto
r
e)
an
d
cr
o
s
s
-
d
o
m
ai
n
(
n
e
w
s
h
ea
d
lin
e
s
r
elate
d
to
th
e
“
Ma
k
an
a
n
B
er
g
izi
Gr
atis
(
MB
G)
”
to
p
ic)
[
19
]
.
T
h
e
m
a
in
co
n
tr
ib
u
tio
n
s
o
f
t
h
is
s
tu
d
y
ar
e
as
f
o
llo
w
s
:
(
i)
p
r
o
v
id
in
g
a
n
e
m
p
ir
ical
a
n
al
y
s
is
o
f
th
e
e
f
f
ec
t
o
f
lear
n
i
n
g
r
ate
v
ar
iatio
n
s
o
n
th
e
ac
cu
r
ac
y
,
s
tab
ilit
y
,
an
d
g
e
n
er
aliza
tio
n
ab
ilit
y
o
f
t
h
e
L
S
T
M
m
o
d
el
an
d
(
ii)
p
r
esen
tin
g
th
e
f
ir
s
t
s
t
u
d
y
t
h
at
ex
a
m
in
e
s
th
e
i
m
p
ac
t
o
f
lear
n
i
n
g
r
ate
v
ar
iatio
n
s
o
n
an
I
n
d
o
n
esian
L
ST
M
m
o
d
el
au
to
m
at
icall
y
lab
eled
u
s
in
g
t
h
e
I
n
d
o
B
E
R
T
m
o
d
el,
w
it
h
v
al
i
d
atio
n
th
r
o
u
g
h
a
o
n
e
-
w
a
y
A
N
OV
A
s
tati
s
tical
test
an
d
ev
alu
a
tio
n
co
n
d
u
cted
o
n
b
o
th
in
-
d
o
m
ai
n
an
d
cr
o
s
s
-
d
o
m
a
in
d
ataset
s
.
T
h
e
r
em
ai
n
d
er
o
f
th
is
p
ap
er
is
o
r
g
an
ized
as:
s
ec
tio
n
2
d
escr
ib
es
th
e
r
esear
ch
m
et
h
o
d
o
lo
g
y
,
s
ec
tio
n
3
p
r
esen
ts
th
e
ex
p
er
i
m
en
tal
r
esu
l
ts
an
d
an
al
y
s
is
,
a
n
d
s
ec
tio
n
4
co
n
cl
u
d
es th
e
s
t
u
d
y
a
n
d
p
r
o
v
id
es d
ir
ec
tio
n
s
f
o
r
f
u
t
u
r
e
r
esear
ch
.
2.
M
E
T
H
O
D
T
h
is
s
tu
d
y
e
m
p
lo
y
s
a
s
en
ti
m
e
n
t
clas
s
if
icatio
n
ap
p
r
o
ac
h
to
an
al
y
ze
te
x
t
u
al
d
ata
s
y
s
te
m
atic
all
y
.
T
h
e
r
esear
ch
m
et
h
o
d
o
lo
g
y
is
s
h
o
w
n
in
Fig
u
r
e
1
,
w
h
ic
h
p
r
esen
ts
t
h
e
p
r
o
ce
s
s
f
r
o
m
d
ata
co
llectio
n
an
d
p
r
ep
r
o
ce
s
s
in
g
to
m
o
d
el
tr
ain
in
g
an
d
ev
al
u
atio
n
.
T
h
e
F
ig
u
r
e
1
p
r
o
v
id
es
a
clea
r
o
v
er
v
ie
w
o
f
th
e
w
o
r
k
f
lo
w
u
s
ed
in
th
is
s
t
u
d
y
.
Fig
u
r
e
1
.
R
esear
ch
m
et
h
o
d
o
lo
g
y
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
ele
co
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
24
,
No
.
2
,
A
p
r
il
20
26
:
56
4
-
57
3
566
2
.
1
.
Da
t
a
s
cr
a
pin
g
D
a
t
a
c
o
ll
e
c
ti
o
n
w
a
s
p
e
r
f
o
r
m
e
d
t
h
r
o
u
g
h
a
w
e
b
s
c
r
a
p
in
g
t
e
ch
n
iq
u
e
u
s
in
g
th
e
G
o
o
g
l
e
Pl
ay
S
c
r
a
p
e
r
[
2
0
]
,
to
s
y
s
te
m
atica
ll
y
o
b
tain
u
s
er
c
o
m
m
e
n
t
s
.
I
n
to
tal,
1
9
,
9
3
6
en
tr
ies
w
er
e
co
llected
,
f
o
c
u
s
i
n
g
o
n
“
Mo
s
t
R
ele
v
an
t”
r
ev
ie
w
s
f
r
o
m
t
h
e
Sire
k
ap
ap
p
licatio
n
av
ai
lab
le
o
n
th
e
Go
o
g
l
e
P
lay
Sto
r
e.
2
.
2
.
Da
t
a
prepa
ra
t
i
o
n
T
h
e
d
ata
p
r
e
p
ar
atio
n
s
tag
e
i
n
v
o
lv
e
s
s
e
v
er
al
ess
e
n
t
ial
p
r
o
ce
s
s
es
to
e
n
s
u
r
e
th
at
t
h
e
d
ataset
is
s
u
itab
le
f
o
r
an
al
y
s
i
s
an
d
m
o
d
eli
n
g
.
T
h
is
s
ta
g
e
co
n
s
i
s
ts
o
f
p
r
ep
r
o
ce
s
s
in
g
,
lab
eli
n
g
,
f
ea
t
u
r
e
ex
tr
ac
tio
n
,
an
d
f
o
r
m
atti
n
g
,
ea
ch
co
n
tr
i
b
u
t
in
g
to
i
m
p
r
o
v
ed
d
ata
q
u
alit
y
an
d
m
o
d
el
co
m
p
atib
ilit
y
.
2
.
2
.
1
.
P
re
pro
ce
s
s
ing
Da
ta
p
r
ep
r
o
ce
s
s
in
g
i
s
a
f
u
n
d
a
m
en
tal
s
tep
i
n
t
h
is
s
t
u
d
y
to
e
n
s
u
r
e
th
a
t
th
e
d
ata
u
s
ed
f
o
r
an
al
y
s
i
s
is
clea
n
,
co
n
s
is
te
n
t,
a
n
d
p
r
o
p
er
ly
p
r
ep
ar
ed
f
o
r
f
u
r
t
h
er
p
r
o
ce
s
s
in
g
.
T
h
is
s
tep
is
cr
u
cia
l
i
n
s
e
n
ti
m
en
t
a
n
al
y
s
is
,
as
i
t
co
n
v
er
ts
r
a
w
tex
t
in
to
a
s
tr
u
ctu
r
ed
f
o
r
m
at
s
u
itab
le
f
o
r
co
m
p
u
tat
io
n
al
p
r
o
ce
s
s
i
n
g
[
2
1
]
,
[
2
2
]
.
T
h
e
p
r
o
ce
s
s
g
en
er
all
y
i
n
v
o
l
v
es
s
e
v
er
al
k
e
y
o
p
er
atio
n
s
,
i
n
cl
u
d
in
g
r
ed
u
n
d
an
c
y
r
e
m
o
v
al
[
2
3
]
,
tex
t
clea
n
in
g
,
to
k
e
n
izatio
n
,
s
to
p
w
o
r
d
r
em
o
v
al,
ca
s
e
f
o
ld
in
g
,
a
n
d
s
te
m
m
i
n
g
[
2
4
]
,
as
w
ell
as
h
an
d
li
n
g
m
i
s
s
i
n
g
v
alu
e
s
[
2
3
]
.
T
h
ese
p
r
ep
r
o
ce
s
s
in
g
s
tep
s
co
llecti
v
el
y
i
m
p
r
o
v
e
t
h
e
q
u
ali
t
y
a
n
d
r
eliab
ilit
y
o
f
t
h
e
d
ataset
f
o
r
m
o
d
el
tr
ain
i
n
g
.
2
.
2
.
2
.
L
a
belin
g
T
h
e
d
ata
lab
elin
g
p
r
o
ce
s
s
w
as
co
n
d
u
cted
u
s
i
n
g
t
h
e
I
n
d
o
B
E
R
T
m
o
d
el
av
ailab
le
o
n
t
h
e
H
u
g
g
i
n
g
Fac
e
p
latf
o
r
m
,
w
h
ic
h
f
ac
ilit
ate
s
c
o
m
m
u
n
it
y
co
llab
o
r
atio
n
b
y
p
r
o
v
id
in
g
o
p
en
-
s
o
u
r
ce
to
o
ls
[
2
5
]
.
T
h
e
p
r
etr
ain
ed
m
o
d
el
u
s
ed
f
o
r
th
is
tas
k
w
a
s
m
d
h
u
g
o
l/i
n
d
o
n
e
s
ia
-
b
er
t
-
s
e
n
ti
m
e
n
t
-
clas
s
i
f
icatio
n
.
Ma
n
u
al
lab
elin
g
w
a
s
n
o
t
p
er
f
o
r
m
ed
d
u
e
to
li
m
ited
lin
g
u
is
t
ic
ex
p
er
tis
e
an
d
t
h
e
n
ee
d
to
m
i
n
i
m
ize
an
n
o
tato
r
s
u
b
j
ec
tiv
it
y
.
T
h
e
I
n
d
o
B
E
R
T
m
o
d
el
w
a
s
ch
o
s
e
n
b
ec
au
s
e
i
t
is
a
m
o
d
er
n
tr
an
s
f
o
r
m
er
-
b
ased
m
o
d
el
tr
ain
ed
o
n
a
lar
g
e
-
s
ca
le
I
n
d
o
n
e
s
ia
n
co
r
p
u
s
,
en
ab
lin
g
a
d
ee
p
er
u
n
d
er
s
tan
d
in
g
o
f
co
n
te
x
tu
a
l
m
e
an
in
g
[
2
6
]
.
Ho
w
e
v
er
,
lex
ico
n
-
b
ased
ap
p
r
o
ac
h
es,
s
u
c
h
as
t
h
e
I
n
d
o
n
e
s
ia
n
S
e
n
t
i
m
e
n
t
L
ex
ico
n
(
I
n
Set)
,
h
av
e
f
u
n
d
a
m
en
tal
li
m
itatio
n
s
b
ec
au
s
e
t
h
e
y
r
el
y
o
n
k
e
y
w
o
r
d
m
atc
h
i
n
g
w
ith
in
t
h
e
lex
ico
n
a
n
d
ca
n
n
o
t
ca
p
tu
r
e
s
e
m
a
n
tic
m
ea
n
i
n
g
p
atter
n
s
ex
p
r
ess
ed
in
f
u
l
l
s
en
te
n
ce
s
[
2
7
]
.
Vale
n
ce
aw
ar
e
d
ictio
n
ar
y
an
d
s
e
n
ti
m
en
t
r
ea
s
o
n
er
(
VA
DE
R
)
an
d
T
ex
tB
lo
b
r
eq
u
ir
e
tr
an
s
latio
n
in
to
E
n
g
lis
h
,
w
h
ich
m
a
y
r
esu
lt
in
th
e
lo
s
s
o
f
t
h
e
o
r
ig
i
n
al
m
ea
n
in
g
[
2
8
]
.
I
n
d
o
B
E
R
T
w
as
u
s
ed
i
n
th
is
s
t
u
d
y
to
au
to
m
atica
l
l
y
lab
el
s
e
n
ti
m
e
n
ts
,
cr
ea
ti
n
g
th
r
ee
clas
s
es
:
n
eg
a
tiv
e
,
n
eu
tr
al,
a
n
d
p
o
s
itiv
e.
Af
ter
t
h
e
lab
elin
g
p
r
o
ce
s
s
,
a
to
tal
o
f
1
7
,
1
5
2
tex
t
en
tr
ies
w
er
e
o
b
ta
in
ed
,
co
n
s
i
s
ti
n
g
o
f
1
2
,
2
7
6
(
7
1
.
6
%)
n
eg
ati
v
e,
2
,
9
4
6
(
1
7
.
2
%)
n
eu
tr
al,
an
d
1
,
9
3
0
(
1
1
.
2
%)
p
o
s
itiv
e
s
e
n
ti
m
en
ts
.
T
h
e
r
es
u
lt
in
g
lab
eled
d
ataset
w
as t
h
e
n
u
s
ed
to
tr
ain
th
e
L
ST
M
m
o
d
el.
2
.
2
.
3
.
Resa
m
p
lin
g
T
h
e
d
ataset
g
en
er
ated
f
r
o
m
th
e
I
n
d
o
B
E
R
T
-
b
ased
lab
elin
g
p
r
o
ce
s
s
w
a
s
f
u
r
t
h
er
r
ef
i
n
e
d
th
r
o
u
g
h
u
n
d
er
s
a
m
p
li
n
g
u
s
in
g
t
h
e
r
an
d
o
m
u
n
d
er
s
a
m
p
ler
tech
n
iq
u
e
to
r
ed
u
ce
class
i
m
b
ala
n
ce
an
d
m
in
i
m
ize
m
o
d
e
l
b
ias
to
w
ar
d
th
e
m
aj
o
r
it
y
class
[
29
]
.
A
f
ter
th
e
u
n
d
er
s
a
m
p
li
n
g
p
r
o
ce
s
s
,
th
e
d
ataset
co
n
s
i
s
te
d
o
f
9
,
2
9
5
en
tr
ies,
w
it
h
clas
s
d
is
tr
ib
u
tio
n
s
o
f
4
,
4
1
9
(
4
7
.
5
%)
n
eg
ati
v
e,
2
,
9
4
6
(
3
1
.
7
%)
n
eu
tr
al,
an
d
1
,
9
3
0
(
2
0
.
8
%)
p
o
s
itiv
e
s
en
ti
m
e
n
ts
.
T
h
e
d
is
tr
ib
u
t
io
n
r
esu
lt
s
af
ter
r
esa
m
p
li
n
g
ar
e
s
h
o
w
n
i
n
Fi
g
u
r
e
2
.
Fig
u
r
e
2
.
C
lass
d
is
tr
ib
u
tio
n
co
m
p
ar
i
s
o
n
b
ef
o
r
e
an
d
a
f
ter
u
n
d
er
s
a
m
p
li
n
g
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
E
va
lu
a
tin
g
le
a
r
n
in
g
r
a
te
effec
ts
o
n
lo
n
g
s
h
o
r
t
-
term me
mo
r
y
fo
r
I
n
d
o
n
esia
n
…
(
S
erly E
ld
in
a
)
567
T
h
e
d
ataset
w
as
s
tr
ati
f
ied
in
t
o
9
0
%
f
o
r
tr
ain
in
g
(
8
,
3
6
5
en
tr
ies)
an
d
1
0
%
f
o
r
test
in
g
(
9
3
0
en
tr
ies),
en
s
u
r
in
g
t
h
at
clas
s
p
r
o
p
o
r
tio
n
s
r
e
m
ai
n
ed
b
ala
n
ce
d
ac
r
o
s
s
s
u
b
s
ets.
A
s
tr
atif
ied
1
0
-
f
o
ld
cr
o
s
s
-
v
alid
atio
n
w
a
s
th
en
ap
p
lied
to
th
e
tr
ain
i
n
g
s
et.
E
ac
h
f
o
ld
p
r
o
d
u
ce
d
tr
ain
in
g
an
d
v
al
id
atio
n
s
u
b
s
ets
w
it
h
b
alan
ce
d
class
d
is
tr
ib
u
tio
n
s
,
en
ab
lin
g
a
co
m
p
r
eh
en
s
i
v
e
m
o
d
el
ev
al
u
atio
n
an
d
en
s
u
r
i
n
g
m
o
r
e
r
eliab
le
an
d
r
ep
r
esen
tativ
e
r
esu
lt
s
[
1
6
]
.
2
.
2
.
4
.
Sp
litt
ing
d
a
t
a
T
h
e
d
ataset
u
s
ed
in
th
is
s
t
u
d
y
co
n
s
is
ted
o
f
9
,
2
9
5
en
tr
ies,
d
iv
id
ed
in
to
a
tr
ain
in
g
s
et
c
o
m
p
r
i
s
in
g
8
9
.
9
9
%
(
8
,
3
6
5
en
tr
ies)
an
d
a
test
in
g
s
et
co
m
p
r
is
i
n
g
1
0
.
0
1
%
(
9
3
0
en
tr
ies).
T
h
e
tr
ain
i
n
g
d
ata
w
er
e
s
u
b
s
eq
u
en
t
l
y
p
ar
titi
o
n
ed
u
s
i
n
g
s
tr
atif
ied
1
0
-
f
o
ld
cr
o
s
s
-
v
ali
d
atio
n
,
w
it
h
9
0
%
(
7
,
5
2
8
en
tr
ies)
u
s
ed
f
o
r
tr
ai
n
in
g
an
d
1
0
% (
8
3
7
en
tr
ies)
f
o
r
v
ali
d
atio
n
in
ea
ch
f
o
ld
d
u
r
in
g
m
o
d
el
tr
ain
in
g
[
30
].
2
.
2
.
5
.
F
ea
t
ure
ex
t
ra
c
t
io
n
Featu
r
e
e
x
tr
ac
tio
n
w
as
co
n
d
u
cted
to
co
n
v
er
t
te
x
t
u
al
d
ata
i
n
to
n
u
m
er
ical
r
ep
r
ese
n
tatio
n
s
s
u
itab
le
f
o
r
p
r
o
ce
s
s
in
g
b
y
t
h
e
clas
s
i
f
icati
o
n
alg
o
r
it
h
m
[
3
1
]
.
T
h
is
p
r
o
ce
s
s
i
n
v
o
l
v
ed
to
k
e
n
izatio
n
,
in
w
h
ic
h
t
h
e
te
x
t
w
as
tr
an
s
f
o
r
m
ed
in
to
in
teg
er
s
eq
u
en
ce
s
u
s
i
n
g
t
h
e
Ker
as
T
o
k
en
izer
[
3
2
]
,
an
d
p
ad
d
in
g
,
w
h
ic
h
s
ta
n
d
ar
d
ized
th
e
in
p
u
t
len
g
t
h
b
y
tr
u
n
ca
ti
n
g
te
x
ts
t
h
at
e
x
ce
ed
e
d
th
e
m
a
x
i
m
u
m
le
n
g
th
o
r
ap
p
en
d
in
g
ze
r
o
s
t
o
s
h
o
r
ter
s
eq
u
e
n
ce
s
[3
3
]
.
T
h
e
ca
teg
o
r
ical
s
en
ti
m
e
n
t
lab
els
w
er
e
m
ap
p
ed
in
to
th
r
ee
class
es
a
n
d
en
co
d
ed
u
s
in
g
o
n
e
-
h
o
t
en
co
d
in
g
.
T
h
e
f
ea
tu
r
e
ex
tr
ac
tio
n
p
r
o
ce
s
s
is
illu
s
tr
ated
s
ch
e
m
at
icall
y
,
a
s
s
h
o
w
n
i
n
Fi
g
u
r
e
3
.
F
ig
u
r
e
3
.
I
llu
s
tr
atio
n
o
f
th
e
f
ea
tu
r
e
ex
tr
ac
tio
n
p
r
o
ce
s
s
2
.
3
.
T
ra
ini
ng
w
it
h
lo
ng
s
ho
rt
-
t
er
m
m
e
m
o
ry
T
h
e
L
ST
M
alg
o
r
it
h
m
f
o
r
s
en
ti
m
e
n
t
an
al
y
s
is
w
as
t
r
ain
ed
u
s
in
g
s
p
ec
if
ic
h
y
p
e
r
p
ar
am
eter
co
n
f
i
g
u
r
atio
n
s
,
w
it
h
a
p
r
i
m
a
r
y
f
o
cu
s
o
n
o
p
ti
m
izi
n
g
t
h
e
lear
n
in
g
r
ate
to
en
s
u
r
e
tr
ain
in
g
s
tab
ilit
y
.
T
h
e
ev
alu
a
ted
lear
n
i
n
g
r
ate
v
al
u
e
s
w
er
e
0
.
0
0
0
1
,
0
.
0
0
1
,
0
.
0
0
2
,
0
.
0
0
5
,
0
.
0
1
,
an
d
0
.
0
2
.
Du
r
in
g
tr
ain
in
g
,
an
ea
r
l
y
s
to
p
p
in
g
m
ec
h
a
n
is
m
w
as
e
m
p
lo
y
ed
to
ter
m
in
a
te
th
e
p
r
o
ce
s
s
w
h
en
i
m
p
r
o
v
e
m
e
n
t
s
in
v
ali
d
atio
n
p
er
f
o
r
m
a
n
ce
b
ec
am
e
i
n
s
ig
n
i
f
i
ca
n
t,
th
er
eb
y
p
r
ev
en
ti
n
g
o
v
er
f
it
tin
g
a
n
d
ac
ce
ler
atin
g
co
n
v
er
g
en
ce
[
3
4
]
.
T
h
e
L
ST
M
m
o
d
el
w
as
i
m
p
le
m
en
ted
u
s
i
n
g
th
e
Ker
a
s
lib
r
ar
y
i
n
P
y
th
o
n
[
3
5
]
.
T
h
e
m
o
d
el
co
n
f
i
g
u
r
atio
n
i
n
t
h
is
s
t
u
d
y
co
n
s
i
s
ted
o
f
a
6
4
-
d
i
m
e
n
s
io
n
al
e
m
b
ed
d
i
n
g
,
a
n
L
ST
M
la
y
er
with
3
2
u
n
it
s
,
an
d
a
d
en
s
e
la
y
er
w
it
h
3
o
u
tp
u
t
u
n
it
s
,
alo
n
g
w
it
h
a
d
r
o
p
o
u
t
r
ate
s
e
t
to
0
.
2
an
d
a
b
atch
s
ize
o
f
3
2
.
T
h
is
co
n
f
ig
u
r
atio
n
w
a
s
ad
ap
ted
f
r
o
m
p
r
ev
io
u
s
s
t
u
d
ies,
in
w
h
ic
h
an
e
m
b
ed
d
in
g
s
ize
o
f
6
4
an
d
a
d
r
o
p
o
u
t
r
ate
o
f
0
.
2
w
er
e
f
o
u
n
d
ef
f
ec
tiv
e
f
o
r
s
en
ti
m
e
n
t
an
a
l
y
s
is
tas
k
s
[
3
6
]
,
w
h
ile
t
h
e
u
s
e
o
f
3
2
L
ST
M
u
n
it
s
f
o
llo
w
ed
a
h
y
b
r
id
ar
ch
itect
u
r
e
ap
p
lied
to
h
o
tel
r
ev
ie
w
s
en
ti
m
en
t
an
al
y
s
i
s
[
3
7
]
.
A
b
atch
s
ize
o
f
3
2
w
a
s
co
n
s
is
ten
t
l
y
ad
o
p
ted
in
b
o
th
p
r
io
r
s
tu
d
ie
s
.
2
.
4
.
T
esting
T
h
e
test
in
g
d
at
a
s
et
w
a
s
r
eser
v
ed
ex
clu
s
i
v
el
y
f
o
r
e
v
al
u
ati
n
g
th
e
f
i
n
al
p
er
f
o
r
m
a
n
ce
o
f
t
h
e
m
o
d
el
an
d
w
a
s
n
o
t
u
s
ed
d
u
r
i
n
g
th
e
tr
ai
n
in
g
o
r
v
alid
atio
n
p
h
ases
to
p
r
ev
en
t
b
ias
[
3
8
]
.
T
h
e
ev
alu
at
io
n
w
as
co
n
d
u
cted
ac
r
o
s
s
t
w
o
d
o
m
ai
n
s
u
s
in
g
a
co
n
f
u
s
io
n
m
a
tr
ix
:
i
n
-
d
o
m
ai
n
,
w
h
ic
h
in
cl
u
d
es
9
3
0
test
s
a
m
p
les
f
r
o
m
Sire
k
ap
ap
p
licatio
n
r
ev
ie
w
s
o
n
t
h
e
Go
o
g
le
P
lay
Sto
r
e
(
4
4
2
n
eg
ativ
e,
2
9
5
n
eu
tr
al,
an
d
1
9
3
p
o
s
itiv
e)
,
an
d
cr
o
s
s
-
d
o
m
ai
n
,
w
h
ich
i
n
cl
u
d
es 1
0
0
n
e
w
s
h
ea
d
li
n
es r
elate
d
to
th
e
M
B
G
(
3
0
n
eg
ativ
e,
4
0
n
eu
tr
al,
a
n
d
3
0
p
o
s
itiv
e)
.
2
.
5
.
M
ea
s
ure
m
e
nt
Mo
d
el
ev
alu
atio
n
w
as
c
o
n
d
u
c
ted
th
r
o
u
g
h
cr
o
s
s
-
v
alid
atio
n
o
n
t
h
e
tr
ain
in
g
d
ata,
f
o
llo
w
ed
b
y
a
o
n
e
-
w
a
y
ANOV
A
test
to
d
eter
m
i
n
e
th
e
s
i
g
n
i
f
ica
n
ce
o
f
p
er
f
o
r
m
an
ce
d
if
f
er
e
n
ce
s
a
m
o
n
g
v
a
r
io
u
s
lear
n
in
g
r
ate
co
n
f
i
g
u
r
atio
n
s
.
A
p
o
s
t
-
h
o
c
test
w
a
s
s
u
b
s
eq
u
en
tl
y
ap
p
lied
t
o
f
u
r
th
er
ex
a
m
in
e
p
air
w
i
s
e
d
if
f
er
en
ce
s
[
39
]
.
T
o
v
alid
ate
th
e
s
tati
s
tical
r
es
u
lts
,
a
f
in
al
e
v
al
u
atio
n
w
a
s
co
n
d
u
cted
o
n
th
e
test
i
n
g
d
ataset
u
n
d
er
t
w
o
s
ce
n
ar
io
s
:
co
m
m
e
n
t
s
f
r
o
m
th
e
Sire
k
ap
ap
p
licatio
n
o
n
th
e
Go
o
g
le
P
la
y
S
to
r
e
an
d
n
e
w
s
h
ea
d
lin
e
s
r
elate
d
to
th
e
MBG
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
ele
co
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
24
,
No
.
2
,
A
p
r
il
20
26
:
56
4
-
57
3
568
p
r
o
g
r
am
.
T
h
e
r
ep
r
ese
n
ta
tiv
e
m
o
d
el
w
it
h
t
h
e
b
est
p
er
f
o
r
m
an
ce
f
r
o
m
ea
c
h
lear
n
i
n
g
r
ate
co
n
f
i
g
u
r
atio
n
w
a
s
s
elec
ted
b
ased
o
n
th
e
o
p
ti
m
al
f
o
ld
.
Mo
d
el
p
e
r
f
o
r
m
a
n
ce
w
a
s
m
ea
s
u
r
ed
u
s
i
n
g
s
ta
n
d
ar
d
class
i
f
icatio
n
m
etr
ic
s
d
er
iv
ed
f
r
o
m
th
e
co
n
f
u
s
io
n
m
atr
ix
,
in
cl
u
d
i
n
g
ac
c
u
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
-
s
co
r
e.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
3
.
1
.
E
x
peri
m
ent
a
l r
esu
lt
s
a
n
d a
na
ly
s
is
T
h
e
ex
p
er
im
e
n
t
s
w
er
e
co
n
d
u
c
ted
o
n
a
tex
t
class
i
f
icat
io
n
tas
k
u
s
in
g
a
L
ST
M
ar
ch
itectu
r
e
o
p
tim
ized
w
it
h
th
e
A
d
a
m
o
p
ti
m
izer
.
An
ea
r
l
y
s
to
p
p
in
g
m
ec
h
a
n
i
s
m
w
it
h
a
p
atien
ce
o
f
t
h
r
ee
ep
o
ch
s
w
a
s
ap
p
lied
to
p
r
ev
en
t
o
v
er
f
itti
n
g
[
3
4
]
.
T
r
ain
in
g
w
a
s
h
a
lted
w
h
e
n
n
o
i
m
p
r
o
v
e
m
e
n
t
i
n
v
alid
atio
n
p
er
f
o
r
m
an
ce
w
a
s
o
b
s
er
v
ed
f
o
r
th
r
ee
co
n
s
ec
u
tiv
e
ep
o
ch
s
,
an
d
th
e
b
es
t
-
p
er
f
o
r
m
i
n
g
m
o
d
e
l
w
a
s
s
e
lecte
d
b
ased
o
n
t
h
e
lo
w
e
s
t
v
alid
atio
n
lo
s
s
be
f
o
r
e
r
ea
ch
in
g
th
e
p
atie
n
ce
t
h
r
es
h
o
ld
.
Fig
u
r
e
4
s
h
o
w
s
t
h
e
v
alid
atio
n
lo
s
s
cu
r
v
e
o
f
t
h
e
m
o
d
el
ac
h
iev
i
n
g
t
h
e
h
ig
h
e
s
t
v
alid
atio
n
ac
c
u
r
ac
y
,
p
r
esen
ted
as
a
r
ep
r
esen
tati
v
e
e
x
a
m
p
le
s
i
n
ce
al
l
f
o
ld
s
ex
h
ib
it
s
i
m
ilar
p
atter
n
s
.
T
h
e
r
ed
d
ash
-
d
o
t
li
n
e
in
d
ica
te
s
t
h
e
s
elec
ted
m
o
d
el
p
r
io
r
to
th
e
o
n
s
et
o
f
i
n
cr
ea
s
i
n
g
lo
s
s
,
illu
s
tr
atin
g
t
h
e
lo
s
s
b
eh
av
io
r
b
ef
o
r
e
p
o
ten
tial o
v
er
f
itti
n
g
.
(
a)
(
b
)
(
c)
(
d
)
(
e)
(
f
)
Fig
u
r
e
4
.
R
ep
r
esen
tati
v
e
lo
s
s
h
is
to
r
y
f
o
r
s
elec
ted
lear
n
i
n
g
r
ates
: (
a)
0
.
0
0
0
1
,
(
b
)
0
.
0
0
1
,
(
c
)
0
.
0
0
2
,
(
d
)
0
.
0
0
5
,
(
e)
0
.
0
1
,
an
d
(
f
)
0
.
0
2
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
E
va
lu
a
tin
g
le
a
r
n
in
g
r
a
te
effec
ts
o
n
lo
n
g
s
h
o
r
t
-
term me
mo
r
y
fo
r
I
n
d
o
n
esia
n
…
(
S
erly E
ld
in
a
)
569
B
ased
o
n
th
e
lo
s
s
c
u
r
v
e
s
s
h
o
w
n
i
n
F
ig
u
r
e
4
,
th
e
m
o
d
el
with
t
h
e
s
m
a
lles
t
lear
n
i
n
g
r
ate
(
0
.
0
0
0
1
)
r
eq
u
ir
ed
m
o
r
e
ep
o
ch
s
to
r
ea
ch
co
n
v
er
g
e
n
ce
d
u
e
to
th
e
li
m
ited
n
u
m
b
er
o
f
w
ei
g
h
t
u
p
d
ates,
r
esu
lti
n
g
in
a
s
lo
w
e
r
,
m
o
r
e
s
tab
le
o
p
ti
m
izatio
n
p
r
o
ce
s
s
.
I
n
co
n
tr
ast,
h
ig
h
er
lear
n
i
n
g
r
ates
(
0
.
0
0
1
–
0
.
0
2
)
ac
ce
ler
ated
th
e
r
ed
u
ctio
n
o
f
tr
ain
i
n
g
lo
s
s
an
d
ca
u
s
ed
an
ea
r
lier
in
cr
ea
s
e
in
v
alid
atio
n
lo
s
s
,
in
d
icati
n
g
t
h
e
o
n
s
et
o
f
o
v
er
f
itti
n
g
.
T
h
ese
co
n
f
i
g
u
r
atio
n
s
ac
h
ie
v
ed
th
eir
b
est
p
er
f
o
r
m
a
n
ce
in
f
e
w
er
ep
o
ch
s
,
ex
h
ib
iti
n
g
f
aster
,
less
s
tab
l
e
co
n
v
er
g
e
n
ce
p
atter
n
s
.
I
n
F
ig
u
r
e
4
(
a)
co
r
r
esp
o
n
d
s
to
0
.
0
0
0
1
,
w
h
ile
F
ig
u
r
es
4
(
b
)
to
(
f
)
r
ep
r
esen
t
lear
n
i
n
g
r
ate
s
o
f
0
.
0
0
1
,
0
.
0
0
2
,
0
.
0
0
5
,
0
.
0
1
,
a
n
d
0
.
0
2
,
r
esp
ec
tiv
el
y
.
T
h
e
r
esu
lts
s
h
o
w
n
in
F
ig
u
r
e
5
in
d
icate
th
at
a
lear
n
i
n
g
r
ate
o
f
0
.
0
0
1
p
r
o
v
id
es
th
e
b
e
s
t
o
v
er
all
p
er
f
o
r
m
a
n
ce
,
w
it
h
h
ig
h
ac
cu
r
ac
y
,
lo
w
v
ar
ian
ce
,
a
n
d
co
n
s
is
ten
t
r
es
u
lts
ac
r
o
s
s
f
o
ld
s
.
T
h
is
lear
n
in
g
r
ate
also
co
n
v
er
g
e
s
f
aster
th
a
n
0
.
0
0
0
1
w
h
ile
m
ai
n
tai
n
i
n
g
s
i
m
i
lar
ac
c
u
r
ac
y
lev
el
s
,
d
e
m
o
n
s
tr
ati
n
g
a
n
o
p
ti
m
a
l
b
alan
ce
b
et
w
ee
n
tr
ain
in
g
s
tab
il
it
y
a
n
d
c
o
n
v
er
g
e
n
ce
s
p
ee
d
.
A
lt
h
o
u
g
h
th
e
d
ata
s
et
an
d
m
o
d
el
ar
ch
i
tectu
r
e
d
if
f
er
[
1
0
]
,
th
e
f
i
n
d
in
g
s
co
n
s
i
s
te
n
tl
y
in
d
i
ca
te
th
at
a
m
o
d
er
ate
lear
n
in
g
r
ate
i
m
p
r
o
v
es
co
n
v
er
g
en
ce
an
d
en
h
a
n
ce
s
t
h
e
m
o
d
el
’
s
lear
n
i
n
g
ca
p
ab
il
it
y
.
B
ased
o
n
th
e
v
alid
atio
n
tr
ain
i
n
g
r
e
s
u
l
ts
,
to
as
s
e
s
s
t
h
e
s
ta
tis
tical
s
i
g
n
if
ican
ce
o
f
p
er
f
o
r
m
a
n
ce
d
if
f
er
en
ce
s
a
m
o
n
g
lear
n
i
n
g
r
ates,
a
o
n
e
-
w
a
y
A
N
OV
A
w
a
s
co
n
d
u
cted
u
s
i
n
g
th
e
1
0
-
f
o
ld
cr
o
s
s
-
v
alid
atio
n
r
es
u
lts
,
w
it
h
ac
cu
r
a
c
y
v
al
u
es
av
er
a
g
ed
ac
r
o
s
s
f
o
ld
s
.
A
s
s
u
m
p
tio
n
tes
ts
co
n
f
ir
m
e
d
th
at
th
e
d
ata
w
er
e
n
o
r
m
all
y
d
i
s
tr
ib
u
ted
(
S
h
ap
ir
o
-
W
ilk
W
=
0
.
9
6
1
4
,
=
0
.
0
5
5
3
)
an
d
h
ad
h
o
m
o
g
en
eo
u
s
v
ar
ia
n
ce
s
(
=
1
.
3639
,
=
0
.
2
5
2
4
)
.
Fig
u
r
e
5
.
C
o
m
p
ar
is
o
n
o
f
lear
n
in
g
r
ate
s
u
s
in
g
s
tr
atif
ied
1
0
-
f
o
ld
cr
o
s
s
-
v
a
lid
ati
on
T
h
e
A
NOV
A
r
es
u
lt
s
s
h
o
w
ed
a
s
ig
n
if
ican
t
e
f
f
ec
t
o
f
lear
n
i
n
g
r
ate
o
n
m
o
d
el
ac
c
u
r
ac
y
(
(
5
,
54
)
=
5
.
1989
,
=
0
.
000575
,
²
=
0
.
3250
)
,
w
ith
eta
s
q
u
ar
ed
i
n
d
icati
n
g
a
lar
g
e
e
f
f
ec
t
s
ize,
s
u
g
g
e
s
ti
n
g
s
tati
s
ticall
y
s
ig
n
i
f
ica
n
t
d
if
f
er
e
n
ce
s
a
m
o
n
g
lear
n
in
g
r
ate
co
n
f
i
g
u
r
atio
n
s
.
T
h
e
u
s
e
o
f
o
n
e
-
w
a
y
ANOV
A
is
co
n
s
is
te
n
t
w
i
t
h
p
r
ev
io
u
s
s
tu
d
ie
s
w
h
ich
a
ls
o
ass
es
s
ed
s
i
g
n
if
ican
ce
(
<
0
.
05
)
[
1
7
]
,
[
39
]
.
Fu
r
th
er
m
o
r
e,
th
e
d
escr
ip
tiv
e
s
tatis
t
ics
o
f
m
o
d
el
p
er
f
o
r
m
an
ce
ac
r
o
s
s
th
e
test
ed
lear
n
in
g
r
ates
ar
e
s
u
m
m
ar
ized
i
n
T
ab
l
e
1
.
A
s
s
h
o
w
n
,
t
h
e
lo
w
er
lear
n
in
g
r
ates
(
0
.
0
0
0
1
an
d
0
.
0
0
1
)
y
ield
ed
th
e
h
i
g
h
e
s
t
m
ea
n
v
alid
atio
n
ac
cu
r
ac
y
w
it
h
r
elati
v
el
y
lo
w
v
ar
ian
ce
,
i
n
d
icati
n
g
s
tab
le
m
o
d
el
b
eh
av
io
r
.
I
n
co
n
tr
a
s
t,
h
i
g
h
er
lear
n
i
n
g
r
ates
(
≥
0
.
0
1
)
r
esu
lted
i
n
d
ec
r
ea
s
ed
ac
cu
r
ac
y
.
T
ab
le
1
.
Descr
ip
tiv
e
s
tat
is
tic
s
o
f
v
alid
atio
n
r
esu
l
ts
ac
r
o
s
s
v
a
r
io
u
s
lear
n
i
n
g
r
ates
L
e
a
r
n
i
n
g
r
a
t
e
M
e
a
n
S
t
d
d
ev
M
i
n
M
a
x
0
.
0
0
0
1
0
.
8
0
4
1
0
.
0
1
2
7
0
.
7
8
8
3
0
.
8
2
6
8
0
.
0
0
1
0
.
8
0
4
2
0
.
0
1
2
0
0
.
7
8
9
5
0
.
8
2
8
0
0
.
0
0
2
0
.
7
9
7
4
0
.
0
1
3
3
0
.
7
8
1
1
0
.
8
2
0
8
0
.
0
0
5
0
.
7
9
6
2
0
.
0
1
0
5
0
.
7
7
8
7
0
.
8
0
7
6
0
.
0
1
0
.
7
8
7
4
0
.
0
2
0
8
0
.
7
6
5
6
0
.
8
2
3
2
0
.
0
2
0
.
7
7
9
7
0
.
0
0
7
2
0
.
7
7
0
3
0
.
7
9
2
1
T
h
e
p
o
s
t
-
h
o
c
an
al
y
s
i
s
[
1
8
]
r
e
v
ea
led
th
at
s
ig
n
i
f
ica
n
t
d
if
f
er
e
n
ce
s
i
n
m
o
d
el
ac
cu
r
ac
y
w
er
e
f
o
u
n
d
o
n
l
y
f
o
r
th
e
h
i
g
h
est
lear
n
i
n
g
r
ate
(
0
.
0
2
)
c
o
m
p
ar
ed
w
it
h
0
.
0
0
0
1
,
0
.
0
0
1
,
an
d
0
.
0
0
2
.
T
ab
le
2
s
u
m
m
ar
izes
th
e
s
e
co
m
p
a
r
is
o
n
s
,
w
h
ile
th
e
r
e
m
a
i
n
in
g
p
air
w
is
e
co
m
p
ar
is
o
n
s
d
id
n
o
t
s
h
o
w
s
i
g
n
i
f
ica
n
t
d
if
f
er
en
c
es
at
a
s
ig
n
i
f
ica
n
ce
lev
el
o
f
=
0
.
0
5
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
ele
co
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
24
,
No
.
2
,
A
p
r
il
20
26
:
56
4
-
57
3
570
T
ab
le
2
.
P
o
s
t
-
h
o
c
an
al
y
s
i
s
o
f
d
if
f
er
e
n
ce
s
b
et
w
ee
n
lear
n
i
n
g
r
ates
G
r
o
u
p
1
G
r
o
u
p
2
M
e
a
n
d
i
f
f
e
r
e
n
c
e
P
-
a
d
j
L
o
w
e
r
U
p
p
e
r
S
i
g
n
i
f
i
c
a
n
t
0
.
0
0
0
1
0.
02
-
0
.
0
2
4
4
0
.
0
0
2
0
-
0
.
0
4
2
1
-
0
.
0
0
6
7
Y
e
s
0
.
0
0
1
0
.
0
2
-
0
.
0
2
4
5
0
.
0
0
1
9
-
0
.
0
4
2
2
-
0
.
0
0
6
8
Y
e
s
0
.
0
0
2
0
.
0
2
-
0
.
0
1
7
7
0
.
0
4
9
9
-
0
.
0
3
5
4
0
Y
e
s
3
.
2
.
E
v
a
lua
t
i
o
n
E
v
alu
a
tio
n
w
as
co
n
d
u
cted
to
v
alid
ate
th
e
tr
ain
i
n
g
r
esu
lt
s
u
s
in
g
t
h
e
test
d
ataset
[
3
8
]
.
L
o
w
er
lear
n
in
g
r
ates
(
0
.
0
0
0
1
an
d
0
.
0
0
1
)
ex
h
ib
ited
m
o
r
e
s
tab
le
co
n
v
er
g
e
n
ce
,
w
it
h
a
o
n
e
-
w
a
y
ANOV
A
in
d
i
ca
tin
g
a
s
ig
n
i
f
ica
n
t
ef
f
ec
t
o
n
ac
cu
r
ac
y
.
T
h
e
m
o
d
el
’
s
g
en
er
aliza
tio
n
ca
p
ab
ilit
y
w
as
f
u
r
th
er
as
s
ess
ed
t
h
r
o
u
g
h
co
n
f
u
s
io
n
m
atr
i
x
an
al
y
s
is
u
n
d
er
t
w
o
s
ce
n
ar
io
s
:
in
-
d
o
m
ai
n
an
d
cr
o
s
s
-
d
o
m
a
in
[
19
]
.
T
h
e
d
eta
iled
ev
alu
atio
n
r
esu
lt
s
ar
e
s
h
o
w
n
i
n
T
ab
le
3
.
Ta
b
le
3
.
C
lass
if
icatio
n
r
ep
o
r
t
: in
-
d
o
m
ai
n
an
d
cr
o
s
s
-
d
o
m
ai
n
D
o
mai
n
L
e
a
r
n
i
n
g
r
a
t
e
A
c
c
u
r
a
c
y
M
a
c
r
o
a
v
e
r
a
g
e
W
e
i
g
h
t
a
v
e
r
a
g
e
P
r
e
c
i
si
o
n
R
e
c
a
l
l
F1
-
s
c
o
r
e
P
r
e
c
i
si
o
n
R
e
c
a
l
l
F1
-
sco
r
e
In
-
d
o
mai
n
0
.
0
0
0
1
0
.
7
8
7
1
0
.
7
7
3
5
0
.
7
8
0
9
0
.
7
7
6
8
0
.
7
8
9
6
0
.
7
8
7
1
0
.
7
8
7
9
In
-
d
o
mai
n
0
.
0
0
1
0
.
7
8
4
9
0
.
7
7
0
1
0
.
7
8
2
7
0
.
7
7
5
3
0
.
7
8
7
8
0
.
7
8
4
9
0
.
7
8
5
6
In
-
d
o
mai
n
0
.
0
0
2
0
.
7
8
7
1
0
.
7
8
2
0
0
.
7
8
2
9
0
.
7
8
1
0
0
.
7
9
2
1
0
.
7
8
7
1
0
.
7
8
8
1
In
-
d
o
mai
n
0
.
0
0
5
0
.
7
8
1
7
0
.
7
7
2
0
0
.
7
7
4
3
0
.
7
7
3
0
0
.
7
8
1
4
0
.
7
8
1
7
0
.
7
8
1
4
In
-
d
o
ma
in
0
.
0
1
0
.
7
7
1
0
0
.
7
5
6
3
0
.
7
6
2
8
0
.
7
5
9
3
0
.
7
7
2
9
0
.
7
7
1
0
0
.
7
7
1
6
In
-
d
o
mai
n
0
.
0
2
0
.
7
7
3
1
0
.
7
6
9
3
0
.
7
6
0
3
0
.
7
6
1
9
0
.
7
7
8
9
0
.
7
7
3
1
0
.
7
7
3
5
C
r
o
ss
-
d
o
mai
n
0
.
0
0
0
1
0
.
3
3
0
0
0
.
6
5
9
7
0
.
3
6
1
1
0
.
2
1
1
2
0
.
6
6
0
4
0
.
3
3
0
0
0
.
1
9
9
4
C
r
o
ss
-
d
o
mai
n
0
.
0
0
1
0
.
3
4
0
0
0
.
7
7
0
8
0
.
3
7
2
2
0
.
2
3
2
1
0
.
7
9
3
8
0
.
3
4
0
0
0
.
2
1
8
5
C
r
o
ss
-
d
o
mai
n
0
.
0
0
2
0
.
3
3
0
0
0
.
3
0
1
5
0
.
3
5
2
8
0
.
2
5
8
1
0
.
3
0
2
6
0
.
3
3
0
0
0
.
2
5
0
2
C
r
o
ss
-
d
o
mai
n
0
.
0
0
5
0
.
3
3
0
0
0
.
6
0
5
3
0
.
3
6
1
1
0
.
2
1
1
8
0
.
5
9
4
7
0
.
3
3
0
0
0
.
1
9
9
7
C
r
o
ss
-
d
o
mai
n
0
.
0
1
0
.
3
6
0
0
0
.
6
0
7
3
0
.
3
8
6
1
0
.
2
8
6
8
0
.
5
9
6
6
0
.
3
6
0
0
0
.
2
7
8
1
C
r
o
ss
-
d
o
mai
n
0
.
0
2
0
.
3
6
0
0
0
.
5
0
1
2
0
.
3
7
2
2
0
.
3
2
53
0
.
4
8
9
5
0
.
3
6
0
0
0
.
3
2
3
1
T
h
e
r
esu
lts
s
h
o
w
t
h
at,
f
o
r
in
-
d
o
m
ai
n
d
ata,
lear
n
in
g
r
ates
o
f
0
.
0
0
0
1
,
0
.
0
0
1
,
an
d
0
.
0
0
2
ac
h
iev
ed
t
h
e
b
est
p
er
f
o
r
m
a
n
ce
,
w
it
h
ac
c
u
r
ac
ies
b
et
w
ee
n
7
8
.
4
9
%
an
d
7
8
.
7
1
%
an
d
F1
-
s
co
r
es
ar
o
u
n
d
0
.
7
8
.
T
h
ese
r
esu
lt
s
in
d
icate
a
g
o
o
d
b
alan
ce
b
et
we
en
p
r
ec
is
io
n
a
n
d
r
ec
all
u
n
d
e
r
th
e
i
m
b
ala
n
ce
d
d
ata
co
n
d
iti
o
n
.
I
n
co
n
tr
ast,
f
o
r
cr
o
s
s
-
d
o
m
ai
n
d
ata,
th
e
o
v
er
all
ac
cu
r
ac
y
d
ec
r
ea
s
ed
.
L
o
w
er
l
ea
r
n
in
g
r
ates
(
0
.
0
0
0
1
–
0
.
0
0
2
)
r
ea
ch
ed
o
n
l
y
3
3
%
–
3
4
%,
w
h
i
le
h
i
g
h
er
lear
n
in
g
r
ates
(
0
.
0
1
an
d
0
.
0
2
)
s
lig
h
tl
y
i
m
p
r
o
v
ed
ac
cu
r
ac
y
to
ab
o
u
t
3
6
%,
w
it
h
F1
-
s
co
r
es
r
an
g
i
n
g
f
r
o
m
0
.
2
7
to
0
.
3
2
.
A
lt
h
o
u
g
h
t
h
e
d
i
f
f
er
e
n
ce
s
w
er
e
n
o
t
s
u
b
s
ta
n
tial,
th
e
r
e
s
u
l
ts
s
u
g
g
e
s
t
t
h
at
h
i
g
h
er
lear
n
in
g
r
ates
p
r
o
v
id
e
s
li
g
h
tl
y
b
etter
g
en
er
aliza
t
io
n
to
o
th
er
d
o
m
ai
n
s
,
w
h
ile
lo
w
er
lear
n
in
g
r
ates
p
er
f
o
r
m
b
etter
f
o
r
i
n
-
d
o
m
ai
n
d
ata.
T
h
i
s
d
if
f
er
e
n
ce
in
d
icate
s
t
h
e
m
o
d
el
’
s
li
m
ited
g
e
n
er
aliza
tio
n
ab
i
lit
y
,
w
h
ic
h
m
a
y
b
e
af
f
ec
ted
b
y
t
h
e
d
is
ti
n
ct
c
h
ar
ac
ter
is
tics
o
f
t
h
e
d
ataset
s
:
u
s
e
r
co
m
m
e
n
ts
ar
e
t
y
p
icall
y
i
n
f
o
r
m
al
a
n
d
co
n
tex
t
-
d
ep
en
d
en
t,
w
h
er
ea
s
n
e
w
s
ti
tle
s
ten
d
to
b
e
m
o
r
e
f
o
r
m
al
an
d
t
o
p
ic
-
f
o
cu
s
ed
.
3
.
3
.
P
er
f
o
rm
a
nce
T
h
e
m
o
d
el
p
er
f
o
r
m
a
n
ce
f
o
r
d
if
f
er
en
t
lear
n
i
n
g
r
ates
is
s
h
o
w
n
i
n
T
ab
les
4
an
d
5
.
Du
r
in
g
th
e
ex
p
er
i
m
e
n
ts
,
th
e
tr
ain
i
n
g
ti
m
e
w
a
s
r
ec
o
r
d
ed
u
s
i
n
g
t
h
e
P
y
th
o
n
ti
m
e
m
o
d
u
le,
a
n
d
m
e
m
o
r
y
u
s
a
g
e
w
a
s
m
o
n
ito
r
ed
t
h
r
o
u
g
h
th
e
p
s
u
til
l
ib
r
ar
y
i
n
Go
o
g
le
C
o
lab
o
r
ato
r
y
.
T
h
e
f
i
n
d
in
g
s
r
ev
ea
l
th
at
a
lea
r
n
in
g
r
ate
o
f
0
.
0
0
2
p
r
o
v
id
ed
th
e
m
o
s
t
ef
f
icie
n
t
tr
ain
i
n
g
ti
m
e,
w
h
ile
a
lear
n
i
n
g
r
ate
o
f
0
.
0
0
1
ac
h
iev
ed
th
e
lo
w
e
s
t
m
e
m
o
r
y
co
n
s
u
m
p
tio
n
w
it
h
o
u
t
s
i
g
n
if
ic
an
tl
y
i
n
cr
ea
s
i
n
g
th
e
tr
ain
i
n
g
d
u
r
atio
n
.
O
v
er
al
l,
t
h
e
p
er
f
o
r
m
an
ce
ac
r
o
s
s
i
n
-
d
o
m
ai
n
a
n
d
cr
o
s
s
-
d
o
m
ai
n
d
atasets
r
e
m
ai
n
ed
r
elativ
e
l
y
c
o
n
s
is
ten
t,
w
it
h
o
n
l
y
m
i
n
o
r
v
ar
iatio
n
s
o
b
s
er
v
ed
d
esp
ite
d
if
f
er
e
n
ce
s
i
n
th
e
n
u
m
b
er
o
f
test
s
a
m
p
le
s
an
d
ev
al
u
a
tio
n
p
er
io
d
s
.
T
ab
le
4
.
A
v
er
ag
e
tr
ai
n
i
n
g
ti
m
e
an
d
m
e
m
o
r
y
u
s
ag
e
fo
r
10
-
f
o
ld
cr
o
s
s
-
v
a
lid
atio
n
L
e
a
r
n
i
n
g
r
a
t
e
A
v
e
r
a
g
e
t
i
me
(
s)
A
v
e
r
a
g
e
me
mo
r
y
(
M
B
)
0
.
0
0
0
1
2
5
9
.
5
1
3
.
3
0
.
0
0
1
8
2
.
1
5
.
3
0
.
0
0
2
6
9
.
9
1
5
.
4
0
.
0
0
5
7
8
.
1
9
.
2
0
.
0
1
7
4
.
1
5
.
2
3
0
.
0
2
6
6
.
3
1
4
.
8
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
E
va
lu
a
tin
g
le
a
r
n
in
g
r
a
te
effec
ts
o
n
lo
n
g
s
h
o
r
t
-
term me
mo
r
y
fo
r
I
n
d
o
n
esia
n
…
(
S
erly E
ld
in
a
)
571
T
ab
le
5
.
Mo
d
el
p
er
f
o
r
m
an
ce
c
o
m
p
ar
is
o
n
o
n
i
n
-
d
o
m
ain
a
n
d
cr
o
s
s
-
d
o
m
ai
n
tes
tin
g
D
a
t
a
se
t
B
e
st
f
o
l
d
L
e
a
r
n
i
n
g
r
a
t
e
T
i
me
(
s)
M
e
mo
r
y
(
M
B
)
In
-
d
o
mai
n
4
0
.
0
0
0
1
0
.
7
9
1
9
.
1
3
In
-
d
o
mai
n
2
0
.
0
0
1
0
.
7
9
0
.
3
8
In
-
d
o
mai
n
2
0
.
0
0
2
0
.
8
1
2
9
.
0
0
In
-
d
o
mai
n
1
0
.
0
0
5
0
.
7
8
6
.
2
5
In
-
d
o
mai
n
5
0
.
0
1
0
.
8
0
1
.
7
5
In
-
d
o
mai
n
2
0
.
0
2
0
.
7
8
1
8
.
6
3
C
r
o
ss
-
d
o
mai
n
4
0
.
0
0
0
1
2.
96
0
.
7
5
C
r
o
ss
-
d
o
mai
n
2
0
.
0
0
1
0
.
5
6
1
6
.
3
2
C
r
o
ss
-
d
o
mai
n
2
0
.
0
0
2
0
.
5
4
9
.
8
8
C
r
o
ss
-
d
o
mai
n
1
0
.
0
0
5
0
.
5
4
0
.
2
5
C
r
o
ss
-
d
o
mai
n
5
0
.
0
1
0
.
5
2
1
2
.
0
1
C
r
o
ss
-
d
o
mai
n
2
0
.
0
2
0
.
5
2
6
.
3
8
4.
CO
NCLU
SI
O
N
T
h
is
s
tu
d
y
a
n
al
y
ze
d
th
e
ef
f
ec
t
o
f
lear
n
in
g
r
ate
v
ar
iatio
n
s
o
n
th
e
s
tab
il
i
t
y
a
n
d
ac
cu
r
ac
y
o
f
L
ST
M
-
b
ased
tex
t
c
lass
if
ica
tio
n
m
o
d
els
u
s
in
g
th
e
A
d
a
m
o
p
ti
m
i
ze
r
.
T
h
e
r
esu
lts
d
e
m
o
n
s
tr
ate
th
at
lear
n
i
n
g
r
ate
s
ig
n
i
f
ica
n
tl
y
i
n
f
l
u
en
ce
s
m
o
d
el
p
er
f
o
r
m
a
n
ce
.
B
ased
o
n
1
0
-
f
o
ld
cr
o
s
s
-
v
alid
atio
n
an
d
a
o
n
e
-
w
a
y
ANOV
A
tes
t,
s
ig
n
i
f
ica
n
t
d
i
f
f
er
e
n
ce
s
w
e
r
e
o
b
s
er
v
ed
a
m
o
n
g
lear
n
i
n
g
r
ates,
w
ith
p
o
s
t
-
h
o
c
an
al
y
s
is
in
d
ica
tin
g
t
h
at
a
lear
n
i
n
g
r
ate
o
f
0
.
0
2
d
if
f
er
ed
s
i
g
n
if
ica
n
tl
y
f
r
o
m
0
.
0
0
0
1
,
0
.
0
0
1
,
an
d
0
.
0
0
2
.
A
n
a
l
y
s
is
o
f
t
h
e
tr
ai
n
i
n
g
a
n
d
v
al
id
atio
n
lo
s
s
cu
r
v
e
s
s
h
o
w
ed
th
at
a
lear
n
i
n
g
r
ate
o
f
0
.
0
0
0
1
p
r
o
d
u
ce
d
th
e
m
o
s
t
s
tab
le
co
n
v
er
g
en
ce
,
al
b
eit
r
eq
u
ir
in
g
m
o
r
e
ep
o
ch
s
.
L
ea
r
n
i
n
g
r
ates
o
f
0
.
0
0
0
1
an
d
0
.
0
0
2
ac
h
iev
ed
t
h
e
h
ig
h
e
s
t
i
n
-
d
o
m
ai
n
ac
cu
r
ac
y
o
f
7
8
.
7
1
%,
w
h
ile
a
lear
n
in
g
r
ate
o
f
0
.
0
0
1
p
r
o
v
id
e
d
an
o
p
ti
m
al
b
alan
ce
b
et
w
ee
n
s
tab
ilit
y
a
n
d
tr
ain
in
g
ef
f
icie
n
c
y
,
r
ea
ch
in
g
7
8
.
4
9
%
in
-
d
o
m
ai
n
ac
cu
r
ac
y
.
Hig
h
er
lear
n
in
g
r
ates
(
0
.
0
1
–
0
.
0
2
)
d
em
o
n
s
tr
ated
b
etter
ad
ap
ta
b
ilit
y
to
cr
o
s
s
-
d
o
m
ai
n
d
ata,
ac
h
iev
in
g
3
6
%
ac
cu
r
ac
y
,
i
n
d
i
ca
tin
g
p
o
ten
tial
f
o
r
i
m
p
r
o
v
i
n
g
g
en
er
aliza
t
io
n
d
esp
ite
lo
w
er
ab
s
o
lu
te
ac
cu
r
ac
y
.
T
h
er
ef
o
r
e,
a
lear
n
in
g
r
ate
o
f
0
.
0
0
1
is
r
ec
o
m
m
en
d
ed
f
o
r
ac
h
iev
in
g
b
o
th
h
ig
h
ac
cu
r
ac
y
a
n
d
ef
f
icie
n
t
tr
ain
i
n
g
,
w
h
er
ea
s
0
.
0
0
0
1
is
p
r
ef
er
ab
le
w
h
e
n
tr
ain
i
n
g
s
tab
ilit
y
is
p
r
io
r
itized
.
Hig
h
er
lear
n
in
g
r
ates
(
0
.
0
1
–
0
.
0
2
)
ca
n
b
e
lev
e
r
ag
ed
to
en
h
a
n
ce
ad
ap
tab
ilit
y
o
n
cr
o
s
s
-
d
o
m
ai
n
d
ata.
T
h
ese
f
in
d
i
n
g
s
p
r
o
v
id
e
p
r
ac
tica
l
g
u
id
a
n
ce
f
o
r
NL
P
p
r
ac
titi
o
n
er
s
in
I
n
d
o
n
es
ia
o
n
e
f
f
ec
tiv
e
l
y
tu
n
i
n
g
lear
n
i
n
g
r
ates
f
o
r
I
n
d
o
n
e
s
ian
s
e
n
ti
m
en
t
an
al
y
s
i
s
tas
k
s
.
F
u
tu
r
e
r
esear
ch
m
a
y
e
x
p
lo
r
e
ad
ap
tiv
e
lear
n
i
n
g
r
at
e
m
ec
h
a
n
i
s
m
s
o
r
s
ch
ed
u
ler
-
b
ased
o
p
ti
m
i
za
tio
n
an
d
e
x
te
n
d
ex
p
er
i
m
e
n
ts
to
o
t
h
er
d
ee
p
lea
r
n
in
g
ar
ch
itect
u
r
es,
s
u
ch
as
b
id
ir
ec
tio
n
al
o
r
atten
tio
n
-
b
ased
L
ST
M
m
o
d
els,
to
f
u
r
t
h
er
i
m
p
r
o
v
e
cr
o
s
s
-
d
o
m
ai
n
g
en
er
aliza
tio
n
.
ACK
NO
WL
E
D
G
M
E
NT
S
W
e
ac
k
n
o
w
led
g
e
t
h
e
Dep
ar
tm
en
t
o
f
I
n
f
o
r
m
atic
s
E
n
g
i
n
ee
r
i
n
g
,
Facu
lt
y
o
f
E
n
g
in
ee
r
i
n
g
an
d
Ma
r
iti
m
e
T
ec
h
n
o
lo
g
y
,
U
n
iv
er
s
itas
Ma
r
i
ti
m
R
aj
a
A
li
Haj
i,
f
o
r
p
r
o
v
id
in
g
t
h
e
f
ac
ilit
ie
s
an
d
ac
ad
e
m
ic
en
v
ir
o
n
m
e
n
t
t
h
at
en
ab
led
th
e
co
m
p
letio
n
o
f
th
is
r
esear
ch
.
F
UNDIN
G
I
NF
O
R
M
AT
I
O
N
Au
t
h
o
r
s
s
tate
n
o
f
u
n
d
i
n
g
i
n
v
o
l
v
ed
.
AUTHO
R
CO
NT
RIB
UT
I
O
NS ST
A
T
E
M
E
NT
T
h
is
j
o
u
r
n
al
u
s
e
s
th
e
C
o
n
tr
ib
u
to
r
R
o
les
T
ax
o
n
o
m
y
(
C
R
ed
iT
)
to
r
ec
o
g
n
ize
in
d
i
v
id
u
al
au
th
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
t
h
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
lla
b
o
r
atio
n
.
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
Ser
l
y
E
ld
in
a
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
T
ek
ad
Ma
tu
latan
✓
✓
✓
✓
✓
✓
✓
✓
✓
No
v
r
izal
Fatta
h
Fa
h
m
itra
✓
✓
✓
✓
✓
✓
✓
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
si
s
I
:
I
n
v
e
st
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
si
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
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
ele
co
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
24
,
No
.
2
,
A
p
r
il
20
26
:
56
4
-
57
3
572
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
Au
t
h
o
r
s
s
tate
n
o
co
n
f
lic
t o
f
i
n
t
er
est.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
ata
s
u
p
p
o
r
tin
g
th
e
ex
p
er
i
m
e
n
tal
f
i
n
d
in
g
s
o
f
th
is
s
t
u
d
y
,
in
clu
d
i
n
g
th
e
m
o
d
el
r
esu
l
ts
o
n
tr
ain
i
n
g
an
d
test
d
ata
a
s
w
ell
a
s
all
r
elate
d
ex
p
er
i
m
e
n
t
g
r
ap
h
s
,
a
r
e
p
u
b
licl
y
a
v
ailab
le
i
n
t
h
e
p
r
o
j
ec
t
r
ep
o
s
ito
r
y
:
[
h
ttp
s
://
g
it
h
u
b
.
co
m
/Ser
l
y
-
E
ld
i
n
a/
L
ST
M
-
L
ea
r
n
i
n
g
R
ate
-
I
n
d
o
n
esia
-
Se
n
ti
m
e
n
t
].
RE
F
E
R
E
NC
E
S
[
1
]
T
.
Jo
se
p
h
,
“
N
a
t
u
r
a
l
l
a
n
g
u
a
g
e
p
r
o
c
e
ssi
n
g
(
N
L
P
)
f
o
r
se
n
t
i
me
n
t
a
n
a
l
y
si
s
i
n
s
o
c
i
a
l
me
d
i
a
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
C
o
m
p
u
t
i
n
g
a
n
d
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
6
,
n
o
.
2
,
p
p
.
3
5
–
4
8
,
2
0
2
4
,
d
o
i
:
1
0
.
4
7
9
4
1
/
i
j
c
e
.
2
1
3
5
.
[
2
]
J
.
Jo
se
a
n
d
R.
S
i
mr
i
t
h
a
,
“
S
e
n
t
i
me
n
t
a
n
a
l
y
si
s
a
n
d
t
o
p
i
c
c
l
a
ssi
f
i
c
a
t
i
o
n
w
i
t
h
L
S
T
M
n
e
t
w
o
r
k
s
a
n
d
T
e
x
t
R
a
z
o
r
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
D
a
t
a
I
n
f
o
rm
a
t
i
c
s
a
n
d
I
n
t
e
l
l
i
g
e
n
t
C
o
m
p
u
t
i
n
g
,
v
o
l
.
3
,
n
o
.
2
,
p
p
.
4
2
–
5
1
,
2
0
2
4
,
d
o
i
:
1
0
.
5
9
4
6
1
/
i
j
d
i
i
c
.
v
3
i
2
.
1
1
5
.
[
3
]
A
.
H
.
N
a
s
u
t
i
o
n
,
A
.
O
n
a
n
,
Y
.
M
u
r
a
k
a
mi
,
W
.
M
o
n
i
k
a
,
a
n
d
A
.
H
a
n
a
f
i
a
h
,
“
B
e
n
c
h
mar
k
i
n
g
o
p
e
n
-
so
u
r
c
e
l
a
r
g
e
l
a
n
g
u
a
g
e
mo
d
e
l
s
f
o
r
se
n
t
i
me
n
t
a
n
d
e
mo
t
i
o
n
c
l
a
ssi
f
i
c
a
t
i
o
n
i
n
I
n
d
o
n
e
si
a
n
t
w
e
e
t
s,”
I
E
EE
Ac
c
e
ss
,
v
o
l
.
1
3
,
p
p
.
9
4
0
0
9
–
9
4
0
2
5
,
2
0
2
5
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
5
.
3
5
7
4
6
2
9
.
[
4
]
S
.
H
o
c
h
r
e
i
t
e
r
a
n
d
J
.
S
c
h
mi
d
h
u
b
e
r
,
“
L
o
n
g
sh
o
r
t
-
t
e
r
m
me
mo
r
y
,
”
N
e
u
r
a
l
C
o
m
p
u
t
a
t
i
o
n
,
v
o
l
.
9
,
n
o
.
8
,
p
p
.
1
7
3
5
–
1
7
8
0
,
1
9
9
7
,
d
o
i
:
1
0
.
1
1
6
2
/
n
e
c
o
.
1
9
9
7
.
9
.
8
.
1
7
3
5
.
[
5
]
S
.
M
.
A
l
-
S
e
l
w
i
e
t
a
l
.
,
“
R
N
N
-
L
S
T
M
:
f
r
o
m
a
p
p
l
i
c
a
t
i
o
n
s
t
o
mo
d
e
l
i
n
g
t
e
c
h
n
i
q
u
e
s
a
n
d
b
e
y
o
n
d
—
sy
st
e
mat
i
c
r
e
v
i
e
w
,
”
J
o
u
rn
a
l
o
f
K
i
n
g
S
a
u
d
U
n
i
v
e
rsi
t
y
-
C
o
m
p
u
t
e
r
a
n
d
I
n
f
o
r
m
a
t
i
o
n
S
c
i
e
n
c
e
s
,
v
o
l
.
3
6
,
n
o
.
5
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
k
s
u
c
i
.
2
0
2
4
.
1
0
2
0
6
8
.
[
6
]
I
.
S
.
B
.
A
z
h
a
r
,
W
.
K
.
S
a
r
i
,
a
n
d
N
.
K
.
P
.
G
u
may
,
“
A
c
o
mp
a
r
a
t
i
v
e
st
u
d
y
o
f
d
e
e
p
l
e
a
r
n
i
n
g
’
s
p
e
r
f
o
r
man
c
e
me
t
h
o
d
s
f
o
r
n
e
w
s
a
r
t
i
c
l
e
u
si
n
g
w
o
r
d
r
e
p
r
e
se
n
t
a
t
i
o
n
s,”
S
i
st
e
m
a
s
i
,
v
o
l
.
1
4
,
n
o
.
2
,
p
.
9
3
2
,
2
0
2
5
,
d
o
i
:
1
0
.
3
2
5
2
0
/
st
m
si
.
v
1
4
i
2
.
5
0
9
0
.
[
7
]
J.
L
.
B
a
a
n
d
D
.
P
.
K
i
n
g
m
a
,
“
A
d
a
m:
a
me
t
h
o
d
f
o
r
st
o
c
h
a
s
t
i
c
o
p
t
i
mi
z
a
t
i
o
n
,
”
3
r
d
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
L
e
a
r
n
i
n
g
Re
p
r
e
se
n
t
a
t
i
o
n
s
,
I
C
L
R
2
0
1
5
-
C
o
n
f
e
r
e
n
c
e
T
r
a
c
k
Pr
o
c
e
e
d
i
n
g
s
,
p
p
.
1
–
1
5
,
2
0
1
5
.
[
8
]
W
.
C
h
e
n
g
,
R
.
P
u
,
a
n
d
B
.
W
a
n
g
,
“
A
M
C
:
a
d
a
p
t
i
v
e
l
e
a
r
n
i
n
g
r
a
t
e
a
d
j
u
st
me
n
t
b
a
se
d
o
n
mo
d
e
l
c
o
mp
l
e
x
i
t
y
,
”
M
a
t
h
e
m
a
t
i
c
s
,
v
o
l
.
1
3
,
n
o
.
4
,
2
0
2
5
,
d
o
i
:
1
0
.
3
3
9
0
/
m
a
t
h
1
3
0
4
0
6
5
0
.
[
9
]
P.
-
J.
C
h
i
a
n
g
,
“
A
d
a
p
t
i
v
e
p
e
n
a
l
t
y
me
t
h
o
d
w
i
t
h
a
n
A
d
a
m
o
p
t
i
mi
z
e
r
f
o
r
e
n
h
a
n
c
e
d
c
o
n
v
e
r
g
e
n
c
e
i
n
o
p
t
i
c
a
l
w
a
v
e
g
u
i
d
e
mo
d
e
so
l
v
e
r
s,”
O
p
t
i
c
s
Ex
p
ress
,
v
o
l
.
3
1
,
n
o
.
1
7
,
p
.
2
8
0
6
5
,
2
0
2
3
,
d
o
i
:
1
0
.
1
3
6
4
/
o
e
.
4
9
5
8
5
5
.
[
1
0
]
C
.
P
e
n
g
,
“
C
o
mp
r
e
h
e
n
s
i
v
e
a
n
a
l
y
si
s
o
f
t
h
e
i
m
p
a
c
t
o
f
l
e
a
r
n
i
n
g
r
a
t
e
a
n
d
d
r
o
p
o
u
t
r
a
t
e
o
n
t
h
e
p
e
r
f
o
r
man
c
e
o
f
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
s
o
n
t
h
e
C
I
F
A
R
-
1
0
d
a
t
a
se
t
,
”
i
n
A
p
p
l
i
e
d
a
n
d
C
o
m
p
u
t
a
t
i
o
n
a
l
E
n
g
i
n
e
e
r
i
n
g
,
2
0
2
4
,
p
p
.
1
8
3
–
192
,
d
o
i
:
1
0
.
5
4
2
5
4
/
2
7
5
5
-
2
7
2
1
/
1
0
2
/
2
0
2
4
1
1
6
1
.
[
1
1
]
A
.
K
.
P
.
A
n
i
l
a
n
d
U
.
K
.
S
i
n
g
h
,
“
A
n
o
p
t
i
m
a
l
so
l
u
t
i
o
n
t
o
t
h
e
o
v
e
r
f
i
t
t
i
n
g
a
n
d
u
n
d
e
r
f
i
t
t
i
n
g
p
r
o
b
l
e
m
o
f
h
e
a
l
t
h
c
a
r
e
mac
h
i
n
e
l
e
a
r
n
i
n
g
mo
d
e
l
s,”
J
o
u
r
n
a
l
o
f
S
y
s
t
e
m
s
En
g
i
n
e
e
ri
n
g
a
n
d
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
(
J
O
S
EI
T
)
,
v
o
l
.
2
,
n
o
.
2
,
p
p
.
7
7
–
8
4
,
2
0
2
3
,
d
o
i
:
1
0
.
2
9
2
0
7
/
j
o
se
i
t
.
v
2
i
2
.
5
4
6
0
.
[1
2
]
N
.
O
.
A
l
j
e
h
a
n
e
,
“
A
n
e
w
a
p
p
r
o
a
c
h
t
o
se
n
t
i
me
n
t
a
n
a
l
y
si
s
o
n
t
w
i
t
t
e
r
d
a
t
a
w
i
t
h
L
S
T
M
,
”
2
0
2
3
3
rd
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
i
n
g
a
n
d
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
(
I
C
C
I
T
)
.
I
EEE,
p
p
.
6
5
7
–
6
6
3
,
S
e
p
.
1
3
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
i
c
c
i
t
5
8
1
3
2
.
2
0
2
3
.
1
0
2
7
3
8
7
6
.
[1
3
]
S
.
I
.
W
i
g
u
n
a
,
A
.
Er
f
i
n
a
,
a
n
d
C
.
W
a
r
man
,
“
S
e
n
t
i
me
n
t
a
n
a
l
y
si
s
o
f
p
u
b
l
i
c
o
p
i
n
i
o
n
o
n
P
i
n
e
t
w
o
r
k
o
n
R
e
d
d
i
t
u
si
n
g
F
i
n
B
E
R
T
,
”
I
n
d
o
n
e
si
a
n
J
o
u
r
n
a
l
o
f
D
a
t
a
a
n
d
S
c
i
e
n
c
e
,
v
o
l
.
6
,
n
o
.
3
,
p
p
.
4
2
6
–
4
3
2
,
2
0
2
5
,
d
o
i
:
1
0
.
5
6
7
0
5
/
i
j
o
d
a
s.v
6
i
3
.
3
4
2
.
[1
4
]
K
.
S
h
i
r
i
n
i
,
M
.
B
.
K
o
r
d
a
n
,
a
n
d
S
.
S
.
G
h
a
r
e
h
v
e
r
a
n
,
“
I
mp
a
c
t
o
f
l
e
a
r
n
i
n
g
r
a
t
e
a
n
d
e
p
o
c
h
s
o
n
L
S
T
M
mo
d
e
l
p
e
r
f
o
r
man
c
e
:
a
st
u
d
y
o
f
c
h
l
o
r
o
p
h
y
l
l
-
a
c
o
n
c
e
n
t
r
a
t
i
o
n
s
i
n
t
h
e
M
a
r
mara
S
e
a
,
”
J
o
u
r
n
a
l
o
f
S
u
p
e
rc
o
m
p
u
t
i
n
g
,
v
o
l
.
8
1
,
n
o
.
1
,
p
.
2
6
5
,
2
0
2
5
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
2
2
7
-
0
2
4
-
0
6
8
0
6
-
2.
[1
5
]
M
.
N
.
Z
a
i
d
a
n
,
Y
.
S
i
b
a
r
o
n
i
,
a
n
d
S
.
S
.
P
r
a
se
t
y
o
w
a
t
i
,
“
L
e
a
r
n
i
n
g
r
a
t
e
a
n
d
e
p
o
c
h
o
p
t
i
mi
z
a
t
i
o
n
i
n
t
h
e
f
i
n
e
-
t
u
n
i
n
g
p
r
o
c
e
ss fo
r
I
n
d
o
b
e
r
t
’
s
p
e
r
f
o
r
man
c
e
o
n
se
n
t
i
me
n
t
a
n
a
l
y
si
s
o
f
M
y
t
e
l
k
o
msel
a
p
p
r
e
v
i
e
w
s,”
J
u
rn
a
l
T
e
k
n
i
k
I
n
f
o
rm
a
t
i
k
a
(
J
u
t
i
f
)
,
v
o
l
.
5
,
n
o
.
5
,
p
p
.
1
4
4
3
–
1
4
5
0
,
2
0
2
4
,
d
o
i
:
1
0
.
5
2
4
3
6
/
1
.
j
u
t
i
f
.
2
0
2
4
.
5
.
5
.
2
3
9
6
.
[1
6
]
S
.
S
z
e
g
h
a
l
m
y
a
n
d
A
.
F
a
z
e
k
a
s,
“
A
c
o
mp
a
r
a
t
i
v
e
st
u
d
y
o
f
t
h
e
u
se
o
f
st
r
a
t
i
f
i
e
d
c
r
o
ss
-
v
a
l
i
d
a
t
i
o
n
a
n
d
d
i
s
t
r
i
b
u
t
i
o
n
-
b
a
l
a
n
c
e
d
st
r
a
t
i
f
i
e
d
c
r
o
ss
-
v
a
l
i
d
a
t
i
o
n
i
n
i
mb
a
l
a
n
c
e
d
l
e
a
r
n
i
n
g
,
”
S
e
n
so
rs
,
v
o
l
.
2
3
,
n
o
.
4
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
s
2
3
0
4
2
3
3
3
.
[1
7
]
K
.
A
n
a
m
a
n
d
A
.
A
l
-
Ju
mai
l
y
,
“
I
mp
r
o
v
e
d
my
o
e
l
e
c
t
r
i
c
p
a
t
t
e
r
n
r
e
c
o
g
n
i
t
i
o
n
o
f
f
i
n
g
e
r
mo
v
e
me
n
t
u
s
i
n
g
r
e
j
e
c
t
i
o
n
-
b
a
se
d
e
x
t
r
e
me
l
e
a
r
n
i
n
g
ma
c
h
i
n
e
,
”
T
e
l
k
o
m
n
i
k
a
(
T
e
l
e
c
o
m
m
u
n
i
c
a
t
i
o
n
C
o
m
p
u
t
i
n
g
E
l
e
c
t
r
o
n
i
c
s
a
n
d
C
o
n
t
ro
l
)
,
v
o
l
.
1
9
,
n
o
.
1
,
p
p
.
1
3
4
–
1
4
5
,
2
0
2
1
,
d
o
i
:
1
0
.
1
2
9
2
8
/
T
EL
K
O
M
N
I
K
A
.
V
1
9
I
1
.
1
6
5
6
6
.
[1
8
]
R
.
F
.
R
o
j
a
s,
C
.
Jo
se
p
h
,
G
.
B
a
r
g
sh
a
d
y
,
a
n
d
K
.
L
.
O
u
,
“
Em
p
i
r
i
c
a
l
c
o
m
p
a
r
i
s
o
n
o
f
d
e
e
p
l
e
a
r
n
i
n
g
m
o
d
e
l
s
f
o
r
f
N
I
R
S
p
a
i
n
d
e
c
o
d
i
n
g
,
”
Fro
n
t
i
e
rs
i
n
N
e
u
ro
i
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
1
8
,
2
0
2
4
,
d
o
i
:
1
0
.
3
3
8
9
/
f
n
i
n
f
.
2
0
2
4
.
1
3
2
0
1
8
9
.
[
19
]
P
.
Jo
sh
i
,
S
.
M
u
n
d
r
a
,
a
n
d
A
.
M
u
n
d
r
a
,
“
P
r
o
t
o
-
A
t
t
-
F
S
L
:
e
n
h
a
n
c
e
d
p
r
o
t
o
t
y
p
i
c
a
l
n
e
t
w
o
r
k
f
o
r
c
r
o
ss
-
d
o
mai
n
f
e
w
-
sh
o
t
a
i
r
l
i
n
e
se
n
t
i
me
n
t
c
l
a
ssi
f
i
c
a
t
i
o
n
,”
S
o
c
i
a
l
N
e
t
w
o
rk
An
a
l
y
s
i
s
a
n
d
Mi
n
i
n
g
,
v
o
l
.
1
5
,
n
o
.
1
,
2
0
2
5
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
3
2
7
8
-
0
2
5
-
0
1
4
3
6
-
9.
[2
0
]
H
.
A
l
d
a
b
b
a
s,
A
.
B
a
j
a
h
z
a
r
,
M
.
A
l
r
u
i
l
y
,
A
.
A
.
Q
u
r
e
sh
i
,
R
.
M
.
A
.
L
a
t
i
f
,
a
n
d
M
.
F
a
r
h
a
n
,
“
G
o
o
g
l
e
P
l
a
y
c
o
n
t
e
n
t
scr
a
p
i
n
g
a
n
d
k
n
o
w
l
e
d
g
e
e
n
g
i
n
e
e
r
i
n
g
u
s
i
n
g
n
a
t
u
r
a
l
l
a
n
g
u
a
g
e
p
r
o
c
e
ssi
n
g
t
e
c
h
n
i
q
u
e
s
w
i
t
h
t
h
e
a
n
a
l
y
si
s
o
f
u
se
r
r
e
v
i
e
w
s,”
J
o
u
r
n
a
l
o
f
I
n
t
e
l
l
i
g
e
n
t
S
y
s
t
e
m
s
,
v
o
l
.
3
0
,
n
o
.
1
,
p
p
.
1
9
2
–
2
0
8
,
2
0
2
0
,
d
o
i
:
1
0
.
1
5
1
5
/
j
i
sy
s
-
2
0
1
9
-
0
1
9
7
.
[2
1
]
M
.
F
.
A
b
d
i
l
l
a
h
a
n
d
K
.
K
u
sn
a
w
i
,
“
C
o
mp
a
r
a
t
i
v
e
a
n
a
l
y
si
s
o
f
l
o
n
g
sh
o
r
t
-
t
e
r
m
me
mo
r
y
a
r
c
h
i
t
e
c
t
u
r
e
f
o
r
t
e
x
t
c
l
a
ssi
f
i
c
a
t
i
o
n
,
”
I
L
K
O
M
J
u
r
n
a
l
I
l
m
i
a
h
,
v
o
l
.
1
5
,
n
o
.
3
,
p
p
.
4
5
5
–
4
6
4
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
0
9
6
/
i
l
k
o
m.v
1
5
i
3
.
1
9
0
6
.
4
5
5
-
4
6
4
.
[2
2
]
C
.
S
a
l
a
z
a
r
,
E.
M
o
n
t
o
y
a
-
M
ú
n
e
r
a
,
a
n
d
J.
A
g
u
i
l
a
r
,
“
S
e
n
t
i
me
n
t
a
n
a
l
y
si
s
i
n
l
e
a
r
n
i
n
g
r
e
so
u
r
c
e
s,”
J
o
u
r
n
a
l
o
f
C
o
m
p
u
t
e
rs
i
n
E
d
u
c
a
t
i
o
n
,
v
o
l
.
1
0
,
n
o
.
4
,
p
p
.
6
3
7
–
6
6
2
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s
4
0
6
9
2
-
0
2
2
-
0
0
2
3
7
-
9.
[2
3
]
S
.
G
a
r
g
,
D
.
C
h
a
t
u
r
v
e
d
i
,
T
.
Ja
i
n
,
A
.
M
i
s
h
r
a
,
a
n
d
A
.
K
a
p
o
o
r
,
“
S
e
n
t
i
me
n
t
a
n
a
l
y
si
s:
t
e
c
h
n
i
q
u
e
s,
l
i
mi
t
a
t
i
o
n
s,
a
n
d
c
a
se
st
u
d
i
e
s
i
n
d
a
t
a
e
x
t
r
a
c
t
i
o
n
a
n
d
c
l
a
ss
i
f
i
c
a
t
i
o
n
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
Re
s
e
a
rc
h
J
o
u
rn
a
l
o
f
En
g
i
n
e
e
r
i
n
g
S
c
i
e
n
c
e
,
v
o
l
.
9
,
n
o
.
3
,
p
p
.
1
–
6
,
2
0
2
3
.
[2
4
]
M
.
A
f
r
a
d
,
D
.
C
.
F
e
b
r
i
a
n
t
o
,
S
.
W
i
j
a
y
a
n
t
o
,
a
n
d
M
.
Y
.
F
a
t
h
o
n
i
,
“
S
e
n
t
i
me
n
t
a
n
a
l
y
si
s o
f
v
i
si
t
o
r
r
e
v
i
e
w
s
o
n
B
a
t
u
r
a
d
e
n
t
o
u
r
i
st
a
t
t
r
a
c
t
i
o
n
u
si
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
me
t
h
o
d
s
,
”
Ed
u
K
o
m
p
u
t
i
k
a
J
o
u
rn
a
l
, v
o
l
.
1
1
,
n
o
.
1
,
p
p
.
5
7
–
6
4
,
2
0
2
4
,
d
o
i
:
1
0
.
1
5
2
9
4
/
e
d
u
k
o
m
.
v
1
1
i
1
.
1
0
5
6
1
.
[2
5
]
U
.
R
.
P
o
l
,
“
H
u
g
g
i
n
g
f
a
c
e
:
r
e
v
o
l
u
t
i
o
n
i
z
i
n
g
A
I
a
n
d
N
L
P
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
f
o
r
Re
s
e
a
r
c
h
i
n
A
p
p
l
i
e
d
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
ri
n
g
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
1
2
,
n
o
.
8
,
p
p
.
1
1
2
1
–
1
1
2
4
,
2
0
2
4
,
d
o
i
:
1
0
.
2
2
2
1
4
/
i
j
r
a
se
t
.
2
0
2
4
.
6
4
0
2
3
.
[2
6
]
H
.
A
h
mad
i
a
n
,
T
.
F
.
A
b
i
d
i
n
,
H
.
R
i
z
a
,
a
n
d
K
.
M
u
c
h
t
a
r
,
“
H
y
b
r
i
d
M
o
d
e
l
s
f
o
r
e
mo
t
i
o
n
c
l
a
ss
i
f
i
c
a
t
i
o
n
a
n
d
se
n
t
i
me
n
t
a
n
a
l
y
si
s
i
n
i
n
d
o
n
e
si
a
n
l
a
n
g
u
a
g
e
,
”
i
n
A
p
p
l
i
e
d
C
o
m
p
u
t
a
t
i
o
n
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
S
o
f
t
C
o
m
p
u
t
i
n
g
,
Y
o
g
y
a
k
a
r
t
a
,
I
n
d
o
n
e
si
a
,
2
0
2
4
,
p
p
.
2
0
9
–
2
1
4
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
4
/
2
8
2
6
7
7
3
.
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
E
va
lu
a
tin
g
le
a
r
n
in
g
r
a
te
effec
ts
o
n
lo
n
g
s
h
o
r
t
-
term me
mo
r
y
fo
r
I
n
d
o
n
esia
n
…
(
S
erly E
ld
in
a
)
573
[2
7
]
Y
.
F
a
u
z
i
a
h
,
B
.
Y
u
w
o
n
o
,
a
n
d
A
.
S
.
A
r
i
b
o
w
o
,
“
L
e
x
i
c
o
n
b
a
se
d
se
n
t
i
me
n
t
a
n
a
l
y
si
s
i
n
i
n
d
o
n
e
si
a
l
a
n
g
u
a
g
e
s
:
a
sy
st
e
mat
i
c
l
i
t
e
r
a
t
u
r
e
r
e
v
i
e
w
,
”
i
n
R
S
F
C
o
n
f
e
r
e
n
c
e
S
e
ri
e
s:
E
n
g
i
n
e
e
r
i
n
g
a
n
d
T
e
c
h
n
o
l
o
g
y
,
2
0
2
1
,
p
p
.
3
6
3
–
3
6
7
,
d
o
i
:
1
0
.
3
1
0
9
8
/
c
se
t
.
v
1
i
1
.
3
9
7
.
[2
8
]
K.
B
a
r
i
k
a
n
d
S
.
M
i
sr
a
,
“
A
n
a
l
y
si
s o
f
c
u
st
o
me
r
r
e
v
i
e
w
s
w
i
t
h
a
n
i
mp
r
o
v
e
d
V
A
D
ER
l
e
x
i
c
o
n
c
l
a
ssi
f
i
e
r
,
”
J
o
u
rn
a
l
o
f
Bi
g
D
a
t
a
,
v
o
l
.
1
1
,
n
o
.
1
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
8
6
/
s
4
0
5
3
7
-
0
2
3
-
0
0
8
6
1
-
x.
[
29
]
S
.
N
.
A
l
mu
a
y
q
i
l
,
M
.
H
u
may
u
n
,
N
.
Z
.
Jh
a
n
j
h
i
,
M
.
F
.
A
l
mu
f
a
r
e
h
,
a
n
d
N
.
A
.
K
h
a
n
,
“
E
n
h
a
n
c
i
n
g
se
n
t
i
me
n
t
a
n
a
l
y
si
s
v
i
a
r
a
n
d
o
m
maj
o
r
i
t
y
u
n
d
e
r
-
sam
p
l
i
n
g
w
i
t
h
r
e
d
u
c
e
d
t
i
me
c
o
m
p
l
e
x
i
t
y
f
o
r
c
l
a
ssi
f
y
i
n
g
t
w
e
e
t
r
e
v
i
e
w
s,”
El
e
c
t
r
o
n
i
c
s
(
S
w
i
t
z
e
rl
a
n
d
)
,
v
o
l
.
1
1
,
n
o
.
2
1
,
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
e
l
e
c
t
r
o
n
i
c
s
1
1
2
1
3
6
2
4
.
[3
0
]
I
.
O
.
M
u
r
a
i
n
a
,
“
I
d
e
a
l
d
a
t
a
se
t
s
p
l
i
t
t
i
n
g
r
a
t
i
o
s
i
n
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms:
g
e
n
e
r
a
l
c
o
n
c
e
r
n
s
f
o
r
d
a
t
a
sc
i
e
n
t
i
st
s
a
n
d
d
a
t
a
a
n
a
l
y
st
s,”
7
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
M
a
r
d
i
n
A
rt
u
k
l
u
S
c
i
e
n
t
i
f
i
c
Re
se
a
r
c
h
e
s
C
o
n
f
e
re
n
c
e
,
p
p
.
4
9
6
–
5
0
4
,
2
0
2
2
.
[3
1
]
A
.
M
a
i
t
i
,
A
.
A
b
a
r
d
a
,
a
n
d
M
.
H
a
n
i
n
i
,
“
T
h
e
i
mp
a
c
t
o
f
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
t
e
c
h
n
i
q
u
e
s
o
n
t
h
e
p
e
r
f
o
r
man
c
e
o
f
t
e
x
t
d
a
t
a
c
l
a
ssi
f
i
c
a
t
i
o
n
mo
d
e
l
s,”
I
n
d
o
n
e
s
i
a
n
J
o
u
r
n
a
l
o
f
E
l
e
c
t
ri
c
a
l
En
g
i
n
e
e
ri
n
g
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
3
5
,
n
o
.
2
,
p
p
.
1
0
4
1
–
1
0
5
2
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s.v
3
5
.
i
2
.
p
p
1
0
4
1
-
1
0
5
2
.
[3
2
]
L
.
D
a
v
o
o
d
i
,
J.
M
e
z
e
i
,
a
n
d
M
.
H
e
i
k
k
i
l
ä
,
“
A
sp
e
c
t
-
b
a
se
d
se
n
t
i
me
n
t
c
l
a
ss
i
f
i
c
a
t
i
o
n
o
f
u
se
r
r
e
v
i
e
w
s t
o
u
n
d
e
r
st
a
n
d
c
u
s
t
o
me
r
sat
i
sf
a
c
t
i
o
n
o
f
e
-
c
o
mm
e
r
c
e
p
l
a
t
f
o
r
ms,”
El
e
c
t
r
o
n
i
c
C
o
m
m
e
rc
e
R
e
se
a
rc
h
,
2
0
2
5
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
0
6
6
0
-
025
-
0
9
9
4
8
-
4.
[3
3
]
J.
S
h
o
b
a
n
a
a
n
d
M
.
M
u
r
a
l
i
,
“
A
n
e
f
f
i
c
i
e
n
t
se
n
t
i
me
n
t
a
n
a
l
y
si
s
me
t
h
o
d
o
l
o
g
y
b
a
se
d
o
n
l
o
n
g
sh
o
r
t
-
t
e
r
m
me
mo
r
y
n
e
t
w
o
r
k
s,”
C
o
m
p
l
e
x
a
n
d
I
n
t
e
l
l
i
g
e
n
t
S
y
st
e
m
s
,
v
o
l
.
7
,
n
o
.
5
,
p
p
.
2
4
8
5
–
2
5
0
1
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
0
7
/
s
4
0
7
4
7
-
0
2
1
-
0
0
4
3
6
-
4.
[3
4
]
M
.
K
.
A
n
a
m,
S
.
D
e
f
i
t
,
H
a
v
i
l
u
d
d
i
n
,
L
.
Ef
r
i
z
o
n
i
,
a
n
d
M
.
B
.
F
i
r
d
a
u
s,
“
E
a
r
l
y
st
o
p
p
i
n
g
o
n
C
N
N
-
L
S
T
M
d
e
v
e
l
o
p
me
n
t
t
o
i
m
p
r
o
v
e
c
l
a
ssi
f
i
c
a
t
i
o
n
p
e
r
f
o
r
man
c
e
,
”
J
o
u
rn
a
l
o
f
Ap
p
l
i
e
d
D
a
t
a
S
c
i
e
n
c
e
s
,
v
o
l
.
5
,
n
o
.
3
,
p
p
.
1
1
7
5
–
1
1
8
8
,
2
0
2
4
,
d
o
i
:
1
0
.
4
7
7
3
8
/
j
a
d
s.v
5
i
3
.
3
1
2
.
[3
5
]
A
.
C
.
M
.
V
.
S
r
i
n
i
v
a
s,
C
.
S
a
t
y
a
n
a
r
a
y
a
n
a
,
C
.
D
i
v
a
k
a
r
,
a
n
d
K
.
P
.
S
i
r
i
sh
a
,
“
S
e
n
t
i
me
n
t
a
n
a
l
y
si
s
u
s
i
n
g
n
e
u
r
a
l
n
e
t
w
o
r
k
a
n
d
L
S
T
M
,
”
i
n
I
O
P
C
o
n
f
e
re
n
c
e
S
e
r
i
e
s:
M
a
t
e
ri
a
l
s
S
c
i
e
n
c
e
a
n
d
En
g
i
n
e
e
r
i
n
g
,
2
0
2
1
,
p
.
0
1
2
0
0
7
,
d
o
i
:
1
0
.
1
0
8
8
/
1
7
5
7
-
8
9
9
x
/
1
0
7
4
/
1
/
0
1
2
0
0
7
.
[3
6
]
R
.
K
.
D
a
s,
M
.
I
sl
a
m,
M
.
M
.
H
a
sa
n
,
S
.
R
a
z
i
a
,
M
.
H
a
s
sa
n
,
a
n
d
S
.
A
.
K
h
u
s
h
b
u
,
“
S
e
n
t
i
me
n
t
a
n
a
l
y
si
s
i
n
m
u
l
t
i
l
i
n
g
u
a
l
c
o
n
t
e
x
t
:
C
o
mp
a
r
a
t
i
v
e
a
n
a
l
y
si
s
o
f
mac
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
h
y
b
r
i
d
d
e
e
p
l
e
a
r
n
i
n
g
mo
d
e
l
s,”
H
e
l
i
y
o
n
,
v
o
l
.
9
,
n
o
.
9
,
p
.
e
2
0
2
8
1
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
h
e
l
i
y
o
n
.
2
0
2
3
.
e
2
0
2
8
1
.
[3
7
]
Y
.
A
.
S
i
n
g
g
a
l
e
n
,
“
B
i
L
S
T
M
-
L
S
T
M
H
y
b
r
i
d
mo
d
e
l
w
i
t
h
g
l
o
v
e
e
mb
e
d
d
i
n
g
s
f
o
r
h
o
t
e
l
r
e
v
i
e
w
se
n
t
i
me
n
t
a
n
a
l
y
si
s,”
J
o
u
rn
a
l
o
f
I
n
f
o
rm
a
t
i
o
n
S
y
st
e
m
R
e
se
a
rc
h
(
J
O
S
H
)
,
v
o
l
.
6
,
n
o
.
2
,
p
p
.
8
5
7
–
8
6
8
,
2
0
2
4
,
d
o
i
:
1
0
.
4
7
0
6
5
/
j
o
sh
.
v
6
i
2
.
6
4
2
0
.
[3
8
]
Z
.
B
.
K
i
z
i
l
k
a
n
,
M
.
S
.
S
i
v
r
i
,
I
.
Y
a
z
i
c
i
,
a
n
d
O
.
F
.
B
e
y
c
a
,
“
N
e
u
r
a
l
n
e
t
w
o
r
k
s
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
,
”
S
p
ri
n
g
e
r
S
e
r
i
e
s
i
n
A
d
v
a
n
c
e
d
Ma
n
u
f
a
c
t
u
r
i
n
g
.
S
p
r
i
n
g
e
r
I
n
t
e
r
n
a
t
i
o
n
a
l
P
u
b
l
i
s
h
i
n
g
,
p
p
.
1
2
7
–
1
5
1
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
0
3
0
-
9
3
8
2
3
-
9
_
5
.
[
39
]
Z
.
Z
mi
r
l
i
,
S
.
El
H
a
r
f
a
o
u
i
,
A
.
M
o
h
ssi
n
e
,
A
.
D
r
i
o
u
i
c
h
,
H
.
C
h
a
a
i
r
,
a
n
d
B
.
S
a
l
l
e
k
,
“
L
e
ss e
n
e
r
g
y
a
n
d
a
l
u
m
i
n
u
m e
l
e
c
t
r
o
d
e
c
o
n
su
m
p
t
i
o
n
f
o
r
f
l
u
o
r
i
d
e
r
e
mo
v
a
l
u
si
n
g
e
l
e
c
t
r
o
c
o
a
g
u
l
a
t
i
o
n
p
r
o
c
e
ss:
o
p
t
i
m
i
z
a
t
i
o
n
b
y
o
n
e
-
w
a
y
A
N
O
V
A
a
n
a
l
y
si
s
a
n
d
e
x
p
e
r
i
me
n
t
a
l
d
e
si
g
n
,
”
D
e
sa
l
i
n
a
t
i
o
n
a
n
d
Wa
t
e
r
T
re
a
t
m
e
n
t
,
v
o
l
.
2
9
2
,
p
p
.
1
8
5
–
2
0
5
,
2
0
2
3
,
d
o
i
:
1
0
.
5
0
0
4
/
d
w
t
.
2
0
2
3
.
2
9
5
0
4
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
S
e
r
ly
Eld
in
a
s
h
e
is
c
u
rre
n
tl
y
p
u
rsu
in
g
a
Ba
c
h
e
lo
r
o
f
En
g
in
e
e
rin
g
(S
.
T
.
)
d
e
g
re
e
in
In
f
o
rm
a
ti
c
s
En
g
in
e
e
rin
g
a
t
th
e
S
c
h
o
o
l
o
f
El
e
c
tri
c
a
l
a
n
d
In
f
o
rm
a
ti
c
s,
Un
iv
e
rsitas
M
a
rit
im
Ra
ja
A
li
Ha
ji
(UMR
A
H).
S
h
e
h
a
s
a
n
in
tere
st
in
a
rti
f
icia
l
in
telli
g
e
n
c
e
(
A
I),
p
a
rti
c
u
larl
y
in
n
a
tu
r
al
lan
g
u
a
g
e
p
ro
c
e
ss
in
g
(NL
P
)
a
n
d
it
s
a
p
p
li
c
a
ti
o
n
s
in
tex
t
a
n
a
ly
si
s.
He
r
re
se
a
r
c
h
a
re
a
s
in
c
lu
d
e
m
a
c
h
in
e
lea
rn
in
g
a
n
d
d
e
e
p
lea
rn
i
n
g
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
at
e
m
a
il
:
se
rl
y
e
ld
in
a
0
3
@g
m
a
il
.
c
o
m
.
Te
k
a
d
M
a
tu
l
a
ta
n
a
ten
u
re
l
e
c
tu
re
r
in
th
e
In
f
o
rm
a
ti
c
s
D
e
p
a
r
tm
e
n
t,
S
c
h
o
o
l
o
f
El
e
c
tri
c
a
l
a
n
d
In
f
o
rm
a
ti
c
s,
Un
iv
e
rsitas
M
a
rit
im
Ra
ja
A
li
Ha
ji
(UMRA
H),
P
ro
v
i
n
c
e
o
f
Riau
Isla
n
d
s.
G
ra
d
u
a
ted
f
ro
m
F
li
n
d
e
rs
Un
iv
e
rsity
o
f
S
o
u
th
A
u
stra
li
a
(
2
0
0
5
)
a
n
d
h
a
d
u
n
d
e
rg
o
n
e
1
y
e
a
r
o
f
p
re
-
d
o
c
t
o
ra
l
e
d
u
c
a
ti
o
n
a
t
A
rizo
n
a
S
tate
Un
iv
e
rsity
(2
0
1
5
).
A
s
P
I
in
th
e
f
ield
o
f
e
d
u
c
a
ti
o
n
a
l
d
a
ta
m
in
in
g
(EDM
)
2
0
1
4
-
2
0
1
7
,
a
n
d
re
se
a
rc
h
a
ss
istan
t
in
th
e
f
ield
s
o
f
m
u
lt
i
m
o
d
a
l
NL
M
,
g
e
n
e
ra
ti
v
e
A
I,
a
n
d
v
isu
a
l
c
o
m
p
u
tati
o
n
a
l.
He
c
a
n
b
e
c
o
n
tac
ted
at
e
m
a
il
:
tek
a
d
.
m
a
tu
lata
n
@u
m
ra
h
.
a
c
.
id
.
No
v
r
i
z
a
l
Fa
tta
h
Fa
h
m
it
r
a
re
c
e
iv
e
d
h
is
Ba
c
h
e
lo
r
’
s
De
g
re
e
in
I
n
f
o
rm
a
ti
c
s
En
g
in
e
e
rin
g
f
ro
m
S
T
M
IK
A
M
IKO
M
Yo
g
y
a
k
a
rta.
Af
ter
th
a
t,
h
e
to
o
k
t
h
e
I
n
f
o
rm
a
ti
c
s
S
tu
d
y
P
r
o
g
ra
m
-
M
a
ste
r
’
s
P
ro
g
ra
m
f
o
r
M
e
d
ica
l
In
f
o
rm
a
ti
c
s
Co
n
c
e
n
tratio
n
a
t
th
e
Isla
m
ic
Un
iv
e
rsit
y
of
In
d
o
n
e
sia
.
In
2
0
2
4
,
h
e
jo
i
n
e
d
Un
iv
e
rsitas
M
a
rit
im
R
a
ja
A
li
Ha
j
i
(UMRA
H)
a
s
a
l
e
c
tu
re
r
f
o
r
th
e
Ba
c
h
e
lo
r
’
s
De
g
re
e
o
f
In
f
o
rm
a
ti
c
s
En
g
in
e
e
rin
g
S
tu
d
y
P
ro
g
ra
m
.
N
o
w
h
i
s
f
ie
l
d
o
f
s
c
ie
n
c
e
is
sy
s
tem
i
n
f
o
rm
a
t
i
o
n
t
e
c
h
n
o
l
o
g
y
a
d
m
i
n
i
s
t
r
a
t
i
o
n
,
h
i
s
r
e
s
e
a
r
c
h
c
o
n
c
l
u
d
e
s
sy
s
t
e
m
a
n
a
ly
s
t
,
u
s
a
b
i
l
i
ty
a
n
a
ly
s
i
s
,
IT
a
u
d
i
t
,
a
n
d
I
T
a
d
m
i
n
i
s
tr
a
t
i
o
n
.
H
e
c
a
n
b
e
c
o
n
t
a
c
t
e
d
at
e
m
a
i
l
:
n
f
f
a
h
m
i
t
r
a
@
u
m
r
a
h
.
a
c
.
i
d
.
Evaluation Warning : The document was created with Spire.PDF for Python.