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
6
,
No
.
3
,
Dec
em
b
er
20
24
,
p
p
.
1
7
59
~
1
7
68
I
SS
N:
2
502
-
4
7
52
,
DOI
: 1
0
.
1
1
5
9
1
/ijee
cs
.v
3
6
.
i
3
.
pp
1
7
59
-
1
7
68
1759
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs
.
ia
esco
r
e.
co
m
Deep learni
ng
util
iza
tion
in
S
u
nda
n
ese script
rec
o
g
ni
tion for
cultural p
reserv
a
tio
n
Ro
s
a
lin
a
1
,
Nuni
k
Af
rilia
na
2
,
Wira
nto
H
er
ry
Ut
o
m
o
3
,
G
ent
a
Sa
hu
ri
4
1
I
n
f
o
r
mat
i
c
s S
t
u
d
y
P
r
o
g
r
a
m
,
F
a
c
u
l
t
y
o
f
C
o
m
p
u
t
i
n
g
,
P
r
e
si
d
e
n
t
U
n
i
v
e
r
si
t
y
,
B
e
k
a
s
i
,
I
n
d
o
n
e
s
i
a
2
F
a
c
u
l
t
y
o
f
En
g
i
n
e
e
r
i
n
g
a
n
d
I
n
f
o
r
ma
t
i
c
s,
U
n
i
v
e
r
s
i
t
a
s
M
u
l
t
i
me
d
i
a
N
u
sa
n
t
a
r
a
,
Ta
n
g
e
r
a
n
g
,
I
n
d
o
n
e
s
i
a
3
M
a
s
t
e
r
o
f
S
c
i
e
n
c
e
i
n
I
n
f
o
r
mat
i
o
n
Te
c
h
n
o
l
o
g
y
S
t
u
d
y
P
r
o
g
r
a
m,
F
a
c
u
l
t
y
o
f
C
o
mp
u
t
i
n
g
,
P
r
e
s
i
d
e
n
t
U
n
i
v
e
r
s
i
t
y
,
B
e
k
a
si
,
I
n
d
o
n
e
s
i
a
4
I
n
f
o
r
mat
i
o
n
S
y
st
e
m
S
t
u
d
y
P
r
o
g
r
a
m,
F
a
c
u
l
t
y
o
f
C
o
m
p
u
t
i
n
g
,
P
r
e
si
d
e
n
t
U
n
i
v
e
r
si
t
y
,
B
e
k
a
si
,
I
n
d
o
n
e
si
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
May
18
,
2
0
2
4
R
ev
is
ed
Au
g
20
,
202
4
Acc
ep
ted
A
ug
31
,
2
0
2
4
Th
is
st
u
d
y
a
d
d
re
ss
e
s
th
e
c
h
a
ll
e
n
g
e
o
f
p
re
se
rv
in
g
th
e
S
u
n
d
a
n
e
se
sc
rip
t,
a
trad
it
io
n
a
l
writi
n
g
s
y
ste
m
o
f
t
h
e
S
u
n
d
a
n
e
se
c
o
m
m
u
n
it
y
i
n
In
d
o
n
e
sia
,
wh
ich
is
a
t
risk
o
f
b
e
i
n
g
f
o
rg
o
tt
e
n
d
u
e
to
tec
h
n
o
lo
g
ica
l
a
d
v
a
n
c
e
m
e
n
ts.
To
tac
k
le
th
is
p
r
o
b
lem
,
we
p
ro
p
o
se
a
d
e
e
p
lea
rn
in
g
a
p
p
ro
a
c
h
u
sin
g
th
e
YO
LOv
8
m
o
d
e
l
fo
r
th
e
a
u
t
o
m
a
ti
c
re
c
o
g
n
it
io
n
o
f
S
u
n
d
a
n
e
se
c
h
a
ra
c
ters
.
Ou
r
m
e
th
o
d
o
lo
g
y
i
n
c
lu
d
e
s
c
re
a
ti
n
g
a
c
o
m
p
re
h
e
n
si
v
e
d
a
tas
e
t,
a
p
p
ly
i
n
g
a
u
g
m
e
n
tatio
n
tec
h
n
i
q
u
e
s,
a
n
d
a
n
n
o
tati
n
g
t
h
e
c
h
a
ra
c
ters
.
Th
e
train
e
d
m
o
d
e
l
a
c
h
iev
e
d
a
p
re
c
isio
n
o
f
9
5
%
a
fter
1
5
0
e
p
o
c
h
s,
d
e
m
o
n
stra
ti
n
g
i
ts
e
ffe
c
ti
v
e
n
e
ss
in
re
c
o
g
n
izi
n
g
S
u
n
d
a
n
e
se
c
h
a
ra
c
ter
s.
Wh
il
e
so
m
e
v
a
riab
il
it
y
in
a
c
c
u
ra
c
y
wa
s
o
b
se
rv
e
d
fo
r
c
e
rtai
n
c
h
a
ra
c
ters
a
n
d
re
a
l
-
ti
m
e
a
p
p
li
c
a
ti
o
n
s,
t
h
e
re
su
lt
s
in
d
ica
te
th
e
fe
a
sib
il
it
y
a
n
d
p
r
o
m
ise
o
f
u
sin
g
d
e
e
p
le
a
rn
in
g
f
o
r
S
u
n
d
a
n
e
se
sc
rip
t
re
c
o
g
n
it
io
n
.
Th
is
re
se
a
rc
h
h
ig
h
li
g
h
ts
th
e
p
o
ten
ti
a
l
o
f
tec
h
n
o
l
o
g
ica
l
s
o
lu
t
io
n
s
to
d
i
g
it
ize
a
n
d
p
re
se
rv
e
t
h
e
S
u
n
d
a
n
e
se
sc
rip
t,
e
n
su
rin
g
it
s
c
o
n
ti
n
u
e
d
leg
a
c
y
a
n
d
a
c
c
e
ss
ib
il
it
y
fo
r
f
u
tu
re
g
e
n
e
ra
ti
o
n
s.
T
h
u
s
,
we
c
o
n
tri
b
u
te
to
c
u
lt
u
ra
l
p
re
se
rv
a
ti
o
n
b
y
p
r
o
v
i
d
i
n
g
a
m
e
th
o
d
t
o
sa
fe
g
u
a
rd
th
e
S
u
n
d
a
n
e
se
sc
rip
t
a
g
a
in
st
o
b
s
o
les
c
e
n
c
e
.
K
ey
w
o
r
d
s
:
C
o
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
s
C
u
ltu
r
al
p
r
eser
v
atio
n
Dee
p
lear
n
in
g
Her
itag
e
p
r
eser
v
atio
n
Su
n
d
an
ese
s
cr
ip
t
YOL
Ov
8
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
:
R
o
s
alin
a
I
n
f
o
r
m
atics Stu
d
y
Pro
g
r
a
m
,
F
ac
u
lty
o
f
C
o
m
p
u
tin
g
,
Pre
s
id
en
t U
n
iv
er
s
ity
B
ek
asi,
W
e
s
t Jav
a
,
I
n
d
o
n
esia
E
m
ail: r
o
s
alin
a@
p
r
esid
en
t.a
c.
id
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
Su
n
d
an
ese
s
cr
ip
t,
k
n
o
w
n
as
Ak
s
ar
a
Su
n
d
a
,
is
a
tr
ad
itio
n
al
wr
itin
g
s
y
s
tem
u
s
e
d
b
y
th
e
Su
n
d
an
ese
p
eo
p
le
o
f
I
n
d
o
n
esia.
I
t
h
o
ld
s
s
ig
n
if
ican
t
cu
ltu
r
al
an
d
h
is
to
r
ical
v
alu
e,
r
ef
lectin
g
th
e
r
ich
h
er
itag
e
o
f
th
e
Su
n
d
an
ese
c
o
m
m
u
n
ity
[
1
]
.
Ak
s
ar
a
n
g
alag
en
a
(
d
e
p
icted
in
Fig
u
r
e
1
)
,
o
r
co
n
s
o
n
a
n
t
letter
s
,
r
ep
r
esen
t
co
n
s
o
n
an
t
p
h
o
n
em
es
in
th
e
Su
n
d
an
ese
s
cr
ip
t
th
at
s
y
llab
icall
y
co
n
tain
th
e
v
o
wel
s
o
u
n
d
/a/.
T
h
er
e
ar
e
eig
h
teen
ty
p
es
o
f
th
ese
a
n
cien
t
Su
n
d
a
n
ese
ch
ar
ac
ter
s
,
ar
r
a
n
g
ed
ac
c
o
r
d
in
g
to
ar
ticu
lato
r
y
p
o
s
itio
n
s
s
u
ch
as
g
u
ttu
r
al
(
th
r
o
at)
,
p
alata
l
(
p
alate
)
,
lin
g
u
al
(
to
n
g
u
e)
,
d
en
tal
(
teeth
)
,
an
d
lab
ial
(
lip
s
)
.
T
h
ese
co
n
s
o
n
an
t
letter
s
ar
e
f
u
n
d
am
e
n
tal
to
th
e
Su
n
d
a
n
ese
s
cr
ip
t,
as
th
ey
f
o
r
m
t
h
e
b
asis
f
o
r
w
r
itin
g
w
o
r
d
s
a
n
d
co
n
v
ey
i
n
g
m
ea
n
in
g
.
E
ac
h
letter
r
ep
r
esen
ts
a
s
p
ec
if
ic
s
o
u
n
d
,
an
d
wh
e
n
co
m
b
in
ed
with
v
o
wel
d
iacr
itics
,
th
ey
c
r
ea
te
s
y
llab
les.
T
h
e
Su
n
d
an
ese
s
cr
ip
t
is
a
n
ab
u
g
id
a,
wh
er
e
ea
ch
c
o
n
s
o
n
a
n
t
letter
ca
r
r
ies
an
in
h
e
r
en
t
v
o
wel
s
o
u
n
d
,
wh
ich
ca
n
b
e
m
o
d
if
ied
b
y
d
iacr
itics
to
alt
er
th
e
v
o
wel
s
o
u
n
d
.
T
h
is
s
y
s
tem
atic
ar
r
an
g
em
en
t
aid
s
in
u
n
d
er
s
tan
d
i
n
g
th
e
p
h
o
n
etic
s
tr
u
ctu
r
e
o
f
th
e
Su
n
d
an
ese
lan
g
u
ag
e
a
n
d
s
u
p
p
o
r
ts
a
cc
u
r
ate
p
r
o
n
u
n
ciatio
n
.
Field
s
tu
d
ies
[
2
]
h
ig
h
lig
h
t
h
o
w
tr
ad
itio
n
al
s
y
s
tem
s
lik
e
Ak
s
ar
a
Su
n
d
a
ca
n
ad
ap
t
an
d
r
e
m
a
in
r
elev
an
t
in
to
d
ay
’
s
er
a.
T
h
is
ad
ap
tab
ilit
y
is
a
test
am
en
t
to
th
e
e
n
d
u
r
in
g
u
tili
ty
o
f
tr
ad
itio
n
al
k
n
o
wle
d
g
e
s
y
s
tem
s
,
wh
ich
ca
n
b
e
in
teg
r
ated
with
m
o
d
e
r
n
tech
n
o
l
o
g
ies
to
ad
d
r
ess
co
n
tem
p
o
r
ar
y
ch
allen
g
es.
T
h
e
Su
n
d
an
ese
s
cr
ip
t,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
6
,
No
.
3
,
Dec
em
b
er
20
24
:
1
7
5
9
-
1
7
6
8
1760
Ak
s
ar
a
Su
n
d
a,
s
er
v
es
as
a
p
o
wer
f
u
l
ex
am
p
le
o
f
h
o
w
tr
ad
itio
n
al
s
y
s
tem
s
ca
n
b
e
p
r
eser
v
ed
an
d
ad
ap
ted
f
o
r
m
o
d
er
n
u
s
e.
Ak
s
ar
a
Su
n
d
a
i
s
a
s
tr
u
ctu
r
ed
an
d
s
y
s
tem
atic
s
cr
ip
t
with
ea
ch
co
n
s
o
n
an
t
letter
ca
r
r
y
in
g
an
in
h
er
en
t
v
o
wel
s
o
u
n
d
th
at
ca
n
b
e
m
o
d
if
ied
b
y
d
iacr
itics
to
co
n
v
ey
d
if
f
er
en
t
m
ea
n
in
g
s
.
T
h
is
s
tr
u
ctu
r
ed
ap
p
r
o
ac
h
en
s
u
r
es
ac
cu
r
ate
p
r
o
n
u
n
ciatio
n
an
d
u
n
d
er
s
tan
d
in
g
o
f
th
e
Su
n
d
an
ese
lan
g
u
ag
e
,
r
ef
lectin
g
a
d
ee
p
cu
ltu
r
al
h
er
itag
e
.
Similar
ly
,
Fi
an
ty
et
a
l.
[
3
]
illu
s
tr
ates
th
e
p
o
ten
tial
f
o
r
co
m
b
i
n
in
g
tr
a
d
itio
n
al
k
n
o
wled
g
e
with
ad
v
an
ce
d
tech
n
o
lo
g
y
.
Ar
tific
i
al
in
tellig
en
ce
(
AI
)
m
o
d
els
ca
n
p
r
o
ce
s
s
v
ast
am
o
u
n
ts
o
f
d
at
a
f
r
o
m
co
m
m
u
n
ity
h
ea
lth
ce
n
ter
s
to
i
d
en
tify
n
u
tr
i
tio
n
al
d
ef
icien
cies
an
d
tr
en
d
s
am
o
n
g
t
o
d
d
ler
s
.
B
y
an
aly
zin
g
p
atter
n
s
in
d
ietar
y
in
tak
e,
g
r
o
wth
m
etr
ics,
an
d
h
e
alth
o
u
tco
m
es,
th
ese
AI
s
y
s
tem
s
ca
n
p
r
o
v
id
e
ac
tio
n
ab
le
in
s
ig
h
ts
f
o
r
h
ea
lth
ca
r
e
p
r
o
v
id
e
r
s
.
Fig
u
r
e
1
.
C
o
n
s
o
n
an
t
letter
s
in
Su
n
d
an
ese
s
cr
ip
t
“n
g
ala
g
en
a”
W
ith
th
e
ad
v
en
t
o
f
d
ig
ital
tec
h
n
o
lo
g
y
a
n
d
th
e
p
r
e
v
alen
ce
o
f
L
atin
s
cr
ip
t,
t
h
e
Su
n
d
an
ese
s
cr
ip
t
f
ac
es
th
e
r
is
k
o
f
m
ar
g
i
n
aliza
tio
n
,
th
r
ea
ten
in
g
th
e
p
r
eser
v
atio
n
o
f
Su
n
d
an
ese
c
u
ltu
r
e
an
d
la
n
g
u
ag
e
.
T
h
is
s
h
if
t
h
ig
h
lig
h
ts
th
e
u
r
g
e
n
t
n
ee
d
f
o
r
in
n
o
v
ativ
e
s
o
lu
tio
n
s
to
ef
f
ec
t
iv
ely
d
ig
itize
an
d
s
af
eg
u
ar
d
th
e
s
cr
ip
t
f
o
r
f
u
tu
r
e
g
en
er
atio
n
s
[
4
]
-
[
6
]
.
On
e
p
r
i
m
ar
y
ch
allen
g
e
in
th
is
p
r
eser
v
atio
n
ef
f
o
r
t
is
th
e
lack
o
f
e
f
f
icien
t
m
eth
o
d
s
f
o
r
r
ec
o
g
n
izin
g
an
d
d
ig
itizin
g
Su
n
d
an
ese
tex
t.
Ma
n
u
al
tr
a
n
s
cr
ip
tio
n
is
lab
o
r
-
in
ten
s
iv
e
a
n
d
p
r
o
n
e
to
in
ac
cu
r
ac
ies,
m
ak
in
g
it
im
p
r
ac
tical
f
o
r
lar
g
e
-
s
ca
le
p
r
eser
v
atio
n
.
T
r
ad
itio
n
al
o
p
tical
ch
ar
ac
te
r
r
ec
o
g
n
iti
o
n
(
OC
R
)
s
y
s
tem
s
also
s
tr
u
g
g
le
with
th
e
u
n
iq
u
e
ch
ar
ac
ter
is
tics
o
f
Su
n
d
an
ese
h
an
d
wr
itin
g
,
as
th
e
s
cr
ip
t’
s
c
o
m
p
lex
an
d
d
iv
er
s
e
s
h
ap
es p
o
s
e
s
ig
n
if
ican
t h
u
r
d
le
s
,
lead
in
g
to
s
u
b
o
p
tim
al
ac
cu
r
ac
y
an
d
r
eliab
ilit
y
.
Un
r
eso
lv
ed
p
r
o
b
lem
s
in
clu
d
e
th
e
lim
ited
ef
f
ec
tiv
en
ess
o
f
ex
is
tin
g
OC
R
s
y
s
tem
s
in
h
a
n
d
lin
g
th
e
co
m
p
lex
a
n
d
v
ar
ied
s
h
ap
es
o
f
Su
n
d
an
ese
c
h
ar
ac
ter
s
,
p
ar
ticu
lar
ly
in
r
ea
l
-
tim
e
a
p
p
licatio
n
s
.
C
u
r
r
en
t
ap
p
r
o
ac
h
es
o
f
ten
f
ail
to
p
r
o
v
i
d
e
ac
cu
r
ate
r
ec
o
g
n
itio
n
u
n
d
er
v
ar
y
in
g
c
o
n
d
itio
n
s
,
s
u
ch
as
d
if
f
er
en
t
lig
h
tin
g
o
r
im
ag
e
q
u
ality
.
M
o
r
eo
v
er
,
in
t
eg
r
atin
g
Su
n
d
a
n
ese
s
cr
ip
t
r
ec
o
g
n
itio
n
in
to
p
r
ac
tical
ap
p
lic
atio
n
s
,
lik
e
m
o
b
ile
tr
an
s
latio
n
to
o
ls
,
r
em
ain
s
ch
al
len
g
in
g
d
u
e
to
th
ese
lim
itatio
n
s
.
I
n
r
esp
o
n
s
e,
th
is
r
esear
ch
in
tr
o
d
u
ce
s
a
n
o
v
el
ap
p
r
o
ac
h
b
y
lev
er
ag
in
g
YOL
Ov
8
,
a
d
ee
p
lear
n
in
g
m
o
d
el
r
en
o
wn
ed
f
o
r
its
p
r
ec
is
io
n
in
o
b
ject
d
etec
tio
n
,
t
o
en
h
an
ce
Su
n
d
a
n
ese
s
cr
ip
t
r
ec
o
g
n
itio
n
.
YOL
Ov
8
'
s
ar
ch
itectu
r
e
allo
ws
f
o
r
m
o
r
e
ac
c
u
r
ate
an
d
ef
f
icien
t
r
ec
o
g
n
itio
n
o
f
Su
n
d
a
n
ese
ch
ar
ac
ter
s
b
y
h
an
d
lin
g
co
m
p
lex
s
h
ap
es a
n
d
d
iv
er
s
e
im
ag
e
co
n
d
it
io
n
s
.
T
h
is
r
esear
ch
aim
s
to
im
p
r
o
v
e
b
o
t
h
th
e
ac
cu
r
ac
y
a
n
d
r
o
b
u
s
tn
ess
o
f
ch
ar
ac
ter
id
e
n
tific
atio
n
,
o
f
f
er
in
g
a
s
ig
n
if
ica
n
t
ad
v
an
ce
m
e
n
t
in
d
ig
itizin
g
a
n
d
p
r
eser
v
i
n
g
Su
n
d
an
ese
tex
ts
.
T
h
is
ap
p
r
o
ac
h
ad
d
r
ess
es
g
ap
s
lef
t
b
y
p
r
e
v
io
u
s
m
eth
o
d
o
l
o
g
ies an
d
e
n
ab
les p
r
ac
tical
ap
p
licatio
n
s
,
s
u
ch
as r
e
al
-
tim
e
m
o
b
ile
tr
an
s
latio
n
to
o
l
s
.
Pre
v
io
u
s
r
esear
ch
o
n
Su
n
d
an
ese
s
cr
ip
t
r
ec
o
g
n
itio
n
h
as
e
x
p
lo
r
ed
v
ar
io
u
s
m
eth
o
d
o
l
o
g
ies,
in
clu
d
i
n
g
tr
ad
itio
n
al
m
ac
h
in
e
lear
n
in
g
a
n
d
d
ee
p
lear
n
in
g
a
p
p
r
o
ac
h
es
[
7
]
-
[
21
]
.
Y
o
u
o
n
ly
l
o
o
k
o
n
ce
(
YOL
O
)
h
as
g
ain
ed
p
r
o
m
in
e
n
ce
in
r
ea
l
-
tim
e
a
p
p
li
ca
tio
n
s
d
u
e
to
its
ex
ce
p
tio
n
al
s
p
ee
d
an
d
ac
c
u
r
ac
y
[
22
]
-
[
24
]
.
YOL
O’
s
u
n
iq
u
e
n
eu
r
al
n
etwo
r
k
d
esig
n
e
n
ab
le
s
it
to
p
r
ed
ict
m
u
ltip
le
b
o
u
n
d
i
n
g
b
o
x
es
an
d
class
p
r
o
b
ab
ilit
ies
s
im
u
ltan
eo
u
s
ly
,
allo
win
g
f
o
r
r
ea
l
-
tim
e
p
r
o
ce
s
s
in
g
o
f
v
id
eo
f
r
am
es
with
h
ig
h
p
r
ec
is
io
n
.
YOL
Ov
8
,
th
e
latest
iter
atio
n
,
b
u
ild
s
u
p
o
n
its
p
r
ed
ec
ess
o
r
s
with
en
h
an
ce
m
e
n
ts
th
at
im
p
r
o
v
e
p
e
r
f
o
r
m
a
n
ce
,
ac
cu
r
ac
y
,
an
d
ef
f
i
cien
cy
in
d
etec
tin
g
o
b
jects
[
2
5
]
.
W
h
ile
YOL
Ov
8
h
as
b
ee
n
ap
p
lied
to
r
ea
l
-
tim
e
Su
n
d
an
ese
s
cr
ip
t
d
etec
tio
n
in
v
id
eo
s
tr
ea
m
s
[
2
6
]
,
its
p
r
ed
o
m
in
an
t
u
s
e
h
as
b
ee
n
in
ca
r
p
late
r
ec
o
g
n
itio
n
[
2
7
]
,
[2
8
]
.
T
h
is
d
em
o
n
s
tr
ates
YOL
Ov
8
'
s
v
er
s
atil
ity
in
h
an
d
lin
g
co
m
p
lex
ch
ar
ac
ter
r
e
co
g
n
itio
n
task
s
with
h
ig
h
ac
c
u
r
ac
y
an
d
s
p
ee
d
,
p
o
s
itio
n
in
g
it
as
a
p
o
wer
f
u
l
to
o
l
f
o
r
d
iv
er
s
e
r
ea
l
-
wo
r
ld
ap
p
licat
io
n
s
.
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:
2
5
0
2
-
4
7
52
Dee
p
lea
r
n
in
g
u
tili
z
a
tio
n
in
S
u
n
d
a
n
ese
s
crip
t reco
g
n
itio
n
fo
r
cu
ltu
r
a
l p
r
eser
va
tio
n
(
R
o
s
a
lin
a
)
1761
2.
M
E
T
H
O
D
T
h
e
m
eth
o
d
o
l
o
g
y
f
o
r
th
e
r
esear
ch
o
n
d
ee
p
lear
n
i
n
g
u
tili
za
tio
n
in
Su
n
d
an
ese
s
cr
ip
t
r
ec
o
g
n
itio
n
f
o
r
cu
ltu
r
al
p
r
eser
v
atio
n
u
s
in
g
Y
OL
Ov
8
in
v
o
lv
es sev
er
al
k
e
y
s
tep
s
.
Firstl
y
,
d
ata
co
llectio
n
will in
v
o
lv
e
g
ath
er
in
g
a
d
iv
er
s
e
d
ataset
o
f
Su
n
d
an
ese
s
cr
ip
t
im
ag
es,
en
s
u
r
in
g
r
ep
r
esen
tatio
n
o
f
v
ar
i
o
u
s
s
ty
les
an
d
c
o
n
tex
ts
.
Pre
p
r
o
ce
s
s
in
g
s
tep
s
will
in
cl
u
d
e
im
ag
e
n
o
r
m
aliza
tio
n
a
n
d
au
g
m
en
tatio
n
t
o
en
h
a
n
ce
m
o
d
el
g
en
er
aliza
tio
n
.
Nex
t,
th
e
YOL
Ov
8
ar
ch
itectu
r
e
will b
e
im
p
lem
en
ted
f
o
r
o
b
j
ec
t d
etec
tio
n
,
cu
s
to
m
ized
to
r
e
co
g
n
ize
Su
n
d
a
n
ese
s
cr
ip
t
ch
ar
ac
ter
s
.
T
r
an
s
f
er
lear
n
in
g
will
b
e
em
p
lo
y
e
d
u
s
in
g
a
p
r
e
-
tr
ain
ed
m
o
d
el
o
n
a
lar
g
e
d
ataset
to
ex
p
ed
ite
tr
ain
in
g
o
n
th
e
Su
n
d
an
ese
s
c
r
ip
t
d
ataset.
T
h
e
m
o
d
el
will
b
e
f
in
e
-
tu
n
ed
u
s
in
g
th
e
c
o
llected
d
ataset,
with
h
y
p
er
p
ar
am
eter
tu
n
in
g
to
o
p
tim
ize
p
er
f
o
r
m
a
n
ce
.
E
v
alu
a
tio
n
will
b
e
co
n
d
u
cted
u
s
in
g
m
etr
ics
s
u
ch
as
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
s
co
r
e
,
with
a
f
o
cu
s
o
n
ac
cu
r
ac
y
in
Su
n
d
an
ese
s
cr
ip
t
ch
ar
ac
ter
d
e
tectio
n
.
T
h
e
m
o
d
el
will
also
b
e
test
ed
o
n
a
s
ep
ar
a
te
v
alid
atio
n
d
ataset
to
ass
ess
g
en
er
aliza
tio
n
.
L
astl
y
,
th
e
r
es
ea
r
ch
will
in
clu
d
e
a
q
u
alitativ
e
an
aly
s
is
o
f
th
e
cu
ltu
r
al
im
p
ac
t
o
f
Su
n
d
an
ese
s
cr
ip
t
r
ec
o
g
n
itio
n
,
co
n
s
id
er
in
g
f
ac
to
r
s
s
u
ch
as
th
e
p
r
eser
v
atio
n
o
f
h
e
r
itag
e
an
d
a
cc
ess
ib
ilit
y
o
f
th
e
s
cr
ip
t in
d
ig
ital e
n
v
ir
o
n
m
e
n
ts
.
2
.
1
.
YO
L
O
o
bje
c
t
det
ec
t
io
n
a
lg
o
rit
hm
YOL
O,
cr
ea
ted
b
y
J
o
s
ep
h
R
e
d
m
o
n
a
n
d
Ali
Far
h
ad
i,
is
a
r
e
n
o
wn
ed
m
o
d
el
f
o
r
o
b
ject
d
ete
ctio
n
an
d
im
ag
e
s
eg
m
en
tatio
n
,
f
ir
s
t
i
n
tr
o
d
u
ce
d
in
2
0
1
5
.
YOL
Ov
8
,
t
h
e
latest
v
er
s
io
n
,
in
co
r
p
o
r
ate
s
n
ew
f
ea
tu
r
es
a
n
d
en
h
an
ce
m
e
n
ts
to
im
p
r
o
v
e
p
e
r
f
o
r
m
a
n
ce
an
d
f
lex
ib
ilit
y
.
Y
OL
Ov
8
f
ea
tu
r
es
a
b
ac
k
b
o
n
e
an
d
h
ea
d
as
co
r
e
co
m
p
o
n
en
ts
o
f
its
co
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
(
C
NN)
.
I
t
b
u
ild
s
o
n
th
e
C
S
ar
ch
itectu
r
e,
with
th
ir
ty
-
f
iv
e
co
n
v
o
l
u
tio
n
al
lay
e
r
s
an
d
cr
o
s
s
-
s
tag
e
p
ar
tial
co
n
n
ec
tio
n
s
th
at
f
ac
ilit
ate
ef
f
icien
t
d
ata
tr
an
s
f
er
b
etwe
en
la
y
er
s
.
YOL
Ov
8
'
s
h
ea
d
p
r
ed
icts
b
o
u
n
d
in
g
b
o
x
es,
ev
alu
ates
o
b
jec
ts
,
an
d
d
eter
m
in
es
class
p
r
o
b
ab
ilit
ies
u
s
in
g
th
e
f
o
llo
win
g
f
o
r
m
u
la
f
o
r
b
o
u
n
d
in
g
b
o
x
p
r
e
d
ictio
n
:
=
(
,
,
,
ℎ
)
(
1
)
w
h
er
e,
an
d
ar
e
ca
lc
u
lated
as:
=
(
̂
)
+
(
2
)
=
(
̂
)
+
(
3
)
Her
e,
σ
is
th
e
s
ig
m
o
id
f
u
n
ctio
n
th
at
m
ap
s
th
e
o
u
tp
u
t
to
a
[
0
,
1
]
r
an
g
e.
̂
an
d
̂
ar
e
th
e
m
o
d
el'
s
r
aw
p
r
ed
ictio
n
s
f
o
r
th
e
ce
n
ter
co
o
r
d
in
ates,
an
d
an
d
ar
e
th
e
co
o
r
d
in
ates o
f
th
e
g
r
id
ce
ll.
an
d
ℎ
ar
e
ca
lcu
lated
as:
=
.
(
̂
)
(4
)
ℎ
=
ℎ
.
(
ℎ
̂
)
(
5
)
Her
e,
an
d
ℎ
ar
e
an
ch
o
r
b
o
x
d
im
en
s
io
n
s
,
an
d
̂
an
d
ℎ
̂
ar
e
th
e
m
o
d
el’
s
r
aw
p
r
e
d
ictio
n
s
f
o
r
wid
th
an
d
h
eig
h
t.
YOL
O
p
r
ed
icts
class
p
r
o
b
a
b
i
liti
es
f
o
r
ea
ch
b
o
u
n
d
in
g
b
o
x
.
Fo
r
ea
c
h
g
r
id
ce
ll,
YOL
O
o
u
tp
u
ts
th
e
p
r
o
b
a
b
ilit
y
o
f
ea
c
h
class
u
s
in
g
a
So
f
tMa
x
f
u
n
ctio
n
:
(
)
=
(
̂
)
∑
(
̂
)
(
6
)
w
h
er
e
̂
is
th
e
r
aw
s
co
r
e
f
o
r
class
an
d
th
e
d
en
o
m
in
at
o
r
is
th
e
s
u
m
o
f
ex
p
o
n
en
tials
o
f
s
co
r
es
f
o
r
all
clas
s
es
.
T
h
is
g
iv
es th
e
p
r
o
b
ab
ilit
y
d
is
tr
ib
u
tio
n
o
v
er
all
class
es f
o
r
th
e
d
etec
ted
o
b
ject.
YOL
O
also
p
r
ed
icts
a
co
n
f
id
e
n
ce
s
co
r
e
f
o
r
ea
ch
b
o
u
n
d
in
g
b
o
x
,
i
n
d
icatin
g
h
o
w
co
n
f
id
en
t
th
e
m
o
d
el
is
th
at
th
e
b
o
x
c
o
n
tain
s
an
o
b
j
ec
t a
n
d
h
o
w
ac
cu
r
ate
th
e
b
o
x
is
:
=
(
I
o
U)
(
7
)
w
h
er
e
o
b
jectn
ess
s
co
r
e
r
e
p
r
es
en
ts
th
e
p
r
o
b
ab
ilit
y
th
at
th
e
b
o
x
co
n
tain
s
an
o
b
ject
an
d
in
te
r
s
ec
tio
n
o
v
er
u
n
io
n
(
I
o
U)
m
ea
s
u
r
es
th
e
o
v
er
la
p
b
etwe
en
th
e
p
r
ed
icted
b
o
u
n
d
in
g
b
o
x
an
d
th
e
g
r
o
u
n
d
tr
u
th
b
o
u
n
d
in
g
b
o
x
.
YOL
Ov
8
d
etec
ts
o
b
jects
at
v
ar
io
u
s
s
ca
les
th
r
o
u
g
h
a
h
ie
r
ar
ch
ical
n
etwo
r
k
s
tr
u
ctu
r
e,
en
s
u
r
in
g
ac
c
u
r
ate
id
en
tific
atio
n
o
f
o
b
jects o
f
d
if
f
er
en
t sizes with
in
an
im
ag
e.
Fi
g
u
r
e
2
d
ep
icts
th
e
s
tr
u
ctu
r
e
o
f
YOL
Ov
8
[
2
6
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
6
,
No
.
3
,
Dec
em
b
er
20
24
:
1
7
5
9
-
1
7
6
8
1762
Fig
u
r
e
2
.
T
h
e
s
tr
u
ctu
r
e
o
f
YO
L
Ov
8
[
2
6
]
2
.
2
.
Da
t
a
c
o
llect
io
n a
nd
prepa
ra
t
io
n
I
n
th
e
d
ata
co
llectio
n
an
d
p
r
ep
ar
atio
n
p
h
ase,
a
d
iv
er
s
e
d
ataset
o
f
Su
n
d
a
n
ese
s
cr
ip
t
i
m
ag
es
was
m
eticu
lo
u
s
ly
ass
em
b
led
to
c
ap
tu
r
e
v
ar
io
u
s
s
ty
les
an
d
c
o
n
tex
ts
o
f
t
h
e
s
cr
ip
t.
T
h
is
d
ataset
in
clu
d
es
2
1
co
n
s
o
n
an
t
letter
s
an
d
1
0
n
u
m
er
als
(
0
to
9
)
,
a
m
o
u
n
tin
g
t
o
a
to
tal
o
f
3
1
d
is
tin
ct
ch
ar
a
cter
s
,
as
d
ep
icted
in
Fig
u
r
e
3
.
Fig
u
r
e
3
.
T
h
e
p
ictu
r
es
o
f
th
e
g
en
er
ated
Su
n
d
an
ese
letter
s
T
o
cr
ea
te
th
e
in
itial
d
ataset,
a
Py
th
o
n
s
cr
ip
t
was
u
s
ed
.
T
h
is
s
cr
ip
t
g
en
er
ated
im
ag
es
o
f
ea
ch
Su
n
d
an
ese
ch
ar
ac
ter
,
en
s
u
r
in
g
th
at
ev
er
y
c
h
ar
ac
ter
was
r
ep
r
esen
ted
in
its
b
asic
f
o
r
m
.
T
o
e
n
h
an
ce
th
e
m
o
d
el'
s
r
o
b
u
s
tn
ess
an
d
g
en
er
aliza
b
ilit
y
,
s
ev
er
al
a
u
g
m
en
tatio
n
tech
n
iq
u
es
wer
e
a
p
p
lied
.
T
h
ese
t
ec
h
n
iq
u
es
in
tr
o
d
u
ce
v
ar
iatio
n
s
in
s
ize,
p
o
s
itio
n
,
an
d
r
o
tatio
n
,
h
elp
in
g
th
e
m
o
d
el
lear
n
to
r
ec
o
g
n
ize
c
h
ar
a
cter
s
u
n
d
er
d
i
v
er
s
e
co
n
d
itio
n
s
.
T
h
e
au
g
m
en
tatio
n
tech
n
iq
u
es in
clu
d
e:
Scalin
g
:
=
(
8
)
R
o
tatio
n
:
=
[
(
)
−
(
)
s
in
(
)
(
)
]
(
9
)
T
r
an
s
latio
n
:
=
[
]
(
10
)
T
h
e
p
r
o
ce
s
s
es
d
escr
ib
ed
in
(
8
)
to
(
1
0
)
r
esu
lted
in
1
,
8
4
0
u
n
iq
u
e
letter
im
ag
es.
E
ac
h
i
m
ag
e
was
an
n
o
tated
u
s
in
g
R
o
b
o
f
l
o
w,
wh
ich
lab
eled
ea
ch
Su
n
d
an
ese
let
ter
.
Ad
d
itio
n
al
au
g
m
en
tatio
n
i
n
clu
d
ed
:
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:
2
5
0
2
-
4
7
52
Dee
p
lea
r
n
in
g
u
tili
z
a
tio
n
in
S
u
n
d
a
n
ese
s
crip
t reco
g
n
itio
n
fo
r
cu
ltu
r
a
l p
r
eser
va
tio
n
(
R
o
s
a
lin
a
)
1763
:
=
±
(
11
)
B
lu
r
r
in
g
:
ℎ
1
.
5
(
12
)
No
is
e:
6%
(
13
)
T
h
e
au
g
m
en
tatio
n
p
r
o
ce
s
s
es
d
escr
ib
ed
in
(
1
1
)
to
(
1
3
)
r
esu
lted
in
a
f
in
al
d
ataset
o
f
4
,
4
1
0
im
ag
es.
T
h
is
d
ataset
was
d
iv
id
ed
in
to
tr
ain
in
g
(
3
,
8
5
5
im
a
g
es),
v
alid
atio
n
(
3
6
6
im
ag
es),
an
d
test
s
ets
(
1
8
9
im
ag
es)
to
en
s
u
r
e
co
m
p
r
eh
en
s
iv
e
m
o
d
el
t
r
ain
in
g
an
d
ev
alu
atio
n
.
2
.
3
.
M
o
del
s
elec
t
io
n a
nd
cus
t
o
m
iza
t
io
n
T
h
e
YOL
Ov
8
m
o
d
el
was
tr
a
in
ed
u
s
in
g
t
h
e
au
g
m
en
ted
d
a
taset,
wh
ich
in
clu
d
ed
4
,
4
1
0
i
m
ag
es
o
f
Su
n
d
an
ese
ch
ar
ac
ter
s
.
T
h
e
p
r
im
ar
y
o
b
jectiv
e
o
f
th
e
tr
ain
in
g
p
r
o
ce
s
s
was
to
en
h
an
ce
th
e
m
o
d
el'
s
ab
ilit
y
to
ac
cu
r
ately
d
is
tin
g
u
is
h
b
etwe
e
n
th
e
3
1
d
if
f
er
e
n
t
Su
n
d
an
ese
c
h
ar
ac
ter
s
,
co
m
p
r
is
in
g
2
1
c
o
n
s
o
n
an
t
letter
s
an
d
1
0
n
u
m
er
als.
T
h
e
t
r
ain
in
g
was
c
o
n
d
u
cte
d
iter
ativ
ely
o
v
er
1
5
0
ep
o
ch
s
.
An
e
p
o
ch
r
ep
r
esen
ts
o
n
e
co
m
p
lete
p
ass
th
r
o
u
g
h
th
e
en
tire
d
ataset
d
u
r
i
n
g
tr
ain
i
n
g
.
T
h
e
iter
ativ
e
tr
ain
in
g
p
r
o
ce
s
s
allo
ws
th
e
m
o
d
el
to
g
r
a
d
u
ally
r
ef
in
e
its
p
ar
am
eter
s
an
d
im
p
r
o
v
e
it
s
p
er
f
o
r
m
an
ce
.
T
h
e
tr
ain
in
g
l
o
s
s
f
u
n
ctio
n
,
wh
ich
m
ea
s
u
r
es
th
e
m
o
d
el’
s
er
r
o
r
d
u
r
in
g
tr
ain
in
g
,
is
co
m
p
o
s
ed
o
f
th
r
ee
m
ain
co
m
p
o
n
en
ts
:
th
e
b
o
u
n
d
in
g
b
o
x
lo
s
s
,
th
e
o
b
jectn
ess
lo
s
s
,
an
d
th
e
class
lo
s
s
.
T
h
e
o
v
er
all
lo
s
s
f
u
n
ctio
n
f
o
r
YOL
Ov
8
is
g
iv
en
b
y
:
=
+
+
(
1
4
)
B
o
u
n
d
in
g
b
o
x
lo
s
s
is
u
s
ed
to
m
ea
s
u
r
e
th
e
d
if
f
er
e
n
ce
b
etwe
en
th
e
p
r
ed
icted
an
d
g
r
o
u
n
d
tr
u
th
b
o
u
n
d
in
g
b
o
x
es,
c
o
m
p
u
te
d
as:
=
.
+
.
(
1
5
)
w
h
er
e:
I
OU
l
o
s
s
is
th
e
I
o
U
lo
s
s
,
ca
lcu
lated
as:
=
1
−
.
L
o
ca
lizatio
n
lo
s
s
m
ea
s
u
r
es th
e
d
ev
iatio
n
o
f
th
e
p
r
ed
icted
b
o
u
n
d
in
g
b
o
x
f
r
o
m
th
e
g
r
o
u
n
d
tr
u
th
b
o
x
.
Ob
ject
l
o
s
s
is
u
s
ed
to
ev
alu
ate
h
o
w
well
th
e
m
o
d
el
p
r
ed
icts
th
e
p
r
esen
ce
s
o
f
an
o
b
ject
with
in
th
e
b
o
u
n
d
in
g
box:
=
−
(
,
ℎ
)
(
1
6
)
w
h
er
e
th
e
o
b
jectn
ess
s
co
r
e
in
d
icate
s
th
e
co
n
f
id
en
ce
t
h
at
an
o
b
ject
ex
is
ts
with
in
th
e
p
r
ed
icte
d
b
o
x
.
2
.
4
.
T
ra
ini
ng
a
nd
ev
a
lua
t
io
n
T
h
e
m
o
d
el
is
tr
ain
ed
u
s
in
g
t
h
e
au
g
m
e
n
ted
d
ataset,
wh
ich
in
clu
d
es
4
,
4
1
0
im
ag
es
o
f
Su
n
d
an
ese
ch
ar
ac
ter
s
,
with
a
f
o
c
u
s
o
n
o
p
tim
izin
g
its
ab
ilit
y
to
d
is
tin
g
u
i
s
h
am
o
n
g
t
h
e
3
1
d
if
f
e
r
en
t
Su
n
d
an
ese
ch
ar
ac
ter
s
.
T
h
e
tr
ain
in
g
p
r
o
ce
s
s
in
v
o
lv
es
an
iter
ativ
e
ap
p
r
o
ac
h
with
a
s
p
ec
if
ied
n
u
m
b
er
o
f
ep
o
c
h
s
.
Du
r
in
g
ea
c
h
e
p
o
ch
,
th
e
m
o
d
el
a
d
ju
s
ts
its
in
ter
n
al
p
ar
am
eter
s
b
ased
o
n
th
e
tr
ain
i
n
g
d
ata
t
o
im
p
r
o
v
e
its
p
er
f
o
r
m
an
ce
in
r
ec
o
g
n
izin
g
Su
n
d
an
ese
ch
a
r
ac
ter
s
.
B
y
tr
ain
in
g
o
v
er
m
u
ltip
le
ep
o
c
h
s
,
th
e
m
o
d
el
g
r
a
d
u
ally
lear
n
s
t
o
r
e
co
g
n
ize
Su
n
d
an
es
e
ch
ar
ac
ter
s
with
h
ig
h
e
r
ac
cu
r
a
cy
.
Af
ter
tr
ain
i
n
g
,
th
e
m
o
d
el's
p
er
f
o
r
m
a
n
ce
is
ev
alu
ated
u
s
in
g
m
etr
ics
s
u
ch
as
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
s
co
r
e.
Pre
cisi
o
n
m
ea
s
u
r
es th
e
p
r
o
p
o
r
tio
n
o
f
c
o
r
r
ec
tly
i
d
en
tifie
d
Su
n
d
an
ese
ch
ar
ac
ter
s
o
u
t o
f
all
c
h
ar
ac
ter
s
id
en
tifie
d
b
y
th
e
m
o
d
el.
=
+
(
1
7
)
R
ec
all
m
ea
s
u
r
es
th
e
p
r
o
p
o
r
t
io
n
o
f
co
r
r
ec
tly
id
en
tifie
d
S
u
n
d
an
ese
c
h
ar
ac
ter
s
o
u
t
o
f
all
ac
tu
al
Su
n
d
an
ese
ch
ar
ac
ter
s
in
th
e
d
a
taset.
=
+
(
1
8
)
T
h
e
F1
s
co
r
e
is
th
e
h
ar
m
o
n
i
c
m
ea
n
o
f
p
r
ec
is
io
n
an
d
r
ec
a
ll,
p
r
o
v
id
in
g
a
b
alan
ce
d
m
ea
s
u
r
e
o
f
th
e
m
o
d
el'
s
o
v
er
all
p
er
f
o
r
m
a
n
ce
in
r
e
co
g
n
izin
g
Su
n
d
a
n
ese
ch
ar
ac
ter
s
.
1
=
2
.
.
+
(
2
0
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
6
,
No
.
3
,
Dec
em
b
er
20
24
:
1
7
5
9
-
1
7
6
8
1764
2
.
5
.
Cultura
l
im
pa
c
t
a
na
ly
s
i
s
T
h
e
cu
ltu
r
al
im
p
ac
t
a
n
aly
s
is
ass
es
s
es
h
o
w
th
e
Su
n
d
an
ese
s
cr
ip
t
r
ec
o
g
n
itio
n
m
o
d
el
co
n
tr
i
b
u
tes
to
th
e
p
r
eser
v
atio
n
o
f
Su
n
d
a
n
ese
cu
ltu
r
al
h
er
itag
e.
I
t
c
o
n
s
id
er
s
f
a
cto
r
s
s
u
ch
as
th
e
s
cr
ip
t'
s
ac
ce
s
s
ib
ilit
y
in
d
ig
ital
en
v
ir
o
n
m
en
ts
an
d
its
r
o
le
in
m
ain
tain
in
g
cu
ltu
r
al
id
en
ti
ty
.
B
y
en
ab
lin
g
th
e
r
ec
o
g
n
i
tio
n
o
f
Su
n
d
an
ese
ch
ar
ac
ter
s
,
th
e
m
o
d
el
h
el
p
s
d
ig
itize
an
d
p
r
eser
v
e
Su
n
d
an
ese
tex
ts
an
d
d
o
cu
m
en
ts
.
T
h
is
en
h
an
ce
m
en
t
in
cr
ea
s
es
th
e
ac
ce
s
s
ib
ilit
y
o
f
Su
n
d
a
n
ese
cu
ltu
r
e
to
a
wid
er
au
d
ie
n
ce
,
c
o
n
tr
ib
u
tin
g
to
t
h
e
lo
n
g
ev
ity
o
f
th
e
cu
ltu
r
al
h
er
itag
e
an
d
en
s
u
r
in
g
th
at
f
u
tu
r
e
g
en
er
atio
n
s
ca
n
ac
ce
s
s
an
d
ap
p
r
ec
iate
Su
n
d
an
ese
liter
atu
r
e
an
d
tr
ad
itio
n
s
.
T
o
q
u
an
tify
th
e
cu
lt
u
r
al
im
p
ac
t,
th
e
f
o
llo
win
g
m
et
r
ics an
d
f
o
r
m
u
las is
u
s
ed
:
Dig
itizatio
n
r
ate
is
u
s
ed
to
m
ea
s
u
r
es
th
e
ex
ten
t
to
wh
ich
p
h
y
s
ical
Su
n
d
an
ese
tex
ts
h
av
e
b
ee
n
co
n
v
er
ted
in
to
d
i
g
ital f
o
r
m
at
:
=
100
(
2
1
)
a
cc
ess
ib
ilit
y
s
co
r
e
is
u
s
ed
to
a
s
s
es
s
es
h
o
w
ac
ce
s
s
ib
le
Su
n
d
a
n
ese
tex
ts
h
av
e
b
ec
o
m
e
d
u
e
to
d
ig
italizatio
n
.
T
h
is
s
co
r
e
co
u
ld
b
e
b
ased
o
n
f
ac
to
r
s
lik
e
th
e
n
u
m
b
er
o
f
d
ig
i
tal
p
latf
o
r
m
s
h
o
s
tin
g
Su
n
d
an
ese
tex
ts
an
d
th
e
f
r
eq
u
e
n
cy
o
f
ac
ce
s
s
:
=
100
(
2
2
)
c
u
ltu
r
al
en
g
ag
e
m
en
t
in
d
ex
is
u
s
ed
to
m
ea
s
u
r
es
th
e
lev
el
o
f
en
g
ag
em
en
t
with
Su
n
d
a
n
ese
cu
ltu
r
al
m
ater
ials
p
o
s
t
-
d
ig
itizatio
n
,
s
u
ch
as
u
s
er
in
ter
ac
tio
n
s
,
ed
u
ca
tio
n
al
u
s
e,
an
d
p
u
b
lic
in
ter
est
:
=
100
(
2
3
)
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
e
tr
ain
in
g
o
f
th
e
YOL
Ov
8
m
o
d
el
o
n
th
e
cu
r
ate
d
an
d
au
g
m
en
ted
Su
n
d
an
ese
letter
d
ataset
r
esu
lted
in
a
p
r
ec
is
io
n
o
f
ap
p
r
o
x
im
atel
y
9
5
%
af
ter
1
5
0
e
p
o
ch
s
.
Pre
ci
s
io
n
is
a
cr
itical
m
etr
ic
th
at
r
ef
lects
th
e
ac
cu
r
ac
y
with
wh
ich
th
e
m
o
d
el
co
r
r
ec
tly
id
en
tifie
s
Su
n
d
an
ese
ch
ar
ac
ter
s
with
in
im
ag
es.
T
h
is
h
ig
h
p
r
ec
is
io
n
d
em
o
n
s
tr
ates
th
e
m
o
d
el'
s
ef
f
ec
tiv
en
ess
in
d
is
tin
g
u
is
h
in
g
am
o
n
g
th
e
3
1
u
n
iq
u
e
Su
n
d
an
ese
letter
s
an
d
n
u
m
b
er
s
.
Ach
ie
v
in
g
a
p
r
ec
is
io
n
o
f
9
5
%
in
d
icate
s
th
at
th
e
m
o
d
el
h
as
a
lo
w
f
alse
-
p
o
s
itiv
e
r
ate,
m
ea
n
in
g
it
co
r
r
ec
tly
id
en
tifie
s
th
e
m
ajo
r
ity
o
f
Su
n
d
an
ese
ch
ar
ac
ter
s
in
t
h
e
d
ataset.
T
h
is
h
ig
h
lev
el
o
f
ac
cu
r
ac
y
is
cr
u
cial
f
o
r
ap
p
licatio
n
s
s
u
ch
as
d
ig
itizin
g
an
d
p
r
eser
v
in
g
Su
n
d
a
n
ese
tex
ts
an
d
d
o
cu
m
en
ts
,
wh
er
e
an
y
er
r
o
r
s
in
ch
ar
ac
ter
r
ec
o
g
n
itio
n
c
o
u
ld
le
ad
to
m
is
in
ter
p
r
etatio
n
o
r
lo
s
s
o
f
cu
ltu
r
al
in
f
o
r
m
atio
n
.
T
h
e
p
lo
t
o
f
th
e
m
o
d
el'
s
r
esu
lt
s
u
m
m
ar
y
,
s
h
o
w
n
in
Fig
u
r
e
4
,
v
is
u
ally
r
ep
r
esen
ts
th
e
tr
ain
in
g
p
r
o
g
r
ess
an
d
ac
h
iev
ed
p
r
ec
is
io
n
,
p
r
o
v
id
i
n
g
a
clea
r
o
v
er
v
iew
o
f
th
e
m
o
d
el'
s
p
er
f
o
r
m
a
n
ce
o
v
er
th
e
tr
ain
in
g
e
p
o
ch
s
.
Fig
u
r
e
4
.
T
h
e
p
lo
t
o
f
m
o
d
el
r
e
s
u
lt su
m
m
ar
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:
2
5
0
2
-
4
7
52
Dee
p
lea
r
n
in
g
u
tili
z
a
tio
n
in
S
u
n
d
a
n
ese
s
crip
t reco
g
n
itio
n
fo
r
cu
ltu
r
a
l p
r
eser
va
tio
n
(
R
o
s
a
lin
a
)
1765
Me
an
wh
ile
,
Fig
u
r
e
5
d
ep
icts
th
e
m
o
d
el'
s
p
r
ed
ictio
n
s
o
n
a
g
iv
en
s
et
o
f
test
im
ag
es
f
o
r
th
e
ch
ar
ac
ter
s
"za"
,
"v
a"
,
"d
a"
,
"la"
,
"f
a"
,
an
d
"ja"
alo
n
g
with
th
eir
r
esp
ec
t
iv
e
ac
cu
r
ac
ies.
T
h
e
m
o
d
el
ac
h
iev
ed
an
ac
cu
r
ac
y
o
f
7
0
%
f
o
r
"z
a"
,
8
0
%
f
o
r
"v
a"
,
7
0
%
f
o
r
"d
a"
,
6
8
%
f
o
r
"la"
,
6
0
%
f
o
r
"f
a"
,
a
n
d
5
0
%
f
o
r
"ja
"
.
T
h
ese
ac
cu
r
ac
ies
r
ef
lect
th
e
m
o
d
el'
s
p
er
f
o
r
m
a
n
ce
in
co
r
r
ec
tly
id
e
n
tify
in
g
ea
ch
Su
n
d
an
ese
ch
ar
a
cter
with
in
th
e
test
im
ag
es.
W
h
ile
s
o
m
e
ch
ar
ac
ter
s
h
av
e
h
ig
h
er
ac
c
u
r
ac
ies
th
an
o
th
e
r
s
,
th
e
o
v
er
all
r
esu
lts
d
em
o
n
s
tr
ate
th
e
m
o
d
el'
s
ca
p
ab
ilit
y
to
r
ec
o
g
n
ize
Su
n
d
an
ese
ch
ar
ac
ter
s
with
v
ar
y
in
g
d
eg
r
ee
s
o
f
ac
cu
r
ac
y
.
Fu
r
th
er
an
aly
s
is
m
ay
b
e
n
ee
d
ed
to
im
p
r
o
v
e
th
e
m
o
d
el'
s
p
er
f
o
r
m
an
ce
,
esp
ec
ially
f
o
r
ch
ar
ac
ter
s
with
lo
wer
ac
cu
r
ac
ies,
to
en
h
an
ce
its
ef
f
ec
tiv
en
ess
in
ap
p
licatio
n
s
s
u
ch
as d
ig
itizin
g
a
n
d
p
r
eser
v
in
g
Su
n
d
an
ese
tex
ts
an
d
d
o
c
u
m
e
n
ts
.
Fig
u
r
e
5
.
T
h
e
m
o
d
el
p
r
e
d
ictio
n
o
n
g
iv
en
s
ets o
f
test
im
ag
es
Fig
u
r
e
6
s
h
o
wca
s
es
th
e
m
o
d
el
'
s
p
r
ed
ictio
n
s
f
o
r
th
e
test
p
h
r
a
s
e
"n
am
a
s
ay
a
r
ak
a"
ca
p
tu
r
e
d
th
r
o
u
g
h
a
web
ca
m
.
T
h
e
m
o
d
el'
s
ac
cu
r
ac
y
f
o
r
th
is
task
is
r
ep
o
r
ted
to
b
e
less
th
an
7
0
%.
T
h
is
s
u
g
g
ests
t
h
at
th
e
m
o
d
el
m
ay
s
tr
u
g
g
le
with
ac
cu
r
ately
r
ec
o
g
n
izin
g
an
d
d
is
tin
g
u
is
h
in
g
th
e
Su
n
d
a
n
ese
ch
a
r
ac
ter
s
in
th
e
p
h
r
ase
wh
en
ca
p
tu
r
ed
in
r
ea
l
-
tim
e
th
r
o
u
g
h
a
web
ca
m
.
T
h
e
lo
wer
ac
c
u
r
a
cy
co
u
l
d
b
e
attr
ib
u
ted
to
v
ar
i
o
u
s
f
ac
to
r
s
s
u
c
h
as
lig
h
tin
g
co
n
d
itio
n
s
,
ca
m
er
a
q
u
ality
,
an
d
im
ag
e
p
r
o
ce
s
s
in
g
is
s
u
es th
at
af
f
ec
t th
e
clar
ity
an
d
q
u
ality
o
f
th
e
in
p
u
t
im
ag
es.
I
m
p
r
o
v
in
g
th
e
m
o
d
el'
s
p
er
f
o
r
m
an
ce
f
o
r
r
ea
l
-
tim
e
a
p
p
licatio
n
s
m
ay
r
eq
u
i
r
e
ad
d
iti
o
n
al
p
r
ep
r
o
ce
s
s
in
g
s
tep
s
,
m
o
d
el
tu
n
in
g
,
o
r
tr
ain
in
g
o
n
a
m
o
r
e
d
iv
e
r
s
e
d
ataset
th
at
in
clu
d
es
web
ca
m
-
ca
p
tu
r
ed
im
ag
es
to
en
h
a
n
ce
its
r
o
b
u
s
tn
ess
an
d
ac
cu
r
ac
y
in
s
u
ch
s
ce
n
ar
io
s
.
Fig
u
r
e
6
.
T
h
e
m
o
d
el
p
r
e
d
ictio
n
o
n
g
iv
en
“
n
am
a
s
ay
a
r
a
k
a”
t
est wo
r
d
s
th
r
o
u
g
h
web
ca
m
T
h
e
Su
n
d
an
ese
s
cr
ip
t
r
ec
o
g
n
i
tio
n
m
o
d
el
h
as
d
e
m
o
n
s
tr
ated
s
ig
n
if
ican
t
p
o
ten
tial
in
p
r
eser
v
in
g
an
d
p
r
o
m
o
tin
g
Su
n
d
an
ese
c
u
ltu
r
al
h
er
itag
e.
B
y
c
o
n
v
e
r
tin
g
d
elica
te
h
is
to
r
ical
m
an
u
s
cr
ip
ts
in
to
d
ig
ital
f
o
r
m
ats,
t
h
e
m
o
d
el
en
s
u
r
es
th
at
th
ese
v
alu
ab
le
tex
ts
ar
e
p
r
eser
v
ed
a
n
d
a
cc
ess
ib
le
to
f
u
tu
r
e
g
en
er
atio
n
s
.
T
h
is
d
ig
itizatio
n
p
r
o
ce
s
s
is
cr
u
cial
f
o
r
r
esear
ch
er
s
s
p
ec
ializin
g
in
Su
n
d
a
n
ese
liter
atu
r
e,
as
it
allo
ws
f
o
r
ea
s
ier
an
aly
s
is
an
d
d
ee
p
er
u
n
d
er
s
tan
d
in
g
o
f
th
e
s
cr
ip
t'
s
cu
ltu
r
al
s
u
b
tleties
.
Ad
d
itio
n
ally
,
th
e
m
o
d
el
’
s
r
e
al
-
tim
e
r
ec
o
g
n
itio
n
ca
p
ab
ilit
ies
o
f
f
er
p
r
ac
tical
s
o
lu
tio
n
s
,
s
u
ch
as
a
m
o
b
ile
ap
p
th
at
tr
an
s
lates
Su
n
d
an
ese
t
ex
t
ca
p
tu
r
ed
b
y
a
s
m
ar
tp
h
o
n
e
ca
m
er
a
.
T
h
is
in
n
o
v
atio
n
n
o
t
o
n
ly
f
ac
ilit
ates
co
m
m
u
n
icatio
n
b
u
t
also
p
r
o
m
o
t
es
th
e
in
teg
r
atio
n
o
f
Su
n
d
an
ese
s
cr
ip
t in
to
d
aily
u
s
e.
Desp
ite
th
ese
ad
v
an
ce
m
en
ts
,
t
h
e
cu
ltu
r
al
im
p
ac
t
an
aly
s
is
,
as
d
etailed
in
T
a
b
le
1
,
i
n
d
icate
s
th
at
th
er
e
is
s
till
s
u
b
s
tan
tial
r
o
o
m
f
o
r
i
m
p
r
o
v
e
m
en
t.
T
h
e
d
ig
itizatio
n
r
ate
a
n
d
u
s
er
e
n
g
ag
e
m
en
t
w
ith
d
ig
ital
te
x
ts
ar
e
r
elativ
ely
m
o
d
est
at
6
0
%.
Ho
wev
er
,
th
e
in
teg
r
atio
n
o
f
Su
n
d
an
ese
tex
ts
o
n
d
ig
ital
p
latf
o
r
m
s
is
lo
wer
,
at
4
5
%,
r
ef
lectin
g
lim
ited
o
n
lin
e
v
is
ib
ilit
y
.
Ad
d
itio
n
ally
,
th
e
av
aila
b
ilit
y
o
f
tr
a
n
s
latio
n
to
o
ls
an
d
ed
u
ca
tio
n
al
r
eso
u
r
ce
s
is
n
o
t
o
p
tim
al,
with
s
co
r
es
o
f
5
0
%
an
d
5
5
%,
r
esp
ec
tiv
ely
.
T
h
e
cu
ltu
r
al
c
o
n
ten
t
r
e
p
r
esen
t
atio
n
is
p
ar
ticu
lar
ly
wea
k
,
at
4
0
%,
s
u
g
g
esti
n
g
th
at
Su
n
d
an
ese
cu
ltu
r
al
m
ater
ials
ar
e
u
n
d
er
r
ep
r
esen
te
d
in
d
ig
ital
f
o
r
m
ats.
T
h
ese
r
esu
lts
h
ig
h
lig
h
t
t
h
e
n
ee
d
f
o
r
m
o
r
e
f
o
c
u
s
ed
ef
f
o
r
ts
to
en
h
a
n
ce
th
e
ac
ce
s
s
ib
ilit
y
,
v
is
ib
ilit
y
,
an
d
e
n
g
ag
em
e
n
t
with
Su
n
d
an
ese
s
cr
ip
t in
d
i
g
ital e
n
v
ir
o
n
m
en
ts
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
6
,
No
.
3
,
Dec
em
b
er
20
24
:
1
7
5
9
-
1
7
6
8
1766
T
ab
le
1
.
Acc
ess
ib
ilit
y
s
co
r
e
r
e
s
u
lt
A
sp
e
c
t
S
c
o
r
e
(
%)
D
i
g
i
t
i
z
a
t
i
o
n
r
a
t
e
60
I
n
t
e
g
r
a
t
i
o
n
o
n
d
i
g
i
t
a
l
p
l
a
t
f
o
r
ms
45
U
ser e
n
g
a
g
e
me
n
t
w
i
t
h
d
i
g
i
t
a
l
t
e
x
t
s
6
0
A
v
a
i
l
a
b
i
l
i
t
y
o
f
t
r
a
n
s
l
a
t
i
o
n
t
o
o
l
s
50
Ed
u
c
a
t
i
o
n
a
l
r
e
s
o
u
r
c
e
a
v
a
i
l
a
b
i
l
i
t
y
55
C
u
l
t
u
r
a
l
c
o
n
t
e
n
t
r
e
p
r
e
se
n
t
a
t
i
o
n
40
4.
CO
NCLU
SI
O
N
T
h
e
ap
p
licatio
n
o
f
d
ee
p
lea
r
n
i
n
g
,
s
p
ec
if
ically
th
e
YOL
Ov
8
m
o
d
el,
in
r
ec
o
g
n
izin
g
Su
n
d
a
n
ese
s
cr
ip
t
is
a
v
ital
ad
v
a
n
ce
m
en
t
f
o
r
p
r
eser
v
in
g
cu
ltu
r
al
h
er
itag
e.
T
h
is
m
o
d
el
h
as
d
em
o
n
s
tr
ated
its
ca
p
ab
ilit
y
b
y
ac
h
iev
in
g
a
h
ig
h
p
r
ec
is
io
n
o
f
ap
p
r
o
x
im
ately
9
5
%
af
ter
1
5
0
ep
o
ch
s
,
h
ig
h
lig
h
tin
g
i
ts
ef
f
ec
tiv
en
ess
in
ac
cu
r
ately
id
en
tif
y
in
g
3
1
d
i
s
tin
ct
Su
n
d
an
ese
ch
ar
ac
ter
s
.
T
h
is
ac
cu
r
ac
y
is
cr
u
cial
f
o
r
d
ig
itizin
g
an
d
s
af
eg
u
ar
d
in
g
Su
n
d
an
ese
tex
ts
,
wh
ich
h
elp
s
en
s
u
r
e
th
eir
a
v
ailab
ilit
y
f
o
r
f
u
tu
r
e
g
en
e
r
atio
n
s
.
Desp
ite
th
ese
p
r
o
m
is
in
g
r
esu
lts
,
th
e
m
o
d
el'
s
r
ea
l
-
wo
r
ld
p
er
f
o
r
m
a
n
ce
r
e
v
e
als
ar
ea
s
n
ee
d
in
g
im
p
r
o
v
em
e
n
t.
T
h
e
d
ig
itizatio
n
r
ate
an
d
u
s
er
en
g
ag
em
e
n
t
ar
e
cu
r
r
en
tly
at
6
0
%,
an
d
th
e
in
te
g
r
atio
n
o
f
Su
n
d
an
ese
tex
ts
o
n
d
ig
ital
p
latf
o
r
m
s
is
o
n
ly
4
5
%.
Ad
d
itio
n
ally
,
tr
a
n
s
latio
n
to
o
ls
an
d
ed
u
ca
tio
n
al
r
eso
u
r
ce
s
ar
e
lac
k
in
g
,
with
s
co
r
e
s
o
f
5
0
%
an
d
5
5
%,
r
esp
ec
tiv
ely
.
Mo
s
t
n
o
tab
ly
,
c
u
ltu
r
al
co
n
ten
t
r
ep
r
esen
tatio
n
is
cr
itically
lo
w
at
4
0
%,
in
d
icatin
g
a
s
ig
n
if
ican
t
g
ap
in
th
e
d
i
g
ital
p
r
esen
ce
o
f
Su
n
d
an
ese
m
ater
ials
.
T
o
o
v
e
r
co
m
e
th
ese
ch
allen
g
es,
f
u
t
u
r
e
r
esear
ch
s
h
o
u
ld
aim
to
r
ef
in
e
th
e
YOL
Ov
8
m
o
d
e
l
f
o
r
b
etter
r
ea
l
-
tim
e
p
e
r
f
o
r
m
an
ce
an
d
r
o
b
u
s
tn
ess
.
T
h
e
r
e
is
also
a
n
ee
d
f
o
r
en
h
an
ce
d
v
is
ib
ilit
y
an
d
in
teg
r
atio
n
o
f
Su
n
d
a
n
ese
tex
ts
o
n
li
n
e,
alo
n
g
with
th
e
d
ev
el
o
p
m
e
n
t
o
f
m
o
r
e
e
f
f
ec
tiv
e
tr
an
s
latio
n
to
o
ls
an
d
ed
u
ca
tio
n
al
r
eso
u
r
ce
s
.
C
o
llab
o
r
ativ
e
ef
f
o
r
ts
f
r
o
m
r
esear
ch
e
r
s
,
tech
n
o
lo
g
y
d
ev
el
o
p
er
s
,
an
d
cu
ltu
r
al
o
r
g
an
izatio
n
s
ar
e
ess
en
tial
to
ad
v
an
cin
g
th
e
s
e
in
itiativ
es
an
d
en
s
u
r
in
g
th
e
co
m
p
r
e
h
en
s
iv
e
p
r
eser
v
atio
n
a
n
d
p
r
o
m
o
tio
n
o
f
Su
n
d
an
ese
h
er
ita
g
e
in
th
e
d
ig
ital e
r
a.
ACK
NO
WL
E
DG
E
M
E
NT
S
T
h
is
wo
r
k
was
s
u
p
p
o
r
ted
b
y
Un
iv
er
s
itas
Mu
ltime
d
ia
Nu
s
an
tar
a
an
d
Pre
s
id
en
t
Un
iv
er
s
ity
.
T
h
e
au
th
o
r
s
wo
u
l
d
lik
e
to
ex
p
r
ess
th
eir
g
r
atitu
d
e
f
o
r
th
e
r
eso
u
r
ce
s
,
s
u
p
p
o
r
t,
an
d
g
u
id
an
ce
p
r
o
v
id
ed
b
y
b
o
t
h
in
s
titu
tio
n
s
.
RE
F
E
R
E
NC
E
S
[
1
]
E.
S
u
mar
l
i
n
a
,
R
.
P
e
r
ma
n
a
,
a
n
d
U
.
D
a
r
sa,
“
T
h
e
r
o
l
e
o
f
su
n
d
a
n
e
s
e
l
e
t
t
e
r
s
a
s
t
h
e
o
n
e
o
f
i
d
e
n
t
i
t
y
a
n
d
l
a
n
g
u
a
g
e
p
r
e
s
e
r
v
e
r
,
”
2
0
2
0
,
d
o
i
:
1
0
.
4
1
0
8
/
e
a
i
.
9
-
11
-
2
0
1
9
.
2
2
9
5
0
3
7
.
[
2
]
K
.
K
a
r
y
o
n
o
,
B
.
M
.
A
b
d
u
l
l
a
h
,
A
.
C
o
t
g
r
a
v
e
,
A
.
B
r
a
s,
a
n
d
J.
C
u
l
l
e
n
,
“
F
i
e
l
d
st
u
d
i
e
s
o
f
t
h
e
A
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
mo
d
e
l
f
o
r
d
e
f
i
n
i
n
g
i
n
d
o
o
r
t
h
e
r
ma
l
c
o
mf
o
r
t
t
o
a
c
k
n
o
w
l
e
d
g
e
t
h
e
a
d
a
p
t
i
v
e
a
s
p
e
c
t
,
”
En
g
i
n
e
e
r
i
n
g
A
p
p
l
i
c
a
t
i
o
n
s
o
f
A
rt
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
1
3
3
,
p
.
1
0
8
3
8
1
,
Ju
l
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
n
g
a
p
p
a
i
.
2
0
2
4
.
1
0
8
3
8
1
.
[
3
]
M
.
I
.
F
i
a
n
t
y
,
M
.
E.
J
o
h
a
n
,
F
.
R
.
S
a
p
u
t
r
i
,
a
n
d
F
.
R
a
h
m
a
h
,
“
D
a
t
a
mi
n
i
n
g
a
n
d
v
i
s
u
a
l
i
z
a
t
i
o
n
f
o
r
t
o
d
d
l
e
r
n
u
t
r
i
t
i
o
n
mo
n
i
t
o
r
i
n
g
i
n
C
o
mm
u
n
i
t
y
H
e
a
l
t
h
C
e
n
t
e
r
s,”
J
o
u
rn
a
l
o
f
S
y
st
e
m
a
n
d
M
a
n
a
g
e
m
e
n
t
S
c
i
e
n
c
e
s
,
v
o
l
.
1
4
,
n
o
.
7
,
p
p
.
5
1
–
7
1
,
Ju
n
.
2
0
2
4
,
d
o
i
:
1
0
.
3
3
1
6
8
/
j
sms
.
2
0
2
4
.
0
7
0
3
.
[
4
]
L.
P
a
r
a
ma
A
r
t
h
a
,
A
.
R
a
t
n
a
sari
,
a
n
d
O
.
K
u
r
n
i
a
d
i
,
“
P
a
r
t
i
c
i
p
a
t
o
r
y
c
u
l
t
u
r
e
c
o
mm
u
n
i
c
a
t
i
o
n
i
n
t
h
e
p
r
e
ser
v
a
t
i
o
n
o
f
S
u
n
d
a
n
e
s
e
m
a
n
u
scr
i
p
t
s,
”
J
o
u
r
n
a
l
o
f
S
c
i
e
n
t
i
f
i
c
R
e
se
a
rc
h
,
E
d
u
c
a
t
i
o
n
,
a
n
d
T
e
c
h
n
o
l
o
g
y
(
J
S
RET)
,
v
o
l
.
2
,
n
o
.
3
,
p
p
.
1
3
2
7
–
1
3
3
6
,
A
u
g
.
2
0
2
3
,
d
o
i
:
1
0
.
5
8
5
2
6
/
j
sr
e
t
.
v
2
i
3
.
2
2
9
.
[
5
]
R
.
H
.
R
o
b
i
n
s
,
“
N
o
mi
n
a
l
a
n
d
v
e
r
b
a
l
d
e
r
i
v
a
t
i
o
n
i
n
S
u
n
d
a
n
e
se,
”
L
i
n
g
u
a
,
v
o
l
.
8
,
p
p
.
3
3
7
–
3
6
9
,
1
9
5
9
,
d
o
i
:
1
0
.
1
0
1
6
/
0
0
2
4
-
3
8
4
1
(
5
9
)
9
0
0
3
5
-
x
[
6
]
M
.
S
u
r
y
a
n
i
,
E
.
P
a
u
l
u
s
,
S
.
H
a
d
i
,
U
.
A
.
D
a
r
sa,
a
n
d
J.
C
.
B
u
r
i
e
,
“
T
h
e
h
a
n
d
w
r
i
t
t
e
n
S
u
n
d
a
n
e
se
p
a
l
m
l
e
a
f
ma
n
u
s
c
r
i
p
t
d
a
t
a
s
e
t
f
r
o
m
1
5
t
h
ce
n
t
u
r
y
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
D
o
c
u
m
e
n
t
An
a
l
y
si
s
a
n
d
Re
c
o
g
n
i
t
i
o
n
,
I
C
D
A
R
,
2
0
1
7
,
v
o
l
.
1
,
p
p
.
7
9
6
–
8
0
0
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
D
A
R
.
2
0
1
7
.
1
3
5
.
[
7
]
A
.
A
.
H
i
d
a
y
a
t
,
K
.
P
u
r
w
a
n
d
a
r
i
,
T
.
W
.
C
e
n
g
g
o
r
o
,
a
n
d
B
.
P
a
r
d
a
me
a
n
,
“
A
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
-
b
a
se
d
a
n
c
i
e
n
t
S
u
n
d
a
n
e
s
e
c
h
a
r
a
c
t
e
r
c
l
a
ssi
f
i
e
r
w
i
t
h
d
a
t
a
a
u
g
m
e
n
t
a
t
i
o
n
,
”
Pr
o
c
e
d
i
a
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
1
7
9
,
p
p
.
1
9
5
–
2
0
1
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
r
o
c
s
.
2
0
2
0
.
1
2
.
0
2
5
.
[
8
]
D
.
F
.
R
a
m
a
d
a
n
,
M
.
D
.
S
u
l
i
s
t
i
y
o
,
a
n
d
A
.
F
.
I
h
san
,
“
N
o
i
s
y
i
m
a
g
e
f
i
l
t
e
r
i
n
g
m
e
t
h
o
d
s
f
o
r
a
n
i
m
p
r
o
v
e
d
S
u
n
d
a
n
e
se
sc
r
i
p
t
h
a
n
d
w
r
i
t
i
n
g
c
l
a
ss
i
f
i
c
a
t
i
o
n
,
”
i
n
2
0
2
3
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
D
a
t
a
S
c
i
e
n
c
e
a
n
d
I
t
s
Ap
p
l
i
c
a
t
i
o
n
s
(
I
C
o
D
S
A)
,
A
u
g
.
2
0
2
3
,
p
p
.
4
5
4
–
4
5
9
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
o
D
S
A
5
8
5
0
1
.
2
0
2
3
.
1
0
2
7
6
4
2
0
.
[
9
]
A
.
H
.
S
e
t
i
a
n
i
n
g
r
u
m
,
K
.
H
u
l
l
i
y
a
h
a
n
d
M
.
F
.
A
mr
i
l
l
a
,
"
S
p
e
e
c
h
R
e
c
o
g
n
i
t
i
o
n
o
f
S
u
n
d
a
n
e
se
D
i
a
l
e
c
t
U
si
n
g
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
M
e
t
h
o
d
w
i
t
h
M
e
l
-
S
p
e
c
t
r
o
g
r
a
m
F
e
a
t
u
r
e
E
x
t
r
a
c
t
i
o
n
,
"
2
0
2
3
1
1
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
C
y
b
e
r
a
n
d
I
T
S
e
r
v
i
c
e
Ma
n
a
g
e
m
e
n
t
(
C
I
T
S
M)
,
M
a
k
a
ss
a
r
,
I
n
d
o
n
e
si
a
,
2
0
2
3
,
p
p
.
1
-
5
,
d
o
i
:
1
0
.
1
1
0
9
/
C
I
TSM
6
0
0
8
5
.
2
0
2
3
.
1
0
4
5
5
4
4
7
.
[
1
0
]
N
.
E.
S
a
f
i
t
r
i
,
A
.
Z
a
h
r
a
,
a
n
d
M
.
A
d
r
i
a
n
i
,
“
S
p
o
k
e
n
l
a
n
g
u
a
g
e
i
d
e
n
t
i
f
i
c
a
t
i
o
n
w
i
t
h
p
h
o
n
o
t
a
c
t
i
c
s
m
e
t
h
o
d
s o
n
M
i
n
a
n
g
k
a
b
a
u
,
S
u
n
d
a
n
e
se
,
a
n
d
J
a
v
a
n
e
se
l
a
n
g
u
a
g
e
s,
”
Pr
o
c
e
d
i
a
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
8
1
,
p
p
.
1
8
2
–
1
8
7
,
2
0
1
6
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
r
o
c
s
.
2
0
1
6
.
0
4
.
0
4
7
.
[
1
1
]
M
.
S
u
r
y
a
n
i
,
S
.
H
a
d
i
,
a
n
d
A
.
M
.
I
.
N
a
su
h
a
,
“
S
u
n
d
a
n
e
se
a
n
c
i
e
n
t
m
a
n
u
sc
r
i
p
t
r
e
t
r
i
e
v
a
l
s
y
st
e
m
c
o
m
p
a
r
i
so
n
o
f
t
w
o
p
r
o
b
a
b
i
l
i
t
y
a
p
p
r
o
a
c
h
e
s,
”
i
n
2
0
1
6
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
c
s
a
n
d
C
o
m
p
u
t
i
n
g
(
I
C
I
C
)
,
2
0
1
6
,
p
p
.
1
0
5
–
1
1
0
,
d
o
i
:
1
0
.
1
1
0
9
/
I
A
C
.
2
0
1
6
.
7
9
0
5
6
9
8
.
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:
2
5
0
2
-
4
7
52
Dee
p
lea
r
n
in
g
u
tili
z
a
tio
n
in
S
u
n
d
a
n
ese
s
crip
t reco
g
n
itio
n
fo
r
cu
ltu
r
a
l p
r
eser
va
tio
n
(
R
o
s
a
lin
a
)
1767
[
1
2
]
C
.
S
l
a
m
e
t
,
Y
.
A
.
G
e
r
h
a
n
a
,
D
.
S
.
M
a
y
l
a
w
a
t
i
,
M
.
A
.
R
a
m
d
h
a
n
i
,
a
n
d
N
.
Z.
S
i
l
mi
,
“
La
t
i
n
t
o
S
u
n
d
a
n
e
s
e
s
c
r
i
p
t
c
o
n
v
e
r
si
o
n
u
si
n
g
F
i
n
i
t
e
S
t
a
t
e
a
u
t
o
ma
t
a
a
l
g
o
r
i
t
h
m,
”
i
n
I
O
P
C
o
n
f
e
r
e
n
c
e
S
e
r
i
e
s:
M
a
t
e
r
i
a
l
s
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
ri
n
g
,
D
e
c
.
2
0
1
8
,
v
o
l
.
4
3
4
,
p
.
0
1
2
0
6
3
,
d
o
i
:
1
0
.
1
0
8
8
/
1
7
5
7
-
8
9
9
X
/
4
3
4
/
1
/
0
1
2
0
6
3
.
[
1
3
]
E.
P
a
u
l
u
s,
M
.
S
u
r
y
a
n
i
,
S
.
H
a
d
i
,
a
n
d
F
.
N
a
t
si
r
,
“
A
n
i
n
i
t
i
a
l
s
t
u
d
y
t
o
so
l
v
e
i
mb
a
l
a
n
c
e
S
u
n
d
a
n
e
se
h
a
n
d
w
r
i
t
t
e
n
d
a
t
a
set
i
n
c
h
a
r
a
c
t
e
r
r
e
c
o
g
n
i
t
i
o
n
,
”
i
n
2
0
1
8
T
h
i
r
d
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
c
s
a
n
d
C
o
m
p
u
t
i
n
g
(
I
C
I
C
)
,
O
c
t
.
2
0
1
8
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
I
A
C
.
2
0
1
8
.
8
7
8
0
4
9
6
.
[
1
4
]
I
.
N
.
Y
u
l
i
t
a
,
A
.
H
i
d
a
y
a
t
,
A
.
S
.
A
b
d
u
l
l
a
h
,
a
n
d
R
.
M
.
A
w
a
n
g
g
a
,
“
F
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
a
n
a
l
y
s
i
s
f
o
r
h
i
d
d
e
n
mark
o
v
m
o
d
e
l
s
i
n
S
u
n
d
a
n
e
s
e
sp
e
e
c
h
r
e
c
o
g
n
i
t
i
o
n
,
”
T
EL
K
O
MN
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
El
e
c
t
ro
n
i
c
s a
n
d
C
o
n
t
r
o
l
)
,
v
o
l
.
1
6
,
n
o
.
5
,
p
.
2
1
9
1
,
O
c
t
.
2
0
1
8
,
d
o
i
:
1
0
.
1
2
9
2
8
/
t
e
l
k
o
mn
i
k
a
.
v
1
6
i
5
.
7
9
2
7
.
[
1
5
]
D
a
f
f
a
A
r
i
f
a
d
i
l
a
h
,
N
o
n
e
A
sr
i
y
a
n
i
k
,
a
n
d
A
g
u
n
g
P
a
m
b
u
d
i
,
“
S
u
n
d
a
S
c
r
i
p
t
D
e
t
e
c
t
i
o
n
U
s
i
n
g
Y
o
u
O
n
l
y
L
o
o
k
O
n
c
e
A
l
g
o
r
i
t
h
m,
”
J
o
u
rn
a
l
o
f
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
En
g
i
n
e
e
ri
n
g
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
3
,
n
o
.
2
,
p
p
.
6
0
6
–
6
1
3
,
2
0
2
4
,
d
o
i
:
1
0
.
5
9
9
3
4
/
j
a
i
e
a
.
v
3
i
2
.
4
4
3
.
[
1
6
]
A
.
A
.
H
i
d
a
y
a
t
,
K
.
P
u
r
w
a
n
d
a
r
i
,
T.
W
.
C
e
n
g
g
o
r
o
,
a
n
d
B
.
P
a
r
d
a
me
a
n
,
“
A
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
-
b
a
s
e
d
A
n
c
i
e
n
t
S
u
n
d
a
n
e
s
e
C
h
a
r
a
c
t
e
r
C
l
a
ssi
f
i
e
r
w
i
t
h
D
a
t
a
A
u
g
m
e
n
t
a
t
i
o
n
,
”
Pr
o
c
e
d
i
a
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
1
7
9
,
p
p
.
1
9
5
–
2
0
1
,
2
0
2
1
,
d
o
i
:
h
t
t
p
s
:
/
/
d
o
i
.
o
r
g
/
1
0
.
1
0
1
6
/
j
.
p
r
o
c
s.
2
0
2
0
.
1
2
.
0
2
5
[
1
7
]
S
.
N
.
R
a
h
maw
a
t
i
,
E
.
W
.
H
i
d
a
y
a
t
,
a
n
d
H
.
M
u
b
a
r
o
k
,
“
I
mp
l
e
me
n
t
a
si
d
e
e
p
l
e
a
r
n
i
n
g
p
a
d
a
p
e
n
g
e
n
a
l
a
n
A
k
s
a
r
a
S
u
n
d
a
me
n
g
g
u
n
a
k
a
n
met
o
d
e
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
,
”
I
N
S
ERT
:
I
n
f
o
rm
a
t
i
o
n
S
y
st
e
m
a
n
d
E
m
e
rg
i
n
g
T
e
c
h
n
o
l
o
g
y
J
o
u
r
n
a
l
,
v
o
l
.
2
,
n
o
.
1
,
p
p
.
4
6
–
5
8
,
2
0
2
1
,
d
o
i
:
1
0
.
2
3
8
8
7
/
i
n
sert
.
v
2
i
1
.
3
7
4
0
5
.
[
1
8
]
M
.
A
.
P
r
a
mesw
a
r
i
,
M
.
D
w
i
S
u
l
i
s
t
i
y
o
,
a
n
d
A
.
F
.
I
h
san
,
“
C
l
a
ss
i
f
i
c
a
t
i
o
n
o
f
h
a
n
d
w
r
i
t
t
e
n
S
u
n
d
a
n
e
se
scr
i
p
t
v
i
a
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
on
C
N
N
-
b
a
s
e
d
a
r
c
h
i
t
e
c
t
u
r
e
s,
”
i
n
2
0
2
3
3
r
d
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
El
e
c
t
r
o
n
i
c
a
n
d
El
e
c
t
ri
c
a
l
E
n
g
i
n
e
e
r
i
n
g
a
n
d
I
n
t
e
l
l
i
g
e
n
t
S
y
s
t
e
m
(
I
C
E3
I
S
)
,
A
u
g
.
2
0
2
3
,
p
p
.
4
0
1
–
4
0
6
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
E3
I
S
5
9
3
2
3
.
2
0
2
3
.
1
0
3
3
5
3
8
2
.
[
1
9
]
S
.
A
l
g
h
y
a
l
i
n
e
,
“
A
r
e
a
l
-
t
i
m
e
s
t
r
e
e
t
a
c
t
i
o
n
s
d
e
t
e
c
t
i
o
n
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
A
d
v
a
n
c
e
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
0
,
n
o
.
2
,
2
0
1
9
,
d
o
i
:
1
0
.
1
4
5
6
9
/
I
JA
C
S
A
.
2
0
1
9
.
0
1
0
0
2
4
3
.
[
2
0
]
S
.
A
l
g
h
y
a
l
i
n
e
,
“
R
e
a
l
-
t
i
me
J
o
r
d
a
n
i
a
n
l
i
c
e
n
se
p
l
a
t
e
r
e
c
o
g
n
i
t
i
o
n
u
s
i
n
g
d
e
e
p
l
e
a
r
n
i
n
g
,
”
J
o
u
r
n
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
rm
a
t
i
o
n
S
c
i
e
n
c
e
s
,
v
o
l
.
3
4
,
n
o
.
6
,
p
p
.
2
6
0
1
–
2
6
0
9
,
J
u
n
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
k
s
u
c
i
.
2
0
2
0
.
0
9
.
0
1
8
.
[
2
1
]
C
.
J
i
a
n
g
e
t
a
l
.
,
“
O
b
j
e
c
t
d
e
t
e
c
t
i
o
n
f
r
o
m
U
A
V
t
h
e
r
ma
l
i
n
f
r
a
r
e
d
i
m
a
g
e
s
a
n
d
v
i
d
e
o
s
u
s
i
n
g
Y
O
LO
mo
d
e
l
s,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
Ap
p
l
i
e
d
E
a
rt
h
O
b
ser
v
a
t
i
o
n
a
n
d
G
e
o
i
n
f
o
rm
a
t
i
o
n
,
v
o
l
.
1
1
2
,
p
.
1
0
2
9
1
2
,
A
u
g
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
a
g
.
2
0
2
2
.
1
0
2
9
1
2
.
[
2
2
]
J.
T
e
r
v
e
n
a
n
d
D
.
C
o
r
d
o
v
a
-
Es
p
a
r
z
a
,
“
A
c
o
mp
r
e
h
e
n
s
i
v
e
r
e
v
i
e
w
o
f
Y
O
L
O
:
f
r
o
m
Y
O
LO
v
1
t
o
Y
O
LO
v
8
a
n
d
b
e
y
o
n
d
,
”
a
r
Xi
v
p
re
p
ri
n
t
,
p
p
.
1
–
2
7
,
2
0
2
3
,
d
o
i
:
1
0
.
4
8
5
5
0
/
a
r
x
i
v
.
2
3
0
4
.
0
0
5
0
1
.
[
2
3
]
R
.
T
u
r
n
b
u
l
l
a
n
d
E.
M
a
n
n
i
x
,
“
D
e
t
e
c
t
i
n
g
a
n
d
r
e
c
o
g
n
i
z
i
n
g
c
h
a
r
a
c
t
e
r
s
i
n
G
r
e
e
k
p
a
p
y
r
i
w
i
t
h
Y
O
LO
v
8
,
D
e
i
T
a
n
d
S
i
mCL
R
,
”
a
r
Xi
v
p
re
p
ri
n
t
,
2
0
2
4
,
d
o
i
:
1
0
.
4
8
5
5
0
/
a
r
X
i
v
.
2
4
0
1
.
1
2
5
1
3
.
[
2
4
]
I
.
M
.
N
a
d
i
f
a
n
d
K
.
K
u
sr
i
n
i
,
“
Li
c
e
n
se
p
l
a
t
e
l
o
c
a
l
i
z
a
t
i
o
n
a
n
d
c
h
a
r
a
c
t
e
r
r
e
c
o
g
n
i
t
i
o
n
u
s
i
n
g
Y
O
LO
v
8
a
n
d
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
,
”
i
n
2
0
2
3
E
i
g
h
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
c
s
a
n
d
C
o
m
p
u
t
i
n
g
(
I
C
I
C
)
,
D
e
c
.
2
0
2
3
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
I
C
6
0
1
0
9
.
2
0
2
3
.
1
0
3
8
2
0
4
6
.
[
2
5
]
T.
A
.
S
h
y
a
a
a
n
d
A
.
A
.
H
a
s
h
i
m,
“
S
u
p
e
r
i
o
r
u
s
e
o
f
Y
O
LO
v
8
t
o
e
n
h
a
n
c
e
c
a
r
l
i
c
e
n
se
p
l
a
t
e
s
d
e
t
e
c
t
i
o
n
sp
e
e
d
a
n
d
a
c
c
u
r
a
c
y
,
”
Re
v
u
e
d
’
I
n
t
e
l
l
i
g
e
n
c
e
Ar
t
i
f
i
c
i
e
l
l
e
,
v
o
l
.
3
8
,
n
o
.
1
,
p
p
.
1
3
9
–
1
4
5
,
F
e
b
.
2
0
2
4
,
d
o
i
:
1
0
.
1
8
2
8
0
/
r
i
a
.
3
8
0
1
1
4
.
[
2
6
]
H
.
F
a
k
h
r
u
r
r
o
j
a
,
D
.
P
r
a
mes
t
i
,
A
.
R
.
H
i
d
a
y
a
t
u
l
l
a
h
,
A
.
A
.
F
a
s
h
i
h
u
l
l
i
s
a
n
,
H
.
B
a
n
g
k
i
t
,
a
n
d
N
.
I
smai
l
,
“
A
u
t
o
m
a
t
e
d
L
i
c
e
n
se
p
l
a
t
e
d
e
t
e
c
t
i
o
n
a
n
d
r
e
c
o
g
n
i
t
i
o
n
u
si
n
g
Y
O
L
O
v
8
a
n
d
O
C
R
w
i
t
h
t
e
l
l
o
d
r
o
n
e
c
a
m
e
r
a
,
”
i
n
2
0
2
3
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
,
C
o
n
t
r
o
l
,
I
n
f
o
rm
a
t
i
c
s
a
n
d
i
t
s
A
p
p
l
i
c
a
t
i
o
n
s
(
I
C
3
I
N
A)
,
O
c
t
.
2
0
2
3
,
p
p
.
2
0
6
–
2
1
1
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
3
I
N
A
6
0
8
3
4
.
2
0
2
3
.
1
0
2
8
5
7
5
0
.
[
2
7
]
R
.
R
.
B
,
G
.
S
w
a
t
h
i
,
E
.
H
i
m
e
sh
,
a
n
d
S
.
S
,
“
E
n
c
o
m
p
a
ss
i
n
g
Y
O
LO
v
8
a
n
d
Ef
f
i
c
i
e
n
t
N
e
t
B
7
f
o
r
A
u
t
o
m
a
t
i
c
l
i
c
e
n
s
e
p
l
a
t
e
i
d
e
n
t
i
f
i
c
a
t
i
o
n
,
”
i
n
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
C
o
m
p
u
t
i
n
g
,
C
o
m
m
u
n
i
c
a
t
i
o
n
,
a
n
d
I
n
t
e
l
l
i
g
e
n
t
S
y
s
t
e
m
s
(
I
C
C
C
I
S
)
,
N
o
v
.
2
0
2
3
,
p
p
.
6
9
4
–
7
0
0
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
C
C
I
S
6
0
3
6
1
.
2
0
2
3
.
1
0
4
2
5
7
7
5
.
[
2
8
]
D
.
R
e
i
s,
J.
K
u
p
e
c
,
J.
H
o
n
g
,
a
n
d
A
.
D
a
o
u
d
i
,
“
R
e
a
l
-
t
i
m
e
f
l
y
i
n
g
o
b
j
e
c
t
d
e
t
e
c
t
i
o
n
w
i
t
h
Y
O
LO
v
8
,
”
a
r
Xi
v
p
r
e
p
ri
n
t
,
2
0
2
3
,
d
o
i
:
1
0
.
4
8
5
5
0
/
a
r
x
i
v
.
2
3
0
5
.
0
9
9
7
2
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Ro
sa
li
n
a
is
a
lec
tu
re
r
a
t
P
re
sid
e
n
t
Un
i
v
e
rsity
,
sp
e
c
ializin
g
i
n
C
o
m
p
u
ter
S
c
ien
c
e
.
He
r
e
x
p
e
rti
se
l
ies
in
Artifi
c
ial
In
tell
ig
e
n
c
e
,
Ap
p
li
e
d
Co
m
p
u
ti
n
g
,
a
n
d
C
o
m
p
u
ti
n
g
M
e
th
o
d
o
l
o
g
ies
,
wh
e
re
s
h
e
a
d
v
a
n
c
e
s
k
n
o
wle
d
g
e
a
n
d
in
n
o
v
a
ti
v
e
so
lu
ti
o
n
s.
S
h
e
wo
r
k
a
ims
t
o
b
rid
g
e
th
e
o
re
ti
c
a
l
re
se
a
rc
h
with
p
ra
c
ti
c
a
l
imp
lem
e
n
tatio
n
,
d
riv
in
g
g
ro
wth
a
n
d
i
n
n
o
v
a
ti
o
n
i
n
th
e
tec
h
c
o
m
m
u
n
it
y
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
r
o
sa
li
n
a
@p
re
si
d
e
n
t.
a
c
.
id
.
Nun
ik
Afr
il
ia
n
a
is
a
d
e
d
ica
ted
p
ro
fe
ss
io
n
a
l
a
t
Un
i
v
e
rsitas
M
u
lt
ime
d
ia
Nu
sa
n
tara
(UMN),
sp
e
c
ializin
g
in
Co
m
p
u
ter
S
c
ien
c
e
.
He
r
e
x
p
e
rti
se
l
ies
in
a
p
p
li
e
d
c
o
m
p
u
ti
n
g
,
c
o
m
p
u
ti
n
g
m
e
th
o
d
o
l
o
g
ies
,
in
f
o
rm
a
ti
o
n
sy
s
tem
,
wh
e
r
e
sh
e
a
d
v
a
n
c
e
s
k
n
o
wle
d
g
e
a
n
d
in
n
o
v
a
ti
v
e
so
l
u
ti
o
n
s.
S
h
e
wo
rk
a
ims
to
b
ri
d
g
e
th
e
o
re
ti
c
a
l
re
se
a
rc
h
with
p
ra
c
ti
c
a
l
imp
lem
e
n
tatio
n
,
d
r
iv
i
n
g
g
r
o
wth
a
n
d
in
n
o
v
a
ti
o
n
i
n
t
h
e
tec
h
c
o
m
m
u
n
it
y
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
n
u
n
ik
@u
m
n
.
a
c
.
id
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
6
,
No
.
3
,
Dec
em
b
er
20
24
:
1
7
5
9
-
1
7
6
8
1768
Wira
n
to
H
e
r
r
y
Uto
m
o
is
a
d
isti
n
g
u
ish
e
d
P
ro
fe
ss
o
r
o
f
C
o
m
p
u
ter
S
c
ie
n
c
e
a
t
P
re
sid
e
n
t
Un
i
v
e
rsity
,
re
n
o
wn
e
d
fo
r
h
is
e
x
p
e
rti
se
in
S
e
rv
ice
Orie
n
ted
Arc
h
it
e
c
tu
re
(S
OA
)
,
Web
S
e
rv
ice
s,
En
terp
r
ise
S
e
rv
ice
Bu
s
(ES
B),
a
n
d
S
o
ftwa
re
a
s
a
S
e
rv
ice
(S
a
a
S
).
Wi
th
a
stro
n
g
a
c
a
d
e
m
ic
b
a
c
k
g
ro
u
n
d
a
n
d
p
ra
c
ti
c
a
l
e
x
p
e
rien
c
e
,
h
e
p
lay
s
a
p
i
v
o
tal
r
o
le
i
n
a
d
v
a
n
c
i
n
g
th
e
se
field
s
th
r
o
u
g
h
re
se
a
rc
h
,
tea
c
h
in
g
,
a
n
d
in
d
u
str
y
c
o
ll
a
b
o
ra
ti
o
n
.
His
wo
rk
h
a
s
c
o
n
tri
b
u
ted
sig
n
ifi
c
a
n
t
ly
to
th
e
u
n
d
e
rsta
n
d
i
n
g
a
n
d
imp
lem
e
n
tatio
n
o
f
m
o
d
e
r
n
so
ftwa
re
d
e
sig
n
p
rin
c
i
p
les
a
n
d
tec
h
n
o
l
o
g
ies
.
He
c
a
n
b
e
c
o
n
t
a
c
ted
a
t
e
m
a
il
:
wira
n
to
.
h
e
rry
@p
r
e
sid
e
n
t.
a
c
.
id
.
G
e
n
ta
S
a
h
u
r
i
a
d
e
d
ica
ted
lec
tu
re
r
a
t
P
re
sid
e
n
t
Un
i
v
e
rsity
'
s
In
fo
rm
a
ti
o
n
S
y
ste
m
s
S
tu
d
y
P
r
o
g
ra
m
,
b
rin
g
s
a
we
a
lt
h
o
f
k
n
o
wle
d
g
e
a
n
d
e
x
p
e
rti
se
t
o
h
i
s
ro
le.
Ho
l
d
in
g
a
M
a
ste
r'
s
d
e
g
re
e
in
I
n
fo
rm
a
ti
c
s
fro
m
t
h
e
sa
m
e
in
stit
u
ti
o
n
u
n
d
e
rsc
o
re
s
h
is
c
o
m
m
it
m
e
n
t
to
a
c
a
d
e
m
ic
e
x
c
e
ll
e
n
c
e
.
Wi
th
a
str
o
n
g
e
d
u
c
a
ti
o
n
a
l
b
a
c
k
g
r
o
u
n
d
a
n
d
a
p
a
ss
io
n
f
o
r
h
is
fiel
d
,
G
e
n
ta
p
lay
s
a
c
ru
c
ial
ro
le
in
sh
a
p
i
n
g
t
h
e
a
c
a
d
e
m
ic
jo
u
rn
e
y
o
f
h
is
stu
d
e
n
ts.
His
a
d
e
p
tn
e
ss
in
c
o
n
v
e
y
in
g
c
o
m
p
lex
c
o
n
c
e
p
ts
fo
ste
rs
a
d
y
n
a
m
ic
a
n
d
e
n
rich
in
g
lea
rn
in
g
e
n
v
ir
o
n
m
e
n
t.
He
d
e
d
ica
ti
o
n
to
h
is
field
a
n
d
h
is
a
b
il
it
y
t
o
i
n
sp
ire
stu
d
e
n
ts
m
a
k
e
h
im
a
v
a
lu
a
b
le
a
ss
e
t
to
P
re
si
d
e
n
t
U
n
iv
e
rsit
y
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
g
e
n
ta.sa
h
u
ri@p
re
sid
e
n
t.
a
c
.
id
.
Evaluation Warning : The document was created with Spire.PDF for Python.