I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
p
u
t
er
Science
Vo
l.
12
,
No
.
2
,
N
o
v
e
m
b
er
201
8
,
p
p
.
7
2
2
~7
2
8
I
SS
N:
2
5
0
2
-
4
7
5
2
,
DOI
: 1
0
.
1
1
5
9
1
/i
j
ee
cs.v
1
2
.i
2
.
p
p
7
2
2
-
7
2
8
722
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
co
r
e.
co
m/jo
u
r
n
a
ls
/in
d
ex
.
p
h
p
/
ijeec
s
O
n
the
Use o
f
E
d
g
e F
ea
tures
and
Ex
po
nential Deca
y
ing
Nu
m
ber of
Nodes
in
th
e
H
idden
La
y
ers for
H
a
ndw
ritt
en Sign
a
ture
Re
co
g
nition
T
eddy
Su
ry
a
G
un
a
w
a
n
1
,
M
ira
K
a
rt
i
w
i
2
1
El
e
c
tri
c
a
l
a
n
d
Co
m
p
u
ter E
n
g
in
e
e
rin
g
De
p
a
rtm
e
n
t,
In
tern
a
ti
o
n
a
l
Isl
a
m
ic Un
iv
e
rsit
y
M
a
la
y
si
a
,
M
a
la
y
sia
2
In
f
o
rm
a
ti
o
n
S
y
ste
m
s De
p
a
rt
m
e
n
t,
In
ter
n
a
ti
o
n
a
l
Isla
m
ic Un
iv
e
rsit
y
M
a
lay
sia
5
3
1
0
0
Ja
lan
G
o
m
b
a
k
,
Ku
a
la
L
u
m
p
u
r,
M
a
lay
sia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
n
4
,
2
0
1
8
R
ev
i
s
ed
A
u
g
2
,
2
0
1
8
A
cc
ep
ted
A
u
g
1
5
,
2
0
1
8
Ha
n
d
w
rit
ten
sig
n
a
t
u
re
s
a
re
p
la
y
in
g
a
n
im
p
o
rtan
t
ro
le
in
f
in
a
n
c
e
,
b
a
n
k
in
g
a
n
d
e
d
u
c
a
ti
o
n
a
n
d
m
o
re
b
e
c
a
u
se
it
is
c
o
n
sid
e
re
d
th
e
“
se
a
l
o
f
a
p
p
r
o
v
a
l”
a
n
d
re
m
a
in
s
th
e
m
o
st
p
re
f
e
rre
d
m
e
a
n
s
o
f
a
u
th
e
n
ti
c
a
ti
o
n
.
In
th
is
p
a
p
e
r,
a
n
o
ff
li
n
e
h
a
n
d
w
rit
ten
sig
n
a
tu
re
a
u
th
e
n
ti
c
a
ti
o
n
a
lg
o
rit
h
m
i
s
p
r
o
p
o
se
d
u
si
n
g
th
e
e
d
g
e
f
e
a
tu
re
s
a
n
d
d
e
e
p
fe
e
d
f
o
rwa
rd
n
e
u
ra
l
n
e
tw
o
rk
(DFNN).
T
h
e
n
u
m
b
e
r
o
f
h
id
d
e
n
lay
e
rs
in
DFNN
is
c
o
n
f
ig
u
re
d
to
b
e
a
t
lea
st
o
n
e
lay
e
r
a
n
d
m
o
re
.
In
th
is
p
a
p
e
r,
a
n
e
x
p
o
n
e
n
ti
a
l
d
e
c
a
y
i
n
g
n
u
m
b
e
r
o
f
n
o
d
e
s in
th
e
h
id
d
e
n
la
y
e
rs
wa
s
p
ro
p
o
se
d
to
a
c
h
iev
e
b
e
tt
e
r
re
c
o
g
n
it
io
n
ra
te
w
it
h
re
a
so
n
a
b
le
trai
n
i
n
g
ti
m
e
.
O
f
th
e
six
e
d
g
e
a
lg
o
rit
h
m
s
e
v
a
lu
a
ted
,
Ro
b
e
rts
o
p
e
ra
to
r
a
n
d
Ca
n
n
y
e
d
g
e
d
e
tec
to
rs
we
re
f
o
u
n
d
to
p
ro
d
u
c
e
b
e
tt
e
r
re
c
o
g
n
it
io
n
ra
te.
Re
su
lt
s
sh
o
w
e
d
th
a
t
th
e
p
ro
p
o
se
d
e
x
p
o
n
e
n
t
ial
d
e
c
a
y
i
n
g
n
u
m
b
e
r
o
f
n
o
d
e
s
in
th
e
h
id
d
e
n
lay
e
rs
o
u
t
p
e
rf
o
rm
o
th
e
r
stru
c
tu
re
.
Ho
w
e
v
e
r,
m
o
re
train
in
g
d
a
ta
w
a
s
re
q
u
i
re
d
so
t
h
a
t
th
e
p
r
o
p
o
se
d
DFNN stru
c
t
u
re
c
o
u
ld
h
a
v
e
m
o
re
e
ff
icie
n
t
lea
rn
in
g
.
K
ey
w
o
r
d
s
:
Dee
p
f
ee
d
f
o
r
w
ar
d
n
e
u
r
al
n
et
w
o
r
k
E
d
g
e
d
etec
tio
n
E
x
p
o
n
en
t
ial
d
ec
a
y
i
n
g
Hid
d
en
la
y
e
rs
Of
f
li
n
e
h
a
n
d
w
r
itte
n
s
i
g
n
at
u
r
e
Co
p
y
rig
h
t
©
2
0
1
8
In
stit
u
te o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts
re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
T
ed
d
y
S
u
r
y
a
G
u
n
a
w
an
E
lectr
ical
an
d
C
o
m
p
u
ter
E
n
g
i
n
ee
r
in
g
Dep
ar
t
m
e
n
t,
I
n
ter
n
atio
n
al
I
s
la
m
ic
U
n
iv
er
s
it
y
Ma
la
y
s
i
a
,
Ma
la
y
s
ia.
E
m
ail:
t
s
g
u
n
a
w
an
@
i
iu
m
.
ed
u
.
m
y
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
h
an
d
w
r
itte
n
s
i
g
n
at
u
r
e
i
s
v
er
y
i
m
p
o
r
tan
t
f
o
r
e
v
er
y
in
d
i
v
id
u
al
as
it
i
s
w
id
el
y
u
s
ed
f
o
r
au
th
e
n
tica
tio
n
p
u
r
p
o
s
es
i
n
e
v
er
y
d
a
y
lif
e.
E
ac
h
o
f
t
h
e
s
i
g
n
er
s
h
as
th
e
ir
o
w
n
s
i
g
n
a
tu
r
e,
w
h
ic
h
i
s
alt
h
o
u
g
h
un
iq
u
e
b
u
t
it
co
u
ld
v
ar
y
f
r
o
m
ti
m
e
to
ti
m
e,
o
r
d
u
e
to
d
if
f
er
e
n
t
to
o
ls
u
s
ed
,
s
u
c
h
as
p
en
w
i
t
h
d
if
f
er
en
t
p
e
n
s
ize,
s
t
y
l
u
s
,
o
r
f
in
g
er
.
T
h
e
h
an
d
w
r
itte
n
s
i
g
n
atu
r
e
au
t
h
e
n
ticati
o
n
s
y
s
te
m
ai
m
s
to
m
i
n
i
m
iz
e
th
e
in
tr
ap
er
s
o
n
a
l
d
if
f
er
e
n
ce
s
[1
]
-
[
2]
.
Sig
n
at
u
r
e
v
er
if
icatio
n
ca
n
b
e
clas
s
i
f
ie
d
in
to
t
w
o
p
ar
ts
w
h
ich
i
s
o
n
li
n
e
an
d
o
f
f
l
in
e.
T
h
is
p
ap
er
f
o
cu
s
es
o
n
th
e
o
f
f
li
n
e
s
y
s
te
m
w
h
ic
h
co
u
ld
b
e
co
n
s
id
er
ed
as
m
o
r
e
ch
a
llen
g
i
n
g
co
m
p
ar
e
to
th
e
o
n
lin
e
s
y
s
te
m
.
T
h
is
is
d
u
e
to
th
e
o
f
f
l
in
e
s
y
s
te
m
d
id
n
o
t
ca
p
tu
r
e
t
h
e
d
y
n
a
m
ic
w
h
ic
h
ca
n
h
elp
th
e
cla
s
s
i
f
ier
to
au
th
e
n
tica
te
b
etter
th
e
s
i
g
n
ato
r
y
[
3
]
.
Ma
n
y
r
esear
c
h
es
h
a
v
e
b
ee
n
co
n
d
u
cted
to
d
ev
elo
p
h
an
d
w
r
itten
s
i
g
n
a
tu
r
e
au
th
e
n
ticatio
n
s
y
s
te
m
.
T
y
p
ical
h
a
n
d
w
r
itte
n
s
i
g
n
a
tu
r
e
au
t
h
e
n
ticat
io
n
s
y
s
te
m
i
s
s
h
o
w
n
i
n
Fi
g
u
r
e
1
.
I
n
[
4
]
,
a
n
o
r
ien
tatio
n
o
f
t
h
e
s
k
eleto
n
an
d
g
r
av
it
y
ce
n
ter
p
o
in
t
w
er
e
co
m
b
i
n
ed
to
ex
tr
ac
t
m
o
r
e
ac
c
u
r
ate
f
ea
tu
r
e
s
.
A
n
o
t
h
er
f
ea
tu
r
e,
i.e
.
E
u
ler
n
u
m
b
er
,
w
as
ca
lc
u
lated
a
s
t
h
e
s
u
b
tr
ac
tio
n
o
f
to
tal
n
u
m
b
er
o
f
o
b
j
ec
ts
i
n
t
h
e
h
a
n
d
w
r
itte
n
i
m
a
g
e
w
i
th
to
tal
n
u
m
b
er
o
f
h
o
les
[
5
]
.
Oth
er
f
e
atu
r
es
h
a
s
b
ee
n
as
w
ell
i
n
th
e
liter
atu
r
e,
s
u
c
h
as
r
o
u
n
d
n
es
s
,
s
k
e
w
n
es
s
,
k
u
r
to
s
is
,
m
ea
n
,
s
tan
d
ar
d
d
ev
iatio
n
,
ar
ea
,
d
is
tr
ib
u
tio
n
d
en
s
it
y
,
e
n
tr
o
p
y
,
co
n
n
ec
ted
co
m
p
o
n
e
n
t a
n
d
p
er
i
m
eter
[2
]
,
[
5]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
On
th
e
Use o
f E
d
g
e
F
ea
tu
r
es a
n
d
E
x
p
o
n
e
n
tia
l D
ec
a
yin
g
N
u
mb
er o
f No
d
es in
th
e…
(
Ted
d
y
S
u
r
ya
Gu
n
a
w
a
n
)
723
Fig
u
r
e
1
.
T
y
p
ical
h
an
d
w
r
it
ten
s
ig
n
at
u
r
e
au
t
h
en
ticatio
n
s
y
s
te
m
On
th
e
clas
s
i
f
ier
p
ar
t,
tw
o
m
eth
o
d
s
h
av
e
b
ee
n
m
o
s
tl
y
u
tili
ze
d
,
i.e
.
SVM
[
6
]
,
n
eu
r
al
n
et
w
o
r
k
[2
]
,
[
7
]
-
[
8]
,
as
w
ell
as
d
ee
p
n
e
u
r
al
n
et
w
o
r
k
[
1
]
.
A
lt
h
o
u
g
h
m
a
n
y
r
e
s
ea
r
ch
es
h
a
v
e
b
ee
n
co
n
d
u
cted
o
n
o
f
f
li
n
e
h
an
d
w
r
itte
n
s
i
g
n
at
u
r
e
au
t
h
en
ti
ca
tio
n
,
b
u
t
th
er
e
ar
e
s
till
m
a
n
y
asp
ec
ts
h
av
e
n
o
t
b
ee
n
co
n
s
id
er
ed
.
I
n
th
is
p
ap
er
,
w
e
h
a
v
e
co
llected
o
u
r
o
w
n
h
a
n
d
w
r
i
tten
s
ig
n
at
u
r
e
i
m
a
g
e
d
atab
ase
w
it
h
v
ar
iatio
n
i
n
th
e
p
o
s
itio
n
an
d
p
en
s
ize
an
d
co
lo
r
u
s
ed
to
s
i
g
n
.
F
u
r
th
er
m
o
r
e,
o
u
r
p
r
ev
io
u
s
r
e
s
ea
r
ch
s
h
o
w
ed
t
h
at
t
h
e
u
s
e
o
f
h
ig
h
p
ass
f
ilter
p
r
o
d
u
ce
b
etter
ac
cu
r
ac
y
co
m
p
ar
ed
to
lo
w
p
ass
f
ilter
[
9
]
.
T
h
e
h
ig
h
p
ass
f
i
lter
u
s
ed
in
[
9
]
is
o
n
l
y
C
an
n
y
ed
g
e
d
etec
to
r
.
T
h
er
ef
o
r
e,
in
t
h
i
s
p
ap
er
,
ar
o
u
n
d
s
i
x
ed
g
e
d
etec
t
io
n
al
g
o
r
it
h
m
s
w
er
e
u
s
ed
,
i
n
cl
u
d
in
g
So
b
el,
P
r
e
w
itt,
R
o
b
er
ts
,
L
ap
lacia
n
o
f
Gau
s
s
ia
n
,
Z
er
o
C
r
o
s
s
,
an
d
C
an
n
y
.
Dee
p
n
eu
r
al
n
e
t
w
o
r
k
s
u
s
e
s
at
lea
s
t
t
w
o
h
id
d
en
la
y
er
s
o
r
m
o
r
e
in
t
h
eir
co
n
f
ig
u
r
atio
n
[
1
0
]
.
T
h
e
o
p
tim
al
s
tr
u
ctu
r
e
o
f
t
h
e
n
eu
r
al
n
et
w
o
r
k
s
i
s
s
til
l
an
ac
t
iv
e
r
esear
ch
ar
ea
.
I
n
[
1
1
]
,
p
r
u
n
i
n
g
m
e
th
o
d
w
er
e
u
s
ed
to
o
b
tain
o
p
ti
m
u
m
D
NN
s
tr
u
ct
u
r
e
.
Ho
w
ev
er
,
t
h
e
s
tep
s
in
v
o
lv
ed
i
s
r
ath
er
c
o
m
p
le
x
.
T
h
er
ef
o
r
e,
th
e
o
b
j
ec
tiv
e
o
f
th
is
p
ap
er
is
t
o
d
ev
elo
p
an
o
f
f
li
n
e
h
a
n
d
w
r
i
tt
en
s
i
g
n
a
tu
r
e
u
s
i
n
g
ed
g
e
f
ea
t
u
r
es
an
d
ex
p
o
n
e
n
tial
d
ec
ay
i
n
g
n
u
m
b
er
o
f
n
o
d
es
in
t
h
e
h
id
d
en
la
y
er
s
o
f
DN
N
s
tr
u
ctu
r
e.
T
h
e
p
r
o
p
o
s
ed
alg
o
r
it
h
m
s
w
ill
b
e
e
v
alu
ated
in
ter
m
s
o
f
tr
ai
n
in
g
ti
m
e
a
n
d
r
ec
o
g
n
itio
n
r
ate.
2.
P
RO
P
O
SE
D
H
ANDW
RI
T
T
E
SI
G
NA
T
UR
E
S U
SI
N
G
D
E
E
P
F
E
E
DF
O
RW
ARD
N
E
URAL
NE
T
WO
RK
S
Fig
u
r
e
2
s
h
o
w
s
o
u
r
p
r
o
p
o
s
ed
alg
o
r
ith
m
,
i
n
w
h
ich
t
h
e
s
y
s
te
m
h
as
t
w
o
m
a
in
p
ar
ts
,
i
.
e.
f
ea
tu
r
e
ex
tr
ac
tio
n
a
n
d
class
i
f
ier
.
T
h
e
f
ea
tu
r
e
ex
tr
ac
tio
n
p
ar
t
is
in
clu
d
i
n
g
th
e
i
m
ag
e
s
eg
m
e
n
t
atio
n
,
alig
n
i
n
g
a
n
d
cr
o
p
p
in
g
,
co
lo
r
to
g
r
ay
s
ca
le
c
o
n
v
er
s
io
n
,
an
d
i
m
a
g
e
f
ilter
i
n
g
.
T
h
e
class
if
ier
p
ar
t
is
in
cl
u
d
in
g
t
h
e
tr
ain
i
n
g
a
n
d
test
i
n
g
o
f
n
e
u
r
al
n
et
w
o
r
k
w
i
th
th
e
d
ev
elo
p
ed
i
m
ag
e
d
atab
ase
.
Fig
u
r
e
2
.
P
r
o
p
o
s
ed
h
an
d
w
r
itte
n
s
i
g
n
a
tu
r
e
au
th
e
n
ticat
io
n
s
y
s
t
e
m
u
s
i
n
g
d
ee
p
n
e
u
r
al
n
et
w
o
r
k
s
2
.
1
.
H
a
nd
w
rit
t
e
Sig
na
t
ure
I
m
a
g
e
Da
t
a
ba
s
e
And E
dg
e
F
ea
t
ures
T
h
e
h
an
d
w
r
itte
n
s
i
g
n
a
tu
r
es
ar
e
co
llected
f
r
o
m
f
i
v
e
p
er
s
o
n
s
u
s
i
n
g
f
i
v
e
d
i
f
f
er
e
n
t
p
e
n
s
ize
a
n
d
s
t
y
le
s
,
each
f
o
r
1
0
ten
ti
m
es
p
r
o
d
u
cin
g
a
to
tal
o
f
5
0
s
ig
n
a
tu
r
e
s
h
av
e
b
ee
n
ta
k
en
f
o
r
ea
ch
p
er
s
o
n
.
T
h
e
to
tal
h
an
d
w
r
itte
n
s
ig
n
at
u
r
es
co
llect
ed
ar
e
2
5
0
im
a
g
es
[
9
]
.
T
h
e
h
an
d
w
r
i
tten
s
i
g
n
at
u
r
es
ar
e
t
h
e
n
s
ca
n
n
ed
u
s
i
n
g
a
s
ca
n
n
er
to
co
n
v
er
t
it
to
th
e
d
ig
ital
i
m
ag
e
s
.
T
h
e
co
lo
r
im
a
g
e
is
co
n
v
er
ted
to
g
r
ay
s
ca
le
im
ag
e
to
r
ed
u
ce
th
e
co
m
p
u
tatio
n
.
T
h
e
i
m
ag
e
s
ize
is
f
i
x
ed
to
b
e
2
0
6
b
y
1
2
8
p
ix
els,
w
h
ich
is
t
h
en
ch
a
n
g
ed
in
t
o
co
lu
m
n
v
ec
to
r
o
f
2
6
3
6
8
.
Fin
all
y
,
th
e
h
a
n
d
w
r
itte
n
s
ig
n
at
u
r
es
d
atab
ase
w
il
l
b
e
d
iv
id
ed
r
an
d
o
m
l
y
f
o
r
ea
c
h
p
e
r
s
o
n
to
b
e
5
0
%
f
o
r
tr
ain
i
n
g
,
1
0
%
f
o
r
cr
o
s
s
v
al
i
d
atio
n
,
an
d
4
0
%
f
o
r
test
in
g
.
Fig
u
r
e
3
s
h
o
w
s
t
h
e
ex
a
m
p
le
o
f
th
e
co
llected
s
ig
n
at
u
r
e
i
m
a
g
es.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
le
c
E
n
g
&
C
o
m
p
Sci,
Vo
l.
12
,
No
.
2
,
No
v
e
m
b
er
2
0
1
8
:
7
2
2
–
7
2
8
724
I
m
ag
e0
1
.
j
p
g
I
m
ag
e0
2
.
j
p
g
I
m
ag
e0
3
.
j
p
g
I
m
ag
e
0
4
.
j
p
g
I
m
ag
e0
5
.
j
p
g
Fig
u
r
e
3
.
E
x
a
m
p
le
o
f
P
er
s
o
n
A
s
ig
n
at
u
r
es
w
it
h
f
i
v
e
d
i
f
f
er
e
n
t
p
en
s
ize
an
d
co
lo
r
Ou
r
p
r
ev
io
u
s
r
esear
ch
s
h
o
w
e
d
th
at
h
i
g
h
p
ass
f
ilter
p
r
o
d
u
ce
b
etter
ac
cu
r
ac
y
co
m
p
ar
ed
to
lo
w
p
ass
f
ilter
[
9
]
.
A
l
th
o
u
g
h
ca
n
n
y
ed
g
e
d
etec
tio
n
i
s
t
h
e
m
o
s
t
p
o
p
u
lar
m
e
th
o
d
f
o
r
ed
g
e
d
etec
tio
n
[
1
2
]
,
b
u
t
w
e
w
ill
ev
alu
a
te
its
e
f
f
ec
t
iv
e
n
es
s
in
D
NN
co
n
f
i
g
u
r
atio
n
ag
a
in
s
t
f
i
v
e
o
th
er
alg
o
r
ith
m
s
.
Fi
g
u
r
e
4
s
h
o
w
s
t
h
e
ex
a
m
p
le
o
f
ed
g
e
d
etec
tio
n
alg
o
r
it
h
m
s
f
o
r
I
m
a
g
e0
2
an
d
I
m
a
g
e0
5
o
f
P
er
s
o
n
A
.
T
h
e
d
if
f
er
e
n
t
p
en
s
ize
an
d
s
t
y
les
w
i
ll
p
r
o
d
u
ce
d
if
f
er
en
t
ed
g
e
f
ea
t
u
r
es,
in
w
h
ich
th
e
s
i
m
ilar
it
y
i
s
r
ath
er
lo
w
.
I
n
th
at
ca
s
e,
t
h
e
tr
ain
i
n
g
o
f
n
e
u
r
al
n
et
w
o
r
k
w
il
l
b
e
r
ath
er
d
if
f
ic
u
lt
to
ac
h
ie
v
e
h
ig
h
r
ec
o
g
n
itio
n
r
ate.
Mo
r
eo
v
er
,
T
ab
le
1
s
h
o
w
s
t
h
e
p
r
o
ce
s
s
i
n
g
ti
m
e
o
f
v
ar
io
u
s
ed
g
e
d
etec
tio
n
al
g
o
r
ith
m
s
to
o
b
tain
ed
g
e
f
ea
tu
r
es
f
o
r
all
2
5
0
i
m
ag
e
s
.
I
t
ca
n
b
e
f
o
u
n
d
t
h
at
P
r
ew
i
tt o
p
er
ato
r
is
th
e
f
aste
s
t,
w
h
ile
C
an
n
y
ed
g
e
d
etec
tio
n
is
th
e
s
l
o
w
es
t.
(
a)
(
b
)
(
c)
(
d
)
(
e)
(
f
)
Fig
u
r
e
4
.
E
x
a
m
p
le
o
f
p
er
s
o
n
a
s
ig
n
at
u
r
es,
i.e
.
i
m
a
g
e0
2
.
j
p
g
(
f
ir
s
t r
o
w
)
an
d
i
m
ag
e0
5
.
j
p
g
(
s
ec
o
n
d
r
o
w
)
,
w
it
h
d
if
f
er
e
n
t e
d
g
e
d
etec
tio
n
al
g
o
r
i
th
m
s
,
(
a)
s
o
b
el,
(
b
)
p
r
ew
i
tt,
(
c)
r
o
b
er
ts
,
(
d
)
lap
lacia
n
o
f
g
au
s
s
ia
n
,
(
e)
ze
r
o
c
r
o
s
s
,
(
f
)
ca
n
n
y
.
T
ab
le
1
.
P
r
o
ce
s
s
in
g
T
i
m
e
o
f
V
ar
io
u
s
E
d
g
e
Dete
ctio
n
A
lg
o
r
it
h
m
s
Ed
g
e
F
e
a
t
u
r
e
s
P
r
o
c
e
ssi
n
g
T
i
me
(
se
c
o
n
d
s)
S
o
b
e
l
0
.
7
3
5
2
P
r
e
w
i
t
t
0
.
6
0
4
8
R
o
b
e
r
t
s
0
.
7
8
0
8
L
a
p
l
a
c
i
a
n
o
f
G
a
u
ssi
a
n
0
.
8
9
9
1
Z
e
r
o
C
r
o
ss
1
.
0
4
6
8
C
a
n
n
y
1
.
1
8
0
8
2
.
2
.
E
x
po
nentia
l D
ec
a
y
ing
Nu
m
b
er
o
f
No
des
in t
he
H
idd
en
L
a
y
er
s
T
h
e
m
a
in
p
r
i
n
cip
le
o
f
DN
N
is
to
u
tili
ze
lo
w
er
le
v
el
f
ea
t
u
r
es
lear
n
in
g
to
u
p
d
ate
th
e
lear
n
in
g
o
f
h
i
g
h
er
f
ea
t
u
r
es.
T
h
er
e
ar
e
m
an
y
a
v
ail
ab
le
d
ee
p
ar
ch
itectu
r
e,
s
u
ch
a
s
n
eu
r
al
n
et
w
o
r
k
s
w
it
h
m
a
n
y
h
i
d
d
en
la
y
er
s
a
n
d
/o
r
m
an
y
h
id
d
e
n
v
ar
iab
les,
co
n
v
o
lu
tio
n
al
n
e
u
r
al
n
et
w
o
r
k
s
,
r
ec
u
r
r
en
t
n
eu
r
al
n
et
w
o
r
k
s
,
an
d
d
ee
p
b
elief
n
et
w
o
r
k
[
1
0
]
,
[
1
3
]
.
I
n
th
is
r
esear
c
h
,
w
e
u
s
ed
d
ee
p
lear
n
in
g
u
s
i
n
g
f
ee
d
f
o
r
w
ar
d
n
eu
r
al
n
et
w
o
r
k
ar
ch
itectu
r
e
s
w
it
h
h
id
d
en
la
y
er
s
w
it
h
m
an
y
h
id
d
en
v
ar
iab
les
[
1
4
]
.
Fig
u
r
e
5
illu
s
tr
ates
t
h
e
d
ee
p
f
ee
d
f
o
r
w
ar
d
n
e
u
r
al
n
et
w
o
r
k
s
tr
u
ct
u
r
e.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
On
th
e
Use o
f E
d
g
e
F
ea
tu
r
es a
n
d
E
x
p
o
n
e
n
tia
l D
ec
a
yin
g
N
u
mb
er o
f No
d
es in
th
e…
(
Ted
d
y
S
u
r
ya
Gu
n
a
w
a
n
)
725
Fig
u
r
e
5
.
Dee
p
f
ee
d
f
o
r
w
ar
d
n
eu
r
al
n
et
w
o
r
k
s
tr
u
ct
u
r
e
I
n
th
i
s
p
ap
er
,
w
e
p
r
o
p
o
s
e
an
ex
p
o
n
en
t
ial
d
ec
a
y
i
n
g
n
u
m
b
e
r
o
f
h
id
d
en
n
o
d
es
d
u
e
to
its
s
i
m
p
lic
it
y
co
m
p
ar
ed
to
p
r
u
n
i
n
g
m
et
h
o
d
as d
escr
ib
ed
in
[
1
1
]
.
I
t c
an
b
e
f
o
r
m
u
lated
as
f
o
llo
w
s
:
(
1
)
W
h
er
e
is
n
e
u
r
al
n
et
w
o
r
k
la
y
er
s
,
w
h
ile
is
th
e
n
u
m
b
er
o
f
n
o
d
es.
I
n
p
u
t
la
y
er
is
d
e
f
i
n
ed
as
,
w
h
ile
th
e
las
t
la
y
er
w
i
ll
b
e
th
e
o
u
tp
u
t
la
y
er
.
Fo
r
ex
a
m
p
le,
if
w
e
h
a
v
e
3
h
id
d
en
la
y
er
s
(
)
,
is
th
e
in
p
u
t
la
y
er
,
is
th
e
f
ir
s
t
h
id
d
en
la
y
er
,
is
th
e
s
ec
o
n
d
h
i
d
d
en
lay
er
,
is
th
e
th
ir
d
h
id
d
e
n
la
y
er
,
an
d
is
th
e
o
u
tp
u
t
la
y
er
.
Usi
n
g
cu
r
v
e
f
itti
n
g
,
w
e
co
u
ld
f
in
d
th
e
p
ar
a
m
eter
an
d
.
I
n
o
u
r
ca
s
e,
at
p
ar
am
e
ter
(
in
p
u
t
la
y
er
)
an
d
at
(
o
u
tp
u
t
la
y
er
)
.
T
h
en
,
p
ar
a
m
eter
co
u
ld
b
e
ca
lcu
lated
as
f
o
llo
w
s
:
(
)
(
2
)
W
h
er
e
is
th
e
n
u
m
b
er
o
f
h
id
d
e
n
la
y
er
s
,
is
th
e
in
p
u
t
n
o
d
es,
an
d
is
th
e
o
u
tp
u
t
n
o
d
es.
T
ab
le
2
s
h
o
w
s
t
h
e
ex
a
m
p
le
o
f
ex
p
o
n
e
n
tial
d
ec
a
y
in
g
n
u
m
b
er
o
f
n
o
d
es
in
v
ar
io
u
s
h
id
d
en
la
y
er
s
,
w
h
e
n
th
e
an
d
,
u
s
in
g
E
q
.
(
1
)
an
d
(
2
)
.
Fig
u
r
e
6
illu
s
t
r
ates
th
e
ex
p
o
n
en
t
ial
d
ec
a
y
i
n
g
n
u
m
b
er
o
f
n
o
d
es f
o
r
4
h
id
d
en
la
y
er
s.
T
ab
le
2
.
E
x
p
o
n
en
tial D
ec
a
y
i
n
g
Nu
m
b
er
o
f
No
d
es in
Var
io
u
s
Hid
d
en
L
a
y
er
s
S
tr
u
ct
u
r
es
H
i
d
d
e
n
L
a
y
e
r
N
o
d
e
s C
o
n
f
i
g
u
r
a
t
i
o
n
1
[
3
6
3
]
2
[
1
5
1
5
8
7
]
3
[
3
0
9
4
3
6
3
4
3
]
4
[
4
7
5
0
8
5
6
1
5
4
2
8
]
5
[
6
3
2
0
1
5
1
5
3
6
3
8
7
2
1
]
6
[
7
7
5
1
2
2
7
8
6
7
0
1
9
7
5
8
1
7
]
F
ig
u
r
e
6
.
E
x
a
m
p
le
o
f
e
x
p
o
n
en
tial d
ec
a
y
in
g
n
u
m
b
er
o
f
n
o
d
es
f
o
r
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
le
c
E
n
g
&
C
o
m
p
Sci,
Vo
l.
12
,
No
.
2
,
No
v
e
m
b
er
2
0
1
8
:
7
2
2
–
7
2
8
726
3.
RE
SU
L
T
S AN
D
AN
AL
Y
SI
S
I
n
th
is
s
ec
tio
n
,
t
h
e
ex
p
er
i
m
e
n
tal
s
etu
p
,
h
a
n
d
w
r
i
tten
s
ig
n
at
u
r
e
im
a
g
e
d
atab
ase
an
d
its
ed
g
e
f
ea
tu
r
es,
tr
ain
i
n
g
a
n
d
tes
tin
g
o
f
d
ee
p
f
ee
d
f
o
r
w
ar
d
n
e
u
r
al
n
et
w
o
r
k
with
e
x
p
o
n
en
tial
d
ec
a
y
in
g
n
u
m
b
er
o
f
n
o
d
es
i
n
th
e
h
id
d
en
la
y
er
s
w
ill b
e
d
is
cu
s
s
e
d
.
3
.
1
.
E
x
peri
m
e
nta
l Set
up
A
h
ig
h
p
er
f
o
r
m
an
ce
s
y
s
te
m
was
u
s
ed
f
o
r
p
r
o
ce
s
s
in
g
,
i.e
.
a
m
u
ltico
r
e
s
y
s
te
m
w
it
h
I
n
tel
C
o
r
e
i7
6
7
0
0
K
4
.
0
0
GHz
(
4
co
r
es
w
it
h
8
th
r
ea
d
s
)
,
3
2
GB
y
tes
R
AM
,
2
5
6
GB
y
tes
SS
D
a
n
d
2
T
B
y
tes
h
ar
d
d
is
k
,
in
s
talled
w
it
h
W
in
d
o
w
s
1
0
o
p
er
atin
g
s
y
s
te
m
an
d
Ma
tlab
2
0
1
8
a
w
it
h
I
m
a
g
e
P
r
o
ce
s
s
in
g
,
Sig
n
al
P
r
o
ce
s
s
i
n
g
a
n
d
Neu
r
al
Net
w
o
r
k
T
o
o
lb
o
x
es.
T
h
e
h
an
d
w
r
itte
n
s
i
g
n
at
u
r
e
d
atab
ase
w
er
e
co
llected
f
r
o
m
f
i
v
e
p
er
s
o
n
,
h
en
ce
t
h
e
o
u
tp
u
t
la
y
er
is
s
et
to
f
iv
e.
T
h
e
n
u
m
b
er
o
f
n
o
d
es
in
t
h
e
h
id
d
en
la
y
e
r
as
w
ell
a
s
h
id
d
en
la
y
er
w
ill
b
e
v
ar
ied
,
w
h
i
le
th
e
p
atter
n
et(
)
Ma
tlab
f
u
n
ctio
n
will
b
e
u
s
ed
.
Oth
er
t
y
p
es
o
f
f
e
ed
f
o
r
w
ar
d
n
e
u
r
al
n
et
w
o
r
k
ca
n
b
e
u
s
ed
as
w
e
ll,
as d
escr
ib
ed
in
[
1
4
]
.
3
.
2
.
T
ra
ini
ng
P
ha
s
e
o
f
Va
rio
us
D
F
NN
Str
uct
ures
I
n
T
ab
le
3
,
th
e
b
est
r
ec
o
g
n
it
io
n
r
ates
w
er
e
h
i
g
h
li
g
h
ted
i
n
b
o
ld
.
A
cr
o
s
s
th
e
r
o
w
,
t
h
e
m
ax
i
m
u
m
r
ec
o
g
n
itio
n
r
ate
is
ac
h
ie
v
ed
w
h
e
n
th
e
s
tr
u
c
tu
r
e
o
f
h
id
d
en
la
y
er
s
ar
e
[
1
0
0
0
1
0
0
1
0
]
an
d
[
3
0
9
4
3
6
3
4
3
]
w
it
h
r
ec
o
g
n
itio
n
r
ate
o
f
9
6
.
8
9
%
a
n
d
9
6
.
6
7
%,
r
esp
ec
tiv
el
y
.
W
h
i
le
ac
r
o
s
s
t
h
e
co
lu
m
n
,
t
h
e
m
a
x
i
m
u
m
r
ec
o
g
n
it
io
n
r
ate
is
ac
h
ie
v
ed
f
o
r
R
o
b
er
t
an
d
C
a
n
n
y
ed
g
e
d
etec
tio
n
al
g
o
r
ith
m
s
w
it
h
r
ec
o
g
n
itio
n
r
a
te
o
f
8
9
.
7
2
%
an
d
8
8
.
3
3
%,
r
esp
ec
tiv
el
y
.
T
h
er
ef
o
r
e,
th
ese
t
w
o
ed
g
e
f
ea
t
u
r
es
an
d
t
w
o
D
FNN
s
tr
u
ct
u
r
es
w
i
ll
b
e
f
u
r
t
h
er
tr
ain
ed
an
d
test
ed
w
it
h
t
h
e
n
e
w
i
m
a
g
es.
Mo
r
eo
v
er
,
t
h
e
la
s
t
s
ix
r
o
w
s
o
f
T
ab
le
3
s
h
o
w
s
t
h
e
p
er
f
o
r
m
an
ce
o
f
th
e
ex
p
o
n
en
t
ial
d
ec
a
y
in
g
n
u
m
b
e
r
o
f
n
o
d
es
f
o
r
h
id
d
en
la
y
er
o
f
o
n
e
to
s
i
x
.
C
o
m
p
ar
ed
t
o
th
e
o
t
h
er
D
FNN
s
tr
u
ct
u
r
es,
it c
o
n
s
is
te
n
tl
y
s
h
o
w
s
h
i
g
h
av
er
a
g
e
r
ec
o
g
n
it
io
n
r
ate
ac
r
o
s
s
v
ar
io
u
s
ed
g
e
f
ea
t
u
r
e
s
.
T
ab
le
3
.
R
ec
o
g
n
itio
n
R
ate
(
%)
o
f
Var
io
u
s
DF
NN
Stru
c
tu
r
es
N
H
i
d
d
e
n
S
o
b
e
l
P
r
e
w
i
t
t
R
o
b
e
r
t
s
L
o
G
z
e
r
o
c
r
o
ss
C
a
n
n
y
A
v
e
r
a
g
e
[
1
0
]
9
6
.
0
0
9
6
.
6
7
9
6
.
6
7
8
6
.
6
7
9
6
.
0
0
9
5
.
3
3
9
4
.
5
6
[
2
0
]
7
4
.
0
0
9
3
.
3
3
9
7
.
3
3
9
1
.
3
3
9
2
.
6
7
9
8
.
6
7
9
1
.
2
2
[
3
0
]
9
6
.
0
0
9
8
.
0
0
9
7
.
3
3
9
4
.
0
0
9
6
.
6
7
9
4
.
0
0
9
6
.
0
0
[
4
0
]
9
6
.
6
7
9
7
.
3
3
9
4
.
0
0
9
6
.
0
0
9
4
.
6
7
9
6
.
0
0
9
5
.
7
8
[
5
0
]
9
6
.
6
7
9
4
.
6
7
9
6
.
0
0
9
6
.
0
0
9
6
.
0
0
9
5
.
3
3
9
5
.
7
8
[
1
0
0
]
9
6
.
0
0
9
6
.
6
7
9
4
.
6
7
9
1
.
3
3
9
3
.
3
3
9
5
.
3
3
9
4
.
5
6
[
2
0
0
]
9
7
.
3
3
8
6
.
0
0
8
4
.
0
0
9
5
.
3
3
7
5
.
3
3
9
6
.
6
7
8
9
.
1
1
[
3
0
0
]
9
4
.
0
0
8
6
.
6
7
9
5
.
3
3
8
6
.
6
7
9
5
.
3
3
9
6
.
0
0
9
2
.
3
3
[
4
0
0
]
9
6
.
0
0
9
5
.
3
3
9
3
.
3
3
9
5
.
3
3
9
4
.
6
7
7
6
.
6
7
9
1
.
8
9
[
5
0
0
]
9
4
.
6
7
8
4
.
6
7
9
5
.
3
3
9
4
.
0
0
9
5
.
3
3
9
4
.
0
0
9
3
.
0
0
[
1
0
0
0
]
9
3
.
3
3
9
4
.
0
0
9
4
.
0
0
8
2
.
0
0
9
2
.
6
7
2
0
.
0
0
7
9
.
3
3
[
2
0
0
0
]
9
5
.
3
3
9
2
.
6
7
6
9
.
3
3
9
3
.
3
3
9
3
.
3
3
9
5
.
3
3
8
9
.
8
9
[
3
0
0
0
]
9
4
.
6
7
6
0
.
0
0
9
0
.
6
7
8
8
.
0
0
8
8
.
6
7
9
3
.
3
3
8
5
.
8
9
[
4
0
0
0
]
9
0
.
0
0
2
3
.
3
3
9
1
.
3
3
7
4
.
6
7
9
2
.
6
7
8
1
.
3
3
7
5
.
5
6
[
5
0
0
0
]
5
7
.
3
3
9
3
.
3
3
7
7
.
3
3
8
9
.
3
3
9
2
.
6
7
7
0
.
6
7
8
0
.
1
1
[
1
0
0
0
0
]
5
8
.
6
7
2
0
.
0
0
5
6
.
6
7
7
2
.
6
7
6
9
.
3
3
4
2
.
0
0
5
3
.
2
2
[
1
0
1
0
]
7
3
.
3
3
7
2
.
0
0
7
8
.
6
7
7
1
.
3
3
2
0
.
0
0
8
4
.
6
7
6
6
.
6
7
[
2
0
2
0
]
9
2
.
6
7
2
3
.
3
3
9
1
.
3
3
9
4
.
0
0
9
2
.
0
0
9
8
.
0
0
8
1
.
8
9
[
3
0
3
0
]
8
1
.
3
3
9
5
.
3
3
9
5
.
3
3
2
2
.
6
7
9
4
.
6
7
9
6
.
6
7
8
1
.
0
0
[
4
0
4
0
]
9
6
.
6
7
9
4
.
0
0
6
4
.
6
7
9
5
.
3
3
9
4
.
6
7
9
6
.
0
0
9
0
.
2
2
[
5
0
5
0
]
9
7
.
3
3
9
5
.
3
3
9
5
.
3
3
5
6
.
6
7
5
0
.
6
7
9
4
.
6
7
8
1
.
6
7
[
1
0
0
1
0
0
]
3
0
.
6
7
9
6
.
6
7
9
2
.
6
7
9
2
.
0
0
4
3
.
3
3
9
5
.
3
3
7
5
.
1
1
[
1
0
0
1
0
]
9
1
.
3
3
9
5
.
3
3
9
0
.
6
7
9
6
.
0
0
9
2
.
0
0
7
8
.
6
7
9
0
.
6
7
[
1
0
1
0
1
0
]
6
6
.
6
7
2
0
.
0
0
7
8
.
0
0
8
4
.
0
0
6
7
.
3
3
5
0
.
6
7
6
1
.
1
1
[
2
0
2
0
2
0
]
8
0
.
6
7
9
2
.
0
0
7
4
.
6
7
9
5
.
3
3
9
4
.
0
0
8
0
.
6
7
8
6
.
2
2
[
3
0
3
0
3
0
]
9
6
.
0
0
9
6
.
6
7
7
7
.
3
3
8
7
.
3
3
3
4
.
6
7
9
6
.
0
0
8
1
.
3
3
[
4
0
4
0
4
0
]
9
5
.
3
3
9
4
.
6
7
9
4
.
0
0
9
6
.
0
0
6
9
.
3
3
9
6
.
0
0
9
0
.
8
9
[
5
0
5
0
5
0
]
9
6
.
0
0
9
5
.
3
3
9
6
.
6
7
9
4
.
0
0
9
4
.
6
7
9
7
.
3
3
9
5
.
6
7
[
1
0
0
1
0
0
1
0
0
]
9
4
.
6
7
9
6
.
0
0
9
8
.
0
0
9
5
.
3
3
5
4
.
0
0
9
5
.
3
3
8
8
.
8
9
[
1
0
0
0
1
0
0
1
0
]
9
6
.
6
7
9
6
.
0
0
9
8
.
6
7
9
6
.
6
7
9
6
.
0
0
9
7
.
3
3
9
6
.
8
9
[
3
6
3
]
9
4
.
6
7
9
4
.
6
7
9
4
.
0
0
9
4
.
6
7
9
4
.
0
0
9
6
.
0
0
9
4
.
6
7
[
1
5
1
5
8
7
]
8
4
.
6
7
9
0
.
6
7
9
5
.
3
3
9
4
.
6
7
9
6
.
6
7
9
8
.
0
0
9
3
.
3
4
[
3
0
9
4
3
6
3
4
3
]
9
6
.
6
7
9
8
.
0
0
9
8
.
0
0
9
5
.
3
3
9
5
.
3
3
9
6
.
6
7
9
6
.
6
7
[
4
7
5
0
8
5
6
1
5
4
2
8
]
9
4
.
0
0
9
6
.
0
0
98
.
0
0
9
5
.
3
3
9
5
.
3
3
9
6
.
6
7
9
5
.
8
9
[
6
3
2
0
1
5
1
5
3
6
3
8
7
2
1
]
9
5
.
3
3
9
5
.
3
3
9
8
.
0
0
9
6
.
0
0
9
7
.
3
3
9
6
.
6
7
9
6
.
4
4
[
7
7
5
1
2
2
7
8
6
7
0
1
9
7
5
8
1
7
]
7
0
.
0
0
9
6
.
6
7
9
7
.
3
3
9
6
.
6
7
9
6
.
0
0
98
9
2
.
4
5
A
v
e
r
a
g
e
8
7
.
5
4
8
4
.
6
3
8
9
.
7
2
8
8
.
2
2
8
4
.
2
0
8
8
.
3
3
8
7
.
1
1
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
On
th
e
Use o
f E
d
g
e
F
ea
tu
r
es a
n
d
E
x
p
o
n
e
n
tia
l D
ec
a
yin
g
N
u
mb
er o
f No
d
es in
th
e…
(
Ted
d
y
S
u
r
ya
Gu
n
a
w
a
n
)
727
I
n
t
h
e
tr
ai
n
i
n
g
p
h
a
s
e,
5
0
%
o
f
th
e
i
m
a
g
e
d
at
ab
ase
w
as
u
s
ed
f
o
r
tr
ain
in
g
,
a
n
d
1
0
%
w
as
u
s
ed
f
o
r
cr
o
s
s
v
alid
atio
n
.
T
h
e
ac
tiv
a
to
n
f
u
n
c
tio
n
u
s
ed
o
n
ea
c
h
n
o
d
es
in
t
h
e
h
id
d
en
la
y
er
s
i
s
s
i
g
m
o
id
f
u
n
c
tio
n
,
e
x
ce
p
t
f
o
r
t
h
e
o
u
tp
u
t
la
y
er
w
h
ic
h
is
s
o
f
t
m
a
x
la
y
er
.
T
h
e
s
ca
led
co
n
j
u
g
at
e
g
r
ad
ien
t
w
as
u
s
ed
as
t
h
e
tr
ain
i
n
g
f
u
n
ctio
n
o
f
b
ac
k
p
r
o
p
ag
atio
n
alg
o
r
ith
m
.
T
h
e
DFNN
w
er
e
tr
ai
n
ed
f
o
r
5
0
ep
o
ch
s
.
Fo
r
ea
ch
r
o
w
i
n
T
ab
le
3
,
th
e
n
u
m
b
er
o
f
n
o
d
es a
r
e
th
e
s
a
m
e,
th
er
e
f
o
r
e
th
e
tr
ain
i
n
g
ti
m
e
is
r
elati
v
el
y
s
i
m
ilar
.
3
.
3
.
O
pti
m
iza
t
io
n a
nd
T
esti
ng
P
ha
s
e
o
f
Va
rio
us
DF
NN
Str
uc
t
ures
Fo
r
te
s
tin
g
p
u
r
p
o
s
e,
w
e
s
e
t
th
e
n
u
m
b
er
o
f
ep
o
ch
s
to
1
0
0
0
.
T
ab
le
4
s
h
o
w
s
t
h
e
r
esu
lts
o
f
t
h
e
tr
ain
in
g
an
d
test
i
n
g
o
f
t
h
e
o
p
ti
m
u
m
DFNN
s
tr
u
ct
u
r
es
f
o
r
t
w
o
ed
g
e
f
ea
tu
r
es,
i.e
.
R
o
b
er
ts
an
d
C
an
n
y
al
g
o
r
ith
m
s
.
On
a
v
er
ag
e,
t
h
e
p
r
o
p
o
s
ed
ex
p
o
n
en
tial
d
ec
a
y
in
g
n
u
m
b
er
o
f
n
o
d
es
DFN
N
s
tr
u
cu
tu
r
es
p
er
f
o
r
m
ed
b
etter
in
ter
m
s
o
f
te
s
tin
g
r
ec
o
g
n
itio
n
r
ate
ac
r
o
s
s
t
w
o
ed
g
e
f
ea
t
u
r
es,
i.e
.
6
9
%
co
m
p
ar
ed
to
6
6
%.
B
ased
o
n
th
is
r
es
u
lt,
an
o
th
er
e
x
p
er
i
m
e
n
t
s
u
s
i
n
g
e
x
p
o
n
en
tial
d
ec
a
y
i
n
g
DFN
N
s
tr
u
ctu
r
e
s
w
a
s
co
n
d
u
cted
u
s
i
n
g
C
an
n
y
ed
g
e
f
ea
tu
r
es
o
n
l
y
a
n
d
th
e
r
es
u
lts
i
s
p
r
esen
t
ed
in
T
ab
le
5
.
Fo
r
b
etter
g
en
er
aliza
tio
n
an
d
to
av
o
id
o
v
er
-
f
itti
n
g
,
th
e
tr
ai
n
i
n
g
ep
o
ch
w
as
s
et
to
2
0
0
as
t
h
e
m
ax
i
m
u
m
p
er
f
o
r
m
a
n
ce
i
n
cr
o
s
s
v
alid
atio
n
i
s
ac
h
ie
v
ed
at
m
u
c
h
lo
w
er
ep
o
ch
t
h
en
1000.
T
ab
le
4
.
T
r
ain
in
g
an
d
T
esti
n
g
o
f
Op
ti
m
u
m
DFNN
Stru
ct
u
r
es
N
H
i
d
d
e
n
Ed
g
e
F
e
a
t
u
r
e
s
T
r
a
i
n
i
n
g
T
i
me
(
s)
T
r
a
i
n
i
n
g
R
e
c
o
g
n
i
t
i
o
n
R
a
t
e
(
%)
T
e
st
i
n
g
R
e
c
o
g
n
i
t
i
o
n
R
a
t
e
(
%)
[
1
0
0
0
1
0
0
1
0
]
R
o
b
e
r
t
s
1
7
1
8
9
5
.
3
3
6
5
.
0
0
[
1
0
0
0
1
0
0
1
0
]
C
a
n
n
y
2
2
9
5
9
7
.
3
3
6
7
.
0
0
[
3
0
9
4
3
6
3
4
3
]
R
o
b
e
r
t
s
5
1
4
4
9
8
.
0
0
6
8
.
0
0
[
3
0
9
4
3
6
3
4
3
]
C
a
n
n
y
6
3
0
3
9
8
.
6
7
7
0
.
0
0
T
ab
le
5
.
T
esti
n
g
R
ec
o
g
n
i
tio
n
R
ate
o
f
E
x
p
o
n
e
n
tia
l D
ec
a
y
i
n
g
DFNN
Str
u
ctu
r
es
N
H
i
d
d
e
n
T
r
a
i
n
i
n
g
T
i
me
(
s)
T
r
a
i
n
i
n
g
R
e
c
o
g
n
i
t
i
o
n
R
a
t
e
(
%)
T
e
st
i
n
g
R
e
c
o
g
n
i
t
i
o
n
R
a
t
e
(
%)
[
3
6
3
]
1
7
0
9
3
.
3
3
5
1
.
0
0
[
1
5
1
5
8
7
]
6
9
0
9
6
.
6
7
6
9
.
0
0
[
3
0
9
4
3
6
3
4
3
]
1
4
1
8
9
6
.
6
7
7
2
.
0
0
[
4
7
5
0
8
5
6
1
5
4
2
8
]
2
2
3
8
1
0
0
.
0
0
7
3
.
0
0
[
6
3
2
0
1
5
1
5
3
6
3
8
7
2
1
]
3
1
0
8
9
9
.
3
3
7
5
.
0
0
[
7
7
5
1
2
2
7
8
6
7
0
1
9
7
5
8
1
7
]
3
9
6
6
9
6
.
0
0
6
4
.
0
0
Fro
m
T
ab
le
5
,
alth
o
u
g
h
t
h
e
p
er
f
o
r
m
an
ce
o
f
a
tr
ai
n
ed
D
FNN
i
s
n
o
n
d
eter
m
in
i
s
tic,
it
co
u
ld
b
e
co
n
clu
d
ed
th
at
th
er
e
i
s
a
p
o
s
it
iv
e
tr
en
d
s
in
th
e
r
ec
o
g
n
itio
n
r
ate
w
h
e
n
t
h
e
n
u
m
b
er
o
f
h
id
d
e
n
la
y
er
s
o
f
D
FNN
w
er
e
i
n
cr
ea
s
ed
f
r
o
m
1
to
5
.
W
h
ile
i
n
cr
ea
s
i
n
g
f
u
t
h
er
t
h
e
n
u
m
b
er
o
f
la
y
er
d
id
n
o
t
i
m
p
r
o
v
e
t
h
e
r
ec
o
g
n
itio
n
r
ate.
T
h
is
co
u
ld
b
e
ca
u
s
e
b
y
o
v
er
f
itti
n
g
o
r
le
s
s
o
f
tr
ain
i
n
g
d
ata
to
b
etter
u
s
e
o
f
th
e
d
ee
p
er
lay
er
s
.
I
n
ter
esti
n
g
l
y
,
th
e
tr
ai
n
i
n
g
r
ec
o
g
n
it
io
n
r
ate
o
f
1
0
0
p
er
ce
n
t
d
id
n
o
t
tr
a
n
s
late
in
to
h
i
g
h
er
te
s
ti
n
g
r
ec
o
g
n
i
tio
n
r
ate.
I
n
s
u
m
m
ar
y
,
th
e
p
r
o
p
o
s
ed
ex
p
o
n
en
t
ial
d
ec
a
y
in
g
n
u
m
b
er
o
f
n
o
d
es
i
n
t
h
e
h
id
d
en
la
y
er
s
p
r
o
v
id
e
a
b
ett
er
DFNN
s
tr
u
ct
u
r
e
wi
t
h
h
i
g
h
r
ec
o
g
n
itio
n
r
ate.
T
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
co
u
ld
b
e
ev
alu
ated
w
it
h
o
t
h
er
h
a
n
d
w
r
itte
n
i
m
a
g
e
d
atab
ase
to
ev
alu
a
te
f
u
r
th
er
it
s
ef
f
ec
ti
v
e
n
e
s
s
.
4.
CO
NCLU
SI
O
N
T
h
is
p
ap
er
h
as
p
r
esen
ted
o
f
f
l
in
e
h
a
n
d
w
r
it
ten
s
i
g
n
atu
r
e
au
t
h
en
t
icatio
n
s
y
s
te
m
u
s
in
g
ed
g
e
f
ea
t
u
r
es
an
d
DFNN.
W
e
f
o
r
m
u
lated
e
x
p
o
n
en
t
ial
d
ec
a
y
i
n
g
n
u
m
b
er
o
f
n
o
d
es
i
n
t
h
e
h
id
d
en
la
y
er
s
o
f
DFNN
s
tr
u
ctu
r
e
s
an
d
u
s
ed
it
o
n
DFN
N.
Mo
r
eo
v
er
,
s
i
x
ed
g
e
d
etec
t
io
n
al
g
o
r
it
h
m
s
w
er
e
e
v
al
u
ated
,
in
w
h
ich
it
w
as
f
o
u
n
d
t
h
at
R
o
b
er
ts
an
d
C
an
n
y
ed
g
e
o
p
er
ato
r
s
p
r
o
d
u
cin
g
h
i
g
h
er
p
er
f
o
r
m
a
n
ce
.
Han
d
w
r
itte
n
i
m
ag
e
d
atab
ase
h
as
b
ee
n
r
ec
o
r
d
e
d
w
h
ic
h
co
n
s
i
s
ts
o
f
1
0
tr
ial
w
i
th
5
d
if
f
er
e
n
t
p
en
o
f
5
p
er
s
o
n
p
r
o
d
u
cin
g
to
tal
o
f
2
5
0
im
ag
e
s
.
R
es
u
lt
s
s
h
o
w
ed
th
at
o
u
r
p
r
o
p
o
s
ed
m
e
th
o
d
,
i.e
.
ex
p
o
n
en
tial
d
ec
a
y
in
g
n
u
m
b
er
o
f
n
o
d
es
in
th
e
h
id
d
en
la
y
er
s
,
p
r
o
d
u
ce
h
ig
h
er
ac
c
u
r
ac
y
.
T
h
e
h
i
g
h
est
test
i
n
g
r
ec
o
g
n
i
tio
n
r
ate
w
as
7
5
.
0
%
u
s
i
n
g
f
iv
e
h
id
d
en
la
y
er
s
.
F
u
r
th
er
r
esear
c
h
in
cl
u
d
es
t
h
e
u
s
e
o
f
d
i
f
f
er
e
n
t
h
an
d
w
r
itte
n
i
m
a
g
e
d
atab
ase,
o
r
th
e
u
s
e
o
f
o
th
er
t
y
p
es
o
f
d
ee
p
lear
n
in
g
li
k
e
co
n
v
o
lu
tio
n
al
n
eu
r
al
n
et
w
o
r
k
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
le
c
E
n
g
&
C
o
m
p
Sci,
Vo
l.
12
,
No
.
2
,
No
v
e
m
b
er
2
0
1
8
:
7
2
2
–
7
2
8
728
A
CK
NO
WL
E
D
G
M
E
NT
S
T
h
e
r
esear
ch
er
s
in
th
i
s
s
tu
d
y
w
o
u
ld
l
ik
e
to
ac
k
n
o
w
led
g
e
th
e
I
n
ter
n
atio
n
al
I
s
la
m
ic
Un
i
v
er
s
it
y
Ma
la
y
s
ia
(
I
I
UM
)
f
o
r
th
e
f
in
a
n
cial
f
u
n
d
in
g
o
f
t
h
is
r
esear
c
h
th
r
o
u
g
h
t
h
e
R
e
s
ea
r
ch
I
n
itiat
i
v
es
Gr
an
t
Sc
h
e
m
e
(
R
I
GS)
R
I
GS1
5
-
070
-
0070.
RE
F
E
R
E
NC
E
S
[1
]
.
D.
Be
a
tri
c
e
a
n
d
H.
T
h
o
m
a
s,
"
On
-
li
n
e
Ha
n
d
w
rit
ten
S
ig
n
a
tu
re
V
e
rif
ica
ti
o
n
u
si
n
g
M
a
c
h
in
e
L
e
a
rn
in
g
Tec
h
n
iq
u
e
s
w
it
h
a
De
e
p
L
e
a
rn
in
g
A
p
p
ro
a
c
h
.
M
a
ste
r'
s
T
h
e
se
s in
M
a
th
,
"
S
c
ien
c
e
s,
L
u
n
d
Un
ive
rs
it
y
,
2
0
1
5
.
[2
]
.
A
.
A
b
u
sh
a
riah
,
T
.
G
u
n
a
w
a
n
,
J.
Ch
e
b
il
,
a
n
d
M
.
A
b
u
s
h
a
ria
h
,
"
A
u
to
m
a
ti
c
p
e
rso
n
id
e
n
t
if
ica
ti
o
n
s
y
ste
m
u
sin
g
h
a
n
d
w
rit
ten
sig
n
a
tu
re
s,"
in
Co
m
p
u
ter
a
n
d
Co
mm
u
n
ic
a
ti
o
n
En
g
i
n
e
e
rin
g
(
ICCCE),
2
0
1
2
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
,
p
p
.
5
6
0
-
5
6
5
,
2
0
1
2
.
[3
]
.
B.
Na
ss
i,
A
.
L
e
v
y
,
Y.
El
o
v
ici,
a
n
d
E.
S
h
m
u
e
li
,
"
Ha
n
d
w
rit
ten
S
ig
n
a
tu
re
V
e
rif
ica
ti
o
n
Us
in
g
Ha
n
d
-
W
o
rn
De
v
ice
s,
"
a
rXiv p
re
p
ri
n
t
a
rX
iv:1
6
1
2
.
0
6
3
0
5
,
2
0
1
6
.
[4
]
.
K.
Ne
a
m
a
h
,
D.
M
o
h
a
m
a
d
,
T
.
S
a
b
a
,
a
n
d
A
.
R
e
h
m
a
n
,
"
Dis
c
ri
m
i
n
a
ti
v
e
f
e
a
tu
re
s
m
in
in
g
f
o
r
o
ff
li
n
e
h
a
n
d
w
rit
ten
sig
n
a
tu
re
v
e
rif
ic
a
ti
o
n
,
"
3
D R
e
se
a
rc
h
,
v
o
l.
5
,
p
p
.
1
-
6
,
2
0
1
4
.
[5
]
.
P
.
M
a
ji
,
S
.
Ch
a
tt
e
rjee
,
S
.
Ch
a
k
ra
b
o
rty
,
N.
Ka
u
sa
r,
S
.
S
a
m
a
n
ta,
a
n
d
N.
De
y
,
"
Eff
e
c
t
o
f
Eu
ler
n
u
m
b
e
r
a
s
a
f
e
a
tu
re
in
g
e
n
d
e
r
re
c
o
g
n
it
io
n
sy
ste
m
f
ro
m
o
ff
li
n
e
h
a
n
d
w
rit
ten
sig
n
a
tu
re
u
sin
g
n
e
u
ra
l
n
e
tw
o
rk
s,"
in
Co
mp
u
ti
n
g
f
o
r S
u
st
a
in
a
b
le
Glo
b
a
l
De
v
e
lo
p
me
n
t
(
INDIACo
m
)
,
2
0
1
5
2
n
d
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
,
p
p
.
1
8
6
9
-
1
8
7
3
,
2
0
1
5
.
[6
]
.
Y.
G
u
e
rb
a
i,
Y.
Ch
ib
a
n
i,
a
n
d
B.
Ha
d
jad
ji
,
"
T
h
e
e
ff
e
c
ti
v
e
u
se
o
f
th
e
o
n
e
-
c
las
s
S
V
M
c
las
sif
ier
fo
r
h
a
n
d
w
rit
ten
sig
n
a
tu
re
v
e
rif
ic
a
ti
o
n
b
a
se
d
o
n
w
r
it
e
r
-
in
d
e
p
e
n
d
e
n
t
p
a
ra
m
e
ters
,
"
Pa
tt
e
rn
Rec
o
g
n
it
io
n
,
v
o
l.
4
8
,
p
p
.
1
0
3
-
1
1
3
,
2
0
1
5
.
[7
]
.
A
.
P
a
n
sa
re
a
n
d
S
.
Bh
a
ti
a
,
"
Ha
n
d
w
rit
ten
sig
n
a
tu
re
v
e
rif
ica
ti
o
n
u
sin
g
n
e
u
ra
l
n
e
tw
o
rk
,
"
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
Ap
p
li
e
d
In
fo
rm
a
t
io
n
S
y
ste
ms
,
v
o
l.
1
,
p
p
.
4
4
-
4
9
,
2
0
1
2
.
[8
]
.
B.
Erk
m
e
n
,
N.
Ka
h
ra
m
a
n
,
R.
A
.
V
u
ra
l,
a
n
d
T
.
Yild
iri
m
,
"
Co
n
ic se
c
ti
o
n
f
u
n
c
ti
o
n
n
e
u
ra
l
n
e
tw
o
rk
c
irc
u
it
ry
f
o
r
o
ff
li
n
e
sig
n
a
tu
re
re
c
o
g
n
it
io
n
,
"
IEE
E
tra
n
sa
c
ti
o
n
s
o
n
n
e
u
r
a
l
n
e
two
rk
s
,
v
o
l.
2
1
,
p
p
.
6
6
7
-
6
7
2
,
2
0
1
0
.
[9
]
.
T
.
S
.
G
u
n
a
wa
n
,
N.
M
a
h
a
m
u
d
,
a
n
d
M
.
Ka
rti
w
i,
"
D
e
v
e
lo
p
m
e
n
t
o
f
o
ff
li
n
e
h
a
n
d
w
rit
ten
sig
n
a
tu
re
a
u
th
e
n
ti
c
a
ti
o
n
u
sin
g
a
rti
f
icia
l
n
e
u
ra
l
n
e
t
w
o
rk
,
"
in
Co
mp
u
ti
n
g
,
En
g
in
e
e
rin
g
,
a
n
d
De
sig
n
(
ICCED)
,
2
0
1
7
In
tern
a
ti
o
n
a
l
Co
n
f
e
r
e
n
c
e
o
n
,
p
p
.
1
-
4
,
2
0
1
7
.
[1
0
]
.
P
.
Kim
,
"
M
A
TL
A
B
D
e
e
p
L
e
a
rn
in
g
,
"
W
it
h
M
a
c
h
in
e
L
e
a
rn
i
n
g
,
Ne
u
ra
l
Ne
two
rk
s a
n
d
Arti
fi
c
ia
l
In
tell
i
g
e
n
c
e
,
2
0
1
7
.
[1
1
]
.
P
.
T
h
o
m
a
s
a
n
d
M
.
-
C
.
S
u
h
n
e
r,
"
A
n
e
w
m
u
lt
il
a
y
e
r
p
e
rc
e
p
t
ro
n
p
r
u
n
in
g
a
lg
o
rit
h
m
f
o
r
c
las
si
f
ica
ti
o
n
a
n
d
re
g
re
ss
io
n
a
p
p
li
c
a
ti
o
n
s,"
Ne
u
ra
l
Pro
c
e
ss
in
g
L
e
tt
e
rs
,
v
o
l.
4
2
,
p
p
.
4
3
7
-
4
5
8
,
2
0
1
5
.
[1
2
]
.
T
.
S
.
G
u
n
a
w
a
n
,
I.
Z.
Ya
a
c
o
b
,
M
.
Ka
rti
w
i,
N.
Is
m
a
il
,
N.
F
.
Za'
b
a
h
,
a
n
d
H.
M
a
n
so
r,
"
A
rti
f
i
c
ial
Ne
u
ra
l
Ne
t
w
o
rk
Ba
se
d
F
a
st
Ed
g
e
De
tec
t
io
n
A
lg
o
rit
h
m
f
o
r
M
RI
M
e
d
ica
l
Im
a
g
e
s,"
I
n
d
o
n
e
sia
n
J
o
u
rn
a
l
o
f
El
e
c
trica
l
E
n
g
i
n
e
e
rin
g
a
n
d
Co
mp
u
ter
S
c
ien
c
e
(
IJ
EE
CS
)
,
v
o
l.
7
,
p
p
.
1
2
3
-
1
3
0
,
2
0
1
7
.
[1
3
]
.
Y.
L
e
Cu
n
,
Y.
Be
n
g
io
,
a
n
d
G
.
Hin
to
n
,
"
De
e
p
lea
rn
in
g
,
"
Na
tu
re
,
v
o
l
.
5
2
1
,
p
p
.
4
3
6
,
2
0
1
5
.
[1
4
]
.
M
.
F
.
A
lg
h
if
a
ri,
T
.
S
.
G
u
n
a
w
a
n
,
a
n
d
M
.
Ka
rti
w
i,
"
S
p
e
e
c
h
Em
o
ti
o
n
Re
c
o
g
n
it
io
n
Us
in
g
De
e
p
F
e
e
d
f
o
rw
a
rd
Ne
u
ra
l
Ne
tw
o
rk
,
"
In
d
o
n
e
si
a
n
J
o
u
rn
a
l
o
f
El
e
c
trica
l
En
g
in
e
e
rin
g
a
n
d
Co
m
p
u
ter
S
c
ien
c
e
(
IJ
EE
CS
)
,
v
o
l.
1
0
,
2
0
1
8
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
T
e
d
d
y
S
u
ry
a
G
u
n
a
wa
n
re
c
e
iv
e
d
h
is
B
En
g
d
e
g
re
e
in
E
lec
tri
c
a
l
En
g
in
e
e
rin
g
w
it
h
c
u
m
lau
d
e
a
wa
rd
f
ro
m
In
stit
u
t
T
e
k
n
o
lo
g
i
Ba
n
d
u
n
g
(IT
B),
In
d
o
n
e
sia
in
1
9
9
8
.
He
o
b
tain
e
d
h
is
M
.
En
g
d
e
g
re
e
in
2
0
0
1
f
ro
m
th
e
S
c
h
o
o
l
o
f
Co
m
p
u
ter
En
g
in
e
e
rin
g
a
t
Na
n
y
a
n
g
Tec
h
n
o
lo
g
ica
l
Un
iv
e
rsit
y
,
S
in
g
a
p
o
re
,
a
n
d
P
h
D
d
e
g
re
e
in
2
0
0
7
f
ro
m
th
e
S
c
h
o
o
l
o
f
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
a
n
d
T
e
le
c
o
m
m
u
n
ica
ti
o
n
s,
T
h
e
Un
iv
e
rsity
o
f
Ne
w
S
o
u
th
W
a
les
,
A
u
stra
li
a
.
His
re
s
e
a
rc
h
in
tere
sts
a
re
in
sp
e
e
c
h
a
n
d
a
u
d
io
p
ro
c
e
ss
in
g
,
b
io
m
e
d
ica
l
sig
n
a
l
p
ro
c
e
s
sin
g
a
n
d
in
str
u
m
e
n
tatio
n
,
im
a
g
e
a
n
d
v
id
e
o
p
r
o
c
e
ss
in
g
,
a
n
d
p
a
ra
ll
e
l
c
o
m
p
u
ti
n
g
.
He
is
c
u
rre
n
tl
y
a
n
I
EE
E
S
e
n
i
o
r
M
e
m
b
e
r
(sin
c
e
2
0
1
2
),
w
a
s
c
h
a
ir
m
a
n
o
f
IEE
E
In
stru
m
e
n
tatio
n
a
n
d
M
e
a
su
re
m
e
n
t
S
o
c
iety
–
M
a
la
y
sia
S
e
c
ti
o
n
(2
0
1
3
a
n
d
2
0
1
4
),
A
ss
o
c
iate
P
r
o
f
e
ss
o
r
(sin
c
e
2
0
1
2
)
,
He
a
d
o
f
De
p
a
rtme
n
t
(2
0
1
5
-
2
0
1
6
)
a
t
De
p
a
rtme
n
t
o
f
El
e
c
tri
c
a
l
a
n
d
Co
m
p
u
ter
En
g
in
e
e
rin
g
,
a
n
d
He
a
d
o
f
P
ro
g
ra
m
m
e
A
c
c
r
e
d
it
a
ti
o
n
a
n
d
Qu
a
li
ty
A
s
su
ra
n
c
e
f
o
r
F
a
c
u
lt
y
o
f
En
g
in
e
e
rin
g
(sin
c
e
2
0
1
7
),
In
tern
a
ti
o
n
a
l
Isla
m
ic
Un
iv
e
rsit
y
M
a
la
y
sia
.
He
is
Ch
a
r
tere
d
En
g
in
e
e
r
(IE
T
,
UK
)
a
n
d
In
sin
y
u
r
P
r
o
f
e
sio
n
a
l
M
a
d
y
a
(P
II
,
In
d
o
n
e
sia
)
sin
c
e
2
0
1
6
.
M
ira
Ka
rti
w
i
c
o
m
p
lete
d
h
e
r
stu
d
i
e
s
a
t
th
e
Un
iv
e
rsit
y
o
f
W
o
ll
o
n
g
o
n
g
,
A
u
stra
li
a
re
su
lt
in
g
in
th
e
f
o
ll
o
w
in
g
d
e
g
re
e
s
b
e
in
g
c
o
n
f
e
rr
e
d
:
Ba
c
h
e
lo
r
o
f
Co
m
m
e
r
c
e
in
Bu
sin
e
ss
In
f
o
rm
a
ti
o
n
S
y
ste
m
s,
M
a
ste
r
in
In
f
o
rm
a
ti
o
n
S
y
ste
m
s
in
2
0
0
1
a
n
d
h
e
r
Do
c
to
r
o
f
P
h
i
lo
so
p
h
y
in
2
0
0
9
.
S
h
e
is
c
u
rre
n
t
ly
a
n
As
so
c
iate
P
ro
f
e
ss
o
r
in
De
p
a
rt
m
e
n
t
o
f
In
f
o
r
m
a
ti
o
n
S
y
st
e
m
s,
K
u
li
y
y
a
h
o
f
In
f
o
r
m
a
ti
o
n
a
n
d
Co
m
m
u
n
ica
ti
o
n
T
e
c
h
n
o
lo
g
y
,
In
te
rn
a
ti
o
n
a
l
Isla
m
ic
Un
iv
e
r
sit
y
M
a
la
y
sia
.
He
r
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
e
lec
tro
n
ic co
m
m
e
rc
e
,
d
a
ta m
in
in
g
,
e
-
h
e
a
lt
h
a
n
d
m
o
b
il
e
a
p
p
li
c
a
ti
o
n
s d
e
v
e
lo
p
m
e
n
t.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
On
th
e
Use o
f E
d
g
e
F
ea
tu
r
es a
n
d
E
x
p
o
n
e
n
tia
l D
ec
a
yin
g
N
u
mb
er o
f No
d
es in
th
e…
(
Ted
d
y
S
u
r
ya
Gu
n
a
w
a
n
)
729
Evaluation Warning : The document was created with Spire.PDF for Python.