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.
1
2
,
No
.
2
,
N
o
v
e
m
b
er
201
8
,
p
p
.
ab
~
cd
I
SS
N:
2502
-
4752
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ee
cs
.
v
1
2
.i
2
.
p
p
ab
-
cd
883
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
J
a
tropha
Curcas
Disea
se Identi
fica
tion Wit
h Ex
tre
me
Lea
rning
Ma
chine
T
ria
nd
o
H
a
m
o
na
ng
a
n Sa
ra
g
ih
1
,
Diny
M
elsy
e
Nurul F
a
j
ri
2
,
Wa
y
a
n F
irda
us
M
a
h
m
u
dy
3
,
Abdu
l
L
a
t
ief
Aba
di
4
,
Yus
uf
P
riy
o
Ang
g
o
d
o
5
1,
2,
3
F
a
c
u
l
ty
o
f
Co
m
p
u
ter S
c
ien
c
e
,
Bra
w
ij
a
y
a
Un
iv
e
rsit
y
,
M
a
lan
g
6
5
1
4
5
,
I
n
d
o
n
e
sia
4
F
a
c
u
lt
y
o
f
Ag
icu
lt
u
re
,
Bra
w
ij
a
y
a
Un
iv
e
rsity
,
M
a
lan
g
6
5
1
4
5
,
I
n
d
o
n
e
sia
5
Da
ta
A
n
a
l
y
st,
Ilm
u
o
n
e
Da
ta,
Ja
k
a
rta 1
2
1
9
0
,
In
d
o
n
e
sia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
A
p
r
9
,
2
0
1
8
R
ev
i
s
ed
Ma
y
2
0
,
2
0
1
8
A
cc
ep
ted
Ju
l
11
,
2
0
1
8
Ja
tr
o
p
h
a
is
a
p
lan
t
th
a
t
h
a
s
m
a
n
y
f
u
n
c
ti
o
n
s,
b
u
t
th
is
p
la
n
t
c
a
n
b
e
a
tt
a
c
k
e
d
b
y
v
a
rio
u
s
d
ise
a
se
s.
Ex
p
e
rt
s
y
ste
m
s
c
a
n
b
e
a
p
p
li
e
d
in
i
d
e
n
ti
f
y
in
g
s
o
th
a
t
c
a
n
h
e
lp
b
o
t
h
f
a
rm
e
rs
a
n
d
e
x
ten
sio
n
w
o
rk
e
rs
to
id
e
n
ti
fy
th
e
d
ise
a
se
.
o
n
e
o
f
m
e
th
o
d
t
h
a
t
c
a
n
b
e
u
se
d
is
Ex
tre
m
e
L
e
a
rn
in
g
M
a
c
h
in
e
.
Ex
tre
m
e
L
e
a
rn
in
g
M
a
c
h
in
e
is
a
m
e
th
o
d
o
f
lea
rn
in
g
in
Ne
u
ra
l
Ne
tw
o
rk
w
h
ich
h
a
s
a
o
n
e
-
ti
m
e
it
e
ra
ti
o
n
c
o
n
c
e
p
t
i
n
e
a
c
h
p
ro
c
e
ss
.
In
th
is
stu
d
y
g
e
t
a
m
a
x
i
m
u
m
a
c
c
u
ra
c
y
o
f
6
6
.
6
7
%
w
it
h
a
n
a
v
e
ra
g
e
a
c
c
u
ra
c
y
o
f
6
0
.
6
1
%
.
T
h
is
p
r
o
v
e
s
th
e
id
e
n
ti
f
ica
ti
o
n
u
sin
g
Ex
tre
m
e
L
e
a
rn
in
g
M
a
c
h
in
e
is
b
e
tt
e
r
th
a
n
th
e
c
o
m
p
a
riso
n
m
e
th
o
d
th
a
t
h
a
s b
e
e
n
d
o
n
e
b
e
f
o
re
.
K
ey
w
o
r
d
s
:
Dete
ctio
n
E
x
tr
e
m
e
L
ea
r
n
in
g
Net
w
o
r
k
J
atr
o
p
h
a
C
u
r
ca
s
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
:
W
ay
a
n
Fird
au
s
Ma
h
m
u
d
y
,
Facu
lt
y
o
f
C
o
m
p
u
ter
Scien
ce
,
B
r
a
w
ij
ay
a
U
n
i
v
er
s
it
y
,
Ma
la
n
g
6
5
1
4
5
,
I
n
d
o
n
esia
.
E
m
ail:
w
a
y
a
n
f
m
@
u
b
.
ac
.
id
1.
I
NT
RO
D
UCT
I
O
N
J
atr
o
p
h
a
p
lan
t
is
a
p
lan
t
t
h
at
ca
n
g
r
o
w
w
ell
in
d
r
y
lo
w
lan
d
w
i
th
a
h
ei
g
h
t
o
f
0
-
5
0
0
m
d
p
l,
r
ain
f
al
l
o
f
300
-
1
0
0
0
m
m
p
er
y
ea
r
an
d
tem
p
er
at
u
r
es
b
et
w
ee
n
2
0
-
26oC
(
1
)
.
T
h
is
p
lan
t
o
r
ig
in
a
ll
y
ca
m
e
f
r
o
m
Am
er
ica
(
2
)
,
b
u
t
ca
n
al
s
o
b
e
f
o
u
n
d
in
So
u
t
h
ea
s
t
Asi
a,
s
o
u
th
er
n
an
d
ce
n
t
r
al
Af
r
ica,
s
o
u
t
h
er
n
I
n
d
ia
(
3
)
,
an
d
I
n
d
o
n
esia
(
1
)
.
T
h
is
p
lan
t
h
as
m
a
n
y
b
en
e
f
its
s
u
c
h
as
b
io
d
iesel
r
ep
lace
m
e
n
t,
an
d
i
ts
s
ee
d
o
il
ca
n
b
e
u
s
ed
as
an
ad
d
iti
v
e
to
ca
n
d
le
m
a
k
i
n
g
,
s
o
ap
,
co
s
m
eti
cs,
an
d
d
eter
g
e
n
ts
(
2
)
.
Mo
r
eo
v
er
,
J
atr
o
p
h
a
o
il
co
n
ten
t
r
ea
c
h
e
s
6
3
%
co
m
p
ar
ed
to
s
o
y
b
ea
n
o
il,
s
u
n
f
lo
w
er
an
d
p
al
m
o
il
(
3
)
.
No
t
ap
ar
t
f
r
o
m
t
h
at,
j
atr
o
p
h
a
cu
lti
v
atio
n
ca
n
s
u
f
f
er
d
is
ea
s
e
s
th
at
attac
k
lea
v
es,
s
te
m
s
,
r
o
o
ts
,
f
lo
w
er
s
,
an
d
s
ee
d
s
.
Di
s
ea
s
es
o
f
J
atr
o
p
h
a
p
lan
ts
ar
e
a
t
h
r
ea
t
to
f
ar
m
e
r
s
b
ec
au
s
e
t
h
e
y
ca
n
ca
u
s
e
d
ea
t
h
(
1
)
an
d
r
esu
lted
i
n
d
ec
r
ea
s
ed
y
ield
s
.
A
cc
o
r
d
in
g
t
o
th
e
r
esu
lts
o
f
i
n
ter
v
ie
w
s
w
it
h
ex
p
er
ts
,
i
n
r
ec
o
g
n
izi
n
g
j
atr
o
p
h
a
d
is
ea
s
es
o
f
t
h
e
f
ar
m
er
s
ar
e
s
till
e
x
p
er
ien
ci
n
g
d
if
f
ic
u
ltie
s
d
u
e
to
lack
o
f
ex
ten
s
io
n
co
u
n
s
e
lin
g
ti
m
e
s
o
th
at
k
n
o
w
led
g
e
o
f
f
ar
m
er
s
ab
o
u
t J
atr
o
p
h
a
cu
r
ca
s
an
d
d
is
ea
s
e
i
s
s
till
lac
k
i
n
g
.
T
o
h
e
lp
f
ar
m
er
s
in
id
en
ti
f
y
in
g
t
h
e
d
is
ea
s
e,
it ta
k
es
a
m
et
h
o
d
th
at
ca
n
u
ti
lize
t
h
e
k
n
o
w
led
g
e
o
f
e
x
p
er
ts
w
h
o
w
i
ll
b
e
in
s
er
ted
i
n
to
t
h
e
co
m
p
u
ter
th
e
n
t
h
e
co
m
p
u
ter
ca
n
g
i
v
e
t
h
e
r
esu
l
ts
o
f
id
e
n
ti
f
i
ca
tio
n
lik
e
a
n
ex
p
er
t,
th
is
s
y
s
t
e
m
is
ca
lled
e
x
p
er
t s
y
s
te
m
(
4
)
.
T
h
e
s
y
s
te
m
m
o
d
el
t
h
at
w
il
l
b
e
d
esig
n
ed
in
th
i
s
p
ap
er
is
u
s
i
n
g
q
u
a
n
titat
iv
e
d
ata
f
r
o
m
e
x
p
er
ts
w
h
o
ar
e
u
s
ed
as
b
asic
k
n
o
w
led
g
e
i
n
t
h
e
s
y
s
te
m
.
Da
ta
f
r
o
m
th
e
e
x
p
er
t
is
d
ata
f
r
o
m
9
d
is
ea
s
es
an
d
3
0
s
y
m
p
to
m
s
.
I
n
d
o
in
g
id
en
t
if
ica
tio
n
o
f
J
atr
o
p
h
a
p
lan
t d
is
ea
s
e
r
eq
u
ir
ed
th
e
ap
p
r
o
p
r
iate
m
eth
o
d
,
s
o
it c
an
id
e
n
ti
f
y
w
e
ll.
I
n
s
o
m
e
s
tu
d
ie
s
o
f
d
is
ea
s
e
id
e
n
ti
f
icati
o
n
,
esp
ec
iall
y
f
o
r
J
atr
o
p
h
a
cu
r
ca
s
w
it
h
t
h
e
s
a
m
e
d
ata
h
a
v
e
b
ee
n
d
o
n
e
b
y
u
s
i
n
g
Fu
zz
y
Ne
u
r
al
Net
w
o
r
k
m
eth
o
d
(
5
)
w
h
ic
h
g
et
a
f
air
l
y
lo
w
ac
cu
r
ac
y
o
f
ab
o
u
t
1
1
.
2
%.
I
t
is
co
n
s
id
er
ed
n
ec
ess
ar
y
to
b
e
im
p
r
o
v
ed
b
y
m
ea
n
s
o
f
o
p
ti
m
izatio
n
u
s
in
g
t
h
e
Si
m
u
lat
ed
A
n
n
ea
li
n
g
m
e
th
o
d
(
6
)
w
h
ic
h
r
esu
lts
p
r
o
m
is
e
to
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
25
02
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l
.
1
2
,
No
.
2
,
No
v
e
m
b
er
201
8
:
xx
–
xx
884
i
m
p
r
o
v
e
r
es
u
lt
s
.
T
h
e
r
es
u
lt
s
o
b
tain
ed
af
ter
th
e
o
p
ti
m
iza
tio
n
,
w
h
ic
h
i
s
eq
u
a
l
to
3
2
.
5
%.
I
n
cr
ea
s
ed
b
y
2
1
.
3
%
th
an
u
s
in
g
F
u
zz
y
Ne
u
r
al
Net
wo
r
k
o
n
l
y
.
T
o
p
r
o
v
id
e
d
ee
p
er
lear
n
in
g
t
o
m
ak
e
d
ec
is
io
n
s
o
n
th
e
d
ete
ctio
n
s
y
s
te
m
ar
e
k
n
o
w
n
s
o
m
e
lear
n
i
n
g
m
et
h
o
d
s
i
n
n
eu
r
al
n
et
w
o
r
k
,
o
n
e
o
f
w
h
ich
is
E
x
tr
e
m
e
L
ea
r
n
in
g
Ma
c
h
in
e
(
E
L
M)
.
T
h
e
s
t
u
d
y
u
s
ed
t
h
e
E
x
tr
e
m
e
L
ea
r
n
i
n
g
Net
w
o
r
k
(
E
L
M)
m
et
h
o
d
co
n
d
u
cted
b
y
R
a
h
m
a
et
al
(
7
)
to
class
if
y
s
tr
o
k
e
lev
el
f
r
o
m
E
lectr
o
ce
p
h
alo
g
r
a
m
an
a
l
y
s
is
(
E
E
G
s
ig
n
a
l)
w
h
ic
h
r
esu
l
ted
in
ac
cu
r
ac
y
ab
o
v
e
7
2
%.
Fu
r
th
er
r
esear
ch
w
a
s
co
n
d
u
cted
b
y
Z
h
an
g
,
w
h
o
p
er
f
o
r
m
ed
ea
r
l
y
d
etec
tio
n
o
f
t
h
e
r
is
k
o
f
h
ea
r
t
f
ail
u
r
e
w
it
h
b
asic
in
f
o
r
m
at
io
n
,
d
em
o
g
r
ap
h
ics
an
d
p
atie
n
t
d
is
ea
s
e
d
ata
as
t
h
e
p
r
i
m
ar
y
in
p
u
t
.
B
y
u
s
i
n
g
E
L
M
t
h
e
r
esu
lt
o
b
tain
e
d
is
q
u
ite
h
ig
h
th
at
is
eq
u
al
to
9
3
%.
B
ased
o
n
p
r
ev
io
u
s
r
esear
ch
u
s
ed
E
L
M,
in
t
h
is
r
esear
c
h
m
et
h
o
d
u
s
ed
is
E
x
tr
e
m
e
L
ea
r
n
i
n
g
Net
w
o
r
k
(
E
L
M)
to
d
etec
t J
atr
o
p
h
a
p
lan
t d
is
ea
s
e
t
y
p
e.
2.
J
AT
RO
P
H
A
CURC
AS
DIS
E
AS
E
T
h
e
ca
u
s
e
o
f
j
atr
o
p
h
a
d
is
ea
s
e
is
p
ath
o
g
e
n
(
1
)
.
T
h
er
e
ar
e
m
an
y
k
i
n
d
s
o
f
p
at
h
o
g
e
n
ic
f
u
n
g
i
th
at
attac
k
th
e
J
atr
o
p
h
a
p
lan
t,
Hel
m
i
n
t
h
o
s
p
o
r
iu
m
tetr
a
m
er
a,
P
estalo
tio
p
s
is
p
ar
ag
u
ar
e
n
s
i
s
,
P
.
Vesico
lo
r
,
C
er
co
s
p
o
r
a
j
atr
o
p
h
ae
cu
r
ce
s
,
P
h
u
to
p
h
t
h
o
r
a
s
p
p
.
,
P
y
t
h
i
u
m
s
p
p
.
,
Fu
s
ar
iu
m
s
p
p
.
,
Do
t
h
io
r
ella
s
p
.
,
C
o
lleto
tr
ich
u
m
s
p
.
,
Oid
iu
m
s
p
.
,
A
lter
n
ar
ia
s
p
.
,
Fu
s
ar
iu
m
s
p
.
,
Xan
t
h
o
m
o
n
a
s
s
p
.
,
J
.
G
o
s
s
y
p
iella
(
8
)
,
an
d
A
r
m
il
lar
ia
tab
escen
s
(
9
)
.
B
ased
o
n
th
e
ab
o
v
e
t
y
p
es
o
f
p
ath
o
g
en
s
ca
u
s
e
v
ar
io
u
s
d
is
ea
s
es
s
u
c
h
as
p
atch
e
s
o
f
lea
v
es,
r
o
o
t
r
o
t
an
d
o
th
er
s
(
1
)
.
Fo
r
m
o
r
e
d
etails,
j
atr
o
p
h
a
d
is
ea
s
es a
n
d
th
eir
s
y
m
p
to
m
s
c
an
b
e
s
ee
n
i
n
T
ab
le
1
b
elo
w
.
T
ab
le
1
.
J
atr
o
p
h
a
C
u
r
ca
s
Dis
e
ase
No
D
i
se
a
se
s
P
a
t
h
o
g
e
n
Ef
f
e
c
t
s
C
a
u
se
s
1
B
a
c
t
e
r
i
a
l
W
i
l
t
Ra
l
s
t
o
n
i
a
so
l
a
n
a
c
e
a
ru
m
B
a
c
t
e
r
i
a
I
n
f
e
c
t
e
d
p
l
a
n
t
s
b
e
c
o
me
w
i
t
h
e
r
e
d
.
-
R
o
t
a
t
t
h
e
b
a
se
o
f
t
h
e
st
e
m a
n
d
r
o
o
t
s.
-
T
h
e
o
t
h
e
r
si
d
e
o
f
t
h
e
p
l
a
n
t
w
i
t
h
e
r
s.
-
Ex
p
e
r
i
e
n
c
i
n
g
d
e
c
a
y
a
t
t
h
e
b
a
se
o
f
t
h
e
b
r
a
n
c
h
.
-
T
h
e
mai
n
st
e
m
b
a
se
so
me
t
i
me
s ro
t
s.
2
C
h
a
r
c
o
a
l
R
o
t
Rh
i
c
z
o
c
t
o
n
i
a
b
a
t
a
t
i
c
o
l
a
F
u
n
g
i
M
a
y
c
a
u
se
sp
r
o
u
t
s
t
o
d
i
e
b
e
f
o
r
e
o
r
a
f
t
e
r
su
r
f
a
c
e
.
-
T
h
e
l
e
a
v
e
s
w
i
t
h
e
r
i
n
a
l
l
p
a
r
t
s
o
f
t
h
e
p
l
a
n
t
su
d
d
e
n
l
y
.
-
T
h
e
l
e
a
v
e
s
w
i
t
h
e
r
y
e
l
l
o
w
i
n
g
a
t
t
h
e
b
o
t
t
o
m
o
f
t
h
e
p
l
a
n
t
a
n
d
f
a
l
l
o
u
t
.
-
R
o
o
t
l
o
o
k
s b
l
a
c
k
i
sh
.
3
P
o
w
d
e
r
y
M
i
l
d
e
w
Pse
u
d
o
i
d
i
u
m
j
a
t
ro
p
h
a
e
F
u
n
g
i
-
Le
a
f
f
a
l
l
o
r
sh
o
o
t
d
o
e
s
n
o
t
d
e
v
e
l
o
p
a
n
d
d
i
e
.
-
Y
o
u
n
g
f
r
u
i
t
s
u
su
a
l
l
y
c
h
a
n
g
e
sh
a
p
e
a
n
d
f
a
l
l
.
-
T
h
e
p
r
e
se
n
c
e
o
f
w
h
i
t
e
p
o
w
d
e
r
y
mi
l
d
e
w
o
n
t
h
e
l
e
a
v
e
s,
f
r
u
i
t
,
a
n
d
s
t
e
ms
w
h
e
n
t
h
e
y
a
r
e
st
i
l
l
y
o
u
n
g
o
r
sh
o
o
t
.
4
A
n
t
r
a
k
n
o
sa
C
o
l
l
e
t
o
t
r
i
c
h
u
m
g
l
o
e
o
s
p
o
r
i
o
i
d
e
s
F
u
n
g
i
-
L
e
a
v
e
s
o
r
f
r
u
it
b
e
c
o
me
d
a
m
a
g
e
d
.
-
S
p
r
o
u
t
sh
o
o
t
s o
f
f
.
-
B
r
o
w
n
r
o
u
n
d
sp
o
t
s
a
r
e
r
e
st
r
i
c
t
e
d
y
e
l
l
o
w
h
a
l
o
.
-
If
a
t
t
a
c
k
i
n
g
t
h
e
e
d
g
e
o
f
t
h
e
l
e
a
v
e
s
a
r
e
i
r
r
e
g
u
l
a
r
sp
o
t
s.
-
B
l
a
c
k
i
s
h
b
r
o
w
n
sp
o
t
s o
n
t
h
e
f
r
u
i
t
s
u
r
f
a
c
e
5
B
a
c
t
e
r
i
a
l
B
l
i
g
h
t
Xa
n
t
h
o
m
o
n
a
s
c
a
m
p
e
s
t
ri
s
.
-
A
q
u
e
o
u
s
sp
o
t
s
b
o
r
d
e
r
i
n
g
l
e
a
f
r
e
p
e
a
t
s
t
o
f
o
r
m
a
n
g
l
e
d
sp
o
t
s.
-
B
l
a
c
k
i
s
h
s
p
o
t
s o
n
t
h
e
l
e
a
v
e
s.
-
U
n
d
e
r
t
h
e
su
r
f
a
c
e
,
l
e
a
v
e
s
l
o
o
k
sh
i
n
y
6
F
u
sari
u
m W
i
l
t
Fu
s
a
ri
u
m
sp
p
.
F
u
n
g
i
P
l
a
n
t
s
b
e
c
o
me
d
e
a
d
-
P
l
a
n
t
w
i
t
h
e
r
e
d
w
i
t
h
y
e
l
l
o
w
i
sh
l
e
a
v
e
s.
-
I
f
t
h
e
st
e
m
i
s
d
e
f
e
n
d
e
d
w
i
l
l
l
o
o
k
t
h
e
p
a
r
t
o
f
t
h
e
w
o
o
d
y
b
r
o
w
n
r
i
b
b
e
d
.
7
D
i
e
b
a
c
k
N
o
t
y
e
t
k
n
o
w
n
-
T
h
e
r
o
t
st
a
r
t
s
f
r
o
m t
h
e
t
i
p
/
t
o
p
o
f
t
h
e
p
l
a
n
t
.
-
L
e
a
v
e
s fal
l
a
n
d
s
t
e
ms l
o
o
k
b
a
r
e
.
-
S
i
d
e
sh
o
o
t
s
c
a
n
n
o
t
g
r
o
w
b
e
c
a
u
se
t
h
e
b
r
a
n
c
h
e
s
r
o
t
.
-
T
h
e
r
o
t
t
e
n
p
a
r
t
i
s
u
s
u
a
l
l
y
w
a
t
e
r
y
a
n
d
t
h
e
sh
o
o
t
s
d
r
y
o
u
t
.
-
I
f
t
h
e
sp
l
i
t
p
a
r
t
w
i
l
l
b
e
see
n
t
h
e
v
e
sse
l
s
a
n
d
b
r
o
w
n
p
i
t
h
.
8
C
e
r
c
o
sp
o
r
a
L
e
a
f
B
l
i
g
h
t
C
e
rc
o
s
p
o
ra
j
a
t
ro
p
h
i
c
o
l
a
F
u
n
g
i
-
I
r
r
e
g
u
l
a
r
b
r
o
w
n
c
o
l
o
r
o
n
l
e
a
v
e
s.
9
A
l
t
e
n
a
r
i
a
L
e
a
f
B
l
i
g
h
t
Al
t
e
n
a
ri
a
F
u
n
g
i
-
S
p
o
t
s ri
n
g
r
o
u
n
d
e
d
l
e
a
v
e
s
3.
DATAS
E
T
I
n
t
h
is
r
e
s
ea
r
ch
ar
e
g
r
o
u
p
ed
in
to
t
w
o
th
at
is
tr
ain
i
n
g
d
at
a
an
d
tes
t
d
ata.
T
h
e
tr
ain
i
n
g
d
ata
w
as
o
b
tain
ed
f
r
o
m
e
x
p
er
ts
o
f
J
atr
o
p
h
a
p
lan
t
d
is
ea
s
e
at
I
n
d
o
n
e
s
ian
C
r
o
p
s
a
n
d
Fib
er
C
r
o
p
s
R
esear
ch
I
n
s
tit
u
te.
Data
o
b
tain
ed
f
r
o
m
t
h
e
r
esu
l
ts
o
f
d
ir
ec
t
in
ter
v
ie
w
s
co
n
d
u
cted
in
2
0
1
5
in
th
e
f
o
r
m
o
f
9
d
is
ea
s
es
an
d
3
0
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
Ja
tr
o
p
h
a
C
u
r
ca
s
Dis
ea
s
e
I
d
en
tifi
ca
tio
n
W
ith
E
xtre
me
Lea
r
n
i
n
g
Ma
ch
in
e
(
Tr
ia
n
d
o
Ha
m
o
n
a
n
g
a
n
S
a
r
a
g
i
h
)
885
s
y
m
p
to
m
s
w
it
h
t
h
e
v
al
u
e
o
f
ea
ch
s
y
m
p
to
m
i
s
w
o
r
th
b
et
wee
n
0
-
1
.
T
h
e
test
d
ata
w
er
e
o
b
tain
ed
f
r
o
m
d
ir
ec
t
o
b
s
er
v
atio
n
d
ata
at
J
atr
o
p
h
a
p
lan
tatio
n
in
S
itu
b
o
n
d
o
.
T
h
e
test
d
ata
o
b
tain
ed
a
m
o
u
n
ted
to
1
6
6
d
ata.
T
h
e
o
b
tain
ed
d
ata
w
ill b
e
t
h
e
l
i
m
itat
io
n
s
i
n
t
h
is
s
tu
d
y
.
4.
NE
URA
L
N
E
T
WO
RK
Neu
r
al
n
et
w
o
r
k
i
s
a
m
o
d
el
in
g
o
f
a
co
g
n
iti
v
e
w
a
y
o
f
th
i
n
k
in
g
t
h
at
is
ca
p
ab
le
o
f
lear
n
in
g
.
T
h
e
lear
n
in
g
p
r
o
ce
s
s
is
a
p
r
o
ce
s
s
w
h
er
e
t
h
e
n
ec
es
s
ar
y
k
n
o
w
led
g
e
w
ill
b
e
s
to
r
ed
in
th
e
n
o
d
es
an
d
w
ei
g
h
ted
(
1
0
)
.
T
h
e
p
r
o
ce
s
s
o
f
ad
d
in
g
k
n
o
w
led
g
e
to
th
e
n
eu
r
al
n
et
w
o
r
k
is
d
o
n
e
co
n
ti
n
u
o
u
s
l
y
s
o
th
a
t
k
n
o
w
led
g
e
w
ill
b
e
m
ax
i
m
a
ll
y
ex
p
lo
ited
to
r
ec
o
g
n
ize
an
o
b
j
ec
t
(
1
1
)
.
T
h
e
ty
p
e
o
f
lear
n
i
n
g
u
n
d
er
ta
k
en
b
y
th
e
n
eu
r
al
n
et
w
o
r
k
i
s
b
ased
o
n
h
i
s
to
r
ical
d
ata.
Neu
r
al
n
et
w
o
r
k
m
et
h
o
d
s
u
s
e
n
o
n
-
li
n
ea
r
i
n
ter
c
o
n
n
ec
ted
ca
lc
u
latio
n
ele
m
e
n
ts
ca
lled
n
e
u
r
o
n
s
.
Ne
u
r
o
n
s
ad
ap
ted
f
r
o
m
b
io
lo
g
ic
al
n
e
u
r
al
n
et
w
o
r
k
s
y
s
te
m
s
h
av
e
"
f
o
u
lt
to
ler
an
t"
p
r
o
p
er
ties
m
ea
n
in
g
n
eu
r
o
n
s
c
an
r
ec
o
g
n
ize
i
n
p
u
t
s
i
g
n
a
ls
t
h
at
ar
e
s
o
m
e
w
h
at
d
i
f
f
er
en
t
f
r
o
m
th
o
s
e
ev
er
r
ec
ei
v
ed
an
d
if
a
n
eu
r
o
n
is
d
a
m
a
g
ed
,
o
th
er
n
e
u
r
o
n
s
ca
n
b
e
tr
ain
ed
to
r
ep
lace
th
e
f
u
n
ctio
n
o
f
t
h
e
d
am
a
g
ed
n
e
u
r
o
n
.
N
eu
r
al
n
et
w
o
r
k
i
s
a
p
r
o
g
r
am
m
ed
s
y
s
te
m
,
m
ea
n
in
g
th
a
t
all
o
u
tp
u
t
o
r
d
ec
is
io
n
tak
en
b
y
t
h
e
n
et
w
o
r
k
i
s
b
ased
o
n
ex
p
er
ien
ce
d
u
r
in
g
t
h
e
lear
n
in
g
p
r
o
ce
s
s
o
r
tr
ain
i
n
g
.
T
h
e
p
u
r
p
o
s
e
o
f
n
e
u
r
al
n
et
w
o
r
k
tr
ain
i
n
g
i
s
to
ac
h
ie
v
e
eq
u
alit
y
b
et
w
ee
n
th
e
ab
ilit
y
o
f
m
e
m
o
r
izat
io
n
an
d
g
e
n
er
ali
za
tio
n
.
T
h
e
ab
ilit
y
to
m
e
m
o
r
i
ze
is
th
e
ab
ilit
y
o
f
n
eu
r
al
n
et
w
o
r
k
s
to
r
ec
ap
tu
r
e
a
p
er
f
ec
tl
y
lear
n
ed
p
atter
n
,
w
h
i
le
g
e
n
er
aliza
tio
n
is
t
h
e
ab
ilit
y
o
f
n
e
u
r
al
n
et
w
o
r
k
s
to
p
r
o
v
id
e
ac
tio
n
o
r
r
esp
o
n
s
e
f
r
o
m
s
i
m
ilar
i
n
p
u
t
p
atter
n
s
(
s
lig
h
tl
y
d
i
f
f
er
en
t
p
a
tter
n
s
)
to
p
r
ev
io
u
s
l
y
r
ec
ei
v
ed
in
p
u
t
p
atter
n
s
(
1
2
)
.
T
h
e
w
a
y
o
f
lear
n
i
n
g
co
n
d
u
cted
b
y
t
h
e
n
eu
r
al
n
et
w
o
r
k
i
s
d
i
v
id
ed
in
to
t
w
o
,
n
a
m
e
l
y
s
u
p
er
v
i
s
ed
lear
n
i
n
g
an
d
u
n
s
u
p
er
v
is
ed
lear
n
i
n
g
.
T
h
e
w
a
y
s
u
p
er
v
is
ed
lear
n
i
n
g
is
s
u
p
er
v
is
ed
lear
n
in
g
s
o
th
at
t
h
e
ex
p
ec
ted
o
u
tp
u
ts
h
a
v
e
b
ee
n
p
r
ev
i
o
u
s
l
y
k
n
o
w
n
b
y
u
s
in
g
ex
i
s
tin
g
d
ata.
On
e
in
p
u
t
p
atter
n
will
b
e
ass
ig
n
ed
to
a
n
eu
r
o
n
i
n
t
h
e
in
p
u
t la
y
er
a
n
d
f
o
r
w
ar
d
ed
to
th
e
n
e
u
r
o
n
in
t
h
e
o
u
tp
u
t
la
y
er
.
T
h
e
n
e
u
r
o
n
s
in
t
h
e
o
u
tp
u
t
la
y
er
w
ill
g
en
er
ate
r
e
s
u
l
ts
a
n
d
ar
e
m
atc
h
ed
to
th
e
tar
g
et
o
u
tp
u
t
p
atte
r
n
.
I
f
t
h
er
e
i
s
a
d
i
f
f
er
en
ce
b
e
t
w
ee
n
t
h
e
lear
n
i
n
g
o
u
tco
m
es
w
it
h
t
h
e
tar
g
et
o
u
tp
u
t
p
atter
n
th
e
n
th
e
er
r
o
r
w
ill
ap
p
ea
r
.
I
f
th
e
er
r
o
r
o
b
tain
ed
i
s
to
o
lar
g
e,
f
u
r
th
er
lear
n
in
g
i
s
r
eq
u
ir
ed
.
E
x
tr
e
m
e
lear
n
in
g
m
ac
h
in
e
i
s
a
n
e
u
r
al
n
et
w
o
r
k
m
et
h
o
d
th
at
h
ad
a
co
n
ce
p
t
ab
o
u
t
u
s
ed
a
s
in
g
le
h
id
d
en
la
y
er
f
ee
d
f
o
r
w
a
r
d
n
et
w
o
r
k
(
1
3
)
.
So
m
e
o
f
n
e
u
r
al
n
et
w
o
r
k
alg
o
r
it
h
m
s
w
as
u
s
ed
in
class
i
f
icatio
n
ar
e
b
ac
k
p
r
o
p
o
g
atio
n
(
1
4
)
,
ex
tr
e
m
e
lear
n
i
n
g
m
ac
h
in
e
(
7
,
1
5
)
,
h
y
b
r
id
ex
tr
e
m
e
lear
n
in
g
m
ac
h
i
n
e
(
1
6
–
19)
,
an
d
ANFI
S
(
2
0
)
5.
NE
URA
L
N
E
T
WO
RK
T
h
er
e
is
a
d
ee
p
e
r
s
tu
d
y
o
f
t
h
e
n
eu
r
al
n
et
w
o
r
k
,
o
n
e
o
f
w
h
ic
h
is
t
h
e
f
ir
s
t
E
x
tr
e
m
e
L
ea
r
n
i
n
g
Ma
ch
i
n
e
p
er
f
o
r
m
ed
b
y
H
u
an
g
i
n
2
0
0
6
(
1
3
)
.
E
L
M
is
o
n
e
o
f
t
h
e
lear
n
in
g
m
et
h
o
d
s
in
Ne
u
r
al
Net
w
o
r
k
w
h
ic
h
h
a
s
th
e
co
n
ce
p
t
o
f
Sin
g
le
Hid
d
en
L
a
y
er
Feed
Fo
r
w
ar
d
.
E
L
M
w
as
c
r
ea
ted
w
ith
t
h
e
ai
m
to
o
v
er
co
m
e
th
e
w
ea
k
n
e
s
s
e
s
o
f
p
r
ev
io
u
s
Ne
u
r
al
Net
w
o
r
k
m
et
h
o
d
s
.
T
h
is
m
eth
o
d
h
a
s
a
v
er
y
f
a
s
t
co
m
p
u
ta
tio
n
co
n
ce
p
t
b
ec
au
s
e
it
o
n
l
y
p
er
f
o
r
m
s
o
n
e
iter
atio
n
p
r
o
ce
s
s
an
d
g
iv
e
s
b
etter
r
esu
lt
f
r
o
m
o
th
er
Neu
r
al
Net
w
o
r
k
m
et
h
o
d
(
1
5
)
.
B
o
b
o
t
in
p
u
t
p
ad
a
E
L
M
b
iasan
y
a
d
ite
n
t
u
k
an
s
ec
ar
a
ac
ak
,
s
ed
an
g
k
a
n
u
n
t
u
k
b
o
b
o
t
o
u
tp
u
t
d
iten
tu
k
an
s
ec
ar
a
an
aliti
k
s
eh
i
n
g
g
a
o
u
tp
u
t
p
ad
a
h
asil
E
L
M
h
a
n
y
a
s
atu
.
T
h
e
w
ei
g
h
t
in
p
u
ts
o
n
t
h
e
E
L
M
ar
e
u
s
u
all
y
d
eter
m
i
n
ed
r
an
d
o
m
l
y
,
w
h
er
ea
s
f
o
r
th
e
o
u
tp
u
t
w
ei
g
h
t
is
d
eter
m
i
n
ed
an
a
l
y
ticall
y
s
o
t
h
at
t
h
e
o
u
tp
u
t
o
n
th
e
E
L
M
r
esu
lt
i
s
o
n
l
y
o
n
e
(
2
1
)
.
I
n
th
e
E
L
M
u
s
es
t
w
o
t
y
p
es
o
f
d
ata,
n
a
m
el
y
tr
ai
n
i
n
g
d
ata
an
d
test
i
n
g
d
ata
(
1
3
)
.
T
h
e
tr
ain
in
g
d
ata
i
s
ai
m
ed
at
o
b
tai
n
i
n
g
th
e
b
est
i
n
p
u
t
w
ei
g
h
t
b
ased
o
n
th
e
b
est
a
cc
u
r
ac
y
r
e
s
u
l
ts
o
n
t
h
e
tr
ai
n
i
n
g
d
ata
u
s
ed
.
T
esti
n
g
d
ata
ai
m
s
to
tes
t
t
h
e
b
est
in
p
u
t
w
ei
g
h
ts
th
a
t
w
er
e
o
b
tain
ed
in
th
e
p
r
o
ce
s
s
o
f
te
s
ti
n
g
tr
ai
n
d
ata
b
y
u
s
i
n
g
test
d
ata.
T
o
ca
lcu
late
th
e
f
i
n
al
ac
c
u
r
ac
y
is
u
s
in
g
t
h
e
av
er
ag
e
b
et
w
ee
n
th
e
tr
ai
n
i
n
g
d
ata
an
d
th
e
test
i
n
g
d
ata.
Mo
d
el
o
f
E
L
M
ca
n
b
e
s
ee
n
i
n
F
ig
u
r
e
1
.
Fig
u
r
e
1
.
E
L
M
ar
ch
itect
u
r
e
m
o
d
el
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
25
02
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l
.
1
2
,
No
.
2
,
No
v
e
m
b
er
201
8
:
xx
–
xx
886
I
n
Fig
u
r
e
1
th
e
E
L
M
ar
ch
itec
tu
r
e
h
as
s
i
m
ilar
ities
as
t
h
e
ar
ch
itect
u
r
e
o
f
o
th
er
Neu
r
al
Net
w
o
r
k
s
th
a
t
u
s
e
t
h
e
co
n
ce
p
t
o
f
B
ac
k
p
r
o
p
o
g
atio
n
lear
n
in
g
.
T
h
e
d
if
f
e
r
e
n
c
e
b
et
w
ee
n
E
L
M
an
d
B
ac
k
p
r
o
p
o
g
atio
n
lear
n
i
n
g
i
s
o
n
w
e
ig
h
t c
alc
u
latio
n
a
n
d
E
L
M
u
s
es o
n
l
y
o
n
e
iter
atio
n
.
P
s
e
u
o
co
d
e
o
f
E
L
M
ca
n
b
e
s
ee
n
o
n
Fi
g
u
r
e
2
.
Fig
u
r
e
2
.
E
L
M
P
s
eu
d
o
co
d
e
(
1
3
)
T
h
e
p
r
o
ce
s
s
o
f
E
L
M
alg
o
r
it
h
m
ac
tu
a
ll
y
h
as
s
i
m
ilar
itie
s
w
i
th
t
h
e
co
n
ce
p
t
o
f
f
ee
d
f
o
r
w
ar
d
lear
n
in
g
.
T
h
e
d
if
f
er
en
ce
is
i
n
th
e
n
u
m
b
er
o
f
lay
er
s
u
s
ed
b
ec
au
s
e
E
L
M
u
s
es
s
i
n
g
le
la
y
er
.
I
n
th
e
te
s
t
o
f
tr
ain
in
g
d
ata
an
d
tes
ti
n
g
d
ata
u
s
i
n
g
t
h
e
s
a
m
e
al
g
o
r
ith
m
f
lo
w
.
T
h
e
d
if
f
er
en
ce
is
o
n
l
y
i
n
t
h
e
d
eter
m
i
n
atio
n
o
f
t
h
e
i
n
p
u
t
w
ei
g
h
ts
,
w
h
er
e
th
e
tes
t
o
f
tr
ain
i
n
g
d
ata
u
s
i
n
g
r
an
d
o
m
i
n
p
u
t
w
eig
h
t
s
,
w
h
ile
test
t
h
e
test
i
n
g
d
ata
u
s
in
g
th
e
b
est
i
n
p
u
t
w
ei
g
h
ts
i
n
t
h
e
tr
ain
i
n
g
d
ata
tes
tin
g
.
T
h
e
f
lo
w
c
h
ar
t o
f
E
L
M
al
g
o
r
ith
m
ca
n
b
e
s
ee
n
in
Fig
u
r
e
3
.
Fig
u
r
e
3
.
E
L
M
Flo
w
c
h
ar
t
6.
RE
SU
L
T
AND
DI
SCUS
SI
O
N
I
n
th
e
E
L
M
test
Neu
r
o
n
test
i
n
g
i
s
p
er
f
o
r
m
ed
to
s
ee
h
o
w
m
an
y
n
eu
r
o
n
s
ar
e
r
eq
u
ir
ed
in
th
e
E
L
M
p
r
o
ce
s
s
to
g
et
t
h
e
b
est
ac
c
u
r
ac
y
.
T
h
is
test
is
p
er
f
o
r
m
ed
f
r
o
m
1
to
2
5
.
T
h
e
f
o
llo
w
in
g
i
s
a
r
esu
lt
o
f
n
e
u
r
o
n
test
i
n
g
o
n
E
L
M
u
s
i
n
g
1
3
5
tr
ai
n
in
g
d
ata
an
d
3
1
test
d
ata.
Fig
u
r
e
4
s
h
o
w
s
t
h
e
r
esu
lts
o
f
n
e
u
r
o
n
test
i
n
g
.
Fig
u
r
e
4
.
Neu
r
o
n
test
i
n
g
0
50
100
1
3
5
7
9
11
13
15
17
19
21
23
25
A
c
c
ur
ac
y
A
m
o
un
t
o
f
N
e
ur
o
n
N
eur
on
Testi
ng
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
Ja
tr
o
p
h
a
C
u
r
ca
s
Dis
ea
s
e
I
d
en
tifi
ca
tio
n
W
ith
E
xtre
me
Lea
r
n
i
n
g
Ma
ch
in
e
(
Tr
ia
n
d
o
Ha
m
o
n
a
n
g
a
n
S
a
r
a
g
i
h
)
887
I
n
n
eu
r
o
n
test
i
n
g
,
t
h
e
b
est
n
e
u
r
o
n
s
ar
e
p
r
esen
t
in
1
9
n
eu
r
o
n
s
.
I
n
th
is
te
s
t
t
h
e
b
est
av
er
a
g
e
ac
cu
r
ac
y
i
s
6
0
.
6
1
an
d
th
e
b
est
ac
cu
r
ac
y
i
s
6
6
.
6
7
%.
T
o
o
m
u
c
h
n
e
u
r
o
n
s
t
h
at
u
s
ed
f
o
r
E
L
M
ca
n
af
f
ec
t
t
h
e
ti
m
e
p
r
o
ce
s
s
i
n
g
o
f
E
L
M,
b
u
t
s
m
all
a
m
o
u
n
t
o
f
n
eu
r
o
n
s
ca
n
af
f
ec
t
lo
w
ac
c
u
r
a
tio
n
to
id
en
ti
f
t
y
b
ec
au
s
e
n
e
u
r
o
n
s
i
n
i
n
p
u
t
la
y
er
i
s
m
o
r
e
t
h
a
n
n
e
u
r
o
n
s
i
n
h
id
d
en
l
a
y
er
.
P
r
ev
io
u
s
r
esear
c
h
h
a
s
b
ee
n
d
o
n
e
u
s
i
n
g
Fu
zz
y
Neu
r
al
Net
w
o
r
k
(
FNN)
a
n
d
F
u
zz
y
Neu
r
al
Net
w
o
r
k
-
Si
m
u
lated
An
n
ea
li
n
g
(
FNN
-
S
A
)
.
I
d
en
ti
f
icatio
n
o
f
J
atr
o
p
h
a
C
u
r
ca
s
b
y
FNN
u
s
ed
FIS
T
s
u
k
a
m
o
to
’
s
m
e
m
b
er
s
h
ip
f
u
n
ctio
n
o
n
J
atr
o
p
h
a
C
u
r
ca
s
s
y
m
p
to
m
s
a
n
d
d
is
ea
s
e.
FNN
-
S
A
u
s
ed
S
A
to
o
p
ti
m
ize
m
e
m
b
er
s
h
ip
f
u
n
ctio
n
o
f
J
atr
o
p
h
a
C
u
r
ca
s
s
y
m
p
to
m
s
an
d
d
is
ea
s
es.
B
as
ed
o
n
E
L
M
test
in
g
th
e
n
co
m
p
ar
ed
w
it
h
o
th
er
m
et
h
o
d
s
s
u
c
h
as F
NN,
FNN
-
S
A
a
n
d
B
ac
k
p
r
o
p
o
g
atio
n
ca
n
b
e
s
ee
n
i
n
T
ab
le
2
.
T
ab
le
2
.
T
es
t r
esu
lts
o
f
s
e
v
er
al
m
eth
o
d
s
M
e
t
h
o
d
B
e
st
A
v
e
r
a
g
e
A
c
c
u
r
a
c
y
B
e
st
M
a
x
A
c
c
u
r
a
c
y
F
N
N
(
5
)
1
1
,
2
%
3
0
%
F
N
N
-
S
A
(
7
)
1
9
.
5
%
3
2
.
5
%
B
a
c
k
p
r
o
p
o
g
a
t
i
o
n
9
,
1
%
1
2
,
1
2
%
EL
M
6
0
,
6
1
%
6
6
,
6
7
%
W
e
u
s
e
1
0
ex
p
er
im
e
n
ts
u
s
i
n
g
th
e
b
est
p
ar
a
m
eter
s
i
n
ea
c
h
m
et
h
o
d
.
B
ased
o
n
co
m
p
ar
ativ
e
r
esu
lts
w
it
h
p
r
ev
io
u
s
l
y
ap
p
lied
m
et
h
o
d
s
,
E
L
M
h
as
m
u
c
h
b
etter
a
cc
u
r
ac
y
r
es
u
lt
s
co
m
p
ar
ed
w
ith
t
h
e
p
r
ev
io
u
s
m
et
h
o
d
.
E
L
M
ca
n
g
i
v
e
b
es
t
ac
c
u
r
ac
y
th
a
n
o
t
h
er
m
et
h
o
d
b
ec
au
s
e
E
L
M
d
eter
m
i
n
ed
t
h
e
w
e
ig
h
ts
b
et
w
ee
n
h
id
d
en
n
eu
r
o
n
s
a
n
d
t
h
e
o
u
tp
u
t
o
f
n
e
u
r
o
n
s
f
r
o
m
a
s
i
n
g
le
h
id
d
en
l
a
y
er
a
n
al
y
ticall
y
.
T
h
is
p
r
o
v
es
th
at
E
L
M
i
s
g
o
o
d
en
o
u
g
h
f
o
r
th
e
id
en
t
if
icatio
n
o
f
j
atr
o
p
h
a
cu
r
ca
s
d
is
ea
s
es c
o
m
p
ar
ed
to
p
r
ev
io
u
s
m
et
h
o
d
s
7.
CO
NCLU
SI
O
N
T
h
e
u
s
e
o
f
t
h
e
E
L
M
m
et
h
o
d
p
r
o
v
id
es
a
m
a
x
i
m
u
m
ac
c
u
r
ac
y
o
f
6
6
.
6
7
%
an
d
an
a
v
er
ag
e
a
cc
u
r
ac
y
o
f
6
0
.
6
1
%.
T
h
ese
r
esu
lts
p
r
o
v
e
th
at
E
L
M
is
b
etter
t
h
a
n
th
e
p
r
ev
io
u
s
co
m
p
ar
i
s
o
n
m
et
h
o
d
f
o
r
id
en
tif
icatio
n
o
f
r
ar
e
f
en
ce
d
is
ea
s
e.
A
cc
u
r
ac
y
r
esu
lt
s
t
h
at
ar
e
s
t
ill
b
elo
w
7
0
%
p
r
o
v
e
s
til
l
n
ee
d
f
u
r
th
er
d
e
v
elo
p
m
e
n
t
f
o
r
th
i
s
E
L
M
m
et
h
o
d
.
Mo
d
if
y
in
g
th
e
E
L
M
u
s
i
n
g
o
th
er
m
et
h
o
d
s
s
u
ch
as
Neu
r
al
Net
w
o
r
k
Ot
h
e
r
m
et
h
o
d
s
o
r
w
it
h
o
p
tim
izatio
n
m
et
h
o
d
s
is
ex
p
ec
ted
to
p
r
o
v
id
e
b
etter
r
esu
lts
t
h
an
ev
er
b
ef
o
r
e.
RE
F
E
R
E
NC
E
S
[1
]
.
Yu
li
a
n
ti
T
,
Hid
a
y
a
h
N.
"
J
a
tro
p
h
a
Cu
rc
a
s
Dise
a
se
"
.
M
a
la
n
g
:
Ba
l
a
i
Pen
e
li
ti
a
n
T
a
n
a
ma
n
Pem
a
n
is
d
a
n
S
e
ra
t
;
2
0
1
5
.
217
-
2
3
2
p
.
[2
]
.
Ak
b
a
r
E,
Ya
a
k
o
b
Z,
Ka
m
a
ru
d
in
S
K,
Ism
a
il
M
,
S
a
li
m
o
n
J.
"
Ch
a
ra
c
teristic
a
n
d
Co
m
p
o
siti
o
n
o
f
Ja
tro
p
h
a
C
u
rc
a
s
Oil
S
e
e
d
f
ro
m
M
a
la
y
sia
a
n
d
it
s
P
o
te
n
ti
a
l
a
s Bio
d
ies
e
l
F
e
e
d
st
o
c
k
F
e
e
d
sto
c
k
"
.
Eu
r J S
c
i
Res
.
2
0
0
9
;
2
9
(
3
):3
9
6
–
4
0
3
.
[3
]
.
G
b
it
z
G
.
"
Ex
p
lo
it
a
ti
o
n
o
f
th
e
tr
o
p
ica
l
o
il
se
e
d
p
lan
t
Ja
t
r
o
p
h
a
c
u
rc
a
s L
"
.
Bi
o
re
so
u
r T
e
c
h
n
o
l
.
1
9
9
9
Ja
n
;
6
7
(
1
):7
3
–
8
2
.
[4
]
.
D
y
m
o
v
a
L
,
S
e
v
a
stjan
o
v
P
,
Ka
c
z
m
a
re
k
K.
"
A
F
o
re
x
trad
in
g
e
x
p
e
rt
sy
st
e
m
b
a
se
d
o
n
a
n
e
w
a
p
p
ro
a
c
h
to
th
e
r
u
le
-
b
a
se
e
v
id
e
n
ti
a
l
re
a
so
n
in
g
"
.
Exp
e
rt
S
y
st A
p
p
l
.
2
0
1
6
;
5
1
:
1
–
1
3
.
[5
]
.
S
a
ra
g
ih
T
H,
F
a
jri
DMN,
H
a
m
d
ian
a
h
A
,
M
a
h
m
u
d
y
W
F
,
A
n
g
g
o
d
o
Y
P
.
"
Ja
tro
p
h
a
Cu
rc
a
s
Dise
a
s
e
Id
e
n
ti
f
ica
ti
o
n
Us
in
g
F
u
z
z
y
N
e
u
ra
l
Ne
tw
o
rk
"
.
In
:
I
n
ter
n
a
t
io
n
a
l
Co
n
fer
e
n
c
e
o
n
S
u
st
a
in
a
b
le
I
n
f
o
rm
a
ti
o
n
E
n
g
in
e
e
rin
g
a
n
d
T
e
c
h
n
o
l
o
g
y
(
S
IET
)
,
Ba
tu
,
In
d
o
n
e
sia
,
2
5
-
2
5
No
v
e
m
b
e
r.
2
0
1
7
.
[6
]
.
F
a
jri
DMN,
S
a
ra
g
ih
T
H,
Ha
m
d
i
a
n
a
h
A
,
M
a
h
m
u
d
y
W
F
,
A
n
g
g
o
d
o
Y
P
.
"
Op
ti
m
ize
d
F
u
z
z
y
Ne
u
r
a
l
Ne
t
w
o
rk
f
o
r
Ja
tro
p
h
a
Cu
rc
a
s
P
la
n
t
Dise
a
se
Id
e
n
ti
f
ica
ti
o
n
"
.
In
:
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
S
u
sta
i
n
a
b
l
e
In
fo
rm
a
ti
o
n
En
g
i
n
e
e
rin
g
a
n
d
T
e
c
h
n
o
lo
g
y
(
S
IET
)
,
Ba
tu
,
In
d
o
n
e
sia
,
2
5
-
2
5
No
v
e
m
b
e
r.
2
0
1
7
.
[7
]
.
Ra
h
m
a
ON
,
W
ij
a
y
a
S
K,
P
ra
w
it
o
,
Ba
d
ri
C.
"
El
e
c
tro
e
n
c
e
p
h
a
lo
g
ra
m
a
n
a
l
y
sis
w
it
h
e
x
tre
m
e
lea
rn
in
g
m
a
c
h
in
e
a
s
a
su
p
p
o
rti
n
g
to
o
l
f
o
r
c
las
sify
in
g
a
c
u
te
isc
h
e
m
ic
stro
k
e
s
e
v
e
rit
y
"
.
In
:
2
0
1
7
In
ter
n
a
ti
o
n
a
l
S
e
min
a
r
o
n
S
e
n
s
o
rs
,
In
stru
me
n
ta
ti
o
n
,
M
e
a
su
re
me
n
t
a
n
d
M
e
tro
lo
g
y
(
IS
S
IM
M
).
IEE
E
;
2
0
1
7
.
p
.
1
8
0
–
6
.
[8
]
.
P
a
d
il
la
D,
M
o
n
terro
s
o
D.
"
P
re
li
m
in
in
a
r
y
d
i
ff
e
re
n
ti
a
ti
o
n
o
f
d
ise
a
se
in
th
e
te
m
p
e
ra
tu
re
(Ja
tro
p
h
a
Cu
sc
a
s)
c
ro
p
in
Nic
a
ra
g
u
a
"
.
M
a
n
a
jo
In
te
g
r P
la
g
a
s
.
1
9
9
9
;
5
1
:6
6
–
9
.
[9
]
.
S
in
g
h
N,
Ha
rsh
NS.
,
Bh
a
rg
a
v
a
A
.
"
Bio
d
e
terio
Ra
ti
o
n
o
f
Ja
tro
p
h
a
C
u
sc
a
s S
e
e
d
s"
.
An
n
F
o
r
.
1
9
9
6
;
4
:5
2
–
4
.
[1
0
]
.
Jin
Y.
"
A
d
v
a
n
c
e
d
F
u
z
z
y
S
y
ste
m
s
De
sig
n
a
n
d
A
p
p
li
c
a
ti
o
n
s"
.
Ne
w
Y
o
rk
:
Ph
y
sic
a
-
Ver
la
g
He
id
e
l
b
e
rg
;
2
0
0
3
.
[1
1
]
.
L
ip
p
m
a
n
n
RP
.
"
A
n
In
tro
d
u
c
ti
o
n
t
o
Co
m
p
u
ti
n
g
w
it
h
Ne
u
ra
l
Ne
ts"
.
IEE
E
AS
S
P
M
a
g
.
1
9
8
7
;4
(
2
):4
–
2
2
.
[1
2
]
.
Hu
rtad
o
C,
L
u
is
J,
F
re
g
o
so
C,
H
e
c
to
r
J.
"
F
o
re
c
a
stin
g
M
e
x
ic
a
n
in
f
latio
n
u
sin
g
n
e
u
ra
l
n
e
tw
o
rk
s"
.
In
:
El
e
c
tro
n
ics
,
Co
mm
u
n
ica
ti
o
n
s a
n
d
Co
mp
u
ti
n
g
(
CONIEL
ECOM
P).
IEE
E
;
2
0
1
3
.
p
.
3
2
–
3
5
.
[1
3
]
.
Hu
a
n
g
G
Bin
,
Zh
u
QY
,
S
iew
CK.
"
Ex
tre
m
e
le
a
rn
in
g
m
a
c
h
in
e
:
T
h
e
o
r
y
a
n
d
a
p
p
l
ica
ti
o
n
s"
.
N
e
u
ro
c
o
mp
u
ti
n
g
.
2
0
0
6
;
7
0
(
1
–
3
):4
8
9
–
5
0
1
.
[1
4
]
.
W
a
n
g
S
,
A
rc
h
e
r
NP
.
"
A
n
e
u
ra
l
n
e
tw
o
rk
b
a
se
d
f
u
z
z
y
se
t
m
o
d
e
l
fo
r
o
rg
a
n
iza
ti
o
n
a
l
d
e
c
isio
n
m
a
k
in
g
"
.
IEE
E
T
ra
n
s
S
y
st M
a
n
Cy
b
e
rn
Pa
rt
C
(
Ap
p
li
c
a
ti
o
n
s
Rev
.
1
9
9
8
M
a
y
;2
8
(2
):
1
9
4
–
2
0
3
.
[1
5
]
.
T
a
n
g
J,
De
n
g
C,
G
u
a
n
g
-
Bin
H.
"
Ex
tre
m
e
Lea
rn
in
g
M
a
c
h
in
e
f
o
r
M
u
lt
il
a
y
e
r
P
e
rc
e
p
tro
n
"
.
IEE
E
T
ra
n
s
Ne
u
r
a
l
Ne
two
rk
s L
e
a
rn
S
y
st
.
2
0
1
6
;2
7
(4
):
8
0
9
–
2
1
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
25
02
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l
.
1
2
,
No
.
2
,
No
v
e
m
b
er
201
8
:
xx
–
xx
888
[1
6
]
.
Al
-
Ya
se
e
n
WL
,
Oth
m
a
n
ZA
,
Na
z
ri
M
ZA
.
"
M
u
lt
i
-
lev
e
l
h
y
b
rid
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
a
n
d
e
x
t
re
m
e
lea
rn
in
g
m
a
c
h
in
e
b
a
se
d
o
n
m
o
d
if
ied
K
-
m
e
a
n
s
f
o
r
in
tru
sio
n
d
e
tec
ti
o
n
sy
st
e
m
"
.
Exp
e
rt
S
y
st
Ap
p
l
[
In
ter
n
e
t
]
.
2
0
1
7
;6
7
:2
9
6
–
3
0
3
.
A
v
a
il
a
b
le f
ro
m
:
h
tt
p
:/
/
d
x
.
d
o
i
.
o
rg
/1
0
.
1
0
1
6
/j
.
e
sw
a
.
2
0
1
6
.
0
9
.
0
4
1
[1
7
]
.
Yo
o
n
H,
P
a
rk
CS
,
Kim
JS,
Ba
e
k
JG
.
"
A
lg
o
rit
h
m
l
e
a
rn
in
g
b
a
se
d
n
e
u
ra
l
n
e
tw
o
rk
in
teg
ra
ti
n
g
fe
a
tu
re
se
lec
ti
o
n
a
n
d
c
las
si
f
ica
ti
o
n
"
.
Exp
e
rt
S
y
st
Ap
p
l
[
In
ter
n
e
t
]
.
2
0
1
3
;4
0
(1
)
:2
3
1
–
4
1
.
Av
a
il
a
b
le
f
ro
m
:
h
tt
p
:
//
d
x
.
d
o
i.
o
rg
/1
0
.
1
0
1
6
/j
.
e
sw
a
.
2
0
1
2
.
0
7
.
0
1
8
[1
8
]
.
G
u
o
P
,
Ch
e
n
g
W
,
Wan
g
Y.
"
H
y
b
rid
e
v
o
lu
ti
o
n
a
ry
a
lg
o
rit
h
m
w
it
h
e
x
tre
m
e
m
a
c
h
in
e
lea
rn
in
g
f
it
n
e
ss
f
u
n
c
ti
o
n
e
v
a
lu
a
ti
o
n
f
o
r
t
w
o
-
sta
g
e
c
a
p
a
c
it
a
ted
fa
c
il
it
y
lo
c
a
ti
o
n
p
ro
b
lem
s"
.
Exp
e
rt
S
y
st
Ap
p
l
[
In
ter
n
e
t
]
.
2
0
1
7
;7
1
:5
7
–
6
8
.
Av
a
il
a
b
le f
ro
m
:
h
tt
p
:/
/
d
x
.
d
o
i
.
o
rg
/
1
0
.
1
0
1
6
/
j.
e
sw
a
.
2
0
1
6
.
1
1
.
0
2
5
[1
9
]
.
Zh
a
n
g
Z.
"
E
ff
icie
n
t
Co
m
p
u
ter
I
n
tru
si
o
n
De
tec
ti
o
n
M
e
th
o
d
Ba
se
d
o
n
A
rti
f
ici
a
l
Be
e
Co
lo
n
y
Op
t
im
iz
e
d
Ke
rn
e
l
Ex
tre
m
e
L
e
a
rn
in
g
M
a
c
h
in
e
"
.
2
0
1
4
;1
2
(3
):
1
9
5
4
–
9
.
[2
0
]
.
Be
ll
a
li
B,
Ha
z
z
a
b
A
,
Bo
u
ss
e
rh
a
n
e
IK,
Ie
f
e
b
v
re
D.
"
A
De
c
o
u
p
led
P
a
ra
m
e
ters
Esti
m
a
to
rs
f
o
r
in
No
n
li
n
e
a
r
S
y
ste
m
s
F
a
u
lt
d
iag
n
o
sis
b
y
A
NFIS
"
.
In
t
J
El
e
c
tr
Co
mp
u
t
En
g
[
In
ter
n
e
t
]
.
2
0
1
1
;
2
(2
):
1
6
6
–
7
4
.
A
v
a
il
a
b
le
f
ro
m
:
h
tt
p
:
//
iae
sjo
u
r
n
a
l.
c
o
m
/o
n
li
n
e
/i
n
d
e
x
.
p
h
p
/IJEC
E/
a
rti
c
le/v
iew
/2
2
1
[2
1
]
.
X
u
S
,
W
a
n
g
J.
"
A
fa
st
in
c
re
m
e
n
tal
e
x
tre
m
e
lea
rn
in
g
m
a
c
h
in
e
a
lg
o
rit
h
m
f
o
r
d
a
ta
stre
a
m
s
c
las
si
f
ic
a
ti
o
n
"
.
Exp
e
rt
S
y
st
Ap
p
l
[
In
ter
n
e
t
]
.
2
0
1
6
;
6
5
:3
3
2
–
4
4
.
Av
a
il
a
b
le f
ro
m
:
h
tt
p
:/
/
d
x
.
d
o
i
.
o
rg
/
1
0
.
1
0
1
6
/
j.
e
sw
a
.
2
0
1
6
.
0
8
.
0
5
2
Evaluation Warning : The document was created with Spire.PDF for Python.