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.
22
,
No
.
3
,
J
u
n
e
2
0
2
1
,
p
p
.
1635
~
1
6
4
2
I
SS
N:
2
5
02
-
4
7
5
2
,
DOI
: 1
0
.
1
1
5
9
1
/i
j
ee
cs.v
2
2
.i
3
.
p
p
1
6
3
5
-
1
6
4
2
1635
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs.ia
esco
r
e.
co
m
I
m
ple
m
e
ntatio
n
m
ul
tiple
linea
r re
g
resio
n in neural
netw
o
rk
predict
go
ld price
M
us
li Ya
nto
1
,
Sig
it
Sa
nja
y
a
2
,
Yula
s
m
i
3
,
Do
di
G
u
s
w
a
nd
i
4
,
Sy
a
f
ri
Arlis
5
1,
4,
5
De
p
a
rtm
e
n
t
o
f
In
f
o
rm
a
ti
c
s
En
g
in
e
e
rin
g
,
F
a
c
u
lt
y
o
f
Co
m
p
u
ter S
c
ien
c
e
,
Un
iv
e
rsitas
P
u
tra In
d
o
n
e
sia
YP
T
K,
In
d
o
n
e
sia
2,
3
De
p
a
rtm
e
n
t
o
f
M
a
n
a
g
e
m
e
n
t,
F
a
c
u
lt
y
o
f
Eco
n
o
m
ic an
d
Bu
sin
e
ss
,
Un
iv
e
rsitas
P
u
tra In
d
o
n
e
sia
YP
T
K,
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
Feb
1
6
,
2
0
2
1
R
ev
i
s
ed
Ma
y
2
,
2
0
2
1
A
cc
ep
ted
Ma
y
5
,
2
0
2
1
T
h
e
m
o
v
e
m
e
n
t
o
f
g
o
ld
p
rice
s in
t
h
e
p
re
v
io
u
s
p
e
rio
d
w
a
s c
ru
c
ial
f
o
r
in
v
e
sto
rs.
Ho
w
e
v
e
r,
f
lu
c
tu
a
ti
o
n
s
in
g
o
l
d
p
r
ice
m
o
v
e
m
e
n
ts
a
lw
a
y
s
o
c
c
u
r.
T
h
e
p
ro
b
lem
in
t
h
is
st
u
d
y
is
h
o
w
to
a
p
p
ly
m
u
lt
ip
le
li
n
e
a
r
re
g
re
ss
io
n
(M
RL
)
i
n
p
re
d
ictin
g
a
rti
f
icia
l
n
e
u
ra
l
n
e
tw
o
rk
s
(AN
N)
o
f
g
o
ld
p
rice
s.
M
RL
is
m
a
th
e
m
a
ti
c
a
l
c
a
lcu
latio
n
tec
h
n
i
q
u
e
u
se
d
to
m
e
a
su
re
th
e
c
o
rre
lati
o
n
b
e
tw
e
e
n
v
a
riab
les
.
T
h
e
re
su
lt
s
o
f
th
e
M
RL
a
n
a
ly
sis
e
n
s
u
re
th
a
t
t
h
e
n
e
tw
o
rk
p
a
tt
e
rn
th
a
t
is
f
o
rm
e
d
c
a
n
p
ro
v
id
e
p
re
c
ise
a
n
d
a
c
c
u
ra
te
p
re
d
ictio
n
re
su
lt
s.
In
a
d
d
it
i
o
n
,
th
is
stu
d
y
a
ims
to
d
e
v
e
lo
p
a
p
re
d
ictiv
e
p
a
tt
e
rn
m
o
d
e
l
t
h
a
t
a
lrea
d
y
e
x
ists.
T
h
e
re
su
lt
s
o
f
th
e
c
o
rre
latio
n
tes
t
o
b
tain
e
d
b
y
M
RL
p
ro
v
id
e
a
c
o
rre
latio
n
o
f
6
2
%
so
th
a
t
t
h
e
tes
t
re
su
lt
s
a
re
sa
i
d
t
o
h
a
v
e
a
si
g
n
if
ica
n
t
e
ff
e
c
t
o
n
g
o
ld
p
rice
m
o
v
e
m
e
n
ts.
T
h
e
n
th
e
p
re
d
ictio
n
re
su
l
ts
g
e
n
e
ra
ted
u
sin
g
a
n
A
NN
h
a
s
a
m
e
a
n
sq
u
a
re
d
e
rro
r
(M
S
E)
v
a
lu
e
o
f
0
.
0
0
4
2
6
4
%
.
T
h
e
b
e
n
e
f
it
s
o
b
tain
e
d
i
n
th
is
stu
d
y
p
ro
v
id
e
a
n
o
v
e
rv
ie
w
o
f
th
e
g
o
ld
p
rice
p
re
d
icti
o
n
p
a
tt
e
rn
m
o
d
e
l
b
y
c
o
n
d
u
c
ti
n
g
lea
rn
i
n
g
a
n
d
a
p
p
r
o
a
c
h
e
s
in
tes
ti
n
g
th
e
a
c
c
u
ra
c
y
o
f
th
e
u
se
o
f
p
re
d
ict
o
r
v
a
riab
les
.
K
ey
w
o
r
d
s
:
A
r
ti
f
icial
n
e
u
r
al
n
et
w
o
r
k
s
B
ac
k
p
r
o
p
ag
atio
n
Go
ld
p
r
ices
Mu
ltip
le
li
n
ea
r
r
eg
r
ess
io
n
P
r
ed
ictio
n
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Mu
s
l
i Y
an
to
Dep
ar
t
m
en
t o
f
I
n
f
o
r
m
atic
s
E
n
g
in
ee
r
i
n
g
Un
i
v
er
s
ita
s
P
u
tr
a
I
n
d
o
n
esia Y
PT
K
P
ad
an
g
2
5
1
4
5
,
I
n
d
o
n
esia
E
m
ail:
m
u
s
li_
y
an
to
@
u
p
i
y
p
tk
.
ac
.
id
1.
I
NT
RO
D
UCT
I
O
N
Go
ld
is
a
co
m
m
o
d
it
y
t
h
at
i
s
m
o
s
t
in
d
e
m
a
n
d
b
y
i
n
v
esto
r
s
f
o
r
in
v
es
tin
g
.
B
esid
es,
g
o
ld
h
as
also
b
ee
n
co
n
s
id
er
ed
as
a
m
ea
n
s
o
f
i
n
v
est
m
e
n
t
an
d
ca
n
b
e
u
s
ed
as
th
e
m
o
s
t
ap
p
r
o
p
r
iate
in
s
tr
u
m
en
t
f
o
r
p
eo
p
le
to
in
v
e
s
t
[
1
]
.
T
h
e
p
r
o
b
lem
th
at
o
f
ten
ar
is
e
s
w
h
e
n
i
n
v
e
s
ti
n
g
i
s
h
o
w
in
v
esto
r
s
p
r
ec
is
e
i
n
m
ak
in
g
d
ec
is
io
n
s
to
d
eter
m
in
e
w
h
e
n
is
th
e
r
i
g
h
t
ti
m
e
to
i
n
v
e
s
t
i
n
g
o
ld
b
ased
o
n
th
e
p
r
ice
th
at
o
cc
u
r
s
i
n
t
h
e
n
ex
t
f
u
t
u
r
e.
T
o
s
o
lv
e
th
is
p
r
o
b
le
m
,
w
e
n
ee
d
a
s
y
s
t
e
m
th
a
t
ca
n
ca
r
r
y
o
u
t
a
p
r
ed
ictiv
e
an
a
l
y
s
is
p
r
o
ce
s
s
to
o
b
s
er
v
e
th
e
g
o
ld
p
r
ice
m
o
v
e
m
e
n
ts
t
h
at
w
i
ll
o
cc
u
r
[
2
]
.
T
h
e
r
esu
lts
o
f
th
is
p
r
o
ce
s
s
ca
n
p
r
o
v
id
e
an
o
v
er
v
ie
w
o
f
th
e
g
o
ld
p
r
ic
e
f
l
u
ctu
a
tio
n
s
t
h
at
w
i
ll o
cc
u
r
an
d
ar
e
ex
p
ec
ted
to
b
e
u
s
ed
as a
r
ef
er
en
ce
f
o
r
i
n
v
e
s
t
m
en
t i
n
ter
ests
[
3
]
.
T
h
e
f
o
r
ec
asti
n
g
p
r
o
ce
s
s
h
a
s
d
ev
elo
p
ed
a
lo
t
a
m
o
n
g
r
e
s
ea
r
ch
er
s
,
esp
ec
iall
y
d
i
s
cu
s
s
i
n
g
t
h
e
to
p
ic
o
f
th
e
g
o
ld
p
r
ice.
On
e
ap
p
r
o
ac
h
th
at
h
a
s
b
ee
n
w
id
el
y
u
s
ed
is
t
h
e
ar
tif
icial
n
e
u
r
al
n
e
t
w
o
r
k
(
ANN)
.
T
h
is
ap
p
r
o
ac
h
is
an
in
ter
p
r
etatio
n
o
f
th
e
w
o
r
k
in
g
p
ictu
r
e
o
f
th
e
h
u
m
a
n
b
io
lo
g
ical
s
y
s
te
m
w
h
ich
ca
n
ca
r
r
y
o
u
t
s
y
s
te
m
ati
c
ca
lcu
latio
n
s
b
ased
o
n
ex
p
er
ien
ce
.
B
ased
o
n
th
e
r
esear
ch
th
at
h
as
b
ee
n
d
o
n
e
in
p
r
ed
ictin
g
g
o
ld
p
r
ices
u
s
in
g
A
N
N,
it
ca
n
p
r
o
v
id
e
o
u
tp
u
t
w
it
h
g
o
o
d
ac
cu
r
ac
y
,
s
o
th
a
t
it
ca
n
b
e
tak
e
n
i
n
to
co
n
s
i
d
er
atio
n
as
w
e
ll
as
i
m
p
o
r
tan
t
i
n
d
icato
r
s
o
f
th
e
ec
o
n
o
m
ic
s
ec
to
r
s
o
f
v
ar
io
u
s
co
m
p
a
n
ie
s
[
4
]
.
Fro
m
th
e
r
es
u
lts
o
f
o
th
er
p
r
ed
ictio
n
p
r
o
ce
s
s
es,
A
N
N
ca
n
p
r
o
d
u
ce
m
ax
i
m
u
m
r
es
u
lts
in
m
a
k
in
g
p
r
ed
ictio
n
s
w
ith
a
f
air
l
y
lo
w
p
er
ce
n
tag
e
o
f
er
r
o
r
v
alu
e
s
[
5
]
,
[
6
]
.
T
h
e
s
a
m
e
r
es
ea
r
ch
s
tates
t
h
at
A
NN
i
s
f
a
s
t
er
an
d
h
as
a
h
i
g
h
d
eg
r
ee
o
f
ac
cu
r
ac
y
i
n
m
a
k
i
n
g
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
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
22
,
No
.
3
,
J
u
n
e
2
0
2
1
:
1
6
3
5
-
1
6
4
2
1636
p
r
ed
ictio
n
s
[
7
]
,
[
8
]
.
So
th
at
A
N
N
is
i
n
s
id
e
[
9
]
,
s
tates
t
h
a
t
th
e
m
o
d
el
d
escr
ib
es
a
s
y
s
te
m
atic
m
o
d
el
in
th
e
lear
n
in
g
p
r
o
ce
s
s
f
r
o
m
in
p
u
t
a
n
d
o
u
tp
u
t
[
1
0
]
.
I
n
th
e
p
r
ed
ict
io
n
ca
s
e,
t
h
e
A
N
N
m
o
d
el
ca
n
b
e
d
ev
elo
p
ed
to
p
r
o
d
u
ce
o
p
ti
m
al
p
r
ed
ictiv
e
r
esu
lt
s
b
ased
o
n
p
er
f
o
r
m
a
n
ce
w
h
ich
i
s
in
f
l
u
en
ce
d
b
y
t
h
e
am
o
u
n
t
o
f
d
ata
u
s
ed
[
1
1
]
.
T
h
is
in
d
icate
s
th
at
ANN
ca
n
b
e
u
s
ed
to
p
r
ed
ict
b
ased
o
n
th
e
u
s
e
o
f
e
x
p
er
i
m
en
tal
d
ata
to
o
b
tai
n
f
air
l
y
g
o
o
d
p
r
ed
ictiv
e
r
esu
lts
[
1
2
]
.
B
ased
o
n
th
e
ex
is
ti
n
g
ex
p
lan
atio
n
s
,
th
e
s
tu
d
y
i
n
th
e
d
is
c
u
s
s
io
n
s
til
l
o
n
l
y
f
o
cu
s
es
o
n
th
e
p
r
ed
ictiv
e
o
u
tp
u
t
w
i
th
o
u
t
e
v
er
p
a
y
i
n
g
at
ten
tio
n
to
th
e
p
r
ed
icto
r
v
ar
iab
les
u
s
ed
.
T
h
er
ef
o
r
e,
th
is
r
esea
r
ch
d
is
c
u
s
s
io
n
w
i
ll
also
d
is
cu
s
s
th
e
g
o
ld
p
r
ice
p
r
e
d
ictio
n
p
r
o
ce
s
s
b
y
i
m
p
le
m
e
n
ti
n
g
m
u
ltip
le
lin
ea
r
r
eg
r
es
s
io
n
(
MR
L
)
in
A
NN.
I
n
th
is
ca
s
e,
t
h
e
n
o
v
e
lt
y
o
f
p
r
ev
i
o
u
s
r
esear
c
h
i
s
t
h
at
t
h
e
i
m
p
le
m
en
tatio
n
o
f
M
R
L
ca
n
b
e
e
x
p
ec
ted
to
m
ea
s
u
r
e
t
h
e
lev
el
o
f
co
r
r
elatio
n
b
et
w
ee
n
th
e
p
r
ed
icto
r
v
ar
iab
les
an
d
th
e
p
r
ed
icted
o
u
tp
u
t.
T
o
p
r
o
v
e
th
e
r
elat
io
n
s
h
ip
b
et
w
ee
n
v
ar
iab
le
s
i
n
th
e
p
r
ed
ictio
n
r
es
u
lts
,
M
R
L
i
s
co
n
s
id
er
ed
th
e
m
o
s
t
f
ea
s
ib
le
to
o
b
s
er
v
e
th
i
s
r
elatio
n
s
h
ip
.
I
n
p
r
ev
io
u
s
s
t
u
d
ies,
it
h
a
s
also
b
ee
n
ex
p
lain
ed
th
at
MR
L
ca
n
s
h
o
w
a
r
elatio
n
s
h
ip
b
et
w
ee
n
p
r
ed
icto
r
s
.
MRL
is
also
ca
lled
o
n
e
o
f
t
h
e
m
ea
s
u
r
in
g
to
o
ls
to
test
th
e
r
elati
o
n
s
h
ip
b
et
w
ee
n
t
h
e
d
ep
en
d
en
t
v
ar
iab
le
a
n
d
th
e
in
d
ep
en
d
en
t
v
ar
iab
le.
I
n
itiall
y
,
it
ca
n
b
e
s
ee
n
t
h
at
M
R
L
ca
n
b
e
u
s
ed
in
a
p
r
ed
ictio
n
m
o
d
e
l
th
at
i
s
ca
r
r
ied
o
u
t
in
th
e
ca
s
e
o
f
p
r
ed
ictin
g
f
u
t
u
r
e
g
o
ld
p
r
ices.
Su
ch
a
m
o
d
el
is
k
n
o
w
n
as
"
f
o
r
ec
ast
-
1
"
an
d
is
co
n
s
id
er
ed
a
b
en
ch
m
ar
k
m
o
d
el
ca
p
ab
le
o
f
ev
alu
a
tin
g
m
o
d
el
p
er
f
o
r
m
an
ce
[
1
3
]
.
Sev
er
al
o
th
er
s
t
u
d
ies
h
a
v
e
als
o
s
tated
th
at
MR
L
ca
n
ca
r
r
y
o
u
t
th
e
p
r
o
ce
s
s
o
f
an
al
y
zi
n
g
f
ac
to
r
s
th
at
af
f
ec
t
ch
a
n
g
e
s
in
t
h
e
p
r
ice
o
f
g
o
ld
in
th
e
f
u
t
u
r
e
[
1
4
]
.
I
n
p
a
r
allel
r
esear
ch
also
ca
r
r
ied
o
u
t
in
th
e
p
r
o
ce
s
s
o
f
p
r
ed
ictin
g
elec
tr
ici
t
y
p
r
ices,
s
t
atin
g
t
h
at
t
h
e
M
R
L
m
et
h
o
d
ca
n
a
n
al
y
ze
v
ar
iab
les
th
a
t
ca
n
af
f
ec
t
t
h
e
p
r
ed
icted
o
u
tp
u
t
r
esu
l
ts
[
1
5
]
.
Fo
r
th
is
r
e
aso
n
,
MR
L
ca
n
tak
e
a
s
tatis
t
ic
al
ap
p
r
o
ac
h
b
y
lo
o
k
in
g
at
th
e
r
elatio
n
s
h
ip
o
f
th
e
v
ar
iab
les u
s
ed
in
i
n
f
lu
e
n
ci
n
g
t
h
e
o
u
tp
u
t
[
1
6
]
.
T
h
e
MRL
ap
p
r
o
ac
h
w
il
l
b
e
ab
le
to
p
r
o
v
id
e
th
e
r
ig
h
t
p
r
ed
icto
r
v
ar
iab
le
s
b
ased
o
n
th
e
r
esu
lts
o
f
th
e
co
r
r
elatio
n
test
s
o
th
at
th
e
p
r
ed
ictio
n
p
r
o
ce
s
s
th
at
w
ill
b
e
ca
r
r
ied
o
u
t
w
i
th
A
NN
i
s
ex
p
ec
ted
to
g
iv
e
m
u
ch
b
etter
r
esu
lts
th
a
n
t
h
e
p
r
ev
io
u
s
p
r
ed
ictio
n
a
n
al
y
s
i
s
p
r
o
ce
s
s
.
T
h
er
ef
o
r
e,
th
is
s
tu
d
y
ai
m
s
to
p
r
o
d
u
ce
a
m
o
r
e
ac
cu
r
ate
p
r
e
d
ictio
n
r
esu
lt
t
h
at
ca
n
b
e
u
s
ed
as
in
f
o
r
m
a
tio
n
o
n
th
e
e
s
ti
m
ated
g
o
ld
p
r
ice
th
a
t
w
il
l
o
cc
u
r
in
t
h
e
n
ex
t
p
er
io
d
.
A
n
o
t
h
er
g
o
al
to
b
e
ac
h
iev
ed
f
r
o
m
th
is
r
esear
ch
b
ased
o
n
th
e
i
m
p
le
m
en
tat
i
o
n
o
f
MR
L
in
th
e
A
N
N
p
r
ed
ictio
n
p
r
o
ce
s
s
i
s
to
b
e
ab
le
to
p
r
o
p
o
s
e
a
b
etter
f
o
r
m
o
f
t
h
e
p
r
ed
ictiv
e
an
al
y
s
is
m
o
d
el.
T
h
is
an
al
y
s
i
s
m
o
d
el
ca
n
b
e
u
s
ed
to
p
r
ed
ict
o
th
er
ca
s
es
to
o
b
tain
p
r
ed
ictiv
e
r
esu
lt
s
w
ith
a
g
o
o
d
lev
el
o
f
ac
cu
r
ac
y
.
T
h
er
ef
o
r
e,
th
is
m
o
d
el
w
ill
b
e
ab
le
to
im
p
r
o
v
e
th
e
p
r
ed
ictiv
e
a
n
al
y
s
is
p
r
o
ce
s
s
t
h
at
h
a
s
b
ee
n
ca
r
r
ied
o
u
t
b
y
A
NN
p
r
ev
io
u
s
l
y
.
2.
RE
S
E
ARCH
M
E
T
H
O
D
T
h
e
r
esear
ch
m
et
h
o
d
o
lo
g
y
is
cr
u
cial
in
d
escr
ib
i
n
g
th
e
r
esea
r
ch
ac
tiv
i
ties
ca
r
r
ied
o
u
t
b
y
r
e
s
ea
r
ch
er
s
.
T
h
e
r
esear
ch
m
et
h
o
d
o
lo
g
y
s
ta
r
ts
f
r
o
m
b
u
ild
i
n
g
a
f
r
a
m
e
w
o
r
k
in
th
e
p
r
o
ce
s
s
o
f
s
o
lv
i
n
g
p
r
o
b
le
m
s
.
T
h
e
s
h
ap
e
o
f
th
e
f
r
a
m
e
w
o
r
k
i
n
t
h
is
s
tu
d
y
is
in
Fi
g
u
r
e
1
.
Fig
u
r
e
1
.
R
esear
ch
m
et
h
o
d
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
I
mp
leme
n
ta
tio
n
mu
ltip
le
lin
ea
r
r
eg
r
esio
n
in
n
eu
r
a
l n
etw
o
r
k
p
r
ed
ict
g
o
ld
p
r
ice
(
Mu
s
li Ya
n
to
)
1637
Fig
u
r
e
1
is
p
r
esen
ted
,
a
p
r
ed
i
ctio
n
m
o
d
el
d
e
v
elo
p
ed
in
t
h
i
s
s
t
u
d
y
.
T
h
e
f
o
llo
w
i
n
g
s
tep
s
ar
e
tak
en
:
i)
T
h
e
f
ir
s
t
s
ta
g
e
is
th
e
s
ta
g
e
f
o
r
an
aly
z
in
g
th
e
d
ata
th
at
w
ill
b
e
u
s
ed
as
a
v
ar
iab
le
f
o
r
th
e
p
r
ed
ictio
n
p
r
o
ce
s
s
;
ii)
T
h
e
s
ec
o
n
d
s
tag
e
is
f
o
r
m
i
n
g
a
p
r
ed
ictiv
e
n
et
w
o
r
k
p
atte
r
n
;
iii)
T
h
e
th
ir
d
s
tag
e
w
ill
t
est
th
e
co
r
r
elatio
n
b
et
w
ee
n
p
r
ed
ictiv
e
v
ar
iab
les
a
n
d
also
test
th
e
co
r
r
elatio
n
w
it
h
t
h
e
p
r
ed
ictio
n
tar
g
et
u
s
in
g
MR
L
;
i
v
)
A
f
ter
th
e
co
r
r
elat
io
n
test
p
h
ase
w
it
h
M
R
L
,
t
h
e
n
e
x
t
s
tep
is
to
an
al
y
z
e
th
e
test
r
es
u
lts
.
I
f
th
e
te
s
t
r
esu
lt
s
g
i
v
e
o
p
ti
m
a
l
r
esu
lt
s
,
th
e
b
est
p
r
ed
icti
v
e
p
atter
n
m
o
d
el
i
s
f
o
u
n
d
.
I
f
n
o
t
th
e
n
r
ep
ea
t
th
e
d
ata
an
a
l
y
s
is
p
r
o
ce
s
s
at
t
h
e
b
eg
in
n
i
n
g
;
v
)
T
h
e
f
i
f
t
h
s
tag
e
is
t
h
e
i
n
itial
s
t
a
g
e
i
n
ca
r
r
y
i
n
g
o
u
t
t
h
e
p
r
ed
ictio
n
p
r
o
ce
s
s
u
s
in
g
A
NN.
At
t
h
i
s
s
tag
e
t
h
e
d
ata
w
i
ll
b
e
n
o
r
m
ali
ze
d
s
o
th
at
it
ca
n
b
e
ca
r
r
ied
o
u
t
in
t
h
e
tr
ain
in
g
p
r
o
ce
s
s
an
d
n
et
w
o
r
k
tes
tin
g
;
a
n
d
v
i)
T
h
e
f
in
al
s
tag
e
i
n
th
is
r
es
ea
r
ch
m
eth
o
d
o
lo
g
y
i
s
to
m
ea
s
u
r
e
th
e
o
u
tp
u
t
lev
el
o
f
t
h
e
n
et
w
o
r
k
s
o
th
at
in
t
h
e
en
d
it
w
ill
f
in
d
a
g
o
o
d
p
r
ed
ictiv
e
r
esu
l
t
2
.
1
.
Da
t
a
a
na
ly
s
is
I
n
p
r
ed
ictin
g
t
h
e
p
r
ice
o
f
g
o
ld
,
th
e
p
r
e
d
icto
r
v
ar
iab
les
u
s
ed
in
cl
u
d
e:
o
il
p
r
ice
(
X1
)
is
a
v
a
r
iab
le
th
at
af
f
ec
ts
g
o
ld
p
r
ice
m
o
v
e
m
e
n
ts
[
1
7
]
,
[
1
8
]
.
T
h
e
ex
ch
an
g
e
r
ate
ag
ain
s
t
th
e
Do
llar
also
h
as
an
in
f
l
u
en
ce
s
o
n
th
e
p
r
ice
o
f
g
o
ld
[
1
9
]
,
[
2
0
]
,
an
d
th
e
in
f
latio
n
r
ate
as
an
i
n
d
icato
r
th
at
p
la
y
s
a
r
o
le
in
f
l
u
ct
u
ati
n
g
g
o
ld
p
r
ices
[
2
1
]
,
[
2
2
]
.
T
h
e
o
u
tp
u
t is
p
r
esen
ted
in
T
ab
le
1
.
T
ab
le
1
.
P
r
ed
icto
r
v
ar
iab
le
O
i
l
P
r
i
c
e
(
X
1
)
Ex
c
h
a
n
g
e
R
a
t
e
(
X
2
)
I
n
f
l
a
t
i
o
n
(
X
3
)
G
o
l
d
P
r
i
c
e
(
X
4
)
2
9
.
7
8
1
3
,
9
1
5
.
0
0
4
.
1
4
%
3
6
.
2
8
3
1
.
0
3
1
3
,
4
6
2
.
0
0
4
.
4
2
%
3
9
.
6
2
3
7
.
3
4
1
3
,
3
4
2
.
0
0
4
.
4
5
%
3
9
.
3
9
4
0
.
7
5
1
3
,
2
7
0
.
0
0
3
.
6
0
%
4
0
.
6
0
4
5
.
9
4
1
3
,
6
8
3
.
0
0
3
.
3
3
%
3
8
.
9
7
4
7
.
6
9
1
3
,
2
4
6
.
0
0
3
.
4
5
%
4
1
.
3
0
4
4
.
1
3
1
3
,
1
5
9
.
0
0
3
.
2
1
%
4
2
.
6
7
4
4
.
8
8
1
3
,
3
6
7
.
0
0
2
.
7
9
%
4
2
.
4
8
4
5
.
0
4
1
3
,
0
6
3
.
0
0
3
.
0
7
%
4
2
.
0
6
4
9
.
2
9
1
3
,
1
1
6
.
0
0
3
.
3
1
%
4
1
.
0
7
4
5
.
2
6
1
3
,
6
3
1
.
0
0
3
.
5
8
%
3
7
.
9
7
5
2
.
6
2
1
3
,
5
0
3
.
0
0
3
.
0
2
%
3
7
.
1
8
2
.
2
.
M
ultiple r
eg
re
s
s
io
n linea
r
(
M
RL
)
Af
ter
t
h
e
p
r
ed
ictiv
e
n
e
t
w
o
r
k
p
atter
n
i
s
f
o
r
m
ed
,
t
h
e
d
is
c
u
s
s
io
n
w
ill
co
n
ti
n
u
e
w
it
h
th
e
p
r
o
ce
s
s
o
f
test
i
n
g
th
e
co
r
r
elatio
n
f
o
r
t
h
e
p
r
ed
icto
r
v
ar
iab
les.
T
h
is
p
r
o
c
ess
u
s
e
s
m
u
l
tip
le
li
n
ea
r
r
eg
r
es
s
io
n
m
et
h
o
d
s
.
T
h
is
m
et
h
o
d
is
v
er
y
f
ea
s
ib
le
in
a
n
al
y
z
in
g
t
h
e
r
elatio
n
s
h
ip
b
et
w
ee
n
v
ar
iab
les
as
a
p
ar
a
m
et
er
to
m
ea
s
u
r
e
t
h
e
r
elatio
n
s
h
ip
b
et
w
ee
n
th
e
p
r
ed
icto
r
(
X)
an
d
th
e
p
r
e
d
icted
r
e
s
u
lt
s
(
Y)
.
Af
ter
th
e
p
r
ed
ictiv
e
n
et
w
o
r
k
p
atter
n
is
f
o
r
m
ed
,
th
e
d
is
cu
s
s
io
n
w
ill
c
o
n
tin
u
e
w
it
h
th
e
p
r
o
ce
s
s
o
f
test
in
g
th
e
co
r
r
elatio
n
f
o
r
th
e
p
r
ed
icto
r
v
ar
iab
les.
T
h
is
p
r
o
ce
s
s
u
s
es
m
u
ltip
le
lin
ea
r
r
eg
r
es
s
io
n
m
et
h
o
d
s
.
T
h
is
m
et
h
o
d
is
v
er
y
f
ea
s
ib
l
e
in
an
al
y
zi
n
g
t
h
e
r
elatio
n
s
h
ip
b
et
w
ee
n
v
ar
iab
le
s
as
a
p
ar
a
m
eter
to
m
ea
s
u
r
e
t
h
e
r
elatio
n
s
h
ip
b
et
w
ee
n
t
h
e
p
r
ed
icto
r
(
X)
an
d
th
e
p
r
ed
icted
r
esu
lts
(
Y)
[
2
3
]
,
[
2
4
]
.
A
f
ter
th
e
p
r
ed
ictiv
e
n
et
w
o
r
k
p
atter
n
is
f
o
r
m
ed
,
th
e
d
is
c
u
s
s
io
n
w
ill
m
u
ltip
le
lin
ea
r
r
eg
r
ess
io
n
(
ML
R
)
is
also
a
v
er
y
s
i
m
p
le
m
et
h
o
d
f
o
r
lo
o
k
in
g
at
th
e
r
elatio
n
s
h
ip
b
etw
ee
n
p
r
ed
icto
r
v
ar
iab
les
a
n
d
r
esp
o
n
s
e
v
ar
iab
les
[
2
5
]
.
I
n
m
u
ltip
le
r
eg
r
e
s
s
io
n
,
th
er
e
ar
e
m
o
r
e
th
a
n
t
w
o
o
r
m
o
r
e
in
d
ep
en
d
e
n
t
v
ar
iab
les an
d
o
n
e
d
ep
en
d
en
t
v
ar
iab
le.
T
h
e
eq
u
atio
n
is
i
n
th
e
i
m
a
g
e
[
2
6
]
:
=
0
+
1
1
+
2
2
+
3
3
.
.
.
.
.
(
1
)
T
o
d
ev
elo
p
m
u
lt
ip
le
lin
ea
r
r
eg
r
ess
io
n
eq
u
atio
n
s
T
h
e
p
ar
am
eter
s
w
er
e
o
b
tai
n
ed
f
r
o
m
t
h
e
tr
ain
in
g
d
ata
an
d
th
e
v
ar
iab
les
w
er
e
ex
tr
ac
ted
f
r
o
m
th
e
d
ataset
u
s
in
g
co
r
r
elatio
n
.
T
h
e
q
u
an
tit
y
r
,
ca
lled
th
e
lin
ea
r
co
r
r
elatio
n
co
ef
f
icien
t,
m
ea
s
u
r
es
th
e
s
tr
en
g
th
an
d
d
i
r
ec
tio
n
o
f
th
e
r
elatio
n
s
h
ip
b
et
w
ee
n
t
w
o
v
ar
iab
les.
T
h
e
m
at
h
f
o
r
m
u
la
f
o
r
r
is
(
2
)
:
=
∑
−
(
∑
)
(
∑
)
√
(
∑
2
(
∑
2
)
−
√
(
∑
2
(
∑
2
)
(
2
)
2
.
3
.
Art
if
ici
a
l neura
l net
w
o
r
k
(
ANN)
I
n
th
e
p
r
o
ce
s
s
o
f
p
r
ed
ictin
g
t
h
e
p
r
ice
o
f
g
o
ld
.
First,
th
e
d
a
ta
is
co
n
v
er
ted
i
n
to
in
ter
v
als
[
0
,
1
]
.
T
h
e
d
ata
to
b
e
c
o
n
v
er
ted
in
cl
u
d
es
th
e
in
p
u
t
an
d
o
u
tp
u
t
la
y
er
s
i
n
th
e
n
et
w
o
r
k
.
T
h
e
in
p
u
t
an
d
o
u
tp
u
t
la
y
er
s
th
at
h
av
e
b
ee
n
ch
a
n
g
ed
,
w
ill
b
e
in
clu
d
ed
in
t
h
e
ac
tiv
atio
n
f
u
n
c
tio
n
.
T
h
is
f
u
n
ctio
n
i
s
v
er
y
n
e
ce
s
s
ar
y
b
ec
au
s
e
th
e
ac
tiv
atio
n
f
u
n
ctio
n
i
s
u
s
ed
as a
f
ee
d
-
f
o
r
w
ar
d
f
o
r
b
o
th
la
y
er
s
.
T
h
e
ac
tiv
atio
n
f
u
n
ctio
n
u
s
ed
is
s
i
g
m
o
id
[
2
7
]
.
I
f
a
lo
g
is
tic
ac
tiv
a
tio
n
f
u
n
ct
io
n
i
s
to
b
e
ap
p
lied
w
h
er
e
x
i
is
t
h
e
i
n
p
u
t
v
al
u
e
(
p
r
ed
icto
r
v
ar
iab
le)
,
th
e
in
p
u
t
v
alu
e
is
co
n
v
er
ted
to
(
0
,
1
)
.
T
h
e
m
a
th
f
o
r
m
u
la
f
o
r
r
is
(
3
)
[
2
8
]
:
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
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
22
,
No
.
3
,
J
u
n
e
2
0
2
1
:
1
6
3
5
-
1
6
4
2
1638
=
−
(
)
(
)
−
(
)
(
3
)
2
.
3
.
P
re
dict
io
n net
w
o
rk
pa
t
t
er
ns
In
th
i
s
s
ta
g
e,
th
e
r
esear
ch
d
is
cu
s
s
io
n
w
ill
co
n
tin
u
e
to
b
u
ild
a
g
o
ld
p
r
ice
p
r
ed
ictio
n
n
et
w
o
r
k
p
atter
n
.
T
h
e
p
atter
n
n
et
w
o
r
k
co
n
s
i
s
ts
o
f
in
p
u
t
la
y
er
n
e
u
r
o
n
s
,
1
n
eu
r
o
n
in
th
e
h
id
d
en
la
y
er
,
an
d
1
n
eu
r
o
n
i
n
th
e
o
u
tp
u
t
la
y
er
[
2
9
]
.
T
h
e
n
et
w
o
r
k
p
atter
n
th
at
i
s
f
o
r
m
ed
is
s
h
o
w
n
i
n
Fi
g
u
r
e
2
.
Fig
u
r
e
2
.
Go
ld
p
r
ice
p
r
ed
ictio
n
n
et
w
o
r
k
p
atter
n
3.
RE
SU
L
T
S
A
ND
AN
AL
Y
SI
S
3
.
1
.
M
RL
a
na
ly
s
is
B
ased
o
n
th
e
ab
o
v
e
eq
u
atio
n
,
th
e
m
u
ltip
le
l
in
ea
r
r
e
g
r
ess
io
n
e
x
p
er
i
m
e
n
t
to
o
b
s
er
v
e
th
e
co
r
r
elatio
n
r
esu
lt
s
o
f
t
h
e
p
r
ed
icto
r
v
ar
iab
les
ca
n
b
e
d
o
n
e
u
s
i
n
g
t
h
e
SP
SS
p
r
o
g
r
a
m
i
n
d
ata
p
r
o
ce
s
s
in
g
,
p
r
o
ce
s
s
in
g
u
s
i
n
g
th
e
v
ar
iab
le
w
o
r
ld
o
il
p
r
ice
(
X
1
)
,
th
e
r
u
p
iah
ex
ch
a
n
g
e
r
ate
(
X2
)
,
an
d
th
e
in
f
lat
io
n
r
ate
(
X3
)
as
an
in
d
ep
en
d
en
t
v
ar
iab
le,
th
e
P
r
ice
o
f
Go
ld
(
Y
)
as
th
e
d
ep
en
d
en
t
v
ar
iab
le.
Fo
llo
w
i
n
g
t
h
e
r
esu
l
ts
o
f
t
h
e
co
r
r
elatio
n
g
en
er
ated
ar
e
in
T
ab
le
2
.
T
ab
le
2
.
P
ea
r
s
o
n
co
r
r
elatio
n
r
esu
lt
C
o
r
r
e
l
a
t
i
o
n
s
X
1
_
O
P
X
2
_
E
R
X
3
_
I
N
F
Y
_
G
P
X
1
_
O
P
P
e
a
r
so
n
C
o
r
r
e
l
a
t
i
o
n
1
.
7
2
3
**
-
.
5
8
0
**
.
2
2
2
S
i
g
.
(
2
-
t
a
i
l
e
d
)
.
0
0
0
.
0
0
0
.
1
5
8
N
42
42
42
42
X
2
_
E
R
P
e
a
r
so
n
C
o
r
r
e
l
a
t
i
o
n
.
7
2
3
**
1
-
.
4
7
3
**
-
.
1
6
8
S
i
g
.
(
2
-
t
a
i
l
e
d
)
.
0
0
0
.
0
0
2
.
2
8
7
N
42
42
42
42
X
3
_
I
N
F
P
e
a
r
so
n
C
o
r
r
e
l
a
t
i
o
n
-
.
5
8
0
**
-
.
4
7
3
**
1
-
.
3
5
0
*
S
i
g
.
(
2
-
t
a
i
l
e
d
)
.
0
0
0
.
0
0
2
.
0
2
3
N
42
42
42
42
Y
_
G
P
P
e
a
r
so
n
C
o
r
r
e
l
a
t
i
o
n
.
2
2
2
-
.
1
6
8
-
.
3
5
0
*
1
S
i
g
.
(
2
-
t
a
i
l
e
d
)
.
1
5
8
.
2
8
7
.
0
2
3
N
42
42
42
42
*
*
.
C
o
r
r
e
l
a
t
i
o
n
i
s
si
g
n
i
f
i
c
a
n
t
a
t
t
h
e
0
.
0
1
l
e
v
e
l
(
2
-
t
a
i
l
e
d
)
.
*
.
C
o
r
r
e
l
a
t
i
o
n
i
s si
g
n
i
f
i
c
a
n
t
a
t
t
h
e
0
.
0
5
l
e
v
e
l
(2
-
t
a
i
l
e
d
)
.
Fro
m
T
ab
le
2
,
it
ca
n
b
e
ex
p
lain
ed
t
h
e
r
elatio
n
s
h
ip
b
et
w
e
en
v
ar
iab
le
s
.
T
h
e
r
elatio
n
s
h
i
p
b
et
w
ee
n
v
ar
iab
les
X1
an
d
X2
h
as
a
s
t
r
o
n
g
r
elatio
n
s
h
ip
(
0
.
7
2
3
)
,
th
e
r
elatio
n
s
h
ip
b
et
w
ee
n
v
ar
iab
l
es
X1
an
d
X3
h
a
s
a
s
tr
o
n
g
r
elatio
n
s
h
ip
(
0
.
5
8
0
)
.
T
h
e
r
elatio
n
s
h
ip
b
et
w
ee
n
v
ar
ia
b
les
X1
an
d
Y
h
as
a
w
ea
k
r
e
latio
n
s
h
ip
(
0
.
2
2
2
)
.
T
h
e
r
elatio
n
s
h
ip
b
et
w
ee
n
v
ar
i
ab
le
X2
an
d
X3
h
as
a
w
ea
k
r
elatio
n
s
h
ip
(
0
.
4
7
3
)
.
T
h
e
r
elati
o
n
s
h
ip
b
et
w
ee
n
X2
an
d
Y
h
as
a
w
ea
k
r
elatio
n
s
h
i
p
(
0
.
2
2
2
)
.
T
h
e
r
elatio
n
s
h
ip
b
et
w
ee
n
v
ar
iab
le
X3
an
d
Y
h
as
a
w
ea
k
ca
teg
o
r
y
(
0
.
3
5
0
)
.
T
o
d
is
co
v
er
r
elatio
n
s
h
ip
o
f
i
n
f
lu
e
n
ce
b
et
w
ee
n
X1
,
X2
,
X3
o
n
Y,
th
e
R
Sq
u
ar
e
t
est
w
as
p
er
f
o
r
m
ed
.
T
h
e
R
Sq
u
ar
e
test
r
esu
lts
ar
e
s
h
o
w
n
i
n
T
ab
le
3
.
Fro
m
th
e
r
esu
l
ts
o
f
th
e
r
eg
r
e
s
s
io
n
p
r
o
ce
s
s
th
at
h
as
b
ee
n
d
o
n
e,
th
e
au
t
h
o
r
s
f
o
u
n
d
th
e
r
esu
lt
s
o
f
R
s
q
u
ar
e
3
7
.
8
%.
T
h
is
is
th
e
r
es
u
lt
o
f
t
h
e
p
er
ce
n
ta
g
e
g
e
n
er
at
ed
f
r
o
m
t
h
e
r
eg
r
e
s
s
io
n
p
r
o
ce
s
s
i
n
th
e
g
o
ld
p
r
ice
p
r
ed
ictio
n
p
r
o
ce
s
s
u
s
i
n
g
3
p
r
ed
icto
r
v
ar
iab
les.
T
h
e
r
em
a
in
in
g
6
2
.
2
%
is
i
n
f
l
u
e
n
ce
d
b
y
o
th
er
v
ar
iab
les
n
o
t
ex
a
m
in
ed
.
T
h
en
th
e
t
tes
t
is
u
s
ed
to
s
ee
th
e
ef
f
ec
t
o
f
th
e
v
a
r
iab
les
X1
,
X2
,
X
3
o
n
Y
p
ar
t
iall
y
d
o
n
e
an
d
th
e
r
esu
lt
s
ca
n
b
e
s
ee
n
i
n
T
ab
le
4
.
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
I
mp
leme
n
ta
tio
n
mu
ltip
le
lin
ea
r
r
eg
r
esio
n
in
n
eu
r
a
l n
etw
o
r
k
p
r
ed
ict
g
o
ld
p
r
ice
(
Mu
s
li Ya
n
to
)
1639
T
ab
le
3
.
Mu
ltip
lelin
ea
r
r
eg
r
es
s
io
n
r
es
u
lts
M
o
d
e
l
S
u
mm
a
r
y
M
o
d
e
l
R
R
S
q
u
a
r
e
A
d
j
u
st
e
d
R
S
q
u
a
r
e
S
t
d
.
Er
r
o
r
o
f
t
h
e
Es
t
i
m
a
t
e
1
.
6
1
5
a
.
3
7
8
.
3
2
9
1
.
3
9
5
8
8
P
r
e
d
i
c
t
o
r
s:
(
C
o
n
s
t
a
n
t
)
,
X
3
_
I
N
F
,
X
2
_
ER
,
X
1
_
O
P
T
ab
le
4
.
T
test
r
esu
lt
C
o
e
f
f
i
c
i
e
n
t
s
a
M
o
d
e
l
U
n
st
a
n
d
a
r
d
i
z
e
d
C
o
e
f
f
i
c
i
e
n
t
s
S
t
a
n
d
a
r
d
i
z
e
d
t
S
i
g
.
B
S
t
d
.
Er
r
o
r
B
e
t
a
1
(
C
o
n
st
a
n
t
)
7
2
.
9
2
2
7
.
7
4
2
9
.
4
1
9
.
0
0
0
X
1
_
O
P
.
0
7
6
.
0
2
9
.
5
2
5
2
.
6
0
8
.
0
1
3
X
2
_
E
R
-
.
0
0
2
.
0
0
1
-
.
7
3
4
-
3
.
9
4
4
.
0
0
0
X
3
_
I
N
F
-
1
.
3
8
8
.
5
5
6
-
.
3
9
3
.
0
1
7
D
e
p
e
n
d
e
n
t
V
a
r
i
a
b
l
e
:
Y
_
G
P
B
ased
o
n
th
e
ab
o
v
e
o
u
tp
u
t,
th
e
r
esu
lts
o
b
tain
ed
f
o
r
X1
,
th
e
r
esu
lt
s
o
f
th
e
t
test
s
h
o
w
t
h
at
th
e
o
il p
r
ice
v
ar
iab
le
h
as
a
s
i
g
n
i
f
ican
t
e
f
f
e
ct
o
n
th
e
p
r
ice
o
f
g
o
ld
.
w
h
er
e
th
e
s
i
g
v
al
u
e
is
0
.
0
1
3
<0
.
0
5
.
Fo
r
X2
,
th
e
t
test
r
esu
lt
s
s
h
o
w
th
at
t
h
e
ex
c
h
an
g
e
r
ate
v
ar
iab
le
h
as
a
s
ig
n
if
ican
t
ef
f
ec
t
o
n
th
e
p
r
ice
o
f
g
o
ld
.
A
s
in
th
e
tab
le
w
h
er
e
th
e
v
al
u
e
o
f
s
i
g
0
.
0
1
3
<0
.
0
0
0
.
Fo
r
v
ar
iab
le
X3
,
th
e
r
esu
lts
o
f
th
e
t
test
s
h
o
w
t
h
at
t
h
e
in
f
l
atio
n
v
ar
iab
le
h
as
a
s
ig
n
i
f
ica
n
t
ef
f
ec
t
o
n
th
e
p
r
ice
o
f
g
o
ld
.
T
h
is
ca
n
b
e
s
ee
n
f
r
o
m
th
e
s
i
g
v
alu
e
o
f
0
.
0
1
7
<0
.
0
5
.
Fo
r
th
e
r
elatio
n
s
h
ip
b
et
w
ee
n
th
e
p
r
ice
o
f
o
il
w
it
h
th
e
p
r
ice
o
f
g
o
ld
.
T
h
e
r
esu
lts
o
f
t
h
is
s
t
u
d
y
ar
e
s
a
m
e
w
i
t
h
p
r
ev
io
u
s
s
t
u
d
ies
co
n
d
u
cted
b
y
[
3
0
]
s
tatin
g
t
h
at
w
o
r
ld
o
il
p
r
ices
ar
e
o
n
e
o
f
th
e
f
ac
to
r
s
th
at
in
f
lu
e
n
ce
th
e
p
r
ice
o
f
g
o
ld
.
Fo
r
th
e
r
elatio
n
s
h
ip
b
et
w
ee
n
t
h
e
ex
c
h
an
g
e
r
ate
a
n
d
th
e
p
r
ice
o
f
g
o
ld
,
th
e
r
esu
l
ts
o
f
t
h
is
s
t
u
d
y
ar
e
i
n
li
n
e
w
it
h
r
esear
ch
co
n
d
u
cted
b
y
[
3
1
]
w
h
ic
h
p
r
o
v
es
t
h
at
t
h
e
e
x
ch
a
n
g
e
r
ate
af
f
ec
ts
th
e
m
o
v
e
m
e
n
t
o
f
g
o
ld
p
r
ices.
Fo
r
th
e
r
elat
io
n
s
h
ip
b
et
w
ee
n
in
f
latio
n
an
d
th
e
p
r
ice
o
f
g
o
ld
.
T
h
e
r
e
s
u
lt
s
o
f
th
i
s
s
tu
d
y
ar
e
also
in
lin
e
w
it
h
r
esear
ch
co
n
d
u
cted
b
y
[
3
2
]
w
h
ich
p
r
o
v
ed
th
at
in
f
latio
n
ca
n
also
in
f
lu
en
ce
g
o
ld
p
r
ice
m
o
v
e
m
e
n
ts
.
So
th
o
s
e
v
ar
iab
les
th
at
h
a
v
e
b
ee
n
te
s
ted
ca
n
b
e
u
s
ed
as v
ar
iab
les i
n
th
e
g
o
ld
p
r
ice
p
r
ed
ictio
n
p
r
o
ce
s
s
.
3
.
2
.
P
re
dict
ANN
I
n
co
n
d
u
ct
in
g
t
h
e
p
r
ed
ictio
n
p
r
o
ce
s
s
,
th
e
A
NN
m
o
d
el
u
s
ed
is
b
ac
k
p
r
o
p
ag
atio
n
.
T
h
e
p
r
o
ce
s
s
b
eg
i
n
s
w
it
h
a
tr
an
s
f
o
r
m
a
tio
n
p
r
o
ce
s
s
.
T
h
ese
r
esu
l
ts
ca
n
b
e
s
ee
n
in
T
ab
le
5
.
A
f
ter
th
e
d
ata
i
s
tr
an
s
f
o
r
m
ed
,
th
e
p
r
e
d
ictio
n
p
r
o
ce
s
s
is
co
n
tin
u
e
d
to
c
o
n
d
u
ct
tr
ain
i
n
g
a
n
d
test
i
n
g
o
n
t
h
e
n
et
w
o
r
k
ar
ch
itect
u
r
e
th
at
h
as
b
ee
n
b
u
il
t
b
ased
o
n
th
e
p
r
ed
icto
r
v
ar
iab
l
es
f
r
o
m
t
h
e
d
ata
an
al
y
s
i
s
p
r
o
c
ess
.
T
h
is
p
r
o
ce
s
s
w
i
ll
p
r
o
d
u
ce
th
e
o
p
ti
m
al
w
ei
g
h
t
in
th
e
f
o
r
m
o
f
p
er
f
o
r
m
a
n
ce
an
d
ep
o
ch
v
alu
e
s
b
ased
o
n
th
e
p
r
ev
io
u
s
n
et
w
o
r
k
p
atter
n
[
3
3
]
,
[
3
4
]
.
T
h
e
tr
ain
in
g
an
d
test
i
n
g
r
es
u
lt
s
tab
le
ca
n
b
e
s
ee
n
i
n
T
ab
le
6
.
T
ab
le
5
.
R
esu
lt o
f
co
n
v
er
t d
at
a
p
r
ed
ict
X1
X2
X3
X4
T
0
.
1
0
0
0
0
0
.
1
0
0
0
0
0
.
9
0
0
0
0
0
.
1
8
3
9
1
6
0
.
2
6
8
5
0
4
0
.
1
7
0
7
8
0
.
1
2
0
6
2
6
0
.
8
3
1
4
2
9
0
.
7
4
6
1
5
4
0
.
1
5
0
3
9
4
0
.
2
6
4
2
2
2
0
.
2
2
4
4
9
4
0
.
7
1
7
1
4
3
0
.
3
2
3
7
7
6
0
.
1
0
0
0
0
0
.
3
2
5
3
7
8
0
.
2
8
4
1
6
2
0
.
5
5
7
1
4
3
0
.
2
8
7
4
1
3
0
.
2
2
7
5
5
9
0
.
4
8
0
9
0
8
0
.
2
4
1
4
3
6
0
.
2
3
7
1
4
3
0
.
3
0
1
3
9
9
0
.
2
7
4
8
0
3
0
.
5
2
0
0
2
3
0
.
2
6
6
4
8
3
0
.
5
9
1
4
2
9
0
.
5
3
0
7
6
9
0
.
5
6
6
1
4
2
0
.
6
7
6
4
8
4
0
.
1
6
6
2
9
8
0
.
1
8
0
0
0
0
.
9
0
0
0
0
0
.
9
0
0
0
0
0
.
5
9
0
4
9
3
0
.
3
8
4
3
4
6
0
.
1
0
0
0
0
0
.
6
9
3
0
0
7
0
.
7
5
3
5
4
3
0
.
6
1
2
5
3
4
0
.
4
2
0
4
4
2
0
.
3
5
1
4
2
9
0
.
7
2
6
5
7
3
0
.
8
5
5
9
0
6
0
.
7
5
5
9
5
7
0
.
5
0
9
5
7
6
0
.
3
6
2
8
5
7
0
.
6
9
3
0
0
7
0
.
7
4
5
6
6
9
0
.
9
0
0
0
0
0
.
5
6
4
8
2
5
0
.
1
5
7
1
4
3
0
.
5
1
9
5
8
0
.
6
2
9
1
3
4
0
.
8
5
4
9
8
6
0
.
9
0
0
0
0
0
.
0
3
1
4
2
9
0
.
1
0
0
0
0
0
.
4
1
8
1
1
T
ab
le
6.
T
r
ain
in
g
an
d
n
et
w
o
r
k
test
in
g
r
es
u
lts
N
e
t
w
o
r
k
P
a
t
t
e
r
n
Er
r
o
r
M
S
E
P
a
t
t
e
r
n
4
-
4
-
1
0
.
0
0
6
2
0
.
0
0
6
3
6
4
P
a
t
t
e
r
n
4
-
6
-
1
0
.
0
0
4
1
0
.
0
0
4
2
6
4
P
a
t
t
e
r
n
4
-
8
-
1
0
.
0
0
5
0
.
0
0
4
8
6
4
P
a
t
t
e
r
n
4
-
10
-
1
0
.
0
1
9
3
0
.
0
1
9
2
6
4
P
a
t
t
e
r
n
4
-
12
-
1
0
.
0
2
0
6
0
.
0
2
0
6
6
4
T
a
b
l
e
6
s
h
o
w
s
th
at
th
e
b
es
t
n
etw
o
r
k
p
a
tt
e
r
n
in
th
e
p
r
e
d
i
c
t
i
o
n
p
r
o
c
e
s
s
i
s
i
n
th
e
4
-
6
-
1
p
a
t
t
e
r
n
w
ith
a
M
S
E
v
a
lu
e
o
f
0
.
0
0
4
8
6
4
.
T
h
e
p
a
tt
e
r
n
r
esu
l
tin
g
f
r
o
m
th
i
s
p
r
o
c
e
s
s
,
in
t
h
i
s
c
as
e
,
n
ee
d
s
t
o
b
e
r
e
c
o
n
s
i
d
e
r
e
d
t
o
e
n
s
u
r
e
t
h
e
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
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
22
,
No
.
3
,
J
u
n
e
2
0
2
1
:
1
6
3
5
-
1
6
4
2
1640
p
r
e
d
i
c
t
iv
e
o
u
t
p
u
t
[
3
5
]
.
T
h
e
M
S
E
v
a
lu
e
c
an
b
e
u
s
e
d
a
s
a
n
ap
p
r
o
a
c
h
i
n
s
ee
in
g
t
h
e
e
r
r
o
r
v
al
u
e
o
f
t
h
e
n
e
t
w
o
r
k
o
u
t
p
u
t
[
3
6
]
.
B
a
s
e
d
o
n
th
e
p
r
ed
i
c
t
i
o
n
an
a
ly
s
i
s
p
r
o
c
ess
c
a
r
r
i
ed
o
u
t
u
s
i
n
g
Ma
t
l
a
b
s
o
f
tw
a
r
e
,
th
e
p
r
e
d
i
ct
i
o
n
r
e
s
u
lt
s
s
h
o
w
th
e
a
c
cu
r
a
cy
in
d
es
c
r
i
b
in
g
th
e
g
o
l
d
p
r
i
c
e
m
o
v
em
en
ts
th
a
t
w
i
ll
o
c
cu
r
in
th
e
n
ex
t
p
e
r
i
o
d
c
a
n
b
e
s
e
en
in
th
e
F
ig
u
r
e
3
a
n
d
a
g
r
a
p
h
o
f
th
e
a
c
q
u
is
i
ti
o
n
o
f
th
e
p
r
e
d
i
c
t
i
o
n
r
es
u
l
ts
is
s
h
o
w
n
in
T
a
b
l
e
7
.
Fro
m
th
e
p
r
ed
ictio
n
p
r
o
ce
s
s
ca
r
r
ied
o
u
t,
th
is
r
esear
ch
ca
n
p
r
o
v
id
e
g
o
o
d
p
r
e
d
ictio
n
r
esu
lt
s
in
p
r
ed
ictin
g
t
h
e
g
o
ld
p
r
ice
th
at
w
il
l
o
cc
u
r
in
th
e
n
e
x
t
p
er
io
d
.
B
ased
o
n
th
e
p
r
ed
ictio
n
tab
le,
s
h
o
w
s
th
at
t
h
e
er
r
o
r
r
ate
is
m
in
i
m
al
b
ased
o
n
t
h
e
s
p
ec
if
ied
tar
g
et.
An
o
th
er
f
in
d
in
g
o
b
tai
n
ed
in
t
h
i
s
s
t
u
d
y
is
th
at
t
h
e
p
r
o
p
o
s
ed
an
al
y
s
is
m
o
d
el
w
i
th
t
h
e
i
m
p
le
m
en
tatio
n
o
f
M
R
L
in
t
h
e
p
r
ed
ictio
n
p
r
o
ce
s
s
u
s
i
n
g
A
N
N
ca
n
d
escr
ib
e
a
b
etter
p
r
ed
ictiv
e
an
al
y
s
i
s
m
o
d
el
an
d
ca
n
i
m
p
r
o
v
e
t
h
e
p
r
ev
io
u
s
p
r
ed
ictio
n
p
r
o
ce
s
s
.
Fig
u
r
e
3
.
Gr
ap
h
o
f
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
p
r
ed
ictio
n
o
u
tp
u
t
T
a
r
g
e
t
P
r
e
d
i
c
t
i
o
n
R
e
su
l
t
T
a
r
g
e
t
P
r
e
d
i
c
t
i
o
n
R
e
su
l
t
3
6
.
2
8
3
5
.
9
0
4
1
.
3
3
9
.
7
0
3
9
.
6
2
3
7
.
5
6
4
2
.
6
7
4
2
.
9
8
3
9
.
3
9
3
7
.
3
4
4
2
.
4
8
4
1
.
1
5
4
0
.
6
3
8
.
0
3
4
2
.
0
6
4
1
.
1
1
3
8
.
9
7
3
8
.
1
6
4
1
.
0
7
4
1
.
4
4
4.
CO
NCLU
SI
O
N
T
h
is
s
tu
d
y
co
n
cl
u
d
es
t
h
at
t
h
e
p
r
ed
ictio
n
m
o
d
el
p
r
o
p
o
s
ed
w
i
th
t
h
e
i
m
p
le
m
e
n
tatio
n
o
f
m
u
lt
ip
le
lin
ea
r
r
eg
r
ess
io
n
m
et
h
o
d
s
in
t
h
e
g
o
ld
p
r
ice
p
r
ed
ictio
n
p
r
o
ce
s
s
u
s
in
g
an
ar
ti
f
icial
n
e
u
r
al
n
et
wo
r
k
ca
n
p
r
esen
t
a
p
r
ec
is
e
an
d
s
tr
u
c
tu
r
ed
p
r
ed
ictio
n
p
r
o
ce
s
s
th
at
p
r
o
v
id
e
s
a
v
er
y
h
ig
h
ac
c
u
r
ac
y
v
al
u
e
an
d
a
f
air
l
y
lo
w
er
r
o
r
r
ate.
T
h
e
r
esu
lts
o
b
tain
ed
b
y
th
e
m
u
ltip
le
l
in
ea
r
r
e
g
r
ess
io
n
m
e
t
h
o
d
ca
n
p
r
o
v
e
t
h
e
co
r
r
elatio
n
b
et
w
ee
n
t
h
e
p
r
ed
icto
r
v
ar
iab
les.
T
h
e
ca
lcu
latio
n
r
esu
lts
o
b
tain
ed
ar
e
6
2
%
o
f
th
e
co
r
r
elatio
n
v
ar
iab
le
co
r
r
elatio
n
(
x
1
,
x
2
,
an
d
x
3
)
af
f
ec
ts
t
h
e
r
es
u
lts
b
ased
o
n
th
e
r
es
u
lts
o
f
th
e
t
-
te
s
t
w
h
ic
h
s
h
o
w
s
t
h
at
ea
ch
v
ar
iab
le
af
f
ec
ts
o
u
tp
u
t
(
y
)
.
Me
an
w
h
ile,
t
h
e
p
r
ed
ictio
n
p
r
o
ce
s
s
u
s
in
g
ar
ti
f
icial
n
e
u
r
al
n
et
w
o
r
k
s
p
r
o
d
u
ce
s
p
r
ed
ictio
n
r
esu
l
ts
w
i
th
a
n
av
er
ag
e
MSE
er
r
o
r
v
alu
e
o
f
0
.
0
0
4
2
6
4
%
.
RE
F
E
R
E
NC
E
S
[1
]
K.
A
d
e
n
,
“
P
re
d
icti
o
n
o
f
G
o
ld
P
rice
s
Us
in
g
A
rti
f
icia
l
Ne
u
ra
l
Ne
tw
o
rk
s,”
Ulu
sla
ra
ra
sı
M
u
h
e
n
d
is.
Ara
stirma
v
e
Ge
li
stirme
De
rg
.
,
n
o
.
A
p
ril
,
p
p
.
8
3
-
8
9
,
2
0
1
7
,
d
o
i:
1
0
.
2
9
1
3
7
/u
m
a
g
d
.
3
5
0
5
9
6
.
[2
]
M
.
Ha
m
d
i
a
n
d
C.
A
lo
u
i,
“
F
o
re
c
a
stin
g
c
ru
d
e
o
il
p
rice
u
sin
g
a
rti
f
icia
l
n
e
u
ra
l
n
e
tw
o
rk
s:
A
li
tera
tu
re
su
rv
e
y
,
”
Eco
n
.
Bu
ll
.
,
v
o
l.
3
5
,
n
o
.
2
,
p
p
.
1
3
3
9
-
1
3
5
9
,
2
0
1
5
.
[3
]
W
.
A
.
A
l
-
Dh
u
ra
ib
i
a
n
d
J.
A
li
,
“
Us
in
g
c
las
sif
i
c
a
ti
o
n
tec
h
n
iq
u
e
s
to
p
re
d
ict
g
o
ld
p
rice
m
o
v
e
m
e
n
t,
”
in
2
0
1
8
4
t
h
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
Co
mp
u
ter
a
n
d
T
e
c
h
n
o
lo
g
y
Ap
p
li
c
a
ti
o
n
s,
ICC
T
A
2
0
1
8
,
2
0
1
8
,
p
p
.
1
2
7
-
1
3
0
,
d
o
i:
1
0
.
1
1
0
9
/CA
TA
.
2
0
1
8
.
8
3
9
8
6
6
9
.
[4
]
I.
u
l
S
a
m
i
a
n
d
K.
Na
z
ir,
“
P
re
d
ict
in
g
F
u
t
u
re
G
o
ld
Ra
tes
u
sin
g
M
a
c
h
in
e
L
e
a
rn
in
g
A
p
p
ro
a
c
h
,
”
I
n
t.
J
.
Ad
v
.
Co
mp
u
t.
S
c
i.
A
p
p
l.
,
v
o
l.
8
,
n
o
.
1
2
,
2
0
1
7
,
d
o
i:
1
0
.
1
4
5
6
9
/
ij
a
c
sa
.
2
0
1
7
.
0
8
1
2
1
3
.
[5
]
P
.
Zh
a
n
g
a
n
d
B.
Ci,
“
De
e
p
b
e
li
e
f
n
e
t
w
o
rk
f
o
r
g
o
ld
p
rice
f
o
re
c
a
stin
g
,
”
Res
o
u
r.
Po
li
c
y
,
v
o
l.
6
9
,
2
0
2
0
,
d
o
i:
1
0
.
1
0
1
6
/j
.
re
so
u
rp
o
l.
2
0
2
0
.
1
0
1
8
0
6
.
[6
]
Y.
S
a
ri,
E.
S
.
W
ij
a
y
a
,
A
.
R.
Ba
s
k
a
ra
,
a
n
d
R.
S
.
D.
Ka
sa
n
d
a
,
“
P
S
O
o
p
ti
m
iza
ti
o
n
o
n
b
a
c
k
p
ro
p
a
g
a
ti
o
n
f
o
r
f
ish
c
a
tch
p
ro
d
u
c
ti
o
n
p
re
d
ictio
n
,
”
T
EL
KO
M
NIKA
T
e
lec
o
mm
u
n
ic
a
ti
o
n
,
Co
mp
u
ti
n
g
,
E
lec
tro
n
ics
a
n
d
Co
n
tro
l
,
v
o
l.
1
8
,
n
o
.
2
,
p
p
.
7
7
6
-
7
8
2
,
2
0
2
0
,
d
o
i:
1
0
.
1
2
9
2
8
/T
EL
K
OMNIK
A
.
V
1
8
I
2
.
1
4
8
2
6
.
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
I
mp
leme
n
ta
tio
n
mu
ltip
le
lin
ea
r
r
eg
r
esio
n
in
n
eu
r
a
l n
etw
o
r
k
p
r
ed
ict
g
o
ld
p
r
ice
(
Mu
s
li Ya
n
to
)
1641
[7
]
Y.
Zh
u
a
n
d
C.
Zh
a
n
g
,
“
G
o
ld
P
r
ice
P
re
d
icti
o
n
Ba
se
d
o
n
P
CA
-
GA
-
BP
Ne
u
ra
l
Ne
t
w
o
rk
,
”
J
.
Co
m
p
u
t.
C
o
m
mu
n
.
,
v
o
l.
6
,
n
o
.
7
,
p
p
.
2
2
-
3
3
,
2
0
1
8
,
d
o
i
:
1
0
.
4
2
3
6
/j
c
c
.
2
0
1
8
.
6
7
0
0
3
.
[8
]
M
.
Yu
so
f
f
,
F
.
M
.
Dn
a
ji
b
,
a
n
d
R.
Is
m
a
il
,
“
H
y
b
rid
b
a
c
k
p
ro
p
a
g
a
ti
o
n
n
e
u
ra
l
n
e
tw
o
rk
-
p
a
rti
c
le
s
w
a
r
m
o
p
ti
m
iza
ti
o
n
f
o
r
se
is
m
ic
d
a
m
a
g
e
b
u
il
d
in
g
p
re
d
icti
o
n
,
”
In
d
o
n
e
sia
n
J
o
u
r
n
a
l
o
f
El
e
c
tr
ica
l
En
g
in
e
e
rin
g
a
n
d
C
o
mp
u
ter
S
c
ien
c
e
,
v
o
l.
1
4
,
n
o
.
1
,
p
p
.
3
6
0
-
3
6
7
,
2
0
1
9
,
d
o
i:
1
0
.
1
1
5
9
1
/i
jee
c
s.v
1
4
.
i
1
.
p
p
3
6
0
-
3
6
7
.
[9
]
S
.
S
u
c
ip
t
o
,
M
.
A
n
n
a
,
M
.
A
r
w
a
n
i,
a
n
d
Y.
He
n
d
ra
w
a
n
,
“
A
ra
p
id
c
l
a
ss
if
i
c
a
ti
o
n
o
f
w
h
e
a
t
f
lo
u
r
p
r
o
tei
n
c
o
n
ten
t
u
si
n
g
a
rti
f
icia
l
n
e
u
ra
l
n
e
tw
o
rk
m
o
d
e
l
b
a
se
d
o
n
b
io
e
lec
tri
c
a
l
p
ro
p
e
rti
e
s,”
T
EL
KOM
NIKA
T
e
lec
o
mm
u
n
ica
ti
o
n
,
Co
m
p
u
t
in
g
,
El
e
c
tro
n
ics
a
n
d
C
o
n
tro
l
,
v
o
l.
1
7
,
n
o
.
2
,
p
p
.
9
2
0
-
9
2
7
,
2
0
1
9
,
d
o
i:
1
0
.
1
2
9
2
8
/T
EL
KO
M
NIK
A
.
V
1
7
I2
.
9
4
5
0
.
[1
0
]
C.
L
in
,
“
Bu
il
d
P
re
d
ictio
n
M
o
d
e
ls
f
o
r
G
o
ld
P
rice
s
Ba
se
d
o
n
Ba
c
k
-
P
ro
p
a
g
a
ti
o
n
Ne
u
ra
l
Ne
tw
o
rk
,
”
Pro
c
e
e
d
in
g
s
o
f
th
e
2
0
1
5
I
n
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
M
o
d
e
li
n
g
,
S
imu
l
a
ti
o
n
a
n
d
Ap
p
li
e
d
M
a
th
e
ma
ti
c
s
,
2
0
1
5
,
p
p
.
1
5
5
-
1
5
8
,
d
o
i:
1
0
.
2
9
9
1
/m
sa
m
-
1
5
.
2
0
1
5
.
3
5
.
[1
1
]
A
.
B.
Ço
lak
,
“
A
n
e
x
p
e
ri
m
e
n
tal
stu
d
y
o
n
th
e
c
o
m
p
a
ra
ti
v
e
a
n
a
l
y
sis
o
f
th
e
e
ffe
c
t
o
f
th
e
n
u
m
b
e
r
o
f
d
a
ta
o
n
th
e
e
rro
r
ra
tes
o
f
a
rti
f
i
c
ial
n
e
u
ra
l
n
e
tw
o
rk
s,”
In
t.
J
.
En
e
rg
y
Res
.
,
v
o
l.
4
5
,
n
o
.
1
,
p
p
.
4
7
8
-
5
0
0
,
2
0
2
1
,
d
o
i:
1
0
.
1
0
0
2
/er.5
6
8
0
.
[1
2
]
A
.
B.
Ço
lak
,
“
Ex
p
e
ri
m
e
n
tal
stu
d
y
f
o
r
th
e
rm
a
l
c
o
n
d
u
c
ti
v
it
y
o
f
w
a
t
e
r
-
b
a
se
d
z
irco
n
iu
m
o
x
id
e
n
a
n
o
f
lu
id
:
De
v
e
lo
p
in
g
o
p
ti
m
a
l
a
rti
f
icia
l
n
e
u
ra
l
n
e
tw
o
rk
a
n
d
p
ro
p
o
si
n
g
n
e
w
c
o
rre
latio
n
,
”
I
n
t.
J
.
E
n
e
rg
y
Res
.
,
v
o
l.
4
5
,
n
o
.
2
,
p
p
.
2
9
1
2
-
2
9
3
0
,
2
0
2
1
,
d
o
i:
1
0
.
1
0
0
2
/er.
5
9
8
8
.
[1
3
]
Z.
Ism
a
il
,
A
.
Ya
h
y
a
,
a
n
d
A
.
S
h
a
b
ri,
“
F
o
re
c
a
stin
g
g
o
ld
p
rice
s
u
si
n
g
m
u
lt
ip
le
li
n
e
a
r
re
g
re
ss
io
n
m
e
th
o
d
,
”
Am.
J
.
A
p
p
l
.
S
c
i.
,
v
o
l
.
6
,
n
o
.
8
,
p
p
.
1
5
0
9
-
1
5
1
4
,
2
0
0
9
,
d
o
i:
1
0
.
3
8
4
4
/aja
ss
p
.
2
0
0
9
.
1
5
0
9
.
1
5
1
4
.
[1
4
]
Y.
En
i
a
n
d
R.
A
ry
a
n
to
,
“
A
n
a
l
y
si
s
o
f
f
a
c
to
rs
th
a
t
a
ff
e
c
t
th
e
m
o
v
e
m
e
n
t
o
f
g
o
ld
’s
p
rice
a
s
in
v
e
st
m
e
n
t
a
lt
e
rn
a
ti
v
e
s
in
In
d
o
n
e
sia
,
”
Ad
v
.
S
c
i.
L
e
tt
.
,
v
o
l.
2
1
,
n
o
.
4
,
p
p
.
8
7
8
-
8
8
1
,
2
0
1
5
,
d
o
i:
1
0
.
1
1
6
6
/as
l.
2
0
1
5
.
5
9
1
2
.
[1
5
]
T
.
Ulg
e
n
a
n
d
G
.
P
o
y
ra
z
o
g
lu
,
“
P
r
e
d
icto
r
a
n
a
ly
sis
f
o
r
e
lec
tri
c
it
y
p
ri
c
e
f
o
re
c
a
stin
g
b
y
m
u
lt
ip
le
li
n
e
a
r
re
g
re
ss
io
n
,
”
in
2
0
2
0
I
n
ter
n
a
ti
o
n
a
l
S
y
mp
o
siu
m
o
n
P
o
we
r
El
e
c
tro
n
ics
,
El
e
c
trica
l
Dr
ive
s,
Au
to
ma
t
io
n
a
n
d
M
o
ti
o
n
,
S
PE
EDAM
2
0
2
0
,
2
0
2
0
,
p
p
.
6
1
8
-
6
2
2
,
d
o
i:
1
0
.
1
1
0
9
/
S
P
EE
DA
M
4
8
7
8
2
.
2
0
2
0
.
9
1
6
1
8
6
6
.
[1
6
]
J.
Kim
,
S
.
Ch
o
,
K.
K
o
,
a
n
d
R.
R.
Ra
o
,
“
S
h
o
rt
-
term
El
e
c
tri
c
L
o
a
d
P
re
d
icti
o
n
Us
in
g
M
u
lt
i
p
le
L
in
e
a
r
Re
g
re
ss
io
n
M
e
th
o
d
,
”
2
0
1
8
IEE
E
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Co
mm
u
n
ica
t
i
o
n
s,
Co
n
tro
l,
a
n
d
Co
m
p
u
ti
n
g
T
e
c
h
n
o
l
o
g
ies
f
o
r
S
ma
rt Grid
s (
S
ma
rtGr
i
d
Co
mm
)
,
2
0
1
8
,
d
o
i:
1
0
.
1
1
0
9
/
S
m
a
rt
G
rid
Co
m
m
.
2
0
1
8
.
8
5
8
7
4
8
9
.
[1
7
]
T
.
H.
L
e
a
n
d
Y.
Ch
a
n
g
,
“
Oil
p
rice
sh
o
c
k
s
a
n
d
g
o
ld
re
tu
rn
s,”
Eco
n
.
In
t
.
,
v
o
l.
1
3
1
,
n
o
.
3
,
p
p
.
7
1
-
1
0
3
,
2
0
1
2
,
d
o
i:
1
0
.
1
0
1
6
/s2
1
1
0
-
7
0
1
7
(1
3
)6
0
0
5
5
-
4.
[1
8
]
L
.
T
h
a
i
-
H
a
a
n
d
Y.
Ch
a
n
g
,
“
Oil
a
n
d
G
o
ld
P
rice
s:
Co
rre
latio
n
a
n
d
Ca
u
sa
li
ty
,
”
Eco
n
o
mic
Gr
o
wth
C
e
n
tre
W
o
rk
in
g
Pa
p
e
r S
e
rie
s
1
1
0
2
,
2
0
1
1
.
[1
9
]
J.
M
a
n
o
j
a
n
d
K.
K.
S
u
re
sh
,
“
F
o
re
c
a
st
m
o
d
e
l
f
o
r
p
rice
o
f
g
o
ld
:
M
u
l
ti
p
le
l
in
e
a
r
re
g
re
ss
io
n
w
it
h
p
ri
n
c
i
p
a
l
c
o
m
p
o
n
e
n
t
a
n
a
ly
sis,”
Th
a
il
.
S
t
a
t.
,
v
o
l.
1
7
,
n
o
.
1
,
p
p
.
1
2
5
-
1
3
2
,
2
0
1
9
.
[2
0
]
V
.
S
o
d
a
u
n
y
k
a
it
ė
a
n
d
R.
M
a
rti
n
k
u
tė
-
Ka
u
li
e
n
ė
,
“
A
ss
e
ss
m
e
n
t
Of
Op
ti
o
n
P
rice
V
o
latil
it
y
,
”
M
o
k
sl.
-
L
iet.
a
teiti
s
,
v
o
l.
1
2
,
p
p
.
1
-
9
,
2
0
2
0
,
d
o
i:
1
0
.
3
8
4
6
/m
la.2
0
2
0
.
9
1
3
9
.
[2
1
]
P
.
K.
Na
ra
y
a
n
,
S
.
Na
ra
y
a
n
,
a
n
d
X
.
Zh
e
n
g
,
“
G
o
ld
a
n
d
o
il
f
u
tu
re
s
m
a
rk
e
ts:
A
re
m
a
rk
e
ts
e
ff
ici
e
n
t?,”
Ap
p
l.
En
e
rg
y
,
v
o
l.
8
7
,
n
o
.
1
0
,
p
p
.
3
2
9
9
-
3
3
0
3
,
2
0
1
0
,
d
o
i:
1
0
.
1
0
1
6
/
j.
a
p
e
n
e
rg
y
.
2
0
1
0
.
0
3
.
0
2
0
.
[2
2
]
J.
Ne
il
l
F
o
rtu
n
e
,
“
T
h
e
in
f
latio
n
r
a
te
o
f
th
e
p
rice
o
f
g
o
ld
,
e
x
p
e
c
ted
p
rice
s
a
n
d
in
tere
st
ra
tes
,
”
J
.
M
a
c
ro
e
c
o
n
.
,
v
o
l.
9
,
n
o
.
1
,
p
p
.
7
1
-
8
2
,
1
9
8
7
,
d
o
i:
1
0
.
1
0
1
6
/S
0
1
6
4
-
0
7
0
4
(
8
7
)
8
0
0
0
7
-
1.
[2
3
]
F
.
J.
F
a
b
o
z
z
i,
S
.
M
.
F
o
c
a
rd
i,
S
.
T
.
Ra
c
h
e
v
,
a
n
d
B.
G
.
A
rsh
a
n
a
p
a
ll
i,
“
M
u
lt
ip
le
L
in
e
a
r
Re
g
re
ss
io
n
,
”
in
T
h
e
Ba
sic
s
o
f
Fi
n
a
n
c
ia
l
Eco
n
o
me
trics
,
2
0
1
4
,
p
p
.
4
1
-
8
0
.
[2
4
]
D.
L
.
Ha
h
s
-
V
a
u
g
h
n
,
R.
G
.
L
o
m
a
x
,
D.
L
.
Ha
h
s
-
V
a
u
g
h
n
,
a
n
d
R.
G
.
L
o
m
a
x
,
“
M
u
lt
ip
le
L
in
e
a
r
Re
g
re
ss
io
n
,
”
in
An
In
tro
d
u
c
ti
o
n
t
o
S
ta
t
isti
c
a
l
C
o
n
c
e
p
ts
,
p
p
.
9
2
3
-
9
9
5
,
2
0
2
0
.
[
2
5
]
T
.
M
.
H
.
H
o
p
e
,
“
L
i
n
e
a
r
r
e
g
r
e
s
s
i
o
n
,
”
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
:
M
e
t
h
o
d
s
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
t
o
B
r
a
i
n
D
i
s
o
r
d
e
r
s
,
p
p
.
6
7
-
81
,
2
0
1
9
.
[2
6
]
F
.
H.
M
.
S
a
ll
e
h
,
S
.
Zain
u
d
i
n
,
a
n
d
S
.
M
.
A
rif
,
“
M
u
lt
ip
le
li
n
e
a
r
re
g
re
ss
io
n
f
o
r
re
c
o
n
stru
c
ti
o
n
o
f
g
e
n
e
re
g
u
lato
ry
n
e
tw
o
rk
s in
so
lv
in
g
c
a
sc
a
d
e
e
rro
r
p
ro
b
lem
s,”
Ad
v
.
Bi
o
i
n
fo
rm
a
ti
c
s
,
v
o
l.
2
0
1
7
,
2
0
1
7
,
d
o
i:
1
0
.
1
1
5
5
/2
0
1
7
/4
8
2
7
1
7
1
.
[2
7
]
S
.
Re
z
a
Kh
a
z
e
,
M
.
M
a
sd
a
ri,
a
n
d
S
.
H
o
jj
a
tk
h
a
h
,
“
A
p
p
li
c
a
ti
o
n
o
f
A
rti
f
icia
l
Ne
u
ra
l
Ne
t
w
o
rk
s
in
Esti
m
a
ti
n
g
P
a
rti
c
i
p
a
ti
o
n
in
El
e
c
ti
o
n
s,”
I
n
t
.
J
.
In
f.
T
e
c
h
n
o
l
.
M
o
d
e
l.
C
o
mp
u
t.
,
v
o
l.
1
,
n
o
.
3
,
p
p
.
2
3
-
3
1
,
2
0
1
3
,
d
o
i:
1
0
.
5
1
2
1
/
ij
it
m
c
.
2
0
1
3
.
1
3
0
3
.
[2
8
]
H.
Ko
c
a
k
a
n
d
T
.
Un
,
“
F
o
re
c
a
stin
g
th
e
G
o
ld
Re
tu
rn
s w
it
h
A
rti
f
ica
l
Ne
u
ra
l
Ne
tw
o
rk
a
n
d
T
ime
S
e
ries
,
”
In
t.
B
u
s.
Res
.
,
v
o
l.
7
,
n
o
.
1
1
,
2
0
1
4
,
d
o
i:
1
0
.
5
5
3
9
/
ib
r.
v
7
n
1
1
p
1
3
9
.
[2
9
]
I.
M
.
S
o
f
ian
,
A
.
K.
Aff
a
n
d
i,
I.
Isk
a
n
d
a
r,
a
n
d
Y.
A
p
rian
i,
“
M
o
n
t
h
ly
ra
in
fa
ll
p
re
d
ictio
n
b
a
se
d
o
n
a
rti
f
icia
l
n
e
u
ra
l
n
e
tw
o
rk
s
w
it
h
b
a
c
k
p
ro
p
a
g
a
ti
o
n
a
n
d
ra
d
ial
b
a
sis
f
u
n
c
ti
o
n
,
”
I
n
t.
J
.
A
d
v
.
In
tell.
I
n
f
o
rm
a
ti
c
s
,
v
o
l.
4
,
n
o
.
2
,
p
p
.
1
5
4
-
1
6
6
,
2
0
1
8
,
d
o
i:
1
0
.
2
6
5
5
5
/i
j
a
i
n
.
v
4
i
2
.
2
0
8
.
[3
0
]
M
.
E.
Bil
d
iri
c
i
a
n
d
F
.
O.
S
o
n
u
stu
n
,
“
T
h
e
e
f
fe
c
ts
o
f
o
il
a
n
d
g
o
l
d
p
ri
c
e
s
o
n
o
il
-
e
x
p
o
rt
in
g
c
o
u
n
tr
ies
,
”
E
n
e
rg
y
S
tr
a
teg
.
Rev
.
,
v
o
l.
2
2
,
p
p
.
2
9
0
-
3
0
2
,
2
0
1
8
,
d
o
i:
1
0
.
1
0
1
6
/j
.
e
sr.
2
0
1
8
.
1
0
.
0
0
4
.
[3
1
]
I.
P
riy
a
d
i,
J.
S
a
n
t
o
n
y
,
a
n
d
J.
Na
’a
m
,
“
Da
ta
M
in
in
g
P
re
d
ic
ti
v
e
M
o
d
e
li
n
g
f
o
r
P
re
d
ictio
n
o
f
G
o
ld
P
rice
s
Ba
se
d
o
n
Do
ll
a
r
Ex
c
h
a
n
g
e
Ra
tes
,
Bi
Ra
tes
a
n
d
W
o
rl
d
Cru
d
e
Oil
P
r
ice
s,”
In
d
o
n
e
s.
J
.
Art
if
.
I
n
tell.
D
a
ta
M
in
.
,
v
o
l.
2
,
n
o
.
2
,
p
p
.
9
3
,
2
0
1
9
,
d
o
i:
1
0
.
2
4
0
1
4
/i
jai
d
m
.
v
2
i2
.
6
8
6
4
.
[3
2
]
L
.
D.
Ru
e
l,
A
.
F
ra
n
ç
o
is,
A
.
G
r
a
u
f
fe
l,
J.
Le
Ro
y
,
a
n
d
T
.
V
a
c
h
e
re
t,
“
Eff
e
c
t
o
f
Be
h
a
v
io
ra
l
F
in
a
n
c
e
o
n
G
o
ld
P
rice
T
re
n
d
,
”
In
t.
J
.
T
ra
d
e
,
Eco
n
.
F
in
a
n
c
.
,
p
p
.
1
2
9
-
1
3
3
,
2
0
1
3
,
d
o
i:
1
0
.
7
7
6
3
/i
j
tef
.
2
0
1
3
.
v
4
.
2
7
2
.
[3
3
]
R.
E.
P
u
tra,
A
.
I.
Nu
rh
id
a
y
a
t,
a
n
d
A
.
Y.
W
ica
k
so
n
o
,
“
Im
p
le
m
e
n
t
a
ti
o
n
o
f
Ne
u
ra
l
Ne
t
w
o
rk
to
d
e
term
in
e
th
e
Ne
w
Co
ll
e
g
e
S
tu
d
e
n
ts,”
in
IOP
Co
n
f
e
re
n
c
e
S
e
rie
s:
M
a
ter
ia
ls
S
c
ien
c
e
a
n
d
En
g
in
e
e
rin
g
,
v
o
l.
2
8
8
,
n
o
.
1
,
2
0
1
8
,
d
o
i
:
1
0
.
1
0
8
8
/
1
7
5
7
-
8
9
9
X
/2
8
8
/1
/
0
1
2
1
2
1
.
[3
4
]
S
.
P
.
S
ireg
a
r
a
n
d
A
.
W
a
n
to
,
“
A
n
a
ly
sis
o
f
A
rti
f
icia
l
Ne
u
ra
l
Ne
t
w
o
rk
A
c
c
u
ra
c
y
Us
in
g
Ba
c
k
p
ro
p
a
g
a
ti
o
n
A
lg
o
rit
h
m
In
P
re
d
ictin
g
P
r
o
c
e
ss
(F
o
re
c
a
stin
g
),
”
IJ
IS
T
ECH
(
In
ter
n
a
ti
o
n
a
l
J
.
In
f.
S
y
st.
T
e
c
h
n
o
l
.
,
v
o
l
.
1
,
n
o
.
1
,
2
0
1
7
,
d
o
i:
1
0
.
3
0
6
4
5
/i
ji
ste
c
h
.
v
1
i1
.
4
.
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
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
22
,
No
.
3
,
J
u
n
e
2
0
2
1
:
1
6
3
5
-
1
6
4
2
1642
[3
5
]
X
.
P
a
n
g
,
Y.
Zh
o
u
,
P
.
W
a
n
g
,
W
.
L
in
,
a
n
d
V
.
C
h
a
n
g
,
“
S
t
o
c
k
m
a
rk
e
t
p
re
d
ictio
n
b
a
se
d
o
n
d
e
e
p
l
o
n
g
sh
o
rt
term
m
e
m
o
r
y
n
e
u
ra
l
n
e
tw
o
rk
,
”
in
CO
M
PL
EX
IS
2
0
1
8
-
Pr
o
c
e
e
d
in
g
s
o
f
th
e
3
r
d
I
n
ter
n
a
t
io
n
a
l
Co
n
fer
e
n
c
e
o
n
Co
m
p
lex
it
y
,
Fu
tu
re
I
n
fo
rm
a
ti
o
n
S
y
ste
ms
a
n
d
Ri
sk
,
v
o
l.
2
0
1
8
-
M
a
rc
h
,
p
p
.
1
0
2
-
1
0
8
,
2
0
1
8
,
d
o
i:
1
0
.
5
2
2
0
/0
0
0
6
7
4
9
9
0
1
0
2
0
1
0
8
.
[3
6
]
M
.
Hiro
n
a
g
a
a
n
d
N.
S
h
im
a
n
o
,
“
Ev
a
lu
a
ti
n
g
th
e
n
o
ise
v
a
rian
c
e
o
f
a
n
im
a
g
e
a
c
q
u
isit
io
n
sy
ste
m
w
it
h
v
a
rio
u
s
re
c
o
n
stru
c
ti
o
n
m
a
tri
c
e
s,”
in
Co
n
f
e
re
n
c
e
o
n
Co
l
o
u
r i
n
Gr
a
p
h
ics
,
Ima
g
i
n
g
,
a
n
d
Vi
sio
n
,
2
0
1
2
,
p
p
.
2
4
7
-
2
5
2
.
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
M
u
sli
Ya
n
to
b
o
rn
in
Ja
k
a
rta
o
n
J
u
ly
7
,
1
9
8
9
.
His
u
n
d
e
rg
ra
d
u
a
te
stu
d
y
w
a
s
c
o
m
p
lete
d
in
2
0
1
2
a
t
Un
iv
e
rsitas
P
u
tra
In
d
o
n
e
sia
Y
P
T
K.
He
c
o
m
p
lete
d
h
is
M
a
ste
rs
d
e
g
re
e
a
t
P
u
t
ra
In
d
o
n
e
sia
Un
iv
e
rsit
y
,
YP
T
K
P
a
d
a
n
g
.
He
c
u
rre
n
tl
y
se
rv
e
s
a
s
a
lec
tu
re
in
t
h
e
In
f
o
rm
a
ti
c
s
En
g
in
e
e
rin
g
stu
d
y
p
ro
g
ra
m
a
t
th
e
Un
iv
e
rsitas
P
u
tra
In
d
o
n
e
sia
Y
P
T
K
P
a
d
a
n
g
.
T
e
a
c
h
in
g
h
isto
ry
th
a
t
h
a
s
b
e
e
n
c
a
rried
o
u
t
sta
rti
n
g
f
ro
m
2
0
1
4
u
n
ti
l
n
o
w
,
su
c
h
a
s
o
b
jec
t
o
rien
ted
p
r
o
g
ra
m
m
in
g
,
m
o
b
il
e
p
ro
g
ra
m
m
in
g
,
a
n
d
c
o
m
p
u
ter
g
ra
p
h
ics
.
P
u
b
li
s
h
e
d
re
se
a
rc
h
h
isto
ry
p
lac
e
s
m
o
re
e
m
p
h
a
si
s
o
n
th
e
a
ti
f
icia
l
n
e
u
ra
l
n
e
tw
o
rk
in
th
e
p
ro
c
e
ss
o
f
id
e
n
ti
f
ica
ti
o
n
a
n
d
p
re
d
icti
o
n
.
S
ig
it
S
a
n
ja
y
a
b
o
rn
in
P
a
d
a
n
g
,
Ju
ly
7
,
1
9
8
9
.
Un
d
e
rg
ra
d
u
a
te
p
r
o
g
ra
m
in
A
c
c
o
u
n
ti
n
g
m
a
jo
r
P
a
d
a
n
g
sta
te
Un
iv
e
rsit
y
c
o
m
p
lete
d
in
2
0
1
3
.
M
a
ste
r
p
ro
g
ra
m
in
M
a
n
a
g
e
m
e
n
t
m
a
jo
r
in
P
a
d
a
n
g
sta
te
Un
iv
e
rsit
y
c
o
m
p
lete
d
in
2
0
1
5
.
Cu
rre
n
t
ly
,
He
is
a
lec
tu
re
r
in
F
a
c
u
lt
y
o
f
Eco
n
o
m
ic
a
n
d
Bu
sin
e
ss
in
Un
iv
e
rsitas
P
u
tra
In
d
o
n
e
sia
Y
P
T
K
P
a
d
a
n
g
.
His
re
se
a
rc
h
f
o
c
u
s
o
n
A
c
c
o
u
n
ti
n
g
,
Bu
sin
e
ss
M
a
n
a
g
e
m
e
n
t
a
n
d
F
in
a
n
c
ial
m
a
n
a
g
e
m
e
n
t.
Yu
la
s
m
i
b
o
rn
in
P
a
d
a
n
g
,
A
u
g
u
st 1
9
,
1
9
7
4
.
U
n
d
e
rg
ra
d
u
a
te p
ro
g
ra
m
in
M
a
rk
e
ti
n
g
M
a
n
a
g
e
m
e
n
t
m
a
jo
r
a
t
P
u
tra
In
d
o
n
e
sia
Un
iv
e
rsity
,
P
a
d
a
n
g
.
M
a
ste
r
P
ro
g
ra
m
in
t
h
e
De
p
a
rtm
e
n
t
o
f
M
a
rk
e
ti
n
g
M
a
n
a
g
e
m
e
n
t
a
t
P
u
tra
In
d
o
n
e
sia
Un
iv
e
rsity
,
P
a
d
a
n
g
a
n
d
Do
c
t
o
r
o
f
M
a
rk
e
ti
n
g
M
a
n
a
g
e
m
e
n
t
S
c
ien
c
e
Do
c
to
ra
te
a
t
UP
I
YA
I
J
a
k
a
rta.
Cu
rre
n
tl
y
w
o
rk
in
g
a
s
a
Lec
tu
re
r
a
n
d
Ch
a
irp
e
rso
n
o
f
M
a
g
ister M
a
n
a
g
e
m
e
n
t
Un
iv
e
rs
it
a
s P
u
tra I
n
d
o
n
e
sia
Y
P
T
K P
a
d
a
n
g
.
Do
d
i
G
u
sw
a
n
d
i
b
o
rn
i
n
Ba
ru
n
g
-
Ba
ru
n
g
Be
lan
tai,
A
g
u
stu
s
3
,
1
9
8
6
.
Un
d
e
rg
ra
d
u
a
te
p
r
o
g
ra
m
in
In
f
o
rm
a
ti
o
n
S
y
ste
m
Un
iv
e
rsitas
P
u
tra
In
d
o
n
e
sia
YP
T
K
c
o
m
p
lete
d
2
0
1
2
.
M
a
ste
r
p
ro
g
ra
m
in
Co
m
p
u
ter
S
c
ien
c
e
a
lso
a
t
Un
iv
e
rsitas
P
u
t
ra
In
d
o
n
e
sa
YP
T
K.
Cu
rre
n
tl
y
,
h
e
is
a
le
c
tu
re
r
in
F
a
c
u
lt
y
o
f
Co
m
p
u
ter
S
c
ien
c
e
in
Un
iv
e
rsitas
P
u
tra
In
d
o
n
e
sia
Y
P
T
K.
His
re
se
a
rc
h
f
o
c
u
s
o
n
d
e
c
isio
n
s
u
p
p
o
rt
sy
ste
m
a
n
d
d
a
ta
m
in
in
g
.
S
y
a
fr
i
Ar
li
s
b
o
r
n
in
P
a
d
a
n
g
o
n
Oc
to
b
e
r
2
3
,
1
9
8
6
.
His
u
n
d
e
rg
ra
d
u
a
te
stu
d
y
w
a
s
c
o
m
p
lete
d
in
2
0
0
9
a
t
Un
iv
e
rsitas
P
u
tra
I
n
d
o
n
e
sia
YP
T
K.
He
c
o
m
p
lete
d
h
i
s
M
a
ste
rs
d
e
g
re
e
a
t
P
u
tra
In
d
o
n
e
sia
Un
iv
e
rsity
,
YP
T
K
P
a
d
a
n
g
.
He
c
u
rre
n
tl
y
se
r
v
e
s
a
s
a
lec
tu
re
in
th
e
I
n
f
o
rm
a
ti
c
s
En
g
in
e
e
rin
g
stu
d
y
p
ro
g
ra
m
a
t
th
e
Un
iv
e
rsitas
P
u
tra
I
n
d
o
n
e
sia
Y
P
T
K P
a
d
a
n
g
.
T
e
a
c
h
in
g
h
ist
o
ry
th
a
t
h
a
s
b
e
e
n
c
a
rried
o
u
t
sta
rti
n
g
f
ro
m
2
0
1
1
u
n
ti
l
n
o
w
,
su
c
h
a
s
d
a
tab
a
se
a
n
d
d
ig
it
a
l
im
a
g
e
p
ro
c
e
ss
in
g
.
P
u
b
li
s
h
e
d
re
se
a
rc
h
h
isto
ry
p
lac
e
s
m
o
re
e
m
p
h
a
sis
o
n
th
e
a
ti
f
icia
l
n
e
u
ra
l
n
e
tw
o
rk
a
n
d
d
ig
it
a
l
im
a
g
e
p
ro
c
e
ss
in
g
.
Evaluation Warning : The document was created with Spire.PDF for Python.