I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
p
ute
r
E
ng
in
ee
ring
(
I
J
E
CE
)
Vo
l.
7
,
No
.
5
,
Octo
b
e
r
2
0
1
7
,
p
p
.
2
7
46
~2
756
I
SS
N:
2
0
8
8
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v7
i
5
.
pp
2
7
4
6
-
2
756
2746
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
jo
u
r
n
a
l.c
o
m/o
n
lin
e/in
d
ex
.
p
h
p
/I
JE
C
E
Ena
bling
Ex
ternal Factors
for Infla
tion Ra
te
F
o
recas
ting
using
Fu
zz
y
Ne
ura
l Sys
te
m
Na
dia
Ro
o
s
m
a
lita
Sa
ri
1
,
Wa
y
a
n F
irda
us
M
a
hm
ud
y
2
,
Aj
i P
ra
s
et
y
a
Wiba
wa
3
,
E
lt
a
So
n
a
litha
4
1,
2
F
a
c
u
lt
y
o
f
Co
m
p
u
ter S
c
ien
c
e
,
Un
iv
e
rsitas
Bra
w
ij
a
y
a
4
F
a
c
u
lt
y
o
f
In
f
o
r
m
a
ti
o
n
T
e
c
h
n
o
l
o
g
y
,
Un
iv
e
rsit
y
o
f
M
e
rd
e
k
a
M
a
lan
g
3
F
a
c
u
lt
y
o
f
En
g
in
e
e
rin
g
,
Un
iv
e
rsitas
Ne
g
e
ri
M
a
lan
g
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Dec
10
,
2
0
1
6
R
ev
i
s
ed
J
u
n
7
,
2
0
1
7
A
cc
ep
ted
A
u
g
11
,
2
0
1
7
In
f
latio
n
is
t
h
e
ten
d
e
n
c
y
o
f
in
c
re
a
sin
g
p
rice
s
o
f
g
o
o
d
s
i
n
g
e
n
e
ra
l
a
n
d
h
a
p
p
e
n
s
c
o
n
ti
n
u
o
u
sly
.
In
d
o
n
e
sia
'
s
e
c
o
n
o
m
y
w
il
l
d
e
c
li
n
e
if
in
f
latio
n
is
n
o
t
c
o
n
tr
o
ll
e
d
p
ro
p
e
rly
.
T
o
c
o
n
tro
l
th
e
in
f
latio
n
ra
te
re
q
u
ired
a
n
i
n
f
latio
n
ra
te
f
o
re
c
a
stin
g
in
In
d
o
n
e
sia
.
T
h
e
f
o
re
c
a
stin
g
re
s
u
lt
w
il
l
b
e
u
se
d
a
s
in
f
o
r
m
a
ti
o
n
to
t
h
e
g
o
v
e
rn
m
e
n
t
in
o
rd
e
r
to
k
e
e
p
th
e
in
f
latio
n
ra
te
sta
b
le.
T
h
is
stu
d
y
p
ro
p
o
se
s
F
u
z
z
y
N
e
u
ra
l
S
y
ste
m
(F
NS)
to
f
o
re
c
a
st
th
e
in
f
latio
n
ra
te.
T
h
is
stu
d
y
u
se
s
h
isto
rica
l
d
a
ta
a
n
d
e
x
tern
a
l
f
a
c
t
o
rs
a
s
th
e
p
a
ra
m
e
ters
.
T
h
e
e
x
t
e
rn
a
l
f
a
c
to
r
u
sin
g
in
th
is
stu
d
y
is
v
e
r
y
i
m
p
o
rtan
t,
w
h
ich
in
f
latio
n
ra
te
is
n
o
t
o
n
ly
a
ff
e
c
t
e
d
b
y
th
e
h
isto
rica
l
d
a
ta.
Ex
tern
a
l
fa
c
to
r
u
se
d
a
re
f
o
u
r
e
x
tern
a
l
f
a
c
t
o
rs
w
h
ich
e
a
c
h
f
a
c
to
r
h
a
s
tw
o
f
u
z
z
y
se
t.
W
h
il
e
h
ist
o
rica
l
d
a
ta
is
d
iv
id
e
d
in
to
t
h
re
e
in
p
u
t
v
a
riab
les
w
it
h
th
re
e
f
u
z
z
y
se
ts.
Th
e
c
o
m
b
in
a
ti
o
n
o
f
th
re
e
in
p
u
t
v
a
r
iab
les
a
n
d
f
o
u
r
e
x
tern
a
l
f
a
c
to
rs
w
il
l
g
e
n
e
ra
t
e
to
o
m
a
n
y
ru
les
.
G
e
n
e
ra
te
o
f
ru
l
e
s
w
it
h
to
o
m
a
n
y
a
m
o
u
n
ts
w
il
l
les
s
e
ffe
c
ti
v
e
a
n
d
h
a
v
e
lo
w
e
r
a
c
c
u
ra
c
y
.
T
h
e
n
o
v
e
lt
y
is
n
e
e
d
e
d
to
m
in
ima
li
z
e
th
e
a
m
o
u
n
t
o
f
ru
les
b
y
u
sin
g
tw
o
ste
p
s
f
u
z
z
y
.
T
o
e
v
a
lu
a
te
th
e
f
o
re
c
a
stin
g
re
su
lt
s,
Ro
o
t
M
e
a
n
s
S
q
u
a
re
Err
o
r
(RM
S
E)
tec
h
n
iq
u
e
is
u
se
d
.
F
u
z
z
y
In
f
e
re
n
c
e
S
y
ste
m
S
u
g
e
n
o
u
se
d
a
s th
e
c
o
m
p
a
riso
n
m
e
th
o
d
.
T
h
e
stu
d
y
re
su
lt
s
sh
o
w
th
a
t
F
NS
h
a
s
a
b
e
tt
e
r
p
e
r
f
o
r
m
a
n
c
e
th
a
n
th
e
c
o
m
p
a
riso
n
m
e
th
o
d
w
it
h
RM
S
E
t
h
a
t
is
1
.
8
1
.
K
ey
w
o
r
d
s
:
Fo
r
e
ca
s
tin
g
Fu
zz
y
n
e
u
r
al
s
y
s
te
m
(
FN
S)
I
n
f
lat
io
n
R
o
o
t
m
ea
n
s
q
u
ar
e
e
r
r
o
r
(
R
MSE
)
Co
p
y
rig
h
t
©
2
0
1
7
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
:
Nad
ia
R
o
o
s
m
alita
Sar
i
,
Facu
lt
y
o
f
C
o
m
p
u
ter
Scien
ce
,
Un
i
v
er
s
ita
s
B
r
a
w
ij
a
y
a,
J
alan
Vete
r
an
,
Ma
lan
g
,
I
n
d
o
n
e
s
ia
,
Facu
lt
y
o
f
I
n
f
o
r
m
a
tio
n
T
ec
h
n
o
lo
g
y
,
Un
iv
er
s
it
y
o
f
Me
r
d
ek
a
Ma
lan
g
,
J
alan
Dien
g
R
a
y
a,
M
alan
g
,
I
n
d
o
n
esia
,
E
m
ail:
n
ad
iar
o
o
s
m
alita
s
ar
i@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
E
co
n
o
m
ic
g
r
o
w
t
h
ca
n
b
e
u
s
ed
to
ass
ess
th
e
d
ev
elo
p
m
en
t
o
f
a
co
u
n
tr
y
.
E
co
n
o
m
ic
g
r
o
w
th
m
ea
n
s
th
e
p
h
y
s
ical
d
ev
e
lo
p
m
en
t
o
f
g
o
o
d
s
an
d
s
er
v
ice
s
p
r
o
d
u
ctio
n
ex
i
s
tin
g
i
n
a
co
u
n
tr
y
[
1
]
.
On
t
h
e
o
th
er
h
an
d
,
i
n
f
latio
n
is
th
e
te
n
d
en
c
y
o
f
i
n
cr
ea
s
i
n
g
p
r
ices
o
f
g
o
o
d
s
in
g
en
er
al
an
d
h
ap
p
en
s
co
n
s
tan
tl
y
[
2
]
.
T
h
er
ef
o
r
e,
it
m
a
y
in
f
lu
e
n
ce
t
h
e
n
atio
n
al
ec
o
n
o
m
ic
g
r
o
w
t
h
.
I
n
o
th
er
w
o
r
d
s
,
in
f
latio
n
co
u
ld
b
e
u
s
ed
as
a
to
o
l
to
m
ea
s
u
r
e
th
e
ec
o
n
o
m
ic
d
ev
elo
p
m
e
n
t o
f
a
co
u
n
tr
y
.
I
n
f
lat
io
n
ca
n
o
cc
u
r
d
u
e
to
th
e
h
i
g
h
co
n
s
u
m
p
tiv
e
p
atter
n
s
o
f
s
o
ciet
y
.
Fo
r
ex
a
m
p
le,
th
e
h
i
g
h
e
m
p
lo
y
m
en
t
o
p
p
o
r
tu
n
itie
s
cr
ea
te
s
a
h
ig
h
le
v
el
o
f
i
n
co
m
e
an
d
f
u
r
t
h
er
r
aises
e
x
p
en
d
it
u
r
es
th
at
e
x
ce
ed
t
h
e
ec
o
n
o
m
ic
ab
ilit
y
o
f
e
x
ce
ed
i
n
g
g
o
o
d
s
an
d
s
er
v
ices.
So
t
h
at
t
h
e
co
n
s
u
m
p
ti
v
e
p
atter
n
s
o
f
s
o
ciet
y
w
il
l
i
n
cr
ea
s
e.
Mo
r
eo
v
er
,
in
f
latio
n
ca
n
also
o
cc
u
r
d
u
e
to
in
cr
ea
s
ed
p
r
ic
es
o
f
i
m
p
o
r
ts
f
r
o
m
t
h
eir
r
eg
i
o
n
s
.
T
h
e
lo
w
er
t
h
e
d
eg
r
ee
o
f
i
m
p
o
r
ted
g
o
o
d
s
co
m
p
e
titi
o
n
to
d
o
m
es
tic
p
r
o
d
u
cts,
th
e
g
r
ea
ter
th
e
i
m
p
ac
t
h
ap
p
en
s
to
th
e
c
h
an
g
es
i
n
th
e
p
r
ice
o
f
i
m
p
o
r
ted
g
o
o
d
s
t
o
th
e
in
f
latio
n
.
I
n
f
latio
n
is
o
f
t
en
en
co
u
n
ter
ed
b
y
d
ev
e
lo
p
in
g
co
u
n
tr
ies,
s
u
c
h
as
I
n
d
o
n
esi
a.
I
n
d
o
n
es
ia
'
s
ec
o
n
o
m
y
w
i
ll
d
ec
lin
e
i
f
in
f
latio
n
i
s
n
o
t
co
n
tr
o
lled
p
r
o
p
e
r
ly
.
O
n
e
o
f
th
e
p
r
o
b
le
m
s
ca
u
s
ed
b
y
in
f
latio
n
i
s
co
n
ti
n
u
o
u
s
c
u
r
r
en
c
y
d
eb
ase
m
e
n
t.
I
n
d
ir
ec
tl
y
,
t
h
e
d
eb
ase
m
e
n
t
m
a
y
a
f
f
ec
t
to
t
h
e
g
lo
b
al
tr
ad
in
g
ac
ti
v
itie
s
.
As
a
r
esu
lt,
it
m
a
y
i
n
cr
ea
s
e
t
h
e
co
s
t
o
f
d
aily
n
ec
es
s
itie
s
an
d
r
aise
th
e
s
p
r
ea
d
o
f
u
n
e
m
p
lo
y
m
e
n
t q
u
a
n
tit
y
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
E
n
a
b
lin
g
E
xtern
a
l F
a
cto
r
s
fo
r
I
n
fla
tio
n
R
a
te
F
o
r
ec
a
s
tin
g
u
s
i
n
g
F
u
z
z
y
.
.
.
(
N
a
d
ia
R
o
o
s
ma
lita
S
a
r
i
)
2747
Fo
r
ec
asti
n
g
s
y
s
te
m
i
s
r
eq
u
ir
ed
to
co
n
tr
o
l th
e
in
f
latio
n
r
ate
r
eq
u
ir
ed
.
I
t a
im
s
to
p
r
o
v
id
e
in
f
o
r
m
atio
n
t
o
th
e
g
o
v
er
n
m
en
t
f
o
r
an
tic
ip
atin
g
t
h
e
f
u
t
u
r
e
i
n
f
latio
n
.
On
t
h
e
o
th
er
h
a
n
d
,
t
h
e
f
o
r
ec
asti
n
g
r
es
u
lts
ca
n
b
e
u
tili
ze
d
b
y
t
h
e
co
m
m
u
n
it
y
at
lar
g
e.
F
o
r
in
v
esto
r
s
,
t
h
e
f
o
r
ec
asti
n
g
r
esu
lt
s
ca
n
b
e
u
s
ed
as
in
v
est
m
en
t
in
f
o
r
m
a
tio
n
.
T
h
e
h
ig
h
i
n
f
latio
n
r
ate
m
ea
n
s
t
h
a
t
th
e
i
n
v
e
s
to
r
co
u
ld
in
cr
ea
s
e
th
e
i
n
v
e
s
t
m
en
ts
o
n
p
r
o
p
er
t
y
is
p
o
s
s
ib
l
y
m
o
r
e
p
r
o
f
ita
b
le.
Fo
r
ec
asti
n
g
is
m
ad
e
b
ased
o
n
h
i
s
to
r
ical
d
ata
w
it
h
ti
m
e
-
s
er
ie
s
a
n
al
y
s
i
s
tec
h
n
iq
u
e,
o
f
t
h
e
p
r
ev
io
u
s
m
o
n
t
h
s
t
h
e
in
f
lat
io
n
o
cc
u
r
s
.
T
h
is
s
t
u
d
y
w
i
ll
also
u
s
e
s
o
m
e
e
x
ter
n
al
f
ac
to
r
s
to
d
eter
m
i
n
e
t
h
e
lev
el
o
f
in
f
latio
n
.
His
to
r
ical
d
ata
a
n
d
ex
ter
n
al
f
ac
to
r
s
ar
e
u
s
ed
a
s
a
n
i
n
p
u
t
v
ar
iab
le,
w
h
ile
t
h
e
o
u
tp
u
t
d
ata
is
t
h
e
f
o
r
ec
asti
n
g
r
esu
lt
s
.
E
x
ter
n
al
f
ac
to
r
s
u
s
ed
in
t
h
is
s
t
u
d
y
i
n
cl
u
d
e
th
e
C
o
n
s
u
m
er
P
r
ice
I
n
d
ex
(
C
P
I
)
,
th
e
B
I
R
ate,
Mo
n
e
y
s
u
p
p
l
y
,
a
n
d
E
x
ch
a
n
g
e
r
ate.
T
h
e
ex
ter
n
al
f
ac
to
r
s
h
a
v
e
b
ee
n
u
s
ed
in
s
e
v
er
al
s
t
u
d
ies [
3
-
8
]
.
I
n
f
lat
io
n
r
ate
f
o
r
ec
ast
in
g
h
a
s
b
ee
n
d
o
n
e
b
y
Mo
s
er
,
et
al
[
9
]
an
d
[
1
0
]
.
Mo
s
er
,
et
al
u
s
ed
Au
to
R
eg
r
es
s
io
n
I
n
te
g
r
ated
Mo
v
i
n
g
Av
er
ag
e
(
A
R
I
M
A
)
to
f
o
r
ec
ast
t
h
e
i
n
f
latio
n
r
ate.
T
h
en
B
ac
iu
u
s
ed
s
to
ch
a
s
tic
m
o
d
el
to
f
o
r
ec
ast th
e
i
n
f
latio
n
r
ate
[
1
0
]
.
R
ec
en
t
s
t
u
d
y
h
a
s
u
s
ed
B
ac
k
p
r
o
p
ag
atio
n
Ne
u
r
al
Net
w
o
r
k
(
N
N)
as
a
m
et
h
o
d
to
f
o
r
ec
ast
th
e
in
f
latio
n
r
ate.
Sar
i,
et
al
u
s
ed
h
is
to
r
ical
d
ata
an
d
C
P
I
as
in
p
u
t
v
ar
iab
les.
A
cc
u
r
ac
y
o
b
tai
n
ed
u
s
i
n
g
m
et
h
o
d
B
ac
k
p
r
o
p
ag
atio
n
NN
m
et
h
o
d
is
0
.
2
0
4
[
2
]
.
T
h
e
ac
cu
r
ac
y
tech
n
iq
u
e
u
s
ed
i
s
t
h
e
R
o
o
t
Me
an
Sq
u
ar
e
E
r
r
o
r
(
R
MSE
)
.
Neu
r
al
Net
w
o
r
k
h
as
th
e
ad
v
an
tag
e
t
h
at
is
m
o
r
e
f
le
x
ib
le
in
ter
m
s
o
f
ad
ap
tin
g
a
n
d
h
as
a
g
o
o
d
ab
ilit
y
to
lear
n
.
Neu
r
al
Net
w
o
r
k
is
ab
le
to
d
etec
t
p
atter
n
s
an
d
tr
en
d
s
in
v
ar
io
u
s
d
ata
s
ets
[
1
2
]
,
b
u
t
Neu
r
al
Net
w
o
r
k
is
w
ea
k
in
e
x
p
lain
in
g
s
o
m
e
th
i
n
g
.
T
h
er
ef
o
r
e,
it
n
ee
d
s
to
b
e
co
m
b
in
ed
w
it
h
f
u
zz
y
lo
g
ic
th
a
t
h
as
a
g
o
o
d
ab
ilit
y
in
ex
p
lain
i
n
g
.
T
h
is
s
tu
d
y
i
s
an
a
d
v
an
ce
d
s
t
u
d
y
f
r
o
m
t
h
e
p
r
ev
i
o
u
s
s
t
u
d
y
[
2
]
.
T
h
is
s
tu
d
y
p
r
o
p
o
s
es
Fu
zz
y
Ne
u
r
al
S
y
s
te
m
(
F
NS)
as a
m
e
th
o
d
th
a
t is ca
p
ab
le
to
p
r
o
d
u
c
e
a
b
etter
ac
cu
r
ac
y
as c
o
m
p
ar
ed
to
th
e
p
r
ev
io
u
s
s
t
u
d
y
[
2
]
.
2.
CURR
E
NT
S
T
UDY
Z
h
an
g
an
d
L
i
[
1
3
]
u
s
ed
th
e
S
VR
m
o
d
el
to
f
o
r
ec
ast
in
f
latio
n
r
ate
in
C
h
in
a.
SV
R
is
a
m
et
h
o
d
u
s
ed
in
m
ak
in
g
d
ec
i
s
io
n
s
.
T
h
is
m
et
h
o
d
ca
n
b
e
co
n
s
id
er
ed
as
t
h
e
i
m
p
r
o
v
e
m
e
n
t
o
f
L
i
n
ea
r
R
eg
r
es
s
io
n
,
w
h
er
e
th
i
s
m
et
h
o
d
is
ab
le
to
g
en
er
ate
a
f
u
n
ctio
n
w
it
h
w
a
v
y
r
es
u
lt
s
f
o
llo
w
t
h
e
d
ata
p
at
h
f
o
r
m
ed
.
T
h
er
ef
o
r
e,
th
e
f
o
r
ec
asti
n
g
r
es
u
lt
b
ec
o
m
es
m
o
r
e
ac
cu
r
ate
as
co
m
p
ar
ed
to
lin
ea
r
r
eg
r
ess
io
n
.
T
h
e
ac
cu
r
ac
y
o
f
th
e
s
y
s
te
m
u
s
in
g
th
e
R
M
SE
is
0
.
1
.
I
n
th
e
p
r
ev
io
u
s
s
tu
d
y
,
Sar
i
[
2
]
u
s
ed
B
ac
k
p
r
o
p
ag
atio
n
Neu
r
al
Net
w
o
r
k
to
f
o
r
ec
ast
th
e
i
n
f
latio
n
r
ate
.
T
h
e
s
tu
d
y
u
s
ed
h
i
s
to
r
ical
d
ata
an
d
C
P
I
as
in
p
u
t
v
ar
iab
le.
T
h
e
R
MSE
o
f
th
e
s
y
s
te
m
o
b
tain
ed
b
y
u
s
i
n
g
B
ac
k
p
r
o
p
ag
atio
n
Neu
r
al
Net
wo
r
k
is
0
.
2
0
4
.
I
n
ad
d
itio
n
to
f
o
r
ec
ast
i
n
f
latio
n
r
ate,
Ne
u
r
al
Ne
t
w
o
r
k
is
also
u
s
ed
f
o
r
f
o
r
ec
asti
n
g
t
h
e
r
is
in
g
d
e
m
an
d
f
o
r
elec
tr
ic
v
eh
icle
s
ap
p
licab
le
to
I
n
d
ian
R
o
ad
C
o
n
d
itio
n
s
[
1
4
]
.
B
ased
o
n
th
eir
s
t
u
d
y
,
P
o
o
r
an
i
an
d
Mu
r
u
g
an
[
15]
s
aid
th
at
Neu
r
al
Net
w
o
r
k
i
s
p
ar
ticu
lar
l
y
e
f
f
ec
ti
v
e
i
n
h
a
n
d
lin
g
o
u
tl
ier
s
.
Neu
r
al
Net
w
o
r
k
h
as
a
g
o
o
d
ab
ilit
y
to
lear
n
,
b
u
t
th
is
m
o
d
el
h
as
a
w
ea
k
n
es
s
i
n
e
x
p
lai
n
in
g
th
i
n
g
s
.
T
h
er
ef
o
r
e
a
Fu
zz
y
Neu
r
al
S
y
s
te
m
(
F
NS)
a
s
th
e
i
n
f
latio
n
r
ate
f
o
r
ec
asti
n
g
m
et
h
o
d
to
im
p
r
o
v
e
t
h
e
f
o
r
ec
as
tin
g
ac
cu
r
ac
y
.
I
n
ter
m
s
o
f
a
f
o
r
ec
asti
n
g
,
f
u
zz
y
lo
g
ic
h
as
b
ee
n
s
u
cc
ess
f
u
ll
y
i
m
p
le
m
e
n
ted
in
th
e
f
o
r
ec
asti
n
g
p
r
o
b
lem
s
u
s
i
n
g
ti
m
e
-
s
er
ies
d
ata
[
1
6
]
.
F
u
zz
y
Ne
u
r
al
S
y
s
te
m
(
FN
S)
h
as
b
ee
n
u
s
ed
b
y
[
1
7
]
f
o
r
m
o
d
elin
g
th
e
n
o
n
li
n
ea
r
s
y
s
te
m
.
W
h
ile
W
ib
a
w
a
et
al
[
1
2
]
u
s
ed
a
co
m
b
in
atio
n
o
f
f
u
zz
y
lo
g
ic
a
n
d
n
e
u
r
al
n
et
wo
r
k
to
f
o
r
ec
ast
th
e
f
o
r
eig
n
ex
c
h
an
g
e.
T
h
is
le
v
el
o
f
ac
cu
r
ac
y
g
e
n
er
ated
b
y
u
s
in
g
Me
an
Sq
u
ar
e
E
r
r
o
r
(
MSE
)
tec
h
n
iq
u
e
is
0
.
2
0
1
.
3.
T
H
E
DA
T
A
S
E
T
T
h
is
s
tu
d
y
u
s
es
t
h
e
d
ataset
i
n
th
e
f
o
r
m
o
f
h
is
to
r
ical
d
ata
f
r
o
m
B
a
n
k
I
n
d
o
n
esia
[
1
8
]
an
d
th
e
B
ad
an
P
u
s
at
Stati
s
ti
k
[
1
9
]
.
T
h
e
d
ata
r
ec
o
r
d
th
at
u
s
ed
is
9
9
d
ata
r
an
g
in
g
f
r
o
m
Octo
b
er
2
0
0
5
–
Desem
b
er
2
0
1
3
.
P
ar
am
eter
s
u
s
ed
in
th
is
s
t
u
d
y
ar
e
h
is
to
r
ical
d
ata
w
it
h
ti
m
e
-
s
er
ies
an
al
y
s
is
(
b
-
1
,
b
-
2
,
b
-
3
)
.
b
-
1
p
ar
am
eter
r
ep
r
esen
t
s
a
m
o
n
th
b
ef
o
r
e,
b
-
2
r
ep
r
esen
ts
t
w
o
m
o
n
t
h
s
b
e
f
o
r
e,
an
d
b
-
3
r
ep
r
e
s
en
t
s
th
r
ee
m
o
n
t
h
s
b
ef
o
r
e.
T
h
is
s
t
u
d
y
al
s
o
u
s
e
s
e
v
er
al
ex
ter
n
al
f
ac
to
r
s
w
h
ic
h
a
f
f
ec
t
to
th
e
i
n
f
latio
n
r
ate,
lik
e
C
P
I
,
B
I
r
ate,
Mo
n
ey
Su
p
p
l
y
,
a
n
d
E
x
ch
a
n
g
e
R
ate.
T
h
o
s
e
p
ar
am
eter
s
u
s
ed
as
i
n
p
u
t
v
ar
iab
le
i
n
i
n
f
latio
n
r
ate
f
o
r
ec
asti
n
g
.
W
h
er
ea
s
o
u
tp
u
t
v
ar
iab
le
is
in
th
e
f
o
r
m
o
f
th
e
i
n
f
latio
n
r
ate
f
o
r
ec
asti
n
g
r
es
u
lt
i
n
I
n
d
o
n
e
s
ia.
T
ab
le
1
an
d
T
a
b
le
2
ar
e
s
h
o
w
i
n
g
t
h
e
d
ata
r
ec
o
r
d
to
ea
c
h
v
ar
iab
le.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
J
E
C
E
Vo
l.
7
,
No
.
5
,
Octo
b
er
2
0
1
7
:
2
7
4
6
–
2
7
5
6
2748
T
ab
le
1
.
I
n
ter
n
al
Var
iab
le
B
ased
o
n
T
im
e
Ser
ies
An
al
y
s
i
s
D
a
t
e
A
c
t
u
a
l
d
a
t
a
b
-
1
b
-
2
b
-
3
D
e
c
-
13
8
.
3
8
8
.
3
7
8
.
3
2
8
.
4
0
N
o
v
-
13
8
.
3
7
8
.
3
2
8
.
4
0
8
.
7
9
O
c
t
-
13
8
.
3
2
8
.
4
0
8
.
7
9
8
.
6
1
S
e
p
-
13
8
.
4
0
8
.
7
9
8
.
6
1
5
.
9
0
A
u
g
-
13
8
.
7
9
8
.
6
1
5
.
9
0
5
.
4
7
Ju
l
-
13
8
.
6
1
5
.
9
0
5
.
4
7
5
.
5
7
Ju
n
-
13
5
.
9
0
5
.
4
7
5
.
5
7
5
.
9
0
M
a
y
-
13
5
.
4
7
5
.
5
7
5
.
9
0
5
.
3
1
A
p
r
-
13
5
.
5
7
5
.
9
0
5
.
3
1
4
.
5
7
M
a
r
-
13
5
.
9
0
5.
31
4
.
5
7
4
.
3
0
F
e
b
-
13
5
.
3
1
4
.
5
7
4
.
3
0
4
.
3
2
Jan
-
13
4
.
5
7
4
.
3
0
4
.
3
2
4
.
6
1
…
…
…
…
…
O
c
t
-
05
1
7
.
8
9
9
.
0
6
8
.
3
3
7
.
8
4
T
ab
le
2.
E
x
ter
n
al
Var
iab
es
D
a
t
e
A
c
t
u
a
l
d
a
t
a
C
P
I
M
o
n
e
y
su
p
p
l
y
B
I
R
a
t
e
Ex
c
h
a
n
g
e
r
a
t
e
D
e
c
-
13
8
.
3
8
1
4
6
.
8
4
8
7
0
4
5
5
.
0
0
7
.
5
0
1
1
9
7
7
.
0
0
N
o
v
-
13
8
.
3
7
1
4
6
.
04
8
5
6
1
4
6
.
0
0
7
.
2
5
1
1
2
3
4
.
0
0
O
c
t
-
13
8
.
3
2
1
4
5
.
8
7
8
6
7
7
2
1
.
0
0
7
.
2
5
1
1
6
1
3
.
0
0
S
e
p
-
13
8
.
4
0
1
4
5
.
7
4
8
5
5
7
8
3
.
0
0
7
.
0
0
1
0
9
2
4
.
0
0
A
u
g
-
13
8
.
7
9
1
4
6
.
2
5
8
7
9
9
8
6
.
0
0
6
.
5
0
1
0
2
7
8
.
0
0
Ju
l
-
13
8
.
6
1
1
4
4
.
6
3
8
5
8
5
5
7
.
0
0
6
.
5
0
9
9
2
9
.
0
0
Ju
n
-
13
5
.
9
0
1
4
0
.
0
3
8
2
2
9
3
0
.
0
0
6
.
0
0
9
8
0
2
.
0
0
M
a
y
-
13
5
.
4
7
1
3
8
.
6
0
8
3
2
2
7
3
.
0
0
5
.
7
5
9
7
2
2
.
0
0
A
p
r
-
13
5
.
5
7
1
3
8
.
6
4
8
1
0
1
1
2
.
0
0
5
.
7
5
9
7
1
9
.
0
0
M
a
r
-
13
5
.
9
0
1
3
8
.
7
8
7
8
6
6
0
6
.
0
0
5
.
7
5
9
6
6
7
.
0
0
F
e
b
-
13
5
.
3
1
1
3
7
.
9
1
7
8
7
9
1
6
.
0
0
5
.
7
5
9
6
9
8
.
0
0
Jan
-
13
4
.
5
7
1
3
6
.
8
8
8
4
1
7
2
2
.
0
0
5
.
7
5
9
6
5
1
.
5
0
…
…
…
…
…
…
O
c
t
-
05
1
7
.
8
9
1
3
5
.
1
5
2
7
3
9
5
4
.
0
0
1
1
.
0
0
10
3
1
0
.
0
0
4.
T
WO
S
T
A
G
E
S F
U
Z
Z
Y
L
O
G
I
C
F
O
R
I
NF
L
A
T
I
O
N
R
A
T
E
F
O
R
E
CAS
T
I
N
G
Fu
zz
y
lo
g
ic
u
s
ed
as
co
m
p
ar
is
o
n
m
et
h
o
d
as
w
el
l
as
p
ar
t
o
f
F
u
zz
y
Ne
u
r
al
S
y
s
te
m
(
FN
S)
m
eth
o
d
.
T
h
e
o
u
tp
u
t
g
en
er
ated
b
y
f
u
zz
y
lo
g
ic
w
ill
b
e
u
s
ed
as
i
n
p
u
t
to
t
h
e
Neu
r
al
Net
w
o
r
k
.
Fu
zz
y
I
n
f
er
en
ce
S
y
s
t
e
m
(
FIS)
Su
g
en
o
i
s
a
m
o
d
el
f
r
o
m
f
u
zz
y
lo
g
ic
u
s
ed
to
f
o
r
ec
ast
th
e
in
f
l
atio
n
r
ate
i
n
I
n
d
o
n
esia.
FIS
S
u
g
en
o
d
e
v
elo
p
ed
b
y
T
ak
ag
h
i,
S
u
g
e
n
o
,
an
d
Ka
n
g
(
T
SK)
[
2
0
]
.
T
h
is
Fu
zz
y
I
n
f
er
e
n
ce
S
y
s
te
m
ch
o
s
en
b
ec
au
s
e
t
h
is
m
o
d
el
is
s
u
i
tab
le
f
o
r
ti
m
e
-
s
er
ie
s
d
ata
s
u
ch
a
s
in
t
h
e
s
t
u
d
y
[
1
6
]
.
FIS
Su
g
en
o
co
n
s
i
s
ts
o
f
t
h
r
ee
p
r
o
ce
s
s
es,
i
n
clu
d
i
n
g
th
e
f
u
zz
if
ica
tio
n
p
r
o
ce
s
s
,
f
u
zz
y
in
f
er
en
ce
e
n
g
i
n
e,
an
d
d
ef
u
zz
i
f
ic
atio
n
.
4
.
1
.
F
uzzif
ica
t
io
n
I
n
p
u
t
v
ar
iab
les
in
t
h
is
s
t
u
d
y
w
ill
b
e
d
iv
id
ed
i
n
to
t
w
o
o
r
m
o
r
e
f
u
zz
y
s
et
s
.
F
u
zz
y
s
et
is
a
u
n
io
n
r
ep
r
esen
t
in
g
ce
r
tai
n
cir
cu
m
s
t
an
ce
s
in
a
f
u
zz
y
v
ar
iab
le
[
2
1
]
.
L
i
n
g
u
i
s
tic
v
ar
iab
les
ar
e
u
n
i
ted
w
ith
f
u
zz
y
s
et,
ea
ch
o
f
w
h
ic
h
h
a
s
a
m
e
m
b
er
s
h
ip
f
u
n
c
tio
n
t
h
at
h
a
s
b
ee
n
d
ef
in
ed
[
2
2
]
.
Me
m
b
er
s
h
ip
f
u
n
ct
io
n
is
a
cu
r
v
e
s
h
o
w
i
n
g
th
e
r
ep
r
esen
tatio
n
o
f
t
h
e
i
n
p
u
t
p
o
in
t
d
ata
i
n
to
m
e
m
b
er
s
h
ip
v
al
u
es
th
at
h
a
s
i
n
t
er
v
al
b
et
w
ee
n
0
-
1
.
Fu
n
ctio
n
to
d
eter
m
in
e
th
e
m
e
m
b
er
s
h
ip
v
al
u
e
is
d
escr
ib
ed
b
y
T
r
ian
g
u
lar
f
u
zz
y
n
u
m
b
er
[
2
3
]
.
Fig
u
r
e
1
s
h
o
w
s
an
ex
a
m
p
le
o
f
a
T
r
ian
g
u
lar
f
u
zz
y
n
u
m
b
er
r
ep
r
esen
ti
n
g
i
n
p
u
t
v
ar
iab
les
b
-
1
,
b
-
2
an
d
b
-
3
[
2
4
]
.
Fig
u
r
e
2
r
ep
r
esen
ts
th
e
e
x
ter
n
al
v
ar
iab
l
es.
Fig
u
r
e
1
.
An
ex
a
m
p
le
o
f
v
ar
iab
le
in
p
u
t ti
m
e
-
s
er
ies
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
E
n
a
b
lin
g
E
xtern
a
l F
a
cto
r
s
fo
r
I
n
fla
tio
n
R
a
te
F
o
r
ec
a
s
tin
g
u
s
i
n
g
F
u
z
z
y
.
.
.
(
N
a
d
ia
R
o
o
s
ma
lita
S
a
r
i
)
2749
µ
(
)
=
{
1
10
−
5
0
≤
5
5
<
<
10
≥
10
(1
)
µ
(
)
=
{
0
−
10
5
1
≤
10
0
<
<
15
≥
15
(2
)
µ
(
)
=
{
0
−
(
−
5
)
5
15
−
5
1
(
≤
5
)
(
≥
15
)
5
<
<
1
0
10
<
<
15
(3
)
Fig
u
r
e
2
.
An
ex
a
m
p
le
o
f
v
ar
iab
le
in
p
u
t e
x
ter
n
al
f
ac
to
r
s
µ
(
)
=
{
1
250
−
100
0
≤
1
5
0
150
<
<
250
≥
250
(4
)
µ
(
)
=
{
0
−
150
100
1
≤
150
150
<
<
250
≥
250
(5
)
4
.
2
.
F
uzzy
I
nfe
re
nce
E
ng
i
ne
T
h
e
r
esu
lts
o
f
t
h
e
ca
l
c
u
latio
n
p
r
o
ce
s
s
o
f
f
u
zz
y
m
e
m
b
er
s
h
ip
v
al
u
ed
t
h
en
in
f
er
e
n
ce
d
t
o
th
e
f
u
zz
y
r
u
les.
A
t
th
e
FIS
S
u
g
e
n
o
m
et
h
o
d
,
im
p
licatio
n
f
u
n
ctio
n
u
s
ed
is
Min
.
T
ab
le
3
is
an
ex
a
m
p
le
o
f
f
u
zz
y
r
u
le
s
u
s
ed
in
t
h
i
s
s
tu
d
y
.
T
h
e
n
u
m
b
er
o
f
f
u
zz
y
r
u
le
s
o
b
tain
ed
f
r
o
m
t
h
e
n
u
m
b
er
o
f
f
u
zz
y
s
et
a
n
d
t
h
en
i
t
p
o
w
er
t
h
e
n
u
m
b
er
o
f
in
p
u
t
v
ar
iab
le
s
.
Fo
r
th
e
e
x
a
m
p
le,
th
er
e
ar
e
t
h
r
ee
in
p
u
t
v
ar
iab
les
an
d
t
w
o
f
u
zz
y
s
e
ts
.
So
th
at
t
h
e
n
u
m
b
er
o
f
f
u
zz
y
r
u
les
o
b
tain
ed
is
e
ig
h
t
f
u
zz
y
r
u
les.
I
n
t
h
i
s
s
t
u
d
y
,
ea
c
h
o
f
f
u
zz
y
lo
g
ic
h
a
s
a
n
u
m
b
e
r
o
f
d
if
f
er
e
n
t
r
u
le
s
.
T
h
e
f
ir
s
t
f
u
zz
y
lo
g
ic
(
p
o
s
itiv
e
p
ar
am
eter
s
)
h
as
5
in
p
u
t
v
ar
ia
b
les
w
it
h
2
f
u
zz
y
s
et
an
d
3
f
u
zz
y
s
et.
T
h
er
ef
o
r
e,
th
e
n
u
m
b
er
f
u
zz
y
r
u
les
ar
e
3
6
.
W
h
ile,
th
e
s
ec
o
n
d
f
u
zz
y
lo
g
ic
(
n
eg
ati
v
e
p
ar
am
e
ter
s
)
h
as
2
in
p
u
t
v
ar
iab
le
s
w
i
t
h
2
f
u
zz
y
s
et.
T
h
en
,
th
er
e
ar
e
4
r
u
le
s
i
n
n
e
g
ati
v
e
p
ar
am
e
ter
s
.
T
h
e
p
o
s
itiv
e
an
d
n
eg
at
iv
e
p
ar
a
m
eter
s
d
escr
ib
e
i
n
Fig
u
r
e
3
an
d
Fi
g
u
r
e
4
b
elo
w
.
T
h
is
class
i
f
icatio
n
o
f
p
ar
a
m
e
t
er
s
ai
m
s
to
m
i
n
i
m
ize
f
u
zz
y
r
u
l
es.
I
f
n
o
t
cla
s
s
i
f
ied
,
th
er
e
ar
e
1
4
4
r
u
les.
Gen
er
atin
g
to
o
m
an
y
r
u
le
s
n
o
t e
f
f
ec
tiv
e
an
d
n
ee
d
m
o
r
e
ti
m
e.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
J
E
C
E
Vo
l.
7
,
No
.
5
,
Octo
b
er
2
0
1
7
:
2
7
4
6
–
2
7
5
6
2750
T
ab
le
3.
A
n
E
x
a
m
p
le
o
f
F
u
zz
y
R
u
les
No
F
u
z
z
y
R
u
l
e
s
R1
I
F
(
b
-
1
)
i
s UP
A
N
D
(
b
-
2
)
i
s UP
A
N
D
(b
-
3)
i
s UP
…
T
H
EN
z
=
a
+
b
1
*
(
b
-
1
)
+
b
2
*
(
b
-
2
)
+
…
R2
I
F
(
b
-
1
)
i
s DO
W
N
A
N
D
(
b
-
2
)
i
s
U
P
A
N
D
(b
-
3)
i
s DO
W
N
…
T
H
EN
z
=
a
+
b
1
*
(
b
-
1
)
+
b
2
*
(
b
-
2
)
+
…
R3
I
F
(
b
-
1
)
i
s
U
P
A
N
D
(
b
-
2
)
i
s DO
W
N
A
N
D
(b
-
3)
i
s UP
…
T
H
EN
z
=
a
+
b
1
*
(
b
-
1
)
+
b
2
*
(
b
-
2
)
+
…
R4
I
F
(
b
-
1
)
i
s UP
A
N
D
(
b
-
2
)
i
s UP
A
N
D
(b
-
3)
i
s DO
W
N
…
T
H
EN
z
=
a
+
b
1
*
(
b
-
1
)
+
b
2
*
(
b
-
2
)
+
…
R5
I
F
(
b
-
1
)
i
s C
O
N
S
T
A
N
T
A
N
D
(
b
-
2
)
i
s
D
O
W
N
A
N
D
(b
-
3)
i
s UP
…
T
H
EN
z
=
a
+
b
1
*
(
b
-
1
)
+
b
2
*
(
b
-
2
)
+
…
4
.
3
D
ef
uzzif
ica
t
io
n
T
h
e
o
u
tp
u
t
v
al
u
e
(
cr
is
p
)
o
b
tain
ed
b
y
c
h
an
g
i
n
g
th
e
i
n
p
u
t
in
to
a
n
u
m
b
er
in
t
h
e
f
u
zz
y
s
et
o
r
th
at
r
ef
er
r
ed
to
d
ef
u
zz
if
icat
io
n
.
De
f
u
zz
if
ica
tio
n
m
et
h
o
d
in
th
e
S
u
g
en
o
m
eth
o
d
is
C
en
ter
Av
er
ag
e
Def
u
zz
y
f
ier
.
T
o
d
ec
r
ea
s
e
th
e
am
o
u
n
t
o
f
f
u
zz
y
r
u
les
t
h
at
ar
e
s
o
m
a
n
y
,
t
h
i
s
s
tu
d
y
u
s
es
t
w
o
s
ta
g
es
f
u
zz
y
tech
n
iq
u
e,
th
at
is
g
r
o
u
p
ed
th
e
p
ar
a
m
eter
s
w
h
ic
h
h
av
e
t
h
e
p
o
s
iti
v
e
an
d
n
eg
at
iv
e
i
n
f
lu
e
n
ce
to
t
h
e
in
f
l
atio
n
r
ate.
I
t
is
s
aid
p
o
s
itiv
e
p
ar
a
m
eter
if
th
e
p
ar
am
eter
ca
n
co
n
tr
o
l
th
e
p
r
ice
lev
el
[
2
4
]
.
M
o
n
e
y
Su
p
p
l
y
a
n
d
C
P
I
a
r
e
o
f
ten
u
s
ed
b
y
I
n
d
o
n
esia
n
g
o
v
er
n
m
e
n
t to
co
n
tr
o
l th
e
p
r
ice
lev
el.
T
h
e
y
ar
e
c
an
b
e
ca
teg
o
r
ized
as p
o
s
iti
v
e
p
ar
a
m
eter
s
.
B
esid
es
th
at,
h
is
to
r
ical
d
ata
a
ls
o
ca
n
b
e
ca
teg
o
r
ized
in
to
t
h
e
p
o
s
it
iv
e
p
ar
am
e
ter
.
T
h
e
r
est
ca
n
b
e
ca
teg
o
r
ized
in
to
t
h
e
n
eg
at
iv
e
p
a
r
a
m
eter
s
h
o
w
ed
in
T
ab
le
4
.
Fig
u
r
e
3
an
d
Fig
u
r
e
4
d
escr
ib
e
th
e
t
w
o
s
ta
g
es o
f
f
u
z
z
y
s
tr
u
ctu
r
e.
T
ab
le
4.
A
n
P
o
s
itiv
e
a
n
d
Neg
a
tiv
e
P
ar
a
m
eter
s
as I
n
p
u
t V
ar
ia
b
les
P
a
r
a
me
t
e
r
s
P
o
si
t
i
v
e
N
e
g
a
t
i
v
e
b
-
1
Ex
c
h
a
n
g
e
r
a
t
e
b
-
2
B
I
r
a
t
e
b
-
3
C
P
I
M
o
n
e
y
S
u
p
p
l
y
Fig
u
r
e
3
.
Fu
zz
y
s
tr
u
ct
u
r
e
w
it
h
p
o
s
itiv
e
p
ar
a
m
eter
Fig
u
r
e
4
.
Fu
zz
y
s
tr
u
ct
u
r
e
w
it
h
n
eg
ati
v
e
p
ar
am
eter
B
ased
o
n
th
e
t
w
o
s
tag
e
s
f
u
zz
y
test
r
esu
l
ts
,
ea
ch
o
f
th
e
s
e
p
r
o
ce
s
s
es p
r
o
d
u
ce
o
u
tp
u
t t
h
at
i
s
in
th
e
f
o
r
m
o
f
in
f
latio
n
f
o
r
ec
asti
n
g
.
T
h
e
f
o
r
ec
asti
n
g
r
es
u
lt
s
ar
e
s
h
o
w
n
i
n
T
ab
le
5
.
Data
p
r
o
ce
s
s
in
g
r
es
u
lt u
s
i
n
g
t
w
o
s
tag
e
s
f
u
zz
y
,
it
u
s
ed
as a
n
i
n
p
u
t v
ar
ia
b
les to
b
e
p
r
o
ce
s
s
ed
u
s
i
n
g
Ne
u
r
al
Net
w
o
r
k
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
E
n
a
b
lin
g
E
xtern
a
l F
a
cto
r
s
fo
r
I
n
fla
tio
n
R
a
te
F
o
r
ec
a
s
tin
g
u
s
i
n
g
F
u
z
z
y
.
.
.
(
N
a
d
ia
R
o
o
s
ma
lita
S
a
r
i
)
27
51
T
ab
le
5.
T
h
e
I
n
f
latio
n
R
ate
Fo
r
ec
asti
n
g
in
I
n
d
o
n
esia o
n
E
ac
h
P
ar
am
eter
D
a
t
e
A
c
t
u
a
l
d
a
t
a
F
o
r
e
c
a
st
i
n
g
r
e
su
l
t
F
I
S
S
u
g
e
n
o
I
F
I
S
S
u
g
e
n
o
I
I
P
a
r
a
me
t
e
r
+
P
a
r
a
me
t
e
r
-
13
-
D
e
c
8
.
3
8
8
.
8
5
0
4
8
1
2
.
4
7
3
5
13
-
N
o
v
8
.
3
7
8
.
7
7
3
1
1
.
3
1
0
7
5
13
-
O
c
t
8
.
3
2
8
.
7
5
5
4
4
1
1
.
6
8
9
7
5
13
-
S
e
p
8
.
4
9
.
1
8
0
9
1
1
0
.
5
8
1
13
-
A
u
g
8
.
7
9
9
.
6
8
3
7
3
9
.
0
9
5
5
13
-
J
u
l
8
.
6
1
6
.
6
9
2
8
.
7
4
6
5
13
-
J
u
n
5
.
9
6
.
1
3
2
8
2
7
.
7
8
13
-
Ma
y
5
.
4
7
6
.
1
3
0
1
4
7
.
2
8
0
2
5
13
-
A
p
r
5
.
5
7
6
.
6
4
4
1
9
7
.
2
7
7
2
5
13
-
M
a
r
5
.
9
6
.
1
6
1
2
7
7
.
2
2
5
2
5
13
-
F
e
b
5
.
3
1
5
.
3
7
9
5
9
7
.
2
5
6
2
5
13
-
J
a
n
4
.
5
7
5
.
0
6
2
1
6
7
.
2
0
9
7
5
…
…
…
…
5
-
O
c
t
1
7
.
8
9
1
7
.
1
3
1
8
.
5
6
1
7
5
5.
T
H
E
P
RO
P
O
SE
D
M
E
T
H
O
D
I
n
Sectio
n
5
,
th
e
s
tu
d
y
p
r
o
p
o
s
es Fu
zz
y
Ne
u
r
al
S
y
s
te
m
(
FNS
)
as in
f
latio
n
f
o
r
ec
ast
in
g
m
et
h
o
d
.
FNS is
a
h
y
b
r
id
m
et
h
o
d
b
et
w
ee
n
FIS
Su
g
en
o
an
d
B
ac
k
p
r
o
p
ag
atio
n
Neu
r
al
Net
w
o
r
k
.
Fi
g
u
r
e
5
illu
s
tr
ates
th
e
s
tr
u
ct
u
r
e
o
f
B
ac
k
p
r
o
p
ag
atio
n
Neu
r
al
N
et
w
o
r
k
[
2
6
]
.
Fig
u
r
e
5
.
T
h
e
B
ac
k
p
r
o
p
ag
atio
n
Neu
r
al
Net
w
o
r
k
’
s
s
tr
u
ct
u
r
e.
(
A
d
ap
ted
b
y
Sa
if
et
al,
2
0
1
3
)
Hav
i
n
g
o
b
tain
ed
t
h
e
f
u
zz
y
o
u
tp
u
t
in
Sectio
n
4
,
th
e
n
e
x
t
s
tag
e
is
t
h
e
tr
ain
i
n
g
d
ata
p
r
o
ce
s
s
.
T
h
e
tr
ain
i
n
g
d
ata
p
r
o
ce
s
s
i
n
Ne
u
r
al
Net
w
o
r
k
is
a
lear
n
i
n
g
d
ata
p
r
o
ce
s
s
.
T
h
e
d
ata
th
at
w
ill
b
e
u
s
ed
in
t
h
e
tr
ai
n
in
g
d
ata
p
r
o
ce
s
s
d
ata
ar
e
7
0
d
ata
r
ec
o
r
d
s
(
A
p
r
il
2
0
0
8
-
Dec
e
m
b
er
2
0
1
3
)
tak
en
f
r
o
m
ea
ch
in
p
u
t
v
ar
iab
le.
I
n
p
u
t
v
ar
iab
le
in
th
is
s
tag
e
is
in
th
e
f
o
r
m
o
f
o
u
tp
u
t p
r
ed
ictio
n
s
g
e
n
er
ated
b
y
t
h
e
FIS
S
u
g
en
o
p
r
o
ce
s
s
i
n
Sec
tio
n
4
.
I
n
th
e
p
r
o
p
o
s
ed
m
et
h
o
d
u
s
ed
3
n
eu
r
o
n
h
id
d
en
la
y
er
s
,
n
a
m
el
y
Z1
,
Z2
,
an
d
Z3
.
T
h
e
n
u
m
b
er
o
f
h
id
d
en
la
y
er
is
d
eter
m
in
ed
to
m
i
n
i
m
ize
t
h
e
c
o
m
p
u
tatio
n
al
p
r
o
ce
s
s
.
Ho
w
e
v
er
,
u
s
e
s
o
m
e
o
f
h
id
d
en
la
y
er
w
il
l
m
i
n
i
m
ize
er
r
o
r
v
alu
e.
6.
NUM
E
RICAL
E
XAM
P
L
E
B
ac
k
p
r
o
p
ag
atio
n
Neu
r
al
Net
w
o
r
k
h
a
s
t
w
o
s
ta
g
es
w
o
r
k
i
n
g
m
ec
h
a
n
i
s
m
,
n
a
m
el
y
f
ee
d
f
o
r
w
ar
d
an
d
b
ac
k
p
r
o
p
ag
atio
n
.
I
n
th
e
f
ee
d
f
o
r
w
ar
d
s
tag
e,
it
is
co
n
d
u
c
ted
th
e
tr
ain
i
n
g
d
ata
p
r
o
ce
s
s
th
at
is
th
e
lear
n
i
n
g
d
ata
p
r
o
ce
s
s
.
T
h
e
tr
ain
i
n
g
d
ata
p
r
o
ce
s
s
also
in
v
o
l
v
es
t
h
e
lear
n
i
n
g
r
ate
te
s
ti
n
g
p
r
o
ce
s
s
.
L
ea
r
n
in
g
r
ate
tes
tin
g
i
s
ca
r
r
ied
o
u
t
to
g
eth
er
w
it
h
tr
ai
n
in
g
d
ata
p
r
o
ce
s
s
.
T
h
e
test
r
es
u
lts
ca
n
b
e
u
s
ed
f
o
r
tes
tin
g
t
h
e
d
ata
at
th
e
f
u
r
t
h
er
s
tag
e
th
at
is
test
i
n
g
t
h
e
n
u
m
b
er
o
f
ep
o
ch
.
I
n
th
i
s
s
tag
e
it
i
s
u
s
ed
6
9
d
ata
r
ec
o
r
d
s
(
A
p
r
il
2
0
0
8
–
Dec
em
b
er
2
0
1
3
)
to
tr
ain
in
g
d
ata
p
r
o
ce
s
s
.
T
h
e
r
esu
lts
o
f
lear
n
in
g
r
ate
te
s
ti
n
g
s
h
o
w
n
in
T
ab
le
6
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
J
E
C
E
Vo
l.
7
,
No
.
5
,
Octo
b
er
2
0
1
7
:
2
7
4
6
–
2
7
5
6
2752
T
ab
le
6.
T
h
e
L
ea
r
n
in
g
R
ate
T
esti
n
g
R
e
s
u
lt o
n
E
ac
h
E
x
p
er
im
en
t
L
e
a
r
n
i
n
g
Ep
o
c
h
Ex
p
e
r
i
me
n
t
r
a
t
e
1
2
3
…
10
Er
r
o
r
R
M
S
E
a
v
e
r
a
g
e
0
.
1
2
0
0
0
0
.
0
0
2
7
5
8
0
.
0
0
2
7
5
6
0
.
0
0
2
7
5
4
…
0
.
0
0
2
7
4
3
0
.
0
0
1
1
0
1
0
.
2
2
0
0
0
0
.
0
0
2
6
4
4
0
.
0
0
2
6
6
6
0
.
0
0
2
6
6
7
…
0
.
0
0
2
6
6
9
0.
0
0
1
0
6
5
0
.
3
2
0
0
0
0
.
0
0
2
6
2
8
0
.
0
0
2
6
5
2
0
.
0
0
2
6
1
8
…
0
.
0
0
2
6
3
9
0
.
0
0
1
0
5
4
0
.
4
2
0
0
0
0
.
0
0
2
6
2
6
0
.
0
0
2
6
1
0
.
0
0
2
6
1
9
…
0
.
0
0
2
6
1
9
0
.
0
0
1
0
4
7
0
.
5
2
0
0
0
0
.
0
0
2
6
3
0
.
0
0
2
6
2
5
0
.
0
0
2
6
3
5
…
0
.
0
0
2
6
7
8
0
.
0
0
1
0
5
7
0
.
6
2
0
0
0
0
.
0
0
2
6
7
5
0
.
0
0
2
6
1
7
0
.
0
0
2
6
5
3
…
0
.
0
0
2
6
4
2
0
.
0
0
1
0
5
9
0
.
7
2
0
0
0
0
.
0
0
2
6
3
0
.
0
0
2
65
0
.
0
0
2
5
9
7
…
0
.
0
0
2
6
5
4
0
.
0
0
1
0
5
3
0
.
8
2
0
0
0
0
.
0
0
2
6
4
2
0
.
0
0
2
6
6
8
0
.
0
0
2
6
5
3
…
0
.
0
0
2
6
6
9
0
.
0
0
1
0
6
3
0
.
9
2
0
0
0
0
.
0
0
2
6
7
6
0
.
0
0
2
6
8
1
0
.
0
0
2
6
8
2
…
0
.
0
0
2
6
7
3
0
.
0
0
1
0
7
1
1
2
0
0
0
0
.
0
0
2
6
4
6
0
.
0
0
2
6
8
7
0
.
0
0
2
6
9
5
…
0
.
0
0
2
6
8
7
0
.
0
0
1
0
7
1
Fig
u
r
e
6
.
L
ea
r
n
i
n
g
r
ate
test
i
n
g
g
r
ap
h
I
n
Fi
g
u
r
e
6
k
n
o
w
n
th
at
t
h
e
lea
r
n
in
g
r
ate
m
o
v
e
m
e
n
t
c
h
ar
t
lo
o
k
d
o
w
n
a
n
d
s
u
d
d
en
l
y
u
p
.
B
asi
ca
ll
y
,
t
h
e
s
m
al
ler
th
e
v
alu
e
o
f
lear
n
i
n
g
r
ate
th
e
n
th
e
lear
n
i
n
g
p
r
o
ce
s
s
w
il
l
b
e
lo
n
g
er
to
r
ea
ch
t
h
e
tar
g
et.
I
n
ad
d
itio
n
,
t
h
e
tar
g
et
m
a
y
n
o
t
b
e
ac
h
iev
ed
d
u
e
to
th
e
co
n
d
itio
n
o
f
th
e
ep
o
ch
s
to
p
p
ed
b
ef
o
r
e
r
ea
ch
in
g
t
h
e
tar
g
et
s
o
th
at
th
e
er
r
o
r
g
en
er
ated
is
s
til
l
h
ig
h
.
Ho
w
e
v
er
,
th
e
lar
g
e
v
alu
e
o
f
l
ea
r
n
in
g
r
ate
w
il
l
m
a
k
e
t
h
e
lea
r
n
in
g
p
r
o
ce
s
s
f
aster
.
T
h
e
f
aster
o
f
th
e
lear
n
i
n
g
p
r
o
ce
s
s
w
ill
allo
w
t
h
e
tar
g
et
to
b
e
ex
ce
ed
ed
.
T
h
er
ef
o
r
e,
th
e
r
esu
lti
n
g
er
r
o
r
ten
d
s
in
th
is
a
n
al
y
s
is
te
n
d
s
to
b
e
h
ig
h
.
I
t
ca
n
b
e
co
n
cl
u
d
ed
th
at
t
h
e
v
alu
e
o
f
lear
n
i
n
g
r
ate
w
h
ic
h
i
s
h
as
s
m
a
ll
an
d
lar
g
e
r
ates
ar
e
d
if
f
ic
u
lt
to
ac
h
ie
v
e
t
h
e
tar
g
et.
I
t
also
in
f
l
u
en
ce
d
b
y
th
e
d
i
f
f
er
e
n
t
d
ata.
I
n
th
i
s
test
th
e
b
est
v
alu
e
f
o
r
l
ea
r
n
in
g
r
ate
is
0
.
4
.
T
h
e
v
al
u
es
ar
e
s
elec
ted
b
ased
o
n
t
h
e
s
m
alle
s
t
er
r
o
r
av
er
ag
e
is
0
.
0
0
1
0
4
7
th
at
s
h
o
w
n
i
n
T
ab
le
6
.
Af
ter
o
b
tai
n
ed
t
h
e
b
est
lear
n
i
n
g
r
ate
v
al
u
e,
t
h
at
v
al
u
e
is
u
s
e
d
to
test
t
h
e
a
m
o
u
n
t
o
f
ep
o
ch
.
T
esti
n
g
i
s
p
er
f
o
r
m
ed
1
0
ti
m
es.
T
h
is
test
ai
m
s
to
g
et
th
e
b
est
ep
o
ch
th
at
u
s
e
to
f
i
n
d
th
e
n
u
m
b
er
o
f
n
eu
r
o
n
s
i
n
f
u
r
th
er
test
i
n
g
.
T
h
e
test
r
es
u
lt is
s
h
o
wn
in
T
ab
le
7
.
T
ab
le
7.
T
h
e
Nu
m
b
er
o
f
E
p
o
ch
T
esti
n
g
R
es
u
lt o
n
E
ac
h
E
x
p
er
i
m
en
t
L
e
a
r
n
i
n
g
Ep
o
c
h
Ex
p
e
r
i
me
n
t
s
r
a
t
e
1
2
3
…
10
Er
r
o
r
R
M
S
E
a
v
e
r
a
g
e
0
.
4
5
0
0
0
0
.
0
0
2
5
9
6
0
.
0
0
2
5
4
0
.
0
0
2
5
7
9
…
0
.
0
0
2
5
7
7
0
.
0
0
2
5
6
3
0
.
4
1
0
0
0
0
0
.
0
0
2
4
4
4
0
.
0
0
2
4
6
8
0
.
0
0
2
4
4
8
…
0
.
0
0
2
4
4
9
0
.
0
0
2
4
8
8
0
.
4
3
0
0
0
0
0
.
0
0
2
3
5
9
0
.
0
0
2
3
6
4
0
.
0
0
2
3
8
8
…
0
.
0
0
2
3
9
5
0
.
0
0
2
3
9
9
0
.
4
5
0
0
0
0
0
.
0
0
2
3
1
5
0
.
0
0
2
3
3
3
0
.
0
0
2
3
4
8
…
0
.
0
0
2
3
3
2
0
.
0
0
2
3
3
8
0
.
4
1
0
0
0
0
0
0
.
0
0
2
2
5
0
.
0
0
2
2
2
4
0.
0
0
2
3
8
9
…
0
.
0
0
2
2
2
8
0
.
0
0
2
2
8
7
0
.
4
1
5
0
0
0
0
0
.
0
0
2
1
8
2
0
.
0
0
2
2
0
8
0
.
0
0
2
1
9
3
…
0
.
0
0
2
1
8
0
.
0
0
2
1
8
9
0
.
4
2
0
0
0
0
0
0
.
0
0
2
1
6
9
0
.
0
0
2
4
9
0
.
0
0
2
4
9
…
0
.
0
0
2
1
6
4
0
.
0
0
2
2
6
4
0
.
4
2
5
0
0
0
0
0
.
0
0
2
1
5
3
0
.
0
0
2
1
5
3
0
.
0
0
2
1
5
4
…
0
.
0
0
2
1
5
5
0
.
0
0
2
1
5
3
0
.
4
3
0
0
0
0
0
0
.
0
0
2
1
4
7
0
.
0
0
2
1
4
9
0
.
0
0
2
1
4
7
…
0
.
0
0
2
1
4
9
0
.
0
0
2
2
0
6
0
.
4
3
2
0
0
0
0
0
.
0
0
2
1
4
5
0
.
0
0
2
3
8
9
0
.
0
0
2
1
4
7
…
0
.
0
0
2
1
4
8
0
.
0
0
2
1
9
3
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
E
n
a
b
lin
g
E
xtern
a
l F
a
cto
r
s
fo
r
I
n
fla
tio
n
R
a
te
F
o
r
ec
a
s
tin
g
u
s
i
n
g
F
u
z
z
y
.
.
.
(
N
a
d
ia
R
o
o
s
ma
lita
S
a
r
i
)
2753
Fig
u
r
e
7
.
T
h
e
n
u
m
b
er
o
f
ep
o
ch
test
i
n
g
Fig
u
r
e
7
s
h
o
w
s
th
e
m
o
v
e
m
en
t
o
f
t
h
e
ep
o
ch
s
ee
m
ed
to
d
ec
li
n
e.
T
h
is
i
s
b
ec
au
s
e
t
h
e
m
o
r
e
ep
o
ch
th
at
u
s
ed
,
t
h
en
lear
n
i
n
g
p
r
o
ce
s
s
will
r
ea
ch
i
n
g
t
h
e
tar
g
e
t
f
astl
y
,
s
o
th
e
r
es
u
lti
n
g
er
r
o
r
is
s
m
al
le
r
.
Ho
w
e
v
er
,
to
g
et
th
at
r
esu
lt,
it
ca
n
tak
e
a
lo
t
o
f
ti
m
e
in
co
m
p
u
ti
n
g
p
r
o
ce
s
s
.
I
n
th
i
s
test
i
n
g
t
h
e
b
est
o
f
ep
o
ch
is
2
5
0
0
0
0
.
T
h
e
v
alu
e
ar
e
s
elec
ted
b
ased
o
n
th
e
th
e
s
m
alles
t o
f
er
r
o
r
av
er
ag
e
is
0
.
0
0
2
1
5
3
as sh
o
w
n
in
T
ab
le
7
.
Hav
i
n
g
o
b
tain
ed
t
h
e
b
e
s
t
o
f
l
ea
r
n
in
g
v
al
u
e
a
n
d
t
h
e
n
u
m
b
er
o
f
ep
o
ch
,
th
e
n
f
u
r
t
h
er
test
in
g
h
a
s
d
o
n
e
th
e
test
i
n
g
o
f
n
eu
r
o
n
.
So
m
e
n
eu
r
al
n
et
w
o
r
k
s
tr
u
ct
u
r
es
ar
e
test
ed
f
o
r
ev
alu
atin
g
th
e
o
p
tim
al
n
et
w
o
r
k
co
n
s
id
er
in
g
t
h
e
n
u
m
b
er
o
f
n
e
u
r
o
n
in
th
e
h
id
d
en
la
y
er
[
2
7
]
.
T
h
e
r
es
u
lt o
f
t
h
ese
te
s
t
s
ar
e
u
s
e
d
in
t
h
e
n
ex
t
s
ta
g
es
is
d
ata
p
r
o
ce
s
s
in
g
u
s
in
g
Ne
u
r
a
l N
et
w
o
r
k
.
T
h
e
test
in
g
n
eu
r
o
n
p
er
f
o
r
m
ed
1
0
ti
m
es.
T
h
e
r
es
u
lt o
f
n
eu
r
o
n
test
in
g
is
s
h
o
w
n
i
n
T
ab
le
8
.
T
ab
le
8.
T
h
e
Nu
m
b
er
o
f
Neu
r
o
n
T
esti
n
g
R
es
u
lt o
n
E
ac
h
E
x
p
er
im
e
n
t
N
e
u
r
o
n
L
e
a
r
n
i
n
g
Ep
o
c
h
Ex
p
e
r
i
me
n
t
s
Er
r
o
r
Rate
1
2
3
…
10
a
v
e
r
a
g
e
R
M
S
E
3
0
.
4
2
5
0
0
0
0
0
.
0
0
2
1
4
2
0
.
0
0
2
1
5
3
0
.
0
0
2
1
5
2
…
0
.
0
0
2
3
8
9
0
.
0
0
2
1
7
7
4
0
.
4
2
5
0
0
0
0
0
.
0
0
2
1
1
3
0
.
0
0
2
1
4
9
0
.
0
0
2
1
1
9
…
0
.
0
0
2
1
6
1
0
.
0
0
2
1
3
5
0
.
4
2
5
0
0
0
0
0
.
0
0
2
1
0
9
0
.
0
0
2
1
2
0
.
0
0
2
1
0
9
…
0
.
0
0
2
1
2
0
.
0
0
2
1
6
9
6
0
.
4
2
5
0
0
0
0
0
.
0
0
2
0
9
7
0
.
0
0
2
1
1
5
0
.
0
0
2
1
1
…
0
.
0
0
2
1
1
1
0
.
0
0
2
1
1
2
7
0
.
4
2
5
0
0
0
0
0
.
0
0
2
0
9
3
0
.
0
0
2
1
1
0
.
0
0
2
1
0
3
…
0
.
0
0
2
1
0
9
0
.
0
0
2
1
1
8
0
.
4
2
5
0
0
0
0
0
.
0
0
2
0
9
9
0
.
0
0
2
1
0
3
0
.
0
0
2
1
3
7
…
0
.
0
0
2
0
9
6
0
.
0
0
2
1
2
5
9
0
.
4
2
5
0
0
0
0
0
.
0
0
2
1
2
2
0
.
0
0
2
1
1
1
0
.
0
0
2
1
1
2
…
0
.
0
0
2
0
9
4
0
.
0
0
2
1
1
2
10
0
.
4
25
0
0
0
0
0
.
0
0
2
1
0
3
0
.
0
0
2
1
1
7
0
.
0
0
2
1
1
4
…
0
.
0
0
2
1
1
1
0
.
0
0
2
1
1
4
Fig
u
r
e
8
.
T
h
e
n
u
m
b
er
o
f
n
eu
r
o
n
test
i
n
g
Fig
u
r
e
8
s
h
o
w
s
t
h
e
m
o
v
e
m
e
n
to
f
er
r
o
r
av
er
ag
e
d
ec
r
ea
s
es
as
th
e
n
u
m
b
er
o
f
n
e
u
r
o
n
s
.
T
h
is
is
b
ec
au
s
e
m
o
r
e
an
d
m
o
r
e
n
eu
r
o
n
s
ar
e
u
s
ed
,
th
e
r
esu
lt
o
f
er
r
o
r
is
g
etti
n
g
s
m
aller
.
Ho
w
e
v
er
,
it
ca
n
t
ak
e
a
lo
t
o
f
ti
m
e
i
n
th
e
co
m
p
u
ti
n
g
p
r
o
ce
s
s
.
I
n
t
h
is
test
t
h
e
b
est
n
e
u
r
o
n
is
7
.
T
h
e
v
al
u
e
ar
e
s
elec
ted
b
ased
o
n
t
h
e
s
m
alle
s
t
o
f
er
r
o
r
av
er
ag
e
is
0
.
0
0
2
1
1
as sh
o
w
n
i
n
T
ab
le
8
.
B
ased
o
n
th
e
test
r
esu
l
t,
th
e
n
u
m
b
er
o
f
n
e
u
r
o
n
s
o
b
tai
n
ed
th
e
b
est
w
ei
g
h
t
s
to
b
e
u
s
ed
f
o
r
test
in
g
d
ata.
T
h
e
w
ei
g
h
ts
ar
e
s
u
m
m
ar
ized
in
T
ab
le
9
.
V
ij
is
w
ei
g
h
t
f
r
o
m
n
eu
r
o
n
i
n
p
u
t
to
n
e
u
r
o
n
h
i
d
d
en
.
T
h
en
,
W
jk
is
w
ei
g
h
t f
r
o
m
n
e
u
r
o
n
h
id
d
en
to
n
eu
r
o
n
o
u
tp
u
t.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
J
E
C
E
Vo
l.
7
,
No
.
5
,
Octo
b
er
2
0
1
7
:
2
7
4
6
–
2
7
5
6
2754
T
ab
le
9.
T
h
e
W
eig
h
ts
Ob
tai
n
e
d
Du
r
in
g
th
e
T
r
ain
in
g
P
r
o
ce
s
s
V
i
j
1
2
3
4
5
6
7
1
-
0
.
8
0
1
1
.
1
1
9
7
8
-
1
.
7
2
8
5
-
1
.
0
2
7
8
-
1
5
.
9
9
3
-
1
.
5
0
4
9
-
4
.
5
5
7
7
2
-
0
.
1
6
9
7
-
0
.
2
6
2
8
0
.
8
9
5
4
5
0
.
0
9
1
1
9
.
6
9
8
3
0
.
6
3
8
9
4
6
.
6
6
1
3
3
W
j
k
1
1
-
2
.
9
6
1
8
2
5
.
2
4
9
2
1
3
-
3
.
3
8
9
1
4
-
3
.
0
3
7
5
-
1
.
6
4
9
6
-
3
.
1
9
1
9
7
3
.
9
8
7
8
1
7.
RE
SU
L
T
AND
DI
SCUS
SI
O
N
I
n
th
i
s
s
tag
e,
it
is
co
n
d
u
cted
t
h
e
d
ata
test
i
n
g
to
g
et
th
e
r
e
s
u
lts
o
f
i
n
f
latio
n
f
o
r
ec
ast
in
g
i
n
I
n
d
o
n
esia.
T
h
e
d
ata
test
in
g
is
d
o
n
e
a
f
ter
o
b
tain
in
g
t
h
e
v
al
u
e
o
f
lear
n
i
n
g
r
ate
a
n
d
th
e
b
e
s
t
w
ei
g
h
t
o
n
t
h
e
tr
ain
i
n
g
d
ata
p
r
o
ce
s
s
.
T
h
e
b
est v
alu
e
o
f
lear
n
in
g
r
ate
i
n
th
e
tr
ai
n
i
n
g
d
ata
p
r
o
ce
s
s
is
0
.
4
w
it
h
co
m
p
u
tatio
n
ti
m
e
is
1
s
ec
o
n
d
.
T
h
e
n
ex
t
p
r
o
ce
s
s
is
d
ata
test
i
n
g
.
Data
u
s
ed
i
n
t
h
e
te
s
ti
n
g
s
t
ag
e
ar
e
3
0
d
ata
(
Octo
b
er
2
0
0
5
–
Ma
r
ch
2
0
0
8
)
.
T
h
is
s
ta
g
e
is
B
ac
k
p
r
o
p
ag
atio
n
m
ec
h
an
is
m
to
p
r
o
d
u
ce
an
i
n
f
la
tio
n
r
ate
f
o
r
ec
asti
n
g
i
n
I
n
d
o
n
e
s
i
a.
T
o
test
th
e
ac
c
u
r
ac
y
o
f
th
e
s
y
s
te
m
,
t
h
is
s
t
u
d
y
u
s
e
s
R
o
o
t
Me
a
n
Sq
u
ar
e
E
r
r
o
r
(
R
MSE
)
tech
n
iq
u
e
.
T
h
is
tech
n
iq
u
e
i
s
ea
s
y
to
i
m
p
le
m
en
t
an
d
h
as
b
ee
n
f
r
eq
u
e
n
tl
y
u
s
ed
i
n
v
ar
iet
y
o
f
s
t
u
d
ies
r
elate
d
to
th
e
f
o
r
ec
asti
n
g
,
as
in
th
e
s
tu
d
y
b
y
Sto
ck
a
n
d
W
atso
n
[
2
8
]
an
d
Sar
i,
et
al
[
2
9
]
.
T
ab
le
1
0
s
h
o
w
s
th
e
f
o
r
ec
asti
n
g
r
es
u
lt
s
u
s
i
n
g
FNS.
T
ab
le
10.
T
h
e
Fo
r
ec
asti
n
g
R
e
s
u
lt b
et
w
en
FNS a
n
d
FIS
S
u
g
e
n
o
Me
th
o
d
B
u
l
a
n
A
c
t
u
a
l
d
a
t
a
F
I
S
S
u
g
e
n
o
F
N
S
M
a
r
-
08
8
.
1
7
4
.
7
4
5
3
6
5
.
6
2
9
1
7
7
F
e
b
-
08
7
.
4
4
.
9
3
4
9
5
5
.
6
8
8
7
1
2
Jan
-
08
7
.
3
6
4
.
2
0
7
7
4
5
.
5
7
9
5
6
4
D
e
c
-
07
6
.
5
9
4
.
2
7
8
9
8
5
.
5
6
6
8
1
9
N
o
v
-
07
6
.
7
1
4
.
7
1
6
1
7
5
.
6
7
2
6
2
4
O
c
t
-
07
6
.
8
8
4
.
9
4
4
0
9
5
.
7
2
4
5
2
2
S
e
p
-
07
6
.
9
5
4
.
7
1
4
3
8
5
.
8
4
0
4
3
1
A
u
g
-
07
6
.
5
1
4
.
3
8
7
3
3
5
.
6
4
4
0
3
5
Ju
l
-
07
6
.
0
6
4
.
0
4
4
8
2
5
.
5
3
4
0
5
4
Ju
n
-
07
5
.
7
7
4
.
4
2
6
5
.
6
8
7
9
7
5
M
a
y
-
07
6
.
0
1
4
.
8
8
7
8
1
6
.
0
7
7
3
6
4
A
p
r
-
07
6
.
2
9
5
.
4
2
0
4
7
7
.
0
0
4
5
5
8
M
a
r
-
07
6
.
5
2
5
.
2
0
7
5
5
7
.
1
8
0
9
8
2
F
e
b
-
07
6
.
3
5
.
4
3
9
9
9
7
.
9
7
3
4
2
8
Jan
-
07
6
.
2
6
6
.
3
1
5
2
5
8
.
3
4
5
9
5
2
…
…
…
…
5
-
O
c
t
1
7
.
8
9
1
8
.
0
3
8
5
2
1
5
.
5
0
3
7
3
R
M
S
E
3
.
5
4
1
.
8
1
Fig
u
r
e
9
.
T
h
e
r
esu
lts
o
f
t
h
e
co
m
p
ar
i
s
o
n
m
et
h
o
d
b
et
w
ee
n
FN
S a
n
d
FIS
S
u
g
e
n
o
f
o
r
in
f
lat
io
n
r
at
e
f
o
r
ec
asti
n
g
T
h
is
s
tu
d
y
is
ad
v
a
n
ce
d
s
tu
d
y
f
r
o
m
p
r
ev
io
u
s
s
tu
d
y
[
3
0
]
.
I
n
th
e
p
r
ev
io
u
s
s
t
u
d
y
u
s
ed
Fu
zz
y
I
n
f
er
en
ce
S
y
s
te
m
(
FIS)
S
u
g
e
n
o
ap
p
r
o
a
ch
f
o
r
i
n
f
latio
n
r
ate
f
o
r
ec
asti
n
g
.
T
i
m
e
s
er
ies
a
n
d
ex
ter
n
al
f
ac
to
r
s
u
s
ed
in
th
a
t
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
E
n
a
b
lin
g
E
xtern
a
l F
a
cto
r
s
fo
r
I
n
fla
tio
n
R
a
te
F
o
r
ec
a
s
tin
g
u
s
i
n
g
F
u
z
z
y
.
.
.
(
N
a
d
ia
R
o
o
s
ma
lita
S
a
r
i
)
2755
s
tu
d
y
[
3
0
]
.
A
cc
u
r
ac
y
o
f
f
o
r
ec
asti
n
g
r
e
s
u
lt
b
y
u
s
in
g
FIS
Su
g
en
o
i
s
3
.
5
4
.
P
r
ev
io
u
s
s
tu
d
y
[
3
0
]
u
s
ed
as
a
co
m
p
ar
is
o
n
m
et
h
o
d
.
T
ab
le
1
0
s
h
o
w
s
a
co
m
p
ar
is
o
n
b
et
wee
n
t
h
e
p
r
o
p
o
s
ed
m
eth
o
d
a
n
d
th
e
co
m
p
ar
is
o
n
m
et
h
o
d
.
I
n
Fi
g
u
r
e
9
it
i
s
k
n
o
w
n
t
h
at
t
h
e
FNS
s
h
o
w
s
t
h
e
m
o
v
e
m
e
n
t
t
h
at
clo
s
er
to
th
e
a
ctu
al
d
ata.
B
y
u
s
i
n
g
R
MSE
tec
h
n
iq
u
e,
th
e
ac
cu
r
ac
y
o
f
t
h
e
s
y
s
te
m
g
e
n
er
ated
b
y
FNS
i
s
1
.
8
1
.
W
h
ile
t
h
e
ac
c
u
r
a
c
y
g
en
er
ated
b
y
t
h
e
co
m
p
ar
is
o
n
m
et
h
o
d
is
3
.
5
4
.
B
ased
o
n
T
ab
le
1
0
FNS
m
e
t
h
o
d
h
as
a
b
etter
p
e
r
f
o
r
m
a
n
ce
an
d
m
a
k
es
a
b
etter
p
r
ed
ictio
n
th
a
n
t
h
e
co
m
p
ar
i
s
o
n
m
eth
o
d
.
T
h
is
r
e
s
u
l
t
ca
n
o
cc
u
r
b
ec
au
s
e
FNS
m
o
d
el
th
er
e
is
a
p
r
o
ce
s
s
o
f
tr
ain
i
n
g
d
ata
n
e
u
r
al
n
e
t
w
o
r
k
s
o
th
at
t
h
is
m
e
th
o
d
is
m
o
r
e
f
le
x
ib
le
i
n
ter
m
s
o
f
ad
ap
tin
g
to
t
h
e
en
v
ir
o
n
m
e
n
t
a
n
d
h
av
e
g
o
o
d
lear
n
in
g
ab
ilit
y
.
8.
CO
NCLU
SI
O
N
Fu
zz
y
Ne
u
r
al
S
y
s
te
m
(
F
NS)
m
et
h
o
d
t
h
at
is
p
r
o
p
o
s
ed
in
th
is
s
t
u
d
y
ca
n
b
e
i
m
p
le
m
e
n
t
ed
f
o
r
t
h
e
in
f
latio
n
r
ate
f
o
r
ec
asti
n
g
i
n
I
n
d
o
n
esia.
T
h
e
r
esu
lt
o
f
R
MSE
ca
lcu
lat
io
n
s
h
o
w
s
t
h
at
FNS
h
a
s
a
b
etter
p
er
f
o
r
m
a
n
ce
t
h
an
t
h
e
co
m
p
a
r
is
o
n
m
et
h
o
d
FIS
Su
g
e
n
o
(
p
r
ev
io
u
s
s
tu
d
y
)
[
3
0
]
.
W
ith
th
e
ad
d
itio
n
o
f
s
o
m
e
ex
ter
n
al
p
ar
a
m
e
ter
s
(
ex
ter
n
al
f
ac
to
r
)
,
th
e
f
o
r
ec
asti
n
g
r
esu
lt
u
s
i
n
g
FN
S
m
et
h
o
d
is
also
b
etter
th
an
u
s
i
n
g
B
ac
k
p
r
o
p
ag
atio
n
Neu
r
al
Net
wo
r
k
in
p
r
ev
io
u
s
s
tu
d
y
[
1
1
]
.
T
h
e
ac
cu
r
ac
y
o
f
th
e
s
y
s
te
m
p
r
o
d
u
ce
d
b
y
FNS
u
s
i
n
g
R
MSE
an
a
l
y
s
is
tec
h
n
iq
u
e
is
1
.
8
1
.
T
h
e
ac
cu
r
ac
y
o
f
th
e
s
y
s
te
m
r
e
s
u
lted
i
n
t
h
i
s
s
t
u
d
y
ca
n
s
till
b
e
i
m
p
r
o
v
ed
.
On
e
o
f
t
h
e
t
h
in
g
s
t
h
at
a
f
f
ec
t
th
e
ac
c
u
r
ac
y
o
f
th
e
s
y
s
te
m
is
th
e
f
o
r
m
atio
n
o
f
f
u
zz
y
r
u
les
a
n
d
d
eter
m
i
n
in
g
t
h
e
i
n
itial
w
ei
g
h
t
s
i
n
t
h
e
Ne
u
r
al
Net
w
o
r
k
tr
ain
i
n
g
p
r
o
ce
s
s
.
I
n
th
is
s
tu
d
y
,
t
h
e
d
eter
m
i
n
atio
n
o
f
f
u
zz
y
r
u
le
s
d
eter
m
i
n
ed
m
an
u
al
l
y
.
W
h
ile
t
h
e
in
itial
w
ei
g
h
t
s
i
n
tr
ai
n
in
g
p
r
o
ce
s
s
ar
e
s
t
ill
d
eter
m
in
ed
r
an
d
o
m
l
y
.
I
t
m
ig
h
t
b
e
t
h
at
s
u
c
h
a
d
eter
m
i
n
atio
n
i
s
le
s
s
f
it.
T
h
er
ef
o
r
e,
g
en
et
ic
al
g
o
r
ith
m
i
m
p
le
m
en
tatio
n
in
t
h
e
n
ex
t
s
t
u
d
y
is
n
ee
d
ed
to
o
p
ti
m
ize
t
h
e
f
u
zz
y
r
u
les
a
n
d
t
h
e
in
i
tial
w
eig
h
t
s
in
tr
ain
in
g
d
ata
p
r
o
ce
s
s
.
Op
ti
m
izatio
n
aim
s
to
i
m
p
r
o
v
e
th
e
ac
c
u
r
ac
y
o
f
th
e
s
y
s
te
m
t
h
at
i
s
b
etter
.
Gen
etic
A
l
g
o
r
it
h
m
h
a
s
b
ee
n
u
s
ed
to
r
eso
lv
e
is
s
u
e
s
r
elate
d
to
th
e
o
p
ti
m
izatio
n
li
k
e
a
s
t
u
d
y
co
n
d
u
cted
b
y
[
3
1
]
.
P
r
o
v
id
e
a
s
tate
m
e
n
t
t
h
at
w
h
a
t
is
e
x
p
ec
ted
,
as
s
tated
i
n
t
h
e
"
I
n
tr
o
d
u
ctio
n
"
ch
ap
ter
ca
n
u
lti
m
atel
y
r
esu
lt
i
n
"
R
es
u
lts
a
n
d
Dis
c
u
s
s
io
n
"
ch
ap
ter
,
s
o
th
er
e
is
co
m
p
a
tib
ilit
y
.
Mo
r
eo
v
er
,
it
ca
n
also
b
e
ad
d
ed
th
e
p
r
o
s
p
ec
t
o
f
th
e
d
ev
elo
p
m
e
n
t
o
f
r
esear
ch
r
esu
l
ts
an
d
ap
p
licatio
n
p
r
o
s
p
ec
ts
o
f
f
u
r
t
h
er
s
t
u
d
ies
in
to
th
e
n
e
x
t
(
b
ased
o
n
r
esu
lt a
n
d
d
is
c
u
s
s
io
n
)
.
RE
F
E
R
E
NC
E
S
[1
]
S
.
S
u
k
ir
n
o
,
“
Pen
g
a
n
t
a
r
T
e
o
ri
M
a
k
ro
Eko
n
o
mi
(
In
tro
d
u
c
ti
o
n
to
t
h
e
T
h
e
o
ry
o
f
M
a
c
ro
Eco
n
o
my
)
”
.
J
a
k
a
rta:
P
T
Ra
ja
G
ra
f
in
d
o
P
e
rsa
d
a
,
2
0
0
8
.
[2
]
N.
R.
S
a
ri,
W
.
F
.
M
a
h
m
u
d
y
,
a
n
d
A
.
P
.
W
ib
a
w
a
,
“
Ba
c
k
p
ro
p
a
g
a
ti
o
n
o
n
Ne
u
ra
l
Ne
tw
o
rk
M
e
th
o
d
f
o
r
In
f
latio
n
Ra
te
F
o
re
c
a
stin
g
in
I
n
d
o
n
e
sia
,
”
In
t
J
S
o
ft
C
o
mp
u
t
Its
A
p
p
l
,
2
0
1
6
.
[3
]
E.
R.
W
u
lan
a
n
d
S
.
N
u
rf
a
iza
,
“
An
a
ly
sis
o
f
F
a
c
to
rs
Aff
e
c
ti
n
g
In
f
la
ti
o
n
in
I
n
d
o
n
e
sia
:
a
n
Isla
m
ic
P
e
rsp
e
c
ti
v
e
,
”
In
t.
J
.
Nu
sa
n
t
.
Isla
m
,
v
o
l.
2
,
n
o
.
2
,
p
p
.
6
7
–
8
0
,
2
0
1
5
.
[4
]
S
.
Ko
o
t
h
s,
T
.
M
it
z
e
,
a
n
d
E
.
Rin
g
h
u
t,
“
In
f
latio
n
F
o
re
c
a
stin
g
-
a
Co
m
p
a
riso
n
b
e
tw
e
e
n
Eco
n
o
m
e
tri
c
M
e
th
o
d
s
a
n
d
a
Co
m
p
u
tatio
n
a
l
A
p
p
r
o
a
c
h
Ba
se
d
o
n
g
e
n
e
ti
c
-
n
e
u
ra
l
f
u
z
z
y
ru
le
-
b
a
s
e
s,”
in
Co
mp
u
ta
ti
o
n
a
l
I
n
telli
g
e
n
c
e
fo
r
Fi
n
a
n
c
ia
l
En
g
i
n
e
e
rin
g
,
2
0
0
3
.
Pr
o
c
e
e
d
in
g
s
.
2
0
0
3
IE
EE
I
n
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
,
2
0
0
3
,
p
p
.
1
8
3
–
1
9
0
.
[5
]
G
.
P
.
Zh
a
n
g
,
“
T
ime
S
e
ries
F
o
re
c
a
stin
g
Us
in
g
A
H
y
b
rid
A
RIM
A
a
n
d
Ne
u
ra
l
Ne
tw
o
rk
M
o
d
e
l,
”
El
se
v
ier
,
v
o
l.
5
0
,
p
p
.
159
–
1
7
5
,
2
0
0
3
.
[6
]
J.
A
rlt
a
n
d
M
.
A
rlt
o
v
a
,
“
F
o
re
c
a
st
in
g
o
f
th
e
A
n
n
u
a
l
I
n
f
la
ti
o
n
Ra
te
i
n
t
h
e
Un
sta
b
le
Eco
n
o
m
ic
Co
n
d
it
i
o
n
s,”
2
0
1
5
,
p
p
.
231
–
2
3
4
.
[7
]
Y.
T
a
n
g
a
n
d
J.
Zh
o
u
,
“
T
h
e
P
e
rfo
rm
a
n
c
e
o
f
P
S
O
-
S
V
M
in
I
n
f
latio
n
F
o
re
c
a
stin
g
,
”
in
S
e
rv
ice
S
y
st
e
ms
a
n
d
S
e
rv
ice
M
a
n
a
g
e
me
n
t
(
ICS
S
S
M
),
2
0
1
5
1
2
t
h
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
,
2
0
1
5
,
p
p
.
1
–
4.
[8
]
DM
A
ti
a
,
"
M
o
d
e
li
n
g
a
n
d
c
o
n
tr
o
l
P
V
-
w
in
d
h
y
b
rid
sy
st
e
m
b
a
se
d
o
n
f
u
z
z
y
lo
g
ic
c
o
n
tro
l
tec
h
n
i
q
u
e
,
”
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
0
,
n
o
.
3
,
p
p
.
4
3
1
-
4
4
1
,
2
0
1
2
.
[9
]
G
.
M
o
se
r,
F
.
Ru
m
ler,
a
n
d
J.
S
c
h
a
rler,
“
F
o
re
c
a
stin
g
A
u
strian
in
f
lati
o
n
,
”
E
lse
v
ier
,
v
o
l.
2
4
,
n
o
.
3
,
p
p
.
4
7
0
–
4
8
0
,
2
0
0
7
.
[1
0
]
I.
-
C.
Ba
c
iu
,
“
S
t
o
c
h
a
stic
M
o
d
e
ls
f
o
r
F
o
re
c
a
stin
g
In
f
latio
n
Ra
te.
Em
p
iri
c
a
l
Ev
id
e
n
c
e
f
ro
m
Ro
m
a
n
ia,”
Pro
c
e
d
ia
Ec
o
n
.
Fi
n
a
n
c
e
,
v
o
l.
2
0
,
p
p
.
4
4
–
5
2
,
2
0
1
5
.
[1
1
]
N.
R.
S
a
ri,
W
.
F
.
M
a
h
m
u
d
y
,
a
n
d
A
.
P
.
W
ib
a
w
a
,
“
Ba
c
k
p
ro
p
a
g
a
t
io
n
o
n
Ne
u
ra
l
Ne
two
rk
M
e
th
o
d
f
o
r
In
fl
a
ti
o
n
R
a
te
Fo
re
c
a
stin
g
in
In
d
o
n
e
sia
,
”
I
n
t.
J
.
S
o
ft
Co
mp
u
t.
Its
Ap
p
l.
,
2
0
1
6
.
[1
2
]
A
.
P
.
W
ib
a
w
a
a
n
d
R.
S
o
e
laim
a
n
,
“
Eff
e
c
ti
v
e
n
e
ss
A
n
a
l
y
sis
M
e
th
o
d
o
f
H
y
b
rid
Ne
u
ra
l
N
e
t
w
o
rk
s
a
n
d
F
u
z
z
y
L
o
g
ic
f
o
r
F
o
re
c
a
stin
g
F
o
re
ig
n
Ex
c
h
a
n
g
e
,
”
2
0
0
7
.
[1
3
]
L
.
Zh
a
n
g
a
n
d
J.
L
i,
“
In
fl
a
ti
o
n
F
o
r
e
c
a
stin
g
Us
i
n
g
S
u
p
p
o
rt V
e
c
to
r
Reg
re
ss
io
n
,
”
2
0
1
2
,
p
p
.
1
3
6
–
1
4
0
.
[1
4
]
S
.
P
o
o
ra
n
i
a
n
d
R.
M
u
ru
g
a
n
,
“
A
No
n
-
L
i
n
e
a
r
Co
n
tro
ll
e
r
fo
r
Fo
re
c
a
stin
g
th
e
Ri
si
n
g
De
ma
n
d
f
o
r
El
e
c
tric
Veh
icle
s
a
p
p
li
c
a
b
le t
o
In
d
i
a
n
R
o
a
d
Co
n
d
it
io
n
s
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
trica
l
a
n
d
Co
mp
u
ter
En
g
in
e
e
ri
n
g
(
IJ
ECE
)
,
v
o
l.
6
,
n
o
.
5
,
p
p
.
2
2
7
4
–
2
2
8
1
,
2
0
1
6
.
[1
5
]
H.K.
P
a
lo
a
n
d
M
ih
ir
Na
ra
y
a
n
M
o
h
a
n
ty
,
“
Cla
ss
if
ica
ti
o
n
o
f
Emo
ti
o
n
a
l
S
p
e
e
c
h
o
f
Ch
il
d
re
n
Us
in
g
Pro
b
a
b
il
ist
ic Ne
u
ra
l
Ne
two
rk
,
”
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
trica
l
a
n
d
C
o
mp
u
ter
En
g
in
e
e
rin
g
(
IJ
ECE
)
,
v
o
l
.
5
,
n
o
.
2
,
p
.
3
1
1
~
3
1
7
,
2
0
1
5
.
Evaluation Warning : The document was created with Spire.PDF for Python.