I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
pu
t
er
E
ng
ineering
(
I
J
E
CE
)
Vo
l.
15
,
No
.
4
,
A
u
g
u
s
t
20
25
,
p
p
.
4
0
9
9
~
4
1
0
8
I
SS
N:
2088
-
8
7
0
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijece.
v
15
i
4
.
pp
4
0
9
9
-
4
1
0
8
4099
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
A hybrid mo
del
t
o
mitiga
te
da
ta g
a
ps a
nd f
lu
ctuatio
ns in ta
x
revenu
e f
o
r
ecas
ti
ng
Ra
hm
a
n T
a
ufik
,
Aristo
t
eles,
I
g
it
Sa
bd
a
I
lm
a
n
D
e
p
a
r
t
me
n
t
o
f
C
o
mp
u
t
e
r
S
c
i
e
n
c
e
,
F
a
c
u
l
t
y
o
f
M
a
t
h
e
ma
t
i
c
s
a
n
d
N
a
t
u
r
a
l
S
c
i
e
n
c
e
s,
U
n
i
v
e
r
si
t
y
o
f
La
m
p
u
n
g
,
B
a
n
d
a
r
La
m
p
u
n
g
,
I
n
d
o
n
e
s
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Sep
4
,
2
0
2
4
R
ev
is
ed
Ap
r
8
,
2
0
2
5
Acc
ep
ted
Ma
y
2
5
,
1
9
3
4
Th
is
stu
d
y
a
d
d
re
ss
e
s
th
e
c
rit
i
c
a
l
c
h
a
ll
e
n
g
e
o
f
a
d
v
a
n
c
in
g
ta
x
re
v
e
n
u
e
fo
re
c
a
stin
g
m
o
d
e
ls
to
e
ffe
c
ti
v
e
l
y
h
a
n
d
le
d
isti
n
c
ti
v
e
d
a
ta
g
a
p
s
a
n
d
in
h
e
re
n
t
flu
c
tu
a
ti
o
n
s
i
n
tax
re
v
e
n
u
e
d
a
ta.
Th
e
se
c
h
a
ll
e
n
g
e
s
a
re
e
v
id
e
n
t
i
n
Lam
p
u
n
g
P
ro
v
i
n
c
e
,
In
d
o
n
e
sia
,
wh
e
re
li
m
it
e
d
te
m
p
o
ra
l
g
ra
n
u
larity
a
n
d
n
o
n
-
li
n
e
a
r
v
a
riab
il
it
y
h
in
d
e
r
a
c
c
u
ra
te
fisc
a
l
p
lan
n
i
n
g
.
De
sp
it
e
a
d
v
a
n
c
e
m
e
n
ts
in
sta
ti
stica
l,
m
a
c
h
in
e
lea
rn
i
n
g
,
a
n
d
h
y
b
ri
d
a
p
p
ro
a
c
h
e
s,
e
x
isti
n
g
m
o
d
e
ls
o
fte
n
fa
ll
sh
o
rt
i
n
sim
u
l
tan
e
o
u
sl
y
m
a
n
a
g
in
g
t
h
e
se
c
h
a
ll
e
n
g
e
s.
A
h
y
b
rid
m
o
d
e
l
in
teg
r
a
ti
n
g
ra
n
d
o
m
fo
re
st
re
g
re
ss
o
rs
fo
r
d
a
ta
i
n
terp
o
latio
n
a
n
d
l
o
n
g
sh
o
rt
-
term
m
e
m
o
ry
(LS
TM
)
f
o
r
c
a
p
tu
ri
n
g
c
o
m
p
lex
tem
p
o
ra
l
p
a
tt
e
rn
s
wa
s
p
ro
p
o
se
d
.
T
h
e
m
o
d
e
l
wa
s
e
v
a
lu
a
ted
,
a
c
h
iev
in
g
a
n
R²
o
f
0
.
8
6
,
r
o
o
t
m
e
a
n
sq
u
a
re
d
e
rr
o
r
(RM
S
E)
o
f
9
.
6
5
b
il
li
o
n
,
a
n
d
m
e
a
n
a
b
so
lu
t
e
p
e
rc
e
n
tag
e
e
rro
r
(M
APE
)
o
f
3
.
4
9
%
.
Alth
o
u
g
h
t
h
e
m
o
d
e
l
h
a
s
li
m
it
a
ti
o
n
s
i
n
g
e
n
e
r
a
li
z
in
g
to
u
n
se
e
n
d
a
ta,
t
h
e
re
su
l
ts
d
e
m
o
n
str
a
te
th
a
t
it
o
u
t
p
e
rfo
rm
s
e
x
isti
n
g
f
o
re
c
a
stin
g
m
o
d
e
ls
re
g
a
rd
in
g
a
c
c
u
ra
c
y
a
n
d
re
li
a
b
il
it
y
.
I
n
teg
ra
ti
n
g
ra
n
d
o
m
fo
re
st
re
g
re
ss
o
rs
a
n
d
l
o
n
g
sh
o
rt
-
term
m
e
m
o
ry
d
e
li
v
e
rs
a
tail
o
re
d
s
o
lu
t
io
n
to
th
e
c
o
m
p
lex
it
ies
o
f
tax
re
v
e
n
u
e
fo
r
e
c
a
stin
g
,
c
o
n
tri
b
u
ti
n
g
to
f
isc
a
l
fo
re
c
a
stin
g
a
n
d
se
tt
in
g
a
f
o
u
n
d
a
ti
o
n
f
o
r
f
u
rth
e
r
e
x
p
lo
ra
ti
o
n
in
t
o
h
y
b
rid
a
p
p
r
o
a
c
h
e
s.
K
ey
w
o
r
d
s
:
Fo
r
ec
asti
n
g
Hy
b
r
id
m
o
d
el
L
o
n
g
s
h
o
r
t
-
ter
m
m
e
m
o
r
y
R
an
d
o
m
f
o
r
est r
eg
r
ess
o
r
s
T
ax
r
ev
e
n
u
e
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
R
ah
m
an
T
au
f
ik
Dep
ar
tm
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
,
Facu
lty
o
f
Ma
th
em
atics a
n
d
Natu
r
al
Scien
ce
s
,
Un
iv
er
s
it
y
o
f
L
a
m
p
u
n
g
3
5
1
4
5
B
an
d
ar
L
a
m
p
u
n
g
,
I
n
d
o
n
esia
E
m
ail: r
ah
m
an
.
tau
f
ik
@
f
m
ip
a.
u
n
ila.
ac
.
id
1.
I
NT
RO
D
UCT
I
O
N
T
ax
r
ev
en
u
e
is
an
im
p
o
r
tan
t
co
m
p
o
n
en
t
o
f
p
u
b
lic
f
in
an
ce
,
s
u
p
p
o
r
tin
g
in
f
r
astru
ct
u
r
e
d
e
v
elo
p
m
en
t,
p
u
b
lic
s
er
v
ices,
a
n
d
ec
o
n
o
m
ic
g
r
o
wth
.
I
n
L
am
p
u
n
g
Pro
v
in
c
e,
I
n
d
o
n
esia,
tax
r
ev
e
n
u
e
r
ep
r
esen
ts
a
s
ig
n
if
ican
t
co
m
p
o
n
en
t
o
f
th
e
r
eg
io
n
al
b
u
d
g
et,
p
r
o
v
id
i
n
g
v
ar
io
u
s
d
e
v
elo
p
m
en
t
in
itiativ
es.
Ho
we
v
er
,
f
lu
ctu
atio
n
s
in
f
in
an
cial
co
n
d
itio
n
s
,
h
i
g
h
p
o
v
er
ty
lev
els,
lim
ited
f
is
ca
l
ca
p
a
city
,
an
d
r
ef
o
r
m
s
in
lo
ca
l
tax
a
tio
n
s
y
s
tem
s
o
f
ten
lead
to
d
is
cr
ep
a
n
cies
b
etwe
e
n
p
r
o
jecte
d
an
d
ac
tu
al
ta
x
r
ev
en
u
es
[
1
]
,
[
2
]
.
A
p
r
elim
in
ar
y
an
aly
s
is
o
f
tax
r
ev
en
u
e
d
ata
in
L
am
p
u
n
g
Pr
o
v
in
ce
f
r
o
m
1
9
9
5
t
o
2
0
2
3
r
e
v
e
als
a
tr
en
d
-
d
r
iv
e
n
g
r
o
wth
p
att
er
n
,
with
an
a
v
er
ag
e
an
n
u
al
g
r
o
wth
r
ate
o
f
2
1
.
8
7
%
an
d
a
v
ar
ian
ce
o
f
1
.
1
7
%.
Desp
ite
th
is
g
r
o
wth
,
a
h
ig
h
s
tan
d
ar
d
d
e
v
iatio
n
o
f
9
1
.
2
8
%
o
f
th
e
m
ea
n
i
n
d
icate
s
s
u
b
s
tan
tial
v
ar
iab
ilit
y
,
co
m
p
o
u
n
d
e
d
b
y
s
ea
s
o
n
al
im
p
ac
ts
c
o
n
tr
ib
u
tin
g
2
4
.
3
4
%
to
th
e
o
v
e
r
all
v
ar
iatio
n
.
T
h
e
s
e
f
in
d
in
g
s
h
ig
h
lig
h
t
th
e
co
m
p
lex
ity
o
f
lo
n
g
-
ter
m
g
r
o
wt
h
tr
en
d
s
,
s
ea
s
o
n
al
f
lu
ctu
atio
n
s
,
a
n
d
n
o
n
-
lin
ea
r
v
ar
iab
ilit
y
in
ta
x
r
e
v
en
u
e
d
ata.
T
h
e
ch
allen
g
e
o
f
f
o
r
ec
asti
n
g
is
f
u
r
th
er
co
m
p
o
u
n
d
e
d
b
y
th
e
d
ata
g
ap
s
,
in
clu
d
in
g
lim
ited
tem
p
o
r
al
g
r
an
u
lar
ity
,
wh
ich
r
ef
e
r
s
to
th
e
av
ailab
ilit
y
o
f
o
n
ly
2
8
y
ea
r
s
o
f
an
n
u
al
in
ter
v
als
.
T
h
ese
ch
allen
g
es
u
n
d
er
s
co
r
e
th
e
n
ee
d
f
o
r
a
d
v
an
ce
d
f
o
r
ec
asti
n
g
m
o
d
els
to
ad
d
r
ess
d
ata
g
ap
s
an
d
m
an
a
g
e
in
h
er
en
t
f
lu
ctu
atio
n
s
in
ta
x
r
e
v
en
u
e
d
ata.
N
u
m
e
r
o
u
s
s
t
u
d
i
es
h
a
v
e
d
e
v
e
l
o
p
e
d
t
a
x
r
e
v
e
n
u
e
f
o
r
e
c
as
t
i
n
g
m
o
d
e
l
s
a
c
r
o
s
s
v
a
r
i
o
u
s
r
e
g
i
o
n
s
a
n
d
e
x
p
l
o
r
e
d
d
i
f
f
e
r
e
n
t
m
o
d
e
l
e
x
t
e
n
s
i
o
n
s
.
Fo
r
i
n
s
t
a
n
c
e
,
S
t
r
ei
m
i
k
i
e
n
e
e
t
a
l.
[
3
]
u
t
i
l
i
z
e
d
a
n
a
u
t
o
r
e
g
r
e
s
s
i
v
e
i
n
t
e
g
r
a
t
e
d
m
o
v
i
n
g
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
4
,
Au
g
u
s
t
20
25
:
4
0
9
9
-
4108
4100
a
v
e
r
a
g
e
(
A
R
I
MA
)
m
o
d
e
l
t
o
f
o
r
e
c
a
s
t
t
o
t
a
l
t
a
x
r
e
v
e
n
u
e
,
i
d
e
n
ti
f
y
i
n
g
s
i
g
n
i
f
i
c
a
n
t
v
a
r
ia
b
l
e
s
a
f
f
e
ct
i
n
g
t
a
x
r
e
v
e
n
u
e
i
n
P
a
k
i
s
t
a
n
.
B
u
x
t
o
n
e
t
a
l
.
[
4
]
d
e
m
o
n
s
t
r
a
t
e
d
t
h
a
t
m
u
l
t
i
-
l
a
y
e
r
p
e
r
c
e
p
t
r
o
n
(
M
L
P
)
o
u
t
p
e
r
f
o
r
m
e
d
t
h
e
l
o
n
g
s
h
o
r
t
-
t
e
r
m
m
e
m
o
r
y
(
L
S
T
M
)
i
n
p
r
e
d
i
c
t
i
n
g
t
a
x
f
o
r
t
h
e
s
t
a
t
e
o
f
I
l
l
i
n
o
is
.
L
a
h
i
r
i
a
n
d
Y
a
n
g
[
5
]
a
d
o
p
t
e
d
a
m
i
x
e
d
-
f
r
e
q
u
e
n
c
y
v
e
c
t
o
r
a
u
t
o
r
e
g
r
e
s
s
i
o
n
(
M
F
-
VA
R
)
m
o
d
e
l
t
o
i
m
p
r
o
v
e
N
e
w
Y
o
r
k
S
t
a
t
e
t
a
x
r
e
v
e
n
u
e
f
o
r
e
c
a
s
ts
,
es
p
e
c
i
al
l
y
i
n
r
e
s
p
o
n
s
e
t
o
t
h
e
v
o
l
a
t
il
i
t
y
i
n
t
r
o
d
u
c
e
d
b
y
t
h
e
c
o
r
o
n
a
v
i
r
u
s
d
i
s
ea
s
e
(
C
OV
I
D
-
19
)
p
a
n
d
e
m
i
c
.
I
n
W
e
n
z
h
o
u
C
it
y
,
X
ie
[
6
]
u
s
e
d
m
u
l
t
i
p
l
e
l
i
n
e
a
r
r
e
g
r
e
s
s
i
o
n
(
M
L
R
)
a
n
d
M
L
P
m
o
d
e
l
s
t
o
f
o
r
e
c
a
s
t
t
a
x
r
e
v
e
n
u
e
,
w
h
i
l
e
a
l
s
o
a
n
a
l
y
z
i
n
g
t
a
x
a
t
i
o
n
f
a
c
t
o
r
s
.
S
e
g
u
n
[
7
]
e
x
a
m
i
n
e
d
a
n
d
c
o
m
p
a
r
e
d
M
L
R
,
s
e
a
s
o
n
a
l
a
u
t
o
r
e
g
r
e
s
s
i
v
e
i
n
t
e
g
r
a
te
d
m
o
v
i
n
g
a
v
e
r
a
g
e
(
S
AR
I
M
A
)
,
a
n
d
L
S
T
M
,
u
t
il
i
z
in
g
m
u
l
t
i
p
l
e
i
n
d
e
p
e
n
d
e
n
t
v
a
r
i
a
b
l
e
s
t
o
f
o
r
e
c
a
s
t
t
a
x
r
e
v
e
n
u
e
i
n
N
i
g
e
r
i
a
.
I
n
t
h
e
s
a
m
e
r
e
g
i
o
n
,
T
a
s
i
’
u
e
t a
l
.
[
8
]
d
e
m
o
n
s
t
r
a
t
e
d
t
h
a
t SA
R
I
M
A
o
u
t
p
e
r
f
o
r
m
e
d
t
h
e
H
o
l
t
-
W
i
n
t
e
r
s
m
o
d
e
l
,
a
l
s
o
k
n
o
w
n
a
s
t
r
i
p
l
e
e
x
p
o
n
e
n
t
i
a
l
s
m
o
o
t
h
i
n
g
(
T
E
S
)
.
I
n
L
a
m
p
u
n
g
P
r
o
v
i
n
c
e
,
K
u
r
n
i
a
s
a
r
i
a
n
d
R
a
m
a
d
h
a
n
i
[
9
]
e
n
c
o
u
n
t
e
r
e
d
c
h
a
l
l
e
n
g
e
s
i
n
a
c
c
u
r
a
t
e
l
y
f
o
r
e
c
a
s
t
i
n
g
a
s
p
e
c
i
f
ic
t
a
x
r
e
v
e
n
u
e
d
u
e
t
o
c
o
m
p
l
e
x
,
n
o
n
-
l
i
n
e
a
r
d
a
t
a
p
a
t
t
e
r
n
s
.
T
h
is
le
d
t
h
e
m
t
o
p
r
o
p
o
s
e
a
n
a
r
t
i
f
i
c
i
al
n
e
u
r
a
l
n
e
t
w
o
r
k
(
AN
N
)
m
o
d
e
l
t
h
a
t
a
c
h
i
e
v
e
d
h
i
g
h
a
c
c
u
r
a
c
y
.
H
o
w
e
v
e
r
,
i
n
a
s
i
m
ila
r
c
a
s
e
,
I
n
f
u
s
i
e
t
a
l
.
[
1
0
]
f
o
u
n
d
t
h
a
t
M
L
R
w
as
m
o
r
e
a
c
c
u
r
a
t
e
t
h
a
n
t
h
e
A
NN
m
o
d
e
l
.
W
h
il
e
t
h
es
e
s
t
u
d
i
es
a
p
p
l
i
e
d
f
o
r
e
c
a
s
t
i
n
g
m
o
d
e
ls
t
o
a
d
d
r
e
s
s
r
e
g
i
o
n
a
l
t
a
x
r
e
v
e
n
u
e
c
h
a
l
l
e
n
g
e
s
,
t
h
e
y
p
r
e
d
o
m
i
n
a
n
t
l
y
r
e
l
i
e
d
o
n
p
r
e
v
a
i
l
i
n
g
m
e
t
h
o
d
o
l
o
g
i
e
s
a
n
d
l
a
c
k
e
d
t
h
e
s
o
p
h
i
s
ti
c
a
ti
o
n
t
o
e
n
h
a
n
c
e
a
c
c
u
r
a
c
y
a
c
r
o
s
s
d
i
v
e
r
s
e
te
m
p
o
r
a
l
s
c
a
l
es
,
l
e
a
v
i
n
g
f
o
r
e
c
a
s
ti
n
g
r
e
l
i
a
b
i
li
t
y
u
n
a
d
d
r
e
s
s
e
d
.
Su
b
s
eq
u
en
t
ad
v
a
n
ce
s
in
tax
r
ev
en
u
e
f
o
r
ec
asti
n
g
h
av
e
f
o
cu
s
ed
o
n
im
p
r
o
v
in
g
th
e
ac
cu
r
ac
y
an
d
r
o
b
u
s
tn
ess
o
f
f
o
r
ec
asti
n
g
m
o
d
els
th
r
o
u
g
h
ad
v
a
n
ce
d
m
eth
o
d
o
lo
g
ies,
in
clu
d
in
g
h
y
b
r
id
ap
p
r
o
ac
h
es.
I
lic
et
a
l.
[
1
1
]
p
r
o
p
o
s
ed
th
e
ex
p
lain
ab
le
b
o
o
s
ted
lin
ea
r
r
eg
r
ess
io
n
(
E
B
L
R
)
alg
o
r
ith
m
th
at
lev
er
ag
es
d
aily
d
ata
g
r
an
u
lar
ity
to
im
p
r
o
v
e
m
o
d
el
p
er
f
o
r
m
a
n
ce
b
y
s
eq
u
e
n
tially
in
co
r
p
o
r
atin
g
v
ar
iab
les,
ac
h
i
ev
in
g
a
n
o
r
m
alize
d
r
o
o
t
m
ea
n
s
q
u
a
r
ed
er
r
o
r
(
R
M
SE)
o
f
0
.
1
5
2
8
.
T
h
ay
y
ib
et
a
l.
[
1
2
]
em
p
lo
y
ed
t
h
e
th
eta
tr
ig
o
n
o
m
etr
ic
s
ea
s
o
n
ality
B
o
x
-
C
o
x
tr
an
s
f
o
r
m
atio
n
AR
I
MA
er
r
o
r
s
tr
en
d
s
ea
s
o
n
al
co
m
p
o
n
e
n
ts
(
T
B
AT
S)
m
o
d
el
f
o
r
f
o
r
ec
asti
n
g
g
o
o
d
s
an
d
s
er
v
ices
ta
x
r
ev
en
u
e
in
I
n
d
ia.
I
t
was
s
h
o
wn
t
o
b
e
m
o
r
e
ac
cu
r
ate
th
an
n
eu
r
al
n
etwo
r
k
m
o
d
els,
with
a
n
R
MSE
o
f
0
.
1
4
1
.
Fath
o
n
i
a
n
d
Sap
u
tr
a
[
1
3
]
em
p
l
o
y
ed
t
h
e
A
R
I
MA
B
o
x
-
J
en
k
in
s
m
o
d
el
to
f
o
r
ec
ast
v
alu
e
-
a
d
d
ed
tax
(
VAT
)
r
e
v
en
u
e
in
I
n
d
o
n
e
s
ia.
T
h
ey
d
e
m
o
n
s
tr
ated
t
h
at
t
h
e
r
esu
ltin
g
f
o
r
ec
ast
clo
s
ely
alig
n
ed
with
ac
tu
al
VAT
r
ev
en
u
e,
e
x
h
ib
itin
g
a
n
R
MSE
o
f
2
.
7
6
5
.
E
x
ten
s
iv
e
s
tu
d
ies
o
n
h
y
b
r
id
m
o
d
els
d
em
o
n
s
tr
ated
p
o
ten
tial
in
in
teg
r
atin
g
f
ea
tu
r
e
s
elec
tio
n
a
n
d
tem
p
o
r
al
m
o
d
e
lin
g
.
T
ic
o
n
a
et
a
l.
[
1
4
]
p
r
esen
ted
a
h
y
b
r
i
d
m
o
d
el
co
m
b
in
in
g
g
en
etic
alg
o
r
it
h
m
s
an
d
n
eu
r
a
l
n
etwo
r
k
s
to
f
o
r
ec
ast
tax
r
e
v
en
u
e
i
n
B
r
az
il,
ac
h
iev
in
g
m
o
r
e
ac
cu
r
ate
r
esu
lts
with
a
m
ea
n
a
b
s
o
lu
te
p
e
r
ce
n
t
ag
e
er
r
o
r
(
MA
PE)
o
f
2
.
3
7
%
a
n
d
a
s
ig
n
if
ica
n
t
r
ed
u
ctio
n
i
n
r
elativ
e
er
r
o
r
.
Sm
y
l
[
1
5
]
in
tr
o
d
u
ce
d
a
d
y
n
am
ic
co
m
p
u
tatio
n
al
n
eu
r
al
n
etwo
r
k
s
y
s
tem
th
at
in
teg
r
ates
ex
p
o
n
en
tial
s
m
o
o
th
in
g
with
L
STM
,
ad
d
r
ess
in
g
is
s
u
es
r
elate
d
to
tem
p
o
r
al
r
eso
lu
tio
n
,
a
n
d
f
o
r
ec
asti
n
g
m
o
n
th
l
y
,
an
n
u
al,
an
d
q
u
ar
ter
ly
d
ata.
Ho
wev
er
,
th
is
s
y
s
tem
wa
s
le
s
s
ef
f
ec
tiv
e
f
o
r
d
aily
an
d
wee
k
ly
d
ata.
Fer
d
o
u
s
h
et
a
l.
[
1
6
]
p
r
o
p
o
s
ed
a
h
y
b
r
i
d
m
o
d
el
th
at
co
m
b
in
es
r
an
d
o
m
f
o
r
est
f
o
r
f
ea
tu
r
e
s
elec
tio
n
with
b
id
ir
ec
tio
n
al
lo
n
g
s
h
o
r
t
-
ter
m
m
em
o
r
y
(
B
iLST
M)
f
o
r
f
o
r
ec
asti
n
g
.
T
h
is
ap
p
r
o
ac
h
y
ield
ed
an
R
MSE
o
f
0
.
4
0
9
0
,
d
em
o
n
s
tr
atin
g
s
u
p
e
r
io
r
p
er
f
o
r
m
a
n
ce
co
m
p
ar
ed
to
tr
a
d
itio
n
al
L
ST
M
m
o
d
els.
Ho
s
s
ain
an
d
I
s
m
ail
[
1
7
]
p
r
o
p
o
s
ed
a
h
y
b
r
i
d
m
o
d
el
co
m
b
i
n
in
g
ex
p
o
n
e
n
tial
au
to
r
e
g
r
ess
iv
e
with
Ma
r
k
o
v
-
s
witch
in
g
g
en
er
ali
ze
d
au
to
r
eg
r
ess
iv
e
co
n
d
itio
n
a
l
h
eter
o
s
k
ed
asti
city
(
MSGAR
C
H)
to
ad
d
r
ess
th
e
is
s
u
es
o
f
v
o
latilit
y
an
d
n
o
n
l
in
ea
r
ity
in
f
in
a
n
cial
tim
e
s
er
ies.
T
h
eir
f
in
d
in
g
s
in
d
icate
d
th
at
th
is
m
o
d
el
o
u
t
p
er
f
o
r
m
e
d
AR
I
M
A
an
d
MSGARC
H
m
o
d
els,
p
ar
ticu
lar
ly
i
n
c
ap
tu
r
in
g
d
o
w
n
s
id
e
r
is
k
.
L
ar
r
o
u
s
s
i
et
a
l
.
[
1
8
]
in
tr
o
d
u
ce
d
a
h
y
b
r
id
d
ee
p
lear
n
i
n
g
m
o
d
el
th
at
in
teg
r
ates
au
to
e
n
co
d
er
s
with
s
tack
ed
L
STM
to
en
h
a
n
ce
th
e
ac
cu
r
ac
y
o
f
to
u
r
is
m
d
em
an
d
f
o
r
ec
asti
n
g
.
T
h
is
ap
p
r
o
ac
h
r
esu
lted
in
an
R
-
s
q
u
ar
ed
(
R
2
)
o
f
9
6
.
5
2
an
d
R
MSE
o
f
0
.
0
0
0
9
9
2
,
d
em
o
n
s
tr
atin
g
th
e
r
o
b
u
s
tn
ess
o
f
th
is
m
o
d
el.
Desp
ite
th
ese
ad
v
an
ce
m
e
n
ts
,
ex
is
tin
g
s
tu
d
ies
h
av
e
p
r
im
ar
il
y
f
o
cu
s
ed
o
n
i
m
p
r
o
v
in
g
eit
h
er
m
o
d
elin
g
tem
p
o
r
al
p
atter
n
s
[
1
2
]
–
[
1
4
]
,
[
1
6
]
–
[
1
8
]
o
r
d
ata
g
r
a
n
u
lar
ity
in
d
iv
i
d
u
al
ly
[
1
1
]
,
[
1
5
]
,
lea
v
in
g
a
cr
itic
al
g
ap
in
u
n
if
ied
ap
p
r
o
ac
h
es
th
at
s
im
u
ltan
eo
u
s
ly
ad
d
r
ess
ir
r
eg
u
lar
ities
in
d
ata
an
d
tem
p
o
r
al
in
c
o
n
s
is
ten
cies
in
tax
r
ev
e
n
u
e
f
o
r
ec
asti
n
g
.
T
h
is
g
ap
u
n
d
er
s
co
r
es
th
e
n
ee
d
f
o
r
a
h
y
b
r
id
ap
p
r
o
ac
h
ca
p
ab
le
o
f
r
e
s
o
lv
in
g
b
o
th
ch
a
llen
g
es si
m
u
ltan
eo
u
s
ly
.
T
h
e
o
b
jectiv
e
o
f
th
is
s
tu
d
y
is
to
p
r
o
p
o
s
e
a
f
o
r
e
ca
s
tin
g
ap
p
r
o
ac
h
th
at
s
im
u
ltan
eo
u
s
ly
ad
d
r
ess
es
b
o
th
d
ata
g
ap
s
an
d
f
lu
ctu
atio
n
s
in
tax
r
ev
en
u
e
d
ata,
wh
ich
ex
is
tin
g
s
tu
d
ies
h
av
e
y
et
t
o
ad
d
r
ess
co
m
p
r
e
h
en
s
iv
ely
.
T
h
e
p
r
o
p
o
s
ed
h
y
b
r
id
m
o
d
el
c
o
m
b
in
es
th
e
s
tr
en
g
th
s
o
f
r
an
d
o
m
f
o
r
est
r
eg
r
ess
o
r
(
R
FR
)
f
o
r
d
ata
in
te
r
p
o
latio
n
an
d
lo
n
g
s
h
o
r
t
-
ter
m
m
em
o
r
y
(
L
STM
)
f
o
r
f
o
r
ec
asti
n
g
ta
x
r
ev
en
u
e,
o
f
f
er
in
g
a
s
o
lu
tio
n
t
o
th
ese
c
h
allen
g
es.
R
F
R
is
an
ef
f
ec
tiv
e
m
o
d
el
f
o
r
a
d
d
r
ess
in
g
c
o
m
p
lex
d
ata
i
n
ter
p
o
latio
n
ch
allen
g
es
in
v
ar
io
u
s
f
ield
s
.
Fo
r
ex
am
p
le,
Ach
ite
et
a
l.
[
1
9
]
s
u
cc
ess
f
u
lly
p
r
ed
icted
a
n
n
u
al
r
a
in
f
all
in
n
o
r
th
er
n
Alg
er
ia,
ac
h
iev
in
g
a
h
ig
h
R
²
o
f
0
.
9
5
2
4
.
Sah
o
o
et
a
l.
[
2
0
]
d
e
m
o
n
s
tr
ated
th
at
R
FR
o
u
tp
er
f
o
r
m
ed
tr
ad
itio
n
al
m
o
d
els
s
u
ch
as
Kr
ig
in
g
an
d
in
v
er
s
e
d
is
tan
ce
weig
h
tin
g
i
n
esti
m
atin
g
cr
o
p
y
ield
s
with
f
in
er
s
p
atial
r
eso
lu
tio
n
.
So
n
g
et
a
l.
[
2
1
]
also
s
h
o
wed
th
at
R
FR
s
ig
n
if
ican
tly
en
h
a
n
ce
d
th
e
r
eso
lu
tio
n
o
f
n
u
tr
ien
t
d
is
tr
ib
u
tio
n
m
ap
s
th
r
o
u
g
h
ef
f
ec
tiv
e
d
ata
in
ter
p
o
latio
n
.
T
h
er
ef
o
r
e,
R
FR
is
p
r
o
p
o
s
ed
to
im
p
r
o
v
e
th
e
g
r
an
u
lar
ity
o
f
i
n
ter
p
o
lated
v
alu
es
f
r
o
m
an
n
u
al
to
m
o
n
th
ly
d
ata.
I
n
co
n
tr
ast,
L
S
T
M
h
as
b
ee
n
r
ec
o
g
n
ized
as
a
p
r
o
m
in
e
n
t
ap
p
r
o
ac
h
i
n
tim
e
s
er
ies
f
o
r
ec
asti
n
g
f
o
r
its
ab
ilit
y
to
m
o
d
el
lo
n
g
-
ter
m
d
ep
e
n
d
en
cies,
as
d
em
o
n
s
tr
ated
in
s
tu
d
ies
s
u
ch
as
[
4
]
,
[
7
]
,
an
d
[
1
5
]
.
T
h
e
r
ev
iewe
d
s
tu
d
ies
in
d
icate
th
at
L
STM
is
ad
ep
t
at
ca
p
tu
r
in
g
i
n
tr
icate
h
is
to
r
ical
d
ata
an
d
ch
allen
g
in
g
tem
p
o
r
al
d
y
n
am
ics
[
2
2
]
,
m
a
k
in
g
it we
ll
-
s
u
ited
f
o
r
a
p
p
licatio
n
s
in
tax
r
ev
en
u
e
f
o
r
ec
asti
n
g
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
A
h
yb
r
id
mo
d
el
t
o
mitig
a
te
d
a
ta
g
a
p
s
a
n
d
flu
ctu
a
tio
n
s
in
ta
x
r
ev
en
u
e
fo
r
ec
a
s
tin
g
(
R
a
h
ma
n
Ta
u
fik
)
4101
T
h
is
s
tu
d
y
in
tr
o
d
u
ce
s
a
h
y
b
r
id
f
o
r
ec
asti
n
g
m
o
d
el
th
at
in
te
g
r
ates
R
F
R
f
o
r
ef
f
ec
tiv
e
d
ata
in
t
er
p
o
latio
n
an
d
L
STM
f
o
r
ca
p
tu
r
i
n
g
co
m
p
lex
tem
p
o
r
al
p
atter
n
s
,
ad
d
r
ess
in
g
b
o
th
d
ata
g
ap
s
an
d
f
lu
ctu
atio
n
s
in
tax
r
ev
en
u
e.
B
y
co
m
b
in
in
g
t
h
ese
m
eth
o
d
s
,
th
e
m
o
d
el
en
h
a
n
ce
s
th
e
ac
cu
r
ac
y
a
n
d
r
eliab
ilit
y
o
f
tax
r
ev
en
u
e
p
r
ed
ictio
n
s
,
s
p
ec
if
ically
f
o
r
L
am
p
u
n
g
Pro
v
in
ce
.
T
h
is
in
t
eg
r
ated
a
p
p
r
o
ac
h
o
v
er
c
o
m
es
th
e
lim
itatio
n
s
o
f
p
r
ev
io
u
s
m
o
d
els,
wh
ich
ty
p
ically
d
o
n
o
t
co
m
p
r
eh
en
s
iv
ely
ad
d
r
ess
th
e
f
o
r
ec
asti
n
g
ch
allen
g
e,
an
d
o
f
f
er
s
a
f
r
am
ewo
r
k
ap
p
licab
le
to
s
im
ilar
f
is
ca
l f
o
r
ec
asti
n
g
ch
allen
g
e
s
g
lo
b
ally
.
2.
M
E
T
H
O
D
T
h
is
s
ec
tio
n
d
escr
ib
es
th
e
m
eth
o
d
o
lo
g
y
u
s
ed
in
t
h
e
s
tu
d
y
.
I
t
o
u
tlin
es
th
e
r
esear
ch
ap
p
r
o
ac
h
a
n
d
ex
p
lain
s
th
e
p
r
o
p
o
s
ed
m
eth
o
d
.
T
h
e
m
o
d
el
in
teg
r
ates
R
F
R
f
o
r
in
ter
p
o
latio
n
an
d
L
STM
f
o
r
tim
e
s
er
ies
f
o
r
ec
asti
n
g
.
2
.
1
.
Resea
rc
h desi
g
n
Fig
u
r
e
1
illu
s
tr
ates
th
e
r
esear
ch
d
esig
n
em
p
lo
y
ed
in
th
is
s
tu
d
y
,
o
u
tlin
in
g
th
e
s
tep
s
i
n
v
o
lv
e
d
in
f
ac
ilit
atin
g
th
e
p
r
o
p
o
s
ed
R
FR
-
L
STM
h
y
b
r
id
m
o
d
el
f
o
r
tax
r
ev
en
u
e
f
o
r
ec
asti
n
g
.
T
h
e
p
r
o
ce
s
s
b
eg
in
s
with
d
ata
co
llectio
n
f
r
o
m
t
h
e
L
am
p
u
n
g
Pro
v
in
ce
C
en
tr
al
Statis
ti
c
s
Ag
en
cy
[
2
3
]
,
co
v
er
in
g
ta
x
r
ev
en
u
e
d
ata
f
r
o
m
1
9
9
5
to
2
0
2
3
.
T
h
e
d
ataset
was
s
o
u
r
ce
d
f
r
o
m
g
o
v
er
n
m
en
t
r
e
p
o
r
ts
an
d
th
en
co
n
v
er
te
d
in
to
C
SV
f
o
r
m
at,
r
esu
ltin
g
in
2
8
r
o
ws,
with
co
l
u
m
n
s
r
ep
r
esen
tin
g
th
e
y
ea
r
an
d
co
r
r
esp
o
n
d
in
g
tax
r
e
v
en
u
e
v
alu
es.
Fig
u
r
e
1
.
R
esear
ch
d
esig
n
Pre
lim
in
ar
y
an
aly
s
is
is
co
n
d
u
cted
to
ex
p
lo
r
e
th
e
ch
a
r
ac
ter
is
tics
o
f
th
e
d
ata.
T
h
is
in
c
lu
d
es
ex
p
lo
r
ato
r
y
d
ata
a
n
aly
s
is
to
id
en
tify
an
o
m
alies,
tr
en
d
a
n
aly
s
is
to
u
n
co
v
er
lo
n
g
-
ter
m
p
a
tter
n
s
,
s
ea
s
o
n
ality
an
aly
s
is
to
d
etec
t
r
ec
u
r
r
in
g
f
l
u
ctu
atio
n
s
,
a
n
d
s
tatio
n
ar
ity
a
n
aly
s
is
to
v
er
i
f
y
c
o
n
s
is
ten
t
s
tatis
tical
p
r
o
p
er
ties
o
v
er
tim
e.
Nex
t,
d
ata
p
r
e
p
r
o
ce
s
s
in
g
is
ca
r
r
ied
o
u
t to
en
h
an
ce
d
ata
q
u
ality
.
Scalin
g
is
p
er
f
o
r
m
ed
u
s
in
g
a
r
o
b
u
s
t
s
ca
ler
,
wh
ich
is
ch
o
s
en
f
o
r
its
r
eliab
ilit
y
in
h
an
d
lin
g
o
u
tlier
s
u
s
in
g
th
e
m
ed
ian
an
d
in
ter
q
u
ar
tile
r
an
g
e
in
s
tead
o
f
th
e
m
ea
n
an
d
s
tan
d
ar
d
d
ev
iatio
n
.
Dif
f
er
e
n
cin
g
ad
d
r
ess
es
n
on
-
s
tatio
n
ar
y
tr
en
d
s
u
s
in
g
f
ir
s
t
-
o
r
d
e
r
d
if
f
er
en
cin
g
,
with
s
tatio
n
ar
ity
ass
es
s
ed
th
r
o
u
g
h
th
e
au
g
m
en
ted
Dick
ey
-
Fu
ller
(
ADF)
test
.
T
h
en
,
R
F
R
i
s
ap
p
lied
to
in
ter
p
o
late
an
n
u
al
d
ata
in
to
m
o
n
th
ly
v
alu
es,
e
n
ab
lin
g
f
in
er
tem
p
o
r
al
r
eso
lu
tio
n
[
1
9
]
–
[
2
1
]
.
T
h
e
d
ataset
is
th
en
s
p
lit
in
to
1
9
9
5
to
2
0
1
7
f
o
r
tr
ain
in
g
(
a
p
p
r
o
x
im
ately
8
0
%)
a
n
d
2
0
1
8
t
o
2
0
2
3
f
o
r
test
in
g
(
ap
p
r
o
x
im
ately
2
0
%),
en
s
u
r
i
n
g
th
at
th
e
test
s
et
r
ep
r
esen
ts
u
n
s
ee
n
d
ata.
Fu
r
th
er
m
o
r
e
,
th
e
L
STM
m
o
d
el
is
tr
ain
ed
o
n
th
e
p
r
e
p
r
o
ce
s
s
ed
m
o
n
th
ly
t
r
ain
in
g
d
ata.
E
x
p
an
d
i
n
g
win
d
o
w
cr
o
s
s
-
v
alid
atio
n
with
f
iv
e
f
o
ld
s
is
ap
p
lied
to
th
e
tr
ain
in
g
d
ata
u
s
in
g
T
im
eSer
iesS
p
lit.
B
y
g
r
ad
u
ally
in
cr
ea
s
in
g
th
e
s
ize
o
f
th
e
t
r
ain
in
g
s
et
wh
ile
k
ee
p
in
g
a
s
ep
ar
a
te
v
alid
atio
n
s
et,
th
is
tech
n
iq
u
e
en
ab
les th
e
m
o
d
el
to
ca
p
tu
r
e
tem
p
o
r
al
p
atter
n
s
an
d
a
d
ap
t
to
s
eq
u
e
n
tial
d
ata
ef
f
ec
tiv
ely
.
M
o
r
eo
v
er
,
it
m
ai
n
tain
s
th
e
tem
p
o
r
al
in
teg
r
ity
o
f
th
e
d
ataset
an
d
m
in
im
izes
d
ata
leak
ag
e,
en
s
u
r
in
g
th
e
v
alid
atio
n
d
ata
r
em
ain
s
u
n
s
ee
n
d
u
r
in
g
tr
ain
in
g
[
2
4
]
,
[
2
5
]
.
I
n
ad
d
itio
n
,
h
y
p
er
p
ar
a
m
eter
tu
n
in
g
is
p
er
f
o
r
m
ed
u
s
in
g
t
h
e
Ker
as
T
u
n
er
lib
r
ar
y
[
2
6
]
to
o
p
tim
ize
th
e
m
o
d
el
co
n
f
ig
u
r
a
tio
n
an
d
co
m
p
u
tatio
n
al
ef
f
icie
n
cy
.
Fu
r
th
er
m
o
r
e,
th
e
m
o
d
el
i
s
ev
alu
ated
o
n
th
e
test
d
ata
to
ass
es
s
its
g
en
er
aliza
tio
n
ab
ilit
y
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
4
,
Au
g
u
s
t
20
25
:
4
0
9
9
-
4108
4102
T
h
e
m
e
th
o
d
o
l
o
g
y
co
n
cl
u
d
es
with
th
e
e
v
alu
atio
n
o
f
th
e
p
r
o
p
o
s
ed
m
o
d
el.
T
h
e
p
e
r
f
o
r
m
a
n
ce
o
f
th
e
p
r
o
p
o
s
ed
h
y
b
r
id
m
o
d
el
was
co
m
p
ar
ed
t
o
v
ar
io
u
s
b
en
ch
m
a
r
k
m
eth
o
d
s
,
in
clu
d
in
g
n
o
n
-
h
y
b
r
id
ap
p
r
o
ac
h
es
s
u
ch
as
ANN,
ML
R
,
L
STM
,
an
d
AR
I
MA
,
as
we
ll
as
h
y
b
r
id
ap
p
r
o
ac
h
es
lik
e
R
FR
-
AR
I
MA
a
n
d
R
FR
-
T
E
S.
T
h
ese
m
o
d
els
wer
e
s
elec
ted
b
ased
o
n
th
eir
ex
ten
s
iv
e
u
s
e
i
n
p
r
ac
tic
al
tim
e
-
s
er
ies
p
r
o
b
lem
s
[
3
]
,
[
4
]
,
[
6
]
–
[
8
]
an
d
p
r
io
r
s
tu
d
ies r
elate
d
to
f
o
r
ec
asti
n
g
L
am
p
u
n
g
tax
r
ev
e
n
u
e
[
9
]
,
[
1
0
]
.
All c
o
m
p
ar
is
o
n
s
wer
e
p
er
f
o
r
m
ed
u
s
in
g
th
e
s
am
e
d
ataset.
Mo
r
eo
v
er
,
th
ese
p
er
f
o
r
m
an
ce
s
ar
e
ev
a
lu
ated
u
s
in
g
MA
PE,
R
MSE
,
an
d
R
2
,
wh
i
ch
ar
e
s
elec
ted
f
o
r
th
eir
ab
ilit
y
to
m
ea
s
u
r
e
r
elativ
e
ac
cu
r
ac
y
,
av
er
ag
e
er
r
o
r
m
ag
n
itu
d
e,
an
d
v
ar
ian
ce
e
x
p
la
n
atio
n
,
h
ig
h
lig
h
tin
g
th
eir
r
elev
an
ce
to
ass
ess
in
g
b
o
th
ir
r
eg
u
lar
ities
in
d
ata
an
d
te
m
p
o
r
al
in
co
n
s
is
ten
cies
in
tax
r
ev
en
u
e
f
o
r
ec
asti
n
g
.
[
2
7
]
,
[
2
8
]
.
2
.
2
.
P
r
o
po
s
ed
m
et
ho
d
A
h
y
b
r
id
r
esear
ch
m
o
d
el
is
p
r
o
p
o
s
ed
to
im
p
r
o
v
e
th
e
a
cc
u
r
ac
y
o
f
tax
r
ev
en
u
e
f
o
r
e
ca
s
tin
g
b
y
co
m
b
in
in
g
two
ad
v
a
n
ce
d
tec
h
n
iq
u
es,
n
a
m
ely
R
FR
an
d
L
STM
.
T
h
e
R
FR
f
o
cu
s
es
o
n
tr
an
s
f
o
r
m
in
g
lo
w
-
f
r
eq
u
e
n
cy
a
n
n
u
al
d
ata
in
to
h
i
g
h
-
f
r
e
q
u
en
c
y
m
o
n
th
ly
d
ata,
a
d
d
r
ess
in
g
d
ata
g
ap
s
.
W
h
ile,
t
h
e
L
STM
lev
er
a
g
es
its
ab
ili
ty
to
ca
p
tu
r
e
c
o
m
p
lex
tem
p
o
r
al
d
e
p
en
d
e
n
cies,
p
r
o
v
i
d
in
g
a
r
o
b
u
s
t
ap
p
r
o
ac
h
f
o
r
p
r
e
d
ictin
g
tax
r
ev
en
u
e
p
atter
n
s
with
en
h
an
ce
d
p
r
ec
is
i
o
n
.
R
F
R
ef
f
ec
tiv
ely
ad
d
r
ess
es
d
ata
g
ap
s
th
r
o
u
g
h
ac
c
u
r
ate
i
n
ter
p
o
latio
n
,
m
an
ag
i
n
g
n
o
n
-
l
in
ea
r
d
ata
p
atter
n
s
,
an
d
im
p
r
o
v
i
n
g
s
tab
i
lity
b
y
r
ed
u
cin
g
o
v
er
f
itti
n
g
th
r
o
u
g
h
en
s
em
b
le
lear
n
in
g
[
1
9
]
–
[
2
1
]
.
T
h
is
m
o
d
el
co
m
b
in
es
th
e
p
r
ed
ictio
n
s
o
f
m
u
ltip
le
d
ec
is
io
n
tr
ee
s
,
ea
ch
tr
a
in
ed
o
n
a
r
an
d
o
m
s
u
b
s
et
o
f
th
e
d
ata
an
d
f
e
atu
r
es
[
2
9
]
.
I
n
th
e
p
r
o
p
o
s
ed
m
o
d
el,
t
h
e
an
n
u
al
tax
r
ev
en
u
e
d
ata
s
er
v
es
as
in
p
u
t
to
ea
ch
d
ec
is
io
n
tr
ee
,
as
ex
p
r
ess
ed
in
f
o
r
m
u
la
(
1
)
:
̂
=
(
;
θ
)
(
1
)
w
h
er
e
̂
is
th
e
p
r
ed
ictio
n
f
r
o
m
th
e
k
-
th
tr
e
e,
a
n
d
r
e
p
r
esen
ts
th
e
p
a
r
am
eter
s
o
f
th
at
t
r
ee
.
T
h
e
f
in
al
p
r
ed
ictio
n
f
r
o
m
t
h
e
R
FR
is
o
b
tain
ed
b
y
av
e
r
ag
in
g
th
e
p
r
ed
ictio
n
s
o
f
all
tr
ee
s
in
th
e
f
o
r
est,
as
s
h
o
wn
i
n
f
o
r
m
u
la
(
2
)
:
̂
=
1
tr
e
e
s
∑
̂
tr
e
e
s
=
1
(
2
)
w
h
er
e
̂
r
ep
r
esen
ts
th
e
p
r
ed
icti
o
n
f
r
o
m
ea
c
h
in
d
iv
id
u
al
tr
ee
,
t
re
e
s
r
ep
r
esen
ts
th
e
n
u
m
b
er
o
f
d
ec
i
s
io
n
tr
ee
s
in
th
e
en
s
em
b
le,
s
et
to
1
0
0
b
ased
o
n
i
n
itial
ex
p
er
im
e
n
ts
,
an
d
̂
r
ep
r
esen
ts
th
e
m
o
n
th
ly
i
n
ter
p
o
l
ated
v
alu
e.
T
h
ese
R
F
R
m
o
n
th
ly
in
ter
p
o
lated
v
al
u
es ser
v
e
as in
p
u
t
to
t
h
e
L
ST
M
m
o
d
el
.
L
STM
is
well
-
s
u
ited
f
o
r
tim
e
s
er
ies
f
o
r
ec
asti
n
g
d
u
e
to
its
ab
ilit
y
to
m
o
d
el
lo
n
g
-
ter
m
d
e
p
en
d
en
cies
an
d
c
o
m
p
lex
tem
p
o
r
al
p
atter
n
s
[
2
2
]
.
As
o
u
tlin
ed
b
y
Go
o
d
f
el
lo
w
et
a
l.
[
3
0
]
,
th
is
p
r
o
ce
s
s
in
v
o
lv
es
m
ain
tain
i
n
g
in
f
o
r
m
atio
n
f
r
o
m
p
r
ev
io
u
s
tim
e
s
tep
s
,
en
ab
lin
g
t
h
e
m
o
d
el
to
r
ec
o
g
n
ize
l
o
n
g
-
te
r
m
p
atter
n
s
in
th
e
d
ata
th
r
o
u
g
h
a
n
etwo
r
k
o
f
g
ates
th
at
r
eg
u
l
ate
th
e
f
lo
w
o
f
in
f
o
r
m
atio
n
.
T
h
e
f
o
llo
win
g
is
an
ex
p
la
n
atio
n
o
f
th
e
g
ates
in
L
STM
:
=
σ
(
⋅
+
⋅
ℎ
−
1
+
)
(
3
)
=
σ
(
⋅
+
⋅
ℎ
−
1
+
)
(
4
)
T
h
e
in
p
u
t
g
ate,
f
o
r
m
u
la
(
3
)
,
d
eter
m
in
es
h
o
w
m
u
c
h
n
ew
i
n
p
u
t
s
h
o
u
l
d
b
e
ad
d
ed
to
th
e
ce
ll
s
tate
.
W
h
ile,
th
e
f
o
r
g
et
g
ate,
f
o
r
m
u
l
a
(
4
)
,
is
r
esp
o
n
s
ib
le
f
o
r
d
ec
id
i
n
g
h
o
w
m
u
ch
o
f
t
h
e
p
r
ev
i
o
u
s
ce
ll
s
tate
s
h
o
u
ld
b
e
r
etain
ed
.
Her
e,
r
ep
r
esen
ts
th
e
in
p
u
t g
ate,
is
th
e
f
o
r
g
et
g
ate,
is
th
e
s
ig
m
o
id
ac
tiv
atio
n
f
u
n
ct
io
n
,
an
d
ar
e
th
e
weig
h
t
m
atr
ices
ass
o
c
iated
with
th
e
cu
r
r
en
t
in
p
u
t
an
d
th
e
p
r
e
v
io
u
s
h
id
d
e
n
s
tate
ℎ
−
1
,
an
d
is
th
e
b
ias
ter
m
.
Nex
t,
th
e
ce
ll
s
tate
is
u
p
d
ated
b
y
co
m
b
in
in
g
th
e
ca
n
d
id
ate
ce
ll
s
tate
̃
with
th
e
r
esu
lts
f
r
o
m
th
e
in
p
u
t a
n
d
f
o
r
g
et
g
ates,
as c
alc
u
lated
in
f
o
r
m
u
las (
5
)
an
d
(
6
)
:
̃
=
ta
n
h
(
⋅
+
⋅
ℎ
−
1
+
)
(
5
)
=
⋅
−
1
+
⋅
̃
(
6
)
Fo
r
m
u
la
(
5
)
ca
lcu
lates
th
e
ca
n
d
id
ate
ce
ll
s
tate
̃
,
wh
e
r
e
ta
n
h
is
th
e
h
y
p
er
b
o
lic
ta
n
g
en
t
ac
tiv
atio
n
f
u
n
ctio
n
.
T
h
is
ca
n
d
id
ate
ce
ll
s
tate
r
ep
r
esen
ts
th
e
n
ew
co
n
te
n
t
th
at
co
u
ld
b
e
a
d
d
ed
to
th
e
ce
ll
s
tate.
Fo
r
m
u
la
(
6
)
t
h
en
u
p
d
ates
t
h
e
ce
ll
s
tate
b
y
co
m
b
in
in
g
th
e
p
r
e
v
io
u
s
c
ell
s
tate
−
1
,
m
o
d
u
lated
b
y
th
e
f
o
r
g
et
g
ate
,
with
th
e
ca
n
d
id
ate
ce
ll st
ate
̃
,
m
o
d
u
lated
b
y
th
e
in
p
u
t
g
ate
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
A
h
yb
r
id
mo
d
el
t
o
mitig
a
te
d
a
ta
g
a
p
s
a
n
d
flu
ctu
a
tio
n
s
in
ta
x
r
ev
en
u
e
fo
r
ec
a
s
tin
g
(
R
a
h
ma
n
Ta
u
fik
)
4103
Fin
ally
,
th
e
o
u
tp
u
t
g
ate
d
eter
m
in
es
th
e
o
u
tp
u
t
o
f
th
e
L
ST
M
ce
ll,
wh
ich
also
s
er
v
es
as
th
e
h
id
d
en
s
tate
f
o
r
t
h
e
n
ex
t tim
e
s
tep
.
T
h
is
is
d
escr
ib
ed
in
f
o
r
m
u
las (
7
)
an
d
(
8
)
:
=
σ
(
⋅
+
⋅
ℎ
−
1
+
)
(
7
)
ℎ
=
⋅
ta
n
h
(
)
(
8
)
I
n
f
o
r
m
u
la
(
7
)
,
is
th
e
o
u
tp
u
t
g
ate,
wh
ich
co
n
tr
o
ls
h
o
w
m
u
ch
o
f
th
e
ce
ll
s
tate
s
h
o
u
ld
b
e
ex
p
o
s
ed
to
th
e
o
u
tp
u
t.
Fo
r
m
u
la
(
8
)
ca
lcu
lates
th
e
h
id
d
en
s
tate
ℎ
−
1
,
a
f
u
n
ctio
n
o
f
th
e
cu
r
r
en
t
ce
ll
s
tate
an
d
th
e
o
u
tp
u
t
g
ate
.
T
h
is
p
r
o
ce
s
s
en
a
b
les
th
e
L
STM
m
o
d
el
to
p
r
o
ce
s
s
s
eq
u
e
n
tial
d
ata,
u
n
c
o
v
er
tem
p
o
r
al
r
elatio
n
s
h
ip
s
,
an
d
g
en
er
ate
f
o
r
ec
asts
f
o
r
s
u
b
s
eq
u
en
t m
o
n
th
l
y
tax
r
e
v
en
u
e
v
alu
e
s
as th
e
f
in
al
o
u
tp
u
t.
T
h
is
h
y
b
r
id
ap
p
r
o
ac
h
c
o
m
b
in
es
th
e
in
ter
p
o
lativ
e
ca
p
ab
ilit
ies
o
f
R
F
R
with
th
e
tem
p
o
r
al
m
o
d
ellin
g
s
tr
en
g
th
s
o
f
L
STM
t
o
ad
d
r
ess
d
ata
g
a
p
s
an
d
f
lu
ctu
atio
n
s
.
B
y
alig
n
in
g
f
o
r
ec
asts
with
k
ey
ec
o
n
o
m
ic
p
atter
n
s
,
th
e
m
eth
o
d
o
f
f
e
r
s
a
s
tr
u
ctu
r
ed
f
r
am
ewo
r
k
f
o
r
r
eliab
le
t
ax
r
ev
en
u
e
p
r
ed
ictio
n
.
T
h
ese
in
s
ig
h
ts
p
r
o
v
id
e
ac
tio
n
ab
le
g
u
i
d
an
ce
,
e
n
s
u
r
in
g
th
e
m
o
d
el
is
ac
ce
s
s
ib
le
an
d
p
r
ac
tical
f
o
r
f
is
ca
l p
o
licy
m
a
k
er
s
.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
is
s
ec
tio
n
p
r
esen
ts
th
e
r
esear
ch
r
esu
lts
alo
n
g
with
a
c
o
m
p
r
eh
en
s
iv
e
d
is
cu
s
s
io
n
,
o
r
g
a
n
ized
in
to
s
u
b
-
s
ec
tio
n
s
,
in
clu
d
in
g
th
e
p
r
o
p
o
s
ed
h
y
b
r
id
m
o
d
el
f
i
n
d
in
g
s
a
n
d
co
m
p
ar
is
o
n
s
to
o
t
h
er
m
o
d
e
ls
.
3
.
1
.
I
nte
rpre
t
a
t
io
n
o
f
m
o
del f
ind
ing
s
T
h
e
p
r
o
p
o
s
ed
h
y
b
r
id
m
o
d
el
i
n
teg
r
ates
R
F
R
f
o
r
in
ter
p
o
latin
g
an
n
u
al
tax
r
e
v
en
u
e
d
ata
in
to
m
o
n
th
ly
v
alu
es,
as
illu
s
tr
ated
i
n
Fig
u
r
e
2
.
T
h
e
m
o
d
el
was
tr
ain
ed
u
s
in
g
h
is
to
r
ical
a
n
n
u
al
tax
d
at
a
an
d
d
e
r
iv
ed
tim
e
-
b
ase
d
f
ea
tu
r
es
with
in
an
e
x
p
an
d
in
g
win
d
o
w
f
r
a
m
ewo
r
k
.
T
h
e
in
ter
p
o
latio
n
was
p
er
f
o
r
m
ed
u
s
in
g
s
p
ec
if
ic
p
ar
am
eter
s
,
n
am
ely
n
_
esti
m
ato
r
s
s
et
to
1
0
0
,
a
r
an
d
o
m
s
tate
o
f
2
4
,
a
n
o
is
e
f
ac
to
r
o
f
0
.
0
1
,
an
d
an
ex
p
a
n
d
in
g
win
d
o
w
s
ize
o
f
4
m
o
n
th
s
.
T
h
ese
p
ar
am
eter
s
wer
e
s
elec
t
ed
b
ased
o
n
iter
ativ
e
e
x
p
er
im
en
tatio
n
to
o
p
tim
ize
ac
cu
r
ac
y
a
n
d
e
f
f
ec
tiv
ely
h
an
d
le
v
ar
iatio
n
s
in
th
e
d
ata
wh
i
le
m
ain
tain
in
g
c
o
n
s
is
ten
cy
in
ca
p
tu
r
in
g
tem
p
o
r
al
d
y
n
am
ics.
T
o
en
s
u
r
e
ac
cu
r
ate
in
ter
p
o
latio
n
,
th
e
p
er
f
o
r
m
a
n
c
e
was
ev
alu
ated
t
h
r
o
u
g
h
k
ey
m
etr
ics,
in
cl
u
d
in
g
R
²,
MA
PE,
an
d
R
MSE
.
An
R
²
o
f
0
.
9
1
7
4
in
d
icate
s
th
at
th
e
m
o
d
el
s
u
cc
ess
f
u
lly
ca
p
tu
r
ed
9
1
.
7
4
%
o
f
t
h
e
v
ar
ian
ce
in
th
e
d
ata,
wh
ile
th
e
R
MSE
o
f
ap
p
r
o
x
im
ately
9
.
9
2
b
illi
o
n
r
e
f
lects
a
lo
w
a
v
er
ag
e
er
r
o
r
b
etwe
en
th
e
in
ter
p
o
lated
v
al
u
es
an
d
th
e
ac
tu
al
d
ata.
T
h
e
MA
PE
o
f
0
.
9
%
h
ig
h
lig
h
ts
th
e
p
r
ec
is
io
n
wi
th
wh
ich
th
e
m
o
d
el
p
r
o
d
u
ce
s
ac
cu
r
ate
in
ter
p
o
latio
n
v
alu
es.
Mo
r
eo
v
e
r
,
t
h
e
v
a
lid
ity
o
f
th
e
in
ter
p
o
latio
n
is
co
n
f
ir
m
ed
b
y
th
e
ag
g
r
eg
ated
m
o
n
t
h
ly
in
ter
p
o
lat
ed
d
ata,
wh
ich
alig
n
s
clo
s
ely
with
th
e
o
r
ig
in
al
a
n
n
u
al
d
ataset,
s
u
p
p
o
r
tin
g
its
u
s
e
f
o
r
r
eliab
le
tax
r
ev
e
n
u
e
f
o
r
ec
a
s
tin
g
.
Fig
u
r
e
2
.
T
h
e
in
ter
p
o
latio
n
d
at
a
p
r
esen
ted
in
a
tr
an
s
f
o
r
m
atio
n
f
r
o
m
an
n
u
al
to
m
o
n
th
ly
d
ata
Su
b
s
eq
u
en
tly
,
th
e
m
o
n
th
ly
i
n
ter
p
o
lated
d
ata
was
m
o
d
ele
d
u
s
in
g
th
e
L
STM
m
o
d
el.
T
h
e
o
p
tim
al
co
n
f
ig
u
r
ati
o
n
co
m
p
r
is
es
2
8
8
u
n
its
,
a
d
r
o
p
o
u
t
r
ate
o
f
0
.
4
,
1
7
6
d
en
s
e
u
n
its
,
th
e
Ad
am
o
p
tim
izer
,
an
d
a
lear
n
in
g
r
ate
o
f
0
.
0
0
1
.
E
x
p
a
n
d
in
g
win
d
o
w
cr
o
s
s
-
v
alid
atio
n
was
ap
p
lied
d
u
r
in
g
th
e
tr
ain
in
g
p
r
o
ce
s
s
,
with
th
e
m
o
d
el
tr
ain
ed
f
o
r
1
0
0
ep
o
c
h
s
.
T
h
is
co
m
b
in
atio
n
o
f
h
y
p
er
p
ar
am
eter
s
an
d
cr
o
s
s
-
v
alid
atio
n
is
p
ar
tic
u
lar
ly
ef
f
ec
tiv
e
f
o
r
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
4
,
Au
g
u
s
t
20
25
:
4
0
9
9
-
4108
4104
tim
e
-
s
er
ies
an
aly
s
is
.
I
t
en
s
u
r
e
s
th
at
th
e
m
o
d
el
is
p
r
o
g
r
ess
iv
ely
tr
ain
ed
o
n
m
o
r
e
d
ata,
en
h
an
cin
g
its
a
b
ilit
y
to
ca
p
tu
r
e
lo
n
g
-
ter
m
t
r
en
d
s
an
d
p
atter
n
s
.
Fig
u
r
e
3
d
em
o
n
s
tr
ates
th
e
p
r
e
d
ictio
n
p
er
f
o
r
m
an
ce
o
f
th
e
co
m
b
in
ed
tr
ain
in
g
an
d
test
in
g
m
o
d
el.
T
h
e
p
er
f
o
r
m
an
ce
o
f
th
e
p
r
o
p
o
s
ed
h
y
b
r
id
m
o
d
el
d
u
r
in
g
t
r
ain
in
g
was
ev
alu
ated
u
s
in
g
s
ev
er
al
m
etr
ics.
T
h
e
R
²
o
f
0
.
8
9
7
in
d
icate
s
th
at
ap
p
r
o
x
im
ately
8
9
.
7
%
o
f
th
e
v
ar
ian
ce
in
th
e
d
ata
was
ca
p
tu
r
ed
,
r
ef
lectin
g
a
s
tr
o
n
g
m
o
d
e
l
f
it.
Ho
wev
er
,
th
e
r
elativ
ely
h
i
g
h
MA
PE
o
f
6
.
2
9
%
o
n
th
e
tr
a
in
in
g
d
ata
s
u
g
g
ests
th
at
wh
ile
th
e
m
o
d
el
f
its
well
o
v
er
all,
it m
ay
s
till
h
av
e
n
o
tic
ea
b
le
p
r
ed
ictio
n
e
r
r
o
r
s
in
s
p
ec
if
ic
ca
s
es.
T
h
is
i
s
f
u
r
th
er
co
n
f
ir
m
ed
b
y
t
h
e
R
MSE
o
f
ap
p
r
o
x
im
ately
3
.
5
2
b
ill
io
n
,
r
ep
r
esen
tin
g
th
e
av
e
r
ag
e
e
r
r
o
r
in
th
e
p
r
ed
ictio
n
s
.
No
tab
ly
,
th
e
R
MSE
o
n
th
e
test
s
et
in
cr
ea
s
ed
to
9
.
6
6
b
illi
o
n
,
in
d
icatin
g
th
at
th
e
m
o
d
el
f
ac
es
ch
allen
g
es
in
g
en
er
alizin
g
to
u
n
s
ee
n
d
ata.
T
h
e
R
²
f
o
r
th
e
u
n
s
ee
n
d
ata
d
r
o
p
p
ed
to
0
.
8
6
,
s
till
s
h
o
win
g
a
s
tr
o
n
g
f
it,
b
u
t
in
d
icatin
g
th
at
th
e
p
er
f
o
r
m
an
ce
o
n
n
ew
d
ata
is
s
l
ig
h
tly
less
r
o
b
u
s
t.
Desp
ite
th
is
,
th
e
MA
PE
o
n
th
e
test
d
ata
im
p
r
o
v
ed
to
3
.
4
9
%,
s
u
g
g
esti
n
g
th
at
th
e
m
o
d
el
m
ain
tain
s
r
ea
s
o
n
ab
le
p
r
ed
ictiv
e
a
cc
u
r
ac
y
.
Alth
o
u
g
h
th
e
p
r
o
p
o
s
ed
h
y
b
r
id
m
o
d
el
p
er
f
o
r
m
s
well
o
n
th
e
tr
ain
in
g
d
ata,
its
a
b
ilit
y
t
o
g
e
n
er
alize
to
u
n
s
ee
n
d
ata
r
em
ain
s
lim
ited
.
T
h
is
lim
itatio
n
is
lik
el
y
d
u
e
to
ex
ter
n
al
ec
o
n
o
m
ic
d
is
r
u
p
tio
n
s
f
r
o
m
2
0
1
8
to
2
0
1
9
th
at
wer
e
n
o
t
ca
p
tu
r
e
d
in
th
e
tr
ain
in
g
d
ata.
T
h
ese
d
is
r
u
p
tio
n
s
ca
u
s
ed
s
ig
n
if
ica
n
t
f
lu
ctu
atio
n
s
,
h
ig
h
lig
h
tin
g
a
p
o
ten
tial
lim
itatio
n
o
f
th
e
in
ter
p
o
latio
n
m
o
d
el,
as
it
s
tr
u
g
g
led
to
a
d
ap
t to
lar
g
e
-
s
ca
le
ch
an
g
es in
th
e
ec
o
n
o
m
ic
la
n
d
s
ca
p
e
an
d
g
en
e
r
ated
in
co
n
s
is
ten
t v
alu
es.
I
n
ad
d
itio
n
,
Fig
u
r
e
4
d
em
o
n
s
tr
ates
th
at
th
e
p
r
o
p
o
s
ed
h
y
b
r
i
d
m
o
d
el
is
p
r
o
m
is
in
g
in
f
o
r
e
ca
s
tin
g
tax
r
ev
en
u
e
f
o
r
L
am
p
u
n
g
Pro
v
i
n
ce
,
with
p
r
o
jectio
n
s
s
h
o
win
g
a
4
.
0
8
%
in
cr
ea
s
e
f
o
r
2
0
2
4
an
d
3
.
7
7
%
f
o
r
2
0
2
5
.
W
h
ile
th
is
s
tu
d
y
f
o
cu
s
es
o
n
d
ata
f
r
o
m
L
a
m
p
u
n
g
Pr
o
v
in
ce
,
th
e
p
r
o
p
o
s
ed
h
y
b
r
id
m
o
d
el
ca
n
b
e
ad
ap
te
d
to
r
eg
io
n
s
with
s
im
ilar
tax
r
ev
e
n
u
e
c
h
ar
a
cter
is
tics
,
r
eq
u
ir
i
n
g
m
o
d
i
f
icatio
n
s
o
n
ly
f
o
r
th
o
s
e
with
d
if
f
er
in
g
tax
s
tr
u
ctu
r
es.
Fo
r
in
s
tan
ce
,
th
e
R
F
R
in
ter
p
o
latio
n
m
eth
o
d
n
e
ed
s
to
b
e
ad
ap
ted
t
o
ac
co
u
n
t
f
o
r
v
ar
y
in
g
tax
d
ata
f
o
r
m
ats
an
d
r
eg
io
n
al
ec
o
n
o
m
ic
in
d
icato
r
s
,
wh
ile
th
e
L
STM
n
ee
d
s
to
b
e
r
ec
o
n
f
ig
u
r
ed
to
r
ef
lect
lo
ca
l
ec
o
n
o
m
ic
cy
cles
an
d
s
ea
s
o
n
al
tr
en
d
s
.
Dif
f
er
en
ce
s
in
tax
d
ata
q
u
ality
an
d
g
r
an
u
lar
ity
ac
r
o
s
s
r
eg
io
n
s
af
f
ec
t
m
o
d
el
p
er
f
o
r
m
a
n
ce
an
d
n
ec
es
s
itate
f
u
r
th
er
r
ef
in
e
m
en
t in
d
ata
p
r
ep
r
o
ce
s
s
in
g
an
d
f
ea
tu
r
e
s
e
lectio
n
.
Fig
u
r
e
3
.
Per
f
o
r
m
an
c
e
o
f
t
h
e
p
r
o
p
o
s
ed
m
o
d
el
o
n
b
o
th
th
e
tr
ai
n
in
g
an
d
test
in
g
d
ata
s
ets
Fig
u
r
e
4
.
Fo
r
ec
asted
ta
x
r
ev
e
n
u
e
d
ata
f
o
r
y
ea
r
s
2
0
2
4
an
d
2
0
2
5
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
A
h
yb
r
id
mo
d
el
t
o
mitig
a
te
d
a
ta
g
a
p
s
a
n
d
flu
ctu
a
tio
n
s
in
ta
x
r
ev
en
u
e
fo
r
ec
a
s
tin
g
(
R
a
h
ma
n
Ta
u
fik
)
4105
3
.
2
.
Co
m
pa
ra
t
iv
e
m
o
dels
dis
cus
s
io
n
T
h
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
p
r
o
p
o
s
ed
h
y
b
r
id
m
o
d
el
was
co
m
p
ar
ed
with
v
ar
i
o
u
s
b
e
n
ch
m
ar
k
m
o
d
els
u
s
in
g
in
s
ig
h
ts
f
r
o
m
ex
is
tin
g
r
e
s
ea
r
ch
an
d
wid
el
y
u
s
ed
f
o
r
ec
a
s
tin
g
m
eth
o
d
s
.
B
en
ch
m
ar
k
m
o
d
els
s
u
ch
as
ANN
an
d
ML
R
wer
e
s
elec
ted
b
ased
o
n
th
eir
p
r
io
r
s
tu
d
ies
in
f
o
r
ec
asti
n
g
L
am
p
u
n
g
tax
r
e
v
en
u
e
[
9
]
[
1
0
]
.
Ad
d
itio
n
a
l
m
o
d
els,
in
clu
d
in
g
L
ST
M
a
n
d
AR
I
MA
,
wer
e
ch
o
s
en
f
o
r
t
h
eir
ex
ten
s
iv
e
u
s
e
i
n
p
r
ac
tical
ti
m
e
-
s
er
ies
p
r
o
b
lem
s
.
Hy
b
r
id
ap
p
r
o
ac
h
es,
in
clu
d
in
g
R
F
R
-
AR
I
MA
an
d
R
F
R
-
T
E
S,
wer
e
test
ed
in
th
is
s
tu
d
y
to
ex
p
lo
r
e
th
e
p
o
ten
tial
o
f
co
m
b
i
n
in
g
r
e
g
r
ess
io
n
an
d
ti
m
e
-
s
er
ies m
eth
o
d
s
.
B
y
co
m
p
a
r
in
g
th
ese
m
o
d
els,
th
is
s
tu
d
y
a
im
s
to
ev
alu
ate
th
e
p
r
o
p
o
s
ed
h
y
b
r
i
d
m
o
d
els
ef
f
ec
tiv
en
ess
in
ad
d
r
ess
in
g
d
ata
g
ap
s
an
d
f
lu
ctu
atio
n
s
,
r
el
ativ
e
to
estab
lis
h
ed
ap
p
r
o
ac
h
es a
n
d
n
ewly
ex
p
l
o
r
e
d
co
m
b
i
n
atio
n
s
.
T
h
e
s
elec
ted
m
o
d
els
ea
ch
o
f
f
er
d
is
tin
ct
ad
v
a
n
tag
es
b
ased
o
n
th
eir
u
n
d
e
r
ly
in
g
m
eth
o
d
o
lo
g
ies.
ANN
is
wid
ely
r
ec
o
g
n
ize
d
f
o
r
its
ab
ilit
y
to
ca
p
tu
r
e
co
m
p
lex
n
o
n
lin
ea
r
p
atter
n
s
in
d
ata
[
9
]
.
ML
R
is
a
class
ica
l
s
tatis
t
ical
ap
p
r
o
ac
h
f
o
r
id
en
ti
f
y
in
g
li
n
ea
r
r
elatio
n
s
h
ip
s
b
et
wee
n
v
ar
iab
les,
m
ak
in
g
it
a
r
eliab
le
b
aselin
e
f
o
r
s
tr
u
ctu
r
ed
d
atasets
[
1
0
]
.
L
ST
M
is
d
esig
n
ed
to
an
aly
ze
s
eq
u
en
tial
d
ata
,
allo
win
g
it
to
ca
p
tu
r
e
l
o
n
g
-
te
r
m
tem
p
o
r
al
p
atter
n
s
an
d
d
e
p
en
d
en
cies
cr
itical
f
o
r
tim
e
-
s
er
ies
f
o
r
ec
asti
n
g
[
7
]
,
[
2
2
]
.
H
y
b
r
id
ap
p
r
o
ac
h
es,
s
u
ch
as
R
F
R
-
AR
I
MA
an
d
R
F
R
-
T
E
S,
co
m
b
in
e
R
FR
f
o
r
d
ata
in
ter
p
o
lat
io
n
[
1
9
]
-
[
2
1
]
with
AR
I
MA
f
o
r
m
o
d
elin
g
lin
ea
r
tem
p
o
r
al
s
tr
u
ctu
r
es
[
1
3
]
,
[
1
7
]
an
d
T
E
S
f
o
r
ad
d
r
ess
in
g
s
ea
s
o
n
al
v
ar
iatio
n
s
th
r
o
u
g
h
ex
p
o
n
e
n
tial
s
m
o
o
th
in
g
[
8
]
.
T
h
e
co
m
p
ar
ativ
e
m
eth
o
d
o
lo
g
y
en
s
u
r
es
th
at
all
m
o
d
els
ar
e
tr
ain
ed
an
d
test
ed
u
s
in
g
th
e
s
am
e
tax
r
ev
en
u
e
d
ataset
f
r
o
m
L
am
p
u
n
g
Pro
v
in
ce
.
T
h
e
d
ataset
was
p
r
ep
r
o
ce
s
s
ed
u
s
in
g
r
o
b
u
s
t
s
ca
lin
g
an
d
d
if
f
er
en
cin
g
d
ata
to
en
h
an
ce
d
ata
q
u
ality
a
n
d
s
tab
i
lity
.
T
o
av
o
i
d
d
ata
leak
a
g
e,
th
e
d
ataset
was
d
iv
id
ed
in
to
8
0
%
f
o
r
tr
ain
in
g
(
1
9
9
5
to
2
0
1
7
)
an
d
2
0
%
f
o
r
test
in
g
(
2
0
1
8
to
2
0
2
3
)
,
m
ain
tain
in
g
t
h
e
o
r
d
er
o
f
d
ata
o
v
er
tim
e.
T
h
e
tr
ain
in
g
s
et
was
f
u
r
th
er
ev
alu
ated
u
s
in
g
E
x
p
an
d
in
g
W
in
d
o
w
C
r
o
s
s
-
Valid
atio
n
,
p
r
o
g
r
ess
iv
ely
in
c
r
ea
s
in
g
th
e
s
ize
o
f
th
e
tr
ain
in
g
s
et
wh
ile
r
eser
v
in
g
a
p
o
r
tio
n
f
o
r
v
alid
atio
n
.
All
m
o
d
els
wer
e
ass
ess
ed
u
s
i
n
g
k
e
y
m
etr
ics,
in
clu
d
in
g
MA
PE,
R
MSE
,
an
d
R
².
T
h
is
co
n
s
is
ten
t
f
r
am
ewo
r
k
en
s
u
r
es
co
n
s
is
ten
cy
an
d
co
m
p
ar
ab
ilit
y
,
allo
win
g
r
eliab
le
co
n
clu
s
io
n
s
ab
o
u
t th
e
p
e
r
f
o
r
m
an
ce
o
f
ea
c
h
m
o
d
el.
T
h
e
r
esu
lts
,
s
u
m
m
ar
ized
in
T
ab
le
1
,
d
em
o
n
s
tr
ated
p
er
f
o
r
m
an
ce
v
a
r
iatio
n
s
ac
r
o
s
s
h
y
b
r
id
an
d
n
o
n
-
h
y
b
r
id
m
o
d
els.
Am
o
n
g
all
t
h
e
m
o
d
els
test
ed
,
th
e
p
r
o
p
o
s
ed
R
F
R
-
L
STM
h
y
b
r
id
m
o
d
el
d
e
m
o
n
s
tr
ates
th
e
b
est
p
er
f
o
r
m
an
ce
,
with
R
²
o
f
0
.
8
6
,
R
MSE
o
f
9
.
6
5
b
illi
o
n
,
an
d
MA
PE
o
f
3
.
4
9
%.
T
h
e
h
ig
h
R
²
in
d
icate
s
th
at
th
e
m
o
d
el
ca
n
ex
p
lai
n
m
o
s
t
o
f
t
h
e
v
ar
ia
b
i
lity
in
th
e
d
ata,
w
h
ile
th
e
lo
w
R
MSE
an
d
MA
PE
s
u
g
g
est
th
at
th
e
av
er
ag
e
p
r
e
d
ictio
n
er
r
o
r
is
r
elativ
ely
s
m
all.
T
h
is
in
d
icate
s
th
at
th
e
p
r
o
p
o
s
ed
R
FR
-
L
S
T
M
h
y
b
r
id
m
o
d
e
l
ef
f
ec
tiv
ely
ca
p
tu
r
es
lo
n
g
-
te
r
m
tem
p
o
r
al
tr
e
n
d
s
an
d
f
lu
ctu
atio
n
s
,
en
ab
lin
g
ac
c
u
r
ate
an
d
s
tab
l
e
p
r
ed
ictio
n
s
.
Mo
r
eo
v
er
,
co
m
p
a
r
is
o
n
s
with
o
th
er
h
y
b
r
id
m
o
d
els,
in
clu
d
in
g
R
FR
-
AR
I
MA
an
d
R
F
R
-
T
E
S,
v
alid
ate
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
p
r
o
p
o
s
ed
R
FR
-
L
STM
h
y
b
r
id
m
o
d
e
l
.
R
F
R
-
AR
I
MA
,
w
ith
R
²
o
f
0
.
6
1
,
R
MSE
o
f
2
8
.
7
7
b
illi
o
n
,
an
d
MA
PE
o
f
8
.
7
9
%,
s
h
o
ws
m
o
d
er
ate
p
er
f
o
r
m
an
c
e
d
u
e
to
its
in
ab
ilit
y
to
ca
p
tu
r
e
th
e
n
o
n
lin
ea
r
p
atter
n
s
in
th
e
d
ata.
T
h
e
R
FR
-
T
E
S
m
o
d
el,
with
R
²
o
f
0
.
1
8
,
R
MSE
o
f
1
0
7
.
0
2
b
illi
o
n
,
an
d
MA
PE
o
f
4
1
.
1
6
%,
ex
h
ib
its
th
e
p
o
o
r
est
p
er
f
o
r
m
a
n
ce
.
T
h
is
is
p
r
im
ar
ily
attr
i
b
u
te
d
to
its
in
ab
ilit
y
to
m
o
d
el
th
e
co
m
p
lex
,
n
o
n
l
in
ea
r
tr
en
d
s
an
d
f
lu
ctu
atio
n
s
in
th
e
d
ata.
T
h
ese
f
in
d
in
g
s
h
ig
h
lig
h
t
th
at
co
m
p
ar
ed
h
y
b
r
id
m
o
d
els
wer
e
less
ef
f
ec
tiv
e
in
ca
p
tu
r
in
g
lo
n
g
-
ter
m
tem
p
o
r
al
p
atter
n
s
an
d
h
an
d
lin
g
th
e
co
m
p
lex
ities
o
f
L
am
p
u
n
g
'
s
tax
r
ev
en
u
e
d
ata
,
u
n
d
er
s
co
r
i
n
g
th
e
a
d
v
an
ta
g
es o
f
th
e
p
r
o
p
o
s
ed
R
FR
-
L
STM
h
y
b
r
id
m
o
d
el.
T
ab
le
1
.
Per
f
o
r
m
an
ce
co
m
p
a
r
is
o
n
o
f
f
o
r
ec
asti
n
g
m
o
d
els
M
o
d
e
l
R²
R
M
S
E
M
A
P
E
R
F
R
-
LST
M
0
.
8
6
9
6
5
7
6
4
9
4
9
6
.
1
5
1
7
9
3
3
.
4
9
%
R
F
R
-
A
R
I
M
A
0
.
6
1
2
8
7
6
8
4
6
4
0
7
3
.
8
0
8
.
7
9
%
R
F
R
-
TES
0
.
1
8
1
0
7
0
1
9
3
3
6
2
6
8
.
7
5
1
9
4
1
.
1
6
%
LSTM
0
.
4
9
1
9
7
1
4
0
5
7
3
4
8
.
4
8
5
9
7
3
7
.
1
3
%
ANN
0
.
5
3
1
7
2
9
8
1
7
4
8
3
7
.
5
5
5
8
6
6
.
5
8
%
M
L
R
0
.
7
1
3
1
2
3
8
6
4
3
9
1
5
6
.
1
0
2
8
7
5
.
1
%
I
n
ad
d
itio
n
,
n
o
n
-
h
y
b
r
id
o
r
s
in
g
le
m
o
d
els,
in
clu
d
in
g
L
STM
,
ANN,
an
d
ML
R
,
wer
e
ev
alu
ated
.
T
h
e
L
STM
m
o
d
el
d
em
o
n
s
tr
ated
a
m
o
d
e
r
ate
lev
el
o
f
p
e
r
f
o
r
m
an
ce
,
with
R
²
o
f
0
.
4
9
,
R
MSE
o
f
1
9
.
7
1
b
illi
o
n
,
an
d
MA
PE
o
f
7
.
1
3
%.
T
h
e
ANN
m
o
d
el,
with
R
²
o
f
0
.
5
3
,
R
MSE
o
f
1
7
.
3
0
b
illi
o
n
,
an
d
MA
PE
o
f
6
.
5
8
%,
p
e
r
f
o
r
m
s
s
im
ilar
ly
to
L
STM
.
I
n
co
n
tr
ast,
ML
R
d
em
o
n
s
tr
ated
b
etter
p
er
f
o
r
m
a
n
ce
in
ter
m
s
o
f
R
²,
ac
h
iev
in
g
R
²
o
f
0
.
7
1
,
R
MSE
o
f
3
1
.
2
3
b
illi
o
n
,
an
d
MA
PE
o
f
5
.
1
%.
Ho
wev
er
,
th
e
r
elativ
ely
h
ig
h
R
MSE
an
d
MA
PE
s
u
g
g
est
th
at
wh
ile
ML
R
p
er
f
o
r
m
s
well
in
ex
p
lain
in
g
v
a
r
ian
ce
,
it
was
l
ess
ef
f
ec
tiv
e
in
ac
cu
r
ately
p
r
ed
ictin
g
th
e
v
alu
es.
T
h
ese
r
esu
lts
co
n
f
ir
m
th
at
w
h
ile
n
o
n
-
h
y
b
r
id
m
o
d
els
p
r
o
v
i
d
e
v
alu
ab
le
esti
m
ates,
th
ey
ar
e
lim
ited
in
th
eir
ab
ilit
y
to
ca
p
tu
r
e
th
e
f
lu
ct
u
a
tio
n
s
with
in
th
e
s
p
ec
if
ied
d
a
ta
co
n
s
tr
ain
ts
.
B
y
co
m
b
in
in
g
in
ter
p
o
latio
n
an
d
tem
p
o
r
al
p
atter
n
m
o
d
elin
g
,
th
e
p
r
o
p
o
s
ed
R
FR
-
L
STM
h
y
b
r
id
m
o
d
el
m
o
r
e
e
f
f
ec
tiv
el
y
ad
d
r
ess
es
th
e
s
e
co
m
p
lex
ities
an
d
p
r
o
v
i
d
es m
o
r
e
ac
cu
r
ate
f
o
r
ec
asts
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
4
,
Au
g
u
s
t
20
25
:
4
0
9
9
-
4108
4106
Ov
er
all,
th
e
co
m
p
a
r
is
o
n
s
r
ev
ea
l
th
at
wh
ile
s
in
g
le
an
d
h
y
b
r
id
m
o
d
els
h
av
e
s
p
ec
if
ic
s
tr
en
g
th
s
,
th
e
R
F
R
-
L
STM
h
y
b
r
id
m
o
d
el
p
r
o
v
id
es
a
m
o
r
e
co
m
p
r
e
h
en
s
iv
e
s
o
lu
tio
n
b
y
ad
d
r
ess
in
g
d
ata
g
a
p
s
an
d
f
lu
ctu
atio
n
s
s
im
u
ltan
eo
u
s
ly
.
T
h
is
h
ig
h
lig
h
t
s
its
p
o
ten
tial
to
u
n
if
y
d
if
f
er
en
t
m
o
d
els
f
o
r
d
e
p
en
d
a
b
le
an
d
p
r
ec
is
e
tax
r
ev
en
u
e
f
o
r
ec
asti
n
g
.
Desp
ite
th
e
p
r
o
m
is
in
g
r
esu
lts
,
f
u
r
th
er
im
p
r
o
v
em
en
ts
ar
e
n
ee
d
ed
to
r
e
f
in
e
r
eg
u
lar
izatio
n
tech
n
iq
u
es,
in
teg
r
ate
m
u
ltip
le
m
eth
o
d
o
lo
g
ies,
a
n
d
en
h
an
ce
m
o
d
el
g
e
n
er
aliza
tio
n
to
h
an
d
l
e
th
e
ch
allen
g
es
o
f
g
en
er
alizin
g
to
u
n
s
ee
n
d
ata.
Nev
er
th
eless
,
th
e
p
r
o
p
o
s
ed
h
y
b
r
id
m
o
d
el
h
as
s
tr
o
n
g
p
o
ten
tial
f
o
r
f
u
r
th
e
r
r
ef
in
em
en
t a
n
d
b
r
o
ad
e
r
ap
p
lic
atio
n
in
f
o
r
ec
asti
n
g
tax
r
e
v
en
u
e.
4.
CO
NCLU
SI
O
N
T
h
is
s
tu
d
y
d
e
v
elo
p
ed
an
R
FR
-
L
STM
h
y
b
r
id
m
o
d
el
to
im
p
r
o
v
e
tax
r
ev
en
u
e
f
o
r
ec
asti
n
g
in
L
am
p
u
n
g
Pro
v
in
ce
b
y
in
te
g
r
atin
g
th
e
in
ter
p
o
latio
n
ca
p
ab
ilit
ies
o
f
R
FR
with
th
e
tem
p
o
r
al
p
atter
n
-
c
ap
tu
r
in
g
f
u
n
ctio
n
o
f
L
STM
.
T
h
e
m
o
d
el
d
em
o
n
s
tr
a
ted
r
o
b
u
s
tn
ess
in
tax
r
ev
en
u
e
f
o
r
ec
asti
n
g
,
ac
h
i
ev
in
g
h
ig
h
p
r
ed
ictiv
e
ac
cu
r
ac
y
with
an
R
²
o
f
0
.
8
6
,
R
MSE
o
f
9
.
6
5
b
illi
o
n
,
an
d
MA
PE
o
f
3
.
4
9
%.
Ho
wev
er
,
th
e
p
r
o
p
o
s
ed
h
y
b
r
id
m
o
d
el’
s
ab
ilit
y
to
g
en
er
alize
to
u
n
s
ee
n
d
ata
r
em
ain
s
a
k
ey
lim
itatio
n
,
as
in
d
icate
d
b
y
th
e
in
cr
e
ase
in
R
MSE
an
d
d
ec
r
ea
s
e
in
R
²
wh
e
n
tes
ted
o
n
n
ew
d
ata.
T
h
ese
f
in
d
in
g
s
u
n
d
e
r
s
co
r
e
th
e
im
p
o
r
tan
ce
o
f
im
p
r
o
v
in
g
m
o
d
el
r
o
b
u
s
tn
ess
an
d
g
en
er
aliza
tio
n
.
Fu
tu
r
e
r
esear
ch
s
h
o
u
ld
ex
p
l
o
r
e
tech
n
iq
u
es
to
en
h
an
ce
g
en
e
r
aliza
tio
n
,
s
u
ch
as
in
co
r
p
o
r
atin
g
ad
d
itio
n
al
d
ata
s
o
u
r
ce
s
o
r
r
ef
i
n
in
g
in
te
r
p
o
latio
n
m
eth
o
d
s
.
Fu
r
t
h
er
m
o
r
e,
in
v
esti
g
atin
g
th
e
ap
p
licab
ilit
y
o
f
th
is
a
p
p
r
o
ac
h
to
o
th
e
r
r
e
g
io
n
s
o
r
co
u
n
tr
ies
with
d
if
f
er
e
n
t
tax
s
tr
u
ct
u
r
es
co
u
l
d
p
r
o
v
i
d
e
v
alu
ab
le
in
s
ig
h
ts
o
n
h
o
w
to
ad
ap
t
th
e
m
o
d
el
f
o
r
b
r
o
ad
er
u
s
e.
Ov
er
all,
th
is
s
tu
d
y
co
n
tr
ib
u
tes
to
ad
v
an
cin
g
f
o
r
ec
asti
n
g
m
et
h
o
d
s
f
o
r
tax
r
ev
en
u
e
p
r
ed
ictio
n
an
d
p
r
o
v
id
es
a
f
o
u
n
d
atio
n
f
o
r
f
u
t
u
r
e
im
p
r
o
v
em
en
ts
in
p
r
ed
ictiv
e
m
o
d
elin
g
.
ACK
NO
WL
E
DG
M
E
N
T
S
T
h
is
wo
r
k
was
s
u
p
p
o
r
ted
b
y
Un
iv
er
s
itas
L
am
p
u
n
g
an
d
R
eg
io
n
al
Dev
elo
p
m
en
t
Plan
n
in
g
Ag
en
cy
o
f
L
am
p
u
n
g
Pro
v
in
ce
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
Fin
an
cial
s
u
p
p
o
r
t
f
o
r
th
is
r
e
s
ea
r
ch
was
p
r
o
v
id
ed
b
y
Daf
tar
I
s
ian
Pelak
s
an
aa
n
An
g
g
a
r
an
B
ad
an
L
ay
an
an
Um
u
m
(
DI
PA BLU)
Un
iv
er
s
itas
L
am
p
u
n
g
.
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
T
h
is
jo
u
r
n
al
u
s
es
th
e
C
o
n
t
r
ib
u
to
r
R
o
les
T
a
x
o
n
o
m
y
(
C
R
ed
iT)
to
r
ec
o
g
n
ize
in
d
iv
i
d
u
al
au
th
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
th
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
llab
o
r
atio
n
.
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
R
ah
m
an
T
au
f
ik
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Ar
is
to
teles
✓
✓
✓
✓
✓
✓
✓
✓
I
g
it Sab
d
a
I
lm
a
n
✓
✓
✓
✓
✓
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
m
i
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
Au
th
o
r
s
s
tate
n
o
co
n
f
lict o
f
in
t
er
est.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
ata
th
at
s
u
p
p
o
r
t
th
e
f
in
d
in
g
s
o
f
th
is
s
tu
d
y
wer
e
ac
q
u
ir
ed
f
r
o
m
p
u
b
licly
ac
ce
s
s
ib
le
s
o
u
r
ce
s
,
s
p
ec
if
ically
th
e
R
eg
io
n
al
Dev
elo
p
m
en
t
Plan
n
in
g
Ag
en
c
y
o
f
L
am
p
u
n
g
Pro
v
in
ce
a
n
d
th
e
C
en
tr
al
B
u
r
ea
u
o
f
Statis
t
ics th
r
o
u
g
h
th
eir
web
s
ite
h
ttp
s
://l
am
p
u
n
g
.
b
p
s
.
g
o
.
i
d
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
A
h
yb
r
id
mo
d
el
t
o
mitig
a
te
d
a
ta
g
a
p
s
a
n
d
flu
ctu
a
tio
n
s
in
ta
x
r
ev
en
u
e
fo
r
ec
a
s
tin
g
(
R
a
h
ma
n
Ta
u
fik
)
4107
RE
F
E
R
E
NC
E
S
[
1
]
M
.
G
u
ma
n
t
i
,
F
.
F
a
u
z
i
,
a
n
d
C
.
Ja
t
i
n
i
n
g
r
u
m
,
“
T
h
e
a
n
a
l
y
si
s
o
f
r
e
g
i
o
n
a
l
i
n
c
o
me
o
n
e
c
o
n
o
m
i
c
g
r
o
w
t
h
L
a
m
p
u
n
g
P
r
o
v
i
n
c
e
,
”
I
J
EBD
(
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
En
t
re
p
re
n
e
u
rs
h
i
p
a
n
d
B
u
si
n
e
ss
D
e
v
e
l
o
p
m
e
n
t
)
,
v
o
l
.
5
,
n
o
.
6
,
p
p
.
1
0
3
6
–
1
0
4
6
,
N
o
v
.
2
0
2
2
,
d
o
i
:
1
0
.
2
9
1
3
8
/
i
j
e
b
d
.
v
5
i
6
.
2
0
1
0
.
[
2
]
A
.
F
i
t
r
i
a
a
n
d
A
.
A
mb
y
a
,
“
T
h
e
Ef
f
e
c
t
o
f
L
o
c
a
l
G
o
v
e
r
m
e
n
t
R
e
v
e
n
u
e
a
n
d
Tr
a
n
sf
e
r
F
u
n
d
s
o
n
F
i
sca
l
C
a
p
a
c
i
t
y
R
a
t
i
o
i
n
La
m
p
u
n
g
P
r
o
v
i
n
c
e
f
r
o
m
2
0
1
7
-
2
0
2
2
,
”
S
i
n
o
m
i
c
s
J
o
u
rn
a
l
,
v
o
l
.
2
,
n
o
.
6
,
p
p
.
1
5
2
5
–
1
5
3
2
,
2
0
2
4
,
d
o
i
:
0
.
5
4
4
4
3
/
s
j
.
v
2
i
6
.
2
4
6
.
[
3
]
D
.
S
t
r
e
i
m
i
k
i
e
n
e
,
R
.
R
a
h
e
e
m
A
h
me
d
,
J.
V
v
e
i
n
h
a
r
d
t
,
S
.
P
.
G
h
a
u
r
i
,
a
n
d
S
.
Za
h
i
d
,
“
F
o
r
e
c
a
s
t
i
n
g
t
a
x
r
e
v
e
n
u
e
s
u
si
n
g
t
i
me
s
e
r
i
e
s
t
e
c
h
n
i
q
u
e
s
–
a
c
a
s
e
o
f
P
a
k
i
st
a
n
,
”
Ec
o
n
o
m
i
c
Re
s
e
a
r
c
h
-
Ek
o
n
o
m
sk
a
I
st
r
a
zi
v
a
n
j
a
,
v
o
l
.
3
1
,
n
o
.
1
,
p
p
.
7
2
2
–
7
5
4
,
Ja
n
.
2
0
1
8
,
d
o
i
:
1
0
.
1
0
8
0
/
1
3
3
1
6
7
7
X
.
2
0
1
8
.
1
4
4
2
2
3
6
.
[
4
]
E.
B
u
x
t
o
n
,
K
.
K
r
i
z
,
M
.
C
r
e
m
e
e
n
s,
a
n
d
K
.
J
a
y
,
“
A
n
a
u
t
o
r
e
g
r
e
ss
i
v
e
d
e
e
p
l
e
a
r
n
i
n
g
m
o
d
e
l
f
o
r
sal
e
s
t
a
x
f
o
r
e
c
a
st
i
n
g
f
r
o
m
m
u
l
t
i
p
l
e
sh
o
r
t
t
i
m
e
seri
e
s,”
i
n
Pr
o
c
e
e
d
i
n
g
s
-
1
8
t
h
I
E
EE
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
M
a
c
h
i
n
e
L
e
a
rn
i
n
g
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s,
I
C
MLA
2
0
1
9
,
D
e
c
.
2
0
1
9
,
p
p
.
1
3
5
9
–
1
3
6
4
.
d
o
i
:
1
0
.
1
1
0
9
/
I
C
M
LA
.
2
0
1
9
.
0
0
2
2
1
.
[
5
]
K
.
La
h
i
r
i
a
n
d
C
.
Y
a
n
g
,
“
B
o
o
s
t
i
n
g
t
a
x
r
e
v
e
n
u
e
s
w
i
t
h
m
i
x
e
d
-
f
r
e
q
u
e
n
c
y
d
a
t
a
i
n
t
h
e
a
f
t
e
r
m
a
t
h
o
f
C
O
V
I
D
-
1
9
:
T
h
e
c
a
se
o
f
N
e
w
Y
o
r
k
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
F
o
re
c
a
st
i
n
g
,
v
o
l
.
3
8
,
n
o
.
2
,
p
p
.
5
4
5
–
5
6
6
,
A
p
r
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
j
f
o
r
e
c
a
s
t
.
2
0
2
1
.
1
0
.
0
0
5
.
[
6
]
H
.
X
i
e
,
“
R
e
s
e
a
r
c
h
o
n
t
h
e
M
o
d
e
l
s
f
o
r
F
o
r
e
c
a
s
t
o
f
T
a
x
R
e
v
e
n
u
e
o
f
W
e
n
z
h
o
u
C
i
t
y
,
”
H
i
g
h
l
i
g
h
t
s
i
n
S
c
i
e
n
c
e
,
En
g
i
n
e
e
ri
n
g
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
8
8
,
p
p
.
1
0
4
3
–
1
0
4
9
,
M
a
r
.
2
0
2
4
,
d
o
i
:
1
0
.
5
4
0
9
7
/
d
g
7
x
7
t
5
6
.
[
7
]
A
.
S
.
A
j
i
s
o
l
a
,
“
A
n
e
f
f
i
c
i
e
n
t
t
i
m
e
se
r
i
e
s
m
o
d
e
l
f
o
r
t
a
x
r
e
v
e
n
u
e
f
o
r
e
c
a
st
i
n
g
:
A
c
a
se
o
f
N
i
g
e
r
i
a
,
”
M
.
S
.
t
h
e
si
s
,
D
e
p
a
r
t
m
e
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
A
f
r
i
c
a
n
U
n
i
v
e
r
si
t
y
o
f
S
c
i
e
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
2
0
2
3
.
[
8
]
T.
M
u
sa
,
A
.
M
.
U
sma
n
,
a
n
d
H
.
D
.
G
a
r
b
a
,
“
M
o
d
e
l
l
i
n
g
a
n
d
f
o
r
e
c
a
st
i
n
g
N
i
g
e
r
i
a
’
s
t
a
x
r
e
v
e
n
u
e
:
A
c
o
m
p
a
r
a
t
i
v
e
a
n
a
l
y
si
s o
f
S
A
R
I
M
A
a
n
d
H
o
l
t
-
W
i
n
t
e
r
s
mo
d
e
l
s,
”
U
MYU
S
c
i
e
n
t
i
f
i
c
a
,
v
o
l
.
3
,
n
o
.
3
,
J
u
l
.
2
0
2
4
,
d
o
i
:
1
0
.
5
6
9
1
9
/
u
s
c
i
.
2
4
3
3
.
0
1
4
.
[
9
]
D
.
K
u
r
n
i
a
sari
,
P
.
S
.
R
a
m
a
d
h
a
n
i
,
W
.
W
a
m
i
l
i
a
n
a
,
a
n
d
W
.
W
a
r
s
o
n
o
,
“
A
p
p
l
i
c
a
t
i
o
n
o
f
t
h
e
a
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
a
l
g
o
r
i
t
h
m
t
o
p
r
e
d
i
c
t
t
h
e
r
e
a
l
i
z
a
t
i
o
n
o
f
t
h
e
d
u
t
y
t
a
x
o
n
t
h
e
n
a
me
o
f
mo
t
o
r
v
e
h
i
c
l
e
s
i
n
La
mp
u
n
g
P
r
o
v
i
n
c
e
,
”
I
n
d
o
n
e
si
a
n
J
o
u
rn
a
l
o
f
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
D
a
t
a
M
i
n
i
n
g
,
v
o
l
.
7
,
n
o
.
2
,
p
.
3
9
2
,
J
u
n
.
2
0
2
4
,
d
o
i
:
1
0
.
2
4
0
1
4
/
i
j
a
i
d
m.
v
7
i
2
.
2
9
4
5
6
.
[
1
0
]
M
.
Z.
I
n
f
u
si
,
G
.
P
.
K
u
su
ma,
a
n
d
D
.
A
.
A
r
h
a
m,
“
P
r
e
d
i
c
t
i
o
n
o
f
l
o
c
a
l
g
o
v
e
r
n
men
t
r
e
v
e
n
u
e
u
s
i
n
g
d
a
t
a
m
i
n
i
n
g
me
t
h
o
d
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
Em
e
r
g
i
n
g
T
e
c
h
n
o
l
o
g
y
a
n
d
Ad
v
a
n
c
e
d
En
g
i
n
e
e
r
i
n
g
,
v
o
l
.
1
2
,
n
o
.
1
,
p
p
.
6
3
–
7
4
,
J
a
n
.
2
0
2
2
,
d
o
i
:
1
0
.
4
6
3
3
8
/
i
j
e
t
a
e
0
1
2
2
_
0
7
.
[
1
1
]
I
.
I
l
i
c
,
B
.
G
ö
r
g
ü
l
ü
,
M
.
C
e
v
i
k
,
a
n
d
M
.
G
.
B
a
y
d
o
ğ
a
n
,
“
E
x
p
l
a
i
n
a
b
l
e
b
o
o
st
e
d
l
i
n
e
a
r
r
e
g
r
e
ssi
o
n
f
o
r
t
i
m
e
ser
i
e
s
f
o
r
e
c
a
st
i
n
g
,
”
P
a
t
t
e
r
n
Re
c
o
g
n
i
t
i
o
n
,
v
o
l
.
1
2
0
,
p
.
1
0
8
1
4
4
,
D
e
c
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
a
t
c
o
g
.
2
0
2
1
.
1
0
8
1
4
4
.
[
1
2
]
P
.
V
.
Th
a
y
y
i
b
,
M
.
N
.
Th
o
r
a
k
k
a
t
t
l
e
,
F
.
U
sma
n
i
,
A
.
T
.
Y
a
h
y
a
,
a
n
d
N
.
H
.
S
.
F
a
r
h
a
n
,
“
R
e
se
a
r
c
h
o
n
t
h
e
m
o
d
e
l
s
f
o
r
f
o
r
e
c
a
s
t
o
f
t
a
x
r
e
v
e
n
u
e
o
f
W
e
n
z
h
o
u
C
i
t
y
,
”
C
o
g
e
n
t
E
c
o
n
o
m
i
c
s
a
n
d
F
i
n
a
n
c
e
,
v
o
l
.
1
1
,
n
o
.
2
,
O
c
t
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
8
0
/
2
3
3
2
2
0
3
9
.
2
0
2
3
.
2
2
8
5
6
4
9
.
[
1
3
]
M
.
I
.
F
a
t
h
o
n
i
a
n
d
A
.
S
a
p
u
t
r
a
,
“
F
o
r
e
c
a
s
t
i
n
g
v
a
l
u
e
-
a
d
d
e
d
t
a
x
(
V
A
T)
r
e
v
e
n
u
e
u
si
n
g
a
u
t
o
r
e
g
r
e
ssi
v
e
i
n
t
e
g
r
a
t
e
d
mo
v
i
n
g
a
v
e
r
a
g
e
(
A
R
I
M
A
)
B
o
x
-
Jen
k
i
n
s
me
t
h
o
d
,
”
S
c
i
e
n
t
a
x
,
v
o
l
.
4
,
n
o
.
2
,
p
p
.
2
0
5
–
2
1
8
,
A
p
r
.
2
0
2
3
,
d
o
i
:
1
0
.
5
2
8
6
9
/
s
t
.
v
4
i
2
.
5
6
8
.
[
1
4
]
W
.
T
i
c
o
n
a
,
K
.
F
i
g
u
e
i
r
e
d
o
,
a
n
d
M
.
V
e
l
l
a
sc
o
,
“
H
y
b
r
i
d
mo
d
e
l
b
a
s
e
d
o
n
g
e
n
e
t
i
c
a
l
g
o
r
i
t
h
ms
a
n
d
n
e
u
r
a
l
n
e
t
w
o
r
k
s
t
o
f
o
r
e
c
a
s
t
t
a
x
c
o
l
l
e
c
t
i
o
n
:
A
p
p
l
i
c
a
t
i
o
n
u
s
i
n
g
e
n
d
o
g
e
n
o
u
s
a
n
d
e
x
o
g
e
n
o
u
s
v
a
r
i
a
b
l
e
s
,
”
i
n
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
2
0
1
7
I
EE
E
2
4
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
g
ress
o
n
E
l
e
c
t
r
o
n
i
c
s
,
El
e
c
t
ri
c
a
l
En
g
i
n
e
e
ri
n
g
a
n
d
C
o
m
p
u
t
i
n
g
,
I
N
T
E
RC
O
N
2
0
1
7
,
A
u
g
.
2
0
1
7
,
p
p
.
1
–
4
.
d
o
i
:
1
0
.
1
1
0
9
/
I
N
TER
C
O
N
.
2
0
1
7
.
8
0
7
9
6
6
0
.
[
1
5
]
S
.
S
my
l
,
“
A
h
y
b
r
i
d
m
e
t
h
o
d
o
f
e
x
p
o
n
e
n
t
i
a
l
smo
o
t
h
i
n
g
a
n
d
r
e
c
u
r
r
e
n
t
n
e
u
r
a
l
n
e
t
w
o
r
k
s
f
o
r
t
i
me
s
e
r
i
e
s
f
o
r
e
c
a
s
t
i
n
g
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
Fo
r
e
c
a
st
i
n
g
,
v
o
l
.
3
6
,
n
o
.
1
,
p
p
.
7
5
–
8
5
,
J
a
n
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
j
f
o
r
e
c
a
st
.
2
0
1
9
.
0
3
.
0
1
7
.
[
1
6
]
Z.
F
e
r
d
o
u
sh
,
B
.
N
.
M
a
h
mu
d
,
A
.
C
h
a
k
r
a
b
a
r
t
y
,
a
n
d
J
.
U
d
d
i
n
,
“
A
sh
o
r
t
-
t
e
r
m h
y
b
r
i
d
f
o
r
e
c
a
s
t
i
n
g
m
o
d
e
l
f
o
r
t
i
m
e
ser
i
e
s
e
l
e
c
t
r
i
c
a
l
-
l
o
a
d
d
a
t
a
u
s
i
n
g
r
a
n
d
o
m
f
o
r
e
st
a
n
d
b
i
d
i
r
e
c
t
i
o
n
a
l
l
o
n
g
s
h
o
r
t
-
t
e
r
m
me
mo
r
y
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
E
l
e
c
t
r
i
c
a
l
a
n
d
C
o
m
p
u
t
e
r
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
1
1
,
n
o
.
1
,
p
p
.
7
6
3
–
7
7
1
,
F
e
b
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
c
e
.
v
1
1
i
1
.
p
p
7
6
3
-
7
7
1
.
[
1
7
]
J.
H
o
ss
a
i
n
a
n
d
M
.
T.
I
smai
l
,
“
P
e
r
f
o
r
man
c
e
o
f
a
n
o
v
e
l
h
y
b
r
i
d
m
o
d
e
l
t
h
r
o
u
g
h
s
i
m
u
l
a
t
i
o
n
a
n
d
h
i
s
t
o
r
i
c
a
l
f
i
n
a
n
c
i
a
l
d
a
t
a
,
”
S
a
i
n
s
Ma
l
a
y
si
a
n
a
,
v
o
l
.
5
1
,
n
o
.
7
,
p
p
.
2
2
4
9
–
2
2
6
4
,
J
u
l
.
2
0
2
2
,
d
o
i
:
1
0
.
1
7
5
7
6
/
j
sm
-
2
0
2
2
-
5
1
0
7
-
2
5
.
[
1
8
]
H
.
La
a
r
o
u
ss
i
,
F
.
G
u
e
r
o
u
a
t
e
,
a
n
d
M
.
S
b
i
h
i
,
“
A
n
o
v
e
l
h
y
b
r
i
d
d
e
e
p
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
f
o
r
t
o
u
r
i
s
m d
e
ma
n
d
f
o
r
e
c
a
st
i
n
g
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
t
ri
c
a
l
a
n
d
C
o
m
p
u
t
e
r
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
1
3
,
n
o
.
2
,
p
p
.
1
9
8
9
–
1
9
9
6
,
A
p
r
.
2
0
2
3
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
c
e
.
v
1
3
i
2
.
p
p
1
9
8
9
-
1
9
9
6
.
[
1
9
]
M
.
A
c
h
i
t
e
,
P
.
Tsa
n
g
a
r
a
t
o
s
,
G
.
P
e
l
l
i
c
o
n
e
,
B
.
M
o
h
a
mm
a
d
i
,
a
n
d
T
.
C
a
l
o
i
e
r
o
,
“
A
p
p
l
i
c
a
t
i
o
n
o
f
m
u
l
t
i
p
l
e
s
p
a
t
i
a
l
i
n
t
e
r
p
o
l
a
t
i
o
n
a
p
p
r
o
a
c
h
e
s
t
o
a
n
n
u
a
l
r
a
i
n
f
a
l
l
d
a
t
a
i
n
t
h
e
W
a
d
i
C
h
e
l
i
f
f
b
a
si
n
(
n
o
r
t
h
A
l
g
e
r
i
a
)
,
”
Ai
n
S
h
a
m
s
E
n
g
i
n
e
e
r
i
n
g
J
o
u
rn
a
l
,
v
o
l
.
1
5
,
n
o
.
3
,
p
.
10
2
5
7
8
,
M
a
r
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
s
e
j
.
2
0
2
3
.
1
0
2
5
7
8
.
[
2
0
]
N
.
K
.
G
.
P
,
P
.
M
.
S
a
h
o
o
,
P
.
D
a
s,
T
.
A
h
ma
d
,
a
n
d
A
.
B
i
sw
a
s,
“
R
a
n
d
o
m
f
o
r
e
st
s
p
a
t
i
a
l
i
n
t
e
r
p
o
l
a
t
i
o
n
t
e
c
h
n
i
q
u
e
s
f
o
r
c
r
o
p
y
i
e
l
d
e
st
i
mat
i
o
n
a
t
d
i
st
r
i
c
t
l
e
v
e
l
,
”
J
o
u
r
n
a
l
o
f
t
h
e
I
n
d
i
a
n
S
o
c
i
e
t
y
o
f
A
g
r
i
c
u
l
t
u
r
a
l
S
t
a
t
i
s
t
i
c
s
,
v
o
l
.
7
8
,
n
o
.
1
,
p
p
.
9
–
1
9
,
M
a
y
2
0
2
4
,
d
o
i
:
1
0
.
5
6
0
9
3
/
j
i
s
a
s.
v
7
8
i
1
.
2
.
[
2
1
]
S
.
S
o
n
g
e
t
a
l
.
,
“
R
a
n
d
o
m
f
o
r
e
st
r
e
g
r
e
ssi
o
n
o
n
m
u
l
t
i
-
p
l
a
t
f
o
r
m
i
n
-
si
t
u
o
c
e
a
n
o
b
serv
a
t
i
o
n
s
:
I
n
v
e
s
t
i
g
a
t
i
n
g
h
i
g
h
-
f
r
e
q
u
e
n
c
y
n
u
t
r
i
e
n
t
d
y
n
a
mi
c
s
i
n
t
h
e
S
o
u
t
h
e
r
n
O
c
e
a
n
,
”
M
a
y
2
0
2
4
,
d
o
i
:
1
0
.
2
2
5
4
1
/
e
ss
o
a
r
.
1
7
1
7
0
7
8
4
9
.
9
1
8
6
7
5
6
5
/
v
1
.
[
2
2
]
D
.
D
.
W
.
P
r
a
v
e
e
n
r
a
j
,
M
.
P
a
n
d
e
y
,
a
n
d
M
.
V
i
c
t
o
r
,
“
T
i
me
ser
i
e
s
f
o
r
e
c
a
st
i
n
g
o
f
st
o
c
k
m
a
r
k
e
t
v
o
l
a
t
i
l
i
t
y
u
si
n
g
LS
TM
n
e
t
w
o
r
k
s
,
”
i
n
2
0
2
3
4
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
C
o
m
p
u
t
a
t
i
o
n
,
A
u
t
o
m
a
t
i
o
n
a
n
d
K
n
o
w
l
e
d
g
e
M
a
n
a
g
e
m
e
n
t
,
I
C
C
A
K
M
2
0
2
3
,
D
e
c
.
2
0
2
3
,
p
p
.
1
–
8
.
d
o
i
:
1
0
.
1
1
0
9
/
I
C
C
A
K
M
5
8
6
5
9
.
2
0
2
3
.
1
0
4
4
9
5
9
6
.
[
2
3
]
“
I
n
d
o
n
e
s
i
a
n
C
e
n
t
r
a
l
B
u
r
e
a
u
o
f
S
t
a
t
i
st
i
c
s
(
B
P
S
)
,
‘
Ta
x
R
e
v
e
n
u
e
i
n
L
a
mp
u
n
g
P
r
o
v
i
n
c
e
.
’
2
0
2
3
.
A
c
c
e
ss
e
d
:
J
u
n
.
1
2
,
2
0
2
4
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s:
/
/
l
a
m
p
u
n
g
.
b
p
s.
g
o
.
i
d
/
i
d
/
p
u
b
l
i
c
a
t
i
o
n
/
2
0
2
4
/
1
1
/
2
2
/
7
9
5
b
2
3
b
0
4
b
6
3
5
b
0
0
3
c
9
f
9
f
a
b
/
f
i
n
a
n
c
i
a
l
-
s
t
a
t
i
st
i
c
s
-
in
-
l
a
m
p
u
n
g
-
p
r
o
v
i
n
c
e
-
2
0
2
3
.
h
t
ml
”.
[
2
4
]
K
.
K
i
n
g
p
h
a
i
a
n
d
Y
.
M
o
sh
f
e
g
h
i
,
“
O
n
t
i
me
seri
e
s
c
r
o
ss
-
v
a
l
i
d
a
t
i
o
n
f
o
r
d
e
e
p
l
e
a
r
n
i
n
g
c
l
a
ssi
f
i
c
a
t
i
o
n
m
o
d
e
l
o
f
m
e
n
t
a
l
w
o
r
k
l
o
a
d
l
e
v
e
l
s
b
a
s
e
d
o
n
EEG
s
i
g
n
a
l
s,
”
i
n
L
e
c
t
u
re
N
o
t
e
s
i
n
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
(
i
n
c
l
u
d
i
n
g
su
b
s
e
ri
e
s
L
e
c
t
u
re
N
o
t
e
s
i
n
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
L
e
c
t
u
re
N
o
t
e
s
i
n
Bi
o
i
n
f
o
rm
a
t
i
c
s)
,
v
o
l
.
1
3
8
1
1
LN
C
S
,
S
p
r
i
n
g
e
r
N
a
t
u
r
e
S
w
i
t
z
e
r
l
a
n
d
,
2
0
2
3
,
p
p
.
4
0
2
–
4
1
6
.
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
0
3
1
-
2
5
8
9
1
-
6
_
3
0
.
[
2
5
]
K
.
H
i
r
a
n
o
a
n
d
J
.
H
.
W
r
i
g
h
t
,
“
A
n
a
l
y
z
i
n
g
c
r
o
ss
-
v
a
l
i
d
a
t
i
o
n
f
o
r
f
o
r
e
c
a
st
i
n
g
w
i
t
h
s
t
r
u
c
t
u
r
a
l
i
n
s
t
a
b
i
l
i
t
y
,
”
J
o
u
rn
a
l
o
f
E
c
o
n
o
m
e
t
r
i
c
s
,
v
o
l
.
2
2
6
,
n
o
.
1
,
p
p
.
1
3
9
–
1
5
4
,
J
a
n
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
e
c
o
n
o
m
.
2
0
2
0
.
1
0
.
0
0
9
.
[
2
6
]
“
I
n
t
r
o
d
u
c
t
i
o
n
t
o
t
h
e
K
e
r
a
s
T
u
n
e
r
,
”
K
e
ra
s
T
u
n
e
r
L
i
b
r
a
ry
.
h
t
t
p
s:
/
/
w
w
w
.
t
e
n
s
o
r
f
l
o
w
.
o
r
g
/
t
u
t
o
r
i
a
l
s/
k
e
r
a
s/
k
e
r
a
s_
t
u
n
e
r
(
a
c
c
e
sse
d
J
u
l
.
0
1
,
2
0
2
4
)
.
[
2
7
]
M
.
S
h
a
n
m
u
g
a
v
a
l
l
i
a
n
d
K
.
M
.
J.
I
g
n
a
t
i
a
,
“
C
o
m
p
a
r
a
t
i
v
e
st
u
d
y
a
m
o
n
g
M
A
P
E,
R
M
S
E
a
n
d
R
s
q
u
a
r
e
o
v
e
r
t
h
e
t
r
e
a
t
me
n
t
t
e
c
h
n
i
q
u
e
s
u
n
d
e
r
g
o
n
e
f
o
r
P
C
O
S
i
n
f
l
u
e
n
c
e
d
w
o
m
e
n
,
”
R
e
c
e
n
t
P
a
t
e
n
t
s
o
n
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
1
8
,
n
o
.
1
,
Jan
.
2
0
2
3
,
d
o
i
:
1
0
.
2
1
7
4
/
0
1
1
8
7
2
2
1
2
1
2
6
9
7
8
6
2
3
1
1
2
0
1
2
2
4
3
5
.
[
2
8
]
N
.
K
.
R
a
i
,
D
.
S
a
r
a
v
a
n
a
n
,
L.
K
u
mar,
P
.
S
h
u
k
l
a
,
a
n
d
R
.
N
.
S
h
a
w
,
“
R
M
S
E
a
n
d
M
A
P
E
a
n
a
l
y
si
s
f
o
r
sh
o
r
t
-
t
e
r
m
s
o
l
a
r
i
r
r
a
d
i
a
n
c
e
,
so
l
a
r
e
n
e
r
g
y
,
a
n
d
l
o
a
d
f
o
r
e
c
a
s
t
i
n
g
u
si
n
g
a
R
e
c
u
r
r
e
n
t
A
r
t
i
f
i
c
i
a
l
N
e
u
r
a
l
N
e
t
w
o
r
k
,
”
i
n
A
p
p
l
i
c
a
t
i
o
n
s
o
f
AI
a
n
d
I
O
T
i
n
R
e
n
e
w
a
b
l
e
En
e
r
g
y
,
El
se
v
i
e
r
,
2
0
2
2
,
p
p
.
1
8
1
–
1
9
2
.
d
o
i
:
1
0
.
1
0
1
6
/
B
9
7
8
-
0
-
3
2
3
-
9
1
6
9
9
-
8
.
0
0
0
1
0
-
3.
[
2
9
]
L.
B
r
e
i
m
a
n
,
“
R
a
n
d
o
m fo
r
e
st
s,
”
Ma
c
h
i
n
e
L
e
a
r
n
i
n
g
,
v
o
l
.
4
5
,
n
o
.
1
,
p
p
.
5
–
3
2
,
2
0
0
1
,
d
o
i
:
1
0
.
1
0
2
3
/
A
:
1
0
1
0
9
3
3
4
0
4
3
2
4
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
4
,
Au
g
u
s
t
20
25
:
4
0
9
9
-
4108
4108
[
3
0
]
I
.
G
o
o
d
f
e
l
l
o
w
,
Y
.
B
e
n
g
i
o
,
a
n
d
A
.
C
o
u
r
v
i
l
l
e
,
D
e
e
p
L
e
a
rn
i
n
g
.
M
I
T
P
r
e
ss,
2
0
1
6
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Ra
h
m
a
n
Ta
u
f
ik
re
c
e
iv
e
d
h
is
b
a
c
h
e
lo
r’s
d
e
g
re
e
i
n
c
o
m
p
u
ter
sc
ien
c
e
e
d
u
c
a
ti
o
n
fro
m
th
e
Un
i
v
e
rsity
o
f
E
d
u
c
a
ti
o
n
,
in
2
0
1
5
,
a
n
d
a
m
a
ste
r’s
d
e
g
re
e
in
c
o
m
p
u
ter
sc
ien
c
e
fro
m
Telk
o
m
Un
i
v
e
rsity
i
n
2
0
1
9
in
Ba
n
d
u
n
g
,
In
d
o
n
e
sia
.
He
is
c
u
rre
n
tl
y
a
lec
tu
re
r
a
t
th
e
De
p
a
rtme
n
t
o
f
C
o
m
p
u
ter
S
c
ien
c
e
s,
Un
iv
e
rsit
y
o
f
Lam
p
u
n
g
,
In
d
o
n
e
sia
.
His
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
d
a
ta an
a
ly
t
ics
,
a
rti
ficia
l
in
telli
g
e
n
c
e
,
a
n
d
in
telli
g
e
n
t
t
u
to
ri
n
g
sy
ste
m
.
In
a
d
d
it
i
o
n
,
h
e
i
s
a
n
a
ss
o
c
iate
e
d
it
o
r
o
f
th
e
jo
u
rn
a
l
In
fo
rm
a
ti
k
:
Ju
r
n
a
l
I
lmu
K
o
m
p
u
te
r
a
t
UPN
Ve
tera
n
Ja
k
a
rta,
In
d
o
n
e
sia
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
ra
h
m
a
n
.
tau
fik
@fm
i
p
a
.
u
n
il
a
.
a
c
.
id
.
Ar
isto
te
les
re
c
e
iv
e
d
h
is b
a
c
h
e
lo
r’s
d
e
g
re
e
i
n
c
o
m
p
u
ter
sc
ien
c
e
fro
m
Un
iv
e
rsitas
P
a
d
jad
jara
n
,
In
d
o
n
e
sia
,
in
2
0
0
4
.
He
th
e
n
p
u
rsu
e
d
h
is
m
a
ste
r’s
d
e
g
re
e
in
c
o
m
p
u
ter
sc
ien
c
e
a
t
In
stit
u
t
P
e
rtan
ian
Bo
g
o
r,
I
n
d
o
n
e
sia
,
a
n
d
g
ra
d
u
a
ted
i
n
2
0
1
1
.
In
2
0
2
4
,
h
e
c
o
m
p
lete
d
h
is
d
o
c
to
ra
te
a
t
t
h
e
F
a
c
u
lt
y
o
f
M
a
th
e
m
a
ti
c
s
a
n
d
Na
t
u
ra
l
S
c
ien
c
e
s
(F
M
IP
A)
a
t
U
n
iv
e
rsitas
Lam
p
u
n
g
,
In
d
o
n
e
sia
.
He
is
c
u
r
re
n
tl
y
th
e
v
ice
d
e
a
n
o
f
th
e
F
a
c
u
lt
y
o
f
M
a
th
e
m
a
ti
c
s
a
n
d
Na
tu
ra
l
S
c
ien
c
e
s,
Un
i
v
e
rsitas
L
a
m
p
u
n
g
,
I
n
d
o
n
e
sia
.
His
re
se
a
rc
h
h
a
s
b
e
e
n
f
u
n
d
e
d
b
y
th
e
Un
iv
e
rsitas
Lam
p
u
n
g
a
n
d
t
h
e
M
in
istr
y
o
f
E
d
u
c
a
ti
o
n
a
n
d
C
u
l
tu
re
o
f
th
e
Re
p
u
b
li
c
o
f
In
d
o
n
e
sia
.
He
h
a
s
a
u
t
h
o
re
d
o
r
c
o
-
a
u
th
o
re
d
m
o
re
th
a
n
2
0
0
re
fe
re
e
d
jo
u
rn
a
l
a
n
d
c
o
n
fe
re
n
c
e
p
a
p
e
rs,
a
n
d
4
b
o
o
k
c
h
a
p
ters
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
a
r
i
s
t
o
t
e
l
e
s
.
1
9
8
1
@
f
m
i
p
a
.
u
n
i
l
a
.
a
c
.
i
d
.
Ig
it
S
a
b
d
a
Ilm
a
n
re
c
e
iv
e
d
h
i
s
b
a
c
h
e
lo
r’s
d
e
g
re
e
i
n
in
f
o
rm
a
ti
o
n
sy
ste
m
s
fro
m
Am
ik
o
m
,
I
n
d
o
n
e
sia
,
i
n
2
0
1
6
,
a
n
d
h
is
m
a
ste
r’s
d
e
g
re
e
i
n
c
o
m
p
u
te
r
sc
ien
c
e
fro
m
Un
iv
e
rsitas
G
a
d
jah
M
a
d
a
,
I
n
d
o
n
e
sia
,
in
2
0
1
9
.
His
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
in
fo
rm
a
ti
o
n
sy
ste
m
s,
d
a
t
a
m
in
in
g
,
a
n
d
d
a
tab
a
se
s.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
ig
it
.
sa
b
d
a
@fm
ip
a
.
u
n
i
la.ac
.
id
.
Evaluation Warning : The document was created with Spire.PDF for Python.