I
AE
S In
t
er
na
t
io
na
l J
o
urna
l o
f
Art
if
icia
l In
t
ellig
ence
(
I
J
-
AI
)
Vo
l.
14
,
No
.
4
,
A
u
g
u
s
t 2
0
2
5
,
p
p
.
2
6
0
1
~
2
6
1
2
I
SS
N:
2
2
5
2
-
8
9
3
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijai.v
14
.i
4
.
p
p
2
6
0
1
-
2
6
1
2
2601
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
i
.
ia
esco
r
e.
co
m
H
y
brid
foreca
stin
g
methods
acro
ss
v
a
ried dom
a
ins
-
a
sy
stema
tic
revi
ew
M
a
lv
ina
Xha
ba
f
t
i,
Va
lent
ina
Sin
a
j
D
e
p
a
r
t
me
n
t
o
f
S
t
a
t
i
s
t
i
c
s a
n
d
A
p
p
l
i
e
d
I
n
f
o
r
mat
i
c
s,
F
a
c
u
l
t
y
o
f
Ec
o
n
o
m
y
,
U
n
i
v
e
r
si
t
y
o
f
Ti
r
a
n
a
,
Ti
r
a
n
a
,
A
l
b
a
n
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Sep
1
3
,
2
0
2
4
R
ev
is
ed
Feb
1
8
,
2
0
2
5
Acc
ep
ted
Ma
r
1
5
,
2
0
2
5
Ti
m
e
se
ries
fo
re
c
a
stin
g
is
o
n
e
o
f
th
e
li
n
k
s
th
a
t
h
a
s
d
e
v
e
lo
p
e
d
si
n
c
e
e
a
rly
ti
m
e
s
d
u
e
t
o
r
isk
m
a
n
a
g
e
m
e
n
t,
e
f
ficie
n
t
a
ll
o
c
a
ti
o
n
o
f
re
so
u
rc
e
s,
p
e
rfo
rm
a
n
c
e
e
v
a
lu
a
ti
o
n
,
stra
teg
ic
p
lan
n
in
g
,
a
n
d
th
e
f
o
rm
u
lati
o
n
o
f
e
ffe
c
ti
v
e
p
o
li
c
ies
fo
r
in
d
i
v
id
u
a
ls,
o
r
g
a
n
iza
ti
o
n
s
,
a
n
d
s
o
c
ieties
.
F
o
re
c
a
stin
g
m
o
d
e
l
s
h
a
v
e
e
v
o
lv
e
d
ste
a
d
il
y
b
y
h
y
b
r
id
izi
n
g
sta
ti
stica
l
a
n
d
n
e
u
ra
l
n
e
two
r
k
tec
h
n
iq
u
e
s
e
n
su
ri
n
g
e
fficie
n
c
y
a
n
d
a
c
c
u
ra
te
p
re
d
ictio
n
s.
In
t
h
is
p
a
p
e
r,
a
sy
ste
m
a
ti
c
re
v
iew
o
f
th
e
li
tera
tu
re
wa
s
m
a
d
e
th
ro
u
g
h
t
h
e
p
re
fe
rre
d
re
p
o
rti
n
g
it
e
m
s
fo
r
sy
ste
m
a
ti
c
re
v
iew
s
a
n
d
m
e
ta
-
a
n
a
ly
se
s
(
P
RIS
M
A
)
m
e
th
o
d
o
l
o
g
y
,
h
i
g
h
li
g
h
ti
n
g
th
e
d
o
m
a
in
s
t
h
a
t
m
o
stly
u
se
h
y
b
ri
d
tec
h
n
iq
u
e
s
b
y
d
e
fi
n
in
g
t
h
e
o
n
e
s
with
th
e
h
ig
h
e
st
fre
q
u
e
n
c
y
o
f
imp
lem
e
n
tat
io
n
i
n
e
a
c
h
d
o
m
a
in
we
p
re
d
e
fin
e
d
.
Du
ri
n
g
th
e
se
lec
ti
o
n
p
r
o
c
e
ss
fro
m
t
h
e
4
se
lec
ted
d
a
tab
a
se
s,
2
2
5
1
wo
r
k
s
we
re
tak
e
n
in
to
c
o
n
si
d
e
ra
ti
o
n
,
o
f
w
h
ich
2
5
we
re
th
e
o
n
e
s
th
a
t
we
re
in
c
lu
d
e
d
i
n
t
h
e
re
v
iew
p
ro
c
e
ss
th
ro
u
g
h
v
a
ri
o
u
s
fil
terin
g
ste
p
s
a
n
d
e
x
c
l
u
sio
n
c
rit
e
ria.
On
g
o
i
n
g
,
we
d
e
fin
e
d
fo
u
r
m
a
in
c
a
teg
o
ries
wh
e
re
we
p
re
s
e
n
ted
e
a
c
h
p
a
p
e
r
in
d
i
v
id
u
a
ll
y
b
y
b
riefly
e
x
p
lai
n
in
g
th
e
u
n
d
e
rly
in
g
d
a
ta,
th
e
p
ro
p
o
se
d
h
y
b
ri
d
fo
re
c
a
stin
g
a
p
p
ro
a
c
h
a
n
d
th
e
e
v
a
lu
a
ti
o
n
p
e
rfo
rm
a
n
c
e
m
e
tri
c
s
su
c
h
a
s
ro
o
t
m
e
a
n
sq
u
a
re
e
rro
r
(
R
M
S
E
)
,
m
e
a
n
a
b
so
lu
te
e
rr
o
r
(M
AE)
,
a
n
d
m
e
a
n
a
b
so
lu
te
p
e
rc
e
n
tag
e
e
rro
r
(M
APE
)
.
In
a
s
u
m
m
a
ry
tab
le,
we
h
ig
h
li
g
h
t
th
e
m
o
st
u
se
d
h
y
b
rid
m
e
th
o
d
s
fo
r
e
a
c
h
d
o
m
a
in
,
c
o
n
c
lu
d
in
g
w
h
ich
o
f
t
h
e
sta
ti
stica
l
a
n
d
d
e
e
p
lea
rn
in
g
m
e
th
o
d
s a
re
m
o
stl
y
a
p
p
li
e
d
in
th
e
s
p
e
c
ifi
e
d
d
o
m
a
in
s.
K
ey
w
o
r
d
s
:
Do
m
ain
E
v
alu
atio
n
m
etr
ic
Hy
b
r
id
m
o
d
el
PR
I
SMA
ch
ec
k
lis
t
Sy
s
tem
atic
r
ev
iew
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
:
Ma
lv
in
a
Xh
ab
af
ti
Dep
ar
tm
en
t o
f
Statis
tics
an
d
Ap
p
lied
I
n
f
o
r
m
atics,
Facu
lty
o
f
E
co
n
o
m
y
,
Un
iv
er
s
ity
o
f
T
ir
an
a
R
o
ad
Ar
b
en
B
r
o
ci,
T
i
r
an
a,
Al
b
an
ia
E
m
ail: x
h
ab
af
tim
alv
in
a
1
@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
f
o
r
ec
asti
n
g
o
f
tim
e
s
er
i
es
n
o
wad
ay
s
h
as
b
ec
o
m
e
a
n
ec
ess
ity
s
in
ce
im
p
o
r
tan
t
a
cto
r
s
o
f
a
co
u
n
tr
y
'
s
ec
o
n
o
m
y
s
u
p
p
o
r
t
th
eir
d
ec
is
io
n
-
m
ak
i
n
g
i
n
th
ese
f
o
r
ec
asts
.
Su
p
p
o
s
e
we
wan
t
to
s
ee
th
e
b
en
ef
its
th
at
th
ese
f
o
r
ec
asts
h
av
e
b
r
o
u
g
h
t
i
n
d
if
f
er
e
n
t
d
o
m
ai
n
s
.
I
n
th
at
ca
s
e,
we
ca
n
f
o
cu
s
o
n
f
o
r
e
x
am
p
le
th
e
f
in
an
cial
an
d
s
to
ck
m
ar
k
et
f
ield
wh
er
e
th
e
f
o
r
ec
asts
h
av
e
h
elp
ed
in
th
e
d
ec
is
io
n
-
m
ak
in
g
p
r
o
ce
s
s
es
an
d
p
r
o
v
id
e
d
v
alu
ab
le
k
n
o
wled
g
e
in
th
e
f
o
r
ec
ast
o
f
s
to
ck
p
r
ices,
th
e
id
en
tific
atio
n
o
f
m
a
r
k
et
t
r
en
d
s
,
p
o
r
tf
o
lio
o
p
t
im
izatio
n
,
an
d
r
is
k
m
an
ag
em
en
t
[
1
]
–
[
3
]
,
t
h
e
f
iel
d
o
f
en
er
g
y
lo
ad
wh
er
e
it
h
a
s
h
elp
ed
i
n
b
etter
p
lan
n
in
g
o
f
p
o
licies
r
elate
d
to
en
er
g
y
,
f
o
r
an
aly
zi
n
g
th
e
d
y
n
am
ics
o
f
th
e
e
n
er
g
y
m
ar
k
et
an
d
p
r
ice
f
o
r
ec
asti
n
g
o
r
e
v
en
ele
ctr
icity
f
o
r
ec
asti
n
g
d
em
an
d
i
n
g
en
e
r
al
[
4
]
,
[
5
]
.
Als
o
,
f
o
r
ec
asts
h
av
e
h
elp
ed
in
o
th
er
s
en
s
itiv
e
d
o
m
ain
s
s
u
ch
as
h
ea
lth
ca
r
e
an
d
m
e
d
icin
e
in
th
e
m
an
ag
em
en
t o
f
ch
r
o
n
ic
d
is
ea
s
es,
th
e
allo
ca
tio
n
o
f
h
ea
lth
ca
r
e
r
eso
u
r
ce
s
,
an
d
s
u
r
v
eillan
ce
o
f
d
is
ea
s
es
th
at
h
av
e
a
r
is
k
o
f
an
o
u
tb
r
ea
k
[
6
]
,
[
7
]
a
n
d
wea
th
er
an
d
clim
ate
d
o
m
ai
n
in
th
e
p
r
e
d
ictio
n
o
f
l
o
n
g
an
d
s
h
o
r
t
-
ter
m
clim
ate
tr
en
d
s
an
d
ch
a
n
g
es,
p
r
ed
ictio
n
o
f
ex
tr
e
m
e
wea
th
er
ev
e
n
ts
,
f
o
r
ec
a
s
tin
g
f
u
tu
r
e
wate
r
a
v
ailab
ilit
y
,
f
lo
o
d
in
g
ev
en
ts
,
an
d
d
r
o
u
g
h
t
co
n
d
itio
n
s
[
8
]
–
[
1
1
]
.
So
,
th
e
im
p
o
r
ta
n
ce
o
f
tim
e
s
er
ies
f
o
r
ec
asti
n
g
n
o
t
o
n
ly
in
th
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
4
,
No
.
4
,
Au
g
u
s
t 2
0
2
5
:
2
6
0
1
-
2
6
1
2
2602
af
o
r
em
en
tio
n
ed
d
o
m
ain
s
b
u
t
in
g
en
er
al
in
d
if
f
er
en
t
f
ield
s
,
h
as
b
ee
n
d
em
o
n
s
tr
ated
f
r
o
m
tim
e
to
tim
e
b
y
ap
p
ly
in
g
tech
n
iq
u
es
o
r
m
et
h
o
d
s
,
s
tar
tin
g
with
th
e
tr
a
d
itio
n
al
o
n
es
th
at
ar
e
s
tatis
tical
an
d
m
o
v
in
g
o
n
to
ar
tific
ial
in
tellig
en
ce
m
eth
o
d
s
.
Statis
t
ical
m
eth
o
d
s
h
av
e
a
lway
s
b
ee
n
r
ec
o
g
n
ized
as
ef
f
ec
tiv
e
in
d
i
f
f
er
en
t
p
r
ed
ictio
n
s
as
a
r
esu
lt
o
f
t
h
e
q
u
an
titativ
e
an
al
y
s
is
th
ey
p
er
f
o
r
m
,
in
ter
p
r
etab
le
r
es
u
lts
,
an
d
ea
s
e
o
f
im
p
lem
en
tatio
n
,
b
u
t
th
ey
ar
e
lim
ited
to
th
e
ty
p
o
lo
g
y
o
f
d
ata
b
ec
a
u
s
e
th
ey
wo
r
k
b
etter
with
lin
ea
r
d
ata
[
1
2
]
–
[
1
4
]
.
Fo
r
th
e
ty
p
o
lo
g
y
o
f
n
o
n
-
lin
ea
r
d
ata,
i
n
tellig
en
t
f
o
r
ec
asti
n
g
m
eth
o
d
s
wer
e
s
ee
n
as
th
e
m
o
s
t
ef
f
ec
tiv
e,
wh
ic
h
d
e
m
o
n
s
tr
ate
th
e
ab
ilit
y
to
ca
p
t
u
r
e
c
o
m
p
le
x
p
atter
n
s
,
to
a
d
ap
t
to
d
y
n
a
m
ic
d
ata
wh
ile
also
in
cr
ea
s
in
g
th
e
p
er
f
o
r
m
an
ce
o
f
lar
g
e
d
ata
s
ets,
m
ak
in
g
th
e
m
v
er
y
ef
f
ec
tiv
e
to
o
ls
f
o
r
tim
e
s
er
ies
f
o
r
ec
asti
n
g
in
v
ar
io
u
s
f
ield
s
[
1
5
]
–
[
1
8
]
.
B
u
t
b
esid
es
th
eir
ef
f
ec
tiv
en
ess
an
d
th
e
ap
p
licatio
n
o
f
ea
ch
tech
n
iq
u
e
in
d
iv
id
u
ally
in
tim
e
s
er
ies,
th
e
h
y
b
r
id
izat
io
n
o
f
s
tatis
tical
an
d
in
tellig
e
n
t
m
eth
o
d
s
h
as
s
h
o
wn
an
im
p
r
o
v
e
d
f
o
r
ec
asti
n
g
p
er
f
o
r
m
an
ce
,
f
le
x
ib
ilit
y
,
ad
a
p
tab
ilit
y
,
s
tab
ilit
y
,
r
is
k
m
itig
atio
n
as
well
as
m
o
r
e
ac
cu
r
ate
in
ter
p
r
etab
ilit
y
m
ak
in
g
th
e
m
m
o
r
e
s
u
itab
le
f
o
r
f
o
r
ec
asti
n
g
tim
e
s
er
ies d
ata
i
n
v
ar
io
u
s
f
ield
s
an
d
a
p
p
licatio
n
s
[
1
9
]
–
[
2
1
]
.
Ou
r
f
o
c
u
s
in
th
is
p
a
p
er
is
n
o
t
to
ev
id
en
ce
th
e
ef
f
ec
tiv
en
ess
an
d
h
i
g
h
p
er
f
o
r
m
an
ce
o
f
h
y
b
r
id
m
eth
o
d
s
co
m
p
ar
ed
t
o
tr
ad
itio
n
al
o
r
in
d
iv
id
u
al
o
n
es
b
ec
au
s
e
o
t
h
er
w
o
r
k
s
h
av
e
p
r
o
v
e
d
th
is
m
atter
.
Hy
b
r
id
f
o
r
ec
ast
in
g
m
eth
o
d
s
h
av
e
em
er
g
e
d
as
p
o
wer
f
u
l
d
ec
is
io
n
-
m
ak
in
g
t
o
o
ls
in
v
ar
io
u
s
f
ield
s
,
o
f
f
e
r
in
g
co
m
p
u
tatio
n
al
ef
f
icien
cy
,
p
r
ed
ictiv
e
ac
c
u
r
ac
y
,
an
d
s
ig
n
if
ican
t
im
p
r
o
v
e
m
e
n
ts
in
f
o
r
ec
asti
n
g
p
er
f
o
r
m
an
c
e
an
d
h
av
e
b
e
co
m
e
im
p
o
r
tan
t
to
o
ls
f
o
r
i
n
f
o
r
m
e
d
d
ec
is
io
n
-
m
ak
in
g
in
f
i
n
a
n
c
e,
en
er
g
y
,
h
ea
lth
ca
r
e
,
an
d
wea
th
er
f
o
r
ec
asti
n
g
[
2
2
]
–
[
2
4
]
.
T
h
e
aim
is
to
h
i
g
h
l
ig
h
t
th
e
d
if
f
er
en
t
m
et
h
o
d
s
co
n
ce
r
n
in
g
th
o
s
e
d
o
m
ai
n
s
th
at
a
p
p
ly
th
e
m
th
e
m
o
s
t
an
d
th
at
h
a
v
e
s
h
o
wn
a
n
im
p
r
o
v
em
en
t a
n
d
p
o
s
itiv
e
im
p
ac
t
o
n
th
eir
r
esp
ec
tiv
e
d
ec
is
io
n
-
m
ak
in
g
.
I
n
th
is
f
o
r
m
,
we
ca
n
c
o
n
clu
d
e
th
e
h
y
b
r
id
m
eth
o
d
th
at
is
wi
d
ely
u
s
ed
i
n
th
e
r
esp
ec
tiv
e
d
o
m
ain
s
b
u
t
also
in
g
en
er
al.
Ou
r
m
o
tiv
atio
n
s
tar
ted
with
th
e
f
ac
t
th
at
t
h
is
ty
p
e
o
f
ap
p
r
o
ac
h
was
m
is
s
in
g
in
th
e
cu
r
r
en
t
liter
atu
r
e
an
d
th
er
ef
o
r
e
d
e
v
elo
p
ed
it
an
d
elab
o
r
ated
it
f
u
r
th
e
r
.
T
o
id
en
tify
th
e
r
ele
v
an
t
liter
atu
r
e
we
n
ee
d
ed
in
th
is
ca
s
e,
we
u
s
ed
th
e
m
eth
o
d
o
lo
g
y
estab
lis
h
e
d
b
y
p
r
ef
e
r
r
ed
r
ep
o
r
tin
g
item
s
f
o
r
s
y
s
t
em
atic
r
ev
iews
an
d
m
eta
-
an
aly
s
es (
PR
I
SMA)
f
o
r
th
is
s
y
s
tem
atic
liter
atu
r
e
r
ev
iew
[
2
5
]
.
First,
we
f
o
r
m
u
lated
th
e
r
esear
ch
q
u
esti
o
n
b
ased
o
n
th
e
k
ey
wo
r
d
s
t
h
at
h
elp
e
d
u
s
i
n
t
h
e
s
ea
r
ch
th
r
o
u
g
h
d
if
f
er
en
t
d
ata
b
ases
,
f
o
llo
wed
b
y
th
e
p
lan
n
in
g
o
f
th
e
r
esear
ch
p
r
o
to
co
l
wh
e
r
e
we
d
ef
in
ed
:
th
e
o
b
jectiv
es,
th
e
s
p
ec
if
ic
m
eth
o
d
th
at
we
will
u
s
e
PR
I
SM
A,
th
e
s
u
itab
ilit
y
cr
iter
io
n
o
f
th
e
in
d
iv
id
u
al
s
tu
d
ies,
th
e
p
lan
n
in
g
o
f
d
ata
ex
tr
ac
tio
n
f
r
o
m
in
d
iv
i
d
u
al
s
tu
d
ies
as
well
as
wh
at
an
aly
s
is
we
wi
l
l
f
o
llo
w.
T
h
en
we
p
r
o
ce
ed
e
d
with
th
e
liter
atu
r
e
s
ea
r
ch
r
ef
er
r
in
g
to
s
ev
er
al
d
atab
ases
th
at
wid
ely
o
f
f
er
wo
r
k
s
in
o
u
r
f
ield
o
f
in
ter
est
b
y
d
ef
in
in
g
th
e
m
ain
k
ey
ter
m
s
,
th
e
y
ea
r
th
e
y
will
co
v
er
,
th
e
n
u
m
b
e
r
o
f
r
esu
lts
h
eld
,
th
e
lan
g
u
a
g
e
o
f
th
e
wo
r
k
s
a
n
d
th
e
p
o
s
s
ib
ilit
y
o
f
ac
ce
s
s
.
I
n
th
e
f
o
llo
win
g
,
we
p
r
o
ce
e
d
ed
with
th
e
s
cr
ee
n
in
g
o
f
th
e
liter
atu
r
e
th
at
was
d
ev
elo
p
ed
in
two
p
h
ases
:
p
r
e
-
s
cr
ee
n
in
g
an
d
s
cr
e
en
in
g
,
with
th
e
ev
alu
atio
n
o
f
th
e
q
u
ality
o
f
th
e
wo
r
k
s
,
an
d
th
e
ex
tr
ac
tio
n
o
f
t
h
e
d
ata,
wh
er
e
we
th
en
d
eter
m
in
ed
th
e
d
o
m
ain
s
in
wh
ich
we
wo
u
ld
f
o
cu
s
b
y
d
iv
id
in
g
t
h
em
in
to
f
o
u
r
ca
teg
o
r
ies an
d
we
an
aly
ze
d
th
e
r
esu
l
ts
.
W
e
p
r
esen
t
ea
ch
p
ap
e
r
in
d
i
v
id
u
ally
f
o
r
ea
ch
ca
teg
o
r
y
b
y
b
r
ief
ly
ex
p
lain
in
g
th
e
u
n
d
e
r
ly
in
g
d
ata,
th
e
p
r
o
p
o
s
ed
h
y
b
r
id
f
o
r
ec
asti
n
g
a
p
p
r
o
ac
h
,
an
d
t
h
e
ev
alu
atio
n
r
e
s
u
lts
th
ey
s
co
r
ed
b
ased
o
n
d
if
f
er
en
t
m
etr
ics
s
u
ch
as
r
o
o
t
m
ea
n
s
q
u
ar
e
e
r
r
o
r
(
R
MSE
)
,
m
ea
n
ab
s
o
lu
te
er
r
o
r
(
MA
E
)
,
a
n
d
m
ea
n
ab
s
o
lu
t
e
p
er
ce
n
tag
e
er
r
o
r
(
MA
PE)
.
W
e
p
r
esen
ted
ea
ch
o
f
th
ese
s
tep
s
in
a
P
R
I
SM
A
f
lo
w
ch
ar
t.
T
h
e
wo
r
k
s
wer
e
s
elec
ted
b
ased
o
n
th
e
in
clu
s
io
n
an
d
e
x
clu
s
io
n
cr
iter
ia,
wh
ich
ar
e
d
etailed
i
n
th
e
m
eth
o
d
s
s
ec
tio
n
.
I
n
th
e
en
d
,
we
in
ter
p
r
eted
an
d
p
r
esen
ted
th
e
r
esu
lts
o
f
th
e
wo
r
k
s
in
a
s
u
m
m
ar
y
tab
le
o
n
wh
i
ch
we
d
r
ew
th
e
r
elev
an
t
c
o
n
cl
u
s
io
n
s
.
I
n
ad
d
itio
n
to
r
ee
m
p
h
asizin
g
th
e
im
p
o
r
t
an
ce
o
f
h
y
b
r
id
m
o
d
els
co
n
c
er
n
in
g
i
n
d
iv
id
u
al
o
n
es,
th
is
p
ap
er
s
p
ec
if
ically
h
ig
h
lig
h
ts
th
e
tech
n
i
q
u
es
th
a
t
h
av
e
a
wid
er
r
an
g
e
o
f
u
s
e
in
s
o
m
e
o
f
th
e
m
o
s
t
well
-
k
n
o
wn
an
d
s
en
s
itiv
e
d
o
m
ain
s
.
2.
M
E
T
H
O
D
T
h
e
m
a
i
n
p
u
r
p
o
s
e
o
f
t
h
i
s
p
a
p
e
r
i
s
t
o
i
d
e
n
t
i
f
y
t
h
e
h
y
b
r
i
d
m
et
h
o
d
s
t
h
a
t
a
r
e
u
s
e
d
t
h
e
m
o
s
t
in
d
i
f
f
e
r
e
n
t
d
o
m
a
i
n
s
,
h
i
g
h
l
i
g
h
ti
n
g
t
h
e
s
t
a
tis
t
i
ca
l
m
et
h
o
d
a
n
d
,
o
n
t
h
e
o
t
h
e
r
h
a
n
d
,
t
h
e
n
e
u
r
a
l
n
e
tw
o
r
k
s
(
d
ee
p
l
e
a
r
n
i
n
g
m
e
t
h
o
d
)
m
o
s
t
u
s
ed
in
h
y
b
r
id
izatio
n
.
T
h
is
was
d
o
n
e
u
s
in
g
th
e
PR
I
SMA
tech
n
iq
u
e
t
o
id
en
tif
y
th
e
m
o
s
t
ac
cu
r
ate
a
n
d
s
u
itab
le
s
tu
d
ies
f
o
r
o
u
r
wo
r
k
[
2
5
]
.
First,
we
f
o
r
m
u
lated
t
h
e
m
ain
r
esear
ch
q
u
esti
o
n
t
h
r
o
u
g
h
p
a
r
ticip
an
ts
,
in
ter
v
en
tio
n
s
,
c
o
m
p
ar
ato
r
s
,
o
u
tco
m
es
(
PICO)
.
I
n
th
e
f
o
ll
o
win
g
,
we
h
a
v
e
p
lan
n
ed
o
u
r
r
esear
ch
p
r
o
to
co
l,
h
ig
h
lig
h
tin
g
th
e
r
esear
c
h
o
b
jectiv
es,
th
e
s
p
ec
if
ic
m
eth
o
d
s
an
d
p
r
o
ce
s
s
es
th
at
we
will
u
s
e,
th
e
s
u
itab
ilit
y
cr
iter
ia
o
f
in
d
iv
i
d
u
al
s
tu
d
ies,
t
h
e
m
eth
o
d
o
f
d
ata
e
x
tr
ac
tio
n
f
r
o
m
th
ese
wo
r
k
s
,
as
well
as
th
e
d
eter
m
in
atio
n
o
f
th
e
p
ath
o
f
an
aly
s
is
th
at
we
w
ill
f
o
llo
w.
W
e
h
a
v
e
d
ef
in
ed
th
e
d
atab
ases
th
at
we
will
s
ea
r
ch
an
d
th
e
y
ea
r
th
at
th
ey
will
co
v
er
,
th
e
s
ea
r
ch
s
tr
ateg
ies
in
clu
d
in
g
th
e
ter
m
s
th
at
we
h
av
e
u
s
ed
as
well
as
th
e
n
u
m
b
er
o
f
s
av
ed
r
esu
lts
th
at
we
h
av
e
p
r
esen
ted
in
th
e
PR
I
SMA
ch
ec
k
lis
t c
h
ar
t.
T
o
id
en
tif
y
th
e
m
o
s
t
r
elev
an
t
wo
r
k
s
,
we
u
s
ed
s
o
m
e
s
ea
r
c
h
ter
m
s
wh
ich
h
el
p
ed
u
s
to
s
y
n
th
esize
th
e
r
esu
lts
o
f
th
e
s
ea
r
ch
es
i
n
th
e
d
i
f
f
er
en
t
d
atab
ases
.
W
e
h
av
e
u
s
ed
ter
m
s
s
u
ch
as
"Hy
b
r
id
f
o
r
ec
ast",
an
d
"Hy
b
r
id
m
o
d
el
"
to
d
ir
ec
t
th
e
s
ea
r
ch
to
war
d
s
th
o
s
e
wo
r
k
s
th
at
h
av
e
u
s
ed
h
y
b
r
id
m
eth
o
d
s
.
W
e
h
av
e
also
u
s
ed
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
Hyb
r
id
fo
r
ec
a
s
tin
g
meth
o
d
s
a
cro
s
s
va
r
ied
d
o
ma
in
s
-
a
s
ystema
tic
r
ev
iew
(
Ma
lvin
a
X
h
a
b
a
f
ti
)
2603
th
e
ter
m
s
"Stati
s
tical",
au
to
r
e
g
r
ess
iv
e
in
teg
r
ated
m
o
v
in
g
a
v
er
ag
e
(
"ARIM
A"
)
,
an
d
s
ea
s
o
n
al
au
to
r
eg
r
ess
iv
e
in
teg
r
ated
m
o
v
i
n
g
av
er
a
g
e
(
"
SAR
I
MA
"
)
,
b
ec
au
s
e
v
ar
io
u
s
wo
r
k
s
h
av
e
r
ef
er
r
e
d
d
ir
ec
tly
to
th
e
tech
n
iq
u
es
w
ith
o
u
t
u
s
in
g
th
e
ter
m
h
y
b
r
id
izatio
n
,
as
we
h
av
e
cited
am
o
n
g
th
e
m
o
s
t
u
s
ed
tech
n
i
q
u
es
in
s
tatis
tics
.
R
eg
ar
d
in
g
in
tellig
en
t
tech
n
iq
u
es,
we
h
av
e
u
s
ed
th
e
ter
m
s
"d
ee
p
lear
n
in
g
"
,
ar
tific
ial
n
eu
r
al
n
etwo
r
k
(
"ANN"
)
,
r
ec
u
r
r
en
t
n
eu
r
al
n
etwo
r
k
(
"R
NN"
)
,
"n
eu
r
al
n
etwo
r
k
",
an
d
lo
n
g
s
h
o
r
t
-
ter
m
m
em
o
r
y
(
"
L
STM
"
)
,
to
ca
p
tu
r
e
wo
r
k
s
th
at
ca
n
b
e
ad
d
r
ess
ed
with
s
u
ch
ter
m
s
as
we
h
av
e
a
ls
o
r
ef
er
r
ed
to
t
h
e
ter
m
s
a
n
d
t
ec
h
n
iq
u
es
th
at
m
o
s
t
u
s
ed
d
ee
p
lear
n
in
g
tec
h
n
iq
u
es.
Ou
r
s
ea
r
ch
is
p
er
f
o
r
m
e
d
in
f
o
u
r
d
atab
ases
as f
o
llo
ws:
‒
I
E
E
E
(
th
r
o
u
g
h
th
e
I
E
E
E
Xp
lo
r
e
p
latf
o
r
m
)
;
‒
E
ls
ev
ier
(
th
r
o
u
g
h
th
e
Scien
ce
Dir
ec
t p
latf
o
r
m
)
;
‒
MD
PI
(
th
r
o
u
g
h
th
e
M
u
ltid
is
cip
lin
ar
y
Dig
ital Pu
b
lis
h
in
g
I
n
s
titu
te
l
ib
r
ar
y
)
;
‒
W
iley
On
lin
e
L
ib
r
ar
y
(
t
h
r
o
u
g
h
th
e
W
iley
On
lin
e
L
ib
r
ar
y
p
l
atf
o
r
m
)
.
I
t
s
h
o
u
ld
b
e
n
o
ted
th
at
t
h
ese
d
atab
ase
s
wer
e
ch
o
s
en
as
th
o
s
e
th
at
in
clu
d
e
d
th
e
wid
e
r
a
n
g
e
o
f
wo
r
k
s
in
o
u
r
f
o
cu
s
,
i.e
.
,
th
e
h
y
b
r
id
izatio
n
o
f
s
tatis
tical
tech
n
iq
u
es
an
d
d
ee
p
lear
n
in
g
,
as
well
as
th
o
s
e
th
at
p
r
o
v
id
ed
th
e
p
o
s
s
ib
ilit
y
o
f
o
p
en
-
s
o
u
r
ce
wo
r
k
s
f
o
r
ac
ce
s
s
.
T
h
e
s
ea
r
ch
wa
s
ca
r
r
ied
o
u
t
f
o
r
t
h
e
last
5
y
ea
r
s
,
2
0
1
9
-
2
0
2
3
,
to
an
aly
ze
th
e
m
o
s
t r
ec
en
t stu
d
ie
s
,
as we
ll a
s
s
e
lec
t th
o
s
e
p
ap
er
s
th
at
wer
e
in
th
e
E
n
g
lis
h
lan
g
u
ag
e
(
T
a
b
le
1
).
T
ab
le
1
.
T
a
b
le
o
f
s
ea
r
ch
q
u
e
r
ies an
d
f
ilter
s
ap
p
lied
to
th
e
d
if
f
e
r
en
t d
atab
ases
D
a
t
a
b
a
s
e
Q
u
e
r
y
A
d
d
i
t
i
o
n
a
l
f
e
a
t
u
r
e
s
I
EEE
X
p
l
o
r
e
(
“
A
l
l
M
e
t
a
d
a
t
a
”
:
“
H
y
b
r
i
d
m
o
d
e
l
*
”
O
R
“
H
y
b
r
i
d
f
o
r
e
c
a
st
”
O
R
“
T
i
me
se
r
i
e
s
F
o
r
e
c
a
st
*
”
)
A
N
D
(
“
A
b
st
r
a
c
t
”
:
“
S
t
a
t
i
s
t
i
c
a
l
”
O
R
(
“
A
b
s
t
r
a
c
t
”
:
A
R
I
M
A
O
R
“
A
b
st
r
a
c
t
”
:
S
A
R
I
M
A
O
R
“
A
b
st
r
a
c
t
”
:
m
o
v
i
n
g
-
a
v
e
r
a
g
e
)
A
N
D
(
“
A
b
s
t
r
a
c
t
”
:
“
d
e
e
p
l
e
a
r
n
i
n
g
”
O
R
“
A
b
st
r
a
c
t
”
:
A
N
N
O
R
“
A
b
st
r
a
c
t
”
:
R
N
N
O
R
“
A
b
s
t
r
a
c
t
”
:
LS
TM
O
R
“
A
b
st
r
a
c
t
”
:
“
N
e
u
r
a
l
N
e
t
w
o
r
k
”
)
Y
e
a
r
s
:
2
0
1
9
–
2
0
2
3
La
n
g
u
a
g
e
:
E
n
g
l
i
sh
S
c
i
e
n
c
e
D
i
r
e
c
t
(
H
y
b
r
i
d
m
o
d
e
l
O
R
H
y
b
r
i
d
f
o
r
e
c
a
st
)
A
N
D
“
T
i
me
s
e
r
i
e
s
f
o
r
e
c
a
s
t
i
n
g
”
A
N
D
T
i
t
l
e
,
a
b
st
r
a
c
t
o
r
a
u
t
h
o
r
-
sp
e
c
i
f
i
e
d
k
e
y
w
o
r
d
s:
(
s
t
a
t
i
st
i
c
a
l
O
R
A
R
I
M
A
O
R
S
A
R
I
M
A
O
R
mo
v
i
n
g
a
v
e
r
a
g
e
)
A
N
D
(
“
d
e
e
p
l
e
a
r
n
i
n
g
”
O
R
A
N
N
O
R
R
N
N
O
R
LST
M
O
R
“
n
e
u
r
a
l
n
e
t
w
o
r
k
”
)
Y
e
a
r
s
:
2
0
1
9
–
2
0
2
3
La
n
g
u
a
g
e
:
E
n
g
l
i
sh
M
u
l
t
i
d
i
sc
i
p
l
i
n
a
r
y
D
i
g
i
t
a
l
P
u
b
l
i
s
h
i
n
g
I
n
st
i
t
u
t
e
(
M
D
P
I
)
(
(
A
l
l
F
i
e
l
d
s:
“
H
y
b
r
i
d
m
o
d
e
l
”
)
O
R
(
A
l
l
f
i
e
l
d
s
:
H
y
b
r
i
d
f
o
r
e
c
a
s
t
)
)
A
N
D
(
(
A
b
st
r
a
c
t
:
S
t
a
t
i
s
t
i
c
a
l
)
O
R
(
A
b
st
r
a
c
t
:
A
R
I
M
A
)
O
R
(
A
b
s
t
r
a
c
t
:
S
A
R
I
M
A
)
O
R
(
A
b
s
t
r
a
c
t
:
M
o
v
i
n
g
-
a
v
e
r
a
g
e
)
)
A
N
D
(
(
A
b
st
r
a
c
t
:
“
D
e
e
p
l
e
a
r
n
i
n
g
”
)
O
R
(
A
b
st
r
a
c
t
:
A
N
N
)
O
R
(
A
b
st
r
a
c
t
:
R
N
N
)
O
R
(
A
b
s
t
r
a
c
t
:
LST
M
)
O
R
(
A
b
s
t
r
a
c
t
:
“
N
e
u
r
a
l
n
e
t
w
o
r
k
”
)
)
Y
e
a
r
s
:
2
0
1
9
–
2
0
2
3
La
n
g
u
a
g
e
:
E
n
g
l
i
sh
W
i
l
e
y
O
n
l
i
n
e
L
i
b
r
a
r
y
"
"
H
y
b
r
i
d
mo
d
e
l
"
O
R
"
T
i
me
seri
e
s
f
o
r
e
c
a
s
t
"
a
n
y
w
h
e
r
e
a
n
d
"
st
a
t
i
st
i
c
a
l
O
R
A
R
I
M
A
O
R
S
A
R
I
M
A
O
R
mo
v
i
n
g
-
a
v
e
r
a
g
e
"
in
t
h
e
A
b
st
r
a
c
t
a
n
d
"
d
e
e
p
l
e
a
r
n
i
n
g
"
O
R
A
N
N
O
R
R
N
N
O
R
LST
M
O
R
"
n
e
u
r
a
l
n
e
t
w
o
r
k
"
"
in
t
h
e
A
b
s
t
r
a
c
t
Y
e
a
r
s
:
2
0
1
9
–
2
0
2
3
La
n
g
u
a
g
e
:
E
n
g
l
i
sh
I
n
Fig
u
r
e
1
,
we
p
r
esen
t
th
e
PR
I
SMA
2
0
2
0
f
lo
w
d
iag
r
am
f
o
r
n
ew
s
y
s
tem
atic
r
ev
iews
in
v
o
lv
in
g
o
n
ly
s
ea
r
ch
es
o
f
d
atab
ases
an
d
r
eg
i
s
tr
ies.
I
n
to
tal,
we
h
av
e
s
elec
t
ed
2
2
5
1
r
ep
o
r
ts
f
r
o
m
th
e
d
ata
b
ases
we
m
en
tio
n
ed
ab
o
v
e.
T
h
e
p
r
o
g
r
am
we
u
s
e
d
to
m
an
ag
e
th
e
p
r
e
-
s
cr
ee
n
i
n
g
p
r
o
ce
s
s
an
d
elim
in
ate
d
u
p
licates
is
C
itav
i.
Ab
o
u
t
2
2
5
d
u
p
licates
wer
e
i
d
en
tifie
d
wh
ich
wer
e
elim
in
ated
an
d
t
h
en
co
n
t
in
u
ed
with
th
e
s
cr
ee
n
in
g
th
e
liter
atu
r
e
p
r
o
ce
s
s
wh
ich
was
ca
r
r
ied
o
u
t
in
two
p
h
ases
:
th
e
f
ir
s
t
p
h
ase,
titl
e
an
d
ab
s
tr
ac
t
s
cr
ee
n
in
g
wh
er
e
all
th
e
titl
es a
n
d
ab
s
tr
ac
ts
wer
e
r
ea
d
an
d
th
e
n
th
e
s
elec
tio
n
o
f
th
o
s
e
m
o
r
e
ap
p
r
o
p
r
iate
as we
ll a
s
th
e
s
ec
o
n
d
p
h
ase,
fu
ll
tex
t
d
o
wn
l
o
ad
in
g
an
d
s
cr
ee
n
in
g
o
f
s
elec
ted
s
tu
d
ies.
Af
t
er
th
e
co
m
p
letio
n
o
f
th
e
f
ir
s
t
p
h
ase,
1
4
0
4
r
e
p
o
r
ts
wer
e
elim
in
ated
,
an
d
6
2
2
r
ep
o
r
ts
wer
e
tr
an
s
f
er
r
ed
t
o
b
e
p
r
o
c
ess
ed
in
th
e
s
ec
o
n
d
p
h
ase.
T
h
e
latter
wer
e
f
ilter
ed
b
y
ev
a
lu
atin
g
th
e
m
eth
o
d
o
lo
g
ical
q
u
ality
o
f
th
ese
ar
ticles a
s
well
a
s
b
ased
o
n
d
if
f
er
en
t
in
clu
s
io
n
a
n
d
e
x
clu
s
io
n
cr
iter
ia.
T
h
e
s
tep
o
f
d
at
a
ex
tr
ac
tio
n
an
d
q
u
ality
ass
ess
m
en
t
o
r
ien
ted
u
s
to
war
d
s
th
e
wo
r
k
s
th
at
h
av
e
an
o
r
ien
tatio
n
to
war
d
s
th
e
r
ese
ar
ch
q
u
esti
o
n
o
f
th
is
p
ap
er
.
T
h
e
wo
r
k
s
th
at
we
r
e
in
clu
d
ed
in
th
e
r
ev
iew
p
r
o
ce
s
s
ar
e
all
h
y
b
r
id
m
o
d
els
o
f
s
tatis
tical
m
eth
o
d
s
an
d
d
ee
p
le
ar
n
in
g
b
ec
a
u
s
e
o
u
r
m
ain
g
o
al,
as
m
en
tio
n
e
d
ab
o
v
e,
is
n
o
t
to
id
en
tify
th
e
f
ac
t
th
at
h
y
b
r
id
m
et
h
o
d
s
ar
e
b
ett
er
th
an
in
d
iv
id
u
al
m
eth
o
d
s
,
b
u
t
to
d
ete
r
m
in
e
th
at
h
y
b
r
id
m
et
h
o
d
s
th
at
o
u
tp
er
f
o
r
m
ed
th
e
o
t
h
er
s
in
d
if
f
er
en
t
d
o
m
ain
s
.
T
h
e
d
o
m
ai
n
s
th
at
we
h
av
e
f
o
c
u
s
ed
o
n
in
t
h
is
wo
r
k
h
a
v
e
b
ee
n
s
elec
ted
r
ef
er
r
in
g
to
th
e
a
m
o
u
n
t o
f
wo
r
k
th
at
we
h
av
e
r
ec
o
r
d
e
d
f
o
r
ea
c
h
o
f
t
h
ese
ar
ea
s
,
th
at
u
s
ed
d
if
f
e
r
e
n
t
h
y
b
r
id
tec
h
n
iq
u
es
as
well
as
th
e
q
u
ality
an
d
co
m
p
atib
ilit
y
o
f
th
ese
r
ep
o
r
ts
with
th
e
o
b
jectiv
es
o
f
o
u
r
wo
r
k
.
Sp
ec
if
ically
,
th
e
d
o
m
ain
s
in
wh
ich
we
h
av
e
f
o
cu
s
ed
ar
e
f
in
an
ce
an
d
s
to
ck
m
ar
k
et
p
r
ed
ictio
n
,
en
er
g
y
f
o
r
ec
asti
n
g
,
h
ea
lth
ca
r
e
a
n
d
m
e
d
i
ca
l
f
o
r
ec
asti
n
g
an
d
wea
th
er
an
d
clim
ate
f
o
r
ec
ast
in
g
,
d
o
m
ain
s
in
wh
ich
h
y
b
r
id
p
r
ed
ictio
n
h
as
p
o
s
itiv
ely
i
m
p
ac
ted
.
R
ep
o
r
ts
th
at
d
id
n
o
t
p
r
o
p
o
s
e
h
y
b
r
i
d
m
o
d
e
ls
o
r
wer
e
o
n
ly
s
tatis
tical
o
r
ANN,
n
eu
r
al
n
etwo
r
k
a
n
d
d
e
ep
lear
n
in
g
h
y
b
r
id
m
o
d
els
wer
e
ex
clu
d
ed
f
r
o
m
t
h
e
an
aly
s
is
.
A
s
ig
n
if
ican
t
p
ar
t
o
f
th
e
r
ep
o
r
ts
w
as
n
o
t
in
clu
d
ed
b
ec
au
s
e
we
d
id
n
o
t
h
a
v
e
ac
ce
s
s
to
th
eir
f
u
ll
tex
t
ev
en
af
ter
c
o
n
tactin
g
th
e
r
esp
ec
tiv
e
au
t
h
o
r
s
o
f
th
e
p
a
p
er
s
.
Sev
er
al
o
th
er
r
ep
o
r
ts
wer
e
n
o
t
i
n
clu
d
ed
d
u
e
to
a
lac
k
o
f
p
r
ec
is
io
n
in
th
e
m
eth
o
d
s
u
s
ed
.
Fin
ally
,
2
5
r
ep
o
r
ts
wer
e
s
elec
ted
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
4
,
No
.
4
,
Au
g
u
s
t 2
0
2
5
:
2
6
0
1
-
2
6
1
2
2604
th
at
m
et
th
e
in
clu
s
io
n
cr
iter
ia
.
B
ec
au
s
e
th
e
d
ata
f
r
o
m
th
e
s
elec
ted
s
tu
d
ies
h
av
e
d
if
f
er
e
n
t
r
esu
lts
r
ef
er
r
in
g
to
th
e
s
u
b
f
ield
,
th
ey
ca
n
ad
d
r
ess
b
u
t
also
th
e
d
atab
ase
in
w
h
ich
th
e
h
y
b
r
id
tech
n
iq
u
es
ar
e
ap
p
lied
,
o
n
ly
th
e
m
o
s
t
im
p
o
r
tan
t c
o
n
clu
s
io
n
s
wer
e
co
n
s
id
er
ed
in
th
is
r
e
v
iew.
Fig
u
r
e
1
.
PR
I
SMA
f
lo
w
ch
ar
t
s
h
o
win
g
th
e
f
ilter
ed
r
esu
lts
f
o
r
ea
ch
f
ilter
s
tep
ac
co
r
d
in
g
t
o
[
2
5
]
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
3
.
1
.
Resul
t
s
T
h
e
r
esu
lts
th
at
we
h
av
e
i
n
clu
d
ed
i
n
th
is
p
a
r
ag
r
a
p
h
a
r
e
d
i
v
id
ed
ac
c
o
r
d
in
g
to
th
e
d
if
f
er
e
n
t
d
o
m
ai
n
s
wh
er
e
we
h
av
e
f
o
cu
s
ed
.
T
h
e
s
tu
d
ies
in
clu
d
ed
in
th
is
r
ev
iew
s
h
o
w
th
e
im
p
o
r
tan
ce
o
f
h
y
b
r
id
tech
n
iq
u
es
b
y
h
ig
h
lig
h
tin
g
th
e
te
r
m
“h
y
b
r
id
i
za
tio
n
”
f
o
r
th
e
r
elev
an
t
f
ield
t
h
at
is
ev
id
en
ce
d
an
d
test
ed
.
I
n
th
e
f
o
ll
o
win
g
,
we
h
av
e
g
r
o
u
p
ed
th
e
r
esu
lts
in
to
f
o
u
r
ca
te
g
o
r
ies
b
ased
o
n
th
e
r
esp
ec
tiv
e
d
o
m
ain
.
T
h
e
f
ir
s
t
ca
teg
o
r
y
is
f
in
an
ce
an
d
s
to
ck
m
ar
k
et
p
r
ed
ictio
n
[
2
6
]
–
[
3
2
]
.
T
h
e
s
ec
o
n
d
ca
te
g
o
r
y
is
en
er
g
y
f
o
r
ec
asti
n
g
[
3
3
]
–
[
3
8
]
.
T
h
e
th
ir
d
ca
teg
o
r
y
is
h
ea
lth
ca
r
e
an
d
m
ed
ical
f
o
r
ec
asti
n
g
[
3
9
]
–
[
4
4
]
.
T
h
e
f
o
u
r
th
ca
teg
o
r
y
is
wea
th
er
an
d
clim
ate
f
o
r
ec
asti
n
g
[
4
5
]
–
[
5
0
]
.
3
.
1
.
1.
F
ina
nce
a
nd
s
t
o
ck
m
a
r
k
et
predict
io
n
Ab
d
u
lr
ah
m
a
n
et
a
l
.
[
2
6
]
p
r
ed
i
cted
s
to
ck
p
r
ice
u
s
in
g
a
h
y
b
r
i
d
AR
I
MA
-
L
STM
m
o
d
el,
b
as
ed
o
n
d
ata
d
ec
o
m
p
o
s
itio
n
with
a
lo
w
-
p
a
s
s
f
ilter
o
f
th
e
d
is
cr
ete
Fo
u
r
ier
tr
an
s
f
o
r
m
.
A
b
d
u
lr
a
h
m
an
e
t
a
l
.
[
2
6
]
u
s
ed
th
e
Gh
an
a
s
to
ck
ex
ch
a
n
g
e
,
wh
ich
is
th
e
s
to
ck
p
r
ice
o
f
a
b
an
k
with
1
3
9
8
in
s
tan
ce
s
f
o
r
th
e
p
er
io
d
Feb
r
u
ar
y
1
to
Sep
tem
b
er
2
1
,
2
0
2
0
.
T
h
ey
also
p
r
ed
icted
th
e
in
d
iv
id
u
al
tec
h
n
iq
u
es
b
esid
es
th
e
h
y
b
r
i
d
tech
n
iq
u
e
wh
ich
was
th
e
m
ain
g
o
al,
n
o
tin
g
th
e
b
e
s
t
p
er
f
o
r
m
an
ce
o
f
th
e
h
y
b
r
id
tech
n
iq
u
e,
AR
I
MA
-
L
STM
b
ased
o
n
th
e
R
MSE
v
alu
es
[
2
6
]
.
Pen
g
et
a
l
.
[
2
7
]
p
r
ed
icted
th
e
p
er
f
o
r
m
an
ce
o
f
th
r
ee
s
to
ck
m
ar
k
et
in
d
ices
u
s
in
g
h
y
b
r
id
AR
I
MA
-
m
u
ltil
ay
er
p
e
r
ce
p
tr
o
n
s
(
MLP
)
an
d
AR
I
MA
-
R
NN
m
eth
o
d
s
o
n
h
is
to
r
ical
d
ata
o
b
tain
ed
f
r
o
m
th
e
Pak
is
tan
s
to
ck
ex
ch
an
g
e
,
th
e
n
atio
n
al
s
to
ck
e
x
ch
an
g
e
o
f
I
n
d
ia,
a
n
d
th
e
Sri
L
an
k
a
s
to
ck
ex
c
h
an
g
e
f
o
r
t
h
e
p
er
io
d
Sep
tem
b
er
6
,
2009
to
Dec
em
b
er
2
6
,
2
0
1
9
.
T
h
e
im
p
lem
en
tatio
n
o
f
th
e
m
et
h
o
d
o
lo
g
ies wa
s
d
iv
id
ed
in
to
t
h
r
ee
p
ar
ts
ac
co
r
d
i
n
g
to
th
e
r
esp
ec
tiv
e
co
u
n
tr
ies
th
at
h
av
e
b
ee
n
s
tu
d
ied
,
th
at
is
Pak
is
tan
,
Sri
L
an
k
a,
an
d
I
n
d
i
a
[
2
7
]
.
T
h
e
r
esu
lts
s
h
o
wed
th
at
AR
I
MA
-
ML
P
o
u
tp
er
f
o
r
m
e
d
AR
I
MA
-
R
NN
f
o
r
th
e
ca
s
e
o
f
I
n
d
ia
a
n
d
Pak
is
tan
,
wh
ile
f
o
r
t
h
e
ca
s
e
o
f
Sri
L
an
k
a
,
AR
I
MA
-
R
NN
p
er
f
o
r
m
e
d
b
etter
[
2
7
]
.
C
o
m
p
a
r
i
s
o
n
s
o
f
ea
ch
m
eth
o
d
wer
e
m
a
d
e
th
r
o
u
g
h
R
MSE
,
MA
PE
,
an
d
MA
E
.
Ku
ls
h
r
esh
th
a
an
d
Vijay
alak
s
h
m
i
[
2
8
]
h
a
v
e
f
o
r
e
ca
s
ted
s
to
ck
m
ar
k
et
d
ata
d
ir
ec
tly
f
r
o
m
th
e
s
o
u
r
ce
o
f
th
e
S&
P
5
0
0
u
s
in
g
a
p
r
ee
x
is
tin
g
ap
p
licatio
n
p
r
o
g
r
am
m
in
g
in
ter
f
ac
e
(
API
)
,
u
s
in
g
two
a
p
p
r
o
ac
h
es:
a
h
y
b
r
id
AR
I
MA
-
L
STM
tech
n
iq
u
e
an
d
a
f
o
r
ec
asti
n
g
lib
r
ar
y
ca
lle
d
p
r
o
p
h
et.
T
h
r
o
u
g
h
th
ese
f
o
r
ec
asts
,
it
aim
s
to
an
aly
ze
th
e
r
is
e
an
d
f
all
in
s
to
ck
v
alu
es
i
n
p
r
ev
io
u
s
y
ea
r
s
.
Acc
o
r
d
in
g
to
th
e
a
u
th
o
r
s
,
th
e
AR
I
MA
-
L
STM
h
y
b
r
id
tech
n
iq
u
e,
b
ased
o
n
th
e
R
MSE
,
M
SE,
an
d
MA
PE,
e
v
alu
atio
n
m
etr
ics,
p
er
f
o
r
m
s
m
u
ch
b
etter
th
an
th
e
p
r
o
p
h
et
tech
n
iq
u
e
[
2
8
]
,
[
2
9
]
.
Mo
n
tañ
o
an
d
Viad
o
[
2
9
]
f
o
r
e
ca
s
ted
th
e
Pes
o
-
Do
llar
ex
ch
an
g
e
r
ate
u
s
in
g
th
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
Hyb
r
id
fo
r
ec
a
s
tin
g
meth
o
d
s
a
cro
s
s
va
r
ied
d
o
ma
in
s
-
a
s
ystema
tic
r
ev
iew
(
Ma
lvin
a
X
h
a
b
a
f
ti
)
2605
h
y
b
r
id
AR
I
MA
-
ANN
tech
n
iq
u
e
b
ased
o
n
B
an
g
k
o
Sen
tr
al
n
g
Pil
ip
in
as
(
B
SP
)
FX
r
ate
d
ata
f
o
r
t
h
e
p
er
i
o
d
2000
-
2
0
2
0
.
I
n
ad
d
i
ti
o
n
t
o
t
h
is
tec
h
n
i
q
u
e,
th
e
i
n
d
i
v
i
d
u
al
r
es
u
l
ts
o
f
t
h
e
Ho
lt
-
W
in
te
r
s
m
o
d
el
,
AR
I
MA
,
a
n
d
AN
N
wer
e
als
o
t
est
ed
,
m
a
k
i
n
g
c
o
m
p
a
r
is
o
n
s
b
ase
d
o
n
th
e
s
t
atis
t
ica
l
e
v
al
u
a
ti
o
n
m
e
tr
ics
M
AE
,
MS
E
,
an
d
R
MS
E
[
2
9
]
.
Acc
o
r
d
in
g
t
o
t
h
e
a
u
t
h
o
r
s
,
t
h
e
h
y
b
r
i
d
m
o
d
el
h
as
t
h
e
l
o
wes
t
m
ea
s
u
r
e
m
e
n
t
o
f
e
r
r
o
r
s
,
e
m
p
h
a
s
izi
n
g
t
h
e
p
o
s
s
i
b
ili
ty
o
f
in
tr
o
d
u
ci
n
g
a
m
o
r
e
a
cc
u
r
at
e
m
et
h
o
d
f
o
r
p
r
e
d
i
cti
n
g
t
h
e
F
X
r
a
te
w
it
h
h
y
b
r
i
d
m
o
d
e
li
n
g
[
2
9
]
.
I
n
th
e
f
o
l
l
o
wi
n
g
p
a
p
e
r
,
Ga
r
c
ía
et
a
l
.
[
3
0
]
m
a
d
e
th
e
f
o
r
e
ca
s
t
o
f
c
lo
s
in
g
p
r
ic
es
ta
k
i
n
g
i
n
t
o
a
cc
o
u
n
t
t
h
e
f
o
l
lo
w
in
g
c
u
r
r
e
n
ci
es:
E
UR
/USD
,
GB
P/
USD,
J
PY/
USD,
A
UD/US
D
,
an
d
N
Z
D/
USD
f
o
r
t
h
e
p
e
r
i
o
d
f
r
o
m
De
ce
m
b
er
1
8
,
2
0
1
7
t
o
J
an
u
ar
y
2
7
,
2
0
2
3
.
T
h
e
a
u
th
o
r
s
h
av
e
also
ch
o
s
en
th
e
d
ai
ly
cl
o
s
in
g
p
r
ice
o
f
th
e
B
itco
in
cr
y
p
to
cu
r
r
e
n
cy
f
u
tu
r
es
co
n
tr
ac
t
to
d
eter
m
in
e
th
e
b
eh
av
io
r
o
f
th
e
p
atter
n
s
[
3
0
]
.
T
h
e
f
o
r
ec
asti
n
g
m
eth
o
d
s
th
at
w
er
e
test
ed
f
o
r
th
eir
ef
f
ec
tiv
en
ess
f
o
r
th
ese
tim
e
s
e
r
ies
wer
e
AR
I
MA
,
L
STM
,
an
d
th
eir
h
y
b
r
id
izatio
n
.
Fro
m
th
e
ev
alu
atio
n
o
f
ea
ch
r
esp
ec
tiv
e
m
o
d
el
u
s
in
g
th
e
e
r
r
o
r
m
ea
s
u
r
es
(
MA
E
,
MA
PE,
an
d
R
MSE
)
,
it
was
c
o
n
clu
d
ed
th
at
th
e
h
y
b
r
id
m
eth
o
d
,
AR
I
MA
-
L
STM
,
r
eg
ar
d
less
o
f
p
er
f
o
r
m
an
ce
f
o
r
s
o
m
e
o
f
th
e
ty
p
es
o
f
c
u
r
r
e
n
cies,
s
u
ch
as
f
o
r
GB
P/U
SD
an
d
NZ
D/USD
wh
er
e
L
STM
m
eth
o
d
p
er
f
o
r
m
ed
b
etter
,
in
o
v
er
all
s
u
g
g
ests
a
s
lig
h
t
im
p
r
o
v
em
en
t
co
m
p
ar
ed
to
in
d
i
v
id
u
al
tech
n
i
q
u
es [
3
0
]
.
Peir
an
o
et
a
l
.
[
3
1
]
p
r
ed
icted
th
e
in
f
latio
n
r
ate
i
n
f
iv
e
L
atin
Am
er
ican
c
o
u
n
tr
ies
b
as
ed
o
n
th
e
SAR
I
MA
-
L
STM
h
y
b
r
id
tech
n
iq
u
e
with
m
o
n
th
ly
d
ata,
f
o
r
th
e
p
er
io
d
f
r
o
m
J
an
u
a
r
y
1
9
5
8
to
J
u
n
e
2
0
1
9
.
Af
te
r
th
e
tr
ain
in
g
o
f
th
e
d
ata,
th
e
r
e
s
p
ec
tiv
e
in
d
iv
id
u
al
a
n
d
h
y
b
r
i
d
tech
n
iq
u
es
wer
e
a
p
p
lied
to
s
ee
th
e
p
er
f
o
r
m
a
n
ce
o
f
ea
ch
o
n
e
[
3
1
]
.
T
h
e
au
th
o
r
s
h
av
e
ap
p
lied
r
o
llin
g
win
d
o
ws
in
th
e
m
o
d
els
th
e
y
h
a
v
e
s
tu
d
ied
,
n
o
t
in
clu
d
in
g
L
STM
,
wh
er
e
th
ey
h
av
e
p
r
e
d
icted
th
e
in
f
latio
n
r
ate
f
o
r
t
h
e
n
ex
t
m
o
n
th
,
m
o
v
in
g
th
e
win
d
o
ws
o
n
e
m
o
n
th
ah
ea
d
an
d
ca
lcu
latin
g
all
a
g
a
in
[
3
1
]
.
B
esid
es
th
e
SAR
I
M
A
-
L
STM
tech
n
iq
u
e,
t
h
e
in
d
i
v
id
u
al
ANN,
f
u
zz
y
in
f
er
en
ce
s
y
s
tem
(
FIS
)
,
ad
ap
tiv
e
n
etwo
r
k
-
b
ased
f
u
zz
y
in
f
er
en
ce
s
y
s
tem
(
ANFI
S
)
,
L
S
T
M,
an
d
SAR
I
MA
tech
n
iq
u
es,
as
well
as
th
e
SA
R
I
MA
-
ANN
h
y
b
r
id
,
wer
e
test
ed
f
o
r
ea
c
h
co
u
n
tr
y
.
Ov
e
r
all,
b
ased
o
n
th
e
MSE
er
r
o
r
m
etr
ic,
it
was
co
n
clu
d
e
d
th
at
th
e
SAR
I
MA
-
L
STM
te
ch
n
iq
u
e
p
er
f
o
r
m
ed
b
etter
c
o
m
p
ar
ed
to
th
e
o
th
er
m
o
d
els
th
at
wer
e
tak
en
in
th
e
s
tu
d
y
[
3
1
]
.
B
u
k
h
ar
i
et
a
l
.
[
3
2
]
to
o
k
in
to
s
tu
d
y
th
e
d
aily
o
p
en
p
r
ice
tim
e
s
er
ies
o
f
Fau
ji
Fer
tili
ze
r
C
o
m
p
an
y
(
FF
C
)
with
d
ata
f
r
o
m
J
an
u
ar
y
1
,
2
0
0
9
to
Ma
y
3
0
,
2
0
1
8
,
to
f
o
r
ec
ast
th
e
s
u
d
d
en
s
to
ch
asti
c
v
ar
iety
o
f
th
e
f
in
an
cial
m
ar
k
et.
T
h
e
m
o
d
els
in
clu
d
ed
in
th
e
s
tu
d
y
ar
e
th
e
AR
FIM
A
-
L
STM
h
y
b
r
i
d
m
o
d
el
as
well
as
th
e
tr
ad
iti
o
n
al
AR
I
MA
,
AR
FIM
A,
L
STM
,
an
d
g
e
n
er
alize
d
r
eg
r
ess
io
n
n
e
u
r
al
n
etwo
r
k
(
GR
NN
)
m
o
d
els
[
3
2
]
.
Fo
r
ea
ch
o
f
th
ese
m
o
d
els,
tr
ain
in
g
an
d
test
in
g
o
f
th
e
s
er
ies
h
av
e
b
ee
n
d
o
n
e
,
d
em
o
n
s
tr
atin
g
in
d
etail
ea
ch
s
tep
u
n
til
th
e
f
in
al
r
esu
lt.
T
h
e
f
in
al
ev
alu
atio
n
was
d
o
n
e
b
ased
o
n
th
e
s
tatis
tical
m
etr
ics
MA
E
,
R
M
SE
an
d
MA
PE.
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
i
d
m
o
d
el
s
ig
n
i
f
ican
tly
p
r
o
v
ed
th
e
b
est m
o
d
el
to
im
p
r
o
v
e
th
e
f
o
r
ec
asti
n
g
o
f
th
e
f
i
n
an
cial
s
er
ies b
y
in
cr
ea
s
in
g
th
e
ac
cu
r
ac
y
r
at
e
o
f
8
0
% [
3
2
]
.
3.
1.
2
.
E
nerg
y
f
o
re
ca
s
t
ing
Du
d
ek
et
a
l
.
[
3
3
]
m
a
d
e
th
e
m
o
n
th
ly
elec
tr
icity
d
em
an
d
f
o
r
e
ca
s
t
f
o
r
3
5
E
u
r
o
p
ea
n
co
u
n
tr
ie
s
b
ased
o
n
th
e
win
n
in
g
e
n
tr
y
in
th
e
M4
2
0
1
8
f
o
r
ec
ast
c
o
m
p
eti
tio
n
f
o
r
m
o
n
th
ly
d
ata
an
d
p
o
i
n
t
f
o
r
ec
a
s
ts
.
T
h
e
tim
e
s
er
ies
u
s
ed
h
av
e
d
if
f
er
e
n
t
len
g
th
s
r
a
n
g
in
g
f
r
o
m
2
4
y
ea
r
s
to
5
y
ea
r
s
.
T
h
e
m
o
d
el
th
at
was
u
s
ed
b
y
th
e
au
th
o
r
s
in
th
is
wo
r
k
is
th
e
ex
p
o
n
en
tial
s
m
o
o
th
in
g
-
r
esid
u
al
d
ilated
(
ETS
-
RD
)
-
L
STM
h
y
b
r
id
m
o
d
el
wh
ich
d
em
o
n
s
tr
ated
a
g
o
o
d
p
er
f
o
r
m
a
n
ce
b
ased
o
n
t
h
e
ev
alu
atio
n
m
etr
ics
(
R
MSE
an
d
MA
PE)
as
well
as
its
m
o
d
er
n
co
m
p
etitio
n
with
th
e
class
ic
an
d
b
ased
o
n
m
ac
h
in
e
lear
n
in
g
(
ML
)
[
3
3
]
.
T
h
e
p
u
r
p
o
s
e
o
f
th
e
s
tu
d
y
was n
o
t
o
n
ly
to
h
ig
h
lig
h
t
th
e
b
en
ef
its
o
f
th
e
h
y
b
r
id
izat
io
n
o
f
th
ese
tech
n
iq
u
es
b
u
t
also
to
d
em
o
n
s
tr
ate
s
tep
-
by
-
s
tep
th
e
tr
ad
itio
n
al
tech
n
iq
u
es
u
s
ed
with
t
h
e
co
r
r
esp
o
n
d
in
g
r
esu
lts
[
3
3
]
.
Gr
an
d
ó
n
et
a
l
.
[
3
4
]
p
r
ed
icted
th
e
n
atio
n
al
d
em
an
d
f
o
r
elec
tr
icity
in
Uk
r
ain
e
,
u
s
in
g
t
h
e
h
o
u
r
ly
d
em
an
d
v
ar
iab
le,
m
ac
r
o
ec
o
n
o
m
ic
v
ar
iab
l
es
an
d
tem
p
er
atu
r
e
f
o
r
th
e
p
er
io
d
2
0
1
3
-
2
0
2
0
.
T
h
e
ap
p
r
o
ac
h
u
s
ed
b
y
th
e
au
th
o
r
s
in
th
i
s
wo
r
k
was
h
y
b
r
id
u
s
in
g
s
tatis
tical
m
eth
o
d
s
s
u
ch
as
AR
I
MA
an
d
d
ee
p
lear
n
in
g
m
eth
o
d
s
s
u
ch
as
L
STM
.
T
h
e
m
eth
o
d
o
l
o
g
y
o
n
wh
ich
th
e
tech
n
iq
u
e
was
ap
p
lied
was
d
iv
id
ed
in
to
th
r
ee
ca
te
g
o
r
ies
th
e
tim
e
s
ca
le:
lo
n
g
-
ter
m
(
an
n
u
al)
,
m
e
d
iu
m
-
ter
m
(
d
aily
)
an
d
s
h
o
r
t
-
ter
m
(
h
o
u
r
l
y
r
eso
lu
tio
n
)
[
3
4
]
.
T
h
e
y
m
an
ag
ed
to
g
et
g
o
o
d
r
esu
lts
n
o
tin
g
th
at
th
e
co
m
b
in
atio
n
o
f
AR
I
MA
as
a
class
ical
s
tatis
tical
m
o
d
el
an
d
L
STM
as
a
d
ee
p
lear
n
i
n
g
m
o
d
el
b
ased
o
n
ML
alg
o
r
i
th
m
s
,
co
r
r
ec
ts
th
e
r
esid
u
als an
d
in
cr
ea
s
es th
e
f
o
r
ec
ast ac
cu
r
ac
y
[
3
4
]
.
R
ash
id
an
d
Vig
[
3
5
]
aim
ed
to
en
s
u
r
e
a
s
tab
le
elec
tr
icity
s
u
p
p
ly
b
y
d
ev
elo
p
in
g
a
h
y
b
r
id
f
o
r
ec
asti
n
g
m
o
d
el
u
s
in
g
h
is
to
r
ical
lo
ad
d
ata
p
r
o
v
id
ed
b
y
th
e
New
Yo
r
k
I
n
d
ep
e
n
d
en
t
Sy
s
tem
Op
er
at
o
r
(
NYI
SO)
f
o
r
th
e
p
er
io
d
f
r
o
m
J
an
u
ar
y
2
0
1
9
to
Dec
em
b
er
2
0
2
1
.
T
h
e
m
o
d
els
an
aly
ze
d
in
th
eir
s
tu
d
y
in
clu
d
ed
AR
I
MA
,
ANN,
an
d
a
h
y
b
r
id
AR
I
MA
–
ANN
ap
p
r
o
ac
h
[
3
5
]
.
T
h
ese
wer
e
ap
p
lied
to
p
er
f
o
r
m
o
n
e
-
s
tep
-
ah
ea
d
an
d
m
u
lti
-
s
tep
-
ah
ea
d
elec
tr
icity
lo
a
d
f
o
r
ec
asti
n
g
a
cr
o
s
s
d
if
f
er
en
t
tem
p
o
r
al
co
n
d
itio
n
s
,
i
n
clu
d
in
g
wee
k
d
ay
s
,
wee
k
en
d
s
,
an
d
h
ig
h
-
d
e
m
an
d
p
er
io
d
s
.
Fo
r
ec
a
s
t
ac
cu
r
ac
y
was
ev
alu
ated
u
s
in
g
R
MSE
an
d
MA
PE
m
et
r
ics.
T
h
e
au
th
o
r
s
co
n
clu
d
e
d
th
at
th
e
h
y
b
r
id
AR
I
MA
–
ANN
m
o
d
el
ac
h
iev
ed
s
u
p
er
io
r
p
er
f
o
r
m
a
n
ce
o
v
er
th
e
s
tan
d
alo
n
e
m
eth
o
d
s
,
with
u
p
to
9
6
%
im
p
r
o
v
em
e
n
t
in
p
r
ed
ictio
n
ac
c
u
r
ac
y
,
m
ak
in
g
it
h
ig
h
ly
e
f
f
ec
tiv
e
f
o
r
s
tab
le
an
d
r
eliab
le
elec
tr
icity
lo
ad
f
o
r
ec
asti
n
g
[
3
5
]
.
I
zu
d
i
n
et
a
l
.
[
3
6
]
m
a
d
e
th
e
elec
tr
icity
co
n
s
u
m
p
tio
n
f
o
r
ec
ast
f
o
r
Ma
lay
s
ia
f
o
r
th
e
tim
e
p
er
io
d
1
9
7
8
-
2
0
1
7
.
I
n
d
i
v
id
u
al
tech
n
iq
u
es
s
u
ch
as
AR
I
MA
an
d
ANN
as
we
ll
as
h
y
b
r
id
AR
I
MA
-
ANN
tech
n
iq
u
es
wer
e
im
p
lem
e
n
ted
.
T
h
e
au
th
o
r
s
o
r
ien
ted
t
h
eir
wo
r
k
to
wa
r
d
s
th
e
h
y
b
r
id
m
o
d
el,
r
ely
i
n
g
o
n
th
e
liter
atu
r
e
s
tu
d
ied
b
y
th
em
b
as
ed
o
n
th
e
s
tr
en
g
th
o
f
th
e
class
ical
m
o
d
els
f
o
r
th
e
lin
ea
r
n
atu
r
e
th
at
ch
ar
ac
ter
izes
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
4
,
No
.
4
,
Au
g
u
s
t 2
0
2
5
:
2
6
0
1
-
2
6
1
2
2606
th
em
as
AR
I
MA
as
well
as
th
e
ANN
m
o
d
el
in
t
h
e
n
o
n
-
lin
ea
r
d
im
en
s
io
n
[
3
6
]
.
MA
E
,
R
MSE
,
an
d
MA
PE
wer
e
u
s
ed
as
p
er
f
o
r
m
an
ce
m
ea
s
u
r
e
s
o
f
ea
ch
m
o
d
el
f
o
r
th
e
y
ea
r
s
2
0
1
4
–
2
0
1
7
.
I
t
was
co
n
clu
d
e
d
th
at
th
e
AR
I
MA
-
ANN
h
y
b
r
id
m
o
d
el
g
av
e
b
et
ter
r
esu
lts
in
ac
cu
r
ate
elec
tr
i
city
u
s
ag
e
p
r
e
d
ictio
n
m
o
d
els
to
in
cr
ea
s
e
p
o
wer
s
y
s
tem
r
eliab
ilit
y
[
3
6
]
.
Sin
h
a
et
a
l
.
[
3
7
]
p
r
e
d
icted
th
e
p
o
we
r
lo
ad
in
th
e
p
er
io
d
2
0
0
6
-
2
0
1
0
in
s
am
p
lin
g
p
er
m
in
u
te
f
o
r
th
e
s
tate
o
f
C
an
ad
a.
T
h
e
p
r
ed
ictio
n
was
m
ad
e
u
s
in
g
s
tatis
tical
m
o
d
els
as
we
ll
as
d
ee
p
lear
n
in
g
m
o
d
els
[
3
7
]
.
T
h
e
f
o
c
u
s
o
f
th
e
p
ap
e
r
was
th
e
p
r
o
p
o
s
al
o
f
th
e
v
ec
to
r
a
u
to
r
eg
r
ess
iv
e
(
V
AR
)
-
C
NN
-
L
STM
(
VACL)
h
y
b
r
id
m
o
d
el
to
co
m
b
in
e
th
e
ca
p
a
b
ilit
ies
o
f
b
o
th
t
y
p
o
lo
g
ies
o
f
s
tatis
tical
an
d
d
e
ep
lear
n
i
n
g
m
o
d
els
[
3
7
]
.
Sev
en
-
tim
e
s
er
ies
wer
e
in
clu
d
ed
in
th
e
m
o
d
el,
w
h
e
r
e
th
e
e
x
p
er
im
e
n
ts
wer
e
p
e
r
f
o
r
m
ed
b
o
th
o
n
th
e
p
r
o
p
o
s
ed
h
y
b
r
id
m
o
d
el
an
d
o
n
m
o
d
els
s
u
ch
as
ML
P,
L
ST
M,
C
NN
-
L
STM
,
an
d
VA
R
.
T
h
e
au
th
o
r
s
co
n
cl
u
d
ed
b
ased
o
n
th
e
r
esu
lts
o
f
th
e
p
ap
er
th
at
th
e
p
r
o
p
o
s
ed
h
y
b
r
id
m
o
d
el,
VACL,
m
ak
es a
m
o
r
e
ef
f
icien
t p
r
ed
ictio
n
o
f
th
e
s
h
o
r
t
-
ter
m
p
o
wer
lo
a
d
[
3
7
]
.
Als
o
,
in
th
is
p
ap
er
,
th
e
ev
al
u
atio
n
m
etr
ics
wer
e
MSE
a
n
d
R
MSE
.
J
ag
ait
et
a
l
.
[
3
8
]
p
r
o
p
o
s
ed
an
ap
p
r
o
ac
h
to
p
r
e
d
ict
th
e
elec
tr
ical
lo
ad
b
ased
o
n
th
e
c
o
m
b
i
n
atio
n
o
f
AR
I
MA
with
R
NN
u
n
d
er
c
o
n
ce
p
t.
T
h
e
d
ata
was
b
ased
o
n
e
ac
h
cu
s
to
m
er
'
s
h
o
u
r
ly
en
er
g
y
c
o
n
s
u
m
p
tio
n
d
ata
f
o
r
th
r
ee
y
ea
r
s
.
Oth
er
v
ar
iab
les
s
u
ch
a
s
tem
p
er
at
u
r
e,
h
u
m
id
ity
,
an
d
p
r
ess
u
r
e
wer
e
also
s
tu
d
ied
.
I
n
ad
d
itio
n
to
th
e
h
y
b
r
id
m
eth
o
d
,
t
h
e
ac
c
u
r
ac
y
o
f
r
o
llin
g
AR
I
MA
an
d
ad
ap
tiv
e
o
n
lin
e
R
NN
wa
s
ch
ec
k
ed
,
wh
er
e
f
o
llo
win
g
th
e
co
m
p
ar
i
s
o
n
o
f
th
ese
lo
ad
f
o
r
ec
asti
n
g
m
o
d
els,
as
well
as
th
e
ex
am
in
atio
n
o
f
s
tatis
tical
s
ig
n
if
ican
ce
[
3
8
]
.
T
h
e
au
th
o
r
s
ca
m
e
to
th
e
co
n
clu
s
io
n
th
at
th
e
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
ex
ce
ed
s
th
e
r
o
llin
g
AR
I
MA
an
d
o
n
lin
e
ad
ap
ti
v
e
R
NN
m
eth
o
d
s
,
em
p
h
asizin
g
th
e
n
ee
d
to
e
x
am
in
e
th
e
er
r
o
r
s
th
at
o
cc
u
r
u
n
d
er
th
e
co
n
ce
p
t
o
f
d
r
if
t.
3.
1.
3
.
H
ea
lt
hca
re
a
nd
m
edica
l f
o
re
ca
s
t
ing
Ketu
an
d
Mish
r
a
[
3
9
]
p
r
e
d
icted
th
e
o
u
tb
r
ea
k
o
f
C
OVI
D
-
1
9
th
r
o
u
g
h
t
h
e
AR
I
MA
-
L
STM
h
y
b
r
id
m
eth
o
d
,
in
th
e
p
er
io
d
was
ch
a
r
ac
ter
ized
as
th
e
m
o
s
t
d
elica
te
p
er
io
d
wh
er
e
it
o
cc
u
r
r
ed
a
n
d
th
e
g
r
ea
test
s
p
r
ea
d
in
alm
o
s
t
all
co
u
n
tr
ies
o
f
th
e
wo
r
ld
,
i.e
.
,
Dec
em
b
er
3
1
,
2
0
1
9
to
Octo
b
e
r
6
,
2
0
2
0
.
Data
,
s
u
ch
as
th
e
n
u
m
b
er
o
f
ac
tiv
e
ca
s
es,
n
u
m
b
er
o
f
co
n
f
i
r
m
ed
ca
s
es,
an
d
to
tal
n
u
m
b
e
r
o
f
d
ea
th
s
,
wer
e
o
b
tain
e
d
f
o
r
5
0
s
tates
[
3
9
]
.
T
h
e
au
th
o
r
s
aim
e
d
to
ev
al
u
ate
h
o
w
th
e
h
y
b
r
i
d
m
o
d
el
p
er
f
o
r
m
s
b
y
co
m
p
ar
in
g
it
with
th
e
two
in
d
i
v
i
d
u
al
m
o
d
els,
i.e
.
,
AR
I
MA
an
d
L
STM
.
Fro
m
th
e
p
r
ed
ictio
n
r
esu
lts
,
wh
er
e
R
MSE
,
MA
PE
,
an
d
R
-
s
q
u
ar
ed
(
R
2
)
wer
e
u
s
ed
as
ev
alu
ativ
e
p
a
r
am
eter
s
,
it
was
p
r
o
v
e
n
th
at
th
e
p
r
o
p
o
s
ed
h
y
b
r
id
m
o
d
el
h
ad
v
alu
es
with
s
ig
n
if
ican
t
d
if
f
e
r
en
ce
s
,
o
u
tp
er
f
o
r
m
in
g
o
th
e
r
k
n
o
wn
tr
ad
iti
o
n
al
m
o
d
els [
3
9
]
.
Z
h
an
g
et
a
l
.
[
4
0
]
f
o
llo
wed
in
t
h
eir
wo
r
k
with
a
h
y
b
r
id
ap
p
r
o
ac
h
,
au
to
r
e
g
r
ess
iv
e
(
AR
)
-
L
STM
,
f
o
r
th
e
p
r
ed
ictio
n
o
f
C
OVI
D
-
1
9
ca
s
es.
T
h
e
d
atab
ase
u
s
ed
co
n
s
is
ted
o
f
two
d
atasets
:
a
s
p
ec
if
ic
d
atab
ase
f
o
r
C
alif
o
r
n
ia
co
u
n
ties
as
well
as
s
ev
en
co
u
n
tr
ies
ar
o
u
n
d
t
h
e
w
o
r
ld
f
o
r
c
o
m
p
ar
ativ
e
an
aly
s
is
.
T
h
e
p
u
r
p
o
s
e
o
f
th
e
au
th
o
r
s
is
to
b
u
ild
a
m
o
d
el
t
h
at
will
ef
f
ec
tiv
ely
i
n
f
lu
en
ce
t
h
e
co
n
t
r
o
l
o
f
p
u
b
lic
h
ea
lth
p
o
licies
an
d
ab
o
v
e
all
C
OVI
D
-
1
9
,
also
h
elp
in
g
in
p
o
s
s
ib
le
p
r
ed
ictio
n
s
f
o
r
p
a
n
d
e
m
ics
th
at
m
ay
o
cc
u
r
in
th
e
f
u
t
u
r
e
[
4
0
]
.
T
h
e
r
esu
lts
o
f
th
e
p
ap
er
s
h
o
wed
th
r
o
u
g
h
th
e
q
u
an
titativ
e
ev
alu
atio
n
m
etr
ic
MA
PE,
th
at
th
e
h
y
b
r
id
AR
-
L
STM
m
o
d
el
o
f
f
er
s
a
m
o
r
e
ac
c
u
r
ate
p
r
ed
i
ctio
n
co
m
p
ar
ed
to
in
d
i
v
id
u
al
tr
ad
itio
n
al
m
eth
o
d
s
,
m
a
k
in
g
m
o
r
e
ev
i
d
en
t
t
h
e
tr
an
s
itio
n
p
ath
o
f
th
e
s
tag
es
o
f
v
ir
u
s
tr
an
s
m
is
s
io
n
as
well
a
s
im
p
r
o
v
in
g
d
ec
is
io
n
-
m
ak
in
g
[
4
0
]
.
J
in
et
a
l
.
[
4
1
]
a
l
s
o
m
a
d
e
a
s
t
u
d
y
f
o
r
t
h
e
p
r
e
d
i
c
t
i
o
n
o
f
t
h
e
s
p
r
e
a
d
o
f
C
OV
I
D
-
1
9
,
f
o
r
t
h
e
c
a
s
e
o
f
C
h
i
n
a
i
n
t
h
e
p
e
r
i
o
d
J
a
n
u
a
r
y
1
,
2021
t
o
Octo
b
er
1
0
,
2
0
2
2
,
ap
p
ly
in
g
th
e
weig
h
tin
g
m
eth
o
d
o
f
th
e
r
eg
r
ess
io
n
co
ef
f
icien
t
in
t
h
e
AR
I
MA
-
L
STM
h
y
b
r
id
p
a
r
allel
m
o
d
el.
B
esid
es
th
is
m
eth
o
d
,
h
e
also
s
tu
d
ied
o
th
er
m
o
d
els
s
u
ch
as
AR
I
MA
,
AR
I
MA
-
L
STM
in
s
er
ies
an
d
s
u
p
p
o
r
t
v
ec
to
r
r
e
g
r
ess
io
n
(
SVR
)
.
B
ased
o
n
s
o
m
e
ev
alu
atio
n
m
etr
ics
s
u
ch
as
R
MSE
,
MA
PE,
an
d
MSE
,
ea
ch
o
f
th
e
m
o
d
els
in
cl
u
d
ed
in
th
e
wo
r
k
was
ev
alu
ated
an
d
it
was
co
n
clu
d
ed
th
at
t
h
e
p
r
o
p
o
s
ed
m
o
d
el
p
er
f
o
r
m
ed
b
etter
th
a
n
th
e
o
th
er
m
o
d
els,
th
u
s
cr
ea
tin
g
a
p
r
ed
ictiv
e
m
o
d
el
th
at
g
u
id
es
th
e
p
r
ev
e
n
tio
n
o
f
t
h
e
s
p
r
ea
d
o
f
C
OVI
D
-
1
9
a
n
d
its
c
o
n
tr
o
l [
4
1
]
.
T
h
e
co
n
tr
ib
u
tio
n
o
f
th
is
p
ap
er
also
f
o
cu
s
es o
n
p
r
o
v
id
in
g
a
r
ef
er
e
n
ce
f
o
r
th
e
f
u
tu
r
e
d
ec
is
io
n
s
o
f
th
e
g
o
v
er
n
m
en
t.
J
in
et
a
l
.
[
4
2
]
im
p
r
o
v
e
d
t
h
e
m
o
d
el
u
s
e
d
in
t
h
e
w
o
r
k
m
e
n
ti
o
n
ed
a
b
o
v
e,
co
m
b
i
n
i
n
g
d
i
f
f
er
e
n
t
s
ta
tis
ti
ca
l
an
d
d
e
ep
le
ar
n
i
n
g
m
o
d
els
s
u
c
h
as
p
ar
tic
le
s
w
a
r
m
o
p
ti
m
iz
ati
o
n
(
PSO
)
-
L
ST
M
-
AR
I
MA
,
m
u
lti
p
l
e
l
in
ea
r
r
e
g
r
ess
i
o
n
(
M
L
R
)
-
L
STM
-
AR
I
MA
,
a
n
d
b
ac
k
-
p
r
o
p
a
g
ati
o
n
n
e
u
r
al
n
etw
o
r
k
(
B
PNN
)
-
L
S
T
M
-
AR
I
MA
.
T
h
e
d
at
a
o
b
tai
n
ed
i
n
t
h
e
s
t
u
d
y
w
er
e
f
o
r
G
er
m
a
n
y
a
n
d
J
ap
an
r
e
g
a
r
d
i
n
g
t
h
e
o
u
t
b
r
ea
k
o
f
C
OV
I
D
-
1
9
f
o
r
t
h
e
p
er
io
d
Ap
r
il
1
,
2
0
2
0
t
o
M
a
r
c
h
9
,
2
0
2
3
.
B
ase
d
o
n
t
h
e
v
a
lu
es
o
f
MS
E
,
R
MS
E
,
a
n
d
MA
E
,
t
h
e
B
P
NN
-
L
ST
M
-
AR
I
MA
m
o
d
el
p
r
o
v
e
d
a
h
i
g
h
e
r
p
r
e
d
ic
ti
o
n
a
cc
u
r
ac
y
,
e
m
p
h
asi
zi
n
g
o
n
c
e
a
g
a
in
t
h
e
co
n
t
r
i
b
u
ti
o
n
t
h
at
t
h
is
w
o
r
k
ca
n
g
i
v
e
t
o
th
e
g
o
v
er
n
m
e
n
t
a
n
d
p
u
b
lic
h
e
alt
h
au
th
o
r
it
ies
[
4
2
]
.
L
i
e
t
a
l
.
[
4
3
]
a
n
al
y
ze
d
t
h
e
AR
I
MA
a
n
d
AR
I
MA
-
GR
NN
m
o
d
els
to
p
r
e
d
ic
t
t
h
e
i
n
ci
d
e
n
ce
o
f
tu
b
er
cu
lo
s
is
in
C
h
i
n
a
,
wit
h
m
o
n
t
h
l
y
d
at
a
f
o
r
t
h
e
p
e
r
io
d
J
a
n
u
ar
y
2
0
0
7
to
J
u
n
e
2
0
1
6
.
T
h
e
p
r
e
d
i
cti
o
n
ac
c
u
r
ac
y
o
f
t
h
e
m
o
d
els
was
e
v
al
u
ate
d
t
h
r
o
u
g
h
R
MS
E
,
a
n
d
MA
PE
co
n
cl
u
d
in
g
t
h
a
t
th
e
h
y
b
r
i
d
AR
I
M
A
-
GR
NN
m
o
d
el
s
h
o
ws
h
i
g
h
er
p
e
r
f
o
r
m
a
n
c
e
i
n
f
i
tti
n
g
an
d
p
r
e
d
i
cti
n
g
th
e
s
h
o
r
t
-
t
er
m
i
n
ci
d
e
n
ce
o
f
t
u
b
er
c
u
l
o
s
is
w
it
h
o
u
t
p
ea
k
a
n
d
b
o
r
d
e
r
i
n
c
id
e
n
ce
[
4
3
]
.
D
e
n
g
e
t
a
l
.
[
4
4
]
m
ad
e
a
f
o
r
e
ca
s
t
o
f
o
u
tp
ati
en
t
v
is
its
i
n
h
o
s
p
i
tals
wit
h
t
h
e
a
r
g
u
m
e
n
t
th
at
t
h
e
y
ca
n
b
e
c
o
m
p
le
x
an
d
c
h
a
n
g
e
ac
c
o
r
d
i
n
g
t
o
t
h
e
s
ea
s
o
n
s
o
f
t
h
e
y
e
ar
,
u
s
i
n
g
th
e
h
y
b
r
i
d
AR
I
MA
-
L
S
T
M
m
e
th
o
d
o
p
ti
m
iz
e
d
b
y
B
P
,
f
o
r
t
h
e
p
e
r
i
o
d
J
u
n
e
1
,
2
0
1
4
t
o
Fe
b
r
u
a
r
y
1
7
,
2
0
1
9
.
T
h
r
e
e
d
e
p
a
r
t
m
e
n
ts
we
r
e
ta
k
e
n
i
n
th
e
s
tu
d
y
f
o
r
a
p
e
r
i
o
d
o
f
2
4
we
e
k
s
(
Se
p
t
em
b
e
r
9
,
2
0
1
8
t
o
Fe
b
r
u
a
r
y
1
7
,
2
0
1
9
)
:
t
h
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
Hyb
r
id
fo
r
ec
a
s
tin
g
meth
o
d
s
a
cro
s
s
va
r
ied
d
o
ma
in
s
-
a
s
ystema
tic
r
ev
iew
(
Ma
lvin
a
X
h
a
b
a
f
ti
)
2607
r
es
p
i
r
at
o
r
y
d
e
p
a
r
t
m
e
n
t
,
w
h
i
c
h
c
o
m
p
a
r
e
d
AR
I
MA
,
L
ST
M,
an
d
AR
I
MA
-
L
S
T
M
o
p
ti
m
i
z
ed
b
y
B
P;
a
n
d
t
h
e
ca
r
d
io
lo
g
y
d
e
p
a
r
t
m
e
n
ts
an
d
d
i
g
est
iv
e
d
e
p
a
r
t
m
e
n
ts
,
w
h
i
ch
co
m
p
a
r
e
d
AR
I
MA
-
L
S
T
M
b
ase
d
o
n
tr
ad
iti
o
n
al
m
et
h
o
d
s
a
n
d
AR
I
MA
-
L
STM
o
p
ti
m
iz
ed
b
y
B
P
[
4
4
]
.
I
n
th
e
r
esp
ec
t
iv
e
c
o
m
p
a
r
is
o
n
t
h
at
was
m
a
d
e
f
o
r
ea
ch
c
ase
th
r
o
u
g
h
t
h
e
p
er
f
o
r
m
an
ce
in
d
i
c
ato
r
s
,
i
n
t
h
e
r
es
p
i
r
at
o
r
y
d
e
p
a
r
t
m
e
n
t
th
e
h
y
b
r
i
d
m
o
d
el
p
e
r
f
o
r
m
e
d
b
et
te
r
,
w
h
il
e
i
n
th
e
o
t
h
e
r
t
wo
d
e
p
a
r
t
m
e
n
ts
,
t
h
e
p
r
o
p
o
s
ed
AR
I
MA
-
L
S
T
M
o
p
ti
m
i
ze
d
b
y
th
e
B
P
m
o
d
el
o
f
f
er
ed
a
b
et
te
r
p
r
e
d
ic
ti
o
n
ac
c
u
r
ac
y
[
4
4
]
.
T
h
e
au
t
h
o
r
s
c
o
n
cl
u
d
e
d
th
at
t
h
is
m
o
d
el
h
el
p
s
t
h
e
r
esp
ec
t
iv
e
p
o
lic
y
m
a
k
e
r
s
t
o
k
n
o
w
i
n
ad
v
a
n
ce
t
h
e
c
h
a
n
g
es
i
n
t
h
e
v
o
l
u
m
e
o
f
o
u
t
p
a
tie
n
ts
i
n
th
e
c
o
m
i
n
g
w
ee
k
s
o
r
m
o
n
t
h
s
.
3.
1.
4
.
Wea
t
her
a
nd
clim
a
t
e
f
o
re
ca
s
t
ing
Xu
et
a
l
.
[
4
5
]
p
r
e
d
ic
te
d
d
r
o
u
g
h
t
f
o
r
7
s
u
b
-
r
eg
io
n
s
o
f
C
h
i
n
a
,
u
s
i
n
g
a
to
tal
o
f
s
i
x
m
o
d
els
(
i
n
d
i
v
i
d
u
al
an
d
h
y
b
r
i
d
)
,
AR
I
MA
,
SVR
,
L
STM
,
AR
I
MA
-
SVR
,
L
S
-
SVR
,
a
n
d
AR
I
MA
-
L
S
T
M
,
f
o
r
t
h
e
p
er
i
o
d
J
an
u
ar
y
1
9
8
0
to
Dec
em
b
er
2
0
1
9
.
T
h
ese
m
o
d
els
ar
e
an
aly
ze
d
f
o
r
th
eir
p
r
e
d
ictio
n
ac
cu
r
ac
y
f
o
r
th
e
s
tan
d
ar
d
ized
p
r
ec
ip
itatio
n
ev
ap
o
r
atio
n
in
d
e
x
(
SP
E
I
)
.
T
h
e
r
esu
lts
o
b
tain
ed
in
th
e
s
tu
d
y
,
b
ased
o
n
th
e
m
o
n
th
ly
r
ai
n
f
all
an
d
tem
p
er
a
tu
r
e
d
ata,
wh
ich
ca
r
r
ied
o
u
t
L
ST
M
an
d
SVR
m
o
d
elin
g
with
SP
E
I
v
alu
es
at
6
,
1
2
,
a
n
d
2
4
-
m
o
n
th
s
ca
les,
in
itially
co
n
clu
d
e
d
th
at
th
e
h
y
b
r
id
m
o
d
els
(
AR
I
MA
-
SVR
,
L
S
-
SV
R
,
an
d
AR
I
MA
-
L
STM
)
h
ad
h
ig
h
er
p
r
e
d
ictio
n
ac
cu
r
ac
y
th
an
th
e
s
in
g
le
m
o
d
el
an
d
in
co
n
cl
u
s
io
n
th
at
th
e
AR
I
MA
-
L
STM
m
o
d
el
f
r
o
m
th
e
th
r
ee
h
y
b
r
id
m
o
d
els
tak
en
i
n
th
e
s
tu
d
y
h
as
th
e
h
ig
h
est
p
r
ed
ictio
n
ac
cu
r
a
cy
o
n
a
m
u
lti
-
tim
e
s
ca
le
[
4
5
]
.
I
n
co
n
clu
s
io
n
,
t
h
e
au
th
o
r
s
co
n
cl
u
d
ed
t
h
at
th
is
m
o
d
el
co
n
tr
i
b
u
tes
to
th
e
im
p
r
o
v
em
en
t
o
f
th
e
s
h
o
r
t
-
ter
m
an
d
l
o
n
g
-
ter
m
p
r
e
d
ictio
n
o
f
d
r
o
u
g
h
t in
C
h
in
a.
Kh
an
et
a
l
.
[
4
6
]
p
r
o
p
o
s
ed
a
co
m
b
i
n
atio
n
o
f
W
av
elet
tr
a
n
s
f
o
r
m
,
s
tatis
tical
m
o
d
els
an
d
ar
tific
ial
in
tellig
en
ce
i.e
.
,
W
av
elet
-
AR
I
MA
-
ANN
f
o
r
t
h
e
p
r
ed
ictio
n
o
f
d
r
o
u
g
h
ts
in
th
e
L
an
g
at
R
iv
er
b
asin
o
f
Ma
lay
s
ia
f
o
r
3
0
y
ea
r
s
with
d
ata
f
r
o
m
J
an
u
ar
y
to
Dec
em
b
er
1
9
8
6
.
T
h
e
in
p
u
ts
r
ec
eiv
ed
in
th
e
s
tu
d
y
wer
e
th
e
m
eteo
r
o
lo
g
ical
d
r
o
u
g
h
t
in
d
ex
,
th
e
s
tan
d
ar
d
ized
p
r
ec
ip
itatio
n
in
d
ex
an
d
th
e
s
tan
d
ar
d
d
aily
p
r
ec
ip
itatio
n
in
d
ex
[
4
6
]
.
B
ased
o
n
th
e
r
esu
lts
o
f
t
h
e
wo
r
k
,
t
h
e
au
th
o
r
s
co
n
clu
d
e
th
at
th
e
p
r
o
p
o
s
ed
h
y
b
r
id
m
o
d
el
p
er
f
o
r
m
ed
b
etter
th
an
th
e
o
th
er
m
o
d
els,
p
r
o
v
i
d
in
g
a
g
r
ea
ter
p
r
e
d
ictio
n
ac
cu
r
ac
y
co
n
ce
r
n
i
n
g
th
e
R
2
m
etr
ic
.
Z
h
ao
et
a
l
.
[
4
7
]
p
r
o
p
o
s
ed
a
co
m
b
in
ed
e
n
s
em
b
le
em
p
ir
ical
m
o
d
e
d
ec
o
m
p
o
s
itio
n
(
EEMD
)
-
L
STM
-
A
R
I
MA
m
o
d
el
f
o
r
f
o
r
ec
asti
n
g
m
o
n
t
h
ly
r
ain
f
all
in
L
u
o
y
an
g
C
ity
,
Hen
an
Pro
v
in
ce
,
C
h
in
a,
f
o
r
th
e
p
er
io
d
J
an
u
ar
y
1
9
7
3
to
Dec
em
b
er
2
0
2
1
[
4
7
]
.
B
esid
es
th
is
h
y
b
r
id
co
m
b
in
atio
n
,
in
d
i
v
id
u
al
m
o
d
els
an
d
h
y
b
r
id
izatio
n
s
o
f
o
th
er
s
wh
ic
h
d
id
n
o
t
p
er
f
o
r
m
b
etter
t
h
an
th
e
m
o
d
el
p
r
o
p
o
s
ed
b
y
t
h
e
a
u
th
o
r
s
.
I
n
itially
,
a
co
m
p
a
r
is
o
n
wa
s
m
ad
e
b
etwe
en
t
h
e
h
y
b
r
id
an
d
in
d
iv
id
u
al
m
o
d
els
wh
er
e
th
e
h
y
b
r
id
s
p
er
f
o
r
m
e
d
b
etter
an
d
th
en
th
e
h
y
b
r
id
m
o
d
els
with
ea
ch
o
th
er
[
4
7
]
.
T
h
e
c
o
m
p
ar
is
o
n
b
etwe
e
n
th
e
m
o
d
els
was
m
ad
e
th
r
o
u
g
h
in
d
icato
r
s
th
at
ar
e
co
m
m
o
n
ly
u
s
ed
f
o
r
m
o
d
el
ev
alu
atio
n
s
u
c
h
as:
R
MSE
a
n
d
MA
E
.
T
h
e
au
t
h
o
r
s
r
el
y
o
n
t
h
e
f
ac
t
t
h
at
a
tr
a
d
itio
n
al
in
d
iv
i
d
u
al
m
o
d
el,
b
ec
au
s
e
o
f
th
e
f
lu
ct
u
atin
g
v
a
r
iatio
n
o
f
th
e
m
o
d
el
d
ata,
ca
n
n
o
t
s
u
m
m
ar
ize
th
e
ch
ar
ac
ter
is
tics
o
f
th
is
s
er
ies,
b
r
in
g
in
g
a
n
in
ac
cu
r
ate
f
o
r
ec
ast.
I
n
t
h
e
en
d
,
it
was
co
n
clu
d
ed
th
at
th
e
E
E
MD
-
L
STM
-
AR
I
MA
h
y
b
r
id
m
o
d
el,
f
o
r
wh
ich
th
e
f
o
r
ec
ast
f
o
r
th
e
m
o
n
th
l
y
r
ain
f
all
f
r
o
m
2
0
2
2
to
2
0
2
4
was
m
a
d
e,
p
er
f
o
r
m
s
c
o
r
r
ec
tly
in
f
o
r
e
ca
s
tin
g
th
e
m
o
n
th
ly
r
ain
f
all
f
o
r
th
is
r
eg
io
n
[
4
7
]
.
Par
asy
r
is
et
a
l
.
[
4
8
]
p
r
ed
icte
d
s
ev
er
al
m
etr
o
lo
g
ical
v
ar
iab
les
s
u
ch
as
tem
p
er
atu
r
e,
h
u
m
id
ity
,
win
d
s
p
ee
d
an
d
d
ir
ec
tio
n
,
f
ir
s
tly
v
ar
iab
les
th
at
p
r
esen
t
s
ea
s
o
n
ality
as
well
as
th
o
s
e
th
at
ar
e
m
o
r
e
s
to
ch
asti
c
an
d
with
o
u
t
s
ea
s
o
n
ality
,
u
s
in
g
th
e
SAR
I
MA
-
L
STM
h
y
b
r
id
m
et
h
o
d
.
T
h
e
wo
r
k
was
d
iv
i
d
ed
i
n
to
two
p
ar
ts
wh
er
e
f
ir
s
t
th
e
tem
p
er
at
u
r
e
a
n
d
h
u
m
i
d
ity
wer
e
p
r
ed
icted
an
d
th
en
i
n
th
e
o
th
er
p
ar
t
t
h
e
win
d
was
p
r
ed
icted
.
T
h
e
d
ata
wer
e
tak
en
f
r
o
m
a
s
p
ec
if
ic
a
r
e
a
o
f
Gr
ee
ce
,
a
h
o
tel
in
C
r
ete
wh
er
e
a
d
ata
ac
q
u
is
itio
n
d
ev
ic
e
was
in
s
talled
an
d
th
e
tim
e
r
eso
lu
tio
n
o
f
th
e
m
ea
s
u
r
em
en
ts
u
s
ed
was
3
h
o
u
r
s
c
o
v
er
in
g
t
h
e
y
ea
r
s
1
9
7
5
–
2
0
0
4
a
n
d
th
e
t
o
tal
f
o
r
ec
ast
h
o
r
izo
n
co
n
s
id
er
ed
it
was
u
p
t
o
2
d
a
y
s
[
4
8
]
.
B
ased
o
n
th
e
lo
ca
lized
tim
e
s
er
ies,
th
e
SAR
I
MA
-
L
STM
h
y
b
r
id
m
o
d
el
o
u
tp
er
f
o
r
m
e
d
th
e
in
d
iv
id
u
al
SAR
I
MA
an
d
L
STM
m
eth
o
d
s
f
o
r
f
o
r
ec
ast
h
o
r
izo
n
s
o
f
1
-
2
d
ay
s
,
co
n
tr
ib
u
tin
g
to
a
b
etter
f
o
r
ec
ast o
f
tem
p
er
at
u
r
e
an
d
win
d
s
p
e
ed
f
o
r
t
h
e
s
p
ec
if
ic
ar
ea
s
tu
d
ie
d
[
4
8
]
.
B
elm
ah
d
i
et
a
l
.
[
4
9
]
f
o
r
ec
asted
th
e
d
aily
g
l
o
b
al
s
o
lar
r
ad
i
atio
n
in
two
cities
in
Mo
r
o
cc
o
with
d
ata
f
r
o
m
J
an
u
ar
y
1
,
2
0
1
5
to
Dec
em
b
er
3
1
,
2
0
1
5
,
f
r
o
m
a
m
ete
o
r
o
lo
g
ical
s
tatio
n
in
s
talled
in
a
s
p
ec
if
ic
lo
ca
tio
n
,
r
ely
in
g
o
n
th
e
f
ee
d
f
o
r
war
d
b
ac
k
p
r
o
p
ag
atio
n
n
e
u
r
al
n
etwo
r
k
(
FF
B
P
)
,
A
R
I
MA
,
an
d
au
to
-
r
eg
r
ess
iv
e
m
o
v
in
g
av
er
ag
e
(
AR
MA
)
m
o
d
els
as
well
as
th
eir
h
y
b
r
id
izatio
n
.
I
n
th
e
r
ea
lized
f
o
r
ec
ast,
th
e
m
o
d
el
th
at
h
ad
th
e
h
ig
h
est
co
r
r
elatio
n
co
e
f
f
icien
t,
i.e
.
,
p
e
r
f
o
r
m
ed
b
etter
with
r
ef
er
en
ce
to
t
h
e
ev
alu
atio
n
m
etr
ics,
was
th
e
AR
I
MA
-
FF
B
P
h
y
b
r
id
m
o
d
el
[
4
9
]
.
T
h
e
au
th
o
r
s
co
n
clu
d
ed
t
h
at
th
is
m
o
d
el
co
u
ld
c
o
n
tr
ib
u
te
to
th
e
p
r
ed
ictio
n
o
f
g
lo
b
al
s
o
lar
r
ad
iatio
n
i
n
o
t
h
er
lo
ca
tio
n
s
,
tak
in
g
in
to
c
o
n
s
id
er
atio
n
wh
eth
er
we
will
h
a
v
e
s
im
ilar
wea
th
er
co
n
d
itio
n
s
in
th
e
f
u
tu
r
e.
L
u
o
an
d
Go
n
g
[
5
0
]
p
r
o
p
o
s
ed
th
e
AR
I
MA
-
W
OA
-
L
STM
m
o
d
el
to
f
o
r
ec
ast
air
p
o
llu
tan
ts
in
two
lar
g
e
cities
in
C
h
in
a,
Sh
ijiazh
u
an
g
an
d
B
ao
d
in
g
f
o
r
th
e
p
e
r
io
d
J
an
u
ar
y
1
,
2
0
1
5
t
o
Ma
r
ch
1
,
2
0
2
2
.
I
n
t
h
e
co
m
p
ar
is
o
n
o
f
t
h
e
p
r
o
p
o
s
ed
m
o
d
el
with
f
iv
e
o
th
er
in
d
iv
id
u
al
a
n
d
h
y
b
r
i
d
m
o
d
els
(
AR
I
MA
,
L
STM
,
AR
I
MA
-
L
STM
,
wh
al
e
o
p
tim
izatio
n
alg
o
r
ith
m
(
W
OA
)
-
SLT
M,
co
m
p
lete
en
s
em
b
le
em
p
ir
ical
m
o
d
e
d
ec
o
m
p
o
s
itio
n
(
C
E
E
MD
AN
)
-
WO
A
-
SLT
M)
th
r
o
u
g
h
R
MSE
an
d
MA
E
.
Me
tr
ics
it
was
co
n
clu
d
e
d
th
at
th
is
m
o
d
el
p
er
f
o
r
m
s
b
etter
in
p
o
l
lu
tan
t
p
r
ed
ictio
n
ac
cu
r
ac
y
,
m
o
d
el
,
an
d
p
r
ed
ictio
n
s
tab
ilit
y
[
5
0
]
.
T
h
e
a
u
th
o
r
s
m
an
ag
ed
to
id
e
n
tify
a
m
o
d
el
th
at
ca
n
h
elp
m
an
a
g
e
air
p
o
ll
u
tio
n
b
etter
an
d
im
p
r
o
v
e
th
e
way
air
p
o
llu
tio
n
is
tr
ea
ted
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
4
,
No
.
4
,
Au
g
u
s
t 2
0
2
5
:
2
6
0
1
-
2
6
1
2
2608
3
.
2
.
D
is
cus
s
io
n
I
n
th
is
p
ap
er
,
to
d
ev
elo
p
a
s
y
s
tem
atic
r
ev
iew
o
f
liter
atu
r
e,
we
u
s
ed
th
e
PR
I
SMA
ch
ec
k
lis
t
m
eth
o
d
o
l
o
g
y
,
wh
ich
f
r
o
m
t
h
e
en
tire
lis
t
o
f
p
o
s
s
ib
le
ar
ticles
f
o
r
r
ev
iew
ex
tr
ac
ted
f
r
o
m
th
e
v
ar
io
u
s
d
atab
ases
th
at
wer
e
tak
en
in
to
co
n
s
id
er
atio
n
,
th
r
o
u
g
h
th
e
s
cr
ee
n
in
g
p
r
o
ce
s
s
as
wel
l
as
d
ata
ex
tr
ac
tio
n
an
d
q
u
ality
ass
es
s
m
en
t,
we
r
ea
ch
ed
2
5
p
ap
er
s
.
T
h
ese
wo
r
k
s
wer
e
class
if
ied
ac
co
r
d
in
g
to
d
if
f
e
r
en
t
d
o
m
ain
s
s
u
ch
as:
f
in
an
ce
a
n
d
s
to
ck
m
ar
k
et
p
r
e
d
ictio
n
,
en
e
r
g
y
f
o
r
ec
asti
n
g
,
h
ea
lth
ca
r
e
an
d
m
e
d
ical
f
o
r
ec
asti
n
g
,
an
d
wea
th
e
r
a
n
d
clim
ate
f
o
r
ec
asti
n
g
,
s
ee
in
g
th
e
im
p
o
r
tan
ce
th
at
h
y
b
r
id
m
et
h
o
d
s
h
ad
f
o
r
ea
c
h
o
f
t
h
em
.
I
n
ad
d
itio
n
to
th
e
class
if
icatio
n
th
r
o
u
g
h
d
o
m
ain
s
,
we
m
ain
ly
f
o
cu
s
ed
o
n
s
cien
tific
p
ap
er
s
th
at
h
av
e
h
y
b
r
i
d
izatio
n
o
f
s
ta
tis
tica
l
m
eth
o
d
s
an
d
n
e
u
r
al
n
etwo
r
k
s
,
co
m
p
ar
is
o
n
o
f
h
y
b
r
id
m
o
d
els
with
tr
ad
itio
n
al
in
d
iv
id
u
al
m
o
d
els
o
r
h
y
b
r
id
with
h
y
b
r
id
,
th
r
o
u
g
h
p
er
f
o
r
m
a
n
ce
m
etr
ics
s
u
ch
as
R
MSE
,
MA
E
,
an
d
MA
PE.
So
,
th
e
m
ain
p
u
r
p
o
s
e
o
f
th
is
p
ap
er
,
as
it
is
m
en
tio
n
ed
ab
o
v
e
in
th
e
i
n
tr
o
d
u
ctio
n
s
ec
tio
n
,
is
n
o
t
t
o
p
o
i
n
t
o
u
t
th
e
e
f
f
ec
tiv
en
ess
t
h
at
h
y
b
r
id
m
eth
o
d
s
h
av
e
in
d
if
f
er
e
n
t
d
o
m
ain
s
b
e
ca
u
s
e
th
is
h
as
alr
ea
d
y
b
ee
n
p
r
o
v
en
b
y
o
th
er
wo
r
k
s
[
2
2
]
,
b
u
t
f
am
iliar
ity
with
d
if
f
er
en
t
h
y
b
r
id
ty
p
o
lo
g
ies
in
th
e
d
o
m
ain
s
we
h
av
e
s
p
ec
if
ied
,
co
n
s
id
er
in
g
th
e
f
r
e
q
u
en
c
y
o
f
u
s
e
o
f
d
if
f
er
en
t
m
eth
o
d
s
in
th
e
g
r
o
u
p
o
f
s
tatis
tical
m
eth
o
d
s
as
well
as
th
at
o
f
th
e
n
eu
r
al
n
etwo
r
k
(
d
ee
p
lear
n
in
g
)
,
in
th
ese
d
o
m
ain
s
.
T
h
u
s
,
we
h
ig
h
lig
h
t
wh
ich
wo
u
ld
b
e
th
e
m
o
s
t
wid
ely
u
s
ed
h
y
b
r
id
izatio
n
m
o
d
el
in
ea
ch
d
o
m
ain
,
in
th
e
r
an
g
e
o
f
m
e
t
h
o
d
s
p
r
esen
ted
in
ea
ch
p
ap
er
.
I
n
th
e
an
aly
s
is
m
ad
e
f
o
r
ea
c
h
p
ap
er
,
we
s
tar
ted
b
y
id
en
ti
f
y
in
g
th
e
f
ield
o
f
p
r
ed
ictio
n
,
th
e
h
y
b
r
id
m
eth
o
d
o
l
o
g
y
u
s
ed
,
t
h
e
s
ize
o
f
th
e
d
ata
o
b
tain
e
d
in
th
e
s
tu
d
y
as
well
as
th
e
m
etr
ics
o
r
p
er
f
o
r
m
an
ce
ev
alu
atio
n
in
d
icato
r
s
o
f
ea
ch
m
o
d
el.
I
n
v
ar
io
u
s
wo
r
k
s
,
we
n
o
ticed
t
h
at
th
er
e
wer
e
co
m
p
a
r
is
o
n
s
o
f
h
y
b
r
id
co
m
b
in
atio
n
s
with
tr
ad
itio
n
al
in
d
iv
id
u
al
m
e
th
o
d
s
wh
er
e
it
was
alwa
y
s
co
n
clu
d
ed
th
at
th
e
h
y
b
r
id
m
et
h
o
d
p
er
f
o
r
m
ed
b
etter
th
an
th
e
in
d
iv
id
u
al
o
n
e
o
r
b
y
co
m
p
ar
in
g
d
if
f
e
r
en
t
h
y
b
r
id
izat
io
n
s
,
th
r
o
u
g
h
m
etr
ics
s
u
c
h
as
R
MSE
,
MA
E
,
MA
PE,
an
d
MSE
.
Fro
m
th
e
h
y
b
r
id
m
eth
o
d
s
u
s
ed
th
at
p
er
f
o
r
m
ed
b
etter
in
th
e
v
ar
i
o
u
s
p
ap
er
s
we
an
aly
ze
d
,
we
ev
id
en
ce
d
th
at
in
th
e
d
o
m
ain
o
f
f
in
an
ce
an
d
s
to
ck
m
ar
k
et
p
r
ed
ictio
n
,
t
h
e
m
eth
o
d
s
th
at
o
u
tp
e
r
f
o
r
m
ed
t
h
e
o
th
er
s
w
er
e:
AR
I
MA
-
L
STM
[
2
6
]
,
[
2
8
]
,
AR
I
MA
-
R
NN
[
2
7
]
,
a
n
d
au
to
r
e
g
r
ess
iv
e
f
r
ac
tio
n
ally
in
teg
r
ate
d
m
o
v
in
g
-
av
er
a
g
e
(
AR
FIM
A
)
-
L
STM
[
3
2
]
f
o
r
s
to
ck
p
r
ice
p
r
ed
ictio
n
,
AR
I
MA
-
ANN
[
2
9
]
,
an
d
AR
I
MA
-
L
STM
[
3
0
]
,
f
o
r
ex
ch
a
n
g
e
r
ate
p
r
e
d
ictio
n
as
well
as
SAR
I
MA
-
L
ST
M
f
o
r
in
f
latio
n
r
ate
p
r
ed
ictio
n
[
3
1
]
.
I
n
th
e
d
o
m
ain
o
f
e
n
e
r
g
y
f
o
r
ec
asti
n
g
,
h
y
b
r
id
m
o
d
els
s
u
ch
as:
E
T
S
-
L
STM
[
3
3
]
,
AR
I
MA
-
L
STM
[
3
4
]
,
AR
I
MA
-
ANN
[
3
5
]
,
[
3
6
]
,
VAR
-
C
NN
-
L
STM
[
3
7
]
,
an
d
AR
I
MA
-
R
NN
[
3
8
]
p
er
f
o
r
m
ed
b
etter
th
r
o
u
g
h
d
i
f
f
er
en
t
s
tu
d
ies
f
o
r
f
o
r
ec
asti
n
g
elec
tr
icity
d
em
a
n
d
o
r
lo
ad
.
I
n
th
e
d
o
m
ain
o
f
h
ea
lth
ca
r
e
an
d
m
e
d
ical
f
o
r
ec
asti
n
g
,
th
e
m
eth
o
d
s
th
at
o
u
tp
er
f
o
r
m
ed
t
h
e
o
th
er
s
wer
e
:
AR
I
MA
-
L
STM
[
3
9
]
,
[
4
1
]
,
AR
-
L
STM
[
4
0
]
an
d
AR
I
MA
-
B
PNN
-
L
STM
[
4
2
]
,
f
o
r
t
h
e
p
r
ed
ictio
n
o
f
th
e
o
u
t
b
r
ea
k
o
f
C
OVI
D
-
1
9
,
AR
I
MA
-
GR
NN
[
4
3
]
,
f
o
r
th
e
p
r
e
d
ictio
n
o
f
tu
b
er
c
u
lo
s
is
an
d
AR
I
MA
-
L
STM
[
4
4
]
,
f
o
r
th
e
p
r
ed
ictio
n
o
f
o
u
tp
atien
t
v
is
its
in
a
h
o
s
p
ital.
L
astl
y
,
in
t
h
e
f
ield
o
f
w
ea
th
e
r
an
d
clim
ate
f
o
r
ec
asti
n
g
,
we
h
av
e:
AR
I
MA
-
L
STM
[
4
5
]
an
d
AR
I
MA
-
ANN
[
4
6
]
,
f
o
r
t
h
e
p
r
ed
ictio
n
o
f
d
r
o
u
g
h
t
an
aly
s
is
,
AR
I
MA
-
EEMD
-
L
S
T
M
[
4
7
]
,
f
o
r
th
e
p
r
e
d
ictio
n
o
f
m
o
n
t
h
ly
r
ai
n
f
alls
,
SAR
I
MA
-
L
STM
[
4
8
]
f
o
r
th
e
p
r
ed
ictio
n
o
f
s
o
m
e
m
etr
o
l
o
g
ic
al
v
ar
iab
les
s
u
ch
as
tem
p
er
atu
r
e,
h
u
m
id
ity
,
win
d
s
p
ee
d
an
d
d
ir
ec
tio
n
,
AR
I
MA
-
FF
B
P
[
4
9
]
,
f
o
r
th
e
p
r
e
d
ictio
n
o
f
g
lo
b
al
s
o
lar
r
ad
iatio
n
a
n
d
AR
I
MA
-
W
OA
-
L
STM
[
5
0
]
f
o
r
air
p
o
llu
t
an
ts
p
r
ed
ictio
n
.
W
e
also
h
av
e
wo
r
k
s
th
at
s
ep
ar
ate
t
h
e
lin
ea
r
an
d
n
o
n
-
lin
ea
r
c
o
m
p
o
n
en
ts
u
s
in
g
wav
elet
tr
an
s
f
o
r
m
er
s
.
Ou
r
w
o
r
k
was
d
i
v
i
d
ed
i
n
t
o
f
o
u
r
g
r
o
u
p
s
wh
ic
h
w
er
e
b
as
ed
o
n
s
p
ec
if
ic
d
o
m
ai
n
s
:
i
)
g
r
o
u
p
1
:
f
i
n
an
ce
an
d
s
to
c
k
m
a
r
k
et
f
o
r
e
ca
s
t
in
g
;
ii)
g
r
o
u
p
2
:
e
n
e
r
g
y
f
o
r
e
ca
s
t
in
g
;
ii
i)
g
r
o
u
p
3
:
h
ea
l
th
ca
r
e
a
n
d
m
e
d
ic
al
f
o
r
e
ca
s
t
in
g
;
an
d
i
v
)
g
r
o
u
p
4
:
we
at
h
e
r
a
n
d
cli
m
at
e
f
o
r
e
ca
s
ti
n
g
.
F
o
r
e
ac
h
d
o
m
ai
n
,
d
i
f
f
e
r
e
n
t
h
y
b
r
i
d
m
et
h
o
d
s
we
r
e
i
d
e
n
t
if
i
e
d
th
a
t
we
r
e
u
s
e
d
a
n
d
t
h
a
t
o
u
t
p
e
r
f
o
r
m
e
d
th
e
o
th
e
r
m
et
h
o
d
s
w
ith
w
h
i
c
h
th
e
y
we
r
e
co
m
p
a
r
e
d
i
n
t
h
e
r
es
p
e
cti
v
e
wo
r
k
s
.
I
n
T
a
b
l
e
2
,
we
h
a
v
e
p
r
ese
n
te
d
a
s
u
m
m
ar
y
o
f
t
h
e
s
tu
d
ies
d
ef
in
in
g
t
h
e
d
o
m
ai
n
,
s
ize
o
f
d
a
ta
,
t
h
e
m
o
d
e
ls
th
a
t
w
er
e
u
s
ed
a
n
d
t
h
o
s
e
t
h
a
t
o
u
t
p
er
f
o
r
m
e
d
as
wel
l
as
t
h
e
p
e
r
f
o
r
m
a
n
ce
i
n
d
ic
at
o
r
s
.
T
h
i
s
ta
b
l
e
h
el
p
s
u
s
t
o
id
e
n
t
if
y
a
n
d
h
ig
h
l
ig
h
t
w
h
ic
h
c
o
m
b
i
n
ati
o
n
s
o
f
h
y
b
r
id
m
et
h
o
d
s
ar
e
t
h
e
m
o
s
t
u
s
e
d
i
n
ea
c
h
d
o
m
ai
n
as
w
ell
as
i
n
g
e
n
e
r
a
l.
I
n
g
e
n
e
r
al
,
r
eg
a
r
d
less
o
f
t
h
e
d
i
f
f
er
e
n
t
co
m
b
i
n
a
ti
o
n
s
t
h
at
h
a
v
e
b
ee
n
a
p
p
li
ed
,
it
is
n
o
t
ed
t
h
at
m
o
s
t
o
f
t
h
e
p
a
p
e
r
s
p
r
es
e
n
t
a
h
y
b
r
id
a
p
p
r
o
a
ch
u
s
in
g
t
h
e
AR
I
MA
m
et
h
o
d
i
n
c
o
m
b
i
n
a
ti
o
n
m
o
s
t
ly
w
it
h
t
h
e
L
S
T
M
m
et
h
o
d
.
AR
I
MA
is
th
e
s
tatis
tical
m
eth
o
d
th
at
p
r
e
v
ails
in
8
0
%
o
f
th
e
wo
r
k
s
,
wh
ile
L
STM
in
6
0
%
o
f
th
em
.
I
f
we
wer
e
to
id
en
tify
th
e
m
et
h
o
d
s
th
at
wer
e
u
s
ed
t
h
e
m
o
s
t
f
o
r
ea
ch
s
p
ec
if
ic
d
o
m
ain
,
we
wo
u
ld
h
av
e:
f
o
r
f
in
an
ce
a
n
d
s
to
ck
m
a
r
k
et
p
r
e
d
ictio
n
,
AR
I
MA
-
L
STM
,
f
o
r
e
n
er
g
y
f
o
r
ec
asti
n
g
,
AR
I
MA
-
L
STM
an
d
AR
I
MA
-
ANN,
f
o
r
h
ea
lth
ca
r
e
an
d
m
e
d
ical
f
o
r
ec
asti
n
g
,
AR
I
MA
-
L
STM
an
d
f
o
r
w
ea
th
e
r
an
d
cli
m
ate
f
o
r
ec
asti
n
g
we
h
av
e
AR
I
MA
-
L
STM
.
W
e
ca
n
n
o
t
s
ay
th
at
t
h
is
h
y
b
r
id
izatio
n
o
u
tp
er
f
o
r
m
s
all
t
h
e
o
th
er
m
et
h
o
d
s
u
s
ed
b
ec
a
u
s
e
th
e
r
esu
lts
o
f
th
e
p
r
ed
ictio
n
s
r
ely
o
n
t
h
e
d
ata
we
ar
e
u
s
in
g
in
a
s
p
ec
if
ic
m
o
d
el,
b
u
t
we
ar
e
b
asin
g
it
o
n
th
e
f
r
eq
u
e
n
cy
o
f
u
s
e
o
f
t
h
ese
m
eth
o
d
s
in
d
if
f
er
e
n
t
d
o
m
ain
s
f
o
r
v
ar
io
u
s
p
r
e
d
ictio
n
s
.
So
o
v
er
all,
if
we
co
m
p
ar
e
th
ese
r
esu
lts
th
at
we
m
an
ag
ed
to
o
b
tain
with
ea
ch
o
f
th
e
wo
r
k
s
th
at
we
h
av
e
in
clu
d
ed
in
th
e
s
tu
d
y
,
we
ca
n
s
ay
th
at
th
e
h
y
b
r
id
m
eth
o
d
s
ar
e
th
e
o
n
es
t
h
at
p
e
r
f
o
r
m
b
est
in
p
r
ed
ictin
g
th
e
d
o
m
ain
s
as
well
as
th
e
m
o
s
t
p
o
p
u
lar
m
eth
o
d
s
u
s
ed
f
o
r
h
y
b
r
i
d
izatio
n
ar
e
AR
I
M
A
with
ANN
o
r
L
STM
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
Hyb
r
id
fo
r
ec
a
s
tin
g
meth
o
d
s
a
cro
s
s
va
r
ied
d
o
ma
in
s
-
a
s
ystema
tic
r
ev
iew
(
Ma
lvin
a
X
h
a
b
a
f
ti
)
2609
T
ab
le
2
.
Su
m
m
a
r
y
o
f
s
tu
d
ies a
p
p
ly
in
g
h
y
b
r
id
tech
n
iq
u
es a
n
d
m
o
d
els f
o
r
f
o
r
ec
asti
n
g
v
ar
io
u
s
d
o
m
ain
s
A
u
t
h
o
r
s
D
o
ma
i
n
Si
ze
o
f
d
a
t
a
Mo
d
e
l
u
s
e
d
Bes
t
mo
d
e
l
Perf
o
rma
n
c
e
i
n
d
i
ca
t
o
r
s
A
b
d
u
l
ra
h
m
an
e
t
a
l
.
[
2
6
]
Fi
n
a
n
ce
a
n
d
s
t
o
c
k
mar
k
e
t
fo
re
ca
s
t
i
n
g
1
st
Fe
b
r
u
ar
y
-
21
s
t
Sep
t
e
mb
er
2
0
2
0
A
RI
M
A
,
L
S
T
M,
A
RIM
A
-
L
S
T
M
A
RI
M
A
-
L
S
T
M
RMS
E
Pen
g
,
e
t
a
l
.
[
2
7
]
Fi
n
a
n
ce
a
n
d
s
t
o
c
k
mar
k
et
f
o
rec
as
t
i
n
g
Sep
t
e
mb
er
6
,
2
0
0
9
-
D
ec
em
b
er
2
6
,
2
0
1
9
A
RI
M
A
,
M
L
P,
R
N
N
,
A
RI
M
A
-
M
L
P
,
A
RI
M
A
-
RN
N
A
RI
M
A
-
R
N
N
an
d
A
RI
M
A
-
ML
P
RMS
E
,
MA
PE
,
MA
E
K
u
l
s
h
re
s
h
t
h
a
a
n
d
V
i
j
a
y
a
l
a
k
s
h
mi
[
2
8
]
Fi
n
a
n
ce
a
n
d
s
t
o
c
k
mar
k
e
t
fo
re
ca
s
t
i
n
g
5
0
0
d
at
a
A
RI
M
A
,
A
RIM
A
-
L
S
T
M,
Pro
p
h
e
t
A
RI
M
A
-
L
S
T
M
RMS
E
,
MS
E
,
MA
PE
,
R
2
Mo
n
t
a
ñ
o
a
n
d
V
i
ad
o
[2
9
]
Fi
n
a
n
ce
a
n
d
s
t
o
c
k
mar
k
et
f
o
rec
as
t
i
n
g
2
0
0
0
-
2
0
2
0
H
o
l
t
W
i
n
t
er
s
,
A
RI
MA
,
A
N
N
,
A
RIM
A
-
ANN
A
RI
M
A
-
A
N
N
RMS
E
,
MA
E
,
M
SE
G
arcí
a
e
t
a
l
.
[
3
0
]
Fi
n
a
n
ce
a
n
d
s
t
o
c
k
mar
k
et
f
o
rec
as
t
i
n
g
D
ec
em
b
er
1
8
,
2
0
1
7
-
J
a
n
u
ar
y
2
7
,
2
0
2
3
A
RI
M
A
,
L
S
T
M,
A
RIM
A
-
L
S
T
M
A
RI
M
A
-
L
S
T
M
RMS
E
,
MA
PE
,
MA
E
Pei
r
an
o
et
a
l
.
[
3
1
]
Fi
n
a
n
ce
a
n
d
s
t
o
c
k
mar
k
et
f
o
rec
as
t
i
n
g
J
a
n
u
ar
y
1
9
5
8
-
J
u
n
e
2
0
1
9
A
N
N
,
FIS,
A
N
FIS,
L
S
T
M
,
S
A
R
IM
A
SA
R
IM
A
-
A
N
N
,
SA
R
IM
A
-
L
S
T
M
SA
R
IM
A
-
L
S
T
M
MSE
Bu
k
h
ar
i
e
t
a
l
.
[3
2
]
Fi
n
a
n
ce
a
n
d
s
t
o
c
k
mar
k
e
t
fo
re
ca
s
t
i
n
g
J
a
n
u
ar
y
1
,
2
0
0
9
-
Ma
y
3
0
,
2
0
1
8
A
RI
M
A
,
A
RFIM
A
,
L
S
T
M
,
G
R
N
N
,
A
RFI
M
A
-
L
S
T
M
A
RF
IM
A
-
L
S
T
M
RMS
E
,
MA
E
,
M
A
P
E
D
u
d
ek
e
t
a
l
.
[
3
3
]
E
n
er
g
y
f
o
re
cas
t
i
n
g
2
4
y
ear
s
G
RN
N
,
A
N
FIS,
L
S
T
M,
A
RI
M
A
,
E
T
S
,
E
T
S
-
G
RN
N
,
A
N
FIS
-
E
T
S,
E
T
S
-
RD
-
L
S
T
M.
E
T
S
-
RD
-
L
S
T
M
RMS
E
,
MA
E
,
Med
i
a
n
A
PE
G
ran
d
ó
n
e
t
a
l
.
[
3
4
]
E
n
er
g
y
fo
re
ca
s
t
i
n
g
2
0
1
3
-
2
0
2
0
A
RI
M
A
,
L
S
T
M,
A
RIM
A
-
L
S
T
M
A
RI
M
A
-
L
S
T
M
RMS
E
,
MA
E
,
M
A
S
E
Ras
h
i
d
a
n
d
V
i
g
[3
5
]
E
n
er
g
y
f
o
re
cas
t
i
n
g
J
a
n
u
ar
y
2
0
1
9
-
D
ec
em
b
er
20
21
A
RI
M
A
,
A
N
N
,
A
RIM
A
-
ANN
A
RI
M
A
-
A
N
N
RMS
E
a
n
d
MA
PE
Izu
d
i
n
e
t
a
l
.
[
3
6
]
E
n
er
g
y
f
o
re
cas
t
i
n
g
1
9
7
8
-
2
0
1
7
A
RI
M
A
,
A
N
N
,
A
RIM
A
-
ANN
A
RI
M
A
-
A
N
N
MA
E
,
RMS
E
,
MA
PE
Si
n
h
a
e
t
a
l
.
[3
7
]
E
n
er
g
y
f
o
re
cas
t
i
n
g
2
0
0
6
-
2
0
1
0
V
A
R,
M
L
P
,
L
S
T
M
,
C
N
N
-
L
S
T
M
,
V
A
R
-
CN
N
-
L
ST
M
V
A
R
-
CN
N
-
L
S
T
M
MA
E
,
RMS
E
,
MS
E
J
a
g
a
i
t
et
a
l
.
[
3
8
]
E
n
er
g
y
f
o
re
cas
t
i
n
g
h
o
u
r
l
y
e
n
e
rg
y
co
n
s
u
mp
t
i
o
n
d
a
t
a
f
o
r
t
h
ree
y
e
ar
s
A
RI
M
A
,
R
N
N
,
A
R
IM
A
-
RN
N
A
RI
M
A
-
R
N
N
MA
E
an
d
MSE
K
e
t
u
a
n
d
M
i
s
h
ra
[
3
9
]
H
ea
l
t
h
care
a
n
d
med
i
c
al
fo
re
ca
s
t
i
n
g
D
ec
em
b
er
3
1
,
2
0
1
9
-
O
c
t
o
b
er
6
,
2
0
2
0
A
RI
M
A
,
L
S
T
M,
A
RIM
A
-
L
S
T
M
A
RI
M
A
-
L
S
T
M
RMS
E
,
MA
PE
,
R
2
Z
h
a
n
g
e
t
a
l
.
[
4
0
]
H
ea
l
t
h
care
a
n
d
med
i
c
al
fo
reca
s
t
i
n
g
Feb
r
u
r
ar
y
0
1
,
2
0
2
0
-
Sep
t
e
mb
er
0
5
,
2
0
2
2
A
RI
M
A
,
L
S
T
M,
L
S
T
M
d
o
u
b
l
e,
A
RIM
A
-
L
ST
M
A
RI
M
A
-
L
S
T
M
MA
PE
J
i
n
et
a
l
.
[
4
1
]
H
ea
l
t
h
care
a
n
d
med
i
c
al
fo
reca
s
t
i
n
g
J
a
n
u
ar
y
1
,
2
0
2
1
-
O
c
t
o
b
er
1
0
,
2
0
2
2
A
RI
M
A
,
L
S
T
M,
A
RIM
A
-
L
S
T
M
,
S
V
R
,
p
ar
al
el
A
RI
M
A
-
L
S
T
M
p
ara
l
e
l
A
RIM
A
-
L
S
T
M
RMS
E
,
MA
PE
,
MS
E
,
MA
E
,
R
2
J
i
n
et
a
l
.
[
4
2
]
H
ea
l
t
h
care
a
n
d
med
i
c
al
fo
reca
s
t
i
n
g
A
p
ri
l
1
,
2
0
2
0
t
o
Marc
h
9
,
2
0
2
3
A
RI
M
A
,
L
S
T
M,
PS
O
-
L
S
T
M
-
A
RIM
A
,
M
L
R
-
L
S
T
M
-
A
RIM
A
a
n
d
BPN
N
-
L
ST
M
-
A
RI
M
A
BPN
N
-
L
ST
M
-
A
RI
M
A
MSE
,
RMS
E
,
MA
E
L
i
e
t
a
l
.
[
4
3
]
H
ea
l
t
h
care
a
n
d
med
i
c
al
fo
reca
s
t
i
n
g
J
a
n
u
ar
y
2
0
0
7
-
J
u
n
e
2
0
1
6
A
RI
M
A
,
A
RIM
A
-
G
R
N
N
A
RI
M
A
-
G
R
N
N
RMS
E
,
MA
E
,
MA
PE
,
ME
R
D
e
n
g
e
t
a
l
.
[4
4
]
H
ea
l
t
h
care
a
n
d
med
i
c
al
fo
reca
s
t
i
n
g
J
u
n
e
1
,
2
0
1
4
t
o
Feb
r
u
a
ry
1
7
,
2
0
1
9
A
RI
M
A
,
L
S
T
M,
A
RIM
A
-
L
S
T
M
A
RI
M
A
-
L
S
T
M
RMS
E
,
MA
E
,
M
A
P
E
X
u
e
t
a
l
.
[4
5
]
W
e
at
h
er
a
n
d
cl
i
ma
t
e
fo
reca
s
t
i
n
g
J
a
n
u
ar
y
1
9
8
0
-
D
ec
em
b
er
2
0
1
9
A
RI
M
A
,
SV
R,
L
ST
M,
A
RI
M
A
-
S
V
R
,
L
S
-
S
V
R,
A
RI
M
A
-
L
S
T
M
A
RI
M
A
-
L
S
T
M
MS
E
,
N
S
E
,
RMS
E
,
M
A
E
K
h
a
n
e
t
a
l
.
[4
6
]
W
e
at
h
er
a
n
d
cl
i
ma
t
e
fo
reca
s
t
i
n
g
J
a
n
u
ar
y
1
9
8
6
-
D
ec
em
b
er
2
0
1
6
A
RI
M
A
,
A
N
N
,
W
a
l
v
el
et
A
RI
M
A
-
A
N
N
W
a
l
v
e
l
et
A
RI
M
A
-
A
N
N
RMS
E
,
R
2
Z
h
a
o
e
t
a
l
.
[4
7
]
W
e
at
h
er
a
n
d
cl
i
ma
t
e
fo
reca
s
t
i
n
g
J
a
n
u
ar
y
1
9
7
3
-
D
ec
em
b
er
2
0
2
1
A
RI
M
A
,
L
S
T
M,
E
M
D
-
L
S
T
M
,
E
E
M
D
-
L
S
T
M
,
E
E
M
D
-
A
RI
M
A
,
E
E
MD
-
L
S
T
M
-
A
RIM
A
E
E
M
D
-
L
S
T
M
-
A
RI
M
A
MA
E
,
M
SE
,
RMS
E
,
R
2
Para
s
y
ri
s
e
t
a
l
.
[
4
8
]
W
e
at
h
er
a
n
d
cl
i
ma
t
e
fo
re
ca
s
t
i
n
g
2
d
a
y
s
L
S
T
M
,
S
A
R
IM
A
,
SA
R
IM
A
-
L
S
T
M
SA
R
IM
A
-
L
S
T
M
MA
E
Bel
ma
h
d
i
et
a
l
.
[
4
9
]
W
e
at
h
er
a
n
d
cl
i
ma
t
e
fo
re
ca
s
t
i
n
g
J
a
n
u
ar
y
1
,
2
0
1
5
-
D
ec
em
b
er
3
1
,
2
0
1
5
A
RI
M
A
,
A
RM
A
,
FFB
P,
A
RI
M
A
-
FF
BP,
A
RM
A
-
FFBP
A
RI
M
A
-
FF
BP
RMS
E
L
u
o
a
n
d
G
o
n
g
[
5
0
]
W
e
at
h
er
a
n
d
cl
i
ma
t
e
fo
re
ca
s
t
i
n
g
J
a
n
u
ar
y
1
,
2
0
1
5
-
Marc
h
1
,
2
0
2
2
A
RI
M
A
,
L
S
T
M,
A
RIM
A
-
L
S
T
M
,
W
O
A
-
L
S
T
M
,
CE
E
M
D
A
N
-
WOA
-
SL
T
M
,
A
RI
M
A
-
WOA
-
L
S
T
M
A
RI
M
A
-
WOA
-
L
S
T
M
RMS
E
a
n
d
R
2
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
4
,
No
.
4
,
Au
g
u
s
t 2
0
2
5
:
2
6
0
1
-
2
6
1
2
2610
4.
CO
NCLU
SI
O
N
T
h
e
s
y
s
tem
atic
r
ev
iew
ca
r
r
ied
o
u
t
f
o
r
th
is
p
ap
er
u
s
ed
th
e
PR
I
SMA
m
eth
o
d
o
lo
g
y
wh
er
e
we
f
o
llo
wed
its
m
ain
s
tep
s
f
r
o
m
th
e
f
o
r
m
u
latio
n
o
f
th
e
r
esear
ch
q
u
esti
o
n
s
to
th
e
in
ter
p
r
etatio
n
an
d
p
r
esen
tatio
n
o
f
th
e
r
esu
lts
.
Fo
u
r
d
atab
ases
wer
e
s
elec
ted
an
d
th
e
m
ain
k
ey
ter
m
s
o
n
w
h
ich
th
e
s
ea
r
ch
will
b
e
ca
r
r
ie
d
o
u
t
wer
e
d
ef
in
ed
.
T
h
e
ter
m
s
wer
e
ch
o
s
en
in
s
u
ch
a
way
as
to
av
o
id
wo
r
k
s
th
at
d
id
n
o
t
u
s
e
h
y
b
r
id
ap
p
licatio
n
s
o
r
th
at
th
e
h
y
b
r
id
izatio
n
was
n
o
t
b
etwe
en
s
tatis
tical
tech
n
iq
u
es
an
d
d
ee
p
lear
n
in
g
.
T
h
e
e
n
tire
wo
r
k
p
r
o
ce
s
s
f
r
o
m
d
o
wn
lo
ad
in
g
t
h
e
r
ef
er
en
ce
s
o
f
th
e
s
elec
ted
wo
r
k
s
to
th
e
s
cr
ee
n
in
g
p
r
o
ce
s
s
was
ca
r
r
ied
o
u
t
in
th
e
C
itav
i
p
r
o
g
r
a
m
.
Fo
llo
win
g
th
e
s
cr
e
en
in
g
p
r
o
ce
s
s
o
f
f
u
ll
-
tex
t
ar
ticles,
th
e
d
o
m
ain
s
we
wo
u
ld
f
o
cu
s
o
n
wer
e
id
en
tifie
d
b
ased
o
n
th
e
d
y
n
a
m
ics
o
f
th
e
s
tu
d
ies
we
h
ad
a
v
ailab
le.
Fo
u
r
wer
e
th
e
ca
teg
o
r
ies
o
f
d
o
m
ain
s
in
wh
ich
we
f
o
cu
s
ed
an
d
p
r
esen
t
ed
ea
ch
p
ap
er
in
d
i
v
id
u
ally
f
o
r
ea
ch
ca
teg
o
r
y
b
y
b
r
ief
ly
ex
p
l
ain
in
g
th
e
f
ield
o
f
p
r
ed
ictio
n
,
th
e
h
y
b
r
id
m
eth
o
d
o
lo
g
y
u
s
ed
,
t
h
e
s
ize
o
f
th
e
d
a
ta
o
b
tain
ed
in
th
e
s
tu
d
y
as
well
as
th
e
m
etr
ics
o
r
p
er
f
o
r
m
an
ce
ev
alu
atio
n
in
d
ic
ato
r
s
o
f
ea
ch
m
o
d
el
s
u
ch
as
R
MSE
,
MA
PE,
an
d
MSE
.
I
n
th
is
p
ap
er
,
th
e
m
ain
f
o
cu
s
was
o
n
h
y
b
r
id
m
eth
o
d
s
wh
er
e,
in
ad
d
itio
n
to
d
em
o
n
s
tr
atin
g
th
e
im
p
r
o
v
em
en
t
an
d
p
o
s
iti
v
e
im
p
ac
t
o
n
d
ec
is
io
n
-
m
ak
in
g
in
ar
ea
s
s
u
ch
as
f
in
an
ce
,
en
er
g
y
,
h
ea
lth
ca
r
e,
wea
th
er
an
d
clim
ate
f
o
r
ec
as
tin
g
,
we
id
en
tifie
d
th
o
s
e
m
eth
o
d
s
th
at
h
av
e
a
m
o
r
e
f
r
e
q
u
en
t
r
a
n
g
e
o
f
u
s
e
co
m
p
ar
ed
t
o
tr
ad
itio
n
al
m
eth
o
d
s
o
r
o
th
er
h
y
b
r
id
(
s
tatis
tica
l
an
d
d
ee
p
lear
n
in
g
)
m
eth
o
d
s
.
T
h
e
ch
ar
ac
ter
is
tics
o
f
th
e
s
tu
d
ies
wer
e
s
u
m
m
ar
ized
in
a
tab
le
wh
ich
h
elp
ed
u
s
in
co
n
clu
d
in
g
th
e
c
o
n
clu
s
io
n
s
.
Du
r
in
g
th
e
a
n
aly
s
is
,
it
wa
s
o
b
s
er
v
ed
th
at
m
o
s
t
o
f
th
e
p
ap
er
s
p
r
esen
t
a
h
y
b
r
id
a
p
p
r
o
ac
h
u
s
in
g
th
e
AR
I
MA
m
eth
o
d
in
co
m
b
in
ati
o
n
m
ain
ly
with
t
h
e
L
STM
m
e
th
o
d
.
AR
I
MA
is
th
e
s
tatis
t
ical
m
eth
o
d
th
at
p
r
ev
ail
s
in
8
0
%
o
f
th
e
wo
r
k
s
,
wh
ile
L
STM
in
6
0
%
o
f
th
em
.
W
e
also
id
en
tifie
d
th
e
m
eth
o
d
s
th
at
ar
e
u
s
ed
m
o
s
t
o
f
ten
f
o
r
ea
ch
d
o
m
ai
n
:
f
i
n
an
cial,
h
ea
lth
ca
r
e,
en
er
g
y
,
an
d
wea
th
er
f
o
r
ec
ast.
Ob
v
io
u
s
ly
,
we
ca
n
n
o
t
co
n
f
i
d
e
n
tly
s
ay
th
at
th
is
h
y
b
r
i
d
izatio
n
o
u
tp
e
r
f
o
r
m
s
all
o
th
er
m
eth
o
d
s
u
s
ed
b
ec
au
s
e
t
h
e
p
r
ed
ictio
n
r
esu
lts
r
ely
o
n
th
e
d
ata
we
u
s
e
i
n
a
s
p
ec
if
ic
m
o
d
el,
b
u
t
we
ar
e
b
asin
g
it
o
n
th
e
f
r
eq
u
e
n
cy
o
f
u
s
e
o
f
th
ese
m
eth
o
d
s
in
d
if
f
er
en
t
f
i
eld
s
b
y
h
ig
h
lig
h
tin
g
a
h
y
b
r
id
m
o
d
el
th
at
ca
n
b
e
g
e
n
er
aliz
ed
an
d
u
s
ed
in
all
m
en
tio
n
ed
d
o
m
ain
s
ab
o
v
e.
I
n
th
e
n
ea
r
f
u
t
u
r
e,
we
aim
to
d
o
a
d
ee
p
e
r
an
al
y
s
is
in
ea
ch
o
f
th
e
s
p
ec
if
ic
d
o
m
ain
s
b
y
an
aly
zin
g
a
wid
er
r
an
g
e
o
f
wo
r
k
s
an
d
h
i
g
h
lig
h
tin
g
f
o
r
ea
ch
d
o
m
ain
t
h
e
r
elev
an
t
s
u
b
ca
teg
o
r
ies
an
d
th
e
h
y
b
r
id
m
eth
o
d
s
th
ey
ap
p
ly
,
a
n
d
h
o
w
ef
f
ec
tiv
e
th
ey
ar
e
o
v
er
a
ll.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
Au
th
o
r
s
s
tate
n
o
f
u
n
d
in
g
in
v
o
lv
ed
.
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
tr
ib
u
to
r
R
o
les
T
ax
o
n
o
m
y
(
C
R
ed
iT)
to
r
ec
o
g
n
ize
in
d
iv
id
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
Ma
lv
in
a
Xh
ab
af
ti
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Vale
n
tin
a
Sin
aj
✓
✓
✓
✓
✓
✓
✓
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
mi
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
Data
av
ailab
ilit
y
is
n
o
t a
p
p
lica
b
le
to
th
is
p
ap
er
as n
o
n
ew
d
at
a
wer
e
cr
ea
ted
o
r
an
aly
ze
d
in
t
h
is
s
tu
d
y
.
RE
F
E
R
E
NC
E
S
[
1
]
R
.
M
u
c
a
j
a
n
d
V
.
S
i
n
a
j
,
“
Ex
c
h
a
n
g
e
r
a
t
e
f
o
r
e
c
a
st
i
n
g
u
si
n
g
A
R
I
M
A
,
N
A
R
a
n
d
A
R
I
M
A
-
A
N
N
h
y
b
r
i
d
m
o
d
e
l
,
”
J
o
u
rn
a
l
o
f
Mu
l
t
i
d
i
sc
i
p
l
i
n
a
ry
En
g
i
n
e
e
ri
n
g
S
c
i
e
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
(
J
ME
S
T
)
,
v
o
l
.
4
,
p
p
.
2
4
5
8
–
9
4
0
3
,
2
0
1
7
.
[
2
]
F
.
I
q
b
a
l
,
D
.
K
o
u
t
m
o
s,
E
.
A
.
A
h
m
e
d
,
a
n
d
L.
M
.
A
l
-
Essa,
“
A
n
o
v
e
l
h
y
b
r
i
d
d
e
e
p
l
e
a
r
n
i
n
g
met
h
o
d
f
o
r
a
c
c
u
r
a
t
e
e
x
c
h
a
n
g
e
r
a
t
e
p
r
e
d
i
c
t
i
o
n
,
”
R
i
sks
,
v
o
l
.
1
2
,
n
o
.
9
,
A
u
g
.
2
0
2
4
,
d
o
i
:
1
0
.
3
3
9
0
/
r
i
sk
s
1
2
0
9
0
1
3
9
.
Evaluation Warning : The document was created with Spire.PDF for Python.