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.
1
5
,
No
.
4
,
A
u
g
u
s
t 2
0
2
6
,
p
p
.
3
4
2
1
~
3
4
3
0
I
SS
N:
2
2
5
2
-
8
9
3
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijai.v
15
.i
4
.
p
p
3
4
2
1
-
3
4
3
0
3421
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
i
.
ia
esco
r
e.
co
m
Co
mputa
tiona
l f
r
a
mewo
rk f
o
r sma
rt
touris
m
ma
na
g
ement:
hy
brid t
ime
series
decom
po
sitio
n a
nd predi
ctive mo
deling
I
wa
n Ady
P
ra
bo
wo
1
,
H
endro
Wij
a
y
a
nto
1
,
T
eg
uh
Su
s
y
a
n
t
o
2
1
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
mat
i
c
s
,
F
a
c
u
l
t
y
o
f
En
g
i
n
e
e
r
i
n
g
,
U
n
i
v
e
r
si
t
a
s
Ti
g
a
S
e
r
a
n
g
k
a
i
,
S
u
r
a
k
a
r
t
a
,
I
n
d
o
n
e
si
a
2
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
mat
i
o
n
S
y
s
t
e
ms
,
F
a
c
u
l
t
y
o
f
E
n
g
i
n
e
e
r
i
n
g
,
U
n
i
v
e
r
si
t
a
s
T
i
g
a
S
e
r
a
n
g
k
a
i
,
S
u
r
a
k
a
r
t
a
,
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
Ma
r
2
8
,
2
0
2
5
R
ev
is
ed
Ma
y
2
0
,
2
0
2
6
Acc
ep
ted
J
u
n
1
9
,
2
0
2
6
S
m
a
rt
to
u
rism
m
a
n
a
g
e
m
e
n
t
i
n
ru
ra
l
m
u
lt
i
-
d
e
stin
a
ti
o
n
se
tt
in
g
s
re
q
u
ires
fo
re
c
a
stin
g
m
e
th
o
d
s
t
h
a
t
a
re
a
c
c
u
ra
te
e
n
o
u
g
h
to
su
p
p
o
rt
v
isit
o
r
a
ll
o
c
a
ti
o
n
,
in
fra
stru
c
tu
re
re
a
d
in
e
ss
,
a
n
d
e
c
o
lo
g
ica
l
p
r
o
tec
ti
o
n
.
Th
is
stu
d
y
p
re
se
n
ts
a
d
e
c
o
m
p
o
siti
o
n
-
b
a
se
d
f
o
re
c
a
stin
g
fra
m
e
wo
rk
fo
r
S
id
o
wa
y
a
h
Vill
a
g
e
,
Ce
n
tral
Ja
v
a
,
In
d
o
n
e
sia
,
wh
ich
in
te
g
ra
tes
th
re
e
a
tt
ra
c
ti
o
n
s
with
d
iffere
n
t
d
e
m
a
n
d
p
ro
fil
e
s:
Um
b
u
l
M
a
n
ten
,
S
i
b
lara
k
,
a
n
d
Ka
m
p
u
n
g
Do
lan
a
n
.
Us
i
n
g
m
o
n
th
ly
v
isit
a
ti
o
n
d
a
ta
fro
m
M
a
y
2
0
2
3
t
o
Ap
ril
2
0
2
4
,
t
h
e
stu
d
y
c
o
m
p
a
re
s
a
d
d
it
iv
e
a
n
d
m
u
lt
ip
li
c
a
ti
v
e
d
e
c
o
m
p
o
sit
io
n
m
o
d
e
ls
wit
h
in
a
c
o
m
m
o
n
w
o
rk
flo
w
o
f
d
a
ta
c
o
ll
e
c
ti
o
n
,
p
re
p
r
o
c
e
ss
in
g
,
tren
d
-
se
a
so
n
a
l
d
e
c
o
m
p
o
siti
o
n
,
m
o
d
e
l
e
v
a
lu
a
ti
o
n
,
a
n
d
su
sta
i
n
a
b
il
it
y
-
o
r
ien
ted
i
n
terp
re
tati
o
n
.
Th
e
c
o
n
tri
b
u
ti
o
n
o
f
t
h
e
stu
d
y
li
e
s
in
c
larify
i
n
g
d
e
stin
a
ti
o
n
-
sp
e
c
ifi
c
c
rit
e
ria
fo
r
se
lec
ti
n
g
a
d
d
it
i
v
e
v
e
rsu
s
m
u
lt
i
p
li
c
a
ti
v
e
m
o
d
e
ls,
i
m
p
ro
v
i
n
g
m
e
th
o
d
o
l
o
g
ica
l
tran
s
p
a
re
n
c
y
in
p
re
p
ro
c
e
ss
in
g
a
n
d
tem
p
o
ra
l
v
a
li
d
a
ti
o
n
,
a
n
d
tran
sla
ti
n
g
f
o
re
c
a
st
o
u
tp
u
ts
in
t
o
p
ra
c
ti
c
a
l
sm
a
rt
to
u
rism
a
c
ti
o
n
s
a
li
g
n
e
d
with
su
sta
i
n
a
b
le
d
e
v
e
l
o
p
m
e
n
t
g
o
a
ls
(
S
DG
s
)
1
1
a
n
d
1
2
.
Th
e
re
su
lt
s
sh
o
w
th
a
t
th
e
m
u
lt
i
p
li
c
a
ti
v
e
-
a
v
e
ra
g
e
a
ll
m
o
d
e
l
y
ield
s
th
e
l
o
we
st
m
e
a
n
a
b
so
lu
te
p
e
rc
e
n
tag
e
e
rro
r
(
M
AP
E
)
f
o
r
Um
b
u
l
M
a
n
ten
(
1
4
.
1
%
)
a
n
d
S
ib
lara
k
(5
6
.
8
%
),
w
h
il
e
th
e
a
d
d
it
iv
e
-
c
e
n
tere
d
m
o
v
in
g
a
v
e
ra
g
e
m
o
d
e
l
is
m
o
re
su
it
a
b
le
fo
r
Ka
m
p
u
n
g
Do
lan
a
n
b
a
se
d
o
n
m
e
a
n
a
b
so
lu
te
d
e
v
iati
o
n
(
M
AD
)
(1
6
2
.
6
).
Alt
h
o
u
g
h
th
e
1
2
-
m
o
n
t
h
d
a
ta
se
t
li
m
it
s
lo
n
g
-
term
g
e
n
e
ra
li
z
a
ti
o
n
,
th
e
fra
m
e
wo
rk
p
ro
v
id
e
s
a
re
p
ro
d
u
c
i
b
le
b
a
sis
fo
r
d
a
ta
-
in
fo
rm
e
d
to
u
rism
m
a
n
a
g
e
m
e
n
t
i
n
ru
ra
l
d
e
stin
a
ti
o
n
s.
K
ey
w
o
r
d
s
:
Pre
d
ictiv
e
an
aly
tics
R
u
r
al
to
u
r
is
m
f
o
r
ec
asti
n
g
Sm
ar
t to
u
r
is
m
Su
s
tain
ab
le
d
ev
elo
p
m
e
n
t g
o
al
s
T
im
e
-
s
er
ies d
ec
o
m
p
o
s
itio
n
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
I
wan
Ad
y
Pra
b
o
wo
Dep
ar
tm
en
t o
f
I
n
f
o
r
m
atics,
Facu
lty
o
f
E
n
g
in
ee
r
i
n
g
,
Un
i
v
er
s
itas
T
ig
a
Ser
an
g
k
ai
Su
r
ak
ar
ta,
C
en
tr
al
J
av
a,
I
n
d
o
n
esia
E
m
ail:
iwan
ad
y
p
@
ts
u
.
ac
.
id
1.
I
NT
RO
D
UCT
I
O
N
R
u
r
al
to
u
r
is
m
d
esti
n
atio
n
s
in
cr
ea
s
in
g
ly
r
eq
u
ir
e
e
v
id
en
ce
-
b
ased
m
an
ag
em
e
n
t
b
ec
au
s
e
v
is
ito
r
g
r
o
wth
,
en
v
ir
o
n
m
en
tal
ca
r
r
y
in
g
ca
p
a
city
,
an
d
l
o
ca
l
cu
ltu
r
al
ass
ets
m
u
s
t
b
e
b
alan
ce
d
with
in
a
s
in
g
le
g
o
v
er
n
an
ce
s
y
s
tem
[
1
]
,
[
2
]
.
T
h
is
ch
alle
n
g
e
b
ec
o
m
es
m
o
r
e
co
m
p
lex
wh
en
a
v
illag
e
m
a
n
ag
es
s
ev
er
al
attr
ac
tio
n
s
s
im
u
ltan
eo
u
s
ly
,
ea
ch
with
d
if
f
er
en
t
d
em
an
d
cy
cles,
v
is
ito
r
s
eg
m
en
ts
,
an
d
o
p
er
atio
n
al
co
n
s
tr
ain
ts
.
Sid
o
way
ah
Villag
e
in
C
en
tr
al
J
av
a,
I
n
d
o
n
esia,
illu
s
tr
ates
th
is
co
n
d
i
tio
n
th
r
o
u
g
h
an
in
te
g
r
ated
t
o
u
r
is
m
ec
o
s
y
s
tem
co
m
p
r
is
in
g
Um
b
u
l
Ma
n
ten
(
n
atu
r
al
s
p
r
in
g
to
u
r
is
m
)
,
Sib
lar
a
k
(
ec
o
t
o
u
r
is
m
an
d
f
esti
v
al
-
b
a
s
ed
v
is
itatio
n
)
,
an
d
Kam
p
u
n
g
D
o
lan
an
(
c
u
ltu
r
al
an
d
ed
u
ca
tio
n
al
to
u
r
is
m
)
.
T
h
ese
in
ter
co
n
n
ec
te
d
s
ites
f
o
r
m
an
in
te
g
r
ated
ec
o
s
y
s
tem
wh
er
e
v
is
ito
r
f
lo
w
s
an
d
r
eso
u
r
ce
d
em
a
n
d
s
ar
e
i
n
ter
d
ep
en
d
en
t.
Acc
u
r
ate
f
o
r
e
ca
s
tin
g
is
th
er
ef
o
r
e
ess
en
tial f
o
r
s
u
s
tain
ab
le
g
o
v
er
n
an
ce
[
2
]
–
[
4
]
.
Fo
r
ec
asti
n
g
m
eth
o
d
s
s
u
ch
as
au
to
r
eg
r
ess
iv
e
in
teg
r
ated
m
o
v
in
g
a
v
er
ag
e
(
AR
I
MA
)
,
s
ea
s
o
n
al
au
to
r
eg
r
ess
iv
e
in
teg
r
ated
m
o
v
in
g
a
v
er
ag
e
(
SAR
I
MA
)
,
an
d
lo
n
g
s
h
o
r
t
-
ter
m
m
em
o
r
y
(
L
STM
)
h
av
e
b
ee
n
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
5
,
No
.
4
,
Au
g
u
s
t 2
0
2
6
:
3
4
2
1
-
3
4
3
0
3422
wid
ely
u
s
ed
in
to
u
r
is
m
d
em
an
d
p
r
ed
ictio
n
[
5
]
–
[
8
]
.
Ho
w
ev
er
,
m
a
n
y
s
tu
d
ies
f
o
cu
s
o
n
u
r
b
a
n
d
esti
n
atio
n
s
,
air
p
o
r
ts
,
o
r
s
in
g
le
attr
ac
tio
n
s
with
lo
n
g
er
d
ata
h
is
to
r
ies
an
d
m
o
r
e
h
o
m
o
g
e
n
eo
u
s
s
ea
s
o
n
al
s
tr
u
ctu
r
es
[
9
]
,
[
1
0
]
.
I
n
r
u
r
al
clu
s
ter
ed
d
esti
n
atio
n
s
,
o
n
e
attr
ac
tio
n
m
ay
f
o
llo
w
r
elativ
ely
s
tab
le
h
o
lid
ay
-
b
ase
d
d
em
an
d
,
an
o
th
e
r
m
ay
d
ep
e
n
d
o
n
ev
en
t
-
d
r
iv
en
s
u
r
g
es,
wh
ile
an
o
th
er
m
a
y
f
l
u
ctu
ate
ac
co
r
d
i
n
g
to
s
ch
o
o
l
v
is
its
o
r
co
m
m
u
n
ity
p
r
o
g
r
a
m
s
.
Un
d
er
s
u
ch
co
n
d
itio
n
s
,
a
s
in
g
le
f
o
r
ec
asti
n
g
f
o
r
m
is
o
f
ten
in
s
u
f
f
icien
t
[
1
1
]
.
T
im
e
-
s
er
ies
d
ec
o
m
p
o
s
itio
n
r
em
ain
s
u
s
ef
u
l
b
ec
au
s
e
it
s
ep
ar
ates
tr
en
d
,
s
ea
s
o
n
al,
an
d
ir
r
eg
u
lar
c
o
m
p
o
n
en
ts
in
an
in
ter
p
r
etab
le
m
an
n
er
[
1
2
]
–
[
1
6
]
.
T
h
e
n
o
v
elty
o
f
th
is
s
tu
d
y
th
er
ef
o
r
e
lies
n
o
t
in
d
ec
o
m
p
o
s
it
io
n
its
elf
,
b
u
t
in
its
u
s
e
as
a
m
an
a
g
er
ial
d
ec
is
io
n
f
r
am
ewo
r
k
f
o
r
a
r
u
r
al
m
u
lti
-
a
ttra
ctio
n
to
u
r
is
m
s
y
s
tem
ch
ar
ac
ter
ized
b
y
lim
ited
d
ata,
d
esti
n
atio
n
-
s
p
ec
if
ic
v
o
latilit
y
,
an
d
ex
p
licit su
s
tain
ab
ilit
y
co
n
ce
r
n
s
.
T
h
e
m
a
in
c
o
n
t
r
i
b
u
ti
o
n
s
o
f
th
i
s
s
t
u
d
y
a
r
e
t
h
r
e
ef
o
l
d
:
f
i
r
s
t,
i
t
p
r
o
p
o
s
es
a
c
lea
r
e
r
h
y
b
r
i
d
d
ec
o
m
p
o
s
it
io
n
wo
r
k
f
l
o
w
f
o
r
h
e
te
r
o
g
en
e
o
u
s
r
u
r
al
m
u
l
ti
-
d
esti
n
a
ti
o
n
t
o
u
r
is
m
s
er
i
es.
Se
co
n
d
,
i
t e
x
p
l
ai
n
s
t
h
e
o
p
e
r
a
ti
o
n
al
r
atio
n
ale
f
o
r
s
elec
tin
g
ad
d
itiv
e
v
er
s
u
s
m
u
ltip
licativ
e
d
ec
o
m
p
o
s
itio
n
ac
co
r
d
in
g
to
d
esti
n
atio
n
b
eh
a
v
io
r
[
1
7
]
,
[
1
8
]
.
T
h
ir
d
,
it
tr
an
s
lates
f
o
r
ec
ast
o
u
tp
u
ts
i
n
to
p
r
ac
tical
s
m
ar
t
to
u
r
is
m
ac
tio
n
s
alig
n
ed
with
s
u
s
tain
ab
le
d
ev
elo
p
m
en
t
g
o
als
(
SDGs
)
1
1
an
d
1
2
[
1
9
]
,
[
2
0
]
.
2.
P
RO
P
O
SE
D
M
E
T
H
O
D
2
.
1
.
Study
a
re
a
a
nd
da
t
a
c
o
l
lect
io
n
T
h
is
s
tu
d
y
ex
am
in
es
to
u
r
is
t
v
is
itatio
n
d
y
n
am
ics
in
Sid
o
w
ay
ah
Villag
e,
C
en
tr
al
J
av
a,
I
n
d
o
n
esia
,
wh
ich
co
m
p
r
is
es
th
r
ee
co
m
p
lem
en
tar
y
attr
ac
tio
n
s
:
Um
b
u
l
Ma
n
ten
,
Sib
lar
ak
,
a
n
d
Kam
p
u
n
g
Do
lan
an
.
T
h
e
an
aly
s
is
u
s
es
m
o
n
th
ly
v
is
itatio
n
d
ata
f
r
o
m
Ma
y
2
0
2
3
to
Ap
r
il
2
0
2
4
o
b
tain
ed
f
r
o
m
lo
ca
l
to
u
r
is
m
ad
m
in
is
tr
ato
r
s
.
T
h
e
d
ataset
wa
s
o
r
g
an
ize
d
to
s
u
p
p
o
r
t
c
o
m
p
ar
ativ
e
f
o
r
ec
asti
n
g
ac
r
o
s
s
attr
ac
t
io
n
s
with
d
if
f
er
en
t
s
ea
s
o
n
al
an
d
v
o
latilit
y
p
r
o
f
iles
wh
ile
p
r
eser
v
in
g
th
e
ch
r
o
n
o
lo
g
y
r
eq
u
ir
ed
f
o
r
tim
e
-
s
er
ies m
o
d
elin
g
.
2
.
2
.
Da
t
a
prepro
ce
s
s
ing
A
s
tr
u
ctu
r
ed
p
r
e
p
r
o
ce
s
s
in
g
wo
r
k
f
lo
w
was
u
s
ed
to
im
p
r
o
v
e
c
o
n
s
is
ten
cy
b
e
f
o
r
e
d
ec
o
m
p
o
s
itio
n
.
Miss
in
g
o
b
s
er
v
atio
n
s
wer
e
co
m
p
leted
b
y
lin
ea
r
in
ter
p
o
latio
n
o
n
ly
wh
en
a
d
jace
n
t
v
alu
es
wer
e
av
ailab
le
[
2
1
]
.
Po
ten
tial
o
u
tlier
s
wer
e
id
en
tif
ied
u
s
in
g
th
e
in
ter
q
u
ar
tile
r
an
g
e
(
I
QR
)
r
u
le
an
d
,
wh
en
ju
d
g
ed
lik
ely
to
d
is
to
r
t
th
e
s
h
o
r
t
m
o
n
th
ly
s
er
ies,
we
r
e
r
ep
lace
d
u
s
in
g
a
c
o
n
s
er
v
a
tiv
e
m
ed
ian
-
b
ased
s
tr
ateg
y
[
2
2
]
.
Fo
r
Kam
p
u
n
g
Do
lan
an
,
t
h
e
Au
g
u
s
t o
u
tlier
(
1
8
v
is
ito
r
s
)
was
r
ep
lace
d
with
t
h
e
m
e
d
ian
(
5
7
0
)
,
ex
p
lain
i
n
g
its
n
o
r
m
alize
d
v
al
u
e
o
f
0
.
4
0
.
Min
-
m
ax
n
o
r
m
aliza
t
io
n
to
[
0
,
1
]
h
ar
m
o
n
ized
s
ca
l
e
v
ar
iatio
n
s
ac
r
o
s
s
d
esti
n
atio
n
s
[
2
3
]
,
[
2
4
]
.
T
h
is
d
ec
is
io
n
was
in
ten
d
ed
to
s
ta
b
ilize
d
ec
o
m
p
o
s
itio
n
r
ath
er
t
h
an
in
f
late
d
e
m
an
d
.
Vis
ito
r
co
u
n
ts
wer
e
th
en
n
o
r
m
alize
d
to
th
e
[
0
,
1
]
in
te
r
v
a
l
f
o
r
cr
o
s
s
-
d
esti
n
atio
n
co
m
p
a
r
is
o
n
,
d
aily
r
ec
o
r
d
s
wer
e
ag
g
r
e
g
ated
in
to
m
o
n
t
h
ly
to
tals
,
an
d
ch
r
o
n
o
lo
g
ical
o
r
d
er
was
p
r
eser
v
ed
in
YYYY
-
MM
f
o
r
m
at
[
2
5
]
,
[
2
6
]
.
Alter
n
ativ
e
im
p
u
tatio
n
s
ch
em
es we
r
e
n
o
t te
s
ted
in
th
e
cu
r
r
en
t stu
d
y
an
d
ar
e
th
e
r
ef
o
r
e
ac
k
n
o
wled
g
ed
as a
lim
itatio
n
.
2
.
3
.
H
y
brid
t
im
e
s
er
ies deco
m
po
s
it
io
n f
ra
m
ew
o
rk
T
o
s
u
p
p
o
r
t
f
o
r
ec
asti
n
g
in
a
h
eter
o
g
e
n
eo
u
s
r
u
r
al
t
o
u
r
is
m
s
ettin
g
,
th
is
s
tu
d
y
ap
p
lie
s
a
h
y
b
r
id
d
ec
o
m
p
o
s
itio
n
f
r
a
m
ewo
r
k
th
a
t
co
m
b
i
n
es
ad
d
itiv
e
an
d
m
u
ltip
licativ
e
f
o
r
m
u
latio
n
s
with
i
n
a
s
in
g
le
wo
r
k
f
lo
w.
T
h
e
aim
is
to
p
r
eser
v
e
in
ter
p
r
etab
ilit
y
wh
ile
allo
win
g
th
e
d
ec
o
m
p
o
s
itio
n
f
o
r
m
to
f
o
llo
w
th
e
o
b
s
er
v
e
d
b
eh
av
io
r
o
f
ea
c
h
d
esti
n
atio
n
.
Ad
d
itiv
e
d
ec
o
m
p
o
s
itio
n
was
ass
ig
n
ed
to
d
esti
n
atio
n
s
with
r
elativ
ely
s
tab
le
s
ea
s
o
n
al
am
p
litu
d
es,
wh
er
ea
s
m
u
ltip
licativ
e
d
ec
o
m
p
o
s
itio
n
was
u
s
ed
f
o
r
d
esti
n
atio
n
s
in
wh
ich
s
ea
s
o
n
al
ef
f
ec
ts
ap
p
ea
r
ed
p
r
o
p
o
r
tio
n
al
t
o
th
e
s
er
ies lev
el
[
2
7
]
–
[
3
0
]
,
as
d
ef
in
ed
i
n
(
1
)
.
=
+
+
(
1
)
Fo
r
ad
d
itiv
e
d
ec
o
m
p
o
s
itio
n
,
d
en
o
tes th
e
tr
en
d
co
m
p
o
n
en
t,
t
h
e
s
ea
s
o
n
al
co
m
p
o
n
en
t,
an
d
th
e
r
esid
u
al
co
m
p
o
n
en
t.
T
h
e
tr
en
d
was
esti
m
ated
u
s
in
g
a
ce
n
te
r
ed
m
o
v
in
g
a
v
er
ag
e
with
a
wi
n
d
o
w
s
ize
o
f
k
=3
,
wh
ile
th
e
s
ea
s
o
n
al
co
m
p
o
n
e
n
t
was
d
er
iv
ed
f
r
o
m
av
e
r
ag
e
m
o
n
th
ly
d
ev
iatio
n
s
.
C
o
n
v
e
r
s
ely
,
m
u
ltip
licativ
e
d
ec
o
m
p
o
s
itio
n
was
ap
p
lied
to
d
esti
n
atio
n
s
with
p
r
o
p
o
r
tio
n
al
s
ea
s
o
n
al
v
ar
iatio
n
,
esp
ec
ial
ly
Sib
lar
ak
,
wh
er
e
f
esti
v
al
p
er
io
d
s
c
r
ea
te
am
p
lifi
ed
d
em
a
n
d
s
p
ik
es
,
as
d
ef
i
n
ed
in
(
2
)
.
Un
d
er
th
is
f
o
r
m
u
latio
n
,
th
e
o
b
s
er
v
ed
s
er
ies
is
r
ep
r
esen
ted
as th
e
p
r
o
d
u
ct
o
f
th
e
tr
en
d
,
s
ea
s
o
n
al,
an
d
r
esid
u
al
co
m
p
o
n
en
ts
.
=
×
×
(
2
)
Fo
r
m
u
ltip
licativ
e
d
ec
o
m
p
o
s
itio
n
,
th
e
tr
en
d
was
also
esti
m
ated
u
s
in
g
a
ce
n
ter
ed
m
o
v
i
n
g
a
v
er
ag
e
with
k
=3
,
wh
ile
th
e
s
ea
s
o
n
a
l
f
ac
to
r
was
d
er
iv
ed
f
r
o
m
r
el
ativ
e
m
o
n
th
ly
r
atio
s
ar
o
u
n
d
th
e
esti
m
ated
tr
en
d
.
T
h
is
d
esti
n
atio
n
-
s
p
ec
if
ic
s
tr
ateg
y
im
p
r
o
v
es
p
r
ac
tical
in
ter
p
r
etab
ilit
y
f
o
r
to
u
r
is
m
m
an
ag
e
r
s
,
b
u
t
th
e
p
r
esen
t
s
tu
d
y
d
o
es
n
o
t
y
et
in
clu
d
e
f
o
r
m
al
s
tatis
tica
l
test
s
f
o
r
s
elec
t
in
g
d
ec
o
m
p
o
s
itio
n
ty
p
e.
Acc
o
r
d
in
g
ly
,
th
e
m
o
d
el
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
C
o
mp
u
ta
tio
n
a
l fra
mewo
r
k
fo
r
s
ma
r
t to
u
r
is
m
ma
n
a
g
eme
n
t:
h
yb
r
id
time
s
erie
s
…
(
I
w
a
n
A
d
y
P
r
a
b
o
w
o
)
3423
ch
o
ice
s
h
o
u
ld
b
e
u
n
d
er
s
to
o
d
as
an
em
p
ir
ical
d
ec
is
io
n
r
u
le
th
at
r
em
ain
s
o
p
en
to
r
ef
in
e
m
en
t
th
r
o
u
g
h
f
u
tu
r
e
s
ea
s
o
n
al
-
s
tr
en
g
th
an
d
lik
elih
o
o
d
-
b
ased
d
iag
n
o
s
tics
.
2
.
4
.
M
o
del
e
v
a
lua
t
i
o
n
Mo
d
el
p
e
r
f
o
r
m
an
ce
was
ev
alu
ated
u
s
in
g
m
ea
n
ab
s
o
lu
te
d
ev
i
atio
n
(
MA
D)
,
m
ea
n
ab
s
o
lu
te
p
er
ce
n
tag
e
er
r
o
r
(
MA
PE)
,
an
d
r
o
o
t
m
ea
n
s
q
u
ar
ed
er
r
o
r
(
R
MSE
)
.
T
h
ese
m
etr
ics
wer
e
s
elec
ted
b
ec
au
s
e
th
ey
jo
in
tly
d
escr
ib
e
ab
s
o
lu
te
d
ev
iatio
n
,
r
elativ
e
f
o
r
ec
asti
n
g
er
r
o
r
,
a
n
d
s
en
s
itiv
ity
to
lar
g
e
m
is
s
es.
M
AD
q
u
an
tifie
s
th
e
av
er
ag
e
ab
s
o
lu
te
d
ev
iatio
n
b
etwe
en
p
r
ed
icted
an
d
o
b
s
er
v
ed
v
alu
es,
p
r
o
v
id
i
n
g
a
d
ir
ec
t in
ter
p
r
etatio
n
o
f
ty
p
ical
f
o
r
ec
asti
n
g
er
r
o
r
,
as d
e
f
in
ed
i
n
(
3
)
.
=
1
∑
|
−
̃
|
−
1
(
3
)
MA
PE
ex
p
r
ess
es
f
o
r
ec
asti
n
g
er
r
o
r
in
p
er
ce
n
tag
e
te
r
m
s
,
en
ab
lin
g
co
m
p
ar
is
o
n
ac
r
o
s
s
d
esti
n
atio
n
s
with
d
if
f
er
en
t
v
is
itatio
n
s
ca
les
,
as d
ef
in
ed
in
(
4
)
.
=
1
∑
|
−
̃
|
=
1
×
10
(
4
)
R
MSE
ass
ig
n
s
g
r
ea
ter
weig
h
t
to
lar
g
e
er
r
o
r
s
a
n
d
is
th
er
ef
o
r
e
u
s
ef
u
l
f
o
r
id
en
tify
i
n
g
m
o
d
el
s
th
at
ar
e
s
en
s
itiv
e
to
s
h
ar
p
s
ea
s
o
n
al
s
h
o
ck
s
o
r
ir
r
eg
u
lar
d
em
a
n
d
s
p
ik
es
,
as d
e
f
in
ed
in
(
5
)
.
=
√
∑
(
yi
−
y
̂
)
2
N
i
=
1
(
5
)
T
o
g
eth
er
,
th
ese
m
etr
ics p
r
o
v
id
e
a
p
r
ac
tical
b
asis
f
o
r
m
o
d
el
c
o
m
p
ar
is
o
n
i
n
th
e
cu
r
r
en
t stu
d
y
.
2
.
5
.
M
o
del
v
a
lid
a
t
io
n
a
nd
ro
bu
s
t
nes
s
t
esting
T
o
ass
ess
g
en
er
aliza
b
ilit
y
with
in
th
e
lim
its
o
f
a
s
h
o
r
t
d
ataset,
tem
p
o
r
al
c
r
o
s
s
-
v
alid
atio
n
was
im
p
lem
en
ted
b
y
tr
ai
n
in
g
t
h
e
m
o
d
el
o
n
Ma
y
2
0
2
3
t
o
Dec
e
m
b
er
2
0
2
3
d
ata
a
n
d
e
v
alu
atin
g
it
o
n
J
an
u
ar
y
2
0
2
4
to
Ap
r
il
2
0
2
4
d
ata
[
3
1
]
.
R
esid
u
al
b
eh
av
io
r
was
th
en
r
ev
iewe
d
u
s
in
g
au
to
c
o
r
r
elati
o
n
f
u
n
ctio
n
/p
a
r
tial
au
to
co
r
r
elatio
n
f
u
n
ctio
n
(
AC
F
/PAC
F
)
in
s
p
ec
tio
n
an
d
L
ju
n
g
-
B
o
x
test
in
g
[
3
2
]
.
I
n
ad
d
itio
n
,
s
en
s
itiv
ity
an
aly
s
is
was
co
n
d
u
cted
b
y
v
ar
y
in
g
th
e
m
o
v
in
g
-
a
v
er
ag
e
win
d
o
w
s
ize
(
k
=3
,
5
,
an
d
7
)
to
ex
am
in
e
th
e
s
tab
ilit
y
o
f
th
e
d
ec
o
m
p
o
s
itio
n
r
esu
lts
.
2
.
6
.
I
nte
g
ra
t
io
n wit
h
s
m
a
rt
t
o
uris
m
s
us
t
a
ina
bil
it
y
g
o
a
ls
T
h
e
f
o
r
ec
asti
n
g
o
u
tp
u
ts
wer
e
in
ter
p
r
eted
as d
ec
is
io
n
-
s
u
p
p
o
r
t
in
p
u
ts
f
o
r
s
m
ar
t to
u
r
is
m
g
o
v
e
r
n
an
ce
.
I
n
p
r
ac
tical
ter
m
s
,
p
r
o
jecte
d
p
ea
k
s
ca
n
i
n
f
o
r
m
v
is
ito
r
r
ed
is
tr
ib
u
tio
n
,
tem
p
o
r
a
r
y
ca
p
ac
ity
c
o
n
t
r
o
l,
s
taf
f
allo
ca
tio
n
,
an
d
in
f
r
astru
ctu
r
e
r
ea
d
in
ess
.
I
n
ad
d
itio
n
,
f
o
r
ec
ast
-
in
f
o
r
m
e
d
o
f
f
-
p
ea
k
p
r
o
g
r
am
m
i
n
g
ca
n
s
u
p
p
o
r
t
m
o
r
e
e
v
en
d
em
an
d
d
is
tr
ib
u
tio
n
an
d
r
ed
u
ce
p
r
ess
u
r
e
o
n
en
v
ir
o
n
m
en
t
ally
s
en
s
itiv
e
o
r
o
p
er
atio
n
ally
co
n
s
tr
ain
ed
s
ites
.
T
h
r
o
u
g
h
th
is
in
ter
p
r
etatio
n
,
t
h
e
f
r
am
ewo
r
k
lin
k
s
p
r
ed
ictiv
e
an
aly
tics
with
s
u
s
tain
ab
ilit
y
-
o
r
ien
te
d
to
u
r
is
m
m
an
ag
em
en
t a
lig
n
ed
with
SD
Gs 1
1
an
d
1
2
s
h
o
ws in
Fig
u
r
e
1
.
Fig
u
r
e
1
.
W
o
r
k
f
lo
w
o
f
th
e
h
y
b
r
id
d
ec
o
m
p
o
s
itio
n
f
r
am
ewo
r
k
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
3
.
1
.
Study
a
re
a
,
da
t
a
co
llect
i
o
n,
a
nd
da
t
a
prepro
ce
s
s
ing
T
ab
le
1
a
n
d
Fig
u
r
e
2
s
u
m
m
ar
ize
th
e
m
o
n
th
ly
v
is
itatio
n
p
r
o
f
iles
o
f
th
e
t
h
r
ee
attr
ac
tio
n
s
an
d
t
h
e
p
r
ep
r
o
ce
s
s
in
g
o
u
tp
u
ts
u
s
ed
f
o
r
m
o
d
elin
g
.
Um
b
u
l
Ma
n
ten
a
n
d
Sib
lar
ak
s
h
o
w
clea
r
y
ea
r
-
en
d
in
cr
ea
s
es,
with
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
5
,
No
.
4
,
Au
g
u
s
t 2
0
2
6
:
3
4
2
1
-
3
4
3
0
3424
p
ea
k
v
alu
es
r
ec
o
r
d
ed
in
Dec
e
m
b
er
,
wh
ile
Kam
p
u
n
g
Do
lan
an
ex
h
ib
its
s
u
b
s
tan
tially
h
ig
h
er
m
o
n
th
-
to
-
m
o
n
th
in
s
tab
ilit
y
.
As
s
h
o
wn
in
T
ab
le
1
,
p
ea
k
v
is
itatio
n
o
cc
u
r
s
in
D
ec
em
b
er
at
Um
b
u
l
Ma
n
ten
(
3
2
,
6
4
4
v
is
ito
r
s
)
a
n
d
Sib
lar
ak
(
1
8
,
7
4
6
v
is
ito
r
s
)
.
Ka
m
p
u
n
g
Do
lan
an
e
x
h
ib
its
ex
tr
e
m
e
f
lu
ctu
atio
n
s
(
r
an
g
in
g
f
r
o
m
1
8
to
1
,
1
2
6
v
is
ito
r
s
m
o
n
th
ly
)
.
T
h
e
p
r
ep
r
o
c
ess
in
g
s
tep
s
in
clu
d
ed
lin
ea
r
in
ter
p
o
l
atio
n
f
o
r
m
is
s
in
g
v
alu
es
[
2
1
]
,
I
QR
-
b
ased
o
u
tlier
d
etec
tio
n
an
d
m
ed
ia
n
r
ep
lace
m
en
t
[
2
2
]
,
m
i
n
-
m
ax
n
o
r
m
aliz
atio
n
[
2
3
]
,
[
2
4
]
,
m
o
n
th
l
y
ag
g
r
eg
atio
n
[
2
5
]
,
[
2
6
]
,
an
d
ch
r
o
n
o
l
o
g
ical
alig
n
m
e
n
t
t
o
YYYY
-
MM
f
o
r
m
at
[
3
3
]
.
Fo
r
Kam
p
u
n
g
Do
lan
a
n
,
Au
g
u
s
t
o
u
tlier
(
1
8
v
is
ito
r
s
)
was
r
ep
lace
d
with
t
h
e
m
e
d
ian
o
f
5
7
0
,
wh
ich
ex
p
lain
s
its
n
o
r
m
alize
d
v
alu
e
o
f
0
.
4
0
.
T
h
e
p
r
ep
r
o
ce
s
s
in
g
s
tag
e
th
er
ef
o
r
e
s
er
v
ed
n
o
t
o
n
l
y
a
tech
n
ical
r
o
le
b
u
t
also
an
in
ter
p
r
etiv
e
o
n
e
b
y
m
ak
in
g
th
e
co
n
tr
ast
b
etwe
en
r
elativ
ely
s
tab
le
an
d
h
i
g
h
ly
v
o
latile
d
esti
n
atio
n
s
m
o
r
e
v
is
ib
le
b
ef
o
r
e
d
ec
o
m
p
o
s
itio
n
was a
p
p
lied
.
T
a
b
l
e
1
.
T
o
u
r
i
s
t
v
is
it
s
a
n
d
d
a
ta
p
r
e
p
r
o
c
e
s
s
i
n
g
M
o
n
t
h
To
u
r
i
st
v
i
si
t
s
P
r
e
p
r
o
c
e
ss
e
d
t
o
u
r
i
st
v
i
si
t
s
U
mb
u
l
M
a
n
t
e
n
S
i
b
l
a
r
a
k
K
a
m
p
u
n
g
D
o
l
a
n
a
n
U
mb
u
l
M
a
n
t
e
n
(
n
o
r
ma
l
i
z
e
d
)
S
i
b
l
a
r
a
k
(
n
o
r
ma
l
i
z
e
d
)
K
a
m
p
u
n
g
D
o
l
a
n
a
n
(
n
o
r
ma
l
i
z
e
d
)
M
a
y
1
2
,
0
0
0
3
,
0
0
0
8
3
2
0
.
0
0
0
.
0
3
0
.
7
1
Ju
n
e
2
0
,
4
1
2
7
,
1
6
6
1
,
1
1
0
0
.
4
1
0
.
2
9
1
.
0
0
Ju
l
y
2
2
,
1
9
9
6
,
5
4
7
5
1
4
0
.
5
0
0
.
2
5
0
.
4
0
A
u
g
u
st
2
0
,
1
7
6
2
,
4
6
8
18
(
5
7
0
)
0
.
4
0
0
.
0
0
0
.
4
0
S
e
p
t
e
m
b
e
r
1
9
,
1
7
3
6
,
0
6
4
7
0
0
0
.
3
5
0
.
2
2
0
.
5
8
O
c
t
o
b
e
r
2
0
,
3
6
1
9
,
6
8
8
5
6
2
0
.
4
1
0
.
4
4
0
.
4
4
N
o
v
e
mb
e
r
2
1
,
0
9
4
9
,
6
3
3
1
,
1
2
6
0
.
4
4
0
.
4
4
1
.
0
0
D
e
c
e
m
b
e
r
3
2
,
6
4
4
1
8
,
7
4
6
9
1
2
1
.
0
0
1
.
0
0
0
.
7
9
Jan
u
a
r
y
2
4
,
9
2
1
6
,
5
1
3
4
1
2
0
.
6
3
0
.
2
5
0
.
3
0
F
e
b
r
u
a
r
y
1
2
,
7
3
2
4
,
3
5
8
5
7
0
0
.
0
4
0
.
1
2
0
.
4
5
M
a
r
c
h
1
8
,
6
3
5
4
,
5
0
7
4
0
6
0
.
3
2
0
.
1
3
0
.
2
9
A
p
r
i
l
1
9
,
9
1
8
3
,
1
2
5
1
1
3
0
.
3
8
0
.
0
4
0
.
0
0
3
.
2
.
Vis
ua
l
o
v
er
v
iew
o
f
des
t
ina
t
io
n v
is
it
a
t
io
n dy
na
m
ics
Fig
u
r
e
2
p
r
o
v
id
es
a
c
o
m
p
ac
t
v
is
u
al
o
v
er
v
iew
o
f
th
e
m
o
n
th
ly
v
is
itatio
n
d
y
n
am
ics
b
ef
o
r
e
f
u
ll
d
ec
o
m
p
o
s
itio
n
is
ex
am
in
ed
.
T
wo
p
atter
n
s
ar
e
im
m
ed
iatel
y
v
is
ib
le:
f
ir
s
t,
Um
b
u
l
Ma
n
ten
an
d
Sib
lar
ak
b
o
th
s
h
o
w
clea
r
in
cr
ea
s
es
to
war
d
t
h
e
y
ea
r
-
e
n
d
h
o
lid
ay
p
er
io
d
.
S
ec
o
n
d
,
Kam
p
u
n
g
Do
lan
an
f
o
l
lo
ws
a
m
o
r
e
er
r
atic
p
ath
,
with
ab
r
u
p
t
s
h
if
ts
th
at
ar
e
less
ea
s
ily
ex
p
lain
ed
b
y
s
im
p
le
s
ea
s
o
n
al
r
eg
u
lar
ity
.
T
h
is
co
n
tr
ast
s
u
p
p
o
r
ts
th
e
s
u
b
s
eq
u
en
t u
s
e
o
f
d
esti
n
atio
n
-
s
p
ec
if
ic
d
ec
o
m
p
o
s
itio
n
lo
g
ic.
Fig
u
r
e
2
.
Mo
n
th
ly
v
is
itatio
n
p
r
o
f
iles
ac
r
o
s
s
th
e
th
r
ee
d
esti
n
a
tio
n
s
3
.
3
.
H
y
brid
t
im
e
s
er
ies deco
m
po
s
it
io
n f
ra
m
ew
o
rk
T
h
is
s
tu
d
y
p
r
esen
ts
a
h
y
b
r
id
tim
e
-
s
er
ies
d
ec
o
m
p
o
s
itio
n
f
r
am
ewo
r
k
th
at
in
teg
r
ates
ad
d
itiv
e
an
d
m
u
ltip
licativ
e
m
o
d
els
to
ca
p
tu
r
e
d
iv
er
s
e
s
ea
s
o
n
al
a
n
d
tr
en
d
b
e
h
av
io
r
s
ac
r
o
s
s
to
u
r
is
m
d
esti
n
atio
n
s
with
h
eter
o
g
en
e
o
u
s
d
em
a
n
d
c
h
ar
a
cter
is
tics
[
2
7
]
.
Ad
d
itiv
e
d
ec
o
m
p
o
s
itio
n
m
o
d
els
ab
s
o
lu
te
s
ea
s
o
n
al
f
lu
ctu
atio
n
s
ar
o
u
n
d
a
s
tab
le
m
ea
n
.
Mu
l
tip
licativ
e
d
ec
o
m
p
o
s
itio
n
ca
p
tu
r
es
p
r
o
p
o
r
tio
n
al
v
ar
iatio
n
s
th
at
s
ca
le
with
d
em
an
d
le
v
els.
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
C
o
mp
u
ta
tio
n
a
l fra
mewo
r
k
fo
r
s
ma
r
t to
u
r
is
m
ma
n
a
g
eme
n
t:
h
yb
r
id
time
s
erie
s
…
(
I
w
a
n
A
d
y
P
r
a
b
o
w
o
)
3425
3
.
3
.
1
.
Dec
o
m
po
s
ed
t
o
uris
t
v
i
s
it
s
f
o
r
Um
bu
l Ma
nte
n
T
ab
le
2
p
r
esen
ts
th
e
in
-
s
am
p
le
d
ec
o
m
p
o
s
itio
n
f
o
r
Um
b
u
l
Ma
n
ten
,
wh
ich
r
ep
r
esen
ts
r
elativ
ely
s
tab
le
n
atu
r
al
to
u
r
is
m
.
T
h
e
ad
d
itiv
e
-
ce
n
ter
e
d
m
o
v
in
g
av
er
ag
e
(
MA
)
r
ev
ea
ls
s
h
o
r
t
-
ter
m
tr
en
d
d
y
n
a
m
ics
(
r
an
g
in
g
f
r
o
m
1
7
,
0
9
5
to
2
6
,
2
2
0
v
is
ito
r
s
)
.
T
h
e
ad
d
itiv
e
-
a
v
er
ag
e
all
ap
p
r
o
ac
h
(
with
a
m
ea
n
o
f
μ
=2
0
,
3
5
5
)
h
ig
h
lig
h
ts
ab
s
o
lu
te
s
ea
s
o
n
al
d
ev
iatio
n
s
:
a
Dec
em
b
er
p
ea
k
(
+1
2
,
2
8
9
v
is
ito
r
s
)
an
d
a
Feb
r
u
ar
y
tr
o
u
g
h
(
−7
,
6
2
3
v
is
ito
r
s
)
.
T
h
e
m
u
ltip
l
icativ
e
-
av
er
ag
e
all
m
o
d
el
ca
p
t
u
r
es
p
r
o
p
o
r
tio
n
al
v
a
r
iatio
n
s
:
a
1
.
6
0
×
in
cr
ea
s
e
in
Dec
em
b
er
an
d
0
.
6
3
×
d
ec
r
ea
s
e
in
Feb
r
u
ar
y
.
T
h
ese
f
in
d
in
g
s
ar
e
co
n
s
is
ten
t
with
p
r
io
r
s
tu
d
i
es
o
n
m
u
ltip
licativ
e
d
ec
o
m
p
o
s
itio
n
f
o
r
p
r
o
p
o
r
tio
n
al
s
ea
s
o
n
al
ef
f
ec
ts
.
T
h
e
r
esu
lts
s
u
p
p
o
r
t
s
ea
s
o
n
al
r
eso
u
r
ce
p
l
an
n
in
g
f
o
r
s
taf
f
in
g
an
d
f
ac
ilit
y
ca
p
ac
ity
.
T
ab
le
2
.
Dec
o
m
p
o
s
ed
to
u
r
is
t v
is
its
f
o
r
Um
b
u
l M
an
ten
M
o
n
t
h
A
d
d
i
t
i
v
e
-
c
e
n
t
e
r
e
d
M
A
A
d
d
i
t
i
v
e
-
a
v
e
r
a
g
e
a
ll
M
u
l
t
i
p
l
i
c
a
t
i
v
e
-
c
e
n
t
e
r
e
d
MA
M
u
l
t
i
p
l
i
c
a
t
i
v
e
-
a
v
e
r
a
g
e
a
ll
S
e
a
so
n
a
l
R
e
si
d
u
a
l
Tr
e
n
d
S
e
a
so
n
a
l
R
e
si
d
u
a
l
Tr
e
n
d
S
e
a
so
n
a
l
R
e
si
d
u
a
l
Tr
e
n
d
S
e
a
so
n
a
l
R
e
si
d
u
a
l
Tr
e
n
d
M
a
y
-
8
,
3
5
5
-
-
-
-
2
0
,
3
5
5
0
.
5
9
-
-
-
-
2
0
,
3
5
5
Ju
n
57
0
1
8
,
2
0
4
1
.
1
2
1
.
0
0
2
0
,
3
5
5
1
.
0
0
1
.
0
0
1
8
,
2
0
4
2
,
2
0
8
0
2
0
,
3
5
5
Ju
l
1
,
8
4
4
0
2
0
,
9
6
1
1
.
0
6
1
.
0
0
2
0
,
3
5
5
1
.
0
9
1
.
0
0
2
0
,
9
6
1
1
,
2
3
8
0
2
0
,
3
5
5
A
u
g
-
1
7
9
0
2
0
,
5
1
6
0
.
9
8
1
.
0
0
2
0
,
3
5
5
0
.
9
9
1
.
0
0
2
0
,
5
1
6
-
3
4
0
0
2
0
,
3
5
5
S
e
p
-
1
,
1
8
2
0
1
9
,
9
0
3
0
.
9
6
1
.
0
0
2
0
,
3
5
5
0
.
9
4
1
.
0
0
1
9
,
9
0
3
-
7
3
0
0
2
0
,
3
5
5
O
c
t
6
0
2
0
,
2
0
9
1
.
0
1
1
.
0
0
2
0
,
3
5
5
1
.
0
0
1
.
0
0
2
0
,
2
0
9
1
5
2
0
2
0
,
3
5
5
N
o
v
7
3
9
0
2
4
,
7
0
0
0
.
8
5
1
.
0
0
2
0
,
3
5
5
1
.
0
4
1
.
0
0
2
4
,
7
0
0
-
3
,
6
0
6
0
2
0
,
3
5
5
D
e
c
1
2
,
2
8
9
0
2
6
,
2
2
0
1
.
2
5
1
.
0
0
2
0
,
3
5
5
1
.
6
0
1
.
0
0
2
6
,
2
2
0
6
,
4
2
4
0
2
0
,
3
5
5
Jan
4
,
5
6
6
0
2
3
,
4
3
2
1
.
0
6
1
.
0
0
2
0
,
3
5
5
1
.
2
2
1
.
0
0
2
3
,
4
3
2
1
,
4
8
9
0
2
0
,
3
5
5
F
e
b
-
7
,
6
2
3
0
1
8
,
7
6
3
0
.
6
8
1
.
0
0
2
0
,
3
5
5
0
.
6
3
1
.
0
0
1
8
,
7
6
3
-
6
,
0
3
1
0
2
0
,
3
5
5
M
a
r
-
1
,
7
2
0
0
1
7
,
0
9
5
1
.
0
9
1
.
0
0
2
0
,
3
5
5
0
.
9
2
1
.
0
0
1
7
,
0
9
5
1
,
5
4
0
0
2
0
,
3
5
5
A
p
r
-
4
3
7
0
-
-
-
2
0
,
3
5
5
0
.
9
8
1
.
0
0
-
-
-
2
0
,
3
5
5
3
.
3
.
2
.
Dec
o
m
po
s
ed
t
o
uris
t
v
i
s
it
s
f
o
r
Sib
la
ra
k
T
ab
le
3
p
r
esen
ts
th
e
d
ec
o
m
p
o
s
itio
n
f
o
r
Sib
lar
ak
,
wh
ich
is
ch
ar
ac
ter
ized
b
y
ev
e
n
t
-
d
r
i
v
en
e
co
to
u
r
is
m
with
h
ig
h
e
r
v
o
latilit
y
.
Ad
d
itiv
e
ap
p
r
o
ac
h
es
ca
p
tu
r
e
ab
s
o
lu
te
d
ev
iatio
n
s
:
an
Au
g
u
s
t
d
ec
lin
e
(
−4
,
3
5
0
v
is
ito
r
s
)
an
d
a
Dec
em
b
er
p
ea
k
(
+1
1
,
9
2
8
v
is
ito
r
s
)
.
M
u
ltip
licativ
e
m
o
d
els
b
etter
r
ep
r
esen
t
p
r
o
p
o
r
tio
n
a
l
d
em
an
d
f
lu
ctu
atio
n
s
.
Dec
e
m
b
er
r
ea
ch
es
2
.
7
5
×
th
e
a
n
n
u
al
m
ea
n
,
in
d
icatin
g
th
at
t
h
e
im
p
a
ct
o
f
f
esti
v
als
s
ca
les
with
th
e
d
esti
n
atio
n
'
s
p
o
p
u
l
ar
ity
.
T
h
e
m
u
ltip
licativ
e
-
ce
n
ter
ed
MA
m
o
d
el
r
e
v
ea
ls
lo
ca
l
tr
en
d
d
y
n
a
m
ics
(
r
an
g
in
g
f
r
o
m
3
,
9
9
7
to
1
2
,
6
8
9
v
is
ito
r
s
)
th
at
g
lo
b
al
av
er
a
g
in
g
s
m
o
o
th
s
o
v
er
.
T
h
ese
f
in
d
in
g
s
s
u
g
g
est
th
at
m
u
ltip
licativ
e
d
ec
o
m
p
o
s
itio
n
is
m
o
r
e
s
u
itab
le
f
o
r
m
an
a
g
in
g
f
esti
v
al
-
d
r
iv
e
n
d
e
m
an
d
s
u
r
g
e
s
.
Ad
d
itiv
e
m
o
d
els
in
f
o
r
m
l
o
w
-
s
ea
s
o
n
m
itig
atio
n
s
tr
ateg
ies.
T
ab
le
3
.
Dec
o
m
p
o
s
ed
to
u
r
is
t v
is
its
f
o
r
Sib
lar
ak
M
o
n
t
h
A
d
d
i
t
i
v
e
-
c
e
n
t
e
r
e
d
M
A
A
d
d
i
t
i
v
e
-
a
v
e
r
a
g
e
a
ll
M
u
l
t
i
p
l
i
c
a
t
i
v
e
-
c
e
n
t
e
r
e
d
MA
M
u
l
t
i
p
l
i
c
a
t
i
v
e
-
a
v
e
r
a
g
e
a
ll
S
e
a
so
n
a
l
R
e
si
d
u
a
l
Tr
e
n
d
S
e
a
so
n
a
l
R
e
si
d
u
a
l
Tr
e
n
d
S
e
a
so
n
a
l
R
e
si
d
u
a
l
Tr
e
n
d
S
e
a
so
n
a
l
R
e
si
d
u
a
l
Tr
e
n
d
M
a
y
-
3
,
8
1
8
0
-
-
-
6
,
8
1
8
0
.
4
4
1
.
0
0
-
-
-
6
,
8
1
8
Ju
n
3
4
8
0
5
,
5
7
1
1
.
2
9
1
.
0
0
6
,
8
1
8
1
.
0
5
1
.
0
0
5
,
5
7
1
1
,
5
9
5
0
6
,
8
1
8
Ju
l
-
2
7
1
0
5
,
3
9
4
1
.
2
1
1
.
0
0
6
,
8
1
8
0
.
9
6
1
.
0
0
5
,
3
9
4
1
,
1
5
3
0
6
,
8
1
8
A
u
g
-
4
,
3
5
0
0
5
,
0
2
6
0
.
4
9
1
.
0
0
6
,
8
1
8
0
.
3
6
1
.
0
0
5
,
0
2
6
-
2
,
5
5
8
0
6
,
8
1
8
S
e
p
-
7
5
4
0
6
,
0
7
3
1
.
0
0
1
.
0
0
6
,
8
1
8
0
.
8
9
1
.
0
0
6
,
0
7
3
-
9
0
6
,
8
1
8
O
c
t
2
,
8
7
0
0
8
,
4
6
2
1
.
1
5
1
.
0
0
6
,
8
1
8
1
.
4
2
1
.
0
0
8
,
4
6
2
1
,
2
2
6
0
6
,
8
1
8
N
o
v
2
,
8
1
5
0
1
2
,
6
8
9
0
.
7
6
1
.
0
0
6
,
8
1
8
1
.
4
1
1
.
0
0
1
2
,
6
8
9
-
3
,
0
5
6
0
6
,
8
1
8
D
e
c
1
1
,
9
2
8
0
1
1
,
6
3
1
1
.
6
1
1
.
0
0
6
,
8
1
8
2
.
7
5
1
.
0
0
1
1
,
6
3
1
7
,
1
1
5
0
6
,
8
1
8
Jan
-
3
0
5
0
9
,
8
7
2
0
.
6
6
1
.
0
0
6
,
8
1
8
0
.
9
6
1
.
0
0
9
,
8
7
2
-
3
,
3
5
9
0
6
,
8
1
8
F
e
b
-
2
,
4
6
0
0
5
,
1
2
6
0
.
8
5
1
.
0
0
6
,
8
1
8
0
.
6
4
1
.
0
0
5
,
1
2
6
-
7
6
8
0
6
,
8
1
8
M
a
r
-
2
,
3
1
1
0
3
,
9
9
7
1
.
1
3
1
.
0
0
6
,
8
1
8
0
.
6
6
1
.
0
0
3
,
9
9
7
5
1
0
0
6
,
8
1
8
A
p
r
-
3
,
6
9
3
0
-
-
-
6
,
8
1
8
0
.
4
6
1
.
0
0
-
-
-
6
,
8
1
8
3
.
3
.
3
.
Dec
o
m
po
s
ed
t
o
uris
t
v
i
s
it
s
f
o
r
K
a
m
pu
ng
Do
la
na
n
T
ab
le
4
p
r
esen
ts
th
e
d
ec
o
m
p
o
s
itio
n
f
o
r
Kam
p
u
n
g
Do
lan
an
,
wh
ich
ex
h
ib
its
ex
tr
em
e
v
o
latil
ity
d
u
e
to
its
d
ep
en
d
e
n
ce
o
n
s
ch
o
o
l
ac
ti
v
ities
an
d
c
u
ltu
r
al
e
v
en
ts
.
T
h
e
ad
d
itiv
e
-
ce
n
ter
ed
MA
m
o
d
el
ca
p
tu
r
es
s
h
o
r
t
-
ter
m
ab
s
o
lu
te
f
lu
ctu
atio
n
s
.
T
h
e
tr
en
d
p
ea
k
s
at
8
6
6
.
6
7
v
is
ito
r
s
(
in
No
v
em
b
e
r
)
a
n
d
d
ec
lin
es
to
3
6
3
.
0
0
v
is
ito
r
s
(
in
Ma
r
ch
)
.
Mu
ltip
licativ
e
m
o
d
els
r
ev
ea
l
d
r
am
atic
p
r
o
p
o
r
t
io
n
al
co
n
tr
asts
.
No
v
e
m
b
er
r
e
ac
h
es
1
.
7
3
9
×
t
h
e
an
n
u
al
m
ea
n
,
wh
ile
Ap
r
il
p
l
u
m
m
ets
to
0
.
1
7
5
×
th
e
m
ea
n
a
te
n
f
o
ld
d
if
f
e
r
en
ce
.
T
h
is
r
ef
lects
th
e
s
tr
o
n
g
s
ea
s
o
n
al
co
n
ce
n
tr
atio
n
th
at
is
ty
p
ical
o
f
ed
u
ca
tio
n
al
to
u
r
is
m
.
Mu
ltip
licativ
e
d
ec
o
m
p
o
s
it
io
n
b
etter
ca
p
tu
r
es
p
ea
k
-
p
e
r
io
d
in
te
n
s
ity
.
Ad
d
itiv
e
m
o
d
els cla
r
if
y
lo
w
-
s
ea
s
o
n
a
b
s
o
lu
te
m
ag
n
itu
d
es f
o
r
tar
g
ete
d
p
r
o
g
r
am
m
i
n
g
.
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
5
,
No
.
4
,
Au
g
u
s
t 2
0
2
6
:
3
4
2
1
-
3
4
3
0
3426
T
ab
le
4
.
Dec
o
m
p
o
s
ed
to
u
r
is
t v
is
its
f
o
r
Kam
p
u
n
g
Do
lan
an
M
o
n
t
h
A
c
t
A
d
d
i
t
i
v
e
-
c
e
n
t
e
r
e
d
M
A
A
d
d
i
t
i
v
e
-
a
v
e
r
a
g
e
a
ll
M
u
l
t
i
p
l
i
c
a
t
i
v
e
-
c
e
n
t
e
r
e
d
MA
M
u
l
t
i
p
l
i
c
a
t
i
v
e
-
a
v
e
r
a
g
e
a
ll
S
e
a
so
n
a
l
R
e
si
d
u
a
l
Tr
e
n
d
S
e
a
so
n
a
l
R
e
si
d
u
a
l
Tr
e
n
d
S
e
a
so
n
a
l
R
e
si
d
u
a
l
Tr
e
n
d
S
e
a
so
n
a
l
R
e
si
d
u
a
l
Tr
e
n
d
M
a
y
8
3
2
-
3
,
8
1
8
0
-
-
-
6
,
8
1
8
0
.
4
4
1
.
0
0
-
-
-
6
,
8
1
8
Ju
n
1
,
1
1
0
3
4
8
0
5
,
5
7
1
1
.
2
9
1
.
0
0
6
,
8
1
8
1
.
0
5
1
.
0
0
5
,
5
7
1
1
,
5
9
5
0
6
,
8
1
8
Ju
l
5
1
4
-
2
7
1
0
5
,
3
9
4
1
.
2
1
1
.
0
0
6
,
8
1
8
0
.
9
6
1
.
0
0
5
,
3
9
4
1
,
1
5
3
0
6
,
8
1
8
A
u
g
5
1
4
-
4
,
3
5
0
0
5
,
0
2
6
0
.
4
9
1
.
0
0
6
,
8
1
8
0
.
3
6
1
.
0
0
5
,
0
2
6
-
2
,
5
5
8
0
6
,
8
1
8
S
e
p
7
0
0
-
7
5
4
0
6
,
0
7
3
1
.
0
0
1
.
0
0
6
,
8
1
8
0
.
8
9
1
.
0
0
6
,
0
7
3
-
9
0
6
,
8
1
8
O
c
t
5
6
2
2
,
8
7
0
0
8
,
4
6
2
1
.
1
5
1
.
0
0
6
,
8
1
8
1
.
4
2
1
.
0
0
8
,
4
6
2
1
,
2
2
6
0
6
,
8
1
8
N
o
v
1
,
1
2
6
2
,
8
1
5
0
1
2
,
6
8
9
0
.
7
6
1
.
0
0
6
,
8
1
8
1
.
4
1
1
.
0
0
1
2
,
6
8
9
-
3
,
0
5
6
0
6
,
8
1
8
D
e
c
9
1
2
1
1
,
9
2
8
0
1
1
,
6
3
1
1
.
6
1
1
.
0
0
6
,
8
1
8
2
.
7
5
1
.
0
0
1
1
,
6
3
1
7
,
1
1
5
0
6
,
8
1
8
Jan
4
1
2
-
3
0
5
0
9
,
8
7
2
0
.
6
6
1
.
0
0
6
,
8
1
8
0
.
9
6
1
.
0
0
9
,
8
7
2
-
3
,
3
5
9
0
6
,
8
1
8
F
e
b
5
7
0
-
2
,
4
6
0
0
5
,
1
2
6
0
.
8
5
1
.
0
0
6
,
8
1
8
0
.
6
4
1
.
0
0
5
,
1
2
6
-
7
6
8
0
6
,
8
1
8
M
a
r
4
0
6
-
2
,
3
1
1
0
3
,
9
9
7
1
.
1
3
1
.
0
0
6
,
8
1
8
0
.
6
6
1
.
0
0
3
,
9
9
7
5
1
0
0
6
,
8
1
8
A
p
r
1
1
3
-
3
,
6
9
3
0
-
-
-
6
,
8
1
8
0
.
4
6
1
.
0
0
-
-
-
6
,
8
1
8
3
.
4
.
M
o
del
ev
a
lua
t
i
o
n f
o
r
U
m
bu
l Ma
nte
n,
Sib
la
ra
k
,
a
nd
K
a
m
pu
ng
Do
la
na
n
T
ab
le
5
an
d
Fig
u
r
e
3
co
m
p
ar
e
th
e
f
o
r
ec
asti
n
g
p
er
f
o
r
m
an
ce
o
f
th
e
f
o
u
r
d
ec
o
m
p
o
s
itio
n
co
n
f
ig
u
r
atio
n
s
u
s
in
g
MA
D,
MA
PE,
an
d
R
M
SE.
Fig
u
r
e
3
m
ak
es
it
ea
s
ier
t
o
d
is
tin
g
u
is
h
s
tab
le
f
r
o
m
u
n
s
t
ab
le
d
esti
n
atio
n
s
b
y
s
h
o
win
g
th
e
r
elativ
e
er
r
o
r
p
r
o
f
ile
ac
r
o
s
s
m
o
d
els.
T
h
e
r
esu
lt
s
s
h
o
w
th
at
th
e
m
u
ltip
licativ
e
-
av
er
ag
e
all
m
o
d
el
ac
h
iev
es
th
e
lo
west
MA
PE
f
o
r
Um
b
u
l
Ma
n
ten
(
1
4
.
1
%)
an
d
Sib
lar
ak
(
5
6
.
8
%),
wh
e
r
ea
s
th
e
ad
d
itiv
e
-
ce
n
ter
ed
MA
m
o
d
el
is
m
o
r
e
d
ef
en
s
ib
le
f
o
r
Kam
p
u
n
g
Do
lan
a
n
b
ec
au
s
e
it
y
ield
s
th
e
lo
west
MA
D
(
1
6
2
.
6
)
.
E
v
en
s
o
,
t
h
e
h
ig
h
MA
PE
v
alu
es
f
o
r
Sib
la
r
ak
an
d
Kam
p
u
n
g
D
o
lan
an
i
n
d
icate
th
at
m
o
d
el
f
it
r
em
ai
n
s
co
n
s
tr
ain
ed
b
y
v
o
latilit
y
an
d
d
ata
s
p
a
r
s
ity
.
T
ab
le
5
.
Mo
d
el
p
er
f
o
r
m
a
n
ce
c
o
m
p
ar
is
o
n
M
o
d
e
l
U
mb
u
l
M
a
n
t
e
n
S
i
b
l
a
r
a
k
K
a
m
p
u
n
g
D
o
l
a
n
a
n
M
A
D
M
A
P
E
(
%)
R
M
S
E
M
A
D
M
A
P
E
(
%)
R
M
S
E
M
A
D
M
A
P
E
(
%)
R
M
S
E
A
d
d
i
t
i
v
e
-
c
e
n
t
e
r
e
d
MA
3
,
0
7
8
1
7
.
5
1
5
,
1
2
7
,
7
6
0
3
,
0
4
4
5
9
.
1
1
7
,
5
4
4
,
4
6
0
1
6
2
.
6
5
8
.
8
6
0
,
2
4
0
A
d
d
i
t
i
v
e
-
a
v
e
r
a
g
e
a
l
l
2
,
7
0
6
1
4
.
4
1
1
,
0
3
7
,
8
2
0
2
,
9
7
8
5
8
.
5
1
7
,
5
3
5
,
3
1
0
1
5
3
.
3
1
6
5
.
0
3
0
,
1
6
2
M
u
l
t
i
p
l
i
c
a
t
i
v
e
-
c
e
n
t
e
r
e
d
MA
2
,
9
0
7
1
6
.
9
1
3
,
1
9
0
,
1
2
0
2
,
9
7
4
5
6
.
8
1
7
,
7
8
3
,
4
7
0
1
9
1
.
7
1
5
7
.
8
6
5
,
3
4
3
M
u
l
t
i
p
l
i
c
a
t
i
v
e
-
a
v
e
r
a
g
e
a
l
l
2
,
6
3
3
1
4
.
1
1
0
,
5
7
1
,
9
7
0
2
,
9
8
1
5
6
.
8
1
7
,
5
5
4
,
3
2
0
1
9
7
.
6
1
5
8
.
4
5
9
,
5
6
7
Fig
u
r
e
3
.
C
o
m
p
a
r
ativ
e
MA
PE
p
r
o
f
ile
ac
r
o
s
s
d
ec
o
m
p
o
s
itio
n
m
o
d
els
3
.
5
.
M
o
del
v
a
lid
a
t
io
n
a
nd
ro
bu
s
t
nes
s
a
na
ly
s
is
Um
bu
l
M
a
nte
n,
Sib
la
ra
k
,
a
nd
K
a
m
pu
ng
Do
la
na
n
Mo
d
el
v
alid
atio
n
an
d
r
o
b
u
s
tn
ess
ch
ec
k
s
wer
e
co
n
d
u
cted
th
r
o
u
g
h
tem
p
o
r
al
cr
o
s
s
-
v
alid
atio
n
,
r
esid
u
a
l
d
iag
n
o
s
tics
,
an
d
m
o
v
in
g
-
win
d
o
w
s
en
s
itiv
ity
an
aly
s
is
.
Fig
u
r
e
4
c
o
m
p
lem
e
n
ts
T
ab
les
6
to
8
b
y
s
u
m
m
a
r
izin
g
th
e
g
en
er
aliza
tio
n
g
ap
s
an
d
r
e
s
id
u
al
ad
eq
u
ac
y
o
f
th
e
s
elec
ted
b
est
-
p
er
f
o
r
m
in
g
m
o
d
els.
T
h
ese
r
esu
lts
p
r
o
v
id
e
a
co
n
cise o
v
er
v
iew
o
f
m
o
d
el
p
er
f
o
r
m
a
n
ce
an
d
r
eliab
ilit
y
.
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
C
o
mp
u
ta
tio
n
a
l fra
mewo
r
k
fo
r
s
ma
r
t to
u
r
is
m
ma
n
a
g
eme
n
t:
h
yb
r
id
time
s
erie
s
…
(
I
w
a
n
A
d
y
P
r
a
b
o
w
o
)
3427
Fig
u
r
e
4
.
Valid
atio
n
s
u
m
m
ar
y
f
o
r
s
elec
ted
b
est
-
p
e
r
f
o
r
m
in
g
m
o
d
els
T
ab
le
6
.
T
em
p
o
r
al
c
r
o
s
s
-
v
alid
atio
n
r
esu
lts
an
d
r
esid
u
al
d
iag
n
o
s
tics
D
e
st
i
n
a
t
i
o
n
M
o
d
e
l
Te
mp
o
r
a
l
c
r
o
ss
-
v
a
l
i
d
a
t
i
o
n
R
e
si
d
u
a
l
d
i
a
g
n
o
st
i
c
s
Tr
a
i
n
i
n
g
M
A
P
E
(
%)
Te
st
i
n
g
M
A
P
E
(
%)
ΔM
A
P
E
(
%)
A
C
F
/
P
A
C
F
r
a
n
d
o
m
n
e
s
s
Lj
u
n
g
-
B
o
x
p
-
v
a
l
u
e
U
mb
u
l
M
a
n
t
e
n
A
d
d
i
t
i
v
e
-
a
v
e
r
a
g
e
a
l
l
1
4
.
4
1
6
.
2
+
1
.
8
Y
e
s
0
.
1
2
M
u
l
t
i
p
l
i
c
a
t
i
v
e
-
a
v
e
r
a
g
e
a
l
l
1
4
.
1
1
5
.
9
+
1
.
8
Y
e
s
0
.
1
0
S
i
b
l
a
r
a
k
M
u
l
t
i
p
l
i
c
a
t
i
v
e
-
a
v
e
r
a
g
e
a
l
l
5
6
.
8
6
1
.
3
+
4
.
5
N
o
(
A
C
F
l
a
g
1
0
.
4
5
)
0
.
0
3
K
a
m
p
u
n
g
D
o
l
a
n
a
n
A
d
d
i
t
i
v
e
-
c
e
n
t
e
r
e
d
MA
5
8
.
8
6
5
.
4
+
6
.
6
Y
e
s
0
.
2
1
T
ab
le
7
.
Sen
s
itiv
ity
o
f
MA
D
t
o
m
o
v
i
n
g
-
av
e
r
ag
e
win
d
o
w
s
ize
D
e
st
i
n
a
t
i
o
n
M
o
d
e
l
M
A
D
(
k
=
3
)
M
A
D
(
k
=
5
)
M
A
D
(
k
=
7
)
U
mb
u
l
M
a
n
t
e
n
A
d
d
i
t
i
v
e
-
c
e
n
t
e
r
e
d
MA
3
,
0
7
8
3
,
2
4
5
3
,
4
1
2
S
i
b
l
a
r
a
k
M
u
l
t
i
p
l
i
c
a
t
i
v
e
-
c
e
n
t
e
r
e
d
MA
2
,
9
7
4
3
,
1
0
2
3
,
3
0
5
K
a
m
p
u
n
g
D
o
l
a
n
a
n
A
d
d
i
t
i
v
e
-
c
e
n
t
e
r
e
d
MA
1
6
2
.
6
1
7
8
.
9
1
9
5
.
3
T
ab
le
8
.
B
en
ch
m
a
r
k
p
e
r
f
o
r
m
a
n
ce
b
ased
o
n
MA
PE
D
e
st
i
n
a
t
i
o
n
D
e
c
o
m
p
o
si
t
i
o
n
m
o
d
e
l
N
a
ï
v
e
b
a
s
e
l
i
n
e
(
%)
I
mp
r
o
v
e
m
e
n
t
(
%)
U
mb
u
l
M
a
n
t
e
n
M
u
l
t
i
p
l
i
c
a
t
i
v
e
-
a
v
e
r
a
g
e
a
l
l
1
8
.
7
4
.
6
S
i
b
l
a
r
a
k
M
u
l
t
i
p
l
i
c
a
t
i
v
e
-
a
v
e
r
a
g
e
a
l
l
6
3
.
5
6
.
7
K
a
m
p
u
n
g
D
o
l
a
n
a
n
A
d
d
i
t
i
v
e
-
c
e
n
t
e
r
e
d
MA
6
7
.
2
8
.
4
3
.
5
.
1
.
T
em
po
ra
l
cr
o
s
s
-
v
a
lid
a
t
io
n a
nd
re
s
idu
a
l dia
g
no
s
t
ic
s
T
em
p
o
r
al
cr
o
s
s
-
v
alid
atio
n
s
h
o
ws
th
at
Um
b
u
l
Ma
n
ten
m
ain
tain
s
r
elativ
ely
s
tab
le
p
er
f
o
r
m
a
n
ce
b
etwe
en
th
e
tr
ain
in
g
a
n
d
test
in
g
p
er
io
d
s
,
wh
er
ea
s
Sib
lar
ak
an
d
Kam
p
u
n
g
Do
lan
a
n
ex
p
e
r
ien
ce
lar
g
er
er
r
o
r
in
cr
ea
s
es.
T
h
is
p
atter
n
s
u
g
g
e
s
ts
th
at
d
em
an
d
i
n
th
e
latter
two
d
esti
n
atio
n
s
is
m
o
r
e
s
tr
o
n
g
ly
in
f
lu
en
ce
d
b
y
ir
r
eg
u
lar
f
ac
to
r
s
th
at
ar
e
n
o
t
f
u
lly
r
ep
r
esen
te
d
in
th
e
s
h
o
r
t
h
is
to
r
ical
s
er
ies.
R
e
s
id
u
al
d
iag
n
o
s
tics
s
u
p
p
o
r
t
th
e
s
am
e
in
ter
p
r
etatio
n
.
Um
b
u
l
Ma
n
ten
an
d
Kam
p
u
n
g
Do
lan
an
s
h
o
w
co
m
p
ar
ativ
el
y
r
an
d
o
m
r
esid
u
al
b
eh
av
io
r
,
b
u
t
Sib
lar
ak
r
etain
s
r
esid
u
al
au
to
co
r
r
elatio
n
,
in
d
icatin
g
t
h
at
ev
en
t
-
r
elate
d
ef
f
ec
ts
r
em
ain
u
n
m
o
d
eled
.
I
n
p
r
ac
tical
ter
m
s
,
th
is
m
ea
n
s
th
at
f
esti
v
al
ca
len
d
ar
s
,
wea
th
er
v
ar
iab
les,
o
r
p
r
o
m
o
tio
n
al
in
te
r
v
en
tio
n
s
s
h
o
u
ld
b
e
in
co
r
p
o
r
ated
in
f
u
tu
r
e
f
o
r
ec
ast
in
g
ex
ten
s
io
n
s
.
3
.
5
.
2
.
Sens
it
iv
it
y
t
esting
T
h
e
m
o
v
in
g
-
win
d
o
w
s
en
s
itiv
ity
an
aly
s
is
in
d
icate
s
th
at
k
=3
o
f
f
er
s
th
e
b
est
co
m
p
r
o
m
is
e
b
etwe
en
r
esp
o
n
s
iv
en
ess
an
d
s
m
o
o
th
n
ess
ac
r
o
s
s
th
e
th
r
ee
d
esti
n
atio
n
s
.
L
ar
g
e
r
win
d
o
ws
r
ed
u
c
e
s
h
o
r
t
-
ter
m
n
o
is
e.
Ho
wev
er
,
th
ey
also
d
elay
tr
e
n
d
ad
ap
tatio
n
an
d
wea
k
en
th
e
v
is
ib
ilit
y
o
f
lo
ca
l seaso
n
al
ch
an
g
es.
3
.
5
.
3
.
B
enchm
a
rk
c
o
m
pa
riso
n
T
h
e
b
e
n
ch
m
ar
k
an
al
y
s
is
s
h
o
ws
th
at
th
e
p
r
o
p
o
s
ed
d
ec
o
m
p
o
s
itio
n
co
n
f
i
g
u
r
atio
n
s
o
u
tp
e
r
f
o
r
m
n
aiv
e
f
o
r
ec
asti
n
g
ac
r
o
s
s
all
d
esti
n
atio
n
s
.
E
v
en
s
o
,
t
h
is
co
m
p
a
r
is
o
n
s
h
o
u
ld
b
e
in
ter
p
r
eted
ca
u
t
io
u
s
ly
b
ec
au
s
e
t
h
e
cu
r
r
en
t
b
en
c
h
m
ar
k
d
o
es
n
o
t
y
et
in
clu
d
e
AR
I
MA
,
SA
R
I
M
A,
o
r
L
STM
b
aselin
es.
T
h
e
m
ain
co
n
tr
ib
u
tio
n
at
th
is
s
tag
e
is
th
er
ef
o
r
e
an
aly
ti
ca
l
tr
an
s
p
ar
en
cy
r
ath
e
r
th
an
e
x
h
au
s
tiv
e
m
o
d
el
s
u
p
e
r
io
r
ity
.
Fig
u
r
e
4
co
n
d
en
s
es
th
e
v
alid
atio
n
ev
i
d
en
ce
r
ep
o
r
ted
in
T
ab
les
6
to
8
.
T
h
e
co
m
p
ar
is
o
n
b
etwe
en
tr
ain
in
g
an
d
te
s
tin
g
MA
PE
s
h
o
ws
th
at
Um
b
u
l
Ma
n
ten
g
en
e
r
alize
s
m
o
r
e
s
m
o
o
th
l
y
th
an
th
e
o
th
er
d
esti
n
atio
n
s
,
wh
ile
th
e
lo
wer
L
ju
n
g
-
B
o
x
p
-
v
alu
es a
n
d
lar
g
er
er
r
o
r
g
ap
s
f
o
r
Sib
lar
ak
h
ig
h
lig
h
t u
n
r
eso
lv
ed
s
tr
u
ctu
r
al
v
o
latilit
y
.
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
5
,
No
.
4
,
Au
g
u
s
t 2
0
2
6
:
3
4
2
1
-
3
4
3
0
3428
3
.
6
.
I
nte
g
ra
t
ed
s
m
a
rt
t
o
uris
m
f
ra
m
ewo
r
k
f
o
r
Sid
o
wa
y
a
h Villa
g
e
T
h
e
in
teg
r
ated
f
r
am
ewo
r
k
em
er
g
in
g
f
r
o
m
t
h
ese
f
in
d
in
g
s
is
b
est
u
n
d
er
s
to
o
d
as
a
p
r
ac
tical
d
ec
is
io
n
-
s
u
p
p
o
r
t
ar
ch
itectu
r
e
r
ath
er
th
a
n
a
f
u
lly
au
t
o
m
at
ed
p
r
e
d
ictio
n
en
g
in
e.
I
t
lin
k
s
d
ata
p
r
ep
ar
atio
n
,
d
ec
o
m
p
o
s
itio
n
-
b
ased
f
o
r
ec
as
tin
g
,
m
o
d
el
in
ter
p
r
etatio
n
,
an
d
m
an
ag
e
r
ial
r
esp
o
n
s
e
with
in
a
s
in
g
le
to
u
r
is
m
-
g
o
v
er
n
a
n
ce
wo
r
k
f
lo
w.
T
ab
le
9
s
u
m
m
a
r
izes
th
is
tr
an
s
latio
n
b
y
c
o
n
n
ec
tin
g
f
o
r
ec
ast
s
ig
n
als
with
r
ec
o
m
m
en
d
ed
ac
tio
n
s
an
d
SDG
-
lin
k
ed
im
p
licatio
n
s
.
T
h
e
f
r
am
ewo
r
k
is
esp
ec
ially
r
elev
an
t
f
o
r
r
u
r
al
d
esti
n
atio
n
s
th
at
n
ee
d
s
im
p
le
b
u
t in
ter
p
r
etab
le
an
aly
tics
u
n
d
er
lim
ited
d
ata
co
n
d
itio
n
s
.
T
ab
le
9
.
Fo
r
ec
ast s
ig
n
als,
m
an
ag
er
ial
ac
tio
n
s
,
an
d
SDG
alig
n
m
en
t
F
o
r
e
c
a
st
si
g
n
a
l
R
e
c
o
mm
e
n
d
e
d
ma
n
a
g
e
r
i
a
l
a
c
t
i
o
n
P
r
i
mary
d
e
st
i
n
a
t
i
o
n
i
mp
l
i
c
a
t
i
o
n
S
D
G
l
i
n
k
a
g
e
S
t
r
o
n
g
y
e
a
r
-
e
n
d
d
e
ma
n
d
s
u
r
g
e
A
c
t
i
v
a
t
e
st
a
f
f
i
n
g
,
p
a
r
k
i
n
g
,
a
n
d
t
e
m
p
o
r
a
r
y
c
a
p
a
c
i
t
y
c
o
n
t
r
o
l
s
U
mb
u
l
M
a
n
t
e
n
a
n
d
S
i
b
l
a
r
a
k
S
D
G
1
1
:
s
a
f
e
r
a
n
d
m
o
r
e
man
a
g
e
a
b
l
e
v
i
s
i
t
o
r
f
l
o
w
s
I
r
r
e
g
u
l
a
r
v
o
l
a
t
i
l
i
t
y
U
se
f
l
e
x
i
b
l
e
sc
h
e
d
u
l
i
n
g
a
n
d
smal
l
-
b
a
t
c
h
r
e
so
u
r
c
e
a
l
l
o
c
a
t
i
o
n
K
a
m
p
u
n
g
D
o
l
a
n
a
n
S
D
G
1
2
:
m
o
r
e
e
f
f
i
c
i
e
n
t
r
e
so
u
r
c
e
u
s
e
P
e
r
si
st
e
n
t
r
e
s
i
d
u
a
l
d
e
p
e
n
d
e
n
c
e
A
d
d
e
v
e
n
t
-
c
a
l
e
n
d
a
r
m
o
n
i
t
o
r
i
n
g
a
n
d
ma
n
u
a
l
r
e
v
i
e
w
b
e
f
o
r
e
p
e
a
k
p
e
r
i
o
d
s
S
i
b
l
a
r
a
k
S
D
G
1
1
a
n
d
1
2
:
r
i
sk
-
a
w
a
r
e
o
p
e
r
a
t
i
o
n
a
l
p
l
a
n
n
i
n
g
Lo
w
-
sea
so
n
d
e
c
l
i
n
e
D
e
p
l
o
y
t
a
r
g
e
t
e
d
e
d
u
c
a
t
i
o
n
a
l
o
r
c
u
l
t
u
r
a
l
p
r
o
m
o
t
i
o
n
s
K
a
m
p
u
n
g
D
o
l
a
n
a
n
a
n
d
sh
o
u
l
d
e
r
-
sea
s
o
n
p
e
r
i
o
d
s
S
D
G
1
2
:
b
a
l
a
n
c
e
d
d
e
m
a
n
d
r
e
d
i
s
t
r
i
b
u
t
i
o
n
3
.
7
.
Dis
cus
s
io
n
T
h
is
s
tu
d
y
d
em
o
n
s
tr
ates
th
at
d
ec
o
m
p
o
s
itio
n
-
b
ased
f
o
r
ec
asti
n
g
ca
n
s
u
p
p
o
r
t
to
u
r
is
m
d
ec
is
i
o
n
-
m
ak
i
n
g
in
d
ata
-
co
n
s
tr
ain
ed
r
u
r
al
s
ettin
g
s
,
b
u
t
its
u
s
ef
u
ln
ess
v
ar
i
es
m
ar
k
ed
ly
ac
r
o
s
s
d
esti
n
ati
o
n
s
.
T
h
e
s
tr
o
n
g
est
p
er
f
o
r
m
an
ce
was
o
b
s
er
v
ed
f
o
r
Um
b
u
l
Ma
n
te
n
,
wh
er
e
s
ea
s
o
n
al
d
em
a
n
d
was
co
m
p
ar
ativ
ely
s
tab
le.
Sib
lar
ak
r
em
ain
ed
m
o
r
e
d
if
f
icu
lt
to
m
o
d
el
b
ec
au
s
e
f
esti
v
al
-
d
r
i
v
e
n
v
is
itatio
n
p
r
o
d
u
ce
s
ir
r
eg
u
lar
s
u
r
g
es,
wh
ile
Kam
p
u
n
g
Do
la
n
an
ex
h
i
b
ited
h
ig
h
v
o
latilit
y
lik
ely
ass
o
ciate
d
with
s
ch
o
o
l
-
g
r
o
u
p
s
ch
ed
u
lin
g
an
d
n
o
n
-
r
ec
u
r
r
in
g
co
m
m
u
n
ity
ac
tiv
ities
.
T
h
ese
d
if
f
er
en
ce
s
ex
p
lain
wh
y
a
s
in
g
le
m
o
d
el
f
o
r
m
is
n
o
t
eq
u
all
y
s
u
itab
le
ac
r
o
s
s
all
th
r
ee
s
ites
.
Acc
o
r
d
in
g
ly
,
t
h
e
p
r
esen
t
co
n
tr
ib
u
tio
n
s
h
o
u
l
d
b
e
r
ea
d
as
a
m
o
r
e
tr
an
s
p
ar
en
t
a
n
d
d
ec
is
io
n
-
o
r
ien
ted
d
ec
o
m
p
o
s
itio
n
f
r
a
m
ewo
r
k
r
at
h
er
th
a
n
a
f
in
al
f
o
r
ec
asti
n
g
b
en
ch
m
ar
k
.
I
t
im
p
r
o
v
es
m
et
h
o
d
o
lo
g
ical
cla
r
ity
b
y
m
ak
in
g
p
r
e
p
r
o
ce
s
s
in
g
c
h
o
ices,
m
o
d
el
-
s
elec
tio
n
lo
g
ic,
a
n
d
v
alid
atio
n
b
o
u
n
d
ar
ies
m
o
r
e
e
x
p
licit.
At
th
e
s
am
e
tim
e,
th
e
s
tu
d
y
r
em
ain
s
lim
ite
d
b
y
its
1
2
-
m
o
n
th
d
ataset,
th
e
ab
s
en
ce
o
f
alter
n
ativ
e
im
p
u
tatio
n
ex
p
er
im
en
ts
,
th
e
lack
o
f
f
o
r
m
al
d
ec
o
m
p
o
s
itio
n
-
s
elec
tio
n
test
s
,
an
d
th
e
o
m
is
s
io
n
o
f
s
tr
o
n
g
er
b
aselin
es
s
u
ch
as
AR
I
MA
,
SAR
I
MA
,
o
r
L
STM
.
Fu
tu
r
e
wo
r
k
s
h
o
u
ld
a
d
d
r
ess
th
ese
g
a
p
s
u
s
in
g
lo
n
g
er
s
er
ies,
r
ich
e
r
ex
o
g
en
o
u
s
v
a
r
iab
les,
an
d
h
y
b
r
id
o
r
en
s
em
b
le
f
o
r
ec
a
s
tin
g
d
esig
n
s
.
4.
CO
NCLU
SI
O
N
T
h
is
s
tu
d
y
e
x
am
in
ed
m
o
n
th
l
y
to
u
r
is
t
v
is
itatio
n
p
atter
n
s
in
Sid
o
way
ah
Villag
e
u
s
in
g
a
h
y
b
r
i
d
d
ec
o
m
p
o
s
itio
n
f
r
am
ewo
r
k
d
e
s
ig
n
ed
f
o
r
th
r
ee
i
n
teg
r
ated
r
u
r
al
d
esti
n
atio
n
s
:
Um
b
u
l
Ma
n
ten
,
Sib
lar
ak
,
an
d
Kam
p
u
n
g
Do
la
n
an
.
T
h
e
r
esu
l
ts
s
h
o
w
th
at
d
esti
n
atio
n
-
s
p
ec
i
f
ic
d
ec
o
m
p
o
s
itio
n
ca
n
s
u
p
p
o
r
t
p
r
ac
tical
to
u
r
is
m
p
lan
n
in
g
wh
en
d
ata
ar
e
lim
ited
,
b
u
t
f
o
r
ec
asti
n
g
q
u
ali
ty
v
ar
ies
s
u
b
s
tan
tially
ac
r
o
s
s
attr
ac
tio
n
ty
p
es.
Mu
ltip
licativ
e
d
ec
o
m
p
o
s
itio
n
is
m
o
r
e
s
u
itab
le
f
o
r
Um
b
u
l
Ma
n
ten
an
d
Sib
lar
ak
,
w
h
er
ea
s
ad
d
itiv
e
-
ce
n
ter
ed
d
ec
o
m
p
o
s
itio
n
is
m
o
r
e
d
ef
e
n
s
ib
le
f
o
r
Kam
p
u
n
g
Do
lan
a
n
.
T
h
e
m
ain
v
al
u
e
o
f
t
h
e
s
tu
d
y
lies
in
o
f
f
er
in
g
a
tr
an
s
p
ar
en
t,
r
ep
r
o
d
u
cib
le,
an
d
s
u
s
tain
ab
ilit
y
-
o
r
ien
ted
f
o
r
ec
a
s
tin
g
wo
r
k
f
l
o
w
r
ath
e
r
th
a
n
a
f
in
al
b
en
c
h
m
ar
k
in
g
r
esu
lt.
Fu
tu
r
e
r
esear
ch
s
h
o
u
ld
ex
ten
d
th
e
d
ataset,
s
tr
en
g
th
en
s
tatis
tical
ev
alu
atio
n
,
an
d
co
m
p
ar
e
th
e
f
r
am
ewo
r
k
ag
ain
s
t b
r
o
ad
er
b
a
s
elin
e
an
d
h
y
b
r
id
m
o
d
els.
ACK
NO
WL
E
DG
M
E
N
T
S
T
h
e
au
th
o
r
s
g
r
atef
u
lly
ac
k
n
o
wled
g
e
th
e
Min
is
tr
y
o
f
E
d
u
ca
tio
n
,
C
u
ltu
r
e,
R
esear
ch
,
an
d
T
ec
h
n
o
lo
g
y
o
f
I
n
d
o
n
esia f
o
r
s
u
p
p
o
r
tin
g
th
i
s
s
tu
d
y
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
T
h
is
r
esear
ch
was
f
u
n
d
ed
b
y
th
e
Min
is
tr
y
o
f
E
d
u
ca
tio
n
,
C
u
ltu
r
e,
R
esear
ch
,
an
d
T
ec
h
n
o
lo
g
y
o
f
I
n
d
o
n
esia
th
r
o
u
g
h
th
e
2
0
2
4
Fu
n
d
a
m
en
tal
-
R
eg
u
lar
R
esear
ch
Sch
em
e
u
n
d
er
g
r
an
t
n
u
m
b
er
s
1
0
8
/E5
/PG.0
2
.
0
0
.
PL/2
0
2
4
,
0
8
2
/LL
6
/PB
/AL
.
0
4
/2
0
2
4
,
an
d
0
0
2
/K
-
PL/L
PP
M/ST
MI
K
-
SN/2
0
2
4
.
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
C
o
mp
u
ta
tio
n
a
l fra
mewo
r
k
fo
r
s
ma
r
t to
u
r
is
m
ma
n
a
g
eme
n
t:
h
yb
r
id
time
s
erie
s
…
(
I
w
a
n
A
d
y
P
r
a
b
o
w
o
)
3429
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
I
wan
Ad
y
Pra
b
o
wo
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Hen
d
r
o
W
ijay
an
to
✓
✓
✓
✓
✓
✓
✓
✓
✓
T
eg
u
h
Su
s
y
an
t
o
✓
✓
✓
✓
✓
✓
✓
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
T
h
e
au
th
o
r
s
d
ec
lar
e
th
at
th
e
r
e
is
n
o
co
n
f
lict o
f
in
ter
est r
eg
ar
d
in
g
th
e
p
u
b
licatio
n
o
f
th
is
ar
t
icle.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
ata
s
u
p
p
o
r
tin
g
th
is
s
t
u
d
y
,
in
clu
d
in
g
m
o
n
th
ly
v
is
itatio
n
co
u
n
ts
,
p
r
e
p
r
o
ce
s
s
ed
s
er
ies,
an
d
d
ec
o
m
p
o
s
itio
n
r
esu
lts
f
o
r
t
h
e
th
r
ee
to
u
r
is
m
s
ites
in
Sid
o
way
ah
Villag
e,
ar
e
a
v
ailab
le
f
r
o
m
th
e
c
o
r
r
esp
o
n
d
in
g
au
th
o
r
,
[
I
AP]
,
u
p
o
n
r
ea
s
o
n
a
b
l
e
r
eq
u
est.
Pu
b
lic
r
elea
s
e
is
cu
r
r
en
tly
r
estricte
d
b
ec
au
s
e
t
h
e
d
ata
ar
e
m
an
ag
e
d
jo
in
tly
with
lo
ca
l
to
u
r
is
m
s
tak
eh
o
ld
er
s
.
Data
av
ailab
ilit
y
is
n
o
t
ap
p
licab
le
to
th
is
p
ap
e
r
as
n
o
n
ew
d
ata
wer
e
cr
ea
ted
o
r
a
n
aly
ze
d
i
n
th
is
s
tu
d
y
.
RE
F
E
R
E
NC
E
S
[
1
]
D
.
B
u
h
a
l
i
s
,
“
T
e
c
h
n
o
l
o
g
y
i
n
t
o
u
r
i
s
m
-
f
r
o
m
i
n
f
o
r
m
a
t
i
o
n
c
o
m
m
u
n
i
c
a
t
i
o
n
t
e
c
h
n
o
l
o
g
i
e
s
t
o
e
T
o
u
r
i
s
m
a
n
d
s
m
a
r
t
t
o
u
r
i
s
m
t
o
w
a
r
d
s
a
m
b
i
e
n
t
i
n
t
e
l
l
i
g
e
n
c
e
t
o
u
r
i
s
m
:
a
p
e
r
s
p
e
c
t
i
v
e
a
r
t
i
c
l
e
,
”
T
o
u
r
i
s
m
R
e
v
i
e
w
,
v
o
l
.
7
5
,
n
o
.
1
,
p
p
.
2
6
7
–
2
7
2
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
8
/
T
R
-
06
-
2
0
1
9
-
0
2
5
8
.
[
2
]
U
.
G
r
e
t
z
e
l
,
M
.
S
i
g
a
l
a
,
Z
.
X
i
a
n
g
,
a
n
d
C
.
K
o
o
,
“
S
mart
t
o
u
r
i
sm
:
f
o
u
n
d
a
t
i
o
n
s
a
n
d
d
e
v
e
l
o
p
m
e
n
t
s,
”
E
l
e
c
t
r
o
n
i
c
M
a
rk
e
t
s
,
v
o
l
.
2
5
,
n
o
.
3
,
p
p
.
1
7
9
–
1
8
8
,
2
0
1
5
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
2
5
2
5
-
0
1
5
-
0
1
9
6
-
8.
[
3
]
H
.
S
o
n
g
a
n
d
G
.
L
i
,
“
T
o
u
r
i
sm
d
e
ma
n
d
m
o
d
e
l
l
i
n
g
a
n
d
f
o
r
e
c
a
st
i
n
g
-
a
r
e
v
i
e
w
o
f
r
e
c
e
n
t
r
e
se
a
r
c
h
,
”
T
o
u
ri
sm
M
a
n
a
g
e
m
e
n
t
,
v
o
l
.
2
9
,
n
o
.
2
,
p
p
.
2
0
3
–
2
2
0
,
2
0
0
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
t
o
u
r
ma
n
.
2
0
0
7
.
0
7
.
0
1
6
.
[
4
]
Y
.
Li
,
C
.
H
u
,
C
.
H
u
a
n
g
,
a
n
d
L.
D
u
a
n
,
“
Th
e
c
o
n
c
e
p
t
o
f
smar
t
t
o
u
r
i
sm
i
n
t
h
e
c
o
n
t
e
x
t
o
f
t
o
u
r
i
s
m
i
n
f
o
r
m
a
t
i
o
n
s
e
r
v
i
c
e
s,
”
T
o
u
ri
sm
Ma
n
a
g
e
m
e
n
t
,
v
o
l
.
5
8
,
p
p
.
2
9
3
–
3
0
0
,
2
0
1
7
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
t
o
u
r
ma
n
.
2
0
1
6
.
0
3
.
0
1
4
.
[
5
]
R
.
La
w
,
G
.
Li
,
D
.
K
.
C
.
F
o
n
g
,
a
n
d
X
.
H
a
n
,
“
To
u
r
i
s
m
d
e
m
a
n
d
f
o
r
e
c
a
s
t
i
n
g
:
a
d
e
e
p
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
,
”
An
n
a
l
s
o
f
T
o
u
r
i
sm
Re
se
a
rc
h
,
v
o
l
.
7
5
,
p
p
.
4
1
0
–
4
2
3
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
n
n
a
l
s
.
2
0
1
9
.
0
1
.
0
1
4
.
[
6
]
Y
.
Li
a
n
d
H
.
C
a
o
,
“
P
r
e
d
i
c
t
i
o
n
f
o
r
t
o
u
r
i
sm
f
l
o
w
b
a
se
d
o
n
LSTM
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
Pro
c
e
d
i
a
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
1
2
9
,
p
p
.
2
7
7
–
2
8
3
,
2
0
1
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
r
o
c
s.2
0
1
8
.
0
3
.
0
7
6
.
[
7
]
S
.
C
.
H
si
e
h
,
“
T
o
u
r
i
sm
d
e
m
a
n
d
f
o
r
e
c
a
st
i
n
g
b
a
se
d
o
n
a
n
LST
M
n
e
t
w
o
r
k
a
n
d
i
t
s
v
a
r
i
a
n
t
s
,
”
Al
g
o
r
i
t
h
m
s
,
v
o
l
.
1
4
,
n
o
.
8
,
p
p
.
1
3
2
–
1
4
5
,
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
a
1
4
0
8
0
2
4
3
.
[
8
]
A
.
S
a
l
a
m
a
n
i
s,
G
.
X
a
n
t
h
o
p
o
u
l
o
u
,
D
.
K
e
h
a
g
i
a
s,
a
n
d
D
.
Tz
o
v
a
r
a
s
,
“
LST
M
-
b
a
se
d
d
e
e
p
l
e
a
r
n
i
n
g
m
o
d
e
l
s
f
o
r
l
o
n
g
-
t
e
r
m
t
o
u
r
i
sm
d
e
m
a
n
d
f
o
r
e
c
a
st
i
n
g
,
”
E
l
e
c
t
r
o
n
i
c
s
,
v
o
l
.
1
1
,
n
o
.
2
2
,
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
e
l
e
c
t
r
o
n
i
c
s
1
1
2
2
3
6
8
1
.
[
9
]
U
.
G
u
n
t
e
r
a
n
d
I
.
Ö
n
d
e
r
,
“
F
o
r
e
c
a
s
t
i
n
g
i
n
t
e
r
n
a
t
i
o
n
a
l
c
i
t
y
t
o
u
r
i
sm
d
e
m
a
n
d
f
o
r
P
a
r
i
s:
a
c
c
u
r
a
c
y
o
f
u
n
i
-
a
n
d
m
u
l
t
i
v
a
r
i
a
t
e
mo
d
e
l
s
e
mp
l
o
y
i
n
g
m
o
n
t
h
l
y
d
a
t
a
,
”
T
o
u
ri
sm
M
a
n
a
g
e
m
e
n
t
,
v
o
l
.
4
6
,
n
o
.
2
,
p
p
.
1
2
3
–
1
3
5
,
2
0
1
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
t
o
u
r
ma
n
.
2
0
1
4
.
0
6
.
0
1
7
.
[
1
0
]
W
.
L
u
,
H
.
R
u
i
,
C
.
Li
a
n
g
,
L.
J
i
a
n
g
,
S
.
Z
h
a
o
,
a
n
d
K
.
L
i
,
“
A
me
t
h
o
d
b
a
se
d
o
n
G
A
-
C
N
N
-
LST
M
f
o
r
d
a
i
l
y
t
o
u
r
i
s
t
f
l
o
w
p
r
e
d
i
c
t
i
o
n
a
t
sce
n
i
c
sp
o
t
s,”
E
n
t
r
o
p
y
,
v
o
l
.
2
2
,
n
o
.
3
,
p
p
.
5
1
2
–
5
2
6
,
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
e
2
2
0
3
0
2
6
1
.
[
1
1
]
H
.
S
o
n
g
,
R
.
T.
R
.
Q
i
u
,
a
n
d
J.
P
a
r
k
,
“
A
r
e
v
i
e
w
o
f
r
e
s
e
a
r
c
h
o
n
t
o
u
r
i
s
m
d
e
m
a
n
d
f
o
r
e
c
a
st
i
n
g
:
l
a
u
n
c
h
i
n
g
t
h
e
a
n
n
a
l
s
o
f
t
o
u
r
i
sm
r
e
sea
r
c
h
c
u
r
a
t
e
d
c
o
l
l
e
c
t
i
o
n
o
n
t
o
u
r
i
sm
d
e
ma
n
d
f
o
r
e
c
a
st
i
n
g
,
”
A
n
n
a
l
s
o
f
T
o
u
r
i
sm
Re
s
e
a
r
c
h
,
v
o
l
.
7
5
,
p
p
.
3
3
8
–
3
6
2
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
n
n
a
l
s.
2
0
1
8
.
1
2
.
0
0
1
.
[
1
2
]
C
.
F
.
C
h
e
n
,
M
.
C
.
L
a
i
,
a
n
d
C
.
C
.
Y
e
h
,
“
F
o
r
e
c
a
s
t
i
n
g
t
o
u
r
i
sm
d
e
m
a
n
d
b
a
s
e
d
o
n
e
m
p
i
r
i
c
a
l
m
o
d
e
d
e
c
o
mp
o
s
i
t
i
o
n
a
n
d
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
K
n
o
w
l
e
d
g
e
-
Ba
s
e
d
S
y
st
e
m
s
,
v
o
l
.
2
6
,
n
o
.
1
2
,
p
p
.
2
8
1
–
2
8
7
,
2
0
1
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
k
n
o
sy
s
.
2
0
1
1
.
0
9
.
0
0
2
.
[
1
3
]
K
.
Y
.
C
h
e
n
,
“
C
o
m
b
i
n
i
n
g
l
i
n
e
a
r
a
n
d
n
o
n
l
i
n
e
a
r
m
o
d
e
l
i
n
f
o
r
e
c
a
st
i
n
g
t
o
u
r
i
sm
d
e
ma
n
d
,
”
Ex
p
e
r
t
S
y
s
t
e
m
s
w
i
t
h
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
3
8
,
n
o
.
8
,
p
p
.
1
0
3
6
8
–
1
0
3
7
6
,
2
0
1
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
sw
a
.
2
0
1
1
.
0
2
.
0
4
9
.
[
1
4
]
S
.
C
a
n
g
,
“
A
c
o
m
p
a
r
a
t
i
v
e
a
n
a
l
y
si
s
o
f
t
h
r
e
e
t
y
p
e
s
o
f
t
o
u
r
i
sm
d
e
ma
n
d
f
o
r
e
c
a
st
i
n
g
mo
d
e
l
s:
i
n
d
i
v
i
d
u
a
l
,
l
i
n
e
a
r
c
o
m
b
i
n
a
t
i
o
n
a
n
d
n
o
n
-
l
i
n
e
a
r
c
o
mb
i
n
a
t
i
o
n
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
T
o
u
ri
sm
Re
se
a
r
c
h
,
v
o
l
.
1
6
,
n
o
.
6
,
p
p
.
5
9
6
–
6
0
7
,
2
0
1
4
,
d
o
i
:
1
0
.
1
0
0
2
/
j
t
r
.
1
9
5
3
.
[
1
5
]
P
.
C
e
n
t
o
b
e
l
l
i
a
n
d
V
.
N
d
o
u
,
“
M
a
n
a
g
i
n
g
c
u
st
o
m
e
r
k
n
o
w
l
e
d
g
e
t
h
r
o
u
g
h
t
h
e
u
se
o
f
b
i
g
d
a
t
a
a
n
a
l
y
t
i
c
s
i
n
t
o
u
r
i
sm
r
e
sea
r
c
h
,
”
C
u
rre
n
t
I
ssu
e
s
i
n
T
o
u
r
i
sm
,
v
o
l
.
2
2
,
n
o
.
1
5
,
p
p
.
1
8
6
2
–
1
8
8
2
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
8
0
/
1
3
6
8
3
5
0
0
.
2
0
1
8
.
1
5
6
4
7
3
9
.
[
1
6
]
J.
M
.
M
.
M
a
r
t
í
n
,
J.
A
.
S
.
F
e
r
n
á
n
d
e
z
,
J.
A
.
R
.
M
a
r
t
í
n
,
a
n
d
M
.
d
e
l
S
.
O
.
R
e
y
,
“
A
n
a
l
y
s
i
s
o
f
t
o
u
r
i
sm
s
e
a
s
o
n
a
l
i
t
y
a
s
a
f
a
c
t
o
r
l
i
mi
t
i
n
g
t
h
e
su
s
t
a
i
n
a
b
l
e
d
e
v
e
l
o
p
me
n
t
o
f
r
u
r
a
l
a
r
e
a
s,
”
J
o
u
rn
a
l
o
f
H
o
s
p
i
t
a
l
i
t
y
a
n
d
T
o
u
r
i
sm
Re
se
a
rc
h
,
v
o
l
.
4
4
,
n
o
.
1
,
p
p
.
4
5
–
7
5
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
7
7
/
1
0
9
6
3
4
8
0
1
9
8
7
6
6
8
8
.
[
1
7
]
J.
C
.
S
.
N
ú
ñ
e
z
,
J
.
A
.
G
.
-
P
u
l
i
d
o
,
a
n
d
R
.
R
.
R
a
mí
r
e
z
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
l
i
e
d
t
o
t
o
u
r
i
sm
:
a
sy
st
e
mat
i
c
r
e
v
i
e
w
,
”
Wi
l
e
y
I
n
t
e
r
d
i
sci
p
l
i
n
a
r
y
R
e
v
i
e
w
s:
D
a
t
a
M
i
n
i
n
g
a
n
d
K
n
o
w
l
e
d
g
e
D
i
sc
o
v
e
ry
,
v
o
l
.
1
4
,
n
o
.
5
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
0
2
/
w
i
d
m.
1
5
4
9
.
[
1
8
]
H
.
Li
,
M
.
H
u
,
a
n
d
G
.
Li
,
“
F
o
r
e
c
a
s
t
i
n
g
t
o
u
r
i
sm
d
e
ma
n
d
w
i
t
h
m
u
l
t
i
s
o
u
r
c
e
b
i
g
d
a
t
a
,
”
An
n
a
l
s
o
f
T
o
u
r
i
sm
Re
s
e
a
r
c
h
,
v
o
l
.
8
3
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
n
n
a
l
s.
2
0
2
0
.
1
0
2
9
1
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
5
,
No
.
4
,
Au
g
u
s
t 2
0
2
6
:
3
4
2
1
-
3
4
3
0
3430
[
1
9
]
H
.
W
e
r
t
h
n
e
r
e
t
a
l
.
,
“
F
u
t
u
r
e
r
e
sea
r
c
h
i
ssu
e
s
i
n
I
T
a
n
d
t
o
u
r
i
sm,
”
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
&
T
o
u
ri
sm
,
v
o
l
.
1
5
,
n
o
.
1
,
p
p
.
1
–
1
5
,
M
a
r
.
2
0
1
5
,
d
o
i
:
1
0
.
1
0
0
7
/
s
4
0
5
5
8
-
0
1
4
-
0
0
2
1
-
9.
[
2
0
]
T.
B
.
-
Ti
a
g
o
,
J.
M
.
C
.
V
e
r
í
ssi
mo
,
a
n
d
F
.
T
i
a
g
o
,
“
S
m
a
r
t
t
o
u
r
i
sm
:
a
sc
i
e
n
t
o
m
e
t
r
i
c
r
e
v
i
e
w
(
2
0
0
8
-
2
0
2
0
)
,
”
E
u
ro
p
e
a
n
J
o
u
r
n
a
l
o
f
T
o
u
r
i
sm
R
e
se
a
rc
h
,
v
o
l
.
3
0
,
p
p
.
1
-
1
8
,
2
0
2
2
,
d
o
i
:
1
0
.
5
4
0
5
5
/
e
j
t
r
.
v
3
0
i
.
2
5
9
3
.
[
2
1
]
X
.
C
h
e
e
t
a
l
.
,
“
Li
n
e
a
r
l
y
i
n
t
e
r
p
o
l
a
t
i
n
g
m
i
ssi
n
g
v
a
l
u
e
s
i
n
t
i
m
e
s
e
r
i
e
s
h
e
l
p
s
l
i
t
t
l
e
f
o
r
l
a
n
d
c
o
v
e
r
c
l
a
ss
i
f
i
c
a
t
i
o
n
u
si
n
g
r
e
c
u
r
r
e
n
t
o
r
a
t
t
e
n
t
i
o
n
n
e
t
w
o
r
k
s,”
I
S
PR
S
J
o
u
rn
a
l
o
f
Ph
o
t
o
g
r
a
m
m
e
t
r
y
a
n
d
Re
m
o
t
e
S
e
n
s
i
n
g
,
v
o
l
.
2
1
2
,
p
p
.
7
3
–
9
5
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
sp
r
s
j
p
r
s
.
2
0
2
4
.
0
4
.
0
2
1
.
[
2
2
]
C
.
S
.
K
.
D
a
s
h
,
A
.
K
.
B
e
h
e
r
a
,
S
.
D
e
h
u
r
i
,
a
n
d
A
.
G
h
o
s
h
,
“
A
n
o
u
t
l
i
e
r
s
d
e
t
e
c
t
i
o
n
a
n
d
e
l
i
mi
n
a
t
i
o
n
f
r
a
m
e
w
o
r
k
i
n
c
l
a
s
si
f
i
c
a
t
i
o
n
t
a
s
k
o
f
d
a
t
a
m
i
n
i
n
g
,
”
D
e
c
i
si
o
n
A
n
a
l
y
t
i
c
s J
o
u
r
n
a
l
,
v
o
l
.
6
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
d
a
j
o
u
r
.
2
0
2
3
.
1
0
0
1
6
4
.
[
2
3
]
F
.
T.
Li
m
a
a
n
d
V
.
M
.
A
.
S
o
u
z
a
,
“
A
l
a
r
g
e
c
o
m
p
a
r
i
so
n
o
f
n
o
r
m
a
l
i
z
a
t
i
o
n
m
e
t
h
o
d
s
o
n
t
i
m
e
ser
i
e
s,
”
B
i
g
D
a
t
a
Re
s
e
a
rc
h
,
v
o
l
.
3
4
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
b
d
r
.
2
0
2
3
.
1
0
0
4
0
7
.
[
2
4
]
Y
.
S
.
K
i
m,
M
.
K
.
K
i
m
,
N
.
F
u
,
J.
L
i
u
,
J.
W
a
n
g
,
a
n
d
J.
S
r
e
b
r
i
c
,
“
I
n
v
e
s
t
i
g
a
t
i
n
g
t
h
e
i
mp
a
c
t
o
f
d
a
t
a
n
o
r
m
a
l
i
z
a
t
i
o
n
me
t
h
o
d
s
o
n
p
r
e
d
i
c
t
i
n
g
e
l
e
c
t
r
i
c
i
t
y
c
o
n
s
u
mp
t
i
o
n
i
n
a
b
u
i
l
d
i
n
g
u
si
n
g
d
i
f
f
e
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
m
o
d
e
l
s
,
”
S
u
s
t
a
i
n
a
b
l
e
C
i
t
i
e
s
a
n
d
S
o
c
i
e
t
y
,
v
o
l
.
1
1
8
,
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
scs
.
2
0
2
4
.
1
0
5
5
7
0
.
[
2
5
]
B
.
R
.
-
T
a
b
a
r
,
T.
E
.
G
o
l
t
s
o
s,
a
n
d
S
.
W
a
n
g
,
“
F
o
r
e
c
a
st
i
n
g
f
o
r
l
e
a
d
-
t
i
me
p
e
r
i
o
d
b
y
t
e
m
p
o
r
a
l
a
g
g
r
e
g
a
t
i
o
n
:
w
h
e
t
h
e
r
t
o
c
o
m
b
i
n
e
a
n
d
h
o
w
,
”
C
o
m
p
u
t
e
rs i
n
I
n
d
u
s
t
ry
,
v
o
l
.
1
4
5
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
m
p
i
n
d
.
2
0
2
2
.
1
0
3
8
0
3
.
[
2
6
]
Y
.
En
s
a
f
i
,
S
.
H
.
A
mi
n
,
G
.
Zh
a
n
g
,
a
n
d
B
.
S
h
a
h
,
“
T
i
me
-
s
e
r
i
e
s
f
o
r
e
c
a
s
t
i
n
g
o
f
se
a
so
n
a
l
i
t
e
ms
sa
l
e
s
u
si
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
–
a
c
o
m
p
a
r
a
t
i
v
e
a
n
a
l
y
s
i
s,”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
I
n
f
o
rm
a
t
i
o
n
M
a
n
a
g
e
m
e
n
t
D
a
t
a
I
n
s
i
g
h
t
s
,
v
o
l
.
2
,
n
o
.
1
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
j
i
me
i
.
2
0
2
2
.
1
0
0
0
5
8
.
[
2
7
]
G
.
X
i
e
,
Y
.
Q
i
a
n
,
a
n
d
S
.
W
a
n
g
,
“
A
d
e
c
o
m
p
o
si
t
i
o
n
-
e
n
s
e
m
b
l
e
a
p
p
r
o
a
c
h
f
o
r
t
o
u
r
i
sm
f
o
r
e
c
a
s
t
i
n
g
,
”
An
n
a
l
s
o
f
T
o
u
ri
sm
R
e
se
a
rc
h
,
v
o
l
.
8
1
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
n
n
a
l
s.
2
0
2
0
.
1
0
2
8
9
1
.
[
2
8
]
X
.
Li
u
,
A
.
L
i
u
,
J.
L.
C
h
e
n
,
a
n
d
G
.
Li
,
“
I
mp
a
c
t
o
f
d
e
c
o
m
p
o
s
i
t
i
o
n
o
n
t
i
me
ser
i
e
s
b
a
g
g
i
n
g
f
o
r
e
c
a
s
t
i
n
g
p
e
r
f
o
r
man
c
e
,
”
T
o
u
r
i
sm
Ma
n
a
g
e
m
e
n
t
,
v
o
l
.
9
7
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
t
o
u
r
ma
n
.
2
0
2
3
.
1
0
4
7
2
5
.
[
2
9
]
X
.
Li
,
X
.
Z
h
a
n
g
,
C
.
Z
h
a
n
g
,
a
n
d
S
.
W
a
n
g
,
“
F
o
r
e
c
a
s
t
i
n
g
t
o
u
r
i
s
m
d
e
ma
n
d
w
i
t
h
a
n
o
v
e
l
r
o
b
u
st
d
e
c
o
mp
o
s
i
t
i
o
n
a
n
d
e
n
s
e
m
b
l
e
f
r
a
mew
o
r
k
,
”
Ex
p
e
r
t
S
y
s
t
e
m
s
w
i
t
h
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
2
3
6
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
sw
a
.
2
0
2
3
.
1
2
1
3
8
8
.
[
3
0
]
L.
G
r
o
ssi
a
n
d
M
.
M
u
ss
i
n
i
,
“
S
e
a
s
o
n
a
l
i
t
y
i
n
t
o
u
r
i
st
f
l
o
w
s:
d
e
c
o
m
p
o
si
n
g
a
n
d
t
e
s
t
i
n
g
c
h
a
n
g
e
s
i
n
se
a
so
n
a
l
c
o
n
c
e
n
t
r
a
t
i
o
n
,
”
T
o
u
ri
sm
Ma
n
a
g
e
m
e
n
t
,
v
o
l
.
8
4
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
t
o
u
r
ma
n
.
2
0
2
1
.
1
0
4
2
8
9
.
[
3
1
]
V
.
C
e
r
q
u
e
i
r
a
,
L.
T
o
r
g
o
,
a
n
d
I
.
M
o
z
e
t
i
č
,
“
E
v
a
l
u
a
t
i
n
g
t
i
m
e
s
e
r
i
e
s
f
o
r
e
c
a
st
i
n
g
mo
d
e
l
s
:
a
n
e
mp
i
r
i
c
a
l
st
u
d
y
o
n
p
e
r
f
o
r
man
c
e
e
s
t
i
m
a
t
i
o
n
met
h
o
d
s,
”
Ma
c
h
i
n
e
L
e
a
r
n
i
n
g
,
v
o
l
.
1
0
9
,
n
o
.
1
1
,
p
p
.
1
9
9
7
–
2
0
2
8
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
0
9
9
4
-
0
2
0
-
0
5
9
1
0
-
7.
[
3
2
]
G
.
M
.
Lj
u
n
g
a
n
d
G
.
E.
P
.
B
o
x
,
“
O
n
a
mea
s
u
r
e
o
f
l
a
c
k
o
f
f
i
t
i
n
t
i
m
e
ser
i
e
s
m
o
d
e
l
s
,
”
B
i
o
m
e
t
r
i
k
a
,
v
o
l
.
6
5
,
n
o
.
2
,
p
p
.
2
9
7
–
3
0
3
,
1
9
7
8
,
d
o
i
:
1
0
.
1
0
9
3
/
b
i
o
m
e
t
/
6
5
.
2
.
2
9
7
.
[
3
3
]
J.
B
a
l
l
e
s
t
e
r
e
t
a
l
.
,
“
T
h
e
e
f
f
e
c
t
o
f
t
e
mp
o
r
a
l
d
a
t
a
a
g
g
r
e
g
a
t
i
o
n
t
o
a
ssess
t
h
e
i
m
p
a
c
t
o
f
c
h
a
n
g
i
n
g
t
e
m
p
e
r
a
t
u
r
e
s
i
n
E
u
r
o
p
e
:
a
n
e
p
i
d
e
mi
o
l
o
g
i
c
a
l
m
o
d
e
l
l
i
n
g
st
u
d
y
,
”
T
h
e
L
a
n
c
e
t
Re
g
i
o
n
a
l
H
e
a
l
t
h
-
Eu
r
o
p
e
,
v
o
l
.
3
6
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
l
a
n
e
p
e
.
2
0
2
3
.
1
0
0
7
7
9
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Iw
a
n
Ady
Pra
b
o
wo
re
c
e
iv
e
d
h
is
m
a
ste
r’s
d
e
g
re
e
in
In
f
o
rm
a
ti
o
n
En
g
i
n
e
e
rin
g
fro
m
Un
iv
e
rsitas
Dia
n
Nu
sw
a
n
to
r
o
,
I
n
d
o
n
e
sia
.
He
is
c
u
rre
n
tl
y
a
ffil
iate
d
with
t
h
e
In
f
o
rm
a
ti
c
s
S
tu
d
y
P
ro
g
ra
m
,
F
a
c
u
lt
y
o
f
En
g
in
e
e
ri
n
g
,
a
t
Un
iv
e
rsitas
T
ig
a
S
e
ra
n
g
k
a
i
.
His
re
se
a
rc
h
in
tere
sts
i
n
c
lu
d
e
ima
g
e
p
ro
c
e
ss
in
g
,
d
e
c
isio
n
su
p
p
o
rt
sy
ste
m
s,
c
o
m
p
u
ter v
isio
n
,
a
n
d
i
n
fo
rm
a
ti
o
n
sy
ste
m
s
in
te
g
ra
ti
o
n
.
His
wo
rk
fo
c
u
se
s
o
n
a
p
p
ly
i
n
g
c
o
m
p
u
tati
o
n
a
l
tec
h
n
iq
u
e
s
to
im
p
ro
v
e
sy
ste
m
p
e
rfo
rm
a
n
c
e
a
n
d
d
e
c
isio
n
-
m
a
k
i
n
g
p
r
o
c
e
ss
e
s
in
p
ra
c
ti
c
a
l
a
p
p
li
c
a
ti
o
n
s.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
iwa
n
a
d
y
p
@ts
u
.
a
c
.
id
o
r
iwa
n
a
d
y
p
@g
m
a
il
.
c
o
m
.
H
e
n
d
r
o
Wija
y
a
n
t
o
re
c
e
iv
e
d
h
is
m
a
ste
r’s
d
e
g
re
e
in
In
fo
rm
a
ti
c
s
En
g
i
n
e
e
rin
g
fro
m
th
e
Un
iv
e
rsitas
Isla
m
I
n
d
o
n
e
sia
,
Y
o
g
y
a
k
a
rta,
I
n
d
o
n
e
sia
.
He
is
c
u
rre
n
tl
y
a
ffil
iate
d
wit
h
th
e
In
f
o
rm
a
ti
c
s
S
tu
d
y
P
ro
g
ra
m
,
F
a
c
u
lt
y
o
f
E
n
g
in
e
e
rin
g
,
Un
i
v
e
rsitas
Ti
g
a
S
e
ra
n
g
k
a
i.
His
re
se
a
rc
h
i
n
tere
sts
i
n
c
lu
d
e
c
y
b
e
rse
c
u
rit
y
,
d
i
g
it
a
l
f
o
re
n
sic
s,
c
ry
p
t
o
g
ra
p
h
y
,
a
n
d
ste
g
a
n
o
g
ra
p
h
y
.
His
re
c
e
n
t
re
se
a
rc
h
fo
c
u
se
s
o
n
c
y
b
e
rse
c
u
rit
y
re
a
d
in
e
ss
a
n
d
p
o
l
icy
d
e
v
e
lo
p
m
e
n
t
fo
r
h
ig
h
e
r
e
d
u
c
a
ti
o
n
in
sti
tu
ti
o
n
s.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
h
e
n
d
r
o
@tsu
.
a
c
.
id
o
r
h
w.wij
a
y
a
n
to
@
g
m
a
il
.
c
o
m
.
T
e
g
u
h
S
u
s
y
a
n
to
re
c
e
iv
e
d
h
is
m
a
ste
r
’
s
d
e
g
re
e
in
Co
m
p
u
ter
S
c
ien
c
e
fro
m
Un
iv
e
rsitas
Ga
d
jah
M
a
d
a
,
I
n
d
o
n
e
sia
.
He
is
c
u
rre
n
tl
y
a
f
fil
iate
d
wit
h
th
e
in
f
o
rm
a
ti
o
n
s
y
ste
m
stu
d
y
p
r
o
g
ra
m
,
F
a
c
u
lt
y
o
f
E
n
g
i
n
e
e
rin
g
,
a
t
Un
i
v
e
rsitas
T
ig
a
S
e
ra
n
g
k
a
i.
His
re
se
a
rc
h
i
n
tere
sts
i
n
c
lu
d
e
d
a
ta
m
in
i
n
g
,
a
lg
o
rit
h
m
imp
lem
e
n
tatio
n
,
a
n
d
d
e
c
isio
n
su
p
p
o
rt
s
y
ste
m
s.
His
wo
rk
fo
c
u
se
s
o
n
th
e
a
n
a
ly
sis
a
n
d
a
p
p
li
c
a
ti
o
n
o
f
d
a
ta
m
in
in
g
a
l
g
o
r
it
h
m
s
fo
r
re
a
l
-
wo
rl
d
p
ro
b
lem
so
lv
in
g
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
teg
u
h
@ts
u
.
a
c
.
id
o
r
te
g
u
h
su
sy
a
n
t
o
@g
m
a
il
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.