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
.
5
,
Octo
b
er
2
0
2
5
,
p
p
.
3
8
8
7
~
3
8
9
6
I
SS
N:
2
2
5
2
-
8
9
3
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijai.v
14
.i
5
.
p
p
3
8
8
7
-
3
8
9
6
3887
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
i
.
ia
esco
r
e.
co
m
Accuracy
of long
sho
rt
-
ter
m memo
ry
m
o
del in
p
redi
cting Yo
Y
i
nflatio
n of
c
ities
i
n Indo
nesia
H
a
rf
ely
L
eipa
ry
,
Adi Set
ia
wa
n
M
a
s
t
e
r
o
f
D
a
t
a
S
c
i
e
n
c
e
P
r
o
g
r
a
m
,
F
a
c
u
l
t
y
o
f
S
c
i
e
n
c
e
a
n
d
M
a
t
h
e
m
a
t
i
c
s,
S
a
t
y
a
W
a
c
a
n
a
C
h
r
i
st
i
a
n
U
n
i
v
e
r
si
t
y
,
S
a
l
a
t
i
g
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
J
an
7
,
2
0
2
5
R
ev
is
ed
J
u
l
1
,
2
0
2
5
Acc
ep
ted
J
u
l
13
,
2
0
2
5
Ou
r
re
se
a
rc
h
e
v
a
lu
a
tes
t
h
e
e
ffe
c
ti
v
e
n
e
ss
o
f
th
e
l
o
n
g
s
h
o
rt
-
term
m
e
m
o
ry
(LS
TM
)
m
o
d
e
l
i
n
f
o
re
c
a
stin
g
a
n
n
u
a
l
y
e
a
r
-
on
-
y
e
a
r
(Yo
Y)
in
flati
o
n
a
c
ro
ss
8
2
c
it
ies
in
In
d
o
n
e
sia
b
a
se
d
o
n
ti
m
e
se
ries
d
a
ta
fro
m
BP
S
e
c
o
n
o
m
ic
r
e
p
o
rts
fo
r
2
0
1
4
-
2
0
2
4
.
T
h
is
st
u
d
y
tes
ts
th
e
a
c
c
u
ra
c
y
o
f
th
e
m
o
d
e
l
in
re
c
o
n
str
u
c
ti
n
g
p
a
st
in
flatio
n
p
a
tt
e
rn
s,
t
h
e
n
e
v
a
lu
a
tes
t
h
e
c
a
p
a
b
il
i
ti
e
s
a
n
d
li
m
it
a
ti
o
n
s
o
f
t
h
e
m
o
d
e
l
in
v
a
rio
u
s
u
r
b
a
n
a
re
a
c
o
n
tex
ts
with
t
h
e
ro
o
t
m
e
a
n
sq
u
a
re
e
rr
o
r
(RM
S
E),
m
e
a
n
a
b
so
lu
te
p
e
rc
e
n
tag
e
e
rro
r
(M
APE
),
a
n
d
c
o
e
fficie
n
t
o
f
d
e
te
rm
in
a
ti
o
n
(
R
2
)
m
e
tri
c
s.
Th
e
fin
d
i
n
g
s
sh
o
w
th
a
t
LS
TM
p
e
rfo
rm
s
we
ll
in
m
e
tro
p
o
li
tan
a
re
a
s
su
c
h
a
s
Ja
k
a
rta,
Ba
n
d
u
n
g
,
a
n
d
S
u
ra
b
a
y
a
wit
h
R
2
v
a
l
u
e
s
>
0
.
8
a
n
d
th
e
lo
we
st
M
APE
o
f
1
0
.
9
1
%
in
Ja
k
a
rta.
Ho
we
v
e
r,
in
sm
a
ll
c
it
ies
w
it
h
h
i
g
h
e
r
e
c
o
n
o
m
ic
v
o
lati
li
ty
su
c
h
a
s
Tan
ju
n
g
P
a
n
d
a
n
,
th
e
m
o
d
e
l
sh
o
ws
sig
n
ifi
c
a
n
t
p
re
d
ictio
n
e
rro
rs
(
R²
<
0
.
5
0
a
n
d
M
A
P
E
u
p
t
o
2
8
3
.
1
1
%
).
M
o
d
e
ra
te
p
e
rfo
rm
a
n
c
e
(0
.
5
0
≤
R²
≤0
.
8
0
)
wa
s
fo
u
n
d
in
c
it
ies
su
c
h
a
s
P
a
lem
b
a
n
g
,
S
e
m
a
ra
n
g
,
a
n
d
M
a
k
a
ss
a
r,
re
flec
ti
n
g
th
e
m
o
d
e
l'
s
a
d
a
p
ti
v
e
a
b
il
it
y
to
m
o
d
e
ra
te
in
flatio
n
p
a
tt
e
r
n
s
.
Th
e
se
re
su
lt
s
e
m
p
h
a
siz
e
th
e
imp
o
rtan
t
r
o
le
o
f
stru
c
tu
re
d
e
c
o
n
o
m
ic
d
a
ta
i
n
imp
r
o
v
i
n
g
th
e
re
li
a
b
il
it
y
o
f
p
re
d
icti
o
n
s,
s
o
t
h
a
t
th
e
p
o
li
c
y
imp
li
c
a
ti
o
n
s
o
f
t
h
is
stu
d
y
in
c
lu
d
e
th
e
u
se
o
f
t
h
e
LS
T
M
m
o
d
e
l
a
s
a
n
e
a
rly
wa
rn
in
g
sy
ste
m
b
y
fisc
a
l
a
n
d
m
o
n
e
tary
a
u
th
o
rit
ies
,
a
s
we
ll
a
s
th
e
n
e
e
d
f
o
r
a
d
a
ta
-
b
a
se
d
in
flat
io
n
c
o
n
tro
l
stra
teg
y
t
o
stre
n
g
t
h
e
n
re
g
i
o
n
a
l
a
n
d
n
a
ti
o
n
a
l
e
c
o
n
o
m
ic
re
sili
e
n
c
e
in
su
p
p
o
rti
n
g
su
sta
in
a
b
le
d
e
v
e
l
o
p
m
e
n
t
to
wa
rd
s
In
d
o
n
e
sia
Ema
s 2
0
4
5
.
K
ey
w
o
r
d
s
:
C
o
ef
f
icien
t o
f
d
eter
m
in
atio
n
I
n
f
latio
n
L
o
n
g
s
h
o
r
t
-
ter
m
m
e
m
o
r
y
M
ea
n
ab
s
o
lu
te
p
er
ce
n
tag
e
er
r
o
r
R
o
o
t
m
ea
n
s
q
u
ar
e
e
r
r
o
r
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
:
Ad
i Setiaw
an
Ma
s
ter
o
f
Data
Scien
ce
Pro
g
r
a
m
,
Facu
lty
o
f
Scien
ce
a
n
d
Ma
t
h
em
atics,
Saty
a
W
ac
an
a
C
h
r
is
tian
Un
iv
er
s
ity
Salatig
a,
I
n
d
o
n
esia
E
m
ail: a
d
i.setiawa
n
@
u
k
s
w.
ed
u
1.
I
NT
RO
D
UCT
I
O
N
I
n
f
latio
n
is
o
n
e
o
f
th
e
f
u
n
d
a
m
en
tal
m
ac
r
o
ec
o
n
o
m
ic
in
d
ica
to
r
s
to
ass
e
s
s
th
e
ec
o
n
o
m
ic
s
t
ab
ilit
y
o
f
a
co
u
n
tr
y
o
r
r
e
g
io
n
.
I
n
f
latio
n
r
e
f
lects
th
e
in
cr
ea
s
e
in
th
e
p
r
ic
e
o
f
g
o
o
d
s
an
d
s
er
v
ices
o
v
er
a
ce
r
tain
p
er
io
d
o
f
tim
e
,
wh
ich
d
ir
ec
tly
a
f
f
ec
ts
p
u
r
ch
asin
g
p
o
wer
,
f
in
an
cial
s
tab
ilit
y
,
an
d
ec
o
n
o
m
ic
g
r
o
wth
.
I
n
I
n
d
o
n
esia,
in
f
latio
n
is
an
im
p
o
r
tan
t
is
s
u
e,
esp
ec
ially
at
th
e
city
lev
el,
d
u
e
to
ec
o
n
o
m
ic
d
ec
en
tr
aliz
atio
n
,
wh
ich
ca
u
s
es
s
tr
u
ctu
r
al
h
eter
o
g
en
eity
in
t
h
e
r
eg
io
n
al
ec
o
n
o
m
y
,
f
is
ca
l
p
o
licy
,
an
d
r
esp
o
n
s
es
to
g
l
o
b
al
d
y
n
am
ics
s
u
ch
as
th
e
in
f
lu
en
ce
o
f
th
e
r
u
p
iah
e
x
ch
an
g
e
r
ate
ag
ain
s
t f
o
r
eig
n
c
u
r
r
e
n
c
ies
[
1
]
–
[
4
]
.
Acc
u
r
ate
in
f
latio
n
f
o
r
ec
asti
n
g
is
ess
en
tial
f
o
r
ef
f
ec
tiv
e
f
is
ca
l
an
d
m
o
n
etar
y
p
o
licy
m
a
n
ag
em
en
t
.
R
eliab
le
p
r
ed
ictio
n
s
en
ab
le
p
o
licy
m
ak
er
s
to
im
p
lem
en
t
s
tr
ateg
ic
m
ea
s
u
r
es
to
m
ain
tain
p
r
ice
s
tab
ilit
y
an
d
s
u
p
p
o
r
t
s
u
s
tain
ab
le
ec
o
n
o
m
ic
g
r
o
wth
.
Ad
v
an
ce
s
in
ar
tific
ial
in
tellig
en
ce
ce
r
tain
ly
p
lay
an
im
p
o
r
tan
t
r
o
le
[
5
]
.
On
e
m
eth
o
d
th
at
s
h
o
ws
g
r
ea
t
p
o
ten
tial
in
tim
e
s
er
ies
d
at
a
an
aly
s
is
s
u
ch
as
th
i
s
s
tu
d
y
is
lo
n
g
s
h
o
r
t
-
ter
m
m
em
o
r
y
(
L
STM
)
.
L
STM
is
o
n
e
o
f
th
e
ar
tific
ial
n
e
u
r
al
n
et
wo
r
k
ar
ch
itectu
r
es
d
esig
n
ed
t
o
ca
p
tu
r
e
c
o
m
p
lex
p
atter
n
s
an
d
l
o
n
g
-
ter
m
d
e
p
en
d
en
cies
in
s
eq
u
en
tial
d
ata.
R
esear
ch
b
y
Su
m
ar
jay
a
an
d
Su
s
ilawati
[
6
]
s
h
o
ws
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.
14
,
No
.
5
,
Octo
b
er
20
25
:
3
8
8
7
-
3
8
9
6
3888
s
u
cc
ess
o
f
L
STM
in
p
r
ed
ictin
g
m
o
n
th
ly
i
n
f
latio
n
in
Den
p
asar
,
with
ac
cu
r
ate
p
r
e
d
ictio
n
r
e
s
u
lts
.
Ho
wev
er
,
th
is
s
tu
d
y
o
n
l
y
co
v
er
s
o
n
e
city
a
n
d
h
as
n
o
t
c
o
n
s
id
er
ed
th
e
as
p
ec
t
o
f
s
tr
u
ctu
r
al
h
eter
o
g
e
n
ei
ty
in
o
t
h
er
r
eg
io
n
s
.
Oth
er
s
tu
d
ies
[
4
]
em
p
h
asize
th
e
r
elatio
n
s
h
ip
b
etwe
en
in
f
lat
io
n
an
d
ec
o
n
o
m
ic
g
r
o
wth
,
b
u
t
d
o
n
o
t
ex
p
l
o
r
e
th
e
r
o
le
o
f
AI
-
b
ased
m
eth
o
d
s
in
i
n
f
latio
n
p
r
ed
ictio
n
.
R
esear
ch
b
y
V
ar
g
as
[
7
]
c
o
m
p
ar
e
d
s
ev
e
r
al
m
ac
h
in
e
lear
n
in
g
m
eth
o
d
s
,
in
clu
d
in
g
L
STM
,
to
p
r
ed
ict
in
f
latio
n
in
C
o
s
ta
R
ica
.
L
STM
p
r
o
v
ed
to
b
e
o
n
e
o
f
t
h
e
b
est
p
er
f
o
r
m
in
g
m
eth
o
d
s
.
T
h
is
f
in
d
in
g
in
d
icat
es
th
e
g
r
ea
t
p
o
ten
tial
o
f
L
STM
in
in
f
latio
n
p
r
ed
ictio
n
,
alt
h
o
u
g
h
th
is
s
tu
d
y
is
lim
ited
to
th
e
C
o
s
ta
R
ican
co
n
tex
t
an
d
h
as
n
o
t
ex
p
lo
r
ed
h
eter
o
g
en
eity
ac
r
o
s
s
r
eg
io
n
s
.
Fu
r
th
er
r
esear
ch
[
2
]
ap
p
lied
v
ar
i
o
u
s
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
s
to
p
r
e
d
ict
in
f
lat
io
n
d
u
r
in
g
th
e
ec
o
n
o
m
ic
cr
is
is
in
Sri
L
an
k
a.
T
h
er
ef
o
r
e,
th
e
r
e
is
s
till
a
r
esear
ch
g
ap
i
n
p
r
ev
io
u
s
s
tu
d
ies.
Gap
s
s
u
ch
as
g
eo
g
r
ap
h
ical
d
i
f
f
er
en
ce
s
,
h
av
e
n
o
t d
is
cu
s
s
ed
th
e
in
f
latio
n
s
p
ec
if
icatio
n
s
o
f
cities in
I
n
d
o
n
esia,
m
o
d
el
ass
ess
m
en
t in
d
icato
r
s
ar
e
s
till
r
ar
e
u
s
in
g
th
e
co
ef
f
icien
t
o
f
d
eter
m
in
atio
n
(
R²
)
.
So
,
it
is
clea
r
th
at
th
e
n
o
v
elty
o
f
f
er
ed
is
to
ev
alu
ate
th
e
ac
cu
r
ac
y
o
f
th
e
L
STM
m
o
d
el
in
p
r
e
d
i
ctin
g
m
o
n
th
ly
in
f
latio
n
f
o
r
8
2
cities
in
I
n
d
o
n
esia,
wh
ich
h
as
n
ev
er
b
ee
n
d
o
n
e
co
m
p
r
eh
e
n
s
iv
ely
.
B
y
in
teg
r
ati
n
g
a
d
ata
-
d
r
iv
en
ap
p
r
o
ac
h
an
d
co
n
te
x
tu
al
a
n
aly
s
is
at
th
e
ci
ty
lev
el,
t
h
is
s
tu
d
y
m
ak
es
a
s
ig
n
if
ican
t
co
n
t
r
ib
u
ti
o
n
to
im
p
r
o
v
in
g
th
e
q
u
ality
o
f
p
r
e
d
ictio
n
s
.
T
h
e
r
esu
lts
ar
e
ex
p
ec
ted
t
o
p
r
o
v
id
e
an
in
-
d
ep
th
u
n
d
e
r
s
tan
d
in
g
o
f
th
e
in
f
latio
n
p
atter
n
s
in
r
e
g
io
n
s
o
f
I
n
d
o
n
esia,
s
u
p
p
o
r
t
d
ata
-
d
r
iv
e
n
p
o
licy
m
ak
in
g
,
a
n
d
p
r
o
m
o
te
p
r
ice
s
ta
b
ilit
y
an
d
s
u
s
tain
ab
le
ec
o
n
o
m
i
c
g
r
o
wth
.
2.
M
E
T
H
O
D
2
.
1
.
L
o
ng
s
ho
rt
-
t
er
m
m
emo
ry
T
h
e
L
STM
m
o
d
el
as
a
v
ar
ian
t
o
f
th
e
r
ec
u
r
r
en
t
n
e
u
r
al
n
etwo
r
k
(
R
NN)
,
as
s
h
o
wn
in
Fig
u
r
e
1
,
b
eg
in
s
with
d
ata
co
llectio
n
an
d
clea
n
i
n
g
[
8
]
.
I
n
f
latio
n
d
ata
f
r
o
m
v
ar
i
o
u
s
cities is
o
r
g
an
ized
,
th
en
t
h
e
clea
n
in
g
p
r
o
ce
s
s
is
ca
r
r
ied
o
u
t
b
y
r
em
o
v
in
g
ir
r
elev
an
t
co
lu
m
n
s
an
d
r
em
o
v
in
g
n
o
t
a
n
u
m
b
er
(
NaN
)
.
Fu
r
t
h
e
r
m
o
r
e,
a
lag
f
ea
t
u
r
e
is
ad
d
ed
to
in
clu
d
e
in
f
latio
n
v
alu
es
in
p
r
ev
i
o
u
s
m
o
n
th
s
as
a
p
r
ed
icto
r
,
wh
ich
h
elp
s
L
STM
u
n
d
er
s
tan
d
tem
p
o
r
al
p
atter
n
s
[
9
]
.
T
h
e
p
r
o
ce
s
s
ed
d
ata
is
th
e
n
n
o
r
m
al
ized
u
s
in
g
s
tan
d
ar
d
m
eth
o
d
s
to
e
n
s
u
r
e
th
at
all
f
ea
tu
r
es
ar
e
o
n
th
e
s
am
e
s
ca
le.
T
h
is
s
p
ee
d
s
u
p
th
e
tr
ain
in
g
p
r
o
ce
s
s
.
Af
ter
th
e
d
ata
is
r
ea
d
y
,
th
e
d
ata
is
d
iv
id
ed
in
to
two
p
a
r
ts
,
n
am
ely
t
r
ain
i
n
g
an
d
test
in
g
d
ata.
T
h
en
th
e
d
ata
d
im
e
n
s
io
n
s
ar
e
co
n
v
e
r
ted
in
to
a
th
r
ee
-
d
im
en
s
io
n
al
f
o
r
m
at
to
m
ee
t th
e
in
p
u
t n
ee
d
s
o
f
th
e
L
STM
: n
u
m
b
er
o
f
s
am
p
les,
am
o
u
n
t o
f
t
im
e,
an
d
n
u
m
b
er
o
f
f
ea
tu
r
es.
T
h
e
L
STM
m
o
d
el
is
d
esig
n
ed
with
s
ev
er
al
lay
er
s
,
s
tar
tin
g
f
r
o
m
t
h
e
in
p
u
t
lay
er
,
f
o
llo
wed
b
y
s
ev
er
al
lay
er
s
eq
u
ip
p
e
d
with
d
r
o
p
o
u
t l
ay
er
s
to
p
r
ev
e
n
t o
v
er
f
itti
n
g
,
a
n
d
en
d
in
g
with
a
d
en
s
e
lay
er
t
h
at
p
r
o
d
u
ce
s
o
u
tp
u
t
in
th
e
f
o
r
m
o
f
in
f
latio
n
p
r
ed
ic
tio
n
v
alu
es
as
o
u
tp
u
t.
T
h
e
m
o
d
el
is
tr
ain
ed
u
s
in
g
Ad
am
o
p
tim
izatio
n
an
d
m
ea
n
s
q
u
ar
ed
er
r
o
r
(
MSE
)
lo
s
s
f
u
n
ctio
n
to
m
i
n
im
ize
th
e
d
if
f
er
e
n
ce
b
etwe
en
p
r
ed
icted
an
d
a
ctu
al
v
alu
es.
Af
ter
tr
ain
in
g
is
co
m
p
lete,
th
e
m
o
d
e
l
is
ev
alu
ated
u
s
in
g
m
etr
ics
s
u
ch
as
m
ea
n
a
b
s
o
lu
te
er
r
o
r
(
M
AE
)
,
m
ea
n
a
b
s
o
lu
te
p
er
ce
n
tag
e
er
r
o
r
(
MA
PE)
,
an
d
R²
[
1
0
]
–
[
1
3
]
.
I
f
th
e
v
alid
atio
n
r
esu
lts
s
h
o
w
th
at
th
e
m
o
d
el
p
er
f
o
r
m
s
well,
th
en
th
e
m
o
d
el
is
ap
p
lied
to
th
e
tes
t
d
ata
,
an
d
th
e
p
r
ed
icted
r
esu
lts
ar
e
co
m
p
ar
ed
with
th
e
ac
tu
al
d
ata.
Ho
wev
er
,
if
th
e
m
o
d
el
d
o
es
n
o
t
p
er
f
o
r
m
well
b
ased
o
n
th
e
e
v
alu
atio
n
m
etr
ics,
h
y
p
er
p
ar
a
m
eter
tu
n
i
n
g
is
p
er
f
o
r
m
e
d
to
im
p
r
o
v
e
ac
cu
r
ac
y
.
Af
ter
tu
n
in
g
,
th
e
m
o
d
el
is
e
v
alu
ated
a
g
ai
n
.
I
f
th
er
e
is
an
im
p
r
o
v
em
e
n
t
i
n
p
er
f
o
r
m
a
n
ce
,
th
e
m
o
d
el
g
o
es
b
ac
k
to
th
e
v
alid
a
tio
n
s
tag
e
to
en
s
u
r
e
th
e
ac
cu
r
a
cy
o
f
th
e
r
esu
lts
.
On
th
e
o
th
er
h
an
d
,
if
th
e
m
o
d
el
h
as
n
o
t
im
p
r
o
v
ed
s
ig
n
i
f
ican
t
ly
,
th
e
n
ex
t
s
tep
is
to
m
a
k
e
f
u
r
th
e
r
im
p
r
o
v
e
m
en
ts
,
s
u
c
h
as
ch
an
g
in
g
th
e
p
r
ep
r
o
ce
s
s
in
g
m
eth
o
d
o
r
u
p
d
atin
g
th
e
n
u
m
b
e
r
o
f
ep
o
c
h
s
.
On
ce
th
e
b
est
m
o
d
el
is
o
b
tai
n
ed
,
th
e
p
r
o
ce
s
s
ca
n
p
r
o
ce
ed
t
o
th
e
im
p
le
m
en
tatio
n
an
d
p
o
licy
an
aly
s
is
s
tag
e.
Fig
u
r
e
1
.
R
esear
ch
f
lo
wc
h
ar
t
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
A
cc
u
r
a
cy
o
f lo
n
g
s
h
o
r
t
-
term me
mo
r
y
mo
d
el
in
p
r
ed
ictin
g
Yo
Y in
fla
tio
n
o
f c
ities
in
…
(
Ha
r
fely
Leip
a
r
y)
3889
2
.
2
.
M
o
del
v
a
lid
a
t
io
n
2
.
2
.
1
.
M
ea
n a
bs
o
lute
er
ro
r
M
A
E
is
a
m
e
t
r
ic
u
s
e
d
t
o
e
v
a
l
u
a
t
e
t
h
e
a
c
c
u
r
a
c
y
o
f
a
f
o
r
e
c
as
t
i
n
g
m
o
d
e
l
.
A
s
m
a
ll
e
r
M
A
E
v
al
u
e
i
n
d
i
c
a
t
e
s
a
h
i
g
h
e
r
l
e
v
e
l
o
f
a
c
c
u
r
a
c
y
a
n
d
s
m
a
l
le
r
a
v
e
r
a
g
e
p
r
e
d
i
c
ti
o
n
e
r
r
o
r
s
[
1
4
]
–
[
1
6
]
.
M
A
E
i
s
f
o
r
m
u
l
a
t
ed
i
n
(
1
)
:
=
1
∑
|
−
|
(
1
)
i
n
(
1
)
,
r
ep
r
esen
ts
th
e
p
r
ed
icte
d
v
alu
e
f
o
r
t
h
e
i
-
th
d
ata
p
o
i
n
t
wh
er
e
i
=1
,
2
,
…,
n
.
T
h
e
v
ar
iab
le
d
e
n
o
tes
th
e
ac
tu
al
v
alu
e
co
r
r
esp
o
n
d
in
g
to
th
e
i
-
t
h
d
ata
p
o
in
t,
with
i
ta
k
in
g
t
h
e
s
am
e
r
an
g
e.
L
astl
y
,
n
r
ef
e
r
s
to
th
e
t
o
tal
s
am
p
le
s
ize
u
s
ed
in
th
e
ca
lcu
l
atio
n
.
2
.
2
.
2
.
Ro
o
t
m
e
a
n sq
ua
re
d e
r
ro
r
R
o
o
t
m
ea
n
s
q
u
ar
e
er
r
o
r
(
R
MSE
)
is
th
e
av
er
ag
e
s
u
m
o
f
th
e
s
q
u
ar
es
o
f
th
e
er
r
o
r
s
,
an
d
ca
n
also
b
e
d
ef
in
ed
as
a
m
ea
s
u
r
e
o
f
th
e
er
r
o
r
p
r
o
d
u
ce
d
in
a
f
o
r
ec
ast
o
r
p
r
ed
ictio
n
m
o
d
el
[
1
7
]
.
A
lo
wer
v
alu
e
in
d
icate
s
a
b
etter
R
MSE
v
alu
e.
T
h
e
R
MSE
v
alu
e
ca
n
b
e
f
o
u
n
d
u
s
in
g
(
2
)
[
1
5
]
,
[
1
8
]
,
[
1
9
]
:
=
√
∑
(
−
)
2
=
1
(
2
)
i
n
(
2
)
f
o
r
r
ep
r
esen
ts
th
e
f
o
r
ec
asted
r
esu
lt
v
alu
e
(
p
r
ed
ictio
n
)
f
o
r
th
e
i
-
th
d
ata
p
o
in
t,
wh
e
r
e
i
r
an
g
es
f
r
o
m
1
to
n
.
T
h
e
v
ar
iab
le
in
d
icate
s
th
e
ac
tu
al
o
b
s
er
v
ed
v
alu
e
co
r
r
es
p
o
n
d
in
g
to
th
e
i
-
th
d
ata
p
o
in
t
with
in
th
e
s
am
e
r
an
g
e.
L
astl
y
,
n
d
en
o
tes th
e
to
tal
s
ize
o
f
th
e
s
am
p
le
u
s
ed
in
t
h
e
an
aly
s
is
.
2
.
2
.
3
.
M
ea
n
a
bs
o
lute
perc
en
t
er
ro
r
MA
PE
is
a
m
ea
s
u
r
e
th
at
s
h
o
ws
th
e
lev
el
o
f
r
elativ
e
er
r
o
r
b
y
p
r
esen
tin
g
it
in
p
er
ce
n
ta
g
e
f
o
r
m
.
I
t
s
tates
th
e
p
er
ce
n
tag
e
er
r
o
r
o
f
th
e
f
o
r
ec
ast
r
esu
lts
with
ac
tu
a
l
d
em
an
d
in
a
ce
r
tain
p
e
r
io
d
o
f
tim
e.
T
h
is
v
alu
e
in
d
icate
s
th
e
p
er
ce
n
tag
e
o
f
e
r
r
o
r
an
d
p
r
o
v
id
es
an
o
v
e
r
v
ie
w
o
f
p
r
ed
ictio
n
s
th
at
ar
e
m
a
d
e
to
o
h
ig
h
o
r
lo
w
co
m
p
ar
ed
to
th
e
ac
tu
al
d
ata
[
1
5
]
,
[
1
7
]
,
[
2
0
]
.
T
h
e
MA
PE
v
alu
e
is
f
o
u
n
d
u
s
in
g
(
3
)
.
I
n
(
3
)
d
escr
ib
ed
as
th
e
p
r
ed
icted
v
al
u
e
f
o
r
th
e
i
-
th
d
at
a
p
o
in
t,
r
ep
r
esen
ts
th
e
co
r
r
esp
o
n
d
in
g
ac
tu
al
v
alu
e
f
o
r
t
h
e
i
-
t
h
d
ata
p
o
i
n
t,
an
d
n
is
th
e
to
tal
n
u
m
b
er
o
f
d
ata
p
o
in
ts
in
th
e
s
am
p
le
[
1
9
]
,
[
2
1
]
.
=
100
∑
|
−
|
|
|
=
1
(
3
)
2
.
2
.
4
.
Co
ef
f
icient
o
f
d
et
er
m
i
na
t
io
n
T
h
e
R
2
is
a
s
tatis
tical
m
etr
ic
th
at
s
h
o
ws
h
o
w
well
a
r
e
g
r
ess
io
n
m
o
d
el
p
r
ed
icts
o
r
e
x
p
lain
s
th
e
v
ar
iab
ilit
y
o
f
th
e
tar
g
et
d
ata
f
o
r
m
u
lated
ac
co
r
d
in
g
t
o
(
4
)
.
R
2
f
o
r
m
u
la
in
(
4
)
is
th
e
s
q
u
ar
e
o
f
t
h
e
co
r
r
elatio
n
co
ef
f
icien
t
(
r
)
b
etwe
en
th
e
ac
t
u
al
v
alu
e
(
)
an
d
th
e
p
r
e
d
icted
v
alu
e
(
̂
)
u
s
ed
to
m
ea
s
u
r
e
t
h
e
e
x
ten
t
to
wh
ic
h
th
e
p
r
e
d
icted
v
al
u
e
ca
n
ex
p
lain
th
e
v
ar
ian
ce
o
f
th
e
ac
tu
al
v
a
lu
e.
Af
ter
th
at,
th
e
r
v
alu
e
is
s
q
u
ar
ed
to
o
b
tain
R
2
,
wh
ich
s
h
o
ws
th
e
p
r
o
p
o
r
tio
n
o
f
th
e
ac
t
u
al
v
alu
e
v
ar
ia
n
ce
th
a
t
ca
n
b
e
ex
p
lain
ed
b
y
t
h
e
p
r
ed
ictio
n
m
o
d
el
.
T
h
e
r
v
alu
e
(
co
r
r
elatio
n
c
o
ef
f
icien
t)
r
an
g
in
g
f
r
o
m
-
1
to
1
in
th
is
s
tu
d
y
was
n
o
t
u
s
ed
co
n
s
id
er
i
n
g
th
at
th
e
d
e
f
in
itio
n
o
f
th
e
v
alu
e
(
n
eg
ativ
e)
is
d
i
f
f
i
cu
lt
to
in
ter
p
r
et
wh
ile
R
2
wh
i
ch
r
an
g
es
f
r
o
m
0
to
1
,
wh
e
r
e
a
v
alu
e
o
f
1
m
ea
n
s
th
at
th
e
p
r
ed
ictio
n
m
o
d
el
is
f
u
lly
ab
le
to
ex
p
lain
th
e
v
ar
ia
n
c
e
o
f
th
e
ac
tu
al
v
alu
e,
wh
ile
a
v
alu
e
o
f
0
in
d
icate
s
th
at
th
e
m
o
d
el
d
o
es n
o
t e
x
p
lai
n
th
e
v
ar
ia
n
ce
in
th
e
ac
tu
al
v
al
u
e
[
1
5
]
,
[
2
1
]
–
[
2
4
]
.
2
=
(
∑
(
−
̅
)
(
−
̂
̅
)
√
∑
(
−
̅
)
2
.
∑
(
̂
−
̂
̅
)
2
)
2
(
4
)
2
.
3
.
Da
t
a
a
nd
s
co
ring
T
h
is
s
tu
d
y
u
s
es
an
n
u
al
in
f
latio
n
r
ate
d
ata
co
n
s
is
tin
g
o
f
1
1
5
r
o
ws,
i.e
s
tar
t
f
r
o
m
Dec
em
b
er
2
0
1
4
u
n
til
J
u
n
e
2
0
2
4
.
I
n
th
is
ca
s
e,
8
2
ci
ties
an
aly
ze
d
in
th
e
d
ataset
in
clu
d
es
Me
u
lab
o
h
,
B
an
d
a
Ac
eh
,
L
h
o
k
s
eu
m
awe
,
Sib
o
lg
a,
Pem
atan
g
s
ian
tar
,
Me
d
an
,
Pad
a
n
g
s
id
im
p
u
an
,
Pad
an
g
,
B
u
k
itti
n
g
g
i,
T
em
b
ilah
an
,
Pek
an
b
ar
u
,
Du
m
ai,
B
u
n
g
o
,
J
am
b
i,
Palem
b
an
g
,
L
u
b
u
k
lin
g
g
au
,
B
en
g
k
u
l
u
,
B
an
d
ar
L
am
p
u
n
g
,
Me
tr
o
,
T
an
ju
n
g
Pan
d
an
,
Pan
g
k
alp
in
an
g
,
B
atam
,
T
an
j
u
n
g
Pin
an
g
,
J
ak
ar
ta,
B
o
g
o
r
,
Su
k
ab
u
m
i,
B
an
d
u
n
g
,
C
ir
eb
o
n
,
B
ek
asi,
Dep
o
k
,
T
asik
m
alay
a,
C
ilaca
p
,
Pu
r
w
o
k
er
to
,
K
u
d
u
s
,
Su
r
ak
ar
ta,
Sem
ar
an
g
,
T
eg
al,
Yo
g
y
a
k
ar
ta,
J
em
b
er
,
B
an
y
u
wan
g
i,
Su
m
en
ep
,
Ked
i
r
i,
Ma
lan
g
,
Pro
b
o
lin
g
g
o
,
Ma
d
iu
n
,
Su
r
a
b
ay
a,
T
a
n
g
er
a
n
g
,
C
ileg
o
n
,
Ser
an
g
,
Sin
g
ar
aja
,
Den
p
asar
,
Ma
tar
am
,
B
im
a,
Ma
u
m
er
e,
Ku
p
a
n
g
,
Po
n
tian
a
k
,
Sin
g
k
awa
n
g
,
Sam
p
it,
Pala
n
g
k
a
R
ay
a,
T
a
n
ju
n
g
,
B
an
jar
m
asin
,
B
alik
p
ap
an
,
Sam
ar
in
d
a,
T
ar
a
k
an
,
Ma
n
ad
o
,
Palu
,
B
u
lu
k
u
m
b
a,
W
atam
p
o
n
e,
Ma
k
ass
ar
,
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.
14
,
No
.
5
,
Octo
b
er
20
25
:
3
8
8
7
-
3
8
9
6
3890
Par
e
-
Par
e,
Palo
p
o
,
Ken
d
ar
i,
B
au
b
au
,
Go
r
o
n
talo
,
Ma
m
u
ju
,
Am
b
o
n
,
T
u
al,
T
e
r
n
ate,
M
an
o
k
war
i,
So
r
o
n
g
,
Me
r
au
k
e,
a
n
d
J
ay
a
p
u
r
a.
Af
te
r
th
e
d
ata
is
clea
n
ed
,
n
o
r
m
al
izatio
n
is
ca
r
r
ied
o
u
t
u
s
in
g
t
h
e
s
tan
d
ar
d
izatio
n
m
eth
o
d
to
en
s
u
r
e
a
u
n
if
o
r
m
d
ata
s
ca
le,
with
th
e
f
o
r
m
u
la
in
(
5
)
wh
er
e
x
is
th
e
ac
tu
al
v
alu
e,
an
d
is
th
e
av
er
ag
e
v
alu
e
an
d
is
th
e
s
tan
d
ar
d
d
ev
i
atio
n
(
)
:
=
−
(
5
)
T
h
e
d
ataset
was
th
en
d
iv
id
ed
in
to
a
tr
ain
in
g
s
et
(
8
0
%)
an
d
a
test
s
et
(
2
0
%),
an
d
its
d
im
en
s
io
n
s
wer
e
co
n
v
er
ted
to
a
th
r
ee
-
d
im
en
s
io
n
al
f
o
r
m
at
(
n
×
t
×
f
)
,
wh
er
e
n
i
s
th
e
n
u
m
b
er
o
f
s
am
p
les,
t
is
th
e
n
u
m
b
er
o
f
lag
f
ea
tu
r
es
(
lag
tim
e)
,
an
d
f
is
th
e
n
u
m
b
er
o
f
f
ea
tu
r
es.
I
n
th
e
m
o
d
el
b
u
ild
in
g
s
tag
e,
an
L
STM
ar
ch
itectu
r
e
was
d
esig
n
ed
with
a
n
in
p
u
t
lay
e
r
to
r
ec
eiv
e
th
e
t
h
r
ee
-
d
im
e
n
s
io
n
al
d
ata,
f
o
llo
wed
b
y
m
u
lti
p
le
L
STM
lay
er
s
to
ca
p
tu
r
e
tem
p
o
r
al
p
atter
n
s
with
g
r
a
d
u
ally
d
ec
r
ea
s
in
g
u
n
its
(
2
5
6
→
1
2
8
→
6
4
)
.
A
d
r
o
p
o
u
t
lay
er
was
ad
d
e
d
to
p
r
ev
en
t
o
v
er
f
itti
n
g
,
an
d
a
d
e
n
s
e
lay
er
was
u
s
ed
to
g
e
n
er
a
te
m
o
n
th
ly
i
n
f
latio
n
p
r
ed
ictio
n
s
.
T
h
e
m
o
d
el
was
o
p
tim
ized
u
s
in
g
t
h
e
MSE
lo
s
s
f
u
n
ctio
n
a
n
d
th
e
Ad
am
alg
o
r
it
h
m
.
T
h
e
m
o
d
el
t
r
ain
in
g
p
r
o
ce
s
s
was
ca
r
r
ied
o
u
t
with
p
ar
am
eter
s
s
u
ch
as
1
0
0
ep
o
ch
s
,
a
b
atch
s
ize
o
f
1
6
,
an
d
u
s
in
g
an
ea
r
ly
s
to
p
p
i
n
g
ca
llb
ac
k
to
s
to
p
t
r
ain
in
g
if
th
e
v
alid
atio
n
p
er
f
o
r
m
an
ce
d
o
e
s
n
o
t
im
p
r
o
v
e
af
te
r
1
5
ep
o
ch
s
,
an
d
R
ed
u
ce
L
R
On
Plateau
to
ad
ap
tiv
ely
r
ed
u
ce
th
e
lear
n
in
g
r
ate.
Af
ter
tr
ain
in
g
,
th
e
m
o
d
el
was
ev
alu
ated
u
s
in
g
m
etr
ics
s
u
ch
as
MA
E
,
MA
PE,
an
d
R
2
.
T
h
e
ev
alu
atio
n
r
esu
lts
wer
e
co
m
p
ar
ed
f
o
r
ea
ch
city
,
an
d
a
p
r
ed
ictio
n
v
is
u
aliza
tio
n
in
th
e
f
o
r
m
o
f
an
ac
tu
al
v
s
p
r
ed
icted
g
r
ap
h
was
cr
ea
te
d
to
u
n
d
er
s
tan
d
th
e
m
o
d
el
p
er
f
o
r
m
a
n
ce
.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
Fig
u
r
e
2
s
h
o
ws
t
h
e
A
n
n
u
al
I
n
f
la
ti
o
n
G
r
a
p
h
f
o
r
th
e
p
er
io
d
2
0
1
5
t
o
2
0
2
4
f
o
r
f
i
v
e
c
iti
es
in
I
n
d
o
n
esi
a,
wh
i
ch
s
h
o
ws
q
u
ite
d
y
n
a
m
ic
in
f
la
ti
o
n
r
a
te
f
l
u
ct
u
ati
o
n
s
i
n
t
h
e
ar
ea
s
o
f
Me
u
la
b
o
h
,
B
a
n
d
a
Ac
eh
,
L
h
o
k
s
e
u
m
awe
,
Sib
o
l
g
a
,
a
n
d
Pe
m
a
ta
n
g
-
Si
a
n
ta
r
.
T
h
e
x
-
a
x
is
r
e
p
r
ese
n
ts
t
h
e
y
e
ar
,
w
h
il
e
t
h
e
y
-
a
x
is
s
h
o
ws
t
h
e
in
f
la
ti
o
n
r
a
te
.
E
ac
h
cit
y
is
r
e
p
r
ese
n
t
ed
b
y
a
d
if
f
er
e
n
t
c
o
l
o
r
a
n
d
m
a
r
k
e
r
,
i
n
d
ic
ati
n
g
in
f
l
ati
o
n
f
l
u
c
tu
ati
o
n
s
o
v
e
r
ti
m
e.
T
h
e
g
r
a
p
h
s
h
o
ws
m
a
r
k
e
d
v
o
la
tili
ty
,
es
p
ec
ial
ly
i
n
t
h
e
ea
r
l
y
y
e
ar
s
,
wit
h
s
h
ar
p
p
e
ak
s
a
n
d
t
r
o
u
g
h
s
,
i
n
d
i
ca
t
in
g
p
e
r
i
o
d
s
o
f
h
i
g
h
a
n
d
lo
w
i
n
f
lat
io
n
.
F
r
o
m
2
0
2
0
o
n
w
ar
d
s
,
t
h
e
r
e
h
as
b
ee
n
a
m
a
r
k
e
d
d
e
cli
n
e
f
o
l
lo
we
d
b
y
an
u
p
wa
r
d
t
r
en
d
t
h
at
p
ea
k
e
d
ar
o
u
n
d
2
0
2
2
b
e
f
o
r
e
s
t
ab
ili
zi
n
g
i
n
r
ec
en
t
y
e
ar
s
.
T
h
is
p
a
tte
r
n
s
u
g
g
ests
t
h
at
e
x
t
er
n
al
ec
o
n
o
m
ic
f
ac
t
o
r
s
,
s
u
c
h
as
g
l
o
b
al
d
is
r
u
p
ti
o
n
s
a
n
d
d
o
m
esti
c
p
o
lic
ies
,
h
a
v
e
af
f
e
ct
ed
i
n
f
lat
i
o
n
d
y
n
am
ics
d
if
f
e
r
e
n
t
ly
a
c
r
o
s
s
ci
ties
.
Fig
u
r
e
3
d
escr
ib
es
t
h
e
co
m
p
ar
is
o
n
o
f
in
f
latio
n
r
ates
b
etwe
en
Me
r
au
k
e
C
ity
an
d
J
ay
ap
u
r
a
C
ity
,
th
er
e
ar
e
th
e
last
2
cities
in
d
ata.
B
o
th
cities
s
h
o
wed
q
u
ite
s
ig
n
if
ican
t
f
lu
ctu
atio
n
s
in
in
f
latio
n
r
ates
d
u
r
in
g
th
e
p
er
io
d
.
Me
r
au
k
e
ten
d
s
to
h
a
v
e
a
h
ig
h
er
in
f
latio
n
r
ate
t
h
an
J
ay
ap
u
r
a,
esp
ec
ially
at
th
e
b
eg
in
n
in
g
o
f
th
e
o
b
s
er
v
atio
n
p
er
i
o
d
.
Ho
wev
er
,
o
v
e
r
tim
e,
th
e
d
if
f
er
en
ce
i
n
in
f
latio
n
r
ates
b
etwe
en
th
e
t
wo
cities
ten
d
s
to
n
ar
r
o
w.
T
h
er
e
ar
e
s
ev
er
al
p
ea
k
s
an
d
v
alley
s
o
f
in
f
latio
n
th
a
t
o
cc
u
r
in
b
o
th
cities,
in
d
icatin
g
s
ea
s
o
n
al
f
ac
to
r
s
o
r
ce
r
tain
ec
o
n
o
m
ic
e
v
en
ts
th
a
t a
f
f
ec
t p
r
ice
lev
els in
b
o
th
a
r
e
as.
Fig
u
r
e
2
.
An
n
u
al
i
n
f
latio
n
o
f
5
ea
r
ly
cities
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
A
cc
u
r
a
cy
o
f lo
n
g
s
h
o
r
t
-
term me
mo
r
y
mo
d
el
in
p
r
ed
ictin
g
Yo
Y in
fla
tio
n
o
f c
ities
in
…
(
Ha
r
fely
Leip
a
r
y)
3891
Fig
u
r
e
3
.
An
n
u
al
i
n
f
latio
n
o
f
th
e
last
2
cities
T
ab
le
1
r
e
f
lects
th
e
y
ea
r
ly
in
f
latio
n
r
ates
in
f
iv
e
cities
ar
e
Me
u
lab
o
h
,
B
an
d
a
Ace
h
,
L
h
o
k
s
eu
m
awe
,
Sib
o
lg
a,
an
d
Pem
atan
g
s
ian
tar
.
E
ac
h
r
o
w
in
th
e
ta
b
le
r
ep
r
esen
ts
th
e
in
f
latio
n
r
ate
f
o
r
a
ce
r
tain
p
er
io
d
th
at
is
co
n
s
is
ten
t
ac
r
o
s
s
th
e
f
iv
e
cities.
I
n
g
en
er
al,
in
f
latio
n
in
L
h
o
k
s
eu
m
awe
ten
d
s
to
b
e
h
ig
h
e
r
th
an
o
th
e
r
cities,
with
a
m
ax
im
u
m
v
alu
e
r
ea
ch
in
g
8
.
5
3
(
1
2
/0
1
/2
0
1
4
)
,
in
d
ica
tin
g
th
at
t
h
e
city
m
ay
ex
p
er
i
en
ce
g
r
e
ater
p
r
ice
p
r
ess
u
r
es o
r
m
o
r
e
s
ig
n
if
ican
t e
co
n
o
m
ic
v
o
latilit
y
th
an
o
t
h
er
c
ities
.
T
ab
le
1
.
First ele
v
en
r
o
ws o
f
d
ata
f
o
r
th
e
f
ir
s
t f
iv
e
cities an
d
s
tatis
t
ical
r
esu
lts
o
f
th
e
clea
n
ed
d
ataset
Y
o
Y
M
e
u
l
a
b
o
h
B
a
n
d
a
A
c
e
h
Lh
o
k
s
e
u
maw
e
S
i
b
o
l
g
a
P
e
mat
a
n
g
s
i
a
n
t
a
r
1
2
/
0
1
/
2
0
1
4
8
.
2
7
.
8
3
8
.
5
3
8
.
3
6
7
.
9
4
1
2
/
0
1
/
2
0
1
5
0
.
5
8
1
.
2
7
2
.
4
4
3
.
3
4
3
.
3
6
1
2
/
0
1
/
2
0
1
6
3
.
7
7
3
.
1
3
5
.
6
7
.
3
9
4
.
7
6
1
2
/
0
1
/
2
0
1
7
4
.
7
6
4
.
8
6
2
.
8
7
3
.
0
8
3
.
1
1
2
/
0
1
/
2
0
1
8
2
.
1
5
6
.
7
2
.
6
3
2
.
7
6
3
.
0
8
1
2
/
0
1
/
2
0
1
9
4
.
2
8
1
.
3
8
1
.
2
2
.
5
8
1
.
5
4
1
2
/
0
1
/
2
0
2
0
4
.
2
4
3
.
4
6
3
.
5
5
2
.
4
2
2
.
7
8
1
2
/
0
1
/
2
0
2
1
2
.
0
7
2
.
4
1
1
.
9
7
1
.
8
6
2
.
1
2
1
2
/
0
1
/
2
0
2
2
6
.
5
6
6
5
.
3
7
6
.
4
3
6
.
1
6
1
2
/
0
1
/
2
0
2
3
1
.
4
2
1
.
5
3
1
.
5
6
2
.
8
2
.
3
0
6
/
0
1
/
2
0
2
4
3
.
9
4
2
.
0
7
2
.
9
7
3
.
7
5
2
.
8
9
I
n
lin
e
with
T
ab
le
s
1
an
d
2
s
h
o
ws
y
ea
r
ly
in
f
latio
n
d
ata
in
f
iv
e
cities
in
ea
s
ter
n
I
n
d
o
n
esia,
n
am
ely
T
er
n
ate,
Ma
n
o
k
war
i,
So
r
o
n
g
,
Me
r
au
k
e,
an
d
J
ay
ap
u
r
a.
E
ac
h
r
o
w
r
ep
r
esen
ts
th
e
in
f
latio
n
r
ate
f
o
r
th
e
s
am
e
tim
e
p
er
io
d
am
o
n
g
th
e
f
iv
e
ci
ties
.
Me
r
au
k
e
C
ity
s
h
o
ws
a
co
n
s
is
ten
tly
h
ig
h
er
in
f
latio
n
r
a
te
th
an
o
th
er
cities,
with
a
p
ea
k
v
al
u
e
r
ea
ch
i
n
g
1
2
.
3
1
,
in
d
icatin
g
th
e
p
o
ten
tial
f
o
r
s
ig
n
if
ican
t
ec
o
n
o
m
ic
p
r
ess
u
r
e
in
th
e
r
e
g
io
n
.
I
n
co
n
tr
ast,
Ma
n
o
k
war
i
ten
d
s
to
h
av
e
th
e
lo
west
an
d
m
o
s
t
s
tab
le
in
f
latio
n
r
ate,
with
v
alu
es
m
o
s
tly
r
an
g
in
g
ar
o
u
n
d
5
–
6
.
Oth
er
cities,
s
u
ch
as
T
er
n
ate
an
d
So
r
o
n
g
,
h
av
e
f
lu
ctu
atin
g
in
f
latio
n
r
ates
b
u
t
ten
d
to
b
e
in
th
e
m
id
d
le
r
an
g
e
.
Me
an
wh
ile,
J
ay
ap
u
r
a
s
h
o
ws
a
m
o
r
e
v
ar
ied
p
a
tter
n
,
with
in
f
latio
n
r
ates
s
o
m
etim
es
ap
p
r
o
ac
h
in
g
th
e
h
ig
h
est v
alu
es in
t
h
is
d
ataset.
T
ab
le
2
.
Sev
en
r
o
ws o
f
t
h
e
last
5
cities o
f
th
e
clea
n
ed
d
ata
s
e
t statis
t
ics r
esu
lts
Te
r
n
a
t
e
M
a
n
o
k
w
a
r
i
S
o
r
o
n
g
M
e
r
a
u
k
e
Jay
a
p
u
r
a
9
.
3
4
5
.
7
6
.
8
3
1
2
.
3
1
7
.
9
8
8
.
2
6
5
.
6
6
7
.
2
1
1
.
8
4
5
.
7
2
8
.
1
1
5
.
3
9
6
.
8
1
1
1
.
6
5
5
.
9
6
7
.
9
2
6
.
6
4
7
.
1
1
9
.
2
5
5
.
9
9
7
.
8
3
6
7
.
0
6
9
.
4
3
7
.
8
3
8
.
6
4
5
.
3
3
6
.
6
2
9
.
0
7
6
.
8
2
8
.
2
2
6
.
1
5
8
.
9
3
8
.
3
5
8
.
1
5
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.
14
,
No
.
5
,
Octo
b
er
20
25
:
3
8
8
7
-
3
8
9
6
3892
T
h
e
p
l
o
t
in
F
ig
u
r
e
4
illu
s
tr
ates
th
e
co
m
p
ar
is
o
n
b
etwe
en
th
e
ac
tu
al
v
alu
e
a
n
d
th
e
p
r
ed
icte
d
v
alu
e
o
f
in
f
latio
n
in
T
an
ju
n
g
Pan
d
a
n
C
ity
,
wh
ich
is
th
e
city
with
th
e
lo
west
R
2
v
alu
e
am
o
n
g
o
th
e
r
cities
with
a
v
alu
e
o
f
0
.
4
8
b
ased
o
n
th
e
d
ata
u
s
ed
.
T
h
e
h
o
r
izo
n
tal
ax
is
(
x
-
ax
is
)
r
ep
r
esen
ts
th
e
tim
e
in
d
ex
o
r
a
ce
r
tain
p
er
io
d
,
wh
ile
th
e
v
er
tical
ax
is
(
y
-
ax
i
s
)
s
h
o
ws
th
e
in
f
latio
n
v
alu
e.
T
h
e
b
lu
e
lin
e
d
ep
icts
th
e
ac
tu
al
v
alu
e,
an
d
th
e
o
r
an
g
e
lin
e
s
h
o
ws
th
e
p
r
ed
ic
ted
r
esu
lts
f
r
o
m
th
e
m
o
d
el.
Fro
m
th
is
v
is
u
aliza
tio
n
,
it
ca
n
b
e
s
ee
n
th
at
th
e
p
r
ed
ictio
n
m
o
d
el
is
q
u
ite
g
o
o
d
at
ca
p
tu
r
in
g
th
e
g
e
n
er
al
p
at
ter
n
o
f
th
e
ac
tu
al
d
ata,
alth
o
u
g
h
th
er
e
a
r
e
s
o
m
e
s
tr
ik
in
g
d
if
f
er
en
ce
s
in
ce
r
tain
p
er
io
d
s
.
T
h
e
ac
tu
al
d
ata
s
h
o
ws
lar
g
er
f
l
u
ctu
atio
n
s
,
esp
ec
i
ally
in
th
e
p
e
r
io
d
ar
o
u
n
d
th
e
5
th
a
n
d
1
3
th
in
d
e
x
,
wh
er
e
th
er
e
is
a
s
h
ar
p
in
c
r
ea
s
e
in
th
e
ac
tu
al
d
ata
th
at
is
n
o
t
f
u
lly
f
o
llo
wed
b
y
th
e
p
r
ed
ictio
n
m
o
d
el.
I
n
c
o
n
tr
ast,
th
e
p
r
ed
ictio
n
ten
d
s
to
b
e
s
m
o
o
th
er
with
s
m
aller
f
lu
ctu
at
io
n
s
.
I
n
ad
d
itio
n
,
in
s
o
m
e
p
ar
ts
,
th
e
p
r
e
d
icted
v
alu
e
is
h
ig
h
er
th
an
th
e
ac
tu
al
v
al
u
e,
f
o
r
ex
am
p
le
i
n
th
e
p
e
r
io
d
ar
o
u
n
d
th
e
1
0
th
t
o
1
2
th
in
d
e
x
.
C
o
n
v
er
s
ely
,
in
th
e
f
in
al
p
er
io
d
,
th
e
ac
t
u
al
v
alu
e
d
r
o
p
s
m
o
r
e
d
r
asti
ca
lly
th
an
th
e
p
r
ed
ictio
n
.
T
h
is
d
if
f
er
en
ce
in
d
icate
s
th
at
th
e
m
o
d
el
h
as
lim
itatio
n
s
in
ca
p
tu
r
in
g
ex
t
r
em
e
v
a
r
iatio
n
s
o
r
s
p
ik
es
th
at
o
cc
u
r
in
t
h
e
ac
tu
al
d
ata.
Fig
u
r
e
4
.
R
esu
lts
o
f
ac
tu
al
d
at
a
an
aly
s
is
an
d
p
r
e
d
ictio
n
s
f
o
r
T
an
ju
n
g
Pan
d
an
C
ity
Fig
u
r
e
5
r
ep
r
esen
ts
a
co
m
p
ar
i
s
o
n
b
etwe
en
th
e
ac
tu
al
an
d
th
e
p
r
ed
icted
in
f
latio
n
v
alu
es
f
o
r
Ma
lan
g
C
ity
b
ased
o
n
th
e
g
iv
en
d
ata.
Acc
o
r
d
in
g
to
th
e
R
2
r
esu
lt,
Ma
lan
g
C
ity
h
as
th
e
h
ig
h
est
v
alu
e
o
f
all
th
e
cities,
at
0
.
9
2
.
T
h
e
h
o
r
izo
n
tal
ax
is
(
x
-
a
x
is
)
r
ep
r
esen
ts
th
e
tim
e
in
d
ex
o
r
a
ce
r
tain
p
e
r
io
d
,
wh
ile
th
e
v
er
tical
ax
is
(
y
-
ax
is
)
s
h
o
ws
th
e
in
f
latio
n
v
alu
e.
T
h
e
b
lu
e
lin
e
d
ep
icts
th
e
ac
t
u
al
d
ata,
wh
ile
th
e
o
r
an
g
e
lin
e
d
e
p
icts
th
e
p
r
ed
icted
r
esu
lts
f
r
o
m
th
e
m
o
d
el
u
s
ed
.
Fro
m
th
is
v
is
u
aliza
tio
n
,
it
ca
n
b
e
o
b
s
er
v
ed
th
at
th
e
tr
en
d
o
f
th
e
p
r
ed
icted
d
ata
f
o
llo
ws
th
e
g
en
er
al
p
atter
n
o
f
th
e
ac
tu
al
d
ata,
alth
o
u
g
h
th
er
e
ar
e
s
ig
n
if
ican
t
d
if
f
er
en
ce
s
at
ce
r
tain
p
o
in
ts
.
T
h
e
ac
tu
al
d
ata
s
h
o
ws
s
h
ar
p
er
f
lu
ctu
atio
n
s
,
esp
ec
ially
ar
o
u
n
d
th
e
1
0
th
tim
e
in
d
ex
,
wh
er
e
th
er
e
is
a
d
r
asti
c
d
ec
r
ea
s
e
in
th
e
ac
tu
al
v
alu
e,
wh
ile
th
e
p
r
ed
ictio
n
r
em
ain
s
in
a
s
m
o
o
th
er
d
ec
r
ea
s
in
g
p
atter
n
.
I
n
th
e
n
e
x
t
p
er
io
d
,
th
e
p
r
ed
ictio
n
ten
d
s
to
ap
p
r
o
ac
h
th
e
ac
tu
al
v
alu
e
,
b
u
t
s
till
s
h
o
ws
a
s
m
all
d
ev
iatio
n
.
T
h
is
p
lo
t
r
ef
lects
th
at
th
e
p
r
e
d
ictio
n
m
o
d
el
is
q
u
ite
ca
p
ab
le
o
f
ca
p
tu
r
in
g
t
h
e
g
en
er
al
p
atter
n
o
f
th
e
in
f
latio
n
tr
en
d
in
Ma
lan
g
C
ity
,
b
u
t is less
s
en
s
itiv
e
to
s
u
d
d
en
f
l
u
ctu
atio
n
s
o
r
ex
tr
em
e
c
h
an
g
es th
at
o
cc
u
r
in
t
h
e
ac
tu
al
d
ata.
T
ab
le
3
d
escr
ib
es
th
e
d
is
tr
ib
u
tio
n
o
f
cities
with
th
e
lo
we
s
t
R²
v
alu
es.
T
h
e
a
n
aly
s
is
r
e
s
u
lts
s
h
o
w
m
o
d
el'
s
p
er
f
o
r
m
an
ce
in
p
r
ed
i
ctin
g
m
o
n
th
ly
in
f
latio
n
v
ar
ie
s
ac
r
o
s
s
th
ese
f
o
u
r
cities,
wi
th
ac
cu
r
ac
y
lev
els
r
an
g
in
g
f
r
o
m
l
o
w
to
q
u
ite
g
o
o
d
.
T
an
j
u
n
g
Pan
d
an
C
ity
r
ec
o
r
d
ed
a
v
al
u
e
R
2
o
f
0
.
4
8
9
,
in
d
icatin
g
lo
w
p
er
f
o
r
m
an
ce
,
with
a
v
er
y
lar
g
e
er
r
o
r
r
ate
s
u
ch
as
MA
PE
r
e
ac
h
in
g
2
9
2
.
7
8
%.
T
h
is
in
d
icat
es
th
at
th
e
in
f
latio
n
p
atter
n
in
th
e
city
is
d
if
f
icu
lt
to
ca
p
tu
r
e
b
y
th
e
m
o
d
el,
p
o
s
s
ib
ly
d
u
e
to
f
lu
ctu
atin
g
d
ata
o
r
s
ig
n
if
ican
t
an
o
m
alies
[
2
5
]
.
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
A
cc
u
r
a
cy
o
f lo
n
g
s
h
o
r
t
-
term me
mo
r
y
mo
d
el
in
p
r
ed
ictin
g
Yo
Y in
fla
tio
n
o
f c
ities
in
…
(
Ha
r
fely
Leip
a
r
y)
3893
Fig
u
r
e
5
.
R
esu
lts
o
f
ac
tu
al
d
at
a
an
aly
s
is
an
d
p
r
e
d
ictio
n
s
f
o
r
Ma
lan
g
C
ity
T
ab
le
3
.
Dis
tr
ib
u
tio
n
o
f
cities with
th
e
lo
west
R²
v
alu
es
(
R
2
≤
0
.
6
0
)
C
i
t
y
M
A
P
E
R²
Ta
n
j
u
n
g
P
a
n
d
a
n
2
8
3
.
1
1
0
.
4
9
M
a
n
a
d
o
2
9
.
3
0
0
.
5
6
M
a
m
u
j
u
3
7
.
8
6
0
.
5
8
Te
r
n
a
t
e
1
7
.
4
1
0
.
5
8
M
a
n
o
k
w
a
r
i
1
9
.
1
0
0
.
6
0
T
ab
le
4
s
h
o
ws
th
e
p
e
r
f
o
r
m
a
n
ce
o
f
L
STM
in
p
r
ed
ictin
g
m
o
n
th
ly
in
f
latio
n
r
ates
o
f
8
2
cities
in
I
n
d
o
n
esia
u
s
in
g
f
o
u
r
m
etr
ics
MSE
,
MA
E
,
MA
PE,
an
d
R
².
T
h
e
m
o
d
el
p
er
f
o
r
m
s
well
in
cities
s
u
ch
as
T
asik
m
alay
a,
Ma
lan
g
,
an
d
Palan
g
k
a
R
ay
a,
with
R²
v
alu
es
r
a
n
g
in
g
f
r
o
m
0
.
8
9
to
0
.
9
0
an
d
MA
PE
b
elo
w
3
0
%,
h
ig
h
lig
h
tin
g
its
ab
ilit
y
to
ca
p
t
u
r
e
s
tab
le
in
f
latio
n
p
atter
n
s
.
Fo
r
ex
a
m
p
le,
Ma
lan
g
ac
h
ie
v
es a
n
MSE
o
f
0
.
8
3
a
n
d
MA
E
o
f
0
.
7
1
r
ef
lectin
g
ac
cu
r
ate
p
r
ed
ictio
n
s
.
I
n
co
n
tr
ast,
cities
s
u
ch
as
T
an
j
u
n
g
Pan
d
an
(
R²
=
0
.
4
8
,
MA
PE=
2
9
2
.
7
8
%)
an
d
Ma
n
a
d
o
(
R²
=0
.
5
6
,
MA
PE=
2
1
.
2
2
%)
s
h
o
w
p
o
o
r
p
er
f
o
r
m
an
ce
,
p
o
s
s
ib
ly
d
u
e
to
d
ata
v
o
latilit
y
o
r
an
o
m
alies.
Me
tr
o
p
o
litan
cities
s
u
ch
as
J
ak
ar
ta
(
R²
=0
.
7
5
)
,
B
an
d
u
n
g
(
R²
=0
.
7
8
)
,
a
n
d
Su
r
a
b
ay
a
(
R²
=0
.
8
9
)
p
er
f
o
r
m
e
d
b
etter
,
b
en
ef
itin
g
f
r
o
m
s
tr
u
ctu
r
e
d
ec
o
n
o
m
ic
s
y
s
tem
s
an
d
co
n
s
is
ten
t
d
ata.
Ho
wev
er
,
s
m
aller
cities
s
u
ch
as
So
r
o
n
g
(
R²
=0
.
6
8
,
MA
PE=
3
8
.
6
0
%)
a
n
d
Go
r
o
n
talo
(
R²
=0
.
6
7
)
f
ac
ed
ch
allen
g
es
d
u
e
to
ir
r
eg
u
lar
p
atter
n
s
o
r
u
n
s
tab
le
ec
o
n
o
m
ic
co
n
d
itio
n
s
.
T
h
is
s
tu
d
y
em
p
h
asizes
th
e
im
p
o
r
tan
ce
o
f
ad
ap
tiv
e
m
o
d
els
f
o
r
m
o
r
e
ac
cu
r
ate
in
f
latio
n
p
r
ed
ictio
n
s
ac
r
o
s
s
r
eg
io
n
s
,
s
u
p
p
o
r
tin
g
b
etter
ec
o
n
o
m
i
c
p
o
licy
p
lan
n
in
g
[
2
3
]
,
[
2
6
]
–
[
2
8
]
.
T
h
e
r
esu
lts
s
h
o
w
th
at
th
e
L
STM
m
o
d
el
p
r
o
d
u
ce
s
ac
cu
r
ate
p
r
ed
ictio
n
s
in
lar
g
e
cities
s
u
ch
a
s
J
ak
ar
ta,
B
an
d
u
n
g
,
an
d
Su
r
ab
a
y
a
with
a
R²
ab
o
v
e
0
.
8
an
d
a
l
o
w
er
r
o
r
r
ate.
Fo
r
ex
a
m
p
le,
J
a
k
ar
ta
h
as
a
MA
PE
o
f
1
0
.
9
1
%,
r
ef
lectin
g
a
n
ac
c
u
r
ate
p
r
ed
ictio
n
r
ate.
Ho
wev
er
,
in
s
m
all
cities
s
u
ch
as
T
an
ju
n
g
Pan
d
a
n
,
th
e
p
er
f
o
r
m
an
ce
o
f
th
is
m
o
d
el
is
lo
wer
,
with
R²
b
elo
w
0
.
5
a
n
d
MA
PE
o
f
2
8
3
.
1
1
%.
Sev
e
r
al
cities,
in
clu
d
in
g
T
asik
m
alay
a
(
R²
=0
.
9
0
)
,
Ma
lan
g
(
R²
=0
.
9
0
)
,
an
d
Palan
g
k
a
-
R
ay
a
(
R²
=0
.
8
9
3
)
,
r
ec
o
r
d
e
d
g
o
o
d
p
er
f
o
r
m
an
ce
with
MA
PE
b
elo
w
3
0
%,
in
d
icatin
g
th
e
m
o
d
el'
s
ab
ilit
y
to
ca
p
t
u
r
e
s
tr
u
ctu
r
ed
i
n
f
latio
n
p
atter
n
s
ef
f
ec
tiv
ely
.
T
h
is
v
ar
iatio
n
is
ca
u
s
ed
b
y
d
if
f
er
e
n
ce
s
in
ec
o
n
o
m
ic
s
tab
ilit
y
,
d
a
ta
co
n
s
is
ten
cy
,
an
d
o
th
e
r
ex
te
r
n
al
f
ac
to
r
s
.
L
ar
g
e
cities
b
en
ef
it
f
r
o
m
s
tab
le
ec
o
n
o
m
ic
co
n
d
itio
n
s
an
d
s
tr
u
ct
u
r
ed
in
f
latio
n
tr
e
n
d
s
,
wh
ich
al
lo
w
th
e
m
o
d
el
to
ca
p
tu
r
e
p
atter
n
s
with
h
ig
h
ac
cu
r
ac
y
.
I
n
co
n
tr
ast,
cities
s
u
ch
as
T
an
ju
n
g
Pan
d
an
e
x
p
er
ie
n
ce
h
ig
h
e
r
v
o
latilit
y
d
u
e
to
ir
r
eg
u
lar
ec
o
n
o
m
ic
ac
t
iv
ities
,
m
ak
in
g
in
f
latio
n
tr
en
d
s
m
o
r
e
d
if
f
icu
lt
to
p
r
e
d
ict.
T
h
e
L
STM
m
o
d
el
is
ef
f
ec
tiv
e
f
o
r
ar
ea
s
with
s
tab
le
d
ata
p
atter
n
s
b
u
t
r
eq
u
ir
es
a
d
d
itio
n
al
ap
p
r
o
ac
h
es
in
ar
ea
s
with
f
lu
ctu
atin
g
d
ata
.
R
ec
o
m
m
en
d
atio
n
s
f
o
r
d
ev
elo
p
m
en
t
in
clu
d
e
th
e
in
teg
r
atio
n
o
f
m
o
r
e
s
p
ec
if
ic
ex
o
g
en
o
u
s
v
ar
iab
les
s
u
ch
as
co
m
m
o
d
ity
p
r
ices,
h
y
p
er
p
ar
a
m
eter
ad
ju
s
tm
en
ts
s
o
th
at
it
is
ex
p
ec
ted
to
s
u
p
p
o
r
t
r
esp
o
n
s
iv
e
ec
o
n
o
m
ic
p
o
licies
b
ased
o
n
lo
ca
l c
h
ar
ac
ter
is
tics
.
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.
14
,
No
.
5
,
Octo
b
er
20
25
:
3
8
8
7
-
3
8
9
6
3894
T
ab
le
4
.
Fin
al
r
esu
lts
o
f
m
o
d
el
ev
alu
atio
n
f
o
r
ea
c
h
city
C
i
t
y
M
S
E
M
A
E
M
A
P
E
R
2
C
i
t
y
M
S
E
M
A
E
M
A
P
E
R
2
M
e
u
l
a
b
o
h
3
.
1
7
1
.
3
8
3
3
.
2
2
0
.
7
6
K
e
d
i
r
i
1
.
9
5
1
.
1
1
2
5
.
9
4
0
.
8
3
B
a
n
d
a
A
c
e
h
6
.
3
1
1
.
6
9
4
3
.
2
9
0
.
7
3
M
a
l
a
n
g
1
.
5
0
0
.
8
8
1
9
.
3
9
0
.
9
0
Lh
o
k
s
e
u
maw
e
1
.
1
8
0
.
9
2
3
0
.
7
7
0
.
6
8
P
r
o
b
o
l
i
n
g
g
o
1
.
5
3
0
.
9
8
2
2
.
1
6
0
.
8
2
S
i
b
o
l
g
a
0
.
8
3
0
.
7
4
1
9
.
2
4
0
.
7
2
M
a
d
i
u
n
0
.
2
6
0
.
4
2
1
4
.
6
1
0
.
8
3
P
e
mat
a
n
g
s
i
a
n
t
a
r
1
.
1
5
0
.
9
2
2
6
.
2
8
0
.
8
0
S
u
r
a
b
a
y
a
2
.
3
6
1
.
2
1
2
3
.
7
5
0
.
8
9
M
e
d
a
n
1
.
8
4
1
.
0
7
3
4
.
1
4
0
.
7
2
Ta
n
g
e
r
a
n
g
0
.
3
9
0
.
5
6
1
8
.
1
3
0
.
7
3
P
a
d
a
n
g
si
d
i
mp
u
a
n
1
.
2
7
0
.
9
1
2
0
.
1
6
0
.
7
5
C
i
l
e
g
o
n
0
.
3
3
0
.
4
7
1
3
.
3
7
0
.
8
3
P
a
d
a
n
g
2
.
8
2
1
.
3
6
3
1
.
9
4
0
.
8
2
S
e
r
a
n
g
1
.
1
3
0
.
9
4
2
6
.
3
9
0
.
8
4
B
u
k
i
t
t
i
n
g
g
i
2
.
9
7
1
.
4
6
4
5
.
4
6
0
.
8
1
S
i
n
g
a
r
a
j
a
1
.
5
6
1
.
0
9
3
1
.
4
9
0
.
6
7
Te
mb
i
l
a
h
a
n
0
.
5
7
0
.
6
1
2
6
.
5
3
0
.
6
3
D
e
n
p
a
sar
2
.
8
4
1
.
2
0
2
4
.
2
6
0
.
8
9
P
e
k
a
n
b
a
r
u
0
.
6
3
0
.
6
3
2
1
.
5
0
0
.
8
2
M
a
t
a
r
a
m
2
.
2
5
1
.
1
1
2
5
.
6
6
0
.
8
6
D
u
ma
i
1
.
0
9
0
.
8
2
1
9
.
4
4
0
.
7
9
B
i
m
a
0
.
8
5
0
.
6
9
2
1
.
5
6
0
.
7
8
B
u
n
g
o
2
.
6
9
1
.
3
6
4
8
.
0
9
0
.
8
0
M
a
u
mer
e
1
0
.
0
7
2
.
6
8
6
7
.
2
5
0
.
7
5
Jamb
i
2
.
4
0
1
.
2
3
3
8
.
9
3
0
.
6
6
K
u
p
a
n
g
2
.
5
4
1
.
1
8
3
0
.
5
2
0
.
8
5
P
a
l
e
m
b
a
n
g
1
.
1
2
0
.
8
2
2
2
.
2
2
0
.
8
5
P
o
n
t
i
a
n
a
k
1
.
3
7
0
.
9
6
3
0
.
9
6
0
.
7
8
Lu
b
u
k
l
i
n
g
g
a
u
0
.
8
4
0
.
7
5
2
5
.
2
0
0
.
8
0
S
i
n
g
k
a
w
a
n
g
0
.
8
2
0
.
7
5
2
5
.
6
8
0
.
8
0
B
e
n
g
k
u
l
u
0
.
9
6
0
.
8
3
2
1
.
1
9
0
.
7
3
S
a
mp
i
t
0
.
4
6
0
.
5
3
1
6
.
9
4
0
.
8
1
B
a
n
d
a
r
La
mp
u
n
g
0
.
6
8
0
.
6
4
1
7
.
3
9
0
.
8
1
P
a
l
a
n
g
k
a
R
a
y
a
1
.
3
9
0
.
8
8
1
9
.
2
8
0
.
8
9
M
e
t
r
o
1
.
3
3
0
.
9
0
2
4
.
3
2
0
.
7
5
Ta
n
j
u
n
g
0
.
6
4
0
.
6
5
2
3
.
3
1
0
.
7
3
Ta
n
j
u
n
g
P
a
n
d
a
n
3
.
0
4
1
.
4
3
2
8
3
.
1
1
0
.
4
9
B
a
n
j
a
r
m
a
si
n
1
.
2
5
0
.
9
1
2
3
.
2
7
0
.
7
8
P
a
n
g
k
a
l
p
i
n
a
n
g
2
.
6
3
1
.
2
1
3
9
.
4
9
0
.
8
6
B
a
l
i
k
p
a
p
a
n
0
.
5
3
0
.
5
2
1
1
.
5
4
0
.
7
4
B
a
t
a
m
0
.
9
9
0
.
8
2
2
4
.
1
2
0
.
8
2
S
a
mari
n
d
a
0
.
4
3
0
.
5
6
1
4
.
6
7
0
.
8
5
Ta
n
j
u
n
g
P
i
n
a
n
g
1
.
2
3
0
.
9
0
2
9
.
9
6
0
.
5
8
Ta
r
a
k
a
n
0
.
4
5
0
.
5
5
2
1
.
1
6
0
.
7
5
Jak
a
r
t
a
0
.
1
4
0
.
2
7
1
0
.
9
1
0
.
7
6
M
a
n
a
d
o
0
.
8
9
0
.
7
0
2
9
.
3
0
0
.
5
6
B
o
g
o
r
0
.
3
6
0
.
4
9
1
1
.
5
8
0
.
7
8
P
a
l
u
0
.
2
3
0
.
4
0
1
2
.
4
3
0
.
6
1
S
u
k
a
b
u
m
i
0
.
4
7
0
.
6
0
1
5
.
2
9
0
.
8
3
B
u
l
u
k
u
mb
a
0
.
2
9
0
.
4
5
1
4
.
7
6
0
.
7
6
B
a
n
d
u
n
g
2
.
6
0
1
.
2
2
4
6
.
1
4
0
.
7
8
W
a
t
a
mp
o
n
e
0
.
3
4
0
.
4
3
1
6
.
3
5
0
.
8
0
C
i
r
e
b
o
n
0
.
9
2
0
.
8
3
2
2
.
3
1
0
.
7
7
M
a
k
a
ss
a
r
0
.
8
9
0
.
7
8
2
0
.
9
0
0
.
8
3
B
e
k
a
s
i
1
.
0
1
0
.
8
8
2
0
.
6
9
0
.
7
3
P
a
r
e
-
P
a
r
e
1
.
4
3
0
.
9
7
2
6
.
0
5
0
.
7
4
D
e
p
o
k
2
.
1
2
1
.
0
5
2
3
.
3
2
0
.
7
8
P
a
l
o
p
o
0
.
9
2
0
.
7
7
2
7
.
6
9
0
.
7
7
Ta
si
k
ma
l
a
y
a
1
.
1
9
0
.
8
3
1
9
.
0
8
0
.
9
0
K
e
n
d
a
r
i
2
.
5
5
1
.
3
1
2
8
.
5
8
0
.
7
3
C
i
l
a
c
a
p
3
.
0
0
1
.
2
0
2
3
.
7
3
0
.
8
6
B
a
u
b
a
u
3
.
0
0
1
.
1
7
2
1
.
0
4
0
.
7
0
P
u
r
w
o
k
e
r
t
o
2
.
5
0
1
.
0
8
2
1
.
9
4
0
.
8
2
G
o
r
o
n
t
a
l
o
1
.
1
4
0
.
9
4
3
4
.
1
2
0
.
6
7
K
u
d
u
s
1
.
5
2
0
.
8
8
1
7
.
9
7
0
.
8
4
M
a
m
u
j
u
0
.
8
9
0
.
7
7
3
7
.
8
6
0
.
5
8
S
u
r
a
k
a
r
t
a
2
.
4
3
1
.
1
3
2
1
.
7
5
0
.
8
9
A
mb
o
n
1
.
6
4
1
.
0
3
2
0
.
3
7
0
.
7
4
S
e
mara
n
g
0
.
7
0
0
.
6
7
1
8
.
0
7
0
.
7
7
Tu
a
l
1
.
0
5
0
.
7
4
1
6
.
9
9
0
.
7
2
Te
g
a
l
0
.
9
8
0
.
8
2
2
0
.
0
4
0
.
8
6
Te
r
n
a
t
e
1
.
2
4
0
.
7
8
1
7
.
4
1
0
.
5
8
Y
o
g
y
a
k
a
r
t
a
2
.
4
4
1
.
1
5
2
2
.
1
0
0
.
8
2
M
a
n
o
k
w
a
r
i
0
.
9
1
0
.
7
8
1
9
.
1
0
0
.
6
0
Jemb
e
r
5
.
9
3
1
.
7
7
3
2
.
4
8
0
.
8
1
S
o
r
o
n
g
0
.
6
9
0
.
7
1
3
7
.
6
4
0
.
6
8
B
a
n
y
u
w
a
n
g
i
2
.
8
6
1
.
2
3
2
5
.
1
1
0
.
6
7
M
e
r
a
u
k
e
0
.
7
6
0
.
6
5
1
8
.
1
7
0
.
6
6
S
u
me
n
e
p
3
.
8
0
1
.
6
6
2
9
.
4
6
0
.
8
5
Jay
a
p
u
r
a
0
.
3
3
0
.
4
5
1
6
.
5
6
0
.
7
7
4.
CO
NCLU
SI
O
N
T
h
is
s
tu
d
y
d
escr
ib
es
h
o
w
e
f
f
e
ctiv
e
th
e
L
STM
m
o
d
el
is
at
p
r
ed
ictin
g
in
f
latio
n
in
v
ar
i
o
u
s
I
n
d
o
n
esian
cities,
esp
ec
ially
in
ar
ea
s
w
it
h
s
tab
le
in
f
latio
n
tr
en
d
s
,
s
u
c
h
as
J
ak
ar
ta,
B
an
d
u
n
g
,
Su
r
a
b
ay
a,
Ma
lan
g
,
a
n
d
T
asik
m
alay
a
(
R²
>0
.
8
0
)
.
Ho
w
ev
er
,
th
e
m
o
d
el
ac
cu
r
ac
y
d
e
cr
ea
s
es
s
ig
n
if
ican
tly
in
cities
ex
p
er
ien
ci
n
g
h
ig
h
ec
o
n
o
m
ic
f
lu
ctu
atio
n
s
s
u
ch
as
T
an
ju
n
g
Pan
d
a
n
,
So
r
o
n
g
,
an
d
Go
r
o
n
talo
(
R²
<0
.
5
0
)
wh
ich
is
m
o
s
tly
ca
u
s
ed
b
y
v
ar
iatio
n
s
in
l
o
ca
l
ec
o
n
o
m
ic
c
o
n
d
itio
n
s
a
n
d
s
ea
s
o
n
al
i
n
f
lu
en
ce
s
.
C
ities
with
m
ed
iu
m
p
r
e
d
i
ctio
n
p
er
f
o
r
m
a
n
ce
(
0
.
5
0
≤
R
2
≤
0
.
8
0
)
s
u
ch
as
Palem
b
an
g
,
Sem
ar
an
g
,
Ma
k
asar
,
an
d
s
ev
er
al
o
th
er
ar
ea
s
s
h
o
w
th
at
th
e
L
STM
m
o
d
el
is
ad
ap
tiv
e
in
ca
p
tu
r
i
n
g
ex
tr
e
m
e
in
f
latio
n
p
atter
n
s
alth
o
u
g
h
im
p
r
o
v
em
e
n
ts
ar
e
n
ee
d
e
d
f
o
r
p
r
ed
ictio
n
ac
c
u
r
ac
y
.
T
h
e
d
if
f
er
en
ce
in
p
e
r
f
o
r
m
an
ce
s
h
o
ws
th
e
im
p
o
r
tan
ce
o
f
im
p
r
o
v
in
g
th
e
q
u
ality
o
f
in
p
u
t
d
ata,
esp
ec
ially
th
r
o
u
g
h
m
o
r
e
r
ele
v
an
t
f
ea
tu
r
e
s
elec
tio
n
,
o
u
tlier
d
etec
tio
n
an
d
h
an
d
lin
g
,
an
d
m
o
r
e
co
m
p
r
e
h
en
s
iv
e
in
teg
r
atio
n
o
f
ex
ter
n
al
ec
o
n
o
m
ic
v
ar
iab
l
es
s
u
ch
as
co
m
m
o
d
ity
p
r
ices
,
u
n
em
p
lo
y
m
en
t
r
ates,
in
ter
est
r
ates,
an
d
f
is
ca
l
p
o
licies.
T
h
is
m
o
d
el
ca
n
b
e
u
s
ed
as
an
ea
r
ly
war
n
in
g
s
y
s
tem
to
ass
is
t
B
an
k
I
n
d
o
n
esia
an
d
lo
ca
l
g
o
v
e
r
n
m
e
n
ts
in
d
ir
ec
tin
g
p
r
ice
s
tab
ilizatio
n
an
d
in
f
latio
n
c
o
n
tr
o
l
p
o
l
icies.
C
itie
s
with
h
ig
h
v
o
lat
ilit
y
r
eq
u
ir
e
r
a
p
id
in
ter
v
en
tio
n
,
s
u
ch
as
s
tr
en
g
th
en
in
g
lo
g
is
tics
d
is
tr
ib
u
tio
n
an
d
s
tab
ilizin
g
co
m
m
o
d
ity
p
r
ice
s
.
I
n
co
n
tr
ast,
cities
with
s
tab
le
in
f
latio
n
ca
n
f
o
c
u
s
p
o
licies
o
n
in
f
r
astru
ctu
r
e
d
ev
elo
p
m
en
t
an
d
lo
n
g
-
ter
m
in
v
estme
n
t
p
lan
n
in
g
.
W
ith
th
e
r
esu
lts
o
f
th
is
s
tu
d
y
,
it
is
h
o
p
e
d
th
at
it
ca
n
b
e
in
teg
r
ated
i
n
to
I
n
d
o
n
esia's
n
atio
n
al
in
f
latio
n
m
o
n
ito
r
in
g
s
y
s
tem
as
a
s
tr
o
n
g
an
d
ac
cu
r
ate
d
atab
ase
f
o
r
s
tate
in
s
titu
tio
n
s
in
d
esig
n
in
g
tar
g
eted
m
o
n
etar
y
an
d
f
is
ca
l p
o
licies s
o
th
at
th
ey
ca
n
h
av
e
an
im
p
ac
t.
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
.
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
A
cc
u
r
a
cy
o
f lo
n
g
s
h
o
r
t
-
term me
mo
r
y
mo
d
el
in
p
r
ed
ictin
g
Yo
Y in
fla
tio
n
o
f c
ities
in
…
(
Ha
r
fely
Leip
a
r
y)
3895
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
T
h
is
jo
u
r
n
al
u
s
es
th
e
C
o
n
t
r
ib
u
to
r
R
o
les
T
a
x
o
n
o
m
y
(
C
R
ed
iT)
to
r
ec
o
g
n
ize
in
d
iv
i
d
u
al
au
th
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
th
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
llab
o
r
atio
n
.
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
Har
f
ely
L
eip
ar
y
✓
✓
✓
✓
✓
✓
✓
✓
Ad
i Setiaw
an
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
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
d
ec
lar
e
t
h
at
th
er
e
ar
e
n
o
k
n
o
wn
c
o
n
f
licts
o
f
in
ter
est
r
eg
ar
d
i
n
g
th
e
p
u
b
licatio
n
o
f
t
h
is
p
ap
er
.
All a
u
th
o
r
ac
tiv
ities
wer
e
co
n
d
u
cted
in
d
ep
en
d
en
tly
f
o
r
ac
ad
em
ic
an
d
s
cien
tific
p
u
r
p
o
s
es.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
a
t
a
s
u
p
p
o
r
t
s
th
i
s
s
t
u
d
y
is
p
u
b
l
i
cly
a
c
c
e
s
s
i
b
le
i
n
G
itH
u
b
a
t
h
t
t
p
s
:/
/
g
i
t
h
u
b
.
c
o
m
/
h
a
r
f
e
l
y
l
e
i
p
ar
y
/
I
n
d
o
n
e
s
i
a
-
I
n
f
l
a
t
i
o
n
-
D
at
a
s
e
t
/b
l
o
b
/
m
a
i
n
/
y
o
y
_
I
n
f
l
a
t
i
o
n
_
d
a
t
a
s
e
t
_
I
n
d
o
n
e
s
i
a
.
cs
v
.
RE
F
E
R
E
NC
E
S
[
1
]
H
.
A
g
i
n
t
a
,
“
S
p
a
t
i
o
t
e
mp
o
r
a
l
a
n
a
l
y
s
i
s
o
f
r
e
g
i
o
n
a
l
i
n
f
l
a
t
i
o
n
i
n
a
n
e
m
e
r
g
i
n
g
c
o
u
n
t
r
y
:
t
h
e
c
a
se
o
f
I
n
d
o
n
e
s
i
a
,
”
Re
g
i
o
n
a
l
S
c
i
e
n
c
e
P
o
l
i
c
y
a
n
d
Pra
c
t
i
c
e
,
v
o
l
.
1
4
,
n
o
.
3
,
p
p
.
6
6
7
–
6
8
8
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
1
1
/
r
s
p
3
.
1
2
5
3
9
.
[
2
]
A
.
S
.
A
.
R
a
j
,
L.
K
u
m
a
r
a
sa
n
k
a
r
a
l
i
n
g
a
m,
M
.
B
a
l
a
m
u
r
u
g
a
n
,
B
.
M
a
h
e
sw
a
r
i
,
J
.
G
o
w
r
i
,
a
n
d
A
.
D
u
t
t
a
,
“
F
o
r
e
c
a
st
i
n
g
t
h
e
e
c
o
n
o
m
i
c
c
r
i
s
i
s
o
f
S
r
i
L
a
n
k
a
:
a
p
p
l
i
c
a
t
i
o
n
o
f
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms
f
o
r
t
i
me
s
e
r
i
e
s
d
a
t
a
,
”
Pr
o
c
e
d
i
a
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
2
3
5
,
p
p
.
1
0
8
7
–
1
0
9
6
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
r
o
c
s.
2
0
2
4
.
0
4
.
1
0
3
.
[
3
]
V
.
F
i
b
r
i
y
a
n
i
,
N
.
C
h
a
m
i
d
a
h
,
a
n
d
T.
S
a
i
f
u
d
i
n
,
“
Es
t
i
m
a
t
i
n
g
t
i
m
e
seri
e
s
se
mi
p
a
r
a
me
t
r
i
c
r
e
g
r
e
ssi
o
n
m
o
d
e
l
u
si
n
g
l
o
c
a
l
p
o
l
y
n
o
mi
a
l
e
st
i
mat
o
r
f
o
r
p
r
e
d
i
c
t
i
n
g
i
n
f
l
a
t
i
o
n
r
a
t
e
i
n
I
n
d
o
n
e
si
a
,
”
J
o
u
r
n
a
l
o
f
K
i
n
g
S
a
u
d
U
n
i
v
e
rsi
t
y
-
S
c
i
e
n
c
e
,
v
o
l
.
3
6
,
n
o
.
1
1
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
k
s
u
s.
2
0
2
4
.
1
0
3
5
4
9
.
[
4
]
N
.
S
e
p
t
r
i
l
a
a
n
d
E.
P
.
K
u
r
n
i
a
si
h
,
“
T
h
e
e
f
f
e
c
t
o
f
i
n
f
l
a
t
i
o
n
a
n
d
e
c
o
n
o
mi
c
g
r
o
w
t
h
o
n
u
n
e
mp
l
o
y
m
e
n
t
r
a
t
e
i
n
A
sea
n
c
o
u
n
t
r
i
e
s,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
Bu
s
i
n
e
ss,
T
e
c
h
n
o
l
o
g
y
a
n
d
O
rg
a
n
i
z
a
t
i
o
n
a
l
B
e
h
a
v
i
o
r
(
I
J
BTO
B)
,
v
o
l
.
2
,
n
o
.
6
,
p
p
.
5
8
0
–
5
9
4
,
2
0
2
2
,
d
o
i
:
1
0
.
5
2
2
1
8
/
i
j
b
t
o
b
.
v
2
i
6
.
2
2
6
.
[
5
]
M
.
Ta
o
,
“
D
i
g
i
t
a
l
b
r
a
i
n
s,
g
r
e
e
n
g
a
i
n
s:
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
’
s
p
a
t
h
t
o
s
u
st
a
i
n
a
b
l
e
t
r
a
n
sf
o
r
m
a
t
i
o
n
,
”
J
o
u
rn
a
l
o
f
E
n
v
i
ro
n
m
e
n
t
a
l
Ma
n
a
g
e
m
e
n
t
,
v
o
l
.
3
7
0
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
e
n
v
m
a
n
.
2
0
2
4
.
1
2
2
6
7
9
.
[
6
]
I
.
W
.
S
u
m
a
r
j
a
y
a
a
n
d
M
.
S
u
si
l
a
w
a
t
i
,
“
F
o
r
e
c
a
st
i
n
g
mo
n
t
h
l
y
i
n
f
l
a
t
i
o
n
r
a
t
e
i
n
D
e
n
p
a
s
a
r
u
si
n
g
l
o
n
g
s
h
o
r
t
-
t
e
r
m
memo
r
y
,
”
J
u
r
n
a
l
Ma
t
e
m
a
t
i
k
a
,
v
o
l
.
1
3
,
n
o
.
1
,
p
p
.
1
1
–
2
4
,
2
0
2
3
.
[
7
]
A
.
R
.
-
v
a
r
g
a
s,
“
F
o
r
e
c
a
st
i
n
g
C
o
st
a
R
i
c
a
n
i
n
f
l
a
t
i
o
n
w
i
t
h
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
m
e
t
h
o
d
s,
”
L
a
t
i
n
Am
e
ri
c
a
n
J
o
u
r
n
a
l
o
f
C
e
n
t
r
a
l
B
a
n
k
i
n
g
,
v
o
l
.
1
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
l
a
t
c
b
.
2
0
2
0
.
1
0
0
0
1
2
.
[
8
]
A
.
El
h
a
l
w
a
g
y
a
n
d
T.
K
a
l
g
a
n
o
v
a
,
“
M
u
l
t
i
-
c
h
a
n
n
e
l
LST
M
-
c
a
p
s
u
l
e
a
u
t
o
e
n
c
o
d
e
r
n
e
t
w
o
r
k
f
o
r
a
n
o
m
a
l
y
d
e
t
e
c
t
i
o
n
o
n
m
u
l
t
i
v
a
r
i
a
t
e
d
a
t
a
,
”
A
p
p
l
i
e
d
S
c
i
e
n
c
e
s
,
v
o
l
.
1
2
,
n
o
.
2
2
,
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
2
2
2
1
1
3
9
3
.
[
9
]
D
.
D
.
P
r
a
mes
t
i
,
D
.
C
.
R
.
N
o
v
i
t
a
sar
i
,
F
.
S
e
t
i
a
w
a
n
,
a
n
d
H
.
K
h
a
u
l
a
sari
,
“
L
o
n
g
-
s
h
o
r
t
t
e
r
m
mem
o
r
y
(
LST
M
)
f
o
r
p
r
e
d
i
c
t
i
n
g
v
e
l
o
c
i
t
y
a
n
d
d
i
r
e
c
t
i
o
n
s
e
a
su
r
f
a
c
e
c
u
r
r
e
n
t
o
n
B
a
l
i
st
r
a
i
t
,
”
B
a
re
k
e
n
g
:
J
o
u
rn
a
l
o
f
Ma
t
h
e
m
a
t
i
c
s
a
n
d
i
t
s
a
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
6
,
n
o
.
2
,
p
p
.
4
5
1
–
4
6
2
,
2
0
2
2
,
d
o
i
:
1
0
.
3
0
5
9
8
/
b
a
r
e
k
e
n
g
v
o
l
1
6
i
s
s2
p
p
4
5
1
-
4
6
2
.
[
1
0
]
S
.
Za
h
a
r
a
,
S
u
g
i
a
n
t
o
,
a
n
d
M
.
B
.
I
l
mi
d
d
a
v
i
q
,
“
C
o
n
s
u
mer
p
r
i
c
e
i
n
d
e
x
p
r
e
d
i
c
t
i
o
n
u
si
n
g
l
o
n
g
s
h
o
r
t
t
e
r
m me
m
o
r
y
(
LS
TM
)
b
a
s
e
d
c
l
o
u
d
c
o
m
p
u
t
i
n
g
,
”
J
o
u
rn
a
l
o
f
Ph
y
si
c
s:
C
o
n
f
e
re
n
c
e
S
e
ri
e
s
,
v
o
l
.
1
4
5
6
,
n
o
.
1
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
8
8
/
1
7
4
2
-
6
5
9
6
/
1
4
5
6
/
1
/
0
1
2
0
2
2
.
[
1
1
]
B
.
M
.
A
c
h
m
a
d
,
S
.
S
a
’
a
d
a
h
,
a
n
d
I
.
K
u
r
n
i
a
w
a
n
,
“
LST
M
a
l
g
o
r
i
t
h
m
i
n
p
r
e
d
i
c
t
i
n
g
c
h
r
o
n
i
c
k
i
d
n
e
y
d
i
se
a
se
o
p
t
i
mi
z
e
d
u
si
n
g
g
e
n
e
t
i
c
a
l
g
o
r
i
t
h
m,
”
J
U
I
T
A:
J
u
r
n
a
l
I
n
f
o
rm
a
t
i
k
a
,
v
o
l
.
1
2
,
n
o
.
2
,
2
0
2
4
,
d
o
i
:
1
0
.
3
0
5
9
5
/
j
u
i
t
a
.
v
1
2
i
2
.
2
2
9
6
5
.
[
1
2
]
A
.
S
e
t
i
a
w
a
n
a
n
d
R
.
W
.
N
.
W
i
j
a
y
a
,
“
C
o
m
p
a
r
i
s
o
n
o
f
A
N
N
m
e
t
h
o
d
a
n
d
l
o
g
i
s
t
i
c
r
e
g
r
e
ss
i
o
n
m
e
t
h
o
d
o
n
s
i
n
g
l
e
n
u
c
l
e
o
t
i
d
e
p
o
l
y
mo
r
p
h
i
sm
g
e
n
e
t
i
c
d
a
t
a
,
”
Ba
rek
e
n
g
:
J
o
u
rn
a
l
o
f
M
a
t
h
e
m
a
t
i
c
s
a
n
d
i
t
s
a
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
7
,
n
o
.
1
,
p
p
.
1
9
7
–
2
1
0
,
2
0
2
3
,
d
o
i
:
1
0
.
3
0
5
9
8
/
b
a
r
e
k
e
n
g
v
o
l
1
7
i
ss
1
p
p
0
1
9
7
-
0
2
1
0
.
[
1
3
]
A
.
A
r
i
st
a
,
“
C
o
mp
a
r
i
s
o
n
d
e
c
i
si
o
n
t
r
e
e
a
n
d
l
o
g
i
s
t
i
c
r
e
g
r
e
ssi
o
n
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
c
l
a
s
si
f
i
c
a
t
i
o
n
a
l
g
o
r
i
t
h
ms
t
o
d
e
t
e
r
mi
n
e
c
o
v
i
d
-
1
9
,
”
S
i
n
k
rO
n
,
v
o
l
.
7
,
n
o
.
1
,
p
p
.
5
9
–
6
5
,
2
0
2
2
,
d
o
i
:
1
0
.
3
3
3
9
5
/
s
i
n
k
r
o
n
.
v
7
i
1
.
1
1
2
4
3
.
[
1
4
]
J.
M
i
c
h
a
ń
k
ó
w
,
P
.
S
a
k
o
w
s
k
i
,
a
n
d
R
.
Ś
l
e
p
a
c
z
u
k
,
“
M
e
a
n
a
b
s
o
l
u
t
e
d
i
r
e
c
t
i
o
n
a
l
l
o
ss
a
s
a
n
e
w
l
o
ss
f
u
n
c
t
i
o
n
f
o
r
mac
h
i
n
e
l
e
a
r
n
i
n
g
p
r
o
b
l
e
ms
i
n
a
l
g
o
r
i
t
h
mi
c
i
n
v
e
st
me
n
t
st
r
a
t
e
g
i
e
s,
”
J
o
u
r
n
a
l
o
f
C
o
m
p
u
t
a
t
i
o
n
a
l
S
c
i
e
n
c
e
,
v
o
l
.
8
1
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
o
c
s.
2
0
2
4
.
1
0
2
3
7
5
.
[
1
5
]
Z.
S
h
a
h
z
a
d
e
t
a
l
.
,
“
A
mu
l
t
i
p
a
r
a
me
t
e
r
f
o
r
e
c
a
s
t
i
n
g
f
o
r
st
o
c
k
t
i
me
seri
e
s
d
a
t
a
u
s
i
n
g
LST
M
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
mo
d
e
l
,
”
M
a
t
h
e
m
a
t
i
c
s
,
v
o
l
.
1
1
,
n
o
.
3
,
2
0
2
3
.
[
1
6
]
S
.
M
u
k
h
e
r
j
e
e
,
B
.
S
a
d
h
u
k
h
a
n
,
N
.
S
a
r
k
a
r
,
D
.
R
o
y
,
a
n
d
S
.
D
e
,
“
S
t
o
c
k
mar
k
e
t
p
r
e
d
i
c
t
i
o
n
u
si
n
g
d
e
e
p
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms,
”
C
A
AI
T
ra
n
s
a
c
t
i
o
n
s
o
n
I
n
t
e
l
l
i
g
e
n
c
e
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
8
,
n
o
.
1
,
p
p
.
8
2
–
9
4
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
4
9
/
c
i
t
2
.
1
2
0
5
9
.
[
1
7
]
Y
.
Li
u
,
“
F
o
r
e
c
a
st
i
n
g
C
h
i
n
a
’
s
c
o
n
s
u
mer
p
r
i
c
e
i
n
d
e
x
(
C
P
I
)
b
a
sed
o
n
c
o
m
b
i
n
e
d
A
R
I
M
A
-
LSTM
m
o
d
e
l
s,”
Fro
n
t
i
e
rs
i
n
Bu
s
i
n
e
ss,
Ec
o
n
o
m
i
c
s
a
n
d
Ma
n
a
g
e
m
e
n
t
,
v
o
l
.
1
6
,
n
o
.
2
,
p
p
.
2
6
4
–
2
7
0
,
2
0
2
4
,
d
o
i
:
1
0
.
5
4
0
9
7
/
v
4
9
d
w
v
6
7
.
[
1
8
]
S
.
M
.
M
o
st
a
f
a
a
n
d
H
.
A
ma
n
o
,
“
Ef
f
e
c
t
o
f
c
l
u
st
e
r
i
n
g
d
a
t
a
i
n
i
mp
r
o
v
i
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
m
o
d
e
l
a
c
c
u
r
a
c
y
,
”
J
o
u
r
n
a
l
o
f
T
h
e
o
r
e
t
i
c
a
l
a
n
d
Ap
p
l
i
e
d
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
9
7
,
n
o
.
2
1
,
p
p
.
2
9
7
3
–
2
9
8
1
,
2
0
1
9
.
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.
14
,
No
.
5
,
Octo
b
er
20
25
:
3
8
8
7
-
3
8
9
6
3896
[
1
9
]
X
.
Ti
a
n
e
t
a
l
.
,
“
U
+
LST
M
-
F
:
a
d
a
t
a
-
d
r
i
v
e
n
g
r
o
w
t
h
p
r
o
c
e
ss
m
o
d
e
l
o
f
r
i
c
e
s
e
e
d
l
i
n
g
s,
”
E
c
o
l
o
g
i
c
a
l
I
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
8
4
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
c
o
i
n
f
.
2
0
2
4
.
1
0
2
9
2
2
.
[
2
0
]
F
.
N
.
S
i
b
a
i
,
A
.
El
-
M
o
u
r
sy
,
a
n
d
A
.
S
i
b
a
i
,
“
F
o
r
e
c
a
s
t
i
n
g
t
h
e
c
o
n
su
m
e
r
p
r
i
c
e
i
n
d
e
x
:
a
c
o
m
p
a
r
a
t
i
v
e
s
t
u
d
y
o
f
mac
h
i
n
e
l
e
a
r
n
i
n
g
met
h
o
d
s,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
C
o
m
p
u
t
i
n
g
a
n
d
D
i
g
i
t
a
l
S
y
st
e
m
s
,
v
o
l
.
1
5
,
n
o
.
1
,
p
p
.
4
8
7
–
4
9
7
,
2
0
2
4
,
d
o
i
:
1
0
.
1
2
7
8
5
/
i
j
c
d
s
/
1
5
0
1
3
7
.
[
2
1
]
B
.
M
a
l
l
a
l
a
,
A
.
I
.
U
.
A
h
m
e
d
,
S
.
V
.
P
a
mi
d
i
,
M
.
O
.
F
a
r
u
q
u
e
,
a
n
d
R
.
R
.
M
,
“
F
o
r
e
c
a
st
i
n
g
g
l
o
b
a
l
su
s
t
a
i
n
a
b
l
e
e
n
e
r
g
y
f
r
o
m
r
e
n
e
w
a
b
l
e
so
u
r
c
e
s
u
s
i
n
g
r
a
n
d
o
m fo
r
e
st
a
l
g
o
r
i
t
h
m,”
R
e
s
u
l
t
s i
n
En
g
i
n
e
e
r
i
n
g
,
v
o
l
.
2
5
,
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
r
i
n
e
n
g
.
2
0
2
4
.
1
0
3
7
8
9
.
[
2
2
]
G
.
S
.
M
o
h
a
mm
a
d
,
“
Est
i
ma
t
e
a
c
c
u
r
a
c
y
o
f
t
h
e
s
a
mp
l
e
d
e
t
e
r
mi
n
a
t
i
o
n
c
o
e
f
f
i
c
i
e
n
t
R
2
a
n
d
R
2
f
o
r
t
h
e
m
u
l
t
i
p
l
e
r
e
g
r
e
ssi
o
n
mo
d
e
l
s,
”
J
o
u
rn
a
l
o
f
S
o
u
t
h
w
e
st
J
i
a
o
t
o
n
g
U
n
i
v
e
r
si
t
y
,
v
o
l
.
5
5
,
n
o
.
1
,
2
0
2
0
,
d
o
i
:
1
0
.
3
5
7
4
1
/
i
ssn
.
0
2
5
8
-
2
7
2
4
.
5
5
.
1
.
2
5
.
[
2
3
]
S
.
M
.
A
l
-
S
e
l
w
i
e
t
a
l
.
,
“
R
N
N
-
LST
M
:
f
r
o
m
a
p
p
l
i
c
a
t
i
o
n
s
t
o
m
o
d
e
l
i
n
g
t
e
c
h
n
i
q
u
e
s
a
n
d
b
e
y
o
n
d
—
s
y
st
e
ma
t
i
c
r
e
v
i
e
w
,
”
J
o
u
rn
a
l
o
f
K
i
n
g
S
a
u
d
U
n
i
v
e
rsi
t
y
-
C
o
m
p
u
t
e
r
a
n
d
I
n
f
o
r
m
a
t
i
o
n
S
c
i
e
n
c
e
s
,
v
o
l
.
3
6
,
n
o
.
5
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
k
s
u
c
i
.
2
0
2
4
.
1
0
2
0
6
8
.
[
2
4
]
C
.
M
a
n
d
a
n
g
,
D
.
P
.
E
.
S
a
e
r
a
n
g
,
a
n
d
W
.
F
r
e
d
e
r
i
k
,
“
T
h
e
i
n
f
l
u
e
n
c
e
o
f
p
r
i
c
e
,
serv
i
c
e
q
u
a
l
i
t
y
a
n
d
p
h
y
s
i
c
a
l
e
n
v
i
r
o
n
men
t
o
n
c
u
st
o
m
e
r
sat
i
sf
a
c
t
i
o
n
c
a
se
s
t
u
d
y
m
a
r
k
o
b
a
r
c
a
f
e
man
d
o
,
”
J
u
rn
a
l
E
MB
A
,
v
o
l
.
5
,
n
o
.
2
,
p
p
.
6
7
8
–
6
8
6
,
2
0
1
7
.
[
2
5
]
H
.
C
.
C
h
e
n
,
W
.
J
.
C
h
e
n
,
a
n
d
Y
.
Zh
o
u
,
“
E
st
i
mat
i
o
n
o
f
c
h
r
o
ma
t
i
c
i
t
y
c
o
o
r
d
i
n
a
t
e
s
f
o
r
LED
s
a
r
r
a
y
b
y
m
o
d
u
l
a
t
i
o
n
o
f
r
e
d
o
r
y
e
l
l
o
w
LED
s
w
i
t
h
a
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
2
0
1
3
N
i
n
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
I
n
t
e
l
l
i
g
e
n
t
I
n
f
o
rm
a
t
i
o
n
H
i
d
i
n
g
a
n
d
M
u
l
t
i
m
e
d
i
a
S
i
g
n
a
l
Pr
o
c
e
ssi
n
g
,
p
p
.
8
8
–
9
1
,
2
0
1
3
,
d
o
i
:
1
0
.
1
1
0
9
/
I
I
H
-
M
S
P
.
2
0
1
3
.
3
1
.
[
2
6
]
Q
.
Q
.
H
e
,
C
.
W
u
,
a
n
d
Y
.
W
.
S
i
,
“
LS
TM
w
i
t
h
p
a
r
t
i
c
l
e
sw
a
m
o
p
t
i
m
i
z
a
t
i
o
n
f
o
r
sa
l
e
s
f
o
r
e
c
a
s
t
i
n
g
,
”
El
e
c
t
ro
n
i
c
C
o
m
m
e
rce
Re
s
e
a
r
c
h
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
5
1
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
l
e
r
a
p
.
2
0
2
2
.
1
0
1
1
1
8
.
[
2
7
]
S
.
A
t
e
f
,
K
.
N
a
k
a
t
a
,
a
n
d
A
.
B
.
El
t
a
w
i
l
,
“
A
d
e
e
p
b
i
-
d
i
r
e
c
t
i
o
n
a
l
l
o
n
g
-
s
h
o
r
t
t
e
r
m
mem
o
r
y
n
e
u
r
a
l
n
e
t
w
o
r
k
-
b
a
s
e
d
met
h
o
d
o
l
o
g
y
t
o
e
n
h
a
n
c
e
s
h
o
r
t
-
t
e
r
m
e
l
e
c
t
r
i
c
i
t
y
l
o
a
d
f
o
r
e
c
a
st
i
n
g
f
o
r
r
e
s
i
d
e
n
t
i
a
l
a
p
p
l
i
c
a
t
i
o
n
s,”
C
o
m
p
u
t
e
rs
a
n
d
I
n
d
u
s
t
ri
a
l
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
1
7
0
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
i
e
.
2
0
2
2
.
1
0
8
3
6
4
.
[
2
8
]
S
.
K
u
b
h
e
k
a
,
“
S
o
u
t
h
A
f
r
i
c
a
n
i
n
f
l
a
t
i
o
n
m
o
d
e
l
l
i
n
g
u
si
n
g
b
o
o
t
s
t
r
a
p
p
e
d
l
o
n
g
s
h
o
r
t
-
t
e
r
m
mem
o
r
y
me
t
h
o
d
s,
”
S
N
B
u
si
n
e
ss
a
n
d
Ec
o
n
o
m
i
c
s
,
v
o
l
.
3
,
n
o
.
7
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s
4
3
5
4
6
-
0
2
3
-
0
0
4
9
0
-
9.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
H
a
r
fe
ly
Le
ip
a
r
y
is
a
g
ra
d
u
a
t
e
o
f
Un
i
v
e
rsitas
Kriste
n
In
d
o
n
e
si
a
M
a
lu
k
u
.
H
e
is
c
u
rre
n
tl
y
a
d
v
a
n
c
in
g
h
is
e
x
p
e
rti
se
b
y
p
u
rsu
i
n
g
a
m
a
ste
r'
s
d
e
g
re
e
in
Da
ta
S
c
ien
c
e
a
t
th
e
F
a
c
u
lt
y
o
f
S
c
ie
n
c
e
a
n
d
M
a
t
h
e
m
a
ti
c
s,
S
a
ty
a
Wac
a
n
a
C
h
risti
a
n
Un
i
v
e
rsity
(UK
S
W)
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
leip
a
r
y
h
a
rfe
ly
@g
m
a
il
.
c
o
m
.
Adi
S
e
tia
w
a
n
He
is
a
d
is
ti
n
g
u
ish
e
d
a
c
a
d
e
m
ic
with
e
x
ten
siv
e
e
x
p
e
rti
se
i
n
m
a
th
e
m
a
ti
c
s,
sta
ti
stics
,
a
n
d
d
a
ta
s
c
ien
c
e
.
He
se
rv
e
d
a
s
t
h
e
De
a
n
o
f
th
e
F
a
c
u
lt
y
o
f
S
c
ien
c
e
a
n
d
M
a
th
e
m
a
ti
c
s
(F
S
M
)
a
t
S
a
ty
a
Wac
a
n
a
Ch
risti
a
n
Un
iv
e
rsit
y
(UK
S
W)
fro
m
2
0
1
7
t
o
2
0
2
2
a
n
d
c
u
rre
n
tl
y
h
o
l
d
s
t
h
e
p
o
siti
o
n
o
f
He
a
d
o
f
th
e
Qu
a
li
t
y
As
su
ra
n
c
e
a
n
d
De
v
e
l
o
p
m
e
n
t
Div
isio
n
(G
P
M
F
)
fo
r
th
e
2
0
2
2
–
2
0
2
7
term
.
Wi
th
a
fo
c
u
s
o
n
t
h
e
M
a
ste
r
o
f
Da
ta
S
c
ien
c
e
p
ro
g
ra
m
,
h
e
tea
c
h
e
s
v
a
rio
u
s
su
b
jec
ts,
i
n
c
l
u
d
i
n
g
sta
ti
stics
,
a
b
stra
c
t
a
lg
e
b
ra
,
a
d
v
a
n
c
e
d
sta
ti
stics
,
m
a
th
e
m
a
ti
c
a
l
sta
ti
stics
,
p
ro
b
a
b
il
i
t
y
th
e
o
ry
,
in
d
u
strial
sta
ti
stics
,
a
n
d
d
a
ta
m
in
in
g
.
He
e
a
rn
e
d
h
is
Ba
c
h
e
lo
r’s
d
e
g
re
e
i
n
M
a
th
e
m
a
ti
c
s
fro
m
Un
i
v
e
rsitas
G
a
d
jah
M
a
d
a
(UG
M
),
Yo
g
y
a
k
a
rta,
In
d
o
n
e
sia
,
i
n
1
9
9
1
.
He
p
u
rsu
e
d
a
d
v
a
n
c
e
d
stu
d
ies
a
t
Vrije
U
n
iv
e
rs
it
e
it
Am
ste
rd
a
m
,
o
b
tain
i
n
g
h
is
m
a
ste
r’s
d
e
g
re
e
in
M
a
th
e
m
a
ti
c
s
in
1
9
9
7
a
n
d
h
is
d
o
c
t
o
ra
te
in
S
tatisti
c
s
in
2
0
0
7
.
His
d
e
d
ica
ti
o
n
t
o
p
r
o
fe
ss
io
n
a
l
d
e
v
e
lo
p
m
e
n
t
is
re
flec
ted
in
h
is
p
a
rti
c
ip
a
ti
o
n
in
n
u
m
e
ro
u
s
wo
rk
sh
o
p
s,
s
u
c
h
a
s
"
LaTe
X
fo
r
R
e
se
a
rc
h
e
rs
a
n
d
S
tu
d
e
n
ts
"
(U
KSW
,
2
0
1
6
),
"
S
u
r
v
e
y
a
n
d
M
a
p
p
i
n
g
Tec
h
n
o
lo
g
y
"
(UG
M
,
2
0
1
6
),
a
n
d
wo
rk
sh
o
p
s
o
n
writi
n
g
h
ig
h
-
q
u
a
li
ty
jo
u
rn
a
l
a
rti
c
les
(UK
S
W,
2
0
1
7
;
UA
D
Yo
g
y
a
k
a
rta,
2
0
1
9
).
H
e
p
ro
f
o
u
n
d
k
n
o
wl
e
d
g
e
a
n
d
c
o
m
m
it
m
e
n
t
to
a
c
a
d
e
m
ic
e
x
c
e
ll
e
n
c
e
m
a
k
e
h
im
a
h
i
g
h
l
y
re
sp
e
c
ted
fi
g
u
re
in
t
h
e
field
o
f
d
a
ta
sc
ien
c
e
a
n
d
sta
ti
stica
l
e
d
u
c
a
ti
o
n
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
a
d
i.
se
ti
a
wa
n
@u
k
sw
.
e
d
u
.
Evaluation Warning : The document was created with Spire.PDF for Python.