I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
p
u
t
er
Science
Vo
l.
22
,
No
.
3
,
J
u
n
e
2
0
2
1
,
p
p
.
1
6
8
8
~
1
6
9
6
I
SS
N:
2
5
02
-
4
7
5
2
,
DOI
: 1
0
.
1
1
5
9
1
/i
j
ee
cs.v
2
2
.i
3
.
p
p
1
6
8
8
-
1
6
9
6
1688
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs.ia
esco
r
e.
co
m
O
utli
ers de
tectio
n in state
-
spa
ce
m
o
del using
indi
ca
tor
sa
turatio
n app
ro
a
ch
F
a
rid
Z
a
m
a
ni Che
Ro
s
e
1
,
M
o
hd
T
a
hir I
s
m
a
il
2
,
M
o
hd
H
a
na
f
i Tu
m
i
n
3
1,
2
S
c
h
o
o
l
o
f
M
a
th
e
m
a
ti
c
a
l
S
c
ien
c
e
s,
Un
iv
e
rsiti
S
a
in
s M
a
lay
sia
(US
M
),
M
a
lay
sia
3
S
c
h
o
o
l
o
f
M
a
t
h
e
m
a
t
i
c
s
a
n
d
B
a
s
i
c
S
c
i
e
n
c
e
s
,
F
a
c
u
l
ty
o
f
S
c
i
e
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
Q
u
e
s
t
I
n
t
e
r
n
a
t
i
o
n
a
l
Un
i
v
e
r
s
i
ty
,
M
a
lay
s
i
a
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Sep
1
0
,
2
0
2
0
R
ev
i
s
ed
Ma
y
6
,
2
0
2
1
A
cc
ep
ted
Ma
y
1
9
,
2
0
2
1
S
tru
c
tu
ra
l
c
h
a
n
g
e
s
t
h
a
t
o
c
c
u
r
d
u
e
to
o
u
tl
iers
m
a
y
re
d
u
c
e
th
e
a
c
c
u
ra
c
y
o
f
a
n
e
sti
m
a
ted
ti
m
e
se
ries
m
o
d
e
l,
sh
if
ti
n
g
th
e
m
e
a
n
d
istri
b
u
t
io
n
a
n
d
c
a
u
si
n
g
f
o
re
c
a
st
f
a
il
u
re
.
T
h
is
stu
d
y
u
s
e
d
g
e
n
e
ra
l
-
to
-
sp
e
c
if
ic
a
p
p
ro
a
c
h
to
d
e
tec
t
o
u
tl
iers
v
ia
in
d
ica
t
o
r
sa
tu
ra
ti
o
n
a
p
p
r
o
a
c
h
in
th
e
l
o
c
a
l
lev
e
l
m
o
d
e
l
fra
m
e
w
o
rk
.
F
o
c
u
sin
g
o
n
im
p
u
lse
i
n
d
ica
to
r
sa
tu
ra
ti
o
n
,
p
e
rf
o
rm
a
n
c
e
re
c
o
rd
e
d
b
y
th
e
su
g
g
e
ste
d
a
p
p
ro
a
c
h
w
a
s
e
v
a
lu
a
te
d
u
si
n
g
M
o
n
te
Ca
rlo
sim
u
latio
n
s.
T
o
tac
k
le
th
e
issu
e
o
f
h
ig
h
e
r
n
u
m
b
e
r
o
f
re
g
re
ss
o
rs
c
o
m
p
a
re
d
to
t
h
e
n
u
m
b
e
r
o
f
o
b
se
rv
a
ti
o
n
s,
th
is
re
se
a
rc
h
u
t
il
iz
e
d
th
e
sp
li
t
-
h
a
lf
a
p
p
r
o
a
c
h
a
lg
o
r
it
h
m
.
W
e
f
o
u
n
d
th
a
t
th
e
im
p
u
lse
in
d
ica
to
r
sa
tu
ra
ti
o
n
p
e
rf
o
rm
a
n
c
e
re
li
e
s
h
e
a
v
il
y
o
n
th
e
siz
e
o
f
o
u
tl
ier,
lo
c
a
ti
o
n
o
f
o
u
tl
ier
a
n
d
n
u
m
b
e
r
o
f
sp
li
ts i
n
th
e
se
ries
e
x
a
m
in
e
d
.
De
tec
ti
o
n
o
f
o
u
tl
iers
u
si
n
g
se
q
u
e
n
ti
a
l
a
n
d
n
o
n
-
se
q
u
e
n
ti
a
l
a
lg
o
rit
h
m
s
is
th
e
m
o
st
c
ru
c
ial
issu
e
in
th
is
stu
d
y
.
T
h
e
se
q
u
e
n
ti
a
l
se
a
rc
h
in
g
a
lg
o
rit
h
m
wa
s
a
b
le
to
o
u
t
p
e
rf
o
rm
th
e
n
o
n
-
se
q
u
e
n
ti
a
l
se
a
rc
h
in
g
a
lg
o
rit
h
m
in
e
li
m
in
a
ti
n
g
th
e
n
o
n
-
sig
n
if
ica
n
t
in
d
ica
to
rs
b
a
se
d
o
n
p
o
ten
c
y
a
n
d
g
a
u
g
e
.
T
h
e
o
u
tl
ier
s
c
a
p
tu
re
d
u
sin
g
im
p
u
lse
i
n
d
ica
t
o
r
sa
tu
ra
ti
o
n
i
n
f
in
a
n
c
ial
ti
m
e
s
sto
c
k
e
x
c
h
a
n
g
e
(
F
T
S
E
)
Un
it
e
d
S
tate
s
o
f
Am
e
ric
a
(US
A)
s
h
a
riah
in
d
e
x
c
o
rre
sp
o
n
d
t
o
th
e
f
in
a
n
c
ial
c
risis i
n
2
0
0
8
-
2
0
0
9
.
K
ey
w
o
r
d
s
:
A
d
d
iti
v
e
o
u
tlier
Gen
er
al
-
to
-
s
p
ec
i
f
ic
I
n
d
icato
r
s
atu
r
atio
n
L
o
ca
l le
v
e
l
Mo
n
te
C
ar
lo
s
i
m
u
latio
n
State
s
p
ac
e
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Far
id
Z
a
m
a
n
i
B
i
n
C
h
e
R
o
s
e
Sch
o
o
l o
f
Ma
t
h
e
m
at
ical
Scie
n
ce
s
Un
i
v
er
s
iti
Sain
s
Ma
la
y
s
ia
1
1
8
0
0
USM,
P
en
an
g
,
Ma
la
y
s
i
a
E
m
ail:
f
ar
id
6
9
0
8
@
g
m
ai
l.c
o
m
1.
I
NT
RO
D
UCT
I
O
N
Ob
s
er
v
atio
n
d
ata
u
s
ed
in
e
m
p
ir
ical
m
o
d
els
ar
e
ass
u
m
ed
t
o
o
r
ig
in
ate
f
r
o
m
s
tatio
n
ar
y
p
r
o
ce
s
s
.
I
n
r
ea
lit
y
,
m
o
s
t
r
ea
l
-
t
i
m
e
s
er
ies
d
ata
ar
e
n
o
t
s
tatio
n
ar
y
a
n
d
th
eir
m
ea
n
s
an
d
v
ar
ian
ce
s
v
ar
y
w
it
h
t
h
e
d
ata.
T
h
e
ch
an
g
es
m
a
y
ta
k
e
v
ar
io
u
s
f
o
r
m
s
,
m
a
g
n
itu
d
e
s
an
d
n
u
m
b
er
s
.
An
y
s
tr
u
ct
u
r
al
c
h
an
g
e
i
n
ti
m
e
s
er
ies
m
a
y
a
f
f
ec
t
p
ar
am
eter
es
ti
m
atio
n
,
esp
ec
ial
l
y
esti
m
at
io
n
o
f
ec
o
n
o
m
ic
a
n
d
f
in
a
n
cial
i
n
d
icato
r
s
.
An
o
u
t
l
ier
in
ti
m
e
s
er
ies
i
s
also
k
n
o
w
n
a
s
an
u
n
u
s
u
al
lar
g
e
v
a
lu
e
o
f
ir
r
eg
u
lar
d
is
t
u
r
b
an
ce
at
a
s
p
ec
i
f
ic
ti
m
e.
T
h
e
ex
is
ten
ce
o
f
o
u
t
l
y
i
n
g
o
b
s
er
v
atio
n
s
a
n
d
s
tr
u
ct
u
r
al
c
h
an
g
es
al
w
a
y
s
r
aise
a
b
ig
q
u
esti
o
n
o
n
t
h
e
ac
c
u
r
ac
y
a
n
d
ef
f
icie
n
c
y
o
f
t
h
e
esti
m
ated
m
o
d
el.
Fail
in
g
to
m
o
d
el
th
e
s
tr
u
ctu
r
al
c
h
a
n
g
e
s
m
a
y
lead
to
m
is
s
p
ec
i
f
icatio
n
o
f
t
h
e
e
m
p
ir
ical
m
o
d
el
an
d
f
o
r
ec
ast
ac
cu
r
ac
y
[
1
]
.
T
h
ese
ar
e
th
e
co
m
m
o
n
p
r
o
b
le
m
s
w
h
e
n
d
ea
lin
g
w
i
th
s
tr
u
ct
u
r
al
ch
an
g
es
i
n
ti
m
e
s
er
ies
d
ata.
He
n
ce
,
th
is
s
tu
d
y
p
r
o
p
o
s
ed
to
s
o
lv
e
t
h
e
p
r
o
b
le
m
o
f
d
is
to
r
tio
n
in
th
e
p
ar
a
m
eter
d
u
e
to
p
r
esen
ce
o
f
o
u
tlier
s
u
s
i
n
g
t
h
e
i
n
d
icato
r
s
at
u
r
atio
n
ap
p
r
o
ac
h
in
g
e
n
er
al
-
to
-
s
p
ec
i
f
ic
(
GE
T
S)
m
o
d
elli
n
g
.
G
e
n
e
r
a
l
-
to
-
s
p
ec
if
i
c
m
o
d
e
l
lin
g
i
s
w
i
d
e
ly
u
s
e
d
t
o
m
o
d
el
e
c
o
n
o
m
i
cs
an
d
f
in
an
c
e
d
a
t
a
.
T
h
e
i
d
ea
o
f
m
o
d
e
l
s
e
l
e
ct
i
o
n
o
r
i
g
in
a
t
e
d
w
ith
[
2
]
b
y
r
e
v
i
s
i
t
in
g
[
3
]
w
o
r
k
o
n
d
at
a
m
i
n
in
g
ex
p
e
r
im
e
n
t
.
H
en
d
r
y
an
d
K
r
o
l
z
ig
[
4
]
i
m
p
r
o
v
ed
th
e
au
to
m
ated
m
u
l
tip
ath
GE
T
S
m
o
d
ellin
g
u
s
i
n
g
MA
T
L
A
B
co
d
e
s
im
u
latio
n
s
b
y
in
cr
ea
s
i
n
g
th
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
Ou
tlier
s
d
etec
tio
n
in
s
ta
te
-
s
p
a
ce
mo
d
el
u
s
in
g
in
d
ica
to
r
s
a
tu
r
a
tio
n
a
p
p
r
o
a
ch
(
F
a
r
id
Za
ma
n
i Ch
e
R
o
s
e
)
1689
co
m
p
u
tatio
n
al
p
o
w
er
1000
-
f
o
ld
.
T
h
e
r
esu
lt
s
attr
ac
ted
[
4
]
to
m
ak
e
f
u
r
th
er
i
m
p
r
o
v
e
m
e
n
ts
o
f
t
h
e
s
elec
tio
n
alg
o
r
ith
m
i
n
Au
to
m
etr
ics.
T
h
en
,
th
e
y
m
ad
e
th
e
al
g
o
r
ith
m
w
o
r
k
s
in
co
m
p
u
ter
p
r
o
g
r
a
m
v
iz
P
cGe
ts
.
A
n
o
t
h
er
i
m
p
r
o
v
e
m
en
t
m
ad
e
w
it
h
t
h
e
t
h
ir
d
i
m
p
le
m
en
tatio
n
o
f
GE
T
S
in
Au
to
m
etr
ic
s
w
as
b
y
[
5
]
th
at
w
o
r
k
s
u
s
i
n
g
t
h
e
s
a
m
e
ap
p
r
o
ac
h
as
in
[
2
]
an
d
[
4
]
.
I
n
d
icato
r
s
atu
r
atio
n
m
et
h
o
d
w
as
e
m
b
o
d
ied
in
A
u
to
m
etr
i
cs
b
y
[
6
]
to
ca
p
tu
r
e
o
u
tlier
s
a
n
d
s
tr
u
ct
u
r
al
b
r
ea
k
s
in
th
e
s
at
u
r
ated
r
eg
r
ess
io
n
m
o
d
el.
I
n
ad
d
itio
n
,
r
ec
en
t
s
t
u
d
y
b
y
[
7
]
e
m
p
lo
y
ed
in
d
icato
r
s
at
u
r
atio
n
ap
p
r
o
ac
h
in
Au
to
m
e
tr
ics
to
m
o
d
el
t
h
e
lo
ca
tio
n
s
h
i
f
ts
a
n
d
s
tr
u
ctu
r
al
b
r
ea
k
s
i
n
n
o
n
-
s
tatio
n
ar
y
b
i
g
d
ata.
Gen
er
al
p
r
o
ce
s
s
es
u
s
ed
to
id
en
ti
f
y
b
o
th
o
u
tlier
s
a
n
d
s
tr
u
c
tu
r
al
b
r
ea
k
s
u
s
i
n
g
s
tate
-
s
p
ac
e
m
o
d
el
s
ar
e
f
u
r
t
h
er
d
is
c
u
s
s
ed
in
[
8
]
.
I
t
is
i
m
p
o
r
tan
t
to
ca
p
tu
r
e
t
h
e
o
u
tlier
s
in
a
m
o
d
el
i
m
m
ed
iatel
y
to
av
o
id
m
is
s
p
ec
if
icatio
n
o
f
p
ar
a
m
eter
esti
m
atio
n
a
n
d
i
m
p
r
o
v
e
f
o
r
ec
ast
ac
cu
r
ac
y
.
Sp
ec
if
ica
ll
y
,
t
h
e
i
n
d
icato
r
s
atu
r
atio
n
ap
p
r
o
ac
h
is
u
s
ed
to
d
etec
t
i
f
th
e
o
u
t
lier
is
c
lo
s
e
to
f
o
r
ec
ast
o
r
ig
in
.
He
n
d
r
y
[
9
]
s
tar
ted
h
i
s
w
o
r
k
o
n
i
m
p
u
ls
e
in
d
icato
r
s
atu
r
atio
n
(
I
I
S)
to
te
s
t
th
e
u
n
k
n
o
w
n
a
m
o
u
n
t
o
f
o
u
tlier
,
s
ig
n
an
d
m
a
g
n
it
u
d
e
o
cc
u
r
r
in
g
at
u
n
k
n
o
wn
lo
ca
tio
n
s
in
ti
m
e
s
er
ies
d
ata.
T
h
e
id
ea
o
f
I
I
S
w
a
s
f
ir
s
t
i
n
tr
o
d
u
ce
d
to
m
o
d
el
US
f
o
o
d
d
e
m
an
d
in
1
9
3
0
s
an
d
1940s
[
1
0
]
.
T
o
d
etec
t
o
u
tlier
s
,
th
e
m
et
h
o
d
cr
ea
ted
a
p
u
ls
e
d
u
m
m
y
v
ar
iab
le
f
o
r
ea
ch
r
es
u
lt
o
b
tain
ed
b
y
th
e
s
tu
d
y
.
T
h
i
s
is
a
n
ac
ti
v
e
an
d
b
u
r
g
eo
n
i
n
g
ar
ea
o
f
r
esear
ch
.
Nu
m
er
o
u
s
s
t
u
d
ies
o
n
th
e
i
n
d
icato
r
s
atu
r
atio
n
ap
p
r
o
ac
h
w
it
h
ec
o
n
o
m
ic
ap
p
licatio
n
s
ca
n
b
e
f
o
u
n
d
i
n
[
1
1
]
-
[
1
6
]
.
T
h
e
ap
p
licatio
n
o
f
in
d
icat
o
r
s
a
tu
r
atio
n
i
s
n
o
t
o
n
l
y
li
m
ited
to
ec
o
n
o
m
ic
r
ese
ar
ch
,
b
u
t a
ls
o
ap
p
licab
le
to
o
th
er
ar
ea
s
o
f
r
esear
ch
s
u
c
h
as c
li
m
ate
ch
a
n
g
e
[
1
7
]
.
A
t
p
r
esen
t
,
r
esear
ch
ab
o
u
t
th
e
p
er
f
o
r
m
a
n
ce
o
f
in
d
icato
r
s
atu
r
atio
n
esp
ec
iall
y
f
r
o
m
s
tr
u
c
tu
r
al
ti
m
e
s
er
ies v
ie
w
p
o
i
n
t i
s
d
o
n
e
b
y
[
1
4
]
u
s
in
g
b
asic
s
tr
u
ct
u
r
al
m
o
d
e
l (
B
SM)
o
n
l
y
.
T
h
e
w
o
r
k
p
r
ese
n
ted
in
t
h
i
s
p
ap
er
is
m
o
tiv
a
ted
b
y
t
h
e
f
ac
t
th
a
t
o
u
tlier
s
ca
n
b
e
id
en
ti
f
ied
a
n
d
m
o
d
elled
v
ia
t
h
e
i
n
d
icato
r
s
atu
r
atio
n
ap
p
r
o
ac
h
.
T
h
er
ef
o
r
e,
w
e
ai
m
to
ap
p
l
y
i
m
p
u
l
s
e
i
n
d
icato
r
ap
p
r
o
ac
h
in
th
e
co
n
te
x
t
o
f
t
h
e
lo
ca
l
le
v
el
m
o
d
el
(
L
L
M)
.
T
h
e
s
tate
-
s
p
ac
e
f
r
a
m
e
w
o
r
k
c
h
o
s
e
n
h
as
a
n
ad
v
a
n
ta
g
e
o
v
er
o
th
er
t
i
m
e
s
er
ie
s
m
o
d
els
s
i
n
ce
th
e
s
t
ate
-
s
p
ac
e
m
et
h
o
d
is
ab
le
to
h
an
d
le
n
o
n
-
s
tatio
n
ar
y
d
ata.
T
y
p
icall
y
,
ec
o
n
o
m
etr
ic
ia
n
s
h
a
n
d
le
n
o
n
-
s
tat
io
n
ar
y
d
ata
u
s
i
n
g
d
i
f
f
er
e
n
cin
g
a
p
p
r
o
ac
h
th
at
r
ed
u
ce
s
th
e
in
t
eg
r
atio
n
o
r
d
er
as
i
n
[
1
8
]
.
Ho
w
e
v
er
,
th
is
ap
p
r
o
ac
h
is
n
o
t
ab
le
to
m
o
d
el
an
y
lo
n
g
-
r
u
n
eq
u
il
ib
r
ia
s
u
c
h
as
r
el
atio
n
s
h
ip
s
i
n
th
e
d
ata.
T
h
er
ef
o
r
e,
w
e
p
r
o
p
o
s
e
to
in
teg
r
ate
th
e
I
I
S
in
s
tate
-
s
p
ac
e
m
o
d
el
f
r
a
m
e
w
o
r
k
s
i
n
ce
it c
a
n
h
an
d
le
n
o
n
-
s
tatio
n
ar
y
d
ata.
Ap
ar
t f
r
o
m
t
h
at,
t
h
e
s
u
g
g
e
s
ted
f
r
a
m
e
w
o
r
k
i
s
ab
le
to
h
an
d
le
m
is
s
in
g
o
r
in
co
m
p
lete
d
ata,
ti
m
e
-
v
ar
y
in
g
r
eg
r
ess
io
n
co
ef
f
icien
ts
an
d
m
u
lti
v
ar
iate
ex
ten
s
io
n
s
.
Hen
ce
,
w
e
d
ec
id
e
to
tak
e
a
n
e
w
lo
o
k
o
n
th
e
lo
ca
l
lev
el
m
o
d
el,
w
h
ich
co
n
s
i
s
ts
o
f
a
r
an
d
o
m
d
is
t
u
r
b
an
ce
ar
o
u
n
d
an
u
n
d
er
l
y
in
g
lev
e
l
w
h
ic
h
f
l
u
ct
u
ates
w
ith
o
u
t
an
y
s
p
ec
if
ic
d
ir
ec
tio
n
.
L
L
M
is
k
n
o
w
n
a
s
th
e
s
i
m
p
lest
m
o
d
el
i
n
th
e
s
tate
-
s
p
ac
e
f
a
m
il
y
a
n
d
it
m
a
y
b
e
d
escr
ib
ed
in
s
tate
-
s
p
ac
e
f
o
r
m
s
.
W
e
r
ef
er
to
[
1
9
]
f
o
r
d
etailed
an
aly
s
is
tr
ea
t
m
e
n
t
o
f
s
tate
-
s
p
ac
e
m
et
h
o
d
s
.
T
h
e
m
ain
b
e
n
ef
it
o
f
L
L
M
is
its
f
u
l
l
y
d
eter
m
in
i
s
tic
s
ta
te
-
s
p
ac
e
m
o
d
el
s
ca
n
also
b
e
ad
d
r
ess
ed
as
cla
s
s
ical
lin
ea
r
r
e
g
r
ess
io
n
m
o
d
els.
T
h
e
p
r
i
m
ar
y
ad
v
an
tag
e
o
f
s
tate
-
s
p
ac
e
m
et
h
o
d
s
i
s
it
f
its
b
etter
to
d
ata
th
a
n
class
ic
l
in
ea
r
r
eg
r
ess
io
n
s
m
o
d
el
[
2
0
]
.
P
r
io
r
w
o
r
k
s
in
[
2
1
]
an
d
[
2
2
]
d
o
n
o
t
em
p
lo
y
I
S
in
Gau
s
s
i
an
s
tate
-
s
p
ac
e
m
o
d
el.
Me
an
w
h
ile,
[
1
4
]
ap
p
lied
im
p
u
l
s
e
an
d
s
tep
in
d
icato
r
s
to
d
etec
t
o
u
tlier
s
an
d
lev
el
s
h
if
t
i
n
th
e
b
asic
s
tr
u
ct
u
r
a
l
m
o
d
el.
Ou
r
s
t
u
d
y
atte
m
p
ts
to
co
n
tr
ib
u
te
to
t
h
e
l
iter
atu
r
e
b
y
ex
a
m
i
n
i
n
g
th
e
p
er
f
o
r
m
an
ce
o
f
I
I
S
in
th
e
co
n
te
x
t
o
f
t
h
e
lo
ca
l
le
v
e
l
m
o
d
el
b
y
as
s
es
s
in
g
t
h
e
p
er
f
o
r
m
an
ce
o
f
I
I
S
in
L
L
M
th
r
o
u
g
h
Mo
n
te
C
ar
lo
s
i
m
u
latio
n
s
r
ep
li
ca
ted
at
=
1000
ti
m
e
s
.
F
u
r
th
er
,
w
e
ap
p
l
y
th
e
i
m
p
u
l
s
e
i
n
d
icato
r
s
at
u
r
atio
n
to
id
en
ti
f
y
o
u
tlier
s
i
n
s
h
ar
iah
-
co
m
p
lian
t
s
to
c
k
p
r
ice
s
er
ies,
s
p
ec
i
f
icall
y
f
in
a
n
cial
t
i
m
es
s
to
ck
e
x
c
h
an
g
e
(
FT
SE
)
h
ij
r
ah
s
h
ar
iah
a
n
d
FT
SE
all
-
w
o
r
ld
s
h
ar
ia
h
.
I
n
ad
d
itio
n
,
n
o
s
t
u
d
y
h
a
s
m
ad
e
t
h
e
e
f
f
o
r
t
to
u
n
d
er
s
tan
d
t
h
e
e
f
f
ec
ti
v
en
e
s
s
o
f
i
n
d
icato
r
s
at
u
r
atio
n
i
n
teg
r
at
io
n
i
n
s
tate
-
s
p
ac
e
m
o
d
el
u
s
i
n
g
g
ets
p
ac
k
ag
e
i
n
R
p
r
o
g
r
a
m
m
i
n
g
la
n
g
u
a
g
e.
T
h
e
g
ets
p
ac
k
a
g
e
d
ev
elo
p
ed
b
y
[
2
3
]
w
a
s
ab
le
to
au
to
m
atica
ll
y
d
eter
m
i
n
e
th
e
r
eq
u
ir
ed
m
o
d
el
b
ased
o
n
g
e
n
er
al
-
to
-
s
p
ec
i
f
ic
m
o
d
e
llin
g
an
d
i
n
d
icato
r
s
atu
r
atio
n
.
Hen
ce
,
w
e
ai
m
to
p
r
o
v
id
e
d
etails
o
f
s
im
u
latio
n
an
al
y
s
i
s
u
s
i
n
g
g
ets
p
ac
k
ag
e
i
n
th
e
co
n
tex
t
o
f
s
tate
-
s
p
ac
e
m
o
d
el.
T
h
e
r
e
s
t
o
f
th
is
p
a
p
e
r
is
a
r
r
an
g
e
d
as
;
s
e
c
t
i
o
n
2
e
la
b
o
r
a
t
e
s
th
e
s
t
r
u
c
tu
r
e
o
f
th
e
l
o
ca
l
l
ev
el
m
o
d
e
l
f
o
r
o
u
t
li
e
r
d
e
t
e
c
ti
o
n
an
d
i
n
t
r
o
d
u
ce
s
th
e
c
o
n
c
e
p
t
s
o
f
i
n
d
ic
a
t
o
r
s
a
t
u
r
at
i
o
n
a
p
p
r
o
a
c
h
an
d
h
o
w
th
e
a
p
p
r
o
a
c
h
c
an
b
e
a
p
p
l
i
e
d
in
t
o
th
e
l
o
ca
l
l
ev
el
m
o
d
e
l
f
r
am
e
w
o
r
k
.
S
e
c
ti
o
n
3
d
es
c
r
i
b
es
th
e
s
im
u
l
a
ti
o
n
s
e
tt
in
g
f
o
r
th
e
M
o
n
t
e
C
a
r
l
o
e
x
p
e
r
im
en
t
an
d
s
h
o
w
s
th
e
p
e
r
f
o
r
m
an
c
e
o
f
M
o
n
t
e
C
a
r
l
o
s
im
u
l
a
t
i
o
n
s
o
n
th
e
d
e
te
c
t
i
o
n
p
o
w
e
r
o
f
I
I
S
.
T
h
en
,
I
I
S
is
a
p
p
l
i
e
d
t
o
r
e
a
l
s
t
o
ck
p
r
i
c
e
d
at
a
f
o
r
d
e
t
e
ct
in
g
o
u
t
l
i
e
r
s
in
s
e
c
ti
o
n
4
.
F
in
a
l
ly
,
s
e
c
ti
o
n
5
w
r
a
p
s
u
p
th
e
w
h
o
l
e
p
a
p
e
r
.
2.
RE
S
E
ARCH
M
E
T
H
O
D
A
s
i
m
p
le
ex
a
m
p
le
o
f
th
e
s
tate
-
s
p
ac
e
m
o
d
el,
th
e
lo
ca
l
lev
el
m
o
d
el
’
s
le
v
el
co
m
p
o
n
e
n
t
v
ar
i
es
o
v
er
ti
m
e.
I
n
th
e
clas
s
ical
r
e
g
r
ess
io
n
m
o
d
el,
th
is
co
m
p
o
n
e
n
t
ca
n
b
e
v
i
e
w
ed
as
t
h
e
i
n
ter
ce
p
t,
h
o
w
e
v
er
,
in
t
h
e
s
ta
te
-
s
p
ac
e
m
o
d
el,
t
h
e
lev
e
l
co
m
p
o
n
en
t
m
a
y
d
i
f
f
er
ac
co
r
d
in
g
to
s
p
ec
if
ic
ti
m
e
p
o
in
t
s
.
T
h
e
lo
ca
l
le
v
el
m
o
d
el
ca
n
b
e
f
o
r
m
u
lated
as
(
1
)
.
=
+
,
~
(
0
,
2
)
(
1
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
22
,
No
.
3
,
J
u
n
e
2
0
2
1
:
1
6
8
8
-
1
6
9
6
1690
+
1
=
+
,
~
(
0
,
2
)
(
2
)
F
o
r
=
1
,
…
,
w
h
er
e
is
th
e
u
n
o
b
s
er
v
e
d
lev
el
at
ti
m
e
t
,
is
th
e
o
b
s
er
v
atio
n
d
is
t
u
r
b
an
ce
o
r
ir
r
eg
u
lar
co
m
p
o
n
e
n
t
at
ti
m
e
t
an
d
i
s
th
e
lev
el
d
is
t
u
r
b
an
ce
at
tim
e
t
.
Su
p
p
o
s
ed
to
b
e
s
er
ial
l
y
an
d
m
u
tu
a
l
l
y
in
d
ep
en
d
en
t,
th
e
o
b
s
er
v
atio
n
a
n
d
lev
e
l
d
is
t
u
r
b
an
ce
s
ar
e
n
o
r
m
all
y
d
is
tr
ib
u
ted
w
it
h
ze
r
o
m
ea
n
a
n
d
v
ar
ia
n
ce
s
an
d
,
r
esp
ec
tiv
el
y
.
W
e
d
en
o
te
(
1
)
as th
e
o
b
s
er
v
atio
n
eq
u
atio
n
,
w
h
ile
(
2
)
is
k
n
o
w
n
as t
h
e
s
t
ate
eq
u
atio
n
.
T
h
e
tr
an
s
itio
n
eq
u
a
tio
n
s
h
o
w
s
t
h
e
f
u
n
d
a
m
e
n
tal
v
al
u
es
b
ased
o
n
a
r
a
n
d
o
m
w
al
k
.
is
th
e
n
o
is
e
f
r
o
m
t
h
e
f
u
n
d
a
m
en
ta
l
th
at
is
e
x
p
ec
ted
to
b
e
u
n
r
ela
ted
f
r
o
m
a
n
y
c
h
a
n
g
e
ex
p
er
ien
ce
d
b
y
.
T
h
e
s
ig
n
a
l
-
to
-
n
o
is
e
r
atio
o
f
v
ar
ian
ce
s
,
=
2
2
⁄
,
m
ea
s
u
r
es
t
h
e
p
o
ten
c
y
o
f
f
u
n
d
a
m
e
n
tal
v
al
u
e
s
i
g
n
al
v
er
s
u
s
r
a
n
d
o
m
d
ev
iat
io
n
.
Du
e
to
th
is
,
t
h
e
lo
ca
l le
v
el
m
o
d
el
ca
n
also
b
e
d
ef
in
ed
as
r
an
d
o
m
w
al
k
p
lu
s
n
o
is
e
m
o
d
el
[
2
0
]
.
I
n
d
icato
r
s
atu
r
atio
n
m
et
h
o
d
s
in
tr
o
d
u
ce
d
b
y
[
9
]
is
ab
le
to
i
d
en
tify
t
h
e
p
r
esen
ce
o
f
s
ev
er
al
o
u
tlier
s
h
ap
p
en
in
g
at
v
ar
io
u
s
lo
ca
tio
n
s
,
an
d
u
n
k
n
o
w
n
m
a
g
n
it
u
d
es.
Mo
r
eo
v
er
,
a
s
lig
h
t
alter
atio
n
to
th
e
m
o
d
el
m
a
y
r
esu
lt
to
id
en
ti
f
icatio
n
o
f
v
ar
i
o
u
s
d
eter
m
in
i
s
tic
s
tr
u
ct
u
r
al
c
h
an
g
e
f
o
r
m
at
s
[
1
]
.
I
n
t
h
is
s
ec
tio
n
,
w
e
d
is
c
u
s
s
I
I
S
s
ig
n
i
f
ica
n
tl
y
.
I
I
S
is
ab
le
to
g
e
n
er
ate
a
f
u
ll
i
n
d
icato
r
v
ar
iab
le
s
s
et,
e.
g
.
,
f
o
r
T
n
u
m
b
er
o
f
o
b
s
er
v
atio
n
s
,
I
I
S
w
i
ll
cr
ea
te
T
in
d
icato
r
s
i
n
th
e
s
et
o
f
ca
n
d
id
ate
v
ar
iab
le
s
.
Ho
w
e
v
er
,
th
is
m
et
h
o
d
w
o
u
ld
n
o
t
in
co
r
p
o
r
ate
all
in
d
icato
r
s
as
r
eg
r
es
s
o
r
s
to
av
o
id
p
er
f
ec
t
f
it
in
g
e
n
er
al
-
to
-
s
p
ec
if
ic
m
o
d
elli
n
g
p
r
o
ce
s
s
.
I
f
all
th
e
in
d
icato
r
s
ar
e
in
cl
u
d
ed
,
th
e
m
o
d
el
w
il
l
h
a
v
e
m
o
r
e
r
eg
r
es
s
o
r
s
as
co
m
p
ar
ed
to
n
u
m
b
er
o
f
o
b
s
er
v
atio
n
s
,
T
.
T
h
is
w
ill
lead
to
d
eg
r
ee
o
f
f
r
ee
d
o
m
d
ef
icie
n
c
y
[
2
4
]
.
T
h
e
im
p
u
l
s
e
in
d
icato
r
s
d
e
f
in
ed
as
{1
{
h=
t
}
}
w
h
er
e
{1
{
h=
t
}
}
eq
u
als
to
u
n
it
y
w
h
e
n
h
=
t
an
d
eq
u
als to
ze
r
o
o
th
er
w
is
e
f
o
r
ℎ
=
1
,
…
, T.
T
o
illu
s
tr
ate
th
e
p
r
o
ce
d
u
r
e,
[
2
5
]
an
d
[
2
6
]
u
s
ed
th
e
s
p
lit
-
h
a
lf
ap
p
r
o
ac
h
to
in
teg
r
ate
I
I
S
in
to
a
g
en
er
ated
m
o
d
el
=
+
f
o
r
=
1
,
…
,
w
h
er
e
is
n
o
r
m
al
l
y
a
n
d
in
d
ep
en
d
en
t
l
y
d
is
tr
ib
u
ted
w
it
h
m
ea
n
ze
r
o
an
d
v
ar
ian
ce
2
.
Sp
ec
if
icall
y
,
i
n
t
h
e
f
ir
s
t
h
al
f
o
f
th
e
s
a
m
p
le,
2
⁄
i
m
p
u
ls
e
in
d
icato
r
s
ar
e
i
n
cl
u
d
ed
in
t
h
e
m
o
d
el
w
h
ic
h
r
esu
lts
to
:
=
+
∑
ℎ
(
2
⁄
)
ℎ
=
1
ℎ
,
(
ℎ
)
+
,
=
1
,
…
,
2
⁄
(
3
)
w
h
er
e
ℎ
,
(
ℎ
)
is
i
m
p
u
l
s
e
in
d
icato
r
v
ec
to
r
an
d
is
th
e
er
r
o
r
ter
m
w
h
i
ch
~
(
0
,
2
)
.
Me
an
w
h
ile
t
h
e
o
th
er
h
al
f
o
f
th
e
s
a
m
p
le
r
es
u
lt to
:
=
+
∑
ℎ
(
−
2
⁄
)
ℎ
=
1
ℎ
,
(
ℎ
)
+
,
=
2
⁄
,
…
,
(
4
)
T
h
e
s
elec
ted
in
d
icato
r
s
at
t
h
e
ch
o
s
en
s
i
g
n
if
ica
n
ce
v
al
u
e,
ar
e
d
eter
m
in
ed
u
s
i
n
g
th
e
t
-
s
tati
s
tics
v
a
lu
e
in
t
h
e
f
ir
s
t
h
al
f
o
f
t
h
e
s
a
m
p
le.
L
o
ca
tio
n
o
f
s
ig
n
i
f
ica
n
t
in
d
icato
r
s
w
il
l
b
e
r
ec
o
r
d
ed
.
T
h
en
,
2
⁄
i
m
p
u
ls
e
in
d
icato
r
is
ad
d
ed
in
th
e
s
e
co
n
d
h
alf
o
f
t
h
e
s
a
m
p
le,
−
2
⁄
,
af
ter
w
h
ic
h
th
e
s
ele
c
tio
n
p
r
o
ce
d
u
r
e
is
p
er
f
o
r
m
ed
r
ep
etiti
v
el
y
to
o
b
tain
s
i
g
n
i
f
ica
n
t
i
n
d
icato
r
s
u
n
d
er
th
e
n
u
ll
h
y
p
o
t
h
esi
s
o
f
n
o
o
u
tlier
.
Fi
n
all
y
,
a
ter
m
i
n
al
m
o
d
el
i
s
o
b
tain
ed
f
r
o
m
j
o
in
in
g
to
g
et
h
er
t
w
o
s
et
s
o
f
s
ig
n
i
f
ica
n
t d
u
m
m
ie
s
.
T
h
e
s
ele
ctio
n
o
f
s
i
g
n
i
f
ica
n
t
in
d
icato
r
s
d
is
cu
s
s
ed
ab
o
v
e
ad
h
er
es
to
s
eq
u
en
t
ial
s
elec
tio
n
w
h
er
e
th
e
n
o
n
-
s
i
g
n
i
f
ica
n
t
in
d
i
ca
to
r
is
d
r
o
p
p
e
d
o
n
e
at
a
ti
m
e
at
c
h
o
s
en
s
ig
n
i
f
ica
n
t
lev
el.
A
lter
n
a
tiv
e
l
y
,
t
h
er
e
is
an
o
th
er
s
elec
t
io
n
al
g
o
r
ith
m
ca
lled
n
o
n
-
s
eq
u
e
n
tial
s
elec
tio
n
.
I
t
w
o
r
k
s
b
y
d
r
o
p
p
i
n
g
all
n
o
n
-
s
i
g
n
i
f
ican
t
in
d
icato
r
s
s
i
m
u
lta
n
eo
u
s
l
y
at
c
h
o
s
en
in
ev
er
y
p
ar
titi
o
n
.
T
h
e
r
etain
ed
in
d
icato
r
s
ar
e
s
ig
n
i
f
ica
n
t
in
d
icato
r
s
.
T
h
is
ap
p
r
o
ac
h
is
al
w
a
y
s
f
ea
s
ib
le
if
th
e
n
u
m
b
er
o
f
r
eg
r
ess
o
r
s
,
N
eq
u
als
to
th
e
n
u
m
b
er
o
f
o
b
s
er
v
atio
n
s
,
T
.
A
s
m
e
n
tio
n
ed
,
if
th
e
to
tal
n
u
m
b
er
o
f
r
e
g
r
ess
o
r
s
is
h
ig
h
er
t
h
an
th
e
n
u
m
b
er
o
f
o
b
s
er
v
atio
n
s
,
>
,
w
e
co
n
s
id
er
a
cr
o
s
s
b
lo
ck
al
g
o
r
ith
m
p
r
o
p
o
s
ed
b
y
[
2
7
]
.
T
h
is
alg
o
r
ith
m
s
e
g
r
eg
a
tes
all
i
n
d
ic
ato
r
s
in
to
m
b
lo
ck
s
,
a
n
d
th
e
s
elec
tio
n
al
g
o
r
ith
m
is
r
ep
ea
ted
.
Hen
ce
,
th
i
s
g
iv
e
s
a
to
tal
o
f
−
(
−
1
)
2
⁄
r
u
n
s
o
f
th
e
s
elec
tio
n
p
r
o
ce
d
u
r
e.
T
h
is
ap
p
r
o
ac
h
w
a
s
e
m
p
lo
y
ed
b
y
[
1
4
]
o
n
th
e
B
S
M
co
n
tex
t.
I
n
s
p
ir
ed
b
y
t
h
eir
w
o
r
k
,
w
e
in
te
g
r
ated
th
e
I
S
ap
p
r
o
ac
h
in
th
e
lo
ca
l
lev
el
m
o
d
el
as
in
(
5
)
.
W
e
h
av
e
d
ef
in
ed
m
as
to
tal
b
lo
ck
s
in
to
w
h
ic
h
in
d
icato
r
s
ar
e
s
p
lit,
an
d
T
is
m
u
l
tip
les
o
f
m
.
Su
p
p
o
s
ed
th
at
th
e
s
ize
o
f
th
e
b
lo
ck
s
ar
e
s
i
m
ilar
,
h
en
ce
,
t
h
e
o
b
s
er
v
atio
n
eq
u
atio
n
in
(
1
)
is
ex
ten
d
ed
to
:
=
+
∑
ℎ
(
⁄
)
ℎ
=
(
⁄
)
(
ℎ
+
1
)
+
1
ℎ
,
(
ℎ
)
+
,
=
1
,
…
,
(
5
)
w
h
er
e
ℎ
,
(
ℎ
)
d
en
o
tes
I
I
S.
Nex
t,
(
4
)
is
co
n
v
er
ted
in
to
s
tate
-
s
p
ac
e
f
o
r
m
to
g
et
h
er
w
it
h
(
2
)
.
Hen
ce
,
th
e
d
ata
g
en
er
ati
n
g
p
r
o
ce
s
s
(
DGP
)
in
(
5
)
ca
n
b
e
r
ep
r
esen
ted
in
m
atr
i
x
n
o
tatio
n
as:
=
+
(
6
)
w
h
er
e
an
d
ar
e
v
ec
to
r
s
o
f
×
1
.
T
h
e
ter
m
is
th
e
I
I
S
in
m
atr
i
x
f
o
r
m
w
it
h
d
i
m
e
n
s
io
n
×
an
d
is
t
h
e
m
atr
i
x
co
ef
f
icien
t
w
it
h
d
i
m
e
n
s
io
n
×
1
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
Ou
tlier
s
d
etec
tio
n
in
s
ta
te
-
s
p
a
ce
mo
d
el
u
s
in
g
in
d
ica
to
r
s
a
tu
r
a
tio
n
a
p
p
r
o
a
ch
(
F
a
r
id
Za
ma
n
i Ch
e
R
o
s
e
)
1691
R
ep
r
esen
tat
io
n
o
f
I
I
S
m
a
tr
ix
f
o
r
u
n
iv
ar
iate
t
i
m
e
s
er
ies as i
n
[
1
7
]
ca
n
b
e
s
h
o
w
n
a
s
:
1
,
=
(
(
1
)
,
0
,
0
,
…
,
0
)
2
,
=
(
0
,
(
1
)
,
0
,
…
,
0
)
3
,
=
(
0
,
0
,
(
1
)
,
…
,
0
)
⋮
⋮
⋮
⋮
,
=
(
0
,
0
,
0
,
…
,
(
1
)
)
(
7
)
w
h
er
e
ℎ
,
=
(
)
w
h
e
n
ℎ
=
an
d
ze
r
o
f
o
r
ℎ
≠
.
Ass
u
m
e
t
h
at
t
h
er
e
is
a
n
o
u
tlie
r
in
t
h
e
f
ir
s
t
b
lo
c
k
,
1
w
it
h
u
n
k
n
o
w
n
lo
ca
tio
n
,
1
an
d
m
a
g
n
i
tu
d
e
o
f
u
n
k
n
o
w
n
o
u
tlier
d
en
o
ted
as
.
T
h
e
DGP
in
m
atr
i
x
n
o
t
atio
n
w
i
ll
b
e
as
f
o
llo
w
s
:
=
+
(
8
)
w
h
er
e
1
=
(
1
,
1
,
…
,
2
⁄
)
is
d
en
o
ted
as
I
I
S
m
atr
ix
a
n
d
1
=
(
1
,
1
,
…
,
2
⁄
)
is
t
h
e
co
ef
f
ic
ien
t
v
ec
t
o
r
f
o
r
th
e
I
I
S.
T
h
u
s
,
th
e
e
s
ti
m
at
ed
co
ef
f
icie
n
t
f
o
r
I
I
S
v
ec
to
r
i
s
o
b
tain
ed
t
h
r
o
u
g
h
o
r
d
in
ar
y
l
ea
s
t
s
q
u
ar
e
(
O
L
S)
esti
m
atio
n
f
o
r
m
u
lated
as:
=
(
)
−
+
(
)
−
=
+
(
)
−
(
9
)
w
h
er
e
b
is
t
h
e
I
I
S
v
ec
to
r
o
f
s
i
ze
2
⁄
×
1
w
h
ich
co
n
s
i
s
ts
o
f
v
al
u
e
o
n
e
at
th
e
lo
ca
tio
n
o
f
o
u
t
lier
,
=
1
an
d
ze
r
o
else
w
h
er
e.
T
h
e
v
ec
to
r
b
is
o
b
tain
ed
w
h
en
s
o
lv
i
n
g
t
h
e
ex
p
r
ess
io
n
(
1
1
)
−
1
1
1
s
h
o
w
in
g
t
h
e
ele
m
en
t
in
b
at
L
1
-
t
h
r
e
f
lects
t
h
e
m
a
g
n
itu
d
e
o
f
o
u
t
lier
,
.
T
h
e
ex
p
ec
ted
v
alu
e
a
n
d
v
ar
ia
n
ce
o
f
est
i
m
a
to
r
̂
1
ar
e
an
d
2
(
1
1
)
−
1
ar
e
r
esp
ec
tiv
ely
o
b
tain
ed
as
s
h
o
w
n
i
n
[
1
7
]
.
T
h
en
,
th
e
d
is
tr
ib
u
tio
n
o
f
th
e
O
L
S
est
i
m
a
to
r
in
th
e
f
ir
s
t b
lo
ck
i
s
:
̂
−
~
(
,
(
)
−
)
(
1
0
)
T
h
er
ef
o
r
e,
th
e
s
i
g
n
if
ican
ce
t
esti
n
g
i
n
GE
T
S
m
o
d
ellin
g
ca
n
b
e
e
m
p
lo
y
ed
w
it
h
s
tan
d
ar
d
t
-
test
s
tatis
t
ics
as
s
h
o
w
n
i
n
[
1
6
]
.
T
h
e
s
ig
n
i
f
ica
n
ce
in
d
icato
r
o
f
I
I
S
w
il
l
r
etain
i
n
t
h
e
m
o
d
el
i
f
th
e
ab
s
o
lu
te
v
al
u
e
o
f
t
-
s
tatis
t
ics i
s
g
r
ea
ter
o
r
eq
u
al
to
th
e
cr
itic
al
v
al
u
e
o
f
t
h
e
ch
o
s
e
n
s
ig
n
i
f
ica
n
ce
lev
el,
|
̂
|
≥
.
On
t
h
e
o
th
er
h
a
n
d
,
th
e
i
m
p
u
l
s
e
i
n
d
icato
r
w
i
ll b
e
e
li
m
i
n
ated
i
f
|
̂
|
<
o
r
th
e
t
-
s
tatis
tics
is
clo
s
e
to
ze
r
o
.
T
h
en
,
th
e
I
I
S
p
r
o
ce
d
u
r
e
in
GE
T
S
m
o
d
ellin
g
d
escr
ib
ed
in
th
is
s
ec
t
io
n
is
r
ep
ea
ted
f
o
r
th
e
s
ec
o
n
d
b
lo
ck
,
2
an
d
f
in
al
ter
m
i
n
al
m
o
d
el.
3.
RE
SU
L
T
S
A
ND
D
IS
CU
SS
I
O
N
3
.
1
.
M
o
nte
Ca
rl
o
s
i
m
ula
t
io
ns
s
et
t
ing
s
P
er
f
o
r
m
a
n
ce
o
f
th
e
in
d
icato
r
s
atu
r
atio
n
ap
p
r
o
ac
h
is
m
ea
s
u
r
e
d
u
s
in
g
Mo
n
te
C
ar
lo
ex
p
er
i
m
en
ts
.
A
ti
m
e
s
er
ies
i
s
g
en
er
ated
b
ased
o
n
th
e
DGP
in
(
5
)
w
it
h
i
n
itia
l
v
a
lu
es
o
f
co
m
p
o
n
en
ts
2
=
0
.
0563
an
d
2
=
1
.
T
h
e
g
en
er
ated
s
er
ie
s
w
er
e
t
h
e
n
a
d
d
ed
w
ith
ad
d
itiv
e
o
u
tlier
s
(
A
O)
.
F
ir
s
tl
y
,
w
e
co
m
e
o
u
t
w
it
h
a
b
e
n
ch
m
ar
k
s
i
m
u
lat
io
n
s
etti
n
g
f
o
r
th
e
DG
P
an
d
o
u
tlier
d
etec
tio
n
p
r
o
ce
d
u
r
e.
T
h
en
,
w
e
co
n
s
id
er
v
ar
io
u
s
alter
n
ati
v
e
s
etti
n
g
s
to
in
v
est
ig
ate
t
h
e
r
o
b
u
s
tn
e
s
s
o
f
th
e
p
r
o
ce
d
u
r
e.
E
v
er
y
ex
p
er
i
m
e
n
t
in
v
o
lv
e
s
1
0
0
0
r
ep
licatio
n
s
.
T
h
e
f
o
llo
w
i
n
g
ar
e
s
p
ec
if
icatio
n
s
f
o
r
s
i
m
u
lati
o
n
s
etti
n
g
s
f
o
r
a
r
ef
er
en
ce
D
G
P
:
−
Sa
m
p
le
s
ize
T
=
2
4
0
o
b
s
er
v
atio
n
s
,
r
ef
lec
tin
g
2
0
y
ea
r
s
o
f
m
o
n
t
h
l
y
d
ata.
−
L
o
ca
tio
n
s
o
f
t
h
e
AO
ar
e
as:
A
s
i
n
g
le
AO
w
a
s
p
o
s
itio
n
ed
r
ig
h
t
i
n
t
h
e
m
id
d
le
o
f
t
h
e
s
a
m
p
le,
w
h
ile
d
o
u
b
le
A
O
w
er
e
p
r
ed
eter
m
i
n
ed
at
th
e
[
0
.
2
5
,
0
.
7
5
]
as a
s
h
ar
e
o
f
len
g
th
T
.
−
T
ar
g
et
s
ize
o
r
s
ig
n
i
f
ica
n
ce
le
v
el,
α
=
0
.
0
0
1
,
0
.
0
1
an
d
0
.
0
2
5
[
1
3
]
d
ef
in
ed
α
as
t
h
e
s
tatis
tical
t
o
ler
an
ce
o
f
t
h
e
p
r
o
ce
d
u
r
e
to
c
o
n
tr
o
l
th
e
r
is
k
o
f
in
ad
v
er
ten
tl
y
r
etai
n
a
n
y
ir
r
el
ev
an
t
in
d
icato
r
.
Fo
r
ex
a
m
p
le,
a
tar
g
et
o
f
0
.
0
1
f
o
r
I
I
S
in
d
icate
s
t
h
at
o
n
av
er
ag
e,
f
o
r
ev
er
y
1
0
0
o
b
s
er
v
atio
n
s
,
w
e
ac
ce
p
t
a
m
a
x
i
m
u
m
o
f
s
in
g
le
i
m
p
u
l
s
e
d
u
m
m
y
t
h
at
i
s
n
o
t i
n
cl
u
d
ed
in
th
e
d
ata
g
e
n
er
atin
g
p
r
o
ce
s
s
.
−
Size
o
f
an
o
u
tlier
is
g
i
v
en
a
s
w
h
er
e
s
is
a
p
o
s
iti
v
e
i
n
te
g
er
an
d
σ
is
th
e
p
r
ed
ictio
n
e
r
r
o
r
s
tan
d
ar
d
d
ev
iatio
n
(
P
E
SD)
o
f
th
e
s
er
ies.
A
s
a
r
ef
er
en
ce
to
[
1
4
]
,
w
e
s
et
7
σ
as
b
en
ch
m
ar
k
v
al
u
e
th
at
d
eter
m
i
n
es
th
e
s
ize
o
f
an
o
u
tlier
.
Ho
w
e
v
er
,
th
e
s
ize
o
f
o
u
tlier
v
ar
ies f
r
o
m
3
σ
,
5
σ
,
9
σ
an
d
1
2
σ
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
22
,
No
.
3
,
J
u
n
e
2
0
2
1
:
1
6
8
8
-
1
6
9
6
1692
−
T
h
er
e
ar
e
t
w
o
s
ea
r
ch
i
n
g
al
g
o
r
ith
m
s
ap
p
lied
in
th
e
s
i
m
u
lati
o
n
s
w
h
ic
h
ar
e
d
en
o
ted
as
n
o
n
-
s
eq
u
en
tia
l
an
d
s
eq
u
en
tial
al
g
o
r
ith
m
s
in
s
elec
t
in
g
s
i
g
n
if
ican
t
in
d
icato
r
s
.
T
h
e
f
o
r
m
er
lead
s
to
1
-
c
u
t
m
o
d
el
s
elec
tio
n
,
w
h
ile
th
e
latter
lead
s
to
m
u
lti
-
p
ath
m
o
d
el
s
elec
t
io
n
[
1
0
]
.
An
a
d
d
itio
n
al
n
u
m
b
er
o
f
p
ath
s
ca
n
b
e
ad
d
ed
b
y
in
cr
ea
s
i
n
g
t
h
e
n
u
m
b
er
o
f
m
b
l
o
ck
s
o
f
r
eg
r
es
s
o
r
s
as
s
u
g
g
este
d
b
y
[
1
7
]
to
r
ed
u
ce
th
e
v
ar
ian
ce
esti
m
ato
r
an
d
in
cr
ea
s
e
t
h
e
d
etec
tio
n
p
o
w
er
o
f
I
I
S.
−
W
ith
r
eg
ar
d
to
o
u
tl
ier
d
etec
tio
n
p
r
o
ce
d
u
r
e
u
s
i
n
g
I
I
S,
t
h
e
i
n
d
icato
r
v
ar
iab
les
ar
e
d
iv
id
ed
i
n
t
o
t
w
o
,
f
o
u
r
a
n
d
s
ix
b
lo
ck
s
.
−
T
h
e
lo
ca
tio
n
s
o
f
A
O
also
v
ar
y
b
ased
o
n
th
e
s
h
ar
e
o
f
t
h
e
s
a
m
p
le.
W
e
d
ec
id
ed
t
o
d
eter
m
in
e
t
h
e
ap
p
r
o
p
r
iate
s
ize
o
f
A
O
i
n
o
u
r
Mo
n
te
C
ar
lo
ex
p
er
i
m
e
n
t
s
u
s
i
n
g
P
E
SD
s
in
ce
w
e
d
ea
l
w
it
h
m
u
ltip
le
s
o
u
r
ce
s
o
f
d
is
t
u
r
b
an
ce
s
i
n
t
h
e
s
tr
u
ct
u
r
al
ti
m
e
s
er
ies.
As
m
e
n
tio
n
ed
,
w
e
d
en
o
te
σ
as P
E
SD o
f
th
e
s
tead
y
-
s
tate
i
n
n
o
v
atio
n
.
I
t c
an
b
e
f
o
r
m
u
lated
as:
=
−
(
|
−
1
)
=
−
(
|
−
1
)
+
(
1
1
)
w
h
er
e
=
{
−
1
,
−
2
,
…
,
1
}
.
Mo
r
eo
v
er
,
th
is
ap
p
r
o
ac
h
is
also
co
n
s
is
te
n
t
w
it
h
[
2
8
]
an
d
[
2
9
]
.
Ov
er
all,
w
e
m
ea
s
u
r
ed
th
e
r
o
b
u
s
tn
e
s
s
o
f
m
o
d
el
b
ased
o
n
f
e
w
asp
ec
t
s
w
h
i
ch
ar
e
n
u
m
b
er
o
f
o
b
s
er
v
atio
n
s
,
T
,
n
u
m
b
er
o
f
AO
ad
d
ed
,
v
alu
es o
f
tar
g
et
s
ize,
m
ag
n
i
tu
d
e
o
f
A
O,
n
u
m
b
er
o
f
b
l
o
ck
s
esti
m
atio
n
an
d
lo
ca
tio
n
s
o
f
AO
in
t
h
e
s
er
ie
s
.
3
.
2
.
E
v
a
lua
t
ing
t
he
perf
o
r
m
a
nce
o
f
M
o
nte
Ca
rlo
ex
perim
e
nt
T
h
e
m
ai
n
g
o
al
o
f
t
h
e
Mo
n
te
C
ar
lo
ex
p
er
i
m
e
n
t
i
s
to
g
a
u
g
e
t
h
e
ef
f
ic
ien
c
y
o
f
I
I
S
i
n
t
h
e
l
o
ca
l
lev
el
m
o
d
el.
T
h
er
ef
o
r
e,
w
e
ap
p
l
y
th
e
co
n
ce
p
ts
o
f
p
o
ten
c
y
a
n
d
g
au
g
e
to
ass
e
s
s
t
h
e
p
er
f
o
r
m
an
ce
o
f
t
h
e
o
u
tlier
d
etec
tio
n
p
r
o
ce
d
u
r
e.
P
o
ten
cy
ca
n
b
e
d
ef
in
ed
as
th
e
p
r
o
p
o
r
ti
o
n
o
f
r
elev
an
t
i
n
d
icato
r
th
at
r
e
m
ai
n
ed
in
th
e
f
in
a
l
m
o
d
el,
w
h
ile
g
a
u
g
e
is
t
h
e
p
r
o
p
o
r
tio
n
o
f
ir
r
elev
an
t
i
n
d
icato
r
th
at
r
e
m
ai
n
ed
in
t
h
e
f
i
n
al
m
o
d
el.
B
o
th
co
n
ce
p
ts
ar
e
co
m
p
u
ted
b
ased
o
n
th
e
r
eten
tio
n
r
ate
d
en
o
ted
b
y
:
̃
=
1
∑
1
[
̂
≠
0
]
,
=
1
,
…
,
=
1
(
1
2
)
=
1
∑
̂
,
(
1
3
)
=
1
−
∑
̂
,
−
(
1
4
)
w
h
er
e
M
d
en
o
te
s
t
h
e
n
u
m
b
er
o
f
r
ep
licatio
n
a
n
d
n
is
th
e
n
u
m
b
er
o
f
tr
u
e
o
u
tlier
s
in
a
p
ar
t
icu
lar
ti
m
e
s
er
ie
s
o
f
len
g
th
T
.
Hen
ce
,
let
an
d
−
b
e
s
ets
o
f
ti
m
e
i
n
d
ices
f
o
r
r
elev
a
n
t
an
d
ir
r
elev
a
n
t
in
d
icato
r
s
i
n
th
e
m
o
d
el
r
esp
ec
tiv
el
y
.
Me
a
n
w
h
ile,
̂
d
en
o
tes
esti
m
ated
co
ef
f
icien
t
i
n
t
h
e
i
m
p
u
ls
e
i
n
d
icato
r
an
d
if
ℎ
,
(
ℎ
)
is
s
elec
ted
,
th
en
th
e
v
ar
iab
le
1
[
̂
≠
0
]
w
ill
ta
k
e
v
a
lu
e
o
n
e,
w
h
er
e
o
n
e
m
ea
n
s
tr
u
e
an
d
ze
r
o
o
th
er
w
is
e.
W
e
f
o
ll
o
w
ed
th
e
r
u
le
o
f
t
h
u
m
b
s
u
g
g
e
s
ted
b
y
[
3
0
]
to
d
eter
m
i
n
e
t
h
e
v
a
lu
e
o
f
tar
g
et
s
ize
=
[
0
.
05
,
1
⁄
]
in
s
to
c
k
r
etu
r
n
s
er
ies.
T
h
is
w
ill
en
s
u
r
e
th
e
lo
w
g
a
u
g
e
v
a
lu
e
b
elo
w
5
%
o
f
th
e
s
a
m
p
le,
T
o
r
o
n
ly
o
n
e
ir
r
elev
an
t
i
n
d
icato
r
v
ar
iab
le
is
m
a
in
ta
in
ed
i
n
th
e
f
in
al
m
o
d
el.
O
n
th
e
o
t
h
er
h
a
n
d
,
th
e
co
n
ce
p
t
o
f
p
o
ten
c
y
a
n
d
g
au
g
e
u
s
ed
in
t
h
is
s
tu
d
y
ca
n
b
e
ill
u
s
tr
ated
as
a
co
n
f
u
s
io
n
m
atr
ix
a
s
i
n
[
1
4
]
.
Ho
w
e
v
er
,
th
e
f
o
llo
w
i
n
g
co
n
f
u
s
io
n
m
atr
i
x
o
n
l
y
s
u
m
m
ar
izes t
h
e
r
esu
lt o
f
o
n
e
Mo
n
te
C
ar
lo
ex
p
er
i
m
e
n
t
s
h
o
wn
in
T
ab
le
1
.
T
ab
le
1
.
Su
m
m
ar
y
r
es
u
lt o
f
o
n
e
Mo
n
te
C
ar
lo
ex
p
er
i
m
e
n
t
A
c
t
u
a
l
P
r
e
d
i
c
t
e
d
T
o
t
a
l
N
o
o
u
t
l
i
e
r
O
u
t
l
i
e
r
N
o
o
u
t
l
i
e
r
W
X
M
(
T
-
n)
O
u
t
l
i
e
r
Y
Z
Mn
T
o
t
a
l
W
+
Y
X
+
Z
MT
W
an
d
Z
ar
e
k
n
o
w
n
as
tr
u
e
p
o
s
itiv
e
a
n
d
tr
u
e
n
e
g
ati
v
e,
d
en
o
te
n
u
m
b
er
s
o
f
co
r
r
ec
t
d
ec
is
io
n
s
m
ad
e
.
On
th
e
o
th
er
h
a
n
d
,
X
an
d
Y,
also
k
n
o
w
n
as
a
f
al
s
e
p
o
s
itiv
e
an
d
f
alse
n
eg
a
tiv
e,
d
en
o
te
f
al
s
e
d
ec
is
io
n
s
w
h
e
n
th
er
e
is
n
o
o
u
tlier
o
r
o
n
e
o
u
tli
er
,
r
esp
ec
tiv
el
y
.
Hen
ce
,
th
e
p
o
ten
c
y
is
d
ef
i
n
ed
as
th
e
r
atio
o
f
Z
/M
n
.
Me
a
n
w
h
ile,
th
e
g
a
u
g
e
is
g
iv
e
n
b
y
t
h
e
r
atio
o
f
X/[
M(
T
-
n
)
]
.
T
h
e
p
o
ten
cy
an
d
g
a
u
g
e
v
al
u
es
w
er
e
tab
u
la
ted
in
T
ab
les
2
an
d
3
as
a
r
esu
lt
o
f
a
n
o
n
-
s
eq
u
en
tia
l
s
ea
r
ch
i
n
g
al
g
o
r
ith
m
ad
o
p
ted
.
I
t
is
ev
id
en
t
th
at
a
v
ar
i
et
y
o
f
f
ac
to
r
s
s
ig
n
i
f
ica
n
tl
y
co
n
tr
ib
u
te
to
r
eten
tio
n
r
ate,
̃
w
h
e
n
I
I
S
ap
p
r
o
ac
h
is
im
p
le
m
en
ted
.
A
O
s
ize
p
la
y
s
a
d
o
m
i
n
an
t
r
o
le
in
r
ete
n
tio
n
r
ate.
As
ex
a
m
i
n
ed
clo
s
el
y
,
ch
an
g
es
in
p
o
ten
c
y
v
alu
e
ab
o
u
t
5
0
%
is
f
o
u
n
d
to
b
e
m
o
r
e
n
o
ticea
b
le
w
h
en
t
h
e
s
ize
o
f
AO
in
cr
ea
s
ed
f
r
o
m
3
σ
to
5
σ
.
Me
an
w
h
ile,
t
h
e
d
if
f
er
e
n
ce
s
lo
w
l
y
r
ed
u
ce
s
w
h
e
n
t
h
e
tar
g
et
s
ize
i
n
cr
ea
s
e
s
.
Ho
w
ev
e
r
,
as
ex
p
ec
ted
,
th
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
Ou
tlier
s
d
etec
tio
n
in
s
ta
te
-
s
p
a
ce
mo
d
el
u
s
in
g
in
d
ica
to
r
s
a
tu
r
a
tio
n
a
p
p
r
o
a
ch
(
F
a
r
id
Za
ma
n
i Ch
e
R
o
s
e
)
1693
p
o
ten
c
y
r
ea
ch
es
o
v
er
9
0
%
as
t
h
e
s
ize
o
f
A
O
i
n
cr
ea
s
es
m
o
r
e
th
an
7
,
alth
o
u
g
h
w
it
h
a
s
m
all
i
n
ac
cu
r
ac
y
.
On
t
h
e
o
th
er
h
a
n
d
,
th
e
g
a
u
g
e
v
al
u
es
clu
s
ter
ed
ar
o
u
n
d
th
e
c
h
o
s
e
n
.
T
h
is
p
r
o
v
es
th
a
t
t
h
e
s
i
g
n
i
f
ican
ce
lev
el
i
s
ab
le
t
o
co
n
tr
o
l th
e
r
is
k
o
f
ir
r
elev
a
n
t i
n
d
icato
r
s
in
ad
v
er
ten
tl
y
r
etai
n
ed
in
th
e
f
i
n
al
ter
m
in
al
m
o
d
el.
T
ab
le
2
.
P
o
ten
cy
a
n
d
g
a
u
g
e
v
a
lu
es
w
h
e
n
co
n
ta
m
i
n
ated
w
ith
s
in
g
le
A
O
w
i
th
d
i
f
f
er
e
n
t si
g
n
i
f
ica
n
t v
al
u
es
u
s
in
g
n
o
n
-
s
eq
u
en
tia
l selec
tio
n
2
b
l
o
c
k
s e
st
i
ma
t
i
o
n
4
b
l
o
c
k
s e
st
i
ma
t
i
o
n
6
b
l
o
c
k
s e
st
i
ma
t
i
o
n
T
=
2
4
0
α
3σ
5σ
7σ
9σ
12σ
3σ
5σ
7σ
9σ
12σ
3σ
5σ
7σ
9σ
12σ
P
o
t
e
n
c
y
0
.
0
0
1
1
8
.
7
7
1
.
9
9
4
.
2
9
8
.
8
1
0
0
1
8
.
7
6
3
.
5
9
4
.
2
9
3
.
5
9
9
.
8
1
3
.
7
7
1
.
9
9
3
.
6
9
8
.
2
9
9
.
9
0
.
0
1
4
5
.
6
8
8
.
6
9
8
.
5
9
9
.
9
1
0
0
4
3
.
6
7
3
.
7
9
8
.
5
1
0
0
1
0
0
4
6
.
6
8
8
.
2
9
7
.
7
9
9
.
6
1
0
0
0
.
0
2
5
5
8
.
1
7
8
.
7
9
6
.
1
1
0
0
1
0
0
5
6
.
6
8
2
.
7
9
9
.
2
9
9
.
9
1
0
0
5
6
.
4
9
2
.
8
9
9
.
1
9
9
.
6
1
0
0
G
a
u
g
e
0
.
0
0
1
0
.
1
3
0
.
3
5
0
.
4
4
0
.
4
5
0
.
4
6
0
.
1
8
0
.
2
5
0
.
4
5
0
.
1
1
0
.
0
4
0
.
3
3
0
.
4
9
0
.
0
7
0
.
0
5
0
.
0
1
0
.
0
1
1
.
1
3
1
.
2
4
1
.
1
8
1
.
1
1
1
.
0
2
1
.
0
3
0
.
9
9
0
.
9
8
0
.
1
4
0
.
5
8
1
.
0
6
1
.
0
7
0
.
6
4
0
.
3
5
0
.
3
3
0
.
0
2
5
0
.
2
7
0
.
4
6
0
.
5
2
2
.
8
8
2
.
5
8
3
.
0
9
2
.
7
9
2
.
3
3
1
.
0
4
1
.
3
9
2
.
7
9
2
.
5
7
1
.
9
9
1
.
9
7
1
.
0
2
T
ab
le
3
.
P
o
ten
cy
a
n
d
g
a
u
g
e
v
a
lu
es
w
h
e
n
co
n
ta
m
i
n
ated
w
ith
d
o
u
b
le
A
O
w
it
h
d
if
f
er
e
n
t si
g
n
if
ica
n
t v
a
lu
e
s
u
s
i
n
g
n
o
n
-
s
eq
u
e
n
tial selec
tio
n
2
b
l
o
c
k
s e
st
i
ma
t
i
o
n
4
b
l
o
c
k
s e
st
i
ma
t
i
o
n
6
b
l
o
c
k
s e
st
i
ma
t
i
o
n
T
=
2
4
0
α
3σ
5σ
7σ
9σ
12σ
3σ
5σ
7σ
9σ
12σ
3σ
5σ
7σ
9σ
12σ
P
o
t
e
n
c
y
0
.
0
0
1
1
3
.
3
7
0
.
8
9
3
.
7
9
7
.
3
9
9
.
9
2
1
.
2
7
0
.
8
9
3
.
7
9
8
.
5
9
9
.
9
2
1
.
2
7
0
.
7
9
3
.
7
9
9
.
0
9
9
.
9
0
.
0
1
4
6
.
3
8
6
.
8
9
8
.
1
9
9
.
3
1
0
0
4
5
.
7
8
6
.
5
9
8
.
1
9
8
.
8
1
0
0
4
5
.
3
8
6
.
4
9
8
.
1
9
9
.
8
1
0
0
0
.
0
2
5
6
1
.
1
9
2
.
5
9
9
.
0
9
9
.
8
1
0
0
5
9
.
7
9
2
.
3
9
9
.
0
9
9
.
9
1
0
0
5
8
.
7
9
2
.
1
9
9
.
0
9
9
.
9
1
0
0
G
a
u
g
e
0
.
0
0
1
0
.
0
8
0
.
0
4
0
.
0
2
0
.
0
1
0
.
0
0
0
.
0
5
0
.
0
8
0
.
0
4
0
.
0
3
0
.
0
4
0
.
2
1
0
.
1
2
0
.
0
6
0
.
0
2
0
.
0
9
0
.
0
1
0
.
8
4
0
.
6
9
0
.
5
1
0
.
4
9
0
.
2
2
0
.
7
7
0
.
5
8
0
.
3
8
0
.
4
2
0
.
3
2
0
.
7
8
0
.
5
3
0
.
2
9
0
.
1
5
0
.
3
3
0
.
0
2
5
3
.
1
6
2
.
5
4
1
.
8
5
1
.
5
0
1
.
9
4
2
.
6
4
2
.
0
2
1
.
3
6
1
.
1
7
1
.
0
9
2
.
3
1
1
.
6
9
1
.
1
1
0
.
6
7
0
.
7
4
I
I
S
also
p
er
f
o
r
m
ed
w
el
l
in
s
eq
u
en
t
ial
s
elec
tio
n
,
as
s
h
o
w
n
in
T
ab
les
4
an
d
5
w
it
h
th
e
p
o
ten
c
y
al
m
o
s
t
r
ea
ch
es
1
0
0
%
f
o
r
b
en
ch
m
ar
k
s
ettin
g
s
.
W
h
en
t
h
e
s
ize
o
f
A
O
i
n
cr
ea
s
ed
f
r
o
m
3
to
5
,
th
e
m
et
h
o
d
is
ab
le
to
i
m
p
r
o
v
e
it
s
i
n
s
tan
t
id
en
ti
f
icat
io
n
r
ate
cir
ca
5
0
%.
T
h
i
s
s
h
o
w
s
t
h
at
t
h
e
I
I
S
ef
f
icie
n
c
y
i
s
h
ig
h
l
y
r
elate
d
to
th
e
m
ag
n
it
u
d
e
o
f
AO,
as
s
ee
n
in
[
1
4
]
,
[
1
7
]
,
[
2
3
]
.
A
s
id
e
f
r
o
m
th
at,
to
tal
n
u
m
b
er
o
f
b
lo
ck
s
,
m
is
also
a
v
ital
cr
iter
io
n
th
at
a
f
f
ec
ts
t
h
e
p
er
f
o
r
m
a
n
ce
o
f
I
I
S
to
d
etec
t
o
u
t
lier
ev
en
t
h
o
u
g
h
t
h
er
e
is
a
s
eq
u
en
tial
s
elec
tio
n
alg
o
r
ith
m
i
n
t
h
e
I
S
ap
p
r
o
ac
h
.
T
h
u
s
,
w
e
d
ec
id
ed
to
s
i
m
u
lat
e
u
s
i
n
g
t
w
o
,
f
o
u
r
an
d
s
ix
b
lo
ck
s
f
o
r
b
o
th
s
er
ies
.
T
h
e
n
u
m
b
er
o
f
b
lo
ck
s
s
el
ec
t
ed
is
b
ased
o
n
[
1
4
]
to
m
i
n
i
m
ize
t
h
e
r
is
k
o
f
m
is
s
i
n
g
a
n
y
ess
e
n
tial
s
tr
u
ct
u
r
al
ch
an
g
e
i
f
th
er
e
ar
e
to
o
m
a
n
y
b
lo
ck
s
u
s
ed
.
W
e
al
s
o
d
is
co
v
er
ed
th
at
o
n
e
li
m
itatio
n
o
f
I
I
S
is
an
y
ad
d
itio
n
a
l
b
lo
ck
s
,
m
m
o
r
e
th
a
n
ten
w
ill n
o
t le
ad
to
th
e
d
etec
tio
n
o
f
o
u
tli
er
s
in
th
e
s
a
m
p
le
o
b
s
er
v
a
tio
n
.
T
ab
le
4
.
P
o
ten
cy
a
n
d
g
a
u
g
e
v
a
lu
es
w
h
e
n
co
n
ta
m
i
n
ated
w
ith
s
in
g
le
A
O
w
i
th
d
i
f
f
er
e
n
t si
g
n
i
f
ica
n
t v
al
u
es
u
s
in
g
s
eq
u
en
tial selec
t
io
n
2
b
l
o
c
k
s e
st
i
ma
t
i
o
n
4
b
l
o
c
k
s e
st
i
ma
t
i
o
n
6
b
l
o
c
k
s e
st
i
ma
t
i
o
n
T
=
2
4
0
α
3σ
5σ
7σ
9σ
12σ
3σ
5σ
7σ
9σ
12σ
3σ
5σ
7σ
9σ
12σ
P
o
t
e
n
c
y
0
.
0
0
1
1
9
.
7
7
5
.
6
9
7
.
6
9
9
.
8
1
0
0
2
1
.
1
7
3
.
9
9
7
.
6
9
9
.
8
1
0
0
2
3
.
4
7
7
.
8
9
8
.
0
9
9
.
6
1
0
0
0
.
0
1
5
0
.
1
9
2
.
5
9
9
.
7
9
9
.
9
1
0
0
4
7
.
0
9
2
.
4
9
9
.
7
1
0
0
1
0
0
4
8
.
0
9
2
.
7
9
9
.
5
1
0
0
1
0
0
0
.
0
2
5
6
4
.
2
9
6
.
7
1
0
0
1
0
0
1
0
0
5
9
.
5
9
5
.
5
9
9
.
9
1
0
0
1
0
0
6
0
.
9
9
6
.
4
9
9
.
9
1
0
0
1
0
0
G
a
u
g
e
0
.
0
0
1
0
.
0
5
0
.
1
0
0
.
0
3
0
.
0
4
0
.
0
2
0
.
1
2
0
.
0
8
0
.
0
2
0
.
0
1
0
.
0
1
0
.
0
9
0
.
0
9
0
.
0
4
0
.
0
1
0
.
0
1
0
.
0
1
0
.
8
7
0
.
7
3
0
.
7
0
0
.
5
9
0
.
5
6
0
.
7
8
0
.
6
1
0
.
3
3
0
.
2
6
0
.
1
6
0
.
7
2
0
.
5
9
0
.
3
2
0
.
2
0
0
.
1
2
0
.
0
2
5
3
.
1
2
2
.
6
3
2
.
2
8
2
.
0
2
1
.
9
1
2
.
5
6
1
.
9
1
1
.
3
4
0
.
8
8
0
.
6
2
2
.
3
4
1
.
6
9
1
.
1
8
0
.
7
6
0
.
4
4
T
ab
le
5
.
P
o
ten
cy
a
n
d
g
a
u
g
e
v
a
lu
es
w
h
e
n
co
n
ta
m
i
n
ated
w
ith
d
o
u
b
le
A
O
w
it
h
d
if
f
er
e
n
t si
g
n
if
ica
n
t v
a
lu
e
s
u
s
i
n
g
s
eq
u
e
n
tial
s
elec
tio
n
2
b
l
o
c
k
s e
st
i
ma
t
i
o
n
4
b
l
o
c
k
s e
st
i
ma
t
i
o
n
6
b
l
o
c
k
s e
st
i
ma
t
i
o
n
T
=
2
4
0
α
3σ
5σ
7σ
9σ
12σ
3σ
5σ
7σ
9σ
12σ
3σ
5σ
7σ
9σ
12σ
P
o
t
e
n
c
y
0
.
0
0
1
2
0
.
2
7
1
.
8
9
5
.
0
9
8
.
8
1
0
0
1
9
.
1
7
0
.
3
9
4
.
6
9
9
.
5
1
0
0
1
9
.
6
7
1
.
6
9
5
.
1
9
9
.
3
1
0
0
0
.
0
1
4
8
.
7
9
0
.
1
9
8
.
7
1
0
0
1
0
0
4
7
.
3
8
9
.
0
9
8
.
8
9
9
.
9
1
0
0
4
7
.
1
9
0
.
6
9
8
.
6
9
9
.
9
1
0
0
0
.
0
2
5
6
4
.
0
9
4
.
5
9
9
.
3
9
9
.
9
1
0
0
6
1
.
7
9
3
.
3
9
9
.
4
9
9
.
9
1
0
0
6
0
.
5
9
3
.
1
9
9
.
5
1
0
0
1
0
0
G
a
u
g
e
0
.
0
0
1
0
.
0
3
0
.
0
2
0
.
0
1
0
.
0
1
0
.
0
0
0
.
1
1
0
.
0
1
0
.
0
3
0
.
0
0
0
.
0
0
0
.
0
9
0
.
0
5
0
.
0
2
0
.
0
0
0
.
0
0
0
.
0
1
0
.
7
8
0
.
5
1
0
.
2
8
0
.
1
2
0
.
0
2
0
.
6
8
0
.
3
4
0
.
1
8
0
.
0
8
0
.
0
1
0
.
6
4
0
.
3
0
0
.
1
1
0
.
0
3
0
.
0
1
0
.
0
2
5
2
.
8
3
1
.
7
8
1
.
0
7
0
.
5
7
0
.
1
7
2
.
2
4
1
.
3
8
0
.
7
4
0
.
3
3
0
.
0
8
1
.
9
3
1
.
0
9
0
.
5
2
0
.
2
2
0
.
0
5
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
22
,
No
.
3
,
J
u
n
e
2
0
2
1
:
1
6
8
8
-
1
6
9
6
1694
As
ex
a
m
in
ed
clo
s
el
y
i
n
T
ab
l
e
6
,
w
e
f
o
u
n
d
s
y
m
m
etr
y
p
att
er
n
f
o
r
p
o
ten
cy
v
alu
e
s
w
h
e
n
th
e
AO
is
lo
ca
ted
in
th
e
s
a
m
p
le
o
b
s
er
v
a
tio
n
s
.
P
er
f
o
r
m
a
n
ce
o
f
I
I
S
i
s
a
f
f
ec
ted
b
y
t
h
e
lo
ca
tio
n
o
f
A
O
w
h
er
e
t
h
e
p
o
ten
c
y
v
alu
e
is
t
h
e
h
ig
h
es
t
w
h
e
n
AO
is
lo
ca
ted
in
th
e
m
id
d
le
o
f
th
e
o
b
s
er
v
atio
n
.
T
h
e
t
w
o
o
u
tlier
s
w
er
e
lo
ca
ted
to
g
eth
er
i
n
t
h
e
s
a
m
e
s
a
m
p
le
h
alf
as
s
u
g
g
es
ted
in
[
1
4
]
to
all
o
w
i
m
m
ed
iate
o
u
t
lier
s
d
etec
ti
o
n
.
T
h
e
id
ea
b
eh
in
d
th
is
is
th
at
th
e
i
m
p
u
l
s
e
i
n
d
icato
r
s
in
t
h
e
h
al
f
s
a
m
p
le
co
v
er
all
th
e
o
u
tlier
s
.
T
ab
le
6
s
h
o
w
s
th
a
t
o
v
er
all
g
a
u
g
e
v
alu
e
s
o
b
tain
ed
ar
e
s
ati
s
f
ac
t
o
r
y
b
ec
au
s
e
t
h
eir
v
al
u
es
ar
e
less
t
h
an
3
%,
w
h
ic
h
i
n
d
ic
ates
th
a
t
th
e
y
ar
e
tig
h
tl
y
c
lu
s
ter
ed
ar
o
u
n
d
th
e
ch
o
s
en
s
ig
n
i
f
ica
n
ce
lev
e
l.
Hig
h
er
tar
g
e
t
s
ize
w
ill
lead
to
to
o
m
a
n
y
r
ete
n
tio
n
d
u
m
m
ie
s
[
2
2
]
.
T
h
u
s
,
th
i
s
ex
p
l
ain
s
h
i
g
h
er
g
a
u
g
e
v
al
u
e
s
if
w
e
s
et
α
=
2
.
5
%.
T
ab
le
6
.
P
o
ten
cy
a
n
d
g
a
u
g
e
v
a
lu
es a
t d
i
f
f
er
e
n
t lo
ca
tio
n
s
.
L
o
c
a
t
i
o
n
o
f
s
i
n
g
l
e
A
O
L
o
c
a
t
i
o
n
s o
f
d
o
u
b
l
e
A
O
0
.
1
0
.
3
0
.
5
0
.
7
0
.
9
[
0
.
1
,
0
.
2
]
[
0
.
3
,
0
.
4
]
[
0
.
5
,
0
.
6
]
[
0
.
7
,
0
.
8
]
[
0
.
9
,
1
]
P
o
t
e
n
c
y
9
5
.
2
9
7
.
2
97
9
6
.
1
9
4
.
4
9
5
.
3
9
6
.
6
9
7
.
0
9
5
.
8
9
4
.
3
G
a
u
g
e
0
.
6
6
0
.
6
7
0
.
6
7
0
.
6
4
0
.
6
3
0
.
2
3
0
.
2
3
0
.
1
3
0
.
2
0
0
.
2
0
*
L
o
c
a
t
i
o
n
o
f
A
O
i
s g
i
v
e
n
a
s
a
sh
a
r
e
o
f
samp
l
e
l
e
n
g
t
h
,
T
4.
E
M
P
I
RICAL
AP
P
L
I
CA
T
I
O
N
T
h
i
s
s
u
b
s
e
ct
i
o
n
w
il
l
d
em
o
n
s
t
r
a
t
e
th
e
u
t
il
i
z
at
i
o
n
o
f
I
I
S
t
o
th
e
s
t
o
ck
r
e
tu
r
n
o
f
th
e
F
T
S
E
U
SA
Sh
a
r
i
ah
i
n
d
ex
.
T
h
e
s
e
r
i
es
c
o
n
s
is
ts
o
f
1
4
2
c
l
o
s
i
n
g
m
o
n
th
ly
p
r
ic
e
s
f
r
o
m
O
c
t
o
b
e
r
2
0
0
7
u
n
t
i
l
J
u
ly
2
0
1
9
.
W
e
a
i
m
e
d
t
o
c
h
a
r
a
ct
e
r
i
z
e
an
y
s
t
r
u
c
tu
r
a
l
c
h
a
n
g
e
s
u
c
h
as
r
e
c
ess
i
o
n
a
r
y
p
e
r
i
o
d
t
r
i
g
g
e
r
e
d
b
y
an
y
f
in
an
c
i
al
c
r
i
s
is
v
i
a
in
d
i
ca
t
o
r
s
a
tu
r
a
ti
o
n
a
p
p
r
o
a
c
h
.
T
h
e
r
e
f
e
r
en
c
e
m
o
d
el
u
s
e
d
is
th
e
l
o
c
a
l l
ev
e
l
m
o
d
e
l
,
a
s
m
en
t
i
o
n
e
d
in
s
e
c
tio
n
2
.
T
h
e
s
e
l
e
ct
i
o
n
o
f
t
a
r
g
et
s
i
z
e
o
r
s
ig
n
if
i
c
an
ce
le
v
e
l
is
d
e
t
e
r
m
in
e
d
b
y
1
⁄
=
0
.
0071
.
S
e
c
ti
o
n
3
s
h
o
w
s
t
h
e
s
i
g
n
if
i
c
an
c
e
o
f
t
o
t
a
l
n
u
m
b
e
r
o
f
b
l
o
ck
s
,
m
,
o
n
th
e
s
t
u
d
y
o
u
t
p
u
t
o
r
o
u
t
li
e
r
s
d
e
t
e
c
ted
.
T
h
u
s
,
w
e
d
e
ci
d
e
d
t
o
g
en
e
r
at
e
th
e
r
esu
l
ts
u
s
in
g
tw
o
,
f
o
u
r
,
s
ix
an
d
t
en
b
l
o
ck
s
,
b
e
f
o
r
e
c
o
m
b
in
in
g
al
l
s
ig
n
if
i
c
an
t
i
n
d
ic
a
t
o
r
s
in
f
in
a
l
t
e
r
m
in
a
l
m
o
d
e
l
.
A
n
in
t
e
r
es
ti
n
g
p
a
t
t
e
r
n
em
e
r
g
e
d
w
h
en
w
e
ex
am
in
e
t
h
e
r
e
s
u
lt
s
o
f
I
I
S
t
a
b
u
l
a
ted
i
n
T
a
b
l
e
7
a
n
d
F
ig
u
r
e
1
.
T
ab
le
7
.
Ou
tlier
s
d
etec
ted
in
F
T
SE
USA
S
h
ar
iah
s
to
ck
r
etu
r
n
u
s
in
g
I
I
S
N
u
mb
e
r
o
f
b
l
o
c
k
s,
m
2
4
6
8
10
Jan
-
08
Jan
-
08
Jan
-
08
Jan
-
08
Jan
-
08
S
e
p
-
08
S
e
p
-
08
S
e
p
-
08
S
e
p
-
08
S
e
p
-
08
Jan
-
09
Jan
-
09
Jan
-
09
Jan
-
09
Jan
-
09
A
p
r
-
10
Fig
u
r
e
1
.
R
esu
lts
o
b
tain
ed
f
r
o
m
th
e
i
m
p
u
ls
e
i
n
d
icato
r
s
atu
r
a
tio
n
m
o
d
el.
T
h
e
u
p
p
er
m
o
s
t f
i
g
u
r
e
p
o
r
tr
ay
s
o
b
s
er
v
ed
(
b
lu
e)
an
d
f
its
(
r
ed
)
ti
m
e
s
er
ie
s
,
r
esp
ec
tiv
el
y
.
T
h
e
ce
n
tr
al
f
i
g
u
r
e
p
o
r
tr
ay
s
t
h
e
s
tan
d
ar
d
ized
r
esid
u
als;
w
h
ile
t
h
e
b
o
tto
m
m
o
s
t f
ig
u
r
e
p
o
r
tr
ay
s
t
h
e
co
ef
f
icie
n
t p
ath
to
g
eth
er
w
it
h
th
e
i
n
ter
ce
p
t a
n
d
es
ti
m
ated
9
5
%
co
n
f
id
e
n
ce
in
ter
v
al
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
Ou
tlier
s
d
etec
tio
n
in
s
ta
te
-
s
p
a
ce
mo
d
el
u
s
in
g
in
d
ica
to
r
s
a
tu
r
a
tio
n
a
p
p
r
o
a
ch
(
F
a
r
id
Za
ma
n
i Ch
e
R
o
s
e
)
1695
T
h
e
d
u
m
m
y
v
ar
iab
les
r
etain
ed
in
t
h
e
m
o
d
el
ar
e
t
h
e
s
a
m
e
e
v
e
n
t
h
o
u
g
h
w
e
v
ar
y
t
h
e
n
u
m
b
er
o
f
b
lo
ck
s
,
m
u
s
in
g
s
eq
u
e
n
tial
s
elec
tio
n
alg
o
r
ith
m
.
T
h
u
s
,
w
e
co
n
cl
u
d
ed
th
at
t
h
e
o
u
tl
ier
s
d
etec
te
d
in
J
an
u
ar
y
2
0
0
8
,
Sep
te
m
b
er
2
0
0
8
an
d
J
an
u
ar
y
2
0
0
9
c
o
r
r
esp
o
n
d
to
th
e
r
ec
e
s
s
io
n
ar
y
p
er
io
d
d
u
e
to
th
e
w
o
r
ld
f
in
an
cial
cr
is
i
s
.
T
h
is
f
i
n
d
in
g
d
e
m
o
n
s
tr
ates
t
h
a
t
I
I
S
is
a
u
s
e
f
u
l
ap
p
r
o
ac
h
to
i
d
en
tify
o
u
t
lier
s
in
f
i
n
a
n
cial
d
ata
as
co
m
p
ar
ed
to
r
ec
en
t
s
tu
d
y
u
s
in
g
s
h
ar
iah
co
m
p
lian
t
s
to
ck
p
r
ices
in
Ma
la
y
s
ia
b
y
[
3
1
]
.
T
h
is
s
tu
d
y
d
if
f
er
s
f
r
o
m
[
3
1
]
r
esear
ch
th
at
w
a
s
p
r
o
n
e
to
m
et
h
o
d
o
lo
g
ical
in
ad
eq
u
ac
ie
s
d
u
e
to
in
ab
ili
t
y
o
f
B
o
x
-
W
h
is
k
er
p
lo
t
to
h
a
n
d
le
n
o
n
-
s
tat
io
n
ar
y
d
ata
an
d
to
m
o
d
el
th
e
o
u
tlier
s
d
etec
ted
.
I
n
ad
d
itio
n
,
th
e
box
-
w
h
i
s
k
er
p
lo
t
ap
p
r
o
ac
h
is
n
o
t
ab
le
to
p
er
f
o
r
m
s
ig
n
i
f
ica
n
ce
test
i
n
g
to
th
e
o
u
tl
ier
s
ca
p
tu
r
ed
co
m
p
ar
ed
to
I
I
S in
GE
T
S
m
o
d
ellin
g
.
5.
CO
NCLU
SI
O
N
T
h
e
p
r
esen
ce
o
f
o
u
tlier
s
i
n
e
co
n
o
m
ic
d
at
a
m
a
y
h
av
e
p
er
n
icio
u
s
e
f
f
ec
ts
o
n
m
o
d
el
esti
m
atio
n
an
d
f
o
r
ec
ast
ac
cu
r
ac
y
.
Hen
ce
,
t
h
i
s
s
t
u
d
y
ai
m
ed
to
s
t
u
d
y
t
h
e
e
f
f
icie
n
c
y
o
f
I
I
S
in
id
en
ti
f
y
i
n
g
o
u
tlier
s
u
s
i
n
g
g
et
s
p
ac
k
ag
e
th
r
o
u
g
h
Mo
n
te
C
ar
lo
s
i
m
u
latio
n
s
.
T
h
is
s
tu
d
y
h
as
s
h
o
w
n
t
h
at
I
I
S
is
v
er
y
u
s
e
f
u
l
i
n
d
ete
ctin
g
o
u
tlier
s
in
th
e
s
ta
te
-
s
p
ac
e
f
r
a
m
e
w
o
r
k
ev
en
th
o
u
g
h
th
e
le
v
el
co
m
p
o
n
en
t
v
ar
ies
o
v
er
ti
m
e.
W
e
ex
p
lo
r
ed
s
ev
er
al
v
ar
iab
les
th
a
t
m
a
y
in
f
l
u
e
n
ce
t
h
e
ef
f
icie
n
c
y
o
f
th
e
p
r
o
p
o
s
ed
m
et
h
o
d
u
s
i
n
g
Mo
n
te
C
ar
lo
s
i
m
u
latio
n
s
.
First,
t
h
e
p
er
f
o
r
m
a
n
ce
o
f
I
I
S
r
elie
s
h
ea
v
il
y
o
n
th
e
s
ize
o
f
o
u
tlier
s
.
T
h
en
,
th
e
lo
ca
tio
n
o
f
A
O
ad
d
ed
h
av
e
a
s
ig
n
i
f
ica
n
t
i
m
p
ac
t
o
n
t
h
e
p
o
ten
c
y
v
al
u
es
.
I
I
S
p
r
o
ce
d
u
r
e
ca
n
ea
s
il
y
id
e
n
ti
f
y
t
h
e
s
i
g
n
i
f
ica
n
t
in
d
icato
r
s
if
t
h
e
o
u
tlier
s
ar
e
ad
d
ed
in
th
e
s
a
m
e
s
a
m
p
le.
Ne
x
t,
th
e
n
u
m
b
er
o
f
b
lo
ck
s
,
m
also
p
lay
s
a
v
ital
r
o
le
to
d
r
iv
e
th
e
p
er
f
o
r
m
a
n
ce
o
f
I
I
S.
Ho
w
e
v
er
,
to
o
m
a
n
y
s
p
li
ts
in
th
e
s
a
m
p
le
d
id
lead
to
an
y
d
etec
tio
n
o
f
s
ig
n
if
ican
t
i
n
d
ic
ato
r
s
.
I
t
is
ess
en
tial
to
lo
ca
te
an
d
q
u
a
n
ti
f
y
th
e
ec
o
n
o
m
ic
s
h
o
c
k
t
h
at
c
h
ar
ac
ter
izes
an
d
m
o
d
el
an
y
s
tr
u
ct
u
r
al
b
r
ea
k
in
th
e
s
er
ie
s
ex
a
m
in
ed
.
A
s
id
e
f
r
o
m
t
h
at,
th
e
f
u
t
u
r
e
w
o
r
k
s
ca
n
also
u
tili
z
e
th
e
s
tep
in
d
icato
r
s
at
u
r
atio
n
(
SIS)
ap
p
r
o
ac
h
in
o
r
d
er
t
o
ca
p
tu
r
e
m
u
ltip
le
s
tr
u
c
tu
r
al
b
r
ea
k
s
.
ACK
NO
WL
E
D
G
E
M
E
NT
S
T
h
e
au
th
o
r
s
w
o
u
ld
li
k
e
to
e
x
ten
d
t
h
eir
s
in
ce
r
e
g
r
atit
u
d
e
to
th
e
Mi
n
is
tr
y
o
f
Hi
g
h
er
E
d
u
ca
tio
n
Ma
la
y
s
ia
(
MO
HE
)
f
o
r
th
e
f
i
n
a
n
cial
s
u
p
p
o
r
ts
r
ec
eiv
ed
f
o
r
th
i
s
w
o
r
k
u
n
d
er
FR
GS
g
r
a
n
t
(
2
0
3
/
P
MA
T
HS/6
7
1
1
6
0
4
)
.
RE
F
E
R
E
NC
E
S
[1
]
J.
L
.
Ca
stle a
n
d
D.
F
.
He
n
d
ry
,
“
M
o
d
e
ll
i
n
g
o
u
r C
h
a
n
g
in
g
W
o
rld
,
”
P
a
lg
ra
v
e
P
iv
o
t,
Ch
a
m
,
2
0
1
9
.
[2
]
Da
v
id
J.
Ha
n
d
,
“
Disc
u
ss
io
n
c
o
n
t
rib
u
ti
o
n
o
n
‘Da
ta
m
in
in
g
re
c
o
n
si
d
e
re
d
:
e
n
c
o
m
p
a
ss
in
g
a
n
d
t
h
e
g
e
n
e
ra
l‐t
o
‐sp
e
c
if
ic
a
p
p
ro
a
c
h
t
o
sp
e
c
if
ica
ti
o
n
se
a
rc
h
’
b
y
Ho
o
v
e
r
a
n
d
P
e
re
z
,
”
T
h
e
Eco
n
o
me
trics
J
o
u
rn
a
l
,
v
o
l
.
2
,
n
o
.
2
,
p
p
.
2
4
1
–
2
4
3
,
1
9
9
9
,
d
o
i:
1
0
.
1
1
1
1
/
1
3
6
8
-
4
2
3
x
.
0
0
0
3
0
.
[3
]
M
.
C.
L
o
v
e
ll
,
“
Da
ta M
in
i
n
g
,
”
T
h
e
Rev
iew o
f
Eco
n
o
mic
s a
n
d
S
t
a
ti
sti
c
s
,
v
o
l.
6
5
,
n
o
.
1
,
p
p
.
1
–
1
2
,
1
9
8
3
.
[4
]
D.
F
.
He
n
d
ry
a
n
d
H.
Kro
lzig
,
“
I
m
p
ro
v
in
g
o
n
‘Da
ta
m
in
in
g
re
c
o
n
sid
e
re
d
’
b
y
K.D.
Ho
o
v
e
r
a
n
d
S
.
J.
P
e
re
z
,
”
T
h
e
Eco
n
o
me
trics
J
o
u
rn
a
l
,
v
o
l.
2
,
n
o
.
2
,
p
p
.
2
0
2
–
2
1
9
,
1
9
9
9
,
d
o
i:
1
0
.
1
1
1
1
/1
3
6
8
-
4
2
3
x
.
0
0
0
2
7
.
[5
]
J.
Ca
stle
a
n
d
N.
S
h
e
p
h
a
r
d
,
“
T
h
e
M
e
th
o
d
o
lo
g
y
a
n
d
Pra
c
t
ice
o
f
Ec
o
n
o
me
trics
:
A
Fes
tsc
h
rift
i
n
H
o
n
o
u
r
o
f
Da
v
id
F.
He
n
d
ry
,
”
OU
P
Ox
f
o
rd
,
p
p
.
1
–
4
6
4
,
2
0
0
9
,
d
o
i:
1
0
.
1
0
9
3
/ac
p
ro
f
:o
so
/9
7
8
0
1
9
9
2
3
7
1
9
7
.
0
0
1
.
0
0
0
1
.
[6
]
C.
S
a
n
t
o
s,
D.
F
.
He
n
d
ry
,
a
n
d
S
.
Jo
h
a
n
se
n
,
“
A
u
to
m
a
ti
c
se
lec
ti
o
n
o
f
in
d
ica
to
rs
i
n
a
f
u
ll
y
sa
tu
ra
ted
re
g
re
ss
io
n
,
”
Co
mp
u
t
a
ti
o
n
a
l
S
ta
t
isti
c
s
,
v
o
l.
2
3
,
n
o
.
2
,
p
p
.
3
1
7
–
3
3
5
,
2
0
0
8
,
d
o
i:
1
0
.
1
0
0
7
/s0
0
1
8
0
-
0
0
7
-
0
0
5
4
-
z.
[7
]
J.
L
.
Ca
stle,
J.
A
.
Do
o
rn
ik
,
a
n
d
D.
F
.
He
n
d
ry
,
“
M
o
d
e
ll
in
g
n
o
n
-
sta
ti
o
n
a
ry
‘Big
Da
ta,’”
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
Fo
re
c
a
stin
g
,
2
0
2
0
,
d
o
i:
1
0
.
1
0
1
6
/
j
.
ij
f
o
re
c
a
st.2
0
2
0
.
0
8
.
0
0
2
.
[8
]
A
n
d
re
w
Ha
rv
e
y
,
S
ie
m
Ja
n
Ko
o
p
m
a
n
,
a
n
d
Je
re
m
y
P
e
n
z
e
r
,
“
M
e
ss
y
T
i
m
e
S
e
ries
:
a
Un
if
ied
A
p
p
ro
a
c
h
,
”
A
d
v
a
n
c
e
s
in
Eco
n
o
me
trics
,
v
o
l.
1
3
,
p
p
.
1
0
3
-
1
4
3
,
1
9
9
8
.
[9
]
D.
F
.
He
n
d
ry
,
“
A
n
e
c
o
n
o
m
e
tri
c
a
n
a
ly
sis
o
f
US
f
o
o
d
e
x
p
e
n
d
it
u
re
,
1
9
3
1
-
1
9
8
9
,
”
i
n
J.
R
M
a
g
n
u
s
a
n
d
M
.
S
.
M
o
rg
a
n
,
M
e
th
o
d
o
l
o
g
y
a
n
d
tac
it
k
n
o
w
led
g
e
:
t
w
o
e
x
p
e
ri
m
e
n
ts
in
e
c
o
n
o
m
e
tri
c
s,
Ch
ich
e
ste
r:
Jo
h
n
W
il
e
y
a
n
d
S
o
n
s,
1
9
9
9
,
p
p
.
3
4
1
-
3
6
1
.
[
1
0
]
D
.
F
.
H
e
n
d
r
y
a
n
d
J
.
A
.
D
o
o
r
n
i
k
,
“
E
m
p
i
r
i
c
a
l
M
o
d
e
l
D
i
s
c
o
v
e
r
y
a
n
d
T
h
e
o
r
y
e
v
a
l
u
a
t
i
o
n
,”
L
o
n
d
o
n
:
T
h
e
M
I
T
P
r
e
s
s
,
2
0
1
4
.
[1
1
]
S
.
Jo
h
a
n
se
n
a
n
d
B.
Nie
lse
n
,
“
A
n
A
n
a
l
y
si
s
o
f
th
e
I
n
d
ica
to
r
S
a
t
u
ra
ti
o
n
Esti
m
a
to
r
a
s
a
Ro
b
u
st
Re
g
re
ss
io
n
Esti
m
a
to
r,
”
T
h
e
M
e
th
o
d
o
l
o
g
y
a
n
d
Pra
c
ti
c
e
o
f
Eco
n
o
me
trics
:
A
Fes
tsc
h
rift
in
Ho
n
o
u
r
o
f
Da
v
id
F.
He
n
d
ry
,
2
0
0
9
,
d
o
i:
1
0
.
1
0
9
3
/ac
p
ro
f
:o
so
/9
7
8
0
1
9
9
2
3
7
1
9
7
.
0
0
3
.
0
0
0
1
.
[1
2
]
N.
R.
Eri
c
ss
o
n
,
“
Ho
w
b
ias
e
d
a
re
U.S
.
g
o
v
e
rn
m
e
n
t
f
o
re
c
a
sts
o
f
th
e
f
e
d
e
ra
l
d
e
b
t?,”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Fo
re
c
a
stin
g
,
v
o
l.
3
3
,
n
o
.
2
,
p
p
.
5
4
3
–
5
5
9
,
2
0
1
7
,
d
o
i:
1
0
.
1
0
1
6
/
j.
ij
f
o
re
c
a
st.2
0
1
6
.
0
9
.
0
0
1
.
[1
3
]
R.
M
a
risc
a
l
a
n
d
A
.
P
o
w
e
ll
,
“
Co
m
m
o
d
it
y
P
rice
Bo
o
m
s
a
n
d
Bre
a
k
s:
De
tec
ti
o
n
,
M
a
g
n
it
u
d
e
a
n
d
I
m
p
li
c
a
ti
o
n
s
f
o
r
De
v
e
lo
p
in
g
Co
u
n
tri
e
s,”
S
sr
n
,
n
o
.
Ja
n
u
a
ry
,
2
0
1
4
,
d
o
i:
1
0
.
2
1
3
9
/ssrn
.
2
3
8
4
4
2
2
.
[1
4
]
M
.
M
a
rc
z
a
k
a
n
d
T
.
P
ro
iett
i,
“
Ou
t
li
e
r
d
e
tec
t
io
n
i
n
stru
c
t
u
ra
l
ti
m
e
se
ries
m
o
d
e
ls:
T
h
e
in
d
ica
to
r
sa
tu
ra
t
io
n
a
p
p
ro
a
c
h
,
”
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
F
o
re
c
a
st
in
g
,
v
o
l.
3
2
,
n
o
.
1
,
p
p
.
1
8
0
–
2
0
2
,
2
0
1
6
,
d
o
i:
1
0
.
1
0
1
6
/j
.
ij
f
o
re
c
a
st.2
0
1
5
.
0
4
.
0
0
5
.
[1
5
]
J.
R.
S
t
il
lw
a
g
o
n
,
“
No
n
-
l
in
e
a
r
e
x
c
h
a
n
g
e
ra
te
re
latio
n
sh
i
p
s:
A
n
a
u
t
o
m
a
te
d
m
o
d
e
l
se
lec
ti
o
n
a
p
p
r
o
a
c
h
w
it
h
i
n
d
ica
to
r
sa
tu
ra
ti
o
n
,
”
N
o
rth
Ame
ric
a
n
J
o
u
rn
a
l
o
f
Eco
n
o
mic
s
a
n
d
Fi
n
a
n
c
e
,
v
o
l.
3
7
,
p
p
.
8
4
–
1
0
9
,
2
0
1
6
,
d
o
i:
1
0
.
1
0
1
6
/j
.
n
a
jef
.
2
0
1
6
.
0
3
.
0
0
9
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
22
,
No
.
3
,
J
u
n
e
2
0
2
1
:
1
6
8
8
-
1
6
9
6
1696
[1
6
]
J.
L
.
Ca
stle,
J.
A
.
Do
o
rn
ik
,
a
n
d
D.
F
.
He
n
d
ry
,
“
Ev
a
lu
a
ti
n
g
A
u
to
m
a
ti
c
M
o
d
e
l
S
e
lec
ti
o
n
,
”
J
o
u
r
n
a
l
o
f
T
ime
S
e
rie
s
Eco
n
o
me
trics
,
v
o
l.
3
,
n
o
.
1
,
2
0
1
1
,
d
o
i
:
1
0
.
2
2
0
2
/
1
9
4
1
-
1
9
2
8
.
1
0
9
7
.
[1
7
]
F
.
P
re
ti
s,
L
.
S
c
h
n
e
i
d
e
r,
J.
E
.
S
m
e
rd
o
n
,
a
n
d
D
.
F
.
He
n
d
ry
,
“
De
tec
ti
n
g
V
o
lca
n
ic
Er
u
p
t
io
n
s
i
n
T
e
m
p
e
ra
tu
re
Re
c
o
n
stru
c
ti
o
n
s
By
De
sig
n
e
d
Bre
a
k
-
In
d
ica
to
r
S
a
tu
ra
ti
o
n
,
”
J
o
u
rn
a
l
o
f
E
c
o
n
o
mic
S
u
rv
e
y
s
,
v
o
l.
3
0
,
n
o
.
3
,
p
p
.
4
0
3
–
4
2
9
,
2
0
1
6
,
d
o
i:
1
0
.
1
1
1
1
/j
o
e
s.1
2
1
4
8
.
[1
8
]
J.
H.
S
to
c
k
a
n
d
M
.
W
.
W
a
tso
n
,
“
F
o
re
c
a
stin
g
Us
in
g
P
ri
n
c
ip
a
l
C
o
m
p
o
n
e
n
ts
F
ro
m
a
L
a
r
g
e
Nu
m
b
e
r
o
f
P
re
d
ict
o
rs,”
J
o
u
rn
a
l
o
f
t
h
e
Ame
ric
a
n
S
ta
ti
stica
l
Asso
c
ia
t
io
n
,
v
o
l.
9
7
,
n
o
.
4
6
0
,
p
p
.
1
167
–
1
1
7
9
,
2
0
0
2
,
d
o
i:
1
0
.
1
1
9
8
/0
1
6
2
1
4
5
0
2
3
8
8
6
1
8
9
6
0
.
[1
9
]
S
.
J.
Co
m
m
a
n
d
e
u
r,
Ja
c
q
u
e
s
J
.
F
.
,
a
n
d
Ko
o
p
m
a
n
,
An
In
tro
d
u
c
ti
o
n
to
S
ta
te
S
p
a
c
e
T
ime
S
e
rie
s
A
n
a
ly
sis
,
F
irst.
Ne
w
Yo
rk
:
Ox
f
o
rd
Un
iv
e
rsit
y
P
re
ss
,
2
0
0
7
.
[2
0
]
J.
Du
rb
i
n
a
n
d
S
.
J.
Ko
o
p
m
a
n
,
T
i
me
S
e
rie
s
An
a
lys
is
b
y
S
t
a
te
S
p
a
c
e
me
th
o
d
s
,
S
e
c
o
n
d
.
Ox
f
o
rd
:
Ox
f
o
rd
Un
iv
e
rsity
P
re
ss
,
2
0
1
2
.
[2
1
]
A
.
C.
A
tk
in
so
n
,
S
.
J.
K
o
o
p
m
a
n
,
a
n
d
N.
S
h
e
p
h
a
rd
,
“
De
tec
ti
n
g
sh
o
c
k
s: Ou
tl
iers
a
n
d
b
re
a
k
s in
ti
m
e
se
ries
,
”
J
o
u
rn
a
l
o
f
Eco
n
o
me
trics
,
v
o
l.
8
0
,
n
o
.
2
,
p
p
.
3
8
7
-
4
2
2
,
1
9
9
7
,
d
o
i:
1
0
.
1
0
1
6
/S
0
3
0
4
-
4
0
7
6
(
9
7
)
0
0
0
5
0
-
X.
[2
2
]
M
.
Be
rg
a
m
e
ll
i
a
n
d
G
.
Urg
a
,
“
De
tec
ti
n
g
M
u
lt
i
p
le
S
tr
u
c
tu
ra
l
Bre
a
k
s :
Du
m
m
y
S
a
tu
ra
ti
o
n
v
s
S
e
q
u
e
n
t
ial
Bo
o
tstrap
p
in
g
.
W
it
h
a
n
A
p
p
li
c
a
ti
o
n
t
o
t
h
e
F
is
h
e
r
Ef
fe
c
t
f
o
r
US,
”
pp.
1
-
4
5
,
2
A
p
ril
2
0
1
4
.
[2
3
]
J.
Re
a
d
e
,
a
n
d
G
.
S
u
c
a
rra
t,
“
G
e
n
e
ra
l
-
to
-
S
p
e
c
if
ic
(
G
ET
S
)
M
o
d
e
ll
i
n
g
a
n
d
In
d
ica
to
r
S
a
tu
ra
ti
o
n
w
it
h
th
e
R
P
a
c
k
a
g
e
g
e
ts,”
Eco
n
o
m
ics
S
e
ries
W
o
rk
in
g
P
a
p
e
rs 7
9
4
,
Un
iv
e
rsity
o
f
O
x
f
o
rd
,
De
p
a
rtm
e
n
t
o
f
Eco
n
o
m
ics
,
p
p
.
1
–
3
0
,
2
0
1
6
.
[2
4
]
J.
L
.
Ca
stle,
J.
A
.
Do
o
rn
ik
,
a
n
d
D.
F
.
He
n
d
ry
,
“
Ro
b
u
st
Disc
o
v
e
r
y
o
f
Re
g
r
e
ss
io
n
M
o
d
e
ls,”
Eco
n
o
me
trics
a
nd
S
ta
ti
st
ics
,
A
v
a
il
a
b
le o
n
li
n
e
1
Ju
n
e
2
0
2
1
,
d
o
i:
1
0
.
1
0
1
6
/j
.
e
c
o
sta
.
2
0
2
1
.
0
5
.
0
0
4
.
[2
5
]
C.
S
a
n
t
o
s,
D.
F
.
He
n
d
ry
,
a
n
d
S
.
Jo
h
a
n
se
n
,
“
A
u
to
m
a
ti
c
se
lec
ti
o
n
o
f
in
d
ica
to
rs
i
n
a
f
u
ll
y
sa
tu
ra
ted
re
g
re
ss
io
n
,
”
Co
mp
u
t
a
ti
o
n
a
l
S
ta
t
isti
c
s
,
v
o
l.
2
3
,
n
o
.
2
,
p
p
.
3
1
7
–
3
3
5
,
2
0
0
8
,
d
o
i:
1
0
.
1
0
0
7
/s0
0
1
8
0
-
0
0
7
-
0
0
5
4
-
z.
[2
6
]
S
.
Jo
h
a
n
se
n
a
n
d
B.
Nie
lse
n
,
“
A
n
A
n
a
l
y
si
s
o
f
th
e
I
n
d
ica
to
r
S
a
t
u
ra
ti
o
n
Esti
m
a
to
r
a
s
a
Ro
b
u
st
Re
g
re
ss
io
n
Esti
m
a
to
r,
”
T
h
e
M
e
th
o
d
o
l
o
g
y
a
n
d
Pra
c
ti
c
e
o
f
Eco
n
o
me
trics
:
A
Fes
tsc
h
rift
in
Ho
n
o
u
r
o
f
Da
v
id
F.
He
n
d
ry
,
2
0
0
9
,
d
o
i:
1
0
.
1
0
9
3
/ac
p
r
o
f
:o
so
/9
7
8
0
1
9
9
2
3
7
1
9
7
.
0
0
3
.
0
0
0
1
.
[2
7
]
D.
F
.
He
n
d
ry
a
n
d
H.
M
.
Kro
lzi
g
,
“
T
h
e
p
ro
p
e
rti
e
s
o
f
a
u
to
m
a
ti
c
g
e
ts
m
o
d
e
ll
in
g
,
”
Eco
n
o
mic
J
o
u
rn
a
l
,
v
o
l
.
1
1
5
,
n
o
.
5
0
2
,
p
p
.
C
32
-
C
6
1
,
2
0
0
5
,
d
o
i:
1
0
.
1
1
1
1
/
j.
0
0
1
3
-
0
1
3
3
.
2
0
0
5
.
0
0
9
7
9
.
x
.
[2
8
]
C.
Ch
a
n
g
,
I
h
,
T
iao
,
G
e
o
rg
e
C.
a
n
d
C
h
e
n
,
“
Esti
m
a
ti
o
n
o
f
ti
m
e
se
ries
p
a
ra
m
e
ters
in
t
h
e
p
re
se
n
c
e
o
f
o
u
tl
iers
,
”
T
e
c
h
n
o
me
trics
,
v
o
l.
3
0
,
n
o
.
2
,
p
p
.
1
9
3
–
2
0
4
,
1
9
8
8
.
[2
9
]
C.
Ch
e
n
a
n
d
L
.
-
M
.
L
iu
,
“
Jo
i
n
t
Es
ti
m
a
ti
o
n
o
f
M
o
d
e
l
P
a
ra
m
e
ters
a
n
d
Ou
t
li
e
r
Ef
f
e
c
ts
in
T
i
m
e
S
e
ries
,
”
J
o
u
r
n
a
l
o
f
th
e
Ame
ric
a
n
S
t
a
ti
stica
l
Asso
c
i
a
ti
o
n
,
v
o
l.
8
8
,
n
o
.
4
2
1
,
p
p
.
2
8
4
-
2
9
7
,
1
9
9
3
,
d
o
i:
1
0
.
2
3
0
7
/2
2
9
0
7
2
4
.
[3
0
]
F
.
P
re
ti
s,
J.
J.
Re
a
d
e
,
a
n
d
G
.
S
u
c
a
rra
t,
“
A
u
to
m
a
ted
g
e
n
e
r
a
l
-
to
-
sp
e
c
if
ic
(
G
E
T
S
)
re
g
r
e
ss
io
n
m
o
d
e
li
n
g
a
n
d
in
d
ica
to
r
sa
tu
ra
ti
o
n
f
o
r
o
u
tl
iers
a
n
d
st
ru
c
tu
ra
l
b
re
a
k
s,”
J
o
u
rn
a
l
o
f
S
ta
ti
st
ica
l
S
o
ft
wa
re
,
v
o
l.
8
6
,
n
o
.
3
,
2
0
1
8
,
d
o
i:
1
0
.
1
8
6
3
7
/
jss.v
0
8
6
.
i0
3
.
[3
1
]
N.
A
.
Ba
k
a
r,
“
M
o
n
te
Ca
rlo
S
im
u
latio
n
f
o
r
Da
ta
V
o
latil
it
y
A
n
a
l
y
sis
o
f
S
to
c
k
P
rice
s
in
Isla
m
ic
F
in
a
n
c
e
f
o
r
M
a
la
y
sia
Co
m
p
o
site
In
d
e
x
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Ad
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
Res
e
a
rc
h
a
n
d
S
c
ien
c
e
,
v
o
l.
6
,
n
o
.
3
,
p
p
.
6
-
1
2
,
2
0
1
9
,
d
o
i:
1
0
.
2
2
1
6
1
/i
jae
rs.6
.
3
.
2
.
Evaluation Warning : The document was created with Spire.PDF for Python.