I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
pu
t
er
E
ng
ineering
(
I
J
E
CE
)
Vo
l.
1
6
,
No
.
3
,
J
u
n
e
20
2
6
,
p
p
.
1531
~
1
5
4
2
I
SS
N:
2088
-
8
7
0
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijece.
v
1
6
i
3
.
pp
1
5
3
1
-
1
5
4
2
1531
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
A risk
-
co
nstra
ine
d SARS
A
–
FIS hy
brid decisio
n
arc
hitectu
re
with
a
da
ptive
exp
lo
ra
tion co
ntrol
J
o
ni F
a
t
1
,2
,
P
a
rwa
di M
o
eng
in
1
,
P
ud
j
i A
s
t
uti
1
,
Sa
lly
Ca
hy
a
t
i
3
1
D
e
p
a
r
t
me
n
t
o
f
I
n
d
u
s
t
r
i
a
l
En
g
i
n
e
e
r
i
n
g
,
U
n
i
v
e
r
si
t
a
s
Tr
i
sa
k
t
i
,
Ja
k
a
r
t
a
,
I
n
d
o
n
e
si
a
2
El
e
c
t
r
i
c
a
l
E
n
g
i
n
e
e
r
i
n
g
P
r
o
g
r
a
m,
U
n
i
v
e
r
si
t
a
s
Ta
r
u
ma
n
a
g
a
r
a
,
J
a
k
a
r
t
a
,
I
n
d
o
n
e
si
a
3
D
e
p
a
r
t
me
n
t
o
f
M
e
c
h
a
n
i
c
a
l
E
n
g
i
n
e
e
r
i
n
g
,
U
n
i
v
e
r
si
t
a
s
Tr
i
s
a
k
t
i
,
Ja
k
a
r
t
a
,
I
n
d
o
n
e
s
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Ma
r
4
,
2
0
2
6
R
ev
is
ed
Ap
r
2
3
,
2
0
2
6
Acc
ep
ted
Ap
r
2
6
,
2
0
2
6
Alg
o
rit
h
m
ic
trad
i
n
g
sy
ste
m
s
o
p
e
ra
te
in
h
i
g
h
ly
d
y
n
a
m
ic
a
n
d
u
n
c
e
rtain
e
n
v
iro
n
m
e
n
ts
wh
e
re
lea
rn
i
n
g
-
b
a
se
d
d
e
c
isio
n
a
g
e
n
ts
m
u
st
b
a
lan
c
e
a
d
a
p
tab
il
it
y
wi
th
strict
ris
k
c
o
n
t
ro
l.
Re
i
n
fo
rc
e
m
e
n
t
lea
rn
in
g
(RL
)
m
e
th
o
d
s
p
ro
v
id
e
a
d
a
p
ti
v
e
p
o
li
c
y
o
p
t
imiz
a
ti
o
n
b
u
t
o
fte
n
su
ffe
r
fr
o
m
u
n
sta
b
le
e
x
p
lo
ra
ti
o
n
a
n
d
l
imited
i
n
terp
re
tab
il
it
y
in
f
in
a
n
c
ial
m
a
rk
e
ts.
T
h
is
stu
d
y
p
ro
p
o
se
s
a
r
isk
-
c
o
n
stra
in
e
d
S
AR
S
A
–
F
IS
h
y
b
r
id
d
e
c
isio
n
a
rc
h
it
e
c
tu
re
wit
h
a
d
a
p
ti
v
e
e
x
p
lo
ra
t
io
n
c
o
n
tro
l
f
o
r
a
lg
o
rit
h
m
ic
trad
in
g
.
T
h
e
f
ra
m
e
wo
rk
in
teg
ra
tes
a
c
o
m
p
a
c
t
S
AR
SA
-
b
a
se
d
re
in
fo
rc
e
m
e
n
t
lea
rn
in
g
e
n
v
iro
n
m
e
n
t
with
a
S
u
g
e
n
o
-
ty
p
e
fu
z
z
y
in
fe
re
n
c
e
sy
ste
m
(F
IS
)
th
a
t
c
o
n
v
e
rts
re
in
fo
rc
e
m
e
n
t
sig
n
a
ls
i
n
t
o
in
terp
re
tab
le
trad
in
g
d
e
c
isio
n
s.
Ex
p
lo
ra
ti
o
n
f
o
ll
o
ws
a
d
e
c
a
y
in
g
ε
-
g
re
e
d
y
p
o
li
c
y
with
a
d
ra
wd
o
wn
-
tri
g
g
e
re
d
re
se
t
m
e
c
h
a
n
ism
t
o
m
a
in
tain
b
o
u
n
d
e
d
ris
k
e
x
p
o
s
u
re
d
u
ri
n
g
lea
rn
in
g
.
T
h
e
sy
ste
m
wa
s
imp
lem
e
n
ted
a
s
a
M
e
taTra
d
e
r
5
Ex
p
e
rt
Ad
v
iso
r
a
n
d
e
v
a
lu
a
te
d
o
n
th
e
G
BP
USD
c
u
r
re
n
c
y
p
a
ir
u
sin
g
h
isto
rica
l
m
a
rk
e
t
d
a
ta.
E
x
p
e
rime
n
tal
re
su
lt
s
sh
o
w
t
h
a
t
t
h
e
h
y
b
ri
d
fra
m
e
wo
rk
imp
ro
v
e
s
tra
d
in
g
p
e
rfo
rm
a
n
c
e
c
o
m
p
a
re
d
with
a
ru
le
-
b
a
se
d
b
a
se
li
n
e
.
Du
ri
n
g
a
si
x
-
m
o
n
t
h
o
u
t
-
of
-
sa
m
p
le
e
v
a
lu
a
ti
o
n
,
t
h
e
sy
ste
m
a
c
h
iev
e
d
a
n
e
t
p
ro
f
it
o
f
9
0
USD
a
n
d
a
p
r
o
fit
fa
c
to
r
o
f
1
.
3
5
,
c
o
m
p
a
re
d
wit
h
1
0
USD
a
n
d
1
.
0
2
fo
r
t
h
e
b
a
se
li
n
e
.
Ex
t
e
n
d
e
d
o
n
e
-
y
e
a
r
tes
ti
n
g
c
o
n
firme
d
sta
b
le
p
ro
fit
a
b
il
it
y
a
n
d
c
o
n
tr
o
ll
e
d
d
ra
wd
o
wn
b
e
h
a
v
i
o
r.
Th
e
re
su
lt
s d
e
m
o
n
stra
te
th
a
t
in
teg
ra
ti
n
g
re
in
f
o
rc
e
m
e
n
t
lea
rn
i
n
g
,
f
u
z
z
y
d
e
c
isio
n
m
a
p
p
in
g
,
a
n
d
e
x
p
li
c
it
ris
k
c
o
n
stra
in
ts
p
ro
v
id
e
s
a
p
ra
c
ti
c
a
l
a
p
p
ro
a
c
h
f
o
r
d
e
v
e
lo
p
in
g
a
d
a
p
ti
v
e
trad
in
g
a
g
e
n
ts.
K
ey
w
o
r
d
s
:
Alg
o
r
ith
m
ic
tr
ad
in
g
Fu
zz
y
in
f
er
e
n
ce
s
y
s
tem
R
ein
f
o
r
ce
m
en
t le
ar
n
i
n
g
R
is
k
-
co
n
s
tr
ain
ed
lear
n
in
g
SAR
S
A
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
:
Par
wad
i M
o
en
g
in
Dep
ar
tm
en
t o
f
I
n
d
u
s
tr
ial
E
n
g
i
n
ee
r
in
g
,
U
n
iv
er
s
itas
T
r
is
ak
ti
J
ak
ar
ta,
I
n
d
o
n
esia
E
m
ail:
p
ar
wad
i@
tr
is
ak
ti.a
c.
id
1.
I
NT
RO
D
UCT
I
O
N
Alg
o
r
ith
m
ic
tr
ad
in
g
s
y
s
tem
s
o
p
er
ate
in
e
n
v
ir
o
n
m
en
ts
th
at
ar
e
u
n
ce
r
tain
,
d
y
n
am
ic,
a
n
d
o
f
ten
n
o
n
-
s
tatio
n
ar
y
.
I
n
f
in
an
cial
m
ar
k
ets,
p
r
ice
m
o
v
em
e
n
ts
ar
e
a
f
f
ec
ted
b
y
v
o
latilit
y
clu
s
ter
in
g
,
s
u
d
d
en
r
eg
im
e
ch
an
g
es,
a
n
d
c
o
m
p
le
x
in
ter
ac
tio
n
s
b
etwe
en
p
ar
ticip
an
ts
.
A
n
au
to
m
ated
d
ec
is
io
n
s
y
s
tem
m
u
s
t
th
er
e
f
o
r
e
b
e
ad
ap
tiv
e,
b
u
t
at
th
e
s
am
e
tim
e
it
m
u
s
t
m
ain
tain
s
tr
ict
r
i
s
k
co
n
tr
o
l.
Desig
n
in
g
a
lear
n
in
g
ar
c
h
itectu
r
e
th
a
t
b
alan
ce
s
ad
ap
tab
ilit
y
,
in
ter
p
r
e
tab
ilit
y
,
an
d
o
p
er
ati
o
n
al
s
tab
il
ity
r
em
ain
s
an
im
p
o
r
tan
t
ch
allen
g
e
in
in
tellig
en
t
f
in
an
cial
d
ec
is
io
n
s
y
s
tem
s
.
R
ein
f
o
r
ce
m
en
t
lear
n
i
n
g
(
R
L
)
h
as
b
ee
n
wid
ely
u
s
ed
f
o
r
s
eq
u
en
tial
d
ec
is
io
n
-
m
ak
in
g
u
n
d
e
r
u
n
c
er
tain
ty
.
Me
th
o
d
s
s
u
ch
as
Q
-
lear
n
in
g
a
n
d
SAR
S
A
allo
w
an
ag
en
t
to
u
p
d
ate
its
ac
tio
n
-
v
alu
e
f
u
n
ctio
n
th
r
o
u
g
h
d
i
r
ec
t
in
te
r
ac
tio
n
with
th
e
e
n
v
ir
o
n
m
e
n
t.
T
h
ese
a
p
p
r
o
ac
h
es
p
r
o
v
i
d
e
o
n
lin
e
lear
n
in
g
ca
p
ab
ilit
y
an
d
a
d
ap
tab
ilit
y
t
o
ch
an
g
in
g
c
o
n
d
itio
n
s
.
Ho
wev
er
,
R
L
m
o
d
els
o
f
te
n
b
e
h
av
e
as
b
lack
-
b
o
x
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
1
6
,
No
.
3
,
J
u
n
e
20
2
6
:
1
5
3
1
-
1
5
4
2
1532
m
ec
h
an
is
m
s
an
d
m
ay
lack
i
n
ter
p
r
etab
ilit
y
.
I
n
a
d
d
itio
n
,
u
n
co
n
s
tr
ain
e
d
ex
p
lo
r
atio
n
p
o
licies
ca
n
g
en
er
ate
u
n
s
tab
le
d
ec
is
io
n
s
,
esp
ec
ially
wh
en
ap
p
lied
in
r
ea
l
-
tim
e
f
i
n
a
n
cial
en
v
ir
o
n
m
en
ts
wh
er
e
r
is
k
ex
p
o
s
u
r
e
m
u
s
t
b
e
co
n
tr
o
lled
.
Fu
zz
y
in
f
er
en
ce
s
y
s
tem
s
(
FIS)
,
p
ar
ticu
lar
ly
Su
g
e
n
o
-
ty
p
e
m
o
d
els,
o
f
f
er
an
in
ter
p
r
etab
le
r
u
le
-
b
ased
s
tr
u
ctu
r
e
f
o
r
r
ea
s
o
n
in
g
u
n
d
e
r
u
n
ce
r
tain
ty
.
T
h
r
o
u
g
h
li
n
g
u
is
tic
v
ar
iab
les
an
d
s
tr
u
ctu
r
e
d
r
u
le
b
ases
,
f
u
zz
y
s
y
s
tem
s
ca
n
r
ep
r
esen
t
ex
p
er
t
k
n
o
wled
g
e
i
n
an
ex
p
licit
m
an
n
er
.
Nev
e
r
th
eless
,
class
ical
f
u
zz
y
s
y
s
tem
s
ar
e
u
s
u
ally
s
tatic.
W
ith
o
u
t
an
e
m
b
ed
d
e
d
lear
n
in
g
m
ec
h
an
is
m
,
th
ey
ca
n
n
o
t
au
to
m
atica
ll
y
ad
ap
t
t
o
ev
o
lv
in
g
m
ar
k
et
s
tates
o
r
ch
an
g
in
g
v
o
l
atility
r
eg
im
es.
Fo
r
th
ese
r
ea
s
o
n
s
,
in
teg
r
atin
g
R
L
with
f
u
zz
y
in
f
er
en
ce
b
ec
o
m
es
a
p
r
o
m
is
in
g
d
ir
ec
tio
n
.
A
h
y
b
r
id
s
tr
u
ctu
r
e
ca
n
co
m
b
in
e
th
e
ad
ap
tab
ilit
y
o
f
R
L
with
th
e
in
ter
p
r
etab
ilit
y
o
f
f
u
zz
y
r
u
les.
Ho
wev
er
,
m
an
y
ex
is
tin
g
h
y
b
r
id
s
ap
p
r
o
ac
h
es
m
ain
ly
f
o
cu
s
o
n
p
r
ed
ictio
n
p
er
f
o
r
m
an
ce
,
wh
ile
lim
ited
atten
tio
n
is
g
iv
en
to
r
is
k
-
awa
r
e
ex
p
lo
r
atio
n
co
n
tr
o
l
an
d
b
o
u
n
d
ed
lear
n
in
g
d
y
n
a
m
ics.
I
n
p
r
ac
tical
f
in
an
cial
s
y
s
tem
s
,
d
ec
is
io
n
p
o
licies
m
u
s
t
o
p
er
ate
in
s
id
e
p
r
ed
ef
in
e
d
r
is
k
lim
its
in
o
r
d
er
to
p
r
ev
en
t
d
estab
ilizin
g
b
eh
av
io
r
d
u
r
in
g
h
ig
h
-
v
o
latilit
y
p
er
io
d
s
.
T
h
is
p
ap
er
p
r
o
p
o
s
es
a
r
is
k
-
co
n
s
tr
ain
ed
SAR
SA
–
FIS
h
y
b
r
id
d
ec
is
io
n
ar
ch
itectu
r
e
with
ad
ap
tiv
e
ex
p
lo
r
atio
n
co
n
tr
o
l.
T
h
e
f
r
a
m
ewo
r
k
is
b
u
ilt
o
n
a
c
o
m
p
a
ct
SAR
SA
-
b
ased
Ma
r
k
o
v
d
e
cisi
o
n
p
r
o
ce
s
s
an
d
a
27
-
r
u
le
Su
g
en
o
f
u
zz
y
i
n
f
er
en
ce
lay
er
th
at
tr
an
s
f
o
r
m
s
r
ein
f
o
r
ce
m
en
t
s
ig
n
als
in
to
s
tr
u
ctu
r
e
d
tr
ad
in
g
d
ec
is
io
n
s
.
T
h
e
ex
p
lo
r
atio
n
m
ec
h
an
is
m
f
o
llo
ws
a
d
ec
a
y
in
g
ε
-
g
r
ee
d
y
p
o
licy
with
an
ad
d
itio
n
al
d
r
awd
o
wn
-
tr
ig
g
e
r
ed
r
eset,
s
o
th
at
lear
n
in
g
r
em
ain
s
ad
a
p
tiv
e
b
u
t
d
o
es
n
o
t
e
x
ce
ed
p
r
ed
ef
in
ed
r
is
k
b
o
u
n
d
ar
ies.
Fu
r
th
er
m
o
r
e,
p
o
s
itio
n
-
lev
e
l
p
r
o
f
it
a
n
d
lo
s
s
th
r
esh
o
ld
s
t
o
g
eth
er
with
a
m
ax
im
u
m
d
r
aw
d
o
wn
s
en
tin
el
ar
e
i
n
co
r
p
o
r
ate
d
to
r
eg
u
lar
ize
th
e
o
v
er
all
s
y
s
tem
b
eh
av
io
r
.
T
h
e
p
r
o
p
o
s
ed
ar
ch
itectu
r
e
is
i
m
p
lem
en
ted
as
a
m
o
d
u
lar
e
x
ec
u
tio
n
ag
e
n
t
an
d
ev
alu
ated
u
s
in
g
h
is
to
r
ical
d
a
ta
f
r
o
m
t
h
e
GB
PUSD
cu
r
r
en
cy
p
air
.
T
h
e
e
x
p
er
im
e
n
tal
ev
alu
atio
n
in
clu
d
es
co
m
p
ar
is
o
n
with
a
r
u
le
-
b
ased
b
aselin
e,
ab
latio
n
an
aly
s
is
,
an
d
m
u
lti
-
h
o
r
izo
n
b
ac
k
test
in
g
in
o
r
d
er
to
ass
ess
p
r
o
f
itab
ilit
y
,
r
is
k
-
a
d
ju
s
ted
ef
f
i
cien
cy
,
an
d
r
o
b
u
s
tn
ess
ac
r
o
s
s
d
if
f
er
en
t m
a
r
k
et
co
n
d
itio
n
s
.
Desp
ite
th
e
g
r
o
win
g
ad
o
p
tio
n
o
f
RL
in
f
in
a
n
cial
d
ec
is
io
n
s
y
s
tem
s
,
s
ev
er
al
lim
itatio
n
s
r
em
ain
.
E
x
is
tin
g
R
L
ap
p
r
o
ac
h
es
f
r
e
q
u
en
tly
r
ely
o
n
u
n
co
n
s
tr
ain
ed
e
x
p
lo
r
atio
n
m
ec
h
an
is
m
s
th
at
m
a
y
g
en
e
r
ate
u
n
s
tab
le
p
o
licies
wh
en
d
ep
lo
y
ed
in
v
o
latile
f
in
an
cial
en
v
ir
o
n
m
e
n
ts
.
Alth
o
u
g
h
FIS
p
r
o
v
id
e
in
ter
p
r
etab
ilit
y
an
d
s
tr
u
ctu
r
ed
r
ea
s
o
n
i
n
g
,
th
e
y
a
r
e
ty
p
ically
s
tatic
an
d
lack
ad
ap
tiv
e
lear
n
i
n
g
ca
p
ab
ilit
y
.
Pre
v
io
u
s
h
y
b
r
i
d
ap
p
r
o
ac
h
es
co
m
b
in
i
n
g
RL
an
d
FIS
p
r
im
ar
ily
em
p
h
asize
p
r
e
d
ictiv
e
p
er
f
o
r
m
an
ce
o
r
p
o
licy
o
p
tim
izatio
n
,
wh
ile
lim
ited
atten
tio
n
h
as
b
ee
n
g
i
v
en
to
r
e
g
u
latin
g
ex
p
lo
r
atio
n
b
eh
av
io
r
u
n
d
e
r
ex
p
licit
r
is
k
co
n
s
tr
ain
ts
.
I
n
p
r
ac
tical
tr
ad
in
g
s
y
s
tem
s
,
u
n
co
n
tr
o
lled
ex
p
lo
r
atio
n
ca
n
lead
to
ex
ce
s
s
iv
e
ex
p
o
s
u
r
e
an
d
u
n
s
tab
le
d
ec
is
io
n
d
y
n
am
ics.
C
o
n
s
eq
u
en
tly
,
th
er
e
r
em
ai
n
s
a
n
ee
d
f
o
r
a
co
m
p
ac
t
h
y
b
r
id
d
ec
is
io
n
ar
ch
itectu
r
e
th
at
in
te
g
r
ates
ad
ap
tiv
e
RL
,
in
ter
p
r
etab
le
f
u
zz
y
r
ea
s
o
n
in
g
,
an
d
ex
p
licit m
ec
h
an
is
m
s
f
o
r
r
i
s
k
-
co
n
s
tr
ain
ed
e
x
p
lo
r
atio
n
.
T
h
is
s
tu
d
y
p
r
o
p
o
s
es a
r
is
k
-
co
n
s
tr
ain
ed
SAR
S
A
–
FIS
h
y
b
r
id
d
ec
is
io
n
ar
ch
itectu
r
e
d
esig
n
ed
t
o
ad
d
r
ess
th
e
lim
itatio
n
s
o
f
co
n
v
e
n
tio
n
al
r
ein
f
o
r
ce
m
e
n
t
lear
n
in
g
s
y
s
tem
s
in
f
in
an
cial
en
v
ir
o
n
m
en
ts
.
T
h
e
f
r
am
ewo
r
k
in
teg
r
ates
a
co
m
p
ac
t
SAR
SA
lear
n
in
g
en
v
ir
o
n
m
e
n
t
with
a
Su
g
en
o
-
ty
p
e
FIS
th
at
m
ap
s
r
e
in
f
o
r
ce
m
e
n
t
s
ig
n
als
in
to
in
ter
p
r
etab
le
tr
ad
in
g
d
ec
is
io
n
s
.
I
n
ad
d
itio
n
,
an
ad
ap
tiv
e
ex
p
lo
r
atio
n
co
n
tr
o
l
m
ec
h
an
is
m
with
a
d
r
awd
o
wn
-
t
r
ig
g
er
e
d
r
eset
is
in
tr
o
d
u
ce
d
t
o
r
e
g
u
late
e
x
p
lo
r
at
io
n
d
y
n
am
ics
u
n
d
e
r
b
o
u
n
d
ed
r
is
k
co
n
d
itio
n
s
.
T
h
e
ar
ch
itectu
r
e
is
im
p
lem
en
ted
as
a
m
o
d
u
lar
e
x
ec
u
tio
n
ag
en
t
in
Me
taT
r
ad
er
5
an
d
ev
alu
ated
th
r
o
u
g
h
m
u
lti
-
h
o
r
izo
n
b
ac
k
test
in
g
ex
p
er
i
m
en
ts
o
n
th
e
GB
PUSD
cu
r
r
en
cy
p
air
.
T
h
e
s
ig
n
if
ican
ce
o
f
th
e
p
r
o
p
o
s
ed
ar
ch
itectu
r
e
lies
in
d
em
o
n
s
tr
atin
g
th
at
RL
,
in
ter
p
r
eta
b
le
f
u
zz
y
d
ec
is
io
n
m
ap
p
in
g
,
a
n
d
ex
p
li
cit
r
is
k
co
n
s
tr
ain
ts
ca
n
b
e
in
teg
r
ated
with
in
a
lig
h
tweig
h
t
o
p
er
atio
n
al
tr
ad
in
g
s
y
s
tem
.
B
y
co
m
b
in
in
g
ad
ap
tiv
e
lear
n
in
g
with
s
tr
u
ctu
r
ed
d
ec
is
io
n
r
u
les,
th
e
f
r
am
ewo
r
k
s
u
p
p
o
r
ts
b
o
th
p
o
li
cy
ad
ap
tab
ilit
y
a
n
d
d
ec
is
io
n
t
r
an
s
p
ar
en
cy
.
Su
ch
ch
ar
ac
ter
is
tics
ar
e
p
ar
ticu
lar
ly
im
p
o
r
tan
t
f
o
r
s
af
ety
-
cr
itical
ar
tific
ial
in
tellig
en
ce
(
AI
)
ap
p
licatio
n
s
wh
er
e
lear
n
in
g
alg
o
r
ith
m
s
m
u
s
t
o
p
e
r
ate
with
in
p
r
ed
ef
in
e
d
r
is
k
b
o
u
n
d
ar
ies.
T
h
e
p
r
o
p
o
s
ed
SAR
S
A
–
FIS
ar
ch
itectu
r
e
th
er
ef
o
r
e
co
n
tr
ib
u
tes
to
th
e
d
e
v
elo
p
m
en
t
o
f
in
ter
p
r
etab
le
an
d
r
is
k
-
awa
r
e
in
tellig
en
t
d
ec
is
io
n
s
y
s
tem
s
s
u
itab
le
f
o
r
d
y
n
am
ic
a
n
d
u
n
ce
r
tain
en
v
ir
o
n
m
en
ts
.
2.
T
H
E
O
R
E
T
I
CA
L
F
O
UNDA
T
I
O
N
AND
R
E
L
AT
E
D
WO
RK
R
L
h
as
b
ee
n
wid
ely
ad
o
p
ted
f
o
r
s
eq
u
en
tial
d
ec
is
io
n
-
m
ak
in
g
p
r
o
b
lem
s
u
n
d
e
r
u
n
ce
r
tain
ty
.
I
n
f
in
an
cial
tr
ad
in
g
r
esear
ch
,
ea
r
l
y
s
tu
d
ies ap
p
lied
SAR
SA(
λ
)
,
Q(
λ
)
,
an
d
T
D(
λ
)
ag
en
ts
f
o
r
p
o
r
tf
o
lio
m
an
ag
e
m
en
t
an
d
r
ep
o
r
ted
im
p
r
o
v
e
m
en
ts
co
m
p
ar
ed
t
o
s
tatic
r
u
le
-
b
ased
b
en
ch
m
ar
k
s
[
1
]
.
Fu
r
th
er
d
e
v
e
lo
p
m
en
ts
in
tr
o
d
u
ce
d
d
ir
ec
tio
n
al
ch
a
n
g
e
R
L
to
im
p
r
o
v
e
r
o
b
u
s
tn
ess
in
h
ig
h
-
f
r
e
q
u
en
cy
an
d
v
o
latile
co
n
d
itio
n
s
[
2
]
.
Mo
r
e
r
ec
en
t
s
tu
d
ies
ap
p
lied
d
ee
p
R
L
ar
ch
i
tectu
r
es,
in
clu
d
i
n
g
c
o
n
v
o
lu
tio
n
al
an
d
r
ec
u
r
r
e
n
t
n
etwo
r
k
s
,
f
o
r
f
ea
tu
r
e
e
x
tr
ac
tio
n
an
d
d
y
n
am
ic
p
o
licy
lear
n
in
g
[
3
]
.
Hy
b
r
id
en
s
em
b
le
a
p
p
r
o
ac
h
es
s
u
ch
as
PP
O,
A2
C
,
a
n
d
S
AC
h
av
e
also
b
ee
n
p
r
o
p
o
s
ed
to
in
cr
ea
s
e
ad
ap
tab
i
lity
ac
r
o
s
s
d
if
f
e
r
en
t
m
ar
k
et
r
e
g
im
es
[
4
]
.
Oth
er
wo
r
k
s
in
teg
r
ated
r
ec
u
r
r
en
t
an
d
ac
to
r
–
cr
itic
s
tr
u
ctu
r
es
to
im
p
r
o
v
e
r
is
k
h
an
d
lin
g
in
n
o
n
-
s
tatio
n
ar
y
en
v
ir
o
n
m
e
n
t
[
5
]
,
[
6
]
.
R
ev
iews
o
f
f
o
r
eig
n
ex
ch
an
g
e
p
r
ed
ictio
n
m
o
d
els
s
h
o
w
th
at
g
ated
r
ec
u
r
r
en
t
u
n
it
(
GR
U)
,
lo
n
g
s
h
o
r
t
-
ter
m
m
em
o
r
y
(
L
STM
)
an
d
tr
an
s
f
o
r
m
er
-
b
ased
m
o
d
els
d
o
m
in
ate
r
ec
en
t
r
esear
ch
,
r
ef
lec
tin
g
th
e
g
r
o
win
g
m
atu
r
ity
o
f
R
L
-
b
ased
f
in
an
cial
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
A
r
is
k
-
co
n
s
tr
a
in
ed
S
A
R
S
A
–
F
I
S
h
yb
r
id
d
ec
is
io
n
a
r
ch
itectu
r
e
…
(
Jo
n
i F
a
t
)
1533
s
y
s
tem
s
[
7
]
.
T
h
ese
d
ev
elo
p
m
en
ts
d
em
o
n
s
tr
ate
s
tr
o
n
g
a
d
ap
tab
ilit
y
o
f
R
L
,
b
u
t
t
h
ey
also
in
tr
o
d
u
ce
h
i
g
h
co
m
p
u
tatio
n
al
c
o
m
p
lex
ity
an
d
lim
ited
in
ter
p
r
etab
ilit
y
.
I
n
p
ar
allel,
FIS
h
av
e
b
ee
n
ap
p
lied
in
f
in
a
n
cial
p
r
e
d
ictio
n
d
u
e
to
th
eir
ca
p
a
b
ilit
y
to
m
an
ag
e
u
n
ce
r
tain
ty
an
d
en
co
d
e
ex
p
er
t
r
ea
s
o
n
in
g
.
Neu
r
al
–
f
u
zz
y
m
o
d
els h
av
e
s
h
o
wn
co
m
p
etitiv
e
p
er
f
o
r
m
a
n
ce
in
s
to
ck
an
d
co
m
m
o
d
it
y
f
o
r
ec
asti
n
g
ta
s
k
s
[
8
]
,
[
9
]
.
Oth
er
ap
p
r
o
ac
h
es
co
m
b
in
ed
f
u
zz
y
lo
g
ic
with
K
alm
an
f
ilter
in
g
an
d
p
ar
ticle
s
war
m
o
p
tim
izatio
n
t
o
im
p
r
o
v
e
r
o
b
u
s
tn
ess
u
n
d
er
n
o
is
y
co
n
d
itio
n
s
[
1
0
]
.
R
L
an
d
f
u
zz
y
h
y
b
r
id
s
h
a
v
e
also
b
ee
n
ex
p
lo
r
ed
,
esp
ec
ially
in
en
v
ir
o
n
m
en
ts
wh
er
e
in
ter
p
r
etab
ilit
y
is
r
eq
u
ir
ed
to
g
e
th
er
with
ad
ap
tiv
e
lear
n
in
g
[
3
]
.
I
n
ad
d
itio
n
,
s
tab
ilit
y
an
aly
s
is
o
f
f
u
zz
y
-
b
ased
in
tellig
en
t
s
y
s
tem
s
h
as
b
ee
n
in
v
esti
g
ated
,
in
clu
d
in
g
asy
m
p
to
tic
s
tab
ilit
y
an
d
p
er
i
o
d
ic
b
eh
a
v
io
r
u
n
d
er
u
n
ce
r
ta
in
ty
an
d
d
ela
y
co
n
d
itio
n
s
[
1
1
]
.
T
h
ese
s
tu
d
ies
h
ig
h
lig
h
t th
at
f
u
zz
y
s
y
s
tem
s
p
r
o
v
id
e
tr
a
n
s
p
ar
en
c
y
an
d
s
tr
u
ctu
r
ed
r
ea
s
o
n
in
g
,
w
h
ile
R
L
p
r
o
v
id
es a
d
ap
tab
ilit
y
.
Gam
e
-
th
eo
r
etic
p
er
s
p
ec
tiv
es
h
av
e
also
b
ee
n
ap
p
lied
t
o
f
in
an
cial
s
y
s
tem
s
to
m
o
d
el
s
tr
ateg
ic
in
ter
ac
tio
n
am
o
n
g
ag
e
n
ts
.
Me
an
-
f
ield
g
am
es
h
a
v
e
b
ee
n
u
s
ed
to
s
tu
d
y
o
p
tim
al
liq
u
id
ati
o
n
u
n
d
er
cr
o
wd
in
g
ef
f
ec
ts
[
1
2
]
,
w
h
ile
s
to
ch
asti
c
t
r
ad
in
g
g
am
es
h
av
e
b
ee
n
p
r
o
p
o
s
ed
to
r
ep
r
esen
t
h
eter
o
g
en
e
o
u
s
b
elief
s
in
m
ar
k
et
d
y
n
am
ics
[
1
3
]
.
Oth
er
w
o
r
k
s
an
aly
ze
f
in
an
cial
s
tab
ilit
y
an
d
s
y
s
tem
ic
r
eso
lu
tio
n
u
s
i
n
g
g
am
e
-
th
eo
r
etic
f
r
am
ewo
r
k
s
[
1
4
]
,
[
1
5
]
.
Gam
e
th
eo
r
y
h
as
also
b
ee
n
u
s
ed
to
e
x
p
lain
liq
u
id
ity
f
o
r
m
atio
n
in
o
r
d
er
-
b
o
o
k
m
ar
k
ets
an
d
to
m
o
d
el
s
to
ck
p
r
ices
th
r
o
u
g
h
Ma
r
k
o
v
-
b
ased
g
am
e
s
tr
u
ctu
r
es
[
1
6
]
,
[
1
7
]
.
Alth
o
u
g
h
th
ese
ap
p
r
o
ac
h
es
p
r
o
v
id
e
u
s
ef
u
l
th
eo
r
etica
l
in
s
ig
h
ts
,
m
o
s
t
o
f
th
em
r
em
ain
co
n
ce
p
tu
al
an
d
ar
e
r
a
r
ely
em
b
ed
d
ed
d
ir
ec
tly
in
to
lig
h
tweig
h
t o
p
er
atio
n
al
tr
ad
in
g
ar
ch
itectu
r
es
[
1
8
]
.
Ov
er
all,
p
r
io
r
liter
atu
r
e
s
h
o
ws
th
at
R
L
p
r
o
v
id
es
ad
ap
tiv
e
p
o
licy
o
p
tim
izatio
n
,
f
u
zz
y
in
f
e
r
e
n
ce
o
f
f
er
s
in
ter
p
r
etab
ilit
y
an
d
s
tr
u
ctu
r
ed
r
ea
s
o
n
in
g
,
a
n
d
g
a
m
e
-
th
eo
r
et
ic
an
aly
s
is
p
r
o
v
id
es
a
p
er
s
p
e
ctiv
e
o
n
b
o
u
n
d
ed
s
tr
ateg
ic
b
eh
av
io
r
[
1
9
]
.
Ho
w
ev
er
,
ex
is
tin
g
s
tu
d
ies
r
ar
ely
co
m
b
in
e
th
ese
elem
en
ts
in
to
a
co
m
p
ac
t
an
d
r
is
k
-
co
n
s
tr
ain
ed
d
ec
is
io
n
ar
ch
itect
u
r
e
s
u
itab
le
f
o
r
r
ea
l
-
tim
e
ex
e
cu
tio
n
.
I
n
p
ar
tic
u
lar
,
lim
ited
atten
tio
n
h
as
b
ee
n
g
iv
en
to
in
te
g
r
atin
g
a
d
ap
tiv
e
e
x
p
lo
r
atio
n
co
n
tr
o
l w
ith
ex
p
lici
t d
r
awd
o
wn
c
o
n
s
tr
ain
ts
in
h
y
b
r
id
r
ein
f
o
r
ce
m
en
t
–
f
u
zz
y
s
y
s
tem
s
.
B
ased
o
n
th
is
th
eo
r
etica
l
b
ac
k
g
r
o
u
n
d
,
th
e
p
r
esen
t
s
tu
d
y
p
r
o
p
o
s
es
a
lig
h
tweig
h
t
SAR
SA
–
FI
S
h
y
b
r
id
ar
ch
itectu
r
e
with
ad
ap
tiv
e
ex
p
l
o
r
atio
n
c
o
n
tr
o
l.
T
h
e
f
r
am
ew
o
r
k
ai
m
s
to
co
m
b
in
e
o
n
lin
e
R
L
,
in
ter
p
r
etab
le
f
u
zz
y
r
u
le
m
ap
p
in
g
,
a
n
d
b
o
u
n
d
ed
r
is
k
r
eg
u
lat
io
n
with
in
a
u
n
if
ied
d
ec
is
io
n
s
tr
u
ctu
r
e
[
1
9
]
.
T
h
e
p
r
o
p
o
s
ed
m
eth
o
d
is
p
o
s
itio
n
e
d
as
a
c
o
m
p
ac
t
an
d
co
m
p
u
tatio
n
ally
ef
f
icie
n
t
alter
n
ativ
e
to
d
ee
p
R
L
ap
p
r
o
ac
h
es,
wh
ile
m
ain
tain
in
g
ad
a
p
tab
ilit
y
an
d
o
p
er
atio
n
al
s
tab
ilit
y
u
n
d
e
r
p
r
ed
e
f
in
ed
r
is
k
lim
its
.
3.
M
E
T
H
O
D
T
h
is
s
ec
tio
n
d
escr
ib
es
th
e
ex
p
er
im
en
tal
d
esig
n
an
d
im
p
lem
e
n
tatio
n
o
f
t
h
e
r
is
k
-
co
n
s
tr
ain
ed
SAR
S
A
–
FIS
h
y
b
r
id
d
ec
is
io
n
a
r
ch
itect
u
r
e.
T
h
e
f
r
am
ewo
r
k
in
teg
r
ate
s
a
co
m
p
ac
t
R
L
en
v
ir
o
n
m
en
t,
a
Su
g
en
o
-
ty
p
e
FIS,
ad
ap
tiv
e
ex
p
lo
r
atio
n
co
n
t
r
o
l,
an
d
m
u
lti
-
lev
el
r
is
k
co
n
s
tr
ain
ts
with
in
a
u
n
if
ied
ex
ec
u
tio
n
ag
en
t.
T
h
e
o
v
e
r
all
o
b
jectiv
e
o
f
th
e
d
esig
n
is
to
c
r
ea
te
an
in
ter
p
r
etab
le
a
n
d
r
is
k
-
awa
r
e
lear
n
in
g
f
r
am
ew
o
r
k
ca
p
ab
le
o
f
a
d
ap
tin
g
to
ch
an
g
in
g
m
ar
k
et
c
o
n
d
itio
n
s
wh
ile
m
ain
tain
in
g
c
o
n
tr
o
lled
tr
a
d
in
g
b
e
h
av
io
r
.
3
.
1
.
Da
t
a
a
nd
ex
ec
utio
n e
nv
iro
nm
ent
T
h
e
ass
et
u
s
ed
in
th
is
s
tu
d
y
is
th
e
GB
PUSD
cu
r
r
en
cy
p
air
.
T
h
e
SAR
SA
ag
en
t
was
tr
ain
ed
o
n
h
is
to
r
ical
d
ata
f
r
o
m
3
0
J
u
n
e
2
0
2
0
t
o
2
J
u
ly
2
0
2
4
.
Ou
t
-
of
-
s
am
p
le
ev
alu
atio
n
was
co
n
d
u
cte
d
f
r
o
m
1
J
an
u
a
r
y
to
3
0
J
u
n
e
2
0
2
5
.
Ad
d
itio
n
al
e
x
ten
d
ed
test
in
g
o
n
2
0
2
3
d
ata
w
as
p
er
f
o
r
m
ed
to
ass
ess
r
o
b
u
s
tn
ess
u
n
d
er
d
if
f
er
en
t
m
ar
k
et
r
e
g
im
es.
T
h
e
s
y
s
tem
was
im
p
lem
en
ted
as
an
ex
p
er
t
ad
v
is
o
r
(
E
A
)
in
Me
taT
r
a
d
er
5
u
s
in
g
th
e
MQ
L
5
p
r
o
g
r
a
m
m
in
g
la
n
g
u
a
g
e.
All
tr
ad
in
g
d
ec
is
io
n
s
o
p
er
ate
o
n
th
e
M1
5
tim
ef
r
am
e.
T
ec
h
n
ical
in
d
icato
r
s
u
s
ed
f
o
r
f
ea
tu
r
e
e
x
tr
ac
tio
n
in
clu
d
e
(
50
)
,
(
10
)
,
(
12
,
26
,
9
)
,
(
14
)
,
an
d
E
MA
-
b
ased
s
tan
d
a
r
d
d
ev
iatio
n
.
Fo
r
r
e
p
r
o
d
u
cib
ilit
y
,
th
e
Q
-
tab
le,
f
u
zz
y
r
u
le
m
atr
i
x
,
an
d
d
r
aw
d
o
wn
s
tatu
s
ar
e
p
er
s
is
ted
to
ex
ter
n
al
tex
t f
iles
af
ter
ea
ch
lear
n
i
n
g
u
p
d
ate.
3
.
2
.
SARSA st
a
t
e
–
a
c
t
io
n e
nv
iro
nm
ent
T
h
e
R
L
co
m
p
o
n
e
n
t
is
f
o
r
m
u
l
ated
as
a
c
o
m
p
ac
t
Ma
r
k
o
v
d
e
cisi
o
n
p
r
o
ce
s
s
with
t
h
r
ee
s
tate
s
an
d
th
r
ee
ac
tio
n
s
.
T
h
e
s
tate
s
p
ac
e
S
=
{
S1
,
S2
,
S3
}
is
d
e
f
in
ed
ac
co
r
d
in
g
to
p
r
ice
d
is
tan
ce
f
r
o
m
E
MA
(
5
0
)
u
s
in
g
a
±
2
0
p
ip
b
ar
r
ier
.
State
S1
r
ep
r
esen
t
s
p
r
ice
b
elo
w
(
50
)
m
in
u
s
2
0
p
ip
s
,
S2
r
ep
r
esen
ts
p
r
ice
with
in
±
2
0
p
ip
s
o
f
th
e
E
MA
,
an
d
S3
r
ep
r
esen
ts
p
r
ice
ab
o
v
e
(
50
)
p
lu
s
2
0
p
ip
s
.
T
h
e
ac
tio
n
s
p
ac
e
=
{
,
,
}
is
en
co
d
ed
as
v
alu
es
0
to
2
an
d
s
elec
ted
th
r
o
u
g
h
a
n
ε
-
g
r
ee
d
y
p
o
lic
y
.
T
r
an
s
itio
n
d
y
n
am
ics
ar
e
g
o
v
e
r
n
ed
b
y
a
f
ix
ed
3
×3
×
3
ten
s
o
r
th
at
in
tr
o
d
u
ce
s
co
n
tr
o
lled
s
to
ch
asti
city
in
n
ex
t
-
s
tate
s
am
p
lin
g
.
T
h
e
r
ewa
r
d
s
tr
u
ctu
r
e
is
d
ef
in
ed
as
a
s
h
ap
e
d
cu
b
e
[
,
,
′
]
,
b
alan
cin
g
ex
p
lo
r
atio
n
p
en
alties
a
n
d
tr
en
d
-
f
o
llo
win
g
in
ce
n
tiv
es.
Actio
n
s
th
at
m
ain
tain
u
n
f
av
o
r
ab
le
s
tates
r
ec
eiv
e
n
eg
ativ
e
r
ewa
r
d
s
,
wh
ile
tr
an
s
itio
n
s
al
ig
n
ed
with
f
av
o
r
ab
le
p
r
ice
m
o
v
em
en
ts
r
ec
eiv
e
p
o
s
itiv
e
r
e
war
d
s
.
T
h
e
SAR
SA u
p
d
ate
r
u
l
e
is
ap
p
lied
at
ev
er
y
m
ar
k
et
tick
as
:
(
,
)
←
(
,
)
+
(
+
(
′
,
′
)
−
(
,
)
)
(
1
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
1
6
,
No
.
3
,
J
u
n
e
20
2
6
:
1
5
3
1
-
1
5
4
2
1534
with
d
is
co
u
n
t f
ac
to
r
γ
=0
.
9
.
T
h
e
lear
n
in
g
r
ate
α
is
ad
ap
tiv
e.
I
t
is
s
ca
led
u
s
in
g
(
14
)
an
d
E
M
A
-
b
ased
s
tan
d
ar
d
d
ev
iatio
n
to
r
ef
lect
v
o
latilit
y
clu
s
ter
in
g
an
d
is
b
o
u
n
d
ed
with
in
th
e
in
ter
v
al
[
0
.
0
1
,
0
.
3
0
]
.
I
n
tr
en
d
in
g
r
eg
im
es,
an
ad
d
itio
n
al
b
o
u
n
d
ed
m
o
m
e
n
tu
m
ad
ju
s
t
m
en
t
d
er
iv
ed
f
r
o
m
E
MA
d
ev
iatio
n
m
o
d
if
ies
α
with
in
±
0
.
1
to
ac
ce
ler
ate
ad
ap
tatio
n
.
Fig
u
r
e
1
illu
s
tr
ates
th
e
SAR
SA
en
v
ir
o
n
m
en
t,
s
h
o
win
g
th
e
th
r
ee
s
tates,
av
ailab
le
ac
tio
n
s
,
an
d
r
ewa
r
d
r
elatio
n
s
h
ip
s
th
at
g
u
id
e
th
e
lear
n
in
g
p
r
o
ce
s
s
.
Fig
u
r
e
1
.
SAR
SA e
n
v
ir
o
n
m
e
n
t w
ith
th
r
ee
s
tates (
S1
–
S3
)
,
av
ailab
le
ac
tio
n
s
,
an
d
c
o
r
r
esp
o
n
d
in
g
r
ewa
r
d
s
ig
n
als
3
.
3
.
Ada
ptiv
e
e
x
plo
ra
t
io
n c
o
ntr
o
l
E
x
p
lo
r
atio
n
f
o
llo
ws a
d
ec
a
y
in
g
ε
-
g
r
ee
d
y
p
o
licy
d
e
f
in
ed
as
ₜ
=
(
ₘ
ᵢ
ₙ
,
₀
ᵗ
)
(
2
)
wh
er
e
ϵ
0
=
0
.
3
0
,
ϵ
min
=
0
.
0
5
,
a
n
d
δ
=
0
.
9
9
9
.
T
o
en
f
o
r
ce
r
is
k
-
co
n
s
tr
ain
ed
lear
n
i
n
g
,
a
d
r
awd
o
wn
-
tr
ig
g
e
r
ed
r
eset
m
ec
h
an
is
m
is
in
tr
o
d
u
ce
d
.
I
f
f
lo
atin
g
e
q
u
ity
d
r
awd
o
wn
ex
ce
ed
s
2
0
%
o
f
th
e
r
u
n
n
in
g
p
e
ak
,
ε
is
r
eset
to
0
.
Af
ter
r
eset,
ex
p
o
n
en
tial
d
ec
a
y
r
esu
m
es.
T
h
is
m
ec
h
a
n
is
m
allo
ws
r
en
ewe
d
ex
p
lo
r
atio
n
d
u
r
in
g
r
e
g
im
e
s
h
if
ts
wh
ile
m
ain
tain
in
g
b
o
u
n
d
ed
r
is
k
ex
p
o
s
u
r
e.
3
.
4
.
F
uzzy
infe
re
nce
inte
g
ra
t
io
n
T
h
e
r
ein
f
o
r
ce
m
en
t
s
ig
n
als
g
en
er
ated
b
y
SAR
SA
ar
e
m
ap
p
ed
in
to
s
tr
u
ctu
r
ed
tr
ad
in
g
d
ec
is
io
n
s
u
s
in
g
a
Su
g
en
o
-
ty
p
e
FIS
co
n
s
is
tin
g
o
f
2
7
r
u
les
ar
r
an
g
e
d
in
a
3
×3
×3
s
tr
u
ct
u
r
e.
T
h
e
in
p
u
ts
o
f
th
e
FIS
ar
e
th
e
n
o
r
m
alize
d
cu
r
r
en
t
-
s
tate
Q
-
v
alu
e,
th
e
n
o
r
m
alize
d
p
r
e
d
icted
n
ex
t
-
s
tate
Q
-
v
alu
e,
an
d
th
e
im
m
ed
iate
r
ewa
r
d
.
E
ac
h
in
p
u
t
v
ar
iab
le
is
p
ar
titi
o
n
ed
in
to
th
r
ee
lin
g
u
is
tic
lev
els:
L
o
w,
Mo
d
er
ate,
an
d
Hig
h
,
d
ef
in
e
d
u
s
in
g
tr
ap
ez
o
id
al
an
d
tr
ian
g
u
lar
m
e
m
b
er
s
h
ip
f
u
n
ctio
n
s
.
T
h
e
r
u
le
b
ase
m
ap
s
th
e
tr
ip
let
(
C
u
r
r
en
t
State,
Pre
d
icted
State,
R
ewa
r
d
)
to
Su
g
en
o
c
o
n
s
eq
u
e
n
ts
in
th
e
s
et
{0
.
5
,
1
.
5
,
2
.
5
},
co
r
r
esp
o
n
d
in
g
to
Sell,
Ho
ld
,
a
n
d
B
u
y
s
ig
n
als.
Def
u
zz
if
icatio
n
is
p
e
r
f
o
r
m
e
d
u
s
in
g
th
e
weig
h
ted
av
er
ag
e
m
et
h
o
d
,
p
r
o
d
u
cin
g
a
co
n
tin
u
o
u
s
co
n
tr
o
l
s
ig
n
al
th
at
is
s
u
b
s
eq
u
en
tly
d
is
cr
etize
d
.
Ou
tp
u
t
v
alu
es
b
elo
w
1
.
0
i
n
d
icate
Se
ll,
v
alu
es
ar
o
u
n
d
1
.
5
in
d
icate
Ho
ld
,
a
n
d
v
alu
es
ab
o
v
e
2
.
0
in
d
icate
B
u
y
.
T
h
e
f
u
zz
y
r
u
le
m
atr
ix
ca
n
b
e
p
er
s
is
ted
to
ex
ter
n
al
s
to
r
ag
e
f
o
r
in
c
r
em
en
tal
tu
n
in
g
a
n
d
r
ep
r
o
d
u
cib
ilit
y
.
R
ep
r
esen
tativ
e
r
u
le
m
a
p
p
in
g
s
ar
e
s
u
m
m
a
r
ized
i
n
T
ab
le
1
,
i
llu
s
tr
atin
g
th
e
r
elatio
n
s
h
ip
b
etwe
en
C
u
r
r
en
t
State
(
C
S),
Pre
d
icted
State
(
PS
)
,
R
e
war
d
(
R
W
)
,
an
d
th
e
c
o
r
r
esp
o
n
d
in
g
Su
g
e
n
o
o
u
tp
u
t.
T
ab
le
1
.
R
ep
r
esen
tativ
e
Su
g
e
n
o
r
u
les m
ap
p
in
g
C
S,
PS
,
an
d
R
W
to
tr
ad
in
g
s
ig
n
als
C
u
r
r
e
n
t
S
t
a
t
e
P
r
e
d
i
c
t
e
d
S
t
a
t
e
R
e
w
a
r
d
O
u
t
p
u
t
S
i
g
n
a
l
Lo
w
Lo
w
Lo
w
0
.
5
S
e
l
l
M
o
d
e
r
a
t
e
M
o
d
e
r
a
t
e
M
o
d
e
r
a
t
e
1
.
5
H
o
l
d
H
i
g
h
H
i
g
h
H
i
g
h
2
.
5
B
u
y
Lo
w
H
i
g
h
M
o
d
e
r
a
t
e
1
.
5
H
o
l
d
H
i
g
h
Lo
w
H
i
g
h
0
.
5
S
e
l
l
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
A
r
is
k
-
co
n
s
tr
a
in
ed
S
A
R
S
A
–
F
I
S
h
yb
r
id
d
ec
is
io
n
a
r
ch
itectu
r
e
…
(
Jo
n
i F
a
t
)
1535
3
.
5
.
E
x
ec
utio
n lo
g
ic
a
nd
risk
co
ns
t
ra
ints
T
r
ad
in
g
is
ex
ec
u
ted
e
x
clu
s
iv
e
ly
o
n
GB
PUSD.
T
h
e
Su
g
en
o
o
u
tp
u
t
s
er
v
es
as
th
e
p
r
im
ar
y
s
ig
n
al
g
ate
an
d
m
u
s
t
b
e
co
n
f
ir
m
e
d
b
y
(
10
)
c
r
o
s
s
o
v
er
an
d
MA
C
D
h
is
to
g
r
am
m
o
m
en
tu
m
b
e
f
o
r
e
tr
ad
e
en
tr
y
.
R
is
k
m
an
ag
em
en
t
is
im
p
lem
en
te
d
at
m
u
ltip
le
lev
els.
E
ac
h
p
o
s
itio
n
in
clu
d
es
a
ta
k
e
-
p
r
o
f
it
th
r
esh
o
ld
o
f
1
0
USD,
with
an
au
x
iliar
y
clo
s
u
r
e
at
1
2
USD
to
s
ec
u
r
e
ex
ten
d
ed
g
a
in
s
.
A
cu
t
-
lo
s
s
th
r
esh
o
ld
o
f
−
8
USD
is
ap
p
lied
wh
en
th
e
f
u
zz
y
s
y
s
tem
in
d
icat
es
r
ev
er
s
al
co
n
d
itio
n
s
.
At
th
e
ac
co
u
n
t
lev
el,
a
m
ax
im
u
m
d
r
a
wd
o
wn
k
ill
-
s
witch
is
im
p
lem
en
ted
v
ia
an
ex
ter
n
al
f
ile.
I
f
ac
tiv
ated
,
all
p
o
s
itio
n
s
ar
e
clo
s
ed
an
d
tr
ad
in
g
is
h
alted
.
T
o
m
itig
ate
tr
ad
e
clu
s
ter
in
g
,
a
m
an
d
ato
r
y
i
n
ter
v
al
o
f
f
o
u
r
h
o
u
r
s
is
im
p
o
s
ed
b
etwe
en
co
n
s
ec
u
tiv
e
tr
ad
es
.
T
h
ese
co
n
s
tr
ain
ts
en
s
u
r
e
th
at
lear
n
in
g
an
d
ex
ec
u
tio
n
o
p
er
ate
with
in
p
r
e
d
ef
in
ed
r
is
k
b
o
u
n
d
ar
ies.
3
.
6
.
B
a
s
eline
a
nd
co
m
pa
ra
t
i
v
e
co
nfig
ura
t
io
ns
T
h
r
ee
c
o
n
f
ig
u
r
atio
n
s
a
r
e
e
v
alu
ated
u
n
d
er
id
en
tical
m
ar
k
et
d
ata,
tr
an
s
ac
tio
n
co
s
ts
,
an
d
r
is
k
co
n
s
tr
ain
ts
.
T
h
e
b
aselin
e
co
n
f
ig
u
r
atio
n
ap
p
lies
r
u
le
-
b
ased
E
MA
an
d
MA
C
D
f
ilter
s
w
ith
i
d
en
tical
p
r
o
f
it
an
d
lo
s
s
p
ar
am
eter
s
b
u
t
with
o
u
t
lear
n
in
g
o
r
f
u
zz
y
in
f
er
en
ce
.
T
h
e
R
L
-
o
n
ly
co
n
f
ig
u
r
atio
n
a
p
p
li
es
SA
R
SA
d
ir
ec
tl
y
u
s
in
g
ar
g
m
ax
(
,
)
f
o
r
ac
tio
n
s
elec
tio
n
.
T
h
e
h
y
b
r
id
co
n
f
ig
u
r
at
io
n
in
teg
r
ates
SAR
S
A,
Su
g
en
o
FIS,
an
d
ad
ap
tiv
e
e
x
p
lo
r
atio
n
c
o
n
tr
o
l.
T
h
is
d
esig
n
is
o
lates
th
e
co
n
t
r
ib
u
tio
n
o
f
h
y
b
r
id
lear
n
in
g
an
d
r
is
k
-
co
n
s
tr
ain
ed
ex
p
lo
r
atio
n
.
3
.
7
.
Sy
s
t
e
m
a
rc
hite
ct
ure
a
n
d r
epro
du
cib
ility
T
h
e
ar
c
h
itectu
r
e
is
im
p
lem
en
t
ed
as
a
m
o
d
u
lar
E
A
c
o
n
s
is
tin
g
o
f
a
SAR
SA
lear
n
in
g
m
o
d
u
le,
f
u
zz
y
in
f
er
en
ce
m
o
d
u
le,
r
is
k
m
an
ag
er
,
an
d
tr
ad
e
ex
ec
u
to
r
.
At
ea
ch
m
ar
k
et
tick
,
tech
n
ical
in
d
ic
ato
r
s
ar
e
co
m
p
u
te
d
an
d
p
ass
ed
to
th
e
SA
R
SA
m
o
d
u
le.
Up
d
ated
Q
-
v
al
u
es
an
d
r
ewa
r
d
s
ar
e
p
r
o
ce
s
s
ed
b
y
th
e
f
u
zz
y
s
y
s
tem
to
g
en
er
ate
a
tr
ad
in
g
s
co
r
e
.
T
h
e
s
ig
n
al
is
v
alid
ated
b
y
co
n
f
ir
m
atio
n
f
ilter
s
an
d
p
r
o
ce
s
s
ed
b
y
th
e
r
is
k
m
an
ag
e
r
b
ef
o
r
e
e
x
ec
u
tio
n
.
E
x
ec
u
te
d
tr
a
d
es a
r
e
f
ed
b
ac
k
in
to
th
e
lear
n
i
n
g
m
o
d
u
le,
e
n
ab
lin
g
c
o
n
tin
u
o
u
s
ad
ap
tatio
n
.
Fig
u
r
e
2
p
r
esen
ts
th
e
s
y
s
tem
ar
ch
itectu
r
e
an
d
s
ig
n
al
f
lo
w
f
r
o
m
m
ar
k
et
d
ata
ac
q
u
is
itio
n
to
ex
ec
u
tio
n
an
d
f
ee
d
b
ac
k
.
Fo
r
r
ep
r
o
d
u
ci
b
ilit
y
,
th
e
Q
-
tab
le
an
d
f
u
zz
y
we
ig
h
t
m
atr
ix
ar
e
wr
itten
to
d
is
k
af
ter
ea
ch
lear
n
i
n
g
s
tep
.
Up
o
n
r
ein
itializatio
n
,
t
h
e
m
o
s
t r
ec
en
t state
is
r
esto
r
ed
,
en
ab
lin
g
c
o
n
tin
u
atio
n
o
f
t
r
ain
i
n
g
ac
r
o
s
s
s
ess
io
n
s
.
Fig
u
r
e
2
.
C
o
m
p
o
n
en
t
-
lev
el
ar
c
h
itectu
r
e
o
f
t
h
e
SAR
SA
–
FIS
h
y
b
r
id
s
y
s
tem
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
1
6
,
No
.
3
,
J
u
n
e
20
2
6
:
1
5
3
1
-
1
5
4
2
1536
T
h
e
d
y
n
am
ic
o
p
e
r
atio
n
al
s
eq
u
en
ce
o
f
th
e
f
r
a
m
ewo
r
k
is
illu
s
tr
ated
in
Fig
u
r
e
3
,
s
h
o
win
g
th
e
p
ip
elin
e
f
r
o
m
m
ar
k
et
d
ata
ac
q
u
is
itio
n
to
s
ig
n
al
g
en
er
atio
n
,
r
is
k
v
ali
d
atio
n
,
ex
ec
u
tio
n
,
an
d
f
ee
d
b
a
ck
-
d
r
iv
e
n
lear
n
in
g
.
T
h
e
ex
p
er
im
en
tal
s
etu
p
o
f
t
h
e
tr
ad
in
g
s
y
s
tem
,
in
clu
d
in
g
d
ata
f
lo
w,
lear
n
in
g
m
o
d
u
les,
an
d
ex
ec
u
tio
n
en
v
ir
o
n
m
en
t,
is
illu
s
tr
ated
in
Fig
u
r
e
s
2
an
d
3
to
e
n
s
u
r
e
r
e
p
r
o
d
u
cib
ilit
y
.
Fig
u
r
e
3
.
Sy
s
tem
f
lo
w
d
iag
r
a
m
o
f
th
e
SAR
SA
–
FIS
h
y
b
r
id
t
r
ad
in
g
a
g
en
t
4.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
B
ac
k
test
in
g
ex
p
e
r
im
en
ts
wer
e
co
n
d
u
cted
o
n
th
e
GB
PUS
D
cu
r
r
en
cy
p
air
to
e
v
alu
ate
th
e
p
er
f
o
r
m
an
ce
o
f
t
h
e
r
is
k
-
c
o
n
s
tr
ain
ed
SAR
SA
–
FIS
h
y
b
r
id
f
r
a
m
ewo
r
k
.
T
h
e
s
ix
-
m
o
n
th
o
u
t
-
of
-
s
am
p
le
ev
alu
atio
n
co
v
er
s
th
e
p
er
i
o
d
f
r
o
m
1
J
a
n
u
ar
y
to
3
0
J
u
n
e
2
0
2
5
.
An
ex
ten
d
ed
o
n
e
-
y
ea
r
ev
alu
atio
n
o
n
2
0
2
3
d
ata
was
p
er
f
o
r
m
ed
t
o
ass
ess
r
o
b
u
s
tn
ess
u
n
d
er
d
if
f
er
e
n
t
v
o
latilit
y
r
eg
im
es.
All
c
o
n
f
ig
u
r
atio
n
s
wer
e
test
ed
u
n
d
er
id
en
tical
m
ar
k
et
d
ata,
tr
an
s
ac
tio
n
co
s
ts
,
an
d
e
x
ec
u
tio
n
co
n
d
itio
n
s
.
4
.
1
.
Six
-
m
o
nth
o
ut
-
of
-
s
a
m
ple e
v
a
lua
t
io
n
(
2
0
2
5
)
Fig
u
r
e
4
p
r
esen
ts
th
e
co
m
p
a
r
ativ
e
eq
u
ity
cu
r
v
es
o
f
th
e
h
y
b
r
id
SAR
SA
–
FIS
f
r
am
ewo
r
k
an
d
th
e
b
aselin
e
r
u
le
-
b
ased
co
n
f
ig
u
r
atio
n
d
u
r
in
g
th
e
2
0
2
5
ev
alu
atio
n
p
er
i
o
d
.
T
h
e
h
y
b
r
id
f
r
am
ewo
r
k
ex
h
ib
its
a
s
tab
l
e
u
p
war
d
b
alan
ce
t
r
ajec
to
r
y
with
lim
ited
eq
u
ity
r
etr
ac
e
m
en
ts
.
T
h
e
s
y
s
tem
ac
h
iev
e
d
a
n
et
p
r
o
f
it
o
f
ap
p
r
o
x
im
ately
9
0
USD,
wh
er
ea
s
th
e
b
aselin
e
co
n
f
i
g
u
r
atio
n
p
r
o
d
u
ce
d
a
p
p
r
o
x
im
ately
1
0
USD
u
n
d
er
th
e
s
am
e
co
n
d
itio
n
s
.
T
h
e
eq
u
ity
g
r
o
wth
o
f
th
e
h
y
b
r
id
m
o
d
el
s
h
o
ws
s
m
o
o
th
er
p
r
o
g
r
ess
io
n
an
d
m
o
r
e
co
n
s
is
ten
t
r
ec
o
v
er
y
f
o
llo
win
g
m
o
d
er
ate
d
r
awd
o
w
n
s
.
Fig
u
r
e
4
.
C
o
m
p
a
r
ativ
e
b
alan
c
e
cu
r
v
es o
f
th
e
SAR
SA
–
FIS
h
y
b
r
id
f
r
am
ewo
r
k
an
d
th
e
b
asel
in
e
s
y
s
tem
d
u
r
in
g
th
e
s
ix
-
m
o
n
th
2
0
2
5
ev
al
u
atio
n
p
er
io
d
T
r
a
d
e
-
l
ev
e
l
b
e
h
a
v
io
r
i
s
i
l
l
u
s
tr
a
t
e
d
i
n
F
i
g
u
r
e
5
,
w
h
i
ch
s
h
o
w
s
t
h
e
d
i
s
t
r
i
b
u
t
i
o
n
o
f
i
n
d
i
v
id
u
a
l
t
r
ad
e
o
u
t
co
m
e
s
o
v
er
t
i
m
e.
T
h
e
S
AR
S
A
–
F
I
S
f
r
a
m
e
w
o
r
k
d
e
m
o
n
s
t
r
a
t
e
s
c
l
e
ar
c
lu
s
t
e
r
i
n
g
o
f
tr
a
d
e
r
e
s
u
l
t
s
ar
o
u
n
d
t
h
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
A
r
is
k
-
co
n
s
tr
a
in
ed
S
A
R
S
A
–
F
I
S
h
yb
r
id
d
ec
is
io
n
a
r
ch
itectu
r
e
…
(
Jo
n
i F
a
t
)
1537
p
r
ed
e
f
in
e
d
t
ak
e
-
p
r
o
f
i
t
(
+
1
0
U
S
D
)
an
d
cu
t
-
lo
s
s
(
−8
U
S
D
)
th
r
e
s
h
o
ld
s
.
T
h
i
s
p
a
t
te
r
n
i
n
d
i
c
a
te
s
s
y
s
t
em
a
t
ic
e
n
f
o
r
c
em
e
n
t
o
f
t
h
e
in
t
en
d
ed
r
i
s
k
–
r
e
w
a
r
d
s
t
r
u
c
t
u
r
e
.
I
n
c
o
n
t
r
a
s
t
,
t
h
e
b
a
s
e
l
in
e
co
n
f
i
g
u
r
a
t
io
n
d
i
s
p
l
ay
s
w
i
d
e
r
d
i
s
p
e
r
s
io
n
,
w
i
t
h
s
ev
e
r
a
l
t
r
ad
e
s
e
x
t
en
d
in
g
i
n
to
d
ee
p
er
ad
v
er
s
e
m
o
v
e
m
e
n
t
s
b
e
f
o
r
e
c
lo
s
u
r
e.
T
h
e
t
i
g
h
t
e
r
c
l
u
s
t
e
r
in
g
o
b
s
er
v
ed
in
th
e
h
y
b
r
i
d
s
y
s
t
e
m
r
ef
l
e
c
t
s
d
i
s
c
i
p
l
i
n
ed
e
x
i
t
co
n
t
r
o
l
an
d
b
o
u
n
d
ed
d
o
w
n
s
i
d
e
ex
p
o
s
u
r
e
.
Fig
u
r
e
5
.
Pro
f
it
–
tim
e
d
is
tr
ib
u
ti
o
n
o
f
th
e
SAR
SA
–
FIS
h
y
b
r
id
f
r
am
ewo
r
k
,
s
h
o
wn
to
g
eth
er
wi
th
th
e
b
aselin
e
s
y
s
tem
o
n
a
co
m
m
o
n
r
e
f
er
en
c
e
ax
is
to
h
ig
h
lig
h
t d
if
f
e
r
en
ce
s
in
tr
ad
e
d
is
p
er
s
io
n
an
d
r
is
k
co
n
tain
m
en
t
C
o
m
p
ar
ativ
e
p
er
f
o
r
m
an
ce
m
e
tr
ics
f
o
r
th
e
s
ix
-
m
o
n
th
p
er
io
d
ar
e
s
u
m
m
ar
ized
in
T
ab
le
2
.
T
h
e
h
y
b
r
i
d
f
r
am
ewo
r
k
ac
h
iev
e
d
a
p
r
o
f
it
f
ac
to
r
o
f
1
.
3
5
an
d
a
h
ig
h
er
d
aily
Sh
ar
p
e
r
atio
r
elativ
e
to
t
h
e
b
aselin
e,
wh
ile
m
ain
tain
in
g
co
m
p
ar
a
b
le
m
ax
i
m
u
m
d
r
aw
d
o
wn
.
T
h
ese
r
esu
l
ts
in
d
icate
im
p
r
o
v
e
d
r
is
k
-
ad
j
u
s
ted
p
er
f
o
r
m
an
ce
with
o
u
t in
cr
ea
s
in
g
d
r
awd
o
wn
s
ev
er
ity
.
T
ab
le
2
.
C
o
m
p
a
r
ativ
e
p
er
f
o
r
m
an
ce
m
etr
ics o
f
th
e
b
aselin
e
(
n
o
AI
)
an
d
SAR
SA
–
FIS
h
y
b
r
id
f
r
am
ewo
r
k
o
n
GB
PU
SD
M
e
t
r
i
c
NO
AI
S
A
R
S
A
–
F
I
S
H
y
b
r
i
d
To
t
a
l
n
e
t
p
r
o
f
i
t
(USD)
10
90
P
r
o
f
i
t
f
a
c
t
o
r
1
.
0
2
1
.
3
5
M
a
x
i
m
u
m
d
r
a
w
d
o
w
n
(
%)
5
.
3
5
.
5
S
h
a
r
p
e
r
a
t
i
o
(
d
a
i
l
y
)
0
.
0
2
0
.
1
8
A
v
e
r
a
g
e
t
r
a
d
e
r
e
t
u
r
n
(
%)
0
.
0
6
0
.
5
2
W
i
n
r
a
t
e
(
%)
5
2
.
1
5
8
.
7
Ex
p
o
s
u
r
e
t
i
me
(
%)
4
2
.
5
4
7
.
2
Tr
a
d
e
c
o
u
n
t
1
7
0
1
7
6
4
.
2
.
E
x
t
ended
o
ne
-
y
ea
r
ev
a
l
ua
t
io
n
(
2
0
2
3
)
T
o
ass
ess
r
o
b
u
s
tn
ess
b
ey
o
n
d
th
e
s
ix
-
m
o
n
th
win
d
o
w,
th
e
S
AR
SA
–
FIS
f
r
am
ewo
r
k
was
b
ac
k
test
ed
o
v
er
th
e
f
u
ll
y
ea
r
o
f
2
0
2
3
.
T
h
is
p
er
io
d
in
cl
u
d
es
v
ar
y
in
g
v
o
latilit
y
r
eg
im
es
an
d
m
ac
r
o
ec
o
n
o
m
ic
c
o
n
d
itio
n
s
.
Fig
u
r
e
6
p
r
esen
ts
th
e
eq
u
ity
cu
r
v
e
f
o
r
th
e
2
0
2
3
ev
alu
atio
n
.
T
h
e
s
y
s
tem
ac
h
iev
ed
a
n
et
p
r
o
f
it
o
f
1
3
7
.
0
6
USD
with
a
p
r
o
f
it
f
ac
t
o
r
o
f
1
.
2
7
an
d
a
Sh
ar
p
e
r
atio
o
f
1
.
2
5
.
Ma
x
im
u
m
d
r
awd
o
wn
d
u
r
in
g
th
is
p
er
io
d
was
2
5
.
3
9
%
.
T
h
e
an
n
u
al
e
q
u
ity
tr
ajec
t
o
r
y
s
h
o
ws
g
r
ad
u
al
u
p
war
d
p
r
o
g
r
e
s
s
io
n
with
s
tr
u
ctu
r
ed
r
ec
o
v
er
y
p
h
ases
f
o
llo
win
g
d
r
awd
o
wn
s
,
in
d
icatin
g
s
tab
le
b
eh
av
io
r
o
v
e
r
a
lo
n
g
er
h
o
r
izo
n
.
Fig
u
r
e
6
.
On
e
-
y
ea
r
b
alan
ce
cu
r
v
e
o
f
SAR
SA
–
FIS
h
y
b
r
id
f
r
a
m
ewo
r
k
(
2
0
2
3
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
1
6
,
No
.
3
,
J
u
n
e
20
2
6
:
1
5
3
1
-
1
5
4
2
1538
Ag
g
r
eg
ate
p
er
f
o
r
m
an
ce
m
etr
i
cs
f
o
r
2
0
2
3
ar
e
s
u
m
m
ar
ized
in
T
ab
le
3
.
T
h
e
s
y
s
tem
ex
e
cu
ted
1
4
4
tr
ad
es
with
a
win
r
ate
o
f
5
6
.
2
5
%.
Av
e
r
ag
e
p
r
o
f
it
a
n
d
l
o
s
s
p
er
tr
ad
e
wer
e
7
.
9
7
US
D
an
d
−8
.
0
8
USD,
r
esp
ec
tiv
ely
,
in
d
icatin
g
s
tab
le
tr
ad
e
ex
p
ec
tan
cy
u
n
d
er
v
a
r
y
i
n
g
m
ar
k
et
co
n
d
itio
n
s
.
T
h
e
b
a
lan
ce
d
g
r
o
s
s
p
r
o
f
it
an
d
lo
s
s
v
alu
es f
u
r
th
e
r
co
n
f
ir
m
co
n
tr
o
lled
tr
a
d
e
m
a
n
ag
em
e
n
t
an
d
co
n
s
is
ten
t
ap
p
licatio
n
o
f
th
e
p
r
ed
ef
i
n
ed
r
is
k
th
r
esh
o
ld
s
.
T
ab
le
3
.
Per
f
o
r
m
an
ce
m
etr
ics o
f
SAR
SA
–
FIS
h
y
b
r
id
f
r
am
e
wo
r
k
d
u
r
in
g
o
n
e
-
y
ea
r
ev
al
u
atio
n
(
2
0
2
3
)
M
e
t
r
i
c
V
a
l
u
e
To
t
a
l
n
e
t
p
r
o
f
i
t
(USD)
1
3
7
.
0
6
G
r
o
ss
p
r
o
f
i
t
(USD)
6
4
5
.
9
0
G
r
o
ss
l
o
ss
(USD)
–
5
0
8
.
8
4
P
r
o
f
i
t
f
a
c
t
o
r
1
.
2
7
S
h
a
r
p
e
r
a
t
i
o
1
.
2
5
M
a
x
i
m
u
m
d
r
a
w
d
o
w
n
(
%)
2
5
.
3
9
To
t
a
l
t
r
a
d
e
s
1
4
4
W
i
n
r
a
t
e
(
%)
5
6
.
2
5
A
v
e
r
a
g
e
p
r
o
f
i
t
t
r
a
d
e
(USD)
7
.
9
7
A
v
e
r
a
g
e
l
o
ss
t
r
a
d
e
(USD)
–
8
.
0
8
4
.
3
.
Sens
it
iv
it
y
a
na
l
y
s
is
o
f
ex
plo
ra
t
io
n a
nd
risk
pa
ra
m
et
er
s
T
o
f
u
r
th
er
ev
alu
ate
th
e
s
tab
ilit
y
o
f
th
e
p
r
o
p
o
s
ed
ar
ch
itectu
r
e,
a
s
en
s
itiv
ity
an
al
y
s
is
was
co
n
d
u
cted
o
n
th
e
m
ain
lear
n
in
g
an
d
r
is
k
-
co
n
tr
o
l
p
a
r
am
eter
s
.
T
h
e
an
aly
s
i
s
f
o
cu
s
es
o
n
th
e
ex
p
lo
r
atio
n
r
ate
an
d
d
r
awd
o
wn
r
eset
th
r
esh
o
ld
th
at
r
e
g
u
late
ad
ap
tiv
e
ex
p
lo
r
atio
n
d
u
r
i
n
g
l
ea
r
n
in
g
.
T
h
e
in
itial
ex
p
l
o
r
atio
n
r
ate
p
a
r
am
eter
v
ar
ied
with
in
a
r
a
n
g
e
o
f
m
o
d
er
ate
v
alu
es
wh
ile
m
ain
tain
i
n
g
th
e
s
am
e
d
ec
ay
s
ch
ed
u
le,
an
d
t
h
e
d
r
awd
o
wn
r
eset
th
r
esh
o
ld
was
ad
ju
s
ted
with
in
a
b
o
u
n
d
ed
in
ter
v
al
ar
o
u
n
d
th
e
b
aselin
e
co
n
f
ig
u
r
atio
n
.
T
h
e
ex
p
er
im
e
n
tal
r
esu
lts
in
d
icate
th
at
th
e
SAR
SA
–
FIS
f
r
am
ewo
r
k
m
ain
ta
in
s
s
tab
le
p
er
f
o
r
m
an
ce
a
cr
o
s
s
th
ese
p
ar
am
eter
v
ar
iatio
n
s
.
Pro
f
it
f
ac
to
r
v
alu
es
r
em
ain
co
n
s
is
ten
tly
ab
o
v
e
th
e
b
aselin
e
co
n
f
ig
u
r
atio
n
,
wh
ile
m
ax
im
u
m
d
r
awd
o
wn
lev
els
r
em
ai
n
w
ith
in
co
n
tr
o
lled
lim
its
.
T
h
ese
o
b
s
er
v
atio
n
s
s
u
g
g
est
th
a
t
h
y
b
r
id
lea
r
n
in
g
ar
ch
itectu
r
e
is
n
o
t
h
ig
h
l
y
s
en
s
itiv
e
to
m
o
d
er
ate
p
a
r
am
eter
a
d
ju
s
tm
en
ts
.
T
h
e
ad
ap
tiv
e
ex
p
l
o
r
atio
n
m
ec
h
an
is
m
ef
f
ec
tiv
ely
r
eg
u
lates
p
o
licy
u
p
d
ates
wh
ile
m
ain
tain
in
g
b
o
u
n
d
e
d
r
is
k
ex
p
o
s
u
r
e.
Ov
er
all,
th
e
s
en
s
itiv
ity
an
aly
s
is
co
n
f
ir
m
s
th
at
th
e
p
r
o
p
o
s
ed
ar
ch
itectu
r
e
ex
h
ib
its
s
tab
le
lear
n
in
g
b
eh
av
io
r
a
n
d
r
o
b
u
s
t
p
er
f
o
r
m
an
ce
ac
r
o
s
s
d
if
f
er
en
t
p
ar
am
eter
s
ettin
g
s
.
T
h
is
s
tab
ili
ty
is
p
ar
ticu
lar
ly
im
p
o
r
tan
t
f
o
r
p
r
ac
tical
d
ep
lo
y
m
e
n
t,
wh
er
e
p
ar
am
eter
tu
n
in
g
m
a
y
v
ar
y
d
e
p
en
d
in
g
o
n
m
ar
k
et
c
o
n
d
itio
n
s
an
d
s
y
s
tem
co
n
f
i
g
u
r
atio
n
.
4
.
4
.
Ro
bu
s
t
nes
s
a
nd
co
ns
i
s
t
ency
a
na
ly
s
is
R
o
b
u
s
tn
ess
is
ev
alu
ated
b
y
co
m
p
ar
in
g
r
esu
lts
ac
r
o
s
s
n
o
n
-
o
v
er
lap
p
i
n
g
ev
al
u
atio
n
h
o
r
izo
n
s
.
I
n
b
o
t
h
th
e
s
ix
-
m
o
n
t
h
an
d
o
n
e
-
y
ea
r
t
ests
,
th
e
SAR
SA
–
FIS
h
y
b
r
id
f
r
am
ewo
r
k
d
em
o
n
s
tr
ates
p
er
s
is
ten
t
p
r
o
f
itab
ilit
y
,
b
o
u
n
d
ed
d
r
awd
o
wn
b
eh
av
io
r
,
an
d
im
p
r
o
v
ed
Sh
ar
p
e
r
atio
s
r
elativ
e
to
th
e
b
aselin
e
c
o
n
f
ig
u
r
atio
n
.
T
h
e
eq
u
ity
cu
r
v
es
in
Fig
u
r
es
4
a
n
d
6
s
h
o
w
s
u
s
tain
ed
u
p
war
d
tr
ajec
to
r
ies
r
ath
er
th
an
is
o
lated
p
e
r
f
o
r
m
an
ce
s
p
ik
es
o
r
s
h
o
r
t
-
liv
ed
g
ain
s
.
T
h
e
clu
s
ter
in
g
o
f
tr
a
d
e
o
u
tco
m
es
o
b
s
er
v
e
d
in
Fig
u
r
e
5
c
o
n
f
ir
m
s
co
n
s
is
t
en
t
en
f
o
r
ce
m
en
t
o
f
tak
e
-
p
r
o
f
it
an
d
cu
t
-
l
o
s
s
co
n
s
tr
ain
ts
,
in
d
icatin
g
th
at
ad
ap
tiv
e
lear
n
in
g
d
o
es
n
o
t
lead
to
d
estab
ilizin
g
ex
p
o
s
u
r
e.
T
h
e
p
er
s
is
ten
ce
o
f
p
o
s
itiv
e
p
r
o
f
it
f
ac
t
o
r
s
ac
r
o
s
s
d
if
f
e
r
en
t
tim
e
h
o
r
izo
n
s
s
u
g
g
ests
th
at
p
er
f
o
r
m
an
c
e
im
p
r
o
v
em
e
n
ts
ar
e
n
o
t
lim
ited
to
a
s
p
ec
if
ic
m
ar
k
et
p
h
ase.
Ov
er
all,
th
e
r
esu
lts
d
em
o
n
s
tr
ate
th
at
th
e
r
is
k
-
co
n
s
tr
ain
ed
SAR
SA
–
FIS
h
y
b
r
id
ar
ch
itectu
r
e
im
p
r
o
v
es
r
is
k
–
r
ewa
r
d
ef
f
icien
cy
wh
ile
m
ain
t
ain
in
g
d
is
cip
lin
ed
ex
p
o
s
u
r
e
c
o
n
tr
o
l.
T
h
e
in
te
g
r
atio
n
o
f
a
d
ap
tiv
e
RL
,
s
tr
u
ct
u
r
ed
f
u
zz
y
d
ec
is
io
n
m
ap
p
i
n
g
,
an
d
d
r
awd
o
wn
-
r
eg
u
lated
e
x
p
lo
r
atio
n
c
o
n
tr
ib
u
te
to
s
tab
le
a
n
d
r
ep
r
o
d
u
cib
l
e
p
er
f
o
r
m
an
ce
u
n
d
er
v
ar
y
i
n
g
m
ar
k
et
co
n
d
itio
n
s
.
B
ey
o
n
d
th
ese
em
p
ir
ical
o
b
s
er
v
atio
n
s
,
th
e
s
tab
ilit
y
ch
ar
ac
ter
is
tics
o
b
s
er
v
ed
in
th
e
ex
p
er
i
m
en
tal
r
esu
lts
also
p
r
o
v
id
e
in
s
ig
h
t in
to
t
h
e
s
u
s
tain
ab
ilit
y
im
p
licatio
n
s
o
f
t
h
e
p
r
o
p
o
s
ed
d
ec
is
io
n
ar
ch
itectu
r
e.
4.
5
.
Su
s
t
a
ina
bil
it
y
im
pli
ca
t
i
o
ns
T
h
e
em
p
ir
ical
r
esu
lts
p
r
esen
ted
in
th
e
p
r
ev
i
o
u
s
s
u
b
s
ec
tio
n
s
p
r
o
v
id
e
in
d
icativ
e
ev
id
en
ce
th
at
th
e
p
r
o
p
o
s
ed
SAR
SA
–
FIS
h
y
b
r
id
f
r
am
ewo
r
k
co
n
tr
ib
u
tes
to
s
u
s
tain
ab
le
tr
ad
in
g
b
e
h
av
io
r
.
I
n
th
e
co
n
tex
t
o
f
alg
o
r
ith
m
ic
tr
a
d
in
g
,
s
u
s
tain
ab
ilit
y
r
ef
er
s
to
th
e
ab
ilit
y
o
f
a
d
e
cisi
o
n
s
y
s
tem
to
m
ain
tain
c
o
n
s
is
ten
t
p
r
o
f
itab
ilit
y
wh
ile
p
r
eser
v
in
g
d
is
cip
lin
ed
r
is
k
co
n
tr
o
l
an
d
s
tab
le
o
p
er
ati
o
n
al
b
eh
a
v
io
r
ac
r
o
s
s
d
if
f
er
en
t
m
ar
k
et
co
n
d
itio
n
s
.
First,
th
e
p
r
o
f
itab
ilit
y
o
u
tco
m
es
o
b
s
er
v
ed
ac
r
o
s
s
b
o
th
e
v
alu
atio
n
h
o
r
izo
n
s
in
d
icate
p
er
s
is
ten
t
p
o
s
itiv
e
p
er
f
o
r
m
an
ce
.
Du
r
i
n
g
th
e
s
ix
-
m
o
n
th
2
0
2
5
e
v
alu
atio
n
,
th
e
S
AR
SA
–
FIS
h
y
b
r
id
f
r
am
ewo
r
k
ac
h
iev
ed
a
n
et
p
r
o
f
it
o
f
ap
p
r
o
x
im
ately
9
0
USD
with
a
p
r
o
f
it
f
ac
to
r
o
f
1
.
3
5
.
I
n
th
e
ex
ten
d
ed
o
n
e
-
y
ea
r
2
0
2
3
ev
a
lu
atio
n
,
th
e
s
y
s
tem
p
r
o
d
u
ce
d
a
n
et
p
r
o
f
it
o
f
1
3
7
USD
with
a
p
r
o
f
it
f
ac
to
r
o
f
1
.
2
7
.
Alth
o
u
g
h
th
e
ab
s
o
lu
te
p
r
o
f
it
v
alu
es
r
em
ain
m
o
d
er
ate,
th
e
co
n
s
is
ten
cy
o
f
p
r
o
f
itab
ilit
y
ac
r
o
s
s
n
o
n
-
o
v
er
lap
p
in
g
p
er
io
d
s
s
u
g
g
ests
th
at
th
e
p
er
f
o
r
m
an
ce
is
n
o
t
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
A
r
is
k
-
co
n
s
tr
a
in
ed
S
A
R
S
A
–
F
I
S
h
yb
r
id
d
ec
is
io
n
a
r
ch
itectu
r
e
…
(
Jo
n
i F
a
t
)
1539
lim
ited
to
a
s
in
g
le
m
ar
k
et
p
h
ase.
Similar
o
b
s
er
v
atio
n
s
h
av
e
b
ee
n
r
e
p
o
r
te
d
in
R
L
s
tu
d
ies
s
h
o
win
g
th
at
ad
ap
tiv
e
tr
ad
in
g
a
g
en
ts
ca
n
im
p
r
o
v
e
f
i
n
an
cial
d
ec
is
io
n
-
m
a
k
in
g
p
er
f
o
r
m
a
n
ce
r
elativ
e
to
co
n
s
er
v
ativ
e
r
u
le
-
b
ased
b
en
ch
m
ar
k
s
[
1
]
,
[
4
]
.
Seco
n
d
,
th
e
r
is
k
–
r
ewa
r
d
ch
ar
ac
ter
is
tics
o
f
th
e
f
r
am
ewo
r
k
f
u
r
th
er
s
u
p
p
o
r
t
th
e
s
u
s
tain
ab
ilit
y
in
ter
p
r
etatio
n
.
T
h
e
s
y
s
tem
m
ain
tain
ed
b
o
u
n
d
ed
m
ax
im
u
m
d
r
awd
o
wn
s
o
f
ap
p
r
o
x
im
ately
5
.
5
%
d
u
r
i
n
g
th
e
2
0
2
5
ev
alu
atio
n
an
d
ab
o
u
t
2
5
.
4
%
d
u
r
in
g
th
e
lo
n
g
er
2
0
2
3
ev
alu
ati
o
n
.
At
th
e
s
am
e
tim
e,
th
e
h
y
b
r
i
d
ar
ch
itectu
r
e
ac
h
iev
e
d
im
p
r
o
v
e
d
r
is
k
-
ad
ju
s
ted
p
er
f
o
r
m
a
n
ce
,
r
ef
lecte
d
b
y
Sh
ar
p
e
r
atio
s
o
f
0
.
1
8
an
d
1
.
2
5
f
o
r
th
e
r
esp
ec
tiv
e
p
er
io
d
s
.
T
r
ad
e
-
le
v
e
l
b
eh
av
io
r
in
d
icate
s
th
at
f
av
o
r
ab
le
p
r
ice
m
o
v
em
en
ts
ar
e
ca
p
t
u
r
ed
wh
ile
ad
v
er
s
e
m
o
v
em
en
ts
r
em
ain
b
o
u
n
d
ed
b
y
p
r
e
d
ef
in
ed
r
is
k
th
r
esh
o
l
d
s
.
Su
ch
b
alan
ce
d
b
eh
av
io
r
is
co
n
s
is
ten
t
with
p
r
ev
io
u
s
s
tu
d
ies
o
n
f
u
zz
y
–
R
L
h
y
b
r
id
s
y
s
tem
s
th
at
em
p
h
asize
r
o
b
u
s
tn
ess
an
d
s
tab
ilit
y
u
n
d
e
r
u
n
ce
r
tai
n
en
v
ir
o
n
m
en
ts
[
3
]
,
[
2
0
]
.
T
h
ir
d
,
th
e
o
p
e
r
atio
n
al
c
h
ar
ac
ter
is
tics
o
f
th
e
tr
a
d
in
g
ag
en
t
also
i
n
d
icate
s
tab
le
s
y
s
tem
b
eh
av
io
r
.
Mo
s
t
tr
ad
es
f
o
llo
w
a
s
h
o
r
t
in
tr
ad
a
y
h
o
l
d
in
g
p
atter
n
,
s
u
g
g
esti
n
g
c
o
n
tr
o
lled
ex
p
o
s
u
r
e
an
d
d
is
cip
lin
ed
tu
r
n
o
v
e
r
[
2
1
]
,
[
2
2
]
.
T
h
is
o
p
er
atio
n
al
s
tr
u
ctu
r
e
r
ed
u
ce
s
p
r
o
lo
n
g
ed
m
ar
k
et
ex
p
o
s
u
r
e
an
d
a
llo
ws
th
e
s
y
s
tem
to
ad
ap
t
m
o
r
e
ef
f
ec
tiv
ely
to
ch
an
g
in
g
v
o
latilit
y
r
eg
im
es.
Fro
m
a
s
tr
ateg
ic
p
er
s
p
ec
tiv
e,
s
u
ch
d
is
cip
lin
ed
b
eh
av
io
r
ca
n
b
e
in
ter
p
r
eted
with
in
th
e
co
n
tex
t
o
f
r
ep
ea
ted
s
tr
ateg
ic
in
ter
ac
tio
n
s
in
f
in
an
cial
m
ar
k
ets,
wh
er
e
ag
en
ts
m
u
s
t
m
ain
tain
s
tab
le
s
tr
ateg
i
es
u
n
d
er
v
ar
y
i
n
g
co
m
p
etitiv
e
co
n
d
itio
n
s
[
1
2
]
,
[
1
3
]
.
Fin
ally
,
th
e
in
teg
r
atio
n
o
f
ex
p
licit
r
is
k
co
n
s
tr
ain
ts
s
tr
en
g
th
en
s
th
e
s
u
s
tain
ab
ilit
y
p
er
s
p
ec
tiv
e
o
f
th
e
p
r
o
p
o
s
ed
ar
ch
it
ec
tu
r
e.
Me
ch
an
is
m
s
s
u
ch
as
ca
p
p
ed
d
r
awd
o
wn
s
,
p
r
ed
ef
in
ed
p
r
o
f
it
a
n
d
lo
s
s
th
r
esh
o
ld
s
,
an
d
c
o
n
f
ir
m
atio
n
f
ilter
s
f
u
n
ctio
n
as
p
r
ac
tical
r
eg
u
lato
r
s
th
at
p
r
e
v
e
n
t
d
estab
ilizin
g
tr
ad
in
g
b
e
h
av
io
r
[
2
3
]
.
T
h
ese
co
n
s
tr
ain
ts
ca
n
b
e
in
ter
p
r
eted
as
p
ay
o
f
f
-
r
eg
u
lar
izin
g
m
ec
h
an
is
m
s
th
at
g
u
id
e
th
e
lear
n
in
g
ag
en
t
to
war
d
s
tab
le
d
ec
is
io
n
p
o
licies.
Similar
id
ea
s
h
av
e
b
ee
n
d
is
cu
s
s
ed
in
f
in
an
cial
s
tab
ilit
y
r
esear
ch
,
w
h
er
e
b
o
u
n
d
e
d
d
ec
is
io
n
r
u
les
h
elp
m
ain
tain
s
y
s
tem
ic
r
o
b
u
s
tn
ess
u
n
d
e
r
u
n
ce
r
tain
ty
[
1
4
]
,
[
1
5
]
.
Fro
m
a
r
esp
o
n
s
ib
le
AI
p
er
s
p
ec
tiv
e,
th
e
p
r
o
p
o
s
ed
f
r
am
e
wo
r
k
also
s
u
p
p
o
r
ts
tr
an
s
p
ar
en
cy
an
d
co
n
tr
o
lled
d
ep
l
o
y
m
en
t
[
2
4
]
.
T
h
e
u
s
e
o
f
a
FIS
en
h
a
n
ce
s
in
ter
p
r
etab
ilit
y
o
f
t
h
e
d
ec
is
io
n
p
r
o
ce
s
s
,
wh
ile
th
e
R
L
co
m
p
o
n
en
t
en
ab
les
ad
ap
tiv
e
r
esp
o
n
s
es
to
ch
an
g
in
g
m
a
r
k
e
t
d
y
n
am
ics.
T
h
ese
d
esig
n
p
r
i
n
cip
les
alig
n
with
r
ec
en
t
d
is
cu
s
s
io
n
s
o
n
r
esp
o
n
s
ib
le
an
d
s
u
s
tain
ab
le
AI
d
e
p
lo
y
m
en
t
in
f
in
a
n
cial
s
y
s
tem
s
[
2
5
]
–
[
2
8
]
.
Ov
er
all,
th
e
co
m
b
in
atio
n
o
f
co
n
s
is
ten
t
p
r
o
f
itab
ilit
y
,
b
o
u
n
d
ed
r
is
k
ex
p
o
s
u
r
e,
an
d
s
tab
le
o
p
e
r
atio
n
al
b
e
h
av
io
r
s
u
g
g
ests
th
at
th
e
SAR
SA
–
FIS
h
y
b
r
id
f
r
am
ewo
r
k
p
r
o
v
id
es
a
s
u
s
tain
ab
le
ap
p
r
o
ac
h
to
alg
o
r
ith
m
ic
tr
ad
in
g
u
n
d
er
v
ar
y
in
g
m
ar
k
et
co
n
d
itio
n
s
.
4
.
6
.
L
im
it
a
t
io
ns
a
nd
deplo
y
m
ent
co
ns
idera
t
io
ns
Alth
o
u
g
h
th
e
ex
p
er
im
en
tal
ev
alu
atio
n
d
em
o
n
s
tr
ates
s
tab
le
an
d
p
r
o
f
itab
le
b
e
h
av
i
o
r
,
s
ev
er
al
lim
itatio
n
s
s
h
o
u
ld
b
e
ac
k
n
o
wled
g
ed
.
First,
ex
p
e
r
im
en
tal
v
al
id
atio
n
is
c
o
n
d
u
cted
u
s
in
g
h
is
to
r
ical
b
ac
k
test
in
g
r
ath
er
th
a
n
r
ea
l
-
tim
e
tr
ad
in
g
en
v
ir
o
n
m
en
ts
.
L
iv
e
m
ar
k
et
d
ep
lo
y
m
en
t
m
ay
in
tr
o
d
u
ce
a
d
d
itio
n
al
o
p
er
atio
n
al
f
ac
to
r
s
s
u
ch
as
ex
ec
u
tio
n
laten
cy
,
s
lip
p
ag
e,
an
d
liq
u
id
ity
c
o
n
s
tr
ain
ts
th
at
ca
n
n
o
t
b
e
f
u
ll
y
ca
p
tu
r
ed
th
r
o
u
g
h
h
is
to
r
ical
s
im
u
latio
n
s
.
T
h
ese
f
ac
to
r
s
m
ay
in
f
lu
e
n
ce
th
e
r
ea
li
ze
d
p
e
r
f
o
r
m
an
ce
o
f
th
e
tr
ad
in
g
ag
e
n
t
in
p
r
ac
tical
s
ettin
g
s
.
Seco
n
d
,
th
e
p
r
o
p
o
s
ed
ar
ch
itectu
r
e
r
elies
o
n
a
co
m
p
ac
t
s
tate
r
ep
r
esen
tatio
n
co
n
s
is
tin
g
o
f
th
r
ee
s
tates
d
er
iv
ed
f
r
o
m
p
r
ice
d
ev
iatio
n
s
r
elativ
e
to
th
e
E
MA
in
d
icato
r
.
W
h
ile
th
is
s
im
p
lifie
d
s
tr
u
ctu
r
e
im
p
r
o
v
es
co
m
p
u
tatio
n
al
ef
f
icien
cy
an
d
i
n
ter
p
r
etab
ilit
y
,
it
m
ay
lim
it
s
ca
lab
ilit
y
wh
en
ap
p
lied
to
m
o
r
e
co
m
p
lex
d
ec
is
io
n
en
v
ir
o
n
m
en
ts
in
v
o
lv
in
g
h
ig
h
-
d
im
en
s
io
n
al
f
ea
tu
r
e
s
p
ac
es
o
r
m
u
lti
-
ass
et
p
o
r
tf
o
lio
s
.
E
x
ten
d
in
g
th
e
f
r
am
ew
o
r
k
to
lar
g
er
s
tate
s
p
ac
es
o
r
m
u
ltip
le
ass
et
s
m
ay
r
eq
u
ir
e
m
o
r
e
ad
v
an
ce
d
lear
n
in
g
m
ec
h
a
n
is
m
s
o
r
h
ier
ar
ch
ical
ar
ch
itectu
r
e
.
T
h
ir
d
,
th
e
f
u
zz
y
in
f
er
e
n
ce
lay
er
em
p
lo
y
s
a
p
r
ed
ef
i
n
ed
r
u
le
s
tr
u
ctu
r
e
d
e
s
ig
n
ed
to
m
ai
n
tain
in
ter
p
r
etab
ilit
y
an
d
d
ec
is
io
n
t
r
an
s
p
ar
en
cy
.
Ho
wev
er
,
m
an
u
al
r
u
le
d
esig
n
m
a
y
b
ec
o
m
e
in
cr
ea
s
in
g
ly
co
m
p
lex
as
th
e
d
im
e
n
s
io
n
ality
o
f
th
e
i
n
p
u
t
s
p
ac
e
g
r
o
ws.
Au
to
m
ated
r
u
le
ad
ap
tatio
n
o
r
r
u
le
-
lear
n
in
g
m
e
ch
an
is
m
s
m
ay
th
er
ef
o
r
e
b
e
r
eq
u
ir
ed
wh
e
n
ap
p
ly
in
g
th
e
a
r
ch
itectu
r
e
to
m
o
r
e
co
m
p
lex
d
o
m
ain
s
.
Desp
ite
t
h
ese
lim
itatio
n
s
,
th
e
p
r
o
p
o
s
ed
ar
ch
itectu
r
e
p
r
o
v
id
es
a
p
r
ac
tical
f
o
u
n
d
atio
n
f
o
r
d
ev
elo
p
in
g
in
te
r
p
r
etab
le
r
ei
n
f
o
r
ce
m
e
n
t
lear
n
in
g
s
y
s
tem
s
with
ex
p
licit
r
is
k
co
n
s
tr
ain
ts
.
Fu
tu
r
e
r
esear
ch
w
ill
in
v
esti
g
ate
ex
ten
s
io
n
s
to
m
u
lti
-
ass
et
tr
ad
in
g
en
v
ir
o
n
m
en
ts
,
in
teg
r
atio
n
with
d
ee
p
r
ei
n
f
o
r
ce
m
en
t le
ar
n
i
n
g
m
o
d
els,
an
d
a
u
to
m
ated
f
u
zz
y
r
u
le
o
p
tim
izatio
n
t
o
im
p
r
o
v
e
s
ca
lab
ilit
y
an
d
d
e
p
lo
y
m
en
t c
ap
a
b
ilit
y
in
r
ea
l
-
wo
r
ld
f
in
an
cial
s
y
s
tem
s
.
5.
CO
NCLU
SI
O
N
T
h
is
s
tu
d
y
p
r
o
p
o
s
ed
a
n
d
ex
p
er
im
en
tally
ev
alu
ated
a
r
is
k
-
c
o
n
s
tr
ain
ed
SAR
SA
–
FIS
h
y
b
r
i
d
d
ec
is
io
n
ar
ch
itectu
r
e
f
o
r
alg
o
r
ith
m
ic
t
r
ad
in
g
.
T
h
e
f
r
am
ewo
r
k
in
teg
r
ates
r
ein
f
o
r
ce
m
en
t
lear
n
in
g
with
a
Su
g
en
o
-
ty
p
e
f
u
zz
y
in
f
e
r
en
ce
s
y
s
tem
an
d
e
x
p
licit
r
is
k
-
co
n
tr
o
l
m
ec
h
an
is
m
s
with
in
a
u
n
if
ied
ex
ec
u
tio
n
ag
en
t.
Ar
ch
itectu
r
e
co
m
b
in
es
th
e
ad
ap
ta
b
ilit
y
o
f
SAR
SA
lear
n
in
g
with
th
e
in
ter
p
r
etab
ilit
y
o
f
f
u
zz
y
d
ec
is
io
n
r
u
les,
wh
ile
ad
ap
tiv
e
ex
p
lo
r
atio
n
c
o
n
tr
o
l
a
n
d
d
r
a
wd
o
wn
co
n
s
tr
ain
ts
r
eg
u
late
s
y
s
tem
s
tab
ilit
y
d
u
r
in
g
lear
n
in
g
.
B
ac
k
test
in
g
ex
p
er
im
en
ts
o
n
t
h
e
GB
PUS
D
cu
r
r
en
cy
p
air
in
d
icate
th
at
th
e
p
r
o
p
o
s
ed
f
r
am
ewo
r
k
ac
h
iev
es
im
p
r
o
v
e
d
p
er
f
o
r
m
an
ce
c
o
m
p
a
r
ed
with
a
r
u
le
-
b
ased
b
aselin
e
co
n
f
i
g
u
r
atio
n
ac
r
o
s
s
b
o
th
s
h
o
r
t
-
t
er
m
an
d
ex
te
n
d
ed
ev
alu
atio
n
h
o
r
izo
n
s
.
Du
r
in
g
th
e
s
ix
-
m
o
n
th
o
u
t
-
of
-
s
am
p
le
e
v
alu
atio
n
in
2
0
2
5
,
th
e
h
y
b
r
id
s
y
s
tem
g
en
er
ated
a
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
1
6
,
No
.
3
,
J
u
n
e
20
2
6
:
1
5
3
1
-
1
5
4
2
1540
n
et
p
r
o
f
it
o
f
a
p
p
r
o
x
im
ately
9
0
USD
with
a
p
r
o
f
it
f
ac
to
r
o
f
1
.
3
5
.
I
n
th
e
o
n
e
-
y
ea
r
ev
al
u
atio
n
o
n
2
0
2
3
d
ata,
t
h
e
s
y
s
tem
ac
h
iev
ed
a
n
et
p
r
o
f
it
o
f
1
3
7
USD
with
a
p
r
o
f
it
f
ac
to
r
o
f
1
.
2
7
a
n
d
a
Sh
ar
p
e
r
atio
o
f
1
.
2
5
.
T
h
e
r
esu
lts
also
s
h
o
w
d
is
cip
lin
ed
d
r
awd
o
wn
b
eh
av
io
r
an
d
c
o
n
s
is
ten
t
en
f
o
r
ce
m
e
n
t
o
f
p
r
ed
ef
in
e
d
r
is
k
th
r
esh
o
ld
s
.
T
r
ad
e
-
lev
el
o
u
tco
m
es
d
em
o
n
s
tr
ate
th
at
th
e
h
y
b
r
id
f
r
am
ewo
r
k
m
ain
tain
s
b
o
u
n
d
e
d
lo
s
s
ex
p
o
s
u
r
e
wh
ile
ca
p
tu
r
in
g
f
av
o
r
a
b
le
p
r
ice
m
o
v
em
en
ts
m
o
r
e
ef
f
ec
tiv
ely
th
an
t
h
e
b
aselin
e
co
n
f
i
g
u
r
atio
n
.
T
h
e
r
esu
lts
f
u
r
th
er
in
d
icate
th
at
ad
ap
tiv
e
lear
n
in
g
,
in
ter
p
r
etab
le
d
ec
is
io
n
r
u
les,
an
d
ex
p
licit
r
is
k
co
n
s
tr
ain
ts
ca
n
b
e
co
m
b
in
ed
with
in
a
lig
h
tweig
h
t
tr
ad
in
g
a
r
ch
itectu
r
e
with
o
u
t
in
tr
o
d
u
cin
g
u
n
s
tab
le
b
eh
av
io
r
.
T
h
e
SAR
SA
co
m
p
o
n
en
t
en
a
b
les
co
n
tin
u
o
u
s
p
o
licy
a
d
ap
t
atio
n
,
wh
ile
th
e
f
u
zz
y
in
f
er
e
n
ce
lay
er
p
r
o
v
i
d
es
s
tr
u
ctu
r
ed
d
ec
is
io
n
m
a
p
p
in
g
th
at
im
p
r
o
v
es
tr
an
s
p
ar
en
cy
a
n
d
o
p
er
atio
n
al
s
tab
ilit
y
.
T
o
g
eth
er
with
d
r
awd
o
wn
-
r
eg
u
lated
ex
p
l
o
r
atio
n
co
n
tr
o
l
,
th
ese
m
ec
h
an
is
m
s
s
u
p
p
o
r
t
co
n
s
is
ten
t
p
er
f
o
r
m
an
ce
ac
r
o
s
s
d
if
f
er
en
t
m
ar
k
et
co
n
d
itio
n
s
.
Ov
e
r
all,
th
e
f
i
n
d
in
g
s
d
em
o
n
s
tr
ate
th
at
a
co
m
p
ac
t
SAR
S
A
–
FIS
h
y
b
r
id
ar
c
h
itec
tu
r
e
ca
n
p
r
o
v
id
e
a
p
r
ac
tical
ap
p
r
o
ac
h
f
o
r
d
e
v
e
lo
p
in
g
ad
ap
tiv
e
an
d
r
is
k
-
aw
ar
e
tr
ad
in
g
a
g
en
ts
.
T
h
e
p
r
o
p
o
s
ed
f
r
am
ewo
r
k
co
n
tr
ib
u
tes
to
th
e
d
esig
n
o
f
in
tellig
en
t
d
ec
is
io
n
s
y
s
tem
s
th
at
b
alan
ce
lear
n
in
g
ca
p
ab
ilit
y
,
in
ter
p
r
etab
ilit
y
,
a
n
d
d
is
cip
lin
ed
r
is
k
m
an
ag
em
en
t
.
Fu
tu
r
e
wo
r
k
will
ex
ten
d
th
e
ar
ch
itectu
r
e
to
m
u
lti
-
a
s
s
et
en
v
ir
o
n
m
en
ts
,
in
v
esti
g
ate
alter
n
ativ
e
r
ei
n
f
o
r
ce
m
en
t
lear
n
i
n
g
v
ar
ian
ts
,
an
d
f
u
r
th
er
ex
p
l
o
r
e
a
d
ap
tiv
e
m
ec
h
an
is
m
s
f
o
r
im
p
r
o
v
in
g
r
o
b
u
s
tn
ess
in
h
ig
h
l
y
v
o
latile
f
in
an
cial
m
ar
k
ets.
ACK
NO
WL
E
DG
M
E
N
T
S
T
h
e
au
th
o
r
s
g
r
atef
u
lly
ac
k
n
o
wled
g
e
th
e
s
u
p
p
o
r
t
o
f
th
e
Do
cto
r
al
Pro
g
r
am
in
I
n
d
u
s
tr
ial
E
n
g
in
ee
r
in
g
,
Un
iv
er
s
itas
T
r
is
ak
ti,
J
ak
ar
ta,
I
n
d
o
n
esia,
wh
er
e
th
is
r
esear
c
h
was
co
n
d
u
cte
d
.
T
h
e
au
th
o
r
also
ac
k
n
o
wled
g
es
th
e
E
lectr
ical
E
n
g
in
ee
r
in
g
Pro
g
r
am
,
Un
iv
e
r
s
itas
T
ar
u
m
an
ag
ar
a,
J
ak
ar
ta,
I
n
d
o
n
esia,
f
o
r
ac
ad
em
ic
an
d
in
s
titu
tio
n
al
s
u
p
p
o
r
t.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
T
h
is
r
esear
ch
was
s
u
p
p
o
r
te
d
b
y
th
e
I
n
s
titu
te
f
o
r
R
esear
ch
an
d
C
o
m
m
u
n
ity
Ser
v
ic
e
(
L
PP
M)
,
Un
iv
er
s
itas
T
ar
u
m
an
ag
ar
a
,
J
ak
ar
ta,
I
n
d
o
n
esia.
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
T
h
is
jo
u
r
n
al
u
s
es
th
e
C
o
n
tr
ib
u
to
r
R
o
les
T
ax
o
n
o
m
y
(
C
R
ed
iT)
to
r
ec
o
g
n
ize
in
d
iv
id
u
al
au
th
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
th
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
llab
o
r
atio
n
.
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
J
o
n
i Fat
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Par
wad
i M
o
en
g
in
✓
✓
✓
✓
✓
Pu
d
ji Astu
ti
✓
✓
✓
✓
✓
Sally
C
ah
y
ati
✓
✓
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
T
h
e
au
th
o
r
s
d
ec
lar
e
th
at
th
e
r
e
is
n
o
co
n
f
lict o
f
in
ter
est r
eg
ar
d
in
g
th
e
p
u
b
licatio
n
o
f
th
is
p
a
p
er
.
I
NF
O
RM
E
D
CO
NS
E
N
T
No
t a
p
p
licab
le.
T
h
is
s
tu
d
y
d
o
e
s
n
o
t in
v
o
lv
e
h
u
m
a
n
p
a
r
ticip
an
ts
o
r
p
er
s
o
n
al
d
ata.
E
T
H
I
CAL AP
P
RO
V
AL
No
t
ap
p
licab
le.
T
h
is
s
tu
d
y
d
o
es
n
o
t
in
v
o
lv
e
h
u
m
an
p
ar
tic
ip
an
ts
,
an
im
als,
o
r
p
er
s
o
n
al
i
d
en
tifia
b
le
d
ata.
Evaluation Warning : The document was created with Spire.PDF for Python.