T
E
L
K
O
M
NIKA
T
elec
o
mm
un
ica
t
io
n Co
m
pu
t
i
ng
E
lect
ro
nics
a
nd
Co
ntr
o
l
Vo
l.
24
,
No
.
4
,
A
u
g
u
s
t
20
26
,
p
p
.
1
2
6
7
~
1
2
7
7
I
SS
N:
1
6
9
3
-
6
9
3
0
,
DOI
: 1
0
.
1
2
9
2
8
/
T
E
L
KOM
NI
K
A
.
v
24
i
4
.
27479
1267
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//telko
mn
ika
.
u
a
d
.
a
c.
i
d
Ada
ptive
t
ra
ding
sy
ste
m
for sus
tain
a
ble f
o
rex
m
a
r
k
e
t
s
J
o
ni F
a
t
1
,2
,
P
a
r
w
a
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 T
r
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 T
a
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
T
r
i
sak
t
i
,
Ja
k
a
r
t
a
,
I
n
d
o
n
e
si
a
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Au
g
16
,
2025
R
ev
i
s
ed
Mar
30
,
2
0
2
6
A
cc
ep
ted
Ma
y
25
,
2026
T
h
is
stu
d
y
p
re
se
n
ts
a
su
sta
in
a
b
le
a
n
d
e
th
ica
ll
y
a
li
g
n
e
d
a
lg
o
rit
h
m
ic
trad
in
g
s
y
ste
m
f
o
r
th
e
Eu
ro
/U
n
it
e
d
S
tate
s
Do
ll
a
r
(
EURUSD
)
c
u
rre
n
c
y
p
a
ir,
in
teg
ra
ti
n
g
re
in
f
o
rc
e
m
e
n
t
lea
rn
in
g
(RL
)
w
it
h
a
S
u
g
e
n
o
-
ty
p
e
f
u
z
z
y
in
f
e
re
n
c
e
m
e
c
h
a
n
is
m
.
T
h
e
f
r
a
m
e
w
o
rk
e
m
p
h
a
siz
e
s
re
sp
o
n
sib
le
A
I
p
rin
c
ip
les
b
y
c
o
m
b
in
in
g
a
d
a
p
tab
i
li
ty
a
n
d
in
t
e
rp
re
tab
il
it
y
to
su
p
p
o
r
t
tran
s
p
a
re
n
t
a
n
d
e
x
p
lain
a
b
le
f
in
a
n
c
ial
d
e
c
isio
n
-
m
a
k
in
g
.
Histo
rica
l
EURUSD
M
1
5
d
a
ta
f
ro
m
2
0
2
0
to
2
0
2
3
w
e
re
u
se
d
f
o
r
tra
in
in
g
,
w
h
il
e
2
0
2
4
d
a
ta
se
rv
e
d
fo
r
o
u
t
-
of
-
sa
m
p
le
tes
ti
n
g
.
T
h
e
s
y
ste
m
e
m
p
lo
y
s
EM
A
5
0
-
b
a
se
d
sta
te
c
la
ss
if
ic
a
ti
o
n
,
tab
u
lar
sta
te
–
a
c
ti
o
n
–
re
w
a
rd
–
sta
te
–
a
c
ti
o
n
o
r
S
A
RS
A
le
a
rn
in
g
,
a
n
d
a
f
u
z
z
y
lo
g
ic
lay
e
r
c
o
m
p
risin
g
2
7
e
x
p
e
rt
-
d
e
f
in
e
d
ru
les
.
Du
ri
n
g
b
a
c
k
tes
ti
n
g
,
th
e
a
g
e
n
t
e
x
e
c
u
ted
7
8
5
tr
a
d
e
s,
a
c
h
iev
in
g
a
n
e
t
p
ro
f
it
o
f
USD
6
1
.
8
5
,
a
p
r
o
f
it
f
a
c
to
r
o
f
1
.
0
4
,
a
n
d
a
b
a
lan
c
e
d
w
in
–
lo
ss
ra
ti
o
.
Risk
-
a
d
ju
ste
d
a
n
a
ly
sis sh
o
we
d
m
o
d
e
ra
te
re
sili
e
n
c
e
(
s
h
a
rp
e
ra
ti
o
=
0
.
5
3
)
a
n
d
a
m
a
x
i
m
u
m
d
ra
w
d
o
w
n
o
f
5
9
.
7
4
%
.
T
h
e
m
o
d
e
l
d
e
m
o
n
stra
ted
stro
n
g
e
q
u
it
y
sta
b
il
it
y
(ES
I
=
0
.
9
6
7
2
)
a
n
d
se
n
siti
v
it
y
to
m
a
c
ro
e
c
o
n
o
m
ic
e
v
e
n
ts
id
e
n
ti
f
ied
t
h
ro
u
g
h
c
u
m
u
lativ
e
su
m
(
CUSUM
)
a
n
a
ly
sis.
W
h
il
e
th
e
s
y
ste
m
m
a
in
tain
e
d
c
a
p
it
a
l
p
re
se
rv
a
ti
o
n
a
n
d
in
terp
re
tab
il
it
y
,
re
sp
o
n
siv
e
n
e
ss
u
n
d
e
r
v
o
latil
e
c
o
n
d
it
io
n
s
re
q
u
ires
im
p
ro
v
e
m
e
n
t.
F
u
tu
re
w
o
rk
w
il
l
fo
c
u
s
o
n
a
d
a
p
t
iv
e
e
x
it
lo
g
ic,
v
o
lati
li
ty
-
a
wa
re
re
wa
rd
m
e
c
h
a
n
is
m
s,
a
n
d
re
g
im
e
-
se
n
siti
v
e
p
o
l
icy
o
p
ti
m
iza
ti
o
n
.
T
h
is
st
u
d
y
c
o
n
tri
b
u
tes
to
a
d
v
a
n
c
in
g
su
sta
i
n
a
b
le,
tran
s
p
a
re
n
t,
a
n
d
risk
-
a
w
a
re
a
rti
f
icia
l
in
telli
g
e
n
c
e
(
AI
)
f
r
a
m
e
w
o
r
k
s in
a
lg
o
rit
h
m
ic t
ra
d
in
g
.
K
ey
w
o
r
d
s
:
A
d
ap
tiv
e
tr
ad
i
n
g
F
u
zz
y
lo
g
ic
R
ein
f
o
r
ce
m
e
n
t le
ar
n
in
g
R
esp
o
n
s
ib
le
ar
tif
icia
l
in
telli
g
e
n
ce
Su
s
tain
ab
il
it
y
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
:
P
ar
w
ad
i M
o
en
g
i
n
Dep
ar
t
m
en
t o
f
I
n
d
u
s
tr
ial
E
n
g
i
n
ee
r
in
g
,
Un
iv
er
s
itas
T
r
is
ak
ti
J
ak
ar
ta,
I
n
d
o
n
esia
E
m
ail:
p
ar
w
ad
i@
tr
i
s
ak
t
i.a
c.
id
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
ap
p
licatio
n
o
f
ar
tif
icial
in
tellig
e
n
ce
(
AI
)
h
as
tr
an
s
f
o
r
m
e
d
alg
o
r
ith
m
ic
tr
ad
in
g
,
p
ar
ticu
l
ar
l
y
in
t
h
e
h
ig
h
l
y
v
o
lati
le
f
o
r
eig
n
ex
c
h
a
n
g
e
(
FO
R
E
X
)
m
ar
k
et.
T
r
ad
it
io
n
al
r
u
le
-
b
ased
s
tr
ateg
ie
s
o
f
t
en
f
ail
to
ad
ap
t
to
r
ap
id
in
tr
ad
ay
f
l
u
ctu
a
tio
n
s
,
w
h
i
le
r
ei
n
f
o
r
ce
m
en
t
lear
n
i
n
g
(
R
L
)
en
ab
le
s
ag
e
n
ts
to
r
ef
in
e
t
h
eir
s
tr
ateg
ie
s
th
r
o
u
g
h
i
n
ter
ac
tio
n
w
it
h
m
ar
k
et
d
ata.
Am
o
n
g
R
L
m
et
h
o
d
s
,
th
e
s
tate
–
ac
tio
n
–
r
e
w
ar
d
–
s
ta
te
–
ac
tio
n
(
S
A
R
S
A
)
alg
o
r
ith
m
o
f
f
er
s
ad
ap
tab
ilit
y
.
Ho
w
e
v
er
,
its
li
m
ited
in
ter
p
r
et
ab
ilit
y
r
ed
u
ce
s
its
s
u
itab
ilit
y
i
n
r
eg
u
lated
an
d
r
is
k
-
s
en
s
iti
v
e
en
v
ir
o
n
m
e
n
ts
[
1
]
–
[
4
]
.
Fu
z
zy
in
f
e
r
e
n
c
e
s
y
s
t
em
s
(
F
I
S)
p
r
o
v
i
d
e
a
t
r
an
s
p
a
r
en
t
,
r
u
l
e
-
b
as
e
d
f
r
am
ew
o
r
k
th
at
e
n
h
an
c
es
in
t
e
r
p
r
e
t
a
b
i
l
ity
an
d
au
d
i
t
a
b
i
l
ity
,
m
ak
i
n
g
th
em
v
a
lu
ab
l
e
f
o
r
r
e
s
p
o
n
s
i
b
l
e
A
I
a
p
p
l
i
ca
t
io
n
s
in
f
in
an
c
e
.
T
h
e
SA
R
SA
-
F
I
S
h
y
b
r
i
d
m
o
d
e
l
c
o
m
b
in
es
R
L
a
d
a
p
t
a
b
i
li
ty
w
ith
f
u
z
zy
l
o
g
i
c
t
r
an
s
p
a
r
en
cy
,
a
d
d
r
e
s
s
in
g
in
c
r
ea
s
i
n
g
d
em
an
d
s
f
o
r
o
v
e
r
s
ig
h
t
,
t
r
an
s
p
ar
e
n
cy
,
an
d
e
th
ic
a
l
d
e
c
is
i
o
n
-
m
ak
in
g
in
au
t
o
m
at
e
d
f
in
an
c
i
al
s
y
s
t
em
s
[
2
]
,
[
5
]
,
[
6
]
.
R
ec
en
t
s
t
u
d
ies
d
e
m
o
n
s
tr
ate
t
h
e
e
f
f
ec
tiv
e
n
es
s
o
f
h
y
b
r
id
in
tellig
e
n
t
m
o
d
els
t
h
at
m
er
g
e
d
ata
-
d
r
iv
e
n
lear
n
in
g
w
it
h
s
tr
u
ct
u
r
ed
r
u
le
s
y
s
te
m
s
.
H
y
b
r
id
ar
ch
itect
u
r
es
s
u
ch
as
lo
n
g
s
h
o
r
t
-
ter
m
m
e
m
o
r
y
–
co
n
v
o
lu
tio
n
al
n
eu
r
al
n
et
w
o
r
k
s
(
L
ST
M
-
C
NN
s
)
,
s
ig
n
al
d
ec
o
m
p
o
s
itio
n
m
o
d
e
ls
(
v
ar
iatio
n
al
m
o
d
e
d
ec
o
m
p
o
s
itio
n
o
r
VM
D
an
d
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1693
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
24
,
No
.
4
,
A
u
g
u
s
t
20
26
:
1
267
-
1
2
7
7
1268
s
in
g
u
lar
s
p
ec
tr
u
m
a
n
al
y
s
i
s
o
r
SS
A
)
,
an
d
r
ec
u
r
r
en
t
n
et
w
o
r
k
s
(
b
id
ir
ec
tio
n
al
lo
n
g
s
h
o
r
t
-
ter
m
m
e
m
o
r
y
(
B
iL
ST
M
)
an
d
g
ated
r
ec
u
r
r
en
t
u
n
it
(
GR
U
)
)
h
a
v
e
ac
h
ie
v
ed
im
p
r
o
v
ed
f
o
r
ec
asti
n
g
ac
cu
r
ac
y
f
o
r
co
m
p
lex
ti
m
e
s
er
ies
[
6
]
–
[
8
]
.
A
d
d
itio
n
all
y
,
o
p
tim
izatio
n
tech
n
iq
u
es
s
u
c
h
as
g
en
et
ic
al
g
o
r
ith
m
s
an
d
s
to
ch
ast
ic
g
r
ad
ien
t
m
et
h
o
d
s
h
a
v
e
en
h
an
ce
d
m
o
d
e
l r
o
b
u
s
tn
es
s
an
d
tr
ai
n
in
g
e
f
f
ici
en
c
y
i
n
h
ig
h
-
f
r
eq
u
en
c
y
en
v
ir
o
n
m
e
n
t
s
[
9
]
–
[
1
1
]
.
Desp
ite
th
e
s
e
ad
v
an
ce
m
e
n
ts
,
f
e
w
ap
p
r
o
ac
h
es
in
co
r
p
o
r
ate
s
u
s
tai
n
ab
ilit
y
-
a
w
ar
e
m
ec
h
a
n
is
m
s
s
u
c
h
as
d
r
a
w
d
o
w
n
li
m
i
ts
,
v
o
latili
t
y
f
ilter
in
g
,
o
r
ca
p
ital
p
r
eser
v
atio
n
.
W
ith
th
e
g
r
o
w
i
n
g
f
o
cu
s
o
n
en
v
ir
o
n
m
en
tal
,
s
o
cial,
an
d
g
o
v
er
n
a
n
ce
(
E
SG
)
p
r
in
cip
les
an
d
th
e
Un
ited
Natio
n
s
S
u
s
tai
n
ab
le
Dev
elo
p
m
en
t
Go
als
(
SDGs
)
,
eth
ical
a
n
d
s
u
s
ta
in
ab
le
d
es
ig
n
i
n
tr
ad
in
g
al
g
o
r
i
th
m
s
h
a
s
b
ec
o
m
e
i
n
cr
ea
s
i
n
g
l
y
i
m
p
o
r
ta
n
t
[
2
]
,
[
1
2
]
,
[
1
3
]
.
Stru
ct
u
r
al
ap
p
r
o
ac
h
es su
c
h
as
tr
ian
g
u
lar
ar
b
itra
g
e
a
n
d
d
ir
ec
tio
n
al
ch
a
n
g
e
tec
h
n
iq
u
e
s
h
a
v
e
a
ls
o
s
h
o
w
n
v
a
lu
e
i
n
m
an
a
g
i
n
g
v
o
latilit
y
a
n
d
ali
g
n
in
g
tr
ad
in
g
b
eh
a
v
io
r
w
it
h
m
ar
k
et
r
eg
i
m
es
[
1
4
]
–
[
1
6
]
.
A
s
A
I
b
ec
o
m
es
m
o
r
e
e
m
b
ed
d
ed
in
f
in
an
cia
l
in
f
r
as
tr
u
ctu
r
e,
th
e
d
e
m
a
n
d
f
o
r
ex
p
lain
ab
le,
eth
ical,
an
d
o
v
er
r
id
e
-
ca
p
ab
le
tr
ad
in
g
s
y
s
te
m
s
co
n
ti
n
u
e
s
to
g
r
o
w
[
1
7
]
–
[
1
9
]
.
A
d
ap
tiv
e
f
r
a
m
e
w
o
r
k
s
th
a
t
in
te
g
r
ate
b
eh
av
io
r
al
s
en
s
iti
v
it
y
,
ca
p
ital
co
n
tr
o
l,
an
d
p
r
ed
ictiv
e
r
esil
ien
ce
ar
e
in
cr
ea
s
in
g
l
y
f
a
v
o
r
ed
,
p
a
r
ticu
lar
l
y
i
n
t
h
e
r
etail
f
o
r
ex
d
o
m
ai
n
[
2
0
]
,
[
2
1
]
.
T
r
a
d
itio
n
al
b
a
s
elin
es
in
alg
o
r
ith
m
ic
tr
ad
in
g
s
u
ch
as
m
o
v
in
g
av
er
a
g
e
cr
o
s
s
o
v
er
s
,
b
u
y
-
a
n
d
-
h
o
ld
s
tr
ateg
ie
s
,
an
d
s
tan
d
alo
n
e
f
u
zz
y
s
y
s
te
m
s
o
f
te
n
f
a
il
to
m
ain
tai
n
p
er
f
o
r
m
an
ce
co
n
s
is
te
n
c
y
u
n
d
er
d
y
n
a
m
ic
v
o
latilit
y
co
n
d
itio
n
s
.
W
h
ile
th
ese
m
et
h
o
d
s
p
r
o
v
id
e
in
ter
p
r
et
ab
ilit
y
o
r
s
tab
ilit
y
in
s
p
ec
i
f
ic
r
eg
i
m
e
s
,
th
e
y
lac
k
ad
ap
tiv
e
lear
n
in
g
an
d
co
n
te
x
t
u
al
a
w
ar
en
es
s
.
RL
ap
p
r
o
ac
h
es,
s
u
c
h
as
Q
-
lear
n
i
n
g
,
i
m
p
r
o
v
e
ad
ap
tab
ilit
y
b
u
t
r
e
m
ain
l
i
m
ited
in
tr
a
n
s
p
ar
en
c
y
an
d
r
is
k
co
n
tr
o
l.
T
h
e
S
AR
S
A
-
FI
S
h
y
b
r
id
m
o
d
el
e
x
ten
d
s
b
e
y
o
n
d
th
ese
b
aselin
es
b
y
co
m
b
i
n
i
n
g
r
ea
l
-
ti
m
e
p
o
lic
y
u
p
d
ates
w
it
h
r
u
le
-
b
ased
in
ter
p
r
etab
ilit
y
,
e
n
ab
lin
g
a
m
o
r
e
s
u
s
tai
n
ab
le
an
d
r
esp
o
n
s
ib
le
ap
p
r
o
ac
h
to
AI
-
d
r
iv
en
f
i
n
an
c
ial
s
y
s
te
m
s
.
T
h
is
s
tu
d
y
p
r
o
p
o
s
es
a
s
u
s
tain
ab
le
an
d
in
ter
p
r
etab
le
alg
o
r
ith
m
ic
tr
ad
in
g
ag
e
n
t
f
o
r
th
e
E
u
r
o
/Un
ited
States
Do
llar
(
E
UR
US
D
)
cu
r
r
en
c
y
p
air
,
b
u
ilt
u
s
in
g
a
h
y
b
r
id
SA
R
S
A
-
FIS
f
r
a
m
e
w
o
r
k
.
T
h
e
o
b
j
ec
tiv
e
is
to
in
te
g
r
ate
RL
w
i
th
f
u
zz
y
lo
g
i
c
to
cr
ea
te
a
s
y
s
te
m
t
h
at
is
b
o
th
ad
ap
tiv
e
to
d
y
n
a
m
ic
m
a
r
k
et
co
n
d
itio
n
s
a
n
d
tr
an
s
p
ar
en
t
in
its
d
ec
is
io
n
-
m
a
k
in
g
f
u
l
f
illi
n
g
k
e
y
p
r
in
cip
les
o
f
r
esp
o
n
s
ib
le
A
I
i
n
f
in
a
n
ce
.
T
h
e
ag
en
t
d
esi
g
n
in
te
g
r
ates
ex
p
o
n
e
n
tia
l
m
o
v
in
g
av
er
ag
e
(
E
M
A
)
-
b
ased
s
tate
c
lass
i
f
icatio
n
,
v
o
latili
t
y
-
s
e
n
s
iti
v
e
r
e
w
ar
d
s
h
ap
in
g
,
an
d
d
r
a
w
d
o
w
n
-
a
w
ar
e
ex
ec
u
tio
n
p
o
licies to
b
alan
ce
ad
ap
tab
ilit
y
w
it
h
et
h
ical
r
is
k
co
n
tr
o
l.
T
h
e
SA
R
S
A
-
F
I
S
ag
e
n
t
w
a
s
tr
ain
ed
o
n
E
UR
USD
M1
5
d
ata
f
r
o
m
2
0
2
0
to
2
0
2
3
an
d
b
ac
k
test
ed
o
n
2
0
2
4
o
u
t
-
of
-
s
a
m
p
le
d
ata.
A
t
o
tal
o
f
7
8
5
tr
ad
es
w
er
e
ex
ec
u
ted
,
y
ield
i
n
g
a
n
et
p
r
o
f
i
t
o
f
USD
6
1
.
8
5
(
in
itial
ca
p
ital
USD
1
0
0
)
w
it
h
a
p
r
o
f
it
f
ac
to
r
o
f
1
.
0
4
an
d
a
b
alan
ce
d
w
i
n
–
lo
s
s
r
ati
o
.
R
is
k
-
ad
j
u
s
t
ed
r
esu
lts
s
h
o
w
ed
m
o
d
er
ate
r
etu
r
n
s
(
s
h
ar
p
e
r
atio
=
0
.
5
3
)
,
s
tr
o
n
g
eq
u
it
y
s
tab
ilit
y
(
E
SI
=
0
.
9
6
7
2
)
,
an
d
s
en
s
iti
v
it
y
to
m
ac
r
o
ec
o
n
o
m
ic
s
h
i
f
ts
d
etec
te
d
th
r
o
u
g
h
c
u
m
u
lat
iv
e
s
u
m
(
C
USUM
)
an
al
y
s
i
s
.
T
h
ese
f
in
d
i
n
g
s
d
e
m
o
n
s
tr
ate
th
e
m
o
d
el
’
s
s
tr
u
c
tu
r
al
r
o
b
u
s
t
n
e
s
s
an
d
i
n
ter
p
r
etab
ilit
y
w
h
ile
id
en
ti
f
y
i
n
g
o
p
p
o
r
tu
n
ities
f
o
r
en
h
a
n
ci
n
g
r
e
g
i
m
e
ad
ap
tatio
n
an
d
ex
i
t
lo
g
ic.
I
n
s
u
m
m
ar
y
,
t
h
e
p
r
o
p
o
s
ed
SAR
S
A
-
FIS
f
r
a
m
e
w
o
r
k
b
r
id
g
es
th
e
g
ap
b
et
w
ee
n
ad
ap
tab
ilit
y
an
d
ex
p
lai
n
ab
ili
t
y
in
A
I
-
d
r
iv
e
n
f
i
n
a
n
cial
s
y
s
te
m
s
,
alig
n
i
n
g
alg
o
r
it
h
m
ic
p
er
f
o
r
m
a
n
ce
w
it
h
r
esp
o
n
s
ib
le
A
I
an
d
s
u
s
tai
n
ab
ilit
y
p
r
in
cip
les.
O
v
er
all,
th
is
r
esear
ch
ad
v
an
ce
s
th
e
d
ev
el
o
p
m
e
n
t
o
f
eth
ical
,
tr
an
s
p
ar
en
t,
a
n
d
r
esil
ien
t tr
ad
in
g
s
y
s
te
m
s
f
o
r
th
e
m
o
d
er
n
f
i
n
an
cial
en
v
ir
o
n
m
e
n
t
.
2.
M
E
T
H
O
D
T
h
e
tr
ad
in
g
a
g
en
t
w
as
d
e
v
elo
p
ed
u
s
i
n
g
a
S
AR
S
A
–
F
I
S
h
y
b
r
id
f
r
a
m
e
w
o
r
k
,
co
m
b
in
in
g
RL
ad
ap
tab
ilit
y
w
it
h
f
u
zz
y
lo
g
ic
t
r
an
s
p
ar
en
c
y
.
T
h
e
S
AR
S
A
al
g
o
r
ith
m
w
a
s
s
e
lecte
d
f
o
r
its
ca
p
ab
ilit
y
to
iter
ati
v
el
y
u
p
d
ate
ac
tio
n
–
v
alu
e
es
ti
m
ates
b
ased
o
n
m
ar
k
et
f
ee
d
b
ac
k
,
wh
ile
th
e
S
u
g
en
o
-
t
y
p
e
FIS
en
s
u
r
ed
in
ter
p
r
etab
ilit
y
an
d
au
d
itab
ili
t
y
o
f
d
ec
is
io
n
s
.
T
h
e
in
te
g
r
atio
n
o
f
t
h
ese
t
w
o
ap
p
r
o
ac
h
es
s
u
p
p
o
r
ts
b
o
th
ad
a
p
tiv
e
lear
n
in
g
a
n
d
r
esp
o
n
s
ib
le
A
I
d
esig
n
,
m
ee
ti
n
g
t
h
e
n
ee
d
s
o
f
r
is
k
-
s
e
n
s
i
tiv
e
f
in
a
n
cial
s
y
s
te
m
s
[
1
]
,
[
4
]
,
[
1
6
]
,
[
2
2
]
.
A
h
y
b
r
id
S
A
R
S
A
-
FIS
s
tr
u
ctu
r
e
t
h
u
s
co
m
b
i
n
es
lear
n
in
g
f
lex
ib
ilit
y
w
it
h
r
u
le
-
b
ased
ex
p
lai
n
ab
ilit
y
,
s
atis
f
y
i
n
g
b
o
t
h
ad
ap
tatio
n
an
d
au
d
itab
ilit
y
r
eq
u
ir
e
m
e
n
t
s
[
2
]
,
[
1
5
]
.
2
.
1
.
Dev
el
o
p
m
ent
e
nv
iro
n
ment
T
h
e
d
ev
elo
p
m
en
t
w
as
i
m
p
le
m
en
ted
ac
r
o
s
s
th
r
ee
p
latf
o
r
m
s
:
P
y
t
h
o
n
3
.
1
0
f
o
r
SAR
S
A
RL
s
i
m
u
latio
n
,
MA
T
L
A
B
R
2
0
2
3
a
f
o
r
FIS
m
o
d
eli
n
g
,
an
d
Me
taT
r
ad
er
5
(
b
u
ild
4
7
5
5
)
f
o
r
r
ea
l
-
ti
m
e
i
m
p
le
m
e
n
tat
io
n
a
n
d
b
ac
k
test
i
n
g
.
T
h
e
o
v
er
all
w
o
r
k
f
lo
w
is
i
llu
s
tr
ated
in
Fig
u
r
e
1
.
His
to
r
ical
E
UR
U
SD
1
5
-
m
i
n
u
te
ca
n
d
lest
ic
k
d
ata
(
J
an
u
ar
y
2
0
2
0
–
Dec
em
b
er
2
0
2
4
)
w
er
e
r
etr
iev
ed
f
r
o
m
Me
t
aT
r
a
d
er
5
.
Data
f
r
o
m
2
0
2
0
–
2
0
2
3
w
er
e
u
s
ed
f
o
r
m
o
d
el
tr
ain
i
n
g
,
an
d
2
0
2
4
d
ata
s
er
v
ed
as
o
u
t
-
of
-
s
a
m
p
le
tes
tin
g
,
co
n
s
is
te
n
t
w
i
th
s
ta
n
d
ar
d
tim
e
-
s
er
ies
v
alid
atio
n
p
r
ac
tices
[
5
]
.
T
h
is
m
u
lt
i
-
p
lat
f
o
r
m
w
o
r
k
f
lo
w
en
s
u
r
es
th
e
r
ep
r
o
d
u
cib
ilit
y
o
f
t
h
e
e
x
p
er
i
m
e
n
tal
p
r
o
ce
s
s
ac
r
o
s
s
s
i
m
u
lat
io
n
,
m
o
d
eli
n
g
,
a
n
d
d
ep
lo
y
m
e
n
t s
tag
e
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
A
d
a
p
tive
tr
a
d
in
g
s
ystem
fo
r
s
u
s
ta
in
a
b
le
fo
r
ex
ma
r
ke
ts
(
Jo
n
i F
a
t
)
1269
Fig
u
r
e
1
.
SAR
S
A
-
FIS
tr
ad
in
g
ag
en
t d
e
v
elo
p
m
e
n
t f
lo
w
c
h
ar
t i
llu
s
tr
atin
g
t
h
e
s
eq
u
e
n
tial p
r
o
ce
s
s
o
f
RL
s
et
u
p
,
f
u
zz
y
i
n
f
er
e
n
ce
m
o
d
eli
n
g
,
s
y
s
t
e
m
in
teg
r
atio
n
,
an
d
s
u
s
tai
n
ab
l
e
b
ac
k
test
i
n
g
2
.
2
.
SARSA
RL
f
ra
m
ew
o
rk
T
h
e
SAR
S
A
e
n
v
ir
o
n
m
e
n
t
w
a
s
m
o
d
eled
u
s
in
g
tab
u
lar
R
L
.
States
w
er
e
d
is
cr
etize
d
i
n
to
th
r
ee
class
e
s
(
S1
,
S2
,
an
d
S3
)
w
h
ic
h
ar
e
b
ased
o
n
E
MA
5
0
d
ev
iatio
n
s
u
s
in
g
±
2
0
p
ip
th
r
esh
o
ld
s
.
A
cti
o
n
s
w
er
e
(
s
ell,
h
o
ld
,
an
d
buy
)
,
r
esu
lti
n
g
in
a
3
×3
Q
-
tab
le.
L
ea
r
n
in
g
p
ar
am
e
ter
s
w
er
e
s
et
as:
lear
n
in
g
r
ate
(
)
=0
.
1
,
d
is
co
u
n
t
f
a
cto
r
(
)
=0
.
9
,
in
itial
=0
.
3
w
it
h
ad
ap
tiv
e
d
ec
a
y
(
←
0
.
9
9
9
×
p
er
s
tep
,
d
o
w
n
to
0
.
0
5
)
.
T
r
ain
in
g
r
an
f
o
r
5
0
0
ep
is
o
d
es
o
r
u
n
til
co
n
v
er
g
e
n
ce
,
u
s
i
n
g
th
e
S
AR
S
A
u
p
d
ate
r
u
le
s
h
o
w
n
in
(
1
)
.
T
h
e
lear
n
ed
Q
tab
le
w
as
e
x
p
o
r
ted
to
an
ex
p
er
t a
d
v
is
o
r
(
E
A
)
i
n
Me
taT
r
ad
e
r
5
.
(
,
)
←
(
,
)
+
[
+
1
+
(
+
1
,
+
1
)
−
(
,
)
]
(
1
)
Her
e,
(
,
)
r
ep
r
esen
ts
t
h
e
ex
p
ec
ted
v
al
u
e
o
f
ta
k
i
n
g
ac
t
io
n
in
s
ta
te
,
w
h
ile
+
1
d
en
o
tes
t
h
e
r
e
w
ar
d
r
ec
eiv
ed
a
f
ter
tr
a
n
s
iti
o
n
in
g
to
s
tate
+
1
an
d
s
e
lecti
n
g
ac
tio
n
+
1
.
T
h
e
alg
o
r
ith
m
u
p
d
ates
its
p
o
li
c
y
iter
ativ
el
y
b
y
i
n
co
r
p
o
r
atin
g
b
o
th
th
e
i
m
m
ed
iate
r
e
w
ar
d
an
d
th
e
ex
p
ec
ted
f
u
t
u
r
e
r
etu
r
n
,
b
alan
ci
n
g
ex
p
lo
r
atio
n
an
d
ex
p
lo
itatio
n
in
th
e
lear
n
i
n
g
p
r
o
ce
s
s
.
P
y
t
h
o
n
m
o
d
u
le
s
Nu
m
P
y
an
d
P
an
d
as
w
er
e
u
s
ed
f
o
r
s
i
m
u
latio
n
,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1693
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
24
,
No
.
4
,
A
u
g
u
s
t
20
26
:
1
267
-
1
2
7
7
1270
en
v
ir
o
n
m
e
n
t tr
a
n
s
i
tio
n
,
a
n
d
Q
-
tab
le
u
p
d
ates.
At
co
n
v
er
g
e
n
c
e,
th
e
Q
-
tab
le
w
as e
m
b
ed
d
ed
in
to
a
cu
s
to
m
e
x
p
er
t
ad
v
is
o
r
o
r
E
A
w
r
itte
n
in
MQ
L
5
f
o
r
r
ea
l
-
ti
m
e
ex
ec
u
ti
o
n
.
T
h
ese
im
p
le
m
e
n
tatio
n
d
etails
f
ac
i
litate
f
u
ll
r
ep
r
o
d
u
cib
ilit
y
o
f
th
e
lear
n
i
n
g
an
d
d
ep
lo
y
m
en
t
p
r
o
ce
s
s
.
T
h
e
E
A
p
ar
a
m
eter
s
in
cl
u
d
ed
a
f
i
x
ed
lo
t
s
ize
o
f
0
.
0
1
,
a
2
0
-
p
ip
s
p
r
ea
d
li
m
it,
a
n
d
a
1
5
-
m
i
n
u
te
co
o
ld
o
w
n
b
et
w
ee
n
tr
ad
es.
R
is
k
co
n
tr
o
l
lo
g
ic
ca
p
p
ed
d
r
aw
d
o
w
n
at
2
0
% v
ia
d
y
n
a
m
i
c
eq
u
it
y
tr
ac
k
i
n
g
.
2
.
3
.
F
I
S
des
ig
n
F
o
r
in
t
e
r
p
r
e
t
a
b
i
l
i
ty
,
a
Su
g
en
o
-
ty
p
e
F
I
S
w
a
s
d
e
v
e
l
o
p
e
d
u
s
in
g
MA
T
L
A
B
.
I
t
ac
c
e
p
t
e
d
th
r
e
e
in
p
u
t
s
:
c
u
r
r
en
t
s
t
a
t
e
,
p
r
e
d
i
c
te
d
n
ex
t
s
ta
t
e
,
a
n
d
r
ew
a
r
d
;
an
d
p
r
o
d
u
c
e
d
o
n
e
o
u
t
p
u
t
s
ig
n
al
.
E
a
c
h
in
p
u
t
w
as
m
o
d
e
le
d
u
s
in
g
t
h
r
e
e
f
u
z
zy
m
e
m
b
e
r
s
h
i
p
f
u
n
c
t
io
n
s
(
l
o
w
,
m
o
d
e
r
a
t
e
,
h
ig
h
)
.
T
h
e
o
u
t
p
u
t
w
a
s
en
c
o
d
e
d
a
s
:
s
e
ll
=
0
.
5
,
h
o
l
d
=
1
.
5
,
an
d
b
uy
=
2
.
5
.
A
to
tal
o
f
2
7
f
u
zz
y
r
u
les co
v
er
ed
all
co
m
b
i
n
atio
n
s
o
f
in
p
u
t
s
.
As
s
h
o
w
n
i
n
Fi
g
u
r
e
2
,
th
e
FI
S
o
p
er
ates
as
a
m
o
d
u
lar
d
ec
i
s
io
n
-
en
h
a
n
cin
g
la
y
er
w
i
th
in
t
h
e
b
r
o
ad
er
S
A
R
S
A
-
FIS
ar
ch
itect
u
r
e.
Up
o
n
r
ec
eiv
in
g
n
o
r
m
alize
d
Q
-
v
alu
es
a
n
d
r
e
w
ar
d
s
f
r
o
m
t
h
e
S
A
R
S
A
a
g
e
n
t,
th
e
in
p
u
t
s
ar
e
p
ass
ed
to
a
f
u
zz
y
r
u
le
b
ase
th
at
e
v
alu
a
tes
t
h
e
m
u
s
i
n
g
t
h
e
p
r
o
d
m
eth
o
d
f
o
r
lo
g
ica
l
co
n
j
u
n
ctio
n
s
a
n
d
p
r
o
b
o
r
f
o
r
d
is
j
u
n
ctio
n
s
.
T
h
e
FIS
la
y
er
ev
al
u
ated
Q
-
v
a
lu
e
s
an
d
r
ew
ar
d
s
u
s
i
n
g
p
r
o
d
an
d
p
r
o
b
o
r
m
eth
o
d
s
f
o
r
f
u
zz
y
lo
g
ic
r
ea
s
o
n
i
n
g
.
A
Su
g
en
o
e
n
g
i
n
e
w
it
h
s
u
m
ag
g
r
e
g
atio
n
a
n
d
w
tav
er
d
ef
u
zz
i
f
ic
atio
n
w
as
u
s
ed
to
g
en
er
ate
cr
is
p
tr
ad
in
g
s
ig
n
al
s
in
r
ea
l
ti
m
e,
en
h
an
c
in
g
d
ec
i
s
io
n
tr
an
s
p
ar
en
c
y
an
d
i
n
ter
p
r
etab
ilit
y
w
i
th
i
n
t
h
e
h
y
b
r
id
m
o
d
el.
T
o
en
s
u
r
e
r
u
le
co
v
er
ag
e,
th
e
FIS
w
as
tes
ted
u
s
in
g
1
0
0
r
an
d
o
m
ized
in
p
u
t
v
ec
to
r
s
[
2
2
]
.
I
n
teg
r
atio
n
w
as
ac
h
ie
v
ed
b
y
m
ap
p
in
g
Q
-
v
al
u
es
to
f
u
zz
y
c
lass
es
:
lo
w
(
<
4
.
35
)
,
m
o
d
er
ate
(
4
.
35
≤
<
10
.
02
)
,
an
d
h
i
g
h
(
≥
10
.
02
)
.
C
o
m
b
in
ed
w
i
th
s
tate
v
ar
iab
les,
th
e
s
e
i
n
p
u
t
s
w
er
e
f
ed
in
to
th
e
FIS
to
g
e
n
er
ate
th
e
tr
ad
in
g
s
i
g
n
a
l.
Fig
u
r
e
2
.
B
lo
ck
d
iag
r
a
m
o
f
t
h
e
Su
g
en
o
-
t
y
p
e
FIS
u
s
ed
i
n
th
e
S
A
R
S
A
-
FIS
tr
ad
in
g
ag
e
n
t,
s
h
o
w
i
n
g
i
n
p
u
t
v
ar
iab
les,
r
u
le
b
ase,
an
d
s
i
g
n
al
o
u
tp
u
t str
u
ctu
r
e
2
.
4
.
Re
w
a
rd
a
nd
s
us
t
a
ina
bil
it
y
m
ec
ha
ni
s
m
s
A
d
i
r
ec
t
i
o
n
a
l
r
e
w
a
r
d
s
t
r
u
ct
u
r
e
w
as
im
p
lem
en
t
e
d
w
ith
in
th
e
SA
R
SA
en
v
i
r
o
n
m
en
t
t
o
g
u
i
d
e
le
a
r
n
in
g
,
as
i
l
lu
s
t
r
a
t
e
d
in
F
ig
u
r
e
3
.
T
h
e
r
e
w
a
r
d
m
a
p
w
as
d
es
ig
n
e
d
t
o
f
av
o
r
u
p
w
a
r
d
t
r
an
s
i
ti
o
n
s
(
e
.
g
.
,
S
1
→
S
2
,
S
2
→
S
3
)
an
d
p
en
alize
d
o
w
n
w
ar
d
o
r
later
al
m
o
v
es,
ac
ce
ler
atin
g
co
n
v
er
g
e
n
ce
w
h
ile
ali
g
n
i
n
g
w
i
th
tr
en
d
-
f
o
llo
w
i
n
g
s
tr
ateg
ie
s
.
T
r
a
i
n
in
g
u
s
e
d
a
B
e
llm
an
-
b
a
s
e
d
e
p
s
i
l
o
n
-
g
r
ee
d
y
p
o
licy
an
d
t
e
r
m
in
a
t
e
d
a
f
t
e
r
1
,
0
0
0
ep
i
s
o
d
e
s
o
r
Q
-
v
a
lu
e
s
t
a
b
il
i
z
at
i
o
n
.
T
h
r
ee
s
u
s
tai
n
ab
ilit
y
f
il
ter
s
w
e
r
e
i
m
p
le
m
e
n
ted
.
A
tr
e
n
d
f
ilter
u
s
ed
E
M
A
5
0
an
d
E
MA
1
0
alig
n
m
e
n
t
to
v
alid
ate
tr
ad
es.
A
v
o
latilit
y
f
ilter
u
s
ed
a
1
4
-
p
er
io
d
av
er
ag
e
tr
u
e
r
an
g
e
(
A
T
R
)
,
b
lo
ck
in
g
tr
ad
es
w
h
en
A
T
R
ex
ce
ed
ed
t
w
ice
it
s
m
ed
ia
n
.
A
d
r
aw
d
o
w
n
li
m
iter
d
ea
ctiv
ate
d
th
e
ag
en
t
af
ter
a
2
0
%
eq
u
it
y
d
r
o
p
.
T
h
ese
f
ilter
s
p
r
o
m
o
ted
r
esp
o
n
s
ib
le
r
i
s
k
-
ta
k
in
g
[
1
5
]
,
[
2
2
]
.
Fin
al
m
o
d
el
f
i
l
es
w
er
e
s
a
v
ed
v
ia
Me
taT
r
ad
er
5
I
/O
s
y
s
te
m
.
T
h
e
Q
-
tab
le
w
as
s
a
v
ed
as
“
S
AR
S
A
_
QT
ab
le_
E
UR
USD.
t
x
t,”
th
e
f
u
zz
y
w
ei
g
h
ts
a
s
“
S
AR
FI
S_
W
eig
h
ts
_
E
UR
USD
.
tx
t,”
an
d
d
r
a
w
d
o
w
n
d
ata
as
“
Ma
x
Dr
a
w
d
o
w
n
S
tatu
s
.
tx
t.”
T
h
is
e
n
s
u
r
ed
cr
o
s
s
-
s
ess
io
n
co
n
ti
n
u
it
y
,
m
o
d
el
r
ep
r
o
d
u
cib
ilit
y
,
an
d
f
ac
ilit
ated
p
o
s
t
-
h
o
c
au
d
itab
ilit
y
.
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
A
d
a
p
tive
tr
a
d
in
g
s
ystem
fo
r
s
u
s
ta
in
a
b
le
fo
r
ex
ma
r
ke
ts
(
Jo
n
i F
a
t
)
1271
Fig
u
r
e
3
.
SAR
S
A
tr
ai
n
i
n
g
e
n
v
ir
o
n
m
e
n
t ill
u
s
tr
ati
n
g
s
tate
tr
a
n
s
itio
n
s
(
S1
–
S3
)
,
p
o
s
s
ib
le
ac
tio
n
s
(
s
ta
y
,
n
e
x
t,
j
u
m
p
)
,
an
d
co
r
r
esp
o
n
d
in
g
r
e
w
ar
d
ass
ig
n
m
en
ts
2
.
5
.
Sy
s
t
em
a
rc
hite
ct
ure
A
s
tr
u
ctu
r
ed
s
eq
u
e
n
ce
d
iag
r
am
a
s
in
Fi
g
u
r
e
4
w
as
d
ev
el
o
p
ed
to
illu
s
tr
ate
th
e
S
A
R
S
A
-
FIS
E
A
w
o
r
k
f
lo
w
,
e
n
co
m
p
as
s
in
g
d
ata
ac
q
u
is
itio
n
,
s
tate
cla
s
s
i
f
icat
io
n
,
ac
tio
n
s
elec
tio
n
,
FIS
ev
al
u
a
tio
n
,
an
d
ex
ec
u
tio
n
f
ilter
i
n
g
(
M
A
C
D,
E
M
A
1
0
,
tr
i
an
g
u
lar
h
ed
g
i
n
g
)
.
E
ac
h
m
o
d
u
le
in
ter
ac
t
s
tr
an
s
p
ar
en
tl
y
w
it
h
o
th
er
s
,
r
ein
f
o
r
cin
g
in
ter
p
r
etab
ilit
y
a
n
d
r
ep
r
o
d
u
cib
ilit
y
ac
r
o
s
s
t
h
e
f
u
l
l tr
ad
in
g
p
ip
elin
e
[
4
]
,
[
1
4
]
.
Fig
u
r
e
4
.
Seq
u
en
ce
d
iag
r
a
m
o
f
th
e
S
A
R
S
A
-
FIS
EA
ar
ch
i
tec
tu
r
e
ill
u
s
tr
ati
n
g
in
it
ializatio
n
,
d
ec
is
io
n
lo
g
ic,
lear
n
in
g
u
p
d
ates,
an
d
s
u
s
tai
n
a
b
le
tr
ad
in
g
w
o
r
k
f
lo
w
in
Me
ta
T
r
a
d
er
5
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1693
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
24
,
No
.
4
,
A
u
g
u
s
t
20
26
:
1
267
-
1
2
7
7
1272
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
e
SA
R
S
A
-
FIS
tr
ad
in
g
a
g
en
t
w
as
ev
a
lu
ated
u
s
in
g
o
n
e
y
ea
r
o
f
o
u
t
-
of
-
s
a
m
p
le
E
UR
US
D
M1
5
d
ata.
T
h
e
s
y
s
te
m
ac
h
ie
v
ed
m
ar
g
i
n
a
l
p
r
o
f
itab
ilit
y
,
w
it
h
a
p
r
o
f
it
f
a
cto
r
s
lig
h
tl
y
ab
o
v
e
u
n
it
y
,
in
d
i
ca
tin
g
n
ea
r
b
r
ea
k
-
ev
en
p
er
f
o
r
m
an
ce
u
n
d
er
r
ea
lis
tic
m
ar
k
e
t c
o
n
d
itio
n
s
.
3
.
1
.
T
ra
din
g
perf
o
rm
a
nce
m
et
ric
s
T
ab
le
1
p
r
esen
ts
th
e
b
ac
k
test
s
u
m
m
ar
y
.
T
h
e
r
esu
lt
s
in
d
icate
a
b
alan
ce
d
d
is
tr
ib
u
t
io
n
b
et
w
ee
n
w
i
n
n
i
n
g
an
d
lo
s
i
n
g
tr
ad
es,
s
u
g
g
e
s
ti
n
g
s
tab
le
d
ec
is
io
n
b
eh
a
v
io
r
r
ath
e
r
th
an
o
v
er
f
itti
n
g
.
T
h
e
ex
p
ec
t
ed
p
ay
o
f
f
r
e
m
ai
n
s
p
o
s
itiv
e
b
u
t
lo
w
,
r
ef
lecti
n
g
a
co
n
s
er
v
ati
v
e
tr
ad
i
n
g
p
r
o
f
i
le.
Ho
w
e
v
er
,
th
e
r
elati
v
el
y
h
i
g
h
d
r
a
w
d
o
w
n
h
ig
h
li
g
h
t
s
v
u
l
n
er
ab
ilit
y
d
u
r
i
n
g
p
r
o
lo
n
g
ed
ad
v
er
s
e
co
n
d
itio
n
s
,
i
n
d
icatin
g
t
h
at
w
h
ile
tr
ad
e
-
lev
e
l
r
is
k
i
s
co
n
tr
o
lled
,
cu
m
u
lat
iv
e
r
is
k
r
e
m
ain
s
a
k
e
y
li
m
ita
tio
n
.
Gr
o
w
t
h
m
etr
ics
s
u
c
h
as
ar
ith
m
etic
h
o
ld
i
n
g
p
er
io
d
r
etu
r
n
(
A
HP
R
)
(
0
.
1
4
%)
an
d
g
eo
m
etr
ic
h
o
ld
in
g
p
er
io
d
r
etu
r
n
(
GHP
R
)
(
0
.
0
6
%
)
r
ef
lect
a
c
o
n
s
er
v
ati
v
e
an
d
lo
w
-
y
ield
s
tr
ateg
y
.
C
o
r
r
elatio
n
b
et
w
ee
n
p
r
o
f
it
an
d
ex
cu
r
s
io
n
m
ea
s
u
r
es
(
m
a
x
i
m
u
m
f
a
v
o
r
ab
le
ex
c
u
r
s
io
n
(
MFE
)
=
0
.
7
7
,
MA
E
=
0
.
7
9
)
s
u
g
g
e
s
ts
v
o
latilit
y
-
s
e
n
s
it
iv
e
o
u
tco
m
es.
T
h
ese
f
i
n
d
in
g
s
s
u
g
g
est
t
h
at
t
h
e
S
AR
S
A
-
FIS
f
r
a
m
e
w
o
r
k
ac
h
iev
e
s
m
icr
o
-
le
v
el
co
n
s
is
ten
c
y
i
n
tr
ad
e
ex
ec
u
t
io
n
b
u
t r
e
m
ai
n
s
li
m
ited
in
m
ac
r
o
-
lev
e
l r
o
b
u
s
tn
e
s
s
u
n
d
er
s
u
s
tai
n
ed
v
o
lati
lit
y
.
T
ab
le
1
.
P
er
f
o
r
m
a
n
ce
s
u
m
m
ar
y
o
f
t
h
e
S
AR
S
A
-
FIS
tr
ad
i
n
g
a
g
en
t b
ased
o
n
o
n
e
-
y
ea
r
b
ac
k
te
s
tin
g
r
es
u
lt
s
f
o
r
E
UR
USD
(
M1
5
T
im
e
f
r
a
m
e)
M
e
t
r
i
c
V
a
l
u
e
T
o
t
a
l
t
r
a
d
e
s
7
8
5
P
r
o
f
i
t
t
r
a
d
e
s (%)
3
9
7
(
5
0
.
5
7
%)
L
o
ss
t
r
a
d
e
s (%)
3
8
8
(
4
9
.
4
3
%)
G
r
o
ss
p
r
o
f
i
t
(
U
S
D
)
1
6
3
8
.
23
G
r
o
ss
l
o
ss (U
S
D
)
-
1
5
7
6
.
38
N
e
t
p
r
o
f
i
t
(
U
S
D
)
61
.
85
P
r
o
f
i
t
F
a
c
t
o
r
1
.
04
Ex
p
e
c
t
e
d
p
a
y
o
f
f
(USD)
0
.
08
S
h
a
r
p
e
r
a
t
io
0
.
53
R
e
c
o
v
e
r
y
f
a
c
t
o
r
0
.
64
M
a
x
d
r
a
w
d
o
w
n
(
U
S
D
)
96
.
66
M
a
x
d
r
a
w
d
o
w
n
(
%)
5
9
.
7
4
%
A
v
e
r
a
g
e
p
r
o
f
i
t
t
r
a
d
e
(USD)
4
.
13
A
v
e
r
a
g
e
l
o
ss t
r
a
d
e
(
U
S
D
)
-
4
.
06
L
a
r
g
e
st
p
r
o
f
i
t
t
r
a
d
e
(
U
S
D
)
7
.
64
L
a
r
g
e
st
l
o
ss t
r
a
d
e
(
U
S
D
)
-
5
.
18
M
a
x
c
o
n
se
c
u
t
i
v
e
w
i
n
s
7
(
U
S
D
2
2
.
4
4
)
M
a
x
c
o
n
se
c
u
t
i
v
e
l
o
sse
s
1
0
(
U
S
D
-
4
0
.
2
0
)
A
H
P
R
(
D
a
i
l
y
)
1
.
0
0
1
4
(
0
.
1
4
%)
G
H
P
R
(
D
a
i
l
y
)
1
.
0
0
0
6
(
0
.
0
6
%)
3
.
2
.
St
a
bil
it
y
a
nd
re
s
ilience
i
nd
ica
t
o
rs
Fig
u
r
e
5
s
h
o
w
s
t
h
at
t
h
e
eq
u
it
y
cu
r
v
e
r
e
m
ain
ed
clo
s
e
to
th
e
b
alan
ce
cu
r
v
e
t
h
r
o
u
g
h
o
u
t
t
h
e
test
.
T
h
is
co
n
d
itio
n
,
m
ea
s
u
r
ed
u
s
i
n
g
th
e
eq
u
it
y
s
tab
ilit
y
i
n
d
ex
(
E
SI)
,
in
d
icate
s
lo
w
f
lo
atin
g
lo
s
s
es
an
d
co
n
s
is
te
n
t
p
o
s
itio
n
co
n
tr
o
l
a
s
i
n
(
2
)
.
Si
m
ilar
s
tab
ilit
y
p
atter
n
s
h
av
e
b
ee
n
r
ep
o
r
ted
in
ca
p
ital
-
p
r
es
er
v
in
g
al
g
o
r
ith
m
ic
tr
ad
in
g
s
y
s
te
m
s
[
2
1
]
,
[
2
2
]
.
=
1
−
∑
|
−
|
∑
(
2
)
I
n
t
h
is
e
x
p
er
i
m
e
n
t,
th
e
E
SI
v
alu
e
o
f
0
.
9
6
7
2
in
d
icate
s
m
i
n
i
m
al
f
lo
ati
n
g
lo
s
s
e
s
a
n
d
s
tr
o
n
g
i
n
tr
ad
a
y
ca
p
ital
co
n
tr
o
l.
T
h
e
s
y
s
te
m
’
s
d
r
a
w
d
o
w
n
r
ec
o
v
er
y
b
eh
a
v
io
r
w
a
s
f
u
r
th
er
as
s
es
s
ed
u
s
i
n
g
th
e
r
o
ll
in
g
r
ec
o
v
er
y
r
atio
,
d
ef
in
ed
i
n
(
3
)
:
=
−
(
−
:
)
(
−
:
)
−
(
−
:
)
(
3
)
w
h
er
e
is
t
h
e
b
ala
n
ce
at
ti
m
e
,
an
d
is
t
h
e
w
i
n
d
o
w
s
ize
(
s
et
to
3
0
in
t
h
i
s
ca
s
e)
.
As
s
h
o
w
n
i
n
Fig
u
r
e
6
,
t
h
e
r
atio
o
s
cillated
s
ig
n
i
f
ican
tl
y
,
in
d
icatin
g
th
at
r
ec
o
v
er
y
p
h
ases
ar
e
n
o
t
co
n
s
is
ten
t
l
y
s
u
s
tain
ed
,
r
ev
ea
lin
g
a
s
tr
u
ct
u
r
al
li
m
itatio
n
in
t
h
e
ab
s
en
ce
o
f
ad
ap
tiv
e
e
x
it
r
ein
f
o
r
ce
m
en
t
m
ec
h
a
n
is
m
s
[
1
]
,
[
2
3
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
A
d
a
p
tive
tr
a
d
in
g
s
ystem
fo
r
s
u
s
ta
in
a
b
le
fo
r
ex
ma
r
ke
ts
(
Jo
n
i F
a
t
)
1273
Fig
u
r
e
5
.
E
q
u
it
y
an
d
b
ala
n
ce
c
u
r
v
e
s
o
f
th
e
S
A
R
S
A
-
FIS
tr
ad
i
n
g
a
g
en
t
o
n
E
UR
USD
(
M1
5
)
,
d
em
o
n
s
tr
ati
n
g
h
ig
h
eq
u
i
t
y
s
tab
ilit
y
(
E
SI
=
0
.
9
6
7
2
)
Fig
u
r
e
6
.
R
o
llin
g
r
ec
o
v
er
y
r
ati
o
o
f
th
e
S
AR
S
A
-
FIS
tr
ad
i
n
g
a
g
en
t o
v
er
3
0
-
p
er
io
d
w
i
n
d
o
w
s
,
in
d
icati
n
g
t
h
e
s
y
s
te
m
’
s
ab
ilit
y
to
r
ec
o
v
er
f
r
o
m
lo
ca
l d
r
a
w
d
o
w
n
s
3
.
3
.
E
qu
it
y
beha
v
io
r
a
nd
m
a
rg
in ef
f
iciency
T
o
d
eter
m
i
n
e
w
h
et
h
er
d
ev
ia
tio
n
s
b
et
w
ee
n
eq
u
it
y
a
n
d
b
alan
ce
w
er
e
s
el
f
-
co
r
r
ec
tin
g
,
a
lag
g
ed
r
eg
r
ess
io
n
an
al
y
s
i
s
w
as p
er
f
o
r
m
ed
in
(
4
)
.
(
−
)
=
+
.
(
−
1
−
−
1
)
+
(
4
)
w
h
e
r
e
a
n
d
a
r
e
t
h
e
e
q
u
ity
an
d
b
a
l
a
n
c
e
a
t
t
im
e
,
r
e
s
p
e
c
t
iv
e
ly
.
A
n
eg
at
iv
e
a
n
d
s
ig
n
if
i
c
an
t
c
o
e
f
f
i
c
i
en
t
w
o
u
l
d
in
d
i
c
at
e
m
e
an
-
r
ev
e
r
t
in
g
b
e
h
a
v
i
o
r
,
w
h
i
l
e
a
p
o
s
it
iv
e
c
o
e
f
f
i
ci
en
t
s
u
g
g
es
ts
p
e
r
s
is
t
en
c
e
o
r
d
i
v
e
r
g
en
ce
.
T
h
e
r
e
g
r
es
s
i
o
n
y
i
e
l
d
e
d
a
c
o
ef
f
i
c
ie
n
t
=
0
.
2401
w
i
th
a
h
i
g
h
ly
s
ig
n
if
i
c
an
t
−
=
1
.
53
10
−
25
(
<
10
−
24
)
.
T
h
is
s
u
g
g
e
s
ts
a
co
n
s
er
v
at
iv
e
p
o
s
itio
n
h
o
ld
i
n
g
s
t
y
le
w
it
h
d
elay
ed
clo
s
u
r
e
o
f
f
lo
atin
g
tr
ad
es.
T
h
e
d
ep
o
s
it
lo
ad
ef
f
ic
ien
c
y
(
DL
E
)
m
etr
ic
w
a
s
i
n
tr
o
d
u
ce
d
to
ev
al
u
ate
m
ar
g
i
n
u
s
ag
e
e
f
f
i
cien
c
y
,
as
de
f
in
ed
i
n
(
5
)
.
=
∆
(
5
)
As
s
ee
n
in
Fi
g
u
r
e
7
,
DL
E
s
h
o
w
ed
s
h
ar
p
f
lu
ct
u
atio
n
s
,
w
i
th
o
cc
asio
n
al
h
i
g
h
ef
f
icie
n
c
y
f
o
llo
w
ed
b
y
d
ee
p
in
e
f
f
ic
ien
cie
s
.
T
h
is
in
d
icate
s
th
at
m
ar
g
i
n
u
tili
za
tio
n
is
r
ea
ctiv
e
r
ath
er
t
h
a
n
an
tic
i
p
ato
r
y
,
s
u
g
g
e
s
ti
n
g
t
h
e
ab
s
en
ce
o
f
f
o
r
w
ar
d
-
lo
o
k
in
g
ca
p
ital a
llo
ca
tio
n
s
tr
ate
g
ies
[
2
4
]
,
[
2
5
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1693
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
24
,
No
.
4
,
A
u
g
u
s
t
20
26
:
1
267
-
1
2
7
7
1274
Fig
u
r
e
7
.
DL
E
o
f
t
h
e
S
AR
S
A
-
FIS
tr
ad
in
g
a
g
e
n
t o
v
er
ti
m
e,
il
lu
s
tr
ati
n
g
th
e
r
elatio
n
s
h
ip
b
etw
ee
n
m
ar
g
i
n
u
tili
za
t
io
n
an
d
eq
u
i
t
y
g
ai
n
3
.
4
.
Str
uct
ura
l
cha
ng
e
det
ec
t
io
n a
nd
ev
ent
a
lig
n
m
ent
T
h
e
C
USUM
al
g
o
r
ith
m
w
a
s
ap
p
lied
to
d
etec
t
r
eg
i
m
e
s
h
i
f
t
s
in
eq
u
it
y
b
eh
a
v
io
r
,
w
h
er
e
d
ev
iatio
n
s
w
er
e
f
la
g
g
ed
o
n
ce
cu
m
u
lati
v
e
r
esid
u
als
ex
ce
ed
ed
±
2
s
tan
d
ar
d
d
ev
iatio
n
s
.
A
s
s
h
o
w
n
i
n
Fi
g
u
r
e
8
,
s
ev
er
a
l
s
tr
u
ct
u
r
al
s
h
i
f
t
s
alig
n
ed
w
it
h
m
aj
o
r
m
ac
r
o
ec
o
n
o
m
ic
ev
e
n
ts
,
in
clu
d
i
n
g
t
h
e
s
ilico
n
v
al
le
y
b
an
k
(
SVB
)
co
llap
s
e
an
d
th
e
cr
ed
it
s
u
is
s
e
ac
q
u
is
it
i
o
n
.
T
h
ese
o
b
s
er
v
atio
n
s
h
ig
h
li
g
h
t
t
h
e
a
g
en
t
’
s
s
e
n
s
iti
v
it
y
to
s
y
s
te
m
ic
v
o
latil
it
y
an
d
its
r
elev
a
n
ce
f
o
r
s
tr
ess
-
r
es
p
o
n
s
iv
e
al
g
o
r
ith
m
ic
tr
ad
i
n
g
s
y
s
te
m
s
[
1
3
]
,
[
2
0
]
.
Fig
u
r
e
8
.
C
h
a
n
g
e
p
o
in
t d
etec
ti
o
n
o
n
th
e
eq
u
i
t
y
c
u
r
v
e
u
s
i
n
g
t
h
e
C
U
SUM
al
g
o
r
ith
m
,
h
i
g
h
li
g
h
ti
n
g
r
e
g
i
m
e
s
h
if
ts
an
d
s
tr
u
ct
u
r
al
tr
an
s
itio
n
s
i
n
tr
ad
in
g
p
er
f
o
r
m
a
n
ce
3
.
5
.
Dis
cus
s
io
n
T
h
e
SA
R
S
A
-
FIS
ag
e
n
t
is
a
h
y
b
r
id
A
I
ar
ch
itectu
r
e
tailo
r
ed
f
o
r
in
ter
p
r
etab
ilit
y
an
d
ca
p
ital
d
i
s
cip
lin
e
in
h
ig
h
-
f
r
eq
u
en
c
y
f
o
r
ex
en
v
i
r
o
n
m
e
n
ts
.
W
h
i
le
th
e
b
ac
k
test
s
h
o
w
ed
a
b
alan
ce
d
w
i
n
-
lo
s
s
r
atio
an
d
m
icr
o
-
ef
f
icien
c
y
[
2
6
]
,
th
e
h
i
g
h
d
r
a
w
d
o
w
n
(
5
9
.
7
4
%)
an
d
m
o
d
est
s
h
ar
p
e
r
atio
(
0
.
5
3
)
in
d
icate
r
esil
ien
ce
li
m
its
.
T
h
is
i
s
co
n
s
is
ten
t
w
it
h
p
r
io
r
f
in
d
in
g
s
h
ig
h
li
g
h
ti
n
g
R
L
s
en
s
iti
v
it
y
to
v
o
latilit
y
a
n
d
th
e
li
m
itatio
n
s
o
f
s
tatic
f
u
zz
y
r
u
le
s
ets
[
2
7
]
,
[
2
8
]
.
T
h
e
s
y
s
te
m
m
ain
tai
n
ed
h
i
g
h
E
SI
(
0
.
9
6
7
2
)
,
v
alid
ati
n
g
lo
w
f
lo
atin
g
e
x
p
o
s
u
r
e
[
2
2
]
.
Ho
w
ev
er
,
th
e
r
o
llin
g
r
ec
o
v
er
y
r
atio
’
s
v
o
latilit
y
a
n
d
lag
g
ed
eq
u
it
y
r
e
g
r
ess
io
n
(
=
0
.
2
4
0
1
)
s
u
g
g
est
t
h
at
o
n
ce
th
e
s
y
s
te
m
en
ter
s
a
d
r
a
w
d
o
w
n
p
h
ase,
r
ec
o
v
er
y
is
n
o
t su
s
tai
n
ed
w
it
h
o
u
t
ex
ter
n
al
r
ei
n
f
o
r
ce
m
en
t.
C
o
m
p
ar
ed
w
it
h
tr
ad
itio
n
al
s
tr
ateg
ies
s
u
c
h
as
m
o
v
i
n
g
-
a
v
er
a
g
e
cr
o
s
s
o
v
er
s
,
buy
-
an
d
-
h
o
ld
a
p
p
r
o
ac
h
es,
an
d
s
ta
n
d
alo
n
e
f
u
zz
y
s
y
s
te
m
s
,
th
e
S
AR
S
A
-
FIS
a
g
en
t
d
e
m
o
n
s
tr
ated
m
o
r
e
s
tab
le
tr
ad
in
g
b
eh
av
io
r
a
n
d
clea
r
er
d
ec
is
io
n
lo
g
ic
ac
r
o
s
s
v
ar
y
i
n
g
m
ar
k
et
r
e
g
i
m
es
[
2
4
]
,
[
2
6
]
.
B
a
s
elin
e
m
o
d
els
d
ep
en
d
o
n
f
i
x
ed
r
u
les
th
at
o
f
ten
f
ai
l
to
ad
ap
t
w
h
e
n
v
o
latilit
y
in
cr
e
ases
o
r
s
tr
u
ctu
r
al
co
n
d
itio
n
s
ch
an
g
e
[
2
5
]
.
I
n
co
n
tr
ast,
th
e
h
y
b
r
id
S
A
R
S
A
-
FIS
f
r
a
m
e
w
o
r
k
co
m
b
i
n
es
ad
ap
ti
v
e
f
ee
d
b
ac
k
f
r
o
m
RL
w
it
h
t
h
e
i
n
ter
p
r
etab
ilit
y
o
f
f
u
zz
y
i
n
f
er
en
ce
[
1
5
]
,
r
e
s
u
l
t
in
g
i
n
s
m
o
o
t
h
e
r
t
r
a
d
e
c
o
n
t
in
u
i
ty
,
im
p
r
o
v
e
d
r
es
p
o
n
s
iv
en
es
s
t
o
r
eg
im
e
s
h
if
ts
,
an
d
g
r
e
at
e
r
d
e
ci
s
i
o
n
tr
a
n
s
p
a
r
e
n
cy
.
T
h
e
s
e
f
in
d
in
g
s
d
em
o
n
s
t
r
a
te
th
a
t
th
e
SA
R
SA
-
F
I
S
f
r
am
e
w
o
r
k
p
r
o
v
id
e
s
a
m
o
r
e
s
t
a
b
l
e
an
d
i
n
t
e
r
p
r
e
t
a
b
l
e
a
lt
e
r
n
a
t
iv
e
t
o
c
o
n
v
en
t
i
o
n
a
l
r
u
l
e
-
b
a
s
e
d
s
t
r
a
te
g
i
e
s
,
p
a
r
ti
cu
l
a
r
ly
u
n
d
e
r
v
a
r
y
in
g
m
a
r
k
e
t
r
eg
im
e
s
[
1
3
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
A
d
a
p
tive
tr
a
d
in
g
s
ystem
fo
r
s
u
s
ta
in
a
b
le
fo
r
ex
ma
r
ke
ts
(
Jo
n
i F
a
t
)
1275
DL
E
an
a
l
y
s
is
f
u
r
t
h
er
ex
p
o
s
e
d
in
co
n
s
i
s
ten
c
y
i
n
ca
p
ital
ef
f
icie
n
c
y
.
Sp
i
k
es
o
f
e
f
f
ec
ti
v
e
n
es
s
w
er
e
f
o
llo
w
ed
b
y
d
ee
p
in
ef
f
icien
c
i
es,
in
d
icatin
g
r
ea
ctiv
e
r
is
k
d
e
p
lo
y
m
e
n
t
r
ath
er
th
an
an
ticip
a
to
r
y
b
eh
a
v
io
r
[
2
4
]
,
[
2
5
]
.
T
h
ese
g
ap
s
r
ef
lect
t
h
e
n
ee
d
f
o
r
ad
ap
tiv
e
m
ar
g
i
n
co
n
tr
o
l,
r
ea
l
-
ti
m
e
v
o
latilit
y
as
s
e
s
s
m
en
t,
an
d
r
e
w
ar
d
s
h
ap
i
n
g
m
ec
h
a
n
is
m
s
a
lig
n
ed
w
i
th
m
ar
k
et
r
eg
i
m
e
s
[
2
3
]
,
[
2
9
]
.
Stru
ctu
r
al
b
r
ea
k
d
ete
ctio
n
v
ia
C
U
SUM
co
n
f
ir
m
ed
s
tr
o
n
g
co
r
r
elatio
n
s
b
et
w
ee
n
m
ac
r
o
ec
o
n
o
m
ic
s
h
o
c
k
s
a
n
d
eq
u
it
y
i
n
f
lectio
n
p
o
i
n
t
s
.
T
h
is
ali
g
n
s
w
it
h
p
r
io
r
w
o
r
k
o
n
th
e
v
u
l
n
er
ab
ilit
y
o
f
r
u
le
-
b
ased
ag
e
n
ts
to
s
y
s
te
m
ic
e
v
e
n
ts
[
1
]
,
an
d
s
u
p
p
o
r
ts
th
e
ca
s
e
f
o
r
e
m
b
ed
d
in
g
r
e
g
i
m
e
-
a
w
ar
en
e
s
s
in
to
al
g
o
r
ith
m
ic
s
y
s
te
m
s
.
T
h
ese
f
i
n
d
i
n
g
s
co
n
f
ir
m
t
h
at
t
h
e
S
A
R
S
A
-
FIS
a
g
en
t
p
r
o
v
id
es
a
s
tr
u
ctu
r
all
y
s
tab
le
an
d
ex
p
lain
ab
le
tr
ad
in
g
f
r
a
m
e
w
o
r
k
ali
g
n
ed
w
i
th
r
esp
o
n
s
ib
le
A
I
p
r
in
cip
les
[
2
1
]
.
Ho
w
e
v
er
,
en
h
an
ci
n
g
r
o
b
u
s
t
n
e
s
s
u
n
d
er
v
o
latile
co
n
d
itio
n
s
r
eq
u
ir
es
th
e
i
n
te
g
r
atio
n
o
f
v
o
l
a
tili
t
y
-
a
w
ar
e
p
o
lic
y
ad
ap
tatio
n
,
d
y
n
a
m
ic
e
x
it
s
tr
at
eg
ies,
an
d
r
ea
l
-
ti
m
e
d
r
a
w
d
o
wn
co
n
tr
o
l
m
ec
h
a
n
i
s
m
s
.
T
h
is
s
tu
d
y
d
e
m
o
n
s
tr
ate
s
th
at
s
u
s
tai
n
ab
le
alg
o
r
it
h
m
ic
tr
ad
in
g
is
n
o
t
s
o
lel
y
d
ef
i
n
ed
b
y
p
r
o
f
itab
ilit
y
,
b
u
t
b
y
s
tab
ilit
y
,
tr
an
s
p
ar
en
c
y
,
a
n
d
co
n
tr
o
lled
r
is
k
ex
p
o
s
u
r
e
u
n
d
er
d
y
n
a
m
ic
m
ar
k
et
co
n
d
itio
n
s
.
4.
CO
NCLU
SI
O
N
T
h
i
s
s
tu
d
y
d
ev
el
o
p
e
d
a
n
d
t
e
s
te
d
a
h
y
b
r
i
d
SA
R
SA
-
F
I
S
a
lg
o
r
i
t
h
m
ic
t
r
a
d
i
n
g
s
y
s
t
em
f
o
r
th
e
E
U
R
U
SD
c
u
r
r
en
cy
p
a
i
r
,
w
h
i
ch
m
e
t
tw
o
k
ey
o
b
je
c
t
iv
es
:
a
d
a
p
ta
b
i
l
ity
an
d
in
t
e
r
p
r
e
t
a
b
i
l
ity
.
T
h
e
m
o
d
e
l
i
n
t
eg
r
at
e
s
RL
w
ith
fu
z
zy
l
o
g
i
c
t
o
o
v
e
r
c
o
m
e
th
e
lim
it
a
t
i
o
n
s
o
f
c
o
n
v
en
ti
o
n
al
r
u
l
e
-
b
a
s
e
d
an
d
p
u
r
e
ly
l
e
a
r
n
in
g
-
b
as
ed
s
t
r
at
eg
i
es
in
h
ig
h
-
f
r
e
q
u
en
cy
f
o
r
ex
en
v
i
r
o
n
m
en
ts
.
I
t
al
s
o
r
e
s
p
o
n
d
s
t
o
th
e
in
c
r
e
a
s
i
n
g
d
em
an
d
f
o
r
r
es
p
o
n
s
i
b
l
e
an
d
s
u
s
t
a
in
a
b
l
e
A
I
in
f
in
an
ci
a
l
s
y
s
t
em
s
.
T
h
e
SA
R
SA
-
F
I
S
ag
e
n
t
,
t
r
ain
e
d
o
n
M
1
5
d
a
t
a
(
2
0
2
0
–
2
0
2
3
)
a
n
d
t
e
s
t
e
d
o
n
2
0
2
4
,
a
c
h
i
ev
e
d
m
o
d
e
r
a
t
e
p
r
o
f
i
t
a
b
il
i
ty
(
p
r
o
f
it
f
a
ct
o
r
=
1
.
0
4
)
,
s
t
r
o
n
g
e
q
u
i
ty
s
t
a
b
i
l
ity
(
E
S
I
=
0
.
9
6
7
2
)
,
a
n
d
b
a
l
a
n
c
e
d
t
r
a
d
in
g
o
u
t
c
o
m
es
.
C
US
U
M
an
a
ly
s
i
s
f
u
r
t
h
e
r
d
em
o
n
s
t
r
a
te
d
th
e
m
o
d
el
’
s
s
en
s
i
t
iv
i
ty
t
o
m
a
c
r
o
e
c
o
n
o
m
i
c
e
v
en
ts
,
c
o
n
f
i
r
m
in
g
t
h
at
t
h
e
a
g
en
t
c
an
a
d
a
p
t
t
o
ev
o
l
v
in
g
m
a
r
k
e
t
d
y
n
am
ic
s
.
H
o
w
e
v
e
r
,
a
s
ig
n
if
i
c
an
t
m
ax
im
u
m
d
r
aw
d
o
w
n
(
5
9
.
7
4
%
)
a
n
d
l
im
it
e
d
r
e
c
o
v
e
r
y
b
eh
av
i
o
r
r
e
v
e
al
e
d
ch
a
l
l
en
g
es
in
m
ai
n
t
a
in
in
g
r
o
b
u
s
tn
es
s
u
n
d
e
r
v
o
l
a
ti
l
e
c
o
n
d
i
ti
o
n
s
.
T
h
ese
f
in
d
i
n
g
s
co
n
f
ir
m
t
h
at
in
te
g
r
atin
g
f
u
zz
y
lo
g
ic
w
it
h
RL
e
n
h
an
ce
s
ex
p
lai
n
ab
ilit
y
a
n
d
alig
n
s
alg
o
r
ith
m
ic
tr
ad
in
g
s
y
s
te
m
s
w
it
h
r
esp
o
n
s
ib
le
A
I
p
r
in
cip
l
es.
T
h
e
p
r
o
p
o
s
ed
f
r
a
m
e
w
o
r
k
d
em
o
n
s
tr
ates
t
h
at
tr
an
s
p
ar
en
c
y
an
d
ad
ap
tab
ilit
y
ca
n
co
ex
i
s
t
w
it
h
i
n
a
r
ep
r
o
d
u
ci
b
le,
r
eg
u
latio
n
-
ali
g
n
ed
tr
ad
in
g
e
n
v
ir
o
n
m
en
t
,
s
u
p
p
o
r
tin
g
eth
ical
co
m
p
l
ian
ce
an
d
s
u
s
tain
ab
le
f
in
a
n
cial
d
ec
is
io
n
-
m
ak
i
n
g
.
Fro
m
a
p
r
ac
tical
p
er
s
p
ec
tiv
e,
s
u
c
h
a
s
y
s
te
m
ca
n
ass
is
t
tr
ad
er
s
,
an
al
y
s
ts
,
an
d
r
eg
u
lato
r
s
i
n
ev
al
u
ati
n
g
au
to
m
ated
d
ec
is
io
n
s
,
i
m
p
r
o
v
i
n
g
au
d
i
tab
ilit
y
,
a
n
d
en
s
u
r
in
g
ad
h
er
en
ce
to
g
o
v
er
n
a
n
ce
s
tan
d
a
r
d
s
.
Fu
t
u
r
e
r
esear
ch
s
h
o
u
ld
f
o
cu
s
o
n
e
n
h
a
n
ci
n
g
r
o
b
u
s
tn
es
s
u
n
d
er
v
o
latile
co
n
d
itio
n
s
t
h
r
o
u
g
h
v
o
latili
t
y
-
s
en
s
itiv
e
r
e
w
ar
d
f
u
n
ctio
n
s
,
ad
ap
tiv
e
ex
it
m
ec
h
a
n
i
s
m
s
,
an
d
r
ea
l
-
ti
m
e
r
eg
i
m
e
d
etec
tio
n
.
E
x
p
an
d
i
n
g
t
h
i
s
f
r
a
m
e
w
o
r
k
to
w
ar
d
d
y
n
a
m
ic
ca
p
ital
m
an
a
g
e
m
e
n
t,
tr
an
s
ac
tio
n
co
s
t
o
p
ti
m
izatio
n
,
a
n
d
m
u
lti
-
ag
en
t
co
o
r
d
in
atio
n
m
a
y
f
u
r
t
h
er
i
m
p
r
o
v
e
p
er
f
o
r
m
an
ce
s
tab
i
lit
y
,
s
ca
lab
il
it
y
,
a
n
d
ca
p
ital
ef
f
icie
n
c
y
ac
r
o
s
s
d
iv
er
s
if
ied
f
i
n
a
n
cial
en
v
ir
o
n
m
en
ts
.
T
h
is
r
esear
ch
co
n
tr
ib
u
tes
to
th
e
ad
v
an
ce
m
en
t
o
f
s
u
s
tai
n
ab
le,
in
ter
p
r
etab
le,
an
d
eth
ical
A
I
s
y
s
te
m
s
f
o
r
f
o
r
ex
tr
ad
in
g
an
d
b
r
o
ad
er
f
in
an
cial
ap
p
licatio
n
s
.
Ov
er
all,
t
h
is
r
esear
c
h
co
n
tr
ib
u
tes
to
th
e
ad
v
an
ce
m
e
n
t
o
f
s
u
s
t
ain
ab
le,
in
ter
p
r
etab
le,
an
d
et
h
i
ca
l
A
I
s
y
s
te
m
s
f
o
r
f
o
r
ex
tr
ad
in
g
a
n
d
b
r
o
ad
e
r
f
in
an
cial
ap
p
licatio
n
s
,
r
ein
f
o
r
cin
g
th
e
in
te
g
r
atio
n
o
f
r
esp
o
n
s
ib
le
A
I
p
r
in
cip
les
in
to
th
e
d
esi
g
n
o
f
i
n
tel
lig
e
n
t
f
i
n
an
c
ial
tech
n
o
lo
g
ies
.
F
UNDIN
G
I
NF
O
RM
AT
I
O
N
Au
t
h
o
r
s
s
tate
n
o
f
u
n
d
i
n
g
i
n
v
o
l
v
ed
.
AUTHO
R
CO
NT
RIB
UT
I
O
NS ST
A
T
E
M
E
NT
T
h
is
j
o
u
r
n
al
u
s
e
s
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
i
v
id
u
al
au
th
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
t
h
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
lla
b
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
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
P
ar
w
ad
i M
o
en
g
i
n
✓
✓
✓
✓
✓
✓
✓
✓
✓
P
u
d
j
i A
s
tu
t
i
✓
✓
✓
✓
✓
✓
✓
✓
Sall
y
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
si
s
I
:
I
n
v
e
st
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
si
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
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1693
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
24
,
No
.
4
,
A
u
g
u
s
t
20
26
:
1
267
-
1
2
7
7
1276
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
Au
t
h
o
r
s
s
tate
n
o
co
n
f
lic
t o
f
i
n
t
er
est.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
ata
th
at
s
u
p
p
o
r
t
th
e
f
in
d
in
g
s
o
f
th
i
s
s
t
u
d
y
ar
e
av
aila
b
le
f
r
o
m
t
h
e
co
r
r
esp
o
n
d
in
g
a
u
th
o
r
,
P
M,
u
p
o
n
r
ea
s
o
n
ab
le
r
eq
u
est.
T
h
e
d
ataset
is
p
ar
t
o
f
an
o
n
g
o
in
g
d
i
s
s
er
tatio
n
p
r
o
j
ec
t
an
d
is
cu
r
r
en
t
l
y
u
n
d
er
co
n
s
id
er
atio
n
f
o
r
p
aten
t
p
r
o
tectio
n
.
P
a
r
tial
d
ata
a
n
d
r
ep
r
o
d
u
cib
le
m
ater
ials
ar
e
av
ailab
le
at
h
ttp
s
:/
/g
i
th
u
b
.
co
m
/j
o
n
if
a
t/S
AR
S
A
-
FIS
-
S
u
s
tai
n
ab
le
-
T
r
ad
in
g
-
Fra
m
e
w
o
r
k
.
RE
F
E
R
E
NC
E
S
[
1
]
A
.
L
.
A
w
a
d
,
S
.
M
.
El
k
a
f
f
a
s
,
a
n
d
M
.
W
.
F
a
k
h
r
,
“
S
t
o
c
k
M
a
r
k
e
t
P
r
e
d
i
c
t
i
o
n
U
si
n
g
D
e
e
p
R
e
i
n
f
o
r
c
e
me
n
t
L
e
a
r
n
i
n
g
,
”
A
p
p
l
i
e
d
S
y
s
t
e
m
I
n
n
o
v
a
t
i
o
n
,
v
o
l
.
6
,
n
o
.
6
,
N
o
v
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
a
s
i
6
0
6
0
1
0
6
.
[
2
]
J.
F
a
t
,
P
.
M
o
e
n
g
i
n
,
P
.
A
st
u
t
i
,
a
n
d
S
.
C
a
h
y
a
t
i
,
“
S
u
st
a
i
n
a
b
i
l
i
t
y
i
n
F
o
r
e
x
Tr
a
d
i
n
g
:
a
R
e
v
i
e
w
i
n
S
e
a
r
c
h
o
f
T
h
e
S
A
R
S
A
-
F
I
S
H
y
b
r
i
d
M
e
t
h
o
d
a
s
a
N
o
v
e
l
t
y
,
”
Bu
l
l
e
t
i
n
o
f
Mo
n
e
t
a
r
y
Ec
o
n
o
m
i
c
s
a
n
d
B
a
n
k
i
n
g
,
v
o
l
.
2
8
,
p
p
.
7
1
–
9
4
,
F
e
b
.
2
0
2
5
,
d
o
i
:
1
0
.
5
9
0
9
1
/
2
4
6
0
-
9
1
9
6
.
2
3
6
9
.
[
3
]
M
.
K
h
u
sh
i
a
n
d
T
.
L
.
M
e
n
g
,
“
R
e
i
n
f
o
r
c
e
me
n
t
l
e
a
r
n
i
n
g
i
n
f
i
n
a
n
c
i
a
l
mar
k
e
t
s,
”
D
a
t
a
,
v
o
l
.
4
,
n
o
.
3
,
2
0
1
9
,
d
o
i
:
1
0
.
3
3
9
0
/
d
a
t
a
4
0
3
0
1
1
0
.
[
4
]
A
.
M
.
O
z
b
a
y
o
g
l
u
,
M
.
U
.
G
u
d
e
l
e
k
,
a
n
d
O
.
B
.
S
e
z
e
r
,
“
D
e
e
p
l
e
a
r
n
i
n
g
f
o
r
f
i
n
a
n
c
i
a
l
a
p
p
l
i
c
a
t
i
o
n
s:
A
su
r
v
e
y
,
”
Ap
p
l
i
e
d
S
o
f
t
C
o
m
p
u
t
i
n
g
J
o
u
rn
a
l
,
v
o
l
.
9
3
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
so
c
.
2
0
2
0
.
1
0
6
3
8
4
.
[
5
]
A
.
A
d
e
g
b
o
y
e
a
n
d
M
.
K
a
mp
o
u
r
i
d
i
s,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
c
l
a
ssi
f
i
c
a
t
i
o
n
a
n
d
r
e
g
r
e
ssi
o
n
mo
d
e
l
s
f
o
r
p
r
e
d
i
c
t
i
n
g
d
i
r
e
c
t
i
o
n
a
l
c
h
a
n
g
e
s
t
r
e
n
d
r
e
v
e
r
sal
i
n
F
X
mark
e
t
s
,
”
Ex
p
e
r
t
S
y
s
t
e
m
s
w
i
t
h
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
7
3
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
sw
a
.
2
0
2
1
.
1
1
4
6
4
5
.
[
6
]
J.
S
h
a
h
,
D
.
V
a
i
d
y
a
,
a
n
d
M
.
S
h
a
h
,
“
A
c
o
mp
r
e
h
e
n
s
i
v
e
r
e
v
i
e
w
o
n
mu
l
t
i
p
l
e
h
y
b
r
i
d
d
e
e
p
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
e
s
f
o
r
st
o
c
k
p
r
e
d
i
c
t
i
o
n
,
”
I
n
t
e
l
l
i
g
e
n
t
S
y
s
t
e
m
s
w
i
t
h
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
6
,
p
.
2
0
0
1
1
1
,
N
o
v
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
sw
a
.
2
0
2
2
.
2
0
0
1
1
1
.
[
7
]
K
.
S
a
k
o
,
B
.
N
.
M
p
i
n
d
a
,
a
n
d
P
.
C
.
R
o
d
r
i
g
u
e
s,
“
N
e
u
r
a
l
N
e
t
w
o
r
k
s
f
o
r
F
i
n
a
n
c
i
a
l
T
i
me
S
e
r
i
e
s
F
o
r
e
c
a
st
i
n
g
,
”
E
n
t
r
o
p
y
,
v
o
l
.
2
4
,
n
o
.
5
,
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
e
2
4
0
5
0
6
5
7
.
[
8
]
K
.
Y
a
n
,
Y
.
W
a
n
g
,
a
n
d
Y
.
L
i
,
“
En
h
a
n
c
e
d
B
o
l
l
i
n
g
e
r
B
a
n
d
S
t
o
c
k
Q
u
a
n
t
i
t
a
t
i
v
e
T
r
a
d
i
n
g
S
t
r
a
t
e
g
y
B
a
se
d
o
n
R
a
n
d
o
m Fo
r
e
st
,
”
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
Ev
o
l
u
t
i
on
,
p
p
.
2
2
–
3
3
,
2
0
2
3
,
d
o
i
:
1
0
.
3
7
2
5
6
/
a
i
e
.
4
1
2
0
2
3
1
9
9
1
.
[
9
]
I
.
M
u
r
t
z
a
,
A
.
S
a
a
d
i
a
,
R
.
B
a
sr
i
,
A
.
I
mr
a
n
,
A
.
A
l
mu
h
a
i
me
e
d
,
a
n
d
A
.
A
l
z
a
h
r
a
n
i
,
“
F
o
r
e
x
I
n
v
e
st
me
n
t
O
p
t
i
mi
z
a
t
i
o
n
U
si
n
g
I
n
st
a
n
t
a
n
e
o
u
s
S
t
o
c
h
a
s
t
i
c
G
r
a
d
i
e
n
t
A
sce
n
t
—
F
o
r
mu
l
a
t
i
o
n
o
f
a
n
A
d
a
p
t
i
v
e
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
A
p
p
r
o
a
c
h
,
”
S
u
s
t
a
i
n
a
b
i
l
i
t
y
(
S
w
i
t
zer
l
a
n
d
)
,
v
o
l
.
1
4
,
n
o
.
2
2
,
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
su
1
4
2
2
1
5
3
2
8
.
[
1
0
]
D
.
K
.
S
h
a
r
ma,
H
.
S
.
H
o
t
a
,
K
.
B
r
o
w
n
,
a
n
d
R
.
H
a
n
d
a
,
“
I
n
t
e
g
r
a
t
i
o
n
o
f
g
e
n
e
t
i
c
a
l
g
o
r
i
t
h
m
w
i
t
h
a
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
f
o
r
st
o
c
k
mark
e
t
f
o
r
e
c
a
st
i
n
g
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
S
y
st
e
m
Ass
u
r
a
n
c
e
E
n
g
i
n
e
e
ri
n
g
a
n
d
M
a
n
a
g
e
m
e
n
t
,
v
o
l
.
1
3
,
n
o
.
S
2
,
p
p
.
8
2
8
–
8
4
1
,
J
u
n
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
3
1
9
8
-
0
2
1
-
0
1
2
0
9
-
5.
[
1
1
]
M
.
S
o
o
r
i
,
B
.
A
r
e
z
o
o
,
a
n
d
R
.
D
a
st
r
e
s,
“
A
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
,
mac
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
i
n
a
d
v
a
n
c
e
d
r
o
b
o
t
i
c
s,
a
r
e
v
i
e
w
,
”
C
o
g
n
i
t
i
v
e
R
o
b
o
t
i
c
s
,
v
o
l
.
3
,
p
p
.
5
4
–
7
0
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
g
r
.
2
0
2
3
.
0
4
.
0
0
1
.
[
1
2
]
M
.
W
.
K
l
e
e
sp
i
e
s
a
n
d
P
.
W
.
D
i
e
r
k
e
s,
“
T
h
e
i
mp
o
r
t
a
n
c
e
o
f
t
h
e
S
u
st
a
i
n
a
b
l
e
D
e
v
e
l
o
p
me
n
t
G
o
a
l
s
t
o
st
u
d
e
n
t
s
o
f
e
n
v
i
r
o
n
me
n
t
a
l
a
n
d
su
st
a
i
n
a
b
i
l
i
t
y
st
u
d
i
e
s
—
a
g
l
o
b
a
l
su
r
v
e
y
i
n
4
1
c
o
u
n
t
r
i
e
s,”
H
u
m
a
n
i
t
i
e
s
a
n
d
S
o
c
i
a
l
S
c
i
e
n
c
e
s
C
o
m
m
u
n
i
c
a
t
i
o
n
s
,
v
o
l
.
9
,
n
o
.
1
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
5
7
/
s
4
1
5
9
9
-
022
-
0
1
2
4
2
-
0.
[
1
3
]
C
.
A
.
R
u
g
g
e
r
i
o
,
“
S
u
st
a
i
n
a
b
i
l
i
t
y
a
n
d
su
s
t
a
i
n
a
b
l
e
d
e
v
e
l
o
p
me
n
t
:
A
r
e
v
i
e
w
o
f
p
r
i
n
c
i
p
l
e
s
a
n
d
d
e
f
i
n
i
t
i
o
n
s,
”
S
c
i
e
n
c
e
o
f
t
h
e
T
o
t
a
l
En
v
i
r
o
n
m
e
n
t
,
v
o
l
.
7
8
6
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
sc
i
t
o
t
e
n
v
.
2
0
2
1
.
1
4
7
4
8
1
.
[
1
4
]
A
.
A
d
e
g
b
o
y
e
,
M
.
K
a
mp
o
u
r
i
d
i
s,
a
n
d
F
.
O
t
e
r
o
,
“
A
l
g
o
r
i
t
h
m
i
c
t
r
a
d
i
n
g
w
i
t
h
d
i
r
e
c
t
i
o
n
a
l
c
h
a
n
g
e
s,”
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
Re
v
i
e
w
,
v
o
l
.
5
6
,
n
o
.
6
,
p
p
.
5
6
1
9
–
5
6
4
4
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
0
4
6
2
-
0
2
2
-
1
0
3
0
7
-
0.
[
1
5
]
A
.
C
i
a
c
c
i
,
T
.
S
u
e
sh
i
g
e
,
H
.
T
a
k
a
y
a
su
,
K
.
C
h
r
i
s
t
e
n
se
n
,
a
n
d
M
.
T
a
k
a
y
a
su
,
“
T
h
e
mi
c
r
o
sco
p
i
c
r
e
l
a
t
i
o
n
s
h
i
p
s
b
e
t
w
e
e
n
t
r
i
a
n
g
u
l
a
r
a
r
b
i
t
r
a
g
e
a
n
d
c
r
o
ss
-
c
u
r
r
e
n
c
y
c
o
r
r
e
l
a
t
i
o
n
s
i
n
a
s
i
m
p
l
e
a
g
e
n
t
b
a
se
d
mo
d
e
l
o
f
f
o
r
e
i
g
n
e
x
c
h
a
n
g
e
mar
k
e
t
s,”
PL
o
S
O
N
E
,
v
o
l
.
1
5
,
n
o
.
6
,
2
0
2
0
,
d
o
i
:
1
0
.
1
3
7
1
/
j
o
u
r
n
a
l
.
p
o
n
e
.
0
2
3
4
7
0
9
.
[
1
6
]
J.
F
a
t
,
H
.
S
.
U
t
a
ma
,
H
.
C
a
n
d
r
a
,
W
.
A
.
P
r
a
n
o
t
o
,
A
.
I
.
Y
o
sh
u
a
,
a
n
d
T
.
C
.
G
i
l
b
e
r
t
,
“
D
e
sai
n
A
l
g
o
r
i
t
ma
D
a
n
I
m
p
l
e
me
n
t
a
si
R
o
b
o
t
T
r
a
d
i
n
g
F
o
r
e
x
H
e
d
g
i
n
g
D
a
n
A
v
e
r
a
g
i
n
g
,
”
J
u
rn
a
l
M
u
a
ra
S
a
i
n
s
,
T
e
k
n
o
l
o
g
i
,
K
e
d
o
k
t
e
ra
n
d
a
n
I
l
m
u
K
e
se
h
a
t
a
n
,
v
o
l
.
7
,
n
o
.
2
,
p
p
.
1
1
5
–
1
2
2
,
2
0
2
3
,
d
o
i
:
1
0
.
2
4
9
1
2
/
j
mst
k
i
k
.
v
7
i
2
.
2
9
0
8
9
.
[
1
7
]
B
.
G
r
e
e
n
,
“
T
h
e
f
l
a
w
s
o
f
p
o
l
i
c
i
e
s
r
e
q
u
i
r
i
n
g
h
u
m
a
n
o
v
e
r
si
g
h
t
o
f
g
o
v
e
r
n
me
n
t
a
l
g
o
r
i
t
h
ms,
”
C
o
m
p
u
t
e
r
L
a
w
a
n
d
S
e
c
u
ri
t
y
R
e
v
i
e
w
,
v
o
l
.
4
5
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
l
sr
.
2
0
2
2
.
1
0
5
6
8
1
.
[
1
8
]
D
.
P
e
t
e
r
s,
K
.
V
o
l
d
,
D
.
R
o
b
i
n
so
n
,
a
n
d
R
.
A
.
C
a
l
v
o
,
“
R
e
sp
o
n
si
b
l
e
A
I
—
Tw
o
f
r
a
mew
o
r
k
s
f
o
r
e
t
h
i
c
a
l
d
e
si
g
n
p
r
a
c
t
i
c
e
,
”
I
EE
E
T
ra
n
s
a
c
t
i
o
n
s
o
n
T
e
c
h
n
o
l
o
g
y
a
n
d
S
o
c
i
e
t
y
,
v
o
l
.
1
,
n
o
.
1
,
p
p
.
3
4
–
4
7
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
T
T
S
.
2
0
2
0
.
2
9
7
4
9
9
1
.
[
1
9
]
R
.
V
e
r
d
e
c
c
h
i
a
,
J.
S
a
l
l
o
u
,
a
n
d
L
.
C
r
u
z
,
“
A
S
y
st
e
mat
i
c
R
e
v
i
e
w
o
f
G
r
e
e
n
A
I
,
”
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
2
0
2
3
,
d
o
i
:
1
0
.
4
8
5
5
0
/
A
R
X
I
V
.
2
3
0
1
.
1
1
0
4
7
.
[
20]
B
.
H
a
y
o
a
n
d
K
.
I
w
a
t
su
b
o
,
“
W
h
o
I
s
S
u
c
c
e
ssf
u
l
i
n
F
o
r
e
i
g
n
Ex
c
h
a
n
g
e
M
a
r
g
i
n
T
r
a
d
i
n
g
?
N
e
w
S
u
r
v
e
y
Ev
i
d
e
n
c
e
f
r
o
m
Ja
p
a
n
,
”
S
u
s
t
a
i
n
a
b
i
l
i
t
y
(
S
w
i
t
zer
l
a
n
d
)
,
v
o
l
.
1
4
,
n
o
.
1
8
,
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
su
1
4
1
8
1
1
6
6
2
.
[
2
1
]
C
.
M
i
l
a
n
a
a
n
d
A
.
A
sh
t
a
,
“
A
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
t
e
c
h
n
i
q
u
e
s
i
n
f
i
n
a
n
c
e
a
n
d
f
i
n
a
n
c
i
a
l
m
a
r
k
e
t
s:
A
su
r
v
e
y
o
f
t
h
e
l
i
t
e
r
a
t
u
r
e
,
”
S
t
r
a
t
e
g
i
c
C
h
a
n
g
e
,
v
o
l
.
3
0
,
n
o
.
3
,
p
p
.
1
8
9
–
2
0
9
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
0
2
/
j
s
c
.
2
4
0
3
.
[
2
2
]
A
.
B
i
g
i
o
t
t
i
a
n
d
A
.
N
a
v
a
r
r
a
,
“
O
p
t
i
m
i
z
i
n
g
a
u
t
o
ma
t
e
d
t
r
a
d
i
n
g
sy
st
e
ms,”
Ad
v
a
n
c
e
s
i
n
I
n
t
e
l
l
i
g
e
n
t
S
y
s
t
e
m
s
a
n
d
C
o
m
p
u
t
i
n
g
,
v
o
l
.
8
5
0
,
p
p
.
2
5
4
–
2
6
1
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
0
3
0
-
0
2
3
5
1
-
5
_
3
0
.
[
2
3
]
Y
.
Q
i
u
,
Y
.
Q
i
u
,
Y
.
Y
u
a
n
,
Z
.
C
h
e
n
,
a
n
d
R
.
L
e
e
,
“
Q
F
-
Tr
a
d
e
r
N
e
t
:
I
n
t
r
a
d
a
y
T
r
a
d
i
n
g
v
i
a
D
e
e
p
R
e
i
n
f
o
r
c
e
me
n
t
W
i
t
h
Q
u
a
n
t
u
m
P
r
i
c
e
L
e
v
e
l
s B
a
se
d
P
r
o
f
i
t
-
A
n
d
-
L
o
ss C
o
n
t
r
o
l
,
”
Fr
o
n
t
i
e
rs i
n
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
4
,
2
0
2
1
,
d
o
i
:
1
0
.
3
3
8
9
/
f
r
a
i
.
2
0
2
1
.
7
4
9
8
7
8
.
[
2
4
]
S
.
B
o
r
o
v
k
o
v
a
a
n
d
I
.
T
si
a
mas,
“
A
n
e
n
se
mb
l
e
o
f
L
S
T
M
n
e
u
r
a
l
n
e
t
w
o
r
k
s fo
r
h
i
g
h
-
f
r
e
q
u
e
n
c
y
st
o
c
k
mark
e
t
c
l
a
ssi
f
i
c
a
t
i
o
n
,
”
J
o
u
r
n
a
l
o
f
Fo
re
c
a
st
i
n
g
,
v
o
l
.
3
8
,
n
o
.
6
,
p
p
.
6
0
0
–
6
1
9
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
0
2
/
f
o
r
.
2
5
8
5
.
[
2
5
]
A
.
S
a
f
a
r
i
a
n
d
M
.
D
a
v
a
l
l
o
u
,
“
O
i
l
p
r
i
c
e
f
o
r
e
c
a
st
i
n
g
u
s
i
n
g
a
h
y
b
r
i
d
mo
d
e
l
,
”
En
e
rg
y
,
v
o
l
.
1
4
8
,
p
p
.
4
9
–
5
8
,
2
0
1
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
n
e
r
g
y
.
2
0
1
8
.
0
1
.
0
0
7
.
[
2
6
]
M
.
Y
a
ma
d
a
a
n
d
T
.
I
t
o
,
“
P
r
i
c
e
d
i
s
c
o
v
e
r
y
a
n
d
l
i
q
u
i
d
i
t
y
r
e
c
o
v
e
r
y
:
F
o
r
e
x
mark
e
t
r
e
a
c
t
i
o
n
s
t
o
ma
c
r
o
a
n
n
o
u
n
c
e
me
n
t
s,”
J
o
u
r
n
a
l
o
f
I
n
t
e
r
n
a
t
i
o
n
a
l
M
o
n
e
y
a
n
d
Fi
n
a
n
c
e
,
v
o
l
.
1
2
0
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
i
mo
n
f
i
n
.
2
0
2
1
.
1
0
2
5
0
2
.
[
2
7
]
Z
.
H
u
,
Y
.
Z
h
a
o
,
a
n
d
M
.
K
h
u
s
h
i
,
“
A
su
r
v
e
y
o
f
f
o
r
e
x
a
n
d
s
t
o
c
k
p
r
i
c
e
p
r
e
d
i
c
t
i
o
n
u
si
n
g
d
e
e
p
l
e
a
r
n
i
n
g
,
”
Ap
p
l
i
e
d
S
y
st
e
m
I
n
n
o
v
a
t
i
o
n
,
v
o
l
.
4
,
n
o
.
1
,
p
p
.
1
–
3
0
,
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
A
S
I
4
0
1
0
0
0
9
.
Evaluation Warning : The document was created with Spire.PDF for Python.