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.
15
,
No
.
2
,
A
p
r
il
20
25
,
p
p
.
2
2
5
4
~
2
2
6
3
I
SS
N:
2088
-
8
7
0
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijece.
v
15
i
2
.
pp
2
2
5
4
-
2
2
6
3
2254
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
Integ
ra
ting deep
l
ea
rning
and o
pti
miza
tion a
lg
o
rithms to
foreca
st real
-
time
stock pri
ces for
i
ntrada
y
t
ra
ders
Nilesh
B
.
K
o
ra
de
1
,
M
a
hend
r
a
B
.
Sa
lun
k
e
2
,
Am
o
l A
.
B
ho
s
le
3
,
Dha
na
s
hri J
o
s
hi
1
,
K
a
v
it
a
P
a
t
il
4
,
Su
nil
M
.
Sa
ng
v
e
5
,
Rus
ha
li A
.
Deshm
uk
h
1
,
Apa
rna
S.
P
a
t
i
l
1
1
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
En
g
i
n
e
e
r
i
n
g
,
JS
P
M
’
s
R
a
j
a
r
sh
i
S
h
a
h
u
C
o
l
l
e
g
e
o
f
En
g
i
n
e
e
r
i
n
g
,
P
u
n
e
,
I
n
d
i
a
2
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
En
g
i
n
e
e
r
i
n
g
,
P
C
ET’s
,
P
i
m
p
r
i
C
h
i
n
c
h
w
a
d
C
o
l
l
e
g
e
o
f
En
g
i
n
e
e
r
i
n
g
a
n
d
R
e
se
a
r
c
h
,
P
u
n
e
,
I
n
d
i
a
3
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
M
I
T
A
r
t
,
D
e
s
i
g
n
a
n
d
Te
c
h
n
o
l
o
g
y
U
n
i
v
e
r
si
t
y
,
P
u
n
e
,
I
n
d
i
a
4
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
B
u
s
i
n
e
ss S
y
st
e
ms,
JS
P
M
’
s
R
a
j
a
r
s
h
i
S
h
a
h
u
C
o
l
l
e
g
e
o
f
En
g
i
n
e
e
r
i
n
g
,
P
u
n
e
,
I
n
d
i
a
5
D
e
p
a
r
t
me
n
t
o
f
A
r
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
D
a
t
a
S
c
i
e
n
c
e
,
V
i
s
h
w
a
k
a
r
m
a
I
n
st
i
t
u
t
e
o
f
Te
c
h
n
o
l
o
g
y
,
P
u
n
e
,
I
n
d
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
n
1
0
,
2
0
2
4
R
ev
is
ed
Dec
8
,
2
0
2
4
Acc
ep
ted
Dec
1
9
,
2
0
2
4
Th
e
n
u
m
b
e
r
o
f
sto
c
k
i
n
v
e
sto
rs
is
ste
a
d
il
y
i
n
c
re
a
sin
g
d
u
e
to
fa
c
to
r
s
su
c
h
a
s
th
e
a
v
a
il
a
b
il
i
ty
o
f
h
i
g
h
-
s
p
e
e
d
in
tern
e
t,
sm
a
rt
trad
in
g
p
latfo
rm
s,
lo
w
e
r
trad
in
g
c
o
m
m
issio
n
s,
a
n
d
th
e
p
e
rc
e
p
ti
o
n
th
a
t
trad
i
n
g
is
a
n
e
ffe
c
ti
v
e
wa
y
o
f
e
a
rn
i
n
g
e
x
tra
in
c
o
m
e
to
e
n
h
a
n
c
e
fin
a
n
c
ial
sta
b
il
it
y
.
Ac
c
u
ra
te
fo
re
c
a
stin
g
is cru
c
ial
to
e
a
rn
in
g
p
ro
f
it
s
i
n
t
h
e
sto
c
k
m
a
rk
e
t,
a
s
it
a
ll
o
ws
trad
e
rs
t
o
a
n
ti
c
i
p
a
te
p
rice
c
h
a
n
g
e
s
a
n
d
m
a
k
e
stra
teg
ic
i
n
v
e
stm
e
n
ts.
Th
e
trad
e
rs
m
u
st
sk
il
lf
u
ll
y
n
e
g
o
t
iate
sh
o
rt
-
term
m
a
rk
e
t
c
h
a
n
g
e
s
to
m
a
x
imiz
e
g
a
i
n
s
a
n
d
m
in
imiz
e
lo
ss
e
s,
a
s
in
trad
a
y
p
r
o
fit
m
o
st
ly
d
e
p
e
n
d
s
o
n
th
e
ti
m
in
g
o
f
b
u
y
a
n
d
se
ll
d
e
c
isio
n
s.
I
n
th
e
p
re
se
n
ted
wo
r
k
,
we
p
ro
v
i
d
e
m
in
u
te
-
by
-
m
in
u
te
f
o
re
c
a
sts
th
a
t
a
ss
ist
in
trad
a
y
trad
e
rs
i
n
m
a
k
in
g
t
h
e
b
e
st
d
e
c
isio
n
s
o
n
wh
e
n
t
o
b
u
y
a
n
d
se
ll
,
c
o
n
se
q
u
e
n
tl
y
m
a
x
imiz
in
g
p
ro
f
it
s
o
n
e
a
c
h
tra
d
e
th
e
y
m
a
k
e
.
We
h
a
v
e
imp
lem
e
n
ted
a
o
n
e
-
d
ime
n
sio
n
a
l
c
o
n
v
o
lu
ti
o
n
a
l
n
e
u
ra
l
n
e
tw
o
rk
a
n
d
b
id
irec
ti
o
n
a
l
lo
n
g
-
s
h
o
rt
-
term
m
e
m
o
ry
(
1
DCN
N
-
BiL
S
TM
)
o
p
ti
m
ize
d
with
p
a
rti
c
le
sw
a
rm
o
p
ti
m
ize
r
(P
S
O)
to
f
o
re
c
a
st
th
e
v
a
lu
e
o
f
st
o
c
k
s
fo
r
e
a
c
h
m
in
u
te
u
sin
g
re
a
l
-
ti
m
e
d
a
ta
e
x
trac
ted
fro
m
Ya
h
o
o
F
in
a
n
c
e
.
T
h
e
p
ro
p
o
se
d
m
e
th
o
d
is
e
v
a
l
u
a
ted
a
g
a
i
n
st
st
a
te
-
of
-
th
e
-
a
rt
tec
h
n
o
l
o
g
y
,
a
n
d
t
h
e
re
su
lt
s
d
e
m
o
n
stra
te
it
s
stro
n
g
p
o
ten
ti
a
l
to
a
c
c
u
ra
tely
fo
re
c
a
st
th
e
o
p
e
n
in
g
p
rice
,
sto
c
k
m
o
v
e
m
e
n
t,
a
n
d
p
rice
fo
r
t
h
e
n
e
x
t
ti
m
e
fra
m
e
.
Th
is
p
r
o
v
i
d
e
s
v
a
lu
a
b
le
in
sig
h
ts f
o
r
in
tra
d
a
y
tra
d
e
rs t
o
m
a
k
e
in
f
o
rm
e
d
b
u
y
o
r
se
ll
d
e
c
isio
n
s.
K
ey
w
o
r
d
s
:
C
o
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
s
Fo
r
ec
asti
n
g
I
n
tr
ad
ay
L
o
n
g
s
h
o
r
t
-
ter
m
m
e
m
o
r
y
Op
tim
izatio
n
Par
ticle
s
war
m
o
p
tim
izatio
n
Sto
ck
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
:
Nilesh
B
.
Ko
r
ad
e
Dep
ar
tm
en
t o
f
C
o
m
p
u
ter
E
n
g
i
n
ee
r
in
g
,
J
SP
M’
s
R
ajar
s
h
i Sh
ah
u
C
o
lleg
e
o
f
E
n
g
in
ee
r
in
g
Pu
n
e,
I
n
d
ia
E
m
ail: n
iles
h
.
k
o
r
ad
e.
m
l@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
n
u
m
b
e
r
o
f
t
r
a
d
e
r
s
is
g
r
o
wi
n
g
a
s
i
t'
s
ea
s
i
e
r
f
o
r
t
h
e
m
t
o
m
a
k
e
i
n
v
e
s
t
m
e
n
ts
i
n
t
h
e
f
i
n
a
n
cia
l
m
a
r
k
e
ts
f
r
o
m
a
n
y
w
h
e
r
e
d
u
e
t
o
t
h
e
a
c
c
e
s
s
i
b
il
i
t
y
o
f
s
o
p
h
i
s
t
i
c
at
e
d
o
n
l
i
n
e
t
r
a
d
i
n
g
p
l
a
t
f
o
r
m
s
.
T
h
e
p
r
o
l
i
f
e
r
a
t
i
o
n
o
f
i
n
s
t
r
u
c
ti
o
n
a
l
r
e
s
o
u
r
c
es
a
n
d
e
q
u
i
p
m
e
n
t
h
a
s
e
n
a
b
le
d
a
g
r
e
a
t
e
r
n
u
m
b
e
r
o
f
p
e
o
p
l
e
t
o
c
o
m
p
r
e
h
e
n
d
a
n
d
g
e
t
i
n
v
o
l
v
e
d
i
n
t
r
a
d
i
n
g
[
1
]
.
W
i
t
h
t
h
e
p
o
t
e
n
t
i
a
l
f
o
r
s
u
b
s
ta
n
t
i
al
b
e
n
e
f
i
ts
a
n
d
f
l
e
x
i
b
l
e
p
a
r
ti
c
i
p
a
ti
o
n
,
t
r
a
d
i
n
g
i
s
c
o
n
s
i
d
e
r
e
d
a
n
a
d
d
i
t
i
o
n
a
l
s
o
u
r
c
e
o
f
i
n
c
o
m
e
f
o
r
i
n
d
i
v
i
d
u
a
l
s
.
T
r
a
d
e
r
s
o
f
t
e
n
g
e
t
i
n
v
o
l
v
e
d
w
i
t
h
t
h
r
e
e
p
r
i
m
a
r
y
t
r
a
d
i
n
g
o
p
t
i
o
n
s
.
T
h
e
p
u
r
c
h
a
s
e
a
n
d
s
a
l
e
o
f
p
u
b
l
i
c
l
y
tr
a
d
e
d
c
o
m
p
a
n
y
s
h
a
r
e
s
o
n
s
t
o
c
k
e
x
c
h
a
n
g
e
s
w
i
t
h
t
h
e
o
b
j
e
c
ti
v
e
o
f
m
a
k
i
n
g
g
a
i
n
s
b
y
w
a
y
o
f
d
i
v
i
d
e
n
d
s
a
n
d
s
t
o
c
k
p
r
i
c
e
g
r
o
w
t
h
i
s
k
n
o
w
n
a
s
e
q
u
it
y
t
r
a
d
i
n
g
[
2
]
.
W
h
e
n
y
o
u
b
u
y
s
t
o
c
k
s
t
h
r
o
u
g
h
e
q
u
i
t
y
t
r
a
d
e
s
,
y
o
u
r
D
e
m
at
a
c
c
o
u
n
t
i
s
c
r
e
d
i
t
e
d
wi
t
h
t
h
o
s
e
s
t
o
c
k
s
.
T
h
e
y
s
t
a
y
i
n
y
o
u
r
p
o
s
s
es
s
i
o
n
u
n
t
i
l
y
o
u
m
a
k
e
t
h
e
c
h
o
i
c
e
t
o
o
f
f
e
r
t
h
e
m
f
o
r
s
a
l
e
,
w
h
i
c
h
m
a
y
t
a
k
e
a
f
e
w
d
a
y
s
t
o
s
e
v
e
r
a
l
y
e
a
r
s
.
T
r
a
d
i
n
g
o
p
t
i
o
n
s
i
n
v
o
l
v
e
t
h
e
b
u
y
i
n
g
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
I
n
teg
r
a
tin
g
d
ee
p
lea
r
n
in
g
a
n
d
o
p
timiz
a
tio
n
a
lg
o
r
ith
ms to
fo
r
ec
a
s
t
…
(
N
iles
h
B
.
K
o
r
a
d
e
)
2255
a
n
d
s
e
l
li
n
g
o
f
c
o
n
t
r
a
c
ts
t
h
at
g
r
an
t
t
h
e
r
i
g
h
t
,
b
u
t
n
o
t
t
h
e
c
o
m
m
i
tm
e
n
t
,
t
o
p
u
r
c
h
a
s
e
o
r
s
el
l
a
s
p
e
ci
f
i
c
as
s
et
a
t
a
f
i
x
e
d
p
r
i
c
e
w
it
h
i
n
a
g
i
v
e
n
w
i
n
d
o
w
o
f
t
i
m
e
[
3
]
.
T
h
e
a
u
t
h
o
r
i
t
y
t
o
b
u
y
a
n
a
s
s
e
t
a
t
a
f
i
x
e
d
p
r
i
c
e
is
o
f
f
e
r
e
d
b
y
a
c
a
ll
o
p
t
i
o
n
,
a
n
d
t
h
e
a
u
t
h
o
r
i
t
y
t
o
s
el
l
i
t
is
o
f
f
e
r
e
d
b
y
a
p
u
t
o
p
t
i
o
n
.
T
o
p
r
o
f
it
f
r
o
m
t
r
a
n
s
i
e
n
t
p
r
i
ce
s
w
i
n
g
s
,
in
t
r
a
d
a
y
t
r
a
d
e
r
s
b
u
y
a
n
d
s
e
l
l
s
t
o
c
k
s
o
n
t
h
e
s
a
m
e
t
r
ad
i
n
g
d
a
y
.
I
n
a
d
d
i
t
i
o
n
t
o
t
e
c
h
n
i
c
a
l
r
e
s
e
a
r
c
h
,
t
r
a
d
e
r
s
i
m
p
l
e
m
e
n
t
s
t
r
a
t
e
g
i
e
s
s
u
c
h
a
s
m
o
m
e
n
t
u
m
t
r
a
d
i
n
g
a
n
d
s
c
a
l
p
i
n
g
t
o
d
e
t
e
c
t
o
p
p
o
r
t
u
n
i
t
i
e
s
.
I
n
t
r
a
d
a
y
t
r
a
d
i
n
g
i
s
r
i
s
k
y
d
u
e
t
o
f
l
u
c
t
u
a
t
i
o
n
s
i
n
t
h
e
m
a
r
k
e
t
,
b
u
t
y
o
u
c
a
n
r
e
d
u
c
e
y
o
u
r
p
o
t
e
n
t
i
a
l
l
o
s
s
wi
t
h
t
h
e
u
s
e
o
f
m
e
c
h
a
n
i
s
m
s
l
i
k
e
s
et
s
t
o
p
-
l
o
s
s
o
r
d
e
r
s
[
4
]
.
T
h
e
r
e
a
r
e
a
f
e
w
o
b
s
ta
c
l
es
f
a
c
e
d
b
y
i
n
tr
a
d
a
y
t
r
a
d
e
r
s
.
a.
W
h
en
a
p
r
ice
h
its
a
ce
r
tain
lev
el
in
in
tr
ad
ay
tr
ad
in
g
an
d
s
tay
s
th
er
e
f
o
r
a
tim
e,
tr
ad
er
s
m
ay
f
in
d
it
d
if
f
icu
lt
to
d
ec
id
e
wh
eth
er
to
s
ell
o
r
wait.
Sellin
g
co
u
ld
r
esu
lt
in
a
lo
s
s
o
f
p
o
ten
tial
g
ain
s
if
th
e
p
r
ice
r
is
es
f
u
r
th
er
,
wh
ile
h
o
ld
in
g
ca
n
lead
t
o
lo
s
s
es if
it f
alls
[
5
]
.
b.
I
t
is
ch
allen
g
in
g
to
p
in
p
o
in
t
th
e
lo
west
an
d
h
ig
h
est
p
r
ic
e
p
o
in
ts
in
in
tr
ad
ay
tr
ad
in
g
,
wh
ich
m
ak
es
it
p
r
o
b
lem
atic
f
o
r
tr
a
d
er
s
to
s
u
cc
ess
f
u
lly
p
lace
b
u
y
a
n
d
s
ell
o
r
d
er
s
with
in
th
e
id
le
p
r
ice
win
d
o
w
[
6
]
.
c.
I
t
is
ch
allen
g
in
g
to
s
ay
with
ce
r
tain
ty
wh
eth
er
th
e
s
to
ck
p
r
ice
will
r
is
e
o
r
f
all
d
u
r
in
g
th
e
p
r
esen
t
-
d
ay
tr
ad
in
g
s
ess
io
n
at
th
e
o
p
en
in
g
tim
e
o
f
th
e
m
a
r
k
et
wh
ile
tr
ad
i
n
g
in
tr
ad
a
y
[
7
]
.
Sev
er
al
ty
p
es
o
f
m
ac
h
i
n
e
lear
n
in
g
(
ML
)
an
d
d
ee
p
lear
n
in
g
(
DL
)
alg
o
r
ith
m
s
h
av
e
b
ee
n
im
p
lem
en
ted
b
y
n
u
m
er
o
u
s
r
esear
ch
er
s
to
a
n
ticip
ate
s
to
ck
p
r
ices
[
8
]
.
M
o
s
t
r
esear
ch
o
n
s
to
ck
f
o
r
ec
asti
n
g
co
n
ce
n
tr
ates
o
n
lo
n
g
-
ter
m
s
to
ck
f
o
r
ec
asti
n
g
,
w
ith
v
er
y
lim
ited
atten
tio
n
g
iv
e
n
to
in
tr
ad
ay
f
o
r
ec
asti
n
g
with
s
h
o
r
ter
tim
ef
r
am
es.
Ho
wev
er
,
th
ese
in
tr
ad
a
y
p
r
e
d
i
ctio
n
s
tr
ateg
ies
o
f
ten
lack
ac
c
u
r
ac
y
,
h
ig
h
lig
h
tin
g
th
e
n
ee
d
f
o
r
a
m
o
r
e
ac
cu
r
ate
f
o
r
ec
asti
n
g
f
r
am
ew
o
r
k
to
im
p
r
o
v
e
th
eir
r
eliab
ilit
y
.
T
h
e
in
n
o
v
ativ
e
co
m
p
u
tatio
n
al
m
eth
o
d
s
en
ab
le
tr
ad
er
s
to
an
aly
ze
lar
g
e
v
o
l
u
m
es
o
f
m
ar
k
et
d
ata,
id
en
tify
tr
e
n
d
s
,
a
n
d
o
f
f
e
r
f
o
r
ec
asts
f
o
r
f
u
tu
r
e
p
r
ice
ch
an
g
es.
B
y
ap
p
ly
in
g
th
ese
in
n
o
v
ativ
e
tec
h
n
iq
u
es,
r
esear
ch
er
s
d
esire
to
b
o
o
s
t
th
e
ac
cu
r
ac
y
o
f
th
eir
f
o
r
ec
asts
,
wh
ich
wil
l
u
ltima
tely
lead
to
an
en
h
an
ce
d
u
n
d
e
r
s
tan
d
in
g
o
f
m
ar
k
et
d
y
n
am
ics
an
d
m
o
r
e
i
n
tellig
en
t
in
v
esti
n
g
d
ec
is
io
n
s
[
9
]
.
I
n
o
r
d
er
t
o
ass
is
t in
tr
ad
ay
tr
ad
er
s
in
p
ick
in
g
th
e
m
o
s
t a
p
p
r
o
p
r
iate
m
o
m
en
ts
to
ex
ec
u
te
b
u
y
an
d
s
ell
o
r
d
er
s
,
th
is
s
tu
d
y
f
o
cu
s
es
o
n
m
in
u
t
e
-
lev
el
s
to
ck
p
r
ice
p
r
ed
ictio
n
.
T
h
e
p
r
esen
ted
r
esear
ch
u
tili
ze
s
m
in
u
te
-
lev
el
SB
I
s
to
ck
d
ata
f
o
r
J
u
n
e
g
ath
er
ed
f
r
o
m
Yah
o
o
Fin
an
ce
.
T
h
e
co
llected
s
to
ck
d
ata
is
p
r
e
p
r
o
ce
s
s
ed
an
d
u
s
ed
to
tr
ain
a
one
-
d
im
en
s
io
n
al
co
n
v
o
l
u
tio
n
al
n
eu
r
al
n
etwo
r
k
an
d
b
id
ir
ec
tio
n
al
lo
n
g
-
s
h
o
r
t
-
ter
m
m
em
o
r
y
(
1
DC
NN
-
B
iLST
M)
m
o
d
el.
T
h
e
m
o
d
el
p
r
e
d
icts
th
e
s
to
ck
p
r
ice
f
o
r
a
1
5
-
m
in
u
te
in
ter
v
al,
a
f
ter
wh
ich
n
ew
d
ata
is
r
etr
iev
ed
f
r
o
m
Ya
h
o
o
Fin
a
n
ce
to
f
o
r
ec
ast
th
e
n
e
x
t
1
5
-
m
i
n
u
te
p
r
ice,
a
n
d
th
is
p
r
o
ce
s
s
c
o
n
tin
u
es
iter
ativ
ely
.
p
ar
ticle
s
war
m
o
p
tim
izer
(
PS
O)
o
p
tim
izatio
n
h
as
b
ee
n
a
p
p
l
ied
f
o
r
esti
m
atin
g
th
e
v
alu
es
f
o
r
s
ev
er
al
1
DC
NN
-
B
iLST
M
p
ar
am
eter
s
th
at
in
f
lu
en
ce
f
o
r
ec
asti
n
g
ac
cu
r
ac
y
.
T
h
e
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
is
ass
es
s
ed
ag
ain
s
t
ex
is
tin
g
m
eth
o
d
s
u
s
in
g
r
eg
r
ess
io
n
m
etr
ics,
tr
en
d
f
o
r
ec
asti
n
g
ca
p
ab
ilit
y
,
an
d
s
win
g
id
en
tific
a
tio
n
.
T
h
e
r
esear
ch
f
in
d
in
g
s
r
ev
ea
l
th
at
PS
O
s
el
ec
ts
th
e
o
p
tim
al
p
ar
am
eter
s
in
f
ewe
r
iter
atio
n
s
,
an
d
th
e
1
DC
NN
-
B
iL
STM
ac
cu
r
ately
f
o
r
ec
asts
th
e
s
to
ck
's o
p
en
in
g
p
r
ice,
tr
e
n
d
,
a
n
d
v
al
u
e
co
m
p
a
r
ed
to
o
th
er
m
eth
o
d
s
.
2.
L
I
T
E
R
AT
U
RE
SU
RVE
Y
As
th
e
s
to
ck
m
ar
k
et
is
s
o
co
m
p
licated
an
d
co
n
tin
u
o
u
s
ly
c
h
an
g
in
g
d
ir
ec
tio
n
,
it
is
ch
all
en
g
in
g
to
p
r
ed
ict
its
m
o
v
em
e
n
ts
.
I
m
p
le
m
en
tin
g
an
ex
tr
a
tr
ee
s
class
if
ier
(
E
T
C
)
m
o
d
el
o
p
tim
ized
f
o
r
s
m
all
-
ter
m
s
to
ck
r
etu
r
n
esti
m
atio
n
,
Pag
liar
o
in
t
r
o
d
u
ce
s
a
n
o
v
el
ap
p
r
o
ac
h
to
s
to
ck
r
et
u
r
n
p
r
ed
ictio
n
.
T
h
e
m
o
d
el
is
tr
ain
ed
u
s
in
g
tech
n
ical
in
d
icato
r
s
,
a
n
d
th
e
tar
g
et
is
th
e
p
e
r
ce
n
tag
e
c
h
an
g
e
in
clo
s
in
g
p
r
ices
f
o
r
1
2
0
en
ter
p
r
is
es
ac
r
o
s
s
d
if
f
er
en
t in
d
u
s
tr
ies af
ter
1
0
tr
ad
in
g
d
ay
s
.
T
h
e
in
d
icato
r
s
u
s
ed
to
p
r
ed
ict
th
e
d
ir
ec
tio
n
o
f
th
e
s
to
ck
p
r
ice
ar
e
th
e
m
ed
iu
m
,
u
p
p
er
,
an
d
lo
wer
B
o
llin
g
er
b
a
n
d
s
,
r
ef
e
r
r
ed
to
as
B
OL
L
M,
B
OL
L
U,
an
d
B
O
L
L
L
;
av
er
ag
e
t
r
u
e
r
an
g
e
(
AT
R
)
;
av
er
ag
e
d
ir
ec
t
io
n
al
in
d
e
x
(
ADX)
;
f
r
ac
tal
weig
h
ted
m
o
v
in
g
av
er
a
g
e
(
FW
MA
)
;
v
o
lu
m
e
-
weig
h
ted
m
o
v
in
g
av
er
ag
e
(
VW
MA
)
;
C
h
an
d
e
f
o
r
ec
ast
o
s
cillato
r
(
C
F
O)
;
an
d
S
ch
af
f
tr
en
d
cy
cle
(
STC).
ev
alu
atin
g
E
T
C
,
wh
ic
h
was
t
r
ain
ed
o
n
d
ec
is
io
n
tr
ee
s
,
ag
ai
n
s
t
b
ag
g
in
g
,
n
u
-
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
(
SVM)
,
K
-
n
eig
h
b
o
r
s
,
XGBo
o
s
t
(
XGB),
an
d
lig
h
t
g
r
ad
ien
t
b
o
o
s
tin
g
m
ac
h
in
e
(
L
GB
M)
class
if
ier
s
,
th
e
r
esu
lts
in
d
icate
th
at
E
T
C
o
u
tp
er
f
o
r
m
ed
th
e
o
th
er
s
,
ac
h
iev
in
g
a
n
ac
cu
r
ac
y
o
f
8
6
.
1
%
[
1
0
]
.
T
h
e
s
to
ck
m
ar
k
et
h
as
a
h
u
g
e
in
f
lu
en
ce
o
n
a
v
ar
iety
o
f
th
in
g
s
,
s
u
ch
as
jo
b
s
,
b
u
s
in
ess
es,
tech
n
o
lo
g
y
,
an
d
th
e
ec
o
n
o
m
y
.
Sin
g
h
et
a
l.
[
1
1
]
p
r
esen
ted
a
f
r
a
m
ewo
r
k
t
o
esti
m
ate
th
e
s
to
ck
p
r
ice
u
s
in
g
th
e
liv
e
m
ar
k
et'
s
r
ea
l
-
tim
e
s
tr
ea
m
,
wh
ich
r
elied
o
n
two
lear
n
in
g
s
tr
ateg
ies:
in
cr
e
m
en
tal
lear
n
in
g
,
wh
ich
u
p
d
ate
s
th
e
m
o
d
el
ev
er
y
tim
e
it
r
ec
e
iv
es
a
n
ew
in
s
tan
ce
o
f
th
e
s
to
ck
f
r
o
m
t
h
e
liv
e
s
tr
ea
m
,
an
d
o
f
f
lin
e
-
o
n
lin
e
lear
n
i
n
g
,
wh
ic
h
r
etr
ain
s
t
h
e
m
o
d
el
af
ter
ea
c
h
tr
ad
i
n
g
s
ess
io
n
to
en
s
u
r
e
it
tak
es
in
to
ac
co
u
n
t
th
e
m
o
s
t
r
ec
en
t
d
ata
c
o
m
p
lex
ities
.
T
h
e
ex
am
in
atio
n
u
s
es
r
ea
l
-
tim
e
d
ata
s
tr
ea
m
s
f
r
o
m
th
e
Natio
n
al
Sto
ck
E
x
ch
a
n
g
e
(
NSE)
an
d
NASDAQ
to
f
o
r
ec
ast
s
to
ck
p
r
ices
f
o
r
th
e
n
ex
t
f
if
teen
m
in
u
tes,
ass
is
tin
g
in
tr
a
-
d
ay
tr
ad
er
s
in
m
a
k
in
g
d
ec
is
io
n
s
.
I
n
c
r
em
en
tal
lin
ea
r
r
eg
r
ess
io
n
h
as
b
ee
n
i
m
p
lem
en
ted
f
o
r
in
c
r
em
en
tal
m
o
d
els,
wh
e
r
ea
s
lo
n
g
s
h
o
r
t
-
ter
m
m
em
o
r
y
(
L
STM
)
an
d
co
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
(
C
NN
)
v
ar
iatio
n
s
h
av
e
b
ee
n
im
p
lem
en
ted
in
f
o
r
ec
asti
n
g
th
r
o
u
g
h
o
f
f
lin
e
-
o
n
lin
e
m
o
d
els.
B
-
L
STM
p
er
f
o
r
m
ed
b
etter
th
an
o
t
h
er
v
ar
iatio
n
s
o
f
L
ST
M,
in
clu
d
i
n
g
b
id
ir
ec
tio
n
al
L
STM
,
v
an
illa
L
STM
,
s
tack
ed
L
STM
,
an
d
C
NN,
wh
en
co
m
p
ar
ed
o
n
r
e
g
r
ess
io
n
m
etr
ics.
As
th
er
e
ar
e
n
u
m
er
o
u
s
ele
m
en
ts
th
at
in
f
lu
e
n
ce
th
e
s
to
ck
m
ar
k
et
an
d
cr
ea
te
an
u
n
p
r
ed
ictab
le
en
v
ir
o
n
m
en
t
f
o
r
in
v
esto
r
s
,
c
h
o
o
s
in
g
a
s
to
ck
f
o
r
a
s
h
o
r
t
-
ter
m
in
v
estme
n
t
ca
r
r
ies
a
s
ig
n
if
i
ca
n
t
r
is
k
o
f
f
ailu
r
e.
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.
15
,
No
.
2
,
Ap
r
il
20
25
:
2
2
5
4
-
2
2
6
3
2256
Har
y
o
n
o
et
a
l.
[
1
2
]
p
r
esen
t
a
m
eth
o
d
o
l
o
g
y
to
ass
ess
th
e
p
er
f
o
r
m
an
ce
o
f
g
r
ap
h
co
n
v
o
lu
tio
n
al
n
etwo
r
k
s
(
GC
N)
lay
er
s
,
L
STM
,
g
ated
r
ec
u
r
r
en
t
u
n
its
(
GR
U)
,
an
d
C
NN
in
I
n
d
o
n
esian
s
to
ck
f
o
r
ec
asti
n
g
.
T
h
e
2
,
5
8
8
,
4
5
1
r
o
ws o
f
s
to
ck
d
ata
f
r
o
m
7
2
7
co
m
p
a
n
ies
o
n
th
e
I
n
d
o
n
esia
s
to
ck
ex
ch
an
g
e
(
I
DX)
ar
e
in
clu
d
ed
in
th
e
d
ataset.
T
h
e
o
u
tco
m
e
r
e
v
ea
ls
th
at
th
e
ar
ch
itectu
r
e
co
n
s
tr
u
cted
u
s
in
g
th
e
L
STM
lay
er
y
ield
s
th
e
g
r
ea
test
r
esu
lts
wh
en
co
m
p
ar
ed
in
ter
m
s
o
f
p
e
r
f
o
r
m
an
ce
an
d
v
alid
ates
th
e
b
est
o
u
tco
m
e.
Op
en
in
g
an
d
clo
s
in
g
p
r
ices,
tr
a
d
in
g
v
o
lu
m
e,
a
n
d
m
ar
k
et
in
d
icato
r
s
ar
e
a
f
ew
o
f
th
e
ch
a
r
ac
ter
is
tics
th
at
d
ef
in
e
s
to
ck
d
ata,
wh
i
ch
is
tim
e
-
s
er
ies
in
n
atu
r
e,
h
ig
h
ly
v
o
latile,
an
d
m
u
ltid
im
en
s
io
n
al.
Usi
n
g
L
STM
,
Ku
m
ar
an
d
Gan
d
h
m
al
[
1
3
]
co
n
s
tr
u
cted
an
in
tellig
en
t
s
y
s
tem
f
o
r
p
r
e
d
ictin
g
th
e
I
n
d
ian
s
to
ck
m
ar
k
et'
s
m
o
v
em
en
ts
.
T
ec
h
n
ical
i
n
d
icat
o
r
s
s
u
ch
as
W
I
L
L
R
,
R
OC
R
,
MO
M,
R
SI,
an
d
R
OC
R
.
H
av
e
b
ee
n
ca
lcu
lated
u
s
i
n
g
th
e
s
to
ck
d
ata
f
o
r
I
n
f
o
s
y
s
an
d
Z
en
s
ar
t
h
at
h
as
b
ee
n
co
llected
f
r
o
m
th
e
NSE
an
d
B
SE.
T
h
e
L
STM
is
tr
ain
ed
u
s
in
g
tech
n
ical
in
d
icato
r
s
,
a
n
d
an
o
p
tim
izatio
n
alg
o
r
ith
m
is
a
p
p
lied
to
o
b
tai
n
th
e
o
p
tim
al
v
alu
e
o
f
t
h
e
L
STM
h
y
p
er
p
ar
am
eter
s
.
T
h
e
f
o
r
ec
asts
'
o
u
tco
m
es
g
u
ar
an
tee
t
h
at
th
eir
f
in
d
in
g
s
will
ass
i
s
t
tr
ad
er
s
an
d
s
to
ck
m
ar
k
et
s
p
ec
ialis
ts
in
co
r
r
ec
tly
ch
o
o
s
in
g
wh
eth
er
to
p
u
r
ch
ase
o
r
s
ell
a
s
p
ec
if
ic
s
h
ar
e.
As
th
e
e
c
o
n
o
m
y
h
as
co
n
t
in
u
e
d
t
o
g
r
o
w
s
i
g
n
if
ic
an
tl
y
i
n
r
e
ce
n
t
y
e
ar
s
,
an
i
n
c
r
e
asi
n
g
n
u
m
b
e
r
o
f
p
eo
p
l
e
h
a
v
e
b
e
g
u
n
m
a
k
i
n
g
i
n
v
es
tm
e
n
ts
in
t
h
e
s
to
c
k
m
a
r
k
et
.
A
D
L
-
b
as
e
d
a
p
p
r
o
ac
h
t
h
a
t
f
o
r
ec
a
s
ts
s
t
o
c
k
p
r
ic
es
b
y
co
m
b
i
n
i
n
g
L
ST
M
a
n
d
B
I
-
G
R
U
h
as
b
e
en
in
tr
o
d
u
ce
d
b
y
Sh
a
b
a
n
et
a
l
.
[
1
4
]
.
T
h
e
N
Y
SE
d
ata
,
w
h
i
ch
was
g
at
h
er
ed
f
o
r
e
v
e
r
y
m
i
n
u
te
b
et
wee
n
Ma
r
c
h
2
0
2
0
a
n
d
Ap
r
i
l
2
0
2
2
,
was
n
o
r
m
ali
ze
d
f
i
r
s
t
,
an
d
B
iGR
U
-
L
S
T
M
was
tr
a
in
e
d
u
s
i
n
g
t
h
a
t
d
at
a.
T
h
e
r
esu
l
ts
i
n
d
i
ca
t
e
t
h
at
t
h
e
s
u
g
g
es
ted
m
o
d
e
l
y
i
el
d
s
R
2
v
al
u
es
o
f
0
.
9
9
4
8
,
R
MSE
o
f
0
.
2
8
8
3
,
MS
E
o
f
0
.
0
8
3
1
,
an
d
MA
E
o
f
0
.
2
0
9
9
.
T
h
e
s
u
g
g
este
d
m
et
h
o
d
h
as
b
ee
n
ass
ess
e
d
w
ith
v
a
r
i
o
u
s
d
at
asets
an
d
t
h
e
l
ates
t
tec
h
n
i
q
u
es
,
a
n
d
t
h
e
r
es
u
lts
d
e
m
o
n
s
tr
ate
t
h
at
it
d
eli
v
e
r
s
b
ett
er
f
o
r
ec
as
ti
n
g
r
es
u
l
t
s
i
n
te
r
m
s
o
f
tr
e
n
d
an
d
cl
o
s
i
n
g
p
r
i
ce
esti
m
a
ti
o
n
.
[
1
5
]
J
i
n
m
a
k
es
u
s
e
o
f
m
ac
h
i
n
e
in
tel
li
g
e
n
c
e
f
o
r
in
v
es
ti
g
at
i
n
g
s
e
n
ti
m
e
n
t
-
d
r
i
v
e
n
s
to
c
k
p
r
ed
ict
io
n
i
n
C
h
i
n
a'
s
f
i
n
an
cia
l
m
a
r
k
et
,
p
ar
t
ic
u
l
ar
ly
f
o
c
u
s
i
n
g
o
n
t
h
e
b
a
n
k
i
n
g
i
n
d
u
s
t
r
y
.
T
h
e
s
t
u
d
y
a
im
s
t
o
r
e
v
e
al
h
o
w
d
i
g
it
al
s
e
n
ti
m
en
t
i
n
f
lu
e
n
ce
s
s
t
o
ck
p
r
ic
e
m
o
v
em
e
n
ts
b
y
i
n
t
eg
r
a
ti
n
g
h
is
t
o
r
i
ca
l
s
t
o
c
k
d
at
a
f
r
o
m
k
e
y
C
h
i
n
ese
b
a
n
k
s
wit
h
s
e
n
ti
m
e
n
t
in
d
i
ce
s
f
r
o
m
B
ai
d
u
.
T
h
e
s
e
v
e
n
p
r
esti
g
i
o
u
s
b
a
n
k
s
l
is
te
d
o
n
t
h
e
S
h
an
g
h
a
i
St
o
c
k
E
x
ch
a
n
g
e
wit
h
d
ail
y
s
to
c
k
p
r
ic
es
f
r
o
m
A
u
g
u
s
t
2
0
2
2
t
o
A
u
g
u
s
t
2
0
2
3
f
r
o
m
Ya
h
o
o
Fi
n
an
ce
a
r
e
u
s
e
d
in
t
h
e
s
t
u
d
y
.
Pri
o
r
t
o
co
n
s
t
r
u
ct
in
g
a
f
i
n
a
l
s
en
t
im
en
t
-
in
te
g
r
at
ed
L
S
T
M
(
S
B
-
L
S
T
M
)
m
o
d
e
l
o
n
t
h
e
SS
E
d
at
ase
t,
g
r
i
d
s
ea
r
c
h
was
u
s
e
d
to
d
et
er
m
i
n
e
t
h
e
i
d
e
al
v
a
lu
e
f
o
r
t
h
e
h
y
p
e
r
p
a
r
a
m
et
e
r
.
T
h
e
o
b
s
er
v
ati
o
n
s
p
r
im
ar
il
y
d
e
m
o
n
s
tr
ate
t
h
at
t
h
e
SB
-
L
S
T
M
m
o
d
el
o
u
tp
er
f
o
r
m
s
a
n
o
r
m
al
L
STM
m
o
d
el
in
t
er
m
s
o
f
p
r
e
d
i
cti
o
n
p
er
f
o
r
m
a
n
ce
.
I
m
p
r
o
v
in
g
p
r
o
f
it
an
d
av
o
i
d
in
g
r
is
k
ar
e
cr
u
cial
f
o
r
a
s
tr
o
n
g
ec
o
n
o
m
y
,
wh
ich
is
th
e
in
ten
t
o
f
ev
er
y
s
to
ck
m
ar
k
et
in
v
estme
n
t.
An
in
tellig
en
t
s
o
f
t
c
o
m
p
u
tin
g
f
r
a
m
ewo
r
k
b
ased
o
n
ef
f
ec
tiv
e
f
ea
tu
r
e
o
p
tim
izatio
n
an
d
h
y
b
r
i
d
d
etec
tio
n
tech
n
iq
u
es
is
p
r
esen
ted
b
y
Ven
k
ateswar
ar
ao
a
n
d
R
ed
d
y
[
1
6
]
to
f
o
r
e
ca
s
t
th
e
d
ir
ec
tio
n
o
f
s
to
ck
m
o
v
em
en
t.
A
n
im
p
r
o
v
e
d
E
b
o
la
o
p
tim
izatio
n
(
I
E
O)
is
im
p
lem
en
ted
in
th
e
in
v
esti
g
atio
n
to
p
r
ep
a
r
e
th
e
d
ata
an
d
elim
in
ate
n
o
is
e
an
d
ir
r
eg
u
la
r
p
atter
n
s
.
T
h
e
ch
ao
t
ic
f
ar
m
lan
d
f
er
tili
ty
(
C
FF
)
alg
o
r
ith
m
is
u
s
ed
t
o
s
elec
t
h
y
p
er
p
ar
am
ete
r
s
an
d
ef
f
ec
tiv
ely
in
cr
ea
s
es
th
e
s
p
ee
d
o
f
co
n
v
e
r
g
en
ce
f
o
r
h
ig
h
-
d
im
en
s
io
n
al
o
p
tim
izatio
n
p
r
o
b
lem
s
.
A
h
y
b
r
id
s
p
ik
i
n
g
-
q
u
an
tu
m
n
eu
r
al
n
etwo
r
k
(H
-
S
QNN)
f
r
am
ewo
r
k
is
p
r
esen
te
d
to
f
o
r
ec
ast
s
to
ck
m
o
v
em
en
t
d
ir
ec
tio
n
,
en
s
u
r
in
g
th
at
f
alse
p
r
e
d
ictio
n
r
ates
ar
e
d
ec
r
ea
s
ed
.
B
ased
o
n
th
e
o
b
s
e
r
v
atio
n
,
t
h
e
h
y
b
r
id
SQNN
f
r
am
ewo
r
k
ac
h
iev
es
p
r
ed
ictin
g
ac
c
u
r
ac
y
o
f
9
5
.
2
% f
o
r
th
e
U.
S.
s
to
ck
,
9
4
.
3
2
%
f
o
r
th
e
Au
s
tr
alian
s
to
ck
,
an
d
9
3
.
5
6
%
f
o
r
C
h
in
a'
s
win
d
ec
o
n
o
m
y
d
atasets
,
r
esp
ec
ti
v
ely
.
As
f
in
an
cial
m
ar
k
ets
ar
e
th
e
f
o
u
n
d
atio
n
o
f
ev
er
y
n
atio
n
'
s
ec
o
n
o
m
y
,
p
r
ec
i
s
ely
co
r
r
ec
t
s
to
ck
m
ar
k
et
f
o
r
e
ca
s
tin
g
is
cr
u
cial
to
h
elp
in
g
i
n
v
esto
r
s
m
ax
im
ize
th
eir
in
v
estme
n
t
r
etu
r
n
s
as
well
as
g
o
v
er
n
m
en
ts
.
T
h
e
u
ltima
te
o
b
jectiv
e
o
f
Ali
et
a
l.
[
1
7
]
r
esear
c
h
is
to
d
is
co
v
er
an
in
n
o
v
ativ
e
a
p
p
r
o
a
ch
f
o
r
ac
c
u
r
ately
p
r
e
d
ictin
g
th
e
KSE
-
1
0
0
in
d
e
x
'
s
d
aily
clo
s
i
n
g
v
alu
es.
As s
tated
b
y
th
e
au
t
h
o
r
s
,
th
e
d
em
o
n
s
tr
ated
h
y
b
r
id
Ak
im
a
-
E
MD
a
n
d
th
e
L
STM
tech
n
iq
u
e
ar
e
q
u
ite
s
u
cc
ess
f
u
l
in
m
ak
in
g
p
r
ed
ictio
n
s
with
n
o
n
s
tatio
n
ar
y
a
n
d
n
o
n
lin
ea
r
d
ata.
T
h
e
h
y
b
r
id
Ak
im
a
-
EMD
-
L
ST
M
m
o
d
el
h
as
b
ee
n
s
u
g
g
ested
as
an
ef
f
ec
tiv
e
m
o
d
el
f
o
r
th
e
p
r
e
d
ictio
n
o
f
n
o
n
-
s
tatio
n
ar
y
an
d
n
o
n
lin
ea
r
co
m
p
lex
f
in
an
cial
tim
e
s
er
ies
d
ata,
as
it
o
u
tp
er
f
o
r
m
s
all
o
th
er
m
o
d
els
co
n
s
id
er
ed
in
th
e
p
r
esen
t
r
esear
ch
wh
e
n
c
o
m
p
ar
ed
to
a
s
in
g
le
L
STM
an
d
o
th
er
en
s
em
b
le
m
o
d
els lik
e
SVM,
R
F,
an
d
DT
.
3.
M
E
T
H
O
D
I
n
th
e
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
p
r
es
en
ted
in
Fig
u
r
e
1
,
we
co
llect
l
iv
e
d
ata
f
r
o
m
Yah
o
o
Fin
an
ce
.
T
h
is
d
ata
is
p
r
ep
r
o
ce
s
s
ed
a
n
d
u
s
ed
to
tr
ain
s
ev
er
al
m
o
d
els,
in
clu
d
in
g
1
DC
NN,
L
STM
,
B
iLST
M,
an
d
1
DC
NN
-
B
iLST
M.
R
eg
r
ess
io
n
m
etr
ics
ev
alu
ate
ea
ch
m
o
d
el'
s
p
er
f
o
r
m
an
ce
,
an
d
th
e
m
o
d
el
th
at
p
r
o
v
i
d
es
th
e
b
est
v
alu
es
an
d
ac
cu
r
ately
i
d
en
tifie
s
tr
en
d
s
is
s
elec
ted
f
o
r
f
o
r
ec
asti
n
g
.
Par
am
eter
s
f
o
r
th
e
m
o
d
els
ar
e
o
p
tim
ized
u
s
in
g
tech
n
iq
u
es
s
u
ch
as
r
an
d
o
m
s
ea
r
ch
,
PS
O,
an
t
co
lo
n
y
,
an
d
Fire
f
ly
.
T
h
ese
o
p
tim
izatio
n
alg
o
r
ith
m
s
ar
e
ass
ess
ed
b
ased
o
n
th
e
n
u
m
b
e
r
o
f
iter
ati
o
n
s
r
eq
u
ir
e
d
an
d
th
e
ac
cu
r
ac
y
o
f
th
e
m
o
d
els
tr
ain
ed
with
th
o
s
e
p
ar
am
eter
s
.
T
h
e
f
in
al
f
o
r
ec
asti
n
g
m
o
d
el
is
b
u
ilt
u
s
in
g
th
e
s
elec
ted
m
o
d
el
an
d
o
p
tim
izatio
n
tech
n
iq
u
es.
E
v
er
y
1
5
m
in
u
tes,
f
r
esh
s
to
ck
d
ata
is
co
llected
,
an
d
th
e
c
h
o
s
en
m
o
d
el
is
r
eb
u
i
lt
with
p
ar
am
eter
s
id
en
tifie
d
b
y
th
e
o
p
tim
izatio
n
alg
o
r
ith
m
.
T
h
e
tr
ain
ed
m
o
d
el
p
r
e
d
icts
s
to
ck
v
al
u
es
f
o
r
th
e
n
ex
t
1
5
m
in
u
tes
to
ass
is
t
in
tr
ad
ay
tr
a
d
er
s
an
d
s
o
on.
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
I
n
teg
r
a
tin
g
d
ee
p
lea
r
n
in
g
a
n
d
o
p
timiz
a
tio
n
a
lg
o
r
ith
ms to
fo
r
ec
a
s
t
…
(
N
iles
h
B
.
K
o
r
a
d
e
)
2257
Go
o
g
le
C
o
lab
s
er
v
es
as
th
e
p
r
im
ar
y
p
latf
o
r
m
f
o
r
th
is
r
es
ea
r
ch
'
s
en
v
ir
o
n
m
e
n
tal
s
etu
p
,
o
f
f
er
in
g
a
clo
u
d
-
b
ased
en
v
ir
o
n
m
e
n
t
with
GPU
s
u
p
p
o
r
t
f
o
r
e
f
f
ec
tiv
e
m
o
d
el
tr
ain
in
g
a
n
d
ex
ec
u
tio
n
.
T
h
e
p
a
n
d
a
s
_
d
a
ta
r
ea
d
er
lib
r
ar
y
is
u
s
ed
to
r
etr
iev
e
s
to
ck
d
ata
f
r
o
m
Yah
o
o
Fin
an
ce
,
en
s
u
r
in
g
ea
s
y
ac
ce
s
s
to
r
eliab
le
f
in
an
cial
d
atasets
.
I
n
o
r
d
er
to
s
tan
d
ar
d
ize
in
p
u
ts
an
d
ef
f
icie
n
tly
ac
ce
s
s
m
o
d
el
co
r
r
ec
t
n
ess
,
th
e
s
k
lear
n
lib
r
ar
y
is
u
s
ed
f
o
r
d
ata
p
r
e
p
r
o
ce
s
s
in
g
an
d
p
e
r
f
o
r
m
an
ce
ev
alu
atio
n
.
T
en
s
o
r
Flo
w
an
d
Ker
as
ar
e
u
s
ed
to
b
u
ild
d
ee
p
lear
n
in
g
m
o
d
els,
o
f
f
e
r
in
g
a
s
tr
o
n
g
f
o
u
n
d
atio
n
f
o
r
im
p
lem
en
tin
g
c
o
m
p
lex
ar
c
h
itectu
r
es
in
to
p
r
ac
tice.
Ma
tp
lo
tlib
an
d
Seab
o
r
n
ar
e
u
s
ed
to
v
is
u
alize
d
ata
tr
e
n
d
s
an
d
o
u
tco
m
es,
allo
win
g
f
o
r
u
n
am
b
ig
u
o
u
s
an
d
in
s
ig
h
tf
u
l g
r
a
p
h
ical
r
ep
r
esen
tatio
n
s
th
r
o
u
g
h
o
u
t t
h
e
an
aly
s
is
.
Fig
u
r
e
1
.
Pro
p
o
s
ed
s
to
ck
f
o
r
ec
asti
n
g
ap
p
r
o
ac
h
3
.
1
.
Da
t
a
s
et
Pan
d
a'
s
d
ata
r
ea
d
er
h
ad
b
ee
n
ap
p
lied
to
ex
tr
ac
t
m
in
u
te
-
by
-
m
in
u
te
h
is
to
r
ical
s
to
ck
d
ata
f
r
o
m
Yah
o
o
Fin
an
ce
o
f
th
e
State
B
an
k
o
f
I
n
d
ia'
s
(
S
B
I
)
J
u
n
e
2
0
2
4
m
o
n
th
[
1
8
]
.
B
asic
p
r
ep
r
o
ce
s
s
in
g
was
co
n
d
u
cted
to
s
tan
d
ar
d
ize
th
e
d
ata,
in
clu
d
in
g
n
o
r
m
aliza
tio
n
.
Miss
in
g
v
al
u
es
wer
e
r
ep
lace
d
with
th
e
p
r
e
ce
d
in
g
v
alu
e,
as
it
was
o
b
s
er
v
ed
th
at
Yah
o
o
Fin
an
ce
d
o
es
n
o
t
r
ec
o
r
d
th
e
s
to
ck
p
r
ice
if
it
r
em
ain
s
th
e
s
am
e
f
o
r
two
co
n
s
ec
u
tiv
e
m
in
u
tes.
T
h
e
d
ata
is
o
r
g
an
ized
m
in
u
te
b
y
m
in
u
te
i
n
th
e
co
l
u
m
n
d
is
p
lay
ed
i
n
T
ab
le
1
.
T
ab
le
1
.
SB
I
m
in
u
te
-
wis
e
o
p
e
n
in
g
p
r
ice
d
ataset
D
a
t
e
/
Ti
me
9
:
1
5
:
0
0
9
:
1
6
:
0
0
9
:
1
7
:
0
0
9
:
1
8
:
0
0
9
:
1
9
:
0
0
9
:
2
0
:
0
0
9
:
2
1
:
0
0
…
1
5
:
2
9
:
0
0
3
/
6
/
2
0
2
4
8
6
7
.
0
4
8
6
6
.
3
4
8
7
5
.
2
9
8
6
7
8
6
9
.
7
0
8
6
5
.
2
9
8
6
2
.
8
4
…
9
0
9
4
/
6
/
2
0
2
4
8
8
0
.
4
0
8
6
4
.
0
4
8
7
4
.
2
0
8
7
9
.
4
0
8
7
8
.
5
4
8
7
4
.
5
8
7
4
.
2
9
7
7
9
.
9
5
5
/
6
/
2
0
2
4
7
9
0
7
8
1
.
1
5
7
8
4
.
5
7
8
1
.
5
4
7
7
6
.
7
9
7
7
3
.
7
5
7
6
5
.
0
9
7
8
7
.
0
9
6
/
6
/
2
0
2
4
7
9
6
.
7
9
8
0
8
.
0
9
8
0
8
.
9
5
8
1
0
8
1
4
.
3
4
8
1
1
8
0
7
.
9
0
8
1
7
.
5
4
7
/
6
/
2
0
2
4
8
1
5
8
1
3
.
0
4
8
1
4
.
2
9
8
1
2
.
5
4
8
1
2
.
5
9
8
1
3
.
8
4
8
1
5
.
2
9
8
2
9
.
7
0
…
…
…
…
…
…
…
…
…
…
3
.
2
.
C
o
nv
o
lutio
na
l neura
l net
wo
rk
C
o
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
'
s
p
o
p
u
lar
ity
h
as
b
ee
n
i
n
cr
e
asin
g
as
a
r
esu
lt
o
f
its
ef
f
ec
t
iv
en
ess
in
d
ea
lin
g
with
a
v
ar
iety
o
f
tim
e
-
s
er
ies
f
o
r
ec
asti
n
g
ch
allen
g
es
as
well
as
its
p
o
ten
tial
to
d
is
co
v
er
p
atter
n
s
an
d
tr
en
d
s
in
d
ata
to
in
cr
ea
s
e
p
r
e
d
icted
ac
cu
r
ac
y
[
1
9
]
.
As
co
m
p
ar
ed
t
o
co
n
v
en
tio
n
al
f
u
lly
c
o
n
n
ec
ted
n
etwo
r
k
s
,
1
DC
NNs
r
eq
u
ir
e
f
ewe
r
p
ar
a
m
eter
s
f
o
r
p
r
o
ce
s
s
in
g
o
n
e
-
d
i
m
en
s
io
n
al
d
ata,
s
u
ch
as
tim
e
-
s
er
ies
d
ata,
an
d
ar
e
ca
p
ab
le
o
f
au
t
o
n
o
m
o
u
s
ly
ex
tr
ac
tin
g
r
elev
an
t
f
ea
tu
r
es
f
r
o
m
r
aw
d
ata.
Fig
u
r
e
2
illu
s
tr
ates
th
e
ar
ch
itectu
r
e
o
f
th
e
C
NN.
I
n
1
D
-
C
NN,
th
e
c
o
n
v
o
lu
tio
n
a
l
lay
er
s
p
e
r
f
o
r
m
c
o
n
v
o
lu
tio
n
o
p
er
atio
n
s
al
o
n
g
a
s
in
g
le
d
im
en
s
io
n
an
d
id
en
tify
lo
ca
l
p
atter
n
s
an
d
f
e
atu
r
es
b
y
s
cr
o
llin
g
o
v
er
t
h
e
d
ata
with
f
ilter
s
ter
m
ed
k
er
n
els
[
2
0
]
.
1
D
-
C
NN
co
n
tr
o
ls
th
e
s
ize
o
f
an
o
u
tp
u
t
m
atr
ix
b
y
a
d
d
in
g
p
ad
d
i
n
g
,
w
h
ich
s
p
ec
if
ies
th
e
n
u
m
b
e
r
o
f
p
ix
els
ad
d
ed
to
a
n
in
p
u
t
m
atr
ix
d
u
r
in
g
th
e
co
n
v
o
lu
tio
n
p
r
o
ce
s
s
.
T
h
e
s
tr
id
e,
o
r
th
e
n
u
m
b
er
o
f
d
is
p
lace
d
p
ix
els,
af
f
ec
ts
h
o
w
th
e
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.
15
,
No
.
2
,
Ap
r
il
20
25
:
2
2
5
4
-
2
2
6
3
2258
f
ilter
co
n
v
o
lv
es
ac
r
o
s
s
th
e
i
n
p
u
t
m
at
r
ix
.
T
h
e
p
o
o
lin
g
la
y
er
s
p
r
eser
v
e
th
e
m
o
s
t
im
p
o
r
tan
t
f
ea
tu
r
es
w
h
ile
r
ed
u
cin
g
th
e
co
m
p
u
tatio
n
al
c
o
m
p
lex
ity
an
d
d
im
e
n
s
io
n
ality
o
f
th
e
in
p
u
t.
B
y
p
er
io
d
icall
y
s
ettin
g
th
e
in
p
u
t
u
n
its
to
ze
r
o
at
a
r
an
d
o
m
f
r
eq
u
en
cy
at
ea
ch
tr
ain
in
g
s
tep
,
th
e
d
r
o
p
o
u
t
lay
er
h
elp
s
r
ed
u
ce
o
v
er
f
itti
n
g
.
A
o
n
e
-
d
im
en
s
io
n
al
ar
r
ay
p
r
o
d
u
ce
d
b
y
f
latten
in
g
th
e
o
u
tp
u
t
m
atr
ix
is
f
ed
in
to
th
e
f
ee
d
-
f
o
r
war
d
n
eu
r
al
n
etwo
r
k
s
o
th
at
it c
an
b
e
p
r
o
ce
s
s
ed
f
u
r
t
h
e
r
[
2
1
]
.
Fig
u
r
e
2
.
C
NN
ar
ch
itectu
r
e
3
.
3
.
L
o
ng
s
ho
rt
-
t
er
m
m
emo
ry
L
o
n
g
s
h
o
r
t
-
ter
m
m
em
o
r
y
(
L
S
T
M)
,
an
u
p
g
r
ad
ed
v
er
s
io
n
o
f
R
NN
th
at
ca
n
ca
p
tu
r
e
d
ata
f
r
o
m
p
r
ev
io
u
s
s
tag
es
an
d
u
s
e
it
f
o
r
f
u
tu
r
e
p
r
e
d
ictio
n
s
,
ca
n
o
v
er
c
o
m
e
th
e
v
a
n
is
h
in
g
g
r
ad
ie
n
t
p
r
o
b
lem
an
d
ex
p
lo
d
in
g
g
r
a
d
ien
t
p
r
o
b
lem
,
two
m
ajo
r
ch
allen
g
es
in
R
NN.
T
h
e
m
em
o
r
y
li
n
e
-
b
ased
L
STM
h
as
p
r
o
v
e
n
to
b
e
ex
ce
e
d
in
g
ly
s
u
cc
ess
f
u
l
in
f
o
r
ec
asti
n
g
s
ce
n
ar
io
s
with
len
g
th
y
d
ata
s
ets.
A
s
in
g
le
p
r
o
ce
s
s
in
g
u
n
it
th
at
ca
n
s
to
r
e
in
f
o
r
m
atio
n
o
v
er
tim
e
is
ca
lled
a
n
L
STM
ce
ll,
an
d
it
is
f
o
u
n
d
with
in
a
n
L
STM
lay
er
[
2
2
]
.
T
h
r
ee
g
ates
ca
n
a
d
d
o
r
r
em
o
v
e
in
f
o
r
m
atio
n
f
r
o
m
th
e
ce
ll st
ate,
wh
ich
is
r
ep
r
esen
ted
b
y
t
h
e
s
tr
aig
h
t lin
e
at
th
e
to
p
o
f
Fig
u
r
e
3
.
Fig
u
r
e
3
.
L
STM
A
r
c
h
itectu
r
e
W
h
at
d
ata
s
h
o
u
ld
b
e
r
etain
ed
an
d
er
ased
f
r
o
m
th
e
ce
ll
s
tate
is
d
eter
m
in
ed
b
y
t
h
e
s
ig
m
o
id
lay
er
,
also
k
n
o
wn
as
th
e
f
o
r
g
et
g
ate
lay
er
.
T
h
e
d
ata
f
r
o
m
t
h
e
cu
r
r
en
t
in
p
u
t
an
d
d
ata
f
r
o
m
a
p
r
ev
io
u
s
h
id
d
en
s
tate
ℎ
−
1
ar
e
m
er
g
ed
an
d
r
u
n
th
r
o
u
g
h
t
h
e
s
ig
m
o
id
f
u
n
ctio
n
,
wh
ich
y
ield
s
v
alu
es
b
etwe
en
0
an
d
1
,
wh
er
e
"d
is
ca
r
d
"
is
in
d
icate
d
b
y
v
alu
es n
ea
r
e
r
0
,
a
n
d
"k
ee
p
"
is
in
d
icate
d
b
y
v
alu
es c
lo
s
er
to
1
.
=
σ
(
[
ℎ
−
1
,
]
+
(
1)
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
I
n
teg
r
a
tin
g
d
ee
p
lea
r
n
in
g
a
n
d
o
p
timiz
a
tio
n
a
lg
o
r
ith
ms to
fo
r
ec
a
s
t
…
(
N
iles
h
B
.
K
o
r
a
d
e
)
2259
Selectin
g
th
e
n
ew
d
ata
th
at
will
b
e
s
to
r
ed
in
th
e
ce
ll
s
tate
in
clu
d
es
two
p
h
ases
.
T
h
e
v
alu
es
we
will
u
p
d
ate
a
r
e
d
eter
m
in
ed
b
y
t
h
e
s
ig
m
o
id
lay
er
(
σ
)
,
a
n
d
a
ta
n
h
l
ay
er
g
en
er
ates
a
v
ec
to
r
with
n
ew
p
o
ten
tial
v
alu
es
(
Ĉ
)
.
E
q
u
atio
n
(
4
)
is
ap
p
lied
in
o
r
d
er
to
u
p
d
ate
t
h
e
ce
ll st
ate
f
r
o
m
th
e
o
ld
−
1
to
th
e
n
ew
.
=
σ
(
[
ℎ
−
1
,
]
+
(
2
)
Ĉ
=
ta
n
h
(
[
ℎ
−
1
,
]
+
(
3
)
=
∗
−
1
+
∗
Ĉ
(
4
)
T
h
e
o
u
tp
u
t
g
ate'
s
s
ig
m
o
id
la
y
er
d
eter
m
in
es
wh
ich
p
o
r
tio
n
s
o
f
th
e
ce
ll
s
tate
to
r
et
u
r
n
as
o
u
tp
u
t.
T
h
e
ta
n
h
lay
e
r
tr
an
s
f
o
r
m
s
th
e
ce
ll st
ate
f
r
o
m
1
to
-
1
,
an
d
o
u
tp
u
t is p
r
o
d
u
ce
d
b
y
m
u
ltip
ly
i
n
g
th
e
s
ig
m
o
id
la
y
er
's o
u
tp
u
t,
b
y
th
e
tan
h
lay
er
's o
u
t
p
u
t r
e
p
r
esen
ted
in
(
5
)
an
d
(
6
)
[
2
3
]
.
=
σ
(
0
[
ℎ
−
1
,
]
+
0
(
5
)
ℎ
=
∗
ta
n
h
(
)
(
6
)
3
.
4
.
P
a
rt
icle
s
wa
rm
o
ptim
iz
er
Par
ticle
s
war
m
o
p
tim
izer
(
P
SO)
is
a
co
m
p
u
tatio
n
al
tech
n
iq
u
e
th
at
aim
s
to
im
p
r
o
v
e
a
ca
n
d
id
ate
s
o
lu
tio
n
iter
ativ
ely
with
r
esp
e
ct
to
a
ce
r
tain
q
u
ality
p
a
r
am
et
er
.
E
v
er
y
p
a
r
ticle
in
th
e
s
war
m
th
at
th
e
p
r
o
g
r
am
m
ain
tain
s
is
a
p
o
ten
tial
s
o
lu
tio
n
[
2
4
]
.
T
h
e
b
est
-
k
n
o
wn
p
o
s
itio
n
s
o
f
th
e
in
d
iv
id
u
al
p
ar
ticles,
as
well
as
th
o
s
e
o
f
th
eir
n
eig
h
b
o
r
s
o
r
th
e
e
n
tire
s
war
m
,
all
h
a
v
e
a
n
im
p
a
ct
o
n
th
e
v
elo
city
at
wh
ich
p
a
r
ticles
tr
av
el
ac
r
o
s
s
th
e
s
ea
r
ch
s
p
ac
e.
E
v
er
y
p
a
r
ticle
in
th
e
s
war
m
h
as
its
p
o
s
itio
n
u
p
d
ated
s
o
th
at
it
will
m
o
v
e
in
th
e
d
ir
ec
tio
n
o
f
th
e
p
ar
ticle
with
th
e
b
est p
o
s
itio
n
.
E
v
er
y
p
ar
ticle
k
ee
p
s
tr
ac
k
o
f
t
wo
th
in
g
s
: “
g
b
est,”
th
e
b
est s
o
lu
tio
n
f
o
u
n
d
b
y
all
p
ar
ticles,
an
d
“p
b
est,”
th
e
b
est
s
o
lu
tio
n
f
o
u
n
d
b
y
ea
ch
p
ar
ti
cle
in
d
ep
en
d
en
tly
,
in
o
r
d
er
to
u
p
d
ate
its
p
o
s
itio
n
an
d
v
el
o
city
in
ea
ch
iter
atio
n
[
2
5
]
.
As
th
e
g
o
al
is
to
lo
wer
f
o
r
ec
asti
n
g
er
r
o
r
,
th
e
M
SE
is
u
tili
ze
d
as
th
e
m
ea
s
u
r
e,
an
d
th
e
o
b
jectiv
e
f
u
n
ctio
n
's
p
u
r
p
o
s
e
is
t
o
m
in
im
i
ze
th
e
MSE
v
alu
e.
An
o
v
er
v
i
ew
o
f
t
h
e
p
h
ases
o
f
p
r
o
ce
s
s
in
g
n
ee
d
e
d
to
a
p
p
ly
th
e
PS
O
is
p
r
esen
ted
b
elo
w
[
2
6
]
,
[
2
7
]
.
Ou
tp
u
t:
T
h
e
lo
west M
SE
is
o
b
tain
ed
f
r
o
m
th
e
m
o
s
t e
f
f
ec
tiv
e
p
ar
am
eter
v
alu
es.
I
n
p
u
ts
:
(
)
o
b
jectiv
e
f
u
n
ctio
n
;
(
,
)
v
ar
iab
le
b
o
u
n
d
ar
y
;
(
)
p
o
p
u
latio
n
s
ize;
(
)
n
u
m
b
er
o
f
d
im
en
s
io
n
s
;
(
)
n
u
m
b
er
o
f
iter
atio
n
s
;
(
)
in
e
r
tia
weig
h
t
(
)
;
(
1
,
2
)
co
r
r
elatio
n
f
ac
to
r
s
;
(
1
,
2
)
r
a
n
d
o
m
n
u
m
b
er
.
L
ev
el
1
:
C
o
m
p
u
te
ar
b
itra
r
y
v
e
lo
city
'
'
an
d
p
o
s
itio
n
'
'
in
all
d
ir
ec
tio
n
s
th
r
o
u
g
h
th
e
f
o
llo
win
g
f
o
r
m
u
la
s
tated
in
(
7
)
a
n
d
(
8
)
.
(
)
=
l
+
r
∗
(
u
−
l
)
(
7
)
(
)
=
+
∗
(
−
)
(
8
)
L
ev
el
2
:
Set
p
ar
ticle
b
est
p
o
s
itio
n
(
)
=
in
itial
p
o
s
itio
n
(
)
an
d
g
lo
b
al
b
est
(
)
=
b
est
p
o
s
itio
n
am
o
n
g
all
p
ar
ticles h
av
in
g
th
e
l
o
west M
SE.
L
ev
el
3
: Fo
r
iter
atio
n
1
to
.
L
ev
el
4
: Fo
r
ea
c
h
p
ar
ticle
1
to
,
ca
lcu
late
th
e
n
ew
p
o
s
itio
n
a
n
d
v
elo
city
u
s
in
g
(
9
)
an
d
(
10
)
.
+
1
=
+
+
1
(
9
)
+
1
=
+
1
1
(
−
)
+
2
2
(
−
)
(
1
0
)
wh
e
r
e
r
ef
er
s
to
t
h
e
v
el
o
cit
y
o
f
th
e
i
th
p
ar
tic
le
i
n
i
te
r
at
io
n
,
r
e
f
er
s
t
o
t
h
e
p
o
s
i
ti
o
n
o
f
a
p
ar
tic
le
,
+
1
is
th
e
n
ewl
y
ca
l
cu
lat
e
d
v
el
o
c
it
y
,
a
n
d
+
1
r
e
f
e
r
s
t
o
t
h
e
n
ewl
y
c
o
m
p
u
te
d
p
o
s
iti
o
n
.
T
h
e
is
t
h
e
p
ar
t
icle'
s
o
w
n
b
es
t
p
o
s
it
io
n
i
n
ite
r
a
ti
o
n
,
an
d
is
t
h
e
g
l
o
b
al
b
est
p
o
s
i
ti
o
n
o
f
a
ll
p
ar
tic
ip
a
n
ts
.
E
n
d
o
f
f
o
r
lo
o
p
Up
d
at
e
s
e
t
t
=
b
est
p
o
s
i
ti
o
n
f
r
o
m
al
l
p
a
r
ti
cl
e
h
a
v
i
n
g
lo
we
r
MSE
i
n
i
te
r
at
io
n
.
E
n
d
o
f
it
er
ati
o
n
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.
15
,
No
.
2
,
Ap
r
il
20
25
:
2
2
5
4
-
2
2
6
3
2260
4.
RE
SU
L
T
AND
DI
SCUS
SI
O
N
T
h
e
1
DC
NN,
L
STM
,
B
i
-
L
ST
M,
an
d
p
r
o
p
o
s
ed
1
DC
NN
-
B
i
L
STM
u
s
in
g
PS
O
wer
e
tr
ain
ed
u
s
in
g
th
e
J
u
n
e
m
o
n
t
h
s
to
ck
m
i
n
u
te
-
wis
e
d
ata.
T
h
e
p
r
ed
ictio
n
in
ter
v
al
i
s
s
et
to
1
5
m
in
u
tes.
Af
ter
ea
ch
1
5
-
m
i
n
u
te
p
e
r
io
d
,
n
ew
liv
e
d
ata
will
b
e
r
etr
iev
e
d
f
r
o
m
Y
ah
o
o
to
f
o
r
ec
ast
th
e
s
u
b
s
eq
u
en
t
1
5
m
in
u
tes
o
f
s
to
ck
m
o
v
em
en
t,
an
d
s
o
o
n
.
I
n
tr
a
d
ay
tr
ad
er
s
ca
n
im
p
r
o
v
e
th
eir
tr
ad
in
g
d
ec
is
io
n
s
an
d
r
is
k
m
an
ag
em
en
t
b
y
u
s
in
g
th
e
tr
en
d
to
d
eter
m
in
e
m
ar
k
et
d
ir
ec
tio
n
,
m
o
m
en
tu
m
,
an
d
p
r
o
s
p
ec
tiv
e
p
atter
n
s
,
wh
ile
th
e
o
p
e
n
in
g
p
r
ice
p
r
o
v
id
es
in
itial
m
ar
k
et
s
en
tim
en
t
an
d
im
p
o
r
tan
t
p
o
in
ts
o
f
r
ef
er
e
n
ce
.
T
ab
le
2
s
h
o
ws
th
e
o
p
en
in
g
p
r
ice
p
r
e
d
ict
io
n
s
f
r
o
m
d
if
f
er
en
t
m
o
d
els,
th
e
tr
en
d
,
an
d
th
e
ac
c
u
r
ac
y
m
etr
ics f
o
r
p
r
ed
ictin
g
th
e
n
ex
t 1
5
-
m
in
u
te
i
n
ter
v
al.
Fig
u
r
e
4
p
r
esen
ts
th
e
s
to
ck
v
alu
e
f
o
r
1
5
m
in
u
tes
o
n
J
u
n
e
2
8
,
2
0
2
4
,
f
r
o
m
9
:1
5
AM
to
9
:3
0
AM
,
as
esti
m
ated
u
s
in
g
d
if
f
er
en
t
a
p
p
r
o
ac
h
es.
T
h
e
r
esu
lt
s
h
o
ws
th
at
th
e
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
f
o
r
ec
asts
a
n
ea
r
b
y
ac
cu
r
ate
o
p
en
in
g
p
r
ice,
th
e
tr
en
d
m
o
v
e
m
en
t,
an
d
s
to
ck
v
alu
es
f
o
r
a
1
5
-
m
in
u
te
in
ter
v
al.
W
h
en
th
e
s
to
ck
m
ar
k
et
o
p
en
s
at
9
:1
5
am
o
n
a
wo
r
k
in
g
d
ay
,
th
e
o
p
en
in
g
p
r
ice
m
ay
s
ig
n
if
ican
tly
d
if
f
er
f
r
o
m
th
e
p
r
ev
i
o
u
s
d
a
y
'
s
clo
s
in
g
p
r
ice,
p
o
ten
tially
lead
i
n
g
to
a
s
u
b
s
tan
tial r
is
e
o
r
f
all
i
n
p
r
ices in
a
s
h
o
r
t p
er
io
d
o
f
ti
m
e
af
ter
th
e
m
ar
k
et
o
p
en
s
.
I
f
y
o
u
ca
n
p
r
ed
ict
th
e
n
ea
r
b
y
o
p
e
n
in
g
p
r
ice
a
n
d
tr
en
d
f
o
r
a
s
h
o
r
t
p
e
r
io
d
af
ter
t
h
e
m
ar
k
et
o
p
en
s
,
y
o
u
ca
n
m
ak
e
s
m
ar
t sh
o
r
t
-
ter
m
in
v
estme
n
ts
an
d
p
o
ten
tially
ea
r
n
s
u
b
s
tan
tial p
r
o
f
its
.
T
ab
le
2
.
C
o
m
p
a
r
is
o
n
o
f
SB
I
s
t
o
ck
f
o
r
ec
asti
n
g
: o
p
e
n
in
g
p
r
ice
,
tr
en
d
,
a
n
d
r
eg
r
ess
io
n
m
etr
ics
M
o
d
e
l
O
p
e
n
i
n
g
P
r
i
c
e
T
r
e
n
d
M
S
E
M
A
E
R
M
S
E
M
A
P
E
1
D
C
N
N
8
4
4
.
3
2
U
p
t
r
e
n
d
2
.
6
9
0
1
.
3
0
0
1
.
6
4
0
0
.
1
5
3
LSTM
8
4
9
.
7
1
U
p
t
r
e
n
d
5
.
1
3
5
1
.
8
8
4
2
.
2
6
6
0
.
2
2
2
Bi
-
LST
M
8
4
5
.
7
0
U
p
t
r
e
n
d
2
.
1
2
1
.
1
7
4
1
.
4
5
8
0
.
1
3
8
1
D
C
N
N
-
Bi
-
LST
M
8
4
6
.
6
2
U
p
t
r
e
n
d
(
9
:
1
5
t
o
9
:
2
3
)
D
o
w
n
t
r
e
n
d
(
9
:
2
3
o
n
w
a
r
d
s)
1
.
0
3
3
0
.
8
5
9
1
.
0
1
6
0
.
1
0
1
C
NN
Sto
ck
Fo
r
ec
asti
n
g
L
STM
Sto
ck
Fo
r
ec
asti
n
g
Bi
-
L
STM
Sto
ck
Fo
r
ec
asti
n
g
PSO
-
1
DC
NN
-
Bi
-
L
STM
Sto
c
k
Fo
r
ec
asti
n
g
Fig
u
r
e
4
.
Actu
al
a
n
d
f
o
r
ec
asted
SB
I
tr
en
d
,
m
ar
k
et
o
p
en
in
g
p
r
ice,
an
d
s
to
ck
p
r
ice
f
o
r
1
5
-
m
i
n
u
te
in
ter
v
als
T
h
e
r
esu
lts
in
d
icate
th
at
th
e
p
r
esen
ted
ap
p
r
o
ac
h
p
r
e
d
ic
ts
th
e
o
p
en
in
g
p
r
ice
m
o
r
e
ac
cu
r
ately
co
m
p
ar
ed
to
o
th
e
r
m
eth
o
d
s
.
T
h
e
tr
en
d
f
o
r
ec
asted
b
y
th
e
p
r
esen
ted
ap
p
r
o
ac
h
i
n
d
icate
s
a
r
is
e
in
p
r
ice
u
n
til 9
:2
3
am
,
f
o
llo
wed
b
y
a
s
u
b
s
eq
u
en
t
d
ec
lin
e
th
at
o
th
er
m
eth
o
d
s
wer
e
u
n
ab
le
to
f
o
r
ec
ast
.
T
h
e
1
DC
NN
-
B
iL
STM
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
I
n
teg
r
a
tin
g
d
ee
p
lea
r
n
in
g
a
n
d
o
p
timiz
a
tio
n
a
lg
o
r
ith
ms to
fo
r
ec
a
s
t
…
(
N
iles
h
B
.
K
o
r
a
d
e
)
2261
m
o
d
el
p
r
o
v
i
d
es
h
ig
h
ly
ac
c
u
r
a
te
s
to
ck
f
o
r
ec
asts
with
m
in
i
m
al
er
r
o
r
s
.
Du
r
i
n
g
m
o
d
el
tr
a
in
in
g
,
t
h
e
v
al
u
es
o
f
p
ar
am
eter
s
h
a
v
e
a
s
u
b
s
tan
tial
im
p
ac
t
o
n
th
e
m
o
d
el'
s
p
er
f
o
r
m
an
ce
,
h
i
g
h
lig
h
tin
g
th
e
ess
en
tial
n
ee
d
to
id
en
tify
o
p
tim
al
p
a
r
am
eter
v
alu
es.
W
e
d
eter
m
in
e
d
o
p
tim
al
v
alu
es
f
o
r
f
ilter
s
,
k
er
n
el
s
ize,
p
o
o
l
s
i
ze
,
n
u
m
b
er
o
f
u
n
its
f
o
r
L
STM
,
b
atch
s
ize,
an
d
e
p
o
ch
s
u
s
in
g
r
a
n
d
o
m
s
ea
r
ch
[
2
8
]
,
Fire
f
ly
[
2
9
]
,
an
t
co
lo
n
y
[
3
0
]
,
a
n
d
PS
O
[
3
1
]
o
p
tim
izatio
n
tech
n
iq
u
es.
T
h
e
r
esu
lts
in
d
icate
th
at
PS
O
o
u
tp
e
r
f
o
r
m
ed
o
th
er
m
eth
o
d
s
,
ac
h
iev
in
g
lo
wer
r
eg
r
ess
io
n
m
etr
ic
v
alu
es
an
d
i
d
en
tify
in
g
o
p
tim
al
p
a
r
am
eter
s
in
a
s
in
g
le
iter
atio
n
.
Pre
d
ictin
g
wh
eth
e
r
th
e
s
to
ck
p
r
ice
will
r
is
e
o
r
f
all
d
u
r
in
g
th
e
cu
r
r
e
n
t
in
tr
ad
ay
tr
ad
in
g
s
ess
io
n
is
in
h
er
en
tly
ch
allen
g
in
g
.
T
h
e
1
DC
NN
-
L
STM
ac
cu
r
ately
p
r
ed
icts
p
r
ice
m
o
v
em
en
ts
,
en
ab
lin
g
in
tr
ad
ay
tr
a
d
er
s
to
m
ak
e
in
f
o
r
m
e
d
d
ec
is
io
n
s
r
eg
ar
d
in
g
b
u
y
in
g
o
r
s
ellin
g
.
5.
CO
NCLU
SI
O
N
A
lo
t
o
f
p
eo
p
le
th
in
k
th
at
tr
a
d
in
g
is
an
ef
f
ec
tiv
e
way
to
i
n
cr
ea
s
e
th
eir
in
co
m
e
a
n
d
im
p
r
o
v
e
th
ei
r
f
in
an
cial
s
ec
u
r
ity
.
Pre
d
ictin
g
p
r
ice
m
o
v
e
m
en
ts
an
d
m
ak
in
g
in
tellig
en
t
in
v
estme
n
ts
h
av
e
b
ec
o
m
e
ess
en
tial
f
o
r
m
ak
in
g
m
o
n
ey
i
n
th
e
s
to
ck
m
ar
k
et,
an
d
b
o
th
r
eq
u
ir
e
ac
c
u
r
a
te
f
o
r
ec
asti
n
g
.
T
h
e
r
esear
ch
f
o
cu
s
es
o
n
in
tr
ad
a
y
tr
ad
er
s
wh
o
b
u
y
a
n
d
s
ell
s
to
ck
s
with
in
th
e
s
am
e
d
ay
.
I
n
i
n
tr
ad
ay
tr
ad
i
n
g
,
k
n
o
win
g
th
e
n
ex
t
m
o
v
em
e
n
t
o
f
a
s
to
ck
allo
ws
tr
ad
er
s
to
m
a
k
e
b
u
y
o
r
s
ell
d
ec
is
io
n
s
m
o
r
e
ea
s
ily
.
T
h
e
s
tu
d
y
im
p
lem
en
ted
a
1
DC
NN
-
B
iLST
M
m
o
d
el
o
p
tim
ized
with
PS
O,
lo
ad
in
g
s
to
ck
d
ata
f
r
o
m
Ya
h
o
o
Fin
an
ce
at
1
5
-
m
in
u
te
in
ter
v
als.
Fo
r
ec
asti
n
g
is
p
er
f
o
r
m
ed
at
1
5
-
m
in
u
te
in
ter
v
als,
an
d
th
e
r
esu
lts
in
d
icate
th
at
th
e
p
r
o
p
o
s
ed
m
et
h
o
d
a
cc
u
r
ately
id
en
tifie
s
tr
en
d
s
an
d
o
p
en
i
n
g
p
r
ices,
with
lo
wer
r
eg
r
ess
io
n
m
etr
ic
v
a
lu
es
co
m
p
ar
ed
to
o
th
e
r
s
tr
ateg
ies.
PS
O
ac
h
iev
es
h
ig
h
er
ac
cu
r
ac
y
with
f
ewe
r
iter
atio
n
s
in
id
en
tif
y
in
g
o
p
ti
m
al
p
ar
am
eter
s
.
T
h
e
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
o
f
f
er
s
v
alu
ab
le
in
s
ig
h
ts
to
in
tr
ad
ay
tr
ad
er
s
,
en
ab
lin
g
th
em
to
m
a
k
e
in
f
o
r
m
ed
d
ec
is
io
n
s
o
n
wh
et
h
er
to
s
ell,
b
u
y
,
o
r
h
o
ld
.
T
h
e
s
tu
d
y
ca
n
b
e
f
u
r
th
er
ex
ten
d
ed
b
y
e
x
p
lo
r
i
n
g
ad
d
itio
n
al
alg
o
r
ith
m
s
an
d
o
p
tim
izatio
n
tech
n
iq
u
es.
T
h
e
ap
p
licatio
n
o
f
1
DC
NN
-
L
STM
is
a
s
ig
n
if
ican
t
im
p
r
o
v
em
e
n
t
f
o
r
i
n
tr
ad
ay
tr
ad
e
r
s
'
to
o
lb
o
x
a
s
it
o
f
f
er
s
ex
ce
llen
t
ca
p
ab
ilit
ies f
o
r
b
etter
s
to
ck
p
r
i
ce
f
o
r
ec
asti
n
g
as we
ll a
s
s
tr
ateg
ic
in
s
ig
h
t in
to
m
a
r
k
et
tr
en
d
s
an
d
m
o
v
em
en
ts
.
RE
F
E
R
E
NC
E
S
[
1
]
A
.
Y
e
n
i
r
e
d
d
y
,
M
.
S
.
N
a
r
a
y
a
n
a
,
K
.
V
.
B
.
G
a
n
e
s
h
,
G
.
P
.
K
u
m
a
r
,
a
n
d
M
.
V
e
n
k
a
t
e
sw
a
r
l
u
,
“
S
t
o
c
k
mar
k
e
t
i
n
d
e
x
p
r
e
d
i
c
t
i
o
n
b
a
se
d
o
n
mark
e
t
t
r
e
n
d
u
si
n
g
LST
M
,
”
I
n
d
o
n
e
s
i
a
n
J
o
u
r
n
a
l
o
f
El
e
c
t
ri
c
a
l
En
g
i
n
e
e
r
i
n
g
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
(
I
J
EE
C
S
)
,
v
o
l
.
3
5
,
n
o
.
3
,
p
p
.
1
6
0
1
–
1
6
0
9
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s.
v
3
5
.
i
3
.
p
p
1
6
0
1
-
1
6
0
9
.
[
2
]
S
.
S
a
k
p
h
o
o
w
a
d
o
n
,
N
.
W
i
s
i
t
p
o
n
g
p
h
a
n
,
a
n
d
C
.
H
a
r
u
e
c
h
a
i
y
a
sa
k
,
“
P
r
e
d
i
c
t
i
n
g
s
t
o
c
k
p
r
i
c
e
m
o
v
e
me
n
t
u
si
n
g
e
f
f
e
c
t
i
v
e
t
h
a
i
f
i
n
a
n
c
i
a
l
p
r
o
b
a
b
i
l
i
s
t
i
c
l
e
x
i
c
o
n
(
T
h
a
i
F
i
n
L
e
x
)
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
t
r
i
c
a
l
a
n
d
C
o
m
p
u
t
e
r
E
n
g
i
n
e
e
ri
n
g
(
I
J
E
C
E
)
,
v
o
l
.
1
1
,
n
o
.
5
,
p
p
.
4
3
1
3
–
4
3
2
4
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
c
e
.
v
1
1
i
5
.
p
p
4
3
1
3
-
4
3
2
4
.
[
3
]
N
.
B
.
K
o
r
a
d
e
a
n
d
M
.
Zu
b
e
r
,
“
S
t
o
c
k
p
r
i
c
e
f
o
r
e
c
a
s
t
i
n
g
u
s
i
n
g
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s
a
n
d
o
p
t
i
m
i
z
a
t
i
o
n
t
e
c
h
n
i
q
u
e
s,”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
Ad
v
a
n
c
e
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
3
,
n
o
.
1
1
,
p
p
.
3
7
8
–
3
8
5
,
2
0
2
2
,
d
o
i
:
1
0
.
1
4
5
6
9
/
I
JA
C
S
A
.
2
0
2
2
.
0
1
3
1
1
4
2
.
[
4
]
K
.
N
.
M
y
i
n
t
a
n
d
M
.
K
h
a
i
n
g
,
“
T
i
me
s
e
r
i
e
s
f
o
r
e
c
a
s
t
i
n
g
sy
s
t
e
m
f
o
r
s
t
o
c
k
m
a
r
k
e
t
d
a
t
a
,
”
I
EEE
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
C
o
n
t
r
o
l
a
n
d
Au
t
o
m
a
t
i
o
n
,
I
C
C
A
,
v
o
l
.
2
0
2
3
-
F
e
b
r
u
,
p
p
.
5
6
–
6
1
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
C
A
5
1
7
2
3
.
2
0
2
3
.
1
0
1
8
1
9
4
5
.
[
5
]
N
.
B
.
K
o
r
a
d
e
a
n
d
M
.
Zu
b
e
r
,
“
F
o
r
e
c
a
st
i
n
g
st
o
c
k
p
r
i
c
e
u
si
n
g
t
i
me
-
s
e
r
i
e
s
a
n
a
l
y
si
s
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s,”
L
e
c
t
u
r
e
N
o
t
e
s
i
n
El
e
c
t
r
i
c
a
l
En
g
i
n
e
e
r
i
n
g
,
v
o
l
.
1
1
4
6
LN
EE,
p
p
.
4
0
3
–
4
2
1
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
981
-
97
-
0
0
3
7
-
0
_
3
1
.
[
6
]
N
.
R
o
u
f
e
t
a
l
.
,
“
S
t
o
c
k
mar
k
e
t
p
r
e
d
i
c
t
i
o
n
u
si
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s:
A
d
e
c
a
d
e
s
u
r
v
e
y
o
n
m
e
t
h
o
d
o
l
o
g
i
e
s,
r
e
c
e
n
t
d
e
v
e
l
o
p
me
n
t
s,
a
n
d
f
u
t
u
r
e
d
i
r
e
c
t
i
o
n
s,”
El
e
c
t
r
o
n
i
c
s
(
S
w
i
t
zer
l
a
n
d
)
,
v
o
l
.
1
0
,
n
o
.
2
1
,
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
e
l
e
c
t
r
o
n
i
c
s
1
0
2
1
2
7
1
7
.
[
7
]
P
.
C
h
h
a
j
e
r
,
M
.
S
h
a
h
,
a
n
d
A
.
K
s
h
i
r
sa
g
a
r
,
“
T
h
e
a
p
p
l
i
c
a
t
i
o
n
s
o
f
a
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s,
s
u
p
p
o
r
t
v
e
c
t
o
r
ma
c
h
i
n
e
s,
a
n
d
l
o
n
g
–
s
h
o
r
t
t
e
r
m m
e
m
o
r
y
f
o
r
st
o
c
k
mar
k
e
t
p
r
e
d
i
c
t
i
o
n
,
”
D
e
c
i
s
i
o
n
A
n
a
l
y
t
i
c
s
J
o
u
r
n
a
l
,
v
o
l
.
2
,
M
a
r
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
d
a
j
o
u
r
.
2
0
2
1
.
1
0
0
0
1
5
.
[
8
]
N
.
B
.
K
o
r
a
d
e
a
n
d
M
.
Z
u
b
e
r
,
“
S
t
o
c
k
f
o
r
e
c
a
st
i
n
g
u
s
i
n
g
m
u
l
t
i
c
h
a
n
n
e
l
C
N
N
a
n
d
f
i
r
e
f
l
y
a
l
g
o
r
i
t
h
m,
”
C
o
g
n
i
t
i
v
e
S
c
i
e
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
P
a
r
t
F
1
4
6
6
,
p
p
.
4
4
7
–
4
5
8
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
9
8
1
-
99
-
2
7
4
2
-
5
_
4
6
.
[
9
]
A
.
M
a
i
t
i
a
n
d
P
.
S
h
e
t
t
y
D
,
“
I
n
d
i
a
n
st
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
l
e
a
r
n
i
n
g
,
”
i
n
I
EE
E
Re
g
i
o
n
1
0
An
n
u
a
l
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
,
Pro
c
e
e
d
i
n
g
s
/
T
EN
C
O
N
,
2
0
2
0
,
v
o
l
.
2
0
2
0
-
N
o
v
e
m
,
p
p
.
1
2
1
5
–
1
2
2
0
.
d
o
i
:
1
0
.
1
1
0
9
/
TEN
C
O
N
5
0
7
9
3
.
2
0
2
0
.
9
2
9
3
7
1
2
.
[
1
0
]
A
.
P
a
g
l
i
a
r
o
,
“
F
o
r
e
c
a
st
i
n
g
si
g
n
i
f
i
c
a
n
t
st
o
c
k
mar
k
e
t
p
r
i
c
e
c
h
a
n
g
e
s
u
s
i
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
:
e
x
t
r
a
t
r
e
e
s
c
l
a
ss
i
f
i
e
r
l
e
a
d
s,”
E
l
e
c
t
r
o
n
i
c
s
(
S
w
i
t
zer
l
a
n
d
)
,
v
o
l
.
1
2
,
n
o
.
2
1
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
e
l
e
c
t
r
o
n
i
c
s
1
2
2
1
4
5
5
1
.
[
1
1
]
T.
S
i
n
g
h
,
R
.
K
a
l
r
a
,
S
.
M
i
sh
r
a
,
S
a
t
a
k
s
h
i
,
a
n
d
M
.
K
u
mar,
“
A
n
e
f
f
i
c
i
e
n
t
r
e
a
l
-
t
i
me
st
o
c
k
p
r
e
d
i
c
t
i
o
n
e
x
p
l
o
i
t
i
n
g
i
n
c
r
e
me
n
t
a
l
l
e
a
r
n
i
n
g
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
,
”
E
v
o
l
v
i
n
g
S
y
st
e
m
s
,
v
o
l
.
1
4
,
n
o
.
6
,
p
p
.
9
1
9
–
9
3
7
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
2
5
3
0
-
022
-
0
9
4
8
1
-
x.
[
1
2
]
A
.
T.
H
a
r
y
o
n
o
,
R
.
S
a
r
n
o
,
a
n
d
K
.
R
.
S
u
n
g
k
o
n
o
,
“
S
t
o
c
k
p
r
i
c
e
f
o
r
e
c
a
st
i
n
g
i
n
I
n
d
o
n
e
s
i
a
s
t
o
c
k
e
x
c
h
a
n
g
e
u
si
n
g
d
e
e
p
l
e
a
r
n
i
n
g
:
A
c
o
m
p
a
r
a
t
i
v
e
st
u
d
y
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
El
e
c
t
r
i
c
a
l
a
n
d
C
o
m
p
u
t
e
r
En
g
i
n
e
e
r
i
n
g
(
I
J
EC
E)
,
v
o
l
.
1
4
,
n
o
.
1
,
p
p
.
8
6
1
–
8
6
9
,
F
e
b
.
2
0
2
4
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
c
e
.
v
1
4
i
1
.
p
p
8
6
1
-
8
6
9
.
[
1
3
]
K
.
K
u
mar
a
n
d
D
.
P
.
G
a
n
d
h
m
a
l
,
“
A
n
i
n
t
e
l
l
i
g
e
n
t
i
n
d
i
a
n
st
o
c
k
mar
k
e
t
f
o
r
e
c
a
st
i
n
g
s
y
st
e
m
u
s
i
n
g
LST
M
d
e
e
p
l
e
a
r
n
i
n
g
,
”
I
n
d
o
n
e
si
a
n
J
o
u
rn
a
l
o
f
E
l
e
c
t
r
i
c
a
l
En
g
i
n
e
e
ri
n
g
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
(
I
J
E
E
C
S
)
,
v
o
l
.
2
1
,
n
o
.
2
,
p
p
.
1
0
8
2
–
1
0
8
9
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s
.
v
2
1
.
i
2
.
p
p
1
0
8
2
-
1
0
8
9
.
[
1
4
]
W
.
M
.
S
h
a
b
a
n
,
E.
A
sh
r
a
f
,
a
n
d
A
.
E.
S
l
a
ma,
“
S
M
P
-
D
L:
a
n
o
v
e
l
st
o
c
k
m
a
r
k
e
t
p
r
e
d
i
c
t
i
o
n
a
p
p
r
o
a
c
h
b
a
s
e
d
o
n
d
e
e
p
l
e
a
r
n
i
n
g
f
o
r
e
f
f
e
c
t
i
v
e
t
r
e
n
d
f
o
r
e
c
a
s
t
i
n
g
,
”
N
e
u
ra
l
C
o
m
p
u
t
i
n
g
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
3
6
,
n
o
.
4
,
p
p
.
1
8
4
9
–
1
8
7
3
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
0
7
/
s
0
0
5
2
1
-
0
2
3
-
0
9
1
7
9
-
4.
[
1
5
]
S
.
Ji
n
,
“
S
e
n
t
i
me
n
t
-
d
r
i
v
e
n
f
o
r
e
c
a
s
t
i
n
g
LST
M
n
e
u
r
a
l
n
e
t
w
o
r
k
s
f
o
r
s
t
o
c
k
p
r
e
d
i
c
t
i
o
n
-
c
a
se
o
f
C
h
i
n
a
b
a
n
k
s
e
c
t
o
r
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
Ad
v
a
n
c
e
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
4
,
n
o
.
1
1
,
p
p
.
1
–
7
,
2
0
2
3
,
d
o
i
:
1
0
.
1
4
5
6
9
/
I
JA
C
S
A
.
2
0
2
3
.
0
1
4
1
1
0
1
.
[
1
6
]
K
.
V
e
n
k
a
t
e
sw
a
r
a
r
a
o
a
n
d
B
.
V
.
R
.
R
e
d
d
y
,
“
A
n
i
n
t
e
l
l
i
g
e
n
t
s
o
f
t
c
o
m
p
u
t
i
n
g
f
r
a
mew
o
r
k
f
o
r
f
o
r
e
c
a
st
i
n
g
s
t
o
c
k
m
o
v
e
men
t
d
i
r
e
c
t
i
o
n
i
n
i
n
t
e
r
n
a
t
i
o
n
a
l
s
t
o
c
k
m
a
r
k
e
t
s,
”
J
o
u
rn
a
l
o
f
T
h
e
o
r
e
t
i
c
a
l
a
n
d
A
p
p
l
i
e
d
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
1
0
1
,
n
o
.
9
,
p
p
.
3
6
3
4
–
3
6
5
2
,
2
0
2
3
.
[
1
7
]
M
.
A
l
i
,
D
.
M
.
K
h
a
n
,
H
.
M
.
A
l
sh
a
n
b
a
r
i
,
a
n
d
A
.
A
.
-
A
.
H
.
E
l
-
B
a
g
o
u
r
y
,
“
P
r
e
d
i
c
t
i
o
n
o
f
c
o
m
p
l
e
x
s
t
o
c
k
m
a
r
k
e
t
d
a
t
a
u
s
i
n
g
a
n
i
m
p
r
o
v
e
d
h
y
b
r
i
d
EM
D
-
LST
M
mo
d
e
l
,
”
A
p
p
l
i
e
d
S
c
i
e
n
c
e
s
,
v
o
l
.
1
3
,
n
o
.
3
,
Ja
n
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
3
0
3
1
4
2
9
.
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.
15
,
No
.
2
,
Ap
r
il
20
25
:
2
2
5
4
-
2
2
6
3
2262
[
1
8
]
Y
a
h
o
o
,
“
Y
a
h
o
o
!
”
h
t
t
p
s
:
/
/
i
n
.
f
i
n
a
n
c
e
.
y
a
h
o
o
.
c
o
m (ac
c
e
ss
e
d
J
u
l
.
0
1
,
2
0
2
4
)
.
[
1
9
]
N
.
B
.
K
o
r
a
d
e
,
M
.
B
.
S
a
l
u
n
k
e
,
A
.
A
.
B
h
o
sl
e
,
P
.
B
.
K
u
mb
h
a
r
k
a
r
,
G
.
G
.
A
sal
k
a
r
,
a
n
d
R
.
G
.
K
h
e
d
k
a
r
,
“
S
t
r
e
n
g
t
h
e
n
i
n
g
se
n
t
e
n
c
e
si
mi
l
a
r
i
t
y
i
d
e
n
t
i
f
i
c
a
t
i
o
n
t
h
r
o
u
g
h
O
p
e
n
A
I
e
mb
e
d
d
i
n
g
s
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
A
d
v
a
n
c
e
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
5
,
n
o
.
4
,
p
p
.
8
2
1
–
8
2
9
,
2
0
2
4
,
d
o
i
:
1
0
.
1
4
5
6
9
/
I
JA
C
S
A
.
2
0
2
4
.
0
1
5
0
4
8
5
.
[
2
0
]
W
.
M
a
,
C
.
G
o
u
,
a
n
d
Y
.
H
o
u
,
“
R
e
se
a
r
c
h
o
n
a
d
a
p
t
i
v
e
1
D
C
N
N
n
e
t
w
o
r
k
i
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
t
e
c
h
n
o
l
o
g
y
b
a
s
e
d
o
n
B
S
G
M
mi
x
e
d
samp
l
i
n
g
,
”
S
e
n
s
o
rs
,
v
o
l
.
2
3
,
n
o
.
1
3
,
p
.
6
2
0
6
,
Ju
l
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
s
2
3
1
3
6
2
0
6
.
[
2
1
]
N
.
B
.
K
o
r
a
d
e
a
n
d
M
.
Zu
b
e
r
,
“
B
o
o
st
st
o
c
k
f
o
r
e
c
a
st
i
n
g
a
c
c
u
r
a
c
y
u
si
n
g
t
h
e
m
o
d
i
f
i
e
d
f
i
r
e
f
l
y
a
l
g
o
r
i
t
h
m
a
n
d
mu
l
t
i
c
h
a
n
n
e
l
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
J
o
u
r
n
a
l
o
f
T
h
e
o
r
e
t
i
c
a
l
a
n
d
A
p
p
l
i
e
d
I
n
f
o
r
m
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
1
0
1
,
n
o
.
7
,
p
p
.
2
6
6
8
–
2
6
7
7
,
2
0
2
3
.
[
2
2
]
S
.
S
a
n
g
a
n
d
L.
Li
,
“
A
n
o
v
e
l
v
a
r
i
a
n
t
o
f
LSTM
s
t
o
c
k
p
r
e
d
i
c
t
i
o
n
m
e
t
h
o
d
i
n
c
o
r
p
o
r
a
t
i
n
g
a
t
t
e
n
t
i
o
n
m
e
c
h
a
n
i
sm,”
M
a
t
h
e
m
a
t
i
c
s
,
v
o
l
.
1
2
,
n
o
.
7
,
2
0
2
4
,
d
o
i
:
1
0
.
3
3
9
0
/
m
a
t
h
1
2
0
7
0
9
4
5
.
[
2
3
]
S
.
Za
h
e
e
r
e
t
a
l
.
,
“
A
m
u
l
t
i
-
p
a
r
a
m
e
t
e
r
f
o
r
e
c
a
st
i
n
g
f
o
r
st
o
c
k
t
i
m
e
s
e
r
i
e
s
d
a
t
a
u
si
n
g
LST
M
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
m
o
d
e
l
,
”
M
a
t
h
e
m
a
t
i
c
s
,
v
o
l
.
1
1
,
n
o
.
3
,
Ja
n
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
ma
t
h
1
1
0
3
0
5
9
0
.
[
2
4
]
A
.
G
.
G
a
d
,
“
P
a
r
t
i
c
l
e
sw
a
r
m
o
p
t
i
mi
z
a
t
i
o
n
a
l
g
o
r
i
t
h
m
a
n
d
i
t
s
a
p
p
l
i
c
a
t
i
o
n
s:
a
s
y
st
e
mat
i
c
r
e
v
i
e
w
,
”
Arc
h
i
v
e
s
o
f
C
o
m
p
u
t
a
t
i
o
n
a
l
Me
t
h
o
d
s
i
n
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
2
9
,
n
o
.
5
,
p
p
.
2
5
3
1
–
2
5
6
1
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
1
8
3
1
-
0
2
1
-
0
9
6
9
4
-
4.
[
2
5
]
N
.
B
.
K
o
r
a
d
e
,
M
.
B
.
S
a
l
u
n
k
e
,
A
.
A
.
B
h
o
sl
e
,
G
.
G
.
A
s
a
l
k
a
r
,
B
.
L
a
l
,
a
n
d
P
.
B
.
K
u
m
b
h
a
r
k
a
r
,
“
El
e
v
a
t
i
n
g
i
n
t
e
l
l
i
g
e
n
t
v
o
i
c
e
a
ssi
s
t
a
n
t
c
h
a
t
b
o
t
s
w
i
t
h
n
a
t
u
r
a
l
l
a
n
g
u
a
g
e
p
r
o
c
e
ssi
n
g
,
a
n
d
O
p
e
n
A
I
t
e
c
h
n
o
l
o
g
i
e
s,”
I
n
d
o
n
e
s
i
a
n
J
o
u
rn
a
l
o
f
El
e
c
t
ri
c
a
l
En
g
i
n
e
e
ri
n
g
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
3
7
,
n
o
.
1
,
p
p
.
5
0
7
–
5
1
7
,
2
0
2
5
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s.
v
3
7
.
i
1
.
p
p
5
0
7
-
5
1
7
.
[
2
6
]
J.
C
.
B
a
n
s
a
l
,
“
P
a
r
t
i
c
l
e
sw
a
r
m
o
p
t
i
mi
z
a
t
i
o
n
,
”
S
t
u
d
i
e
s
i
n
C
o
m
p
u
t
a
t
i
o
n
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
7
7
9
,
p
p
.
1
1
–
2
3
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
3
1
9
-
9
1
3
4
1
-
4
_
2
.
[
2
7
]
W
.
D
o
n
g
sh
u
,
T.
D
a
p
e
i
,
a
n
d
L
.
Le
i
,
“
P
a
r
t
i
c
l
e
sw
a
r
m
o
p
t
i
mi
z
a
t
i
o
n
a
l
g
o
r
i
t
h
m:
a
n
o
v
e
r
v
i
e
w
,
”
S
o
f
t
C
o
m
p
u
t
i
n
g
,
v
o
l
.
2
2
,
p
p
.
3
8
7
–
4
0
8
,
2
0
1
8
.
[
2
8
]
B
e
r
g
s
t
r
a
J
a
n
d
B
e
n
g
i
o
Y
,
“
R
a
n
d
o
m
sea
r
c
h
f
o
r
h
y
p
e
r
-
p
a
r
a
me
t
e
r
o
p
t
i
mi
z
a
t
i
o
n
,
”
J
o
u
r
n
a
l
o
f
m
a
c
h
i
n
e
l
e
a
rn
i
n
g
r
e
se
a
rc
h
,
v
o
l
.
1
3
,
n
o
.
2
,
p
p
.
2
8
1
–
3
0
5
,
2
0
1
2
.
[
2
9
]
N
.
B
a
c
a
n
i
n
,
T
.
B
e
z
d
a
n
,
K
.
V
e
n
k
a
t
a
c
h
a
l
a
m
,
a
n
d
F
.
A
l
-
Tu
r
j
ma
n
,
“
O
p
t
i
mi
z
e
d
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
b
y
f
i
r
e
f
l
y
a
l
g
o
r
i
t
h
m
f
o
r
mag
n
e
t
i
c
r
e
so
n
a
n
c
e
i
ma
g
e
c
l
a
ss
i
f
i
c
a
t
i
o
n
o
f
g
l
i
o
ma
b
r
a
i
n
t
u
m
o
r
g
r
a
d
e
,
”
J
o
u
rn
a
l
o
f
Re
a
l
-
T
i
m
e
I
m
a
g
e
Pr
o
c
e
ssi
n
g
,
v
o
l
.
1
8
,
n
o
.
4
,
p
p
.
1
0
8
5
–
1
0
9
8
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
5
5
4
-
0
2
1
-
0
1
1
0
6
-
x.
[
3
0
]
F
.
A
b
b
a
s,
M
.
Y
a
smi
n
,
M
.
F
a
y
y
a
z
,
M
.
A
.
El
a
z
i
z
,
S
.
L
u
,
a
n
d
A
.
A
.
A
b
d
El
-
L
a
t
i
f
,
“
G
e
n
d
e
r
c
l
a
ssi
f
i
c
a
t
i
o
n
u
s
i
n
g
p
r
o
p
o
sed
C
N
N
-
b
a
s
e
d
mo
d
e
l
a
n
d
a
n
t
c
o
l
o
n
y
o
p
t
i
mi
z
a
t
i
o
n
,
”
Ma
t
h
e
m
a
t
i
c
s
,
v
o
l
.
9
,
n
o
.
1
9
,
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
ma
t
h
9
1
9
2
4
9
9
.
[
3
1
]
Y
.
W
a
n
g
,
H
.
Z
h
a
n
g
,
a
n
d
G
.
Z
h
a
n
g
,
“
c
P
S
O
-
C
N
N
:
a
n
e
f
f
i
c
i
e
n
t
P
S
O
-
b
a
s
e
d
a
l
g
o
r
i
t
h
m
f
o
r
f
i
n
e
-
t
u
n
i
n
g
h
y
p
e
r
-
p
a
r
a
m
e
t
e
r
s
o
f
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s
,
”
S
w
a
r
m
a
n
d
E
v
o
l
u
t
i
o
n
a
r
y
C
o
m
p
u
t
a
t
i
o
n
,
v
o
l
.
4
9
,
p
p
.
1
1
4
–
1
2
3
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
s
w
e
v
o
.
2
0
1
9
.
0
6
.
0
0
2
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Niles
h
B.
K
o
r
a
d
e
se
rv
e
s
a
s
a
n
a
ss
istan
t
p
r
o
fe
ss
o
r
a
t
JS
P
M
’
s
Ra
jars
h
i
S
h
a
h
u
Co
ll
e
g
e
o
f
En
g
in
e
e
ri
n
g
,
P
u
n
e
,
I
n
d
ia.
He
is
a
d
a
ta
sc
ien
c
e
p
r
o
fe
ss
io
n
a
l
a
n
d
h
o
l
d
s
a
P
h
.
D
.
i
n
c
o
m
p
u
ter
sc
ien
c
e
a
n
d
e
n
g
in
e
e
r
in
g
.
His
re
se
a
rc
h
in
tere
sts
e
n
c
o
m
p
a
ss
d
a
ta
sc
ien
c
e
,
d
a
ta
a
n
a
ly
ti
c
s,
ti
m
e
se
ries
a
n
a
ly
sis,
m
a
c
h
in
e
lea
rn
in
g
,
n
a
tu
ra
l
la
n
g
u
a
g
e
p
ro
c
e
ss
in
g
,
a
n
d
d
e
e
p
lea
rn
in
g
.
He
h
a
s
c
o
n
tri
b
u
ted
t
o
n
u
m
e
ro
u
s
c
o
n
su
l
tan
c
y
p
ro
jec
ts,
fil
e
d
se
v
e
ra
l
In
d
ian
p
a
ten
ts,
a
n
d
o
b
tai
n
e
d
c
o
p
y
ri
g
h
ts
fo
r
h
is
i
n
n
o
v
a
ti
v
e
i
d
e
a
s.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
n
il
e
sh
.
k
o
ra
d
e
.
m
l@
g
m
a
il
.
c
o
m
.
Ma
h
e
n
d
r
a
B.
S
a
lu
n
k
e
is
a
n
a
ss
istan
t
p
ro
fe
ss
o
r
a
t
P
CET
’s
P
imp
ri
Ch
i
n
c
h
wa
d
Co
ll
e
g
e
o
f
E
n
g
i
n
e
e
rin
g
a
n
d
Re
se
a
rc
h
,
P
u
n
e
,
In
d
ia.
He
is
a
d
a
ta
sc
ien
c
e
p
ro
fe
ss
io
n
a
l
with
a
P
h
D
i
n
c
o
m
p
u
ter
e
n
g
i
n
e
e
rin
g
.
H
is
re
se
a
rc
h
a
re
a
s
a
re
d
a
ta
sc
ien
c
e
,
Io
T
,
a
n
d
m
icro
p
ro
c
e
ss
o
rs
.
H
e
w
o
r
k
e
d
a
s
P
u
n
e
U
n
i
v
e
r
s
i
t
y
'
s
f
o
r
m
e
r
d
e
p
a
r
tm
e
n
t
h
e
a
d
a
n
d
c
h
a
i
r
m
a
n
o
f
t
h
e
m
i
c
r
o
p
r
o
c
e
ss
o
r
s
u
b
j
e
c
t
.
He
h
a
s
w
o
r
k
e
d
o
n
s
e
v
e
ra
l
c
o
n
s
u
l
t
a
n
c
y
p
r
o
j
e
c
t
s
,
f
i
le
d
s
e
v
e
r
a
l
I
n
d
i
a
n
p
a
t
e
n
t
s
,
a
n
d
o
b
t
a
i
n
e
d
c
o
p
y
r
i
g
h
t
s
f
o
r
h
i
s
c
r
e
a
t
i
v
e
i
d
e
a
s
.
He
c
a
n
b
e
c
o
n
t
a
c
t
e
d
a
t
e
m
a
i
l
:
m
a
h
e
n
d
r
a
.
s
a
l
u
n
k
e
@
p
c
c
o
e
r
.
i
n
.
Am
o
l
A.
Bh
o
sle
is
a
n
a
ss
o
c
iate
p
ro
fe
ss
o
r
a
t
th
e
S
c
h
o
o
l
o
f
C
o
m
p
u
ti
n
g
,
M
IT
Ar
t,
De
sig
n
,
a
n
d
Tec
h
n
o
l
o
g
y
Un
i
v
e
rsity
,
P
u
n
e
,
I
n
d
ia.
He
is
a
d
a
ta
sc
ien
c
e
p
ro
fe
ss
io
n
a
l
wit
h
a
P
h
D
in
c
o
m
p
u
ter
sc
ien
c
e
a
n
d
e
n
g
i
n
e
e
rin
g
.
His
re
se
a
rc
h
a
re
a
s
a
re
d
a
ta
sc
ien
c
e
,
d
a
ta
a
n
a
ly
sis,
ti
m
e
se
ries
,
m
a
c
h
in
e
lea
rn
in
g
,
NL
P
,
a
n
d
d
e
e
p
lea
rn
in
g
.
He
h
a
s
wo
rk
e
d
o
n
se
v
e
ra
l
c
o
n
s
u
lt
a
n
c
y
p
ro
jec
ts,
fil
e
d
se
v
e
ra
l
In
d
ian
p
a
te
n
ts,
a
n
d
o
b
tai
n
e
d
c
o
p
y
ri
g
h
ts
fo
r
h
is
c
re
a
ti
v
e
id
e
a
s.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
a
m
o
lab
h
o
sle
@g
m
a
il
.
c
o
m
.
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
I
n
teg
r
a
tin
g
d
ee
p
lea
r
n
in
g
a
n
d
o
p
timiz
a
tio
n
a
lg
o
r
ith
ms to
fo
r
ec
a
s
t
…
(
N
iles
h
B
.
K
o
r
a
d
e
)
2263
Dha
n
a
shri
J
o
shi
is
a
n
a
ss
istan
t
p
r
o
fe
ss
o
r
a
t
JSP
M
’s
Ra
jars
h
i
S
h
a
h
u
C
o
ll
e
g
e
o
f
En
g
i
n
e
e
rin
g
,
P
u
n
e
,
In
d
ia.
S
h
e
i
s
a
d
a
ta
sc
ien
c
e
p
ro
fe
ss
io
n
a
l
with
a
m
a
ste
r
in
c
o
m
p
u
ter
e
n
g
in
e
e
rin
g
.
He
r
re
se
a
rc
h
a
re
a
s
a
re
d
a
ta
sc
ien
c
e
,
c
y
b
e
r
se
c
u
rit
y
,
a
n
d
b
lo
c
k
c
h
a
i
n
tec
h
n
o
l
o
g
y
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
j
d
h
a
n
a
sh
rim@
g
m
a
il
.
c
o
m
.
K
a
v
ita
Pa
t
il
is
a
n
a
ss
istan
t
p
ro
fe
ss
o
r
a
t
JSP
M
’s
Ra
jars
h
i
S
h
a
h
u
Co
l
leg
e
o
f
En
g
i
n
e
e
rin
g
,
P
u
n
e
,
In
d
ia.
S
h
e
is
a
d
a
ta
sc
ien
c
e
p
ro
fe
ss
io
n
a
l
w
it
h
a
M
a
ste
r
in
Co
m
p
u
ter
En
g
i
n
e
e
rin
g
.
He
r
re
se
a
rc
h
a
re
a
s
a
re
d
a
ta
sc
ien
c
e
,
c
y
b
e
r
se
c
u
rit
y
,
a
n
d
b
lo
c
k
c
h
a
in
tec
h
n
o
l
o
g
y
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
k
a
v
it
a
p
a
ti
l.
0
6
@
g
m
a
il
.
c
o
m
S
u
n
il
M.
S
a
n
g
v
e
is
a
p
r
o
fe
ss
o
r,
a
t
De
p
a
rtme
n
t
o
f
Artif
icia
l
In
te
ll
ig
e
n
c
e
a
n
d
Da
ta
S
c
ien
c
e
a
t
Vish
wa
k
a
rm
a
In
stit
u
te
o
f
Tec
h
n
o
l
o
g
y
,
P
u
n
e
,
In
d
ia.
He
is a d
a
ta s
c
ien
c
e
p
ro
fe
ss
io
n
a
l
with
a
P
h
D
in
c
o
m
p
u
ter
sc
ien
c
e
a
n
d
e
n
g
in
e
e
ri
n
g
.
His
re
se
a
rc
h
a
re
a
s
a
re
d
a
ta
sc
ien
c
e
,
d
a
ta
a
n
a
ly
sis,
ti
m
e
se
ries
,
m
a
c
h
in
e
lea
rn
in
g
,
NLP
,
a
n
d
d
e
e
p
lea
rn
i
n
g
.
He
h
a
s
wo
rk
e
d
o
n
se
v
e
ra
l
c
o
n
su
lt
a
n
c
y
p
ro
jec
ts,
fil
e
d
se
v
e
r
a
l
In
d
ian
p
a
ten
ts
,
o
b
tain
e
d
c
o
p
y
r
ig
h
ts
f
o
r
h
is
c
re
a
ti
v
e
id
e
a
s,
a
n
d
g
u
i
d
e
d
se
v
e
ra
l
re
se
a
rc
h
sc
h
o
lars
.
He
is
a
li
fe
m
e
m
b
e
r
o
f
I
n
d
ian
S
o
c
iet
y
fo
r
Tec
h
n
ica
l
Ed
u
c
a
ti
o
n
,
m
e
m
b
e
r
o
f
IAEN
G
(HK
)
a
n
d
IS
RD.
He
c
a
n
b
e
c
o
n
tac
t
e
d
a
t
e
m
a
il
:
su
n
il
.
sa
n
g
v
e
@
v
it
.
e
d
u
.
Rush
a
li
A.
De
shm
u
k
h
is
a
n
a
ss
o
c
iate
p
ro
fe
ss
o
r
a
t
JSP
M
’
s
Ra
jars
h
i
S
h
a
h
u
Co
ll
e
g
e
o
f
En
g
in
e
e
rin
g
,
P
u
n
e
,
In
d
ia.
S
h
e
is
a
d
a
ta
sc
ien
c
e
p
r
o
fe
ss
io
n
a
l
with
a
P
h
.
D
.
i
n
c
o
m
p
u
ter
sc
ien
c
e
a
n
d
e
n
g
in
e
e
ri
n
g
.
He
r
re
se
a
rc
h
a
re
a
s
a
re
d
a
ta
sc
ien
c
e
,
d
a
ta
a
n
a
l
y
sis,
t
ime
se
ries
,
m
a
c
h
in
e
lea
rn
in
g
,
NLP
,
a
n
d
d
e
e
p
lea
rn
i
n
g
.
S
h
e
h
a
s
wo
r
k
e
d
o
n
se
v
e
ra
l
c
o
n
su
lt
a
n
c
y
p
ro
jec
ts,
f
il
e
d
se
v
e
ra
l
In
d
ian
p
a
t
e
n
ts,
o
b
tain
e
d
c
o
p
y
r
ig
h
ts
f
o
r
h
e
r
c
re
a
ti
v
e
id
e
a
s,
a
n
d
g
u
id
e
d
se
v
e
ra
l
re
se
a
rc
h
sc
h
o
lars
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
ru
sh
a
li
d
e
sh
m
u
k
h
7
8
@g
m
a
il
.
c
o
m
.
Apa
r
n
a
S
.
Pa
til
is
a
n
a
ss
istan
t
p
r
o
fe
ss
o
r
a
t
JSP
M
’s
Ra
jars
h
i
S
h
a
h
u
Co
ll
e
g
e
o
f
En
g
i
n
e
e
rin
g
,
P
u
n
e
,
In
d
ia.
S
h
e
i
s
a
d
a
ta
sc
ien
c
e
p
ro
fe
ss
io
n
a
l
with
a
m
a
ste
r
in
c
o
m
p
u
ter
e
n
g
in
e
e
rin
g
.
He
r
re
se
a
rc
h
a
re
a
s
a
re
d
a
ta
sc
ien
c
e
,
c
y
b
e
r
se
c
u
rit
y
,
a
n
d
b
lo
c
k
c
h
a
i
n
tec
h
n
o
l
o
g
y
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
a
p
a
rn
a
p
a
ti
l1
6
@g
m
a
il
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.