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.
14
,
No
.
6
,
Dec
em
b
er
20
24
,
p
p
.
7
0
8
0
~
7
0
8
9
I
SS
N:
2088
-
8
7
0
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijece.
v
14
i
6
.
pp
7
0
8
0
-
7
0
8
9
7080
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
A
co
mpa
ra
tive st
udy
of long
sho
rt
-
term
me
mo
ry
bas
ed
lo
ng
-
term
el
ectr
i
c
a
l loa
d f
o
recas
tin
g
t
echniqu
es
with
hy
pe
rpa
ra
meter
o
p
timiza
tion
G
ee
t
ha
M
a
ni
1
,
Su
re
s
h
Seet
h
a
ra
ma
n
2
,
J
o
t
hin
a
t
ha
n
K
a
nd
a
s
a
m
y
3
,
L
ek
s
hm
y
P
re
ma
cha
nd
ra
n L
a
d
ha
4
,
Anis
h J
o
hn
P
a
ul
M
o
ha
nd
a
s
5
,
Swa
m
y
Siv
a
s
ub
ra
m
o
nia
m
6
,
Va
la
rm
a
t
hi I
y
a
pp
a
n Re
nu
g
a
dev
i
6
1
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
i
c
a
l
a
n
d
El
e
c
t
r
o
n
i
c
s E
n
g
i
n
e
e
r
i
n
g
,
S
r
i
Esh
w
a
r
C
o
l
l
e
g
e
o
f
E
n
g
i
n
e
e
r
i
n
g
,
C
o
i
m
b
a
t
o
r
e
,
I
n
d
i
a
2
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
o
n
i
c
s a
n
d
C
o
m
mu
n
i
c
a
t
i
o
n
En
g
i
n
e
e
r
i
n
g
,
S
r
i
Es
h
w
a
r
C
o
l
l
e
g
e
o
f
E
n
g
i
n
e
e
r
i
n
g
,
C
o
i
m
b
a
t
o
r
e
,
I
n
d
i
a
3
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
i
c
a
l
En
g
i
n
e
e
r
i
n
g
,
A
n
n
a
m
a
l
a
i
U
n
i
v
e
r
si
t
y
,
C
h
i
d
a
mb
a
r
a
m,
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
E
n
g
i
n
e
e
r
i
n
g
,
L
B
S
I
n
st
i
t
u
t
e
o
f
Te
c
h
n
o
l
o
g
y
f
o
r
W
o
me
n
,
T
h
i
r
u
v
a
n
a
n
t
h
a
p
u
r
a
m,
I
n
d
i
a
5
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
i
c
a
l
a
n
d
El
e
c
t
r
o
n
i
c
s E
n
g
i
n
e
e
r
i
n
g
,
M
a
r
E
p
h
r
a
e
m
C
o
l
l
e
g
e
o
f
E
n
g
i
n
e
e
r
i
n
g
a
n
d
Te
c
h
n
o
l
o
g
y
,
M
a
r
t
h
a
n
d
a
m,
I
n
d
i
a
6
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
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
,
R
Y
G
O
T
T
e
c
h
n
o
l
o
g
i
e
s,
C
h
e
n
n
a
i
,
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
Ma
y
2
1
,
2
0
2
4
R
ev
is
ed
J
u
l 2
2
,
2
0
2
4
Acc
ep
ted
Au
g
6
,
2
0
2
4
Lo
n
g
-
term
l
o
a
d
fo
re
c
a
stin
g
(L
TL
F
)
is
c
ru
c
ial
f
o
r
re
li
a
b
le
e
lec
tri
c
it
y
s
u
p
p
ly
,
in
fra
stru
c
tu
re
p
la
n
n
i
n
g
,
a
n
d
in
f
o
r
m
e
d
e
n
e
rg
y
p
o
l
icie
s,
e
n
su
r
in
g
g
ri
d
sta
b
il
it
y
a
n
d
e
fficie
n
t
re
so
u
rc
e
a
ll
o
c
a
ti
o
n
.
Trad
it
io
n
a
l
m
e
th
o
d
s
,
l
ik
e
sta
ti
st
ica
l
m
o
d
e
l
s
a
n
d
e
x
p
e
rt
j
u
d
g
m
e
n
t,
re
l
y
o
n
h
ist
o
rica
l
d
a
ta
b
u
t
m
a
y
stru
g
g
le
with
d
y
n
a
m
i
c
c
h
a
n
g
e
s
i
n
tec
h
n
o
lo
g
y
,
re
g
u
lati
o
n
s,
a
n
d
c
o
n
su
m
e
r
b
e
h
a
v
i
o
r.
A
d
d
re
ss
in
g
c
h
a
ll
e
n
g
e
s
su
c
h
a
s
e
c
o
n
o
m
ic
u
n
c
e
rtain
ti
e
s,
se
a
so
n
a
l
v
a
riatio
n
s,
d
a
t
a
q
u
a
li
ty
,
a
n
d
i
n
teg
ra
ti
n
g
re
n
e
wa
b
le
e
n
e
rg
y
re
q
u
i
re
s
a
d
v
a
n
c
e
d
f
o
re
c
a
stin
g
m
o
d
e
ls
a
n
d
a
d
a
p
ti
v
e
stra
teg
ies
.
Th
is
re
se
a
rc
h
a
ims
to
d
e
v
e
lo
p
a
n
e
fficie
n
t
LT
LF
m
o
d
e
l
fo
r
th
e
Co
im
b
a
to
re
re
g
io
n
in
Tam
il
Na
d
u
,
In
d
ia,
u
sin
g
l
o
n
g
sh
o
rt
-
term
m
e
m
o
ry
(LS
TM
)
n
e
two
r
k
s.
Wh
il
e
LS
TM
h
a
s
li
m
it
a
ti
o
n
s
i
n
c
a
p
tu
r
in
g
l
o
n
g
-
term
d
e
p
e
n
d
e
n
c
ies
a
n
d
re
q
u
ires
h
ig
h
d
a
ta
q
u
a
li
t
y
a
n
d
c
o
m
p
lex
m
a
n
a
g
e
m
e
n
t,
o
p
ti
m
izi
n
g
h
y
p
e
rp
a
ra
m
e
ters
,
in
c
l
u
d
i
n
g
th
r
o
u
g
h
t
h
e
o
p
p
o
siti
o
n
-
b
a
se
d
h
u
n
ter
-
p
re
y
o
p
ti
m
iza
ti
o
n
(OH
P
O)
tec
h
n
iq
u
e
,
is
e
x
p
l
o
re
d
to
e
n
h
a
n
c
e
it
s
p
re
d
ictiv
e
p
e
rfo
rm
a
n
c
e
.
Th
e
re
su
l
ts
sh
o
w
t
h
a
t
th
e
p
ro
p
o
se
d
OH
P
O
-
c
o
n
fi
g
u
r
e
d
LS
TM
m
o
d
e
l
fo
r
LT
LF
a
c
h
iev
e
s
su
p
e
rio
r
p
e
rfo
rm
a
n
c
e
c
o
m
p
a
re
d
to
o
th
e
r
tec
h
n
iq
u
e
s,
with
a
m
e
a
n
sq
u
a
re
e
rro
r
(M
S
E)
o
f
0
.
2
5
,
ro
o
t
m
e
a
n
sq
u
a
re
e
rro
r
(RM
S
E)
o
f
0
.
5
a
n
d
m
e
a
n
a
b
so
lu
te
p
e
rc
e
n
tag
e
e
rro
r
(M
APE
)
o
f
0
.
2
7
.
T
h
is
re
se
a
rc
h
u
n
d
e
rsc
o
re
s
th
e
sig
n
ifi
c
a
n
c
e
o
f
imp
ro
v
i
n
g
LT
LF
p
re
c
isio
n
f
o
r
in
fo
rm
e
d
d
e
c
isio
n
-
m
a
k
in
g
in
i
n
fra
stru
c
tu
re
p
la
n
n
i
n
g
a
n
d
e
n
e
r
g
y
p
o
li
c
y
fo
rm
u
latio
n
.
K
ey
w
o
r
d
s
:
L
o
n
g
s
h
o
r
t
-
ter
m
m
e
m
o
r
y
Hy
p
er
p
ar
a
m
eter
tu
n
in
g
Op
p
o
s
itio
n
b
ased
lear
n
in
g
Hu
n
ter
p
r
e
y
o
p
tim
izatio
n
L
o
n
g
-
ter
m
elec
tr
ical
lo
ad
f
o
r
ec
asti
n
g
R
ec
u
r
r
en
t n
eu
r
al
n
etwo
r
k
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
:
Gee
th
a
Ma
n
i
Dep
ar
tm
en
t o
f
E
lectr
ical
an
d
E
lectr
o
n
ics E
n
g
in
ee
r
i
n
g
,
Sri
E
s
h
war
C
o
lleg
e
o
f
E
n
g
in
ee
r
in
g
C
o
im
b
ato
r
e,
I
n
d
ia
E
m
ail: e
n
g
r
s
u
g
ee
th
aa
@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
L
o
ad
f
o
r
ec
asti
n
g
is
cr
u
cial
f
o
r
p
o
wer
s
y
s
tem
s
ch
ed
u
lin
g
,
o
p
er
atio
n
,
a
n
d
p
lan
n
in
g
,
r
ed
u
cin
g
th
e
co
s
ts
o
f
b
u
ild
in
g
p
o
we
r
f
ac
ilit
ies
an
d
o
p
tim
izin
g
s
tar
tu
p
co
s
ts
o
f
g
en
er
atin
g
u
n
its
.
I
t
is
ca
teg
o
r
i
ze
d
in
to
s
h
o
r
t
-
ter
m
,
m
id
-
ter
m
,
an
d
lo
n
g
-
te
r
m
f
o
r
e
ca
s
tin
g
[
1
]
,
[
2
]
.
T
r
ad
itio
n
al
m
eth
o
d
s
s
tr
u
g
g
le
with
n
o
n
-
lin
e
ar
tim
e
s
er
ies
d
ata,
lead
in
g
to
t
h
e
ad
o
p
tio
n
o
f
ar
tific
ial
in
tellig
en
ce
(
AI
)
m
eth
o
d
s
lik
e
ar
tific
ial
n
e
u
r
al
n
etwo
r
k
s
(
ANNs
)
,
r
ec
u
r
r
en
t
n
e
u
r
al
n
etwo
r
k
s
(
R
NNs
)
,
f
u
zz
y
lo
g
ic
,
an
d
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
es
(
SVMs
)
f
o
r
im
p
r
o
v
ed
ac
cu
r
ac
y
in
lo
n
g
-
ter
m
lo
a
d
f
o
r
ec
asti
n
g
(
L
T
L
F)
[
3
]
–
[
7
]
.
U
n
d
er
esti
m
atin
g
o
r
o
v
er
esti
m
atin
g
lo
n
g
-
ter
m
lo
ad
r
esu
lts
in
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
A
co
mp
a
r
a
tive
s
tu
d
y
o
f lo
n
g
s
h
o
r
t
-
term me
mo
r
y
b
a
s
ed
lo
n
g
-
term e
lectrica
l lo
a
d
…
(
Gee
th
a
Ma
n
i
)
7081
s
ig
n
if
ican
t
o
p
er
atio
n
al
is
s
u
es
an
d
f
in
a
n
cial
lo
s
s
es
[
8
]
.
lo
n
g
s
h
o
r
t
-
ter
m
m
em
o
r
y
(
L
STM
)
n
etwo
r
k
s
,
d
esig
n
e
d
f
o
r
h
a
n
d
lin
g
lo
n
g
-
ter
m
d
e
p
en
d
en
cies,
ar
e
in
c
r
ea
s
in
g
ly
u
s
ed
f
o
r
L
T
L
F,
with
o
p
tim
izatio
n
tech
n
iq
u
es
en
h
an
cin
g
th
eir
p
er
f
o
r
m
a
n
ce
[
9
]
–
[
1
5
]
.
H
y
p
er
p
ar
am
eter
o
p
tim
izatio
n
th
r
o
u
g
h
m
et
h
o
d
s
lik
e
g
r
id
s
ea
r
ch
o
r
r
an
d
o
m
s
ea
r
ch
,
th
o
u
g
h
c
o
s
tly
,
is
v
ital
f
o
r
L
STM
p
e
r
f
o
r
m
an
ce
[
1
6
]
,
[
1
7
]
.
T
ec
h
n
i
q
u
es
s
u
c
h
as
p
ar
ticle
s
war
m
o
p
tim
izatio
n
(
PS
O)
,
g
en
etic
a
lg
o
r
ith
m
s
,
an
d
h
u
n
ter
-
p
r
e
y
o
p
tim
izatio
n
(
HPO)
h
av
e
b
ee
n
ex
p
lo
r
ed
f
o
r
b
etter
f
o
r
ec
asti
n
g
ac
cu
r
ac
y
,
with
HPO
n
ee
d
in
g
o
p
p
o
s
itio
n
-
b
ased
le
ar
n
in
g
s
tr
ateg
ies to
o
v
er
c
o
m
e
lo
ca
l o
p
tim
a
is
s
u
es
[
1
8
]
–
[
2
4
]
.
2.
L
I
T
E
R
AT
U
RE
R
E
VI
E
W
Mo
h
am
m
ed
an
d
Al
-
B
az
i
[
2
5
]
en
h
an
ce
d
tr
ad
itio
n
al
AN
Ns
with
th
e
ad
a
p
tiv
e
b
ac
k
p
r
o
p
a
g
atio
n
alg
o
r
ith
m
(
AB
PA)
f
o
r
m
o
r
e
a
cc
u
r
ate
lo
n
g
-
ter
m
lo
a
d
f
o
r
ec
a
s
ts
,
ac
h
iev
in
g
m
in
im
al
m
ea
n
ab
s
o
lu
te
p
e
r
ce
n
tag
e
er
r
o
r
(
MA
PE)
a
n
d
m
ea
n
s
q
u
a
r
e
er
r
o
r
(
MSE
)
v
alu
es.
An
o
th
er
2
0
2
2
s
tu
d
y
p
r
o
p
o
s
ed
a
lin
k
ed
d
em
an
d
s
tr
ateg
y
u
s
in
g
wav
elet
d
ec
o
m
p
o
s
itio
n
,
E
L
AT
L
B
O,
an
d
B
ay
esian
o
p
tim
izatio
n
(
B
O)
f
o
r
p
r
ed
icti
n
g
a
m
etal
in
d
u
s
tr
y
m
icr
o
g
r
id
'
s
d
em
an
d
tim
e
s
er
ies
with
m
in
im
al
in
p
u
t
d
ata
[
2
6
]
.
Du
r
in
g
co
r
o
n
av
i
r
u
s
d
is
ea
s
e
2
0
1
9
(
C
OVI
D
-
19
)
,
an
L
STM
m
o
d
el
with
a
s
i
m
p
lex
o
p
tim
izer
was
u
s
ed
to
esti
m
ate
elec
tr
ic
u
s
ag
e,
im
p
r
o
v
i
n
g
f
o
r
ec
asti
n
g
ac
cu
r
ac
y
b
y
5
.
6
%
[
2
7
]
.
A
h
y
b
r
i
d
lo
a
d
f
o
r
ec
asti
n
g
s
y
s
tem
d
ev
elo
p
ed
i
n
2
0
2
2
ac
h
ie
v
ed
th
e
lo
west
p
r
ed
ictio
n
er
r
o
r
f
o
r
th
r
ee
m
o
n
th
s
an
d
h
ig
h
est
ac
cu
r
ac
y
f
o
r
s
ix
m
o
n
th
s
[
2
8
]
.
T
h
e
BO
-
p
ar
ticle
s
war
m
o
p
tim
izatio
n
(
BO
-
PSO
)
alg
o
r
ith
m
,
wh
ich
elim
in
ates
g
r
a
d
ien
t
ca
l
cu
latio
n
s
,
o
u
t
p
er
f
o
r
m
ed
s
tate
-
of
-
th
e
-
a
r
t
alg
o
r
ith
m
s
in
p
r
ed
i
ctiv
e
ac
cu
r
ac
y
[
2
9
]
.
HPO,
b
ased
o
n
p
r
ed
ato
r
-
p
r
e
y
d
y
n
am
ics,
s
h
o
wed
s
tr
o
n
g
o
p
tim
izatio
n
p
e
r
f
o
r
m
an
ce
i
n
m
u
ltip
le
test
s
[
3
0
]
.
Ad
v
an
ce
d
o
p
p
o
s
itio
n
-
b
ased
le
ar
n
in
g
(
OB
L
)
v
ar
iatio
n
s
wer
e
class
if
ied
to
b
alan
ce
e
x
p
lo
r
ati
o
n
an
d
e
x
p
lo
itatio
n
f
o
r
alg
o
r
ith
m
s
u
cc
ess
[
3
1
]
.
I
n
2
0
2
4
,
r
esear
ch
h
i
g
h
lig
h
ted
th
e
n
ee
d
f
o
r
ac
c
u
r
ate
s
o
lar
p
o
wer
g
en
er
atio
n
f
o
r
ec
asti
n
g
,
p
r
o
p
o
s
in
g
th
e
e
v
o
lu
tio
n
o
f
c
u
b
to
p
r
e
d
ato
r
(
E
C
P)
tech
n
iq
u
e
w
h
ich
ac
h
iev
ed
a
p
r
ed
ictio
n
ac
cu
r
ac
y
o
f
9
7
.
2
%,
s
u
r
p
ass
in
g
o
th
er
m
eth
o
d
s
an
d
o
p
tim
izin
g
r
en
ewa
b
le
en
e
r
g
y
r
eso
u
r
ce
m
an
ag
em
en
t
[
3
2
]
.
3.
P
RO
P
O
SE
D
M
E
T
H
O
D
L
T
L
F
p
r
ed
icts
f
u
tu
r
e
elec
tr
icity
d
em
an
d
to
en
s
u
r
e
r
eliab
le
s
u
p
p
ly
,
o
p
tim
ize
in
f
r
astru
ctu
r
e,
in
f
o
r
m
p
o
licy
d
ec
is
io
n
s
,
m
ain
tain
g
r
i
d
s
tab
ilit
y
,
an
d
p
r
o
m
o
te
ec
o
n
o
m
ic
ef
f
icien
cy
in
e
n
er
g
y
in
d
u
s
tr
ies.
C
h
allen
g
es
in
L
T
L
F
u
s
in
g
tr
ad
itio
n
al
ap
p
r
o
a
ch
es
in
clu
d
e
d
if
f
icu
lties
in
ca
p
tu
r
in
g
co
m
p
lex
,
n
o
n
-
lin
ea
r
r
el
atio
n
s
h
ip
s
;
lim
ited
ad
ap
tab
ilit
y
to
d
y
n
am
ic
ch
a
n
g
es
in
tech
n
o
lo
g
y
,
r
eg
u
latio
n
s
,
an
d
co
n
s
u
m
e
r
b
eh
a
v
io
r
;
is
s
u
es
with
d
ata
q
u
ality
an
d
av
ailab
ilit
y
;
h
an
d
lin
g
s
ea
s
o
n
al
v
ar
iatio
n
s
an
d
wea
th
er
s
en
s
itiv
ity
;
in
teg
r
atin
g
r
en
ewa
b
le
en
er
g
y
s
o
u
r
ce
s
;
m
an
ag
in
g
m
o
d
el
co
m
p
lex
ity
an
d
in
ter
p
r
etab
ilit
y
;
an
d
ad
d
r
ess
in
g
ec
o
n
o
m
ic
u
n
ce
r
tain
ties
.
Ov
er
co
m
i
n
g
t
h
ese
ch
allen
g
es
r
eq
u
i
r
es
ad
v
an
ce
d
f
o
r
ec
asti
n
g
tech
n
iq
u
es,
r
o
b
u
s
t
d
ata
m
an
a
g
em
en
t
p
r
ac
t
ices,
an
d
ad
a
p
tiv
e
s
tr
ateg
ies
to
im
p
r
o
v
e
ac
cu
r
a
cy
in
p
r
e
d
ictin
g
elec
tr
icity
d
em
an
d
o
v
er
e
x
ten
d
e
d
p
er
i
o
d
s
.
T
h
is
r
esear
ch
en
d
ea
v
o
r
s
to
cr
ea
te
an
e
f
f
ec
t
iv
e
L
T
L
F
m
o
d
el
tailo
r
e
d
f
o
r
th
e
C
o
im
b
ato
r
e
R
eg
io
n
in
T
am
il
Nad
u
,
I
n
d
ia,
lev
er
ag
in
g
L
STM
n
etwo
r
k
s
.
Alth
o
u
g
h
L
STM
s
tr
u
g
g
les
with
ca
p
tu
r
in
g
lo
n
g
-
ter
m
r
elatio
n
s
h
ip
s
an
d
n
ee
d
s
h
ig
h
-
q
u
ality
d
ata
an
d
co
m
p
l
ex
m
an
ag
em
e
n
t,
th
is
s
tu
d
y
ex
p
lo
r
es
im
p
r
o
v
in
g
its
p
r
e
d
ictiv
e
ac
cu
r
ac
y
b
y
o
p
tim
izin
g
h
y
p
e
r
p
ar
am
eter
s
u
s
in
g
th
e
o
p
tim
izatio
n
tec
h
n
iq
u
es.
I
d
en
tif
y
in
g
th
e
o
p
tim
al
h
y
p
er
p
a
r
am
eter
s
f
o
r
L
STM
th
r
o
u
g
h
m
an
u
al
o
r
t
r
ial
-
an
d
-
er
r
o
r
p
r
o
ce
s
s
es
is
tim
e
-
co
n
s
u
m
in
g
an
d
co
m
p
u
ta
tio
n
ally
co
m
p
le
x
,
n
ec
ess
itatin
g
th
e
in
co
r
p
o
r
ati
o
n
o
f
o
p
tim
izatio
n
tech
n
i
q
u
es.
T
h
e
r
esear
ch
ex
p
lo
r
es
v
ar
io
u
s
o
p
tim
izatio
n
tech
n
iq
u
es,
in
clu
d
i
n
g
p
a
r
ticle
s
war
m
o
p
tim
izatio
n
(
PS
O)
,
g
r
ey
wo
lf
o
p
tim
izatio
n
(
GW
O)
,
an
d
h
u
n
ter
-
p
r
e
y
o
p
tim
izatio
n
(
HPO)
.
T
h
e
to
p
-
p
er
f
o
r
m
in
g
h
u
n
ter
-
p
r
ey
o
p
ti
m
izatio
n
tech
n
iq
u
e
is
en
h
a
n
c
ed
with
o
p
p
o
s
itio
n
-
b
ased
lear
n
in
g
an
d
r
ef
er
r
e
d
to
as
o
p
p
o
s
itio
n
-
b
ased
h
u
n
te
r
-
p
r
ey
o
p
tim
izatio
n
(
OHPO)
.
3
.
1
.
P
r
o
blem
identif
ica
t
io
n
Acc
u
r
ate
L
T
L
F
is
cr
u
cial
f
o
r
th
e
p
o
wer
in
d
u
s
tr
y
t
o
m
an
ag
e
f
u
tu
r
e
en
e
r
g
y
d
em
a
n
d
s
e
f
f
ec
tiv
ely
.
T
r
ad
itio
n
al
f
o
r
ec
asti
n
g
m
eth
o
d
s
o
f
ten
s
tr
u
g
g
le
with
co
m
p
l
ex
v
ar
iab
les
lik
e
wea
th
er
,
ec
o
n
o
m
ic
co
n
d
itio
n
s
,
an
d
p
o
p
u
latio
n
tr
en
d
s
.
I
n
C
o
im
b
ato
r
e,
I
n
d
ia,
r
ap
id
u
r
b
an
iz
atio
n
an
d
ec
o
n
o
m
ic
g
r
o
wth
a
r
e
d
r
iv
in
g
in
cr
ea
s
ed
elec
tr
icity
d
em
an
d
.
T
o
im
p
r
o
v
e
ac
cu
r
ac
y
,
n
ew
L
T
L
F
a
p
p
r
o
ac
h
es
ar
e
n
ee
d
ed
.
Ov
er
co
m
in
g
ch
allen
g
es
r
eq
u
ir
es
ad
v
an
ce
d
f
o
r
ec
asti
n
g
m
o
d
els,
r
o
b
u
s
t
d
ata
m
a
n
a
g
em
en
t,
a
n
d
a
d
ap
tiv
e
s
tr
ateg
ies
to
n
av
ig
ate
th
e
d
y
n
am
ic
e
n
er
g
y
en
v
ir
o
n
m
e
n
t
ef
f
ec
tiv
ely
.
3
.
2
.
Resea
rc
h
o
bje
ct
i
v
e
T
h
e
o
b
jectiv
e
o
f
t
h
e
r
esear
c
h
is
to
d
ev
el
o
p
a
n
o
v
el
L
STM
-
b
ased
ap
p
r
o
ac
h
f
o
r
L
T
L
F
in
C
o
im
b
ato
r
e,
T
am
il
Nad
u
,
an
d
I
n
d
ia,
o
p
tim
izin
g
th
e
m
o
d
el'
s
ac
cu
r
ac
y
th
r
o
u
g
h
o
p
p
o
s
itio
n
-
b
as
ed
h
y
p
er
p
ar
am
ete
r
o
p
tim
izatio
n
a
n
d
e
v
alu
atin
g
its
p
er
f
o
r
m
an
ce
u
s
in
g
e
r
r
o
r
m
e
tr
ics
lik
e
MSE
,
r
o
o
t
m
ea
n
s
q
u
ar
e
er
r
o
r
(
R
MSE
)
,
an
d
MA
PE.
−
T
o
d
ev
elo
p
a
n
o
v
el
ap
p
r
o
ac
h
f
o
r
L
T
L
F in
th
e
C
o
im
b
ato
r
e
r
e
g
io
n
o
f
T
am
il Na
d
u
,
I
n
d
ia.
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.
14
,
No
.
6
,
Dec
em
b
e
r
20
24
:
7
0
8
0
-
7
0
8
9
7082
−
U
s
i
n
g
a
n
L
S
T
M
n
e
tw
o
r
k
f
o
r
L
T
L
F
a
l
l
o
w
s
f
o
r
l
ea
r
n
i
n
g
o
r
d
e
r
d
e
p
e
n
d
e
n
c
e
i
n
s
e
q
u
e
n
c
e
p
r
e
d
i
ct
i
o
n
p
r
o
b
l
e
m
s
.
−
T
o
in
cr
ea
s
e
th
e
ac
cu
r
ac
y
o
f
th
e
f
o
r
ec
asti
n
g
m
o
d
el,
we
o
p
tim
ize
th
e
L
STM
h
y
p
er
p
a
r
am
eter
s
u
s
in
g
o
p
p
o
s
itio
n
-
b
ased
lear
n
in
g
in
t
h
e
HPO
tech
n
iq
u
e.
−
T
o
ass
ess
h
o
w
well
th
e
s
u
g
g
ested
m
eth
o
d
p
er
f
o
r
m
s
in
r
elatio
n
to
alter
n
ativ
e
co
m
p
ar
is
o
n
ap
p
r
o
ac
h
es u
s
in
g
a
r
an
g
e
o
f
er
r
o
r
m
et
r
ics,
in
clu
d
in
g
MSE
,
R
MSE
,
an
d
MA
PE
.
3
.
3
.
L
o
ng
s
ho
rt
-
t
er
m
m
emo
ry
L
STM
is
an
id
ea
l
R
NN
ar
ch
it
ec
tu
r
e
f
o
r
lo
n
g
-
ter
m
elec
tr
icity
d
em
a
n
d
f
o
r
ec
asti
n
g
d
u
e
t
o
it
s
ab
ilit
y
to
lear
n
s
eq
u
en
tial
d
ep
en
d
en
cie
s
an
d
p
atter
n
s
i
n
h
is
to
r
ical
d
ata,
en
a
b
lin
g
ac
c
u
r
ate
f
u
t
u
r
e
p
r
e
d
ictio
n
s
.
I
t
ef
f
ec
tiv
ely
ad
d
r
ess
es
v
an
is
h
in
g
o
r
ex
p
lo
d
in
g
g
r
a
d
ien
t
is
s
u
es
d
u
r
in
g
tr
ain
in
g
o
n
len
g
th
y
d
ata
s
eq
u
en
ce
s
an
d
ca
n
h
an
d
le
in
p
u
t
d
ata
o
f
v
ar
y
in
g
le
n
g
th
s
,
in
cl
u
d
in
g
m
i
s
s
in
g
o
r
in
co
m
p
lete
d
ata.
T
h
is
m
ak
es
L
STM
s
p
ar
ticu
lar
ly
s
u
itab
le
f
o
r
an
aly
zin
g
d
ata
o
v
e
r
s
ev
er
al
m
o
n
th
s
to
a
y
ea
r
.
T
h
is
s
tu
d
y
u
s
ed
7
5
%
o
f
th
e
d
ataset
f
r
o
m
2
0
1
6
to
2
0
1
8
f
o
r
tr
ain
i
n
g
an
d
v
alid
atio
n
an
d
u
s
ed
th
e
r
em
ain
in
g
2
5
%
f
r
o
m
2
0
1
9
t
o
ev
alu
ate
th
e
m
o
d
el'
s
p
er
f
o
r
m
an
ce
.
At
ea
ch
tim
e
s
tep
,
th
e
L
STM
n
etwo
r
k
r
ec
eiv
es
an
in
p
u
t
v
ec
to
r
(
)
,
th
e
ce
ll
s
tate
(
−
1
)
,
th
e
p
r
ec
ed
in
g
h
id
d
en
s
tate
(
ℎ
−
1
)
,
an
d
an
in
p
u
t
v
ec
to
r
.
W
e
n
ex
t
u
s
e
(
1
)
-
(
6
)
to
ca
lc
u
late
th
e
n
ew
h
id
d
en
s
tate
(
ℎ
)
,
ce
ll st
ate
(
)
an
d
in
p
u
t g
ate
(
).
(
)
=
(
+
ℎ
(
−
1
)
+
)
(
1
)
(
)
=
(
+
ℎ
(
−
1
)
+
)
(
2
)
(
t_t
il
de
)
=
ℎ
(
_
+
ℎ
(
−
1
)
+
)
(
3
)
(
)
=
(
+
ℎ
(
−
1
)
+
)
(
4
)
(
)
=
⊗
−
1
+
⊗
_
(
5
)
ℎ
(
ℎ
)
=
⊗
ℎ
(
6
)
I
n
an
L
STM
n
etwo
r
k
,
th
e
s
ig
m
o
id
f
u
n
ctio
n
(
σ
)
an
d
⊗
elem
en
t
-
wis
e
m
u
ltip
licatio
n
ar
e
k
ey
o
p
er
atio
n
s
.
T
h
e
in
p
u
t
v
ec
to
r
at
tim
e
s
tep
is
wh
ile
ℎ
−
1
an
d
−
1
r
ep
r
esen
t
th
e
p
r
e
v
io
u
s
h
id
d
en
a
n
d
ce
ll
s
tates.
T
h
e
f
o
r
g
et,
in
p
u
t,
an
d
o
u
tp
u
t g
ates a
r
e
u
n
d
er
th
e
co
n
t
r
o
lled
b
y
weig
h
t
m
atr
ices a
n
d
b
ias v
ec
to
r
s
(
,
,
,
,
,
,
,
,
,
,
,
an
d
)
,
wh
ich
d
eter
m
i
n
e
th
e
am
o
u
n
t
o
f
i
n
f
o
r
m
atio
n
r
et
ain
ed
o
r
d
is
ca
r
d
ed
.
Ho
w
m
u
c
h
o
f
th
e
p
r
io
r
ce
ll
s
tate
s
h
o
u
ld
b
e
r
em
em
b
er
e
d
is
d
ec
id
ed
b
y
t
h
e
f
o
r
g
et
g
ate
.
Ho
w
m
u
ch
o
f
th
e
ca
n
d
id
ate
ce
ll
s
tate
−
s
h
o
u
ld
b
e
a
d
d
ed
to
th
e
ce
ll
s
tate
is
d
eter
m
in
ed
b
y
th
e
in
p
u
t
g
ate.
T
h
e
o
u
tp
u
t
g
ate
d
eter
m
in
es
h
o
w
m
u
ch
o
f
t
h
e
cu
r
r
en
t
ce
ll
s
tate
s
h
o
u
ld
b
e
o
u
tp
u
t
as
th
e
h
id
d
e
n
s
tate
ℎ
.
B
ac
k
p
r
o
p
ag
atio
n
th
r
o
u
g
h
tim
e
tr
ai
n
s
th
e
n
etwo
r
k
to
m
in
im
ize
lo
s
s
f
u
n
ctio
n
s
s
u
ch
as
MSE
,
R
MSE
,
o
r
MA
PE.
Hy
p
er
p
ar
a
m
eter
s
,
wh
ich
d
ef
i
n
e
th
e
n
etwo
r
k
'
s
ar
ch
itectu
r
e
an
d
b
eh
av
io
r
,
ar
e
cr
u
cial
f
o
r
ac
c
u
r
ate
lo
a
d
f
o
r
ec
asti
n
g
.
T
o
p
r
ev
e
n
t
u
n
d
e
r
f
itti
n
g
o
r
o
v
er
f
itti
n
g
an
d
en
s
u
r
e
o
p
tim
al
p
er
f
o
r
m
an
ce
,
w
e
m
u
s
t
tu
n
e
th
o
s
e
u
tili
zin
g
tech
n
iq
u
es su
ch
as PSO,
GW
O,
HP
O,
an
d
o
p
p
o
s
itio
n
-
b
ased
HPO.
3
.
4
.
O
pp
o
s
it
io
n ba
s
e
d hun
t
e
r
prey
o
ptim
iza
t
i
o
n
HPO,
a
p
o
p
u
latio
n
-
b
ased
m
eth
o
d
f
o
r
o
p
tim
izin
g
h
y
p
er
p
ar
a
m
eter
s
,
b
en
ef
its
f
r
o
m
in
teg
r
atin
g
OB
L
t
o
en
h
an
ce
ex
p
l
o
r
atio
n
,
ex
p
lo
itatio
n
,
c
o
n
v
e
r
g
en
ce
s
p
ee
d
,
an
d
r
o
b
u
s
tn
ess
.
OB
L
g
en
e
r
ates
a
v
ar
iety
o
f
s
o
lu
tio
n
s
,
ass
is
tin
g
in
escap
in
g
lo
ca
l
o
p
tim
a
an
d
ac
ce
ler
atin
g
co
n
v
er
g
e
n
ce
wh
ile
r
ed
u
cin
g
s
en
s
itiv
ity
to
in
itial
co
n
d
itio
n
s
a
n
d
n
o
is
e.
T
h
e
iter
ativ
e
OHPO
p
r
o
ce
s
s
o
p
tim
ize
s
p
r
ey
l
o
ca
tio
n
s
with
OB
L
,
all
o
win
g
th
e
h
u
n
ter
to
ad
ju
s
t
b
ased
o
n
th
e
o
p
tim
al
p
r
ey
lo
ca
tio
n
,
m
ak
i
n
g
it
ef
f
e
ctiv
e
f
o
r
L
STM
m
o
d
els.
Fig
u
r
e
1
illu
s
tr
ates
th
e
OHPO
p
r
o
ce
s
s
.
I
n
itially
,
th
e
p
o
p
u
latio
n
is
r
an
d
o
m
ly
s
et
as
to
(
⃗
)
=
{
1
⃗
⃗
⃗
⃗
,
2
⃗
⃗
⃗
⃗
⃗
,
…,
⃗
⃗
⃗
⃗
⃗
},
A
p
r
o
p
o
s
ed
a
lg
o
r
ith
m
r
ev
is
es
in
d
iv
id
u
al
p
o
s
itio
n
s
in
ea
ch
iter
atio
n
,
ev
alu
ates
th
em
u
s
in
g
an
o
b
jectiv
e
f
u
n
cti
o
n
,
an
d
g
en
er
ates
a
r
an
d
o
m
p
o
p
u
latio
n
to
ap
p
l
y
a
n
o
p
p
o
s
itio
n
-
b
ased
s
tr
ateg
y
,
w
h
ich
is
b
e
n
ef
icial
f
o
r
c
o
m
p
lex
,
n
o
n
lin
ea
r
s
o
lu
tio
n
s
p
ac
es with
n
u
m
er
o
u
s
lo
ca
l
o
p
tim
a.
,
d
en
o
tes th
e
c
u
r
r
en
t so
l
u
tio
n
.
,
=
+
−
,
(
7
)
E
q
u
a
t
i
o
n
(
7
)
c
o
m
b
i
n
e
s
o
p
p
o
s
i
t
i
o
n
-
b
a
s
e
d
a
n
d
r
a
n
d
o
m
s
o
l
u
t
i
o
n
s
w
i
t
h
i
n
d
e
f
i
n
e
d
b
o
u
n
d
s
t
o
e
v
a
l
u
a
t
e
f
i
t
n
e
s
s
,
g
u
i
d
e
d
b
y
a
l
g
o
r
i
t
h
m
i
c
r
u
l
es
a
n
d
s
t
r
at
e
g
i
e
s
.
P
o
s
i
t
i
o
n
s
o
f
p
o
p
u
l
a
t
i
o
n
m
e
m
b
e
r
s
a
r
e
it
e
r
a
ti
v
e
l
y
a
d
j
u
s
t
e
d
t
o
e
n
h
a
n
c
e
s
o
l
u
t
i
o
n
s
,
e
v
a
l
u
a
t
e
d
b
y
t
h
e
o
b
je
c
t
i
v
e
f
u
n
c
t
i
o
n
.
E
q
u
a
ti
o
n
(
8
)
r
a
n
d
o
m
l
y
a
s
s
i
g
n
s
p
o
s
it
i
o
n
s
wi
t
h
in
t
h
e
s
e
a
r
c
h
s
p
a
c
e
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
A
co
mp
a
r
a
tive
s
tu
d
y
o
f lo
n
g
s
h
o
r
t
-
term me
mo
r
y
b
a
s
ed
lo
n
g
-
term e
lectrica
l lo
a
d
…
(
Gee
th
a
Ma
n
i
)
7083
=
(
1
,
)
•
∗
(
−
)
+
(
8
)
I
n
th
is
ca
s
e,
r
e
p
r
esen
ts
th
e
l
o
ca
tio
n
o
f
th
e
h
u
n
ter
o
r
p
r
ey
,
is
a
r
an
d
o
m
v
alu
e
b
etwe
en
0
a
n
d
1
,
d
en
o
tes
th
e
p
r
o
b
lem
v
ar
ia
b
les'
lo
west
v
alu
e
(
lo
wer
b
o
u
n
d
ar
y
)
,
d
en
o
tes
th
eir
h
ig
h
e
s
t
v
alu
e
(
u
p
p
er
b
o
u
n
d
ar
y
)
,
a
n
d
d
e
n
o
tes
th
e
p
r
o
b
lem
'
s
to
tal
n
u
m
b
e
r
o
f
v
ar
iab
les
(
d
im
e
n
s
io
n
s
)
.
C
alc
u
latin
g
th
e
f
itn
ess
f
u
n
ctio
n
d
eter
m
in
es
wh
ich
s
o
l
u
tio
n
h
o
l
d
s
th
e
o
p
tim
al
h
y
p
er
p
ar
am
eter
s
f
o
r
e
f
f
ec
tiv
e
lo
n
g
-
ter
m
elec
tr
ical
lo
ad
f
o
r
ec
asti
n
g
.
Fig
u
r
e
1
.
Flo
w
ch
a
r
t o
f
o
p
p
o
s
itio
n
-
b
ased
h
u
n
ter
p
r
ey
o
p
tim
i
za
tio
n
E
q
u
atio
n
s
(
9
)
-
(
1
2
)
ca
lcu
late
t
h
e
f
itn
ess
o
f
ea
ch
s
o
lu
tio
n
o
n
c
e
th
e
in
itial
p
o
p
u
latio
n
is
cr
ea
t
ed
an
d
th
e
p
o
s
itio
n
s
o
f
ea
ch
a
g
en
t a
r
e
d
et
er
m
in
ed
.
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.
14
,
No
.
6
,
Dec
em
b
e
r
20
24
:
7
0
8
0
-
7
0
8
9
7084
=
1
∑
(
−
^
)
=
1
2
(
9
)
=
√
∑
(
−
^
)
2
=
1
(
1
0
)
=
1
∑
|
−
^
|
=
1
(
1
1
)
(
)
=
+
+
3
(
1
2
)
T
h
e
p
r
o
p
o
s
ed
s
ea
r
ch
m
ec
h
an
is
m
o
p
t
im
ize
s
h
y
p
er
p
a
r
am
et
e
r
s
b
y
d
i
r
ec
t
in
g
ag
e
n
t
s
to
wa
r
d
s
o
p
t
im
al
p
o
s
it
io
n
s
th
r
o
u
g
h
t
wo
s
t
ep
s
:
ex
p
lo
r
at
io
n
an
d
ex
p
lo
it
at
io
n
.
E
x
p
lo
r
at
io
n
in
v
o
lv
es
r
an
d
o
m
b
e
h
av
io
r
s
,
r
ev
e
al
in
g
p
r
o
m
i
s
in
g
ar
ea
s
,
wh
i
le
ex
p
lo
i
ta
tio
n
m
i
n
im
iz
e
s
th
e
s
e
b
eh
av
i
o
r
s
to
f
ac
i
li
ta
te
s
ea
r
ch
in
g
ar
o
u
n
d
th
e
s
e
id
en
t
if
i
ed
ar
ea
s
.
,
(
+
1
)
=
,
(
)
+
0
.
5
[
(
2
(
)
−
,
(
)
)
+
(
2
(
1
−
)
(
)
−
,
(
)
)
]
(
1
3
)
E
q
u
atio
n
(
1
3
)
is
r
esp
o
n
s
ib
le
f
o
r
u
p
d
atin
g
th
e
h
u
n
ter
'
s
cu
r
r
e
n
t
p
o
s
itio
n
r
ep
r
esen
ted
b
y
(
)
b
ased
o
n
th
e
n
ex
t
p
o
s
itio
n
(
(
−
1
)
)
,
th
e
p
r
ey
'
s
p
o
s
itio
n
(
)
,
th
e
m
ea
n
o
f
all
p
o
s
itio
n
s
(
l
)
,
an
d
an
a
d
ap
tiv
e
p
ar
am
eter
(
Z
)
ca
lcu
lated
u
s
in
g
(
1
4
)
.
=
⃗
⃗
1
<
C
;
IDX
=
(
p
=
=
0
)
;
=
2
⊗
+
⃗
⃗
3
⊗
(
~
I
DX
)
(
1
4
)
I
n
th
is
s
ce
n
ar
i
o
,
⃗
⃗
1
an
d
⃗
⃗
3
ar
e
r
a
n
d
o
m
v
ec
to
r
s
(
0
-
1
)
,
is
a
b
in
a
r
y
v
ec
t
o
r
(
0
o
r
1
)
in
d
icatin
g
t
h
e
n
u
m
b
er
o
f
p
r
o
b
lem
v
a
r
iab
les,
2
is
a
r
an
d
o
m
n
u
m
b
er
(
0
-
1
)
,
a
n
d
I
DX
in
d
ex
es
⃗
⃗
1
wh
er
e
==
0
.
Par
am
eter
g
o
v
er
n
s
ex
p
lo
r
atio
n
v
er
s
u
s
ex
p
lo
itatio
n
,
r
ed
u
cin
g
g
r
ad
u
ally
f
r
o
m
1
t
o
0
.
0
2
ac
r
o
s
s
iter
atio
n
s
u
s
in
g
(
1
5
)
.
=
1
−
(
0
.
98
)
(
1
5
)
is
th
e
m
ax
im
u
m
n
u
m
b
er
o
f
it
er
atio
n
s
,
an
d
iter
r
e
f
er
s
to
th
e
cu
r
r
en
t
iter
atio
n
v
alu
e.
W
h
er
e
th
e
f
ir
s
t
s
tep
is
to
ca
lcu
late
th
e
av
er
ag
e
p
o
s
itio
n
o
f
all
s
ea
r
ch
ag
en
ts
u
s
in
g
(
1
6
)
an
d
d
en
o
te
it
as
µ
.
Fin
d
in
g
ea
ch
s
ea
r
ch
ag
en
t'
s
d
is
tan
ce
f
r
o
m
th
e
m
ea
n
p
o
s
itio
n
is
th
e
s
ec
o
n
d
s
tag
e.
=
1
∑
⃗
=
1
(
1
6
)
Usi
n
g
(
1
7
)
t
o
ca
lcu
late
th
e
d
is
tan
ce
b
ased
o
n
th
e
E
u
clid
ea
n
d
is
tan
ce
(
),
(
)
=
(
∑
(
,
−
)
2
=
1
)
1
2
(
1
7
)
E
q
u
atio
n
(
1
8
)
s
tates th
at
th
e
p
r
ey
(
)
is
th
e
s
ea
r
ch
ag
en
t w
ith
th
e
lar
g
est d
is
tan
ce
f
r
o
m
th
e
m
ea
n
p
o
s
itio
n
.
⃗
⃗
=
⃗
⁄
⥂
(
)
(
)
(
1
8
)
T
h
e
co
n
v
e
r
g
en
ce
o
f
th
e
alg
o
r
i
th
m
will
b
e
d
elay
ed
if
we
co
n
t
in
u
o
u
s
ly
s
elec
t
th
e
s
ea
r
ch
ag
e
n
t
th
at
h
as
th
e
g
r
ea
test
d
is
tan
ce
f
r
o
m
th
e
m
ea
n
p
o
s
itio
n
(
µ)
at
th
e
en
d
o
f
ea
ch
iter
atio
n
.
I
n
th
e
h
u
n
ti
n
g
co
n
tex
t,
t
h
e
p
r
ey
d
ies
wh
en
it
is
ca
u
g
h
t,
f
o
r
cin
g
th
e
h
u
n
ter
to
m
o
v
e
o
n
t
o
a
n
e
w
tar
g
et.
E
q
u
atio
n
(
1
9
)
d
escr
i
b
es
th
e
d
ec
r
ea
s
in
g
m
eth
o
d
we
em
p
lo
y
t
o
ad
d
r
ess
th
is
p
r
o
b
lem
.
=
(
×
)
(
1
9
)
wh
er
e
N
r
ep
r
esen
ts
th
e
q
u
a
n
tity
o
f
s
ea
r
c
h
ag
e
n
ts
.
W
e
n
o
w
ad
ju
s
t
(
1
8
)
an
d
u
tili
ze
(
2
0
)
t
o
d
eter
m
in
e
th
e
p
r
ey
p
o
s
itio
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
A
co
mp
a
r
a
tive
s
tu
d
y
o
f lo
n
g
s
h
o
r
t
-
term me
mo
r
y
b
a
s
ed
lo
n
g
-
term e
lectrica
l lo
a
d
…
(
Gee
th
a
Ma
n
i
)
7085
⃗
⃗
=
⃗
⁄
⥂
(
)
(
2
0
)
I
n
i
t
i
a
ll
y
,
k
b
e
s
t
e
q
u
a
ls
,
t
h
e
c
o
u
n
t
o
f
s
e
a
r
c
h
a
g
e
n
t
s
.
T
h
e
h
u
n
t
e
r
t
a
r
g
e
t
s
t
h
e
f
a
r
t
h
es
t
s
e
a
r
c
h
a
g
e
n
t
f
r
o
m
t
h
e
a
v
e
r
a
g
e
p
o
s
i
t
i
o
n
(
µ
)
f
o
r
at
t
a
c
k
.
E
a
c
h
i
t
e
r
at
i
o
n
s
o
r
ts
o
f
a
g
e
n
ts
b
y
d
i
s
t
a
n
c
e
f
r
o
m
µ
.
T
h
e
o
p
tim
a
l
g
l
o
b
a
l
p
o
s
it
i
o
n
o
f
f
e
r
s
a
s
a
f
e
a
r
e
a
f
o
r
s
e
le
c
t
i
n
g
p
r
e
y
,
i
n
c
r
e
a
s
i
n
g
p
r
e
y
s
u
r
v
i
v
a
l
ch
a
n
c
e
s
.
E
q
u
a
t
i
o
n
(
2
1
)
u
p
d
a
t
e
s
th
e
p
r
e
y
'
s
p
o
s
i
ti
o
n
.
,
(
+
1
)
=
(
)
+
(
2
4
)
×
(
(
)
−
,
(
)
)
(
2
1
)
T
h
e
f
o
r
m
u
la
d
escr
ib
es
a
d
y
n
am
ic
p
r
ey
p
o
s
itio
n
(
)
an
d
its
f
u
tu
r
e
(
+
1
)
,
o
p
tim
ized
at
with
ad
ap
tiv
ely
d
ete
r
m
in
ed
(
1
4
)
,
an
d
a
d
ju
s
ted
b
y
r
an
d
o
m
4
.
Par
am
eter
,
b
alan
cin
g
e
x
p
lo
r
atio
n
an
d
ex
p
lo
itatio
n
,
d
ec
r
ea
s
es
iter
ativ
ely
(
1
5
)
.
T
h
e
m
eth
o
d
u
s
es
C
OS
f
o
r
ex
p
lo
itatio
n
,
p
o
s
itio
n
in
g
p
r
ey
at
v
ar
y
in
g
an
g
les
f
r
o
m
.
E
q
u
atio
n
(
2
2
)
,
in
teg
r
atin
g
(
1
3
)
an
d
(
2
1
)
,
in
clu
d
es
β
=
0
.
1
an
d
r
an
d
o
m
5
(0
-
1
)
:
if
5
<
,
th
e
ag
en
t h
u
n
ts
,
u
p
d
atin
g
v
ia
(
2
2
a)
; if
5
>
,
it p
r
ey
s
,
u
p
d
atin
g
v
ia
(
2
2
b
)
.
(
+
1
)
=
{
(
)
+
.
5
[
(
2
−
(
)
)
+
(
2
(
1
−
)
−
(
)
)
]
5
(
22
)
+
(
2
4
)
×
(
−
(
)
)
(
22
)
(
2
2
)
Op
p
o
s
itio
n
-
b
ased
s
tr
ateg
ies
en
h
an
ce
t
h
e
p
e
r
f
o
r
m
an
ce
o
f
HPO
tech
n
iq
u
es
b
y
in
t
r
o
d
u
cin
g
a
co
m
p
lem
en
tar
y
s
ea
r
ch
d
ir
ec
ti
o
n
.
I
n
tr
ad
itio
n
al
HPO,
p
r
e
y
(
o
p
tim
al
s
o
lu
tio
n
s
)
is
s
o
u
g
h
t
b
y
p
r
ed
ato
r
s
(
s
ea
r
ch
ag
en
ts
)
in
a
co
m
p
etitiv
e
m
an
n
er
.
OHPO
in
tr
o
d
u
ce
s
a
p
ar
allel
s
ea
r
ch
f
o
r
s
o
lu
tio
n
s
th
at
ar
e
o
p
p
o
s
ite
(
co
m
p
lem
en
t
)
to
th
e
cu
r
r
en
t
b
est
s
o
lu
tio
n
s
f
o
u
n
d
.
T
h
is
d
u
al
-
d
ir
ec
tio
n
s
ea
r
ch
in
cr
ea
s
es
th
e
ex
p
lo
r
atio
n
o
f
th
e
s
ea
r
ch
s
p
ac
e,
p
o
ten
tially
d
is
c
o
v
er
in
g
b
etter
s
o
lu
tio
n
s
f
aster
an
d
m
o
r
e
r
o
b
u
s
tly
.
I
n
L
T
L
F,
th
is
ap
p
r
o
ac
h
aim
s
to
im
p
r
o
v
e
th
e
id
en
tific
atio
n
o
f
o
p
tim
al
h
y
p
er
p
ar
am
eter
s
,
en
h
an
cin
g
th
e
m
o
d
el'
s
p
r
ed
ictiv
e
ac
cu
r
ac
y
an
d
ef
f
icien
cy
.
4.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
e
s
tu
d
y
u
tili
ze
d
elec
tr
ical
l
o
ad
d
ata
f
r
o
m
th
e
2
3
0
/1
1
0
k
V
au
to
s
u
b
s
tatio
n
in
C
o
im
b
at
o
r
e,
T
am
il
Nad
u
,
I
n
d
ia,
r
ec
o
r
d
e
d
at
1
0
-
m
in
u
te
in
ter
v
als
f
r
o
m
2
0
1
6
t
o
2
0
1
9
,
alo
n
g
s
id
e
clim
ate
d
at
a.
E
ig
h
t
in
d
ep
en
d
en
t
v
ar
iab
les,
in
clu
d
in
g
tem
p
e
r
atu
r
e,
win
d
s
p
ee
d
,
an
d
h
u
m
i
d
ity
,
wer
e
an
aly
ze
d
.
W
e
u
tili
ze
d
th
e
OHPO
tech
n
iq
u
e
to
o
p
tim
ize
h
y
p
er
p
a
r
am
eter
s
f
o
r
an
L
STM
m
o
d
el
to
f
o
r
ec
ast
lo
n
g
-
ter
m
elec
tr
ical
lo
ad
.
OHPO,
a
m
etah
eu
r
is
tic
alg
o
r
ith
m
,
m
im
ics
p
r
ed
ato
r
-
p
r
ey
d
y
n
am
ics
to
en
h
a
n
ce
s
ea
r
ch
ef
f
icien
c
y
.
OHPO
-
co
n
f
ig
u
r
e
d
L
STM
d
id
b
etter
th
a
n
o
t
h
er
m
eth
o
d
s
in
lo
n
g
-
ter
m
lo
ad
f
o
r
ec
asti
n
g
,
as
s
h
o
wn
b
y
MSE
,
R
MSE
,
an
d
MA
PE
test
s
.
T
h
is
was b
ec
au
s
e
it u
s
ed
an
o
p
p
o
s
itio
n
-
b
ased
s
tr
ateg
y
.
Fig
u
r
es 2
to
7
illu
s
tr
ate
th
ese
f
in
d
in
g
s
.
T
h
e
s
tu
d
y
ev
al
u
ated
v
ar
io
u
s
L
T
L
F
ap
p
r
o
ac
h
es
u
s
in
g
L
S
T
M
m
o
d
els
b
y
co
m
p
ar
in
g
t
h
eir
MSE
,
R
MSE
,
an
d
MA
PE.
T
h
e
OHPO
-
co
n
f
ig
u
r
ed
L
STM
m
o
d
el
d
em
o
n
s
tr
ated
th
e
b
est
p
er
f
o
r
m
a
n
ce
with
th
e
lo
west
MSE
(
0
.
2
5
)
,
R
MSE
(
0
.
5
)
,
an
d
MA
PE
(
0
.
2
7
)
,
in
d
icatin
g
th
e
h
ig
h
est
ac
cu
r
ac
y
.
T
h
e
HPO
-
co
n
f
ig
u
r
ed
L
STM
was
th
e
s
ec
o
n
d
b
est,
with
an
R
MSE
o
f
1
an
d
a
h
ig
h
e
r
MA
PE
v
alu
e.
GW
O
an
d
PS
O
-
co
n
f
ig
u
r
ed
L
STM
tech
n
iq
u
es
h
ad
h
ig
h
e
r
R
MSE
an
d
MA
PE
v
alu
es,
wh
ile
tr
a
d
itio
n
al
L
STM
s
h
o
wed
s
ig
n
if
ican
t
im
p
r
o
v
e
m
en
t
th
r
o
u
g
h
h
y
p
er
p
a
r
am
eter
o
p
tim
izatio
n
,
wh
ich
is
estab
lis
h
ed
in
Fig
u
r
es 8
(
a)
to
8
(
c)
.
Fig
u
r
e
2.
C
o
m
p
a
r
is
o
n
o
f
th
e
a
ctu
al
an
d
tr
ad
itio
n
a
l
ANN
m
o
d
el
p
r
ed
icted
v
alu
es
f
o
r
L
T
L
F
Fig
u
r
e
3.
C
o
m
p
a
r
is
o
n
o
f
r
ea
l
v
alu
es v
s
co
n
v
e
n
tio
n
a
l
L
STM
m
o
d
el
p
r
e
d
icted
v
alu
es
f
o
r
L
T
L
F
M
on
t
h
M
on
t
h
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.
14
,
No
.
6
,
Dec
em
b
e
r
20
24
:
7
0
8
0
-
7
0
8
9
7086
Fig
u
r
e
4
.
C
o
m
p
a
r
is
o
n
b
etwe
e
n
th
e
PS
O
-
co
n
f
ig
u
r
ed
L
STM
m
o
d
el
p
r
e
d
icted
v
alu
es
f
o
r
L
T
L
F a
n
d
th
e
ac
tu
al
v
alu
es
Fig
u
r
e
5
.
C
o
m
p
a
r
is
o
n
o
f
th
e
GW
O
-
co
n
f
ig
u
r
ed
L
STM
m
o
d
el'
s
p
r
ed
icted
v
alu
es f
o
r
L
T
L
F with
th
e
ac
tu
al
v
alu
es
Fig
u
r
e
6
.
C
o
m
p
ar
is
o
n
o
f
HPO
-
co
n
f
ig
u
r
ed
L
STM
m
o
d
el
p
r
e
d
icted
v
alu
es
f
o
r
L
T
L
F with
ac
tu
al
v
alu
es
Fig
u
r
e
7.
C
o
m
p
a
r
is
o
n
o
f
ac
tu
a
l v
alu
es
v
s
OHPO
co
n
f
ig
u
r
ed
L
STM
m
o
d
el
p
r
ed
icted
v
alu
es
f
o
r
L
T
L
F
(
a)
(
b
)
(
c)
Fig
u
r
e
8
.
C
o
m
p
a
r
is
o
n
o
f
(
a)
MSE
,
(
b
)
R
MSE
,
(
c)
MA
PE
f
o
r
d
if
f
e
r
en
t te
ch
n
iq
u
es
in
L
T
L
F
M
on
t
h
M
on
t
h
M
on
t
h
M
on
t
h
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
A
co
mp
a
r
a
tive
s
tu
d
y
o
f lo
n
g
s
h
o
r
t
-
term me
mo
r
y
b
a
s
ed
lo
n
g
-
term e
lectrica
l lo
a
d
…
(
Gee
th
a
Ma
n
i
)
7087
5.
CO
NCLU
SI
O
N
T
h
is
s
tu
d
y
p
r
o
p
o
s
es
an
ap
p
r
o
ac
h
to
d
ev
elo
p
i
n
g
an
L
T
L
F
m
o
d
el
f
o
r
th
e
C
o
im
b
ato
r
e
r
eg
io
n
in
T
am
il
Nad
u
,
I
n
d
ia.
Usi
n
g
L
STM
n
et
wo
r
k
s
an
d
o
p
p
o
s
itio
n
-
b
ased
le
ar
n
in
g
in
th
e
h
u
n
ter
-
p
r
ey
o
p
tim
izatio
n
tech
n
iq
u
e
to
tu
n
e
h
y
p
er
p
ar
am
eter
s
s
ig
n
if
ican
tly
im
p
r
o
v
ed
th
e
m
o
d
el's
ac
cu
r
ac
y
.
T
h
e
r
esu
lts
d
em
o
n
s
tr
ate
th
at
th
e
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
o
u
tp
er
f
o
r
m
s
co
m
p
ar
ativ
e
tech
n
i
q
u
es
i
n
ter
m
s
o
f
v
ar
io
u
s
er
r
o
r
m
e
asu
r
es
f
o
r
L
T
L
F,
ac
h
iev
in
g
an
MSE
o
f
0
.
2
5
,
R
MSE
o
f
0
.
5
,
an
d
MA
PE
o
f
0
.
2
7
.
T
h
ese
f
in
d
in
g
s
ar
e
cr
u
cial
f
o
r
th
e
p
o
wer
s
y
s
tem
in
d
u
s
tr
y
,
as
ac
cu
r
ate
L
T
L
F
is
ess
en
tial
f
o
r
p
lan
n
in
g
a
n
d
m
an
ag
in
g
f
u
tu
r
e
e
n
er
g
y
d
em
an
d
s
.
Mo
r
eo
v
er
,
th
e
ap
p
r
o
ac
h
s
h
o
ws
p
o
ten
tial
f
o
r
en
h
an
cin
g
L
T
L
F
n
o
t
o
n
ly
i
n
C
o
im
b
ato
r
e
b
u
t
also
in
o
th
er
r
eg
io
n
s
.
W
h
ile
t
h
is
s
tu
d
y
m
ak
es
im
p
o
r
tan
t
co
n
tr
i
b
u
tio
n
s
to
th
e
f
ield
o
f
L
T
L
F,
th
er
e
ar
e
lim
itatio
n
s
th
at
f
u
t
u
r
e
r
esear
ch
co
u
l
d
ad
d
r
ess
.
Fo
r
in
s
tan
ce
,
ex
p
a
n
d
in
g
th
e
s
tu
d
y
s
co
p
e
to
in
cl
u
d
e
ad
d
itio
n
al
r
eg
io
n
s
o
r
ex
p
lo
r
in
g
alter
n
ativ
e
o
p
tim
izatio
n
tech
n
iq
u
es
co
u
l
d
y
ield
f
u
r
th
e
r
in
s
ig
h
ts
.
Ov
er
all,
th
is
r
esear
ch
o
f
f
er
s
a
p
r
o
m
is
in
g
ap
p
r
o
ac
h
to
ad
d
r
ess
in
g
th
e
ch
allen
g
e
o
f
L
T
L
F a
n
d
h
o
l
d
s
s
ig
n
if
ican
t im
p
licatio
n
s
f
o
r
th
e
p
o
wer
s
y
s
tem
in
d
u
s
tr
y
.
RE
F
E
R
E
NC
E
[
1
]
Z.
Y
u
,
Z.
N
i
u
,
W
.
Ta
n
g
,
a
n
d
Q
.
W
u
,
“
D
e
e
p
l
e
a
r
n
i
n
g
f
o
r
d
a
i
l
y
p
e
a
k
l
o
a
d
f
o
r
e
c
a
st
i
n
g
—
a
n
o
v
e
l
g
a
t
e
d
r
e
c
u
r
r
e
n
t
n
e
u
r
a
l
n
e
t
w
o
r
k
c
o
m
b
i
n
i
n
g
d
y
n
a
mi
c
t
i
me
w
a
r
p
i
n
g
,
”
I
EEE
A
c
c
e
ss
,
v
o
l
.
7
,
p
p
.
1
7
1
8
4
–
1
7
1
9
4
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
1
9
.
2
8
9
5
6
0
4
.
[
2
]
B
.
J
i
a
n
g
e
t
a
l
.
,
“
D
y
n
a
mi
c
t
e
mp
o
r
a
l
d
e
p
e
n
d
e
n
c
y
m
o
d
e
l
f
o
r
m
u
l
t
i
p
l
e
st
e
p
s
a
h
e
a
d
s
h
o
r
t
-
t
e
r
m
l
o
a
d
f
o
r
e
c
a
s
t
i
n
g
o
f
p
o
w
e
r
sy
s
t
e
m
,
”
I
EEE
T
r
a
n
s
a
c
t
i
o
n
s
o
n
I
n
d
u
st
ry
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
6
0
,
n
o
.
4
,
p
p
.
5
2
4
4
–
5
2
5
4
,
Ju
l
.
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
t
i
a
.
2
0
2
4
.
3
3
7
5
8
0
2
.
[
3
]
H
.
H
.
Ç
e
v
i
k
a
n
d
M
.
Ç
u
n
k
a
ş,
“
S
h
o
r
t
-
t
e
r
m
l
o
a
d
f
o
r
e
c
a
st
i
n
g
u
s
i
n
g
f
u
z
z
y
l
o
g
i
c
a
n
d
A
N
F
I
S
,
”
N
e
u
r
a
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
.
2
6
,
n
o
.
6
,
p
p
.
1
3
5
5
–
1
3
6
7
,
J
a
n
.
2
0
1
5
,
d
o
i
:
1
0
.
1
0
0
7
/
s
0
0
5
2
1
-
014
-
1
8
0
9
-
4.
[
4
]
S
.
K
a
r
t
h
i
k
a
,
V
.
M
a
r
g
a
r
e
t
,
a
n
d
K
.
B
a
l
a
r
a
ma
n
,
“
H
y
b
r
i
d
sh
o
r
t
t
e
r
m
l
o
a
d
f
o
r
e
c
a
st
i
n
g
u
s
i
n
g
A
R
I
M
A
-
S
V
M
,
”
2
0
1
7
I
n
n
o
v
a
t
i
o
n
s
i
n
Po
w
e
r
a
n
d
A
d
v
a
n
c
e
d
C
o
m
p
u
t
i
n
g
T
e
c
h
n
o
l
o
g
i
e
s (i
-
P
AC
T
)
,
V
e
l
l
o
r
e
,
I
n
d
i
a
,
2
0
1
7
,
p
p
.
1
-
7,
d
o
i
:
1
0
.
1
1
0
9
/
i
p
a
c
t
.
2
0
1
7
.
8
2
4
5
0
6
0
.
[
5
]
M
.
L
u
y
,
V
.
A
t
e
s,
N
.
B
a
r
i
sci
,
H
.
P
o
l
a
t
,
a
n
d
E.
C
a
m
,
“
S
h
o
r
t
-
t
e
r
m f
u
z
z
y
l
o
a
d
f
o
r
e
c
a
st
i
n
g
m
o
d
e
l
u
s
i
n
g
g
e
n
e
t
i
c
–
f
u
z
z
y
a
n
d
a
n
t
c
o
l
o
n
y
–
f
u
z
z
y
k
n
o
w
l
e
d
g
e
b
a
s
e
o
p
t
i
m
i
z
a
t
i
o
n
,
”
Ap
p
l
i
e
d
S
c
i
e
n
c
e
s
,
v
o
l
.
8
,
n
o
.
6
,
M
a
y
2
0
1
8
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
8
0
6
0
8
6
4
.
[
6
]
A
.
A
l
M
a
m
u
n
,
M
.
S
o
h
e
l
,
N
.
M
o
h
a
m
mad
,
M
.
S
.
H
a
q
u
e
S
u
n
n
y
,
D
.
R
.
D
i
p
t
a
,
a
n
d
E.
H
o
ssa
i
n
,
“
A
c
o
m
p
r
e
h
e
n
si
v
e
r
e
v
i
e
w
o
f
t
h
e
l
o
a
d
f
o
r
e
c
a
st
i
n
g
t
e
c
h
n
i
q
u
e
s
u
s
i
n
g
si
n
g
l
e
a
n
d
h
y
b
r
i
d
p
r
e
d
i
c
t
i
v
e
mo
d
e
l
s,
”
I
E
EE
Ac
c
e
ss
,
v
o
l
.
8
,
p
p
.
1
3
4
9
1
1
–
1
3
4
9
3
9
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
a
c
c
e
s
s.
2
0
2
0
.
3
0
1
0
7
0
2
.
[
7
]
K
.
B
.
L
i
n
d
b
e
r
g
,
P
.
S
e
l
j
o
m
,
H
.
M
a
d
s
e
n
,
D
.
F
i
s
c
h
e
r
,
a
n
d
M
.
K
o
r
p
å
s,
“
L
o
n
g
-
t
e
r
m
e
l
e
c
t
r
i
c
i
t
y
l
o
a
d
f
o
r
e
c
a
st
i
n
g
:
c
u
r
r
e
n
t
a
n
d
f
u
t
u
r
e
t
r
e
n
d
s,
”
U
t
i
l
i
t
i
e
s
P
o
l
i
c
y
,
v
o
l
.
5
8
,
p
p
.
1
0
2
–
1
1
9
,
Ju
n
.
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
u
p
.
2
0
1
9
.
0
4
.
0
0
1
.
[
8
]
S
.
R
.
K
h
u
n
t
i
a
,
J.
L.
R
u
e
d
a
,
a
n
d
M
.
A
.
M
.
M
.
d
e
r
M
e
i
j
d
e
n
,
“
Lo
n
g
-
t
e
r
m
e
l
e
c
t
r
i
c
i
t
y
l
o
a
d
f
o
r
e
c
a
st
i
n
g
c
o
n
s
i
d
e
r
i
n
g
v
o
l
a
t
i
l
i
t
y
u
si
n
g
mu
l
t
i
p
l
i
c
a
t
i
v
e
e
r
r
o
r
m
o
d
e
l
,
”
En
e
rg
i
e
s
,
v
o
l
.
1
1
,
n
o
.
1
2
,
N
o
v
.
2
0
1
8
,
d
o
i
:
1
0
.
3
3
9
0
/
e
n
1
1
1
2
3
3
0
8
.
[
9
]
M
.
S
.
H
o
ss
a
i
n
a
n
d
H
.
M
a
h
m
o
o
d
,
“
S
h
o
r
t
-
t
e
r
m
l
o
a
d
f
o
r
e
c
a
s
t
i
n
g
u
s
i
n
g
a
n
LST
M
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
I
EEE
P
o
w
e
r
a
n
d
En
e
r
g
y
C
o
n
f
e
re
n
c
e
a
t
I
l
l
i
n
o
i
s (PE
C
I
)
,
F
e
b
.
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
p
e
c
i
4
8
3
4
8
.
2
0
2
0
.
9
0
6
4
6
5
4
.
[
1
0
]
S
.
Zh
a
n
g
,
R
.
C
h
e
n
,
J.
C
a
o
,
a
n
d
J.
T
a
n
,
“
A
C
N
N
a
n
d
LST
M
-
b
a
s
e
d
m
u
l
t
i
-
t
a
sk
l
e
a
r
n
i
n
g
a
r
c
h
i
t
e
c
t
u
r
e
f
o
r
s
h
o
r
t
a
n
d
me
d
i
u
m
-
t
e
r
m
e
l
e
c
t
r
i
c
i
t
y
l
o
a
d
f
o
r
e
c
a
st
i
n
g
,
”
El
e
c
t
r
i
c
Po
w
e
r
S
y
s
t
e
m
s
Re
s
e
a
r
c
h
,
v
o
l
.
2
2
2
,
S
e
p
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
p
sr
.
2
0
2
3
.
1
0
9
5
0
7
.
[
1
1
]
M
.
J
.
A
.
S
h
o
h
a
n
,
M
.
O
.
F
a
r
u
q
u
e
,
a
n
d
S
.
Y
.
F
o
o
,
“
F
o
r
e
c
a
st
i
n
g
o
f
e
l
e
c
t
r
i
c
l
o
a
d
u
s
i
n
g
a
h
y
b
r
i
d
LST
M
-
N
e
u
r
a
l
P
r
o
p
h
e
t
m
o
d
e
l
,
”
En
e
r
g
i
e
s
,
v
o
l
.
1
5
,
n
o
.
6
,
M
a
r
.
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
e
n
1
5
0
6
2
1
5
8
.
[
1
2
]
N
.
M
o
u
n
i
r
,
H
.
O
u
a
d
i
,
a
n
d
I
.
Jr
h
i
l
i
f
a
,
“
S
h
o
r
t
-
t
e
r
m
e
l
e
c
t
r
i
c
l
o
a
d
f
o
r
e
c
a
st
i
n
g
u
si
n
g
a
n
EM
D
-
BI
-
LSTM
a
p
p
r
o
a
c
h
f
o
r
smar
t
g
r
i
d
e
n
e
r
g
y
ma
n
a
g
e
me
n
t
sy
s
t
e
m
,
”
En
e
r
g
y
a
n
d
Bu
i
l
d
i
n
g
s
,
v
o
l
.
2
8
8
,
Ju
n
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
n
b
u
i
l
d
.
2
0
2
3
.
1
1
3
0
2
2
.
[
1
3
]
I
.
S
.
Jah
a
n
,
V
.
S
n
a
sel
,
a
n
d
S
.
M
i
s
a
k
,
“
I
n
t
e
l
l
i
g
e
n
t
sy
s
t
e
ms
f
o
r
p
o
w
e
r
l
o
a
d
f
o
r
e
c
a
st
i
n
g
:
a
s
t
u
d
y
r
e
v
i
e
w
,
”
En
e
rg
i
e
s
,
v
o
l
.
1
3
,
n
o
.
2
2
,
N
o
v
.
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
e
n
1
3
2
2
6
1
0
5
.
[
1
4
]
S
.
H
.
R
a
f
i
,
N
a
h
i
d
-
Al
-
M
a
s
o
o
d
,
S
.
R
.
D
e
e
b
a
,
a
n
d
E.
H
o
ssa
i
n
,
“
A
s
h
o
r
t
-
t
e
r
m
l
o
a
d
f
o
r
e
c
a
s
t
i
n
g
me
t
h
o
d
u
si
n
g
i
n
t
e
g
r
a
t
e
d
C
N
N
a
n
d
LSTM
n
e
t
w
o
r
k
,
”
I
EE
E
A
c
c
e
ss
,
v
o
l
.
9
,
p
p
.
3
2
4
3
6
–
3
2
4
4
8
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
a
c
c
e
ss
.
2
0
2
1
.
3
0
6
0
6
5
4
.
[
1
5
]
M
.
A
b
d
a
l
l
a
h
,
N
.
A
n
Le
K
h
a
c
,
H
.
Ja
h
r
o
m
i
,
a
n
d
A
.
D
e
l
i
a
Ju
r
c
u
t
,
“
A
h
y
b
r
i
d
C
N
N
-
LST
M
b
a
s
e
d
a
p
p
r
o
a
c
h
f
o
r
a
n
o
m
a
l
y
d
e
t
e
c
t
i
o
n
sy
st
e
ms
i
n
S
D
N
s,”
T
h
e
1
6
t
h
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
Av
a
i
l
a
b
i
l
i
t
y
,
Re
l
i
a
b
i
l
i
t
y
a
n
d
S
e
c
u
r
i
t
y
,
V
i
e
n
n
a
,
A
u
st
r
i
a
,
A
u
g
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
4
5
/
3
4
6
5
4
8
1
.
3
4
6
9
1
9
0
.
[
1
6
]
S
.
W
a
n
g
,
C
.
M
a
,
Y
.
X
u
,
J
.
W
a
n
g
,
a
n
d
W
.
W
u
,
“
A
h
y
p
e
r
p
a
r
a
me
t
e
r
o
p
t
i
m
i
z
a
t
i
o
n
a
l
g
o
r
i
t
h
m
f
o
r
t
h
e
LST
M
t
e
mp
e
r
a
t
u
r
e
p
r
e
d
i
c
t
i
o
n
mo
d
e
l
i
n
d
a
t
a
c
e
n
t
e
r
,
”
S
c
i
e
n
t
i
f
i
c
Pr
o
g
ra
m
m
i
n
g
,
v
o
l
.
2
0
2
2
,
p
p
.
1
–
1
3
,
D
e
c
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
2
/
6
5
1
9
9
0
9
.
[
1
7
]
B
.
N
a
k
i
sa
,
M
.
N
.
R
a
st
g
o
o
,
A
.
R
a
k
o
t
o
n
i
r
a
i
n
y
,
F
.
M
a
i
r
e
,
a
n
d
V
.
C
h
a
n
d
r
a
n
,
“
Lo
n
g
s
h
o
r
t
t
e
r
m
mem
o
r
y
h
y
p
e
r
p
a
r
a
m
e
t
e
r
o
p
t
i
m
i
z
a
t
i
o
n
f
o
r
a
n
e
u
r
a
l
n
e
t
w
o
r
k
b
a
se
d
e
m
o
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
f
r
a
mew
o
r
k
,
”
I
EE
E
Ac
c
e
ss
,
v
o
l
.
6
,
p
p
.
4
9
3
2
5
–
4
9
3
3
8
,
2
0
1
8
,
d
o
i
:
1
0
.
1
1
0
9
/
a
c
c
e
s
s.
2
0
1
8
.
2
8
6
8
3
6
1
.
[
1
8
]
Y.
-
Y
.
H
o
n
g
a
n
d
Y
.
-
H
.
C
h
a
n
,
“
S
h
o
r
t
-
t
e
r
m
e
l
e
c
t
r
i
c
l
o
a
d
f
o
r
e
c
a
s
t
i
n
g
u
si
n
g
p
a
r
t
i
c
l
e
sw
a
r
m
o
p
t
i
mi
z
a
t
i
o
n
-
b
a
s
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
,
”
E
n
g
i
n
e
e
r
i
n
g
Ap
p
l
i
c
a
t
i
o
n
s
o
f
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
1
2
6
,
N
o
v
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
n
g
a
p
p
a
i
.
2
0
2
3
.
1
0
6
7
7
3
.
[
1
9
]
Z.
S
h
a
f
i
e
i
C
h
a
f
i
a
n
d
H
.
A
f
r
a
k
h
t
e
,
“
S
h
o
r
t
-
t
e
r
m
l
o
a
d
f
o
r
e
c
a
s
t
i
n
g
u
si
n
g
n
e
u
r
a
l
n
e
t
w
o
r
k
a
n
d
p
a
r
t
i
c
l
e
sw
a
r
m
o
p
t
i
mi
z
a
t
i
o
n
(
P
S
O
)
a
l
g
o
r
i
t
h
m,
”
M
a
t
h
e
m
a
t
i
c
a
l
Pr
o
b
l
e
m
s
i
n
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
2
0
2
1
,
p
p
.
1
–
1
0
,
A
p
r
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
1
/
5
5
9
8
2
6
7
.
[
2
0
]
A
.
M
.
M
.
A
L
-
Q
a
y
s
i
,
A
.
B
o
z
k
u
r
t
,
a
n
d
Y
.
A
t
e
s
,
“
Lo
a
d
f
o
r
e
c
a
s
t
i
n
g
b
a
se
d
o
n
g
e
n
e
t
i
c
a
l
g
o
r
i
t
h
m
–
a
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
-
a
d
a
p
t
i
v
e
n
e
u
r
o
-
f
u
z
z
y
i
n
f
e
r
e
n
c
e
sy
s
t
e
ms
:
a
c
a
se
st
u
d
y
i
n
I
r
a
q
,
”
En
e
rg
i
e
s
,
v
o
l
.
1
6
,
n
o
.
6
,
M
a
r
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
e
n
1
6
0
6
2
9
1
9
.
[
2
1
]
S
.
M
.
S
w
a
my
,
B
.
M
.
M
a
r
sa
l
i
n
e
,
a
n
d
I
.
R
.
V
a
l
a
r
m
a
t
h
i
,
“
P
r
e
d
i
c
t
i
n
g
s
o
l
a
r
p
o
w
e
r
p
o
t
e
n
t
i
a
l
v
i
a
r
e
f
u
r
b
i
s
h
e
d
A
N
N
i
n
a
sso
c
i
a
t
e
d
w
i
t
h
a
r
t
i
f
i
c
i
a
l
f
i
s
h
sw
a
r
m
o
p
t
i
m
i
z
a
t
i
o
n
(
A
F
S
O
)
,
”
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
S
c
i
e
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
2
9
,
n
o
.
5
,
p
p
.
2
8
1
2
–
2
8
2
5
,
2
0
2
0
.
[
2
2
]
L.
S
h
a
o
,
Q
.
G
u
o
,
C
.
L
i
,
J.
L
i
,
a
n
d
H
.
Y
a
n
,
“
S
h
o
r
t
-
t
e
r
m
l
o
a
d
f
o
r
e
c
a
st
i
n
g
b
a
se
d
o
n
EE
M
D
-
W
O
A
-
LSTM
c
o
mb
i
n
a
t
i
o
n
mo
d
e
l
,
”
Ap
p
l
i
e
d
B
i
o
n
i
c
s
a
n
d
Bi
o
m
e
c
h
a
n
i
c
s
,
v
o
l
.
2
0
2
2
,
p
p
.
1
–
1
4
,
A
u
g
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
2
/
2
1
6
6
0
8
2
.
[
2
3
]
S
.
R
.
I
n
k
o
l
l
u
,
G
.
V
.
P
.
A
n
j
a
n
e
y
u
l
u
,
K
o
t
a
i
a
h
N
.
C
.
,
a
n
d
N
a
g
a
r
a
j
a
K
u
mari
.
C
H
,
“
A
n
a
p
p
l
i
c
a
t
i
o
n
o
f
h
u
n
t
e
r
-
p
r
e
y
o
p
t
i
m
i
z
a
t
i
o
n
f
o
r
max
i
mi
z
i
n
g
p
h
o
t
o
v
o
l
t
a
i
c
h
o
st
i
n
g
c
a
p
a
c
i
t
y
a
l
o
n
g
w
i
t
h
m
u
l
t
i
-
o
b
j
e
c
t
i
v
e
o
p
t
i
mi
z
a
t
i
o
n
i
n
r
a
d
i
a
l
d
i
s
t
r
i
b
u
t
i
o
n
n
e
t
w
o
r
k
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
I
n
t
e
l
l
i
g
e
n
t
E
n
g
i
n
e
e
r
i
n
g
a
n
d
S
y
s
t
e
m
s
,
v
o
l
.
1
5
,
n
o
.
4
,
A
u
g
.
2
0
2
2
,
d
o
i
:
1
0
.
2
2
2
6
6
/
i
j
i
e
s
2
0
2
2
.
0
8
3
1
.
5
2
.
[
2
4
]
W
.
Lo
n
g
,
J
.
Ji
a
o
,
X
.
L
i
a
n
g
,
S
.
C
a
i
,
a
n
d
M
.
X
u
,
“
A
r
a
n
d
o
m
o
p
p
o
si
t
i
o
n
-
b
a
s
e
d
l
e
a
r
n
i
n
g
g
r
e
y
w
o
l
f
o
p
t
i
mi
z
e
r
,
”
I
E
EE
Ac
c
e
ss
,
v
o
l
.
7
,
p
p
.
1
1
3
8
1
0
–
1
1
3
8
2
5
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
a
c
c
e
s
s.
2
0
1
9
.
2
9
3
4
9
9
4
.
[
2
5
]
N
.
A
.
M
o
h
a
mm
e
d
a
n
d
A
.
A
l
-
B
a
z
i
,
“
A
n
a
d
a
p
t
i
v
e
b
a
c
k
p
r
o
p
a
g
a
t
i
o
n
a
l
g
o
r
i
t
h
m
f
o
r
l
o
n
g
-
t
e
r
m
e
l
e
c
t
r
i
c
i
t
y
l
o
a
d
f
o
r
e
c
a
s
t
i
n
g
,
”
N
e
u
r
a
l
C
o
m
p
u
t
i
n
g
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
3
4
,
n
o
.
1
,
p
p
.
4
7
7
–
4
9
1
,
A
u
g
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
0
7
/
s
0
0
5
2
1
-
0
2
1
-
0
6
3
8
4
-
x.
[
2
6
]
S
.
M
o
a
l
e
m
,
R
.
M
.
A
h
a
r
i
,
G
.
S
h
a
h
g
h
o
l
i
a
n
,
M
.
M
o
a
z
z
a
mi
,
a
n
d
S
.
M
.
K
a
z
e
mi
,
“
L
o
n
g
-
t
e
r
m
e
l
e
c
t
r
i
c
i
t
y
d
e
m
a
n
d
f
o
r
e
c
a
st
i
n
g
i
n
t
h
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.
14
,
No
.
6
,
Dec
em
b
e
r
20
24
:
7
0
8
0
-
7
0
8
9
7088
st
e
e
l
c
o
m
p
l
e
x
mi
c
r
o
-
g
r
i
d
e
l
e
c
t
r
i
c
i
t
y
su
p
p
l
y
c
h
a
i
n
—
a
c
o
u
p
l
e
d
a
p
p
r
o
a
c
h
,
”
En
e
rg
i
e
s
,
v
o
l
.
1
5
,
n
o
.
2
1
,
O
c
t
.
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
e
n
1
5
2
1
7
9
7
2
.
[
2
7
]
X
.
Li
,
Y
.
W
a
n
g
,
G
.
M
a
,
X
.
C
h
e
n
,
Q
.
S
h
e
n
,
a
n
d
B
.
Y
a
n
g
,
“
El
e
c
t
r
i
c
l
o
a
d
f
o
r
e
c
a
st
i
n
g
b
a
se
d
o
n
Lo
n
g
-
sh
o
r
t
-
t
e
r
m
-
memo
r
y
n
e
t
w
o
r
k
v
i
a
si
mp
l
e
x
o
p
t
i
mi
z
e
r
d
u
r
i
n
g
C
O
V
I
D
-
1
9
,
”
En
e
rg
y
R
e
p
o
r
t
s
,
v
o
l
.
8
,
p
p
.
1
–
1
2
,
S
e
p
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
g
y
r
.
2
0
2
2
.
0
3
.
0
5
1
.
[
2
8
]
F
.
M
.
B
u
t
t
e
t
a
l
.
,
“
I
n
t
e
l
l
i
g
e
n
c
e
b
a
se
d
a
c
c
u
r
a
t
e
me
d
i
u
m
a
n
d
l
o
n
g
t
e
r
m
l
o
a
d
f
o
r
e
c
a
st
i
n
g
s
y
st
e
m,
”
Ap
p
l
i
e
d
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
3
6
,
n
o
.
1
,
Ju
n
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
8
0
/
0
8
8
3
9
5
1
4
.
2
0
2
2
.
2
0
8
8
4
5
2
.
[
2
9
]
Y
.
L
i
,
Y
.
Z
h
a
n
g
,
a
n
d
Y
.
C
a
i
,
“
A
n
e
w
h
y
p
e
r
-
p
a
r
a
me
t
e
r
o
p
t
i
m
i
z
a
t
i
o
n
me
t
h
o
d
f
o
r
p
o
w
e
r
l
o
a
d
f
o
r
e
c
a
st
b
a
se
d
o
n
r
e
c
u
r
r
e
n
t
n
e
u
r
a
l
n
e
t
w
o
r
k
s,”
Al
g
o
ri
t
h
m
s
,
v
o
l
.
1
4
,
n
o
.
6
,
M
a
y
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
a
1
4
0
6
0
1
6
3
.
[
3
0
]
I
.
N
a
r
u
e
i
,
F
.
K
e
y
n
i
a
,
a
n
d
A
.
S
a
b
b
a
g
h
M
o
l
a
h
o
sse
i
n
i
,
“
H
u
n
t
e
r
–
p
r
e
y
o
p
t
i
m
i
z
a
t
i
o
n
:
a
l
g
o
r
i
t
h
m
a
n
d
a
p
p
l
i
c
a
t
i
o
n
s
,
”
S
o
f
t
C
o
m
p
u
t
i
n
g
,
v
o
l
.
2
6
,
n
o
.
3
,
p
p
.
1
2
7
9
–
1
3
1
4
,
D
e
c
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
0
7
/
s
0
0
5
0
0
-
0
2
1
-
0
6
4
0
1
-
0.
[
3
1
]
J.
Li
,
Y
.
G
a
o
,
K
.
W
a
n
g
,
a
n
d
Y
.
S
u
n
,
“
A
d
u
a
l
o
p
p
o
si
t
i
o
n
-
b
a
se
d
l
e
a
r
n
i
n
g
f
o
r
d
i
f
f
e
r
e
n
t
i
a
l
e
v
o
l
u
t
i
o
n
w
i
t
h
p
r
o
t
e
c
t
i
v
e
me
c
h
a
n
i
sm
f
o
r
e
n
g
i
n
e
e
r
i
n
g
o
p
t
i
m
i
z
a
t
i
o
n
p
r
o
b
l
e
ms,
”
Ap
p
l
i
e
d
S
o
f
t
C
o
m
p
u
t
i
n
g
,
v
o
l
.
1
1
3
,
D
e
c
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
s
o
c
.
2
0
2
1
.
1
0
7
9
4
2
.
[
3
2
]
F
.
S
a
y
e
e
d
,
K
.
R
.
A
h
me
d
,
a
n
d
S
.
M
.
S
w
a
my
,
“
A
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
b
a
s
e
d
s
u
c
c
o
r
e
d
p
o
w
e
r
p
r
e
d
i
c
t
i
o
n
i
n
s
t
a
n
d
a
l
o
n
e
P
V
s
y
s
t
e
m,
”
Au
st
ra
l
i
a
n
J
o
u
rn
a
l
o
f
E
l
e
c
t
r
i
c
a
l
a
n
d
El
e
c
t
r
o
n
i
c
s
E
n
g
i
n
e
e
r
i
n
g
,
p
p
.
1
–
1
4
,
A
p
r
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
8
0
/
1
4
4
8
8
3
7
x
.
2
0
2
4
.
2
3
4
5
9
9
2
.
BIO
G
RA
PH
IES
O
F
AU
TH
O
R
S
G
e
e
th
a
Ma
n
i
a
ss
istan
t
p
r
o
fe
ss
o
r
,
EEE
De
p
a
rtme
n
t
,
S
r
i
Es
h
wa
r
Co
ll
e
g
e
o
f
En
g
i
n
e
e
rin
g
,
Co
im
b
a
to
re
.
S
h
e
r
e
c
e
iv
e
d
h
e
r
B.
E.
,
d
e
g
re
e
in
e
lec
tro
n
ics
a
n
d
c
o
m
m
u
n
ica
ti
o
n
e
n
g
in
e
e
rin
g
a
n
d
M
.
E
.
i
n
p
o
we
r
e
lec
tro
n
ics
a
n
d
d
ri
v
e
s
).
S
h
e
c
o
m
p
lete
d
P
h
D
in
e
lec
tri
c
a
l
e
n
g
in
e
e
rin
g
in
An
n
a
U
n
iv
e
rsit
y
Ch
e
n
n
a
i
.
S
h
e
p
u
b
li
sh
e
d
m
o
re
th
a
n
1
5
p
a
p
e
rs
in
i
n
tern
a
ti
o
n
a
l
a
n
d
n
a
ti
o
n
a
l
j
o
u
r
n
a
ls.
Also
p
re
se
n
ted
m
o
re
th
a
n
1
0
p
a
p
e
rs
i
n
n
a
ti
o
n
a
l
a
n
d
in
tern
a
t
io
n
a
l
c
o
n
fe
re
n
c
e
s.
He
r
re
se
a
rc
h
in
tere
sts
a
c
c
u
m
u
late
in
th
e
a
re
a
o
f
p
o
we
r
e
lec
tro
n
ics
,
c
o
n
tro
l
sy
ste
m
s,
d
ig
i
tal
sy
ste
m
s
a
n
d
a
n
a
l
o
g
e
lec
tro
n
ics
.
S
h
e
is
m
e
m
b
e
r
o
f
IEE
E,
IAENG
,
a
n
d
IS
TE
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
e
n
g
rsu
g
e
e
th
a
a
@g
m
a
il
.
c
o
m
.
S
u
r
e
s
h
S
e
e
t
h
a
r
a
m
a
n
p
r
o
f
e
s
s
o
r
,
E
C
E
D
e
p
a
r
tm
e
n
t
,
S
r
i
E
s
h
w
a
r
c
o
l
l
e
g
e
o
f
E
n
g
i
n
e
e
r
i
n
g
,
C
o
i
m
b
a
t
o
r
e
,
r
e
c
e
i
v
e
d
h
i
s
B
.
E
.
,
d
e
g
r
e
e
i
n
e
l
e
c
t
r
i
c
a
l
a
n
d
e
l
e
c
t
r
o
n
i
c
s
e
n
g
i
n
e
e
r
i
n
g
f
r
o
m
B
h
a
r
a
t
h
i
a
r
U
n
i
v
e
rs
i
t
y
,
M
.
E
i
n
p
o
w
e
r
s
y
s
t
e
m
s
f
r
o
m
G
o
v
e
r
n
m
e
n
t
C
o
l
l
e
g
e
o
f
T
e
c
h
n
o
l
o
g
y
,
C
o
i
m
b
a
t
o
r
e
,
P
h
D
d
e
g
r
e
e
i
n
e
le
c
t
ric
a
l
e
n
g
i
n
e
e
r
i
n
g
i
n
A
n
n
a
U
n
i
v
e
r
s
i
ty
C
h
e
n
n
a
i
,
a
n
d
r
e
c
e
i
v
e
d
P
D
F
i
n
I
d
a
h
o
S
t
a
t
e
U
n
i
v
e
r
s
i
t
y
,
U
S
A
.
H
e
p
u
b
l
i
s
h
e
d
4
0
p
a
p
e
r
s
i
n
i
n
t
e
r
n
a
t
i
o
n
a
l
j
o
u
r
n
a
l
s
a
n
d
1
4
i
n
n
a
t
i
o
n
a
l
j
o
u
r
n
a
l
s
.
A
l
s
o
p
re
s
e
n
ted
3
8
p
a
p
e
r
s
i
n
n
a
t
i
o
n
a
l
a
n
d
i
n
t
e
r
n
a
t
i
o
n
a
l
c
o
n
f
e
re
n
c
e
s
.
H
is
r
e
s
e
a
r
c
h
i
n
t
e
r
e
s
t
s
a
c
c
u
m
u
l
a
te
i
n
t
h
e
a
r
e
a
o
f
p
o
w
e
r
s
y
s
t
e
m
,
p
o
w
e
r
e
l
e
c
t
r
o
n
i
c
s
,
c
o
n
t
r
o
l
a
n
d
d
i
g
i
t
a
l
s
y
s
t
e
m
s
,
a
n
d
s
m
a
r
t
g
r
i
d
.
H
e
i
s
a
m
e
m
b
e
r
o
f
I
S
T
E
,
I
E
T
E
,
I
A
ENG
(Ho
n
g
k
o
n
g
)
S
e
n
i
o
r
M
e
m
b
e
r
o
f
I
E
E
E
,
(
U
S
A
)
a
n
d
F
e
l
l
o
w
M
e
m
b
e
r
I
E
.
H
e
c
a
n
b
e
c
o
n
t
a
c
t
e
d
a
t
e
m
a
i
l
:
e
n
g
r
r
s
u
r
e
s
h
@
g
m
a
i
l
.
c
o
m
.
J
o
th
i
n
a
t
h
a
n
K
a
n
d
a
sa
m
y
is
a
s
so
c
iate
p
ro
fe
ss
o
r
wit
h
th
e
De
p
a
rt
m
e
n
t
o
f
El
e
c
tri
c
a
l
a
n
d
E
lec
tro
n
ics
En
g
in
e
e
rin
g
An
n
a
m
a
lai
Un
iv
e
rsit
y
,
A
n
n
a
m
a
lai
Na
g
a
r,
Ch
i
d
a
m
b
a
ra
m
,
In
d
ia.
He
re
c
e
iv
e
d
th
e
BE
De
g
re
e
i
n
E
lec
tri
c
a
l
a
n
d
El
e
c
tr
o
n
ics
E
n
g
in
e
e
rin
g
a
n
d
th
e
M
E
d
e
g
re
e
i
n
P
o
we
r
S
y
ste
m
fro
m
An
n
a
m
a
lai
Un
iv
e
rsity
.
He
re
c
e
iv
e
d
P
h
.
D.
d
e
g
re
e
in
th
e
y
e
a
r
o
f
2
0
1
7
fr
o
m
An
n
a
m
a
lai
Un
iv
e
rsity
,
A
n
n
a
m
a
lai
Na
g
a
r.
His
re
se
a
r
c
h
to
p
ic
in
c
l
u
d
e
s
p
o
we
r
sy
ste
m
o
p
e
ra
ti
o
n
a
n
d
c
o
n
tro
l
,
se
c
u
rit
y
An
a
l
y
sis.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
jo
th
i.
e
e
a
u
@g
m
a
il
.
c
o
m
.
Le
k
shm
y
Pre
m
a
c
h
a
n
d
r
a
n
La
d
h
a
re
c
e
iv
e
d
h
e
r
P
h
.
D.
in
c
o
m
p
u
ter
sc
ien
c
e
a
n
d
e
n
g
in
e
e
rin
g
fr
o
m
th
e
U
n
iv
e
rsit
y
o
f
Ke
ra
la
in
Ja
n
u
a
ry
2
0
2
2
.
S
h
e
e
a
rn
e
d
h
e
r
b
a
c
h
e
lo
r’s
d
e
g
re
e
in
i
n
fo
rm
a
ti
o
n
tec
h
n
o
l
o
g
y
fr
o
m
M
.
S
.
Un
i
v
e
rsity
,
Tam
il
Na
d
u
,
in
2
0
0
4
,
a
n
d
h
e
r
m
a
ste
r’s
d
e
g
re
e
in
c
o
m
p
u
ter
sc
ien
c
e
a
n
d
e
n
g
i
n
e
e
rin
g
fro
m
Ka
r
u
n
y
a
De
e
m
e
d
Un
iv
e
rsity
,
C
o
imb
a
to
re
,
in
2
0
0
6
.
S
h
e
is
c
u
rre
n
t
ly
a
n
a
ss
ist
a
n
t
p
r
o
fe
ss
o
r
i
n
c
o
m
p
u
ter
sc
ien
c
e
a
n
d
e
n
g
in
e
e
rin
g
a
t
LBS
In
stit
u
te o
f
Tec
h
n
o
l
o
g
y
fo
r
Wo
m
e
n
,
Tri
v
a
n
d
r
u
m
,
a
n
d
th
e
Un
iv
e
rsi
ty
o
f
Ke
ra
la
sin
c
e
2
0
0
8
.
He
r
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
p
riv
a
c
y
-
p
re
se
rv
in
g
d
a
ta
m
i
n
in
g
,
m
a
c
h
in
e
lea
rn
i
n
g
,
d
e
e
p
lea
rn
i
n
g
,
a
n
d
b
ig
d
a
ta an
a
ly
t
ics
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
lek
s
h
m
y
y
v
i
n
o
d
@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
A
co
mp
a
r
a
tive
s
tu
d
y
o
f lo
n
g
s
h
o
r
t
-
term me
mo
r
y
b
a
s
ed
lo
n
g
-
term e
lectrica
l lo
a
d
…
(
Gee
th
a
Ma
n
i
)
7089
Ani
sh
J
o
h
n
Pa
u
l
Mo
h
a
n
d
a
s
is
a
d
isti
n
g
u
ish
e
d
re
se
a
rc
h
e
r
in
re
n
e
wa
b
le
e
n
e
rg
y
sy
ste
m
s,
h
o
ld
i
n
g
a
d
o
c
to
ra
te
in
h
y
b
ri
d
re
n
e
wa
b
le
e
n
e
rg
y
sy
ste
m
s
a
n
d
a
p
o
st
g
ra
d
u
a
te
d
e
g
re
e
in
e
n
e
rg
y
e
n
g
i
n
e
e
rin
g
.
Wi
t
h
o
v
e
r
1
2
y
e
a
rs
a
s
h
e
a
d
o
f
t
h
e
De
p
a
rtme
n
t
o
f
EE
E,
Dr.
An
ish
Jo
h
n
P
a
u
l
h
a
s
led
imp
a
c
tfu
l
re
se
a
rc
h
a
n
d
m
a
n
a
g
e
d
in
n
o
v
a
ti
v
e
p
ro
jec
ts
i
n
h
y
b
ri
d
re
n
e
wa
b
le
e
n
e
r
g
y
sy
ste
m
s.
Th
e
ir
w
o
rk
h
a
s
si
g
n
ifi
c
a
n
tl
y
a
d
v
a
n
c
e
d
t
h
e
field
o
f
su
sta
in
a
b
le
e
n
e
rg
y
tec
h
n
o
l
o
g
ies
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
a
n
i
sh
jo
h
n
p
a
u
l@g
m
a
il
.
c
o
m
.
S
wa
m
y
S
i
v
a
su
b
r
a
m
o
n
i
a
m
is
a
se
a
so
n
e
d
re
se
a
rc
h
e
r
a
n
d
d
a
ta
s
c
ien
ti
st
with
o
v
e
r
n
in
e
y
e
a
rs
o
f
e
x
p
e
rien
c
e
a
t
RYG
OT
-
Te
c
h
n
o
l
o
g
ies
.
His
wo
r
k
is
fo
c
u
se
d
o
n
a
d
v
a
n
c
in
g
th
e
field
s
o
f
a
rti
f
icia
l
in
tel
li
g
e
n
c
e
(
AI)
a
n
d
m
a
c
h
in
e
lea
rn
i
n
g
(M
L)
.
He
h
a
s
m
a
d
e
sig
n
if
ica
n
t
c
o
n
tri
b
u
ti
o
n
s
th
r
o
u
g
h
h
is
in
n
o
v
a
t
iv
e
re
se
a
rc
h
a
n
d
a
p
p
li
c
a
ti
o
n
o
f
A
I/M
L
tec
h
n
iq
u
e
s,
h
e
lp
i
n
g
to
d
riv
e
fo
rwa
rd
t
h
e
c
o
m
p
a
n
y
'
s
str
a
teg
ic
g
o
a
ls
a
n
d
sh
a
p
e
t
h
e
fu
tu
r
e
o
f
th
e
se
ra
p
id
ly
e
v
o
lv
in
g
d
isc
ip
li
n
e
s.
His
e
x
p
e
rti
se
a
n
d
d
e
d
ica
ti
o
n
h
a
v
e
e
sta
b
li
sh
e
d
h
im
a
s
a
lea
d
in
g
fi
g
u
re
in
th
e
in
d
u
stry
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
sw
a
m
y
.
sm
8
6
@g
m
a
il
.
c
o
m
.
Va
la
r
m
a
th
i
Iy
a
p
p
a
n
Re
n
u
g
a
d
e
v
i
re
c
e
iv
e
d
h
e
r
m
a
ste
r’s
d
e
g
re
e
(M
CA)
fro
m
M
S
Un
iv
e
rsity
i
n
2
0
1
1
.
S
h
e
o
b
tai
n
e
d
h
e
r
b
a
c
h
e
l
o
r’s
d
e
g
re
e
i
n
BS
c
c
o
m
p
u
ter
sc
ien
c
e
fr
o
m
M
S
Un
iv
e
rsity
in
2
0
0
9
.
Cu
r
re
n
tl
y
,
sh
e
wo
rk
s
a
s
a
re
se
a
rc
h
a
ss
o
c
iate
in
m
a
c
h
in
e
lea
rn
i
n
g
a
n
d
d
a
ta
sc
ien
c
e
a
t
RYG
OT
Tec
h
n
o
lo
g
ies
.
He
r
c
u
rre
n
t
re
se
a
rc
h
i
n
tere
sts
i
n
c
lu
d
e
a
rti
ficia
l
i
n
telli
g
e
n
c
e
a
n
d
m
a
c
h
in
e
lea
rn
i
n
g
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
v
a
larm
a
th
i.
j1
@g
m
a
il
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.