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
.
1
,
Feb
r
u
ar
y
20
25
,
p
p
.
995
~
1
0
0
6
I
SS
N:
2088
-
8
7
0
8
,
DOI
: 1
0
.
1
1
5
9
1
/
ijece
.
v
15
i
1
.
pp
9
9
5
-
1
006
995
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
H
y
brid d
eep l
ea
rning
f
o
r esti
ma
tion o
f
sta
te
-
of
-
hea
lt
h
in lit
hium
-
io
n bat
terie
s
Denis
E
k
a
Ca
hy
a
ni
1
,
L
a
ng
la
ng
G
um
ila
r
2
,
Arif
Nur
Af
a
n
di
2
,
Aj
i P
ra
s
et
y
a
Wiba
wa
2
,
Ahm
a
d K
a
dri J
un
o
h
3
1
D
e
p
a
r
t
me
n
t
o
f
M
a
t
h
e
m
a
t
i
c
s
,
F
a
c
u
l
t
y
o
f
M
a
t
h
e
mat
i
c
s
a
n
d
N
a
t
u
r
a
l
S
c
i
e
n
c
e
s,
U
n
i
v
e
r
s
i
t
a
s Ne
g
e
r
i
M
a
l
a
n
g
,
M
a
l
a
n
g
,
I
n
d
o
n
e
si
a
2
D
e
p
a
r
t
me
n
t
E
l
e
c
t
r
i
c
a
l
E
n
g
i
n
e
e
r
i
n
g
,
F
a
c
u
l
t
y
o
f
E
n
g
i
n
e
e
r
i
n
g
,
U
n
i
v
e
r
si
t
a
s
N
e
g
e
r
i
M
a
l
a
n
g
,
M
a
l
a
n
g
,
I
n
d
o
n
e
si
a
3
I
n
st
i
t
u
t
e
o
f
E
n
g
i
n
e
e
r
i
n
g
M
a
t
h
e
ma
t
i
c
s
,
U
n
i
v
e
r
si
t
i
M
a
l
a
y
s
i
a
P
e
r
l
i
s
,
P
e
r
l
i
s
,
M
a
l
a
y
si
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
n
6
,
2
0
2
4
R
ev
is
ed
Au
g
3
1
,
2
0
2
4
Acc
ep
ted
Oct
1
,
2
0
2
4
Li
th
i
u
m
-
io
n
(li
-
i
o
n
)
b
a
tt
e
ries
h
a
v
e
a
h
ig
h
e
n
e
rg
y
d
e
n
sit
y
a
n
d
a
lo
n
g
c
y
c
le
li
fe
.
Li
t
h
iu
m
-
i
o
n
b
a
tt
e
ries
h
a
v
e
a
fin
it
e
li
fe
sp
a
n
,
a
n
d
t
h
e
ir
e
n
e
rg
y
sto
ra
g
e
c
a
p
a
c
it
y
d
imin
is
h
e
s
with
u
se
.
In
o
rd
e
r
to
p
ro
p
e
rly
p
lan
b
a
tt
e
r
y
m
a
in
ten
a
n
c
e
,
th
e
sta
te
o
f
h
e
a
lt
h
(
S
o
H)
o
f
li
t
h
i
u
m
-
io
n
b
a
tt
e
ries
is
c
ru
c
ial.
Th
is
stu
d
y
a
ims
to
c
o
m
b
i
n
e
two
d
e
e
p
lea
rn
i
n
g
t
e
c
h
n
iq
u
e
s
(h
y
b
rid
d
e
e
p
lea
rn
in
g
),
n
a
m
e
ly
c
o
n
v
o
lu
ti
o
n
a
l
n
e
u
ra
l
n
e
two
rk
(
CNN
)
a
n
d
b
i
d
irec
ti
o
n
a
l
lo
n
g
s
h
o
rt
-
term
m
e
m
o
ry
(BiL
S
TM
)
,
fo
r
S
o
H
e
stim
a
ti
o
n
i
n
li
-
i
o
n
b
a
tt
e
ries
.
T
h
is
st
u
d
y
c
o
n
tras
ts
h
y
b
rid
d
e
e
p
lea
rn
i
n
g
m
e
th
o
d
s
to
sin
g
le
d
e
e
p
lea
rn
i
n
g
m
o
d
e
ls
so
th
a
t
t
h
e
m
o
st
su
i
tab
le
m
o
d
e
l
fo
r
a
c
c
u
ra
tely
m
e
a
su
rin
g
th
e
S
o
H
i
n
li
th
iu
m
-
i
o
n
b
a
tt
e
ries
c
a
n
b
e
d
e
term
in
e
d
.
In
c
o
m
p
a
riso
n
t
o
o
th
e
r
m
e
th
o
d
o
lo
g
ies
,
CNN
-
BiL
S
TM
y
ield
s
t
h
e
b
e
st
re
su
lt
s.
T
h
e
CNN
-
BiL
S
TM
a
lg
o
rit
h
m
y
ield
s
RM
S
E,
m
e
a
n
sq
u
a
re
e
rro
r
(M
S
E)
,
m
e
a
n
a
b
so
lu
te
e
rro
r
(M
AE)
,
a
n
d
m
e
a
n
a
b
so
lu
te
p
e
rc
e
n
tag
e
e
rro
r
(
M
APE
)
in
th
e
f
o
ll
o
wi
n
g
o
r
d
e
r:
0
.
0
0
9
1
6
,
0
.
0
0
0
0
8
4
,
0
.
0
0
4
8
,
a
n
d
0
.
0
0
6
0
3
.
Th
is
i
n
d
ica
tes
th
a
t
CNN
-
BiL
S
TM
,
a
s
a
h
y
b
rid
d
e
e
p
lea
rn
in
g
m
o
d
e
l,
is
a
b
le
to
c
a
lcu
late
th
e
a
p
p
ro
x
ima
te
c
a
p
a
c
it
y
o
f
th
e
li
t
h
iu
m
-
i
o
n
b
a
tt
e
ry
m
o
re
a
c
c
u
ra
tely
th
a
n
o
t
h
e
r
m
e
th
o
d
s.
K
ey
w
o
r
d
s
:
B
id
ir
ec
tio
n
al
lo
n
g
s
h
o
r
t
-
ter
m
m
em
o
r
y
C
o
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
h
y
b
r
id
d
ee
p
lea
r
n
in
g
L
ith
iu
m
-
I
on
L
o
n
g
s
h
o
r
t
-
ter
m
m
e
m
o
r
y
r
ec
u
r
r
en
t
n
eu
r
al
n
etwo
r
k
s
State
-
of
-
h
ea
lth
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
:
Den
is
E
k
a
C
ah
y
an
i
Dep
ar
tm
en
t o
f
Ma
th
em
atics,
Facu
lty
o
f
Ma
th
e
m
atics a
n
d
Na
tu
r
al
Scien
ce
s
,
Un
iv
er
s
itas
Neg
er
i M
alan
g
J
l.
Sem
ar
an
g
No
.
5
,
Su
m
b
er
s
ar
i,
L
o
wo
k
war
u
,
Ma
lan
g
,
E
ast
Ja
v
a
6
5
1
4
5
,
I
n
d
o
n
esia
E
m
ail: d
en
is
.
ek
a.
ca
h
y
a
n
i.f
m
ip
a@
u
m
.
ac
.
id
1.
I
NT
RO
D
UCT
I
O
N
L
ith
iu
m
-
io
n
(
li
-
i
o
n
)
b
atter
ies
h
av
e
a
h
ig
h
en
er
g
y
d
e
n
s
ity
an
d
a
lo
n
g
cy
cle
life
[
1
]
.
L
ith
iu
m
-
io
n
b
atter
ies
ca
n
o
p
tim
ize
en
er
g
y
u
tili
za
tio
n
f
r
o
m
s
o
lar
p
an
els
an
d
p
r
o
v
id
e
a
r
eliab
le
en
e
r
g
y
s
u
p
p
ly
w
h
en
it
is
n
ee
d
ed
[
2
]
.
Ho
wev
er
,
lith
iu
m
-
io
n
b
atter
ies
h
av
e
a
r
estricte
d
s
h
elf
life
an
d
ex
p
er
ie
n
ce
a
d
ec
lin
e
in
en
er
g
y
s
to
r
ag
e
ca
p
ac
ity
o
v
e
r
tim
e
an
d
u
s
e
[
3
]
.
T
h
is
ca
n
in
f
lu
en
ce
t
h
e
p
er
f
o
r
m
an
ce
o
f
th
e
eq
u
ip
m
en
t
an
d
th
e
b
atter
y
life
.
State
o
f
Hea
lth
esti
m
ati
o
n
o
n
lith
iu
m
-
io
n
b
atter
ies
in
cr
ea
s
es
b
atter
y
u
tili
za
tio
n
ef
f
icien
cy
as
a
r
esu
lt.
E
s
tim
atin
g
th
e
s
tate
o
f
h
ea
l
th
(
So
H)
o
f
lith
iu
m
-
io
n
b
att
er
ies
ca
n
b
e
ac
co
m
p
lis
h
ed
u
s
in
g
a
v
ar
iety
o
f
tech
n
iq
u
es,
s
u
ch
as
b
atter
y
s
e
n
s
o
r
s
,
m
ath
em
atica
l
m
o
d
els,
v
is
u
al
m
eth
o
d
s
,
an
d
d
ee
p
lear
n
in
g
m
eth
o
d
s
b
ased
o
n
b
atter
y
m
a
n
ag
em
e
n
t
tech
n
o
lo
g
y
[
4
]
,
[
5
]
.
Dee
p
lear
n
i
n
g
o
f
f
e
r
s
m
o
r
e
ac
cu
r
ate
esti
m
ates
o
f
So
H
an
d
r
em
ain
in
g
u
s
ef
u
l
life
(
R
UL
)
th
an
th
e
o
t
h
er
m
eth
o
d
s
an
d
en
ab
les
s
y
s
tem
s
to
m
o
n
ito
r
t
h
e
s
tate
o
f
t
h
e
b
atter
y
i
n
ac
tu
al
tim
e
[
6
]
.
Pre
v
io
u
s
r
esear
ch
h
as
u
tili
ze
d
d
ee
p
lear
n
in
g
f
o
r
b
atter
y
h
ea
lth
esti
m
atio
n
u
s
in
g
m
eth
o
d
s
s
u
ch
as
co
n
v
o
l
u
tio
n
al
n
e
u
r
al
n
etwo
r
k
(
C
NN)
[
7
]
,
lo
n
g
s
h
o
r
t
-
te
r
m
m
em
o
r
y
(
L
STM
)
[
8
]
,
B
id
ir
ec
tio
n
al
L
STM
(
B
iLST
M
)
[
9
]
,
an
d
d
ee
p
b
eli
ef
n
etwo
r
k
s
(
DB
Ns)
[
1
0
]
.
Pri
o
r
s
tu
d
ies
o
n
ly
em
p
lo
y
ed
a
s
i
n
g
le
d
ee
p
lear
n
in
g
tech
n
iq
u
e,
wh
ich
lack
ed
g
e
n
er
aliza
tio
n
ca
p
ab
ilit
ies
an
d
was
d
ep
en
d
en
t
o
n
tr
ain
in
g
d
ata,
r
esu
ltin
g
i
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
.
1
,
Feb
r
u
ar
y
20
25
:
9
9
5
-
1
0
0
6
996
o
v
er
f
itti
n
g
.
T
h
is
n
ew
r
esear
ch
co
m
b
in
es
C
NN
an
d
B
iLST
M
f
o
r
L
i
-
io
n
b
atter
y
So
H
esti
m
atio
n
in
o
r
d
er
t
o
p
r
o
v
id
e
m
o
r
e
ac
cu
r
ate
r
esu
lts
b
y
u
tili
zin
g
th
e
s
tr
en
g
th
s
o
f
b
o
th
m
eth
o
d
s
.
Hy
b
r
id
d
ee
p
lear
n
in
g
ca
n
o
v
er
co
m
e
g
en
er
aliza
tio
n
p
r
o
b
lem
s
a
n
d
r
ed
u
ce
o
v
er
f
itti
n
g
ca
u
s
ed
b
y
tr
ain
in
g
d
ata
d
e
p
en
d
e
n
ce
,
th
er
eb
y
i
n
cr
ea
s
in
g
esti
m
atio
n
ac
cu
r
ac
y
[
1
1
]
.
T
h
is
s
tu
d
y
'
s
o
b
jectiv
e
is
to
e
m
p
lo
y
h
y
b
r
id
d
ee
p
lear
n
in
g
te
ch
n
iq
u
es
to
esti
m
ate
th
e
So
H
o
f
lith
iu
m
-
io
n
b
atter
ies.
T
h
e
h
y
b
r
i
d
d
ee
p
lear
n
in
g
m
eth
o
d
u
tili
ze
d
in
r
esear
ch
is
a
co
m
b
in
atio
n
o
f
C
NN
an
d
B
iLST
M.
C
NN
h
as
th
e
ab
ilit
y
to
p
r
o
ce
s
s
d
ata
with
a
lar
g
e
n
u
m
b
er
o
f
f
ea
tu
r
es
an
d
ca
p
tu
r
e
co
m
p
lex
p
atter
n
s
an
d
r
elatio
n
s
h
ip
s
b
etwe
en
f
ea
t
u
r
e
s
o
n
b
atter
y
d
ata
[
1
2
]
.
C
NN,
h
o
wev
er
,
is
lim
ited
in
its
ab
ilit
y
to
an
aly
ze
s
eq
u
en
tial
d
ata
co
r
r
elatio
n
s
a
n
d
tim
e
-
r
elate
d
d
ata
r
elatio
n
s
h
ip
s
.
I
n
co
n
tr
ast,
B
iLST
M
h
as
an
ad
v
an
tag
e
f
o
r
o
v
er
co
m
i
n
g
C
NN'
s
lim
itatio
n
s
in
th
at
it
ca
n
an
aly
ze
s
eq
u
e
n
tial
d
ata
co
r
r
elatio
n
s
a
n
d
tim
e
r
elatio
n
s
h
ip
s
with
in
d
ata
[
1
3
]
.
T
h
is
r
esear
ch
co
n
t
r
ib
u
tes
to
co
m
b
in
in
g
C
NN
an
d
B
iLST
M
to
lev
er
ag
e
th
e
s
tr
en
g
th
s
o
f
b
o
th
m
eth
o
d
s
,
with
th
e
ex
p
ec
tatio
n
o
f
p
r
o
d
u
ci
n
g
a
h
y
b
r
i
d
d
ee
p
l
ea
r
n
in
g
m
eth
o
d
t
h
at
is
m
o
r
e
p
o
wer
f
u
l
an
d
m
o
r
e
ac
cu
r
ate
f
o
r
m
ea
s
u
r
i
n
g
th
e
So
H
o
f
lith
iu
m
-
io
n
b
atter
ies.
T
h
is
r
esear
ch
also
co
m
p
ar
es
th
e
p
er
f
o
r
m
an
ce
o
f
h
y
b
r
id
d
ee
p
lear
n
in
g
an
d
s
in
g
le
d
ee
p
lear
n
in
g
in
o
r
d
er
to
d
e
ter
m
in
e
th
e
o
p
tim
al
m
o
d
el
f
o
r
esti
m
atin
g
So
H
in
lith
iu
m
-
io
n
b
atter
ies.
Pre
v
io
u
s
r
esear
ch
h
as
d
ev
elo
p
ed
an
esti
m
ate
o
f
th
e
s
tate
o
f
h
ea
lth
(
So
H)
f
o
r
lith
iu
m
-
io
n
b
atter
ies.
Du
an
et
a
l.
[
1
4
]
co
m
p
ar
ed
t
h
e
m
ac
h
in
e
lear
n
in
g
tec
h
n
iq
u
e
s
k
-
n
ea
r
est
n
eig
h
b
o
r
s
(K
-
NN)
,
l
o
g
is
tic
r
eg
r
ess
io
n
(
L
R
)
,
en
s
em
b
le
lear
n
in
g
(
E
L
)
,
an
d
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
(
SVM)
.
T
h
ese
r
esear
ch
r
esu
l
ts
d
em
o
n
s
tr
ate
t
h
at
th
e
E
L
m
eth
o
d
is
m
o
r
e
ef
f
ec
tiv
e
th
an
o
th
er
m
eth
o
d
s
.
Fu
r
th
er
m
o
r
e
,
th
e
esti
m
atio
n
o
f
So
H
in
lith
iu
m
-
io
n
b
atter
ies
u
s
in
g
d
ee
p
lear
n
in
g
is
g
r
o
win
g
.
J
o
et
a
l.
[
1
5
]
c
o
m
p
ar
ed
t
h
e
C
NN,
f
ee
d
f
o
r
w
ar
d
n
eu
r
al
n
etwo
r
k
(
FNN)
,
an
d
lo
n
g
s
h
o
r
t
-
ter
m
m
em
o
r
y
(
L
STM
)
a
n
d
f
o
u
n
d
t
h
at
th
e
L
STM
m
eth
o
d
p
er
f
o
r
m
ed
b
etter
th
an
th
e
o
th
er
m
eth
o
d
s
.
J
ia
et
a
l.
[
1
6
]
e
s
tim
ates
So
H
an
d
R
UL
u
s
in
g
Gau
s
s
ian
p
r
o
ce
s
s
r
eg
r
ess
io
n
(
GPR
)
an
d
p
r
o
d
u
ce
s
g
o
o
d
p
r
ed
ictio
n
s
o
f
esti
m
atio
n
ac
cu
r
ac
y
.
K
h
an
et
a
l.
[
1
7
]
c
o
m
p
ar
ed
a
d
ap
tiv
e
b
o
o
s
tin
g
(
AB
)
,
s
u
p
p
o
r
t
v
ec
to
r
r
eg
r
ess
io
n
(
SVR
)
,
L
STM
,
m
u
lti
-
lay
er
p
er
ce
p
tr
o
n
(
ML
P),
b
i
-
d
ir
ec
tio
n
al
L
STM
(
B
iLST
M)
,
an
d
C
NN
an
d
r
esu
lted
in
t
h
e
B
iLST
M
m
eth
o
d
b
ein
g
th
e
b
est
m
eth
o
d
co
m
p
ar
ed
to
o
th
er
m
eth
o
d
s
.
Ho
wev
er
,
th
ese
s
tu
d
ies
h
av
e
lim
itatio
n
s
in
m
ea
s
u
r
in
g
th
e
So
H
o
f
lith
iu
m
-
io
n
b
atter
ies
u
s
in
g
o
n
ly
o
n
e
s
elec
ted
m
ac
h
in
e
lear
n
in
g
o
r
d
ee
p
lear
n
in
g
m
eth
o
d
.
C
o
m
b
in
in
g
d
ee
p
lear
n
in
g
m
et
h
o
d
s
(
h
y
b
r
i
d
d
ee
p
lear
n
in
g
)
c
an
b
e
u
s
ed
to
im
p
r
o
v
e
th
e
ac
cu
r
ac
y
o
f
So
H
esti
m
atio
n
[
1
8
]
,
[
1
9
]
.
T
h
e
h
y
b
r
id
C
NN
-
L
STM
m
o
d
e
l
u
tili
ze
d
in
s
tu
d
y
[
2
0
]
p
r
o
v
e
d
s
u
p
er
io
r
to
eith
e
r
C
NN
o
r
L
STM
.
B
iLST
M
is
an
ev
o
lu
tio
n
o
f
th
e
L
STM
p
ar
ad
ig
m
,
s
o
B
iLST
M
alwa
y
s
p
r
o
d
u
ce
s
s
u
p
er
io
r
r
esu
lts
.
C
NN
is
u
n
ab
le
to
a
n
aly
ze
s
eq
u
en
tial
c
o
r
r
elatio
n
s
a
n
d
tem
p
o
r
al
r
elatio
n
s
h
i
p
s
in
d
at
a.
B
iLST
M
h
as
th
e
b
en
ef
it
o
f
b
ei
n
g
ab
le
to
ex
a
m
in
e
d
ata
s
eq
u
en
tial
co
r
r
elat
io
n
s
an
d
in
ter
tem
p
o
r
al
r
elatio
n
s
h
ip
s
.
C
NN
an
d
B
iLST
M
ca
n
p
r
o
v
id
e
m
o
r
e
ac
cu
r
ate
esti
m
ates o
f
lith
iu
m
-
io
n
b
atter
y
So
H
wh
en
u
s
ed
to
g
et
h
er
.
2.
M
AT
E
R
I
AL
A
ND
M
E
T
H
O
DS
T
h
is
s
tu
d
y
esti
m
ates
th
e
So
H
in
L
ith
iu
m
-
I
o
n
b
atter
ies
u
s
in
g
h
y
b
r
i
d
d
ee
p
lear
n
in
g
.
T
h
e
r
es
ea
r
ch
u
s
es
f
iv
e
s
tag
es
o
f
m
eth
o
d
:
d
ata
p
r
ep
r
o
ce
s
s
in
g
,
d
ata
m
o
d
elin
g
,
h
y
p
er
p
ar
am
eter
tu
n
in
g
,
an
d
ev
alu
atio
n
.
T
h
e
ex
p
lan
atio
n
o
f
ea
ch
m
eth
o
d
is
as f
o
llo
ws.
2
.
1
.
Da
t
a
s
et
T
h
e
s
tu
d
y
u
tili
ze
d
d
ata
f
r
o
m
th
e
NASA
p
r
o
g
n
o
s
tics
d
ata
r
ep
o
s
ito
r
y
[
2
1
]
,
[
2
2
]
.
T
h
e
d
ata
in
clu
d
es
ex
p
er
im
en
tal
i
n
f
o
r
m
atio
n
a
b
o
u
t
th
e
lith
iu
m
-
io
n
b
atter
y
u
s
ed
b
y
NASA
s
atellites.
B
at
ter
ies
with
v
ar
io
u
s
o
p
er
atin
g
p
ar
am
ete
r
s
(
ch
ar
g
in
g
,
d
is
ch
a
r
g
in
g
,
an
d
im
p
e
d
a
n
ce
)
wer
e
test
ed
at
v
ar
io
u
s
tem
p
er
atu
r
es.
T
h
e
d
ataset
in
clu
d
es
m
u
ltip
le
att
r
ib
u
tes,
in
clu
d
in
g
cy
cle,
am
b
ien
t
tem
p
e
r
atu
r
e,
d
atetim
e,
ca
p
ac
ity
,
v
o
ltag
e
m
ea
s
u
r
ed
,
c
u
r
r
en
t
m
ea
s
u
r
ed
,
t
em
p
er
atu
r
e
m
ea
s
u
r
ed
,
ac
tu
al
l
o
ad
,
v
o
ltag
e
l
o
ad
,
an
d
tim
e.
T
h
e
d
ata
i
n
clu
d
es
3
4
b
atter
y
ty
p
es,
in
cl
u
d
in
g
B
0
0
5
5
,
B
0
0
2
8
,
B
0
0
3
0
,
B
0
0
1
8
,
an
d
B
0
0
0
5
.
T
ab
le
1
p
r
esen
ts
a
s
u
b
s
et
o
f
th
e
d
ataset.
2
.
2
.
Da
t
a
p
re
pro
ce
s
s
ing
T
h
e
d
a
t
a
p
r
e
p
r
o
c
e
s
s
i
n
g
p
h
a
s
e
i
n
v
o
l
v
e
s
d
a
t
a
f
il
t
e
r
i
n
g
,
S
O
H
c
a
l
c
u
l
a
ti
o
n
s
,
a
n
d
t
h
e
s
e
l
ec
t
i
o
n
o
f
b
a
t
t
e
r
y
d
a
t
a
a
tt
r
i
b
u
t
es
.
W
h
e
n
d
at
a
is
f
il
t
e
r
e
d
,
t
h
e
v
a
r
i
et
y
o
f
b
a
tt
e
r
y
wit
h
a
f
l
u
ct
u
a
t
i
n
g
r
a
t
i
o
o
f
c
a
p
a
c
ity
t
o
c
y
c
l
e
c
u
r
v
e
s
is
e
l
i
m
i
n
a
te
d
.
T
h
e
c
a
p
a
ci
t
y
a
n
d
cy
c
l
e
c
u
r
v
e
s
o
f
a
l
l
v
a
r
i
e
ti
e
s
o
f
b
a
t
t
e
r
i
es
a
r
e
e
x
a
m
i
n
e
d
,
a
n
d
t
h
e
ty
p
e
o
f
b
a
t
t
e
r
y
wi
th
a
d
o
w
n
w
a
r
d
o
r
g
o
o
d
c
u
r
v
e
w
i
l
l
b
e
u
t
i
li
z
e
d
i
n
t
h
i
s
s
t
u
d
y
.
T
h
e
b
a
t
t
e
r
y
t
y
p
e
d
a
t
a
w
a
s
f
i
l
t
e
r
ed
i
n
t
o
n
i
n
e
d
i
s
ti
n
c
t
b
a
t
t
e
r
y
v
a
r
i
e
ti
e
s
,
i
n
c
l
u
d
i
n
g
B
0
0
0
5
,
B
0
0
0
6
,
B
0
0
0
7
,
B
0
0
1
8
,
B
0
0
2
5
,
B
0
0
2
6
,
B
0
0
2
7
,
B
0
0
2
8
,
a
n
d
B
0
0
3
6
.
Du
r
in
g
th
e
p
r
e
p
r
o
ce
s
s
in
g
p
h
a
s
e,
th
e
So
H
ca
lcu
latio
n
is
al
s
o
p
er
f
o
r
m
ed
u
s
in
g
(
1
)
.
S
tate
o
f
h
ea
lth
(
)
ch
ec
k
s
ar
e
p
er
f
o
r
m
ed
o
n
all
b
atter
y
ty
p
es
[
1
7
]
,
[
2
3
]
.
=
×
100%
(
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
Hyb
r
id
d
ee
p
lea
r
n
in
g
fo
r
esti
ma
tio
n
o
f sta
te
-
of
-
h
ea
lth
in
lit
h
iu
m
-
io
n
b
a
tter
ies
(
Den
is
E
ka
C
a
h
ya
n
i
)
997
: th
e
cu
r
r
e
n
t c
y
cle'
s
m
ax
im
u
m
ca
p
ac
ity
: th
e
f
ir
s
t c
y
cle’
s
m
ax
im
u
m
ca
p
ac
ity
T
h
e
ev
alu
atio
n
o
f
b
atter
y
d
a
ta
attr
ib
u
tes
is
also
p
er
f
o
r
m
e
d
d
u
r
in
g
th
e
p
r
ep
r
o
ce
s
s
in
g
p
h
ase.
T
h
e
attr
ib
u
tes
cy
cle,
am
b
ien
t
tem
p
er
atu
r
e,
an
d
d
atetim
e
th
at
ar
e
ir
r
elev
an
t
to
th
e
li
-
io
n
b
atte
r
y
SOH
esti
m
atio
n
p
r
o
ce
s
s
ar
e
r
em
o
v
ed
.
T
h
e
d
ata
attr
ib
u
tes
u
tili
s
ed
in
th
is
s
tu
d
y
ar
e
ca
p
ac
ity
,
v
o
ltag
e
m
ea
s
u
r
ed
,
cu
r
r
en
t
m
ea
s
u
r
ed
,
tem
p
er
at
u
r
e
m
ea
s
u
r
ed
,
cu
r
r
en
t
lo
ad
,
v
o
ltag
e
l
o
ad
,
tim
e,
an
d
So
H.
T
h
e
s
a
m
p
le
d
ata
af
ter
d
ata
p
r
ep
r
o
ce
s
s
in
g
ar
e
d
is
p
lay
ed
in
T
ab
le
2
.
T
ab
le
1
.
T
h
e
d
ataset
ap
p
lied
i
n
th
is
s
tu
d
y
C
y
c
l
e
A
mb
i
e
n
t
t
e
m
p
e
r
a
t
u
r
e
D
a
t
e
t
i
m
e
C
a
p
a
c
i
t
y
V
o
l
t
a
g
e
m
e
a
s
u
r
e
d
C
u
r
r
e
n
t
m
e
a
s
u
r
e
d
Te
mp
e
r
a
t
u
r
e
m
e
a
s
u
r
e
d
C
u
r
r
e
n
t
l
o
a
d
V
o
l
t
a
g
e
l
o
a
d
Ti
me
1
24
2
0
0
9
-
02
-
13
2
3
:
1
2
:
2
8
1
.
8
0
4
6
8
5
4
.
1
6
6
7
0
4
0
.
0
0
0
8
9
9
2
6
.
5
0
7
2
8
7
0
.
0
0
0
2
4
.
1
8
1
2
9
.
5
0
0
1
24
2
0
0
9
-
02
-
13
2
3
:
1
2
:
2
8
1
.
8
0
4
6
8
5
3
.
9
3
0
9
8
1
-
1
.
9
9
8
4
7
0
2
6
.
5
5
5
0
8
2
1
.
9
9
9
2
2
.
8
8
1
3
9
.
4
6
9
…
…
…
…
…
…
…
…
…
…
1
6
8
24
2
0
0
8
-
05
-
27
2
0
:
4
5
:
4
2
1
.
3
2
5
0
7
9
3
.
5
8
7
3
3
6
0
.
0
0
1
2
1
9
3
4
.
5
6
5
5
8
0
0
.
0
0
0
6
0
.
0
0
0
2
8
1
0
.
6
4
0
T
ab
le
2
.
T
h
e
d
ataset
af
ter
d
ata
p
r
ep
r
o
ce
s
s
in
g
C
a
p
a
c
i
t
y
V
o
l
t
a
g
e
m
e
a
s
u
r
e
d
C
u
r
r
e
n
t
m
e
a
s
u
r
e
d
Te
mp
e
r
a
t
u
r
e
mea
s
u
r
e
d
C
u
r
r
e
n
t
l
o
a
d
V
o
l
t
a
g
e
l
o
a
d
Ti
me
S
o
H
1
.
8
0
4
6
8
5
4
.
1
6
6
7
0
4
0
.
0
0
0
8
9
9
2
6
.
5
0
7
2
8
7
0
.
0
0
0
2
4
.
1
8
1
2
9
.
5
0
0
1
.
0
0
0
0
0
0
1
.
8
0
4
6
8
5
3
.
9
3
0
9
8
1
-
1
.
9
9
8
4
7
0
2
6
.
5
5
5
0
8
2
1
.
9
9
9
2
2
.
8
8
1
3
9
.
4
6
9
0
.
9
4
6
7
8
8
…
…
…
…
…
…
…
…
1
.
3
2
5
0
7
9
3
.
5
8
7
3
3
6
0
.
0
0
1
2
1
9
3
4
.
5
6
5
5
8
0
0
.
0
0
0
6
0
.
0
0
0
2
8
1
0
.
6
4
0
0
.
7
3
4
2
4
3
2
.
3
.
Da
t
a
m
o
delin
g
T
h
is
s
tu
d
y
esti
m
ates
So
H
u
s
i
n
g
h
y
b
r
i
d
d
ee
p
lear
n
in
g
tech
n
iq
u
es,
in
clu
d
i
n
g
s
tan
d
a
r
d
d
ee
p
lear
n
in
g
-
L
STM
,
Stan
d
ar
d
d
ee
p
lea
r
n
in
g
-
B
iLST
M,
s
tan
d
ar
d
d
ee
p
lea
r
n
in
g
-
Simp
leR
NN,
C
NN
-
L
STM
,
C
NN
-
B
iLST
M,
an
d
C
NN
-
Simp
leR
NN.
Hy
b
r
id
d
ee
p
lear
n
i
n
g
m
eth
o
d
s
ar
e
also
co
m
p
ar
ed
to
d
ee
p
lear
n
in
g
m
eth
o
d
s
s
u
ch
as
Stan
d
ar
d
Dee
p
L
ea
r
n
in
g
,
L
ST
M,
B
iLST
M,
Simp
leR
NN,
an
d
C
NN.
T
r
ain
in
g
b
atter
y
d
ata
is
co
n
d
u
cte
d
u
s
in
g
b
atter
y
d
ata
B
0
0
0
5
,
B
0
0
0
6
,
B
0
0
0
7
,
B
0
0
1
8
,
B
0
0
2
5
,
B
0
0
2
6
,
B
0
0
2
7
,
B
0
0
2
8
,
an
d
B
0
0
3
6
.
T
h
e
tr
ain
in
g
d
ata
is
d
if
f
er
en
tiated
b
y
c
o
m
b
in
i
n
g
d
ata
f
o
r
all
b
atter
y
ty
p
es
with
tr
ain
in
g
d
ata
f
o
r
ea
ch
b
atter
y
ty
p
e.
I
n
ad
d
itio
n
,
d
ata
test
in
g
is
co
n
d
u
cted
u
s
in
g
B
0
0
5
5
b
atter
y
d
ata.
C
NN
-
B
iL
STM
m
o
d
el
is
a
h
y
b
r
id
d
ee
p
lear
n
in
g
tech
n
iq
u
e
th
at
co
m
b
i
n
es
1
-
D
C
NN
with
B
iLST
M
m
o
d
els.
T
h
e
C
NN
m
o
d
el
is
p
r
o
ce
s
s
ed
in
p
ar
allel
with
th
e
B
iLST
M
m
o
d
el.
T
h
e
C
NN
an
d
B
iLST
M
m
o
d
els
ar
e
co
m
b
in
e
d
to
p
r
o
d
u
ce
a
m
o
d
el
with
co
n
ca
te
n
ated
f
ea
tu
r
es
f
o
r
esti
m
atin
g
So
H.
So
H
ca
lcu
latio
n
s
ar
e
p
er
f
o
r
m
ed
d
u
r
in
g
tr
ain
in
g
an
d
d
ata
test
in
g
s
o
th
at
p
r
e
d
icted
an
d
ac
tu
al
So
H
v
al
u
es c
an
b
e
co
m
p
ar
ed
.
T
h
e
C
NN
m
o
d
el
co
n
tain
s
1
-
d
i
m
en
s
io
n
al
co
n
v
o
lu
ti
o
n
al
wh
ic
h
ac
tiv
ates
ce
r
tain
f
ea
tu
r
es o
f
th
e
d
ata
t
o
p
r
o
d
u
ce
a
f
ea
tu
r
e
m
ap
,
f
o
llo
wed
b
y
r
ec
tifie
d
li
n
ea
r
u
n
its
(
R
eL
U)
wh
ich
en
a
b
le
f
aster
an
d
m
o
r
e
e
f
f
ec
tiv
e
tr
ain
in
g
.
Fu
r
th
er
m
o
r
e,
m
ax
p
o
o
lin
g
s
im
p
lifie
s
th
e
o
u
tp
u
t
b
y
p
er
f
o
r
m
in
g
n
o
n
lin
ea
r
d
o
wn
s
am
p
lin
g
t
h
er
eb
y
r
ed
u
cin
g
th
e
n
u
m
b
er
o
f
p
a
r
am
eter
s
th
at
th
e
n
etwo
r
k
n
ee
d
s
to
lear
n
.
T
h
e
p
r
o
ce
s
s
co
n
tin
u
es
with
1
-
d
im
en
s
io
n
al
co
n
v
o
l
u
tio
n
al
+REL
U
an
d
m
ax
p
o
o
lin
g
ag
ain
.
T
h
en
,
f
latten
lay
er
to
co
n
v
er
t
th
e
two
-
d
im
en
s
io
n
al
f
ea
tu
r
e
m
atr
ix
in
t
o
a
v
ec
t
o
r
.
Fin
ally
,
th
e
f
u
lly
c
o
n
n
ec
ted
lay
er
(
FC
L
)
with
th
e
ac
tiv
atio
n
f
u
n
ctio
n
is
ad
d
ed
with
th
e
n
u
m
b
e
r
o
f
n
eu
r
o
n
s
.
T
h
e
B
iLST
M
m
o
d
el
co
n
tain
s
th
e
B
iLST
M
lay
er
an
d
t
h
e
d
r
o
p
o
u
t
lay
e
r
is
r
ep
ea
ted
twice.
T
h
e
m
o
d
el
is
co
n
tin
u
ed
with
d
e
n
s
e_
1
an
d
d
en
s
e_
2
lay
er
s
.
T
h
e
n
,
Flatten
lay
er
an
d
FC
L
.
T
h
e
m
o
d
e
ls
ar
e
co
m
b
in
ed
t
o
p
r
o
d
u
ce
co
n
ca
ten
ated
f
ea
tu
r
es
th
at
co
m
b
i
n
e
f
ea
tu
r
es
f
r
o
m
t
h
e
C
NN
an
d
B
iLST
M
m
o
d
els
.
T
h
e
m
o
d
el
o
u
tp
u
t
ca
n
p
r
o
d
u
ce
So
H
esti
m
ates.
T
h
e
ar
ch
itectu
r
e
o
f
th
e
C
NN
-
B
i
L
STM
m
o
d
el
is
s
h
o
wn
in
Fig
u
r
e
1
.
2
.
4
.
H
y
perpa
ra
m
e
t
er
t
uning
T
h
e
h
y
p
er
p
ar
a
m
eter
o
p
tim
iz
atio
n
p
h
ase
d
eter
m
i
n
es
th
e
p
ar
am
eter
s
o
f
th
e
o
p
tim
al
e
x
p
er
im
en
tal
s
ce
n
ar
io
.
T
h
is
s
tu
d
y
em
p
lo
y
s
th
e
p
ar
am
eter
s
lo
s
s
f
u
n
ctio
n
,
o
p
tim
izer
,
b
atch
_
s
ize,
m
o
d
el
ac
tiv
atio
n
,
an
d
ep
o
ch
.
Me
an
_
s
q
u
a
r
ed
_
e
r
r
o
r
i
s
th
e
lo
s
s
f
u
n
ctio
n
u
tili
ze
d
i
n
th
is
s
tu
d
y
.
Me
an
wh
ile,
A
d
am
is
th
e
o
p
tim
izer
u
s
ed
.
B
atch
_
Size
is
s
et
to
5
0
.
T
h
e
er
a
u
tili
ze
d
is
3
0
.
T
h
e
n
th
e
em
p
lo
y
e
d
ac
tiv
atio
n
m
o
d
el
i
s
tan
h
.
2
.
5
.
E
v
a
lua
t
i
o
n
T
h
e
r
esear
ch
u
tili
s
ed
f
o
u
r
m
e
tr
ics
to
ass
e
s
s
th
e
ef
f
ec
tiv
en
ess
o
f
th
e
im
p
lem
en
ted
p
r
o
ce
d
u
r
e.
T
h
is
d
ee
p
lear
n
i
n
g
m
et
h
o
d
is
ev
a
lu
ated
u
s
in
g
m
ea
n
ab
s
o
lu
te
er
r
o
r
(
MA
E
)
,
m
ea
n
s
q
u
ar
e
e
r
r
o
r
(
MSE
)
,
m
ea
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
.
1
,
Feb
r
u
ar
y
20
25
:
9
9
5
-
1
0
0
6
998
ab
s
o
lu
te
p
er
ce
n
tag
e
er
r
o
r
(
M
APE)
,
an
d
r
o
o
t
m
ea
n
s
q
u
ar
e
er
r
o
r
(
R
MSE
)
.
I
n
eq
u
atio
n
s
(
2
)
,
(
3
)
,
(
4
)
,
a
n
d
(
5
)
,
th
e
m
etr
ics
ar
e
d
is
p
lay
ed
[
2
4
]
,
[
2
5
]
.
is
th
e
am
o
u
n
t
o
f
d
at
a
th
at
is
m
ea
s
u
r
ed
o
r
p
r
ed
icte
d
.
is
th
e
ac
tu
al
So
H
u
s
ed
in
r
ea
l te
r
m
s
,
wh
ile
~
is
th
e
p
r
ed
icted
So
H
p
r
o
d
u
ce
d
b
y
th
e
m
o
d
el.
=
1
∑
(
−
~
)
2
=
1
(
2
)
=
√
=
√
1
∑
(
−
~
)
2
=
1
(
3
)
=
1
∑
|
=
1
−
~
|
(
4
)
=
100%
∑
|
−
~
|
=
1
(
5
)
Fig
u
r
e
1
.
T
h
e
C
NN
-
B
iLST
M
a
r
ch
itectu
r
e
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
I
n
th
is
s
ec
tio
n
,
th
e
r
esu
lts
o
f
t
h
e
r
esear
ch
ar
e
ex
p
lain
ed
alo
n
g
with
a
co
m
p
r
eh
en
s
iv
e
d
is
cu
s
s
io
n
.
T
h
is
s
ec
tio
n
co
n
s
is
ts
o
f
d
ata
co
llectio
n
an
d
r
esu
lts
an
d
d
is
cu
s
s
io
n
.
T
h
e
ex
p
la
n
atio
n
o
f
ea
ch
m
eth
o
d
is
as f
o
llo
ws.
3
.
1
.
Da
t
a
c
o
llect
io
n
I
n
th
e
NASA
p
r
o
g
n
o
s
tics
d
ata
r
ep
o
s
ito
r
y
,
th
er
e
ar
e
3
0
1
,
7
1
0
r
ec
o
r
d
s
.
T
h
er
e
a
r
e
a
to
tal
o
f
2
5
1
,
0
7
3
r
ec
o
r
d
s
af
ter
p
r
e
p
r
o
ce
s
s
in
g
.
T
h
e
d
ata
ar
e
u
tili
s
ed
as
tr
ain
in
g
d
ata
to
co
n
s
tr
u
ct
a
h
y
b
r
id
d
ee
p
lear
n
in
g
m
o
d
el
f
o
r
esti
m
atin
g
th
e
So
H
o
f
lith
i
u
m
-
io
n
b
atter
ies.
Usi
n
g
2
2
,
6
6
2
r
ec
o
r
d
s
f
r
o
m
th
e
B
0
0
5
5
d
at
aset
to
ev
alu
ate
th
e
d
ee
p
lear
n
in
g
m
o
d
el.
3
.
2
.
Resul
t
a
nd
d
is
cus
s
io
n
T
h
is
s
tu
d
y
u
s
es
elev
en
ex
p
e
r
im
en
tal
s
ce
n
ar
io
s
f
o
r
th
e
esti
m
atio
n
o
f
th
e
s
tate
o
f
h
ea
l
th
o
f
li
-
io
n
b
atter
ies.
T
h
e
ex
p
er
im
e
n
tal
s
ce
n
ar
io
s
u
s
ed
ar
e
s
tan
d
ar
d
d
ee
p
lear
n
in
g
-
L
STM
,
s
tan
d
ar
d
d
ee
p
lear
n
in
g
-
B
iLST
M,
s
tan
d
ar
d
d
ee
p
lea
r
n
in
g
-
Simp
leR
NN,
C
NN
-
L
STM
,
C
NN
-
B
iLST
M,
C
NN
-
Si
m
p
leR
NN,
s
tan
d
ar
d
d
ee
p
lear
n
i
n
g
,
L
STM
,
B
iLST
M,
Simp
leR
NN,
an
d
C
NN.
T
h
e
e
v
alu
atio
n
r
esu
lts
o
f
ea
ch
m
eth
o
d
f
o
r
esti
m
atin
g
th
e
So
H
o
f
lith
iu
m
-
io
n
b
atter
ies ar
e
d
is
p
lay
e
d
in
T
ab
le
3
.
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
Hyb
r
id
d
ee
p
lea
r
n
in
g
fo
r
esti
ma
tio
n
o
f sta
te
-
of
-
h
ea
lth
in
lit
h
iu
m
-
io
n
b
a
tter
ies
(
Den
is
E
ka
C
a
h
ya
n
i
)
999
T
h
e
ev
alu
atio
n
f
in
d
in
g
s
o
f
th
is
r
esear
ch
,
as
s
h
o
w
n
in
T
ab
le
3
,
in
d
icate
t
h
at
C
NN
-
B
iLST
M
o
u
tp
er
f
o
r
m
ed
o
th
er
ap
p
r
o
ac
h
es.
T
h
e
C
NN
-
B
iLST
M
ap
p
r
o
ac
h
y
ield
s
th
e
f
o
llo
win
g
v
alu
es
in
th
e
o
r
d
er
o
f
R
MSE
,
M
SE,
MA
E
,
an
d
MA
PE:
0
.
0
0
9
1
6
,
0
.
0
0
0
0
8
4
,
0
.
0
0
4
8
,
an
d
0
.
0
0
6
0
3
.
T
h
e
h
y
b
r
id
d
e
ep
lear
n
in
g
m
eth
o
d
th
at
o
b
tain
ed
th
e
n
ex
t
b
est
r
es
u
lts
was
s
tan
d
ar
d
d
ee
p
lear
n
in
g
-
B
iLST
M
wh
ich
o
b
tain
e
d
R
MSE
,
MSE
,
MA
E
,
an
d
MA
PE
v
alu
es
r
esp
ec
tiv
ely
as
f
o
llo
ws:
0
.
0
0
9
6
9
,
0
.
0
0
0
0
9
4
,
0
.
0
0
5
7
5
,
an
d
0
.
0
0
7
2
4
.
T
h
e
m
o
d
el
th
at
r
ec
eiv
ed
th
e
n
e
x
t
b
est
ev
al
u
at
io
n
f
o
r
a
s
in
g
le
d
ee
p
lear
n
in
g
m
o
d
el
was
B
iLST
M
with
R
MSE
,
MSE
,
MA
E
,
an
d
MA
PE
v
alu
es r
esp
ec
tiv
el
y
as f
o
llo
ws 0
.
0
1
0
7
5
,
0
.
0
0
0
1
1
,
0
.
0
0
6
4
9
,
an
d
0
.
0
0
7
5
6
.
T
ab
le
3
.
T
h
e
ev
alu
atio
n
o
f
R
MSE
,
MSE
,
MA
E
,
an
d
MA
PE
M
e
t
h
o
d
s
R
M
S
E
M
S
E
M
A
E
M
A
P
E
S
t
a
n
d
a
r
d
d
e
e
p
l
e
a
r
n
i
n
g
-
LS
TM
0
.
0
1
0
9
4
0
.
0
0
0
1
1
0
.
0
0
5
8
0
.
0
0
7
7
1
S
t
a
n
d
a
r
d
d
e
e
p
l
e
a
r
n
i
n
g
-
B
i
LS
TM
0
.
0
0
9
6
9
0
.
0
0
0
0
9
4
0
.
0
0
5
7
5
0
.
0
0
7
2
4
S
t
a
n
d
a
r
d
d
e
e
p
l
e
a
r
n
i
n
g
-
S
i
mp
l
e
R
N
N
0
.
0
1
2
9
3
0
.
0
0
0
1
6
0
.
0
0
6
6
5
0
.
0
0
8
1
4
C
N
N
-
LSTM
0
.
0
1
6
8
0
.
0
0
0
2
8
0
.
0
1
0
1
3
0
.
0
1
3
9
9
CNN
-
B
i
L
S
T
M
0
.
0
0
9
1
6
0
.
0
0
0
0
8
4
0
.
0
0
4
8
0
.
0
0
6
0
3
C
N
N
-
S
i
mp
l
e
R
N
N
0
.
0
1
4
7
1
0
.
0
0
0
2
1
0
.
0
0
7
5
6
0
.
0
0
9
0
2
S
t
a
n
d
a
r
d
d
e
e
p
l
e
a
r
n
i
n
g
0
.
0
4
2
4
9
0
.
0
0
1
8
0
.
0
2
9
9
5
0
.
0
3
8
2
4
B
i
LST
M
0
.
0
1
0
7
5
0
.
0
0
0
1
1
0
.
0
0
6
4
9
0
.
0
0
7
5
6
LSTM
0
.
0
1
4
8
3
0
.
0
0
0
2
2
0
.
0
1
0
8
5
0
.
0
1
2
6
4
S
i
mp
l
e
R
N
N
0
.
0
1
3
1
1
0
.
0
0
0
1
7
0
.
0
0
7
5
8
0
.
0
0
9
2
C
N
N
0
.
0
2
5
1
4
0
.
0
0
0
6
3
0
.
0
1
5
8
4
0
.
0
1
9
2
8
T
h
is
r
esear
ch
also
ev
alu
ates
t
h
e
p
er
f
o
r
m
an
ce
o
f
ea
ch
b
atter
y
ty
p
e
to
esti
m
ate
th
e
Sta
te
o
f
Hea
lth
o
f
li
-
io
n
b
atter
ies.
T
h
e
f
o
llo
win
g
b
atter
y
ty
p
es
ar
e
u
tili
ze
d
:
B
0
0
0
5
,
B
0
0
0
6
,
B
0
0
0
7
,
B
0
0
1
8
,
B
0
0
2
5
,
B
0
0
2
6
,
B
0
0
2
7
,
B
0
0
2
8
,
an
d
B
0
0
3
6
.
E
ac
h
ty
p
e
o
f
b
atter
y
is
ev
alu
ated
u
s
in
g
s
tan
d
ar
d
d
ee
p
lear
n
in
g
,
L
STM
,
B
iLST
M,
Simp
leR
NN,
an
d
C
NN.
T
ab
le
4
d
is
p
lay
s
th
e
e
v
alu
atio
n
r
esu
lts
f
o
r
R
MSE
,
MSE
,
MA
E
,
an
d
MA
PE
f
o
r
ea
ch
ty
p
e
o
f
b
atter
y
u
s
ed
to
esti
m
ate
So
H.
T
ab
le
4
o
f
th
e
ev
alu
atio
n
r
esu
lts
f
o
r
th
is
s
tu
d
y
r
ev
ea
led
th
at
B
iLST
M
co
n
s
i
s
ten
tly
p
r
o
d
u
c
ed
th
e
b
est
r
esu
lts
wh
en
co
m
p
ar
ed
t
o
s
tan
d
ar
d
d
ee
p
lear
n
i
n
g
,
L
STM
,
Simp
leR
NN,
an
d
C
NN
f
o
r
ea
ch
b
atter
y
ty
p
e.
T
h
e
B
0
0
2
5
b
atter
y
ac
h
iev
ed
th
e
g
r
ea
test
ev
alu
atio
n
v
alu
e
with
R
MSE
,
MSE
,
MA
E
,
a
n
d
MA
PE
v
alu
es
o
f
0
.
0
0
0
5
9
,
3
.
4
8
7
1
,
0
.
0
0
0
4
7
,
a
n
d
0
.
0
0
0
4
8
,
r
esp
ec
tiv
ely
.
T
h
en
,
t
h
e
m
o
d
el
with
th
e
s
ec
o
n
d
-
b
est
ev
alu
atio
n
r
esu
lts
f
o
r
ea
ch
ty
p
e
o
f
b
atter
y
d
ata
is
th
e
Simp
leR
NN
m
o
d
el.
T
h
is
s
tu
d
y
illu
s
tr
ates
th
e
co
m
p
ar
is
o
n
cu
r
v
e
b
etwe
en
So
H
a
n
d
So
H
p
r
ed
ictio
n
s
f
o
r
ev
e
r
y
cy
cle.
So
H
th
at
is
u
s
ed
is
So
H
d
ata
f
r
o
m
b
atter
y
B
0
0
5
5
,
wh
ile
So
H
th
at
is
p
r
ed
icted
is
So
H
p
r
e
d
ictio
n
r
esu
lt
f
r
o
m
tr
ain
in
g
d
ata.
T
h
e
co
m
p
ar
is
o
n
o
f
So
H
an
d
So
H
p
r
ed
ictio
n
s
is
d
ep
icted
in
Fig
u
r
e
2
(
s
ee
in
ap
p
en
d
i
x
)
.
So
H
is
r
ep
r
esen
ted
b
y
th
e
b
lu
e
lin
e,
a
n
d
p
r
e
d
icted
So
H
is
r
ep
r
esen
te
d
b
y
th
e
o
r
a
n
g
e
lin
e.
Fig
u
r
e
2
s
h
o
ws
th
at
C
NN
-
B
i
L
STM
h
as
a
r
ea
s
o
n
ab
ly
ac
cu
r
ate
m
o
d
el
p
r
e
d
ictio
n
an
d
is
n
ea
r
to
th
e
So
H
v
alu
e
w
h
en
co
m
p
a
r
ed
to
o
th
er
m
eth
o
d
s
.
Fig
u
r
e
2
c
o
n
s
is
ts
o
f
s
u
b
f
ig
u
r
es
in
clu
d
in
g
Fig
u
r
e
2
(
a)
s
tan
d
ar
d
d
ee
p
lear
n
in
g
-
L
STM
,
Fig
u
r
e
2
(
b
)
s
tan
d
a
r
d
d
e
ep
lear
n
i
n
g
-
B
iLST
M,
Fig
u
r
e
2
(
c)
s
tan
d
ar
d
d
ee
p
lea
r
n
in
g
-
Simp
leR
NN,
Fig
u
r
e
2
(
d
)
C
NN
-
L
STM
,
F
ig
u
r
e
2
(
e)
C
NN
-
B
iL
STM
,
Fig
u
r
e
2
(f)
C
NN
-
Simp
le
R
NN,
Fig
u
r
e
2
(
g
)
s
tan
d
a
r
d
d
ee
p
lear
n
in
g
,
Fig
u
r
e
2
(
h
)
L
STM
,
Fig
u
r
e
2
(
i)
B
iLST
M,
Fig
u
r
e
2
(
j
)
Simp
leR
NN,
an
d
Fig
u
r
e
2
(
k
)
C
NN.
C
NN
-
B
iL
STM
p
r
o
v
id
es
m
o
d
el
p
r
e
d
ictio
n
s
with
in
a
r
an
g
e
n
ea
r
o
r
c
lo
s
e
to
ac
tu
al
So
H
v
alu
es,
r
esu
ltin
g
in
s
u
p
er
i
o
r
p
er
f
o
r
m
a
n
ce
in
ter
m
s
o
f
p
r
ed
ic
tio
n
.
Fu
r
th
er
m
o
r
e,
C
NN
-
B
iLST
M
ca
n
g
en
er
alize
well
f
r
o
m
tr
ain
in
g
d
ata
to
r
a
n
d
o
m
d
ata.
C
NN
-
B
iLST
M
h
as
a
lo
w
er
r
o
r
r
ate
wh
en
p
r
e
d
ictin
g
So
H
v
alu
es.
C
NN
-
B
iL
STM
ca
n
ef
f
ec
tiv
ely
ap
p
ly
s
ig
n
if
ica
n
t p
atter
n
s
ex
tr
ac
ted
f
r
o
m
tr
ain
in
g
d
ata
to
n
e
w
d
ata.
Fig
u
r
e
2
illu
s
tr
ates
th
at
co
m
p
ar
ed
to
o
th
er
ap
p
r
o
ac
h
es,
t
h
e
s
tan
d
ar
d
d
ee
p
lear
n
in
g
m
o
d
el
ac
cu
r
ately
f
o
r
ec
asts
r
ea
l
So
H
v
alu
es
th
r
o
u
g
h
o
u
t
a
b
r
o
a
d
s
p
ec
tr
u
m
.
C
o
n
v
en
tio
n
al
d
ee
p
lear
n
in
g
m
e
th
o
d
s
p
r
o
v
i
d
e
less
p
r
ec
is
e
m
o
d
el
p
r
ed
ictio
n
s
f
o
r
p
r
ed
ictin
g
So
H
v
alu
es.
T
h
e
m
o
d
el
is
in
f
lu
en
ce
d
b
y
b
ias
in
th
e
tr
ain
in
g
d
ata,
lead
in
g
it
to
r
o
u
tin
ely
f
o
r
ec
as
t
So
H
v
alu
es
th
at
ar
e
to
o
h
ig
h
,
r
esu
ltin
g
in
a
s
u
b
s
tan
tial
d
is
p
ar
ity
b
etwe
en
th
e
ac
tu
al
an
d
a
n
ticip
ated
So
H.
T
h
e
s
ig
n
if
ican
t
d
is
p
ar
ities
ac
r
o
s
s
So
H
cu
r
v
es
m
ig
h
t
a
r
is
e
f
r
o
m
m
ea
s
u
r
em
en
t
m
is
tak
es
o
r
f
laws
d
u
r
in
g
th
e
c
alcu
latio
n
o
f
th
e
p
r
ec
is
e
So
H
v
alu
e.
Sh
o
u
ld
t
h
e
d
ata
u
s
ed
f
o
r
m
o
d
el
tr
ain
in
g
b
e
in
ac
cu
r
ate,
it is
lik
ely
th
at
th
e
m
o
d
el'
s
p
r
ed
ictio
n
s
will a
ls
o
b
e
im
p
r
ec
is
e.
C
NN
-
B
iL
STM
is
th
e
o
p
tim
al
m
o
d
el
f
o
r
esti
m
atin
g
So
H
in
lith
iu
m
-
io
n
b
atter
ies,
ac
co
r
d
i
n
g
to
th
is
s
tu
d
y
.
T
h
is
tech
n
iq
u
e
is
p
r
ef
e
r
ab
le
to
o
th
er
h
y
b
r
id
an
d
d
ee
p
lear
n
in
g
tech
n
iq
u
es.
T
h
is
is
d
u
e
to
th
e
f
ac
t
th
at
th
e
co
m
b
in
atio
n
o
f
C
NN
an
d
B
iLST
M
m
o
d
els
ca
n
p
r
o
d
u
ce
o
p
tim
al
m
o
d
el
p
er
f
o
r
m
an
ce
,
allo
win
g
f
o
r
b
etter
s
tate
o
f
h
ea
lth
p
r
ed
ictio
n
co
m
p
ar
ed
to
o
th
er
m
o
d
els.
C
NN
'
s
m
o
d
el
ex
ce
ls
at
ex
tr
ac
tin
g
h
ier
ar
ch
ical
f
ea
tu
r
es
f
r
o
m
d
ata
i
n
o
r
d
er
to
id
en
tif
y
p
atter
n
s
th
at
a
r
e
d
if
f
icu
lt
t
o
r
e
co
g
n
is
e
in
n
u
m
er
ical
d
ata.
I
n
co
n
tr
ast,
B
iLST
M
is
ab
le
to
ca
p
tu
r
e
te
m
p
o
r
al
p
att
er
n
s
in
d
ata
s
eq
u
en
ce
s
.
B
y
c
o
m
b
in
in
g
C
NN
an
d
B
iLST
M,
m
o
d
els
a
r
e
ab
le
to
ex
tr
ac
t
v
ital
in
f
o
r
m
atio
n
,
r
es
u
ltin
g
in
m
o
r
e
r
o
b
u
s
t
r
ep
r
es
en
tatio
n
s
o
f
f
ea
tu
r
es.
I
n
ad
d
itio
n
,
m
o
d
el
C
NN
-
B
iLST
M
ca
n
h
elp
r
ed
u
ce
o
v
er
f
itti
n
g
.
C
NN
h
as
a
p
r
o
p
en
s
ity
to
g
en
er
ate
a
lar
g
e
n
u
m
b
er
o
f
f
ea
tu
r
es,
an
d
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
.
1
,
Feb
r
u
ar
y
20
25
:
9
9
5
-
1
0
0
6
1000
B
iLST
M
ca
n
h
elp
co
n
tr
o
l
t
h
e
co
m
p
lex
ity
o
f
th
e
m
o
d
el
b
y
u
tili
zin
g
co
n
tex
t
u
al
in
f
o
r
m
ati
o
n
f
r
o
m
b
o
th
d
ata
in
p
u
t
d
ir
ec
tio
n
s
.
T
h
is
ca
n
r
e
d
u
ce
th
e
r
is
k
o
f
o
v
e
r
f
itti
n
g
th
a
t
ca
n
o
cc
u
r
with
d
ee
p
lear
n
in
g
m
o
d
els.
Utilizin
g
th
e
s
tr
en
g
th
s
o
f
ea
ch
ar
ch
itectu
r
e
m
ak
es
th
e
co
m
b
in
at
io
n
o
f
th
e
C
NN
an
d
B
iLS
T
M
m
o
d
els
m
o
r
e
ad
v
an
tag
e
o
u
s
th
an
o
th
er
m
o
d
e
ls
.
T
ab
le
4
.
T
h
e
ev
alu
atio
n
o
f
R
MSE
,
MSE
,
MA
E
,
an
d
MA
PE
f
o
r
ea
c
h
b
atter
y
ty
p
e
M
e
t
h
o
d
s
R
M
S
E
M
S
E
M
A
E
M
A
P
E
B
a
t
t
e
r
y
B
0
0
0
5
S
t
a
n
d
a
r
d
d
e
e
p
l
e
a
r
n
i
n
g
0
.
0
5
2
7
3
0
.
0
0
2
7
8
0
.
0
3
1
3
0
7
0
.
0
3
7
1
7
6
B
i
L
S
T
M
0
.
0
0
4
9
2
2
.
4
2
8
1
1
0
.
0
0
4
0
7
0
.
0
0
4
8
4
LSTM
0
.
0
4
3
1
7
0
.
0
0
1
8
6
0
.
0
3
7
6
1
0
.
0
4
7
1
4
S
i
mp
l
e
R
N
N
0
.
0
1
2
7
7
0
.
0
0
0
1
6
0
.
0
1
0
1
8
0
.
0
1
2
0
3
C
N
N
0
.
0
5
2
7
9
0
.
0
0
2
7
8
0
.
0
3
1
2
2
0
.
0
3
6
9
7
B
a
t
t
e
r
y
B
0
0
0
6
S
t
a
n
d
a
r
d
d
e
e
p
l
e
a
r
n
i
n
g
0
.
0
7
3
9
4
0
.
0
0
5
4
6
8
0
.
0
4
3
2
0
.
0
5
7
5
6
B
i
L
S
T
M
0
.
0
0
2
7
0
7
.
3
3
3
3
0
.
0
0
2
1
5
0
.
0
0
2
8
4
LSTM
0
.
0
1
3
2
8
0
.
0
0
0
1
7
0
.
0
0
9
0
1
0
.
0
1
0
9
4
S
i
mp
l
e
R
N
N
0
.
0
0
5
5
7
3
.
1
0
3
9
8
0
.
0
0
4
1
3
0
.
0
0
5
5
8
C
N
N
0
.
0
7
1
4
5
0
.
0
0
5
1
0
0
.
0
4
0
2
1
0
.
0
5
3
1
1
B
a
t
t
e
r
y
B
0
0
0
7
S
t
a
n
d
a
r
d
D
e
e
p
L
e
a
r
n
i
n
g
0
.
0
1
6
0
1
0
.
0
0
0
2
5
0
.
0
0
9
0
3
0
.
0
1
0
6
3
B
i
L
S
T
M
0
.
0
0
4
1
2
1
.
7
0
4
6
1
0
.
0
0
3
7
2
0
.
0
0
4
2
5
LSTM
0
.
0
1
7
2
7
0
.
0
0
0
2
0
.
0
1
2
3
3
0
.
0
1
3
2
5
S
i
mp
l
e
R
N
N
0
.
0
0
6
8
7
2
4
.
7
2
3
0
0
0
.
0
0
4
9
2
0
.
0
0
5
7
6
C
N
N
0
.
0
1
4
8
8
0
.
0
0
0
2
2
0
.
0
0
7
6
1
0
.
0
0
8
9
0
B
a
t
t
e
r
y
B
0
0
1
8
S
t
a
n
d
a
r
d
D
e
e
p
L
e
a
r
n
i
n
g
0
.
0
2
4
9
7
0
.
0
0
0
6
2
0
.
0
1
4
4
3
0
.
0
1
7
0
1
B
i
L
S
T
M
0
.
0
0
7
0
7
5
.
0
0
1
7
8
0
.
0
0
5
9
2
0
.
0
0
6
9
3
LSTM
0
.
0
0
8
0
3
6
.
4
6
0
4
1
0
.
0
0
5
4
1
0
.
0
0
6
6
9
S
i
mp
l
e
R
N
N
0
.
0
2
3
0
2
0
.
0
0
0
5
3
0
.
0
0
9
5
8
0
.
0
1
1
4
6
C
N
N
0
.
0
2
8
2
3
0
.
0
0
0
7
9
0
.
0
1
7
7
6
0
.
0
2
1
1
3
B
a
t
t
e
r
y
B
0
0
2
5
S
t
a
n
d
a
r
d
d
e
e
p
l
e
a
r
n
i
n
g
0
.
0
0
4
6
1
2
.
1
2
9
9
5
0
.
0
0
3
9
0
0
.
0
0
3
9
7
B
i
L
S
T
M
0
.
0
0
0
5
9
3
.
4
8
7
1
6
0
.
0
0
0
4
7
0
.
0
0
0
4
8
LSTM
0
.
0
0
5
7
0
3
.
2
6
0
4
0
0
.
0
0
5
1
3
0
.
0
0
5
2
4
S
i
mp
l
e
R
N
N
0
.
0
0
0
8
9
8
.
0
0
5
4
3
0
.
0
0
0
5
8
0
.
0
0
0
5
9
C
N
N
0
.
0
0
4
5
7
2
.
0
8
8
7
5
0
.
0
0
4
1
0
0
.
0
0
4
1
8
B
a
t
t
e
r
y
B
0
0
2
6
S
t
a
n
d
a
r
d
d
e
e
p
l
e
a
r
n
i
n
g
0
.
0
0
8
7
1
7
.
5
9
8
8
9
0
.
0
0
4
1
8
0
.
0
0
4
7
2
B
i
L
S
T
M
0
.
0
0
2
2
8
5
.
2
0
3
5
3
0
.
0
0
1
9
7
0
.
0
0
2
0
7
LSTM
0
.
0
0
2
4
2
5
.
8
6
0
6
6
0
.
0
0
1
7
0
0
.
0
0
1
7
4
S
i
mp
l
e
R
N
N
0
.
0
0
5
1
2
2
.
6
2
7
8
5
0
.
0
0
4
9
1
0
.
0
0
5
0
9
C
N
N
0
.
0
0
2
7
7
7
.
7
1
7
3
5
0
.
0
0
2
1
9
0
.
0
0
2
2
8
B
a
t
t
e
r
y
B
0
0
2
7
S
t
a
n
d
a
r
d
d
e
e
p
l
e
a
r
n
i
n
g
0
.
0
0
2
9
5
8
.
7
4
2
4
4
0
.
0
0
2
2
8
0
.
0
0
2
3
1
B
i
L
S
T
M
0
.
0
0
0
7
5
5
.
7
2
0
4
9
0
.
0
0
0
5
7
0
.
0
0
0
5
7
LSTM
0
.
0
0
7
2
1
5
.
2
0
0
9
7
0
.
0
0
6
6
3
0
.
0
0
6
7
1
S
i
mp
l
e
R
N
N
0
.
0
0
3
6
7
1
.
3
5
2
8
9
0
.
0
0
3
4
2
0
.
0
0
3
4
6
C
N
N
0
.
0
0
3
1
5
9
.
9
7
6
2
7
0
.
0
0
2
6
5
0
.
0
0
2
6
7
B
a
t
t
e
r
y
B
0
0
2
8
S
t
a
n
d
a
r
d
d
e
e
p
l
e
a
r
n
i
n
g
0
.
0
0
3
5
2
1
.
2
4
5
3
5
0
.
0
0
2
7
8
0
.
0
0
2
8
5
B
i
L
S
T
M
0
.
0
0
1
4
6
2
.
1
4
9
9
1
0
.
0
0
0
9
5
0
.
0
0
0
9
8
LSTM
0
.
0
0
4
6
4
2
.
1
5
4
3
1
0
.
0
0
3
9
8
0
.
0
0
4
0
7
S
i
mp
l
e
R
N
N
0
.
0
0
1
5
8
2
.
5
1
2
0
9
0
.
0
0
1
3
7
0
.
0
0
1
3
9
C
N
N
0
.
0
0
2
4
4
5
.
9
9
0
4
6
0
.
0
0
1
8
9
0
.
0
0
1
9
3
B
a
t
t
e
r
y
B
0
0
3
6
S
t
a
n
d
a
r
d
d
e
e
p
l
e
a
r
n
i
n
g
0
.
0
1
1
1
8
0
.
0
0
0
1
2
0
.
0
0
3
8
7
0
.
0
0
5
5
6
B
i
L
S
T
M
0
.
0
0
2
7
3
7
.
4
7
5
5
2
0
.
0
0
1
7
6
0
.
0
0
2
5
2
LSTM
0
.
0
0
6
5
2
4
.
2
5
5
7
4
0
.
0
0
4
5
5
0
.
0
0
6
6
1
S
i
mp
l
e
R
N
N
0
.
0
0
3
2
8
1
.
0
7
7
5
8
0
.
0
0
2
1
3
0
.
0
0
2
9
8
C
N
N
0
.
0
1
0
6
5
0
.
0
0
0
1
1
0
.
0
0
8
4
3
0
.
0
1
2
1
6
E
v
a
l
u
a
t
i
o
n
o
f
a
s
i
n
g
l
e
d
e
e
p
l
ea
r
n
i
n
g
m
o
d
e
l
y
i
e
l
d
s
a
B
i
L
S
T
M
m
o
d
e
l
t
h
a
t
i
s
s
u
p
e
r
i
o
r
t
o
o
th
e
r
m
o
d
e
l
s
.
B
i
L
S
T
M
i
s
a
r
e
c
u
r
r
e
n
c
e
m
o
d
e
l
c
a
p
a
b
l
e
o
f
c
a
p
t
u
r
i
n
g
t
e
m
p
o
r
a
l
r
e
l
a
t
i
o
n
s
h
i
p
s
i
n
d
a
t
a
.
B
i
L
S
T
M
e
n
a
b
l
e
s
t
h
e
m
o
d
e
l
t
o
s
e
e
t
h
e
c
o
n
t
e
x
t
b
e
f
o
r
e
a
n
d
a
f
t
e
r
a
g
i
v
e
n
t
i
m
e
,
w
h
i
c
h
i
s
c
r
u
c
i
a
l
f
o
r
i
d
e
n
t
i
f
y
i
n
g
t
r
e
n
d
s
a
n
d
p
a
t
t
e
r
n
s
f
o
r
l
i
-
i
o
n
b
a
t
t
e
r
y
S
o
H
es
t
i
m
a
t
i
o
n
.
B
i
L
ST
M
i
s
c
a
p
a
b
l
e
o
f
i
d
e
n
t
i
f
y
i
n
g
L
i
-
i
o
n
b
a
t
t
e
r
y
c
h
a
r
a
c
t
e
r
i
s
t
i
cs
s
u
c
h
a
s
d
e
g
r
a
d
a
t
i
o
n
o
v
e
r
t
i
m
e
a
n
d
v
a
r
i
a
t
i
o
n
s
i
n
r
e
s
p
o
n
s
e
d
u
r
i
n
g
c
h
a
r
g
e
a
n
d
d
i
s
c
h
a
r
g
e
c
y
c
l
e
s
.
B
i
L
S
T
M
is
w
e
ll
-
s
u
i
t
e
d
t
o
t
h
i
s
t
y
p
e
o
f
t
a
s
k
d
u
e
t
o
it
s
c
a
p
ac
i
t
y
t
o
r
e
ca
l
l
p
a
s
t
i
n
f
o
r
m
a
ti
o
n
a
n
d
u
s
e
i
t
t
o
m
a
k
e
p
r
e
d
i
c
t
i
o
n
s
a
b
o
u
t
t
h
e
f
u
tu
r
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
Hyb
r
id
d
ee
p
lea
r
n
in
g
fo
r
esti
ma
tio
n
o
f sta
te
-
of
-
h
ea
lth
in
lit
h
iu
m
-
io
n
b
a
tter
ies
(
Den
is
E
ka
C
a
h
ya
n
i
)
1001
4.
CO
NCLU
SI
O
N
T
h
e
s
tu
d
y
s
u
cc
ess
f
u
lly
esti
m
ated
th
e
So
H
o
f
lith
iu
m
-
io
n
b
atter
ies
u
s
in
g
h
y
b
r
id
d
e
ep
lear
n
in
g
m
eth
o
d
s
.
T
h
e
h
y
b
r
i
d
d
ee
p
lea
r
n
in
g
m
eth
o
d
s
u
s
ed
in
th
is
s
t
u
d
y
ar
e
s
tan
d
a
r
d
d
ee
p
lear
n
in
g
-
L
STM
,
s
tan
d
ar
d
d
ee
p
lear
n
in
g
-
B
iLST
M,
s
tan
d
ar
d
d
ee
p
lear
n
in
g
-
Simp
leR
NN,
C
NN
-
L
STM
,
C
NN
-
B
i
L
STM
,
an
d
C
NN
-
Simp
leR
NN
.
T
h
is
r
esear
ch
c
o
m
p
ar
es
h
y
b
r
id
d
ee
p
lear
n
in
g
m
eth
o
d
s
with
s
in
g
le
d
ee
p
lear
n
in
g
m
o
d
els
s
u
c
h
as
s
tan
d
ar
d
d
ee
p
lear
n
in
g
,
L
STM
,
B
iLST
M,
Simp
leR
N
N,
a
n
d
C
NN.
C
NN
-
B
iLST
M
h
as
th
e
b
est
r
e
s
u
lts
co
m
p
ar
ed
to
o
th
er
m
eth
o
d
s
.
T
h
e
C
NN
-
B
iLST
M
m
eth
o
d
o
b
t
ain
s
R
MSE
,
MSE
,
MA
E
,
an
d
MA
PE
in
s
eq
u
en
ce
o
f
0
.
0
0
9
1
6
,
0
.
0
0
0
0
8
4
,
0
.
0
0
4
8
,
an
d
0
.
0
0
6
0
3
.
T
h
e
m
o
d
el
th
at
r
ec
eiv
ed
th
e
n
ex
t
b
est
ev
alu
atio
n
f
o
r
a
s
in
g
le
d
ee
p
lear
n
in
g
m
o
d
el
was
B
iLST
M
with
R
MSE
,
MSE
,
MA
E
,
an
d
MA
PE
v
alu
es
r
es
p
ec
tiv
ely
as
f
o
llo
ws
0
.
0
1
0
7
5
,
0
.
0
0
0
1
1
,
0
.
0
0
6
4
9
,
a
n
d
0
.
0
0
7
5
6
.
T
h
is
s
u
g
g
ests
th
at
th
e
C
NN
-
B
iLST
M
h
as
th
e
ab
i
lity
to
esti
m
ate
th
e
b
est L
i
-
io
n
b
atter
y
So
H
co
m
p
ar
ed
to
o
t
h
er
m
eth
o
d
s
.
Fu
tu
r
e
r
esear
ch
ca
n
co
m
b
in
e
C
NN
tr
an
s
f
er
lear
n
in
g
m
o
d
els
s
u
ch
as
R
esn
et5
0
,
VGG1
9
,
I
n
ce
p
tio
n
V3
to
p
r
ed
ict
State
-
of
-
Hea
lth
o
n
li
-
io
n
b
atter
ies.
E
n
s
em
b
le
tr
an
s
f
er
lear
n
in
g
C
NN
ca
n
b
e
c
o
m
b
in
ed
with
o
th
e
r
m
o
d
els
s
u
ch
as
B
iLST
M
o
r
L
STM
to
p
r
o
d
u
ce
b
etter
p
er
f
o
r
m
an
ce
b
ec
au
s
e
it
co
m
b
in
es
th
e
ad
v
a
n
tag
es
o
f
th
ese
m
eth
o
d
s
.
Fu
tu
r
e
r
esear
ch
ca
n
also
esti
m
ate
th
e
R
UL
o
f
li
-
io
n
b
atter
ies
s
o
th
at
th
e
r
esu
lts
o
b
tain
ed
ar
e
m
o
r
e
co
m
p
r
eh
e
n
s
iv
e
th
an
o
n
l
y
esti
m
atin
g
So
H.
AP
P
E
NDI
X
(
a)
(
b
)
Fig
u
r
e
2
.
C
u
r
v
e
o
f
c
o
m
p
a
r
is
o
n
b
etwe
en
So
H
an
d
p
r
e
d
icted
So
H
(
a)
s
tan
d
ar
d
d
ee
p
lear
n
in
g
-
L
STM
an
d
(
b
)
s
tan
d
ar
d
d
ee
p
lear
n
in
g
-
B
iLST
M
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
.
1
,
Feb
r
u
ar
y
20
25
:
9
9
5
-
1
0
0
6
1002
(
c)
(
d
)
(
e)
Fig
u
r
e
2
.
C
u
r
v
e
o
f
c
o
m
p
a
r
is
o
n
b
etwe
en
So
H
an
d
p
r
e
d
icted
So
H
(
c)
s
tan
d
ar
d
d
ee
p
lear
n
in
g
-
Simp
leR
NN,
(
d
)
C
NN
-
L
STM
,
an
d
(
e
)
C
NN
-
B
iLST
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
Hyb
r
id
d
ee
p
lea
r
n
in
g
fo
r
esti
ma
tio
n
o
f sta
te
-
of
-
h
ea
lth
in
lit
h
iu
m
-
io
n
b
a
tter
ies
(
Den
is
E
ka
C
a
h
ya
n
i
)
1003
(f)
(
g
)
(
h
)
Fig
u
r
e
2
.
C
u
r
v
e
o
f
c
o
m
p
a
r
is
o
n
b
etwe
en
So
H
an
d
p
r
e
d
icted
So
H:
(
f
)
C
NN
-
Simp
leR
NN,
(
g
)
s
tan
d
ar
d
d
ee
p
lear
n
in
g
,
an
d
(
h
)
L
STM
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
.
1
,
Feb
r
u
ar
y
20
25
:
9
9
5
-
1
0
0
6
1004
(
i)
(
j)
(
k
)
Fig
u
r
e
2
.
C
u
r
v
e
o
f
c
o
m
p
a
r
is
o
n
b
etwe
en
So
H
an
d
p
r
e
d
icted
So
H:
(
i)
B
iLST
M,
(
j)
Simp
leR
NN,
an
d
(
k
)
C
NN
Evaluation Warning : The document was created with Spire.PDF for Python.