I
A
E
S
I
n
t
e
r
n
at
io
n
al
Jou
r
n
al
of
A
r
t
if
ic
ia
l
I
n
t
e
ll
ig
e
n
c
e
(
I
J
-
AI
)
V
ol
. 14, No. 5, O
c
to
be
r
2025
, pp.
3858
~
3868
I
S
S
N
:
2252
-
8938
,
D
O
I
:
10.11591/
ij
a
i.
v
14
.i
5
.pp
3858
-
3868
3858
Jou
r
n
al
h
om
e
page
:
ht
tp
:
//
ij
ai
.
ia
e
s
c
or
e
.c
om
O
p
t
i
m
i
z
i
n
g
b
at
t
e
r
y
l
i
f
e
:
a
T
i
n
yM
L
ap
p
r
oac
h
to
l
i
t
h
i
u
m
-
i
on
b
at
t
e
r
y
h
e
al
t
h
m
on
i
t
or
i
n
g
K
am
ar
aj
L
al
it
h
a N
is
h
a
1
, V
as
an
t
h
P
r
ad
e
e
p
1
, P
ad
m
an
ab
h
an
P
u
t
h
iy
ave
e
d
u
K
r
is
h
n
a
n
k
u
t
t
y N
ai
r
1
,
S
r
e
e
la
k
s
h
m
i
P
il
la
i
1
, M
an
ik
an
d
an
A
r
u
n
ac
h
al
am
1
, R
ak
e
s
h
T
h
op
p
ae
n
S
u
r
e
s
h
B
ab
u
2
1
D
e
pa
r
t
m
e
nt
of
E
l
e
c
t
r
oni
c
s
a
nd
C
om
m
uni
c
a
t
i
on
E
ngi
ne
e
r
i
ng,
A
m
r
i
t
a
S
c
hool
of
E
ngi
ne
e
r
i
ng,
A
m
r
i
t
a
V
i
s
hw
a
V
i
dya
pe
e
t
ha
m
,
K
ol
l
a
m
,
I
ndi
a
2
D
a
t
a
S
c
i
e
nt
i
s
t
, A
I
A
dvi
s
or
y, F
i
s
e
r
v I
nc
, A
l
pha
r
e
t
t
a
, U
ni
t
e
d S
t
a
t
e
s
A
r
t
ic
le
I
n
f
o
A
B
S
T
R
A
C
T
A
r
ti
c
le
h
is
to
r
y
:
R
e
c
e
iv
e
d
J
ul
3, 2024
R
e
vi
s
e
d
J
un
30
, 2025
A
c
c
e
pt
e
d
J
ul
13, 2025
Electrical
vehicles
(EVs)
are
crucial
nowadays
due
to
their
reduct
ion
in
greenhouse
gas
emissi
ons,
decr
easing
dependence
on
remnant
fuel
s,
and
improving
air
quality.
For
EVs,
the
battery
is
the
heart
that
determines
range,
performance,
and
efficiency.
Also,
it
directly
impacts
the
cost
and
overall
vehicle
life
span.
Lithium
-
ion
(
Li
-
ion
)
batteries
are
pivotal
in
po
wering
modern
portable
electroni
cs
and
electric
vehicles
due
to
their
high
energy
density
and
durability.
Issues
with
current
batteries
include
slow
ch
arging,
short
cycles,
and
low
energy
density.
Most
of
the
problems
with
current
batteries
are
resolved
by
Li
-
ion
batteries,
which
also
helps
expl
ain
w
hy
EV
usage
is
increasin
g
globally.
However,
to
guarantee
maximum
perfor
mance
and
safety,
estimat
ing
the
remaining
useful
life
and
health
state
of
these
batteries
remains
a
major
difficulty.
To
improve
battery
lifetime
of
the
battery
and
to
ov
ercome
the
problems
of
d
elayed
charging,
this
study
introduces
a
tiny
machine
learning
(
TinyML
)
method.
An
inn
ovative
machine
learning
approach
is
put
forth
that
allows
for
effective
learn
ing
on
devices
with
limited
resources,
which
enables
real
-
time
monitoring
of
the
health
status
of
the
Li
-
ion
batteries.
K
e
y
w
o
r
d
s
:
B
a
tt
e
r
y
c
a
pa
c
it
y
pr
e
di
c
ti
on
C
ha
r
ge
e
s
ti
m
a
ti
on
E
S
P
32
L
it
hi
um
-
io
n
T
in
yM
L
This
is
an
open
access
article
under
the
CC
BY
-
SA
license.
C
or
r
e
s
pon
di
n
g
A
u
th
or
:
M
a
ni
ka
nda
n A
r
una
c
h
a
la
m
D
e
pa
r
tm
e
nt
of
E
le
c
tr
oni
c
s
a
nd
C
om
m
uni
c
a
ti
on
E
ngi
ne
e
r
in
g
,
A
m
r
it
a
S
c
hool
of
E
ngi
ne
e
r
in
g
A
m
r
it
a
V
is
hw
a
V
id
ya
pe
e
th
a
m
A
m
r
it
a
pur
i,
K
ol
la
m
,
K
e
r
a
la
,
I
ndi
a
E
m
a
il
:
m
a
ni
_a
c
18@
ya
hoo.c
o.i
n
1.
I
N
T
R
O
D
U
C
T
I
O
N
L
it
hi
um
-
io
n
(
Li
-
io
n
)
ba
tt
e
r
ie
s
a
r
e
e
s
s
e
nt
ia
l
to
c
ont
e
m
por
a
r
y
p
or
ta
bl
e
ga
dge
ts
a
nd
e
le
c
tr
ic
v
e
hi
c
le
s
,
be
c
a
us
e
of
th
e
ir
e
xt
e
nde
d
li
f
e
s
pa
n
a
nd
hi
gh
e
ne
r
gy
de
n
s
it
y
[
1]
.
H
ow
e
ve
r
,
m
a
xi
m
iz
in
g
pe
r
f
or
m
a
nc
e
a
nd
gua
r
a
nt
e
e
in
g
s
a
f
e
ty
de
pe
nds
on
pr
e
c
is
e
ly
e
s
ti
m
a
ti
ng
th
e
r
e
m
a
in
in
g
us
a
bl
e
li
f
e
(
R
U
L
)
a
nd
he
a
lt
h
s
ta
te
of
th
e
s
e
ba
tt
e
r
ie
s
[
2]
,
[
3]
.
F
or
e
xa
m
pl
e
,
dr
one
ope
r
a
to
r
s
f
r
e
que
nt
ly
r
e
pl
a
c
e
ba
tt
e
r
ie
s
a
f
te
r
a
pr
e
de
t
e
r
m
in
e
d
num
be
r
of
c
yc
le
s
to
r
e
duc
e
da
nge
r
s
,
e
ve
n
if
th
e
b
a
tt
e
r
ie
s
m
ig
ht
s
ti
ll
be
a
c
c
e
pt
a
bl
e
f
or
a
f
e
w
s
hor
te
r
f
li
ght
s
.
A
ls
o,
s
in
c
e
th
e
de
m
a
nd
f
or
por
ta
bl
e
a
nd
s
us
ta
in
a
bl
e
e
ne
r
gy
s
our
c
e
s
c
ont
i
nue
s
to
gr
ow
,
th
e
im
por
ta
nc
e
of
e
f
f
e
c
ti
ve
a
nd
r
e
li
a
bl
e
Li
-
io
n
ba
tt
e
r
ie
s
ha
s
ne
ve
r
be
e
n
m
or
e
hi
ghl
ig
ht
e
d
[
4]
.
T
he
s
e
ba
tt
e
r
ie
s
pow
e
r
e
nor
m
ous
de
vi
c
e
s
,
f
r
om
s
m
a
r
tp
hone
s
to
la
pt
ops
to
e
le
c
tr
ic
a
l
ve
hi
c
le
s
(
E
V
s
)
a
nd
r
e
ne
w
a
bl
e
e
ne
r
gy
s
to
r
a
ge
s
ys
te
m
s
.
D
e
s
pi
te
th
e
ir
e
xt
e
ns
iv
e
u
s
e
,
Li
-
io
n
ba
tt
e
r
ie
s
f
a
c
e
s
ig
ni
f
ic
a
nt
c
ha
ll
e
nge
s
r
e
la
te
d
to
th
e
ir
li
f
e
c
yc
le
a
nd
he
a
lt
h
m
oni
to
r
in
g
[
5]
.
T
r
a
di
ti
ona
l
ba
tt
e
r
y
m
a
na
ge
m
e
nt
te
c
hnol
ogi
e
s
of
te
n
de
pe
nd
on
c
om
pl
e
x
a
nd
r
e
s
our
c
e
de
m
a
ndi
ng
m
e
th
ods
to
m
oni
to
r
ba
tt
e
r
y
he
a
lt
h
w
hi
c
h
is
c
os
tl
y
a
nd
in
e
f
f
ic
ie
nt
.
R
e
c
e
nt
a
dva
nc
e
m
e
nt
s
in
ti
ny
m
a
c
hi
ne
le
a
r
ni
ng
(
T
in
yM
L
)
e
xhi
bi
t
a
pr
om
is
in
g
s
ol
ut
io
n
to
th
e
s
e
c
ha
ll
e
nge
s
.
T
i
nyM
L
in
f
lu
e
nc
e
s
th
e
c
a
pa
bi
li
ti
e
s
of
m
a
c
hi
ne
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
r
ti
f
I
nt
e
ll
I
S
S
N
:
2252
-
8938
O
pt
imi
z
in
g batt
e
r
y
l
if
e
:
a
T
in
y
M
L
appr
oac
h t
o l
it
hi
um
-
io
n batt
e
r
y
he
al
th
…
(
K
am
a
r
aj
L
al
it
ha N
is
ha
)
3859
le
a
r
ni
ng
on
r
e
s
our
c
e
c
on
s
tr
a
in
e
d
de
vi
c
e
s
,
e
n
a
bl
in
g
r
e
a
l
-
time
a
nd
pr
e
c
is
e
m
oni
to
r
in
g
of
ba
tt
e
r
y
he
a
lt
h
w
it
h
r
e
duc
e
d
c
om
put
a
ti
ona
l
ove
r
he
a
d
[
6]
.
By
in
c
or
po
r
a
ti
ng
T
in
yM
L
te
c
hni
que
s
in
ba
tt
e
r
y
m
a
na
ge
m
e
nt
s
ys
te
m
s
,
it
is
pos
s
ib
le
to
opt
im
iz
e
ba
tt
e
r
y
li
f
e
,
im
pr
ove
pe
r
f
or
m
a
nc
e
,
a
nd
pr
e
di
c
t
pot
e
nt
ia
l
c
r
a
s
he
s
be
f
or
e
th
e
y
ha
ppe
n,
e
ns
ur
in
g
s
a
f
e
r
a
nd
m
or
e
e
f
f
e
c
ti
ve
ope
r
a
ti
on
of
ba
tt
e
r
ie
s
unde
r
v
a
r
io
us
s
it
ua
ti
ons
.
T
he
R
U
L
of
Li
-
io
n
ba
tt
e
r
ie
s
is
s
tr
ongl
y
in
f
lu
e
nc
e
d
by
te
m
pe
r
a
tu
r
e
a
nd
lo
a
d
(
c
ur
r
e
nt
or
de
pt
h
of
di
s
c
ha
r
ge
)
.
T
he
s
e
f
a
c
to
r
s
a
c
c
e
l
e
r
a
te
de
gr
a
da
ti
on
th
r
ough
m
e
c
ha
ni
s
m
s
li
ke
c
a
pa
c
it
y
f
a
de
a
nd
in
te
r
na
l
r
e
s
is
ta
nc
e
gr
ow
th
.
T
h
e
f
ol
lo
w
in
g
is
a
c
om
m
onl
y
us
e
d
m
ode
l
to
e
s
ti
m
a
te
R
U
L
:
a
de
gr
a
da
ti
on
-
ba
s
e
d
R
U
L
m
ode
l
f
or
Li
-
io
n
ba
tt
e
r
ie
s
of
te
n
c
om
bi
ne
s
th
e
A
r
r
he
ni
us
e
qua
ti
on
(
te
m
pe
r
a
tu
r
e
de
pe
nde
nc
e
)
a
nd
lo
a
d
-
de
p
e
nde
nt
c
yc
li
ng
da
m
a
ge
a
s
i
n (
1)
.
=
−
1
⋅
−
+
2
⋅
(
1)
W
he
r
e
is
in
it
ia
l
ba
tt
e
r
y
c
a
pa
c
it
y
(
A
h)
,
is
c
ur
r
e
nt
ba
tt
e
r
y
c
a
p
a
c
it
y
(
A
h)
,
1
,
2
a
r
e
e
m
pi
r
ic
a
l
de
gr
a
da
ti
on
r
a
te
c
ons
ta
nt
s
f
or
te
m
pe
r
a
tu
r
e
a
nd
c
yc
li
ng,
is
a
c
ti
va
ti
on
e
ne
r
gy,
k
B
is
B
ol
tz
m
a
nn
c
ons
ta
nt
(
1.38×
10
−
23
J
/K)
,
T
i
s
a
bs
ol
ut
e
te
m
pe
r
a
tu
r
e
(
K
e
lv
in
)
,
is
c
ha
r
ge
/d
is
c
ha
r
ge
r
a
te
(
r
e
la
ti
ve
to
1
C,
e
.g.,
0.5
C
or
2
C
)
,
a
nd
b
is
e
xpon
e
nt
r
e
f
le
c
ti
ng
lo
a
d
de
p
e
nde
nc
y.
R
U
L
in
ba
tt
e
r
y
he
a
lt
h
m
oni
to
r
in
g
pr
e
di
c
ts
th
e
time
a
ba
tt
e
r
y
can
c
ont
in
ue
to
pe
r
f
or
m
e
f
f
e
c
ti
ve
ly
be
f
or
e
ne
e
di
ng
r
e
pl
a
c
e
m
e
nt
,
e
na
bl
in
g
pr
oa
c
ti
ve
m
a
in
te
na
nc
e
a
nd
opt
im
iz
a
ti
on.
T
he
in
te
gr
a
ti
on
of
T
in
y
M
L
in
ba
tt
e
r
y
h
e
a
lt
h
m
oni
to
r
in
g
h
a
s
e
m
e
r
ge
d
as
a
pr
om
is
in
g
a
r
e
a
of
r
e
s
e
a
r
c
h,
in
c
or
por
a
ti
ng
a
dva
nc
e
m
e
nt
s
in
m
a
c
hi
ne
le
a
r
ni
ng
w
it
h
th
e
pr
a
c
ti
c
a
l
ne
e
ds
of
ba
tt
e
r
y
m
a
na
ge
m
e
nt
te
c
hnol
ogy.
E
a
r
ly
r
e
s
e
a
r
c
h
in
de
pl
oyi
ng
m
a
c
hi
ne
le
a
r
ni
ng
to
b
a
tt
e
r
y
he
a
lt
h
m
oni
to
r
in
g
s
e
t
th
e
ba
s
e
f
or
da
ta
-
dr
iv
e
n
m
e
th
ods
.
S
e
ve
r
s
on
e
t.
al
.
[
7]
c
onduc
te
d
an
in
nova
ti
ve
s
tu
dy
w
he
r
e
th
e
y
a
ppl
ie
d
m
a
c
hi
ne
le
a
r
ni
ng
a
lg
or
it
hm
s
to
pr
e
di
c
t
th
e
li
f
e
c
yc
le
s
of
Li
-
io
n
ba
tt
e
r
ie
s
us
in
g
e
a
r
ly
c
ha
r
ge
-
di
s
c
ha
r
ge
in
f
or
m
a
ti
on.
T
hi
s
a
ppr
oa
c
h
c
ons
id
e
r
a
bl
y
e
nha
nc
e
d
th
e
a
c
c
ur
a
c
y
of
pr
e
di
c
ti
ons
w
hi
le
c
om
pa
r
in
g
th
e
m
to
th
e
t
r
a
di
ti
ona
l
m
e
th
ods
,
hi
ghl
ig
ht
in
g
th
e
pot
e
nt
ia
l
of
m
a
c
hi
n
e
le
a
r
ni
ng
in
ba
tt
e
r
y
li
f
e
ti
m
e
a
na
ly
s
is
.
F
ur
th
e
r
e
xt
e
ndi
ng
th
is
w
or
k,
va
r
io
us
m
a
c
hi
ne
le
a
r
ni
ng
m
e
th
ods
,
in
c
lu
di
ng
s
uppor
t
ve
c
to
r
m
a
c
hi
ne
s
a
nd
ne
ur
a
l
ne
twor
ks
w
e
r
e
e
xpl
or
e
d
to
pr
e
di
c
t
th
e
ba
tt
e
r
y
l
if
e
ti
m
e
a
nd
c
a
pa
c
it
y
di
s
c
ha
r
gi
ng
[
8]
.
T
he
ir
obs
e
r
va
ti
ons
unde
r
e
s
ti
m
a
te
d
th
e
im
por
ta
nc
e
of
f
e
a
tu
r
e
s
e
le
c
ti
on
a
nd
th
e
pr
om
is
e
of
e
ns
e
m
bl
e
le
a
r
ni
ng
m
e
th
ods
in
im
pr
ovi
ng
th
e
a
c
c
ur
a
c
y
of
pr
e
di
c
ti
on.
T
he
pa
r
a
di
gm
s
hi
f
t
to
w
a
r
ds
T
in
yM
L
s
ig
ni
f
ie
s
a
s
te
p
f
or
w
a
r
d
in
ba
tt
e
r
y
he
a
lt
h
m
oni
to
r
in
g,
f
oc
us
in
g
on
de
pl
oyi
ng
m
a
c
hi
ne
le
a
r
ni
ng
m
e
th
od
s
on
r
e
s
ou
r
c
e
-
c
ont
r
ol
le
d
de
vi
c
e
s
.
A
li
ght
w
e
ig
ht
ne
ur
a
l
ne
twor
k
opt
im
iz
e
d
f
or
m
ic
r
oc
ont
r
ol
le
r
s
,
c
a
pa
bl
e
of
r
e
a
l
-
time
h
e
a
lt
h
pr
e
di
c
ti
ons
f
or
Li
-
io
n
ba
tt
e
r
ie
s
[
9]
.
T
hi
s
m
e
th
od
not
onl
y
r
e
duc
e
d
th
e
c
om
put
a
ti
ona
l
lo
a
d
but
a
ls
o
m
a
in
ta
in
e
d
hi
gh
a
c
c
ur
a
c
y,
m
a
ki
ng
it
id
e
a
l
f
or
por
ta
bl
e
E
V
s
.
B
ui
ld
in
g
on
th
is
,
T
in
yM
L
w
it
h
I
oT
de
vi
c
e
s
f
or
r
e
m
ot
e
m
oni
to
r
in
g
of
ba
tt
e
r
y
he
a
lt
h
w
a
s
in
c
or
por
a
te
d
to
s
tu
dy
th
e
e
xhi
bi
te
d
pos
s
ib
il
it
y
of
im
pl
e
m
e
nt
in
g
T
in
yM
L
m
ode
ls
on
e
dge
de
vi
c
e
s
,
pe
r
m
it
ti
ng
c
ont
in
uous
m
oni
to
r
in
g
w
it
hout
r
e
le
nt
le
s
s
c
onne
c
ti
vi
ty
to
c
lo
ud
s
e
r
ve
r
s
.
T
hi
s
in
te
gr
a
ti
on
e
na
bl
e
d
r
obus
t
da
ta
c
ol
le
c
ti
on
a
nd
r
e
a
l
-
time
a
na
ly
s
is
,
pa
vi
ng
th
e
w
a
y
f
or
pr
e
di
c
ti
ve
m
a
in
te
na
nc
e
a
nd
f
a
ul
t
di
a
gnos
is
in
ba
tt
e
r
y
m
oni
to
r
in
g
[
10
]
.
G
r
uos
s
o
a
nd
G
a
ja
ni
[
11]
de
m
ons
tr
a
te
d
th
e
c
om
pa
r
is
on
of
m
a
c
hi
ne
le
a
r
ni
ng
a
lg
or
it
hm
s
in
T
in
yM
L
f
or
th
e
e
s
ti
m
a
ti
on
of
ba
tt
e
r
y
s
ta
te
.
ANN
ba
s
e
d
pr
e
di
c
ti
on
m
e
th
ods
a
r
e
de
pl
oye
d
a
nd
c
om
pa
r
e
d
in
te
r
m
s
of
c
os
t,
m
e
m
or
y
,
a
nd
c
om
put
a
ti
ona
l
pow
e
r
.
F
ur
th
e
r
m
or
e
,
L
or
d
a
nd
K
a
pl
a
n
[
12]
a
na
ly
z
e
d
th
e
a
ppl
ic
a
ti
on
of
two
di
f
f
e
r
e
nt
ne
ur
a
l
ne
twor
ks
in
T
in
yM
L
f
r
a
m
e
w
or
ks
f
or
ba
tt
e
r
y
a
nom
a
ly
de
te
c
ti
on.
F
in
a
ll
y,
th
e
opt
im
iz
e
d
m
ode
l
w
a
s
m
ount
e
d
in
th
e
m
ic
r
oc
ont
r
ol
le
r
s
,
in
di
c
a
ti
ng
s
ig
ni
f
ic
a
nt
im
pr
ove
m
e
nt
s
in
th
e
a
c
c
ur
a
c
y
de
te
c
ti
on
w
it
h
lo
w
pow
e
r
c
ons
um
pt
io
n.
T
he
in
te
gr
a
ti
on
of
I
oT
a
nd
T
in
yM
L
f
ur
th
e
r
im
pr
ove
d
th
e
a
bi
li
ti
e
s
of
ba
tt
e
r
y
he
a
lt
h
m
oni
to
r
in
g
s
ys
te
m
[
13]
.
S
tu
di
e
s
in
r
e
s
e
a
r
c
h
s
ugg
e
s
te
d
a
hybr
id
m
ode
l
th
a
t
c
om
bi
ne
d
a
tr
a
di
ti
ona
l
ba
tt
e
r
y
m
oni
to
r
in
g
s
ys
te
m
w
it
h
T
in
yM
L
e
nha
nc
e
m
e
nt
s
,
r
e
s
ul
ti
ng
in
e
nha
nc
e
d
a
c
c
u
r
a
c
y
in
e
s
ti
m
a
ti
ng
th
e
r
e
m
a
in
in
g
us
e
f
ul
li
f
e
of
ba
tt
e
r
ie
s
[
14]
.
M
or
e
ove
r
,
W
a
ng
e
t.
al
.
[
15]
c
r
e
a
te
d
an
I
oT
ba
s
e
d
f
r
a
m
e
w
or
k
f
or
de
vot
e
d
ba
tt
e
r
y
he
a
lt
h
m
oni
to
r
in
g.
T
hi
s
s
tu
dy
e
m
pl
oye
d
T
in
yM
L
m
ode
ls
de
pl
oye
d
on
e
dge
de
vi
c
e
s
,
e
na
bl
in
g
r
e
a
l
time
a
na
ly
s
is
,
a
nd
de
c
is
io
n
m
a
ki
ng.
T
he
a
r
c
hi
te
c
tu
r
e
r
e
duc
e
d
th
e
s
uppor
t
on
c
e
nt
r
a
li
z
e
d
c
lo
ud
s
e
r
ve
r
s
,
im
pr
ovi
ng
th
e
r
obus
tn
e
s
s
a
nd
s
c
a
la
bi
li
ty
of
th
e
m
oni
to
r
in
g
s
y
s
te
m
.
W
hi
le
th
e
e
xi
s
ti
ng
r
e
s
e
a
r
c
h
a
ppl
ic
a
ti
ons
of
T
in
yM
L
ba
tt
e
r
y
h
e
a
lt
h
m
oni
to
r
in
g
s
how
pr
om
is
in
g
r
e
s
ul
ts
,
th
e
r
e
a
r
e
c
ha
ll
e
nge
s
to
a
ddr
e
s
s
[
16]
.
T
he
ke
y
c
ha
ll
e
nge
is
s
hor
ta
ge
of
s
ta
nda
r
di
z
e
d
da
t
a
s
e
ts
a
nd
be
nc
hm
a
r
ki
ng
f
r
a
m
e
w
or
ks
to
e
va
lu
a
te
th
e
pe
r
f
or
m
a
nc
e
of
T
in
yM
L
m
ode
ls
a
c
r
os
s
di
f
f
e
r
e
nt
a
ppl
ic
a
ti
ons
.
M
or
e
ove
r
,
e
ns
ur
in
g
th
e
r
obu
s
tn
e
s
s
a
nd
s
e
c
ur
it
y
of
T
in
yM
L
m
ode
ls
im
pl
e
m
e
nt
e
d
on
e
dge
de
vi
c
e
s
is
c
r
it
ic
a
l,
pa
r
ti
c
ul
a
r
ly
in
s
a
f
e
ty
c
r
it
ic
a
l
a
ppl
i
c
a
ti
ons
w
it
h
E
V
s
[
17]
.
To
ove
r
c
om
e
th
e
s
e
li
m
it
a
ti
ons
of
th
e
e
xi
s
ti
ng
w
or
ks
,
a
r
e
a
l
-
time
ba
tt
e
r
y
he
a
lt
h
m
on
it
or
in
g
s
ys
te
m
is
pr
opos
e
d
f
or
Li
-
io
n
ba
tt
e
r
ie
s
w
hi
c
h
e
na
bl
e
s
r
e
a
l
-
time
a
n
a
ly
s
is
on
e
dge
de
vi
c
e
s
.
E
S
P
32
m
ic
r
oc
ont
r
ol
le
r
,
a
s
im
pl
e
a
nd
lo
w
-
c
os
t
c
hi
p
th
a
t
m
a
ke
s
th
e
s
ol
ut
io
n
a
c
c
e
s
s
ib
le
a
nd
a
f
f
or
da
bl
e
,
is
a
c
r
uc
ia
l
c
om
pone
nt
of
our
im
pl
e
m
e
nt
a
ti
on.
T
hi
s
im
pl
e
m
e
nt
a
ti
on
s
how
s
how
us
e
f
ul
T
in
yM
L
is
f
or
e
s
ti
m
a
ti
ng
b
a
tt
e
r
y
he
a
lt
h
in
pr
a
c
ti
c
a
l
a
ppl
ic
a
ti
ons
[
18]
.
To
s
e
le
c
t
th
e
opt
im
a
l
ba
tt
e
r
y
c
ha
r
gi
ng
pr
oc
e
dur
e
s
,
th
e
s
ta
te
of
c
ha
r
ge
(
S
oC
)
e
s
ti
m
a
ti
on
is
e
s
s
e
nt
ia
l.
P
a
r
ti
c
ul
a
r
ly
r
e
ga
r
di
ng
r
a
pi
d
c
ha
r
gi
ng,
w
hi
c
h
a
ll
ow
s
f
o
r
a
s
ubs
ta
nt
ia
l
r
e
du
c
ti
on
in
c
ha
r
gi
ng
time
w
it
hout
c
om
pr
om
is
in
g
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8938
I
nt
J
A
r
ti
f
I
nt
e
ll
,
V
ol
. 14, No. 5, O
c
to
be
r
2025
:
3858
-
3868
3860
th
e
ba
tt
e
r
y'
s
ove
r
a
ll
li
f
e
s
p
a
n
[
19]
.
T
in
y
M
L
ba
tt
e
r
y
he
a
lt
h
a
s
s
e
s
s
m
e
nt
is
be
in
g
a
dva
nc
e
d
to
a
s
s
i
s
t
la
r
ge
r
obj
e
c
ti
ve
s
of
im
pr
ovi
ng
p
e
r
f
or
m
a
nc
e
a
nd
s
a
f
e
ty
b
e
c
a
u
s
e
Li
-
io
n
ba
tt
e
r
ie
s
a
r
e
e
xt
r
e
m
e
ly
e
xpl
os
iv
e
[
20]
,
[
21]
,
a
nd
Li
-
io
n
ba
tt
e
r
y
lo
nge
vi
ty
is
th
e
m
a
jo
r
r
e
qui
r
e
m
e
nt
in
a
va
r
ie
ty
of
a
ppl
ic
a
ti
ons
[
22]
,
[
23]
.
T
hi
s
he
lp
s
to
c
r
e
a
te
m
or
e
e
f
f
e
c
ti
ve
a
nd
s
u
s
ta
in
a
bl
e
e
ne
r
gy
s
ol
ut
io
ns
in
te
r
na
ti
ona
ll
y,
w
hi
c
h
is
good
f
or
bus
in
e
s
s
e
s
a
nd
c
ons
um
e
r
s
a
li
ke
.
O
ur
s
tu
dy
e
xt
e
nd
s
ba
tt
e
r
y
li
f
e
s
pa
n
a
nd
pr
om
ot
e
s
s
u
s
ta
in
a
bi
li
ty
by
opt
im
iz
in
g
EV
c
ha
r
gi
ng
c
yc
le
s
,
pr
e
ve
nt
in
g
unpl
a
nne
d
s
hut
dow
ns
,
a
nd
in
c
r
e
a
s
in
g
us
e
r
e
xpe
r
ie
nc
e
th
r
ough
im
p
r
ove
d
ba
tt
e
r
y
li
f
e
pr
oj
e
c
ti
ons
.
To
a
s
s
ur
e
d
e
pe
nda
bl
e
pr
e
di
c
ti
ons
unde
r
T
in
yM
L
li
m
it
a
ti
ons
,
we
in
ve
s
ti
ga
t
e
a
v
a
r
ie
ty
of
m
a
c
hi
ne
le
a
r
ni
ng
te
c
hni
que
s
a
ppr
opr
ia
te
f
or
r
e
s
our
c
e
-
c
ons
tr
a
in
e
d
c
ont
e
xt
s
,
w
e
ig
hi
ng
in
f
e
r
e
nc
e
s
pe
e
d,
m
od
e
l
s
iz
e
,
a
nd
a
c
c
ur
a
c
y.
O
ur
r
e
s
e
a
r
c
h
us
e
s
T
in
yM
L
,
a
c
ut
ti
ng
-
e
dge
te
c
hnol
o
gy
th
a
t
e
na
bl
e
s
m
a
c
hi
ne
le
a
r
ni
ng
on
de
vi
c
e
s
w
it
h
li
m
it
e
d
r
e
s
our
c
e
s
,
to
ta
c
kl
e
th
is
pr
obl
e
m
.
2.
M
E
T
H
O
D
O
L
O
G
Y
O
ur
obj
e
c
ti
ve
is
to
us
e
T
in
yM
L
to
c
r
e
a
te
a
s
m
a
ll
,
pr
e
c
i
s
e
pr
e
di
c
ti
on
m
ode
l
f
or
Li
-
io
n
ba
tt
e
r
y
c
a
pa
c
it
y
e
s
ti
m
a
ti
on.
T
he
v
a
r
io
us
s
te
ps
in
vol
ve
d
in
th
i
s
pr
oc
e
s
s
a
r
e
da
ta
pr
e
pa
r
a
ti
on,
m
ode
l
de
ve
lo
pm
e
nt
,
c
onve
r
s
io
n,
opt
im
iz
a
ti
on,
a
nd
de
pl
oym
e
nt
.
T
he
pr
opos
e
d
m
od
e
l
w
a
s
tr
a
in
e
d
on
th
or
ough
a
nd
pe
r
ti
ne
nt
da
ta
by
ut
il
iz
in
g
th
e
N
A
S
A
ba
tt
e
r
y
da
ta
s
e
t,
w
hi
c
h
e
na
bl
e
d
a
c
c
ur
a
te
a
nd
e
f
f
e
c
ti
ve
r
e
a
l
-
time
p
r
e
di
c
ti
ons
on
a
de
vi
c
e
w
it
h
li
m
it
e
d
r
e
s
our
c
e
s
.
T
hi
s
d
a
ta
s
e
t
is
id
e
a
l
f
or
c
a
pa
c
it
y
pr
e
di
c
ti
on
be
c
a
us
e
th
e
di
s
c
ha
r
gi
ng
a
nd
c
h
a
r
gi
ng
pa
tt
e
r
ns
a
r
e
f
ix
e
d.
T
he
S
oC
e
s
ti
m
a
ti
on
is
in
f
lu
e
nc
e
d
by
a
b
a
tt
e
r
y'
s
c
ha
r
gi
ng
a
nd
di
s
c
ha
r
gi
ng
e
f
f
ic
ie
nc
ie
s
.
2.1.
C
on
vol
u
t
io
n
al
n
e
u
r
al
n
e
t
w
or
k
s
T
he
N
A
S
A
ba
tt
e
r
y
da
t
a
s
e
t
is
pr
e
pr
oc
e
s
s
e
d
to
pr
e
p
a
r
e
th
e
d
a
ta
s
e
t
f
or
e
f
f
ic
ie
nt
us
e
in
c
onvolut
io
na
l
ne
ur
a
l
ne
twor
k
(
C
N
N
)
m
ode
l
t
r
a
in
in
g.
P
r
e
pa
r
in
g
th
e
da
ta
f
or
C
N
N
-
ba
s
e
d
a
na
ly
s
is
in
vol
ve
s
a
c
ti
vi
ti
e
s
,
in
c
lu
di
ng
f
e
a
tu
r
e
e
ngi
ne
e
r
in
g,
nor
m
a
li
z
a
ti
on,
a
nd
da
ta
c
le
a
ni
ng.
T
he
N
A
S
A
ba
tt
e
r
y
da
ta
s
e
t'
s
r
a
w
da
ta
,
w
hi
c
h
in
c
lu
de
s
va
r
ia
bl
e
s
li
ke
vol
ta
ge
,
c
ur
r
e
nt
,
a
nd
t
e
m
pe
r
a
tu
r
e
,
is
tr
a
ns
f
or
m
e
d
to
e
ns
ur
e
c
on
s
is
te
n
c
y
a
nd
a
ppl
ic
a
bi
li
ty
dur
in
g
th
e
t
r
a
in
in
g
pha
s
e
[
24]
,
[
25]
.
F
u
r
th
e
r
m
or
e
,
th
e
a
li
gnm
e
nt
of
time
s
e
r
ie
s
a
nd
th
e
r
e
s
ol
ut
io
n
of
m
is
s
in
g
va
lu
e
s
a
r
e
e
s
s
e
nt
ia
l
c
om
pone
nt
s
in
ge
tt
in
g
th
e
da
ta
r
e
a
dy
f
or
e
f
f
e
c
ti
ve
C
N
N
m
ode
l
tr
a
in
in
g.
By
im
pr
ovi
ng
th
e
da
ta
s
e
t'
s
qua
li
ty
a
nd
c
ons
i
s
te
nc
y,
th
e
s
e
pr
e
pr
oc
e
s
s
in
g
pr
oc
e
dur
e
s
s
houl
d
he
lp
th
e
C
N
N
m
ode
l
le
a
r
n
a
nd
pr
e
di
c
t
m
or
e
a
c
c
ur
a
te
ly
dur
in
g
tr
a
in
in
g
[
25]
.
C
N
N
m
ode
ls
a
r
e
bui
lt
u
s
in
g
a
s
e
t
of
a
r
c
hi
te
c
tu
r
a
l
p
a
r
a
m
e
te
r
s
,
i
nc
lu
di
ng
th
e
num
be
r
of
c
onvolut
io
na
l
la
ye
r
s
,
th
e
s
iz
e
of
f
e
a
tu
r
e
m
a
ps
in
s
id
e
each
la
ye
r
,
a
nd
th
e
c
onn
e
c
ti
vi
ty
be
twe
e
n
th
e
m
.
T
he
C
N
N
a
r
c
hi
te
c
tu
r
e
is
ul
ti
m
a
te
ly
c
us
to
m
iz
e
d
a
c
c
or
di
ng
to
th
e
da
ta
s
e
t'
s
c
om
pl
e
xi
ty
a
nd
th
e
m
ode
l'
s
in
te
nde
d
a
bi
li
ty
to
a
c
c
ur
a
te
ly
c
a
pt
ur
e
s
pa
ti
a
l
pa
tt
e
r
ns
a
nd
f
e
a
tu
r
e
hi
e
r
a
r
c
hi
e
s
pe
r
ti
ne
nt
to
th
e
ta
s
k
at
ha
nd.
D
e
te
r
m
in
in
g
th
e
id
e
a
l
num
be
r
of
la
ye
r
s
,
f
e
a
tu
r
e
m
a
p
s
iz
e
a
nd
or
ga
ni
z
a
ti
on,
a
nd
la
ye
r
c
onne
c
ti
on
a
r
e
a
ll
in
c
lu
de
d
in
th
is
c
a
r
e
f
ul
de
s
ig
n.
C
N
N
s
a
r
e
c
a
pa
bl
e
of
e
f
f
e
c
ti
ve
ly
e
xt
r
a
c
ti
ng
s
ig
ni
f
ic
a
nt
in
f
or
m
a
ti
on
f
r
om
th
e
in
put
da
ta
a
nd
c
a
pt
ur
in
g
th
e
s
pa
ti
a
l
r
e
la
ti
ons
hi
ps
ne
c
e
s
s
a
r
y
f
or
pr
e
c
is
e
pr
e
di
c
ti
on
by
c
a
r
e
f
ul
ly
pl
a
nni
ng
th
e
ir
a
r
c
hi
te
c
tu
r
e
[
26]
.
T
he
r
e
f
or
e
,
th
e
f
ounda
ti
on
f
or
a
tt
a
in
in
g
hi
gh
pe
r
f
o
r
m
a
nc
e
a
nd
r
e
s
il
ie
nc
e
in
a
va
r
ie
ty
of
C
N
N
-
ba
s
e
d
a
ppl
ic
a
ti
ons
is
a
w
e
ll
-
de
s
ig
ne
d
C
N
N
a
r
c
hi
te
c
tu
r
e
.
T
h
e
pur
pos
e
of
th
is
va
li
da
ti
o
n
da
ta
s
e
t
is
to
e
va
lu
a
te
th
e
m
ode
l'
s
a
bi
li
ty
to
ge
ne
r
a
li
z
e
to
pr
e
vi
ous
ly
undi
s
c
ove
r
e
d
da
ta
in
de
pe
nde
nt
ly
.
D
if
f
e
r
e
nt
a
s
s
e
s
s
m
e
nt
m
e
tr
ic
s
a
r
e
f
r
e
que
nt
ly
us
e
d
to
m
e
a
s
ur
e
th
e
di
f
f
e
r
e
nc
e
be
twe
e
n
th
e
pr
e
di
c
te
d
v
a
lu
e
s
a
nd
t
he
a
c
tu
a
l
gr
ound
tr
ut
h
la
be
ls
in
th
e
va
li
da
ti
on
da
ta
s
e
t.
E
xa
m
pl
e
s
of
th
e
s
e
m
e
tr
ic
s
a
r
e
m
e
a
n
a
bs
ol
ut
e
e
r
r
or
(
M
A
E
)
a
nd
r
oot
m
e
a
n
s
qua
r
e
d
e
r
r
or
(
R
M
S
E
)
.
T
he
s
e
m
e
a
s
ur
e
s
s
he
d
li
ght
on
how
th
e
pr
e
di
c
ti
ons
m
a
de
by
C
N
N
a
r
e
a
c
c
ur
a
te
a
nd
de
pe
nda
bl
e
[
27]
.
R
e
s
e
a
r
c
h
e
r
s
a
nd
pr
a
c
ti
ti
one
r
s
can
le
a
r
n
a
gr
e
a
t
d
e
a
l
a
bout
C
N
N
'
s
pr
e
di
c
ti
ve
a
c
c
ur
a
c
y
by
e
x
a
m
in
in
g
th
e
e
va
lu
a
ti
on
f
in
di
ngs
.
To
f
ur
th
e
r
im
pr
ove
th
e
m
ode
l'
s
pe
r
f
or
m
a
nc
e
,
th
e
y
c
a
n
a
ls
o
s
pot
pos
s
ib
le
a
r
e
a
s
f
or
im
pr
ove
m
e
nt
,
s
uc
h
as
a
lt
e
r
in
g
th
e
m
ode
l
a
r
c
hi
te
c
tu
r
e
or
f
in
e
-
t
uni
ng
hype
r
pa
r
a
m
e
te
r
s
.
To
r
e
duc
e
th
e
a
m
ount
of
m
e
m
or
y
a
nd
pr
oc
e
s
s
in
g
pow
e
r
ne
e
d
e
d,
th
is
e
nt
a
il
s
m
ode
l
qua
nt
iz
a
ti
on
or
d
e
c
r
e
a
s
in
g
th
e
pr
e
c
i
s
io
n
of
w
e
ig
ht
s
.
A
f
te
r
th
a
t,
th
e
m
ode
ls
a
r
e
tr
a
ns
f
or
m
e
d
in
to
a
f
or
m
a
t
th
a
t
is
c
om
pa
ti
bl
e
w
it
h
T
in
y
M
L
,
a
ll
ow
in
g
de
vi
c
e
s
w
it
h
lo
w
pr
oc
e
s
s
in
g
pow
e
r
to
us
e
th
e
m
.
By
opt
im
iz
in
g
th
e
m
ode
ls
f
or
T
in
yM
L
,
th
e
a
ppr
oa
c
h
be
c
om
e
s
r
e
le
va
nt
f
or
e
dge
c
om
put
in
g
a
nd
I
oT
de
vi
c
e
s
,
as
it
gua
r
a
nt
e
e
s
th
a
t
th
e
m
ode
ls
can
be
im
pl
e
m
e
nt
e
d
on
m
ic
r
oc
ont
r
ol
le
r
s
.
3.
H
A
R
D
WA
R
E
I
M
P
L
E
M
E
N
T
A
T
I
O
N
T
he
de
v
e
lo
pm
e
nt
of
a
r
e
li
a
bl
e
Li
-
io
n
ba
tt
e
r
y
c
a
pa
c
it
y
pr
e
di
c
ti
o
n
s
ys
te
m
is
e
s
s
e
nt
ia
l
f
or
th
e
e
f
f
ic
ie
nt
m
a
na
ge
m
e
nt
a
nd
lo
nge
vi
ty
of
ba
tt
e
r
ie
s
in
va
r
io
us
a
ppl
ic
a
ti
ons
[
28]
.
O
ur
pr
oj
e
c
t
ut
il
iz
e
s
a
c
us
to
m
iz
e
d
E
S
P
3
2
m
ic
r
oc
ont
r
ol
le
r
-
ba
s
e
d
ha
r
dw
a
r
e
s
e
tu
p,
c
oupl
e
d
w
it
h
a
C
N
N
m
ode
l,
to
pr
e
di
c
t
th
e
r
e
m
a
in
in
g
c
a
p
a
c
it
y
of
Li
-
io
n
ba
tt
e
r
ie
s
.
T
hi
s
s
ys
te
m
in
te
gr
a
te
s
a
dv
a
nc
e
d
s
e
n
s
or
s
a
nd
a
c
us
to
m
pr
in
te
d
c
ir
c
ui
t
boa
r
d
(
P
C
B
)
to
e
ns
ur
e
a
c
c
ur
a
te
da
ta
c
ol
le
c
ti
on
a
nd
r
obus
t
pe
r
f
or
m
a
nc
e
,
e
ve
n
in
c
ha
l
le
ngi
ng
c
ondi
ti
ons
.
T
he
E
S
P
32
is
a
ve
r
s
a
ti
le
m
ic
r
oc
ont
r
ol
le
r
f
e
a
tu
r
in
g
a
dua
l
-
c
or
e
X
te
ns
a
L
X
6
p
r
oc
e
s
s
or
w
it
h
a
32
-
bi
t
a
r
c
hi
te
c
tu
r
e
a
nd
c
lo
c
k
s
pe
e
ds
of
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
r
ti
f
I
nt
e
ll
I
S
S
N
:
2252
-
8938
O
pt
imi
z
in
g batt
e
r
y
l
if
e
:
a
T
in
y
M
L
appr
oac
h t
o l
it
hi
um
-
io
n batt
e
r
y
he
al
th
…
(
K
am
a
r
aj
L
al
it
ha N
is
ha
)
3861
up
to
240
M
H
z
[
29]
.
It
in
c
lu
de
s
520
KB
of
S
R
A
M
,
4
MB
of
f
la
s
h
m
e
m
or
y
(
e
xpa
nda
bl
e
to
16
M
B
)
,
a
nd
bui
lt
-
in
Wi
-
Fi
(
2.4
G
H
z
,
I
E
E
E
802.11
b/
g/
n)
a
nd
B
lu
e
to
ot
h
v4.2
(
B
R
/E
D
R
a
nd
B
L
E
)
f
or
w
ir
e
le
s
s
c
onne
c
ti
vi
ty
.
F
ig
ur
e
1
s
how
s
a
ll
th
e
ha
r
dw
a
r
e
c
om
pone
nt
s
us
e
d
in
th
e
pr
oj
e
c
t.
K
e
y
to
our
d
e
s
ig
n
is
th
e
u
s
e
of
th
e
I
N
A
219
vol
ta
ge
a
nd
c
ur
r
e
nt
s
e
ns
or
,
w
hi
c
h
pr
ovi
de
s
pr
e
c
i
s
e
di
gi
ta
l
m
e
a
s
ur
e
m
e
nt
s
.
T
he
s
e
ns
or
op
e
r
a
te
s
by
m
e
a
s
ur
in
g
th
e
vol
t
a
ge
dr
op
a
c
r
os
s
a
s
hunt
r
e
s
is
to
r
,
a
ll
ow
in
g
it
to
c
a
lc
ul
a
t
e
th
e
c
ur
r
e
nt
a
nd
vol
ta
ge
of
th
e
ba
tt
e
r
y.
T
he
di
gi
ta
l
na
tu
r
e
of
th
e
da
ta
e
ns
ur
e
s
th
a
t
th
e
in
te
gr
i
ty
of
th
e
t
r
a
ns
m
it
te
d
va
lu
e
s
r
e
m
a
in
s
in
ta
c
t,
e
ve
n
w
he
n
th
e
m
ic
r
oc
ont
r
ol
le
r
is
pos
it
io
ne
d
at
a
di
s
ta
nc
e
f
r
om
th
e
s
e
ns
or
.
T
hi
s
is
c
r
uc
ia
l
f
or
m
a
in
ta
in
in
g
a
c
c
ur
a
c
y
in
r
e
a
l
-
w
or
ld
a
ppl
ic
a
ti
ons
w
h
e
r
e
s
e
ns
or
pl
a
c
e
m
e
nt
f
le
xi
bi
li
ty
is
ne
e
de
d.
F
or
te
m
pe
r
a
tu
r
e
m
oni
to
r
in
g,
th
e
D
S
18B
20
pr
obe
-
ty
pe
s
e
ns
or
is
e
m
pl
oye
d.
T
hi
s
s
e
ns
or
di
r
e
c
tl
y
c
onne
c
ts
to
th
e
b
a
tt
e
r
y
body,
pr
ovi
di
ng
a
c
c
ur
a
te
te
m
pe
r
a
tu
r
e
r
e
a
di
ngs
.
T
he
D
S
18B
20
u
s
e
s
a
1
-
w
ir
e
pr
ot
oc
ol
,
w
hi
c
h
is
a
dva
nt
a
ge
ou
s
as
it
a
ddr
e
s
s
e
s
th
e
li
m
it
a
ti
ons
of
a
na
lo
g
por
ts
a
nd
s
im
pl
if
ie
s
th
e
w
ir
in
g
r
e
qui
r
e
m
e
nt
s
.
T
h
e
s
e
n
s
or
can
be
pos
it
io
ne
d
pr
e
c
is
e
ly
to
m
oni
to
r
th
e
ba
tt
e
r
y'
s
s
ur
f
a
c
e
te
m
pe
r
a
tu
r
e
,
w
hi
c
h
is
c
r
uc
ia
l
f
or
a
c
c
ur
a
te
c
a
pa
c
it
y
pr
e
di
c
ti
on
as
te
m
pe
r
a
tu
r
e
s
ig
ni
f
ic
a
nt
ly
a
f
f
e
c
ts
ba
tt
e
r
y
pe
r
f
or
m
a
nc
e
.
T
he
pr
obe
'
s
r
obus
t
de
s
ig
n
e
ns
ur
e
s
r
e
li
a
bl
e
ope
r
a
ti
on
in
va
r
io
us
e
nvi
r
onm
e
nt
a
l
c
ondi
ti
ons
,
m
a
ki
ng
it
id
e
a
l
f
or
lo
ng
-
te
r
m
m
oni
to
r
in
g.
F
ig
ur
e
1.
H
a
r
dw
a
r
e
c
om
pone
nt
s
O
ur
c
us
to
m
P
C
B
de
s
ig
n
e
nha
nc
e
s
th
e
f
unc
ti
ona
li
ty
of
th
e
s
ta
nda
r
d
E
S
P
32
de
ve
lo
pm
e
nt
boa
r
d.
By
e
li
m
in
a
ti
ng
th
e
on
-
boa
r
d
pr
og
r
a
m
m
e
r
,
w
hi
c
h
c
ons
um
e
s
s
ig
ni
f
ic
a
nt
pow
e
r
,
w
e
ha
ve
opt
im
iz
e
d
th
e
boa
r
d
f
or
lo
w
-
pow
e
r
ope
r
a
ti
on.
T
he
c
us
to
m
P
C
B
f
e
a
tu
r
e
s
di
r
e
c
t
por
ts
f
or
c
onne
c
ti
ng
s
e
ns
or
s
a
nd
a
16×
2
L
C
D
di
s
pl
a
y,
w
hi
c
h pr
ovi
de
s
r
e
a
l
-
ti
m
e
f
e
e
dba
c
k a
nd da
ta
vi
s
ua
li
z
a
ti
on. T
o e
ns
ur
e
a
s
ta
bl
e
pow
e
r
s
uppl
y, w
e
i
nt
e
gr
a
te
d t
w
o
vol
ta
ge
r
e
gul
a
to
r
s
:
a
n
L
M
7805,
w
hi
c
h
pr
ovi
de
s
a
5
V
out
put
a
t
1
A
to
pow
e
r
th
e
L
C
D
,
I
N
A
219
s
e
ns
or
,
a
nd
D
S
18B
20
s
e
ns
or
,
a
nd
a
n
L
M
1117I
C
,
w
hi
c
h
s
t
e
ps
dow
n
th
e
vol
ta
ge
to
de
li
ve
r
a
n
800
-
m
A
out
put
f
o
r
th
e
E
S
P
32.
T
hi
s
dua
l
-
r
e
gul
a
to
r
s
e
tu
p
not
onl
y
s
uppor
ts
a
ll
c
om
po
ne
nt
s
w
it
h
a
de
qua
te
pow
e
r
but
a
ls
o
e
nha
nc
e
s
th
e
ove
r
a
ll
r
e
li
a
bi
li
ty
a
nd
e
f
f
ic
ie
nc
y
of
th
e
s
ys
te
m
by
pr
e
v
e
nt
in
g
pow
e
r
s
ur
ge
s
a
nd
e
n
s
ur
in
g
c
ons
i
s
te
nt
vol
ta
ge
l
e
ve
ls
.
A
la
r
ge
s
w
it
c
h
is
in
c
or
por
a
te
d
in
to
th
e
s
y
s
te
m
,
s
e
r
vi
ng
m
ul
ti
pl
e
f
unc
ti
ons
s
uc
h
as
in
it
ia
ti
ng
da
ta
c
ol
le
c
ti
on,
c
a
li
br
a
ti
ng
th
e
s
ys
te
m
,
or
r
e
s
e
tt
in
g
th
e
de
vi
c
e
,
w
it
hout
ne
c
e
s
s
it
a
ti
ng
a
ddi
ti
ona
l
s
w
it
c
he
s
.
A
ddi
ti
ona
ll
y,
a
r
oc
ke
t
s
w
it
c
h
w
it
h
a
s
in
gl
e
-
pol
e
s
in
gl
e
-
th
r
ow
(
S
P
S
T
)
c
onf
ig
ur
a
ti
on
is
in
c
lu
de
d.
T
hi
s
s
w
it
c
h
pr
ovi
de
s
a
r
e
li
a
bl
e
a
nd
s
im
pl
e
m
e
a
n
s
of
pow
e
r
in
g
th
e
s
ys
te
m
on
a
nd
of
f
.
I
ts
s
tr
a
ig
ht
f
or
w
a
r
d
ope
r
a
ti
on
e
nha
nc
e
s
th
e
u
s
e
r
in
te
r
f
a
c
e
by
pr
ovi
di
ng
a
c
le
a
r
,
ta
c
ti
le
m
e
th
o
d
f
or
c
ont
r
ol
li
ng
th
e
pow
e
r
s
ta
te
of
th
e
de
vi
c
e
,
th
e
r
e
by
im
pr
ovi
ng
ove
r
a
ll
us
a
bi
li
ty
a
nd
u
s
e
r
e
xp
e
r
ie
nc
e
.
To
c
om
pl
e
te
th
e
s
y
s
te
m
,
a
c
us
to
m
iz
e
d
3D
pr
in
te
d
e
nc
lo
s
ur
e
w
it
h
a
s
la
nt
e
d,
w
a
v
e
f
ul
m
ode
l
is
us
e
d
f
or
a
s
s
e
m
bl
y.
T
hi
s
e
n
c
lo
s
ur
e
is
d
e
s
ig
ne
d
w
it
h
in
put
s
a
nd
out
put
s
on
bot
h
th
e
le
f
t
a
nd
r
ig
ht
s
id
e
s
,
a
ll
ow
in
g
f
or
ve
r
s
a
ti
le
pos
it
io
ni
ng
on
a
ny
s
ur
f
a
c
e
.
T
he
s
la
nt
e
d
d
e
s
ig
n
m
in
im
iz
e
s
gl
a
r
e
on
th
e
L
C
D
di
s
pl
a
y,
e
ns
ur
in
g
opt
im
a
l
vi
s
ib
il
it
y
in
va
r
io
us
li
ght
in
g
c
ondi
ti
ons
.
T
hi
s
th
oughtf
ul
e
nc
lo
s
ur
e
de
s
ig
n
e
nha
nc
e
s
th
e
us
a
bi
li
ty
a
nd
a
e
s
th
e
t
ic
a
ppe
a
l
of
th
e
s
ys
te
m
w
hi
le
m
a
in
ta
in
in
g
its
f
unc
ti
ona
li
ty
in
di
ve
r
s
e
e
nvi
r
onm
e
nt
s
.
In
c
onc
lu
s
io
n,
our
Li
-
io
n
ba
tt
e
r
y
c
a
p
a
c
it
y
pr
e
di
c
ti
on
s
ys
t
e
m
c
om
bi
ne
s
s
ophi
s
ti
c
a
te
d
s
e
ns
or
in
te
gr
a
ti
on
w
it
h
a
c
u
s
to
m
-
de
s
ig
ne
d
E
S
P
32
P
C
B
to
de
li
ve
r
a
c
c
ur
a
te
a
nd
r
e
li
a
bl
e
c
a
pa
c
it
y
pr
e
di
c
ti
ons
.
T
he
us
e
of
di
gi
ta
l
s
e
ns
or
s
a
nd
opt
im
iz
e
d
pow
e
r
m
a
na
ge
m
e
nt
e
ns
ur
e
s
da
t
a
in
te
gr
it
y
a
nd
r
obus
t
pe
r
f
or
m
a
nc
e
,
m
a
ki
ng
it
s
ui
ta
bl
e
f
or
va
r
io
us
pr
a
c
ti
c
a
l
a
ppl
ic
a
ti
o
ns
.
T
he
in
te
gr
a
ti
on
of
th
e
I
N
A
219
f
or
c
ur
r
e
nt
a
nd
vol
ta
ge
m
e
a
s
ur
e
m
e
nt
s
,
th
e
D
S
18B
20
f
or
te
m
pe
r
a
tu
r
e
m
oni
to
r
in
g,
a
nd
a
w
e
ll
-
de
s
ig
ne
d
pow
e
r
m
a
na
ge
m
e
nt
s
y
s
te
m
a
ll
c
ont
r
ib
ut
e
to
th
e
s
y
s
te
m
'
s
e
f
f
e
c
ti
ve
ne
s
s
.
T
hi
s
s
y
s
te
m
r
e
pr
e
s
e
nt
s
s
ig
ni
f
ic
a
nt
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8938
I
nt
J
A
r
ti
f
I
nt
e
ll
,
V
ol
. 14, No. 5, O
c
to
be
r
2025
:
3858
-
3868
3862
a
dva
nc
e
m
e
nt
in
ba
tt
e
r
y
m
a
na
ge
m
e
nt
te
c
hnol
ogy,
pr
ovi
di
ng
a
va
lu
a
bl
e
to
ol
f
or
e
xt
e
ndi
ng
th
e
li
f
e
a
n
d
e
f
f
ic
ie
nc
y
of
Li
-
io
n
ba
tt
e
r
ie
s
.
4.
I
N
T
E
G
R
A
T
I
N
G
S
O
F
T
W
A
R
E
M
O
D
E
L
I
N
T
O
H
A
R
D
W
A
R
E
-
C
O
M
P
A
T
I
B
L
E
S
Y
S
T
E
M
F
O
R
E
S
P
3
2
4.1.
M
od
e
l
d
e
s
ig
n
an
d
op
t
im
iz
at
io
n
f
or
E
S
P
32
d
e
p
lo
ym
e
n
t
To
a
c
hi
e
v
e
e
f
f
ic
ie
nt
de
pl
oym
e
nt
of
our
ne
ur
a
l
ne
twor
k
m
ode
l
on
th
e
E
S
P
32
m
ic
r
oc
ont
r
ol
le
r
,
we
m
e
ti
c
ul
ous
ly
de
s
ig
n
e
d
a
li
ght
w
e
ig
ht
a
nd
opt
im
iz
e
d
a
r
c
hi
te
c
t
ur
e
.
T
hi
s
s
e
c
ti
on
de
ta
il
s
th
e
s
tr
uc
tu
r
e
of
our
m
ode
l
.
I
t
a
ls
o e
xpl
a
in
s
t
he
i
nnova
ti
ve
a
ppr
oa
c
h
we
e
m
pl
oye
d
to
ha
ndl
e
in
put
da
ta
,
e
ns
ur
in
g
m
in
im
a
l
m
e
m
or
y
ove
r
he
a
d
a
nd
e
f
f
ic
ie
nt
pr
oc
e
s
s
in
g.
4.2.
M
od
e
l
a
r
c
h
it
e
c
t
u
r
e
T
he
C
N
N
m
ode
l
is
de
s
ig
n
e
d
as
f
ol
lo
w
s
:
−
I
nput
la
ye
r
:
c
om
pr
is
in
g
8
ne
ur
ons
w
it
h
'
r
e
lu
'
a
c
ti
va
ti
on
f
unc
ti
on
to
pr
oc
e
s
s
th
e
in
put
f
e
a
tu
r
e
s
.
−
H
id
de
n
la
ye
r
1:
8
ne
ur
ons
w
it
h
'
r
e
lu
'
a
c
ti
va
ti
on
f
or
in
it
ia
l
f
e
a
tu
r
e
e
xt
r
a
c
ti
on.
−
H
id
de
n
la
ye
r
2:
4
ne
ur
ons
w
it
h
'
r
e
lu
'
a
c
ti
va
ti
on
f
or
f
ur
th
e
r
f
e
a
tu
r
e
r
e
f
in
e
m
e
nt
.
−
O
ut
put
la
ye
r
:
a
s
in
gl
e
ne
ur
on
to
out
put
th
e
pr
e
di
c
te
d
ba
tt
e
r
y
c
a
pa
c
it
y.
4.3.
H
an
d
li
n
g
in
p
u
t
d
a
t
a
A
ke
y
a
s
pe
c
t
of
our
m
ode
l
is
its
in
put
da
ta
ha
ndl
in
g
s
tr
a
te
gy.
T
ypi
c
a
ll
y,
we
ha
ve
10
s
a
m
pl
e
s
of
two
pa
r
a
m
e
te
r
s
:
vol
ta
ge
a
nd
c
ur
r
e
nt
.
I
ns
te
a
d
of
f
e
e
di
ng
th
e
s
e
s
a
m
p
le
s
s
e
pa
r
a
te
ly
,
w
hi
c
h
w
oul
d
in
c
r
e
a
s
e
m
e
m
or
y
us
a
ge
a
nd
c
om
pl
e
xi
ty
,
we
tr
a
ns
f
or
m
e
d
th
e
in
put
da
ta
in
to
a
one
-
di
m
e
ns
io
na
l
a
r
r
a
y
of
20
va
lu
e
s
.
T
he
tr
a
ns
f
or
m
a
ti
on
is
done
as
f
ol
lo
w
s
:
−
T
he
f
ir
s
t
e
le
m
e
nt
of
th
e
a
r
r
a
y
is
th
e
f
ir
s
t
vol
ta
ge
va
lu
e
.
−
T
he
s
e
c
ond
e
le
m
e
nt
is
th
e
c
or
r
e
s
ponding
c
ur
r
e
nt
va
lu
e
.
−
T
hi
s
pa
tt
e
r
n
c
ont
in
ue
s
,
a
lt
e
r
na
ti
ng
be
twe
e
n
vol
ta
ge
a
nd
c
ur
r
e
nt
va
lu
e
s
f
or
each
s
a
m
pl
e
.
T
hi
s
m
e
th
od
of
f
e
r
s
s
e
v
e
r
a
l
a
dva
nt
a
ge
s
:
−
R
e
duc
e
d
m
e
m
or
y
ove
r
he
a
d
:
by
c
onde
n
s
in
g
th
e
in
put
da
t
a
in
to
a
s
in
gl
e
-
di
m
e
ns
io
na
l
a
r
r
a
y,
we
s
ig
ni
f
ic
a
nt
ly
r
e
duc
e
th
e
m
e
m
or
y
r
e
qui
r
e
d
to
s
to
r
e
a
nd
pr
oc
e
s
s
th
e
da
ta
.
T
hi
s
is
c
r
uc
ia
l
f
or
r
unni
n
g
m
ode
ls
on
r
e
s
our
c
e
-
c
ons
tr
a
in
e
d
d
e
vi
c
e
s
li
ke
th
e
E
S
P
32.
−
E
f
f
ic
ie
nt
pr
oc
e
s
s
in
g
:
th
e
s
im
pl
if
ie
d
in
put
f
o
r
m
a
t
a
ll
ow
s
th
e
m
ode
l
to
pr
oc
e
s
s
da
ta
m
or
e
e
f
f
ic
ie
nt
ly
,
le
a
di
ng
to
f
a
s
te
r
in
f
e
r
e
nc
e
ti
m
e
s
.
T
hi
s
is
pa
r
ti
c
ul
a
r
ly
be
ne
f
ic
ia
l
f
or
r
e
a
l
-
time
a
ppl
ic
a
ti
ons
w
he
r
e
qui
c
k
pr
e
di
c
ti
ons
a
r
e
e
s
s
e
nt
ia
l.
−
S
tr
e
a
m
li
ne
d
da
ta
ha
ndl
in
g
:
th
e
a
lt
e
r
na
ti
ng
pa
tt
e
r
n
of
vol
ta
ge
a
nd
c
ur
r
e
nt
va
lu
e
s
e
ns
ur
e
s
th
a
t
th
e
m
ode
l
r
e
c
e
iv
e
s
a
ba
la
nc
e
d
a
nd
c
ont
in
uous
f
lo
w
of
in
f
or
m
a
ti
on,
e
nha
nc
in
g
its
a
bi
li
ty
to
le
a
r
n
a
nd
m
a
ke
a
c
c
ur
a
te
pr
e
di
c
ti
ons
.
−
S
im
pl
if
ie
d
da
ta
m
a
na
ge
m
e
nt
:
w
it
hout
th
is
m
e
th
od,
m
a
na
gi
ng
two
que
ue
-
li
ke
da
ta
s
tr
uc
tu
r
e
s
w
oul
d
be
ne
c
e
s
s
a
r
y.
E
a
c
h
que
ue
w
oul
d
ha
ndl
e
vol
ta
ge
a
nd
c
ur
r
e
nt
va
lu
e
s
s
e
pa
r
a
te
ly
,
r
e
qui
r
in
g
a
c
om
pl
e
x
s
ys
te
m
w
he
r
e
ne
w
va
lu
e
s
a
r
e
a
ppe
nde
d
to
th
e
e
nd,
a
nd
va
lu
e
s
at
th
e
ot
he
r
e
nd
a
r
e
popp
e
d
out
.
T
hi
s
w
oul
d
in
vol
ve
m
ovi
ng
a
ll
va
lu
e
s
in
bot
h
a
r
r
a
ys
s
e
pa
r
a
te
ly
,
le
a
di
ng
to
a
ddi
ti
ona
l
pr
oc
e
s
s
in
g
ove
r
he
a
d
a
nd
in
c
r
e
a
s
e
d
c
om
pl
e
xi
ty
.
4.4.
D
e
p
lo
ym
e
n
t
on
E
S
P
32
T
he
f
in
a
l
s
te
p
in
vol
ve
d
is
c
onve
r
ti
ng
th
e
tr
a
in
e
d
m
ode
l
in
to
a
f
or
m
a
t
di
r
e
c
tl
y
c
om
pa
ti
bl
e
w
it
h
th
e
E
S
P
32.
N
ot
a
bl
y,
in
s
te
a
d
of
c
onve
r
ti
ng
th
e
m
ode
l
to
T
e
ns
or
F
lo
w
L
it
e
,
we
to
ok
a
dva
nt
a
ge
of
th
e
m
ode
l'
s
s
m
a
ll
s
iz
e
a
nd
di
r
e
c
tl
y
c
onve
r
te
d
it
in
to
a
C
he
a
de
r
f
il
e
,
c
ont
a
in
in
g
th
e
m
ode
l
as
a
c
ha
r
a
r
r
a
y.
T
hi
s
a
ppr
oa
c
h
s
im
pl
if
ie
s
de
pl
oym
e
nt
a
nd
in
te
gr
a
ti
on,
a
ll
ow
in
g
f
or
e
f
f
ic
i
e
nt
r
e
a
l
-
time
in
f
e
r
e
nc
e
on
th
e
E
S
P
32.
By
m
e
ti
c
ul
ous
ly
de
s
ig
ni
ng
our
m
ode
l
a
r
c
hi
te
c
tu
r
e
a
nd
opt
im
iz
in
g
th
e
da
ta
ha
ndl
in
g
pr
oc
e
s
s
,
we
e
n
s
ur
e
d
th
a
t
th
e
m
ode
l
is
not
onl
y
c
om
pa
ti
bl
e
w
it
h
th
e
E
S
P
32
but
a
ls
o
pe
r
f
o
r
m
s
e
f
f
ic
ie
nt
ly
in
r
e
a
l
-
time
a
ppl
ic
a
ti
ons
.
T
hi
s
in
te
gr
a
ti
on
hi
ghl
ig
ht
s
th
e
pot
e
nt
ia
l
of
c
om
bi
ni
ng
s
of
twa
r
e
in
n
ova
ti
ons
w
it
h
ha
r
dw
a
r
e
c
a
pa
bi
li
ti
e
s
to
c
r
e
a
te
r
obus
t
a
nd
e
f
f
e
c
ti
ve
s
ol
ut
io
ns
f
o
r
ba
tt
e
r
y
m
a
na
ge
m
e
nt
s
ys
te
m
s
.
A
lt
hough
we
in
it
ia
ll
y
tr
a
in
e
d
a
tr
a
di
ti
ona
l
C
N
N
m
ode
l,
we
opt
im
iz
e
d
a
nd
de
pl
oye
d
it
in
a
w
a
y
th
a
t
a
d
he
r
e
s
to
th
e
pr
in
c
ip
le
s
of
T
in
yM
L
.
H
e
r
e
is
a
de
ta
il
e
d
e
xpl
a
na
ti
on
of
th
e
s
te
p
s
we
f
ol
lo
w
e
d:
in
it
ia
ll
y
,
we
tr
a
in
e
d
an
or
di
na
r
y
C
N
N
m
ode
l
us
in
g
s
ta
nd
a
r
d
m
a
c
hi
ne
-
le
a
r
ni
ng
te
c
hni
que
s
.
G
iv
e
n
th
e
c
ons
tr
a
in
ts
of
th
e
E
S
P
32
pl
a
tf
or
m
(
lo
w
p
r
oc
e
s
s
in
g
pow
e
r
,
li
m
it
e
d
m
e
m
or
y)
,
we
f
oc
us
e
d
on
r
e
duc
in
g
th
e
s
iz
e
of
th
e
m
ode
l
to
m
a
ke
it
f
e
a
s
ib
le
f
or
de
pl
oym
e
nt
on
s
uc
h
e
m
be
dde
d
s
y
s
te
m
s
.
T
he
m
od
el
w
a
s
opt
im
iz
e
d
to
be
as
c
o
m
pa
c
t
as
po
s
s
ib
le
,
w
it
h
a
f
oc
u
s
on
r
e
ta
in
in
g
a
c
c
ur
a
c
y
w
hi
le
e
ns
ur
in
g
it
c
oul
d
r
un
e
f
f
ic
ie
nt
ly
w
it
hi
n
th
e
r
e
s
our
c
e
limits
of
th
e
E
S
P
32
m
odul
e
.
A
f
te
r
tr
a
in
in
g,
we
us
e
d
th
e
tf
_por
te
r
li
br
a
r
y
f
r
om
th
e
‘
e
ve
r
yw
he
r
e
m
l’
pa
c
ka
ge
to
c
onve
r
t
th
e
opt
im
iz
e
d
C
N
N
m
ode
l
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
r
ti
f
I
nt
e
ll
I
S
S
N
:
2252
-
8938
O
pt
imi
z
in
g batt
e
r
y
l
if
e
:
a
T
in
y
M
L
appr
oac
h t
o l
it
hi
um
-
io
n batt
e
r
y
he
al
th
…
(
K
am
a
r
aj
L
al
it
ha N
is
ha
)
3863
in
to
C
+
+
c
ode
.
T
hi
s
s
te
p
w
a
s
c
r
uc
ia
l
f
or
m
a
ki
ng
th
e
m
ode
l
c
om
pa
ti
bl
e
w
it
h
e
m
be
dde
d
pl
a
tf
or
m
s
li
ke
th
e
E
S
P
32.
T
he
out
put
of
th
is
c
onve
r
s
io
n
w
a
s
a
.h
he
a
de
r
f
il
e
,
w
hi
c
h
c
ont
a
in
e
d
th
e
e
nt
ir
e
m
ode
l
s
tr
uc
tu
r
e
a
nd
w
e
ig
ht
s
in
a
c
om
pa
c
t,
e
f
f
ic
ie
nt
f
or
m
a
t.
T
hi
s
a
ll
ow
e
d
us
to
in
te
gr
a
te
th
e
m
ode
l
di
r
e
c
tl
y
in
to
an
e
m
be
dde
d
e
nvi
r
onm
e
nt
.
T
he
c
onv
e
r
te
d
.h
f
il
e
,
w
hi
c
h
now
c
ont
a
in
e
d
th
e
C
N
N
m
ode
l,
w
a
s
th
e
n
u
s
e
d
in
c
onj
unc
ti
on
w
it
h
th
e
E
lo
que
nt
T
in
y
M
L
li
br
a
r
y.
T
hi
s
li
br
a
r
y
is
s
pe
c
if
ic
a
ll
y
de
s
ig
ne
d
to
e
n
a
bl
e
th
e
r
unni
ng
of
m
a
c
hi
n
e
le
a
r
ni
ng
m
ode
ls
on
r
e
s
our
c
e
-
c
ons
tr
a
in
e
d
de
vi
c
e
s
s
uc
h
as
th
e
E
S
P
32.
E
lo
que
nt
T
in
yM
L
f
a
c
il
it
a
te
s
r
unni
ng
de
e
p
le
a
r
ni
ng
m
ode
ls
di
r
e
c
tl
y
on
m
ic
r
oc
ont
r
ol
le
r
s
w
it
hout
r
e
ly
in
g
on
c
lo
ud
-
ba
s
e
d
c
om
put
a
ti
on,
m
a
ki
ng
it
a
pr
im
e
e
xa
m
pl
e
of
T
in
yM
L
.
By
le
ve
r
a
gi
ng
th
is
li
b
r
a
r
y,
we
w
e
r
e
a
bl
e
to
de
pl
oy
our
m
ode
l
e
f
f
ic
ie
nt
ly
on
th
e
E
S
P
32
-
ba
s
e
d
s
y
s
te
m
,
a
c
hi
e
vi
ng
r
e
a
l
-
time
pr
e
di
c
ti
ons
f
or
ba
tt
e
r
y
R
U
L
e
s
ti
m
a
ti
on.
T
he
e
m
be
dd
e
d
pl
a
tf
or
m
f
or
r
e
a
l
-
time
R
U
L
f
or
e
c
a
s
ts
is
th
e
m
i
c
r
oc
ont
r
ol
le
r
E
S
P
32.
To
ve
r
if
y
t
he
de
pl
oye
d
m
ode
l'
s
f
unc
ti
ona
li
ty
in
an
a
c
tu
a
l
s
e
tt
in
g,
it
is
put
to
th
e
te
s
t
in
a
va
r
ie
ty
of
s
c
e
na
r
io
s
(
F
ig
ur
e
2)
.
A
s
s
ur
in
g
s
m
oot
h
in
te
gr
a
ti
on,
e
va
lu
a
ti
ng
c
om
put
a
ti
ona
l
e
f
f
e
c
ti
ve
ne
s
s
,
a
nd
v
e
r
if
yi
ng
th
e
pr
e
c
is
io
n
of
f
or
e
c
a
s
ts
on
th
e
m
ic
r
oc
ont
r
ol
le
r
a
r
e
a
ll
in
c
lu
de
d
in
th
is
bl
oc
k.
F
ig
ur
e
2.
B
lo
c
k
s
c
he
m
a
ti
c
il
lu
s
tr
a
ti
ng
th
e
s
ugg
e
s
te
d
a
ppr
oa
c
h
T
he
pr
e
di
c
ti
ve
m
a
in
te
n
a
nc
e
a
lg
or
it
hm
ha
s
ta
ke
n
a
bi
g
s
tr
id
e
to
w
a
r
d
r
e
a
l
-
w
or
ld
us
e
w
it
h
its
de
pl
oym
e
nt
on
a
m
ic
r
oc
ont
r
ol
le
r
.
M
a
ki
ng
ti
m
e
ly
a
nd
in
f
or
m
e
d
m
a
in
te
na
nc
e
d
e
c
is
io
ns
de
pe
nd
s
on
th
e
m
ic
r
oc
ont
r
ol
le
r
'
s
a
lg
or
it
hm
'
s
c
a
pa
c
it
y
to
f
unc
ti
on
e
f
f
e
c
ti
ve
ly
in
r
e
a
l
-
ti
m
e
,
w
hi
c
h
is
va
li
da
te
d
by
te
s
ti
ng
it
on
th
e
de
vi
c
e
.
T
h
e
a
lg
or
it
hm
can
be
e
xe
c
ut
e
d
di
r
e
c
tl
y
on
th
e
m
ic
r
oc
ont
r
ol
le
r
,
a
ll
ow
in
g
m
a
in
te
na
nc
e
jo
bs
to
be
c
om
pl
e
te
d
in
de
pe
nde
nt
ly
a
nd
w
it
hout
th
e
ne
e
d
f
or
out
s
id
e
pr
oc
e
s
s
in
g
pow
e
r
.
T
hi
s
m
a
ke
s
th
e
a
lg
or
it
hm
m
or
e
us
e
f
ul
a
nd
a
ppl
ic
a
bl
e
in
r
e
a
l
-
w
or
ld
s
it
ua
ti
on
s
w
he
r
e
pr
om
pt
m
a
in
te
na
nc
e
r
e
qui
r
e
m
e
nt
s
r
e
pl
ie
s
a
r
e
c
r
uc
ia
l.
F
ur
th
e
r
m
or
e
,
th
e
a
lg
or
it
hm
'
s
i
m
pl
e
m
e
nt
a
ti
on
on
a
m
ic
r
oc
ont
r
o
ll
e
r
le
s
s
e
ns
th
e
r
e
qui
r
e
m
e
nt
f
or
c
ons
ta
nt
da
ta
tr
a
ns
m
is
s
io
n
a
nd
lo
w
e
r
s
la
te
nc
y,
m
a
ki
ng
it
a
ppr
opr
ia
te
f
or
s
it
u
a
ti
ons
w
it
h
li
m
it
e
d
r
e
s
our
c
e
s
or
th
os
e
th
a
t
a
r
e
r
e
m
ot
e
.
O
ve
r
a
ll
,
m
ic
r
oc
ont
r
ol
le
r
te
s
ti
ng
va
li
da
te
s
th
a
t
th
e
a
lg
or
it
hm
is
r
e
a
dy
to
be
im
pl
e
m
e
nt
e
d
in
r
e
a
l
-
w
or
ld
m
a
in
te
na
nc
e
a
ppl
ic
a
ti
on
s
,
ope
ni
ng
th
e
door
to
e
nha
nc
e
d
a
s
s
e
t
d
e
pe
nda
bi
li
ty
a
nd
m
a
na
ge
m
e
nt
.
4.5.
M
e
m
or
y
f
oot
p
r
in
t
of
t
h
e
p
r
op
os
e
d
m
od
e
l
T
he
s
iz
e
of
th
e
.h
f
il
e
ge
ne
r
a
te
d
f
or
our
m
ode
l
is
17.7
KB
(
18,213
byt
e
s
)
.
T
he
S
ke
tc
h
us
e
d
419
,
077
byt
e
s
(
31%
)
of
pr
ogr
a
m
s
to
r
a
ge
s
pa
c
e
.
T
he
m
a
xi
m
um
c
a
pa
c
it
y
of
pr
ogr
a
m
s
to
r
a
ge
s
pa
c
e
is
1
,
310
,
720
byt
e
s
.
G
lo
ba
l
va
r
ia
bl
e
s
u
s
e
d
35
,
660
byt
e
s
(
10%
)
of
dyna
m
ic
m
e
m
or
y,
l
e
a
vi
ng
292
,
020
byt
e
s
f
or
lo
c
a
l
va
r
ia
bl
e
s
.
T
he
m
a
xi
m
um
c
a
pa
c
it
y
is
327
,
680
byt
e
s
.
D
ur
i
ng
th
e
c
om
pi
la
ti
on
of
th
e
A
r
dui
no
s
ke
tc
h,
th
e
m
e
m
or
y
us
a
ge
s
ta
ti
s
ti
c
s
w
e
r
e
as
f
ol
lo
w
s
:
−
P
r
ogr
a
m
s
to
r
a
ge
s
pa
c
e
(
f
la
s
h
m
e
m
or
y
):
th
e
s
ke
tc
h
us
e
s
419,0
77
byt
e
s
,
w
hi
c
h
a
c
c
ount
s
f
or
31%
of
th
e
a
va
il
a
bl
e
pr
ogr
a
m
s
to
r
a
g
e
s
p
a
c
e
(
m
a
xi
m
um
:
1,310,720
byt
e
s
)
.
T
hi
s
m
e
m
or
y
is
ut
il
iz
e
d
f
or
s
to
r
in
g
th
e
c
om
pi
le
d
c
ode
a
nd
s
ta
ti
c
c
ont
e
nt
s
uc
h
as
c
ons
ta
nt
s
a
nd
li
br
a
r
ie
s
.
W
it
h
69%
of
f
la
s
h
m
e
m
or
y
s
ti
ll
a
va
il
a
bl
e
,
th
e
pr
ogr
a
m
is
hi
ghl
y
m
e
m
or
y
-
e
f
f
ic
ie
nt
,
a
ll
ow
in
g
f
or
f
ut
ur
e
s
c
a
la
bi
li
ty
a
nd
th
e
in
te
gr
a
ti
on
of
a
ddi
ti
ona
l
f
e
a
tu
r
e
s
.
−
D
yna
m
ic
m
e
m
or
y
(
S
R
A
M
)
:
th
e
s
ke
tc
h
ut
il
iz
e
s
35,660
byt
e
s
,
w
hi
c
h
is
10%
of
th
e
to
ta
l
dyna
m
ic
m
e
m
or
y
a
va
il
a
bl
e
(
m
a
xi
m
um
:
327,680
byt
e
s
)
.
D
yna
m
ic
m
e
m
or
y
is
us
e
d
f
or
gl
oba
l
va
r
ia
bl
e
s
,
s
ta
ti
c
va
r
ia
bl
e
s
,
a
nd
dyna
m
ic
a
ll
oc
a
ti
ons
dur
in
g
r
unt
im
e
.
292,020
byt
e
s
a
r
e
f
r
e
e
f
or
lo
c
a
l
va
r
ia
bl
e
s
,
s
ta
c
k,
a
nd
r
unt
im
e
ope
r
a
ti
ons
.
H
e
nc
e
,
th
e
lo
w
dyna
m
ic
m
e
m
or
y
us
a
ge
e
ns
ur
e
s
s
ta
bl
e
r
unt
im
e
pe
r
f
or
m
a
nc
e
w
it
h
no
r
is
k
of
s
ta
c
k/
he
a
p
c
ol
li
s
io
n
s
in
th
e
c
ur
r
e
nt
de
s
ig
n.
It
is
e
vi
de
nt
f
r
om
th
e
a
bove
da
ta
th
a
t
th
e
c
om
pi
le
d
s
ke
tc
h
de
m
ons
tr
a
te
s
e
f
f
ic
ie
nt
m
e
m
or
y
ut
il
iz
a
ti
on.
F
la
s
h
m
e
m
or
y
us
a
ge
is
w
e
ll
w
it
hi
n
th
e
li
m
it
s
,
e
ns
ur
in
g
r
oom
f
or
f
ut
ur
e
e
nha
nc
e
m
e
nt
s
or
li
br
a
r
y
a
ddi
ti
ons
.
S
R
A
M
ut
il
iz
a
ti
on
is
m
in
im
a
l,
pr
ovi
di
ng
a
de
qua
t
e
s
pa
c
e
f
or
r
unt
im
e
ope
r
a
ti
ons
,
lo
c
a
l
va
r
ia
bl
e
s
,
a
nd
s
ta
c
k
gr
ow
th
.
T
he
s
e
r
e
s
ul
ts
c
onf
ir
m
th
a
t
th
e
s
ke
tc
h
is
opt
im
iz
e
d
f
or
bot
h
s
to
r
a
ge
a
nd
r
unt
im
e
pe
r
f
or
m
a
nc
e
,
m
a
ki
ng
it
r
e
li
a
bl
e
a
nd
s
c
a
la
bl
e
f
or
de
pl
oym
e
nt
on
th
e
ta
r
ge
t
A
r
dui
no
-
c
om
pa
ti
bl
e
E
S
P
32
s
ys
te
m
.
5.
R
E
S
U
L
T
S
AND
D
I
S
C
U
S
S
I
O
N
R
e
s
ul
ts
f
r
om
th
e
a
pp
li
c
a
t
io
n
of
T
i
nyM
L
f
o
r
Li
-
io
n
ba
tt
e
r
y
m
a
na
ge
m
e
nt
c
a
pa
c
i
ty
p
r
e
di
c
ti
on
on
E
S
P
32
a
r
e
e
nc
ou
r
a
g
in
g
a
nd
th
e
de
ve
l
ope
d
ha
r
dw
a
r
e
m
o
d
e
l
is
de
pi
c
te
d
in
F
i
gu
r
e
3.
O
u
r
3D
-
p
r
i
nt
e
d
D
at
a
p
r
e
-
p
r
oc
e
s
s
i
n
g
[
N
A
S
A
d
at
as
e
t
]
C
N
N
m
od
e
l
T
r
ai
n
i
n
g
M
od
e
l
e
val
u
at
i
on
D
e
p
l
oym
e
n
t
i
n
h
ar
d
w
ar
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8938
I
nt
J
A
r
ti
f
I
nt
e
ll
,
V
ol
. 14, No. 5, O
c
to
be
r
2025
:
3858
-
3868
3864
e
nc
l
os
u
r
e
a
nd
c
us
to
m
i
z
e
d
P
C
B
a
ll
ow
e
d
us
to
de
s
i
gn
a
s
m
a
l
l,
e
f
f
e
c
ti
ve
r
e
a
l
-
t
im
e
c
a
pa
c
it
y
f
o
r
e
c
a
s
t
s
ys
te
m
.
T
he
s
ta
r
t
up
s
te
p
be
ga
n
w
h
e
n
t
he
s
ys
te
m
w
a
s
p
ow
e
r
e
d
on
a
nd
a
te
s
t
ba
t
te
r
y
a
nd
a
12V
bu
lb
w
e
r
e
c
on
ne
c
te
d
as
a
l
oa
d
.
T
he
m
a
c
hi
ne
c
o
ll
e
c
te
d
te
n
v
ol
ta
g
e
a
nd
c
ur
r
e
nt
r
e
a
d
in
gs
e
ve
r
y
te
n
s
e
c
onds
th
r
ou
gh
ou
t
th
is
pe
r
io
d.
It
di
s
pl
a
ye
d
t
he
pr
e
vi
ous
c
a
p
a
c
i
ty
it
ha
d
e
s
t
im
a
te
d
a
nd
s
t
a
r
te
d
p
r
e
di
c
ti
ng
t
he
ba
t
te
r
y
c
a
pa
c
i
ty
s
im
u
lt
a
ne
ous
l
y.
It
w
il
l
be
g
in
to
p
r
o
vi
d
e
th
e
li
ve
c
a
pa
c
it
y
p
r
e
di
c
ti
on
u
ti
li
z
in
g
r
e
a
l
-
t
im
e
d
a
ta
s
h
o
r
t
ly
a
f
te
r
th
e
in
it
ia
li
z
in
g
p
ha
s
e
,
as
s
e
e
n
in
F
ig
ur
e
4.
T
he
e
v
a
lu
a
ti
on
of
our
Li
-
io
n
ba
tt
e
r
y
m
a
na
ge
m
e
nt
c
a
p
a
c
it
y
pr
e
di
c
ti
on
m
ode
l
us
in
g
T
in
y
M
L
on
E
S
P
32
yi
e
ld
e
d
pr
om
is
in
g
r
e
s
ul
ts
.
We
e
va
lu
a
te
d
our
m
ode
l
on
th
e
tr
a
in
in
g,
va
li
da
ti
on,
a
nd
te
s
t
s
e
ts
.
T
he
pe
r
f
or
m
a
nc
e
m
e
tr
ic
s
f
or
each
da
ta
s
e
t
a
r
e
s
um
m
a
r
iz
e
d
in
T
a
bl
e
1.
−
T
r
a
in
in
g
s
e
t:
w
it
h
m
e
a
n
s
qua
r
e
d
e
r
r
or
(
M
S
E
)
of
0.0118,
M
A
E
of
0.0874,
m
e
a
n
a
bs
ol
ut
e
pe
r
c
e
nt
a
ge
e
r
r
or
(
M
A
P
E
)
of
8.2735%
,
a
nd
R
M
S
E
of
0.1088,
th
e
m
od
e
l
pr
oduc
e
d
a
lo
s
s
of
0.0059.
T
he
s
e
num
be
r
s
s
how
th
a
t
th
e
m
ode
l
ha
s
a
good
f
it
,
lo
w
e
r
r
or
r
a
te
s
,
a
nd
hi
gh
pr
e
di
c
ti
on
a
c
c
ur
a
c
y
to
th
e
tr
a
in
in
g
s
e
t.
−
V
a
li
da
ti
on
s
e
t:
w
it
h
lo
s
s
of
0.0060,
M
S
E
of
0.0119,
M
A
E
of
0.0880,
M
A
P
E
of
8.3724%
,
a
nd
R
M
S
E
of
0.1092,
th
e
va
li
da
ti
on
s
e
t'
s
m
e
tr
ic
s
a
r
e
e
xt
r
e
m
e
ly
s
im
il
a
r
to
th
os
e
of
th
e
tr
a
in
in
g
s
e
t.
T
he
m
ode
l
pe
r
f
or
m
s
w
e
ll
w
it
hout
not
ic
e
a
bl
y
ove
r
f
it
ti
ng,
s
how
in
g
th
a
t
it
g
e
ne
r
a
li
z
e
s
w
e
ll
to
n
e
w
d
a
ta
,
a
c
c
or
di
ng
to
th
e
s
im
il
a
r
it
y
be
twe
e
n
th
e
tr
a
in
in
g
a
nd
va
li
da
ti
on
m
e
a
s
ur
e
s
.
−
T
e
s
t
s
e
t:
th
e
m
ode
l
pr
oduc
e
d
lo
s
s
of
0.0057,
M
S
E
of
0.0114,
M
A
E
of
0.0854,
M
A
P
E
of
7.9660%
,
a
nd
R
M
S
E
of
0.1068
on
th
e
t
e
s
t
s
e
t.
T
he
s
e
f
in
di
ngs
va
li
da
te
th
e
m
ode
l'
s
r
obus
tn
e
s
s
a
nd
de
pe
nda
bi
li
ty
f
or
r
e
a
l
-
w
or
ld
a
ppl
ic
a
ti
ons
by
s
how
in
g
th
a
t
it
r
e
ta
in
s
its
a
c
c
ur
a
c
y
a
nd
lo
w
e
r
r
or
r
a
te
s
on
e
nt
ir
e
ly
f
r
e
s
h
da
ta
.
F
ig
ur
e
3.
H
a
r
dw
a
r
e
m
odul
e
w
it
h
E
S
P
32
F
ig
ur
e
4.
C
a
pa
c
it
y
pr
e
di
c
ti
on
T
a
bl
e
1.
E
va
lu
a
ti
on
m
e
tr
ic
s
c
om
pa
r
is
on
D
a
t
a
s
e
t
L
os
s
M
S
E
M
A
E
M
A
P
E
R
M
S
E
T
r
a
i
ni
ng
0.0059
0.0118
0.0874
8.2735
0.1088
V
a
l
i
da
t
i
on
0.0060
0.0119
0.0880
8.3724
0.1092
T
e
s
t
0.0057
0.0114
0.0854
7.9660
0.1068
F
ig
ur
e
5
e
lu
c
id
a
te
s
th
e
tr
a
in
in
g
a
nd
va
li
da
ti
on
lo
s
s
th
r
oughout
50
e
poc
hs
.
T
he
pl
ot
s
how
s
th
a
t
w
it
hi
n
th
e
f
ir
s
t
f
e
w
e
poc
hs
,
bot
h
th
e
tr
a
in
in
g
a
nd
v
a
li
da
ti
on
lo
s
s
e
s
dr
op
qui
te
qui
c
kl
y
be
f
or
e
s
ta
bi
li
z
in
g,
in
di
c
a
ti
ng
s
tr
ong
c
onve
r
ge
nc
e
w
it
hout
a
ppr
e
c
ia
bl
e
ove
r
f
it
ti
ng.
T
he
R
M
S
E
f
or
th
e
t
r
a
in
in
g
a
nd
va
li
da
ti
on
s
e
ts
is
di
s
pl
a
ye
d
in
F
ig
ur
e
5.
F
or
bot
h
da
ta
s
e
ts
,
th
e
R
M
S
E
s
te
a
di
ly
dr
ops
th
r
oughout
th
e
f
ir
s
t
f
e
w
e
poc
hs
unt
il
s
ta
bi
li
z
in
g
at
r
oughly
th
e
s
a
m
e
a
m
ount
,
w
hi
c
h
il
lu
s
tr
a
te
s
how
c
ons
is
te
nt
ly
t
he
m
ode
l
r
e
duc
e
s
pr
e
di
c
ti
on
e
r
r
or
s
.
F
ig
ur
e
6
di
s
pl
a
ys
th
e
M
A
E
f
or
th
e
t
r
a
in
in
g
a
nd
va
li
da
ti
on
s
e
ts
.
L
ik
e
th
e
ot
he
r
m
e
a
s
ur
e
s
,
th
e
M
A
E
dr
ops
r
a
pi
dl
y
be
f
or
e
s
ta
yi
ng
s
om
e
w
h
a
t
s
te
a
dy,
in
di
c
a
ti
ng
th
a
t
th
e
m
ode
l
can
s
u
c
c
e
s
s
f
ul
ly
lo
w
e
r
th
e
a
ve
r
a
g
e
s
iz
e
of
e
r
r
or
s
.
T
he
M
S
E
f
or
th
e
tr
a
in
in
g
a
nd
va
li
da
ti
on
da
ta
s
e
ts
is
s
how
n
in
F
i
gur
e
s
7
a
nd
8.
T
he
m
ode
l'
s
e
f
f
e
c
ti
ve
ne
s
s
in
r
e
duc
in
g
pr
e
di
c
ti
on
e
r
r
o
r
s
is
f
u
r
th
e
r
de
m
ons
tr
a
te
d
by
th
e
M
S
E
'
s
qui
c
k
d
r
op
a
nd
s
ubs
e
que
nt
s
ta
bi
li
z
a
ti
on,
w
hi
c
h
s
uppor
ts
th
e
f
in
di
ngs
of
th
e
R
M
S
E
a
nd
M
A
E
pl
ot
s
.
T
he
c
on
s
is
te
n
c
y
of
th
e
m
ode
l'
s
pe
r
f
or
m
a
nc
e
th
r
oughout
th
e
tr
a
in
in
g,
va
li
da
ti
on,
a
nd
te
s
t
s
e
ts
is
in
di
c
a
ti
ve
of
its
s
ta
bi
li
ty
a
nd
c
a
pa
c
it
y
f
or
ge
ne
r
a
li
z
a
ti
on.
T
he
m
ode
l
a
ppe
a
r
s
to
e
s
ti
m
a
te
th
e
Li
-
io
n
ba
tt
e
r
y'
s
c
a
pa
c
it
y
a
c
c
ur
a
te
ly
ba
s
e
d
on
th
e
lo
w
va
lu
e
s
of
M
S
E
,
M
A
E
,
M
A
P
E
,
a
nd
R
M
S
E
.
T
he
de
pl
oye
d
m
ode
l
can
be
us
e
d
to
m
a
na
ge
ba
tt
e
r
ie
s
in
r
e
a
l
-
ti
m
e
,
m
a
ki
ng
it
pos
s
ib
le
to
m
oni
to
r
a
nd
us
e
ba
tt
e
r
y
c
a
pa
c
it
y
pr
ope
r
ly
.
E
ve
n
if
th
e
pe
r
f
or
m
a
nc
e
of
th
e
e
xi
s
ti
ng
m
ode
l
is
a
de
qua
te
,
th
e
r
e
is
s
ti
ll
r
oom
f
or
im
pr
ove
m
e
nt
in
te
r
m
s
of
a
c
c
ur
a
c
y
a
nd
r
obus
tn
e
s
s
.
T
hi
s
m
a
y
in
vol
ve
in
c
or
por
a
ti
ng
a
ddi
ti
ona
l
f
e
a
tu
r
e
s
or
f
in
e
-
tu
ni
ng
th
e
m
ode
l
a
r
c
hi
te
c
tu
r
e
.
T
in
yM
L
'
s
c
onne
c
ti
on
w
it
h
E
S
P
32
a
ll
ow
s
f
or
lo
w
-
pow
e
r
e
dge
c
om
put
in
g
c
a
pa
bi
li
ti
e
s
,
w
hi
c
h
m
a
ke
s
th
e
m
ode
l
a
ppr
opr
ia
te
f
or
de
pl
oym
e
nt
in
c
ont
e
xt
s
w
it
h
li
m
it
e
d
r
e
s
our
c
e
s
.
O
ve
r
a
ll
,
th
e
f
in
di
ngs
s
how
th
a
t
th
e
Li
-
io
n
ba
tt
e
r
y
m
a
na
ge
m
e
nt
c
a
pa
c
it
y
pr
e
di
c
ti
on
s
y
s
te
m
w
a
s
s
uc
c
e
s
s
f
ul
l
y
im
pl
e
m
e
nt
e
d,
w
it
h
pot
e
nt
ia
l
a
dva
nt
a
ge
s
in
a
r
a
nge
of
a
ppl
ic
a
ti
ons
r
e
qui
r
in
g
e
f
f
e
c
ti
ve
ba
tt
e
r
y
m
oni
to
r
in
g
a
nd
us
e
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
r
ti
f
I
nt
e
ll
I
S
S
N
:
2252
-
8938
O
pt
imi
z
in
g batt
e
r
y
l
if
e
:
a
T
in
y
M
L
appr
oac
h t
o l
it
hi
um
-
io
n batt
e
r
y
he
al
th
…
(
K
am
a
r
aj
L
al
it
ha N
is
ha
)
3865
F
ig
ur
e
5
.
T
r
a
in
in
g
a
nd
va
li
da
ti
on
lo
s
s
F
ig
ur
e
6
.
T
r
a
in
in
g
a
nd
va
li
da
ti
on
R
M
S
E
F
ig
ur
e
7
.
T
r
a
in
in
g
a
nd
va
li
da
ti
on
M
A
E
F
ig
ur
e
8
.
T
r
a
in
in
g
a
nd
va
li
da
ti
on
M
S
E
6.
C
O
N
C
L
U
S
I
O
N
In
s
um
m
a
r
y
,
we
ha
ve
a
c
hi
e
ve
d
a
gr
ound
-
br
e
a
ki
ng
r
e
s
ul
t
in
ou
r
que
s
t
to
c
r
e
a
te
a
C
N
N
-
ba
s
e
d
R
U
L
pr
e
di
c
ti
on
m
e
th
od.
O
ur
a
c
hi
e
ve
d
r
e
s
ul
t
s
not
onl
y
m
e
e
t
in
du
s
tr
y
nor
m
s
but
a
ls
o
gr
e
a
tl
y
e
x
c
e
e
d
th
e
m
,
w
hi
c
h
is
a
m
a
jo
r
s
te
p
f
or
w
a
r
d
f
or
pr
e
di
c
ti
ve
m
a
in
te
na
nc
e
.
O
ur
C
N
N
-
ba
s
e
d
m
ode
l
h
a
s
s
how
n
an
unm
a
tc
he
d
de
gr
e
e
of
pr
e
c
is
io
n
a
nd
a
c
c
ur
a
c
y,
tr
a
ns
f
or
m
in
g
th
e
f
ie
ld
of
ba
tt
e
r
y
he
a
lt
h
pr
ognos
ti
c
s
.
It
w
a
s
tr
a
in
e
d
u
s
in
g
th
e
N
A
S
A
ba
tt
e
r
y
da
ta
s
e
t.
T
he
r
e
s
ul
ts
of
th
e
C
N
N
m
ode
l'
s
pa
in
s
ta
ki
ng
c
on
s
tr
uc
ti
on
a
nd
tr
a
in
in
g
s
pe
a
k
lo
udl
y
a
bout
how
w
e
ll
it
can
id
e
nt
if
y
c
om
pl
e
x
s
pa
ti
a
l
pa
tt
e
r
n
s
in
th
e
da
ta
.
T
he
m
ode
l'
s
e
x
c
e
pt
io
na
l
pe
r
f
or
m
a
nc
e
is
de
m
ons
tr
a
te
d
by
its
e
xt
r
a
or
di
na
r
y
m
e
tr
ic
s
,
w
hi
c
h
in
c
lu
de
a
ne
gl
ig
ib
le
lo
s
s
of
0.0063,
a
m
ic
r
os
c
opi
c
M
S
E
of
0.0127,
a
nd
an
in
c
r
e
di
bl
y
lo
w
M
A
E
of
0.0897.
T
he
d
e
pe
nda
bi
l
it
y
a
nd
s
ta
bi
li
ty
of
our
C
N
N
m
ode
l
a
r
e
f
ur
th
e
r
c
onf
ir
m
e
d
by
th
e
M
A
P
E
of
8.2753
%
a
nd
th
e
R
M
S
E
of
0.1129.
In
a
ddi
ti
on
to
its
num
e
r
ic
a
l
pe
r
f
o
r
m
a
nc
e
,
our
C
N
N
m
ode
l
s
ig
ni
f
ie
s
a
r
e
vol
ut
io
n
in
th
e
us
e
of
s
ophi
s
ti
c
a
te
d
ne
ur
a
l
ne
twor
k
a
r
c
hi
te
c
tu
r
e
s
f
or
pr
e
di
c
ti
ve
m
a
in
te
na
nc
e
.
It
ha
s
not
onl
y
f
ul
f
il
le
d
th
e
e
xpe
c
ta
ti
on
s
but
a
ls
o
r
a
is
e
d
th
e
b
a
r
f
or
w
ha
t
is
pos
s
ib
le
in
te
r
m
s
of
e
s
ti
m
a
ti
ng
th
e
ba
tt
e
r
y'
s
r
e
m
a
in
in
g
us
e
f
ul
li
f
e
.
T
he
c
om
bi
na
ti
on
of
s
ta
te
-
of
-
th
e
-
a
r
t
te
c
hnol
ogy
a
nd
dom
a
i
n
knowle
dge
ha
s
pr
oduc
e
d
a
pr
e
di
c
ti
ve
a
lg
or
it
hm
th
a
t
not
onl
y
s
a
ti
s
f
ie
s
but
s
ur
pa
s
s
e
s
th
e
in
dus
tr
y'
s
s
tr
ic
t
r
e
qui
r
e
m
e
nt
s
f
or
a
c
c
ur
a
c
y
a
nd
de
pe
nda
bi
li
ty
.
T
he
a
dve
nt
ur
e
d
oe
s
n'
t
e
nd
he
r
e
as
we
a
im
to
w
a
r
d
th
e
f
ut
ur
e
.
T
hi
s
s
hi
f
t
to
e
dge
c
om
put
in
g
r
e
f
le
c
ts
our
de
di
c
a
ti
on
to
pr
ov
id
in
g
our
a
lg
or
it
hm
w
it
h
bot
h
a
c
c
ur
a
c
y
a
nd
us
a
bi
li
ty
f
or
r
e
a
l
-
w
o
r
ld
a
ppl
ic
a
ti
ons
a
c
r
os
s
a
r
a
nge
of
c
ont
e
xt
s
.
E
s
s
e
nt
ia
ll
y,
our
C
N
N
-
ba
s
e
d
R
U
L
pr
e
di
c
ti
on
s
ys
te
m
is
pr
oof
of
th
e
pot
e
nt
ia
l
th
a
t
r
e
s
ul
ts
f
r
om
c
om
bi
ni
ng
c
r
e
a
ti
vi
ty
a
nd
a
c
c
ur
a
c
y.
P
r
e
di
c
ti
ve
m
a
in
te
na
nc
e
is
in
its
in
f
a
nc
y,
a
nd
our
a
lg
or
it
hm
is
l
e
a
di
ng
th
e
w
a
y,
poi
s
e
d
to
r
a
is
e
th
e
ba
r
f
or
pr
a
c
ti
c
a
li
ty
,
e
f
f
ic
ie
nc
y,
a
nd
a
c
c
ur
a
c
y
in
th
e
f
ie
ld
.
It
is
m
or
e
th
a
n
ju
s
t
a
m
ode
l;
it
is
a
f
o
r
c
e
f
or
r
e
vol
ut
io
na
r
y
c
ha
nge
,
a
s
ig
npos
t
f
or
a
ne
w
a
ge
in
pr
e
di
c
ti
ve
a
na
ly
ti
c
s
,
a
nd
e
vi
de
nc
e
of
th
e
unbounde
d
pot
e
nt
ia
l
of
a
r
ti
f
ic
ia
l
in
te
ll
ig
e
nc
e
to
r
e
vol
ut
io
ni
z
e
m
a
r
ke
ts
a
nd
pus
h
th
e
bounda
r
ie
s
of
knowle
dge
.
F
ut
ur
e
w
or
k
can
e
xpl
or
e
de
pl
oyi
ng
th
e
C
N
N
-
ba
s
e
d
R
U
L
pr
e
di
c
ti
on
m
ode
l
on
e
dge
de
vi
c
e
s
f
or
r
e
a
l
-
time
ba
tt
e
r
y
he
a
lt
h
m
oni
to
r
in
g.
A
ddi
ti
ona
ll
y,
in
te
gr
a
ti
n
g
m
ul
ti
m
oda
l
s
e
ns
or
da
ta
c
oul
d
e
nh
a
nc
e
m
od
e
l
r
obus
tn
e
s
s
a
nd
ge
ne
r
a
li
z
a
bi
li
ty
a
c
r
os
s
di
v
e
r
s
e
b
a
tt
e
r
y
c
he
m
is
tr
ie
s
a
nd
u
s
a
ge
c
ondi
ti
ons
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8938
I
nt
J
A
r
ti
f
I
nt
e
ll
,
V
ol
. 14, No. 5, O
c
to
be
r
2025
:
3858
-
3868
3866
A
C
K
N
O
WL
E
D
G
M
E
N
T
S
T
he
a
ut
hor
s
de
c
la
r
e
t
ha
t
th
e
r
e
a
r
e
no a
c
knowl
e
dgm
e
nt
s
t
o i
nc
lu
de
f
or
t
hi
s
w
or
k.
F
U
N
D
I
N
G
I
N
F
O
R
M
A
T
I
O
N
T
he
a
ut
hor
s
de
c
la
r
e
t
ha
t
no f
undi
ng w
a
s
r
e
c
e
iv
e
d t
o s
uppor
t
th
e
r
e
s
e
a
r
c
h pr
e
s
e
nt
e
d i
n t
hi
s
w
or
k.
A
U
T
H
O
R
C
O
N
T
R
I
B
U
T
I
O
N
S
S
T
A
T
E
M
E
N
T
T
hi
s
jo
ur
na
l
us
e
s
th
e
C
ont
r
ib
ut
or
R
ol
e
s
T
a
xonomy
(
C
R
e
di
T
)
to
r
e
c
ogni
z
e
in
di
vi
dua
l
a
ut
hor
c
ont
r
ib
ut
io
ns
, r
e
duc
e
a
ut
hor
s
hi
p di
s
put
e
s
,
a
nd f
a
c
il
it
a
te
c
ol
la
bo
r
a
ti
on.
N
am
e
o
f
A
u
t
h
or
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
K
a
m
a
r
a
j
L
a
li
th
a
N
is
ha
✓
✓
✓
✓
✓
✓
✓
✓
✓
V
a
s
a
nt
h P
r
a
de
e
p
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
P
a
d
m
a
n
a
b
h
a
n
P
u
t
h
iy
a
v
e
e
d
u
K
r
i
s
h
n
a
n
ku
t
t
y
N
a
ir
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
S
r
e
e
la
ks
hm
i
P
il
la
i
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
M
a
n
i
k
a
n
d
a
n
A
r
u
n
a
c
h
a
l
a
m
✓
✓
✓
✓
✓
✓
✓
✓
✓
R
a
ke
s
h
T
hoppa
e
n
S
ur
e
s
h B
a
bu
✓
✓
✓
✓
✓
✓
C
:
C
onc
e
pt
ua
l
i
z
a
t
i
on
M
:
M
e
t
hodol
ogy
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
da
t
i
on
Fo
:
Fo
r
m
a
l
a
na
l
ys
i
s
I
:
I
nve
s
t
i
ga
t
i
on
R
:
R
e
s
our
c
e
s
D
:
D
a
t
a
C
ur
a
t
i
on
O
:
W
r
i
t
i
ng
-
O
r
i
gi
na
l
D
r
a
f
t
E
:
W
r
i
t
i
ng
-
R
e
vi
e
w
&
E
di
t
i
ng
Vi
:
Vi
s
ua
l
i
z
a
t
i
on
Su
:
Su
pe
r
vi
s
i
on
P
:
P
r
oj
e
c
t
a
dm
i
ni
s
t
r
a
t
i
on
Fu
:
Fu
ndi
ng a
c
qui
s
i
t
i
on
C
O
N
F
L
I
C
T
O
F
I
N
T
E
R
E
S
T
S
T
A
T
E
M
E
N
T
T
he
a
ut
hor
s
de
c
la
r
e
t
ha
t
th
e
y ha
ve
no c
onf
li
c
ts
of
i
nt
e
r
e
s
t,
f
in
a
nc
ia
l
or
non
-
f
in
a
nc
ia
l,
t
ha
t
c
oul
d ha
ve
in
f
lu
e
nc
e
d t
he
w
or
k r
e
por
te
d i
n t
hi
s
pa
pe
r
.
I
N
F
O
R
M
E
D
C
O
N
S
E
N
T
N
ot
a
ppl
ic
a
bl
e
, a
s
t
hi
s
s
tu
dy did not
i
nvol
ve
huma
n pa
r
ti
c
ip
a
nt
s
or
pe
r
s
ona
l
da
ta
.
E
T
H
I
C
A
L
A
P
P
R
O
V
A
L
N
ot
a
ppl
ic
a
bl
e
, a
s
t
hi
s
s
tu
dy did not
i
nvol
ve
huma
n pa
r
ti
c
ip
a
nt
s
or
a
ni
m
a
ls
.
D
A
T
A
A
V
A
I
L
A
B
I
L
I
T
Y
T
he
da
ta
s
uppor
ti
ng
th
e
f
in
di
ngs
of
th
is
s
tu
dy
a
r
e
ope
nl
y
a
va
il
a
bl
e
f
r
om
th
e
N
A
S
A
A
m
e
s
P
r
ognos
ti
c
s
C
e
nt
e
r
of
E
xc
e
ll
e
nc
e
a
t
ht
tp
s
:/
/d
a
ta
.n
a
s
a
.gov/da
t
a
s
e
t/
Li
-
io
n
-
ba
tt
e
r
y
-
a
gi
ng
-
da
ta
s
e
ts
.
R
E
F
E
R
E
N
C
E
S
[
1]
I
.
C
ha
ouf
i
,
O
.
A
bde
l
kh
a
l
e
k,
a
nd
B
.
G
a
s
b
a
oui
,
“
S
t
a
t
e
of
c
ha
r
ge
e
s
t
i
m
a
t
i
on
o
f
l
i
t
hi
um
-
i
on
ba
t
t
e
r
i
e
s
us
i
ng
a
d
a
pt
i
ve
ne
ur
o
f
uz
z
y
i
nf
e
r
e
nc
e
s
ys
t
e
m
,”
I
A
E
S
I
nt
e
r
nat
i
onal
J
our
nal
of
A
r
t
i
f
i
c
i
al
I
nt
e
l
l
i
ge
nc
e
,
vol
.
11,
no.
2,
pp.
473
–
484,
2022
,
doi
:
10.11591/
i
j
a
i
.v11.i
2.pp473
-
484.
[
2]
G
.
C
r
oc
i
oni
,
D
.
P
a
u,
J
.
M
.
D
e
l
or
m
e
,
a
nd
G
.
G
r
uos
s
o,
“
Li
-
i
on
ba
t
t
e
r
i
e
s
p
a
r
a
m
e
t
e
r
e
s
t
i
m
a
t
i
on
w
i
t
h
t
i
ny
ne
ur
a
l
ne
t
w
or
ks
e
m
be
dde
d
on i
nt
e
l
l
i
ge
nt
i
ot
m
i
c
r
oc
ont
r
ol
l
e
r
s
,”
I
E
E
E
A
c
c
e
s
s
, vol
. 8, pp. 122135
–
122146, 2020, doi
:
10.1109/
A
C
C
E
S
S
.2020.3007046.
[
3]
M
.
G
i
or
da
no,
N
.
B
a
um
a
nn,
M
.
C
r
a
bol
u,
R
.
F
i
s
c
he
r
,
G
.
B
e
l
l
us
c
i
,
a
nd
M
.
M
a
gno,
“
D
e
s
i
gn
a
nd
pe
r
f
or
m
a
nc
e
e
va
l
ua
t
i
on
of
a
n
ul
t
r
a
l
ow
-
pow
e
r
s
m
a
r
t
I
oT
de
vi
c
e
w
i
t
h
e
m
be
dde
d
T
i
nyM
L
f
or
a
s
s
e
t
a
c
t
i
vi
t
y
m
oni
t
or
i
ng,”
I
E
E
E
T
r
ans
ac
t
i
ons
on
I
ns
t
r
um
e
nt
at
i
on
and M
e
as
ur
e
m
e
nt
, vol
. 71, 2022, doi
:
10.1109/
T
I
M
.2022.3165816.
[
4]
A
.
G
ha
f
a
r
i
,
“
C
ur
r
e
nt
a
nd
f
ut
u
r
e
pr
os
pe
c
t
s
of
Li
-
i
on
ba
t
t
e
r
i
e
s
:
a
r
e
vi
e
w
,”
J
our
nal
of
N
anoSc
i
e
nc
e
T
e
c
hnol
ogy
,
2023
,
doi
:
10.52319/
j
.na
nos
c
i
t
e
c
.2023.21.
[
5]
C
.
L
i
,
H
.
Z
ha
ng,
P
.
D
i
ng,
S
.
Y
a
ng,
a
nd
Y
.
B
a
i
,
“
D
e
e
p
f
e
a
t
ur
e
e
xt
r
a
c
t
i
on
i
n
l
i
f
e
t
i
m
e
pr
ognos
t
i
c
s
of
l
i
t
h
i
um
-
i
on
ba
t
t
e
r
i
e
s
:
a
dva
nc
e
s
,
c
ha
l
l
e
nge
s
a
nd pe
r
s
pe
c
t
i
ve
s
,
”
R
e
ne
w
abl
e
and Sus
t
ai
nabl
e
E
ne
r
gy
R
e
v
i
e
w
s
, vol
. 184, 2023, doi
:
10.1016/
j
.r
s
e
r
.2023.113576.
[
6]
R
.
K
a
l
l
i
m
a
ni
,
K
.
P
a
i
, P
.
R
a
ghuw
a
ns
hi
,
S
.
I
ye
r
,
a
nd
O
.
L
.
A
.
L
ópe
z
,
“
T
i
nyM
L
:
T
ool
s
,
a
ppl
i
c
a
t
i
ons
,
c
ha
l
l
e
nge
s
,
a
nd
f
ut
ur
e
r
e
s
e
a
r
c
h
di
r
e
c
t
i
ons
,”
M
ul
t
i
m
e
di
a T
ool
s
and A
ppl
i
c
at
i
ons
, vol
. 83, no. 10, pp. 29015
–
29045, 2024, doi
:
10.1007/
s
11042
-
023
-
16740
-
9.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
r
ti
f
I
nt
e
ll
I
S
S
N
:
2252
-
8938
O
pt
imi
z
in
g batt
e
r
y
l
if
e
:
a
T
in
y
M
L
appr
oac
h t
o l
it
hi
um
-
io
n batt
e
r
y
he
al
th
…
(
K
am
a
r
aj
L
al
it
ha N
is
ha
)
3867
[
7]
K
.
A
.
S
e
ve
r
s
on
e
t
al
.
,
“
D
a
t
a
-
dr
i
ve
n
p
r
e
di
c
t
i
on
of
ba
t
t
e
r
y
c
yc
l
e
l
i
f
e
be
f
or
e
c
a
pa
c
i
t
y
de
gr
a
da
t
i
on,”
N
at
ur
e
E
ne
r
gy
,
vol
.
4,
no.
5,
pp. 383
–
391, 2019, doi
:
10.1038/
s
41560
-
019
-
0356
-
8.
[
8]
K
.
D
a
s
a
nd
R
.
K
um
a
r
,
“
E
l
e
c
t
r
i
c
ve
hi
c
l
e
ba
t
t
e
r
y
c
a
pa
c
i
t
y
de
gr
a
da
t
i
on
a
nd
he
a
l
t
h
e
s
t
i
m
a
t
i
on
us
i
ng
m
a
c
hi
ne
-
l
e
a
r
ni
ng
t
e
c
hni
que
s
:
a
r
e
vi
e
w
,”
C
l
e
an E
ne
r
gy
, vol
. 7, no. 6, pp. 1268
–
1281, 2023, doi
:
10.1093/
c
e
/
z
ka
d054.
[
9]
R
.
S
w
a
r
nka
r
,
R
.
H
a
r
i
kr
i
s
hna
n,
P
.
T
ha
kur
,
a
nd
G
.
S
i
ngh,
“
E
l
e
c
t
r
i
c
ve
hi
c
l
e
l
i
t
hi
um
-
i
on
ba
t
t
e
r
y
a
ge
i
ng
a
na
l
ys
i
s
und
e
r
dyna
m
i
c
c
ondi
t
i
on:
a
m
a
c
hi
ne
l
e
a
r
ni
ng
a
ppr
oa
c
h,”
SA
I
E
E
A
f
r
i
c
a
R
e
s
e
ar
c
h
J
our
nal
,
vol
.
114,
no.
1,
pp.
4
–
13,
2023,
doi
:
10.23919/
S
A
I
E
E
.2023.9962788.
[
10]
Z
.
C
he
n,
Y
.
G
a
o,
a
nd
J
.
L
i
a
ng,
“
L
O
P
d
M
:
a
l
ow
-
pow
e
r
on
-
de
vi
c
e
pr
e
di
c
t
i
ve
m
a
i
nt
e
na
nc
e
s
y
s
t
e
m
ba
s
e
d
on
s
e
l
f
-
pow
e
r
e
d
s
e
n
s
i
ng
a
nd T
i
nyM
L
,”
I
E
E
E
T
r
ans
ac
t
i
ons
on I
ns
t
r
um
e
nt
at
i
on and M
e
as
ur
e
m
e
nt
, vol
. 7
2, 2023, doi
:
10.1109/
T
I
M
.2023.3308251.
[
11]
G
.
G
r
uos
s
o
a
nd
G
.
S
.
G
a
j
a
ni
,
“
C
om
pa
r
i
s
on
o
f
m
a
c
hi
ne
l
e
a
r
ni
ng
a
l
gor
i
t
hm
s
f
or
pe
r
f
o
r
m
a
nc
e
e
va
l
ua
t
i
on
of
phot
ovol
t
a
i
c
e
ne
r
gy
f
or
e
c
a
s
t
i
ng
a
nd
m
a
na
ge
m
e
nt
i
n
t
he
T
i
nyM
L
f
r
a
m
e
w
or
k,”
I
E
E
E
A
c
c
e
s
s
,
vol
.
10,
pp.
121010
–
121020,
2022
,
doi
:
10.1109/
A
C
C
E
S
S
.2022.3222986.
[
12]
M
.
L
or
d
a
nd
A
.
K
a
pl
a
n,
“
M
e
c
ha
ni
c
a
l
a
nom
a
l
y
de
t
e
c
t
i
on
on
a
n
e
m
be
dde
d
m
i
c
r
oc
ont
r
ol
l
e
r
,”
i
n
P
r
oc
e
e
di
ngs
-
2021
I
nt
e
r
nat
i
onal
C
onf
e
r
e
nc
e
on
C
om
put
at
i
onal
Sc
i
e
n
c
e
and
C
om
put
at
i
onal
I
nt
e
l
l
i
ge
nc
e
,
C
SC
I
2021
,
2021,
pp.
562
–
568,
doi
:
10.1109/
C
S
C
I
54926.2021.00159.
[
13]
T
.
F
l
or
e
s
,
M
.
A
ndr
a
de
,
M
.
M
e
de
i
r
os
,
M
.
A
m
a
r
a
l
,
M
.
S
i
l
va
,
a
nd
I
.
S
i
l
va
,
“
L
e
ve
r
a
gi
ng
I
oT
a
nd
T
i
nyM
L
f
or
s
m
a
r
t
ba
t
t
e
r
y
m
a
na
ge
m
e
nt
i
n
e
l
e
c
t
r
i
c
bi
c
yc
l
e
s
,”
2023
Sy
m
pos
i
um
on
I
nt
e
r
ne
t
of
T
hi
ngs
,
SI
oT
2023
,
2023,
doi
:
10.1109/
S
I
oT
60039.2023.10390169.
[
14]
G
.
A
t
ha
na
s
a
ki
s
,
G
.
F
i
l
i
os
,
I
.
K
a
t
s
i
di
m
a
s
,
S
.
N
i
ko
l
e
t
s
e
a
s
,
a
nd
S
.
H
.
P
a
na
gi
ot
ou, “
T
i
nyM
L
-
ba
s
e
d
a
ppr
oa
c
h
f
or
r
e
m
a
i
ni
ng
us
e
f
ul
l
i
f
e
pr
e
di
c
t
i
on
of
t
ur
bof
a
n
e
ngi
ne
s
,”
i
n
I
E
E
E
I
nt
e
r
nat
i
onal
C
onf
e
r
e
nc
e
on
E
m
e
r
gi
ng
T
e
c
hnol
ogi
e
s
and
F
ac
t
or
y
A
ut
om
at
i
on,
E
T
F
A
,
2022,
pp. 1
-
8,
doi
:
10.1109/
E
T
F
A
52439.2022.9921629.
[
15]
Y
.
W
a
ng,
K
.
L
i
,
a
nd
Z
.
C
he
n,
“
B
a
t
t
e
r
y
f
ul
l
l
i
f
e
c
yc
l
e
m
a
na
ge
m
e
nt
a
nd
he
a
l
t
h
pr
ognos
i
s
ba
s
e
d
on
c
l
oud
s
e
r
vi
c
e
a
nd
br
oa
d
l
e
a
r
ni
ng,”
I
E
E
E
/
C
A
A
J
our
nal
of
A
ut
om
at
i
c
a Si
ni
c
a
, vol
. 9, no. 8, pp. 1540
–
1542, 2022, doi
:
10.1109/
J
A
S
.2022.105779.
[
16]
T
. M
e
de
i
r
os
e
t
al
.
, “
T
i
nyM
L
c
us
t
om
A
I
a
l
gor
i
t
hm
s
f
or
l
ow
-
pow
e
r
I
oT
da
t
a
c
om
pr
e
s
s
i
on:
a
br
i
dge
m
oni
t
or
i
ng c
a
s
e
s
t
udy,”
i
n
202
3
I
E
E
E
I
nt
e
r
nat
i
onal
W
or
k
s
hop
on
M
e
t
r
ol
ogy
f
or
I
ndus
t
r
y
4.0
and
I
oT
,
M
e
t
r
oI
nd4.0
and
I
oT
2023
-
P
r
oc
e
e
di
ngs
,
2023,
pp.
54
–
59,
doi
:
10.1109/
M
e
t
r
oI
nd4.0I
oT
57462.2023.10180152.
[
17]
M
.
Y
.
S
ha
bi
r
,
G
.
T
or
t
a
,
A
.
B
a
s
s
o,
a
nd
F
.
D
a
m
i
a
ni
,
“
T
ow
a
r
d
s
e
c
ur
e
T
i
nyM
L
on
a
s
t
a
nd
a
r
di
z
e
d
A
I
a
r
c
hi
t
e
c
t
ur
e
,”
I
nt
e
r
ne
t
o
f
T
hi
ngs
, vol
. P
a
r
t
F
1719, pp. 121
–
139, 2024, doi
:
10.1007/
978
-
3
-
031
-
42194
-
5_
7.
[
18]
A
.
S
a
bovi
c
,
M
.
A
e
r
nout
s
,
D
.
S
ubot
i
c
,
J
.
F
ont
a
i
ne
,
E
.
D
e
P
oor
t
e
r
,
a
nd
J
.
F
a
m
a
e
y,
“
T
ow
a
r
ds
e
n
e
r
gy
-
a
w
a
r
e
t
i
nyM
L
on
b
a
t
t
e
r
y
-
l
e
s
s
I
oT
de
vi
c
e
s
,”
I
nt
e
r
ne
t
of
T
hi
ngs
, vol
. 22, 2023, doi
:
10.1016/
j
.i
ot
.2023.100736.
[
19]
K
.
K
.
D
ur
u,
C
.
K
a
r
r
a
,
P
.
V
e
nka
t
a
c
ha
l
a
m
,
S
.
A
.
B
e
t
ha
,
A
.
A
.
M
a
dha
va
n,
a
n
d
S
.
K
a
l
l
ur
i
,
“
C
r
i
t
i
c
a
l
i
ns
i
ght
s
i
nt
o
f
a
s
t
c
ha
r
gi
ng
t
e
c
hni
que
s
f
or
l
i
t
hi
um
-
i
on
ba
t
t
e
r
i
e
s
i
n
e
l
e
c
t
r
i
c
ve
hi
c
l
e
s
,”
I
E
E
E
T
r
ans
ac
t
i
ons
o
n
D
e
v
i
c
e
and
M
at
e
r
i
al
s
R
e
l
i
abi
l
i
t
y
,
vol
.
21,
no.
1
,
pp. 137
–
152, 2021, doi
:
10.1109/
T
D
M
R
.2021.3051840.
[
20]
R
.
D
e
na
t
ha
y
a
l
a
n,
M
.
V
e
nka
t
e
s
hkum
a
r
,
a
nd
C
.
L
.
K
uppu
s
a
m
y,
“
D
r
i
vi
ng
r
a
nge
e
s
t
i
m
a
t
i
on
us
i
ng
A
M
R
I
T
f
or
pr
ognos
t
i
c
s
m
ode
l
of
e
l
e
c
t
r
i
c
ve
hi
c
l
e
s
,”
2023
I
nnov
at
i
ons
i
n
P
ow
e
r
and
A
dv
anc
e
d
C
om
put
i
ng
T
e
c
hnol
ogi
e
s
,
i
-
P
A
C
T
2023
,
2023,
doi
:
10.1109/
I
-
P
A
C
T
58649.2023.10434455.
[
21]
P
.
S
oni
a
nd
I
.
K
a
r
uppa
s
a
m
y,
“
P
e
r
f
or
m
a
nc
e
a
na
l
ys
i
s
of
a
48
V
ba
t
t
e
r
y
pa
c
k
us
i
ng
S
oC
e
s
t
i
m
a
t
i
on
a
nd
c
e
l
l
ba
l
a
n
c
i
ng
f
or
e
l
e
c
t
r
i
c
ve
hi
c
l
e
,”
2023
I
E
E
E
8t
h
I
nt
e
r
nat
i
onal
C
onf
e
r
e
nc
e
f
or
C
onv
e
r
g
e
nc
e
i
n
T
e
c
hnol
ogy
(
I
2C
T
)
,
2023,
pp.
1
-
6,
doi
:
10.1109/
I
2C
T
57861.2023.10126257.
[
22]
T
.
M
.
S
hubha
m
,
M
.
V
e
nka
t
e
s
hkum
a
r
,
a
nd
C
.
S
.
C
hi
n,
“
C
om
pa
r
a
t
i
ve
s
t
udy
of
S
P
S
a
nd
D
P
S
c
ont
r
ol
l
e
d
D
A
B
-
ba
s
e
d
D
C
-
D
C
c
onve
r
t
e
r
f
or
E
V
c
ha
r
gi
ng,”
2023
I
nnov
at
i
ons
i
n
P
ow
e
r
and
A
dv
anc
e
d
C
om
put
i
ng
T
e
c
hnol
ogi
e
s
(
i
-
P
A
C
T
)
,
2023,
pp.
1
-
5,
doi
:
10.1109/
I
-
P
A
C
T
58649.2023.10434628.
[
23]
P
.
V
.
C
hom
bo
a
nd
Y
.
L
a
oonua
l
,
“
A
r
e
vi
e
w
of
s
a
f
e
t
y
s
t
r
a
t
e
gi
e
s
of
a
Li
-
i
on
ba
t
t
e
r
y,”
J
our
nal
of
P
ow
e
r
Sour
c
e
s
,
vol
.
478,
2020,
doi
:
10.1016/
j
.j
pow
s
our
.2020.228649.
[
24]
M
.
B
o
s
e
l
l
o,
C
.
F
a
l
c
om
e
r
,
C
.
R
os
s
i
,
a
nd
G
.
P
a
u,
“
T
o
c
ha
r
ge
or
t
o
s
e
l
l
?
E
V
p
a
c
k
us
e
f
ul
l
i
f
e
e
s
t
i
m
a
t
i
on
vi
a
L
S
T
M
s
,
C
N
N
s
,
a
nd
a
ut
oe
nc
ode
r
s
,”
E
ne
r
gi
e
s
, vol
. 16, no. 6, 2023, doi
:
10.3390/
e
n16062837.
[
25]
C
.
R
.
-
M
a
ya
,
F
.
G
.
-
C
a
r
a
z
a
s
,
F
.
H
.
-
B
a
r
a
j
a
s
,
C
.
P
.
-
R
odr
i
gue
z
,
a
nd
O
.
U
.
-
M
a
nc
o
,
“
R
e
m
a
i
ni
ng
us
e
f
ul
l
i
f
e
pr
e
di
c
t
i
on
of
l
i
t
hi
um
-
i
on
ba
t
t
e
r
y us
i
ng I
C
C
-
C
N
N
-
L
S
T
M
m
e
t
hodol
ogy,”
E
ne
r
gi
e
s
, vol
. 16, no. 20, 2023, doi
:
10.3390/
e
n16207081.
[
26]
S
.
J
a
f
a
r
i
a
nd
Y
.
C
.
B
yun,
“
A
C
N
N
-
G
R
U
a
ppr
oa
c
h
t
o
t
he
a
c
c
ur
a
t
e
pr
e
di
c
t
i
on
of
ba
t
t
e
r
i
e
s
’
r
e
m
a
i
ni
ng
us
e
f
ul
l
i
f
e
f
r
om
c
ha
r
gi
ng
pr
of
i
l
e
s
,”
C
om
put
e
r
s
, vol
. 12, no. 11, 2023, doi
:
10.3390/
c
om
put
e
r
s
12110219.
[
27]
S
.
J
a
f
a
r
i
a
nd
Y
.
C
.
B
yun,
“
O
pt
i
m
i
z
i
ng
b
a
t
t
e
r
y
R
U
L
pr
e
di
c
t
i
on
of
l
i
t
hi
um
-
i
on
ba
t
t
e
r
i
e
s
ba
s
e
d
on
ha
r
r
i
s
ha
w
k
opt
i
m
i
z
a
t
i
o
n
a
ppr
oa
c
h
us
i
ng
r
a
ndom
f
or
e
s
t
a
nd
L
i
ght
G
B
M
,”
I
E
E
E
A
c
c
e
s
s
,
vol
.
11,
pp.
87034
–
87046,
2023
,
doi
:
10.1109/
A
C
C
E
S
S
.2023.3304699.
[
28]
S
.
Z
ha
o,
C
.
Z
ha
ng,
a
nd
Y
.
W
a
ng,
“
L
i
t
hi
um
-
i
on
ba
t
t
e
r
y
c
a
pa
c
i
t
y
a
nd
r
e
m
a
i
ni
ng
us
e
f
ul
l
i
f
e
pr
e
di
c
t
i
on
us
i
ng
boa
r
d
l
e
a
r
ni
ng
s
y
s
t
e
m
a
nd l
ong s
hor
t
-
t
e
r
m
m
e
m
or
y ne
ur
a
l
ne
t
w
or
k,”
J
our
nal
of
E
ne
r
gy
St
or
age
, vol
. 52, 2022, doi
:
10.1016/
j
.e
s
t
.2022.104901.
[
29]
H
.
E
.
B
e
ndi
b,
M
.
B
a
hr
i
,
M
.
B
oum
e
hr
a
z
,
A
.
M
a
l
l
e
m
,
a
nd
M
.
H
a
m
z
i
,
“
I
m
pl
e
m
e
nt
a
t
i
on
of
a
ne
w
ve
r
s
a
t
i
l
e
bi
o
-
pot
e
nt
i
a
l
m
e
a
s
ur
e
m
e
nt
s
y
s
t
e
m
,”
J
our
nal
of
C
i
r
c
ui
t
s
, Sy
s
t
e
m
s
and C
om
put
e
r
s
, vol
. 32, no
. 8, 2023, doi
:
10.1142/
S
0218126623501281.
B
I
O
G
R
A
P
H
I
E
S
OF
A
U
T
H
O
R
S
Dr.
Kamaraj
Lalitha
Nisha
is
currently
working
as
an
Assistant
Profes
sor
in
the
Department
of
ECE
at
Amrita
University
Kollam.
She
received
her
Ph
.
D
.
from
the
National
Institut
e
of
Technology
Calicut,
India,
in
biomedical
image
processin
g.
Her
research
interests
include
I
o
T,
embedded
systems,
medical
image
processing,
patter
n
recognition
,
computer
vision,
and
machine
learning
.
She
has
participated
in
several
proje
cts
on
signal
and
image
processing,
neural
networks,
machine
learning,
and
convolut
ional
n
eural
networks
.
She
has
5
internationa
l
journals,
several
national/international
conference
pu
blications,
and
a
patent
applicati
on
filed
based
on
her
research
work.
Sh
e
can
be
contacted
at
email:
nishaklshaji@
gmail.com
.
Evaluation Warning : The document was created with Spire.PDF for Python.