I
nte
rna
t
io
na
l J
o
urna
l o
f
Appl
ied P
o
wer
E
ng
i
neer
ing
(
I
J
AP
E
)
Vo
l.
1
5
,
No
.
3
,
Sep
tem
b
er
20
2
6
,
p
p
.
1
3
7
5
~
1
385
I
SS
N:
2252
-
8
7
9
2
,
DOI
:
1
0
.
1
1
5
9
1
/ijap
e
.
v
1
5
.
i
3
.
pp
1
3
7
5
-
1
3
8
5
1375
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//
ija
p
e.
ia
esco
r
e.
co
m/
A deep
learning
a
ppro
a
ch f
o
r el
ect
ric vehicle
batte
r
y
charg
ing
dura
tion estima
t
i
o
n using
Io
T
T
um
ulu
ri
K
a
nthim
a
t
hi
1
,
Ad
him
o
o
la
m Sa
ira
m
2
,
Dura
ira
j
Cha
nd
ra
k
a
la
3
,
M
o
o
rt
hy
R
a
dh
ik
a
4
,
B
icha
g
a
l Sha
da
k
s
ha
ra
pp
a
5
,
P
it
cha
i J
o
hn
B
rit
t
o
6
,
M
ina
k
s
hi Sa
na
dh
y
a
7
,
B
a
la
s
ub
ra
m
a
nia
n Sug
a
ny
a
8
,
Chellia
h Sri
niv
a
s
a
n
9
1
D
e
p
a
r
t
me
n
t
o
f
M
e
c
h
a
n
i
c
a
l
E
n
g
i
n
e
e
r
i
n
g
,
K
o
n
e
r
u
La
k
sh
mai
a
h
E
d
u
c
a
t
i
o
n
F
o
u
n
d
a
t
i
o
n
,
G
u
n
t
u
r
,
I
n
d
i
a
2
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
S
a
v
e
e
t
h
a
S
c
h
o
o
l
o
f
En
g
i
n
e
e
r
i
n
g
,
S
a
v
e
e
t
h
a
I
n
st
i
t
u
t
e
o
f
M
e
d
i
c
a
l
a
n
d
Te
c
h
n
i
c
a
l
S
c
i
e
n
c
e
s
,
S
a
v
e
e
t
h
a
U
n
i
v
e
r
si
t
y
,
C
h
e
n
n
a
i
,
I
n
d
i
a
3
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
i
c
a
l
a
n
d
El
e
c
t
r
o
n
i
c
s E
n
g
i
n
e
e
r
i
n
g
,
Ea
sw
a
r
i
En
g
i
n
e
e
r
i
n
g
C
o
l
l
e
g
e
,
C
h
e
n
n
a
i
,
I
n
d
i
a
4
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
mat
i
o
n
Te
c
h
n
o
l
o
g
y
,
R
.
M
.
D
.
En
g
i
n
e
e
r
i
n
g
C
o
l
l
e
g
e
,
C
h
e
n
n
a
i
,
I
n
d
i
a
5
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
S
r
i
S
a
i
r
a
m
C
o
l
l
e
g
e
o
f
En
g
i
n
e
e
r
i
n
g
,
B
e
n
g
a
l
u
r
u
,
I
n
d
i
a
6
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
i
c
a
l
a
n
d
El
e
c
t
r
o
n
i
c
s E
n
g
i
n
e
e
r
i
n
g
,
J.J
.
C
o
l
l
e
g
e
o
f
E
n
g
i
n
e
e
r
i
n
g
a
n
d
Te
c
h
n
o
l
o
g
y
,
Ti
r
u
c
h
i
r
a
p
p
a
l
l
i
,
I
n
d
i
a
7
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
o
n
i
c
s a
n
d
C
o
m
mu
n
i
c
a
t
i
o
n
En
g
i
n
e
e
r
i
n
g
,
F
a
c
u
l
t
y
o
f
E
n
g
i
n
e
e
r
i
n
g
a
n
d
Te
c
h
n
o
l
o
g
y
,
S
R
M
I
n
s
t
i
t
u
t
e
o
f
S
c
i
e
n
c
e
a
n
d
Te
c
h
n
o
l
o
g
y
,
D
e
l
h
i
-
N
C
R
C
a
m
p
u
s,
G
h
a
z
i
a
b
a
d
,
I
n
d
i
a
8
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
S
c
h
o
o
l
o
f
C
o
m
p
u
t
i
n
g
,
V
e
l
T
e
c
h
R
a
n
g
a
r
a
j
a
n
D
r
.
S
a
g
u
n
t
h
a
l
a
R
&D
I
n
st
i
t
u
t
e
o
f
S
c
i
e
n
c
e
a
n
d
Te
c
h
n
o
l
o
g
y
,
C
h
e
n
n
a
i
,
I
n
d
i
a
9
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
S
a
v
e
e
t
h
a
S
c
h
o
o
l
o
f
En
g
i
n
e
e
r
i
n
g
,
S
a
v
e
e
t
h
a
I
n
st
i
t
u
t
e
o
f
M
e
d
i
c
a
l
a
n
d
Te
c
h
n
i
c
a
l
S
c
i
e
n
c
e
s
,
S
a
v
e
e
t
h
a
U
n
i
v
e
r
si
t
y
,
C
h
e
n
n
a
i
,
I
n
d
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Dec
3
,
2
0
2
5
R
ev
is
ed
J
u
l 1
0
,
2
0
2
6
Acc
ep
ted
Au
g
1
5
,
2
0
2
6
Th
e
ra
p
id
d
e
v
e
lo
p
m
e
n
t
o
f
e
lec
tri
c
v
e
h
icle
s (E
Vs
)
h
a
s in
c
re
a
se
d
th
e
d
e
sire
fo
r
p
re
c
ise
c
h
a
rg
in
g
d
u
ra
ti
o
n
e
stim
a
te
to
e
n
h
a
n
c
e
c
h
a
rg
i
n
g
sta
ti
o
n
a
d
m
in
istratio
n
a
n
d
e
lev
a
te
c
u
sto
m
e
r
e
x
p
e
rien
c
e
.
Th
is
re
se
a
rc
h
p
re
se
n
ts
a
d
e
e
p
lea
r
n
in
g
(DL)
a
rc
h
it
e
c
tu
re
th
a
t
u
se
s
in
tern
e
t
o
f
th
in
g
s
(Io
T)
-
e
n
a
b
led
d
a
ta
to
c
a
teg
o
rise
c
h
a
rg
in
g
d
u
ra
ti
o
n
in
t
o
s
h
o
rt
,
m
e
d
iu
m
,
a
n
d
lo
n
g
c
las
sifica
ti
o
n
s.
T
h
e
a
ss
e
ss
m
e
n
t
d
a
tas
e
t
c
o
m
p
rise
s
m
a
n
y
n
u
m
e
rica
l
a
n
d
c
a
teg
o
rica
l
v
a
riab
les
a
ffe
c
ti
n
g
b
a
tt
e
ry
p
e
rf
o
rm
a
n
c
e
a
n
d
c
h
a
rg
in
g
b
e
h
a
v
io
u
r,
p
r
o
v
id
i
n
g
a
th
o
ro
u
g
h
fo
u
n
d
a
ti
o
n
fo
r
p
re
d
ictio
n
.
Th
e
sy
ste
m
u
ti
l
ise
s
a
d
e
e
p
n
e
u
ra
l
n
e
tw
o
rk
(DN
N)
a
rc
h
it
e
c
tu
re
with
n
o
n
li
n
e
a
r
tran
sfo
rm
a
ti
o
n
s
a
n
d
re
g
u
larisa
ti
o
n
t
e
c
h
n
iq
u
e
s,
train
e
d
wit
h
a
d
a
p
ti
v
e
o
p
ti
m
isa
ti
o
n
to
p
r
o
v
i
d
e
d
u
ra
b
le
c
o
n
v
e
rg
e
n
c
e
.
Ex
ten
si
v
e
e
x
p
e
rime
n
ts
in
d
ica
te
th
a
t
th
e
p
ro
p
o
se
d
m
o
d
e
l
a
c
h
iev
e
s
a
n
o
v
e
ra
ll
a
c
c
u
ra
c
y
o
f
9
9
.
2
6
%
,
m
a
rk
e
d
l
y
imp
r
o
v
i
n
g
trad
it
io
n
a
l
m
a
c
h
in
e
lea
rn
i
n
g
(
M
L)
t
e
c
h
n
iq
u
e
s.
Th
e
se
re
su
lt
s
h
ig
h
li
g
h
t
t
h
e
p
o
t
e
n
ti
a
l
o
f
DL
t
o
a
d
e
p
tl
y
d
isc
e
r
n
c
o
m
p
lex
li
n
k
a
g
e
s
in
c
h
a
rg
i
n
g
d
y
n
a
m
ics
,
p
r
o
v
i
d
in
g
d
e
p
e
n
d
a
b
le
p
re
d
icti
o
n
s
f
o
r
d
u
ra
ti
o
n
c
las
sifica
ti
o
n
.
Th
e
fra
m
e
wo
rk
p
r
o
v
id
e
s
a
n
a
d
v
a
n
c
e
d
b
a
sis
fo
r
imp
le
m
e
n
tatio
n
in
sm
a
rt
c
h
a
rg
in
g
in
fra
str
u
c
tu
re
s,
f
a
c
il
it
a
ti
n
g
e
ffe
c
ti
v
e
sc
h
e
d
u
li
n
g
,
m
in
imi
z
in
g
wa
it
in
g
ti
m
e
s,
a
n
d
e
n
d
o
rsi
n
g
p
re
d
ictiv
e
m
a
in
ten
a
n
c
e
m
e
a
su
re
s.
It
e
n
h
a
n
c
e
s
th
e
re
li
a
b
i
li
ty
a
n
d
e
fficie
n
c
y
o
f
EV
c
h
a
rg
i
n
g
e
c
o
sy
ste
m
s
with
d
a
ta
-
d
riv
e
n
,
Io
T
-
e
n
a
b
le
d
DL
tec
h
n
o
l
o
g
ies
.
K
ey
w
o
r
d
s
:
C
h
ar
g
in
g
d
u
r
atio
n
esti
m
atio
n
Dee
p
lear
n
in
g
E
lectr
ic
v
eh
icles
E
n
er
g
y
m
an
ag
e
m
en
t
I
n
ter
n
et
o
f
th
in
g
s
Sm
ar
t m
o
b
ilit
y
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
T
u
m
u
lu
r
i K
a
n
th
im
ath
i
Dep
ar
tm
en
t o
f
Me
ch
an
ical
E
n
g
in
ee
r
in
g
,
Ko
n
er
u
L
ak
s
h
m
aia
h
E
d
u
ca
tio
n
Fo
u
n
d
atio
n
Vad
d
eswar
am
,
Gu
n
tu
r
,
An
d
h
r
a
Pra
d
esh
,
I
n
d
ia
E
m
ail:
p
k
an
th
i1
9
7
8
@
g
m
ail.
c
o
m
1.
I
NT
RO
D
UCT
I
O
N
E
Vs
ar
e
s
ee
in
g
tr
em
en
d
o
u
s
g
r
o
wth
o
win
g
t
o
en
v
ir
o
n
m
en
tal
co
n
s
id
er
atio
n
s
an
d
ad
v
a
n
ce
m
en
ts
in
b
atter
y
tech
n
o
lo
g
y
.
E
f
f
ec
tiv
e
b
illi
n
g
m
an
ag
e
m
en
t
is
ess
en
tial
to
m
in
im
is
e
waitin
g
tim
es
an
d
en
h
a
n
ce
cu
s
to
m
er
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
9
2
I
n
t J Ap
p
l Po
wer
E
n
g
,
Vo
l.
1
5
,
No
.
3
,
Sep
tem
b
er
20
2
6
:
1
3
7
5
-
1
3
8
5
1376
ex
p
er
ien
ce
.
C
o
n
v
en
tio
n
al
m
ac
h
in
e
lear
n
in
g
m
eth
o
d
s
,
s
u
ch
as
KNN
an
d
Naiv
e
B
ay
es,
o
f
ten
s
tr
u
g
g
le
to
id
e
n
tify
in
tr
icate
p
atter
n
s
with
in
I
o
T
-
en
ab
led
in
f
o
r
m
atio
n
.
I
o
T
d
ev
ices
p
r
o
v
id
e
r
ea
l
-
tim
e
b
atter
y
an
d
en
v
ir
o
n
m
en
tal
in
f
o
r
m
atio
n
,
en
ab
lin
g
p
r
ed
icti
v
e
an
aly
tics
f
o
r
en
h
a
n
ce
d
ch
ar
g
in
g
ef
f
icie
n
cy
.
Pre
cisely
ca
lcu
latin
g
ch
ar
g
in
g
p
er
io
d
is
d
if
f
icu
lt
o
win
g
t
o
s
e
v
er
al
d
y
n
am
ic
elem
e
n
ts
,
in
clu
d
in
g
b
atter
y
s
tate
-
of
-
ch
ar
g
e,
t
em
p
er
atu
r
e,
b
atter
y
ag
e,
an
d
c
h
ar
g
e
r
ty
p
e.
C
o
n
v
en
tio
n
al
m
ac
h
in
e
lear
n
in
g
m
o
d
els
o
f
te
n
e
x
h
ib
it
r
estr
icted
ac
cu
r
ac
y
a
n
d
g
en
er
alis
atio
n
,
wh
ic
h
im
p
ai
r
s
ef
f
ec
tiv
e
s
ch
ed
u
lin
g
an
d
p
r
e
d
ictiv
e
m
ain
ten
an
ce
.
T
h
e
p
r
im
a
r
y
co
n
tr
ib
u
tio
n
s
o
f
th
is
s
tu
d
y
ar
e:
i)
I
n
teg
r
atio
n
o
f
I
o
T
d
ata:
E
m
p
l
o
y
in
g
r
ea
l
-
tim
e
d
ata
f
r
o
m
v
a
r
io
u
s
s
en
s
o
r
s
m
o
n
ito
r
in
g
b
atter
y
an
d
am
b
ien
t
co
n
d
itio
n
s
.
ii)
Dee
p
lear
n
in
g
a
r
ch
itectu
r
e
: U
t
ili
z
in
g
DNN
to
s
im
u
late
in
tr
icate
r
elatio
n
s
h
ip
s
am
o
n
g
d
iv
er
s
e
f
ea
tu
r
es.
iii)
E
n
h
an
ce
d
p
r
e
d
ictiv
e
p
r
ec
is
io
n
:
Attain
in
g
s
u
p
er
io
r
ac
cu
r
ac
y
an
d
an
elev
ated
F1
-
s
co
r
e,
b
ey
o
n
d
co
n
v
en
tio
n
al
m
ac
h
in
e
lear
n
in
g
m
eth
o
d
o
lo
g
ies.
iv
)
Pra
ctica
l
ap
p
licab
ili
ty
:
E
s
tab
l
is
h
in
g
a
f
r
am
ewo
r
k
f
o
r
in
tel
lig
en
t
ch
ar
g
e
s
ch
ed
u
lin
g
an
d
an
ticip
ato
r
y
m
ain
ten
an
ce
.
T
h
e
f
o
llo
win
g
p
ar
ts
o
f
th
is
p
ap
er
ar
e
o
r
g
a
n
is
ed
as
f
o
llo
ws.
Sectio
n
2
ex
am
in
es
r
elev
a
n
t
s
tu
d
ies
o
n
E
V
ch
ar
g
in
g
esti
m
ates
an
d
I
o
T
s
o
lu
tio
n
s
.
Sectio
n
3
o
u
tlin
es
t
h
e
p
r
o
p
o
s
ed
DL
f
r
am
ewo
r
k
an
d
p
r
ep
r
o
ce
s
s
in
g
m
eth
o
d
o
l
o
g
ies.
Sectio
n
4
d
el
in
ea
tes
th
e
d
ataset
an
d
ex
p
e
r
im
en
tal
tech
n
iq
u
e
,
h
i
g
h
lig
h
ti
n
g
th
e
f
r
am
ewo
r
k
'
s
ef
f
icac
y
.
Sectio
n
5
co
n
cl
u
d
es th
e
wo
r
k
a
n
d
p
r
o
p
o
s
es f
u
tu
r
e
r
esear
ch
d
ir
ec
tio
n
s
in
s
m
ar
t c
h
ar
g
in
g
s
y
s
tem
s
.
T
o
en
h
an
ce
p
ac
k
p
e
r
f
o
r
m
an
c
e,
th
is
wo
r
k
in
tr
o
d
u
ce
s
an
ac
tiv
e
ce
ll
b
alan
cin
g
s
tr
ateg
y
f
o
r
E
Vs
th
at
r
ed
u
ce
s
ca
p
ac
ity
an
d
ac
ce
ler
ates
d
eter
io
r
atio
n
[
1
]
.
T
h
e
m
eth
o
d
in
v
o
lv
es
d
is
p
er
s
in
g
s
u
r
p
lu
s
ch
ar
g
e
f
r
o
m
h
ig
h
-
SOC
ce
l
ls
an
d
in
cr
ea
s
in
g
d
is
ch
ar
g
e
tim
e
f
r
o
m
lo
w
-
SOC
ce
lls
.
T
o
ad
d
r
ess
th
e
ch
allen
g
e
o
f
co
n
tr
o
llin
g
th
e
o
n
lin
e
ch
ar
g
in
g
o
f
n
u
m
e
r
o
u
s
E
V
at
o
n
ce
in
an
u
n
p
r
e
d
ictab
le
ch
ar
g
in
g
e
n
v
ir
o
n
m
en
t
with
e
r
r
a
tic
E
V
ar
r
iv
als
an
d
d
ep
ar
tu
r
es,
th
is
p
r
o
p
o
s
es
a
m
u
lti
-
ag
en
t
d
ee
p
r
ein
f
o
r
ce
m
en
t
lear
n
in
g
-
b
ased
ch
ar
g
i
n
g
s
ch
e
d
u
lin
g
ap
p
r
o
ac
h
f
o
r
E
V
ch
ar
g
in
g
s
tatio
n
s
[
2
]
.
B
y
lo
wer
in
g
ca
p
ac
ity
an
d
s
p
ee
d
i
n
g
u
p
d
e
g
r
ad
atio
n
,
th
is
wo
r
k
in
tr
o
d
u
ce
s
a
n
ac
tiv
e
ce
ll
b
alan
cin
g
s
tr
ateg
y
f
o
r
E
V
th
at
im
p
r
o
v
es
p
ac
k
p
e
r
f
o
r
m
a
n
ce
b
y
s
p
r
ea
d
in
g
s
u
r
p
lu
s
ch
ar
g
e
f
r
o
m
h
ig
h
-
SOC
ce
lls
an
d
ex
ten
d
in
g
d
is
ch
ar
g
e
d
u
r
atio
n
f
r
o
m
lo
w
-
SOC
ce
lls
[
1
]
.
E
x
am
i
n
in
g
asp
ec
ts
s
u
ch
as
p
r
ec
is
io
n
,
test
in
g
co
n
d
itio
n
s
,
in
p
u
t/o
u
tp
u
t,
an
d
d
ata
q
u
ality
,
th
is
r
esear
ch
ass
ess
es
f
ee
d
-
f
o
r
war
d
n
eu
r
al
n
et
wo
r
k
s
(
FF
NNs)
f
o
r
ML
-
b
ased
E
V
s
tate
o
f
ch
ar
g
e
an
d
h
ea
lth
esti
m
ate
[
3
]
.
A
n
ew
ML
alg
o
r
ith
m
f
o
r
esti
m
atin
g
th
e
R
UL
o
f
E
V
lith
iu
m
-
io
n
b
atter
ies
[
4
]
.
R
an
d
o
m
f
o
r
est
,
K
-
Nea
r
est
n
eig
h
b
o
u
r
s
,
an
d
g
r
ad
ien
t
b
o
o
s
tin
g
d
ec
is
io
n
tr
ee
ar
e
s
o
m
e
o
f
th
e
ar
tific
ial
n
eu
r
al
n
etwo
r
k
s
(
ANNs)
u
s
ed
in
t
h
e
f
r
a
m
e
wo
r
k
,
wh
ic
h
also
in
c
o
r
p
o
r
ate
s
ANNs
f
o
r
f
ea
tu
r
e
ex
tr
ac
tio
n
a
n
d
en
s
em
b
le
m
o
d
ellin
g
.
Fo
cu
s
s
in
g
o
n
asp
ec
ts
s
u
ch
E
V
b
atter
y
h
ea
lth
,
f
u
n
ct
io
n
,
a
n
d
r
em
ain
in
g
u
s
ab
le
life
,
th
e
ar
ticle
ex
p
lain
s
h
o
w
to
o
p
tim
is
e
E
V
b
atter
y
p
er
f
o
r
m
a
n
ce
u
s
in
g
p
r
e
d
ictiv
e
ML
ap
p
r
o
ac
h
es
[
5
]
.
B
ec
au
s
e
o
f
th
eir
r
ap
id
d
e
p
letio
n
co
s
t,
tech
n
ical
d
ev
el
o
p
m
en
ts
,
h
ig
h
en
er
g
y
an
d
p
o
wer
d
e
n
s
ity
,
an
d
s
u
itab
ilit
y
f
o
r
elec
tr
ic
m
o
b
ilit
y
,
lith
iu
m
-
io
n
b
atter
ies
ar
e
p
er
f
ec
t
[
6
]
.
W
ith
o
u
t
tak
in
g
elec
tr
o
c
h
em
ic
al
p
r
o
p
er
ties
in
to
ac
co
u
n
t,
an
ML
s
y
s
tem
is
cr
ea
t
ed
to
esti
m
ate
th
e
s
tate
o
f
h
ea
lt
h
f
r
o
m
v
o
ltag
e,
c
u
r
r
e
n
t,
an
d
te
m
p
er
atu
r
e
u
tili
z
in
g
KNN,
SVR
,
DT
,
an
d
R
F
r
eg
r
ess
o
r
s
.
B
y
co
n
s
tr
u
ctin
g
a
s
m
ar
t
ch
ar
g
in
g
h
u
b
n
etwo
r
k
u
tili
s
in
g
d
y
n
am
ic
K
-
m
ea
n
s
clu
s
ter
in
g
,
th
is
r
esear
ch
in
tr
o
d
u
ce
s
a
n
ew
m
et
h
o
d
f
o
r
ch
ar
g
in
g
E
Vs
[
7
]
.
Static
clu
s
ter
in
g
s
y
s
tem
s
ar
e
in
ef
f
icien
t
an
d
ca
u
s
e
ch
ar
g
in
g
s
tatio
n
lo
a
d
s
s
in
ce
E
V
u
s
e
p
atter
n
s
ar
e
u
n
p
r
ed
ictab
le.
A
c
h
ar
g
e
s
ch
e
d
u
lin
g
s
y
s
tem
f
o
r
E
V
f
leets
th
at
m
ax
im
i
z
es
r
em
ain
in
g
u
s
ef
u
l
life
(
R
UL
)
f
o
r
all
b
a
tter
ies
an
d
r
ed
u
ce
s
g
r
ee
n
h
o
u
s
e
g
as
em
is
s
io
n
s
[
8
]
.
Ma
k
in
g
s
u
r
e
th
at
ch
ar
g
in
g
o
n
e
ca
r
as
late
as
f
ea
s
ib
le
m
ax
i
m
i
z
es
R
UL
,
th
e
s
tr
ateg
y
u
tili
z
es
two
o
p
tim
i
z
atio
n
m
eth
o
d
s
an
d
an
ML
m
o
d
el.
Op
tim
i
z
atio
n
ap
p
r
o
ac
h
es
f
o
r
lith
iu
m
-
io
n
b
atter
y
m
an
a
g
e
m
en
t
in
E
Vs
ar
e
in
v
esti
g
at
ed
in
th
is
co
m
p
r
eh
e
n
s
iv
e
m
ap
p
i
n
g
r
esea
r
ch
[
9
]
.
I
m
p
r
o
v
in
g
b
atter
y
d
ep
en
d
ab
ilit
y
,
p
r
o
lo
n
g
in
g
lo
n
g
ev
i
ty
,
an
d
o
p
tim
i
z
in
g
en
er
g
y
m
a
n
ag
em
e
n
t
r
eq
u
ir
es
co
m
b
in
in
g
ad
v
a
n
ce
d
f
ilter
in
g
tech
n
iq
u
es,
ML
,
a
n
d
o
p
tim
i
z
atio
n
alg
o
r
ith
m
s
.
I
m
p
r
o
v
in
g
ef
f
icien
cy
,
r
ed
u
cin
g
en
er
g
y
co
n
s
u
m
p
tio
n
,
an
d
ex
ten
d
in
g
b
atter
y
lo
n
g
ev
ity
ar
e
s
o
m
e
o
f
th
e
g
o
als o
f
th
is
p
ap
er
'
s
ex
p
lo
r
atio
n
o
f
a
r
tific
ial
in
tellig
en
ce
(
A
I
)
a
n
d
ML
ap
p
r
o
ac
h
es
t
o
o
p
tim
is
in
g
E
V
b
atter
y
ch
ar
g
i
n
g
o
p
er
atio
n
s
[
1
0
]
.
A
m
o
r
e
ef
f
icien
t
ap
p
r
o
ac
h
f
o
r
m
an
a
g
in
g
E
V
b
atter
ies
is
d
ev
elo
p
ed
b
y
th
e
r
esear
ch
team
u
s
in
g
I
o
T
,
ML
,
a
n
d
b
lo
ck
c
h
ain
tec
h
n
o
lo
g
y
[
1
1
]
.
Data
b
ases
,
th
e
lig
h
t
GB
M
class
if
ier
,
an
d
a
p
o
wer
s
ch
ed
u
lin
g
m
eth
o
d
ar
e
u
s
ed
to
p
r
o
ce
s
s
d
ata
co
llected
b
y
I
o
T
s
en
s
o
r
s
,
wh
ich
in
clu
d
e
in
f
o
r
m
atio
n
o
n
th
e
v
e
h
icle'
s
p
o
s
itio
n
,
ch
ar
g
e
lev
el,
an
d
d
is
tan
ce
tr
av
el.
T
h
is
s
tu
d
y
in
tr
o
d
u
ce
s
a
f
u
zz
y
ap
p
r
o
ac
h
f
o
r
co
n
tr
o
llin
g
th
e
c
h
ar
g
i
n
g
a
n
d
d
is
ch
ar
g
in
g
o
f
lith
iu
m
-
io
n
b
atter
ies
u
s
ed
in
E
Vs
[
1
2
]
.
T
h
e
p
u
r
p
o
s
e
o
f
th
is
s
tu
d
y
was
to
ex
am
in
e
th
e
tr
u
e
e
n
er
g
y
c
o
n
s
u
m
p
ti
o
n
o
f
co
m
m
er
cial
B
E
Vs
in
T
h
ail
an
d
b
y
test
in
g
th
em
in
r
ea
l
-
w
o
r
ld
s
ce
n
ar
i
o
s
o
n
s
ev
er
al
r
o
u
tes,
in
clu
d
in
g
u
r
b
an
an
d
r
u
r
al
o
n
es
[
1
3
]
.
T
h
e
d
ata
was
co
llected
u
s
in
g
o
n
b
o
ar
d
d
iag
n
o
s
tics
an
d
GPS
eq
u
ip
m
en
t.
T
o
h
elp
with
m
is
s
io
n
p
lan
n
in
g
an
d
u
n
co
v
e
r
th
e
r
ea
s
o
n
s
f
o
r
r
ap
id
ag
ein
g
,
th
is
r
esear
ch
s
tu
d
y
em
p
lo
y
s
a
cu
s
to
m
is
ed
n
eu
r
al
n
etwo
r
k
to
ass
ess
th
e
s
tate
o
f
h
ea
lth
(
SOH)
o
f
a
n
E
V
f
leet
u
s
in
g
f
ield
d
ata
[
1
4
]
.
T
o
m
itig
ate
u
n
ce
r
tain
ty
a
n
d
p
r
io
r
itis
e
th
e
n
ee
d
s
o
f
th
e
cli
en
t,
th
is
s
tu
d
y
in
tr
o
d
u
ce
s
a
f
u
zz
y
m
u
lti
-
cr
iter
ia
d
ec
is
io
n
-
m
ak
in
g
ap
p
r
o
ac
h
f
o
r
ch
o
o
s
in
g
a
s
u
s
tain
ab
le
b
atter
y
p
r
o
v
id
er
f
o
r
B
SS
.
T
h
e
ap
p
r
o
a
ch
m
ak
es
u
s
e
o
f
tr
ia
n
g
u
lar
f
u
z
zy
n
u
m
b
er
s
(
T
FN)
an
d
q
u
alit
y
f
u
n
ctio
n
d
ep
l
o
y
m
en
t
(
QFD)
[
1
5
]
.
T
o
ch
a
r
g
e
E
V
b
atter
ies
m
o
r
e
ef
f
icien
tly
,
o
u
r
s
tu
d
y
s
u
g
g
ests
a
n
o
v
el
ap
p
r
o
ac
h
[
1
6
]
.
B
y
r
eg
u
l
atin
g
th
e
c
u
r
r
en
t
th
at
f
lo
ws
f
r
o
m
th
e
PV
ar
r
a
y
to
t
h
e
E
V
b
att
er
y
an
d
b
ac
k
to
t
h
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ap
p
l Po
wer
E
n
g
I
SS
N:
2252
-
8
7
9
2
A
d
ee
p
lea
r
n
in
g
a
p
p
r
o
a
ch
fo
r
elec
tr
ic
ve
h
icle
b
a
tter
y
ch
a
r
g
in
g
…
(
Tu
mu
lu
r
i Ka
n
th
ima
th
i
)
1377
g
r
id
,
th
e
b
id
ir
ec
tio
n
al
co
n
v
er
t
er
'
s
f
u
zz
y
lo
g
ic
co
n
tr
o
ller
(
FL
C
)
m
ak
es
ch
ar
g
in
g
an
d
d
is
ch
ar
g
in
g
p
r
o
ce
s
s
es
as
ef
f
icien
t
as
p
o
s
s
ib
le.
Fo
cu
s
in
g
o
n
s
tate
-
of
-
th
e
-
ar
t
ML
r
eg
r
ess
io
n
m
o
d
els,
th
is
wo
r
k
in
v
esti
g
ates
th
e
s
h
o
r
tco
m
in
g
s
o
f
c
o
n
v
e
n
tio
n
al
ap
p
r
o
ac
h
es
to
E
V
b
atter
y
s
tat
e
-
of
-
ch
a
r
g
e
esti
m
atio
n
[
1
7
]
.
F
o
r
m
an
a
g
in
g
p
o
wer
g
r
id
co
n
g
esti
o
n
in
E
u
r
o
p
e,
th
is
s
tu
d
y
s
u
g
g
ests
an
in
tellig
en
tly
r
eg
u
lated
B
E
V
ch
ar
g
in
g
s
tr
ateg
y
[
1
8
]
.
T
h
is
p
ap
e
r
ex
am
in
es
E
Vs
an
d
e
v
alu
ates
c
u
r
r
en
t
ch
ar
g
in
g
m
eth
o
d
s
,
with
an
em
p
h
asis
o
n
h
y
b
r
id
ca
r
d
esig
n
s
an
d
r
ec
h
ar
g
in
g
in
f
r
astru
ctu
r
e
[
1
9
]
.
T
o
h
elp
in
f
r
astru
ctu
r
e
o
p
er
ato
r
s
o
p
tim
i
z
e
E
V
ch
ar
g
in
g
m
eth
o
d
s
ex
a
m
in
es
th
e
d
u
r
atio
n
s
o
f
E
V
ch
ar
g
e
ev
en
ts
in
Gr
ea
ter
Ma
n
ch
ester
,
ex
p
o
s
in
g
th
e
ef
f
e
cts
o
f
wea
th
er
an
d
s
ea
s
o
n
s
o
n
ch
ar
g
in
g
b
e
h
av
io
r
[
2
0
]
.
T
h
is
s
tu
d
y
s
u
g
g
ests
a
s
er
v
ice
m
o
d
e
ar
ch
itectu
r
e
to
p
r
o
v
id
e
g
r
id
-
f
r
ien
d
ly
elec
tr
ic
v
eh
ic
le
ch
ar
g
in
g
f
o
r
u
s
er
s
[
2
1
]
.
Use
o
p
tim
i
z
atio
n
m
eth
o
d
s
b
ased
o
n
s
to
ch
asti
c
v
ar
iab
les
to
co
n
tr
o
l
th
e
f
lo
w
o
f
E
V
ch
ar
g
in
g
an
d
d
is
ch
ar
g
in
g
in
ca
r
p
ar
k
s
[
2
2
]
.
T
h
e
p
u
r
p
o
s
e
o
f
th
is
r
esear
ch
is
to
f
in
d
th
e
b
est
d
ee
p
lear
n
in
g
m
o
d
el
f
o
r
p
r
e
d
ictin
g
wh
en
E
Vs
will
ar
r
iv
e
at
ch
ar
g
in
g
s
tatio
n
s
an
d
h
o
w
lo
n
g
it
will
tak
e
th
em
to
ch
ar
g
e
[
2
3
]
.
T
h
e
d
ev
elo
p
m
en
t
o
f
elec
tr
ic
v
eh
icle
tech
n
o
lo
g
y
en
a
b
les
in
d
ep
en
d
en
t
wh
ee
l
to
r
q
u
e
co
n
tr
o
l,
o
f
f
e
r
in
g
a
u
n
i
q
u
e
o
p
p
o
r
tu
n
ity
to
im
p
r
o
v
e
v
eh
icle
s
tab
ilit
y
an
d
m
a
n
ag
e
t
h
r
o
u
g
h
to
r
q
u
e
v
ec
to
r
in
g
[
2
4
]
.
2.
M
E
T
H
O
D
T
h
e
p
r
o
p
o
s
ed
s
y
s
tem
f
o
r
esti
m
atin
g
E
V
ch
ar
g
in
g
d
u
r
atio
n
f
u
n
ctio
n
s
as
a
co
m
p
r
eh
e
n
s
iv
e
v
iew
th
at
in
co
r
p
o
r
ates
I
o
T
-
e
n
ab
led
d
at
a
ac
q
u
is
itio
n
,
d
ata
p
r
e
p
r
o
ce
s
s
in
g
,
DNN
m
o
d
ellin
g
,
tr
ai
n
in
g
with
a
d
ap
tiv
e
o
p
tim
i
z
atio
n
,
an
d
th
e
u
ltima
te
class
if
icatio
n
o
f
ch
ar
g
in
g
d
u
r
a
tio
n
in
to
s
h
o
r
t,
m
ed
iu
m
,
an
d
l
o
n
g
ca
teg
o
r
ies.
T
h
e
r
esear
ch
em
p
lo
y
s
lith
iu
m
-
io
n
(Li
-
io
n
)
b
atter
ies,
r
ep
r
esen
ted
b
y
a
s
im
p
lifie
d
e
q
u
iv
alen
t
cir
cu
it
m
o
d
el
(
E
C
M)
.
T
h
e
v
o
ltag
e
o
f
th
e
b
atter
y
wh
e
n
ch
ar
g
i
n
g
is
d
en
o
ted
as
(
1
)
.
(
)
=
OC
V
−
(
)
⋅
(
1
)
W
h
er
e
OC
V
is
th
e
o
p
en
-
cir
c
u
it
v
o
ltag
e,
(
)
is
th
e
c
h
ar
g
in
g
c
u
r
r
en
t
,
an
d
is
th
e
i
n
ter
n
al
r
esis
tan
ce
.
T
h
ese
f
ea
tu
r
es,
alo
n
g
with
en
v
ir
o
n
m
en
tal
p
ar
am
ete
r
s
,
wer
e
u
s
ed
t
o
tr
ain
th
e
DNN
f
o
r
class
if
y
in
g
ch
ar
g
in
g
d
u
r
atio
n
.
Fig
u
r
e
1
illu
s
tr
ates
th
e
p
r
o
p
o
s
e
d
s
y
s
tem
,
wh
ich
b
eg
in
s
with
I
o
T
-
en
ab
led
d
ata
c
o
llectio
n
f
r
o
m
ch
ar
g
i
n
g
s
tatio
n
s
,
c
o
llectin
g
k
ey
o
p
e
r
atio
n
al
in
f
o
r
m
atio
n
o
n
E
V.
T
h
e
r
aw
d
at
a
is
p
r
o
ce
s
s
ed
to
p
r
ep
r
o
ce
s
s
in
g
,
wh
ich
in
clu
d
es
clea
n
in
g
,
n
o
r
m
ali
z
atio
n
,
an
d
en
co
d
in
g
,
to
g
u
ar
a
n
tee
q
u
ality
an
d
co
n
s
is
ten
cy
.
T
h
e
p
r
o
ce
s
s
ed
d
ata
is
f
u
r
th
er
an
aly
z
ed
b
y
a
DNN,
wh
ich
id
en
tifie
s
h
id
d
en
r
elatio
n
s
h
ip
s
a
n
d
ca
teg
o
r
is
es
ch
ar
g
i
n
g
tim
e
i
n
to
s
h
o
r
t,
m
ed
i
u
m
,
o
r
lo
n
g
ca
teg
o
r
ies.
T
h
e
p
r
e
d
icted
o
u
tp
u
ts
f
ac
ilit
ate
ap
p
licatio
n
s
s
u
ch
as
r
ea
l
-
tim
e
u
s
er
ass
is
tan
ce
,
in
tellig
en
t
s
ch
ed
u
lin
g
,
a
n
d
p
r
ed
ictiv
e
m
ai
n
ten
an
ce
wit
h
in
E
V
c
h
ar
g
in
g
i
n
f
r
astru
ctu
r
e.
Fig
u
r
e
1
.
W
o
r
k
f
lo
w
o
f
th
e
I
o
T
-
en
ab
led
c
h
ar
g
in
g
d
u
r
atio
n
p
r
ed
ictio
n
s
y
s
tem
T
h
e
p
r
o
ce
s
s
b
eg
i
n
s
with
I
o
T
d
ev
ices
in
teg
r
ated
in
t
o
th
e
ch
ar
g
in
g
in
f
r
astru
ctu
r
e,
wh
ich
i
n
ce
s
s
an
tly
m
o
n
ito
r
d
iv
e
r
s
e
o
p
er
atio
n
al
an
d
co
n
tex
tu
al
asp
ec
ts
th
r
o
u
g
h
o
u
t
th
e
ch
ar
g
in
g
p
r
o
ce
d
u
r
e.
T
h
e
r
aw
m
ea
s
u
r
em
en
ts
ar
e
s
en
t
to
a
ce
n
tr
alis
ed
co
m
p
u
te
u
n
it,
eith
er
i
n
th
e
clo
u
d
o
r
at
th
e
ed
g
e,
w
h
er
e
p
r
ep
r
o
ce
s
s
in
g
o
cc
u
r
s
to
en
s
u
r
e
th
e
d
ataset
is
clea
n
,
s
tan
d
ar
d
is
ed
,
an
d
ap
p
r
o
p
r
iate
f
o
r
in
p
u
t
in
to
th
e
DL
m
o
d
el.
Pre
p
r
o
ce
s
s
in
g
en
co
m
p
ass
es
m
an
y
s
tag
es,
f
ir
s
t
with
d
ata
c
lean
in
g
to
a
d
d
r
ess
ab
s
en
t
o
r
i
n
co
n
s
is
ten
t
v
alu
es
u
s
in
g
im
p
u
tatio
n
o
r
f
ilter
in
g
m
eth
o
d
s
,
s
u
cc
ee
d
e
d
b
y
n
o
r
m
alis
atio
n
to
ad
ju
s
t
co
n
tin
u
o
u
s
v
alu
es
in
to
a
u
n
i
f
o
r
m
n
u
m
er
ical
r
an
g
e.
A
co
n
v
en
tio
n
al
n
o
r
m
alis
atio
n
m
eth
o
d
,
s
u
c
h
as m
in
–
m
a
x
s
ca
lin
g
,
is
ex
p
r
ess
ed
as
(
2
)
.
′
=
−
−
(
2
)
W
h
er
e
is
th
e
o
r
ig
in
al
f
ea
tu
r
e
v
alu
e,
d
en
o
te
th
e
lo
west
an
d
m
ax
im
u
m
v
alu
es f
o
r
th
at
f
ea
tu
r
e,
wh
er
ea
s
′
r
ep
r
esen
ts
th
e
n
o
r
m
ali
z
ed
o
u
t
p
u
t.
T
h
is
g
u
ar
an
tees
th
at
all
n
u
m
er
ical
ch
ar
a
cter
is
tics
co
n
tr
ib
u
te
eq
u
itab
ly
d
u
r
in
g
m
o
d
el
tr
ai
n
in
g
.
On
e
-
h
o
t
e
n
co
d
in
g
is
u
tili
z
ed
f
o
r
ca
teg
o
r
y
in
f
o
r
m
atio
n
lik
e
c
ar
k
in
d
o
r
ch
a
r
g
in
g
m
o
d
e,
tr
a
n
s
f
o
r
m
in
g
s
y
m
b
o
li
c
ca
teg
o
r
ies
in
to
b
in
a
r
y
v
ec
t
o
r
s
th
at
r
em
o
v
e
u
n
d
esire
d
o
r
d
in
al
co
r
r
elatio
n
s
.
R
esam
p
lin
g
p
r
o
ce
d
u
r
es
ar
e
e
m
p
lo
y
ed
to
r
ec
tif
y
th
e
im
b
alan
ce
ac
r
o
s
s
tar
g
et
class
es,
en
s
u
r
in
g
a
m
o
r
e
c
o
n
s
is
ten
t
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
9
2
I
n
t J Ap
p
l Po
wer
E
n
g
,
Vo
l.
1
5
,
No
.
3
,
Sep
tem
b
er
20
2
6
:
1
3
7
5
-
1
3
8
5
1378
d
is
tr
ib
u
tio
n
o
f
s
h
o
r
t,
m
ed
i
u
m
,
an
d
lo
n
g
ch
ar
g
i
n
g
d
u
r
atio
n
s
,
th
er
eb
y
en
h
an
cin
g
t
h
e
m
o
d
el'
s
g
en
er
ali
z
atio
n
.
Up
o
n
co
m
p
letio
n
o
f
p
r
e
p
r
o
ce
s
s
in
g
,
th
e
d
ataset
is
d
iv
id
ed
in
to
tr
a
in
in
g
,
v
alid
atio
n
,
an
d
test
s
u
b
s
ets,
g
u
ar
an
teein
g
s
tr
atif
icatio
n
ac
r
o
s
s
d
u
r
atio
n
ca
teg
o
r
ies.
T
h
e
p
r
ed
ictiv
e
f
o
u
n
d
atio
n
o
f
th
e
f
r
a
m
ewo
r
k
is
a
f
ee
d
-
f
o
r
war
d
DNN
with
n
u
m
er
o
u
s
h
id
d
en
lay
er
s
,
en
g
in
ee
r
ed
to
id
e
n
tify
n
o
n
li
n
ea
r
r
elatio
n
s
h
ip
s
b
etwe
en
in
p
u
t
p
ar
am
eter
s
an
d
ch
ar
g
in
g
d
u
r
atio
n
ca
teg
o
r
ies.
E
v
er
y
co
n
ce
ale
d
lay
er
d
o
es
a
lin
ea
r
tr
an
s
latio
n
o
f
its
in
p
u
ts
,
s
u
b
s
eq
u
en
tly
ap
p
ly
in
g
a
n
o
n
lin
ea
r
ac
tiv
atio
n
f
u
n
ctio
n
.
T
h
e
o
u
t
p
u
t o
f
a
h
id
d
en
lay
er
is
ca
lcu
lated
m
ath
e
m
atica
lly
as
(
3
)
.
(
)
=
(
)
(
−
1
)
+
(
)
,
(
)
=
(
(
)
)
(
3
)
W
h
er
e
(
)
is
th
e
weig
h
t
m
atr
ix
o
f
lay
er
,
(
)
is
th
e
b
ias
v
ec
t
o
r
,
a
n
d
(
−
1
)
is
th
e
in
p
u
t
f
r
o
m
th
e
p
r
ec
ed
in
g
lay
er
,
(
)
r
ep
r
esen
ts
th
e
p
r
e
-
ac
ti
v
atio
n
lin
ea
r
co
m
b
i
n
atio
n
,
w
h
er
ea
s
(
)
d
en
o
tes
th
e
p
o
s
t
-
ac
tiv
atio
n
o
u
tp
u
t.
T
h
e
s
elec
ted
ac
tiv
atio
n
f
u
n
cti
o
n
f
o
r
th
e
h
i
d
d
en
lay
er
s
is
th
e
r
ec
tifie
d
lin
ea
r
u
n
it
(
R
eL
U)
,
d
ef
in
ed
as
(
4
)
.
(
)
=
(
0
,
)
(
4
)
Fig
u
r
e
2
s
h
o
ws
th
at
t
h
e
DNN
p
r
o
ce
s
s
es
p
r
e
-
p
r
o
ce
s
s
ed
I
o
T
d
ata
v
ia
m
a
n
y
f
u
lly
lin
k
ed
h
id
d
en
lay
er
s
u
tili
s
in
g
R
eL
U
ac
t
iv
atio
n
,
b
atch
n
o
r
m
ali
z
atio
n
,
a
n
d
d
r
o
p
o
u
t te
ch
n
iq
u
es to
d
is
ce
r
n
co
m
p
le
x
p
atter
n
s
.
T
h
e
f
in
al
o
u
tp
u
t
la
y
er
u
s
es
s
o
f
tm
ax
ac
tiv
atio
n
to
class
if
y
ch
ar
g
in
g
d
u
r
atio
n
in
to
s
h
o
r
t,
m
ed
iu
m
,
o
r
l
o
n
g
class
if
icatio
n
s
,
f
ac
ilit
atin
g
p
r
ec
is
e
p
r
ed
ictio
n
s
f
o
r
E
V
c
h
ar
g
in
g
m
an
a
g
em
en
t
.
Fig
u
r
e
2
.
DNN
ar
ch
itectu
r
e
f
o
r
ch
ar
g
i
n
g
d
u
r
atio
n
p
r
ed
ictio
n
I
t
in
teg
r
ates
n
o
n
lin
ea
r
ity
a
n
d
m
itig
ates
s
atu
r
atio
n
p
r
o
b
lem
s
p
r
ev
alen
t
with
s
ig
m
o
i
d
o
r
h
y
p
er
b
o
lic
tan
g
en
t
f
u
n
ctio
n
s
.
T
o
en
h
a
n
ce
s
tab
ilit
y
an
d
co
n
v
er
g
e
n
ce
,
b
at
ch
n
o
r
m
ali
z
atio
n
m
ay
b
e
im
p
l
em
en
ted
af
ter
ea
c
h
lin
ea
r
tr
an
s
f
o
r
m
atio
n
,
s
tan
d
ar
d
i
z
in
g
in
ter
m
ed
iate
o
u
t
p
u
ts
p
r
io
r
to
ac
tiv
atio
n
.
T
o
p
r
e
v
en
t
o
v
er
f
itti
n
g
,
d
r
o
p
o
u
t
r
eg
u
lar
is
atio
n
is
u
tili
z
ed
,
r
an
d
o
m
ly
d
is
ab
lin
g
a
p
e
r
ce
n
tag
e
o
f
n
eu
r
o
n
es
d
u
r
in
g
tr
ain
in
g
to
e
n
ab
le
th
e
n
etwo
r
k
to
ac
q
u
ir
e
m
o
r
e
g
e
n
er
alis
ab
le
r
ep
r
esen
tatio
n
s
.
I
n
th
e
f
in
al
s
tag
e
o
f
th
e
n
etwo
r
k
,
a
s
o
f
tm
ax
lay
e
r
is
u
s
ed
to
p
r
o
v
id
e
a
p
r
o
b
ab
ilit
y
d
is
tr
ib
u
tio
n
o
v
er
th
e
th
r
ee
p
o
ten
tial
class
es
o
f
c
h
ar
g
in
g
d
u
r
atio
n
.
T
h
e
s
o
f
tm
ax
f
u
n
ctio
n
is
d
ef
i
n
ed
as
(
5
)
.
(
)
=
∑
=
1
(
5
)
W
h
er
e
is
th
e
lo
g
it
ass
o
ciate
d
with
class
,
wh
er
e
K
is
th
e
t
o
tal
n
u
m
b
e
r
o
f
class
es.
T
h
is
g
u
ar
an
tees
th
at
th
e
to
tal
o
f
p
r
o
b
ab
ilit
ies
eq
u
als
o
n
e
an
d
th
at
ea
ch
an
ticip
ated
o
u
tp
u
t
m
ay
b
e
u
n
d
er
s
to
o
d
as
th
e
p
r
o
b
ab
ilit
y
o
f
b
elo
n
g
in
g
to
a
ce
r
tain
class
.
T
h
e
aim
o
f
th
e
p
r
o
p
o
s
ed
tr
ain
in
g
f
r
am
ewo
r
k
is
to
m
in
im
i
z
e
th
e
ca
teg
o
r
ical
cr
o
s
s
-
en
tr
o
p
y
l
o
s
s
f
u
n
ctio
n
,
wh
ich
m
ea
s
u
r
es
th
e
d
is
p
ar
ity
b
etwe
en
p
r
ed
icted
class
p
r
o
b
a
b
ilit
ies
an
d
th
e
ac
tu
al
o
n
e
-
h
o
t e
n
co
d
ed
lab
els.
T
h
e
lo
s
s
f
u
n
ctio
n
is
r
ep
r
esen
ted
as
(
6
)
.
=
−
∑
=
1
l
og
(
̂
)
(
6
)
W
h
er
e
r
ep
r
esen
ts
th
e
g
r
o
u
n
d
tr
u
th
lab
el
f
o
r
class
an
d
̂
d
en
o
t
es
th
e
p
r
ed
icted
p
r
o
b
ab
ilit
y
f
o
r
th
at
ca
teg
o
r
y
.
B
y
o
p
tim
i
z
in
g
th
is
f
u
n
ctio
n
,
th
e
n
etwo
r
k
ac
q
u
ir
es
th
e
ca
p
ac
ity
to
en
h
an
ce
th
e
lik
elih
o
o
d
o
f
th
e
ac
c
u
r
ate
d
u
r
atio
n
class
.
T
h
e
ad
a
p
tiv
e
m
o
m
en
t
esti
m
atio
n
(
Ad
am
)
tech
n
iq
u
e
is
u
tili
z
ed
to
o
p
t
im
is
e
th
e
n
etwo
r
k
p
ar
am
eter
s
.
Ad
am
in
teg
r
ates
th
e
ad
v
an
tag
es
o
f
m
o
m
en
tu
m
an
d
R
MSPr
o
p
b
y
s
u
s
tain
in
g
r
u
n
n
in
g
av
e
r
ag
es
o
f
b
o
th
th
e
f
ir
s
t
in
s
tan
t
(
m
ea
n
)
an
d
th
e
s
ec
o
n
d
m
o
m
en
t
(
u
n
ce
n
te
r
ed
v
ar
ian
ce
)
o
f
g
r
ad
ien
ts
.
T
h
e
p
ar
am
eter
u
p
d
atin
g
r
u
le
f
o
r
Ad
am
is
p
r
esen
ted
as
(
7
)
.
+
1
=
−
∙
̂
√
̂
+
(
7
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ap
p
l Po
wer
E
n
g
I
SS
N:
2252
-
8
7
9
2
A
d
ee
p
lea
r
n
in
g
a
p
p
r
o
a
ch
fo
r
elec
tr
ic
ve
h
icle
b
a
tter
y
ch
a
r
g
in
g
…
(
Tu
mu
lu
r
i Ka
n
th
ima
th
i
)
1379
W
h
er
e
d
en
o
tes
th
e
m
o
d
el
p
a
r
am
eter
s
at
tim
e
s
tep
,
r
ep
r
esen
ts
th
e
lear
n
in
g
r
ate,
an
d
̂
s
ig
n
if
ies
th
e
v
ar
iab
le
̂
tim
e
s
tep
t,
̂
is
th
e
b
ias
-
co
r
r
ec
ted
f
ir
s
t
m
o
m
e
n
t
esti
m
atio
n
.
I
t
is
th
e
b
ias
-
co
r
r
ec
ted
s
ec
o
n
d
m
o
m
en
t
esti
m
ate,
an
d
is
a
n
eg
lig
i
b
le
co
n
s
tan
t
to
p
r
e
v
en
t
d
i
v
is
io
n
b
y
ze
r
o
.
T
h
is
ad
a
p
tiv
e
t
ec
h
n
iq
u
e
en
h
a
n
ce
s
co
n
v
er
g
en
ce
v
el
o
city
an
d
s
tab
ilit
y
r
elativ
e
to
co
n
v
en
tio
n
al
s
t
o
ch
asti
c
g
r
ad
ien
t
d
escen
t.
T
r
ain
in
g
is
co
n
d
u
cted
b
y
m
in
i
-
b
atch
lear
n
i
n
g
,
w
h
er
ein
th
e
d
ataset
is
p
ar
titi
o
n
ed
in
to
s
m
all
er
b
atch
es
to
ac
h
iev
e
a
c
o
m
p
r
o
m
is
e
b
e
twee
n
co
m
p
u
tin
g
ef
f
icien
c
y
an
d
co
n
v
er
g
e
n
ce
s
tab
ilit
y
.
B
ac
k
p
r
o
p
ag
atio
n
is
em
p
lo
y
ed
d
u
r
in
g
t
r
ain
in
g
to
c
alcu
late
th
e
g
r
a
d
ien
t
o
f
t
h
e
l
o
s
s
f
u
n
ctio
n
c
o
n
ce
r
n
in
g
ea
ch
p
a
r
am
eter
.
T
h
e
ch
ain
r
u
le
o
f
d
if
f
e
r
en
tiatio
n
is
u
tili
z
ed
s
eq
u
en
tially
,
tr
an
s
m
itti
n
g
th
e
m
is
tak
e
b
ac
k
war
d
th
r
o
u
g
h
th
e
n
etwo
r
k
to
f
ac
ilit
ate
th
e
ad
ju
s
tm
en
t
o
f
w
eig
h
ts
an
d
b
iases
in
ac
co
r
d
a
n
ce
with
th
e
Ad
am
o
p
tim
is
atio
n
alg
o
r
ith
m
.
E
a
r
ly
s
to
p
p
in
g
s
er
v
es
as
a
p
r
ec
au
ti
o
n
ar
y
m
ea
s
u
r
e,
h
altin
g
tr
ain
i
n
g
wh
en
v
alid
atio
n
l
o
s
s
d
o
es
n
o
t
im
p
r
o
v
e
o
v
er
a
ce
r
tain
n
u
m
b
er
o
f
ep
o
c
h
s
,
th
er
eb
y
av
er
tin
g
o
v
er
f
itti
n
g
.
Af
ter
co
m
p
letio
n
o
f
tr
ai
n
in
g
,
th
e
d
ep
lo
y
e
d
m
o
d
el
m
ay
r
e
ce
iv
e
r
ea
l
-
tim
e
I
o
T
d
ata
f
r
o
m
ch
ar
g
in
g
s
tatio
n
s
.
T
h
e
d
ata
is
s
u
b
jecte
d
to
th
e
i
d
en
tical
p
r
ep
ar
atio
n
p
r
o
ce
d
u
r
e
as
th
e
tr
ai
n
in
g
d
ata
b
ef
o
r
e
b
ei
n
g
in
p
u
t
in
to
th
e
tr
ain
ed
n
eu
r
al
n
etwo
r
k
.
T
h
e
m
o
d
el
g
en
e
r
ate
s
p
r
o
b
ab
ilit
y
v
alu
es
f
o
r
ea
ch
d
u
r
atio
n
class
,
an
d
th
e
class
with
th
e
h
ig
h
est
p
r
o
b
ab
ilit
y
is
d
esig
n
ated
as
th
e
p
r
o
jecte
d
ca
teg
o
r
y
.
T
h
ese
f
o
r
ec
asts
ar
e
co
n
v
ey
ed
to
b
o
th
E
V
d
r
i
v
er
s
an
d
ch
ar
g
in
g
s
tatio
n
o
wn
er
s
.
T
h
e
s
o
lu
tio
n
o
f
f
er
s
cu
s
to
m
er
s
ac
cu
r
ate
ch
ar
g
in
g
tim
e
esti
m
atio
n
s
to
en
h
an
ce
p
lan
n
in
g
an
d
c
o
n
v
e
n
ien
ce
,
wh
ile
en
ab
lin
g
o
p
er
ato
r
s
to
i
n
tellig
en
tly
s
ch
e
d
u
le
c
h
ar
g
i
n
g
s
lo
ts
,
o
p
tim
i
z
e
r
eso
u
r
ce
allo
ca
tio
n
,
an
d
f
o
r
ec
ast
in
f
r
a
s
tr
u
ctu
r
e
d
em
an
d
.
Fu
r
th
er
m
o
r
e,
d
is
cr
ep
an
cies
b
etwe
en
p
r
ed
icted
an
d
ac
tu
al
d
u
r
atio
n
s
ca
n
b
e
ex
am
in
e
d
to
i
d
en
tify
ab
n
o
r
m
alities
,
p
o
ten
tia
lly
in
d
icatin
g
b
atter
y
d
eter
io
r
a
tio
n
,
in
ef
f
icien
cies,
o
r
eq
u
ip
m
en
t
f
ailu
r
es,
t
h
e
r
eb
y
f
ac
ilit
atin
g
p
r
ed
ictiv
e
m
ai
n
ten
an
ce
ap
p
r
o
ac
h
es.
T
ab
le
1
illu
s
tr
ates th
e
p
r
o
p
o
s
ed
DNN,
d
etailin
g
th
e
u
n
its
,
ac
ti
v
atio
n
f
u
n
ctio
n
s
,
an
d
r
eg
u
lar
is
atio
n
p
r
o
ce
d
u
r
es
f
o
r
ea
ch
lay
er
,
illu
s
tr
atin
g
th
e
n
etwo
r
k
'
s
tr
an
s
f
o
r
m
atio
n
o
f
i
n
p
u
t
d
ata
to
p
r
ed
ict
s
h
o
r
t,
m
ed
iu
m
,
o
r
lo
n
g
ch
ar
g
in
g
p
e
r
i
o
d
s
.
T
ab
le
2
s
h
o
ws
ess
en
tial
b
atter
y
m
etr
ics
g
ath
er
ed
f
r
o
m
I
o
T
s
en
s
o
r
s
,
u
s
ed
f
o
r
tr
ain
in
g
an
d
test
in
g
th
e
DNN
f
o
r
d
u
r
atio
n
p
r
ed
ictio
n
.
T
ab
le
1
.
Pro
p
o
s
ed
DNN
ar
ch
it
ec
tu
r
e
p
ar
am
ete
r
s
La
y
e
r
U
n
i
t
s
A
c
t
i
v
a
t
i
o
n
R
e
g
u
l
a
r
i
z
a
t
i
o
n
I
n
p
u
t
64
–
–
H
i
d
d
e
n
1
1
2
8
R
e
LU
D
r
o
p
o
u
t
,
B
a
t
c
h
N
o
r
m
H
i
d
d
e
n
2
1
2
8
R
e
LU
D
r
o
p
o
u
t
,
B
a
t
c
h
N
o
r
m
H
i
d
d
e
n
3
64
R
e
LU
D
r
o
p
o
u
t
,
B
a
t
c
h
N
o
r
m
O
u
t
p
u
t
3
S
o
f
t
ma
x
–
T
ab
le
2
.
E
V
b
atter
y
p
a
r
am
eter
s
u
s
ed
f
o
r
DNN
tr
ain
in
g
an
d
test
in
g
P
a
r
a
me
t
e
r
D
e
scri
p
t
i
o
n
/
U
n
i
t
s
V
a
l
u
e
s
B
a
t
t
e
r
y
t
y
p
e
C
h
e
mi
s
t
r
y
o
f
t
h
e
b
a
t
t
e
r
y
Li
-
i
o
n
,
L
i
F
e
P
O
4
C
a
p
a
c
i
t
y
M
a
x
i
m
u
m
e
n
e
r
g
y
st
o
r
a
g
e
50
–
1
0
0
A
h
N
o
mi
n
a
l
v
o
l
t
a
g
e
R
a
t
e
d
v
o
l
t
a
g
e
3
.
7
V
S
t
a
t
e
-
of
-
c
h
a
r
g
e
(
S
O
C
)
C
u
r
r
e
n
t
c
h
a
r
g
e
l
e
v
e
l
0
–
1
0
0
%
C
h
a
r
g
i
n
g
c
y
c
l
e
s
N
u
mb
e
r
o
f
f
u
l
l
c
h
a
r
g
e
-
d
i
sc
h
a
r
g
e
c
y
c
l
e
s
50
–
5
0
0
B
a
t
t
e
r
y
t
e
m
p
Te
mp
e
r
a
t
u
r
e
d
u
r
i
n
g
c
h
a
r
g
i
n
g
20
–
4
5
°
C
D
e
g
r
a
d
a
t
i
o
n
r
a
t
e
B
a
t
t
e
r
y
a
g
i
n
g
e
f
f
e
c
t
(
%)
0
–
5%
Ef
f
i
c
i
e
n
c
y
En
e
r
g
y
e
f
f
i
c
i
e
n
c
y
(
%)
85
–
9
8
%
EV
mo
d
e
l
V
e
h
i
c
l
e
m
o
d
e
l
M
o
d
e
l
A
,
B
,
C
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
is
d
ataset
[
2
5
]
co
n
tain
s
in
f
o
r
m
atio
n
r
elate
d
to
th
e
c
h
ar
g
in
g
ch
a
r
ac
ter
is
tics
o
f
E
V
b
att
er
ies.
T
h
e
d
ataset
in
clu
d
es sev
er
al
asp
ec
t
s
in
f
lu
en
cin
g
b
atter
y
p
er
f
o
r
m
a
n
ce
,
d
eter
io
r
atio
n
,
an
d
c
h
ar
g
in
g
d
u
r
atio
n
,
as we
ll
as
th
e
o
b
jectiv
e
v
ar
iab
le
d
en
o
tin
g
th
e
ca
teg
o
r
is
atio
n
o
f
o
p
ti
m
al
ch
ar
g
in
g
d
u
r
atio
n
.
T
h
e
d
ataset
h
as
b
o
th
n
u
m
er
ical
an
d
ca
teg
o
r
y
attr
ib
u
tes,
d
esig
n
ed
f
o
r
an
aly
tical
o
r
p
r
ed
ictiv
e
p
u
r
p
o
s
es.
Op
tim
al
ch
ar
g
in
g
d
u
r
atio
n
class
ar
e:
˗
0
→
Sh
o
r
t (
≤
4
0
m
i
n
)
˗
1
→
Me
d
iu
m
(
≤
8
0
m
in
)
˗
2
→
L
o
n
g
(
>8
0
m
in
)
Fig
u
r
e
3
s
h
o
ws
th
e
co
r
r
elatio
n
b
etwe
en
b
atter
y
s
tate
-
of
-
ch
a
r
g
e
(
SOC
)
an
d
ef
f
icien
cy
,
d
e
m
o
n
s
tr
atin
g
th
at
ef
f
icien
cy
s
tay
s
co
n
tin
u
o
u
s
ly
elev
ated
th
r
o
u
g
h
o
u
t
d
i
v
er
s
e
SOC
lev
els,
s
ig
n
if
y
in
g
s
tead
y
p
er
f
o
r
m
an
c
e
o
v
e
r
v
ar
ied
ch
ar
g
e
lev
els.
Fig
u
r
e
4
illu
s
tr
ates
th
e
r
elatio
n
s
h
i
p
b
etwe
en
b
atter
y
SOC
an
d
ch
ar
g
in
g
cy
cles,
em
p
h
asi
z
in
g
th
e
v
ar
iety
i
n
u
s
ag
e
p
atter
n
s
an
d
d
e
m
o
n
s
tr
atin
g
h
o
w
v
ar
io
u
s
SOC
lev
els
r
el
ate
to
a
s
p
ec
tr
u
m
o
f
b
atter
y
cy
cles.
T
a
b
le
3
illu
s
tr
ates
th
e
d
is
tr
ib
u
tio
n
o
f
c
h
ar
g
i
n
g
d
u
r
atio
n
class
es,
s
h
o
win
g
a
s
lig
h
t
im
b
alan
ce
,
with
m
ed
iu
m
an
d
lo
n
g
d
u
r
atio
n
s
o
cc
u
r
r
in
g
m
o
r
e
f
r
e
q
u
en
tly
th
an
s
h
o
r
t
-
d
u
r
atio
n
d
ata.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
9
2
I
n
t J Ap
p
l Po
wer
E
n
g
,
Vo
l.
1
5
,
No
.
3
,
Sep
tem
b
er
20
2
6
:
1
3
7
5
-
1
3
8
5
1380
Fig
u
r
e
3
.
B
atter
y
ef
f
icien
cy
Fig
u
r
e
4
.
C
h
ar
g
in
g
c
y
cles
T
ab
le
3
.
Sam
p
le
c
o
u
n
t
p
er
ch
a
r
g
in
g
d
u
r
atio
n
class
C
l
a
s
s
C
o
u
n
t
P
e
r
c
e
n
t
a
g
e
(
%)
S
h
o
r
t
(
0
)
2
0
1
2
0
.
1
M
e
d
i
u
m (
1
)
4
0
4
4
0
.
4
Lo
n
g
(
2
)
3
9
5
3
9
.
5
To
t
a
l
1
0
0
0
1
0
0
I
n
th
is
ap
p
r
o
ac
h
,
r
a
n
d
o
m
o
v
e
r
s
am
p
lin
g
is
u
tili
z
ed
to
ad
d
r
e
s
s
clas
s
im
b
alan
ce
in
o
p
tim
al
ch
ar
g
in
g
d
u
r
atio
n
ca
teg
o
r
ies.
T
h
e
d
atas
et
in
itially
h
ad
a
f
ewe
r
n
u
m
b
er
o
f
s
am
p
les
in
t
h
e
"Sh
o
r
t"
c
lass
r
elativ
e
to
th
e
"M
ed
iu
m
"
a
n
d
"L
o
n
g
"
class
es,
p
o
ten
tially
b
iasi
n
g
th
e
DN
N
to
war
d
s
th
e
m
ajo
r
ity
class
es.
B
y
eq
u
ali
z
in
g
th
e
n
u
m
b
er
s
ac
r
o
s
s
all
ca
teg
o
r
ies,
th
e
m
o
d
el
ac
q
u
ir
es
p
atter
n
s
u
n
if
o
r
m
l
y
ac
r
o
s
s
all
clas
s
es.
T
h
is
en
s
u
r
es
d
ep
en
d
a
b
le
class
if
icatio
n
o
f
s
h
o
r
t,
m
ed
iu
m
,
an
d
lo
n
g
ch
ar
g
in
g
in
ter
v
als,
im
p
r
o
v
es
eq
u
ity
,
r
ed
u
ce
s
b
ias,
an
d
en
h
an
ce
s
th
e
o
v
er
all
r
o
b
u
s
tn
ess
o
f
th
e
p
r
o
p
o
s
ed
DNN
-
b
ased
p
r
e
d
ictiv
e
s
y
s
tem
.
T
ab
le
4
s
h
o
ws
th
e
m
eth
o
d
in
wh
ich
r
an
d
o
m
o
v
er
s
am
p
lin
g
e
q
u
ilib
r
ates
class
d
is
tr
ib
u
tio
n
to
4
0
4
f
o
r
ea
ch
ca
teg
o
r
y
.
Data
is
co
n
s
tan
tly
d
iv
i
d
ed
in
to
tr
ain
in
g
,
v
alid
atio
n
,
a
n
d
te
s
tin
g
s
ets
u
s
in
g
7
0
:1
5
:1
5
s
p
lit.
T
h
is
eq
u
itab
le
d
iv
is
io
n
en
a
b
les
th
e
DNN
to
lear
n
eq
u
ally
f
r
o
m
all
class
es,
m
iti
g
ates
b
ias
to
war
d
s
an
y
ce
r
tai
n
len
g
th
,
an
d
f
ac
ilit
ates
d
ep
en
d
ab
le
ass
ess
m
en
t
o
f
m
o
d
el
ef
f
icac
y
o
n
n
o
v
el
d
ata
wh
ile
p
r
eser
v
in
g
class
co
n
s
is
ten
cy
ac
r
o
s
s
all
s
u
b
s
ets.
T
ab
le
4
.
B
alan
ce
d
d
ataset
s
p
lit
u
s
in
g
r
an
d
o
m
o
v
er
s
am
p
lin
g
C
l
a
s
s
O
r
i
g
i
n
a
l
c
o
u
n
t
A
f
t
e
r
r
a
n
d
o
m
o
v
e
r
sam
p
l
i
n
g
c
o
u
n
t
Tr
a
i
n
(
7
0
%)
V
a
l
i
d
a
t
i
o
n
(
1
5
%)
Te
st
(
1
5
%)
S
h
o
r
t
(
0
)
2
0
1
4
0
4
2
8
3
61
60
M
e
d
i
u
m (
1
)
4
0
4
4
0
4
2
8
3
61
60
Lo
n
g
(
2
)
3
9
5
4
0
4
2
8
3
61
60
To
t
a
l
1
0
0
0
1
2
1
2
8
4
9
1
8
3
1
8
0
Fig
u
r
e
5
illu
s
tr
ates
th
e
DNN
c
o
n
f
u
s
io
n
m
atr
ix
,
wh
ich
in
d
icate
s
a
h
ig
h
lev
el
o
f
ac
cu
r
ac
y
in
c
lass
if
y
in
g
E
V
ch
ar
g
i
n
g
p
er
io
d
s
.
Am
o
n
g
6
0
s
am
p
les
p
er
test
class
,
o
n
ly
a
lim
ited
n
u
m
b
e
r
o
f
m
is
c
lass
if
icatio
n
s
wer
e
o
b
s
er
v
ed
:
two
s
h
o
r
t
s
ess
io
n
s
wer
e
p
r
ed
icted
as
m
e
d
iu
m
o
r
l
en
g
th
y
,
wh
ile
o
n
e
m
ed
iu
m
s
ess
io
n
was
f
o
r
ec
asted
as
s
h
o
r
t.
T
h
is
s
u
g
g
ests
th
at
o
v
er
lap
p
i
n
g
b
atter
y
s
tates
o
r
an
alo
g
o
u
s
en
v
ir
o
n
m
en
tal
f
a
cto
r
s
in
ter
m
itten
tly
in
f
lu
en
ce
class
d
if
f
er
en
c
e.
T
h
e
m
o
d
el
ac
cu
r
ately
p
r
e
d
icted
lo
n
g
-
d
u
r
atio
n
s
ess
io
n
s
,
d
em
o
n
s
tr
ati
n
g
its
r
esil
ien
ce
an
d
d
e
p
en
d
a
b
ilit
y
in
d
if
f
e
r
en
ti
atin
g
ch
ar
g
i
n
g
tim
e
g
r
o
u
p
s
.
T
h
e
DNN
co
n
f
u
s
io
n
m
atr
ix
d
e
m
o
n
s
tr
ates
ex
ce
p
tio
n
al
class
if
icatio
n
ac
cu
r
ac
y
,
with
1
7
7
o
f
1
8
0
s
am
p
les
ac
cu
r
ately
p
r
ed
icted
.
T
h
er
e
wer
e
o
n
ly
th
r
ee
m
is
class
if
icatio
n
s
:
two
in
th
e
s
h
o
r
t
ca
teg
o
r
y
an
d
o
n
e
in
th
e
m
ed
iu
m
ca
teg
o
r
y
,
wh
ils
t
th
e
lo
n
g
d
u
r
atio
n
s
attain
ed
f
lawless
ac
cu
r
ac
y
.
T
h
is
illu
s
tr
ates
th
e
m
o
d
el'
s
s
tab
ilit
y
,
h
ig
h
g
en
er
alis
atio
n
,
an
d
d
e
p
en
d
a
b
l
e
p
er
f
o
r
m
an
ce
in
f
o
r
ec
asti
n
g
o
p
tim
al
E
V
b
atter
y
c
h
ar
g
in
g
p
er
io
d
s
ac
r
o
s
s
all
ca
teg
o
r
ies.
Fig
u
r
e
6
illu
s
tr
ates
th
e
DNN
ac
cu
r
ac
y
g
r
ap
h
,
wh
ich
d
em
o
n
s
tr
ates
a
co
n
s
is
ten
t
r
is
e
in
tr
ain
in
g
ac
cu
r
ac
y
th
r
o
u
g
h
o
u
t
e
p
o
ch
s
,
with
v
alid
atio
n
ac
cu
r
ac
y
clo
s
el
y
alig
n
in
g
,
s
ig
n
if
y
i
n
g
r
o
b
u
s
t
lear
n
in
g
,
co
n
v
er
g
en
ce
,
a
n
d
m
i
n
im
al
o
v
e
r
f
itti
n
g
.
Fig
u
r
e
7
illu
s
tr
ates
th
e
lo
s
s
g
r
ap
h
,
d
em
o
n
s
tr
atin
g
a
c
o
n
tin
u
o
u
s
d
ec
r
ea
s
e
in
b
o
th
tr
ain
in
g
an
d
v
alid
atio
n
lo
s
s
ac
r
o
s
s
th
e
ep
o
ch
s
,
s
ig
n
if
y
in
g
s
u
cc
ess
f
u
l
lear
n
in
g
,
h
ig
h
co
n
v
er
g
en
ce
,
lo
w
o
v
er
f
itti
n
g
,
an
d
r
o
b
u
s
t
g
en
er
al
is
atio
n
o
f
th
e
DNN
m
o
d
el.
T
h
e
DNN
ac
cu
r
ac
y
g
r
a
p
h
in
d
icate
s
a
co
n
tin
u
o
u
s
in
cr
ea
s
e
in
tr
ain
in
g
ac
cu
r
ac
y
,
ac
h
iev
i
n
g
9
8
.
8
9
%
at
ep
o
ch
1
0
0
,
wh
ile
v
alid
atio
n
a
cc
u
r
ac
y
s
tan
d
s
at
9
8
.
3
%.
T
h
is
s
ig
n
if
ies
ef
f
icien
t
lear
n
in
g
,
r
o
b
u
s
t
co
n
v
er
g
e
n
ce
,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ap
p
l Po
wer
E
n
g
I
SS
N:
2252
-
8
7
9
2
A
d
ee
p
lea
r
n
in
g
a
p
p
r
o
a
ch
fo
r
elec
tr
ic
ve
h
icle
b
a
tter
y
ch
a
r
g
in
g
…
(
Tu
mu
lu
r
i Ka
n
th
ima
th
i
)
1381
an
d
m
in
im
al
o
v
e
r
f
itti
n
g
,
illu
s
tr
atin
g
th
e
m
o
d
el'
s
ca
p
ac
ity
to
g
en
er
alis
e
ef
f
ec
tiv
ely
a
n
d
ac
cu
r
ately
ca
teg
o
r
i
z
e
E
V
ch
ar
g
i
n
g
d
u
r
atio
n
s
ac
r
o
s
s
all
ca
teg
o
r
ies.
T
h
e
DNN
lo
s
s
g
r
ap
h
in
d
icate
s
t
h
at
th
e
tr
ain
i
n
g
lo
s
s
d
ec
r
ea
s
es
to
0
.
0
1
1
a
n
d
th
e
v
alid
atio
n
lo
s
s
to
0
.
0
1
7
at
th
e
1
0
0
th
ep
o
c
h
.
T
h
is
co
n
s
is
ten
t
r
ed
u
ctio
n
s
ig
n
if
ies
ex
ce
llen
t
lear
n
in
g
,
h
ig
h
co
n
v
er
g
en
ce
,
a
n
d
s
m
all
o
v
er
f
itti
n
g
,
v
alid
atin
g
t
h
e
m
o
d
el'
s
s
tab
ilit
y
an
d
d
ep
en
d
ab
le
g
en
er
ali
z
atio
n
f
o
r
p
r
ec
is
e
ca
teg
o
r
i
z
atio
n
o
f
E
V
b
atter
y
ch
ar
g
in
g
tim
es.
Fig
u
r
e
8
illu
s
tr
ates
a
co
m
p
ar
is
o
n
a
cr
o
s
s
KNN,
Naiv
e
B
ay
es
[
2
6
]
,
an
d
DNN,
in
d
icatin
g
th
at
th
e
p
r
o
p
o
s
ed
DNN
ac
h
iev
es
th
e
h
ig
h
est
ac
cu
r
ac
y
in
a
d
d
itio
n
to
b
alan
ce
d
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
-
s
co
r
e
.
Fig
u
r
e
5
.
DNN
co
n
f
u
s
io
n
m
atr
ix
f
o
r
E
V
ch
ar
g
in
g
class
if
icatio
n
Fig
u
r
e
6
.
Acc
u
r
ac
y
o
f
DNN
o
v
er
ep
o
c
h
s
Fig
u
r
e
7
.
DNN
m
o
d
el
lo
s
s
co
n
v
er
g
en
ce
Fig
u
r
e
8
.
C
o
m
p
a
r
is
o
n
o
f
ML
m
o
d
els p
er
f
o
r
m
an
ce
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
9
2
I
n
t J Ap
p
l Po
wer
E
n
g
,
Vo
l.
1
5
,
No
.
3
,
Sep
tem
b
er
20
2
6
:
1
3
7
5
-
1
3
8
5
1382
T
h
e
DNN
m
o
d
el
attain
s
an
o
v
er
all
ac
cu
r
ac
y
o
f
9
8
.
8
9
%,
with
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
-
s
co
r
e
at
9
8
.
3
3
%,
ex
ce
ed
in
g
class
ic
m
ac
h
in
e
lea
r
n
in
g
tech
n
iq
u
es
in
clu
d
e
KNN
(
9
8
%
ac
cu
r
a
cy
)
a
n
d
n
ai
v
e
b
a
y
es
(
9
3
%
ac
cu
r
ac
y
)
.
T
h
is
illu
s
tr
ates
th
e
DNN
's
ex
c
ep
tio
n
al
ca
p
ac
ity
to
d
is
ce
r
n
n
o
n
lin
ea
r
an
d
in
tr
icate
co
r
r
elatio
n
s
am
o
n
g
s
ev
er
al
I
o
T
-
en
a
b
led
f
ac
to
r
s
in
f
lu
en
cin
g
b
atter
y
p
e
r
f
o
r
m
an
ce
.
Sh
o
r
t
c
h
ar
g
in
g
s
ess
io
n
s
s
h
o
w
m
in
im
al
p
r
ed
ictio
n
er
r
o
r
s
,
b
u
t
m
ed
iu
m
an
d
ex
ten
d
e
d
s
ess
io
n
s
d
em
o
n
s
tr
ate
co
n
s
id
er
ab
l
e
v
ar
iab
ilit
y
attr
ib
u
tab
le
to
u
s
er
b
eh
av
io
u
r
.
T
h
e
in
teg
r
atio
n
o
f
I
o
T
d
ata
im
p
r
o
v
es
p
er
f
o
r
m
an
ce
.
T
h
is
p
latf
o
r
m
en
h
an
ce
s
s
ch
ed
u
lin
g
,
m
in
im
i
s
es
wai
t
tim
e
s
,
an
d
f
ac
ilit
ates
p
r
ed
ictiv
e
m
ain
ten
a
n
ce
f
o
r
ef
f
ec
tiv
e
E
V
ch
ar
g
in
g
s
y
s
tem
s
.
T
h
e
r
esear
ch
u
tili
z
es
d
ata
f
r
o
m
a
s
in
g
le
s
o
u
r
ce
(
Kag
g
le)
,
wh
ich
m
a
y
n
o
t
in
clu
d
e
all
elec
tr
ic
v
eh
icle
t
y
p
es
o
r
ac
tu
al
en
v
ir
o
n
m
en
tal
co
n
d
itio
n
s
.
T
h
is
m
ay
g
en
er
ate
b
ias in
f
o
r
ec
asts
in
u
n
r
ep
r
esen
ted
ci
r
cu
m
s
tan
ce
s
.
4.
CO
NCLU
SI
O
N
T
h
is
p
ap
er
p
r
esen
ts
a
DL
f
r
a
m
ewo
r
k
u
s
in
g
I
o
T
an
d
DNN
t
o
f
o
r
ec
ast
o
p
tim
al
ch
ar
g
i
n
g
ti
m
es
f
o
r
E
V
b
atter
ies.
T
h
e
s
y
s
tem
e
f
f
icien
t
ly
co
m
b
in
es
p
r
e
p
r
o
ce
s
s
in
g
,
f
e
atu
r
e
an
al
y
s
is
,
an
d
b
alan
ce
d
d
ataset
m
an
ag
em
en
t
u
s
in
g
r
an
d
o
m
o
v
e
r
s
am
p
lin
g
,
p
r
o
v
id
i
n
g
e
q
u
al
r
e
p
r
esen
tatio
n
o
f
ea
ch
class
.
DNN
h
as
en
h
an
ce
d
p
er
f
o
r
m
an
ce
r
elativ
e
to
co
n
v
en
tio
n
al
ML
m
o
d
els
s
u
ch
KNN
an
d
Naiv
e
B
ay
es,
with
a
tr
ain
in
g
ac
c
u
r
a
cy
o
f
9
8
.
8
9
%,
with
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
-
s
co
r
e
o
v
er
9
8
.
3
3
%.
T
h
e
tr
ain
in
g
an
d
v
alid
atio
n
ac
c
u
r
ac
y
a
n
d
lo
s
s
cu
r
v
es
d
em
o
n
s
tr
ate
s
ig
n
if
ican
t
co
n
v
er
g
en
ce
,
litt
le
o
v
er
f
itti
n
g
,
a
n
d
h
ig
h
g
en
e
r
ali
z
atio
n
to
u
n
s
ee
n
d
ata.
T
h
e
s
tu
d
y
o
f
th
e
co
n
f
u
s
io
n
m
atr
ix
f
u
r
th
e
r
s
u
b
s
tan
tiates
th
e
m
o
d
el'
s
d
ep
en
d
ab
ilit
y
,
r
ev
e
alin
g
o
n
ly
a
lim
ited
n
u
m
b
e
r
o
f
m
is
class
if
icat
io
n
s
am
o
n
g
th
e
s
h
o
r
t,
m
e
d
iu
m
,
an
d
lo
n
g
c
h
ar
g
in
g
tim
e
ca
teg
o
r
i
es.
T
h
e
p
r
o
p
o
s
ed
f
r
am
ewo
r
k
'
s
ca
p
ac
ity
to
id
en
tif
y
co
m
p
lex
n
o
n
lin
ea
r
c
o
r
r
elatio
n
s
in
E
V
b
atter
y
d
ata
f
ac
ilit
ates
p
r
ec
is
e
an
d
r
eliab
le
p
r
ed
ictio
n
s
o
f
c
h
ar
g
in
g
tim
es,
h
en
ce
im
p
r
o
v
i
n
g
b
atter
y
e
f
f
ic
ien
cy
an
d
u
s
er
ex
p
e
r
ien
ce
.
T
h
e
I
o
T
-
e
n
ab
led
DNN
d
eliv
er
s
p
r
ec
is
e
f
o
r
ec
asts
o
f
ch
ar
g
e
d
u
r
atio
n
s
,
en
ab
lin
g
ef
f
icien
t sch
ed
u
lin
g
an
d
p
r
e
d
ictiv
e
m
ain
ten
an
ce
.
Fu
tu
r
e
r
esear
c
h
s
h
o
u
ld
u
s
e
m
u
lti
-
s
o
u
r
ce
in
f
o
r
m
atio
n
,
in
v
esti
g
a
te
ad
ap
tiv
e
ch
a
r
g
in
g
tech
n
iq
u
es,
an
d
ac
co
u
n
t
f
o
r
g
r
id
an
d
r
en
ewa
b
le
e
n
er
g
y
lim
itatio
n
s
to
d
ev
elo
p
m
o
r
e
in
tellig
en
t E
V
ch
ar
g
in
g
s
y
s
tem
s
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
Au
th
o
r
s
s
tate
n
o
f
u
n
d
in
g
in
v
o
lv
ed
.
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
T
h
is
jo
u
r
n
al
u
s
es
th
e
C
o
n
tr
ib
u
to
r
R
o
les
T
ax
o
n
o
m
y
(
C
R
ed
iT)
to
r
ec
o
g
n
ize
in
d
iv
id
u
al
au
th
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
th
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
llab
o
r
atio
n
.
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
T
u
m
u
lu
r
i K
a
n
th
im
ath
i
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Ad
h
im
o
o
lam
Sair
am
✓
✓
✓
✓
Du
r
air
aj
C
h
an
d
r
a
k
ala
✓
✓
Mo
o
r
th
y
R
ad
h
ik
a
✓
✓
✓
B
ich
ag
al
Sh
ad
ak
s
h
ar
ap
p
a
✓
✓
✓
✓
Pit
ch
ai
J
o
h
n
B
r
itto
✓
✓
✓
✓
Min
ak
s
h
i San
ad
h
y
a
✓
✓
B
alasu
b
r
am
an
ian
Su
g
an
y
a
✓
✓
✓
C
h
elliah
Srin
iv
asan
✓
✓
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
Au
th
o
r
s
s
tate
n
o
co
n
f
lict o
f
in
t
er
est.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ap
p
l Po
wer
E
n
g
I
SS
N:
2252
-
8
7
9
2
A
d
ee
p
lea
r
n
in
g
a
p
p
r
o
a
ch
fo
r
elec
tr
ic
ve
h
icle
b
a
tter
y
ch
a
r
g
in
g
…
(
Tu
mu
lu
r
i Ka
n
th
ima
th
i
)
1383
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
ata
t
h
at
s
u
p
p
o
r
t
t
h
e
f
in
d
in
g
s
o
f
th
is
s
tu
d
y
a
r
e
av
ailab
l
e
f
r
o
m
th
e
co
r
r
esp
o
n
d
in
g
a
u
th
o
r
,
[
T
K]
,
u
p
o
n
r
ea
s
o
n
ab
le
r
eq
u
est.
RE
F
E
R
E
NC
E
S
[
1
]
Y
.
A
.
S
u
l
t
a
n
,
A
.
A
.
El
a
d
l
,
M
.
A
.
H
a
ss
a
n
,
a
n
d
S
.
A
.
G
a
m
e
l
,
“
E
n
h
a
n
c
i
n
g
e
l
e
c
t
r
i
c
v
e
h
i
c
l
e
b
a
t
t
e
r
y
l
i
f
e
s
p
a
n
:
i
n
t
e
g
r
a
t
i
n
g
a
c
t
i
v
e
b
a
l
a
n
c
i
n
g
a
n
d
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
f
o
r
p
r
e
c
i
se
R
U
L
e
s
t
i
m
a
t
i
o
n
,
”
S
c
i
e
n
t
i
f
i
c
R
e
p
o
r
t
s
,
v
o
l
.
1
5
,
n
o
.
1
,
2
0
2
5
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
5
9
8
-
0
2
4
-
8
2
7
7
8
-
w.
[
2
]
Y
.
Li
,
Z
.
Zh
a
n
g
,
a
n
d
Q
.
X
i
n
g
,
“
R
e
a
l
-
t
i
me
o
n
l
i
n
e
c
h
a
r
g
i
n
g
c
o
n
t
r
o
l
o
f
e
l
e
c
t
r
i
c
v
e
h
i
c
l
e
c
h
a
r
g
i
n
g
s
t
a
t
i
o
n
b
a
se
d
o
n
a
mu
l
t
i
-
a
g
e
n
t
d
e
e
p
r
e
i
n
f
o
r
c
e
me
n
t
l
e
a
r
n
i
n
g
,
”
E
n
e
r
g
y
,
v
o
l
.
3
1
9
,
p
.
1
3
5
0
9
5
,
M
a
r
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
n
e
r
g
y
.
2
0
2
5
.
1
3
5
0
9
5
.
[
3
]
G
.
A
n
i
l
k
u
mar
,
N
.
R
a
ma
k
r
i
s
h
n
a
,
K
.
S
u
r
e
sh
,
S
.
S
r
e
e
d
e
v
i
,
G
.
J
a
sw
a
n
t
h
k
u
m
a
r
,
a
n
d
P
.
S
.
B
r
a
h
m
a
n
a
n
d
a
m,
“
R
e
v
o
l
u
t
i
o
n
i
z
i
n
g
EV
b
a
t
t
e
r
y
man
a
g
e
me
n
t
t
h
r
o
u
g
h
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
-
a
c
a
s
e
st
u
d
y
,
”
AI
P
C
o
n
f
e
r
e
n
c
e
Pro
c
e
e
d
i
n
g
s
,
v
o
l
.
3
2
9
8
,
n
o
.
1
,
2
0
2
5
,
d
o
i
:
1
0
.
1
0
6
3
/
5
.
0
2
7
9
3
5
7
.
[
4
]
W
.
H
u
a
n
g
,
T
.
Z
h
o
u
,
J
.
M
a
,
a
n
d
X
.
C
h
e
n
,
“
A
n
e
n
sem
b
l
e
m
o
d
e
l
b
a
s
e
d
o
n
f
u
si
o
n
o
f
m
u
l
t
i
p
l
e
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms
f
o
r
r
e
mai
n
i
n
g
u
sef
u
l
l
i
f
e
p
r
e
d
i
c
t
i
o
n
o
f
l
i
t
h
i
u
m
b
a
t
t
e
r
y
i
n
e
l
e
c
t
r
i
c
v
e
h
i
c
l
e
s
,
”
I
n
n
o
v
a
t
i
o
n
s
i
n
Ap
p
l
i
e
d
En
g
i
n
e
e
r
i
n
g
a
n
d
T
e
c
h
n
o
l
o
g
y
,
p
p
.
1
–
1
2
,
M
a
r
.
2
0
2
5
,
d
o
i
:
1
0
.
6
2
8
3
6
/
i
a
e
t
.
v
4
i
1
.
3
1
9
.
[
5
]
V
.
S
.
N
a
r
e
s
h
,
G
.
V
.
N
.
S
.
R
.
R
a
t
n
a
k
a
r
a
R
a
o
,
a
n
d
D
.
V
.
N
.
P
r
a
b
h
a
k
a
r
,
“
P
r
e
d
i
c
t
i
v
e
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
i
n
o
p
t
i
mi
z
i
n
g
t
h
e
p
e
r
f
o
r
ma
n
c
e
o
f
e
l
e
c
t
r
i
c
v
e
h
i
c
l
e
b
a
t
t
e
r
i
e
s
:
t
e
c
h
n
i
q
u
e
s,
c
h
a
l
l
e
n
g
e
s
,
a
n
d
s
o
l
u
t
i
o
n
s,”
W
i
l
e
y
I
n
t
e
r
d
i
s
c
i
p
l
i
n
a
ry
R
e
v
i
e
w
s:
D
a
t
a
M
i
n
i
n
g
a
n
d
K
n
o
w
l
e
d
g
e
D
i
sco
v
e
r
y
,
v
o
l
.
1
4
,
n
o
.
5
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
0
2
/
w
i
d
m
.
1
5
3
9
.
[
6
]
K
.
D
a
s,
R
.
K
u
m
a
r
,
a
n
d
A
.
K
r
i
s
h
n
a
,
“
A
n
a
l
y
z
i
n
g
e
l
e
c
t
r
i
c
v
e
h
i
c
l
e
b
a
t
t
e
r
y
h
e
a
l
t
h
p
e
r
f
o
r
ma
n
c
e
u
si
n
g
su
p
e
r
v
i
se
d
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
Re
n
e
w
a
b
l
e
a
n
d
S
u
st
a
i
n
a
b
l
e
En
e
rg
y
R
e
v
i
e
w
s
,
v
o
l
.
1
8
9
,
p
.
1
1
3
9
6
7
,
J
a
n
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
r
ser.
2
0
2
3
.
1
1
3
9
6
7
.
[
7
]
V
.
S
r
i
v
i
d
h
y
a
,
S
.
G
o
w
r
i
sw
a
r
i
,
N
.
V
.
A
n
t
o
n
y
,
S
.
M
u
r
u
g
a
n
,
K
.
A
n
i
t
h
a
,
a
n
d
M
.
R
a
j
mo
h
a
n
,
“
O
p
t
i
mi
z
i
n
g
e
l
e
c
t
r
i
c
v
e
h
i
c
l
e
c
h
a
r
g
i
n
g
n
e
t
w
o
r
k
s
u
s
i
n
g
c
l
u
s
t
e
r
i
n
g
t
e
c
h
n
i
q
u
e
,
”
i
n
2
0
2
4
2
n
d
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
C
o
m
p
u
t
e
r,
C
o
m
m
u
n
i
c
a
t
i
o
n
a
n
d
C
o
n
t
ro
l
(
I
C
4
)
,
I
EEE,
F
e
b
.
2
0
2
4
,
p
p
.
1
–
5
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
4
5
7
4
3
4
.
2
0
2
4
.
1
0
4
8
6
4
2
2
.
[
8
]
N
.
N
a
v
e
e
n
k
u
mar,
V
.
S
r
i
d
e
v
i
,
R
.
B
h
a
r
a
t
h
i
,
N
.
M
i
s
h
r
a
,
S
.
M
u
r
u
g
a
n
,
a
n
d
S
.
V
e
l
m
u
r
u
g
a
n
,
“
C
l
o
u
d
-
i
n
t
e
g
r
a
t
e
d
c
l
e
a
n
f
u
e
l
g
e
n
e
r
a
t
i
o
n
f
o
r
so
l
a
r
-
h
y
d
r
o
g
e
n
p
r
o
d
u
c
t
i
o
n
w
i
t
h
w
i
r
e
l
e
ss
sen
s
o
r
n
e
t
w
o
r
k
s
,
”
i
n
7
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
I
n
v
e
n
t
i
v
e
C
o
m
p
u
t
a
t
i
o
n
T
e
c
h
n
o
l
o
g
i
e
s,
I
C
I
C
T
2
0
2
4
,
2
0
2
4
,
p
p
.
1
6
1
7
–
1
6
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
I
C
T6
0
1
5
5
.
2
0
2
4
.
1
0
5
4
4
6
5
9
.
[
9
]
C
.
Tr
i
p
p
-
B
a
r
b
a
,
J.
A
.
A
g
u
i
l
a
r
-
C
a
l
d
e
r
ó
n
,
L.
U
r
q
u
i
z
a
-
A
g
u
i
a
r
,
A
.
Z
a
l
d
í
v
a
r
-
C
o
l
a
d
o
,
a
n
d
A
.
R
a
m
í
r
e
z
-
N
o
r
i
e
g
a
,
“
A
s
y
st
e
mat
i
c
ma
p
p
i
n
g
st
u
d
y
o
n
st
a
t
e
e
st
i
mat
i
o
n
t
e
c
h
n
i
q
u
e
s
f
o
r
l
i
t
h
i
u
m
-
i
o
n
b
a
t
t
e
r
i
e
s
i
n
e
l
e
c
t
r
i
c
v
e
h
i
c
l
e
s,
”
W
o
r
l
d
E
l
e
c
t
ri
c
Ve
h
i
c
l
e
J
o
u
rn
a
l
,
v
o
l
.
1
6
,
n
o
.
2
,
2
0
2
5
,
d
o
i
:
1
0
.
3
3
9
0
/
w
e
v
j
1
6
0
2
0
0
5
7
.
[
1
0
]
H
.
P
.
B
h
u
p
a
t
h
i
a
n
d
S
.
C
h
i
n
t
a
,
“
A
I
-
p
o
w
e
r
e
d
e
f
f
i
c
i
e
n
c
y
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s
f
o
r
EV
b
a
t
t
e
r
y
c
h
a
r
g
i
n
g
,
”
Ar
t
i
c
l
e
i
n
ES
P
J
o
u
r
n
a
l
o
f
En
g
i
n
e
e
r
i
n
g
&
T
e
c
h
n
o
l
o
g
y
A
d
v
a
n
c
e
m
e
n
t
s
,
2
0
2
5
,
d
o
i
:
1
0
.
5
6
4
7
2
/
2
5
8
3
9
2
3
3
/
I
JA
S
T
-
V
2
I
3
P
1
0
7
.
[
1
1
]
K
.
S
u
j
i
t
,
K
.
C
.
R
a
m
a
sw
a
m
y
,
S
.
R
.
M
a
t
h
i
y
a
l
a
g
a
n
,
J
.
G
i
r
i
,
a
n
d
M
.
K
a
n
a
n
,
“
A
n
e
f
f
i
c
i
e
n
t
b
a
t
t
e
r
y
ma
n
a
g
e
m
e
n
t
s
y
st
e
m
f
o
r
e
l
e
c
t
r
i
c
v
e
h
i
c
l
e
s
u
si
n
g
I
o
T
&
b
l
o
c
k
c
h
a
i
n
,
”
R
e
su
l
t
s
i
n
En
g
i
n
e
e
r
i
n
g
,
v
o
l
.
2
7
,
p
.
1
0
6
2
8
4
,
S
e
p
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
r
i
n
e
n
g
.
2
0
2
5
.
1
0
6
2
8
4
.
[
1
2
]
A
.
Za
i
n
e
b
,
M
.
V
i
j
a
y
a
sa
n
t
h
i
,
a
n
d
P
.
N
.
M
a
n
d
a
d
i
,
“
F
u
z
z
y
l
o
g
i
c
c
o
n
t
r
o
l
l
e
r
b
a
s
e
d
c
h
a
r
g
i
n
g
a
n
d
d
i
s
c
h
a
r
g
i
n
g
c
o
n
t
r
o
l
f
o
r
b
a
t
t
e
r
y
i
n
EV
a
p
p
l
i
c
a
t
i
o
n
s,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
E
l
e
c
t
r
i
c
a
l
a
n
d
El
e
c
t
r
o
n
i
c
s
R
e
sea
r
c
h
,
v
o
l
.
1
2
,
n
o
.
1
,
p
p
.
1
–
7
,
Jan
.
2
0
2
4
,
d
o
i
:
1
0
.
3
7
3
9
1
/
i
j
e
e
r
.
1
2
0
1
0
1
.
[
1
3
]
W
.
A
c
h
a
r
i
y
a
v
i
r
i
y
a
e
t
a
l
.
,
“
Est
i
ma
t
i
n
g
e
n
e
r
g
y
c
o
n
s
u
mp
t
i
o
n
o
f
b
a
t
t
e
r
y
e
l
e
c
t
r
i
c
v
e
h
i
c
l
e
s
u
s
i
n
g
v
e
h
i
c
l
e
s
e
n
so
r
d
a
t
a
a
n
d
mac
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
e
s,
”
E
n
e
rg
i
e
s
,
v
o
l
.
1
6
,
n
o
.
1
7
,
p
.
6
3
5
1
,
S
e
p
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
e
n
1
6
1
7
6
3
5
1
.
[
1
4
]
T.
L
e
h
m
a
n
n
a
n
d
F
.
W
e
i
ß
,
“
L
i
t
h
i
u
m
-
i
o
n
b
a
t
t
e
r
y
a
g
i
n
g
a
n
a
l
y
s
i
s
o
f
a
n
e
l
e
c
t
r
i
c
v
e
h
i
c
l
e
f
l
e
e
t
u
si
n
g
a
t
a
i
l
o
r
e
d
n
e
u
r
a
l
n
e
t
w
o
r
k
st
r
u
c
t
u
r
e
,
”
Ap
p
l
i
e
d
S
c
i
e
n
c
e
s
,
v
o
l
.
1
3
,
n
o
.
7
,
p
.
4
4
4
8
,
M
a
r
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
3
0
7
4
4
4
8
.
[
1
5
]
K
.
K
o
i
r
a
l
a
a
n
d
S
h
a
b
b
i
r
u
d
d
i
n
,
“
O
p
t
i
mal
se
l
e
c
t
i
o
n
o
f
su
s
t
a
i
n
a
b
l
e
b
a
t
t
e
r
y
su
p
p
l
i
e
r
f
o
r
e
l
e
c
t
r
i
c
v
e
h
i
c
l
e
b
a
t
t
e
r
y
s
w
a
p
p
i
n
g
s
t
a
t
i
o
n
,
”
En
e
r
g
y
S
o
u
r
c
e
s
,
Pa
r
t
A:
Re
c
o
v
e
r
y
,
U
t
i
l
i
za
t
i
o
n
,
a
n
d
E
n
v
i
ro
n
m
e
n
t
a
l
Ef
f
e
c
t
s
,
v
o
l
.
4
5
,
n
o
.
1
,
p
p
.
2
2
0
6
–
2
2
2
7
,
A
p
r
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
8
0
/
1
5
5
6
7
0
3
6
.
2
0
2
3
.
2
1
8
5
7
0
2
.
[
1
6
]
A
.
K
a
r
t
h
i
k
e
y
a
n
,
N
.
S
.
V
a
n
i
t
h
a
,
T.
M
e
e
n
a
k
s
h
i
,
R
.
R
a
m
a
n
i
,
a
n
d
S
.
M
u
r
u
g
a
n
,
“
El
e
c
t
r
i
c
v
e
h
i
c
l
e
b
a
t
t
e
r
y
c
h
a
r
g
i
n
g
i
n
g
r
i
d
sy
s
t
e
m
u
si
n
g
f
u
z
z
y
b
a
se
d
b
i
d
i
r
e
c
t
i
o
n
a
l
c
o
n
v
e
r
t
e
r
,
”
i
n
2
0
2
3
3
r
d
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
I
n
n
o
v
a
t
i
v
e
M
e
c
h
a
n
i
sm
s
f
o
r
I
n
d
u
s
t
ry
A
p
p
l
i
c
a
t
i
o
n
s
(
I
C
I
MIA)
,
I
EEE,
D
e
c
.
2
0
2
3
,
p
p
.
1
4
4
7
–
1
4
5
2
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
I
M
I
A
6
0
3
7
7
.
2
0
2
3
.
1
0
4
2
6
5
8
1
.
[
1
7
]
H
.
G
a
i
k
w
a
d
,
J.
R
.
S
a
i
n
i
,
a
n
d
H
.
G
a
i
k
w
a
d
,
“
P
r
e
d
i
c
t
i
v
e
mo
d
e
l
i
n
g
o
f
Li
-
i
o
n
b
a
t
t
e
r
y
s
t
a
t
e
o
f
c
h
a
r
g
e
i
n
e
l
e
c
t
r
i
c
v
e
h
i
c
l
e
s
:
st
u
d
y
o
f
m
o
d
e
r
n
mac
h
i
n
e
l
e
a
r
n
i
n
g
r
e
g
r
e
ss
o
r
s,”
S
m
a
r
t
I
n
n
o
v
a
t
i
o
n
,
S
y
s
t
e
m
s
a
n
d
T
e
c
h
n
o
l
o
g
i
e
s
,
v
o
l
.
3
9
5
S
I
S
T,
p
p
.
4
4
1
–
4
5
5
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
9
8
1
-
97
-
5
0
8
1
-
8
_
3
4
.
[
1
8
]
R
.
R
a
m
a
n
,
S
.
M
u
t
h
u
m
a
r
i
l
a
k
s
h
m
i
,
G
.
J
e
t
h
a
v
a
,
R
.
Ja
g
t
a
p
,
M
.
L
a
l
i
t
h
a
,
a
n
d
S
.
M
u
r
u
g
a
n
,
“
E
n
e
r
g
y
m
o
n
i
t
o
r
i
n
g
i
n
so
l
a
r
-
p
o
w
e
r
e
d
b
u
i
l
d
i
n
g
s
u
si
n
g
i
n
t
e
r
n
e
t
o
f
t
h
i
n
g
s
,
”
i
n
2
0
2
3
2
n
d
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
S
m
a
rt
T
e
c
h
n
o
l
o
g
i
e
s
f
o
r
S
m
a
r
t
N
a
t
i
o
n
,
S
m
a
rt
T
e
c
h
C
o
n
2
0
2
3
,
2
0
2
3
,
p
p
.
3
1
8
–
3
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
S
ma
r
t
Te
c
h
C
o
n
5
7
5
2
6
.
2
0
2
3
.
1
0
3
9
1
8
2
6
.
[
1
9
]
M
.
N
a
o
u
i
,
A
.
F
l
a
h
,
L.
S
b
i
t
a
,
M
.
B
e
n
H
a
me
d
,
a
n
d
A
.
T.
A
z
a
r
,
“
I
n
t
e
l
l
i
g
e
n
t
c
o
n
t
r
o
l
s
y
st
e
m
f
o
r
h
y
b
r
i
d
e
l
e
c
t
r
i
c
v
e
h
i
c
l
e
w
i
t
h
a
u
t
o
n
o
m
o
u
s
c
h
a
r
g
i
n
g
,
”
S
t
u
d
i
e
s
i
n
C
o
m
p
u
t
a
t
i
o
n
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
1
0
9
3
,
p
p
.
4
0
5
–
4
3
7
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
0
3
1
-
2
8
7
1
5
-
2
_
1
3
.
[
2
0
]
Y
.
A
l
i
,
F
.
M
o
n
s
u
u
r
,
C
.
M
o
r
t
o
n
,
a
n
d
C
.
K
.
M
a
n
,
“
M
o
d
e
l
l
i
n
g
e
l
e
c
t
r
i
c
v
e
h
i
c
l
e
c
h
a
r
g
i
n
g
e
v
e
n
t
s
u
si
n
g
a
r
a
n
d
o
m
p
a
r
a
met
e
r
d
u
r
a
t
i
o
n
a
p
p
r
o
a
c
h
,
”
T
ra
v
e
l
B
e
h
a
v
i
o
u
r
a
n
d
S
o
c
i
e
t
y
,
v
o
l
.
3
9
,
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
t
b
s.
2
0
2
5
.
1
0
0
9
8
9
.
[
2
1
]
Z.
F
u
,
X
.
L
i
u
,
J
.
Z
h
a
n
g
,
T.
Z
h
a
n
g
,
X
.
L
i
u
,
a
n
d
Y
.
J
i
a
n
g
,
“
O
r
d
e
r
l
y
s
o
l
a
r
c
h
a
r
g
i
n
g
o
f
e
l
e
c
t
r
i
c
v
e
h
i
c
l
e
s
a
n
d
i
t
s
i
m
p
a
c
t
o
n
c
h
a
r
g
i
n
g
b
e
h
a
v
i
o
r
:
a
y
e
a
r
-
r
o
u
n
d
f
i
e
l
d
e
x
p
e
r
i
me
n
t
,
”
A
p
p
l
i
e
d
E
n
e
rg
y
,
v
o
l
.
3
8
1
,
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
p
e
n
e
r
g
y
.
2
0
2
4
.
1
2
5
2
1
1
.
[
2
2
]
M
.
N
i
k
z
a
d
a
n
d
A
.
S
a
m
i
m
i
,
“
A
ss
e
ss
men
t
o
f
t
i
me
-
b
a
s
e
d
d
e
ma
n
d
r
e
s
p
o
n
s
e
p
r
o
g
r
a
ms
f
o
r
e
l
e
c
t
r
i
c
v
e
h
i
c
l
e
c
h
a
r
g
i
n
g
f
a
c
i
l
i
t
i
e
s,
”
Re
n
e
w
a
b
l
e
E
n
e
r
g
y
F
o
c
u
s
,
v
o
l
.
5
3
,
p
.
1
0
0
6
9
3
,
Ju
n
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
r
e
f
.
2
0
2
5
.
1
0
0
6
9
3
.
[
2
3
]
A
.
T.
Y
a
p
ı
c
ı
,
N
.
A
b
u
t
,
a
n
d
T.
Er
f
i
d
a
n
,
“
C
o
m
p
a
r
i
n
g
t
h
e
e
f
f
e
c
t
i
v
e
n
e
s
s
o
f
d
e
e
p
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
e
s
f
o
r
c
h
a
r
g
i
n
g
t
i
me
p
r
e
d
i
c
t
i
o
n
i
n
e
l
e
c
t
r
i
c
v
e
h
i
c
l
e
s:
K
o
c
a
e
l
i
e
x
a
m
p
l
e
,
”
E
n
e
r
g
i
e
s
,
v
o
l
.
1
8
,
n
o
.
8
,
2
0
2
5
,
d
o
i
:
1
0
.
3
3
9
0
/
e
n
1
8
0
8
1
9
6
1
.
[
2
4
]
R
.
S
u
d
h
a
r
s
a
n
e
t
a
l
.
,
“
M
o
d
e
l
l
i
n
g
a
n
d
si
mu
l
a
t
i
o
n
o
f
t
o
r
q
u
e
v
e
c
t
o
r
i
n
g
i
n
e
l
e
c
t
r
i
c
v
e
h
i
c
l
e
s
f
o
r
e
n
h
a
n
c
e
d
st
a
b
i
l
i
t
y
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
Ad
v
a
n
c
e
s
in
S
i
g
n
a
l
and
I
m
a
g
e
S
c
i
e
n
c
e
s
,
v
o
l
.
1
2
,
n
o
.
1
s
,
p
p
.
4
8
3
–
4
9
5
,
J
a
n
.
2
0
2
6
,
d
o
i
:
1
0
.
2
9
2
8
4
/
i
j
a
s
i
s.
1
2
.
1
s.
2
0
2
6
.
4
8
3
-
4
9
5
.
[
2
5
]
Zi
y
a
,
“
EV
_
b
a
t
t
e
r
y
_
c
h
a
r
g
i
n
g
_
d
a
t
a
.
”
2
0
2
5
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s
:
/
/
w
w
w
.
k
a
g
g
l
e
.
c
o
m
/
d
a
t
a
se
t
s/
z
i
y
a
0
7
/
e
v
-
b
a
t
t
e
r
y
-
c
h
a
r
g
i
n
g
-
d
a
t
a
[
2
6
]
A
.
V
.
P
a
n
c
h
b
h
a
i
,
R
.
R
a
ma
n
,
C
.
B
.
Th
a
c
k
e
r
,
S
.
M
u
t
h
u
mari
l
a
k
s
h
mi
,
a
n
d
S
.
M
u
r
u
g
a
n
,
“
R
e
si
d
e
n
t
i
a
l
e
l
e
c
t
r
i
c
v
e
h
i
c
l
e
c
h
a
r
g
i
n
g
s
t
a
t
i
o
n
u
si
n
g
t
h
e
i
n
t
e
r
n
e
t
o
f
t
h
i
n
g
s
,
”
i
n
2
0
2
3
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
P
o
w
e
r
En
e
r
g
y
,
E
n
v
i
r
o
n
m
e
n
t
a
n
d
I
n
t
e
l
l
i
g
e
n
t
C
o
n
t
r
o
l
,
P
EEIC
2
0
2
3
,
2
0
2
3
,
p
p
.
9
8
7
–
9
9
1
,
d
o
i
:
1
0
.
1
1
0
9
/
P
E
EI
C
5
9
3
3
6
.
2
0
2
3
.
1
0
4
5
0
5
6
9
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
9
2
I
n
t J Ap
p
l Po
wer
E
n
g
,
Vo
l.
1
5
,
No
.
3
,
Sep
tem
b
er
20
2
6
:
1
3
7
5
-
1
3
8
5
1384
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Dr
.
Tu
m
u
lu
r
i
K
a
n
th
i
m
a
t
h
i
is
a
n
a
ss
istan
t
p
ro
fe
ss
o
r
in
th
e
De
p
a
rtme
n
t
o
f
M
e
c
h
a
n
ica
l
En
g
in
e
e
rin
g
a
n
d
p
ro
fe
ss
o
r
-
in
-
c
h
a
rg
e
(
Ac
a
d
e
m
ics
a
t
Ko
n
e
r
u
Lak
s
h
m
a
iah
Ed
u
c
a
ti
o
n
F
o
u
n
d
a
ti
o
n
(KL
EF
),
Va
d
d
e
sw
a
ra
m
,
G
u
n
tu
r
Dist.
,
A
n
d
h
ra
P
ra
d
e
sh
,
In
d
ia.
S
h
e
o
b
tai
n
e
d
B.
E
.
i
n
m
e
c
h
a
n
ica
l
e
n
g
in
e
e
rin
g
i
n
t
h
e
y
e
a
r
2
0
0
0
fro
m
S
ir
C.
R.
R
Co
l
leg
e
o
f
En
g
i
n
e
e
rin
g
,
El
u
r
u
,
a
ffil
iate
d
to
An
d
h
ra
Un
i
v
e
rsity
,
M
.
Tec
h
.
in
t
h
e
rm
a
l
e
n
g
i
n
e
e
rin
g
i
n
th
e
y
e
a
r
2
0
1
1
fro
m
JN
TU
Hy
d
e
ra
b
a
d
,
a
n
d
P
h
.
D
.
i
n
th
e
y
e
a
r
2
0
2
4
fr
o
m
JN
TU
Hy
d
e
ra
b
a
d
in
th
e
a
re
a
o
f
h
e
a
t
tran
sfe
r
.
S
h
e
h
a
s
1
8
y
e
a
rs
o
f
tea
c
h
in
g
e
x
p
e
rien
c
e
i
n
b
o
th
u
n
d
e
r
g
ra
d
u
a
te
a
n
d
p
o
stg
ra
d
u
a
te
lev
e
ls
.
S
h
e
h
a
s
g
u
i
d
e
d
m
a
n
y
B.
E
.
a
n
d
M
.
E
.
p
ro
jec
ts.
S
h
e
h
a
s
p
u
b
li
sh
e
d
2
5
a
rti
c
le
s
in
v
a
ri
o
u
s
n
a
ti
o
n
a
l
a
n
d
in
ter
n
a
ti
o
n
a
l
jo
u
rn
a
ls
.
S
h
e
h
a
s
e
x
p
e
rt
ise
in
th
e
s
u
b
jec
ts
li
k
e
th
e
rm
o
d
y
n
a
m
ics
,
flu
i
d
m
e
c
h
a
n
i
c
s,
h
e
a
t
tran
sfe
r,
a
n
d
a
p
p
li
e
d
t
h
e
rm
o
d
y
n
a
m
ics
.
S
h
e
h
a
s
m
e
m
b
e
rsh
ip
s
in
I
S
HRA
E
a
n
d
S
AE
p
ro
fe
ss
io
n
a
l
b
o
d
ies
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
p
k
a
n
t
h
i
1
9
7
8
@g
m
a
il
.
c
o
m
.
Dr
.
Adh
im
o
o
la
m
S
a
ira
m
c
o
m
p
lete
d
h
is
B.
E.
,
M
.
E.
,
a
n
d
P
h
.
D.
in
c
o
m
p
u
ter
sc
ien
c
e
a
n
d
e
n
g
in
e
e
rin
g
a
n
d
is
c
u
r
re
n
tl
y
se
rv
in
g
a
s
a
p
ro
fe
ss
o
r
in
t
h
e
De
p
a
rtme
n
t
o
f
Co
m
p
u
te
r
S
c
ien
c
e
a
n
d
En
g
in
e
e
rin
g
,
S
IM
AT
S
En
g
in
e
e
rin
g
,
S
a
v
e
e
th
a
In
stit
u
te
o
f
M
e
d
ica
l
a
n
d
Tec
h
n
ica
l
S
c
ien
c
e
s
(S
IM
ATS
),
Ch
e
n
n
a
i,
I
n
d
ia.
He
h
a
s
1
8
y
e
a
rs
o
f
tea
c
h
in
g
e
x
p
e
rien
c
e
in
h
i
g
h
e
r
e
d
u
c
a
ti
o
n
a
n
d
h
a
s
b
e
e
n
a
c
ti
v
e
l
y
i
n
v
o
lv
e
d
i
n
tea
c
h
in
g
,
re
se
a
rc
h
,
c
u
rricu
lu
m
d
e
v
e
l
o
p
m
e
n
t,
a
n
d
m
e
n
to
rin
g
u
n
d
e
rg
ra
d
u
a
te an
d
p
o
s
tg
ra
d
u
a
te stu
d
e
n
ts.
His a
c
a
d
e
m
ic i
n
tere
sts in
c
lu
d
e
c
o
m
p
u
te
r
sc
ien
c
e
a
n
d
e
n
g
in
e
e
rin
g
,
we
b
te
c
h
n
o
l
o
g
ies
,
a
rti
ficia
l
in
telli
g
e
n
c
e
,
m
a
c
h
in
e
lea
rn
in
g
,
d
a
t
a
sc
ien
c
e
,
c
y
b
e
rse
c
u
rit
y
,
Io
T
,
a
n
d
c
lo
u
d
c
o
m
p
u
ti
n
g
.
He
h
a
s
m
a
d
e
sig
n
ifi
c
a
n
t
re
se
a
rc
h
c
o
n
tri
b
u
ti
o
n
s,
h
a
v
i
n
g
p
u
b
li
sh
e
d
m
o
re
th
a
n
3
0
re
se
a
rc
h
p
a
p
e
rs
in
re
p
u
ted
in
tern
a
ti
o
n
a
l
jo
u
rn
a
l
s
a
n
d
i
n
tern
a
ti
o
n
a
l
c
o
n
fe
re
n
c
e
p
r
o
c
e
e
d
in
g
s.
He
h
a
s
a
lso
g
u
id
e
d
n
u
m
e
ro
u
s
stu
d
e
n
t
p
r
o
jec
ts,
p
a
rti
c
ip
a
ted
in
fa
c
u
lt
y
d
e
v
e
lo
p
m
e
n
t
p
r
o
g
ra
m
s,
a
n
d
c
o
n
tri
b
u
te
d
to
v
a
ri
o
u
s
a
c
a
d
e
m
ic
a
n
d
re
se
a
rc
h
a
c
ti
v
it
ies
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
d
r.
a
.
sa
iraa
m
@g
m
a
il
.
c
o
m
.
Dura
ira
j
Ch
a
n
d
r
a
k
a
l
a
is
wo
rk
i
n
g
a
s
a
n
a
ss
istan
t
p
ro
fe
ss
o
r
in
Eas
wa
ri
En
g
i
n
e
e
rin
g
Co
ll
e
g
e
,
Ch
e
n
n
a
i,
Tam
il
Na
d
u
.
S
h
e
a
wa
rd
e
d
B.
E
.
d
e
g
re
e
in
e
lec
tri
c
a
l
a
n
d
e
lec
tro
n
ics
e
n
g
in
e
e
rin
g
fro
m
Aru
lmig
u
Ka
las
a
li
n
g
a
m
Co
ll
e
g
e
o
f
E
n
g
i
n
e
e
rin
g
,
Kris
h
n
a
n
k
o
il
,
Viru
d
h
u
n
a
g
a
r
District,
Tam
il
Na
d
u
,
in
th
e
y
e
a
r
2
0
0
0
a
n
d
M
.
E
.
d
e
g
re
e
in
a
p
p
li
e
d
e
lec
tro
n
ics
fro
m
Co
im
b
a
to
re
I
n
stit
u
te
o
f
Tec
h
n
o
lo
g
y
,
Co
imb
a
to
re
,
Tam
il
Na
d
u
,
i
n
th
e
y
e
a
r
2
0
0
7
.
S
h
e
h
a
s
2
0
+
y
e
a
rs
o
f
tea
c
h
i
n
g
e
x
p
e
rien
c
e
.
Also
,
s
h
e
is
c
u
rre
n
tl
y
d
o
in
g
p
a
rt
ti
m
e
-
P
h
.
D
.
d
e
g
re
e
i
n
F
a
c
u
lt
y
o
f
E
lec
tro
n
ics
a
n
d
C
o
m
m
u
n
ica
ti
o
n
E
n
g
i
n
e
e
rin
g
,
An
n
a
Un
iv
e
rsity
,
Ch
e
n
n
a
i,
Tam
il
Na
d
u
,
In
d
ia.
S
h
e
h
a
s
p
u
b
li
s
h
e
d
1
4
p
a
te
n
ts
a
n
d
p
re
se
n
ted
/
p
u
b
li
sh
e
d
a
ro
u
n
d
5
0
+
p
a
p
e
rs
i
n
Jo
u
rn
a
ls
a
n
d
c
o
n
fe
re
n
c
e
s
.
He
r
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
c
y
b
e
r
se
c
u
rit
y
,
sm
a
rt
g
rid
,
a
n
d
imp
lem
e
n
tatio
n
o
f
o
p
ti
m
iza
ti
o
n
te
c
h
n
iq
u
e
s
i
n
p
o
we
r
sy
ste
m
e
n
g
in
e
e
rin
g
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
c
h
a
n
d
ra
k
a
la.d
.
e
e
e
@g
m
a
il
.
c
o
m
.
Mo
o
r
th
y
R
a
d
h
i
k
a
is
a
n
a
ss
istan
t
p
r
o
fe
ss
o
r
i
n
De
p
a
rtme
n
t
o
f
In
f
o
rm
a
ti
o
n
Tec
h
n
o
l
o
g
y
a
t
R.
M
.
D.
E
n
g
i
n
e
e
rin
g
Co
ll
e
g
e
.
S
h
e
o
b
tai
n
e
d
h
e
r
Ba
c
h
e
lo
r’s
o
f
Tec
h
n
o
lo
g
y
d
e
g
re
e
in
in
f
o
rm
a
ti
o
n
tec
h
n
o
lo
g
y
fr
o
m
Bh
a
jara
n
g
E
n
g
i
n
e
e
rin
g
Co
l
leg
e
a
n
d
M
a
ste
r
o
f
En
g
i
n
e
e
rin
g
d
e
g
re
e
i
n
c
o
m
p
u
te
r
sc
ien
c
e
a
n
d
e
n
g
in
e
e
ri
n
g
fro
m
Ve
lam
m
a
l
En
g
in
e
e
ri
n
g
Co
ll
e
g
e
.
S
h
e
is
c
u
rre
n
tl
y
p
u
rsu
in
g
h
e
r
P
h
.
D
.
d
e
g
re
e
fro
m
An
n
a
Un
i
v
e
rsity
.
He
r
a
re
a
s
o
f
in
tere
st
in
c
lu
d
e
b
ig
d
a
ta,
m
a
c
h
in
e
lea
rn
in
g
,
d
a
tab
a
se
m
a
n
a
g
e
m
e
n
t
s
y
ste
m
,
a
n
d
d
a
ta
str
u
c
tu
re
.
S
h
e
h
a
s
p
u
b
li
sh
e
d
5
p
a
p
e
rs
in
in
tern
a
ti
o
n
a
l
jo
u
rn
a
ls
a
n
d
c
o
n
fe
re
n
c
e
s
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
ra
d
ik
a
m
o
o
rt
h
i@
g
m
a
il
.
c
o
m
.
Dr
.
Bicha
g
a
l
S
h
a
d
a
k
sha
r
a
p
p
a
c
u
rre
n
tl
y
wo
r
k
in
g
a
s
t
h
e
p
rin
c
i
p
a
l
o
f
S
ri
S
a
iram
Co
ll
e
g
e
o
f
E
n
g
i
n
e
e
rin
g
(
F
o
rm
e
rly
S
h
ird
i
S
a
i
En
g
in
e
e
rin
g
Co
ll
e
g
e
),
An
e
k
a
l,
Ba
n
g
a
l
o
re
.
He
h
a
s
o
b
tai
n
e
d
h
is
u
n
d
e
r
g
ra
d
u
a
ti
o
n
in
CS
E,
m
a
ste
r
o
f
sc
ien
c
e
i
n
so
ftw
a
re
sy
ste
m
s
,
a
n
d
P
h
.
D
.
i
n
CS
E.
He
h
a
s
rich
a
c
a
d
e
m
ic
a
n
d
re
se
a
rc
h
e
x
p
e
rien
c
e
fo
r
a
b
o
u
t
2
7
y
e
a
rs.
He
is
a
c
ti
v
e
ly
i
n
v
o
lv
e
d
in
g
u
i
d
in
g
P
h
.
D
.
c
a
n
d
id
a
tes
i
n
t
h
e
field
o
f
CS
E
.
He
h
a
s
p
u
b
li
s
h
e
d
a
n
d
p
re
se
n
te
d
m
a
n
y
re
se
a
rc
h
p
a
p
e
rs i
n
n
a
ti
o
n
a
l
a
n
d
i
n
tern
a
ti
o
n
a
l
c
o
n
fe
re
n
c
e
s a
n
d
re
p
u
ted
j
o
u
r
n
a
ls
.
He
h
a
s m
a
n
y
p
a
ten
ts t
o
h
is
c
re
d
it
.
He
h
a
s
p
u
b
li
s
h
e
d
m
o
re
th
a
n
6
0
p
a
p
e
rs
i
n
re
p
u
ted
n
a
ti
o
n
a
l
a
n
d
i
n
tern
a
ti
o
n
a
l
j
o
u
r
n
a
ls
a
n
d
h
e
h
a
s
p
u
b
li
s
h
e
d
1
7
b
o
o
k
s
fo
r
VTU
stu
d
e
n
ts
a
s
we
ll
;
h
e
h
a
s
fil
e
d
1
7
p
a
te
n
ts.
As
a
n
a
c
a
d
e
m
icia
n
,
h
e
h
a
s
se
rv
e
d
in
d
if
fe
re
n
t
c
a
p
a
c
it
ies
a
s
lec
tu
re
r,
se
n
io
r
lec
tu
re
r,
a
ss
t.
p
r
o
fe
ss
o
r,
a
n
d
HO
D
sp
a
n
n
in
g
a
b
o
u
t
2
0
y
e
a
rs.
He
h
a
s
a
d
m
in
istrativ
e
e
x
p
e
rien
c
e
a
s
v
ice
p
rin
c
ip
a
l
fo
r
9
y
e
a
rs an
d
a
s
p
ri
n
c
ip
a
l
f
o
r
6
y
e
a
rs.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
sh
a
d
b
ich
a
g
a
l@g
m
a
il
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.