I
nte
rna
t
io
na
l J
o
urna
l o
f
P
o
wer
E
lect
ro
nics
a
nd
Driv
e
S
y
s
t
em
(
I
J
P
E
DS)
Vo
l.
16
,
No
.
4
,
Dec
em
b
er
20
25
,
p
p
.
2
4
1
9
~
2
4
2
8
I
SS
N:
2
0
8
8
-
8
6
9
4
,
DOI
: 1
0
.
1
1
5
9
1
/ijp
ed
s
.
v
16
.
i
4
.
p
p
2
4
1
9
-
2
4
2
8
2419
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
p
e
d
s
.
ia
esco
r
e.
co
m
Superv
ised lea
rni
ng
f
o
r f
a
st
inv
ers
e mo
tor con
trol
ma
pping
:
a
co
mpa
ra
tive stud
y
on SRM
and B
LDC
mo
tors
S
.
Su
dh
ee
r
K
um
a
r
Reddy
,
J
.
N
.
Cha
nd
ra
Sek
ha
r
D
e
p
a
r
t
me
n
t
o
f
E
l
e
c
t
r
i
c
a
l
a
n
d
E
l
e
c
t
r
o
n
i
c
E
n
g
i
n
e
e
r
i
n
g
,
S
r
i
V
e
n
k
a
t
e
sh
w
a
r
a
U
n
i
v
e
r
s
i
t
y
C
o
l
l
e
g
e
o
f
E
n
g
i
n
e
e
r
i
n
g
,
Ti
r
u
p
a
t
i
,
I
n
d
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Ma
y
1
6
,
2
0
2
5
R
ev
is
ed
Sep
1
5
,
2
0
2
5
Acc
ep
ted
Oct
2
,
2
0
2
5
Th
is
p
a
p
e
r
in
v
e
stig
a
tes
th
e
a
p
p
li
c
a
ti
o
n
o
f
m
a
c
h
in
e
lea
rn
in
g
(M
L
)
m
o
d
e
ls,
sp
e
c
ifi
c
a
ll
y
a
rti
ficia
l
n
e
u
ra
l
n
e
t
wo
rk
s
(AN
N)
a
n
d
XG
Bo
o
st,
fo
r
re
a
l
-
ti
m
e
m
o
to
r
c
o
n
tr
o
l,
f
o
c
u
si
n
g
o
n
sw
it
c
h
e
d
re
l
u
c
tan
c
e
m
o
to
rs
(S
RM
)
a
n
d
b
r
u
sh
les
s
DC
m
o
to
rs
(BLDC).
Trad
it
i
o
n
a
l
in
v
e
rs
e
d
y
n
a
m
ics
m
a
p
p
in
g
fo
r
m
o
to
r
c
o
n
tro
l
is
c
o
m
p
a
re
d
wit
h
M
L
a
p
p
ro
a
c
h
e
s
t
o
h
ig
h
li
g
h
t
a
d
v
a
n
tag
e
s
in
sp
e
e
d
,
a
c
c
u
ra
c
y
,
a
n
d
d
e
p
l
o
y
m
e
n
t
e
ffici
e
n
c
y
.
Da
tas
e
ts
sim
u
latin
g
th
e
i
n
p
u
t
-
o
u
t
p
u
t
b
e
h
a
v
i
o
r
o
f
b
o
th
m
o
t
o
r
ty
p
e
s
a
re
u
se
d
to
train
a
n
d
tes
t
th
e
m
o
d
e
ls.
Ke
y
p
e
rfo
rm
a
n
c
e
m
e
tri
c
s
su
c
h
a
s
m
e
a
n
sq
u
a
re
d
e
rro
r
(
M
S
E),
R
²
sc
o
r
e
,
train
in
g
ti
m
e
,
a
n
d
late
n
c
y
a
re
e
v
a
lu
a
ted
,
with
t
h
e
g
o
a
l
o
f
re
p
lac
in
g
trad
it
io
n
a
l
c
o
n
tro
l
m
e
th
o
d
s
i
n
re
a
l
-
ti
m
e
a
p
p
li
c
a
ti
o
n
s.
Re
su
lt
s
i
n
d
ica
te
t
h
a
t
M
L
m
o
d
e
ls
o
u
t
p
e
rfo
rm
tra
d
it
i
o
n
a
l
m
e
th
o
d
s
in
term
s
o
f
p
re
d
icti
o
n
a
c
c
u
ra
c
y
a
n
d
d
e
p
lo
y
m
e
n
t
s
p
e
e
d
,
s
u
g
g
e
stin
g
a
p
ro
m
isin
g
p
a
th
to
wa
rd
m
o
re
e
ffi
c
ien
t
a
n
d
a
d
a
p
ti
v
e
m
o
to
r
c
o
n
tro
l
sy
ste
m
s.
Th
e
n
o
v
e
l
ty
o
f
th
is
wo
r
k
li
e
s
i
n
a
p
p
l
y
i
n
g
su
p
e
rv
ise
d
lea
rn
in
g
d
irec
tl
y
fo
r
in
v
e
rse
m
o
to
r
c
o
n
tr
o
l
m
a
p
p
in
g
,
th
e
re
b
y
e
li
m
in
a
ti
n
g
t
h
e
n
e
e
d
f
o
r
e
x
p
l
icit
a
n
a
ly
ti
c
a
l
m
o
d
e
ls
a
n
d
e
n
a
b
li
n
g
a
u
n
ifi
e
d
,
d
a
ta
-
d
riv
e
n
b
e
n
c
h
m
a
rk
in
g
fra
m
e
wo
rk
a
c
ro
ss
S
RM
a
n
d
BLDC.
K
ey
w
o
r
d
s
:
Ar
tific
ial
n
eu
r
al
n
etwo
r
k
s
B
r
u
s
h
less
D
C
m
o
to
r
s
I
n
v
er
s
e
d
y
n
am
ics
Ma
ch
in
e
lear
n
in
g
Switch
ed
r
elu
ctan
ce
m
o
to
r
s
XGBo
o
s
t
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
:
S
.
Su
d
h
ee
r
Ku
m
a
r
R
ed
d
y
Dep
ar
tm
e
n
t
o
f
E
l
ec
t
r
i
ca
l
a
n
d
E
le
ct
r
o
n
i
c
E
n
g
in
ee
r
i
n
g
,
S
r
i
Ve
n
k
at
esh
wa
r
a
U
n
i
v
e
r
s
it
y
C
o
l
le
g
e
o
f
E
n
g
i
n
e
e
r
i
n
g
T
ir
u
p
ati,
An
d
h
r
a
Pra
d
esh
,
I
n
d
i
a
E
m
ail: su
d
h
ee
r
s
o
m
u
@
g
m
ail.
c
o
m
1.
I
NT
RO
D
UCT
I
O
N
Acc
u
r
ate
an
d
ef
f
icien
t
m
o
to
r
co
n
tr
o
l
is
f
u
n
d
am
en
tal
to
m
o
d
er
n
elec
tr
ic
d
r
iv
e
s
y
s
tem
s
,
p
ar
ticu
lar
ly
in
ap
p
licatio
n
s
r
eq
u
ir
i
n
g
r
ea
l
-
ti
m
e
p
er
f
o
r
m
an
ce
s
u
c
h
as
r
o
b
o
tics
,
elec
tr
ic
v
eh
icles,
in
d
u
s
tr
ial
au
to
m
atio
n
,
a
n
d
r
en
ewa
b
le
en
er
g
y
s
y
s
tem
s
.
T
r
ad
itio
n
al
m
o
to
r
c
o
n
tr
o
l
s
tr
ateg
ies
o
f
ten
r
ely
o
n
f
o
r
war
d
o
r
in
v
er
s
e
d
y
n
am
ic
m
o
d
els,
wh
er
e
c
o
n
tr
o
l
in
p
u
t
is
co
m
p
u
ted
b
ased
o
n
a
m
at
h
em
atica
l
f
o
r
m
u
latio
n
o
f
m
o
t
o
r
b
e
h
av
io
r
.
W
h
i
l
e
e
f
f
e
c
t
i
v
e
u
n
d
e
r
i
d
e
a
l
c
o
n
d
i
t
i
o
n
s
,
t
h
e
s
e
c
l
ass
i
c
al
m
e
t
h
o
d
s
a
r
e
o
f
t
e
n
h
i
n
d
e
r
e
d
b
y
c
h
a
l
l
e
n
g
e
s
s
u
c
h
a
s
n
o
n
l
i
n
e
a
r
i
t
i
es
,
p
a
r
a
m
e
t
r
i
c
u
n
c
e
r
t
a
i
n
ti
es
,
a
n
d
c
o
m
p
u
t
a
t
i
o
n
a
l
c
o
m
p
l
e
x
i
t
y
,
esp
e
c
i
a
l
l
y
w
h
e
n
a
p
p
l
i
e
d
t
o
m
o
to
r
s
w
i
t
h
n
o
n
l
i
n
e
a
r
c
h
a
r
a
c
t
e
r
is
t
i
cs
li
k
e
s
w
i
t
c
h
e
d
r
elu
c
t
a
n
c
e
m
o
t
o
r
s
(
S
R
M
)
a
n
d
b
r
u
s
h
l
es
s
DC
m
o
t
o
r
s
(
B
L
DC
)
[
1
]
,
[
2
]
.
I
n
v
er
s
e
m
o
to
r
m
ap
p
i
n
g
,
d
ete
r
m
in
in
g
th
e
n
ec
ess
ar
y
in
p
u
t
p
ar
am
eter
s
(
e.
g
.
,
v
o
ltag
e
o
r
cu
r
r
en
t)
to
ac
h
iev
e
a
d
esire
d
o
u
tp
u
t
(
e.
g
.
,
to
r
q
u
e
o
r
s
p
ee
d
)
,
is
ce
n
tr
al
to
r
ea
l
-
tim
e
co
n
tr
o
l.
Ho
wev
er
,
d
er
iv
in
g
an
aly
tical
in
v
er
s
e
m
o
d
els
f
o
r
co
m
p
lex
n
o
n
lin
ea
r
m
o
to
r
s
ca
n
b
e
i
n
f
e
asib
le
o
r
co
m
p
u
tatio
n
ally
e
x
p
e
n
s
iv
e.
Mo
r
e
o
v
er
,
th
ese
m
o
d
els
ty
p
ically
r
eq
u
ir
e
ac
cu
r
ate
s
y
s
tem
id
en
tific
atio
n
an
d
s
u
f
f
er
d
e
g
r
ad
atio
n
in
p
er
f
o
r
m
an
ce
d
u
e
to
ex
ter
n
al
d
is
tu
r
b
a
n
ce
s
,
lo
ad
v
ar
iatio
n
s
,
an
d
m
o
d
elin
g
e
r
r
o
r
s
.
I
n
r
esp
o
n
s
e
to
th
ese
c
h
allen
g
e
s
,
s
u
p
er
v
is
ed
m
ac
h
in
e
lear
n
in
g
h
as
e
m
er
g
e
d
as
a
p
r
o
m
is
in
g
alter
n
ativ
e
f
o
r
i
n
v
er
s
e
m
o
to
r
m
ap
p
in
g
.
B
y
lear
n
in
g
th
e
f
u
n
ctio
n
al
r
elatio
n
s
h
ip
b
etwe
en
d
esire
d
m
o
to
r
o
u
tp
u
ts
an
d
co
r
r
esp
o
n
d
in
g
in
p
u
ts
f
r
o
m
d
a
ta,
s
u
p
er
v
is
ed
lear
n
in
g
m
o
d
els
s
u
ch
as
ar
tific
ial
n
eu
r
al
n
etwo
r
k
s
(
ANN)
an
d
ex
tr
em
e
g
r
ad
ien
t
b
o
o
s
t
in
g
(
XGBo
o
s
t)
ca
n
ef
f
ec
tiv
el
y
a
p
p
r
o
x
im
ate
in
v
er
s
e
d
y
n
am
ic
s
with
o
u
t
r
e
q
u
ir
in
g
ex
p
licit
m
o
to
r
eq
u
atio
n
s
.
T
h
e
s
e
m
o
d
els
o
f
f
er
f
ast
in
f
er
en
ce
,
r
o
b
u
s
t
g
en
er
aliza
tio
n
,
an
d
th
e
ab
ilit
y
to
lear
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
6
9
4
I
n
t J Po
w
E
lec
&
Dr
i Sy
s
t
,
Vo
l.
16
,
No
.
4
,
Dec
em
b
er
20
25
:
2419
-
2
4
2
8
2420
d
ir
ec
tly
f
r
o
m
em
p
ir
ical
d
ata,
m
ak
in
g
th
em
p
a
r
ticu
lar
ly
s
u
itab
le
f
o
r
r
e
al
-
tim
e
ap
p
licatio
n
s
.
Mo
to
r
co
n
tr
o
l
s
y
s
tem
s
h
av
e
tr
ad
itio
n
ally
em
p
lo
y
ed
m
o
d
el
-
b
ased
co
n
tr
o
l
tech
n
iq
u
es
s
u
ch
as
p
r
o
p
o
r
tio
n
al
-
in
teg
r
al
-
d
e
r
iv
ativ
e
(
PID
)
co
n
tr
o
ller
s
,
in
v
er
s
e
d
y
n
am
ic
m
o
d
els,
an
d
m
o
d
el
p
r
e
d
ictiv
e
co
n
tr
o
l
(
MPC
)
[
3
]
-
[
5
]
.
W
h
ile
ef
f
ec
tiv
e
f
o
r
lin
ea
r
s
y
s
tem
s
o
r
well
-
p
ar
am
eter
ized
m
o
to
r
s
,
th
ese
ap
p
r
o
ac
h
es
f
ac
e
lim
itatio
n
s
wh
en
ap
p
lied
to
n
o
n
lin
ea
r
o
r
h
ig
h
ly
d
y
n
am
ic
m
ac
h
in
es
lik
e
SR
M
an
d
B
L
DC
,
wh
ich
e
x
h
ib
it
s
tr
o
n
g
m
ag
n
etic
n
o
n
li
n
ea
r
ities
,
s
atu
r
atio
n
ef
f
ec
ts
,
an
d
d
e
p
en
d
e
n
cy
o
n
p
r
ec
is
e
r
o
to
r
p
o
s
itio
n
[
6
]
,
[
7
]
.
I
n
v
er
s
e
d
y
n
am
ics
-
b
ased
co
n
t
r
o
l
s
tr
ateg
ies
s
ee
k
to
co
m
p
u
te
co
n
tr
o
l
in
p
u
ts
th
at
r
esu
lt
in
d
esire
d
o
u
tp
u
ts
.
H
o
wev
er
,
th
is
r
e
q
u
ir
es
an
ac
c
u
r
ate
m
o
to
r
m
o
d
el,
o
f
ten
f
o
r
m
u
lated
u
s
in
g
d
if
f
er
en
tial
eq
u
atio
n
s
an
d
lo
o
k
u
p
tab
les
d
e
r
iv
ed
f
r
o
m
f
in
ite
elem
en
t
an
al
y
s
is
(
FEA)
o
r
em
p
ir
ical
m
ea
s
u
r
em
e
n
ts
[
8
]
,
[
9
]
.
T
h
e
co
m
p
lex
it
y
an
d
co
m
p
u
tatio
n
al
d
em
an
d
s
o
f
s
u
ch
m
o
d
els o
f
ten
in
h
ib
it th
e
ir
ap
p
licatio
n
in
r
ea
l
-
tim
e
s
y
s
tem
s
[
1
0
]
.
I
n
co
n
tr
ast,
d
ata
-
d
r
iv
en
a
p
p
r
o
ac
h
es
u
s
in
g
s
u
p
er
v
is
ed
m
ac
h
i
n
e
lear
n
in
g
(
ML
)
h
av
e
g
ai
n
ed
s
ig
n
if
i
ca
n
t
tr
ac
tio
n
in
r
ec
en
t
y
ea
r
s
.
T
h
e
s
e
m
eth
o
d
s
lev
er
ag
e
m
o
to
r
i
n
p
u
t
-
o
u
tp
u
t
d
atasets
to
lear
n
in
v
er
s
e
m
ap
p
in
g
s
with
o
u
t
ex
p
licit
p
h
y
s
ical
m
o
d
elin
g
[
1
1
]
,
[
1
2
]
.
Ar
tific
ial
n
eu
r
al
n
etwo
r
k
s
(
ANNs)
h
av
e
b
ee
n
wid
ely
in
v
esti
g
ated
f
o
r
m
o
to
r
c
o
n
tr
o
l
task
s
d
u
e
to
th
eir
u
n
iv
er
s
al
ap
p
r
o
x
im
atio
n
ca
p
ab
ilit
y
an
d
ad
ap
tab
ilit
y
to
n
o
n
lin
ea
r
f
u
n
ctio
n
s
[
1
3
]
-
[
1
5
]
.
XGBo
o
s
t,
a
d
ec
is
io
n
-
tr
ee
-
b
a
s
ed
en
s
em
b
le
tech
n
i
q
u
e,
h
as
also
em
er
g
ed
as
a
p
o
wer
f
u
l
r
eg
r
ess
o
r
in
in
d
u
s
tr
ial
ap
p
licatio
n
s
d
u
e
to
its
h
ig
h
ac
c
u
r
ac
y
an
d
f
aster
tr
a
in
in
g
co
n
v
er
g
en
c
e
co
m
p
ar
ed
to
d
ee
p
n
eu
r
al
m
o
d
els [
1
6
]
-
[
1
8
]
.
R
esear
ch
b
y
J
in
g
et
a
l
.
[
1
9
]
d
em
o
n
s
tr
ated
th
at
n
eu
r
al
n
etwo
r
k
s
ca
n
ef
f
ec
tiv
ely
a
p
p
r
o
x
im
a
te
in
v
er
s
e
to
r
q
u
e
co
n
tr
o
l
laws
f
o
r
SR
Ms
with
r
ed
u
ce
d
to
r
q
u
e
r
i
p
p
le.
Similar
ly
,
r
esear
ch
er
s
in
[
2
0
]
-
[
2
2
]
ap
p
lied
d
ee
p
lea
r
n
in
g
to
B
L
DC
m
o
to
r
s
an
d
ac
h
iev
e
d
r
ea
l
-
tim
e
p
o
s
iti
o
n
esti
m
atio
n
with
o
u
t
en
c
o
d
er
s
.
H
o
w
e
v
e
r
,
t
h
es
e
m
e
t
h
o
d
s
o
f
t
e
n
l
a
c
k
f
o
r
m
a
l
s
t
ab
i
l
i
t
y
g
u
a
r
a
n
t
e
es
a
n
d
c
a
n
s
u
f
f
e
r
f
r
o
m
o
v
e
r
f
i
t
t
i
n
g
i
f
n
o
t
p
r
o
p
e
r
l
y
r
e
g
u
l
a
r
i
z
e
d
[
2
3
]
.
R
ea
l
-
tim
e
ap
p
licab
ilit
y
r
e
m
ain
s
a
s
ig
n
if
ica
n
t
b
a
r
r
ier
.
T
h
e
i
n
f
er
en
ce
laten
cy
,
esp
ec
ially
f
o
r
d
ee
p
m
o
d
els,
ca
n
r
estrict
th
eir
u
s
e
in
em
b
ed
d
ed
en
v
ir
o
n
m
en
ts
.
W
o
r
k
s
s
u
ch
as [
2
4
]
-
[
2
6
]
h
av
e
ex
p
lo
r
e
d
m
o
d
e
l simp
lific
atio
n
an
d
p
r
u
n
in
g
t
o
r
e
d
u
ce
co
m
p
u
tatio
n
al
co
s
t,
wh
ile
[
2
7
]
em
p
h
asize
s
th
e
n
ee
d
f
o
r
h
y
b
r
id
s
y
s
t
em
s
co
m
b
in
in
g
class
ical
co
n
tr
o
l a
n
d
ML
to
e
n
s
u
r
e
s
af
e
ty
an
d
in
ter
p
r
etab
ilit
y
.
Fu
r
th
er
m
o
r
e
,
wh
ile
s
o
m
e
s
tu
d
ies
co
m
p
a
r
e
m
o
d
el
ac
c
u
r
ac
y
,
f
ew
p
r
o
v
id
e
a
c
o
m
p
r
eh
en
s
iv
e
co
m
p
ar
is
o
n
ac
r
o
s
s
m
o
to
r
ty
p
es
(
e.
g
.
,
SR
M
v
s
.
B
L
DC
)
u
s
in
g
u
n
if
ied
d
atasets
an
d
m
etr
ics.
T
h
is
p
a
p
er
ad
d
r
ess
es
th
at
g
ap
b
y
b
en
ch
m
ar
k
in
g
ANN
an
d
XGBo
o
s
t
m
o
d
els
f
o
r
b
o
t
h
m
o
to
r
ty
p
es,
ev
alu
atin
g
n
o
t
o
n
l
y
p
r
ed
ictiv
e
ac
cu
r
ac
y
b
u
t a
ls
o
la
ten
cy
,
ef
f
icien
c
y
,
an
d
r
ea
l
-
tim
e
f
ea
s
ib
ilit
y
.
T
h
is
p
ap
er
e
x
p
lo
r
es
t
h
e
u
s
e
o
f
s
u
p
er
v
is
ed
lea
r
n
in
g
f
o
r
in
v
e
r
s
e
co
n
tr
o
l
m
ap
p
in
g
o
f
SR
M
an
d
B
L
DC
m
o
to
r
s
,
f
o
c
u
s
in
g
o
n
s
p
ee
d
,
ac
cu
r
ac
y
,
an
d
r
ea
l
-
tim
e
f
ea
s
i
b
ilit
y
.
L
ar
g
e
s
y
n
th
etic
d
atase
ts
wer
e
g
en
er
ated
th
r
o
u
g
h
s
im
u
latio
n
,
ca
p
tu
r
in
g
a
wid
e
r
a
n
g
e
o
f
m
o
to
r
o
p
e
r
atin
g
co
n
d
itio
n
s
.
T
wo
r
ep
r
esen
tativ
e
s
u
p
er
v
is
ed
m
o
d
els
,
ANN
an
d
XGBo
o
s
t
,
wer
e
tr
ain
ed
to
p
r
ed
ict
m
o
to
r
i
n
p
u
t sig
n
als b
ased
o
n
d
esire
d
o
u
tp
u
t ta
r
g
ets.
T
h
e
tr
ain
ed
m
o
d
els
wer
e
th
en
ev
alu
ated
o
n
th
eir
ab
ilit
y
to
a
p
p
r
o
x
im
ate
th
e
in
v
er
s
e
co
n
tr
o
l
law
wit
h
h
ig
h
f
id
elity
a
n
d
lo
w
laten
cy
.
T
h
e
p
r
im
ar
y
co
n
tr
ib
u
tio
n
s
o
f
t
h
is
wo
r
k
ar
e
as
f
o
llo
ws:
i)
Dev
elo
p
m
en
t
o
f
s
u
p
er
v
is
ed
le
ar
n
in
g
m
o
d
els
f
o
r
in
v
er
s
e
m
o
t
o
r
co
n
tr
o
l
o
f
SR
M
an
d
B
L
DC
m
o
to
r
s
u
s
in
g
ANN
an
d
XGBo
o
s
t a
r
ch
itectu
r
es.
ii)
C
o
m
p
ar
ativ
e
an
aly
s
is
o
f
b
o
th
m
o
to
r
t
y
p
es
u
n
d
er
id
e
n
tical
co
n
d
itio
n
s
u
s
in
g
c
o
n
s
is
ten
t
d
atasets
,
p
er
f
o
r
m
an
ce
m
etr
ics,
an
d
p
r
ep
r
o
ce
s
s
in
g
p
ip
elin
es.
iii)
E
v
alu
atio
n
o
f
m
o
d
el
p
er
f
o
r
m
an
ce
in
ter
m
s
o
f
p
r
ed
ictio
n
ac
cu
r
ac
y
(
R
²,
MSE
)
,
r
ea
l
-
tim
e
s
u
itab
ilit
y
(
laten
cy
)
,
a
n
d
p
r
ac
tical
ef
f
icie
n
cy
m
etr
ics.
iv
)
I
n
s
ig
h
t
in
to
m
o
d
el
s
u
itab
ilit
y
f
o
r
d
ep
l
o
y
m
en
t
in
r
ea
l
-
tim
e
em
b
ed
d
e
d
s
y
s
tem
s
,
r
ep
lacin
g
o
r
au
g
m
en
tin
g
tr
ad
itio
n
al
co
n
tr
o
l m
ec
h
a
n
is
m
s
.
T
h
e
r
e
m
ain
d
er
o
f
th
is
p
ap
er
i
s
o
r
g
an
ize
d
as
f
o
llo
ws:
Sectio
n
2
p
r
o
v
id
es
a
b
r
ief
r
ev
iew
o
f
r
elate
d
wo
r
k
an
d
ex
is
tin
g
tech
n
iq
u
es
in
in
v
er
s
e
m
o
to
r
c
o
n
tr
o
l.
Sectio
n
3
d
escr
ib
es
th
e
d
ataset
g
en
er
atio
n
p
r
o
ce
s
s
,
p
r
ep
r
o
ce
s
s
in
g
s
tep
s
,
lear
n
in
g
m
o
d
els
,
a
n
d
tr
ai
n
in
g
s
tr
ateg
y
.
Sectio
n
4
p
r
esen
ts
ex
p
er
i
m
en
tal
r
esu
lts
an
d
an
aly
s
is
.
Sectio
n
5
co
n
clu
d
es th
e
p
ap
er
an
d
s
u
g
g
ests
d
ir
ec
tio
n
s
f
o
r
f
u
tu
r
e
r
esear
c
h
.
2.
M
E
T
H
O
DO
L
O
G
Y
T
h
is
s
ec
tio
n
elab
o
r
ates
o
n
t
h
e
d
esig
n
an
d
im
p
l
em
en
tatio
n
o
f
ML
m
o
d
els
f
o
r
r
ea
l
-
tim
e
in
v
e
r
s
e
co
n
tr
o
l
m
a
p
p
in
g
o
f
SR
M
an
d
b
r
u
s
h
less
DC
(
B
L
DC
)
m
o
to
r
s
.
T
h
e
g
o
al
is
to
p
r
ed
ict
th
e
n
ec
ess
ar
y
co
n
tr
o
l
in
p
u
ts
th
at
y
ield
d
esire
d
d
y
n
am
ic
r
esp
o
n
s
es
u
n
d
er
v
ar
y
in
g
o
p
er
atin
g
c
o
n
d
itio
n
s
.
T
h
e
p
r
o
p
o
s
e
d
w
o
r
k
f
l
o
w
c
o
m
p
r
i
s
e
s
f
o
u
r
k
e
y
s
t
a
g
es
:
i
)
d
a
t
a
s
et
g
e
n
e
r
a
t
i
o
n
a
n
d
p
r
e
p
r
o
ce
s
s
i
n
g
,
ii
)
f
e
at
u
r
e
s
e
l
e
c
ti
o
n
a
n
d
n
o
r
m
a
l
i
z
a
t
i
o
n
,
ii
i
)
m
o
d
e
l
t
r
a
i
n
i
n
g
u
s
i
n
g
s
u
p
e
r
v
i
s
ed
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
m
s
,
a
n
d
iv
)
p
e
r
f
o
r
m
a
n
c
e
e
v
a
l
u
a
t
i
o
n
u
s
i
n
g
ap
p
r
o
p
r
i
a
t
e
m
e
t
r
i
cs
.
T
wo
r
ep
r
esen
tativ
e
s
u
p
er
v
is
ed
lear
n
in
g
m
eth
o
d
s
ar
e
c
o
n
s
id
er
ed
:
ANN
,
as
s
h
o
wn
in
Fig
u
r
e
1
,
an
d
XGBo
o
s
t
,
as
s
h
o
wn
in
Fig
u
r
e
2
.
T
h
ese
m
o
d
els
ar
e
tr
ain
e
d
to
lear
n
th
e
in
v
er
s
e
d
y
n
a
m
ics
o
f
th
e
m
o
t
o
r
,
ef
f
ec
tiv
ely
m
ap
p
in
g
d
esire
d
o
u
tp
u
ts
(
e.
g
.
,
to
r
q
u
e
,
s
p
ee
d
)
a
n
d
m
ea
s
u
r
ed
s
tates
to
th
e
co
r
r
esp
o
n
d
in
g
co
n
tr
o
l
s
ig
n
als (
e.
g
.
,
cu
r
r
en
t r
e
f
er
en
ce
,
g
atin
g
s
ig
n
als).
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Po
w
E
lec
&
Dr
i Sy
s
t
I
SS
N:
2088
-
8
6
9
4
S
u
p
ervis
ed
lea
r
n
in
g
fo
r
fa
s
t in
ve
r
s
e
mo
to
r
co
n
tr
o
l
ma
p
p
in
g
:
a
co
mp
a
r
a
tive
…
(
S
.
S
u
d
h
ee
r
K
u
ma
r
R
ed
d
y
)
2421
Fig
u
r
e
1
.
ANN
ar
ch
itectu
r
e
f
o
r
in
v
er
s
e
co
n
tr
o
l m
a
p
p
in
g
Fig
u
r
e
2
.
XGBo
o
s
t m
o
d
el
f
lo
w
2
.
1
.
Da
t
a
s
et
g
ener
a
t
io
n a
nd
co
llect
io
n
T
o
tr
ain
an
d
e
v
alu
ate
m
ac
h
in
e
lear
n
in
g
m
o
d
els
f
o
r
f
ast
in
v
er
s
e
co
n
tr
o
l
m
ap
p
in
g
,
s
y
n
t
h
et
ic
d
atasets
wer
e
g
en
er
ated
f
o
r
SR
M
an
d
B
L
DC
,
an
d
ar
e
lis
ted
in
T
ab
le
1
.
T
h
e
d
ata
wer
e
eith
er
co
llec
ted
v
ia
h
ig
h
-
f
i
d
elity
m
o
to
r
s
im
u
latio
n
s
o
r
d
ir
ec
tly
f
r
o
m
e
x
p
er
im
e
n
tal
m
o
to
r
b
e
n
ch
es
u
n
d
e
r
v
ar
io
u
s
o
p
er
atin
g
c
o
n
d
itio
n
s
.
T
h
e
s
y
s
tem
in
p
u
ts
in
clu
d
e
d
esire
d
to
r
q
u
e,
s
p
ee
d
,
lo
ad
,
r
o
t
o
r
a
n
g
l
e,
an
d
s
u
p
p
l
y
v
o
ltag
e
,
wh
ile
t
h
e
o
u
tp
u
t r
ep
r
esen
ts
th
e
r
eq
u
ir
e
d
co
n
tr
o
l
s
ig
n
al
o
r
cu
r
r
en
t
r
e
f
er
en
ce
,
ef
f
ec
tiv
el
y
s
o
lv
in
g
th
e
i
n
v
er
s
e
co
n
t
r
o
l
m
ap
p
in
g
p
r
o
b
lem
.
E
ac
h
d
ataset
co
n
s
is
ts
o
f
1
0
,
0
0
0
–
5
0
,
0
0
0
s
am
p
les
,
an
d
all
f
ea
tu
r
es
wer
e
n
o
r
m
alize
d
u
s
in
g
Min
Ma
x
s
ca
lin
g
to
en
s
u
r
e
u
n
if
o
r
m
ity
ac
r
o
s
s
tr
ain
in
g
an
d
test
in
g
p
h
ases
.
2
.
2
.
F
e
a
t
ure
des
cr
iptio
n
I
n
p
u
t
f
e
a
t
u
r
e
s
w
e
r
e
s
el
e
c
te
d
b
a
s
e
d
o
n
t
h
ei
r
p
h
y
s
ic
a
l
r
e
l
e
v
a
n
c
e
t
o
m
o
t
o
r
c
o
n
t
r
o
l
a
n
d
t
h
e
i
r
i
m
p
a
ct
o
n
m
o
t
o
r
d
y
n
a
m
i
c
s
.
T
h
e
s
e
i
n
cl
u
d
e
b
o
t
h
m
e
a
s
u
r
a
b
l
e
s
i
g
n
a
l
s
a
n
d
c
o
n
t
r
o
l
r
e
f
e
r
e
n
c
e
s
a
r
e
g
i
v
e
n
i
n
T
a
b
l
e
2
.
T
h
e
t
a
r
g
e
t
v
a
r
i
a
b
l
e
i
s
t
h
e
i
n
v
e
r
s
e
m
a
p
p
e
d
c
o
n
t
r
o
l
s
i
g
n
a
l
r
e
q
u
i
r
e
d
to
a
c
h
i
e
v
e
t
h
e
s
p
ec
i
f
i
e
d
m
o
t
o
r
b
e
h
a
v
i
o
r
.
T
ab
le
1
.
Mo
t
o
r
p
a
r
am
eter
s
u
s
ed
f
o
r
SR
M
an
d
B
L
DC
da
tasets
D
e
scri
p
t
i
o
n
Ty
p
e
U
n
i
t
s
S
R
M
r
a
n
g
e
B
LD
C
r
a
n
g
e
A
p
p
l
i
e
d
i
n
p
u
t
v
o
l
t
a
g
e
I
n
p
u
t
V
o
l
t
s (V
)
0
–
4
0
0
V
0
–
4
0
0
V
P
h
a
se
c
u
r
r
e
n
t
I
n
p
u
t
A
mp
(
A
)
0
–
5
0
A
0
–
5
0
A
R
o
t
a
t
i
o
n
a
l
sp
e
e
d
o
f
m
o
t
o
r
I
n
p
u
t
R
P
M
0
–
5
0
0
0
R
P
M
0
–
5
0
0
0
R
P
M
O
u
t
p
u
t
t
o
r
q
u
e
O
u
t
p
u
t
/
t
a
r
g
e
t
Nm
C
a
l
c
u
l
a
t
e
d
o
r
m
e
a
s
u
r
e
d
C
a
l
c
u
l
a
t
e
d
o
r
m
e
a
s
u
r
e
d
M
e
c
h
a
n
i
c
a
l
l
o
a
d
a
p
p
l
i
e
d
I
n
p
u
t
Nm
0
–
5
0
N
m
0
–
5
0
N
m
O
u
t
p
u
t
/
I
n
p
u
t
p
o
w
e
r
r
a
t
i
o
D
e
r
i
v
e
d
%
C
o
m
p
u
t
e
d
f
r
o
m
t
h
e
p
r
e
d
i
c
t
i
o
n
C
o
m
p
u
t
e
d
f
r
o
m
t
h
e
p
r
e
d
i
c
t
i
o
n
O
p
e
r
a
t
i
n
g
t
e
mp
e
r
a
t
u
r
e
I
n
p
u
t
°C
2
5
–
8
0
°
C
2
5
–
8
0
°
C
R
e
g
r
e
ssi
o
n
t
a
r
g
e
t
Ta
r
g
e
t
C
u
s
t
o
m
F
r
o
m
d
a
t
a
se
t
F
r
o
m
d
a
t
a
se
t
T
ab
le
2
.
I
n
p
u
t
f
ea
tu
r
es u
s
ed
f
o
r
in
v
er
s
e
co
n
tr
o
l m
a
p
p
in
g
F
e
a
t
u
r
e
S
y
mb
o
l
U
n
i
t
D
e
scri
p
t
i
o
n
D
e
si
r
e
d
t
o
r
q
u
e
T
∗
Nm
Ta
r
g
e
t
t
o
r
q
u
e
t
o
b
e
p
r
o
d
u
c
e
d
b
y
t
h
e
mo
t
o
r
R
o
t
o
r
sp
e
e
d
ω
r
a
d
/
s
I
n
st
a
n
t
a
n
e
o
u
s
a
n
g
u
l
a
r
v
e
l
o
c
i
t
y
R
o
t
o
r
p
o
si
t
i
o
n
θ
d
e
g
r
e
e
s
R
o
t
o
r
a
n
g
l
e
(
m
e
c
h
a
n
i
c
a
l
p
o
s
i
t
i
o
n
)
Lo
a
d
t
o
r
q
u
e
T
L
Nm
Lo
a
d
a
p
p
l
i
e
d
t
o
t
h
e
m
o
t
o
r
s
h
a
f
t
D
C
su
p
p
l
y
v
o
l
t
a
g
e
V
dc
V
o
l
t
s
V
o
l
t
a
g
e
l
e
v
e
l
s
u
p
p
l
i
e
d
t
o
t
h
e
i
n
v
e
r
t
e
r
/
mo
t
o
r
Te
mp
e
r
a
t
u
r
e
(
o
p
t
i
o
n
a
l
)
T
e
nv
°C
A
mb
i
e
n
t
o
r
w
i
n
d
i
n
g
t
e
mp
e
r
a
t
u
r
e
(
o
p
t
i
o
n
a
l
)
C
o
n
t
r
o
l
o
u
t
p
u
t
(
t
a
r
g
e
t
)
I
∗
A
mp
e
r
e
s
O
u
t
p
u
t
c
u
r
r
e
n
t
o
r
c
o
n
t
r
o
l
i
n
p
u
t
r
e
q
u
i
r
e
d
3.
M
AT
H
E
M
AT
I
CA
L
F
O
RM
UL
A
T
I
O
N
I
n
v
er
s
e
m
o
to
r
co
n
tr
o
l
aim
s
t
o
co
m
p
u
te
th
e
co
n
tr
o
l
in
p
u
t
u
(
t)
r
eq
u
ir
e
d
t
o
p
r
o
d
u
ce
a
d
e
s
ir
ed
m
o
to
r
o
u
tp
u
t
Yd
(
t)
,
s
u
ch
as
to
r
q
u
e
o
r
s
p
ee
d
.
Un
lik
e
f
o
r
war
d
m
o
d
els
,
wh
ich
s
im
u
late
s
y
s
tem
o
u
tp
u
t
f
r
o
m
k
n
o
wn
in
p
u
ts
,
in
v
er
s
e
m
o
d
els m
ap
th
e
tar
g
et
o
u
tp
u
t b
ac
k
to
th
e
c
o
n
tr
o
l sig
n
als n
ee
d
ed
to
ac
h
iev
e
it.
3
.
1
.
P
r
o
blem
s
t
a
t
e
m
ent
I
n
a
tr
a
d
itio
n
al
m
o
t
o
r
c
o
n
tr
o
l
s
y
s
tem
,
th
e
m
o
to
r
’
s
b
eh
a
v
io
r
is
r
ep
r
esen
ted
b
y
a
f
o
r
war
d
d
y
n
am
ics
f
u
n
ctio
n
as
g
iv
en
in
(
1
)
,
an
d
th
e
in
v
er
s
e
co
n
tr
o
l p
r
o
b
lem
ca
n
b
e
ex
p
r
ess
ed
as g
iv
en
in
(
2
)
.
(
)
=
(
(
)
,
(
)
)
(
1
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
6
9
4
I
n
t J Po
w
E
lec
&
Dr
i Sy
s
t
,
Vo
l.
16
,
No
.
4
,
Dec
em
b
er
20
25
:
2419
-
2
4
2
8
2422
(
)
=
−
1
(
(
)
,
(
)
)
(
2
)
W
h
er
e:
y(
t)
is
th
e
o
u
tp
u
t
(
e.
g
.
,
to
r
q
u
e
o
r
s
p
ee
d
)
,
u
(
t)
is
th
e
co
n
tr
o
l
in
p
u
t
(
e.
g
.
,
cu
r
r
en
t
r
ef
er
en
ce
,
v
o
ltag
e
s
ig
n
al,
o
r
PW
M
d
u
ty
cy
cle)
,
x
(
t)
r
ep
r
esen
ts
th
e
m
o
to
r
'
s
in
ter
n
al
s
tates
(
e.
g
.
,
s
p
ee
d
,
p
o
s
itio
n
,
lo
ad
)
,
Y
d
(
t)
is
th
e
d
esire
d
o
u
tp
u
t,
an
d
f
−1
(
⋅
)
is
th
e
in
v
er
s
e
o
f
t
h
e
s
y
s
tem
’
s
d
y
n
a
m
ics.
I
n
r
ea
l
-
wo
r
ld
s
y
s
tem
s
,
o
b
tain
i
n
g
an
an
aly
tical
f
o
r
m
o
f
f
−1
i
s
o
f
ten
in
f
ea
s
ib
le
d
u
e
to
n
o
n
lin
ea
r
ities
,
p
ar
am
eter
u
n
ce
r
tain
ties
,
an
d
co
u
p
lin
g
e
f
f
ec
ts
.
T
h
er
ef
o
r
e,
m
ac
h
in
e
lear
n
in
g
r
eg
r
ess
io
n
m
o
d
els
ar
e
u
s
ed
to
ap
p
r
o
x
im
ate
th
is
in
v
e
r
s
e
m
ap
p
in
g
as g
iv
e
n
in
(
3
)
.
∧
(
)
=
∧
−
1
(
(
)
,
(
)
)
(
3
)
W
h
er
e
f
θ
^
−
1
i
s
a
lear
n
ed
ap
p
r
o
x
im
atio
n
o
f
th
e
in
v
er
s
e
f
u
n
c
tio
n
,
p
ar
am
eter
ized
b
y
weig
h
ts
θ
.
T
h
e
m
o
d
el
is
tr
ain
ed
to
m
in
im
ize
th
e
m
ea
n
s
q
u
ar
ed
er
r
o
r
(
MSE
)
b
etwe
en
th
e
p
r
ed
icted
a
n
d
tr
u
e
c
o
n
tr
o
l
in
p
u
ts
,
wh
ich
ar
e
g
iv
en
in
(
4
)
.
(
)
=
1
∑
‖
∧
−
‖
2
=
1
(
4
)
W
h
er
e
N
is
th
e
n
u
m
b
er
o
f
tr
ai
n
in
g
s
am
p
les.
3
.
2
.
M
a
chine
lea
rning
m
o
de
ls
T
o
d
e
v
e
l
o
p
t
h
e
i
n
v
e
r
s
e
m
a
p
p
in
g
e
s
s
e
n
t
i
a
l
f
o
r
m
o
t
o
r
c
o
n
t
r
o
l
,
t
w
o
s
u
p
e
r
v
i
s
e
d
r
e
g
r
es
s
i
o
n
a
l
g
o
r
i
t
h
m
s
—
a
r
t
i
f
i
c
ia
l
n
e
u
r
a
l
n
e
t
w
o
r
k
(
A
N
N)
a
n
d
e
x
t
r
e
m
e
g
r
a
d
i
e
n
t
b
o
o
s
t
i
n
g
(
X
G
B
o
o
s
t
)
,
we
r
e
u
t
i
l
iz
e
d
.
T
h
e
s
e
l
e
ct
i
o
n
o
f
t
h
e
s
e
m
o
d
e
l
s
w
as
b
as
e
d
o
n
t
h
e
i
r
d
is
ti
n
c
t
a
d
v
a
n
t
a
g
es
:
t
h
e
A
NN
’
s
ca
p
a
b
i
l
i
t
y
t
o
r
e
p
r
es
e
n
t
i
n
t
r
i
c
at
e
n
o
n
l
i
n
e
a
r
d
y
n
a
m
i
c
s
,
a
n
d
X
G
B
o
o
s
t
’
s
e
f
f
i
c
i
e
n
c
y
i
n
h
a
n
d
l
i
n
g
s
t
r
u
c
t
u
r
e
d
d
a
ta
w
h
i
l
e
en
s
u
r
i
n
g
m
o
d
e
l
i
n
t
e
r
p
r
e
t
a
b
il
i
t
y
a
n
d
r
o
b
u
s
t
n
e
s
s
.
3
.
2
.
1
.
Art
if
icia
l
neura
l net
wo
rk
(
ANN)
A
f
ee
d
f
o
r
war
d
m
u
ltil
ay
er
p
er
ce
p
tr
o
n
with
two
h
id
d
en
lay
e
r
s
(
6
4
an
d
3
2
n
e
u
r
o
n
s
)
,
R
eL
U
ac
tiv
atio
n
,
tr
ain
ed
u
s
in
g
b
ac
k
p
r
o
p
a
g
atio
n
an
d
th
e
Ad
am
o
p
tim
izer
.
A
f
u
lly
co
n
n
ec
ted
f
ee
d
f
o
r
war
d
n
eu
r
al
n
etwo
r
k
was
d
esig
n
ed
with
th
e
f
o
llo
win
g
a
r
ch
itectu
r
e,
as sh
o
wn
in
Fi
g
u
r
e
3
.
i)
I
n
p
u
t
lay
er
:
r
ec
eiv
es
n
o
r
m
alize
d
f
ea
tu
r
es
s
u
ch
as
d
esire
d
to
r
q
u
e,
r
o
t
o
r
s
p
ee
d
,
p
o
s
itio
n
,
lo
ad
to
r
q
u
e,
an
d
v
o
ltag
e.
ii)
Hid
d
en
l
ay
er
s
:
f
ir
s
t
h
id
d
en
lay
er
:
6
4
n
eu
r
o
n
s
,
R
eL
U
ac
tiv
atio
n
;
an
d
s
ec
o
n
d
h
id
d
en
lay
er
:
3
2
n
eu
r
o
n
s
,
R
eL
U
ac
tiv
atio
n
.
iii)
Ou
tp
u
t
l
ay
er
:
p
r
o
d
u
ce
s
th
e
r
e
q
u
ir
ed
co
n
tr
o
l
s
ig
n
al
(
e.
g
.
,
p
h
ase
cu
r
r
en
t)
.
T
r
ain
in
g
d
etails:
a)
o
p
tim
izer
:
Ad
am
,
b
)
lo
s
s
f
u
n
ctio
n
:
m
ea
n
s
q
u
ar
e
d
er
r
o
r
(
MSE
)
,
c)
E
p
o
ch
s
:
1
0
0
–
2
0
0
(
ea
r
ly
s
to
p
p
i
n
g
u
s
ed
)
,
a
n
d
d
)
b
atch
s
ize:
1
2
8
.
3
.
2
.
2
.
E
x
t
re
m
e
g
ra
dient
bo
o
s
t
ing
(
XG
B
o
o
s
t
)
XGBo
o
s
t
i
s
a
h
ig
h
-
p
er
f
o
r
m
an
ce
g
r
ad
ien
t
-
b
o
o
s
ted
tr
ee
en
s
e
m
b
le
th
at
ex
ce
ls
in
ca
p
tu
r
in
g
n
o
n
lin
ea
r
in
ter
ac
tio
n
s
an
d
h
an
d
lin
g
s
tr
u
ctu
r
ed
d
ata.
A
g
r
a
d
ien
t
-
b
o
o
s
ted
tr
ee
en
s
em
b
le
with
1
0
0
esti
m
ato
r
s
an
d
a
lear
n
in
g
r
ate
o
f
0
.
1
,
k
n
o
wn
f
o
r
its
r
o
b
u
s
tn
ess
an
d
h
an
d
lin
g
o
f
n
o
n
lin
ea
r
ity
,
as
s
h
o
wn
i
n
Fig
u
r
e
4
.
M
o
d
el
c
o
n
f
ig
u
r
atio
n
:
n
u
m
b
er
o
f
tr
ee
s
:
100
,
l
ea
r
n
in
g
r
ate:
0
.
1
,
m
ax
im
u
m
d
e
p
th
:
6
,
b
r
e
g
:
s
q
u
ar
ed
e
r
r
o
r
,
an
d
s
u
b
s
am
p
le
r
atio
:
0.
8
XGBo
o
s
t
n
atu
r
ally
h
a
n
d
les f
ea
tu
r
e
i
n
ter
ac
tio
n
s
an
d
is
r
elativ
ely
r
o
b
u
s
t to
f
ea
tu
r
e
s
ca
lin
g
.
I
t a
ls
o
p
r
o
v
i
d
es in
ter
p
r
etab
le
i
n
s
ig
h
ts
th
r
o
u
g
h
f
ea
tu
r
e
im
p
o
r
t
an
ce
s
co
r
es.
Fig
u
r
e
3
.
Ar
c
h
itectu
r
e
o
f
th
e
a
r
tific
ial
n
eu
r
al
n
etwo
r
k
(
ANN)
m
o
d
el
f
o
r
in
v
e
r
s
e
m
o
t
o
r
co
n
t
r
o
l m
ap
p
in
g
Fig
u
r
e
4
.
E
x
tr
em
e
g
r
ad
ien
t
b
o
o
s
tin
g
f
lo
w
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Po
w
E
lec
&
Dr
i Sy
s
t
I
SS
N:
2088
-
8
6
9
4
S
u
p
ervis
ed
lea
r
n
in
g
fo
r
fa
s
t in
ve
r
s
e
mo
to
r
co
n
tr
o
l
ma
p
p
in
g
:
a
co
mp
a
r
a
tive
…
(
S
.
S
u
d
h
ee
r
K
u
ma
r
R
ed
d
y
)
2423
3.
3
.
T
ra
ini
ng
a
nd
v
a
lid
a
t
io
n
s
t
ra
t
eg
y
T
o
en
s
u
r
e
m
o
d
el
g
e
n
er
aliza
b
il
ity
an
d
p
r
ev
en
t
o
v
er
f
itti
n
g
,
th
e
f
o
llo
win
g
d
ata
h
an
d
lin
g
p
r
o
ce
d
u
r
es we
r
e
ad
o
p
ted
a
n
d
g
iv
en
in
(
5
)
.
-
T
r
ain
-
test
s
p
l
it
:
8
0
% o
f
th
e
d
at
a
was u
s
ed
f
o
r
tr
ain
i
n
g
,
a
n
d
2
0
% wa
s
r
eser
v
ed
f
o
r
test
in
g
.
-
C
r
o
s
s
-
v
alid
atio
n
:
f
iv
e
-
f
o
l
d
cr
o
s
s
-
v
alid
atio
n
was e
m
p
lo
y
ed
t
o
ass
es
s
r
o
b
u
s
tn
ess
ac
r
o
s
s
m
u
ltip
le
d
ata
p
ar
titi
o
n
s
.
-
No
r
m
aliza
tio
n
:
al
l f
ea
tu
r
es we
r
e
s
ca
led
u
s
in
g
m
in
-
m
ax
n
o
r
m
aliza
tio
n
to
th
e
r
a
n
g
e
[
0
,
1
]
.
-
R
o
o
t
m
ea
n
s
q
u
ar
e
d
er
r
o
r
(
R
M
SE)
:
=
√
1
∑
(
(
)
−
(
)
)
2
=
1
(
5)
4.
RE
SU
L
T
S AN
D
AN
AL
Y
SI
S
T
h
is
s
ec
tio
n
p
r
esen
ts
th
e
e
x
p
er
im
en
tal
r
esu
lts
o
f
a
p
p
ly
in
g
m
ac
h
in
e
lea
r
n
in
g
m
o
d
els
to
r
ea
l
-
tim
e
in
v
er
s
e
m
o
to
r
co
n
tr
o
l
m
a
p
p
in
g
o
f
SR
M
an
d
B
L
DC
m
o
to
r
s
.
B
o
th
m
o
d
els,
ANN
an
d
XG
B
o
o
s
t,
wer
e
tr
ain
ed
an
d
ev
alu
ate
d
f
o
r
th
eir
p
r
ed
ict
io
n
ac
cu
r
ac
y
,
co
m
p
u
tatio
n
al
e
f
f
icien
cy
,
a
n
d
r
ea
l
-
tim
e
s
u
itab
i
lity
.
4
.
1
.
Da
t
a
s
et
prepa
ra
t
io
n
Data
s
ets
f
o
r
SR
M
an
d
B
L
DC
m
o
to
r
s
wer
e
eith
er
s
y
n
th
etica
lly
g
en
er
ated
v
ia
h
i
g
h
-
f
id
elity
s
im
u
latio
n
s
o
r
co
llected
th
r
o
u
g
h
ex
p
er
im
en
tal
s
etu
p
s
.
T
h
ese
d
atasets
ca
p
tu
r
e
a
r
an
g
e
o
f
o
p
er
atin
g
co
n
d
itio
n
s
an
d
in
clu
d
e
v
ar
ia
b
les
s
u
ch
as
to
r
q
u
e,
s
p
ee
d
,
v
o
l
tag
e,
r
o
to
r
p
o
s
itio
n
,
a
n
d
lo
a
d
.
All
f
ea
tu
r
es
wer
e
n
o
r
m
alize
d
u
s
in
g
Min
Ma
x
s
ca
lin
g
.
E
ac
h
d
ataset
was
s
p
lit
in
to
tr
ain
in
g
(
8
0
%)
an
d
test
in
g
(
2
0
%)
s
ets
b
ef
o
r
e
m
o
d
el
f
itti
n
g
.
4
.
2
.
M
o
del
co
nfig
ura
t
io
n su
m
m
a
r
y
ANN
:
A
f
ee
d
f
o
r
war
d
m
u
ltil
a
y
er
p
er
ce
p
tr
o
n
(
ML
P)
co
m
p
r
is
in
g
two
h
id
d
en
lay
e
r
s
with
6
4
an
d
3
2
n
eu
r
o
n
s
,
r
esp
ec
tiv
ely
.
R
eL
U
ac
tiv
atio
n
was
u
s
ed
th
r
o
u
g
h
o
u
t,
an
d
th
e
m
o
d
el
was
o
p
tim
ized
u
s
in
g
t
h
e
Ad
a
m
o
p
tim
izer
.
XGBo
o
s
t
:
A
g
r
ad
i
en
t
-
b
o
o
s
ted
e
n
s
em
b
le
o
f
1
0
0
d
ec
is
io
n
tr
ee
s
tr
ain
ed
with
a
l
ea
r
n
in
g
r
ate
o
f
0
.
1
an
d
a
m
ax
im
u
m
tr
ee
d
ep
th
o
f
6
.
Kn
o
wn
f
o
r
its
s
ca
lab
ilit
y
a
n
d
r
o
b
u
s
tn
ess
,
XGBo
o
s
t
i
s
ef
f
ec
tiv
e
in
ca
p
tu
r
in
g
co
m
p
lex
n
o
n
lin
ea
r
in
ter
ac
tio
n
s
.
4
.
3
.
L
ea
rning
curv
e
a
na
ly
s
is
T
o
u
n
d
e
r
s
t
a
n
d
t
h
e
c
o
n
v
e
r
g
e
n
c
e
b
e
h
a
v
i
o
r
o
f
t
h
e
m
o
d
e
l
s
,
l
e
a
r
n
i
n
g
c
u
r
v
e
s
w
e
r
e
p
l
o
t
t
e
d
b
y
v
a
r
y
i
n
g
t
h
e
t
r
a
i
n
i
n
g
s
et
s
iz
e
a
n
d
r
e
c
o
r
d
i
n
g
t
h
e
c
o
r
r
e
s
p
o
n
d
i
n
g
R
²
s
c
o
r
e
o
n
t
h
e
v
a
l
i
d
a
t
i
o
n
s
et
.
F
i
g
u
r
es
5
a
n
d
6
s
h
o
w
h
o
w
t
h
e
p
r
e
d
i
c
t
i
o
n
p
e
r
f
o
r
m
a
n
c
e
(
R
²
s
c
o
r
e
)
o
f
A
N
N
a
n
d
X
GB
o
o
s
t
e
v
o
l
v
e
s
w
it
h
i
n
c
r
e
a
s
i
n
g
t
r
a
i
n
i
n
g
d
a
t
a
f
o
r
t
h
e
S
R
M
m
o
t
o
r
.
B
o
t
h
m
o
d
e
ls
d
em
o
n
s
t
r
a
t
e
u
p
wa
r
d
t
r
e
n
d
s
i
n
ac
c
u
r
a
c
y
,
c
o
n
f
i
r
m
i
n
g
e
f
f
e
c
ti
v
e
l
e
a
r
n
i
n
g
.
XG
B
o
o
s
t
r
e
a
c
h
e
s
h
i
g
h
e
r
R
²
v
a
l
u
es
m
o
r
e
q
u
i
c
k
l
y
,
i
n
d
i
c
a
t
i
n
g
b
e
tt
e
r
g
e
n
e
r
a
l
i
z
a
ti
o
n
e
v
e
n
w
i
t
h
s
m
a
ll
e
r
t
r
a
in
i
n
g
s
u
b
s
e
ts
.
T
h
is
r
ef
lects XG
B
o
o
s
t’
s
ab
ili
t
y
to
ef
f
icien
tly
e
x
tr
ac
t p
atter
n
s
in
lo
w
-
d
ata
co
n
d
itio
n
s
,
wh
ich
is
cr
itical
in
r
ea
l
-
tim
e
co
n
tr
o
l
wh
er
e
la
b
eled
d
ata
m
ig
h
t
b
e
lim
ited
.
Similar
to
th
e
S
R
M
ca
s
e,
th
i
s
p
lo
t
v
is
u
alize
s
th
e
lear
n
in
g
b
e
h
av
io
r
f
o
r
t
h
e
B
L
DC
m
o
to
r
.
W
h
ile
b
o
th
m
o
d
el
s
ev
en
tu
ally
co
n
v
er
g
e
t
o
h
ig
h
R
²
s
co
r
es,
XGBo
o
s
t
ag
ain
ex
h
ib
its
f
aster
co
n
v
e
r
g
e
n
ce
.
T
h
e
s
teep
er
s
lo
p
e
o
f
XG
B
o
o
s
t’
s
cu
r
v
e
at
s
m
aller
d
atas
et
s
izes
em
p
h
asizes
its
s
u
p
er
io
r
d
ata
ef
f
icien
cy
.
T
h
is
is
p
ar
ticu
lar
ly
im
p
o
r
tan
t
i
n
s
ce
n
ar
io
s
in
v
o
lv
in
g
d
y
n
am
i
c
lo
ad
s
an
d
f
r
e
q
u
en
t
tr
an
s
itio
n
s
in
m
o
to
r
s
tates.
F
ig
u
r
e
s
5
an
d
6
s
h
o
w
th
at
b
o
th
m
o
d
els
ac
h
iev
e
h
ig
h
ac
c
u
r
ac
y
r
ap
id
ly
,
with
XGBo
o
s
t c
o
n
v
er
g
in
g
s
lig
h
tly
f
aster
,
in
d
icatin
g
b
etter
lear
n
in
g
ef
f
icien
cy
o
n
s
m
aller
d
atasets
.
Fig
u
r
e
5
.
L
ea
r
n
in
g
cu
r
v
e
f
o
r
SR
M
m
o
to
r
u
s
in
g
ANN
an
d
XGBo
o
s
t
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
6
9
4
I
n
t J Po
w
E
lec
&
Dr
i Sy
s
t
,
Vo
l.
16
,
No
.
4
,
Dec
em
b
er
20
25
:
2419
-
2
4
2
8
2424
Fig
u
r
e
6
.
L
ea
r
n
in
g
cu
r
v
e
f
o
r
B
L
DC
mo
to
r
u
s
in
g
ANN
an
d
XGBo
o
s
t
4
.
4
.
Resid
ua
l
dis
t
ributio
n
R
esid
u
al
p
lo
ts
,
a
s
s
h
o
wn
in
Fig
u
r
e
7
,
p
r
o
v
id
e
in
s
ig
h
ts
in
to
th
e
d
is
tr
ib
u
tio
n
o
f
p
r
ed
icti
o
n
er
r
o
r
s
.
I
d
ea
lly
,
r
esid
u
als
s
h
o
u
l
d
b
e
c
en
ter
ed
ar
o
u
n
d
ze
r
o
with
m
in
im
al
s
p
r
ea
d
.
F
ig
u
r
e
7
co
m
p
ar
es
th
e
r
esid
u
als
—
d
if
f
er
en
ce
s
b
etwe
en
p
r
e
d
icted
an
d
ac
tu
al
o
u
tp
u
ts
,
f
o
r
b
o
th
m
o
d
els
an
d
m
o
to
r
ty
p
es.
I
d
ea
l
ly
,
r
esid
u
als
s
h
o
u
ld
b
e
s
y
m
m
etr
ically
d
is
tr
ib
u
te
d
ar
o
u
n
d
ze
r
o
with
m
in
im
al
s
p
r
ea
d
.
XGBo
o
s
t
d
is
p
lay
s
a
tig
h
ter
r
esid
u
al
s
p
r
ea
d
f
o
r
b
o
th
m
o
to
r
s
,
in
d
icatin
g
m
o
r
e
c
o
n
s
is
ten
t
an
d
ac
cu
r
ate
p
r
ed
ictio
n
s
.
ANN,
wh
ile
s
till
ef
f
ec
tiv
e,
s
h
o
ws
a
b
r
o
ad
e
r
d
is
tr
ib
u
tio
n
,
s
u
g
g
e
s
tin
g
o
cc
asio
n
al
lar
g
e
r
d
ev
iatio
n
s
f
r
o
m
g
r
o
u
n
d
tr
u
t
h
.
XGBo
o
s
t
ex
h
ib
its
tig
h
ter
r
esid
u
al
clu
s
ter
in
g
co
m
p
ar
ed
t
o
ANN,
s
u
g
g
esti
n
g
f
ewe
r
la
r
g
e
er
r
o
r
s
an
d
b
etter
c
o
n
s
is
ten
cy
in
p
r
ed
ictio
n
s
.
4
.
5
.
F
e
a
t
ure
im
po
rt
a
nce
a
na
ly
s
is
Featu
r
e
im
p
o
r
tan
ce
was
ass
es
s
ed
to
u
n
d
er
s
tan
d
wh
ich
in
p
u
t
f
ea
tu
r
es
h
ad
th
e
m
o
s
t
in
f
lu
en
ce
o
n
th
e
m
o
d
el'
s
o
u
tp
u
t.
Fig
u
r
e
8
v
is
u
alize
s
wh
ich
in
p
u
t
f
ea
t
u
r
es
m
o
s
t
s
ig
n
if
ican
tly
im
p
ac
t
m
o
d
el
p
r
ed
ictio
n
s
.
Fo
r
XGBo
o
s
t,
im
p
o
r
tan
ce
is
d
er
iv
ed
f
r
o
m
s
p
lit g
ain
,
wh
ile
f
o
r
A
NN,
SHAP v
alu
es in
d
icate
co
n
tr
ib
u
tio
n
.
I
n
b
o
th
m
o
t
o
r
s
an
d
m
o
d
els,
r
o
to
r
p
o
s
itio
n
an
d
d
esire
d
to
r
q
u
e
co
n
s
is
ten
tly
r
an
k
h
ig
h
est.
T
h
is
co
n
f
ir
m
s
th
eir
d
o
m
in
an
t
r
o
le
in
in
v
er
s
e
co
n
tr
o
l
m
ap
p
i
n
g
,
ali
g
n
in
g
with
p
h
y
s
ical
m
o
to
r
b
e
h
av
io
r
wh
er
e
to
r
q
u
e
co
n
tr
o
l
is
h
ig
h
ly
d
e
p
en
d
e
n
t
o
n
r
o
to
r
d
y
n
am
ics.
Fo
r
XGBo
o
s
t
,
f
ea
tu
r
e
im
p
o
r
tan
ce
was
co
m
p
u
ted
u
s
in
g
b
u
ilt
-
in
g
ain
-
b
ased
m
etr
ics
,
an
d
f
o
r
ANN
,
SHAP
(
S
Hap
ley
Ad
d
itiv
e
ex
Plan
atio
n
s
)
v
alu
es
wer
e
u
s
ed
f
o
r
in
ter
p
r
etab
ilit
y
.
I
n
b
o
th
ca
s
es,
r
o
to
r
p
o
s
itio
n
an
d
d
esire
d
t
o
r
q
u
e
e
m
er
g
ed
as
d
o
m
i
n
an
t
f
e
atu
r
es,
h
ig
h
lig
h
tin
g
th
eir
cr
itical
r
o
le
in
in
v
er
s
e
co
n
tr
o
l m
ap
p
in
g
.
Fig
u
r
e
7
.
R
esid
u
al
d
is
t
r
ib
u
tio
n
f
o
r
SR
M
&
B
L
DC
mo
to
r
u
s
in
g
ANN
an
d
XGBo
o
s
t
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Po
w
E
lec
&
Dr
i Sy
s
t
I
SS
N:
2088
-
8
6
9
4
S
u
p
ervis
ed
lea
r
n
in
g
fo
r
fa
s
t in
ve
r
s
e
mo
to
r
co
n
tr
o
l
ma
p
p
in
g
:
a
co
mp
a
r
a
tive
…
(
S
.
S
u
d
h
ee
r
K
u
ma
r
R
ed
d
y
)
2425
Fig
u
r
e
8
.
Featu
r
e
im
p
o
r
ta
n
ce
f
o
r
SR
M
&
B
L
DC
m
o
to
r
u
s
in
g
ANN
an
d
XGBo
o
s
t
4
.
6
.
M
o
del
ef
f
iciency
a
nd
a
c
cura
cy
co
m
pa
riso
n
Mo
d
el
ef
f
icien
cy
was
ev
alu
ated
u
s
in
g
p
r
ed
icted
v
s
.
ac
tu
al
m
o
to
r
ef
f
icien
c
y
,
an
d
r
e
s
u
lts
wer
e
s
u
m
m
ar
ized
u
s
in
g
b
o
x
p
lo
ts
.
E
f
f
icien
cy
d
is
tr
ib
u
tio
n
s
o
f
ANN
an
d
XGBo
o
s
t
m
o
d
els
ar
e
s
h
o
wn
v
ia
b
o
x
p
lo
ts
in
Fig
u
r
e
9
,
co
m
p
a
r
in
g
p
r
ed
icte
d
m
o
to
r
ef
f
icien
c
y
with
ac
tu
a
l
p
er
f
o
r
m
an
ce
.
XGBo
o
s
t
ac
h
iev
es
tig
h
ter
b
o
x
p
lo
t
b
o
u
n
d
s
an
d
h
ig
h
er
m
e
d
ian
e
f
f
icien
cy
v
alu
es
f
o
r
b
o
th
m
o
to
r
ty
p
es,
r
ef
lectin
g
g
r
ea
ter
p
r
ec
is
io
n
an
d
less
v
ar
ian
ce
.
ANN,
alth
o
u
g
h
co
m
p
etitiv
e,
s
h
o
ws
s
lig
h
tly
lo
w
er
m
ed
ian
s
an
d
b
r
o
a
d
er
s
p
r
ea
d
s
,
in
d
icatin
g
m
o
r
e
v
ar
iab
ilit
y
in
p
r
ed
ictio
n
ac
c
u
r
ac
y
.
T
h
is
r
ein
f
o
r
ce
s
XGBo
o
s
t's
ad
v
an
tag
e
in
b
o
t
h
ac
c
u
r
ac
y
a
n
d
co
n
s
is
ten
cy
.
Fig
u
r
e
9
.
E
f
f
icien
cy
c
o
m
p
ar
is
o
n
o
f
SR
M
an
d
B
L
DC
m
o
d
els
T
ab
le
3
s
h
o
ws
th
at
XGBo
o
s
t
co
n
s
is
ten
tly
o
u
tp
er
f
o
r
m
s
t
h
e
ANN
m
o
d
el
ac
r
o
s
s
all
ev
alu
at
io
n
m
etr
ics
f
o
r
b
o
th
SR
M
an
d
B
L
DC
m
o
to
r
s
.
I
t
ac
h
iev
es
lo
wer
m
ea
n
s
q
u
ar
ed
er
r
o
r
s
(
0
.
0
0
2
8
f
o
r
S
R
M
an
d
0
.
0
0
4
4
f
o
r
B
L
DC
)
an
d
h
ig
h
er
R
²
s
co
r
es,
in
d
icatin
g
m
o
r
e
ac
cu
r
ate
an
d
r
eliab
le
p
r
e
d
ictio
n
s
.
Ad
d
itio
n
ally
,
XGBo
o
s
t
ex
h
ib
its
f
aster
tr
ain
in
g
tim
es
a
n
d
lo
wer
in
f
er
e
n
ce
laten
c
y
,
w
h
ich
ar
e
cr
u
cial
f
o
r
r
ea
l
-
tim
e
c
o
n
tr
o
l
a
p
p
licatio
n
s
.
I
n
ter
m
s
o
f
e
f
f
icien
cy
,
XGBo
o
s
t
also
lead
s
with
9
6
.
5
%
f
o
r
SR
M
an
d
9
4
.
7
%
f
o
r
B
L
DC
,
co
m
p
ar
ed
to
ANN’
s
9
4
.
8
%
a
n
d
9
2
.
3
%,
r
esp
ec
tiv
el
y
.
T
h
ese
r
esu
lts
h
ig
h
lig
h
t
XG
B
o
o
s
t’
s
s
u
p
er
io
r
p
er
f
o
r
m
an
ce
an
d
s
u
itab
ilit
y
f
o
r
r
ea
l
-
tim
e
in
v
er
s
e
m
o
t
o
r
co
n
tr
o
l ta
s
k
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
6
9
4
I
n
t J Po
w
E
lec
&
Dr
i Sy
s
t
,
Vo
l.
16
,
No
.
4
,
Dec
em
b
er
20
25
:
2419
-
2
4
2
8
2426
T
h
e
lar
g
er
g
ain
s
o
f
XGBo
o
s
t
o
v
er
ANN
o
n
SR
M
s
tem
f
r
o
m
SR
M
p
h
y
s
ics:
its
d
o
u
b
ly
s
alien
t
s
tr
u
ctu
r
e
an
d
d
ee
p
m
ag
n
etic
s
atu
r
atio
n
cr
ea
te
a
h
ig
h
l
y
n
o
n
li
n
ea
r
,
an
g
le
-
d
ep
e
n
d
en
t
to
r
q
u
e
–
cu
r
r
en
t
r
elatio
n
s
h
ip
with
p
r
o
n
o
u
n
ce
d
r
ip
p
le.
L
ea
r
n
in
g
s
u
c
h
p
iece
wis
e,
in
te
r
ac
tio
n
-
h
ea
v
y
i
n
v
er
s
e
m
a
p
p
in
g
s
b
en
ef
its
f
r
o
m
b
o
o
s
ted
tr
ee
s
’
ab
ilit
y
to
ca
p
t
u
r
e
h
ete
r
o
g
en
eo
u
s
r
e
g
im
es
an
d
s
h
ar
p
s
p
lits
,
y
ield
in
g
tig
h
ter
r
esid
u
als
an
d
lo
wer
v
ar
ian
ce
ac
r
o
s
s
r
u
n
s
.
C
o
n
v
er
s
ely
,
B
L
DC
to
r
q
u
e
is
m
o
r
e
r
ep
ea
tab
le
u
n
d
er
tr
ap
ez
o
i
d
al/s
in
u
s
o
id
al
b
ac
k
-
E
MF
an
d
d
is
cr
ete
co
m
m
u
tatio
n
e
v
en
ts
,
s
o
b
o
th
m
o
d
els
f
it
well
an
d
th
e
p
er
f
o
r
m
an
ce
g
ap
n
a
r
r
o
w
s
.
C
o
n
s
is
ten
tly
,
o
u
r
f
ea
tu
r
e
-
im
p
o
r
tan
ce
an
al
y
s
is
r
an
k
s
r
o
to
r
p
o
s
itio
n
an
d
d
esire
d
to
r
q
u
e
as
th
e
to
p
d
r
i
v
er
s
f
o
r
b
o
th
m
o
to
r
s
(
r
ef
lectin
g
to
r
q
u
e
r
elian
ce
o
n
elec
tr
o
m
ec
h
an
ical
alig
n
m
e
n
t)
,
an
d
r
esid
u
al
p
lo
ts
s
h
o
w
XGB
o
o
s
t’
s
tig
h
ter
er
r
o
r
s
p
r
ea
d
.
T
h
ese
p
atter
n
s
alig
n
with
th
e
s
tati
s
tically
s
ig
n
if
ican
t
im
p
r
o
v
em
e
n
ts
r
e
p
o
r
ted
in
T
ab
le
3
(
lo
wer
MSE
,
h
ig
h
er
R
²,
n
a
r
r
o
wer
C
I
s
,
an
d
p
<
0
.
0
1
v
s
.
ANN)
.
T
ab
le
3
.
Per
f
o
r
m
an
ce
c
o
m
p
a
r
is
o
n
o
f
ANN
an
d
XGBo
o
s
t f
o
r
SR
M
an
d
B
L
DC
m
o
to
r
s
M
o
d
e
l
M
o
t
o
r
t
y
p
e
M
S
E
±
S
D
R
²
s
c
o
r
e
(
9
5
%
C
I
)
Tr
a
i
n
i
n
g
t
i
m
e
(
s)
La
t
e
n
c
y
(
s)
Ef
f
i
c
i
e
n
c
y
(
%
±
S
D
)
p
-
v
a
l
u
e
(
v
s
ANN)
ANN
S
R
M
0
.
0
0
3
5
±
0
.
0
0
0
2
0
.
9
9
5
4
(
0
.
9
9
4
9
–
0
.
9
9
5
9
)
2
5
.
4
0
.
0
1
2
9
4
.
8
±
0
.
3
–
X
G
B
o
o
st
S
R
M
0
.
0
0
2
8
±
0
.
0
0
0
1
0
.
9
9
7
2
(
0
.
9
9
6
9
–
0
.
9
9
7
5
)
1
8
.
7
0
.
0
1
0
9
6
.
5
±
0
.
2
0
.
0
0
4
ANN
B
LD
C
0
.
0
0
5
2
±
0
.
0
0
0
3
0
.
9
9
3
7
(
0
.
9
9
3
0
–
0
.
9
9
4
4
)
3
0
.
1
0
.
0
1
5
9
2
.
3
±
0
.
4
–
X
G
B
o
o
st
B
LD
C
0
.
0
0
4
4
±
0
.
0
0
0
2
0
.
9
9
6
1
(
0
.
9
9
5
6
–
0
.
9
9
6
6
)
2
0
.
3
0
.
0
1
2
9
4
.
7
±
0
.
3
0
.
0
0
6
N
o
t
e
:
S
D
=
S
t
a
n
d
a
r
d
d
e
v
i
a
t
i
o
n
f
r
o
m
n
=
1
0
r
u
n
s
;
9
5
%
C
I
=
C
o
n
f
i
d
e
n
c
e
i
n
t
e
r
v
a
l
o
n
R
²
;
p
-
v
a
l
u
e
c
o
mp
u
t
e
d
u
si
n
g
p
a
i
r
e
d
t
-
t
e
st
b
e
t
w
e
e
n
A
N
N
a
n
d
X
G
B
o
o
st
p
e
r
mo
t
o
r
t
y
p
e
;
a
n
d
B
o
l
d
p
-
v
a
l
u
e
s
(
<
0
.
0
5
)
i
n
d
i
c
a
t
e
a
st
a
t
i
s
t
i
c
a
l
l
y
s
i
g
n
i
f
i
c
a
n
t
d
i
f
f
e
r
e
n
c
e
.
T
o
f
u
r
t
h
er
co
n
tex
tu
alize
th
e
b
en
ef
its
o
f
s
u
p
er
v
is
ed
le
ar
n
in
g
,
a
q
u
alitativ
e
co
m
p
a
r
is
o
n
with
co
n
v
en
tio
n
al
co
n
tr
o
ller
s
is
p
r
o
v
id
ed
in
T
ab
le
4
.
As
s
h
o
wn
in
T
ab
le
4
,
class
ical
co
n
tr
o
lle
r
s
s
u
ch
as
PID
an
d
MPC
ar
e
ef
f
ec
tiv
e
in
s
tr
u
ct
u
r
ed
co
n
d
itio
n
s
b
u
t
r
eq
u
i
r
e
p
r
ec
is
e
m
o
d
elin
g
o
r
f
r
e
q
u
en
t
r
etu
n
in
g
u
n
d
er
n
o
n
lin
ea
r
ities
.
I
n
co
n
tr
ast,
s
u
p
er
v
is
ed
lear
n
in
g
m
o
d
els
(
A
NN,
XGBo
o
s
t)
lev
er
ag
e
d
ata
-
d
r
iv
en
ad
ap
ta
b
ilit
y
,
ac
h
iev
in
g
l
o
w
-
laten
cy
in
f
er
e
n
ce
with
s
tr
o
n
g
r
o
b
u
s
tn
ess
ac
r
o
s
s
m
o
to
r
ty
p
es.
T
h
is
h
ig
h
lig
h
ts
th
eir
s
u
itab
ilit
y
f
o
r
r
ea
l
-
tim
e
e
m
b
ed
d
ed
d
e
p
lo
y
m
en
t c
o
m
p
ar
ed
t
o
tr
ad
itio
n
al
m
eth
o
d
s
.
T
ab
le
4
.
Qu
alitativ
e
co
m
p
ar
is
o
n
o
f
ML
v
s
tr
ad
itio
n
al
c
o
n
tr
o
ller
s
M
e
t
h
o
d
A
d
a
p
t
a
b
i
l
i
t
y
t
o
n
o
n
l
i
n
e
a
r
i
t
i
es
R
e
a
l
-
t
i
me
f
e
a
s
i
b
i
l
i
t
y
(
l
a
t
e
n
c
y
)
D
a
t
a
r
e
q
u
i
r
e
me
n
t
R
o
b
u
st
n
e
ss
t
o
f
a
u
l
t
s/
d
i
st
u
r
b
a
n
c
e
s
Ea
se
o
f
i
mp
l
e
m
e
n
t
a
t
i
o
n
P
I
D
Li
mi
t
e
d
(
r
e
q
u
i
r
e
s
t
u
n
i
n
g
;
p
o
o
r
w
i
t
h
sa
t
u
r
a
t
i
o
n
&
r
i
p
p
l
e
)
H
i
g
h
(
µ
s
–
ms
r
a
n
g
e
)
N
o
n
e
(
m
o
d
e
l
-
b
a
s
e
d
)
M
o
d
e
r
a
t
e
(
n
e
e
d
s re
-
t
u
n
i
n
g
u
n
d
e
r
l
o
a
d
/
f
a
u
l
t
s)
V
e
r
y
s
i
mp
l
e
M
P
C
G
o
o
d
(
h
a
n
d
l
e
s
c
o
n
s
t
r
a
i
n
t
s,
o
p
t
i
m
i
z
a
t
i
o
n
-
b
a
se
d
)
M
o
d
e
r
a
t
e
(
ms
–
t
e
n
s
o
f
ms,
c
o
m
p
u
t
a
t
i
o
n
a
l
l
y
h
e
a
v
y
)
R
e
q
u
i
r
e
s s
y
s
t
e
m
mo
d
e
l
S
t
r
o
n
g
(
p
r
e
d
i
c
t
i
v
e
,
b
u
t
d
e
p
e
n
d
s
o
n
a
c
c
u
r
a
t
e
mo
d
e
l
)
C
o
m
p
l
e
x
I
n
v
e
r
se
D
y
n
a
mi
c
m
o
d
e
l
s
A
c
c
u
r
a
t
e
i
f
mo
d
e
l
i
s e
x
a
c
t
,
b
u
t
p
o
o
r
u
n
d
e
r
p
a
r
a
m
e
t
e
r
v
a
r
i
a
t
i
o
n
M
o
d
e
r
a
t
e
(
l
o
o
k
u
p
t
a
b
l
e
s
o
r
e
q
u
a
t
i
o
n
s)
H
i
g
h
(
r
e
q
u
i
r
e
s
mo
t
o
r
e
q
u
a
t
i
o
n
s
/
F
EA
)
W
e
a
k
(
se
n
si
t
i
v
e
t
o
u
n
c
e
r
t
a
i
n
t
i
e
s)
M
o
d
e
r
a
t
e
ANN
(
Th
i
s
w
o
r
k
)
S
t
r
o
n
g
(
l
e
a
r
n
s
n
o
n
l
i
n
e
a
r
d
y
n
a
mi
c
s)
H
i
g
h
(
l
a
t
e
n
c
y
~
0
.
0
1
2
s)
R
e
q
u
i
r
e
s
d
a
t
a
s
e
t
G
o
o
d
(
g
e
n
e
r
a
l
i
z
e
s
a
c
r
o
ss
v
a
r
y
i
n
g
l
o
a
d
s)
M
o
d
e
r
a
t
e
X
G
B
o
o
st
(
Th
i
s
w
o
r
k
)
S
t
r
o
n
g
(
c
a
p
t
u
r
e
s
n
o
n
l
i
n
e
a
r
i
t
i
e
s,
b
e
t
t
e
r
g
e
n
e
r
a
l
i
z
a
t
i
o
n
)
H
i
g
h
(
l
a
t
e
n
c
y
~
0
.
0
1
0
s)
R
e
q
u
i
r
e
s
d
a
t
a
s
e
t
S
t
r
o
n
g
(
st
a
b
l
e
r
e
s
i
d
u
a
l
s,
t
i
g
h
t
e
r
e
r
r
o
r
b
o
u
n
d
s)
M
o
d
e
r
a
t
e
5.
CO
NCLU
SI
O
N
T
h
is
s
tu
d
y
co
n
d
u
cted
a
r
ig
o
r
o
u
s
co
m
p
a
r
ativ
e
an
aly
s
is
o
f
ar
tific
ial
n
eu
r
al
n
etwo
r
k
s
(
ANN)
an
d
eXtr
em
e
g
r
ad
ie
n
t
b
o
o
s
tin
g
(
XGBo
o
s
t
)
f
o
r
in
v
er
s
e
m
o
d
elin
g
an
d
r
ea
l
-
tim
e
co
n
tr
o
l
o
f
s
witch
ed
r
elu
ctan
ce
m
o
to
r
s
(
SR
M)
an
d
br
u
s
h
less
DC
(
B
L
DC
)
m
o
to
r
s
.
B
o
th
m
o
d
els
s
u
cc
ess
f
u
lly
ca
p
tu
r
e
d
n
o
n
lin
ea
r
m
o
to
r
d
y
n
am
ics;
h
o
wev
er
,
XGBo
o
s
t
co
n
s
is
ten
tly
d
eliv
er
ed
s
u
p
er
io
r
p
er
f
o
r
m
an
ce
ac
r
o
s
s
all
ev
a
lu
ated
c
r
iter
ia.
Fo
r
SR
M,
it
ac
h
iev
ed
a
lo
wer
M
SE
(
0
.
0
0
2
8
v
s
.
0
.
0
0
3
5
)
,
h
ig
h
er
R
²
(
0
.
9
9
7
2
v
s
.
0
.
9
9
5
4
)
,
r
e
d
u
ce
d
tr
ain
in
g
tim
e
(
1
8
.
7
s
v
s
.
2
5
.
4
s
)
,
a
n
d
f
aster
in
f
er
en
ce
laten
cy
(
0
.
0
1
0
s
v
s
.
0
.
0
1
2
s
)
,
alo
n
g
with
im
p
r
o
v
ed
ef
f
icien
c
y
(
9
6
.
5
%
v
s
.
9
4
.
8
%).
C
o
m
p
ar
ab
le
g
ain
s
wer
e
o
b
s
er
v
ed
f
o
r
B
L
DC
,
co
n
f
ir
m
in
g
XGBo
o
s
t’
s
r
o
b
u
s
t
n
ess
ac
r
o
s
s
m
o
to
r
ty
p
es.
B
ey
o
n
d
r
aw
ac
c
u
r
ac
y
,
th
e
s
tu
d
y
d
em
o
n
s
tr
ated
th
at
XGBo
o
s
t
o
f
f
er
s
tig
h
ter
r
esid
u
al
d
is
tr
ib
u
tio
n
s
,
g
r
ea
ter
s
tab
ilit
y
ac
r
o
s
s
tr
ials
,
an
d
clea
r
f
ea
tu
r
e
r
ele
v
an
ce
p
atter
n
s
—
m
o
s
t
n
o
tab
ly
t
h
e
d
o
m
in
an
t
in
f
lu
en
ce
o
f
r
o
to
r
p
o
s
itio
n
an
d
d
esire
d
t
o
r
q
u
e
—
alig
n
in
g
with
estab
lis
h
ed
p
h
y
s
ical
p
r
i
n
cip
les.
T
h
ese
attr
ib
u
tes
m
ak
e
XGBo
o
s
t
h
ig
h
ly
s
u
itab
le
f
o
r
d
ep
lo
y
m
en
t
in
r
ea
l
-
tim
e
em
b
ed
d
ed
s
y
s
tem
s
,
wh
er
e
co
m
p
u
tati
o
n
al
ef
f
icien
cy
a
n
d
r
eliab
ilit
y
ar
e
cr
itica
l.
T
h
e
n
o
v
elty
o
f
th
is
wo
r
k
lies
in
u
n
if
y
in
g
SR
M
an
d
B
L
DC
b
en
ch
m
ar
k
i
n
g
u
n
d
e
r
id
en
tical
ex
p
e
r
im
en
tal
c
o
n
d
it
io
n
s
,
in
teg
r
atin
g
b
o
th
s
tatis
ti
ca
l
an
d
in
ter
p
r
etab
ilit
y
an
al
y
s
es,
an
d
ex
p
licitly
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Po
w
E
lec
&
Dr
i Sy
s
t
I
SS
N:
2088
-
8
6
9
4
S
u
p
ervis
ed
lea
r
n
in
g
fo
r
fa
s
t in
ve
r
s
e
mo
to
r
co
n
tr
o
l
ma
p
p
in
g
:
a
co
mp
a
r
a
tive
…
(
S
.
S
u
d
h
ee
r
K
u
ma
r
R
ed
d
y
)
2427
q
u
an
tify
in
g
r
ea
l
-
tim
e
f
ea
s
ib
i
lity
th
r
o
u
g
h
laten
cy
an
d
ef
f
icien
cy
m
etr
ics.
T
h
is
estab
lis
h
es
a
r
ep
licab
le
m
eth
o
d
o
l
o
g
y
f
o
r
f
u
t
u
r
e
ML
-
b
ased
m
o
to
r
co
n
tr
o
l
r
esear
c
h
.
Fu
tu
r
e
ex
ten
s
io
n
s
will
f
o
cu
s
o
n
em
b
ed
d
in
g
r
ein
f
o
r
ce
m
e
n
t
lear
n
in
g
f
o
r
a
d
ap
tiv
e
clo
s
ed
-
lo
o
p
co
n
tr
o
l,
v
alid
atin
g
p
er
f
o
r
m
a
n
ce
o
n
h
ar
d
war
e
-
in
-
t
h
e
-
lo
o
p
(
HI
L
)
test
b
ed
s
,
an
d
test
in
g
m
o
d
el
r
o
b
u
s
tn
ess
u
n
d
e
r
f
au
lt
-
p
r
o
n
e
o
p
e
r
atin
g
c
o
n
d
itio
n
s
u
s
in
g
f
au
lt
in
jectio
n
d
atasets
.
Ad
d
itio
n
ally
,
in
teg
r
atin
g
f
au
lt
-
to
le
r
an
t
lear
n
in
g
m
ec
h
an
is
m
s
will
f
u
r
th
er
en
h
an
ce
r
eliab
ilit
y
in
s
af
ety
-
cr
itical
m
o
to
r
d
r
i
v
e
ap
p
licatio
n
s
.
I
m
p
o
r
ta
n
tly
,
th
e
p
r
o
p
o
s
ed
f
r
am
ewo
r
k
ca
n
b
e
g
en
er
alize
d
to
o
th
e
r
m
o
to
r
ty
p
es
an
d
s
ea
m
less
ly
in
teg
r
ated
in
to
in
tellig
en
t
d
r
iv
e
s
y
s
tem
s
,
en
ab
lin
g
s
ca
lab
le,
r
eliab
le,
an
d
ad
a
p
tiv
e
m
o
to
r
co
n
tr
o
l so
lu
tio
n
s
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
T
h
e
au
th
o
r
s
d
ec
lar
e
th
at
n
o
f
u
n
d
s
,
g
r
an
ts
,
o
r
o
th
e
r
s
u
p
p
o
r
t
wer
e
r
ec
eiv
ed
d
u
r
in
g
th
e
p
r
e
p
ar
atio
n
o
f
th
is
m
an
u
s
cr
ip
t.
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
S
.
Su
d
h
ee
r
Ku
m
a
r
R
ed
d
y
✓
✓
✓
✓
✓
✓
✓
✓
✓
J
.
N
.
C
h
an
d
r
a
Sek
h
ar
✓
✓
✓
✓
✓
✓
✓
✓
✓
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
T
h
e
au
th
o
r
s
s
tate
n
o
co
n
f
lict o
f
in
ter
est.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
a
t
a
a
v
a
i
l
a
b
i
l
it
y
d
o
e
s
n
o
t
ap
p
l
y
t
o
t
h
i
s
p
a
p
e
r
as
n
o
n
e
w
d
at
a
w
e
r
e
c
r
e
at
e
d
o
r
a
n
a
l
y
z
e
d
i
n
th
i
s
s
t
u
d
y
.
RE
F
E
R
E
NC
E
S
[
1
]
J.
H
o
l
t
z
,
“
A
d
v
a
n
c
e
d
P
W
M
a
n
d
p
r
e
d
i
c
t
i
v
e
c
o
n
t
r
o
l
-
a
n
o
v
e
r
v
i
e
w
,
”
I
EEE
T
r
a
n
sa
c
t
i
o
n
s
o
n
I
n
d
u
s
t
ri
a
l
E
l
e
c
t
r
o
n
i
c
s
,
v
o
l
.
6
3
,
n
o
.
6
,
p
p
.
3
8
3
7
–
3
8
4
4
,
2
0
1
6
,
d
o
i
:
1
0
.
1
1
0
9
/
TI
E.
2
0
1
5
.
2
5
0
4
3
4
7
.
[
2
]
A
.
A
b
d
e
l
-
A
z
i
z
,
M
.
E
l
g
e
n
e
d
y
,
a
n
d
B
.
W
i
l
l
i
a
ms,
“
R
e
v
i
e
w
o
f
sw
i
t
c
h
e
d
r
e
l
u
c
t
a
n
c
e
m
o
t
o
r
c
o
n
v
e
r
t
e
r
s
a
n
d
t
o
r
q
u
e
r
i
p
p
l
e
mi
n
i
mi
sa
t
i
o
n
t
e
c
h
n
i
q
u
e
s f
o
r
e
l
e
c
t
r
i
c
v
e
h
i
c
l
e
a
p
p
l
i
c
a
t
i
o
n
s
,
”
En
e
rg
i
e
s
,
v
o
l
.
1
7
,
n
o
.
1
3
,
p
.
3
2
6
3
,
J
u
l
.
2
0
2
4
,
d
o
i
:
1
0
.
3
3
9
0
/
e
n
1
7
1
3
3
2
6
3
.
[
3
]
K
.
K
,
L
.
D
.
V
,
P
.
A
v
a
g
a
d
d
i
,
a
n
d
M
.
K
.
K
,
“
D
e
si
g
n
a
n
d
e
v
a
l
u
a
t
i
o
n
o
f
p
o
w
e
r
c
o
n
v
e
r
t
e
r
f
o
r
i
n
t
e
g
r
a
t
i
o
n
o
f
l
i
t
h
i
u
m
-
i
o
n
b
a
t
t
e
r
y
a
n
d
r
e
n
e
w
a
b
l
e
s
o
u
r
c
e
s
,
”
Re
s
u
l
t
s
i
n
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
2
5
,
p
.
1
0
4
4
0
9
,
M
a
r
.
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
4
4
0
9
.
[
4
]
K
.
K
r
i
s
h
n
a
m
u
r
t
h
y
,
S
.
P
a
d
m
a
n
a
b
a
n
,
F
.
B
l
a
a
b
j
e
r
g
,
R
.
B
.
N
e
e
l
a
k
a
n
d
a
n
,
a
n
d
K
.
R
.
P
r
a
b
h
u
,
“
P
o
w
e
r
e
l
e
c
t
r
o
n
i
c
c
o
n
v
e
r
t
e
r
c
o
n
f
i
g
u
r
a
t
i
o
n
s
i
n
t
e
g
r
a
t
i
o
n
w
i
t
h
h
y
b
r
i
d
e
n
e
r
g
y
s
o
u
r
c
e
s
–
a
c
o
mp
r
e
h
e
n
s
i
v
e
r
e
v
i
e
w
f
o
r
st
a
t
e
-
o
f
t
h
e
-
a
r
t
i
n
r
e
s
e
a
r
c
h
,
”
El
e
c
t
ri
c
P
o
w
e
r
C
o
m
p
o
n
e
n
t
s
a
n
d
S
y
s
t
e
m
s
,
v
o
l
.
4
7
,
n
o
.
1
8
,
p
p
.
1
6
2
3
–
1
6
5
0
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
8
0
/
1
5
3
2
5
0
0
8
.
2
0
1
9
.
1
6
8
9
4
5
7
.
[
5
]
M
.
M
o
r
a
r
i
,
C
.
E.
G
a
r
c
i
a
,
a
n
d
D
.
M
.
P
r
e
t
t
,
“
M
o
d
e
l
p
r
e
d
i
c
t
i
v
e
c
o
n
t
r
o
l
:
Th
e
o
r
y
a
n
d
p
r
a
c
t
i
c
e
,
”
I
FA
C
Pr
o
c
e
e
d
i
n
g
s
Vo
l
u
m
e
s
,
v
o
l
.
2
1
,
n
o
.
4
,
p
p
.
1
–
1
2
,
1
9
8
8
,
d
o
i
:
1
0
.
1
0
1
6
/
b
9
7
8
-
0
-
08
-
0
3
5
7
3
5
-
5
.
5
0
0
0
6
-
1.
[
6
]
Y
.
H
a
o
e
t
a
l
.
,
“
T
o
r
q
u
e
a
n
a
l
y
t
i
c
a
l
m
o
d
e
l
o
f
sw
i
t
c
h
e
d
r
e
l
u
c
t
a
n
c
e
m
o
t
o
r
c
o
n
s
i
d
e
r
i
n
g
m
a
g
n
e
t
i
c
sa
t
u
r
a
t
i
o
n
,
”
I
ET
E
l
e
c
t
ri
c
Po
w
e
r
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
4
,
n
o
.
7
,
p
p
.
1
1
4
8
–
1
1
5
3
,
J
u
l
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
4
9
/
i
e
t
-
e
p
a
.
2
0
1
9
.
0
9
8
7
.
[
7
]
D
.
N
i
k
h
i
t
h
a
a
n
d
J.
N
.
C
.
S
e
k
h
a
r
,
“
M
o
d
e
l
i
n
g
a
n
d
si
m
u
l
a
t
i
o
n
o
f
I
M
d
r
i
v
e
p
e
r
f
o
r
ma
n
c
e
u
s
i
n
g
P
I
,
A
N
N
a
n
d
F
LC
,
”
i
n
2
0
1
3
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
I
T
C
o
n
v
e
r
g
e
n
c
e
a
n
d
S
e
c
u
ri
t
y
(
I
C
I
T
C
S
)
,
I
EEE,
D
e
c
.
2
0
1
3
,
p
p
.
1
–
4
.
d
o
i
:
1
0
.
1
1
0
9
/
I
C
I
TC
S
.
2
0
1
3
.
6
7
1
7
8
5
8
.
[
8
]
K
.
K
a
m
b
a
l
a
,
“
M
o
d
e
l
i
n
g
a
n
d
p
e
r
f
o
r
man
c
e
a
n
a
l
y
s
i
s
o
f
B
LD
C
mo
t
o
r
u
n
d
e
r
d
i
f
f
e
r
e
n
t
o
p
e
r
a
t
i
n
g
s
p
e
e
d
c
o
n
d
i
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
En
g
i
n
e
e
ri
n
g
an
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
6
,
n
o
.
4
,
p
p
.
2
1
4
6
8
–
2
1
4
7
5
,
J
u
n
.
2
0
1
7
,
d
o
i
:
1
0
.
1
8
5
3
5
/
i
j
e
c
s
/
v
6
i
5
.
4
6
.
[
9
]
M
.
V
e
d
a
d
i
,
“
O
p
t
i
mi
z
e
d
c
a
s
c
a
d
e
d
p
o
s
i
t
i
o
n
c
o
n
t
r
o
l
o
f
B
LD
C
m
o
t
o
r
s
c
o
n
si
d
e
r
i
n
g
t
o
r
q
u
e
r
i
p
p
l
e
,
”
2
n
d
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
Em
e
rg
i
n
g
T
e
c
h
n
o
l
o
g
i
e
s
i
n
El
e
c
t
r
o
n
i
c
s,
C
o
m
p
u
t
i
n
g
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
,
I
C
ETEC
C
2
0
2
5
,
2
0
2
5
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
ETEC
C
6
5
3
6
5
.
2
0
2
5
.
1
1
0
7
1
1
3
7
.
[
1
0
]
D
.
M
o
h
a
n
r
a
j
e
t
a
l
.
,
“
A
re
v
i
e
w
o
f
B
L
D
C
mo
t
o
r
:
st
a
t
e
o
f
a
r
t
,
a
d
v
a
n
c
e
d
c
o
n
t
r
o
l
t
e
c
h
n
i
q
u
e
s,
a
n
d
a
p
p
l
i
c
a
t
i
o
n
s
,
”
I
EE
E
Ac
c
e
ss
, v
o
l
.
1
0
,
p
p
.
5
4
8
3
3
–
5
4
8
6
9
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
2
.
3
1
7
5
0
1
1
.
[
1
1
]
G
.
Y
a
o
,
J.
F
e
n
g
,
G
.
W
a
n
g
,
a
n
d
S
.
H
a
n
,
“
B
LD
C
mo
t
o
r
s
se
n
s
o
r
l
e
ss c
o
n
t
r
o
l
b
a
se
d
o
n
M
LP t
o
p
o
l
o
g
y
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
E
n
e
r
g
i
e
s
,
v
o
l
.
1
6
,
n
o
.
1
0
,
p
.
4
0
2
7
,
M
a
y
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
e
n
1
6
1
0
4
0
2
7
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
6
9
4
I
n
t J Po
w
E
lec
&
Dr
i Sy
s
t
,
Vo
l.
16
,
No
.
4
,
Dec
em
b
er
20
25
:
2419
-
2
4
2
8
2428
[
1
2
]
K
.
K
u
mar,
V
.
L
.
D
e
v
i
,
A
.
P
r
a
s
a
d
,
H
.
R
e
d
d
y
G
a
l
i
,
a
n
d
R
.
Ti
w
a
r
i
,
“
A
n
a
l
y
s
i
s
o
f
a
f
u
e
l
c
e
l
l
-
f
e
d
B
LD
C
mo
t
o
r
d
r
i
v
e
w
i
t
h
a
d
o
u
b
l
e
b
o
o
s
t
c
o
n
v
e
r
t
e
r
f
o
r
e
l
e
c
t
r
i
c
v
e
h
i
c
l
e
a
p
p
l
i
c
a
t
i
o
n
,
”
S
m
a
rt
G
r
i
d
s
f
o
r
R
e
n
e
w
a
b
l
e
E
n
e
r
g
y
S
y
st
e
m
s
,
E
l
e
c
t
ri
c
V
e
h
i
c
l
e
s
a
n
d
E
n
e
r
g
y
S
t
o
r
a
g
e
S
y
s
t
e
m
s
,
p
p
.
5
9
–
7
5
,
2
0
2
2
,
d
o
i
:
1
0
.
1
2
0
1
/
9
7
8
1
0
0
3
3
1
1
1
9
5
-
4.
[
1
3
]
K
.
K
r
i
sh
n
a
mu
r
t
h
y
a
n
d
V
.
L.
D
e
v
i
,
“
F
u
e
l
c
e
l
l
f
e
d
e
l
e
c
t
r
i
c
a
l
v
e
h
i
c
l
e
p
e
r
f
o
r
man
c
e
a
n
a
l
y
s
i
s
w
i
t
h
e
n
r
i
c
h
e
d
sw
i
t
c
h
e
d
p
a
r
a
me
t
e
r
c
u
k
c
o
n
v
e
r
t
e
r
,
”
R
e
c
e
n
t
A
d
v
a
n
c
e
s
i
n
El
e
c
t
ri
c
a
l
&
E
l
e
c
t
r
o
n
i
c
En
g
i
n
e
e
r
i
n
g
(
Fo
rm
e
r
l
y
Re
c
e
n
t
P
a
t
e
n
t
s
o
n
El
e
c
t
r
i
c
a
l
&
E
l
e
c
t
r
o
n
i
c
En
g
i
n
e
e
ri
n
g
)
,
v
o
l
.
1
7
,
n
o
.
1
0
,
p
p
.
9
5
4
–
9
6
5
,
2
0
2
3
,
d
o
i
:
1
0
.
2
1
7
4
/
2
3
5
2
0
9
6
5
1
6
6
6
6
2
3
0
6
0
7
1
2
5
1
3
7
.
[
1
4
]
Y
.
G
u
o
,
Z
.
H
o
u
,
S
.
L
i
u
,
a
n
d
S
.
Ji
n
,
“
D
a
t
a
-
d
r
i
v
e
n
m
o
d
e
l
-
f
r
e
e
a
d
a
p
t
i
v
e
p
r
e
d
i
c
t
i
v
e
c
o
n
t
r
o
l
f
o
r
a
c
l
a
ss
o
f
M
I
M
O
n
o
n
l
i
n
e
a
r
d
i
s
c
r
e
t
e
-
t
i
m
e
s
y
st
e
ms w
i
t
h
st
a
b
i
l
i
t
y
a
n
a
l
y
si
s,”
I
EEE
A
c
c
e
ss
,
v
o
l
.
7
,
p
p
.
1
0
2
8
5
2
–
1
0
2
8
6
6
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
1
9
.
2
9
3
1
1
9
8
.
[
1
5
]
Y
.
Le
C
u
n
,
Y
.
B
e
n
g
i
o
,
a
n
d
G
.
H
i
n
t
o
n
,
“
D
e
e
p
l
e
a
r
n
i
n
g
,
”
N
a
t
u
re
,
v
o
l
.
5
2
1
,
n
o
.
7
5
5
3
,
p
p
.
4
3
6
–
4
4
4
,
M
a
y
2
0
1
5
,
d
o
i
:
1
0
.
1
0
3
8
/
n
a
t
u
r
e
1
4
5
3
9
.
[1
6
]
J.
N
.
C
h
a
n
d
r
a
S
e
k
h
a
r
a
n
d
G
.
V
.
M
a
r
u
t
h
e
sw
a
r
,
“
D
i
r
e
c
t
t
o
r
q
u
e
c
o
n
t
r
o
l
o
f
i
n
d
u
c
t
i
o
n
mo
t
o
r
u
s
i
n
g
e
n
h
a
n
c
e
d
f
i
r
e
f
l
y
a
l
g
o
r
i
t
h
m
—
A
N
F
I
S
,
”
J
o
u
r
n
a
l
o
f
C
i
rc
u
i
t
s,
S
y
st
e
m
s
a
n
d
C
o
m
p
u
t
e
rs
,
v
o
l
.
2
6
,
n
o
.
0
6
,
p
.
1
7
5
0
0
9
2
,
J
u
n
.
2
0
1
7
,
d
o
i
:
1
0
.
1
1
4
2
/
S
0
2
1
8
1
2
6
6
1
7
5
0
0
9
2
X
.
[
1
7
]
T.
C
h
e
n
a
n
d
C
.
G
u
e
s
t
r
i
n
,
“
X
G
B
o
o
s
t
:
A
sc
a
l
a
b
l
e
t
r
e
e
b
o
o
s
t
i
n
g
s
y
st
e
m,”
i
n
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
2
2
n
d
A
C
M
S
I
G
K
D
D
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
K
n
o
w
l
e
d
g
e
D
i
s
c
o
v
e
r
y
a
n
d
D
a
t
a
Mi
n
i
n
g
,
A
u
g
.
2
0
1
6
,
p
p
.
7
8
5
–
7
9
4
.
d
o
i
:
1
0
.
1
1
4
5
/
2
9
3
9
6
7
2
.
2
9
3
9
7
8
5
.
[
1
8
]
Y
.
Y
a
n
g
,
M
.
M
.
M
.
H
a
q
u
e
,
D
.
B
a
i
,
a
n
d
W
.
T
a
n
g
,
“
F
a
u
l
t
d
i
a
g
n
o
si
s
o
f
e
l
e
c
t
r
i
c
mo
t
o
r
s
u
si
n
g
d
e
e
p
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms
a
n
d
i
t
s
a
p
p
l
i
c
a
t
i
o
n
:
a
r
e
v
i
e
w
,
”
E
n
e
r
g
i
e
s
,
v
o
l
.
1
4
,
n
o
.
2
1
,
p
.
7
0
1
7
,
O
c
t
.
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
e
n
1
4
2
1
7
0
1
7
.
[
1
9
]
B
.
J
i
n
g
,
G
.
Li
a
n
g
,
X
.
D
a
n
g
,
a
n
d
Y
.
Ji
a
n
g
,
“
R
e
d
u
c
i
n
g
t
o
r
q
u
e
r
i
p
p
l
e
f
o
r
s
w
i
t
c
h
e
d
r
e
l
u
c
t
a
n
c
e
m
o
t
o
r
s
b
y
c
u
r
r
e
n
t
r
e
sh
a
p
i
n
g
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
S
c
i
e
n
t
i
f
i
c
R
e
p
o
rt
s
,
v
o
l
.
1
5
,
n
o
.
1
,
p
.
1
7
5
3
0
,
M
a
y
2
0
2
5
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
5
9
8
-
0
2
5
-
0
2
2
2
8
-
z
.
[
2
0
]
V
.
L
a
k
s
h
m
i
D
e
v
i
,
K
.
K
u
mar,
S
.
R
.
K
i
r
a
n
,
a
n
d
N
.
M
.
G
i
r
i
s
h
K
u
m
a
r
,
“
A
n
a
l
y
s
i
s
o
f
e
n
e
r
g
y
m
a
n
a
g
e
me
n
t
s
y
s
t
e
m
i
n
mi
c
r
o
g
r
i
d
o
p
e
r
a
t
i
o
n
s
,
l
o
a
d
s
u
p
p
o
r
t
,
a
n
d
c
o
n
t
r
o
l
h
i
e
r
a
r
c
h
y
,
”
2
0
2
3
2
n
d
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
T
r
e
n
d
s
i
n
El
e
c
t
r
i
c
a
l
,
El
e
c
t
r
o
n
i
c
s
a
n
d
C
o
m
p
u
t
e
r
E
n
g
i
n
e
e
r
i
n
g
,
T
EE
C
C
O
N
2
0
2
3
,
p
p
.
1
3
–
1
6
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
T
EEC
C
O
N
5
9
2
3
4
.
2
0
2
3
.
1
0
3
3
5
8
5
9
.
[
2
1
]
S
.
K
r
i
s
h
n
a
m
o
o
r
t
h
y
a
n
d
P
.
P
.
K
.
P
a
n
i
k
k
a
r
,
“
M
o
d
i
f
i
e
d
sw
i
t
c
h
i
n
g
c
o
n
t
r
o
l
o
f
S
R
M
d
r
i
v
e
s fo
r
e
l
e
c
t
r
i
c
v
e
h
i
c
l
e
s
a
p
p
l
i
c
a
t
i
o
n
w
i
t
h
t
o
r
q
u
e
r
i
p
p
l
e
r
e
d
u
c
t
i
o
n
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
Po
w
e
r
El
e
c
t
ro
n
i
c
s
a
n
d
D
r
i
v
e
S
y
s
t
e
m
s
,
v
o
l
.
1
5
,
n
o
.
1
,
p
p
.
1
4
7
–
1
5
9
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
p
e
d
s
.
v
1
5
.
i
1
.
p
p
1
4
7
-
1
5
9
.
[
2
2
]
K
.
K
u
mar
,
N
.
R
.
B
a
b
u
,
a
n
d
K
.
R
.
P
r
a
b
h
u
,
“
A
n
a
l
y
si
s
o
f
i
n
t
e
g
r
a
t
e
d
B
o
o
st
-
C
u
k
h
i
g
h
v
o
l
t
a
g
e
g
a
i
n
D
C
-
D
C
c
o
n
v
e
r
t
e
r
w
i
t
h
R
B
F
N
M
P
P
T
f
o
r
so
l
a
r
P
V
a
p
p
l
i
c
a
t
i
o
n
,
”
i
n
2
0
1
7
I
n
n
o
v
a
t
i
o
n
s
i
n
P
o
w
e
r
a
n
d
Ad
v
a
n
c
e
d
C
o
m
p
u
t
i
n
g
T
e
c
h
n
o
l
o
g
i
e
s
(
i
-
P
AC
T
)
,
I
EEE,
A
p
r
.
2
0
1
7
,
p
p
.
1
–
6
.
d
o
i
:
1
0
.
1
1
0
9
/
I
P
A
C
T.
2
0
1
7
.
8
2
4
5
0
7
2
.
[
2
3
]
J.
L
.
B
a
a
n
d
D
.
P
.
K
i
n
g
ma
,
“
A
d
a
m:
A
me
t
h
o
d
f
o
r
s
t
o
c
h
a
s
t
i
c
o
p
t
i
m
i
z
a
t
i
o
n
,
”
3
r
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
L
e
a
r
n
i
n
g
Re
p
r
e
se
n
t
a
t
i
o
n
s
,
I
C
L
R
2
0
1
5
-
C
o
n
f
e
r
e
n
c
e
T
r
a
c
k
Pr
o
c
e
e
d
i
n
g
s
,
p
p
.
1
–
1
5
,
2
0
1
5
.
[
2
4
]
S
.
H
a
n
,
H
.
M
a
o
,
a
n
d
W
.
J.
D
a
l
l
y
,
“
D
e
e
p
c
o
m
p
r
e
ss
i
o
n
:
C
o
mp
r
e
ssi
n
g
d
e
e
p
n
e
u
r
a
l
n
e
t
w
o
r
k
s
w
i
t
h
p
r
u
n
i
n
g
,
t
r
a
i
n
e
d
q
u
a
n
t
i
z
a
t
i
o
n
a
n
d
H
u
f
f
man
c
o
d
i
n
g
,
”
4
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
L
e
a
r
n
i
n
g
R
e
p
r
e
se
n
t
a
t
i
o
n
s,
I
C
L
R
2
0
1
6
-
C
o
n
f
e
r
e
n
c
e
T
r
a
c
k
Pr
o
c
e
e
d
i
n
g
s
,
2
0
1
6
.
[
2
5
]
Z.
H
o
u
a
n
d
S
h
a
n
g
t
a
i
Ji
n
,
“
D
a
t
a
-
d
r
i
v
e
n
m
o
d
e
l
-
f
r
e
e
a
d
a
p
t
i
v
e
c
o
n
t
r
o
l
f
o
r
a
c
l
a
ss
o
f
M
I
M
O
n
o
n
l
i
n
e
a
r
d
i
s
c
r
e
t
e
-
t
i
m
e
sy
s
t
e
ms
,
”
I
E
EE
T
ra
n
s
a
c
t
i
o
n
s
o
n
N
e
u
r
a
l
N
e
t
w
o
rks
,
v
o
l
.
2
2
,
n
o
.
1
2
,
p
p
.
2
1
7
3
–
2
1
8
8
,
D
e
c
.
2
0
1
1
,
d
o
i
:
1
0
.
1
1
0
9
/
TN
N
.
2
0
1
1
.
2
1
7
6
1
4
1
.
[
2
6
]
M
.
B
e
n
o
s
ma
n
,
“
M
o
d
e
l
‐
b
a
s
e
d
v
s
d
a
t
a
‐
d
r
i
v
e
n
a
d
a
p
t
i
v
e
c
o
n
t
r
o
l
:
A
n
o
v
e
r
v
i
e
w
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
A
d
a
p
t
i
v
e
C
o
n
t
ro
l
a
n
d
S
i
g
n
a
l
Pr
o
c
e
ssi
n
g
,
v
o
l
.
3
2
,
n
o
.
5
,
p
p
.
7
5
3
–
7
7
6
,
M
a
y
2
0
1
8
,
d
o
i
:
1
0
.
1
0
0
2
/
a
c
s
.
2
8
6
2
.
[
2
7
]
H
.
S
a
r
ma
a
n
d
A
.
B
a
r
d
a
l
a
i
,
“
A
n
i
n
t
e
l
l
i
g
e
n
t
P
I
D
c
o
n
t
r
o
l
l
e
r
t
u
n
i
n
g
f
o
r
sp
e
e
d
c
o
n
t
r
o
l
o
f
B
LD
C
mo
t
o
r
u
si
n
g
d
r
i
v
i
n
g
t
r
a
i
n
i
n
g
-
b
a
s
e
d
o
p
t
i
m
i
z
a
t
i
o
n
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
P
o
w
e
r
E
l
e
c
t
r
o
n
i
c
s
a
n
d
D
r
i
v
e
S
y
s
t
e
m
s
,
v
o
l
.
1
4
,
n
o
.
4
,
p
p
.
2
4
7
4
–
2
4
8
6
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
p
e
d
s
.
v
1
4
.
i
4
.
p
p
2
4
7
4
-
2
4
8
6
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
S
.
S
u
d
h
e
e
r
K
u
m
a
r
Re
d
d
y
is
a
d
e
d
ica
ted
re
se
a
rc
h
sc
h
o
lar
c
u
rr
e
n
tl
y
p
u
rs
u
in
g
h
is
P
h
.
D.
a
t
S
ri
Ve
n
k
a
tes
h
wa
ra
Un
iv
e
rsity
C
o
ll
e
g
e
o
f
E
n
g
i
n
e
e
rin
g
,
Ti
r
u
p
a
ti
.
His
a
c
a
d
e
m
ic
fo
u
n
d
a
ti
o
n
in
c
l
u
d
e
s
a
n
M
.
Tec
h
.
d
e
g
re
e
fro
m
JN
TU
A
n
a
n
tap
u
r
a
n
d
a
B.
Tec
h
.
fr
o
m
RG
M
En
g
i
n
e
e
rin
g
Co
l
leg
e
,
Na
n
d
y
a
l.
Wi
th
a
ro
b
u
st
tea
c
h
in
g
c
a
re
e
r
sp
a
n
n
in
g
fr
o
m
2
0
1
3
t
o
t
h
e
p
re
se
n
t,
h
e
h
a
s
c
o
n
tri
b
u
ted
sig
n
ifi
c
a
n
tl
y
a
s
a
n
e
d
u
c
a
to
r
in
g
o
v
e
rn
m
e
n
t
p
o
l
y
tec
h
n
ics
.
F
u
rth
e
rm
o
re
,
h
e
h
a
s
p
lay
e
d
a
n
in
stru
m
e
n
tal
ro
le
in
h
is
i
n
stit
u
ti
o
n
,
se
rv
in
g
a
s
a
m
e
m
b
e
r
o
f
v
a
rio
u
s
c
o
m
m
it
tee
s
a
n
d
a
c
ti
v
e
l
y
p
a
rti
c
ip
a
ti
n
g
i
n
th
e
su
c
c
e
ss
fu
l
a
tt
a
in
m
e
n
t
o
f
NBA
a
c
c
re
d
it
a
ti
o
n
.
He
c
a
n
b
e
c
o
n
tac
te
d
a
t
e
m
a
il
:
su
d
h
e
e
rso
m
u
@g
m
a
il
.
c
o
m
.
Dr
.
J
.
N.
Cha
n
d
r
a
S
e
k
h
a
r
is
a
n
a
ss
o
c
iate
p
r
o
fe
ss
o
r
i
n
th
e
De
p
a
rtme
n
t
o
f
El
e
c
tri
c
a
l
a
n
d
E
lec
tro
n
ics
En
g
in
e
e
rin
g
,
S
ri
Ve
n
k
a
tes
wa
ra
Un
iv
e
rsity
Co
l
leg
e
o
f
En
g
i
n
e
e
rin
g
,
Ti
r
u
p
a
ti
,
I
n
d
ia.
He
re
c
e
iv
e
d
h
is
P
h
.
D.
in
P
o
we
r
El
e
c
tro
n
ics
a
n
d
Driv
e
s
fro
m
S
ri
Ve
n
k
a
tes
wa
ra
Un
iv
e
rsity
i
n
2
0
1
9
a
n
d
M
.
E.
i
n
P
o
we
r
E
lec
tro
n
i
c
s
a
n
d
I
n
d
u
strial
Driv
e
s
fro
m
S
a
th
y
a
b
a
m
a
In
stit
u
te
o
f
S
c
ien
c
e
a
n
d
Tec
h
n
o
l
o
g
y
,
C
h
e
n
n
a
i,
in
2
0
0
6
.
His
re
se
a
rc
h
in
tere
sts
in
c
l
u
d
e
p
o
we
r
e
lec
tro
n
ics
,
e
lec
tri
c
d
ri
v
e
s,
re
n
e
wa
b
le
e
n
e
rg
y
sy
ste
m
s,
e
lec
tri
c
v
e
h
icle
s,
a
n
d
i
n
telli
g
e
n
t
c
o
n
tr
o
l
tec
h
n
i
q
u
e
s.
He
h
a
s
p
u
b
l
ish
e
d
m
o
re
th
a
n
3
0
p
a
p
e
rs
in
re
p
u
ted
S
CI/
S
c
o
p
u
s
-
in
d
e
x
e
d
j
o
u
rn
a
ls
a
n
d
c
o
n
fe
re
n
c
e
s,
a
u
th
o
r
e
d
b
o
o
k
c
h
a
p
ters
,
a
n
d
c
o
n
tri
b
u
ted
t
o
i
n
tern
a
ti
o
n
a
l
p
u
b
li
c
a
ti
o
n
s.
He
a
lso
se
rv
e
s
a
s
a
n
Ac
a
d
e
m
ic
Ed
it
o
r
a
n
d
re
v
iew
e
r
fo
r
se
v
e
ra
l
lea
d
in
g
j
o
u
r
n
a
ls
a
n
d
is
a
m
e
m
b
e
r
o
f
IE
EE
,
A
CM
,
a
n
d
IEI
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
c
h
a
n
d
u
.
ji
n
k
a
@g
m
a
il
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.