I
AE
S In
t
er
na
t
io
na
l J
o
urna
l o
f
Art
if
icia
l In
t
ellig
ence
(
I
J
-
AI
)
Vo
l.
1
5
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
6
,
p
p
.
154
~
163
I
SS
N:
2
2
5
2
-
8
9
3
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijai.v
15
.i
1
.
p
p
1
5
4
-
1
6
3
154
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
i
.
ia
esco
r
e.
co
m
An AI
-
driv
en
framewo
rk f
o
r
ef
f
ici
ent
a
nd acc
ura
te
ca
libra
tion
o
f
elect
ricity m
ete
rs using
e
x
trem
e
g
ra
dient
bo
o
sting
Ro
s
a
lin
a
1
,
Nuni
k
Af
rilia
na
2
1
I
n
f
o
r
mat
i
c
s S
t
u
d
y
P
r
o
g
r
a
m
,
F
a
c
u
l
t
y
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
P
r
e
si
d
e
n
t
U
n
i
v
e
r
si
t
y
,
B
e
k
a
si
,
I
n
d
o
n
e
si
a
2
I
n
f
o
r
mat
i
c
s S
t
u
d
y
P
r
o
g
r
a
m
,
F
a
c
u
l
t
y
o
f
E
n
g
i
n
e
e
r
i
n
g
a
n
d
I
n
f
o
r
m
a
t
i
c
s,
U
n
i
v
e
r
si
t
a
s
M
u
l
t
i
me
d
i
a
N
u
sa
n
t
a
r
a
,
Ta
n
g
e
r
a
n
g
,
I
n
d
o
n
e
s
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Dec
1
0
,
2
0
2
5
R
ev
is
ed
Dec
1
9
,
2
0
2
5
Acc
ep
ted
J
an
1
0
,
2
0
2
6
Ca
li
b
ra
ti
o
n
tes
ti
n
g
p
lay
s
a
v
it
a
l
ro
le
i
n
e
lec
tri
c
it
y
m
e
ter
m
a
n
u
fa
c
tu
rin
g
t
o
g
u
a
ra
n
tee
m
e
a
su
re
m
e
n
t
a
c
c
u
ra
c
y
a
n
d
c
o
m
p
li
a
n
c
e
with
i
n
d
u
stry
sta
n
d
a
rd
s.
I
n
p
ra
c
ti
c
e
,
h
o
we
v
e
r,
c
o
n
v
e
n
ti
o
n
a
l
c
a
li
b
ra
ti
o
n
m
e
t
h
o
d
s
a
re
o
ften
h
i
n
d
e
re
d
b
y
len
g
t
h
y
tes
t
c
y
c
les
a
n
d
th
e
h
ig
h
c
o
st
o
f
e
x
p
a
n
d
in
g
tes
t
b
e
n
c
h
c
a
p
a
c
it
y
.
Th
is
stu
d
y
p
r
o
p
o
se
s
a
d
a
ta
-
d
riv
e
n
a
p
p
r
o
a
c
h
to
a
d
d
re
ss
th
e
se
li
m
it
a
ti
o
n
s
b
y
a
p
p
ly
in
g
m
a
c
h
in
e
lea
rn
in
g
tec
h
n
iq
u
e
s
to
o
p
ti
m
ize
c
a
li
b
ra
ti
o
n
t
e
stin
g
.
An
e
x
trem
e
g
ra
d
ien
t
b
o
o
sti
n
g
(
XG
B
o
o
st
)
re
g
re
ss
io
n
m
o
d
e
l,
e
n
h
a
n
c
e
d
t
h
ro
u
g
h
sy
ste
m
a
ti
c
h
y
p
e
rp
a
ra
m
e
ter
tu
n
in
g
a
n
d
fe
a
tu
re
e
n
g
i
n
e
e
rin
g
,
wa
s
d
e
v
e
lo
p
e
d
to
p
re
d
ict
c
a
li
b
ra
ti
o
n
o
u
tco
m
e
s
u
si
n
g
d
a
ta
o
b
tain
e
d
fr
o
m
e
x
isti
n
g
p
ro
d
u
c
ti
o
n
tes
t
b
e
n
c
h
e
s.
Wh
e
n
e
v
a
lu
a
ted
u
n
d
e
r
re
a
l
m
a
n
u
fa
c
tu
ri
n
g
li
n
e
c
o
n
d
it
io
n
s
,
t
h
e
p
ro
p
o
se
d
m
e
th
o
d
sh
o
rten
e
d
c
a
li
b
ra
ti
o
n
ru
n
ti
m
e
b
y
a
b
o
u
t
5
5
%
c
o
m
p
a
re
d
with
m
a
n
u
a
l
p
ro
c
e
d
u
re
s
re
ly
in
g
o
n
p
o
we
r
su
p
p
l
y
u
n
it
s
(
PSU
)
a
n
d
sta
n
d
a
rd
m
e
ter
c
a
l
c
u
latio
n
s,
wh
il
e
m
a
in
tain
in
g
re
li
a
b
le
m
e
a
su
re
m
e
n
t
a
c
c
u
ra
c
y
.
Th
e
fra
m
e
wo
rk
a
lso
a
c
h
iev
e
d
l
o
we
r
ro
o
t
m
e
a
n
sq
u
a
re
e
rro
r
(RM
S
E)
,
d
e
m
o
n
stra
t
in
g
imp
ro
v
e
d
p
re
d
icti
v
e
p
e
rf
o
rm
a
n
c
e
.
In
a
d
d
it
i
o
n
t
o
re
p
o
rti
n
g
th
e
se
re
su
lt
s,
th
e
stu
d
y
d
e
sc
rib
e
s
th
e
p
re
p
ro
c
e
ss
in
g
p
ip
e
li
n
e
,
m
o
d
e
l
se
lec
ti
o
n
p
ro
c
e
ss
,
a
n
d
o
p
ti
m
iza
ti
o
n
stra
te
g
y
,
p
ro
v
i
d
in
g
a
p
ra
c
ti
c
a
l
a
n
d
re
p
li
c
a
b
le
fra
m
e
wo
rk
fo
r
in
teg
ra
ti
n
g
a
rt
ifi
c
ial
in
telli
g
e
n
c
e
(AI)
in
to
in
d
u
strial
c
a
li
b
ra
ti
o
n
p
r
o
c
e
ss
e
s
.
K
ey
w
o
r
d
s
:
Ar
tific
ial
in
tellig
en
ce
C
alib
r
atio
n
test
in
g
E
lectr
icity
m
eter
Sm
ar
t f
ac
to
r
y
XGBo
o
s
t r
eg
r
ess
io
n
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
:
R
o
s
alin
a
I
n
f
o
r
m
atics Stu
d
y
Pro
g
r
a
m
,
F
ac
u
lty
o
f
C
o
m
p
u
ter
Scien
ce
,
P
r
esid
en
t U
n
iv
er
s
ity
B
ek
asi,
I
n
d
o
n
esia
E
m
ail: r
o
s
alin
a@
p
r
esid
en
t.a
c.
id
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
m
an
u
f
ac
t
u
r
in
g
o
f
elec
tr
icity
m
eter
s
is
a
v
ital
in
d
u
s
tr
y
,
wh
er
e
ac
cu
r
ac
y
a
n
d
r
eliab
ilit
y
a
r
e
cr
itical
to
en
s
u
r
e
f
air
an
d
p
r
ec
is
e
b
il
lin
g
f
o
r
co
n
s
u
m
e
r
s
[
1
]
.
At
t
h
e
ce
n
ter
o
f
th
is
p
r
o
ce
s
s
lies
ca
lib
r
atio
n
test
in
g
,
wh
ich
v
er
if
ies
th
e
ac
cu
r
ac
y
o
f
m
eter
r
ea
d
in
g
s
ag
ain
s
t
a
s
tan
d
ar
d
r
ef
er
e
n
ce
b
e
n
ch
.
T
h
i
s
s
tep
is
n
o
t
o
n
l
y
a
tech
n
ical
n
ec
ess
ity
b
u
t
also
a
r
eg
u
lato
r
y
r
eq
u
i
r
em
en
t,
as
it
e
n
s
u
r
es
co
m
p
lian
ce
with
n
atio
n
a
l
an
d
in
ter
n
atio
n
al
s
tan
d
ar
d
s
.
Desp
ite
its
im
p
o
r
tan
ce
,
ca
lib
r
atio
n
i
n
its
tr
ad
itio
n
al
f
o
r
m
r
em
ain
s
h
i
g
h
ly
ti
m
e
-
co
n
s
u
m
in
g
an
d
lab
o
r
-
in
ten
s
iv
e,
cr
ea
tin
g
s
ig
n
if
ican
t
ch
allen
g
es
f
o
r
m
a
n
u
f
ac
tu
r
e
r
s
th
at
m
u
s
t
b
alan
ce
s
tr
ict
ac
cu
r
ac
y
r
eq
u
ir
em
e
n
ts
with
th
e
n
ee
d
f
o
r
ef
f
icien
t,
lar
g
e
-
s
ca
le
p
r
o
d
u
ctio
n
.
T
r
ad
itio
n
al
ca
lib
r
atio
n
m
eth
o
d
s
r
eq
u
ir
e
ea
ch
m
eter
to
b
e
t
ested
in
d
iv
id
u
ally
,
o
f
te
n
u
n
d
e
r
m
u
ltip
le
lo
ad
co
n
d
itio
n
s
,
an
d
c
o
m
p
ar
ed
ag
ain
s
t
a
s
tan
d
ar
d
r
e
f
er
e
n
ce
b
en
ch
.
W
h
ile
th
is
g
u
ar
an
tees
m
ea
s
u
r
em
en
t
ac
cu
r
ac
y
,
it
b
ec
o
m
es
a
s
er
i
o
u
s
b
o
ttlen
ec
k
i
n
h
ig
h
-
v
o
lu
m
e
m
an
u
f
ac
t
u
r
in
g
en
v
ir
o
n
m
en
ts
.
Fo
r
in
s
tan
ce
,
f
ac
ilit
ies
th
at
p
r
o
d
u
ce
th
o
u
s
a
n
d
s
o
f
m
eter
s
d
aily
f
ac
e
p
r
o
l
o
n
g
ed
ca
lib
r
atio
n
cy
cles,
wh
i
ch
d
ir
ec
tly
co
n
s
tr
ain
th
r
o
u
g
h
p
u
t
an
d
d
elay
d
eliv
er
y
s
ch
ed
u
les.
T
o
co
p
e
with
th
is
d
em
an
d
,
m
a
n
u
f
ac
tu
r
er
s
o
f
ten
ex
p
an
d
ca
p
a
city
b
y
in
v
esti
n
g
in
ad
d
itio
n
al
test
b
e
n
ch
es.
Ho
wev
e
r
,
th
is
a
p
p
r
o
ac
h
in
tr
o
d
u
ce
s
s
ev
e
r
al
n
ew
p
r
o
b
lem
s
:
th
e
ac
q
u
is
itio
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
A
n
A
I
-
d
r
iven
fr
a
mewo
r
k
fo
r
ef
ficien
t a
n
d
a
cc
u
r
a
te
ca
lib
r
a
tio
n
o
f e
lectricity m
eters
u
s
in
g
…
(
R
o
s
a
lin
a
)
155
an
d
m
ain
ten
an
ce
o
f
b
e
n
ch
es
r
ep
r
esen
t
a
s
u
b
s
tan
tial
f
in
an
cia
l
b
u
r
d
e
n
,
th
e
n
ee
d
f
o
r
ad
d
itio
n
al
s
k
illed
o
p
er
ato
r
s
in
cr
ea
s
es
lab
o
r
co
s
ts
,
an
d
th
e
p
h
y
s
ical
s
p
ac
e
r
eq
u
ir
e
d
f
o
r
lar
g
e
test
b
en
ch
in
s
tallatio
n
s
cr
ea
tes
lo
g
is
tica
l
d
if
f
icu
lties
.
T
h
ese
co
m
b
in
ed
f
ac
to
r
s
m
ak
e
s
ca
lin
g
p
r
o
d
u
ctio
n
b
o
th
co
s
tly
an
d
in
ef
f
icien
t,
p
ar
ticu
lar
ly
in
a
co
m
p
etitiv
e
m
ar
k
et
wh
er
e
f
le
x
ib
ilit
y
an
d
r
esp
o
n
s
iv
en
ess
ar
e
cr
itical.
Giv
en
th
ese
lim
itatio
n
s
,
t
h
er
e
is
g
r
o
win
g
in
te
r
est
in
a
d
o
p
ti
n
g
a
d
v
an
ce
d
tech
n
o
lo
g
ies
—
p
ar
ticu
lar
ly
ar
tific
ial
in
tellig
en
ce
(
AI
)
—
to
im
p
r
o
v
e
ca
lib
r
atio
n
ef
f
ici
en
cy
.
I
n
tellig
en
t
ca
lib
r
atio
n
h
as
alr
ea
d
y
b
ee
n
ex
p
lo
r
ed
in
d
iv
er
s
e
d
o
m
ai
n
s
,
s
u
ch
as
m
icr
o
-
elec
tr
o
-
m
ec
h
an
ical
s
y
s
tem
s
(
MEMS
)
s
en
s
o
r
f
u
s
io
n
[
2
]
,
[
3
]
,
s
tr
ap
d
o
wn
in
er
tial
n
av
ig
atio
n
s
y
s
tem
s
(
SIN
S)
[
4
]
,
v
o
r
tex
f
lo
wm
eter
ca
lib
r
atio
n
[
5
]
,
an
d
ev
en
al
g
o
r
ith
m
i
c
m
u
s
ic
co
m
p
o
s
itio
n
[
6
]
.
T
h
ese
s
tu
d
ies
d
em
o
n
s
tr
ate
h
o
w
m
ac
h
in
e
lear
n
in
g
m
o
d
els,
esp
ec
ial
ly
r
eg
r
ess
io
n
-
b
ased
ap
p
r
o
ac
h
es,
ca
n
p
r
o
v
id
e
f
aster
an
d
m
o
r
e
ac
cu
r
ate
p
r
ed
ictio
n
s
th
an
tr
ad
itio
n
al
ca
lib
r
atio
n
tech
n
iq
u
es
.
Ho
wev
er
,
d
esp
ite
th
e
ev
id
e
n
t
b
en
ef
its
,
th
e
ap
p
licatio
n
o
f
in
tellig
en
t
ca
lib
r
atio
n
in
elec
tr
icity
m
ete
r
m
an
u
f
ac
tu
r
in
g
r
em
ain
s
lim
ite
d
.
On
e
n
o
tab
le
co
n
tr
ib
u
tio
n
i
s
th
e
f
r
am
ewo
r
k
p
r
o
p
o
s
ed
b
y
Z
aid
an
et
a
l.
[
7
]
,
wh
ich
em
p
lo
y
ed
a
u
to
m
ated
test
s
y
s
tem
s
an
d
in
ter
ch
an
g
e
ab
l
e
v
ir
tu
al
in
s
tr
u
m
en
ts
(
I
VI
)
f
o
r
r
ap
id
ca
li
b
r
atio
n
.
W
h
ile
p
r
o
m
is
in
g
,
s
u
ch
ap
p
r
o
ac
h
es
h
av
e
y
et
to
b
e
f
u
lly
ad
ap
ted
f
o
r
elec
tr
icity
m
eter
p
r
o
d
u
ctio
n
,
wh
er
e
th
e
v
o
lu
m
e
a
n
d
co
m
p
lex
ity
o
f
ca
li
b
r
atio
n
d
ata
p
r
esen
t b
o
th
ch
all
en
g
es a
n
d
o
p
p
o
r
tu
n
ities
f
o
r
AI
-
d
r
iv
en
s
o
lu
tio
n
s
.
Am
o
n
g
av
ail
ab
le
t
ec
h
n
i
q
u
es
,
tr
e
e
-
b
ase
d
m
o
d
e
ls
s
u
c
h
as
ex
t
r
e
m
e
g
r
a
d
ie
n
t
b
o
o
s
ti
n
g
(
XGB
o
o
s
t
)
h
av
e
s
h
o
wn
c
o
n
s
i
d
e
r
a
b
l
e
p
o
t
en
tia
l
i
n
h
a
n
d
li
n
g
la
r
g
e
-
s
ca
le
,
co
m
p
le
x
d
at
asets
.
XGBo
o
s
t
,
i
n
p
ar
t
ic
u
la
r
,
is
w
id
el
y
r
e
co
g
n
iz
e
d
f
o
r
its
p
r
e
d
i
cti
v
e
p
o
we
r
an
d
ef
f
i
cie
n
cy
,
o
u
tp
e
r
f
o
r
m
i
n
g
alt
e
r
n
ati
v
es
s
u
ch
as
s
u
p
p
o
r
t v
ec
to
r
m
a
ch
in
es
(
SVM
)
,
d
e
cisi
o
n
tr
ee
s
(
DT
)
,
a
n
d
g
r
a
d
ie
n
t
b
o
o
s
ti
n
g
d
e
cisi
o
n
t
r
e
es
(
GB
D
T
)
i
n
a
v
ar
iet
y
o
f
a
p
p
li
ca
t
io
n
s
[
8
]
–
[
1
0
]
.
I
ts
e
n
s
e
m
b
le
a
p
p
r
o
ac
h
,
wh
ic
h
c
o
m
b
in
es
m
u
lt
ip
le
we
a
k
lea
r
n
e
r
s
i
n
t
o
a
r
o
b
u
s
t
p
r
e
d
i
cti
v
e
m
o
d
el,
all
o
ws
it
t
o
d
el
iv
e
r
h
i
g
h
a
cc
u
r
a
cy
w
h
il
e
m
iti
g
ati
n
g
o
v
e
r
f
itti
n
g
th
r
o
u
g
h
in
te
g
r
at
ed
r
e
g
u
la
r
i
za
t
io
n
[
1
1
]
,
[
1
2
]
.
F
u
r
th
e
r
m
o
r
e
,
XGBo
o
s
t
is
w
ell
-
s
u
it
ed
f
o
r
in
d
u
s
tr
ial
a
p
p
li
ca
t
io
n
s
d
u
e
t
o
its
e
f
f
i
ci
en
t
m
e
m
o
r
y
u
s
e
,
a
b
ili
ty
to
m
a
n
ag
e
m
is
s
i
n
g
d
at
a,
an
d
s
c
ala
b
i
lit
y
a
cr
o
s
s
d
is
t
r
i
b
u
te
d
c
o
m
p
u
ti
n
g
p
lat
f
o
r
m
s
[
1
3
]
,
[
1
4
]
.
T
h
ese
c
h
a
r
a
cte
r
is
t
ics
m
a
k
e
it
p
a
r
ti
c
u
la
r
l
y
r
e
le
v
a
n
t
t
o
ele
ct
r
i
cit
y
m
et
e
r
m
a
n
u
f
ac
t
u
r
i
n
g
,
wh
er
e
v
ast
a
m
o
u
n
ts
o
f
c
ali
b
r
ati
o
n
d
a
ta
a
r
e
g
en
e
r
at
ed
d
ai
ly
.
T
o
a
c
h
ie
v
e
o
p
ti
m
a
l
r
e
s
u
lts
,
h
o
w
e
v
e
r
,
X
GB
o
o
s
t
r
e
q
u
i
r
es
c
ar
e
f
u
l
h
y
p
e
r
p
a
r
a
m
et
er
t
u
n
i
n
g
t
o
b
al
a
n
ce
ac
c
u
r
a
cy
a
n
d
g
en
er
ali
za
ti
o
n
.
Fin
e
-
tu
n
i
n
g
t
h
es
e
p
a
r
a
m
et
e
r
s
is
co
m
p
le
x
,
es
p
e
cia
ll
y
w
h
e
n
d
e
ali
n
g
wi
th
h
i
g
h
-
d
i
m
e
n
s
i
o
n
al
d
at
asets
t
y
p
i
ca
l
o
f
m
a
n
u
f
ac
tu
r
i
n
g
en
v
i
r
o
n
m
e
n
ts
.
R
e
ce
n
t
s
t
u
d
ies
ac
r
o
s
s
e
n
g
i
n
ee
r
i
n
g
,
e
n
e
r
g
y
,
an
d
m
a
n
u
f
ac
t
u
r
i
n
g
d
o
m
ai
n
s
h
a
v
e
d
e
m
o
n
s
tr
ate
d
t
h
e
s
t
r
o
n
g
p
r
e
d
ic
ti
v
e
ca
p
a
b
il
it
y
o
f
X
GB
o
o
s
t
an
d
t
h
e
b
en
ef
its
o
f
s
y
s
te
m
a
tic
m
o
d
el
o
p
ti
m
i
za
ti
o
n
[
1
5
]
–
[
2
3
]
.
I
n
p
a
r
ti
c
u
la
r
,
o
p
ti
m
iz
ati
o
n
s
t
r
at
e
g
ies
s
u
c
h
as
p
ar
tic
le
s
w
ar
m
o
p
ti
m
iz
ati
o
n
(
PS
O
)
h
av
e
p
r
o
v
e
n
e
f
f
e
cti
v
e
f
o
r
e
f
f
ici
en
tl
y
s
ea
r
c
h
i
n
g
s
u
ita
b
l
e
h
y
p
e
r
p
a
r
a
m
ete
r
c
o
n
f
ig
u
r
a
ti
o
n
s
[
2
4
]
–
[
2
6
]
.
B
y
i
n
t
eg
r
a
ti
n
g
XG
B
o
o
s
t w
it
h
PS
O
-
b
ase
d
o
p
tim
iz
ati
o
n
,
i
t
b
ec
o
m
es
p
o
s
s
i
b
le
t
o
d
ev
el
o
p
a
n
i
n
te
lli
g
e
n
t
ca
li
b
r
at
io
n
f
r
am
ew
o
r
k
t
h
at
n
o
t
o
n
ly
r
e
d
u
c
es
ca
li
b
r
ati
o
n
ti
m
e
b
u
t
als
o
m
in
im
izes
r
e
lia
n
c
e
o
n
c
o
s
tl
y
t
est
b
e
n
c
h
in
f
r
ast
r
u
ct
u
r
e
a
n
d
d
e
cr
ea
s
es
o
p
er
ati
o
n
al
e
x
p
e
n
s
es
.
T
h
is
s
tu
d
y
in
v
esti
g
ates
th
e
in
teg
r
atio
n
o
f
XGBo
o
s
t
with
PS
O
-
d
r
iv
en
o
p
tim
izatio
n
to
cr
ea
te
a
s
ca
lab
le
ca
lib
r
atio
n
s
y
s
tem
f
o
r
elec
tr
icity
m
eter
m
an
u
f
ac
tu
r
i
n
g
.
T
h
e
g
o
al
is
to
s
tr
ea
m
lin
e
c
alib
r
atio
n
,
en
h
a
n
ce
p
r
o
d
u
ctio
n
t
h
r
o
u
g
h
p
u
t,
a
n
d
i
m
p
r
o
v
e
co
s
t
-
ef
f
ec
tiv
e
n
ess
with
o
u
t
c
o
m
p
r
o
m
is
in
g
ac
c
u
r
ac
y
o
r
co
m
p
lian
ce
.
B
y
au
to
m
atin
g
an
d
r
ef
in
i
n
g
t
h
is
ess
en
tial
s
tep
,
th
e
p
r
o
p
o
s
ed
a
p
p
r
o
ac
h
o
f
f
er
s
a
p
ath
wa
y
to
war
d
s
m
ar
ter
,
m
o
r
e
ef
f
icien
t m
an
u
f
ac
tu
r
in
g
p
r
ac
ti
ce
s
th
at
ca
n
b
etter
r
esp
o
n
d
to
ev
o
lv
in
g
m
ar
k
et
d
em
an
d
s
.
2.
M
E
T
H
O
D
2
.
1
.
Resea
rc
h
f
ra
m
ewo
r
k
T
h
e
r
esear
ch
f
r
am
ew
o
r
k
f
o
r
t
h
e
d
ev
el
o
p
m
en
t
o
f
an
in
tellig
en
t
ca
lib
r
atio
n
v
e
r
if
icatio
n
t
est
s
y
s
tem
aim
s
to
p
r
e
d
ict
ac
cu
r
ate
test
m
etr
o
lo
g
y
in
elec
tr
icity
m
eter
m
an
u
f
ac
tu
r
in
g
.
T
h
e
f
r
a
m
ewo
r
k
,
s
h
o
wn
in
Fig
u
r
e
1
,
is
g
r
o
u
n
d
ed
i
n
a
liter
atu
r
e
r
ev
iew
th
at
estab
lis
h
es
th
e
b
aselin
e
f
o
r
th
e
r
esear
ch
.
T
h
e
p
r
o
b
lem
ad
d
r
ess
ed
in
th
is
s
tu
d
y
p
er
ta
in
s
to
th
e
ca
lib
r
atio
n
test
in
g
p
r
o
ce
s
s
in
th
e
elec
tr
icity
m
eter
m
an
u
f
ac
tu
r
in
g
in
d
u
s
tr
y
,
s
p
ec
if
ically
th
e
m
etr
o
lo
g
y
ch
allen
g
es
ass
o
ciate
d
with
s
tan
d
ar
d
ca
lib
r
atio
n
test
b
en
ch
es.
T
h
e
tr
ad
itio
n
al
ca
lib
r
atio
n
p
r
o
ce
s
s
r
eq
u
ir
es
co
m
p
a
r
in
g
th
e
m
eter
u
n
d
er
test
to
a
s
tan
d
ar
d
m
eter
test
b
en
ch
,
a
tim
e
-
co
n
s
u
m
in
g
p
r
o
ce
d
u
r
e
with
lo
n
g
c
y
cle
tim
es
[
2
7
]
.
I
n
cr
ea
s
in
g
p
r
o
d
u
ctio
n
ca
p
ac
ity
wo
u
ld
t
y
p
ically
n
ec
ess
itate
ad
d
itio
n
al
ex
p
e
n
s
iv
e
test
b
en
ch
es,
cr
ea
tin
g
a
f
in
an
cial
b
u
r
d
e
n
.
T
h
e
r
esear
ch
h
y
p
o
th
esis
s
u
g
g
ests
th
at
m
ac
h
in
e
lear
n
in
g
ca
n
p
r
o
v
id
e
a
s
o
lu
ti
o
n
b
y
p
r
ed
ictin
g
ac
cu
r
ate
ca
lib
r
atio
n
r
esu
lts
,
th
u
s
elim
in
atin
g
th
e
n
ee
d
f
o
r
ad
d
itio
n
al
test
b
e
n
ch
es.
B
ased
o
n
th
is
,
a
p
r
e
d
ictiv
e
m
o
d
el
u
s
in
g
m
ac
h
i
n
e
lear
n
in
g
is
d
ev
elo
p
ed
t
o
au
t
o
m
ate
an
d
o
p
tim
ize
t
h
e
ca
lib
r
atio
n
v
er
if
icatio
n
test
p
r
o
ce
s
s
.
2
.
2
.
Da
t
a
c
o
llect
io
n
T
h
e
d
ata
co
llectio
n
p
r
o
ce
s
s
in
th
is
s
tu
d
y
ce
n
ter
s
o
n
ca
lib
r
atio
n
test
r
esu
lts
s
o
u
r
ce
d
f
r
o
m
m
eter
test
b
en
ch
m
ac
h
in
es u
tili
ze
d
d
u
r
in
g
m
an
u
f
ac
tu
r
i
n
g
.
T
h
e
d
ataset
co
m
p
r
is
es
m
eter
r
ea
d
in
g
s
,
test
p
ar
am
eter
s
s
u
ch
as
v
o
ltag
e
an
d
cu
r
r
en
t,
an
d
ass
o
c
iated
ca
lib
r
atio
n
o
u
tco
m
es,
in
clu
d
in
g
r
ec
o
r
d
ed
er
r
o
r
v
alu
es.
T
h
ese
d
ata
p
o
in
ts
,
d
r
awn
f
r
o
m
t
h
e
in
ter
n
al
m
ac
h
in
e
d
atab
ase,
r
ep
r
esen
t
a
wid
e
r
an
g
e
o
f
m
eter
m
o
d
els
an
d
test
in
g
co
n
d
itio
n
s
,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
6
:
154
-
1
6
3
156
ca
p
tu
r
in
g
th
e
d
iv
er
s
ity
in
h
er
en
t
in
th
e
p
r
o
d
u
ctio
n
e
n
v
ir
o
n
m
en
t.
T
o
alig
n
with
in
d
u
s
tr
y
s
tan
d
ar
d
s
,
all
ca
lib
r
atio
n
r
esu
lts
co
n
f
o
r
m
to
th
e
ac
cu
r
ac
y
t
h
r
esh
o
ld
s
d
e
f
in
e
d
f
o
r
s
tan
d
ar
d
-
class
m
eter
s
.
I
n
ad
d
itio
n
t
o
th
e
p
r
im
a
r
y
d
at
a,
s
u
p
p
lem
e
n
tar
y
in
f
o
r
m
atio
n
s
u
ch
as
p
r
o
d
u
ctio
n
lin
e
i
d
en
t
if
ier
s
an
d
en
v
ir
o
n
m
en
tal
v
ar
iab
les
(
e.
g
.
,
tem
p
er
atu
r
e
an
d
h
u
m
id
ity
)
was
in
co
r
p
o
r
ated
wh
e
r
e
av
ailab
le
to
ev
alu
ate
th
eir
in
f
lu
en
ce
o
n
ca
lib
r
atio
n
p
er
f
o
r
m
an
ce
an
d
s
tr
en
g
th
en
m
o
d
el
r
eliab
ilit
y
.
B
ef
o
r
e
m
o
d
elin
g
,
th
e
d
ataset
u
n
d
er
wen
t
a
s
y
s
tem
atic
p
r
e
p
r
o
ce
s
s
in
g
p
h
ase:
m
is
s
in
g
v
alu
es
wer
e
ad
d
r
ess
ed
u
s
in
g
m
ea
n
o
r
m
o
d
e
im
p
u
tatio
n
,
o
u
tlier
s
wer
e
ca
p
p
e
d
v
ia
t
h
e
i
n
ter
q
u
ar
tile
r
a
n
g
e
(
I
QR
)
m
eth
o
d
,
an
d
f
ea
t
u
r
es
wer
e
n
o
r
m
ali
ze
d
u
s
in
g
m
in
-
m
ax
s
ca
lin
g
.
I
r
r
ele
v
an
t
attr
ib
u
tes
(
e.
g
.
,
tim
estam
p
s
)
wer
e
ex
clu
d
e
d
,
a
n
d
i
n
ter
ac
tio
n
f
ea
tu
r
es
—
s
u
ch
as
v
o
ltag
e
-
cu
r
r
en
t
p
air
s
—
wer
e
en
g
in
ee
r
ed
to
im
p
r
o
v
e
p
r
ed
i
ctiv
e
ca
p
ac
ity
.
Featu
r
e
s
elec
t
io
n
was
g
u
id
ed
b
y
co
r
r
elatio
n
an
aly
s
is
an
d
m
u
t
u
al
in
f
o
r
m
atio
n
s
co
r
es.
Fo
r
m
o
d
el
tr
ain
in
g
an
d
ev
alu
atio
n
,
th
e
d
ataset
wa
s
d
iv
id
ed
in
t
o
an
8
0
:2
0
r
atio
,
en
s
u
r
in
g
r
o
b
u
s
t te
s
tin
g
o
n
p
r
ev
io
u
s
ly
u
n
s
ee
n
d
ata.
Fig
u
r
e
1
.
T
h
e
r
esear
ch
f
r
am
e
wo
r
k
f
o
r
in
tellig
en
t c
alib
r
atio
n
v
er
if
icatio
n
test
s
y
s
tem
2
.
3
.
M
o
del
d
ev
elo
pm
ent
us
ing
XG
B
o
o
s
t
W
ith
th
e
d
ataset
p
r
o
p
er
ly
p
r
ep
ar
ed
,
th
e
n
ex
t
s
tep
in
v
o
lv
es
tr
ain
in
g
th
e
XGBo
o
s
t
m
o
d
el.
T
h
is
alg
o
r
ith
m
b
u
ild
s
its
p
r
ed
ictiv
e
s
tr
en
g
th
th
r
o
u
g
h
an
en
s
em
b
le
o
f
DT
,
wh
er
e
ea
ch
s
u
cc
ess
iv
e
tr
ee
is
d
esig
n
ed
to
co
r
r
ec
t
th
e
r
esid
u
al
er
r
o
r
s
lef
t
b
y
its
p
r
e
d
ec
ess
o
r
s
.
I
n
ev
er
y
iter
atio
n
,
a
n
ew
DT
is
co
n
s
tr
u
cted
u
s
in
g
th
e
g
r
ad
ien
t
o
f
th
e
l
o
s
s
f
u
n
ctio
n
,
wh
ich
q
u
an
tifie
s
th
e
d
if
f
er
en
ce
b
etwe
en
p
r
ed
icted
a
n
d
ac
tu
al
v
alu
es.
T
h
is
g
r
ad
ien
t
b
o
o
s
tin
g
m
ec
h
an
is
m
allo
ws
th
e
m
o
d
el
to
iter
ativ
e
ly
r
ef
in
e
its
p
er
f
o
r
m
an
ce
b
y
r
ed
u
cin
g
p
r
ed
ictio
n
er
r
o
r
s
o
v
er
tim
e.
T
h
e
u
n
d
er
l
y
in
g
m
ath
em
atica
l
s
tr
u
ctu
r
e
o
f
XGBo
o
s
t
ce
n
ter
s
o
n
o
p
tim
izin
g
an
o
b
jectiv
e
f
u
n
ctio
n
,
wh
ich
co
m
b
in
es
a
lo
s
s
f
u
n
ctio
n
—
m
ea
s
u
r
in
g
p
r
e
d
ictio
n
ac
cu
r
ac
y
—
with
a
r
eg
u
lar
izatio
n
ter
m
th
at
p
en
alize
s
m
o
d
el
co
m
p
lex
ity
.
T
h
is
co
m
b
in
atio
n
n
o
t
o
n
ly
en
h
an
ce
s
p
r
e
d
ictiv
e
p
r
ec
is
io
n
b
u
t
also
h
elp
s
p
r
ev
e
n
t
o
v
er
f
itti
n
g
.
T
h
e
o
b
jectiv
e
f
u
n
ctio
n
is
f
o
r
m
ally
ex
p
r
ess
ed
in
(
1
)
,
r
ef
lectin
g
th
e
m
o
d
el
’
s
b
alan
ce
b
etwe
en
ac
cu
r
ac
y
an
d
g
e
n
er
aliza
tio
n
.
(
)
=
∑
(
,
̂
)
+
∑
Ω
(
)
=
1
=
1
(
1
)
W
h
er
e:
−
(
,
̂
)
is
th
e
lo
s
s
f
u
n
ctio
n
(
e.
g
.
,
m
ea
n
s
q
u
ar
ed
er
r
o
r
)
f
o
r
th
e
p
r
ed
icte
d
an
d
ac
t
u
al
v
alu
es.
−
Ω
(
)
is
th
e
r
eg
u
lar
izatio
n
te
r
m
,
wh
i
ch
p
en
alize
s
co
m
p
le
x
ity
in
th
e
m
o
d
el
to
p
r
ev
e
n
t o
v
e
r
f
itti
n
g
.
−
K
r
ep
r
esen
ts
th
e
n
u
m
b
er
o
f
tr
e
es.
−
r
ep
r
esen
ts
th
e
DT
in
th
e
m
o
d
el.
I
n
th
is
s
tu
d
y
,
m
o
d
el
p
er
f
o
r
m
a
n
ce
was a
s
s
es
s
ed
u
s
in
g
r
o
o
t m
ea
n
s
q
u
ar
e
er
r
o
r
(
R
MSE
)
,
m
ea
n
ab
s
o
lu
te
er
r
o
r
(
MA
E
)
,
an
d
th
e
co
ef
f
icien
t
o
f
d
eter
m
in
atio
n
(
R
²)
.
R
MSE
an
d
MA
E
ca
p
tu
r
e
th
e
a
v
er
ag
e
m
ag
n
itu
d
e
o
f
p
r
ed
ictio
n
er
r
o
r
s
,
wh
ile
R
²
m
ea
s
u
r
es
h
o
w
well
th
e
m
o
d
el
e
x
p
lain
s
v
ar
ian
ce
in
th
e
tar
g
et
v
ar
iab
le.
T
o
en
s
u
r
e
r
o
b
u
s
tn
ess
,
a
f
i
v
e
-
f
o
l
d
cr
o
s
s
-
v
alid
atio
n
p
r
o
ce
d
u
r
e
was
a
p
p
lied
.
T
o
v
alid
ate
th
e
ch
o
i
ce
o
f
XGBo
o
s
t,
its
p
er
f
o
r
m
an
ce
was
co
m
p
ar
e
d
with
s
u
p
p
o
r
t
v
ec
to
r
r
eg
r
ess
io
n
(
SVR
)
,
r
an
d
o
m
f
o
r
ests
(
R
F)
,
an
d
lin
ea
r
r
eg
r
ess
io
n
(
L
R
)
.
T
h
e
ex
p
er
im
en
tal
r
esu
lt
s
ar
e
p
r
esen
ted
in
T
a
b
le
1
.
As
s
h
o
wn
in
T
a
b
le
1
,
XG
B
o
o
s
t
co
n
s
is
ten
tly
o
u
tp
er
f
o
r
m
ed
th
e
alter
n
ativ
e
m
o
d
els
ac
r
o
s
s
all
ev
alu
atio
n
m
etr
ics.
C
o
m
p
ar
e
d
to
RF
an
d
SVR
,
XGBo
o
s
t
a
ch
iev
ed
lo
wer
er
r
o
r
r
at
es
(
R
MSE
=0
.
1
1
8
,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
A
n
A
I
-
d
r
iven
fr
a
mewo
r
k
fo
r
ef
ficien
t a
n
d
a
cc
u
r
a
te
ca
lib
r
a
tio
n
o
f e
lectricity m
eters
u
s
in
g
…
(
R
o
s
a
lin
a
)
157
MA
E
=
0
.
0
9
5
)
an
d
a
h
ig
h
e
r
R
²
v
alu
e
(
0
.
9
2
1
)
,
in
d
icatin
g
s
tr
o
n
g
er
ex
p
la
n
ato
r
y
p
o
wer
an
d
p
r
ed
ictiv
e
ac
cu
r
ac
y
.
I
ts
p
er
f
o
r
m
an
ce
a
d
v
an
tag
e
is
lar
g
ely
attr
ib
u
ted
to
its
r
eg
u
lar
izatio
n
f
r
am
ewo
r
k
,
wh
ich
ef
f
ec
tiv
ely
co
n
tr
o
ls
m
o
d
el
co
m
p
lex
ity
,
an
d
its
ab
ilit
y
to
h
an
d
le
o
u
tlier
s
an
d
m
is
s
in
g
v
alu
es
with
in
th
e
ca
lib
r
at
io
n
d
ataset.
T
h
ese
r
esu
lts
d
em
o
n
s
tr
ate
th
at
XGBo
o
s
t
is
n
o
t
o
n
ly
ca
p
ab
le
o
f
d
eliv
er
in
g
m
o
r
e
ac
cu
r
ate
p
r
ed
ictio
n
s
th
an
co
n
v
en
tio
n
al
m
o
d
els
b
u
t
is
al
s
o
b
etter
s
u
ited
f
o
r
th
e
d
iv
er
s
e
an
d
c
o
m
p
lex
d
atasets
ty
p
ically
en
co
u
n
ter
ed
in
elec
tr
icity
m
eter
ca
lib
r
atio
n
.
T
h
e
f
in
d
i
n
g
s
ju
s
tify
its
s
elec
tio
n
as
th
e
co
r
e
m
o
d
el
f
o
r
th
e
in
t
ellig
en
t
ca
lib
r
atio
n
f
r
am
ewo
r
k
p
r
o
p
o
s
ed
in
th
is
s
tu
d
y
.
T
ab
le
1
.
C
o
m
p
a
r
ativ
e
p
er
f
o
r
m
an
ce
o
f
m
ac
h
in
e
lear
n
in
g
m
o
d
els
M
o
d
e
l
R
M
S
E
M
A
E
R²
LR
0
.
1
8
7
0
.
1
5
2
0
.
8
4
2
S
V
R
0
.
1
6
1
0
.
1
2
7
0
.
8
7
6
RF
0
.
1
4
2
0
.
1
1
4
0
.
8
9
2
X
G
B
o
o
st
0
.
1
1
8
0
.
0
9
5
0
.
9
2
1
2
.
4
.
H
y
perpa
ra
m
e
t
er
t
un
ing
a
nd
o
ptim
iza
t
io
n
I
n
th
is
s
tu
d
y
,
PSO
was
u
til
iz
ed
to
id
en
tify
th
e
o
p
tim
al
s
et
o
f
h
y
p
er
p
ar
am
eter
s
f
o
r
th
e
XGBo
o
s
t
m
o
d
el.
PS
O
is
a
p
o
p
u
latio
n
-
b
ased
o
p
tim
izatio
n
tech
n
i
q
u
e
th
at
s
im
u
lates
th
e
s
o
cial
b
e
h
av
io
r
o
f
a
s
war
m
,
wh
er
e
ea
ch
p
ar
ticle
r
e
p
r
esen
t
s
a
p
o
ten
tial
s
o
lu
tio
n
—
in
th
is
ca
s
e,
a
s
p
ec
if
ic
co
m
b
in
atio
n
o
f
h
y
p
er
p
ar
a
m
eter
s
s
u
ch
as
lear
n
in
g
r
ate,
m
ax
im
u
m
d
ep
th
,
an
d
th
e
n
u
m
b
er
o
f
e
s
tim
ato
r
s
.
T
h
e
alg
o
r
ith
m
iter
a
tiv
ely
u
p
d
ates
ea
ch
p
ar
ticle’
s
p
o
s
itio
n
in
th
e
s
ea
r
ch
s
p
ac
e
b
ased
o
n
its
o
wn
b
est
-
k
n
o
wn
p
o
s
itio
n
an
d
th
e
g
lo
b
al
b
est
p
o
s
itio
n
id
en
tifie
d
b
y
th
e
s
war
m
.
T
o
co
n
f
ig
u
r
e
th
e
o
p
tim
izatio
n
,
a
s
war
m
o
f
2
0
p
ar
ticles
was
in
itialized
,
an
d
th
e
s
ea
r
c
h
p
r
o
ce
s
s
was
allo
wed
to
r
u
n
f
o
r
a
m
a
x
im
u
m
o
f
5
0
iter
atio
n
s
o
r
u
n
til
co
n
v
er
g
en
ce
.
T
h
ese
v
alu
es
wer
e
s
elec
ted
to
p
r
o
v
id
e
a
b
alan
ce
b
etwe
en
ex
p
lo
r
atio
n
an
d
c
o
m
p
u
tatio
n
al
ef
f
icien
c
y
:
a
s
m
aller
s
war
m
m
a
y
li
m
it
th
e
d
iv
er
s
ity
o
f
ca
n
d
id
ate
s
o
lu
tio
n
s
,
wh
ile
e
x
ce
s
s
iv
ely
lar
g
e
s
war
m
s
s
ig
n
if
ican
tly
in
cr
ea
s
e
co
m
p
u
tati
o
n
al
co
s
t
with
o
u
t
a
p
r
o
p
o
r
tio
n
al
im
p
r
o
v
em
e
n
t
in
ac
cu
r
ac
y
.
Similar
ly
,
5
0
iter
atio
n
s
wer
e
f
o
u
n
d
s
u
f
f
icien
t
to
a
ch
iev
e
co
n
v
er
g
en
ce
in
p
r
elim
in
a
r
y
test
s
,
as
p
er
f
o
r
m
an
ce
g
ain
s
p
latea
u
ed
b
ey
o
n
d
th
is
p
o
i
n
t.
T
h
e
s
ea
r
ch
s
p
ac
e
f
o
r
h
y
p
e
r
p
ar
am
eter
s
was d
ef
in
ed
as f
o
llo
ws,
b
ased
o
n
p
r
i
o
r
r
esear
ch
an
d
p
r
ac
tical
co
n
s
tr
ain
ts
in
ca
lib
r
atio
n
d
ata
s
ets:
−
L
ea
r
n
in
g
r
ate
(
η
)
:
0
.
0
1
-
0
.
3
,
a
s
m
aller
lear
n
in
g
r
ate
(
clo
s
er
to
0
.
0
1
)
en
ab
les
g
r
a
d
u
al
co
n
v
er
g
en
ce
an
d
r
ed
u
ce
s
th
e
r
is
k
o
f
o
v
er
s
h
o
o
tin
g
o
p
tim
al
s
o
lu
tio
n
s
,
wh
ile
h
ig
h
er
v
alu
es
(
u
p
to
0
.
3
)
allo
w
f
aster
co
n
v
er
g
en
ce
b
u
t m
ay
i
n
cr
ea
s
e
th
e
r
is
k
o
f
o
v
er
f
itti
n
g
.
−
Ma
x
im
u
m
tr
ee
d
e
p
th
:
3
-
10
,
s
h
allo
wer
tr
ee
s
(
d
ep
th
3
-
5
)
p
r
e
v
en
t
o
v
er
f
itti
n
g
an
d
im
p
r
o
v
e
g
en
er
aliza
tio
n
,
wh
ile
d
ee
p
er
tr
ee
s
(
u
p
to
1
0
)
e
n
ab
le
th
e
m
o
d
el
to
ca
p
tu
r
e
c
o
m
p
lex
p
atter
n
s
in
ca
lib
r
atio
n
d
ata.
−
N
u
m
b
er
o
f
esti
m
ato
r
s
(
tr
ee
s
)
:
5
0
-
500
,
t
h
is
r
a
n
g
e
b
alan
ce
s
co
m
p
u
tatio
n
al
ef
f
icien
c
y
w
ith
p
r
ed
ictiv
e
p
o
wer
; to
o
f
ew
tr
ee
s
m
ay
u
n
d
er
f
it,
wh
ile
to
o
m
a
n
y
ca
n
s
lo
w
tr
ain
in
g
with
o
u
t sig
n
if
ican
t a
c
cu
r
ac
y
g
ai
n
s
.
−
S
u
b
s
am
p
le
r
atio
: 0
.
6
-
1
.
0
, t
h
is
p
ar
am
eter
co
n
tr
o
ls
th
e
f
r
ac
tio
n
o
f
tr
ain
in
g
d
ata
s
am
p
led
f
o
r
ea
ch
tr
ee
,
wit
h
v
alu
es
u
n
d
e
r
1
.
0
ad
d
i
n
g
s
to
ch
asti
city
th
at
h
elp
s
p
r
ev
en
t
o
v
er
f
itti
n
g
.
−
C
o
lu
m
n
s
am
p
le
b
y
tr
e
e
(
f
ea
t
u
r
e
s
am
p
lin
g
r
atio
)
:
0
.
5
-
1
.
0
,
s
am
p
lin
g
f
ea
tu
r
es
in
tr
o
d
u
ce
s
d
i
v
er
s
ity
in
tr
ee
co
n
s
tr
u
ctio
n
a
n
d
r
e
d
u
ce
s
co
r
r
e
latio
n
am
o
n
g
tr
ee
s
,
en
h
a
n
cin
g
g
en
er
aliza
tio
n
.
Du
r
in
g
ea
c
h
iter
atio
n
,
p
ar
ticle
s
ad
ju
s
ted
th
eir
v
elo
cities
an
d
p
o
s
itio
n
s
u
s
in
g
th
e
s
tan
d
ar
d
PS
O
u
p
d
ate
r
u
les
p
r
esen
ted
in
(
2
)
an
d
(
3
)
wh
ich
b
alan
ce
e
x
p
lo
r
atio
n
a
n
d
e
x
p
lo
itatio
n
b
y
in
co
r
p
o
r
ati
n
g
b
o
th
in
d
iv
id
u
al
an
d
co
llectiv
e
lear
n
in
g
c
o
m
p
o
n
en
ts
.
(
+
1
)
=
(
)
+
1
.
(
0
,
1
)
.
(
−
)
+
2
.
(
0
,
1
)
.
(
−
)
(
2
)
(
+
1
)
=
(
)
+
(
+
1
)
(
3
)
W
h
er
e:
−
(
)
is
th
e
v
elo
city
o
f
p
ar
ticle
i
ii in
d
im
en
s
io
n
d
d
d
at
tim
e
ttt.
−
(
)
i
s
th
e
p
o
s
itio
n
(
h
y
p
er
p
ar
am
et
er
v
alu
e)
o
f
p
a
r
ticle
iii in
d
im
e
n
s
io
n
d
d
d
.
−
is
th
e
b
est p
o
s
itio
n
(
h
y
p
er
p
a
r
am
eter
s
et)
f
o
u
n
d
b
y
p
ar
ticle
i
ii.
−
is
th
e
b
est p
o
s
itio
n
f
o
u
n
d
b
y
t
h
e
g
lo
b
al
s
war
m
.
−
is
th
e
in
er
tia
weig
h
t th
at
co
n
t
r
o
ls
th
e
im
p
ac
t o
f
p
r
ev
io
u
s
v
el
o
cities.
−
1
an
d
2
ar
e
co
g
n
itiv
e
a
n
d
s
o
cial
c
o
ef
f
icien
ts
,
r
esp
ec
tiv
ely
(
t
y
p
ic
ally
s
et
to
1
.
5
)
.
−
(
0
,
1
)
is
a
r
an
d
o
m
n
u
m
b
er
b
etwe
en
0
an
d
1
,
ad
d
in
g
s
to
ch
asti
city
t
o
th
e
s
ea
r
ch
p
r
o
ce
s
s
.
T
h
e
o
p
tim
izatio
n
o
b
jectiv
e
was
to
m
in
im
ize
th
e
R
MSE
th
r
o
u
g
h
f
i
v
e
-
f
o
l
d
cr
o
s
s
-
v
ali
d
atio
n
.
T
h
is
en
s
u
r
ed
t
h
at
th
e
ch
o
s
en
h
y
p
er
p
a
r
am
eter
s
n
o
t
o
n
ly
m
in
im
ized
p
r
ed
ictio
n
er
r
o
r
s
b
u
t
also
s
u
p
p
o
r
ted
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
6
:
154
-
1
6
3
158
g
en
er
aliza
tio
n
to
u
n
s
ee
n
d
ata.
T
h
e
f
in
al
h
y
p
er
p
ar
am
eter
co
n
f
ig
u
r
atio
n
s
elec
ted
b
y
PS
O
was
a
lear
n
in
g
r
ate
o
f
0
.
0
8
,
m
a
x
im
u
m
d
e
p
th
o
f
6
,
3
0
0
esti
m
ato
r
s
,
s
u
b
s
am
p
le
r
atio
o
f
0
.
8
,
an
d
co
lu
m
n
s
am
p
le
r
atio
o
f
0
.
7
,
wh
ich
d
eliv
er
ed
th
e
b
est tr
ad
e
-
o
f
f
b
et
wee
n
ac
cu
r
ac
y
a
n
d
c
o
m
p
u
tati
o
n
al
ef
f
icien
c
y
.
2
.
5
.
M
o
del
v
a
lid
a
t
io
n
T
h
e
m
o
d
el
is
v
alid
ated
th
r
o
u
g
h
cr
o
s
s
-
v
alid
atio
n
to
en
s
u
r
e
its
g
en
e
r
aliza
b
ilit
y
an
d
r
o
b
u
s
tn
ess
.
C
r
o
s
s
-
v
alid
atio
n
h
elp
s
p
r
ev
e
n
t
o
v
e
r
f
itti
n
g
a
n
d
e
n
s
u
r
es
th
at
th
e
m
o
d
el
ca
n
m
a
k
e
ac
cu
r
ate
p
r
e
d
ictio
n
s
o
n
u
n
s
ee
n
d
ata.
T
h
e
m
o
d
el'
s
p
er
f
o
r
m
an
ce
is
ev
alu
ated
u
s
in
g
R
MSE
as
in
(
4
)
an
d
MA
E
as
in
(
5
)
,
wh
er
e
is
th
e
n
u
m
b
er
o
f
d
ata
p
o
i
n
ts
,
is
th
e
ac
tu
al
v
alu
e,
̂
is
th
e
p
r
ed
icted
v
alu
e.
=
√
1
∑
(
−
̂
)
2
=
1
(
4
)
=
1
∑
|
−
̂
|
=
1
(
5
)
2
.
6
.
Co
m
pa
riso
n wit
h
t
ra
dit
io
na
l c
a
lib
ra
t
io
n m
et
ho
d
T
o
ev
alu
ate
th
e
ef
f
ec
tiv
en
ess
o
f
th
e
p
r
o
p
o
s
ed
in
tellig
en
t
ca
lib
r
atio
n
s
y
s
tem
,
a
d
etailed
c
o
m
p
ar
is
o
n
was
co
n
d
u
cted
ag
ain
s
t
th
e
tr
a
d
itio
n
al
m
an
u
al
m
eth
o
d
.
C
o
n
v
en
tio
n
al
ca
lib
r
atio
n
ty
p
ically
in
v
o
lv
es
m
atch
in
g
ea
ch
m
eter
’
s
r
ea
d
in
g
to
a
r
ef
er
en
ce
d
ev
ice
th
r
o
u
g
h
s
ev
er
al
test
in
g
c
y
cles,
wh
ich
n
o
t
o
n
ly
d
em
an
d
s
co
n
s
id
er
ab
le
tim
e
an
d
lab
o
r
b
u
t
also
i
n
tr
o
d
u
ce
s
v
a
r
iab
ilit
y
d
u
e
to
h
u
m
an
in
v
o
lv
em
en
t.
I
n
co
n
t
r
ast,
th
e
m
ac
h
in
e
lear
n
in
g
-
b
ased
ap
p
r
o
ac
h
p
r
ed
icts
ca
lib
r
atio
n
o
u
tco
m
es u
s
in
g
a
tr
ain
ed
XGBo
o
s
t
m
o
d
el,
s
ig
n
if
ican
tly
r
ed
u
cin
g
th
e
tim
e
a
n
d
e
f
f
o
r
t
n
ee
d
ed
p
er
m
eter
.
Mu
ltip
le
c
o
n
f
ig
u
r
atio
n
s
o
f
th
e
m
o
d
el
w
er
e
test
ed
to
en
s
u
r
e
r
o
b
u
s
tn
ess
,
in
clu
d
in
g
th
o
s
e
tu
n
ed
with
Gr
id
Sear
ch
C
V,
R
an
d
o
m
ized
Sear
c
h
C
V,
B
ay
esi
an
o
p
tim
izatio
n
,
a
B
ay
esian
-
SVM
h
y
b
r
id
,
an
d
a
d
ef
au
lt
m
o
d
el
with
o
u
t
h
y
p
er
p
ar
am
eter
tu
n
i
n
g
.
T
h
ese
v
a
r
iatio
n
s
wer
e
co
m
p
ar
e
d
b
ased
o
n
p
r
ed
ictio
n
ac
cu
r
ac
y
,
p
r
o
ce
s
s
in
g
tim
e,
an
d
er
r
o
r
r
ate
s
.
Am
o
n
g
th
em
,
th
e
p
r
o
p
o
s
ed
m
o
d
el
co
n
s
is
ten
tly
o
u
tp
er
f
o
r
m
ed
th
e
r
est,
ac
h
iev
i
n
g
th
e
h
i
g
h
est
ac
cu
r
ac
y
an
d
l
o
west
er
r
o
r
,
th
er
e
b
y
d
em
o
n
s
tr
a
tin
g
its
p
o
ten
tial
to
s
tr
ea
m
lin
e
th
e
ca
lib
r
atio
n
p
r
o
c
ess
an
d
s
er
v
e
as a
r
eliab
le
alter
n
ativ
e
to
tr
a
d
itio
n
al
m
eth
o
d
s
.
2
.
7
.
I
m
ple
m
ent
a
t
io
n
s
t
eps
o
v
er
v
iew
T
h
e
m
o
d
el
d
ev
elo
p
m
en
t
p
r
o
ce
s
s
was
s
y
s
tem
atica
lly
o
r
g
an
ized
in
to
a
f
iv
e
-
s
tag
e
p
ip
el
in
e,
ea
ch
d
esig
n
ed
to
e
n
h
an
ce
d
ata
q
u
al
ity
an
d
m
o
d
el
p
e
r
f
o
r
m
an
ce
.
T
h
e
f
ir
s
t
s
tag
e
in
v
o
l
v
ed
r
aw
d
a
ta
ex
tr
ac
tio
n
f
r
o
m
ca
lib
r
atio
n
lo
g
s
,
wh
ich
p
r
o
v
id
ed
th
e
f
o
u
n
d
atio
n
al
d
ataset
f
o
r
t
h
e
s
tu
d
y
.
T
h
is
was
f
o
llo
wed
b
y
d
ata
p
r
ep
r
o
ce
s
s
in
g
,
wh
er
e
m
is
s
in
g
v
alu
es,
n
o
is
e,
an
d
o
u
tlier
s
wer
e
h
an
d
led
t
h
r
o
u
g
h
clea
n
i
n
g
an
d
tr
an
s
f
o
r
m
atio
n
p
r
o
ce
d
u
r
es
to
en
s
u
r
e
co
n
s
is
ten
cy
an
d
r
eliab
ilit
y
.
I
n
th
e
th
i
r
d
s
tag
e,
f
ea
tu
r
e
s
elec
tio
n
an
d
cr
ea
tio
n
wer
e
ca
r
r
ied
o
u
t
u
s
in
g
d
o
m
ain
e
x
p
er
tis
e
to
en
g
i
n
ee
r
v
ar
iab
les
th
at
c
o
u
ld
s
ig
n
i
f
ican
tly
im
p
r
o
v
e
m
o
d
el
lear
n
in
g
an
d
g
en
er
aliza
tio
n
.
T
h
e
f
o
u
r
th
s
tag
e
f
o
c
u
s
ed
o
n
m
o
d
el
tr
ain
in
g
,
u
tili
zin
g
t
h
e
XGBo
o
s
t
alg
o
r
ith
m
k
n
o
wn
f
o
r
its
s
p
ee
d
an
d
p
er
f
o
r
m
a
n
ce
,
in
co
m
b
in
atio
n
with
PSO
to
f
in
e
-
t
u
n
e
h
y
p
er
p
ar
am
eter
s
f
o
r
o
p
ti
m
al
r
esu
lts
.
Fin
ally
,
th
e
f
if
th
s
tag
e
in
v
o
lv
ed
e
v
alu
atio
n
,
em
p
lo
y
in
g
cr
o
s
s
-
v
alid
atio
n
to
m
ea
s
u
r
e
m
o
d
el
r
o
b
u
s
tn
ess
an
d
b
en
ch
m
ar
k
in
g
it
ag
ai
n
s
t
b
o
th
tr
ad
itio
n
al
an
d
alter
n
ativ
e
m
ac
h
in
e
lear
n
in
g
m
eth
o
d
s
to
v
alid
ate
its
ef
f
ec
tiv
en
ess
.
As
illu
s
tr
ated
in
Fig
u
r
e
2
,
th
is
p
ip
elin
e
e
n
s
u
r
e
s
a
s
tr
u
ctu
r
ed
a
n
d
ef
f
icien
t
wo
r
k
f
lo
w.
T
o
o
ls
s
u
ch
as
Py
th
o
n
'
s
s
cik
it
-
lear
n
,
XGBo
o
s
t,
an
d
Op
tu
n
a
wer
e
in
teg
r
ated
in
to
a
clo
u
d
-
b
ased
J
u
p
y
ter
en
v
ir
o
n
m
en
t,
en
ab
lin
g
r
ep
r
o
d
u
cib
ilit
y
,
c
o
llab
o
r
ativ
e
d
ev
elo
p
m
en
t,
an
d
s
ca
lab
ilit
y
f
o
r
f
u
tu
r
e
e
n
h
an
ce
m
en
ts
an
d
d
ep
lo
y
m
en
t
in
r
ea
l
-
wo
r
ld
a
p
p
licatio
n
s
.
Fig
u
r
e
2
.
Mo
d
el
d
ev
el
o
p
m
e
n
t
p
r
o
ce
s
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
A
n
A
I
-
d
r
iven
fr
a
mewo
r
k
fo
r
ef
ficien
t a
n
d
a
cc
u
r
a
te
ca
lib
r
a
tio
n
o
f e
lectricity m
eters
u
s
in
g
…
(
R
o
s
a
lin
a
)
159
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
3
.
1
.
T
im
e
e
f
f
iciency
T
h
e
in
teg
r
atio
n
o
f
AI
in
th
e
ca
lib
r
atio
n
test
in
g
o
f
elec
tr
ici
ty
m
eter
s
h
as
d
e
m
o
n
s
tr
ated
s
ig
n
if
ican
t
im
p
r
o
v
em
e
n
ts
in
tim
e
ef
f
icien
cy
,
alig
n
in
g
d
ir
ec
tly
with
th
e
g
o
al
o
f
cr
ea
tin
g
a
m
o
r
e
ef
f
icien
t
an
d
lo
w
-
co
s
t
p
r
o
ce
s
s
f
o
r
m
eter
m
a
n
u
f
ac
t
u
r
in
g
.
T
r
ad
itio
n
al
ca
lib
r
atio
n
m
eth
o
d
s
,
wh
ich
r
ely
h
ea
v
ily
o
n
m
an
u
al
in
p
u
t
an
d
o
p
er
ato
r
j
u
d
g
m
en
t,
ar
e
o
f
ten
t
im
e
-
co
n
s
u
m
in
g
an
d
p
r
o
n
e
to
h
u
m
an
e
r
r
o
r
.
T
h
ese
ch
allen
g
e
s
ar
e
allev
iated
b
y
AI
s
o
lu
tio
n
s
,
wh
ich
au
t
o
m
ate
ca
lib
r
atio
n
p
r
o
ce
s
s
es with
g
r
ea
ter
p
r
ec
is
io
n
an
d
s
p
ee
d
.
T
ab
le
2
s
h
o
ws
th
e
s
ig
n
if
ican
t
im
p
r
o
v
em
en
t
in
tim
e
ef
f
ici
en
cy
wh
e
n
u
s
in
g
AI
-
d
r
iv
e
n
ca
lib
r
atio
n
m
eth
o
d
s
co
m
p
a
r
ed
to
tr
ad
itio
n
al
m
eth
o
d
s
in
elec
tr
icity
m
eter
m
an
u
f
ac
tu
r
i
n
g
.
T
h
e
tab
le
h
ig
h
lig
h
ts
th
e
tim
e
r
eq
u
ir
ed
f
o
r
ca
lib
r
atin
g
o
n
e
m
eter
an
d
th
e
t
o
tal
tim
e
f
o
r
1
0
0
m
eter
s
u
n
d
er
b
o
th
m
eth
o
d
s
.
I
n
t
h
e
tr
ad
itio
n
al
m
eth
o
d
,
it
tak
es
2
0
m
in
u
tes
p
er
m
eter
f
o
r
ca
lib
r
atio
n
,
lea
d
in
g
to
a
to
tal
o
f
2
,
0
0
0
m
in
u
tes
f
o
r
1
0
0
m
eter
s
.
T
h
is
p
r
o
ce
s
s
r
elies
h
ea
v
ily
o
n
m
an
u
al
in
p
u
t
an
d
o
p
er
ato
r
ju
d
g
m
en
t,
wh
ich
ca
n
b
e
s
lo
w
an
d
p
r
o
n
e
to
er
r
o
r
s
.
T
h
e
tim
e
r
eq
u
ir
ed
f
o
r
ca
lib
r
atio
n
is
th
u
s
r
elativ
ely
h
ig
h
,
r
esu
ltin
g
in
in
cr
ea
s
ed
p
r
o
d
u
ctio
n
c
o
s
ts
an
d
d
elay
s
.
I
n
co
n
tr
ast,
th
e
AI
-
d
r
i
v
en
m
eth
o
d
r
ed
u
ce
s
th
e
tim
e
p
er
m
eter
t
o
ju
s
t 1
0
m
in
u
tes,
cu
ttin
g
t
h
e
to
tal
ca
lib
r
atio
n
tim
e
f
o
r
1
0
0
m
eter
s
d
o
wn
to
1
,
0
0
0
m
in
u
tes.
AI
s
o
lu
tio
n
s
au
to
m
ate
th
e
ca
lib
r
atio
n
p
r
o
ce
s
s
,
m
in
im
izin
g
h
u
m
a
n
in
ter
v
en
tio
n
,
w
h
ich
r
esu
lts
in
f
aster
,
m
o
r
e
co
n
s
is
ten
t,
an
d
ac
cu
r
ate
o
u
tc
o
m
es.
T
h
e
u
s
e
o
f
AI
n
o
t
o
n
ly
im
p
r
o
v
es
p
r
ec
is
io
n
b
u
t
also
s
ig
n
if
ican
tly
s
p
ee
d
s
u
p
th
e
p
r
o
ce
s
s
,
r
ed
u
cin
g
th
e
o
v
er
all
tim
e
s
p
en
t
o
n
ca
lib
r
atio
n
.
T
h
e
tim
e
s
av
in
g
s
o
f
5
0
%
b
etwe
en
t
h
e
two
m
eth
o
d
s
d
em
o
n
s
tr
ates
th
e
p
o
te
n
tial
f
o
r
s
u
b
s
tan
tial
ef
f
icien
cy
g
ain
s
.
B
y
in
te
g
r
atin
g
AI
in
to
ca
lib
r
atio
n
test
in
g
,
elec
tr
icity
m
eter
m
an
u
f
ac
tu
r
er
s
ca
n
r
e
d
u
ce
tim
e
s
p
en
t
o
n
ea
ch
ca
lib
r
atio
n
c
y
c
le,
lead
in
g
t
o
f
aster
p
r
o
d
u
cti
o
n
,
lo
wer
lab
o
r
co
s
ts
,
an
d
a
m
o
r
e
co
s
t
-
ef
f
ec
tiv
e
m
an
u
f
ac
tu
r
in
g
p
r
o
ce
s
s
.
T
ab
le
2
.
C
o
m
p
a
r
is
o
n
o
f
tim
e
e
f
f
icien
cy
in
ca
lib
r
atio
n
m
et
h
o
d
s
C
a
l
i
b
r
a
t
i
o
n
m
e
t
h
o
d
Ti
me
p
e
r
m
e
t
e
r
(
m
i
n
u
t
e
s)
Ti
me
f
o
r
1
0
0
m
e
t
e
r
s (
m
i
n
u
t
e
s)
Ti
me
s
a
v
i
n
g
s (%)
Tr
a
d
i
t
i
o
n
a
l
m
e
t
h
o
d
20
2
,
0
0
0
-
AI
-
d
r
i
v
e
n
m
e
t
h
o
d
10
1
,
0
0
0
50
3
.
2
.
Acc
ura
cy
T
h
e
ad
o
p
tio
n
o
f
AI
in
ca
lib
r
atio
n
test
in
g
h
as
led
to
s
u
b
s
t
an
tial
g
ain
s
in
b
o
th
tim
e
ef
f
icien
cy
an
d
ac
cu
r
ac
y
.
Un
lik
e
m
an
u
al
ap
p
r
o
ac
h
es,
wh
ich
ar
e
o
f
ten
p
r
o
n
e
to
v
ar
iab
ilit
y
an
d
h
u
m
a
n
er
r
o
r
,
th
e
AI
-
b
ased
s
y
s
tem
d
em
o
n
s
tr
ated
g
r
ea
ter
co
n
s
is
ten
cy
in
d
etec
tin
g
ca
lib
r
atio
n
d
e
v
iatio
n
s
.
T
h
is
im
p
r
o
v
ed
p
r
ec
is
io
n
r
esu
lts
in
m
o
r
e
d
ep
en
d
ab
le
o
u
tco
m
e
s
,
u
ltima
tely
en
h
an
ci
n
g
th
e
r
eliab
ilit
y
o
f
th
e
o
v
er
all
p
r
o
c
ess
.
T
o
ass
ess
th
e
s
y
s
tem
’
s
p
er
f
o
r
m
an
c
e,
k
e
y
ev
alu
atio
n
m
etr
ics
—
R
MSE
an
d
MA
E
—
wer
e
em
p
lo
y
ed
,
with
th
e
r
esu
lts
illu
s
tr
ated
in
Fig
u
r
es
3
a
n
d
4
.
T
h
ese
m
etr
ics
p
r
o
v
id
e
a
clea
r
in
d
icatio
n
o
f
th
e
m
o
d
el’
s
ac
c
u
r
ac
y
ac
r
o
s
s
v
a
r
io
u
s
test
in
g
s
ce
n
ar
io
s
.
Fig
u
r
e
3
.
R
SME
r
esu
lts
o
f
AI
in
th
e
ca
lib
r
atio
n
test
in
g
o
f
ele
ctr
icity
m
eter
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
6
:
154
-
1
6
3
160
Fig
u
r
e
4
.
MA
E
r
esu
lts
o
f
AI
i
n
th
e
ca
lib
r
atio
n
test
in
g
o
f
ele
ctr
icity
m
eter
s
F
i
g
u
r
e
3
i
l
lu
s
t
r
a
t
e
s
a
c
o
m
p
ar
a
t
i
v
e
a
n
a
ly
s
i
s
o
f
R
M
S
E
v
a
l
u
e
s
b
e
t
w
ee
n
t
h
e
A
I
-
d
r
i
v
en
a
n
d
t
r
ad
i
t
i
o
n
a
l
c
a
l
i
b
r
a
t
io
n
m
e
t
h
o
d
s
a
cr
o
s
s
m
u
l
t
i
p
le
t
e
s
t
i
n
g
p
h
a
s
e
s
.
R
MS
E
s
e
r
v
e
s
a
s
a
c
r
u
c
i
a
l
i
n
d
i
ca
t
o
r
o
f
c
a
l
ib
r
a
t
io
n
p
r
e
c
i
s
io
n
,
w
h
er
e
lo
w
e
r
v
a
lu
e
s
d
e
n
o
t
e
g
r
ea
t
e
r
a
c
c
u
r
a
cy
.
T
h
e
A
I
-
b
a
s
e
d
a
p
p
r
o
a
c
h
c
o
n
s
i
s
t
e
n
t
l
y
r
ec
o
r
d
s
R
M
S
E
v
a
l
u
e
s
a
s
l
o
w
a
s
0
.
0
0
1
i
n
m
o
s
t
p
h
a
s
e
s
,
i
n
d
i
c
a
t
in
g
m
in
i
m
a
l
d
e
v
i
a
t
io
n
f
r
o
m
a
c
t
u
a
l
ca
l
ib
r
a
t
io
n
v
a
l
u
e
s
.
I
n
c
o
n
tr
a
s
t
,
th
e
t
r
a
d
i
t
io
n
a
l
m
e
th
o
d
y
i
e
l
d
s
h
i
g
h
er
R
M
S
E
v
a
lu
es
—
s
u
c
h
a
s
0
.
0
0
7
a
n
d
0
.
0
0
8
—
s
u
g
g
e
s
t
i
n
g
g
r
e
at
e
r
v
a
r
i
ab
i
l
i
t
y
an
d
r
e
d
u
c
e
d
a
cc
u
r
a
c
y
i
n
t
h
e
ca
l
i
b
r
a
t
i
o
n
r
e
s
u
l
t
s
.
W
h
a
t
s
t
a
n
d
s
o
u
t
i
n
F
i
g
u
r
e
3
i
s
th
e
c
o
n
s
i
s
t
e
n
cy
o
f
t
h
e
AI
m
o
d
e
l
i
n
m
a
in
t
a
in
i
n
g
l
o
w
-
e
r
r
o
r
p
r
ed
i
c
t
io
n
s
a
c
r
o
s
s
d
iv
e
r
s
e
t
e
s
t
i
n
g
c
o
n
d
i
t
io
n
s
.
T
h
e
s
e
n
e
ar
-
ze
r
o
R
M
S
E
v
a
l
u
e
s
n
o
t
o
n
ly
v
a
l
i
d
a
t
e
t
h
e
m
o
d
e
l’
s
h
i
g
h
p
r
ed
i
c
t
iv
e
a
cc
u
r
a
c
y
b
u
t
a
l
s
o
d
e
m
o
n
s
t
r
a
t
e
i
t
s
c
a
p
ac
i
t
y
t
o
g
e
n
er
a
l
i
z
e
ef
f
e
c
t
iv
e
ly
ac
r
o
s
s
v
ar
y
in
g
s
c
en
a
r
io
s
.
T
h
i
s
r
e
in
f
o
r
ce
s
th
e
p
o
t
e
n
t
i
a
l
o
f
t
h
e
p
r
o
p
o
s
e
d
X
G
B
o
o
s
t
-
b
a
s
e
d
in
t
e
l
l
ig
e
n
t
c
a
l
ib
r
a
t
io
n
s
y
s
t
e
m
f
o
r
r
e
l
ia
b
l
e
d
ep
l
o
y
m
en
t
i
n
r
e
a
l
-
wo
r
ld
m
a
n
u
f
a
c
tu
r
in
g
e
n
v
i
r
o
n
m
en
t
s
.
T
h
e
o
b
s
e
r
v
e
d
d
i
s
p
a
r
i
t
y
i
n
R
M
S
E
u
n
d
e
r
s
c
o
r
e
s
t
h
e
c
l
e
a
r
a
d
v
a
n
t
a
g
e
o
f
A
I
i
n
m
a
n
a
g
i
n
g
c
a
l
i
b
r
a
t
i
o
n
t
a
s
k
s
.
B
y
l
e
v
e
r
a
g
i
n
g
l
a
r
g
e
d
a
t
a
s
e
t
s
a
n
d
a
d
v
a
n
c
e
d
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
m
s
,
t
h
e
A
I
-
d
r
i
v
e
n
m
e
t
h
o
d
m
i
n
i
m
i
z
e
s
h
u
m
a
n
i
n
t
e
r
v
e
n
t
i
o
n
a
n
d
t
h
e
i
n
c
o
n
s
i
s
t
e
n
c
i
e
s
t
h
a
t
o
f
t
e
n
a
c
c
o
m
p
a
n
y
m
a
n
u
a
l
p
r
o
c
e
s
s
e
s
.
T
r
a
d
i
t
i
o
n
a
l
m
e
t
h
o
d
s
,
w
h
i
c
h
r
e
l
y
h
e
a
v
i
l
y
o
n
o
p
e
r
a
t
o
r
e
x
p
e
r
t
i
s
e
a
n
d
m
a
n
u
a
l
a
d
j
u
s
t
m
e
n
t
s
,
a
r
e
i
n
h
e
r
e
n
t
l
y
m
o
r
e
s
u
s
c
e
p
t
i
b
l
e
t
o
e
r
r
o
r
.
T
h
e
r
e
f
o
r
e
,
t
h
e
c
o
n
s
i
s
t
e
n
t
l
y
l
o
w
e
r
R
M
S
E
v
a
l
u
e
s
a
c
h
i
e
v
e
d
b
y
t
h
e
A
I
s
y
s
t
e
m
h
i
g
h
l
i
g
h
t
i
t
s
r
e
l
i
a
b
i
l
i
t
y
a
n
d
p
r
e
c
i
s
i
o
n
—
k
e
y
a
t
t
r
i
b
u
t
e
s
f
o
r
e
n
h
a
n
c
i
n
g
p
r
o
d
u
c
t
i
v
i
t
y
a
n
d
r
e
d
u
c
i
n
g
e
r
r
o
r
s
i
n
e
l
e
c
t
r
i
c
i
t
y
m
e
t
e
r
m
a
n
u
f
a
c
t
u
r
i
n
g
.
F
i
g
u
r
e
4
i
l
l
u
s
t
r
a
t
e
s
t
h
e
M
AE
o
b
s
e
r
v
ed
i
n
b
o
t
h
AI
-
b
a
s
ed
a
n
d
c
o
n
v
en
t
i
o
n
a
l
c
a
l
ib
r
a
t
io
n
m
e
th
o
d
s
a
c
r
o
s
s
m
u
l
t
i
p
le
t
e
s
t
i
n
g
p
h
a
s
e
s
.
A
s
a
k
e
y
i
n
d
i
c
a
to
r
o
f
p
r
e
d
i
c
t
iv
e
a
c
c
u
r
a
cy
,
M
AE
r
ef
l
e
c
t
s
t
h
e
av
e
r
ag
e
a
b
s
o
l
u
te
d
if
f
er
e
n
c
e
b
e
t
w
e
e
n
p
r
ed
i
c
t
ed
a
n
d
ac
t
u
a
l
v
a
lu
e
s
—
w
h
e
r
e
s
m
a
l
l
e
r
v
a
l
u
e
s
i
n
d
ic
a
t
e
m
o
r
e
p
r
ec
i
s
e
c
a
l
i
b
r
a
t
io
n
.
T
h
e
AI
-
b
a
s
e
d
a
p
p
r
o
a
c
h
co
n
s
i
s
t
e
n
t
ly
d
em
o
n
s
t
r
a
t
e
s
lo
w
e
r
M
A
E
f
ig
u
r
e
s
,
wi
t
h
v
a
l
u
e
s
s
u
ch
a
s
0
.
0
0
0
3
8
an
d
0
.
0
0
0
5
2
,
s
ig
n
if
y
i
n
g
a
h
ig
h
l
ev
e
l
o
f
ac
c
u
r
a
c
y
an
d
m
in
i
m
a
l
d
e
v
i
at
i
o
n
.
I
n
c
o
n
t
r
a
s
t
,
th
e
t
r
a
d
i
t
io
n
a
l
m
e
th
o
d
r
e
co
r
d
s
h
ig
h
er
e
r
r
o
r
r
a
te
s
,
i
n
c
l
u
d
i
n
g
0
.
0
0
3
2
9
a
n
d
0
.
0
0
1
3
4
,
s
u
g
g
e
s
t
in
g
l
e
s
s
co
n
s
i
s
t
e
n
t
p
e
r
f
o
r
m
a
n
c
e
a
n
d
a
g
r
ea
t
e
r
m
a
r
g
in
f
o
r
d
ev
i
a
t
io
n
.
T
h
e
s
e
r
e
s
u
l
t
s
h
i
g
h
l
i
g
h
t
th
e
l
i
m
it
a
t
i
o
n
s
o
f
m
a
n
u
a
l
c
a
l
i
b
r
a
t
io
n
,
w
h
ic
h
i
s
o
f
t
e
n
s
u
b
j
e
c
t
to
i
n
co
n
s
i
s
t
en
c
i
e
s
s
t
e
m
m
i
n
g
f
r
o
m
h
u
m
a
n
e
r
r
o
r
a
n
d
p
r
o
c
ed
u
r
a
l
v
a
r
i
ab
i
l
i
t
y
.
T
h
e
s
u
p
e
r
io
r
p
r
e
c
is
i
o
n
o
f
th
e
A
I
-
d
r
i
v
en
s
y
s
t
em
u
n
d
e
r
s
c
o
r
e
s
i
t
s
r
e
l
i
a
b
i
l
i
ty
,
u
l
t
im
a
t
e
l
y
s
u
p
p
o
r
t
i
n
g
i
m
p
r
o
v
ed
m
e
t
e
r
q
u
a
l
i
t
y
a
n
d
p
r
o
d
u
c
t
io
n
e
f
f
ic
i
e
n
cy
.
M
e
a
n
w
h
i
le
,
T
ab
l
e
3
c
o
m
p
a
r
es
v
a
r
i
o
u
s
a
l
g
o
r
i
th
m
i
c
c
o
n
f
ig
u
r
a
t
io
n
s
f
o
r
Ne
u
t
r
a
l
I
M
A
X
(
0
.
5
L
)
t
e
s
t
p
o
i
n
t
.
S
e
v
er
a
l
X
G
B
o
o
s
t
m
o
d
e
l
s
w
e
r
e
t
e
s
t
e
d
,
i
n
co
r
p
o
r
a
t
i
n
g
t
u
n
i
n
g
s
t
r
a
t
eg
i
e
s
l
i
k
e
G
r
i
d
S
e
ar
c
h
C
V
,
R
a
n
d
o
m
i
z
e
d
S
ea
r
ch
C
V
,
a
n
d
B
a
y
e
s
S
e
a
r
ch
C
V
w
i
t
h
in
p
ip
e
l
i
n
e
s
t
r
u
c
tu
r
e
s
.
T
h
e
p
r
o
p
o
s
e
d
m
o
d
e
l,
i
n
co
r
p
o
r
a
t
i
n
g
o
p
t
i
m
iz
e
d
p
a
r
am
e
t
e
r
s
,
em
e
r
g
e
d
a
s
m
o
s
t
e
f
f
ec
t
i
v
e
—
a
ch
ie
v
i
n
g
l
o
w
e
s
t
R
M
S
E
o
f
0
.
0
0
5
a
n
d
n
e
ar
-
p
e
r
f
e
c
t
a
c
c
u
r
a
c
y
s
c
o
r
e
s
(
9
9
.
9
2
6
%
f
o
r
tr
a
i
n
in
g
an
d
9
9
.
9
3
5
%
f
o
r
te
s
t
i
n
g
)
.
W
h
i
le
i
t
s
t
r
a
in
i
n
g
t
im
e
w
a
s
r
e
la
t
i
v
e
ly
l
o
n
g
e
r
at
2
0
1
.
2
s
e
co
n
d
s
,
th
e
p
r
ed
i
c
t
io
n
t
im
e
r
e
m
a
in
e
d
r
a
p
id
a
t
0
.
0
1
2
s
e
co
n
d
s
,
d
e
m
o
n
s
t
r
a
t
i
n
g
b
o
th
p
e
r
f
o
r
m
a
n
c
e
an
d
e
f
f
i
c
i
e
n
c
y
.
3
.
3
.
Co
s
t
-
e
f
f
ec
t
iv
eness
A
l
t
h
o
u
g
h
t
h
e
i
n
i
t
ia
l
i
n
v
e
s
tm
e
n
t
in
th
e
AI
-
b
a
s
e
d
c
a
l
i
b
r
a
t
i
o
n
s
y
s
t
e
m
w
a
s
h
i
g
h
e
r
th
a
n
t
h
a
t
o
f
c
o
n
v
e
n
t
io
n
a
l
m
e
t
h
o
d
s
,
t
h
e
lo
n
g
-
te
r
m
f
in
an
c
i
a
l
b
en
e
f
i
t
s
we
r
e
s
u
b
s
t
an
t
i
a
l
.
T
h
e
s
y
s
t
em
r
e
q
u
ir
e
d
an
u
p
f
r
o
n
t
c
o
s
t
o
f
ap
p
r
o
x
i
m
a
t
e
ly
$
1
5
,
0
0
0
,
co
v
er
i
n
g
h
ar
d
w
ar
e
i
n
te
g
r
a
t
i
o
n
,
s
o
f
t
wa
r
e
d
e
p
lo
y
m
e
n
t
,
a
n
d
s
t
a
f
f
tr
a
i
n
in
g
.
H
o
w
e
v
er
,
t
h
e
s
e
ex
p
en
s
e
s
w
er
e
o
f
f
s
e
t
b
y
r
e
cu
r
r
i
n
g
s
av
i
n
g
s
i
n
o
p
er
a
t
io
n
a
l
ar
e
a
s
.
S
p
e
c
if
i
ca
l
l
y
,
t
h
e
r
e
d
u
c
t
i
o
n
i
n
m
a
n
u
a
l
l
ab
o
r
f
r
o
m
$
5
0
0
t
o
$
2
0
0
p
e
r
d
ay
,
co
m
b
in
ed
w
i
t
h
f
e
w
er
d
ef
e
c
t
s
a
n
d
l
e
s
s
r
e
w
o
r
k
,
g
e
n
e
r
a
t
ed
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
A
n
A
I
-
d
r
iven
fr
a
mewo
r
k
fo
r
ef
ficien
t a
n
d
a
cc
u
r
a
te
ca
lib
r
a
tio
n
o
f e
lectricity m
eters
u
s
in
g
…
(
R
o
s
a
lin
a
)
161
a
v
e
r
ag
e
s
a
v
in
g
s
o
f
$
2
,
5
0
0
p
er
p
r
o
d
u
c
t
i
o
n
b
a
t
ch
.
T
h
e
e
f
f
ic
ie
n
c
y
g
a
i
n
s
w
e
r
e
eq
u
a
l
ly
s
i
g
n
i
f
i
c
a
n
t.
Pr
o
c
e
s
s
i
n
g
t
i
m
e
p
e
r
m
e
t
er
w
a
s
r
ed
u
c
ed
f
r
o
m
2
0
to
1
0
m
i
n
u
t
e
s
,
w
h
i
l
e
c
a
l
i
b
r
a
t
io
n
a
c
cu
r
a
c
y
i
m
p
r
o
v
ed
f
r
o
m
a
3
.
5
%
er
r
o
r
r
a
t
e
t
o
0
.
8
%
i
n
T
ab
l
e
4
.
T
h
e
s
e
i
m
p
r
o
v
em
e
n
t
s
r
e
d
u
c
ed
b
o
th
l
ab
o
r
i
n
t
en
s
i
t
y
an
d
m
a
t
e
r
i
a
l
w
a
s
t
ag
e
,
c
o
n
tr
i
b
u
t
i
n
g
t
o
l
o
w
er
o
v
e
r
a
ll
m
a
n
u
f
a
c
tu
r
in
g
co
s
t
s
.
T
h
e
r
e
t
u
r
n
o
n
i
n
v
e
s
t
m
en
t
(
R
O
I
)
w
a
s
c
a
l
c
u
l
a
t
ed
b
y
c
o
m
p
a
r
in
g
th
e
n
e
t
s
av
i
n
g
s
a
c
h
i
e
v
e
d
w
i
th
i
n
th
e
f
ir
s
t
s
i
x
m
o
n
t
h
s
o
f
d
ep
l
o
y
m
en
t
a
g
a
i
n
s
t
th
e
i
n
i
t
i
a
l
i
m
p
l
e
m
e
n
t
a
t
io
n
co
s
t
.
W
i
t
h
cu
m
u
la
t
i
v
e
s
av
i
n
g
s
o
f
ap
p
r
o
x
i
m
a
t
e
l
y
$
2
2
,
5
0
0
o
v
e
r
th
i
s
p
e
r
i
o
d
,
t
h
e
s
y
s
t
e
m
a
c
h
i
ev
e
d
a
n
R
O
I
o
f
1
5
0
%
.
T
h
i
s
r
e
s
u
l
t
h
ig
h
l
ig
h
t
s
n
o
t
o
n
ly
t
h
e
ec
o
n
o
m
ic
f
ea
s
i
b
i
l
i
t
y
b
u
t
a
l
s
o
t
h
e
p
r
a
c
t
i
ca
l
v
a
l
u
e
o
f
i
n
te
g
r
a
t
i
n
g
A
I
i
n
to
th
e
c
a
l
i
b
r
a
t
i
o
n
p
r
o
c
e
s
s
.
T
ab
le
3
.
C
o
m
p
a
r
is
o
n
o
f
m
o
d
el
p
er
f
o
r
m
an
ce
o
n
N
eu
tr
al
a
n
d
I
MA
X
(
0
5
L
)
Te
st
p
o
i
n
t
M
o
d
e
l
R
M
S
E
A
c
c
u
r
a
c
y
(
t
r
a
i
n
)
A
c
c
u
r
a
c
y
(
t
e
st
)
Tr
a
i
n
t
i
me
(
s)
P
r
e
d
i
c
t
i
o
n
t
i
m
e
(
s)
N
e
u
t
r
a
l
X
G
B
o
o
st
0
.
0
6
2
9
9
.
9
0
2
9
0
.
1
9
1
1
6
2
.
7
0
.
0
2
9
I
M
A
X
G
r
i
d
S
e
a
r
c
h
C
V
w
i
t
h
(
0
5
L)
P
a
r
a
me
t
e
r
X
G
B
o
o
st
0
.
0
6
2
9
9
.
9
0
2
9
0
.
1
9
1
1
4
3
.
2
0
.
0
3
2
G
r
i
d
S
e
a
r
c
h
C
V
w
i
t
h
P
i
p
e
l
i
n
e
X
G
B
o
o
st
0
.
1
5
9
3
2
.
3
5
1
3
6
.
7
2
0
2
6
.
3
0
.
0
0
7
R
a
n
d
o
m
i
z
e
d
S
e
a
r
c
h
C
V
X
G
B
_
p
a
r
a
ms
w
i
t
h
P
i
p
e
l
i
n
e
X
G
B
o
o
st
0
.
1
4
1
4
8
.
1
8
0
5
0
.
1
7
2
9
.
1
0
.
0
0
7
R
a
n
d
o
m
i
z
e
d
S
e
a
r
c
h
C
V
S
V
M
_
p
a
r
a
ms w
i
t
h
P
i
p
e
l
i
n
e
X
G
B
o
o
st
0
.
1
4
5
4
6
.
2
4
4
4
6
.
9
3
2
1
5
8
.
5
0
.
0
0
5
B
a
y
e
sS
e
a
r
c
h
C
V
X
G
B
_
p
a
r
a
ms
w
i
t
h
P
i
p
e
l
i
n
e
X
G
B
o
o
st
N
o
0
.
1
3
6
5
2
.
7
3
6
5
3
.
6
3
9
0
.
1
0
.
0
0
5
P
a
r
a
me
t
e
r
P
r
o
p
o
se
d
m
o
d
e
l
0
.
0
0
5
9
9
.
9
2
6
9
9
.
9
3
5
2
0
1
.
2
0
.
0
1
2
T
ab
le
4
.
C
o
m
p
a
r
is
o
n
o
f
co
s
t
-
e
f
f
ec
tiv
en
ess
b
etwe
en
tr
ad
itio
n
al
an
d
AI
-
d
r
iv
en
ca
lib
r
atio
n
m
eth
o
d
s
C
r
i
t
e
r
i
a
Tr
a
d
i
t
i
o
n
a
l
m
e
t
h
o
d
AI
-
i
mp
l
e
me
n
t
e
d
m
e
t
h
o
d
I
mp
r
o
v
e
m
e
n
t
Ti
me
(
mi
n
u
t
e
s
p
e
r
me
t
e
r
)
2
0
mi
n
u
t
e
s
1
0
mi
n
u
t
e
s
5
0
%
r
e
d
u
c
t
i
o
n
C
a
l
i
b
r
a
t
i
o
n
a
c
c
u
r
a
c
y
(
R
M
S
E)
3
.
5
%
e
r
r
o
r
r
a
t
e
0
.
8
%
e
r
r
o
r
r
a
t
e
7
7
%
i
mp
r
o
v
e
me
n
t
La
b
o
r
c
o
s
t
s (
p
e
r
d
a
y
)
$
5
0
0
$
2
0
0
6
0
%
r
e
d
u
c
t
i
o
n
O
v
e
r
a
l
l
c
o
st
(
p
e
r
b
a
t
c
h
)
$
5
,
0
0
0
$
2
,
5
0
0
5
0
%
r
e
d
u
c
t
i
o
n
R
O
I
-
1
5
0
%
i
n
6
m
o
n
t
h
s
-
4.
CO
NCLU
SI
O
N
T
h
i
s
s
t
u
d
y
p
r
o
p
o
s
ed
a
n
AI
-
d
r
i
v
e
n
ca
l
i
b
r
a
t
i
o
n
t
e
s
t
i
n
g
a
p
p
r
o
a
c
h
f
o
r
e
le
c
t
r
i
c
i
ty
m
e
te
r
m
a
n
u
f
a
c
tu
r
in
g
,
l
e
v
e
r
ag
i
n
g
X
G
B
o
o
s
t
w
i
th
P
S
O
-
b
a
s
e
d
h
y
p
e
r
p
ar
a
m
e
t
er
t
u
n
in
g
.
T
h
e
m
e
t
h
o
d
d
e
m
o
n
s
t
r
a
ted
s
i
g
n
if
i
c
a
n
t
g
a
in
s
i
n
p
r
ed
i
c
t
i
v
e
ac
c
u
r
a
cy
(
l
o
w
er
R
M
S
E
)
,
r
e
d
u
c
ed
te
s
t
i
n
g
t
im
e
,
a
n
d
e
n
h
a
n
ce
d
c
o
s
t
-
e
f
f
i
c
ie
n
c
y
co
m
p
a
r
ed
to
t
r
a
d
i
t
io
n
a
l
m
a
n
u
a
l
c
a
l
i
b
r
a
t
i
o
n
.
A
r
ig
o
r
o
u
s
p
i
p
e
l
in
e
—
i
n
co
r
p
o
r
a
t
in
g
d
a
t
a
p
r
e
p
r
o
c
e
s
s
i
n
g
,
f
ea
t
u
r
e
en
g
in
e
e
r
in
g
,
a
n
d
s
y
s
t
e
m
a
t
ic
ev
a
l
u
a
t
i
o
n
—
p
r
o
v
e
d
e
s
s
e
n
t
i
a
l
i
n
m
ax
i
m
i
z
in
g
m
o
d
e
l
p
er
f
o
r
m
an
c
e
.
E
x
p
e
r
i
m
e
n
t
a
l
c
o
m
p
a
r
i
s
o
n
s
f
u
r
th
e
r
u
n
d
e
r
s
c
o
r
e
d
X
G
B
o
o
s
t
’
s
s
u
p
er
i
o
r
i
t
y
.
W
h
i
l
e
LR
an
d
S
V
R
e
x
h
i
b
i
t
ed
l
i
m
i
t
ed
c
ap
a
c
i
ty
in
h
a
n
d
l
i
n
g
th
e
co
m
p
le
x
n
o
n
l
in
e
a
r
p
a
t
t
er
n
s
i
n
h
e
r
e
n
t
i
n
ca
l
ib
r
a
t
io
n
d
a
t
a
,
RF
p
e
r
f
o
r
m
ed
b
e
t
t
e
r
b
u
t
s
t
i
l
l
f
e
l
l
s
h
o
r
t
in
b
a
l
an
c
i
n
g
a
c
cu
r
ac
y
w
i
t
h
c
o
m
p
u
ta
t
i
o
n
a
l
e
f
f
i
c
i
en
cy
.
B
y
c
o
n
t
r
a
s
t,
X
G
B
o
o
s
t
w
i
th
P
S
O
c
o
n
s
i
s
t
e
n
t
ly
o
u
t
p
e
r
f
o
r
m
e
d
t
h
e
s
e
a
l
te
r
n
a
t
iv
e
s
,
a
ch
i
e
v
in
g
b
o
th
h
ig
h
ac
c
u
r
ac
y
an
d
s
c
al
a
b
i
l
i
ty
.
B
ey
o
n
d
p
e
r
f
o
r
m
a
n
c
e
m
e
t
r
i
c
s
,
t
h
e
ap
p
r
o
a
ch
y
i
e
ld
ed
t
an
g
ib
l
e
e
c
o
n
o
m
i
c
b
en
e
f
i
ts
,
i
n
c
lu
d
in
g
r
ed
u
c
e
d
l
ab
o
r
co
s
t
s
,
l
o
we
r
d
ef
e
c
t
r
a
t
e
s
,
an
d
a
r
a
p
id
R
O
I
,
e
s
t
a
b
l
i
s
h
i
n
g
i
t
s
p
r
a
c
t
i
c
a
l
v
i
ab
i
l
i
t
y
f
o
r
l
a
r
g
e
-
s
c
a
le
d
e
p
lo
y
m
e
n
t.
C
o
l
l
e
c
t
i
v
e
ly
,
th
e
s
e
f
i
n
d
in
g
s
h
i
g
h
l
i
g
h
t
n
o
t
o
n
l
y
th
e
t
e
c
h
n
i
c
a
l
ef
f
e
c
t
iv
e
n
e
s
s
o
f
th
e
p
r
o
p
o
s
ed
s
o
l
u
t
io
n
b
u
t
a
l
s
o
i
t
s
s
t
r
a
t
e
g
i
c
v
a
l
u
e
i
n
ad
v
an
c
in
g
s
m
a
r
t
f
a
c
t
o
r
y
in
i
t
i
a
t
i
v
e
s
,
o
f
f
e
r
in
g
m
an
u
f
a
c
tu
r
e
r
s
a
r
o
b
u
s
t
an
d
c
o
s
t
-
e
f
f
e
c
ti
v
e
p
a
t
h
wa
y
t
o
w
ar
d
i
n
t
e
l
l
i
g
en
t
au
t
o
m
a
t
i
o
n
.
ACK
NO
WL
E
DG
E
M
E
NT
S
T
h
is
r
esear
ch
was
m
ad
e
p
o
s
s
ib
le
th
r
o
u
g
h
th
e
s
u
p
p
o
r
t
o
f
Un
iv
er
s
itas
Mu
ltime
d
ia
Nu
s
an
tar
a
an
d
Pre
s
id
en
t
Un
iv
er
s
ity
.
T
h
e
a
u
t
h
o
r
s
s
in
ce
r
ely
a
p
p
r
ec
iate
th
e
r
eso
u
r
ce
s
,
ass
is
tan
ce
,
an
d
g
u
id
an
ce
p
r
o
v
id
e
d
b
y
th
ese
in
s
titu
tio
n
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
6
:
154
-
1
6
3
162
F
UNDING
I
NF
O
R
M
A
T
I
O
N
T
h
is
wo
r
k
was f
u
n
d
e
d
b
y
Pre
s
id
en
t U
n
iv
er
s
ity
an
d
U
n
iv
er
s
itas
Mu
ltime
d
ia
Nu
s
an
tar
a
as p
ar
t o
f
th
eir
in
s
titu
tio
n
al
r
esear
ch
s
u
p
p
o
r
t
p
r
o
g
r
am
,
wh
ic
h
p
r
o
v
id
e
d
f
in
an
cial
ass
is
tan
ce
,
ac
ad
em
ic
s
u
p
er
v
is
io
n
,
a
n
d
r
esear
ch
in
f
r
astru
ctu
r
e
n
ec
ess
ar
y
f
o
r
th
e
co
m
p
letio
n
o
f
th
is
s
tu
d
y
.
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
R
o
s
alin
a
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Nu
n
ik
Af
r
ilian
a
✓
✓
✓
✓
✓
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.
I
NF
O
RM
E
D
CO
NS
E
N
T
W
e
h
av
e
o
b
tain
ed
in
f
o
r
m
ed
c
o
n
s
en
t f
r
o
m
all
in
d
iv
id
u
als in
c
lu
d
ed
in
t
h
is
s
tu
d
y
.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
ata
th
at
s
u
p
p
o
r
t
th
e
f
in
d
in
g
s
o
f
th
is
s
tu
d
y
ar
e
av
ailab
le
f
r
o
m
th
e
co
r
r
esp
o
n
d
in
g
a
u
th
o
r
,
[
R
]
,
u
p
o
n
r
ea
s
o
n
ab
le
r
eq
u
est.
RE
F
E
R
E
NC
E
S
[
1
]
M
.
H
.
Z
a
f
a
r
e
t
a
l
.
,
“
S
t
e
p
t
o
w
a
r
d
s
se
c
u
r
e
a
n
d
r
e
l
i
a
b
l
e
smar
t
g
r
i
d
s
i
n
I
n
d
u
s
t
r
y
5
.
0
:
a
f
e
d
e
r
a
t
e
d
l
e
a
r
n
i
n
g
a
ssi
s
t
e
d
h
y
b
r
i
d
d
e
e
p
l
e
a
r
n
i
n
g
mo
d
e
l
f
o
r
e
l
e
c
t
r
i
c
i
t
y
t
h
e
f
t
d
e
t
e
c
t
i
o
n
u
s
i
n
g
sm
a
r
t
m
e
t
e
r
s
,
”
E
n
e
rg
y
R
e
p
o
r
t
s
,
v
o
l
.
1
0
,
p
p
.
3
0
0
1
–
3
0
1
9
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
g
y
r
.
2
0
2
3
.
0
9
.
1
0
0
.
[
2
]
N
.
A
f
r
i
l
i
a
n
a
,
D
.
K
r
ó
l
,
a
n
d
F
.
L
.
G
a
o
l
,
“
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
t
e
c
h
n
i
q
u
e
s
f
o
r
a
ssess
i
n
g
d
a
t
a
q
u
a
l
i
t
y
:
t
o
w
a
r
d
s
k
n
o
w
l
e
d
g
e
-
d
r
i
v
e
n
p
r
o
c
e
ss
i
n
g
,
”
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
a
t
i
o
n
a
l
S
c
i
e
n
c
e
,
K
r
a
k
o
w
,
P
o
l
a
n
d
:
S
p
r
i
n
g
e
r
,
2
0
2
1
,
p
p
.
3
9
2
–
4
0
5
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
030
-
7
7
9
6
7
-
2
_
3
3
.
[
3
]
M
.
M
a
h
y
o
u
b
,
S
.
H
.
A
b
d
u
l
h
u
ss
a
i
n
,
F
.
N
a
t
a
l
i
a
,
S
.
S
u
d
i
r
m
a
n
,
a
n
d
B
.
M
.
M
a
h
mm
o
d
,
“
A
b
s
t
r
a
c
t
p
a
t
t
e
r
n
i
ma
g
e
g
e
n
e
r
a
t
i
o
n
u
si
n
g
g
e
n
e
r
a
t
i
v
e
a
d
v
e
r
sar
i
a
l
n
e
t
w
o
r
k
s,
”
i
n
2
0
2
3
1
5
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
D
e
v
e
l
o
p
m
e
n
t
s
i
n
e
S
y
s
t
e
m
s
E
n
g
i
n
e
e
ri
n
g
(
D
e
S
E)
,
2
0
2
3
,
p
p
.
1
7
2
–
1
7
7
,
d
o
i
:
1
0
.
1
1
0
9
/
D
e
S
E5
8
2
7
4
.
2
0
2
3
.
1
0
0
9
9
8
7
1
.
[
4
]
A
.
M
.
S
h
k
e
l
a
n
d
Y
.
W
a
n
g
,
“
S
t
r
a
p
d
o
w
n
i
n
e
r
t
i
a
l
n
a
v
i
g
a
t
i
o
n
me
c
h
a
n
i
sm,
”
Pe
d
e
s
t
ri
a
n
I
n
e
rt
i
a
l
N
a
v
i
g
a
t
i
o
n
w
i
t
h
S
e
l
f
‐
C
o
n
t
a
i
n
e
d
Ai
d
i
n
g
,
J
o
h
n
W
i
l
e
y
& S
o
n
s
,
L
t
d
.
,
2
0
2
1
,
p
p
.
3
7
–
4
6
,
d
o
i
:
1
0
.
1
0
0
2
/
9
7
8
1
1
1
9
6
9
9
9
1
0
.
c
h
3
.
[
5
]
J
.
C
h
e
n
,
F
.
R
.
T
i
a
n
,
S
.
C
.
W
a
n
g
,
B
.
L
i
,
W
.
Z
h
a
n
g
,
a
n
d
S
.
X
.
W
a
n
,
“
S
i
g
n
a
l
i
t
e
r
a
t
i
v
e
s
e
a
r
c
h
m
e
t
h
o
d
b
a
s
e
d
o
n
k
a
l
m
a
n
f
i
l
t
e
r
f
o
r
v
o
r
t
e
x
f
l
o
w
m
e
t
e
r
,
”
I
E
E
E
T
r
a
n
s
a
c
t
i
o
n
s
o
n
I
n
s
t
r
u
m
e
n
t
a
t
i
o
n
a
n
d
M
e
a
s
u
r
e
m
e
n
t
,
v
o
l
.
7
3
,
p
p
.
1
–
1
3
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
T
I
M
.
2
0
2
3
.
3
3
2
8
6
8
7
.
[
6
]
J.
F
.
A
r
i
n
e
z
,
Q
.
C
h
a
n
g
,
R
.
X
.
G
a
o
,
C
.
X
u
,
a
n
d
J.
Zh
a
n
g
,
“
A
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
i
n
a
d
v
a
n
c
e
d
ma
n
u
f
a
c
t
u
r
i
n
g
:
c
u
r
r
e
n
t
s
t
a
t
u
s
a
n
d
f
u
t
u
r
e
o
u
t
l
o
o
k
,
”
J
o
u
r
n
a
l
o
f
M
a
n
u
f
a
c
t
u
ri
n
g
S
c
i
e
n
c
e
a
n
d
En
g
i
n
e
e
ri
n
g
,
T
ra
n
s
a
c
t
i
o
n
s
o
f
t
h
e
A
S
M
E
,
v
o
l
.
1
4
2
,
n
o
.
1
1
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
1
5
/
1
.
4
0
4
7
8
5
5
.
[
7
]
M
.
A
.
Z
a
i
d
a
n
e
t
a
l
.
,
“
I
n
t
e
l
l
i
g
e
n
t
c
a
l
i
b
r
a
t
i
o
n
a
n
d
v
i
r
t
u
a
l
se
n
si
n
g
f
o
r
i
n
t
e
g
r
a
t
e
d
l
o
w
-
c
o
st
a
i
r
q
u
a
l
i
t
y
se
n
so
r
,
”
I
EEE
S
e
n
so
rs
J
o
u
r
n
a
l
,
v
o
l
.
2
0
,
n
o
.
2
2
,
p
p
.
1
3
6
3
8
–
1
3
6
5
2
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
JS
EN
.
2
0
2
0
.
3
0
1
0
3
1
6
.
[
8
]
N
.
M
.
S
.
I
sw
a
r
i
,
N
.
A
f
r
i
l
i
a
n
a
,
E.
M
.
D
h
a
r
ma
,
a
n
d
N
.
P
.
W
.
Y
u
n
i
a
r
i
,
“
E
n
h
a
n
c
i
n
g
a
s
p
e
c
t
-
b
a
se
d
se
n
t
i
me
n
t
a
n
a
l
y
s
i
s
i
n
v
i
s
i
t
o
r
r
e
v
i
e
w
u
si
n
g
sem
a
n
t
i
c
s
i
mi
l
a
r
i
t
y
,
”
J
o
u
rn
a
l
o
f
Ap
p
l
i
e
d
D
a
t
a
S
c
i
e
n
c
e
s
,
v
o
l
.
5
,
n
o
.
2
,
p
p
.
7
2
4
–
7
3
5
,
2
0
2
4
,
d
o
i
:
1
0
.
4
7
7
3
8
/
j
a
d
s.v
5
i
2
.
2
4
9
.
[
9
]
Z.
W
e
n
,
Q
.
L
i
,
B
.
H
e
,
a
n
d
B
.
C
u
i
,
“
C
h
a
l
l
e
n
g
e
s
a
n
d
o
p
p
o
r
t
u
n
i
t
i
e
s
o
f
b
u
i
l
d
i
n
g
f
a
st
G
B
D
T
sy
s
t
e
ms
,
”
i
n
I
J
C
AI
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
i
n
t
C
o
n
f
e
re
n
c
e
o
n
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
2
0
2
1
,
p
p
.
4
6
6
1
–
4
6
6
8
,
d
o
i
:
1
0
.
2
4
9
6
3
/
i
j
c
a
i
.
2
0
2
1
/
6
3
2
.
[
1
0
]
N
.
A
.
K
o
n
k
i
n
,
“
D
e
t
e
r
mi
n
a
t
i
o
n
o
p
t
i
m
a
l
ma
x
i
mu
m
u
s
a
b
l
e
f
r
e
q
u
e
n
c
y
p
r
e
d
i
c
t
i
o
n
p
e
r
i
o
d
s
f
o
r
i
o
n
o
sp
h
e
r
i
c
r
a
d
i
o
c
h
a
n
n
e
l
s
u
s
i
n
g
t
h
e
X
G
B
o
o
st
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
m,”
i
n
2
0
2
3
S
y
st
e
m
s
o
f
S
i
g
n
a
l
s
G
e
n
e
ra
t
i
n
g
a
n
d
Pro
c
e
ss
i
n
g
i
n
t
h
e
Fi
e
l
d
o
f
o
n
B
o
a
r
d
C
o
m
m
u
n
i
c
a
t
i
o
n
s
,
M
o
s
c
o
w
,
R
u
ss
i
a
n
F
e
d
e
r
a
t
i
o
n
:
I
EEE,
2
0
2
3
,
p
p
.
1
–
4
,
d
o
i
:
1
0
.
1
1
0
9
/
I
EEEC
O
N
F
5
6
7
3
7
.
2
0
2
3
.
1
0
0
9
2
1
8
6
.
[
1
1
]
S
.
H
a
k
k
a
l
a
n
d
A
.
A
.
L
a
h
c
e
n
,
“
X
G
B
o
o
st
t
o
e
n
h
a
n
c
e
l
e
a
r
n
e
r
p
e
r
f
o
r
ma
n
c
e
p
r
e
d
i
c
t
i
o
n
,
”
C
o
m
p
u
t
e
rs
a
n
d
E
d
u
c
a
t
i
o
n
:
A
rt
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
7
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
a
e
a
i
.
2
0
2
4
.
1
0
0
2
5
4
.
[
1
2
]
S
.
K
.
K
i
a
n
g
a
l
a
a
n
d
Z
.
W
a
n
g
,
“
A
n
e
f
f
e
c
t
i
v
e
a
d
a
p
t
i
v
e
c
u
st
o
m
i
z
a
t
i
o
n
f
r
a
m
e
w
o
r
k
f
o
r
sm
a
l
l
ma
n
u
f
a
c
t
u
r
i
n
g
p
l
a
n
t
s
u
si
n
g
e
x
t
r
e
me
g
r
a
d
i
e
n
t
b
o
o
s
t
i
n
g
-
X
G
B
o
o
st
a
n
d
r
a
n
d
o
m
f
o
r
e
st
e
n
se
mb
l
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms
i
n
a
n
I
n
d
u
st
r
y
4
.
0
e
n
v
i
r
o
n
me
n
t
,
”
Ma
c
h
i
n
e
L
e
a
r
n
i
n
g
w
i
t
h
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
4
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
m
l
w
a
.
2
0
2
1
.
1
0
0
0
2
4
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
A
n
A
I
-
d
r
iven
fr
a
mewo
r
k
fo
r
ef
ficien
t a
n
d
a
cc
u
r
a
te
ca
lib
r
a
tio
n
o
f e
lectricity m
eters
u
s
in
g
…
(
R
o
s
a
lin
a
)
163
[
1
3
]
Y
.
L
i
u
e
t
a
l
.
,
“
R
e
s
e
a
r
c
h
o
n
t
h
e
p
r
e
d
i
c
t
i
o
n
o
f
g
r
e
e
n
p
l
u
m
a
c
i
d
i
t
y
b
a
s
e
d
o
n
i
m
p
r
o
v
e
d
X
G
B
o
o
st
,
”
S
e
n
so
rs
,
v
o
l
.
2
1
,
n
o
.
3
,
p
p
.
1
–
1
5
,
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
s
2
1
0
3
0
9
3
0
.
[
1
4
]
Z.
F
a
s
k
a
,
L.
K
h
r
i
ss
i
,
K
.
H
a
d
d
o
u
c
h
,
a
n
d
N
.
E
l
A
k
k
a
d
,
“
A
r
o
b
u
st
a
n
d
c
o
n
s
i
st
e
n
t
st
a
c
k
g
e
n
e
r
a
l
i
z
e
d
e
n
sem
b
l
e
-
l
e
a
r
n
i
n
g
f
r
a
mew
o
r
k
f
o
r
i
ma
g
e
s
e
g
me
n
t
a
t
i
o
n
,
”
J
o
u
rn
a
l
o
f
En
g
i
n
e
e
ri
n
g
a
n
d
A
p
p
l
i
e
d
S
c
i
e
n
c
e
,
v
o
l
.
7
0
,
n
o
.
1
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
8
6
/
s
4
4
1
4
7
-
0
2
3
-
0
0
2
2
6
-
4.
[
1
5
]
P
.
A
.
H
.
P
h
a
m
a
n
d
N
.
D
.
H
o
a
n
g
,
“
M
e
t
a
h
e
u
r
i
s
t
i
c
o
p
t
i
m
i
z
a
t
i
o
n
o
f
e
x
t
r
e
me
g
r
a
d
i
e
n
t
b
o
o
st
i
n
g
ma
c
h
i
n
e
f
o
r
e
n
h
a
n
c
e
d
p
r
e
d
i
c
t
i
o
n
o
f
l
a
t
e
r
a
l
s
t
r
e
n
g
t
h
o
f
r
e
i
n
f
o
r
c
e
d
c
o
n
c
r
e
t
e
c
o
l
u
m
n
s
u
n
d
e
r
c
y
c
l
i
c
l
o
a
d
i
n
g
s,”
R
e
s
u
l
t
s
i
n
E
n
g
i
n
e
e
r
i
n
g
,
v
o
l
.
2
4
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
r
i
n
e
n
g
.
2
0
2
4
.
1
0
3
1
2
5
.
[
1
6
]
Y
.
X
i
a
,
S
.
Ji
a
n
g
,
L
.
M
e
n
g
,
a
n
d
X
.
J
u
,
“
X
G
B
o
o
st
-
B
-
G
H
M
:
a
n
e
n
s
e
mb
l
e
mo
d
e
l
w
i
t
h
f
e
a
t
u
r
e
s
e
l
e
c
t
i
o
n
a
n
d
G
H
M
l
o
ss
f
u
n
c
t
i
o
n
o
p
t
i
m
i
z
a
t
i
o
n
f
o
r
c
r
e
d
i
t
sc
o
r
i
n
g
,
”
S
y
s
t
e
m
s
,
v
o
l
.
1
2
,
n
o
.
7
,
2
0
2
4
,
d
o
i
:
1
0
.
3
3
9
0
/
sy
st
e
ms
1
2
0
7
0
2
5
4
.
[
1
7
]
D
.
C
.
F
e
n
g
,
Z.
T
.
Li
u
,
X
.
D
.
W
a
n
g
,
Z
.
M
.
J
i
a
n
g
,
a
n
d
S
.
X
.
Li
a
n
g
,
“
F
a
i
l
u
r
e
mo
d
e
c
l
a
ss
i
f
i
c
a
t
i
o
n
a
n
d
b
e
a
r
i
n
g
c
a
p
a
c
i
t
y
p
r
e
d
i
c
t
i
o
n
f
o
r
r
e
i
n
f
o
r
c
e
d
c
o
n
c
r
e
t
e
c
o
l
u
mn
s
b
a
se
d
o
n
e
n
s
e
mb
l
e
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
m,”
Ad
v
a
n
c
e
d
E
n
g
i
n
e
e
ri
n
g
I
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
4
5
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
e
i
.
2
0
2
0
.
1
0
1
1
2
6
.
[
1
8
]
D
.
La
i
,
C
.
D
e
mart
i
n
o
,
a
n
d
Y
.
X
i
a
o
,
“
I
n
t
e
r
p
r
e
t
a
b
l
e
m
a
c
h
i
n
e
-
l
e
a
r
n
i
n
g
m
o
d
e
l
s
f
o
r
m
a
x
i
m
u
m
d
i
sp
l
a
c
e
me
n
t
s
o
f
R
C
b
e
a
ms
u
n
d
e
r
i
mp
a
c
t
l
o
a
d
i
n
g
p
r
e
d
i
c
t
i
o
n
s,
”
E
n
g
i
n
e
e
r
i
n
g
S
t
r
u
c
t
u
res
,
v
o
l
.
2
8
1
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
n
g
s
t
r
u
c
t
.
2
0
2
3
.
1
1
5
7
2
3
.
[
1
9
]
A
.
G
o
g
i
n
e
n
i
,
I
.
K
.
P
a
n
d
a
y
,
P
.
K
u
mar,
a
n
d
R
.
K
.
P
a
sw
a
n
,
“
P
r
e
d
i
c
t
i
n
g
c
o
m
p
r
e
ssi
v
e
st
r
e
n
g
t
h
o
f
c
o
n
c
r
e
t
e
w
i
t
h
f
l
y
a
sh
a
n
d
a
d
mi
x
t
u
r
e
u
si
n
g
X
G
B
o
o
st
:
a
c
o
m
p
a
r
a
t
i
v
e
st
u
d
y
o
f
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms,
”
Asi
a
n
J
o
u
rn
a
l
o
f
C
i
v
i
l
E
n
g
i
n
e
e
r
i
n
g
,
v
o
l
.
2
5
,
n
o
.
1
,
p
p
.
6
8
5
–
6
9
8
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
0
7
/
s
4
2
1
0
7
-
0
2
3
-
0
0
8
0
4
-
0.
[
2
0
]
S
.
H
a
mi
d
a
,
O
.
E.
L.
G
a
n
n
o
u
r
,
B
.
C
h
e
r
r
a
d
i
,
H
.
O
u
a
j
j
i
,
a
n
d
A
.
R
a
i
h
a
n
i
,
“
O
p
t
i
mi
z
a
t
i
o
n
o
f
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms
h
y
p
e
r
-
p
a
r
a
m
e
t
e
r
s
f
o
r
i
m
p
r
o
v
i
n
g
t
h
e
p
r
e
d
i
c
t
i
o
n
o
f
p
a
t
i
e
n
t
s
i
n
f
e
c
t
e
d
w
i
t
h
C
O
V
I
D
-
1
9
,
”
i
n
2
0
2
0
I
EE
E
2
n
d
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
El
e
c
t
r
o
n
i
c
s
,
C
o
n
t
r
o
l
,
O
p
t
i
m
i
z
a
t
i
o
n
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
(
I
C
E
C
O
C
S
)
,
K
e
n
i
t
r
a
,
M
o
r
o
c
c
o
:
I
EEE,
2
0
2
0
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
E
C
O
C
S
5
0
1
2
4
.
2
0
2
0
.
9
3
1
4
3
7
3
.
[
2
1
]
Y
.
W
a
n
g
e
t
a
l
.
,
“
S
h
o
r
t
-
t
e
r
m
l
o
a
d
f
o
r
e
c
a
s
t
i
n
g
o
f
i
n
d
u
s
t
r
i
a
l
c
u
s
t
o
m
e
r
s
b
a
se
d
o
n
S
V
M
D
a
n
d
X
G
B
o
o
st
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
El
e
c
t
r
i
c
a
l
Po
w
e
r
a
n
d
E
n
e
r
g
y
S
y
st
e
m
s
,
v
o
l
.
1
2
9
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
j
e
p
e
s.
2
0
2
1
.
1
0
6
8
3
0
.
[
2
2
]
Z.
Z
h
a
n
g
,
Y
.
H
u
a
n
g
,
R
.
Q
i
n
,
W
.
R
e
n
,
a
n
d
G
.
W
e
n
,
“
X
G
B
o
o
s
t
-
b
a
se
d
o
n
-
l
i
n
e
p
r
e
d
i
c
t
i
o
n
o
f
s
e
a
m
t
e
n
s
i
l
e
s
t
r
e
n
g
t
h
f
o
r
A
l
-
L
i
a
l
l
o
y
i
n
l
a
ser
w
e
l
d
i
n
g
:
e
x
p
e
r
i
me
n
t
st
u
d
y
a
n
d
m
o
d
e
l
l
i
n
g
,
”
J
o
u
rn
a
l
o
f
Ma
n
u
f
a
c
t
u
r
i
n
g
Pr
o
c
e
ss
e
s
,
v
o
l
.
6
4
,
p
p
.
3
0
–
4
4
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
ma
p
r
o
.
2
0
2
0
.
1
2
.
0
0
4
.
[
2
3
]
Z.
P
e
n
g
,
Q
.
H
u
a
n
g
,
a
n
d
Y
.
H
a
n
,
“
M
o
d
e
l
r
e
se
a
r
c
h
o
n
f
o
r
e
c
a
s
t
o
f
se
c
o
n
d
-
h
a
n
d
h
o
u
s
e
p
r
i
c
e
i
n
C
h
e
n
g
d
u
b
a
sed
o
n
X
G
b
o
o
st
a
l
g
o
r
i
t
h
m,
”
i
n
2
0
1
9
I
E
EE
1
1
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
A
d
v
a
n
c
e
d
I
n
f
o
c
o
m
m
T
e
c
h
n
o
l
o
g
y
,
I
C
AI
T
2
0
1
9
,
Ji
n
a
n
,
C
h
i
n
a
:
I
EEE,
2
0
1
9
,
p
p
.
1
6
8
–
1
7
2
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
A
I
T.
2
0
1
9
.
8
9
3
5
8
9
4
.
[
2
4
]
M
.
H
.
P
.
S
w
a
r
i
,
I
.
P
.
S
.
H
a
n
d
i
k
a
,
I
.
K
.
S
.
S
a
t
w
i
k
a
,
a
n
d
H
.
E.
W
a
h
a
n
i
,
“
O
p
t
i
mi
z
a
t
i
o
n
o
f
s
i
n
g
l
e
e
x
p
o
n
e
n
t
i
a
l
smo
o
t
h
i
n
g
u
s
i
n
g
p
a
r
t
i
c
l
e
sw
a
r
m
o
p
t
i
mi
z
a
t
i
o
n
a
n
d
m
o
d
i
f
i
e
d
p
a
r
t
i
c
l
e
sw
a
r
m
o
p
t
i
mi
z
a
t
i
o
n
i
n
s
a
l
e
s
f
o
r
e
c
a
st
,
”
i
n
2
0
2
2
I
EEE
8
t
h
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
I
n
t
e
r
n
a
t
i
o
n
a
l
S
e
m
i
n
a
r
(
I
T
I
S
)
,
S
u
r
a
b
a
y
a
,
I
n
d
o
n
e
si
a
:
I
EEE,
2
0
2
2
,
p
p
.
2
9
2
–
2
9
6
,
d
o
i
:
1
0
.
1
1
0
9
/
I
TI
S
5
7
1
5
5
.
2
0
2
2
.
1
0
0
1
0
0
3
4
.
[
2
5
]
S
.
G
u
a
n
a
n
d
X
.
Li
,
“
A
n
i
n
t
e
r
v
a
l
mu
l
t
i
-
o
b
j
e
c
t
i
v
e
p
a
r
t
i
c
l
e
sw
a
r
m
o
p
t
i
mi
z
a
t
i
o
n
a
l
g
o
r
i
t
h
m
w
i
t
h
n
i
c
h
i
n
g
t
e
c
h
n
o
l
o
g
y
f
o
r
m
u
l
t
i
m
o
d
a
l
p
r
o
b
l
e
ms,
”
i
n
2
0
2
3
3
5
t
h
C
h
i
n
e
se
C
o
n
t
r
o
l
a
n
d
D
e
c
i
si
o
n
C
o
n
f
e
re
n
c
e
(
C
C
D
C
)
,
Y
i
c
h
a
n
g
,
C
h
i
n
a
:
I
EEE,
2
0
2
3
,
p
p
.
4
0
1
8
–
4
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
C
C
D
C
5
8
2
1
9
.
2
0
2
3
.
1
0
3
2
6
5
6
3
.
[
2
6
]
E.
T
u
r
a
j
l
i
ć
,
“
M
u
l
t
i
l
e
v
e
l
t
h
r
e
sh
o
l
d
i
n
g
i
ma
g
e
se
g
me
n
t
a
t
i
o
n
b
a
s
e
d
o
n
m
u
l
t
i
-
sw
a
r
m
p
a
r
t
i
c
l
e
sw
a
r
m
o
p
t
i
mi
z
a
t
i
o
n
w
i
t
h
a
d
y
n
a
m
i
c
l
e
a
r
n
i
n
g
st
r
a
t
e
g
y
a
n
d
K
a
p
u
r
’
s
e
n
t
r
o
p
y
,
”
i
n
2
0
2
3
3
1
s
t
T
e
l
e
c
o
m
m
u
n
i
c
a
t
i
o
n
s
F
o
r
u
m
(
T
ELFO
R)
,
B
e
l
g
r
a
d
e
,
S
e
r
b
i
a
:
I
EEE,
2
0
2
3
,
p
p
.
1
–
4
,
d
o
i
:
1
0
.
1
1
0
9
/
T
ELFO
R
5
9
4
4
9
.
2
0
2
3
.
1
0
3
7
2
7
4
1
.
[
2
7
]
X
.
Y
u
,
L
.
Zh
u
,
Y
.
W
a
n
g
,
D
.
F
i
l
e
v
,
a
n
d
X
.
Y
a
o
,
“
I
n
t
e
r
n
a
l
c
o
m
b
u
s
t
i
o
n
e
n
g
i
n
e
c
a
l
i
b
r
a
t
i
o
n
u
si
n
g
o
p
t
i
mi
z
a
t
i
o
n
a
l
g
o
r
i
t
h
ms
,
”
A
p
p
l
i
e
d
En
e
r
g
y
,
v
o
l
.
3
0
5
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
p
e
n
e
r
g
y
.
2
0
2
1
.
1
1
7
8
9
4
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Ro
sa
li
n
a
is
a
lec
tu
re
r
a
t
P
re
sid
e
n
t
Un
i
v
e
rsity
,
sp
e
c
ializin
g
in
C
o
m
p
u
ter
S
c
ie
n
c
e
.
He
r
e
x
p
e
rti
se
li
e
s
in
a
rti
ficia
l
in
t
e
ll
ig
e
n
c
e
,
a
p
p
li
e
d
c
o
m
p
u
ti
n
g
,
a
n
d
c
o
m
p
u
t
in
g
m
e
th
o
d
o
l
o
g
ie
s,
wh
e
re
sh
e
a
d
v
a
n
c
e
s
k
n
o
wle
d
g
e
a
n
d
i
n
n
o
v
a
ti
v
e
so
l
u
ti
o
n
s.
H
e
r
wo
rk
f
o
c
u
se
s
o
n
b
ri
d
g
i
n
g
th
e
o
re
ti
c
a
l
re
se
a
rc
h
with
p
ra
c
ti
c
a
l
imp
lem
e
n
tatio
n
,
d
ri
v
i
n
g
g
r
o
wth
a
n
d
in
n
o
v
a
ti
o
n
in
th
e
tec
h
c
o
m
m
u
n
it
y
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
ro
sa
li
n
a
@p
re
sid
e
n
t.
a
c
.
i
d
.
Nun
ik
Afr
il
i
a
n
a
is
a
d
e
d
ica
ted
p
r
o
fe
ss
io
n
a
l
a
t
U
n
iv
e
rsitas
M
u
l
ti
m
e
d
ia
Nu
sa
n
tara
(UMN),
sp
e
c
ializin
g
in
Co
m
p
u
t
e
r
S
c
ien
c
e
.
He
r
e
x
p
e
rti
se
e
n
c
o
m
p
a
ss
e
s
a
p
p
li
e
d
i
n
fo
rm
a
ti
c
s,
in
fo
rm
a
ti
o
n
s
y
ste
m
s,
a
n
d
c
o
m
p
u
t
a
ti
o
n
a
l
i
n
telli
g
e
n
c
e
,
t
h
ro
u
g
h
wh
ich
sh
e
e
n
h
a
n
c
e
s
k
n
o
wle
d
g
e
a
n
d
d
e
v
e
lo
p
s
c
re
a
ti
v
e
s
o
lu
t
io
n
s.
Th
e
o
b
jec
ti
v
e
o
f
h
e
r
wo
r
k
is
t
o
c
o
n
n
e
c
t
t
h
e
o
re
ti
c
a
l
re
se
a
rc
h
with
p
ra
c
ti
c
a
l
a
p
p
li
c
a
ti
o
n
,
f
o
ste
ri
n
g
g
r
o
wth
a
n
d
i
n
n
o
v
a
ti
o
n
wit
h
in
th
e
tec
h
n
o
lo
g
y
c
o
m
m
u
n
it
y
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
n
u
n
ik
@
u
m
n
.
a
c
.
id
.
Evaluation Warning : The document was created with Spire.PDF for Python.