T
E
L
K
O
M
NIKA
T
elec
o
mm
un
ica
t
io
n Co
m
pu
t
i
ng
E
lect
ro
nics
a
nd
Co
ntr
o
l
Vo
l.
23
,
No
.
6
,
Dec
em
b
er
20
25
,
p
p
.
1
5
4
3
~1
554
I
SS
N:
1
6
9
3
-
6
9
3
0
,
DOI
: 1
0
.
1
2
9
2
8
/
T
E
L
KOM
NI
K
A
.
v
23
i
6
.
27128
1543
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//jo
u
r
n
a
l.u
a
d
.
a
c.
id
/in
d
ex
.
p
h
p
/TELK
OM
N
I
K
A
Applica
tion
o
f
a
rt
ificial int
ellig
ence
i
n e
m
iss
io
n p
redi
ction
for
hy
brid elec
tric
v
e
hicles:
i
n
tegra
tin
g
ANN
a
nd
GPR
H
er
u P
riy
a
nto
1
,
Rizqo
n F
a
j
a
r
1
,
Ya
a
ro
T
ela
u
m
ba
n
ua
1
,
Ariy
a
nto
1
,
M
o
ha
m
m
a
d M
uk
hl
a
s
A
f
1
,
Sig
it
T
ri
At
m
a
j
a
1
,
M
uh
a
m
m
a
d Sa
m
s
ul
M
a
a
rif
1,
2
,
K
urnia
F
a
j
a
r
A
dh
i Su
kra
1,
2
,
F
a
uzi D
w
i Set
i
a
w
a
n
1
1
R
e
se
a
r
c
h
C
e
n
t
e
r
f
o
r
T
r
a
n
sp
o
r
t
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
N
a
t
i
o
n
a
l
R
e
se
a
r
c
h
a
n
d
I
n
n
o
v
a
t
i
o
n
A
g
e
n
c
y
,
S
o
u
t
h
T
a
n
g
e
r
a
n
g
,
I
n
d
o
n
e
si
a
2
M
e
c
h
a
n
i
c
a
l
P
r
e
c
i
si
o
n
E
n
g
i
n
e
e
r
i
n
g
M
a
l
a
y
si
a
-
Jap
a
n
I
n
t
e
r
n
a
t
i
o
n
a
l
I
n
st
i
t
u
t
e
o
f
T
e
c
h
n
o
l
o
g
y
,
U
n
i
v
e
r
si
t
i
T
e
k
n
o
l
o
g
i
M
a
l
a
y
si
a
(
U
T
M
)
,
K
u
a
l
a
L
u
mp
u
r
,
M
a
l
a
y
si
a
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
A
p
r
14
,
2
0
2
5
R
ev
i
s
ed
Sep
11
,
2
0
2
5
A
cc
ep
ted
Oct
19
,
2
0
2
5
In
re
c
e
n
t
y
e
a
r
s,
h
y
b
rid
e
lec
tri
c
v
e
h
icle
s
(HEV
s)
h
a
v
e
e
m
e
r
g
e
d
a
s
a
p
ro
m
isin
g
so
lu
ti
o
n
to
m
it
ig
a
te
v
e
h
icu
lar
e
m
issio
n
s
a
n
d
im
p
ro
v
e
f
u
e
l
e
ff
ici
e
n
c
y
.
T
h
is
stu
d
y
f
o
c
u
se
s
o
n
t
h
e
T
o
y
o
ta
P
ri
u
s
HEV,
e
m
p
lo
y
in
g
a
d
v
a
n
c
e
d
a
rti
f
icia
l
n
e
u
ra
l
n
e
tw
o
rk
s
(AN
N)
a
n
d
G
a
u
ss
ian
p
ro
c
e
ss
re
g
re
ss
io
n
(G
P
R)
to
d
e
v
e
lo
p
a
p
re
d
ictiv
e
m
o
d
e
l
f
o
r
v
e
h
icle
e
m
issio
n
s.
Th
e
m
o
d
e
l
c
o
n
sid
e
rs
m
u
lt
ip
le
p
o
ll
u
tan
ts,
i
n
c
lu
d
in
g
c
a
rb
o
n
m
o
n
o
x
id
e
(C
O),
c
a
rb
o
n
d
io
x
id
e
(CO₂
),
h
y
d
ro
c
a
rb
o
n
s
(H
C),
a
n
d
n
it
ro
g
e
n
o
x
id
e
s
(NO
x
),
m
e
a
su
re
d
u
n
d
e
r
d
iv
e
rse
d
riv
in
g
c
o
n
d
it
i
o
n
s.
T
h
e
A
N
N
m
o
d
e
l
p
re
d
icts
e
m
issi
o
n
tren
d
s,
w
h
il
e
G
P
R
e
stim
a
te
s
p
re
d
icti
o
n
u
n
c
e
rtain
ty
,
e
n
h
a
n
c
in
g
t
h
e
m
o
d
e
l
’
s
ro
b
u
stn
e
ss
.
T
h
e
G
P
R
m
o
d
e
ls
a
c
h
iev
e
d
u
n
c
e
rtain
ty
lev
e
ls
o
f
±0
.
8
2
9
p
p
m
f
o
r
CO,
±9
.
9
7
8
p
p
m
f
o
r
HC,
±0
.
1
4
4
p
p
m
f
o
r
NO
x
,
a
n
d
±4
1
1
.
2
5
6
p
p
m
f
o
r
CO₂
,
re
sp
e
c
ti
v
e
l
y
,
u
n
d
e
rsc
o
rin
g
th
e
r
o
b
u
st
n
e
ss
o
f
th
e
in
teg
ra
ted
a
p
p
ro
a
c
h
f
o
r
e
m
issio
n
p
re
d
ictio
n
.
T
h
is
re
se
a
rc
h
a
im
s
to
s
u
p
p
o
rt
t
h
e
d
e
v
e
lo
p
m
e
n
t
o
f
m
o
re
su
sta
in
a
b
le
v
e
h
icle
tec
h
n
o
lo
g
ies
a
n
d
in
f
o
rm
p
o
li
c
y
m
a
k
in
g
f
o
r
e
n
v
iro
n
m
e
n
tal
su
sta
in
a
b
il
it
y
(e
.
g
.
,
Eu
ro
6
/E
u
ro
7
sta
n
d
a
rd
s).
Ov
e
ra
ll
,
th
e
stu
d
y
a
d
d
re
ss
e
s
h
o
w
a
rti
f
ici
a
l
in
telli
g
e
n
c
e
(A
I)
c
a
n
b
e
u
ti
l
ize
d
t
o
a
c
h
iev
e
a
c
c
u
ra
te
m
u
lt
i
-
p
o
ll
u
ta
n
t
e
m
issio
n
p
re
d
ictio
n
s
i
n
HE
V
s.
T
h
e
f
in
d
i
n
g
s
re
v
e
a
l
th
a
t
a
n
in
teg
ra
ted
A
NN
-
G
P
R
a
p
p
r
o
a
c
h
y
ield
s
su
p
e
ri
o
r
p
re
d
ictiv
e
p
e
rf
o
r
m
a
n
c
e
(R²
v
a
lu
e
s
a
p
p
ro
a
c
h
in
g
1
.
0
)
w
it
h
q
u
a
n
ti
f
iab
le
u
n
c
e
rtain
ty
,
o
u
t
p
e
rf
o
rm
in
g
a
sta
n
d
-
a
lo
n
e
A
N
N
m
o
d
e
l
a
n
d
p
r
o
v
id
i
n
g
a
r
o
b
u
st
so
lu
ti
o
n
t
o
th
e
e
m
issio
n
p
re
d
icti
o
n
c
h
a
ll
e
n
g
e
.
K
ey
w
o
r
d
s
:
A
r
ti
f
icial
n
e
u
r
al
n
et
w
o
r
k
s
E
m
is
s
io
n
p
r
ed
ictio
n
Gau
s
s
ia
n
p
r
o
ce
s
s
r
eg
r
ess
io
n
H
y
b
r
id
elec
tr
ic
v
eh
ic
les
P
r
ed
ictio
n
u
n
ce
r
tain
t
y
V
eh
icle
e
m
is
s
io
n
s
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
:
Her
u
P
r
iy
a
n
to
R
esear
ch
C
en
ter
f
o
r
T
r
an
s
p
o
r
t
atio
n
T
ec
h
n
o
lo
g
y
,
Na
tio
n
al
R
esear
ch
an
d
I
n
n
o
v
at
io
n
Ag
en
c
y
St
.
P
u
s
p
ip
tek
No
.
6
0
,
Setu
,
So
u
th
T
an
g
er
an
g
,
B
an
ten
,
1
5
3
1
4
,
I
n
d
o
n
esia
E
m
ail:
h
er
u
0
1
3
@
b
r
in
.
g
o
.
id
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
in
cr
ea
s
in
g
n
u
m
b
er
o
f
m
o
to
r
v
eh
icles
in
r
ec
e
n
t
d
ec
ad
es
h
as
led
to
s
ig
n
i
f
ican
t
en
v
i
r
o
n
m
e
n
tal
co
n
ce
r
n
s
,
p
ar
ticu
lar
l
y
r
eg
ar
d
in
g
air
p
o
llu
tio
n
f
r
o
m
ex
h
a
u
s
t
e
m
is
s
io
n
s
.
Veh
icles
p
o
w
er
ed
b
y
in
ter
n
al
co
m
b
u
s
t
io
n
en
g
i
n
es
(
I
C
E
)
r
elea
s
e
h
ar
m
f
u
l
g
a
s
es
p
o
llu
ta
n
t
s
in
c
l
u
d
in
g
ca
r
b
o
n
d
io
x
id
e
(
C
O₂
)
,
n
itro
g
en
o
x
id
e
s
(
NOx
)
,
an
d
p
ar
ticu
late
m
atter
(
PM
)
lead
to
p
o
o
r
air
q
u
alit
y
an
d
cli
m
a
te
ch
a
n
g
e.
T
h
ese
p
o
llu
tan
ts
n
eg
a
tiv
el
y
i
m
p
ac
t
p
u
b
lic
h
ea
lth
,
ec
o
s
y
s
te
m
s
,
a
n
d
g
lo
b
al
cli
m
ate
s
tab
ilit
y
.
I
n
r
esp
o
n
s
e,
g
o
v
er
n
m
en
t
s
a
n
d
th
e
au
to
m
o
ti
v
e
in
d
u
s
tr
y
h
a
v
e
b
ee
n
ac
ti
v
el
y
e
x
p
lo
r
in
g
e
n
v
ir
o
n
m
e
n
tall
y
f
r
ien
d
l
y
s
o
lu
tio
n
s
to
m
it
ig
ate
v
e
h
icle
e
m
i
s
s
io
n
s
.
O
n
e
p
r
o
m
i
s
in
g
in
n
o
v
a
tio
n
is
t
h
e
d
ev
elo
p
m
e
n
t
o
f
h
y
b
r
id
elec
tr
ic
v
eh
icle
s
(
HE
Vs),
ca
n
en
h
a
n
c
e
en
er
g
y
e
f
f
icien
c
y
an
d
lo
w
er
p
o
llu
tio
n
b
y
co
m
b
in
in
g
an
e
lectr
ic
m
o
to
r
w
i
t
h
an
in
ter
n
al
co
m
b
u
s
tio
n
e
n
g
in
e.
co
m
p
ar
ed
to
co
n
v
e
n
tio
n
al
f
o
s
s
il
-
f
u
el
-
p
o
w
e
r
ed
v
eh
icles
[
1
]
,
[
2
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
23
,
No
.
6
,
Dec
em
b
er
20
25
:
1
5
4
3
-
1
554
1544
Desp
ite
th
e
ir
p
o
ten
tial
b
en
e
f
its
,
HE
Vs
s
till
p
r
esen
t
ch
allen
g
es
i
n
ac
cu
r
atel
y
m
ea
s
u
r
in
g
a
n
d
p
r
ed
ictin
g
e
m
is
s
io
n
s
.
Var
iati
o
n
s
in
d
r
iv
in
g
p
atter
n
s
,
r
o
a
d
co
n
d
itio
n
s
,
an
d
d
r
iv
er
b
eh
av
io
r
ca
n
ca
u
s
e
f
l
u
ctu
a
tio
n
s
i
n
e
m
i
s
s
io
n
le
v
els,
m
ak
i
n
g
it
d
if
f
ic
u
lt
to
d
ev
elo
p
co
n
s
is
te
n
t
r
eg
u
lato
r
y
an
d
en
v
ir
o
n
m
en
ta
l
s
tr
ateg
ie
s
.
T
o
ad
d
r
ess
th
ese
co
m
p
lex
i
ties
[
3
]
,
[
4
]
.
B
y
lev
er
a
g
in
g
r
ea
l
-
ti
m
e
d
ata
f
r
o
m
v
eh
ic
l
e
s
en
s
o
r
s
,
ar
tific
ial
in
telli
g
e
n
ce
(
A
I
)
al
g
o
r
ith
m
s
ca
n
id
en
tify
e
m
i
s
s
io
n
tr
e
n
d
s
an
d
p
r
o
v
id
e
ac
cu
r
ate
p
r
ed
icti
o
n
s
u
n
d
er
d
i
f
f
er
e
n
t
o
p
er
atin
g
co
n
d
itio
n
s
,
o
f
f
er
in
g
a
m
o
r
e
ef
f
ec
tiv
e
ap
p
r
o
ac
h
to
m
an
a
g
i
n
g
v
e
h
icle
e
m
is
s
io
n
s
[
5
]
.
T
h
is
s
tu
d
y
e
x
p
lo
r
es
h
o
w
HE
Vs
co
n
tr
ib
u
te
to
r
ed
u
ci
n
g
e
m
is
s
io
n
s
an
d
e
x
a
m
i
n
e
s
th
e
r
o
l
e
o
f
A
I
i
n
en
h
a
n
ci
n
g
e
m
is
s
io
n
p
r
ed
ictio
n
ac
cu
r
ac
y
.
T
h
e
r
esear
ch
aim
s
to
u
n
co
v
er
th
e
s
y
n
er
g
y
b
et
w
ee
n
h
y
b
r
id
v
e
h
icle
tech
n
o
lo
g
y
a
n
d
A
I
-
d
r
iv
e
n
p
r
ed
ictiv
e
m
o
d
els
i
n
ac
h
iev
i
n
g
m
o
r
e
s
u
s
tai
n
ab
le
an
d
lo
w
-
e
m
i
s
s
io
n
tr
a
n
s
p
o
r
tatio
n
s
y
s
te
m
s
[
1
]
,
[
6
]
.
Mo
to
r
v
eh
icl
e
e
m
i
s
s
io
n
s
,
i
n
cl
u
d
in
g
t
h
o
s
e
f
r
o
m
h
y
b
r
id
v
e
h
icle
s
l
i
k
e
t
h
e
T
o
y
o
ta
P
r
iu
s
,
r
e
m
a
in
a
m
aj
o
r
co
n
tr
ib
u
to
r
to
air
p
o
llu
tio
n
a
n
d
cli
m
a
te
ch
a
n
g
e.
W
h
ile
HE
Vs
h
elp
m
iti
g
a
te
e
m
i
s
s
io
n
s
,
t
h
eir
ef
f
ec
tiv
e
n
e
s
s
v
ar
ie
s
d
u
e
to
o
p
er
atio
n
al
co
n
d
itio
n
s
.
A
r
eliab
le
p
r
ed
ictiv
e
m
o
d
el
is
n
ee
d
ed
to
a
d
d
r
ess
th
ese
in
co
n
s
is
te
n
cie
s
an
d
p
r
o
v
id
e
ac
cu
r
ate
esti
m
atio
n
s
o
f
e
m
i
s
s
io
n
s
.
A
r
ti
f
icial
n
e
u
r
al
n
et
w
o
r
k
s
(
A
N
N)
ar
e
co
m
m
o
n
l
y
u
til
ize
d
to
p
r
e
d
ict
em
is
s
io
n
tr
en
d
s
,
y
e
t
th
eir
in
ab
ilit
y
to
q
u
an
t
if
y
p
r
ed
ictio
n
u
n
ce
r
ta
in
t
y
ca
n
l
i
m
it
th
e
ir
ef
f
ec
t
iv
e
n
es
s
.
I
n
co
n
tr
ast,
Gau
s
s
ian
p
r
o
ce
s
s
r
eg
r
ess
io
n
(
GP
R
)
is
ca
p
ab
le
o
f
esti
m
ati
n
g
u
n
ce
r
tain
t
y
,
en
h
a
n
cin
g
t
h
e
r
eliab
ilit
y
o
f
p
r
ed
ict
iv
e
m
o
d
els
[
7
]
,
[
8
]
.
B
y
i
n
te
g
r
atin
g
A
NN
a
n
d
GP
R
,
a
m
o
r
e
co
m
p
r
eh
e
n
s
i
v
e
an
d
r
o
b
u
s
t
h
y
b
r
id
p
r
ed
ictio
n
m
o
d
el
ca
n
b
e
d
ev
elo
p
ed
.
T
h
is
s
tu
d
y
s
ee
k
s
to
an
s
w
er
k
e
y
r
esear
ch
q
u
e
s
tio
n
s
:
w
h
at
a
r
e
th
e
e
m
i
s
s
io
n
ch
ar
ac
ter
is
t
ics
o
f
h
y
b
r
id
v
e
h
icle
s
u
n
d
er
d
iv
er
s
e
d
r
iv
in
g
co
n
d
itio
n
s
?
h
o
w
ca
n
p
r
ed
ictiv
e
m
o
d
els
b
e
d
esig
n
ed
to
p
r
o
v
id
e
h
ig
h
-
ac
cu
r
ac
y
e
m
is
s
io
n
f
o
r
ec
asts
w
it
h
m
ea
s
u
r
ab
le
u
n
c
er
tain
t
y
?
Veh
ic
u
lar
e
m
i
s
s
io
n
m
o
d
elin
g
is
co
m
m
o
n
l
y
e
m
p
lo
y
ed
to
p
r
ed
ict
th
e
a
m
o
u
n
t
o
f
e
x
h
a
u
s
t
e
m
is
s
io
n
s
p
r
o
d
u
ce
d
b
y
d
if
f
er
en
t
v
eh
icl
e
t
y
p
es
(
ca
r
b
o
n
m
o
n
o
x
id
e
(
C
O)
,
C
O₂,
h
y
d
r
o
ca
r
b
o
n
s
(
HC
)
,
an
d
NOx
)
.
S
u
c
h
m
o
d
el
s
p
la
y
a
cr
u
cia
l
r
o
le
in
en
v
ir
o
n
m
e
n
tal
i
m
p
ac
t
as
s
es
s
m
en
t,
tr
an
s
p
o
r
tatio
n
p
o
lic
y
d
ev
elo
p
m
e
n
t,
an
d
t
h
e
ad
v
an
ce
m
en
t
o
f
s
u
s
tai
n
ab
le
au
to
m
o
tiv
e
tec
h
n
o
lo
g
ies.
T
h
e
y
a
ls
o
h
elp
an
al
y
ze
th
e
i
n
f
lu
e
n
ce
o
f
k
e
y
f
ac
to
r
s
f
u
el
t
y
p
e,
o
p
er
atin
g
co
n
d
itio
n
s
,
v
e
h
ic
le
s
p
ec
i
f
icatio
n
s
o
n
e
m
is
s
io
n
s
.
T
h
e
u
r
g
e
n
c
y
o
f
a
d
d
r
ess
in
g
v
e
h
ic
u
lar
e
m
is
s
io
n
s
s
te
m
s
f
r
o
m
t
h
eir
d
ir
ec
t
im
p
licatio
n
s
o
n
en
v
ir
o
n
m
e
n
tal
s
u
s
tain
ab
ili
t
y
an
d
p
u
b
lic
h
ea
lt
h
.
W
h
ile
HE
Vs
o
f
f
er
a
p
r
o
m
is
in
g
s
o
l
u
tio
n
,
th
eir
e
m
is
s
io
n
s
r
e
m
ai
n
v
ar
iab
le
d
u
e
to
f
ac
to
r
s
l
ik
e
d
r
iv
in
g
b
eh
a
v
io
r
an
d
r
o
ad
c
o
n
d
itio
n
s
.
As
a
r
esu
lt,
ac
cu
r
ate
an
d
r
eliab
le
em
i
s
s
io
n
p
r
ed
ictio
n
m
o
d
els
ar
e
ess
en
tia
l
to
f
ac
ilit
ate
b
etter
e
m
is
s
io
n
co
n
tr
o
l
s
tr
ate
g
ies,
in
f
o
r
m
p
o
lic
y
m
ak
er
s
,
an
d
s
u
p
p
o
r
t
th
e
d
ev
elo
p
m
e
n
t
o
f
s
u
s
tai
n
ab
le
tr
an
s
p
o
r
tatio
n
tech
n
o
lo
g
ies.
T
h
is
r
esear
ch
ai
m
s
to
d
ev
elo
p
a
m
u
lti
-
p
o
ll
u
tan
t
e
m
is
s
io
n
p
r
ed
ictio
n
m
o
d
el
f
o
r
h
y
b
r
id
v
e
h
icles
u
s
i
n
g
a
co
m
b
in
a
tio
n
o
f
d
ee
p
lear
n
in
g
tech
n
iq
u
e
s
an
d
GP
R
.
T
h
e
m
o
d
el
f
o
cu
s
es
o
n
p
r
ed
ictin
g
e
m
is
s
io
n
s
o
f
C
O,
C
O₂,
NOx
,
an
d
H
C
w
h
ile
en
s
u
r
in
g
b
o
th
ac
cu
r
ac
y
an
d
r
eliab
ili
t
y
[
9
]
,
[
1
0
]
.
B
y
v
alid
ati
n
g
m
o
d
el
p
er
f
o
r
m
an
ce
ag
ain
s
t
r
ea
l
-
w
o
r
ld
d
ata
u
n
d
er
Un
ited
Natio
n
s
E
C
E
R
8
3
s
ta
n
d
ar
d
d
r
iv
in
g
c
y
c
les,
t
h
is
r
esea
r
ch
o
f
f
er
s
i
n
s
i
g
h
ts
o
n
th
e
s
tr
en
g
t
h
s
a
n
d
w
ea
k
n
ess
es
o
f
d
i
f
f
er
e
n
t
p
r
ed
ictio
n
tech
n
iq
u
e
s
.
Fu
r
t
h
er
m
o
r
e,
a
n
al
y
zi
n
g
th
e
f
ac
to
r
s
co
n
tr
ib
u
ti
n
g
to
e
m
i
s
s
io
n
p
r
ed
ictio
n
u
n
ce
r
tain
t
y
w
il
l
en
h
a
n
c
e
th
e
m
o
d
el
’
s
p
r
ac
tical
ap
p
licab
ilit
y
in
e
m
is
s
io
n
m
an
a
g
e
m
e
n
t.
T
h
e
ex
p
e
cted
o
u
tco
m
es
o
f
t
h
i
s
r
esear
ch
ar
e
s
i
g
n
if
ican
t
f
o
r
t
h
e
d
ev
elo
p
m
e
n
t
o
f
HE
V
tech
n
o
lo
g
y
a
n
d
th
e
f
o
r
m
u
latio
n
o
f
m
o
r
e
ef
f
ec
t
iv
e
e
m
i
s
s
io
n
-
r
ed
u
ct
io
n
s
tr
ate
g
ies.
T
h
e
s
tu
d
y
is
an
t
icip
ated
to
y
ield
an
ac
cu
r
ate
an
d
ef
f
icie
n
t
m
u
lti
-
p
o
llu
ta
n
t
e
m
is
s
io
n
p
r
ed
ictio
n
m
o
d
el
b
y
i
n
teg
r
ati
n
g
A
NN
a
n
d
GP
R
.
T
h
is
m
o
d
el
w
ill
f
ac
ilit
ate
d
ee
p
er
an
al
y
s
is
o
f
f
ac
to
r
s
in
f
lu
e
n
ci
n
g
e
m
is
s
io
n
s
an
d
o
f
f
er
b
etter
esti
m
atio
n
s
f
o
r
HE
Vs.
T
o
en
s
u
r
e
p
r
ac
tical
ap
p
licab
ilit
y
,
m
o
d
e
l
v
alid
atio
n
is
co
n
d
u
cted
u
s
in
g
test
d
ata
co
m
p
lian
t
w
i
th
Un
i
ted
Natio
n
s
Ec
o
n
o
m
ic
C
o
m
m
is
s
io
n
f
o
r
E
u
r
o
p
e
(
UN
E
C
E
)
R
8
3
s
tan
d
ar
d
s
,
en
s
u
r
in
g
r
o
b
u
s
t
n
es
s
in
h
an
d
li
n
g
e
m
i
s
s
io
n
v
ar
iab
ilit
y
[
1
1
]
,
[
1
2
]
.
I
n
s
u
m
m
ar
y
,
t
h
is
s
t
u
d
y
ad
d
r
ess
es
t
h
e
cr
itical
q
u
esti
o
n
o
f
h
o
w
A
I
-
b
ased
m
o
d
els
ca
n
i
m
p
r
o
v
e
th
e
ac
cu
r
ac
y
o
f
HE
V
e
m
is
s
io
n
p
r
ed
ictio
n
s
.
T
o
an
s
w
er
th
is
q
u
esti
o
n
,
w
e
d
ev
e
lo
p
ed
an
in
teg
r
ated
A
NN
-
GP
R
m
o
d
el
th
a
t
co
m
b
i
n
es
t
h
e
p
atter
n
-
r
ec
o
g
n
itio
n
s
tr
en
g
t
h
o
f
A
N
N
w
it
h
GP
R
’
s
ab
ilit
y
to
q
u
an
t
if
y
u
n
ce
r
tai
n
t
y
.
T
h
e
ap
p
r
o
ac
h
in
v
o
lv
e
s
tr
ain
i
n
g
th
e
h
y
b
r
id
m
o
d
el
o
n
r
ea
l
-
w
o
r
ld
e
m
is
s
io
n
d
ata
f
r
o
m
a
T
o
y
o
ta
P
r
iu
s
u
n
d
er
s
ta
n
d
ar
d
u
r
b
an
an
d
e
x
tr
a
-
u
r
b
an
d
r
iv
i
n
g
c
y
cle
s
,
an
d
ev
a
lu
at
in
g
p
er
f
o
r
m
a
n
ce
w
it
h
r
ig
o
r
o
u
s
v
al
id
atio
n
m
e
tr
ics
(
r
o
o
t
m
ea
n
s
q
u
ar
ed
er
r
o
r
(
R
MSE
)
,
m
ea
n
ab
s
o
lu
te
er
r
o
r
(
MA
E
)
,
R
²)
.
T
h
e
r
esu
lt
s
s
h
o
w
t
h
at
th
e
ANN
-
GP
R
h
y
b
r
id
m
o
d
el
ac
h
iev
e
s
s
u
p
er
io
r
ac
cu
r
ac
y
w
it
h
R
²
v
al
u
es
ap
p
r
o
ac
h
in
g
1
.
0
ac
r
o
s
s
all
tar
g
eted
p
o
llu
tan
ts
an
d
ef
f
ec
tiv
e
l
y
ca
p
tu
r
e
s
p
r
ed
ictio
n
u
n
ce
r
tain
t
y
,
o
u
tp
er
f
o
r
m
in
g
a
s
tan
d
alo
n
e
A
NN
i
n
tr
ac
k
in
g
e
m
i
s
s
io
n
tr
en
d
s
.
C
o
n
s
eq
u
en
tl
y
,
t
h
i
s
i
n
te
g
r
ated
m
o
d
elin
g
ap
p
r
o
ac
h
b
r
id
g
es
a
k
e
y
g
ap
i
n
h
y
b
r
id
v
e
h
icle
e
m
is
s
io
n
m
o
d
eli
n
g
,
p
r
o
v
id
in
g
a
r
o
b
u
s
t
p
r
ed
ictiv
e
to
o
l
th
at
ca
n
i
n
f
o
r
m
e
m
is
s
io
n
co
n
tr
o
l
p
o
licies
an
d
g
u
id
e
t
h
e
d
ev
elo
p
m
e
n
t
o
f
clea
n
er
v
e
h
icle
tec
h
n
o
lo
g
ies
f
o
r
s
u
s
tai
n
ab
le
tr
an
s
p
o
r
tatio
n
.
Var
io
u
s
s
ta
k
e
h
o
ld
er
s
s
tan
d
to
b
en
ef
it
f
r
o
m
t
h
ese
o
u
tco
m
es
:
th
e
r
esear
c
h
co
m
m
u
n
it
y
g
ai
n
s
n
e
w
i
n
s
i
g
h
t
s
i
n
to
A
I
-
d
r
i
v
en
e
m
i
s
s
io
n
m
o
d
el
in
g
,
t
h
e
a
u
to
m
o
ti
v
e
in
d
u
s
tr
y
ca
n
i
m
p
le
m
e
n
t
i
m
p
r
o
v
ed
p
r
ed
ictiv
e
co
n
tr
o
ls
f
o
r
l
o
w
er
e
m
is
s
io
n
s
,
p
o
lic
y
m
a
k
er
s
o
b
tain
a
s
cie
n
ti
f
ic
b
asis
f
o
r
s
tr
icter
e
m
i
s
s
io
n
s
tan
d
ar
d
s
,
an
d
s
o
ciet
y
at
lar
g
e
w
ill
b
en
e
f
it
f
r
o
m
i
m
p
r
o
v
ed
air
q
u
ality
a
n
d
en
v
ir
o
n
m
e
n
tal
s
u
s
tai
n
ab
ilit
y
.
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
A
p
p
lica
tio
n
o
f a
r
tifi
cia
l in
tellig
en
ce
in
emiss
io
n
p
r
ed
ictio
n
f
o
r
h
yb
r
id
elec
tr
ic
ve
h
icles:
…
(
Heru
P
r
iya
n
to
)
1545
2.
M
E
T
H
O
D
T
h
is
s
ec
tio
n
d
escr
ib
es
th
e
d
ev
elo
p
m
e
n
t
o
f
th
e
e
m
i
s
s
io
n
p
r
ed
ictio
n
m
o
d
el
u
s
in
g
an
d
GP
R
.
I
t
co
v
er
s
th
e
d
ata
co
llectio
n
p
r
o
ce
s
s
,
m
o
d
el
d
ev
elo
p
m
e
n
t,
an
d
tr
ain
i
n
g
p
r
o
ce
d
u
r
es.
2
.
1
.
ANN
m
o
del
Mu
ltip
le
ANN
ar
c
h
itect
u
r
es
w
er
e
test
ed
(
5
-
2
0
n
e
u
r
o
n
s
,
s
i
n
g
l
e/
m
u
lti
h
id
d
en
la
y
er
s
)
u
s
i
n
g
g
r
id
s
ea
r
ch
an
d
cr
o
s
s
-
v
alid
atio
n
.
T
h
e
f
i
n
a
l
ar
ch
itectu
r
e
w
i
th
1
0
n
e
u
r
o
n
s
in
o
n
e
h
id
d
en
la
y
er
w
as
s
ele
cted
as
it
b
alan
ce
d
ac
cu
r
ac
y
w
it
h
co
m
p
u
tatio
n
al
ef
f
icie
n
c
y
.
A
NN
is
a
p
ar
al
lel
p
r
o
ce
s
s
in
g
ap
p
r
o
a
ch
es
th
at
ca
n
s
p
ec
if
icall
y
d
escr
ib
e
n
o
n
-
li
n
ea
r
an
d
co
m
p
lex
in
ter
ac
tio
n
s
u
s
in
g
i
n
p
u
t
-
o
u
t
p
u
t
d
ata
s
et
tr
ain
in
g
p
atter
n
[
1
3
]
,
[
1
4
]
.
T
h
e
A
NN
m
o
d
el
o
p
er
ates
in
th
r
ee
s
ta
g
e
s
:
f
ee
d
f
o
r
w
ar
d
,
b
ac
k
-
p
r
o
p
ag
a
tio
n
,
an
d
w
e
ig
h
t
ad
j
u
s
t
m
e
n
t,
ca
lcu
lated
b
ased
o
n
estab
lis
h
ed
eq
u
atio
n
s
[
1
5
]
,
[
1
6
]
.
I
n
th
e
f
ir
s
t
s
tag
e,
ea
ch
i
n
p
u
t
n
o
d
e
r
ec
eiv
es
an
in
p
u
t
v
al
u
e
(
=
1
,
2
,
3
,
.
.
.
,
)
an
d
f
o
r
w
ar
d
s
t
h
e
s
i
g
n
a
l
to
all
n
o
d
es
in
t
h
e
h
id
d
en
la
y
er
.
E
a
c
h
h
i
d
d
en
lay
e
r
n
o
d
e
s
u
m
s
a
l
l
w
ei
g
h
t
e
d
in
p
u
t
s
ig
n
a
ls
(
)
,
w
h
e
r
e
x
i
i
s
m
u
lt
i
p
l
ie
d
b
y
th
e
w
ei
g
h
t
(
)
a
n
d
a
d
d
e
d
t
o
t
h
e
r
e
c
e
iv
e
d
b
i
as
(
=
1
,
2
,
3
,
.
.
.
,
p
)
a
s
s
h
o
w
n
in
(
1
)
.
T
h
e
o
u
t
p
u
t
s
ig
n
a
l
f
r
o
m
th
e
h
i
d
d
en
l
ay
e
r
n
o
d
e
is
c
a
l
cu
l
a
te
d
u
s
in
g
th
e
a
ct
iv
a
ti
o
n
f
u
n
c
t
i
o
n
as
in
(
2
)
.
=
+
∑
=
1
(
1
)
=
(
)
(
2
)
I
n
(
1
)
an
d
(
2
)
r
ep
r
esen
t th
e
w
e
ig
h
ted
s
u
m
a
n
d
ac
tiv
atio
n
f
u
n
ctio
n
s
i
n
th
e
h
id
d
en
la
y
er
.
E
ac
h
o
u
tp
u
t
la
y
er
n
o
d
e
(
k
=
1
,
2
,
3
,
.
.
.
,
m
)
,
s
u
m
s
all
s
ig
n
al
s
f
r
o
m
th
e
h
id
d
en
la
y
e
r
n
o
d
es
(
m
u
l
tip
lied
b
y
w
ei
g
h
t
s
w
j
k
,
an
d
ad
d
ed
t
o
th
e
b
ias
)
as in
(
3
)
.
T
h
e
o
u
tp
u
t si
g
n
a
l f
r
o
m
th
e
o
u
t
p
u
t n
o
d
e
is
t
h
e
n
ca
lcu
lated
u
s
i
n
g
t
h
e
ac
ti
v
atio
n
f
u
n
ctio
n
(
4
)
.
_
=
+
∑
=
1
(
3
)
=
(
_
)
(
4
)
I
n
(
3
)
an
d
(
4
)
ar
e
f
o
r
w
ei
g
h
ted
s
u
m
an
d
ac
ti
v
atio
n
i
n
o
u
tp
u
t l
a
y
er
.
I
n
th
e
s
ec
o
n
d
s
tag
e
(
b
ac
k
-
p
r
o
p
ag
atio
n
)
,
th
e
er
r
o
r
in
f
o
r
m
ati
o
n
(
)
b
etw
ee
n
ea
c
h
o
u
tp
u
t
n
o
d
e
(
)
an
d
th
e
tar
g
et
v
alu
e
(
)
r
elate
d
to
th
e
tr
ain
in
g
d
ata
is
ca
lcu
lated
as
in
(
5
)
.
T
o
a
d
j
u
s
t
th
e
w
e
ig
h
ts
an
d
b
iases
,
co
r
r
ec
tio
n
s
f
o
r
w
e
ig
h
t
s
(
∆
)
an
d
b
iases
(
∆
)
ar
e
ca
lcu
lated
u
s
i
n
g
a
p
r
ed
eter
m
i
n
ed
lear
n
i
n
g
r
ate
(
α
)
as
g
iv
e
n
i
n
(
6
)
an
d
(
7
)
.
=
(
−
)
′
(
_
)
(
5
)
∆
=
(
6
)
∆
=
(
7
)
T
h
e
er
r
o
r
ca
lcu
latio
n
an
d
w
ei
g
h
t/b
ias
u
p
d
ate
f
o
r
th
e
o
u
tp
u
t la
y
er
ar
e
ex
p
r
ess
ed
in
(
5
)
-
(
7
)
.
I
n
th
e
th
ir
d
s
tag
e
(
w
ei
g
h
t
ad
j
u
s
t
m
e
n
t)
,
th
e
er
r
o
r
in
f
o
r
m
a
tio
n
(
)
b
etw
ee
n
ea
ch
h
id
d
en
la
y
er
n
o
d
e
(
,
j
=
1
,
2
,
3
,
.
.
.
,
p
)
an
d
th
e
i
n
p
u
t
la
y
er
n
o
d
es
i
s
ca
lc
u
lated
as
in
(
8
)
.
W
eig
h
t
co
r
r
ec
tio
n
s
(
∆
)
an
d
b
ias
co
r
r
ec
tio
n
s
(
∆
)
ar
e
co
m
p
u
ted
to
ad
j
u
s
t
th
e
w
eig
h
t
(
)
an
d
b
ias
(
)
v
alu
es
as
s
h
o
w
n
in
(
9
)
an
d
(
1
0
)
u
s
in
g
th
e
lear
n
i
n
g
r
ate
(
α
)
.
=
(
∑
=
1
)
′
(
)
(
8
)
∆
=
(
9
)
∆
=
(
1
0
)
I
n
(
8
)
-
(
1
0
)
ar
e
e
r
r
o
r
p
r
o
p
ag
atio
n
an
d
u
p
d
ate
f
o
r
h
id
d
en
la
y
er
.
Af
ter
t
h
ese
ad
j
u
s
t
m
en
ts
,
ea
ch
o
u
tp
u
t
u
n
i
t
is
u
p
d
ated
w
it
h
n
e
w
w
ei
g
h
t
an
d
b
ias
v
al
u
es
as
i
n
(
1
1
)
an
d
(
1
2
)
,
an
d
s
im
ilar
l
y
ea
ch
h
id
d
en
u
n
it
’
s
p
ar
a
m
e
ter
s
ar
e
u
p
d
ated
as in
(
1
3
)
an
d
(
1
4
)
.
(
)
=
(
)
+
∆
(
1
1
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
23
,
No
.
6
,
Dec
em
b
er
20
25
:
1
5
4
3
-
1
554
1546
(
)
=
(
)
+
∆
(
1
2
)
(
)
=
(
)
+
∆
(
1
3
)
(
)
=
(
)
+
∆
(
1
4
)
I
n
(
1
1
)
-
(
1
4
)
a
r
e
f
in
al
w
ei
g
h
t a
n
d
b
ias u
p
d
ate
eq
u
atio
n
s
.
T
h
e
ar
ch
itect
u
r
e
o
f
th
e
A
N
N
is
s
h
o
w
n
i
n
Fi
g
u
r
e
1
.
Fig
u
r
e
1
.
A
NN
a
r
c
h
itect
u
r
e
2
.
2
.
E
x
peri
m
ent
a
l set
up
a
n
d
da
t
a
co
llect
io
n
T
h
e
v
eh
icle
test
s
w
er
e
co
n
d
u
cted
at
th
e
T
h
er
m
o
d
y
n
a
m
ics
Mo
to
r
an
d
Pro
p
u
ls
io
n
S
y
s
te
m
s
L
ab
o
r
ato
r
y
o
f
t
h
e
Natio
n
al
R
esear
c
h
an
d
I
n
n
o
v
a
tio
n
Ag
e
n
c
y
.
T
h
e
t
ests
f
o
llo
w
ed
t
h
e
c
u
r
r
en
t
I
n
d
o
n
esian
s
ta
n
d
ar
d
s
,
s
p
ec
if
icall
y
t
h
e
UN
E
C
E
R
8
3
r
eg
u
lat
io
n
s
[
1
7
]
,
[
1
8
]
.
T
h
e
v
eh
icle
w
a
s
p
lace
d
o
n
a
ch
a
s
s
i
s
d
y
n
a
m
o
m
eter
an
d
o
p
er
ated
u
s
in
g
t
w
o
d
r
iv
e
c
y
cl
es:
u
r
b
an
d
r
iv
e
c
y
cle
(
U
D
C
)
an
d
ex
tr
a
U
DC
(
E
UD
C
)
.
T
h
e
ca
r
w
a
s
d
r
iv
e
n
f
o
r
ap
p
r
o
x
im
a
tel
y
1
,
1
8
0
s
ec
o
n
d
s
,
an
d
m
ea
s
u
r
e
m
e
n
ts
w
er
e
tak
e
n
f
o
r
s
ev
er
al
e
m
i
s
s
io
n
p
ar
a
m
e
ter
s
,
in
cl
u
d
in
g
C
O,
C
O₂,
HC
,
an
d
NOx
.
A
d
d
itio
n
all
y
,
e
n
v
ir
o
n
m
e
n
tal
p
ar
a
m
et
er
s
s
u
ch
as
te
m
p
er
at
u
r
e,
p
r
ess
u
r
e,
g
as
f
lo
w
r
ate,
h
u
m
id
it
y
,
an
d
v
e
h
icle
s
p
ee
d
w
er
e
r
ec
o
r
d
ed
.
F
ig
u
r
e
2
illu
s
tr
at
es th
e
UN
E
C
E
R
8
3
d
r
iv
in
g
c
y
cle
.
Fig
u
r
e
2
.
UN
E
C
E
R
8
3
d
r
iv
in
g
c
y
cle
2
.
3
.
G
P
R
m
o
del
GP
R
is
a
n
o
n
-
p
ar
a
m
etr
ic
B
a
y
esian
r
e
g
r
ess
io
n
m
et
h
o
d
w
id
el
y
u
s
ed
i
n
m
ac
h
in
e
lear
n
i
n
g
d
u
e
to
its
ef
f
ec
tiv
e
n
e
s
s
w
it
h
s
m
all
d
atas
ets
an
d
its
ab
ilit
y
to
p
r
o
v
id
e
p
r
ed
ictiv
e
u
n
ce
r
tai
n
t
y
m
ea
s
u
r
es
[
1
9
]
,
[
2
0
]
.
GP
R
m
o
d
el
s
t
h
e
d
is
tr
ib
u
tio
n
o
f
a
n
u
n
k
n
o
w
n
tar
g
et
f
u
n
c
tio
n
b
ase
d
o
n
tr
ain
i
n
g
d
ata,
u
n
d
er
th
e
ass
u
m
p
tio
n
t
h
at
t
h
e
d
ata
ca
n
b
e
d
escr
ib
ed
b
y
a
G
P
R
.
I
t
d
ef
in
es
a
p
r
io
r
o
v
er
f
u
n
ctio
n
s
an
d
u
s
es
a
co
v
ar
ia
n
ce
f
u
n
ctio
n
(
k
er
n
el)
to
d
escr
ib
e
th
e
r
elatio
n
s
h
ip
b
et
w
ee
n
an
y
t
w
o
d
ata
p
o
in
ts
.
T
h
e
ch
o
ice
o
f
k
er
n
el
f
u
n
ct
io
n
d
eter
m
in
e
s
th
e
s
h
ap
e
o
f
th
e
i
n
f
er
r
ed
r
elatio
n
s
h
ip
.
Se
v
er
al
k
er
n
els
(
r
ad
ial
b
asis
f
u
n
ct
io
n
(
R
B
F
)
,
s
q
u
ar
ed
ex
p
o
n
en
tial
(
SE
)
,
an
d
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
A
p
p
lica
tio
n
o
f a
r
tifi
cia
l in
tellig
en
ce
in
emiss
io
n
p
r
ed
ictio
n
f
o
r
h
yb
r
id
elec
tr
ic
ve
h
icles:
…
(
Heru
P
r
iya
n
to
)
1547
co
m
b
i
n
ed
)
w
er
e
co
m
p
ar
ed
.
T
h
e
p
o
l
y
n
o
m
ial
k
er
n
e
l
w
as
c
h
o
s
en
d
u
e
to
it
s
s
u
p
er
io
r
p
er
f
o
r
m
an
ce
o
n
e
m
is
s
io
n
d
ata,
y
ield
i
n
g
lo
w
er
R
M
SE
an
d
h
ig
h
er
co
ef
f
icie
n
t
o
f
d
eter
m
in
at
io
n
(
R²
)
co
m
p
ar
ed
to
o
th
er
s
w
h
ile
m
ai
n
tai
n
in
g
r
ea
s
o
n
ab
le
co
m
p
u
tatio
n
a
l
co
s
t.
I
n
th
is
s
t
u
d
y
,
a
p
o
ly
n
o
m
ial
k
er
n
el
w
a
s
e
m
p
lo
y
ed
f
o
r
th
e
GP
R
m
o
d
el
to
ca
p
tu
r
e
n
o
n
-
lin
ea
r
tr
en
d
s
in
th
e
e
m
is
s
io
n
d
ata.
B
y
tr
ain
i
n
g
th
e
GP
R
m
o
d
el
o
n
th
e
av
ailab
le
d
ata,
w
e
o
b
tain
n
o
t
o
n
l
y
a
p
r
ed
ictio
n
f
o
r
ea
ch
o
u
tp
u
t
(
e
m
is
s
io
n
lev
el)
b
u
t
al
s
o
an
e
s
ti
m
ate
o
f
th
e
u
n
ce
r
tain
t
y
(
co
n
f
id
en
ce
i
n
ter
v
a
l)
ass
o
cia
ted
w
it
h
th
a
t
p
r
ed
ictio
n
.
T
h
is
f
ea
t
u
r
e
o
f
GP
R
is
p
ar
ticu
lar
l
y
u
s
e
f
u
l
f
o
r
u
n
d
er
s
ta
n
d
in
g
t
h
e
r
eliab
ilit
y
o
f
th
e
m
o
d
el
’
s
esti
m
ate
s
u
n
d
er
v
ar
io
u
s
co
n
d
itio
n
s
.
2
.
4
.
M
o
del
dev
elo
p
m
ent
a
nd
t
ra
ini
ng
T
h
e
in
teg
r
ated
m
o
d
elin
g
ap
p
r
o
ac
h
w
a
s
d
ev
elo
p
ed
an
d
ev
alu
ated
u
s
i
n
g
M
A
T
L
A
B
(
n
eu
r
a
l
n
et
w
o
r
k
f
itti
n
g
to
o
l
(
NFT
to
o
l
)
f
o
r
A
N
N
tr
ain
i
n
g
,
co
m
b
i
n
ed
w
it
h
cu
s
to
m
r
o
u
ti
n
es
f
o
r
GP
R
)
.
T
w
el
v
e
in
p
u
t
p
ar
a
m
eter
s
w
er
e
s
elec
ted
as
m
o
d
el
f
ea
t
u
r
es
,
en
co
m
p
a
s
s
i
n
g
v
eh
icle
d
y
n
a
m
ics
a
n
d
en
v
ir
o
n
m
e
n
tal
co
n
d
itio
n
s
:
v
e
h
icl
e
s
p
ee
d
,
air
p
r
ess
u
r
e,
r
elativ
e
h
u
m
id
it
y
,
ab
s
o
lu
te
h
u
m
id
it
y
,
d
r
y
-
b
u
lb
air
te
m
p
er
atu
r
e,
wet
-
b
u
lb
te
m
p
er
atu
r
e,
d
e
w
p
o
in
t
te
m
p
er
atu
r
e,
ex
h
a
u
s
t
g
as
f
lo
w
v
o
lu
m
e,
ex
h
au
s
t
g
as
p
r
ess
u
r
e,
ex
h
a
u
s
t
g
as
te
m
p
er
atu
r
e,
ex
h
a
u
s
t
g
a
s
f
lo
w
r
ate,
an
d
a
co
r
r
ec
tio
n
f
ac
to
r
f
o
r
NOx
.
T
h
e
tar
g
et
o
u
tp
u
t
s
f
o
r
p
r
ed
ictio
n
w
er
e
th
e
e
m
is
s
io
n
co
n
ce
n
tr
atio
n
s
o
f
C
O,
C
O₂,
H
C
,
an
d
NOx
.
T
h
e
t
w
elv
e
c
h
o
s
e
n
in
p
u
t
p
ar
am
eter
s
w
er
e
j
u
s
ti
f
ied
:
v
e
h
icle
s
p
ee
d
af
f
ec
ts
lo
ad
,
h
u
m
id
it
y
/te
m
p
er
atu
r
e
i
n
f
lu
e
n
c
e
co
m
b
u
s
tio
n
ch
e
m
i
s
tr
y
,
a
n
d
ex
h
a
u
s
t
p
ar
a
m
eter
s
ca
p
tu
r
e
e
n
g
in
e
-
o
u
t
an
d
a
f
ter
-
tr
ea
t
m
e
n
t p
er
f
o
r
m
a
n
ce
.
Usi
n
g
t
h
e
A
N
N
NFT
o
o
l,
w
e
c
o
n
f
i
g
u
r
ed
a
f
ee
d
-
f
o
r
w
ar
d
n
eu
r
al
n
et
w
o
r
k
w
i
th
1
2
i
n
p
u
t
n
o
d
es,
a
s
i
n
g
l
e
h
id
d
en
la
y
er
co
n
ta
in
i
n
g
1
0
n
e
u
r
o
n
s
,
a
n
d
1
o
u
tp
u
t
n
o
d
e
(
f
o
r
ea
ch
e
m
i
s
s
io
n
v
ar
iab
le,
a
s
ep
ar
ate
n
et
w
o
r
k
w
as
tr
ain
ed
)
.
T
h
e
L
ev
e
n
b
er
g
-
Ma
r
q
u
ar
d
t
(
L
M)
al
g
o
r
ith
m
w
a
s
e
m
p
lo
y
ed
f
o
r
n
et
w
o
r
k
tr
ain
i
n
g
(
Fig
u
r
e
3
s
h
o
w
s
t
h
e
ch
o
s
en
n
et
w
o
r
k
ar
ch
itect
u
r
e)
.
T
h
e
d
ataset
co
n
s
is
ted
o
f
1
,
1
8
0
d
ata
p
o
in
ts
r
ec
o
r
d
e
d
f
r
o
m
th
e
d
r
iv
e
c
y
cle
ex
p
er
i
m
e
n
ts
;
w
e
p
ar
titi
o
n
ed
t
h
is
d
ata
i
n
to
7
0
%
f
o
r
tr
ai
n
in
g
,
1
5
%
f
o
r
v
al
id
atio
n
,
an
d
1
5
%
f
o
r
test
i
n
g
(
as
illu
s
tr
ated
in
Fi
g
u
r
e
4
)
.
T
h
e
L
M
tr
ain
in
g
al
g
o
r
ith
m
w
as
c
h
o
s
en
f
o
r
its
f
as
t
co
n
v
er
g
en
ce
a
n
d
ef
f
icie
n
t
m
e
m
o
r
y
u
s
a
g
e
(
Fig
u
r
e
5
d
ep
icts
th
e
tr
a
in
i
n
g
p
er
f
o
r
m
a
n
ce
cu
r
v
e
s
)
[
2
1
]
,
[
2
2
]
.
A
f
ter
tr
ain
i
n
g
t
h
e
A
N
N,
w
e
r
ec
o
r
d
e
d
th
e
m
ea
n
s
q
u
ar
ed
er
r
o
r
(
MSE
)
an
d
co
ef
f
ic
ien
t
o
f
d
eter
m
in
a
t
io
n
(
R²
)
o
n
th
e
tr
ain
in
g
an
d
v
alid
atio
n
s
et
s
as
p
r
eli
m
in
ar
y
p
er
f
o
r
m
a
n
ce
in
d
i
ca
to
r
s
.
A
d
d
itio
n
all
y
,
th
e
tr
ai
n
ed
m
o
d
els
w
er
e
ev
al
u
ated
o
n
th
e
in
d
ep
en
d
e
n
t
test
d
ataset
u
s
i
n
g
R
MSE
a
n
d
MA
E
to
q
u
an
t
if
y
p
r
ed
ictiv
e
p
er
f
o
r
m
an
ce
[
2
3
]
,
[
2
4
]
.
T
h
ese
v
alid
atio
n
m
etr
ics
,
to
g
eth
er
w
it
h
R
²,
p
r
o
v
id
e
a
c
o
m
p
r
e
h
en
s
iv
e
as
s
es
s
m
en
t
:
R
MSE
an
d
MA
E
m
ea
s
u
r
e
th
e
av
er
ag
e
d
ev
iatio
n
o
f
p
r
ed
ictio
n
s
f
r
o
m
ac
tu
al
v
al
u
e
s
(
w
it
h
R
MSE
g
i
v
i
n
g
g
r
ea
ter
w
eig
h
t
to
lar
g
er
er
r
o
r
s
)
,
w
h
e
r
ea
s
R
²
r
ef
lects
th
e
p
r
o
p
o
r
tio
n
o
f
em
i
s
s
io
n
v
ar
ian
ce
ex
p
lain
ed
b
y
t
h
e
m
o
d
el.
Af
ter
tr
ain
i
n
g
,
th
e
r
es
u
lti
n
g
A
N
N
m
o
d
el
p
r
o
v
id
es
p
o
in
t p
r
ed
ictio
n
s
f
o
r
e
m
i
s
s
io
n
s
b
u
t d
o
es n
o
t in
h
er
en
tl
y
q
u
an
tify
p
r
ed
ictio
n
u
n
ce
r
tain
t
y
.
Fig
u
r
e
3
.
Size
o
f
th
e
n
et
w
o
r
k
f
o
r
m
ed
Fo
r
th
e
GP
R
m
o
d
el,
th
e
s
a
m
e
tr
ain
i
n
g
a
n
d
tes
t
d
ataset
s
w
er
e
u
s
ed
to
lear
n
th
e
r
elatio
n
s
h
i
p
b
et
w
ee
n
th
e
i
n
p
u
t
f
ea
t
u
r
es
a
n
d
ea
ch
e
m
is
s
io
n
o
u
tp
u
t.
T
h
e
GP
R
w
a
s
co
n
f
i
g
u
r
ed
w
it
h
a
p
o
l
y
n
o
m
ial
k
er
n
el
an
d
o
p
tim
ized
h
y
p
er
p
ar
a
m
eter
s
to
b
alan
ce
b
ias
an
d
v
ar
ian
ce
f
o
r
th
e
g
i
v
en
d
ata.
T
r
ain
in
g
t
h
e
GP
R
m
o
d
el
y
ield
s
a
p
r
ed
ictiv
e
m
ea
n
f
u
n
c
tio
n
(
w
h
ich
g
i
v
es
th
e
e
m
is
s
io
n
e
s
ti
m
a
te)
an
d
a
n
as
s
o
ciate
d
s
ta
n
d
ar
d
d
ev
iatio
n
(
w
h
ic
h
ca
n
b
e
tr
an
s
lated
i
n
to
a
p
r
ed
ict
io
n
in
ter
v
al
f
o
r
u
n
ce
r
tai
n
t
y
q
u
an
ti
f
icatio
n
)
[
2
5
]
,
[
2
6
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
23
,
No
.
6
,
Dec
em
b
er
20
25
:
1
5
4
3
-
1
554
1548
Fig
u
r
e
4
.
Me
n
u
a
n
d
test
d
ata
Fig
u
r
e
5
.
Net
w
o
r
k
tr
ai
n
i
n
g
r
es
u
lts
Fin
all
y
,
w
e
co
m
b
in
ed
th
e
s
tr
en
g
t
h
s
o
f
b
o
th
m
o
d
els
:
th
e
ANN
w
as
u
s
ed
to
ca
p
tu
r
e
th
e
u
n
d
er
l
y
in
g
n
o
n
li
n
ea
r
m
ap
p
in
g
f
r
o
m
in
p
u
ts
to
e
m
i
s
s
io
n
o
u
tp
u
ts
,
a
n
d
t
h
e
GP
R
w
as
ap
p
lied
i
n
p
ar
allel
to
esti
m
ate
t
h
e
u
n
ce
r
tai
n
t
y
o
f
th
o
s
e
p
r
e
d
ictio
n
s
.
T
h
e
p
er
f
o
r
m
a
n
ce
o
f
t
h
e
h
y
b
r
id
A
NN
-
GP
R
ap
p
r
o
ac
h
w
as
th
e
n
v
alid
ated
o
n
th
e
test
s
et.
W
e
ev
al
u
ated
th
e
m
o
d
el
’
s
g
e
n
er
aliza
tio
n
b
y
co
m
p
ar
i
n
g
p
r
ed
icted
e
m
is
s
io
n
v
al
u
es
a
g
ain
s
t
th
e
ac
tu
al
m
ea
s
u
r
ed
v
a
lu
e
s
f
o
r
th
e
test
d
ata,
u
s
i
n
g
R
MSE
,
M
AE
,
an
d
R
²
a
s
k
e
y
p
er
f
o
r
m
a
n
c
e
m
etr
ic
s
.
Hi
g
h
R
²
v
alu
e
s
alo
n
g
s
id
e
lo
w
R
M
SE
an
d
M
A
E
o
n
t
h
e
te
s
t
s
et
w
o
u
ld
s
er
v
e
a
s
e
m
p
ir
ical
ev
id
en
ce
t
h
at
t
h
e
m
o
d
el
ac
cu
r
atel
y
ca
p
t
u
r
es
e
m
is
s
io
n
p
atter
n
s
,
w
h
ile
t
h
e
GP
R
’
s
o
u
t
p
u
t
p
r
o
v
id
es
in
s
i
g
h
t
in
to
t
h
e
co
n
f
id
e
n
ce
o
f
ea
c
h
p
r
ed
ictio
n
.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
3
.
1
.
M
o
del
perf
o
r
m
a
nce
a
nd
ev
a
lua
t
io
n
T
h
e
p
er
f
o
r
m
an
ce
o
f
t
h
e
A
N
N
an
d
GP
R
m
o
d
els
w
a
s
ev
a
lu
ated
u
s
in
g
s
e
v
er
al
m
etr
ic
s
,
in
clu
d
i
n
g
R
MSE
,
M
A
E
,
an
d
t
h
e
co
ef
f
ici
en
t
o
f
d
eter
m
in
at
io
n
(
R
²)
[
2
7
]
,
[
2
8
]
.
Fo
r
th
ese
m
etr
ic
s
,
lo
w
er
R
MSE
an
d
M
A
E
v
alu
e
s
co
r
r
esp
o
n
d
to
m
o
r
e
ac
cu
r
ate
p
r
ed
ictio
n
s
,
an
d
th
e
R
²
v
alu
e
clo
s
er
to
1
s
h
o
w
th
at
t
h
e
m
o
d
el
ex
p
lain
s
a
lar
g
er
p
o
r
tio
n
o
f
th
e
v
ar
ia
n
ce
in
t
h
e
e
m
i
s
s
io
n
d
ata.
T
h
e
m
o
d
els
w
er
e
v
alid
ated
u
s
in
g
t
h
e
h
eld
-
o
u
t
te
s
t
d
ataset
to
ass
ess
p
r
ed
ictiv
e
p
er
f
o
r
m
a
n
ce
f
o
r
ea
ch
p
o
llu
ta
n
t,
an
d
t
h
eir
r
esu
lts
w
er
e
co
m
p
ar
ed
ag
ain
s
t
ea
c
h
o
th
er
as
w
ell
a
s
ag
ai
n
s
t e
x
p
ec
tatio
n
s
f
r
o
m
tr
ad
itio
n
al
m
o
d
eli
n
g
ap
p
r
o
ac
h
es.
B
en
ch
m
ar
k
i
n
g
w
as
also
co
n
d
u
cted
w
it
h
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
(
SVM
)
,
r
an
d
o
m
f
o
r
est,
a
n
d
g
r
ad
ien
t
b
o
o
s
tin
g
m
o
d
els.
T
h
ese
alter
n
ativ
es
p
er
f
o
r
m
ed
ad
eq
u
atel
y
b
u
t
w
er
e
less
ac
c
u
r
ate
an
d
m
o
r
e
co
m
p
u
tatio
n
all
y
ex
p
en
s
iv
e
t
h
an
t
h
e
ANN
-
GP
R
h
y
b
r
id
,
r
ein
f
o
r
ci
n
g
t
h
e
s
u
p
er
io
r
ity
o
f
th
e
p
r
o
p
o
s
ed
m
eth
o
d
.
I
n
s
tan
ce
s
o
f
u
n
d
er
p
er
f
o
r
m
a
n
ce
(
e.
g
.
,
NO
x
s
p
ik
e
s
d
u
r
i
n
g
ac
ce
ler
atio
n
)
in
d
icate
u
n
m
o
d
eled
ca
tal
y
s
t
ef
f
icie
n
c
y
;
th
e
s
e
in
s
i
g
h
ts
ca
n
g
u
id
e
s
e
n
s
o
r
o
r
f
e
atu
r
e
ex
p
a
n
s
io
n
.
R
²
v
al
u
e
s
clo
s
e
to
0
.
9
9
9
m
ea
n
t
h
at
th
e
m
o
d
el
al
m
o
s
t
p
er
f
ec
tl
y
r
ep
licates
e
m
i
s
s
io
n
d
y
n
a
m
ic
s
.
I
n
p
r
ac
tice,
th
is
ac
cu
r
ac
y
e
n
s
u
r
es
e
m
is
s
io
n
co
n
tr
o
l
s
y
s
t
e
m
s
i
n
HE
V
s
ca
n
an
ticip
ate
p
o
llu
ta
n
t sp
i
k
es a
n
d
co
m
p
l
y
w
it
h
E
u
r
o
6
/7
s
tan
d
ar
d
s
.
T
ab
le
1
p
r
esen
ts
a
q
u
a
n
titati
v
e
co
m
p
ar
is
o
n
b
et
w
ee
n
th
e
A
NN
b
ased
m
o
d
el
an
d
t
h
e
GP
R
m
o
d
el
f
o
r
ea
ch
p
o
llu
ta
n
t.
T
h
e
R
²
v
al
u
e
s
in
t
h
is
T
ab
le
1
in
d
icate
ea
ch
m
o
d
el
’
s
ab
ilit
y
to
ex
p
lai
n
v
ar
i
an
ce
i
n
t
h
e
e
m
is
s
io
n
d
ata,
w
h
ile
t
h
e
MSE
p
r
o
v
id
es
a
m
ea
s
u
r
e
o
f
p
r
ed
ictio
n
er
r
o
r
.
T
h
e
GP
R
m
o
d
el
co
n
s
i
s
ten
t
l
y
o
u
tp
er
f
o
r
m
ed
th
e
A
N
N
m
o
d
el
ac
r
o
s
s
a
ll
p
o
llu
ta
n
ts
,
a
s
ev
id
en
ce
d
b
y
h
i
g
h
er
R
²
an
d
lo
w
er
er
r
o
r
v
alu
es.
T
h
e
s
u
b
s
ta
n
tial
l
y
lo
w
er
MSE
v
al
u
es
f
o
r
GP
R
(
esp
ec
iall
y
n
o
tab
le
in
C
O₂
a
n
d
NOx
p
r
ed
ictio
n
s
)
h
i
g
h
li
g
h
t
it
s
s
u
p
er
io
r
ac
cu
r
ac
y
.
Ov
er
all,
GP
R
p
r
o
v
id
ed
m
o
r
e
r
eliab
le
esti
m
atio
n
s
w
it
h
lo
w
e
r
p
r
e
d
ictio
n
er
r
o
r
s
,
m
ak
i
n
g
it
a
r
o
b
u
s
t
ch
o
ice
f
o
r
e
m
is
s
io
n
m
o
d
elin
g
i
n
th
i
s
co
n
t
ex
t.
T
ab
le
1
.
C
o
m
p
ar
is
o
n
b
et
w
ee
n
GP
R
an
d
A
N
N
r
esu
lt
Emi
ssi
o
n
M
e
t
h
o
d
M
S
E
R
2
CO
G
P
R
0
.
1
4
7
9
0
.
9
9
9
A
N
N
1
7
.
6
8
7
3
0
.
9
8
2
CO
2
G
P
R
4
1
1
.
2
5
5
8
0
.
9
9
7
A
N
N
2
0
3
2
0
5
.
3
1
6
7
9
0
.
9
6
7
N
O
x
G
P
R
0
.
1
4
3
5
0
.
9
9
9
A
N
N
2
4
5
.
5
8
2
9
3
0
.
9
8
7
HC
G
P
R
3
7
.
6
4
8
3
0
.
9
9
6
A
N
N
0
.
1
4
1
5
3
9
0
.
9
9
5
(
N
o
t
e
:
C
O
,
C
O
₂,
N
O
x
a
n
d
H
C
e
mi
ssi
o
n
s v
a
l
u
e
s i
n
p
p
m)
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
A
p
p
lica
tio
n
o
f a
r
tifi
cia
l in
tellig
en
ce
in
emiss
io
n
p
r
ed
ictio
n
f
o
r
h
yb
r
id
elec
tr
ic
ve
h
icles:
…
(
Heru
P
r
iya
n
to
)
1549
3
.
2
.
P
re
dict
io
n
a
cc
ura
cy
a
n
d t
re
nd
s
B
ey
o
n
d
th
e
ag
g
r
eg
a
te
er
r
o
r
m
etr
ics,
t
h
e
m
o
d
els
’
b
eh
a
v
io
r
o
v
er
ti
m
e
an
d
ac
r
o
s
s
d
r
iv
i
n
g
co
n
d
itio
n
s
w
a
s
ex
a
m
in
ed
.
Fi
g
u
r
e
s
6
to
9
illu
s
tr
ate
t
h
e
m
ea
s
u
r
ed
v
s
.
p
r
ed
icted
em
is
s
io
n
tr
aj
ec
to
r
ies
f
o
r
C
O,
C
O₂,
HC
,
an
d
NOx
,
r
esp
ec
ti
v
el
y
,
o
v
er
t
h
e
co
u
r
s
e
o
f
th
e
u
r
b
an
a
n
d
E
UDC
.
T
h
e
C
O
e
m
is
s
io
n
p
r
ed
ictio
n
s
s
h
o
w
t
h
at
t
h
e
h
y
b
r
id
A
NN
-
GP
R
m
o
d
el
s
u
cc
ess
f
u
l
l
y
ca
p
t
u
r
es
t
h
e
f
l
u
ct
u
ati
o
n
p
atter
n
s
o
b
s
er
v
ed
i
n
th
e
ac
tu
al
m
ea
s
u
r
e
m
e
n
t
s
f
o
r
b
o
th
d
r
iv
e
c
y
cle
s
.
T
h
e
p
r
ed
ictiv
e
tr
ac
es
clo
s
el
y
f
o
ll
o
w
t
h
e
r
ea
l
e
m
i
s
s
io
n
c
u
r
v
es
,
w
i
th
o
n
l
y
m
i
n
o
r
d
ev
iatio
n
s
.
T
h
ese
s
m
all
d
is
cr
ep
an
cies
ca
n
b
e
attr
ib
u
ted
to
ex
ter
n
al
e
n
v
ir
o
n
m
e
n
tal
f
ac
to
r
s
(
s
u
c
h
a
s
tr
an
s
ien
t
ch
an
g
es
in
te
m
p
er
at
u
r
e
o
r
p
r
ess
u
r
e)
th
at
w
er
e
n
o
t
f
u
ll
y
c
ap
tu
r
ed
b
y
th
e
m
o
d
el
i
n
p
u
ts
.
Ov
er
all,
t
h
e
h
i
g
h
ag
r
ee
m
e
n
t
b
et
w
ee
n
p
r
ed
icted
an
d
o
b
s
er
v
ed
C
O
v
alu
es
co
n
f
ir
m
s
th
e
m
o
d
el
’
s
ef
f
ec
ti
v
e
n
ess
in
lear
n
i
n
g
th
e
e
m
is
s
io
n
d
y
n
a
m
ic
s
o
f
HE
V
o
p
er
atio
n
.
Si
m
i
lar
l
y
,
f
o
r
C
O₂
e
m
i
s
s
io
n
s
,
th
r
o
u
g
h
o
u
t
t
h
e
d
r
iv
i
n
g
c
y
cle
s
,
th
e
m
o
d
el
’
s
p
r
ed
ictio
n
s
c
lo
s
el
y
m
atc
h
th
e
e
m
p
ir
ical
d
ata.
I
n
p
ar
ticu
lar
,
th
e
GP
R
co
m
p
o
n
en
t
o
f
t
h
e
m
o
d
el
p
r
o
v
id
es
co
n
f
id
en
c
e
in
ter
v
als
(
s
h
ad
ed
r
eg
io
n
s
i
n
Fi
g
u
r
e
7
)
th
at
r
e
m
a
in
n
ar
r
o
w
in
m
o
s
t
s
e
g
m
en
ts
,
i
n
d
icatin
g
h
ig
h
ce
r
tai
n
t
y
i
n
t
h
e
p
r
ed
ictio
n
s
.
E
v
en
d
u
r
in
g
s
e
g
m
en
t
s
w
h
er
e
th
e
v
eh
icle
tr
a
n
s
itio
n
ed
b
et
w
ee
n
u
r
b
an
an
d
ex
tr
a
-
u
r
b
a
n
p
h
ase
s
(
w
h
ich
ca
n
ca
u
s
e
s
ig
n
i
f
ica
n
t
v
ar
iab
ilit
y
in
C
O₂
o
u
tp
u
t
d
u
e
to
ch
a
n
g
in
g
e
n
g
i
n
e
lo
ad
s
an
d
r
eg
e
n
er
ativ
e
b
r
ak
in
g
i
n
th
e
HE
V)
,
th
e
m
o
d
el
m
ai
n
tai
n
ed
ac
c
u
r
ate
es
ti
m
ate
s
.
T
h
is
p
er
f
o
r
m
a
n
ce
r
e
f
l
ec
ts
t
h
e
m
o
d
el
’
s
ab
il
it
y
to
ac
c
o
u
n
t
f
o
r
v
ar
iat
io
n
s
in
co
m
b
u
s
tio
n
ef
f
icie
n
c
y
a
n
d
en
er
g
y
m
a
n
a
g
e
m
en
t b
et
w
ee
n
d
if
f
er
e
n
t d
r
iv
i
n
g
r
e
g
i
m
es.
Fo
r
HC
an
d
NOx
e
m
is
s
io
n
s
,
th
e
h
y
b
r
id
m
o
d
el
ag
ain
d
e
m
o
n
s
tr
ates
s
tr
o
n
g
p
r
ed
i
ctiv
e
ca
p
ab
ilit
ies.
T
h
e
p
r
ed
icted
HC
lev
els
Fig
u
r
e
8
tr
ac
k
th
e
m
ea
s
u
r
ed
d
ata
w
ell,
ca
p
tu
r
i
n
g
r
ap
id
ch
an
g
e
s
th
at
o
cc
u
r
d
u
r
in
g
ac
ce
ler
atio
n
an
d
d
ec
eler
atio
n
ev
en
t
s
.
T
h
e
GP
R
u
n
ce
r
tain
t
y
b
o
u
n
d
s
f
o
r
HC
ar
e
s
li
g
h
tl
y
wid
er
d
u
r
in
g
ce
r
tai
n
h
ig
h
v
ar
iab
ilit
y
s
e
g
m
e
n
ts
,
s
u
g
g
e
s
ti
n
g
th
a
t
th
e
m
o
d
el
r
i
g
h
t
l
y
ex
p
r
es
s
es
le
s
s
co
n
f
id
en
ce
i
n
p
r
ed
ictio
n
s
u
n
d
er
th
o
s
e
tr
an
s
ie
n
t
co
n
d
itio
n
s
p
o
ten
tiall
y
d
u
e
to
u
n
m
o
d
eled
f
ac
to
r
s
lik
e
ca
tal
y
s
t
ef
f
icie
n
c
y
v
a
r
iatio
n
.
I
n
th
e
ca
s
e
o
f
NOx
Fi
g
u
r
e
9
,
th
e
m
o
d
el
’
s
p
r
ed
ictio
n
s
n
o
t
o
n
l
y
f
o
llo
w
t
h
e
ac
tu
al
e
m
i
s
s
io
n
tr
en
d
b
u
t
als
o
h
ig
h
lig
h
t
s
p
ec
i
f
ic
p
o
in
ts
i
n
th
e
d
r
i
v
e
c
y
cle
w
h
er
e
u
n
ce
r
tai
n
t
y
is
e
lev
ated
.
T
h
ese
t
y
p
icall
y
co
r
r
esp
o
n
d
to
in
s
t
an
ce
s
o
f
a
g
g
r
ess
iv
e
ac
ce
ler
atio
n
o
r
h
ig
h
en
g
i
n
e
l
o
ad
,
w
h
ic
h
ar
e
k
n
o
w
n
to
p
r
o
d
u
ce
s
p
ik
e
s
in
N
Ox
e
m
i
s
s
io
n
s
.
I
d
en
tify
i
n
g
th
e
s
e
r
eg
io
n
s
o
f
h
ig
h
er
u
n
ce
r
tai
n
t
y
is
v
al
u
ab
le:
it
in
d
icate
s
w
h
er
e
th
e
m
o
d
el
(
a
n
d
b
y
ex
ten
s
io
n
,
e
m
is
s
io
n
s
co
n
tr
o
l
s
y
s
te
m
s
)
m
i
g
h
t
n
ee
d
to
p
ay
e
x
tr
a
atten
t
io
n
o
r
w
h
er
e
ad
d
iti
o
n
al
s
en
s
o
r
in
p
u
t
s
m
i
g
h
t
b
e
r
eq
u
ir
ed
to
im
p
r
o
v
e
ac
cu
r
ac
y
.
Fig
u
r
e
6
. Me
asu
r
e
m
en
t a
n
d
p
r
ed
ictio
n
g
r
ap
h
s
o
f
C
O
e
m
is
s
io
n
s
Fig
u
r
e
7
.
Me
asu
r
e
m
en
t a
n
d
p
r
ed
ictio
n
g
r
ap
h
s
o
f
C
O
2
e
m
is
s
io
n
s
Fig
u
r
e
8
.
Me
asu
r
e
m
en
t a
n
d
p
r
ed
ictio
n
g
r
ap
h
s
o
f
HC
e
m
is
s
io
n
s
Fig
u
r
e
9
.
Me
asu
r
e
m
en
t a
n
d
p
r
ed
ictio
n
g
r
ap
h
s
o
f
NOx
e
m
is
s
io
n
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
23
,
No
.
6
,
Dec
em
b
er
20
25
:
1
5
4
3
-
1
554
1550
3
.
3
.
Uncer
t
a
inty
a
na
ly
s
is
A
d
is
tin
c
t
ad
v
an
tag
e
o
f
th
e
GP
R
co
m
p
o
n
en
t
is
it
s
ab
ilit
y
to
q
u
an
tify
p
r
ed
ictiv
e
u
n
ce
r
tain
t
y
.
T
o
ev
alu
a
te
th
is
asp
ec
t,
t
h
e
p
r
ed
ictio
n
u
n
ce
r
tain
ties
o
f
th
e
A
N
N
an
d
GP
R
m
o
d
el
s
w
er
e
co
m
p
ar
ed
f
o
r
ea
c
h
p
o
llu
tan
t,
as
s
u
m
m
ar
ized
in
T
ab
le
2
t
h
e
GP
R
m
o
d
el
d
em
o
n
s
tr
at
ed
co
n
s
is
te
n
tl
y
lo
w
er
u
n
c
er
tain
t
y
(
n
ar
r
o
w
er
p
r
ed
ictio
n
in
ter
v
al
s
)
ac
r
o
s
s
a
ll
p
o
llu
tan
ts
co
m
p
ar
ed
to
th
e
A
NN
m
o
d
el,
r
ein
f
o
r
cin
g
th
e
r
eliab
ilit
y
o
f
t
h
e
in
te
g
r
ated
ap
p
r
o
ac
h
in
e
m
i
s
s
i
o
n
m
o
d
elli
n
g
[
2
9
]
,
[
3
0
]
.
T
h
ese
r
esu
lt
s
s
h
o
w
th
a
t
n
o
t
o
n
l
y
d
o
es
GP
R
ac
h
iev
e
h
ig
h
er
ac
cu
r
ac
y
,
b
u
t
it
also
p
r
o
v
id
es
m
o
r
e
co
n
f
id
e
n
ce
in
ea
ch
p
r
ed
ictio
n
,
an
im
p
o
r
tan
t
co
n
s
id
er
atio
n
f
o
r
p
r
ac
tical
ap
p
licatio
n
s
.
T
ab
le
2
.
C
o
m
p
ar
is
o
n
o
f
u
n
ce
r
t
ain
t
y
r
e
s
u
l
t
Emi
ssi
o
n
M
e
t
h
o
d
U
n
c
e
r
t
a
i
n
t
y
(
p
p
m)
CO
G
P
R
±
0
.
8
2
9
A
N
N
±
1
.
2
3
7
HC
G
P
R
±
9
.
9
7
8
A
N
N
±
1
3
.
7
5
6
N
O
x
G
P
R
±
0
.
1
4
4
A
N
N
±
0
.
1
9
9
CO
2
G
P
R
±
4
1
1
.
2
5
6
A
N
N
±
4
2
6
.
7
6
3
B
ein
g
ab
le
to
q
u
an
ti
f
y
u
n
ce
r
t
ain
t
y
is
p
ar
ticu
lar
l
y
v
al
u
ab
le
f
o
r
r
eg
u
lato
r
y
a
n
d
o
p
er
atio
n
al
p
u
r
p
o
s
es.
P
o
licy
m
ak
er
s
ca
n
u
tili
ze
t
h
es
e
in
s
i
g
h
ts
to
r
ef
i
n
e
v
e
h
icle
e
m
is
s
io
n
s
tan
d
ar
d
s
an
d
d
ev
elo
p
tar
g
eted
m
iti
g
atio
n
s
tr
ateg
ie
s
f
o
r
h
i
g
h
-
e
m
is
s
io
n
s
ce
n
ar
io
s
.
Fo
r
in
s
ta
n
ce
,
if
th
e
m
o
d
el
id
en
ti
f
ie
s
a
ce
r
tai
n
d
r
iv
in
g
co
n
d
itio
n
t
h
at
lead
s
to
h
i
g
h
u
n
ce
r
tain
t
y
i
n
N
Ox
p
r
ed
ictio
n
s
,
r
eg
u
lato
r
s
m
i
g
h
t
in
v
es
tig
a
te
th
a
t
s
ce
n
ar
io
f
u
r
th
er
o
r
s
et
s
p
ec
if
i
c
g
u
id
eli
n
e
s
to
m
a
n
ag
e
it.
A
u
t
o
m
o
t
i
v
e
m
a
n
u
f
ac
tu
r
er
s
an
d
en
g
i
n
ee
r
s
ca
n
also
lev
er
a
g
e
an
u
n
ce
r
ta
in
t
y
-
a
w
ar
e
m
o
d
el
to
i
m
p
r
o
v
e
r
ea
l
-
ti
m
e
em
is
s
io
n
co
n
tr
o
l
s
y
s
te
m
s
in
H
E
Vs
,
en
s
u
r
in
g
t
h
at
th
e
v
eh
icle
’
s
co
n
tr
o
l
alg
o
r
it
h
m
s
ac
co
u
n
t
f
o
r
co
n
d
itio
n
s
w
h
e
r
e
em
i
s
s
io
n
s
ar
e
less
p
r
ed
ictab
le.
I
n
s
u
m
m
ar
y
,
in
co
r
p
o
r
atin
g
GP
R
-
b
ased
u
n
ce
r
tai
n
t
y
a
n
al
y
s
is
ad
d
s
a
lay
er
o
f
tr
an
s
p
ar
en
c
y
a
n
d
r
o
b
u
s
tn
ess
to
e
m
is
s
io
n
p
r
ed
ictio
n
th
at
p
u
r
el
y
d
eter
m
in
i
s
tic
m
o
d
els
(
li
k
e
a
s
tan
d
ar
d
A
NN)
w
o
u
ld
lack
.
T
a
b
le
2
p
r
ed
ictiv
e
u
n
ce
r
tain
t
y
c
o
m
p
ar
is
o
n
b
et
w
ee
n
GP
R
an
d
A
NN
m
o
d
els
f
o
r
ea
ch
p
o
l
lu
ta
n
t
.
(
U
n
ce
r
tain
t
y
v
al
u
es
r
ep
r
ese
n
t
an
ap
p
r
o
x
i
m
ate
±
r
an
g
e
ar
o
u
n
d
t
h
e
p
r
ed
icted
m
ea
n
)
.
C
o
m
p
ar
ed
w
it
h
p
r
ev
io
u
s
w
o
r
k
s
,
th
is
s
t
u
d
y
ad
v
a
n
ce
s
t
h
e
lit
er
atu
r
e
b
y
co
m
b
i
n
i
n
g
A
N
N’
s
n
o
n
li
n
ea
r
m
ap
p
in
g
ca
p
ab
ilit
y
w
it
h
GP
R
’
s
s
tr
e
n
g
th
i
n
u
n
ce
r
tai
n
t
y
q
u
a
n
ti
f
icatio
n
.
GP
R
’
s
s
u
p
er
io
r
it
y
f
o
r
C
O₂
p
r
ed
ictio
n
in
h
y
b
r
id
s
a
n
d
p
o
ten
tial
in
la
b
o
r
ato
r
y
en
g
i
n
e
s
,
th
e
p
r
esen
t
s
tu
d
y
e
x
te
n
d
s
th
e
s
e
in
s
ig
h
t
s
t
o
r
ea
l
-
w
o
r
ld
h
y
b
r
id
co
n
d
itio
n
s
[
2
7
]
,
[
3
1
]
,
[
3
2
]
.
Ov
er
all,
th
e
i
n
te
g
r
ated
A
NN
-
G
P
R
m
o
d
el
s
h
o
w
s
s
tr
o
n
g
p
o
te
n
tial
as
a
d
ec
is
io
n
-
s
u
p
p
o
r
t
to
o
l
f
o
r
e
m
is
s
io
n
r
eg
u
la
tio
n
,
ad
ap
tiv
e
co
n
tr
o
l
s
tr
ateg
ie
s
,
an
d
s
u
s
tai
n
ab
le
v
eh
ic
le
tec
h
n
o
lo
g
y
d
ev
elo
p
m
en
t.
3
.
4
.
L
i
m
it
a
t
io
ns
a
nd
f
uture
w
o
rk
T
h
e
p
r
o
p
o
s
ed
A
NN
-
GP
R
e
m
i
s
s
io
n
p
r
ed
ictio
n
m
o
d
el
s
h
o
w
s
p
r
o
m
i
s
e,
b
u
t
s
e
v
er
al
li
m
i
tatio
n
s
r
e
m
ai
n
.
I
t
w
as
tr
ai
n
ed
an
d
test
ed
o
n
l
y
o
n
o
n
e
HE
V
m
o
d
el
(
T
o
y
o
ta
P
r
iu
s
)
u
n
d
er
s
p
ec
if
ic
u
r
b
a
n
an
d
ex
tr
a
-
u
r
b
an
c
y
c
les,
li
m
it
in
g
its
g
e
n
er
aliza
b
ilit
y
t
o
o
th
er
v
eh
icles
o
r
co
n
d
itio
n
s
s
u
c
h
as
r
u
r
al
d
r
iv
in
g
,
h
i
g
h
-
s
p
ee
d
cr
u
is
i
n
g
,
o
r
ex
tr
e
m
e
w
ea
t
h
er
.
Fu
r
t
h
er
m
o
r
e
,
v
alid
atio
n
r
elied
o
n
UN
E
C
E
R
8
3
s
tan
d
ar
d
s
,
w
h
ich
m
a
y
n
o
t
r
ep
r
esen
t
g
lo
b
al
d
r
iv
in
g
c
y
cles.
An
o
th
er
ch
all
en
g
e
lie
s
in
th
e
co
m
p
u
tatio
n
a
l
in
ten
s
it
y
o
f
GP
R
,
w
h
ich
co
u
ld
h
in
d
er
r
ea
l
-
ti
m
e
ap
p
licatio
n
s
as d
ata
s
ize
i
n
cr
ea
s
es.
Fu
t
u
r
e
r
esear
ch
s
h
o
u
ld
ad
d
r
ess
t
h
ese
co
n
s
tr
ai
n
ts
b
y
ex
p
a
n
d
in
g
d
atase
ts
to
i
n
cl
u
d
e
m
u
lt
ip
le
HE
V
t
y
p
es,
ad
d
itio
n
al
d
r
i
v
in
g
c
y
cle
s
,
an
d
e
x
tr
e
m
e
e
n
v
ir
o
n
m
en
tal
co
n
d
itio
n
s
.
B
r
o
ad
er
d
ata
co
v
er
ag
e,
alig
n
ed
w
it
h
in
ter
n
a
tio
n
al
s
ta
n
d
ar
d
s
,
w
o
u
ld
im
p
r
o
v
e
r
o
b
u
s
t
n
ess
ac
r
o
s
s
r
eg
io
n
s
.
On
th
e
co
m
p
u
ta
tio
n
al
s
i
d
e,
ap
p
ly
i
n
g
s
p
ar
s
e
o
r
ap
p
r
o
x
i
m
ate
GP
R
m
eth
o
d
s
(
e.
g
.
,
i
n
d
u
ci
n
g
p
o
in
t
ap
p
r
o
x
i
m
atio
n
s
)
co
u
ld
s
ig
n
i
f
ica
n
tl
y
r
ed
u
ce
co
m
p
lex
it
y
w
h
ile
m
ai
n
tai
n
in
g
ac
c
u
r
ac
y
.
Mo
r
eo
v
er
,
ex
p
lo
r
in
g
h
y
b
r
id
f
r
a
m
e
w
o
r
k
s
s
u
ch
a
s
A
NN
-
b
a
y
e
s
ian
n
eu
r
al
n
et
w
o
r
k
(
B
NN)
o
r
A
NN
-
lo
n
g
s
h
o
r
t
-
ter
m
m
e
m
o
r
y
(
L
ST
M)
w
o
u
ld
e
n
r
ich
u
n
ce
r
tai
n
t
y
esti
m
at
io
n
a
n
d
ca
p
tu
r
e
te
m
p
o
r
al
d
ep
en
d
en
cies,
o
f
f
er
in
g
s
tr
o
n
g
er
p
r
ed
ictiv
e
ca
p
ab
ilit
ies f
o
r
em
is
s
io
n
d
y
n
a
m
ic
s
.
An
o
th
er
i
m
p
o
r
tan
t
d
ir
ec
tio
n
is
th
e
in
te
g
r
atio
n
o
f
ad
ap
tiv
e
le
ar
n
in
g
m
ec
h
a
n
is
m
s
.
A
n
o
n
b
o
a
r
d
s
y
s
te
m
th
at
u
p
d
ates
its
el
f
w
ith
r
ea
l
-
ti
m
e
s
en
s
o
r
d
ata
w
o
u
ld
allo
w
t
h
e
m
o
d
el
to
m
ai
n
tai
n
ac
cu
r
ac
y
as
v
eh
icle
s
ag
e
o
r
en
co
u
n
ter
n
e
w
co
n
d
itio
n
s
.
S
u
c
h
a
d
a
p
t
a
b
il
i
ty
c
o
u
l
d
r
e
d
u
c
e
u
n
c
e
r
ta
in
ty
d
u
r
in
g
a
ty
p
i
c
al
s
c
en
a
r
i
o
s
a
n
d
en
h
an
c
e
p
r
e
d
i
c
t
iv
e
r
el
i
a
b
il
i
ty
.
U
lt
im
a
te
ly
,
b
r
o
a
d
en
in
g
d
at
a
s
c
o
p
e
,
im
p
r
o
v
in
g
ef
f
ic
i
en
cy
,
an
d
en
a
b
l
in
g
a
d
a
p
t
iv
e
l
e
a
r
n
in
g
w
il
l
s
t
r
en
g
th
en
th
e
m
o
d
el
’
s
a
p
p
l
i
c
a
b
i
li
ty
f
o
r
r
e
a
l
-
w
o
r
l
d
em
is
s
i
o
n
c
o
n
t
r
o
l
an
d
s
u
s
ta
in
a
b
l
e
t
r
a
n
s
p
o
r
t
a
t
i
o
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
A
p
p
lica
tio
n
o
f a
r
tifi
cia
l in
tellig
en
ce
in
emiss
io
n
p
r
ed
ictio
n
f
o
r
h
yb
r
id
elec
tr
ic
ve
h
icles:
…
(
Heru
P
r
iya
n
to
)
1551
4.
CO
NCLU
SI
O
N
T
h
is
s
tu
d
y
d
ev
elo
p
ed
an
d
v
alid
ated
an
in
te
g
r
ated
A
NN
-
GP
R
f
r
a
m
e
w
o
r
k
f
o
r
p
r
ed
ictin
g
m
u
lti
-
p
o
llu
tan
t
e
m
is
s
io
n
s
i
n
HEV
u
n
d
er
s
tan
d
ar
d
d
r
iv
in
g
c
y
cle
s
.
T
h
e
r
esu
lts
s
h
o
w
ed
th
at
A
NN
w
as
ab
le
to
ca
p
tu
r
e
g
en
er
al
e
m
i
s
s
io
n
tr
en
d
s
,
b
u
t
GP
R
co
n
s
i
s
ten
tl
y
o
u
tp
er
f
o
r
m
e
d
it
w
ith
h
i
g
h
er
co
ef
f
icie
n
ts
o
f
d
eter
m
i
n
atio
n
a
n
d
lo
w
er
p
r
ed
ictio
n
er
r
o
r
s
ac
r
o
s
s
all
p
o
llu
tan
ts
.
I
n
ad
d
itio
n
,
th
e
GP
R
co
m
p
o
n
en
t
p
r
o
v
id
ed
q
u
an
ti
f
iab
le
u
n
ce
r
tai
n
t
y
es
ti
m
a
tes,
m
ak
in
g
t
h
e
p
r
ed
ictio
n
s
n
o
t
o
n
l
y
a
cc
u
r
ate
b
u
t
al
s
o
m
o
r
e
r
eliab
le.
T
h
ese
f
i
n
d
in
g
s
co
n
f
ir
m
th
at
i
n
te
g
r
ati
n
g
A
NN
an
d
GP
R
en
h
a
n
ce
s
m
o
d
el
r
o
b
u
s
t
n
ess
,
o
f
f
er
i
n
g
a
m
o
r
e
ef
f
e
ctiv
e
ap
p
r
o
ac
h
th
a
n
eith
er
m
eth
o
d
alo
n
e.
B
e
y
o
n
d
its
tech
n
ical
co
n
tr
ib
u
t
io
n
,
th
is
in
teg
r
ated
f
r
a
m
e
w
o
r
k
p
r
o
v
id
es
a
s
cie
n
ti
f
ic
f
o
u
n
d
atio
n
f
o
r
e
m
i
s
s
io
n
m
a
n
a
g
e
m
e
n
t
a
n
d
r
eg
u
lato
r
y
d
ev
el
o
p
m
e
n
t
to
w
ar
d
E
u
r
o
6
/7
s
tan
d
ar
d
s
.
T
h
e
ab
ilit
y
to
q
u
an
ti
f
y
p
r
ed
ictiv
e
u
n
ce
r
tai
n
t
y
m
a
k
e
s
it
s
u
itab
le
f
o
r
r
ea
l
-
ti
m
e
m
o
n
ito
r
i
n
g
a
n
d
ad
ap
tiv
e
e
m
is
s
io
n
co
n
tr
o
l
in
HE
Vs.
ACK
NO
WL
E
D
G
M
E
NT
S
T
h
e
au
th
o
r
s
w
o
u
ld
li
k
e
to
ex
p
r
ess
th
e
ir
s
in
ce
r
e
g
r
atit
u
d
e
to
Mr
.
Dr
.
A
a
m
M
u
h
ar
a
m
,
M.
E
n
g
.
,
Hea
d
o
f
th
e
R
esear
c
h
C
e
n
ter
f
o
r
T
r
a
n
s
p
o
r
tatio
n
T
ec
h
n
o
lo
g
y
Nat
i
o
n
al
R
esear
ch
a
n
d
I
n
n
o
v
at
io
n
Ag
e
n
c
y
,
f
o
r
h
is
in
v
a
lu
ab
le
g
u
id
an
ce
an
d
co
n
ti
n
u
o
u
s
s
u
p
p
o
r
t
th
r
o
u
g
h
o
u
t
th
is
r
esear
c
h
.
His
e
x
p
er
ti
s
e
an
d
in
s
i
g
h
t
f
u
l
s
u
g
g
e
s
tio
n
s
h
a
v
e
s
i
g
n
if
ica
n
tl
y
co
n
tr
ib
u
ted
to
th
e
d
ev
elo
p
m
en
t
o
f
th
i
s
s
tu
d
y
.
W
e
also
ex
ten
d
o
u
r
d
ee
p
est
ap
p
r
ec
iatio
n
to
Mr
.
Mo
k
h
tar
,
S.T
.
,
M.
T
.
,
Hea
d
o
f
th
e
T
h
er
m
o
d
y
n
a
m
ic
s
,
E
n
g
i
n
es,
an
d
P
r
o
p
u
ls
io
n
L
ab
o
r
ato
r
y
Natio
n
al
R
e
s
ea
r
ch
an
d
I
n
n
o
v
atio
n
Ag
en
c
y
,
f
o
r
p
r
o
v
id
in
g
th
e
n
ec
e
s
s
ar
y
r
esear
c
h
f
ac
ilit
ies
an
d
tec
h
n
ica
l
s
u
p
p
o
r
t
th
at
m
ad
e
th
i
s
w
o
r
k
p
o
s
s
ib
le.
His
en
co
u
r
a
g
e
m
en
t
a
n
d
ass
is
tan
ce
h
av
e
b
ee
n
i
n
s
tr
u
m
e
n
tal
i
n
en
s
u
r
i
n
g
th
e
s
m
o
o
t
h
p
r
o
g
r
ess
o
f
o
u
r
ex
p
er
im
e
n
t
s
an
d
an
al
y
s
es.
w
e
w
o
u
ld
also
lik
e
to
ex
p
r
ess
o
u
r
s
in
ce
r
e
g
r
atit
u
d
e
to
Un
i
v
er
s
iti
T
ek
n
o
l
o
g
i
Ma
la
y
s
i
a
(
UT
M)
f
o
r
p
r
o
v
id
in
g
ac
ce
s
s
to
t
h
e
s
o
f
t
w
ar
e
f
ac
ilit
ies
t
h
a
t
g
r
ea
tl
y
s
u
p
p
o
r
ted
th
e
co
m
p
letio
n
o
f
t
h
i
s
r
esear
ch
w
o
r
k
.
F
u
r
th
er
m
o
r
e,
w
e
w
o
u
ld
lik
e
to
ac
k
n
o
w
led
g
e
all
c
o
lleag
u
e
s
an
d
s
taf
f
m
e
m
b
er
s
w
h
o
h
a
v
e
co
n
tr
ib
u
te
d
,
d
ir
ec
tly
o
r
in
d
ir
ec
tl
y
,
to
th
e
co
m
p
letio
n
o
f
t
h
is
r
esear
c
h
.
T
h
eir
v
al
u
ab
le
in
p
u
t
an
d
co
o
p
er
atio
n
ar
e
g
r
ea
tl
y
a
p
p
r
ec
iated
.
Fin
all
y
,
w
e
ar
e
g
r
atef
u
l
f
o
r
th
e
s
u
p
p
o
r
t
f
r
o
m
o
u
r
in
s
tit
u
tio
n
an
d
E
L
S
A
f
u
n
d
s
,
w
h
ic
h
h
a
v
e
f
ac
il
itated
th
is
r
esear
c
h
en
d
ea
v
o
r
.
F
UNDIN
G
I
NF
O
RM
AT
I
O
N
T
h
is
r
esear
ch
w
a
s
m
ad
e
p
o
s
s
ib
le
th
r
o
u
g
h
th
e
co
llect
iv
e
f
i
n
an
cia
l
co
n
tr
ib
u
tio
n
s
o
f
t
h
e
c
o
-
au
t
h
o
r
s
,
u
tili
zi
n
g
E
L
S
A
f
u
n
d
s
to
s
u
p
p
o
r
t
th
e
ex
p
er
i
m
en
ta
l
ac
tiv
i
ties
co
n
d
u
cted
at
th
e
T
h
er
m
o
d
y
n
a
m
ics,
E
n
g
i
n
es,
an
d
P
r
o
p
u
ls
io
n
L
ab
o
r
ato
r
y
.
W
e
s
in
ce
r
el
y
ap
p
r
ec
iate
th
e
d
ed
icati
o
n
an
d
co
m
m
it
m
e
n
t
o
f
all
co
n
tr
ib
u
to
r
s
w
h
o
h
av
e
p
lay
ed
a
cr
u
cia
l r
o
le
in
en
s
u
r
i
n
g
t
h
e
s
u
cc
es
s
f
u
l c
o
m
p
le
tio
n
o
f
th
i
s
s
t
u
d
y
.
AUTHO
R
CO
NT
RIB
UT
I
O
NS ST
A
T
E
M
E
NT
T
h
is
j
o
u
r
n
al
u
s
e
s
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
i
v
id
u
al
au
th
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
t
h
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
lla
b
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
Her
u
P
r
iy
a
n
to
✓
✓
✓
✓
✓
✓
✓
✓
✓
R
izq
o
n
Faj
ar
✓
✓
✓
✓
✓
✓
✓
✓
Yaa
r
o
T
elau
m
b
an
u
a
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Ar
i
y
an
to
✓
✓
✓
✓
✓
✓
✓
✓
Mu
h
a
m
m
ad
Mu
k
h
las
A
f
✓
✓
✓
✓
✓
✓
✓
✓
Sig
it T
r
i A
t
m
aj
a
✓
✓
✓
✓
✓
✓
Mu
h
a
m
m
ad
Sa
m
s
u
l
Ma
ar
if
✓
✓
✓
✓
✓
✓
✓
Ku
r
n
ia
Faj
ar
A
d
h
i
Su
k
r
a
✓
✓
✓
✓
✓
✓
✓
✓
✓
Fau
zi
D
w
i
Setia
w
a
n
✓
✓
✓
✓
✓
✓
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
si
s
I
:
I
n
v
e
st
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
si
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
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
23
,
No
.
6
,
Dec
em
b
er
20
25
:
1
5
4
3
-
1
554
1552
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
d
ec
lar
e
th
at
t
h
er
e
is
n
o
co
n
f
lict o
f
i
n
ter
es
t r
eg
ar
d
in
g
t
h
e
p
u
b
licatio
n
o
f
t
h
is
p
a
p
er
.
I
NF
O
RM
E
D
CO
NSE
N
T
T
h
is
s
tu
d
y
d
o
es
n
o
t
in
v
o
l
v
e
h
u
m
a
n
p
ar
ticip
an
t
s
,
p
er
s
o
n
al
d
ata,
o
r
c
o
n
f
id
en
t
ial
in
f
o
r
m
atio
n
r
eq
u
ir
in
g
in
f
o
r
m
ed
co
n
s
e
n
t.
E
T
H
I
CAL AP
P
RO
V
AL
T
h
is
r
esear
ch
d
o
es
n
o
t
in
v
o
l
v
e
h
u
m
a
n
p
ar
ticip
an
ts
,
a
n
i
m
als
,
o
r
an
y
s
en
s
iti
v
e
d
ata
r
eq
u
ir
i
n
g
et
h
ical
ap
p
r
o
v
al.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
ata
s
u
p
p
o
r
tin
g
t
h
e
f
i
n
d
in
g
s
o
f
th
is
s
t
u
d
y
ar
e
av
aila
b
le
u
p
o
n
r
ea
s
o
n
ab
le
r
eq
u
est.
I
n
ter
ested
r
esear
ch
er
s
m
a
y
co
n
tac
t th
e
f
ir
s
t a
u
t
h
o
r
f
o
r
ac
ce
s
s
to
th
e
d
ata
.
RE
F
E
R
E
NC
E
S
[
1
]
G
.
K
e
e
g
a
n
,
P
.
N
e
l
e
n
d
r
a
n
,
a
n
d
O
.
O
l
u
w
a
f
e
mi
,
“
M
o
d
e
l
i
n
g
a
n
d
s
i
mu
l
a
t
i
o
n
o
f
h
y
b
r
i
d
e
l
e
c
t
r
i
c
v
e
h
i
c
l
e
s
f
o
r
su
st
a
i
n
a
b
l
e
t
r
a
n
sp
o
r
t
a
t
i
o
n
:
i
n
s
i
g
h
t
s i
n
t
o
f
u
e
l
sav
i
n
g
s
a
n
d
e
mi
ssi
o
n
s re
d
u
c
t
i
o
n
,”
En
e
rg
i
e
s
,
v
o
l
.
1
7
,
n
o
.
2
0
,
2
0
2
4
,
d
o
i
:
1
0
.
3
3
9
0
/
e
n
1
7
2
0
5
2
2
5
.
[
2
]
S
.
K
h
a
l
i
d
,
“
A
c
o
mp
r
e
h
e
n
si
v
e
r
e
v
i
e
w
o
f
a
d
v
a
n
c
e
d
c
o
n
t
r
o
l
st
r
a
t
e
g
i
e
s
f
o
r
h
y
b
r
i
d
e
l
e
c
t
r
i
c
v
e
h
i
c
l
e
s,”
H
y
b
r
i
d
El
e
c
t
ri
c
V
e
h
i
c
l
e
s
a
n
d
D
i
st
ri
b
u
t
e
d
R
e
n
e
w
a
b
l
e
En
e
rg
y
C
o
n
v
e
rsi
o
n
:
C
o
n
t
r
o
l
a
n
d
V
i
b
r
a
t
i
o
n
A
n
a
l
y
si
s
,
p
p
.
5
5
-
9
8
,
2
0
2
4
,
d
o
i
:
1
0
.
4
0
1
8
/
9
7
9
-
8
-
3
6
9
3
-
5
7
9
7
-
2
.
c
h
0
0
2
.
[
3
]
C
.
M
a
i
n
o
,
D
.
M
i
s
u
l
,
A
.
D
i
M
a
u
r
o
,
a
n
d
E.
S
p
e
ssa,
“
A
d
e
e
p
n
e
u
r
a
l
n
e
t
w
o
r
k
b
a
se
d
mo
d
e
l
f
o
r
t
h
e
p
r
e
d
i
c
t
i
o
n
o
f
h
y
b
r
i
d
e
l
e
c
t
r
i
c
v
e
h
i
c
l
e
s c
a
r
b
o
n
d
i
o
x
i
d
e
e
mi
ss
i
o
n
s
,
”
E
n
e
r
g
y
a
n
d
AI
,
v
o
l
.
5
,
p
.
1
0
0
0
7
3
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
g
y
a
i
.
2
0
2
1
.
1
0
0
0
7
3
.
[
4
]
Y
.
M
e
h
t
a
,
R
.
X
u
,
B
.
L
i
m,
J.
W
u
,
a
n
d
J.
G
a
o
,
“
A
r
e
v
i
e
w
f
o
r
g
r
e
e
n
e
n
e
r
g
y
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
A
I
s
e
r
v
i
c
e
s
,”
En
e
rg
i
e
s
,
v
o
l
.
1
6
,
n
o
.
1
5
,
p
.
5
7
1
8
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
e
n
1
6
1
5
5
7
1
8
.
[
5
]
J.
U
d
o
h
,
J.
L
u
,
a
n
d
Q
.
X
u
,
“
A
p
p
l
i
c
a
t
i
o
n
o
f
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
t
o
p
r
e
d
i
c
t
C
O
2
e
mi
ss
i
o
n
s
i
n
l
i
g
h
t
-
d
u
t
y
v
e
h
i
c
l
e
s,”
S
e
n
so
rs
,
v
o
l
.
2
4
,
n
o
.
2
4
,
p
.
8
2
1
9
,
2
0
2
4
,
d
o
i
:
1
0
.
3
3
9
0
/
s
2
4
2
4
8
2
1
9
.
[
6
]
S
.
K
a
t
r
e
d
d
i
a
n
d
A
.
T
h
i
r
u
v
e
n
g
a
d
a
m
,
“
Tr
i
p
b
a
se
d
mo
d
e
l
i
n
g
o
f
f
u
e
l
c
o
n
su
mp
t
i
o
n
i
n
mo
d
e
r
n
h
e
a
v
y
-
d
u
t
y
v
e
h
i
c
l
e
s
u
si
n
g
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
,
”
En
e
r
g
i
e
s
,
v
o
l
.
1
4
,
n
o
.
2
4
,
p
p
.
1
–
1
2
,
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
e
n
1
4
2
4
8
5
9
2
.
[
7
]
D
.
Z
h
o
n
g
,
B
.
L
i
u
,
L
.
L
i
u
,
W
.
F
a
n
,
a
n
d
J.
T
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
a
l
g
o
r
i
t
h
ms
f
o
r
h
y
b
r
i
d
e
l
e
c
t
r
i
c
p
o
w
e
r
t
r
a
i
n
s
y
st
e
m
c
o
n
t
r
o
l
:
A
r
e
v
i
e
w
,”
En
e
r
g
i
e
s
,
v
o
l
.
1
8
,
n
o
.
8
,
2
0
2
5
,
d
o
i
:
1
0
.
3
3
9
0
/
e
n
1
8
0
8
2
0
1
8
.
[
8
]
S
.
R
.
Y
o
o
,
J.
W
.
S
h
i
n
,
a
n
d
S
.
H
.
C
h
o
i
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
v
e
h
i
c
l
e
f
u
e
l
e
f
f
i
c
i
e
n
c
y
p
r
e
d
i
c
t
i
o
n
,
”
S
c
i
e
n
t
i
f
i
c
Re
p
o
rt
s
,
v
o
l
.
1
5
,
n
o
.
1
,
p
p
.
1
–
2
0
,
2
0
2
5
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
5
9
8
-
0
2
5
-
9
6
9
9
9
-
0.
[
9
]
A
.
A
.
A
l
h
u
ssa
n
,
M
.
M
e
t
w
a
l
l
y
,
a
n
d
S
.
K
.
T
o
w
f
e
k
,
“
P
r
e
d
i
c
t
i
n
g
C
O
2
e
mi
ssi
o
n
s
w
i
t
h
a
d
v
a
n
c
e
d
d
e
e
p
l
e
a
r
n
i
n
g
mo
d
e
l
s
a
n
d
a
h
y
b
r
i
d
g
r
e
y
l
a
g
g
o
o
se
o
p
t
i
mi
z
a
t
i
o
n
a
l
g
o
r
i
t
h
m
,
”
M
a
t
h
e
m
a
t
i
c
s
,
v
o
l
.
1
3
,
n
o
.
9
,
2
0
2
5
,
d
o
i
:
1
0
.
3
3
9
0
/
ma
t
h
1
3
0
9
1
4
8
1
.
[
10
]
J.
C
.
F
e
r
r
e
i
r
a
a
n
d
M
.
Es
p
e
r
a
n
ç
a
,
“
E
n
h
a
n
c
i
n
g
su
s
t
a
i
n
a
b
l
e
l
a
st
-
m
i
l
e
d
e
l
i
v
e
r
y
:
T
h
e
i
mp
a
c
t
o
f
e
l
e
c
t
r
i
c
v
e
h
i
c
l
e
s a
n
d
A
I
o
p
t
i
mi
z
a
t
i
o
n
o
n
u
r
b
a
n
l
o
g
i
st
i
c
s
,”
Wo
rl
d
E
l
e
c
t
r
i
c
Ve
h
i
c
l
e
J
o
u
r
n
a
l
,
v
o
l
.
1
6
,
n
o
.
5
,
p
p
.
1
–
1
5
,
2
0
2
5
,
d
o
i
:
1
0
.
3
3
9
0
/
w
e
v
j
1
6
0
5
0
2
4
2
.
[1
1
]
R
.
Y
a
n
g
e
t
a
l
.
,
“
A
n
a
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
mo
d
e
l
t
o
p
r
e
d
i
c
t
e
f
f
i
c
i
e
n
c
y
a
n
d
e
mi
ss
i
o
n
s
o
f
a
g
a
so
l
i
n
e
e
n
g
i
n
e
,”
Pr
o
c
e
sses
,
v
o
l
.
1
0
,
n
o
.
2
,
p
p
.
1
–
2
0
,
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
p
r
1
0
0
2
0
2
0
4
.
[1
2
]
D
.
T
e
n
a
-
G
a
g
o
,
G
.
G
o
l
c
a
r
e
n
a
r
e
n
j
i
,
I
.
M
a
r
t
i
n
e
z
-
A
l
p
i
st
e
,
Q
.
W
a
n
g
,
a
n
d
J
.
M
.
A
l
c
a
r
a
z
-
C
a
l
e
r
o
,
“
M
a
c
h
i
n
e
-
l
e
a
r
n
i
n
g
-
b
a
se
d
c
a
r
b
o
n
d
i
o
x
i
d
e
c
o
n
c
e
n
t
r
a
t
i
o
n
p
r
e
d
i
c
t
i
o
n
f
o
r
h
y
b
r
i
d
v
e
h
i
c
l
e
s
,”
S
e
n
s
o
rs
, v
o
l
.
2
3
,
n
o
.
3
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
s
2
3
0
3
1
3
5
0
.
[1
3
]
V
.
Y
a
d
a
v
,
A
.
K
.
Y
a
d
a
v
,
V
.
S
i
n
g
h
,
a
n
d
T
.
S
i
n
g
h
,
“
A
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
a
n
i
n
n
o
v
a
t
i
v
e
a
p
p
r
o
a
c
h
i
n
a
i
r
p
o
l
l
u
t
a
n
t
p
r
e
d
i
c
t
i
o
n
f
o
r
e
n
v
i
r
o
n
me
n
t
a
l
a
p
p
l
i
c
a
t
i
o
n
s:
A
r
e
v
i
e
w
,
”
Re
su
l
t
s
i
n
En
g
i
n
e
e
r
i
n
g
,
v
o
l
.
2
2
,
n
o
.
M
a
y
,
p
.
1
0
2
3
0
5
,
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
2
3
0
5
.
[1
4
]
V
.
C
h
a
n
d
r
a
n
,
C
.
K
.
P
a
t
i
l
,
A
.
K
a
r
t
h
i
c
k
,
D
.
G
a
n
e
sh
a
p
e
r
u
m
a
l
,
R
.
R
a
h
i
m,
a
n
d
A
.
G
h
o
sh
,
“
S
t
a
t
e
o
f
c
h
a
r
g
e
e
st
i
ma
t
i
o
n
o
f
l
i
t
h
i
u
m
-
i
o
n
b
a
t
t
e
r
y
f
o
r
e
l
e
c
t
r
i
c
v
e
h
i
c
l
e
s
u
si
n
g
mac
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms
,
”
W
o
rl
d
El
e
c
t
ri
c
Ve
h
i
c
l
e
J
o
u
r
n
a
l
,
v
o
l
.
1
2
,
n
o
.
1
,
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
w
e
v
j
1
2
0
1
0
0
3
8
.
[1
5
]
Y
.
E.
A
l
t
u
n
a
n
d
O
.
A
.
K
u
t
l
a
r
,
“
En
e
r
g
y
man
a
g
e
me
n
t
sy
st
e
ms
’
mo
d
e
l
i
n
g
a
n
d
o
p
t
i
mi
z
a
t
i
o
n
i
n
h
y
b
r
i
d
e
l
e
c
t
r
i
c
v
e
h
i
c
l
e
s
,”
En
e
rg
i
e
s
,
v
o
l
.
1
7
,
n
o
.
7
,
2
0
2
4
,
d
o
i
:
1
0
.
3
3
9
0
/
e
n
1
7
0
7
1
6
9
6
.
[1
6
]
W
.
M
.
A
sh
r
a
f
e
t
a
l
.
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
ssi
s
t
e
d
i
mp
r
o
v
e
d
d
e
sal
i
n
a
t
i
o
n
p
i
l
o
t
sy
st
e
m
d
e
si
g
n
a
n
d
e
x
p
e
r
i
me
n
t
a
t
i
o
n
f
o
r
t
h
e
c
i
r
c
u
l
a
r
e
c
o
n
o
my
,
”
J
o
u
r
n
a
l
o
f
Wa
t
e
r
Pro
c
e
ss
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
6
3
,
p
.
1
0
5
5
3
5
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
w
p
e
.
2
0
2
4
.
1
0
5
5
3
5
.
[1
7
]
U
n
i
t
e
d
N
a
t
i
o
n
s
E
c
o
n
o
mi
c
C
o
mm
i
ssi
o
n
f
o
r
Eu
r
o
p
e
(
U
N
EC
E)
,
“
R
e
g
u
l
a
t
i
o
n
n
o
.
8
3
:
U
n
i
f
o
r
m p
r
o
v
i
si
o
n
s
c
o
n
c
e
r
n
i
n
g
t
h
e
a
p
p
r
o
v
a
l
o
f
v
e
h
i
c
l
e
s
w
i
t
h
r
e
g
a
r
d
t
o
t
h
e
e
mi
ssi
o
n
o
f
p
o
l
l
u
t
a
n
t
s a
c
c
o
r
d
i
n
g
t
o
e
n
g
i
n
e
f
u
e
l
r
e
q
u
i
r
e
me
n
t
s,
”
O
f
f
i
c
i
a
l
J
o
u
r
n
a
l
o
f
t
h
e
Eu
r
o
p
e
a
n
U
n
i
o
n
,
v
o
l
.
8
4
,
n
o
.
1
1
,
p
p
.
2
0
-
2
2
6
,
20
12
.
[
18
]
K
.
F
.
A
.
S
u
k
r
a
,
H
.
P
r
i
y
a
n
t
o
,
D
.
I
n
d
r
i
a
t
mo
n
o
,
M
.
A
.
W
i
j
a
y
a
n
t
o
,
I
.
Y
.
I
k
h
san
u
d
i
n
,
a
n
d
Y
.
A
.
Er
ma
n
sy
a
h
,
“
I
m
p
a
c
t
o
f
r
o
a
d
l
o
a
d
p
a
r
a
me
t
e
r
s
o
n
v
e
h
i
c
l
e
C
O
2
e
mi
ss
i
o
n
s
a
n
d
f
u
e
l
e
c
o
n
o
m
y
:
A
c
a
se
st
u
d
y
i
n
I
n
d
o
n
e
si
a
,
”
J
o
u
rn
a
l
o
f
M
e
c
h
a
t
r
o
n
i
c
s
,
El
e
c
t
r
i
c
a
l
Po
w
e
r
,
a
n
d
Ve
h
i
c
u
l
a
r
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
1
4
,
n
o
.
1
,
p
p
.
8
7
–
9
3
,
2
0
2
3
,
d
o
i
:
1
0
.
1
4
2
0
3
/
j
.
me
v
.
2
0
2
3
.
v
1
4
.
8
7
-
9
3
.
[
19
]
R
.
C
.
M
a
ma
t
,
A
.
R
a
ml
i
,
a
n
d
A
.
B
.
B
a
w
a
mo
h
i
d
d
i
n
,
“
A
c
o
mp
a
r
a
t
i
v
e
a
n
a
l
y
si
s
o
f
G
a
u
ssi
a
n
p
r
o
c
e
ss
r
e
g
r
e
ssi
o
n
a
n
d
s
u
p
p
o
r
t
v
e
c
t
o
r
mac
h
i
n
e
s
i
n
p
r
e
d
i
c
t
i
n
g
c
a
r
b
o
n
e
mi
s
si
o
n
s
f
r
o
m
b
u
i
l
d
i
n
g
c
o
n
s
t
r
u
c
t
i
o
n
a
c
t
i
v
i
t
i
e
s
,
”
J
o
u
rn
a
l
o
f
A
d
v
a
n
c
e
d
Re
se
a
rc
h
i
n
A
p
p
l
i
e
d
Me
c
h
a
n
i
c
s
,
v
o
l
.
1
3
1
,
n
o
.
1
,
p
p
.
1
8
5
–
1
9
6
,
2
0
2
5
,
d
o
i
:
1
0
.
3
7
9
3
4
/
a
r
a
m.
1
3
1
.
1
.
1
8
5
1
9
6
.
[
20
]
M
.
O
.
O
y
e
d
e
j
i
,
M
.
A
l
d
h
a
i
f
a
l
l
a
h
,
H
.
R
e
z
k
,
a
n
d
A
.
A
.
A
.
M
o
h
a
me
d
,
“
C
o
mp
u
t
a
t
i
o
n
a
l
mo
d
e
l
s
f
o
r
f
o
r
e
c
a
st
i
n
g
e
l
e
c
t
r
i
c
v
e
h
i
c
l
e
e
n
e
r
g
y
d
e
man
d
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
E
n
e
rg
y
R
e
se
a
rc
h
,
v
o
l
.
2
0
2
3
,
n
o
.
0
1
,
p
.
1
9
3
4
1
8
8
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
3
/
1
9
3
4
1
8
8
.
[2
1
]
Z
.
Y
a
n
,
S
.
Z
h
o
n
g
,
L
.
L
i
n
,
a
n
d
Z
.
C
u
i
,
“
A
d
a
p
t
i
v
e
L
e
v
e
n
b
e
r
g
–
M
a
r
q
u
a
r
d
t
a
l
g
o
r
i
t
h
m:
A
n
e
w
o
p
t
i
mi
z
a
t
i
o
n
st
r
a
t
e
g
y
f
o
r
L
e
v
e
n
b
e
r
g
–
M
a
r
q
u
a
r
d
t
n
e
u
r
a
l
n
e
t
w
o
r
k
s,”
Ma
t
h
e
m
a
t
i
c
s
,
v
o
l
.
9
,
n
o
.
1
7
,
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
m
a
t
h
9
1
7
2
1
7
6
.
[2
2
]
R
.
L
.
G
.
K
a
k
a
ï
,
M
.
Eg
a
h
,
C
.
G
.
H
o
u
n
me
n
o
u
,
“
Ef
f
e
c
t
o
f
d
a
t
a
se
t
p
a
r
t
i
t
i
o
n
a
n
d
n
o
r
mal
i
z
a
t
i
o
n
me
t
h
o
d
s
i
n
t
h
e
h
y
p
e
r
p
a
r
a
me
t
e
r
s
Evaluation Warning : The document was created with Spire.PDF for Python.