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.
2
3
,
No
.
4
,
A
u
g
u
s
t
2
0
2
5
,
p
p
.
1
000
~1
0
0
9
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
2
3
i
4
.
2
6
4
4
9
1000
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
Fuel
co
nsu
m
p
tion
predic
tion o
f
c
iv
il air cra
ft
s
using
deep
lea
rning
:
a
co
m
p
a
ra
tive study
Q
uo
c
H
un
g
Ng
uy
en,
H
o
a
ng
L
a
n Ng
uy
en
S
c
h
o
o
l
o
f
B
u
s
i
n
e
ss I
n
f
o
r
mat
i
o
n
T
e
c
h
n
o
l
o
g
y
,
U
EH
C
o
l
l
e
g
e
o
f
Te
c
h
n
o
l
o
g
y
a
n
d
D
e
si
g
n
,
U
n
i
v
e
r
si
t
y
o
f
Ec
o
n
o
mi
c
s
H
o
C
h
i
M
i
n
h
C
i
t
y
(
U
EH
)
,
V
i
e
t
n
a
m
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
n
30
,
2
0
2
4
R
ev
i
s
ed
A
p
r
21
,
2
0
2
5
A
cc
ep
ted
Ma
y
10
,
2025
A
c
c
u
ra
te
f
u
e
l
c
o
n
su
m
p
ti
o
n
p
re
d
i
c
ti
o
n
is
c
rit
ica
l
f
o
r
m
in
i
m
izin
g
t
h
e
a
d
v
e
rse
im
p
a
c
t
o
f
f
u
e
l
e
m
issio
n
s
o
n
t
h
e
e
n
v
iro
n
m
e
n
t,
c
o
n
se
rv
in
g
f
u
e
l,
a
n
d
re
d
u
c
in
g
f
li
g
h
t
c
o
sts.
A
d
d
it
io
n
a
ll
y
,
p
re
c
ise
f
u
e
l
f
o
re
c
a
stin
g
e
n
h
a
n
c
e
s
traje
c
to
ry
p
re
d
ictio
n
a
n
d
su
p
p
o
r
ts
e
f
fe
c
ti
v
e
a
ir
traff
ic
m
a
n
a
g
e
m
e
n
t.
Th
is
stu
d
y
e
v
a
lu
a
tes
th
e
p
re
d
ictiv
e
p
e
r
f
o
r
m
a
n
c
e
o
f
t
w
o
d
e
e
p
lea
rn
in
g
tec
h
n
iq
u
e
s
in
p
re
d
ictin
g
t
h
e
f
u
e
l
c
o
n
su
m
p
ti
o
n
o
f
a
c
iv
il
a
ircra
f
t
b
e
lo
n
g
in
g
to
A
irb
u
s
A
3
2
0
NEO.
Ba
se
d
o
n
t
h
e
a
n
a
ly
s
is,
th
e
f
in
d
i
n
g
s
sh
o
w
th
a
t
t
h
e
d
e
e
p
n
e
u
ra
l
n
e
tw
o
rk
(DN
N)
m
o
d
e
l
h
a
s
b
e
tt
e
r
sc
o
re
o
f
in
d
ica
to
rs
a
n
d
t
h
a
n
t
h
e
re
c
u
rre
n
t
n
e
u
ra
l
n
e
tw
o
rk
(RNN
)
in
c
lu
d
in
g
m
e
a
n
a
b
so
lu
te
e
rro
r
(
M
A
E
)
,
m
e
a
n
sq
u
a
re
d
e
rro
r
(
MSE
)
,
r
o
o
t
m
e
a
n
sq
u
a
re
d
e
rro
r
(
RM
S
E
)
a
n
d
R
-
sq
u
a
re
d
(
R
2
).
By
in
teg
ra
ti
n
g
a
n
a
u
t
o
m
a
ted
fe
a
tu
re
se
lec
ti
o
n
a
p
p
r
o
a
c
h
w
it
h
a
n
o
p
ti
m
ize
d
d
e
e
p
lea
rn
in
g
f
ra
m
e
w
o
rk
,
th
is
re
se
a
r
c
h
c
o
n
tri
b
u
tes
to
t
h
e
d
e
v
e
lo
p
m
e
n
t
o
f
a
ro
b
u
st
a
n
d
e
f
f
icie
n
t
p
re
d
ictiv
e
sy
ste
m
f
o
r
f
u
e
l
c
o
n
su
m
p
ti
o
n
.
T
h
e
f
in
d
i
n
g
s
h
a
v
e
p
ra
c
ti
c
a
l
im
p
li
c
a
ti
o
n
s
f
o
r
im
p
ro
v
in
g
f
u
e
l
m
a
n
a
g
e
m
e
n
t
stra
teg
ies
in
a
v
iatio
n
,
lea
d
in
g
to
c
o
st sa
v
in
g
s a
n
d
re
d
u
c
e
d
e
m
issio
n
s.
On
e
li
m
it
a
ti
o
n
o
f
th
is stu
d
y
is
it
s relian
c
e
o
n
sp
e
c
if
ic en
v
iro
n
m
e
n
tal
v
a
riab
les
,
w
h
ich
m
a
y
li
m
it
th
e
m
o
d
e
l
’
s
g
e
n
e
ra
li
z
a
b
il
it
y
a
c
ro
ss
d
if
f
e
r
e
n
t
f
li
g
h
t
c
o
n
d
it
i
o
n
s
,
a
ircra
f
t
ty
p
e
s,
a
n
d
o
p
e
ra
ti
o
n
a
l
sc
e
n
a
rio
s.
K
ey
w
o
r
d
s
:
A
ir
cr
a
f
t tr
aj
ec
to
r
y
p
r
ed
ictio
n
Dee
p
n
eu
r
al
n
e
t
w
o
r
k
s
Mu
t
u
al
in
f
o
r
m
a
tio
n
f
ea
tu
r
e
s
elec
tio
n
P
r
e
d
i
c
t
i
o
n
o
f
j
e
t
f
u
e
l
c
o
n
s
u
m
p
t
i
o
n
R
ec
u
r
r
en
t n
e
u
r
al
n
et
w
o
r
k
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
:
Qu
o
c
Hu
n
g
Ng
u
y
en
Sch
o
o
l o
f
B
u
s
i
n
e
s
s
I
n
f
o
r
m
at
io
n
T
ec
h
n
o
lo
g
y
,
UE
H
C
o
lle
g
e
o
f
T
ec
h
n
o
lo
g
y
a
n
d
Desi
g
n
Un
i
v
er
s
it
y
o
f
E
co
n
o
m
ics Ho
C
h
i M
in
h
C
i
t
y
(
UE
H)
5
9
C
Ng
u
y
e
n
Din
h
C
h
ie
u
Stre
e
t,
Xu
an
Ho
a
W
ar
d
,
Dis
tr
ict
3
,
Ho
C
h
i M
i
n
h
C
it
y
,
Viet
n
a
m
E
m
ail:
h
u
n
g
n
q
@
u
e
h
.
ed
u
.
v
n
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
a
v
i
at
i
o
n
i
n
d
u
s
t
r
y
i
s
a
m
a
jo
r
c
o
n
t
r
i
b
u
t
o
r
t
o
g
l
o
b
a
l
g
r
e
en
h
o
u
s
e
g
as
em
i
s
s
i
o
n
s
,
p
r
im
a
r
i
ly
th
r
o
u
g
h
i
ts
p
r
o
d
u
c
t
i
o
n
o
f
2
.
I
n
2
0
1
0
,
t
h
e
in
t
e
r
n
at
i
o
n
a
l
av
i
at
i
o
n
i
n
d
u
s
t
r
y
c
o
n
s
u
m
e
d
a
p
p
r
o
x
im
a
t
ely
1
4
2
m
il
l
i
o
n
t
o
n
s
o
f
f
u
e
l
,
r
e
s
u
lt
in
g
in
4
4
8
m
i
l
li
o
n
m
e
t
r
i
c
t
o
n
s
(
Mt
,
1
k
g
×
1
0
9
)
o
f
em
is
s
i
o
n
s
2
,
an
d
f
u
e
l
c
o
n
s
u
m
p
t
i
o
n
is
e
x
p
ec
t
e
d
t
o
2
.
8
–
2
.
9
t
im
e
s
b
y
2
0
4
0
[
1
]
.
H
o
w
ev
e
r
,
b
y
2
0
1
3
,
t
h
e
t
o
ta
l
g
a
s
2
g
e
n
e
r
at
e
d
f
r
o
m
c
o
m
m
e
r
c
ia
l
f
l
ig
h
ts
h
a
d
r
e
a
c
h
e
d
7
0
7
m
i
l
li
o
n
t
o
n
s
a
n
d
f
u
th
e
r
in
c
r
e
as
e
t
o
9
2
0
m
il
l
i
o
n
t
o
n
s
b
y
2
0
1
9
(
a
b
o
u
t
3
0
%
in
6
y
e
a
r
s
)
[
2
]
,
[
3
]
.
A
i
r
c
r
af
t
e
n
g
in
es
p
r
o
d
u
c
e
2
a
s
a
f
ix
e
d
r
a
t
io
o
f
3
.
1
6
k
g
2
p
e
r
1
k
g
o
f
b
u
r
n
ed
f
u
e
l
,
m
ak
in
g
i
t
a
p
e
r
s
is
t
en
t
g
r
e
e
n
h
o
u
s
e
g
as
[
4
]
.
I
t
s
l
o
n
g
lif
e
t
im
e
in
th
e
a
tm
o
s
p
h
e
r
e
m
ak
es
2
a
p
o
t
e
n
t
g
r
e
e
n
h
o
u
s
e
g
as
.
On
ce
em
i
tt
e
d
,
2
r
em
ai
n
s
in
t
h
e
a
tm
o
s
p
h
e
r
e
f
o
r
c
en
t
u
r
ie
s
,
w
ith
2
0
p
e
r
c
en
t
r
em
a
in
f
o
r
th
o
u
s
an
d
s
o
f
y
e
a
r
s
[
5
]
.
T
h
e
r
ef
o
r
e
,
a
l
l
th
e
em
is
s
i
o
n
s
g
en
e
r
a
te
d
f
r
o
m
a
i
r
c
r
a
f
t
w
il
l
t
ak
e
m
an
y
t
im
e
t
o
b
e
c
o
n
v
e
r
t
e
d
.
T
h
e
C
O
V
I
D
-
1
9
p
a
n
d
em
ic
t
em
p
o
r
a
r
i
ly
r
e
d
u
c
e
d
g
l
o
b
a
l
f
l
ig
h
t
a
ct
iv
ity
in
2
0
2
0
b
y
n
e
a
r
ly
5
0
%
,
s
ig
n
if
i
c
an
t
ly
d
e
c
r
e
a
s
in
g
g
r
e
en
h
o
u
s
e
g
a
s
em
is
s
i
o
n
s
[
6
]
,
[
7
]
.
T
h
i
s
s
h
a
r
p
d
e
c
l
in
e
u
n
d
e
r
s
c
o
r
e
s
th
e
a
v
i
at
i
o
n
s
e
c
t
o
r
’
s
p
r
o
f
o
u
n
d
en
v
i
r
o
n
m
en
t
al
im
p
a
ct
an
d
h
ig
h
l
ig
h
ts
th
e
u
r
g
en
t
n
ee
d
f
o
r
s
u
s
t
a
in
a
b
le
s
o
lu
ti
o
n
s
.
Fu
r
th
e
r
m
o
r
e
,
th
e
c
o
n
t
in
u
e
d
g
r
o
w
th
in
p
a
s
s
en
g
e
r
n
u
m
b
e
r
s
ex
a
c
e
r
b
at
e
s
th
e
p
r
o
b
l
em
.
I
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
F
u
el
co
n
s
u
mp
tio
n
p
r
ed
ictio
n
o
f c
ivil a
ir
cra
ft
s
u
s
in
g
d
ee
p
le
a
r
n
in
g
:
a
co
mp
a
r
a
tive
…
(
Qu
o
c
Hu
n
g
N
g
u
ye
n
)
1001
2
0
1
0
,
t
h
e
in
d
u
s
t
r
y
t
r
an
s
p
o
r
t
e
d
2
.
4
b
i
l
li
o
n
p
a
s
s
en
g
e
r
s
,
a
f
ig
u
r
e
p
r
o
je
c
t
e
d
t
o
r
e
ac
h
8
.
2
b
il
l
i
o
n
b
y
2
0
4
0
[
8
]
–
[
1
0
]
.
T
h
u
s
,
a
v
i
a
t
i
o
n
-
r
e
la
t
e
d
em
is
s
i
o
n
s
c
o
u
l
d
t
r
i
p
l
e
b
y
2
0
5
0
c
o
m
p
a
r
ed
t
o
2
0
1
5
l
e
v
e
ls
[
1
1
]
,
[
1
2
]
.
T
o
m
iti
g
ate
t
h
ese
i
m
p
ac
ts
,
t
h
e
E
u
r
o
p
ea
n
U
n
io
n
C
o
m
m
i
s
s
io
n
h
as
b
ee
n
ap
p
l
y
in
g
s
o
l
u
t
io
n
s
s
u
c
h
s
u
s
tai
n
ab
le
av
iatio
n
f
u
els
(
S
AF)
an
d
f
li
g
h
t
r
o
u
tes
o
p
ti
m
iz
atio
n
s
[
1
3
]
.
Ho
w
e
v
er
,
to
ap
p
ly
s
o
lu
tio
n
s
,
cu
r
r
en
t
f
o
r
ec
asti
n
g
m
o
d
els
f
o
r
f
u
el
co
n
s
u
m
p
tio
n
h
av
e
m
an
y
v
ar
iatio
n
,
lead
in
g
to
2
lar
g
e
d
e
v
iatio
n
s
in
th
e
ca
lcu
latio
n
o
f
i
m
p
ac
t
s
an
d
o
th
er
em
i
s
s
io
n
s
.
B
esid
es,
p
o
o
r
p
r
ed
ictio
n
s
ca
n
r
es
u
lt
in
f
i
n
an
cia
l
lo
s
s
es
f
o
r
air
lin
e
s
b
y
f
aili
n
g
to
d
etec
t a
ir
cr
af
t
m
a
lf
u
n
ct
io
n
s
i
n
ti
m
e.
T
h
e
co
n
tr
ib
u
tio
n
o
f
p
ap
er
is
u
s
i
n
g
d
ee
p
lear
n
in
g
m
o
d
el
in
clu
d
in
g
d
ee
p
n
eu
r
al
n
e
t
w
o
r
k
(
DNN)
an
d
r
ec
u
r
r
en
t
n
e
u
r
al
n
et
w
o
r
k
(
R
NN)
to
p
r
ed
ict
ac
cu
r
atel
y
air
cr
af
t
f
u
el
co
n
s
u
m
p
tio
n
o
f
a
l
o
n
g
d
is
ta
n
ce
.
Fli
g
h
t
m
o
n
ito
r
s
d
ata
is
u
s
ed
f
o
r
f
u
eli
n
g
co
n
s
u
m
p
tio
n
ass
e
s
s
m
e
n
t.
An
u
n
d
er
s
co
r
ed
p
o
in
t
in
th
e
p
ap
er
is
an
o
p
tim
ize
d
p
r
o
ce
s
s
u
s
in
g
o
p
en
ed
an
d
ef
f
i
cien
t
m
o
d
els,
f
ea
tu
r
es
s
e
lectio
n
m
et
h
o
d
to
ea
s
il
y
p
u
t
th
e
m
o
d
el
in
to
p
r
ac
tices
.
As
a
r
esu
lt,
t
w
o
m
ai
n
f
o
cu
s
e
d
p
o
in
ts
in
th
e
p
ap
er
ar
e
f
ea
tu
r
es
s
elec
tio
n
m
et
h
o
d
(
m
u
tu
a
l
in
f
o
r
m
a
tio
n
(
MI
)
)
an
d
th
e
g
o
o
d
d
ee
p
lear
n
in
g
m
o
d
el
(
th
e
r
esu
lt
o
f
co
m
p
ar
is
o
n
b
et
w
ee
n
DNN
a
n
d
R
NN)
.
T
h
e
in
v
o
lv
e
m
e
n
t
o
f
b
ig
d
ata,
p
o
w
er
f
u
l to
o
ls
ar
e
r
eq
u
ir
ed
to
tr
an
s
f
o
r
m
t
h
o
s
e
d
ata
b
ef
o
r
e
r
u
n
n
in
g
t
h
e
p
r
o
ce
s
s
.
2.
M
E
T
H
O
D
2
.
1
.
Def
ini
t
io
n o
f
qu
ick
a
cc
e
s
s
re
co
rder
da
t
a
A
q
u
ick
ac
ce
s
s
r
ec
o
r
d
er
(
QAR)
[
1
4
]
is
a
s
y
s
te
m
t
h
at
ca
n
e
asil
y
a
n
d
q
u
ic
k
l
y
co
llect
air
c
r
af
t
d
ata.
I
t
co
n
s
is
ts
o
f
an
a
ir
b
o
r
n
e
d
ev
ice
f
o
r
d
ata
r
ec
o
r
d
in
g
a
n
d
a
g
r
o
u
n
d
s
o
f
t
w
ar
e
s
tatio
n
f
o
r
d
ata
s
t
o
r
ag
e
an
d
an
a
l
y
s
is
.
QAR
ca
n
ca
p
tu
r
e
s
ap
p
r
o
x
i
m
a
tel
y
2
0
0
0
p
ar
am
eter
s
p
er
air
cr
af
t,
in
c
lu
d
i
n
g
p
o
s
itio
n
,
m
o
ti
o
n
,
o
p
er
atio
n
s
,
an
d
w
ar
n
in
g
s
,
b
u
t
its
d
ata
r
e
m
ai
n
s
co
n
f
id
en
t
ial
a
n
d
is
r
ar
el
y
u
s
ed
in
r
esear
c
h
[
1
5
]
.
Un
li
k
e
f
l
ig
h
t
d
ata
r
ec
o
r
d
er
s
(
FDR
)
an
d
co
c
k
p
it
v
o
ice
r
ec
o
r
d
er
s
(
C
VR
)
,
Q
A
R
s
ar
e
n
o
t
m
a
n
d
ato
r
y
an
d
ar
e
t
y
p
icall
y
in
s
talled
in
ea
s
il
y
ac
ce
s
s
ib
le
lo
ca
tio
n
s
,
s
u
c
h
as
air
lin
e
ca
b
i
n
s
,
f
o
r
r
o
u
tin
e
m
o
n
i
to
r
in
g
o
f
air
cr
af
t
s
y
s
te
m
s
an
d
cr
e
w
p
er
f
o
r
m
an
c
e
[
1
6
]
,
[
1
7
]
.
QA
R
d
ata
is
tr
an
s
lated
th
r
o
u
g
h
a
d
ata
d
ec
o
d
in
g
f
r
a
m
e
(
also
k
n
o
w
n
as
a
d
ata
f
r
a
m
e)
.
I
t
r
ec
ei
v
e
s
in
p
u
t
f
r
o
m
th
e
f
l
ig
h
t
d
ata
ac
q
u
is
i
tio
n
u
n
it
an
d
h
a
s
ev
o
lv
ed
f
r
o
m
u
s
in
g
m
a
g
n
etic
tap
es
to
s
o
lid
-
s
ta
te
m
e
m
o
r
y
.
P
r
ev
io
u
s
l
y
,
d
ata
h
ad
to
b
e
m
a
n
u
al
l
y
r
etr
ie
v
ed
,
p
r
o
ce
s
s
ed
,
an
d
s
to
r
ed
,
lead
in
g
to
s
ig
n
i
f
ica
n
t
o
p
er
atio
n
al
co
s
ts
.
Ho
w
e
v
er
,
m
o
d
er
n
w
ir
eles
s
tech
n
o
lo
g
y
n
o
w
allo
w
s
s
ec
u
r
e,
r
ea
l
-
ti
m
e
tr
an
s
m
is
s
io
n
o
f
co
m
p
r
ess
ed
an
d
en
cr
y
p
ted
Q
AR
d
ata
v
ia
m
o
b
ile
n
et
w
o
r
k
s
,
i
m
p
r
o
v
i
n
g
e
f
f
icien
c
y
,
r
ed
u
ci
n
g
co
s
ts
,
a
n
d
en
h
a
n
ci
n
g
d
ata
av
ailab
ilit
y
[
1
8
]
.
2
.
2
.
M
u
t
ua
l inf
o
r
m
a
t
io
n
Mu
t
u
al
in
f
o
r
m
a
tio
n
(
MI
)
[
1
9
]
q
u
an
ti
f
ie
s
th
e
d
ep
en
d
en
ce
b
e
t
w
ee
n
t
w
o
r
an
d
o
m
v
ar
iab
les.
A
h
i
g
h
MI
[
2
0
]
s
co
r
e
in
d
icate
s
a
s
tr
o
n
g
r
elatio
n
s
h
ip
w
it
h
t
h
e
tar
g
et
v
ar
iab
le,
m
ak
i
n
g
it
u
s
e
f
u
l
f
o
r
p
r
ed
ictio
n
.
A
lo
w
MI
s
co
r
e
in
d
icate
s
s
u
g
g
est
s
m
i
n
i
m
al
i
n
f
l
u
en
ce
,
w
h
ile
an
MI
s
c
o
r
e
o
f
ze
r
o
s
ig
n
i
f
ies
co
m
p
lete
in
d
ep
en
d
en
ce
[
2
1
]
.
Fo
r
t
w
o
d
is
cr
ete
v
ar
iab
les
an
d
w
it
h
a
j
o
in
t
p
r
o
b
ab
ilit
y
d
is
t
r
ib
u
tio
n
o
f
(
,
)
,
th
e
v
alu
e
o
f
MI
o
f
t
h
i
s
d
is
tr
ib
u
tio
n
i
s
d
en
o
ted
(
;
)
w
i
th
t
h
e
f
o
llo
w
in
g
f
o
r
m
u
la:
(
;
)
=
∑
∑
(
,
)
(
,
)
(
)
(
)
=
(
1
)
w
h
er
e
(
)
an
d
(
)
p
r
esen
t
th
e
m
ar
g
in
al
p
r
o
b
ab
ilit
y
f
u
n
c
tio
n
o
f
an
d
an
d
p
r
esen
ts
th
e
j
o
in
t
d
is
tr
ib
u
tio
n
f
u
n
ctio
n
o
f
an
d
,
r
esp
ec
tiv
el
y
.
is
t
h
e
ex
p
e
cted
v
alu
e
o
n
t
h
e
d
is
tr
ib
u
ti
o
n
.
Fo
r
t
w
o
co
n
tin
u
o
u
s
v
ar
iab
les
an
d
w
it
h
a
j
o
in
t
p
r
o
b
ab
ilit
y
d
i
s
tr
i
b
u
tio
n
o
f
(
,
)
,
th
e
v
a
lu
e
o
f
MI
o
f
th
i
s
d
is
tr
ib
u
tio
n
i
s
d
en
o
ted
as
(
;
)
w
it
h
th
e
f
o
llo
w
i
n
g
f
o
r
m
u
la:
(
;
)
=
∬
(
,
)
(
,
)
(
)
(
)
=
(
2
)
th
e
f
o
r
m
u
la
f
o
r
MI
ca
n
b
e
eq
u
iv
ale
n
t to
th
e
f
o
llo
w
in
g
:
(
;
)
=
(
)
+
(
)
−
(
,
)
(
3
)
=
(
,
)
−
(
)
−
(
|
)
w
h
er
e
(
)
an
d
(
)
ar
e
th
e
b
o
u
n
d
ar
y
en
tr
o
p
ies.
(
|
)
an
d
(
|
)
ar
e
co
n
d
itio
n
al
en
tr
o
p
ies.
(
,
)
is
th
e
s
et
o
f
e
n
tr
o
p
ies o
f
X
an
d
Y
.
T
o
f
u
ll
y
g
r
asp
MI
[
2
2
]
,
w
e
n
ee
d
to
u
n
d
er
s
tan
d
e
n
tr
o
p
y
an
d
co
n
d
itio
n
a
l
en
tr
o
p
y
.
Acc
o
r
d
in
g
to
Sh
a
n
n
o
n
,
en
tr
o
p
y
q
u
an
ti
f
ie
s
u
n
ce
r
tain
t
y
in
a
p
r
o
b
ab
ilit
y
d
is
tr
ib
u
tio
n
.
Un
ce
r
tai
n
t
y
h
er
e
m
ea
n
s
th
e
“
s
u
r
p
r
is
e”
o
f
th
e
v
ar
iab
le,
w
h
ich
m
ea
n
s
th
e
p
r
o
b
ab
ilit
y
o
f
a
v
al
u
e
in
t
h
e
v
ar
iab
le
is
v
er
y
lo
w
b
u
t
it
h
ap
p
en
s
.
T
h
er
ef
o
r
e,
“
s
u
r
p
r
is
e”
w
ill
b
e
in
v
er
s
el
y
p
r
o
p
o
r
tio
n
al
to
p
r
o
b
ab
ilit
y
.
T
h
en
,
u
s
e
th
e
lo
g
ar
ith
m
o
n
th
e
in
v
er
s
e
o
f
th
e
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
.
4
,
A
u
g
u
s
t
20
25
:
1
0
0
0
-
1
0
0
9
1002
p
r
o
b
a
b
ilit
y
to
r
etu
r
n
th
e
v
alu
e
s
0
an
d
1
t
o
an
s
w
er
t
h
e
q
u
esti
o
n
w
h
et
h
er
th
er
e
is
s
u
r
p
r
is
e
in
th
e
ev
en
t
o
r
n
o
t.
I
f
1
(
)
eq
u
als
1
lead
s
to
(
1
(
)
)
eq
u
als
0
,
th
is
m
ea
n
s
th
er
e
is
n
o
ele
m
e
n
t
o
f
s
u
r
p
r
is
e
in
t
h
e
ev
e
n
t
an
d
i
s
co
m
p
lete
l
y
p
r
ed
ictab
le.
On
th
e
co
n
tr
ar
y
,
1
(
)
m
o
v
i
n
g
to
w
ar
d
s
0
lead
s
to
(
1
(
)
)
,
th
en
th
e
r
es
u
lt
is
in
d
eter
m
i
n
ate
an
d
“su
r
p
r
is
e”
c
an
o
cc
u
r
b
ec
au
s
e
“
s
u
r
p
r
is
e”
is
s
o
m
e
th
i
n
g
th
at
ca
n
n
o
t
b
e
d
ete
r
m
in
ed
.
T
y
p
icall
y
,
in
i
n
f
o
r
m
atio
n
s
y
s
te
m
s
,
u
n
ce
r
tain
t
y
is
cr
ea
ted
i
n
t
h
e
in
f
o
r
m
atio
n
s
o
u
r
ce
(
i
n
p
u
t)
a
n
d
tr
an
s
m
i
s
s
io
n
c
h
a
n
n
e
l
b
ec
au
s
e
w
e
r
ea
ll
y
d
o
n
o
t
k
n
o
w
f
o
r
s
u
r
e
w
h
ic
h
in
f
o
r
m
at
io
n
s
o
u
r
ce
w
e
r
ec
eiv
e
an
d
w
h
ich
s
ig
n
al
is
r
ec
eiv
ed
[
2
3
]
.
I
n
s
h
o
r
t,
en
tr
o
p
y
(
s
y
m
b
o
l:
H(
X)
)
is
a
m
ea
s
u
r
e
o
f
th
e
u
n
ce
r
tai
n
t
y
o
f
a
r
an
d
o
m
v
ar
ia
b
le.
T
h
e
h
ig
h
er
th
e
en
tr
o
p
y
,
th
e
h
i
g
h
er
t
h
e
u
n
ce
r
t
ain
t
y
o
f
a
v
ar
iab
le.
Gi
v
e
n
a
d
is
cr
ete
an
d
d
is
tr
ib
u
ted
r
an
d
o
m
v
ar
iab
le
d
is
tr
ib
u
ted
ac
co
r
d
in
g
to
P
: X
-
>
[
0
,
1
]
,
th
e
f
o
r
m
u
la
f
o
r
en
tr
o
p
y
is
:
(
)
∶
=
∑
(
)
l
og
(
1
(
)
)
=
[
1
−
l
og
(
(
)
)
]
(
4
)
th
e
f
o
r
m
u
la
f
o
r
en
tr
o
p
y
w
it
h
c
o
n
tin
u
o
u
s
v
ar
iab
les i
s
:
(
)
∶
=
−
∫
(
)
(
(
)
)
(
5
)
f
r
o
m
t
h
er
e,
co
n
d
itio
n
al
e
n
tr
o
p
y
(
s
y
m
b
o
l:
H
(
Y|X
)
)
talk
s
ab
o
u
t th
e
p
r
o
b
ab
ilit
y
o
f
v
ar
iab
le
X
o
cc
u
r
r
in
g
w
i
th
o
u
t
Y
.
C
o
n
d
itio
n
a
l e
n
tr
o
p
y
w
it
h
d
i
s
cr
ete
an
d
co
n
ti
n
u
o
u
s
v
ar
iab
le
s
h
as t
h
e
f
o
r
m
u
la:
(
|
)
=
∑
(
,
)
(
,
)
(
)
,
(
6
)
(
|
)
=
∫
(
,
)
(
,
)
(
)
(
7
)
T
h
u
s
,
w
e
ca
n
r
el
y
o
n
en
tr
o
p
y
to
ex
p
lain
th
e
MI
al
g
o
r
it
h
m
as
f
o
llo
w
s
.
I
f
t
h
e
p
r
o
b
ab
ilit
y
o
f
P
XY
(
x
,
y
)
ap
p
r
o
ac
h
in
g
ze
r
o
lead
s
to
a
v
alu
e
(
,
)
(
)
o
f
0
,
(
(
,
)
(
,
)
(
)
)
w
ill
ap
p
r
o
ac
h
0
,
w
h
ich
m
ea
n
s
t
h
at
v
ar
iab
le
Y
d
o
es
n
o
t
h
a
v
e
m
u
c
h
in
f
o
r
m
at
io
n
r
elate
d
to
X,
th
en
th
e
v
al
u
e
o
f
MI
is
0
an
d
th
e
t
w
o
v
ar
iab
les
ar
e
co
m
p
lete
l
y
i
n
d
ep
en
d
en
t.
I
n
ca
s
e
(
,
)
it
ap
p
r
o
ac
h
es
o
n
e,
(
,
)
(
)
it
w
i
ll
g
r
ad
u
all
y
ap
p
r
o
ac
h
ze
r
o
.
T
h
is
m
ea
n
s
t
h
at
v
ar
iab
le
Y
c
o
n
tain
s
m
o
r
e
i
n
f
o
r
m
atio
n
r
elate
d
to
v
ar
iab
le
X
an
d
t
h
e
les
s
"
s
u
r
p
r
is
e"
h
ap
p
en
s
b
et
w
ee
n
t
h
e
t
w
o
v
ar
iab
le
s
.
T
h
er
ef
o
r
e,
it
ca
n
b
e
co
n
cl
u
d
ed
t
h
at
t
h
e
t
w
o
v
ar
iab
les
ar
e
r
elat
ed
o
r
o
v
er
lap
(
w
i
th
(
,
)
(
)
=
0
an
d
(
,
)
=
1
)
.
3.
T
H
E
P
RO
P
O
SE
D
M
O
DE
L
T
h
e
3
-
s
tag
e
ar
ch
i
tectu
r
e
o
f
t
h
e
p
r
o
p
o
s
ed
m
o
d
el
is
s
h
o
w
n
i
n
Fi
g
u
r
e
1
.
T
h
e
s
h
o
w
n
s
as
Fi
g
u
r
e
1
th
e
p
r
o
ce
s
s
b
eg
in
s
w
it
h
d
ata
co
llectio
n
f
r
o
m
f
li
g
h
t
d
ata
in
ter
f
ac
e
m
a
n
a
g
e
m
en
t
u
n
it
an
d
Q
A
R
s
y
s
te
m
s
,
f
o
llo
w
ed
b
y
d
ec
o
d
in
g
b
i
n
ar
y
d
ata
an
d
s
to
r
in
g
it
in
a
s
tr
u
ct
u
r
ed
d
ata
w
ar
e
h
o
u
s
e
co
n
tai
n
i
n
g
p
ar
a
m
e
tr
ic
d
ata,
tech
n
ical
d
o
cu
m
en
ts
,
an
d
k
n
o
w
led
g
e
m
o
d
els.
T
h
r
o
u
g
h
p
r
ep
r
o
ce
s
s
in
g
s
tep
s
s
u
c
h
as
h
a
n
d
li
n
g
a
n
o
m
al
ies,
r
esh
ap
in
g
d
ata,
an
d
f
ea
t
u
r
e
s
elec
tio
n
u
s
i
n
g
m
u
tu
a
l
in
f
o
r
m
at
io
n
,
th
e
s
tu
d
y
e
n
s
u
r
es
t
h
at
o
n
l
y
r
ele
v
a
n
t
v
ar
i
ab
les
ar
e
u
s
ed
f
o
r
m
o
d
el
tr
ain
in
g
.
T
w
o
d
ee
p
lear
n
in
g
ar
ch
itect
u
r
es,
R
NN
an
d
DNN,
ar
e
im
p
le
m
e
n
ted
an
d
f
i
n
e
-
tu
n
ed
to
ac
h
iev
e
o
p
tim
a
l
p
er
f
o
r
m
a
n
ce
.
T
h
e
e
v
alu
a
tio
n
r
ev
ea
l
s
th
at
DNN
o
u
tp
er
f
o
r
m
s
R
NN
in
ter
m
s
o
f
ac
cu
r
ac
y
.
Af
te
r
ev
alu
a
tio
n
,
p
ar
a
m
eter
s
m
o
d
if
i
ca
tio
n
is
ap
p
lied
f
o
r
ac
cu
r
ac
y
i
m
p
r
o
v
e
m
en
t.
T
h
is
p
ap
er
u
s
es
Q
AR
d
ata
f
r
o
m
an
A
ir
b
u
s
A
3
2
0
NE
O
[
2
4
]
.
A
ir
cr
af
t
ca
n
r
ec
o
r
d
6
0
0
–
3
,
0
0
0
p
ar
am
eter
s
in
a
d
ata
f
r
a
m
e
f
ile,
b
u
t
d
u
e
to
co
m
p
u
tatio
n
al,
s
ec
u
r
it
y
,
an
d
s
to
r
ag
e
co
n
s
tr
ai
n
ts
,
o
n
l
y
k
e
y
p
ar
am
eter
s
w
er
e
s
elec
ted
in
cl
u
d
in
g
f
u
el
f
lo
w
,
ca
lib
r
ated
air
s
p
ee
d
,
s
tat
ic
air
tem
p
er
atu
r
e,
p
r
ess
u
r
e
altitu
d
e,
w
i
n
d
s
p
ee
d
at
th
e
to
p
o
f
t
h
e
c
o
ck
p
it,
s
id
e
w
i
n
d
s
p
ee
d
,
lef
t
l
an
d
in
g
g
ea
r
,
r
ig
h
t
lan
d
i
n
g
g
ea
r
,
n
o
s
e
la
n
d
in
g
g
ea
r
,
s
tan
d
ar
d
ac
ce
ler
atio
n
[
2
5
]
.
T
h
e
o
u
tp
u
t
is
th
e
f
u
el
co
n
s
u
m
p
tio
n
r
ate,
r
e
f
lectin
g
th
e
f
u
el
co
n
s
u
m
p
tio
n
f
lo
w
.
T
h
er
e
ar
e
9
in
p
u
t
f
ac
to
r
s
,
r
em
o
v
i
n
g
r
ed
u
n
d
an
t
v
ar
iab
les
to
o
p
tim
ize
p
er
f
o
r
m
an
ce
.
Af
te
r
th
at,
th
e
d
ataset
is
s
p
lit
in
to
8
0
%
f
o
r
tr
ain
in
g
an
d
2
0
%
f
o
r
test
in
g
.
B
ased
o
n
a
r
ev
ie
w
o
f
e
x
is
ti
n
g
r
esear
ch
,
R
NN
an
d
DNN
ar
e
s
elec
ted
f
o
r
co
m
p
ar
is
o
n
i
n
n
e
x
t
s
tep
.
Af
ter
b
u
ild
i
n
g
th
e
m
o
d
el,
tr
ain
in
g
d
ata
is
f
ed
in
to
t
h
e
m
o
d
el
to
co
n
d
u
ct
lear
n
in
g
.
Af
ter
m
a
th
,
m
o
v
i
n
g
to
m
o
d
el
v
al
id
atio
n
is
c
h
ec
k
t
h
e
r
eliab
ilit
y
o
f
t
h
e
m
o
d
el.
T
h
e
tes
t
s
et
d
ata
is
f
ed
in
to
th
e
m
o
d
els
f
o
r
lear
n
in
g
an
d
th
e
esti
m
a
ted
f
u
el
co
n
s
u
m
p
tio
n
is
o
b
tain
ed
.
P
er
f
o
r
m
a
n
ce
is
ass
ess
ed
u
s
i
n
g
m
ea
n
s
q
u
ar
ed
er
r
o
r
(
MSE
)
,
r
o
o
t
m
ea
n
s
q
u
ar
ed
er
r
o
r
(
R
MSE
)
,
R
-
s
q
u
ar
ed
(
2
)
,
an
d
m
e
an
ab
s
o
lu
te
er
r
o
r
(
MA
E
)
to
en
s
u
r
e
r
eliab
ili
t
y
.
T
h
e
r
esu
lts
ar
e
t
h
e
n
co
m
p
ar
e
d
w
it
h
p
r
ev
io
u
s
s
tu
d
ie
s
,
an
d
m
o
d
el
w
eig
h
t
s
ar
e
ad
j
u
s
ted
iter
ativ
el
y
u
n
til o
p
ti
m
al
ac
cu
r
ac
y
is
ac
h
ie
v
ed
.
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
F
u
el
co
n
s
u
mp
tio
n
p
r
ed
ictio
n
o
f c
ivil a
ir
cra
ft
s
u
s
in
g
d
ee
p
le
a
r
n
in
g
:
a
co
mp
a
r
a
tive
…
(
Qu
o
c
Hu
n
g
N
g
u
ye
n
)
1003
Fig
u
r
e
1
.
A
r
ch
itectu
r
e
o
f
p
r
o
p
o
s
ed
m
o
d
el
3
.
1
.
Da
t
a
prepro
ce
s
s
ing
QAR
is
a
d
ig
ital
r
ec
o
r
d
in
g
d
ev
ice
[
2
6
]
th
at
s
to
r
es
d
ata
in
a
b
in
ar
y
f
o
r
m
at
as
a
s
tr
ea
m
o
f
b
its
,
i.e
.
,
a
s
eq
u
en
ce
o
f
0
s
a
n
d
1
s
[
2
7
]
.
Sto
r
in
g
d
ata
i
n
b
i
n
ar
y
f
o
r
m
at
i
m
p
r
o
v
es
s
to
r
ag
e
e
f
f
icien
c
y
b
y
r
ed
u
ci
n
g
f
ile
s
ize
b
y
u
p
to
te
n
ti
m
e
s
co
m
p
ar
ed
to
f
o
r
m
at
s
s
u
c
h
as
C
SV
[
2
8
]
.
Ho
w
e
v
er
,
d
ec
o
d
in
g
b
in
ar
y
d
ata
in
to
m
ea
n
i
n
g
f
u
l
tech
n
ical
v
a
lu
e
s
r
eq
u
ir
es
s
tr
u
ctu
r
ed
lo
g
ic.
T
h
is
p
r
o
ce
s
s
ad
h
er
es
to
th
e
ae
r
o
n
a
u
tical
r
ad
io
in
co
r
p
o
r
ate
d
(
AR
I
NC
)
s
tan
d
ar
d
s
,
w
i
th
A
R
I
NC
7
1
7
ap
p
lied
to
o
ld
er
air
cr
af
t
m
o
d
els
an
d
AR
I
NC
7
6
7
u
s
ed
f
o
r
n
e
w
er
o
n
es
[
2
9
]
.
A
d
ataf
r
a
m
e,
a
co
m
p
r
eh
en
s
i
v
e
te
x
t
d
o
cu
m
e
n
t,
d
ef
in
e
s
t
h
e
s
tr
u
ctu
r
e,
p
ar
a
m
eter
lo
ca
t
io
n
s
,
an
d
d
ec
o
d
in
g
r
u
les
n
ec
e
s
s
ar
y
f
o
r
d
ata
in
ter
p
r
etatio
n
[
1
8
]
.
T
h
e
QAR
co
n
tin
u
o
u
s
l
y
r
ec
o
r
d
s
d
ata
in
4
-
s
ec
o
n
d
b
lo
ck
s
,
w
it
h
ea
ch
s
ec
o
n
d
co
n
tai
n
in
g
b
et
wee
n
6
4
an
d
1
0
2
4
w
o
r
d
s
.
E
ac
h
s
u
b
f
r
a
m
e
b
eg
i
n
s
w
ith
a
1
2
-
b
it
s
y
n
c
h
r
o
n
izatio
n
wo
r
d
(
e.
g
.
,
0
x
2
4
7
,
0
x
5
B
8
)
.
A
f
r
a
m
e
co
n
s
i
s
ts
o
f
f
o
u
r
s
u
b
f
r
a
m
es,
an
d
th
e
lar
g
e
s
t
u
n
it
,
th
e
s
u
p
er
f
r
a
m
e,
i
s
d
eter
m
in
ed
b
y
t
h
e
f
r
a
m
e
co
u
n
ter
(
r
an
g
in
g
f
r
o
m
0
to
4
0
9
5
)
.
A
n
e
w
s
u
p
er
f
r
a
m
e
b
e
g
i
n
s
w
h
e
n
ev
er
t
h
e
f
r
a
m
e
co
u
n
ter
m
o
d
u
lo
1
6
eq
u
als ze
r
o
(
i.e
.
,
w
h
en
f
r
a
m
e
% 1
6
=
0
)
.
Af
ter
d
ec
o
d
in
g
,
th
e
d
ata
is
s
to
r
ed
as
a
tim
e
s
er
ies,
in
cl
u
d
in
g
s
er
ies
I
D,
ti
m
es
ta
m
p
,
an
d
ass
o
ciate
d
d
o
u
b
le
an
d
s
tr
in
g
v
al
u
es.
T
h
e
n
ex
t
s
tep
is
to
r
esh
ap
e
th
e
d
ata
to
ex
tr
ac
t
f
ea
tu
r
es
b
y
ti
m
e
s
ta
m
p
.
I
n
t
h
e
clea
n
i
n
g
s
tep
,
th
e
co
n
v
er
ted
d
ata
is
p
r
o
ce
s
s
ed
t
o
h
an
d
le
o
u
tlier
s
an
d
m
is
s
i
n
g
v
alu
e
s
to
en
s
u
r
e
q
u
al
it
y
b
ef
o
r
e
s
p
litt
in
g
in
to
tr
ain
i
n
g
an
d
test
in
g
s
et
s
.
3
.
2
.
M
o
del t
ra
ini
ng
a
nd
v
a
li
da
t
io
n
T
h
e
d
ata
u
s
ed
f
o
r
m
o
d
el
esti
m
atio
n
is
h
i
s
to
r
ical
d
ata
d
iv
id
ed
in
to
a
tr
ai
n
i
n
g
s
et
a
n
d
a
n
ev
a
l
u
atio
n
s
et.
T
h
e
d
ata
s
p
litt
in
g
i
s
p
er
f
o
r
m
e
d
u
s
i
n
g
s
tr
ati
f
ied
s
a
m
p
li
n
g
b
a
s
ed
o
n
t
h
e
tar
g
e
t
v
ar
iab
le
lab
els,
w
it
h
a
r
atio
o
f
8
0
% f
o
r
tr
ain
i
n
g
an
d
2
0
%
f
o
r
ev
alu
a
tio
n
.
T
h
e
m
o
d
el
s
ar
e
est
i
m
ated
u
s
i
n
g
t
h
e
P
y
t
h
o
n
lib
r
ar
ies o
f
T
en
s
o
r
Flo
w.
T
h
e
m
o
d
el
tu
n
i
n
g
p
ar
a
m
eter
s
ar
e
d
escr
ib
ed
in
th
e
T
ab
le
1
.
T
h
is
p
ap
er
ch
o
o
s
es
f
o
u
r
i
n
d
icat
o
r
s
to
co
m
p
ar
e
an
d
ev
alu
a
te,
in
cl
u
d
in
g
M
A
E
,
MS
E
,
R
MSE
,
an
d
2
[
3
0
]
:
−
MA
E
i
s
to
m
ea
s
u
r
e
ac
cu
r
ac
y
f
o
r
co
n
tin
u
o
u
s
v
ar
iab
les
[
3
1
]
.
T
h
e
av
er
ag
e
ab
s
o
lu
te
er
r
o
r
h
as th
e
f
o
llo
w
i
n
g
f
o
r
m
u
la:
=
1
∑
|
|
=
1
(
8
)
−
T
h
e
MSE
is
th
e
r
is
k
f
u
n
ctio
n
[
3
2
]
,
c
o
r
r
esp
o
n
d
in
g
to
th
e
ex
p
e
cted
v
alu
e
o
f
t
h
e
s
q
u
ar
ed
er
r
o
r
lo
s
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
.
4
,
A
u
g
u
s
t
20
25
:
1
0
0
0
-
1
0
0
9
1004
=
1
∑
(
−
Ῡ
)
2
=
1
(
9
)
−
R
MSE
p
r
o
v
id
es
in
s
i
g
h
t
in
to
th
e
o
v
er
all
er
r
o
r
d
is
tr
ib
u
tio
n
[
3
3
]
.
I
f
th
ey
ar
e
eq
u
al,
all
er
r
o
r
s
h
av
e
th
e
s
a
m
e
m
ag
n
it
u
d
e.
=
√
1
∑
2
=
1
(
1
0
)
−
2
p
r
o
v
id
es
in
f
o
r
m
atio
n
ab
o
u
t
th
e
g
o
o
d
n
ess
o
f
f
it
o
f
a
m
o
d
el
[
3
4
]
.
T
h
e
v
alu
e
o
f
2
w
ill
r
an
g
e
f
r
o
m
0
to
1
,
w
h
er
e
1
in
d
icate
s
p
er
f
ec
t
p
r
ed
ictio
n
ac
cu
r
ac
y
,
w
h
ile
0
m
ea
n
s
n
o
co
r
r
elatio
n
.
A
h
i
g
h
er
R
²
s
i
g
n
i
f
ies
g
r
ea
ter
m
o
d
el
r
eliab
ilit
y
.
T
h
e
f
o
r
m
u
la
f
o
r
th
is
m
ea
s
u
r
e
is
as
f
o
llo
w
s
:
2
=
1
−
∑
(
−
Ẏ
)
2
=
1
∑
(
−
Ῡ
)
2
=
1
(
1
1
)
T
ab
le
1
.
Mo
d
el
tu
n
i
n
g
p
ar
a
m
e
ter
s
in
T
en
s
o
r
Flo
w
M
o
d
e
l
L
a
y
e
r
D
e
c
r
i
p
t
i
o
n
i
n
T
e
n
so
r
F
l
o
w
R
N
N
[
3
5
]
Emb
e
d
d
i
n
g
T
u
r
n
s
p
o
si
t
i
v
e
i
n
t
e
g
e
r
s
(
i
n
d
e
x
e
s)
i
n
t
o
d
e
n
se
v
e
c
t
o
r
s
o
f
f
i
x
e
d
s
i
z
e
.
T
h
e
c
o
n
f
i
g
u
r
e
d
a
r
g
u
me
n
t
s
a
r
e
i
n
p
u
t
_
d
i
m
=
1
.
0
0
0
,
o
u
t
p
u
t
_
d
i
m
=
6
4
.
L
o
n
g
sh
o
r
t
-
t
e
r
m me
mo
r
y
(
L
S
T
M
)
[
3
6
]
B
a
se
d
o
n
a
v
a
i
l
a
b
l
e
r
u
n
t
i
m
e
h
a
r
d
w
a
r
e
a
n
d
c
o
n
st
r
a
i
n
t
s,
t
h
i
s
l
a
y
e
r
w
i
l
l
c
h
o
o
se
d
i
f
f
e
r
e
n
t
i
mp
l
e
me
n
t
a
t
i
o
n
s
(
c
u
D
N
N
-
b
a
se
d
o
r
b
a
c
k
e
n
d
-
n
a
t
i
v
e
)
t
o
max
i
mi
z
e
t
h
e
p
e
r
f
o
r
man
c
e
.
U
n
i
t
i
s
1
2
8
.
D
e
n
se
D
e
n
se
i
mp
l
e
me
n
t
s
t
h
e
o
p
e
r
a
t
i
o
n
:
o
u
t
p
u
t
=
a
c
t
i
v
a
t
i
o
n
(
d
o
t
(
i
n
p
u
t
,
k
e
r
n
e
l
)
+
b
i
a
s)
w
h
e
r
e
a
c
t
i
v
a
t
i
o
n
i
s
t
h
e
e
l
e
me
n
t
-
w
i
se
a
c
t
i
v
a
t
i
o
n
f
u
n
c
t
i
o
n
p
a
ss
e
d
a
s
t
h
e
a
c
t
i
v
a
t
i
o
n
a
r
g
u
me
n
t
w
i
t
h
1
0
u
n
i
t
s
.
D
e
n
se
D
e
n
se
i
mp
l
e
me
n
t
s
t
h
e
o
p
e
r
a
t
i
o
n
:
o
u
t
p
u
t
=
a
c
t
i
v
a
t
i
o
n
(
d
o
t
(
i
n
p
u
t
,
k
e
r
n
e
l
)
+
b
i
a
s)
w
h
e
r
e
a
c
t
i
v
a
t
i
o
n
i
s
t
h
e
e
l
e
me
n
t
-
w
i
se
a
c
t
i
v
a
t
i
o
n
f
u
n
c
t
i
o
n
p
a
ss
e
d
a
s
t
h
e
a
c
t
i
v
a
t
i
o
n
a
r
g
u
me
n
t
(
u
n
i
t
=
1
)
DNN
[
3
7
]
D
e
n
se
D
e
n
se
i
mp
l
e
me
n
t
s
t
h
e
o
p
e
r
a
t
i
o
n
:
o
u
t
p
u
t
=
a
c
t
i
v
a
t
i
o
n
(
d
o
t
(
i
n
p
u
t
,
k
e
r
n
e
l
)
+
b
i
a
s)
w
h
e
r
e
a
c
t
i
v
a
t
i
o
n
i
s
t
h
e
e
l
e
me
n
t
-
w
i
se
a
c
t
i
v
a
t
i
o
n
f
u
n
c
t
i
o
n
p
a
ss
e
d
a
s t
h
e
a
c
t
i
v
a
t
i
o
n
a
r
g
u
me
n
t
n
a
me
d
r
e
l
u
(
c
o
n
f
i
g
u
r
e
d
a
r
g
u
me
n
t
s:
u
n
i
t
=
6
4
;
a
c
t
i
v
a
t
i
o
n
=
r
e
l
u
)
D
e
n
se
D
e
n
se
i
mp
l
e
me
n
t
s
t
h
e
o
p
e
r
a
t
i
o
n
:
o
u
t
p
u
t
=
a
c
t
i
v
a
t
i
o
n
(
d
o
t
(
i
n
p
u
t
,
k
e
r
n
e
l
)
+
b
i
a
s)
w
h
e
r
e
a
c
t
i
v
a
t
i
o
n
i
s
t
h
e
e
l
e
me
n
t
-
w
i
se
a
c
t
i
v
a
t
i
o
n
f
u
n
c
t
i
o
n
p
a
ss
e
d
a
s t
h
e
a
c
t
i
v
a
t
i
o
n
a
r
g
u
me
n
t
n
a
me
d
r
e
l
u
(
c
o
n
f
i
g
u
r
e
d
a
r
g
u
me
n
t
s:
u
n
i
t
=
6
4
;
a
c
t
i
v
a
t
i
o
n
=
r
e
l
u
)
D
e
n
se
D
e
n
se
i
mp
l
e
me
n
t
s
t
h
e
o
p
e
r
a
t
i
o
n
:
o
u
t
p
u
t
=
a
c
t
i
v
a
t
i
o
n
(
d
o
t
(
i
n
p
u
t
,
k
e
r
n
e
l
)
+
b
i
a
s)
w
h
e
r
e
a
c
t
i
v
a
t
i
o
n
i
s
t
h
e
e
l
e
me
n
t
-
w
i
se
a
c
t
i
v
a
t
i
o
n
f
u
n
c
t
i
o
n
p
a
ss
e
d
a
s
t
h
e
a
c
t
i
v
a
t
i
o
n
a
r
g
u
me
n
t
(
u
n
i
t
=
1
)
3
.
3
.
M
o
del selec
t
io
n a
nd
deplo
y
m
e
nt
A
t
t
h
is
p
h
a
s
e,
a
co
m
p
r
e
h
en
s
i
v
e
ev
al
u
atio
n
o
f
th
e
m
o
d
el
w
il
l
b
e
co
n
d
u
cted
,
co
n
s
id
er
in
g
m
e
n
tio
n
m
es
u
r
es:
M
A
E
,
MSE
,
R
MS
E
,
an
d
R
s
q
u
ar
ed
(
2
)
.
A
co
m
p
ar
ativ
e
an
al
y
s
is
en
s
u
r
e
s
th
e
b
est
-
p
er
f
o
r
m
i
n
g
m
o
d
el
m
ai
n
tai
n
s
s
tab
ili
t
y
ac
r
o
s
s
tr
ain
in
g
a
n
d
test
s
et
s
w
h
il
e
o
p
t
i
m
izi
n
g
k
e
y
m
etr
ics.
T
h
e
s
elec
ted
m
o
d
el
i
s
th
en
i
n
te
g
r
ated
w
it
h
th
e
MI
m
eth
o
d
to
estab
lis
h
a
co
m
p
r
e
h
e
n
s
i
v
e
s
elec
t
io
n
p
r
o
ce
s
s
.
4.
E
XP
E
R
I
M
E
NT
A
L
RE
SUL
T
S
4
.
1
.
M
o
del t
un
ing
a
nd
s
elec
t
io
n
Mo
d
els
ar
e
r
an
k
ed
b
ased
o
n
p
er
f
o
r
m
a
n
ce
m
etr
ics
in
th
e
tr
ain
i
n
g
s
et
w
i
th
tr
en
d
s
a
n
al
y
z
ed
o
n
th
e
ev
alu
a
tio
n
s
et.
T
h
e
Fi
g
u
r
e
2
(
a)
in
d
icate
s
a
d
cr
ea
s
e
th
e
l
o
s
s
f
u
n
ctio
n
i
n
b
o
th
tr
ai
n
i
n
g
an
d
tes
tin
g
.
DN
N
o
u
tp
er
f
o
r
m
s
R
N
N
w
it
h
lo
w
er
M
A
E
(
3
4
6
.
6
4
v
s
.
9
5
8
.
1
7
)
a
n
d
R
M
SE
(
2
8
1
1
.
2
v
s
.
3
1
0
8
.
2
4
)
,
ac
h
iev
i
n
g
9
0
%
r
eliab
ilit
y
(
R
²
=
0
.
9
0
)
.
Ho
w
e
v
er
,
d
u
e
to
o
v
er
f
itt
in
g
te
n
d
en
cies,
R
N
N
is
co
n
s
id
er
ed
th
e
m
o
r
e
o
p
ti
m
al
m
o
d
el
f
o
r
f
u
e
l c
o
n
s
u
m
p
t
io
n
p
r
ed
ictio
n
s
h
o
w
n
as T
ab
le
2
.
B
esid
es,
th
e
m
o
d
el
s
h
o
w
n
o
s
ig
n
s
o
f
u
n
d
er
f
itt
in
g
o
r
o
v
er
f
i
ttin
g
,
w
it
h
b
o
th
tr
ain
i
n
g
an
d
ev
alu
a
tio
n
lo
s
s
f
u
n
c
tio
n
s
d
ec
r
ea
s
i
n
g
.
C
o
n
v
er
g
e
n
ce
p
o
in
t
at
t
h
e
4
th
tr
a
in
i
n
g
ti
m
e
b
ec
au
s
e
n
o
s
ig
n
i
f
i
ca
n
t
ch
a
n
g
e
s
o
cc
u
r
b
ey
o
n
d
th
is
p
o
i
n
t
(
t
h
e
5
th
to
1
8
th
tr
ain
in
g
ti
m
e
s
)
.
T
h
er
ef
o
r
e,
at
th
e
4
th
tr
ain
in
g
s
es
s
io
n
th
e
m
o
d
el
is
m
o
s
t
ef
f
ec
tiv
e.
Si
m
ilar
l
y
,
Fi
g
u
r
e
2
(
b
)
s
h
o
w
t
h
at
t
h
e
lo
s
s
f
u
n
ctio
n
in
tr
ai
n
i
n
g
a
n
d
tes
tin
g
i
s
d
ec
r
ea
s
in
g
.
B
esid
es,
t
h
e
m
o
d
el
d
o
es n
o
t
s
h
o
w
s
i
g
n
s
o
f
u
n
d
er
f
itti
n
g
o
r
o
v
er
f
itti
n
g
.
T
ab
le
2
.
I
n
d
icato
r
s
o
f
t
w
o
m
o
d
els R
NN
a
n
d
DNN
Me
a
s
u
r
i
n
g
i
n
d
i
c
a
t
o
r
s
MA
E
MS
E
R
MS
E
2
DNN
3
4
6
.
6
4
7
9
0
2
8
2
5
.
1
4
2
8
1
1
.
2
0
.
9
0
R
N
N
9
5
8
.
1
7
9
6
6
1
1
8
4
.
1
9
3
1
0
8
.
2
4
0
.
8
7
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
F
u
el
co
n
s
u
mp
tio
n
p
r
ed
ictio
n
o
f c
ivil a
ir
cra
ft
s
u
s
in
g
d
ee
p
le
a
r
n
in
g
:
a
co
mp
a
r
a
tive
…
(
Qu
o
c
Hu
n
g
N
g
u
ye
n
)
1005
(
a)
(
b
)
Fig
u
r
e
2
.
E
v
alu
ate
m
o
d
el
th
r
o
u
g
h
MSE
:
(
a)
lo
s
s
f
u
n
ctio
n
in
tr
ain
i
n
g
a
n
d
test
i
n
g
o
f
R
NN
m
o
d
el
an
d
(
b
)
lo
s
s
f
u
n
ctio
n
in
tr
ai
n
i
n
g
a
n
d
test
i
n
g
o
f
DNN
m
o
d
el
A
t
th
e
s
a
m
e
ti
m
e,
t
h
e
m
o
d
el
’
s
lo
s
s
f
u
n
ctio
n
o
n
tr
ai
n
i
n
g
a
n
d
ev
alu
a
tio
n
s
et
b
o
th
d
ec
r
ea
s
ed
,
r
ea
ch
in
g
co
n
v
er
g
e
n
ce
p
o
in
t a
t t
h
e
2
nd
tr
ain
i
n
g
ti
m
e,
w
it
h
n
o
s
i
g
n
if
ican
t c
h
a
n
g
e
s
f
r
o
m
t
h
e
5
th
to
5
0
th
it
er
atio
n
.
T
h
er
ef
o
r
e,
at
th
e
s
ec
o
n
d
tr
ai
n
i
n
g
s
es
s
io
n
th
e
m
o
d
el
is
m
o
s
t
e
f
f
ec
t
iv
e.
Ho
w
e
v
er
,
th
e
ch
ar
t
i
n
d
icate
s
s
lig
h
t
u
n
d
er
f
itt
in
g
,
s
u
g
g
e
s
ti
n
g
th
e
n
ee
d
f
o
r
ad
d
itio
n
al
p
ar
a
m
eter
s
o
r
a
m
o
r
e
co
m
p
lex
m
o
d
el
to
p
r
ev
en
t f
u
r
t
h
e
r
u
n
d
er
f
it
tin
g
.
T
h
e
s
h
o
w
n
a
s
F
ig
u
r
e
s
3
(
a)
an
d
(
b
)
co
m
p
ar
e
t
h
e
r
ea
l
v
a
lu
e
a
n
d
p
r
ed
icted
v
alu
e,
s
h
o
w
i
n
g
8
7
%
ac
cu
r
ac
y
f
o
r
R
NN
an
d
9
0
%
f
o
r
DNN,
c
o
n
f
ir
m
in
g
DNN
as
th
e
b
etter
m
o
d
el.
B
esid
es,
th
e
C
NN
m
o
d
el
s
tr
u
g
g
les
w
i
th
v
al
u
es
in
th
e
4
0
,
0
0
0
–
6
0
,
0
0
0
r
an
g
e,
lead
in
g
to
er
r
o
r
s
.
Me
an
w
h
ile,
th
e
DNN
m
o
d
el
i
s
f
o
r
ec
asti
n
g
w
it
h
a
lo
w
er
er
r
o
r
p
r
o
b
ab
ilit
y
.
T
h
er
ef
o
r
e,
th
er
e
ar
e
t
w
o
d
ir
ec
tio
n
s
to
ad
j
u
s
t
th
i
s
ac
c
u
r
ac
y
:
(
i
)
r
ef
in
i
n
g
t
h
e
m
o
d
el
to
b
etter
ca
p
tu
r
e
v
al
u
e
f
lu
ct
u
atio
n
s
o
f
air
cr
af
t
an
d
(
ii
)
ex
p
a
n
d
in
g
t
h
e
d
ataset,
as
t
h
e
cu
r
r
e
n
t
s
tu
d
y
is
b
ased
o
n
a
s
i
n
g
le
f
li
g
h
t.
W
ith
th
e
ab
o
v
e
ac
cu
r
ac
y
,
t
h
e
m
o
d
el
s
’
ac
cu
r
ac
y
ali
g
n
s
w
it
h
[
3
8
]
w
h
o
s
e
ac
h
iv
ed
ea
c
h
f
l
ig
h
t p
h
a
s
e
f
l
u
ct
u
ates a
r
o
u
n
d
9
0
-
9
9
% a
cc
u
r
ac
y
; a
n
d
9
6
% d
u
r
in
g
ta
k
eo
f
f
.
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
.
4
,
A
u
g
u
s
t
20
25
:
1
0
0
0
-
1
0
0
9
1006
(
a)
(
b
)
Fig
u
r
e
3
.
E
v
alu
ate
m
o
d
el
th
r
o
u
g
h
ac
t
u
al
v
s
p
r
ed
icted
v
alu
es
:
(
a)
p
r
e
d
ictio
n
r
esu
lt
s
o
f
t
h
e
R
NN
m
o
d
el
an
d
(
b
)
p
r
ed
ictio
n
r
esu
lts
o
f
th
e
DN
N
m
o
d
el
4
.
2
.
Dis
cus
s
io
n
T
h
is
s
tu
d
y
p
r
o
v
id
es
e
v
id
en
ce
th
at
v
ar
io
u
s
f
ac
to
r
s
s
u
c
h
as
ca
lib
r
ated
air
s
p
ee
d
,
s
tatic
air
tem
p
er
at
u
r
e,
p
r
ess
u
r
e
altit
u
d
e,
w
i
n
d
s
p
ee
d
at
th
e
co
c
k
p
it,
an
d
s
id
e
w
i
n
d
s
p
ee
d
s
i
g
n
i
f
ica
n
tl
y
i
m
p
ac
t
civ
il
a
ir
cr
af
t
f
u
el
co
n
s
u
m
p
tio
n
.
B
y
le
v
er
ag
i
n
g
t
w
o
d
ee
p
lear
n
in
g
m
o
d
el
s
DNN
an
d
R
NN,
th
e
s
tu
d
y
h
i
g
h
lig
h
ts
t
h
e
ef
f
ec
ti
v
en
e
s
s
o
f
p
ar
a
m
eter
t
u
n
i
n
g
to
e
n
h
a
n
c
e
p
r
ed
ictio
n
ac
cu
r
ac
y
.
No
tab
l
y
,
th
e
DNN
m
o
d
el,
w
h
e
n
co
m
b
in
ed
w
i
th
th
e
MI
m
et
h
o
d
f
o
r
f
ea
t
u
r
e
s
elec
tio
n
,
ac
h
iev
ed
s
u
p
er
io
r
p
er
f
o
r
m
an
c
e
(
R
²=
9
0
%,
MA
E
=3
4
6
.
6
4
,
M
SE=
7
,
9
0
2
,
8
2
5
.
1
4
)
,
o
u
tp
er
f
o
r
m
i
n
g
R
NN.
I
n
co
m
p
ar
is
o
n
w
it
h
[
3
9
]
–
[
4
1
]
,
t
h
is
r
esear
ch
ad
o
p
ts
a
b
r
o
ad
er
ap
p
r
o
ac
h
,
co
n
s
id
er
in
g
m
u
ltip
le
p
h
ase
s
an
d
i
n
teg
r
ati
n
g
ex
p
licit
f
ea
t
u
r
e
s
elec
tio
n
.
Ad
d
itio
n
all
y
,
t
h
e
s
t
u
d
y
e
m
p
h
as
izes
th
e
ad
v
a
n
ta
g
e
o
f
d
ee
p
lear
n
in
g
o
v
er
tr
ad
itio
n
al
s
tati
s
tical
m
et
h
o
d
s
,
s
h
o
w
i
n
g
th
a
t
tu
n
i
n
g
m
o
d
el
p
ar
am
eter
s
s
ig
n
i
f
ica
n
tl
y
en
h
a
n
ce
s
p
r
ed
ictio
n
ac
cu
r
ac
y
.
B
esid
es,
ea
r
lier
ap
p
r
o
ac
h
es
o
f
ten
r
elied
o
n
tr
ad
itio
n
al
s
ta
t
is
tical
m
et
h
o
d
s
o
r
d
ef
au
lt
co
n
f
i
g
u
r
atio
n
s
o
f
m
ac
h
in
e
lear
n
i
n
g
al
g
o
r
ith
m
s
,
th
i
s
s
t
u
d
y
s
h
o
w
s
th
at
p
ar
a
m
eter
t
u
n
in
g
ca
n
s
ig
n
i
f
ica
n
tl
y
i
m
p
r
o
v
e
p
r
ed
icti
v
e
ac
cu
r
ac
y
.
Ho
w
e
v
er
,
li
m
itatio
n
s
e
x
i
s
t,
i
n
clu
d
in
g
r
elia
n
ce
o
n
s
p
ec
i
f
ic
e
n
v
ir
o
n
m
e
n
tal
v
ar
iab
les
t
h
at
m
a
y
a
f
f
e
c
t
g
en
er
aliza
b
ili
t
y
a
n
d
th
e
ab
s
e
n
ce
o
f
r
ea
l
-
ti
m
e
v
al
id
atio
n
.
T
h
e
R
NN
m
o
d
el
’
s
lo
w
er
p
er
f
o
r
m
an
ce
s
u
g
g
est
s
its
te
m
p
o
r
al
lear
n
in
g
p
o
ten
tial
is
n
o
t
f
u
l
l
y
u
t
ilized
.
Fu
t
u
r
e
r
esear
ch
s
h
o
u
ld
ex
p
lo
r
e
h
y
b
r
id
d
e
ep
lear
n
in
g
m
o
d
els
(
e.
g
.
,
DNN
w
it
h
r
ec
u
r
r
en
t
o
r
t
r
an
s
f
o
r
m
er
-
b
a
s
ed
ar
ch
itectu
r
es)
to
ca
p
tu
r
e
b
o
th
te
m
p
o
r
al
an
d
s
p
atia
l
d
ep
en
d
en
cies.
T
r
an
s
f
er
lear
n
i
n
g
co
u
ld
f
u
r
th
er
en
h
a
n
ce
ad
ap
tab
ilit
y
ac
r
o
s
s
d
if
f
er
en
t
air
cr
af
t
t
y
p
e
s
an
d
f
lig
h
t
co
n
d
itio
n
s
.
T
o
im
p
r
o
v
e
p
r
ac
tical
ap
p
licab
ilit
y
,
f
u
t
u
r
e
w
o
r
k
s
h
o
u
ld
f
o
cu
s
o
n
p
h
ase
-
s
p
e
ci
f
ic
m
o
d
eli
n
g
,
r
ea
l
-
ti
m
e
v
alid
atio
n
,
m
u
lti
-
s
o
u
r
ce
d
ata
in
te
g
r
atio
n
,
an
d
l
ig
h
t
w
ei
g
h
t
d
ee
p
lear
n
i
n
g
ar
c
h
itect
u
r
es
to
d
ev
elo
p
s
ca
lab
le
an
d
in
ter
p
r
etab
le
f
u
el
co
n
s
u
m
p
tio
n
p
r
ed
ictio
n
m
o
d
els,
o
p
ti
m
izi
n
g
av
ia
tio
n
o
p
er
atio
n
s
an
d
r
ed
u
ci
n
g
C
O₂
e
m
is
s
io
n
s
.
5.
CO
NCLU
SI
O
N
T
h
e
f
in
d
in
g
s
o
f
th
i
s
s
tu
d
y
co
n
f
ir
m
t
h
at
DNN
w
ith
o
p
ti
m
ize
d
p
a
r
am
eter
tu
n
i
n
g
an
d
f
ea
tu
r
e
s
elec
tio
n
,
o
u
tp
er
f
o
r
m
R
NN
i
n
p
r
ed
ictin
g
a
ir
cr
af
t
f
u
e
l
co
n
s
u
m
p
tio
n
.
T
h
e
co
m
b
i
n
atio
n
o
f
MI
e
v
alu
a
tio
n
e
n
h
an
ce
s
au
to
m
at
io
n
,
en
ab
li
n
g
f
a
s
ter
f
o
r
ec
asti
n
g
a
n
d
ea
r
l
y
d
etec
ti
o
n
o
f
f
u
el
a
n
o
m
al
ies,
i
m
p
r
o
v
in
g
m
ain
ten
a
n
ce
ef
f
icien
c
y
an
d
co
s
t
-
ef
f
ec
ti
v
e
n
ess
.
Desp
ite
its
ef
f
ec
t
iv
e
n
es
s
,
th
e
m
o
d
el
h
as
s
e
v
er
al
li
m
i
t
atio
n
s
th
a
t
r
eq
u
ir
e
i
m
p
r
o
v
e
m
en
t.
T
h
e
s
t
u
d
y
i
s
b
ased
o
n
d
ata
f
r
o
m
a
s
in
g
le
Air
b
u
s
A
3
2
0
NE
O
f
li
g
h
t,
lack
i
n
g
v
al
id
atio
n
ac
r
o
s
s
o
th
er
A
ir
b
u
s
an
d
B
o
ein
g
m
o
d
els,
w
h
ic
h
d
if
f
er
in
s
ea
t
in
g
ca
p
ac
it
y
,
f
li
g
h
t
s
p
ee
d
,
an
d
w
ei
g
h
t.
I
t
is
n
ec
ess
ar
y
to
ex
p
an
d
a
n
d
b
u
ild
m
o
r
e
m
o
d
el
s
f
o
r
u
s
e
w
it
h
o
th
er
air
cr
a
f
t
m
o
d
els.
Seco
n
d
l
y
,
t
h
e
d
atase
t
is
li
m
ited
,
co
v
er
in
g
o
n
l
y
o
n
e
f
lig
h
t
w
it
h
o
u
t
d
is
t
i
n
g
u
i
s
h
i
n
g
b
et
w
ee
n
tak
eo
f
f
,
cr
u
is
i
n
g
,
an
d
lan
d
in
g
p
h
ase
s
,
af
f
ec
tin
g
p
r
ed
ictio
n
ac
cu
r
ac
y
.
T
h
e
m
o
d
el
h
as
n
o
t
b
ee
n
ad
j
u
s
ted
to
p
r
e
d
ict
ea
c
h
p
h
ase
b
u
t
is
c
u
r
r
en
tl
y
u
s
in
g
a
f
i
x
ed
m
o
d
el
to
p
r
ed
ict
th
e
en
tire
f
li
g
h
t.
T
h
ir
d
l
y
,
t
h
e
u
s
a
g
e
m
o
d
els
a
r
e
th
e
f
o
u
n
d
atio
n
m
o
d
els
f
o
r
f
o
r
ec
asti
n
g
f
u
e
l
co
n
s
u
m
p
tio
n
.
An
o
th
er
ch
al
len
g
e
is
h
a
n
d
lin
g
ab
n
o
r
m
al
v
alu
e
s
in
Q
A
R
d
ata,
p
ar
ticu
lar
l
y
i
n
co
r
r
ec
ted
ai
r
s
p
ee
d
an
d
f
u
el
f
lo
w
,
w
h
ic
h
d
is
to
r
t
p
r
ed
ictio
n
s
.
W
h
ile
L
ST
M
in
R
NN
h
elp
s
m
it
ig
ate
t
h
is
,
h
i
g
h
er
r
o
r
r
ates
p
er
s
is
t,
n
ec
es
s
itati
n
g
m
o
r
e
ad
v
an
ce
d
tech
n
iq
u
es.
Fi
n
all
y
,
th
e
m
o
d
el
r
elies
s
o
lel
y
o
n
air
cr
af
t
-
r
e
co
r
d
ed
p
ar
am
eter
s
,
w
it
h
o
u
t
in
co
r
p
o
r
atin
g
ex
ter
n
al
f
ac
to
r
s
li
k
e
w
ea
t
h
er
an
d
a
ir
tr
af
f
ic,
l
i
m
iti
n
g
i
ts
ad
ap
tab
ilit
y
to
r
ea
l
-
w
o
r
ld
co
n
d
itio
n
s
.
T
o
s
o
lv
e
th
i
s
p
r
o
b
lem
,
t
h
e
m
o
d
el
n
ee
d
s
to
r
e
s
ea
r
ch
m
o
r
e
ex
ter
n
al
f
ac
to
r
s
to
ca
lcu
late
a
n
ac
ce
p
tab
le
in
d
ex
o
r
v
alu
e
r
an
g
e
to
m
ea
s
u
r
e
t
h
ese
f
ac
to
r
s
in
t
h
e
m
o
d
el.
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
F
u
el
co
n
s
u
mp
tio
n
p
r
ed
ictio
n
o
f c
ivil a
ir
cra
ft
s
u
s
in
g
d
ee
p
le
a
r
n
in
g
:
a
co
mp
a
r
a
tive
…
(
Qu
o
c
Hu
n
g
N
g
u
ye
n
)
1007
R
esear
ch
o
n
MI
v
ar
iab
le
s
elec
tio
n
m
eth
o
d
an
d
d
ee
p
lear
n
i
n
g
m
o
d
els
h
as led
to
a
n
au
to
m
at
ed
p
r
o
ce
s
s
f
o
r
f
u
el
p
r
ed
ictio
n
,
o
p
en
in
g
n
e
w
a
v
e
n
u
e
s
f
o
r
i
m
p
r
o
v
e
m
en
t.
Sp
ec
i
f
icall
y
,
t
h
er
e
ar
e
t
w
o
d
ir
ec
tio
n
s
o
f
d
ev
elo
p
m
en
t
:
d
ep
th
an
d
b
r
ea
d
th
.
Dev
e
lo
p
in
g
in
a
b
r
o
ad
d
ir
e
ctio
n
,
r
ea
l
-
ti
m
e
a
n
o
m
al
y
d
etec
tio
n
ca
n
b
e
b
u
i
lt
to
to
aler
t
air
lin
es
o
f
p
o
ten
tial
r
i
s
k
s
an
d
p
r
ed
ict
f
lig
h
t
d
ela
y
s
d
u
e
to
w
ea
t
h
er
o
r
o
p
er
ati
o
n
al
f
ac
to
r
s
.
A
ir
cr
a
f
t
to
p
r
o
m
p
tl
y
tak
e
m
ea
s
u
r
e
s
to
p
r
ev
en
t
a
v
iatio
n
ac
cid
en
t
s
o
r
p
o
ten
tial
an
d
r
is
k
y
tec
h
n
ical
er
r
o
r
s
.
I
n
ter
m
s
o
f
d
ep
th
,
th
e
m
o
d
el
ca
n
b
e
d
e
v
elo
p
ed
to
in
co
r
p
o
r
ate
ad
d
itio
n
al
v
ar
iab
les
b
e
y
o
n
d
air
cr
af
t
tr
ac
k
i
n
g
d
ata
to
en
h
a
n
ce
ac
cu
r
ac
y
,
m
i
n
i
m
ize
e
r
r
o
r
s
,
an
d
o
p
tim
ize
f
u
el
e
f
f
icie
n
c
y
.
ACK
NO
WL
E
D
G
M
E
NT
S
T
h
is
r
esear
ch
is
f
u
n
d
ed
b
y
U
n
iv
er
s
it
y
o
f
E
co
n
o
m
ics Ho
C
h
i
Min
h
C
it
y
,
Viet
n
a
m
(
UE
H)
F
UNDIN
G
I
NF
O
RM
AT
I
O
N
T
h
e
au
th
o
r
s
d
ec
lar
e
th
at
n
o
ex
ter
n
al
f
u
n
d
i
n
g
w
as
r
ec
ei
v
ed
to
s
u
p
p
o
r
t
th
e
r
esear
ch
,
d
ata
c
o
llectio
n
,
an
al
y
s
is
,
o
r
w
r
iti
n
g
o
f
th
is
m
a
n
u
s
cr
ip
t.
T
h
is
w
o
r
k
w
a
s
ca
r
r
ied
o
u
t
in
d
ep
en
d
en
tl
y
w
it
h
o
u
t
f
i
n
an
cia
l
ass
is
tan
ce
f
r
o
m
an
y
p
u
b
lic,
co
m
m
er
cial,
o
r
n
o
t
-
f
o
r
-
p
r
o
f
i
t f
u
n
d
in
g
ag
e
n
c
y
.
A
u
t
h
o
r
s
s
tate
n
o
f
u
n
d
in
g
i
n
v
o
l
v
ed
.
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
Qu
o
c
Hu
n
g
Ng
u
y
en
✓
✓
✓
✓
✓
✓
✓
✓
✓
Ho
an
g
L
a
n
Ng
u
y
en
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
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
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
th
e
y
h
av
e
n
o
k
n
o
w
n
co
m
p
eti
n
g
f
in
an
cial
in
ter
es
ts
o
r
p
er
s
o
n
al
r
el
atio
n
s
h
ip
s
th
at
co
u
ld
h
av
e
ap
p
ea
r
ed
to
in
f
l
u
en
ce
t
h
e
w
o
r
k
r
ep
o
r
ted
in
t
h
is
p
ap
er
.
Fu
r
th
er
m
o
r
e,
th
e
au
th
o
r
s
h
av
e
n
o
n
o
n
-
f
i
n
an
cia
l
co
m
p
etin
g
in
ter
e
s
ts
,
s
u
c
h
as
p
o
liti
ca
l,
id
eo
lo
g
ical,
ac
ad
em
ic,
o
r
in
tellectu
al
co
n
f
licts
,
in
r
elatio
n
to
th
e
co
n
te
n
t o
f
t
h
is
m
a
n
u
s
cr
ip
t.
Au
t
h
o
r
s
s
tate
n
o
co
n
f
lict o
f
in
ter
est.
I
NF
O
RM
E
D
CO
NSE
N
T
T
h
is
p
ap
er
d
o
es
n
o
t
in
v
o
lv
e
an
y
h
u
m
a
n
p
ar
ticip
an
ts
,
p
er
s
o
n
al
d
ata,
o
r
id
en
tif
iab
le
in
f
o
r
m
atio
n
.
T
h
er
ef
o
r
e,
in
f
o
r
m
ed
co
n
s
e
n
t
w
a
s
n
o
t
r
eq
u
ir
ed
.
A
ll
d
ata
u
ti
lized
in
th
i
s
r
esear
ch
w
er
e
d
er
iv
ed
f
r
o
m
air
cr
af
t
s
y
s
te
m
r
ec
o
r
d
in
g
s
a
n
d
t
ec
h
n
ic
al
s
o
u
r
ce
s
t
h
at
d
o
n
o
t
co
n
tain
an
y
p
r
i
v
ate
o
r
s
en
s
iti
v
e
i
n
f
o
r
m
atio
n
.
T
h
e
a
u
th
o
r
s
co
n
f
ir
m
th
a
t th
e
s
tu
d
y
co
m
p
lie
s
w
ith
et
h
ical
r
esear
c
h
s
ta
n
d
ar
d
s
an
d
in
s
titu
tio
n
al
g
u
id
elin
e
s
.
E
T
H
I
CAL AP
P
RO
V
AL
T
h
is
r
esear
ch
d
id
n
o
t
in
v
o
lv
e
an
y
ex
p
er
i
m
en
ts
o
n
h
u
m
a
n
p
ar
ticip
an
ts
o
r
an
i
m
al
s
.
T
h
er
ef
o
r
e,
eth
ical
r
ev
ie
w
a
n
d
ap
p
r
o
v
al
w
er
e
n
o
t
ap
p
licab
le.
A
ll
d
ata
u
s
ed
i
n
th
is
s
t
u
d
y
w
er
e
co
llected
f
r
o
m
a
ir
cr
af
t
s
y
s
te
m
s
a
n
d
o
n
b
o
ar
d
s
en
s
o
r
s
,
w
h
ic
h
d
o
n
o
t
in
clu
d
e
p
er
s
o
n
al,
m
ed
ical,
o
r
b
io
lo
g
ical
in
f
o
r
m
atio
n
.
T
h
e
au
th
o
r
s
a
f
f
ir
m
th
a
t
th
e
s
tu
d
y
w
a
s
co
n
d
u
cted
in
ac
co
r
d
an
ce
w
i
th
ap
p
licab
le
in
s
ti
tu
tio
n
a
l
p
o
licies,
eth
ical
r
esear
ch
p
r
in
cip
les,
an
d
n
atio
n
al
r
e
g
u
latio
n
s
co
n
ce
r
n
i
n
g
n
o
n
-
h
u
m
an
-
s
u
b
j
ec
t r
esear
ch
.
No
eth
ical
v
io
latio
n
s
o
cc
u
r
r
ed
d
u
r
in
g
t
h
e
co
u
r
s
e
o
f
th
i
s
p
ap
er
.
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
.
4
,
A
u
g
u
s
t
20
25
:
1
0
0
0
-
1
0
0
9
1008
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
Qu
ic
k
A
cc
es
s
R
ec
o
r
d
er
(
QAR)
f
li
g
h
t
-
d
ata
u
s
ed
i
n
t
h
is
s
t
u
d
y
w
er
e
o
b
tain
ed
u
n
d
er
a
co
n
f
id
e
n
tialit
y
a
g
r
ee
m
e
n
t
with
t
h
e
p
ar
tn
er
air
li
n
e
an
d
co
n
tain
co
m
m
er
ciall
y
s
en
s
iti
v
e
o
p
er
atio
n
al
in
f
o
r
m
atio
n
.
T
h
er
ef
o
r
e,
th
e
r
a
w
Q
AR
f
iles
ca
n
n
o
t b
e
s
h
ar
ed
p
u
b
licl
y
.
P
r
o
ce
s
s
ed
f
ea
tu
r
e
tab
le
s
,
m
o
d
el
-
tr
ai
n
in
g
s
cr
ip
ts
,
a
n
d
a
d
e
-
id
en
ti
f
ied
s
y
n
th
e
tic
s
a
m
p
le
s
u
f
f
i
cien
t
to
r
ep
r
o
d
u
ce
th
e
r
ep
o
r
ted
r
esu
lts
ar
e
a
v
aila
b
le
f
r
o
m
t
h
e
co
r
r
esp
o
n
d
in
g
a
u
th
o
r
,
Qu
o
c
H
u
n
g
N
g
u
y
e
n
(
h
u
n
g
n
q
@
u
e
h
.
ed
u
.
v
n
)
,
u
p
o
n
r
ea
s
o
n
ab
le
r
eq
u
est
f
o
r
n
o
n
-
co
m
m
er
cial
r
esear
ch
p
u
r
p
o
s
es
an
d
s
u
b
j
ec
t
to
a
s
ig
n
ed
n
o
n
-
d
is
clo
s
u
r
e
ag
r
ee
m
e
n
t.
RE
F
E
R
E
NC
E
S
[
1
]
J.
Y
a
n
t
o
a
n
d
R
.
P
.
L
i
e
m,
“
A
i
r
c
r
a
f
t
f
u
e
l
b
u
r
n
p
e
r
f
o
r
man
c
e
st
u
d
y
:
A
d
a
t
a
-
e
n
h
a
n
c
e
d
mo
d
e
l
i
n
g
a
p
p
r
o
a
c
h
,
”
T
r
a
n
sp
o
rt
a
t
i
o
n
Re
s
e
a
rc
h
Pa
rt
D
:
T
ra
n
s
p
o
rt
a
n
d
E
n
v
i
ro
n
m
e
n
t
,
v
o
l
.
6
5
,
p
p
.
5
7
4
–
5
9
5
,
D
e
c
.
2
0
1
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
t
r
d
.
2
0
1
8
.
0
9
.
0
1
4
.
[
2
]
D
.
S
.
L
e
e
e
t
a
l
.
,
“
A
v
i
a
t
i
o
n
a
n
d
g
l
o
b
a
l
c
l
i
mat
e
c
h
a
n
g
e
i
n
t
h
e
2
1
s
t
c
e
n
t
u
r
y
,
”
At
m
o
sp
h
e
ri
c
E
n
v
i
r
o
n
m
e
n
t
,
v
o
l
.
4
3
,
n
o
.
2
2
–
2
3
,
p
p
.
3
5
2
0
–
3
5
3
7
,
Ju
l
.
2
0
0
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
t
mo
se
n
v
.
2
0
0
9
.
0
4
.
0
2
4
.
[
3
]
K
.
s
.
Y
i
n
,
P
.
D
a
r
g
u
sc
h
,
a
n
d
A
.
H
a
l
o
g
,
“
A
n
a
n
a
l
y
si
s
o
f
t
h
e
g
r
e
e
n
h
o
u
se
g
a
s
e
mi
ssi
o
n
s
p
r
o
f
i
l
e
o
f
a
i
r
l
i
n
e
s
f
l
y
i
n
g
t
h
e
A
u
st
r
a
l
i
a
n
i
n
t
e
r
n
a
t
i
o
n
a
l
mark
e
t
,
”
J
o
u
r
n
a
l
o
f
Ai
r
T
ra
n
s
p
o
r
t
M
a
n
a
g
e
m
e
n
t
,
v
o
l
.
4
7
,
p
p
.
2
1
8
–
2
2
9
,
A
u
g
.
2
0
1
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
a
i
r
t
r
a
ma
n
.
2
0
1
5
.
0
6
.
0
0
5
.
[
4
]
J.
M
.
C
o
l
l
i
n
s
a
n
d
D
.
M
c
L
a
r
t
y
,
“
A
l
l
-
e
l
e
c
t
r
i
c
c
o
mm
e
r
c
i
a
l
a
v
i
a
t
i
o
n
w
i
t
h
so
l
i
d
o
x
i
d
e
f
u
e
l
c
e
l
l
-
g
a
s
t
u
r
b
i
n
e
-
b
a
t
t
e
r
y
h
y
b
r
i
d
s,
”
Ap
p
l
i
e
d
En
e
r
g
y
,
v
o
l
.
2
6
5
,
p
.
1
1
4
7
8
7
,
M
a
y
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
p
e
n
e
r
g
y
.
2
0
2
0
.
1
1
4
7
8
7
.
[
5
]
J.
K
.
B
r
u
e
c
k
n
e
r
a
n
d
C
.
A
b
r
e
u
,
“
A
i
r
l
i
n
e
f
u
e
l
u
s
a
g
e
a
n
d
c
a
r
b
o
n
e
mi
ss
i
o
n
s:
D
e
t
e
r
mi
n
i
n
g
f
a
c
t
o
r
s,”
J
o
u
r
n
a
l
o
f
A
i
r
T
ra
n
s
p
o
r
t
Ma
n
a
g
e
m
e
n
t
,
v
o
l
.
6
2
,
p
p
.
1
0
–
1
7
,
J
u
l
.
2
0
1
7
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
a
i
r
t
r
a
ma
n
.
2
0
1
7
.
0
1
.
0
0
4
.
[
6
]
S
.
Ek
i
c
i
,
M
.
A
y
a
r
,
U
.
K
i
l
i
c
,
a
n
d
T
.
H
.
K
a
r
a
k
o
c
,
“
P
e
r
f
o
r
man
c
e
b
a
se
d
a
n
a
l
y
si
s
f
o
r
t
h
e
A
n
k
a
r
a
-
L
o
n
d
o
n
r
o
u
t
e
i
n
t
e
r
ms
o
f
e
mi
ssi
o
n
s
a
n
d
f
u
e
l
c
o
n
s
u
mp
t
i
o
n
o
f
d
i
f
f
e
r
e
n
t
c
o
mb
i
n
a
t
i
o
n
s
o
f
a
i
r
c
r
a
f
t
/
e
n
g
i
n
e
:
A
n
I
M
P
A
C
T
a
p
p
l
i
c
a
t
i
o
n
,
”
J
o
u
r
n
a
l
o
f
A
i
r
T
r
a
n
s
p
o
rt
Ma
n
a
g
e
m
e
n
t
,
v
o
l
.
1
0
8
,
p
.
1
0
2
3
5
7
,
M
a
y
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
a
i
r
t
r
a
ma
n
.
2
0
2
2
.
1
0
2
3
5
7
.
[
7
]
S
.
G
ö
ss
l
i
n
g
a
n
d
J.
H
i
g
h
a
m,
“
T
h
e
L
o
w
-
C
a
r
b
o
n
I
mp
e
r
a
t
i
v
e
:
D
e
st
i
n
a
t
i
o
n
M
a
n
a
g
e
me
n
t
u
n
d
e
r
U
r
g
e
n
t
C
l
i
ma
t
e
C
h
a
n
g
e
,
”
J
o
u
rn
a
l
o
f
T
ra
v
e
l
Re
se
a
r
c
h
,
v
o
l
.
6
0
,
n
o
.
6
,
p
p
.
1
1
6
7
–
1
1
7
9
,
J
u
l
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
7
7
/
0
0
4
7
2
8
7
5
2
0
9
3
3
6
7
9
.
[
8
]
S
.
B
e
c
k
e
n
a
n
d
B
.
M
a
c
k
e
y
,
“
W
h
a
t
r
o
l
e
f
o
r
o
f
f
se
t
t
i
n
g
a
v
i
a
t
i
o
n
g
r
e
e
n
h
o
u
s
e
g
a
s
e
mi
ssi
o
n
s
i
n
a
d
e
e
p
-
c
u
t
c
a
r
b
o
n
w
o
r
l
d
?
,
”
J
o
u
r
n
a
l
o
f
Ai
r Tr
a
n
s
p
o
rt
M
a
n
a
g
e
m
e
n
t
,
v
o
l
.
6
3
,
p
p
.
7
1
–
8
3
,
A
u
g
.
2
0
1
7
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
a
i
r
t
r
a
m
a
n
.
2
0
1
7
.
0
5
.
0
0
9
.
[
9
]
C
.
A
.
A
r
t
e
r
,
J.
J.
B
u
o
n
o
c
o
r
e
,
C
.
M
o
n
i
r
u
z
z
a
man
,
D
.
Y
a
n
g
,
J.
H
u
a
n
g
,
a
n
d
S
.
A
r
u
n
a
c
h
a
l
a
m,
“
A
i
r
q
u
a
l
i
t
y
a
n
d
h
e
a
l
t
h
-
r
e
l
a
t
e
d
i
m
p
a
c
t
s
o
f
t
r
a
d
i
t
i
o
n
a
l
a
n
d
a
l
t
e
r
n
a
t
e
j
e
t
f
u
e
l
s
f
r
o
m
a
i
r
p
o
r
t
a
i
r
c
r
a
f
t
o
p
e
r
a
t
i
o
n
s
i
n
t
h
e
U
.
S
.
,
”
E
n
v
i
r
o
n
m
e
n
t
I
n
t
e
r
n
a
t
i
o
n
a
l
,
v
o
l
.
1
5
8
,
p
.
1
0
6
9
5
8
,
Jan
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
n
v
i
n
t
.
2
0
2
1
.
1
0
6
9
5
8
.
[
1
0
]
M
.
G
r
o
t
e
,
I
.
W
i
l
l
i
a
ms,
a
n
d
J
.
P
r
e
st
o
n
,
“
D
i
r
e
c
t
c
a
r
b
o
n
d
i
o
x
i
d
e
e
mi
ssi
o
n
s
f
r
o
m
c
i
v
i
l
a
i
r
c
r
a
f
t
,
”
At
m
o
s
p
h
e
ri
c
E
n
v
i
r
o
n
m
e
n
t
,
v
o
l
.
9
5
,
p
p
.
2
1
4
–
2
2
4
,
O
c
t
.
2
0
1
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
t
mo
se
n
v
.
2
0
1
4
.
0
6
.
0
4
2
.
[
1
1
]
G
.
P
.
B
r
a
sse
u
r
e
t
a
l
.
,
“
I
mp
a
c
t
o
f
a
v
i
a
t
i
o
n
o
n
c
l
i
ma
t
e
:
F
A
A
’
s
A
v
i
a
t
i
o
n
C
l
i
ma
t
e
C
h
a
n
g
e
R
e
se
a
r
c
h
I
n
i
t
i
a
t
i
v
e
(
A
C
C
R
I
)
p
h
a
se
I
I
,
”
Bu
l
l
e
t
i
n
o
f
t
h
e
Am
e
r
i
c
a
n
M
e
t
e
o
r
o
l
o
g
i
c
a
l
S
o
c
i
e
t
y
,
v
o
l
.
9
7
,
n
o
.
4
,
p
p
.
5
6
1
–
5
8
3
,
A
p
r
.
2
0
1
6
,
d
o
i
:
1
0
.
1
1
7
5
/
B
A
M
S
-
D
-
13
-
0
0
0
8
9
.
1
.
[
1
2
]
S
.
E
k
i
c
i
,
M
.
A
y
a
r
,
I
.
O
r
h
a
n
,
a
n
d
T
.
H
.
K
a
r
a
k
o
c
,
“
C
r
u
i
se
a
l
t
i
t
u
d
e
p
a
t
t
e
r
n
s
f
o
r
mi
n
i
mi
z
i
n
g
f
u
e
l
c
o
n
s
u
mp
t
i
o
n
a
n
d
e
m
i
s
si
o
n
:
A
d
e
t
a
i
l
e
d
a
n
a
l
y
si
s o
f
f
i
v
e
p
r
o
mi
n
e
n
t
a
i
r
c
r
a
f
t
,
”
E
n
e
r
g
y
,
v
o
l
.
2
9
5
,
p
.
1
3
0
9
8
9
,
M
a
y
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
n
e
r
g
y
.
2
0
2
4
.
1
3
0
9
8
9
.
[
1
3
]
D
.
S
.
L
e
e
e
t
a
l
.
,
“
T
r
a
n
s
p
o
r
t
i
mp
a
c
t
s
o
n
a
t
mo
sp
h
e
r
e
a
n
d
c
l
i
ma
t
e
:
A
v
i
a
t
i
o
n
,
”
At
m
o
sp
h
e
ri
c
E
n
v
i
ro
n
m
e
n
t
,
v
o
l
.
4
4
,
n
o
.
3
7
,
p
p
.
4
6
7
8
–
4
7
3
4
,
D
e
c
.
2
0
1
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
t
mo
se
n
v
.
2
0
0
9
.
0
6
.
0
0
5
.
[
1
4
]
Y
.
H
u
i
a
n
d
M
.
F
a
n
x
i
n
g
,
“
A
p
p
l
i
c
a
t
i
o
n
o
f
I
mp
r
o
v
e
d
S
A
X
A
l
g
o
r
i
t
h
m
t
o
Q
A
R
F
l
i
g
h
t
D
a
t
a
,
”
P
h
y
s
i
c
s
Pro
c
e
d
i
a
,
v
o
l
.
2
4
,
p
p
.
1
4
0
6
–
1
4
1
3
,
2
0
1
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
h
p
r
o
.
2
0
1
2
.
0
2
.
2
0
9
.
[
1
5
]
L
.
W
a
n
g
,
C
.
W
u
,
a
n
d
R
.
S
u
n
,
“
A
n
a
n
a
l
y
si
s
o
f
f
l
i
g
h
t
Q
u
i
c
k
A
c
c
e
ss R
e
c
o
r
d
e
r
(
Q
A
R
)
d
a
t
a
a
n
d
i
t
s
a
p
p
l
i
c
a
t
i
o
n
s
i
n
p
r
e
v
e
n
t
i
n
g
l
a
n
d
i
n
g
i
n
c
i
d
e
n
t
s
,
”
Re
l
i
a
b
i
l
i
t
y
E
n
g
i
n
e
e
ri
n
g
a
n
d
S
y
s
t
e
m
S
a
f
e
t
y
,
v
o
l
.
1
2
7
,
p
p
.
8
6
–
9
6
,
Ju
l
.
2
0
1
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
r
e
ss.
2
0
1
4
.
0
3
.
0
1
3
.
[
1
6
]
W
.
H
.
P
a
n
,
Y
.
W
.
F
e
n
g
,
C
.
L
u
,
a
n
d
J.
Q
.
L
i
u
,
“
A
n
a
l
y
z
i
n
g
t
h
e
o
p
e
r
a
t
i
o
n
r
e
l
i
a
b
i
l
i
t
y
o
f
a
e
r
o
e
n
g
i
n
e
u
si
n
g
Q
u
i
c
k
A
c
c
e
ss
R
e
c
o
r
d
e
r
f
l
i
g
h
t
d
a
t
a
,
”
R
e
l
i
a
b
i
l
i
t
y
En
g
i
n
e
e
r
i
n
g
a
n
d
S
y
st
e
m
S
a
f
e
t
y
,
v
o
l
.
2
3
5
,
p
.
1
0
9
1
9
3
,
Ju
l
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
r
e
ss.2
0
2
3
.
1
0
9
1
9
3
.
[
1
7
]
M
.
S
t
r
o
h
m
e
i
e
r
,
V
.
L
e
n
d
e
r
s,
a
n
d
I
.
M
a
r
t
i
n
o
v
i
c
,
“
O
n
t
h
e
se
c
u
r
i
t
y
o
f
t
h
e
a
u
t
o
mat
i
c
d
e
p
e
n
d
e
n
t
s
u
r
v
e
i
l
l
a
n
c
e
-
b
r
o
a
d
c
a
st
p
r
o
t
o
c
o
l
,
”
I
EEE
C
o
m
m
u
n
i
c
a
t
i
o
n
s
S
u
rv
e
y
s
a
n
d
T
u
t
o
ri
a
l
s
,
v
o
l
.
1
7
,
n
o
.
2
,
p
p
.
1
0
6
6
–
1
0
8
7
,
2
0
1
5
,
d
o
i
:
1
0
.
1
1
0
9
/
C
O
M
S
T
.
2
0
1
4
.
2
3
6
5
9
5
1
.
[
1
8
]
A
.
G
r
e
b
e
n
še
k
a
n
d
T
.
M
a
g
i
st
e
r
,
“
Ef
f
e
c
t
o
f
se
a
so
n
a
l
t
r
a
f
f
i
c
v
a
r
i
a
b
i
l
i
t
y
o
n
t
h
e
p
e
r
f
o
r
man
c
e
o
f
a
i
r
n
a
v
i
g
a
t
i
o
n
se
r
v
i
c
e
p
r
o
v
i
d
e
r
s,
”
J
o
u
rn
a
l
o
f
Ai
r
T
ra
n
s
p
o
r
t
Ma
n
a
g
e
m
e
n
t
,
v
o
l
.
2
5
,
p
p
.
2
2
–
2
5
,
D
e
c
.
2
0
1
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
a
i
r
t
r
a
ma
n
.
2
0
1
2
.
0
4
.
0
0
3
.
[
1
9
]
J.
H
e
,
L
.
Q
u
,
P
.
W
a
n
g
,
a
n
d
Z
.
L
i
,
“
A
n
o
s
c
i
l
l
a
t
o
r
y
p
a
r
t
i
c
l
e
sw
a
r
m
o
p
t
i
m
i
z
a
t
i
o
n
f
e
a
t
u
r
e
se
l
e
c
t
i
o
n
a
l
g
o
r
i
t
h
m
f
o
r
h
y
b
r
i
d
d
a
t
a
b
a
se
d
o
n
mu
t
u
a
l
i
n
f
o
r
ma
t
i
o
n
e
n
t
r
o
p
y
,
”
A
p
p
l
i
e
d
S
o
f
t
C
o
m
p
u
t
i
n
g
,
v
o
l
.
1
5
2
,
p
.
1
1
1
2
6
1
,
F
e
b
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
so
c
.
2
0
2
4
.
1
1
1
2
6
1
.
[
2
0
]
B
.
K
.
B
u
r
i
a
n
,
K
.
L
.
M
o
si
e
r
,
U
.
M
.
F
i
sch
e
r
,
a
n
d
J.
A
.
K
o
c
h
a
n
,
“
N
e
w
t
e
a
ms
o
n
t
h
e
f
l
i
g
h
t
d
e
c
k
:
H
u
m
a
n
s
a
n
d
c
o
n
t
e
x
t
-
se
n
si
t
i
v
e
i
n
f
o
r
mat
i
o
n
a
u
t
o
m
a
t
i
o
n
,
”
i
n
H
u
m
a
n
Fa
c
t
o
rs
i
n
Av
i
a
t
i
o
n
a
n
d
Ae
r
o
s
p
a
c
e
,
T
h
i
rd
E
d
i
t
i
o
n
,
El
se
v
i
e
r
,
2
0
2
2
,
p
p
.
5
9
–
87
,
d
o
i
:
1
0
.
1
0
1
6
/
B
9
7
8
-
0
-
12
-
4
2
0
1
3
9
-
2
.
0
0
0
0
8
-
3.
[
2
1
]
P
.
L
a
t
h
a
m
a
n
d
Y
.
R
o
u
d
i
,
“
M
u
t
u
a
l
i
n
f
o
r
mat
i
o
n
,
”
S
c
h
o
l
a
r
p
e
d
i
a
,
v
o
l
.
4
,
n
o
.
1
,
p
.
1
6
5
8
,
2
0
0
9
,
d
o
i
:
1
0
.
4
2
4
9
/
s
c
h
o
l
a
r
p
e
d
i
a
.
1
6
5
8
.
[
2
2
]
C
.
H
u
,
J.
W
u
,
C
.
S
u
n
,
X
.
C
h
e
n
,
a
n
d
R
.
Y
a
n
,
“
M
u
t
u
a
l
i
n
f
o
r
mat
i
o
n
-
b
a
se
d
f
e
a
t
u
r
e
d
i
se
n
t
a
n
g
l
e
d
n
e
t
w
o
r
k
f
o
r
a
n
o
mal
y
d
e
t
e
c
t
i
o
n
u
n
d
e
r
v
a
r
i
a
b
l
e
w
o
r
k
i
n
g
c
o
n
d
i
t
i
o
n
s,
”
M
e
c
h
a
n
i
c
a
l
S
y
st
e
m
s
a
n
d
S
i
g
n
a
l
Pr
o
c
e
ssi
n
g
,
v
o
l
.
2
0
4
,
p
.
1
1
0
8
0
4
,
D
e
c
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
y
mss
p
.
2
0
2
3
.
1
1
0
8
0
4
.
[
2
3
]
J.
M
e
n
s
a
h
,
“
S
u
st
a
i
n
a
b
l
e
d
e
v
e
l
o
p
me
n
t
:
M
e
a
n
i
n
g
,
h
i
s
t
o
r
y
,
p
r
i
n
c
i
p
l
e
s,
p
i
l
l
a
r
s,
a
n
d
i
m
p
l
i
c
a
t
i
o
n
s fo
r
h
u
ma
n
a
c
t
i
o
n
:
L
i
t
e
r
a
t
u
r
e
r
e
v
i
e
w
,
”
C
o
g
e
n
t
S
o
c
i
a
l
S
c
i
e
n
c
e
s
,
v
o
l
.
5
,
n
o
.
1
,
Jan
.
2
0
1
9
,
d
o
i
:
1
0
.
1
0
8
0
/
2
3
3
1
1
8
8
6
.
2
0
1
9
.
1
6
5
3
5
3
1
.
[
2
4
]
S
.
Ek
i
c
i
,
“
T
h
e
r
mo
d
y
n
a
mi
c
ma
p
p
i
n
g
o
f
A
3
2
1
-
2
0
0
i
n
t
e
r
ms
o
f
p
e
r
f
o
r
man
c
e
p
a
r
a
me
t
e
r
s,
s
u
st
a
i
n
a
b
i
l
i
t
y
i
n
d
i
c
a
t
o
r
s
a
n
d
t
h
e
r
mo
-
e
c
o
l
o
g
i
c
a
l
p
e
r
f
o
r
man
c
e
a
t
v
a
r
i
o
u
s fl
i
g
h
t
p
h
a
se
s,”
En
e
r
g
y
,
v
o
l
.
2
0
2
,
p
.
1
1
7
6
9
2
,
J
u
l
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
n
e
r
g
y
.
2
0
2
0
.
1
1
7
6
9
2
.
[
2
5
]
C
.
T
o
n
g
,
X
.
Y
i
n
,
S
.
W
a
n
g
,
a
n
d
Z
.
Z
h
e
n
g
,
“
A
n
o
v
e
l
d
e
e
p
l
e
a
r
n
i
n
g
me
t
h
o
d
f
o
r
a
i
r
c
r
a
f
t
l
a
n
d
i
n
g
sp
e
e
d
p
r
e
d
i
c
t
i
o
n
b
a
se
d
o
n
c
l
o
u
d
-
b
a
se
d
se
n
so
r
d
a
t
a
,
”
Fu
t
u
re
G
e
n
e
ra
t
i
o
n
C
o
m
p
u
t
e
r
S
y
st
e
m
s
,
v
o
l
.
8
8
,
p
p
.
5
5
2
–
5
5
8
,
N
o
v
.
2
0
1
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
f
u
t
u
r
e
.
2
0
1
8
.
0
6
.
0
2
3
.
[
2
6
]
C
.
E.
L
a
n
,
K
.
W
u
,
a
n
d
J
.
Y
u
,
“
F
l
i
g
h
t
c
h
a
r
a
c
t
e
r
i
st
i
c
s a
n
a
l
y
si
s b
a
se
d
o
n
Q
A
R
d
a
t
a
o
f
a
j
e
t
t
r
a
n
s
p
o
r
t
d
u
r
i
n
g
l
a
n
d
i
n
g
a
t
a
h
i
g
h
-
a
l
t
i
t
u
d
e
a
i
r
p
o
r
t
,
”
C
h
i
n
e
s
e
J
o
u
rn
a
l
o
f
Ae
r
o
n
a
u
t
i
c
s
,
v
o
l
.
2
5
,
n
o
.
1
,
p
p
.
1
3
–
2
4
,
F
e
b
.
2
0
1
2
,
d
o
i
:
1
0
.
1
0
1
6
/
S
1
0
0
0
-
9
3
6
1
(
1
1
)
6
0
3
5
7
-
9.
[
2
7
]
G
.
W
a
l
k
e
r
,
“
El
e
c
t
r
o
n
i
c
D
a
t
a
R
e
c
o
r
d
e
r
s,”
i
n
E
n
c
y
c
l
o
p
e
d
i
a
o
f
Fo
r
e
n
s
i
c
S
c
i
e
n
c
e
s:
V
o
l
u
m
e
1
-
4
,
T
h
i
r
d
E
d
i
t
i
o
n
,
El
se
v
i
e
r
,
2
0
2
2
,
p
p
.
2
3
7
–
248
,
d
o
i
:
1
0
.
1
0
1
6
/
B
9
7
8
-
0
-
12
-
8
2
3
6
7
7
-
2
.
0
0
1
4
4
-
6.
[
2
8
]
F
.
S
c
h
w
a
i
g
e
r
a
n
d
F
.
H
o
l
z
a
p
f
e
l
,
“
F
a
st
d
e
c
o
d
i
n
g
o
f
a
r
i
n
c
7
1
7
f
l
i
g
h
t
d
a
t
a
r
e
c
o
r
d
i
n
g
s,”
i
n
AI
AA
S
c
i
t
e
c
h
2
0
2
1
Fo
r
u
m
,
R
e
st
o
n
,
V
i
r
g
i
n
i
a
:
A
me
r
i
c
a
n
I
n
st
i
t
u
t
e
o
f
A
e
r
o
n
a
u
t
i
c
s
a
n
d
A
st
r
o
n
a
u
t
i
c
s,
Ja
n
.
2
0
2
1
,
p
p
.
1
–
12
,
d
o
i
:
1
0
.
2
5
1
4
/
6
.
2
0
2
1
-
1
9
8
2
.
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
F
u
el
co
n
s
u
mp
tio
n
p
r
ed
ictio
n
o
f c
ivil a
ir
cra
ft
s
u
s
in
g
d
ee
p
le
a
r
n
in
g
:
a
co
mp
a
r
a
tive
…
(
Qu
o
c
Hu
n
g
N
g
u
ye
n
)
1009
[
2
9
]
J.
J.
R
o
w
l
a
n
d
a
n
d
M
.
L
a
w
t
o
n
,
“
A
v
e
r
sat
i
l
e
mi
c
r
o
p
r
o
c
e
sso
r
-
b
a
se
d
sy
n
c
h
r
o
n
i
z
a
t
i
o
n
d
e
c
o
d
e
r
f
o
r
r
e
p
l
a
y
f
r
o
m
f
l
i
g
h
t
d
a
t
a
r
e
c
o
r
d
e
r
s,
”
J
o
u
rn
a
l
o
f
Mi
c
ro
c
o
m
p
u
t
e
r A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
2
,
n
o
.
1
,
p
p
.
8
7
–
9
3
,
J
a
n
.
1
9
8
9
,
d
o
i
:
1
0
.
1
0
1
6
/
0
7
4
5
-
7
1
3
8
(
8
9
)
9
0
0
0
9
-
2.
[
3
0
]
M
.
S
t
e
u
r
e
r
,
R
.
J.
H
i
l
l
,
a
n
d
N
.
P
f
e
i
f
e
r
,
“
M
e
t
r
i
c
s
f
o
r
e
v
a
l
u
a
t
i
n
g
t
h
e
p
e
r
f
o
r
man
c
e
o
f
mac
h
i
n
e
l
e
a
r
n
i
n
g
b
a
se
d
a
u
t
o
mat
e
d
v
a
l
u
a
t
i
o
n
mo
d
e
l
s,”
J
o
u
r
n
a
l
o
f
Pr
o
p
e
rt
y
R
e
se
a
rc
h
,
v
o
l
.
3
8
,
n
o
.
2
,
p
p
.
9
9
–
1
2
9
,
A
p
r
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
8
0
/
0
9
5
9
9
9
1
6
.
2
0
2
0
.
1
8
5
8
9
3
7
.
[
3
1
]
C
.
J.
W
i
l
l
mo
t
t
a
n
d
K
.
M
a
t
s
u
u
r
a
,
“
A
d
v
a
n
t
a
g
e
s
o
f
t
h
e
me
a
n
a
b
so
l
u
t
e
e
r
r
o
r
(
M
A
E)
o
v
e
r
t
h
e
r
o
o
t
me
a
n
s
q
u
a
r
e
e
r
r
o
r
(
R
M
S
E)
i
n
a
sse
ssi
n
g
a
v
e
r
a
g
e
mo
d
e
l
p
e
r
f
o
r
man
c
e
,
”
C
l
i
m
a
t
e
Re
se
a
r
c
h
,
v
o
l
.
3
0
,
n
o
.
1
,
p
p
.
7
9
–
8
2
,
2
0
0
5
,
d
o
i
:
1
0
.
3
3
5
4
/
c
r
0
3
0
0
7
9
.
[
3
2
]
T
.
H
a
st
i
e
,
J.
F
r
i
e
d
m
a
n
,
a
n
d
R
.
T
i
b
s
h
i
r
a
n
i
,
T
h
e
E
l
e
m
e
n
t
s
o
f
S
t
a
t
i
st
i
c
a
l
L
e
a
r
n
i
n
g
.
i
n
S
p
r
i
n
g
e
r
S
e
r
i
e
s
i
n
S
t
a
t
i
st
i
c
s
.
N
e
w
Y
o
r
k
,
N
Y
:
S
p
r
i
n
g
e
r
N
e
w
Y
o
r
k
,
2
0
0
1
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
0
-
3
8
7
-
2
1
6
0
6
-
5.
[
3
3
]
T
.
C
h
a
i
a
n
d
R
.
R
.
D
r
a
x
l
e
r
,
“
R
o
o
t
M
e
a
n
S
q
u
a
r
e
Er
r
o
r
(
R
M
S
E)
o
r
M
e
a
n
A
b
so
l
u
t
e
Er
r
o
r
(
M
A
E)
,
”
G
e
o
sc
i
e
n
t
i
f
i
c
M
o
d
e
l
D
e
v
e
l
o
p
m
e
n
t
,
v
o
l
.
7
,
p
p
.
1
5
2
5
–
1
5
3
4
,
2
0
1
4
.
[
3
4
]
C
.
L
.
C
h
e
n
g
,
S
h
a
l
a
b
h
,
a
n
d
G
.
G
a
r
g
,
“
C
o
e
f
f
i
c
i
e
n
t
o
f
d
e
t
e
r
mi
n
a
t
i
o
n
f
o
r
mu
l
t
i
p
l
e
me
a
su
r
e
me
n
t
e
r
r
o
r
mo
d
e
l
s,”
J
o
u
r
n
a
l
o
f
Mu
l
t
i
v
a
ri
a
t
e
A
n
a
l
y
si
s
,
v
o
l
.
1
2
6
,
p
p
.
1
3
7
–
1
5
2
,
A
p
r
.
2
0
1
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
m
v
a
.
2
0
1
4
.
0
1
.
0
0
6
.
[
3
5
]
C
.
F
u
e
t
a
l
.
,
“
P
r
e
d
i
c
t
i
o
n
o
f
e
mi
ssi
o
n
c
h
a
r
a
c
t
e
r
i
st
i
c
s
o
f
d
i
e
se
l
/
n
-
h
e
x
a
n
o
l
/
g
r
a
p
h
e
n
e
o
x
i
d
e
b
l
e
n
d
e
d
f
u
e
l
s
b
a
se
d
o
n
f
a
s
t
o
u
t
l
i
e
r
d
e
t
e
c
t
i
o
n
-
sp
a
r
r
o
w
s
e
a
r
c
h
a
l
g
o
r
i
t
h
m
-
b
i
d
i
r
e
c
t
i
o
n
a
l
r
e
c
u
r
r
e
n
t
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
Pr
o
c
e
ss
S
a
f
e
t
y
a
n
d
En
v
i
r
o
n
m
e
n
t
a
l
Pro
t
e
c
t
i
o
n
,
v
o
l
.
1
8
7
,
p
p
.
1
0
7
6
–
1
0
9
6
,
J
u
l
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
se
p
.
2
0
2
4
.
0
5
.
0
2
7
.
[
3
6
]
J.
Z
h
a
n
g
a
n
d
S
.
L
i
,
“
A
i
r
q
u
a
l
i
t
y
i
n
d
e
x
f
o
r
e
c
a
st
i
n
B
e
i
j
i
n
g
b
a
se
d
o
n
C
N
N
-
L
S
T
M
mu
l
t
i
-
mo
d
e
l
,
”
C
h
e
m
o
s
p
h
e
r
e
,
v
o
l
.
3
0
8
,
p
.
1
3
6
1
8
0
,
D
e
c
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
h
e
mo
sp
h
e
r
e
.
2
0
2
2
.
1
3
6
1
8
0
.
[
3
7
]
G
.
E.
H
i
n
t
o
n
,
S
.
O
s
i
n
d
e
r
o
,
a
n
d
Y
.
W
.
T
e
h
,
“
A
f
a
st
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
m
f
o
r
d
e
e
p
b
e
l
i
e
f
n
e
t
s,”
N
e
u
r
a
l
C
o
m
p
u
t
a
t
i
o
n
,
v
o
l
.
1
8
,
n
o
.
7
,
p
p
.
1
5
2
7
–
1
5
5
4
,
Ju
l
.
2
0
0
6
,
d
o
i
:
1
0
.
1
1
6
2
/
n
e
c
o
.
2
0
0
6
.
1
8
.
7
.
1
5
2
7
.
[
3
8
]
T
.
B
a
k
l
a
c
i
o
g
l
u
,
“
M
o
d
e
l
i
n
g
t
h
e
f
u
e
l
f
l
o
w
-
r
a
t
e
o
f
t
r
a
n
s
p
o
r
t
a
i
r
c
r
a
f
t
d
u
r
i
n
g
f
l
i
g
h
t
p
h
a
se
s
u
s
i
n
g
g
e
n
e
t
i
c
a
l
g
o
r
i
t
h
m
-
o
p
t
i
mi
z
e
d
n
e
u
r
a
l
n
e
t
w
o
r
k
s,”
Ae
r
o
s
p
a
c
e
S
c
i
e
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
4
9
,
p
p
.
5
2
–
6
2
,
F
e
b
.
2
0
1
6
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
st
.
2
0
1
5
.
1
1
.
0
3
1
.
[
3
9
]
M
.
Z
h
a
n
g
,
Q
.
H
u
a
n
g
,
S
.
L
i
u
,
a
n
d
Y
.
Z
h
a
n
g
,
“
F
u
e
l
c
o
n
su
m
p
t
i
o
n
mo
d
e
l
o
f
t
h
e
c
l
i
m
b
i
n
g
p
h
a
se
o
f
d
e
p
a
r
t
u
r
e
a
i
r
c
r
a
f
t
b
a
se
d
o
n
f
l
i
g
h
t
d
a
t
a
a
n
a
l
y
si
s,”
S
u
st
a
i
n
a
b
i
l
i
t
y
(
S
w
i
t
z
e
r
l
a
n
d
)
,
v
o
l
.
1
1
,
n
o
.
1
6
,
p
.
4
3
6
2
,
A
u
g
.
2
0
1
9
,
d
o
i
:
1
0
.
3
3
9
0
/
s
u
1
1
1
6
4
3
6
2
.
[
4
0
]
S
.
A
t
i
p
a
n
a
n
d
P
.
C
h
o
m
d
e
j
,
“
F
u
e
l
C
o
n
su
mp
t
i
o
n
A
n
a
l
y
si
s
o
f
G
r
a
d
u
a
l
C
l
i
m
b
P
r
o
c
e
d
u
r
e
w
i
t
h
V
a
r
i
e
d
C
l
i
m
b
A
n
g
l
e
a
n
d
A
i
r
sp
e
e
d
,
”
S
u
s
t
a
i
n
a
b
l
e
A
v
i
a
t
i
o
n
.
S
p
r
i
n
g
e
r In
t
e
r
n
a
t
i
o
n
a
l
Pu
b
l
i
s
h
i
n
g
,
2
0
2
3
,
p
p
.
3
1
5
–
3
2
0
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
0
3
1
-
3
7
9
4
3
-
7
_
4
2
.
[
4
1
]
L
.
Z
h
a
n
g
,
A
.
B
i
a
n
,
C
.
Ji
a
n
g
,
a
n
d
L
.
W
u
,
“
A
C
o
mp
r
e
h
e
n
si
v
e
F
r
a
mew
o
r
k
f
o
r
E
st
i
ma
t
i
n
g
A
i
r
c
r
a
f
t
F
u
e
l
C
o
n
s
u
mp
t
i
o
n
B
a
se
d
o
n
F
l
i
g
h
t
T
r
a
j
e
c
t
o
r
i
e
s,”
a
r
Xi
v
,
S
e
p
.
2
0
2
4
,
d
o
i
:
1
0
.
4
8
5
5
0
/
a
r
X
i
v
.
2
4
0
9
.
0
5
4
2
9
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Q
u
o
c
H
u
n
g
Ng
u
y
e
n
is
a
se
n
io
r
lec
tu
re
r
a
n
d
re
se
a
rc
h
e
r
a
t
t
h
e
S
c
h
o
o
l
o
f
Bu
sin
e
s
s
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
l
o
g
y
,
UEH
C
o
ll
e
g
e
o
f
T
e
c
h
n
o
l
o
g
y
a
n
d
De
sig
n
,
Un
iv
e
rsit
y
o
f
Eco
n
o
m
ics
Ho
C
h
i
M
in
h
Cit
y
(UEH),
V
ietn
a
m
.
He
re
c
e
iv
e
d
h
is
P
h
.
D
.
i
n
Co
m
p
u
ter
S
c
ien
c
e
f
ro
m
Ha
n
o
i
Un
iv
e
rsit
y
o
f
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
lo
g
y
(HU
S
T
)
in
2
0
1
6
.
His
re
se
a
rc
h
in
tere
sts
i
n
c
lu
d
e
b
ig
d
a
ta
a
n
a
ly
ti
c
s
m
e
th
o
d
s
u
si
n
g
a
rti
f
icia
l
in
telli
g
e
n
c
e
a
n
d
b
l
o
c
k
c
h
a
in
e
n
c
ry
p
ti
o
n
tec
h
n
o
l
o
g
y
,
w
it
h
a
p
p
li
c
a
ti
o
n
s
in
t
h
e
f
ield
s
o
f
e
c
o
n
o
m
ics
,
b
u
sin
e
ss
,
sc
ien
c
e
,
tec
h
n
o
l
o
g
y
,
m
e
d
icin
e
,
a
g
ricu
lt
u
re
,
a
n
d
m
o
re
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
h
u
n
g
n
g
q
@
u
e
h
.
e
d
u
.
v
n
.
H
o
a
n
g
La
n
Ng
u
y
e
n
i
s
a
M
a
s
t
e
r
’
s
d
e
g
r
e
e
h
o
l
d
e
r
i
n
I
n
f
o
r
m
a
t
i
o
n
D
e
s
i
g
n
a
n
d
T
e
c
h
n
o
l
o
g
y
f
r
o
m
t
h
e
U
n
i
v
e
r
s
i
t
y
o
f
E
c
o
n
o
m
i
c
s
H
o
C
h
i
M
i
n
h
C
i
t
y
.
C
u
r
r
e
n
t
l
y
,
s
h
e
h
o
l
d
s
t
h
e
p
o
s
i
t
i
o
n
o
f
D
a
t
a
E
n
g
i
n
e
e
r
a
t
F
P
T
S
o
f
t
w
a
r
e
i
n
V
i
e
t
n
a
m
.
S
h
e
c
a
n
b
e
c
o
n
t
a
c
t
e
d
a
t
e
m
a
i
l
:
l
a
n
n
g
u
y
e
n
.
2
1
2
1
1
8
0
0
5
@
s
t
.
u
e
h
.
e
d
u
.
v
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.