I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
pu
t
er
E
ng
ineering
(
I
J
E
CE
)
Vo
l.
15
,
No
.
3
,
J
u
n
e
20
25
,
p
p
.
3362
~
3
3
7
2
I
SS
N:
2088
-
8
7
0
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijece.
v
15
i
3
.
pp
3
3
6
2
-
3
3
7
2
3362
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
Enha
ncing
t
a
bula
r data
ana
ly
sis
f
o
r clas
sifica
tion o
f
a
irline
pa
ss
eng
er sa
tisfac
tion usin
g
Ta
bNe
t
deep
neura
l ne
tw
o
rk
Ra
chid K
a
idi
1
,
H
icha
m
O
m
a
ra
2
,
M
o
ha
m
ed
L
a
za
a
r
3
,
M
o
h
a
m
m
ed
Al
Achha
b
4
1
F
a
c
u
l
t
y
o
f
S
c
i
e
n
c
e
s,
A
b
d
e
l
ma
l
e
k
E
ss
a
a
d
i
U
n
i
v
e
r
s
i
t
y
,
Te
t
o
u
a
n
,
M
o
r
o
c
c
o
2
P
o
l
y
d
i
sc
i
p
l
i
n
a
r
y
F
a
c
u
l
t
y
,
S
i
d
i
M
o
h
a
mm
e
d
B
e
n
A
b
d
e
l
l
a
h
U
n
i
v
e
r
si
t
y
,
Ta
z
a
,
M
o
r
o
c
c
o
3
N
a
t
i
o
n
a
l
H
i
g
h
e
r
S
c
h
o
o
l
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
S
y
s
t
e
ms A
n
a
l
y
si
s,
M
o
h
a
mm
e
d
V
U
n
i
v
e
r
si
t
y
i
n
R
a
b
a
t
,
R
a
b
a
t
,
M
o
r
o
c
c
o
4
N
a
t
i
o
n
a
l
S
c
h
o
o
l
o
f
A
p
p
l
i
e
d
S
c
i
e
n
c
e
s
,
A
b
d
e
l
mal
e
k
Ess
a
a
d
i
U
n
i
v
e
r
si
t
y
,
Te
t
o
u
a
n
,
M
o
r
o
c
c
o
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Sep
1
,
2
0
2
4
R
ev
is
ed
J
an
1
3
,
2
0
2
5
Acc
ep
ted
Ma
r
3
,
2
0
2
5
In
a
n
e
ra
o
f
a
ir
trav
e
l,
u
n
d
e
rsta
n
d
i
n
g
a
n
d
e
n
h
a
n
c
in
g
p
a
ss
e
n
g
e
r
sa
ti
sf
a
c
ti
o
n
a
re
p
iv
o
tal
to
th
e
su
c
c
e
ss
o
f
a
irl
i
n
e
s
a
n
d
th
e
o
v
e
ra
ll
p
a
ss
e
n
g
e
r
e
x
p
e
rien
c
e
.
An
a
ly
z
in
g
a
irl
in
e
p
a
ss
e
n
g
e
r
sa
ti
sfa
c
ti
o
n
u
si
n
g
tab
u
lar
d
a
ta
c
a
n
p
o
se
v
a
rio
u
s
c
h
a
ll
e
n
g
e
s,
b
o
t
h
wh
e
n
e
m
p
l
o
y
i
n
g
c
las
sic
a
l
sta
ti
stica
l
m
e
th
o
d
s
a
n
d
wh
e
n
lev
e
ra
g
in
g
m
a
c
h
in
e
lea
rn
in
g
a
n
d
d
e
e
p
lea
rn
in
g
tec
h
n
iq
u
e
s.
On
th
e
o
n
e
h
a
n
d
,
sta
ti
stica
l
a
p
p
r
o
a
c
h
e
s
p
o
se
v
a
ri
o
u
s
c
h
a
ll
e
n
g
e
s
in
c
l
u
d
i
n
g
li
m
it
e
d
fe
a
tu
re
e
n
g
in
e
e
rin
g
tec
h
n
iq
u
e
s,
th
e
a
ss
u
m
p
ti
o
n
o
f
l
in
e
a
rit
y
o
f
t
h
e
d
a
ta
se
ts
a
n
d
li
m
it
e
d
p
re
d
ictiv
e
p
o
we
r.
T
h
e
n
a
g
a
i
n
,
th
e
u
se
o
f
m
a
c
h
in
e
lea
rn
in
g
a
n
d
d
e
e
p
lea
rn
i
n
g
tec
h
n
iq
u
e
s
m
a
y
fa
c
e
o
th
e
r
c
h
a
ll
e
n
g
e
s
su
c
h
a
s
th
e
p
ro
b
lem
o
f
o
v
e
rfit
ti
n
g
,
d
iffi
c
u
lt
y
i
n
i
n
terp
re
ti
n
g
d
a
ta,
in
ten
siv
e
re
so
u
rc
e
re
q
u
irem
e
n
ts,
a
n
d
t
h
e
g
e
n
e
ra
li
z
a
ti
o
n
p
ro
b
lem
in
d
e
p
lo
y
in
g
m
a
c
h
in
e
lea
rn
i
n
g
-
b
a
se
d
m
e
th
o
d
s.
T
h
is
p
a
p
e
r
p
re
se
n
ts
a
n
o
v
e
l
d
e
e
p
lea
r
n
in
g
a
p
p
r
o
a
c
h
u
t
il
izin
g
Tab
Ne
t
t
o
c
las
sify
a
irl
in
e
p
a
ss
e
n
g
e
r
sa
ti
sfa
c
ti
o
n
.
Lev
e
ra
g
in
g
a
c
o
m
p
re
h
e
n
siv
e
d
a
tas
e
t
c
o
m
p
risin
g
v
a
rio
u
s
p
a
ss
e
n
g
e
r
-
re
late
d
a
tt
rib
u
tes
,
o
u
r
Tab
Ne
t
-
b
a
s
e
d
m
o
d
e
l
d
e
m
o
n
stra
tes
e
x
c
e
p
ti
o
n
a
l
p
e
rfo
rm
a
n
c
e
in
d
isti
n
g
u
ish
i
n
g
b
e
twe
e
n
sa
ti
sfie
d
a
n
d
d
issa
ti
sfie
d
p
a
ss
e
n
g
e
rs.
Ou
r
m
o
d
e
l
’
s
ro
b
u
stn
e
ss
in
h
a
n
d
li
n
g
tab
u
lar
d
a
ta,
u
n
d
e
rsc
o
re
s it
s p
o
we
r
a
s a
v
a
lu
a
b
le t
o
o
l
fo
r
t
h
e
a
v
iatio
n
in
d
u
str
y
.
C
o
m
p
a
rin
g
o
u
t
re
su
lt
s
t
o
re
c
e
n
t
p
a
p
e
rs
s
h
o
w
th
a
t
o
u
t
m
o
d
e
l
o
u
tp
e
rf
o
rm
s
th
e
se
stu
d
ies
i
n
term
s
o
f
a
c
c
u
ra
c
y
,
p
re
c
isio
n
,
re
c
a
l
l
a
n
d
a
re
a
u
n
d
e
r
th
e
c
u
r
v
e
.
T
h
e
re
su
lt
s
sh
o
w
th
a
t
o
u
r
Tab
Ne
t
Ne
two
r
k
m
o
d
e
l
o
u
t
p
e
rfo
rm
s
a
ll
imp
lem
e
n
ted
m
a
c
h
in
e
lea
rn
in
g
m
o
d
e
ls
b
y
re
a
c
h
in
g
re
sp
e
c
ti
v
e
ly
t
h
e
f
o
ll
o
wi
n
g
re
su
lt
s:
9
6
.
4
7
%
,
9
6
.
4
1
%
a
n
d
9
6
.
2
4
%
fo
r
a
c
c
u
ra
c
y
,
F
1
-
sc
o
re
a
n
d
G
-
m
e
a
n
sc
o
re
.
K
ey
w
o
r
d
s
:
Av
iatio
n
C
u
s
to
m
er
ex
p
er
ien
ce
C
u
s
to
m
er
f
ee
d
b
ac
k
Dee
p
lear
n
in
g
Ma
ch
in
e
lear
n
in
g
Pas
s
en
g
er
s
atis
f
ac
tio
n
Ser
v
ice
q
u
ality
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
R
ac
h
id
Kaid
i
Facu
lty
o
f
Scien
ce
s
,
Ab
d
elm
al
ek
E
s
s
aa
d
i U
n
iv
er
s
ity
T
eto
u
an
,
M
o
r
o
cc
o
E
m
ail:
k
aid
ir
ac
h
id
1
9
8
2
@
g
m
a
il.c
o
m
1.
I
NT
RO
D
UCT
I
O
N
Av
iatio
n
is
o
n
e
o
f
th
e
m
o
s
t
wid
ely
em
p
lo
y
ed
a
n
d
s
af
est
m
o
d
es
o
f
tr
an
s
p
o
r
tatio
n
.
T
h
e
an
ticip
ated
s
ce
n
ar
io
was
a
th
r
ee
f
o
ld
in
cr
e
ase
in
g
lo
b
al
air
tr
a
n
s
p
o
r
t
d
e
m
an
d
f
r
o
m
2
0
2
0
t
o
2
0
5
0
[
1
]
,
[
2
]
.
T
h
e
I
n
ter
n
atio
n
al
Air
T
r
an
s
p
o
r
t
Ass
o
ciatio
n
(
I
AT
A)
p
r
ed
icts
th
at
th
er
e
will
b
e
a
3
.
7
%
y
ea
r
ly
i
n
cr
ea
s
e
in
air
tr
av
el
d
em
an
d
,
r
esu
ltin
g
in
an
esti
m
ated
7
.
2
b
illi
o
n
air
p
ass
en
g
er
s
b
y
th
e
y
ea
r
2
0
3
5
[
3
]
,
[
4
]
.
T
h
at
is
w
h
y
m
illi
o
n
s
o
f
p
ass
en
g
er
s
ar
o
u
n
d
th
e
g
lo
b
e
p
r
e
f
er
is
b
ec
au
s
e
o
f
s
af
ety
an
d
p
r
o
f
ess
io
n
al
s
er
v
ices.
I
n
a
n
er
a
d
ef
in
e
d
b
y
r
ap
id
g
lo
b
aliza
tio
n
an
d
h
eig
h
ten
ed
co
n
n
ec
tiv
ity
,
a
v
iatio
n
tr
an
s
p
o
r
t
s
tan
d
s
as
a
co
r
n
er
s
to
n
e
o
f
m
o
d
er
n
m
o
b
ilit
y
,
lin
k
in
g
p
e
o
p
l
e
an
d
p
lace
s
with
u
n
p
r
ec
ed
en
ted
s
p
ee
d
an
d
ac
ce
s
s
ib
ilit
y
.
T
h
at
is
wh
y
th
e
a
v
iatio
n
in
d
u
s
tr
y
h
as
co
n
s
is
ten
tly
s
tr
iv
ed
to
en
s
u
r
e
n
o
t
o
n
ly
th
e
s
af
et
y
an
d
ef
f
icien
c
y
o
f
air
tr
av
e
l
b
u
t
also
th
e
s
atis
f
ac
tio
n
an
d
well
-
b
ein
g
o
f
its
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
E
n
h
a
n
cin
g
ta
b
u
la
r
d
a
ta
a
n
a
ly
s
is
fo
r
cla
s
s
ifica
tio
n
o
f a
ir
lin
e
p
a
s
s
en
g
er sa
tis
fa
ctio
n
…
(
R
a
c
h
id
K
a
id
i
)
3363
p
ass
en
g
er
s
.
As
th
e
d
em
a
n
d
f
o
r
air
tr
av
el
c
o
n
tin
u
es
to
s
u
r
g
e,
u
n
d
e
r
s
tan
d
in
g
an
d
m
e
asu
r
in
g
p
ass
en
g
er
s
atis
f
ac
tio
n
h
as b
ec
o
m
e
an
im
p
er
ativ
e
g
o
al
f
o
r
ai
r
lin
es a
n
d
t
h
e
av
iatio
n
in
d
u
s
tr
y
as a
wh
o
le.
T
r
ad
itio
n
ally
,
th
e
m
ea
s
u
r
em
e
n
t
o
f
p
ass
en
g
er
s
atis
f
ac
tio
n
in
av
iatio
n
h
as
r
elied
o
n
co
n
v
en
tio
n
al
s
u
r
v
ey
s
an
d
f
ee
d
b
ac
k
m
e
ch
an
is
m
s
[
5
]
–
[
9
]
.
W
h
ile
th
ese
m
et
h
o
d
s
h
av
e
p
r
o
v
id
ed
v
alu
a
b
le
i
n
s
ig
h
ts
,
th
ey
o
f
te
n
s
u
f
f
er
f
r
o
m
lim
itatio
n
s
s
u
ch
as
s
u
b
jectiv
ity
,
s
m
all
s
am
p
le
s
iz
es,
an
d
d
elay
ed
r
esp
o
n
s
es.
Mo
r
eo
v
er
,
th
e
a
v
iatio
n
lan
d
s
ca
p
e
is
d
y
n
am
ic,
with
c
o
u
n
tles
s
f
ac
to
r
s
af
f
ec
tin
g
p
ass
en
g
er
s
atis
f
ac
tio
n
,
in
clu
d
i
n
g
t
ick
et
p
r
icin
g
,
f
lig
h
t
p
u
n
ctu
ality
,
in
-
f
lig
h
t a
m
en
itie
s
,
an
d
cu
s
to
m
e
r
s
er
v
ice.
T
o
s
tay
co
m
p
etitiv
e
an
d
r
esp
o
n
s
iv
e
to
p
ass
en
g
er
n
ee
d
s
,
th
e
av
iatio
n
in
d
u
s
tr
y
r
eq
u
ir
es
m
o
r
e
s
o
p
h
is
ticated
an
d
r
ea
l
-
tim
e
ap
p
r
o
ac
h
es
to
g
au
g
e
p
as
s
en
g
er
s
atis
f
ac
tio
n
co
m
p
r
eh
e
n
s
iv
ely
s
u
ch
as d
ata
m
in
in
g
f
o
r
in
s
tan
ce
[
1
0
]
.
I
n
th
e
co
n
tex
t
o
f
th
e
av
iatio
n
in
d
u
s
tr
y
in
th
e
USA,
Hay
ad
i
et
a
l.
[
1
1
]
co
n
d
u
cted
a
n
a
n
aly
s
is
o
f
co
m
p
etitio
n
a
n
d
cu
s
to
m
er
s
atis
f
ac
tio
n
am
o
n
g
air
lin
es.
T
h
ey
em
p
lo
y
ed
v
ar
i
o
u
s
class
ical
class
if
icatio
n
m
o
d
els,
in
clu
d
in
g
K
-
n
ea
r
est
n
eig
h
b
o
r
s
(
KNN)
,
lo
g
is
tic
r
eg
r
ess
io
n
(
L
R
)
,
G
au
s
s
ian
n
aïv
e
B
ay
es
(
NB
)
,
d
ec
is
io
n
tr
ee
s
(
DT
)
,
an
d
r
a
n
d
o
m
f
o
r
est
(
R
F)
.
T
h
e
f
ir
s
t
s
tep
in
th
eir
an
aly
s
is
was
to
clea
n
th
e
d
ata,
wh
ich
co
n
s
is
ted
o
f
1
3
0
,
0
0
0
s
am
p
les
an
d
2
2
f
ea
tu
r
es.
Ou
t
o
f
th
ese
2
2
f
ea
tu
r
es,
1
4
wer
e
o
b
tain
ed
th
r
o
u
g
h
a
s
u
r
v
e
y
.
Af
ter
r
em
o
v
in
g
s
am
p
les
th
at
co
n
tain
in
g
eith
er
0
v
alu
e
s
o
r
NaN
,
th
ey
wer
e
lef
t
with
a
d
ataset
co
n
tain
in
g
7
0
,
0
0
0
s
am
p
les.
Am
o
n
g
th
e
m
o
d
els
test
ed
,
R
an
d
o
m
Fo
r
est
y
ield
ed
th
e
b
est
r
esu
lts
with
an
ar
ea
u
n
d
e
r
th
e
cu
r
v
e
(
AUC
)
o
f
0
.
9
9
,
p
r
ec
is
io
n
o
f
0
.
9
7
,
a
n
d
r
ec
all
o
f
0
.
9
4
.
T
h
e
d
ef
au
lt
th
r
esh
o
ld
v
al
u
e
f
o
r
r
an
d
o
m
f
o
r
est
was
s
et
at
0
.
5
.
H
o
wev
er
,
wh
e
n
th
ey
in
cr
ea
s
ed
th
e
th
r
esh
o
ld
to
0
.
7
,
th
e
p
r
ec
is
io
n
im
p
r
o
v
e
d
f
r
o
m
0
.
9
7
to
0
.
9
9
.
Pas
s
en
g
er
s
atis
f
ac
tio
n
p
lay
s
a
cr
u
cial
r
o
le
in
air
lin
e
s
elec
tio
n
.
T
o
ass
ess
p
ass
en
g
er
s
atis
f
ac
tio
n
lev
els,
Nu
r
d
in
a
an
d
Pu
s
p
ita
[
1
2
]
em
p
lo
y
ed
two
m
ac
h
in
e
lear
n
in
g
m
o
d
els
f
o
r
class
if
icatio
n
.
T
h
e
y
u
tili
ze
d
a
Kag
g
le
d
ataset
co
m
p
r
is
in
g
2
6
,
0
0
0
s
a
m
p
les
with
9
f
ea
tu
r
es
an
d
o
n
e
lab
el.
T
h
e
f
ir
s
t
m
o
d
el
u
s
ed
wa
s
n
aïv
e
B
ay
es,
wh
ich
lev
er
ag
es p
r
o
b
ab
ilit
y
an
d
s
tatis
tical
ca
lcu
latio
n
s
to
p
r
ed
ict
th
e
class
o
f
s
am
p
les.
Fo
r
th
e
s
ec
o
n
d
m
o
d
el
th
e
y
u
s
ed
KNN,
wh
ich
d
etec
ts
th
e
in
p
u
t
class
b
y
ca
lcu
latin
g
E
u
clid
ea
n
d
is
tan
ce
s
.
KNN
is
s
im
p
le
t
o
im
p
lem
en
t,
ea
s
y
to
u
n
d
e
r
s
tan
d
an
d
ca
n
ca
p
t
u
r
e
c
o
m
p
lex
an
d
n
o
n
lin
ea
r
r
elatio
n
s
h
ip
s
in
d
ata,
m
ak
in
g
i
t
ef
f
ec
tiv
e
f
o
r
class
if
icatio
n
ta
s
k
s
.
T
h
e
test
r
esu
lts
r
ev
ea
led
a
p
r
ec
is
io
n
v
alu
e
o
f
8
2
.
2
5
%
f
o
r
n
aïv
e
B
ay
es
an
d
6
7
.
3
5
%
f
o
r
KNN,
wh
ich
is
r
ela
tiv
ely
lo
w
an
d
in
d
icate
s
th
e
n
ee
d
to
f
in
e
-
tu
n
e
th
e
m
o
d
els f
o
r
b
etter
r
esu
lts
.
Pre
d
ictin
g
air
cr
af
t
p
ass
en
g
er
s
atis
f
ac
tio
n
an
d
id
e
n
tify
in
g
th
e
p
r
im
ar
y
in
f
lu
e
n
cin
g
f
ac
to
r
s
p
lay
a
v
ital
r
o
le
in
h
elp
in
g
air
lin
es
en
h
a
n
ce
th
eir
s
er
v
ices,
g
ain
a
co
m
p
etitiv
e
ed
g
e,
an
d
tack
le
ch
allen
g
in
g
s
itu
atio
n
s
ef
f
ec
tiv
ely
.
T
o
ad
d
r
ess
th
is
,
J
ia
n
g
et
a
l
.
[
1
3
]
p
r
o
p
o
s
ed
an
in
n
o
v
ativ
e
m
o
d
el
ca
lled
R
F
-
R
FE
-
L
R
,
wh
ich
co
m
b
in
es
f
ea
tu
r
e
s
elec
tio
n
tech
n
iq
u
es
to
s
tr
ea
m
lin
e
th
e
d
ataset.
T
h
e
d
ataset
co
n
s
is
ted
o
f
2
3
f
ea
tu
r
es,
ca
teg
o
r
ized
in
to
b
asic
in
f
o
r
m
atio
n
,
f
lig
h
t
d
etai
ls
,
an
d
p
ass
en
g
er
s
atis
f
ac
tio
n
attr
ib
u
tes.
T
o
d
eter
m
in
e
th
e
o
p
tim
al
n
u
m
b
e
r
o
f
f
ea
tu
r
es
f
o
r
a
n
aly
s
is
,
th
ey
co
n
d
u
cted
cr
o
s
s
-
v
alid
atio
n
ex
p
e
r
im
en
ts
,
f
in
d
in
g
t
h
at
u
tili
zin
g
1
7
f
ea
tu
r
es
r
esu
lted
in
th
e
b
est
p
er
f
o
r
m
an
ce
.
T
h
e
s
tu
d
y
co
m
p
ar
ed
v
ar
io
u
s
class
if
ic
atio
n
m
o
d
els,
in
cl
u
d
in
g
KNN,
lo
g
is
tic
r
eg
r
ess
io
n
,
r
an
d
o
m
f
o
r
est,
Gau
s
s
ian
n
aïv
e
B
ay
es,
an
d
B
P
n
eu
r
al
n
etwo
r
k
s
,
b
ef
o
r
e
an
d
a
f
ter
f
ea
tu
r
e
s
elec
tio
n
.
T
h
e
r
esu
lts
in
d
icate
d
th
at
th
e
R
F
m
o
d
el,
with
its
1
7
s
elec
ted
f
ea
tu
r
es,
ac
h
iev
ed
th
e
b
est
r
esu
lt
in
ter
m
s
o
f
ac
cu
r
ac
y
o
f
0
.
9
6
3
,
p
r
ec
is
io
n
o
f
0
.
9
7
3
,
r
ec
all
o
f
0
.
9
4
2
,
F1
v
alu
e
o
f
0
.
9
5
7
,
an
d
an
AUC
v
alu
e
o
f
0
.
9
6
1
.
T
h
is
d
em
o
n
s
tr
ated
th
e
m
o
d
el
’
s
r
o
b
u
s
tn
ess
in
p
r
ed
icti
n
g
p
ass
en
g
er
s
atis
f
ac
tio
n
an
d
r
ev
ea
led
its
p
o
te
n
tial
f
o
r
g
u
i
d
in
g
air
lin
es
in
m
ak
in
g
d
ata
-
d
r
iv
e
n
d
ec
is
io
n
s
to
en
h
an
ce
cu
s
to
m
er
ex
p
er
ien
ce
s
an
d
o
v
er
all
s
er
v
ice
q
u
ality
.
Ho
m
aid
an
d
M
o
u
lits
as
[
1
4
]
co
n
d
u
cted
a
c
o
m
p
r
e
h
en
s
iv
e
in
v
esti
g
atio
n
em
p
lo
y
in
g
v
a
r
io
u
s
ML
alg
o
r
ith
m
s
,
in
clu
d
in
g
R
F,
L
R
,
s
u
p
p
o
r
t
v
ec
t
o
r
m
ac
h
in
e
(
SVM)
,
XGBo
o
s
t,
an
d
n
aïv
e
B
ay
es
(
NB
)
.
T
h
eir
f
in
d
in
g
s
d
em
o
n
s
tr
ated
th
at
XGBo
o
s
t
ex
h
ib
ited
s
u
p
er
i
o
r
p
e
r
f
o
r
m
an
ce
co
m
p
ar
e
d
to
o
th
er
ML
m
o
d
els,
ac
h
iev
in
g
im
p
r
ess
iv
e
r
esu
lts
in
ter
m
s
o
f
ac
cu
r
ac
y
(
8
8
%),
p
r
ec
is
io
n
(
8
5
%),
r
ec
all
(
8
3
%),
an
d
F1
-
Sco
r
e
(
8
4
%).
Ku
m
a
r
et
a
l.
[
1
5
]
p
r
o
p
o
s
ed
a
n
o
v
el
m
eth
o
d
f
o
r
ass
ess
in
g
air
lin
e
p
ass
en
g
er
s
atis
f
ac
tio
n
.
T
h
eir
ap
p
r
o
ac
h
in
v
o
l
v
ed
co
llectin
g
twee
ts
f
r
o
m
T
witter
an
d
s
u
b
s
eq
u
e
n
tly
e
x
tr
ac
tin
g
r
elev
an
t
f
ea
t
u
r
es.
T
h
e
y
em
p
lo
y
ed
th
r
ee
d
i
f
f
er
en
t
m
ac
h
in
e
lear
n
in
g
m
o
d
els,
n
a
m
ely
ar
tific
ial
n
eu
r
al
n
et
wo
r
k
s
(
ANN)
,
SVM,
an
d
co
n
v
o
lu
ti
o
n
al
n
eu
r
al
n
etwo
r
k
s
(
C
NN)
.
T
h
e
r
esu
lts
in
d
icate
d
th
at
C
NN
o
u
tp
er
f
o
r
m
ed
t
h
e
o
th
er
m
o
d
els,
wh
ich
is
co
n
s
is
ten
t
with
th
e
ex
p
ec
tatio
n
th
at
co
n
v
o
lu
tio
n
al
n
etwo
r
k
s
e
x
ce
l a
t a
n
aly
zin
g
an
d
e
x
tr
ac
tin
g
p
er
tin
en
t i
n
f
o
r
m
atio
n
f
r
o
m
d
atas
ets.
I
n
th
is
co
n
tex
t,
th
e
ad
v
e
n
t
o
f
d
ee
p
lear
n
in
g
tec
h
n
iq
u
es
h
as
o
p
en
ed
u
p
n
ew
h
o
r
izo
n
s
f
o
r
im
p
r
o
v
in
g
th
e
m
ea
s
u
r
em
en
t
o
f
p
ass
en
g
er
s
atis
f
ac
tio
n
.
Dee
p
lear
n
in
g
(
DL
)
,
a
s
u
b
s
et
o
f
a
r
tific
ial
in
tellig
en
c
e,
h
as
d
em
o
n
s
tr
ated
u
n
p
ar
alleled
ca
p
a
b
ilit
ies
in
p
r
o
ce
s
s
in
g
v
ast
am
o
u
n
ts
o
f
d
ata,
d
etec
tin
g
s
u
b
tle
p
atter
n
s
,
an
d
m
ak
in
g
ac
c
u
r
ate
p
r
ed
ictio
n
s
.
B
y
h
ar
n
ess
in
g
th
e
p
o
wer
o
f
d
ee
p
lear
n
in
g
,
th
e
av
iatio
n
in
d
u
s
tr
y
ca
n
tr
an
s
f
o
r
m
its
ap
p
r
o
ac
h
to
u
n
d
er
s
tan
d
i
n
g
an
d
en
h
a
n
cin
g
p
ass
en
g
er
s
atis
f
ac
tio
n
.
B
u
t
th
e
p
r
o
b
lem
o
f
d
ee
p
lea
r
n
i
n
g
ap
p
r
o
ac
h
es
is
th
e
lim
itatio
n
s
o
f
d
ea
lin
g
with
co
m
p
lex
tab
u
lar
d
ata
in
o
r
d
er
to
g
et
in
s
ig
h
ts
wh
ich
r
eq
u
ir
e
a
d
e
d
icate
d
d
ee
p
n
e
u
r
al
f
o
r
tab
u
lar
d
ata
in
s
tead
o
f
im
p
lem
en
tin
g
class
ical
d
ee
p
lear
n
in
g
m
o
d
els.
T
h
is
p
ap
er
aim
s
to
d
elv
e
in
t
o
th
e
r
ea
lm
o
f
a
v
iatio
n
p
ass
en
g
er
s
atis
f
ac
tio
n
m
ea
s
u
r
em
en
t
b
y
l
ev
er
ag
in
g
cu
ttin
g
-
ed
g
e
d
ee
p
lear
n
in
g
tech
n
iq
u
es.
T
h
ese
tech
n
i
q
u
es
ca
n
b
e
ap
p
lied
to
a
v
a
r
iety
o
f
d
ata
s
o
u
r
ce
s
,
s
u
ch
as
p
ass
en
g
er
r
ev
iews,
s
o
cial
m
ed
ia
s
en
tim
en
t
an
al
y
s
is
,
an
d
o
p
er
atio
n
al
d
ata,
to
p
r
o
v
id
e
a
h
o
lis
tic
an
d
r
ea
l
tim
e
ass
es
s
m
en
t
o
f
p
ass
en
g
er
s
atis
f
ac
tio
n
.
B
y
d
o
in
g
s
o
,
air
lin
es
an
d
av
iatio
n
s
tak
eh
o
ld
er
s
ca
n
g
ain
in
v
al
u
ab
le
in
s
ig
h
ts
in
to
p
ass
en
g
er
p
r
ef
e
r
en
ce
s
,
id
en
tify
ar
ea
s
f
o
r
im
p
r
o
v
em
e
n
t,
an
d
u
ltima
tely
e
n
h
an
ce
th
e
o
v
e
r
all
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
3
,
J
u
n
e
20
25
:
3
3
6
2
-
3
3
7
2
3364
p
ass
en
g
er
ex
p
er
ie
n
ce
.
As
th
e
av
iatio
n
in
d
u
s
tr
y
co
n
tin
u
e
s
to
ev
o
lv
e
an
d
ad
ap
t
t
o
c
h
an
g
in
g
p
ass
en
g
er
ex
p
ec
tatio
n
s
,
th
is
p
ap
er
s
tan
d
s
as
a
v
ital
co
n
tr
ib
u
tio
n
to
th
e
f
ield
,
o
f
f
er
in
g
a
r
o
a
d
m
ap
f
o
r
a
m
o
r
e
d
ata
-
d
r
iv
en
an
d
r
esp
o
n
s
iv
e
ap
p
r
o
ac
h
to
p
a
s
s
en
g
er
s
atis
f
ac
tio
n
m
ea
s
u
r
em
en
t.
B
y
h
ar
n
ess
in
g
th
e
p
o
ten
ti
al
o
f
d
ee
p
lear
n
i
n
g
,
we
en
d
ea
v
o
r
to
n
o
t
o
n
ly
im
p
r
o
v
e
th
e
q
u
ality
o
f
air
tr
av
el
b
u
t
a
ls
o
en
s
u
r
e
th
at
p
ass
en
g
er
s
’
v
o
i
ce
s
an
d
ex
p
e
r
ien
ce
s
ar
e
at
th
e
f
o
r
ef
r
o
n
t o
f
av
iatio
n
in
n
o
v
atio
n
[
1
6
]
–
[
1
8
]
.
Ou
r
r
esear
ch
will
en
co
m
p
ass
an
ad
v
an
ce
d
ap
p
r
o
ac
h
b
ased
o
n
T
ab
Nets
ar
ch
itectu
r
e,
in
cl
u
d
in
g
d
ata
co
llectio
n
,
p
r
ep
r
o
ce
s
s
in
g
,
an
d
th
e
d
ev
elo
p
m
en
t
o
f
d
ee
p
lear
n
in
g
m
o
d
els
tailo
r
ed
to
th
e
av
iatio
n
co
n
tex
t.
W
e
will
also
ev
alu
ate
th
e
p
er
f
o
r
m
an
ce
o
f
th
ese
m
o
d
els
ag
ain
s
t
tr
ad
itio
n
al
s
ati
s
f
ac
tio
n
m
ea
s
u
r
em
en
t
m
eth
o
d
s
to
h
ig
h
lig
h
t
th
e
ad
v
a
n
tag
es
o
f
a
d
o
p
tin
g
d
ee
p
lear
n
in
g
tec
h
n
iq
u
es
d
ed
icate
d
to
tab
u
lar
d
ata.
Nu
m
er
o
u
s
r
esear
c
h
er
s
h
av
e
d
elv
ed
in
to
th
e
r
ea
lm
o
f
p
ass
en
g
er
s
atis
f
ac
tio
n
u
tili
zin
g
b
o
th
m
ac
h
in
e
lear
n
i
n
g
(
ML
)
[
5
]
,
[
1
3
]
–
[
1
5
]
an
d
DL
[
1
3
]
,
[
1
5
]
,
[
1
9
]
,
[
2
0
]
tech
n
iq
u
es
with
in
th
e
ex
is
tin
g
liter
atu
r
e.
I
t
is
n
o
tewo
r
th
y
th
at
DL
-
b
ased
s
o
lu
tio
n
s
co
n
s
is
ten
tly
o
u
tp
er
f
o
r
m
tr
ad
iti
o
n
al
ML
m
o
d
els.
T
h
is
is
n
o
t
s
u
r
p
r
is
in
g
,
as
d
ee
p
lear
n
i
n
g
m
o
d
els
ar
e
r
en
o
wn
ed
f
o
r
th
eir
h
eig
h
ten
ed
ac
c
u
r
ac
y
an
d
s
tab
ilit
y
in
ex
t
r
ac
tin
g
a
n
d
a
n
aly
zin
g
k
ey
f
ea
tu
r
es
cr
itica
l
f
o
r
class
if
icatio
n
.
Mo
r
eo
v
er
,
th
e
y
e
x
ce
l
in
u
n
c
o
v
er
in
g
in
tr
icate
p
atter
n
s
with
i
n
d
atasets
,
tr
an
s
latin
g
in
to
im
p
r
ess
iv
e
r
ea
l
-
wo
r
ld
d
ep
lo
y
m
e
n
t
r
esu
lts
.
H
o
wev
er
,
a
c
o
m
m
o
n
lim
itatio
n
in
th
ese
p
r
ev
io
u
s
s
tu
d
ies
is
th
e
a
b
s
en
ce
o
f
a
m
o
d
el
s
p
ec
if
ically
d
esig
n
ed
t
o
h
a
n
d
l
e
tab
u
lar
d
ata.
T
o
ad
d
r
ess
th
i
s
g
ap
,
o
u
r
s
tu
d
y
e
m
p
lo
y
s
a
n
a
d
v
an
ce
d
ap
p
r
o
ac
h
-
T
ab
Nets
m
eticu
lo
u
s
ly
cr
af
ted
f
o
r
tab
u
lar
d
ata
an
aly
s
is
.
T
ab
-
Net
s
tan
d
s
as
a
n
eu
r
al
n
etwo
r
k
ar
ch
itectu
r
e
ex
p
licitly
tailo
r
ed
f
o
r
p
r
o
ce
s
s
in
g
s
tr
u
ctu
r
ed
d
ata,
c
o
m
m
o
n
l
y
en
c
o
u
n
ter
e
d
i
n
d
ata
b
ases
an
d
s
p
r
ea
d
s
h
ee
ts
.
I
ts
v
alu
e
p
r
o
p
o
s
itio
n
lies
in
its
d
u
al
ca
p
ab
ilit
y
o
f
p
r
o
v
i
d
in
g
h
ig
h
p
er
f
o
r
m
an
ce
p
r
ed
ictiv
e
m
o
d
e
lin
g
wh
ile
o
f
f
e
r
in
g
in
ter
p
r
etab
le
in
s
ig
h
ts
in
to
f
ea
t
u
r
e
im
p
o
r
tan
ce
.
T
ab
Net
ac
h
iev
es
th
is
u
n
iq
u
e
b
alan
ce
th
r
o
u
g
h
its
ar
ch
itectu
r
e
,
wh
ich
co
m
b
i
n
es
th
e
i
n
ter
p
r
et
ab
ilit
y
o
f
d
ec
is
io
n
tr
ee
s
with
th
e
f
lex
ib
ilit
y
o
f
d
ee
p
lear
n
in
g
.
L
e
v
er
ag
in
g
s
p
ar
s
e
atten
tio
n
m
ec
h
an
is
m
s
,
T
ab
Net
s
elec
tiv
ely
f
o
cu
s
es
o
n
s
u
b
s
ets
o
f
in
p
u
t
f
ea
tu
r
es
at
ea
ch
d
ec
is
io
n
s
tep
.
T
h
is
ef
f
icien
t
ap
p
r
o
ac
h
e
n
ab
les
it
to
h
an
d
l
e
h
ig
h
d
im
e
n
s
io
n
al
d
ata
ef
f
ec
tiv
ely
,
m
itig
atin
g
th
e
r
is
k
o
f
o
v
er
f
itti
n
g
.
Ad
d
itio
n
ally
,
T
a
b
Net
’
s
r
o
b
u
s
tn
ess
ex
ten
d
s
to
its
ca
p
ab
ilit
y
to
h
an
d
le
m
is
s
in
g
d
ata
g
r
ac
ef
u
lly
.
T
h
e
r
esu
lts
o
f
all
o
u
r
e
x
p
er
im
e
n
ts
,
wh
ich
in
v
o
lv
e
d
em
p
lo
y
in
g
v
ar
io
u
s
co
n
f
ig
u
r
atio
n
s
f
o
r
b
o
th
th
e
en
co
d
er
a
n
d
d
ec
o
d
er
s
tep
s
,
wer
e
aim
ed
at
at
tain
in
g
s
ig
n
if
ican
t
im
p
r
o
v
em
e
n
ts
in
th
e
p
er
f
o
r
m
a
n
ce
o
f
t
h
e
T
ab
Net
n
etwo
r
k
;
I
n
f
ac
t,
we
im
p
lem
en
t
R
F,
DT
,
K
NN,
ML
P,
L
R
an
d
NB
to
co
m
p
a
r
e
class
ica
l m
ac
h
in
e
lear
n
in
g
m
o
d
els p
e
r
f
o
r
m
a
n
ce
s
(
R
F,
DT
,
KNN,
L
R
an
d
NB
)
,
n
eu
r
al
n
etwo
r
k
m
o
d
el
(
ML
P)
p
er
f
o
r
m
a
n
ce
s
a
n
d
T
a
b
Net
p
er
f
o
r
m
a
n
ce
s
.
R
esu
lts
s
h
o
w
in
ter
m
s
o
f
ac
cu
r
ac
y
,
F1
-
s
co
r
e
an
d
G
-
m
ea
n
s
co
r
e
h
o
w
T
ab
Net
ex
ce
l
s
ig
n
if
ican
tly
all
o
f
th
ese
ML
m
o
d
els,
o
n
ly
R
F
an
d
ML
P
g
iv
e
r
esu
lts
clo
s
e
to
T
ab
Net.
W
h
ile
co
m
p
ar
i
n
g
o
u
r
r
esu
lts
to
th
e
s
tate
-
of
-
t
h
e
-
ar
t
p
ap
er
s
in
ter
m
s
o
f
ac
c
u
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all
an
d
AUC,
we
f
in
d
o
u
t
th
at
o
u
r
T
ab
Net
m
o
d
el
o
u
tp
er
f
o
r
m
s
also
all
o
f
th
ese
s
tu
d
ies.
W
e
ca
n
s
ay
t
h
at
th
is
m
o
d
el
ca
n
b
e
p
r
o
p
o
s
ed
in
r
ea
l
-
life
s
itu
atio
n
s
th
at
r
eq
u
ir
e
r
ea
l
-
tim
e
a
n
aly
s
is
o
f
p
ass
en
g
er
’
s
s
atis
f
ac
tio
n
.
T
h
e
r
est o
f
th
is
p
ap
er
is
s
tr
u
ctu
r
es a
s
f
o
llo
w:
A
r
elate
d
wo
r
k
s
ec
tio
n
wh
er
e
we
p
r
esen
t state
o
f
th
e
ar
t
p
ap
er
s
th
at
s
tu
d
y
ai
r
lin
e
p
ass
en
g
er
s
s
atis
f
ac
tio
n
u
s
in
g
m
ac
h
in
e
lear
n
i
n
g
a
n
d
d
ee
p
lear
n
in
g
tech
n
iq
u
es.
A
m
ater
ial
an
d
m
eth
o
d
s
s
ec
tio
n
wh
er
e
we
d
escr
ib
e
th
e
d
ataset
u
s
ed
in
th
is
s
tu
d
y
an
d
a
th
e
o
r
ical
b
ac
k
g
r
o
u
n
d
o
f
th
e
m
o
d
el
an
d
m
etr
ics
u
s
ed
i
n
th
is
s
tu
d
y
.
A
r
esu
lts
an
d
d
i
s
cu
s
s
io
n
s
ec
tio
n
wh
er
e
we
p
r
o
v
id
e
r
esu
lts
o
f
th
is
s
tu
d
y
an
d
th
e
an
aly
s
is
an
d
in
te
r
p
r
etatio
n
o
f
th
ese
r
esu
lts
,
an
d
f
in
ally
a
s
ec
tio
n
d
ed
i
ca
ted
f
o
r
co
n
clu
s
io
n
f
o
llo
we
d
b
y
th
is
p
ap
e
r
’
s
r
ef
er
e
n
ce
s
.
2.
M
AT
E
R
I
AL
S AN
D
M
E
T
H
O
DS
2
.
1
.
Da
t
a
s
et
des
cr
iptio
n
I
n
o
u
r
wo
r
k
we
u
s
e
th
e
“
air
li
n
e
p
ass
en
g
er
s
atis
f
ac
tio
n
”
d
at
aset
th
at
en
co
m
p
ass
es
1
2
9
,
8
8
0
s
am
p
les
with
2
4
f
ea
tu
r
es.
Desig
n
ed
to
ex
p
lo
r
e
p
ass
en
g
er
ex
p
e
r
ien
ce
s
an
d
s
atis
f
ac
tio
n
with
air
l
in
e
s
er
v
ices,
th
ese
f
ea
tu
r
es
ar
e
d
iv
id
e
d
in
to
p
er
s
o
n
al
in
f
o
r
m
atio
n
(
e.
g
.
,
ag
e
,
g
en
d
er
)
,
tr
a
v
el
d
etails
(
e.
g
.
,
f
li
g
h
t
d
is
tan
ce
,
a
r
r
iv
al
d
elay
)
,
an
d
s
er
v
ice
r
atin
g
s
(
e.
g
.
,
W
iFi
q
u
ality
,
f
o
o
d
,
en
ter
tain
m
en
t)
.
T
h
is
Kag
g
le
-
h
o
s
ted
d
at
aset
o
f
f
er
s
in
s
ig
h
ts
in
to
f
ac
to
r
s
d
r
iv
in
g
p
ass
en
g
er
co
n
ten
tm
en
t a
n
d
d
is
s
atis
f
ac
tio
n
in
th
e
air
lin
e
i
n
d
u
s
tr
y
[
2
1
]
,
[
2
2
]
.
T
h
e
d
ataset
co
m
p
r
is
es sev
er
al
v
ar
iab
les as lis
ted
b
elo
w:
−
Satis
f
ac
tio
n
v
ar
iab
le,
wh
ich
s
er
v
es
as
th
e
tar
g
et
v
ar
iab
le.
I
t
ca
teg
o
r
izes
cu
s
to
m
er
s
in
to
two
g
r
o
u
p
s
,
s
atis
f
ied
o
r
d
is
s
atis
f
ied
with
th
e
air
lin
e
’
s
s
er
v
ices.
−
Gen
d
er
: I
d
e
n
tifie
s
cu
s
to
m
er
g
en
d
er
(
Ma
le/Fem
ale)
.
−
C
u
s
to
m
er
T
y
p
e:
C
lass
if
ies as
“
L
o
y
al
”
o
r
“
Dis
lo
y
al
”
b
ased
o
n
p
r
ev
i
o
u
s
in
ter
ac
tio
n
s
.
−
Ag
e:
Pro
v
id
es in
s
ig
h
ts
in
to
p
a
s
s
en
g
er
ag
e
d
is
tr
ib
u
tio
n
.
−
T
y
p
e
o
f
T
r
av
el:
C
ateg
o
r
izes a
s
“
B
u
s
in
es
s
”
o
r
“
Per
s
o
n
al
”
tr
a
v
el.
−
C
las
s
: I
n
d
icate
s
s
er
v
ice
class
(
E
co
n
o
m
y
,
E
co
Plu
s
,
B
u
s
in
ess
)
.
−
Fli
g
h
t D
is
tan
ce
: Q
u
an
tifie
s
f
li
g
h
t d
is
tan
ce
in
m
iles
.
−
Dep
ar
tu
r
e
Ar
r
iv
al
Dela
y
in
Mi
n
u
tes:
Qu
an
tifie
s
f
lig
h
t d
elay
i
n
m
in
u
tes.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
E
n
h
a
n
cin
g
ta
b
u
la
r
d
a
ta
a
n
a
ly
s
is
fo
r
cla
s
s
ifica
tio
n
o
f a
ir
lin
e
p
a
s
s
en
g
er sa
tis
fa
ctio
n
…
(
R
a
c
h
id
K
a
id
i
)
3365
−
Fu
r
th
er
m
o
r
e
,
s
ev
er
al
v
ar
iab
le
s
g
au
g
e
s
p
ec
if
ic
asp
ec
ts
o
f
th
e
cu
s
to
m
er
ex
p
er
ie
n
ce
,
ea
ch
r
ated
o
n
a
s
ca
le
f
r
o
m
0
to
5
.
Ho
w
ar
e:
s
ea
t
co
m
f
o
r
t,
d
ep
a
r
tu
r
e/ar
r
i
v
al
s
atis
f
ac
tio
n
with
f
lig
h
t
tim
es
,
f
o
o
d
an
d
d
r
in
k
,
g
ate
lo
ca
tio
n
,
in
f
lig
h
t
W
i
-
Fi
s
er
v
ice,
in
f
lig
h
t
e
n
ter
tain
m
en
t,
o
n
li
n
e
s
u
p
p
o
r
t,
ea
s
e
o
f
o
n
lin
e
b
o
o
k
in
g
,
o
n
-
b
o
ar
d
s
er
v
ice,
leg
r
o
o
m
s
er
v
ice,
b
ag
g
ag
e
h
an
d
lin
g
,
c
h
ec
k
-
in
s
er
v
ice,
clea
n
lin
ess
,
o
n
lin
e
b
o
ar
d
in
g
,
ea
s
e
o
f
o
n
lin
e
b
o
o
k
in
g
,
o
n
-
b
o
ar
d
s
er
v
ice,
l
eg
r
o
o
m
s
er
v
ice,
b
ag
g
ag
e
h
an
d
lin
g
,
c
h
e
ck
-
in
s
er
v
ice
,
clea
n
lin
ess
,
o
n
lin
e
b
o
ar
d
in
g
,
s
ea
t
co
m
f
o
r
t,
d
ep
a
r
tu
r
e/ar
r
iv
al
tim
e
co
n
v
en
ien
ce
,
f
o
o
d
an
d
d
r
i
n
k
,
g
ate
lo
ca
tio
n
,
in
f
ig
h
t
W
i
-
Fi
s
er
v
ice,
I
n
f
lig
h
t
E
n
ter
tain
m
e
n
t
,
“
Dep
ar
tu
r
e
d
elay
in
m
in
u
tes
”
an
d
“
Ar
r
iv
al
d
elay
in
m
in
u
tes
”
.
T
ab
le
1
s
h
o
wca
s
es
th
e
cla
s
s
d
i
s
tr
ib
u
tio
n
ac
r
o
s
s
tr
ain
an
d
test
d
atasets
.
T
h
is
b
alan
ce
d
d
is
tr
ib
u
tio
n
,
with
4
5
,
0
2
5
in
s
tan
ce
s
o
f
“
Satis
f
ied
”
an
d
5
8
,
8
7
9
in
s
tan
ce
s
o
f
“
N
eu
tr
al
o
r
d
is
s
atis
f
ied
”
clas
s
es,
av
er
ts
th
e
n
ee
d
f
o
r
p
r
e
-
tr
ain
in
g
b
alan
cin
g
tech
n
iq
u
es.
I
t
u
n
d
er
s
co
r
es
th
e
d
ataset
’
s
s
u
itab
ilit
y
f
o
r
tr
ain
in
g
m
o
d
els,
en
s
u
r
in
g
r
o
b
u
s
t
p
er
f
o
r
m
an
ce
an
d
g
e
n
er
aliza
tio
n
with
o
u
t c
lass
im
b
alan
ce
co
n
ce
r
n
s
.
T
ab
le
1
.
C
lass
d
is
tr
ib
u
tio
n
in
t
r
ain
in
g
an
d
test
s
ets
C
l
a
s
s
Tr
a
i
n
Te
st
S
a
t
i
sf
i
e
d
4
5
0
2
5
1
1
4
0
3
N
e
u
t
r
a
l
o
r
d
i
ss
a
t
i
sf
i
e
d
5
8
8
7
9
1
4
5
7
3
2
.
2
.
T
a
bNet
cla
s
s
if
ier
T
ab
u
lar
d
ata
h
o
ld
s
g
r
ea
t
im
p
o
r
tan
ce
ac
r
o
s
s
a
wid
e
r
an
g
e
o
f
i
n
d
u
s
tr
ies,
in
clu
d
in
g
h
ea
lth
ca
r
e,
f
in
a
n
ce
,
b
an
k
in
g
,
r
etail,
an
d
m
ar
k
etin
g
.
Ar
ik
an
d
Pfister
p
r
o
v
id
e
an
in
n
o
v
ativ
e
an
d
in
ter
p
r
etab
le
ca
n
o
n
ical
ar
ch
itectu
r
e,
h
ar
n
ess
in
g
th
e
in
h
er
en
t
ca
p
a
b
ilit
ies
o
f
d
ee
p
n
eu
r
al
n
etwo
r
k
s
.
T
h
is
in
n
o
v
ativ
e
m
et
h
o
d
o
lo
g
y
co
m
b
in
es
th
e
ad
v
an
tag
es
o
f
u
n
s
u
p
er
v
is
ed
p
r
e
-
tr
ain
in
g
,
m
a
k
in
g
it
ea
s
ier
to
p
r
e
d
ict
h
id
d
e
n
f
ea
tu
r
es,
with
th
e
p
o
wer
o
f
s
u
p
er
v
is
ed
lear
n
i
n
g
to
im
p
r
o
v
e
th
e
ef
f
ec
tiv
e
n
ess
o
f
class
if
icatio
n
an
d
p
r
e
d
ictiv
e
task
s
.
I
t
h
ar
n
ess
es
s
eq
u
en
tial
atten
tio
n
m
ec
h
an
is
m
s
to
s
tr
ateg
ically
s
elec
t
r
elev
an
t
f
ea
tu
r
es
d
u
r
in
g
ea
c
h
d
ec
is
io
n
s
tep
.
T
h
is
n
o
t
o
n
ly
f
o
s
ter
s
in
ter
p
r
etab
ilit
y
b
u
t
also
p
r
o
m
o
tes
m
o
r
e
ef
f
icien
t
lear
n
in
g
b
y
f
o
cu
s
in
g
th
e
lea
r
n
in
g
c
ap
ac
ity
o
n
th
e
m
o
s
t
s
ig
n
if
ican
t
f
ea
t
u
r
es.
T
h
e
T
ab
Net
[
2
3
]
class
if
ier
ar
ch
itectu
r
e
co
n
s
is
ts
o
f
a
n
en
c
o
d
er
th
at
u
s
es
a
s
eq
u
en
ce
o
f
d
ec
is
io
n
s
tep
s
,
en
co
m
p
ass
in
g
f
ea
tu
r
e
tr
an
s
f
o
r
m
atio
n
s
an
d
att
en
tio
n
m
ec
h
a
n
is
m
s
.
I
ts
m
ain
r
o
le
is
to
d
is
ce
r
n
an
d
h
ig
h
lig
h
t
t
h
e
m
o
s
t
in
f
o
r
m
ativ
e
attr
ib
u
tes
o
f
t
h
e
in
p
u
t
d
ata.
A
n
d
a
d
ec
o
d
e
r
th
at
tak
es
th
e
r
ep
r
esen
tatio
n
f
r
o
m
th
e
en
co
d
er
a
n
d
r
ec
o
n
s
tr
u
cts th
e
f
ea
tu
r
es.
2
.
3
.
T
a
bNet
enco
der
Fig
u
r
e
1
s
h
o
ws
th
e
ar
ch
itectu
r
e
o
f
T
ab
Net
E
n
c
o
d
er
.
T
h
e
i
n
itial
s
tep
in
v
o
lv
es
u
tili
zin
g
th
e
d
ataset
with
o
u
t
an
y
f
ea
tu
r
e
en
g
i
n
ee
r
i
n
g
.
Su
b
s
eq
u
en
tly
,
a
s
er
ies
o
f
f
u
n
d
am
e
n
tal
o
p
er
atio
n
s
ar
e
a
p
p
lied
,
wh
ich
i
n
clu
d
e
b
atch
n
o
r
m
aliza
tio
n
,
f
ea
tu
r
e
tr
an
s
f
o
r
m
atio
n
,
a
n
d
d
ata
s
p
litt
in
g
.
Fo
llo
win
g
th
is
,
a
r
e
p
etitiv
e
s
eq
u
en
ce
o
f
s
tep
s
u
n
f
o
ld
s
,
co
m
p
r
is
in
g
s
ev
er
al
o
p
er
atio
n
s
in
ea
ch
s
tep
:
atten
tiv
e
tr
an
s
f
o
r
m
atio
n
,
m
ask
in
g
,
f
ea
tu
r
e
tr
an
s
f
o
r
m
atio
n
,
d
ata
s
p
litt
in
g
,
an
d
co
n
c
lu
d
in
g
with
th
e
ap
p
licatio
n
o
f
th
e
r
ec
t
if
ied
lin
ea
r
u
n
it
(
R
eL
U)
.
T
h
e
d
eter
m
in
atio
n
o
f
th
e
n
u
m
b
er
o
f
s
tep
s
is
co
n
tin
g
en
t
u
p
o
n
th
e
av
ailab
le
c
o
m
p
u
tatio
n
al
ca
p
ac
ity
,
m
ea
n
i
n
g
t
h
at
th
e
n
u
m
b
er
o
f
s
tep
s
is
in
f
lu
en
ce
d
b
y
th
e
s
y
s
tem
’
s
co
m
p
u
tatio
n
al
r
eso
u
r
ce
s
Fig
u
r
e
1
.
T
a
b
Net
en
co
d
er
ar
c
h
itectu
r
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
3
,
J
u
n
e
20
25
:
3
3
6
2
-
3
3
7
2
3366
2
.
3
.
1
.
F
ea
t
ure
t
r
a
ns
f
o
rm
er
T
h
e
in
clu
s
io
n
o
f
th
e
f
ea
t
u
r
e
t
r
an
s
f
o
r
m
er
with
in
th
e
T
ab
Net
ar
ch
itectu
r
e
p
lay
s
a
s
ig
n
if
ica
n
t
r
o
le
in
au
g
m
en
tin
g
th
e
m
o
d
el
’
s
ca
p
ac
ity
to
ac
q
u
ir
e
a
r
ich
e
r
a
n
d
m
o
r
e
i
n
f
o
r
m
a
t
i
v
e
d
a
t
a
r
e
p
r
e
s
e
n
t
a
t
io
n
.
I
t
f
a
c
i
l
i
t
at
e
s
t
h
e
m
o
d
e
l
’
s
c
a
p
a
b
i
li
t
y
t
o
d
is
c
e
r
n
i
n
t
r
i
c
a
t
e
,
n
o
n
-
l
i
n
ea
r
r
e
l
a
ti
o
n
s
h
i
p
s
i
n
h
e
r
e
n
t
i
n
t
h
e
t
a
b
u
l
a
r
d
a
t
a
.
T
h
e
f
e
a
t
u
r
e
t
r
a
n
s
f
o
r
m
e
r
c
o
m
p
r
is
e
s
tw
o
p
a
r
ts
:
o
n
e
t
h
a
t
is
s
h
a
r
e
d
a
c
r
o
s
s
d
e
c
is
i
o
n
s
t
e
p
s
a
n
d
o
n
e
t
h
a
t
is
d
e
ci
s
io
n
s
t
e
p
-
d
e
p
e
n
d
e
n
t
.
E
a
c
h
o
f
t
h
e
s
e
c
o
m
p
o
n
e
n
t
s
i
s
c
o
m
p
o
s
e
d
o
f
f
u
l
l
y
c
o
n
n
e
c
t
e
d
l
a
y
er
s
,
b
a
t
c
h
n
o
r
m
a
l
i
za
t
i
o
n
,
a
n
d
g
at
e
d
l
i
n
e
a
r
u
n
i
ts
.
I
n
Fig
u
r
e
2
,
th
e
r
ep
r
esen
tatio
n
illu
s
tr
ates
th
e
co
n
s
titu
en
ts
o
f
th
e
Featu
r
e
T
r
an
s
f
o
r
m
er
,
wh
ich
co
m
p
r
is
es
a
to
tal
o
f
f
o
u
r
lay
e
r
s
o
f
g
ated
lin
ea
r
u
n
it
(
GL
U)
b
lo
ck
s
,
th
e
2
GL
U
b
lo
ck
s
s
h
o
u
ld
b
e
s
h
a
r
ed
an
d
2
s
h
o
u
l
d
b
e
in
d
ep
en
d
en
t
t
o
en
h
an
ce
th
e
r
o
b
u
s
tn
ess
an
d
e
f
f
icien
cy
o
f
th
e
lear
n
in
g
p
r
o
ce
s
s
.
I
n
GL
U
b
lo
c
k
[
2
4
]
,
th
e
in
p
u
t
is
s
p
lit
in
to
two
p
ar
ts
alo
n
g
its
last
d
im
en
s
io
n
,
a
n
o
n
lin
ea
r
tr
a
n
s
f
o
r
m
atio
n
is
ap
p
lied
u
s
in
g
t
h
e
s
ig
m
o
id
f
u
n
ctio
n
(
2
)
f
o
r
th
e
s
ec
o
n
d
p
ar
t,
an
d
th
e
o
u
tp
u
t
is
th
e
elem
en
t
-
wis
e
p
r
o
d
u
ct
b
etwe
en
th
e
f
ir
s
t
p
ar
t
an
d
th
e
o
u
tp
u
t
o
f
th
e
s
ig
m
o
id
ac
tiv
atio
n
:
(
)
=
1
⨂
(
2
)
(
1
)
Fu
r
th
er
m
o
r
e
,
af
ter
ea
c
h
b
lo
c
k
,
a
n
o
r
m
aliza
tio
n
s
tep
with
a
s
ca
lin
g
f
ac
to
r
o
f
√
0
.
5
is
ap
p
lied
.
T
h
is
o
p
er
atio
n
co
n
tr
ib
u
tes
to
s
tab
ilit
y
in
th
e
tr
ain
in
g
p
r
o
ce
s
s
,
en
s
u
r
in
g
th
at
th
e
v
ar
ian
c
e
o
f
th
e
m
o
d
el
’
s
a
ctiv
atio
n
s
r
em
ain
s
with
in
r
ea
s
o
n
ab
le
b
o
u
n
d
s
.
Fig
u
r
e
2
.
Featu
r
e
tr
an
s
f
o
r
m
er
2
.
3
.
2
.
At
t
ent
iv
e
t
r
a
ns
f
o
rm
er
Fo
llo
win
g
th
e
co
m
p
letio
n
o
f
th
e
Featu
r
e
T
r
an
s
f
o
r
m
er
s
tag
e,
th
e
r
esu
ltan
t
o
u
tp
u
t
p
ass
to
Atten
tiv
e
B
lo
ck
.
T
h
is
p
ar
ticu
lar
b
lo
ck
p
lay
s
a
p
iv
o
tal
r
o
le
in
th
e
f
ea
tu
r
e
s
elec
tio
n
p
r
o
ce
s
s
.
I
n
Fig
u
r
e
3
,
a
r
ep
r
esen
tatio
n
elu
cid
ates
th
e
in
ter
n
al
co
m
p
o
n
en
ts
co
m
p
r
is
in
g
th
e
Atten
tiv
e
B
lo
ck
.
I
t
en
co
m
p
ass
es
a
Fu
lly
C
o
n
n
ec
ted
lay
er
,
a
B
atch
No
r
m
aliza
tio
n
la
y
er
,
a
lay
er
d
e
d
icate
d
t
o
Prio
r
Scale
s
,
an
d
a
Sp
ar
s
em
ax
lay
e
r
[
2
5
]
em
p
l
o
y
ed
f
o
r
th
e
p
u
r
p
o
s
e
o
f
c
o
ef
f
icien
t
n
o
r
m
ali
za
tio
n
.
T
h
e
e
m
p
lo
y
m
en
t
o
f
th
e
Sp
ar
s
em
ax
lay
er
f
ac
ilit
ates
th
e
s
p
ar
s
e
s
elec
tio
n
o
f
s
alien
t
f
ea
tu
r
es,
th
er
e
b
y
en
h
an
cin
g
th
e
in
ter
p
r
eta
b
ilit
y
an
d
ef
f
icien
cy
o
f
th
e
f
ea
tu
r
e
s
el
ec
tio
n
p
r
o
ce
s
s
.
T
h
e
Sp
ar
s
em
ax
f
u
n
cti
o
n
is
d
ef
in
e
d
as (
2
)
(
)
=
{
−
,
0
}
(
2
)
Fig
u
r
e
3
.
Atten
tiv
e
tr
a
n
s
f
o
r
m
e
r
w
h
er
e
th
e
th
r
esh
o
ld
τ
is
ca
lcu
lated
u
s
in
g
f
o
r
m
u
la
(
3
)
(
)
=
(
(
∑
_
(
≤
(
)
)
▒
_
)
−
1
)
(
)
⁄
(
3
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
E
n
h
a
n
cin
g
ta
b
u
la
r
d
a
ta
a
n
a
ly
s
is
fo
r
cla
s
s
ifica
tio
n
o
f a
ir
lin
e
p
a
s
s
en
g
er sa
tis
fa
ctio
n
…
(
R
a
c
h
id
K
a
id
i
)
3367
An
d
k
(
z)
is
th
e
m
ax
im
u
m
in
d
e
x
(
f
r
o
m
th
e
s
o
r
te
d
s
et
o
f
in
p
u
t
z)
th
at
m
ee
ts
th
is
co
n
d
itio
n
(
4
)
.
(
)
∶
=
{
[
]
|
1
+
(
)
>
∑
(
)
≤
}
(
4
)
2
.
3
.
3
A
t
t
ent
io
n ma
s
k
Su
b
s
eq
u
en
t
to
th
e
atten
tiv
e
tr
an
s
f
o
r
m
er
s
tep
,
th
e
o
u
tp
u
t
is
d
ir
ec
ted
to
war
d
s
an
atten
ti
o
n
m
ask
.
T
h
is
m
ask
s
er
v
es
a
cr
u
cial
r
o
le
in
id
en
tify
in
g
t
h
e
s
elec
ted
f
ea
t
u
r
es,
en
ab
lin
g
th
e
m
o
d
el
to
q
u
an
tify
t
h
e
o
v
e
r
all
im
p
o
r
tan
ce
o
f
th
ese
f
ea
t
u
r
es
wh
ile
also
co
n
d
u
ct
in
g
a
d
etai
led
an
aly
s
is
at
ea
ch
s
tep
o
f
th
e
p
r
o
ce
s
s
.
W
h
en
it
b
ec
o
m
es
n
ec
ess
ar
y
to
c
o
m
b
in
e
th
e
m
ask
s
f
r
o
m
v
ar
i
o
u
s
s
tep
s
,
a
co
ef
f
icien
t
is
in
tr
o
d
u
ce
d
t
o
weig
h
th
e
r
elativ
e
im
p
o
r
tan
ce
o
f
ea
ch
s
tep
i
n
th
e
d
ec
is
io
n
-
m
ak
i
n
g
p
r
o
ce
s
s
.
F
o
r
ca
lcu
latin
g
th
e
a
g
g
r
e
g
ate
d
ec
is
io
n
co
n
tr
ib
u
tio
n
f
o
r
a
s
am
p
le
b
th
d
ec
is
io
n
s
tep
i
,
th
e
f
o
llo
win
g
f
o
r
m
u
la
is
u
s
ed
(
5
)
[
]
=
∑
(
,
[
]
)
=
1
(
5
)
w
h
er
e
d
b
,
c
[
i
]
is
th
e
o
u
tp
u
t o
f
f
ea
tu
r
e
c
f
o
r
th
e
s
am
p
le
.
2
.
4
.
T
a
bNet
deco
der
T
h
e
Fig
u
r
e
4
s
h
o
ws
th
e
T
ab
Net
d
ec
o
d
er
ar
ch
itectu
r
e.
I
t
’
s
d
is
tin
g
u
is
h
ed
b
y
its
co
m
p
o
s
itio
n
,
b
eg
in
n
in
g
with
a
f
ea
tu
r
e
tr
an
s
f
o
r
m
er
,
w
h
ich
is
s
u
b
s
eq
u
en
tly
f
o
llo
wed
b
y
f
u
lly
co
n
n
ec
ted
lay
er
s
o
p
er
atin
g
with
in
th
e
d
ec
is
io
n
s
tep
.
T
h
e
r
esu
lts
o
f
t
h
is
o
p
er
atio
n
ar
e
th
en
s
u
b
jecte
d
to
s
u
m
m
atio
n
with
th
e
r
ec
o
n
s
tr
u
cted
f
ea
t
u
r
es.
T
h
e
d
ec
o
d
er
is
co
m
p
o
s
ed
o
f
f
e
atu
r
e
tr
an
s
f
o
r
m
er
s
,
f
o
llo
wed
b
y
FC
lay
er
s
at
ea
ch
d
ec
is
io
n
s
tep
.
T
h
e
o
u
tp
u
ts
a
r
e
s
u
m
m
ed
to
o
b
tain
th
e
r
ec
o
n
s
tr
u
cted
f
ea
tu
r
es
[
2
3
]
.
Fig
u
r
e
4.
T
a
b
Net
d
ec
o
d
er
ar
c
h
itectu
r
e
2
.
5
.
M
o
del e
v
a
lua
t
io
n m
et
rics
E
v
a
l
u
a
t
i
n
g
m
a
c
h
i
n
e
le
a
r
n
i
n
g
m
o
d
e
l
s
i
s
a
c
r
u
ci
a
l
s
te
p
t
o
c
o
m
p
r
e
h
e
n
s
i
v
e
l
y
e
v
al
u
a
t
e
t
h
e
i
r
p
e
r
f
o
r
m
a
n
c
e
.
R
e
l
y
i
n
g
o
n
a
s
i
n
g
l
e
m
e
t
r
i
c
m
ay
n
o
t
p
r
o
v
i
d
e
a
c
o
m
p
l
e
t
e
p
i
c
t
u
r
e
,
a
s
a
m
o
d
e
l
c
a
n
p
e
r
f
o
r
m
w
e
l
l
o
n
o
n
e
m
e
t
r
i
c
b
u
t
p
o
o
r
l
y
o
n
a
n
o
t
h
e
r
.
F
u
r
t
h
e
r
m
o
r
e
,
t
h
e
d
a
t
a
s
et
is
i
m
b
a
la
n
c
e
d
wh
i
c
h
m
e
a
n
s
r
el
y
i
n
g
o
n
l
y
o
n
a
cc
u
r
a
c
y
m
a
y
l
e
a
d
t
o
d
i
s
t
o
r
t
e
d
r
e
s
u
l
t
s
.
F
o
r
t
h
a
t
p
u
r
p
o
s
e
,
i
n
o
u
r
s
t
u
d
y
,
w
e
u
s
e
a
v
a
r
i
e
t
y
o
f
m
e
t
r
i
c
s
,
i
n
c
l
u
d
i
n
g
A
c
c
u
r
a
c
y
,
F
1
-
s
c
o
r
e
,
g
-
m
e
a
n
s
c
o
r
e
,
p
r
e
c
is
i
o
n
,
r
e
c
a
ll
,
a
n
d
AU
C
,
t
o
c
o
m
p
r
e
h
e
n
s
i
v
e
l
y
e
v
al
u
a
t
e
a
n
d
d
e
m
o
n
s
t
r
a
te
t
h
e
p
e
r
f
o
r
m
a
n
c
e
o
f
o
u
r
m
o
d
e
l
s
.
2
.
5
.
1
.
Acc
ura
cy
Acc
u
r
ac
y
is
a
co
m
m
o
n
ev
al
u
a
tio
n
m
etr
ic
u
s
ed
to
ass
ess
th
e
p
er
f
o
r
m
an
ce
o
f
a
class
if
icatio
n
m
o
d
el.
I
t
m
ea
s
u
r
es th
e
p
r
o
p
o
r
tio
n
o
f
co
r
r
ec
tly
class
if
ied
in
s
tan
ce
s
o
u
t o
f
th
e
to
tal
in
s
tan
ce
s
in
th
e
d
at
aset:
=
(
+
)
(
+
+
+
)
⁄
(
6
)
w
h
er
e
T
p
an
d
T
n
ar
e
th
e
tr
u
e
p
o
s
itiv
e
an
d
n
eg
ativ
e;
an
d
F
p
a
n
d
F
n
ar
e
th
e
f
alse p
o
s
itiv
e
an
d
n
eg
ativ
e.
2
.
5
.
2
.
F
1
-
s
co
re
T
h
e
F1
s
co
r
e
is
an
alter
n
ativ
e
ev
alu
atio
n
m
etr
ic
i
n
m
ac
h
in
e
lear
n
i
n
g
.
I
t
o
f
f
er
s
a
m
o
r
e
d
etailed
p
er
s
p
ec
tiv
e
o
n
a
m
o
d
el
’
s
p
e
r
f
o
r
m
a
n
ce
b
y
co
n
s
id
er
i
n
g
its
p
er
f
o
r
m
a
n
ce
o
n
in
d
i
v
id
u
al
class
es
r
ath
er
th
an
p
r
o
v
id
i
n
g
an
o
v
e
r
all
ass
ess
m
e
n
t,
as a
cc
u
r
ac
y
d
o
es.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
3
,
J
u
n
e
20
25
:
3
3
6
2
-
3
3
7
2
3368
1
=
2
.
(
×
)
(
+
)
⁄
(
7
)
w
h
er
e
p
r
ec
is
io
n
is
:
=
(
+
)
⁄
(
8
)
an
d
r
ec
all
is
:
=
(
+
)
⁄
(
9
)
2
.
5
.
3
.
G
-
M
ea
n sco
re
T
h
e
G
-
Me
an
,
also
k
n
o
wn
as
th
e
Geo
m
etr
ic
Me
an
s
co
r
e,
is
an
ass
es
s
m
en
t
m
etr
ic
th
at
tak
es
in
to
ac
co
u
n
t
b
o
th
s
en
s
itiv
ity
an
d
s
p
ec
if
icity
in
a
class
if
icatio
n
m
o
d
el.
I
t p
l
ay
s
a
cr
u
cial
r
o
le
in
ac
h
iev
in
g
a
b
alan
ce
b
etwe
en
ac
cu
r
ately
id
en
tify
in
g
p
o
s
itiv
e
an
d
n
eg
ativ
e
ca
s
es,
m
ak
in
g
it
p
ar
ticu
lar
ly
u
s
ef
u
l
wh
en
d
ea
lin
g
with
im
b
alan
ce
d
d
atasets
.
−
=
√
×
(
1
0
)
w
h
er
e
=
(
+
)
⁄
(
1
1
)
2
.
5
.
4
.
AUC
T
h
e
AUC
i
s
a
v
ital
m
etr
ic
in
b
in
ar
y
class
if
icatio
n
task
s
.
I
t
q
u
an
tifie
s
a
m
o
d
el
’
s
ab
ilit
y
to
d
is
cr
im
in
ate
b
etwe
en
p
o
s
itiv
e
an
d
n
eg
ativ
e
class
es
b
y
m
ea
s
u
r
in
g
th
e
ar
ea
u
n
d
er
th
e
r
ec
eiv
e
r
o
p
er
atin
g
ch
ar
ac
ter
is
tic
(
R
O
C
)
cu
r
v
e.
A
h
ig
h
er
AUC
s
ig
n
if
ie
s
b
etter
class
if
icatio
n
ac
cu
r
ac
y
,
m
a
k
in
g
it
a
v
alu
a
b
le
to
o
l
f
o
r
m
o
d
el
ev
alu
atio
n
an
d
co
m
p
ar
is
o
n
.
I
t
p
r
o
v
id
es
a
co
n
cise
s
u
m
m
ar
y
o
f
a
class
if
ier
’
s
o
v
er
all
p
e
r
f
o
r
m
an
ce
ac
r
o
s
s
v
ar
io
u
s
d
ec
is
io
n
th
r
esh
o
ld
s
,
s
im
p
lify
in
g
th
e
ass
ess
m
en
t p
r
o
ce
s
s
in
m
ac
h
in
e
le
ar
n
in
g
.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
3
.
1
.
P
er
f
o
r
m
a
nces a
na
ly
s
is
o
f
T
a
bNet
a
nd
im
plem
ent
ed
m
a
chine le
a
rning
m
o
dels
T
o
d
em
o
n
s
tr
ate
th
e
p
er
f
o
r
m
a
n
ce
o
f
T
ab
Net
m
o
d
els,
we
c
o
n
d
u
cted
a
co
m
p
r
eh
e
n
s
iv
e
co
m
p
ar
is
o
n
o
f
T
ab
Net
’
s
r
esu
lts
ag
ain
s
t
s
ev
e
r
al
class
ical
m
ac
h
in
e
lear
n
in
g
m
o
d
els,
ea
ch
ev
alu
ated
u
s
in
g
th
e
f
o
llo
win
g
k
e
y
m
etr
ics:
ac
cu
r
ac
y
,
F1
s
co
r
e,
a
n
d
g
-
m
ea
n
s
co
r
e.
T
a
b
le
2
s
h
o
ws
th
e
r
esu
lt
o
b
tain
ed
.
Am
o
n
g
th
e
m
o
d
els
test
ed
,
th
e
T
ab
NetCl
ass
if
ier
s
tan
d
s
o
u
t
as
an
ex
ce
p
tio
n
al
co
n
ten
d
er
,
b
o
asti
n
g
t
h
e
h
ig
h
est
s
co
r
es
ac
r
o
s
s
all
th
r
ee
m
ea
s
u
r
es.
No
tab
ly
,
t
h
e
T
ab
N
etC
las
s
if
ie
r
ac
h
iev
es
an
im
p
r
ess
iv
e
p
r
ec
is
io
n
r
ate
o
f
9
6
.
4
7
%,
s
ig
n
alin
g
th
at
a
s
u
b
s
tan
tial
p
o
r
tio
n
o
f
in
s
tan
ce
s
ar
e
co
r
r
ec
tly
class
if
ied
.
T
h
is
h
ig
h
p
r
ec
is
io
n
u
n
d
er
s
co
r
es
th
e
m
o
d
el
’
s
ab
ilit
y
to
ef
f
ec
tiv
ely
d
is
ce
r
n
th
e
v
ar
io
u
s
class
e
s
with
in
th
e
d
ataset.
Fu
r
th
er
m
o
r
e
,
th
e
T
ab
NetCl
ass
if
ier
m
ain
tain
s
its
s
u
p
er
io
r
ity
in
ter
m
s
o
f
th
e
F1
s
co
r
e,
a
m
etr
ic
h
ar
m
o
n
izin
g
p
r
ec
is
io
n
an
d
r
ec
all,
r
ea
ch
i
n
g
a
s
co
r
e
o
f
9
6
.
4
1
%.
T
h
is
h
ig
h
lig
h
ts
th
e
m
o
d
el
’
s
eq
u
ilib
r
iu
m
b
etwe
en
ac
cu
r
ate
p
o
s
itiv
e
p
r
ed
ictio
n
s
an
d
th
e
c
o
m
p
r
eh
en
s
iv
e
ca
p
tu
r
e
o
f
ac
tu
al
p
o
s
itiv
e
in
s
tan
ce
s
.
Similar
ly
,
th
e
T
ab
NetCl
ass
if
ier
’
s
g
eo
m
etr
ic
s
co
r
e
o
f
9
6
.
2
4
%
r
ef
lects
its
ca
p
ac
ity
to
ac
h
iev
e
a
h
ar
m
o
n
io
u
s
b
ala
n
ce
b
etwe
en
p
r
ec
is
io
n
a
n
d
r
e
ca
ll
th
r
o
u
g
h
th
e
g
eo
m
et
r
ic
m
ea
n
.
T
h
e
c
o
n
s
is
ten
t
p
er
f
o
r
m
an
ce
s
o
f
th
e
R
F
an
d
M
L
P
m
o
d
els
ac
r
o
s
s
all
th
r
ee
m
etr
ics
also
u
n
d
er
s
co
r
e
th
eir
r
o
b
u
s
tn
ess
,
with
th
e
R
F
ac
h
iev
in
g
an
ac
cu
r
a
cy
o
f
9
6
.
2
8
%,
an
F1
s
co
r
e
o
f
9
6
.
2
1
%,
a
n
d
a
g
eo
m
etr
ic
s
co
r
e
o
f
9
6
.
0
5
%,
wh
ile
th
e
ML
P
attain
s
9
6
.
2
0
%,
9
6
.
1
3
%,
an
d
9
6
.
0
4
%,
r
esp
ec
tiv
ely
.
Alth
o
u
g
h
th
e
DT
,
KNN,
an
d
Naïv
e
B
ay
es
m
o
d
els
d
is
p
lay
s
lig
h
tly
lo
wer
s
co
r
es,
th
ey
s
till
p
r
esen
t
cr
ed
ib
le
o
u
tc
o
m
es,
s
h
o
wca
s
in
g
th
eir
ab
ilit
y
to
p
r
e
d
ict
with
p
r
ec
is
io
n
.
No
tab
ly
,
L
R
lag
s
b
eh
in
d
o
th
er
m
o
d
e
ls
with
an
ac
cu
r
ac
y
o
f
8
1
.
7
0
%.
T
h
is
r
elativ
ely
lo
wer
a
cc
u
r
ac
y
m
ig
h
t
ar
is
e
f
r
o
m
th
e
in
h
er
en
t
s
im
p
licity
an
d
lin
ea
r
ity
o
f
L
R
,
s
u
g
g
esti
n
g
th
at
f
o
r
th
is
s
p
ec
if
ic
d
ataset,
m
o
r
e
co
m
p
le
x
m
o
d
els
lik
e
T
ab
NetCl
ass
if
ier
,
R
F,
a
n
d
ML
P
ar
e
b
etter
s
u
ited
to
ca
p
tu
r
e
in
tr
i
ca
te
p
atter
n
s
an
d
co
m
p
lex
ities
.
I
n
s
u
m
m
ar
y
,
th
e
c
o
llectiv
e
r
es
u
lts
co
llectiv
ely
im
p
ly
th
at
th
e
T
ab
NetCl
ass
if
ier
s
h
in
es
as
a
v
er
s
atile
an
d
d
ep
en
d
a
b
le
m
o
d
el
f
o
r
p
r
ed
icti
n
g
air
lin
e
p
ass
en
g
e
r
s
atis
f
ac
ti
o
n
.
Fig
u
r
e
5
illu
s
tr
ates
th
e
co
m
p
ar
ativ
e
p
er
f
o
r
m
a
n
ce
o
f
s
ev
en
m
ac
h
in
e
lear
n
in
g
m
o
d
els
ac
r
o
s
s
th
e
ac
cu
r
ac
y
,
F1
-
Sco
r
e,
an
d
G
-
M
ea
n
s
co
r
e
f
o
r
th
e
class
if
icatio
n
o
f
p
ass
en
g
er
’
s
s
atis
f
ac
tio
n
.
T
h
is
f
ig
u
r
e
r
ein
f
o
r
ce
s
th
e
f
in
d
in
g
s
f
r
o
m
th
e
p
r
e
v
io
u
s
tab
les,
em
p
h
asizin
g
t
h
at
T
ab
Net
is
th
e
clea
r
lea
d
er
in
ter
m
s
o
f
p
r
ed
ictiv
e
p
er
f
o
r
m
an
ce
f
o
r
th
is
p
ar
ticu
la
r
class
if
icatio
n
task
.
I
ts
co
n
s
is
ten
tly
h
ig
h
er
v
alu
es
ac
r
o
s
s
all
m
etr
ics
in
d
icate
it
s
s
u
p
er
io
r
it
y
o
v
er
th
e
o
th
er
m
o
d
els co
n
s
id
er
ed
in
th
is
s
tu
d
y
.
T
ab
Net
’
s
s
u
p
er
io
r
p
er
f
o
r
m
a
n
c
e
in
th
is
s
tu
d
y
ca
n
b
e
attr
ib
u
ted
to
s
ev
er
al
k
ey
f
ac
to
r
s
.
I
ts
ar
ch
itectu
r
al
co
m
p
lex
ity
,
th
e
f
ea
tu
r
in
g
atten
tio
n
m
ec
h
a
n
is
m
s
,
en
ab
les
it
to
d
is
ce
r
n
in
tr
icate
p
atter
n
s
an
d
r
elatio
n
s
h
ip
s
with
in
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
E
n
h
a
n
cin
g
ta
b
u
la
r
d
a
ta
a
n
a
ly
s
is
fo
r
cla
s
s
ifica
tio
n
o
f a
ir
lin
e
p
a
s
s
en
g
er sa
tis
fa
ctio
n
…
(
R
a
c
h
id
K
a
id
i
)
3369
th
e
d
ataset,
allo
win
g
it
to
p
r
io
r
itize
r
elev
an
t
in
f
o
r
m
atio
n
an
d
ca
p
tu
r
e
n
o
n
-
lin
ea
r
d
ep
e
n
d
en
c
ies
ef
f
ec
tiv
ely
.
W
e
also
h
av
e
th
e
r
eg
u
lar
izatio
n
t
ec
h
n
iq
u
es
s
u
ch
as
f
ea
tu
r
e
d
r
o
p
o
u
t
an
d
s
p
ar
s
ity
co
n
s
tr
ain
ts
p
r
ev
en
t
o
v
er
f
itti
n
g
,
co
n
tr
ib
u
tin
g
to
th
e
m
o
d
el
’
s
r
o
b
u
s
t
g
en
er
aliza
tio
n
.
Fu
r
t
h
er
m
o
r
e,
th
e
p
o
s
s
ib
ilit
y
o
f
en
s
em
b
le
lear
n
in
g
am
p
lifie
s
its
ca
p
ab
ilit
ies.
Fu
r
th
er
m
o
r
e,
e
f
f
ec
tiv
e
f
ea
tu
r
e
e
n
g
in
ee
r
i
n
g
tai
lo
r
ed
to
th
e
d
ataset
’
s
ch
ar
ac
ter
is
tics
l
ik
ely
p
lay
ed
a
r
o
le
in
o
p
tim
izin
g
T
a
b
Net
’
s
p
er
f
o
r
m
an
ce
.
T
ab
le
2
.
Per
f
o
r
m
an
ce
s
co
m
p
ar
is
o
n
b
etwe
en
T
ab
Net
an
d
m
ac
h
in
e
lear
n
in
g
m
o
d
els
A
c
c
u
r
a
c
y
F1
-
S
c
o
r
e
G
-
M
e
a
n
S
c
o
r
e
R
a
n
d
o
m F
o
r
e
s
t
9
6
.
2
8
9
6
.
2
1
9
6
.
0
5
D
e
c
i
s
i
o
n
Tr
e
e
9
4
.
7
3
9
4
.
6
5
9
4
.
6
7
K
N
N
9
2
.
5
5
9
2
.
3
8
9
2
.
0
4
M
LP
9
6
.
2
0
9
6
.
1
3
9
6
.
0
4
LR
8
1
.
7
0
8
6
.
8
4
8
6
.
6
6
N
a
ï
v
e
B
a
y
e
s
8
6
.
1
2
8
5
.
8
1
8
5
.
6
1
Ta
b
N
e
t
C
l
a
ssi
f
i
e
r
9
6
.
4
7
9
6
.
4
1
9
6
.
2
4
Fig
u
r
e
5
.
Vis
u
aliza
tio
n
d
e
p
ictin
g
T
ab
Net
alo
n
g
s
id
e
o
th
e
r
im
p
lem
en
ted
m
ac
h
in
e
lear
n
i
n
g
m
o
d
els
3
.
2
.
Co
m
pa
ra
t
iv
e
perf
o
r
m
a
nces
a
na
ly
s
is
o
f
T
a
bNet
a
nd
t
he
s
t
a
t
e
-
of
-
t
he
-
a
rt
s
t
ud
ies
T
ab
le
3
s
h
o
ws
th
e
r
esu
lts
o
f
th
e
estab
lis
h
ed
co
m
p
ar
ativ
e
s
tu
d
y
b
etwe
en
o
u
r
d
ev
elo
p
ed
m
o
d
el
an
d
s
tate
o
f
th
e
ar
t
s
tu
d
ies
th
at
tr
ea
ted
t
h
e
p
r
o
b
lem
o
f
an
aly
zin
g
an
d
class
if
y
in
g
th
e
s
ati
s
f
ac
tio
n
o
f
air
lin
e
p
ass
en
g
er
s
.
R
esu
lts
s
h
o
w
th
at
T
ab
Net
o
u
t
p
er
f
o
r
m
s
all
o
th
er
m
o
d
els
in
t
er
m
s
o
f
ac
c
u
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all
,
an
d
AUC.
I
t
ac
h
iev
es
th
e
h
ig
h
est
ac
cu
r
ac
y
an
d
p
r
ec
is
io
n
wh
ile
m
ain
tain
in
g
a
h
ig
h
r
ec
all
r
ate
an
d
AUC
s
co
r
e,
in
d
icatin
g
s
tr
o
n
g
o
v
er
all
p
er
f
o
r
m
an
ce
.
R
F
also
d
em
o
n
s
tr
ates
s
tr
o
n
g
p
e
r
f
o
r
m
a
n
ce
,
with
h
ig
h
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
a
n
d
a
r
esp
ec
tab
le
AUC
s
co
r
e.
Ho
wev
er
,
T
a
b
Net
s
lig
h
tly
o
u
t
p
er
f
o
r
m
s
it
in
m
o
s
t
m
etr
ics.
PS
O
+
NB
p
er
f
o
r
m
s
b
etter
th
an
GA
+
NB
in
ter
m
s
o
f
Ac
cu
r
ac
y
,
Pre
cisi
o
n
,
an
d
R
ec
all.
Ad
d
itio
n
ally
,
it p
r
o
v
id
es a
n
AUC s
co
r
e
o
f
9
2
.
3
%,
in
d
icatin
g
g
o
o
d
d
is
cr
i
m
in
ato
r
y
p
o
wer
.
GA
+
NB
ac
h
iev
es
t
h
e
lo
west
p
er
f
o
r
m
an
ce
a
m
o
n
g
th
e
m
o
d
els,
with
th
e
lo
west
Acc
u
r
ac
y
,
Pre
cisi
o
n
,
a
n
d
R
ec
all
s
co
r
es.
W
e
ca
n
s
ay
th
at
th
e
r
esu
lts
s
u
g
g
est
th
at
T
ab
Net
is
th
e
to
p
-
p
er
f
o
r
m
in
g
m
o
d
el
in
th
is
co
m
p
ar
ativ
e
s
tu
d
y
,
o
f
f
e
r
in
g
th
e
h
i
g
h
est
ac
cu
r
ac
y
a
n
d
p
r
ec
is
io
n
wh
ile
m
ain
tain
in
g
a
g
o
o
d
b
ala
n
ce
b
etwe
en
r
ec
all
a
n
d
AUC.
I
n
s
u
m
m
ar
y
,
we
ca
n
s
ay
th
at
th
e
r
esu
lts
s
u
g
g
est
th
a
t
T
ab
Net
a
p
p
ea
r
s
t
o
b
e
th
e
p
r
ef
er
r
e
d
ch
o
ice
f
o
r
th
e
class
if
icat
io
n
o
f
p
ass
en
g
er
’
s
s
atis
f
ac
tio
n
,
as it c
o
n
s
i
s
ten
tly
a
ch
iev
es th
e
h
ig
h
est
p
er
f
o
r
m
an
ce
ac
r
o
s
s
m
u
ltip
le
m
etr
ics
co
m
p
ar
ed
to
t
h
e
s
ix
im
p
lem
en
ted
m
ac
h
i
n
e
lear
n
in
g
m
o
d
els.
Fu
r
th
er
m
o
r
e,
T
ab
Net
is
th
e
b
est m
o
d
el
in
th
is
co
m
p
ar
ativ
e
s
tu
d
y
with
h
ig
h
est v
alu
es o
f
th
e
u
s
e
m
etr
ics.
T
ab
le
3
.
Per
f
o
r
m
an
ce
s
co
m
p
ar
is
o
n
b
etwe
en
T
ab
Net
an
d
s
tate
o
f
ar
t stu
d
ies
A
c
c
u
r
a
c
y
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
AUC
G
A
+
N
B
[
2
6
]
8
5
.
9
9
8
7
.
9
1
8
7
.
4
3
-
P
S
O
+
N
B
[
2
7
]
8
6
.
1
3
8
7
.
9
0
8
7
.
2
9
9
2
.
3
RF
9
6
.
2
8
9
7
.
2
3
9
4
.
2
1
9
6
.
0
5
Ta
b
N
e
t
9
6
.
4
4
9
7
.
5
7
9
4
.
3
1
9
6
.
2
4
4.
CO
NCLU
SI
O
N
I
n
co
n
clu
s
io
n
,
th
is
co
m
p
r
eh
e
n
s
iv
e
s
tu
d
y
co
m
p
ar
in
g
th
e
p
er
f
o
r
m
a
n
ce
o
f
v
ar
io
u
s
m
ac
h
i
n
e
lear
n
in
g
m
o
d
els
f
o
r
t
h
e
class
if
icatio
n
o
f
p
ass
en
g
er
’
s
s
atis
f
ac
tio
n
s
h
o
ws
th
e
r
o
b
u
s
tn
ess
o
f
T
ab
Ne
t
n
eu
r
al
n
etwo
r
k
in
d
ea
lin
g
with
tab
u
lar
d
ata.
I
ts
co
n
s
is
ten
t
s
u
p
er
io
r
ity
in
ter
m
s
o
f
Acc
u
r
ac
y
,
F1
-
Sco
r
e,
a
n
d
G
-
Me
an
s
co
r
e
is
attr
ib
u
ted
to
its
ar
ch
itectu
r
al
co
m
p
lex
ity
,
atten
tio
n
m
ec
h
an
is
m
s
an
d
n
o
n
-
lin
ea
r
ity
ca
p
t
u
r
in
g
ab
ilit
ies.
T
ab
Net
’
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
3
,
J
u
n
e
20
25
:
3
3
6
2
-
3
3
7
2
3370
r
o
b
u
s
tn
ess
to
h
an
d
le
co
m
p
le
x
,
h
i
g
h
-
d
im
e
n
s
io
n
al
d
atasets
m
ak
e
it
a
c
o
m
p
ellin
g
ch
o
i
ce
f
o
r
a
co
m
p
le
x
class
if
icatio
n
s
u
ch
as
c
lass
if
y
in
g
air
lin
e
p
ass
en
g
er
s
s
atis
f
ac
t
io
n
.
Hav
in
g
a
d
ed
icate
d
d
ee
p
lear
n
in
g
m
o
d
el
f
o
r
tab
u
lar
d
ata
h
elp
ed
i
n
im
p
r
o
v
in
g
th
e
p
er
f
o
r
m
an
c
es
o
f
o
u
r
class
if
icatio
n
task
co
m
p
ar
e
d
to
o
th
e
r
m
ac
h
i
n
e
lear
n
in
g
m
o
d
els
an
d
s
tate
o
f
t
h
e
ar
t
s
tu
d
ies.
I
n
th
is
s
tu
d
y
we
o
n
ly
o
n
o
n
e
d
ataset,
we
p
r
o
p
o
s
e
f
o
r
in
o
u
r
f
u
tu
r
e
wo
r
k
to
ad
d
o
th
er
d
ata
s
ets in
o
r
d
er
to
test
if
o
u
t m
o
d
el
is
d
a
ta
in
d
ep
en
d
en
t
a
n
d
ca
n
d
ea
l w
ith
d
if
f
er
e
n
t k
in
d
o
f
d
ata
s
ets.
As
a
p
er
s
p
ec
tiv
e
ar
is
in
g
f
r
o
m
th
is
s
tu
d
y
,
we
s
u
g
g
est
th
e
d
ev
elo
p
m
e
n
t
o
f
a
m
o
r
e
r
o
b
u
s
t
d
ee
p
lear
n
in
g
m
o
d
el
f
o
r
h
an
d
lin
g
tab
u
lar
d
ata
in
th
e
co
n
tex
t
o
f
s
atis
f
ac
tio
n
class
if
icatio
n
th
at
a
d
d
r
es
s
es
th
e
ch
allen
g
es
ass
o
ciate
d
with
tr
ain
in
g
a
n
d
t
esti
n
g
tim
e
ef
f
icien
cy
to
e
n
s
u
r
e
th
e
cr
e
atio
n
o
f
a
h
ig
h
-
p
er
f
o
r
m
an
ce
m
o
d
el
th
at
o
p
tim
izes
r
eso
u
r
ce
co
n
s
u
m
p
ti
o
n
.
Strik
in
g
a
b
alan
ce
b
etwe
en
m
o
d
el
p
e
r
f
o
r
m
an
ce
a
n
d
co
m
p
u
tatio
n
al
ef
f
icien
cy
will b
e
cr
u
cial
f
o
r
p
r
ac
tical
ap
p
licatio
n
s
an
d
s
ca
l
ab
ilit
y
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
W
e
d
ec
lar
e
o
n
o
u
r
h
o
n
o
r
th
at
t
h
is
s
tu
d
y
was c
ar
r
ied
o
u
t w
ith
o
u
t a
n
y
ex
ter
n
al
f
u
n
d
in
g
.
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
T
h
is
jo
u
r
n
al
u
s
es
th
e
C
o
n
tr
ib
u
to
r
R
o
les
T
ax
o
n
o
m
y
(
C
R
ed
iT)
to
r
ec
o
g
n
ize
in
d
iv
id
u
al
au
th
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
th
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
llab
o
r
atio
n
.
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
R
ac
h
id
Kaid
i
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Hich
am
Om
ar
a
✓
✓
✓
✓
✓
✓
✓
✓
Mo
h
am
ed
L
az
aa
r
✓
✓
✓
✓
Mo
h
am
m
ed
Al
Ach
h
ab
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
Au
th
o
r
s
s
tate
n
o
co
n
f
lict o
f
in
t
er
est.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
ata
t
h
at
s
u
p
p
o
r
t
th
e
f
in
d
in
g
s
o
f
t
h
is
s
tu
d
y
will
b
e
av
a
ilab
le
in
Air
lin
es
cu
s
to
m
er
s
atis
f
ac
tio
n
.
h
ttp
s
:
//w
w
w
.
ka
g
g
le.
co
m/d
a
ta
s
ets/
s
jle
s
h
r
a
c/a
ir
lin
es
-
cu
s
to
me
r
-
s
a
tis
fa
ctio
n
.
RE
F
E
R
E
NC
E
S
[
1
]
“
C
a
r
b
o
n
o
f
f
se
t
t
i
n
g
a
n
d
r
e
d
u
c
t
i
o
n
s
c
h
e
me
f
o
r
i
n
t
e
r
n
a
t
i
o
n
a
l
a
v
i
a
t
i
o
n
(
C
O
R
S
I
A
)
,
”
I
C
AO
.
h
t
t
p
s:
/
/
w
w
w
.
i
c
a
o
.
i
n
t
/
e
n
v
i
r
o
n
m
e
n
t
a
l
-
p
r
o
t
e
c
t
i
o
n
/
C
O
R
S
I
A
/
P
a
g
e
s/
d
e
f
a
u
l
t
.
a
sp
x
(
a
c
c
e
s
se
d
S
e
p
.
0
1
,
2
0
2
4
)
.
[
2
]
S
.
G
ö
ssl
i
n
g
a
n
d
A
.
H
u
m
p
e
,
“
T
h
e
g
l
o
b
a
l
s
c
a
l
e
,
d
i
s
t
r
i
b
u
t
i
o
n
a
n
d
g
r
o
w
t
h
o
f
a
v
i
a
t
i
o
n
:
I
mp
l
i
c
a
t
i
o
n
s
f
o
r
c
l
i
m
a
t
e
c
h
a
n
g
e
,
”
G
l
o
b
a
l
En
v
i
r
o
n
m
e
n
t
a
l
C
h
a
n
g
e
,
v
o
l
.
6
5
,
N
o
v
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
g
l
o
e
n
v
c
h
a
.
2
0
2
0
.
1
0
2
1
9
4
.
[
3
]
X
.
Zh
a
n
g
a
n
d
S
.
M
a
h
a
d
e
v
a
n
,
“
A
i
r
c
r
a
f
t
r
e
-
r
o
u
t
i
n
g
o
p
t
i
m
i
z
a
t
i
o
n
a
n
d
p
e
r
f
o
r
man
c
e
a
s
sessm
e
n
t
u
n
d
e
r
u
n
c
e
r
t
a
i
n
t
y
,
”
D
e
c
i
s
i
o
n
S
u
p
p
o
r
t
S
y
s
t
e
m
s
,
v
o
l
.
9
6
,
p
p
.
6
7
–
8
2
,
A
p
r
.
2
0
1
7
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
d
ss
.
2
0
1
7
.
0
2
.
0
0
5
.
[
4
]
X
.
Zh
a
n
g
a
n
d
S
.
M
a
h
a
d
e
v
a
n
,
“
E
n
sem
b
l
e
mac
h
i
n
e
l
e
a
r
n
i
n
g
m
o
d
e
l
s
f
o
r
a
v
i
a
t
i
o
n
i
n
c
i
d
e
n
t
r
i
sk
p
r
e
d
i
c
t
i
o
n
,
”
D
e
c
i
si
o
n
S
u
p
p
o
r
t
S
y
st
e
m
s
,
v
o
l
.
1
1
6
,
p
p
.
4
8
–
6
3
,
J
a
n
.
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
d
ss.
2
0
1
8
.
1
0
.
0
0
9
.
[
5
]
H
.
Ji
a
n
g
a
n
d
Y
.
Zh
a
n
g
,
“
A
n
a
ssessm
e
n
t
o
f
p
a
ss
e
n
g
e
r
e
x
p
e
r
i
e
n
c
e
a
t
M
e
l
b
o
u
r
n
e
A
i
r
p
o
r
t
,
”
J
o
u
rn
a
l
o
f
Ai
r
T
r
a
n
s
p
o
rt
Ma
n
a
g
e
m
e
n
t
,
v
o
l
.
5
4
,
p
p
.
8
8
–
9
2
,
J
u
l
.
2
0
1
6
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
a
i
r
t
r
a
ma
n
.
2
0
1
6
.
0
4
.
0
0
2
.
[
6
]
M
.
A
r
i
f
,
A
.
G
u
p
t
a
,
a
n
d
A
.
W
i
l
l
i
a
ms,
“
C
u
s
t
o
mer
ser
v
i
c
e
i
n
t
h
e
a
v
i
a
t
i
o
n
i
n
d
u
s
t
r
y
–
a
n
e
x
p
l
o
r
a
t
o
r
y
a
n
a
l
y
si
s
o
f
U
A
E
a
i
r
p
o
r
t
s,
”
J
o
u
r
n
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
.
3
2
,
p
p
.
1
–
7
,
S
e
p
.
2
0
1
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
a
i
r
t
r
a
m
a
n
.
2
0
1
3
.
0
5
.
0
0
1
.
[
7
]
W.
-
H
.
Ts
a
i
,
W
.
H
s
u
,
a
n
d
W
.
-
C
.
C
h
o
u
,
“
A
g
a
p
a
n
a
l
y
s
i
s
mo
d
e
l
f
o
r
i
mp
r
o
v
i
n
g
a
i
r
p
o
r
t
s
e
r
v
i
c
e
q
u
a
l
i
t
y
,
”
T
o
t
a
l
Q
u
a
l
i
t
y
M
a
n
a
g
e
m
e
n
t
&
Bu
si
n
e
ss E
x
c
e
l
l
e
n
c
e
,
v
o
l
.
2
2
,
n
o
.
1
0
,
p
p
.
1
0
2
5
–
1
0
4
0
,
O
c
t
.
2
0
1
1
,
d
o
i
:
1
0
.
1
0
8
0
/
1
4
7
8
3
3
6
3
.
2
0
1
1
.
6
1
1
3
2
6
.
[
8
]
R
.
M
e
r
k
e
r
t
a
n
d
A
.
G
.
A
ssaf,
“
U
s
i
n
g
D
EA
mo
d
e
l
s
t
o
j
o
i
n
t
l
y
e
st
i
ma
t
e
ser
v
i
c
e
q
u
a
l
i
t
y
p
e
r
c
e
p
t
i
o
n
a
n
d
p
r
o
f
i
t
a
b
i
l
i
t
y
–
E
v
i
d
e
n
c
e
f
r
o
m
i
n
t
e
r
n
a
t
i
o
n
a
l
a
i
r
p
o
r
t
s,
”
T
ra
n
s
p
o
r
t
a
t
i
o
n
R
e
se
a
rc
h
P
a
rt
A:
P
o
l
i
c
y
a
n
d
Pr
a
c
t
i
c
e
,
v
o
l
.
7
5
,
p
p
.
4
2
–
5
0
,
M
a
y
2
0
1
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
t
r
a
.
2
0
1
5
.
0
3
.
0
0
8
.
[
9
]
E.
R
u
i
z
,
W
.
F
.
Y
u
s
h
i
mi
t
o
,
L.
A
b
u
r
t
o
,
a
n
d
R
.
d
e
l
a
C
r
u
z
,
“
P
r
e
d
i
c
t
i
n
g
p
a
sse
n
g
e
r
sa
t
i
sf
a
c
t
i
o
n
i
n
p
u
b
l
i
c
t
r
a
n
s
p
o
r
t
a
t
i
o
n
u
s
i
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
m
o
d
e
l
s
,
”
T
r
a
n
sp
o
r
t
a
t
i
o
n
R
e
s
e
a
r
c
h
Pa
rt
A:
P
o
l
i
c
y
a
n
d
Pr
a
c
t
i
c
e
,
v
o
l
.
1
8
1
,
M
a
r
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
t
r
a
.
2
0
2
4
.
1
0
3
9
9
5
.
[
1
0
]
T.
N
o
v
i
a
n
t
o
r
o
a
n
d
J.
-
P
.
H
u
a
n
g
,
“
I
n
v
e
st
i
g
a
t
i
n
g
a
i
r
l
i
n
e
p
a
ss
e
n
g
e
r
sa
t
i
sf
a
c
t
i
o
n
:
D
a
t
a
mi
n
i
n
g
m
e
t
h
o
d
,
”
Re
s
e
a
r
c
h
i
n
T
ra
n
s
p
o
r
t
a
t
i
o
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
E
n
h
a
n
cin
g
ta
b
u
la
r
d
a
ta
a
n
a
ly
s
is
fo
r
cla
s
s
ifica
tio
n
o
f a
ir
lin
e
p
a
s
s
en
g
er sa
tis
fa
ctio
n
…
(
R
a
c
h
id
K
a
id
i
)
3371
Bu
si
n
e
ss &
M
a
n
a
g
e
m
e
n
t
,
v
o
l
.
4
3
,
Ju
n
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
r
t
b
m
.
2
0
2
1
.
1
0
0
7
2
6
.
[
1
1
]
B
.
H
.
H
a
y
a
d
i
,
J.
-
M
.
K
i
m,
K
.
H
u
l
l
i
y
a
h
,
a
n
d
H
.
T.
S
u
k
m
a
n
a
,
“
P
r
e
d
i
c
t
i
n
g
a
i
r
l
i
n
e
p
a
ss
e
n
g
e
r
s
a
t
i
s
f
a
c
t
i
o
n
w
i
t
h
c
l
a
s
s
i
f
i
c
a
t
i
o
n
a
l
g
o
r
i
t
h
m
s,”
I
J
I
I
S
:
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
I
n
f
o
r
m
a
t
i
c
s
a
n
d
I
n
f
o
r
m
a
t
i
o
n
S
y
st
e
m
s
,
v
o
l
.
4
,
n
o
.
1
,
p
p
.
8
2
–
9
4
,
M
a
r
.
2
0
2
1
,
d
o
i
:
1
0
.
4
7
7
3
8
/
i
j
i
i
s
.
v
4
i
1
.
8
0
.
[
1
2
]
A
.
N
u
r
d
i
n
a
a
n
d
A
.
B
.
I
.
P
u
sp
i
t
a
,
“
N
a
ï
v
e
B
a
y
e
s
a
n
d
K
N
N
f
o
r
a
i
r
l
i
n
e
p
a
s
se
n
g
e
r
s
a
t
i
sf
a
c
t
i
o
n
c
l
a
ssi
f
i
c
a
t
i
o
n
:
C
o
m
p
a
r
a
t
i
v
e
a
n
a
l
y
s
i
s
,
”
J
o
u
rn
a
l
o
f
I
n
f
o
rm
a
t
i
o
n
S
y
s
t
e
m
Ex
p
l
o
r
a
t
i
o
n
a
n
d
Re
s
e
a
r
c
h
,
v
o
l
.
1
,
n
o
.
2
,
J
u
l
.
2
0
2
3
,
d
o
i
:
1
0
.
5
2
4
6
5
/
j
o
i
ser
.
v
1
i
2
.
1
6
7
.
[
1
3
]
X
.
Ji
a
n
g
,
Y
.
Z
h
a
n
g
,
Y
.
Li
,
a
n
d
B
.
Z
h
a
n
g
,
“
F
o
r
e
c
a
s
t
a
n
d
a
n
a
l
y
s
i
s
o
f
a
i
r
c
r
a
f
t
p
a
sse
n
g
e
r
sa
t
i
sf
a
c
t
i
o
n
b
a
s
e
d
o
n
R
F
-
R
F
E
-
LR
m
o
d
e
l
,
”
S
c
i
e
n
t
i
f
i
c
Re
p
o
r
t
s
,
v
o
l
.
1
2
,
n
o
.
1
,
J
u
l
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
3
8
/
s4
1
5
9
8
-
0
2
2
-
1
4
5
6
6
-
3.
[
1
4
]
M
.
S
.
H
o
m
a
i
d
a
n
d
I
.
M
o
u
l
i
t
sas
,
“
M
e
a
su
r
i
n
g
a
i
r
p
o
r
t
s
e
r
v
i
c
e
q
u
a
l
i
t
y
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,
”
i
n
2
0
2
2
T
h
e
6
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
A
d
v
a
n
c
e
s i
n
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
O
c
t
.
2
0
2
2
,
p
p
.
8
–
1
4
.
d
o
i
:
1
0
.
1
1
4
5
/
3
5
7
1
5
6
0
.
3
5
7
1
5
6
2
.
[
1
5
]
S
.
K
u
m
a
r
a
n
d
M
.
Zy
mb
l
e
r
,
“
A
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
t
o
a
n
a
l
y
z
e
c
u
s
t
o
mer
s
a
t
i
sf
a
c
t
i
o
n
f
r
o
m
a
i
r
l
i
n
e
t
w
e
e
t
s,
”
J
o
u
rn
a
l
o
f
Bi
g
D
a
t
a
,
v
o
l
.
6
,
n
o
.
1
,
D
e
c
.
2
0
1
9
,
d
o
i
:
1
0
.
1
1
8
6
/
s4
0
5
3
7
-
019
-
0
2
2
4
-
1.
[
1
6
]
S
.
D
e
b
,
M
.
A
l
i
A
h
m
e
d
,
a
n
d
D
.
D
a
s,
“
S
e
r
v
i
c
e
q
u
a
l
i
t
y
e
st
i
ma
t
i
o
n
a
n
d
i
mp
r
o
v
e
men
t
p
l
a
n
o
f
b
u
s
S
e
r
v
i
c
e
:
A
p
e
r
c
e
p
t
i
o
n
a
n
d
e
x
p
e
c
t
a
t
i
o
n
b
a
s
e
d
a
n
a
l
y
s
i
s,”
C
a
se
S
t
u
d
i
e
s
o
n
T
r
a
n
sp
o
r
t
Po
l
i
c
y
,
v
o
l
.
1
0
,
n
o
.
3
,
p
p
.
1
7
7
5
–
1
7
8
9
,
S
e
p
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
st
p
.
2
0
2
2
.
0
7
.
0
0
8
.
[
1
7
]
L.
D
e
l
l
’
O
l
i
o
,
A
.
I
b
e
a
s,
a
n
d
P
.
C
e
c
i
n
,
“
Th
e
q
u
a
l
i
t
y
o
f
serv
i
c
e
d
e
s
i
r
e
d
b
y
p
u
b
l
i
c
t
r
a
n
sp
o
r
t
u
s
e
r
s,”
T
r
a
n
sp
o
r
t
P
o
l
i
c
y
,
v
o
l
.
1
8
,
n
o
.
1
,
p
p
.
2
1
7
–
2
2
7
,
J
a
n
.
2
0
1
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
t
r
a
n
p
o
l
.
2
0
1
0
.
0
8
.
0
0
5
.
[
1
8
]
C
.
Z
h
a
n
g
,
Y
.
Li
u
,
W
.
L
u
,
a
n
d
G
.
X
i
a
o
,
“
E
v
a
l
u
a
t
i
n
g
p
a
ss
e
n
g
e
r
s
a
t
i
sf
a
c
t
i
o
n
i
n
d
e
x
b
a
se
d
o
n
P
LS
-
S
E
M
m
o
d
e
l
:
E
v
i
d
e
n
c
e
f
r
o
m
C
h
i
n
e
se
p
u
b
l
i
c
t
r
a
n
sp
o
r
t
s
e
r
v
i
c
e
,
”
T
r
a
n
s
p
o
rt
a
t
i
o
n
R
e
se
a
rc
h
P
a
rt
A:
P
o
l
i
c
y
a
n
d
Pra
c
t
i
c
e
,
v
o
l
.
1
2
0
,
p
p
.
1
4
9
–
1
6
4
,
F
e
b
.
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
t
r
a
.
2
0
1
8
.
1
2
.
0
1
3
.
[
1
9
]
S.
-
H
.
P
a
r
k
,
M
.
-
Y
.
K
i
m
,
Y
.
-
J.
K
i
m
,
a
n
d
Y
.
-
H
.
P
a
r
k
,
“
A
d
e
e
p
l
e
a
r
n
i
n
g
sp
p
r
o
a
c
h
t
o
a
n
a
l
y
z
e
s
i
r
l
i
n
e
c
u
st
o
m
e
r
p
r
o
p
e
n
s
i
t
i
e
s:
T
h
e
c
a
s
e
o
f
S
o
u
t
h
K
o
r
e
a
,
”
A
p
p
l
i
e
d
S
c
i
e
n
c
e
s
,
v
o
l
.
1
2
,
n
o
.
4
,
F
e
b
.
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
2
0
4
1
9
1
6
.
[
2
0
]
H
.
B
.
S
a
n
k
a
r
a
n
a
r
a
y
a
n
a
n
,
B
.
V
V
i
sh
w
a
n
a
t
h
,
a
n
d
V
.
R
a
t
h
o
d
,
“
A
n
e
x
p
l
o
r
a
t
o
r
y
a
n
a
l
y
s
i
s f
o
r
p
r
e
d
i
c
t
i
n
g
p
a
ss
e
n
g
e
r
sa
t
i
sf
a
c
t
i
o
n
a
t
g
l
o
b
a
l
h
u
b
a
i
r
p
o
r
t
s u
si
n
g
l
o
g
i
s
t
i
c
m
o
d
e
l
t
r
e
e
s,”
i
n
2
0
1
6
S
e
c
o
n
d
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
Re
se
a
r
c
h
i
n
C
o
m
p
u
t
a
t
i
o
n
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
N
e
t
w
o
rk
s (I
C
R
C
I
C
N
)
,
S
e
p
.
2
0
1
6
,
p
p
.
2
8
5
–
2
9
0
.
d
o
i
:
1
0
.
1
1
0
9
/
I
C
R
C
I
C
N
.
2
0
1
6
.
7
8
1
3
6
7
2
.
[
2
1
]
C
.
C
.
E
.
v
a
n
G
e
e
st
,
Y
.
W
a
n
Y
i
t
,
Z.
T
.
G
o
u
l
i
e
v
,
a
n
d
K
.
Q
u
i
l
l
e
,
“
P
r
e
d
i
c
t
i
v
e
mo
d
e
l
s
w
i
t
h
X
A
I
:
A
c
o
mp
a
r
a
t
i
v
e
s
t
u
d
y
o
f
e
n
h
a
n
c
i
n
g
a
i
r
l
i
n
e
c
u
st
o
mer
s
a
t
i
sf
a
c
t
i
o
n
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
2
0
2
3
C
o
n
f
e
r
e
n
c
e
o
n
H
u
m
a
n
C
e
n
t
e
r
e
d
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
:
Ed
u
c
a
t
i
o
n
a
n
d
Pra
c
t
i
c
e
,
D
e
c
.
2
0
2
3
,
p
p
.
3
6
–
4
1
.
d
o
i
:
1
0
.
1
1
4
5
/
3
6
3
3
0
8
3
.
3
6
3
3
1
8
9
.
[
2
2
]
S
.
Ja
n
a
,
“
A
i
r
l
i
n
e
s
c
u
s
t
o
m
e
r
sa
t
i
sf
a
c
t
i
o
n
,
”
K
a
g
g
l
e
.
h
t
t
p
s:
/
/
w
w
w
.
k
a
g
g
l
e
.
c
o
m/
d
a
t
a
s
e
t
s
/
sj
l
e
s
h
r
a
c
/
a
i
r
l
i
n
e
s
-
c
u
st
o
mer
-
sat
i
sf
a
c
t
i
o
n
(
a
c
c
e
s
se
d
D
e
c
.
0
2
,
2
0
2
4
)
.
[
2
3
]
S
.
Ö
.
A
r
i
k
a
n
d
T
.
P
f
i
st
e
r
,
“
Ta
b
N
e
t
:
A
t
t
e
n
t
i
v
e
i
n
t
e
r
p
r
e
t
a
b
l
e
t
a
b
u
l
a
r
l
e
a
r
n
i
n
g
,
”
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
AAAI
C
o
n
f
e
ren
c
e
o
n
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
3
5
,
n
o
.
8
,
p
p
.
6
6
7
9
–
6
6
8
7
,
M
a
y
2
0
2
1
,
d
o
i
:
1
0
.
1
6
0
9
/
a
a
a
i
.
v
3
5
i
8
.
1
6
8
2
6
.
[
2
4
]
Y
.
N
.
D
a
u
p
h
i
n
,
A
.
F
a
n
,
M
.
A
u
l
i
,
a
n
d
D
.
G
r
a
n
g
i
e
r
,
“
La
n
g
u
a
g
e
m
o
d
e
l
i
n
g
w
i
t
h
g
a
t
e
d
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
t
w
o
r
k
s,
”
Pr
e
p
r
.
a
rXi
v
.
1
6
1
2
.
0
8
0
8
3
,
D
e
c
.
2
0
1
6
.
[
2
5
]
A
.
F
.
T.
M
a
r
t
i
n
s
a
n
d
R
.
F
.
A
st
u
d
i
l
l
o
,
“
F
r
o
m
s
o
f
t
ma
x
t
o
s
p
a
r
s
e
ma
x
:
A
s
p
a
r
se
m
o
d
e
l
o
f
a
t
t
e
n
t
i
o
n
a
n
d
m
u
l
t
i
-
l
a
b
e
l
c
l
a
ss
i
f
i
c
a
t
i
o
n
,
”
Pre
p
r
.
a
rX
i
v
.
1
6
0
2
.
0
2
0
6
8
,
F
e
b
.
2
0
1
6
.
[
2
6
]
Y
.
R
e
l
i
g
i
a
a
n
d
D
.
M
a
u
l
a
n
a
,
“
G
e
n
e
t
i
c
a
l
g
o
r
i
t
h
m
o
p
t
i
mi
z
a
t
i
o
n
o
n
N
a
v
e
B
a
y
e
s
f
o
r
a
i
r
l
i
n
e
c
u
st
o
m
e
r
sat
i
sf
a
c
t
i
o
n
c
l
a
ss
i
f
i
c
a
t
i
o
n
,
”
J
I
S
A(
J
u
r
n
a
l
I
n
f
o
rm
a
t
i
k
a
d
a
n
S
a
i
n
s)
,
v
o
l
.
4
,
n
o
.
2
,
p
p
.
1
2
1
–
1
2
6
,
D
e
c
.
2
0
2
1
,
d
o
i
:
1
0
.
3
1
3
2
6
/
j
i
sa
.
v
4
i
2
.
9
2
5
.
[
2
7
]
A
.
N
u
r
d
i
n
a
a
n
d
A
.
B
.
I
.
P
u
sp
i
t
a
,
“
N
a
i
v
e
B
a
y
e
s
a
n
d
K
N
N
f
o
r
a
i
r
l
i
n
e
p
a
ss
e
n
g
e
r
sat
i
sf
a
c
t
i
o
n
c
l
a
ss
i
f
i
c
a
t
i
o
n
:
c
o
m
p
a
r
a
t
i
v
e
a
n
a
l
y
s
i
s
,
”
J
o
u
rn
a
l
o
f
I
n
f
o
rm
a
t
i
o
n
S
y
s
t
e
m
Ex
p
l
o
r
a
t
i
o
n
a
n
d
Re
s
e
a
r
c
h
,
v
o
l
.
1
,
n
o
.
2
,
p
p
.
5
2
7
–
5
3
3
,
J
u
l
.
2
0
2
3
,
d
o
i
:
1
0
.
5
2
4
6
5
/
j
o
i
ser.v
1
i
2
.
1
6
7
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Ra
c
h
id
K
a
i
d
i
is
c
u
rre
n
tl
y
a
d
o
c
to
ra
l
stu
d
e
n
t
a
t
th
e
F
a
c
u
lt
y
o
f
S
c
i
e
n
c
e
s
o
f
Teto
u
a
n
,
Ab
d
e
lma
lek
Essa
â
d
i
Un
iv
e
rsit
y
,
M
o
ro
c
c
o
.
He
re
c
e
iv
e
d
h
is
m
a
ste
r'
s
d
e
g
re
e
fro
m
M
o
h
a
m
m
e
d
VI
In
tern
a
ti
o
n
a
l
Ac
a
d
e
m
y
o
f
Ci
v
il
Av
iati
o
n
Ca
sa
b
lan
c
a
M
o
ro
c
c
o
.
His
re
se
a
rc
h
fo
c
u
se
s
o
n
a
rti
ficia
l
i
n
telli
g
e
n
c
e
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
k
a
id
irac
h
i
d
1
9
8
2
@g
m
a
il
.
c
o
m
.
H
icha
m
O
m
a
r
a
is
c
u
rre
n
tl
y
a
P
ro
fe
ss
o
r
o
f
Co
m
p
u
ter
S
c
ien
c
e
i
n
th
e
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
t
th
e
P
o
ly
d
isc
ip
li
n
a
ry
F
a
c
u
lt
y
o
f
Taz
a
,
S
id
i
M
o
h
a
m
e
d
Be
n
Ab
d
e
ll
a
h
Un
iv
e
rsity
,
M
o
ro
c
c
o
.
He
re
c
e
iv
e
d
h
is
P
h
D
fro
m
t
h
e
F
a
c
u
l
ty
o
f
S
c
i
e
n
c
e
a
t
Ab
d
e
lma
lek
Essa
â
d
i
Un
iv
e
rsity
,
M
o
r
o
c
c
o
.
He
h
a
s
p
a
rt
icip
a
ted
in
n
u
m
e
ro
u
s n
a
ti
o
n
a
l
a
n
d
in
tern
a
ti
o
n
a
l
sc
ien
t
ifi
c
a
n
d
o
rg
a
n
iza
ti
o
n
a
l
c
o
m
m
it
tee
s.
His
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
a
rt
ifi
c
ial
in
telli
g
e
n
c
e
,
ima
g
e
p
ro
c
e
ss
in
g
,
b
i
g
d
a
ta,
a
n
d
o
t
h
e
r
a
r
e
a
s.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
h
.
o
m
a
ra
@u
a
e
.
a
c
.
m
a
.
Evaluation Warning : The document was created with Spire.PDF for Python.