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
.
5
,
Octo
b
er
20
25
,
p
p
.
4
8
9
9
~
4
9
0
6
I
SS
N:
2088
-
8
7
0
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijece.
v
15
i
5
.
pp
4
8
9
9
-
4
9
0
6
4899
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
O
ptimi
zing
vehicl
e select
io
n
in
sup
ply
chain ma
na
g
ement w
ith
da
ta
-
driv
en st
ra
t
eg
ies
I
m
a
ne
Z
er
o
ua
l,
J
a
ber
E
l Bo
uh
di
di
S
I
G
L
La
b
o
r
a
t
o
r
y
,
EN
S
A
TE,
A
b
d
e
l
m
a
l
e
k
Essa
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
Feb
2
,
2
0
2
5
R
ev
is
ed
J
u
n
2
0
,
2
0
2
5
Acc
ep
ted
J
u
n
3
0
,
2
0
2
5
Lo
g
isti
c
s
h
a
s
u
n
d
e
rg
o
n
e
sig
n
ifi
c
a
n
t
tran
sfo
rm
a
ti
o
n
to
a
d
d
re
ss
th
e
c
o
m
p
lex
e
c
o
n
o
m
ic,
so
c
ial,
a
n
d
e
n
v
iro
n
m
e
n
tal
c
h
a
ll
e
n
g
e
s
o
f
t
h
e
m
o
d
e
rn
e
ra
.
To
m
a
in
tain
c
o
m
p
e
ti
ti
v
e
n
e
ss
,
lo
g
isti
c
s
p
ro
v
i
d
e
rs
h
a
v
e
b
e
e
n
c
o
m
p
e
ll
e
d
to
o
p
ti
m
ize
o
p
e
ra
ti
o
n
s,
m
e
e
t
in
c
re
a
sin
g
c
u
st
o
m
e
r
e
x
p
e
c
tatio
n
s,
a
n
d
imp
r
o
v
e
sa
ti
sfa
c
ti
o
n
.
Cri
ti
c
a
l
issu
e
s
imp
a
c
ti
n
g
lo
g
isti
c
s
p
e
rfo
rm
a
n
c
e
i
n
c
lu
d
e
traffic
c
o
n
g
e
sti
o
n
,
in
fra
str
u
c
tu
re
li
m
it
a
ti
o
n
s,
r
isin
g
d
e
m
a
n
d
,
a
n
d
t
h
e
c
o
m
p
lex
it
ies
o
f
v
e
h
icle
sc
h
e
d
u
li
n
g
,
c
o
o
rd
i
n
a
ti
o
n
,
a
n
d
m
a
n
a
g
e
m
e
n
t.
T
h
e
se
c
h
a
ll
e
n
g
e
s
fre
q
u
e
n
tl
y
d
isr
u
p
t
d
e
li
v
e
ry
o
p
e
r
a
ti
o
n
s,
u
n
d
e
rm
in
in
g
e
fficie
n
c
y
a
n
d
o
v
e
ra
ll
sy
ste
m
p
e
rfo
rm
a
n
c
e
.
Th
is
p
a
p
e
r
p
ro
p
o
se
s
th
e
a
p
p
l
ica
ti
o
n
o
f
th
re
e
m
a
c
h
in
e
lea
rn
in
g
m
o
d
e
ls
a
ime
d
a
t
o
p
ti
m
izin
g
d
e
li
v
e
r
y
p
ro
c
e
ss
e
s,
with
a
fo
c
u
s
o
n
imp
ro
v
i
n
g
v
e
h
icle
a
ss
ig
n
m
e
n
t
f
o
r
o
r
d
e
r
d
e
li
v
e
ries
.
By
lev
e
ra
g
in
g
t
h
e
se
m
o
d
e
ls,
lo
g
isti
c
s
p
ro
v
i
d
e
rs
c
a
n
e
n
h
a
n
c
e
d
e
c
isio
n
-
m
a
k
i
n
g
a
n
d
o
p
e
ra
ti
o
n
a
l
e
fficie
n
c
y
.
Th
e
stu
d
y
d
e
fin
e
s
th
e
c
o
re
p
ro
b
lem
a
n
d
e
v
a
l
u
a
tes
se
v
e
ra
l
m
a
c
h
in
e
lea
rn
in
g
a
p
p
r
o
a
c
h
e
s to
b
o
lster l
o
g
isti
c
s d
e
li
v
e
ry
s
y
ste
m
s.
K
ey
w
o
r
d
s
:
Ar
tific
ial
in
tellig
en
ce
C
ity
lo
g
is
tics
Dec
is
io
n
tr
ee
s
L
o
g
is
tic
r
eg
r
ess
io
n
Neu
r
al
n
etwo
r
k
s
Ur
b
an
lo
g
is
tics
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
:
I
m
an
e
Z
er
o
u
al
SIG
L
L
ab
o
r
ato
r
y
,
E
NSAT
E
,
Ab
d
elm
alek
E
s
s
ad
i U
n
iv
er
s
ity
T
eto
u
an
,
M
o
r
o
cc
o
E
m
ail: im
an
e.
ze
r
o
u
al
1
@
etu
.
u
ae
.
ac
.
m
a
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
s
u
p
p
l
y
ch
ai
n
in
d
u
s
tr
y
e
n
co
u
n
ter
s
n
u
m
e
r
o
u
s
c
h
allen
g
es
[
1
]
,
with
lo
g
is
tics
b
ein
g
a
ce
n
tr
al
co
n
ce
r
n
,
esp
ec
ially
f
o
r
d
is
tr
ib
u
to
r
s
an
d
tr
an
s
p
o
r
te
r
s
.
Alth
o
u
g
h
t
h
e
lo
g
is
tics
s
ec
to
r
h
as
ex
p
er
ien
ce
d
r
ap
id
g
r
o
wth
,
it
h
as
also
ex
ac
er
b
ated
s
o
cial
an
d
e
n
v
ir
o
n
m
en
tal
is
s
u
es,
in
clu
d
in
g
s
ev
er
e
tr
af
f
ic
co
n
g
esti
o
n
an
d
in
cr
ea
s
ed
p
o
llu
tio
n
in
u
r
b
a
n
ar
ea
s
[
2
]
.
Ad
d
r
ess
in
g
th
ese
ch
allen
g
es
n
ec
ess
itates
co
lla
b
o
r
atio
n
am
o
n
g
all
s
tak
eh
o
ld
er
s
an
d
th
e
im
p
lem
e
n
tatio
n
o
f
ef
f
ec
tiv
e
s
tr
ateg
ies
to
m
itig
ate
th
eir
im
p
ac
ts
.
T
h
is
p
ap
er
p
r
o
p
o
s
es
an
in
n
o
v
ativ
e
s
o
lu
tio
n
th
at
lev
er
ag
es
s
cien
tific
r
esear
ch
an
d
ar
tific
ial
in
tellig
en
ce
tech
n
iq
u
e
s
to
o
p
tim
ize
u
r
b
an
f
r
eig
h
t
tr
an
s
p
o
r
tatio
n
p
la
n
n
i
n
g
an
d
in
f
r
astru
ctu
r
e.
Sp
ec
i
f
ically
,
it
in
tr
o
d
u
ce
s
s
ev
er
al
m
ac
h
in
es
lear
n
in
g
m
o
d
els,
in
clu
d
in
g
m
u
ltin
o
m
ia
l
lo
g
is
tic
r
eg
r
ess
io
n
,
to
p
r
ed
i
ct
th
e
m
o
s
t
s
u
itab
le
v
eh
icle
f
o
r
o
r
d
e
r
d
eliv
er
ies.
Ad
d
itio
n
ally
,
th
e
s
tu
d
y
co
m
p
a
r
es
two
o
th
er
m
o
d
els
to
id
en
tify
th
e
b
est
ap
p
r
o
ac
h
f
o
r
th
e
s
ce
n
ar
io
.
T
h
e
p
a
p
er
em
p
h
asizes
th
e
s
o
cial
an
d
en
v
ir
o
n
m
en
tal
cr
iticis
m
s
u
r
r
o
u
n
d
i
n
g
d
eliv
er
y
tr
an
s
p
o
r
t
[
3
]
,
o
f
te
n
d
u
e
to
in
e
f
f
icien
t
r
o
u
tes
an
d
lac
k
o
f
ad
ap
ta
b
ilit
y
in
p
la
n
n
in
g
.
B
y
f
o
c
u
s
in
g
o
n
s
elec
tin
g
th
e
ap
p
r
o
p
r
iate
v
e
h
icle
f
o
r
d
eliv
er
ies,
th
is
r
esear
ch
aim
s
to
r
ed
u
ce
f
in
an
cial
b
u
r
d
en
s
an
d
en
v
ir
o
n
m
en
tal
im
p
ac
ts
,
th
er
eb
y
im
p
r
o
v
in
g
th
e
e
f
f
icien
cy
an
d
p
r
ec
is
io
n
o
f
u
r
b
a
n
f
r
eig
h
t
o
p
er
atio
n
s
.
2.
M
E
T
H
O
D
2
.
1
.
Arc
hite
ct
ura
l o
v
er
v
iew
o
f
t
he
pro
po
s
ed
s
o
lutio
n
T
h
e
p
r
o
p
o
s
ed
ar
ch
itectu
r
e,
illu
s
tr
ated
in
Fig
u
r
e
1
,
o
u
tlin
es
s
ev
er
al
k
ey
s
tag
es
f
o
r
ev
alu
atin
g
m
ac
h
in
e
lear
n
in
g
m
o
d
els
in
lo
g
is
tics
d
eliv
er
y
s
y
s
tem
s
.
T
h
ese
s
tag
es
ar
e
d
esig
n
ed
to
en
s
u
r
e
ef
f
ec
ti
v
e
d
ata
p
r
ep
ar
atio
n
,
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
.
5
,
Octo
b
e
r
20
25
:
4
8
9
9
-
4
9
0
6
4900
m
o
d
el
tr
ai
n
in
g
,
ev
alu
atio
n
,
a
n
d
d
e
p
lo
y
m
e
n
t.
T
h
e
ar
c
h
itectu
r
e
r
ep
r
esen
ts
a
s
tr
u
ctu
r
ed
p
ip
elin
e
th
at
f
a
cilitates
th
e
ex
tr
ac
tio
n
,
p
r
o
ce
s
s
in
g
,
a
n
d
an
aly
s
is
o
f
h
is
to
r
ical
d
ata
to
o
p
tim
ize
d
ec
is
io
n
-
m
a
k
in
g
i
n
d
eliv
er
y
o
p
er
atio
n
s
.
L
et’
s
b
r
ea
k
d
o
wn
ea
ch
s
tep
in
d
etail:
Fig
u
r
e
1
.
Ma
ch
i
n
e
lear
n
in
g
-
b
a
s
ed
ar
ch
itectu
r
e
f
o
r
o
p
tim
izin
g
lo
g
is
tics
d
eliv
er
y
s
y
s
tem
s
a.
Data
ex
tr
ac
tio
n
f
r
o
m
h
is
to
r
ic
al
d
ata
:
T
h
e
f
ir
s
t
s
tep
in
v
o
lv
es
ex
tr
ac
tin
g
r
elev
an
t
d
ata
f
r
o
m
th
e
h
is
to
r
ical
lo
g
is
tics
r
ec
o
r
d
s
d
ata
b
ase.
T
h
is
d
ata
s
er
v
es
as
th
e
f
o
u
n
d
ati
o
n
f
o
r
m
o
d
el
tr
ain
s
,
in
cl
u
d
in
g
d
eliv
er
y
tim
es,
v
eh
icle
p
er
f
o
r
m
an
ce
,
o
r
d
er
ch
ar
ac
ter
is
tics
,
an
d
o
th
er
f
ac
t
o
r
s
th
at
in
f
lu
en
ce
lo
g
is
tics
o
p
er
atio
n
s
.
b.
Data
s
et
p
r
ep
r
o
ce
s
s
in
g
:
On
ce
th
e
d
ata
is
co
llected
,
it
is
p
r
o
ce
s
s
ed
to
en
s
u
r
e
its
q
u
ality
a
n
d
co
n
s
is
ten
cy
.
T
h
is
s
tag
e
in
v
o
lv
es:
−
H
a
n
d
l
i
n
g
m
i
s
s
i
n
g
d
a
t
a
:
M
is
s
i
n
g
o
r
i
n
c
o
m
p
l
e
t
e
e
n
t
r
i
es
a
r
e
a
d
d
r
e
s
s
e
d
t
h
r
o
u
g
h
i
m
p
u
t
a
t
i
o
n
o
r
r
e
m
o
v
a
l
[
4
]
.
−
R
em
o
v
in
g
d
u
p
licates: Du
p
licate
r
ec
o
r
d
s
ar
e
elim
in
ate
d
[
5
]
t
o
p
r
ev
e
n
t b
ias an
d
en
s
u
r
e
d
ata
in
teg
r
ity
.
−
Data
t
r
an
s
f
o
r
m
atio
n
:
Su
ch
as
n
o
r
m
aliza
tio
n
a
n
d
en
c
o
d
in
g
[
6
]
is
ap
p
lied
to
m
a
k
e
th
e
d
ata
s
u
itab
le
f
o
r
m
ac
h
in
e
lear
n
in
g
m
o
d
els
.
c.
Data
s
et
s
p
litt
in
g
:
T
o
ev
alu
ate
m
o
d
el
p
er
f
o
r
m
an
ce
ef
f
ec
tiv
el
y
,
th
e
d
ataset
is
s
p
lit
in
to
two
p
ar
ts
:
a
tr
ain
in
g
s
et
an
d
a
test
s
et.
T
h
e
tr
ain
in
g
s
et
is
u
s
ed
to
tr
ain
th
e
m
ac
h
i
n
e
lear
n
in
g
m
o
d
els,
wh
ile
th
e
test
s
et
i
s
k
ep
t
s
ep
ar
ate
f
o
r
e
v
alu
atin
g
th
e
f
in
al
m
o
d
el
p
er
f
o
r
m
a
n
ce
.
d.
Featu
r
e
s
elec
tio
n
:
Featu
r
e
s
elec
tio
n
is
p
er
f
o
r
m
ed
to
i
d
en
tify
th
e
m
o
s
t
r
elev
an
t
f
ea
t
u
r
es
f
o
r
m
o
d
el
tr
ain
in
g
.
T
h
is
s
tep
is
ap
p
lied
ex
clu
s
iv
ely
to
th
e
m
u
ltin
o
m
ial
lo
g
is
tic
r
eg
r
ess
io
n
m
o
d
el,
u
s
in
g
c
o
r
r
elatio
n
-
b
ased
f
ea
tu
r
e
s
elec
tio
n
[
7
]
to
r
ed
u
ce
d
im
en
s
io
n
ality
b
y
s
elec
tin
g
f
ea
tu
r
es
th
at
ar
e
m
o
s
t
s
tr
o
n
g
ly
co
r
r
elate
d
with
th
e
tar
g
et
v
ar
ia
b
le
(
e.
g
.
,
d
eliv
e
r
y
d
u
r
atio
n
,
m
ater
ial
s
h
ip
p
ed
)
.
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
Op
timiz
in
g
ve
h
icle
s
elec
tio
n
i
n
s
u
p
p
ly
ch
a
in
ma
n
a
g
eme
n
t w
ith
…
(
I
ma
n
e
Zer
o
u
a
l
)
4901
e.
Mo
d
elin
g
:
T
h
is
s
tag
e
in
v
o
lv
es
tr
ain
in
g
th
r
ee
d
if
f
er
e
n
t
m
ac
h
in
e
lear
n
in
g
m
o
d
els
to
ev
alu
ate
th
eir
p
er
f
o
r
m
an
ce
in
p
r
ed
ictin
g
o
p
ti
m
al
v
eh
icle
ass
ig
n
m
en
ts
f
o
r
o
r
d
er
d
eliv
er
ies.
T
h
e
m
o
d
els u
s
ed
ar
e:
−
Mu
ltin
o
m
ial
lo
g
is
tic
r
eg
r
ess
io
n
:
A
s
tatis
tical
m
o
d
el
th
at
p
r
ed
icts
th
e
p
r
o
b
ab
ilit
y
o
f
a
v
eh
icle
b
ein
g
s
u
itab
le
f
o
r
an
o
r
d
e
r
b
ased
o
n
m
u
ltip
le
f
ea
tu
r
es
[
8
]
.
−
Dec
is
io
n
tr
ee
:
A
tr
ee
-
b
ased
alg
o
r
ith
m
th
at
s
p
lits
d
ata
in
to
b
r
an
ch
es
[
9
]
,
p
r
ed
ictin
g
t
h
e
b
est
v
eh
icle
f
o
r
d
eliv
er
y
b
ased
o
n
d
ec
is
io
n
r
u
l
es.
−
Neu
r
al
n
etwo
r
k
p
er
ce
p
tr
o
n
:
A
d
ee
p
lear
n
in
g
m
o
d
el
th
at
u
s
es
in
ter
co
n
n
ec
ted
lay
e
r
s
o
f
n
eu
r
o
n
s
to
lear
n
co
m
p
lex
p
atter
n
s
in
th
e
d
ata
[
1
0
]
.
f.
T
esti
n
g
an
d
e
v
alu
atin
g
:
Af
ter
tr
ain
in
g
th
e
m
o
d
els,
th
eir
p
r
e
d
ictio
n
s
ar
e
test
ed
ag
ai
n
s
t
th
e
a
ctu
al
o
u
tco
m
es
(
tr
u
e
lab
els)
f
r
o
m
th
e
test
s
et.
T
h
e
ev
alu
atio
n
p
r
o
ce
s
s
in
v
o
lv
es:
−
C
o
m
p
ar
is
o
n
o
f
p
r
ed
ictio
n
s
with
tr
u
e
lab
els
:
Ass
ess
in
g
h
o
w
well
th
e
m
o
d
els’
p
r
e
d
ictio
n
s
a
lig
n
with
th
e
ac
tu
al
d
ata.
−
E
v
alu
atin
g
m
etr
ics:
C
o
m
m
o
n
p
er
f
o
r
m
an
ce
m
etr
ics,
s
u
ch
as
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
-
s
co
r
e,
ar
e
u
s
ed
to
ass
ess
m
o
d
el
ef
f
ec
tiv
en
ess
.
−
C
r
o
s
s
-
v
alid
atio
n
:
T
o
e
n
s
u
r
e
m
o
d
el
r
eliab
ilit
y
,
cr
o
s
s
-
v
alid
ati
o
n
is
p
e
r
f
o
r
m
ed
t
o
p
r
ev
en
t
o
v
er
f
itti
n
g
[
1
1
]
an
d
ass
ess
th
e
m
o
d
els’
p
er
f
o
r
m
an
ce
o
n
u
n
s
ee
n
d
ata.
g.
Dep
lo
y
m
en
t:
T
h
e
to
p
-
p
er
f
o
r
m
in
g
m
o
d
el
is
th
en
d
ep
lo
y
ed
to
a
p
r
o
d
u
ctio
n
e
n
v
ir
o
n
m
en
t
,
f
o
llo
win
g
th
ese
s
tep
s
:
−
C
r
ea
tin
g
a
R
E
ST
API
:
A
R
E
STf
u
l
API
is
d
ev
elo
p
e
d
to
en
ab
le
s
ea
m
less
co
m
m
u
n
icati
o
n
b
etwe
en
ex
ter
n
al
s
y
s
tem
s
an
d
th
e
m
o
d
e
l,
allo
win
g
f
o
r
r
ea
l
-
tim
e
d
ata
i
n
p
u
t a
n
d
in
s
tan
t o
u
t
p
u
t o
f
p
r
e
d
ictio
n
s
.
−
Pro
d
u
ctio
n
d
ep
lo
y
m
en
t:
T
h
e
m
o
d
el
is
in
teg
r
ated
in
to
th
e
lo
g
is
tics
s
y
s
tem
,
f
ac
ilit
atin
g
r
ea
l
-
tim
e
p
r
ed
ictio
n
s
an
d
o
p
tim
izin
g
v
e
h
icle
ass
ig
n
m
en
ts
f
o
r
d
eliv
e
r
ies.
2
.
2
.
Da
t
a
e
x
plo
ra
t
io
n a
nd
prepro
ce
s
s
ing
W
h
en
an
o
r
d
er
is
co
n
f
ir
m
ed
a
s
f
ea
s
ib
le
f
o
r
d
eliv
er
y
,
it
is
im
p
o
r
tan
t
to
d
ef
in
e
its
p
r
o
f
ile.
T
h
is
p
r
o
f
ile
s
er
v
es
as
a
d
etailed
d
escr
ip
tio
n
o
f
th
e
o
r
d
er
,
h
elp
in
g
to
id
e
n
tify
th
e
m
o
s
t
s
u
itab
le
d
eliv
er
y
v
e
h
icle.
Def
in
in
g
th
e
o
r
d
er
p
r
o
f
ile
in
v
o
lv
es
co
n
s
id
er
in
g
v
ar
i
o
u
s
f
ac
to
r
s
,
in
c
lu
d
in
g
th
e
ch
a
r
ac
ter
is
tics
o
f
th
e
g
o
o
d
s
(
s
u
ch
as
v
o
lu
m
e,
weig
h
t,
an
d
n
atu
r
e)
,
th
e
tar
g
et
cu
s
to
m
er
,
th
e
ex
p
e
cted
d
eliv
er
y
tim
elin
e,
an
d
th
e
d
eliv
er
y
ty
p
o
lo
g
y
(
i.e
.
,
th
e
ty
p
e
o
f
d
eliv
e
r
y
s
er
v
ice
r
eq
u
ir
ed
,
s
u
c
h
as
u
r
g
en
t
,
s
ch
ed
u
led
.
.
.
)
.
B
y
u
n
d
er
s
tan
d
in
g
th
ese
f
ac
to
r
s
,
lo
g
is
tics
p
r
o
f
ess
io
n
als
ca
n
b
etter
m
atch
th
e
s
p
ec
if
ic
r
eq
u
ir
em
en
ts
o
f
th
e
o
r
d
er
with
th
e
av
ailab
le
v
eh
icles
d
u
r
in
g
th
e
d
eliv
er
y
p
la
n
n
in
g
p
r
o
ce
s
s
.
T
o
id
en
tify
th
e
ap
p
r
o
p
r
iate
v
e
h
icle
f
o
r
th
e
d
eliv
e
r
y
,
it
is
n
ec
ess
ar
y
to
d
ef
in
e
b
o
th
in
p
u
t
an
d
o
u
tp
u
t
v
ar
iab
les
th
at
r
ep
r
esen
t
th
e
r
elev
an
t
p
ar
am
ete
r
s
an
d
ch
a
r
ac
ter
is
tics
.
T
h
ese
in
p
u
ts
f
o
r
m
th
e
b
asis
f
o
r
d
ec
id
in
g
w
h
ich
v
eh
icle
is
m
o
s
t
s
u
ited
f
o
r
tr
an
s
p
o
r
tin
g
th
e
g
o
o
d
s
.
So
m
e
k
ey
p
ar
am
eter
s
to
co
n
s
id
er
in
clu
d
e:
a.
Natu
r
e
o
f
th
e
g
o
o
d
s
:
T
h
e
ty
p
e
o
f
g
o
o
d
s
to
b
e
tr
an
s
p
o
r
te
d
s
ig
n
if
ican
tly
im
p
ac
ts
th
e
v
eh
icle
s
elec
tio
n
.
C
er
tain
g
o
o
d
s
,
lik
e
h
az
ar
d
o
u
s
m
ater
ials
,
o
r
f
r
ag
ile
p
r
o
d
u
cts,
r
eq
u
ir
e
s
p
ec
if
ic
s
to
r
ag
e,
h
an
d
lin
g
,
a
n
d
tr
an
s
p
o
r
tatio
n
c
o
n
d
itio
n
s
.
A
v
eh
icle
th
at
d
o
es
n
o
t
m
ee
t
th
es
e
r
eq
u
ir
em
e
n
ts
co
u
ld
d
am
ag
e
o
r
ev
e
n
r
en
d
er
th
e
g
o
o
d
s
u
n
f
it f
o
r
d
eli
v
er
y
.
b.
Deliv
er
y
d
is
tan
ce
:
T
h
e
d
is
tan
ce
b
etwe
en
th
e
o
r
ig
i
n
an
d
d
es
tin
atio
n
d
ir
ec
tly
af
f
ec
ts
v
e
h
icle
ca
p
ac
ity
,
f
u
el
ef
f
icien
cy
,
a
n
d
d
eliv
e
r
y
tim
e.
L
o
n
g
er
d
is
tan
ce
s
m
ay
r
e
q
u
ir
e
v
eh
icles
with
h
ig
h
er
f
u
el
c
ap
ac
ity
o
r
th
o
s
e
m
o
r
e
s
u
ited
f
o
r
lo
n
g
-
h
a
u
l tr
ip
s
.
c.
Deliv
er
y
d
u
r
atio
n
:
T
h
e
tim
e
r
eq
u
ir
ed
to
tr
an
s
p
o
r
t
th
e
g
o
o
d
s
f
r
o
m
th
e
s
tar
t
p
o
in
t
to
t
h
e
en
d
p
o
in
t
ca
n
in
f
lu
en
ce
th
e
c
h
o
ice
o
f
v
eh
ic
le.
Fo
r
i
n
s
tan
ce
,
a
tim
e
-
s
en
s
itiv
e
d
eliv
er
y
m
a
y
r
e
q
u
ir
e
a
v
eh
icle
th
at
ca
n
tr
av
el
f
aster
o
r
ca
n
n
av
i
g
ate
th
r
o
u
g
h
ar
ea
s
with
less
co
n
g
esti
o
n
.
T
h
e
in
p
u
t v
ar
ia
b
les ar
e
th
e
p
ar
am
eter
s
an
d
ch
ar
ac
ter
is
tics
o
f
th
e
d
eliv
er
y
m
en
tio
n
ed
ab
o
v
e,
wh
ile
th
e
o
u
tp
u
t
v
a
r
iab
le
is
th
e
s
u
itab
le
v
eh
icle
f
o
r
th
e
d
eliv
er
y
.
T
h
e
p
r
o
p
o
s
ed
m
o
d
el
is
ap
p
lied
to
th
e”
Deliv
er
y
T
r
u
ck
T
r
ip
”
d
ataset,
wh
ich
co
n
tain
s
d
eliv
er
y
tr
ip
in
f
o
r
m
atio
n
f
o
r
ea
ch
o
r
d
er
,
in
clu
d
in
g
th
e
ty
p
e
o
f
v
eh
icle
th
at
is
s
u
itab
le
f
o
r
ea
ch
d
eliv
er
y
.
T
h
e
d
ataset
is
d
iv
id
ed
in
to
two
p
ar
ts
:
th
e
tr
ain
in
g
s
et,
u
s
ed
to
tr
ain
th
e
m
o
d
el
an
d
m
in
im
ize
er
r
o
r
s
,
an
d
th
e
test
s
et,
u
s
ed
to
e
v
alu
ate
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
tr
ain
ed
m
o
d
el.
B
ef
o
r
e
f
ee
d
in
g
th
e
d
ataset
in
to
th
e
m
o
d
el,
we
n
o
ticed
th
at
s
o
m
e
f
ea
tu
r
es
wer
e
n
o
t
n
o
r
m
ally
d
is
tr
ib
u
ted
.
As
a
r
esu
lt,
s
tan
d
ar
d
izatio
n
o
f
th
e
d
ataset
is
n
ec
ess
ar
y
[
1
2
]
.
W
e
ap
p
ly
th
e
Stan
d
ar
d
Scaler
p
r
ep
r
o
ce
s
s
in
g
tech
n
iq
u
e
to
s
tan
d
ar
d
ize
th
e
d
ata
[
1
3
]
,
u
s
in
g
th
e
(
1
)
:
′
=
−
(
1
)
W
h
er
e:
:
is
th
e
tr
ain
in
g
s
am
p
le
:
is
th
e
s
tan
d
ar
d
d
e
v
iatio
n
o
f
t
h
e
tr
ain
in
g
s
am
p
les
:
is
th
e
m
ea
n
o
f
th
e
tr
ai
n
in
g
s
a
m
p
les
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
.
5
,
Octo
b
e
r
20
25
:
4
8
9
9
-
4
9
0
6
4902
T
o
f
o
cu
s
o
n
th
e
m
o
s
t
r
elev
an
t
d
ata
f
o
r
o
u
r
m
o
d
el,
we
s
ele
cted
s
ev
er
al
k
ey
c
o
lu
m
n
s
,
as
s
h
o
wn
in
T
ab
le
1
.
T
h
ese
in
clu
d
e
“De
liv
er
y
I
D”,
“Bo
o
k
in
g
I
D”,
“Da
te”,
“De
s
tin
atio
n
lo
ca
tio
n
”,
“On
-
tim
e
d
elay
”,
“T
r
i
p
s
tar
t
d
ate”
,
“T
r
i
p
e
n
d
d
at
e”
,
“T
r
a
n
s
f
o
r
m
atio
n
d
is
tan
c
e”
,
“M
ater
ial
s
h
ip
p
ed
”,
an
d
“Ve
h
icle
t
y
p
e”
.
Ad
d
itio
n
ally
,
we
cr
ea
ted
a
n
e
w
co
lu
m
n
,
“T
r
an
s
f
o
r
m
atio
n
d
u
r
atio
n
”,
wh
ic
h
ca
lcu
lates
th
e
tim
e
tak
en
f
o
r
ea
ch
d
eliv
er
y
b
y
s
u
b
tr
ac
tin
g
th
e
“T
r
ip
s
tar
t
d
ate”
f
r
o
m
th
e
“T
r
ip
en
d
d
ate”
.
B
ef
o
r
e
ap
p
l
y
in
g
th
e
m
o
d
el,
w
e
p
er
f
o
r
m
ed
d
ata
clea
n
in
g
b
y
f
i
r
s
t
id
en
tify
in
g
an
d
r
em
o
v
i
n
g
a
n
y
r
o
ws
with
m
is
s
in
g
o
r
in
co
m
p
lete
v
alu
es.
T
h
is
s
tep
was
cr
u
cial
to
en
s
u
r
e
th
at
th
e
d
ataset
u
s
ed
f
o
r
tr
ai
n
in
g
th
e
m
o
d
el
is
b
o
th
co
m
p
lete
an
d
r
eliab
le,
p
r
ev
en
tin
g
an
y
is
s
u
es
th
at
m
ig
h
t
ar
is
e
f
r
o
m
m
is
s
in
g
d
ata
[
1
4
]
.
Ad
d
itio
n
ally
,
we
f
ilter
ed
o
u
t
n
eg
ativ
e
v
alu
es
in
th
e
T
r
an
s
f
o
r
m
atio
n
d
u
r
atio
n
co
lu
m
n
,
e
n
s
u
r
in
g
th
at
it
o
n
l
y
co
n
tain
s
v
alid
,
p
o
s
itiv
e
v
al
u
es.
T
h
e
“M
ater
ial
s
h
ip
p
ed
”
c
o
lu
m
n
co
n
s
is
ts
o
f
v
ar
i
o
u
s
ca
teg
o
r
ies,
wh
ich
we
en
c
o
d
ed
in
to
b
in
a
r
y
c
o
lu
m
n
s
u
s
in
g
th
e
On
eHo
tEn
co
d
er
[
1
5
]
.
Similar
ly
,
th
e
“Ve
h
icle
ty
p
e”
co
lu
m
n
i
n
clu
d
es m
u
ltip
le
ca
teg
o
r
ies,
wh
ich
we
co
n
v
er
ted
to
n
u
m
er
ical
lab
els
u
s
in
g
th
e
La
b
elE
n
co
d
er
[
1
6
]
.
T
h
ese
n
u
m
er
ical
lab
els
will
b
e
u
s
ed
as
o
u
r
tar
g
et
v
ar
iab
le
(
y
)
.
Af
ter
clea
n
in
g
an
d
p
r
ep
r
o
ce
s
s
in
g
th
e
d
ata,
we
s
p
lit
it
i
n
to
t
wo
s
ets:
(
X)
,
wh
ic
h
co
n
tain
s
t
h
e
f
ea
tu
r
e
v
ar
iab
les
(
in
p
u
t
v
ar
iab
les),
a
n
d
(
y
)
,
wh
ich
r
ep
r
esen
ts
th
e
tar
g
et
v
ar
iab
le
“
Veh
icle
ty
p
e
”
.
T
o
av
o
id
an
y
o
v
er
lap
,
we
r
e
m
o
v
e
d
th
e
“
Ve
h
icle
ty
p
e
”
co
lu
m
n
f
r
o
m
(
X)
,
en
s
u
r
in
g
th
at
it
r
em
ain
s
ex
cl
u
s
iv
ely
in
th
e
(
y
)
s
et,
wh
ich
is
u
s
ed
f
o
r
p
r
ed
ictio
n
s
.
Nex
t,
we
u
s
ed
Scik
it
-
lear
n
’
s
tr
a
in
test
s
p
lit
f
u
n
ctio
n
to
d
iv
i
d
e
th
e
d
ataset
in
to
two
p
ar
ts
:
a
tr
ain
in
g
s
et
an
d
a
test
s
et.
T
h
e
tr
ain
in
g
s
et
i
s
u
s
ed
to
f
it
th
e
m
o
d
el,
en
ab
lin
g
it
to
lear
n
th
e
r
elatio
n
s
h
ip
s
b
etwe
en
th
e
f
ea
t
u
r
es
an
d
th
e
tar
g
et
v
ar
iab
le.
T
h
e
test
s
et
is
th
en
u
s
ed
to
ev
alu
ate
th
e
m
o
d
el’
s
p
er
f
o
r
m
an
ce
b
y
co
m
p
a
r
in
g
it
s
p
r
ed
ictio
n
s
to
th
e
ac
tu
al
v
alu
es,
p
r
o
v
id
i
n
g
a
m
ea
s
u
r
e
o
f
h
o
w
well
th
e
m
o
d
el
g
en
er
alize
s
to
n
ew,
u
n
s
ee
n
d
at
a.
T
ab
le
1
.
C
o
lu
m
n
v
alu
e
e
x
am
p
les f
r
o
m
th
e
lo
g
is
tics
d
ataset
C
o
l
u
mn
n
a
me
Ty
p
e
V
a
l
u
e
s
(
e
x
a
m
p
l
e
)
D
e
scri
p
t
i
o
n
Tr
a
n
s
p
o
r
t
a
t
i
o
n
d
i
st
a
n
c
e
N
u
meri
c
a
l
8
4
6
0
.
0
Th
e
d
i
st
a
n
c
e
t
r
a
v
e
l
e
d
t
o
mo
v
e
g
o
o
d
s f
r
o
m t
h
e
o
r
i
g
i
n
t
o
t
h
e
d
e
st
i
n
a
t
i
o
n
(
k
m)
Tr
a
n
s
p
o
r
t
a
t
i
o
n
d
u
r
a
t
i
o
n
N
u
meri
c
a
l
3
1
.
0
Th
e
t
i
me
t
a
k
e
n
t
o
m
o
v
e
g
o
o
d
s
f
r
o
m t
h
e
o
r
i
g
i
n
t
o
t
h
e
d
e
s
t
i
n
a
t
i
o
n
(
sec
o
n
d
s)
M
a
t
e
r
i
a
l
sh
i
p
p
e
d
C
a
t
e
g
o
r
i
c
a
l
TO
O
L
K
I
T
S
ET
Th
e
t
y
p
e
o
f
m
a
t
e
r
i
a
l
t
h
a
t
h
a
s
b
e
e
n
d
e
l
i
v
e
r
e
d
V
e
h
i
c
l
e
t
y
p
e
C
a
t
e
g
o
r
i
c
a
l
2
1
M
T
,
4
0
F
T
3
X
L
Tr
a
i
l
e
r
3
5
M
T
Th
e
t
y
p
e
o
f
v
e
h
i
c
l
e
u
se
d
f
o
r
t
r
a
n
s
p
o
r
t
i
n
g
g
o
o
d
s
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
3
.
1
.
M
ultino
m
ia
l lo
g
is
t
ic
re
g
re
s
s
i
o
n f
o
r
deliv
er
y
v
ehicle
predict
io
n
T
o
m
ak
e
p
r
ed
ictio
n
s
,
we
d
e
cid
ed
to
u
s
e
m
u
ltin
o
m
ial
lo
g
is
tic
r
eg
r
ess
io
n
,
a
s
u
p
er
v
is
ed
m
ac
h
in
e
lear
n
in
g
m
o
d
el.
T
h
is
m
o
d
el
is
a
class
if
icatio
n
tech
n
iq
u
e
th
at
ex
ten
d
s
lo
g
is
tic
r
eg
r
ess
io
n
to
h
an
d
le
ca
teg
o
r
ica
l
d
ep
en
d
e
n
t
v
a
r
iab
les
with
m
o
r
e
th
an
two
p
o
s
s
ib
le
o
u
tco
m
es
[
1
7
]
.
W
e
s
elec
ted
th
is
alg
o
r
ith
m
b
ec
au
s
e
o
u
r
tar
g
et
v
ar
iab
le,
“
Ve
h
icle
ty
p
e
”
,
co
n
s
is
ts
o
f
m
u
ltip
le
class
es.
Af
ter
tr
ain
in
g
t
h
e
m
o
d
el,
we
a
s
s
es
s
ed
its
p
er
f
o
r
m
an
ce
b
y
ca
l
cu
latin
g
th
e
ac
cu
r
ac
y
,
w
h
ich
r
ep
r
esen
ts
th
e
p
r
o
p
o
r
tio
n
o
f
co
r
r
ec
t
p
r
e
d
ictio
n
s
r
elativ
e
to
th
e
to
tal
p
r
ed
ictio
n
s
.
I
n
o
u
r
ca
s
e,
th
e
m
o
d
el
ac
h
iev
ed
7
6
%
ac
cu
r
ac
y
o
n
th
e
tr
ain
i
n
g
s
et
an
d
6
0
%
ac
cu
r
ac
y
o
n
th
e
test
s
et.
T
h
e
s
ig
n
if
ican
t
d
if
f
er
en
ce
(
o
v
er
10%
)
b
etwe
en
th
e
tr
ain
in
g
an
d
test
ac
cu
r
ac
ie
s
s
u
g
g
ests
p
o
ten
tial o
v
er
f
itti
n
g
.
Ov
er
f
itti
n
g
o
cc
u
r
s
wh
en
th
e
m
o
d
el
b
ec
o
m
es to
o
s
p
ec
ialized
in
m
em
o
r
izin
g
t
h
e
tr
ain
in
g
d
ata,
lea
d
in
g
to
h
ig
h
p
er
f
o
r
m
a
n
ce
o
n
t
h
e
tr
a
in
in
g
s
et
b
u
t
p
o
o
r
g
en
er
aliza
tio
n
to
n
ew,
u
n
s
ee
n
d
ata
(
i.e
.
,
t
h
e
test
s
et)
.
As
a
r
esu
lt,
th
e
m
o
d
el
p
er
f
o
r
m
s
w
o
r
s
e
o
n
th
e
test
s
et,
wh
ich
lo
wer
s
th
e
test
ac
cu
r
ac
y
.
3
.
2
.
M
ulti
-
la
y
er
perc
ept
ro
n
f
o
r
deliv
er
y
v
ehicle
predict
io
n
An
o
th
er
m
ac
h
in
e
lear
n
in
g
al
g
o
r
ith
m
we
u
s
ed
to
p
r
ed
ict
th
e
s
u
itab
le
v
e
h
icle
f
o
r
d
eliv
er
y
is
th
e
m
u
ltil
ay
er
p
er
ce
p
tr
o
n
(
ML
P),
a
ty
p
e
o
f
n
e
u
r
al
n
etwo
r
k
m
o
d
el
th
at
is
p
ar
ticu
lar
ly
well
-
s
u
it
ed
f
o
r
class
if
icatio
n
p
r
o
b
lem
s
[
1
8
]
.
T
h
e
p
r
ep
r
o
ce
s
s
in
g
s
tep
s
f
o
r
o
u
r
d
ataset,
as d
escr
ib
ed
ea
r
lier
,
ar
e
th
e
s
am
e
a
s
th
o
s
e
u
s
ed
f
o
r
th
e
m
u
ltin
o
m
ial
lo
g
is
tic
r
eg
r
ess
io
n
m
o
d
el.
Fo
r
t
r
ain
in
g
,
th
e
ML
P
m
o
d
el
u
tili
ze
s
two
h
i
d
d
en
lay
er
s
,
as
illu
s
tr
ated
in
Fig
u
r
e
2
.
T
h
e
f
ir
s
t
h
id
d
en
lay
er
co
n
tain
s
th
r
ee
n
eu
r
o
n
s
,
wh
ile
th
e
s
ec
o
n
d
h
id
d
en
lay
e
r
h
as
two
n
eu
r
o
n
s
.
T
h
e
alg
o
r
ith
m
p
r
o
ce
s
s
es
th
e
in
p
u
t
d
ata,
a
p
p
lies
tr
an
s
f
o
r
m
atio
n
s
,
an
d
th
e
n
p
ass
es
th
e
r
esu
lts
to
th
e
o
u
tp
u
t
lay
er
,
wh
ich
g
en
er
ates th
e
f
i
n
a
l p
r
ed
ictio
n
.
T
o
ass
ess
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
m
u
ltil
ay
er
p
er
ce
p
tr
o
n
m
o
d
el,
we
ev
al
u
ated
it
u
s
in
g
s
ev
er
a
l
class
if
icatio
n
m
etr
ics,
as
illu
s
t
r
ated
in
Fig
u
r
e
3
,
f
o
r
ea
ch
o
f
th
e
th
r
ee
class
es
(
3
0
,
3
4
,
a
n
d
3
6
)
.
T
h
ese
m
etr
ics
in
clu
d
e
p
r
ec
is
io
n
,
r
ec
all,
F1
-
s
co
r
e,
an
d
s
u
p
p
o
r
t
(
th
e
n
u
m
b
e
r
o
f
in
s
tan
ce
s
o
f
ea
ch
class
in
th
e
d
ataset)
.
T
h
ese
m
etr
ics
p
r
o
v
id
e
a
co
m
p
r
e
h
en
s
iv
e
u
n
d
er
s
tan
d
in
g
o
f
h
o
w
well
th
e
m
o
d
el
p
r
ed
icts
th
e
co
r
r
ec
t
v
eh
icle
ty
p
e
f
o
r
d
eliv
er
y
.
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
Op
timiz
in
g
ve
h
icle
s
elec
tio
n
i
n
s
u
p
p
ly
ch
a
in
ma
n
a
g
eme
n
t w
ith
…
(
I
ma
n
e
Zer
o
u
a
l
)
4903
Fig
u
r
e
2
.
ML
P
class
if
ier
m
o
d
e
l f
o
r
v
e
h
icle
ty
p
e
p
r
ed
ictio
n
u
s
in
g
tr
an
s
p
o
r
tatio
n
d
ata
Fig
u
r
e
3
.
C
lass
if
icatio
n
r
ep
o
r
t
f
o
r
m
u
lti
-
lay
e
r
p
er
ce
p
tr
o
n
a.
Pre
cisi
o
n
is
th
e
r
atio
o
f
co
r
r
ec
tly
p
r
ed
icted
p
o
s
itiv
e
in
s
tan
ce
s
o
v
er
th
e
to
tal
p
r
ed
icted
p
o
s
itiv
e
in
s
tan
ce
,
as
s
h
o
wn
in
(
2
)
:
:
+
(
2
)
b.
R
ec
all
is
th
e
r
atio
o
f
co
r
r
ec
tly
p
r
ed
icted
p
o
s
itiv
e
in
s
tan
ce
s
o
v
er
th
e
to
tal
ac
t
u
al
p
o
s
itiv
e
in
s
tan
ce
s
[
1
9
]
,
as
s
h
o
wn
in
(
3
)
:
:
+
(
3
)
c.
F1
-
s
co
r
e
is
th
e
h
ar
m
o
n
ic
m
ea
n
o
f
p
r
ec
is
io
n
an
d
r
ec
all,
an
d
it
p
r
o
v
id
es
a
b
alan
ce
b
etwe
e
n
p
r
ec
is
io
n
an
d
r
ec
all
[
2
0
]
,
as sh
o
wn
in
(
4
)
:
1
−
:
2
∗
(
×
)
+
(
4
)
d.
Mic
r
o
a
v
e
r
a
g
e
o
f
p
r
ec
is
i
o
n
,
r
e
ca
ll
,
an
d
F1
-
s
c
o
r
e
is
a
w
ei
g
h
te
d
av
er
a
g
e
th
at
ac
co
u
n
ts
f
o
r
c
la
s
s
im
b
a
la
n
c
e
b
y
co
n
s
i
d
e
r
i
n
g
t
h
e
t
o
t
al
n
u
m
b
e
r
o
f
i
n
s
t
an
ce
s
ac
r
o
s
s
all
c
las
s
es
[
2
1
]
.
I
n
c
o
n
tr
ast
,
Ma
cr
o
a
v
e
r
ag
e
is
a
n
u
n
wei
g
h
t
ed
a
v
er
ag
e
o
f
p
r
e
cisi
o
n
,
r
ec
all
,
a
n
d
F
1
-
s
c
o
r
e,
t
r
e
ati
n
g
ea
c
h
c
lass
e
q
u
all
y
r
e
g
a
r
d
le
s
s
o
f
its
s
i
ze
.
I
n
o
u
r
c
ase
,
t
h
e
m
o
d
el
’
s
p
e
r
f
o
r
m
a
n
c
e
is
as
:
wei
g
h
te
d
a
v
e
r
a
g
e
p
r
ec
is
i
o
n
:
0
.
5
8
,
r
ec
all
:
0
.
8
0
,
a
n
d
F1
-
s
c
o
r
e:
0
.
6
6
.
T
h
ese
v
alu
es
in
d
icate
m
o
d
er
at
e
p
er
f
o
r
m
a
n
ce
o
v
e
r
all.
T
h
e
r
el
ativ
ely
h
ig
h
r
ec
all
o
f
8
0
%
s
u
g
g
ests
th
at
th
e
m
o
d
el
is
ef
f
ec
tiv
e
at
co
r
r
ec
tly
id
en
tify
in
g
p
o
s
itiv
e
in
s
tan
ce
s
.
Ho
wev
er
,
th
e
lo
wer
p
r
ec
is
io
n
o
f
5
8
%
in
d
icate
s
th
at
o
n
ly
ab
o
u
t
5
8
%
o
f
th
e
i
n
s
tan
ce
s
p
r
ed
icted
as
p
o
s
itiv
e
ar
e
co
r
r
ec
t,
m
e
an
i
n
g
th
e
m
o
d
el
h
as
a
r
elativ
ely
h
ig
h
f
alse p
o
s
itiv
e
r
ate.
Fo
r
in
d
iv
id
u
al
class
es:
−
C
las
s
3
4
s
h
o
ws th
e
h
ig
h
est p
r
ec
is
io
n
an
d
r
ec
all,
in
d
icatin
g
t
h
e
m
o
d
el
p
er
f
o
r
m
s
b
est f
o
r
th
i
s
class
.
−
C
las
s
3
0
h
as
th
e
h
ig
h
est
r
ec
all
b
u
t
th
e
lo
west
p
r
ec
is
io
n
,
s
u
g
g
esti
n
g
th
e
m
o
d
el
is
m
o
r
e
p
r
o
n
e
to
f
alse
p
o
s
itiv
es f
o
r
th
is
class
.
−
C
las
s
3
6
ex
h
ib
its
b
o
th
th
e
lo
w
est p
r
ec
is
io
n
an
d
r
ec
all,
s
ig
n
al
in
g
p
o
o
r
p
e
r
f
o
r
m
an
ce
f
o
r
th
is
class
.
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
.
5
,
Octo
b
e
r
20
25
:
4
8
9
9
-
4
9
0
6
4904
3
.
3
.
Dec
is
io
n t
re
e
a
l
g
o
rit
hm
f
o
r
deliv
er
y
v
ehicle
predict
io
n
T
h
e
f
in
al
m
o
d
el
e
x
p
lo
r
e
d
i
n
th
is
s
ec
tio
n
is
th
e
d
ec
is
io
n
tr
ee
,
a
s
u
p
er
v
is
ed
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
co
m
m
o
n
ly
u
s
ed
f
o
r
class
if
icatio
n
task
s
.
T
h
is
m
o
d
el
is
p
ar
ticu
lar
l
y
u
s
ef
u
l
f
o
r
p
r
o
b
lem
s
w
h
er
e
t
h
e
g
o
al
is
to
ass
ig
n
in
p
u
ts
to
o
n
e
o
f
s
ev
er
al
p
r
ed
ef
i
n
ed
class
es
b
ased
o
n
ce
r
tain
f
ea
tu
r
es
[
2
2
]
.
W
e
tr
ain
ed
th
e
d
ec
is
io
n
tr
ee
o
n
th
e
s
am
e
d
ata
s
et
as
th
e
p
r
ev
io
u
s
m
o
d
els
an
d
g
en
er
ate
d
th
e
class
if
icatio
n
r
ep
o
r
t,
as
s
h
o
w
n
in
Fig
u
r
e
4
.
T
h
e
r
esu
lts
f
r
o
m
th
e
class
if
icatio
n
r
ep
o
r
t,
b
ased
o
n
th
e
test
d
ata,
r
ev
ea
l
th
e
f
o
ll
o
win
g
p
er
f
o
r
m
a
n
ce
m
etr
ics f
o
r
th
e
d
ec
is
io
n
tr
ee
cl
ass
if
ier
:
Pre
cisi
o
n
:
66%
,
R
ec
al
l:
82%
,
an
d
F1
-
s
co
r
e:
68%
.
Pre
cisi
o
n
m
ea
s
u
r
es
th
e
ac
cu
r
a
cy
o
f
p
o
s
itiv
e
p
r
e
d
ictio
n
s
,
with
th
e
m
o
d
el
co
r
r
ec
tly
p
r
e
d
ictin
g
6
6
%
o
f
p
o
s
itiv
e
in
s
tan
ce
s
.
R
ec
all
r
ef
le
cts
th
e
m
o
d
el’
s
ab
ilit
y
to
id
en
t
if
y
ac
tu
al
p
o
s
itiv
es,
co
r
r
ec
tly
i
d
en
tify
in
g
8
2
%
o
f
th
em
.
T
h
e
F1
-
s
co
r
e,
th
e
h
a
r
m
o
n
ic
m
ea
n
o
f
p
r
ec
is
io
n
an
d
r
ec
all,
is
68%
,
o
f
f
er
in
g
a
b
alan
ce
d
v
iew
o
f
p
er
f
o
r
m
an
ce
.
W
h
ile
th
e
m
o
d
el
h
as
h
ig
h
r
ec
all
82%
,
in
d
icatin
g
it
d
etec
ts
m
o
s
t
p
o
s
itiv
e
in
s
tan
ce
s
,
its
lo
wer
p
r
ec
is
io
n
6
6
%
s
u
g
g
ests
it m
is
class
if
ies
s
o
m
e
n
eg
ativ
es a
s
p
o
s
itiv
es.
I
n
s
u
m
m
ar
y
,
th
e
class
if
ier
h
as a
weig
h
ted
av
er
ag
e
p
r
ec
is
io
n
o
f
6
6
%
,
r
e
ca
ll
o
f
82%
,
an
d
F1
-
s
co
r
e
o
f
68%
,
in
d
icatin
g
g
o
o
d
d
etec
tio
n
o
f
p
o
s
itiv
es
b
u
t
with
s
o
m
e
f
alse p
o
s
itiv
es.
T
h
e
th
r
ee
m
ac
h
in
e
lear
n
i
n
g
m
o
d
els
test
ed
in
th
is
s
tu
d
y
(
m
u
ltin
o
m
ial
lo
g
is
tic
r
eg
r
ess
io
n
,
d
ec
is
io
n
tr
ee
,
an
d
m
u
ltil
ay
er
p
er
ce
p
tr
o
n
)
p
r
o
v
id
e
v
alu
ab
le
in
s
ig
h
t
s
in
to
p
r
ed
ictin
g
th
e
m
o
s
t
s
u
itab
le
v
e
h
icle
f
o
r
d
eliv
er
y
ass
ig
n
m
en
ts
.
Ho
we
v
er
,
all
m
o
d
els
en
c
o
u
n
ter
e
d
ch
allen
g
es
r
elate
d
to
b
o
th
u
n
d
er
f
itti
n
g
an
d
o
v
er
f
itti
n
g
,
lar
g
ely
d
u
e
to
th
e
lim
ited
s
ize
an
d
co
m
p
lex
ity
o
f
th
e
d
ataset.
Un
d
er
f
itti
n
g
was
o
b
s
er
v
ed
wh
e
n
th
e
m
o
d
els
f
ailed
to
ca
p
tu
r
e
t
h
e
u
n
d
er
ly
in
g
p
atter
n
s
in
th
e
d
ata
[
2
3
]
,
wh
ile
o
v
er
f
itti
n
g
o
cc
u
r
r
e
d
wh
en
th
e
m
o
d
els
lear
n
ed
th
e
tr
ain
in
g
d
ata
to
o
well,
in
clu
d
in
g
n
o
is
e
an
d
ir
r
elev
an
t
d
etails
[
2
4
]
.
T
h
is
l
ed
to
p
er
f
o
r
m
an
c
e
in
co
n
s
is
ten
cy
,
with
th
e
m
o
d
e
ls
p
er
f
o
r
m
i
n
g
s
ig
n
if
ica
n
tly
b
etter
o
n
t
h
e
tr
ain
in
g
d
ata
th
a
n
o
n
th
e
test
d
ata
,
wh
ich
is
a
co
m
m
o
n
s
y
m
p
to
m
o
f
o
v
e
r
f
itti
n
g
.
T
o
g
ain
a
m
o
r
e
co
m
p
r
eh
e
n
s
iv
e
u
n
d
e
r
s
tan
d
in
g
o
f
m
o
d
el
p
er
f
o
r
m
an
ce
,
we
u
s
ed
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
-
s
co
r
e
as
ad
d
itio
n
al
ev
alu
at
io
n
m
etr
ics,
alo
n
g
s
id
e
ac
c
u
r
ac
y
.
Acc
u
r
ac
y
alo
n
e
ca
n
s
o
m
eti
m
es
b
e
m
is
lead
in
g
,
esp
ec
ially
in
m
u
lti
-
class
class
i
f
icatio
n
task
s
,
wh
er
e
class
im
b
alan
ce
m
ay
s
k
ew
th
e
m
o
d
el’
s
tr
u
e
p
er
f
o
r
m
an
ce
.
T
o
r
ed
u
ce
o
v
er
f
itti
n
g
,
we
ad
j
u
s
ted
th
e
m
u
ltin
o
m
ial
lo
g
is
tic
r
eg
r
ess
io
n
m
o
d
el
b
y
ap
p
ly
in
g
cr
o
s
s
-
v
alid
atio
n
,
wh
ich
h
elp
s
b
etter
ass
ess
its
g
en
er
aliza
tio
n
to
u
n
s
ee
n
d
ata,
as
s
h
o
wn
in
Fig
u
r
e
5
.
Desp
ite
th
ese
ad
ju
s
tm
en
ts
,
th
e
p
er
f
o
r
m
an
c
e
o
f
th
e
m
o
d
e
ls
co
u
ld
b
e
f
u
r
th
er
im
p
r
o
v
ed
b
y
a
p
p
ly
in
g
tech
n
iq
u
es
s
u
ch
as
h
y
p
e
r
p
ar
am
eter
tu
n
in
g
[
2
5
]
,
en
s
em
b
le
lear
n
in
g
,
an
d
t
r
ain
in
g
o
n
lar
g
er
,
m
o
r
e
d
iv
er
s
e
d
atasets
.
Fu
tu
r
e
wo
r
k
co
u
ld
also
ex
p
lo
r
e
m
eth
o
d
s
lik
e
ea
r
ly
s
to
p
p
in
g
[
2
6
]
a
n
d
d
r
o
p
o
u
t
d
u
r
in
g
tr
ai
n
in
g
[
2
7
]
to
e
n
h
an
ce
g
en
er
al
izatio
n
an
d
r
e
d
u
c
e
o
v
er
f
itti
n
g
.
Fig
u
r
e
4
.
C
lass
if
icatio
n
r
ep
o
r
t
f
o
r
d
ec
is
io
n
t
r
ee
m
o
d
el
Fig
u
r
e
5
.
C
r
o
s
s
-
v
alid
atio
n
ac
c
u
r
ac
y
f
o
r
m
u
ltin
o
m
ial
lo
g
is
tic
r
eg
r
ess
io
n
4.
CO
NCLU
SI
O
N
T
h
e
in
teg
r
ati
o
n
o
f
a
r
tific
ial
in
tellig
en
ce
in
lo
g
is
tics
h
as
th
e
p
o
ten
tial
t
o
s
ig
n
if
ican
tly
o
p
tim
iz
e
p
r
o
ce
s
s
es
b
y
an
aly
zi
n
g
d
ata
a
n
d
m
ak
i
n
g
r
ea
l
-
tim
e
p
r
e
d
ictio
n
s
an
d
d
ec
is
io
n
s
.
T
h
is
ca
p
ab
il
ity
ca
n
h
elp
ca
r
r
ier
s
en
h
an
ce
t
h
e
p
r
o
f
itab
ilit
y
o
f
t
h
eir
o
p
e
r
atio
n
s
in
u
r
b
a
n
ar
ea
s
,
im
p
r
o
v
e
o
v
e
r
all
p
er
f
o
r
m
an
ce
,
an
d
u
ltima
tely
in
cr
ea
s
e
cu
s
to
m
er
s
atis
f
ac
tio
n
an
d
lo
y
alty
.
I
n
th
is
p
a
p
er
,
we
ex
p
e
r
im
en
ted
with
th
r
e
e
m
ac
h
in
e
lear
n
in
g
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
Op
timiz
in
g
ve
h
icle
s
elec
tio
n
i
n
s
u
p
p
ly
ch
a
in
ma
n
a
g
eme
n
t w
ith
…
(
I
ma
n
e
Zer
o
u
a
l
)
4905
m
o
d
els
to
tack
le
a
class
if
icatio
n
p
r
o
b
lem
,
aim
in
g
to
id
en
tify
th
e
m
o
s
t
s
u
itab
le
m
o
d
el
b
ased
o
n
v
ar
io
u
s
ev
alu
atio
n
m
etr
ics.
I
n
ad
d
itio
n
to
m
o
d
el
s
elec
tio
n
,
th
e
q
u
al
ity
o
f
th
e
d
ata
p
lay
s
a
c
r
u
cial
r
o
le.
E
f
f
ec
tiv
e
d
ata
p
r
ep
r
o
ce
s
s
in
g
s
u
ch
as
clea
n
in
g
,
tr
an
s
f
o
r
m
atio
n
,
a
n
d
p
r
ep
ar
atio
n
en
s
u
r
es
th
at
th
e
d
ata
is
p
r
o
p
er
l
y
s
tr
u
ctu
r
e
d
f
o
r
th
e
alg
o
r
ith
m
,
wh
ich
h
elp
s
im
p
r
o
v
e
th
e
lear
n
in
g
p
r
o
ce
s
s
.
As
a
f
in
al
n
o
te,
f
u
tu
r
e
r
esear
ch
s
h
o
u
ld
f
o
cu
s
o
n
in
co
r
p
o
r
atin
g
en
v
ir
o
n
m
en
tal
f
ac
to
r
s
in
to
lo
g
is
tics
o
p
tim
izatio
n
m
o
d
els.
T
h
is
co
u
ld
in
c
lu
d
e
en
r
ich
in
g
th
e
d
ataset
with
cr
iter
ia
lik
e
C
O
2
em
is
s
io
n
s
an
d
f
u
el
c
o
n
s
u
m
p
ti
o
n
,
w
h
ich
a
r
e
ess
en
tial
f
o
r
p
r
o
m
o
tin
g
s
u
s
tain
ab
le
lo
g
is
tics
p
r
ac
tices.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
Au
th
o
r
s
s
tate
n
o
f
u
n
d
in
g
in
v
o
lv
ed
.
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
I
m
an
e
Z
er
o
u
al
J
ab
er
E
l Bo
u
h
d
id
i
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
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
Der
iv
ed
d
ata
s
u
p
p
o
r
tin
g
th
e
f
in
d
in
g
s
o
f
t
h
is
s
tu
d
y
ar
e
av
ail
ab
le
f
r
o
m
t
h
e
co
r
r
esp
o
n
d
i
n
g
au
th
o
r
,
IZ
,
o
n
r
eq
u
est.
RE
F
E
R
E
NC
E
S
[
1
]
P
.
S
i
r
i
saw
a
t
,
N
.
H
a
s
a
c
h
o
o
,
a
n
d
T
.
S
.
R
o
d
b
u
n
d
i
t
h
,
“
S
u
st
a
i
n
a
b
l
e
s
u
p
p
l
y
c
h
a
i
n
m
a
n
a
g
e
m
e
n
t
c
h
a
l
l
e
n
g
e
s
a
n
a
l
y
s
i
s
i
n
l
o
c
a
l
p
l
a
s
t
i
c
r
e
c
y
c
l
i
n
g
b
u
si
n
e
ss
,
”
C
l
e
a
n
e
r L
o
g
i
st
i
c
s a
n
d
S
u
p
p
l
y
C
h
a
i
n
,
v
o
l
.
1
3
,
p
.
1
0
0
1
8
8
,
D
e
c
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
l
s
c
n
.
2
0
2
4
.
1
0
0
1
8
8
.
[
2
]
T.
S
.
Ta
m
i
r
e
t
a
l
.
,
“
Tr
a
f
f
i
c
c
o
n
g
e
st
i
o
n
p
r
e
d
i
c
t
i
o
n
u
si
n
g
d
e
c
i
s
i
o
n
t
r
e
e
,
l
o
g
i
st
i
c
r
e
g
r
e
ssi
o
n
a
n
d
n
e
u
r
a
l
n
e
t
w
o
r
k
s,”
I
FA
C
-
Pa
p
e
rsO
n
L
i
n
e
,
v
o
l
.
5
3
,
n
o
.
5
,
p
p
.
5
1
2
–
5
1
7
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
f
a
c
o
l
.
2
0
2
1
.
0
4
.
1
3
8
.
[
3
]
J.
A
l
l
e
n
e
t
a
l
.
,
“
U
n
d
e
r
st
a
n
d
i
n
g
t
h
e
t
r
a
n
s
p
o
r
t
a
n
d
C
O
2
i
mp
a
c
t
s
o
f
o
n
-
d
e
man
d
mea
l
d
e
l
i
v
e
r
i
e
s
:
A
L
o
n
d
o
n
c
a
se
s
t
u
d
y
,
”
C
i
t
i
e
s
,
v
o
l
.
1
0
8
,
p
.
1
0
2
9
7
3
,
J
a
n
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
i
t
i
e
s
.
2
0
2
0
.
1
0
2
9
7
3
.
[
4
]
X
.
La
i
,
X
.
W
u
,
L.
Zh
a
n
g
,
W
.
Lu
,
a
n
d
C
.
Z
h
o
n
g
,
“
I
mp
u
t
a
t
i
o
n
s
o
f
m
i
ssi
n
g
v
a
l
u
e
s
u
si
n
g
a
t
r
a
c
k
i
n
g
-
r
e
m
o
v
e
d
a
u
t
o
e
n
c
o
d
e
r
t
r
a
i
n
e
d
w
i
t
h
i
n
c
o
m
p
l
e
t
e
d
a
t
a
,
”
N
e
u
ro
c
o
m
p
u
t
i
n
g
,
v
o
l
.
3
6
6
,
p
p
.
5
4
–
6
5
,
N
o
v
.
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
n
e
u
c
o
m
.
2
0
1
9
.
0
7
.
0
6
6
.
[
5
]
L.
Y
u
e
,
“
Th
e
c
o
m
p
a
r
i
s
o
n
o
f
s
t
o
r
a
g
e
sp
a
c
e
o
f
t
h
e
t
w
o
m
e
t
h
o
d
s
u
se
d
i
n
S
Q
L
serv
e
r
t
o
r
e
mo
v
e
d
u
p
l
i
c
a
t
e
r
e
c
o
r
d
s
,
”
Pr
o
c
e
d
i
a
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
1
3
1
,
p
p
.
6
9
1
–
6
9
8
,
2
0
1
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
r
o
c
s.
2
0
1
8
.
0
4
.
3
1
3
.
[
6
]
M
.
H
u
,
C
.
Z
h
a
n
g
,
a
n
d
W
.
D
e
n
g
,
“
C
o
n
st
r
u
c
t
e
d
e
n
c
o
d
e
d
d
a
t
a
b
a
se
d
c
o
d
e
d
d
i
st
r
i
b
u
t
e
d
D
N
N
t
r
a
i
n
i
n
g
f
o
r
e
d
g
e
c
o
m
p
u
t
i
n
g
sc
e
n
a
r
i
o
,
”
Ph
y
s
i
c
a
l
C
o
m
m
u
n
i
c
a
t
i
o
n
,
v
o
l
.
6
7
,
p
.
1
0
2
4
9
9
,
D
e
c
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
h
y
c
o
m.
2
0
2
4
.
1
0
2
4
9
9
.
[
7
]
S
.
Zh
a
n
g
,
T.
W
a
n
g
,
K
.
W
o
r
d
e
n
,
L.
S
u
n
,
a
n
d
E.
J
.
C
r
o
ss,
“
C
a
n
o
n
i
c
a
l
-
c
o
r
r
e
l
a
t
i
o
n
-
b
a
se
d
f
a
st
f
e
a
t
u
r
e
s
e
l
e
c
t
i
o
n
f
o
r
st
r
u
c
t
u
r
a
l
h
e
a
l
t
h
mo
n
i
t
o
r
i
n
g
,
”
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
Pro
c
e
ss
i
n
g
,
v
o
l
.
2
2
3
,
p
.
1
1
1
8
9
5
,
J
a
n
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
y
m
ssp
.
2
0
2
4
.
1
1
1
8
9
5
.
[
8
]
C
.
K
.
G
e
h
r
i
n
g
e
r
,
G
.
P
.
M
a
r
t
i
n
,
B
.
V
a
n
C
a
l
s
t
e
r
,
K
.
L.
H
y
r
i
c
h
,
S
.
M
.
M
.
V
e
r
st
a
p
p
e
n
,
a
n
d
J.
C
.
S
e
r
g
e
a
n
t
,
“
H
o
w
t
o
d
e
v
e
l
o
p
,
v
a
l
i
d
a
t
e
,
a
n
d
u
p
d
a
t
e
c
l
i
n
i
c
a
l
p
r
e
d
i
c
t
i
o
n
m
o
d
e
l
s
u
s
i
n
g
m
u
l
t
i
n
o
mi
a
l
l
o
g
i
st
i
c
r
e
g
r
e
ssi
o
n
,
”
J
o
u
rn
a
l
o
f
C
l
i
n
i
c
a
l
E
p
i
d
e
m
i
o
l
o
g
y
,
v
o
l
.
1
7
4
,
p
.
1
1
1
4
8
1
,
O
c
t
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
c
l
i
n
e
p
i
.
2
0
2
4
.
1
1
1
4
8
1
.
[
9
]
L.
B
o
u
n
i
a
a
n
d
I
.
S
e
t
i
t
r
a
,
“
En
h
a
n
c
i
n
g
t
h
e
i
n
t
e
l
l
i
g
i
b
i
l
i
t
y
o
f
d
e
c
i
s
i
o
n
t
r
e
e
s
w
i
t
h
c
o
n
c
i
s
e
a
n
d
r
e
l
i
a
b
l
e
p
r
o
b
a
b
i
l
i
st
i
c
e
x
p
l
a
n
a
t
i
o
n
s
,
”
D
a
t
a
& K
n
o
w
l
e
d
g
e
E
n
g
i
n
e
e
r
i
n
g
,
v
o
l
.
1
5
6
,
p
.
1
0
2
3
9
4
,
M
a
r
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
d
a
t
a
k
.
2
0
2
4
.
1
0
2
3
9
4
.
[
1
0
]
I
.
B
e
t
k
i
e
r
,
“
E
st
i
ma
t
i
n
g
t
r
a
v
e
l
t
i
m
e
i
n
t
r
a
n
s
p
o
r
t
n
e
t
w
o
r
k
w
i
t
h
a
c
o
mb
i
n
e
d
m
u
l
t
i
-
a
t
t
r
i
b
u
t
e
d
g
r
a
p
h
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
a
n
d
mu
l
t
i
l
a
y
e
r
p
e
r
c
e
p
t
r
o
n
m
o
d
e
l
,
”
E
n
g
i
n
e
e
ri
n
g
A
p
p
l
i
c
a
t
i
o
n
s
o
f
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
1
4
2
,
p
.
1
0
9
8
9
8
,
F
e
b
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
n
g
a
p
p
a
i
.
2
0
2
4
.
1
0
9
8
9
8
.
[
1
1
]
N
.
A
c
h
a
r
k
i
,
A
.
B
e
r
t
o
n
c
e
l
l
o
,
a
n
d
J.
G
a
r
n
i
e
r
,
“
R
o
b
u
s
t
p
r
e
d
i
c
t
i
o
n
i
n
t
e
r
v
a
l
e
st
i
mat
i
o
n
f
o
r
G
a
u
ssi
a
n
p
r
o
c
e
sses
b
y
c
r
o
ss
-
v
a
l
i
d
a
t
i
o
n
met
h
o
d
,
”
C
o
m
p
u
t
a
t
i
o
n
a
l
S
t
a
t
i
s
t
i
c
s &
D
a
t
a
A
n
a
l
y
si
s
,
v
o
l
.
1
7
8
,
p
.
1
0
7
5
9
7
,
F
e
b
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
sd
a
.
2
0
2
2
.
1
0
7
5
9
7
.
[
1
2
]
I
.
K
.
K
h
a
n
,
H
.
D
a
u
d
,
N
.
Za
i
n
u
d
d
i
n
,
a
n
d
R
.
S
o
k
k
a
l
i
n
g
a
m
,
“
S
t
a
n
d
a
r
d
i
z
i
n
g
r
e
f
e
r
e
n
c
e
d
a
t
a
i
n
g
a
p
s
t
a
t
i
s
t
i
c
f
o
r
sel
e
c
t
i
o
n
o
p
t
i
mal
n
u
m
b
e
r
o
f
c
l
u
st
e
r
i
n
K
-
m
e
a
n
s
a
l
g
o
r
i
t
h
m,
”
Al
e
x
a
n
d
r
i
a
E
n
g
i
n
e
e
r
i
n
g
J
o
u
rn
a
l
,
v
o
l
.
1
1
8
,
p
p
.
2
4
6
–
2
6
0
,
A
p
r
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
e
j
.
2
0
2
5
.
0
1
.
0
3
4
.
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
.
5
,
Octo
b
e
r
20
25
:
4
8
9
9
-
4
9
0
6
4906
[
1
3
]
R
.
C
R
a
n
d
D
.
S
.
C
P
,
“
E
v
a
l
u
a
t
i
n
g
d
e
e
p
l
e
a
r
n
i
n
g
w
i
t
h
d
i
f
f
e
r
e
n
t
f
e
a
t
u
r
e
sc
a
l
i
n
g
t
e
c
h
n
i
q
u
e
s
f
o
r
EEG
-
b
a
se
d
m
u
s
i
c
e
n
t
r
a
i
n
me
n
t
b
r
a
i
n
c
o
m
p
u
t
e
r
i
n
t
e
r
f
a
c
e
,
”
e
-
Pri
m
e
-
A
d
v
a
n
c
e
s
i
n
E
l
e
c
t
r
i
c
a
l
En
g
i
n
e
e
r
i
n
g
,
El
e
c
t
ro
n
i
c
s
a
n
d
E
n
e
r
g
y
,
v
o
l
.
7
,
p
.
1
0
0
4
4
8
,
M
a
r
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
r
i
me.
2
0
2
4
.
1
0
0
4
4
8
.
[
1
4
]
W.
-
T.
H
o
n
g
a
n
d
H
.
-
K
.
Y
o
o
n
,
“
Est
i
m
a
t
i
n
g
m
i
ssi
n
g
v
a
l
u
e
s
i
n
c
o
m
p
r
e
ss
i
v
e
s
t
r
e
n
g
t
h
o
f
c
e
me
n
t
i
t
i
o
u
s
ma
t
e
r
i
a
l
s
:
A
mac
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
st
a
t
i
st
i
c
a
l
a
p
p
r
o
a
c
h
w
i
t
h
i
r
r
e
g
u
l
a
r
d
a
t
a
,
”
J
o
u
rn
a
l
o
f
B
u
i
l
d
i
n
g
E
n
g
i
n
e
e
r
i
n
g
,
v
o
l
.
1
0
1
,
p
.
1
1
1
7
9
7
,
M
a
y
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
o
b
e
.
2
0
2
5
.
1
1
1
7
9
7
.
[
1
5
]
A
.
A
l
a
z
e
b
,
“
U
t
i
l
i
z
i
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
w
i
t
h
u
n
i
q
u
e
P
e
n
t
a
p
l
e
t
d
a
t
a
st
r
u
c
t
u
r
e
t
o
e
n
h
a
n
c
e
d
a
t
a
i
n
t
e
g
r
i
t
y
,
”
C
o
m
p
u
t
e
rs,
M
a
t
e
ri
a
l
s
&
C
o
n
t
i
n
u
a
,
v
o
l
.
7
7
,
n
o
.
3
,
p
p
.
2
9
9
5
–
3
0
1
4
,
2
0
2
3
,
d
o
i
:
1
0
.
3
2
6
0
4
/
c
mc
.
2
0
2
3
.
0
4
3
1
7
3
.
[
1
6
]
H
.
A
ssm
i
e
t
a
l
.
,
“
A
r
o
b
u
st
s
e
c
u
r
i
t
y
d
e
t
e
c
t
i
o
n
st
r
a
t
e
g
y
f
o
r
n
e
x
t
g
e
n
e
r
a
t
i
o
n
I
o
T
n
e
t
w
o
r
k
s,
”
C
o
m
p
u
t
e
rs,
M
a
t
e
ri
a
l
s
&
C
o
n
t
i
n
u
a
,
v
o
l
.
8
2
,
n
o
.
1
,
p
p
.
4
4
3
–
4
6
6
,
2
0
2
5
,
d
o
i
:
1
0
.
3
2
6
0
4
/
c
m
c
.
2
0
2
4
.
0
5
9
0
4
7
.
[
1
7
]
X
.
G
u
o
,
A
.
C
h
a
u
h
a
n
,
J.
V
e
r
sch
o
o
r
,
a
n
d
A
.
M
a
r
g
e
r
t
,
“
A
q
u
a
l
i
t
y
d
e
c
a
y
mo
d
e
l
w
i
t
h
m
u
l
t
i
n
o
m
i
a
l
l
o
g
i
st
i
c
r
e
g
r
e
ss
i
o
n
a
n
d
i
m
a
g
e
-
b
a
se
d
d
e
e
p
l
e
a
r
n
i
n
g
t
o
p
r
e
d
i
c
t
t
h
e
f
i
r
mn
e
s
s
o
f
‘
C
o
n
f
e
r
e
n
c
e
’
p
e
a
r
s
i
n
t
h
e
d
o
w
n
st
r
e
a
m
su
p
p
l
y
c
h
a
i
n
s,
”
J
o
u
r
n
a
l
o
f
S
t
o
re
d
Pr
o
d
u
c
t
s
Re
se
a
rc
h
,
v
o
l
.
1
0
9
,
p
.
1
0
2
4
5
0
,
D
e
c
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
s
p
r
.
2
0
2
4
.
1
0
2
4
5
0
.
[
1
8
]
N
.
S
l
i
m
a
n
i
,
I
.
S
l
i
m
a
n
i
,
N
.
S
b
i
t
i
,
a
n
d
M
.
A
m
g
h
a
r
,
“
Tr
a
f
f
i
c
f
o
r
e
c
a
st
i
n
g
i
n
M
o
r
o
c
c
o
u
si
n
g
a
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s,
”
Pr
o
c
e
d
i
a
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
1
5
1
,
p
p
.
4
7
1
–
4
7
6
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
r
o
c
s.
2
0
1
9
.
0
4
.
0
6
4
.
[
1
9
]
R
.
S
a
l
l
e
s
e
t
a
l
.
,
“
S
o
f
t
ED
:
M
e
t
r
i
c
s
f
o
r
so
f
t
e
v
a
l
u
a
t
i
o
n
o
f
t
i
me
s
e
r
i
e
s
e
v
e
n
t
d
e
t
e
c
t
i
o
n
,
”
C
o
m
p
u
t
e
rs
&
I
n
d
u
st
ri
a
l
E
n
g
i
n
e
e
r
i
n
g
,
v
o
l
.
1
9
8
,
p
.
1
1
0
7
2
8
,
D
e
c
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
i
e
.
2
0
2
4
.
1
1
0
7
2
8
.
[
2
0
]
W
.
Ji
a
,
Y
.
Q
i
n
,
a
n
d
C
.
Z
h
a
o
,
“
R
a
p
i
d
d
e
t
e
c
t
i
o
n
o
f
a
d
u
l
t
e
r
a
t
e
d
l
a
mb
mea
t
u
s
i
n
g
n
e
a
r
i
n
f
r
a
r
e
d
a
n
d
e
l
e
c
t
r
o
n
i
c
n
o
s
e
:
A
F
1
-
sc
o
r
e
-
M
R
E
d
a
t
a
f
u
si
o
n
a
p
p
r
o
a
c
h
,
”
F
o
o
d
C
h
e
m
i
s
t
r
y
,
v
o
l
.
4
3
9
,
p
.
1
3
8
1
2
3
,
M
a
y
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
f
o
o
d
c
h
e
m.
2
0
2
3
.
1
3
8
1
2
3
.
[
2
1
]
A
.
B
e
r
g
e
r
a
n
d
S
.
G
u
d
a
,
“
T
h
r
e
s
h
o
l
d
o
p
t
i
m
i
z
a
t
i
o
n
f
o
r
F
m
e
a
s
u
r
e
o
f
m
a
c
r
o
-
a
v
e
r
a
g
e
d
p
r
e
c
i
s
i
o
n
a
n
d
r
e
c
a
l
l
,
”
P
a
t
t
e
rn
Re
c
o
g
n
i
t
i
o
n
,
v
o
l
.
1
0
2
,
p
.
1
0
7
2
5
0
,
J
u
n
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
a
t
c
o
g
.
2
0
2
0
.
1
0
7
2
5
0
.
[
2
2
]
A
.
A
r
g
e
n
t
e
-
G
a
r
r
i
d
o
,
C
.
Z
u
h
e
r
o
s,
M
.
V
.
L
u
z
ó
n
,
a
n
d
F
.
H
e
r
r
e
r
a
,
“
A
n
i
n
t
e
r
p
r
e
t
a
b
l
e
c
l
i
e
n
t
d
e
c
i
si
o
n
t
r
e
e
a
g
g
r
e
g
a
t
i
o
n
p
r
o
c
e
ss
f
o
r
f
e
d
e
r
a
t
e
d
l
e
a
r
n
i
n
g
,
”
I
n
f
o
rm
a
t
i
o
n
S
c
i
e
n
c
e
s
,
v
o
l
.
6
9
4
,
p
.
1
2
1
7
1
1
,
M
a
r
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
n
s
.
2
0
2
4
.
1
2
1
7
1
1
.
[
2
3
]
M
.
C
z
a
j
k
o
w
s
k
i
a
n
d
M
.
K
r
e
t
o
w
s
k
i
,
“
D
e
c
i
s
i
o
n
t
r
e
e
u
n
d
e
r
f
i
t
t
i
n
g
i
n
m
i
n
i
n
g
o
f
g
e
n
e
e
x
p
r
e
ss
i
o
n
d
a
t
a
.
A
n
e
v
o
l
u
t
i
o
n
a
r
y
m
u
l
t
i
-
t
e
st
t
r
e
e
a
p
p
r
o
a
c
h
,
”
Ex
p
e
rt
S
y
s
t
e
m
s
w
i
t
h
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
3
7
,
p
p
.
3
9
2
–
4
0
4
,
D
e
c
.
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
sw
a
.
2
0
1
9
.
0
7
.
0
1
9
.
[
2
4
]
J.
L.
A
n
d
r
e
w
s
,
“
A
d
d
r
e
ssi
n
g
o
v
e
r
f
i
t
t
i
n
g
a
n
d
u
n
d
e
r
f
i
t
t
i
n
g
i
n
G
a
u
ss
i
a
n
mo
d
e
l
-
b
a
se
d
c
l
u
st
e
r
i
n
g
,
”
C
o
m
p
u
t
a
t
i
o
n
a
l
S
t
a
t
i
st
i
c
s
&
D
a
t
a
An
a
l
y
si
s
,
v
o
l
.
1
2
7
,
p
p
.
1
6
0
–
1
7
1
,
N
o
v
.
2
0
1
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
s
d
a
.
2
0
1
8
.
0
5
.
0
1
5
.
[
2
5
]
R
.
E
l
S
h
a
w
i
,
M
.
B
a
h
ma
n
,
a
n
d
S
.
S
a
k
r
,
“
T
o
t
u
n
e
o
r
n
o
t
t
o
t
u
n
e
?
A
n
a
p
p
r
o
a
c
h
f
o
r
r
e
c
o
m
me
n
d
i
n
g
i
m
p
o
r
t
a
n
t
h
y
p
e
r
p
a
r
a
me
t
e
r
s
f
o
r
c
l
a
ss
i
f
i
c
a
t
i
o
n
a
n
d
c
l
u
st
e
r
i
n
g
a
l
g
o
r
i
t
h
ms,
”
Fu
t
u
r
e
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
.
1
6
3
,
p
.
1
0
7
5
2
4
,
F
e
b
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
f
u
t
u
r
e
.
2
0
2
4
.
1
0
7
5
2
4
.
[
2
6
]
S
.
B
ö
s,
“
S
t
a
t
i
st
i
c
a
l
mec
h
a
n
i
c
s
a
p
p
r
o
a
c
h
t
o
e
a
r
l
y
s
t
o
p
p
i
n
g
a
n
d
w
e
i
g
h
t
d
e
c
a
y
,
”
P
h
y
si
c
a
l
R
e
v
i
e
w
E
,
v
o
l
.
5
8
,
n
o
.
1
,
p
p
.
8
3
3
–
8
4
4
,
J
u
l
.
1
9
9
8
,
d
o
i
:
1
0
.
1
1
0
3
/
P
h
y
s
R
e
v
E.
5
8
.
8
3
3
.
[
2
7
]
H
.
W
u
a
n
d
X
.
G
u
,
“
T
o
w
a
r
d
s d
r
o
p
o
u
t
t
r
a
i
n
i
n
g
f
o
r
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s
,
”
N
e
u
r
a
l
N
e
t
w
o
rks
,
v
o
l
.
7
1
,
p
p
.
1
–
1
0
,
N
o
v
.
2
0
1
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
n
e
u
n
e
t
.
2
0
1
5
.
0
7
.
0
0
7
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Im
a
n
e
Ze
r
o
u
a
l
S
h
e
is
a
d
a
ta
e
n
g
in
e
e
r
c
u
rre
n
tl
y
p
u
rsu
i
n
g
a
P
h
.
D.
in
c
o
m
p
u
ter
sc
ien
c
e
a
t
th
e
Re
se
a
rc
h
La
b
o
ra
to
r
y
o
f
I
n
fo
rm
a
ti
o
n
S
y
ste
m
s
a
n
d
S
o
f
twa
re
En
g
i
n
e
e
rin
g
(S
IG
L)
,
Un
iv
e
rsity
Ab
d
e
lma
lek
Essa
a
d
i,
Na
ti
o
n
a
l
S
c
h
o
o
l
o
f
Ap
p
li
e
d
S
c
ien
c
e
s
-
Teto
u
a
n
,
M
o
r
o
c
c
o
.
S
h
e
h
o
l
d
s
a
n
e
n
g
in
e
e
rin
g
d
e
g
re
e
in
i
n
fo
rm
a
ti
o
n
sy
ste
m
s
a
n
d
d
e
c
isio
n
su
p
p
o
rt
fr
o
m
th
e
Na
ti
o
n
a
l
S
c
h
o
o
l
o
f
A
p
p
l
ied
S
c
ien
c
e
s
in
M
o
ro
c
c
o
a
n
d
a
m
a
ste
r’s
d
e
g
re
e
in
b
ig
d
a
ta
a
n
d
m
a
c
h
in
e
lea
rn
in
g
fr
o
m
th
e
Un
iv
e
rsit
y
o
f
L
il
le,
F
ra
n
c
e
.
He
r
re
se
a
r
c
h
in
tere
sts
in
c
lu
d
e
m
a
c
h
in
e
lea
rn
in
g
,
in
tern
e
t
o
f
th
in
g
s
(Io
T)
a
p
p
l
ica
ti
o
n
s,
b
ig
d
a
ta
a
n
a
ly
ti
c
s,
d
a
ta
e
n
g
in
e
e
rin
g
,
a
n
d
sc
a
lab
le
d
a
ta
p
ro
c
e
ss
in
g
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t:
ima
n
e
.
z
e
ro
u
a
l1
@e
tu
.
u
a
e
.
a
c
.
m
a
.
J
a
b
e
r
E
l
Bo
u
h
d
i
d
i
is
a
n
HD
R
P
ro
fe
ss
o
r
o
f
Co
m
p
u
ter
S
c
ie
n
c
e
a
t
th
e
S
IGL
Lab
o
ra
to
r
y
,
U
n
iv
e
rsit
y
Ab
d
e
lma
lek
Essa
a
d
i,
Na
ti
o
n
a
l
S
c
h
o
o
l
o
f
Ap
p
li
e
d
S
c
ien
c
e
s
-
Teto
u
a
n
-
M
o
ro
c
c
o
.
His
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
we
b
se
m
a
n
ti
c
,
m
u
lt
i
-
a
g
e
n
ts’
sy
ste
m
s,
e
-
lea
rn
i
n
g
a
d
a
p
ti
v
e
sy
ste
m
s
a
n
d
b
ig
d
a
ta.
H
e
h
a
s
se
v
e
ra
l
p
a
p
e
rs
i
n
in
ter
n
a
ti
o
n
a
l
c
o
n
fe
re
n
c
e
s
a
n
d
jo
u
rn
a
ls.
He
c
a
n
b
e
c
o
n
tac
ted
a
t:
jab
e
r.
e
lb
o
u
h
d
id
i@
u
a
e
.
a
c
.
m
a
.
Evaluation Warning : The document was created with Spire.PDF for Python.