I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
p
ute
r
E
ng
in
ee
ring
(
I
J
E
CE
)
Vo
l.
11
,
No
.
4
,
A
u
g
u
s
t
2021
,
p
p
.
3
4
8
3
~
3
4
9
1
I
SS
N:
2
0
8
8
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v
1
1
i
4
.
pp
3
4
8
3
-
3
4
9
1
3483
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
Big
data
t
ra
ff
i
c
ma
na
g
em
ent
in
v
eh
icula
r ad
-
ho
c n
et
w
o
rk
T
a
nta
o
ui M
o
ua
d
1
,
L
a
a
na
o
ui
M
y
Driss
2
,
K
a
bil
M
us
t
a
ph
a
3
1
,3
Ha
ss
a
n
II
Un
iv
e
rsity
,
M
o
h
a
m
m
e
d
ia,
M
o
r
o
c
c
o
2
Ca
d
i
Ay
y
a
d
Un
iv
e
rsit
y
,
M
a
rra
k
e
c
h
,
M
o
ro
c
c
o
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Au
g
5
,
2
0
20
R
ev
i
s
ed
Dec
1
9
,
20
20
A
cc
ep
ted
J
an
1
9
,
2
0
21
T
o
d
a
y
,
th
e
w
o
rld
h
a
s
e
x
p
e
rien
c
e
d
a
n
e
w
tren
d
w
it
h
re
g
a
rd
to
d
a
ta
s
y
ste
m
m
a
n
a
g
e
m
e
n
t,
trad
it
i
o
n
a
l
d
a
tab
a
se
m
a
n
a
g
e
m
e
n
t
to
o
ls
h
a
v
e
b
e
c
o
m
e
o
u
t
d
a
ted
a
n
d
th
e
y
w
il
l
n
o
lo
n
g
e
r
b
e
a
b
le
to
p
ro
c
e
ss
th
e
m
a
s
s
o
f
d
a
ta
g
e
n
e
ra
ted
b
y
d
if
fe
re
n
t
s
y
ste
m
s,
th
a
t'
s
w
h
y
b
ig
d
a
ta
is
th
e
re
to
p
ro
c
e
ss
th
is
m
a
ss
o
f
d
a
ta
to
b
rin
g
o
u
t
c
ru
c
ial
i
n
f
o
rm
a
ti
o
n
h
id
d
e
n
in
th
is
d
a
ta,
a
n
d
w
it
h
o
u
t
b
ig
d
a
ta
tec
h
n
o
l
o
g
ies
th
e
trea
tme
n
t
is
v
e
r
y
d
iff
icu
lt
to
m
a
n
a
g
e
;
a
m
o
n
g
th
e
d
o
m
a
in
s
th
a
t
u
se
s
b
ig
d
a
ta
tec
h
n
o
l
o
g
ies
is
v
e
h
icu
lar
a
d
-
h
o
c
n
e
tw
o
rk
to
m
a
n
a
g
e
th
e
ir
v
o
lu
m
in
o
u
s
d
a
ta.
I
n
t
h
is
a
rti
c
le,
w
e
e
st
a
b
li
sh
i
n
t
h
e
f
irst
ste
p
a
m
e
th
o
d
t
h
a
t
a
ll
o
w
to
d
e
tec
t
a
n
o
m
a
li
e
s
o
r
a
c
c
i
d
e
n
ts
w
it
h
in
t
h
e
ro
a
d
a
n
d
c
o
m
p
u
t
e
th
e
ti
m
e
sp
e
n
t
in
e
a
c
h
ro
a
d
se
c
ti
o
n
in
re
a
l
ti
m
e
,
w
h
ich
p
e
rm
it
u
s
to
o
b
tain
a
d
a
tab
a
se
h
a
v
in
g
th
e
e
stim
a
ted
ti
m
e
sp
e
n
t
in
a
ll
se
c
ti
o
n
s
in
re
a
l
ti
m
e
,
th
is
w
i
ll
se
rv
e
u
s
to
se
n
d
t
o
t
h
e
v
e
h
icle
s
th
e
rig
h
t
e
stim
a
ted
ti
m
e
o
f
a
rriv
a
l
a
ll
a
lo
n
g
t
h
e
ir
jo
u
r
n
e
y
a
n
d
th
e
o
p
ti
m
a
l
ro
u
te
to
a
tt
a
in
th
e
ir
d
e
stin
a
ti
o
n
.
T
h
is
d
a
tab
a
se
is
u
se
f
u
l
to
u
ti
l
ize
it
li
k
e
in
p
u
ts
f
o
r
m
a
c
h
in
e
lea
rn
in
g
to
p
re
d
ict
t
h
e
p
lac
e
s
a
n
d
ti
m
e
s
w
h
e
re
th
e
p
ro
b
a
b
il
it
y
o
f
a
c
c
id
e
n
ts
is
h
ig
h
e
r.
T
h
e
e
x
p
e
rime
n
tal
re
su
lt
s
p
ro
v
e
th
a
t
o
u
r
m
e
th
o
d
p
e
rm
it
s
u
s
to
a
v
o
id
c
o
n
g
e
stio
n
s
a
n
d
a
p
p
o
rti
o
n
th
e
lo
a
d
o
f
v
e
h
icle
s in
a
ll
ro
a
d
s e
f
f
e
c
ti
v
e
l
y
,
a
lso
it
c
o
n
tr
ib
u
tes
to
r
o
a
d
sa
f
e
t
y
.
K
ey
w
o
r
d
s
:
B
ig
d
ata
I
n
telli
g
en
t tr
an
s
p
o
r
tatio
n
s
y
s
te
m
s
Ma
ch
i
n
e
lear
n
i
n
g
T
r
af
f
ic
co
n
g
e
s
tio
n
s
p
r
ed
ictio
n
T
r
af
f
ic
m
a
n
ag
e
m
e
n
t
Veh
ic
u
lar
ad
h
o
c
n
et
w
o
r
k
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
:
T
an
tao
u
i M
o
u
ad
Dep
ar
t
m
en
t o
f
m
at
h
e
m
atic
s
an
d
ap
p
licatio
n
s
Hass
a
n
I
I
Un
i
v
er
s
it
y
,
FS
T
,
Mo
h
a
m
m
ed
ia,
Mo
r
o
cc
o
Facu
lté
d
es Sc
ien
ce
s
et
T
ec
h
n
i
q
u
es d
e
Mo
h
a
m
m
ed
ia
B
P
1
4
6
Mo
h
a
m
m
ed
ia
2
8
8
0
6
Mo
r
o
cc
o
E
m
ail:
m
o
u
ad
.
tan
tao
u
i
-
et
u
@
e
tu
.
u
n
i
v
h
2
c.
m
a
1.
I
NT
RO
D
UCT
I
O
N
T
o
d
ay
citie
s
ar
e
d
ev
elo
p
in
g
m
o
r
e
an
d
m
o
r
e
u
n
til
i
t
b
ec
o
m
es
w
h
at
w
e
ca
ll
s
m
ar
t
cit
ies,
o
u
r
g
o
al
is
to
a
m
elio
r
ate
tr
a
f
f
ic
m
a
n
ag
e
m
e
n
t
i
n
in
telli
g
en
t
tr
a
n
s
p
o
r
t
s
y
s
te
m
(
I
T
S
)
,
th
i
s
i
s
a
r
esear
ch
ar
ea
t
h
at
ca
tc
h
th
e
atten
tio
n
o
f
r
esear
ch
co
m
m
u
n
it
y
m
ai
n
l
y
in
t
h
e
f
ield
o
f
c
o
m
p
u
ter
s
cie
n
ce
b
ec
au
s
e
o
f
s
o
cial
an
d
ec
o
n
o
m
ic
ch
alle
n
g
e
s
.
T
h
e
d
iv
er
s
it
y
o
f
d
ata
s
o
u
r
ce
s
p
r
o
d
u
ce
s
v
o
lu
m
in
o
u
s
d
ata
d
escr
ib
ed
b
y
its
d
if
f
er
e
n
t
t
y
p
e
a
n
d
v
elo
cit
y
,
t
h
o
s
e
d
ata
h
a
v
e
b
ec
o
m
e
d
i
f
f
icu
lt
to
h
a
n
d
le,
in
t
h
i
s
co
n
tex
t,
b
ig
d
ata
tech
n
o
lo
g
i
es
is
t
h
e
s
o
lu
t
io
n
to
h
an
d
le
th
i
s
m
as
s
i
v
e
d
ata
i
n
r
e
al
ti
m
e,
o
n
e
o
f
t
h
e
r
esear
c
h
ar
ea
s
t
h
at
r
el
y
o
n
b
ig
d
ata
tech
n
o
lo
g
ies
i
s
v
eh
ic
u
lar
ad
-
h
o
c
n
et
w
o
r
k
f
o
r
m
a
n
a
g
i
n
g
th
eir
v
o
lu
m
i
n
o
u
s
d
ata.
Ou
r
ci
t
ies h
a
v
e
e
x
p
er
ien
ce
d
a
g
r
o
w
in
g
tr
en
d
o
f
n
o
n
-
s
to
p
v
eh
ic
les.
T
h
e
b
u
l
k
y
i
n
cr
ea
s
e
i
n
v
e
h
icle
s
n
u
m
b
er
h
as
e
n
g
en
d
er
ed
lo
t
o
f
s
o
cial
an
d
en
v
ir
o
n
m
en
tal
p
r
o
b
lem
s
i
n
ev
er
y
d
a
y
li
f
e
w
i
th
i
n
c
ities
li
k
e
m
an
y
tr
af
f
ic
j
a
m
s
,
r
o
ad
ac
cid
en
ts
a
n
d
b
r
ea
th
ta
k
i
n
g
air
p
o
llu
tio
n
,
in
th
is
d
ir
ec
ti
o
n
,
I
T
S
is
r
esear
ch
d
o
m
ai
n
o
f
in
ter
es
t
to
th
e
r
esear
ch
co
m
m
u
n
it
y
p
r
in
c
ip
all
y
i
n
co
m
p
u
ter
s
cien
ce
d
o
m
ai
n
d
u
e
to
c
h
alle
n
g
e
s
r
ais
ed
.
Ou
r
g
o
al
is
to
f
i
n
d
o
u
t
a
w
a
y
f
o
r
p
r
ed
ictin
g
tr
af
f
ic
d
en
s
it
y
o
n
all
r
o
ad
s
an
d
v
ar
io
u
s
citie
s
w
h
ic
h
w
o
u
ld
p
er
m
it
u
s
a
f
ter
w
ar
d
to
p
r
ed
ict
p
lace
s
w
h
er
e
t
h
e
p
r
o
b
ab
ilit
y
o
f
ac
cid
en
ts
is
h
ig
h
.
T
o
attain
th
is
g
o
al,
w
e
h
a
v
e
to
estab
lis
h
a
r
o
ad
d
en
s
it
y
p
r
ed
ictio
n
m
et
h
o
d
u
tili
zi
n
g
v
o
lu
m
i
n
o
u
s
d
ata
g
at
h
er
ed
d
u
r
in
g
v
e
h
icle
-
v
eh
ic
le
an
d
v
e
h
icle
-
i
n
f
r
as
tr
u
ct
u
r
e
co
m
m
u
n
ic
atio
n
[
1
]
.
Veh
icu
lar
ad
h
o
c
n
et
w
o
r
k
(
V
ANE
T
s
)
h
as
m
ad
e
s
i
n
ce
t
h
eir
b
ir
th
,
an
in
cr
e
asi
n
g
l
y
ad
v
an
ce
m
e
n
t.
M
an
y
s
ta
n
d
ar
d
s
,
ap
p
licatio
n
s
an
d
m
eth
o
d
s
o
f
d
ata
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
11
,
No
.
4
,
A
u
g
u
s
t 2
0
2
1
:
3
4
8
3
-
3491
3484
p
r
o
ce
s
s
in
g
h
a
v
e
b
ee
n
e
s
tab
lis
h
ed
to
r
e
m
ed
y
t
h
e
c
h
ar
ac
ter
is
tics
o
f
th
is
n
e
w
g
en
d
er
o
f
n
et
w
o
r
k
s
.
T
h
e
m
ai
n
ch
alle
n
g
e
s
in
cr
ea
s
e
esp
ec
iall
y
f
r
o
m
th
e
h
i
g
h
m
o
b
ilit
y
o
f
v
e
h
icles
a
n
d
th
e
s
p
atio
-
t
e
m
p
o
r
al
d
iv
er
s
it
y
o
f
tr
af
f
ic
d
en
s
it
y
.
A
m
o
n
g
t
h
e
m
ai
n
co
m
p
o
n
en
ts
o
f
t
h
e
ar
ch
itect
u
r
e
o
f
VANE
T
ar
e
on
-
b
o
ar
d
u
n
it
(
OB
U)
w
h
ic
h
ar
e
o
n
m
o
b
ile
n
o
d
e
f
o
r
f
ac
ilit
ati
n
g
c
o
m
m
u
n
icatio
n
w
it
h
o
t
h
er
m
o
b
ile
n
o
d
es
s
u
c
h
a
s
v
eh
ic
les
a
n
d
f
i
x
ed
s
tatio
n
s
li
k
e
r
o
ad
s
id
e
u
n
its
v
ia
d
ed
icate
d
s
h
o
r
t
-
r
an
g
e
co
m
m
u
n
ica
tio
n
s
(
DSR
C
)
an
d
th
e
ab
ilit
y
to
co
m
m
u
n
icate
u
tili
zi
n
g
ce
llu
lar
r
ad
io
n
et
w
o
r
k
s
li
k
e
G
SM,
4
G,
W
i
-
Fi
a
n
d
W
iM
AX.
A
l
s
o
,
t
h
er
e
ar
e
r
o
ad
-
s
id
e
u
n
it
s
(
R
SU
s
)
w
h
ic
h
ar
e
th
e
b
ase
s
tatio
n
s
th
a
t
h
a
n
d
le
VANE
T
ap
p
licatio
n
s
an
d
m
a
n
ag
e
ac
tio
n
s
to
s
h
ar
e
an
d
p
r
o
ce
s
s
in
f
o
r
m
at
io
n
an
d
also
d
is
s
e
m
in
ate
d
ata,
p
r
o
v
id
es
tr
af
f
ic
d
ir
ec
to
r
ies,
b
eh
av
e
as
lo
ca
tio
n
s
er
v
er
s
,
an
d
co
n
n
ec
t
to
th
e
I
n
ter
n
et
an
d
ex
ter
n
al
ce
n
tr
alize
d
o
r
d
is
tr
ib
u
ted
s
er
v
er
s
.
A
n
d
ce
n
tr
alize
d
clo
u
d
w
h
ic
h
i
s
a
g
e
n
d
er
o
f
co
m
p
u
ter
ar
c
h
ite
ct
u
r
e
w
h
er
e
all
o
r
m
o
s
t
o
f
t
h
e
tr
ea
t
m
e
n
t
o
r
co
m
p
u
tatio
n
i
s
p
r
o
ce
s
s
ed
o
n
s
u
c
h
a
ce
n
tr
al
s
er
v
er
.
C
e
n
tr
alize
d
co
m
p
u
ti
n
g
e
n
ab
les t
h
e
d
ep
lo
y
m
en
t o
f
all
I
T
r
eso
u
r
ce
s
,
ad
m
i
n
is
tr
atio
n
an
d
m
an
a
g
e
m
en
t o
f
th
e
ce
n
tr
al
s
er
v
er
.
2.
RE
L
AT
E
D
WO
RK
S
A
ct
u
all
y
,
V
A
NE
T
en
v
ir
o
n
m
e
n
t
is
b
ec
o
m
i
n
g
as
a
b
ig
d
ata
p
r
o
b
lem
.
T
h
er
ef
o
r
e,
v
ar
io
u
s
b
i
g
d
ata
to
o
ls
ca
n
b
e
u
s
ed
to
m
a
n
a
g
e
d
ata
f
r
o
m
V
A
NE
T
s
f
o
r
i
m
p
r
o
v
i
n
g
tr
af
f
ic
m
a
n
ag
e
m
e
n
t.
On
e
o
f
t
h
e
i
m
p
o
r
tan
t
w
o
r
k
s
th
at
i
n
ter
est
u
s
w
a
s
ab
o
u
t
i
m
p
le
m
en
t
in
g
V
A
NE
T
Dij
k
s
tr
a
alg
o
r
ith
m
[
2
]
,
th
e
y
i
m
p
le
m
e
n
t
ed
th
e
alg
o
r
it
h
m
in
H
ad
o
o
p
M
ap
R
ed
u
ce
en
v
ir
o
n
m
en
t
an
d
th
e
co
m
p
ar
ed
it
to
a
d
i
j
ik
s
t
r
a
i
m
p
le
m
en
ted
in
a
s
i
m
p
le
N
et
B
ea
n
s
.
An
o
th
er
w
o
r
k
w
h
ic
h
is
v
er
y
i
m
p
o
r
ta
n
t
is
d
etec
t
in
g
w
it
h
in
t
h
e
V
ANE
T
n
et
w
o
r
k
th
e
v
eh
ic
les
t
h
at
ca
n
p
r
o
ce
ed
as
i
n
f
o
r
m
atio
n
h
u
b
s
w
h
o
s
e
r
o
le
is
to
g
at
h
er
i
n
f
o
r
m
atio
n
f
r
o
m
t
h
e
n
et
w
o
r
k
a
n
d
s
h
ar
e
it.
R
an
k
i
n
g
al
g
o
r
ith
m
i
s
d
ev
elo
p
ed
in
th
is
co
n
te
x
t
lik
e
f
o
r
ex
a
m
p
le
I
n
f
o
R
an
k
[
3
]
.
Sp
ee
d
p
r
ed
ictio
n
alg
o
r
ith
m
s
ar
e
ess
en
tial
f
o
r
m
an
a
g
i
n
g
tr
af
f
ic
in
t
h
e
f
ie
ld
o
f
in
tell
ig
e
n
t
tr
an
s
p
o
r
t
s
y
s
te
m
;
B
ig
d
ata
b
ased
d
ee
p
lear
n
in
g
s
p
ee
d
p
r
ed
ictio
n
(
B
DDL
-
SP
)
[
4
]
is
a
s
p
ee
d
p
r
e
d
ictio
n
alg
o
r
it
h
m
th
at
ca
n
p
r
ed
ict
th
e
s
p
ee
d
o
f
a
v
e
h
icle
i
n
h
ig
h
w
a
y
s
a
n
d
u
r
b
a
n
ar
ea
s
r
o
ad
n
et
w
o
r
k
s
.
T
h
er
e
ar
e
n
e
w
s
y
s
te
m
s
to
m
an
a
g
e
v
o
l
u
m
in
o
u
s
Data
g
e
n
er
ated
in
r
ea
l
-
ti
m
e
b
y
d
if
f
er
en
t
ag
en
t
s
u
c
h
as
v
e
h
icles
an
d
r
o
ad
s
id
e
u
n
it
s
(
R
SUs
)
en
s
u
r
i
n
g
a
r
ap
id
tr
ea
tm
e
n
t
o
f
d
ata
in
th
e
p
u
r
p
o
s
e
to
m
a
k
e
r
o
ad
m
a
n
a
g
e
m
e
n
t
d
ec
is
io
n
s
.
T
h
o
s
e
n
e
w
s
y
s
te
m
s
ca
n
b
e
u
tili
ze
d
f
o
r
ex
a
m
p
le
to
co
m
p
u
te
t
h
e
e
s
ti
m
ated
ar
r
iv
a
l
ti
m
e
o
f
v
e
h
icle
s
o
r
p
r
ed
ict
ac
cid
en
ts
a
n
d
co
n
g
esti
o
n
s
w
i
th
th
e
h
elp
o
f
n
ai
v
e
b
a
y
es
an
d
d
is
tr
ib
u
ted
r
an
d
o
m
f
o
r
est
(
D
R
F)
[
5
]
.
On
e
o
f
t
h
ese
s
y
s
te
m
s
i
s
t
h
e
L
a
m
b
d
a
ar
ch
itect
u
r
e
(
L
A
)
[
6
]
w
h
ic
h
is
d
ata
tr
ea
t
m
e
n
t
ar
ch
itect
u
r
e
th
at
allo
w
s
h
an
d
li
n
g
m
as
s
i
v
e
d
ata
in
b
atch
an
d
in
r
ea
l
ti
m
e.
I
n
ar
ti
cle
[
7
]
,
an
ex
p
er
i
m
e
n
t
o
n
I
T
S
en
v
ir
o
n
m
e
n
t
w
as
i
m
p
le
m
en
te
d
to
ass
ess
th
e
tr
af
f
ic
d
en
s
it
y
esti
m
atio
n
ab
o
u
t
d
if
f
er
en
t
citi
es
o
n
d
if
f
er
e
n
t
r
o
ad
s
an
d
ca
r
r
y
o
u
t
a
co
m
p
ar
ati
v
e
e
v
alu
a
tio
n
r
el
y
i
n
g
o
n
th
a
t
p
ar
am
eter
.
I
n
ar
ticle
[
8
]
,
th
e
a
u
t
h
o
r
s
s
u
g
g
est
a
s
y
s
te
m
to
s
en
d
w
i
th
d
y
n
a
m
ic
m
a
n
n
er
r
ep
o
r
ts
ag
ain
s
t
s
elf
is
h
a
n
d
m
a
licio
u
s
v
e
h
icle
s
.
T
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
u
tili
ze
s
a
n
en
cr
y
p
tio
n
m
ec
h
an
i
s
m
to
ex
c
h
an
g
e
m
e
s
s
a
g
es.
I
n
ar
ticle
[
9
]
,
in
th
e
f
ir
s
t
h
a
n
d
,
au
th
o
r
s
p
r
o
p
o
s
ed
ar
ch
itectu
r
e
f
o
r
lar
g
e
o
n
-
v
eh
icle
d
atasets
w
h
ich
ad
m
in
i
s
t
er
ce
n
tr
alize
d
ac
ce
s
s
to
m
as
s
i
v
e
d
ata.
T
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
in
te
g
r
ates
ce
n
tr
alize
d
d
ata
s
to
r
ag
e
an
d
p
r
o
ce
s
s
in
g
m
ec
h
a
n
i
s
m
,
an
d
a
d
is
tr
ib
u
ted
d
ata
s
to
r
ag
e
m
ec
h
an
is
m
f
o
r
r
ea
l
-
ti
m
e
p
r
o
ce
s
s
i
n
g
a
n
d
an
a
l
y
s
i
s
.
I
n
ar
ticle
[
1
0
]
,
a
r
o
u
ti
n
g
p
r
o
to
co
l
w
as
p
r
o
p
o
s
ed
w
h
ic
h
i
s
b
ased
o
n
r
o
ad
v
eh
ic
le
d
en
s
it
y
in
r
ea
l
t
i
m
e.
T
h
e
co
m
p
u
tatio
n
o
f
r
o
ad
d
en
s
it
y
is
b
ased
o
n
ea
ch
v
e
h
icle
to
w
h
ic
h
it
b
elo
n
g
s
b
y
u
tili
zi
n
g
tag
m
e
s
s
a
g
es a
n
d
th
e
r
o
ad
in
f
o
r
m
atio
n
tab
le.
I
n
ar
ticle
[
1
1
]
,
th
e
s
y
n
th
et
i
c
m
i
n
o
r
it
y
o
v
er
s
a
m
p
l
in
g
tec
h
n
iq
u
e
i
s
u
s
ed
f
o
r
r
ec
o
n
s
tr
u
cti
n
g
th
e
ex
p
er
i
m
e
n
tal
d
ataset,
t
h
e
m
i
n
o
r
ity
s
a
m
p
le
s
i
n
th
e
s
t
u
d
y
d
a
taset
w
er
e
o
v
er
s
a
m
p
led
an
d
n
e
w
s
a
m
p
les
w
er
e
s
y
n
t
h
esized
f
o
r
co
m
p
leti
n
g
t
h
e
m
is
s
in
g
d
ata.
I
n
ar
ticle
[
1
2
]
,
in
th
e
f
ir
s
t
h
a
n
d
,
th
e
y
r
ev
ie
w
ed
V
A
NE
T
tech
n
o
lo
g
ies
f
o
r
ef
f
icie
n
t
an
d
r
eliab
le
d
ata
tr
an
s
m
i
s
s
io
n
.
An
d
th
e
n
,
th
e
y
p
r
esen
ted
t
h
e
m
eth
o
d
s
u
s
ed
b
y
B
i
g
Data
f
o
r
s
t
u
d
y
in
g
t
h
e
c
h
ar
ac
t
er
is
tics
o
f
V
A
NE
T
s
an
d
i
m
p
r
o
v
in
g
t
h
eir
p
er
f
o
r
m
a
n
ce
.
I
n
ar
ticle
[
1
3
]
,
a
n
e
w
r
o
u
tin
g
p
r
o
to
co
l
is
p
r
o
p
o
s
ed
w
h
ic
h
u
s
es
(
li
n
k
g
u
ar
a
n
tee)
an
d
(
f
o
r
w
ar
d
in
g
m
o
v
e
m
en
t
d
is
tan
ce
)
a
n
o
d
e
to
s
elec
t
th
e
n
e
x
t
h
o
p
n
o
d
e.
T
h
ey
u
s
ed
th
e
w
ei
g
h
ted
f
u
n
ctio
n
b
y
n
o
r
m
alizi
n
g
all
q
u
alit
y
-
of
-
s
er
v
ice
m
etr
ic
s
.
I
n
ar
ticle
[
1
4
]
,
th
e
H2
O
an
d
W
E
KA
e
x
tr
ac
tio
n
to
o
ls
ar
e
u
s
ed
f
o
r
ev
alu
ati
n
g
f
iv
e
c
lass
if
ier
s
o
n
t
w
o
lar
g
e
s
et
s
o
f
w
o
r
k
s
h
o
p
d
at
a.
T
h
e
class
i
f
ier
s
u
t
ilized
ar
e:
A
d
ab
o
o
s
tM1
,
C
4
.
5
,
r
an
d
o
m
f
o
r
est
(
R
F),
n
a
i
v
e
b
a
y
e
s
,
(
w
i
th
th
e
C
4
.
5
b
asic
class
i
f
ier
)
an
d
B
ag
g
i
n
g
.
T
h
e
s
elec
tio
n
o
f
attr
ib
u
tes
i
s
ap
p
lied
an
d
also
th
e
p
r
o
b
lem
o
f
cla
s
s
i
m
b
alan
ce
i
s
tack
led
.
T
h
eir
ex
p
er
ien
ce
s
s
h
o
w
ed
th
at
n
ai
v
e
b
ay
es
(
NB
)
g
av
e
t
h
e
o
p
ti
m
a
l
r
esu
lts
,
w
it
h
t
h
e
s
h
o
r
test
ca
lc
u
latio
n
ti
m
e
a
n
d
a
p
r
ac
tical
ar
ea
u
n
d
er
t
h
e
cu
r
v
e
(
A
U
C
)
a
n
d
ac
c
u
r
ac
y
(
AC
C
)
.
I
n
p
ap
er
[
1
5
]
,
n
a
m
ed
d
ata
n
et
w
o
r
k
i
n
g
(
ND
N
)
is
n
e
w
I
n
ter
n
et
ar
ch
itec
t
u
r
e
h
a
s
b
ee
n
es
tab
lis
h
ed
to
s
ettle
t
h
e
V
A
NE
T
n
et
w
o
r
k
s
w
ea
k
n
e
s
s
es
a
n
d
to
m
an
a
g
e
co
u
n
tle
s
s
ap
p
licatio
n
s
s
u
c
h
as
o
b
j
ec
t
tr
ac
k
in
g
,
tr
ac
k
i
n
g
a
m
o
b
ile
v
eh
ic
le
an
d
h
a
n
d
li
n
g
an
e
f
f
ec
tiv
e
co
m
m
u
n
icatio
n
c
h
a
n
n
el
i
n
t
h
e
V
A
NE
T
.
I
n
ar
ticle
[
1
6
]
,
th
is
r
esear
c
h
p
r
o
j
ec
t
p
r
o
p
o
s
es
an
e
f
f
icien
t
an
d
s
ec
u
r
e
d
ata
co
llectio
n
tec
h
n
iq
u
e
t
h
at
en
s
u
r
es
t
h
e
s
ec
u
r
it
y
an
d
co
n
f
id
en
tial
it
y
o
f
d
ata
ex
ch
a
n
g
ed
b
et
w
ee
n
v
e
h
icle
s
an
d
R
SU
s
.
I
t
i
s
b
ased
o
n
as
y
m
m
etr
ic
e
n
cr
y
p
tio
n
t
h
at
en
s
u
r
es
s
ec
u
r
e
co
m
m
u
n
icatio
n
b
et
w
ee
n
v
e
h
i
cles
an
d
R
SUs
.
I
n
t
h
is
tec
h
n
i
q
u
e,
s
ec
u
r
e
au
t
h
e
n
ticatio
n
is
estab
lis
h
ed
b
et
w
ee
n
th
e
v
e
h
icle
an
d
th
e
R
SU
b
ef
o
r
e
th
e
R
SU
b
eg
i
n
s
to
co
llect
th
e
v
e
h
icle
d
ata.
I
n
ar
ticle
[
1
7
]
,
b
y
s
ig
n
i
f
ican
tl
y
ex
p
an
d
in
g
th
e
s
ca
le
o
f
t
h
e
n
et
w
o
r
k
an
d
p
er
f
o
r
m
in
g
r
ea
l
-
ti
m
e
an
d
lo
n
g
-
ter
m
i
n
f
o
r
m
atio
n
p
r
o
ce
s
s
in
g
,
v
eh
ic
u
lar
VANE
T
s
ar
e
m
o
v
in
g
to
w
ar
d
s
th
e
I
n
ter
n
et
o
f
v
e
h
icle
s
(
I
o
V)
,
w
h
ich
p
r
o
m
is
es
e
f
f
ec
t
iv
e
a
n
d
i
n
telli
g
e
n
t
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:
2
0
8
8
-
8708
B
ig
d
a
ta
tr
a
ffic m
a
n
a
g
eme
n
t i
n
ve
h
icu
la
r
a
d
-
h
o
c
n
etw
o
r
k
(
T
a
n
ta
o
u
i
Mo
u
a
d
)
3485
p
r
o
s
p
ec
ts
f
o
r
a
f
u
tu
r
e
tr
an
s
p
o
r
t
s
y
s
te
m
.
On
t
h
e
o
th
er
h
a
n
d
,
v
eh
icles
ar
e
n
o
t
j
u
s
t
co
n
s
u
m
er
s
;
th
e
y
also
g
e
n
er
ate
h
u
g
e
a
m
o
u
n
t
s
an
d
t
y
p
es
o
f
d
ata,
ca
lled
b
ig
d
ata
.
I
n
th
is
ar
ticle,
th
e
y
f
ir
s
t
ex
a
m
i
n
ed
th
e
r
elatio
n
s
h
ip
b
et
w
ee
n
I
o
V
an
d
b
ig
d
ata
i
n
t
h
e
v
eh
ic
u
lar
en
v
ir
o
n
m
e
n
t,
m
ai
n
l
y
o
n
h
o
w
I
o
V
s
u
p
p
o
r
ts
tr
an
s
m
is
s
io
n
,
s
to
r
ag
e,
co
m
p
u
tin
g
u
s
i
n
g
b
ig
d
ata
an
d
h
o
w
I
o
V
p
u
lls
b
en
e
f
it
o
f
b
ig
d
ata
f
o
r
ch
ar
ac
ter
izatio
n
,
p
er
f
o
r
m
a
n
ce
ev
alu
atio
n
an
d
b
ig
d
ata
s
u
p
p
o
r
t
f
o
r
a
co
m
m
u
n
icat
io
n
p
r
o
to
co
l
d
esig
n
.
I
n
ar
ticle
[
1
8
]
,
au
to
n
o
m
o
u
s
v
e
h
icle
(
A
V
)
tech
n
o
lo
g
y
lead
s
to
m
a
n
y
ec
o
n
o
m
ic
an
d
s
o
cial
b
en
ef
it
s
an
d
i
m
p
ac
ts
.
T
h
e
tr
ajec
to
r
y
p
lan
n
i
n
g
is
o
n
e
o
f
t
h
e
ess
e
n
tial
an
d
cr
itical
task
s
o
f
d
r
iv
i
n
g
t
h
e
a
u
to
n
o
m
o
u
s
v
e
h
icle.
I
n
t
h
is
ar
ticle,
t
h
e
y
tac
k
led
t
h
e
p
r
o
b
le
m
o
f
tr
aj
ec
to
r
y
p
lan
n
i
n
g
f
o
r
f
u
ll
y
a
u
to
n
o
m
o
u
s
v
eh
icle
s
.
T
h
e
co
n
s
tr
u
cted
m
eth
o
d
s
ar
e
i
n
ten
d
ed
f
o
r
au
to
n
o
m
o
u
s
v
e
h
icl
es
in
a
clo
u
d
b
ased
s
m
ar
t
v
eh
ic
le
en
v
ir
o
n
m
e
n
t.
T
h
is
ar
ticle
p
r
esen
ts
a
n
o
p
ti
m
al
an
d
s
af
e
tr
aj
ec
to
r
y
s
elec
tio
n
m
et
h
o
d
in
a
u
to
n
o
m
o
u
s
v
e
h
icles.
T
h
e
s
elec
tio
n
o
f
t
h
e
s
a
f
et
y
tr
aj
ec
to
r
y
in
th
is
w
o
r
k
is
m
a
in
l
y
b
ase
d
o
n
th
e
e
x
p
lo
itatio
n
o
f
B
i
g
D
ata
an
d
t
h
e
a
n
al
y
s
i
s
o
f
r
ea
l
-
li
f
e
ac
cid
en
t
d
ata
an
d
r
ea
l
-
ti
m
e
co
n
n
ec
ted
v
e
h
icle
d
ata.
I
n
th
e
p
ap
er
[
1
9
]
,
au
th
o
r
s
an
al
y
ze
ch
a
n
n
e
l
esti
m
atio
n
tec
h
n
iq
u
es
f
o
r
Ma
s
s
iv
e
m
u
l
tip
le
-
in
p
u
t
m
u
ltip
le
-
o
u
tp
u
t
s
y
s
te
m
s
.
T
h
e
y
d
id
a
c
o
m
p
ar
i
s
o
n
a
m
o
n
g
th
e
d
if
f
er
e
n
t
ch
a
n
n
e
l
esti
m
atio
n
t
ec
h
n
iq
u
es.
Fo
r
th
e
p
ap
er
[
2
0
]
,
th
e
y
talk
ed
ab
o
u
t
th
e
h
i
s
to
r
y
o
f
th
e
ev
o
lu
tio
n
o
f
d
ata
h
an
d
li
n
g
s
y
s
te
m
s
,
a
n
d
t
h
e
y
d
is
c
u
s
s
th
e
e
x
i
s
ti
n
g
s
tate
o
f
b
ig
d
ata
h
a
n
d
lin
g
s
y
s
te
m
s
i
n
th
e
co
n
te
x
t
o
f
d
ata
s
to
r
ag
e,
m
o
d
el,
a
n
d
q
u
er
y
en
g
in
e
s
o
f
b
ig
d
ata
h
a
n
d
li
n
g
s
y
s
te
m
s
.
I
n
th
e
ar
ticle
[
2
1
]
,
Sh
a
o
f
u
L
i
n
et
a
l.
u
s
ed
Gu
iz
h
o
u
as
an
ex
a
m
p
le
to
p
r
o
d
u
ce
a
s
p
atio
-
te
m
p
o
r
al
b
ig
d
ata
h
an
d
lin
g
s
y
s
te
m
lea
n
e
d
o
n
GI
S
b
u
s
s
in
g
tech
n
iq
u
e.
I
n
t
h
e
ar
tic
le
[
2
2
]
,
au
t
h
o
r
s
p
r
o
d
u
ce
d
an
d
cr
ea
ted
a
n
e
w
d
is
tr
ib
u
ted
b
ig
d
ata
m
an
a
g
e
m
e
n
t
s
y
s
te
m
(
DB
DM
S)
an
d
it
o
f
f
er
s
b
i
g
d
ata
r
ea
l
-
ti
m
e
g
at
h
er
i
n
g
,
s
ea
r
ch
an
d
p
er
p
etu
al
s
to
r
ag
e.
Had
o
o
p
ec
o
s
y
s
te
m
s
ee
m
to
b
e
v
er
y
i
m
p
o
r
tan
t,
i
n
t
h
e
ar
ticle
[
2
3
]
,
au
th
o
r
s
a
n
al
y
ze
th
e
Had
o
o
p
ar
ch
itectu
r
e
an
d
Had
o
o
p
ec
o
s
y
s
te
m
.
I
n
ar
ticle
[
2
4
]
,
B
r
u
n
s
w
ic
k
er
et
a
l
.
d
ev
elo
p
ed
o
n
r
esear
ch
is
s
u
e
w
h
ic
h
is
r
elate
d
to
o
p
en
d
ig
ita
l
co
llab
o
r
atio
n
an
d
estab
lis
h
ed
th
e
d
ata
an
al
y
tica
l
ch
alle
n
g
e
s
w
h
ic
h
n
ee
d
to
b
e
r
ev
ea
led
to
an
s
w
er
t
h
ese
i
m
p
o
r
tan
t
r
esear
ch
is
s
u
es.
I
n
t
h
e
p
ap
er
[
2
5
]
,
B
u
k
h
ar
i
et
a
l.
p
r
o
p
o
s
ed
a
m
eth
o
d
b
ased
o
n
b
ig
d
ata
d
e
m
o
g
r
ap
h
y
m
a
n
a
g
i
n
g
s
y
s
te
m
u
s
i
n
g
ap
ac
h
e
Had
o
o
p
p
latf
o
r
m
to
s
ettle
tr
o
u
b
les
o
f
d
e
m
o
g
r
ap
h
y
h
ig
h
r
is
i
n
g
d
ata
m
a
n
a
g
in
g
.
I
n
t
h
e
p
ap
er
[
2
6
]
Ma
lik
et
a
l
.
h
a
v
e
an
a
l
y
ze
d
t
h
e
v
ar
io
u
s
m
ec
h
an
is
m
s
o
f
r
e
s
o
u
r
ce
allo
ca
tio
n
,
m
o
d
e
s
elec
tio
n
f
o
r
u
n
d
er
l
y
in
g
co
m
m
u
n
icatio
n
s
i
n
t
h
e
s
e
n
s
e
o
f
d
ev
ice
to
d
ev
ice
an
d
c
o
o
p
er
ativ
e
co
m
m
u
n
icatio
n
te
ch
n
iq
u
es
a
n
d
t
h
e
y
estab
lis
h
a
n
e
w
tech
n
iq
u
e
L
T
E
-
A
d
v
a
n
ce
d
P
r
o
.
I
n
th
e
p
ap
er
[
2
7
]
,
au
th
o
r
s
s
ettle
t
h
e
is
s
u
e
o
f
o
v
er
ta
k
i
n
g
lar
g
er
v
eh
ic
le
b
y
co
n
s
tr
u
cti
n
g
ad
-
h
o
c
co
n
n
ec
tio
n
b
ased
o
n
5
G
tec
h
n
o
lo
g
y
w
it
h
th
e
v
eh
ic
le
to
b
e
o
v
er
tak
e
n
.
3.
RE
S
E
ARCH
M
E
T
H
O
D
3
.
1
.
Ano
m
a
ly
det
ec
t
io
n
I
n
th
i
s
p
ap
er
,
it’
s
ab
o
u
t
tr
a
f
f
i
c
m
an
a
g
e
m
e
n
t
in
r
ea
l
-
ti
m
e,
we
p
r
o
p
o
s
e
a
s
y
s
te
m
co
n
s
tr
u
ct
th
at
f
ir
s
tl
y
b
u
ild
a
b
ase
th
at
co
n
tain
t
h
e
esti
m
ated
s
p
en
d
i
n
g
ti
m
e
o
f
e
ac
h
s
ec
tio
n
o
f
all
r
o
ad
s
in
th
e
cit
y
at
t
h
e
p
r
esen
t.
Seco
n
d
l
y
,
t
h
e
m
et
h
o
d
w
ill
b
e
ab
le
to
d
etec
t
an
o
m
al
ies
i
n
t
h
e
r
o
ad
s
o
th
at,
w
it
h
t
h
e
h
elp
o
f
t
h
e
b
ase,
w
e
ca
n
co
m
p
u
te
t
h
e
ti
m
e
r
eq
u
ir
ed
to
r
ea
ch
an
y
d
esti
n
atio
n
f
r
o
m
an
y
s
o
u
r
ce
in
r
ea
l
ti
m
e.
Mo
r
e
p
r
ec
is
el
y
,
f
o
r
th
e
co
n
s
tr
u
ct
io
n
o
f
t
h
e
b
ase,
ea
ch
v
eh
icle
lo
g
s
th
e
ti
m
e
o
f
e
n
tr
y
at
t
h
e
b
eg
i
n
n
in
g
an
d
th
e
e
n
d
o
f
a
s
ec
tio
n
,
af
ter
th
at
i
t
tr
a
n
s
m
it
s
t
h
is
i
n
f
o
r
m
ati
o
n
an
d
its
id
en
ti
f
ier
(
I
D)
to
t
h
e
R
SU
i
n
o
r
d
er
to
co
m
p
u
te
t
h
e
s
p
en
d
i
n
g
ti
m
e
o
f
th
e
r
o
ad
s
ec
tio
n
.
So
,
w
e
h
av
e
th
e
tr
ac
es
o
f
ti
m
e
s
p
en
t
to
cr
o
s
s
ea
ch
s
ec
tio
n
o
f
all
v
e
h
icle
s
w
h
ic
h
w
ill
allo
w
u
s
to
h
av
e
a
b
ase
co
n
tain
in
g
t
h
e
esti
m
ated
s
p
en
d
i
n
g
t
i
m
e
o
f
al
l
th
e
r
o
ad
s
ec
tio
n
s
in
r
ea
l
ti
m
e.
T
h
is
ap
p
r
o
ac
h
is
p
r
esen
ted
in
Fig
u
r
e
1
.
A
f
ter
th
at,
w
h
e
n
a
v
e
h
icle
a
s
k
s
f
o
r
a
r
o
u
te
to
its
d
est
in
at
io
n
,
o
u
r
s
y
s
te
m
w
i
ll
b
e
ab
le
to
tr
an
s
m
it
t
h
e
r
o
u
te
to
r
ea
ch
its
d
esti
n
atio
n
to
th
e
v
e
h
icl
e
a
n
d
th
e
esti
m
ated
ar
r
iv
al
t
i
m
e
a
lo
n
g
it
s
w
a
y
.
T
h
is
ap
p
r
o
ac
h
is
p
r
esen
ted
in
Fig
u
r
e
2
.
A
n
o
t
h
er
u
ti
lit
y
o
f
t
h
i
s
b
ase,
w
e
ca
n
lo
ca
te
a
n
ac
cid
en
t
o
r
an
an
o
m
al
y
i
n
a
s
ec
tio
n
w
h
e
n
w
e
r
ec
ei
v
e
a
r
ec
en
t sp
e
n
d
in
g
ti
m
e
o
f
v
e
h
icle
s
v
er
y
b
i
g
g
er
co
m
p
ar
ed
to
w
h
at
th
er
e
is
in
th
e
b
ase.
T
h
is
ap
p
r
o
ac
h
is
p
r
esen
ted
in
Fig
u
r
e
3
.
I
n
o
th
er
w
o
r
d
,
th
e
s
y
s
te
m
w
il
l
r
ec
eiv
e
s
p
en
d
i
n
g
ti
m
e
o
f
all
v
e
h
icle
s
all
alo
n
g
th
eir
w
a
y
s
,
th
e
n
we
w
il
l
co
m
p
ar
e
th
ese
v
alu
e
s
w
h
ich
w
e
h
a
v
e
j
u
s
t
r
ec
eiv
ed
w
it
h
th
e
co
r
r
esp
o
n
d
in
g
v
al
u
es
wh
ich
ar
e
in
t
h
e
b
ase,
if
t
h
e
d
if
f
er
en
ce
cr
o
s
s
e
s
a
th
r
esh
o
ld
,
th
en
w
e
w
i
ll
d
ed
u
ce
th
at
th
er
e
i
s
an
an
o
m
al
y
o
r
an
ev
e
n
t
s
i
n
ce
t
h
e
m
aj
o
r
ity
o
f
v
eh
icles
s
p
en
d
to
o
m
u
ch
ti
m
e
i
n
a
s
ec
tio
n
x
.
Af
t
er
n
o
ticin
g
t
h
at
th
er
e
i
s
a
c
h
an
g
e
i
n
ter
m
s
o
f
ti
m
e
s
p
en
t
o
n
a
p
ar
tic
u
lar
s
ec
t
io
n
,
o
u
r
s
y
s
te
m
u
p
d
ates
i
m
m
ed
iat
el
y
t
h
e
b
ase
s
p
e
n
d
in
g
ti
m
e
o
f
th
e
s
ec
t
io
n
a
f
f
ec
ted
b
y
t
h
e
c
h
an
g
e.
An
d
th
e
o
p
p
o
s
ite
is
tr
u
e,
if
t
h
e
t
i
m
e
s
p
e
n
t i
n
a
s
ec
tio
n
i
s
r
ed
u
ce
d
,
s
o
w
e
d
ed
u
ce
t
h
at
th
er
e
is
n
o
m
o
r
e
tr
af
f
ic
j
a
m
f
o
r
ex
a
m
p
le
i
n
t
h
at
s
ec
tio
n
,
s
o
w
e
u
p
d
ate
t
h
e
b
ase
as
w
ell.
T
h
er
ef
o
r
e
,
o
u
r
d
atab
ase
is
al
w
a
y
s
u
p
to
d
ate
in
r
ea
l
ti
m
e
tr
af
f
ic
s
tat
u
s
a
n
d
ch
a
n
g
es
o
f
d
if
f
er
en
t
s
ec
t
io
n
s
.
Fro
m
t
h
e
s
ta
r
t
o
f
a
v
e
h
icle,
it
estab
lis
h
es
t
h
e
d
esire
d
d
esti
n
a
tio
n
;
th
e
s
y
s
te
m
w
i
ll
ch
o
o
s
e
t
h
e
b
est
p
ath
to
r
ea
ch
its
d
esti
n
atio
n
r
el
y
i
n
g
o
n
t
h
e
b
ase
o
f
th
e
s
p
e
n
d
in
g
ti
m
e
b
y
c
h
o
o
s
i
n
g
t
h
e
p
ath
w
i
th
t
h
e
m
in
i
m
u
m
ex
p
e
n
d
itu
r
e
ti
m
e
b
y
s
u
m
m
i
n
g
t
h
e
s
p
en
d
in
g
ti
m
e
o
f
d
i
f
f
er
e
n
t sect
io
n
s
o
f
t
h
e
p
ath
d
r
a
w
n
.
W
e
ca
n
s
u
m
m
ar
ize
all
o
u
r
u
s
e
ca
s
e
s
in
Fi
g
u
r
e
4
.
T
h
is
m
ec
h
a
n
is
m
w
ill
h
elp
v
eh
ic
les
to
av
o
id
s
ec
tio
n
s
o
f
r
o
ad
w
h
er
e
th
er
e
is
an
a
n
o
m
al
y
o
r
co
n
g
es
tio
n
;
n
o
t
o
n
l
y
th
at,
b
u
t
it
r
ed
u
ce
s
a
u
to
m
a
ticall
y
t
h
e
g
r
a
v
it
y
o
f
h
a
v
i
n
g
an
ac
c
id
en
t.
Af
ter
h
a
v
i
n
g
estab
lis
h
ed
th
e
o
p
ti
m
al
r
o
u
te
at
th
e
b
eg
in
n
i
n
g
o
f
th
e
v
eh
ic
l
e
tr
ip
,
at
ea
ch
en
tr
y
i
n
a
s
ec
tio
n
,
th
e
v
e
h
icle
s
e
n
d
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
11
,
No
.
4
,
A
u
g
u
s
t 2
0
2
1
:
3
4
8
3
-
3491
3486
a
n
o
ti
f
icatio
n
o
f
it
s
e
n
tr
y
a
n
d
i
ts
r
o
u
te
to
t
h
e
s
y
s
te
m
to
ch
ec
k
if
t
h
er
e
i
s
a
n
a
n
o
m
al
y
o
r
a
m
o
d
if
icatio
n
in
ter
m
s
o
f
esti
m
ated
ti
m
e
f
o
r
cr
o
s
s
i
n
g
f
o
llo
w
in
g
s
ec
tio
n
s
o
f
t
h
e
r
o
u
te
estab
li
s
h
ed
,
i
f
y
e
s
,
t
h
e
s
y
s
te
m
w
ill
lo
o
k
f
o
r
an
o
th
er
m
o
r
e
o
p
ti
m
al
r
o
u
t
e
a
n
d
it
w
ill
s
e
n
d
h
i
m
t
h
e
n
e
w
p
ath
,
o
t
h
er
w
is
e
th
e
v
e
h
icle
co
n
tin
u
es
in
h
is
r
o
u
te
estab
lis
h
ed
b
ef
o
r
eh
an
d
.
T
h
ese
ch
ec
k
s
o
f
t
h
e
s
tate
o
f
th
e
n
e
x
t
s
ec
tio
n
ar
e
ca
r
r
ied
o
u
t
all
al
o
n
g
its
p
ath
an
d
at
ea
ch
en
tr
y
o
f
a
s
ec
tio
n
;
th
i
s
is
d
u
e
to
t
h
e
f
r
eq
u
e
n
t
c
h
a
n
g
e
o
f
th
e
s
tate
o
f
th
e
tr
a
f
f
ic
w
it
h
i
n
t
h
e
V
A
NE
T
n
et
w
o
r
k
.
T
h
is
ch
ar
ac
ter
i
s
tic
o
f
th
ese
f
r
eq
u
e
n
t
ch
ec
k
s
g
iv
es
o
u
r
m
et
h
o
d
m
o
r
e
p
r
ec
i
s
io
n
r
eg
ar
d
in
g
t
h
e
esti
m
ated
ti
m
e
o
f
ar
r
iv
al
o
f
t
h
e
v
eh
icle
s
.
Fig
u
r
e
1
.
Seq
u
en
ce
d
iag
r
a
m
o
f
b
u
ild
i
n
g
a
b
ase
co
n
tain
i
n
g
th
e
e
s
ti
m
ated
s
p
en
t
ti
m
e
o
f
all
t
h
e
s
ec
t
io
n
s
Fig
u
r
e
2
.
Seq
u
en
ce
d
iag
r
a
m
o
f
s
e
n
d
in
g
to
th
e
v
eh
ic
le
th
e
e
s
ti
m
ated
ti
m
e
o
f
a
r
r
iv
al
all
alo
n
g
its
w
a
y
Fig
u
r
e
3
.
Seq
u
en
ce
d
iag
r
a
m
o
f
d
etec
tin
g
a
n
ac
cid
en
t o
r
an
a
n
o
m
al
y
i
n
a
s
ec
tio
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:
2
0
8
8
-
8708
B
ig
d
a
ta
tr
a
ffic m
a
n
a
g
eme
n
t i
n
ve
h
icu
la
r
a
d
-
h
o
c
n
etw
o
r
k
(
T
a
n
ta
o
u
i
Mo
u
a
d
)
3487
Fig
u
r
e
4
.
Su
m
m
ar
y
o
f
all
p
ar
ts
o
f
th
e
m
eth
o
d
o
lo
g
y
3
.
2
.
P
re
dict
io
n
o
f
a
no
m
a
lie
s
Ou
r
g
o
al
in
t
h
i
s
p
ar
t
is
to
p
r
ed
ict
th
e
ar
ea
s
an
d
th
e
co
r
r
esp
o
n
d
in
g
ti
m
e
s
ta
m
p
w
h
er
e
th
e
r
is
k
o
f
co
n
g
es
tio
n
s
o
r
ac
cid
en
ts
is
h
ig
h
,
w
e
u
tili
ze
d
t
h
e
d
atab
ase
co
n
s
tr
u
cted
ab
o
v
e
co
m
p
r
i
s
in
g
t
h
e
e
s
ti
m
ated
s
p
en
d
in
g
ti
m
e
o
f
d
i
f
f
er
en
t
r
o
a
d
s
ec
tio
n
s
,
a
n
d
w
e
ad
d
to
th
i
s
d
atab
ase
th
e
av
er
a
g
e
s
p
ee
d
o
f
ea
ch
r
o
ad
s
ec
tio
n
,
d
en
s
it
y
tr
a
f
f
ic
o
f
it,
an
d
th
e
ti
m
esta
m
p
,
a
n
d
th
e
r
esu
lts
o
f
a
n
o
m
alie
s
d
etec
tio
n
p
ar
t
d
o
n
e
ab
o
v
e,
w
e
u
ti
lized
th
ese
a
ttrib
u
te
s
li
k
e
o
u
r
d
at
aset
i
n
p
u
t
s
f
o
r
m
ac
h
in
e
lear
n
in
g
.
T
w
o
d
i
f
f
er
en
t
cla
s
s
i
f
ie
r
s
ar
e
u
ti
lized
an
d
co
m
p
ar
ed
:
n
ai
v
e
b
a
y
es
(
NB
)
an
d
d
is
cr
i
m
i
n
an
t
r
an
d
o
m
f
o
r
est
(
DR
F)
to
d
is
ce
r
n
ar
ea
s
w
h
e
r
e
th
er
e
w
ill
h
ap
p
e
n
an
a
n
o
m
al
y
.
T
h
e
n
ai
v
e
B
a
y
e
s
i
an
cla
s
s
i
f
icatio
n
i
s
a
t
y
p
e
o
f
s
i
m
p
le
p
r
o
b
ab
ilis
tic
B
a
y
e
s
ia
n
c
lass
i
f
icatio
n
b
ased
o
n
B
a
y
es
'
t
h
eo
r
e
m
w
it
h
a
s
tr
o
n
g
(
ca
lled
n
ai
v
e)
i
n
d
ep
en
d
en
ce
o
f
t
h
e
as
s
u
m
p
tio
n
s
.
I
t
i
m
p
le
m
e
n
t
s
a
n
ai
v
e
B
ay
e
s
ian
c
lass
if
ier
,
o
r
n
ai
v
e
B
ay
e
s
clas
s
i
f
ier
,
b
elo
n
g
i
n
g
to
th
e
f
a
m
i
l
y
o
f
li
n
ea
r
class
i
f
ier
s
.
W
h
ile
f
o
r
DR
F,
it
is
p
ar
t
o
f
m
ac
h
i
n
e
lear
n
i
n
g
te
ch
n
iq
u
es.
T
h
is
al
g
o
r
ith
m
[
2
8
]
co
m
b
i
n
es
t
h
e
co
n
ce
p
ts
o
f
r
an
d
o
m
s
u
b
s
p
a
ce
s
a
n
d
b
ag
g
i
n
g
.
D
is
cr
i
m
i
n
an
t
r
a
n
d
o
m
f
o
r
est
al
g
o
r
it
h
m
tr
ai
n
s
o
n
m
u
ltip
le
d
ec
is
io
n
tr
ee
s
tr
ain
ed
o
n
s
lig
h
tl
y
d
i
f
f
er
e
n
t
d
ata
s
u
b
s
ets.
T
h
e
b
asis
o
f
t
h
e
ca
lcu
latio
n
is
b
ased
o
n
d
ec
is
i
o
n
tr
ee
lear
n
in
g
.
B
r
ei
m
an
's
[
2
9
]
p
r
o
p
o
s
al
aim
s
to
co
r
r
ec
t
s
ev
er
al
k
n
o
w
n
d
r
a
w
b
a
ck
s
o
f
t
h
e
i
n
itial
m
et
h
o
d
,
s
u
c
h
as
th
e
s
en
s
iti
v
it
y
o
f
s
i
n
g
le
t
r
ee
s
to
th
e
o
r
d
er
o
f
p
r
ed
icto
r
s
,
b
y
ca
lc
u
lati
n
g
a
s
e
t
o
f
X
p
ar
tially
i
n
d
ep
en
d
en
t
tr
ee
s
.
T
h
e
class
f
ea
tu
r
e
o
f
o
u
r
c
lass
i
f
icatio
n
is
th
e
co
n
g
es
tio
n
d
e
g
r
ee
.
First,
b
o
th
t
h
e
NB
a
n
d
DR
F
m
e
th
o
d
s
ca
n
ac
h
iev
e
s
u
p
er
b
ac
c
u
r
ac
y
v
al
u
es.
T
h
e
class
i
f
icatio
n
r
esu
l
t
h
as
t
h
r
ee
d
if
f
er
e
n
t
v
al
u
e
s
:
m
i
n
o
r
,
in
ter
m
ed
iate
an
d
m
aj
o
r
.
Fo
r
th
e
n
aïv
e
b
a
y
es
m
et
h
o
d
,
in
T
ab
le
1
,
ac
cu
r
ac
y
(
AC
C
)
attai
n
s
ab
o
u
t
8
3
.
5
%,
(
in
c
lass
if
ica
t
io
n
m
et
h
o
d
s
,
A
cc
u
r
ac
y
i
s
t
h
e
n
u
m
b
er
o
f
co
r
r
ec
t
p
r
ed
ictio
n
s
m
ad
e
b
y
t
h
e
m
o
d
e
l
o
v
er
all
d
if
f
er
en
t
p
r
ed
ictio
n
s
d
o
n
e,
an
d
ar
ea
u
n
d
er
th
e
cu
r
v
e
(
A
U
C
)
is
a
k
i
n
d
o
f
p
er
f
o
r
m
an
ce
f
o
r
class
i
f
ica
tio
n
m
et
h
o
d
th
at
ex
p
r
es
s
h
o
w
m
u
c
h
m
o
d
el
is
ab
le
to
d
is
tin
g
u
is
h
b
et
w
ee
n
class
es.)
,
an
d
f
o
r
DR
F,
t
h
e
v
alu
es
at
tain
ab
o
u
t
8
8
.
3
%.
DR
F
class
i
f
ier
h
ad
th
e
b
i
g
g
e
s
t
ti
m
e
o
f
co
m
p
u
tatio
n
(
n
ea
r
l
y
1
5
s
)
.
T
ab
le
1
an
d
Fig
u
r
e
5
s
h
o
w
t
h
e
s
u
m
m
ar
ized
r
e
s
u
lt
s
o
f
clas
s
i
f
icatio
n
f
o
r
th
e
t
w
o
clas
s
if
ier
s
.
Fo
r
DR
F,
d
esp
ite
o
f
t
h
e
cla
s
s
i
f
ica
tio
n
r
esu
lts
is
be
tter
th
at
t
h
e
n
aïv
e
b
a
y
e
s
r
esu
l
ts
,
it
to
o
k
m
o
r
e
ti
m
e
(
1
5
s
)
.
Fo
r
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
11
,
No
.
4
,
A
u
g
u
s
t 2
0
2
1
:
3
4
8
3
-
3491
3488
r
ea
l
-
ti
m
e
m
o
d
e,
w
it
h
f
e
w
er
f
ea
tu
r
es,
u
s
i
n
g
n
aï
v
e
b
a
y
e
s
wo
u
ld
b
e
g
o
o
d
in
p
r
o
v
id
in
g
m
o
s
t
lik
el
y
t
h
e
r
ig
h
t
d
ec
is
io
n
q
u
ic
k
l
y
,
an
d
t
h
e
n
t
h
e
aler
t
w
ill
b
e
s
e
n
t
to
t
h
e
p
a
r
ticip
atin
g
v
e
h
icle
a
n
d
t
h
e
d
r
iv
er
to
h
a
v
e
b
etter
d
ec
is
io
n
.
T
ab
le
1
.
DR
F a
n
d
NB
class
i
f
i
ca
tio
n
r
esu
l
ts
C
l
a
ssi
f
i
e
r
T
i
me
o
f
c
o
mp
u
t
a
t
i
o
n
A
C
C
A
U
C
N
a
ï
v
e
B
a
y
e
s
0
.
0
4
8
3
.
5
63
R
a
n
d
o
m F
o
r
e
st
15
8
8
.
3
61
Fig
u
r
e
5
.
DR
F a
n
d
NB
ac
cu
r
a
r
y
r
es
u
lt
s
4.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
e
p
r
o
p
o
s
ed
m
et
h
o
d
co
n
s
i
s
t
s
at
estab
li
s
h
i
n
g
t
h
e
o
p
ti
m
al
p
ath
to
t
h
e
d
esti
n
atio
n
b
y
ch
o
o
s
in
g
t
h
e
s
ec
tio
n
s
o
f
r
o
ad
th
at
h
a
v
e
t
h
e
m
i
n
i
m
u
m
s
p
en
d
i
n
g
ti
m
e
r
el
y
in
g
o
n
u
tili
z
in
g
b
i
g
d
ata
tec
h
n
o
lo
g
ies
to
ass
u
r
e
a
f
ast
tr
ea
t
m
e
n
t
i
n
r
ea
l
ti
m
e.
I
n
th
e
s
i
m
u
latio
n
b
elo
w
,
w
e
to
o
k
th
e
m
ap
o
f
C
asab
la
n
ca
cit
y
,
Mo
r
o
cc
o
;
an
d
th
en
w
e
cu
t
th
e
r
o
ad
s
in
to
s
ec
tio
n
s
as
is
s
h
o
w
n
i
n
Fi
g
u
r
e
6
.
T
h
e
s
i
m
u
la
tio
n
w
as
d
o
n
e
b
y
s
i
m
u
lato
r
s
u
m
o
th
at
g
en
er
ate
s
tr
af
f
ic,
a
n
d
w
e
u
s
ed
a
n
av
i
g
atio
n
m
ap
m
o
d
u
le
t
h
at
u
tili
ze
s
o
u
r
d
atab
ase
co
n
tai
n
in
g
ti
m
e
s
p
en
t
o
n
ea
ch
r
o
ad
s
ec
tio
n
a
n
d
f
i
n
d
th
e
b
est
r
o
u
te
w
it
h
m
in
i
m
a
l
ti
m
e
.
T
o
s
h
o
w
th
e
u
s
e
f
u
l
n
es
s
o
f
i
m
m
ed
iate
d
atab
ase
ch
an
g
es
an
d
al
w
a
y
s
k
ee
p
in
g
t
h
e
d
atab
ase
u
p
to
d
ate,
w
e
m
e
n
tio
n
ed
i
n
t
h
e
tab
le
o
n
l
y
f
o
u
r
v
eh
ic
les
w
h
ic
h
h
a
v
e
th
e
s
a
m
e
d
esti
n
atio
n
a
n
d
s
o
u
r
c
e.
Fig
u
r
e
6
.
VA
NE
T
co
m
p
o
n
e
n
t
s
an
d
cu
tt
in
g
r
o
ad
s
in
to
s
ec
tio
n
s
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:
2
0
8
8
-
8708
B
ig
d
a
ta
tr
a
ffic m
a
n
a
g
eme
n
t i
n
ve
h
icu
la
r
a
d
-
h
o
c
n
etw
o
r
k
(
T
a
n
ta
o
u
i
Mo
u
a
d
)
3489
T
h
e
T
a
b
le
2
s
h
o
w
s
th
e
iti
n
er
ar
y
o
f
th
e
v
e
h
icle
s
as
s
i
g
n
ed
b
y
o
u
r
p
r
o
p
o
s
ed
m
et
h
o
d
ac
co
r
d
in
g
to
t
h
e
d
esti
n
atio
n
e
s
tab
lis
h
ed
b
ef
o
r
e
h
an
d
b
y
t
h
e
v
e
h
icle,
t
h
e
s
y
s
te
m
i
s
b
ased
o
n
t
h
e
d
atab
ase
o
f
th
e
s
p
en
d
in
g
ti
m
e
o
f
ea
ch
s
ec
t
io
n
o
f
r
o
ad
to
ass
i
g
n
th
e
v
e
h
icles
an
o
p
ti
m
al
r
o
u
te
.
I
n
t
h
e
ex
a
m
p
le
s
h
o
w
n
b
elo
w,
at
t
w
el
v
e
o
’
clo
c
k
n
o
o
n
,
t
h
e
v
eh
ic
le
n
u
m
b
er
o
n
e
s
tar
t
it
s
tr
ip
f
r
o
m
r
o
ad
n
u
m
b
er
o
n
e
w
ith
s
ec
tio
n
n
u
m
b
er
o
n
e
an
d
w
i
s
h
es
to
r
ea
ch
r
o
ad
n
u
m
b
er
n
i
n
e
w
it
h
s
ec
tio
n
n
u
m
b
er
t
h
r
ee
as
it
s
d
esire
d
d
esti
n
atio
n
,
o
u
r
s
y
s
te
m
a
f
f
ec
ted
to
th
e
v
eh
ic
l
e
a
r
o
u
te
in
d
icate
d
in
th
e
‘
r
o
u
te’
f
ield
o
f
th
e
T
ab
le
2
,
it
is
a
s
eq
u
en
ce
o
f
co
u
p
le
s
(
x
,
y
)
t
h
at
th
e
v
eh
ic
le
w
il
l
f
o
llo
w
t
h
r
o
u
g
h
o
u
t
its
tr
ip
,
x
b
ein
g
th
e
id
en
t
if
ier
o
f
t
h
e
r
o
ad
an
d
y
b
ein
g
th
e
s
ec
tio
n
o
f
th
e
r
o
ad
x
.
Fo
r
th
e
v
eh
ic
le
n
u
m
b
er
t
w
o
,
it
ar
r
iv
ed
j
u
s
t
af
ter
v
e
h
icle
n
u
m
b
er
o
n
e
at
1
2
:0
2
an
d
w
an
ts
to
g
o
to
th
e
s
a
m
e
d
esti
n
atio
n
as
v
e
h
icle
n
u
m
b
er
o
n
e,
as
w
e
ca
n
s
ee
,
t
h
e
s
y
s
te
m
h
as
a
f
f
e
cted
to
it
th
e
s
a
m
e
r
o
u
te
b
ec
au
s
e
t
h
e
b
ase
is
t
h
e
s
a
m
e
a
n
d
s
o
t
h
e
o
p
ti
m
al
r
o
u
t
e
s
ta
y
s
t
h
e
s
a
m
e
a
s
th
e
f
ir
s
t
o
n
e.
Fo
r
th
e
v
eh
icle
n
u
m
b
er
t
h
r
ee
th
at
ar
r
iv
ed
at
1
2
:1
7
an
d
h
as
th
e
s
a
m
e
d
esti
n
atio
n
as
v
e
h
icle
n
u
m
b
er
o
n
e
a
n
d
t
w
o
,
w
e
n
o
ticed
th
at
t
h
e
s
y
s
te
m
h
as
a
s
s
i
g
n
ed
a
d
if
f
er
e
n
t
r
o
u
te
th
a
n
th
o
s
e
o
f
t
h
e
t
w
o
p
r
ev
io
u
s
v
e
h
icles,
t
h
is
is
b
ec
au
s
e
th
e
s
p
e
n
d
in
g
ti
m
e
o
f
s
ec
tio
n
5
o
f
r
o
u
t
e
2
h
as
b
ec
o
m
e
b
ig
g
er
b
ec
au
s
e
o
f
a
p
ar
ticu
lar
an
o
m
al
y
th
at
c
an
b
e
eith
er
a
n
ac
cid
en
t,
co
n
g
esti
o
n
,
a
n
d
an
ev
e
n
t
(
An
o
m
al
y
d
etec
ted
in
(
2
,
5
)
,
i
ts
s
p
en
d
in
g
ti
m
e
is
b
ec
o
m
in
g
b
ig
g
er
an
d
is
u
p
d
ated
in
th
e
b
ase)
an
d
th
is
w
ill
p
u
s
h
t
h
e
s
y
s
te
m
to
lo
o
k
f
o
r
a
n
e
w
r
o
u
te
w
h
ich
i
s
m
o
r
e
o
p
tim
al
t
h
an
t
h
e
o
ld
o
n
e.
As
w
e
ca
n
s
ee
i
n
T
ab
le
2
,
th
e
n
e
w
r
o
u
te
i
s
t
h
ir
d
r
o
u
te
i
n
T
ab
le
2
th
at
h
as
d
u
r
atio
n
o
f
f
i
f
t
y
m
i
n
u
te
s
;
th
is
th
ir
d
r
o
u
te
is
m
o
r
e
o
p
ti
m
al
th
a
n
t
h
e
o
ld
r
o
u
te
a
f
f
ec
ted
to
v
eh
ic
le
n
u
m
b
er
o
n
e
an
d
t
wo
b
ec
au
s
e
af
ter
th
e
an
o
m
al
y
d
etec
ted
,
its
d
u
r
atio
n
h
a
s
b
ec
o
m
e
eq
u
al
to
s
ix
t
y
m
i
n
u
te
s
.
B
ec
au
s
e
o
f
t
h
e
f
r
eq
u
en
t
c
h
a
n
g
e
s
i
n
t
h
e
tr
af
f
ic
s
tate
in
t
h
e
V
A
NE
T
n
et
w
o
r
k
,
t
h
er
e
ar
e
m
a
n
y
r
ea
l
-
ti
m
e
u
p
d
ates
o
n
th
e
d
atab
ase;
t
h
e
T
ab
le
3
illu
s
tr
ates
an
ex
tr
ac
t
o
f
t
h
i
s
d
atab
ase.
T
h
e
p
r
o
p
o
s
ed
m
et
h
o
d
g
a
v
e
u
s
a
w
a
y
to
av
o
id
co
n
g
est
io
n
s
an
d
to
r
ed
u
ce
t
h
e
g
r
av
it
y
to
h
av
e
a
n
ac
cid
en
t,
I
t
is
an
o
th
er
w
a
y
to
g
iv
e
to
u
s
e
r
a
s
af
e
itin
er
ar
y
to
r
ea
ch
th
ei
r
d
esti
n
atio
n
m
o
r
e
ac
cu
r
atel
y
,
t
h
e
o
th
er
m
et
h
o
d
s
in
th
e
r
elate
d
m
et
h
o
d
m
e
n
tio
n
ed
in
th
e
liter
atu
r
e
p
r
ed
ict
if
t
h
er
e
is
an
ac
cid
en
t
o
r
co
n
g
esti
o
n
i
n
w
h
at
w
ill
h
ap
p
en
,
th
e
ad
v
a
n
tag
e
o
f
o
u
r
m
et
h
o
d
is
t
h
at
it
k
n
o
w
s
i
n
r
ea
l
ti
m
e
w
h
at
is
h
ap
p
en
in
g
i
n
th
e
d
i
f
f
er
e
n
t
r
o
ad
s
ec
tio
n
s
,
it
is
n
o
t
a
p
r
ed
ictio
n
,
b
u
t
it
illu
s
tr
ate
w
h
at
is
ac
tu
all
y
h
ap
p
en
i
n
g
in
th
e
r
o
ad
s
b
ased
o
n
t
h
e
ti
m
e
s
p
en
t b
y
t
h
e
v
e
h
icles
liv
e,
al
s
o
w
h
e
n
w
e
s
ee
th
at
v
e
h
icles
s
p
e
n
d
to
o
m
u
c
h
t
i
m
e
o
n
s
o
m
e
s
ec
tio
n
s
s
o
w
e
w
i
ll
k
n
o
w
t
h
at
it
i
s
co
n
g
e
s
ted
(
h
i
g
h
d
e
n
s
it
y
)
o
r
th
er
e
is
an
a
n
o
m
a
l
y
i
n
th
at
s
ec
tio
n
s
o
o
u
r
s
y
s
te
m
w
ill
r
ed
ir
ec
t
n
e
x
t
v
eh
i
cles
to
an
o
t
h
er
r
o
u
te.
I
t
al
s
o
h
elp
s
to
h
a
v
e
as
a
k
in
d
o
f
b
alan
ce
o
f
lo
ad
s
i
n
ter
m
s
th
at
o
u
r
m
et
h
o
d
m
a
k
e
s
f
ill
r
o
ad
s
b
y
th
e
v
e
h
icle
s
,
an
d
as
s
o
o
n
as
th
at
s
tar
ts
to
b
e
b
u
s
y
,
it
r
er
o
u
tes
th
e
f
o
llo
w
in
g
v
eh
icles
to
a
r
o
ad
th
at
is
less
lo
ad
ed
th
an
t
h
e
o
t
h
er
s
,
o
u
r
m
et
h
o
d
d
ev
elo
p
s
th
i
s
ef
f
ec
t
o
f
b
ala
n
ce
o
f
lo
ad
in
an
au
to
m
atic
m
an
n
er
.
T
ab
le
2
.
Veh
icle
itin
er
ar
y
as
s
i
g
n
ed
b
y
o
u
r
m
et
h
o
d
T
i
me
V
e
h
i
c
l
e
I
D
S
o
u
r
c
e
R
o
u
t
e
D
u
r
a
t
i
o
n
12
:
0
0
1
(
1
,
1
)
(
1
,
1
)
-
>
(
1
,
2
)
-
>
(
2
,
4
)
-
>
(
2
,
5
)
-
>
(
4
,
6
)
-
>
(
4
,
7
)
-
>
(
6
,
2
)
-
>
(
9
,
3
)
45
mi
n
12
:
0
2
2
(
1
,
1
)
(
1
,
1
)
-
>
(
1
,
2
)
-
>
(
2
,
4
)
-
>
(
2
,
5
)
-
>
(
4
,
6
)
-
>
(
4
,
7
)
-
>
(
6
,
2
)
-
>
(
9
,
3
)
4
7
mi
n
12
:
1
7
3
(
1
,
1
)
(
1
,
1
)
-
>
(
1
,
2
)
-
>
(
3
,
1
)
-
>
(
5
,
5
)
-
>
(
4
,
8
)
-
>
(
4
,
9
)
-
>
(
6
,
2
)
-
>
(
9
,
3
)
5
1
mi
n
12
:
1
9
4
(
1
,
1
)
(
1
,
1
)
-
>
(
1
,
2
)
-
>
(
3
,
1
)
-
>
(
5
,
5
)
-
>
(
4
,
8
)
-
>
(
4
,
9
)
-
>
(
6
,
2
)
-
>
(
9
,
3
)
5
3
mi
n
T
ab
le
3
.
A
n
ex
tr
ac
t o
f
th
e
d
ata
b
ase
co
n
tain
i
n
g
all
r
o
ad
s
ec
tio
n
s
d
u
r
atio
n
ti
m
e
(
r
o
a
d
,
se
c
t
i
o
n
)
Est
i
m
a
t
e
d
d
u
r
a
t
i
o
n
t
i
me
a
t
1
2
:
0
0
Est
i
m
a
t
e
d
d
u
r
a
t
i
o
n
t
i
me
a
t
1
2
:
1
0
Est
i
m
a
t
e
d
d
u
r
a
t
i
o
n
t
i
me
a
t
1
2
:
2
0
(
1
,
1
)
6
m
i
n
30
se
c
7
m
i
n
20
se
c
8
m
i
n
52
se
c
(
1
,
2
)
7
m
i
n
13
se
c
7
m
i
n
13
se
c
7
m
i
n
13
se
c
(
1
,
3
)
8
m
i
n
1
9
se
c
8
m
i
n
43
se
c
8
m
i
n
32
se
c
(
2
,
1
)
6
m
i
n
41
se
c
6
m
i
n
23
se
c
6
m
i
n
55
se
c
(
2
,
3
)
5
m
i
n
22
se
c
5
m
i
n
29
se
c
5
m
i
n
28
se
c
(
3
,
4
)
7
m
i
n
50
se
c
7
m
i
n
45
se
c
7
m
i
n
30
se
c
(
4
,
1
)
8
m
i
n
21
se
c
8
m
i
n
32
se
c
8
m
i
n
40
se
c
(
2
,
5
)
7
m
i
n
5
4
se
c
13
mi
n
41
se
c
1
2
m
i
n
36
se
c
(
7
,
3
)
9
m
i
n
2
2
se
c
9
m
i
n
4
5
se
c
9
m
i
n
10
se
c
T
h
is
ap
p
r
o
ac
h
is
illu
s
tr
ated
in
T
ab
le
4
,
r
o
ad
s
ec
tio
n
(
1
,
1
)
i
s
af
f
ec
ted
to
m
a
n
y
r
o
u
te
s
s
en
t
to
o
m
an
y
v
eh
ic
les,
s
o
af
ter
a
w
h
ile
(
2
0
m
in
)
,
it
b
ec
o
m
e
s
a
litt
le
co
n
g
ested
(
m
ed
i
u
m
d
en
s
it
y
)
,
an
d
u
n
li
k
e
(
1
,
3
)
,
th
e
s
y
s
te
m
d
o
esn
’
t
u
s
ed
it
in
t
h
e
r
o
u
tes,
s
o
a
f
ter
a
w
h
ile
it
b
ec
o
m
e
s
lo
w
co
n
g
ested
.
Fo
r
(
2
,
5
)
,
its
esti
m
ated
d
u
r
atio
n
ti
m
e
m
o
v
ed
f
r
o
m
7
m
in
to
1
3
m
in
b
ec
au
s
e
o
f
an
a
n
o
m
al
y
s
o
w
e
s
to
p
to
u
s
e
th
i
s
s
e
ctio
n
in
r
o
u
te
s
u
n
ti
l
it
b
ec
o
m
e
n
o
r
m
al.
T
h
o
s
e
m
a
n
y
u
p
d
ates
at
t
h
e
le
v
el
o
f
th
e
d
atab
ase
let
o
u
r
m
et
h
o
d
m
o
r
e
a
c
cu
r
ate
co
n
ce
r
n
in
g
th
e
esti
m
ated
ti
m
e
o
f
ar
r
iv
al
o
f
v
e
h
icle
s
an
d
to
r
o
u
te
v
eh
icle
s
in
d
if
f
er
en
t
p
ath
s
.
O
u
r
ar
ch
it
ec
tu
r
e
is
co
m
p
o
s
ed
o
f
ce
n
tr
alize
d
b
atch
d
ata
s
to
r
ag
e
a
n
d
p
r
o
ce
s
s
i
n
g
m
ec
h
a
n
i
s
m
a
n
d
a
d
is
tr
ib
u
ted
d
ata
s
to
r
ag
e
m
ec
h
an
i
s
m
f
o
r
r
ea
l
-
ti
m
e
tr
ea
t
m
e
n
t
a
n
d
an
al
y
s
is
to
m
a
n
a
g
e
an
d
p
r
o
ce
s
s
th
e
f
lo
w
f
r
o
m
t
h
e
v
e
h
icle
i
n
a
p
ar
ti
cu
lar
ar
ea
.
Fo
r
th
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
11
,
No
.
4
,
A
u
g
u
s
t 2
0
2
1
:
3
4
8
3
-
3491
3490
tech
n
o
lo
g
ies
u
s
ed
o
n
t
h
e
s
i
m
u
latio
n
,
w
e
b
en
e
f
ited
f
r
o
m
L
A
ad
v
an
tag
e
s
,
w
e
u
s
ed
ap
ac
h
e
s
to
r
m
f
o
r
t
h
e
r
ea
l
-
ti
m
e
a
n
al
y
s
is
to
p
r
o
ce
s
s
d
is
tr
i
b
u
ted
an
d
f
aster
f
lo
w
tr
ea
t
m
e
n
t
.
W
h
ile
f
o
r
p
r
o
ce
s
s
in
g
t
h
e
d
at
a
m
ass
,
w
e
u
tili
ze
d
Had
o
o
p
Ma
p
R
ed
u
ce
th
at
co
n
s
tr
u
cts
th
e
d
atab
ase
t
h
at
will
b
e
u
tili
ze
d
b
y
s
p
ee
d
la
y
e
r
w
h
ic
h
i
s
a
f
ast
-
p
r
o
ce
s
s
in
g
la
y
er
in
r
ea
l
ti
m
e.
T
h
u
s
,
th
e
ex
p
er
i
m
en
tal
r
esu
lt
an
d
an
al
y
s
is
p
r
o
v
ed
th
at
t
h
e
p
r
o
p
o
s
ed
a
r
ch
itec
tu
r
e
m
o
d
el
is
a
n
o
p
ti
m
a
l
s
o
l
u
tio
n
th
at
u
tili
ze
s
b
ig
d
ata
tech
n
o
lo
g
ies,
d
est
in
ed
to
tr
a
n
s
f
er
d
ata
in
a
n
ea
r
r
ea
l
-
ti
m
e
tr
ea
t
m
e
n
t d
esti
n
ed
f
o
r
in
tell
ig
en
t tr
an
s
p
o
r
tatio
n
s
y
s
te
m
i
n
a
v
eh
ic
u
lar
ad
-
h
o
c
en
v
ir
o
n
m
e
n
t.
T
ab
le
4
.
Statu
s
o
f
d
if
f
er
en
t r
o
ad
s
ec
tio
n
at
T
an
d
T
+
2
0
m
i
n
T
i
me
R
o
a
d
se
c
t
i
o
n
D
e
n
si
t
y
a
t
T
D
e
n
si
t
y
a
t
T
+
2
0
m
i
n
1
2
:
0
0
(
1
,
1
)
l
o
w
M
e
d
i
u
m
1
2
:
0
0
(
2
,
5
)
M
e
d
i
u
m
V
e
r
y
h
i
g
h
1
2
:
1
0
(
1
,
3
)
M
e
d
i
u
m
L
o
w
1
3
:
0
0
(
x
,
y
)
l
o
w
L
o
w
5.
CO
NCLU
SI
O
N
VANE
T
en
g
e
n
d
er
v
o
l
u
m
i
n
o
u
s
d
ata
w
h
ic
h
i
s
co
m
p
licated
to
h
a
n
d
le;
t
h
er
e
f
o
r
e,
b
ig
d
ata
te
ch
n
o
lo
g
ies
ar
e
i
m
p
o
r
tan
t
to
m
in
e
m
ea
n
i
n
g
f
u
l
d
ata
f
r
o
m
t
h
ese
b
ig
d
ata.
R
o
ad
ac
cid
en
t
s
ar
e
t
h
r
ea
ti
n
g
th
e
li
v
e
s
o
f
h
u
m
an
b
ein
g
s
,
an
d
in
th
e
p
u
r
p
o
s
e
o
f
f
in
d
i
n
g
o
u
t
a
n
alter
n
ati
v
e
f
o
r
th
e
is
s
u
e
o
f
p
r
ed
ictin
g
th
e
h
ig
h
p
r
o
b
ab
ilit
y
o
f
v
eh
ic
l
e
ac
cid
en
t
s
,
t
h
is
p
ap
er
u
tili
ze
s
t
h
e
b
en
e
f
it
s
o
f
b
ig
d
at
a
to
en
h
an
ce
tr
af
f
ic
m
a
n
ag
e
m
en
t,
w
e
e
s
tab
lis
h
ed
r
ea
l
-
ti
m
e
a
n
o
m
al
ies
d
etec
tio
n
s
y
s
te
m
i
n
r
ea
l
ti
m
e
e
m
p
lo
y
in
g
p
ar
allel
d
ata
tr
ea
t
m
e
n
t,
t
h
i
s
g
av
e
to
o
u
r
m
et
h
o
d
f
ast
ex
ec
u
tio
n
ti
m
e.
Ou
r
m
e
t
h
o
d
ai
m
s
to
k
n
o
w
e
x
ac
tl
y
t
h
e
ti
m
e
s
p
e
n
t
to
cr
o
s
s
ea
c
h
s
e
ctio
n
o
n
ea
ch
r
o
ad
,
w
h
ic
h
w
ill
g
i
v
e
u
s
a
co
n
tr
o
l
to
w
ell
m
a
n
a
g
e
th
e
tr
af
f
ic
an
d
s
en
d
to
v
eh
icles
an
ac
cu
r
at
e
esti
m
ated
ti
m
e
o
f
ar
r
iv
als
a
n
d
th
e
b
est
s
a
f
e
r
o
u
te
to
r
ea
ch
t
h
eir
d
esti
n
atio
n
.
A
n
d
al
s
o
,
an
o
m
al
ies
p
r
ed
ict
io
n
s
y
s
te
m
w
as
d
ev
elo
p
ed
w
i
th
t
h
e
h
elp
o
f
m
ac
h
in
e
lear
n
in
g
tech
n
iq
u
es.
T
h
at
w
ill
h
elp
u
s
to
av
o
id
tr
af
f
ic
co
n
g
e
s
tio
n
an
d
r
ed
u
ce
th
e
r
is
k
o
f
ac
cid
en
t
s
.
T
h
e
r
esu
lts
o
f
o
u
r
e
x
p
er
i
m
en
t
s
h
o
w
th
at
o
u
r
m
et
h
o
d
d
ec
r
ea
s
es
co
n
g
e
s
tio
n
s
ig
n
i
f
ica
n
tl
y
a
n
d
s
o
d
ec
r
ea
s
e
ac
c
id
en
ts
an
d
o
u
r
r
es
u
lt
s
h
av
e
lo
w
laten
c
y
a
n
d
h
i
g
h
ac
cu
r
ac
y
.
O
u
r
f
u
tu
r
e
r
esear
ch
is
to
m
o
r
e
ex
p
lo
it
th
e
b
ase
o
f
s
p
en
d
in
g
ti
m
e
p
er
s
ec
tio
n
estab
lis
h
ed
o
n
th
is
m
et
h
o
d
an
d
m
er
g
i
n
g
it
w
it
h
m
ac
h
in
e
lear
n
i
n
g
tec
h
n
iq
u
es to
h
a
v
e
a
h
i
g
h
co
n
tr
o
l o
n
m
an
a
g
i
n
g
tr
af
f
ic
a
n
d
h
av
in
g
b
etter
r
esu
lts
.
RE
F
E
R
E
NC
E
S
[1
]
Da
Cu
n
h
a
,
F
.
D.,
B
o
u
k
e
rc
h
e
,
A
.
,
V
il
las
,
L
.
,
V
ia
n
a
,
A
.
C.
,
a
n
d
L
o
u
re
iro
,
A
.
A
.
, “
Da
ta
c
o
m
m
u
n
ica
ti
o
n
in
V
A
NET
s: a
su
rv
e
y
,
c
h
a
ll
e
n
g
e
s a
n
d
a
p
p
li
c
a
ti
o
n
s
,”
Diss
.
INRIA
S
a
c
la
y
;
INRI
A
,
2
0
1
4
.
[2
]
B
.
P
u
n
a
m
,
a
n
d
V
.
Ji
n
d
a
l
,
“
Us
e
o
f
b
ig
d
a
ta
tec
h
n
o
l
o
g
y
in
v
e
h
icu
lar
a
d
-
h
o
c
n
e
tw
o
rk
s
,”
2
0
1
4
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Ad
v
a
n
c
e
s in
Co
mp
u
ti
n
g
,
C
o
mm
u
n
ica
ti
o
n
s
a
n
d
In
fo
r
ma
ti
c
s (
ICACCI)
,
2
0
1
4
,
p
p
.
1
6
7
7
-
1
6
8
3
.
[3
]
Kh
a
n
,
Ju
n
a
i
d
,
Ya
c
in
e
G
h
a
m
ri
-
D
o
u
d
a
n
e
,
a
n
d
A
li
El
M
a
sri
,
“
V
e
rs
u
n
e
a
p
p
ro
c
h
e
c
e
n
trée
in
f
o
r
m
a
t
io
n
(ICN)
p
o
u
r
id
e
n
ti
f
ier l
e
s v
é
h
icu
les
im
p
o
rtan
ts d
a
n
s les
V
A
NET
s
,”
Pro
c
e
e
d
in
g
s
o
f
t
h
e
c
o
n
fer
e
n
c
e
CFIP
NOTE
RE
2
0
1
5
,
2
0
1
5
.
[4
]
Ch
e
n
g
,
Z.
,
Ch
o
w
,
M
.
Y.,
Ju
n
g
,
D.,
a
n
d
Je
o
n
,
J
.
,
“
A
b
ig
d
a
ta
b
a
se
d
d
e
e
p
lea
rn
in
g
a
p
p
ro
a
c
h
f
o
r
v
e
h
icle
sp
e
e
d
p
re
d
ictio
n
,
”
2
0
1
7
I
EE
E
2
6
t
h
I
n
ter
n
a
ti
o
n
a
l
S
y
mp
o
si
u
m o
n
I
n
d
u
stria
l
El
e
c
tro
n
ics
(
IS
IE)
,
2
0
1
7
,
p
p
.
3
8
9
-
3
9
4
.
[5
]
A
l
N
a
jad
a
,
Ha
m
z
a
h
,
a
n
d
I
m
a
d
M
a
h
g
o
u
b
,
“
A
n
ti
c
ip
a
ti
o
n
a
n
d
a
ler
t
s
y
ste
m
o
f
c
o
n
g
e
stio
n
a
n
d
a
c
c
id
e
n
ts
in
V
A
NE
T
u
sin
g
Big
Da
ta
a
n
a
l
y
sis
f
o
r
In
tel
li
g
e
n
t
T
ra
n
sp
o
rtatio
n
S
y
ste
m
s
,”
2
0
1
6
IEE
E
S
y
m
p
o
siu
m
S
e
rie
s
o
n
Co
mp
u
t
a
ti
o
n
a
l
In
telli
g
e
n
c
e
(
S
S
CI)
,
2
0
1
6
,
p
p
.
1
-
8.
[6
]
M
a
rz
,
Na
th
a
n
,
a
n
d
Ja
m
e
s
Warre
n
.
,
“
Big
Da
ta:
P
ri
n
c
ip
les
a
n
d
b
e
st
p
ra
c
ti
c
e
s
o
f
sc
a
lab
le
re
a
l
-
ti
m
e
d
a
ta
sy
ste
m
s
,
”
Ne
w
Yo
rk
;
M
a
n
n
i
n
g
P
u
b
li
c
a
ti
o
n
s Co
.
,
2
0
1
5
.
[7
]
M
a
h
a
jan
,
A
n
sh
u
l,
a
n
d
A
rv
in
d
e
r
Ka
u
r
,
“
P
re
d
ictiv
e
Urb
a
n
T
ra
ff
ic
F
lo
w
M
o
d
e
l
u
sin
g
V
e
h
icu
lar
Bi
g
Da
ta
,
”
In
d
ia
n
J
o
u
rn
a
l
o
f
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l.
9
,
n
o
.
42
,
p
p
.
1
-
8
,
2
0
1
6
.
[8
]
Bo
-
Ra
n
g
L
in
,
T
sa
n
-
P
i
n
W
a
n
g
,
“
D
y
n
a
m
ic
Re
p
o
rti
n
g
M
e
c
h
a
n
ism
s
f
o
r
T
ru
st
M
a
n
a
g
e
m
e
n
t
in
Ve
h
icu
la
r
A
d
-
h
o
c
Ne
tw
o
rk
s,
”
AIT
,
2
0
1
6
[9
]
Da
n
iel,
A
lf
re
d
,
A
n
a
n
d
P
a
u
l,
a
n
d
Aw
a
is
A
h
m
a
d
.
,
“
Ne
a
r
re
a
l
-
ti
m
e
b
ig
d
a
ta
a
n
a
ly
sis
o
n
v
e
h
icu
lar
n
e
tw
o
rk
s
,”
2
0
1
5
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
S
o
ft
-
Co
mp
u
t
in
g
a
n
d
Ne
two
rk
s S
e
c
u
rit
y
(
ICS
NS
),
2
0
1
5
,
p
p
.
1
-
7.
[1
0
]
Yu
,
Hy
u
n
,
Jo
o
n
Yo
o
,
a
n
d
S
a
n
g
h
y
u
n
A
h
n
,
“
A
V
A
NE
T
ro
u
ti
n
g
b
a
se
d
o
n
t
h
e
re
a
l
-
ti
m
e
ro
a
d
v
e
h
icle
d
e
n
sity
in
t
h
e
c
it
y
e
n
v
iro
n
m
e
n
t
,
”
2
0
1
3
F
if
th
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Ub
iq
u
it
o
u
s
a
n
d
F
u
tu
re
Ne
tw
o
rk
s
(
ICUFN)
,
p
p
.
3
3
3
-
337
,
2
0
1
3
,
d
o
i
:
1
0
.
1
1
0
9
/I
CUFN.
2
0
1
3
.
6
6
1
4
8
3
6
.
[1
1
]
Zh
a
o
,
H.,
Y
u
,
H.,
M
a
o
,
T
.
,
Zh
a
n
g
,
M.,
a
n
d
Zh
u
,
H
.
,
“
V
e
h
icle
A
c
c
id
e
n
t
Risk
P
re
d
icti
o
n
Ov
e
r
A
d
a
Bo
o
st
f
ro
m
V
A
NET
s
,”
2
0
1
8
1
0
th
I
n
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
I
n
telli
g
e
n
t
Hu
m
a
n
-
M
a
c
h
i
n
e
S
y
ste
ms
a
n
d
Cy
b
e
rn
e
ti
c
s
(
IH
M
S
C)
,
2
0
1
8
,
p
p
.
3
9
-
43
,
d
o
i:
1
0
.
1
1
0
9
/IH
M
S
C.
2
0
1
8
.
1
0
1
1
5
.
[1
2
]
Ch
e
n
g
,
N.,
L
y
u
,
F
.
,
C
h
e
n
,
J.,
Xu
,
W
.
,
Zh
o
u
,
H.,
Zh
a
n
g
,
S
.
,
a
n
d
S
h
e
n
,
X
.,
“
Big
d
a
ta
d
riv
e
n
v
e
h
icu
lar
n
e
tw
o
rk
s
,
”
IEE
E
Ne
two
rk
,
v
o
l
.
3
2
,
n
o
.
6
,
p
p
.
1
6
0
-
1
6
7
,
2
0
1
8
.
[1
3
]
G
a
wa
s,
M
a
h
a
d
e
v
A
.
,
M
a
n
a
s
M
u
lay
,
a
n
d
V
.
Bh
a
ti
a
,
“
Cro
ss
L
a
y
e
r
A
p
p
ro
a
c
h
f
o
r
Ne
ig
h
b
o
r
No
d
e
S
e
l
e
c
ti
o
n
in
V
A
NET
Ro
u
ti
n
g
,
”
2
0
1
8
1
1
t
h
In
ter
n
a
ti
o
n
a
l
S
y
mp
o
siu
m
o
n
C
o
mm
u
n
ica
t
io
n
S
y
ste
ms
,
Ne
two
rk
s
&
Dig
it
a
l
S
ig
n
a
l
Pro
c
e
ss
in
g
(
CS
NDS
P)
,
2
0
1
8
,
p
p
.
1
-
6
,
d
o
i
:
1
0
.
1
1
0
9
/C
S
ND
S
P
.
2
0
1
8
.
8
4
7
1
8
4
0
.
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:
2
0
8
8
-
8708
B
ig
d
a
ta
tr
a
ffic m
a
n
a
g
eme
n
t i
n
ve
h
icu
la
r
a
d
-
h
o
c
n
etw
o
r
k
(
T
a
n
ta
o
u
i
Mo
u
a
d
)
3491
[1
4
]
A
l
Na
jad
a
,
Ha
m
z
a
h
,
a
n
d
Im
a
d
M
a
h
g
o
u
b
.
,
“
Big
v
e
h
icu
lar
traff
ic
d
a
ta
m
in
in
g
:
T
o
w
a
rd
s
a
c
c
id
e
n
t
a
n
d
c
o
n
g
e
stio
n
p
re
v
e
n
ti
o
n
,”
2
0
1
6
In
ter
n
a
ti
o
n
a
l
W
ire
les
s
Co
mm
u
n
ica
ti
o
n
s
a
n
d
M
o
b
il
e
Co
m
p
u
ti
n
g
Co
n
fer
e
n
c
e
(IW
CM
C)
,
2
0
1
6
,
p
p
.
2
5
6
-
261
,
d
o
i:
1
0
.
1
1
0
9
/IW
CM
C.
2
0
1
6
.
7
5
7
7
0
6
7
[1
5
]
A
li
n
a
n
i
,
A
n
n
a
d
il
an
d
A
li
n
a
n
i
,
Ka
rim
.
,
“
Re
a
l
-
T
i
m
e
P
u
s
h
-
Ba
se
d
Da
ta
F
o
rw
a
rd
in
g
f
o
r
T
a
r
g
e
t
T
ra
c
k
in
g
in
V
e
h
icu
lar
Na
m
e
d
Da
ta
N
e
t
w
o
rk
in
g
,”
2
0
1
8
IEE
E
S
ma
rt
W
o
rl
d
,
U
b
iq
u
it
o
u
s
I
n
telli
g
e
n
c
e
&
Co
mp
u
ti
n
g
,
Ad
v
a
n
c
e
d
&
T
ru
ste
d
Co
mp
u
t
in
g
,
S
c
a
la
b
le
C
o
mp
u
ti
n
g
&
Co
mm
u
n
ica
ti
o
n
s,
Cl
o
u
d
&
Bi
g
Da
ta
C
o
mp
u
ti
n
g
,
I
n
ter
n
e
t
o
f
Peo
p
le
a
n
d
S
ma
rt
Cit
y
I
n
n
o
v
a
ti
o
n
(
S
m
a
rtW
o
rld
/
S
CAL
COM
/
UIC/
AT
C/
C
BDCo
m/
IOP/S
CI)
,
2
0
1
8
,
p
p
.
1
5
8
7
-
1
5
9
2
,
doi
:
1
0
.
1
1
0
9
/S
m
a
rtW
o
rld
.
2
0
1
8
.
0
0
2
7
2
.
[1
6
]
M
.
A
ru
n
,
a
n
d
B
.
P
a
n
d
e
y
,
“
A
s
y
m
m
e
tri
c
e
n
c
r
y
p
ti
o
n
b
a
se
d
se
c
u
re
a
n
d
e
f
f
ici
e
n
t
d
a
ta
g
a
th
e
rin
g
tec
h
n
i
q
u
e
in
V
A
NET
,
”
2
0
1
7
7
th
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Cl
o
u
d
C
o
mp
u
ti
n
g
,
D
a
t
a
S
c
ien
c
e
a
n
d
En
g
in
e
e
rin
g
-
Co
n
fl
u
e
n
c
e
,
2
0
1
7
,
p
p
.
3
6
9
-
372
,
d
o
i:
1
0
.
1
1
0
9
/CONF
L
UENCE.
2
0
1
7
.
7
9
4
3
1
7
7
.
[1
7
]
X
u
,
W
.
,
Zh
o
u
,
H.,
Ch
e
n
g
,
N.,
L
y
u
,
F
.
,
S
h
i,
W
.
,
Ch
e
n
,
J.,
a
n
d
S
h
e
n
,
X
.,
“
In
tern
e
t
o
f
v
e
h
icle
s
in
b
ig
d
a
ta
e
ra
,”
IEE
E/
CAA
J
o
u
rn
a
l
o
f
A
u
t
o
m
a
ti
c
a
S
in
ica
,
2
0
1
7
,
v
o
l.
5
,
n
o
.
1
,
p
p
.
1
9
-
35
,
d
o
i:
1
0
.
1
1
0
9
/JA
S
.
2
0
1
7
.
7
5
1
0
7
3
6
.
[1
8
]
A
l
Na
j
a
d
a
,
Ha
m
z
a
h
,
a
n
d
Im
a
d
M
a
h
g
o
u
b
,
“
A
u
to
n
o
m
o
u
s
v
e
h
icle
s
sa
fe
-
o
p
ti
m
a
l
traje
c
to
r
y
se
l
e
c
ti
o
n
b
a
se
d
o
n
b
ig
d
a
ta
a
n
a
ly
sis
a
n
d
p
re
d
e
f
in
e
d
u
se
r
p
re
f
e
r
e
n
c
e
s
,
”
2
0
1
6
IEE
E
7
t
h
An
n
u
a
l
Ub
iq
u
i
to
u
s
Co
mp
u
t
in
g
,
El
e
c
tro
n
ics
&
M
o
b
il
e
Co
mm
u
n
ica
ti
o
n
C
o
n
fer
e
n
c
e
(
UEM
CON)
,
2
0
1
6
,
p
p
. 1
-
6
,
d
o
i
:
1
0
.
1
1
0
9
/UEM
CON
.
2
0
1
6
.
7
7
7
7
9
2
2
.
[1
9
]
N
.
S
h
a
ik
,
an
d
P
.
K
.
M
a
l
ik
.
,
“
A
R
e
tro
sp
e
c
ti
o
n
o
f
Ch
a
n
n
e
l
Esti
m
a
ti
o
n
T
e
c
h
n
iq
u
e
s
f
o
r
5
G
W
irele
ss
C
o
m
m
u
n
ica
ti
o
n
s:
Op
p
o
r
tu
n
it
ies
a
n
d
C
h
a
ll
e
n
g
e
s
,”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Ad
v
a
n
c
e
d
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
lo
g
y
,
v
o
l.
29
,
n
o
.
5
,
p
p
.
8
4
6
9
-
8
4
7
9
,
2
0
2
0
.
[2
0
]
X
iao
y
o
n
g
,
L
u
W
e
i,
a
n
d
Zh
a
n
g
F
e
n
g
,
“
Histo
ry
,
c
u
rre
n
t
sta
tu
s
a
n
d
fu
tu
re
o
f
b
ig
d
a
ta
m
a
n
a
g
e
m
e
n
t
s
y
s
tem
s
,
”
J
o
u
rn
a
l
o
f
S
o
ft
w
a
re
,
v
o
l.
3
0
,
n
o
1
,
p
p
.
1
2
7
-
1
4
1
,
2
0
1
9
,
d
o
i:
1
0
.
1
3
3
2
8
/j
.
c
n
k
i.
j
o
s.0
0
5
6
4
4
.
[2
1
]
L
in
,
S
.
,
L
u
o
,
B.
,
L
u
o
,
J.,
W
a
n
g
,
Z.
,
a
n
d
W
e
i,
Y.
,
“
G
u
izh
o
u
Big
D
a
ta
M
a
n
a
g
e
m
e
n
t
S
y
ste
m
a
n
d
Ke
y
T
e
c
h
n
o
l
o
g
y
,”
2
0
1
8
2
6
t
h
I
n
t
.
C
o
n
fer
e
n
c
e
o
n
Ge
o
in
f
o
rm
a
ti
c
s
,
p
p
.
1
-
7
,
2
0
1
8
,
d
o
i:
1
0
.
1
1
0
9
/G
EOINFORM
A
T
ICS
.
2
0
1
8
.
8
5
5
7
1
0
9
.
[2
2
]
Ch
e
n
,
H.
Y.
,
“
De
sig
n
a
n
d
Re
a
l
iza
ti
o
n
o
f
a
Distrib
u
ted
Big
Da
ta
M
a
n
a
g
e
m
e
n
t
S
y
ste
m
,”
Ad
v
a
n
c
e
d
M
a
ter
ia
ls
Res
e
a
rc
h
,
v
o
l.
1
0
3
0
,
p
p
.
1
9
0
0
-
1
9
0
4
,
2
0
1
4
,
d
o
i:
1
0
.
4
0
2
8
/www
.
sc
ien
ti
f
ic.n
e
t/
a
m
r.
1
0
3
0
-
1
0
3
2
.
1
9
0
0
.
[2
3
]
Ra
j,
A
.
,
a
n
d
D’S
o
u
z
a
,
R.
,
“
A
Re
v
ie
w
o
n
Ha
d
o
o
p
Eco
S
y
ste
m
fo
r
Big
Da
ta
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
S
c
ien
ti
f
ic
Res
e
a
rc
h
in
C
o
mp
u
ter
S
c
ien
c
e
,
E
n
g
i
n
e
e
rin
g
a
n
d
I
n
fo
rm
a
ti
o
n
T
e
c
h
n
o
l
o
g
y
,
2
0
1
9
,
d
o
i
:
1
0
.
3
2
6
2
8
/C
S
E
IT
1
9
5
1
7
2
.
[2
4
]
Bru
n
sw
ick
e
r,
S
.
,
Be
rti
n
o
,
E
.
,
a
n
d
M
a
tei,
S
.
,
“
Big
d
a
ta
f
o
r
o
p
e
n
d
i
g
it
a
l
in
n
o
v
a
ti
o
n
–
a
re
se
a
rc
h
ro
a
d
m
a
p
,”
Bi
g
D
a
ta
Res
e
a
rc
h
,
v
o
l.
2
,
n
o
.
2
,
p
p
.
53
-
58
,
d
o
i
:
1
0
.
1
0
1
6
/j
.
b
d
r.
2
0
1
5
.
0
1
.
0
0
8
.
[2
5
]
Bu
k
h
a
ri,
S
.
S
.
,
P
a
rk
,
J.,
a
n
d
S
h
i
n
,
D.
R.
,
“
Ha
d
o
o
p
b
a
se
d
De
m
o
g
ra
p
h
y
Big
Da
ta
M
a
n
a
g
e
m
e
n
t
S
y
ste
m
,”
2
0
1
8
1
9
t
h
IEE
E/
ACIS
In
ter
n
a
ti
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
S
o
ft
w
a
re
En
g
in
e
e
rin
g
,
Arti
fi
c
i
a
l
I
n
telli
g
e
n
c
e
,
N
e
two
rk
in
g
a
n
d
Pa
ra
ll
e
l/
Distri
b
u
te
d
Co
m
p
u
t
in
g
(
S
NPD)
,
2
0
1
8
,
p
p
.
9
3
-
98
,
d
o
i:
1
0
.
1
1
0
9
/sn
p
d
.
2
0
1
8
.
8
4
4
1
0
3
2
.
[2
6
]
M
a
li
k
,
P
.
K.,
W
a
d
h
w
a
,
D.
S.
a
n
d
Kh
in
d
a
,
J.
S.
,
“
A
S
u
rv
e
y
o
f
D
e
v
ice
to
De
v
ice
a
n
d
Co
o
p
e
ra
ti
v
e
Co
m
m
u
n
ica
ti
o
n
f
o
r
th
e
F
u
t
u
re
Ce
ll
u
lar Ne
tw
o
rk
s
,”
In
t
J
W
ire
les
s In
f
Ne
two
rk
s
,
p
p
.
1
-
2
2
,
2
0
2
0
,
d
o
i:
1
0
.
1
0
0
7
/s
1
0
7
7
6
-
020
-
0
0
4
8
2
-
8
.
[2
7
]
A
.
Ra
h
i
m
,
P
.
K
.
M
a
ll
ik
,
V
.
A
.
S
a
n
k
a
r
P
o
n
n
a
p
a
ll
i
.,
"
F
ra
c
tal
A
n
ten
n
a
De
sig
n
f
o
r
Ov
e
rtak
in
g
o
n
Hig
h
w
a
y
s
in
5
G
V
e
h
icu
lar
Co
m
m
u
n
ica
ti
o
n
A
d
-
hoc
Ne
tw
o
rk
s
En
v
iro
n
m
e
n
t
,
"
In
te
rn
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
En
g
in
e
e
rin
g
a
n
d
Ad
v
a
n
c
e
d
T
e
c
h
n
o
l
o
g
y
(
IJ
EA
T
)
,
v
o
l
.
9
,
n
o
.
1
S
6
,
2
0
1
9
,
p
p
1
5
7
-
1
6
0
,
d
o
i
:
1
0
.
3
5
9
4
0
/i
jea
t.
A
1
0
3
1
.
1
2
9
1
S
6
1
9
.
[2
8
]
Ho
,
T
in
Ka
m
,
“
Ra
n
d
o
m
D
e
c
isio
n
F
o
re
sts
,
”
Pro
c
e
e
d
in
g
s
o
f
3
rd
in
t
e
rn
a
ti
o
n
a
l
c
o
n
fer
e
n
c
e
o
n
d
o
c
u
m
e
n
t
a
n
a
lys
is
a
n
d
re
c
o
g
n
it
i
o
n
,
1
9
9
5
,
p
p
.
2
7
8
-
2
8
2
.
[2
9
]
L
e
o
Bre
i
m
a
n
,
“
Ra
n
d
o
m
F
o
re
sts,
”
M
a
c
h
in
e
L
e
a
rn
i
n
g
,
v
o
l.
4
5
,
n
o
.
1
,
p
p
.
5
-
3
2
,
2
0
0
1
.
Evaluation Warning : The document was created with Spire.PDF for Python.