I
A
E
S
I
n
t
e
r
n
at
io
n
al
Jou
r
n
al
of
A
r
t
if
ic
ia
l
I
n
t
e
ll
ig
e
n
c
e
(
I
J
-
A
I
)
V
ol
.
10
, N
o. 1, M
a
r
c
h
2021
, pp.
224
~
233
I
S
S
N
:
2252
-
8938
,
D
O
I
:
10.11591/
ij
a
i.
v
10
.i
1
.pp
224
-
233
224
Jou
r
n
al
h
om
e
page
:
ht
tp
:
//
ij
ai
.
ia
e
s
c
or
e
.c
om
R
e
c
e
n
t
d
e
v
e
l
op
m
e
n
t
of
sm
ar
t
t
r
af
f
i
c
l
i
gh
t
s
A
’
is
ya N
u
r
A
u
li
a Y
u
s
u
f
,
A
j
ib
S
e
t
yo A
r
if
in
, F
it
r
i
Y
u
li
Z
u
lk
if
li
Department of Electrical En
gineering, Universit
as Indonesia
,
Indonesia
A
r
t
ic
le
I
n
f
o
A
B
S
T
R
A
C
T
A
r
ti
c
le
h
is
to
r
y
:
R
e
c
e
iv
e
d S
e
p
26, 2020
R
e
vi
s
e
d N
ov 3, 2020
A
c
c
e
pt
e
d D
e
c
14, 2020
Increased
traffic
flow
causes
congestion
,
especially
in
large
cities
.
Even
though
congestion
is
not
unusual,
traffic
jams
still
r
esult
in
ver
y
high
economic
and soci
al loss
es.
Several f
actors caus
e
congesti
on, one
of
which is
traffic
lights.
Theref
ore,
a
mechanism
is
needed
so
that
traffic
lig
hts
can
intelligently a
nd adaptive
ly manage
signal time a
llocation ac
cording to tr
affic
flow
conditions.
A
traffic
light
with
this
type
of
mechanism
is
kno
wn
as
a
smart
traffic
light.
Smart
traffic
light
cycle
settings
can
be
g
rouped
b
ased
on
the
traffic
density,
scenarios
for
emergency
vehicles,
and
the
inter
ests
of
pedestrians.
This
paper
analyzes
the
methods
and
technologies
used
in
the
development
of
smart
tr
affic
light
technology
from
the
perspective
o
f
these
three
situations
as
well
as
the
development
of
smart
traffic
light
tech
nology
in the futur
e
.
K
e
y
w
o
r
d
s
:
A
da
pt
iv
e
t
r
a
f
f
ic
l
ig
ht
I
nt
e
ll
ig
e
nt
t
r
a
ns
por
ta
ti
on
s
ys
te
m
M
a
c
hi
ne
l
e
a
r
ni
ng
S
m
a
r
t
c
it
y
S
m
a
r
t
tr
a
f
f
ic
li
gh
t
This is an
open
acce
ss artic
le unde
r the
CC BY
-
SA
license.
C
or
r
e
s
pon
di
n
g A
u
th
or
:
A
’
is
ya
N
ur
A
ul
ia
Y
us
uf
D
e
pa
r
tm
e
nt
of
E
le
c
tr
ic
a
l
E
ngi
ne
e
r
in
g
U
ni
ve
r
s
it
a
s
I
ndone
s
ia
K
ukus
a
n,
B
e
ji
, K
ot
a
D
e
pok, J
a
w
a
B
a
r
a
t,
I
ndone
s
ia
16425
E
m
a
il
:
a
is
ya
.nur
@
ui
.a
c
.i
d
1.
I
N
T
R
O
D
U
C
T
I
O
N
I
nc
r
e
a
s
e
s
in
tr
a
f
f
ic
f
lo
w
,
e
s
p
e
c
ia
ll
y
in
l
a
r
ge
c
it
ie
s
,
c
a
u
s
e
th
e
p
r
obl
e
m
of
c
onge
s
ti
on.
I
n
a
ddi
ti
on
to
th
e
tr
a
f
f
ic
de
ns
it
y,
th
e
popula
ti
on,
e
c
onomy,
a
nd
in
f
r
a
s
tr
uc
tu
r
e
i
nf
lu
e
nc
e
c
onge
s
ti
on.
E
ve
n
th
ough c
onge
s
ti
on
is
not
unus
ua
l,
tr
a
f
f
ic
ja
m
s
s
ti
ll
c
a
us
e
ve
r
y
hi
gh
lo
s
s
e
s
bot
h
e
c
onomi
c
a
ll
y
a
nd
s
o
c
ia
ll
y.
B
a
s
e
d
on
r
e
s
e
a
r
c
h
c
onduc
te
d by I
N
R
I
X
i
n 2018
[
1
]
, i
n
I
s
ta
nbul
(
T
ur
ke
y)
a
nd M
os
c
ow
(
R
us
s
ia
)
, t
he
t
im
e
l
os
s
e
s
of
m
ot
or
is
ts
due
to
tr
a
f
f
ic
ja
m
s
r
e
a
c
he
d
210
a
nd
157
hour
s
,
r
e
s
pe
c
ti
ve
ly
.
I
n
B
os
to
n
(
U
ni
te
d
S
ta
te
s
)
,
c
onge
s
ti
on
c
a
us
e
d
164
hour
s
to
be
lo
s
t,
w
it
h
lo
s
s
e
s
pe
r
dr
iv
e
r
r
e
a
c
hi
ng
$2,291
a
nd
c
it
y
da
m
a
ge
s
a
s
hi
gh
a
s
$4.1
bi
ll
io
n.
I
n
I
ndone
s
ia
a
lo
ne
,
in
2017
[
2]
,
c
onge
s
ti
on
c
a
us
e
d
a
n
a
ve
r
a
ge
of
56
hour
s
o
f
ti
m
e
lo
s
s
.
J
a
ka
r
ta
,
in
th
e
s
a
m
e
y
e
a
r
,
be
c
a
m
e
th
e
12t
h m
os
t
c
onge
s
te
d
c
it
y i
n t
he
w
or
ld
, w
it
h a
l
os
s
of
63 hour
s
l
os
t
due
t
o t
r
a
f
f
ic
. T
a
bl
e
1 s
how
s
t
he
i
m
pa
c
t
of
c
onge
s
ti
on i
n t
e
r
m
s
of
t
im
e
l
os
s
.
T
a
bl
e
2 s
how
s
t
he
e
c
onomi
c
da
m
a
ge
c
a
u
s
e
d by c
ong
e
s
ti
on.
I
n
a
ddi
ti
on
to
th
e
ti
m
e
a
nd
e
c
onomi
c
im
pa
c
t
s
,
c
onge
s
ti
on
n
e
ga
ti
ve
ly
im
pa
c
ts
m
ot
or
is
ts
w
ho
a
r
e
tr
a
ppe
d
in
tr
a
f
f
ic
.
F
r
om
th
e
ps
yc
hol
ogi
c
a
l
pe
r
s
pe
c
ti
ve
,
[
3]
s
ta
te
s
th
a
t
c
onge
s
ti
on
c
a
n
c
a
u
s
e
s
tr
e
s
s
a
nd
a
ggr
e
s
s
iv
e
b
e
ha
vi
our
.
A
c
c
or
di
ng
to
[
4]
,
s
e
v
e
r
a
l
f
a
c
to
r
s
c
a
us
e
c
ong
e
s
ti
on,
s
uc
h
a
s
r
oa
d
n
a
r
r
ow
in
g,
tr
a
f
f
ic
de
ns
it
y,
a
nd
tr
a
f
f
ic
li
ght
s
.
T
he
f
ix
e
d
c
yc
le
m
e
th
od,
w
hi
c
h
is
s
ti
ll
us
e
d
in
m
os
t
tr
a
f
f
ic
li
ght
s
,
is
c
ur
r
e
nt
ly
c
ons
id
e
r
e
d
in
e
f
f
ic
ie
nt
be
c
a
us
e
it
in
c
r
e
a
s
e
s
tr
a
f
f
ic
de
ns
it
y
a
nd
c
onge
s
ti
on,
e
s
p
e
c
ia
ll
y
on
r
oa
ds
th
a
t
ha
ve
hi
gh
tr
a
f
f
ic
f
lo
w
vol
um
e
s
[
5]
.
T
he
r
e
f
or
e
,
a
m
e
c
ha
ni
s
m
is
ne
e
de
d
s
o
th
a
t
tr
a
f
f
ic
li
ght
s
c
a
n
in
te
ll
ig
e
nt
ly
a
nd
a
da
pt
iv
e
ly
m
a
na
ge
s
ig
na
l
ti
m
e
a
ll
oc
a
ti
on
a
c
c
or
di
ng
to
tr
a
f
f
ic
f
lo
w
c
ondi
ti
ons
.
T
hi
s
ty
pe
of
m
e
c
ha
ni
s
m
ga
ve
r
is
e
t
o t
he
ne
w
t
e
r
m
“
s
m
a
r
t
tr
a
f
f
ic
l
ig
ht
”
.
I
n
ge
ne
r
a
l,
th
e
d
e
ve
lo
pm
e
nt
of
s
m
a
r
t
tr
a
f
f
ic
li
ght
te
c
hnol
ogy
ha
s
be
e
n
di
s
c
us
s
e
d
in
r
e
s
e
a
r
c
h
[5
-
8]
.
H
ow
e
ve
r
,
th
e
pr
e
vi
ous
pa
pe
r
ha
s
not
th
or
oughly
di
s
c
us
s
e
d
th
e
te
c
hnol
ogy,
bot
h
in
te
r
m
s
of
ha
r
dw
a
r
e
a
nd
s
of
twa
r
e
,
a
s
w
e
ll
a
s
f
ur
th
e
r
de
ve
lo
pm
e
nt
of
s
m
a
r
t
tr
a
f
f
ic
li
gh
t
.
R
e
s
e
a
r
c
h
r
e
la
te
d
to
s
m
a
r
t
tr
a
f
f
ic
li
ght
s
ha
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
r
ti
f
I
nt
e
ll
I
S
S
N
:
2252
-
8938
R
e
c
e
nt
de
v
e
lo
pm
e
nt
of
s
m
a
r
t
tr
af
fi
c
l
ig
ht
s
(
A
’
is
y
a N
ur
A
ul
ia
Y
us
uf
)
225
pr
oduc
e
d
tr
a
f
f
ic
li
ght
s
th
a
t
c
a
n
a
d
a
pt
to
c
e
r
ta
in
tr
a
f
f
ic
s
it
ua
ti
ons
.
S
m
a
r
t
tr
a
f
f
ic
li
ght
c
yc
le
s
e
tt
in
gs
c
a
n
be
gr
oupe
d
ba
s
e
d
on
th
e
tr
a
f
f
ic
de
ns
it
y,
s
c
e
na
r
io
s
f
or
e
m
e
r
ge
nc
y
ve
hi
c
le
s
,
a
nd
th
e
in
te
r
e
s
ts
of
th
e
pe
de
s
tr
ia
n.
T
hi
s
pa
pe
r
a
na
ly
z
e
s
th
e
m
e
th
ods
a
nd
te
c
hnol
ogi
e
s
us
e
d
in
th
e
de
ve
lo
pm
e
nt
of
s
m
a
r
t
tr
a
f
f
ic
li
ght
te
c
hnol
ogy
f
r
om
th
e
pe
r
s
pe
c
ti
ve
s
of
th
e
s
e
th
r
e
e
s
it
ua
ti
on
s
.
A
s
nove
lt
ie
s
of
th
is
pa
pe
r
a
r
e
c
om
pr
e
he
n
s
iv
e
r
e
vi
e
w
a
nd
pr
e
di
c
ti
on of
t
he
de
ve
lo
pm
e
nt
of
s
m
a
r
t
tr
a
f
f
ic
l
ig
ht
t
e
c
hnol
ogy
in
t
he
f
ut
ur
e
. T
he
c
om
pos
it
io
n of
t
hi
s
pa
pe
r
i
s
:
c
ha
pt
e
r
2
di
s
c
us
s
e
s
th
e
c
la
s
s
if
ic
a
ti
on
of
c
ur
r
e
nt
s
m
a
r
t
tr
a
f
f
ic
li
ght
te
c
hnol
ogy,
c
ha
pt
e
r
3
de
s
c
r
ib
e
s
th
e
r
e
c
e
nt
de
ve
lo
pm
e
nt
s
of
s
m
a
r
t
tr
a
f
f
ic
l
ig
ht
s
, a
nd t
he
c
onc
lu
s
io
n
s
a
r
e
pr
e
s
e
nt
e
d i
n c
ha
pt
e
r
4.
T
a
bl
e
1
. L
os
s
e
s
i
n l
a
r
ge
c
it
ie
s
due
t
o c
onge
s
ti
on
[
2]
R
a
nk
C
i
t
y
C
ount
r
y
C
ont
i
ne
nt
P
e
a
k H
our
s
S
pe
nt
i
n
C
onge
s
t
i
on
I
nr
i
x C
onge
s
t
i
on
I
nde
x
A
ve
r
a
ge
C
onge
s
t
i
on
R
a
t
e
1
L
os
A
nge
l
e
s
;
C
A
U
S
A
N
or
t
h
A
m
e
r
i
c
a
102
18.3
12%
11
B
a
ngkok
T
ha
i
l
a
nd
A
s
i
a
64
12.5
23%
12
J
a
ka
r
t
a
I
ndone
s
i
a
A
s
i
a
63
13.4
20%
13
W
a
s
hi
ngt
on;
D
C
U
S
A
N
or
t
h A
m
e
r
i
c
a
63
10.8
11%
24
R
i
o de
J
a
ne
i
r
o
B
r
a
z
i
l
S
out
h A
m
e
r
i
c
a
51
10.6
15%
25
M
uni
c
h
G
e
r
m
a
ny
E
ur
ope
51
9.1
16%
T
a
bl
e
2
. E
c
onomi
c
l
os
s
e
s
due
t
o
c
onge
s
ti
on
[
1]
U
r
ba
n A
r
e
a
H
our
s
L
os
t
i
n
C
onge
s
t
i
on
(
R
a
nk 2018)
Y
e
a
r
O
ve
r
Y
e
a
r
C
ha
nge
I
nne
r
C
i
t
y L
a
s
t
-
m
i
l
e
T
r
a
ve
l
T
i
m
e
(
m
i
nut
e
s
)
I
nne
r
C
i
t
y
L
a
s
t
-
m
i
l
e
S
pe
e
d (
m
ph)
C
os
t
of
C
onge
s
t
i
on
(
pe
r
dr
i
ve
r
)
C
os
t
of
C
onge
s
t
i
on
(
pe
r
c
i
t
y)
B
os
t
on, M
A
164 (
1)
-
10%
6
11
$2,291
$ 4.1B
W
a
s
hi
ngt
on, D
C
155 (
2)
-
3%
5
11
$2,161
$ 4.6B
C
hi
c
a
go, I
L
138 (
4)
4%
5
12
$1,920
$ 6.2B
L
ondon
227 (
1)
1%
8
7
₤
1,680
₤
4.9B
B
i
r
m
i
ngha
m
134 (
12)
-
4%
5
12
₤
994
₤
388.7M
G
l
a
s
gow
99
(
16)
4%
5
13
₤
736
₤
320.4M
2.
R
E
S
E
A
R
C
H
M
E
T
H
O
D
A
tr
a
f
f
ic
c
ont
r
ol
m
e
c
ha
ni
s
m
w
a
s
f
ir
s
t
a
tt
e
m
pt
e
d
in
T
ol
e
do,
O
hi
o,
in
1908,
in
vol
vi
ng
s
e
m
a
phor
e
s
ig
na
ls
f
r
om
a
to
w
e
r
in
th
e
m
id
d
le
of
a
n
in
te
r
s
e
c
ti
on
c
ont
r
ol
le
d
by
th
e
pol
ic
e
in
s
id
e
.
T
he
a
dopt
io
n
o
f
tr
a
f
f
ic
li
ght
te
c
hnol
ogy
be
ga
n
a
f
te
r
H
e
nr
y
F
or
d
in
tr
oduc
e
d
th
e
m
ode
l
T
in
1908,
w
hi
c
h
be
ga
n
be
in
g
m
a
s
s
-
pr
oduc
e
d
in
1913
[
9]
.
I
n
1920,
W
il
li
a
m
P
ot
ts
c
r
e
a
te
d
th
e
f
ir
s
t
f
our
-
w
a
y,
th
r
e
e
-
c
ol
or
tr
a
f
f
ic
li
gh
ts
by
a
ddi
ng
a
n
a
m
be
r
"
c
a
ut
io
n"
li
ght
,
w
he
r
e
a
s
pr
e
vi
ous
tr
a
f
f
ic
li
ght
s
ha
d
in
c
lu
de
d
onl
y
two
s
ig
na
l
li
ght
s
,
r
e
d
a
nd
gr
e
e
n.
T
h
e
a
ddi
ti
on
w
a
s
m
a
de
to
in
c
r
e
a
s
e
th
e
s
a
f
e
ty
of
th
e
dr
iv
in
g
pr
oc
e
s
s
.
T
hi
s
tr
a
f
f
ic
li
ght
de
s
ig
n
be
c
a
m
e
s
ta
nda
r
d
in
th
e
m
id
-
1930s
a
nd
w
a
s
in
s
ta
ll
e
d
in
D
e
tr
oi
t,
M
ic
hi
ga
n
[
10]
.
T
he
de
ve
lo
pm
e
nt
of
tr
a
f
f
ic
li
gh
ts
ha
s
c
ont
in
ue
d
th
r
ough
th
e
a
ppl
ic
a
ti
on
of
ne
w
te
c
hnol
ogi
e
s
or
c
om
bi
na
ti
ons
of
e
xi
s
ti
ng
te
c
hnol
ogi
e
s
.
F
ig
ur
e
1
s
how
s
th
e
c
la
s
s
if
ic
a
ti
on of
t
he
de
ve
lo
pm
e
nt
of
t
he
t
r
a
f
f
ic
l
ig
ht
t
e
c
hnol
ogy tha
t
e
xi
s
ts
t
o
da
y.
F
ig
ur
e
1. S
m
a
r
t
tr
a
f
f
ic
l
ig
ht
c
la
s
s
if
ic
a
ti
on
I
n
ge
ne
r
a
l,
r
e
s
e
a
r
c
h
on
tr
a
f
f
ic
li
ght
s
f
oc
us
e
s
m
or
e
on
s
e
tt
in
g
s
ig
na
l
s
c
he
dul
in
g
in
a
c
c
or
da
nc
e
w
it
h
th
e
m
a
in
m
ot
iv
a
ti
ons
of
tr
a
f
f
ic
li
ght
s
.
B
a
s
e
d
on
th
e
ir
m
ot
iv
a
ti
on,
s
m
a
r
t
tr
a
f
f
ic
li
ght
s
c
a
n
be
di
vi
de
d
in
to
tr
a
f
f
ic
li
ght
s
to
r
e
duc
e
c
onge
s
ti
on
a
nd
gi
ve
pr
i
or
it
y
to
ve
hi
c
le
s
i
n
e
m
e
r
ge
nc
y s
it
ua
ti
ons
or
tr
a
f
f
ic
li
ght
s
w
hos
e
s
c
he
dul
in
g
a
dj
us
ts
to
th
e
pr
e
s
e
nc
e
a
nd
num
be
r
of
pe
de
s
tr
ia
ns
.
S
tu
di
e
s
[
11
-
44]
f
oc
us
on
s
c
he
dul
in
g
tr
a
f
f
ic
li
ght
s
to
r
e
duc
e
c
onge
s
ti
on.
W
it
h
th
is
m
ot
iv
a
ti
on,
tr
a
f
f
ic
li
ght
s
de
te
c
t
th
e
num
be
r
or
le
ngt
h
of
ve
hi
c
le
que
ue
s
in
one
la
ne
a
nd
c
om
pa
r
e
th
is
v
a
lu
e
to
th
a
t
of
ot
he
r
la
ne
s
.
A
l
onge
r
gr
e
e
n
li
ght
w
i
ll
be
gi
ve
n
f
or
la
ne
s
w
it
h
gr
e
a
te
r
num
be
r
s
of
ve
hi
c
le
s
or
que
ue
le
ngt
h
s
.
S
tu
di
e
s
[
45
-
52]
f
oc
us
on
s
c
he
dul
in
g
tr
a
f
f
ic
li
ght
s
f
or
e
m
e
r
ge
nc
y
s
it
ua
ti
on
s
.
B
a
s
ic
a
ll
y,
w
it
h
th
is
m
ot
iv
a
ti
on,
tr
a
f
f
ic
l
ig
ht
s
de
te
c
t
a
ppr
oa
c
hi
ng
e
m
e
r
ge
n
c
y
ve
hi
c
le
s
a
nd
a
s
s
ig
n
a
gr
e
e
n
li
ght
to
th
e
la
ne
th
a
t
th
e
a
ppr
oa
c
hi
ng
e
m
e
r
ge
nc
y
ve
hi
c
le
i
s
in
.
T
hi
s
m
e
c
h
a
ni
s
m
e
n
s
ur
e
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8938
I
nt
J
A
r
ti
f
I
nt
e
ll
,
V
ol
.
10
, N
o.
1, M
a
r
c
h
20
21
:
224
–
233
226
th
a
t
e
m
e
r
ge
nc
y
ve
hi
c
le
s
a
lwa
y
s
ha
ve
th
e
gr
e
e
n
li
ght
s
e
ve
r
y
t
im
e
th
e
y
pa
s
s
th
r
ough
a
tr
a
f
f
ic
li
ght
s
o
th
a
t
e
m
e
r
ge
nc
y
ve
hi
c
le
s
c
a
n
r
e
a
c
h
th
e
ir
de
s
ti
na
ti
on
a
s
s
oon
a
s
pos
s
ib
le
.
I
n
s
tu
di
e
s
[
53
-
56
]
,
th
e
m
ot
iv
a
ti
on
of
th
e
tr
a
f
f
ic
li
ght
de
s
ig
n
is
to
d
e
te
c
t
p
e
de
s
tr
ia
ns
a
nd
le
t
th
e
m
c
r
os
s
th
e
r
oa
d
f
ir
s
t.
A
de
ta
il
e
d
e
xpl
a
na
ti
on
of
e
a
c
h
s
tu
dy i
s
pr
e
s
e
nt
e
d i
n t
he
f
ol
lo
w
in
g c
ha
pt
e
r
s
.
3.
R
E
S
U
L
T
S
A
N
D
D
I
S
C
U
S
S
I
O
N
B
a
s
e
d
on
th
e
ir
m
ot
iv
a
ti
on,
s
m
a
r
t
t
r
a
f
f
ic
li
gh
ts
c
a
n
be
di
vi
de
d
i
nt
o
tr
a
f
f
ic
li
ght
s
to
r
e
duc
e
c
onge
s
ti
on
a
nd give
pr
io
r
it
y t
o ve
hi
c
le
s
i
n e
m
e
r
ge
nc
y
s
it
ua
ti
ons
or
t
r
a
f
f
ic
l
i
ght
s
w
hos
e
s
c
h
e
dul
in
g a
dj
us
ts
t
o t
he
pr
e
s
e
n
c
e
a
nd numbe
r
of
pe
de
s
tr
ia
ns
.
3.1.
S
m
ar
t
t
r
af
f
ic
l
ig
h
t
s
f
or
c
on
ge
s
t
io
n
r
e
d
u
c
t
io
n
I
n
[
11]
,
a
n
e
m
e
r
ge
nc
y
tr
a
f
f
ic
c
ont
r
ol
s
ys
te
m
f
or
a
n
in
te
r
s
e
c
ti
o
n
in
th
e
e
ve
nt
of
a
n
a
c
c
id
e
nt
,
w
it
h
de
a
dl
oc
k
r
e
c
ove
r
y,
li
ve
lo
c
k
pr
e
ve
nt
io
n,
a
nd
c
onf
li
c
t
r
e
s
ol
ut
io
n
,
is
de
s
ig
ne
d
ba
s
e
d
on
P
e
tr
i
ne
ts
(
P
N
s
)
.
A
P
N
is
a
m
ode
l
f
or
s
im
ul
a
ti
ng
a
nd
a
na
ly
z
in
g c
om
pl
e
x
di
s
c
r
e
te
e
ve
nt
dyna
m
ic
s
y
s
te
m
s
.
I
n
[
12]
de
te
r
m
in
e
s
th
e
be
s
t
lo
c
a
ti
on
f
or
in
s
ta
ll
in
g
s
e
ns
or
ne
twor
ks
in
tr
a
f
f
ic
ne
twor
ks
.
I
n
th
is
s
tu
dy,
th
r
e
e
ty
pe
s
of
a
ge
nt
s
a
r
e
de
s
ig
ne
d
s
o
th
a
t
th
e
m
in
im
um
t
r
a
ve
l
ti
m
e
c
a
n be
a
c
hi
e
ve
d:
a
t
r
a
f
f
ic
li
ght
m
a
na
ge
m
e
nt
a
ge
nt
, a
t
r
a
f
f
ic
de
te
c
ti
on a
ge
nt
, a
n
d
a
tr
a
f
f
ic
li
ght
c
ont
r
ol
a
ge
nt
a
t
a
n
in
te
r
s
e
c
ti
on.
I
n
[
13]
us
e
s
a
w
ir
e
le
s
s
s
e
n
s
or
ne
twor
k
(
W
S
N
)
th
a
t
is
im
pl
e
m
e
nt
e
d
a
t
a
c
r
os
s
r
oa
ds
,
a
nd
th
e
s
e
s
e
ns
or
s
m
a
ke
de
c
is
io
ns
a
bout
tr
a
f
f
ic
m
ove
m
e
nt
s
to
m
in
i
m
iz
e
th
e
w
a
it
in
g
ti
m
e
s
a
nd
a
ve
r
a
ge
que
ue
le
ngt
hs
.
T
he
a
lg
or
it
hm
pr
opos
e
d
in
th
is
s
ys
te
m
opt
im
iz
e
s
tr
a
f
f
ic
li
ght
s
c
he
dul
in
g w
it
hout
c
ha
ngi
ng t
he
or
de
r
of
t
he
c
ur
r
e
nt
l
ig
ht
c
yc
le
s
s
o t
ha
t
r
oa
d us
e
r
s
a
r
e
not
c
onf
us
e
d.
I
n
[
14]
,
a
s
ys
te
m
th
a
t
is
a
bl
e
to
r
e
c
ogni
z
e
tr
a
f
f
ic
li
ght
s
on
a
s
m
a
r
tp
hone
pl
a
tf
or
m
is
c
r
e
a
te
d.
T
he
pr
opos
e
d
s
ys
t
e
m
is
a
l
s
o
a
bl
e
to
r
e
c
ogni
z
e
th
e
tr
a
f
f
ic
li
ght
c
yc
le
.
I
n
[
15]
pr
opos
e
s
a
s
y
s
te
m
c
on
s
is
ti
ng
of
th
r
e
e
a
ge
nt
s
,
na
m
e
ly
,
tr
a
f
f
ic
li
ght
m
a
na
ge
m
e
nt
a
ge
nt
s
(
T
L
A
ge
nt
s
)
,
t
r
a
f
f
ic
ja
m
de
te
c
ti
on
a
ge
nt
s
(
T
J
a
m
A
ge
nt
s
)
a
nd
a
ge
nt
s
th
a
t
c
ont
r
ol
tr
a
f
f
ic
li
ght
s
a
t
in
te
r
s
e
c
ti
ons
(
I
nt
e
r
s
e
c
ti
on
A
ge
nt
s
)
.
A
T
L
A
ge
nt
is
pl
a
c
e
d
a
t
e
a
c
h
tr
a
f
f
ic
l
ig
ht
to
r
e
gul
a
te
th
e
c
ha
nge
s
in
th
e
li
ght
s
ig
na
ls
.
T
J
a
m
A
ge
nt
s
a
r
e
pl
a
c
e
d
in
ve
hi
c
le
s
a
nd
s
e
ns
or
s
in
s
ta
ll
e
d
in
s
e
ve
r
a
l
pl
a
c
e
s
a
nd
r
e
c
e
iv
e
tr
a
f
f
ic
in
f
or
m
a
ti
on.
A
I
nt
e
r
s
e
c
ti
onA
ge
nt
is
a
tr
a
f
f
ic
li
ght
c
om
m
uni
c
a
ti
on
s
ys
te
m
a
t
a
pa
r
ti
c
ul
a
r
i
nt
e
r
s
e
c
ti
on t
ha
t
r
e
c
e
iv
e
s
i
nf
or
m
a
ti
on f
r
om
t
he
ne
a
r
e
s
t
T
J
a
m
A
ge
nt
a
nd de
te
r
m
in
e
s
t
he
t
r
a
f
f
ic
l
ig
ht
c
yc
le
ba
s
e
d on tha
t
in
f
or
m
a
ti
on.
I
n
[
16]
ut
il
iz
e
s
R
F
I
D
t
e
c
hnol
ogy to de
te
c
t
tr
a
f
f
ic
j
a
m
s
. T
he
t
r
a
f
f
ic
l
ig
ht
c
yc
le
is
dyna
m
ic
a
ll
y r
e
gul
a
te
d ba
s
e
d on tr
a
f
f
ic
de
ns
it
y t
o m
in
im
iz
e
c
onge
s
ti
on w
it
h t
he
he
lp
of
a
n i
nt
e
r
ne
t
of
t
hi
ngs
(
I
oT
)
s
e
ns
or
.
E
a
c
h
ve
hi
c
le
ha
s
a
pa
s
s
iv
e
R
F
I
D
ta
g
in
s
ta
ll
e
d,
a
nd
th
e
s
e
ns
or
r
e
c
or
ds
th
e
num
be
r
of
ve
hi
c
le
s
pa
s
s
in
g
th
r
ough
to
th
e
ne
xt
s
e
ns
or
.
I
n
[
17]
p
r
opos
e
s
a
phe
r
om
one
-
ba
s
e
d
tr
a
f
f
ic
m
a
na
ge
m
e
nt
f
r
a
m
e
w
or
k
to
r
e
duc
e
c
onge
s
ti
on
by
c
om
bi
ni
ng
dyna
m
ic
ve
hi
c
le
r
e
r
out
in
g
s
tr
a
te
gi
e
s
a
nd
tr
a
f
f
ic
li
ght
c
ont
r
ol
.
E
a
c
h
ve
hi
c
le
phe
r
om
one
tr
a
f
f
ic
de
pos
it
a
nd
phe
r
om
one
in
te
nt
io
n
(
r
e
pr
e
s
e
nt
in
g
th
e
c
ur
r
e
nt
a
nd
f
ut
ur
e
t
r
a
f
f
ic
de
ns
it
ie
s
)
a
r
e
r
e
c
or
de
d
dur
in
g
a
tr
ip
.
I
f
c
onge
s
ti
on
oc
c
ur
s
,
th
e
f
r
a
m
e
w
or
k
a
dopt
s
a
pr
oa
c
ti
ve
ve
hi
c
le
r
e
r
out
in
g
s
tr
a
te
gy,
w
he
r
e
ve
hi
c
le
s
t
ha
t
ne
e
d t
o be
r
e
r
out
e
d a
r
e
s
e
le
c
te
d a
nd give
n a
n a
lt
e
r
na
ti
ve
r
out
e
be
f
or
e
t
he
y e
nt
e
r
a
j
a
m
m
e
d
r
oa
d.
I
n
[
18]
e
va
lu
a
te
s
two s
c
he
dul
in
g
a
lg
or
it
hm
s
,
n
a
m
e
ly
,
th
e
e
a
r
li
e
s
t
de
a
dl
in
e
f
ir
s
t
(
E
D
F
)
a
nd
f
ix
e
d
pr
io
r
it
y
(
F
P
)
a
lg
or
i
th
m
s
.
I
n
th
e
F
P
a
lg
or
it
hm
,
ve
hi
c
le
s
a
r
e
gr
oupe
d
in
to
f
our
c
la
s
s
e
s
.
T
he
la
ne
w
it
h
th
e
hi
ghe
s
t
pr
io
r
it
y
ve
hi
c
le
is
s
e
r
ve
d
f
ir
s
t.
I
n
th
e
E
D
F
a
lg
or
it
hm
,
ve
h
ic
le
s
a
r
e
pr
io
r
it
iz
e
d
ba
s
e
d
on
de
a
dl
in
e
s
to
de
s
ti
na
ti
ons
.
W
it
h
th
is
a
lg
or
it
hm
,
th
e
num
be
r
of
s
to
ps
,
a
ve
r
a
ge
de
la
ys
a
nd
pr
io
r
it
iz
e
d
ve
hi
c
le
tr
a
ve
l
ti
m
e
s
a
r
e
s
ig
ni
f
ic
a
nt
ly
r
e
duc
e
d.
T
he
E
D
F
a
lg
or
it
hm
yi
e
ld
s
be
tt
e
r
pe
r
f
or
m
a
nc
e
th
a
n
F
P
.
I
n
[
19]
pr
opos
e
s
a
n
im
a
ge
pr
oc
e
s
s
in
g
-
ba
s
e
d
tr
a
f
f
ic
c
ont
r
ol
s
ys
te
m
us
in
g
M
A
T
L
A
B
c
ode
th
a
t
c
ha
nge
s
th
e
tr
a
f
f
ic
li
gh
t
s
ig
na
l
ti
m
e
b
y
c
ons
id
e
r
in
g
th
e
tr
a
f
f
ic
de
ns
it
y.
T
he
s
y
s
te
m
a
im
s
to
r
e
duc
e
w
a
it
in
g
ti
m
e
s
on
e
m
pt
y
r
oa
ds
.
T
he
im
a
ge
in
e
a
c
h
la
ne
i
s
obt
a
in
e
d us
in
g a
w
e
bc
a
m
, a
nd t
he
numbe
r
of
ve
hi
c
le
s
on t
he
r
oa
d a
nd t
he
t
r
a
f
f
ic
de
ns
it
y a
r
e
c
a
lc
ul
a
te
d
by
a
ppl
yi
ng
th
e
s
ui
ta
bl
e
M
A
T
L
A
B
f
unc
ti
on.
T
h
e
dur
a
ti
on
o
f
th
e
gr
e
e
n
li
ght
i
s
de
te
r
m
in
e
d
b
a
s
e
d
on
th
e
de
ns
it
y of
t
he
t
r
a
f
f
ic
dur
a
ti
on, whe
r
e
a
l
onge
r
t
im
e
i
s
gi
ve
n f
or
de
ns
e
r
r
oa
ds
.
I
n
[
20]
de
vi
s
e
s
a
two
-
le
ve
l
s
tr
a
te
gy
a
t
th
e
in
te
r
s
e
c
ti
on
to
pr
e
ve
nt
c
on
ge
s
ti
on
c
a
u
s
e
d
by
a
c
c
id
e
nt
s
.
L
e
ve
l
one
i
s
us
e
d t
o s
to
p a
ve
hi
c
le
f
r
om
dr
iv
in
g
i
n a
c
e
r
ta
in
di
r
e
c
ti
on, a
nd l
e
ve
l
two is
us
e
d t
o
gi
ve
a
w
a
r
ni
n
g
th
a
t
r
e
c
om
m
e
nds
not
dr
iv
in
g
in
a
c
e
r
ta
in
di
r
e
c
ti
on.
I
n
[
21]
pr
opos
e
s
a
n
a
r
ti
f
ic
ia
l
be
e
c
ol
ony
(
A
B
C
)
a
lg
or
it
hm
to
m
in
im
iz
e
th
e
a
ve
r
a
ge
w
a
it
in
g
ti
m
e
(
A
W
T
)
a
t
a
n
in
te
r
s
e
c
ti
on
ba
s
e
d
on
th
e
dyna
m
ic
tr
a
f
f
ic
lo
a
d
in
put
.
T
hi
s
a
lg
or
it
hm
is
in
s
pi
r
e
d
by
hon
e
ybe
e
s
w
a
r
m
b
e
ha
vi
our
a
nd
c
a
n
opt
im
iz
e
th
e
w
a
it
in
g
ti
m
e
by
98.43%
f
or
a
s
im
ul
a
ti
on
dur
a
ti
on
of
1800
s
e
c
onds
.
I
n
[
22]
us
e
s
tr
a
f
f
ic
c
onge
s
ti
on
da
ta
f
r
om
G
oogl
e
'
s
A
P
I
to
de
s
ig
n
a
da
pt
iv
e
tr
a
f
f
ic
li
ght
s
th
a
t
c
a
n
r
e
duc
e
tr
a
f
f
ic
c
onge
s
ti
on
by
de
t
e
c
ti
ng
c
onge
s
ti
on
f
r
om
th
e
poi
nt
of
de
p
a
r
tu
r
e
to
th
e
ne
a
r
e
s
t
tr
a
f
f
ic
li
ght
.
O
ne
a
dva
nt
a
ge
of
th
is
m
e
th
od
is
th
a
t
it
doe
s
not
ha
ve
hi
gh
in
f
r
a
s
tr
uc
tu
r
e
in
s
ta
ll
a
ti
on
c
os
ts
(
s
uc
h
a
s
th
os
e
f
or
th
e
in
s
ta
ll
a
ti
on
of
s
e
ns
or
ne
twor
ks
)
.
I
nf
or
m
a
ti
on
c
a
n
be
de
li
ve
r
e
d
w
it
h
a
n
a
ve
r
a
ge
de
la
y
of
1.5
s
e
c
onds
(
m
a
xi
m
um
of
3
s
e
c
onds
)
.
I
n
[
23]
s
e
ts
tr
a
f
f
ic
li
ght
s
s
o
th
a
t
ve
hi
c
le
s
do
not
s
to
p
w
he
n
tr
a
f
f
ic
c
ondi
ti
ons
a
r
e
lo
w
us
in
g
L
a
N
P
r
o
(
a
s
m
a
r
t
tr
a
f
f
ic
li
ght
m
odul
e
s
pe
c
if
ic
a
ll
y
f
or
qui
e
t
s
tr
e
e
ts
/i
nt
e
r
s
e
c
ti
on
s
)
.
I
n
[
24]
pr
opos
e
s
a
two
-
w
a
y
tr
a
f
f
ic
-
li
ght
-
to
-
ve
hi
c
le
c
om
m
uni
c
a
ti
on
(
T
L
V
C
)
s
c
he
dul
in
g
s
c
he
m
e
to
r
e
duc
e
f
ue
l
c
ons
um
pt
io
n
a
nd
C
O
2
e
m
is
s
io
ns
by
e
ns
ur
in
g
th
a
t
la
r
ge
ve
hi
c
le
s
c
a
n
di
r
e
c
tl
y
c
r
os
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
r
ti
f
I
nt
e
ll
I
S
S
N
:
2252
-
8938
R
e
c
e
nt
de
v
e
lo
pm
e
nt
of
s
m
a
r
t
tr
af
fi
c
l
ig
ht
s
(
A
’
is
y
a N
ur
A
ul
ia
Y
us
uf
)
227
tr
a
f
f
ic
li
ght
s
w
it
hout
s
to
ppi
ng.
H
e
a
vy
-
dut
y
ve
hi
c
le
s
a
r
e
gi
ve
n
pr
io
r
it
y
to
c
r
os
s
th
e
tr
a
f
f
ic
li
ght
f
ir
s
t.
T
he
s
im
ul
a
ti
on
r
e
s
ul
ts
s
how
th
a
t
th
e
gr
e
e
n
li
ght
hi
t
r
a
te
f
o
r
a
ll
v
e
hi
c
le
s
,
e
s
pe
c
ia
ll
y
ve
hi
c
le
s
w
it
h
he
a
vy
lo
a
ds
,
in
c
r
e
a
s
e
s
s
ig
ni
f
ic
a
nt
ly
.
I
n
[
25]
us
e
s
a
W
S
N
to
c
ol
le
c
t
r
oa
d
t
r
a
f
f
ic
da
ta
in
r
e
a
l
-
ti
m
e
,
a
f
uz
z
y
lo
gi
c
c
ont
r
ol
le
r
(
F
L
C
)
f
o
r
de
c
is
io
n
m
a
ki
ng
(
w
hi
c
h
pa
th
to
gi
ve
th
e
gr
e
e
n
li
ght
to
f
ir
s
t)
,
a
nd
a
r
ou
ti
ng
a
lg
or
it
hm
th
a
t
dyna
m
ic
a
ll
y
gi
ve
s
a
gr
e
e
n l
ig
ht
ba
s
e
d on da
ta
f
r
om
t
he
F
L
C
.
I
n
[
26]
pr
opos
e
s
a
dyna
m
ic
r
out
in
g
s
tr
a
te
gy t
ha
t
co
ns
ta
nt
ly
pr
ovi
de
s
m
ot
or
is
ts
w
it
h
tr
a
ve
l
ti
m
e
upda
te
s
a
nd
c
ons
id
e
r
s
a
da
pt
iv
e
s
ig
na
l
c
ont
r
ol
f
or
e
f
f
ic
ie
nt
r
out
in
g
in
th
e
a
c
tu
a
l
tr
a
ns
por
t
ne
twor
k.
R
out
in
g
is
u
s
e
d
to
r
e
duc
e
th
e
que
u
e
le
ngt
h
a
nd
a
ve
r
a
ge
w
a
it
in
g
ti
m
e
a
nd
in
c
r
e
a
s
e
th
e
a
ve
r
a
ge
s
pe
e
d
in
th
e
ne
tw
or
k.
I
n
[
27]
us
e
s
th
e
a
da
pt
iv
e
ne
ur
o
-
f
uz
z
y
in
f
e
r
e
nc
e
s
ys
te
m
(
A
N
F
I
S
)
m
e
th
od t
o p
r
oc
e
s
s
r
oa
d de
ns
it
y a
nd r
oa
d w
id
th
da
ta
t
o
de
te
r
m
in
e
t
he
dur
a
ti
on o
f
a
gi
ve
n g
r
e
e
n l
ig
ht
.
T
he
r
oa
d
de
n
s
it
y
is
c
a
lc
ul
a
te
d
b
a
s
e
d
on
th
e
vi
de
o
t
a
ke
n
by
t
he
s
ys
te
m
a
nd
pr
oc
e
s
s
e
d
u
s
in
g
th
e
c
onne
c
te
d
c
om
pone
nt
la
be
li
ng
(
C
C
L
)
m
e
th
od.
C
C
L
im
a
ge
r
e
s
ul
ts
a
r
e
c
o
m
pa
r
e
d
w
it
h
th
e
im
a
ge
c
ondi
ti
on
of
a
n
e
m
pt
y
r
oa
d
(
w
it
hout
a
ve
hi
c
le
)
to
obt
a
in
th
e
v
e
hi
c
le
d
e
ns
it
y
pe
r
c
e
nt
a
ge
.
R
oa
d
c
ondi
ti
on
da
ta
(
in
th
e
f
or
m
of
vi
de
o
f
oot
a
ge
)
a
r
e
c
ol
le
c
te
d,
a
nd
r
oa
d
im
a
ge
s
a
r
e
ta
ke
n
w
h
e
n
th
e
r
e
a
r
e
no
ve
hi
c
le
s
(
c
le
a
r
r
oa
d
c
ondi
ti
ons
)
.
W
he
n
th
e
obj
e
c
t
in
th
e
te
s
t
im
a
ge
h
a
s
be
e
n
obt
a
in
e
d,
th
e
r
oa
d
de
n
s
it
y
is
c
a
lc
ul
a
t
e
d
by
c
om
pa
r
is
on
w
it
h
th
e
e
m
pt
y
r
oa
d
im
a
ge
th
a
t
w
a
s
pr
e
vi
ou
s
ly
obt
a
in
e
d.
D
a
ta
on
th
e
r
oa
d
de
ns
it
y
a
nd
li
ne
w
id
th
a
r
e
th
e
A
N
F
I
S
in
put
s
f
or
de
te
r
m
in
in
g
th
e
dur
a
ti
on
of
a
gi
ve
n
gr
e
e
n
li
ght
.
I
n
[
28]
pr
opo
s
e
s
a
pr
e
ti
m
e
d
s
ys
t
e
m
to
a
c
c
om
m
oda
t
e
tr
a
f
f
ic
va
r
ia
ti
ons
.
T
he
s
ys
te
m
de
te
r
m
in
e
s
th
e
tr
a
f
f
ic
de
ns
it
y
f
r
om
th
e
in
te
ns
it
y
hi
s
to
gr
a
m
s
ta
nda
r
d
de
vi
a
ti
on
o
f
th
e
im
a
ge
r
e
pr
e
s
e
nt
in
g
th
e
ve
hi
c
le
de
te
c
ti
on
a
r
e
a
of
a
la
ne
a
nd
m
o
di
f
ie
s
th
e
gr
e
e
n
ti
m
e
of
e
a
c
h
in
te
r
s
e
c
ti
on.
T
he
s
ys
te
m
c
ont
r
ol
s
th
e
f
lo
w
of
ve
hi
c
le
s
ba
s
e
d
on
s
ig
n
a
l
-
ti
m
in
g
pl
a
ns
a
nd
d
e
te
r
m
in
e
s
th
e
tr
a
f
f
ic
de
n
s
it
y
by
de
te
c
ti
ng
a
ll
obj
e
c
ts
in
th
e
ve
hi
c
le
de
te
c
ti
on
a
r
e
a
in
e
a
c
h
l
a
ne
w
it
h
f
our
w
ir
e
le
s
s
I
P
c
a
m
e
r
a
s
a
nd
th
e
n
m
odi
f
yi
ng
th
e
c
ur
r
e
nt
gr
e
e
n
ti
m
e
o
f
a
la
ne
.
E
a
c
h
c
a
m
e
r
a
c
a
p
tu
r
e
s
th
e
e
nt
ir
e
ve
hi
c
le
w
a
it
in
g
a
r
e
a
,
but
th
e
pr
ogr
a
m
de
te
c
ts
onl
y
th
e
ve
hi
c
le
s
in
th
e
ve
hi
c
le
de
te
c
ti
on
a
r
e
a
.
T
he
tr
a
f
f
ic
de
ns
it
y
is
de
te
r
m
in
e
d
by
c
a
lc
ul
a
ti
ng
th
e
in
te
n
s
it
y
hi
s
to
gr
a
m
in
th
e
e
nt
ir
e
r
e
gi
on
of
in
te
r
e
s
t
(
R
O
I
)
.
T
he
s
y
s
te
m
c
a
l
c
ul
a
te
s
th
e
s
t
a
nda
r
d
de
vi
a
ti
on
of
th
e
hi
s
to
gr
a
m
.
I
f
th
e
va
lu
e
is
s
m
a
ll
e
r
th
a
n
th
e
lo
w
th
r
e
s
hol
d,
th
e
s
y
s
te
m
c
onc
lu
de
s
th
a
t
tr
a
f
f
ic
de
ns
it
y
is
lo
w
,
a
nd
gr
e
e
n
ti
m
e
is
s
hor
te
ne
d.
I
f
th
e
v
a
lu
e
is
hi
ghe
r
th
a
n
th
e
hi
gh
th
r
e
s
hol
d,
th
e
s
ys
te
m
c
onc
lu
de
s
t
ha
t
th
e
t
r
a
f
f
ic
de
ns
it
y i
s
hi
gh, a
nd t
h
e
gr
e
e
n t
im
e
i
s
e
xt
e
nde
d.
I
n
[
29]
bui
ld
s
two
ki
nd
s
of
r
e
in
f
or
c
e
m
e
nt
l
e
a
r
ni
ng
a
lg
or
it
hm
s
,
na
m
e
ly
,
d
e
e
p
pol
ic
y
-
gr
a
di
e
nt
(
P
G
)
a
nd
va
lu
e
-
f
unc
ti
on
-
ba
s
e
d
a
ge
nt
s
,
th
a
t
c
a
n
pr
e
di
c
t
th
e
b
e
s
t
po
s
s
ib
le
tr
a
f
f
ic
s
ig
na
l
f
or
tr
a
f
f
ic
in
te
r
s
e
c
ti
ons
.
T
he
a
da
pt
iv
e
tr
a
f
f
ic
li
ght
c
ont
r
ol
a
ge
nt
r
e
c
e
iv
e
s
a
s
n
a
ps
hot
of
th
e
c
u
r
r
e
nt
gr
a
phi
c
a
l
tr
a
f
f
ic
s
im
ul
a
to
r
a
nd
ge
ne
r
a
te
s
a
c
ont
r
ol
s
ig
na
l.
P
G
-
ba
s
e
d
a
ge
nt
s
m
a
p
th
e
ir
ob
s
e
r
va
ti
ons
di
r
e
c
tl
y
to
th
e
c
ont
r
ol
s
ig
na
l,
w
hi
le
va
lu
e
-
f
unc
ti
on
-
ba
s
e
d
a
ge
nt
s
f
ir
s
t
e
s
ti
m
a
te
th
e
va
lu
e
s
f
or
a
ll
le
ga
l
c
ont
r
ol
s
ig
na
ls
a
nd
th
e
n
c
hoos
e
th
e
opt
im
a
l
c
ont
r
ol
a
c
ti
on
w
it
h t
he
hi
ghe
s
t
va
lu
e
.
I
n
[
31]
m
ode
ls
t
he
t
r
a
f
f
ic
s
ig
na
l
c
ont
r
ol
l
e
r
us
in
g a
n a
c
to
r
-
c
r
it
ic
r
e
in
f
o
r
c
e
m
e
n
t
le
a
r
ni
ng
a
dva
nt
a
ge
a
lg
or
it
hm
(
A
3C
)
w
it
h
va
r
io
us
s
ta
te
r
e
pr
e
s
e
nt
a
ti
ons
to
de
te
r
m
in
e
di
f
f
e
r
e
nc
e
s
in
pe
r
f
o
r
m
a
nc
e
.
T
he
pa
r
a
m
e
te
r
s
s
tu
di
e
d
in
c
lu
de
th
e
ve
hi
c
l
e
de
n
s
it
y,
tr
a
f
f
ic
f
lo
w
,
que
ue
s
,
lo
c
a
ti
on,
a
nd
s
pe
e
d
to
ge
th
e
r
w
it
h
th
e
c
ur
r
e
nt
tr
a
f
f
ic
pha
s
e
,
c
yc
le
le
ngt
h
a
nd
dur
a
ti
on
of
r
e
d
li
ght
s
.
I
n
[
32]
in
tr
oduc
e
s
a
ne
w
a
ppr
oa
c
h
ba
s
e
d
on
a
m
odi
f
ie
d
r
ound
-
r
obi
n
s
c
he
dul
in
g
a
lg
or
it
hm
ba
s
e
d
on
ge
ne
ti
c
a
lg
or
it
hm
te
c
hni
qu
e
s
th
a
t
opt
im
iz
e
th
e
ti
m
in
g
e
f
f
ic
ie
nc
y
of
s
ig
na
le
d
in
te
r
s
e
c
ti
ons
.
I
n
or
de
r
to
e
va
lu
a
te
th
e
c
os
t
f
unc
ti
on
a
nd
c
he
c
k
if
th
e
gl
oba
l
opt
im
um
ha
s
be
e
n
r
e
a
c
h
e
d,
th
is
te
c
hni
que
u
s
e
s
in
it
ia
l
ti
m
in
g
pa
tt
e
r
ns
to
pr
oduc
e
ne
w
of
f
s
pr
in
g
(
in
te
r
m
s
of
le
ngt
h
of
de
la
y)
.
T
he
m
odi
f
ic
a
ti
ons
im
pl
e
m
e
nt
e
d
in
th
e
tr
a
di
ti
ona
l
nor
m
a
l
r
ound
-
r
obi
n
s
c
he
dul
in
g
a
lg
or
it
hm
a
r
e
b
a
s
e
d
on
N
O
R
lo
gi
c
ga
te
s
.
W
he
n
two
ve
r
ti
c
a
ll
y
c
onne
c
te
d
li
ne
s
do
not
ha
ve
ve
hi
c
le
a
c
ti
vi
ty
,
in
s
te
a
d
of
th
e
tr
a
f
f
ic
s
ys
te
m
gi
vi
ng
th
e
m
a
gr
e
e
n
li
ght
,
th
e
s
ys
t
e
m
w
il
l
gi
ve
a
gr
e
e
n
li
ght
to
a
not
he
r
la
n
e
th
a
t
ha
s
a
t
le
a
s
t
one
ve
hi
c
le
th
a
t
w
il
l
c
r
o
s
s
th
e
in
te
r
s
e
c
ti
on. A
s
e
t
of
tr
a
f
f
ic
c
ount
e
r
s
i
s
a
ppl
ie
d
dur
in
g
3 s
pe
c
if
ic
p
e
r
io
ds
to
c
a
pt
ur
e
th
e
tr
a
f
f
ic
f
lo
w
a
nd
de
la
y
in
e
a
c
h
c
r
os
s
in
g
la
ne
.
T
he
c
a
lc
ul
a
ti
o
n
la
s
ts
f
or
20
m
in
ut
e
s
in
e
a
c
h
pe
r
io
d.
I
n
[
33]
pr
opos
e
s
a
n
a
ut
om
a
te
d
s
y
s
te
m
th
a
t
c
a
n
de
te
c
t
e
m
e
r
ge
nc
y
ve
hi
c
le
s
in
he
a
vy
tr
a
f
f
ic
f
r
om
C
C
T
V
f
oot
a
ge
us
in
g
a
de
e
p
c
onvol
ut
io
na
l
ne
ur
a
l
ne
twor
k
to
c
om
m
uni
c
a
te
th
is
in
f
or
m
a
ti
on
to
tr
a
f
f
ic
li
ght
s
or
to
a
ut
om
a
ti
c
a
ll
y
na
vi
ga
te
ot
he
r
v
e
hi
c
le
s
to
c
l
e
a
r
th
e
r
oa
ds
(
gi
vi
ng
pr
io
r
it
y
to
e
m
e
r
ge
nc
y
ve
hi
c
l
e
s
)
.
T
hi
s
s
ys
t
e
m
ta
ke
s
r
oa
d
r
e
c
or
di
ngs
f
r
om
C
C
T
V
a
nd
de
te
c
ts
e
m
e
r
ge
nc
y
ve
hi
c
le
s
.
P
ic
tu
r
e
s
a
r
e
ta
ke
n
e
ve
r
y
s
e
c
ond
w
it
h
th
e
C
C
T
V
c
a
m
e
r
a
s
.
I
n
e
a
c
h
pi
c
tu
r
e
,
e
a
c
h
ve
hi
c
le
on
th
e
r
oa
d
is
de
te
c
te
d
a
nd
th
e
s
ys
te
m
c
la
s
s
if
ie
s
th
e
ve
hi
c
le
s
in
to
e
m
e
r
ge
nc
y
ve
hi
c
le
s
a
nd
or
di
na
r
y
ve
hi
c
le
s
.
I
f
a
n
e
m
e
r
ge
nc
y
v
e
hi
c
le
is
f
ound,
th
e
c
om
put
e
r
not
if
ie
s
th
e
tr
a
f
f
ic
pol
ic
e
or
th
e
a
ut
om
a
te
d s
ys
te
m
to
c
le
a
r
th
e
r
oa
d. T
he
Y
ol
o
-
V
3 a
lg
or
it
hm
is
us
e
d
f
or
obj
e
c
t
de
te
c
ti
on
be
c
a
u
s
e
th
is
a
lg
or
it
hm
i
s
f
a
s
t
a
nd c
a
pa
bl
e
of
pr
oc
e
s
s
in
g 45 im
a
ge
s
pe
r
s
e
c
ond with a c
om
put
e
r
w
it
h
a
good p
r
oc
e
s
s
or
.
I
n
[
34]
de
te
c
ts
r
e
d
li
ght
s
a
nd
gi
ve
s
ve
hi
c
le
s
a
nd
pe
de
s
tr
ia
ns
w
a
r
ni
ngs
ne
a
r
r
e
d
li
ght
s
us
in
g
a
s
m
a
r
tp
hone
.
A
pr
io
r
it
y s
ys
te
m
f
or
t
r
a
f
f
ic
l
ig
ht
s
,
w
hi
c
h w
e
ig
ht
s
e
a
c
h l
a
ne
ba
s
e
d
on t
he
numbe
r
a
nd t
ype
of
ve
hi
c
le
s
w
hi
c
h a
r
e
in
th
a
t
la
ne
,
is
im
pl
e
m
e
nt
e
d.
I
n
[
35]
pr
opos
e
s
a
s
y
s
te
m
c
ons
i
s
ti
ng
of
tr
us
te
d
a
ut
hor
it
y
(
T
A
)
th
a
t
r
e
gul
a
te
s
ve
hi
c
le
da
ta
ba
s
e
s
a
nd c
om
m
uni
c
a
te
s
w
it
h
ve
hi
c
le
s
w
it
h
3G
/4
G
ne
twor
ks
.
I
n
a
ddi
ti
on,
a
tr
a
f
f
ic
li
ght
s
ys
te
m
is
in
tr
oduc
e
d
th
a
t
ope
r
a
te
s
by
e
xc
ha
ngi
ng
in
f
or
m
a
ti
on
(
ve
hi
c
le
s
t
a
tu
s
)
be
twe
e
n
th
e
ve
hi
c
le
a
nd
th
e
tr
a
f
f
ic
li
ght
c
ont
r
ol
le
r
.
B
a
s
e
d
on
th
e
s
ta
te
of
th
e
ve
hi
c
le
,
th
e
tr
a
f
f
ic
li
ght
de
te
r
m
in
e
s
w
hi
c
h
v
e
hi
c
le
ha
s
pr
io
r
it
y.
I
n
[
36]
pr
opos
e
s
ve
hi
c
le
m
a
c
r
os
c
opi
c
m
ot
io
n
pl
a
nni
ng
(
V
M
M
P
)
f
o
r
r
o
ut
e
opt
im
iz
a
ti
on
a
nd
ve
hi
c
le
s
pe
e
d
us
in
g
da
t
a
tr
a
f
f
ic
a
nd ve
hi
c
le
c
ha
r
a
c
te
r
is
ti
c
s
w
it
h ve
hi
c
le
c
onne
c
ti
vi
ty
(
V
2V
, V
2I
, ve
hi
c
le
-
to
-
c
lo
ud)
. T
he
a
lg
or
it
h
m
us
e
d
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8938
I
nt
J
A
r
ti
f
I
nt
e
ll
,
V
ol
.
10
, N
o.
1, M
a
r
c
h
20
21
:
224
–
233
228
to
de
te
r
m
in
e
th
e
ve
hi
c
le
r
ou
te
s
is
a
ge
ne
ti
c
a
lg
or
it
hm
.
I
n
[
37]
pr
opos
e
s
a
da
ta
tr
a
ns
m
is
s
io
n
c
om
m
uni
c
a
ti
on
m
e
c
ha
ni
s
m
in
vol
vi
ng
th
r
e
e
uni
ts
:
c
ong
e
s
ti
on
de
te
c
ti
on,
d
a
ta
c
ont
r
ol
,
a
nd
c
onge
s
ti
on
c
ont
r
ol
.
C
onge
s
ti
on
de
te
c
ti
on
is
u
s
e
d
to
m
e
a
s
ur
e
th
e
le
ve
l
of
th
e
c
ha
nne
l
us
e
d
to
de
te
c
t
c
onge
s
ti
on.
D
a
ta
c
ont
r
ol
is
us
e
d
to
c
ol
le
c
t
a
nd
f
il
te
r
m
e
s
s
a
ge
s
(
to
a
voi
d
r
e
dunda
nc
y)
a
nd
th
e
n
to
g
r
oup
m
e
s
s
a
ge
s
in
to
4
c
lu
s
te
r
s
.
C
onge
s
ti
on
c
ont
r
ol
is
us
e
d
to
de
te
r
m
in
e
th
e
c
om
m
uni
c
a
ti
on
p
a
r
a
m
e
te
r
s
(
tr
a
ns
m
is
s
io
n
r
a
nge
,
r
a
te
)
.
T
he
pr
e
de
te
r
m
in
e
d
c
om
m
uni
c
a
ti
on
pa
r
a
m
e
te
r
s
a
r
e
s
e
nt
by
tr
a
f
f
ic
li
ght
s
to
ve
hi
c
le
s
th
a
t
ne
e
d
to
s
to
p
a
t
r
e
d
li
ght
s
to
r
e
duc
e
c
ol
li
s
io
ns
a
nd
c
ont
r
ol
c
ong
e
s
ti
on.
I
n
[
38]
e
xpl
oi
ts
a
f
iv
e
-
m
e
g
a
pi
xe
l
r
e
s
ol
ut
io
n
C
C
D
c
a
m
e
r
a
d
e
s
ig
ne
d
a
nd
us
e
d t
o m
oni
to
r
r
e
a
l
-
t
im
e
t
r
a
f
f
ic
a
ppr
oa
c
hi
ng e
a
c
h i
nt
e
r
s
e
c
ti
on a
nd t
o m
e
a
s
ur
e
t
he
t
r
a
f
f
ic
vol
um
e
of
e
a
c
h l
a
ne
a
nd
que
ue
,
tr
a
ns
m
it
ti
ng
r
e
a
l
-
ti
m
e
da
ta
pa
r
a
m
e
te
r
s
to
th
e
t
r
a
f
f
ic
li
ght
c
ont
r
ol
s
ys
te
m
,
s
uc
h
a
s
th
e
le
ngt
h
of
th
e
ve
hi
c
le
a
nd t
he
a
ve
r
a
ge
w
a
it
in
g t
im
e
.
T
he
de
vi
c
e
w
il
l
de
f
in
e
t
h
e
vi
de
o f
r
a
m
e
by
f
r
a
m
e
a
nd ma
tc
h t
he
r
out
e
i
n
que
s
ti
on
a
ut
om
a
ti
c
a
ll
y,
m
oni
to
r
th
e
pa
s
s
a
ge
of
ve
hi
c
le
s
a
nd
m
a
ke
de
c
is
io
ns
ba
s
e
d
on
th
e
a
c
ti
ons
of
ve
hi
c
le
s
.
T
o
c
ont
r
ol
tr
a
f
f
ic
li
ght
s
a
t
one
poi
nt
,
a
r
e
a
l
-
ti
m
e
tr
a
f
f
ic
in
di
c
a
to
r
is
li
nke
d
to
tr
a
f
f
ic
li
ght
s
.
T
hi
s
s
ys
te
m
c
a
n
a
ls
o
be
u
s
e
d
a
s
a
s
e
n
s
or
f
or
tr
a
f
f
ic
gui
da
nc
e
s
y
s
te
m
s
f
o
r
th
e
u
r
ba
n
r
oa
d
ne
twor
k
to
pr
ovi
de
tr
a
f
f
ic
gui
da
nc
e
in
put
da
ta
a
nd t
o m
oni
to
r
t
he
ove
r
a
ll
r
oa
d c
ondi
ti
ons
a
ut
om
a
ti
c
a
ll
y.
I
n
[
39]
de
ve
lo
ps
a
be
tt
e
r
a
nd
dyna
m
ic
tr
a
f
f
ic
li
ght
c
ont
r
ol
de
s
ig
n
us
in
g
th
e
f
uz
z
y
M
a
m
da
ni
lo
gi
c
m
e
th
od
.
T
he
a
n
a
ly
s
is
i
s
ba
s
e
d
on
th
e
le
ngt
h
of
th
e
ve
hi
c
l
e
que
u
e
in
e
a
c
h
la
n
e
a
t
th
e
in
te
r
s
e
c
ti
on,
th
e
w
id
th
of
e
a
c
h
r
oa
d,
th
e
num
be
r
of
ve
hi
c
le
s
he
a
di
ng
to
th
e
tr
a
f
f
ic
(
in
te
r
s
e
c
ti
on)
a
nd
th
e
v
e
hi
c
le
s
pe
e
d.
T
he
dur
a
ti
on
of
th
e
gr
e
e
n
li
ght
pe
r
io
d
f
or
e
a
c
h
la
ne
c
a
n
be
opt
im
iz
e
d
ba
s
e
d
on
pa
r
a
m
e
te
r
s
s
uc
h
a
s
th
e
le
ngt
h
of
th
e
qu
e
ue
in
e
a
c
h
la
ne
,
th
e
num
be
r
of
ve
hi
c
le
s
e
nt
e
r
in
g
th
e
que
ue
,
th
e
ve
hi
c
le
s
pe
e
d
a
nd
th
e
w
id
th
of
e
a
c
h
la
ne
.
F
r
om
th
e
pa
r
a
m
e
te
r
va
lu
e
s
,
th
e
μ
va
lu
e
is
th
e
n
de
te
r
m
in
e
d
f
or
a
ppl
ic
a
ti
on
ba
s
e
d
on
th
e
r
ul
e
c
a
lc
ul
a
ti
on.
L
a
n
e
s
w
it
h
lo
nge
r
ve
hi
c
le
li
ne
s
w
il
l
ha
ve
lo
nge
r
gr
e
e
n
li
ght
pe
r
io
ds
th
a
n
ot
he
r
la
ne
s
w
it
h
f
e
w
e
r
ve
hi
c
le
s
.
I
n
[
40]
pr
opos
e
s
va
li
da
ti
o
n
s
tr
a
te
gi
e
s
ba
s
e
d
on
ge
ne
ti
c
a
lg
or
it
hm
s
a
nd
a
ut
om
a
ti
c
ge
ne
r
a
ti
on
f
or
di
f
f
e
r
e
nt
tr
a
f
f
ic
s
c
e
na
r
io
s
.
S
om
e
of
th
e
pa
r
a
m
e
te
r
s
us
e
d
f
or
va
li
da
ti
on
a
s
s
e
s
s
m
e
nt
in
c
lu
de
th
e
num
be
r
of
ve
hi
c
le
s
a
r
r
iv
in
g
a
t
th
e
ir
de
s
ti
na
ti
on,
C
O
2
e
m
is
s
io
ns
,
N
O
x,
a
nd
tr
a
ve
l
ti
m
e
(
c
a
n
s
e
le
c
t
c
e
r
ta
in
c
yc
le
s
f
or
c
e
r
ta
in
tr
a
f
f
i
c
c
ondi
ti
ons
)
.
I
n
[
41]
opt
im
iz
e
s
th
e
tr
a
f
f
ic
f
lo
w
by
pr
opos
in
g
two
a
ppr
oa
c
he
s
:
R
I
T
C
O
a
nd
V
I
T
C
O
.
W
it
h
R
I
T
C
O
,
th
e
s
e
n
s
or
c
ol
le
c
t
s
r
oa
d
in
f
or
m
a
ti
on
(
que
ue
num
be
r
of
ve
hi
c
le
s
)
a
nd
th
e
n
te
ll
s
th
e
tr
a
f
f
ic
li
ght
s
to
s
e
t
th
e
c
yc
le
ba
s
e
d
on
th
e
in
f
or
m
a
ti
on.
W
it
h
V
I
T
C
O
,
ve
hi
c
le
s
e
x
c
ha
nge
in
f
or
m
a
ti
on
w
it
h
e
a
c
h
ot
he
r
to
de
te
c
t
tr
a
f
f
ic
ja
m
s
a
nd
te
ll
tr
a
f
f
ic
li
gh
ts
to
r
e
gul
a
te
c
yc
le
s
.
In
[
42]
de
s
ig
ns
a
r
e
a
l
-
ti
m
e
tr
a
f
f
ic
li
ght
opt
im
iz
a
ti
on
s
ys
te
m
to
r
e
s
pond
to
s
udde
n
c
ha
nge
s
in
pa
r
a
m
e
te
r
s
s
o
th
a
t
th
e
tr
a
f
f
ic
s
ys
te
m
c
a
n
ope
r
a
te
e
f
f
ic
ie
nt
ly
.
T
he
s
ys
te
m
c
a
lc
ul
a
te
s
th
e
num
b
e
r
of
ve
hi
c
le
s
in
a
la
ne
a
nd
d
e
te
r
m
in
e
s
th
e
s
c
he
dul
in
g
of
tr
a
f
f
ic
li
ght
s
ba
s
e
d
on
th
a
t
num
be
r
.
I
n
[
43]
us
e
s
s
e
n
s
or
s
a
nd
c
a
m
e
r
a
s
to
c
ol
le
c
t
tr
a
f
f
ic
da
ta
.
T
h
e
s
e
d
a
ta
a
r
e
s
ubs
e
qu
e
nt
ly
a
na
ly
z
e
d,
w
it
h
th
e
s
e
ns
or
da
ta
b
e
in
g
us
e
d
to
pr
ovi
de
tr
a
f
f
ic
in
f
or
m
a
ti
on.
I
f
th
e
le
ngt
h
of
th
e
tr
a
f
f
ic
que
ue
is
lo
nge
r
th
a
n
100
m
e
te
r
s
,
th
e
ve
hi
c
le
s
a
ppr
oa
c
hi
ng
th
e
in
te
r
s
e
c
ti
on
w
il
l
be
n
ot
if
ie
d.
T
he
c
a
m
e
r
a
da
ta
a
r
e
us
e
d
to
vi
e
w
th
e
ve
hi
c
le
da
ta
(
li
c
e
n
s
e
pl
a
te
,
ty
pe
of
ve
hi
c
le
)
.
I
n
[
44]
pr
opos
e
s
a
hi
s
to
r
y
-
ba
s
e
d
tr
a
f
f
ic
m
a
na
ge
m
e
nt
a
lg
or
it
hm
.
T
he
tr
a
f
f
ic
in
f
or
m
a
ti
on
of
th
e
pr
e
vi
ous
ye
a
r
a
r
e
u
s
e
d
to
pr
e
di
c
t
c
ur
r
e
nt
tr
a
f
f
ic
f
lo
w
.
F
r
om
th
e
s
e
pr
e
di
c
ti
ons
,
th
e
c
yc
le
f
or
gr
e
e
n l
ig
ht
s
a
nd r
e
d l
ig
ht
s
i
s
t
he
n r
e
gul
a
te
d.
3.2.
S
m
ar
t
t
r
af
f
ic
l
ig
h
t
s
f
or
e
m
e
r
ge
n
c
y ve
h
ic
le
s
I
n
[
45]
us
e
s
R
F
I
D
s
to
de
te
c
t
s
to
le
n
ve
hi
c
le
s
.
I
f
a
s
to
le
n
ve
hi
c
le
c
r
os
s
e
s
a
n
in
te
r
s
e
c
ti
on,
a
n
S
M
S
is
s
e
nt
to
th
e
pol
ic
e
pos
t.
E
m
e
r
ge
nc
y
ve
hi
c
le
s
a
r
e
di
s
ti
ngui
s
he
d
b
y
R
F
I
D
ta
gs
,
a
nd
th
e
c
onc
e
pt
of
gr
e
e
n
w
a
v
e
s
(
a
lwa
ys
ge
tt
in
g
a
gr
e
e
n
li
ght
)
is
u
s
e
d. T
hi
s
m
e
c
ha
ni
s
m
doe
s
no
t
us
e
a
c
a
m
e
r
a
du
e
to
w
e
a
th
e
r
pr
obl
e
m
s
(
if
th
e
w
e
a
th
e
r
i
s
ba
d, t
he
i
m
a
ge
qua
li
ty
de
te
r
io
r
a
te
s
, a
nd t
he
i
m
a
g
e
pr
oc
e
s
s
in
g i
s
c
om
pl
ic
a
te
d)
.
I
n
[
46]
c
ons
tr
uc
ts
a
n
in
te
gr
a
te
d
s
ys
te
m
s
o
th
a
t
e
a
c
h
ve
hi
c
le
c
a
n
c
om
m
uni
c
a
te
.
E
a
c
h
ve
hi
c
le
pr
ovi
de
s
in
f
or
m
a
ti
on
(
s
pe
e
d)
f
or
ot
he
r
ve
hi
c
le
s
. T
he
gr
e
e
n l
ig
ht
dur
a
ti
on i
s
c
a
lc
ul
a
te
d ba
s
e
d on the
di
s
ta
nc
e
of
t
he
ve
hi
c
le
t
o
th
e
i
nt
e
r
s
e
c
ti
on a
nd t
he
e
s
ti
m
a
te
d
ti
m
e
of
a
r
r
iv
a
l.
T
he
num
be
r
of
ve
hi
c
le
s
is
c
ount
e
d
us
in
g
a
c
a
m
e
r
a
,
a
nd
e
m
e
r
ge
nc
y
ve
hi
c
le
s
a
r
e
di
s
ti
ngui
s
he
d us
in
g s
e
ns
or
s
.
I
n
[
47]
de
s
ig
ns
a
n a
c
c
id
e
nt
de
te
c
ti
ng, a
le
r
ti
ng a
nd t
r
a
c
ki
ng me
c
ha
ni
s
m
s
o t
ha
t
a
n
a
m
bul
a
nc
e
c
a
n
im
m
e
di
a
te
ly
pa
s
s
th
r
ough
a
n
in
te
r
s
e
c
ti
on
a
s
qui
c
kl
y
a
s
pos
s
ib
le
.
T
he
s
ys
t
e
m
is
e
qui
ppe
d
w
it
h
a
pa
ti
e
nt
he
a
lt
h
(
vi
ta
l
s
ig
n)
m
oni
to
r
in
g
s
y
s
te
m
.
In
[
48]
e
s
t
a
bl
is
he
s
a
tr
a
f
f
ic
c
ont
r
ol
s
c
he
m
e
b
a
s
e
d
on
P
L
C
s
.
F
or
de
te
c
ti
ng
e
m
e
r
ge
nc
y
ve
hi
c
le
s
a
nd
tr
ig
ge
r
in
g
e
m
e
r
ge
nc
y
pr
ot
oc
ol
s
,
R
F
I
D
ta
gs
a
r
e
us
e
d.
U
nde
r
nor
m
a
l
ope
r
a
ti
ng
c
ondi
ti
ons
,
th
e
nor
m
a
l
s
ig
na
l
s
e
que
nc
e
is
m
a
in
ta
in
e
d;
w
he
n
th
e
e
m
e
r
ge
nc
y
pr
ot
oc
ol
is
tr
ig
ge
r
e
d,
th
e
s
ta
te
of
th
e
de
vi
c
e
is
c
ha
nge
d
be
f
o
r
e
a
n
e
m
e
r
ge
nc
y
ve
hi
c
le
r
e
a
c
he
s
th
e
in
te
r
s
e
c
ti
on.
T
he
m
a
c
hi
ne
r
e
tu
r
ns
to
it
s
us
u
a
l
s
t
a
te
w
h
e
n
th
e
e
m
e
r
ge
nc
y
s
it
ua
ti
on
i
s
ove
r
.
I
n
[
49]
de
s
ig
ns
a
c
ont
r
ol
s
ys
t
e
m
ba
s
e
d
on
s
of
twa
r
e
de
f
in
e
d
ne
twor
ki
ng
(
S
D
N
)
a
nd
th
e
I
oT
to
m
odi
f
y
th
e
tr
a
f
f
ic
li
ght
c
yc
le
w
he
n
th
e
r
e
is
a
n
e
m
e
r
ge
nc
y
w
it
h
th
e
a
id
of
tr
a
f
f
ic
c
a
m
e
r
a
s
.
T
he
S
D
N
c
ont
r
ol
le
r
c
ont
a
c
ts
th
e
c
lo
ud
to
c
ol
le
c
t
tr
a
f
f
ic
da
ta
a
nd
a
r
r
a
nge
th
e
t
r
a
f
f
ic
li
ght
c
yc
le
ba
s
e
d
on
th
a
t
da
ta
.
I
n
[
50]
us
e
s
R
F
I
D
to
tr
a
c
k
th
e
a
r
r
iv
a
l
of
a
m
bul
a
nc
e
s
a
t
a
c
e
r
ta
in
di
s
ta
nc
e
.
T
he
R
F
I
D
da
t
a
a
r
e
pr
oc
e
s
s
e
d
by
a
m
ic
r
oc
ont
r
ol
le
r
,
w
hi
c
h
c
ha
nge
s
th
e
li
ght
s
ig
na
l
to
gr
e
e
n
w
he
n
th
e
a
m
bul
a
nc
e
pa
s
s
e
s
th
r
ough
th
e
tr
a
f
f
ic
li
ght
.
G
P
S
,
w
hi
c
h
is
e
m
be
dde
d
in
a
m
bul
a
nc
e
dr
iv
e
r
m
obi
le
de
vi
c
e
s
,
is
u
s
e
d
to
s
e
nd
in
f
or
m
a
ti
on
f
r
om
m
obi
le
de
vi
c
e
s
to
th
e
c
lo
ud.
T
he
m
obi
le
de
vi
c
e
s
a
r
e
us
e
d
to
a
ut
he
nt
ic
a
te
th
e
e
m
e
r
ge
nc
y
a
nd
none
m
e
r
ge
nc
y
c
ondi
ti
ons
of
th
e
a
m
bul
a
nc
e
.
I
n
[
51
]
s
ugge
s
ts
th
a
t
a
s
ys
te
m
s
ig
na
l
th
e
ne
a
r
e
s
t
tr
a
f
f
ic
li
ght
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
r
ti
f
I
nt
e
ll
I
S
S
N
:
2252
-
8938
R
e
c
e
nt
de
v
e
lo
pm
e
nt
of
s
m
a
r
t
tr
af
fi
c
l
ig
ht
s
(
A
’
is
y
a N
ur
A
ul
ia
Y
us
uf
)
229
w
he
n
a
n
a
m
bul
a
nc
e
a
ppr
oa
c
he
s
.
R
F
I
D
te
c
hnol
ogy
is
us
e
d
in
th
is
s
tu
dy
by
e
m
be
ddi
ng
R
F
I
D
ta
gs
i
n
a
m
bul
a
nc
e
s
.
T
h
e
a
m
bul
a
nc
e
dr
iv
e
r
a
c
ti
va
te
s
th
e
ta
g
if
th
e
a
m
bul
a
nc
e
is
unde
r
e
m
e
r
ge
nc
y
c
ondi
ti
ons
,
a
n
d
th
e
n
th
e
ta
g
is
de
te
c
te
d
by
a
tr
a
f
f
ic
li
ght
w
it
h
a
n
R
F
I
D
r
e
a
de
r
.
T
he
tr
a
f
f
ic
li
ght
c
ha
ng
e
s
to
gr
e
e
n
w
he
n
th
e
a
m
bul
a
nc
e
r
e
a
c
h
e
s
a
c
e
r
ta
in
di
s
ta
n
c
e
f
r
om
th
e
tr
a
f
f
ic
li
ght
a
nd
r
e
m
a
in
s
gr
e
e
n
unt
il
th
e
a
m
bul
a
n
c
e
pa
s
s
e
s
th
e
tr
a
f
f
ic
l
ig
ht
.
I
n
[
52]
us
e
s
R
F
I
D
to
c
ont
r
ol
tr
a
f
f
ic
s
ig
na
ls
by
m
e
a
s
ur
in
g
ve
h
ic
le
de
ns
it
y.
R
F
I
D
-
ba
s
e
d
te
c
hnol
ogy
th
a
t
c
a
n
c
le
a
r
tr
a
f
f
ic
c
onge
s
ti
on
dur
in
g
c
r
ow
de
d
hou
r
s
a
nd
pr
o
vi
de
e
m
e
r
ge
nc
y
ve
hi
c
le
s
w
it
h
pr
ot
e
c
te
d
la
ne
s
is
pr
opos
e
d.
T
he
m
a
in
a
im
of
th
is
s
ys
t
e
m
is
to
c
ont
r
ol
tr
a
f
f
ic
e
f
f
e
c
ti
ve
ly
a
nd
e
nc
our
a
g
e
m
ove
m
e
nt
by
e
m
e
r
ge
nc
y
ve
hi
c
le
s
.
E
m
e
r
ge
nc
y
ve
hi
c
le
s
a
r
e
m
a
r
ke
d
w
he
n,
a
t
a
c
e
r
ta
in
di
s
ta
nc
e
,
a
n
R
F
I
D
s
ig
na
l
is
de
te
c
te
d.
W
he
n
a
n
e
m
e
r
ge
nc
y
ve
hi
c
le
is
a
ppr
oa
c
hi
ng,
th
e
tr
a
f
f
ic
s
e
r
v
e
r
not
if
ie
s
th
e
A
r
dui
no
a
t
th
e
ju
nc
ti
on.
T
hi
s
in
f
or
m
a
ti
on
obt
a
in
e
d
by
A
r
dui
no
is
th
e
n
ba
la
nc
e
d
by
th
e
R
F
I
D
s
ig
na
l
a
c
qui
r
e
d
f
r
om
th
e
R
F
I
D
r
e
a
de
r
.
T
hi
s
c
onf
ir
m
s
w
he
th
e
r
or
not
th
e
c
a
r
is
in
a
n
e
m
e
r
ge
nc
y
s
e
tt
in
g.
U
nt
il
ve
r
if
ie
d,
by
s
w
it
c
hi
ng
to
th
e
gr
e
e
n
li
ght
,
th
e
pa
th
f
or
th
e
e
m
e
r
ge
nc
y
ve
hi
c
le
i
s
c
l
e
a
r
e
d.
I
f
a
n
e
m
e
r
ge
nc
y
v
e
hi
c
le
r
e
c
e
iv
e
s
a
n
R
F
I
D
s
ig
na
l
f
r
om
A
r
dui
no,
th
e
n
th
e
gr
e
e
n
li
ght
s
a
r
e
gi
ve
n
f
or
th
e
ir
di
r
e
c
ti
on.
T
r
a
f
f
ic
in
f
or
m
a
ti
on
is
s
ubm
it
te
d
to
th
e
s
e
r
ve
r
s
o
th
a
t,
u
s
in
g
w
e
b pa
ge
s
, u
s
e
r
s
c
a
n de
te
r
m
in
e
t
he
t
r
a
f
f
ic
c
ondi
ti
ons
.
3.
3
.
S
m
ar
t
t
r
af
f
ic
li
gh
t
s
f
or
p
e
d
e
s
t
r
ia
n
s
I
n
[
53]
us
e
s
a
f
uz
z
y
-
ba
s
e
d
a
ppr
oa
c
h
by
a
ppl
yi
ng
th
r
e
e
m
e
m
be
r
s
hi
p
f
unc
ti
ons
(
lo
w
,
m
e
di
um
,
a
nd
hi
gh)
f
or
th
e
num
be
r
of
pe
de
s
tr
ia
ns
(
in
put
)
a
nd
th
e
pha
s
e
of
th
e
tr
a
f
f
ic
li
ght
s
(
out
put
)
.
T
he
c
r
it
ic
a
l
ti
m
e
(
c
r
os
s
in
g
ti
m
e
a
ga
in
is
ti
ght
)
a
nd
nonc
r
it
ic
a
l
ti
m
e
a
r
e
de
te
r
m
in
e
d
by
a
r
ul
e
.
P
e
de
s
tr
ia
n
c
r
os
s
in
g
is
pr
io
r
it
iz
e
d,
s
o
th
e
a
ll
oc
a
ti
on
of
r
e
d
li
ght
ti
m
e
f
or
ve
hi
c
le
s
in
c
r
e
a
s
e
s
if
th
e
n
um
be
r
of
c
r
os
s
e
r
s
in
c
r
e
a
s
e
s
.
I
n
[
54]
opt
im
iz
e
s
tr
a
f
f
ic
li
ght
s
s
o
th
a
t
s
lo
w
pe
de
s
tr
ia
ns
(
di
s
a
bl
e
d/
e
ld
e
r
ly
pe
opl
e
)
c
a
n
c
r
os
s
s
a
f
e
ly
a
nd
c
onge
s
ti
on
is
m
in
im
iz
e
d.
A
ddi
ti
ona
l
gr
e
e
n
li
ght
ti
m
e
is
a
ll
oc
a
te
d
to
pe
de
s
tr
ia
ns
onl
y
w
h
e
n
a
s
lo
w
pe
de
s
tr
ia
n
is
de
te
c
te
d
(
f
r
om
th
e
I
oT
de
vi
c
e
in
s
ta
ll
e
d
on
th
e
s
lo
w
pe
de
s
tr
ia
n)
.
In
[
55]
e
s
ta
bl
is
he
s
a
m
ode
l
f
or
s
ig
na
l
-
c
ont
r
ol
le
d
in
te
r
s
e
c
ti
on
s
im
ul
a
ti
on t
ha
t
c
a
n be
us
e
d t
o t
e
s
t
th
e
e
f
f
ic
a
c
y of
a
da
pt
iv
e
c
ont
r
ol
i
n di
f
f
e
r
e
n
t
t
r
a
f
f
ic
c
ondi
ti
ons
, i
nc
lu
di
ng t
h
e
pr
e
s
e
nc
e
or
a
bs
e
nc
e
of
in
te
r
s
e
c
ti
ona
l
pe
de
s
tr
ia
n
tr
a
f
f
ic
us
in
g
t
he
M
ont
e
C
a
r
lo
m
e
th
od.
T
he
di
f
f
e
r
e
nc
e
in
th
e
s
pe
e
d
of
th
e
in
c
om
in
g
tr
a
f
f
ic
f
lo
w
a
nd
th
e
pr
e
s
e
nc
e
or
a
b
s
e
n
c
e
of
pe
de
s
tr
ia
n
tr
a
f
f
ic
is
d
e
te
r
m
in
e
d
by
th
e
ve
hi
c
le
de
la
y,
que
ue
le
ngt
h,
a
nd
tr
a
f
f
ic
li
ght
c
yc
le
s
.
T
hi
s
r
e
s
e
a
r
c
h
c
r
e
a
te
s
a
num
e
r
ic
a
l
m
ode
l
th
a
t
r
e
p
r
e
s
e
nt
s
th
e
pe
r
f
or
m
a
nc
e
of
a
n
in
te
r
s
e
c
ti
on
w
it
h
a
da
pt
iv
e
c
ont
r
ol
to
obt
a
in
th
e
a
ve
r
a
ge
v
a
lu
e
of
th
e
tr
a
f
f
ic
li
ght
c
yc
le
s
th
a
t
c
a
n
be
us
e
d,
th
e
le
ngt
h
of
th
e
q
ue
ue
a
nd
th
e
ve
hi
c
le
de
la
y.
I
n
[
56]
pr
opos
e
s
a
r
oa
d
c
r
os
s
in
g
s
ys
t
e
m
us
in
g
s
e
ns
or
s
,
C
C
T
V
, a
nd
il
lu
m
in
a
to
r
s
to
tr
a
c
k
pe
d
e
s
tr
ia
ns
a
nd
il
lu
m
in
a
te
th
e
m
to
he
lp
m
ot
or
is
ts
m
or
e
e
a
s
il
y
a
voi
d
da
nge
r
ous
s
it
ua
ti
ons
. T
hi
s
s
y
s
te
m
c
ons
i
s
ts
of
s
ix
m
a
in
pa
r
ts
,
na
m
e
ly
,
a
C
C
T
V
a
n
a
ly
z
e
r
,
w
hi
c
h
w
or
ks
c
lo
s
e
ly
w
it
h
C
C
T
V
to
tr
a
c
k
p
e
de
s
tr
ia
ns
a
nd
r
e
c
or
d
c
r
o
s
s
in
gs
;
bounda
r
y
de
te
c
to
r
s
to
d
e
te
c
t
pe
d
e
s
tr
ia
ns
a
nd
ve
hi
c
l
e
s
e
nt
e
r
in
g
c
e
r
ta
in
a
r
e
a
s
;
il
lu
m
in
a
to
r
s
to
il
lu
m
in
a
te
c
r
os
s
in
gs
a
nd
a
ll
ow
pe
de
s
tr
ia
ns
to
be
s
e
e
n
f
r
om
a
f
a
r
a
nd
to
pr
ovi
de
li
ght
f
or
C
C
T
V
;
c
ont
r
ol
uni
ts
a
nd
c
ont
r
ol
c
e
nt
e
r
s
to
obt
a
in
th
e
la
te
s
t
tr
a
f
f
ic
c
ondi
ti
ons
a
nd
s
e
nd
c
e
r
ta
in
vi
de
o
r
e
c
or
di
ngs
a
nd
ope
r
a
te
a
lg
or
it
hm
s
;
a
nd
e
m
e
r
ge
nc
y
r
e
s
pon
s
e
c
e
nt
e
r
s
f
or
r
e
por
ti
ng
s
y
s
te
m
s
to
th
e
c
ont
r
ol
c
e
nt
e
r
i
n t
he
e
ve
nt
of
a
n a
c
c
id
e
nt
.
3.
4
.
D
is
c
u
s
s
io
n
T
he
de
ve
lo
pm
e
nt
of
s
m
a
r
t
tr
a
f
f
ic
li
ght
te
c
hnol
ogy
in
c
lu
de
s
s
e
ve
r
a
l
a
s
pe
c
ts
,
in
c
lu
di
ng
th
e
pr
oc
e
s
s
of
ve
hi
c
le
de
te
c
ti
on,
bot
h
publ
ic
a
nd
e
m
e
r
ge
nc
y
v
e
hi
c
le
s
,
th
e
pr
oc
e
s
s
of
pe
de
s
tr
ia
n
de
te
c
ti
on,
a
nd
th
e
s
c
he
dul
in
g
a
lg
or
it
hm
u
s
e
d
f
or
va
r
io
us
s
p
e
c
if
ic
s
it
ua
ti
on
s
.
I
n
th
e
pr
oc
e
s
s
of
de
te
c
ti
ng
ve
hi
c
le
s
or
tr
a
f
f
ic
c
onge
s
ti
on, t
e
c
hnol
ogy s
uc
h
a
s
c
a
m
e
r
a
s
, w
ir
e
le
s
s
s
e
n
s
or
ne
two
r
ks
, a
nd R
F
I
D
i
s
us
e
d. T
o de
t
e
c
t
pe
de
s
tr
i
a
ns
a
t
a
c
r
os
s
in
g,
th
e
c
a
m
e
r
a
te
c
hnol
ogy
is
of
te
n
us
e
d.
R
F
I
D
te
c
hnol
ogy
is
c
om
m
onl
y
us
e
d
to
di
s
ti
ngui
s
h
ty
pe
s
o
f
ve
hi
c
le
s
.
I
n
th
is
c
a
s
e
,
e
m
e
r
ge
n
c
y
ve
hi
c
le
s
a
r
e
m
or
e
w
id
e
ly
gi
ve
n
R
F
I
D
to
di
s
ti
ngui
s
h
th
e
m
f
r
om
ot
he
r
ve
hi
c
le
s
.
W
he
n
a
tr
a
f
f
ic
li
ght
de
te
c
ts
th
e
pr
e
s
e
nc
e
of
R
F
I
D
in
a
n
e
m
e
r
ge
nc
y
ve
hi
c
le
,
th
e
la
n
e
of
th
e
e
m
e
r
ge
nc
y
ve
hi
c
le
is
gi
ve
n
pr
io
r
it
y
f
or
th
e
gr
e
e
n
li
ght
s
o
t
ha
t
th
e
e
m
e
r
ge
nc
y
ve
hi
c
le
c
a
n
di
r
e
c
tl
y
pa
s
s
th
r
ough
th
e
c
r
os
s
in
g
w
it
hout
s
to
ppi
ng.
R
F
I
D
is
c
hos
e
n
be
c
a
us
e
it
ha
s
a
lo
ng
-
di
s
ta
nc
e
r
a
nge
,
d
oe
s
not
r
e
qui
r
e
a
li
ne
of
s
ig
ht
,
is
r
obus
t
to
c
h
a
ll
e
ngi
ng
e
nvi
r
onm
e
nt
s
a
nd
c
a
n
tr
a
c
k
obj
e
c
t
s
in
r
e
a
l
-
ti
m
e
.
C
a
m
e
r
a
s
a
r
e
a
lt
e
r
na
ti
ve
t
e
c
hnol
ogy f
or
de
te
c
ti
ng ve
hi
c
le
de
ns
it
y a
nd t
he
pr
e
s
e
nc
e
of
pe
de
s
tr
ia
n
s
be
c
a
us
e
t
he
y c
a
n de
s
c
r
ib
e
tr
a
f
f
ic
c
ondi
ti
ons
w
it
h
h
i
gh
a
c
c
ur
a
c
y
f
r
om
th
e
r
e
s
ul
ts
of
im
a
ge
pr
oc
e
s
s
in
g,
a
lt
hough
th
e
le
ve
l
of
a
c
c
ur
a
c
y
is
di
r
e
c
tl
y
pr
opor
ti
ona
l
to
th
e
im
a
ge
qua
li
ty
obt
a
in
e
d.
I
n
te
r
m
s
o
f
th
e
us
e
of
a
lg
or
it
hm
s
f
or
s
c
he
dul
in
g
tr
a
f
f
ic
li
ght
s
,
in
ge
ne
r
a
l,
a
r
ti
f
ic
ia
l
in
te
ll
ig
e
nc
e
a
nd
m
a
c
hi
ne
le
a
r
ni
n
g
a
lg
or
it
hm
s
s
uc
h
a
s
f
uz
z
y
lo
gi
c
a
lg
or
it
hm
s
,
ge
ne
ti
c
a
lg
or
it
hm
s
a
nd ne
ur
a
l
ne
twor
ks
a
r
e
us
e
d. E
a
c
h of
th
e
s
e
a
lg
or
it
hm
s
ha
s
a
dva
nt
a
ge
s
a
nd dis
a
dv
a
nt
a
ge
s
,
a
s
s
how
n i
n
T
a
bl
e
3.
A
lt
hough
th
e
de
ve
lo
pm
e
nt
of
s
m
a
r
t
tr
a
f
f
ic
li
ght
is
a
bl
e
to
pr
ovi
de
c
onve
ni
e
nc
e
s
u
c
h
a
s
r
e
duc
in
g
tr
a
ve
l
ti
m
e
a
nd
s
to
ps
a
t
in
te
r
s
e
c
ti
ons
,
th
e
r
e
is
one
pr
obl
e
m
th
a
t
hi
nde
r
s
th
e
a
da
pt
a
ti
on
of
s
m
a
r
t
tr
a
f
f
ic
li
ght
,
na
m
e
ly
th
e
c
o
s
ts
r
e
qui
r
e
d
f
or
s
ig
na
l
c
ont
r
ol
de
vi
c
e
s
,
c
om
m
uni
c
a
ti
on
ne
twor
ks
a
nd
pe
r
io
di
c
upd
a
te
s
to
r
e
gul
a
te
s
ys
te
m
s
th
a
t
a
r
e
a
bl
e
to
a
da
pt
to
tr
a
f
f
ic
c
ondi
ti
ons
.
T
hi
s
a
da
pt
iv
e
s
y
s
te
m
r
e
qui
r
e
s
pe
r
io
di
c
tr
a
f
f
ic
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8938
I
nt
J
A
r
ti
f
I
nt
e
ll
,
V
ol
.
10
, N
o.
1, M
a
r
c
h
20
21
:
224
–
233
230
r
e
s
e
a
r
c
h
a
nd
r
e
c
a
li
br
a
ti
on.
F
or
f
ur
th
e
r
te
c
hnol
ogi
c
a
l
de
ve
lo
pm
e
nt
s
,
bot
h
in
te
r
m
s
of
in
dus
tr
y
a
nd
a
c
a
de
m
ic
r
e
s
e
a
r
c
h,
it
is
e
xpe
c
te
d
th
a
t
s
m
a
r
t
tr
a
f
f
ic
li
ght
s
w
il
l
be
a
bl
e
t
o
ope
r
a
te
in
a
c
c
or
da
nc
e
w
it
h
c
ha
ngi
ng
t
r
a
f
f
ic
c
ondi
ti
ons
t
hr
ough high
-
s
pe
e
d c
om
m
uni
c
a
ti
on. F
ur
th
e
r
de
ve
lo
p
m
e
nt
of
t
he
a
lg
or
it
hm
i
s
r
e
qui
r
e
d t
o
be
a
bl
e
t
o
in
te
gr
a
te
pos
it
io
n,
s
pe
e
d
a
nd
que
ue
da
ta
r
e
c
e
iv
e
d
f
r
om
ve
hi
c
le
s
a
s
w
e
ll
a
s
s
e
ns
or
a
nd
tr
a
ns
m
it
te
r
in
f
r
a
s
tr
uc
tu
r
e
,
to
m
a
ke
pr
e
di
c
ti
ons
a
nd
s
tr
a
te
gi
e
s
to
m
oni
to
r
,
le
a
r
n
a
nd
r
e
s
pond
to
tr
a
f
f
ic
c
ondi
ti
ons
opt
im
a
ll
y.
I
n
th
e
f
ol
lo
w
in
g
ye
a
r
s
,
s
m
a
r
t
tr
a
f
f
ic
li
ght
is
e
xpe
c
te
d
to
be
c
om
e
a
n
in
f
r
a
s
tr
uc
tu
r
e
c
a
p
a
bl
e
of
m
a
na
gi
ng t
r
a
f
f
ic
i
nde
pe
nde
nt
ly
s
o t
ha
t
th
e
huma
n e
r
r
or
f
a
c
to
r
i
n t
hi
s
t
a
s
k c
a
n b
e
m
in
im
iz
e
d.
T
a
bl
e
3
. C
om
pa
r
is
on of
a
lg
or
it
hm
s
us
e
d f
or
s
m
a
r
t
tr
a
f
f
ic
l
ig
ht
s
c
he
dul
in
g
F
uz
z
y L
ogi
c
A
l
gor
i
t
hm
G
e
ne
t
i
c
A
l
gor
i
t
hm
N
e
ur
a
l
N
e
t
w
or
k
A
dva
nt
a
ge
s
U
s
e
s
s
i
m
pl
e
m
a
t
he
m
a
t
i
c
s
f
or
s
ys
t
e
m
s
t
ha
t
a
r
e
nonl
i
ne
a
r
, i
s
i
nt
e
gr
a
t
e
d a
nd
c
om
pl
e
x;
ha
s
hi
gh pr
e
c
i
s
i
on.
S
uppor
t
s
m
ul
t
i
obj
e
c
t
i
ve
opt
i
m
i
z
a
t
i
on;
i
s
s
ui
t
a
bl
e
f
or
di
s
c
r
e
t
e
pr
obl
e
m
s
, c
ont
i
nuous
pr
obl
e
m
s
or
bot
h.
C
a
n l
e
a
r
n f
r
om
c
om
pl
e
x a
nd
nonl
i
ne
a
r
r
e
l
a
t
i
ons
hi
p m
ode
l
s
;
ha
s
no l
i
m
i
t
s
on t
he
i
nput
va
r
i
a
bl
e
s
.
D
i
s
a
dva
nt
a
ge
s
H
a
s
ve
r
y hi
gh c
om
put
a
t
i
ona
l
r
e
qui
r
e
m
e
nt
s
f
or
a
hi
gh de
gr
e
e
of
a
c
c
ur
a
c
y;
r
e
s
pons
e
i
s
not
r
e
a
l
-
t
i
m
e
;
l
i
m
i
t
e
d us
e
of
i
nput
va
r
i
a
bl
e
s
.
H
a
s
ve
r
y hi
gh c
om
put
a
t
i
ona
l
r
e
qui
r
e
m
e
nt
s
;
t
a
ke
s
a
l
ong
t
i
m
e
.
R
e
qui
r
e
s
c
ons
i
d
e
r
a
bl
e
c
om
put
i
ng
r
e
s
our
c
e
s
;
no
s
pe
c
i
f
i
c
r
ul
e
s
f
or
de
t
e
r
m
i
ni
ng
t
he
ne
t
w
or
k us
e
d.
4.
C
O
N
C
L
U
S
I
O
N
S
m
a
r
t
tr
a
f
f
ic
li
ght
is
a
te
c
hnol
ogy
th
a
t
is
e
xp
e
c
te
d
to
be
a
bl
e
to
s
ol
ve
c
onge
s
ti
on
pr
obl
e
m
s
.
T
he
m
e
th
ods
a
nd
te
c
hnol
ogi
e
s
u
s
e
d
in
th
e
d
e
ve
lo
pm
e
nt
of
s
m
a
r
t
tr
a
f
f
ic
li
ght
to
r
e
duc
e
tr
a
f
f
ic
de
ns
it
y
a
nd
de
te
c
t
e
m
e
r
ge
nc
y
ve
hi
c
l
e
s
a
s
w
e
ll
a
s
p
e
de
s
tr
ia
n
a
r
e
a
na
l
y
z
e
d
in
th
is
pa
pe
r
.
I
n
th
e
f
ut
ur
e
,
s
m
a
r
t
tr
a
f
f
ic
li
ght
is
e
xpe
c
te
d t
o m
a
na
ge
t
r
a
f
f
ic
i
nde
pe
nde
nt
ly
t
o r
e
duc
e
t
h
e
huma
n
e
r
r
or
f
a
c
to
r
i
n t
hi
s
t
a
s
k
.
A
C
K
N
O
WL
E
D
G
E
M
E
N
T
S
T
hi
s
w
or
k
i
s
f
unde
d
unde
r
th
e
c
ont
r
a
c
t
num
be
r
N
K
B
-
304
1/
U
N
2.R
3.1/
H
K
P
.05.00/2019
by
th
e
I
ndone
s
ia
n
G
ove
r
nm
e
nt
S
c
hol
a
r
s
hi
p
P
M
D
S
U
f
r
om
th
e
M
in
is
tr
y
of
R
e
s
e
a
r
c
h,
T
e
c
hnol
ogy,
a
nd
H
ig
he
r
E
duc
a
ti
on (
K
e
m
r
is
te
kdi
kt
i)
.
R
E
F
E
R
E
N
C
E
S
[1]
T.
Reed
and
J.
Kidd,
“INRIX
Global
Traffic
Sc
orecard,”
2019.
[Online].
Available:
https://static.poder360.com.br/2019/02/INRIX_2018_Global_Traffic_Score
card_Report__final_.pdf.
[2]
G.
Cookson,
“INRIX
Global
Traffic
Scorecard,”
2018.
[Online].
Available:
https://www.missionline.it/wp
-
content/
uploads/
2018/02
/INRIX_20
17_Traffic_
Scorecard_F
ina
l.pdf
[3]
D.
A.
Hennessy
and
D.
L.
Wiesenthal,
“Traffic
Congestion,
Driver
Stress,
and
Driver
Aggression,”
Aggresiv
e
Behav.
, vol. 25, pp. 409
–
423, 1999,
DOI: 10.1002/(S
ICI)1098
-
2337(1999)25:6<
409::AID
-
AB2>
3.0.CO;2
-
0.
[4]
Jakarta
Open
Data,
“Causes
of
Congestion
in
Jakarta
in
2011,”
2015.
[Online].
Available:
http://data.jakarta.go.id/dataset/d341296f
-
f5c3
-
4276
-
9cdb
-
b514d14673b9/resource/a4175fba
-
a0eb
-
4ced
-
9f66
-
8e225206a06f/download/Data
-
Penyeb
ab
-
Kemacetan
-
di
-
Jakarta
-
Tahun
-
2011.csv. [Accessed: 27
-
Apr
-
2019].
[5]
O.
Avate
fipour,
S.
Member,
F.
Sadry,
and
S.
Member,
“Traffic
M
an
agement
System
Using
IoT
Technology
-
A
Comparat
ive
Review,”
2018
IEEE
Int.
Conf.
Electro/Information
Technol,
2018
,
pp.
1041
–
1047,
doi:
10.1109/EIT.2018.8500246.
[6]
M.
Kabrane,
S.
Krit,
and
L.
El
Maimou
ni,
“Smart
Cities:
Study
and
Comparison
of
Traffic
Light
Optimization
in
Modern
Urban
Areas
Using
Artificial
Intelligence,”
Int.
J.
Adv.
Res.
C
omput.
Sci.
Softw.
Eng.
,
vol.
8,
no.
2,
pp.
10
-
18, 2018, doi:10.23956/ijarcsse.v8i2.570.
[7]
R.
Hawi,
G.
Okeyo,
and
M
.
Kimwele,
“Techniques
for
Smart
Tr
affic
Control:
An
In
-
depth
Review,”
Int.
J.
Comput. Ap
pl. Techn
ol. Res.
, vol. 4, no. 7, pp. 566
–
573, 2015, doi:10.7753/IJCATR0407.1014.
[8]
A.
H.
Ahmed,
“A
Review
of
Adaptive
Intelligent
Traffic
Control
Systems,”
J.
Res.
Bus.
Soc.
Sci.
,
vol.
1,
no.
1,
pp.
2209
–
7880, 2018.
[9]
C.
Mcshane,
“The
Origins
And
Globalization
Of
Traffic
Control
Signals,”
J.
Urban
Hist.
,
vol.
25,
no.
3,
pp.
379
–
404, 1999.
[10]
The
Henry
Ford,
“First
Tri
-
Color,
Four
-
Directional
Traffic
Signal,
1920.”
[Online].
Available:
https://www.thehenryford.org/collections
-
and
-
research/digit
al
-
collecti
ons/arti
fact/2274
57/#sl
ide=
gs
-
225140.
[11]
L.
Qi,
M.
Zhou,
and
W.
Luan,
“Emergency
Traffic
-
Light
Control
System
Design
for
Intersections
Subject
to
Accidents,”
IEEE Trans
. Intell.
Transp.
Syst.
, vol. 17, no. 1, pp. 1
–
14, 2016, doi:10.1109/TITS.2015.2466073.
[12]
L.
Cruz
-
piris,
D.
Rivera,
S.
Fernandez,
a
nd
I.
Marsa
-
maestre,
“O
ptimized
Sensor
Network
and
Multi
-
Agen
t
Decision
Support
for
Smart
Traffic
Light
Management,”
Se
nsors
,
vol.
18,
no.
2,
pp.
435,
2018,
doi:10.3390/s18020435.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
r
ti
f
I
nt
e
ll
I
S
S
N
:
2252
-
8938
R
e
c
e
nt
de
v
e
lo
pm
e
nt
of
s
m
a
r
t
tr
af
fi
c
l
ig
ht
s
(
A
’
is
y
a N
ur
A
ul
ia
Y
us
uf
)
231
[13]
K.
Zaatouri,
M.
H.
Jeridi,
and
T.
Ezzedine,
“Adaptive
Traffic
Light
Control
System
Based
on
WSN
:
Algorithm
Optimization
and
Hardware
Design,”
in
26th
International
Confer
ence
on
Software,
Telecommunications
and
Computer
Networks (
SoftCOM)
, pp. 1
–
6, 2018, doi:10.23919/SOFTCOM.2018.8555802.
[14]
W.
Liu
et
al.
,
“Real
-
Time
Traffic
Light
R
ecogniti
on
Based
on
Smart
phone
Platform
s,”
IEEE
Trans.
Circuits
Syst.
Video Technol.
, vol. 27, no. 5, pp. 1118
–
1131, 2017, doi:10.1109/TCSVT.2016.2515338..
[15]
L.
Cruz
-
piris,
D.
Rivera,
I.
Marsa
-
m
aestre,
E.
De,
and
S.
Fernandez,
“Intelligent
Traffic
Light
Mana
gement
using
Multi
-
Behavior
al
Agents,”
in
Jornadas
de
Ingenieri
a
Telemati
ca
,
pp.
27
–
29,
2017
,
d
oi:
10.4995/JITEL2017.2017.7061
.
[16]
A.
Atta,
S.
Abbas,
and
M.
A.
Khan
et
al
.,
“An
adaptive
Approach
:
S
mart
Traffic
Congestion
Control
System,”
J.
King Saud U
niv.
-
Comput. In
f. Sci.
, 2018, doi:10.1016/j.jksuci.2018.10.011.
[17]
Z.
Cao,
S.
Jiang,
J.
Zhang,
and
H.
Guo,
“A
Unified
Framework
for
V
ehicle
Rerouting
and
Traffic
Light
Control
t
o
Reduce
Traffic
Congestion,”
IEEE
Trans.
Intell.
Transp.
Syst.
,
v
ol.
18,
no.
7,
pp.
1
958
-
1973,
July
2017,
doi:10.1109/TITS.2016.2613997.
[18]
A.
Ahmad,
R.
Arshad,
S.
A.
Mahmud,
G.
M.
Khan,
H.
S.
Al
-
raweshi
dy,
and
S.
Member,
“Earliest
-
Deadline
-
Based
Schedu
ling
to
Reduce
Urban
Traf
fic
Congesti
on,”
IEEE
Trans.
Intell.
Transp.
Syst.
,
vol.
15,
no.
4
,
pp.
1510
–
1526
,
2014, doi:10.1109/TITS.2014.2300693.
[19]
Khushi,
“Smart
Control
of
Traffic
Light
System
using
Image
Process
ing,”
in
Internati
onal
Conference
on
Current
Trends
in
Computer,
Electrical,
Electronics
and
Communication
(CTCEEC)
,
pp.
99
–
103,
2017,
d
oi:10.1109/CTCEEC.2017.8454966.
[20]
L.
Qi,
M.
Zhou,
and
W.
Luan,
“A
Two
-
level
Traffic
Light
Control
S
trategy
for
Preventing
Incident
-
Based
Urban
Traffic
Congestion,”
IEEE
Trans.
Intell.
Transp.
Syst.
,
vo
l.
19,
no.
1,
pp.
13
-
24,
Jan.
2018
,
doi:10.1109/TITS.2016
.2625324.
[21]
R.
F.
Adebiyi,
K.
A.
Abubilal,
M.
B.
Mu’azu,
and
B.
H.
Adebiyi,
“Development
and
Simulation
of
Adaptiv
e
Traffic
Light
Controller
Using
Artificial
Bee
Colony
Algorithm,”
Int.
J.
Intell.
Syst.
Appl.
,
vol.
8,
pp.
68
–
74,
2018
,
doi:
10.5815/ijisa.2018.08.06.
[22]
S.
Mishra,
D.
Bhattacharya,
and
A.
Gupta,
“Congestion
Adapti
ve
Traffic
Light
Control
and
Notification
Architecture Using Goog
le Maps APIs,”
Data
, vol. 3, no. 4, 2018, doi:10.3390/data3040067.
[23]
C.
M.
Silva,
A.
L.
L.
Aquino,
and
W.
M
.
Jr,
“Smart
Traffic
Light
for
Low
Traffic
Conditions
A
Solution
for
Improving
the Drivers S
afety,”
Mob. Netw
. Appl.
, vol. 20, pp. 285
–
293, 2015, doi:10.1007/s11036
-
015
-
0571
-
x.
[24]
C.
Suthaputchakun
and
Z.
Sun,
“A
Novel
Traffic
Light
Scheduling
Based
on
TLVC
a
nd
Vehicles’
Priority
fo
r
Reducing
Fuel
Consumption
and
$
\
text{
CO}
_2$
Emission,”
in
IEE
E
Systems
Journal
,
vol.
12,
no.
2,
pp.
1230
-
1238, June 2018, doi: 10.1109/JSYST.2015.2500587.
[25]
R.
Hawi,
G.
Okeyo,
and
M.
Kimwele,
“Smart
Traffic
Light
Contr
ol
using
Fuzzy
Logic
and
Wireless
Senso
r
Network,” in
Computing Co
nferenc
e
, 2017, pp. 450
–
460, doi:10.1109/SAI.2017.8252137.
[26]
H.
Chai,
H.
M.
Zhang,
D.
Ghosal,
and
C.
Chuah,
“Dynamic
traffi
c
routing
in
a
network
with
adaptive
signa
l
control,
”
Transp. R
es. Pa
rt C
, vol. 85,
pp. 64
–
85, 2017, doi:10.1016/j.trc.2017.08.017.
[27]
U.
Andayani,
D.
Arisandi,
B.
Siregar,
M.
F.
Syahputra,
and
M.
A.
M
uchtar,
“Simulation
of
Dynamic
Traffic
Light
Setting
Using
Adaptiv
e
Neuro
-
Fuzzy
Inference
System
(
ANFIS
)
Simulation
of
Dynamic
Traffic
Ligh
t
Setting
Using Adaptive Neuro
-
Fuzzy
Infer
ence
System
( ANFI
S ),”
J. Phys.
C
onf. Ser
.
, vol. 1235, 2019, doi:10.1088/1742
-
6596/1235/1/012058.
[28]
F.
Kurniawan,
H.
Sajati,
and
O.
Dinaryanto,
“Adaptive
Traffic
Controller
Based
On
Pre
-
Timed
System,
”
TELKOMNI
KA
, vo
l. 14, no. 1, p
p. 56
–
63, 2016, doi:10.12928/TELKOMNIKA.v14i1.2798.
[29]
S.
S.
Mousavi,
M.
Schukat,
and
E.
Howley,
“Traffic
light
control
usi
ng
deep
policy
-
gradient
and
value
-
function
-
based reinforceme
nt learning,”
IET Intell
. Trans
p. Syst.
, vol. 11, pp. 417
–
42
3, 2017, doi:10.1049/iet
-
its.2017.0153.
[30]
A.
Simdiankin,
I.
Uspensky,
L.
Belyu,
and
K.
Ratnikov,
“A
met
hod
to
assess
congestion
in
various
traffic
directions
A
method
to
assess
congestion
in
various
traffic
di
rection
s,”
Transp.
Res.
Proce
dia
,
vol.
36,
pp.
72
5
–
731, 2018, doi:10.1016/j.trpro.2018.12.099.
[31]
W.
Genders
and
S.
Razavi,
“Evaluating
reinforcement
learning
stat
e
representations
for
adaptive
traffic
signal
control,
”
Procedia Comput. Sci.
, vol. 130, pp. 26
–
33, 2018, doi:10.1016/j.procs.2018.04.008.
[32]
N.
M.
Sadiq
and
S.
A.
Adepoju,
“Adaptive
Traffic
Control
System
using
Modified
Round
Robin
and
Genetic
Algorithm,”
i
-
manager’s J. Digit
. Signal Pro
cess.
, vol. 6, no. 2, pp. 17
–
24, 2018, doi:10.26634/jdp.6.2.15592.
[33]
S.
Roy
and
M.
S.
Rahman,
“Emergency
Vehicle
Dete
ction
on
Heavy
Traffic
Road
from
CCTV
Footage
Usin
g
Deep
Convolutional
Neural
Network,”
2019
Int.
Conf.
Electr.
Co
mput.
Commun.
Eng.
,
pp.
1
–
6,
2019,
doi:
10.1109/ECACE.2019.8679295.
[34]
I.
Santos
-
gonzález,
P.
Caballero
-
gil,
A.
Rivero
-
garcía,
and
C.
Caballero
-
g
il,
“Priority
and
collision
avoidance
system for traf
fic lights,”
Ad Hoc Networks
, vol. 94, 2019, doi:10.1016/j.adhoc.2019.101931.
[35]
M.
Özkul,
I.
Capuni,
and
E.
Domnori,
“Context
-
Aware
Intellig
ent
Traffic
Light
Control
through
Secure
Messaging,”
J. Adv. T
ran
sp.
, vol. 2018, 2018, doi:10.1155/2018/4251701.
[36]
C.
Miao,
H.
Liu,
G.
G.
Zhu,
and
H.
Chen,
“Connectivity
-
based
optimization
of
vehicle
route
and
speed
for
improved
fuel
economy,”
Transp.
Res.
Part
C
,
vol.
91,
no.
April,
pp.
353
–
368,
2018
,
doi:10.1016/j.trc.2
018.04.014.
[37]
N.
Taherkhani,
S.
Pierre,
and
S.
Member,
“Centralized
and
Local
ized
Data
Congestion
Control
Strategy
for
Vehicular
Ad
Hoc
Networks
Using
a
Machine
Learning
Clustering
A
lgorithm,”
IEEE
Trans.
Intell.
Transp.
Syst.
,
vol. 17, no. 11, pp. 3275
–
3285, 2016, doi:
10.1109/TITS.2016.2546555.
[38]
X.
Wen
-
juan
and
L.
Jian
-
feng,
“Application
of
Vision
Sensing
Technology
in
Urban
Intelligent
Traffic
Control
System,”
2018 4th Int. Conf. Comput. Technol. Appl
, pp. 74
–
77, 2018, doi:10.1109/CATA.2018.8398659.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8938
I
nt
J
A
r
ti
f
I
nt
e
ll
,
V
ol
.
10
, N
o.
1, M
a
r
c
h
20
21
:
224
–
233
232
[39]
D.
Hartanti,
R.
N.
A
ziza,
and
P.
C.
Siswipraptini,
“Optimization
of
smart
traffic
lights
to
prevent
traffic
congestion
using fuzzy logic,”
TELKOMNI
KA
, vol. 17, no. 1, pp. 320
–
327, 2019, doi:10.12928/TELKOMNIKA.v17i1.10129.
[40]
J.
Ferrer,
J.
García
-
nieto,
E.
Alba,
and
F.
Chicano,
“Intelligent
Testi
ng
of
Traffic
Light
Programs
:
Validation
in
Smart Mo
bility Sc
enar
ios,”
Math. Prob
l. Eng
, vol. 2016, 2016, doi:10.1155/2016/3871046.
[41]
O.
Younis,
N.
Moayeri,
and
S.
Member,
“Employing
Cyb
er
-
Physica
l
Systems :
Dynamic
Traf
fic
Light
Control
at
Road Inte
rsection
s,”
IEEE Internet
Things
J.
, vol. 4, no. 6, pp. 2286
–
2296, 2017, doi:10.1109/JIOT.2017.2765243.
[42]
Y.
Celik
and
A.
T.
Karadeniz,
“Intelligent
Systems
and
Application
s
in
Engineering
Urban
Traffic
Optimization
with Real Tim
e Intelligence Intersection
Traffic Light Sys
tem,”
Int. J.
Intell. Sys
t. Appl.
Eng.
, vol. 6, no. 3, pp. 214
-
219, 2018, DOI: 10.18201/ijisae.2018644780.
[43]
R.
H.
Goudar
and
H.
N.
Megha,
“Next
generation
intelligent
traffic
ma
nagement
system
and
analysis
for
smart
cities,”
in
Internati
onal Con
ference On Smar
t Technol
ogy for Sma
rt Nati
on
, 2017, pp. 999
–
1003.
[44]
K.
M.
A.
Yousef,
A.
Shatnawi,
M.
Latayfeh,
K.
M.
Ahmad,
A.
Shat
nawi,
and
M.
Latayfeh,
“Intelligent
Tra
ffic
Light
Scheduli
ng
Technique
Using
Calendar
-
Based
History
Informati
on,”
Futur.
Gener.
Comput.
Syst
,
vol.
91,
pp
.
124
-
135, 2018, doi:
10.1016/j.future.2018.08.037.
[45]
S.
Kulkarni,
“Intelligent
Traffic
Control
System
Implementation
for
T
raffic
Violation
Control,
Congestion
Con
trol
and
Stolen
Vehicle
Detection,”
Int.
J.
Recent
Contrib.
from
Eng.
S
ci.
IT
,
vol.
5,
no.
2,
pp.
57
–
71,
2017,
DOI:
10.3991/ijes.v5i2.7230.
[46]
K.
Nellore
and
G.
P.
Hancke,
“Traffic
Management
fo
r
Emergency
Vehicle
Priority
Based
on
Visual
Sensing,”
Sensors
, v
ol. 16, no. 11, 2016, doi: 10.3390/s16111892.
[47]
S.
Kapoor,
P.
Gupta,
P.
Sharma,
and
P.
N.
Singh,
“Intelligent
Amb
ulance
with
Automatic
Traffic
Control,”
Int.
Res. J. Eng. Technol
, vol. 04, no. 04, pp. 1264
–
1266, 2017.
[48]
S.
Amir,
M.
S.
Kamal,
S.
S.
Khan,
and
K.
M.
A.
Salam,
“PLC
Ba
sed
Traffic
Control
System
with
Emergency
Vehicle
Detection
and
Management,”
in
Internati
onal
Conference
o
n
Intelligen
t
Computin
g,Instrumen
tation
an
d
Control Tec
hnologies
(ICICICT)
, 2017, pp. 1467
–
1472, doi: 10.1109/ICICICT1.2017.83427
86.
[49]
A.
Rego
et
al.
,
“Software
Defined
Network
-
based
Control
Syste
m
for
an
Efficient
Traffic
Management
for
Emergency
Situations
in
Smart
Cities,”
Futur.
Gener.
Comput.
Syst
,
vol.
88,
pp.
243
-
253,
2018,
doi:
10.1016/j.future.2018.05.054.
[50]
B.
J.
Saradha,
“Int
elligent
Traffic
Signal
Control
System
For
Ambul
ance
Using
RFID
And
CLOUD,”
Int.
Conf.
Comput. Com
mun. Tec
hnol
, pp. 90
–
96, 2017, doi: 10.1109/ICCCT2.2017.7972255.
[51]
S. Anton
ov, “Sma
rt tra
ffic
contro
l system
for a
mbulanc
e,”
Advanced
Aspects of Theoretical Ele
ctrical
Engineer
ing,
Sofia’2016,
pp. 95
-
98, 2017.
[52]
T.
Naik,
R.
Roopalakshmi,
D.
R.
N,
P.
Jain,
and
B.
H.
Sowmya,
“R
FID
-
Based
Smart
Traffic
Control
Framework
for Emergency Vehi
cles,”
2018 Second Int. Conf. Inven. Commun. Comput. Technol.
, pp. 398
–
401, 2018.
[53]
G.
P.
Id,
T.
C.
Id,
and
A.
Canale,
“Smart
Pedestrian
Crossing
Management
at
Traffic
Light
Junctions
through
a
Fuzzy
-
Based Ap
proach
,”
Futur. Internet
, vol. 10, no. 2, 2018, doi:
10.3390/fi10020015.
[54]
H.
J.
Lee,
R.
Y.
Kim
and
H.
S.
Son,
“Evaluation
of
a
Smart
Traffic
Light
System
with
an
IOT
-
based
Connective
Mechanism,”
Internati
onal
Informati
on
Institut
e
(Tokyo).
Informati
on
,
vol.
20,
no.
2,
pp.
953
-
961,
2017.
[Online].
Available:
https://search.proquest.com/scholarly
-
journals/eva
luation
-
smart
-
traffic
-
light
-
system
-
with
-
iot/docview/20
32343134/se
-
2?accountid=
17242.
[55]
R.
Andronov
and
E.
Leverents,
“Calculation
of
vehicle
delay
at
signal
-
controll
ed
intersect
ions
with
adaptive
traffic
cont
rol algorit
hm,”
MATEC Web C
onf.
, vol. 143, 2018, DOI: 10.1051/matecconf/201714304008.
[
56]
K.
An,
Y.
J.
Jeong,
S.
Lee,
and
D.
Seo,
“Smart
Crossing
System
usin
g
IoT,”
in
IEEE
International
Conference
on
Consumer
Electron
ics (ICCE
)
, pp. 9
–
10, 2017
.
B
I
O
G
R
A
P
H
I
E
S
O
F
A
U
T
H
O
R
S
A’isya
Nur
Aulia
Yusuf
received
the
Bachelor
degree
in
Informat
ion
Technology
from
the
Universitas
Gadjah
Mada
2018.
She
is
a
PMDSU
scholarship
awarde
e
and
a
doctor
candidate
at
the Univer
sity of Indone
sia. Her
resear
ch intere
st are Ma
chine Le
arning an
d IoT.
Ajib Setyo Arifin
received
the Bachelor
in
Electrical En
gineering and
Master’s Degree fro
m
the
Univer
sitas
Indonesia,
in
2009
and
2011,
respectively.
He
has
got
the
PhD
degree
in
Telecommunications
in
2015
from
the
Keio
University,
Japan.
He
is
an
assistant
professor
at
Universitas
Indonesia.
He
is
a
head
of
telecommunication
laboratory
i
n
Department
of
E
lectrica
l
Engineering.
His
research
areas
include
Wireless
Sensor
Networks,
Wireless
Communication,
and sign
al process
ing for
communi
cation.
He is a m
ember of t
he IEEE.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
r
ti
f
I
nt
e
ll
I
S
S
N
:
2252
-
8938
R
e
c
e
nt
de
v
e
lo
pm
e
nt
of
s
m
a
r
t
tr
af
fi
c
l
ig
ht
s
(
A
’
is
y
a N
ur
A
ul
ia
Y
us
uf
)
233
Fitri
Yuli
Zulkifli
received
all
her
degree
in
electrical
engineering
for
Bachelo
r
(1997)
and
PhD
(cum
laude)
degrees,
(2009)
from
Universitas
Indonesia,
while
MSc
degree
in
Telecommunication and Information Technology Department, University
of Karlsruhe, Germany
(2002).
She
received
DAAD
(Deutscher
Akademischer
Austauschdi
enst)
schola
rship
to
study
her
master
degree
in
Germany.
Her
research
interests
are
Antenna,
Pr
opagation,
Microwave
and
in
the
field
of
Electromagnetic.
She
joined
the
Antenna
Propagation
and
Microwave
Research
Group (AMRG) UI since 199
7 and
has become lecturer since
1998. S
he has published more than
200
papers
in
international/national
journals
and
conference
proceedi
ngs
and
has
been
involved
in
more
than
40
granted
researches.
With
all
of
here
activities,
in
20
11
she
was
granted
“Best
Lecturer
Award
(Dosen
Berprestas
i)”
from
Universitas
Indonesia
and
achieved
4th
place
“Best
Lecturer
Award”
from
the
government
of
Republic
Indonesia
in
th
e
same
year.
Prof.
Yuli
is
involved
in
many
teamwork
activities
and
also
involved
as
organ
izing
committee
in
many
seminars
and
worksh
ops.
She
has
been
the
Secretary
and
Treasur
er
of
IEEE
joint
chapter
MTT/AP
and
in
2010
as
Treasurer
of
the
same
joint
chapter,
then
from
2011
-
2012
she
has
become
the
joint
chapter
chair.
2013
-
2016
she
was
the
coordinator
for
technical
activity
in
IEEE
Indo
nesia
section.
In
2017
-
2018,
she
was
the
IEEE
Indonesia
Sectio
n
Chair
and
in
2019
-
2020,
she
serves
as
committee
member
for
R10
Conference
and
Technical
Seminar
and
Conference
Quality
Management.
Now
she
is
the
executive
committee
of
joint
ch
apter
MTT/AP
-
S
and
also
head of advisory board of I
EEE Indonesia Section.
Evaluation Warning : The document was created with Spire.PDF for Python.