I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
pu
t
er
E
ng
ineering
(
I
J
E
CE
)
Vo
l.
1
4
,
No
.
5
,
Octo
b
er
20
2
4
,
p
p
.
5
8
4
8
~
5
8
5
7
I
SS
N:
2088
-
8
7
0
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijece.
v
1
4
i
5
.
pp
5
8
4
8
-
5
8
5
7
5848
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
Pedestr
ia
n f
lo
w
p
rediction i
n com
mercia
l av
enue
M
a
rwa
ne
B
en
ha
do
u
1
,
Am
in
a
E
l G
o
nn
o
un
i
2
,
Abde
lo
ua
hi
d L
y
hy
a
o
ui
2
1
La
b
o
r
a
t
o
r
y
o
f
E
c
o
n
o
mi
c
S
t
u
d
i
e
s,
D
i
g
i
t
a
l
A
n
a
l
y
s
i
s,
a
n
d
A
r
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
F
a
c
u
l
t
y
o
f
La
w
Ec
o
n
o
m
i
c
a
n
d
S
o
c
i
a
l
S
c
i
e
n
c
e
s
o
f
Te
t
o
u
a
n
,
A
b
d
e
l
m
a
l
e
k
Ess
a
â
d
i
U
n
i
v
e
r
si
t
y
,
Te
t
o
u
a
n
,
M
o
r
o
c
c
o
2
La
b
o
r
a
t
o
r
y
o
f
I
n
n
o
v
a
t
i
v
e
Te
c
h
n
o
l
o
g
i
e
s,
N
a
t
i
o
n
a
l
S
c
h
o
o
l
o
f
A
p
p
l
i
e
d
S
c
i
e
n
c
e
s
,
A
b
d
e
l
m
a
l
e
k
Essa
â
d
i
U
n
i
v
e
r
s
i
t
y
,
T
a
n
g
i
e
r
,
M
o
r
o
c
c
o
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Dec
1
3
,
2
0
2
3
R
ev
is
ed
J
u
n
8
,
2
0
2
4
Acc
ep
ted
J
u
n
1
6
,
2
0
2
4
M
o
b
i
li
ty
p
lan
s
a
re
o
n
e
o
f
t
h
e
m
o
st
imp
o
rtan
t
m
a
n
a
g
e
m
e
n
t
t
o
o
ls
fo
r
c
it
y
d
e
v
e
lo
p
m
e
n
t
a
n
d
a
n
imp
o
rtan
t
fa
c
to
r
fo
r
so
c
iety
a
n
d
e
c
o
n
o
m
i
c
g
ro
wth
,
wh
e
re
p
e
d
e
strian
s
a
re
th
e
e
n
d
g
o
a
l
o
f
a
n
y
m
o
b
il
it
y
p
lan
.
Hu
m
a
n
b
e
h
a
v
io
r
is
g
e
n
e
ra
ll
y
u
n
p
re
d
icta
b
le,
a
n
d
m
a
n
y
a
tt
e
m
p
ts
h
a
v
e
b
e
e
n
in
t
e
re
ste
d
a
t
p
e
d
e
strian
s'
m
o
b
il
it
y
i
n
u
r
b
a
n
e
n
v
ir
o
n
m
e
n
ts
,
b
o
th
m
icro
s
c
o
p
ic
a
n
d
m
a
c
ro
sc
o
p
ic
(flo
w,
d
e
n
si
ty
,
a
n
d
sp
e
e
d
)
lev
e
ls.
Th
e
o
b
jec
ti
v
e
o
f
p
e
d
e
strian
traffic
flo
w
p
re
d
ictio
n
is
to
p
re
d
ict
t
h
e
n
u
m
b
e
r
o
f
p
e
d
e
strian
s
a
t
th
e
n
e
x
t
m
o
m
e
n
t.
As
sistin
g
o
p
e
ra
to
rs
a
n
d
c
it
y
m
a
n
a
g
e
rs
i
n
m
a
k
in
g
d
e
c
isio
n
s
in
u
r
b
a
n
e
n
v
iro
n
m
e
n
ts
su
c
h
a
s
e
m
e
rg
e
n
c
y
su
p
p
o
rt
sy
ste
m
s,
a
n
d
q
u
a
li
t
y
-
of
-
se
rv
ice
e
v
a
lu
a
ti
o
n
.
Th
is
stu
d
y
a
ims
to
m
o
d
e
l
a
n
d
p
re
d
ict
b
i
-
d
irec
ti
o
n
a
l
p
e
d
e
strian
flo
w
in
a
c
o
m
m
e
rc
ial
a
v
e
n
u
e
,
b
a
se
d
o
n
tw
o
e
ss
e
n
ti
a
l
sta
g
e
s,
d
a
ta
c
o
ll
e
c
ti
o
n
th
ro
u
g
h
v
i
d
e
o
re
c
o
rd
i
n
g
o
v
e
r
two
m
o
n
th
s (p
e
d
e
strian
fl
o
w) an
d
d
a
ta an
a
ly
sis
u
sin
g
m
a
c
h
i
n
e
lea
rn
in
g
a
l
g
o
ri
th
m
s
th
a
t
p
ro
v
i
d
e
a
lo
we
r
e
rro
r
a
n
d
a
h
ig
h
e
r
a
c
c
u
ra
c
y
ra
te.
Two
m
e
tri
c
s
we
re
se
lec
ted
a
s
b
a
sic
m
e
a
su
re
s
to
e
v
a
lu
a
te
th
e
m
o
d
e
l
p
e
rfo
rm
a
n
c
e
s,
ro
o
t
m
e
a
n
sq
u
a
re
e
rro
r
(
RM
S
E
)
a
n
d
c
o
e
fficie
n
t
o
f
d
e
ter
m
in
a
ti
o
n
R
2
.
Artifi
c
ial
n
e
u
ra
l
n
e
two
rk
(
AN
N)
g
iv
e
s
a
li
t
tl
e
b
e
tt
e
r
p
e
rfo
rm
a
n
c
e
a
n
d
fi
tn
e
ss
.
K
ey
w
o
r
d
s
:
Fo
r
ec
asti
n
g
Ma
ch
in
e
lear
n
in
g
Mo
r
o
cc
o
Ped
estrian
f
lo
w
Su
s
tain
ab
le
m
o
b
ilit
y
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
:
Ma
r
wan
e
B
en
h
ad
o
u
L
ab
o
r
ato
r
y
o
f
E
co
n
o
m
ic
Stu
d
i
es,
Dig
ital A
n
aly
s
is
,
an
d
Ar
tific
ial
I
n
tellig
en
ce
,
Facu
lty
o
f
L
aw
E
co
n
o
m
ic
an
d
So
cial
Scien
ce
s
o
f
T
eto
u
a
n
,
Ab
d
elm
alek
E
s
s
aâ
d
i U
n
iv
er
s
ity
Ma
r
til T
éto
u
an
h
ig
h
way
,
T
ét
o
u
an
,
Mo
r
o
cc
o
E
m
ail:
m
ar
wan
e.
f
eg
.
i
n
f
o
@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
W
alk
in
g
is
an
ess
en
tial
ac
tiv
ity
with
in
u
r
b
an
ce
n
ter
s
,
wh
er
e
v
ar
io
u
s
tr
av
el
-
attr
ac
tin
g
ac
t
iv
ities
ar
e
co
n
ce
n
tr
ated
(
s
ch
o
o
ls
,
h
o
s
p
itals
,
s
h
o
p
p
in
g
ce
n
ter
s
,
an
d
ad
m
i
n
is
tr
ativ
e
en
titi
es).
T
h
is
co
n
ce
n
tr
atio
n
o
f
ac
tiv
ity
attr
ac
to
r
s
ca
u
s
es
co
n
g
esti
o
n
at
th
e
lev
el
o
f
p
e
d
estrian
f
lo
w,
i
n
ad
d
itio
n
,
t
h
ese
ar
ea
s
ar
e
n
o
t
alwa
y
s
s
u
itab
le
to
s
u
p
p
o
r
t
h
ig
h
p
ed
estrian
f
lo
w,
s
u
ch
as
n
ar
r
o
w
o
r
p
o
o
r
ly
m
ain
tain
ed
s
id
ewa
lk
s
with
a
v
ar
iety
o
f
o
b
s
tacle
s
in
ter
p
o
s
ed
,
wh
ich
o
f
f
er
a
p
o
o
r
lev
el
o
f
s
er
v
ice
to
p
ed
estrian
s
.
T
h
er
ef
o
r
e,
th
e
s
tu
d
y
o
f
p
ed
e
s
tr
ian
f
lo
w
aim
s
to
in
cr
ea
s
e
p
ed
estrian
s
af
ety
,
m
ain
tain
th
e
p
ed
estrian
n
etwo
r
k
'
s
co
n
tin
u
ity
,
en
co
u
r
a
g
e
walk
in
g
,
an
d
im
p
r
o
v
e
th
e
q
u
ality
o
f
p
ed
estrian
s
er
v
ice
[
1
]
.
W
e
ch
o
s
e
as
a
s
tu
d
y
ar
ea
a
c
o
m
m
er
cial
a
v
en
u
e,
wh
er
e
m
o
s
t
o
f
th
e
s
to
r
es
a
n
d
s
h
o
p
p
i
n
g
ce
n
ter
s
ar
e
co
n
ce
n
tr
ated
.
T
h
is
c
o
n
ce
n
tr
at
io
n
ca
u
s
es
a
h
ig
h
d
em
a
n
d
in
ter
m
s
o
f
p
e
d
estrian
f
lo
w.
Ur
b
an
in
f
r
astru
ctu
r
es
m
u
s
t
b
e
ad
a
p
ted
to
s
u
p
p
o
r
t
th
e
lev
el
o
f
s
er
v
ice
r
e
q
u
ir
ed
(
a
v
o
id
co
n
g
esti
o
n
)
.
T
h
e
m
ath
e
m
atica
l
m
o
d
elin
g
o
f
p
ed
estrian
m
o
v
em
en
t
is
r
elat
iv
ely
co
m
p
lex
,
t
h
at'
s
wh
y
we
r
eso
r
t
to
ex
p
er
im
en
tal
d
ata
s
u
ch
as
p
ed
estrian
f
lo
w,
d
ef
i
n
ed
as
t
h
e
n
u
m
b
er
o
f
p
e
d
estrian
s
p
ass
in
g
th
r
o
u
g
h
an
ar
ea
in
a
s
p
ec
if
ic
tim
e
i
n
ter
v
al.
T
h
r
o
u
g
h
th
e
u
s
e
o
f
m
ac
h
i
n
e
lear
n
in
g
alg
o
r
ith
m
s
,
we
will
m
o
d
el
a
n
d
p
r
e
d
ict
p
ed
estrian
f
lo
w
an
d
th
u
s
h
av
e
a
to
o
l
to
ass
is
t
o
p
er
ato
r
s
an
d
city
m
a
n
ag
er
s
in
m
ak
in
g
d
ec
is
io
n
s
in
u
r
b
an
en
v
ir
o
n
m
e
n
ts
an
d
co
n
tr
o
llin
g
p
e
d
estrian
cr
o
wd
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:
2088
-
8
7
0
8
P
ed
estr
ia
n
flo
w
p
r
ed
ictio
n
in
co
mme
r
cia
l a
ve
n
u
e
(
Ma
r
w
a
n
e
B
en
h
a
d
o
u
)
5849
T
o
u
n
d
er
s
tan
d
p
ed
estrian
b
eh
av
io
r
i
n
u
r
b
an
j
o
u
r
n
e
y
s
,
r
esear
ch
er
s
u
s
e
p
ed
estrian
m
o
v
em
en
t
m
o
d
elin
g
.
T
h
ey
a
r
e
d
if
f
e
r
en
ti
ated
in
to
two
ca
teg
o
r
ies:
m
icr
o
s
co
p
ic
an
d
m
ac
r
o
s
co
p
ic
m
o
d
els.
Mic
r
o
s
co
p
ic
m
o
d
els,
ev
alu
ate
th
e
b
eh
av
i
o
r
o
f
a
n
in
d
iv
i
d
u
al
p
e
d
estrian
.
I
n
m
a
n
y
s
tu
d
ies
co
n
d
u
cte
d
,
s
u
ch
as
ce
llu
lar
au
to
m
ata
m
o
d
els
C
A,
th
e
m
et
h
o
d
is
b
ased
o
n
th
e
d
is
cr
etiza
tio
n
o
f
s
p
ac
e
in
ce
lls
,
ea
ch
p
e
d
estrian
o
cc
u
p
ies
a
ce
ll
with
a
d
ir
ec
tio
n
o
f
p
r
ef
er
en
ce
[
2
]
.
T
h
e
s
o
cial
f
o
r
ce
m
o
d
el
SF
is
b
ased
o
n
th
e
an
alo
g
y
with
New
to
n
ia
n
p
h
y
s
ics,
wh
er
e
th
e
p
ed
estrian
is
s
u
b
jecte
d
to
attr
ac
tio
n
f
o
r
ce
s
an
d
r
ep
r
ess
io
n
wh
ic
h
ac
t
o
n
its
ac
ce
ler
atio
n
[
3
]
.
I
n
o
th
e
r
s
tu
d
ies,
b
ased
o
n
d
is
cr
ete
ch
o
ice
m
o
d
els,
wh
er
e
r
esear
ch
er
s
m
o
d
el
walk
in
g
alter
n
ativ
es
b
ased
o
n
f
ac
to
r
s
,
s
u
ch
: a
s
s
p
ee
d
,
r
a
d
ial
d
ir
ec
tio
n
,
an
d
th
e
n
u
m
b
e
r
o
f
p
ed
estrian
s
p
r
esen
t
[
4
]
.
On
th
e
o
th
er
h
an
d
,
t
h
e
m
ac
r
o
s
co
p
ic
m
o
d
el
is
id
en
tifie
d
b
y
th
r
ee
p
ar
am
eter
s
: f
lo
w,
s
p
ee
d
,
a
n
d
d
en
s
ity
[
5
]
,
[
6
]
.
Fru
in
'
s
f
ir
s
t
wo
r
k
s
in
th
at
f
ield
an
aly
ze
d
t
h
e
r
elatio
n
s
h
ip
b
etwe
en
m
ac
r
o
s
co
p
ic
v
ar
iab
les
s
u
ch
as
f
lo
w
d
en
s
ity
an
d
v
elo
city
as p
e
d
estrian
ch
ar
ac
ter
is
tics
in
u
r
b
an
ar
ea
s
[
7
]
.
Su
k
h
ad
ia
et
a
l.
[
8
]
h
a
v
e
s
tu
d
ied
th
e
ef
f
ec
t
o
f
ev
en
ts
o
n
p
e
d
estrian
b
eh
av
io
r
an
aly
zi
n
g
p
ed
estrian
f
lo
w,
walk
in
g
s
p
ee
d
,
d
en
s
ity
,
an
d
s
p
ac
e
u
s
in
g
r
eg
r
ess
io
n
an
aly
s
is
.
Als
o
at
s
ig
n
alize
d
in
ter
s
ec
tio
n
s
,
r
esear
ch
er
s
s
tu
d
ied
p
e
d
estrian
b
e
h
av
io
r
b
y
q
u
a
n
tify
in
g
s
o
m
e
attr
ib
u
tes
lik
e
r
o
a
d
a
n
d
cr
o
s
s
walk
wid
th
,
g
en
d
e
r
,
b
id
ir
ec
tio
n
al
f
l
o
w,
cr
o
s
s
in
g
ti
m
e,
also
p
ed
estrian
ch
ar
ac
ter
is
tics
as
m
ale
-
f
em
al
e
-
ch
ild
.
T
h
e
o
b
s
er
v
e
d
d
ata
f
l
o
w
is
p
lo
tted
an
d
th
e
s
ca
tter
ed
d
iag
r
am
s
f
o
llo
w
Gr
ee
n
b
er
g
'
s
lo
g
ar
ith
m
ic
m
o
d
el
[
9
]
.
Als
o
,
Mu
ley
et
a
l.
[
1
0
]
h
av
e
s
tu
d
ie
d
p
ed
estrian
cr
o
s
s
in
g
s
p
ee
d
at
s
ig
n
alize
d
in
ter
s
ec
tio
n
s
u
s
in
g
tr
af
f
ic
an
aly
ze
r
s
o
f
twar
e,
th
e
r
esu
lts
s
h
o
w
a
co
r
r
elatio
n
b
etwe
en
s
p
ee
d
an
d
cr
o
s
s
walk
len
g
th
in
r
ed
a
n
d
g
r
ee
n
in
d
icatio
n
s
b
u
t
p
ed
estr
ian
ex
it
s
p
ee
d
s
wer
e
i
n
d
ep
e
n
d
en
t
o
f
cr
o
s
s
walk
len
g
th
.
A
n
o
th
er
s
tu
d
y
p
er
s
p
ec
tiv
e
is
p
ed
estrian
cr
o
wd
m
o
d
elin
g
s
u
ch
as
a
m
ac
r
o
s
co
p
ic
m
o
d
el,
w
h
er
e
p
ed
estrian
s
ar
e
s
u
b
ject
to
th
e
laws
o
f
g
as
f
lo
w.
I
n
m
a
n
y
s
tu
d
ies,
au
th
o
r
s
attem
p
t
to
d
escr
ib
e
p
ed
estrian
m
o
b
ilit
y
an
d
b
e
h
av
io
r
.
W
in
d
y
an
i
et
a
l.
[
1
1
]
p
r
o
p
o
s
e
th
e
L
ax
-
W
en
d
r
o
f
f
s
ch
em
e
f
o
r
co
n
s
er
v
atio
n
laws,
d
escr
ib
in
g
v
elo
city
-
d
e
n
s
ity
r
elatio
n
u
s
in
g
lin
ea
r
r
e
g
r
ess
io
n
,
th
ey
v
er
i
f
y
th
e
p
e
d
estrian
f
lo
w
co
n
s
er
v
atio
n
ac
co
r
d
in
g
to
t
h
e
two
eq
u
atio
n
s
th
at
d
escr
ib
e
th
e
v
elo
city
as a
f
u
n
ctio
n
o
f
d
en
s
ity
.
I
n
o
t
h
er
s
tu
d
ies,
r
esear
ch
er
s
d
escr
ib
e
f
ast
ex
it
s
ce
n
ar
io
s
in
p
ed
estrian
cr
o
wd
s
,
u
s
in
g
th
e
Hu
g
h
es
m
o
d
el
an
d
m
ea
n
f
ield
g
am
e
with
n
o
n
lin
ea
r
m
o
b
ilit
ies
[
1
2
]
.
I
n
o
u
r
s
tu
d
y
,
we
p
r
o
ce
ed
to
th
e
m
o
d
elin
g
an
d
p
r
e
d
ictio
n
o
f
p
ed
estrian
f
lo
w
i
n
a
c
o
m
m
er
ci
al
av
en
u
e.
I
n
th
e
liter
atu
r
e,
th
er
e
ar
e
3
w
ay
s
o
f
f
o
r
ec
asti
n
g
m
eth
o
d
s
:
s
tatis
tical
m
o
d
els,
m
ac
h
in
e
lear
n
in
g
-
b
ased
m
o
d
els,
an
d
d
ee
p
lear
n
in
g
-
b
ased
m
o
d
els.
Pre
v
io
u
s
s
tu
d
ies
r
ep
o
r
t
ed
in
th
e
liter
atu
r
e
r
ev
iew
p
r
o
p
o
s
e
p
r
ed
ictio
n
alg
o
r
ith
m
s
to
f
o
r
ec
ast p
ed
estri
an
f
lo
w.
Dav
is
et
a
l.
[
1
3
]
d
eter
m
in
e
h
o
w
ca
n
h
o
u
r
ly
f
lo
w
b
e
p
r
e
d
icted
b
ased
o
n
s
h
o
r
t
co
u
n
tin
g
in
ter
v
als
u
s
in
g
lin
ea
r
r
eg
r
ess
io
n
,
wh
er
e
th
e
m
id
d
le
in
ter
v
al
p
o
s
itio
n
ev
en
t
p
r
o
d
u
ce
d
th
e
b
est
m
o
d
el
r
eg
ar
d
less
o
f
th
e
s
ize
o
f
th
e
co
u
n
t
in
ter
v
al.
B
ar
g
eg
o
l
et
a
l.
[
1
4
]
u
s
e
r
eg
r
ess
io
n
an
aly
s
is
to
d
eter
m
in
e
th
e
r
e
latio
n
s
h
ip
b
etwe
en
s
p
ac
e
m
ea
n
s
p
ee
d
,
f
l
o
w
r
ate,
an
d
d
e
n
s
ity
o
f
p
e
d
estrian
s
,
in
ad
d
itio
n
,
th
e
au
th
o
r
s
m
o
d
el
p
ed
estrian
d
en
s
ity
u
s
in
g
g
en
etic
al
g
o
r
ith
m
(
GP)
as
an
o
p
tim
izatio
n
alg
o
r
ith
m
.
I
n
a
n
o
th
e
r
s
tu
d
y
,
Fu
jim
o
t
o
et
a
l.
[
1
5
]
aim
to
in
v
esti
g
ate
th
e
r
elatio
n
s
h
ip
b
e
twee
n
th
e
s
p
atial
c
o
n
d
itio
n
a
n
d
cr
o
wd
walk
n
at
u
r
e
u
s
in
g
r
eg
r
ess
io
n
an
aly
s
is
.
L
ieb
ig
et
a
l.
[
1
6
]
u
s
e
Ga
u
s
s
ian
p
r
o
ce
s
s
r
eg
r
ess
io
n
with
d
if
f
u
s
io
n
k
er
n
el
in
clu
d
in
g
t
o
p
o
lo
g
ical
in
f
o
r
m
atio
n
to
esti
m
ate
p
ed
estrian
m
o
b
ilit
y
v
o
lu
m
e
an
d
h
o
w
tr
ajec
to
r
y
p
att
er
n
s
im
p
r
o
v
e
tr
a
f
f
ic
p
r
ed
ictio
n
ac
cu
r
ac
y
.
Z
h
an
g
et
a
l.
[
1
7
]
an
aly
ze
p
ed
estrian
cr
o
wd
d
en
s
ity
an
d
s
p
ee
d
u
s
in
g
d
ata
f
r
o
m
ce
llu
lar
o
p
er
at
o
r
s
th
r
o
u
g
h
a
h
y
b
r
i
d
m
o
d
el,
th
e
lo
g
d
is
tan
ce
p
ath
lo
s
s
(
L
D
PL
)
,
an
d
th
e
Gau
s
s
ian
p
r
o
ce
s
s
GP
with
s
u
p
er
v
is
ed
lear
n
in
g
f
o
r
m
o
d
elin
g
,
r
eg
r
ess
io
n
,
an
d
p
r
e
d
ictio
n
.
Z
h
ao
et
a
l.
[
1
8
]
u
s
e
an
ar
tific
ial
n
eu
r
al
n
etwo
r
k
to
m
o
d
el
an
d
p
r
ed
ict
p
ed
estrian
u
n
i
d
ir
ec
tio
n
al
an
d
b
id
ir
ec
tio
n
al
f
lo
w,
th
is
m
o
d
el
is
b
ased
o
n
2
s
u
b
m
o
d
els
,
s
em
icir
cu
lar
f
o
r
war
d
s
p
ac
e
-
b
ased
(
SF
SB
)
to
lear
n
m
ag
n
itu
d
e
an
d
r
ec
tan
g
u
lar
f
o
r
war
d
s
p
ac
e
-
b
ased
(
R
FS
B
)
to
lear
n
d
ir
ec
tio
n
v
elo
city
.
T
o
r
d
eu
x
et
a
l.
[
1
9
]
ev
alu
ate
p
ed
estrian
p
r
e
d
ictio
n
f
lo
w
in
co
m
p
lex
g
eo
m
e
tr
ies
(
co
r
r
id
o
r
an
d
b
o
ttlen
ec
k
)
f
ee
d
f
o
r
war
d
n
eu
r
a
l n
etwo
r
k
(
s
in
g
le
h
id
d
e
n
lay
er
H=
3
with
3
n
o
d
es)
co
m
p
ar
ed
with
th
e
W
ield
m
an
m
o
d
el,
w
h
er
e
th
e
f
ir
s
t
s
h
o
ws
th
e
b
est
r
esu
lts
.
C
o
h
e
n
a
n
d
D
aly
o
t
[
2
0
]
d
ev
el
o
p
ed
an
ar
tifi
cial
n
eu
r
al
n
etwo
r
k
m
o
d
el
to
p
r
ed
ict
p
ed
estrian
tr
af
f
ic
f
lo
w
lev
els.
C
o
h
en
a
n
d
Daly
o
t
[
2
1
]
im
p
lem
en
t
6
m
ac
h
in
e
lear
n
i
n
g
alg
o
r
ith
m
s
(
ar
tific
ial
n
eu
r
al
n
etwo
r
k
,
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e,
s
to
ch
asti
c
g
r
ad
ien
t
d
escen
t,
Ad
aBo
o
s
t
,
d
ec
is
io
n
tr
ee
,
an
d
r
a
n
d
o
m
f
o
r
est
)
to
m
o
d
el
th
e
co
r
r
elatio
n
b
etwe
en
th
e
s
p
atial
f
ea
t
u
r
es,
r
o
a
d
n
etwo
r
k
s
tr
u
ctu
r
e,
an
d
p
ed
estrian
tr
af
f
ic
f
lo
w,
s
u
ch
th
at
r
an
d
o
m
f
o
r
est
alg
o
r
ith
m
s
h
o
ws
th
e
b
est
r
esu
lts
.
L
u
ca
et
a
l.
[
2
2
]
i
n
v
esti
g
ate
d
ee
p
lear
n
in
g
alg
o
r
ith
m
s
to
p
r
ed
ict
cr
o
wd
p
ed
estrian
f
lo
w
an
d
co
m
p
ar
e
th
em
with
class
ic
tim
e
-
s
er
ies
m
o
d
els
b
ased
o
n
au
to
r
eg
r
ess
io
n
s
u
c
h
as
au
to
r
e
g
r
ess
iv
e
in
teg
r
ated
m
o
v
in
g
a
v
er
ag
e
(
AR
I
MA
)
.
L
iu
et
a
l.
[
2
3
]
d
ev
elo
p
ed
a
m
o
d
el
to
p
r
e
d
ict
th
e
cr
o
w
d
f
lo
w
i
n
a
walk
in
g
s
tr
ee
t
u
s
in
g
th
e
g
r
ap
h
co
n
v
o
lu
tio
n
al
n
etwo
r
k
(
GC
N
)
m
o
d
el
an
d
co
m
p
ar
ed
GC
N
with
b
aseli
n
e
m
eth
o
d
s
(
h
is
to
r
ical
av
er
a
g
e,
au
t
o
r
eg
r
ess
iv
e
in
teg
r
ated
m
o
v
i
n
g
av
er
a
g
e,
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e,
co
n
v
o
l
u
tio
n
al
n
eu
r
al
n
etwo
r
k
,
lo
n
g
s
h
o
r
t
-
ter
m
m
em
o
r
y
an
d
s
p
atio
-
tem
p
o
r
al
co
n
v
o
lu
ti
o
n
al
n
etwo
r
k
)
to
v
alid
ate
t
h
e
p
er
f
o
r
m
an
ce
o
f
p
ed
estrian
f
lo
w
p
r
ed
ictio
n
.
An
g
el
et
a
l.
[
2
4
]
u
s
e
th
e
d
ec
is
io
n
tr
e
e
r
eg
r
ess
o
r
alg
o
r
ith
m
to
id
en
ti
f
y
th
e
ass
o
ciatio
n
b
etwe
en
walk
way
v
o
lu
m
e
an
d
b
u
ilt en
v
ir
o
n
m
en
t
f
ea
tu
r
es.
T
an
g
ier
city
h
as
ex
p
er
ie
n
ce
d
a
s
p
ec
tacu
lar
leap
in
u
r
b
an
iza
tio
n
an
d
p
o
p
u
latio
n
g
r
o
wth
[
2
5
]
,
an
d
in
th
e
last
d
ec
ad
e
h
as b
ec
o
m
e
th
e
s
ec
o
n
d
ec
o
n
o
m
ic
h
u
b
o
f
Mo
r
o
cc
o
.
So
,
th
is
is
ac
co
m
p
an
ie
d
b
y
in
cr
ea
s
ed
u
r
b
an
m
o
b
ilit
y
,
b
o
t
h
v
eh
icu
la
r
an
d
p
ed
estrian
.
T
h
is
ar
ticle
s
tu
d
ies
b
i
-
d
ir
ec
tio
n
al
p
ed
estrian
f
l
o
w
in
a
co
m
m
er
cial
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
1
4
,
No
.
5
,
Octo
b
e
r
2
0
2
4
:
5
8
4
8
-
5
8
5
7
5850
av
en
u
e
i
n
T
an
g
ier
.
T
h
e
d
im
e
n
s
io
n
s
o
f
th
e
av
en
u
e
ar
e
as
f
o
llo
ws:
th
e
p
ed
estrian
s
id
ewa
lk
wid
th
is
7
m
eter
s
an
d
7
m
ete
r
s
wid
th
f
o
r
ca
r
s
wh
er
e
3
m
eter
s
ar
e
f
o
r
p
ar
k
i
n
g
,
as
illu
s
tr
ated
in
Fig
u
r
e
1
(
a)
,
ac
co
r
d
in
g
to
d
ir
ec
t
o
b
s
er
v
atio
n
s
,
h
ig
h
co
n
g
esti
o
n
at
th
e
p
ed
estrian
lev
el
is
n
o
t
ed
.
Sin
ce
t
h
e
d
im
en
s
io
n
s
o
f
t
h
e
av
e
n
u
e
d
o
n
o
t
ch
an
g
e,
it
is
in
ter
esti
n
g
to
k
n
o
w
h
o
w
th
e
p
ed
estrian
f
l
o
w
will
ev
o
lv
e
in
th
e
f
u
tu
r
e
,
ev
al
u
atin
g
th
e
walk
way
'
s
ab
ilit
y
to
s
u
s
tain
an
ad
eq
u
ate
lev
el
o
f
p
ed
estrian
s
an
d
h
elp
d
ec
is
io
n
-
m
ak
er
s
to
p
r
o
p
o
s
e
o
p
er
atio
n
al
s
o
lu
tio
n
s
.
As
a
s
tu
d
y
m
eth
o
d
o
lo
g
y
,
we
m
o
d
el
an
d
p
r
e
d
ict
b
id
ir
ec
tio
n
al
p
ed
estrian
tr
af
f
ic
f
lo
w.
Fo
r
th
is
p
u
r
p
o
s
e,
we
u
s
e
ar
tific
ial
n
eu
r
al
n
etwo
r
k
(
AN
N)
an
d
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
i
n
e
(
SVM)
m
ac
h
in
e
lea
r
n
in
g
m
o
d
els,
m
ak
i
n
g
a
co
m
p
ar
is
o
n
b
etwe
en
th
e
two
alg
o
r
ith
m
s
th
at
b
est
p
r
ed
ict
th
e
f
lo
w.
As
a
r
esu
lt,
ANN
g
iv
es
a
litt
le
b
etter
p
er
f
o
r
m
an
ce
an
d
f
itn
ess
co
m
p
ar
ed
to
th
e
s
u
p
p
o
r
t
v
ec
to
r
r
eg
r
ess
io
n
(
SVR
)
alg
o
r
ith
m
.
T
h
is
wo
r
k
wo
u
ld
b
e
t
h
e
f
ir
s
t
attem
p
t
to
s
tu
d
y
p
ed
estri
an
f
lo
w
in
T
an
g
ier
city
b
y
ap
p
ly
in
g
m
ac
h
in
e
lear
n
i
n
g
alg
o
r
ith
m
s
(
n
o
s
tu
d
y
h
as
b
ee
n
estab
lis
h
ed
s
o
f
ar
i
n
th
at
s
en
s
e)
.
T
h
e
wo
r
k
will
b
e
d
i
v
id
ed
as
f
o
llo
ws:
an
in
tr
o
d
u
ctio
n
p
r
e
s
en
tin
g
th
e
r
esear
c
h
o
b
jectiv
e,
s
tu
d
ies
ca
r
r
ied
o
u
t
in
th
is
s
en
s
e,
li
m
itatio
n
s
,
an
d
o
u
r
c
o
n
tr
ib
u
tio
n
.
T
h
en
a
s
ec
o
n
d
s
ec
tio
n
e
x
p
lain
s
th
e
m
eth
o
d
f
o
llo
wed
,
th
is
s
ec
tio
n
in
tu
r
n
d
iv
id
e
d
in
t
o
2
s
ec
tio
n
s
,
t
h
e
d
ata
c
o
llectio
n
p
r
o
ce
d
u
r
e
a
n
d
d
ata
p
r
o
ce
s
s
in
g
th
r
o
u
g
h
ar
tific
ial
n
eu
r
al
n
etw
o
r
k
a
n
d
s
u
p
p
o
r
t
v
ec
t
o
r
r
eg
r
es
s
io
n
.
A
th
ir
d
s
ec
tio
n
p
r
esen
ts
th
e
r
esu
lts
o
b
tain
e
d
,
co
m
p
ar
in
g
th
e
two
alg
o
r
it
h
m
s
th
r
o
u
g
h
r
o
o
t
m
ea
n
s
q
u
ar
ed
er
r
o
r
(
R
MSE
)
an
d
2
(
d
eter
m
in
a
tio
n
co
ef
f
icien
t)
,
an
d
f
in
ally
a
co
n
clu
s
io
n
.
2.
M
E
T
H
O
D
T
h
is
ar
ticle
aim
s
to
m
o
d
el
an
d
p
r
e
d
ict
p
ed
estrian
tr
a
f
f
ic
f
l
o
w
o
n
s
id
ewa
lk
s
in
c
o
m
m
er
c
ial
av
en
u
e,
co
n
s
id
er
in
g
d
ata
co
llected
in
T
an
g
ier
city
(
Mo
r
o
cc
o
)
.
T
h
e
s
tep
s
f
o
llo
wed
f
o
r
th
is
ar
e
d
etailed
in
th
e
f
o
llo
win
g
s
ec
tio
n
s
.
T
h
ese
s
tag
es c
an
b
e
s
u
m
m
ar
ized
in
two
ess
en
tial p
o
in
ts
.
-
Data
co
llectio
n
:
Ped
estrian
f
lo
w
an
d
av
en
u
e
g
e
o
m
etr
y
.
-
Mo
d
el
an
d
p
ed
estrian
f
l
o
w
p
r
ed
ictio
n
:
Data
an
aly
s
is
ap
p
ly
in
g
ANN
an
d
SVR
.
C
o
m
p
ar
in
g
ANN
an
d
SV
R
r
esu
lts
u
s
in
g
r
o
o
t m
ea
n
s
q
u
ar
e
d
er
r
o
r
(
R
MSE
)
an
d
2
(
d
eter
m
in
atio
n
co
ef
f
icien
t
)
.
2
.
1
.
Da
t
a
co
llect
io
n
2
.
1
.
1
.
Study
a
re
a
s
elec
t
io
n
I
n
th
is
s
tu
d
y
,
we
ch
o
s
e
a
co
m
m
er
cial
av
en
u
e
in
T
an
g
ier
city
to
an
aly
ze
th
e
p
ed
estrian
f
lo
w.
T
h
e
p
r
in
cip
al
cr
iter
io
n
f
o
r
s
ite
s
elec
tio
n
was
lan
d
u
s
e
(
co
m
m
er
cial
an
d
en
ter
tain
m
e
n
t)
,
an
aly
zin
g
a
m
ix
e
d
p
o
p
u
latio
n
o
f
em
p
l
o
y
ee
s
,
s
h
o
p
p
er
s
,
an
d
v
is
ito
r
s
.
T
h
e
s
tu
d
y
ar
ea
(
Me
x
iq
u
e
a
v
en
u
e
)
,
as
d
ep
icted
in
Fig
u
r
e
1
(
a)
,
is
lo
ca
te
d
in
t
h
e
ce
n
te
r
o
f
th
e
city
.
W
ith
m
o
r
e
th
an
8
5
s
to
r
es
an
d
1
4
s
h
o
p
p
in
g
ce
n
ter
s
,
it
is
a
ca
tch
m
en
t
ar
ea
with
h
ig
h
p
ed
estrian
m
o
v
em
en
t.
As
s
h
o
wn
in
Fig
u
r
e
1
(
a)
,
th
e
s
id
ewa
lk
wid
th
is
7
m
eter
s
,
b
u
t
th
e
ef
f
ec
tiv
e
wid
th
h
as
an
av
er
a
g
e
o
f
3
m
ete
r
s
.
Als
o
,
th
e
p
r
esen
ce
o
f
v
e
h
icles,
m
ak
es
p
ed
estrian
m
o
b
ilit
y
d
if
f
icu
lt.
2
.
1
.
2
.
P
ro
ce
du
re
o
f
da
t
a
co
ll
ec
t
io
n
Data
co
llectio
n
m
u
s
t
f
o
llo
w
a
well
-
s
tr
u
ctu
r
ed
m
eth
o
d
o
lo
g
y
to
av
o
id
r
ep
ea
tin
g
f
iel
d
wo
r
k
.
First,
we
u
s
e
a
m
ap
t
o
lo
ca
te
t
h
e
ar
e
a
to
b
e
s
tu
d
ied
(
u
s
in
g
Op
en
Str
ee
tMa
p
)
,
th
en
we
p
r
o
ce
ed
t
o
m
o
d
el
th
e
ar
ea
with
a
g
r
ap
h
,
id
en
tifie
d
b
y
n
o
d
es
(
in
ter
s
ec
tio
n
o
f
av
e
n
u
es
in
th
i
s
ca
s
e
O,
H,
I
,
an
d
J
)
an
d
s
eg
m
en
ts
(
av
en
u
es,
in
th
is
ca
s
e,
OH,
HI
,
I
J
)
,
as
d
e
p
icted
in
Fig
u
r
e
1
(
b
)
,
an
d
f
i
n
ally
,
Fig
u
r
e
1
(
c)
d
escr
ib
es
th
e
lo
ca
tio
n
o
f
th
e
av
en
u
e
o
n
th
e
m
a
p
o
f
T
an
g
ier
city
.
T
h
e
d
ata
co
llectio
n
r
ef
er
s
to
th
e
b
id
ir
ec
tio
n
al
p
ed
estrian
f
lo
w/m
in
u
s
in
g
v
id
eo
r
ec
o
r
d
i
n
g
,
d
u
r
in
g
a
we
ek
d
iv
id
ed
in
t
o
7
in
ter
v
als/
d
ay
an
d
m
ak
i
n
g
1
5
m
ea
s
u
r
em
e
n
ts
/s
ec
tio
n
/in
ter
v
al,
th
e
tim
e
in
ter
v
als
ar
e:
7
h
4
5
-
8
h
1
5
,
9
h
4
5
-
1
0
h
1
5
,
1
1
h
4
5
-
1
2
h
1
5
,
1
3
h
4
5
-
1
4
h
1
5
,
1
5
h
4
5
-
1
6
h
1
5
,
1
7
h
4
5
-
1
8
h
4
5
,
1
9
h
4
5
-
2
0
h
1
5
.
Fo
r
ea
ch
s
eg
m
en
t,
7
3
5
m
ea
s
u
r
em
en
ts
ar
e
o
b
tain
ed
f
o
r
ea
ch
wee
k
/m
o
n
th
an
d
d
u
r
in
g
tw
o
m
o
n
th
s
(
J
u
n
e
a
n
d
No
v
em
b
er
,
to
tak
e
in
to
ac
c
o
u
n
t th
e
wea
th
er
,
ac
co
r
d
in
g
to
th
e
m
o
n
th
)
.
2
.
2
.
Da
t
a
a
na
l
y
s
is
Ped
estrian
n
etwo
r
k
tr
af
f
ic
d
ata
ar
e
n
o
n
lin
ea
r
;
th
er
ef
o
r
e,
m
ac
h
in
e
lear
n
in
g
(
ML
)
alg
o
r
ith
m
s
(
s
u
p
er
v
is
ed
lear
n
in
g
,
u
n
s
u
p
er
v
is
ed
lear
n
in
g
,
an
d
r
ein
f
o
r
ce
m
en
t
lear
n
in
g
)
ar
e
v
er
y
ap
p
r
o
p
r
iate
f
o
r
m
ak
in
g
p
r
ed
ictio
n
s
an
d
id
en
tif
y
in
g
p
atter
n
s
au
to
m
atica
lly
.
ML
is
a
s
u
b
ca
teg
o
r
y
o
f
ar
tific
ial
in
t
ellig
en
ce
in
wh
ich
co
m
p
u
ter
s
im
itate
h
u
m
a
n
lear
n
in
g
,
th
r
o
u
g
h
th
e
ex
tr
ac
tio
n
o
f
k
n
o
wled
g
e
ab
o
u
t
u
n
o
b
s
er
v
e
d
p
r
o
p
er
ties
o
f
a
n
o
b
ject
b
ased
o
n
th
e
p
r
o
p
er
ties
th
at
h
av
e
b
ee
n
o
b
s
er
v
e
d
.
E
n
c
o
m
p
ass
es
m
an
y
ty
p
es
o
f
p
r
o
b
l
em
s
,
class
if
icatio
n
,
r
an
k
in
g
,
an
d
r
e
g
r
ess
io
n
.
So
m
e
o
f
th
e
b
est
-
k
n
o
wn
ML
a
lg
o
r
ith
m
s
ar
e
d
ec
is
io
n
tr
ee
,
B
ay
esian
n
etwo
r
k
s
,
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e,
an
d
ar
tific
ial
n
eu
r
al
n
etwo
r
k
.
in
th
is
ar
ticle,
we
u
s
e
n
eu
r
al
n
etwo
r
k
s
an
d
SVR
,
an
d
th
eir
p
r
o
v
en
ef
f
ec
tiv
en
ess
in
f
o
r
ec
asti
n
g
task
s
[
2
6
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
P
ed
estr
ia
n
flo
w
p
r
ed
ictio
n
in
co
mme
r
cia
l a
ve
n
u
e
(
Ma
r
w
a
n
e
B
en
h
a
d
o
u
)
5851
(a
)
(b
)
(c
)
Fig
u
r
e
1
.
Stu
d
y
ar
ea
,
(
a)
o
v
er
v
iew
o
f
th
e
av
e
n
u
e,
(
b
)
a
v
en
u
e
m
o
d
el,
an
d
(
c)
av
en
u
e
lo
ca
tio
n
2
.
2
.
1
.
Su
pp
o
rt
v
ec
t
o
r
m
a
chi
ne
Su
p
p
o
r
t
v
ec
to
r
m
ac
h
in
es
(
SV
M)
ar
e
a
s
et
o
f
s
u
p
e
r
v
is
ed
le
ar
n
in
g
al
g
o
r
ith
m
s
d
ev
elo
p
e
d
b
y
Vap
n
i
k
an
d
C
o
r
tes
in
1
9
9
5
[
2
7
]
.
T
h
e
ir
g
o
o
d
p
er
f
o
r
m
an
ce
led
t
o
th
eir
u
s
e
to
s
o
lv
e
a
lar
g
e
v
ar
iet
y
o
f
class
if
icatio
n
(
SVM)
an
d
r
eg
r
ess
io
n
(
SVR
)
p
r
o
b
lem
s
f
o
r
lin
ea
r
a
n
d
n
o
n
-
li
n
ea
r
d
ata
(
we
ca
n
tr
a
n
s
f
o
r
m
t
o
lin
ea
r
d
ata
u
s
in
g
k
er
n
el
f
u
n
ctio
n
)
.
T
h
e
SVR
alg
o
r
ith
m
is
b
ased
o
n
f
in
d
i
n
g
t
h
e
h
y
p
e
r
p
lan
e
th
at
m
o
d
els
th
e
tr
en
d
o
f
th
e
tr
ain
in
g
d
ata
an
d
b
ased
o
n
it
p
r
ed
ictin
g
an
y
d
ata
in
t
h
e
f
u
tu
r
e,
th
e
m
ain
id
ea
is
alwa
y
s
th
e
s
am
e:
m
in
im
ize
th
e
er
r
o
r
.
B
ased
o
n
a
s
et
o
f
tr
ain
in
g
s
am
p
le
{
,
}
with
=
1
,
…
,
th
e
r
e
g
r
ess
io
n
f
u
n
ctio
n
th
at
ca
n
ap
p
r
o
x
im
ate
t
h
e
o
u
tp
u
t e
x
p
r
ess
ed
b
y
(
1
)
.
=
+
(
1
)
T
h
e
co
ef
f
icien
ts
,
v
ec
t
o
r
an
d
b
ias
,
esti
m
ated
b
y
r
eso
lv
in
g
a
q
u
a
d
r
atic
p
r
o
g
r
am
m
in
g
p
r
o
b
lem
,
th
e
o
b
jectiv
e
f
u
n
ctio
n
ex
p
lain
ed
b
y
(
2
)
u
n
d
e
r
th
e
two
c
o
n
d
itio
n
s
,
ex
p
r
ess
ed
th
r
o
u
g
h
(
3
)
an
d
(
4
)
:
1
2
‖
‖
2
+
.
∑
|
−
|
=
1
(
2
)
S
u
b
ject
to
:
−
≤
+
≥
0
(
3
)
−
≤
+
∗
∗
≥
0
(
4
)
wh
er
e
|
−
|
th
e
-
in
s
en
s
itiv
e
lo
s
s
f
u
n
ctio
n
(
tr
ain
i
n
g
er
r
o
r
)
.
T
h
e
co
n
s
tan
t
d
eter
m
in
e
th
e
tr
ad
eo
f
f
b
etwe
en
th
e
tr
ain
in
g
er
r
o
r
a
n
d
th
e
p
en
alizin
g
ter
m
‖
‖
2
.
T
h
e
is
th
e
esti
m
ato
r
o
u
tp
u
t
p
r
o
d
u
ce
d
in
r
esp
o
n
s
e
to
th
e
in
p
u
t
ex
am
p
le
.
T
h
e
p
ar
am
eter
r
ep
r
esen
t
th
e
h
y
p
er
p
lan
e
m
ar
g
e.
T
h
e
p
r
am
eter
s
an
d
∗
s
lac
k
v
ar
iab
les th
at
d
escr
ib
es th
e
lo
s
s
f
u
n
ctio
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
1
4
,
No
.
5
,
Octo
b
e
r
2
0
2
4
:
5
8
4
8
-
5
8
5
7
5852
T
o
s
o
lv
e
th
is
o
p
tim
izatio
n
p
r
o
b
lem
,
we
co
n
s
tr
u
ct
a
L
ag
r
a
n
g
i
an
f
u
n
ctio
n
(
)
,
(
5
)
:
M
in
imize
(
,
,
∗
,
,
∗
,
,
∗
)
=
1
2
‖
‖
2
+
.
∑
(
+
=
1
∗
)
−
∑
(
+
=
1
∗
∗
)
−
∑
(
+
=
1
−
+
+
)
−
∑
∗
(
=
1
−
−
+
+
∗
)
(
5
)
,
∗
,
,
∗
is
L
ag
r
an
g
e
m
u
ltip
lier
s
.
C
ar
r
y
in
g
o
u
t th
is
o
p
tim
izatio
n
,
we
o
b
tain
(
6
)
,
(
7
)
,
a
n
d
(
8
)
.
̂
=
∑
(
−
∗
)
=
1
(
6
)
+
=
(
7
)
∗
+
=
(
8
)
All
th
e
co
n
s
tr
ain
ts
th
at
ar
e
n
o
t
s
atis
f
ied
as
eq
u
alities
,
th
e
co
r
r
esp
o
n
d
in
g
v
a
r
iab
les
o
f
th
e
d
u
al
p
r
o
b
lem
,
ex
p
r
ess
ed
b
y
t
h
e
o
b
jectiv
e
f
u
n
ctio
n
d
escr
ib
ed
b
y
(
9
)
,
s
u
b
ject
to
(
10
)
.
Ma
x
im
ize
∑
(
−
∗
)
=
1
−
∑
(
−
∗
)
=
1
−
∑
(
−
∗
)
(
−
∗
)
(
,
)
,
=
1
(
9
)
Su
b
ject
to
:
∑
(
−
∗
)
=
0
=
1
0
≤
,
∗
≤
(
1
0
)
Fin
ally
,
th
e
n
o
n
lin
ea
r
f
u
n
ctio
n
,
(
11
)
is
o
b
tain
ed
as:
=
∑
(
−
∗
)
(
,
)
+
=
1
(
1
1
)
w
h
e
r
e
(
,
)
is
d
ef
in
e
d
as
th
e
k
e
r
n
el
f
u
n
ctio
n
.
An
y
f
u
n
cti
o
n
t
h
at
s
a
tis
f
ies
Me
r
ce
r
’
s
th
eo
r
em
ca
n
b
e
u
s
ed
as
th
e
k
er
n
el
f
u
n
ctio
n
(
s
ig
m
o
id
al
,
lin
ea
r
,
r
ad
ial
b
asis
)
[
2
8
]
.
I
n
t
h
is
r
esear
ch
,
th
e
p
ar
am
eter
s
u
s
ed
to
s
h
o
w
th
e
b
est
r
esu
lts
ar
e:
r
ad
ial
b
asis
k
er
n
el
f
u
n
ctio
n
,
=
1
0
0
,
=
0
an
d
=
0
(
R
B
F
p
ar
am
eter
)
.
Gau
s
s
ian
r
ad
ial
b
asis
f
u
n
ctio
n
,
d
etailed
in
(
13
)
:
(
,
)
=
e
xp
(
−
‖
−
‖
2
2
2
)
(
1
2
)
2
.
2
.
2
.
Art
if
icia
l neura
l net
wo
rk
An
ar
tific
ial
n
eu
r
al
n
etwo
r
k
(
ANN)
is
a
m
ath
em
atica
l
m
o
d
el
th
at
attem
p
ts
to
im
i
tate
th
e
f
u
n
ctio
n
in
g
o
f
th
e
h
u
m
an
b
r
ain
,
as
s
h
o
wn
in
Fig
u
r
e
2
.
Acc
o
r
d
in
g
to
t
h
e
n
etwo
r
k
to
p
o
lo
g
y
,
we
ca
n
d
if
f
er
en
tiate
b
etwe
en
f
ee
d
f
o
r
war
d
,
b
ac
k
f
o
r
war
d
,
an
d
r
ec
u
r
r
en
t.
Neu
r
al
n
et
wo
r
k
s
o
r
p
er
ce
p
tr
o
n
(
s
u
p
er
v
is
ed
lear
n
in
g
wit
h
m
u
ltil
ay
er
p
er
ce
p
tr
o
n
(
MLP
)
)
,
as
r
ep
r
esen
ted
in
Fig
u
r
e
1
,
ar
e
th
e
m
o
s
t
u
s
ed
,
ex
te
n
d
in
g
th
eir
ap
p
licatio
n
to
alm
o
s
t
all
tech
n
ical
ar
ea
s
.
T
h
e
m
ain
elem
en
ts
ar
e
n
etwo
r
k
s
tr
u
ctu
r
e,
ac
tiv
atio
n
f
u
n
ctio
n
s
(
Sig
m
o
id
,
Gau
s
s
ian
,
L
in
ea
r
,
.
.
.
)
,
an
d
lear
n
in
g
alg
o
r
ith
m
(
co
n
s
is
ts
o
f
all
n
etwo
r
k
p
ar
am
eter
s
ad
ju
s
tm
en
t)
[
2
9
]
.
L
ea
r
n
in
g
is
an
iter
ativ
e
p
r
o
c
ess
s
tar
tin
g
f
r
o
m
a
s
et
o
f
r
a
n
d
o
m
weig
h
ts
,
lear
n
in
g
s
ee
k
s
a
s
et
o
f
weig
h
ts
th
at
allo
ws
th
e
ANN
to
d
ev
elo
p
a
s
p
ec
if
ic
task
(
f
o
r
war
d
p
r
o
p
ag
atio
n
)
.
ML
P
n
e
two
r
k
s
u
s
e
an
er
r
o
r
f
u
n
ctio
n
th
at
m
ea
s
u
r
es
t
h
eir
cu
r
r
e
n
t
p
er
f
o
r
m
a
n
ce
,
b
ased
o
n
t
h
eir
weig
h
ts
(
er
r
o
r
esti
m
atio
n
)
.
L
ea
r
n
in
g
b
ec
o
m
es
a
p
r
o
ce
s
s
o
f
s
ea
r
ch
in
g
f
o
r
th
o
s
e
weig
h
ts
th
at
m
ak
e
s
aid
f
u
n
ctio
n
m
in
im
al
(
b
a
ck
war
d
p
r
o
p
ag
atio
n
,
u
s
in
g
g
r
ad
ie
n
t
d
escen
t,
b
ac
k
p
r
o
p
a
g
atio
n
,
q
u
asi
-
New
to
n
,
L
ev
en
b
er
g
-
Ma
r
q
u
ar
d
t)
.
T
h
ese
tr
ain
in
g
p
r
o
ce
s
s
es
will
b
e
r
ep
ea
ted
a
ce
r
tain
n
u
m
b
er
o
f
tim
es
(
E
p
o
c
h
s
)
,
to
a
d
ju
s
t
th
e
v
al
u
e
o
f
th
e
d
if
f
er
e
n
t
p
ar
am
ete
r
s
o
f
o
u
r
n
etwo
r
k
[
3
0
]
.
W
e
ca
n
s
u
m
m
ar
ize
th
e
alg
o
r
ith
m
in
th
e
f
o
llo
w
in
g
s
tep
s
,
test
in
g
an
d
tr
ain
i
n
g
.
a.
Fo
r
war
d
p
r
o
p
ag
atio
n
,
m
o
d
el
r
esu
lt (
o
u
tp
u
t
)
,
ex
p
r
ess
ed
b
y
(
12
)
:
=
0
+
∑
.
(
0
+
∑
.
−
=
1
)
=
1
(
1
2
)
wh
er
e
:
weig
h
ts
,
(
)
:
ac
tiv
atio
n
f
u
n
ctio
n
,
o
u
tp
u
t
,
−
:
in
p
u
ts
.
b.
E
r
r
o
r
esti
m
atio
n
,
e
x
p
r
ess
ed
in
(
13
)
:
=
1
.
∑
(
−
(
0
+
∑
.
(
0
+
∑
.
−
=
1
)
=
1
)
)
2
=
1
(
1
3
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
P
ed
estr
ia
n
flo
w
p
r
ed
ictio
n
in
co
mme
r
cia
l a
ve
n
u
e
(
Ma
r
w
a
n
e
B
en
h
a
d
o
u
)
5853
wh
er
e
is
co
s
t f
u
n
ctio
n
.
c.
B
ac
k
war
d
p
r
o
p
ag
atio
n
,
u
p
d
atin
g
weig
h
ts
to
m
in
im
ize
t
h
e
er
r
o
r
f
u
n
ctio
n
(
c
o
s
t)
,
as e
x
p
r
ess
e
d
in
(
14
)
:
(
+
1
)
=
(
)
−
.
∆
(
)
(
1
4
)
wh
er
e
is
lear
n
in
g
r
ate
an
d
∆
(
)
is
g
r
ad
ien
t o
f
co
s
t f
u
n
ctio
n
.
Fo
r
o
u
r
ANN
m
o
d
el,
o
n
e
f
ee
d
f
o
r
war
d
,
t
h
e
n
u
m
b
e
r
o
f
h
id
d
en
lay
er
s
is
o
n
e,
with
1
0
n
e
u
r
o
n
s
an
d
th
e
n
u
m
b
er
o
f
ep
o
ch
s
is
f
ix
ed
o
n
1
,
0
0
0
,
a
n
d
th
e
n
etwo
r
k
is
tr
ain
ed
with
th
e
L
ev
en
b
er
g
–
Ma
r
q
u
a
r
d
t
alg
o
r
ith
m
to
m
in
im
ize
f
u
n
ctio
n
s
an
d
allo
w
f
ast co
n
v
e
r
g
en
ce
.
Fig
u
r
e
2
.
Ar
c
h
itectu
r
e
n
e
u
r
al
n
etwo
r
k
m
o
d
el
2
.
2
.
3
.
Da
t
a
des
cr
iptio
n a
nd
t
re
a
t
m
ent
T
h
e
in
p
u
t d
ata
o
f
ea
c
h
s
eg
m
e
n
t
is
a
m
atr
ix
o
f
th
e
m
o
n
t
h
,
d
a
y
,
tim
e,
an
d
th
e
n
u
m
b
er
o
f
p
e
d
estrian
s
in
th
e
p
r
ev
i
o
u
s
s
eg
m
en
t.
T
h
e
o
u
tp
u
t
v
ec
to
r
is
a
v
ec
t
o
r
o
f
th
e
p
ed
estrian
’
s
f
l
o
w
f
o
r
a
g
iv
e
n
m
o
n
th
–
d
a
y
an
d
tim
e.
T
h
e
v
ar
iab
les
a
r
e
e
n
co
d
ed
as
f
o
llo
ws:
o
u
r
in
p
u
t
d
ata
i
s
a
m
atr
ix
o
f
m
o
n
th
,
d
ay
,
an
d
tim
e.
E
ac
h
elem
en
t
o
f
th
is
m
atr
ix
is
ex
p
r
ess
ed
as:
-
F
o
r
t
h
e
m
o
n
t
h
w
e
c
o
n
s
i
d
e
r
t
h
e
v
a
l
u
e
s
o
f
1
,
2
,
…
,
1
2
t
o
i
d
e
n
t
i
f
y
t
h
e
m
o
n
t
h
s
,
J
a
n
u
a
r
y
,
Fe
b
r
u
a
r
y
,
…
D
e
c
e
m
b
e
r
-
Fo
r
th
e
d
ay
we
u
s
ed
th
e
n
u
m
b
er
s
1
,
2
,
…,
7
to
id
e
n
tify
Mo
n
d
ay
….
,
Su
n
d
ay
-
Fo
r
h
o
u
r
s
,
we
ca
n
ex
p
r
ess
th
r
o
u
g
h
(
15
)
:
=
ℎ
+
60
24
(
1
5
)
Fo
r
ea
ch
s
eg
m
en
t,
7
3
5
m
ea
s
u
r
em
en
ts
ar
e
o
b
tain
ed
ea
ch
wee
k
/m
o
n
th
an
d
d
u
r
in
g
two
m
o
n
th
s
(
J
u
n
e
a
n
d
No
v
em
b
er
)
.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
I
n
o
u
r
s
im
u
latio
n
s
,
8
0
%
o
f
th
e
d
ata
was
u
s
ed
as
in
p
u
t
to
S
VR
an
d
ANN
m
o
d
els
(
tr
ain
in
g
d
ata)
an
d
th
e
r
em
ain
in
g
2
0
%
is
in
ten
d
ed
to
test
th
e
m
o
d
el
(
test
in
g
d
ata)
.
I
n
Fig
u
r
es
3
,
4,
an
d
5
we
ex
h
ib
it
th
e
s
im
u
latio
n
r
esu
lts
o
f
p
ed
estrian
’
s
f
lo
w,
r
ea
l
d
ata,
an
d
p
r
e
d
ic
tio
n
o
f
ev
e
r
y
s
eg
m
en
t
in
Me
x
iq
u
e
Av
en
u
e
,
OH,
HI
,
I
J
,
u
s
in
g
SVR
an
d
ANN
m
eth
o
d
s
f
o
r
two
m
o
n
th
s
J
u
n
e
an
d
No
v
em
b
e
r
.
Fig
u
r
e
3
s
h
o
ws
th
e
s
im
u
latio
n
r
esu
lt
(
co
m
p
ar
is
o
n
b
etwe
en
th
e
r
ea
l
r
esu
lt
o
f
p
ed
estrian
f
lo
w,
ANN
m
o
d
el,
a
n
d
SVR
m
o
d
el)
o
f
th
e
OH
s
eg
m
en
t,
wh
er
e
Fig
u
r
e
3
(
a)
s
h
o
ws
th
e
r
esu
lt
f
o
r
J
u
n
e,
wh
i
le
Fig
u
r
e
3
(
b
)
s
h
o
ws
th
e
s
im
u
latio
n
r
esu
lts
f
o
r
No
v
em
b
er
.
Fig
u
r
e
4
s
h
o
ws
th
e
HI
s
eg
m
e
n
t'
s
s
im
u
latio
n
r
esu
lt
(
c
o
m
p
ar
is
o
n
b
etwe
en
th
e
r
ea
l
r
esu
lt
o
f
p
ed
estrian
f
lo
w,
ANN
m
o
d
el
,
an
d
SVR
m
o
d
el)
.
Fig
u
r
e
4
(
a)
s
h
o
ws
th
e
r
esu
lt
f
o
r
J
u
n
e,
wh
ile
Fig
u
r
e
4
(
b
)
s
h
o
ws
th
e
s
im
u
latio
n
r
esu
lts
f
o
r
No
v
em
b
er
.
I
t
ca
n
b
e
s
ee
n
in
th
e
r
esu
lts
th
at
th
e
t
wo
al
g
o
r
ith
m
s
ANN
an
d
SVR
ad
eq
u
ately
s
im
u
late
th
e
r
ea
l p
ed
estrian
f
lo
w.
Fig
u
r
e
5
s
h
o
ws
th
e
I
J
s
eg
m
en
t's
s
im
u
latio
n
r
esu
lt
(
c
o
m
p
ar
is
o
n
b
etwe
en
th
e
r
ea
l
r
esu
lt
o
f
p
ed
estrian
f
lo
w,
ANN
m
o
d
el,
a
n
d
SVR
m
o
d
el)
.
Fig
u
r
e
5
(
a)
s
h
o
ws
th
e
r
esu
lt
f
o
r
J
u
n
e,
w
h
ile
Fig
u
r
e
5
(
b
)
s
h
o
ws
th
e
s
im
u
latio
n
r
esu
lts
f
o
r
No
v
em
b
er
.
I
t
is
o
b
s
er
v
ed
th
at
th
e
tw
o
alg
o
r
ith
m
s
ANN
an
d
SVR
ad
eq
u
ately
s
im
u
late
th
e
r
ea
l p
ed
estrian
f
lo
w.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
1
4
,
No
.
5
,
Octo
b
e
r
2
0
2
4
:
5
8
4
8
-
5
8
5
7
5854
Ju
n
e
N
o
ve
mb
e
r
(
a
)
(
b
)
Fig
u
r
e
3
.
Simu
latio
n
r
esu
lts
f
o
r
OH
s
eg
m
en
t,
(
a)
J
u
n
e
an
d
(
b
)
No
v
em
b
e
r
Ju
n
e
N
o
ve
mb
e
r
(
a
)
(
b
)
Fig
u
r
e
4
.
Simu
latio
n
r
esu
lts
f
o
r
HI
s
eg
m
en
t,
(
a
)
J
u
n
e
a
n
d
(
b
)
No
v
em
b
er
Ju
n
e
N
o
ve
mb
e
r
(
a
)
(
b
)
Fig
u
r
e
5
.
Simu
latio
n
r
esu
lts
f
o
r
I
J
s
eg
m
en
t,
(
a)
J
u
n
e
an
d
(
b
)
No
v
em
b
er
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
P
ed
estr
ia
n
flo
w
p
r
ed
ictio
n
in
co
mme
r
cia
l a
ve
n
u
e
(
Ma
r
w
a
n
e
B
en
h
a
d
o
u
)
5855
T
wo
p
er
f
o
r
m
a
n
ce
cr
iter
ia
wer
e
u
s
ed
to
ev
alu
ate
th
e
p
r
ed
icti
o
n
ab
ilit
y
o
f
th
e
SV
R
an
d
ANN
m
o
d
el,
as
s
h
o
wn
in
T
ab
les
1
an
d
2
,
in
clu
d
in
g
d
ete
r
m
in
atio
n
co
e
f
f
i
cien
t
2
an
d
R
MSE
,
ex
p
lain
ed
b
y
(
16
)
an
d
(
17
)
r
esp
ec
tiv
ely
.
W
e
u
s
e
th
ese
two
m
etr
ics to
ass
ess
p
r
ed
ictio
n
r
esu
lts
an
d
th
e
s
im
u
latio
n
'
s
ef
f
ec
tiv
en
ess
.
2
=
∑
(
̂
−
̅
)
2
=
1
∑
(
−
̅
)
2
=
1
(
1
6
)
=
√
1
∑
(
̂
−
)
2
=
1
(
1
7
)
T
h
e
R
MSE
i
s
co
n
s
id
er
ed
an
ex
ce
llen
t
er
r
o
r
m
etr
ic
an
d
r
ep
r
esen
ts
th
e
s
am
p
le
s
tan
d
ar
d
d
ev
iatio
n
o
f
th
e
d
if
f
er
en
ce
s
b
etwe
en
p
r
ed
icted
v
alu
es
an
d
o
b
s
er
v
ed
v
alu
es
o
f
p
ed
estrian
f
lo
w.
T
h
e
d
eter
m
in
atio
n
co
ef
f
icie
n
t
2
r
ep
r
esen
ts
h
o
w
well
th
e
f
o
r
ec
asti
n
g
m
o
d
el
ex
p
lain
s
th
e
co
llected
d
ata
(
s
h
o
ws
th
e
g
o
o
d
n
ess
o
f
f
it
f
o
r
r
eg
r
ess
io
n
m
o
d
els),
wh
er
e
̂
,
,
an
d
̅
d
en
o
tes
th
e
esti
m
ated
,
o
b
s
er
v
ed
a
n
d
th
e
av
er
a
g
e
o
f
v
alu
es
r
esp
ec
tiv
ely
.
N
r
ep
r
esen
ts
th
e
n
u
m
b
er
o
f
s
am
p
les f
o
r
p
r
ed
ict
io
n
.
T
ab
le
1
.
R
MSE
v
alu
es f
o
r
SVR
an
d
ANN
alg
o
r
ith
m
s
f
o
r
ev
e
r
y
s
eg
m
e
n
t o
f
Me
x
i
q
u
e
av
en
u
e
OH
HI
IJ
R
M
S
E
-
S
V
R
2
.
59
3
.
24
3
.
24
R
M
S
E
-
ANN
2
.
49
3
.
03
3
.
29
T
ab
le
2
.
2
v
alu
es f
o
r
SVR
an
d
ANN
alg
o
r
ith
m
s
f
o
r
ev
er
y
s
eg
m
e
n
t o
f
Me
x
iq
u
e
a
v
en
u
e
OH
HI
IJ
2
-
S
V
R
0
.
70
0
.
71
0
.
61
2
-
ANN
0
.
71
0
.
74
0
.
60
Acc
o
r
d
in
g
to
T
ab
les
1
an
d
2
,
th
e
a
v
er
ag
e
v
alu
e
o
f
ea
ch
p
er
f
o
r
m
an
ce
cr
iter
io
n
s
h
o
ws
it
ca
n
b
e
o
b
s
er
v
ed
f
r
o
m
t
h
e
esti
m
ated
2
an
d
R
MSE
v
alu
es,
th
at
b
o
th
SVR
an
d
ANN
c
o
u
ld
b
e
u
s
ed
to
m
o
d
el
an
d
s
im
u
late
p
ed
estrian
f
lo
w.
AN
N
g
iv
es
a
litt
le
b
etter
p
er
f
o
r
m
an
ce
an
d
f
itn
ess
c
o
m
p
ar
e
d
to
th
e
SVR
alg
o
r
ith
m
.
T
h
e
p
r
ep
ar
atio
n
o
f
t
h
is
wo
r
k
h
ad
two
ess
en
tial
o
b
jectiv
es,
th
e
f
ir
s
t
is
to
m
o
d
el
th
e
p
e
d
estrian
f
lo
w
in
a
co
m
m
er
cial
av
e
n
u
e,
an
d
th
is
h
as
a
d
ir
ec
t
im
p
ac
t
o
n
th
e
p
o
s
s
ib
ilit
ies
o
f
f
u
tu
r
e
c
o
n
g
esti
o
n
o
f
th
is
av
e
n
u
e.
T
h
e
s
ec
o
n
d
o
b
jectiv
e
is
th
e
co
m
p
ar
is
o
n
b
etwe
en
ANN
an
d
SVR
,
with
ANN
h
av
in
g
b
ee
n
th
e
o
b
ject
o
f
s
tu
d
y
i
n
s
ev
er
al
s
cien
tific
ar
ticles
o
n
t
h
e
m
o
d
elin
g
an
d
p
r
ed
ictio
n
o
f
p
ed
estrian
f
lo
w
an
d
wh
ich
h
as
p
r
o
v
en
t
o
b
e
a
g
o
o
d
m
o
d
el
f
o
r
th
e
s
im
u
latio
n
o
f
th
e
p
e
d
estrian
f
l
o
w.
Mo
r
eo
v
er
,
SVR
m
eth
o
d
ac
c
o
r
d
i
n
g
to
th
e
liter
atu
r
e,
th
er
e
ar
e
n
o
t
m
an
y
wo
r
k
s
th
at
h
av
e
u
s
ed
th
is
m
eth
o
d
as
a
p
r
ed
ictio
n
o
r
s
im
u
latio
n
m
o
d
el
o
f
p
ed
estrian
f
lo
w
b
u
t it
is
u
s
ed
in
tr
af
f
ic
f
lo
w
(
v
eh
icu
lar
)
m
o
d
elin
g
,
an
d
t
h
e
s
im
u
latio
n
r
esu
lts
s
h
o
w
g
o
o
d
r
e
s
u
lts
.
Acc
o
r
d
in
g
to
s
im
u
latio
n
r
esu
lts
in
d
icate
d
in
Fig
u
r
es
3
,
4
,
a
n
d
5
th
e
ANN
an
d
SVR
m
o
d
e
ls
s
im
u
lat
e
ad
eq
u
ately
t
h
e
r
ea
l
p
ed
estria
n
f
lo
w.
T
h
e
f
in
d
in
g
s
in
d
icat
e
th
at
th
e
p
r
o
p
o
s
ed
m
o
d
els
ar
e
r
ea
s
o
n
a
b
le
an
d
ca
p
ab
le
o
f
s
im
u
latin
g
an
d
p
r
ed
ictin
g
p
e
d
estrian
f
l
o
w.
I
f
we
r
eso
r
t
to
a
d
escr
ip
tiv
e
a
n
aly
s
is
o
f
th
e
av
er
a
g
e
p
ed
estrian
f
lo
w
al
o
n
g
th
e
th
r
e
e
s
eg
m
en
ts
o
f
t
h
e
av
e
n
u
e
a
n
d
co
n
s
id
er
t
h
e
7
in
ter
v
als
o
f
th
e
d
ay
,
d
u
r
i
n
g
J
u
n
e
an
d
No
v
e
m
b
er
,
as
s
h
o
wn
in
Fig
u
r
e
6
(
a)
.
Fig
u
r
e
6
(
b
)
i
n
d
icat
es
th
e
lev
el
o
f
s
er
v
ice
in
t
h
e
a
v
en
u
e
ac
c
o
r
d
in
g
to
th
e
h
ig
h
way
ca
p
ac
ity
m
a
n
u
al
(
HC
M)
g
u
id
e
[
3
1
]
.
(
a)
(
b
)
Fig
u
r
e
6
.
D
escr
ip
tiv
e
a
n
aly
s
is
o
f
p
ed
estrian
f
lo
w,
(
a
)
av
er
a
g
e
p
ed
estrian
f
lo
w
p
er
m
in
u
te
in
ea
ch
s
eg
m
en
t
,
an
d
(
b
)
PLOS
,
p
ed
estrian
l
ev
e
l
o
f
s
er
v
ice
in
th
e
av
en
u
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
1
4
,
No
.
5
,
Octo
b
e
r
2
0
2
4
:
5
8
4
8
-
5
8
5
7
5856
I
n
Fig
u
r
e
6
(
a
)
,
th
e
r
esu
lt
s
h
o
ws
th
at
th
e
p
ed
estrian
f
lo
w
in
cr
ea
s
es
p
r
o
g
r
ess
iv
ely
,
f
r
o
m
th
e
f
ir
s
t
in
ter
v
al
7
h
4
5
-
8
h
1
5
to
th
e
last
in
ter
v
al
1
9
h
4
5
-
2
0
h
1
5
,
in
th
e
th
r
ee
s
eg
m
en
ts
.
Fu
r
th
er
m
o
r
e,
th
e
f
lo
w
in
cr
ea
s
es
s
ig
n
if
ican
tly
f
r
o
m
th
e
in
te
r
v
a
ls
1
7
h
4
5
-
1
8
h
1
5
to
1
9
h
4
5
-
2
0
h
1
5
.
I
t
is
also
n
o
te
d
th
at
th
e
p
ed
estrian
f
lo
w
is
h
ig
h
er
i
n
th
e
two
s
eg
m
en
ts
H
I
an
d
I
J
th
an
in
t
h
e
OH
s
eg
m
en
t.
Fig
u
r
e
6
(
b
)
,
d
escr
ib
es
th
e
p
ed
estrian
lev
el
o
f
s
er
v
ice
(
PLOS)
in
t
h
is
av
en
u
e.
PLOS
is
a
m
ea
s
u
r
e
th
at
q
u
an
tifie
s
walk
way
co
m
f
o
r
t
le
v
els,
d
ef
in
ed
in
to
s
ix
ca
teg
o
r
ies
(
A,
B
,
C
,
D,
E
,
F)
ea
ch
lev
el
d
ef
in
es
th
e
r
a
n
g
e
o
f
v
alu
es,
f
o
r
ex
am
p
le,
a
g
o
o
d
lev
el
(
b
est
tr
af
f
ic
co
n
d
itio
n
)
is
d
ef
in
ed
with
th
e
letter
A
u
n
til
r
ea
ch
in
g
th
e
w
o
r
s
t
lev
el,
F
(
h
ig
h
co
n
g
esti
o
n
)
.
Acc
o
r
d
i
n
g
to
t
h
e
r
esu
lt
o
b
tain
ed
,
L
OS
A=
3
3
.
3
3
%,
L
OS
B
=3
3
.
3
3
%
an
d
L
O
S
C
=3
3
.
3
3
%.
T
h
e
r
esu
lt
d
is
tr
ib
u
tio
n
is
e
q
u
itab
le,
L
OS C,
it is
d
u
e
to
th
e
in
cr
ea
s
e
in
f
lo
w
in
th
e
h
o
u
r
ly
in
ter
v
al
1
9
h
4
5
-
2
0
h
1
5
.
4.
CO
NCLU
SI
O
N
Mo
b
ilit
y
p
lan
s
ar
e
o
n
e
o
f
t
h
e
m
o
s
t
im
p
o
r
ta
n
t
m
an
a
g
em
en
t
to
o
ls
f
o
r
city
d
ev
elo
p
m
e
n
t
an
d
an
im
p
o
r
tan
t
f
ac
t
o
r
f
o
r
s
o
ciety
a
n
d
ec
o
n
o
m
ic
g
r
o
wth
.
Ped
estr
ian
s
ar
e
th
e
en
d
g
o
al
o
f
an
y
m
o
b
ilit
y
p
lan
.
W
e
h
av
e
f
o
u
n
d
th
r
o
u
g
h
th
e
liter
atu
r
e,
th
at
p
ed
estrian
b
e
h
av
i
o
r
h
as
b
ee
n
s
tu
d
ied
b
y
s
ev
e
r
al
au
th
o
r
s
,
an
d
b
y
d
if
f
er
en
t
p
er
s
p
ec
tiv
es,
s
o
cial
an
d
m
ath
em
atica
l
m
o
d
elin
g
.
I
n
th
is
wo
r
k
,
we
h
av
e
s
tu
d
ied
p
ed
estrian
m
o
b
ilit
y
in
a
co
m
m
er
cial
av
en
u
e
o
f
T
a
n
g
ier
city
.
T
h
is
s
tu
d
y
h
as
co
n
ce
n
tr
ated
o
n
th
e
p
ed
estrian
f
lo
w
m
o
d
el.
T
h
e
d
ata
co
llectio
n
p
r
o
ce
s
s
h
as
b
ee
n
d
ev
elo
p
e
d
th
r
o
u
g
h
th
e
im
p
l
em
en
tatio
n
o
f
a
m
eth
o
d
o
lo
g
y
to
f
ac
ilit
ate
an
d
o
p
tim
ize
th
e
p
r
o
ce
s
s
.
we
h
a
v
e
d
ev
elo
p
ed
two
p
r
ed
ictio
n
m
o
d
els
b
ased
o
n
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
s
ANN
an
d
SVR
.
T
h
e
r
esu
lts
s
h
o
w
th
at
ANN
g
iv
es
a
litt
le
b
etter
p
er
f
o
r
m
an
ce
a
n
d
f
itn
ess
co
m
p
ar
ed
to
th
e
SVR
alg
o
r
ith
m
,
u
s
in
g
d
eter
m
in
atio
n
co
ef
f
icien
t
2
an
d
R
MSE
.
T
h
e
an
aly
s
is
o
f
p
ed
estrian
f
lo
w
r
e
v
ea
ls
th
e
ab
ilit
y
o
f
b
o
th
m
eth
o
d
s
SVR
an
d
A
NN
to
p
r
ed
ict
th
e
n
u
m
b
er
o
f
p
ed
estrian
s
in
d
if
f
er
en
t
p
ar
ts
o
f
tim
e.
W
e
ca
n
u
s
e
th
is
r
esu
lt
as
a
d
ec
is
io
n
t
o
o
l
to
im
p
r
o
v
e
p
ed
estrian
m
o
b
ilit
y
in
th
is
ar
ea
,
s
u
ch
as
p
e
d
estrian
izatio
n
o
f
th
e
av
en
u
e.
RE
F
E
R
E
NC
E
S
[
1
]
U
n
i
t
e
d
N
a
t
i
o
n
s
E
c
o
n
o
mi
c
C
o
mm
i
s
si
o
n
f
o
r
Eu
r
o
p
e
,
“
S
p
a
t
i
a
l
p
l
a
n
n
i
n
g
f
o
r
su
st
a
i
n
a
b
l
e
u
r
b
a
n
mo
b
i
l
i
t
y
a
n
d
a
c
c
e
ssi
b
i
l
i
t
y
,
”
i
n
A
H
a
n
d
b
o
o
k
o
n
S
u
st
a
i
n
a
b
l
e
U
r
b
a
n
M
o
b
i
l
i
t
y
a
n
d
S
p
a
t
i
a
l
Pl
a
n
n
i
n
g
,
U
n
i
t
e
d
N
a
t
i
o
n
s,
2
0
2
0
,
p
p
.
1
5
–
56
,
d
o
i
:
1
0
.
1
8
3
5
6
/
6
c
a
6
6
c
9
2
-
e
n
.
[
2
]
T.
-
Q
.
Ta
n
g
,
B
.
-
T
.
Zh
a
n
g
,
a
n
d
C
.
-
Z
.
X
i
e
,
“
M
o
d
e
l
i
n
g
a
n
d
s
i
mu
l
a
t
i
o
n
o
f
p
e
d
e
st
r
i
a
n
f
l
o
w
i
n
u
n
i
v
e
r
si
t
y
c
a
n
t
e
e
n
,
”
S
i
m
u
l
a
t
i
o
n
Mo
d
e
l
l
i
n
g
Pra
c
t
i
c
e
a
n
d
T
h
e
o
ry
,
v
o
l
.
9
5
,
p
p
.
9
6
–
1
1
1
,
S
e
p
.
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
si
m
p
a
t
.
2
0
1
9
.
0
4
.
0
1
1
.
[
3
]
X
.
C
h
e
n
,
M
.
Tr
e
i
b
e
r
,
V
.
K
a
n
a
g
a
r
a
j
,
a
n
d
H
.
Li
,
“
S
o
c
i
a
l
f
o
r
c
e
m
o
d
e
l
s
f
o
r
p
e
d
e
s
t
r
i
a
n
t
r
a
f
f
i
c
–
s
t
a
t
e
o
f
t
h
e
a
r
t
,
”
T
ra
n
sp
o
r
t
R
e
v
i
e
w
s
,
v
o
l
.
3
8
,
n
o
.
5
,
p
p
.
6
2
5
–
6
5
3
,
N
o
v
.
2
0
1
7
,
d
o
i
:
1
0
.
1
0
8
0
/
0
1
4
4
1
6
4
7
.
2
0
1
7
.
1
3
9
6
2
6
5
.
[
4
]
J.
A
r
e
l
l
a
n
a
,
L.
G
a
r
z
ó
n
,
J.
Es
t
r
a
d
a
,
a
n
d
V
.
C
a
n
t
i
l
l
o
,
“
O
n
t
h
e
u
se
o
f
v
i
r
t
u
a
l
i
mm
e
r
s
i
v
e
r
e
a
l
i
t
y
f
o
r
d
i
scr
e
t
e
c
h
o
i
c
e
e
x
p
e
r
i
m
e
n
t
s
t
o
mo
d
e
l
l
i
n
g
p
e
d
e
s
t
r
i
a
n
b
e
h
a
v
i
o
u
r
,
”
J
o
u
rn
a
l
o
f
C
h
o
i
c
e
Mo
d
e
l
l
i
n
g
,
v
o
l
.
3
7
,
p
.
1
0
0
2
5
1
,
D
e
c
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
o
c
m.2
0
2
0
.
1
0
0
2
5
1
.
[
5
]
L.
D
.
V
a
n
u
mu
,
K
.
R
a
ma
c
h
a
n
d
r
a
R
a
o
,
a
n
d
G
.
Ti
w
a
r
i
,
“
F
u
n
d
a
m
e
n
t
a
l
d
i
a
g
r
a
ms
o
f
p
e
d
e
st
r
i
a
n
f
l
o
w
c
h
a
r
a
c
t
e
r
i
s
t
i
c
s
:
A
r
e
v
i
e
w
,
”
Eu
r
o
p
e
a
n
T
r
a
n
sp
o
r
t
R
e
se
a
rc
h
R
e
v
i
e
w
,
v
o
l
.
9
,
n
o
.
4
,
S
e
p
.
2
0
1
7
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
2
5
4
4
-
017
-
0
2
6
4
-
6.
[
6
]
E.
M
o
u
s
t
a
i
d
a
n
d
G
.
F
l
ö
t
t
e
r
ö
d
,
“
M
a
c
r
o
sc
o
p
i
c
m
o
d
e
l
o
f
mu
l
t
i
d
i
r
e
c
t
i
o
n
a
l
p
e
d
e
s
t
r
i
a
n
n
e
t
w
o
r
k
f
l
o
w
s
,
”
T
r
a
n
sp
o
r
t
a
t
i
o
n
Re
se
a
rc
h
P
a
r
t
B:
Me
t
h
o
d
o
l
o
g
i
c
a
l
,
v
o
l
.
1
4
5
,
p
p
.
1
–
2
3
,
M
a
r
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
t
r
b
.
2
0
2
0
.
1
2
.
0
0
4
.
[
7
]
J.
J
.
F
r
u
i
n
,
“
D
e
si
g
n
i
n
g
f
o
r
p
e
d
e
s
t
r
i
a
n
s
:
A
l
e
v
e
l
-
of
-
serv
i
c
e
c
o
n
c
e
p
t
,
”
5
0
t
h
An
n
u
a
l
M
e
e
t
i
n
g
o
f
t
h
e
H
i
g
h
w
a
y
Re
se
a
rc
h
B
o
a
r
d
,
Wa
s
h
i
n
g
t
o
n
D
i
s
t
ri
c
t
o
f
C
o
l
u
m
b
i
a
,
U
n
i
t
e
d
S
t
a
t
e
s
,
1
9
7
1
.
[
8
]
H
.
S
u
k
h
a
d
i
a
,
S
.
M
.
D
a
v
e
,
J
.
S
h
a
h
,
a
n
d
D
.
R
a
t
h
v
a
,
“
T
h
e
e
f
f
e
c
t
o
f
e
v
e
n
t
s
o
n
p
e
d
e
st
r
i
a
n
b
e
h
a
v
i
o
r
a
n
d
i
t
s
c
o
m
p
a
r
i
so
n
w
i
t
h
n
o
r
m
a
l
w
a
l
k
i
n
g
b
e
h
a
v
i
o
r
i
n
C
B
D
A
r
e
a
i
n
I
n
d
i
a
n
c
o
n
t
e
x
t
,
”
T
ra
n
s
p
o
r
t
a
t
i
o
n
R
e
se
a
rc
h
Pr
o
c
e
d
i
a
,
v
o
l
.
1
7
,
p
p
.
6
5
3
–
6
6
3
,
2
0
1
6
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
t
r
p
r
o
.
2
0
1
6
.
1
1
.
1
2
0
.
[
9
]
S
.
D
a
s,
D
.
M
u
k
h
e
r
j
e
e
,
P
.
S
a
h
a
,
a
n
d
S
.
K
.
R
o
y
,
“
P
e
d
e
st
r
i
a
n
f
l
o
w
c
h
a
r
a
c
t
e
r
i
s
t
i
c
s
a
t
s
i
g
n
a
l
i
z
e
d
i
n
t
e
r
s
e
c
t
i
o
n
s
i
n
m
i
x
e
d
t
r
a
f
f
i
c
si
t
u
a
t
i
o
n
s
:
a
c
a
s
e
s
t
u
d
y
i
n
K
o
l
k
a
t
a
,
I
n
d
i
a
,
”
Pr
o
c
e
d
i
a
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
1
3
0
,
p
p
.
1
5
0
–
1
5
6
,
2
0
1
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
r
o
c
s
.
2
0
1
8
.
0
4
.
0
2
4
.
[
1
0
]
D
.
M
u
l
e
y
,
W
.
A
l
h
a
j
y
a
s
e
e
n
,
M
.
K
h
a
r
b
e
c
h
e
,
a
n
d
M
.
A
l
-
S
a
l
e
m
,
“
P
e
d
e
s
t
r
i
a
n
s’
sp
e
e
d
a
n
a
l
y
si
s
a
t
si
g
n
a
l
i
z
e
d
c
r
o
ss
w
a
l
k
s
,
”
Pr
o
c
e
d
i
a
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
1
3
0
,
p
p
.
5
6
7
–
5
7
4
,
2
0
1
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
r
o
c
s.
2
0
1
8
.
0
4
.
1
0
2
.
[
1
1
]
F
.
W
i
n
d
y
a
n
i
,
P
.
H
.
G
u
n
a
w
a
n
,
a
n
d
D
.
Ta
r
w
i
d
i
,
“
M
a
c
r
o
sc
o
p
i
c
m
o
d
e
l
l
i
n
g
o
f
p
e
d
e
s
t
r
i
a
n
f
l
o
w
s
b
a
se
d
o
n
c
o
n
ser
v
a
t
i
o
n
l
a
w
,
”
J
o
u
rn
a
l
o
f
Ph
y
si
c
s:
C
o
n
f
e
re
n
c
e
S
e
r
i
e
s
,
v
o
l
.
1
6
4
1
,
n
o
.
1
,
p
.
1
2
0
3
1
,
N
o
v
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
8
8
/
1
7
4
2
-
6
5
9
6
/
1
6
4
1
/
1
/
0
1
2
0
3
1
.
[
1
2
]
N
.
K
.
M
a
h
a
t
o
,
A
.
K
l
a
r
,
a
n
d
S
.
T
i
w
a
r
i
,
“
M
o
d
e
l
i
n
g
a
n
d
si
mu
l
a
t
i
o
n
o
f
m
a
c
r
o
sc
o
p
i
c
p
e
d
e
s
t
r
i
a
n
f
l
o
w
m
o
d
e
l
s,”
i
n
Ma
t
h
e
m
a
t
i
c
s
i
n
I
n
d
u
st
r
y
,
S
p
r
i
n
g
e
r
I
n
t
e
r
n
a
t
i
o
n
a
l
P
u
b
l
i
sh
i
n
g
,
2
0
1
9
,
p
p
.
4
3
7
–
4
4
4
.
[
1
3
]
S
.
E.
D
a
v
i
s,
L.
E.
K
i
n
g
,
a
n
d
H
.
D
.
R
o
b
e
r
t
so
n
,
“
P
r
e
d
i
c
t
i
n
g
p
e
d
e
st
r
i
a
n
c
r
o
ssw
a
l
k
v
o
l
u
m
e
s,”
T
ra
n
s
p
o
r
t
a
t
i
o
n
R
e
se
a
rc
h
R
e
c
o
r
d
,
n
o
.
1
1
6
8
,
p
p
.
2
5
–
3
0
,
1
9
8
8
.
[
1
4
]
I
.
B
a
r
g
e
g
o
l
,
S
.
M
.
H
o
sse
i
n
i
a
n
,
V
.
N
a
j
a
f
i
M
o
g
h
a
d
d
a
m
G
i
l
a
n
i
,
M
.
N
i
k
o
o
k
a
r
,
a
n
d
A
.
O
r
o
u
e
i
,
“
P
r
e
se
n
t
a
t
i
o
n
o
f
r
e
g
r
e
ssi
o
n
a
n
a
l
y
s
i
s,
G
P
a
n
d
G
M
D
H
mo
d
e
l
s
t
o
p
r
e
d
i
c
t
t
h
e
p
e
d
e
s
t
r
i
a
n
d
e
n
s
i
t
y
i
n
v
a
r
i
o
u
s
u
r
b
a
n
f
a
c
i
l
i
t
i
e
s,
”
Fr
o
n
t
i
e
rs
o
f
S
t
ru
c
t
u
r
a
l
a
n
d
C
i
v
i
l
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
1
6
,
n
o
.
2
,
p
p
.
2
5
0
–
2
6
5
,
F
e
b
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
7
0
9
-
0
2
1
-
0
7
8
5
-
x.
[
1
5
]
N
.
F
u
j
i
mo
t
o
e
t
a
l
.
,
“
S
t
u
d
y
o
n
p
e
d
e
s
t
r
i
a
n
f
l
o
w
p
r
e
d
i
c
t
i
o
n
o
f
sp
e
c
i
f
i
c
f
l
o
w
u
s
i
n
g
d
i
me
n
s
i
o
n
l
e
ss
w
i
d
t
h
,
”
i
n
T
h
e
Pr
o
c
e
e
d
i
n
g
s
o
f
1
1
t
h
Asi
a
-
O
c
e
a
n
i
a
S
y
m
p
o
s
i
u
m
o
n
F
i
re
S
c
i
e
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
S
p
r
i
n
g
e
r
S
i
n
g
a
p
o
r
e
,
2
0
2
0
,
p
p
.
2
5
5
–
2
6
8
.
[
1
6
]
T.
L
i
e
b
i
g
,
Z.
X
u
,
M
.
M
a
y
,
a
n
d
S
.
W
r
o
b
e
l
,
“
P
e
d
e
st
r
i
a
n
q
u
a
n
t
i
t
y
e
st
i
ma
t
i
o
n
w
i
t
h
t
r
a
j
e
c
t
o
r
y
p
a
t
t
e
r
n
s
,
”
i
n
L
e
c
t
u
re
N
o
t
e
s
i
n
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
S
p
r
i
n
g
e
r
B
e
r
l
i
n
H
e
i
d
e
l
b
e
r
g
,
2
0
1
2
,
p
p
.
6
2
9
–
6
4
3
.
[
1
7
]
K
.
Z
h
a
n
g
,
M
.
W
a
n
g
,
B
.
W
e
i
,
a
n
d
D
.
S
u
n
,
“
I
d
e
n
t
i
f
i
c
a
t
i
o
n
a
n
d
p
r
e
d
i
c
t
i
o
n
o
f
l
a
r
g
e
p
e
d
e
st
r
i
a
n
f
l
o
w
i
n
u
r
b
a
n
a
r
e
a
s
b
a
s
e
d
o
n
a
h
y
b
r
i
d
d
e
t
e
c
t
i
o
n
a
p
p
r
o
a
c
h
,
”
S
u
s
t
a
i
n
a
b
i
l
i
t
y
,
v
o
l
.
9
,
n
o
.
1
,
p
.
3
6
,
D
e
c
.
2
0
1
6
,
d
o
i
:
1
0
.
3
3
9
0
/
s
u
9
0
1
0
0
3
6
.
[
1
8
]
X
.
Z
h
a
o
,
L
.
X
i
a
,
J.
Z
h
a
n
g
,
a
n
d
W
.
S
o
n
g
,
“
A
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
b
a
se
d
mo
d
e
l
i
n
g
o
n
u
n
i
d
i
r
e
c
t
i
o
n
a
l
a
n
d
b
i
d
i
r
e
c
t
i
o
n
a
l
p
e
d
e
s
t
r
i
a
n
f
l
o
w
a
t
st
r
a
i
g
h
t
c
o
r
r
i
d
o
r
s,”
P
h
y
s
i
c
a
A:
S
t
a
t
i
s
t
i
c
a
l
Me
c
h
a
n
i
c
s
a
n
d
i
t
s
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
5
4
7
,
A
r
t
.
n
o
.
1
2
3
8
2
5
,
Ju
n
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
h
y
sa.
2
0
1
9
.
1
2
3
8
2
5
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
P
ed
estr
ia
n
flo
w
p
r
ed
ictio
n
in
co
mme
r
cia
l a
ve
n
u
e
(
Ma
r
w
a
n
e
B
en
h
a
d
o
u
)
5857
[
1
9
]
A
.
To
r
d
e
u
x
,
M
.
C
h
r
a
i
b
i
,
A
.
S
e
y
f
r
i
e
d
,
a
n
d
A
.
S
c
h
a
d
sc
h
n
e
i
d
e
r
,
“
P
r
e
d
i
c
t
i
o
n
o
f
p
e
d
e
st
r
i
a
n
d
y
n
a
m
i
c
s
i
n
c
o
m
p
l
e
x
a
r
c
h
i
t
e
c
t
u
r
e
s
w
i
t
h
a
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s
,
”
J
o
u
r
n
a
l
o
f
I
n
t
e
l
l
i
g
e
n
t
T
ra
n
s
p
o
r
t
a
t
i
o
n
S
y
st
e
m
s
,
v
o
l
.
2
4
,
n
o
.
6
,
p
p
.
5
5
6
–
5
6
8
,
Ju
n
.
2
0
1
9
,
d
o
i
:
1
0
.
1
0
8
0
/
1
5
4
7
2
4
5
0
.
2
0
1
9
.
1
6
2
1
7
5
6
.
[
2
0
]
A
.
C
o
h
e
n
a
n
d
S
.
D
a
l
y
o
t
,
“
P
e
d
e
s
t
r
i
a
n
t
r
a
f
f
i
c
f
l
o
w
p
r
e
d
i
c
t
i
o
n
b
a
s
e
d
o
n
A
N
N
mo
d
e
l
a
n
d
O
S
M
d
a
t
a
,
”
Pr
o
c
e
e
d
i
n
g
s o
f
t
h
e
I
C
A
,
v
o
l
.
2
,
p
p
.
1
–
8
,
Ju
l
.
2
0
1
9
,
d
o
i
:
1
0
.
5
1
9
4
/
i
c
a
-
p
r
o
c
-
2
-
20
-
2
0
1
9
.
[
2
1
]
A
.
C
o
h
e
n
a
n
d
S
.
D
a
l
y
o
t
,
“
M
a
c
h
i
n
e
‐
l
e
a
r
n
i
n
g
p
r
e
d
i
c
t
i
o
n
mo
d
e
l
s
f
o
r
p
e
d
e
s
t
r
i
a
n
t
r
a
f
f
i
c
f
l
o
w
l
e
v
e
l
s
:
T
o
w
a
r
d
s
o
p
t
i
mi
z
i
n
g
w
a
l
k
i
n
g
r
o
u
t
e
s f
o
r
b
l
i
n
d
p
e
d
e
s
t
r
i
a
n
s
,
”
T
r
a
n
sa
c
t
i
o
n
s
i
n
G
I
S
,
v
o
l
.
2
4
,
n
o
.
5
,
p
p
.
1
2
6
4
–
1
2
7
9
,
A
u
g
.
2
0
2
0
,
d
o
i
:
1
0
.
1
1
1
1
/
t
g
i
s.
1
2
6
7
4
.
[
2
2
]
M
.
L
u
c
a
,
G
.
B
a
r
l
a
c
c
h
i
,
B
.
Le
p
r
i
,
a
n
d
L.
P
a
p
p
a
l
a
r
d
o
,
“
A
s
u
r
v
e
y
o
n
d
e
e
p
l
e
a
r
n
i
n
g
f
o
r
h
u
ma
n
mo
b
i
l
i
t
y
,
”
A
C
M
C
o
m
p
u
t
i
n
g
S
u
r
v
e
y
s
,
v
o
l
.
5
5
,
n
o
.
1
,
D
e
c
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
4
5
/
3
4
8
5
1
2
5
.
[
2
3
]
M
.
Li
u
,
L.
Li
,
Q
.
Li
,
Y
.
B
a
i
,
a
n
d
C
.
H
u
,
“
P
e
d
e
s
t
r
i
a
n
f
l
o
w
p
r
e
d
i
c
t
i
o
n
i
n
o
p
e
n
p
u
b
l
i
c
p
l
a
c
e
s
u
s
i
n
g
g
r
a
p
h
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
t
w
o
r
k
,
”
I
S
PR
S
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
G
e
o
-
I
n
f
o
rm
a
t
i
o
n
,
v
o
l
.
1
0
,
n
o
.
7
,
p
.
4
5
5
,
J
u
l
.
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
i
j
g
i
1
0
0
7
0
4
5
5
.
[
2
4
]
A
.
A
n
g
e
l
,
A
.
C
o
h
e
n
,
T.
N
e
l
so
n
,
a
n
d
P
.
P
l
a
u
t
,
“
E
v
a
l
u
a
t
i
n
g
t
h
e
r
e
l
a
t
i
o
n
s
h
i
p
b
e
t
w
e
e
n
w
a
l
k
i
n
g
a
n
d
s
t
r
e
e
t
c
h
a
r
a
c
t
e
r
i
s
t
i
c
s b
a
s
e
d
o
n
b
i
g
d
a
t
a
a
n
d
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
n
a
l
y
s
i
s,
”
S
o
c
i
a
l
S
c
i
e
n
c
e
Re
s
e
a
r
c
h
N
e
t
w
o
r
k
,
p
p
.
1
-
2
7
,
A
u
g
.
2
0
2
3
,
d
o
i
:
1
0
.
2
1
3
9
/
ssr
n
.
4
5
5
5
6
3
1
.
[
2
5
]
H
i
g
h
C
o
mm
i
ssi
o
n
e
r
f
o
r
P
l
a
n
n
i
n
g
,
“
P
r
o
j
e
c
t
i
o
n
s
o
f
t
h
e
p
o
p
u
l
a
t
i
o
n
o
f
r
e
g
i
o
n
s
a
n
d
p
r
o
v
i
n
c
e
s
2
0
1
4
–
2
0
3
0
,
”
(
i
n
F
r
e
n
c
h
)
h
t
t
p
s
:
/
/
w
w
w
.
h
c
p
.
ma
/
r
e
g
i
o
n
-
t
a
n
g
e
r
/
P
r
o
j
e
c
t
i
o
n
s
-
de
-
la
-
p
o
p
u
l
a
t
i
o
n
-
d
e
s
-
p
r
o
v
i
n
c
e
s
-
et
-
p
r
e
f
e
c
t
u
r
e
s
-
de
-
la
-
r
e
g
i
o
n
-
T
TA
_
a
3
2
2
.
h
t
ml
(
a
c
c
e
s
se
d
O
c
t
.
2
0
,
2
0
2
3
)
.
[
2
6
]
A.
-
A
.
N
a
y
a
n
,
B
.
K
i
j
si
r
i
k
u
l
,
a
n
d
Y
.
I
w
a
h
o
r
i
,
“
C
o
r
o
n
a
v
i
r
u
s
d
i
s
e
a
se
s
i
t
u
a
t
i
o
n
a
n
a
l
y
si
s
a
n
d
p
r
e
d
i
c
t
i
o
n
u
si
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
:
a
st
u
d
y
o
n
B
a
n
g
l
a
d
e
sh
i
p
o
p
u
l
a
t
i
o
n
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
t
ri
c
a
l
a
n
d
C
o
m
p
u
t
e
r
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
1
2
,
n
o
.
4
,
pp
.
4
2
1
7
–
4
2
2
7
,
A
u
g
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
c
e
.
v
1
2
i
4
.
p
p
4
2
1
7
-
4
2
2
7
.
[
2
7
]
C
.
C
o
r
t
e
s
a
n
d
V
.
V
a
p
n
i
k
,
“
S
u
p
p
o
r
t
-
v
e
c
t
o
r
n
e
t
w
o
r
k
s,”
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
,
v
o
l
.
2
0
,
n
o
.
3
,
p
p
.
2
7
3
–
2
9
7
,
S
e
p
.
1
9
9
5
,
d
o
i
:
1
0
.
1
0
0
7
/
b
f
0
0
9
9
4
0
1
8
.
[
2
8
]
Y
.
S
h
a
o
a
n
d
Q
.
J
i
a
n
g
,
“
A
n
e
w
c
l
a
ss o
f
B
e
sse
l
k
e
r
n
e
l
f
u
n
c
t
i
o
n
s
f
o
r
s
u
p
p
o
r
t
v
e
c
t
o
r
m
a
c
h
i
n
e
,
”
I
EE
E
Ac
c
e
ss
,
v
o
l
.
1
2
,
p
p
.
5
3
5
7
–
5
3
6
4
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
a
c
c
e
ss
.
2
0
2
4
.
3
3
5
0
1
9
5
.
[
2
9
]
M
.
H
.
X
u
a
n
W
a
i
,
A
.
H
u
o
n
g
,
a
n
d
X
.
N
g
u
,
“
S
o
i
l
mo
i
st
u
r
e
l
e
v
e
l
p
r
e
d
i
c
t
i
o
n
u
si
n
g
o
p
t
i
c
a
l
t
e
c
h
n
i
q
u
e
a
n
d
a
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
E
l
e
c
t
ri
c
a
l
a
n
d
C
o
m
p
u
t
e
r
E
n
g
i
n
e
e
r
i
n
g
,
v
o
l
.
1
1
,
n
o
.
2
,
pp
.
1
7
5
2
–
1
7
6
0
,
A
p
r
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
c
e
.
v
1
1
i
2
.
p
p
1
7
5
2
-
1
7
6
0
.
[
3
0
]
W
.
C
a
r
d
o
s
o
e
t
a
l
.
,
“
M
o
d
e
l
i
n
g
o
f
a
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s
f
o
r
s
i
l
i
c
o
n
p
r
e
d
i
c
t
i
o
n
i
n
t
h
e
c
a
st
i
r
o
n
p
r
o
d
u
c
t
i
o
n
p
r
o
c
e
ss,
”
I
A
ES
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
1
1
,
n
o
.
2
,
pp
.
5
3
0
-
5
3
8
,
J
u
n
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
a
i
.
v
1
1
.
i
2
.
p
p
5
3
0
-
5
3
8
.
[
3
1
]
Tr
a
n
s
p
o
r
t
a
t
i
o
n
R
e
sea
r
c
h
B
o
a
r
d
,
U
rb
a
n
st
r
e
e
t
se
g
m
e
n
t
s
,
I
n
H
i
g
h
w
a
y
C
a
p
a
c
i
t
y
M
a
n
u
a
l
(
H
C
M),
5
t
h
E
d
i
t
i
o
n
,
5
t
h
e
d
.
W
a
s
h
i
n
g
t
o
n
,
D
.
C
.
:
N
a
t
i
o
n
a
l
R
e
sea
r
c
h
C
o
u
n
c
i
l
W
a
s
h
i
n
g
t
o
n
,
D
.
C
.
,
2
0
1
0
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Ma
r
wa
n
e
Be
n
h
a
d
o
u
is
a
n
a
ss
istan
t
p
ro
fe
ss
o
r
o
f
i
n
fo
rm
a
ti
c
s,
a
t
Ab
d
e
lma
le
k
Essa
â
d
i
Un
iv
e
rsity
.
His
re
se
a
rc
h
in
tere
sts
in
c
l
u
d
e
tele
c
o
m
m
u
n
ica
ti
o
n
s,
m
a
th
e
m
a
ti
c
a
l
m
o
d
e
li
n
g
a
n
d
c
o
m
p
u
ti
n
g
,
traffic
e
n
g
in
e
e
rin
g
,
a
n
d
s
u
sta
in
a
b
le
m
o
b
il
it
y
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
m
a
rwa
n
e
.
fe
g
.
in
fo
@g
m
a
il
.
c
o
m
.
Am
in
a
El
G
o
n
n
o
u
n
i
re
c
e
iv
e
d
a
c
o
m
p
u
ter
sc
ien
c
e
d
e
g
re
e
fro
m
th
e
S
c
ien
c
e
a
n
d
Tec
h
n
o
l
o
g
y
De
p
a
rtme
n
t
,
A
b
d
e
l
m
a
lek
Essa
a
d
i
Un
i
v
e
rsity
,
Ta
n
g
ier,
M
o
ro
c
c
o
,
t
h
e
D.E
.
S
.
A.
d
e
g
re
e
in
tele
c
o
m
m
u
n
ica
ti
o
n
s
sy
ste
m
s
fro
m
th
e
F
a
c
u
lt
y
o
f
S
c
ien
c
e
o
f
Teto
u
a
n
,
M
o
ro
c
c
o
,
a
n
d
th
e
P
h
.
D.
d
e
g
re
e
in
tele
c
o
m
m
u
n
ica
ti
o
n
s
a
n
d
i
n
fo
rm
a
ti
c
s
fro
m
th
e
F
a
c
u
lt
y
o
f
S
c
ien
c
e
o
f
Teto
u
a
n
,
M
o
r
o
c
c
o
.
He
r
re
se
a
r
c
h
in
tere
sts
in
c
lu
d
e
a
rti
ficia
l
in
telli
g
e
n
c
e
,
m
a
c
h
in
e
lea
rn
in
g
,
a
n
d
sta
ti
stica
l
lea
rn
in
g
fo
r
si
g
n
a
l
p
ro
c
e
ss
in
g
,
c
o
g
n
it
i
v
e
ra
d
i
o
,
a
n
d
se
n
so
r
n
e
two
rk
s.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
a
m
in
a
_
e
lg
o
@
y
a
h
o
o
.
fr
.
Abd
e
lo
u
a
h
id
Ly
h
y
a
o
u
i
is
a
fu
ll
p
ro
fe
ss
o
r
a
t
th
e
Na
ti
o
n
a
l
S
c
h
o
o
l
o
f
A
p
p
li
e
d
S
c
ien
c
e
s
o
f
Tan
g
ier.
He
h
o
l
d
s
t
h
e
P
h
D
d
e
g
re
e
i
n
tele
c
o
m
m
u
n
ica
ti
o
n
s
e
n
g
i
n
e
e
rin
g
fro
m
t
h
e
Esc
u
e
la
P
o
li
tec
n
ica
S
u
p
e
ri
o
r,
Un
i
v
e
rsid
a
d
Ca
rlo
s
III
d
e
M
a
d
ri
d
.
Hi
s
re
se
a
r
c
h
in
tere
sts
in
c
lu
d
e
d
a
ta sc
ien
c
e
,
a
rti
ficia
l
in
telli
g
e
n
c
e
,
a
n
d
sm
a
rt
c
it
ies
.
He
h
a
s p
a
rti
c
ip
a
ted
in
se
v
e
ra
l
n
a
ti
o
n
a
l
a
n
d
in
tern
a
ti
o
n
a
l
re
se
a
rc
h
p
ro
jec
ts
a
n
d
h
a
s
m
o
re
th
a
n
1
5
0
sc
ien
ti
fic
p
u
b
li
c
a
ti
o
n
s.
He
is
a
m
e
m
b
e
r
o
f
sc
ien
ti
fic
c
o
m
m
it
tee
s
o
f
se
v
e
ra
l
n
a
ti
o
n
a
l
a
n
d
i
n
tern
a
ti
o
n
a
l
c
o
n
fe
re
n
c
e
s
a
n
d
jo
u
rn
a
ls.
d
irec
to
r
o
f
th
e
I
n
n
o
v
a
ti
v
e
Tec
h
n
o
lo
g
ies
Lab
o
ra
to
r
y
,
e
lec
ted
m
e
m
b
e
r
o
f
th
e
S
c
ie
n
ti
fic
Co
u
n
c
il
,
th
e
Bo
a
rd
o
f
Dire
c
to
rs,
t
h
e
P
e
d
a
g
o
g
ica
l
Co
m
m
issio
n
o
f
th
e
Un
iv
e
r
sity
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
ly
h
y
a
o
u
i@
g
m
a
il
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.