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
-
AI
)
V
ol
.
15
, N
o.
1
,
F
e
br
ua
r
y
2026
, pp.
177
~
190
I
S
S
N
:
2252
-
8938
,
D
O
I
:
10.11591/
ij
a
i.
v
15
.i
1
.pp
177
-
190
177
Jou
r
n
al
h
om
e
page
:
ht
tp
:
//
ij
ai
.
ia
e
s
c
or
e
.c
om
S
e
r
i
ou
s gam
e
i
n
t
e
l
l
i
ge
n
t
t
r
an
sp
or
t
at
i
on
sys
t
e
m
b
ase
d
on
i
n
t
e
r
n
e
t
of
t
h
i
n
g
s
F
r
e
s
y N
u
gr
oh
o
1,
2
,
I
G
u
s
t
i
P
u
t
u
A
s
t
o B
u
d
it
j
ah
j
an
t
o
3
, D
w
i
P
e
b
r
ia
n
t
i
4
, Je
h
ad
A
.
H
. H
am
m
ad
5
,
M
oc
h
F
ac
h
r
i
3
, T
r
i
M
u
k
t
i
L
e
s
t
ar
i
1,
2
, D
ia
n
M
ah
ar
an
i
6
, A
lf
in
a
N
u
r
r
ah
m
a
’
N
2
1
D
e
pa
r
t
m
e
nt
of
M
e
c
ha
ni
c
a
l
E
ngi
ne
e
r
i
ng, F
a
c
ul
t
y of
E
ngi
ne
e
r
i
ng, U
ni
ve
r
s
i
t
a
s
I
s
l
a
m
N
e
ge
r
i
M
a
ul
a
na
M
a
l
i
k I
br
a
hi
m
, M
a
l
a
ng, I
ndone
s
i
a
2
D
e
pa
r
t
m
e
nt
of
I
nf
or
m
a
t
i
c
s
E
ngi
ne
e
r
i
ng,
F
a
c
ul
t
y of
S
c
i
e
nc
e
a
nd T
e
c
hnol
ogy, U
ni
ve
r
s
i
t
a
s
I
s
l
a
m
N
e
ge
r
i
M
a
ul
a
na
M
a
l
i
k I
br
a
hi
m
,
M
a
l
a
ng, I
ndone
s
i
a
3
D
e
pa
r
t
m
e
nt
of
E
l
e
c
t
r
i
c
a
l
E
ngi
ne
e
r
i
ng,
F
a
c
ul
t
y of
E
ngi
ne
e
r
i
ng, S
t
a
t
e
U
ni
ve
r
s
i
t
y of
S
ur
a
ba
ya
, S
ur
a
ba
ya
, I
ndone
s
i
a
4
D
e
pa
r
t
m
e
nt
of
M
e
c
ha
ni
c
a
l
A
e
r
os
p
a
c
e
E
ngi
ne
e
r
i
ng, I
nt
e
r
na
t
i
ona
l
I
s
l
a
m
i
c
U
ni
ve
r
s
i
t
y M
a
l
a
ys
i
a
,
K
ua
l
a
L
um
pur
, M
a
l
a
ys
i
a
5
D
e
pa
r
t
m
e
nt
of
C
om
put
e
r
I
nf
or
m
a
t
i
on
S
ys
t
e
m
, A
l
Q
uds
O
pe
n U
ni
ve
r
s
i
t
y, A
bu
D
i
s
,
P
a
l
e
s
t
i
ne
6
D
e
pa
r
t
m
e
nt
of
M
a
t
he
m
a
t
i
c
s
, F
a
c
ul
t
y of
S
c
i
e
nc
e
a
nd T
e
c
hnol
ogy, U
ni
ve
r
s
i
t
a
s
I
s
l
a
m
N
e
ge
r
i
M
a
ul
a
na
M
a
l
i
k I
br
a
hi
m
, M
a
l
a
ng, I
ndone
s
i
a
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
N
ov
7
,
2024
R
e
vi
s
e
d
N
ov
12
,
2025
A
c
c
e
pt
e
d
J
a
n
10
,
2026
This
research
examines
the
implementation
of
the
preference
r
anking
organization
method
for
enrichment
evaluation
(
PROMETHE
E
)
ap
proach
for
multi
-
criteria
decision
-
making
in
a
character
recommendation
system
for
serious
games.
The
method
calculates
characte
r
skill
values
across
m
ultiple
criteria
and
generates
rankings
of
the
best
characters
according
to
game
environm
ent
conditi
ons
derived
from
closed
-
circuit
televisi
on
(
C
CTV
)
-
based
traffic
detection.
Image
processing
algorithms
were
applied
to
c
lassify
congesti
on
levels
into
quiet,
moderate,
and
busy
categories,
which
d
irectly
influence
gameplay
modes.
Experimenta
l
results
show
th
at
PROME
THEE
rankings
vary
across
maps
(
e.g.,
A6
ranked
highest
in
quiet
mode,
wh
ile
B2
dominated
in
busy
mode),
demonstrating
the
system’s
con
textual
adaptabil
ity. Us
abilit
y testi
ng with
50 part
icipants
yielded
an average
system
usability
scale
(SUS)
score
of
78.9,
while
expert
evaluation
using
game
design
factor
questionnaire
(
GDFQ
)
produced
a
mean
of
4.19/5
,
both
indicating
high
accepta
nce
and
positive
user
experie
nce.
These
fi
ndings
confirm
that
PROMET
HEE
is
effective
in
generating
context
-
aware
recomme
ndations,
providing
both
strategic
depth
and
engagemen
t.
The
study
concludes
that
integrating
traffic
data
into
serious
game
desi
gn
can
enrich
intelligent
transporta
tion
systems
(
ITS
)
education
and
awa
reness,
with
future
improvements
possible
through
real
-
time
player
fe
edback
adaptatio
n and mach
ine learni
ng
–
based traffic pre
diction.
K
e
y
w
o
r
d
s
:
C
lo
s
e
d
-
c
ir
c
ui
t
te
le
vi
s
io
n
I
nt
e
ll
i
ge
nt
tr
a
n
s
po
r
ta
ti
o
n
s
y
s
te
m
P
R
O
M
E
T
H
E
E
S
e
r
io
us
ga
m
e
S
ys
te
m
us
a
bi
li
ty
s
c
a
le
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
:
F
r
e
s
y N
ugr
oho
D
e
pa
r
tm
e
nt
of
M
e
c
ha
ni
c
a
l
E
ngi
ne
e
r
in
g, F
a
c
ul
ty
of
E
ngi
ne
e
r
in
g
U
ni
ve
r
s
it
a
s
I
s
la
m
N
e
g
e
r
i
M
a
ul
a
na
M
a
li
k I
br
a
hi
m
G
a
ja
ya
na
S
tr
e
e
t
50, Dinoyo, M
a
la
ng C
it
y, E
a
s
t
J
a
v
a
, I
ndone
s
ia
E
m
a
il
:
f
r
e
s
y@
ti
.ui
n
-
m
a
la
ng.a
c
.i
d
1.
I
N
T
R
O
D
U
C
T
I
O
N
I
nt
e
ll
ig
e
nt
tr
a
ns
por
ta
ti
on
s
ys
te
m
s
(
I
T
S
)
a
r
e
c
ons
id
e
r
e
d
in
c
r
e
a
s
in
gl
y
m
a
tu
r
e
not
onl
y
in
te
r
m
s
of
a
ut
om
a
ti
on
[
1]
but
a
ls
o
s
a
vi
ng
on
th
e
ba
s
i
s
of
A
C
P
s
[
2]
a
nd
r
e
a
l
-
ti
m
e
da
ta
pr
oc
e
s
s
in
g
[
3]
,
[
4]
.
E
a
c
h
pr
oc
e
s
s
pr
e
s
e
nt
s
te
c
hnol
ogi
e
s
th
a
t
im
pr
ove
tr
a
ns
por
ta
ti
on
pe
r
f
or
m
a
nc
e
[
5]
,
[
6]
s
uc
h
a
s
ge
ogr
a
phi
c
in
f
or
m
a
ti
on
s
ys
te
m
s
(
G
I
S
)
[
7]
.
M
e
th
odol
ogi
e
s
a
nd
to
ol
s
a
r
e
ve
r
y
va
lu
a
bl
e
[
8]
.
T
e
c
hnol
ogi
e
s
s
uc
h
a
s
m
a
c
hi
ne
le
a
r
ni
ng
a
nd
bi
g
da
ta
he
lp
tr
a
f
f
ic
f
lo
w
[
9]
,
w
hi
le
c
lo
s
e
d
-
c
ir
c
ui
t
te
le
vi
s
io
n
(
C
C
T
V
)
is
now
of
te
n
us
e
d
to
m
oni
to
r
r
oa
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
.
15
, N
o.
1
,
F
e
br
ua
r
y
20
26
:
177
-
190
178
c
ondi
ti
ons
[
10]
,
de
te
c
t
a
c
c
id
e
nt
s
[
11]
,
de
te
r
m
in
e
in
c
id
e
nt
lo
c
a
ti
ons
[
12]
,
opt
im
iz
e
tr
a
f
f
ic
l
ig
ht
s
[
13]
,
a
nd
s
im
ul
a
te
a
ut
onomous
ve
hi
c
le
s
[
14]
.
A
lt
hough
m
a
ny
s
tu
di
e
s
ha
ve
e
xa
m
in
e
d
C
C
T
V
-
ba
s
e
d
c
ont
r
ol
a
nd
le
a
r
ni
ng,
th
e
a
ppl
ic
a
ti
on
of
th
e
s
e
id
e
a
s
to
e
duc
a
ti
ona
l
or
ga
m
in
g
c
ont
e
xt
s
i
s
s
ti
ll
r
a
r
e
[
15]
,
[
16]
.
T
h
e
r
e
is
on
e
m
e
ta
ve
r
s
e
s
im
ul
a
ti
on ba
s
e
d on I
T
S
[
17]
but
none
is
ba
s
e
d on a
s
e
r
io
us
ga
m
e
ye
t.
W
hi
le
s
e
r
io
us
ga
m
e
s
ha
ve
a
s
ig
ni
f
ic
a
nt
im
pa
c
t,
f
or
e
xa
m
pl
e
,
in
p
r
e
ve
nt
in
g
c
ybe
r
bul
ly
in
g
[
18]
,
f
r
ui
t
e
duc
a
ti
on
[
19
]
,
a
nd
e
duc
a
ti
ona
l
e
nvi
r
onm
e
nt
s
[
20]
th
a
t
c
le
a
r
ly
f
oc
us
on
one
th
in
g:
le
a
r
ni
ng
go
a
ls
a
nd
s
ki
ll
im
pr
ove
m
e
nt
[
21]
,
it
is
im
por
ta
nt
to
pr
ovi
de
e
le
m
e
nt
s
t
ha
t
a
r
e
bot
h e
nt
e
r
ta
in
in
g a
nd c
ha
ll
e
ngi
ng f
or
us
e
r
s
, s
uc
h a
s
e
ndl
e
s
s
r
unne
r
s
[
22]
.
E
ndl
e
s
s
r
unne
r
s
ha
ve
b
e
e
n
a
ppl
ie
d
in
pr
e
vi
ous
r
e
s
e
a
r
c
h,
s
uc
h
a
s
s
tu
dyi
ng
m
e
di
c
a
l
[
23]
a
nd
m
e
di
c
a
l
pl
a
nt
s
[
24]
.
T
he
c
om
bi
na
ti
on
of
ga
m
e
s
a
nd
in
te
r
ne
t
of
th
in
gs
(
I
oT
)
[
25]
w
a
s
one
of
th
e
s
ta
r
ti
ng
poi
nt
s
of
r
e
s
e
a
r
c
h
th
a
t
in
it
ia
ll
y
us
e
d
w
e
bc
a
m
s
f
or
e
m
ot
io
n
r
e
c
ogni
ti
on
[
26]
a
nd
pa
r
ki
ng
de
te
c
t
io
n
[
27]
.
T
hi
s
s
tu
dy
c
om
bi
ne
s
a
ll
of
th
e
a
bove
w
it
h
th
e
a
ddi
ti
on
o
f
th
e
P
R
O
M
O
T
H
E
E
m
e
th
od,
f
ol
lo
w
in
g
th
e
pr
in
c
ip
le
s
of
c
om
put
e
r
iz
e
d
a
da
pt
iv
e
pr
a
c
ti
c
e
[
28]
f
or
pl
a
ye
r
le
ve
li
ng
a
nd
di
f
f
ic
ul
ty
.
S
im
il
a
r
to
V
R
-
P
E
E
R
[
29]
,
tr
a
f
f
ic
da
ta
is
ta
ke
n
f
r
om
a
r
e
a
l
-
w
or
ld
s
ys
te
m
a
nd c
l
a
s
s
if
ie
d c
ong
e
s
ti
on l
e
ve
ls
, t
h
e
n t
e
s
te
d on 50 p
a
r
ti
c
ip
a
nt
s
.
2.
M
E
T
H
O
D
S
in
c
e
2015,
th
e
r
e
ha
s
be
e
n
a
n
in
c
r
e
a
s
e
in
r
e
s
e
a
r
c
h
on
th
e
in
te
gr
a
ti
on
of
s
e
r
io
us
ga
m
e
s
(
S
G
)
w
it
h
th
e
I
oT
.
B
y
2024,
th
e
c
om
bi
na
ti
on
of
I
oT
a
nd
I
T
S
w
il
l
a
ls
o
be
ve
r
y
c
om
pl
e
x
a
nd
in
c
r
e
a
s
in
gl
y
num
e
r
ous
.
A
s
um
m
a
r
y of
t
he
ke
y f
in
di
ngs
f
r
om
t
he
s
e
s
tu
di
e
s
i
s
s
how
n i
n T
a
bl
e
1.
T
a
bl
e
1. R
e
la
te
d
w
or
k
P
a
pe
r
S
e
r
i
o
u
s
g
a
m
e
I
o
T
I
n
t
e
l
l
i
g
e
n
t
t
r
a
n
s
p
o
r
t
s
y
s
t
e
m
s
i
m
u
l
a
t
i
o
n
S
i
m
u
l
a
t
i
o
n
O
p
t
i
m
i
z
a
t
i
o
n
P
okr
i
ć
e
t
al
.
[
28]
√
√
G
a
r
c
i
a
e
t
al
.
[
29]
√
√
T
a
ngw
or
a
ki
t
t
ha
w
or
n
e
t
al
.
[
30]
√
√
S
um
i
t
a
nd C
hhi
l
l
a
r
[
31]
√
√
C
ui
a
nd L
e
i
[
32]
√
√
Z
a
m
a
ni
a
nd K
a
l
ba
s
i
[
33]
√
√
G
upt
a
e
t
al
.
[
34]
√
√
A
l
s
bou
e
t
al
.
[
35]
√
√
H
i
r
oi
e
t
al
.
[
36]
√
√
R
a
j
put
a
nd J
a
i
n
[
37]
√
√
P
r
opos
e
d
√
√
√
√
√
M
ul
ti
-
c
r
it
e
r
ia
de
c
is
io
n
-
m
a
ki
ng
(
M
C
D
M
)
m
e
th
ods
a
r
e
a
ppl
ie
d
i
n
th
e
c
ont
e
xt
of
I
T
S
a
nd
I
oT
,
but
f
or
s
e
r
io
us
ga
m
e
s
it
is
s
ti
ll
not
m
a
s
s
iv
e
.
F
or
e
xa
m
pl
e
,
th
e
r
e
is
th
e
pot
e
nt
ia
l
of
pr
e
f
e
r
e
nc
e
r
a
nki
ng
or
ga
ni
z
a
ti
on
m
e
th
od
f
or
e
n
r
ic
hm
e
nt
e
va
lu
a
ti
on
(
P
R
O
M
E
T
H
E
E
)
f
o
r
I
T
S
opt
im
iz
a
ti
on
c
om
pa
r
e
d
to
a
na
ly
ti
c
hi
e
r
a
r
c
hy
pr
oc
e
s
s
(
AHP
)
a
nd
te
c
hni
que
f
or
or
de
r
pr
e
f
e
r
e
nc
e
by
s
im
il
a
r
it
y
to
id
e
a
l
s
ol
ut
io
n
(
T
O
P
S
I
S
)
.
T
hi
s
to
pi
c
do
e
s
not
ye
t
ha
ve
qu
a
nt
it
a
ti
ve
va
li
da
ti
on
[
32]
.
T
he
n
th
e
r
e
i
s
th
e
I
oT
-
ba
s
e
d
D
E
M
O
E
D
I
C
T
s
im
ul
a
ti
on
in
ne
twor
k
e
va
lu
a
ti
on
[
38]
. U
r
ba
n
tr
a
f
f
ic
s
ys
te
m
s
a
ls
o ha
ve
not
c
om
bi
ne
d t
he
us
e
of
M
C
D
M
m
e
th
ods
, t
hus
l
im
it
in
g t
he
i
r
c
onne
c
ti
on t
o s
e
r
io
us
ga
m
e
s
a
nd r
e
a
l
-
w
or
ld
a
da
pt
iv
e
ga
m
e
pl
a
y
[
37]
.
A
c
om
pr
e
he
ns
iv
e
s
tu
dy
a
ls
o
s
how
s
th
a
t
A
H
P
is
m
or
e
w
id
e
l
y
us
e
d
in
th
e
in
te
gr
a
ti
on
of
M
C
D
M
m
e
th
ods
th
a
n
P
R
O
M
E
T
H
E
E
,
c
onf
ir
m
in
g
th
e
s
c
a
r
c
it
y
of
r
e
s
e
a
r
c
h
e
xpl
or
in
g
th
e
pot
e
nt
ia
l
of
P
R
O
M
E
T
H
E
E
in
ga
m
e
-
ba
s
e
d
a
d
a
pt
iv
e
s
ys
t
e
m
s
[
39]
.
T
he
P
R
O
M
E
T
H
E
E
m
e
th
od
w
a
s
in
tr
oduc
e
d
to
a
s
s
e
s
s
th
e
le
v
e
l
of
tr
us
t
of
pa
r
ti
c
ip
a
nt
s
in
a
n
ur
ba
n
pl
a
nni
ng
ga
m
e
,
de
m
ons
tr
a
ti
ng
th
e
pot
e
nt
ia
l
of
P
R
O
M
E
T
H
E
E
in
a
s
s
e
s
s
in
g
a
s
pe
c
ts
of
pl
a
ye
r
be
ha
vi
or
[
40]
.
O
n
th
e
ot
he
r
ha
nd,
th
e
c
om
pa
r
is
on
o
f
P
R
O
M
E
T
H
E
E
w
it
h
A
H
P
a
nd
T
O
P
S
I
S
i
n
de
te
r
m
in
in
g
th
e
lo
c
a
ti
on
of
s
ol
a
r
P
V
f
a
r
m
s
w
it
h
th
e
hi
ghe
s
t
s
c
or
e
in
P
R
O
M
E
T
H
E
E
(
0.92
c
om
pa
r
e
d
to
0.85
in
A
H
P
a
nd
0.78
in
T
O
P
S
I
S
)
,
c
onf
ir
m
in
g
th
e
s
upe
r
io
r
it
y
of
th
is
m
e
th
od
in
th
e
I
T
S
c
ont
e
xt
e
v
e
n
th
ough
it
ha
s
not
be
e
n di
r
e
c
tl
y a
ppl
ie
d t
o s
e
r
io
us
ga
m
e
s
[
41]
.
2.1.
S
e
r
io
u
s
gam
e
S
e
r
i
ou
s
g
a
m
e
s
a
r
e
m
e
nt
a
l
le
a
r
n
in
g
th
r
ou
gh
c
o
m
pu
te
r
s
ba
s
e
d
on
c
e
r
t
a
in
r
ul
e
s
,
ut
i
li
z
in
g
e
nt
e
r
t
a
in
m
e
nt
f
or
tr
a
in
in
g
[
42]
,
s
im
ul
a
ti
on
[
4
3]
,
te
a
c
hi
ng
[
44]
a
n
d
l
e
a
r
ni
n
g
pr
o
c
e
s
s
[
4
5]
,
he
a
l
th
w
or
l
d
s
im
ul
a
ti
on
[
4
6]
,
pol
ic
y
s
im
ul
a
ti
on
[
4
7]
,
t
our
is
m
d
e
s
ti
n
a
t
io
n
s
[
48]
,
c
o
m
m
u
ni
c
a
ti
o
n
s
im
u
l
a
ti
on
[
4
9]
,
a
n
d
e
n
vi
r
onm
e
n
t
[
50]
,
[
5
1]
.
S
e
r
io
u
s
ga
m
e
s
h
a
s
b
e
e
n
a
p
pl
i
e
d
in
va
r
io
u
s
f
ie
ld
s
t
o
f
a
c
i
li
t
a
t
e
t
he
te
a
c
hi
ng
a
nd
le
a
r
ni
n
g
pr
oc
e
s
s
a
nd
im
pr
ov
e
l
e
a
r
ni
ng
c
on
c
e
nt
r
a
t
io
n
[
52]
.
T
h
e
m
a
in
be
n
e
f
it
s
of
s
e
r
i
ou
s
g
a
m
e
s
in
c
l
ud
e
pr
ovi
di
n
g
l
e
a
r
ni
n
g
m
o
ti
v
a
t
io
n
[
53]
,
im
pr
o
ve
lo
gi
c
a
l
r
e
a
s
o
ni
ng,
a
n
d
e
nh
a
n
c
e
th
e
in
te
r
a
c
ti
ve
s
i
de
[
54]
.
E
nd
le
s
s
r
un
n
e
r
i
s
r
e
c
o
gni
z
e
d
a
s
on
e
of
t
h
e
pe
r
f
e
c
t
ge
n
r
e
s
in
ga
m
e
b
e
c
a
u
s
e
t
hi
s
g
a
m
e
do
e
s
no
t
c
o
nt
a
in
vi
o
le
nc
e
,
r
a
c
is
m
,
or
p
or
n
ogr
a
ph
y
[
5
5]
.
T
h
e
g
a
m
e
ha
s
m
a
n
y
ob
s
t
a
c
le
s
th
a
t
tr
a
i
n
th
e
pl
a
y
e
r
'
s
c
o
n
c
e
nt
r
a
ti
on
[
56
]
.
T
h
e
go
a
l
of
t
hi
s
pl
a
y
e
r
is
t
o
ge
t
a
s
m
a
ny
s
c
or
e
s
a
s
po
s
s
ib
le
[
57]
.
T
h
e
e
nd
le
s
s
r
unn
e
r
ga
m
e
c
a
n
be
pl
a
y
e
d
b
y
a
ll
a
g
e
s
b
e
c
a
u
s
e
th
e
c
o
nc
e
p
t
i
s
e
a
s
y
t
o
u
nd
e
r
s
t
a
nd
[
5
8]
.
T
hi
s
ty
p
e
of
g
a
m
e
u
s
e
s
2D
or
3
D
c
h
a
r
a
c
t
e
r
m
o
de
ls
t
h
a
t
c
a
n
b
e
pl
a
y
e
d
on m
ob
il
e
p
ho
ne
s
[
42]
a
nd
c
om
p
ut
e
r
s
[
5
9]
.
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
Se
r
io
us
gam
e
i
nt
e
ll
ig
e
nt
t
r
an
s
por
ta
ti
on s
y
s
te
m
ba
s
e
d on int
e
r
ne
t
of
t
hi
ng
s
(
F
r
e
s
y
N
ugr
oho)
179
2.2.
P
R
O
M
E
T
H
E
E
f
or
m
u
la
t
io
n
To
r
a
nk t
he
a
lt
e
r
na
ti
ve
s
(
c
ha
r
a
c
t
e
r
s
)
ba
s
e
d on mul
ti
pl
e
c
r
it
e
r
ia
,
th
e
P
R
O
M
E
T
H
E
E
i
s
a
ppl
ie
d
[
60]
.
‒
P
r
e
f
e
r
e
nc
e
f
unc
ti
on:
f
or
e
a
c
h pa
ir
of
a
lt
e
r
na
ti
ve
s
,
a
a
nd b with cr
it
e
r
io
n k, the
pr
e
f
e
r
e
nc
e
f
unc
ti
on i
s
:
(
,
)
=
(
(
,
)
)
,
(
,
)
=
(
)
−
(
)
(
1)
w
he
r
e
(
)
is
t
he
e
va
lu
a
ti
on of
a
lt
e
r
na
ti
ve
unde
r
c
r
it
e
r
io
n
.
‒
P
r
e
f
e
r
e
nc
e
in
de
x:
t
he
gl
oba
l
pr
e
f
e
r
e
nc
e
i
nde
x of
a
lt
e
r
na
ti
ve
ove
r
is
de
f
in
e
d a
s
:
(
,
)
=
∑
=
1
⋅
(
,
)
,
∑
=
1
=
1
(
2)
w
he
r
e
is
t
he
w
e
ig
ht
of
c
r
it
e
r
io
n
.
‒
P
r
e
f
e
r
e
nc
e
f
unc
ti
on:
f
or
e
a
c
h pa
ir
of
a
lt
e
r
na
ti
ve
s
,
a
nd
w
it
h c
r
it
e
r
io
n
, t
he
pr
e
f
e
r
e
nc
e
f
unc
ti
on i
s
:
+
(
)
=
1
−
1
∑
∈
,
≠
(
,
)
,
−
(
)
=
1
−
1
∑
∈
,
≠
(
,
)
(
3)
‒
P
r
e
f
e
r
e
nc
e
f
unc
ti
on:
f
or
e
a
c
h pa
ir
of
a
lt
e
r
na
ti
ve
s
,
a
a
nd b with cr
it
e
r
io
n k, the
pr
e
f
e
r
e
nc
e
f
unc
ti
on i
s
:
(
)
=
+
(
)
−
−
(
)
(
4)
T
he
a
lt
e
r
na
ti
ve
s
a
r
e
t
he
n r
a
nke
d a
c
c
or
di
ng t
o
(
a
)
, w
he
r
e
hi
ghe
r
va
lu
e
s
i
ndi
c
a
te
be
tt
e
r
r
a
nki
ng.
2.3.
I
n
t
e
ll
ig
e
n
t
t
r
an
s
p
or
t
at
io
n
s
ys
t
e
m
I
T
S
e
n
c
om
p
a
s
s
a
w
id
e
r
a
nge
of
a
ppl
i
c
a
ti
ons
,
jo
ur
n
e
y
ti
m
e
pl
a
n
ni
ng
[
61]
,
tr
a
f
f
i
c
f
lo
w
pr
e
di
c
ti
on
[
62]
,
ve
hi
c
le
s
a
f
e
ty
s
ys
te
m
[
63]
,
a
nd
r
out
e
opt
im
iz
a
ti
on
[
64]
.
I
T
S
de
pl
oym
e
nt
is
e
xpe
c
te
d
to
s
ol
ve
m
obi
li
t
y
m
a
na
ge
m
e
nt
c
ha
ll
e
ng
e
s
[
31]
,
tr
a
di
ti
ona
l
a
nd
e
le
c
tr
ic
v
e
hi
c
le
s
,
a
s
w
e
ll
a
s
e
f
f
e
c
ti
ve
a
nd
lo
w
-
c
os
t
[
37]
.
I
T
S
e
nha
nc
e
m
e
nt
s
c
ont
r
ib
ut
e
to
im
pr
ovi
ng
pr
e
di
c
ti
on
a
c
c
ur
a
c
y,
e
f
f
e
c
ti
ve
ly
s
w
it
c
h
la
ne
s
,
a
nd
m
it
ig
a
ti
ng
th
e
pr
opa
ga
ti
on of
t
r
a
f
f
ic
c
onge
s
ti
on
[
65]
.
2.4.
I
n
t
e
r
n
e
t
of
t
h
in
gs
T
he
l
a
te
s
t
i
nnov
a
ti
on
[
66]
th
a
t
c
a
n
be
u
s
e
d
in
r
e
s
e
a
r
c
h
a
nd
it
c
o
nne
c
t
b
e
twe
e
n
s
e
n
s
or
-
ba
s
e
d
ob
je
c
t
s
to
th
e
I
nt
e
r
n
e
t,
w
e
c
a
l
l
a
s
I
oT
. I
o
T
c
ons
i
s
t
s
of
c
om
m
uni
c
a
ti
on
, da
t
a
, c
om
put
a
ti
on,
a
nd dy
na
m
i
c
s
e
ns
in
g of
obj
e
c
t
s
be
c
a
us
e
t
he
y
a
r
e
s
e
n
s
or
-
b
a
s
e
d
[
67]
.
R
e
s
e
a
r
c
h
e
r
s
pr
e
di
c
t
th
a
t
in
th
e
f
ut
ur
e
w
he
n
I
o
T
is
de
pl
oy
e
d
i
n
l
a
r
ge
num
be
r
s
,
it
w
il
l
ge
n
e
r
a
t
e
dyn
a
m
ic
s
e
n
s
or
-
b
a
s
e
d
d
a
ta
e
ve
r
y s
e
c
o
nd
[
68]
.
T
he
in
f
or
m
a
ti
on
[
6
9]
or
da
t
a
obt
a
in
e
d
is
t
h
e
n
a
na
ly
z
e
d a
n
d r
e
p
or
te
d i
n a
f
or
m
a
t
t
ha
t
i
s
e
a
s
y t
o
vi
s
ua
li
z
e
[
70]
s
o
t
ha
t
i
t
i
s
e
a
s
y t
o
unde
r
s
ta
nd.
2.5.
S
ys
t
e
m
d
e
s
ig
n
T
he
de
s
ig
n
of
s
e
r
io
us
ga
m
e
-
I
nt
e
ll
ig
e
nt
tr
a
ns
por
ta
ti
on
s
ys
te
m
s
(
SG
-
I
T
S
)
c
ons
is
ts
of
f
iv
e
m
a
in
pa
r
ts
w
hi
c
h
a
r
e
C
C
T
V
pl
a
c
e
m
e
nt
,
tr
a
f
f
ic
ja
m
,
ve
hi
c
le
c
ount
in
g,
s
e
r
io
us
ga
m
e
in
f
or
m
a
ti
on
a
nd
S
G
-
I
T
S
.
T
he
c
onne
c
ti
on/
hi
e
r
a
r
c
hy
di
a
gr
a
m
s
how
n
in
F
ig
ur
e
1.
T
he
f
in
it
e
s
t
a
te
m
a
c
hi
ne
(
F
S
M
)
de
s
ig
n
of
S
G
-
I
T
S
,
s
how
n
in
F
ig
ur
e
2,
il
lu
s
tr
a
te
s
th
e
ga
m
e
f
lo
w
a
nd
a
lt
e
r
na
ti
ve
s
e
le
c
ti
ons
de
te
r
m
in
e
d
us
in
g
th
e
P
R
O
M
E
T
H
E
E
m
e
th
od,
w
hi
c
h
e
va
lu
a
te
s
s
ix
c
r
it
e
r
ia
ba
s
e
d
on
pl
a
ye
r
a
c
hi
e
ve
m
e
nt
s
.
P
la
ye
r
s
na
vi
ga
te
f
r
om
th
e
m
a
in
m
e
nu
to
m
a
p
a
nd
c
ha
r
a
c
te
r
s
e
le
c
ti
on
,
w
he
r
e
th
e
s
y
s
te
m
e
it
he
r
r
e
c
om
m
e
nd
s
a
c
h
a
r
a
c
te
r
vi
a
P
R
O
M
E
T
H
E
E
or
pr
oc
e
e
ds
di
r
e
c
tl
y
to
ga
m
e
pl
a
y
ba
s
e
d
on
th
e
pl
a
ye
r
’
s
m
a
nua
l
c
hoi
c
e
.
I
n
th
e
de
ve
lo
pm
e
nt
pr
oc
e
s
s
,
da
ta
pr
e
pa
r
a
ti
on
s
e
r
ve
s
a
s
a
pr
im
a
r
y
pha
s
e
in
bui
ld
in
g
th
e
a
lt
e
r
na
ti
ve
s
e
le
c
ti
on
s
ys
te
m
of
S
G
-
I
T
S
.
I
n
th
is
s
ta
ge
,
th
e
da
ta
r
e
qui
r
e
d
a
r
e
a
lt
e
r
na
ti
ve
s
a
nd c
r
it
e
r
ia
. T
hi
s
da
ta
i
s
r
e
la
te
d t
o
a
nd c
r
uc
ia
l
f
or
de
te
r
m
in
in
g t
he
f
in
a
l
c
a
lc
ul
a
ti
on r
e
s
ul
ts
.
F
ig
ur
e
1. H
ie
r
a
r
c
hy
di
a
gr
a
m
of
t
he
a
na
ly
s
is
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
.
15
, N
o.
1
,
F
e
br
ua
r
y
20
26
:
177
-
190
180
F
ig
ur
e
2. F
S
M
s
ys
te
m
i
n unit
y
2.5.1. Alt
e
r
n
at
iv
e
A
lt
e
r
na
ti
ve
da
ta
c
ont
a
in
s
th
e
c
h
a
r
a
c
te
r
s
pl
a
ye
r
s
w
il
l
us
e
in
th
i
s
S
G
-
I
T
S
ga
m
e
.
I
t
ge
ne
r
a
ll
y
in
c
lu
de
s
s
e
ve
r
a
l
opt
io
ns
w
it
h
a
s
e
t
of
va
lu
e
s
th
a
t
s
uppor
t
pl
a
y
e
r
s
in
w
in
ni
ng
th
e
ga
m
e
.
E
a
c
h
c
ha
r
a
c
te
r
w
il
l
pr
ovi
de
a
uni
que
e
xpe
r
ie
nc
e
a
nd
c
a
n
h
e
lp
pl
a
ye
r
s
ove
r
c
om
e
hi
ghe
r
di
f
f
ic
ul
ty
le
ve
ls
.
T
hi
s
da
ta
c
ont
a
in
s
c
ha
r
a
c
t
e
r
s
w
it
h
pr
ic
e
s
s
um
m
a
r
iz
e
d i
n t
he
T
a
bl
e
2.
T
a
bl
e
2.
A
lt
e
r
na
ti
ve
A
l
t
e
r
na
t
i
ve
P
r
i
c
e
A1
50
…
…
A
14
700
A
15
800
2.5.2.
C
r
it
e
r
ia
T
he
c
r
it
e
r
ia
us
e
d
to
e
v
a
lu
a
te
c
ha
r
a
c
t
e
r
s
in
th
e
ga
m
e
a
r
e
li
s
te
d
in
T
a
bl
e
3,
w
it
h
e
a
c
h
c
r
it
e
r
io
n
w
e
ig
ht
e
d
di
f
f
e
r
e
nt
ly
ba
s
e
d
on
tr
a
f
f
ic
c
ondi
ti
ons
.
O
n
m
a
ps
w
it
h
c
a
lm
tr
a
f
f
ic
,
it
'
s
r
e
c
om
m
e
nde
d
to
lo
ok
f
o
r
c
ha
r
a
c
te
r
s
w
it
h hi
gh
qui
c
kne
s
s
a
nd c
oi
n s
ur
ge
, a
s
t
hi
s
w
il
l
m
a
k
e
c
ol
le
c
ti
ng c
oi
ns
m
or
e
e
f
f
ic
ie
nt
.
O
n m
ode
r
a
te
m
a
ps
, i
t'
s
r
e
c
om
m
e
nde
d t
o l
ook
f
or
c
ha
r
a
c
te
r
s
w
it
h hi
gh
c
oi
n
p
ul
le
r
,
a
s
t
hi
s
w
il
l
ge
ne
r
a
te
m
or
e
c
oi
ns
but
w
it
h
s
li
ght
ly
he
a
vi
e
r
tr
a
f
f
ic
.
O
n
th
e
m
os
t
di
f
f
ic
ul
t
m
a
ps
,
n
a
m
e
ly
b
u
s
y,
it
'
s
c
r
uc
ia
l
to
ha
ve
ba
r
r
ie
r
pr
ot
e
c
ti
on,
a
s
it
w
il
l
pr
ot
e
c
t
pl
a
ye
r
s
f
r
om
hi
gh
-
im
pa
c
t
ve
hi
c
le
i
m
pa
c
ts
.
T
a
bl
e
3. C
r
it
e
r
ia
C
r
i
t
e
r
i
a
M
e
a
ns
M
a
p
Q
ui
e
t
M
ode
r
a
t
e
B
us
y
C1
Q
ui
c
kne
s
s
0.23
0.10
0.12
C2
C
oi
n
pul
l
e
r
0.14
0.36
0.12
C3
J
um
pi
ng
0.14
0.25
0.16
C4
B
a
r
r
i
e
r
0.16
0.08
0.33
C5
C
oi
n
s
ur
ge
0.19
0.10
0.10
C6
S
pr
i
nt
0.15
0.12
0.18
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
Se
r
io
us
gam
e
i
nt
e
ll
ig
e
nt
t
r
an
s
por
ta
ti
on s
y
s
te
m
ba
s
e
d on int
e
r
ne
t
of
t
hi
ng
s
(
F
r
e
s
y
N
ugr
oho)
181
2.6.
G
am
e
d
e
s
ig
n
2.6.1. S
t
or
yl
in
e
T
he
S
G
-
I
T
S
ga
m
e
f
e
a
tu
r
e
s
a
s
to
r
yl
in
e
w
he
r
e
a
c
ha
r
a
c
te
r
m
us
t
r
un
e
ndl
e
s
s
ly
th
r
ough
a
c
onge
s
te
d
ur
ba
n
e
nvi
r
onm
e
nt
.
T
r
a
f
f
ic
c
ondi
ti
ons
a
r
e
c
r
uc
ia
l
be
c
a
us
e
th
e
y
a
f
f
e
c
t
how
w
e
ll
th
e
p
la
ye
r
c
ont
r
ol
s
th
e
i
r
c
ha
r
a
c
te
r
a
nd
in
te
r
a
c
ts
w
it
h
c
oi
ns
a
nd
ot
he
r
it
e
m
s
on
th
e
r
oa
d.
I
ni
ti
a
ll
y,
C
C
T
V
c
a
m
e
r
a
s
c
a
pt
ur
e
im
a
ge
s
of
tr
a
f
f
ic
ja
m
s
on
a
pa
r
ti
c
ul
a
r
r
oa
d,
w
hi
c
h
a
r
e
th
e
n
pr
oc
e
s
s
e
d
us
in
g
P
yt
hon.
T
r
a
f
f
ic
ja
m
s
in
th
e
ga
m
e
dyna
m
ic
a
ll
y
a
da
pt
ba
s
e
d
on
th
e
s
c
a
n
s
.
P
la
ye
r
s
w
it
h
hi
gh
s
c
or
e
s
w
il
l
in
c
r
e
a
s
e
th
e
in
te
n
s
it
y
of
th
e
c
ha
ll
e
nge
a
nd t
he
l
e
ve
l
of
t
r
a
f
f
ic
j
a
m
s
, a
nd vic
e
ve
r
s
a
.
2.6.2. S
t
or
yb
oar
d
T
he
s
to
r
yboa
r
d
pr
ovi
de
s
s
uppor
t
to
th
e
im
pl
e
m
e
nt
a
ti
on
a
s
it
il
lu
s
tr
a
te
s
th
e
c
onc
e
pt
a
nd
s
to
r
yl
in
e
of
th
e
ga
m
e
f
r
om
s
ta
r
t
to
f
in
is
h
in
T
a
bl
e
4.
T
a
bl
e
4
s
ho
w
s
th
a
t
th
e
r
e
a
r
e
s
ix
ty
pe
s
of
s
c
e
ne
m
e
nu
s
:
m
e
nu,
in
s
tr
uc
ti
on,
m
a
p,
c
ha
r
a
c
te
r
,
c
ha
r
r
r
e
c
o
m
m
,
a
nd
g
a
m
e
pl
a
y.
E
a
c
h
m
e
nu
ha
s
it
s
ow
n
f
unc
ti
on.
F
or
e
xa
m
pl
e
,
in
th
e
m
a
p
s
c
e
ne
,
pl
a
ye
r
s
c
a
n
c
hoos
e
a
m
a
p
to
de
te
r
m
in
e
w
he
r
e
t
he
y
w
il
l
pl
a
y.
I
n
th
e
c
ha
r
a
c
te
r
s
c
e
ne
,
th
is
pa
ge
di
s
pl
a
ys
a
li
s
t
of
pl
a
ya
bl
e
c
ha
r
a
c
te
r
s
,
a
nd
pl
a
ye
r
s
c
a
n
c
hoos
e
th
e
r
ol
e
th
e
y
w
a
nt
to
pl
a
y.
T
he
ga
m
e
pl
a
y
s
c
e
ne
is
t
he
m
a
in
s
c
e
n
e
t
o be
pl
a
ye
d.
T
a
bl
e
4. S
to
r
yboa
r
d
S
c
e
ne
E
xpl
a
na
t
i
on
M
e
nu
U
pon
f
i
r
s
t
e
nt
e
r
i
ng
t
he
ga
m
e
,
pl
a
ye
r
s
a
r
e
pr
e
s
e
nt
e
d
w
i
t
h
t
he
m
a
i
n
m
e
nu
c
ons
i
s
t
s
of
s
t
a
r
t
,
hi
gh s
c
or
e
, c
r
e
di
t
a
nd qui
t
.
I
ns
t
r
uc
t
i
on
P
l
a
ye
r
s
c
a
n
f
i
nd
out
how
t
o
c
ont
r
ol
t
he
c
ha
r
a
c
t
e
r
a
nd
us
e
f
e
a
t
ur
e
s
s
uc
h
a
s
m
a
gne
t
s
t
o
ge
t
m
or
e
c
oi
ns
i
n
i
ns
t
r
uc
t
i
on
pa
ge
.
M
a
p
P
l
a
ye
r
s
c
a
n
c
hoos
e
m
a
p t
o de
t
e
r
m
i
ne
w
he
r
e
t
he
pl
a
ye
r
w
i
l
l
pl
a
y.
C
ha
r
a
c
t
e
r
T
hi
s
pa
ge
di
s
pl
a
ys
l
i
s
t
of
pl
a
ya
bl
e
c
ha
r
a
c
t
e
r
s
.
C
ha
r
-
r
e
c
om
m
T
hi
s
pa
ge
w
i
l
l
a
l
l
ow
pl
a
ye
r
t
o ge
t
r
e
c
om
m
e
nda
t
i
on c
ha
r
a
c
t
e
r
.
G
a
m
e
pl
a
y
T
hi
s
i
s
t
he
m
a
i
n ga
m
e
pl
a
y pa
ge
.
2.7.
T
e
s
t
p
la
n
T
he
S
G
-
I
T
S
s
ys
te
m
w
a
s
te
s
te
d
to
e
va
lu
a
te
th
e
us
e
of
th
e
P
R
O
M
E
T
H
E
E
m
e
th
od
f
o
r
c
ha
r
a
c
te
r
r
e
c
om
m
e
nda
ti
ons
ba
s
e
d
on
tr
a
f
f
ic
c
ondi
ti
ons
de
r
iv
e
d
f
r
om
C
C
T
V
im
a
ge
a
n
a
ly
s
is
.
C
C
T
V
f
unc
ti
ons
a
s
a
c
ont
e
xt
ua
l
vi
s
ua
l
e
le
m
e
nt
r
a
th
e
r
th
a
n
pe
r
f
or
m
in
g
r
e
a
l
-
ti
m
e
r
e
c
or
di
ng,
w
hi
le
im
a
ge
pr
oc
e
s
s
in
g
in
P
yt
hon
c
la
s
s
if
ie
s
tr
a
f
f
ic
le
ve
ls
in
to
bus
y,
m
ode
r
a
te
,
a
nd
qui
e
t
c
a
te
go
r
ie
s
.
G
a
m
e
e
xpe
r
ts
us
e
r
a
ti
ngs
to
de
te
r
m
in
e
w
he
th
e
r
a
c
ha
r
a
c
te
r
m
e
e
ts
th
e
c
r
it
e
r
ia
f
or
r
e
c
om
m
e
nd
e
d
g
a
m
e
pl
a
y.
M
e
a
nw
hi
le
,
ge
ne
r
a
l
u
s
e
r
s
pr
ovi
de
f
e
e
dba
c
k
th
r
ough
a
G
oogl
e
F
or
m
s
-
ba
s
e
d
s
ur
ve
y.
T
he
c
o
m
bi
ne
d
r
e
s
ul
ts
f
r
om
s
ys
te
m
te
s
ti
ng,
e
xpe
r
t
e
va
lu
a
ti
on,
a
nd
us
e
r
f
e
e
dba
c
k
w
e
r
e
a
na
ly
z
e
d
to
de
te
r
m
in
e
th
e
e
f
f
e
c
ti
ve
ne
s
s
of
th
e
P
R
O
M
E
T
H
E
E
in
te
gr
a
ti
on
a
nd guide
f
ur
th
e
r
de
ve
lo
pm
e
nt
of
S
G
-
I
T
S
.
3.
R
E
S
U
L
T
S
A
N
D
D
I
S
C
U
S
S
I
O
N
3.1.
S
ys
t
e
m
t
e
s
t
in
g r
e
s
u
lt
s
T
he
c
a
lc
ul
a
ti
ons
a
r
e
ta
ke
n
f
r
om
C
C
T
V
s
c
a
n
s
a
nd
m
a
p
c
la
s
s
if
ic
a
ti
on.
T
he
n,
th
e
P
R
O
M
E
T
H
E
E
c
a
lc
ul
a
ti
on i
m
pl
e
m
e
nt
a
ti
on i
s
pl
a
c
e
d i
n a
r
e
c
om
m
e
nda
ti
on butt
on i
n t
he
c
ha
r
a
c
te
r
s
e
le
c
ti
on me
nu. T
he
r
e
s
ul
ts
a
r
e
i
nt
e
gr
a
te
d i
nt
o t
he
uni
ty
e
nvi
r
onm
e
nt
s
o t
ha
t
th
e
y c
a
n be
pl
a
ye
d by pla
ye
r
s
.
3.1.1. I
m
age
p
r
o
c
e
s
s
in
g al
gor
it
h
m
t
e
s
t
in
g
T
e
s
t
da
ta
d
e
r
iv
e
d
f
r
om
C
C
T
V
vi
de
o
us
in
g
P
yt
hon
w
il
l
obt
a
in
ve
hi
c
le
de
ns
it
y
c
la
s
s
if
ic
a
ti
on
w
it
h
li
ght
,
m
e
di
um
,
a
nd
bus
y
tr
a
f
f
ic
c
a
te
gor
ie
s
.
D
e
te
c
ti
on
a
c
c
ur
a
c
y
is
done
by
c
om
pa
r
in
g
th
e
num
be
r
of
de
te
c
te
d
ve
hi
c
le
s
w
it
h
th
e
num
be
r
of
gr
ound
tr
ut
h
ve
hi
c
le
s
,
a
nd
th
e
r
e
s
ul
ts
a
r
e
s
to
r
e
d
in
th
e
da
ta
ba
s
e
.
T
he
num
be
r
of
ve
hi
c
le
s
c
a
n
be
s
e
e
n
in
r
e
pr
e
s
e
nt
in
g
th
e
tr
a
f
f
ic
c
a
te
gor
y
(
F
ig
ur
e
3)
.
D
e
te
c
ti
on
pe
r
f
o
r
m
a
nc
e
is
a
ls
o
e
va
lu
a
te
d
us
in
g
a
c
onf
us
io
n
m
a
tr
ix
w
it
h
T
P
=
3,
F
P
=
2,
F
N
=
2,
a
nd
T
N
=
0,
r
e
s
ul
ti
ng
in
pr
e
c
is
io
n=
0.60,
r
e
c
a
ll
=
0.60
,
a
nd
F1
-
s
c
or
e
=
0.60.
W
it
h
th
e
s
e
r
e
s
ul
ts
,
it
c
a
n
be
e
xp
e
c
te
d
th
a
t
a
n
a
lg
or
it
hm
c
a
n
id
e
nt
if
y
ve
hi
c
le
s
c
or
r
e
c
tl
y
but
th
e
r
e
is
s
ti
ll
a
s
li
ght
ove
r
e
s
ti
m
a
ti
on
or
unde
r
e
s
ti
m
a
ti
on
th
a
t
s
li
ght
ly
a
f
f
e
c
ts
th
e
c
la
s
s
if
ic
a
ti
on
a
c
c
ur
a
c
y.
E
ve
n
s
o, t
he
pe
r
f
or
m
a
nc
e
i
s
s
ti
ll
a
c
c
e
pt
a
bl
e
.
3.1.2. P
R
O
M
E
T
H
E
E
m
e
t
h
od
i
m
p
le
m
e
n
t
at
io
n
t
e
s
t
in
g
T
he
P
R
O
M
E
T
H
E
E
m
e
th
od
te
s
ti
ng
is
c
a
lc
ul
a
te
d
f
r
om
a
ll
c
ha
r
a
c
te
r
s
,
w
it
h
c
ha
r
a
c
te
r
r
a
nki
ngs
a
nd
ne
t
f
lo
w
va
lu
e
s
a
c
c
or
di
ng
to
tr
a
f
f
ic
c
ondi
ti
ons
.
T
a
bl
e
5
s
pe
c
if
ic
a
ll
y
pr
e
s
e
nt
s
th
e
c
ha
r
a
c
te
r
s
ki
ll
va
lu
e
d
a
ta
s
e
t
.
T
a
bl
e
6 s
how
s
t
he
w
e
ig
ht
e
d
c
r
it
e
r
ia
pr
oc
e
s
s
e
d t
hr
ough the
P
R
O
M
E
T
H
E
E
f
or
m
ul
a
ti
on.
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
.
15
, N
o.
1
,
F
e
br
ua
r
y
20
26
:
177
-
190
182
F
ig
ur
e
3. C
C
T
V
vi
de
o
T
a
bl
e
5. M
e
th
od
te
s
ti
ng
C
r
i
t
e
r
i
a
A
l
t
e
r
na
t
i
ve
A1
A2
A3
A4
A5
A6
A7
A8
A9
A
10
A
11
A
12
A
13
A
14
A
15
C1
2
1.5
2
2
1.5
2
2
3
2
2
2
2
2
2
2
C2
3
1
2
2
3
2
2
2
2.5
2
4
3
3
4
5
C3
1
4
2
3
1
0.5
0.5
2
2.5
3.5
2
3
4
3
5
C4
3
2
1
1
2
0
0
3.5
2
2
4
2
2
2
4
C5
0
1
3
2
1
5
5
1
3.5
3.5
1
4
3
2
3
C6
3
2
2
2
3
1.5
1.5
3.5
2
2
4
3
3
3.5
5
T
a
bl
e
6
pr
e
s
e
nt
s
th
e
r
e
s
ul
ti
ng
r
a
nki
ngs
,
w
he
r
e
hi
ghe
r
ne
t
f
lo
w
va
lu
e
s
in
di
c
a
t
e
s
upe
r
io
r
c
ha
r
a
c
te
r
s
.
I
n
th
e
90
-
c
oi
n
s
c
e
na
r
io
,
th
e
pr
oc
e
s
s
li
m
it
s
th
e
c
hoi
c
e
s
to
s
ix
f
e
a
s
ib
le
c
ha
r
a
c
te
r
s
(
A
1
–
A
6)
,
w
hi
c
h
a
r
e
th
e
n
r
a
nke
d
us
in
g
P
R
O
M
E
T
H
E
E
to
id
e
nt
if
y
th
e
be
s
t
c
hoi
c
e
f
or
e
a
c
h
tr
a
f
f
ic
c
ondi
ti
on.
T
he
r
e
s
ul
ts
in
di
c
a
te
th
a
t
e
a
c
h
a
lt
e
r
na
ti
ve
e
xhi
bi
t
s
di
s
ti
nc
t
s
tr
e
ngt
hs
unde
r
di
f
f
e
r
e
nt
tr
a
f
f
ic
c
ondi
ti
ons
:
A
2
pe
r
f
or
m
s
be
s
t
in
bus
y
s
c
e
na
r
io
s
,
w
hi
le
A
4
m
a
in
ta
in
s
c
ons
i
s
te
nt
s
ta
bi
li
ty
a
c
r
os
s
a
ll
c
ondi
ti
ons
.
I
n
c
ont
r
a
s
t,
A
1
a
nd
A
5
pe
r
f
or
m
w
e
a
ke
r
unde
r
qui
e
t
a
nd
m
ode
r
a
te
tr
a
f
f
ic
,
a
nd
A
6
e
x
c
e
ls
onl
y
in
lo
w
-
tr
a
f
f
ic
s
it
ua
ti
ons
.
O
ve
r
a
ll
,
A
4
a
nd
A
2 a
r
e
th
e
m
os
t
a
da
pt
iv
e
opt
io
ns
,
e
f
f
e
c
ti
ve
ly
m
a
tc
hi
ng
va
r
yi
ng
c
ong
e
s
ti
on
le
ve
ls
.
T
he
r
a
nki
ng
di
s
tr
ib
ut
io
n
c
le
a
r
ly
s
e
pa
r
a
te
s
hi
gh
a
nd
lo
w
pe
r
f
or
m
in
g
a
lt
e
r
na
ti
ve
s
,
pr
ovi
di
ng
us
e
f
ul
in
s
ig
ht
f
or
r
e
c
om
m
e
ndi
ng
c
ha
r
a
c
te
r
s
ba
s
e
d
on a
va
il
a
bl
e
r
e
s
our
c
e
s
(
pl
a
ye
r
c
oi
ns
)
a
nd s
im
ul
a
te
d t
r
a
f
f
ic
c
ond
it
io
ns
.
T
a
bl
e
6. P
R
O
M
E
T
H
E
E
ne
t
f
lo
w
r
a
nki
ng r
e
s
ul
ts
f
or
c
ha
r
a
c
te
r
unde
r
di
f
f
e
r
e
nt
t
r
a
f
f
ic
c
ondi
ti
ons
A
l
t
e
r
na
t
i
ve
R
e
s
ul
t
Q
ui
e
t
M
ode
r
a
t
e
B
us
y
A1
-
0.38
-
0.32
0.31
A2
0.06
0.16
0.53
A3
0.22
0.12
-
0.13
A4
0.26
0.67
0.15
A5
-
0.51
-
0.38
-
0.25
A6
0.35
-
0.25
-
0.61
T
a
bl
e
7 s
how
s
a
s
ig
ni
f
ic
a
nt
di
f
f
e
r
e
nc
e
i
n s
c
or
e
s
be
twe
e
n pl
a
ye
r
s
w
ho f
ol
lo
w
e
d t
he
r
e
c
om
m
e
nda
ti
ons
a
nd
th
os
e
w
ho
di
dn'
t
a
f
te
r
two
m
in
ut
e
s
of
g
a
m
e
pl
a
y.
I
n
th
i
s
c
a
s
e
,
pl
a
ye
r
1
c
hos
e
a
lt
e
r
na
ti
ve
1
on
a
qui
e
t
m
a
p,
e
ve
n
th
ough
th
e
s
ys
te
m
ha
d
r
e
c
om
m
e
nde
d
a
lt
e
r
na
ti
ve
6.
T
he
r
e
s
ul
t
w
a
s
poor
c
ha
r
a
c
te
r
pe
r
f
o
r
m
a
nc
e
a
nd
a
lo
w
e
r
s
c
or
e
. T
hi
s
g
a
p i
s
due
t
o A
6 of
f
e
r
in
g a
va
lu
e
of
5 a
nd A
1
la
c
ki
ng a
c
oi
n boos
t.
T
a
bl
e
7. C
om
pa
r
is
on of
pl
a
ye
r
s
c
or
e
s
w
it
h a
nd w
it
hout
P
R
O
M
E
T
H
E
E
M
a
p
R
e
c
om
m
e
nde
d
c
ha
r
a
c
t
e
r
P
l
a
ye
r
S
c
or
e
w
i
t
h P
R
O
M
E
T
H
E
E
S
c
or
e
w
i
t
hout
P
R
O
M
E
T
H
E
E
Q
ui
e
t
A6
P1
120
75
P2
115
80
P3
118
70
M
ode
r
a
t
e
A4
P1
140
95
P2
138
100
P3
142
90
B
us
y
A2
P1
160
110
P2
155
105
P3
158
100
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
Se
r
io
us
gam
e
i
nt
e
ll
ig
e
nt
t
r
an
s
por
ta
ti
on s
y
s
te
m
ba
s
e
d on int
e
r
ne
t
of
t
hi
ng
s
(
F
r
e
s
y
N
ugr
oho)
183
3.2. E
xp
e
r
t
t
e
s
t
in
g r
e
s
u
lt
s
S
ys
te
m
te
s
ti
ng
in
vol
ve
d
e
xp
e
r
t
r
e
s
ponde
nt
s
w
it
h
pr
of
e
s
s
io
na
l
ba
c
kgr
ounds
in
ga
m
e
de
ve
lo
pm
e
nt
a
nd
de
s
ig
n.
E
va
lu
a
ti
on
w
a
s
c
onduc
t
e
d
us
in
g
th
e
ga
m
e
de
s
ig
n
f
a
c
to
r
que
s
ti
onna
ir
e
(
G
D
F
Q
)
(
T
a
bl
e
8)
,
w
hi
c
h
a
s
s
e
s
s
e
s
e
ig
ht
ke
y
di
m
e
ns
io
n
s
:
ga
m
e
goa
ls
,
ga
m
e
m
e
c
ha
ni
s
m
,
in
te
r
a
c
ti
on,
f
r
e
e
dom
,
s
e
ns
a
ti
on,
ga
m
e
va
lu
e
,
c
ha
ll
e
nge
,
a
nd
f
lo
w
.
E
a
c
h
f
a
c
to
r
c
om
pr
is
e
s
one
to
f
our
s
p
e
c
if
ic
a
s
s
e
s
s
m
e
nt
it
e
m
s
[
71]
.
T
h
e
a
n
s
w
e
r
f
r
e
que
nc
y
of
e
ig
ht
ke
y
di
m
e
ns
io
ns
s
how
n
in
F
ig
ur
e
4,
a
s
a
n
e
xa
m
pl
e
,
f
or
f
r
e
e
dom
,
a
ll
of
th
e
r
e
s
ponde
nt
a
gr
e
e
s
,
f
or
in
te
r
a
c
ti
on,
a
bout
45%
r
e
s
ponde
nt
s
a
gr
e
e
a
nd
a
bout
65%
di
s
a
gr
e
e
.
E
xpe
r
t
e
va
lu
a
ti
ons
yi
e
ld
e
d
a
n
ove
r
a
ll
a
ve
r
a
ge
s
c
or
e
of
4.23/5.
T
he
ga
m
e
'
s
m
e
c
h
a
ni
c
s
r
e
c
e
iv
e
d
th
e
hi
ghe
s
t
r
a
ti
ng
(
4.5)
f
or
it
s
c
ons
i
s
te
nc
y
w
it
h
th
e
c
hos
e
n
ge
nr
e
.
T
he
s
e
n
s
a
ti
on
a
s
p
e
c
t
a
c
hi
e
ve
d
a
r
a
ti
ng
of
4.4
f
or
it
s
e
nga
gi
ng
vi
s
ua
l
in
te
r
f
a
c
e
.
H
ow
e
ve
r
,
opt
io
ns
f
or
im
pr
ovi
ng
pl
a
ye
r
c
ont
r
ol
a
r
e
s
ti
ll
pr
ovi
de
d.
T
h
e
s
e
r
e
s
ul
ts
in
di
c
a
te
th
a
t
S
G
-
I
T
S
m
e
e
ts
th
e
m
a
in
s
ta
nda
r
ds
i
n ga
m
e
s
tr
uc
tu
r
e
a
nd r
e
qui
r
e
s
s
li
ght
i
m
pr
ove
m
e
nt
s
i
n f
le
xi
bl
e
pl
a
ye
r
c
ont
r
ol
.
T
a
bl
e
8. G
a
m
e
de
s
ig
n f
a
c
to
r
que
s
ti
onna
ir
e
N
o.
Q
ue
s
t
i
on
1
G
a
m
e
goa
l
s
‒
T
hi
s
ga
m
e
f
e
a
t
ur
e
s
w
e
l
l
-
de
f
i
ne
d t
a
s
ks
a
nd
s
t
a
ge
s
‒
I
know
m
y obj
e
c
t
i
ve
i
n t
he
ga
m
e
‒
I
pr
e
f
e
r
t
o a
c
hi
e
ve
a
nd ge
t
be
s
t
r
e
s
ul
t
i
n ga
m
e
2
G
a
m
e
m
e
c
ha
ni
s
m
‒
T
he
ga
m
e
pl
a
y i
s
a
c
c
or
da
nc
e
w
i
t
h t
he
g
e
nr
e
c
a
r
r
i
e
d
‒
T
he
r
ul
e
s
of
t
he
ga
m
e
a
r
e
e
a
s
y t
o unde
r
s
t
a
nd
‒
I
l
i
ke
t
he
ga
m
e
pl
a
y i
n t
he
ga
m
e
3
I
nt
e
r
a
c
t
i
on
‒
I
nt
e
r
a
c
t
i
on i
n pl
a
yi
ng t
he
ga
m
e
i
s
f
un. G
a
m
e
pl
a
y a
nd c
ont
r
ol
s
a
r
e
c
l
e
a
r
a
nd e
a
s
y t
o unde
r
s
t
a
nd
‒
In
-
ga
m
e
he
l
p a
nd a
dvi
c
e
f
e
a
t
ur
e
s
a
r
e
c
l
e
a
r
a
nd e
a
s
y t
o unde
r
s
t
a
nd
‒
I
nt
e
r
a
c
t
i
on i
n ga
m
e
pl
a
y i
s
f
un
4
F
r
e
e
dom
‒
G
a
m
e
c
ha
r
a
c
t
e
r
s
c
a
n b
e
e
a
s
i
l
y c
ont
r
ol
l
e
d by pl
a
ye
r
s
5
S
e
ns
a
t
i
on
‒
T
he
c
ol
or
s
a
nd l
a
yout
of
t
he
i
nt
e
r
f
a
c
e
c
a
ught
m
y e
ye
‒
T
he
i
c
ons
a
nd f
unc
t
i
ons
a
r
e
c
l
e
a
r
a
nd i
nt
ui
t
i
ve
‒
T
he
gr
a
phi
c
s
a
nd s
ound i
n t
he
ga
m
e
a
r
e
a
bund
a
nt
6
G
a
m
e
v
a
l
ue
‒
I
w
a
nt
t
o ge
t
t
he
hi
ghe
s
t
s
c
or
e
‒
SG
-
I
T
S
c
ont
e
nt
be
c
om
e
s
i
nt
e
r
e
s
t
i
ng w
he
n a
dde
d t
o t
he
ga
m
e
.
7
C
ha
l
l
e
nge
‒
I
f
e
e
l
c
ha
l
l
e
nge
d t
o c
om
pl
e
t
e
t
he
ga
m
e
‒
I
c
a
n w
i
n t
he
ga
m
e
e
a
s
i
l
y
‒
I
w
a
nt
t
o pl
a
y t
he
a
dva
nc
e
d ve
r
s
i
on of
t
he
ga
m
e
F
ig
ur
e
4. T
e
s
t
r
e
s
ul
ts
by g
a
m
e
e
xpe
r
ts
F
or
th
e
G
D
F
Q
,
a
ll
e
xpe
r
t
obs
e
r
va
ti
ons
(
10
e
xpe
r
ts
×
22
it
e
m
s
=
220
r
a
ti
ngs
)
a
s
th
e
s
a
m
pl
e
.
A
n
a
lt
e
r
na
ti
ve
w
oul
d
be
to
te
s
t
th
e
a
v
e
r
a
ge
p
e
r
e
xpe
r
t
(
n
=
10)
.
H
ow
e
ve
r
,
tr
e
a
ti
ng
e
a
c
h
it
e
m
r
a
ti
ng
a
s
a
n
obs
e
r
va
ti
on
is
of
te
n
a
ppl
ie
d
w
he
n
th
e
goa
l
is
to
te
s
t
w
he
th
e
r
t
he
ove
r
a
ll
m
e
a
n
r
a
ti
ng
is
s
ig
ni
f
ic
a
nt
ly
hi
ghe
r
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
.
15
, N
o.
1
,
F
e
br
ua
r
y
20
26
:
177
-
190
184
th
a
n
th
e
ne
ut
r
a
l
va
lu
e
,
s
how
n
in
T
a
bl
e
9.
C
om
pa
r
e
=
29
.
99
w
it
h
≈
1
.
645
.
S
in
c
e
≫
,
w
e
r
e
je
c
t
0
a
t
=
0
.
05
.
T
he
m
e
a
n
G
D
F
Q
r
a
ti
n
g
(
4.
19)
i
s
s
t
a
ti
s
ti
c
a
l
ly
f
a
r
hi
gh
e
r
th
a
n
ne
u
tr
a
l
be
nc
hm
a
r
k
of
3 (
p
≪
0
.00
1)
.
T
hi
s
i
n
di
c
a
te
s
th
a
t
e
x
p
e
r
t
s
e
va
l
ua
te
d
ga
m
e
d
e
s
ig
n
f
a
c
to
r
s
ve
r
y
po
s
it
iv
e
ly
.
3.3. Us
ab
il
it
y t
e
s
t
in
g
U
s
a
bi
li
ty
te
s
ti
ng
w
a
s
c
onduc
te
d
w
it
h
50
pl
a
ye
r
s
to
m
e
a
s
ur
e
e
a
s
e
of
us
e
,
pl
a
ye
r
s
a
ti
s
f
a
c
ti
on,
a
nd
ove
r
a
ll
us
a
bi
li
ty
of
th
e
S
G
-
I
T
S
pr
o
to
ty
pe
.
T
he
s
ys
te
m
us
a
bi
li
ty
s
c
a
le
(
S
U
S
)
w
a
s
e
m
pl
oye
d
w
it
h
a
1
–
5
L
ik
e
r
t
s
c
a
le
.
E
a
c
h
of
th
e
te
n
qu
e
s
ti
ons
li
s
te
d
in
T
a
bl
e
10.
B
a
s
e
d
on
T
a
bl
e
10,
th
e
S
G
-
I
T
S
pr
ot
ot
ype
a
c
hi
e
ve
d
a
n
a
ve
r
a
ge
S
U
S
s
c
or
e
of
78.95,
w
hi
c
h
is
c
a
te
gor
iz
e
d
a
s
good
us
a
bi
li
ty
(
70
–
80)
a
nd
a
ppr
oa
c
hi
ng
ve
r
y
good
(
>
80)
.
T
hi
s
in
di
c
a
te
s
th
a
t
m
os
t
pl
a
ye
r
s
f
ound
th
e
ga
m
e
e
a
s
y
to
ope
r
a
te
a
nd
e
nj
oya
bl
e
.
P
os
it
iv
e
i
te
m
s
s
c
or
e
d
a
bove
4.5,
r
e
f
le
c
ti
ng
s
tr
ong
us
e
r
e
nga
ge
m
e
nt
,
w
hi
le
ne
ga
ti
ve
it
e
m
s
s
c
or
e
d
be
lo
w
2.0,
in
di
c
a
ti
ng
m
in
im
a
l
ope
r
a
ti
ona
l
di
f
f
ic
ul
ty
a
s
i
ll
us
tr
a
te
d i
n F
ig
ur
e
5.
T
a
bl
e
9. O
ne
-
s
a
m
pl
e
t
-
te
s
t
G
D
F
Q
I
t
e
m
V
a
l
ue
D
a
t
a
N
um
be
r
of
r
e
s
ponde
nt
s
:
220
S
a
m
pl
e
m
e
a
n:
ˉ
4.1909
S
a
m
pl
e
s
t
a
nda
r
d de
vi
a
t
i
on:
0.5890
B
e
nc
hm
a
r
k (
nul
l
hypot
he
s
i
s
)
:
0
3
S
i
gni
f
i
c
a
nc
e
l
e
ve
l
:
0.05
H
ypot
he
s
e
s
0
:
3
:
>
3
D
e
gr
e
e
s
of
f
r
e
e
dom
=
−
1
=
220
−
1
=
219
C
r
i
t
i
c
a
l
va
l
ue
0
.
05
,
219
≈
1
.
645
C
om
put
a
t
i
on
=
ˉ
−
0
/
√
=
4
.
1
9
0
9
−
3
0
.
5
8
9
0
/
√
2
2
0
=
1
.
1
9
0
9
0
.
0
3
9
7
≈
29
.
99
T
a
bl
e
10. S
U
S
que
s
ti
ons
No
Q
ue
s
t
i
on
1
I
a
m
i
nt
e
r
e
s
t
e
d i
n pl
a
yi
ng ga
m
e
a
ga
i
n
2
I
f
ound i
t
i
s
qui
t
e
c
om
pl
i
c
a
t
e
d t
o us
e
t
he
ga
m
e
3
T
he
ga
m
e
f
e
e
l
s
us
e
r
-
f
r
i
e
ndl
y a
nd e
a
s
y t
o ope
r
a
t
e
4
I
ne
e
de
d he
l
p f
r
om
a
not
he
r
pe
r
s
on or
t
e
c
hni
c
i
a
n w
hi
l
e
pl
a
yi
ng
5
T
he
f
e
a
t
ur
e
s
i
n t
he
ga
m
e
w
or
k a
s
e
xpe
c
t
e
d
6
I
f
ound s
om
e
a
s
pe
c
t
s
of
t
he
ga
m
e
i
nc
on
s
i
s
t
e
nt
7
I
be
l
i
e
ve
ot
he
r
s
c
a
n e
a
s
i
l
y f
i
gur
e
out
how
t
o pl
a
y t
he
ga
m
e
8
T
he
ga
m
e
f
e
l
t
c
onf
us
i
ng t
o m
e
9
I
ha
d no di
f
f
i
c
ul
t
y us
i
ng t
he
ga
m
e
10
I
t
t
ook m
e
s
om
e
t
i
m
e
t
o a
da
pt
be
f
or
e
I
f
ul
l
y unde
r
s
t
ood how
t
o us
e
t
he
ga
m
e
.
F
ig
ur
e
5. U
s
a
bi
li
ty
t
e
s
ti
ng r
e
s
ul
ts
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
Se
r
io
us
gam
e
i
nt
e
ll
ig
e
nt
t
r
an
s
por
ta
ti
on s
y
s
te
m
ba
s
e
d on int
e
r
ne
t
of
t
hi
ng
s
(
F
r
e
s
y
N
ugr
oho)
185
T
o va
li
da
te
t
he
S
U
S
s
ta
ti
s
ti
c
a
ll
y, a
one
-
s
id
e
d (
r
ig
ht
-
ta
il
e
d)
t
e
s
t
w
a
s
c
onduc
te
d
. T
h
e
hypothe
s
is
unde
r
e
xa
m
in
a
ti
on
w
a
s
w
h
e
th
e
r
th
e
s
a
m
pl
e
m
e
a
n
s
c
or
e
is
gr
e
a
te
r
t
ha
n
th
e
be
nc
hm
a
r
k.
B
a
s
e
d
on
th
e
te
s
t
d
a
ta
in
T
a
bl
e
11.
D
e
c
i
s
io
n
r
ul
e
c
om
pa
r
e
s
:
c
a
l
c
ul
a
t
e
d
=
6
.
52
w
it
h
c
r
i
t
i
c
a
l
=
1
.
677
.
S
in
c
e
c
a
l
c
ul
a
t
e
d
>
c
r
i
t
i
c
a
l
,
w
e
r
e
je
c
t
0
pa
da
=
0
.
05
.
C
onc
lu
s
io
n:
th
e
r
e
is
s
tr
ong
s
ta
ti
s
ti
c
a
l
e
vi
de
nc
e
th
a
t
th
e
m
e
a
n
S
U
S
s
c
or
e
is
gr
e
a
te
r
th
a
n
68
(
p <
0.05)
. I
n ot
he
r
w
or
ds
, t
he
s
ys
te
m
’
s
us
a
bi
li
ty
i
s
s
ig
ni
f
ic
a
nt
ly
a
bove
t
he
“
a
c
c
e
pt
a
bl
e
”
b
e
nc
hm
a
r
k.
T
a
bl
e
11. One
-
s
a
m
pl
e
t
-
te
s
t
S
U
S
I
t
e
m
V
a
l
ue
D
a
t
a
N
um
be
r
of
r
e
s
ponde
nt
s
:
50
S
a
m
pl
e
m
e
a
n:
ˉ
78.95
S
a
m
pl
e
s
t
a
nda
r
d de
vi
a
t
i
on:
11.8783
B
e
nc
hm
a
r
k (
nul
l
hypot
he
s
i
s
)
:
0
68
S
i
gni
f
i
c
a
nc
e
l
e
ve
l
:
0.05
H
ypot
he
s
e
s
0
:
68
:
>
68
D
e
gr
e
e
s
of
f
r
e
e
dom
=
−
1
=
50
−
1
=
49
C
r
i
t
i
c
a
l
va
l
ue
0
.
05
,
49
≈
1
.
677
C
om
put
a
t
i
on
=
ˉ
−
0
/
√
=
78
.
95
−
68
11
.
8
7
8
3
/
√
50
=
10
.
95
1
.
6
7
9
≈
6
.
52
3.4.
C
om
p
ar
is
on
w
it
h
e
xi
s
t
in
g w
or
k
s
I
n
pyt
hon
-
ba
s
e
d
ve
hi
c
le
de
te
c
ti
on,
th
e
de
te
c
te
d a
c
c
ur
a
c
y
i
s
84.5%
a
c
r
os
s
th
r
e
e
tr
a
f
f
ic
de
ns
it
y
le
ve
ls
,
w
it
h
a
n
a
ve
r
a
ge
pr
oc
e
s
s
in
g
ti
m
e
of
a
bout
one
s
e
c
ond
pe
r
f
r
a
m
e
.
H
ow
e
ve
r
,
th
is
r
e
s
ul
t
is
s
ti
ll
lo
w
e
r
th
a
n
th
e
Y
O
L
O
v4
–
D
e
e
pS
O
R
T
m
od
e
l
w
it
h
87.98%
w
hi
c
h
de
te
c
ts
13
t
ype
s
of
ve
hi
c
le
s
[
72]
.
P
r
io
r
it
iz
in
g
pr
oc
e
s
s
in
g
s
pe
e
d
a
nd
s
m
oot
h
ga
m
e
in
te
gr
a
ti
on
a
r
e
th
e
m
a
in
obj
e
c
ti
ve
s
in
th
is
s
tu
dy.
M
e
a
nw
hi
le
,
th
e
Y
O
L
O
–
O
pe
nC
V
r
e
a
l
-
ti
m
e
de
te
c
ti
on
m
ode
l
a
ppr
oa
c
h
c
a
n
s
uppor
t
dyn
a
m
ic
ga
m
e
di
f
f
ic
ul
ty
a
da
pt
a
ti
on
[
73]
.
T
he
a
da
pt
a
ti
on
r
e
s
ponds
in
a
bout
one
s
e
c
ond
a
nd
i
s
c
om
pa
r
a
bl
e
to
f
lo
w
-
s
ta
te
-
ba
s
e
d
[
74]
a
nd
f
uz
z
y
lo
gi
c
–
ba
s
e
d
[
75]
di
f
f
ic
ul
ty
a
dj
us
tm
e
nt
a
ppr
oa
c
he
s
.
I
ts
m
a
in
s
tr
e
ngt
h
li
e
s
in
le
ve
r
a
gi
ng
r
e
a
l
-
w
or
ld
t
r
a
f
f
ic
da
ta
,
m
a
ki
ng
in
-
ga
m
e
c
ha
ll
e
nge
s
c
ont
e
xt
ua
ll
y
r
e
le
va
nt
.
H
ow
e
v
e
r
,
s
ys
te
m
pe
r
f
or
m
a
nc
e
de
pe
nds
on
C
C
T
V
qua
li
ty
a
nd
m
a
y
e
xpe
r
ie
nc
e
l
a
te
nc
y du
e
t
o ne
twor
k di
s
r
upt
io
ns
or
de
te
c
ti
on de
gr
a
da
ti
on.
3.5.
D
is
c
u
s
s
io
n
T
he
r
e
s
ul
ts
of
im
a
ge
pr
oc
e
s
s
in
g
s
how
th
a
t
th
e
s
ys
te
m
is
a
bl
e
to
de
te
c
t
ve
hi
c
le
s
a
nd
c
la
s
s
if
y
tr
a
f
f
ic
w
it
h
f
a
ir
ly
good
a
c
c
ur
a
c
y.
w
it
h
a
lo
w
num
be
r
of
f
a
ls
e
pos
it
iv
e
s
a
nd
f
a
l
s
e
ne
g
a
ti
ve
s
,
th
is
s
how
s
th
a
t
th
e
a
lg
or
it
hm
a
ls
o
r
e
m
a
in
s
s
ta
bl
e
in
va
r
io
us
c
ondi
ti
ons
.
T
he
P
R
O
M
E
T
H
E
E
-
ba
s
e
d
c
ha
r
a
c
te
r
r
e
c
om
m
e
nda
ti
on
s
ys
te
m
pr
oduc
e
s
a
b
a
la
nc
e
d
r
a
nki
ng
a
nd
is
c
ons
is
t
e
nt
w
it
h
th
e
ga
m
e
'
s
obj
e
c
ti
ve
s
.
B
a
s
e
d
on
e
xpe
r
t
f
e
e
dba
c
k
a
s
s
e
s
s
m
e
nt
s
of
4.23
out
of
5,
a
nd
th
e
S
U
S
te
s
t,
th
e
s
ys
te
m
obt
a
in
e
d
a
n
a
v
e
r
a
ge
s
c
or
e
of
78.96.
T
he
s
e
r
e
s
ul
ts
in
di
c
a
te
t
ha
t
th
e
S
G
-
I
T
S
ga
m
e
ha
s
good us
a
bi
li
ty
, e
f
f
e
c
ti
ve
f
unc
ti
ons
, a
nd i
s
pos
it
iv
e
ly
r
e
c
e
iv
e
d by us
e
r
s
.
4.
C
O
N
C
L
U
S
I
O
N
A
N
D
F
U
T
U
R
E
WORK
T
hi
s
s
tu
dy
ha
s
s
uc
c
e
s
s
f
ul
ly
in
te
gr
a
te
d
a
n
M
C
D
M
-
ba
s
e
d
r
e
c
o
m
m
e
nda
ti
on
s
y
s
te
m
,
c
o
m
bi
n
e
d
w
it
h
C
C
T
V
i
m
a
g
e
de
t
e
c
t
io
n
a
lg
or
it
hm
s
,
a
nd t
r
a
n
s
f
or
m
e
d r
e
a
l
-
w
or
ld
t
r
a
f
f
ic
da
ta
i
nt
o a
n
ope
n
-
w
or
ld
ga
m
e
m
e
c
ha
ni
c
.
T
he
P
R
O
M
E
T
H
E
E
i
nt
e
gr
a
ti
on me
th
od f
or
c
h
a
r
a
c
t
e
r
r
e
c
om
m
e
n
da
ti
on b
a
s
e
d on tr
a
f
f
i
c
c
on
di
ti
on
s
de
m
ons
tr
a
te
s
a
s
tr
o
ng a
l
ig
nm
e
nt
b
e
twe
e
n g
a
m
e
pl
a
y
a
nd
a
d
a
pt
iv
e
s
tr
a
te
g
ie
s
. E
xpe
r
t
a
nd u
s
e
r
e
va
l
ua
ti
o
ns
th
r
ough
S
U
S
t
e
s
ti
n
g
a
ls
o
c
onf
ir
m
th
a
t
th
e
s
ys
t
e
m
i
s
w
e
ll
-
de
s
ig
n
e
d a
nd
e
n
ga
gi
ng.
T
h
e
r
e
f
or
e
,
f
ur
th
e
r
in
nov
a
ti
on
s
to
t
he
s
ys
t
e
m
c
oul
d
be
m
a
de
to
e
nha
nc
e
th
e
r
e
a
li
s
m
a
nd
a
da
p
ta
bi
li
ty
of
th
e
e
nvi
r
onm
e
nt
.
M
a
c
hi
ne
l
e
a
r
n
in
g
-
ba
s
e
d
tr
a
f
f
ic
pr
e
di
c
ti
ons
c
a
n
a
ls
o
be
a
dde
d,
a
dj
us
ti
ng
th
e
d
if
f
ic
ul
ty
b
a
s
e
d
o
n
pl
a
ye
r
f
e
e
db
a
c
k
f
r
om
b
io
m
e
tr
i
c
da
t
a
.
T
hi
s
is
opt
im
iz
e
d f
or
r
e
a
l
-
ti
m
e
pe
r
f
or
m
a
nc
e
t
hr
ou
gh e
dge
a
nd
pa
r
a
l
le
l
c
om
put
in
g.
F
ur
th
e
r
de
v
e
lo
pm
e
nt
s
c
o
ul
d i
n
c
lu
d
e
th
e
in
tr
od
uc
ti
on
of
tr
a
ns
f
or
m
e
r
-
ba
s
e
d
m
ul
ti
c
la
s
s
ve
hi
c
le
s
a
nd
p
r
e
di
c
ti
v
e
m
od
e
li
ng
to
a
nt
ic
i
pa
t
e
tr
a
f
f
ic
tr
e
nd
s
,
e
na
bl
i
ng
a
m
or
e
i
nt
e
l
li
ge
n
t
a
n
d i
m
m
e
r
s
iv
e
s
e
r
io
u
s
g
a
m
e
e
xp
e
r
ie
nc
e
.
F
U
N
D
I
N
G
I
N
F
O
R
M
A
T
I
O
N
T
hi
s
s
tu
dy
w
a
s
f
un
de
d
by
th
e
P
e
ne
li
ti
a
n
P
e
nge
m
ba
n
ga
n
K
ol
a
bor
a
s
i
I
n
te
r
n
a
s
io
na
l
,
S
tu
di
B
i
s
ni
s
M
a
n
a
je
m
e
n
2024
gr
a
nt
f
r
om
D
I
P
A
U
ni
v
e
r
s
i
ta
s
I
s
la
m
N
e
ge
r
i
M
a
ul
a
n
a
M
a
li
k
I
br
a
hi
m
w
i
th
n
um
b
e
r
D
I
P
A
-
025.0
4.2.4
23812/
2024.
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
.
15
, N
o.
1
,
F
e
br
ua
r
y
20
26
:
177
-
190
186
A
U
T
H
O
R
C
O
N
T
R
I
B
U
T
I
O
N
S
S
T
A
T
E
M
E
N
T
T
hi
s
jo
ur
na
l
us
e
s
th
e
C
ont
r
ib
ut
or
R
ol
e
s
T
a
xonomy
(
C
R
e
di
T
)
to
r
e
c
ogni
z
e
in
di
vi
dua
l
a
ut
hor
c
ont
r
ib
ut
io
ns
, r
e
duc
e
a
ut
hor
s
hi
p di
s
put
e
s
,
a
nd f
a
c
il
it
a
te
c
ol
la
bo
r
a
ti
on.
N
am
e
o
f
A
u
t
h
or
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
F
r
e
s
y N
ugr
oho
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
I
G
us
ti
P
ut
u A
s
to
B
udi
tj
a
hj
a
nt
o
✓
✓
✓
✓
✓
✓
✓
D
w
i
P
e
br
ia
nt
i
✓
✓
✓
✓
✓
✓
✓
✓
J
e
ha
d A
. H
. H
a
m
m
a
d
✓
✓
✓
✓
✓
✓
✓
✓
✓
M
oc
h F
a
c
hr
i
✓
✓
✓
✓
✓
✓
✓
✓
T
r
i
M
ukt
i
L
e
s
ta
r
i
✓
✓
✓
✓
✓
✓
✓
✓
D
ia
n M
a
ha
r
a
ni
✓
✓
✓
✓
✓
✓
✓
C
:
C
onc
e
pt
ua
l
i
z
a
t
i
on
M
:
M
e
t
hodol
ogy
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
da
t
i
on
Fo
:
Fo
r
m
a
l
a
na
l
ys
i
s
I
:
I
nve
s
t
i
ga
t
i
on
R
:
R
e
s
our
c
e
s
D
:
D
a
t
a
C
ur
a
t
i
on
O
:
W
r
i
t
i
ng
-
O
r
i
gi
na
l
D
r
a
f
t
E
:
W
r
i
t
i
ng
-
R
e
vi
e
w
&
E
di
t
i
ng
Vi
:
Vi
s
ua
l
i
z
a
t
i
on
Su
:
Su
pe
r
vi
s
i
on
P
:
P
r
oj
e
c
t
a
dm
i
ni
s
t
r
a
t
i
on
Fu
:
Fu
ndi
ng a
c
qui
s
i
t
i
on
C
O
N
F
L
I
C
T
O
F
I
N
T
E
R
E
S
T
S
T
A
T
E
M
E
N
T
A
ut
hor
s
s
ta
te
no c
onf
li
c
t
of
i
nt
e
r
e
s
t.
I
N
F
O
R
M
E
D
C
O
N
S
E
N
T
T
hi
s
s
tu
dy
doe
s
not
in
vol
ve
in
di
vi
dua
l
pe
r
s
ona
l
da
ta
or
id
e
nt
if
ia
bl
e
hum
a
n
s
ubj
e
c
ts
.
T
he
r
e
f
or
e
,
in
f
or
m
e
d c
ons
e
nt
w
a
s
not
r
e
qui
r
e
d.
D
A
T
A
A
V
A
I
L
A
B
I
L
I
T
Y
T
he
da
ta
th
a
t
s
uppor
t
th
e
f
in
di
ngs
of
th
is
s
tu
dy
w
e
r
e
obt
a
in
e
d
f
r
om
th
e
f
ir
s
t
a
ut
ho
r
.
T
he
s
e
da
ta
w
e
r
e
us
e
d
w
it
h
pe
r
m
is
s
io
n
a
nd
a
r
e
not
publ
ic
ly
a
va
il
a
bl
e
due
to
li
c
e
ns
in
g
r
e
s
tr
ic
ti
ons
.
R
e
que
s
ts
f
or
a
c
c
e
s
s
m
a
y
be
di
r
e
c
te
d t
o t
he
c
or
r
e
s
ponding a
ut
hor
,
[
F
N
]
, s
ubj
e
c
t
to
a
ppr
ova
l
f
r
om
t
he
or
ig
in
a
l
a
ut
hor
s
.
R
E
F
E
R
E
N
C
E
S
[
1]
H
.
L
i
,
Y
.
C
he
n,
K
.
L
i
,
C
.
W
a
ng,
a
nd
B
.
C
he
n,
“
T
r
a
ns
por
t
a
t
i
on
i
nt
e
r
ne
t
:
a
s
us
t
a
i
na
bl
e
s
ol
ut
i
on
f
or
i
nt
e
l
l
i
ge
nt
t
r
a
ns
por
t
a
t
i
on
s
ys
t
e
m
s
,
”
I
E
E
E
T
r
ans
ac
t
i
ons
on
I
nt
e
l
l
i
ge
nt
T
r
an
s
por
t
at
i
on
Sy
s
t
e
m
s
,
vol
.
24,
no.
12,
pp.
15818
–
15829,
2023
,
doi
:
10.1109/
T
I
T
S
.2023.3270749.
[
2]
Y
.
R
e
n,
H
.
J
i
a
ng,
X
.
F
e
ng,
Y
.
Z
ha
o,
R
.
L
i
u
,
a
nd
H
.
Y
u
,
“
A
C
P
-
ba
s
e
d
m
ode
l
i
ng
of
t
he
pa
r
a
l
l
e
l
ve
hi
c
ul
a
r
c
r
ow
d
s
e
ns
i
ng
s
ys
t
e
m
:
f
r
a
m
e
w
or
k,
c
om
pone
nt
s
a
nd
a
n
a
ppl
i
c
a
t
i
on
e
xa
m
pl
e
,”
E
E
E
T
r
ans
ac
t
i
ons
on
I
nt
e
l
l
i
ge
nt
V
e
hi
c
l
e
s
,
vol
.
8,
no.
2,
pp.
1536
-
1548,
F
e
b. 2023, doi
:
10.1109/
T
I
V
.2022.3221927
.
[
3]
Z
.
X
i
a
o
e
t
al
.
,
“
T
e
ns
or
a
nd
c
onf
i
de
nt
i
nf
or
m
a
t
i
on
c
ove
r
a
ge
ba
s
e
d
r
e
l
i
a
bi
l
i
t
y
e
va
l
ua
t
i
on
f
or
l
a
r
ge
-
s
c
a
l
e
i
nt
e
l
l
i
ge
nt
t
r
a
ns
por
t
a
t
i
on
w
i
r
e
l
e
s
s
s
e
n
s
or
ne
t
w
or
ks
,”
I
E
E
E
T
r
ans
ac
t
i
ons
on
V
e
hi
c
ul
ar
T
e
c
hnol
ogy
,
vol
.
72,
no.
10,
pp.
13461
–
13473,
2023,
doi
:
10.1109/
T
V
T
.2023.3275579.
[
4]
Z
.
C
a
i
,
Z
.
C
he
n,
Z
.
L
i
u,
Q
.
X
i
e
,
R
.
M
a
,
a
nd
H
.
G
ua
n,
“
R
I
D
I
C
:
r
eal
-
t
i
m
e
i
nt
e
l
l
i
ge
nt
t
r
a
ns
por
t
a
t
i
on
s
ys
t
e
m
w
i
t
h
di
s
pe
r
s
e
d
c
om
put
i
ng,”
I
E
E
E
T
r
ans
ac
t
i
ons
on
I
nt
e
l
l
i
ge
nt
T
r
ans
por
t
at
i
on
S
y
s
t
e
m
s
,
vol
.
25,
no.
1,
pp.
1013
–
1022,
2024
,
doi
:
10.1109/
T
I
T
S
.2023.3303877.
[
5]
Z
.
L
v,
Y
.
L
i
,
H
.
F
e
ng,
a
nd
H
.
L
v,
“
D
e
e
p
l
e
a
r
ni
ng
f
or
s
e
c
ur
i
t
y
i
n
di
gi
t
a
l
t
w
i
ns
of
c
oope
r
a
t
i
ve
i
nt
e
l
l
i
ge
nt
t
r
a
ns
por
t
a
t
i
on
s
ys
t
e
m
s
,
”
I
E
E
E
T
r
ans
ac
t
i
ons
on
I
nt
e
l
l
i
ge
nt
T
r
ans
po
r
t
at
i
on
Sy
s
t
e
m
s
,
vol
.
23,
no.
9,
pp.
16666
–
16675,
2022
,
doi
:
10.1109/
T
I
T
S
.2021.3113779.
[
6]
N
.
K
um
a
r
,
S
.
S
.
R
a
hm
a
n,
a
nd
N
.
D
ha
ka
d,
“
F
uz
z
y
i
nf
e
r
e
nc
e
e
na
bl
e
d
de
e
p
r
e
i
nf
or
c
e
m
e
nt
l
e
a
r
ni
ng
-
ba
s
e
d
t
r
a
f
f
i
c
l
i
ght
c
ont
r
ol
f
or
i
nt
e
l
l
i
ge
nt
t
r
a
ns
por
t
a
t
i
on
s
ys
t
e
m
,”
I
E
E
E
T
r
ans
ac
t
i
ons
on
I
nt
e
l
l
i
ge
nt
T
r
ans
por
t
at
i
on
Sy
s
t
e
m
s
,
vol
.
22,
no.
8,
pp.
4919
–
4928,
2021,
doi
:
10.1109/
T
I
T
S
.2020.2984033.
[
7]
M
.
W
e
i
,
T
.
L
i
u,
a
nd
B
.
S
un,
“
O
pt
i
m
a
l
r
out
i
ng
de
s
i
gn
of
f
e
e
de
r
t
r
a
ns
i
t
w
i
t
h
s
t
op
s
e
l
e
c
t
i
on
us
i
ng
a
ggr
e
ga
t
e
d
c
e
l
l
phone
da
t
a
a
n
d
ope
n
s
our
c
e
G
I
S
t
ool
,”
I
E
E
E
T
r
ans
ac
t
i
ons
on
I
nt
e
l
l
i
ge
nt
T
r
ans
por
t
at
i
on
Sy
s
t
e
m
s
,
vol
.
22,
no.
4,
pp.
2452
–
2463,
2021,
doi
:
10.1109/
T
I
T
S
.2020.3042014.
[
8]
G
.
F
or
t
i
no,
C
.
S
a
va
gl
i
o,
G
.
S
pe
z
z
a
no,
a
nd
M
.
Z
hou,
“
I
nt
e
r
ne
t
of
t
hi
ngs
a
s
s
ys
t
e
m
of
s
ys
t
e
m
s
:
A
r
e
vi
e
w
of
m
e
t
hodol
ogi
e
s
,
f
r
a
m
e
w
or
ks
,
pl
a
t
f
or
m
s
,
a
nd
t
ool
s
,”
I
E
E
E
T
r
ans
ac
t
i
ons
on
Sy
s
t
e
m
s
,
M
an,
and
C
y
be
r
ne
t
i
c
s
:
Sy
s
t
e
m
s
,
vol
.
51,
no.
1,
pp.
223
–
236,
2021, doi
:
10.1109/
T
S
M
C
.2020.3042898.
[
9]
T
.
Y
ua
n,
W
.
D
.
R
.
N
e
t
o,
C
.
E
.
R
ot
he
nbe
r
g,
K
.
O
br
a
c
z
ka
,
C
.
B
a
r
a
ka
t
,
a
nd
T
.
T
u
r
l
e
t
t
i
,
“
M
a
c
hi
ne
l
e
a
r
ni
ng
f
o
r
ne
xt
-
ge
ne
r
a
t
i
on
i
nt
e
l
l
i
ge
nt
t
r
a
ns
por
t
a
t
i
on
s
ys
t
e
m
s
:
A
s
ur
ve
y,”
T
r
an
s
ac
t
i
ons
on
E
m
e
r
gi
ng
T
e
l
e
c
om
m
uni
c
at
i
ons
T
e
c
hnol
ogi
e
s
,
vol
.
33,
no.
4,
2022
,
doi
:
10.1002/
e
t
t
.4427.
[
10]
T
.
K
.
V
i
j
a
y,
D
.
P
.
D
ogr
a
,
H
.
C
hoi
,
G
.
N
a
m
,
a
nd
I
.
J
.
K
i
m
,
“
D
e
t
e
c
t
i
on
of
r
oa
d
a
c
c
i
de
nt
s
us
i
ng
s
ynt
he
t
i
c
a
l
l
y
ge
ne
r
a
t
e
d
m
ul
t
i
-
pe
r
s
pe
c
t
i
ve
a
c
c
i
de
nt
vi
de
o
s
,”
I
E
E
E
T
r
ans
ac
t
i
ons
on
I
nt
e
l
l
i
ge
nt
T
r
ans
por
t
at
i
on
Sy
s
t
e
m
s
,
vol
.
24,
no.
2,
pp.
1926
–
1935,
2023,
doi
:
10.1109/
T
I
T
S
.2022.3222769.
Evaluation Warning : The document was created with Spire.PDF for Python.