I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
pu
t
er
Science
Vo
l.
24
,
No
.
2
,
N
o
v
em
b
e
r
20
21
,
p
p
.
9
9
3
~
1
0
0
0
I
SS
N:
2
5
0
2
-
4
7
5
2
,
DOI
:
1
0
.
1
1
5
9
1
/ijeecs.v
2
4
.i
2
.
pp
993
-
1
0
0
0
993
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs.ia
esco
r
e.
co
m
M
a
chine learning
appro
a
ch on ro
a
d accidents
ana
ly
sis
in
C
a
la
ba
rzon
,
Phili
ppines:
a
n
input
t
o
roa
d sa
fet
y
ma
n
a
g
ement
K
riste
lle
Ann R.
T
o
rr
e
s
1
,
J
o
na
rdo
R.
Aso
r
2
1
Co
ll
e
g
e
o
f
Crimin
a
l
J
u
stice
Ed
u
c
a
ti
o
n
,
Lag
u
n
a
S
tate
P
o
l
y
tec
h
n
ic
Un
v
e
rsity
-
L
o
s Ba
ñ
o
s Ca
m
p
u
s,
Lag
u
n
a
,
P
h
il
ip
p
i
n
e
s
2
Co
ll
e
g
e
o
f
Co
m
p
u
ter S
t
u
d
ies
,
Lag
u
n
a
S
tate
P
o
ly
tec
h
n
ic Un
i
v
e
rsity
-
Lo
s Ba
ñ
o
s Ca
m
p
u
s,
La
g
u
n
a
,
P
h
i
li
p
p
i
n
e
s
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
a
n
24
,
2
0
2
1
R
ev
is
ed
Au
g
31
,
2
0
2
1
Acc
ep
ted
Sep
7
,
2
0
2
1
Th
is
re
se
a
rc
h
wa
s
c
o
n
d
u
c
ted
to
h
e
lp
t
h
e
traffic
p
o
li
c
y
m
a
k
e
rs
a
n
d
g
e
n
e
ra
l
p
u
b
li
c
i
n
p
re
v
e
n
ti
n
g
ro
a
d
i
n
c
id
e
n
t
s
u
sin
g
t
h
e
c
o
l
lec
ted
traffic
a
c
c
id
e
n
t
d
a
tas
e
t
b
e
twe
e
n
th
e
y
e
a
rs
2
0
1
6
a
n
d
2
0
1
9
.
Da
ta
m
in
in
g
u
si
n
g
c
las
sifica
ti
o
n
a
lg
o
rit
h
m
wa
s
u
ti
li
z
e
d
to
d
e
v
e
l
o
p
a
p
re
d
i
c
ti
v
e
m
o
d
e
l
fo
r
p
re
d
ictin
g
o
c
c
u
rre
n
c
e
s
o
f
traffic
a
c
c
id
e
n
ts.
Clas
sifica
ti
o
n
a
lg
o
rit
h
m
s
su
c
h
a
s
d
e
c
isio
n
tree
,
k
-
n
n
,
n
a
ïv
e
b
a
y
e
s
a
n
d
n
e
u
ra
l
n
e
two
r
k
h
a
v
e
b
e
e
n
c
o
m
p
a
re
d
i
n
i
d
e
n
ti
f
y
in
g
b
e
tt
e
r
c
las
sifica
ti
o
n
c
a
p
a
b
il
i
ty
in
c
las
sify
in
g
sta
g
e
o
f
fe
lo
n
y
.
Ne
u
ra
l
n
e
tw
o
rk
sh
o
ws
a
v
e
ry
p
r
o
m
isin
g
re
su
lt
i
n
c
las
sify
in
g
ro
a
d
a
c
c
id
e
n
t
wit
h
a
to
tal
a
c
c
u
ra
c
y
re
su
lt
o
f
8
7
.
6
3
%
.
No
n
e
th
e
les
s,
k
-
n
n
a
n
d
n
a
ïv
e
b
a
y
e
s
b
o
th
a
c
q
u
ire
d
a
h
i
g
h
e
r
th
a
n
8
0
%
a
c
c
u
ra
c
y
wh
ich
sh
o
ws
th
a
t
t
h
is
c
las
sifica
ti
o
n
a
l
g
o
rit
h
m
s
we
re
a
lso
g
o
o
d
in
p
re
d
ictin
g
r
o
a
d
a
c
c
id
e
n
ts
.
M
o
re
o
v
e
r,
p
u
b
l
ic
v
e
h
icle
is
m
o
r
e
p
ro
n
e
i
n
a
c
c
id
e
n
t
ra
th
e
r
th
a
n
p
ri
v
a
te
v
e
h
ic
le
in
b
o
t
h
sta
g
e
o
f
fe
lo
n
y
a
n
d
a
c
c
id
e
n
t
m
a
y
o
c
c
u
r
b
e
twe
e
n
o
r
o
n
3
:0
0
p
m
a
n
d
6
:0
0
p
m
.
K
ey
w
o
r
d
s
:
C
las
s
if
icatio
n
alg
o
r
ith
m
Dec
is
io
n
tr
ee
M
ac
h
in
e
lear
n
in
g
Naïv
e
b
ay
es
Neu
r
al
n
etwo
r
k
R
o
ad
tr
af
f
ic
ac
cid
en
ts
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
:
Kr
is
telle
An
n
R
.
T
o
r
r
es
C
o
lleg
e
o
f
C
r
im
in
al
J
u
s
tice
E
d
u
ca
tio
n
L
ag
u
n
a
State
Po
ly
tech
in
ic
Un
i
v
er
s
ity
-
L
o
s
B
añ
o
s
C
am
p
u
s
B
r
g
y
.
Ma
lin
ta,
L
o
s
B
añ
o
s
,
L
a
g
u
n
a,
Ph
ilip
p
in
es
E
m
ail: to
r
r
esk
r
is
tellean
n
@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
R
o
ad
tr
af
f
ic
ac
cid
en
ts
co
u
l
d
h
ap
p
en
i
n
an
y
p
lace
at
an
y
g
iv
en
tim
e.
Ma
n
y
s
tu
d
ies
h
a
d
n
o
ted
th
at
th
ese
ac
cid
en
ts
h
av
e
alwa
y
s
b
ee
n
a
p
e
r
en
n
ial
p
r
o
b
lem
[
1
]
-
[
4
]
.
T
h
is
p
r
o
b
lem
h
as
b
ee
n
r
ec
o
g
n
ized
b
y
th
e
Un
ited
Natio
n
s
Gen
er
al
Ass
e
m
b
ly
’
s
d
ec
lar
atio
n
o
f
th
e
d
ec
ad
e
o
f
ac
tio
n
f
o
r
r
o
ad
s
af
ety
2011
-
2
0
2
0
[
5
]
.
T
h
e
r
o
ad
t
h
at
is
s
u
p
p
o
s
ed
to
lead
,
b
r
in
g
,
a
n
d
tr
i
g
g
er
ec
o
n
o
m
ic
d
ev
elo
p
m
e
n
ts
,
tu
r
n
ed
o
u
t
to
b
ec
o
m
e
e
v
er
y
o
n
e’
s
acce
s
s
an
d
g
atew
ay
to
r
o
ad
tr
a
f
f
ic
ac
cid
en
ts
,
r
esu
ltin
g
in
in
ju
r
ies,
an
d
wo
r
s
t,
d
ea
th
to
m
o
to
r
is
ts
.
Dea
th
is
th
e
m
o
s
t
s
ig
n
if
ican
t
c
o
n
s
eq
u
en
ce
o
f
in
ju
r
ies
[
6
]
.
Gh
ad
ir
za
d
eh
et
a
l
.
[
7
]
cited
th
at
as
a
r
esu
lt
o
f
tr
af
f
ic
co
llis
io
n
,
ar
o
u
n
d
1
.
3
5
m
illi
o
n
p
eo
p
le
d
ie
ea
ch
y
ea
r
,
wh
ile
2
0
to
5
0
m
illi
o
n
p
eo
p
le
s
u
f
f
er
n
o
n
-
f
atal
in
ju
r
ies.
I
n
ter
m
s
o
f
d
is
ab
ilit
y
-
ad
ju
s
ted
life
y
ea
r
s
(
DAL
Ys)
lo
s
t
g
lo
b
ally
,
r
o
ad
tr
a
f
f
ic
ac
cid
en
ts
wer
e
p
r
ev
io
u
s
ly
r
a
n
k
ed
n
in
th
lead
i
n
g
ca
u
s
e
o
f
m
o
r
tality
,
m
o
r
b
id
ity
,
d
is
ea
s
e
b
u
r
d
en
in
1
9
9
0
a
n
d
wer
e
p
r
ed
icted
to
b
e
th
e
th
ir
d
m
ajo
r
k
iller
an
d
t
h
e
lar
g
est
lea
d
in
g
ca
u
s
e
o
f
d
e
ath
an
d
d
is
ab
ilit
y
b
y
2
0
2
0
[
8
]
.
Du
e
t
o
th
e
g
r
o
win
g
d
em
an
d
f
o
r
ca
r
s
an
d
au
to
m
o
b
i
les f
o
r
u
s
e,
ac
cid
en
ts
h
av
e
in
cr
ea
s
ed
d
r
am
atica
lly
[
9
]
.
T
h
is
p
h
en
o
m
e
n
o
n
ca
u
s
es
in
d
iv
id
u
als,
th
eir
f
am
ili
es,
an
d
n
atio
n
s
as a
wh
o
le
to
s
u
f
f
er
s
i
g
n
if
ican
t e
co
n
o
m
ic
lo
s
s
es.
I
n
C
alab
ar
zo
n
R
eg
io
n
,
Ph
ilip
p
in
es,
th
er
e
ar
e
a
to
tal
o
f
7
0
,
1
7
8
r
o
ad
tr
af
f
ic
ac
cid
e
n
ts
r
ec
o
r
d
ed
b
y
th
e
Ph
ilip
p
in
e
Natio
n
al
Po
lice
f
r
o
m
2
0
1
6
to
2
0
1
9
.
Yea
r
2
0
1
7
r
ec
o
r
d
ed
t
h
e
h
ig
h
est
n
u
m
b
er
o
f
f
atalities
with
1
8
,
8
0
9
in
cid
e
n
ts
; 2
0
1
8
with
1
8
,
3
4
4
;
2
0
1
9
with
1
6
,
9
8
7
; a
n
d
2
0
1
6
with
1
6
,
0
3
8
ca
s
es.
I
t is o
b
v
io
u
s
in
t
h
is
d
ata
th
at
th
er
e
is
a
h
ig
h
ac
cid
en
t f
r
eq
u
en
cy
s
ig
n
if
y
in
g
a
p
r
o
b
lem
atic
an
d
r
em
ed
y
is
n
ee
d
e
d
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2502
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
2
4
,
No
.
2
,
No
v
em
b
er
20
21
:
9
9
3
-
1
0
0
0
994
M
a
n
y
s
c
h
o
l
a
r
s
a
n
d
r
e
s
e
a
r
c
h
e
r
s
h
a
v
e
c
o
n
d
u
c
t
e
d
s
t
u
d
i
e
s
a
n
d
w
r
i
t
i
n
g
s
o
f
t
h
e
a
n
a
l
y
s
is
o
n
t
h
e
r
a
t
e
o
f
r
o
a
d
t
r
a
f
f
i
c
a
c
ci
d
e
n
ts
.
T
h
e
s
e
p
e
o
p
le
h
a
v
e
u
s
e
d
s
t
at
is
t
ic
a
l
t
o
o
l
s
s
u
c
h
a
s
c
h
i
-
s
q
u
a
r
e
a
n
al
y
s
is
,
c
o
r
r
e
l
a
t
i
o
n
-
c
o
e
f
f
i
c
ie
n
t
a
n
a
l
y
s
is
,
c
o
m
p
a
r
at
i
v
e
a
n
al
y
s
is
,
m
u
l
t
i
p
l
e
r
e
g
r
e
s
s
i
o
n
a
n
al
y
s
i
s
,
a
n
d
t
i
m
e
-
s
e
r
i
es
a
n
a
l
y
s
is
t
o
a
n
al
y
z
e
t
h
e
i
r
d
a
t
a
.
T
h
e
c
h
i
-
s
q
u
a
r
e
a
n
a
l
y
s
is
o
f
[
1
0
]
p
r
o
v
i
d
e
d
e
v
i
d
e
n
c
e
f
o
r
t
h
e
d
e
s
i
g
n
a
n
d
i
m
p
l
e
m
e
n
t
a
t
i
o
n
o
f
c
o
n
c
r
e
t
e
a
n
d
u
r
g
e
n
t
l
y
n
e
e
d
e
d
p
r
e
v
e
n
t
i
v
e
s
t
r
a
te
g
i
e
s
t
o
c
o
n
t
r
o
l
t
h
e
al
m
o
s
t
c
o
m
p
l
e
t
e
l
y
p
r
e
v
e
n
ta
b
l
e
f
at
a
l
it
i
es
o
f
r
o
a
d
a
c
c
i
d
e
n
ts
.
M
e
a
n
w
h
i
l
e
,
c
h
i
-
sq
u
a
r
e
d
a
u
t
o
m
a
t
i
c
i
n
t
e
r
a
c
ti
o
n
d
e
t
e
c
ti
o
n
(
C
HA
I
D
)
d
e
c
is
i
o
n
t
r
e
e
t
e
c
h
n
i
q
u
e
w
a
s
u
s
e
d
t
o
i
d
e
n
t
i
f
y
s
i
g
n
i
f
i
c
a
n
t
r
is
k
f
a
c
t
o
r
s
a
n
d
e
x
p
l
o
r
e
t
h
e
e
f
f
e
ct
o
f
v
a
r
i
o
u
s
c
o
m
b
in
a
t
i
o
n
s
o
f
m
aj
o
r
r
is
k
f
a
c
t
o
r
s
o
n
r
o
a
d
s
i
d
e
a
cc
i
d
e
n
ts
i
n
a
c
c
o
r
d
a
n
c
e
t
o
t
h
e
g
e
n
e
r
a
te
d
d
e
c
i
s
i
o
n
r
u
l
es
,
a
n
d
t
o
r
e
c
o
m
m
en
d
s
p
e
c
i
f
i
c
i
m
p
r
o
v
e
d
c
o
u
n
t
e
r
m
e
a
s
u
r
e
s
[
1
1
]
.
Ku
m
ar
an
d
T
o
s
h
n
iwal
[
1
2
]
do
an
aly
s
is
o
f
h
o
u
r
ly
r
o
a
d
ac
cid
en
t
co
u
n
ts
u
s
in
g
h
ier
ar
c
h
ical
clu
s
ter
in
g
,
an
d
co
p
h
en
etic
co
r
r
elatio
n
co
ef
f
icien
t
(
C
PC
C
)
s
h
o
wed
th
a
t
th
e
p
r
o
p
o
s
ed
m
eth
o
d
is
ca
p
ab
le
o
f
ef
f
icien
tly
g
r
o
u
p
th
e
d
if
f
er
en
t
d
is
tr
icts
with
s
im
ilar
r
o
ad
ac
cid
en
t
p
atter
n
s
in
to
s
in
g
le
clu
s
ter
o
r
g
r
o
u
p
wh
ich
ca
n
b
e
u
s
ed
f
o
r
tr
e
n
d
an
aly
s
is
o
r
s
im
ilar
t
ask
s
.
Vig
n
esh
k
u
m
ar
et
a
l.
[
1
3
]
d
o
co
m
p
ar
ativ
e
an
aly
s
is
r
ev
ea
led
th
at
I
n
d
ia
h
as
o
n
e
o
f
th
e
h
ig
h
est
f
atality
r
ate
s
in
r
o
ad
ac
cid
en
ts
,
w
h
ich
ar
e
8
.
1
d
ea
th
s
p
er
1
0
,
0
0
0
m
o
t
o
r
v
eh
icles
o
n
th
e
r
o
a
d
in
2
0
1
3
co
m
p
ar
ed
with
th
e
r
ates
in
o
th
er
d
ev
elo
p
ed
co
u
n
tr
ies
lik
e
Au
s
tr
al
ia,
Au
s
tr
ia,
Ho
n
g
Ko
n
g
,
New
Z
ea
lan
d
,
USA,
C
an
ad
a,
an
d
So
u
th
Ko
r
ea
.
T
h
e
ca
s
u
alty
r
is
k
is
h
ig
h
er
in
I
n
d
ia
as
co
m
p
ar
e
d
to
th
e
in
d
ices
o
f
th
e
m
en
tio
n
ed
d
ev
elo
p
ed
co
u
n
tr
ies.
W
h
ile
r
o
ad
s
af
et
y
s
itu
atio
n
is
im
p
r
o
v
in
g
in
d
e
v
elo
p
ed
s
o
cieties,
m
o
s
t
d
ev
elo
p
in
g
co
u
n
tr
ies lik
e
I
n
d
ia
ar
e
f
ac
in
g
an
ev
e
r
-
wo
r
s
en
in
g
s
itu
atio
n
.
On
o
n
e
h
a
n
d
,
[
1
4
]
r
eg
r
ess
io
n
an
al
y
s
is
o
f
r
o
ad
tr
af
f
ic
ac
c
id
en
ts
an
d
p
o
p
u
latio
n
g
r
o
wth
in
Gh
an
a
s
h
o
wed
th
r
ee
k
e
y
f
i
n
d
in
g
s
:
a
s
y
s
tem
atic
v
is
ib
le
p
atter
n
o
f
g
r
o
wth
in
b
o
th
r
o
ad
tr
af
f
ic
ac
cid
en
ts
a
n
d
p
o
p
u
latio
n
o
v
er
th
e
p
er
io
d
;
ev
id
en
ce
o
f
s
tatis
tical
r
elatio
n
s
h
ip
b
etwe
en
r
o
a
d
tr
a
f
f
ic
ac
cid
e
n
ts
an
d
p
o
p
u
latio
n
g
r
o
wth
in
Gh
an
a
in
d
icate
d
t
h
at
f
o
r
t
h
e
p
er
i
o
d
u
n
d
e
r
s
tu
d
y
b
ased
o
n
th
e
av
ailab
l
e
d
ata,
p
o
p
u
latio
n
is
ab
le
to
ac
co
u
n
t f
o
r
7
2
.
9
p
er
ce
n
t
o
f
th
e
ch
an
g
es in
ac
cid
e
n
ts
.
Aim
in
g
to
aid
in
th
e
r
e
d
u
ct
io
n
o
f
cr
im
e
i
n
cid
en
ts
in
a
p
r
o
v
in
cial
s
ettin
g
[
1
5
]
an
d
m
u
n
icip
al
s
ettin
g
[
1
6
]
,
th
ese
s
tu
d
ies
u
tili
ze
d
a
m
ac
h
in
e
lear
n
in
g
to
d
e
v
elo
p
a
p
r
e
d
ictiv
e
m
o
d
el
in
i
n
v
esti
g
atin
g
cr
im
e
r
ec
o
r
d
s
.
Aso
r
et
a
l
.
[
1
7
]
an
al
y
ze
d
th
e
d
ata
f
r
o
m
th
e
r
o
a
d
a
cc
id
en
t
to
r
ev
ea
l
n
ew
tr
en
d
s
t
h
at
ca
n
b
e
u
s
ed
as
p
r
ec
au
tio
n
a
r
y
m
ea
s
u
r
e
to
at
least
m
in
im
ize
th
e
y
ea
r
l
y
ac
cid
en
t.
An
o
th
e
r
,
th
e
tr
en
d
an
aly
s
is
o
f
r
esu
lts
o
f
[
1
8
]
ca
ll
f
o
r
clo
s
e
m
o
n
ito
r
in
g
o
f
i
n
ju
r
ies
d
u
r
in
g
h
ig
h
-
r
is
k
p
er
io
d
s
in
o
r
d
er
to
m
an
a
g
e
a
n
d
r
e
d
u
ce
th
e
in
ju
r
y
r
ate.
L
astl
y
,
Par
v
ar
eh
et
a
l.
[
1
9
]
a
s
ce
r
tain
ed
th
at
r
o
ad
tr
a
f
f
ic
a
cc
id
en
t
wo
u
ld
b
e
an
in
cr
ea
s
e
in
th
e
n
u
m
b
er
o
f
ac
cid
en
ts
o
cc
u
r
r
in
g
in
th
e
f
u
tu
r
e.
T
h
er
e
ar
e
a
ls
o
s
tu
d
ies
th
at
in
v
esti
g
ated
n
eu
r
al
n
etwo
r
k
in
r
o
ad
tr
af
f
ic
an
al
y
s
is
.
Fo
r
ex
am
p
le,
th
e
r
esear
ch
o
f
[
2
0
]
,
[
2
1
]
h
as
f
o
u
n
d
o
u
t
th
at
th
e
n
eu
r
al
n
etwo
r
k
en
ab
les
s
h
o
r
t
-
ter
m
p
r
e
d
ictio
n
r
esu
lts
wh
ich
c
an
b
e
u
s
ed
in
a
p
p
licatio
n
s
f
o
r
t
r
af
f
ic
m
an
a
g
em
en
t.
I
n
tellig
e
n
t
tr
an
s
p
o
r
t
s
y
s
tem
s
an
d
n
e
u
r
al
n
etwo
r
k
s
wer
e
u
tili
ze
d
to
d
e
v
elo
p
r
o
ad
tr
af
f
i
c
m
an
ag
em
e
n
t
m
o
d
el
to
s
o
lv
e
tr
af
f
ic
m
a
n
ag
em
e
n
t
p
r
o
b
lem
s
.
Fu
r
th
er
m
o
r
e,
[
2
2
]
m
eth
o
d
p
r
o
v
id
ed
a
s
o
lu
tio
n
i
n
m
ak
i
n
g
b
etter
tr
a
n
s
p
o
r
tatio
n
d
ec
is
io
n
s
;
an
d
th
e
n
e
u
r
al
n
e
two
r
k
is
a
p
lau
s
ib
l
e
ap
p
r
o
ac
h
to
r
ec
o
g
n
ize
tr
af
f
ic
co
n
d
itio
n
s
.
T
h
e
m
o
d
if
ied
n
eu
r
al
n
etwo
r
k
m
o
d
el
o
f
[
2
3
]
p
r
esen
ts
a
s
ig
n
if
ican
t
o
p
p
o
r
tu
n
ity
f
o
r
m
o
d
elin
g
cr
a
s
h
f
r
eq
u
en
c
y
with
th
e
s
tr
u
ctu
r
e
o
p
tim
izatio
n
alg
o
r
ith
m
a
n
d
r
u
le
ex
tr
ac
tio
n
m
eth
o
d
,
a
n
d
th
e
r
ef
o
r
e
ca
n
b
e
co
n
s
id
er
ed
as a
g
o
o
d
alter
n
ati
v
e
f
o
r
an
aly
s
is
o
f
r
o
a
d
s
af
ety
.
T
h
e
in
f
o
r
m
atio
n
th
at
is
ac
q
u
ir
ed
f
r
o
m
d
ata
m
in
in
g
ap
p
r
o
ac
h
es
aim
ed
to
d
ev
elo
p
a
p
r
e
d
ictiv
e
m
o
d
e
l
f
o
r
f
u
tu
r
e
o
cc
u
r
r
en
ce
s
o
f
n
u
m
b
er
s
o
f
tr
af
f
ic
ac
cid
en
ts
.
Acc
o
r
d
in
g
to
Srilath
a
et
a
l
.
[
2
4
]
,
ac
cid
en
t
p
r
ed
ictio
n
i
s
o
n
e
o
f
th
e
m
o
s
t
im
p
o
r
tan
t
as
p
ec
ts
o
f
r
o
ad
s
af
ety
,
wh
er
eb
y
an
ac
cid
en
t
ca
n
b
e
an
ticip
ated
b
ef
o
r
e
it
ac
tu
ally
h
ap
p
en
s
a
n
d
p
r
ec
au
tio
n
ar
y
m
ea
s
u
r
es
tak
en
t
o
p
r
ev
en
t
it.
T
h
is
s
tu
d
y
aim
s
to
d
ev
elo
p
a
m
o
d
el
f
o
r
r
o
a
d
ac
cid
en
ts
u
s
in
g
m
ac
h
in
e
lear
n
ig
alg
o
r
ith
m
s
.
2.
M
E
T
H
O
DS
2
.
1
.
D
a
t
a
g
a
t
hering
A
letter
o
f
r
eq
u
est
was
s
u
b
m
itted
to
th
e
r
eg
io
n
al
in
v
esti
g
atio
n
an
d
d
etec
tiv
e
m
an
ag
e
m
en
t
d
iv
is
io
n
(
R
I
DM
D)
o
f
PNP
C
alab
ar
zo
n
to
o
b
tain
th
e
r
o
ad
ac
cid
e
n
t
r
e
p
o
r
t.
T
h
e
letter
ass
u
r
ed
th
at
t
h
e
d
ata
t
h
at
will
b
e
o
b
tain
ed
f
r
o
m
th
e
o
f
f
ice
will
b
e
u
s
ed
e
x
clu
s
iv
ely
in
th
is
s
tu
d
y
.
T
h
e
co
llected
d
ata
co
n
tain
s
th
e
f
o
u
r
(
4
)
y
ea
r
r
ec
o
r
d
b
etwe
en
2
0
1
6
an
d
2
0
1
9
.
As
s
h
o
wn
in
T
ab
le
1
,
th
e
d
ataset
h
as
th
e
attr
ib
u
tes
p
o
lice
p
r
o
v
in
cial
o
f
f
ice
(
PP
O)
,
B
ar
an
g
ay
,
Date
,
T
im
e,
Place,
Stag
e
o
f
Felo
n
y
a
n
d
V
eh
icle
T
y
p
e.
T
h
ese
attr
ib
u
tes
wer
e
test
ed
f
ir
s
t
to
s
ee
if
th
ey
ar
e
all
r
esp
o
n
d
in
g
in
th
e
class
if
icatio
n
alg
o
r
ith
m
s
.
I
t
will
b
e
th
en
s
elec
ted
an
d
ex
tr
ac
t
o
n
ly
th
o
s
e
attr
ib
u
tes th
at
s
h
o
ws v
iab
ilit
y
o
n
th
e
p
r
o
ject.
2
.
2
.
D
a
t
a
pre
-
pro
ce
s
s
ing
/s
elec
t
io
n
I
n
th
is
p
ar
t,
th
e
d
ataset
is
f
ir
s
t
tr
an
s
f
o
r
m
ed
in
lo
wer
ca
s
e
t
o
m
ak
e
s
u
r
e
th
at
it
will
h
a
v
e
th
e
s
am
e
m
ea
n
in
g
i
n
th
e
m
o
d
el
d
ev
el
o
p
m
en
t.
Un
n
ec
ess
ar
y
o
b
jects
in
ev
er
y
in
s
tan
ce
a
r
e
also
r
e
m
o
v
ed
s
u
c
h
as
wh
ite
s
p
ac
e
an
d
o
th
er
s
p
ec
ial
ch
a
r
a
cter
in
clu
d
in
g
ty
p
o
g
r
a
p
h
ical
e
r
r
o
r
.
Up
o
n
ass
u
r
in
g
th
at
e
v
er
y
in
s
tan
ce
in
s
id
e
th
e
d
ataset
h
av
e
th
e
s
am
e
m
ea
n
i
n
g
,
s
o
m
e
co
lu
m
n
s
ar
e
r
e
m
o
v
e
d
f
o
r
it sh
o
ws d
u
p
licatio
n
f
r
o
m
o
th
er
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
Ma
ch
in
e
lea
r
n
in
g
a
p
p
r
o
a
ch
o
n
r
o
a
d
a
cc
id
en
ts
a
n
a
lysi
s
in
C
a
la
b
a
r
z
o
n
…
(
K
r
is
telle
A
n
n
R
.
To
r
r
es
)
995
I
t
is
n
e
ce
s
s
ar
y
an
d
v
ital
to
m
o
d
el
d
ev
elo
p
m
en
t
t
o
d
iv
i
d
e
th
e
d
ataset
in
to
two
p
ar
ts
wh
ic
h
a
r
e
f
am
o
u
s
as
tr
ain
s
et
an
d
test
s
et.
Sh
o
wn
in
th
e
T
ab
le
2
th
at
8
0
%
o
f
th
e
d
ataset
will
b
e
th
e
tr
ain
s
et
wh
ile
th
e
r
em
ain
in
g
2
0
%
will
b
e
th
e
test
s
et.
Div
is
io
n
o
f
d
ataset
ar
e
d
o
n
e
th
r
o
u
g
h
s
tr
atif
ied
r
an
d
o
m
s
am
p
lin
g
,
wh
ich
f
o
cu
s
in
th
e
s
tag
e
o
f
f
elo
n
y
an
d
PP
O.
T
h
is
is
to
ass
u
r
e
th
at
b
ias in
class
if
y
in
g
an
d
p
r
e
d
ictio
n
p
r
o
ce
s
s
will b
e
elim
in
ated
.
T
h
e
d
ataset
is
tr
ain
ed
in
th
r
ee
d
if
f
er
e
n
t
m
o
s
tly
u
s
ed
m
a
ch
in
e
lear
n
in
g
alg
o
r
ith
m
in
d
o
cu
m
e
n
t
class
if
icatio
n
an
d
r
o
ad
ac
cid
en
ts
n
am
ely
d
ec
is
io
n
tr
ee
,
k
-
N
N
an
d
n
aïv
e
b
ay
es
[
1
6
]
-
[
2
6
]
.
T
h
is
was
d
o
n
e
u
s
in
g
r
ap
id
m
in
er
–
a
f
am
o
u
s
d
ata
m
i
n
in
g
to
o
l
t
h
at
u
s
ed
b
y
ex
p
e
r
ts
in
m
o
d
el
d
e
v
elo
p
m
e
n
t
[
2
7
]
.
L
ik
ewise,
th
e
d
ataset
is
also
tr
ain
ed
in
n
eu
r
al
n
etwo
r
k.
T
ab
le
1
.
Attr
ib
u
tes o
f
r
o
a
d
tr
af
f
ic
ac
cid
en
ts
d
ataset
A
t
t
r
i
b
u
t
e
s
D
e
scri
p
t
i
o
n
D
a
t
a
t
y
p
e
PPO
P
o
l
i
c
e
O
f
f
i
c
e
i
n
w
h
i
c
h
t
h
e
a
c
c
i
d
e
n
t
h
a
s b
e
e
n
r
e
p
o
r
t
e
d
a
n
d
r
e
c
o
r
d
e
d
S
t
r
i
n
g
B
a
r
a
n
g
a
y
B
a
r
a
n
g
a
y
w
h
e
r
e
t
h
e
a
c
c
i
d
e
n
t
o
c
c
u
r
s
S
t
r
i
n
g
D
a
y
D
a
y
o
f
t
h
e
W
e
e
k
w
h
e
n
t
h
e
a
c
c
i
d
e
n
t
o
c
c
u
r
s
S
t
r
i
n
g
M
o
n
t
h
M
o
n
t
h
w
h
e
n
t
h
e
a
c
c
i
d
e
n
t
o
c
c
u
r
s
S
t
r
i
n
g
Y
e
a
r
Y
e
a
r
w
h
e
n
t
h
e
a
c
c
i
d
e
n
t
o
c
c
u
r
s
I
n
t
e
g
e
r
Ti
me
C
o
mm
i
t
t
e
d
Ti
me
w
h
e
n
t
h
e
a
c
c
i
d
e
n
t
o
c
c
u
r
s
Ti
me
S
t
a
g
e
o
f
F
e
l
o
n
y
P
e
r
i
o
d
o
f
e
x
e
c
u
t
i
o
n
o
f
a
c
t
s
S
t
r
i
n
g
V
e
h
i
c
l
e
T
y
p
e
Ty
p
e
o
f
t
h
e
v
e
h
i
c
l
e
i
n
v
o
l
v
e
d
i
n
t
h
e
a
c
c
i
d
e
n
t
S
t
r
i
n
g
T
ab
le
2
.
Dis
tr
ib
u
tio
n
o
f
s
tag
e
o
f
f
elo
n
y
in
tr
ai
n
an
d
test
d
ataset
S
t
a
g
e
o
f
F
e
l
o
n
y
Tr
a
i
n
S
e
t
Te
st
S
e
t
C
o
n
s
u
mm
a
t
e
d
4
4
1
7
1
1
0
4
R
e
c
k
l
e
ss I
mp
r
u
d
e
n
c
e
3
5
8
2
8
9
6
To
t
a
l
7
9
9
9
2
0
0
0
2
.
3
.
Alg
o
rit
hm
e
v
a
lua
t
io
n
2
.
3
.
1
.
Co
nfusi
o
n m
a
t
rix
C
o
n
f
u
s
i
o
n
m
a
t
r
i
x
w
il
l
b
e
t
h
e
o
n
e
t
o
u
s
e
i
n
v
i
s
u
a
l
i
zi
n
g
t
h
e
c
l
a
s
s
i
f
ic
a
t
i
o
n
c
o
r
r
e
c
t
n
es
s
o
f
t
h
e
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
m
.
I
t
i
s
a
w
e
l
l
-
k
n
o
w
n
t
a
b
l
e
f
o
r
d
es
c
r
i
b
i
n
g
t
h
e
p
e
r
f
o
r
m
a
n
c
e
o
f
c
h
o
s
e
n
al
g
o
r
i
t
h
m
o
r
c
l
as
s
i
f
i
c
at
i
o
n
m
o
d
e
l
.
A
s
i
ll
u
s
t
r
a
t
e
d
i
n
Fi
g
u
r
e
1
,
c
o
n
f
u
s
i
o
n
m
a
t
r
i
x
c
o
n
t
a
i
n
s
t
h
e
n
u
m
b
e
r
o
f
t
r
u
e
p
o
s
i
t
i
v
e
(
T
P
)
,
t
r
u
e
n
e
g
a
t
i
v
e
(
T
N
)
,
f
a
l
s
e
p
o
s
it
i
v
e
(
FP
)
a
n
d
f
a
l
s
e
n
e
g
a
ti
v
e
(
F
N
)
i
n
c
l
as
s
i
f
y
i
n
g
t
h
e
s
t
a
g
e
o
f
f
e
l
o
n
y
u
s
i
n
g
t
h
e
d
a
t
a
s
et
.
A
s
i
d
e
f
r
o
m
t
h
e
s
e
,
c
o
n
f
u
s
i
o
n
m
a
t
r
i
x
is
o
f
t
e
n
u
s
e
d
t
o
c
o
m
p
u
t
e
r
e
c
a
ll
,
p
r
e
c
is
io
n
,
f
1
-
s
c
o
r
e
a
n
d
s
p
e
c
i
f
i
ci
t
y
.
Fig
u
r
e
1
.
C
o
n
f
u
s
io
n
m
atr
i
x
2
.
3
.
2
.
Rec
a
ll/S
ens
it
iv
it
y
R
ec
all
o
r
s
en
s
itiv
ity
d
escr
ib
es
th
e
ca
p
a
b
ilit
y
o
f
th
e
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
to
p
o
i
n
t
a
n
ass
ig
n
ed
v
alu
e
as
th
e
ac
tu
al
v
al
u
e.
I
n
t
h
is
p
ap
er
,
r
ec
all
will
s
h
o
w
th
e
ca
p
ab
ilit
y
o
f
th
e
alg
o
r
ith
m
t
o
p
o
in
t
t
h
e
co
r
r
ec
t
s
tag
e
o
f
f
elo
n
y
.
I
t
is
th
e
to
ta
l
n
u
m
b
er
o
f
th
e
t
r
u
e
p
o
s
itiv
es
o
r
s
tag
e
o
f
f
elo
n
y
(
c
o
n
s
u
m
m
ated
o
r
r
ec
k
less
im
p
r
u
d
e
n
ce
)
t
h
at
is
id
en
tifie
d
co
r
r
ec
tly
b
y
th
e
alg
o
r
ith
m
d
iv
id
ed
b
y
s
u
m
o
f
tr
u
e
p
o
s
iti
v
es
an
d
f
alse
n
eg
ativ
e
o
r
in
co
r
r
ec
tly
la
b
eled
s
tag
e
o
f
f
elo
n
y
(
a
co
n
s
u
m
m
ated
th
at
is
lab
elled
as
r
ec
k
less
im
p
r
u
d
e
n
ce
)
.
R
ec
all’
s
f
o
r
m
u
la
is
as (
1
)
.
R
ec
all
=
TP
TP
+
FN
(
1
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2502
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
2
4
,
No
.
2
,
No
v
em
b
er
20
21
:
9
9
3
-
1
0
0
0
996
2
.
3
.
3
.
P
re
cisi
o
n
Pre
cisi
o
n
is
u
s
ed
to
s
h
o
w
th
e
ac
cu
r
ac
y
o
r
co
r
r
ec
t
n
es
s
o
f
th
e
p
r
ed
ictio
n
o
r
class
if
icatio
n
.
I
t
s
h
o
ws
th
e
ab
ilit
y
o
f
th
e
m
o
d
el
to
id
en
tif
y
r
elev
a
n
t
d
ata
p
o
in
ts
.
Pre
cisi
o
n
is
th
e
n
u
m
b
er
o
f
tr
u
e
p
o
s
itiv
e
d
iv
id
e
d
b
y
th
e
s
u
m
o
f
tr
u
e
p
o
s
itiv
e
an
d
f
al
s
e
n
eg
ativ
e
o
r
r
ec
k
less
im
p
r
u
d
en
ce
w
h
ich
is
lab
elled
as
co
n
s
u
m
m
at
ed
.
T
h
e
f
o
r
m
u
la
f
o
r
p
r
ec
is
io
n
is
as (
2
)
:
Pre
cisi
o
n
=
TP
TP
+
FP
(
2
)
2
.
3
.
4
.
F
1
-
Sco
re
Ma
x
im
izin
g
eith
er
r
ec
all
o
r
p
r
ec
is
io
n
to
ass
u
r
e
th
at
th
e
m
o
d
el
will
b
e
s
u
b
s
tan
tial
is
an
a
cc
ep
tab
le
p
r
o
ce
s
s
.
Ho
wev
er
,
it
s
till
s
u
g
g
ested
th
at
b
o
th
o
f
th
em
b
len
d
with
ea
c
h
o
t
h
er
.
F1
-
s
co
r
e
is
b
asically
th
e
h
ar
m
o
n
ic
m
ea
n
o
f
r
ec
all
a
n
d
p
r
ec
is
io
n
.
I
t
g
iv
es
a
n
e
q
u
al
w
eig
h
t
to
b
o
th
m
ea
s
u
r
es;
a
m
et
r
ic
u
s
ed
t
o
cr
ea
te
a
b
alan
ce
m
o
d
el
with
o
p
tim
al
b
alan
ce
o
f
r
ec
all
a
n
d
p
r
ec
is
io
n
.
T
h
e
(
3
)
s
h
o
ws th
e
m
etr
ic
f
o
r
m
u
la
o
f
F
-
s
co
r
e:
F1
-
Sco
r
e
=
2
*
∗
+
(
3
)
2
.
3
.
5
.
Sp
ec
if
icit
y
Sp
ec
if
icity
q
u
an
tifie
s
th
e
ev
as
io
n
o
f
f
alse
p
o
s
itiv
es.
I
t
is
ca
l
led
T
r
u
e
Neg
ativ
e
R
ate,
m
ea
s
u
r
in
g
th
e
p
r
o
p
o
r
tio
n
o
f
n
eg
ati
v
es
th
at
ar
e
co
r
r
ec
tly
i
d
e
n
tifie
d
.
I
t
is
th
e
n
u
m
b
e
r
o
f
tr
u
e
n
eg
ativ
es
d
iv
id
ed
b
y
tr
u
e
n
eg
ativ
es p
lu
s
f
alse p
o
s
itiv
es.
T
h
e
(
4
)
s
h
o
ws th
e
m
etr
ic
f
o
r
m
u
la
o
f
Sp
ec
if
icity
;
Sp
ec
if
icity
=
+
(
4
)
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
I
t
is
a
v
er
y
cr
itical
d
ec
is
io
n
t
o
ch
o
o
s
e
a
class
if
icatio
n
alg
o
r
ith
m
.
T
o
r
eso
lv
e
th
e
ex
is
tin
g
p
r
o
b
lem
,
th
er
e
is
n
o
p
ar
ticu
lar
class
if
icatio
n
alg
o
r
ith
m
.
I
n
o
th
e
r
wo
r
d
s
,
an
y
is
s
u
e
is
n
o
t
s
o
lv
ed
in
th
e
b
est
way
b
y
th
e
b
est
alg
o
r
ith
m
.
Fo
r
d
if
f
er
e
n
t
d
atasets
o
r
d
if
f
er
e
n
t
is
s
u
es,
th
er
e
ar
e
class
if
icatio
n
alg
o
r
ith
m
s
th
at
o
f
f
e
r
d
if
f
er
en
t
r
esu
lts
.
B
ef
o
r
e
g
o
in
g
i
n
to
th
e
d
ee
p
er
in
v
esti
g
atio
n
,
d
if
f
er
en
t
class
if
icatio
n
alg
o
r
ith
m
s
f
o
r
t
h
e
g
iv
en
d
ataset
o
f
s
tag
e
o
f
f
elo
n
y
h
a
v
e
b
ee
n
co
m
p
ar
ed
in
t
h
is
s
tu
d
y
.
T
ab
le
3
s
h
o
ws
th
at
n
eu
r
al
n
etwo
r
k
h
as
a
b
etter
class
if
icatio
n
ca
p
ab
ilit
y
in
p
r
ed
ictin
g
s
tag
e
o
f
f
elo
n
y
.
I
t
g
ar
n
e
r
ed
a
to
tal
ac
c
u
r
ac
y
o
f
8
7
.
6
3
%
a
n
d
0
.
7
5
f
o
r
k
a
p
p
a.
Fro
m
h
er
e,
n
eu
r
al
n
etwo
r
k
will
b
e
th
e
f
o
cu
s
o
f
ev
alu
atio
n
s
in
ce
it
s
h
o
ws
a
v
e
r
y
p
r
o
m
is
in
g
r
esu
lt.
Neu
r
al
n
e
tw
o
r
k
h
as
b
ee
n
co
n
s
id
er
e
d
as
th
e
b
est
class
if
ier
s
ag
ain
s
t sev
er
al
co
m
m
o
n
class
if
ier
s
in
ter
m
s
o
f
ac
c
u
r
ac
y
a
n
d
co
m
p
u
tatio
n
al
e
f
f
icien
cy
.
C
o
n
f
u
s
io
n
m
atr
ix
in
th
e
T
ab
l
e
4
s
h
o
ws
th
at
n
eu
r
al
n
etwo
r
k
is
b
etter
in
class
if
y
in
g
co
n
s
u
m
m
ated
r
ath
er
th
a
n
r
ec
k
less
im
p
r
u
d
en
ce
in
ter
m
s
o
f
n
u
m
b
er
.
Ho
we
v
er
,
th
e
n
u
m
b
er
o
f
c
o
n
s
u
m
m
ated
is
way
h
ig
h
er
th
at
r
ec
k
less
im
p
r
u
d
en
ce
w
h
ich
m
ay
ca
u
s
e
b
ias
in
th
is
p
ar
t.
T
o
tak
e
a
lo
o
k
clo
s
er
to
th
e
r
e
s
u
lt,
it
is
n
ec
es
s
ar
y
to
ev
alu
ate
th
e
n
eu
r
al
n
etwo
r
k
alg
o
r
ith
m
b
ased
o
n
its
ab
ilit
y
to
class
if
y
th
e
s
tag
e
o
f
f
elo
n
y
.
4
7
6
6
a
n
d
7
5
5
ar
e
th
e
ac
tu
al
n
u
m
b
er
o
f
co
n
s
u
m
m
ated
in
th
e
d
ataset,
h
o
we
v
er
,
th
e
alg
o
r
ith
m
class
if
ied
th
e
7
5
5
as
r
ec
k
less
im
p
r
u
d
e
n
ce
,
th
is
h
ap
p
e
n
s
wh
en
s
o
m
e
o
f
th
e
d
ata
h
as
th
e
s
am
e
p
atter
n
.
Sam
e
with
4
8
1
an
d
3
9
9
7
.
Th
e
F1
-
s
co
r
e
in
T
ab
le
5
i
n
d
icate
s
th
at
n
eu
r
al
n
etwo
r
k
is
b
etter
in
class
if
y
in
g
c
o
n
s
u
m
m
ated
th
an
th
e
r
ec
k
less
im
p
r
u
d
e
n
ce
.
T
h
is
g
o
es
to
s
h
o
w
th
at
co
n
s
u
m
m
ated
as
Stag
e
o
f
Felo
n
y
ca
n
p
r
o
v
id
e
ac
cu
r
ate
p
r
e
d
ictio
n
a
n
d
r
eliab
le
s
tatem
en
t in
p
r
ed
ictin
g
th
e
o
cc
u
r
r
en
ce
o
f
r
o
ad
tr
a
f
f
i
c
ac
cid
en
ts
with
in
th
e
r
eg
i
o
n
.
T
ab
le
3
.
Alg
o
r
ith
m
ev
al
u
atio
n
A
l
g
o
r
i
t
h
m
A
c
c
u
r
a
c
y
K
a
p
p
a
D
e
c
i
s
i
o
n
Tr
e
e
7
4
.
2
0
0
.
5
1
k
-
NN
8
2
.
0
1
0
.
6
3
N
a
ï
v
e
B
a
y
e
s
8
6
.
2
8
0
.
7
3
N
e
u
r
a
l
N
e
t
w
o
r
k
8
7
.
6
3
0
.
7
5
T
ab
le
4
.
C
o
n
f
u
s
io
n
m
atr
ix
-
n
e
u
r
al
n
etwo
r
k
t
r
u
e
C
o
n
su
m
mat
e
d
t
r
u
e
R
e
c
k
l
e
ss I
mp
r
u
d
e
n
c
e
P
r
e
d
i
c
t
e
d
C
o
n
s
u
mm
a
t
e
d
4
7
6
6
4
8
1
P
r
e
d
i
c
t
e
d
R
e
c
k
l
e
ss I
mp
r
u
d
e
n
c
e
7
5
5
3
9
9
7
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
Ma
ch
in
e
lea
r
n
in
g
a
p
p
r
o
a
ch
o
n
r
o
a
d
a
cc
id
en
ts
a
n
a
lysi
s
in
C
a
la
b
a
r
z
o
n
…
(
K
r
is
telle
A
n
n
R
.
To
r
r
es
)
997
T
ab
le
5
.
R
esu
lt o
f
n
e
u
r
al
n
etw
o
r
k
ev
al
u
atio
n
S
t
a
g
e
o
f
F
e
l
o
n
y
R
e
c
a
l
l
P
r
e
c
i
s
i
o
n
F1
-
sc
o
r
e
S
p
e
c
i
f
i
c
i
t
y
C
o
n
s
u
mm
a
t
e
d
8
6
.
3
2
9
0
.
8
3
8
8
.
5
2
8
9
.
2
6
R
e
c
k
l
e
ss I
mp
r
u
d
e
n
c
e
8
9
.
2
6
8
4
.
1
1
8
6
.
6
0
8
6
.
3
3
S
h
o
w
n
i
n
F
i
g
u
r
e
2
i
s
t
h
e
p
r
e
d
ic
t
e
d
s
t
a
g
e
o
f
f
el
o
n
y
t
h
a
t
m
a
y
o
c
c
u
r
i
n
e
a
c
h
p
r
o
v
i
n
c
e
.
I
t
c
a
n
b
e
o
b
s
e
r
v
e
d
t
h
a
t
t
h
e
r
e
is
a
h
i
g
h
e
r
c
h
a
n
c
e
o
f
o
c
c
u
r
r
i
n
g
r
e
c
k
l
e
s
s
i
m
p
r
u
d
e
n
c
e
i
n
B
a
ta
n
g
a
s
,
L
a
g
u
n
a
a
n
d
Q
u
e
zo
n
w
h
i
l
e
t
h
e
C
a
v
i
t
e
h
a
s
n
o
c
h
a
n
c
e
o
f
o
c
c
u
r
r
i
n
g
r
e
c
k
l
e
s
s
i
m
p
r
u
d
e
n
c
e
h
o
w
e
v
e
r
a
v
e
r
y
h
i
g
h
p
o
s
s
i
b
i
l
i
t
y
o
f
c
o
n
s
u
m
m
a
t
e
d
.
F
i
g
u
r
e
3
r
e
v
e
a
ls
t
h
a
t
i
n
t
e
r
m
s
o
f
d
a
y
o
f
o
c
c
u
r
r
e
n
c
e
,
c
o
n
s
u
m
m
a
t
e
d
h
a
s
a
h
i
g
h
p
o
s
s
i
b
il
i
t
y
o
f
o
c
c
u
r
r
i
n
g
i
n
S
u
n
d
a
y
s
w
h
i
l
e
r
e
c
k
le
s
s
i
m
p
r
u
d
e
n
c
e
i
s
S
at
u
r
d
a
y
s
.
I
t
c
an
a
l
s
o
b
e
o
b
s
e
r
v
e
d
t
h
at
r
o
a
d
ac
c
i
d
e
n
t
h
as
a
h
i
g
h
c
h
a
n
c
e
i
n
an
y
d
a
y
o
f
t
h
e
w
e
e
k
.
T
h
i
s
r
es
u
l
t c
o
u
l
d
b
e
a
tt
r
i
b
u
t
e
d
to
t
h
e
l
a
r
g
e
v
o
l
u
m
e
o
f
v
e
h
i
c
l
es
e
v
e
r
y
d
a
y
.
P
e
o
p
l
e
g
o
o
u
t e
v
e
r
y
w
e
e
k
d
a
y
f
o
r
w
o
r
k
o
r
t
o
e
n
j
o
y
t
h
e
i
r
d
a
y
s
o
f
f
f
r
o
m
w
o
r
k
e
v
e
r
y
w
e
e
k
e
n
d
.
L
i
k
e
w
i
s
e
,
F
i
g
u
r
e
4
r
e
f
l
e
c
t
s
t
h
at
t
h
e
m
o
n
t
h
o
f
M
a
y
a
n
d
D
e
c
e
m
b
e
r
h
a
s
t
h
e
h
i
g
h
e
s
t
p
r
o
b
a
b
i
l
i
t
y
o
f
o
c
c
u
r
r
i
n
g
r
o
a
d
a
c
c
i
d
e
n
ts
,
s
p
e
ci
f
i
c
a
ll
y
,
r
e
c
k
le
s
s
i
m
p
r
u
d
e
n
c
e
i
n
D
e
c
e
m
b
e
r
a
n
d
c
o
n
s
u
m
m
a
t
e
d
i
n
M
a
y
.
T
h
i
s
r
e
s
u
l
t
i
m
p
l
i
e
d
t
h
e
n
e
e
d
f
o
r
t
h
e
t
r
a
f
f
i
c
m
a
n
a
g
e
r
s
t
o
h
e
i
g
h
t
e
n
t
h
e
t
r
a
f
f
i
c
p
o
l
i
c
i
n
g
d
u
r
i
n
g
t
h
i
s
p
e
r
i
o
d
t
o
r
e
d
u
c
e
t
h
e
p
r
o
b
a
b
i
l
i
t
y
o
f
r
o
a
d
t
r
a
f
f
i
c
a
c
c
i
d
e
n
ts
.
I
t
s
h
o
ws
in
th
e
Fig
u
r
e
5
th
at
p
u
b
lic
v
eh
icle
is
m
o
r
e
p
r
o
n
e
i
n
ac
cid
en
t
r
ath
er
th
a
n
p
r
iv
ate
v
eh
icle
in
b
o
th
co
n
s
u
m
m
ated
a
n
d
r
ec
k
l
ess
im
p
r
u
d
en
ce
.
T
h
e
m
o
s
t
v
u
ln
er
ab
le
r
o
ad
u
s
er
s
ar
e
p
ass
en
g
er
s
o
n
p
u
b
lic
tr
an
s
p
o
r
t
[
3
]
s
in
ce
th
er
e
h
a
p
p
e
n
to
b
e
m
o
r
e
p
ass
en
g
er
s
in
o
n
e
v
eh
icle
[
2
8
]
.
Ma
n
y
in
d
iv
id
u
als
r
ely
o
n
th
is
m
o
d
e
o
f
t
r
an
s
p
o
r
t.
Su
c
h
m
o
d
es
o
f
p
u
b
lic
tr
an
s
p
o
r
t,
with
m
an
y
o
p
e
r
atin
g
illeg
ally
,
ar
e
p
o
o
r
ly
r
e
g
u
lated
an
d
m
an
ag
ed
[
2
8
]
.
O
n
t
h
e
o
t
h
e
r
h
a
n
d
,
i
t
i
s
al
s
o
s
h
o
w
n
i
n
t
h
e
f
i
g
u
r
e
t
h
a
t
t
h
e
r
e
is
s
t
i
ll
a
p
o
s
s
i
b
il
i
t
y
t
h
a
t
p
r
i
v
a
t
e
v
e
h
i
cl
e
m
u
s
t
b
e
i
n
v
o
l
v
e
d
i
n
r
o
a
d
ac
ci
d
e
n
t
.
F
i
g
u
r
e
6
p
r
es
e
n
ts
t
h
a
t
b
o
t
h
c
o
n
s
u
m
m
a
t
e
d
a
n
d
r
e
c
k
l
es
s
i
m
p
r
u
d
e
n
c
e
m
a
y
o
c
c
u
r
b
e
t
w
e
e
n
o
r
o
n
3
:
0
0
p
m
a
n
d
6
:
0
0
p
m
.
Acc
o
r
d
in
g
to
h
g
.
o
r
g
[
2
9
]
,
m
an
y
f
atalities
tr
an
s
p
ir
e
b
etwe
en
6
p
m
an
d
9
p
m
,
a
n
d
3
p
m
t
o
6
p
.
m
.
M
o
s
t
f
a
t
a
l
a
c
ci
d
e
n
t
s
d
u
r
i
n
g
w
o
r
k
i
n
g
d
a
y
s
o
c
c
u
r
b
et
w
e
e
n
5
p
m
a
n
d
6
p
m
.
I
t
c
a
n
b
e
a
l
s
o
n
o
t
e
d
t
h
at
t
h
e
r
e
is
a
h
i
g
h
p
r
o
b
a
b
i
l
i
t
y
t
h
a
t
r
ec
k
l
e
s
s
i
m
p
r
u
d
e
n
c
e
m
a
y
o
c
c
u
r
r
e
d
b
e
t
w
e
e
n
9
:0
0
a
m
a
n
d
1
2
:
0
0
p
m
.
Fig
u
r
e
2
.
C
l
ass
if
ied
s
tag
e
o
f
f
e
lo
n
y
in
ea
c
h
p
r
o
v
in
ce
Fig
u
r
e
3
.
C
lass
if
ied
s
tag
e
o
f
f
e
lo
n
y
b
ased
o
n
th
e
d
ay
o
cc
u
r
r
e
n
ce
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2502
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
2
4
,
No
.
2
,
No
v
em
b
er
20
21
:
9
9
3
-
1
0
0
0
998
Fig
u
r
e
4
.
C
lass
if
ied
s
tag
e
o
f
f
e
lo
n
y
b
ased
o
n
th
e
m
o
n
t
h
o
cc
u
r
r
en
ce
s
Fig
u
r
e
5
.
C
lass
if
ied
s
tag
e
o
f
f
e
lo
n
y
b
ased
o
n
th
e
ty
p
e
o
f
v
e
h
i
cle
Fig
u
r
e
6
.
C
lass
if
ied
s
tag
e
o
f
f
e
lo
n
y
b
ased
o
n
th
e
tim
e
o
f
o
cc
u
r
r
en
ce
4.
C
O
NCLU
SI
O
N
S
A
ND
F
UT
URE WO
RK
S
T
h
e
g
iv
en
d
ata
n
o
ted
th
at
th
e
r
e
is
a
h
ig
h
ac
cid
en
t
f
r
eq
u
en
cy
s
ig
n
if
y
in
g
a
p
r
o
b
lem
atic
an
d
r
em
ed
y
is
n
ee
d
ed
.
T
o
h
elp
th
e
tr
af
f
ic
p
o
l
icy
m
ak
er
s
an
d
g
en
e
r
al
p
u
b
lic
in
p
r
ev
en
tin
g
th
ese
in
cid
en
ts
,
d
ata
m
in
in
g
u
s
in
g
class
if
icatio
n
alg
o
r
ith
m
was
u
tili
ze
d
to
d
ev
elo
p
a
p
r
ed
ictiv
e
m
o
d
el
f
o
r
f
u
tu
r
e
o
cc
u
r
r
en
ce
s
o
f
n
u
m
b
er
s
o
f
tr
af
f
ic
ac
cid
en
ts
.
T
h
e
p
atter
n
s
th
at
wer
e
d
ev
elo
p
ed
u
s
in
g
th
is
in
tellig
en
ce
ar
e
co
n
d
u
civ
e
to
tar
g
ete
d
en
h
a
n
ce
m
e
n
t o
f
th
e
ex
is
tin
g
r
o
ad
s
af
ety
m
ea
s
u
r
es a
n
d
in
th
e
f
u
tu
r
e
r
o
ad
s
af
ety
m
an
ag
e
m
e
n
t.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
Ma
ch
in
e
lea
r
n
in
g
a
p
p
r
o
a
ch
o
n
r
o
a
d
a
cc
id
en
ts
a
n
a
lysi
s
in
C
a
la
b
a
r
z
o
n
…
(
K
r
is
telle
A
n
n
R
.
To
r
r
es
)
999
Dif
f
er
en
t c
lass
if
icatio
n
alg
o
r
ith
m
s
s
u
ch
as d
ec
is
io
n
tr
ee
,
k
-
NN,
n
aïv
e
b
ay
es a
n
d
n
e
u
r
al
n
et
wo
r
k
h
av
e
b
ee
n
co
m
p
a
r
ed
f
o
r
th
e
g
iv
e
n
d
ataset
in
id
en
tify
in
g
b
etter
class
if
ica
tio
n
ca
p
ab
ilit
y
in
c
lass
if
y
in
g
s
tag
e
o
f
f
elo
n
y
.
T
h
e
alg
o
r
ith
m
ev
al
u
atio
n
s
h
o
wed
th
at
t
h
e
n
eu
r
al
n
et
wo
r
k
is
th
e
b
est
alg
o
r
ith
m
in
c
lass
if
y
in
g
th
e
s
tag
e
o
f
f
elo
n
y
.
T
h
e
r
esu
lts
o
f
n
e
u
r
a
l n
etwo
r
k
alg
o
r
ith
m
s
h
o
w
th
at
in
ter
m
s
o
f
p
r
o
v
i
n
ce
,
th
er
e
is
a
g
r
ea
ter
lik
elih
o
o
d
o
f
r
ec
k
less
im
p
r
u
d
en
ce
in
B
a
tan
g
as,
L
ag
u
n
a
a
n
d
Qu
ez
o
n
wh
ile
th
e
C
av
ite
s
h
o
ws
a
v
er
y
h
ig
h
p
o
s
s
ib
ilit
y
o
f
o
cc
u
r
r
e
n
ce
o
f
co
n
s
u
m
m
ated
tr
af
f
ic
ac
cid
en
ts
.
I
n
ter
m
s
o
f
d
ay
o
f
o
cc
u
r
r
en
ce
,
co
n
s
u
m
m
ated
h
as
a
h
i
g
h
p
o
s
s
ib
ilit
y
o
f
o
cc
u
r
r
in
g
in
Su
n
d
ay
s
wh
ile
r
ec
k
less
im
p
r
u
d
en
ce
is
Satu
r
d
ay
s
.
On
th
e
o
th
er
h
an
d
,
m
o
n
th
s
o
f
Ma
y
an
d
Dec
em
b
e
r
h
as
t
h
e
h
ig
h
est
p
r
o
b
ab
ilit
y
o
f
o
cc
u
r
r
i
n
g
r
o
a
d
tr
a
f
f
ic
ac
cid
e
n
ts
;
r
ec
k
l
ess
im
p
r
u
d
en
ce
in
Dec
em
b
er
an
d
co
n
s
u
m
m
ated
in
Ma
y
.
Pu
b
lic
v
eh
icle
is
m
o
r
e
p
r
o
n
e
in
ac
ci
d
en
t
r
at
h
er
th
a
n
p
r
iv
a
te
v
eh
icle
i
n
b
o
th
s
tag
e
o
f
f
elo
n
y
.
An
ac
cid
en
t
m
ay
o
cc
u
r
b
etwe
en
o
r
o
n
3
:0
0
p
m
an
d
6
:
0
0
p
m
.
I
t
is
also
n
o
tice
t
h
at
m
o
s
t
o
f
th
e
ac
cid
en
t r
ec
o
r
d
ed
in
th
e
p
a
s
t f
o
u
r
y
ea
r
s
is
f
r
o
m
th
e
No
r
th
er
n
p
ar
t
o
f
C
av
ite.
B
ased
o
n
th
e
f
in
d
in
g
s
an
d
co
n
clu
s
io
n
s
,
th
er
e
m
ay
b
e
a
n
ee
d
f
o
r
th
e
tr
af
f
ic
m
an
a
g
er
s
,
an
d
p
o
lice
an
d
tr
af
f
ic
o
f
f
icer
s
to
h
eig
h
ten
th
e
ir
p
o
licin
g
d
u
r
i
n
g
th
e
g
iv
en
a
ttrib
u
tes
to
r
ed
u
ce
th
e
p
r
o
b
a
b
ilit
y
o
f
r
o
ad
tr
af
f
ic
ac
cid
en
ts
.
T
r
af
f
ic
m
a
n
ag
er
s
m
ay
co
n
s
id
er
i
m
p
r
o
v
in
g
th
ei
r
ex
is
tin
g
ac
tio
n
p
lan
s
an
d
p
r
ev
en
tiv
e
m
ea
s
u
r
es
b
ased
o
n
th
e
p
r
e
d
ictiv
e
m
o
d
el
p
r
esen
ted
in
t
h
is
r
esear
ch
.
T
r
af
f
ic
m
an
a
g
er
s
an
d
p
o
licy
m
a
k
er
s
m
ay
co
n
s
id
er
th
e
ap
p
licatio
n
o
f
d
ata
m
in
i
n
g
tech
n
iq
u
es
u
s
in
g
class
if
icatio
n
alg
o
r
ith
m
i
n
f
o
r
m
u
latio
n
o
f
r
elate
d
p
lan
s
,
p
r
o
g
r
a
m
s
,
an
d
m
ea
s
u
r
es
o
n
r
o
ad
tr
af
f
ic
s
af
ety
.
L
astl
y
,
th
e
f
u
tu
r
e
r
esear
ch
e
r
s
m
ay
co
n
d
u
ct
s
im
ilar
s
tu
d
y
u
s
in
g
o
th
er
class
if
icatio
n
alg
o
r
ith
m
s
f
o
r
f
u
r
th
er
v
alid
ity
o
f
th
e
p
r
esen
t f
in
d
in
g
s
.
ACK
NO
WL
E
DG
E
M
E
NT
T
h
e
au
th
o
r
s
wo
u
ld
lik
e
to
ex
p
r
ess
th
eir
g
r
atitu
d
e
to
th
e
L
ag
u
n
a
State
Po
ly
tech
n
ic
Un
iv
er
s
ity
f
o
r
th
eir
co
n
s
tan
t
s
u
p
p
o
r
t
in
f
u
lf
i
llin
g
th
is
s
tu
d
y
,
an
d
to
th
e
R
I
DM
D
-
Ph
ilip
p
in
e
Natio
n
al
Po
lice
R
eg
io
n
I
V
-
A
(C
alab
ar
zo
n
),
i
n
p
r
o
v
id
in
g
th
e
d
atasets
in
ac
co
m
p
lis
h
in
g
th
is
r
esear
ch
s
tu
d
y
.
RE
F
E
R
E
NC
E
S
[1
]
D.
De
m
e
a
n
d
M
.
Ba
ri,
“
Traffic
Ac
c
id
e
n
t
Ca
u
se
s
a
n
d
I
ts
Co
u
n
ter
m
e
a
su
re
s
o
n
Ad
d
is
Ab
a
b
a
-
Ad
a
m
a
Ex
p
re
ss
wa
y
,”
J
o
u
rn
a
l
o
f
E
q
u
it
y
i
n
S
c
ien
c
e
a
n
d
S
u
sta
in
a
b
le De
v
e
lo
p
me
n
t,
v
o
l.
2
,
n
o
.
2
,
p
p
.
1
3
-
2
3
.
2
0
1
8
.
[2
]
C.
Wan
g
d
i
,
M
.
S
.
G
u
ru
n
g
,
T.
Du
b
a
,
E.
Wi
l
k
in
s
o
n
,
Z
.
M
.
T
u
n
,
a
n
d
J.
P
.
Tri
p
a
t
h
y
,
“
Bu
rd
e
n
,
p
a
tt
e
r
n
a
n
d
c
a
u
se
s
o
f
ro
a
d
traffic
a
c
c
id
e
n
ts
in
B
h
u
tan
,
2
0
1
3
-
2
0
1
4
:
a
p
o
li
c
e
re
c
o
rd
re
v
ie
w,”
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
In
j
u
ry
Co
n
tr
o
l
a
n
d
S
a
fety
Pro
m
o
ti
o
n
,
v
o
l.
2
5
,
n
o
.
1
,
p
p
.
65
-
6
9
,
M
a
r.
2
0
1
8
,
d
o
i:
1
0
.
1
0
8
0
/1
7
4
5
7
3
0
0
.
2
0
1
7
.
1
3
4
1
9
3
0
.
[3
]
S
.
G
o
p
a
lak
rish
n
a
n
,
“
A
p
u
b
li
c
h
e
a
lt
h
p
e
rsp
e
c
ti
v
e
o
f
ro
a
d
traffic
a
c
c
id
e
n
ts
,”
J
o
u
rn
a
l
o
f
F
a
mily
M
e
d
icin
e
a
n
d
Prima
ry
Ca
re
,
v
o
l.
1
,
n
o
.
2
,
p
p
.
1
4
4
-
1
5
0
,
Ju
l
y
2
0
1
2
,
d
o
i:
1
0
.
4
1
0
3
/2
2
4
9
-
4
8
6
3
.
1
0
4
9
8
7
.
[4
]
M
.
K.
G
e
b
ru
,
“
Ro
a
d
traffic
a
c
c
id
e
n
t:
H
u
m
a
n
se
c
u
rit
y
p
e
rsp
e
c
ti
v
e
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Pe
a
c
e
a
n
d
De
v
e
lo
p
me
n
t
S
t
u
d
ies
,
v
o
l.
8
,
n
o
.
2
,
p
p
.
1
5
-
2
4
,
2
0
1
7
,
d
o
i
:
1
0
.
5
8
9
7
/I
JPDS
2
0
1
6
.
0
2
8
9
.
[5
]
M
.
M
.
P
e
d
e
n
a
n
d
P
.
P
u
v
a
n
a
c
h
a
n
d
ra
,
“
L
o
o
k
i
n
g
b
a
c
k
o
n
1
0
y
e
a
rs
o
f
g
lo
b
a
l
r
o
a
d
sa
fe
ty
,
”
In
ter
n
a
ti
o
n
a
l
He
a
lt
h
,
v
o
l.
1
1
,
n
o
.
5
,
p
p
.
3
2
7
-
3
3
0
,
2
0
1
9
,
d
o
i:
1
0
.
1
0
9
3
/i
n
th
e
a
lt
h
/i
h
z
0
4
2
.
[6
]
Wo
rld
He
a
lt
h
Or
g
a
n
iza
ti
o
n
.
R
o
a
d
tra
ff
ic
in
j
u
rie
s
.
2
0
2
1
.
Ac
c
e
ss
e
d
:
Ja
n
u
a
ry
2
4
,
2
0
2
1
.
[On
l
in
e
].
Av
a
il
a
b
le:
h
tt
p
s:/
/www
.
wh
o
.
in
t/
n
e
ws
-
ro
o
m
/f
a
c
t
-
sh
e
e
ts/d
e
tail/
ro
a
d
-
traffic
-
in
j
u
r
ies
[7
]
M
.
R.
G
h
a
d
irza
d
e
h
e
t
a
l
.
,
“
S
tat
u
s a
n
d
tren
d
o
f
d
e
a
th
s
d
u
e
to
traffic a
c
c
id
e
n
ts
fro
m
2
0
0
1
t
o
2
0
1
0
i
n
Ir
a
n
,”
Ira
n
i
a
n
J
.
Ep
id
e
mi
o
l
,
v
o
l
.
1
1
,
n
o
.
2
,
p
p
.
1
3
-
2
2
,
N
o
v
.
2
0
1
5
.
[O
n
li
n
e
].
Av
a
il
a
b
l
e
:
h
tt
p
s:
//
irj
e
.
t
u
m
s.a
c
.
ir/
a
rti
c
le
-
1
-
5
3
8
7
-
e
n
.
h
tml
[8
]
Wo
rld
He
a
lt
h
Org
a
n
iza
ti
o
n
.
Ped
e
stria
n
sa
fety
:
a
ro
a
d
sa
fety
ma
n
u
a
l
fo
r
d
e
c
isio
n
-
ma
k
e
rs
a
n
d
p
ra
c
ti
ti
o
n
e
rs
.
2
0
1
3
.
Ac
c
e
ss
e
d
:
Ap
ril
8
,
2
0
2
0
.
[O
n
li
n
e
]
.
Av
a
il
a
b
le:
h
tt
p
s://
ww
w.wh
o
.
in
t/
p
u
b
li
c
a
ti
o
n
s/i/
it
e
m
/p
e
d
e
strian
-
sa
fe
ty
-
a
-
ro
a
d
-
sa
fe
ty
-
m
a
n
u
a
l
-
fo
r
-
d
e
c
isio
n
-
m
a
k
e
rs
-
a
n
d
-
p
ra
c
ti
ti
o
n
e
rs
[9
]
Z.
Ha
li
m
,
R.
Ka
lso
o
m
,
S
.
Ba
sh
ir
,
a
n
d
G
.
Ab
b
a
s,
“
Artifi
c
ial
i
n
telli
g
e
n
c
e
tec
h
n
iq
u
e
s
fo
r
d
riv
in
g
sa
fe
ty
a
n
d
v
e
h
icl
e
c
ra
sh
p
re
d
ictio
n
,
”
Arti
fi
c
ia
l
In
telli
g
e
n
c
e
Rev
iew
,
v
o
l
.
4
6
,
p
p
.
3
5
1
-
3
8
7
,
F
e
b
.
2
0
1
6
,
d
o
i:
1
0
.
1
0
0
7
/s
1
0
4
6
2
-
0
1
6
-
9
4
6
7
-
9
.
[
10
]
G
.
Am
p
a
n
o
z
i
e
t
a
l
.
,
“
An
a
l
y
s
is
o
f
fa
tal
m
o
to
r
v
e
h
icle
c
o
ll
isio
n
s:
e
v
i
d
e
n
c
e
fr
o
m
Ce
n
tr
a
l
M
a
c
e
d
o
n
ia,
G
re
e
c
e
,
”
Hip
p
o
k
ra
ti
a
,
v
o
l.
1
5
,
n
o
.
1
,
p
p
.
3
2
-
3
6
.
Ja
n
.
2
0
1
1
.
[1
1
]
G
.
Ch
e
n
g
,
R.
C
h
e
n
g
,
Y.
P
e
i
,
a
n
d
L.
X
u
,
“
P
r
o
b
a
b
il
it
y
o
f
ro
a
d
si
d
e
a
c
c
id
e
n
ts
fo
r
c
u
r
v
e
d
se
c
ti
o
n
s
o
n
h
ig
h
wa
y
s,”
M
a
t
h
e
ma
ti
c
a
l
Pro
b
lem
s in
E
n
g
in
e
e
rin
g
,
v
o
l.
2
0
2
0
,
M
a
y
2
0
2
0
,
d
o
i
:
1
0
.
1
1
5
5
/2
0
2
0
/9
6
5
6
4
3
4
.
[1
2
]
S
.
Ku
m
a
r
a
n
d
D.
J.
To
sh
n
iwa
l
,
“
An
a
ly
sis
o
f
h
o
u
rl
y
ro
a
d
a
c
c
id
e
n
t
c
o
u
n
ts
u
si
n
g
h
iera
rc
h
ica
l
c
lu
ste
rin
g
a
n
d
c
o
p
h
e
n
e
ti
c
c
o
rre
latio
n
c
o
e
fficie
n
t
(CP
CC)
,
”
J
o
u
rn
a
l
o
f
Bi
g
D
a
ta
,
v
o
l
.
3
,
n
o
.
1
3
,
Ju
l
y
2
0
1
6
,
doi
:
1
0
.
1
1
8
6
/s4
0
5
3
7
-
0
1
6
-
0
0
4
6
-
3
.
[1
3
]
C.
Vig
n
e
sh
k
u
m
a
r,
A.
Ra
m
a
c
h
a
n
d
ra
n
,
a
n
d
K.
R.
Yo
g
a
n
a
th
a
n
,
“
A
c
o
m
p
a
ra
ti
v
e
stu
d
y
o
n
r
o
a
d
sa
fe
ty
situ
a
ti
o
n
i
n
In
d
ia wit
h
se
lec
ted
d
e
v
e
l
o
p
e
d
c
o
u
n
tri
e
s
,
”
In
t.
J
.
Eme
rg
.
T
re
n
d
s
En
g
.
De
v
e
lo
p
.
,
v
o
l.
3
,
n
o
.
5
,
p
p
.
5
5
-
62
,
Ap
r
.
2
0
1
5
.
[1
4
]
B.
Ag
y
e
m
a
n
g
,
G
.
K.
Ab
led
u
,
a
n
d
R.
S
e
m
e
v
o
h
,
“
Re
g
re
ss
io
n
a
n
a
ly
sis
o
f
ro
a
d
traffic
a
c
c
id
e
n
ts
a
n
d
p
o
p
u
lati
o
n
g
ro
wt
h
in
G
h
a
n
a
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
B
u
sin
e
ss
a
n
d
S
o
c
i
a
l
Res
e
a
rc
h
(IJ
BS
R),
v
o
l.
3
,
n
o
.
1
0
,
p
p
.
4
1
-
47,
Oc
to
b
e
r
2
0
1
3
.
[1
5
]
F
.
F
.
Ba
lah
a
d
ia,
J.
R.
As
o
r
,
G
.
M
.
Ca
ted
ril
la,
M
.
Vill
a
rica
,
a
n
d
J.
M
.
Ca
b
ien
te,
“
I
n
telli
g
e
n
t
i
n
v
e
stig
a
ti
o
n
o
n
c
rime
in
c
id
e
n
t
re
p
o
r
ts
in
th
e
p
ro
v
in
c
e
o
f
La
g
u
n
a
th
r
o
u
g
h
p
re
d
icti
v
e
m
o
d
e
l
d
e
v
e
lo
p
m
e
n
t
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Ad
v
a
n
c
e
d
T
re
n
d
s
i
n
C
o
mp
u
ter
S
c
ien
c
e
a
n
d
En
g
i
n
e
e
rin
g
,
v
o
l.
9
,
n
o
.
1
.
3
,
p
p
.
1
3
9
-
1
4
4
,
2
0
2
0
,
d
o
i:
1
0
.
3
0
5
3
4
/
ij
a
tcs
e
/2
0
2
0
/
2
0
9
1
.
3
2
0
2
0
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2502
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
2
4
,
No
.
2
,
No
v
em
b
er
20
21
:
9
9
3
-
1
0
0
0
1000
[1
6
]
J.
R.
As
o
r
a
n
d
S
.
B
.
S
a
p
in
,
“
Im
p
l
e
m
e
n
tatio
n
o
f
p
re
d
ictiv
e
c
rime
a
n
a
ly
ti
c
s
in
m
u
n
icip
a
l
c
rime
m
a
n
a
g
e
m
e
n
t
sy
ste
m
in
Ca
lau
a
n
,
Lag
u
n
a
,
P
h
il
i
p
p
i
n
e
s,”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Ad
v
a
n
c
e
d
T
re
n
d
s
in
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
i
n
e
e
rin
g
,
v
o
l.
9
,
n
o
.
1
.
3
,
p
p
.
1
5
0
-
1
5
7
,
2
0
2
0
,
d
o
i
:
1
0
.
3
0
5
3
4
/i
jatc
se
/2
0
2
0
/2
2
9
1
.
3
2
0
2
0
.
[1
7
]
J.
R.
As
o
r,
G
.
M
.
B.
Ca
ted
ril
la
,
a
n
d
J.
E.
Estra
d
a
,
“
A
stu
d
y
o
n
th
e
ro
a
d
a
c
c
id
e
n
ts
u
si
n
g
d
a
ta
i
n
v
e
stig
a
ti
o
n
a
n
d
v
isu
a
li
z
a
ti
o
n
i
n
Lo
s
Ba
ñ
o
s,
Lag
u
n
a
,
P
h
il
i
p
p
i
n
e
s
,”
2
0
1
8
I
n
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
I
n
f
o
rm
a
ti
o
n
a
n
d
Co
mm
u
n
ica
ti
o
n
s T
e
c
h
n
o
l
o
g
y
(IC
OIACT
)
,
2
0
1
8
,
p
p
.
9
6
-
1
0
1
,
d
o
i:
1
0
.
1
1
0
9
/ICOIACT.
2
0
1
8
.
8
3
5
0
6
6
2
.
[1
8
]
M
.
Ab
d
u
lk
a
b
ir,
R.
S
.
T
u
n
d
e
,
a
n
d
U.
A.
Ed
e
m
,
“
Tren
d
a
n
a
l
y
si
s
o
n
ro
a
d
traffic
a
c
c
id
e
n
t
in
Ni
g
e
ria
,”
S
c
ien
c
e
In
n
o
v
a
ti
o
n
,
v
o
l.
3
,
n
o
.
5
,
p
p
.
5
2
-
5
7
,
S
e
p
t.
2
0
1
5
,
d
o
i:
1
0
.
1
1
6
4
8
/j
.
si
.
2
0
1
5
0
3
0
5
.
1
2
.
[1
9
]
M
.
P
a
rv
a
re
h
e
t
a
l
.
,
“
As
se
ss
m
e
n
t
a
n
d
p
re
d
ictio
n
o
f
ro
a
d
a
c
c
id
e
n
t
in
j
u
ries
tren
d
u
sin
g
ti
m
e
-
se
ries
m
o
d
e
ls
in
Ku
rd
istan
,”
Bu
rn
T
ra
u
ma
,
v
o
l.
6
,
n
o
.
9
,
M
a
r.
2
0
1
8
,
d
o
i
:
1
0
.
1
1
8
6
/s
4
1
0
3
8
-
0
1
8
-
0
1
1
1
-
6
.
[2
0
]
A.
Brz
o
z
o
ws
k
a
,
D.
Bu
b
e
l,
a
n
d
A.
Ka
li
n
ich
e
n
k
o
,
“
An
a
ly
sis
o
f
th
e
ro
a
d
traffic
m
a
n
a
g
e
m
e
n
t
sy
ste
m
in
t
h
e
n
e
u
ra
l
n
e
two
rk
d
e
v
e
l
o
p
m
e
n
t
p
e
rsp
e
c
ti
v
e
,
”
Ea
ste
rn
-
E
u
ro
p
e
a
n
J
o
u
rn
a
l
o
f
En
ter
p
rise
T
e
c
h
n
o
lo
g
ies
,
vol
.
2
,
n
o
.
3
,
p
p
.
1
6
-
2
4
,
M
a
r.
2
0
1
9
,
d
o
i:
1
0
.
1
5
5
8
7
/
1
7
2
9
-
4
0
6
1
.
2
0
1
9
.
1
6
0
0
4
9
.
[2
1
]
T.
P
a
m
u
la,
“
R
o
a
d
traffic
p
a
ra
m
e
ters
p
re
d
ictio
n
in
u
r
b
a
n
traffic
m
a
n
a
g
e
m
e
n
t
sy
ste
m
s
u
sin
g
n
e
u
ra
l
n
e
two
rk
s,”
T
ra
n
s
p
o
rt
Pro
b
lem
s
,
v
o
l.
6
,
n
o
.
3
,
p
p
.
1
2
3
-
1
2
8
.
2
0
1
1
.
[2
2
]
Q
.
Z
e
n
g
,
H
.
H
u
a
n
g
,
X
.
P
e
i
,
S
.
C
.
W
o
n
g
,
a
n
d
M
.
G
a
o
,
“
R
u
l
e
e
x
t
r
a
c
t
i
o
n
f
r
o
m
a
n
o
p
t
i
m
i
z
e
d
n
e
u
r
a
l
n
e
t
w
o
r
k
f
o
r
t
r
a
f
f
i
c
c
r
a
s
h
f
r
e
q
u
e
n
c
y
m
o
d
e
l
i
n
g
,
”
A
c
c
i
d
e
n
t
A
n
a
l
y
s
i
s
&
P
r
e
v
e
n
t
i
o
n
,
v
o
l
.
97
,
p
p
.
8
7
-
9
5
,
D
e
c
.
2
0
1
6
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
a
p
.
2
0
1
6
.
0
8
.
0
1
7
.
[2
3
]
A.
Ata
,
M
.
A.
Kh
a
n
,
S
.
Ab
b
a
s,
G
.
Ah
m
a
d
,
a
n
d
A.
F
a
ti
m
a
,
“
M
o
d
e
ll
in
g
sm
a
rt
ro
a
d
traffic
c
o
n
g
e
sti
o
n
c
o
n
tro
l
sy
ste
m
u
sin
g
m
a
c
h
i
n
e
lea
rn
in
g
tec
h
n
iq
u
e
s,”
Ne
u
ra
l
Ne
two
rk
W
o
rld
,
v
o
l.
29
,
n
o
.
2
,
p
p
.
9
9
-
1
1
0
,
2
0
1
9
,
d
o
i:
1
0
.
1
4
3
1
1
/NNW
.
2
0
1
9
.
2
9
.
0
0
8
.
[2
4
]
M
.
S
ril
a
th
a
,
N.
Va
m
sh
i,
R.
A
n
iru
th
,
P
.
Na
re
n
d
a
r,
a
n
d
C.
Ha
re
e
sh
,
“
Au
to
m
a
ti
c
Ac
c
id
e
n
t
Av
o
i
d
a
n
c
e
a
n
d
De
tec
ti
o
n
S
y
ste
m
u
sin
g
Lab
VIEW
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
A
d
v
a
n
c
e
d
T
re
n
d
s
in
Co
mp
u
ter
S
c
ien
c
e
a
n
d
E
n
g
in
e
e
rin
g
,
v
o
l.
9
n
o
.
4
,
p
p
.
5
3
1
4
-
5
3
1
9
,
2
0
2
0
,
d
o
i:
1
0
.
3
0
5
3
4
/
ij
a
tcs
e
/2
0
2
0
/
1
6
4
9
4
2
0
2
0
.
[2
5
]
S
.
L.
Ti
n
g
,
W.
H
.
Ip
,
a
n
d
A.
H.
C.
Tsa
n
g
,
“
Is
Na
iv
e
Ba
y
e
s
a
g
o
o
d
c
las
sifier
fo
r
d
o
c
u
m
e
n
t
c
las
sifi
c
a
ti
o
n
,
”
i
n
In
t.
J
.
S
o
ft
w
.
En
g
.
Ap
p
l.
,
v
o
l.
5
,
n
o
.
3
,
p
p
.
3
7
-
4
6
,
2
0
1
1
.
[2
6
]
J.
R.
As
o
r
a
n
d
M
.
A.
T.
S
u
b
i
o
n
,
“
RES
EARCH+
+
:
An
Ac
a
d
e
m
ic
S
o
c
ial
Ne
two
r
k
in
g
Re
se
a
rc
h
Co
m
m
u
n
it
y
P
o
rtal
fo
r
P
ro
f
il
in
g
a
n
d
Ex
p
e
rti
se
Clas
sifica
ti
o
n
,
”
2
0
1
8
In
ter
n
a
ti
o
n
a
l
S
e
min
a
r
o
n
Res
e
a
rc
h
o
f
I
n
fo
rm
a
t
io
n
T
e
c
h
n
o
lo
g
y
a
n
d
In
tell
ig
e
n
t
S
y
ste
ms
(IS
RI
T
I)
,
2
0
1
8
,
p
p
.
4
7
0
-
4
7
5
,
d
o
i:
1
0
.
1
1
0
9
/I
S
RITI.
2
0
1
8
.
8
8
6
4
4
8
3
.
[2
7
]
G
.
M
.
B.
Ca
ted
ril
la
a
n
d
J.
R.
As
o
r.
“
P
a
tt
e
rn
Re
c
o
g
n
it
i
o
n
fr
o
m
Ra
d
io
lo
g
y
Re
p
o
rts
to
wa
rd
s
P
re
d
icti
v
e
Lu
n
g
Dise
a
se
M
a
n
ifes
tatio
n
in
M
u
n
icip
a
l
S
e
tt
i
n
g
s
,
”
2
0
1
8
I
n
ter
n
a
ti
o
n
a
l
S
e
mi
n
a
r
o
n
Res
e
a
rc
h
o
f
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
l
o
g
y
a
n
d
In
telli
g
e
n
t
S
y
ste
ms
(IS
R
IT
I)
,
2
0
1
8
,
p
p
.
4
7
6
-
4
8
0
,
d
o
i:
1
0
.
1
1
0
9
/I
S
RI
TI.
2
0
1
8
.
8
8
6
4
2
4
1
.
[2
8
]
T
.
B
.
J
o
e
w
o
n
o
,
a
n
d
H
.
K
u
b
o
t
a
,
“
S
a
f
e
t
y
a
n
d
s
e
c
u
r
i
t
y
i
m
p
r
o
v
e
m
e
n
t
i
n
p
u
b
l
i
c
t
r
a
n
s
p
o
r
t
a
t
i
o
n
b
a
s
e
d
o
n
p
u
b
l
i
c
p
e
r
c
e
p
t
i
o
n
i
n
d
e
v
e
l
o
p
i
n
g
c
o
u
n
t
r
i
e
s
,
”
I
A
T
S
S
R
e
s
e
a
r
c
h
,
v
o
l
.
30,
n
o
.
1
,
p
p
.
8
6
-
1
0
0
.
2
0
0
6
,
d
o
i
:
1
0
.
1
0
1
6
/
S
0
3
8
6
-
1
1
1
2
(
1
4
)
6
0
1
5
9
-
X
.
[2
9
]
HG
.
o
rg
.
Fa
t
a
l
Ca
r
Acc
id
e
n
t
S
t
a
ti
stics
.
(2
0
2
0
).
Ac
c
e
ss
e
d
:
S
e
p
t.
2
9
,
2
0
2
0
.
[On
l
in
e
].
Av
a
il
a
b
le:
h
tt
p
s:/
/www
.
h
g
.
o
r
g
/l
e
g
a
l
-
a
rti
c
les
/
fa
tal
-
car
-
a
c
c
id
e
n
t
-
sta
ti
stics
-
2
9
8
3
6
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
K
r
iste
ll
e
Ann
R.
To
r
r
e
s
is
a
fa
c
u
lt
y
m
e
m
b
e
r
a
n
d
d
e
sig
n
a
te
d
a
s
Re
se
a
rc
h
a
n
d
De
v
e
lo
p
m
e
n
t
Im
p
lem
e
n
ti
n
g
Un
i
t
He
a
d
o
f
th
e
Co
ll
e
g
e
o
f
Crimin
a
l
Ju
stice
Ed
u
c
a
ti
o
n
o
f
th
e
Lag
u
n
a
S
tate
P
o
ly
tec
h
n
ic
U
n
iv
e
rsit
y
-
Lo
s
Ba
ñ
o
s
Ca
m
p
u
s.
S
h
e
is
a
n
a
lu
m
n
a
o
f
Ba
tan
g
a
s
S
tate
Un
iv
e
rsity
-
JPL
P
C
M
a
lv
a
r
Ca
m
p
u
s
wh
e
re
sh
e
c
o
m
p
lete
d
h
e
r
b
a
c
h
e
lo
r’s
d
e
g
re
e
in
Crimin
o
l
o
g
y
.
S
h
e
is
a
re
g
istere
d
c
rimin
o
l
o
g
ist.
S
h
e
a
ls
o
c
o
m
p
lete
d
h
e
r
M
a
ste
r
o
f
S
c
ien
c
e
in
Crimin
a
l
Ju
stice
with
sp
e
c
ializa
ti
o
n
in
Crimi
n
o
l
o
g
y
,
a
n
d
with
Ac
a
d
e
m
ic
Distin
c
ti
o
n
in
2
0
1
9
a
t
De
La
S
a
ll
e
Un
iv
e
rsity
-
Da
sm
a
ri
ñ
a
s.
S
h
e
is
c
u
rre
n
tl
y
p
u
rsu
in
g
h
e
r
Do
c
t
o
r
o
f
P
h
il
o
so
p
h
y
d
e
g
re
e
in
Cr
imin
a
l
Ju
stice
with
sp
e
c
ializa
ti
o
n
i
n
Cri
m
in
o
lo
g
y
a
t
L
y
c
e
u
m
o
f
P
h
il
i
p
p
in
e
s Un
iv
e
rsity
-
Ba
tan
g
a
s.
J
o
n
a
r
d
o
R.
As
o
r
wa
s b
o
r
n
i
n
L
o
s
Ba
ñ
o
s,
La
g
u
n
a
,
P
h
il
i
p
p
i
n
e
s
o
n
J
u
n
e
1
2
,
1
9
9
0
.
He
g
ra
d
u
a
ted
a
t
th
e
Lag
u
n
a
S
tate
P
o
ly
tec
h
n
ic
Un
iv
e
rsit
y
-
Lo
s
Ba
ñ
o
s
c
a
m
p
u
s
with
t
h
e
d
e
g
re
e
b
a
c
h
e
lo
r
o
f
sc
ien
c
e
in
in
f
o
rm
a
ti
o
n
tec
h
n
o
l
o
g
y
o
n
M
a
rc
h
2
0
1
6
.
M
r.
As
o
r
fi
n
ish
e
d
h
is
m
a
ste
r
i
n
i
n
fo
rm
a
ti
o
n
tec
h
n
o
l
o
g
y
d
e
g
re
e
a
t
th
e
Tec
h
n
o
lo
g
ica
l
I
n
stit
u
te
o
f
th
e
P
h
il
i
p
p
i
n
e
s
-
M
a
n
il
a
,
o
n
Oc
to
b
e
r
2
0
1
8
.
He
is
c
u
rre
n
tl
y
wo
r
k
in
g
a
s
Co
l
leg
e
In
str
u
c
to
r
a
t
th
e
Lag
u
n
a
S
tate
P
o
l
y
tec
h
n
ic
U
n
iv
e
rsit
y
-
L
o
s
Ba
ñ
o
s
Ca
m
p
u
s,
M
a
li
n
ta,
Lo
s
B
a
ñ
o
s,
Lag
u
n
a
,
P
h
i
li
p
p
in
e
s.
He
p
u
b
li
s
h
e
d
so
m
e
o
f
h
is
p
a
p
e
r
in
c
lu
d
in
g
h
is
m
a
ste
r
th
e
sis
a
t
d
iff
e
re
n
t
c
o
ll
o
q
u
i
u
m
sp
o
n
so
re
d
b
y
I
EE
E
wh
e
re
a
s
th
e
p
a
p
e
rs
a
re
a
ll
in
IEE
E
x
p
lo
re
Dig
it
a
l
Li
b
ra
ry
a
n
d
in
d
e
x
e
d
i
n
S
c
o
p
u
s.
His
re
se
a
rc
h
stu
d
y
f
o
c
u
se
s
o
n
t
h
e
o
p
ti
m
iza
ti
o
n
a
n
d
u
sa
g
e
o
f
m
a
c
h
i
n
e
lea
rn
in
g
a
l
g
o
r
it
h
m
a
n
d
k
n
o
wle
d
g
e
d
isc
o
v
e
ry
i
n
d
a
tab
a
se
s.
Evaluation Warning : The document was created with Spire.PDF for Python.