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
.
1
,
Octo
b
er
2
0
2
1
,
p
p
.
44
4
~
4
5
1
I
SS
N:
2
5
0
2
-
4
7
5
2
,
DOI
: 1
0
.
1
1
5
9
1
/ijeecs.v
24
.i
1
.
pp
444
-
4
5
1
444
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs.ia
esco
r
e.
co
m
Incident
f
o
recas
ti
ng
mo
del f
o
r mo
t
o
rcycle driv
ing
b
a
sed o
n Io
T
a
nd
a
rtif
icia
l i
ntel
lig
ence
E
s
t
eba
n Ale
j
a
nd
ro
Cá
rdena
s
-
L
a
nchero
s
1
,
Nel
s
o
n E
nriqu
e
Ver
a
-
P
a
rr
a
2
1,
2
F
a
c
u
lt
y
o
f
En
g
in
e
e
rin
g
,
U
n
iv
e
r
sid
a
d
Distrit
a
l
F
ra
n
c
isc
o
Jo
sé
d
e
Ca
ld
a
s,
Bo
g
o
tá,
C
o
lo
m
b
ia
2
G
ICO
G
E
Re
se
a
rc
h
g
ro
u
p
,
Un
i
v
e
rsid
a
d
Distrit
a
l
F
ra
n
c
isc
o
Jo
sé
d
e
Ca
ld
a
s,
Bo
g
o
tá,
C
o
lo
m
b
ia
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Ju
n
3
,
2021
R
ev
is
ed
Au
g
4
,
2
0
2
1
Acc
ep
ted
Au
g
7
,
2
0
2
1
In
tern
e
t
o
f
t
h
in
g
s
(Io
T)
a
n
d
a
rti
ficia
l
in
telli
g
e
n
c
e
p
r
o
v
i
d
e
m
o
re
a
n
d
m
o
re
so
lu
ti
o
n
s
to
t
h
e
e
x
e
rc
ise
o
f
c
a
p
t
u
rin
g
d
a
ta
e
ffe
c
ti
v
e
ly
,
tak
in
g
t
h
e
m
th
ro
u
g
h
p
ro
c
e
ss
in
g
a
n
d
a
n
a
ly
sis
sta
g
e
s
t
o
e
x
trac
t
v
a
l
u
a
b
le
in
f
o
rm
a
ti
o
n
.
Cu
rre
n
tl
y
,
tec
h
n
o
l
o
g
ica
l
t
o
o
ls
a
re
a
p
p
li
e
d
t
o
c
o
u
n
tera
c
t
i
n
c
id
e
n
ts
i
n
m
o
t
o
rc
y
c
le
d
riv
i
n
g
,
wh
e
th
e
r
th
e
y
a
re
p
a
rt
o
f
th
e
sa
m
e
v
e
h
icle
o
r
a
re
e
x
tern
a
ll
y
i
n
v
o
l
v
e
d
i
n
th
e
e
n
v
iro
n
m
e
n
t.
In
c
i
d
e
n
ts
i
n
m
o
to
rc
y
c
le
d
riv
in
g
a
re
in
c
re
a
sin
g
d
u
e
to
th
e
d
e
m
a
n
d
fo
r
th
e
a
c
q
u
isit
i
o
n
o
f
t
h
e
se
v
e
h
icle
s,
wh
ich
m
a
k
e
s
it
im
p
o
rtan
t
to
g
e
n
e
ra
te
a
n
a
p
p
r
o
a
c
h
to
wa
rd
s
re
d
u
c
in
g
t
h
e
risk
o
f
r
o
a
d
a
c
c
id
e
n
ts
b
a
se
d
o
n
th
e
a
n
a
ly
sis
o
f
d
y
n
a
m
ic
b
e
h
a
v
i
o
r
wh
il
e
d
riv
in
g
.
T
h
e
d
e
v
e
l
o
p
m
e
n
t
o
f
t
h
is
re
se
a
rc
h
b
e
g
a
n
wit
h
t
h
e
d
e
tec
ti
o
n
a
n
d
st
o
ra
g
e
o
f
d
a
ta
a
ss
o
c
iate
d
with
th
e
d
y
n
a
m
ic
a
c
c
e
lera
ti
o
n
v
a
riab
le
o
f
a
m
o
to
rc
y
c
le
wh
il
e
d
riv
in
g
,
th
i
s
with
th
e
h
e
lp
o
f
a
3
-
a
x
is
a
c
c
e
lero
m
e
ter
se
n
so
r
g
e
n
e
ra
ti
n
g
a
d
a
tas
e
t,
wh
ich
wa
s
p
ro
c
e
ss
e
d
a
n
d
a
n
a
ly
z
e
d
f
o
r
late
r
b
e
tak
e
n
b
y
t
h
re
e
p
re
d
icti
v
e
c
las
sifica
ti
o
n
m
o
d
e
ls
b
a
se
d
o
n
m
a
c
h
in
e
lea
rn
in
g
w
h
ich
we
re
d
e
c
isio
n
tree
s
,
K
-
Ne
a
re
st
n
e
i
g
h
b
o
rs
a
n
d
ra
n
d
o
m
fo
re
sts
.
T
h
e
p
e
rfo
rm
a
n
c
e
o
f
e
a
c
h
m
o
d
e
l
wa
s
e
v
a
lu
a
ted
in
th
e
tas
k
o
f
b
e
tt
e
r
c
las
sify
in
g
th
e
lev
e
l
o
f
a
c
c
id
e
n
t
risk
,
c
o
n
c
e
rn
in
g
t
h
e
d
riv
i
n
g
st
y
le
b
a
se
d
o
n
c
e
rtain
l
e
v
e
ls
o
f
a
c
c
e
lera
ti
o
n
.
Th
e
ra
n
d
o
m
fo
re
st
m
o
d
e
l
s
h
o
we
d
a
sli
g
h
t
ly
b
e
tt
e
r
p
e
rf
o
rm
a
n
c
e
c
o
m
p
a
re
d
t
o
th
a
t
sh
o
wn
b
y
th
e
o
th
e
r
two
m
o
d
e
ls,
with
9
7
.
2
4
%
a
c
c
u
ra
c
y
a
n
d
re
c
a
ll
,
9
7
.
1
6
%
p
re
c
isio
n
a
n
d
9
7
.
1
7
%
F
1
sc
o
re
.
K
ey
w
o
r
d
s
:
Acc
eler
o
m
eter
Ar
tific
ial
in
tellig
en
ce
Dr
iv
in
g
b
e
h
av
io
r
I
n
ter
n
et
o
f
t
h
in
g
s
Ma
ch
in
e
lear
n
in
g
Mo
to
r
cy
cle
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
:
E
s
teb
an
Alejan
d
r
o
C
ár
d
e
n
as L
an
ch
er
o
s
Facu
lty
o
f
E
n
g
in
ee
r
in
g
Un
iv
er
s
id
ad
Dis
tr
ital
Fra
n
cisco
J
o
s
é
d
e
C
ald
as
B
o
g
o
tá,
C
o
lo
m
b
ia
E
m
ail: c
lest
eb
an
a@
co
r
r
eo
.
u
d
i
s
tr
ital.e
d
u
.
co
1.
I
NT
RO
D
UCT
I
O
N
C
ities
,
h
av
in
g
a
r
o
ad
in
f
r
astru
ctu
r
e,
ca
n
s
h
o
w
a
v
ar
iab
le
c
ir
cu
latio
n
o
f
m
o
t
o
r
c
y
cles.
I
n
th
e
ca
s
e
o
f
B
o
g
o
tá
-
C
o
lo
m
b
ia,
f
r
o
m
J
an
u
a
r
y
to
Dec
em
b
er
2
0
2
0
,
5
1
8
,
6
6
6
m
o
to
r
cy
cles
wer
e
r
eg
is
ter
ed
,
with
a
g
r
o
wth
o
f
4
.
1
4
%
c
o
m
p
ar
e
d
t
o
th
e
s
am
e
p
er
io
d
i
n
2
0
1
9
[
1
]
.
T
h
e
u
s
e
o
f
th
e
m
o
to
r
cy
cle
b
ec
o
m
es
an
alter
n
ativ
e
th
at
p
r
esen
ts
ce
r
tain
ad
v
a
n
tag
es
c
o
m
p
ar
ed
to
tr
an
s
p
o
r
t
b
y
ca
r
.
T
h
e
m
ain
ad
v
an
tag
es
ar
e
ass
o
ciate
d
wi
th
m
o
n
e
y
an
d
tim
e,
s
in
ce
f
u
el
an
d
m
ain
t
en
an
ce
co
s
ts
ar
e
lo
wer
;
in
ter
m
s
o
f
tim
e,
tr
an
s
p
o
r
t
b
y
m
o
t
o
r
cy
cle
in
th
e
city
is
f
aster
,
m
ak
in
g
t
h
e
s
am
e
tr
ip
th
at
m
ak
es a
ca
r
b
y
5
0
% o
r
7
0
% less
tim
e.
Ho
wev
er
,
it h
as a
d
is
ad
v
an
tag
e
r
elate
d
to
a
h
ig
h
er
r
is
k
o
f
ac
cid
e
n
ts
[
2
]
.
I
n
cr
ea
s
es in
m
o
to
r
cy
cle
s
ales
in
r
ec
en
t y
ea
r
s
r
ef
lect
an
in
c
r
e
ase
in
th
e
n
u
m
b
er
s
o
f
d
ea
th
s
a
n
d
s
er
io
u
s
in
ju
r
ies ca
u
s
ed
to
t
h
eir
d
r
iv
er
s
[
3
]
,
[
4
]
.
Mo
to
r
cy
cle
u
s
er
s
r
ep
r
esen
t
5
3
.
2
%
o
f
th
e
to
tal
n
u
m
b
e
r
o
f
d
ea
th
s
an
d
5
9
.
7
%
o
f
th
e
to
tal
n
u
m
b
er
o
f
in
ju
r
ies
r
eg
is
ter
ed
in
th
e
co
u
n
tr
y
d
u
e
to
r
o
a
d
ac
cid
e
n
ts
[
5
]
,
th
e
h
i
g
h
s
p
ee
d
s
,
th
e
in
s
tab
ilit
y
o
f
th
e
v
eh
icle
a
n
d
th
e
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
I
n
cid
en
t fo
r
ec
a
s
tin
g
mo
d
el
fo
r
mo
to
r
cy
cle
d
r
ivin
g
b
a
s
ed
o
n
I
o
T…
(
E
s
teb
a
n
A
leja
n
d
r
o
C
á
r
d
en
a
s
-
La
n
ch
ero
s
)
445
in
ad
eq
u
ate
s
tate
o
f
th
e
r
o
a
d
,
c
an
ca
u
s
e
an
ac
cid
en
t
th
at
will
d
ir
ec
tly
af
f
ec
t
th
e
in
teg
r
ity
o
f
th
e
d
r
iv
er
b
ec
a
u
s
e
h
e
is
ex
p
o
s
ed
an
d
is
o
n
ly
p
r
o
t
ec
ted
b
y
g
lo
v
es,
b
o
o
ts
,
h
elm
et
an
d
clo
th
i
n
g
in
g
en
er
al.
W
ith
d
r
iv
er
b
eh
a
v
io
r
a
n
d
c
o
n
g
ested
r
o
ad
c
o
n
d
itio
n
s
,
ac
cid
e
n
ts
o
f
ten
o
cc
u
r
.
Ap
p
licatio
n
s
d
ev
elo
p
e
d
f
o
r
s
m
ar
t
p
h
o
n
es
ca
n
g
en
e
r
ate
aler
ts
to
av
o
id
ac
cid
en
ts
b
y
a
n
aly
zin
g
d
ata
f
r
o
m
th
e
ac
ce
ler
o
m
eter
an
d
g
y
r
o
s
co
p
e
s
en
s
o
r
s
in
c
o
r
p
o
r
a
ted
in
th
e
p
h
o
n
e.
R
esear
ch
h
as
ad
o
p
ted
m
ac
h
i
n
e
lear
n
in
g
-
b
ased
m
o
tio
n
id
en
tific
atio
n
p
r
o
ce
s
s
es.
T
h
e
d
ev
ice
ca
lcu
lates
ac
tiv
ity
b
ased
o
n
s
ev
er
al
p
r
ed
eter
m
i
n
ed
ca
teg
o
r
ies
o
f
d
r
iv
e
r
s
tatu
s
.
Statu
s
ca
teg
o
r
ies
ca
n
b
e
n
o
r
m
al,
zi
g
za
g
,
s
le
ep
y
,
r
ig
h
t
tu
r
n
,
lef
t
tu
r
n
,
U
-
tu
r
n
,
s
u
d
d
en
b
r
ak
i
n
g
,
an
d
s
u
d
d
en
ac
ce
ler
atio
n
[
2
]
.
Ma
ch
in
e
lear
n
i
n
g
ca
n
b
e
v
e
r
y
u
s
ef
u
l
in
r
ec
o
g
n
izin
g
d
r
iv
i
n
g
p
atter
n
s
.
T
h
e
p
r
o
b
lem
is
f
o
r
m
u
lated
as
a
class
if
icatio
n
task
to
id
en
tify
th
e
class
o
f
d
r
iv
in
g
p
atter
n
s
u
s
in
g
d
ata
c
o
llected
f
r
o
m
th
e
s
en
s
o
r
s
.
Sev
er
al
m
ac
h
in
e
lear
n
in
g
tech
n
iq
u
es c
an
b
e
im
p
lem
en
ted
,
in
clu
d
in
g
Gau
s
s
ian
m
ix
tu
r
e
m
o
d
els,
th
e
k
-
n
ea
r
est n
eig
h
b
o
r
m
o
d
el,
d
ec
is
io
n
tr
ee
s
,
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
es,
r
an
d
o
m
f
o
r
ests
,
an
d
h
id
d
en
M
ar
k
o
v
m
o
d
els
(
HM
M)
,
wh
er
e
th
ese
last
tw
o
s
h
o
w
a
h
ig
h
p
er
f
o
r
m
an
ce
in
th
e
r
ec
o
g
n
itio
n
o
f
d
r
iv
in
g
p
atter
n
s
[
6
]
,
[
7
]
.
E
ac
h
m
o
to
r
c
y
cle
is
tak
en
as
an
in
d
iv
id
u
al
ag
en
t
an
d
its
d
y
n
am
ic
ac
ce
ler
atio
n
v
a
r
iab
le
is
s
tu
d
ied
,
wh
ich
is
p
r
esen
t
d
u
r
in
g
th
e
ti
m
e
th
at
th
e
ac
tiv
ity
elap
s
es
[
8
]
an
d
is
ca
p
tu
r
e
d
b
y
a
s
en
s
o
r
in
th
e
lo
n
g
itu
d
in
al
an
d
later
al
a
x
es
[
9
]
,
th
is
d
ata
g
o
es
th
r
o
u
g
h
a
tr
an
s
f
o
r
m
atio
n
p
h
ase
to
e
x
tr
ac
t
in
t
er
p
r
etab
le
s
tatis
tical
ch
ar
ac
ter
is
tics
f
r
o
m
th
is
r
aw
d
ata
[
1
0
]
,
r
esu
ltin
g
in
t
h
e
cr
ea
tio
n
o
f
a
tr
ain
in
g
d
ataset
wh
ich
ca
n
b
e
u
s
ed
in
th
e
in
v
esti
g
a
tio
n
o
f
ce
r
tain
ev
e
n
ts
o
r
d
ec
is
io
n
s
[
1
1
]
.
A
class
if
icatio
n
in
to
f
o
u
r
ca
te
g
o
r
ies
ass
o
c
iated
with
lev
els
o
f
r
is
k
in
d
r
iv
in
g
will
p
r
ed
ict
n
ew
d
ata
f
r
o
m
th
e
tr
ain
in
g
d
ataset
an
d
g
iv
e
th
e
an
s
wer
to
th
e
co
r
r
ec
t
class
[
1
2
]
,
[
1
3
]
.
I
n
t
h
is
r
esear
ch
,
th
r
ee
m
ac
h
in
e
le
ar
n
in
g
class
if
ier
m
o
d
els
will
b
e
tak
en
,
th
e
y
will
b
e
co
m
p
ar
ed
,
an
d
e
v
alu
ated
,
t
o
v
alid
ate
wh
ich
is
th
e
o
n
e
th
at
s
h
o
ws
th
e
b
est
p
er
f
o
r
m
an
ce
to
class
if
y
lev
els
o
f
ac
cid
en
t r
is
k
,
th
u
s
lead
in
g
to
t
h
e
f
o
r
ec
ast o
f
in
cid
en
ts
in
d
r
iv
in
g
.
2.
RE
S
E
ARCH
M
E
T
H
O
D
2
.
1
.
D
a
t
a
s
et
cr
e
a
t
io
n
Fro
m
a
d
ata
a
r
ticle
en
titl
e
d
“Da
taset
o
n
p
o
wer
ed
two
wh
ee
ler
s
f
all
an
d
cr
iti
ca
l
ev
en
ts
d
etec
tio
n
”
[
1
4
]
,
Sev
er
al
s
u
b
-
d
atasets
ar
e
ex
tr
ac
ted
,
wh
ich
w
ill
b
e
tr
an
s
f
o
r
m
ed
,
an
aly
ze
d
an
d
u
n
if
ied
,
in
o
r
d
er
to
b
e
ab
le
to
g
en
er
ate
a
p
r
e
d
ictiv
e
class
if
icatio
n
m
o
d
el
th
at
wo
r
k
s
with
th
ese
d
ata
an
d
lead
s
to
th
e
f
o
r
ec
asti
n
g
o
f
m
o
to
r
c
y
cle
d
r
iv
in
g
in
cid
e
n
ts
.
Fo
r
th
e
d
ev
elo
p
m
e
n
t
o
f
th
is
r
esear
ch
,
th
e
d
ata
will
b
e
tak
en
f
r
o
m
th
e
m
en
tio
n
ed
d
ata
ar
ticle.
T
h
e
d
a
ta
ar
ticle
p
r
esen
ts
th
e
d
ata
g
en
er
ated
b
y
a
3
D
in
er
tial
m
ea
s
u
r
em
en
t
u
n
it,
wh
ich
in
co
r
p
o
r
ates
3
ac
ce
ler
o
m
eter
s
an
d
3
g
y
r
o
s
co
p
es.
Fo
r
th
is
in
v
esti
g
atio
n
o
n
ly
th
e
a
cc
eler
atio
n
co
m
p
o
n
e
n
ts
(
,
,
)
will
b
e
u
s
ed
.
T
h
e
in
e
r
tial
m
e
asu
r
em
en
t
u
n
it
was
m
o
u
n
ted
o
n
th
e
m
o
to
r
cy
cle
c
o
llectin
g
t
h
e
d
ata
dur
in
g
8
co
n
tr
o
lled
e
x
p
er
im
e
n
ts
,
ca
p
tu
r
in
g
ev
er
y
s
ec
o
n
d
a
s
am
p
le
o
f
th
e
m
a
g
n
itu
d
e
o
f
a
cc
eler
atio
n
f
o
r
ea
c
h
o
f
th
e
th
r
ee
s
p
atial
d
im
e
n
s
io
n
s
(
,
,
)
[
1
5
]
,
th
e
s
am
p
le
will
b
e
s
t
o
r
ed
in
a
r
eg
is
ter
.
T
h
e
m
ag
n
itu
d
e
o
f
ac
ce
ler
atio
n
is
g
iv
en
in
/
2
.
2
.
1
.
1
.
Da
t
a
s
et
t
ra
ns
f
o
rma
t
io
n
T
h
e
aim
is
to
e
x
tr
ac
t
f
r
o
m
th
e
s
u
b
-
d
atasets
,
m
etr
ics
b
ased
o
n
ex
p
lo
r
ato
r
y
s
tatis
tical
m
ea
s
u
r
es,
to
b
e
ab
le
to
m
ak
e
in
ter
p
r
etatio
n
s
a
b
o
u
t
th
e
d
ata
[
1
6
]
.
T
h
is
r
eq
u
i
r
es
d
iv
id
in
g
ea
ch
s
u
b
-
d
ataset
in
to
win
d
o
ws
an
d
s
u
b
-
win
d
o
ws
o
f
tu
p
les,
s
o
t
h
at
ex
p
lo
r
ato
r
y
s
tatis
tics
m
ea
s
u
r
em
en
ts
ca
n
b
e
p
er
f
o
r
m
ed
o
n
ea
ch
o
f
th
ese,
f
o
r
,
,
r
esp
ec
tiv
ely
.
E
ac
h
s
u
b
-
d
atas
et
co
n
tain
s
b
etwe
en
5
0
,
0
0
0
an
d
1
3
0
,
0
0
0
t
u
p
les,
win
d
o
ws
o
f
1
0
0
r
ec
o
r
d
s
wer
e
estab
lis
h
ed
o
n
e
ac
h
s
u
b
-
d
ataset,
lik
ewise,
s
u
b
-
win
d
o
ws
wer
e
g
en
er
ated
wh
ic
h
ar
e
in
th
e
m
id
d
le
o
f
two
win
d
o
ws
also
o
f
1
0
0
tu
p
les.
W
in
d
o
ws
an
d
s
u
b
-
win
d
o
ws
will
b
ec
o
m
e
f
u
tu
r
e
n
ew
tu
p
les.
A
v
alu
e
o
f
1
0
0
tu
p
les
was
ch
o
s
en
f
o
r
ea
c
h
w
in
d
o
w
a
n
d
s
u
b
-
win
d
o
w,
t
o
m
ain
tain
a
lar
g
e
s
et
o
f
n
ew
tu
p
les.
Sam
p
le
s
ize
is
an
im
p
o
r
tan
t
co
n
s
id
er
atio
n
f
o
r
r
esear
ch
.
L
ar
g
e
r
s
am
p
le
s
izes
p
r
o
v
id
e
m
o
r
e
ac
c
u
r
ate
m
e
an
v
alu
es,
id
en
tif
y
o
u
tlier
s
th
at
co
u
ld
s
k
ew
th
e
d
a
ta
in
a
s
m
aller
s
am
p
le
an
d
p
r
o
v
id
e
a
s
m
aller
m
ar
g
i
n
o
f
er
r
o
r
[
1
7
]
.
A
s
u
b
-
win
d
o
w,
wh
ich
co
n
tain
s
1
0
0
tu
p
les,
is
in
th
e
m
id
d
le
o
f
two
win
d
o
ws,
th
at
is
,
it
co
v
er
s
th
e
last
5
0
tu
p
les
o
f
t
h
e
f
ir
s
t
win
d
o
w
a
n
d
th
e
f
ir
s
t
5
0
tu
p
les o
f
th
e
s
ec
o
n
d
win
d
o
w,
t
h
e
s
ec
o
n
d
s
u
b
-
win
d
o
w
co
v
er
s
th
e
last
5
0
tu
p
les
o
f
th
e
s
ec
o
n
d
win
d
o
w
an
d
t
h
e
f
i
r
s
t
5
0
tu
p
l
es
o
f
t
h
e
th
ir
d
win
d
o
w,
an
d
s
o
o
n
g
en
e
r
atin
g
an
o
v
er
lap
p
i
n
g
s
et
o
f
n
ew
tu
p
les
.
Me
tr
ics
b
ased
o
n
ex
p
lo
r
ato
r
y
s
tatis
tical
m
ea
s
u
r
es
will
b
e
ex
tr
ac
ted
f
r
o
m
th
is
o
v
er
lap
p
i
n
g
s
et.
T
h
e
m
etr
ics
will
b
e
b
ased
o
n
t
h
e
f
o
llo
win
g
ty
p
es
o
f
e
x
p
lo
r
ato
r
y
s
t
atis
tics
m
ea
s
u
r
es:
i)
Me
asu
r
e
o
f
ce
n
t
r
al
ten
d
e
n
cy
:
av
er
ag
e
;
ii)
Po
s
itio
n
m
ea
s
u
r
em
en
ts
:
m
ax
im
u
m
,
m
in
im
u
m
Q1
q
u
a
r
tile
(
2
5
%),
Q2
q
u
ar
tile (
5
0
%)
an
d
Q3
q
u
a
r
tile
(
7
5
%)
; a
n
d
iii)
Dis
p
er
s
io
n
m
ea
s
u
r
es: v
ar
ian
ce
a
n
d
s
tan
d
ar
d
d
e
v
iatio
n
.
T
h
er
e
is
a
t
o
tal
o
f
8
m
et
r
ic
s
b
ased
o
n
ex
p
l
o
r
ato
r
y
s
tatis
tics
m
ea
s
u
r
es,
th
ese
8
m
etr
i
cs
will
b
e
ca
lcu
lated
f
o
r
ea
c
h
o
f
th
e
3
m
ag
n
itu
d
es
o
f
ac
ce
le
r
atio
n
,
,
in
ea
ch
s
u
b
-
win
d
o
w,
o
b
tain
i
n
g
a
to
tal
o
f
2
4
m
etr
ics
o
r
in
p
u
t
v
ar
iab
les
f
o
r
ea
ch
s
u
b
-
win
d
o
w.
T
h
e
r
e
will
b
e
8
n
ew
tr
an
s
f
o
r
m
ed
d
atasets
co
r
r
esp
o
n
d
in
g
to
th
e
8
co
n
tr
o
lled
e
x
p
er
im
e
n
ts
,
th
ese
will
in
itially
h
av
e
2
4
c
o
l
u
m
n
s
co
r
r
esp
o
n
d
i
n
g
to
ea
ch
m
etr
ic
th
at
h
er
e
will
also
b
e
ca
lled
th
e
in
p
u
t
v
ar
iab
le,
b
y
n
u
m
b
e
r
o
f
s
u
b
-
win
d
o
w
s
(
tu
p
les).
T
h
e
v
al
u
es
o
f
ea
ch
o
f
th
e
2
4
m
etr
i
cs
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
24
,
No
.
1
,
Octo
b
er
2
0
2
1
:
44
4
-
45
1
446
m
u
s
t
b
e
p
lo
tted
,
th
eir
b
eh
av
i
o
r
an
aly
ze
d
an
d
a
co
n
clu
s
io
n
will
b
e
o
b
tain
ed
p
er
s
u
b
-
win
d
o
w,
wh
ich
will
lead
to
g
en
er
ate
a
lab
el
f
o
r
th
at
s
u
b
-
win
d
o
w,
lo
ca
te
d
in
a
last
co
lu
m
n
(
n
u
m
b
e
r
2
5
)
o
f
t
h
e
n
e
w
tr
an
s
f
o
r
m
ed
s
u
b
-
d
ataset,
wh
ich
will
b
e
tak
en
a
s
th
e
o
u
tp
u
t
v
ar
iab
le
[
1
8
]
,
[
1
9
]
.
T
h
e
8
s
u
b
-
d
atasets
m
u
s
t
b
e
jo
in
ed
an
d
f
o
r
m
a
f
in
al
d
ataset,
th
is
w
ill
b
e
h
o
s
t
ed
in
a
GitHu
b
r
ep
o
s
ito
r
y
.
T
h
is
f
in
al
d
ata
s
et
is
tak
en
b
y
a
m
ac
h
in
e
lear
n
in
g
m
o
d
el,
wh
ich
co
n
s
is
ts
o
f
an
alg
o
r
ith
m
tr
ain
ed
b
y
th
ese
d
ata;
th
e
m
o
d
el
will
p
r
o
v
id
e
an
o
u
tp
u
t
wh
ich
is
co
n
s
id
er
ed
a
f
o
r
ec
ast b
ased
o
n
th
e
d
ata
th
at
tr
ain
e
d
th
e
m
o
d
e
l
[
2
0
]
-
[
2
3
]
.
2
.
1
.
2
.
Da
t
a
a
na
ly
s
t
W
h
en
m
an
u
al
lab
elin
g
is
p
er
f
o
r
m
ed
f
o
r
ea
ch
s
u
b
-
win
d
o
w,
t
h
is
lab
elin
g
will
co
r
r
esp
o
n
d
t
o
a
ce
r
tain
ca
teg
o
r
y
o
f
r
is
k
le
v
el
in
m
o
t
o
r
cy
cle
d
r
iv
in
g
.
T
h
e
d
ef
in
itio
n
o
f
th
e
ca
teg
o
r
ies
is
b
ased
o
n
lo
n
g
itu
d
i
n
al
an
d
later
al
ac
ce
ler
atio
n
lev
els
(
,
)
ass
o
ciate
d
with
d
an
g
er
o
u
s
n
ess
[
2
4
]
an
d
with
p
ar
ticu
lar
way
s
o
f
d
r
iv
in
g
,
s
u
ch
as
a
p
r
o
f
ess
io
n
al
d
r
iv
er
wo
u
ld
d
o
in
a
d
a
r
in
g
an
d
s
p
o
r
ty
way
o
r
ev
e
n
as
a
b
eg
in
n
e
r
wo
u
l
d
d
r
iv
e
in
a
m
o
r
e
ca
lm
an
d
r
elax
e
d
way
[
2
5
]
.
T
h
e
m
a
n
u
al
lab
elin
g
p
r
o
ce
d
u
r
e
is
b
ased
o
n
th
e
ass
ig
n
m
en
t
o
f
a
r
is
k
lev
el
f
o
r
ea
ch
s
u
b
-
win
d
o
w,
t
h
er
e
ar
e
4
r
is
k
lev
el
o
p
tio
n
s
,
a
n
d
ea
c
h
lev
el
will
h
av
e
ass
o
ciate
d
a
n
u
m
er
ical
v
alu
e
as
s
h
o
wn
in
T
ab
le
1
.
T
ab
le
1
,
in
th
e
last
co
lu
m
n
,
wh
ich
is
n
u
m
b
er
2
5
,
will
b
e
th
e
d
ata
o
f
t
h
e
n
u
m
er
ical
v
alu
e
ass
o
ciate
d
with
ea
ch
r
is
k
lev
el.
T
h
e
f
o
llo
win
g
cr
iter
ia
ar
e
ta
k
en
in
ac
co
u
n
t
to
ass
ig
n
a
r
is
k
lev
el
to
ea
ch
s
u
b
-
win
d
o
w,
th
ese
will
b
e
co
n
s
id
e
r
ed
o
n
ly
f
o
r
t
h
e
v
ar
iab
les
r
elat
ed
to
th
e
co
m
p
o
n
e
n
ts
o
f
ac
ce
l
er
atio
n
f
o
r
th
e
"x
"
an
d
"
y
"
a
x
es
(
,
)
,
s
in
ce
o
n
th
e
z
ax
is
(
)
th
e
ac
ce
ler
atio
n
co
m
p
o
n
e
n
t
o
f
th
e
ea
r
th
'
s
g
r
a
v
ity
f
o
r
ce
is
m
an
if
ested
,
an
d
it ten
d
s
to
r
e
m
ain
co
n
s
tan
t
[
2
6
]
,
[
2
7
]
.
T
h
es
e
cr
ite
r
ia
ar
e
m
en
tio
n
ed
:
−
Av
er
ag
e
th
at
f
its
with
in
ea
ch
ac
ce
ler
atio
n
r
an
g
e
f
r
o
m
T
ab
le
1
:
B
ein
g
th
e
m
ea
n
o
f
th
e
d
ata
in
ea
ch
s
u
b
-
win
d
o
w,
th
e
d
e
f
in
itio
n
o
f
its
ce
n
tr
al
ten
d
en
c
y
is
an
im
p
o
r
tan
t m
ea
s
u
r
e
to
co
n
s
id
er
.
−
Ma
x
im
u
m
an
d
m
in
im
u
m
n
o
t
to
o
f
ar
ap
ar
t:
T
h
e
f
ac
t
th
at
th
ese
two
m
ea
s
u
r
em
en
ts
ar
e
n
o
t
to
o
f
ar
a
p
ar
t
s
h
o
ws th
at
th
er
e
is
g
r
ea
ter
u
n
i
f
o
r
m
ity
in
th
e
v
alu
e
o
f
th
e
d
at
a
in
ea
ch
s
u
b
-
win
d
o
w
.
−
Qu
ar
tiles
Q1
an
d
Q2
th
at
f
it
o
r
ar
e
clo
s
e
to
ea
ch
ac
ce
ler
atio
n
r
an
g
e
in
T
ab
le
1
:
Hav
in
g
in
2
5
%
an
d
5
0
%
o
f
th
e
o
b
s
er
v
atio
n
s
d
ata
th
at
f
it
with
in
a
r
an
g
e
o
f
ac
ce
ler
atio
n
s
s
ig
n
if
ican
tly
d
eter
m
in
es
in
wh
ich
ca
teg
o
r
y
o
f
r
is
k
lev
el
th
e
s
u
b
-
win
d
o
w
wo
u
ld
b
e
.
−
Var
ian
ce
an
d
s
tan
d
ar
d
d
ev
iatio
n
n
o
t
v
er
y
h
ig
h
:
T
h
ese
two
m
ea
s
u
r
es
in
d
icate
h
o
w
d
is
p
er
s
ed
th
e
v
alu
es
o
f
th
e
s
am
p
le
d
ata
ca
n
b
e,
f
o
r
th
i
s
ca
s
e,
if
th
e
d
ata
is
m
o
r
e
co
n
c
en
tr
ated
,
th
ey
s
h
o
w
a
s
im
ilar
t
r
en
d
.
I
t
is
en
o
u
g
h
th
at
o
n
e
o
f
th
e
t
wo
ac
ce
ler
atio
n
co
m
p
o
n
e
n
ts
,
eith
er
o
s
h
o
ws
a
n
o
ticea
b
le
ch
an
g
e
to
ca
teg
o
r
ize
th
e
s
u
b
-
win
d
o
w,
o
th
er
wis
e
it
will
r
em
ain
i
n
th
e
"L
o
w"
ca
te
g
o
r
y
with
a
n
u
m
er
ical
v
alu
e
o
f
"0
".
I
n
Fig
u
r
e
1
,
th
e
d
ata
b
eh
av
io
r
f
o
r
a
s
u
b
-
win
d
o
w
is
s
h
o
wn
,
we
s
ee
th
at
f
o
r
th
e
co
m
p
o
n
e
n
t
,
th
e
m
ea
n
,
th
e
d
is
tan
ce
b
etwe
en
th
e
m
ax
im
u
m
an
d
th
e
m
in
im
u
m
,
th
e
q
u
a
r
tiles
Q1
an
d
Q2
,
th
e
v
ar
ian
c
e
an
d
th
e
s
tan
d
ar
d
d
ev
iatio
n
c
o
n
f
o
r
m
to
t
h
e
af
o
r
em
en
tio
n
ed
cr
iter
ia
a
n
d
allo
w
u
s
to
d
ec
id
e
th
at
t
h
e
m
o
s
t
ap
p
r
o
p
r
iate
ca
teg
o
r
y
f
o
r
th
is
s
u
b
-
win
d
o
w
is
a
"No
ta
b
le"
r
is
k
lev
el
with
a
n
u
m
er
ica
l
v
alu
e
o
f
"
1
".
Fig
u
r
e
1
.
B
eh
av
i
o
r
o
f
th
e
2
4
m
etr
ics co
r
r
esp
o
n
d
in
g
to
a
s
u
b
-
win
d
ow
T
ab
le
1
.
R
is
k
lev
els an
d
th
eir
ass
o
ciate
d
n
u
m
er
ical
v
alu
es
R
i
s
k
l
e
v
e
l
A
c
c
e
l
e
r
a
t
i
o
n
r
a
n
g
e
(
/
)
N
u
meri
c
a
l
v
a
l
u
e
Lo
w
0
–
2
,
5
0
N
o
t
a
b
l
e
2
,
5
–
5
1
H
i
g
h
5
–
7
2
V
e
r
y
h
i
g
h
> 7
3
Acc
eler
a
ti
on
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
I
n
cid
en
t fo
r
ec
a
s
tin
g
mo
d
el
fo
r
mo
to
r
cy
cle
d
r
ivin
g
b
a
s
ed
o
n
I
o
T…
(
E
s
teb
a
n
A
leja
n
d
r
o
C
á
r
d
en
a
s
-
La
n
ch
ero
s
)
447
2
.
2
.
P
ro
po
s
ed
m
a
chine le
a
r
nin
g
m
o
dels
T
h
er
e
is
a
d
ataset
with
2
5
co
lu
m
n
s
,
wh
er
e
2
4
o
f
th
em
c
o
r
r
e
s
p
o
n
d
to
th
e
r
esp
ec
tiv
e
m
etr
ics
o
r
in
p
u
t
v
ar
iab
les
o
b
tain
ed
f
r
o
m
th
e
ex
p
lo
r
ato
r
y
s
tatis
tics
m
ea
s
u
r
es,
an
d
co
lu
m
n
n
u
m
b
er
2
5
o
r
o
u
t
p
u
t
v
ar
iab
le,
wo
u
ld
b
e
th
e
r
is
k
lev
el
co
lu
m
n
co
r
r
esp
o
n
d
in
g
to
th
e
m
an
u
ally
lab
eled
d
ata
o
r
class
.
T
h
r
ee
wi
d
ely
u
s
ed
p
r
ed
ictiv
e
m
o
d
els
o
f
m
ac
h
in
e
lea
r
n
in
g
b
ased
o
n
s
u
p
er
v
is
ed
lea
r
n
in
g
ar
e
p
r
o
p
o
s
ed
,
wh
ich
w
o
r
k
with
class
i
f
icatio
n
alg
o
r
ith
m
s
an
d
h
av
e
p
r
esen
ted
g
o
o
d
r
esu
lts
f
o
r
p
r
o
b
lem
s
o
f
a
s
im
ilar
n
atu
r
e
[
2
8
]
-
[
3
0
]
;
t
h
ese
ar
e
m
en
tio
n
e
d
:
Dec
is
io
n
tr
ee
s
(
DT
)
:
d
ec
is
io
n
tr
ee
s
ar
e
s
eq
u
e
n
tial
m
o
d
els,
lo
g
ically
co
m
b
in
in
g
a
s
eq
u
en
ce
o
f
s
im
p
le
test
s
;
ea
ch
test
co
m
p
ar
es
a
n
u
m
er
ic
att
r
ib
u
te
to
a
th
r
esh
o
ld
v
alu
e
o
r
a
n
o
m
i
n
al
attr
ib
u
te
t
o
a
s
et
o
f
p
o
s
s
ib
le
v
alu
e
s
.
W
h
en
a
d
ata
p
o
i
n
t
f
all
s
in
to
a
p
ar
titi
o
n
ed
r
eg
io
n
,
a
d
ec
is
io
n
tr
ee
class
if
ies
it
a
s
b
el
o
n
g
in
g
to
th
e
m
o
s
t
f
r
eq
u
e
n
t c
lass
in
th
at
r
eg
io
n
[
3
1
]
.
KNN
(
k
-
n
ea
r
est
n
eig
h
b
o
r
s
)
:
T
h
is
m
e
th
o
d
f
in
d
s
th
e
k
clo
s
est n
eig
h
b
o
r
s
o
f
th
e
lab
eled
in
s
tan
ce
s
to
th
e
u
n
lab
eled
in
s
tan
ce
u
s
in
g
th
e
E
u
clid
ea
n
d
is
tan
ce
b
etwe
en
th
e
f
ea
tu
r
e
v
ec
to
r
s
.
R
etu
r
n
s
th
e
l
ab
el
th
at
r
ep
r
esen
ts
th
e
m
o
s
t
n
eig
h
b
o
r
s
[
3
2
]
.
R
an
d
o
m
f
o
r
ests
(
R
F):
r
an
d
o
m
f
o
r
ests
ar
e
a
co
m
b
in
atio
n
o
f
p
r
ed
icto
r
tr
ee
s
in
s
u
ch
a
way
th
at
ea
ch
tr
ee
d
e
p
en
d
s
o
n
th
e
v
alu
es
o
f
a
r
an
d
o
m
v
ec
to
r
s
am
p
led
i
n
d
ep
e
n
d
en
tly
an
d
with
th
e
s
am
e
d
is
tr
ib
u
tio
n
f
o
r
all
tr
ee
s
in
t
h
e
f
o
r
est.
C
lass
if
icatio
n
p
r
o
b
lem
s
ar
e
s
o
lv
ed
b
y
an
al
y
zin
g
th
e
o
u
tp
u
t
o
f
th
e
tr
ee
s
.
Mo
s
t o
f
th
e
v
o
tes o
f
th
e
class
o
r
ca
teg
o
r
y
d
eter
m
in
es th
e
p
r
e
d
ictio
n
o
f
t
h
e
r
an
d
o
m
f
o
r
ests
[
3
3
]
.
2
.
2
.
1
.
I
m
plem
ent
a
t
i
o
n o
f
t
he
m
o
dels
T
h
e
p
y
th
o
n
p
r
o
g
r
am
m
in
g
lan
g
u
ag
e
is
h
ig
h
ly
s
u
itab
le
in
ter
m
s
o
f
m
o
d
el
im
p
lem
en
tatio
n
,
as
it
i
s
estab
lis
h
in
g
its
elf
as
o
n
e
o
f
th
e
m
o
s
t
p
o
p
u
lar
lan
g
u
ag
es
f
o
r
s
cien
tific
co
m
p
u
tin
g
.
T
h
a
n
k
s
to
its
h
ig
h
-
lev
el
in
ter
ac
tiv
e
n
atu
r
e
an
d
s
cien
tific
lib
r
ar
y
ec
o
s
y
s
tem
,
it
is
an
att
r
ac
tiv
e
o
p
tio
n
f
o
r
alg
o
r
it
h
m
i
c
d
ev
elo
p
m
e
n
t
an
d
ex
p
lo
r
ato
r
y
d
ata
an
aly
s
is
[
3
4
]
,
[
3
5
]
.
Pri
o
r
to
th
e
im
p
lem
en
tatio
n
o
f
ea
ch
o
f
th
e
th
r
e
e
m
ac
h
in
e
lea
r
n
in
g
m
o
d
els,
it
is
n
ec
ess
ar
y
to
p
r
o
p
er
ly
d
iv
id
e
th
e
f
in
al
d
ataset
in
to
tr
ai
n
in
g
an
d
test
in
g
s
u
b
s
ets.
T
h
e
tr
ain
in
g
s
u
b
s
et
is
ap
p
lied
to
tr
ain
o
r
ad
ju
s
t
th
e
m
o
d
el
an
d
th
e
test
s
u
b
s
et
is
n
ec
ess
ar
y
f
o
r
an
ev
alu
atio
n
o
f
th
e
f
in
al
m
o
d
el
[
3
6
]
.
Ad
d
itio
n
ally
,
p
r
o
p
er
s
p
litt
in
g
m
in
im
izes
th
e
p
o
ten
tial
f
o
r
b
ias
in
th
e
ev
alu
a
tio
n
an
d
v
alid
atio
n
p
r
o
ce
s
s
[
3
7
]
.
Of
th
e
to
tal
d
ata,
7
0
% is
d
esig
n
ated
as a
tr
ain
in
g
s
u
b
s
et
an
d
3
0
% a
s
a
test
s
u
b
s
et.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
3
.
1
.
C
o
m
pa
riso
n o
f
m
a
chin
e
lea
rning
m
o
dels
A
f
t
e
r
i
m
p
l
e
m
e
n
t
i
n
g
t
h
e
t
h
r
e
e
m
a
c
h
i
n
e
l
ea
r
n
i
n
g
m
o
d
e
l
s
,
we
p
r
o
c
e
e
d
t
o
v
a
l
i
d
at
e
h
o
w
e
f
f
e
c
t
i
v
e
t
h
e
c
a
p
a
c
i
t
y
o
f
e
a
c
h
p
r
o
p
o
s
e
d
m
o
d
e
l
i
s
t
o
c
o
r
r
e
c
t
l
y
i
d
e
n
t
i
f
y
c
l
as
s
es
.
V
a
l
i
d
at
i
o
n
w
i
l
l
b
e
b
a
s
e
d
o
n
a
c
o
n
f
u
s
i
o
n
m
a
t
r
i
x
a
s
s
h
o
w
n
i
n
F
i
g
u
r
e
2
w
h
i
c
h
w
i
ll
d
e
f
i
n
e
t
h
e
f
o
l
l
o
wi
n
g
m
e
t
r
i
cs
:
a
c
c
u
r
a
c
y
,
p
r
e
c
i
s
i
o
n
,
r
e
c
a
l
l
a
n
d
F
1
s
c
o
r
e
[
3
8
]
.
Fo
r
th
e
ac
cu
r
ac
y
m
etr
ic,
in
ad
d
itio
n
to
ex
p
o
s
in
g
th
e
r
esu
lts
o
f
ea
ch
o
f
th
e
th
r
ee
m
o
d
els
p
r
o
p
o
s
ed
in
th
i
s
in
v
esti
g
atio
n
,
a
co
m
p
ar
is
o
n
will
b
e
m
a
d
e
o
f
t
h
ese
r
es
u
lts
with
th
o
s
e
g
en
er
ated
b
y
two
o
th
er
p
r
e
v
io
u
s
in
v
esti
g
atio
n
s
;
th
e
f
ir
s
t
p
r
o
p
o
s
es
a
m
ac
h
in
e
lear
n
in
g
f
r
am
e
wo
r
k
f
o
r
d
r
i
v
in
g
p
atter
n
r
ec
o
g
n
itio
n
[
6
]
an
d
will
b
e
n
am
ed
"I
n
v
esti
g
atio
n
1
",
th
e
s
ec
o
n
d
f
o
cu
s
es
o
n
d
etec
t
in
g
d
r
iv
in
g
ev
en
ts
b
y
ap
p
ly
i
n
g
th
e
m
eth
o
d
o
f
lear
n
in
g
s
ets
f
o
r
class
if
icatio
n
[
7
]
,
we
will
n
am
e
th
is
"I
n
v
est
ig
atio
n
2
".
T
h
e
r
esu
lts
o
f
th
e
a
cc
u
r
ac
y
m
etr
ic
f
o
r
th
is
in
v
esti
g
atio
n
,
“I
n
v
esti
g
ati
o
n
1
”
a
n
d
“I
n
v
esti
g
atio
n
2
”;
a
r
e
o
b
s
er
v
e
d
in
T
a
b
le
2
.
(
a)
(b
)
(
c)
Fig
u
r
e
2
.
C
o
n
f
u
s
io
n
m
atr
ices
:
(
a)
d
ec
is
io
n
tr
ee
s
,
(
b
)
KNN
an
d
(
c)
R
an
d
o
m
f
o
r
ests
T
ab
le
2.
Acc
u
r
ac
y
m
etr
ic
A
c
c
u
r
a
c
y
M
o
d
e
l
Th
i
s
i
n
v
e
s
t
i
g
a
t
i
o
n
I
n
v
e
st
i
g
a
t
i
o
n
1
I
n
v
e
st
i
g
a
t
i
o
n
2
D
e
c
i
s
i
o
n
t
r
e
e
s
9
5
,
9
%
-
8
4
,
7
4
%
K
-
n
e
a
r
e
s
t
n
e
i
g
h
b
o
r
s
9
5
,
4
%
8
2
,
4
±
7
,
4
%
8
5
,
1
8
%
R
a
n
d
o
m f
o
r
e
s
t
s
9
6
,
1
%
8
4
,
7
±
7
,
6
%
9
4
,
0
7
%
T
h
e
ac
cu
r
ac
y
p
er
ce
n
tag
es
o
f
th
e
th
r
ee
m
o
d
els
p
r
o
p
o
s
ed
in
th
is
in
v
esti
g
atio
n
ar
e
s
o
m
ew
h
at
h
ig
h
er
th
an
th
o
s
e
th
at
r
esu
lted
f
r
o
m
i
n
v
esti
g
atio
n
s
1
an
d
2
.
T
h
e
th
r
ee
in
v
esti
g
atio
n
s
attem
p
t
to
s
o
lv
e
p
r
o
b
lem
s
o
f
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
24
,
No
.
1
,
Octo
b
er
2
0
2
1
:
44
4
-
45
1
448
s
im
ilar
n
atu
r
es;
h
o
wev
er
,
th
ei
r
m
eth
o
d
o
lo
g
ies
m
ay
d
i
f
f
er
;
it
is
o
b
s
er
v
ed
th
at
th
e
r
a
n
d
o
m
f
o
r
est
m
o
d
el
f
o
r
th
e
th
r
ee
s
ce
n
ar
io
s
p
r
esen
ts
a
h
ig
h
er
ac
c
u
r
ac
y
.
W
ith
th
e
‘
wei
g
h
ted
’
av
er
a
g
e
p
a
r
am
eter
,
th
e
o
th
er
m
etr
ics
ar
e
ca
lcu
lated
f
o
r
ea
c
h
lab
el.
B
y
h
av
in
g
a
class
im
b
alan
ce
,
wh
i
ch
o
cc
u
r
s
wh
en
t
h
er
e
is
a
s
ig
n
if
ic
an
t
d
if
f
er
en
ce
in
th
e
am
o
u
n
t
o
f
d
ata
co
r
r
esp
o
n
d
in
g
to
ea
c
h
class
[
3
9
]
;
a
weig
h
ted
av
er
ag
e
m
ak
es
m
o
r
e
s
en
s
e,
wh
er
e
th
e
weig
h
ts
ar
e
ca
lcu
lated
b
y
th
e
f
r
eq
u
e
n
cy
o
f
a
ce
r
tain
class
,
weig
h
tin
g
th
e
m
etr
ic
o
f
ea
ch
class
b
y
th
e
n
u
m
b
er
o
f
s
am
p
les o
f
th
at
class
[
4
0
]
.
ℎ
=
1
#
1
+
2
#
2
+
⋯
+
#
(
1
)
R
esu
lts
-
m
etr
ics
with
a
‘
weig
h
t
ed
’
a
v
er
ag
e
p
ar
a
m
eter
o
f
p
r
ec
i
s
io
n
,
r
ec
all
an
d
F1
s
co
r
e
a
r
e
o
b
s
er
v
ed
i
n
T
a
b
le
3
an
d
in
Fig
u
r
e
3
.
T
h
e
th
r
ee
m
o
d
els
s
h
o
w
clo
s
e
p
er
f
o
r
m
an
ce
r
atio
s
;
h
o
wev
er
,
th
e
r
a
n
d
o
m
f
o
r
est
m
o
d
el
h
as
th
e
h
ig
h
est p
er
f
o
r
m
an
ce
r
atio
; a
cc
o
r
d
in
g
to
th
is
,
it is
th
e
m
o
d
el
t
h
at
b
est s
u
its
th
e
in
v
esti
g
atio
n
.
T
ab
le
3.
Pre
cisi
o
n
,
r
ec
all
an
d
F1
s
co
r
e
m
etr
ics;
wi
th
‘
weig
h
t
ed
’
av
er
a
g
e
p
ar
a
m
eter
M
o
d
e
l
(
‘
w
e
i
g
h
t
e
d
'
a
v
e
r
a
g
e
)
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
F
1
sc
o
r
e
D
e
c
i
s
i
o
n
t
r
e
e
s
9
6
,
1
%
9
6
,
0
%
9
6
,
0
%
K
-
n
e
a
r
e
s
t
n
e
i
g
h
b
o
r
s
9
5
,
1
%
9
5
,
2
%
9
5
,
0
%
R
a
n
d
o
m f
o
r
e
s
t
s
9
6
,
2
%
9
6
,
3
%
9
6
,
2
%
Fig
u
r
e
3
.
Pre
cisi
o
n
r
e
ca
ll a
n
d
F1
s
co
r
e
m
etr
ic,
wi
th
‘
weig
h
ted
’
av
er
a
g
e
p
ar
a
m
eter
3
.
2
.
Resul
t
s
o
f
t
he
e
v
a
lua
t
io
n m
et
rics f
o
r
t
he
cho
s
en
m
o
del w
it
h a
djuste
d hy
per
pa
ra
m
et
er
s
R
esu
lt
-
ac
cu
r
ac
y
m
etr
ic
is
o
b
s
er
v
ed
in
T
ab
le
4
.
T
o
o
b
tain
p
r
ec
is
io
n
,
r
ec
all
a
n
d
F1
s
co
r
e,
th
e
‘
weig
h
ted
’
av
er
a
g
e
p
ar
am
eter
was
co
n
s
id
er
ed
,
th
is
r
esu
lt
i
s
o
b
s
er
v
ed
in
T
ab
le
5
.
W
ith
th
e
ad
ju
s
tm
en
t
o
f
h
y
p
er
p
ar
am
eter
s
,
an
im
p
r
o
v
e
m
en
t
in
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
m
o
d
el
was
g
e
n
er
ated
,
th
is
is
ev
id
en
ce
d
in
T
ab
l
e
6
an
d
in
Fig
u
r
e
4
.
T
h
e
a
d
ju
s
ted
h
y
p
e
r
p
ar
am
ete
r
s
wer
e
"n
_
esti
m
ato
r
s
"
=
1
0
0
a
n
d
"r
a
n
d
o
m
_
s
tate"
=
100.
T
ab
le
4.
Acc
u
r
ac
y
m
etr
ic
-
r
an
d
o
m
f
o
r
ests
m
o
d
el
with
ad
ju
s
ted
h
y
p
e
r
p
ar
a
m
eter
s
M
o
d
e
l
A
c
c
u
r
a
c
y
R
a
n
d
o
m F
o
r
e
s
t
s
9
7
,
2
4
%
T
ab
le
5
.
Pre
cisi
o
n
,
r
ec
all
an
d
F1
s
co
r
e
m
etr
ics;
with
‘
weig
h
t
ed
’
av
er
a
g
e
p
ar
a
m
eter
-
r
a
n
d
o
m
f
o
r
ests
m
o
d
e
l
with
ad
ju
s
ted
h
y
p
e
r
p
ar
am
ete
r
s
M
o
d
e
l
(
‘
w
e
i
g
h
t
e
d
'
a
v
e
r
a
g
e
)
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
F
1
sc
o
r
e
R
a
n
d
o
m F
o
r
e
s
t
s
9
7
,
1
6
%
9
7
,
2
4
%
9
7
,
1
7
%
T
ab
le
6
.
I
m
p
r
o
v
ed
p
er
f
o
r
m
an
c
e
o
f
th
e
r
an
d
o
m
f
o
r
est m
o
d
el
d
u
e
to
th
e
ad
ju
s
tm
en
t o
f
h
y
p
er
p
ar
am
eter
s
Ev
a
l
u
a
t
i
o
n
me
t
r
i
c
A
d
j
u
st
m
e
n
t
o
f
h
y
p
e
r
p
a
r
a
me
t
e
r
s
I
mp
r
o
v
e
m
e
n
t
W
i
t
h
o
u
t
W
i
t
h
A
c
c
u
r
a
c
y
9
6
,
1
0
%
9
7
,
2
4
%
1
,
1
9
%
P
r
e
c
i
s
i
o
n
9
6
,
2
0
%
9
7
,
1
6
%
1
,
0
0
%
R
e
c
a
l
l
9
6
,
3
0
%
9
7
,
2
4
%
0
,
9
8
%
F
1
sc
o
r
e
9
6
,
2
0
%
9
7
,
1
7
%
1
,
0
1
%
Ap
ar
t
f
r
o
m
th
e
h
y
p
e
r
p
ar
am
eter
s
th
at
ar
e
estab
lis
h
ed
b
y
d
ef
a
u
lt,
th
e
n
u
m
b
e
r
o
f
esti
m
ato
r
s
“n
_
esti
m
ato
r
s
”
is
k
ep
t
at
th
e
m
ax
im
u
m
(
1
0
0
)
,
th
u
s
th
e
r
e
wi
ll
b
e
a
g
r
ea
ter
n
u
m
b
er
o
f
tr
ee
s
wh
ich
in
c
r
ea
s
es
th
e
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
I
n
cid
en
t fo
r
ec
a
s
tin
g
mo
d
el
fo
r
mo
to
r
cy
cle
d
r
ivin
g
b
a
s
ed
o
n
I
o
T…
(
E
s
teb
a
n
A
leja
n
d
r
o
C
á
r
d
en
a
s
-
La
n
ch
ero
s
)
449
p
er
f
o
r
m
an
ce
m
ak
i
n
g
th
e
p
r
ed
ictio
n
s
m
o
r
e
s
tab
le;
ad
d
itio
n
a
lly
,
a
p
ar
am
eter
to
a
d
ju
s
t
is
th
e
“r
an
d
o
m
-
s
tate”
,
wh
ich
co
n
tr
o
ls
b
o
th
th
e
r
an
d
o
m
n
ess
o
f
th
e
s
am
p
les
u
s
ed
wh
en
co
n
s
tr
u
ctin
g
tr
ee
s
an
d
t
h
e
s
am
p
lin
g
o
f
th
e
ch
ar
ac
ter
is
tics
to
co
n
s
id
er
w
h
en
lo
o
k
in
g
f
o
r
t
h
e
b
est
d
iv
is
io
n
in
ea
ch
n
o
d
e,
it
is
ad
j
u
s
ted
to
1
0
0
,
th
u
s
o
b
tain
in
g
th
e
b
est
r
esu
lt
f
o
llo
win
g
a
d
eter
m
in
is
tic
b
eh
av
io
r
.
I
m
p
o
r
ta
n
ce
m
ea
s
u
r
es
o
f
v
a
r
i
ab
les
p
r
o
d
u
ce
d
b
y
r
an
d
o
m
f
o
r
ests
h
av
e
also
b
ee
n
s
u
g
g
ested
f
o
r
t
h
e
s
elec
tio
n
o
f
r
elev
an
t
p
r
ed
icto
r
v
ar
iab
l
es
in
d
ata
an
aly
s
is
,
h
o
wev
er
,
th
ese
v
a
r
iab
le
im
p
o
r
tan
ce
m
ea
s
u
r
es
s
h
o
w
a
b
ias
to
war
d
s
co
r
r
elate
d
p
r
ed
icto
r
v
ar
iab
les
[
4
1
]
.
T
h
is
m
ea
s
u
r
e
is
in
clu
d
ed
a
n
d
s
h
o
w
n
in
Fig
u
r
e
5
.
Fig
u
r
e
4
.
I
m
p
r
o
v
ed
p
er
f
o
r
m
an
ce
o
f
th
e
r
an
d
o
m
f
o
r
est m
o
d
el
d
u
e
to
th
e
ad
ju
s
tm
e
n
t o
f
h
y
p
er
p
ar
am
eter
s
.
Fig
u
r
e
5
.
Var
iab
le
s
s
co
r
e
b
y
d
eg
r
ee
o
f
im
p
o
r
ta
n
ce
4.
CO
NCLU
SI
O
N
Acc
o
r
d
in
g
to
t
h
e
m
ea
s
u
r
em
e
n
t
o
f
im
p
o
r
tan
ce
o
f
v
ar
iab
les,
th
o
s
e
with
th
e
h
ig
h
est
s
co
r
e
ar
e
th
e
Q2
q
u
ar
tile,
f
o
llo
wed
b
y
th
e
m
ea
n
,
th
e
Q3
q
u
a
r
tile,
th
e
Q1
q
u
a
r
tile,
m
ax
im
u
m
an
d
m
in
im
u
m
;
th
ey
ar
e
ass
o
ciate
d
with
th
e
x
ax
is
(
lo
n
g
itu
d
i
n
al
a
cc
eler
atio
n
)
,
s
in
ce
it
is
in
th
is
ax
is
wh
er
e
a
g
r
ea
te
r
b
eh
a
v
io
r
is
ev
id
en
ce
d
with
in
th
e
d
ataset.
I
t
wo
u
ld
b
e
ex
p
e
cted
th
at,
if
th
e
r
e
wer
e
a
g
r
ea
ter
ac
tiv
ity
in
th
e
y
-
ax
is
(
late
r
al
ac
ce
ler
atio
n
)
,
a
s
im
ilar
s
itu
atio
n
wo
u
ld
b
e
r
ef
l
ec
ted
h
er
e
in
te
r
m
s
o
f
th
e
s
co
r
e
o
f
th
e
im
p
o
r
tan
ce
o
f
v
ar
ia
b
les.
Sin
ce
th
e
o
u
tp
u
t
v
ar
iab
le
o
f
th
e
r
is
k
lev
el
r
esu
lts
in
an
attr
ib
u
te
o
f
4
p
o
s
s
ib
le
class
e
s
,
th
e
ev
alu
atio
n
o
f
all
th
e
cla
s
s
es
m
u
s
t
b
e
co
n
s
id
er
ed
,
to
a
d
d
th
e
m
an
d
o
b
tain
th
e
ac
tu
al
ev
al
u
atio
n
o
f
th
e
class
if
ier
m
o
d
el
f
o
r
t
h
e
attr
ib
u
te.
Her
e,
f
o
r
m
u
latin
g
th
is
,
we
h
av
e
in
tr
o
d
u
ce
d
th
e
ev
al
u
atio
n
o
f
c
lass
if
icatio
n
weig
h
ted
av
er
ag
e
f
o
r
th
e
g
en
er
al
r
ec
o
g
n
itio
n
r
ate
o
f
th
e
class
if
ier
m
o
d
el,
wh
ich
r
e
f
lects
h
o
w
well
th
e
class
if
ier
m
o
d
el
r
ec
o
g
n
izes
th
e
attr
ib
u
tes
o
f
th
e
4
class
es.
T
h
e
th
r
ee
m
o
d
els
im
p
lem
en
ted
r
esu
lted
in
g
o
o
d
i
n
d
ex
es
in
ter
m
s
o
f
class
p
r
ed
ictio
n
,
h
o
wev
er
,
th
e
R
an
d
o
m
Fo
r
ests
m
o
d
el
h
as
a
s
lig
h
t
ad
v
an
tag
e
in
th
e
r
esu
lts
g
en
er
ated
b
y
its
ev
alu
atio
n
m
etr
ics
co
m
p
ar
ed
to
th
e
Dec
is
io
n
T
r
e
es
(
av
er
ag
e
o
f
0
.
2
1
%
h
ig
h
er
)
an
d
K
n
ea
r
est
n
eig
h
b
o
r
s
(
a
v
er
ag
e
1
.
2
9
%
h
ig
h
er
)
m
o
d
els,
d
u
e
to
its
s
im
p
licity
an
d
r
an
d
o
m
izatio
n
p
r
o
ce
s
s
.
R
an
d
o
m
f
o
r
ests
ar
e
co
n
s
id
er
ed
a
n
ef
f
ec
tiv
e
p
r
ed
ictio
n
to
o
l
a
n
d
b
y
a
d
ju
s
tin
g
th
eir
h
y
p
er
p
ar
a
m
eter
s
,
an
av
er
ag
e
im
p
r
o
v
em
e
n
t
o
f
clo
s
e
to
1
.
0
4
%
o
f
th
e
r
esu
lts
g
en
er
ated
b
y
th
eir
e
v
al
u
atio
n
m
etr
ics
ca
n
b
e
ac
h
ie
v
e
d
.
As
a
f
u
tu
r
e
d
e
v
elo
p
m
e
n
t,
it
co
u
ld
g
e
n
er
ate
o
u
r
o
wn
d
ataset
wh
er
e
th
e
r
e
is
g
r
ea
ter
ac
tiv
ity
r
elate
d
to
later
a
l
ac
ce
ler
atio
n
s
an
d
v
alid
ate
th
e
im
p
o
r
tan
ce
with
in
th
e
v
ar
iab
les
th
at
ch
ar
ac
ter
ize
th
e
r
is
k
o
f
d
an
g
er
,
lik
ewi
s
e,
b
e
ab
le
to
co
n
s
id
er
th
e
v
ar
iab
le
f
r
o
m
th
e
g
y
r
o
s
co
p
e
(
an
g
u
lar
v
elo
city
in
th
e
th
r
ee
s
p
atial
ax
es),
p
er
f
o
r
m
in
g
a
s
im
ilar
d
ata
p
r
o
ce
s
s
in
g
an
d
an
al
y
s
is
,
th
u
s
ad
d
in
g
o
n
e
m
o
r
e
ch
a
r
ac
ter
i
s
tic
to
th
e
f
o
r
ec
ast
o
f
in
ci
d
en
ts
in
m
o
to
r
c
y
cle
d
r
iv
i
n
g
.
Oth
er
p
r
e
d
ictiv
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
24
,
No
.
1
,
Octo
b
er
2
0
2
1
:
44
4
-
45
1
450
class
if
icatio
n
m
o
d
els
b
ased
o
n
s
u
p
er
v
is
ed
lear
n
in
g
ca
n
b
e
im
p
lem
en
ted
,
s
u
ch
as
b
ay
esian
n
etwo
r
k
s
,
n
eu
r
a
l
n
etwo
r
k
s
o
r
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
es,
an
d
with
th
is
v
alid
ate
th
e
p
er
f
o
r
m
a
n
ce
th
at
th
ey
co
u
ld
h
av
e
i
n
a
p
r
o
b
lem
o
f
th
is
n
atu
r
e.
RE
F
E
R
E
NC
E
S
[1
]
A.
F
e
n
a
lco
,
"
In
f
o
rm
e
De
M
a
trí
c
u
l
a
s De
M
o
to
s A Dicie
m
b
re
De
2
0
2
0
,
"
B
o
g
o
tá
,
2
0
2
1
.
[2
]
F
.
M
.
Nu
sw
a
n
t
o
ro
,
A.
S
u
d
a
rso
n
o
,
a
n
d
T
.
B.
S
a
n
t
o
so
,
"
Ab
n
o
rm
a
l
Driv
in
g
De
tec
ti
o
n
b
a
se
d
o
n
Ac
c
e
lero
m
e
ter
a
n
d
g
y
r
o
sc
o
p
e
se
n
so
r
o
n
sm
a
rtp
h
o
n
e
u
sin
g
Artifi
c
ial
Ne
u
ra
l
Ne
two
rk
(AN
N)
a
lg
o
rit
h
m
,
"
In
ter
n
a
ti
o
n
a
l
El
e
c
tro
n
ics
S
y
mp
o
si
u
m (IE
S
)
,
p
p
.
3
5
6
-
3
6
3
,
2
0
2
0
,
d
o
i:
1
0
.
1
1
0
9
/IE
S
5
0
8
3
9
.
2
0
2
0
.
9
2
3
1
8
5
1
.
[3
]
D
.
Clark
e
,
P
.
Ward
,
C.
Ba
rtl
e
,
a
n
d
W.
Tr
u
m
a
n
,
"
I
n
-
d
e
p
t
h
S
t
u
d
y
o
f
M
o
to
rc
y
c
le
Ac
c
id
e
n
ts,"
R
o
a
d
S
a
fety
Res
e
a
rc
h
Rep
,
v
o
l.
5
4
,
2
0
0
4
.
[4
]
B.
P
h
a
rm
a
c
o
p
o
e
ia,
“
Co
n
tr
o
ll
e
r
o
f
He
r
M
a
jes
ty
’s S
tatio
n
e
ry
Offic
e
,
”
No
rwis
h
,
v
o
l
.
1
,
p
.
8
0
5
,
2
0
0
4
.
[5
]
Ob
se
rv
a
to
rio
Na
c
io
n
a
l
d
e
S
e
g
u
r
i
d
a
d
Vía
l,
"
Ag
e
n
c
ia
Na
c
io
n
a
l
d
e
S
e
g
u
ri
d
a
d
Vía
l,
"
2
0
2
1
.
A
c
c
e
ss
e
d
:
Ap
ril
8,
2
0
2
1
.
[On
li
n
e
].
A
v
a
il
a
b
le:
h
tt
p
s://
a
n
sv
.
g
o
v
.
c
o
/
o
b
se
rv
a
t
o
rio
[6
]
F
.
Attal
,
A.
B
o
u
b
e
z
o
u
l,
L.
O
u
k
h
e
ll
o
u
,
a
n
d
S
.
Esp
ié,
"
P
o
we
re
d
T
wo
-
Wh
e
e
ler
Ri
d
in
g
P
a
tt
e
rn
Re
c
o
g
n
it
i
o
n
Us
in
g
a
M
a
c
h
in
e
-
Lea
rn
in
g
F
ra
m
e
wo
rk
,
"
in
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
In
tell
ig
e
n
t
T
ra
n
sp
o
rta
ti
o
n
S
y
ste
ms
,
v
o
l.
1
6
,
n
o
.
1
,
p
p
.
475
-
4
8
7
,
F
e
b
.
2
0
1
5
,
d
o
i:
1
0
.
1
1
0
9
/T
ITS
.
2
0
1
4
.
2
3
4
6
2
4
3
.
[7
]
B.
Bo
se
,
J.
Du
tt
a
,
S
.
G
h
o
sh
,
P
.
P
r
a
m
a
n
ick
,
a
n
d
S
.
R
o
y
,
"
S
m
a
rtp
h
o
n
e
b
a
se
d
sy
ste
m
f
o
r
re
a
l
-
ti
m
e
a
g
g
re
ss
iv
e
d
ri
v
in
g
d
e
tec
ti
o
n
a
n
d
m
a
rk
i
n
g
ra
sh
d
riv
in
g
-
p
r
o
n
e
a
re
a
s,"
Asso
c
i
a
ti
o
n
f
o
r
C
o
mp
u
t
in
g
M
a
c
h
i
n
e
ry
-
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
Pro
c
e
e
d
in
g
S
e
rie
s
,
n
o
.
2
7
,
p
p
.
1
-
6
,
2
0
1
8
,
d
o
i:
1
0
.
1
1
4
5
/3
1
7
0
5
2
1
.
3
1
7
0
5
4
9
.
[8
]
I.
Zafa
r
a
n
d
K.
M
.
I
q
b
a
l
,
"
Au
to
m
a
ti
c
in
c
id
e
n
t
d
e
tec
ti
o
n
i
n
sm
a
rt
c
it
y
u
si
n
g
m
u
lt
i
p
le t
ra
ffic fl
o
w
p
a
ra
m
e
ters
v
ia V2
X
c
o
m
m
u
n
ica
ti
o
n
,
"
I
n
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Distrib
u
ted
S
e
n
so
r
N
e
two
rk
s,
v
o
l.
1
4
,
n
o
.
1
1
,
p
p
.
1
-
2
3
,
2
0
1
8
,
d
o
i
:
1
0
.
1
1
7
7
/
1
5
5
0
1
4
7
7
1
8
8
1
5
8
4
5
.
[9
]
F
.
Attal,
A.
Bo
u
b
e
z
o
u
l,
L.
Ou
k
h
e
ll
o
u
,
a
n
d
S
.
Esp
ié,
"
A
n
a
ly
sis
a
n
d
c
las
sifica
ti
o
n
o
f
P
o
we
re
d
Tw
o
W
h
e
e
lers
Rid
in
g
P
a
tt
e
rn
,
"
T
ra
n
sp
o
rt
Res
e
a
rc
h
Are
n
a
(T
RA
)
5
th
Co
n
fer
e
n
c
e
:
T
r
a
n
sp
o
rt
S
o
l
u
ti
o
n
s
fro
m
Res
e
a
rc
h
t
o
De
p
lo
y
me
n
t,
n
o
.
0
1
5
4
0
7
6
1
,
2
0
1
4
,
p
p
.
1
-
10
.
[1
0
]
Z.
Li
,
K.
Zh
a
n
g
,
B
.
Ch
e
n
,
Y.
Do
n
g
,
a
n
d
L.
Z
h
a
n
g
,
"
Dri
v
e
r
id
e
n
ti
fica
ti
o
n
in
in
telli
g
e
n
t
v
e
h
icle
sy
ste
m
s
u
sin
g
m
a
c
h
in
e
lea
rn
in
g
a
lg
o
rit
h
m
s,"
IE
T
In
telli
g
e
n
t
T
ra
n
sp
o
rt
S
y
ste
ms
,
v
o
l.
1
3
,
n
o
.
1
,
p
p
.
4
0
-
4
7
,
2
0
1
8
,
d
o
i:
1
0
.
1
0
4
9
/
iet
-
it
s.2
0
1
7
.
0
2
5
4
.
[1
1
]
E.
Ah
m
e
d
,
I.
Ya
q
o
o
b
,
I.
A.
Tar
g
i
o
Ha
sh
e
m
,
I
.
Kh
a
n
,
A.
M
.
I.
Ab
d
a
ll
a
Ah
m
e
d
,
M
.
Im
ra
n
,
a
n
d
A.
V.
Va
silak
o
s,
"
T
h
e
ro
le
o
f
b
ig
d
a
ta
a
n
a
ly
ti
c
s
in
I
n
ter
n
e
t
o
f
T
h
in
g
s,"
C
o
mp
u
ter
Ne
two
rk
s,
n
o
.
S
1
3
8
9
-
1
2
8
6
(
1
7
)
3
0
2
5
9
-
1
,
p
.
1
,
2
0
1
7
,
d
o
i:
1
0
.
1
0
1
6
/
j.
c
o
m
n
e
t.
2
0
1
7
.
0
6
.
0
1
3
.
[1
2
]
A.
H.
S
h
a
o
n
,
“
Id
e
n
ti
fica
ti
o
n
o
f
D
a
n
g
e
ro
u
s
Driv
i
n
g
Be
h
a
v
i
o
r
U
si
n
g
Na
tu
ra
li
stic
Dri
v
i
n
g
Da
ta,
”
M
u
n
ich
:
T
e
c
h
n
ica
l
Un
ive
rs
it
y
o
f
M
u
n
ic
h
,
2
0
1
9
.
[1
3
]
S
.
B.
Ko
tsian
ti
s,
"
S
u
p
e
rv
ise
d
M
a
c
h
in
e
Lea
rn
in
g
:
A
Re
v
iew
o
f
Clas
sifica
ti
o
n
Tec
h
n
i
q
u
e
s,"
Un
ive
rs
it
y
o
f
Pelo
p
o
n
n
e
se
,
Gr
e
e
c
e
,
p
p
.
2
4
8
-
2
6
8
,
2
0
0
7
.
[1
4
]
A.
Bo
u
b
e
z
o
u
l,
F
.
D
u
fo
u
r,
S
.
Bo
u
a
z
iz,
B.
Larn
a
u
d
ie
,
a
n
d
S
.
Es
p
ié,
"
Da
tas
e
t
o
n
p
o
we
re
d
two
w
h
e
e
lers
fa
ll
a
n
d
c
rit
ica
l
e
v
e
n
ts d
e
tec
ti
o
n
,
"
EL
S
EV
I
ER
,
v
o
l.
2
3
,
n
o
.
2
3
5
2
-
3
4
0
9
,
p
p
.
1
-
6
,
2
0
1
9
,
d
o
i:
1
0
.
1
0
1
6
/
j.
d
ib
.
2
0
1
9
.
1
0
3
8
2
8
.
[1
5
]
A.
Bo
u
b
e
z
o
u
l,
S
.
Es
p
ié,
Br
u
n
o
L
a
rn
a
u
d
ie
,
a
n
d
S
.
B
o
u
a
z
iz,
"
A
si
m
p
le
fa
ll
d
e
tec
ti
o
n
a
l
g
o
ri
th
m
fo
r
p
o
we
re
d
tw
o
wh
e
e
lers
,
"
EL
S
E
VIE
R,
v
o
l.
2
1
,
n
o
.
3
,
p
p
.
2
8
6
-
2
9
7
,
2
0
1
3
,
d
o
i:
1
0
.
1
0
1
6
/j
.
c
o
n
e
n
g
p
ra
c
.
2
0
1
2
.
1
0
.
0
0
9
.
[1
6
]
K.
S
a
h
o
o
,
A.
K.
S
a
m
a
l,
J.
P
ra
m
a
n
ik
a
n
d
S
.
K.
P
a
n
i,
"
Ex
p
lo
ra
to
ry
Da
ta
An
a
ly
sis
u
sin
g
P
y
th
o
n
,
"
I
n
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
In
n
o
v
a
ti
v
e
T
e
c
h
n
o
lo
g
y
a
n
d
Exp
lo
ri
n
g
E
n
g
in
e
e
rin
g
,
v
o
l.
8
,
n
o
.
2
2
7
8
-
3
0
7
5
,
p
p
.
4
7
2
7
-
4
7
2
9
,
2
0
1
9
.
[1
7
]
J.
Zam
b
o
n
i,
"
S
c
ien
c
in
g
,
"
2
0
1
8
.
Ac
c
e
ss
e
d
:
Ap
r.
2
0
,
2
0
1
8
]
.
[On
li
n
e
].
Av
a
il
a
b
le:
h
t
tp
s://
sc
ien
c
i
n
g
.
c
o
m
/ad
v
a
n
tag
e
s
-
larg
e
-
sa
m
p
le
-
siz
e
-
7
2
1
0
1
9
0
.
h
tml
[1
8
]
T.
Ha
stie,
R.
Ti
b
sh
iran
i
,
a
n
d
J.
F
ried
m
a
n
,
"
Ov
e
rv
iew
o
f
S
u
p
e
rv
ise
d
Lea
rn
i
n
g
,
"
i
n
T
h
e
El
e
me
n
ts
o
f
S
ta
ti
stica
l
L
e
a
rn
in
g
D
a
ta
M
i
n
in
g
,
I
n
fer
e
n
c
e
,
a
n
d
Pre
d
ictio
n
,
S
tan
fo
r
d
CA,
USA,
S
p
ri
n
g
e
r,
p
p
.
9
-
1
1
,
2
0
0
9
,
d
o
i:
1
0
.
1
0
0
7
/
b
9
4
6
0
8
_
2
.
[1
9
]
A.
E.
M
o
h
a
m
e
d
,
"
Co
m
p
a
ra
ti
v
e
S
tu
d
y
o
f
F
o
u
r
S
u
p
e
rv
ise
d
M
a
c
h
in
e
Lea
rn
i
n
g
Tec
h
n
i
q
u
e
s
fo
r
Clas
sifica
ti
o
n
,
"
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
A
p
p
li
e
d
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l.
7
,
n
o
.
2
,
p
p
.
5
-
1
8
,
2
0
1
7
.
[2
0
]
P
.
Cu
n
n
i
n
g
h
a
m
,
M
.
Co
r
d
,
a
n
d
S
.
J.
De
lan
y
,
"
S
u
p
e
rv
ise
d
Le
a
rn
in
g
,
"
i
n
M
a
c
h
in
e
L
e
a
rn
i
n
g
T
e
c
h
n
iq
u
e
s
fo
r
M
u
lt
ime
d
ia
,
Be
rli
n
,
S
p
rin
g
e
r,
p
p
.
2
1
-
2
2
,
2
0
0
8
.
[2
1
]
H.
Bh
a
v
sa
r
a
n
d
A.
G
a
n
a
tra,
"
A
Co
m
p
a
ra
ti
v
e
S
t
u
d
y
o
f
Trai
n
in
g
Alg
o
rit
h
m
s
fo
r
S
u
p
e
rv
ise
d
M
a
c
h
in
e
Lea
rn
in
g
,
"
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
S
o
f
t
Co
m
p
u
ti
n
g
a
n
d
E
n
g
in
e
e
rin
g
,
v
o
l.
2
,
n
o
.
4
,
p
p
.
7
4
-
8
1
,
2
0
1
2
.
[2
2
]
N.
Ra
ju
,
S
.
S
.
Ark
a
tk
a
r
a
n
d
G
.
Jo
sh
i,
"
Ex
p
e
rien
c
e
s
o
f
su
p
e
r
v
ise
d
M
a
c
h
in
e
Lea
rn
in
g
to
re
p
li
c
a
te
d
riv
in
g
b
e
h
a
v
io
r
u
n
d
e
r
traffic e
n
v
ir
o
n
m
e
n
t
,
"
C
o
n
fe
re
n
c
e
p
a
p
e
r
-
re
se
a
rc
h
g
a
te,
2
0
1
9
,
p
.
1
6
.
[2
3
]
N.
M
.
N.
M
a
t
h
iv
a
n
a
n
,
N.
A.
M
d
.
G
h
a
n
i
,
a
n
d
R.
M
.
J
a
n
o
r,
"
P
e
rfo
r
m
a
n
c
e
a
n
a
ly
sis
o
f
su
p
e
rv
ise
d
lea
rn
in
g
m
o
d
e
ls
f
o
r
p
ro
d
u
c
t
ti
tl
e
c
las
sifica
ti
o
n
,
"
IAE
S
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Art
if
ici
a
l
In
telli
g
e
n
c
e
(IJ
AI)
,
v
o
l.
8
,
n
o
.
3
,
p
p
.
2
9
9
-
3
0
6
,
2
0
1
9
,
d
o
i:
1
0
.
1
1
5
9
1
/i
jai.
v
8
.
i3
.
p
p
2
2
8
-
2
3
6
.
[2
4
]
F
u
Li
,
Ha
i
Z
h
a
n
g
,
Hu
a
n
Ch
e
,
a
n
d
Xia
o
c
h
e
n
Qiu
,
"
Da
n
g
e
ro
u
s
d
ri
v
i
n
g
b
e
h
a
v
io
r
d
e
tec
ti
o
n
u
si
n
g
sm
a
rtp
h
o
n
e
se
n
so
rs,"
2
0
1
6
IEE
E
1
9
t
h
I
n
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
In
telli
g
e
n
t
T
ra
n
sp
o
rt
a
ti
o
n
S
y
ste
ms
(IT
S
C)
,
2
0
1
6
,
p
p
.
1
9
0
2
-
1
9
0
7
,
d
o
i:
1
0
.
1
1
0
9
/I
TS
C.
2
0
1
6
.
7
7
9
5
8
6
4
.
[2
5
]
S
.
Wi
ll
,
B.
M
e
tz,
T.
Ha
m
m
e
r,
M
.
M
ö
rb
e
,
M
.
He
n
z
ler,
F
.
Ha
r
n
isc
h
m
a
c
h
e
r
,
a
n
d
G
.
M
a
tsc
h
l,
"
M
e
th
o
d
o
l
o
g
ica
l
c
o
n
sid
e
ra
ti
o
n
s
re
g
a
rd
i
n
g
m
o
t
o
rc
y
c
le
n
a
tu
ra
li
stic
rid
i
n
g
in
v
e
stig
a
t
io
n
s
b
a
se
d
o
n
t
h
e
u
se
o
f
g
-
g
d
ia
g
ra
m
s
fo
r
rid
e
r
p
ro
fil
e
d
e
tec
ti
o
n
,
"
E
L
S
E
VIE
R,
p
p
.
1
-
1
2
,
2
0
2
0
,
d
o
i:
1
0
.
1
0
1
6
/j
.
ss
c
i.
2
0
2
0
.
1
0
4
8
4
0
.
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
I
n
cid
en
t fo
r
ec
a
s
tin
g
mo
d
el
fo
r
mo
to
r
cy
cle
d
r
ivin
g
b
a
s
ed
o
n
I
o
T…
(
E
s
teb
a
n
A
leja
n
d
r
o
C
á
r
d
en
a
s
-
La
n
ch
ero
s
)
451
[2
6
]
P
.
N.
M
o
ra
les
,
"
S
e
n
so
rs
-
S
e
n
so
rs
Offs
e
t,
"
in
S
m
a
rt
M
o
v
e
me
n
t
De
tec
ti
o
n
Fo
r
An
d
ro
i
d
P
h
o
n
e
s
,
Ba
rc
e
lo
n
a
,
Un
iv
e
rsitat
P
o
li
tèc
n
ic
a
d
e
Ca
tal
u
n
y
a
,
2
0
1
6
,
p
p
.
1
5
-
23
.
[2
7
]
M
.
Tec
p
o
y
o
t
l
-
To
rre
s,
R.
Ca
b
e
ll
o
-
Ru
iz,
P
.
Va
rg
a
s
-
Ch
a
b
le,
J.
G
.
Ve
ra
-
Dim
a
s
,
a
n
d
A.
Oc
a
m
p
o
-
Di
az
,
"
P
e
rfo
rm
a
n
c
e
o
f
c
o
m
p
li
a
n
t
m
e
c
h
a
n
ism
s
a
p
p
li
e
d
t
o
a
m
o
d
ifi
e
d
sh
a
p
e
a
c
c
e
lero
m
e
ter
o
f
sin
g
le
a
n
d
d
o
u
b
le
lay
e
r,
"
I
n
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
trica
l
a
n
d
C
o
mp
u
ter
En
g
in
e
e
rin
g
(IJ
ECE
)
,
vol
.
9
,
n
o
.
6
,
p
p
.
4
6
7
5
-
4
6
8
3
,
2
0
1
9
,
d
o
i:
1
0
.
1
1
5
9
1
/i
jec
e
.
v
9
i6
.
p
p
4
6
7
5
-
4
6
8
3
.
[2
8
]
N.
Do
g
r
u
a
n
d
A.
S
u
b
a
si,
"
Traff
ic
a
c
c
id
e
n
t
d
e
tec
ti
o
n
u
si
n
g
ra
n
d
o
m
fo
re
st
c
las
sifier,"
2
0
1
8
1
5
t
h
L
e
a
rn
i
n
g
a
n
d
T
e
c
h
n
o
l
o
g
y
C
o
n
fer
e
n
c
e
(L
&
T
)
,
2
0
1
8
,
p
p
.
4
0
-
4
5
,
d
o
i:
1
0
.
1
1
0
9
/L
T
.
2
0
1
8
.
8
3
6
8
5
0
9
.
[2
9
]
M
.
Re
z
a
p
o
u
r,
A.
M
.
M
o
lan
,
a
n
d
K.
Ks
a
ib
a
ti
,
"
An
a
l
y
z
in
g
in
j
u
r
y
se
v
e
rit
y
o
f
m
o
to
rc
y
c
le
a
t
-
fa
u
l
t
c
ra
sh
e
s
u
sin
g
m
a
c
h
in
e
lea
rn
in
g
tec
h
n
i
q
u
e
s,
d
e
c
isio
n
t
re
e
a
n
d
l
o
g
ist
ic
re
g
re
ss
io
n
m
o
d
e
ls,"
I
n
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
T
ra
n
s
p
o
rt
a
ti
o
n
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l.
9
,
n
o
.
2
,
p
p
.
8
9
-
9
9
,
2
0
2
0
,
d
o
i:
1
0
.
1
0
1
6
/j
.
ij
tst.
2
0
1
9
.
1
0
.
0
0
2
.
[3
0
]
B.
K.
M
o
h
a
n
ta,
D.
Je
n
a
,
N.
M
o
h
a
p
a
tra,
S
.
Ra
m
a
su
b
b
a
re
d
d
y
,
a
n
d
B.
S
.
Ra
wa
l,
"
M
a
c
h
in
e
lea
rn
i
n
g
b
a
se
d
a
c
c
id
e
n
t
p
re
d
ictio
n
i
n
se
c
u
re
Io
T
e
n
a
b
le t
r
a
n
sp
o
rtati
o
n
s
y
ste
m
,
"
J
o
u
rn
a
l
o
f
I
n
telli
g
e
n
t
&
F
u
zz
y
S
y
ste
ms
,
p
p
.
1
-
1
3
,
2
0
2
1
.
[3
1
]
S.
B
.
K
o
tsian
ti
s,
"
De
c
isio
n
tree
s:
a
re
c
e
n
t
o
v
e
r
v
iew
,
"
S
p
rin
g
e
r
,
v
o
l.
3
8
,
n
o
.
4
,
p
p
.
2
6
1
-
2
6
2
,
2
0
1
1
,
d
o
i:
1
0
.
1
0
0
7
/s
1
0
4
6
2
-
0
1
1
-
9
2
7
2
-
4
.
[3
2
]
A.
D.
M
c
Do
n
a
l
d
,
J.
D
.
Lee
,
C.
S
c
h
wa
rz
,
a
n
d
T.
L.
Br
o
wn
,
"
S
tee
ri
n
g
i
n
a
Ra
n
d
o
m
F
o
re
st:
E
n
se
m
b
le
Lea
rn
in
g
f
o
r
De
tec
ti
n
g
Dro
ws
i
n
e
ss
-
Re
late
d
Lan
e
De
p
a
rtu
re
s,"
Hu
ma
n
Fa
c
to
rs
a
n
d
Erg
o
n
o
mic
s
S
o
c
iety
.
,
v
o
l.
5
6
,
n
o
.
5
,
p
p
.
9
8
6
-
998
,
2
0
1
3
,
d
o
i:
1
0
.
1
1
7
7
/
0
0
1
8
7
2
0
8
1
3
5
1
5
2
7
2
.
[3
3
]
L.
Bre
ima
n
,
"
Ra
n
d
o
m
F
o
re
sts,"
M
a
c
h
i
n
e
L
e
a
r
n
in
g
-
S
p
ri
n
g
e
r,
v
o
l
.
4
5
,
n
o
.
1
,
p
p
.
5
-
6
,
2
0
0
1
.
[3
4
]
F
.
P
e
d
re
g
o
sa
,
G
.
V
a
ro
q
u
a
u
x
,
A
.
G
ra
m
fo
rt,
V.
M
ich
e
l,
B.
Th
ir
io
n
,
O.
G
rise
l
,
a
n
d
M
.
Blo
n
d
e
l
,
"
S
c
ik
it
-
lea
rn
:
M
a
c
h
in
e
Lea
rn
i
n
g
in
P
y
t
h
o
n
,
"
J
o
u
rn
a
l
o
f
M
a
c
h
in
e
L
e
a
rn
i
n
g
Res
e
a
rc
h
,
v
o
l.
1
2
,
p
p
.
2
8
2
5
-
2
8
3
0
,
2
0
1
1
.
[3
5
]
Y.
Re
n
,
"
P
y
th
o
n
M
a
c
h
in
e
Lea
rn
in
g
-
B
o
o
k
Re
v
iew
,
"
I
n
ter
n
a
t
io
n
a
l
J
o
u
r
n
a
l
o
f
Kn
o
wled
g
e
-
Ba
se
d
Or
g
a
n
iz
a
ti
o
n
s,
v
o
l.
1
1
,
n
o
.
1
,
p
p
.
6
7
-
7
0
,
2
0
2
1
.
[3
6
]
K.
M
a
lh
o
tra
a
n
d
A.
P
.
S
in
g
h
,
"
I
m
p
lem
e
n
tatio
n
o
f
d
e
c
isio
n
tree
a
lg
o
rit
h
m
o
n
F
P
G
A
d
e
v
ice
s,"
IA
E
S
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Arti
fi
c
i
a
l
I
n
telli
g
e
n
c
e
,
vo
l.
1
0
,
n
o
.
1
,
p
p
.
1
3
1
-
1
3
8
,
2
0
2
1
,
d
o
i:
1
0
.
1
1
5
9
1
/
ij
a
i.
v
1
0
.
i1
.
p
p
1
3
1
-
1
3
8
.
[3
7
]
D.
Ka
n
g
a
n
d
S
.
Oh
,
"
Ba
lan
c
e
d
tr
a
in
in
g
/t
e
st
se
t
sa
m
p
li
n
g
f
o
r
p
r
o
p
e
r
e
v
a
lu
a
ti
o
n
o
f
c
las
sifica
ti
o
n
m
o
d
e
ls,"
In
telli
g
e
n
t
Da
ta
A
n
a
lys
is,
v
o
l.
2
4
,
n
o
.
1
,
p
p
.
5
-
1
8
,
2
0
2
0
,
d
o
i:
1
0
.
3
2
3
3
/IDA
-
1
9
4
4
7
7
.
[3
8
]
D.
S
a
rk
a
r,
R
.
Ba
li
a
n
d
T.
S
h
a
rm
a
,
"
B
u
il
d
in
g
,
T
u
n
in
g
,
a
n
d
De
p
lo
y
i
n
g
M
o
d
e
ls,"
in
Pra
c
ti
c
a
l
ma
c
h
in
e
lea
rn
in
g
w
it
h
Pyth
o
n
,
Ba
n
g
a
lo
re
,
A
p
re
ss
,
p
p
.
2
7
2
-
2
7
5
,
2
0
1
8
,
d
o
i:
1
0
.
1
0
0
7
/
9
7
8
-
1
-
4
8
4
2
-
3
2
0
7
-
1
_
5
.
[3
9
]
C.
Kim
,
H.
Lee
,
a
n
d
H.
Ju
n
g
,
"
F
ru
it
tree
d
ise
a
se
c
las
sifica
ti
o
n
sy
ste
m
u
sin
g
g
e
n
e
ra
ti
v
e
a
d
v
e
rsa
rial
n
e
two
rk
s,
"
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
tr
ica
l
a
n
d
Co
m
p
u
ter
En
g
in
e
e
rin
g
,
v
o
l.
1
1
,
n
o
.
3
,
p
p
.
2
5
0
8
-
2
5
1
5
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
5
9
1
/i
jec
e
.
v
1
1
i
3
.
p
p
2
5
0
8
-
2
5
1
5
.
[4
0
]
V.
P
a
tro
a
n
d
M
.
R.
P
a
tra,
"
Au
g
m
e
n
ti
n
g
Weig
h
ted
A
v
e
ra
g
e
wi
th
Co
n
fu
si
o
n
M
a
tri
x
to
En
h
a
n
c
e
Clas
sifica
ti
o
n
Ac
c
u
ra
c
y
,
"
T
ra
n
s
a
c
ti
o
n
s
o
n
M
a
c
h
in
e
L
e
a
rn
in
g
a
n
d
Art
if
icia
l
In
telli
g
e
n
c
e
,
v
o
l.
2
,
n
o
.
4
,
p
p
.
7
7
-
9
0
,
2
0
1
4
,
d
o
i:
1
0
.
1
4
7
3
8
/t
m
lai.
2
4
.
3
2
8
.
[4
1
]
C.
S
tr
o
b
l
,
A.
L.
Bo
u
les
teix
,
T.
A.
Th
o
m
a
s
Kn
e
ib
,
a
n
d
A.
Zeilei
s
,
"
Co
n
d
it
io
n
a
l
v
a
riab
le
imp
o
rta
n
c
e
fo
r
ra
n
d
o
m
fo
re
sts,"
B
M
C
Bi
o
in
f
o
rm
a
ti
c
s,
v
o
l.
9
,
n
o
.
3
0
7
,
p
p
.
1
-
1
1
,
2
0
0
8
,
d
o
i:
1
0
.
1
1
8
6
/
1
4
7
1
-
2
1
0
5
-
9
-
3
0
7
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Este
b
a
n
Ale
ja
n
d
r
o
Cá
r
d
e
n
a
s
-
La
n
c
h
e
r
o
s
is
a
s
t
u
d
e
n
t
o
f
t
h
e
m
a
ste
r’s
p
ro
g
ra
m
i
n
in
fo
rm
a
ti
o
n
a
n
d
c
o
m
m
u
n
ica
ti
o
n
sc
ien
c
e
s
a
t
th
e
Un
iv
e
rsid
a
d
D
istri
tal
F
ra
n
c
isc
o
Jo
sé
d
e
Ca
ld
a
s (Bo
g
o
tá,
Co
lo
m
b
ia),
El
e
c
t
ro
n
ic E
n
g
i
n
e
e
r
fro
m
t
h
e
sa
m
e
Un
iv
e
rsity
.
Ne
lso
n
En
r
iq
u
e
Ve
r
a
-
Pa
r
r
a
is
a
P
ro
fe
ss
o
r
a
n
d
C
o
o
r
d
in
a
t
o
r
o
f
th
e
m
a
ste
r’s
p
ro
g
ra
m
in
in
fo
rm
a
ti
o
n
a
n
d
c
o
m
m
u
n
ica
ti
o
n
sc
ien
c
e
s
a
t
th
e
Un
iv
e
rsid
a
d
D
istri
tal
F
ra
n
c
isc
o
Jo
sé
d
e
Ca
ld
a
s
(Bo
g
o
tá,
C
o
lo
m
b
ia),
Do
c
to
r
o
f
En
g
in
e
e
ri
n
g
fro
m
t
h
e
sa
m
e
Un
iv
e
rsity
,
El
e
c
tro
n
ic
En
g
i
n
e
e
r
fro
m
t
h
e
Un
i
v
e
rsid
a
d
S
u
rc
o
l
o
m
b
ian
a
(Ne
i
v
a
,
Co
l
o
m
b
i
a
),
Re
se
a
rc
h
e
r
in
p
a
ra
ll
e
l
c
o
m
p
u
ti
n
g
,
h
i
g
h
p
e
rfo
rm
a
n
c
e
c
o
m
p
u
ti
n
g
,
sc
ien
c
e
d
a
ta an
d
b
io
in
f
o
rm
a
ti
c
s.
Evaluation Warning : The document was created with Spire.PDF for Python.