I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
p
u
t
er
Science
Vo
l.
22
,
No
.
3
,
J
u
n
e
202
1
,
p
p
.
1427
~
1
4
3
5
I
SS
N:
2
5
0
2
-
4
7
5
2
,
DOI
: 1
0
.
1
1
5
9
1
/i
j
ee
cs.v
2
2
.i
3
.
pp
1
4
2
7
-
1
4
3
5
1427
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs.ia
esco
r
e.
co
m
Fire
in
ciden
ts vis
ua
liz
a
tion a
nd
pa
tt
ern
rec
o
g
nition
using
m
a
chine
learning
a
lg
o
rith
m
s
J
o
na
rdo
R.
Aso
r
1
,
J
ef
f
er
s
o
n L
.
L
er
io
s
2
,
S
herw
in B
.
Sa
pin
3
,
J
o
ce
ly
n O
.
P
a
da
lla
n
4
,
Cheste
r
Ale
x
is
C.
B
ua
m
a
5
1
-
4
Co
ll
e
g
e
o
f
Co
m
p
u
ter S
tu
d
ies
(
CCS
),
L
a
g
u
n
a
S
tate
P
o
ly
tec
h
n
ic Un
iv
e
rsit
y
,
L
o
s Ba
ñ
o
s,
L
a
g
u
n
a
,
P
h
il
ip
p
i
n
e
s
5
Co
ll
e
g
e
o
f
A
rts
a
n
d
S
c
ien
c
e
s (CA
S
),
L
a
g
u
n
a
S
tate
P
o
ly
tec
h
n
ic Un
iv
e
rsity
,
L
o
s Ba
ñ
o
s,
L
a
g
u
n
a
,
P
h
i
li
p
p
i
n
e
s
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
an
1
3
,
2
0
2
1
R
ev
i
s
ed
Ma
y
3
1
,
2
0
2
1
A
cc
ep
ted
J
u
n
1
3
,
2
0
2
1
A
f
ire
in
c
id
e
n
t
is
a
d
e
v
a
sta
ti
n
g
e
v
e
n
t
th
a
t
c
a
n
b
e
a
v
o
i
d
e
d
w
it
h
e
n
o
u
g
h
k
n
o
w
led
g
e
o
n
h
o
w
a
n
d
w
h
e
n
it
m
a
y
o
c
c
u
r.
F
o
r
th
e
p
a
st
y
e
a
rs,
f
ir
e
in
c
id
e
n
ts
h
a
v
e
b
e
c
o
m
e
a
b
ig
p
ro
b
lem
f
o
r
th
e
P
h
il
ip
p
in
e
s,
si
n
c
e
it
a
ff
e
c
ts
th
e
so
c
io
-
e
c
o
n
o
m
ic g
ro
w
th
o
f
th
e
c
o
u
n
try
.
M
a
c
h
in
e
lea
rn
i
n
g
a
lg
o
rit
h
m
is a
w
e
ll
-
k
n
o
w
n
tec
h
n
iq
u
e
to
p
re
d
ict
a
n
d
a
n
a
ly
z
e
d
a
ta.
It
c
a
n
a
ls
o
b
e
u
se
d
t
o
re
c
o
g
n
ize
p
a
tt
e
rn
a
n
d
d
e
v
e
lo
p
m
o
d
e
ls
f
o
r
a
rti
f
icia
l
in
telli
g
e
n
c
e
.
P
a
tt
e
rn
re
c
o
g
n
it
io
n
th
r
o
u
g
h
m
a
c
h
in
e
lea
rn
in
g
a
lg
o
rit
h
m
is
a
lrea
d
y
e
sta
b
li
sh
e
d
a
n
d
h
a
v
e
p
r
o
v
e
n
it
se
lf
a
c
c
u
ra
te
in
d
if
fe
re
n
t
f
ield
s
su
c
h
a
s
e
d
u
c
a
ti
o
n
,
c
rim
e
,
h
e
a
lt
h
a
n
d
m
a
n
y
o
th
e
rs
in
c
lu
d
in
g
f
ire
in
c
id
e
n
ts.
T
h
is
p
a
p
e
r
a
i
m
s
to
d
e
v
e
lo
p
a
m
o
d
e
l
f
o
r
re
c
o
g
n
izin
g
p
a
tt
e
rn
s
o
f
f
ire i
n
c
id
e
n
ts
in
th
e
p
r
o
v
in
c
e
o
f
L
a
g
u
n
a
,
P
h
il
ip
p
i
n
e
s imp
lem
e
n
ti
n
g
a
m
a
c
h
in
e
lea
rn
in
g
a
lg
o
rit
h
m
.
W
i
th
th
e
f
o
re
g
o
in
g
p
ro
jec
t,
it
is
f
o
u
n
d
o
u
t
t
h
a
t
a
re
c
u
rre
n
t
n
e
u
ra
l
n
e
tw
o
rk
sh
o
ws
a
n
a
sto
n
ish
in
g
re
su
lt
in
term
s
o
f
p
a
tt
e
rn
re
c
o
g
n
it
io
n
.
F
u
rt
h
e
r,
it
is
a
lso
f
o
u
n
d
th
a
t
Ca
lam
b
a
Cit
y
is
th
e
m
o
st v
u
ln
e
ra
b
le
a
re
a
in
c
a
se
o
f
f
ire o
c
c
u
rre
n
c
e
in
t
h
e
P
ro
v
in
c
e
o
f
L
a
g
u
n
a
.
K
ey
w
o
r
d
s
:
Fire
Mo
d
el
d
ev
elo
p
m
e
n
t
P
atter
n
r
ec
o
g
n
itio
n
R
NN
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
:
J
o
n
ar
d
o
R
.
A
s
o
r
C
o
lleg
e
o
f
C
o
m
p
u
ter
St
u
d
ies
L
a
g
u
n
a
State
P
o
l
y
tec
h
n
ic
Un
i
v
er
s
it
y
Ma
lin
ta,
L
o
s
B
añ
o
s
,
L
ag
u
n
a
4030
,
P
h
ilip
p
in
es
E
m
ail:
aso
r
.
j
o
n
ar
d
o
@
ls
p
u
.
ed
u
.
p
h
1.
I
NT
RO
D
UCT
I
O
N
Fire
is
o
n
e
o
f
t
h
e
i
n
it
ial
d
is
co
v
er
ies o
f
h
u
m
a
n
it
y
,
a
n
d
ar
g
u
ab
l
y
t
h
e
m
o
s
t i
m
p
o
r
tan
t o
n
e.
I
t g
av
e
u
s
t
h
e
ab
ilit
y
to
co
o
k
f
o
o
d
,
f
o
r
g
e
m
etal
to
o
ls
,
an
d
m
a
n
ag
e
p
o
w
er
p
lan
ts
.
T
h
e
k
n
o
w
n
h
az
ar
d
s
o
f
f
ir
e
f
o
r
th
e
f
ir
s
t
g
en
er
atio
n
s
f
o
r
th
e
p
eo
p
le
w
er
e
li
m
i
ted
to
th
er
m
al
r
is
k
s
o
n
l
y
.
B
u
t
d
esp
ite
t
h
e
ess
e
n
tia
l
u
s
e
o
f
lig
h
t,
it
ca
n
d
estro
y
h
o
u
s
e
s
an
d
p
r
o
p
er
ties
in
le
s
s
t
h
an
an
h
o
u
r
[
1
]
.
Fire
d
is
aster
is
a
co
m
m
o
n
th
r
ea
t
to
li
v
es
a
n
d
p
r
o
p
er
ty
.
T
h
e
ef
f
ec
ts
o
f
f
ir
e
d
is
a
s
ter
s
ca
n
b
e
h
ar
m
f
u
l
to
h
u
m
a
n
s
;
i
t
ca
n
lead
to
s
e
v
er
e
in
j
u
r
y
a
n
d
ev
e
n
d
ea
th
.
T
h
e
m
aj
o
r
ity
o
f
f
atalitie
s
ar
e
tr
ap
p
e
d
civ
ilian
s
w
h
o
d
ied
o
f
s
m
o
k
e
in
h
alatio
n
o
f
b
u
r
n
in
g
m
ater
ia
ls
[
2
]
.
Fire
-
r
elate
d
in
j
u
r
ie
s
an
d
d
ea
th
s
ar
e
g
r
o
w
i
n
g
i
n
cr
ea
s
i
n
g
l
y
an
d
n
ee
d
to
b
e
co
n
tr
o
lled
.
R
esear
ch
i
n
L
o
n
d
o
n
,
E
n
g
lan
d
h
as
s
h
o
w
n
t
h
at
t
h
e
m
aj
o
r
ity
o
f
f
ir
e
d
ea
t
h
s
h
av
e
o
cc
u
r
r
ed
in
co
m
m
u
n
ities
w
i
th
h
i
g
h
er
le
v
el
s
o
f
s
o
cio
ec
o
n
o
m
ic
d
ep
r
iv
atio
n
,
m
ea
s
u
r
ed
b
y
u
n
e
m
p
lo
y
m
en
t,
lo
w
i
n
co
m
e
s
,
h
ea
lt
h
ed
u
ca
tio
n
,
cr
i
m
e
a
n
d
h
o
u
s
in
g
[
3
]
.
T
h
e
2
0
1
8
r
ep
o
r
t
o
f
W
o
r
ld
H
ea
lth
Or
g
an
iza
ti
o
n
(
W
HO)
r
eg
ar
d
in
g
lo
s
s
o
f
lif
e
r
elate
d
to
f
ir
e
in
cid
en
t
s
s
h
o
w
s
t
h
at
t
h
e
P
h
ili
p
p
in
es
r
an
k
s
1
1
th
o
u
t
o
f
2
0
in
th
e
r
an
k
in
g
o
f
m
o
s
t
d
ea
th
to
lls
ca
u
s
ed
b
y
f
ir
e
in
cid
en
t
s
w
it
h
ap
p
r
o
x
i
m
atel
y
1
0
0
0
f
atalities
r
ec
o
r
d
ed
[
4
]
.
P
h
y
s
ical
d
is
co
m
f
o
r
t
an
d
o
v
er
ex
er
tio
n
,
cr
as
h
es,
o
b
j
ec
ts
b
ein
g
h
it,
an
d
ex
p
o
s
u
r
e
to
f
ir
e
m
ater
ials
ar
e
t
h
e
m
ai
n
ca
u
s
es o
f
f
ir
e
i
n
j
u
r
y
[
5
]
.
I
n
th
e
P
h
ilip
p
in
es
esp
ec
iall
y
i
n
t
h
e
Natio
n
al
C
ap
ital
A
r
ea
,
f
i
r
e
in
cid
en
t
s
h
a
v
e
i
n
cr
ea
s
ed
s
i
g
n
i
f
ica
n
tl
y
o
v
er
th
e
y
ea
r
s
an
d
ar
e
m
aj
o
r
t
h
r
ea
t
to
th
e
ec
o
n
o
m
y
.
Fire
s
s
p
r
ea
d
r
a
p
id
ly
d
u
e
to
ad
jo
in
in
g
h
o
m
e
s
in
r
esid
en
tia
l
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
22
,
No
.
3
,
J
u
n
e
2
0
2
1
:
1
4
2
7
-
1
4
3
5
1428
ar
ea
s
.
Ma
n
y
f
ac
to
r
s
th
at
lead
t
o
f
ir
e
-
r
elate
d
ac
cid
en
ts
ar
e
tr
ig
g
er
ed
b
y
elec
tr
ical
w
ir
in
g
,
u
n
atte
n
d
ed
g
as
s
to
v
e
s
an
d
th
e
u
s
e
o
f
ca
n
d
les
as
a
li
g
h
t
s
o
u
r
ce
.
Me
an
w
h
ile,
u
n
a
u
t
h
o
r
ized
co
n
n
ec
tio
n
s
an
d
th
e
u
s
e
o
f
ca
b
le
j
u
m
p
er
s
f
o
r
elec
tr
ic
m
eter
s
ar
e
th
e
n
u
m
b
er
o
n
e
ca
u
s
e
o
f
f
ir
e
i
n
cr
o
w
d
ed
r
esid
en
tial
ar
ea
s
[
6
]
.
T
h
e
n
ee
d
f
o
r
tech
n
ical
i
m
p
r
o
v
e
m
en
t
s
i
n
t
h
e
s
t
u
d
y
o
f
f
ir
e
e
v
en
t
s
i
s
v
er
y
i
m
p
o
r
tan
t.
W
ith
t
h
e
aid
o
f
ad
d
itio
n
al
f
ir
e
an
al
y
s
is
eq
u
ip
m
en
t,
f
ir
e
s
er
v
ices
ca
n
h
a
v
e
a
g
r
ea
ter
u
n
d
er
s
ta
n
d
in
g
o
f
f
ir
e
i
n
cid
en
t
s
.
T
h
ey
w
o
u
ld
t
h
e
n
b
e
ab
le
to
co
m
e
to
a
co
n
cl
u
s
io
n
ab
o
u
t
h
o
w
to
m
i
n
i
m
ize
a
n
d
p
r
ev
en
t
f
ir
e
ac
cid
e
n
ts
.
Fire
D
ep
ar
tm
e
n
t
s
w
il
l
ca
r
r
y
o
u
t
a
r
i
s
k
-
r
ed
u
ctio
n
,
d
r
ill,
p
r
o
g
r
am
s
,
an
d
a
w
ar
en
e
s
s
-
r
aisi
n
g
p
la
n
[
7
]
.
P
atter
n
r
ec
o
g
n
itio
n
is
a
s
cie
n
ti
f
ic
d
is
cip
lin
e
w
h
o
s
e
ai
m
is
to
r
ec
o
g
n
ize
o
b
j
ec
ts
in
a
v
ar
iet
y
o
f
ca
teg
o
r
ies
o
r
class
es.
Dep
e
n
d
in
g
o
n
th
e
ap
p
licatio
n
,
th
e
s
e
o
b
j
ec
ts
m
a
y
b
e
ca
teg
o
r
ized
as
i
m
a
g
es
o
r
s
ig
n
a
l
w
a
v
ef
o
r
m
s
o
r
s
o
m
e
s
o
r
t
o
f
m
ea
s
u
r
e
m
e
n
t
th
a
t
n
ee
d
s
to
b
e
class
if
ied
[
8
]
an
d
r
ef
er
r
ed
to
th
ese
o
b
j
ec
ts
u
s
in
g
t
h
e
g
en
er
ic
ter
m
p
atter
n
s
[
9
]
.
P
atter
n
id
en
tif
ica
tio
n
h
as
a
lo
n
g
tr
ad
itio
n
,
b
u
t
u
n
t
il
th
e
1
9
6
0
s
,
it
w
as
m
ai
n
l
y
th
e
p
r
o
d
u
ctiv
it
y
o
f
ac
ad
em
ic
s
t
u
d
y
in
th
e
f
ie
ld
o
f
s
tatis
t
ics
[
1
0
]
,
[
1
1
]
.
A
s
w
it
h
all
el
s
e
t
h
e
ad
v
e
n
t
o
f
co
m
p
u
ter
s
i
n
cr
ea
s
ed
t
h
e
d
em
a
n
d
f
o
r
p
r
ac
tical
ap
p
licat
io
n
s
f
o
r
p
atter
n
r
ec
o
g
n
it
io
n
,
w
h
ic
h
i
n
t
u
r
n
g
e
n
er
ated
n
e
w
d
e
m
an
d
s
f
o
r
m
o
r
e
th
eo
r
etica
l d
ev
elo
p
m
e
n
ts
[
1
2
]
.
R
eg
r
es
s
io
n
co
m
es
f
r
o
m
t
h
e
c
ateg
o
r
y
o
f
s
u
p
er
v
is
ed
lear
n
i
n
g
;
d
ea
ls
w
it
h
t
h
e
r
elatio
n
s
h
ip
b
et
w
ee
n
a
ca
teg
o
r
ical
d
ep
en
d
en
t
v
ar
iab
l
e
an
d
o
n
e
o
r
m
o
r
e
i
n
d
ep
en
d
en
t
v
ar
iab
les
b
y
esti
m
ati
n
g
p
r
o
b
ab
ilit
ies
u
s
i
n
g
a
s
ig
m
o
id
f
u
n
c
tio
n
[
1
3
]
.
I
n
o
th
er
in
s
ta
n
ce
s
,
an
al
y
s
is
u
s
es
t
h
e
d
ec
is
io
n
tr
ee
alg
o
r
it
h
m
.
F
ir
e
ac
cid
en
ts
i
n
ter
m
s
o
f
d
ec
is
io
n
-
m
a
k
i
n
g
p
r
i
n
cip
les,
u
s
in
g
t
h
e
ter
m
in
o
lo
g
y
o
f
d
ec
i
s
io
n
-
m
a
k
i
n
g
a
n
d
r
is
k
an
al
y
s
is
as
th
e
b
asi
s
f
o
r
th
e
r
elatio
n
s
h
ip
b
et
w
ee
n
f
ir
e
m
an
ag
e
m
e
n
t
d
ec
is
io
n
-
m
a
k
in
g
an
d
in
cid
en
t
o
u
tco
m
e
s
[
1
4
]
.
T
h
e
b
asic
ap
p
r
o
ac
h
is
e
m
b
o
d
ied
in
o
n
e
o
f
th
e
co
r
e
p
r
in
cip
les
o
f
d
ec
i
s
io
n
a
n
al
y
s
is
,
t
h
at
o
f
t
h
e
d
ec
o
m
p
o
s
itio
n
b
y
wh
ich
lar
g
e,
co
m
p
le
x
p
r
o
b
lem
s
ca
n
b
e
b
etter
u
n
d
e
r
s
to
o
d
b
y
b
r
ea
k
i
n
g
t
h
e
m
d
o
w
n
o
r
"
d
ec
o
m
p
o
s
in
g
"
th
e
m
in
to
s
m
aller
m
o
r
e
m
an
a
g
ea
b
le
p
r
o
b
le
m
s
th
at
ca
n
b
e
r
eso
lv
ed
o
r
d
ef
in
ed
i
n
s
o
m
e
d
etail
[
1
5
]
.
T
o
d
ay
,
m
ac
h
in
e
l
ea
r
n
in
g
al
g
o
r
ith
m
s
ar
e
co
m
m
o
n
l
y
u
s
ed
to
id
en
ti
f
y
tr
e
n
d
s
n
o
t
o
n
l
y
i
n
cr
i
m
e,
ed
u
ca
tio
n
,
h
ea
lt
h
an
d
b
u
s
i
n
e
s
s
b
u
t
also
in
f
ir
e
in
cid
en
t
s
[
1
6
]
-
[1
8
]
.
T
h
e
m
ain
o
b
j
ec
tiv
e
o
f
t
h
is
p
ap
er
is
to
r
ec
o
g
n
ized
p
atter
n
a
n
d
id
en
ti
f
y
tr
en
d
s
o
f
f
ir
e
i
n
cid
en
t
s
in
L
ag
u
n
a,
P
h
ilip
p
in
es
u
s
i
n
g
m
ac
h
i
n
e
lear
n
i
n
g
al
g
o
r
ith
m
s
.
2.
RE
S
E
ARCH
M
E
T
H
O
D
2
.
1
.
Da
t
a
c
o
llect
io
n
T
h
e
f
ir
e
in
cid
en
t
s
d
ata
o
b
tain
ed
f
r
o
m
B
u
r
ea
u
o
f
f
ir
e
p
r
o
tectio
n
(
B
FP
)
a
r
e
r
ec
o
r
d
s
co
v
er
in
g
th
e
p
er
io
d
o
f
2
0
1
4
to
2
0
1
8
f
ir
e
in
cid
en
ts
in
L
ag
u
n
a.
T
h
e
d
ata
ar
e
class
i
f
ied
w
it
h
t
h
e
f
o
llo
w
i
n
g
ca
teg
o
r
ies;
ti
m
e
an
d
p
lace
w
h
er
e
th
e
f
ir
e
in
cid
en
t
o
cc
u
r
r
ed
,
o
cc
u
p
an
cy
,
t
h
e
ca
u
s
e
o
f
f
i
r
e,
alar
m
lev
e
l,
an
d
ca
s
u
altie
s
in
th
e
f
ir
e
in
cid
en
t.
A
lar
m
lev
e
l
w
ill
b
e
u
s
ed
as
t
h
e
class
f
o
r
class
if
y
i
n
g
f
ir
e
i
n
ci
d
en
ts
.
I
t
is
co
m
p
o
s
ed
o
f
s
i
x
in
s
tan
ce
s
n
a
m
el
y
:
1
st
,
2
nd
, 3
rd
, 4
th
,
5
th
an
d
n
o
alar
m
.
2
.
2
.
P
re
-
pro
ce
s
s
ing
o
f
da
t
a
P
r
e
-
p
r
o
ce
s
s
in
g
is
n
ec
ess
ar
y
to
m
ak
e
s
u
r
e
th
at
t
h
e
d
ataset
co
n
t
ain
s
n
o
b
iases
i
n
r
ec
o
g
n
izi
n
g
p
atter
n
s
o
f
f
ir
e
i
n
cid
en
t
s
.
First,
th
e
d
ata
u
n
d
er
w
e
n
t n
o
r
m
aliza
tio
n
w
h
er
e
th
e
d
ata
h
as
a
n
u
n
k
n
o
w
n
o
r
u
n
id
en
ti
f
ied
attr
ib
u
te
an
d
is
n
o
t
co
m
p
a
tib
le
w
it
h
t
h
e
s
p
ec
i
f
ic
d
ataset.
T
h
e
n
o
r
m
aliza
tio
n
p
r
o
ce
s
s
is
r
eq
u
ir
e
d
to
m
i
n
i
m
ize
d
ata
r
ed
u
n
d
an
c
y
.
C
lea
n
in
g
an
d
o
r
g
an
izi
n
g
t
h
e
d
ata
(
r
em
o
v
in
g
s
y
m
b
o
l
s
an
d
co
n
v
er
ti
n
g
th
e
te
x
t
in
to
lo
w
er
ca
s
e)
is
also
r
ec
o
m
m
e
n
d
ed
to
m
ak
e
t
h
e
d
ata
m
ea
n
i
n
g
f
u
l.
T
h
e
f
ir
e
i
n
cid
en
ts
d
ata
h
a
s
n
u
m
er
o
u
s
at
tr
ib
u
tes
i
n
t
h
e
g
i
v
e
n
r
a
w
d
ata
w
h
ich
ar
e
n
o
t
n
ee
d
ed
in
d
ev
elo
p
in
g
th
e
p
r
o
j
ec
t.
I
n
ass
u
r
i
n
g
t
h
at
a
q
u
alit
y
m
o
d
el
w
ill
b
e
d
ev
elo
p
ed
,
attr
ib
u
tes
w
i
th
t
h
e
s
a
m
e
m
ea
n
i
n
g
w
a
s
r
e
m
o
v
ed
[
1
9
]
,
[
2
0
]
.
Sin
ce
d
ate
o
cc
u
r
r
ed
an
d
in
cid
en
t
r
ep
o
r
t
ar
e
th
e
s
a
m
e,
o
n
e
o
f
th
ese
attr
ib
u
te
s
w
as
r
em
o
v
ed
an
d
th
e
o
th
er
o
n
e
w
as
s
u
s
tai
n
ed
to
r
em
o
v
e
d
ata
n
o
is
es.
T
h
is
w
as
d
o
n
e
in
th
e
en
t
ir
e
d
ataset
w
h
ic
h
p
r
o
v
i
d
e
th
e
d
ataset
attr
ib
u
tes
s
h
o
w
n
in
T
ab
le
1
.
T
ab
le
1
.
A
ttrib
u
tes
o
f
L
a
g
u
n
a
f
ir
e
in
cid
e
n
ts
d
atase
t
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
D
a
t
e
O
c
c
u
r
r
e
d
Ex
a
c
t
D
a
t
e
o
f
F
i
r
e
I
n
c
i
d
e
n
t
h
a
p
p
e
n
D
a
t
e
T
i
me
O
c
c
u
r
r
e
d
Ex
a
c
t
T
i
me
T
i
me
O
c
c
u
p
a
n
c
y
C
l
a
ssi
f
i
c
a
t
i
o
n
o
f
S
t
r
u
c
t
u
r
e
S
t
r
i
n
g
C
a
u
se
o
f
F
i
r
e
C
a
u
se
s o
f
t
h
e
F
i
r
e
S
t
r
i
n
g
A
l
a
r
m
L
e
v
e
l
T
h
e
A
l
a
r
m
L
e
v
e
l
o
f
F
i
r
e
I
n
t
e
g
e
r
C
a
s
u
a
l
t
i
e
s
T
h
e
c
a
su
a
l
t
i
e
s ma
d
e
b
y
t
h
e
F
i
r
e
I
n
t
e
g
e
r
L
o
c
a
t
i
o
n
W
h
e
r
e
t
h
e
f
i
r
e
i
n
c
i
d
e
n
t
s o
c
c
u
r
r
e
d
S
t
r
i
n
g
I
n
s
tati
s
tics
a
n
d
m
ac
h
i
n
e
lear
n
i
n
g
,
it
i
s
u
s
u
all
y
a
r
eq
u
ir
e
m
e
n
t
t
o
s
p
lit
th
e
d
ata
in
to
t
w
o
s
u
b
s
et
s
-
t
h
e
tr
ai
n
an
d
test
s
et.
T
h
e
tr
ain
d
ataset
w
il
l
b
e
u
s
ed
to
f
it
th
e
m
o
d
el,
in
o
r
d
er
to
m
a
k
e
p
r
ed
ictio
n
s
o
n
th
e
test
d
ataset.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
F
ir
e
in
cid
en
ts
visu
a
liz
a
tio
n
a
n
d
p
a
tter
n
r
ec
o
g
n
itio
n
u
s
in
g
m
a
ch
in
e
lea
r
n
in
g
…
(
Jo
n
a
r
d
o
R
.
A
s
o
r
)
1429
Sep
ar
atin
g
t
h
e
d
ata
in
to
tr
ain
s
et
w
h
ic
h
is
8
0
%
an
d
2
0
%,
th
e
test
s
et.
T
h
ese
t
w
o
ar
e
n
e
ed
ed
s
o
th
er
e
is
an
u
n
b
ia
s
ed
p
r
ed
ictio
n
o
f
f
ir
e
i
n
c
id
en
ts
d
ata
an
d
e
v
alu
a
te
d
ata
m
i
n
in
g
m
o
d
els
[
2
1
]
.
B
y
s
i
m
p
l
y
lo
o
k
i
n
g
at
T
ab
le
2
,
it
is
n
o
ticea
b
le
th
at
th
e
d
atasets
co
n
tain
s
o
m
u
ch
b
ias
in
ter
m
s
o
f
n
u
m
b
er
s
o
f
o
cc
u
r
r
en
ce
s
.
Sin
ce
th
is
p
r
o
j
ec
t
in
te
n
d
s
to
r
ec
o
g
n
ize
p
atter
n
,
th
is
w
il
l
n
o
t
b
e
a
p
r
o
b
lem
,
h
o
w
e
v
er
,
in
s
o
m
e
s
tu
d
ie
s
esp
ec
iall
y
in
telli
g
en
t
s
y
s
te
m
s
an
d
m
o
d
el
d
ev
elo
p
m
e
n
t,
th
is
b
ias
m
u
s
t
b
e
eli
m
in
ated
.
No
n
et
h
eles
s
,
s
y
n
th
e
tic
m
i
n
o
r
it
y
o
v
er
s
a
m
p
li
n
g
tech
n
iq
u
e
(
SMOT
E
)
is
im
p
le
m
e
n
ted
in
th
is
p
ap
er
to
ass
u
r
e
th
at
t
h
e
e
v
alu
a
tio
n
o
f
m
ac
h
i
n
e
lear
n
i
n
g
alg
o
r
ith
m
w
il
l
n
o
t
co
n
tain
an
y
b
ias.
SMOT
E
f
i
n
d
s
th
e
c
lo
s
est
n
ei
g
h
b
o
r
s
in
m
i
n
o
r
it
y
c
lass
f
o
r
ea
c
h
s
a
m
p
le
i
n
t
h
e
cla
s
s
.
I
t
th
e
n
d
r
a
w
s
a
li
n
e
b
et
w
ee
n
t
h
e
n
e
ig
h
b
o
r
s
an
d
g
e
n
er
ates
r
a
n
d
o
m
p
o
in
ts
o
n
th
e
lin
e
f
o
r
p
r
o
d
u
cin
g
n
e
w
d
ata.
T
h
e
u
s
e
o
f
th
i
s
m
et
h
o
d
is
v
ital i
n
p
r
ed
ictin
g
class
o
f
f
ir
e
i
n
cid
en
ts
[
2
2
]
.
T
ab
le
2
.
Dis
tr
ib
u
tio
n
o
f
f
ir
e
alar
m
in
tr
ai
n
an
d
tes
t d
ataset
A
l
a
r
m
L
e
v
e
l
T
r
a
i
n
S
e
t
T
e
st
S
e
t
1
st
A
l
a
r
m
2
,
0
9
8
5
2
4
2
nd
A
l
a
r
m
53
13
3
rd
A
l
a
r
m
19
5
4
th
A
l
a
r
m
9
2
5
th
A
l
a
r
m
1
1
N
o
A
l
a
r
m
1
0
6
27
T
o
t
a
l
2
2
8
6
57
2
.
3
.
Alg
o
rit
h
m
ev
a
lua
t
io
n
I
n
o
r
d
er
to
u
n
d
er
s
tan
d
th
e
co
m
p
ar
at
iv
e
q
u
alit
ies
o
f
th
e
alg
o
r
ith
m
,
it
is
cr
u
cial
to
ev
alu
at
e
th
e
m
.
T
h
e
p
r
im
ar
y
m
e
th
o
d
s
to
ev
al
u
atio
n
ca
n
b
e
ch
ar
ac
ter
ized
as
ex
p
er
im
e
n
tal.
E
x
p
er
i
m
e
n
tal
ev
a
lu
atio
n
ap
p
lies
t
h
e
alg
o
r
ith
m
to
lear
n
i
n
g
ta
s
k
s
to
s
tu
d
y
it
s
p
er
f
o
r
m
an
ce
i
n
p
r
ac
tice.
So
m
e
m
o
d
els
m
a
y
g
i
v
e
s
at
is
f
y
in
g
r
esu
lts
w
h
e
n
ev
alu
a
tin
g
b
u
t
o
th
er
s
m
a
y
g
i
v
e
p
o
o
r
r
esu
lts
w
h
en
e
v
al
u
ated
[
2
3
]
.
T
h
er
ef
o
r
e,
it
is
an
e
x
ce
ll
en
t
w
a
y
to
ev
a
lu
ate
m
ac
h
in
e
lear
n
i
n
g
al
g
o
r
ith
m
s
t
o
h
av
e
a
w
ell
p
r
o
ce
s
s
ed
p
r
o
j
ec
t.
T
h
is
p
h
ase
r
eq
u
ir
es th
e
f
o
llo
w
i
n
g
:
2
.
3
.
1
.
Co
nfusi
o
n
m
a
t
ri
x
A
c
o
n
f
u
s
i
o
n
m
at
r
ix
w
il
l
b
e
u
s
e
d
t
o
c
h
a
r
a
ct
e
r
i
z
e
t
h
e
o
u
t
p
u
t
o
f
a
c
la
s
s
if
i
ca
t
i
o
n
m
o
d
e
l
o
r
c
l
as
s
i
f
i
e
r
in
a
c
o
l
l
e
c
ti
o
n
o
f
t
e
s
t
d
a
t
a
f
o
r
w
h
ic
h
t
r
u
e
v
alu
e
s
a
r
e
k
n
o
w
n
.
T
h
i
s
m
ak
es
q
u
i
ck
r
e
c
o
g
n
it
i
o
n
o
f
c
o
n
f
u
s
i
o
n
b
e
tw
ee
n
g
r
o
u
p
s
.
On
e
cl
a
s
s
is
u
s
u
al
ly
m
i
s
m
a
r
k
e
d
as
th
e
o
th
e
r
,
s
o
m
o
s
t
o
u
t
p
u
t
m
e
t
r
i
c
s
a
r
e
c
o
m
p
u
te
d
f
r
o
m
th
e
c
o
n
f
u
s
i
o
n
m
a
t
r
ix
[
2
4
]
,
[
2
5
]
.
T
h
e
c
o
n
f
u
s
i
o
n
m
a
t
r
ix
i
s
u
s
ef
u
l
f
o
r
ev
a
lu
a
ti
n
g
a
m
o
d
e
l
w
h
en
k
n
o
w
in
g
th
e
t
r
u
e
r
e
s
p
o
n
s
e
v
a
lu
es.
T
h
e
p
o
i
n
t
o
f
th
e
c
o
n
f
u
s
i
o
n
m
a
tr
i
x
in
th
e
p
r
o
je
c
t
i
s
t
o
d
e
f
i
n
e
t
h
e
p
e
r
f
o
r
m
a
n
c
e
s
u
ch
a
s
m
e
asu
r
in
g
p
r
e
c
i
s
i
o
n
,
r
e
c
al
l,
f
-
s
c
o
r
e
,
a
n
d
f
al
l
o
u
t
,
as
s
h
o
w
n
in
Fig
u
r
e
1
[
2
6
]
,
[
2
7
]
.
Fig
u
r
e
1
.
C
o
n
f
u
s
io
n
Ma
tr
i
x
2
.
3
.
2
.
Rec
a
ll/
s
ens
it
iv
it
y
T
h
e
r
ec
all
m
etr
ic
s
h
o
w
s
t
h
e
ca
p
ab
ilit
y
o
f
a
m
o
d
el
to
d
is
co
v
er
all
th
e
ap
p
r
o
p
r
iate
ca
s
es
in
a
d
ataset.
I
t
is
th
e
r
atio
o
f
th
e
to
tal
n
u
m
b
er
o
f
s
u
itab
le
class
i
f
ied
p
o
s
itiv
e
ex
a
m
p
le
s
d
iv
id
ed
b
y
th
e
to
tal
n
u
m
b
er
o
f
p
o
s
itiv
e
ex
a
m
p
le
s
.
I
t
ca
n
b
e
th
o
u
g
h
t
a
s
a
m
o
d
e
l’
s
s
k
il
l
to
f
in
d
all
th
e
d
ata
p
o
in
ts
o
f
in
ter
e
s
t
i
n
a
d
at
aset.
T
h
e
(
1
)
s
h
o
w
th
e
m
e
tr
ic
f
o
r
m
u
la
o
f
r
ec
all
.
R
ec
a
ll =
+
+
(
1
)
2
.
3
.
3
.
P
re
cisi
o
n
T
h
e
p
r
e
c
i
s
i
o
n
m
e
t
r
i
c
s
h
o
w
s
t
h
e
a
c
c
u
r
a
c
y
o
f
t
h
e
p
o
s
i
t
i
v
e
c
l
a
s
s
.
I
t
a
l
s
o
m
e
a
s
u
r
e
s
h
o
w
p
o
s
s
i
b
l
e
t
h
e
p
r
e
d
i
c
t
i
o
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
22
,
No
.
3
,
J
u
n
e
2
0
2
1
:
1
4
2
7
-
1
4
3
5
1430
o
f
t
h
e
p
o
s
i
t
i
v
e
c
l
a
s
s
i
s
a
c
c
u
r
a
t
e
.
P
r
e
c
i
s
i
o
n
i
s
i
d
e
n
t
i
f
i
e
d
a
s
t
h
e
n
u
m
b
e
r
o
f
t
r
u
e
p
o
s
i
t
i
v
e
s
d
i
v
i
d
e
d
b
y
t
h
e
n
u
m
b
e
r
o
f
t
r
u
e
p
o
s
i
t
i
v
e
p
l
u
s
t
h
e
n
u
m
b
e
r
o
f
f
a
l
s
e
p
o
s
i
t
i
v
e
s
.
F
a
l
s
e
p
o
s
i
t
i
v
e
s
a
r
e
c
a
s
e
s
t
h
a
t
t
h
e
m
o
d
e
l
i
n
c
o
r
r
e
c
t
l
y
l
a
b
e
l
s
a
s
p
o
s
i
t
i
v
e
t
h
a
t
a
r
e
a
c
t
u
a
l
l
y
n
e
g
a
t
i
v
e
.
T
h
e
(
2
)
s
h
o
w
s
t
h
e
m
e
t
r
i
c
f
o
r
m
u
l
a
o
f
p
r
e
c
i
s
i
o
n
.
P
r
ec
is
io
n
=
+
+
(
2
)
2
.
3
.
4
.
F
-
Sco
re
I
n
s
o
m
e
co
n
d
itio
n
s
,
i
t
is
r
e
m
ar
k
ab
le
to
m
a
x
i
m
ize
t
h
e
u
s
e
o
f
e
ith
er
r
ec
all
o
r
p
r
ec
is
io
n
at
th
e
co
s
t
o
f
th
e
o
th
er
m
e
tr
ics.
F
-
s
co
r
e
is
th
e
h
ar
m
o
n
ic
m
ea
n
o
f
b
o
th
p
r
ec
is
io
n
an
d
r
ec
all,
w
h
er
ea
s
f
o
r
an
F
-
s
co
r
e
s
co
p
e
th
e
b
est
v
alu
e
i
s
1
an
d
th
e
w
o
r
s
t
i
s
0
.
I
t
g
iv
e
s
th
e
w
ei
g
h
ted
av
er
ag
e
o
f
r
ec
all
an
d
p
r
ec
is
io
n
.
T
h
er
e
a
r
e
o
th
er
m
etr
ic
s
f
o
r
co
m
b
i
n
i
n
g
p
r
ec
is
io
n
an
d
r
ec
all
,
b
u
t
th
e
F
-
sc
o
r
e
is
t
h
e
m
o
s
t
co
m
m
o
n
l
y
u
s
ed
.
I
f
cr
ea
tin
g
a
b
alan
ce
d
class
i
f
icatio
n
m
o
d
el
w
i
th
th
e
o
p
ti
m
al
b
alan
c
e
o
f
r
ec
all
an
d
p
r
ec
is
io
n
,
t
h
en
th
e
u
s
e
o
f
F
-
s
co
r
e
is
an
e
x
ce
ll
en
t
ch
o
ice.
T
h
e
(
3
)
s
h
o
w
s
t
h
e
m
etr
ic
f
o
r
m
u
la
o
f
F
-
s
co
r
e
.
F
-
S
co
r
e
= 2
*
∗
+
(
3
)
2
.
3
.
5
.
Sp
ec
if
icit
y
I
t
q
u
an
ti
f
ie
s
t
h
e
ev
a
s
io
n
o
f
f
al
s
e
p
o
s
itiv
e
s
.
I
t
is
ca
lled
tr
u
e
n
eg
ati
v
e
r
ate,
m
ea
s
u
r
i
n
g
t
h
e
p
r
o
p
o
r
tio
n
o
f
n
eg
at
iv
e
s
t
h
at
ar
e
co
r
r
ec
tl
y
id
e
n
ti
f
ied
.
I
n
th
i
s
s
tu
d
y
,
s
p
ec
i
f
icit
y
w
il
l
m
ea
s
u
r
e
h
o
w
m
a
n
y
co
r
r
ec
t
alar
m
lev
el
s
ar
e
p
r
ed
icted
co
r
r
ec
tly
.
T
h
e
(
4
)
s
h
o
w
s
t
h
e
m
etr
ic
f
o
r
m
u
la
o
f
s
p
ec
if
icit
y
.
S
p
ec
ificity
=
+
(
4
)
2
.
3
.
6
.
F
a
llo
ut
T
h
e
f
alse
p
o
s
it
iv
e
r
ate
o
r
f
all
o
u
t
is
ca
lcu
la
ted
as
t
h
e
r
atio
b
et
w
ee
n
t
h
e
n
u
m
b
er
o
f
n
e
g
at
iv
e
e
v
en
t
s
w
r
o
n
g
l
y
ca
te
g
o
r
ized
as p
o
s
itiv
e
an
d
th
e
to
tal
n
u
m
b
er
o
f
ac
tu
al
n
e
g
ativ
e
e
v
e
n
ts
.
Fallo
u
t
is
r
eq
u
ir
ed
to
co
m
p
u
te
an
d
illu
s
tr
ate
th
e
t
w
o
m
etr
ics
to
h
av
e
a
b
ett
er
r
ep
r
esen
tatio
n
o
f
th
e
r
ec
ei
v
er
o
p
er
atin
g
ch
ar
ac
ter
is
tic
(
R
OC
)
cu
r
v
e.
T
h
e
(
5
)
s
h
o
w
s
th
e
m
etr
i
c
f
o
r
m
u
la
o
f
f
a
llo
u
t
.
F
a
llo
u
t =
1
–
S
p
ec
ificity
(
5
)
3.
RE
SU
L
T
S
A
ND
D
IS
CU
SS
I
O
N
I
n
th
is
s
tu
d
y
f
o
u
r
d
if
f
er
e
n
t
m
ac
h
in
e
lear
n
i
n
g
al
g
o
r
ith
m
s
n
a
m
el
y
,
s
u
p
p
o
r
t
v
ec
to
r
r
eg
r
ess
o
r
,
d
ec
is
io
n
tr
ee
r
eg
r
ess
o
r
,
r
an
d
o
m
f
o
r
est
r
eg
r
ess
o
r
an
d
r
ec
u
r
r
e
n
t
n
e
u
r
al
n
et
w
o
r
k
(
R
NN)
w
er
e
u
s
ed
to
d
ev
elo
p
ed
a
m
o
d
el
f
o
r
p
atter
n
r
ec
o
g
n
itio
n
an
d
v
is
u
aliza
tio
n
o
f
f
ir
e
o
cc
u
r
r
en
ce
s
in
th
e
p
r
o
v
in
ce
o
f
L
a
g
u
n
a,
P
h
ili
p
p
in
es.
T
h
is
s
ec
tio
n
w
il
l
d
is
cu
s
s
t
h
e
f
i
n
d
in
g
s
i
n
b
o
th
m
o
d
el
d
ev
elo
p
m
en
t
a
n
d
d
ata
v
is
u
aliza
t
io
n
.
Fi
g
u
r
es
an
d
t
ab
les
w
er
e
u
s
ed
to
ea
s
il
y
s
h
o
w
t
h
e
r
es
u
lts
i
n
ex
p
e
r
i
m
en
ts
d
o
n
e
in
t
h
i
s
s
t
u
d
y
.
3
.
1
.
Resul
t
s
ba
s
ed
o
n
a
lg
o
rit
h
m
ev
a
lua
t
io
n
As
s
h
o
w
n
in
T
ab
le
3
,
all
o
f
th
e
alg
o
r
it
h
m
s
p
ass
ed
th
e
t
y
p
ical
ac
cu
r
ac
y
f
o
r
m
o
d
el
d
ev
elo
p
m
e
n
t,
h
o
w
ev
er
,
as s
h
o
w
n
o
n
t
h
e
tab
le,
Dec
is
io
n
tr
ee
r
eg
r
es
s
o
r
an
d
r
an
d
o
m
f
o
r
est r
e
g
r
ess
o
r
o
v
er
f
i
ts
th
e
m
o
d
el
w
h
ic
h
w
a
s
n
o
t
a
g
r
ea
t
id
ea
.
Fu
r
th
er
m
o
r
e,
R
NN
s
h
o
w
s
an
i
m
p
r
es
s
iv
e
r
esu
lt
b
u
t
h
a
s
a
m
i
n
o
r
p
r
o
b
le
m
in
ter
m
s
o
f
th
e
d
is
tan
ce
r
es
u
lt
o
f
r
o
o
t
m
ea
n
s
q
u
ar
e
er
r
o
r
(
R
MSE
)
an
d
s
tan
d
ar
d
d
ev
iatio
n
.
T
h
is
lead
s
to
d
o
f
u
r
t
h
er
ev
al
u
atio
n
in
th
e
lear
n
i
n
g
o
f
ea
ch
al
g
o
r
ith
m
.
T
ab
le
3.
R
o
o
t
m
ea
n
s
q
u
ar
ed
er
r
o
r
r
e
p
o
r
t o
f
alg
o
r
ith
m
s
A
l
g
o
r
i
t
h
m
R
M
S
E
(
t
r
a
i
n
)
R
M
S
E
(
t
e
st
)
S
T
D
(
t
r
a
i
n
)
S
T
D
(
t
e
st
)
S
u
p
p
o
r
t
V
e
c
t
o
r
R
e
g
r
e
sso
r
0
.
6
2
0
.
6
2
0
.
2
3
0
.
2
4
D
e
c
i
si
o
n
T
r
e
e
R
e
g
r
e
sso
r
1
.
6
9
1
.
6
6
0
.
2
5
0
.
2
3
R
a
n
d
o
m F
o
r
e
st
R
e
g
r
e
sso
r
0
.
1
3
7
.
7
3
0
.
2
5
0
.
3
1
R
e
c
u
r
r
e
n
t
N
e
u
r
a
l
N
e
t
w
o
r
k
0
.
0
9
2
0
.
0
8
5
0
.
1
6
2
0
.
1
7
1
T
ab
le
4
r
ep
r
esen
ts
th
e
co
n
f
u
s
io
n
m
a
tr
ix
w
h
ic
h
is
ac
q
u
ir
ed
th
r
o
u
g
h
t
h
e
u
s
e
o
f
P
y
th
o
n
an
d
a
f
ter
ap
p
ly
i
n
g
SMOT
E
.
I
t
in
clu
d
es
tr
u
e
p
o
s
itiv
e,
tr
u
e
n
e
g
ati
v
e,
f
al
s
e
p
o
s
it
iv
e
an
d
f
al
s
e
n
e
g
ati
v
e
o
f
th
e
l
ab
el
ch
o
s
en
in
t
h
e
d
ataset.
Hen
ce
,
th
e
tab
le
s
h
o
w
s
th
at
r
ec
u
r
r
en
t n
e
u
r
al
n
et
w
o
r
k
o
n
l
y
p
r
ed
icted
a
w
r
o
n
g
lab
el
i
n
2
nd
alar
m
an
d
n
o
alar
m
.
T
h
er
ef
o
r
e,
th
er
e
ar
e
s
o
m
e
v
al
u
e
s
w
h
ic
h
m
a
y
b
e
f
o
u
n
d
o
n
1
st
alar
m
a
n
d
n
o
alar
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
F
ir
e
in
cid
en
ts
visu
a
liz
a
tio
n
a
n
d
p
a
tter
n
r
ec
o
g
n
itio
n
u
s
in
g
m
a
ch
in
e
lea
r
n
in
g
…
(
Jo
n
a
r
d
o
R
.
A
s
o
r
)
1431
T
ab
le
4.
C
o
n
f
u
s
io
n
m
atr
i
x
o
f
R
NN
b
ased
o
n
th
e
f
ir
e
alar
m
l
ev
els
T
r
u
e
1
st
A
l
a
r
m
T
r
u
e
2
nd
A
l
a
r
m
T
r
u
e
3
rd
A
l
a
r
m
T
r
u
e
4
th
A
l
a
r
m
T
r
u
e
N
o
A
l
a
r
m
P
r
e
d
i
c
t
e
d
1
st
A
l
a
r
m
1
1
6
0
0
0
0
P
r
e
d
i
c
t
e
d
2
nd
A
l
a
r
m
0
1
2
0
0
0
8
P
r
e
d
i
c
t
e
d
3
rd
A
l
a
r
m
0
0
1
2
9
0
0
P
r
e
d
i
c
t
e
d
4
th
A
l
a
r
m
0
0
0
1
2
0
0
P
r
e
d
i
c
t
e
d
N
o
A
l
a
r
m
4
0
0
0
1
1
2
As
s
h
o
w
n
in
T
ab
le
5
,
r
ec
all
h
a
s
a
to
tal
m
ea
n
o
f
0
.
9
8
w
h
ic
h
m
ea
n
s
t
h
at
th
e
cla
s
s
i
f
ied
lab
els
ar
e
co
r
r
ec
t
w
it
h
m
i
n
i
m
u
m
er
r
o
r
.
L
ik
e
w
is
e,
as
i
n
d
icate
d
in
p
r
ec
is
io
n
,
t
h
e
co
r
r
ec
tn
es
s
o
f
t
h
e
alg
o
r
it
h
m
in
ter
m
s
o
f
p
r
ed
ictin
g
f
ir
e
o
cc
u
r
r
en
ce
is
ac
c
u
r
ate
g
ai
n
in
g
a
to
tal
m
ea
n
s
co
r
e
o
f
0
.
9
8
2
.
F
-
s
co
r
e
g
ar
n
er
ed
a
to
tal
m
ea
n
o
f
0
.
9
8
ap
p
r
o
ac
h
in
g
1
w
h
ic
h
is
t
h
e
b
ase
o
f
p
r
ed
ictio
n
ac
cu
r
ac
y
.
A
s
f
o
r
s
p
ec
if
icit
y
,
0
.
9
8
2
to
tal
m
ea
n
w
as
ac
q
u
ir
ed
w
h
ic
h
m
ea
n
s
th
a
t
th
e
alg
o
r
it
h
m
i
s
ca
p
ab
le
o
f
s
p
ec
if
y
in
g
ea
ch
lab
el
in
clas
s
i
f
ic
atio
n
co
r
r
ec
tly
.
W
h
er
ea
s
,
f
a
llo
u
t
w
h
ic
h
r
ep
r
esen
t
s
th
e
in
co
r
r
ec
t
p
r
ed
ictio
n
o
f
th
e
alg
o
r
ith
m
,
a
to
tal
m
ea
n
o
f
0
.
0
2
w
as
attai
n
ed
,
th
er
ef
o
r
e,
th
e
alg
o
r
it
h
m
h
as
a
p
r
o
m
i
s
in
g
p
r
ed
ictio
n
ca
p
ab
ilit
y
.
T
ab
le
5
.
R
esu
lt o
f
R
NN
al
g
o
r
ith
m
e
v
al
u
atio
n
A
l
a
r
m
L
e
v
e
l
s
R
e
c
a
l
l
P
r
e
c
i
si
o
n
F
-
S
c
o
r
e
S
p
e
c
i
f
i
c
i
t
y
F
a
l
l
o
u
t
1
st
A
l
a
r
m
0
.
9
7
1
0
.
9
8
0
.
9
7
0
.
0
3
2
nd
A
l
a
r
m
1
0
.
9
4
0
.
9
7
1
0
3
rd
A
l
a
r
m
1
1
1
1
0
4
th
A
l
a
r
m
1
1
1
1
0
N
o
A
l
a
r
m
0
.
9
3
0
.
9
7
0
.
9
5
0
.
9
4
0
.
0
6
T
o
t
a
l
M
e
a
n
0
.
9
8
0
.
9
8
2
0
.
9
8
0
.
9
8
2
0
.
0
2
3
.
2
.
Resul
t
s
ba
s
ed
o
n
da
t
a
v
i
s
ua
liza
t
io
n
B
ased
o
n
th
e
d
ata
o
f
B
FP
,
m
o
s
t
ca
s
es
o
f
f
ir
e
o
cc
u
r
r
en
ce
s
in
L
a
g
u
n
a
w
er
e
d
u
r
in
g
th
e
y
ea
r
2
0
1
4
w
i
t
h
8
0
2
ca
s
es
w
h
ile
2
0
1
7
h
as
t
h
e
l
ea
s
t
o
cc
u
r
r
en
ce
s
ac
c
u
m
u
lated
w
it
h
4
4
9
ca
s
es
as
s
h
o
w
n
i
n
F
i
g
u
r
e
2
.
T
h
e
ch
a
n
g
es
o
v
er
ti
m
e
i
n
t
h
e
g
r
ap
h
is
d
y
n
a
m
ic,
t
h
er
e
ar
e
y
ea
r
s
t
h
at
s
o
m
eti
m
es
th
e
ca
s
es
o
f
in
cid
e
n
t
s
ar
e
en
o
r
m
o
u
s
an
d
s
o
m
eti
m
es,
les
s
e
r.
Fig
u
r
e
3
s
h
o
w
s
th
a
t th
e
h
i
g
h
e
s
t c
ase
o
f
f
ir
e
in
cid
en
ts
o
cc
u
r
r
ed
in
th
e
m
o
n
th
o
f
A
p
r
il h
av
i
n
g
6
2
7
in
cid
en
ts
an
d
tak
in
g
th
e
c
lo
s
est
s
p
o
t
in
ter
m
s
o
f
i
n
cid
en
ts
r
ec
o
r
d
ed
is
th
e
m
o
n
t
h
o
f
Ma
r
ch
,
r
ec
o
r
d
in
g
6
1
8
ev
en
t
s
.
Mo
r
eo
v
er
,
th
e
m
o
n
th
o
f
Sep
te
m
b
er
h
as
t
h
e
l
ea
s
t
o
cc
u
r
r
en
ce
o
f
f
ir
e
in
cid
en
ts
ac
cu
m
u
lati
n
g
7
7
ca
s
es
i
n
a
5
y
ea
r
s
s
p
a
n
f
r
o
m
2
0
1
4
to
2
0
1
8
.
Fig
u
r
e
4
d
is
p
la
y
s
th
at
f
ir
e
i
n
cid
en
ts
u
s
u
all
y
h
ap
p
en
d
u
r
in
g
t
h
e
w
ee
k
e
n
d
s
.
T
h
e
g
r
ap
h
s
i
g
n
i
f
ie
s
t
h
e
n
u
m
b
er
s
o
f
f
ir
e
ev
e
n
ts
t
h
at
o
cc
u
r
s
ev
er
y
d
a
y
i
n
th
e
p
r
o
v
in
c
e
L
ag
u
n
a.
B
ased
o
n
th
e
o
b
s
er
v
atio
n
o
f
t
h
e
g
r
ap
h
,
m
an
y
i
n
cid
e
n
ts
h
ap
p
en
o
n
Su
n
d
a
y
w
i
th
4
5
4
ca
s
es
w
h
ile
wed
n
esd
a
y
h
as
t
h
e
s
m
a
lles
t
ca
s
es
o
f
f
ir
e
w
it
h
3
8
3
ca
s
es.
T
h
is
i
m
p
lies
th
a
t
th
e
B
u
r
ea
u
o
f
Fire
P
r
o
tectio
n
n
ee
d
s
to
b
e
aler
t
an
d
p
r
ep
ar
ed
d
u
r
i
n
g
th
e
w
ee
k
e
n
d
s
to
l
ess
e
n
f
ir
e
d
is
a
s
ter
s
i
n
t
h
e
p
r
o
v
in
ce
.
Fi
g
u
r
e
5
d
ep
icts
th
a
t t
h
e
n
u
m
er
o
u
s
ca
s
es o
f
f
ir
es a
r
e
u
s
u
all
y
h
ap
p
en
in
g
a
t
th
e
ti
m
e
o
f
2
:0
0
to
3
:0
0
in
th
e
af
ter
n
o
o
n
w
h
ile
t
h
eir
s
m
a
ll
ca
s
es
o
f
f
ir
e
o
cc
u
r
in
th
e
ti
m
e
o
f
4
:0
0
in
th
e
m
o
r
n
i
n
g
.
Fig
u
r
e
2
.
Fire
in
cid
en
t
s
in
L
a
g
u
n
a
p
er
Yea
r
s
in
ce
2
0
1
4
u
p
-
to
2
0
1
8
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
22
,
No
.
3
,
J
u
n
e
2
0
2
1
:
1
4
2
7
-
1
4
3
5
1432
Fig
u
r
e
3
.
Mo
n
th
l
y
p
atter
n
o
f
f
i
r
e
in
cid
en
ts
i
n
L
a
g
u
n
a
Fig
u
r
e
4.
Dail
y
p
atter
n
o
f
f
ir
e
in
cid
en
t
s
i
n
L
a
g
u
n
a
Fig
u
r
e
5
.
T
im
e
p
atter
n
o
f
f
ir
e
i
n
cid
en
t
s
in
L
a
g
u
n
a
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
F
ir
e
in
cid
en
ts
visu
a
liz
a
tio
n
a
n
d
p
a
tter
n
r
ec
o
g
n
itio
n
u
s
in
g
m
a
ch
in
e
lea
r
n
in
g
…
(
Jo
n
a
r
d
o
R
.
A
s
o
r
)
1433
As
F
ig
u
r
e
6
s
h
o
w
s
,
it
is
s
tated
th
at
th
e
s
ix
citie
s
in
L
a
g
u
n
a
w
h
ic
h
ar
e
B
iñ
an
,
C
ab
u
y
ao
,
C
a
la
m
b
a,
San
P
ab
lo
,
San
P
ed
r
o
an
d
Sta.
R
o
s
a
ar
e
m
o
r
e
lik
el
y
to
h
a
v
e
ca
s
es
o
f
f
ir
e
in
cid
en
t
s
b
ec
au
s
e
o
f
s
e
v
er
e
p
o
p
u
latio
n
s
in
th
ese
ci
ties
.
Am
o
n
g
all
o
f
t
h
e
s
ix
citie
s
,
C
ala
m
b
a
C
it
y
h
as
r
ec
o
r
d
ed
s
ev
e
r
al
in
cid
en
t
s
in
2
0
1
4
to
2
0
1
8
.
Ho
w
e
v
er
,
th
er
e
ar
e
o
n
l
y
m
i
n
o
r
ca
s
es in
t
h
e
t
w
en
t
y
-
f
o
u
r
r
e
m
ai
n
i
n
g
m
u
n
icip
alities
i
n
th
e
p
r
o
v
i
n
ce
o
f
L
ag
u
n
a.
Fig
u
r
e
6.
Su
m
m
ar
y
o
f
f
ir
e
in
ci
d
en
ts
i
n
L
a
g
u
n
a
p
er
m
u
n
icip
al
it
y
4.
CO
NCLU
SI
O
N
Am
o
n
g
all
t
h
e
m
ac
h
i
n
e
lear
n
i
n
g
al
g
o
r
ith
m
s
u
s
ed
in
t
h
is
s
t
u
d
y
,
th
e
R
NN
i
s
n
o
ticed
to
p
o
s
s
e
s
s
a
b
etter
an
d
p
r
ec
is
e
m
o
d
el.
T
h
e
ev
alu
a
tio
n
o
f
th
e
R
NN
i
m
p
lies
i
n
d
if
f
er
en
t
p
ar
am
eter
s
an
d
d
is
p
la
y
s
an
au
s
p
icio
u
s
r
esu
lt
ch
o
o
s
in
g
th
e
lab
el
o
f
alar
m
le
v
els.
I
t
is
clea
r
th
at
t
h
e
u
s
e
o
f
t
h
e
alg
o
r
ith
m
p
r
o
v
id
es
a
q
u
alit
y
p
atter
n
in
p
r
ed
ictin
g
f
ir
e
i
n
cid
en
t
s
i
n
t
h
e
P
r
o
v
in
ce
o
f
L
a
g
u
n
a.
T
h
er
ef
o
r
e,
r
ec
u
r
r
e
n
t
n
eu
r
al
n
et
w
o
r
k
ca
n
b
e
u
s
e
d
in
d
ev
elo
p
in
g
a
n
ar
tif
icial
in
te
lli
g
en
ce
m
o
d
el
t
h
at
is
ca
p
ab
le
o
f
lear
n
i
n
g
p
atter
n
s
o
n
h
o
w
f
ir
e
o
cc
u
r
r
ed
in
t
h
e
p
r
o
v
in
ce
o
f
L
a
g
u
n
a.
B
ased
o
n
th
e
d
ata
g
ath
er
ed
f
r
o
m
th
e
B
FP
R
e
g
io
n
al
O
f
f
ice
R
eg
io
n
I
V
-
A
,
2
0
1
4
is
lis
ted
as
th
e
m
o
s
t
tr
ag
ic
y
ea
r
in
ter
m
s
o
f
f
ir
e
o
cc
u
r
r
en
ce
s
.
Al
s
o
,
it
is
n
o
ticed
th
at
th
e
m
o
n
t
h
o
f
Ma
r
ch
an
d
A
p
r
il
ar
e
th
e
t
w
o
v
u
l
n
er
ab
le
m
o
n
t
h
s
in
f
ir
e
i
n
cid
en
t
s
.
L
i
k
e
w
i
s
e,
Su
n
d
a
y
s
,
o
f
all
d
a
y
s
h
as
r
ec
o
r
d
ed
th
e
g
r
ea
test
n
u
m
b
er
o
f
f
ir
es
in
th
e
p
r
o
v
in
ce
o
f
L
a
g
u
n
a,
m
o
s
tl
y
o
cc
u
r
r
in
g
b
etw
ee
n
2
:0
0
an
d
3
:0
0
in
th
e
af
te
r
n
o
o
n
.
Mo
r
eo
v
er
,
th
e
cities
o
f
L
a
g
u
n
a
ar
e
f
o
u
n
d
to
h
av
e
n
u
m
er
o
u
s
co
u
n
ts
o
f
f
ir
e
in
cid
en
t
s
,
in
p
ar
ticu
lar
,
a
m
o
n
g
th
e
s
e
cities,
C
ala
m
b
a
C
it
y
h
as
t
h
e
h
i
g
h
e
s
t
f
ir
e
in
cid
en
t
s
r
ec
o
r
d
ed
.
T
h
u
s
,
m
o
s
t o
f
th
e
f
ir
e
in
cid
e
n
ts
i
n
v
o
lv
ed
is
g
r
as
s
f
ir
e
f
o
llo
w
ed
b
y
r
es
id
en
tial a
r
ea
s
.
RE
F
E
R
E
NC
E
S
[1
]
S
.
L
e
e
,
C.
W
u
,
a
n
d
K.
H
u
n
g
,
“
A
stu
d
y
o
n
f
ire
risk
s
to
f
iref
i
g
h
ters
in
t
h
e
b
u
il
d
i
n
g
w
it
h
p
h
o
t
o
v
o
lt
a
ic
s
y
ste
m
,
”
2
0
1
7
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
Ap
p
li
e
d
S
y
ste
m
In
n
o
v
a
ti
o
n
(
ICAS
I)
,
2
0
1
7
,
p
p
.
1
1
7
4
-
1
1
7
7
,
d
o
i:
1
0
.
1
1
0
9
/ICA
S
I.
2
0
1
7
.
7
9
8
8
5
0
0
.
[2
]
F
.
Jo
h
n
sto
n
,
e
t
a
l
,
“
Esti
m
a
ted
g
l
o
b
a
l
m
o
rtalit
y
a
tt
rib
u
tab
le
to
sm
o
k
e
f
ro
m
lan
d
sc
a
p
e
f
ires
,
”
En
v
ir
o
n
me
n
t
a
l
He
a
lt
h
Per
sp
e
c
ti
v
e
,
v
o
l.
1
2
0
,
n
o
.
5
,
p
p
.
6
9
5
-
7
0
1
,
M
a
y
2
0
1
2
,
d
o
i
:
1
0
.
1
2
8
9
/
e
h
p
.
1
1
0
4
4
2
2
.
[3
]
Ho
lb
o
rn
,
No
la
n
,
a
n
d
G
o
lt
,
“
A
n
a
n
a
ly
sis
o
f
fa
tal
u
n
in
ten
t
io
n
a
l
d
w
e
ll
in
g
f
ires
in
v
e
stig
a
ted
b
y
L
o
n
d
o
n
F
ire
Brig
a
d
e
”
,
Fi
re
S
a
fety
J
o
u
rn
a
l,
v
o
l
.
3
8
,
p
p
.
1
-
42
,
F
e
b
.
F
e
b
.
2
0
1
5
,
d
o
i:
1
0
.
1
0
1
6
/S
0
3
7
9
-
7
1
1
2
(
0
2
)
0
0
0
4
9
-
8.
[4
]
Bru
sh
li
n
k
y
,
A
h
re
n
s,
S
o
k
o
lo
v
,
a
n
d
W
a
g
n
e
r,
“
W
o
rld
F
ire
S
tatisti
c
s
2
0
1
5
,”
I
n
ter
n
a
ti
o
n
a
l
Asso
c
ia
ti
o
n
o
f
F
ire
a
n
d
Res
c
u
e
S
e
rv
ice
s
,
2
0
1
5
.
[5
]
A
.
Ho
u
se
r,
B.
Ja
c
k
so
n
,
J.
Ba
rti
s
,
a
n
d
D.
P
e
ters
o
n
,
“
Em
e
rg
e
n
c
y
Re
sp
o
n
d
e
r
In
ju
ries
a
n
d
F
a
talit
ies
,
in
N
a
ti
o
n
a
l
P
e
rso
n
a
l
P
r
o
tec
ti
v
e
T
e
c
h
n
o
lo
g
y
L
a
b
o
ra
to
ry
,”
S
a
n
t
a
M
o
n
ica
,
C
A:
RA
ND
Co
r
p
o
ra
ti
o
n
,
2
0
0
4
.
[
O
n
li
n
e
].
Av
a
il
a
b
le:
h
tt
p
s://
w
ww
.
ra
n
d
.
o
rg
/p
u
b
s/
tec
h
n
ica
l_
re
p
o
rts/T
R1
0
0
.
h
t
m
l.
A
lso
a
v
a
il
a
b
le i
n
p
ri
n
t
f
o
rm
.
[6
]
A
.
Ra
m
o
s,
“
Ru
ra
l
a
n
d
In
-
b
e
tw
e
e
n
”
,
Ja
n
.
2
0
1
5
.
[
O
n
li
n
e
]
.
A
v
a
il
a
b
le:
h
tt
p
s:/
/www
.
f
ire
f
ig
h
tern
a
ti
o
n
.
c
o
m
[7
]
M
.
Y.
In
g
a
l,
R.
L
.
T
.
T
o
len
ti
n
o
,
M
.
J.
V
a
len
c
ia,
F
.
F
.
Ba
lah
a
d
ia
,
a
n
d
A
.
R.
Ca
b
a
ll
e
ro
,
“
F
ire
in
c
id
e
n
ts
m
a
n
a
g
e
m
e
n
t
s
y
ste
m
in
th
e
c
it
y
o
f
M
a
n
il
a
th
ro
u
g
h
g
e
o
-
m
a
p
p
in
g
,
”
2
0
1
6
IE
EE
R
e
g
io
n
1
0
S
y
mp
o
si
u
m
(
T
ENS
Y
M
P)
,
2
0
1
6
,
p
p
.
3
9
9
-
4
0
3
,
d
o
i:
1
0
.
1
1
0
9
/T
ENCON
S
p
rin
g
.
2
0
1
6
.
7
5
1
9
4
4
0
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
22
,
No
.
3
,
J
u
n
e
2
0
2
1
:
1
4
2
7
-
1
4
3
5
1434
[8
]
C.
S
iv
a
,
“
T
h
e
Diff
e
r
e
n
c
e
o
f
M
a
c
h
in
e
L
e
a
rn
in
g
a
n
d
P
a
tt
e
r
n
Re
c
o
g
n
it
io
n
,
”
No
v
.
2
0
1
8
.
[
O
n
li
n
e
]
.
A
v
a
il
a
b
le:
h
tt
p
s:/
/d
z
o
n
e
.
c
o
m
/article
s/
m
a
c
h
in
e
-
lea
rn
in
g
-
a
n
d
-
p
a
tt
e
rn
-
re
c
o
g
n
it
io
n
[9
]
S
.
T
h
e
o
d
o
rid
is
a
n
d
K.
Ko
u
tro
u
m
b
a
s,
“
P
a
tt
e
rn
Re
c
o
g
n
it
i
o
n
2
n
d
E
d
it
io
n
,”
Gr
e
e
c
e
:
Aca
d
e
mic
Pre
ss
;
An
Im
p
rin
t
o
f
El
se
v
ier
,
2
0
1
4
.
[1
0
]
T
.
M
.
Co
v
e
r,
“
G
e
o
m
e
tri
c
a
l
a
n
d
S
tatisti
c
a
l
P
r
o
p
e
rti
e
s
o
f
S
y
ste
m
s
o
f
L
in
e
a
r
In
e
q
u
a
li
ti
e
s
w
it
h
A
p
p
li
c
a
ti
o
n
s
i
n
P
a
tt
e
r
n
Re
c
o
g
n
it
i
o
n
,
”
IEE
E
T
r
a
n
s
a
c
ti
o
n
s
o
n
El
e
c
tro
n
ic
Co
m
p
u
ter
s
,
v
o
l.
EC
-
1
4
,
n
o
.
3
,
p
p
.
3
2
6
-
3
3
4
,
Ju
n
e
1
9
6
5
,
d
o
i:
1
0
.
1
1
0
9
/
P
G
EC.
1
9
6
5
.
2
6
4
1
3
7
.
[1
1
]
M
.
Y.
Or
o
n
g
,
A
.
M
.
S
iso
n
,
a
n
d
A
.
A
.
He
rn
a
n
d
e
z
,
“
M
it
ig
a
ti
n
g
v
u
ln
e
ra
b
il
it
ies
t
h
ro
u
g
h
f
o
re
c
a
stin
g
a
n
d
c
rim
e
tren
d
a
n
a
ly
sis,
”
2
0
1
8
5
th
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Bu
si
n
e
ss
a
n
d
I
n
d
u
stria
l
Res
e
a
rc
h
(
ICBIR
)
,
M
a
y
2
0
1
8
,
p
p
.
5
7
-
6
2
,
d
o
i:
1
0
.
1
1
0
9
/ICBIR.
2
0
1
8
.
8
3
9
1
1
6
6
.
[1
2
]
X
.
L
a
g
o
rc
e
,
G
.
Orc
h
a
rd
,
F
.
G
a
ll
u
p
p
i,
B.
E.
S
h
i
,
a
n
d
R.
B
.
Be
n
o
s
m
a
n
,
“
HO
T
S
:
A
h
iera
rc
h
y
o
f
e
v
e
n
t
-
b
a
se
d
ti
m
e
-
su
rf
a
c
e
s
f
o
r
p
a
tt
e
rn
re
c
o
g
n
it
io
n
,
”
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
Pa
tt
e
rn
A
n
a
lys
is
a
n
d
M
a
c
h
in
e
In
tell
ig
e
n
c
e
,
v
o
l.
3
9
,
n
o
.
7
,
p
p
.
1
3
4
6
-
1
3
5
9
,
Ju
l.
2
0
1
7
,
d
o
i:
1
0
.
1
1
0
9
/T
P
A
M
I.
2
0
1
6
.
2
5
7
4
7
0
7
.
[1
3
]
J.
B.
L
a
n
i,
“
W
h
a
t
is L
o
g
isti
c
R
e
g
r
e
ss
io
n
,
”
Ju
n
.
2
0
1
5
.
[
O
n
li
n
e
]
.
A
v
a
i
lab
le:
h
tt
p
s://
w
ww
.
sta
ti
stics
so
lu
t
i
o
n
s.c
o
m
/w
h
a
t
-
is
-
lo
g
isti
c
-
re
g
re
ss
io
n
/
[1
4
]
G
.
Am
a
tu
ll
i,
M
.
J.
R
o
d
rig
u
e
s,
M
.
T
ro
m
b
e
tt
i
,
a
n
d
R.
L
o
v
re
g
li
o
,
“
A
ss
e
ss
in
g
L
o
n
g
-
ter
m
F
ire
Risk
a
t
L
o
c
a
l
S
c
a
le
b
y
M
e
a
n
s
o
f
De
c
isio
n
T
re
e
T
e
c
h
n
iq
u
e
,”
J
o
u
rn
a
l
o
f
Ge
o
p
h
y
sic
a
l
Res
e
a
rc
h
At
mo
sp
h
e
re
s
,
p
p
.
6
5
-
6
7
,
De
c
.
2
0
1
6
,
d
o
i:
1
0
.
1
0
2
9
/2
0
0
5
JG
0
0
0
1
3
3
.
[1
5
]
J.
M
.
S
a
v
e
lan
d
a
n
d
L
.
F
.
Ne
u
e
n
sc
h
w
a
n
d
e
r,
“
A
S
ig
n
a
l
De
tec
ti
o
n
F
ra
m
e
w
o
rk
to
Ev
a
lu
a
te
M
o
d
e
ls
o
f
T
re
e
M
o
rtalit
y
F
o
ll
o
w
in
g
F
ire
Da
m
a
g
e
,”
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
F
o
re
st
S
c
ien
c
e
,
p
p
.
9
8
-
1
0
0
,
2
0
1
7
,
d
o
i
:
1
0
.
1
0
9
3
/f
o
re
stsc
ien
c
e
/3
6
.
1
.
6
6
.
[1
6
]
J.
R.
A
so
r
a
n
d
M
.
A
.
T
.
S
u
b
io
n
,
“
RES
EA
RCH+
+
:
A
n
a
c
a
d
e
m
ic
s
o
c
ial
n
e
tw
o
rk
in
g
re
se
a
r
c
h
c
o
m
m
u
n
it
y
p
o
rtal
f
o
r
p
ro
f
il
in
g
a
n
d
e
x
p
e
rti
se
c
las
sif
ica
ti
o
n
,
”
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
RIT
I)
,
2
0
1
8
,
p
p
.
4
7
0
-
4
7
5
,
d
o
i:
1
0
.
1
1
0
9
/I
S
RI
T
I.
2
0
1
8
.
8
8
6
4
4
8
3
.
[1
7
]
G
.
M
.
B.
Ca
ted
ril
la
a
n
d
J.
R.
A
so
r,
“
P
a
tt
e
r
n
Re
c
o
g
n
it
io
n
f
ro
m
Ra
d
io
lo
g
y
Re
p
o
rts
to
w
a
rd
s
P
re
d
ictiv
e
L
u
n
g
Dise
a
s
e
M
a
n
if
e
sta
ti
o
n
in
M
u
n
ici
p
a
l
S
e
tt
i
n
g
s
,”
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
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
RIT
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
T
I.
2
0
1
8
.
8
8
6
4
2
4
1
.
[1
8
]
J.
R.
A
so
r,
G
.
M
.
B.
Ca
ted
ril
la,
a
n
d
Je
f
f
e
r
so
n
L
.
L
e
rio
s,
“
Us
a
g
e
o
f
c
las
si
f
ica
ti
o
n
a
lg
o
rit
h
m
f
o
r
e
x
trac
ti
n
g
k
n
o
w
led
g
e
in
c
h
o
les
tero
l
re
p
o
r
t
to
w
a
rd
s n
o
n
-
c
o
m
m
u
n
ica
b
le d
ise
a
se
a
n
a
l
y
sis,”
J
o
u
rn
a
l
o
f
Ad
v
a
n
c
e
s in
In
fo
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
v
o
l.
1
1
,
n
o
.
4
,
p
p
.
2
6
5
-
2
7
0
,
No
v
.
2
0
2
0
,
d
o
i:
1
0
.
1
2
7
2
0
/j
a
it
.
1
1
.
4
.
2
6
5
-
2
7
0
.
[1
9
]
J.
R.
A
so
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
L
o
s
Ba
ñ
o
s,
L
a
g
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
Co
n
fer
e
n
c
e
o
n
I
n
fo
rm
a
t
io
n
a
n
d
Co
mm
u
n
ica
ti
o
n
s T
e
c
h
n
o
l
o
g
y
(
ICOIACT
)
,
2
0
1
8
,
p
p
.
9
6
-
1
0
1
,
d
o
i:
1
0
.
1
2
7
2
0
/
jait.
1
1
.
4
.
2
6
5
-
2
7
0
.
[2
0
]
J.
R.
A
so
r
a
n
d
S
.
B.
S
a
p
in
,
“
Im
p
lem
e
n
tatio
n
o
f
P
re
d
ictiv
e
Crim
e
A
n
a
l
y
ti
c
s
in
M
u
n
ici
p
a
l
Crim
e
M
a
n
a
g
e
m
e
n
t
S
y
ste
m
in
Ca
lau
a
n
,
L
a
g
u
n
a
,
P
h
il
ip
p
in
e
s
,”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
A
d
v
a
n
c
e
d
T
re
n
d
s i
n
Co
mp
u
ter
S
c
ien
c
e
a
n
d
En
g
in
e
e
rin
g
,
v
o
l.
9
,
n
o
.
1
.
3
,
p
p
.
1
50
-
1
5
7
,
Ju
n
.
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
.
[2
1
]
J.
L
e
rio
s
a
n
d
M
.
V
il
laric
a
,
“
P
a
tt
e
rn
Ex
trac
ti
o
n
o
f
W
a
ter
Qu
a
li
t
y
P
re
d
ictio
n
Us
i
n
g
M
a
c
h
in
e
L
e
a
rn
in
g
A
l
g
o
rit
h
m
s
o
f
W
a
ter
Re
se
r
v
o
ir
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
M
e
c
h
a
n
ic
a
l
En
g
in
e
e
rin
g
a
n
d
R
o
b
o
ti
c
s
Res
e
a
r
c
h
,
v
o
l
.
8
,
n
o
.
6
,
p
p
.
9
9
2
-
9
9
7
,
2
0
1
9
,
d
o
i:
1
0
.
1
8
1
7
8
/i
jm
e
rr.
[2
2
]
N.
Ch
a
w
la,
K.
Bo
wy
e
r,
L
.
Ha
ll
,
a
n
d
P
.
Ke
g
e
lm
e
y
e
r,
“
S
M
O
T
E:
S
y
n
t
h
e
ti
c
m
in
o
rit
y
o
v
e
r
-
s
a
m
p
li
n
g
tec
h
n
iq
u
e
”
,
J
o
u
rn
a
l
o
f
Arti
f
icia
l
I
n
telli
g
e
n
c
e
Res
e
a
rc
h
,
v
o
l.
1
6
,
n
o
.
1
,
p
p
.
3
2
1
-
3
2
4
,
Ju
n
.
2
0
0
2
,
d
o
i:
1
0
.
1
6
1
3
/
jair.
9
5
3
.
[2
3
]
A
.
M
ish
ra
,
“
M
e
tri
c
s
to
e
v
a
l
u
a
te
y
o
u
r
m
a
c
h
in
e
lea
rn
in
g
a
lg
o
rit
h
m
,
”
F
e
b
.
2
0
1
8
.
[
O
n
li
n
e
]
.
A
v
a
il
a
b
le:
h
tt
p
s:/
/t
o
w
a
rd
sd
a
tas
c
ien
c
e
.
c
o
m
/
m
e
tri
c
s
-
to
-
e
v
a
lu
a
te
-
y
o
u
r
-
m
a
c
h
in
e
-
lea
rn
in
g
-
a
lg
o
rit
h
m
-
f
1
0
b
a
6
e
3
8
2
3
4
[2
4
]
G
.
I.
W
e
b
b
,
“
A
l
g
o
rit
h
m
e
v
a
lu
a
ti
o
n
,
i
n
e
n
c
y
c
lo
p
e
d
ia o
f
m
a
c
h
in
e
lea
rn
in
g
,
”
B
o
sto
n
,
S
p
rin
g
e
r
,
2
0
1
5
,
p
p
.
4
5
.
[2
5
]
F
.
F
.
Ba
lah
a
d
ia,
J.
R
.
A
so
r,
G
.
M
.
B.
Ca
ted
ril
la,
M
.
V
il
laric
a
,
a
n
d
J.
M
.
Ca
b
ie
n
te,
“
In
telli
g
e
n
t
I
n
v
e
stig
a
ti
o
n
o
n
Crim
e
In
c
id
e
n
t
Re
p
o
rts
in
th
e
P
ro
v
in
c
e
o
f
L
a
g
u
n
a
th
ro
u
g
h
P
re
d
ictiv
e
M
o
d
e
l
De
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
E
n
g
i
n
e
e
rin
g
,
v
o
l.
9
,
n
o
.
1
.
3
,
p
p
.
1
3
9
-
1
4
4
,
J
u
n
.
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
.
[2
6
]
M
.
Niw
a
ri
y
a
,
A
.
Ra
jp
u
t
,
a
n
d
S
.
J
a
lo
re
e
,
“
Da
ta
M
in
in
g
A
p
p
ro
a
c
h
f
o
r
Dia
b
e
tes
P
re
d
icti
o
n
u
si
n
g
B
P
S
O,
S
VM,
KN
N
a
n
d
Na
ïv
e
Ba
y
e
s
Cla
ss
i
f
iers
,”
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
C
o
mp
u
ter
S
c
ien
c
e
a
n
d
E
n
g
i
n
e
e
rin
g
,
v
o
l.
9
,
n
o
.
1
.
5
,
p
p
.
2
8
6
-
2
9
3
,
S
e
p
t.
2
0
2
0
,
d
o
i:
1
0
.
3
0
5
3
4
/
ij
a
tcs
e
/2
0
2
0
/
4
1
9
1
.
5
2
0
2
0
.
[2
7
]
E.
R.
Bo
n
d
o
c
,
e
t
a
l.
,
“
A
n
in
telli
g
e
n
t
r
o
a
d
traff
ic
in
f
o
rm
a
ti
o
n
sy
ste
m
u
sin
g
tex
t
a
n
a
ly
sis
in
t
h
e
m
o
st
c
o
n
g
e
ste
d
ro
a
d
s
in
M
e
tr
o
M
a
n
il
a
,”
2
0
1
8
IEE
E
1
0
th
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
Hu
m
a
n
o
id
,
Na
n
o
tec
h
n
o
lo
g
y
,
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
l
o
g
y
,
C
o
mm
u
n
ica
ti
o
n
a
n
d
Co
n
tro
l,
En
v
iro
n
me
n
t
a
n
d
M
a
n
a
g
e
me
n
t
(
HNICEM
)
,
2
0
1
8
,
p
p
.
1
-
6
,
d
o
i:
1
0
.
1
1
0
9
/HNICE
M
.
2
0
1
8
.
8
6
6
6
4
1
6
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
F
ir
e
in
cid
en
ts
visu
a
liz
a
tio
n
a
n
d
p
a
tter
n
r
ec
o
g
n
itio
n
u
s
in
g
m
a
ch
in
e
lea
r
n
in
g
…
(
Jo
n
a
r
d
o
R
.
A
s
o
r
)
1435
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
J
o
n
a
r
d
o
R
.
As
o
r
w
a
s
b
o
rn
i
n
L
o
s
Ba
ñ
o
s,
L
a
g
u
n
a
,
P
h
il
ip
p
i
n
e
s
o
n
Ju
n
e
1
2
,
1
9
9
0
.
He
g
ra
d
u
a
ted
a
t
t
h
e
L
a
g
u
n
a
S
tate
P
o
ly
tec
h
n
ic
Un
iv
e
rsit
y
,
L
o
s
Ba
ñ
o
s
c
a
m
p
u
s
w
it
h
th
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.
A
so
r
f
in
ish
e
d
h
is
m
a
ste
r
in
in
f
o
rm
a
ti
o
n
tec
h
n
o
lo
g
y
a
t
th
e
T
e
c
h
n
o
lo
g
ica
l
In
sti
tu
te
o
f
th
e
P
h
il
i
p
p
i
n
e
s
,
M
a
n
i
la,
o
n
Oc
to
b
e
r
2
0
1
8
.
He
is
c
u
rre
n
tl
y
w
o
rk
in
g
a
s
Co
ll
e
g
e
In
str
u
c
to
r
a
t
th
e
L
a
g
u
n
a
S
tate
P
o
ly
tec
h
n
ic
Un
iv
e
rsit
y
,
L
o
s
Ba
ñ
o
s
Ca
m
p
u
s,
M
a
li
n
ta,
L
o
s
Ba
ñ
o
s,
L
a
g
u
n
a
,
P
h
il
i
p
p
i
n
e
s.
His
re
se
a
rc
h
st
u
d
y
f
o
c
u
se
s
o
n
th
e
o
p
ti
m
iza
ti
o
n
a
n
d
u
sa
g
e
o
f
m
a
c
h
in
e
lea
rn
in
g
a
lg
o
rit
h
m
a
n
d
k
n
o
w
led
g
e
d
isc
o
v
e
r
y
in
d
a
tab
a
se
s.
J
e
ffe
r
so
n
L.
Le
r
io
s
is
a
g
ra
d
u
a
te o
f
Do
c
to
r
o
f
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
l
o
g
y
a
t
th
e
T
e
c
h
n
o
lo
g
ica
l
In
stit
u
te
o
f
t
h
e
P
h
il
i
p
p
i
n
e
s
M
a
n
il
a
.
Cu
rre
n
t
ly
,
h
e
is
a
n
A
ss
istan
t
P
ro
f
e
ss
o
r
II
a
t
t
h
e
Co
ll
e
g
e
o
f
Co
m
p
u
ter
S
tu
d
ies
,
L
a
g
u
n
a
S
tat
e
P
o
ly
tec
h
n
ic
Un
iv
e
rsity
,
L
o
s
Ba
ñ
o
s
Ca
m
p
u
s.
His
re
s
e
a
rc
h
in
tere
st
is
in
th
e
f
ield
o
f
e
n
v
iro
n
m
e
n
tal
m
o
d
e
li
n
g
,
in
telli
g
e
n
t
sy
ste
m
s,
in
f
o
rm
a
ti
o
n
tec
h
n
o
l
o
g
y
,
d
a
ta
m
in
in
g
,
a
n
d
d
a
ta
a
n
a
ly
ti
c
s.
Dr
.
S
h
e
r
w
in
B.
S
a
p
in
is
c
u
rre
n
tl
y
th
e
Ch
a
irp
e
rso
n
o
f
th
e
Cu
r
ricu
lu
m
a
n
d
In
str
u
c
ti
o
n
De
v
e
lo
p
m
e
n
t
a
n
d
th
e
Co
o
rd
i
n
a
to
r
f
o
r
L
o
c
a
l
G
o
v
e
rn
m
e
n
t
Un
it
o
f
L
a
g
u
n
a
S
tate
P
o
ly
tec
h
n
ic
Un
iv
e
rsit
y
-
L
o
s
Ba
ñ
o
s
Ca
m
p
u
s.
His
re
se
a
rc
h
in
tere
sts
a
re
i
n
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
lo
g
y
Ed
u
c
a
ti
o
n
,
M
a
th
e
m
a
ti
c
s
Ed
u
c
a
ti
o
n
,
a
n
d
E
d
u
c
a
ti
o
n
a
l
M
a
n
a
g
e
m
e
n
t.
He
a
u
t
h
o
re
d
v
a
rio
u
s
re
se
a
rc
h
stu
d
ies
p
u
b
li
sh
e
d
i
n
d
if
f
e
r
e
n
t
in
tern
a
ti
o
n
a
l
jo
u
rn
a
ls.
J
o
c
e
ly
n
O
.
Pa
d
a
ll
a
n
is
a
g
ra
d
u
a
te
o
f
M
a
ste
r
o
f
A
rts
in
Ed
u
c
a
ti
o
n
m
a
jo
r
in
Ed
u
c
a
ti
o
n
a
l
M
a
n
a
g
e
m
e
n
t
a
t
th
e
L
a
g
u
n
a
S
tate
P
o
ly
tec
h
n
ic
Un
iv
e
rsity
,
L
o
s
Ba
ñ
o
s
.
C
u
rre
n
tl
y
,
s
h
e
is
a
n
A
s
sista
n
t
P
r
o
f
e
ss
o
r
II
a
t
th
e
C
o
ll
e
g
e
o
f
Co
m
p
u
ter
S
tu
d
ies
,
L
a
g
u
n
a
S
tate
P
o
ly
tec
h
n
ic
Un
iv
e
rsit
y
,
L
o
s Ba
ñ
o
s Ca
m
p
u
s
a
n
d
a
f
f
il
iate
d
a
s a
d
v
ise
r
o
f
CCS
-
S
tu
d
e
n
t
c
o
u
n
c
il
.
H res
e
a
rc
h
in
tere
st i
s in
th
e
f
ield
o
f
in
f
o
rm
a
ti
o
n
tec
h
n
o
l
o
g
y
,
so
f
t
wa
re
d
e
v
e
lo
p
m
e
n
t
a
n
d
d
a
ta an
a
ly
ti
c
s.
Dr
.
Ch
e
ste
r
Ale
x
is
C.
B
u
a
m
a
is
a
Co
ll
e
g
e
P
ro
f
e
ss
o
r
a
t
L
a
g
u
n
a
S
ta
te
P
o
ly
tec
h
n
ic
Un
iv
e
rsity
u
n
d
e
r
th
e
F
a
c
u
lt
y
o
f
Co
ll
e
g
e
o
f
A
rts
a
n
d
S
c
ien
c
e
s
.
A
Co
n
su
lt
a
n
t
o
f
th
e
De
p
a
rtm
e
n
t
o
f
Ed
u
c
a
ti
o
n
Ce
n
tral
Of
f
ice
f
o
r
L
e
a
r
n
in
g
A
ss
e
ss
m
e
n
t
a
n
d
Na
ti
o
n
a
l
T
ra
in
e
r
o
f
th
e
Co
m
m
issio
n
o
n
Hig
h
e
r
Ed
u
c
a
ti
o
n
f
o
r
G
e
n
e
ra
l
Ed
u
c
a
ti
o
n
Co
u
rse
s.
He
is
a
lso
a
m
e
m
b
e
r
o
f
lo
c
a
l
a
n
d
in
tern
a
ti
o
n
a
l
o
rg
a
n
iza
ti
o
n
s:
h
e
is
a
F
e
ll
o
w
a
n
d
S
e
n
i
o
r
M
e
m
b
e
r
o
f
th
e
Ro
y
a
l
In
stit
u
te
o
f
M
a
n
a
g
e
m
e
n
t
a
n
d
th
e
Ro
y
a
l
In
sti
tu
te
o
f
Ed
u
c
a
to
rs,
S
i
n
g
a
p
o
re
,
Re
a
d
in
g
A
ss
o
c
iatio
n
o
f
t
h
e
P
h
il
i
p
p
i
n
e
s,
a
n
d
In
ter
n
a
ti
o
n
a
l
En
g
li
sh
L
e
a
rn
e
rs
T
ra
in
in
g
In
sti
tu
te.
He
h
a
s
a
M
a
ste
r'
s
d
e
g
re
e
in
M
a
n
a
g
e
m
e
n
t
m
a
jo
r
in
P
u
b
li
c
A
d
m
in
istratio
n
a
n
d
a
Ba
c
h
e
lo
r'
s
d
e
g
re
e
in
Jo
u
rn
a
li
sm
.
He
w
a
s
c
o
n
f
e
rre
d
a
Do
c
to
ra
te
De
g
re
e
in
P
h
il
o
s
o
p
h
y
m
a
jo
r
in
P
u
b
li
c
A
d
m
in
istratio
n
i
n
2
0
1
6
a
n
d
g
ra
d
u
a
te
d
w
it
h
a
Do
c
to
ra
te
De
g
r
e
e
in
P
h
il
o
s
o
p
h
y
m
a
jo
r
in
Bu
sin
e
ss
M
a
n
a
g
e
m
e
n
t
in
2
0
1
8
.
His res
e
a
rc
h
in
tere
st i
s in
S
o
c
ial
S
c
ien
c
e
,
a
n
d
B
u
sin
e
ss
M
a
n
a
g
e
m
e
n
t
.
Evaluation Warning : The document was created with Spire.PDF for Python.