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.
3
7
,
No
.
1
,
J
an
u
ar
y
20
2
5
,
p
p
.
54
0
~
55
0
I
SS
N:
2
502
-
4
7
52
,
DOI
: 1
0
.
1
1
5
9
1
/ijee
cs
.v
3
7
.
i
1
.
pp
54
0
-
55
0
540
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs
.
ia
esco
r
e.
co
m
Cla
ss
ificatio
n of
wea
ther
co
nditio
ns ba
sed o
n
a
uto
ma
tic
wea
th
er
sta
tion da
ta using
a
multi
-
la
y
er per
ceptron
n
eura
l ne
twork
M
uh
a
m
m
a
d Ar
is
t
o
I
nd
ra
j
a
y
a
,
T
a
n Sury
a
ni So
llu
,
M
er
y
Su
bito
,
Yuli A
s
m
i R
a
hm
a
n,
E
rwin
Ar
dia
s
Sa
pu
t
ra
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
i
c
a
l
En
g
i
n
e
e
r
i
n
g
,
F
a
c
u
l
t
y
o
f
En
g
i
n
e
e
r
i
n
g
,
U
n
i
v
e
r
s
i
t
y
o
f
Ta
d
u
l
a
k
o
,
P
a
l
u
,
I
n
d
o
n
e
s
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
n
30
,
2
0
2
4
R
ev
is
ed
Sep
11
,
2
0
2
4
Acc
ep
ted
Sep
29
,
2
0
2
4
Wea
th
e
r
is
o
n
e
o
f
t
h
e
imp
o
r
tan
t
e
lem
e
n
ts
th
a
t
g
re
a
tl
y
d
e
term
in
e
s
h
u
m
a
n
a
c
ti
v
it
ies
,
e
sp
e
c
ially
th
o
se
re
late
d
to
e
c
o
n
o
m
ic
fa
c
to
rs.
Th
e
re
fo
re
,
u
n
d
e
rsta
n
d
i
n
g
we
a
th
e
r
c
o
n
d
it
io
n
s
u
sin
g
we
a
th
e
r
p
a
ra
m
e
ters
a
s
a
re
fe
re
n
c
e
is
imp
o
rtan
t
fo
r
h
u
m
a
n
li
fe
,
s
o
a
m
e
th
o
d
is
n
e
e
d
e
d
to
c
las
sify
we
a
th
e
r
acco
rd
in
g
to
it
s
c
a
teg
o
r
y
so
t
h
a
t
th
e
in
f
o
rm
a
ti
o
n
p
r
o
d
u
c
e
d
c
a
n
b
e
u
se
d
f
o
r
v
a
rio
u
s
n
e
e
d
s.
De
term
in
i
n
g
we
a
th
e
r
c
o
n
d
it
i
o
n
s
in
a
n
a
re
a
will
n
o
t
ru
n
we
l
l
with
o
u
t
a
re
li
a
b
le
m
e
th
o
d
th
a
t
c
a
n
a
n
a
ly
z
e
e
x
isti
n
g
we
a
th
e
r
p
a
ra
m
e
ters
.
Th
e
re
fo
re
,
in
th
is
st
u
d
y
,
t
h
e
we
a
th
e
r
c
o
n
d
it
io
n
c
las
sifica
ti
o
n
p
r
o
c
e
ss
wa
s
c
a
rried
o
u
t
u
si
n
g
th
e
m
u
l
ti
lay
e
r
p
e
rc
e
p
tro
n
a
lg
o
rit
h
m
,
a
t
y
p
e
o
f
n
e
u
ra
l
n
e
two
rk
(NN
)
a
lg
o
rit
h
m
.
All
d
a
ta
a
n
a
ly
z
e
d
we
re
we
a
th
e
r
p
a
ra
m
e
ter
d
a
ta
c
o
ll
e
c
ted
b
y
m
i
n
i
we
a
th
e
r
sta
ti
o
n
s
p
lac
e
d
o
n
lan
d
.
Th
e
we
a
th
e
r
p
a
ra
m
e
ters
u
se
d
we
re
tem
p
e
ra
tu
re
,
h
u
m
id
it
y
,
a
ir
p
re
ss
u
re
,
win
d
sp
e
e
d
,
d
e
w
p
o
in
t
,
win
d
c
h
il
l,
d
a
il
y
ra
in
fa
ll
,
s
o
lar
ra
d
iati
o
n
,
a
n
d
UV
in
d
e
x
.
T
h
is
stu
d
y
wa
s
c
o
n
d
u
c
ted
in
P
a
l
u
c
it
y
,
Ce
n
tral
S
u
law
e
si P
ro
v
in
c
e
,
I
n
d
o
n
e
sia
.
T
h
e
c
las
sifica
ti
o
n
p
r
o
c
e
ss
c
a
rried
o
u
t
b
y
th
e
m
u
lt
il
a
y
e
r
p
e
rc
e
p
tro
n
a
l
g
o
ri
th
m
wa
s
c
a
rried
o
u
t
o
n
th
e
Altair
AI
S
tu
d
io
a
p
p
li
c
a
ti
o
n
a
n
d
p
ro
d
u
c
e
d
a
n
a
c
c
u
ra
c
y
v
a
l
u
e
o
f
9
3
.
8
7
%
,
re
c
a
ll
o
f
9
2
.
3
3
%
,
a
n
d
p
re
c
isio
n
o
f
9
1
.
2
9
%
.
K
ey
w
o
r
d
s
:
Acc
u
r
ac
y
Altair
AI
s
tu
d
io
C
las
s
if
icatio
n
Mu
lti
-
lay
er
p
er
ce
p
tr
o
n
W
ea
th
er
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
:
Me
r
y
Su
b
ito
Dep
ar
tm
en
t o
f
E
lectr
ical
E
n
g
i
n
ee
r
in
g
,
Facu
lty
o
f
E
n
g
in
ee
r
in
g
,
Un
iv
er
s
ity
o
f
T
ad
u
la
k
o
So
ek
ar
n
o
-
Hatta
R
o
ad
Kilo
m
et
er
9
,
Palu
9
4
1
1
2
,
C
en
tr
al
Su
la
wesi,
I
n
d
o
n
esia
E
m
ail: m
er
y
.
s
u
b
ito
@
u
n
tad
.
ac
.
id
1.
I
NT
RO
D
UCT
I
O
N
W
ea
th
er
is
a
d
y
n
am
ic
asp
ec
t
o
f
th
e
E
ar
th
’
s
atm
o
s
p
h
er
e
th
at
ch
an
g
es
f
r
eq
u
e
n
tly
.
T
em
p
e
r
atu
r
e,
ai
r
p
r
ess
u
r
e,
h
u
m
id
ity
,
lig
h
t
in
te
n
s
ity
,
an
d
r
ain
f
all
all
h
av
e
a
n
i
m
p
ac
t
o
n
th
e
wea
th
er
in
a
g
iv
en
lo
ca
tio
n
.
W
ea
th
er
co
n
d
itio
n
s
g
r
ea
tly
d
eter
m
in
e
wh
eth
er
o
r
n
o
t
co
m
m
u
n
ity
ac
tiv
ities
r
u
n
s
m
o
o
th
ly
[
1
]
.
I
n
th
e
f
ield
o
f
tr
an
s
p
o
r
tatio
n
,
esp
ec
ially
av
ia
tio
n
an
d
s
ea
tr
an
s
p
o
r
tatio
n
,
wea
th
er
co
n
d
itio
n
s
ar
e
cr
itica
l
in
ter
m
s
o
f
s
af
ety
[
2
]
.
Ma
n
y
ac
cid
e
n
ts
,
esp
ec
ially
in
th
e
av
iatio
n
s
ec
to
r
,
ar
e
i
n
d
ir
ec
tly
ca
u
s
ed
b
y
th
e
in
f
l
u
e
n
ce
o
f
wea
th
er
,
s
o
wea
th
er
p
r
e
d
ictio
n
is
s
ig
n
if
ican
t
in
s
u
p
p
o
r
tin
g
th
e
tr
a
n
s
p
o
r
tatio
n
s
ec
to
r
,
esp
ec
iall
y
in
s
ea
an
d
air
tr
an
s
p
o
r
tatio
n
.
I
n
th
e
a
g
r
icu
l
tu
r
al
an
d
p
lan
tatio
n
s
ec
to
r
s
,
th
e
r
o
le
o
f
wea
th
er
i
n
d
eter
m
in
in
g
a
g
r
icu
ltu
r
a
l
p
r
o
d
u
ctio
n
r
esu
lts
is
h
u
g
e
[
3
]
,
[
4
]
.
W
h
eth
er
th
at
is
in
g
o
o
d
co
n
d
itio
n
will
en
co
u
r
a
g
e
m
a
x
im
u
m
ag
r
ic
u
ltu
r
al
p
r
o
d
u
ctio
n
an
d
p
r
o
v
id
e
lar
g
e
ec
o
n
o
m
ic
b
en
e
f
its
f
o
r
f
ar
m
er
s
[
5
]
,
[
6
]
.
On
th
e
o
th
er
h
a
n
d
,
ex
tr
em
e
wea
th
er
s
u
ch
as
lo
n
g
d
r
o
u
g
h
ts
an
d
e
x
tr
e
m
e
r
ain
s
will
ca
u
s
e
cr
o
p
f
a
ilu
r
es
wh
ich
h
av
e
im
p
licatio
n
s
f
o
r
a
s
ig
n
if
ican
t
r
ed
u
ctio
n
in
p
r
o
f
its
f
o
r
f
a
r
m
er
s
an
d
u
n
d
er
ce
r
tain
c
o
n
d
it
io
n
s
will
ca
u
s
e
s
ca
r
city
o
f
s
ev
er
al
ag
r
icu
ltu
r
al
co
m
m
o
d
ities
th
at
ar
e
n
ee
d
e
d
b
y
th
e
co
m
m
u
n
ity
.
T
h
er
ef
o
r
e,
th
e
ab
ilit
y
t
o
p
r
e
d
ict
we
ath
er
co
n
d
itio
n
s
is
ess
en
tial
in
an
ticip
atin
g
th
e
in
f
lu
en
ce
o
f
wea
t
h
e
r
o
n
th
e
ec
o
n
o
m
ic
ac
tiv
ities
o
f
a
r
eg
i
o
n
[
7
]
,
[
8
]
.
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:
2
5
0
2
-
4
7
52
C
la
s
s
i
fica
tio
n
o
f wea
th
er c
o
n
d
itio
n
s
b
a
s
ed
o
n
a
u
to
ma
tic
w
ea
th
er
…
(
Mu
h
a
mma
d
A
r
is
to
I
n
d
r
a
ja
ya
)
541
Data
m
in
in
g
is
a
p
r
o
ce
s
s
th
at
co
m
p
r
is
es
d
ata
co
llectin
g
an
d
th
e
ap
p
licatio
n
o
f
p
ast
d
ata
t
o
d
is
co
v
er
an
o
r
d
er
,
p
atter
n
,
o
r
r
elatio
n
s
h
ip
in
m
ass
iv
e
d
ata
[
9
]
.
D
ata
m
in
in
g
in
v
o
lv
es
f
o
u
r
d
is
cip
lin
es:
s
tatis
tic
s
,
v
is
u
aliza
tio
n
,
d
atab
ases
,
a
n
d
m
ac
h
in
e
lear
n
in
g
.
Ma
ch
in
e
l
ea
r
n
in
g
is
a
s
u
b
s
et
o
f
ar
tific
ial
in
tellig
en
ce
th
at
d
ea
ls
with
b
u
ild
in
g
p
r
o
g
r
am
m
in
g
ap
p
r
o
ac
h
es
b
ased
o
n
p
r
e
v
i
o
u
s
d
ata
ac
q
u
is
itio
n
an
d
in
ter
s
ec
ts
with
s
tatis
tics
an
d
o
p
tim
izatio
n
[
1
0
]
.
C
u
r
r
e
n
tly
,
n
u
m
er
o
u
s
p
r
o
g
r
am
s
u
s
e
d
ata
m
in
i
n
g
tec
h
n
iq
u
es
t
o
cl
ass
if
y
wea
th
er
,
an
d
r
esear
ch
r
elate
d
to
wea
th
er
class
if
icatio
n
is
n
o
t
s
o
m
eth
i
n
g
v
er
y
n
ew.
T
h
er
e
h
av
e
b
ee
n
s
ev
er
al
s
tu
d
ies
th
at
h
av
e
b
ee
n
ca
r
r
ied
o
u
t
p
r
ev
io
u
s
ly
wh
ich
h
av
e
also
b
ee
n
p
u
b
lis
h
ed
as
s
cien
tific
ar
ticles.
Z
h
ao
a
n
d
W
u
[
1
1
]
,
in
h
is
r
esear
ch
,
c
o
n
d
u
cted
r
esear
ch
u
s
in
g
t
h
e
co
n
v
o
lu
t
io
n
al
n
eu
r
al
n
etwo
r
k
(
C
NN)
m
eth
o
d
in
th
e
class
if
icatio
n
p
r
o
ce
s
s
wh
ich
h
e
ca
r
r
ied
o
u
t
b
ased
o
n
th
e
v
is
u
al
co
n
d
itio
n
s
o
f
ea
ch
wea
th
e
r
co
n
d
itio
n
(
s
u
n
n
y
,
f
o
g
g
y
,
r
ain
y
,
s
n
o
w
y
)
.
Go
el
et
a
l.
[
1
2
]
also
ca
r
r
ied
o
u
t
a
w
ea
th
er
co
n
d
itio
n
class
if
icatio
n
p
r
o
ce
s
s
b
ased
o
n
ca
p
tu
r
ed
im
a
g
es
o
f
ea
c
h
we
ath
er
co
n
d
itio
n
an
d
p
r
o
ce
s
s
ed
u
s
in
g
th
e
VGG1
9
m
o
d
el
wh
ich
p
r
o
d
u
ce
d
an
ac
cu
r
ac
y
v
alu
e
o
f
9
8
.
5
%.
Dr
its
as
et
a
l.
[
1
3
]
class
if
ied
wea
t
h
er
co
n
d
itio
n
s
u
s
in
g
f
iv
e
d
ata
attr
ib
u
tes,
n
am
ely
d
ay
,
p
r
ec
i
p
itatio
n
,
tem
p
er
atu
r
e,
win
d
,
an
d
wea
th
er
,
an
d
i
n
v
o
lv
e
d
s
ev
er
al
tech
n
iq
u
es
i
n
th
e
class
if
icatio
n
p
r
o
ce
s
s
,
n
am
ely
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
(
SVM)
,
r
an
d
o
m
f
o
r
est
(
R
F),
an
d
n
eu
r
al
n
etwo
r
k
(
NN)
.
I
n
th
is
r
esear
ch
,
we
ca
r
r
ie
d
o
u
t
a
p
r
o
ce
s
s
o
f
class
if
y
in
g
wea
th
er
co
n
d
itio
n
s
b
ased
o
n
t
h
e
wea
th
er
p
ar
am
eter
s
th
at
wer
e
c
o
llected
.
T
h
e
r
esear
ch
lo
ca
tio
n
its
elf
is
p
r
ec
is
ely
in
Palu
c
ity
,
C
en
tr
al
Su
lawe
s
i
Pro
v
in
ce
,
I
n
d
o
n
esia.
T
h
e
city
o
f
Palu
its
elf
i
s
a
city
cr
o
s
s
ed
b
y
th
e
eq
u
ato
r
,
wh
ich
in
o
th
e
r
wo
r
d
s
is
a
tr
o
p
ical
ar
ea
with
h
ig
h
lev
els
o
f
r
ain
f
all
th
r
o
u
g
h
o
u
t
th
e
y
ea
r
.
T
h
e
p
ar
am
eter
d
ata
u
s
ed
in
th
is
r
esear
ch
ar
e
tem
p
er
atu
r
e,
h
u
m
id
ity
,
air
p
r
e
s
s
u
r
e,
win
d
s
p
ee
d
,
d
ew
p
o
in
t,
win
d
ch
ill,
d
aily
r
ai
n
f
all,
s
o
lar
r
ad
iatio
n
,
a
n
d
UV
in
d
ex
.
T
h
is
d
ata
was
co
llected
u
s
in
g
th
e
MI
SOL
W
S2
3
2
0
a
u
to
m
atic
wea
th
er
s
tatio
n
d
ev
i
ce
.
T
o
ca
r
r
y
o
u
t
th
is
class
if
icatio
n
p
r
o
ce
s
s
o
u
r
s
elv
es,
we
u
s
e
th
e
Altair
AI
s
t
u
d
io
a
p
p
licatio
n
,
wh
ich
was
p
r
ev
i
o
u
s
ly
ca
lled
R
ap
id
Min
er
s
tu
d
io
.
T
h
is
ap
p
licatio
n
is
h
an
d
y
in
t
h
e
d
ata
m
in
in
g
p
r
o
ce
s
s
,
d
ata
p
r
e
d
ictio
n
,
an
d
m
ac
h
in
e
lear
n
in
g
[
1
4
]
.
T
h
is
class
if
icati
o
n
m
et
h
o
d
em
p
lo
y
s
a
m
u
lti
-
lay
er
p
e
r
ce
p
tr
o
n
(
ML
P)
alg
o
r
i
th
m
,
a
f
o
r
m
o
f
NN
tech
n
iq
u
e.
T
h
e
p
ar
a
m
eter
s
u
s
ed
to
ass
es
s
th
e
p
er
f
o
r
m
a
n
c
e
o
f
th
e
alg
o
r
ith
m
ar
e
ac
c
u
r
ac
y
,
p
r
ec
is
io
n
,
a
n
d
r
ec
all
.
2.
M
E
T
H
O
D
T
h
is
s
ec
tio
n
ex
p
lain
s
th
e
b
asi
c
th
eo
r
y
o
f
th
e
alg
o
r
ith
m
u
s
ed
in
th
is
r
esear
ch
alo
n
g
with
th
e
p
r
o
f
ile
o
f
th
e
lo
ca
tio
n
wh
er
e
th
e
d
ata
was
co
llected
alo
n
g
with
th
e
au
to
m
atic
wea
th
er
s
tatio
n
eq
u
ip
m
en
t
u
s
ed
i
n
th
is
r
esear
ch
.
T
h
e
alg
o
r
ith
m
u
s
ed
in
th
is
r
esear
ch
is
ML
P
an
d
t
h
e
r
esear
ch
lo
ca
tio
n
its
elf
is
i
n
Palu
c
ity
,
C
en
tr
al
Su
lawe
s
i
Pro
v
in
ce
,
I
n
d
o
n
esia.
I
n
th
is
r
esear
ch
,
t
h
e
MI
SOL
W
S2
3
2
0
d
ev
ice
was
also
u
s
ed
as
an
au
to
m
atic
wea
th
er
s
tatio
n
wh
ich
f
u
n
ctio
n
s
to
co
llect
wea
th
er
p
a
r
a
m
ete
r
d
ata.
2
.
1
.
M
ulti
-
la
y
er
perc
ept
ro
n
a
lg
o
rit
hm
A
MLP
is
a
f
o
r
m
o
f
ar
tific
ial
n
eu
r
al
n
etwo
r
k
(
ANN)
c
o
m
p
r
is
in
g
s
ev
er
al
lay
e
r
s
o
f
n
e
u
r
o
n
s
[
1
5
]
.
T
h
e
n
eu
r
o
n
s
o
f
th
e
MLP
ty
p
ically
u
s
e
n
o
n
lin
ea
r
ac
tiv
atio
n
f
u
n
ctio
n
s
,
wh
ich
allo
ws
th
e
n
etwo
r
k
to
lear
n
co
m
p
lex
d
ata
p
atter
n
s
.
MLP
s
ar
e
im
p
o
r
tan
t
in
m
ac
h
in
e
lear
n
in
g
b
ec
a
u
s
e
th
ey
ca
n
lea
r
n
n
o
n
lin
ea
r
c
o
r
r
elatio
n
s
in
d
ata,
r
esu
ltin
g
in
ef
f
ec
tiv
e
m
o
d
els
f
o
r
class
if
ic
atio
n
,
r
eg
r
ess
io
n
,
an
d
p
atter
n
r
ec
o
g
n
itio
n
task
s
.
A
m
u
ltil
ay
er
p
er
ce
p
tr
o
n
is
a
f
ee
d
f
o
r
war
d
NN
o
f
f
u
lly
lin
k
e
d
n
eu
r
o
n
s
th
at
u
s
e
a
n
o
n
lin
ea
r
ac
tiv
at
io
n
f
u
n
ctio
n
.
I
t
is
co
m
m
o
n
l
y
u
s
ed
to
d
i
f
f
er
en
tiat
e
d
ata
th
at
is
n
o
t
lin
ea
r
l
y
s
ep
a
r
ab
le.
MLP
its
elf
co
n
s
is
ts
o
f
t
h
r
ee
lay
er
s
,
n
am
ely
in
p
u
t,
o
u
tp
u
t,
an
d
m
o
r
e
th
a
n
o
n
e
h
i
d
d
en
lay
er
[
1
6
]
,
[
1
7
]
.
T
h
e
lay
er
ar
r
an
g
em
en
t
o
f
t
h
e
MLP
ca
n
b
e
s
ee
n
in
Fig
u
r
e
1
.
E
ac
h
lay
er
i
n
th
e
M
L
P
h
as its
f
u
n
ctio
n
s
.
T
h
e
f
u
n
ct
io
n
s
ar
e
as f
o
llo
ws:
Fig
u
r
e
1
.
An
ex
am
p
le
o
f
a
ML
P
with
two
h
id
d
en
lay
er
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
7
,
No
.
1
,
J
an
u
ar
y
20
2
5
:
54
0
-
55
0
542
2
.
1
.
1
.
I
np
ut
l
a
y
er
T
h
e
in
p
u
t
lay
er
is
m
ad
e
u
p
o
f
n
o
d
es
o
r
n
eu
r
o
n
s
th
at
r
ec
eiv
e
in
itial
in
p
u
t
d
ata
[
1
8
]
.
E
ac
h
n
eu
r
o
n
r
ep
r
esen
ts
a
ce
r
tain
asp
ec
t
o
r
d
im
e
n
s
io
n
o
f
th
e
in
p
u
t
d
ata.
T
h
e
n
u
m
b
er
o
f
n
e
u
r
o
n
s
in
th
e
in
p
u
t
lay
er
is
d
ep
en
d
e
n
t
on
t
h
e
in
p
u
t
d
ata
’
s
d
im
en
s
io
n
ality
[
1
9
]
.
T
h
e
in
p
u
t
lay
er
o
f
a
MLP
ac
ce
p
ts
in
p
u
t
d
ata,
wh
ich
m
a
y
b
e
f
ea
tu
r
es
tak
en
f
r
o
m
in
p
u
t
s
am
p
les
in
a
d
ataset.
E
ac
h
n
eu
r
o
n
in
th
e
in
p
u
t
lay
er
r
e
p
r
ese
n
ts
a
s
in
g
le
f
ea
tu
r
e,
an
d
th
e
y
d
o
n
o
t
d
o
an
y
co
m
p
u
tatio
n
s
;
in
s
tead
,
th
ey
p
ass
th
e
in
p
u
t
v
alu
es
to
t
h
e
n
e
u
r
o
n
s
in
th
e
f
ir
s
t
h
id
d
e
n
lay
er
.
2
.
1
.
2
.
H
idd
en
l
a
y
er
E
ac
h
n
eu
r
o
n
in
a
h
id
d
e
n
lay
er
r
ec
eiv
es
in
p
u
ts
f
r
o
m
all
n
eu
r
o
n
s
in
th
e
p
r
ec
ed
in
g
lay
er
(
eith
er
th
e
in
p
u
t
lay
e
r
o
r
a
n
o
th
e
r
h
id
d
e
n
lay
er
)
a
n
d
c
r
ea
tes
an
o
u
t
p
u
t
th
at
is
p
ass
ed
o
n
to
th
e
f
o
llo
win
g
lay
e
r
[
2
0
]
.
T
h
e
n
u
m
b
er
o
f
h
id
d
en
lay
e
r
s
an
d
n
eu
r
o
n
s
in
ea
ch
h
id
d
en
la
y
er
ar
e
h
y
p
er
p
ar
am
eter
s
t
h
at
m
u
s
t
b
e
d
eter
m
in
e
d
d
u
r
in
g
th
e
m
o
d
el
cr
ea
tio
n
s
tag
e
[
2
1
]
.
T
h
e
h
id
d
en
lay
er
s
o
f
a
MLP
ar
e
m
ad
e
u
p
o
f
in
ter
c
o
n
n
ec
ted
n
e
u
r
o
n
s
th
at
ex
ec
u
te
co
m
p
u
tatio
n
s
o
n
t
h
e
in
co
m
in
g
d
ata.
E
ac
h
n
eu
r
o
n
in
a
h
id
d
en
la
y
er
r
ec
eiv
es
in
p
u
t
f
r
o
m
ev
e
r
y
n
e
u
r
o
n
in
th
e
p
r
e
v
io
u
s
lay
er
[
2
2
]
.
T
h
e
in
p
u
ts
ar
e
m
u
ltip
lied
b
y
th
e
ap
p
r
o
p
r
iate
weig
h
ts
,
r
ep
r
esen
ted
as
w.
T
h
e
weig
h
ts
g
o
v
er
n
h
o
w
m
u
c
h
in
f
lu
e
n
ce
o
n
e
n
e
u
r
o
n
’
s
in
p
u
t
h
as
o
n
an
o
th
e
r
’
s
o
u
tp
u
t.
I
n
a
d
d
itio
n
to
weig
h
ts
,
ea
ch
n
e
u
r
o
n
in
th
e
h
id
d
e
n
la
y
er
is
ass
ig
n
ed
a
b
ias,
d
en
o
ted
as
b
.
T
h
e
b
ias
a
d
d
s
m
o
r
e
i
n
p
u
t
t
o
th
e
n
eu
r
o
n
,
allo
win
g
it
to
ch
a
n
g
e
its
o
u
t
p
u
t
th
r
esh
o
ld
.
B
iases
,
lik
e
weig
h
ts
,
ar
e
lear
n
ed
d
u
r
i
n
g
th
e
tr
ain
in
g
p
r
o
ce
s
s
.
T
h
e
weig
h
te
d
to
tal
o
f
ea
ch
n
e
u
r
o
n
’
s
in
p
u
ts
i
n
a
h
id
d
en
o
r
o
u
tp
u
t
lay
e
r
is
ca
lc
u
lated
.
T
h
is
en
tails
m
u
ltip
ly
in
g
ea
ch
in
p
u
t
b
y
its
m
atch
in
g
weig
h
t,
to
talin
g
t
h
e
p
r
o
d
u
cts,
an
d
ad
d
in
g
t
h
e
b
ias ex
p
r
ess
ed
in
(
1
).
ℎ
=
∑
(
×
)
+
=
1
(
1
)
W
h
er
e
n
is
th
e
to
tal
n
u
m
b
er
o
f
in
p
u
t
co
n
n
ec
tio
n
s
,
w
i
is
th
e
weig
h
t
o
f
th
e
i
in
p
u
t,
an
d
x
i
is
th
e
i
in
p
u
t
v
alu
e.
T
h
e
weig
h
ted
s
u
m
is
s
u
b
s
eq
u
en
tly
p
r
o
ce
s
s
ed
b
y
an
ac
tiv
atio
n
f
u
n
ctio
n
,
in
d
icate
d
as
f
.
T
h
e
ac
tiv
atio
n
f
u
n
ctio
n
a
d
d
s
n
o
n
l
in
ea
r
ity
to
th
e
n
etwo
r
k
,
lettin
g
it
lear
n
an
d
ex
p
r
ess
co
m
p
licated
c
o
r
r
elatio
n
s
in
d
ata.
T
h
e
ac
tiv
atio
n
f
u
n
ctio
n
d
e
f
in
es
th
e
n
e
u
r
o
n
’
s
o
u
tp
u
t
r
an
g
e
an
d
b
eh
av
io
r
i
n
r
esp
o
n
s
e
to
v
ar
io
u
s
in
p
u
t
v
alu
es.
T
h
e
ac
tiv
atio
n
f
u
n
ctio
n
u
s
ed
i
s
d
eter
m
in
ed
b
y
th
e
n
atu
r
e
o
f
t
h
e
task
an
d
th
e
n
etwo
r
k
’
s
d
esire
d
q
u
alities
.
2
.
1
.
3
.
O
utput
l
a
y
er
T
h
e
n
eu
r
o
n
s
in
th
is
lay
er
p
r
o
d
u
ce
th
e
n
etwo
r
k
’
s
f
in
al
o
u
tp
u
t.
T
h
e
n
u
m
b
er
o
f
n
eu
r
o
n
s
in
th
e
o
u
tp
u
t
lay
er
v
ar
ies
ac
co
r
d
in
g
to
th
e
task
.
I
n
b
in
ar
y
class
if
icatio
n
,
d
ep
en
d
in
g
o
n
th
e
ac
tiv
atio
n
f
u
n
ctio
n
,
th
er
e
m
ay
b
e
o
n
e
o
r
two
n
e
u
r
o
n
s
ex
p
r
ess
in
g
th
e
lik
elih
o
o
d
o
f
b
elo
n
g
in
g
t
o
o
n
e
class
;
h
o
wev
e
r
,
i
n
m
u
lti
-
class
class
if
icat
io
n
task
s
,
th
e
o
u
tp
u
t
lay
er
m
ay
h
av
e
s
ev
er
al
n
eu
r
o
n
s
.
T
h
e
o
u
t
p
u
t
lay
e
r
o
f
a
MLP
g
en
er
ates
th
e
n
etwo
r
k
’
s
f
in
al
p
r
ed
i
ctio
n
s
o
r
o
u
tp
u
ts
.
T
h
e
n
u
m
b
er
o
f
n
eu
r
o
n
s
in
th
e
o
u
tp
u
t
lay
er
d
ep
e
n
d
s
o
n
th
e
task
at
h
an
d
(
e.
g
.
,
b
in
ar
y
class
if
icatio
n
,
m
u
lti
-
class
clas
s
if
icatio
n
,
r
eg
r
ess
io
n
)
[
1
6
]
.
E
a
ch
n
eu
r
o
n
in
th
e
o
u
tp
u
t
lay
er
r
ec
eiv
es
in
p
u
t
f
r
o
m
th
e
n
eu
r
o
n
s
i
n
th
e
last
h
id
d
e
n
lay
er
an
d
p
e
r
f
o
r
m
s
an
ac
tiv
atio
n
f
u
n
ctio
n
.
T
h
is
ac
tiv
atio
n
f
u
n
ctio
n
is
ty
p
ically
d
is
tin
ct
f
r
o
m
th
o
s
e
em
p
lo
y
e
d
i
n
th
e
h
id
d
en
lay
e
r
s
,
an
d
it
g
en
er
ates th
e
f
in
al
o
u
tp
u
t v
alu
e
o
r
p
r
ed
ictio
n
.
2
.
2
.
Resea
rc
h lo
ca
t
io
n a
nd
da
t
a
s
et
co
llect
io
n
As
ex
p
lain
ed
in
th
e
in
tr
o
d
u
ct
io
n
,
th
is
r
esear
ch
is
lo
ca
ted
in
Palu
c
ity
,
C
en
tr
al
Su
lawe
s
i
Pro
v
in
ce
,
I
n
d
o
n
esia.
Palu
,
th
e
ca
p
ital
o
f
C
en
tr
al
Su
lawe
s
i
Pro
v
in
ce
,
I
n
d
o
n
esia,
is
lo
ca
ted
o
n
th
e
Pa
lu
Valley
an
d
Palu
B
ay
p
lain
s
.
T
h
e
r
e
g
io
n
h
as
f
i
v
e
d
im
en
s
io
n
s
:
m
o
u
n
tain
o
u
s
t
er
r
ain
,
v
alle
y
s
,
r
iv
er
s
,
b
ay
s
,
a
n
d
o
ce
a
n
s
.
Palu
c
ity
h
as
an
ar
ea
o
f
3
9
5
.
0
6
s
q
u
ar
e
k
ilo
m
eter
s
d
iv
id
ed
in
to
eig
h
t
s
u
b
-
d
is
tr
icts
.
Palu
c
ity
i
s
lo
ca
t
ed
b
etwe
en
0
°.3
6
"
-
0
°.5
6
"
So
u
th
L
atitu
d
e
an
d
1
1
9
°.4
5
"
-
1
2
1
°.1
"
E
ast
L
o
n
g
itu
d
e,
m
ak
in
g
it
d
ir
ec
tly
o
n
th
e
E
q
u
ato
r
with
a
0
-
7
0
0
m
eter
s
h
ig
h
ab
o
v
e
s
ea
lev
el.
T
h
e
m
ap
o
f
Palu
c
ity
its
elf
,
wh
ich
is
lo
ca
ted
o
n
Su
lawe
s
i
I
s
lan
d
,
I
n
d
o
n
esia,
ca
n
b
e
s
ee
n
in
Fig
u
r
e
2
.
Palu
c
ity
,
lik
e
o
th
er
r
eg
io
n
s
i
n
I
n
d
o
n
esia,
h
as
two
s
ea
s
o
n
s
:
s
u
m
m
er
a
n
d
r
ain
y
s
ea
s
o
n
.
Su
m
m
er
last
s
f
r
o
m
Ap
r
il
t
o
Sep
tem
b
er
,
an
d
th
e
r
ain
y
s
ea
s
o
n
r
u
n
s
f
r
o
m
Oc
to
b
er
t
o
Ma
r
c
h
.
T
h
e
m
ax
im
u
m
r
ain
f
all
r
ec
o
r
d
ed
at
th
e
Mu
tiar
a
Palu
Me
teo
r
o
lo
g
ical
Statio
n
in
2
0
1
0
was
1
2
3
.
0
m
m
in
J
u
n
e,
with
th
e
lo
west
b
ein
g
1
1
.
7
m
m
in
Ma
r
ch
.
Me
a
n
wh
ile,
in
2
0
1
0
,
t
h
e
av
er
a
g
e
win
d
s
p
ee
d
was
3
.
7
k
n
o
ts
.
Palu
c
ity
’
s
lo
ca
tio
n
o
n
th
e
e
q
u
ato
r
also
co
n
tr
ib
u
tes
s
ig
n
if
ican
tly
to
th
e
p
r
esen
t
m
icr
o
clim
ate.
Of
co
u
r
s
e,
g
eo
g
r
ap
h
ical
ch
ar
ac
te
r
is
tics
lik
e
th
is
wil
l
ca
u
s
e
Palu
C
ity
to
r
ec
eiv
e
a
lo
t
o
f
s
u
n
lig
h
t
f
o
r
a
n
ex
ten
d
e
d
p
er
io
d
,
m
ak
in
g
t
h
e
lo
ca
tio
n
h
o
tter
th
an
o
th
er
cities
[
2
3
]
.
T
h
e
wea
th
er
p
a
r
am
eter
d
ata
u
s
ed
in
th
is
r
esea
r
ch
ar
e
te
m
p
er
atu
r
e,
h
u
m
id
ity
,
air
p
r
es
s
u
r
e,
win
d
s
p
ee
d
,
s
o
lar
r
ad
iatio
n
,
UV
in
d
ex
,
an
d
r
ain
f
all
lev
els.
All
o
f
th
ese
p
ar
am
eter
s
ca
n
b
e
u
s
ed
u
s
in
g
an
au
t
o
m
atic
wea
th
er
s
tatio
n
d
ev
ice,
n
am
el
y
MI
SOL
W
S2
3
2
0
.
T
h
is
p
r
o
d
u
ct
its
elf
is
m
ad
e
b
y
J
iax
in
g
Miso
l
E
lectr
o
n
ics
C
o
.
,
L
td
.
T
h
is
d
e
v
ice
is
o
f
ten
u
s
ed
b
y
o
th
er
r
esear
ch
e
r
s
to
d
etec
t
wea
th
er
p
ar
am
eter
s
in
an
ar
ea
an
d
d
is
p
lay
th
em
o
n
a
web
s
ite
p
ag
e
.
T
h
i
s
d
ev
ice
c
o
n
s
is
ts
o
f
two
m
ai
n
p
ar
ts
,
n
am
ely
an
ex
ter
n
al
d
ev
ice
co
n
s
is
tin
g
o
f
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:
2
5
0
2
-
4
7
52
C
la
s
s
i
fica
tio
n
o
f wea
th
er c
o
n
d
itio
n
s
b
a
s
ed
o
n
a
u
to
ma
tic
w
ea
th
er
…
(
Mu
h
a
mma
d
A
r
is
to
I
n
d
r
a
ja
ya
)
543
wea
th
er
p
ar
am
ete
r
s
en
s
o
r
s
p
la
ce
d
in
t
h
e
ex
ter
n
al
en
v
ir
o
n
m
e
n
t
wh
ich
ca
n
b
e
s
ee
n
in
Fig
u
r
e
3
.
I
n
t
h
is
r
esear
ch
,
we
p
lace
d
th
is
d
ev
ice
o
n
a
b
u
ild
in
g
th
at
is
th
e
h
ig
h
est
co
m
p
ar
ed
to
its
s
u
r
r
o
u
n
d
in
g
s
s
o
th
at
it
ca
n
m
ea
s
u
r
e
win
d
s
p
ee
d
well.
Ap
ar
t
f
r
o
m
th
e
wea
th
er
p
ar
a
m
eter
s
en
s
o
r
s
p
lace
d
o
u
ts
id
e
t
h
e
b
u
ild
in
g
wh
ich
ar
e
r
ec
ei
v
e
d
v
ia
r
ad
io
co
m
m
u
n
icatio
n
lin
es,
th
is
wea
th
er
s
tatio
n
h
as
a
d
ev
ice
th
at
f
u
n
ctio
n
s
as
a
r
ec
ei
v
er
o
f
th
e
c
o
llected
d
ata
wh
ich
ca
n
b
e
s
ee
n
in
Fig
u
r
e
4
.
T
h
is
r
ec
eiv
in
g
d
ev
ice
in
ad
d
itio
n
to
co
llectin
g
th
e
d
ata
co
llecte
d
o
b
tain
e
d
b
y
th
e
s
en
s
o
r
ca
n
also
d
is
p
lay
f
ac
tu
al
d
ata
r
eg
ar
d
in
g
t
h
e
co
n
d
itio
n
o
f
th
e
m
ea
s
u
r
e
m
en
t
r
esu
lts
o
f
wea
th
er
d
ata
v
ia
its
L
C
D
s
cr
ee
n
.
Ap
ar
t
f
r
o
m
th
at
,
th
is
d
e
v
ice
is
also
ca
p
ab
le
o
f
s
en
d
i
n
g
t
h
e
c
o
llected
d
ata
to
t
h
e
co
m
p
u
ter
i
n
r
ea
l
-
tim
e
.
Fig
u
r
e
2
.
T
h
e
m
ap
s
o
f
Palu
c
it
y
Fig
u
r
e
3
.
MI
SOL
W
S2
3
2
0
o
u
t
d
o
o
r
s
en
s
o
r
Fig
u
r
e
4
.
MI
SOL
W
S2
3
2
0
r
ec
eiv
er
Data
co
llectio
n
was
ca
r
r
ied
o
u
t
f
o
r
s
ix
m
o
n
th
s
s
tar
tin
g
f
r
o
m
J
an
u
ar
y
to
J
u
n
e,
wh
er
e
t
h
e
d
at
a
ex
ce
r
p
t
ca
n
b
e
s
ee
n
in
Fig
u
r
e
5
.
Data
co
llectio
n
is
ca
r
r
ied
o
u
t
in
we
ath
er
co
n
d
itio
n
s
wh
er
e
th
e
we
ath
er
ca
n
ch
a
n
g
e
all
th
e
tim
e.
T
h
is
is
b
ec
au
s
e
,
in
Ma
y
,
Palu
c
ity
ex
p
er
ien
ce
s
a
t
r
an
s
itio
n
s
ea
s
o
n
s
o
th
at
in
o
n
e
m
o
n
th
th
e
wea
th
er
ca
n
ch
an
g
e
q
u
ite
q
u
ic
k
ly
.
Fo
r
ex
am
p
le,
d
u
r
in
g
t
h
e
d
a
y
th
e
wea
th
er
is
s
u
n
n
y
,
b
u
t
d
u
r
in
g
t
h
e
d
ay
th
e
wea
th
e
r
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
7
,
No
.
1
,
J
an
u
ar
y
20
2
5
:
54
0
-
55
0
544
co
n
d
itio
n
s
ca
n
im
m
ed
iately
c
h
an
g
e
t
o
clo
u
d
y
an
d
n
o
t
lo
n
g
af
ter
th
at
it
c
an
r
ain
q
u
ite
h
e
av
ily
.
T
h
r
o
u
g
h
d
ata
co
llectio
n
,
1
0
3
7
wea
th
er
p
ar
a
m
eter
d
ata
wer
e
o
b
tain
ed
wh
ic
h
wer
e
d
iv
id
e
d
in
to
s
ev
e
r
al
class
es,
n
am
ely
:
1.
Su
n
n
y
Su
n
n
y
wea
th
er
is
a
wea
th
er
c
o
n
d
itio
n
t
h
at
d
escr
ib
es
th
e
s
k
y
in
b
r
ig
h
t
c
o
n
d
itio
n
s
a
n
d
s
u
n
lig
h
t
ca
n
b
e
f
elt
clea
r
ly
an
d
h
as a
h
ig
h
lev
el
o
f
UV
r
ad
iatio
n
.
2.
Su
n
n
y
clo
u
d
y
Su
n
n
y
,
clo
u
d
y
wea
th
er
is
ch
ar
ac
ter
ized
b
y
th
e
lar
g
e
n
u
m
b
e
r
o
f
clo
u
d
s
v
is
ib
le
in
th
e
s
k
y
.
I
n
th
is
co
n
d
itio
n
,
th
e
in
ten
s
ity
o
f
s
u
n
lig
h
t
is
n
o
t
as
h
ig
h
as
in
s
u
n
n
y
wea
th
e
r
wh
ich
is
ch
ar
ac
te
r
ized
b
y
lo
w
lev
els
o
f
s
o
lar
r
ad
iatio
n
an
d
UV
in
d
ex
.
3.
C
lo
u
d
y
C
lo
u
d
y
wea
th
er
is
ch
a
r
ac
ter
iz
ed
b
y
th
e
s
k
y
b
ein
g
co
v
e
r
ed
with
th
ick
clo
u
d
s
.
T
h
ese
clo
u
d
s
b
lo
ck
s
u
n
lig
h
t,
ca
u
s
in
g
v
er
y
lo
w
s
o
lar
r
a
d
iatio
n
an
d
UV
in
d
ex
v
alu
es.
4.
L
ig
h
t r
ain
L
ig
h
t r
ain
is
a
wea
th
er
c
o
n
d
iti
o
n
with
lo
w
in
ten
s
ity
with
a
r
a
in
r
ate
o
f
less
th
an
2
.
5
m
m
/h
(
<0
.
1
”/h
r
)
[
2
4
]
.
5.
Mo
d
er
ate
r
ain
Mo
d
er
ate
r
ain
o
cc
u
r
s
wh
en
th
e
r
ain
f
all
r
ate
r
an
g
es
f
r
o
m
2
.
6
to
7
.
5
m
m
/h
o
u
r
(
0
.
1
to
0
.
3
"/
h
o
u
r
)
o
r
0
.
0
4
to
0
.
1
2
5
m
m
/m
in
u
te
(
0
.
0
0
1
7
to
0
.
0
0
5
"/
h
o
u
r
)
,
wh
ich
eq
u
ates
to
2
6
to
7
5
f
u
ll
tip
p
in
g
b
u
ck
et
s
p
er
h
o
u
r
(
2
6
to
7
5
p
u
ls
es/h
o
u
r
)
f
o
r
a
r
ai
n
g
au
g
e
with
a
r
eso
lu
tio
n
o
f
0
.
1
m
m
[
2
4
]
.
6.
Hea
v
y
r
ain
Hea
v
y
r
ain
is
a
r
ain
y
wea
th
er
co
n
d
itio
n
i
n
wh
ich
th
e
r
ain
r
at
e
ex
ce
ed
s
7
.
6
to
5
0
m
m
/h
o
u
r
(
0
.
3
to
2
"/h
o
u
r
)
o
r
0
.
1
2
5
to
0
.
8
3
m
m
/m
in
u
te
(
0
.
0
0
5
"
to
0
.
0
3
3
"/m
in
u
te)
,
wh
i
ch
am
o
u
n
ts
to
7
6
o
r
m
o
r
e
f
u
ll
tip
p
in
g
b
u
ck
ets
p
er
h
o
u
r
(
7
6
+
p
u
ls
es/h
o
u
r
)
o
n
a
r
ain
g
au
g
e
with
a
r
eso
lu
tio
n
o
f
0
.
1
m
m
[
2
4
]
.
7.
C
lear
n
ig
h
t
A
clea
r
n
ig
h
t
is
a
wea
th
e
r
c
o
n
d
itio
n
wh
er
e
th
e
s
k
y
ap
p
e
ar
s
clea
r
o
f
clo
u
d
s
an
d
th
e
s
tar
s
ca
n
b
e
s
ee
n
clea
r
ly
.
8.
C
lo
u
d
y
n
ig
h
t
T
h
is
is
a
wea
th
er
co
n
d
itio
n
at
n
ig
h
t w
h
er
e
cl
o
u
d
s
co
v
er
th
e
s
k
y
an
d
th
e
ey
e
ca
n
n
o
t see
th
e
s
tar
s
.
9.
L
ig
h
t r
ain
y
n
ig
h
t
T
h
is
is
a
r
ain
y
co
n
d
itio
n
th
at
o
cc
u
r
s
at
n
ig
h
t
wh
e
n
th
e
r
ai
n
r
a
te
is
less
th
an
2
.
5
m
m
/h
o
u
r
(
<
0
.
1
"/h
o
u
r
)
.
10.
Mo
d
er
ate
r
ain
y
n
ig
h
t
T
h
is
is
a
r
ain
y
co
n
d
itio
n
at
n
i
g
h
t
wh
er
e
r
ain
f
all
r
an
g
es
f
r
o
m
2
.
6
to
7
.
5
m
m
/h
o
u
r
(
0
.
1
to
0
.
3
"/h
o
u
r
)
o
r
0
.
0
4
to
0
.
1
2
5
m
m
/m
i
n
u
te
(
0
.
0
0
1
7
to
0
.
0
0
5
"/
h
o
u
r
)
,
wh
ich
is
eq
u
iv
alen
t
to
2
6
to
7
5
f
u
ll
tip
p
i
n
g
b
u
ck
ets
p
er
h
o
u
r
(
2
6
t
o
7
5
p
u
ls
es/h
o
u
r
)
f
o
r
a
r
ain
g
au
g
e
with
a
r
eso
lu
tio
n
o
f
0
.
1
m
m
.
11.
Hea
v
y
r
ain
y
n
ig
h
t
I
t
is
a
r
ain
y
wea
th
er
co
n
d
itio
n
th
at
o
cc
u
r
s
at
n
ig
h
t
wh
en
th
e
r
ain
r
ate
e
x
ce
ed
s
7
.
6
to
5
0
m
m
/h
o
u
r
(
0
.
3
to
2
"/h
o
u
r
)
o
r
0
.
1
2
5
to
0
.
8
3
m
m
/m
in
u
te
(
0
.
0
0
5
"
to
0
.
0
3
3
"/m
in
u
te)
,
wh
ic
h
am
o
u
n
ts
to
7
6
o
r
m
o
r
e
f
u
ll
tip
p
in
g
b
u
ck
ets p
er
h
o
u
r
(
7
6
+
p
u
ls
es/h
o
u
r
)
o
n
a
r
ain
g
au
g
e
with
a
r
eso
lu
tio
n
o
f
0
.
1
m
m
.
Fig
u
r
e
5
.
A
s
n
ap
s
h
o
t o
f
t
h
e
d
a
ta
th
at
h
as b
ee
n
en
te
r
ed
in
to
th
e
Altair
AI
s
tu
d
io
ap
p
licat
io
n
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:
2
5
0
2
-
4
7
52
C
la
s
s
i
fica
tio
n
o
f wea
th
er c
o
n
d
itio
n
s
b
a
s
ed
o
n
a
u
to
ma
tic
w
ea
th
er
…
(
Mu
h
a
mma
d
A
r
is
to
I
n
d
r
a
ja
ya
)
545
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
is
s
ec
tio
n
ex
p
lain
s
th
e
d
ata
p
r
o
ce
s
s
in
g
p
r
o
ce
s
s
-
p
ar
a
m
eter
d
ata
th
at
h
as
b
ee
n
o
b
tain
ed
u
s
in
g
th
e
MI
SOL
W
S2
3
2
0
au
to
m
atic
w
ea
th
er
s
tatio
n
.
T
h
e
d
ata
o
b
tain
ed
in
r
ea
l
-
tim
e
is
th
en
p
r
o
ce
s
s
ed
u
s
in
g
th
e
MLP
alg
o
r
ith
m
i
n
th
e
Altair
AI
s
tu
d
io
a
p
p
licatio
n
.
Altair
A
I
s
tu
d
io
f
o
r
m
er
ly
k
n
o
wn
as
R
a
p
id
Min
er
is
a
d
ata
s
cien
ce
s
o
f
twar
e
p
latf
o
r
m
d
ev
elo
p
ed
b
y
th
e
co
m
p
an
y
o
f
th
e
s
am
e
n
a
m
e
th
at
p
r
o
v
i
d
es
an
in
teg
r
ated
en
v
ir
o
n
m
en
t
f
o
r
d
ata
p
r
e
p
ar
a
tio
n
,
m
ac
h
i
n
e
lear
n
in
g
,
d
ee
p
lear
n
in
g
,
tex
t
m
in
i
n
g
,
a
n
d
p
r
ed
ictiv
e
an
al
y
s
is
.
I
t
i
s
u
s
ed
f
o
r
b
u
s
in
ess
an
d
co
m
m
er
cial
p
u
r
p
o
s
es,
as
well
as
f
o
r
r
esear
ch
,
ed
u
ca
t
io
n
,
tr
ain
in
g
,
r
ap
i
d
p
r
o
to
ty
p
in
g
,
an
d
ap
p
licatio
n
d
ev
elo
p
m
e
n
t
,
a
n
d
s
u
p
p
o
r
ts
all
s
tep
s
in
th
e
m
ac
h
in
e
lear
n
in
g
p
r
o
ce
s
s
in
clu
d
in
g
d
ata
p
r
ep
a
r
atio
n
,
r
esu
lts
v
is
u
al
izatio
n
,
m
o
d
el
v
alid
atio
n
,
a
n
d
o
p
tim
izatio
n
.
3
.
1
.
Da
t
a
prepro
ce
s
s
ing
Pro
ce
s
s
in
g
o
f
th
e
d
ata
o
b
tain
ed
is
ca
r
r
ied
o
u
t
th
r
o
u
g
h
s
ev
e
r
al
s
tag
es.
T
h
e
p
r
o
ce
s
s
s
tep
s
ca
r
r
ied
o
u
t
u
s
in
g
Altair
AI
Stu
d
io
ca
n
b
e
s
ee
n
in
Fig
u
r
e
6
.
Pre
v
io
u
s
l
y
,
th
e
d
ata
s
en
t
b
y
th
e
au
to
m
atic
wea
th
er
s
tatio
n
d
ev
ice
was
in
a
f
ile
with
th
e
C
SV
ex
ten
s
io
n
.
T
o
m
ak
e
p
r
o
c
ess
in
g
ea
s
ier
,
th
e
f
ile
is
th
en
co
n
v
er
ted
t
o
th
e
x
ls
x
ex
ten
s
io
n
.
B
ef
o
r
e
th
e
d
ata
is
p
r
o
ce
s
s
ed
b
y
th
e
MLP
alg
o
r
ith
m
,
t
h
e
d
ata
f
ir
s
t
g
o
es
t
h
r
o
u
g
h
a
s
t
ag
e
ca
lled
p
r
ep
r
o
ce
s
s
in
g
.
T
h
is
p
r
o
ce
s
s
b
eg
in
s
with
th
e
s
elec
t
attr
ib
u
te
s
p
r
o
ce
s
s
.
I
n
th
is
p
r
o
ce
s
s
,
th
e
y
ea
r
,
m
o
n
th
,
an
d
tim
e
o
f
d
ata
c
o
llectio
n
ar
e
f
ilt
er
ed
to
b
e
p
r
o
ce
s
s
ed
in
to
t
h
e
alg
o
r
ith
m
.
T
h
is
aim
s
to
av
o
i
d
er
r
o
r
s
in
t
h
e
th
r
ee
tr
ain
in
g
p
r
o
ce
s
s
es
in
th
e
al
g
o
r
ith
m
.
Fu
r
th
e
r
m
o
r
e
,
in
th
e
r
e
m
o
v
e
d
u
p
licates
s
ec
tio
n
,
d
u
p
licate
d
ata
will
b
e
r
em
o
v
ed
.
Fu
r
th
er
m
o
r
e,
in
th
e
s
p
lit
d
ata
s
ec
tio
n
,
th
e
wea
th
er
p
ar
am
eter
d
ata
th
at
h
as
b
ee
n
c
o
llected
is
d
iv
id
ed
b
ased
o
n
th
e
n
ee
d
s
f
o
r
th
e
tr
a
in
in
g
a
n
d
test
in
g
p
r
o
ce
s
s
es.
T
h
e
d
iv
is
io
n
its
elf
is
7
0
%
f
o
r
t
h
e
tr
ain
in
g
p
r
o
ce
s
s
an
d
3
0
%
f
o
r
th
e
test
in
g
p
r
o
ce
s
s
.
T
h
e
p
e
r
f
o
r
m
an
ce
o
f
th
e
tr
a
in
in
g
p
r
o
ce
s
s
is
m
ea
s
u
r
e
d
u
s
in
g
th
r
ee
p
ar
am
eter
s
,
n
am
ely
:
1.
Acc
u
r
ac
y
Acc
u
r
ac
y
is
a
n
e
v
alu
atio
n
m
e
tr
ic
th
at
m
ea
s
u
r
es
h
o
w
well
a
m
o
d
el
m
ak
es
co
r
r
ec
t
p
r
e
d
ictio
n
s
o
u
t
o
f
th
e
to
tal
p
r
ed
ictio
n
s
it
m
a
k
es.
I
n
t
h
e
co
n
te
x
t
o
f
class
if
icatio
n
,
ac
cu
r
ac
y
p
r
o
v
i
d
es
an
id
ea
o
f
h
o
w
o
f
ten
a
m
o
d
el
p
r
ed
icts
th
e
co
r
r
ec
t c
lass
,
wh
eth
er
it is
p
o
s
itiv
e
o
r
n
e
g
ativ
e
[
2
5
]
.
2.
Pre
cisi
o
n
Pre
cisi
o
n
is
an
ev
alu
atio
n
m
etr
ic
th
at
m
ea
s
u
r
es
h
o
w
well
a
m
o
d
el
m
ak
es
co
r
r
ec
t
p
r
e
d
ictio
n
s
f
o
r
th
e
p
o
s
itiv
e
class
o
u
t
o
f
th
e
to
tal
p
o
s
itiv
e
p
r
ed
ictio
n
s
.
I
n
th
e
co
n
tex
t
o
f
class
if
icatio
n
,
p
r
ec
is
io
n
p
r
o
v
id
es
an
id
ea
o
f
h
o
w
o
f
ten
a
m
o
d
el
co
r
r
ec
tly
p
r
ed
icts
th
e
p
o
s
itiv
e
cla
s
s
,
am
o
n
g
all
th
e
p
o
s
itiv
e
p
r
ed
ictio
n
s
m
ad
e
b
y
th
e
m
o
d
el
[
2
5
]
.
3.
R
ec
all
R
ec
all
is
a
m
etr
ic
th
at
m
ea
s
u
r
es
h
o
w
m
an
y
p
o
s
itiv
e
ca
s
es
th
e
class
if
ier
ac
cu
r
ately
p
r
ed
icte
d
o
u
t
o
f
all
th
e
p
o
s
itiv
e
ca
s
es in
th
e
d
ataset.
I
t is so
m
etim
es r
ef
er
r
ed
to
as se
n
s
itiv
ity
[
2
5
]
.
I
n
th
e
d
ata
p
r
o
ce
s
s
in
g
s
tag
e,
i
n
ad
d
itio
n
t
o
th
e
d
ata
an
al
y
s
is
p
r
o
ce
s
s
in
v
o
lv
in
g
th
e
ML
P
a
lg
o
r
ith
m
,
o
n
e
o
f
th
e
i
m
p
o
r
ta
n
t
s
tag
es
in
d
ata
p
r
o
ce
s
s
in
g
is
cr
o
s
s
-
v
al
id
atio
n
.
C
r
o
s
s
-
v
alid
atio
n
is
a
s
tatis
t
ical
tech
n
iq
u
e
u
s
ed
in
m
ac
h
in
e
lear
n
in
g
a
n
d
o
th
er
p
r
ed
ictiv
e
m
o
d
elin
g
to
a
s
s
es
s
th
e
p
er
f
o
r
m
an
ce
an
d
g
e
n
er
aliza
tio
n
ab
ilit
y
o
f
a
m
o
d
el.
T
h
is
tech
n
i
q
u
e
p
r
o
v
id
es
a
m
o
r
e
ac
c
u
r
ate
esti
m
a
te
o
f
m
o
d
el
p
e
r
f
o
r
m
an
ce
o
n
u
n
s
ee
n
d
ata.
An
o
t
h
er
im
p
o
r
tan
t
b
en
e
f
it
o
f
cr
o
s
s
-
v
alid
atio
n
is
th
at
it
h
elp
s
d
at
a
an
aly
s
ts
o
v
e
r
co
m
e
th
e
p
r
o
b
lem
o
f
o
v
er
f
itti
n
g
o
r
co
n
d
itio
n
s
wh
e
n
th
e
m
o
d
e
l
is
to
o
s
p
ec
if
ic
to
th
e
tr
ain
i
n
g
d
ata
s
o
th
at
it
is
less
g
o
o
d
at
an
aly
zi
n
g
n
ew
d
ata
[
2
6
]
.
Fig
u
r
e
6
.
Data
p
r
o
ce
s
s
in
g
d
iag
r
am
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
7
,
No
.
1
,
J
an
u
ar
y
20
2
5
:
54
0
-
55
0
546
3
.
2
.
P
er
f
o
r
m
a
nce
a
na
ly
s
is
As
p
r
ev
io
u
s
ly
e
x
p
lain
ed
,
th
e
d
ata
an
aly
s
is
u
s
ed
i
n
th
is
s
tu
d
y
u
s
es
a
MLP
alg
o
r
ith
m
c
o
m
m
o
n
l
y
ab
b
r
ev
iated
as
ML
P.
T
h
e
an
a
ly
s
is
p
r
o
ce
s
s
ca
r
r
ied
o
u
t
in
th
is
s
tu
d
y
was
ca
r
r
ied
o
u
t
th
r
o
u
g
h
s
ev
e
r
al
s
tag
es.
I
n
th
e
f
ir
s
t
s
tag
e,
wea
th
er
p
ar
am
eter
d
ata
an
al
y
s
is
was
ca
r
r
ied
o
u
t
u
s
in
g
th
e
s
tan
d
ar
d
MLP
co
n
f
ig
u
r
atio
n
i
n
th
e
Altair
AI
Stu
d
i
o
ap
p
licatio
n
.
I
n
Altair
AI
Stu
d
io
,
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
MLP
is
co
n
f
i
g
u
r
e
d
u
s
in
g
p
ar
am
eter
s
,
n
am
ely
tr
ain
i
n
g
c
y
cle,
n
u
m
b
e
r
o
f
g
e
n
er
atio
n
s
,
an
d
n
u
m
b
er
o
f
en
s
em
b
les.
T
h
ese
p
ar
am
eter
s
will
af
f
ec
t
th
e
a
b
ilit
y
o
f
th
e
alg
o
r
ith
m
to
lear
n
th
e
in
p
u
t
d
ata.
B
y
u
s
in
g
th
e
d
ef
a
u
lt
co
n
f
ig
u
r
atio
n
o
f
Altair
AI
Stu
d
io
,
n
am
el
y
th
e
tr
ain
in
g
c
y
cle
is
s
et
to
1
0
,
th
e
n
u
m
b
er
o
f
g
en
er
atio
n
s
is
s
et
to
1
0
,
an
d
th
e
n
u
m
b
er
o
f
en
s
em
b
les
is
s
e
t
to
4
,
th
e
r
esu
lts
o
f
th
e
an
aly
s
is
p
er
f
o
r
m
an
c
e
ca
r
r
ied
o
u
t
b
y
th
e
lear
n
in
g
an
d
tr
ain
in
g
p
r
o
ce
s
s
ca
n
b
e
s
ee
n
in
Fig
u
r
es 7
an
d
8
.
Fig
u
r
e
7
.
Acc
u
r
ac
y
v
alu
e
o
f
test
in
g
in
th
e
tr
ain
in
g
p
r
o
ce
s
s
Fig
u
r
e
8
.
Acc
u
r
ac
y
v
alu
e
o
f
test
in
g
in
th
e
t
esti
n
g
p
r
o
ce
s
s
B
ased
o
n
th
e
an
aly
s
is
p
r
o
ce
s
s
ca
r
r
ied
o
u
t
u
s
in
g
s
tan
d
ar
d
co
n
f
ig
u
r
atio
n
v
alu
es,
th
e
ac
cu
r
a
cy
v
alu
e
i
n
th
e
tr
ain
in
g
p
r
o
ce
s
s
was
8
7
.
7
9
%
an
d
8
5
.
1
6
%
in
th
e
test
in
g
p
r
o
ce
s
s
.
T
h
e
d
etailed
p
er
f
o
r
m
an
ce
co
m
p
a
r
is
o
n
v
alu
es in
th
e
tr
ain
in
g
an
d
test
in
g
p
r
o
ce
s
s
es c
an
b
e
s
ee
n
in
T
a
b
le
1.
Alth
o
u
g
h
b
ased
o
n
th
e
p
er
f
o
r
m
an
ce
g
en
er
ate
d
f
r
o
m
th
e
a
n
aly
s
is
ca
r
r
ied
o
u
t,
th
e
ac
cu
r
ac
y
o
f
th
e
class
if
ied
d
ata
is
s
ti
ll
q
u
ite
h
ig
h
,
wh
ich
is
ab
o
v
e
8
5
%
in
th
e
tr
ain
in
g
an
d
test
in
g
p
r
o
ce
s
s
.
Als
o
,
th
e
ac
cu
r
ac
y
r
esu
lts
in
th
e
lear
n
in
g
p
r
o
ce
s
s
an
d
test
in
g
p
r
o
ce
s
s
ar
e
n
o
t
s
tr
ik
in
g
s
o
th
e
y
ca
n
b
e
ca
teg
o
r
ized
as
n
o
t
o
v
er
f
itti
n
g
.
Ho
wev
e
r
,
th
e
n
u
m
b
er
o
f
in
co
r
r
ec
t
d
ata
in
th
e
class
if
icat
io
n
p
r
o
ce
s
s
is
s
till
q
u
ite
a
lo
t.
I
n
th
e
test
in
g
p
r
o
ce
s
s
,
o
u
t
o
f
3
1
0
d
a
ta
u
s
ed
in
th
e
test
in
g
p
r
o
ce
s
s
,
4
6
d
a
ta
wer
e
p
r
ed
icted
in
c
o
r
r
ec
tly
.
A
s
n
ip
p
et
o
f
in
co
r
r
ec
tly
p
r
ed
icted
d
ata
ca
n
b
e
s
ee
n
in
Fig
u
r
e
9
.
T
ab
le
1
.
Per
f
o
r
m
an
ce
r
esu
lts
o
f
th
e
an
aly
s
is
p
er
f
o
r
m
ed
b
y
t
h
e
MLP
alg
o
r
ith
m
u
s
in
g
th
e
s
tan
d
ar
d
co
n
f
ig
u
r
atio
n
P
a
r
a
me
t
e
r
s
Tr
a
i
n
i
n
g
Te
st
i
ng
A
c
c
u
r
a
c
y
8
7
.
7
9
%
+
/
-
3
.
3
4
%
8
5
.
1
6
%
P
r
e
c
i
s
i
o
n
8
4
.
5
8
%
+
/
-
6
.
5
2
%
8
6
.
1
7
%
R
e
c
a
l
l
8
4
.
2
8
%
8
5
.
9
3
%
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:
2
5
0
2
-
4
7
52
C
la
s
s
i
fica
tio
n
o
f wea
th
er c
o
n
d
itio
n
s
b
a
s
ed
o
n
a
u
to
ma
tic
w
ea
th
er
…
(
Mu
h
a
mma
d
A
r
is
to
I
n
d
r
a
ja
ya
)
547
Fig
u
r
e
9
.
I
n
co
r
r
ec
t d
ata
in
t
h
e
an
aly
s
is
p
r
o
ce
s
s
T
o
o
v
e
r
co
m
e
th
e
m
a
n
y
e
r
r
o
r
s
,
in
th
e
n
ex
t
s
tag
e
we
to
o
k
th
e
in
itiativ
e
to
in
c
r
ea
s
e
th
e
tr
ain
in
g
cy
cle
,
th
e
n
u
m
b
e
r
o
f
en
s
em
b
les,
an
d
th
e
n
u
m
b
e
r
o
f
g
e
n
er
atio
n
s
.
T
h
e
ad
d
itio
n
o
f
v
alu
es
s
et
f
o
r
t
h
e
th
r
ee
p
ar
a
m
eter
s
will
af
f
ec
t
th
e
alg
o
r
ith
m
’
s
ab
i
lity
to
lear
n
in
p
u
t
d
ata.
T
h
e
p
r
o
ce
s
s
o
f
a
d
d
in
g
p
ar
am
eter
v
alu
es
is
ca
r
r
ied
o
u
t
g
r
ad
u
all
y
an
d
r
esu
lts
in
an
in
cr
ea
s
e
in
th
e
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
an
d
r
ec
all
v
al
u
es
.
T
h
is
c
an
h
ap
p
en
b
ec
au
s
e
wh
en
th
e
alg
o
r
ith
m
’
s
lear
n
in
g
cy
cle
in
cr
ea
s
es,
it
will
al
s
o
in
cr
ea
s
e
th
e
n
u
m
b
e
r
o
f
n
e
u
r
o
n
s
u
s
ed
b
y
th
e
alg
o
r
ith
m
.
As
a
co
m
p
ar
is
o
n
,
i
n
th
e
p
r
o
ce
s
s
u
s
in
g
th
e
d
ef
au
lt
v
alu
e,
th
e
n
u
m
b
er
o
f
n
e
u
r
o
n
s
u
s
ed
in
th
e
h
id
d
e
n
lay
er
is
4
3
u
n
its
.
T
h
e
r
elatio
n
s
h
ip
b
etwe
en
th
e
ad
d
itio
n
o
f
t
r
ain
in
g
cy
cles,
th
e
n
u
m
b
e
r
o
f
en
s
em
b
les,
an
d
th
e
n
u
m
b
er
o
f
g
en
e
r
atio
n
s
f
o
r
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
MLP
alg
o
r
ith
m
in
th
e
tr
ain
in
g
an
d
test
in
g
p
r
o
ce
s
s
es
ca
n
b
e
s
ee
n
in
T
ab
le
2
a
n
d
T
a
b
le
3
.
T
ab
le
2
.
Per
f
o
r
m
an
ce
o
f
th
e
tr
ain
in
g
p
r
o
ce
s
s
with
m
o
d
if
ied
co
n
f
ig
u
r
atio
n
Tr
a
i
n
i
n
g
c
y
c
l
e
s
N
u
mb
e
r
o
f
e
n
sem
b
l
e
N
u
mb
e
r
o
f
g
e
n
e
r
a
t
i
o
n
A
c
c
u
r
a
c
y
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
15
15
15
8
9
.
8
7
%
+
/
-
3
.
4
8
%
8
7
.
9
4
%
+
/
-
5
.
5
7
%
8
8
.
3
6
%
+
/
-
4
.
6
8
%
20
20
20
8
8
.
9
1
%
+
/
-
3
.
5
8
%
8
6
.
1
2
%
+
/
-
5
.
2
7
%
8
6
.
0
7
%
+
/
-
3
.
6
6
%
25
25
25
8
9
.
6
0
%
+
/
-
4
.
7
2
%
8
7
.
1
6
%
+
/
-
5
.
9
4
%
8
6
.
9
8
%
+
/
-
6
.
3
4
%
30
30
30
8
9
.
3
2
%
+
/
-
4
.
0
4
%
8
9
.
0
1
%
+
/
-
5
.
0
9
%
8
8
.
3
2
%
+
/
-
5
.
1
0
%
35
35
35
9
0
.
0
1
%
+
/
-
4
.
2
4
%
8
8
.
6
5
%
+
/
-
5
.
2
6
%
8
7
.
8
3
%
+
/
-
4
.
2
6
%
40
40
40
9
0
.
2
9
%
+
/
-
1
.
9
5
%
8
6
.
8
2
%
+
/
-
5
.
8
5
%
8
6
.
4
7
%
+
/
-
5
.
0
7
%
42
42
42
9
2
.
1
0
%
+
/
-
3
.
0
6
%
8
8
.
7
9
%
+
/
-
5
.
4
6
%
8
8
.
8
7
%
+
/
-
5
.
0
9
%
44
44
44
9
2
.
0
9
%
+
/
-
4
.
0
9
%
9
0
.
2
6
%
+
/
-
4
.
7
6
%
9
0
.
2
4
%
+
/
-
3
.
8
0
%
45
45
45
9
0
.
4
3
%
+
/
-
3
.
3
5
%
8
7
.
8
1
%
+/
-
6
.
8
3
%
8
7
.
3
4
%
+
/
-
5
.
6
8
%
46
46
46
9
0
.
8
5
%
+
/
-
3
.
9
7
%
8
8
.
2
5
%
+
/
-
5
.
9
9
%
8
7
.
7
6
%
+
/
-
6
.
1
5
%
47
47
47
9
1
.
8
2
%
+
/
-
2
.
8
9
%
9
0
.
0
6
%
+
/
-
4
.
5
5
%
8
9
.
2
2
%
+
/
-
4
.
2
1
%
48
48
48
9
1
.
8
2
%
+
/
-
3
.
2
9
%
8
8
.
5
0
%
+
/
-
5
.
8
4
%
8
7
.
7
4
%
+
/
-
5
.
8
6
%
T
ab
le
3
.
Per
f
o
r
m
an
ce
o
f
th
e
test
in
g
p
r
o
ce
s
s
with
m
o
d
if
ied
co
n
f
ig
u
r
atio
n
Tr
a
i
n
i
n
g
c
y
c
l
e
s
N
u
mb
e
r
o
f
e
n
sem
b
l
e
N
u
mb
e
r
o
f
g
e
n
e
r
a
t
i
o
n
A
c
c
u
r
a
c
y
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
15
15
15
8
7
.
7
4
%
8
8
.
9
2
%
9
0
.
3
6
%
20
20
20
8
8
.
3
9
%
8
6
.
1
2
%
8
7
.
1
5
%
25
25
25
9
4
.
5
2
%
9
4
.
2
2
%
9
3
.
5
0
%
30
30
30
9
2
.
9
0
%
9
4
.
4
1
%
9
4
.
2
0
%
35
35
35
9
0
.
9
7
%
8
9
.
7
1
%
9
2
.
9
3
%
40
40
40
9
1
.
2
9
%
9
2
.
1
0
%
9
2
.
2
3
%
42
42
42
8
8
.
3
9
%
8
9
.
4
6
%
,
9
1
.
3
9
%
44
44
44
9
3
.
8
7
%
9
1
.
2
9
%
9
2
.
3
9
%
45
45
45
9
3
.
8
7
%
9
2
.
7
5
%
9
2
.
7
2
%
46
46
46
9
1
.
9
4
%
9
1
.
1
3
%
9
1
.
4
4
%
47
47
47
8
9
.
0
3
%
8
7
.
0
6
%
9
1
.
9
2
%
48
48
48
8
9
.
6
8
%
8
7
.
5
9
%
9
0
.
4
8
%
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
7
,
No
.
1
,
J
an
u
ar
y
20
2
5
:
54
0
-
55
0
548
B
ased
o
n
th
e
ca
lcu
latio
n
s
,
th
e
b
est
ac
cu
r
ac
y
v
alu
e
f
o
r
t
h
e
MLP
alg
o
r
ith
m
was
9
0
.
4
3
%
+/
-
3
.
3
5
%
in
th
e
tr
ain
in
g
p
r
o
ce
s
s
an
d
9
3
.
8
7
%
in
th
e
test
in
g
p
r
o
ce
s
s
.
T
h
is
v
alu
e
was
ac
h
iev
ed
b
y
s
ettin
g
th
e
t
r
ain
in
g
cy
cle
co
n
f
ig
u
r
atio
n
,
n
u
m
b
er
o
f
en
s
em
b
les,
an
d
n
u
m
b
er
o
f
g
en
e
r
atio
n
s
to
4
5
.
At
th
is
f
ig
u
r
e,
th
e
p
r
ec
is
io
n
was
8
7
.
8
1
%
+/
-
6
.
8
3
%
f
o
r
t
r
ain
in
g
an
d
9
2
.
7
5
%
f
o
r
test
in
g
,
wh
ile
th
e
r
ec
all
was 8
7
.
3
4
%
+/
-
5
.
6
8
%
f
o
r
th
e
tr
ai
n
in
g
p
r
o
ce
s
s
an
d
9
2
.
7
2
%
f
o
r
tr
ain
i
n
g
.
Alth
o
u
g
h
test
in
g
was
co
n
d
u
cted
u
n
til
th
e
th
r
ee
p
ar
a
m
eter
s
r
ea
ch
ed
4
8
,
th
er
e
was
a
r
is
k
o
f
o
v
er
f
itti
n
g
.
T
h
i
s
is
ev
id
en
t
f
r
o
m
th
e
in
cr
ea
s
i
n
g
ly
s
ig
n
if
ica
n
t
d
is
cr
ep
an
cy
i
n
ac
cu
r
ac
y
s
co
r
es
b
etwe
en
th
e
tr
ain
i
n
g
a
n
d
test
in
g
p
r
o
ce
s
s
es,
in
d
icatin
g
th
at
th
e
test
in
g
m
eth
o
d
is
o
v
e
r
ly
r
elian
t
o
n
a
s
in
g
le
m
o
d
el.
B
y
in
cr
ea
s
in
g
th
e
tr
ain
in
g
cy
cle
v
alu
e,
th
e
n
u
m
b
er
o
f
en
s
em
b
les,
an
d
th
e
n
u
m
b
e
r
o
f
g
e
n
er
atio
n
s
th
at
af
f
ec
t
th
e
lev
el
o
f
lear
n
in
g
ca
r
r
ied
o
u
t
b
y
th
e
alg
o
r
ith
m
,
it
s
h
o
ws
th
at
its
p
er
f
o
r
m
an
ce
is
g
ettin
g
b
etter
,
wh
er
e
p
r
ev
io
u
s
ly
th
e
ac
cu
r
ac
y
v
alu
e
o
b
tain
ed
was
8
7
.
7
9
%
+/
-
3
.
3
4
%
f
o
r
th
e
lear
n
in
g
p
r
o
ce
s
s
an
d
8
5
.
1
6
%
f
o
r
th
e
test
in
g
p
r
o
ce
s
s
.
I
n
a
d
d
itio
n
t
o
in
cr
ea
s
in
g
p
er
f
o
r
m
an
ce
,
in
cr
ea
s
in
g
th
e
v
al
u
e
o
f
th
e
th
r
ee
p
ar
am
eter
s
also
af
f
ec
ts
th
e
n
u
m
b
er
o
f
n
eu
r
o
n
s
in
th
e
h
id
d
e
n
lay
e
r
u
s
ed
in
d
ata
p
r
o
ce
s
s
in
g
,
if
p
r
e
v
io
u
s
ly
in
th
e
d
ef
a
u
lt
p
ar
am
eter
s
,
th
e
n
u
m
b
e
r
o
f
n
eu
r
o
n
s
u
s
ed
was
4
3
u
n
its
,
th
en
af
te
r
th
e
v
alu
e
o
f
th
e
th
r
ee
p
ar
am
eter
s
was
in
cr
ea
s
ed
to
r
ea
ch
th
e
b
est
v
alu
e
o
f
4
5
,
th
e
n
u
m
b
er
o
f
n
eu
r
o
n
s
u
s
ed
b
ec
a
m
e
1
4
5
u
n
i
ts
.
T
h
e
in
cr
ea
s
e
i
n
p
er
f
o
r
m
an
ce
,
esp
ec
ially
o
n
th
e
ac
cu
r
ac
y
s
id
e,
f
in
ally
h
ad
an
im
p
ac
t
o
n
r
ed
u
cin
g
th
e
n
u
m
b
er
o
f
in
co
r
r
ec
t
d
ata
in
th
e
class
if
icatio
n
p
r
o
ce
s
s
.
I
f
in
th
e
in
itial
test
with
th
e
d
ef
au
lt
p
ar
am
eter
s
th
e
n
u
m
b
er
o
f
in
co
r
r
ec
t
d
ata
was
4
6
d
ata,
t
h
en
at
t
h
e
b
est
ac
cu
r
ac
y
v
alu
e,
th
e
n
u
m
b
er
o
f
in
co
r
r
ec
t
d
ata
d
r
o
p
p
e
d
to
1
9
d
ata.
T
h
e
wr
o
n
g
p
r
ed
ictio
n
d
ata
s
n
ip
p
et
ca
n
b
e
s
ee
n
in
Fig
u
r
e
1
0
.
Fig
u
r
e
10
.
I
n
co
r
r
ec
t d
ata
s
n
ip
p
ets in
th
e
d
ata
p
r
o
ce
s
s
in
g
p
r
o
ce
s
s
u
s
in
g
MLP
with
m
o
d
if
ied
p
ar
am
eter
s
4.
CO
NCLU
SI
O
N
T
h
e
p
u
r
p
o
s
e
o
f
th
is
s
tu
d
y
was
to
test
wh
eth
er
th
e
MLP
alg
o
r
ith
m
is
ca
p
ab
le
o
f
class
if
y
in
g
wea
th
er
co
n
d
itio
n
s
with
a
h
ig
h
lev
el
o
f
ac
cu
r
ac
y
an
d
a
lo
w
e
r
r
o
r
r
ate.
T
h
r
o
u
g
h
th
e
test
s
th
at
h
av
e
b
ee
n
ca
r
r
ie
d
o
u
t
a
n
d
b
ased
o
n
th
e
p
er
f
o
r
m
an
ce
v
alu
es
o
b
tain
ed
,
it
ca
n
b
e
co
n
clu
d
ed
th
at
th
e
MLP
alg
o
r
i
th
m
is
ca
p
ab
le
o
f
c
lass
if
y
in
g
wea
th
er
with
a
f
air
ly
h
ig
h
lev
el
o
f
ac
cu
r
ac
y
,
wh
ich
is
9
3
.
8
7
%
in
th
e
test
in
g
p
r
o
ce
s
s
.
T
h
is
te
s
t
al
s
o
s
h
o
ws
th
at
ch
an
g
in
g
th
e
t
r
ain
in
g
cy
cles,
n
u
m
b
er
o
f
g
en
e
r
a
tio
n
s
,
an
d
n
u
m
b
er
o
f
en
s
em
b
le
p
ar
am
eter
s
t
h
at
af
f
ec
t
th
e
lear
n
in
g
ab
ilit
y
o
f
th
e
MLP
al
g
o
r
ith
m
will
s
ig
n
if
ican
tly
in
c
r
ea
s
e
th
e
ac
cu
r
ac
y
o
f
t
h
e
MLP
alg
o
r
ith
m
.
T
h
e
i
n
cr
ea
s
e
in
p
er
f
o
r
m
a
n
ce
h
as
an
im
p
ac
t
o
n
r
ed
u
cin
g
th
e
n
u
m
b
er
o
f
i
n
co
r
r
ec
t
d
ata
in
th
e
class
if
icatio
n
p
r
o
ce
s
s
,
wh
er
e
if
in
th
e
in
itial
tes
t
,
th
e
n
u
m
b
er
o
f
in
co
r
r
ec
t
d
ata
was
4
6
d
ata
in
th
e
test
in
g
p
r
o
ce
s
s
,
th
en
in
th
e
p
r
o
ce
s
s
with
th
e
b
est
lev
el
o
f
ac
cu
r
ac
y
,
th
e
n
u
m
b
e
r
o
f
in
c
o
r
r
ec
t
d
ata
d
r
o
p
p
e
d
to
1
9
d
ata.
Ho
wev
er
,
th
is
in
cr
ea
s
e
also
h
as
lim
itatio
n
s
,
wh
er
e
wh
en
th
e
th
r
ee
p
ar
am
eter
s
ar
e
s
et
to
v
alu
es
th
at
a
r
e
to
h
ig
h
,
th
e
r
esu
ltin
g
p
e
r
f
o
r
m
an
ce
v
alu
es
ten
d
to
ex
p
er
i
en
ce
o
v
e
r
f
itti
n
g
wh
ich
is
m
ar
k
ed
b
y
a
s
tr
ik
in
g
d
if
f
er
en
ce
in
ac
c
u
r
ac
y
v
al
u
e
s
in
th
e
tr
ain
in
g
an
d
test
in
g
p
r
o
ce
s
s
es.
T
h
er
ef
o
r
e,
to
o
b
t
ain
b
etter
ac
cu
r
ac
y
v
alu
es
f
r
o
m
th
is
s
tu
d
y
,
it
is
h
ig
h
ly
r
ec
o
m
m
en
d
ed
to
u
s
e
s
u
p
er
io
r
alg
o
r
i
th
m
s
s
u
ch
a
s
d
ee
p
lear
n
in
g
in
f
u
r
th
er
r
esear
ch
.
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:
2
5
0
2
-
4
7
52
C
la
s
s
i
fica
tio
n
o
f wea
th
er c
o
n
d
itio
n
s
b
a
s
ed
o
n
a
u
to
ma
tic
w
ea
th
er
…
(
Mu
h
a
mma
d
A
r
is
to
I
n
d
r
a
ja
ya
)
549
RE
F
E
R
E
NC
E
S
[
1
]
C
.
F
a
n
g
,
C
.
L
v
,
F
.
C
a
i
,
H
.
L
i
u
,
J.
W
a
n
g
,
a
n
d
M
.
S
h
u
a
i
,
“
W
e
a
t
h
e
r
c
l
a
ssi
f
i
c
a
t
i
o
n
f
o
r
o
u
t
d
o
o
r
p
o
w
e
r
m
o
n
i
t
o
r
i
n
g
b
a
sed
o
n
i
m
p
r
o
v
e
d
S
q
u
e
e
z
e
N
e
t
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
-
2
0
2
0
5
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
I
n
f
o
rm
a
t
i
o
n
S
c
i
e
n
c
e
,
C
o
m
p
u
t
e
r
T
e
c
h
n
o
l
o
g
y
a
n
d
T
ra
n
s
p
o
rt
a
t
i
o
n
,
I
S
C
T
T
2
0
2
0
,
N
o
v
.
2
0
2
0
,
p
p
.
1
1
–
1
5
,
d
o
i
:
1
0
.
1
1
0
9
/
I
S
C
TT
5
1
5
9
5
.
2
0
2
0
.
0
0
0
0
9
.
[
2
]
R
.
K
u
m
a
r
,
“
F
u
z
z
y
i
n
t
e
n
si
v
e
d
e
c
i
s
i
o
n
f
u
n
c
t
i
o
n
-
b
a
se
d
w
e
a
t
h
e
r
p
r
e
d
i
c
t
i
o
n
u
si
n
g
m
u
l
t
i
-
p
e
r
c
e
p
t
i
o
n
n
e
u
r
a
l
c
l
a
s
si
f
i
c
a
t
i
o
n
f
o
r
su
c
c
e
ss
i
v
e
c
r
o
p
r
e
c
o
mm
e
n
d
a
t
i
o
n
i
n
b
i
g
d
a
t
a
a
n
a
l
y
si
s,
”
i
n
2
n
d
I
E
EE
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
D
i
st
r
i
b
u
t
e
d
C
o
m
p
u
t
i
n
g
a
n
d
E
l
e
c
t
ri
c
a
l
C
i
rc
u
i
t
s
a
n
d
E
l
e
c
t
r
o
n
i
c
s,
I
C
D
C
EC
E
2
0
2
3
,
A
p
r
.
2
0
2
3
,
p
p
.
1
–
5
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
D
C
EC
E
5
7
8
6
6
.
2
0
2
3
.
1
0
1
5
0
6
2
5
.
[
3
]
M
.
T
i
a
n
,
X
.
C
h
e
n
,
H
.
Zh
a
n
g
,
P
.
Z
h
a
n
g
,
K
.
C
a
o
,
a
n
d
R
.
W
a
n
g
,
“
W
e
a
t
h
e
r
c
l
a
ssi
f
i
c
a
t
i
o
n
me
t
h
o
d
b
a
se
d
o
n
s
p
i
k
i
n
g
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
i
n
2
0
2
1
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
D
i
g
i
t
a
l
S
o
c
i
e
t
y
a
n
d
I
n
t
e
l
l
i
g
e
n
t
S
y
st
e
m
s,
D
S
I
n
S
2
0
2
1
,
D
e
c
.
2
0
2
1
,
p
p
.
1
3
4
–
1
3
7
,
d
o
i
:
1
0
.
1
1
0
9
/
D
S
I
n
S
5
4
3
9
6
.
2
0
2
1
.
9
6
7
0
5
5
7
.
[
4
]
R
.
M
e
e
n
a
l
,
K
.
K
a
i
l
a
sh
,
P
.
A
.
M
i
c
h
a
e
l
,
J.
J.
Jo
s
e
p
h
,
F
.
T.
Jo
s
h
,
a
n
d
E.
R
a
j
a
se
k
a
r
a
n
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
b
a
s
e
d
smar
t
w
e
a
t
h
e
r
p
r
e
d
i
c
t
i
o
n
,
”
I
n
d
o
n
e
si
a
n
J
o
u
r
n
a
l
o
f
E
l
e
c
t
ri
c
a
l
E
n
g
i
n
e
e
ri
n
g
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
(
I
J
EE
C
S
)
,
v
o
l
.
2
8
,
n
o
.
1
,
p
p
.
5
0
8
–
5
1
5
,
O
c
t
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s.
v
2
8
.
i
1
.
p
p
5
0
8
-
5
1
5
.
[
5
]
R
.
M
e
e
n
a
l
,
P
.
A
.
M
i
c
h
a
e
l
,
D
.
P
a
m
e
l
a
,
a
n
d
E.
R
a
j
a
se
k
a
r
a
n
,
“
W
e
a
t
h
e
r
p
r
e
d
i
c
t
i
o
n
u
s
i
n
g
r
a
n
d
o
m
f
o
r
e
s
t
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
m
o
d
e
l
,
”
I
n
d
o
n
e
si
a
n
J
o
u
r
n
a
l
o
f
E
l
e
c
t
r
i
c
a
l
E
n
g
i
n
e
e
ri
n
g
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
(
I
J
EEC
S
)
,
v
o
l
.
2
2
,
n
o
.
2
,
p
p
.
1
2
0
8
–
1
2
1
5
,
M
a
y
2
0
2
1
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s
.
v
2
2
.
i
2
.
p
p
1
2
0
8
-
1
2
1
5
.
[
6
]
N
.
B
o
g
d
a
n
o
v
s
,
V
.
B
i
st
r
o
v
s,
E
.
P
e
t
e
r
so
n
s
,
A
.
I
p
a
t
o
v
s,
a
n
d
R
.
B
e
l
i
n
sk
i
s,
“
W
e
a
t
h
e
r
p
r
e
d
i
c
t
i
o
n
a
l
g
o
r
i
t
h
m
b
a
se
d
o
n
h
i
st
o
r
i
c
a
l
d
a
t
a
u
si
n
g
K
a
l
ma
n
f
i
l
t
e
r
,
”
i
n
Pro
c
e
e
d
i
n
g
s
-
2
0
1
8
A
d
v
a
n
c
e
s
i
n
W
i
re
l
e
ss
a
n
d
O
p
t
i
c
a
l
C
o
m
m
u
n
i
c
a
t
i
o
n
s
,
RTU
WO
2
0
1
8
,
N
o
v
.
2
0
1
8
,
p
p
.
9
4
–
9
9
,
d
o
i
:
1
0
.
1
1
0
9
/
R
TU
W
O
.
2
0
1
8
.
8
5
8
7
7
9
5
.
[
7
]
Q
.
F
u
,
D
.
N
i
u
,
Z
.
Z
a
n
g
,
J.
H
u
a
n
g
,
a
n
d
L.
D
i
a
o
,
“
M
u
l
t
i
-
st
a
t
i
o
n
s
’
w
e
a
t
h
e
r
p
r
e
d
i
c
t
i
o
n
b
a
s
e
d
o
n
h
y
b
r
i
d
mo
d
e
l
u
s
i
n
g
1
D
C
N
N
a
n
d
B
i
-
LSTM
,
”
i
n
C
h
i
n
e
se
C
o
n
t
ro
l
C
o
n
f
e
re
n
c
e
,
C
C
C
,
Ju
l
.
2
0
1
9
,
v
o
l
.
2
0
1
9
-
J
u
l
y
,
p
p
.
3
7
7
1
–
3
7
7
5
,
d
o
i
:
1
0
.
2
3
9
1
9
/
C
h
i
C
C
.
2
0
1
9
.
8
8
6
6
4
9
6
.
[
8
]
G
.
M
e
t
i
,
R
.
K
.
G
.
K
r
i
s
h
n
e
g
o
w
d
a
,
a
n
d
G
.
S
.
S
w
a
m
y
,
“
R
a
i
n
f
a
l
l
a
n
a
l
y
si
s
a
n
d
p
r
e
d
i
c
t
i
o
n
u
si
n
g
e
n
s
e
m
b
l
e
l
e
a
r
n
i
n
g
f
o
r
K
a
r
n
a
t
a
k
a
S
t
a
t
e
,
”
I
n
d
o
n
e
si
a
n
J
o
u
r
n
a
l
o
f
E
l
e
c
t
ri
c
a
l
E
n
g
i
n
e
e
r
i
n
g
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
(
I
J
EE
C
S
)
,
v
o
l
.
3
2
,
n
o
.
2
,
p
p
.
1
1
8
7
–
1
1
9
8
,
N
o
v
.
2
0
2
3
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s
.
v
3
2
.
i
2
.
p
p
1
1
8
7
-
1
1
9
8
.
[
9
]
D
.
K
.
S
i
n
g
h
a
n
d
N
.
G
o
e
l
,
“
A
n
a
l
y
s
i
n
g
d
a
t
a
m
i
n
i
n
g
t
e
c
h
n
i
q
u
e
s
o
n
b
a
n
k
c
u
st
o
m
e
r
s
f
o
r
c
r
e
d
i
t
s
c
o
r
e
,
”
i
n
I
C
RI
T
O
2
0
2
0
-
I
EEE
8
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
R
e
l
i
a
b
i
l
i
t
y
,
I
n
f
o
c
o
m
T
e
c
h
n
o
l
o
g
i
e
s
a
n
d
O
p
t
i
m
i
za
t
i
o
n
(
T
ren
d
s
a
n
d
F
u
t
u
re
D
i
re
c
t
i
o
n
s)
,
J
u
n
.
2
0
2
0
,
p
p
.
1
2
9
3
–
12
9
5
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
R
I
TO
4
8
8
7
7
.
2
0
2
0
.
9
1
9
7
9
0
9
.
[
1
0
]
H
.
Er
o
l
,
B
.
M
.
T
y
o
d
e
n
,
a
n
d
R
.
Er
o
l
,
“
C
l
a
ss
i
f
i
c
a
t
i
o
n
p
e
r
f
o
r
ma
n
c
e
s
o
f
d
a
t
a
mi
n
i
n
g
c
l
u
st
e
r
i
n
g
a
l
g
o
r
i
t
h
ms
f
o
r
r
e
mo
t
e
l
y
se
n
se
d
mu
l
t
i
s
p
e
c
t
r
a
l
i
ma
g
e
d
a
t
a
,
”
i
n
2
0
1
8
I
E
EE
(
S
M
C
)
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
I
n
n
o
v
a
t
i
o
n
s
i
n
I
n
t
e
l
l
i
g
e
n
t
S
y
st
e
m
s
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
I
N
I
S
T
A
2
0
1
8
,
Ju
l
.
2
0
1
8
,
p
p
.
1
–
4
,
d
o
i
:
1
0
.
1
1
0
9
/
I
N
I
S
TA
.
2
0
1
8
.
8
4
6
6
3
2
0
.
[
1
1
]
X
.
Z
h
a
o
a
n
d
C
.
W
u
,
“
W
e
a
t
h
e
r
c
l
a
s
si
f
i
c
a
t
i
o
n
b
a
se
d
o
n
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s,”
i
n
Pr
o
c
e
e
d
i
n
g
s
-
2
0
2
1
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
W
i
re
l
e
ss
C
o
m
m
u
n
i
c
a
t
i
o
n
s
a
n
d
S
m
a
r
t
G
r
i
d
,
I
C
W
C
S
G
2
0
2
1
,
A
u
g
.
2
0
2
1
,
p
p
.
2
9
3
–
2
9
6
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
W
C
S
G
5
3
6
0
9
.
2
0
2
1
.
0
0
0
6
4
.
[
1
2
]
S
.
G
o
e
l
,
S
.
M
a
r
k
a
n
d
a
y
,
a
n
d
S
.
M
o
h
a
n
t
y
,
“
A
n
a
l
y
si
s
o
f
mu
l
t
i
-
c
l
a
ss
w
e
a
t
h
e
r
c
l
a
ss
i
f
i
c
a
t
i
o
n
u
si
n
g
d
e
e
p
l
e
a
r
n
i
n
g
m
o
d
e
l
s
a
n
d
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
c
l
a
ss
i
f
i
e
r
s,”
i
n
Pr
o
c
e
e
d
i
n
g
s
-
2
0
2
2
O
I
T
S
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
O
C
I
T
2
0
2
2
,
D
e
c
.
2
0
2
2
,
p
p
.
2
2
3
–
2
2
7
,
d
o
i
:
1
0
.
1
1
0
9
/
O
C
I
T5
6
7
6
3
.
2
0
2
2
.
0
0
0
5
0
.
[
1
3
]
E.
D
r
i
t
sas
,
M
.
Tr
i
g
k
a
,
a
n
d
P
.
M
y
l
o
n
a
s,
“
A
m
u
l
t
i
-
c
l
a
s
s
c
l
a
ssi
f
i
c
a
t
i
o
n
a
p
p
r
o
a
c
h
f
o
r
w
e
a
t
h
e
r
f
o
r
e
c
a
s
t
i
n
g
w
i
t
h
mac
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s,
”
i
n
2
0
2
2
1
7
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
W
o
rks
h
o
p
o
n
S
e
m
a
n
t
i
c
a
n
d
S
o
c
i
a
l
Me
d
i
a
Ad
a
p
t
a
t
i
o
n
a
n
d
P
e
rs
o
n
a
l
i
z
a
t
i
o
n
,
S
MA
P
2
0
2
2
,
N
o
v
.
2
0
2
2
,
p
p
.
1
–
5
,
d
o
i
:
1
0
.
1
1
0
9
/
S
M
A
P
5
6
1
2
5
.
2
0
2
2
.
9
9
4
2
1
2
1
.
[
1
4
]
T.
P
a
w
a
r
,
P
.
K
a
l
r
a
,
a
n
d
D
.
M
e
h
r
o
t
r
a
,
“
A
n
a
l
y
s
i
s
o
f
se
n
t
i
me
n
t
s
f
o
r
sp
o
r
t
s
d
a
t
a
u
s
i
n
g
R
a
p
i
d
M
i
n
e
r
,
”
i
n
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
2
n
d
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
G
r
e
e
n
C
o
m
p
u
t
i
n
g
a
n
d
I
n
t
e
r
n
e
t
o
f
T
h
i
n
g
s,
I
C
G
C
I
o
T
2
0
1
8
,
A
u
g
.
2
0
1
8
,
p
p
.
6
2
5
–
6
2
8
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
G
C
I
o
T.
2
0
1
8
.
8
7
5
2
9
8
9
.
[
1
5
]
A
.
D
.
N
o
v
i
k
a
a
n
d
A
.
S
.
G
i
r
sa
n
g
,
“
M
u
l
t
i
-
l
a
y
e
r
p
e
r
c
e
p
t
r
o
n
h
y
p
e
r
p
a
r
a
met
e
r
o
p
t
i
mi
z
a
t
i
o
n
u
si
n
g
Ja
y
a
a
l
g
o
r
i
t
h
m
f
o
r
d
i
se
a
se
c
l
a
ss
i
f
i
c
a
t
i
o
n
,
”
I
n
d
o
n
e
s
i
a
n
J
o
u
rn
a
l
o
f
El
e
c
t
r
i
c
a
l
En
g
i
n
e
e
r
i
n
g
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
(
I
J
EE
C
S
)
,
v
o
l
.
3
5
,
n
o
.
1
,
p
p
.
6
2
0
–
6
3
0
,
J
u
l
.
2
0
2
4
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s.
v
3
5
.
i
1
.
p
p
6
2
0
-
6
3
0
.
[
1
6
]
M
.
Ta
m
u
l
i
o
n
i
s
a
n
d
A
.
S
e
r
a
c
k
i
s,
“
C
o
mp
a
r
i
so
n
o
f
m
u
l
t
i
-
l
a
y
e
r
p
e
r
c
e
p
t
r
o
n
a
n
d
c
a
sc
a
d
e
f
e
e
d
-
f
o
r
w
a
r
d
n
e
u
r
a
l
n
e
t
w
o
r
k
f
o
r
h
e
a
d
-
r
e
l
a
t
e
d
t
r
a
n
sf
e
r
f
u
n
c
t
i
o
n
i
n
t
e
r
p
o
l
a
t
i
o
n
,
”
i
n
2
0
1
9
O
p
e
n
C
o
n
f
e
re
n
c
e
o
f
E
l
e
c
t
r
i
c
a
l
,
El
e
c
t
r
o
n
i
c
a
n
d
I
n
f
o
rm
a
t
i
o
n
S
c
i
e
n
c
e
s,
e
S
t
re
a
m
2
0
1
9
-
Pro
c
e
e
d
i
n
g
s
,
A
p
r
.
2
0
1
9
,
p
p
.
1
–
4
,
d
o
i
:
1
0
.
1
1
0
9
/
e
S
t
r
e
a
m.
2
0
1
9
.
8
7
3
2
1
5
8
.
[
1
7
]
H
.
C
a
i
a
n
d
X
.
W
a
n
g
,
“
S
t
e
a
d
y
-
st
a
t
e
t
o
r
q
u
e
p
r
e
d
i
c
t
i
o
n
o
f
i
n
v
e
r
t
e
r
-
f
e
d
i
n
d
u
c
t
i
o
n
ma
c
h
i
n
e
b
a
se
d
o
n
mu
l
t
i
-
l
a
y
e
r
p
e
r
c
e
p
t
r
o
n
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
i
n
2
0
2
3
I
EEE
En
e
r
g
y
C
o
n
v
e
rsi
o
n
C
o
n
g
ress
a
n
d
Ex
p
o
si
t
i
o
n
,
EC
C
E
2
0
2
3
,
O
c
t
.
2
0
2
3
,
p
p
.
3
8
0
2
–
3
8
0
9
,
d
o
i
:
1
0
.
1
1
0
9
/
EC
C
E
5
3
6
1
7
.
2
0
2
3
.
1
0
3
6
2
1
9
1
.
[
1
8
]
S
.
Je
n
a
,
D
.
P
.
M
i
s
h
r
a
,
a
n
d
S
.
M
i
s
h
r
a
,
“
D
e
t
e
c
t
i
o
n
a
n
d
c
l
a
ss
i
f
i
c
a
t
i
o
n
o
f
p
e
r
man
e
n
t
f
a
u
l
t
u
s
i
n
g
mu
l
t
i
-
l
a
y
e
r
p
e
r
c
e
p
t
r
o
n
m
o
d
e
l
i
n
a
d
i
s
t
r
i
b
u
t
i
o
n
n
e
t
w
o
r
k
,
”
i
n
2
0
2
3
I
EEE
3
rd
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
S
m
a
r
t
T
e
c
h
n
o
l
o
g
i
e
s f
o
r
Po
w
e
r
,
E
n
e
r
g
y
a
n
d
C
o
n
t
r
o
l
,
S
T
PE
C
2
0
2
3
,
D
e
c
.
2
0
2
3
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
S
TP
EC
5
9
2
5
3
.
2
0
2
3
.
1
0
4
3
1
0
4
8
.
[
1
9
]
X
.
X
u
,
S
.
L.
K
e
o
h
,
C
.
K
.
S
e
o
w
,
Q
.
C
a
o
,
a
n
d
S
.
K
.
B
i
n
A
b
d
u
l
R
a
h
i
m
,
“
T
o
w
a
r
d
s
p
r
e
d
i
c
t
i
o
n
o
f
b
u
s
a
r
r
i
v
a
l
t
i
m
e
u
si
n
g
mu
l
t
i
-
l
a
y
e
r
p
e
r
c
e
p
t
r
o
n
(
M
LP)
a
n
d
M
LP
r
e
g
r
e
ss
o
r
,
”
i
n
2
0
2
3
8
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
B
u
si
n
e
ss
a
n
d
I
n
d
u
st
r
i
a
l
Re
s
e
a
r
c
h
,
I
C
BI
R
2
0
2
3
-
Pro
c
e
e
d
i
n
g
s
,
M
a
y
2
0
2
3
,
p
p
.
6
6
9
–
6
7
4
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
B
I
R
5
7
5
7
1
.
2
0
2
3
.
1
0
1
4
7
6
1
4
.
[
2
0
]
A
.
S
a
d
i
q
a
n
d
N
.
Y
a
h
y
a
,
“
F
r
a
c
t
i
o
n
a
l
st
o
c
h
a
s
t
i
c
g
r
a
d
i
e
n
t
d
e
s
c
e
n
t
b
a
s
e
d
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
m
f
o
r
mu
l
t
i
-
l
a
y
e
r
p
e
r
c
e
p
t
r
o
n
n
e
u
r
a
l
n
e
t
w
o
r
k
s,”
i
n
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
I
n
t
e
l
l
i
g
e
n
t
a
n
d
A
d
v
a
n
c
e
d
S
y
s
t
e
m
s:
En
h
a
n
c
e
t
h
e
Pre
s
e
n
t
f
o
r
a
S
u
st
a
i
n
a
b
l
e
Fu
t
u
re,
I
C
I
AS
2
0
2
1
,
Ju
l
.
2
0
2
1
,
p
p
.
1
–
4
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
I
A
S
4
9
4
1
4
.
2
0
2
1
.
9
6
4
2
6
8
7
.
[
2
1
]
H
.
Y
a
n
g
,
“
Tr
a
n
s
mi
ss
i
o
n
l
i
n
e
f
a
u
l
t
d
e
t
e
c
t
i
o
n
b
a
se
d
o
n
m
u
l
t
i
-
l
a
y
e
r
p
e
r
c
e
p
t
r
o
n
,
”
i
n
P
ro
c
e
e
d
i
n
g
s
-
2
0
2
2
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
Bi
g
D
a
t
a
,
I
n
f
o
rm
a
t
i
o
n
a
n
d
C
o
m
p
u
t
e
r
N
e
t
w
o
rk,
BD
I
C
N
2
0
2
2
,
J
a
n
.
2
0
2
2
,
p
p
.
7
7
8
–
7
8
1
,
d
o
i
:
1
0
.
1
1
0
9
/
B
D
I
C
N
5
5
5
7
5
.
2
0
2
2
.
0
0
1
5
1
.
[
2
2
]
J.
S
a
t
h
y
a
a
n
d
F
.
M
a
r
y
H
a
r
i
n
F
e
r
n
a
n
d
e
z
,
“
C
r
i
m
e
d
e
t
e
c
t
i
o
n
u
s
i
n
g
mu
l
t
i
-
l
a
y
e
r
p
e
r
c
e
p
t
r
o
n
i
n
s
o
c
i
a
l
me
d
i
a
p
l
a
t
f
o
r
m
s,”
i
n
1
2
t
h
I
E
EE
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
A
d
v
a
n
c
e
d
C
o
m
p
u
t
i
n
g
,
I
C
o
AC
2
0
2
3
,
A
u
g
.
2
0
2
3
,
p
p
.
1
–
8
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
o
A
C
5
9
5
3
7
.
2
0
2
3
.
1
0
2
5
0
0
1
4
.
[
2
3
]
M
.
L.
A
l
l
o
k
e
n
d
e
k
a
n
d
E.
El
l
i
s
a
,
“
R
e
c
o
n
d
i
t
i
o
n
i
n
g
t
h
e
r
e
si
l
i
e
n
c
e
o
f
P
a
l
u
c
i
t
y
w
i
t
h
i
n
t
h
e
n
a
t
u
r
a
l
d
i
sas
t
e
r
st
o
r
i
e
s,”
I
O
P
C
o
n
f
e
r
e
n
c
e
S
e
r
i
e
s:
E
a
r
t
h
a
n
d
E
n
v
i
r
o
n
m
e
n
t
a
l
S
c
i
e
n
c
e
,
v
o
l
.
1
0
8
2
,
n
o
.
1
,
p
.
0
1
2
0
2
0
,
S
e
p
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
8
8
/
1
7
5
5
-
1
3
1
5
/
1
0
8
2
/
1
/
0
1
2
0
2
0
.
[
2
4
]
M
e
t
e
o
r
o
l
o
g
i
c
a
l
S
e
r
v
i
c
e
o
f
C
a
n
a
d
a
,
“
M
A
N
O
B
S
-
m
a
n
u
a
l
o
f
s
u
r
f
a
c
e
w
e
a
t
h
e
r
o
b
ser
v
a
t
i
o
n
s,”
p
.
4
7
5
,
2
0
1
5
.
[
2
5
]
L.
A
n
d
r
a
d
e
-
A
r
e
n
a
s
,
I
.
R
u
b
i
o
-
P
a
u
c
a
r
,
a
n
d
C
.
Y
a
c
t
a
y
o
-
A
r
i
a
s,
“
P
r
e
d
i
c
t
i
v
e
mo
d
e
l
s
i
n
A
l
z
h
e
i
mer
’
s
d
i
se
a
se
:
a
n
e
v
a
l
u
a
t
i
o
n
b
a
s
e
d
o
n
d
a
t
a
mi
n
i
n
g
t
e
c
h
n
i
q
u
e
s
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
E
l
e
c
t
ri
c
a
l
a
n
d
C
o
m
p
u
t
e
r
E
n
g
i
n
e
e
r
i
n
g
(
I
J
E
C
E)
,
v
o
l
.
1
4
,
n
o
.
3
,
p
p
.
2
9
8
8
–
300
2
,
Ju
n
.
2
0
2
4
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
c
e
.
v
1
4
i
3
.
p
p
2
9
8
8
-
3
0
0
2
.
[
2
6
]
K
.
M
n
i
c
h
,
A
.
P
o
l
e
w
k
o
-
K
l
i
m,
A
.
K
.
G
o
l
i
n
s
k
a
,
W
.
L
e
si
n
s
k
i
,
a
n
d
W
.
R
.
R
u
d
n
i
c
k
i
,
“
S
u
p
e
r
l
e
a
r
n
i
n
g
w
i
t
h
r
e
p
e
a
t
e
d
c
r
o
s
s
v
a
l
i
d
a
t
i
o
n
,
”
i
n
I
EEE
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
D
a
t
a
Mi
n
i
n
g
W
o
r
k
sh
o
p
s,
I
C
D
M
W
,
N
o
v
.
2
0
2
0
,
v
o
l
.
2
0
2
0
-
N
o
v
e
mb
e
r
,
p
p
.
6
2
9
–
6
3
5
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
D
M
W
5
1
3
1
3
.
2
0
2
0
.
0
0
0
8
9
.
Evaluation Warning : The document was created with Spire.PDF for Python.