I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
pu
t
er
Science
Vo
l.
24
,
No
.
3
,
Dec
em
b
er
2
0
2
1
,
p
p
.
1
4
0
5
~
1
4
1
3
I
SS
N:
2
5
0
2
-
4
7
5
2
,
DOI
: 1
0
.
1
1
5
9
1
/ijeecs.v
24
.i
3
.
pp
1
4
0
5
-
1
4
1
3
1405
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs.ia
esco
r
e.
co
m
Dista
nt
temperat
ure and h
umidity
mo
nitoring
:
p
red
iction a
nd
mea
surem
ent
F
a
rr
uk
h H
a
f
ee
z
1
,
Usm
a
n Ulla
h
Sh
eik
h
2
,
At
t
a
ull
a
h K
hid
r
a
ni
3
,
M
uh
a
m
m
a
d Ak
ra
m
B
ha
y
o
4
,
Sa
leh Ma
s
o
ud
Abda
lla
h Alt
ba
wi
5
,
T
o
uq
ee
r
Ahm
ed
J
um
a
ni
6
1
,
2,
5
S
c
h
o
o
l
o
f
El
e
c
tri
c
a
l
En
g
in
e
e
ri
n
g
,
U
n
iv
e
rsit
i
Tek
n
o
l
o
g
i
M
a
lay
si
a
,
Jo
h
o
r
,
M
a
lay
sia
3
F
a
c
u
lt
y
o
f
El
e
c
tri
c
a
l
E
n
g
i
n
e
e
rin
g
,
Ba
lo
c
h
istan
Un
i
v
e
rsity
o
f
E
n
g
i
n
e
e
rin
g
a
n
d
Tec
h
n
o
l
o
g
y
,
Kh
u
z
d
a
r,
P
a
k
istan
4
De
p
a
rtme
n
t
o
f
El
e
c
tri
c
a
l
E
n
g
i
n
e
e
rin
g
,
Q
u
a
id
-
e
-
Aw
a
m
Un
iv
e
rsity
o
f
E
n
g
i
n
e
e
rin
g
,
S
c
ien
c
e
a
n
d
Tec
h
n
o
l
o
g
y
,
Na
wa
b
sh
a
h
,
P
a
k
istan
6
De
p
a
rtme
n
t
o
f
El
e
c
tri
c
a
l
E
n
g
i
n
e
e
rin
g
,
M
e
h
ra
n
U
n
iv
e
rsit
y
o
f
En
g
i
n
e
e
ri
n
g
a
n
d
Tec
h
n
o
lo
g
y
,
Kh
a
irp
u
r,
P
a
k
istan
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
n
5
,
2021
R
ev
is
ed
Oct
14
,
2
0
2
1
Acc
ep
ted
Oct
27
,
2
0
2
1
S
e
n
sin
g
e
n
v
iro
n
m
e
n
tal
m
e
a
su
rin
g
p
a
ra
m
e
ters
h
a
s
a
p
iv
o
tal
r
o
le
in
o
u
r
e
v
e
ry
d
a
y
l
iv
e
s.
M
o
st
o
f
o
u
r
d
a
il
y
li
fe
a
c
ti
v
it
ies
d
e
p
e
n
d
u
p
o
n
e
n
v
iro
n
m
e
n
tal
c
o
n
d
i
ti
o
n
s.
Ac
c
u
ra
te
i
n
fo
rm
a
ti
o
n
a
b
o
u
t
th
e
se
p
a
ra
m
e
ters
a
lso
h
e
lp
s
in
se
v
e
ra
l
in
d
u
stria
l
a
p
p
li
c
a
ti
o
n
s
l
ik
e
v
e
n
ti
latio
n
ra
te
c
a
lcu
latio
n
,
e
n
e
r
g
y
p
re
d
ictio
n
,
sto
c
k
m
a
in
ten
a
n
c
e
i
n
wa
re
h
o
u
se
s,
a
n
d
sa
v
in
g
fro
m
h
a
rm
fu
l
c
o
n
d
it
io
n
s.
Th
e
e
m
e
rg
e
n
c
e
o
f
m
a
c
h
in
e
lea
rn
i
n
g
c
a
n
m
a
k
e
it
e
a
sy
to
p
re
d
ict
su
c
h
t
ime
se
ries
p
ro
b
lem
s.
Th
is
p
a
p
e
r
d
e
sc
rib
e
s
t
h
e
d
e
si
g
n
o
f
a
re
m
o
tel
y
c
o
n
tro
ll
e
d
ro
b
o
ti
c
c
a
r
fo
r
m
e
a
su
rin
g
a
n
d
p
re
d
icti
n
g
h
u
m
id
it
y
a
n
d
tem
p
e
ra
tu
re
.
A
c
u
sto
m
ize
d
a
p
p
f
o
r
a
c
c
e
ss
in
g
t
h
e
ro
b
o
ti
c
c
a
r
is
d
e
sig
n
e
d
to
in
d
ica
te
p
re
d
icte
d
a
n
d
re
a
l
-
ti
m
e
m
e
a
su
re
d
v
a
lu
e
s
o
f
h
u
m
id
it
y
a
n
d
tem
p
e
ra
tu
re
.
A
se
n
so
r
i
n
st
a
ll
e
d
b
u
ilt
-
in
h
e
lp
s
in
th
e
m
e
a
su
re
m
e
n
t.
Th
e
re
c
u
rre
n
t
n
e
u
ra
l
n
e
two
rk
(RNN
)
m
o
d
e
l
is
u
se
d
t
o
p
re
d
ict
h
u
m
i
d
it
y
a
n
d
tem
p
e
ra
tu
re
.
F
o
r
th
is
p
u
rp
o
se
,
e
x
p
e
rime
n
ts
a
re
c
a
rried
o
u
t
in
b
o
t
h
o
u
t
d
o
o
r
a
n
d
i
n
d
o
o
r
se
tt
in
g
s.
Ac
c
u
ra
c
y
o
f
8
5
%
a
n
d
9
0
%
is
a
c
h
iev
e
d
in
a
n
o
u
t
d
o
o
r
e
n
v
i
ro
n
m
e
n
t
a
n
d
in
d
o
o
r
se
tt
in
g
s.
K
ey
w
o
r
d
s
:
An
d
r
o
id
a
p
p
R
ec
u
r
r
en
t n
eu
r
al
n
etwo
r
k
R
em
o
te
s
en
s
in
g
R
o
b
o
tic
ca
r
Sen
s
o
r
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
:
Far
r
u
k
h
Haf
ee
z
S
ch
o
o
l o
f
E
lectr
ical
E
n
g
in
ee
r
in
g
Un
iv
er
s
iti T
ek
n
o
lo
g
i M
ala
y
s
ia
8
1
3
1
0
Sk
u
d
ai,
J
o
h
o
r
B
ah
r
u
,
J
o
h
o
r
-
Ma
la
y
s
ia
E
m
ail:
h
af
ee
z@
g
r
ad
u
ate.
u
tm
.
m
y
1.
I
NT
RO
D
UCT
I
O
N
I
n
th
e
last
d
ec
ad
e
,
ar
tific
ial
i
n
tellig
en
ce
-
b
ased
tec
h
n
iq
u
es
d
ev
elo
p
m
e
n
t
h
a
d
a
g
r
ea
t
im
p
ac
t
o
n
all
f
ield
s
.
Ma
ch
in
e
lea
r
n
in
g
alg
o
r
ith
m
s
ar
e
b
ased
o
n
in
v
esti
g
atin
g
p
atter
n
s
,
d
ata,
an
d
tr
e
n
d
s
th
at
p
r
o
d
u
ce
d
p
r
o
m
is
in
g
r
esu
lts
in
th
e
f
i
eld
s
o
f
lan
g
u
ag
e
p
r
o
ce
s
s
in
g
,
p
r
e
d
ictio
n
s
,
s
elf
-
d
r
iv
i
n
g
ca
r
,
h
ea
lth
ca
r
e,
class
if
icatio
n
s
,
an
d
s
u
r
v
eillan
ce
s
y
s
tem
s
[
1
]
-
[
4
]
.
Po
p
u
lar
s
ea
r
ch
en
g
in
es
lik
e
Yo
u
tu
b
e
,
Go
o
g
le,
an
d
s
o
cial
m
ed
ia
s
ites
,
s
u
ch
as
I
n
s
tag
r
a
m
,
T
witter
,
an
d
Face
b
o
o
k
o
wn
th
eir
s
p
ec
if
ic
lear
n
i
n
g
to
o
ls
[
5
]
-
[
7
]
.
W
ea
th
er
f
o
r
ec
asti
n
g
,
ea
r
th
q
u
a
k
e
p
r
ed
ic
tio
n
s
,
r
ain
e
x
p
ec
tatio
n
s
h
a
v
e
a
ls
o
b
ee
n
e
x
p
l
o
r
e
d
in
th
e
m
etr
o
lo
g
y
f
ield
[
8
]
-
[
1
3
]
.
I
n
ter
n
et
o
f
t
h
in
g
s
(
I
o
T
)
is
an
o
th
er
wid
ely
u
s
e
d
tec
h
n
o
lo
g
y
a
r
o
u
n
d
th
e
g
lo
b
e.
Acc
o
r
d
in
g
t
o
s
o
m
e
an
al
y
s
ts
,
th
e
I
o
T
r
e
v
o
lu
tio
n
is
m
u
c
h
s
ig
n
i
f
ican
t
th
an
th
e
i
n
d
u
s
tr
ial
r
ev
o
lu
tio
n
.
So
m
e
o
f
its
ap
p
licat
io
n
in
clu
d
es
Sm
ar
t
h
o
m
es,
b
an
k
in
g
,
r
etails,
h
ea
lth
ca
r
e,
ag
r
icu
ltu
r
e,
a
n
d
in
d
u
s
tr
ies.
I
o
T
d
ev
elo
p
m
en
t
was
m
o
r
e
p
r
o
m
in
en
t
i
n
r
ec
en
t y
ea
r
s
.
Ho
wev
er
,
h
ig
h
-
s
p
ee
d
an
d
af
f
o
r
d
ab
le
s
m
ar
tp
h
o
n
es a
r
e
o
n
e
o
f
th
e
cr
u
cial
f
ac
t
o
r
s
.
I
o
T
ap
p
licatio
n
s
ca
n
b
e
ea
s
ily
ass
ess
ed
b
y
m
o
b
ile
p
h
o
n
e
ap
p
s
th
an
we
b
ap
p
s
.
Ho
wev
er
,
b
o
th
o
f
th
ese
tec
h
n
o
lo
g
ies
ar
e
b
ein
g
u
s
ed
b
y
s
cien
tis
ts
an
d
r
esear
ch
er
s
[
1
4
]
-
[
1
7
]
.
W
h
en
ar
tific
ial
in
tellig
en
ce
(
AI
)
is
u
s
ed
in
co
n
ju
n
ctio
n
with
I
o
T
,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
24
,
No
.
3
,
Dec
em
b
er
2
0
2
1
:
1
4
0
5
-
1
4
1
3
1406
as
it
is
d
o
n
e
o
n
c
lo
u
d
s
,
s
u
ch
as
p
r
ed
ictiv
e
en
g
in
es,
th
e
en
d
d
ev
ice
o
r
tem
p
o
r
ar
y
n
o
d
e
s
to
r
es
r
ea
l
-
tim
e
d
ata
p
r
o
v
id
e
d
b
y
s
en
s
o
r
s
.
T
h
e
d
at
a
is
s
en
t
to
th
e
clo
u
d
b
y
n
o
d
es
o
r
en
d
d
e
v
ices,
wh
er
e
it
is
p
r
o
ce
s
s
ed
b
y
a
p
r
ed
ictiv
e
e
n
g
in
e
lea
d
in
g
to
a
d
ec
is
io
n
th
at
is
s
en
t
to
th
e
co
n
tr
o
l
d
e
v
ices.
All
o
f
th
is
h
ap
p
en
s
with
o
u
t
h
u
m
an
in
ter
f
er
en
ce
,
r
esu
lts
in
a
d
ec
lin
e
in
m
ain
ten
an
ce
co
s
t.
T
h
is
p
ap
er
p
r
o
v
id
es
a
m
o
d
el
f
o
r
p
r
ed
ictin
g
an
d
m
ea
s
u
r
in
g
th
e
h
u
m
id
ity
a
n
d
t
em
p
er
atu
r
e
i
n
an
y
l
o
ca
tio
n
b
y
u
s
in
g
W
i
-
Fi
to
co
n
n
ec
t
to
a
r
o
b
o
tic
v
eh
icle.
T
h
is
will
b
e
d
o
n
e
in
b
o
t
h
an
o
u
t
d
o
o
r
an
d
in
d
o
o
r
en
v
ir
o
n
m
e
n
t.
T
h
e
r
ec
u
r
r
e
n
t
n
eu
r
al
n
etwo
r
k
is
u
s
ed
to
p
r
ed
ict
h
u
m
id
ity
an
d
tem
p
er
at
u
r
e.
T
h
e
r
o
b
o
tic
ca
r
'
s
s
en
s
o
r
is
u
s
e
d
f
o
r
th
e
m
ea
s
u
r
em
en
ts
.
T
h
e
DHT
2
2
s
en
s
o
r
f
o
r
h
u
m
id
ity
an
d
tem
p
er
atu
r
e
ass
ess
m
en
t,
an
in
ter
n
e
t
p
r
o
to
co
l
(
IP
)
ca
m
er
a
f
o
r
d
r
iv
in
g
t
h
e
r
o
b
o
tic
ca
r
to
th
e
r
eq
u
ir
ed
p
lace
,
an
d
a
n
o
d
e
m
i
cr
o
co
n
tr
o
ller
u
n
it
(
No
d
e
MCU
)
E
SP
3
2
f
o
r
m
o
n
ito
r
in
g
a
n
d
c
o
n
n
ec
tin
g
,
ar
e
th
e
m
ain
co
m
p
o
n
en
ts
o
f
th
e
r
o
b
o
tic
ca
r
.
T
h
e
cu
s
to
m
ized
ap
p
is
d
esig
n
ed
to
in
d
icate
th
e
ca
r
’
s
cu
r
r
en
t
p
o
s
itio
n
with
m
ea
s
u
r
ed
an
d
p
r
ed
icted
v
alu
es
o
f
h
u
m
id
ity
an
d
tem
p
e
r
atu
r
e.
Var
iatio
n
in
tem
p
er
atu
r
e
r
an
g
es
f
r
o
m
4
-
4
8
˚
C
an
d
v
ar
iatio
n
in
h
u
m
id
ity
r
an
g
es
f
r
o
m
3
6
-
80
%.
I
n
th
i
s
wo
r
k
,
in
s
tead
o
f
r
ely
in
g
o
n
m
ea
s
u
r
em
en
t
o
r
p
r
ed
ictio
n
th
at
wer
e
u
s
ed
m
o
s
tly
in
p
r
ev
i
o
u
s
r
esear
c
h
es,
b
o
th
ap
p
r
o
ac
h
es;
m
ea
s
u
r
em
en
t
as
well
as
p
r
ed
ictio
n
ar
e
u
s
ed
s
im
u
ltan
eo
u
s
ly
,
to
d
o
co
m
p
a
r
is
o
n
an
d
an
aly
s
is
f
o
r
g
ettin
g
m
a
x
im
u
m
ac
c
u
r
ac
y
a
n
d
p
r
ec
is
io
n
in
th
e
d
esire
d
s
en
s
in
g
p
ar
am
ete
r
s
.
T
h
e
r
em
ain
in
g
p
ap
er
is
s
tr
u
ct
u
r
ed
in
th
e
f
o
llo
wi
n
g
m
a
n
n
er
:
s
ec
tio
n
2
d
is
cu
s
s
es
th
e
o
v
er
v
iew
o
f
th
e
r
esear
ch
co
n
d
u
cted
o
n
wea
th
er
f
o
r
ec
asti
n
g
an
d
I
o
T
m
ac
h
in
e
lear
n
in
g
d
ev
elo
p
m
en
t.
T
h
e
f
ir
s
t
s
u
b
s
ec
tio
n
d
escr
ib
es
th
e
tech
n
ical
d
ef
i
n
itio
n
o
f
th
e
r
o
b
o
tic
ca
r
;
th
e
s
ec
o
n
d
s
u
b
s
ec
tio
n
d
is
cu
s
s
es
Ap
p
d
e
v
elo
p
m
e
n
t
f
o
r
r
em
o
te
lo
ca
tio
n
ac
ce
s
s
,
an
d
th
e
th
ir
d
s
u
b
s
ec
tio
n
in
t
r
o
d
u
ce
s
th
e
r
ec
u
r
s
iv
e
n
eu
r
al
n
etwo
r
k
.
I
n
s
ec
tio
n
4
,
g
iv
en
th
e
ex
p
er
im
e
n
tal
r
esu
lts
an
d
ev
alu
atio
n
ar
e
o
u
tlin
ed
.
E
v
en
tu
ally
,
th
e
co
n
clu
s
io
n
o
f
th
e
r
esear
ch
an
d
f
u
tu
r
e
p
er
s
p
ec
tiv
e
ar
e
p
r
esen
ted
.
2.
P
RE
VIOU
S WO
RK
Fo
r
ec
asti
n
g
wea
th
er
is
n
o
t
n
e
w;
it
h
as
ex
is
ted
s
in
ce
th
e
b
e
g
in
n
in
g
o
f
tim
e,
b
u
t
it
is
n
o
t
lim
ited
to
h
u
m
an
s
.
All
an
im
als,
wh
et
h
e
r
o
n
-
ai
r
,
wate
r
,
o
r
la
n
d
p
r
ed
i
ct
f
u
tu
r
e
co
n
d
itio
n
s
.
Hu
m
an
s
u
s
ed
to
u
s
e
n
atu
r
e
clu
es
an
d
s
ay
in
g
s
to
f
o
r
ec
as
t
th
e
we
ath
er
b
ef
o
r
e
th
e
d
ev
elo
p
m
en
t
o
f
s
cien
tific
m
eth
o
d
s
.
T
h
e
d
esig
n
o
f
s
o
p
h
is
ticated
in
s
tr
u
m
en
ts
r
es
u
lted
in
th
e
s
cien
tific
an
aly
s
is
o
f
m
eteo
r
o
lo
g
y
.
Ma
ch
in
e
lear
n
in
g
-
b
ased
an
d
s
tatis
t
ical
ap
p
r
o
ac
h
es
to
tem
p
er
atu
r
e
p
r
ed
ictio
n
ar
e
d
u
al
m
ea
n
s
o
f
m
o
d
er
n
ap
p
r
o
ac
h
es.
R
eg
r
ess
io
n
ap
p
r
o
ac
h
es
s
u
ch
a
s
n
o
n
-
l
i
n
e
a
r
a
n
d
m
u
l
t
i
p
l
e
li
n
e
a
r
r
e
g
r
e
s
s
i
o
n
s
a
r
e
t
h
e
b
a
s
is
o
f
m
o
s
t
s
t
at
is
t
i
ca
l
m
o
d
e
l
s
[
1
8
]
,
[
1
9
]
.
Gar
d
n
er
et
a
l.
[
2
0
]
u
s
ed
Gau
s
s
ian
p
r
o
ce
s
s
an
d
Kr
ig
in
g
(
KR
I
G)
r
eg
r
ess
io
n
m
eth
o
d
s
f
o
r
tem
p
er
atu
r
e
p
r
ed
ictio
n
.
Fu
r
th
er
,
g
en
er
aliz
ed
ad
d
itiv
e
m
o
d
elin
g
(
GAM
)
is
u
s
ed
b
y
s
o
m
e
r
esear
ch
er
s
.
W
an
g
et
a
l.
[
2
1
]
p
r
o
p
o
s
ed
th
e
GAM
in
th
e
p
r
ed
ictio
n
m
o
d
el
an
d
co
n
s
e
q
u
en
tly
g
o
t
s
u
cc
ess
f
u
l
in
f
in
d
in
g
an
ef
f
ec
tiv
e
ass
o
ciatio
n
b
etwe
en
en
v
ir
o
n
m
en
tal
v
ar
iab
les
an
d
p
r
e
d
ictiv
e
v
ar
iab
les.
Oth
er
r
esear
c
h
er
s
u
s
ed
h
y
b
r
i
d
m
eth
o
d
s
to
g
et
o
p
tim
ized
r
esu
lts
b
esid
es
th
ese
s
tati
s
tical
tech
n
iq
u
es.
Desp
ite
th
is
,
f
o
r
ec
asts
wer
e
f
o
u
n
d
to
b
e
t
o
o
f
a
r
o
f
f
th
e
g
r
o
u
n
d
.
I
n
th
e
y
ea
r
2
0
1
0
,
a
n
ew
ag
e
o
f
th
e
m
o
d
e
r
n
m
ac
h
in
e
an
d
d
ee
p
lear
n
in
g
b
e
g
an
to
d
ev
elo
p
.
T
h
e
p
o
p
u
lar
ity
o
f
m
ac
h
i
n
e
lear
n
i
n
g
in
o
th
er
f
ield
s
u
r
g
es
m
etr
o
l
o
g
ical
r
esear
ch
er
s
t
o
ap
p
ly
in
th
e
ar
ea
.
Acc
o
r
d
in
g
to
Dag
li
[
2
2
]
,
it is
n
o
t p
o
s
s
ib
le
to
ass
im
ilate
all
th
e
d
ata
u
s
in
g
co
n
v
en
tio
n
al
m
et
h
o
d
s
.
W
ea
th
er
f
o
r
ec
asti
n
g
in
v
o
lv
e
s
p
ar
am
eter
s
s
u
ch
as
h
u
m
id
ity
an
d
tem
p
er
atu
r
e,
s
n
o
w
o
r
r
ain
f
o
r
ec
asti
n
g
,
b
ar
o
m
etr
ic
p
r
ess
u
r
e,
an
d
win
d
s
p
ee
d
f
o
r
ec
asti
n
g
.
R
esear
ch
er
s
h
a
v
e
p
r
o
p
o
s
ed
v
ar
io
u
s
tem
p
e
r
atu
r
e
m
o
d
els
f
o
r
d
iv
er
s
e
en
v
ir
o
n
m
en
tal
co
n
d
itio
n
s
b
ased
o
n
a
wid
e
r
an
g
e
o
f
s
tu
d
ies.
Fo
r
i
n
s
tan
ce
,
th
e
m
o
d
els
p
r
o
p
o
s
ed
in
[
2
3
]
,
[
2
4
]
f
o
r
e
ca
s
ted
th
e
in
d
o
o
r
tem
p
er
at
u
r
e,
an
d
th
e
m
o
d
el
in
[
2
5
]
,
[
2
6
]
ev
alu
ated
th
e
tem
p
er
atu
r
e
p
r
ed
ictio
n
f
o
r
th
e
lo
n
g
-
ter
m
.
T
h
e
c
o
n
v
e
n
tio
n
a
l
s
ig
n
al
p
r
o
ce
s
s
in
g
m
eth
o
d
s
ar
e
r
ep
lace
d
b
y
th
e
latest
d
ee
p
lear
n
in
g
m
o
d
els
lik
e
g
ated
r
ec
u
r
r
en
t
u
n
its
(
GR
U)
,
lo
n
g
s
h
o
rt
-
te
r
m
m
e
m
o
r
y
(
L
STM
)
,
an
d
co
n
v
o
l
u
tio
n
al
n
eu
r
al
n
etwo
r
k
(
C
NN)
.
Ho
s
s
ain
et
a
l.
[
2
7
]
u
s
ed
d
ee
p
n
eu
r
al
n
etwo
r
k
s
al
o
n
g
with
s
tan
d
ar
d
n
eu
r
al
n
etwo
r
k
s
an
d
s
tack
ed
d
en
o
is
in
g
au
to
-
en
c
o
d
er
s
(
SDAE
)
u
s
in
g
d
if
f
er
en
t
p
a
r
am
eter
s
.
SDAE
ac
h
iev
ed
an
av
er
ag
e
ac
cu
r
ac
y
o
f
9
7
.
9
4
%,
wh
ile
co
n
v
en
tio
n
al
ANN
ac
h
iev
ed
a
n
ac
c
u
r
ac
y
o
f
9
4
.
9
2
%.
R
ec
u
r
r
en
t
n
eu
r
a
l
n
etwo
r
k
(
R
NN)
,
co
n
v
o
lu
tio
n
a
l
n
eu
r
al
n
etwo
r
k
(
C
NN)
m
o
d
e
ls
,
an
d
co
n
d
itio
n
al
r
estricte
d
b
o
ltzm
an
n
m
ac
h
i
n
e
(
C
R
B
M)
wer
e
co
n
tr
asted
in
S
alm
an
et
a
l.
[
2
8
]
r
esear
ch
.
T
h
e
ac
cu
r
ac
y
o
f
r
ain
f
all
p
r
ed
ictio
n
u
s
in
g
r
ec
u
r
r
en
t
n
eu
r
al
i
s
f
o
u
n
d
to
b
e
m
ax
im
u
m
.
B
ec
au
s
e
o
f
its
s
u
p
er
i
o
r
s
u
cc
ess
in
m
u
ltiv
ar
iate
tim
e
-
s
er
ies
f
o
r
ec
asti
n
g
,
L
STM
,
a
v
ar
ia
n
t
o
f
R
NN,
h
a
s
g
o
tten
a
lo
t
o
f
p
u
b
licity
.
Go
ap
et
a
l.
[
2
9
]
p
r
o
p
o
s
ed
a
s
m
ar
t
ir
r
ig
atio
n
m
o
d
el
b
ased
o
n
a
f
ield
s
en
s
o
r
a
n
d
m
eteo
r
o
lo
g
y
.
Usi
n
g
wea
th
er
p
r
ed
ictio
n
an
d
s
o
il
m
o
is
tu
r
e
d
at
a
f
r
o
m
t
h
e
in
ter
n
et,
th
e
m
o
d
el
p
r
ed
icted
f
ield
ir
r
ig
atio
n
is
r
eq
u
ir
ed
.
R
ah
ay
u
et
a
l.
[
3
0
]
a
p
p
lied
lo
n
g
s
h
o
r
t
-
te
r
m
m
em
o
r
y
(
L
STM
)
to
p
r
ed
ict
d
aily
te
m
p
e
r
atu
r
es
o
v
er
th
e
n
e
x
t
th
r
ee
d
a
y
s
with
f
iv
e
class
es,
n
am
ely
"Co
ld
",
"Co
o
l",
"No
r
m
al",
"War
m
"
an
d
"Ho
t".
T
esti
n
g
ac
cu
r
ac
y
is
f
o
u
n
d
to
b
e
9
0
.
9
2
%
an
d
tr
ain
in
g
is
claim
ed
to
b
e
8
0
.
3
6
%
f
o
r
test
in
g
d
ata.
Z
h
an
g
et
a
l.
[
3
1
]
ap
p
lie
d
co
n
v
o
lu
tio
n
al
L
STM
to
m
e
asu
r
e
s
u
r
f
ac
e,
b
u
t
th
e
s
u
b
s
u
r
f
ac
e
tem
p
er
atu
r
e
t
o
p
r
ed
ict
3
-
D
o
ce
an
tem
p
er
atu
r
e
.
R
esu
lts
d
em
o
n
s
tr
ated
th
e
o
v
e
r
all
h
ig
h
er
ac
c
u
r
ac
y
t
h
an
ea
r
li
er
s
tu
d
ies.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
Dis
ta
n
t te
mp
era
tu
r
e
a
n
d
h
u
mi
d
ity
mo
n
ito
r
in
g
:
p
r
ed
ictio
n
a
n
d
mea
s
u
r
eme
n
t
(
F
a
r
r
u
kh
Ha
fe
ez
)
1407
3.
M
E
T
H
O
DO
L
O
G
Y
3
.
1
.
W
o
r
k
ing
m
ec
ha
nis
m
Fig
u
r
e
1
d
ep
icts
a
b
lo
ck
d
i
ag
r
am
o
f
th
e
m
eth
o
d
.
T
h
e
h
u
m
id
ity
-
tem
p
er
atu
r
e
m
ea
s
u
r
in
g
s
en
s
o
r
DHT
2
2
o
n
th
e
r
o
b
o
tic
ca
r
m
ea
s
u
r
es
r
ea
l
-
tim
e
h
u
m
id
ity
-
tem
p
er
atu
r
e
d
ata
at
th
e
cu
r
r
en
t
s
p
o
t.
A
m
o
u
n
ted
I
P
ca
m
er
a
allo
ws
th
e
r
o
b
o
tic
ca
r
to
b
e
tr
a
n
s
p
o
r
ted
t
o
an
y
p
o
s
itio
n
in
s
id
e
o
r
o
u
ts
id
e.
T
h
e
No
d
eM
C
U
s
y
s
tem
,
wh
ich
is
m
o
u
n
te
d
o
n
th
e
r
o
b
o
tic
ca
r
,
h
an
d
les
all
o
f
th
e
co
m
p
u
tin
g
an
d
in
f
o
r
m
atio
n
p
r
o
ce
s
s
in
g
.
C
u
s
to
m
ap
p
licatio
n
s
b
u
ilt
o
n
th
e
An
d
r
o
id
p
latf
o
r
m
ar
e
u
s
ed
t
o
v
iew
r
ea
l
-
tim
e
d
ata
an
d
m
o
n
ito
r
th
e
r
o
b
o
tic
ca
r
.
R
NN
is
ap
p
lied
to
f
o
r
ec
ast
h
u
m
i
d
ity
an
d
tem
p
e
r
atu
r
e
u
s
in
g
r
ea
l
-
tim
e
r
ec
o
r
d
ed
d
ata.
T
h
is
p
r
e
d
icted
v
alu
e
wo
u
ld
ap
p
ea
r
al
o
n
g
s
id
e
th
e
m
ea
s
u
r
e
d
v
alu
e
in
th
e
e
v
en
t
o
f
s
en
s
o
r
f
ailu
r
e
o
r
to
co
m
p
ar
e
t
h
e
p
r
ed
icted
an
d
m
ea
s
u
r
ed
v
alu
es.
T
h
e
lab
is
ch
o
s
en
as
an
in
s
id
e
lo
ca
tio
n
f
o
r
p
r
e
d
ictio
n
,
wh
ile
f
o
r
th
e
o
u
ts
id
e
lo
ca
tio
n
,
th
e
o
u
ts
id
e
b
u
ild
in
g
lo
ca
tio
n
is
c
o
n
s
id
er
e
d
.
Fo
r
b
o
th
lo
ca
tio
n
s
,
d
ata
is
co
llected
f
o
r
a
y
ea
r
.
T
h
e
m
o
u
n
ted
s
en
s
o
r
s
co
llect
in
d
o
o
r
p
o
s
itio
n
d
ata,
wh
ile
t
h
e
lo
ca
l
m
eteo
r
o
lo
g
ical
d
ata
ce
n
ter
o
b
tain
s
o
u
td
o
o
r
d
ata
.
Fo
r
tr
ain
in
g
an
d
r
esear
ch
,
a
s
et
d
ay
tim
e
is
u
s
ed
.
I
n
th
e
f
o
llo
win
g
s
eg
m
e
n
t,
th
e
R
NN
alg
o
r
ith
m
is
d
is
cu
s
s
ed
in
d
etail.
T
h
er
e
ar
e
th
r
ee
s
ec
tio
n
s
o
f
th
e
f
u
n
ctio
n
al
d
ef
in
itio
n
.
T
h
e
f
ir
s
t
s
ec
tio
n
ad
d
r
ess
ed
d
ev
ice
h
ar
d
war
e;
th
e
s
ec
o
n
d
s
ec
tio
n
elab
o
r
ated
o
n
c
u
s
to
m
izab
le
a
p
p
licatio
n
d
e
v
elo
p
m
e
n
t,
an
d
th
e
th
ir
d
s
ec
tio
n
clar
if
ied
t
h
e
R
NN
alg
o
r
ith
m
'
s
ap
p
licatio
n
.
Fig
u
r
e
1
.
B
lo
ck
d
iag
r
am
with
m
ain
co
m
p
o
n
en
ts
3
.
2
.
R
o
bo
t
ic
ca
r
m
o
du
le
f
u
nct
io
na
l
d
escript
io
n
T
h
e
No
d
eM
C
U
E
SP
8
2
6
6
ac
t
s
as
th
e
p
r
o
ce
s
s
in
g
an
d
co
n
tr
o
llin
g
d
ev
ice
f
o
r
th
e
r
o
b
o
tic
ca
r
,
wh
ile
th
e
I
P
ca
m
er
a
allo
ws
m
o
n
ito
r
in
g
to
wo
r
k
f
r
o
m
a
r
em
o
te
p
o
s
iti
o
n
,
t
h
e
DHT
2
2
allo
ws
h
u
m
id
ity
an
d
tem
p
e
r
atu
r
e
m
ea
s
u
r
em
en
t,
th
e
m
o
to
r
an
d
d
r
iv
er
m
o
d
u
le
with
DC
m
o
to
r
f
o
r
th
e
r
o
b
o
tic
ca
r
'
s
m
o
tio
n
.
T
h
e
No
d
eM
C
U
in
co
r
p
o
r
ates
an
d
m
o
n
ito
r
s
h
a
r
d
war
e
wh
ile
s
till
co
m
m
u
n
ica
tin
g
with
th
e
m
o
b
ile
ap
p
an
d
clo
u
d
s
er
v
er
.
T
h
e
N
ode
MCU)
is
p
r
o
g
r
am
m
ed
in
L
UA,
an
d
its
b
u
ilt
-
in
W
i
-
Fi
f
ea
tu
r
e
allo
ws
f
o
r
ea
s
ier
d
ata
s
h
ar
in
g
b
etwe
en
th
e
m
o
b
ile
ap
p
an
d
clo
u
d
s
er
v
er
.
Fig
u
r
e
2
d
ep
icts
th
e
p
r
im
a
r
y
f
u
n
ctio
n
al
p
h
ases
.
DHT
2
2
s
en
s
o
r
m
ea
s
u
r
es
h
u
m
id
ity
an
d
tem
p
er
at
u
r
e
with
a
p
r
ec
is
io
n
o
f
±
1
%
an
d
±
1
°
C
,
r
esp
ec
tiv
ely
,
f
r
o
m
0
-
1
0
0
p
er
ce
n
t
an
d
-
4
0
°C
to
8
0
°C
.
DHT
2
2
m
ea
s
u
r
es
tem
p
er
atu
r
e
with
a
n
eg
ativ
e
tem
p
er
atu
r
e
co
ef
f
ici
en
t
NT
C
tem
p
er
atu
r
e
s
en
s
o
r
an
d
h
u
m
id
ity
with
a
c
o
m
b
in
atio
n
o
f
two
elec
tr
o
d
es a
n
d
a
m
o
is
tu
r
e
-
h
o
ld
i
n
g
s
u
b
s
tr
ate.
T
h
e
s
e
n
s
o
r
o
f
4
0
b
i
t
s
o
f
s
e
r
i
a
l
d
a
t
a
i
s
p
r
o
c
es
s
e
d
;
t
h
e
c
u
r
r
e
n
t
v
a
l
u
e
o
f
h
u
m
i
d
i
t
y
a
n
d
t
e
m
p
e
r
a
tu
r
e
v
a
l
u
e
s
a
r
e
o
b
t
a
i
n
e
d
a
n
d
s
e
n
t
t
o
t
h
e
m
o
b
i
l
e
a
p
p
.
T
h
e
m
o
t
o
r
d
r
i
v
e
r
m
o
d
u
l
e
i
s
l
i
n
k
e
d
b
e
t
w
e
e
n
t
h
e
m
o
t
o
r
s
a
n
d
N
o
d
e
M
C
U
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
24
,
No
.
3
,
Dec
em
b
er
2
0
2
1
:
1
4
0
5
-
1
4
1
3
1408
t
o
e
n
s
u
r
e
t
h
a
t
t
h
e
v
o
l
t
a
g
e
-
c
u
r
r
e
n
t
r
e
q
u
i
r
e
m
e
n
t
s
o
f
t
h
e
DC
m
o
t
o
r
.
A
n
I
P
c
a
m
e
r
a
i
s
at
t
a
c
h
e
d
t
o
a
r
o
b
o
t
i
c
c
a
r
f
o
r
l
o
c
a
t
i
o
n
t
r
a
c
k
i
n
g
a
n
d
m
o
t
i
o
n
.
T
h
e
c
a
m
e
r
a'
s
W
i
-
F
i
,
I
P
a
d
d
r
ess
e
s
,
a
n
d
b
a
u
d
r
a
t
e
a
r
e
s
e
t
f
i
r
s
t
,
f
o
l
l
o
w
e
d
b
y
t
h
e
r
e
s
t
o
f
t
h
e
p
a
r
a
m
e
t
e
r
v
a
l
u
es
.
F
o
r
r
em
o
t
e
m
o
b
i
l
e
a
p
p
c
o
n
t
r
o
l
,
s
p
ec
if
i
e
d
p
a
r
a
m
e
t
e
r
v
a
l
u
es
a
r
e
u
s
e
d
.
Fig
u
r
e
2
.
R
o
b
o
tic
ca
r
f
u
n
ctio
n
al
b
lo
ck
v
iew
3
.
3
.
M
o
bil
e
a
pp
a
rc
hite
ct
ura
l
w
o
rk
ing
T
h
e
cu
s
to
m
ized
ap
p
is
b
ased
o
n
th
e
An
d
r
o
id
p
latf
o
r
m
f
o
r
ac
ce
s
s
in
g
r
em
o
te
lo
ca
tio
n
s
.
Fig
u
r
e
3
s
h
o
ws
a
f
lo
wch
a
r
t
with
f
o
u
r
b
r
an
ch
es,
ea
ch
s
p
ec
if
y
in
g
a
p
r
o
ce
s
s
's
m
o
b
ile
ap
p
s
tep
s
i
n
s
eq
u
en
ce
.
T
h
e
f
ir
s
t
b
r
an
ch
e
x
p
lain
s
h
o
w
to
lin
k
a
n
I
P
ca
m
er
a
t
o
a
m
o
b
ile
ap
p
.
Af
ter
s
ea
r
ch
in
g
f
o
r
a
liv
e
s
tr
e
am
in
g
m
o
d
u
le
with
C
am
er
a
ad
m
in
cr
e
d
en
tials
,
a
liv
e
v
id
eo
s
ess
io
n
is
cr
ea
ted
u
s
in
g
co
n
ten
t
d
eliv
er
y
n
etwo
r
k
s
(
C
DN)
f
o
r
o
f
f
e
r
in
g
p
r
em
iu
m
v
i
d
eo
q
u
ality
an
d
a
n
ad
d
itio
n
al
lay
er
o
f
p
r
o
tectio
n
.
As
v
id
eo
s
tr
ea
m
in
g
b
eg
in
s
,
th
e
v
id
eo
'
s
p
ix
el,
r
eso
lu
tio
n
,
a
n
d
b
it
r
ate
ar
e
s
ca
led
to
f
it
th
e
ap
p
'
s
s
ize.
B
r
an
ch
2
d
ep
icts
a
r
o
b
o
tic
ca
r
tak
i
n
g
ca
r
e
o
f
t
h
e
p
r
e
-
d
ef
in
ed
s
tep
s
.
T
h
e
No
d
eM
C
U
is
u
s
ed
to
in
itialize
th
e
a
p
p
b
ased
o
n
th
e
m
o
to
r
p
in
s
s
p
ec
if
i
ed
in
th
e
h
ar
d
war
e.
B
o
th
th
e
Ap
p
an
d
No
d
eM
C
U
p
ar
am
eter
s
ar
e
s
y
n
ch
r
o
n
ized
an
d
th
e
b
o
ar
d
'
s
tes
t
L
E
D
is
u
s
ed
f
o
r
m
o
n
ito
r
in
g
.
Fo
u
r
-
way
d
ir
ec
tio
n
s
ar
e
test
ed
u
s
in
g
f
o
u
r
ar
r
o
ws
o
n
th
e
m
o
b
ile
ap
p
af
ter
th
e
lin
k
is
e
s
tab
lis
h
ed
an
d
L
E
D
ch
ec
k
in
g
.
B
r
an
ch
n
o
.
3
d
ep
ict
s
th
e
m
ea
s
u
r
es
in
v
o
lv
ed
i
n
co
l
lectin
g
tem
p
er
a
tu
r
e
an
d
h
u
m
id
ity
v
alu
es
f
r
o
m
th
e
No
d
eM
C
U
an
d
d
is
p
lay
in
g
th
em
o
n
th
e
ap
p
.
B
ef
o
r
e
co
n
n
e
ctin
g
with
th
e
ap
p
,
th
e
s
en
s
o
r
s
en
d
s
s
er
ial
d
ata
tr
an
s
m
is
s
io
n
an
d
N
o
d
eM
C
U
m
u
s
t
b
e
ch
ec
k
ed
.
On
ce
th
e
a
p
p
lin
k
is
estab
lis
h
ed
,
a
m
o
v
in
g
r
o
b
o
tic
ca
r
is
u
s
ed
to
test
th
e
co
n
t
in
u
o
u
s
u
p
d
atin
g
o
f
h
u
m
id
ity
an
d
tem
p
er
atu
r
e
v
alu
es in
v
ar
io
u
s
co
n
d
itio
n
s
.
T
h
e
s
tep
s
in
B
r
an
ch
No
.
4
ex
p
lain
th
e
in
itial
s
tep
s
in
co
n
n
ec
tin
g
th
e
ap
p
to
clo
u
d
d
ata
to
d
is
p
lay
ex
p
ec
t
ed
tem
p
er
atu
r
e
an
d
h
u
m
id
ity
v
alu
es.
A
clo
u
d
s
er
v
er
is
m
ad
e
ac
ce
s
s
ib
le,
an
d
th
e
o
b
tain
ed
d
ata
m
u
s
t
b
e
co
n
v
er
t
ed
to
th
e
f
o
r
m
at
o
f
a
m
o
b
ile
ap
p
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
Dis
ta
n
t te
mp
era
tu
r
e
a
n
d
h
u
mi
d
ity
mo
n
ito
r
in
g
:
p
r
ed
ictio
n
a
n
d
mea
s
u
r
eme
n
t
(
F
a
r
r
u
kh
Ha
fe
ez
)
1409
Fig
u
r
e
3
.
An
d
r
o
id
ap
p
licatio
n
p
r
o
ce
s
s
f
lo
w
ch
ar
t
3
.
4
.
T
em
pera
t
ure
a
nd
h
um
idi
t
y
p
re
dict
io
n
s
y
s
t
em
u
s
ing
RNN
T
h
e
R
NN
m
o
d
el
is
u
s
ed
to
esti
m
ate
h
u
m
id
ity
an
d
tem
p
er
at
u
r
e.
T
h
e
i
n
d
o
o
r
d
ata
c
o
llectio
n
is
m
ad
e
u
p
o
f
lab
d
ata
f
r
o
m
th
e
m
o
u
n
t
ed
s
en
s
o
r
,
wh
ile
th
e
o
u
td
o
o
r
d
ata
is
s
o
u
r
ce
d
f
r
o
m
a
g
lo
b
al
w
ea
th
er
d
atab
ase.
T
o
k
ee
p
th
e
n
etwo
r
k
'
s
tr
ain
in
g
q
u
ality
,
ap
p
r
o
p
r
iate
d
at
a
s
p
litt
in
g
is
n
ee
d
ed
f
o
r
tr
ain
in
g
,
au
th
en
ticatio
n
,
an
d
an
aly
s
is
.
Fo
r
test
in
g
an
d
tr
ain
i
n
g
,
th
e
d
ata
s
et
is
d
iv
id
ed
in
to
2
0
%
an
d
8
0
%,
r
esp
ec
tiv
ely
.
T
en
s
o
r
f
lo
w
v
er
s
io
n
2
.
3
.
0
is
u
s
ed
to
d
esig
n
th
e
m
o
d
el
in
Py
th
o
n
2
.
7
with
Ker
a
s
L
ib
r
ar
y
.
T
ab
le
1
s
h
o
ws
ce
r
t
ai
n
h
y
p
e
r
p
ar
am
ete
r
s
th
at
co
n
tr
ib
u
te
to
m
in
u
te
d
if
f
e
r
en
ce
s
.
Hy
p
er
-
p
ar
am
eter
s
s
u
c
h
as
ep
o
ch
,
m
ea
n
a
b
s
o
lu
te
er
r
o
r
,
an
d
lear
n
in
g
r
ate
ar
e
co
n
s
id
er
ed
to
b
e
k
ey
elem
en
ts
f
o
r
f
o
r
ec
asti
n
g
ef
f
icien
c
y
.
T
ab
le
1
.
Su
m
m
a
r
y
o
f
R
NN
m
o
d
el’
s
p
ar
am
eter
v
alu
es
H
y
p
e
r
p
a
r
a
m
e
t
e
r
s
V
a
l
u
e
s
Lo
ss F
u
n
c
t
i
o
n
Le
a
r
n
i
n
g
R
a
t
e
R
e
c
u
r
r
e
n
t
S
t
e
p
’
s Ac
t
i
v
a
t
i
o
n
F
u
n
c
t
i
o
n
A
c
t
i
v
a
t
i
o
n
F
u
n
c
t
i
o
n
N
e
u
r
o
n
s
i
n
L
a
y
e
r
1
N
e
u
r
o
n
s
i
n
L
a
y
e
r
2
Ep
o
c
h
s
O
p
t
i
mi
z
e
r
M
S
E
0
.
0
0
0
6
9
si
g
m
o
i
d
t
a
n
h
32
54
2
5
0
A
d
a
m
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
24
,
No
.
3
,
Dec
em
b
er
2
0
2
1
:
1
4
0
5
-
1
4
1
3
1410
On
e
o
f
th
e
in
itial
s
tep
s
af
ter
d
ata
p
r
ep
r
o
ce
s
s
in
g
is
to
f
in
d
th
e
r
elatio
n
b
etwe
en
v
ar
i
ab
les
an
d
u
n
d
er
ly
i
n
g
f
ac
t
o
r
s
.
T
h
is
is
ac
co
m
p
lis
h
ed
b
y
th
e
u
s
e
o
f
f
ac
to
r
an
aly
s
is
(
FA)
.
T
h
e
Kaiser
-
Me
y
er
-
Olk
in
(
KM
O
)
test
is
u
s
ed
to
d
eter
m
in
e
th
e
d
ataset
f
ac
to
r
ab
ilit
y
.
F
o
r
s
elec
tin
g
th
e
n
u
m
b
er
o
f
v
ar
iab
les
,
th
e
Kaiser
cr
iter
ia
an
d
th
e
s
cr
ee
p
lo
t
ar
e
u
s
ed
.
T
ab
le
2
s
u
m
m
ar
izes
th
e
r
esu
lts
o
f
d
if
f
er
en
t
lear
n
i
n
g
r
at
es
f
o
r
p
er
f
o
r
m
an
ce
f
o
llo
win
g
er
r
o
r
v
ar
iatio
n
.
Du
r
i
n
g
tr
ain
in
g
,
v
ar
i
o
u
s
lear
n
in
g
r
ates
wer
e
s
elec
ted
in
th
is
m
o
d
el
.
Du
r
in
g
tr
ain
i
n
g
,
lear
n
in
g
r
ates
o
f
0
.
0
0
0
2
5
,
0
.
0
0
0
6
9
,
0
.
0
0
0
7
5
,
0
.
0
0
1
,
0
.
0
1
,
an
d
0
.
0
3
3
g
e
n
er
ated
m
in
im
u
m
lo
s
s
es
with
r
ea
s
o
n
ab
le
tr
ain
in
g
s
p
ee
d
.
T
h
e
m
o
d
el'
s
o
u
tp
u
t
was
ev
alu
ated
u
s
in
g
m
ea
n
ab
s
o
lu
te
er
r
o
r
lo
s
s
to
id
en
tify
ac
ce
p
tab
le
h
y
p
er
-
p
ar
am
eter
s
.
T
h
e
d
if
f
er
en
ce
in
v
ar
io
u
s
lear
n
in
g
r
ates
f
r
o
m
m
o
d
els
1
-
6
is
o
b
v
i
o
u
s
;
r
ev
ea
lin
g
th
at
m
o
d
el
6
p
er
f
o
r
m
s
th
e
b
est with
a
lear
n
in
g
r
ate
is
o
f
0
.
0
0
0
6
9
.
T
ab
le
2
.
An
aly
s
is
o
f
v
ar
io
u
s
le
ar
n
in
g
r
ates in
ter
m
s
o
f
p
er
f
o
r
m
an
ce
M
o
d
e
l
M
S
LE
R
M
S
E
l
e
a
r
n
i
n
g
r
a
t
e
s
M
A
E
Ep
o
c
h
1
0
.
0
0
1
9
3
.
8
8
3
1
0
.
0
1
1
.
4
0
4
2
2
5
0
2
0
.
0
1
1
8
2
1
.
6
3
6
9
0
.
0
3
3
2
.
9
3
2
9
2
5
0
3
0
.
0
0
4
7
7
.
8
7
4
3
0
.
0
0
1
1
.
8
5
9
2
5
0
4
0
.
0
1
1
7
1
1
.
0
0
4
0
0
.
0
0
0
7
5
2
.
1
6
7
6
2
5
0
5
4
.
8
7
6
2
2
3
.
5
2
3
3
0
.
0
0
0
2
5
3
.
0
3
5
6
2
5
0
6
0
.
0
0
7
0
5
.
8
5
0
1
0
.
0
0
0
6
9
2
.
1
8
1
5
2
5
0
T
esti
n
g
f
o
r
f
o
r
ec
asti
n
g
is
co
n
d
u
cted
af
te
r
tr
ain
in
g
an
d
tu
n
i
n
g
o
f
th
e
R
NN
n
etwo
r
k
.
Me
a
n
s
q
u
ar
ed
lo
g
ar
ith
m
ic
er
r
o
r
(
MSL
E
)
,
r
o
o
t
m
ea
n
s
q
u
a
r
ed
er
r
o
r
(
R
MSE
)
,
an
d
m
ea
n
a
b
s
o
lu
te
er
r
o
r
(
MA
E
)
b
etwe
en
Y
predicted
(
p
r
ed
icted
v
alu
e)
an
d
Y
real
(
r
ea
l
v
alu
e)
ar
e
u
s
ed
to
ev
alu
ate
t
h
e
p
e
r
f
o
r
m
an
ce
at
tim
e
t
an
d
N,
t
o
tal
ev
alu
atio
n
n
u
m
b
er
s
.
T
h
e
f
o
r
m
u
lae
f
o
r
all
o
f
th
em
is
ex
p
r
ess
ed
as:
R
M
SL
E
=
1
N
∑
(
l
og
(
+
1
)
−
l
og
(
+
1
)
2
)
n
t
=
1
(
1
)
R
M
SE
=
√
∑
(
−
)
2
N
t
=
1
N
(
2
)
MAE
=
1
N
∑
|
−
|
N
t
=
1
(
3
)
4.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
Fig
u
r
e
4
s
h
o
ws
th
e
d
if
f
er
e
n
ce
b
etwe
en
th
e
(
ex
p
ec
ted
a
n
d
r
ea
l)
tem
p
er
atu
r
es
an
d
h
u
m
id
ity
o
v
e
r
9
0
h
o
u
r
s
.
T
h
e
r
esu
lt
in
d
icate
s
th
at
th
e
R
NN
s
y
s
tem
i
s
a
r
eliab
l
e
m
eth
o
d
to
p
r
ed
ict
o
u
td
o
o
r
a
n
d
in
d
o
o
r
h
u
m
id
it
y
an
d
tem
p
er
atu
r
e.
I
n
th
e
in
d
o
o
r
ar
ea
,
th
e
d
if
f
er
en
ce
in
(
p
r
ed
icted
an
d
r
ea
l
)
tem
p
e
r
atu
r
e
v
alu
e
r
an
g
es
f
r
o
m
0
.
8
5
-
5
.
3
6
°C
.
On
th
e
co
n
tr
ar
y
,
th
e
d
if
f
e
r
en
ce
in
t
h
e
h
u
m
i
d
ity
(
p
r
e
d
icted
an
d
r
ea
l
v
alu
e
s
)
r
an
g
e
f
r
o
m
1
.
5
6
-
7
.
5
%.
T
h
e
r
esu
lt
d
ep
icts
t
h
at
t
h
e
o
u
td
o
o
r
s
ettin
g
s
h
av
e
a
litt
l
e
h
ig
h
er
d
if
f
er
e
n
ce
i
n
h
u
m
id
it
y
an
d
tem
p
er
atu
r
e
.
Fo
r
in
s
tan
ce
,
th
e
tem
p
er
atu
r
e
d
if
f
er
en
ce
r
a
n
g
es
f
r
o
m
1
.
3
5
-
8
.
3
6
°C
,
an
d
th
e
h
u
m
id
ity
d
if
f
er
en
ce
r
an
g
es
f
r
o
m
2
.
5
6
-
8
.
3
% in
o
u
td
o
o
r
c
o
n
d
itio
n
s
.
T
ab
le
3
s
h
o
w
s
th
e
c
o
m
p
ar
i
s
o
n
r
e
s
u
lts
o
f
th
e
d
e
f
in
ed
p
ar
a
m
eter
s
.
T
ab
le
3
.
Per
f
o
r
m
an
ce
o
f
R
NN
m
o
d
el
Lo
c
a
t
i
o
n
P
a
r
a
me
t
e
r
C
r
i
t
e
r
i
o
n
s
V
a
l
u
e
s
La
b
Te
mp
e
r
a
t
u
r
e
M
e
a
n
a
b
so
l
u
t
e
e
r
r
o
r
R
o
o
t
me
a
n
sq
u
a
r
e
d
e
r
r
o
r
(
R
M
S
E)
A
c
c
u
r
a
c
y
w
h
e
n
p
r
e
d
i
c
t
i
o
n
e
r
r
o
r
i
s
sm
a
l
l
e
r
t
h
a
n
3
°
C
1
.
3
8
1
.
7
1
90
H
u
mi
d
i
t
y
M
e
a
n
a
b
so
l
u
t
e
e
r
r
o
r
R
o
o
t
me
a
n
sq
u
a
r
e
d
e
r
r
o
r
(
R
M
S
E)
A
c
c
u
r
a
c
y
w
h
e
n
p
r
e
d
i
c
t
i
o
n
e
r
r
o
r
i
s
sm
a
l
l
e
r
t
h
a
n
3
°
C
2
.
3
1
2
.
4
3
92
O
u
t
s
i
d
e
Te
mp
e
r
a
t
u
r
e
M
e
a
n
a
b
so
l
u
t
e
e
r
r
o
r
R
o
o
t
me
a
n
sq
u
a
r
e
d
e
r
r
o
r
(
R
M
S
E)
A
c
c
u
r
a
c
y
w
h
e
n
p
r
e
d
i
c
t
i
o
n
e
r
r
o
r
i
s
sm
a
l
l
e
r
t
h
a
n
3
°
C
1
.
1
8
1
.
6
3
90
H
u
mi
d
i
t
y
M
e
a
n
a
b
so
l
u
t
e
e
r
r
o
r
R
o
o
t
me
a
n
sq
u
a
r
e
d
e
r
r
o
r
(
R
M
S
E)
A
c
c
u
r
a
c
y
w
h
e
n
p
r
e
d
i
c
t
i
o
n
e
r
r
o
r
i
s
sm
a
l
l
e
r
t
h
a
n
3
°
C
2
.
2
1
2
.
5
6
90
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
Dis
ta
n
t te
mp
era
tu
r
e
a
n
d
h
u
mi
d
ity
mo
n
ito
r
in
g
:
p
r
ed
ictio
n
a
n
d
mea
s
u
r
eme
n
t
(
F
a
r
r
u
kh
Ha
fe
ez
)
1411
(
a)
(
b
)
(
c)
Fig
u
r
e
4
.
R
NN
Actu
al
an
d
p
r
e
d
icted
tem
p
er
atu
r
e
an
d
h
u
m
i
d
ity
g
r
ap
h
s
:
(
a)
o
u
t
d
o
o
r
h
u
m
id
ity
,
(
b
)
o
u
td
o
o
r
tem
p
e
r
atu
r
e
,
(
c)
in
d
o
o
r
h
u
m
id
ity
,
an
d
(
d
)
in
d
o
o
r
tem
p
er
atu
r
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
24
,
No
.
3
,
Dec
em
b
er
2
0
2
1
:
1
4
0
5
-
1
4
1
3
1412
5.
CO
NCLU
SI
O
N
AND
F
U
T
U
RE
W
O
RK
T
h
e
h
y
b
r
id
m
o
d
el
a
p
p
r
o
ac
h
to
ex
am
in
e
th
e
h
u
m
id
ity
an
d
te
m
p
er
atu
r
e
is
p
r
o
p
o
s
ed
in
t
h
is
p
ap
er
.
T
h
e
h
y
b
r
id
m
o
d
el
aim
s
to
co
m
p
ar
e
m
ea
s
u
r
ed
an
d
ex
p
ec
ted
v
al
u
es
in
a
s
in
g
le
s
tu
d
y
.
R
NN,
a
d
ata
-
d
r
iv
en
m
ac
h
in
e
lear
n
in
g
al
g
o
r
ith
m
,
is
d
e
v
elo
p
ed
to
p
r
ed
ict
h
u
m
id
ity
an
d
t
em
p
er
atu
r
e.
T
esti
n
g
a
n
d
ass
ess
m
en
t
ar
e
d
o
n
e
i
n
b
o
t
h
a
n
o
u
t
d
o
o
r
a
n
d
a
n
i
n
d
o
o
r
e
n
v
i
r
o
n
m
e
n
t
.
I
n
c
o
n
t
r
as
t
t
o
t
h
e
o
u
t
d
o
o
r
w
o
r
l
d
,
t
h
e
s
t
a
ti
s
t
i
c
a
l
r
e
s
u
lt
r
ev
ea
ls
th
a
t
in
d
o
o
r
e
n
v
ir
o
n
m
en
ts
ac
h
iev
e
d
h
ig
h
ac
cu
r
ac
y
.
T
o
v
e
r
if
y
th
at
th
e
p
r
o
p
o
s
ed
m
o
d
el'
s
ac
cu
r
ac
y
m
u
s
t
b
e
im
p
r
o
v
e
d
.
T
h
is
ca
n
b
e
ac
c
o
m
p
lis
h
ed
b
y
p
r
e
p
ar
in
g
m
o
r
e
d
ata
f
o
r
a
lo
n
g
er
tim
e.
A
m
o
r
e
s
o
p
h
is
ticated
m
eteo
r
o
lo
g
y
-
r
elate
d
alg
o
r
ith
m
m
ay
also
b
e
u
s
ed
to
o
b
tain
r
e
liab
le
p
r
ed
ictio
n
v
alu
es.
Ho
w
ev
er
,
in
th
is
ar
ticle,
we
h
av
e
u
s
ed
a
h
y
b
r
id
ap
p
r
o
ac
h
r
ath
er
th
a
n
r
ely
in
g
s
o
lely
o
n
ex
p
ec
ted
r
esu
lts
.
Usi
n
g
a
s
o
p
h
is
ticated
an
d
d
ed
icate
d
h
u
m
id
ity
an
d
tem
p
e
r
atu
r
e
s
en
s
o
r
will im
p
r
o
v
e
m
e
asu
r
em
en
t a
cc
u
r
ac
y
.
RE
F
E
R
E
NC
E
S
[1
]
T.
Yo
u
n
g
,
D.
Ha
z
a
rik
a
,
S
.
P
o
r
ia,
a
n
d
E.
Ca
m
b
ria,
“
Re
c
e
n
t
tr
e
n
d
s
in
d
e
e
p
lea
rn
i
n
g
-
b
a
se
d
n
a
tu
ra
l
lan
g
u
a
g
e
p
ro
c
e
ss
in
g
[Re
v
iew
Article
],
”
IE
EE
C
o
mp
u
ta
ti
o
n
a
l
In
tell
ig
e
n
c
e
M
a
g
a
zin
e
,
I
n
stit
u
te
o
f
El
e
c
trica
l
a
n
d
E
lec
tro
n
ic
s
En
g
i
n
e
e
rs
In
c
.
,
v
o
l
.
1
3
,
n
o
.
3
,
p
p
.
5
5
-
7
5
,
Au
g
-
2
0
1
8
,
d
o
i:
1
0
.
1
1
0
9
/M
CI.
2
0
1
8
.
2
8
4
0
7
3
8
.
[2
]
B.
No
rg
e
o
t,
B.
S
.
G
li
c
k
sb
e
rg
,
a
n
d
A.
J.
Bu
tt
e
,
“
A
c
a
ll
fo
r
d
e
e
p
-
lea
rn
in
g
h
e
a
lt
h
c
a
re
,
”
Na
t
u
re
M
e
d
icin
e
,
Na
t
u
re
Pu
b
li
s
h
in
g
Gr
o
u
p
,
v
o
l.
2
5
,
n
o
.
1
,
p
p
.
1
4
-
1
5
,
0
1
-
Ja
n
-
2
0
1
9
,
d
o
i:
1
0
.
1
0
3
8
/s4
1
5
9
1
-
0
1
8
-
0
3
2
0
-
3
.
[3
]
R.
Vij
a
n
d
B.
Ka
u
sh
i
k
,
“
A
su
rv
e
y
o
n
v
a
rio
u
s
fa
c
e
d
e
tec
ti
n
g
a
n
d
trac
k
in
g
tec
h
n
iq
u
e
s
in
v
i
d
e
o
se
q
u
e
n
c
e
s,”
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
I
n
telli
g
e
n
t
Co
m
p
u
t
in
g
a
n
d
Co
n
tro
l
S
y
ste
ms
,
ICCS
2
0
1
9
,
2
0
1
9
,
p
p
.
6
9
-
7
3
,
d
o
i:
1
0
.
1
1
0
9
/ICCS
4
5
1
4
1
.
2
0
1
9
.
9
0
6
5
4
8
3
.
[4
]
N.
M
e
h
d
iy
e
v
,
J.
E
v
e
rm
a
n
n
,
a
n
d
P
.
F
e
tt
k
e
,
“
A
No
v
e
l
Bu
si
n
e
ss
P
r
o
c
e
ss
P
re
d
ictio
n
M
o
d
e
l
Us
i
n
g
a
De
e
p
Lea
rn
in
g
M
e
th
o
d
,
”
B
u
s.
In
f.
S
y
st.
En
g
.
,
v
o
l
.
6
2
,
n
o
.
2
,
p
p
.
1
4
3
-
1
5
7
,
A
p
r.
2
0
2
0
,
d
o
i:
1
0
.
1
0
0
7
/s1
2
5
9
9
-
0
1
8
-
0
5
5
1
-
3
.
[5
]
M
.
H.
Ab
d
E
l
-
Ja
wa
d
,
R.
Ho
d
h
o
d
,
a
n
d
Y.
M
.
K.
Om
a
r,
“
S
e
n
ti
m
e
n
t
a
n
a
ly
sis
o
f
so
c
ial
m
e
d
ia n
e
two
rk
s
u
si
n
g
m
a
c
h
in
e
lea
rn
in
g
,
”
in
ICENCO
2
0
1
8
,
1
4
th
In
ter
n
a
ti
o
n
a
l
Co
m
p
u
ter
En
g
i
n
e
e
rin
g
Co
n
fer
e
n
c
e
:
S
e
c
u
re
S
ma
rt
S
o
c
ieties
,
2
0
1
9
,
p
p
.
1
7
4
-
1
7
6
,
d
o
i:
1
0
.
1
1
0
9
/ICE
N
CO.
2
0
1
8
.
8
6
3
6
1
2
4
.
[6
]
O.
Ko
lch
y
n
a
,
T.
T
.
P
.
S
o
u
z
a
,
P
.
Trele
a
v
e
n
,
a
n
d
T
.
As
te,
“
Twit
ter
S
e
n
ti
m
e
n
t
An
a
l
y
sis:
Lex
ico
n
M
e
th
o
d
,
M
a
c
h
i
n
e
Lea
rn
in
g
M
e
th
o
d
a
n
d
T
h
e
ir
C
o
m
b
in
a
ti
o
n
,
”
I
n
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
Eme
rg
i
n
g
T
e
c
h
n
o
lo
g
ies
in
L
e
a
rn
in
g
,
v
o
l.
1
2
,
n
o
.
3
,
p
p
.
4
5
-
56
,
J
u
l.
2
0
1
5
.
[7
]
M
.
S
a
n
ti
ll
a
n
a
,
A.
T.
Ng
u
y
e
n
,
M
.
Dre
d
z
e
,
M
.
J.
P
a
u
l,
E.
O.
Ns
o
e
sie
,
a
n
d
J
.
S
.
Br
o
wn
ste
in
,
“
Co
m
b
in
in
g
S
e
a
rc
h
,
S
o
c
ial
M
e
d
ia,
a
n
d
Tra
d
it
i
o
n
a
l
D
a
ta
S
o
u
rc
e
s
to
Im
p
ro
v
e
In
fl
u
e
n
z
a
S
u
rv
e
il
lan
c
e
,
”
PL
OS
Co
m
p
u
t
.
Bi
o
l
.
,
v
o
l
.
1
1
,
n
o
.
1
0
,
p
.
e
1
0
0
4
5
1
3
,
Oc
t.
2
0
1
5
,
d
o
i:
1
0
.
1
3
7
1
/
jo
u
rn
a
l.
p
c
b
i.
1
0
0
4
5
1
3
.
[8
]
A.
S
h
a
ra
ff
a
n
d
S
.
R
.
R
o
y
,
“
Co
m
p
a
ra
ti
v
e
An
a
l
y
sis
o
f
Tem
p
e
ra
tu
re
P
re
d
icti
o
n
Us
in
g
Re
g
re
ss
io
n
M
e
th
o
d
s
a
n
d
Ba
c
k
P
ro
p
a
g
a
ti
o
n
Ne
u
ra
l
Ne
two
rk
,
”
Pro
c
e
e
d
in
g
s
o
f
th
e
2
n
d
In
ter
n
a
t
io
n
a
l
Co
n
fer
e
n
c
e
o
n
T
re
n
d
s
in
El
e
c
tro
n
ics
a
n
d
In
fo
rm
a
t
ics
,
2
0
1
8
,
p
p
.
4
5
-
5
6
,
d
o
i:
1
0
.
1
1
0
9
/ICOEI.
2
0
1
8
.
8
5
5
3
8
0
3
.
[9
]
E.
S
re
e
h
a
ri,
“
P
re
d
ictio
n
o
f
Cli
m
a
t
e
Va
riab
le
u
sin
g
M
u
l
ti
p
le
Li
n
e
a
r
Re
g
re
ss
io
n
,
”
2
0
1
8
4
th
I
n
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
C
o
mp
u
ti
n
g
C
o
mm
u
n
ic
a
ti
o
n
a
n
d
Au
to
ma
ti
o
n
,
ICCCA
2
0
1
8
,
2
0
1
8
,
p
p
.
7
-
1
0
,
d
o
i:
1
0
.
1
1
0
9
/CCAA.
2
0
1
8
.
8
7
7
7
4
5
2
.
[1
0
]
I.
P
a
rk
,
H.
S
.
Kim
,
J
.
Lee
,
J.
H.
Kim
,
C.
H.
S
o
n
g
,
a
n
d
H.
K.
Kim
,
“
Tem
p
e
ra
tu
re
p
re
d
ictio
n
u
sin
g
t
h
e
m
issin
g
d
a
ta
re
fin
e
m
e
n
t
m
o
d
e
l
b
a
se
d
o
n
a
lo
n
g
s
h
o
rt
-
term
m
e
m
o
ry
n
e
u
ra
l
n
e
two
rk
,
”
At
m
o
sp
h
e
re
(Ba
se
l)
.
,
v
o
l.
1
0
,
n
o
.
1
1
,
p
p
.
1
-
16,
2
0
1
9
,
d
o
i:
1
0
.
3
3
9
0
/atm
o
s1
0
1
1
0
7
1
8
.
[1
1
]
S
.
P
.
M
e
n
o
n
,
“
P
re
d
ictio
n
o
f
T
e
m
p
e
ra
tu
re
u
sin
g
Li
n
e
a
r
Re
g
re
ss
io
n
,
”
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
El
e
c
trica
l,
El
e
c
tro
n
ics
,
Co
mm
u
n
ica
ti
o
n
Co
mp
u
ter
T
e
c
h
n
o
l
o
g
ies
a
n
d
Op
ti
mi
za
ti
o
n
T
e
c
h
n
iq
u
e
s
,
ICEE
CCOT
2
0
1
7
,
p
p
.
1
7
-
2
7
,
2
0
1
7
,
d
o
i:
1
0
.
1
1
0
9
/IC
EE
CCOT.
2
0
1
7
.
8
2
8
4
5
8
8
.
[1
2
]
S
.
P
.
M
e
n
o
n
,
R.
Bh
a
ra
d
wa
j,
P
.
S
h
e
tt
y
,
P
.
S
a
n
u
,
a
n
d
S
.
Na
g
e
n
d
ra
,
“
P
re
d
ictio
n
o
f
tem
p
e
r
a
tu
re
u
sin
g
li
n
e
a
r
re
g
re
ss
io
n
,
”
In
t
.
Co
n
f.
E
lec
tr.
El
e
c
tro
n
.
Co
mm
u
n
.
C
o
mp
u
t.
T
e
c
h
n
o
l.
O
p
ti
m.
T
e
c
h
.
ICEE
CCOT
2
0
1
7
,
v
o
l.
2
0
1
8
-
Ja
n
u
a
,
p
p
.
6
7
0
-
6
7
1
,
2
0
1
8
,
d
o
i
:
1
0
.
1
1
0
9
/IC
EE
CCOT.2
0
1
7
.
8
2
8
4
5
88
.
[1
3
]
T.
K
h
a
n
,
M
.
Ra
b
b
a
n
i,
S
.
M
.
Tan
v
ir
S
i
d
d
iq
u
e
e
,
a
n
d
A.
M
a
j
u
m
d
e
r,
“
An
In
n
o
v
a
ti
v
e
Da
ta
M
i
n
in
g
Ap
p
ro
a
c
h
fo
r
De
term
in
e
Earth
q
u
a
k
e
P
ro
b
a
b
il
it
y
Ba
se
d
o
n
Li
n
e
a
r
Re
g
re
ss
io
n
Al
g
o
rit
h
m
,
”
Pro
c
.
2
0
1
9
3
rd
IEE
E
I
n
t.
C
o
n
f.
El
e
c
tr
.
Co
mp
u
t
.
Co
mm
u
n
.
T
e
c
h
n
o
l
.
IC
E
CCT
2
0
1
9
,
2
0
1
9
,
p
p
.
7
-
1
0
,
d
o
i:
1
0
.
1
1
0
9
/ICE
CCT.
2
0
1
9
.
8
8
6
9
2
8
6
.
[1
4
]
S
.
S
.
P
a
ti
l
a
n
d
S
.
A.
T
h
o
ra
t,
“
Ear
ly
d
e
tec
ti
o
n
o
f
g
ra
p
e
s
d
ise
a
se
s
u
s
in
g
m
a
c
h
in
e
lea
rn
i
n
g
a
n
d
Io
T,
”
i
n
Pro
c
e
e
d
in
g
s
-
20
1
6
2
n
d
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
C
o
g
n
it
ive
Co
m
p
u
t
in
g
a
n
d
I
n
fo
rm
a
ti
o
n
Pr
o
c
e
ss
in
g
,
CC
IP
2
0
1
6
,
2
0
1
6
,
d
o
i:
1
0
.
1
1
0
9
/CCIP
.
2
0
1
6
.
7
8
0
2
8
8
7
.
[1
5
]
P
.
S
.
P
a
n
d
e
y
,
“
M
a
c
h
in
e
Lea
rn
i
n
g
a
n
d
Io
T
fo
r
p
re
d
ictio
n
a
n
d
d
e
tec
ti
o
n
o
f
stre
ss
,
”
in
Pro
c
e
e
d
in
g
s
o
f
th
e
2
0
1
7
1
7
th
In
ter
n
a
t
io
n
a
l
Co
n
fer
e
n
c
e
o
n
Co
mp
u
ta
ti
o
n
a
l
S
c
ie
n
c
e
a
n
d
Its
Ap
p
li
c
a
t
io
n
s
,
ICCS
A
2
0
1
7
,
2
0
1
7
,
d
o
i:
1
0
.
1
1
0
9
/ICCS
A.
2
0
1
7
.
8
0
0
0
0
1
8
.
[1
6
]
M
.
M
o
h
a
m
m
a
d
i,
A.
Al
-
F
u
q
a
h
a
,
S
.
S
o
r
o
u
r,
a
n
d
M
.
G
u
iza
n
i,
“
De
e
p
lea
rn
in
g
fo
r
I
o
T
b
ig
d
a
ta
a
n
d
stre
a
m
in
g
a
n
a
ly
ti
c
s:
A
su
rv
e
y
,
”
IEE
E
C
o
mm
u
n
ica
ti
o
n
s
S
u
rv
e
y
s
a
n
d
T
u
t
o
ria
ls
,
v
o
l
.
2
0
,
n
o
.
4
,
p
p
.
2
9
2
3
-
2
9
6
0
,
2
0
1
8
,
d
o
i:
1
0
.
1
1
0
9
/COM
S
T.
2
0
1
8
.
2
8
4
4
3
4
1
.
[1
7
]
N.
Ba
ra
c
a
ld
o
,
B.
Ch
e
n
,
H.
L
u
d
w
ig
,
A.
S
a
fa
v
i,
a
n
d
R.
Z
h
a
n
g
,
“
De
tec
ti
n
g
p
o
is
o
n
i
n
g
a
tt
a
c
k
s
o
n
m
a
c
h
in
e
lea
rn
i
n
g
in
Io
T
e
n
v
ir
o
n
m
e
n
ts,”
in
P
ro
c
e
e
d
i
n
g
s
-
2
0
1
8
IEE
E
In
ter
n
a
ti
o
n
a
l
C
o
n
g
re
ss
o
n
I
n
ter
n
e
t
o
f
T
h
i
n
g
s,
ICI
OT
2
0
1
8
-
Pa
rt
o
f
t
h
e
2
0
1
8
IEE
E
W
o
rld
C
o
n
g
re
ss
o
n
S
e
rv
ice
s
,
2
0
1
8
,
p
p
.
5
7
-
6
4
,
d
o
i:
1
0
.
1
1
0
9
/ICIOT.
2
0
1
8
.
0
0
0
1
5
.
[1
8
]
O.
G
iu
sto
li
si,
A.
Do
g
li
o
n
i,
D.
A.
S
a
v
ic,
a
n
d
B.
W
.
Web
b
,
“
A
m
u
lt
i
-
m
o
d
e
l
a
p
p
r
o
a
c
h
t
o
a
n
a
l
y
sis
o
f
e
n
v
ir
o
n
m
e
n
ta
l
p
h
e
n
o
m
e
n
a
,
”
En
v
iro
n
.
M
o
d
e
l.
S
o
f
tw
.
,
v
o
l.
2
2
,
n
o
.
5
,
p
p
.
6
7
4
-
6
8
2
,
M
a
y
2
0
0
7
,
d
o
i
:
1
0
.
1
0
1
6
/j
.
e
n
v
s
o
ft.
2
0
0
5
.
1
2
.
0
2
6
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
Dis
ta
n
t te
mp
era
tu
r
e
a
n
d
h
u
mi
d
ity
mo
n
ito
r
in
g
:
p
r
ed
ictio
n
a
n
d
mea
s
u
r
eme
n
t
(
F
a
r
r
u
kh
Ha
fe
ez
)
1413
[1
9
]
D.
Ca
issie
,
“
Th
e
th
e
rm
a
l
re
g
ime
o
f
riv
e
rs:
A
re
v
iew
,
”
F
re
sh
wa
ter
Bio
lo
g
y
,
v
o
l.
5
1
,
n
o
.
8
.
J
o
h
n
Wi
l
e
y
&
S
o
n
s,
Lt
d
,
p
p
.
1
3
8
9
-
1
4
0
6
,
2
0
0
6
,
d
o
i:
1
0
.
1
1
1
1
/j
.
1
3
6
5
-
2
4
2
7
.
2
0
0
6
.
0
1
5
9
7
.
x
.
[2
0
]
B.
G
a
rd
n
e
r,
P
.
J.
S
u
ll
i
v
a
n
,
a
n
d
A
.
J.
Lem
b
o
,
Jr
.
,
“
P
re
d
icti
n
g
stre
a
m
tem
p
e
ra
tu
re
s:
g
e
o
sta
ti
stic
a
l
m
o
d
e
l
c
o
m
p
a
riso
n
u
sin
g
a
lt
e
rn
a
ti
v
e
d
istan
c
e
m
e
tr
ics
,
”
Ca
n
.
J
.
Fi
sh
.
A
q
u
a
t.
S
c
i
.
,
v
o
l.
6
0
,
n
o
.
3
,
p
p
.
3
4
4
-
3
5
1
,
M
a
r.
2
0
0
3
,
d
o
i:
1
0
.
1
1
3
9
/f0
3
-
0
2
5
.
[2
1
]
S
.
Wan
g
,
G
.
M
o
ris
h
ima
,
R.
S
h
a
r
m
a
,
a
n
d
L.
G
il
b
e
rts
o
n
,
“
T
h
e
Us
e
o
f
G
e
n
e
ra
li
z
e
d
Ad
d
it
i
v
e
M
o
d
e
ls
fo
r
F
o
re
c
a
stin
g
th
e
Ab
u
n
d
a
n
c
e
o
f
Qu
e
e
ts
Riv
e
r
Co
h
o
S
a
lmo
n
,
”
No
rth
Am.
J
.
Fi
s
h
.
M
a
n
a
g
.
,
v
o
l.
2
9
,
n
o
.
2
,
p
p
.
4
2
3
-
4
3
3
,
Ap
r.
2
0
0
9
,
d
o
i:
1
0
.
1
5
7
7
/M
0
7
-
0
5
5
.
1
.
[2
2
]
C.
H.
Da
g
li
,
“
M
a
c
h
in
e
Lea
rn
in
g
M
e
th
o
d
s
fo
r
Da
ta
As
sim
il
a
ti
o
n
,
”
In
tell.
En
g
.
S
y
st.
t
h
ro
u
g
h
Arti
f.
N
e
u
ra
l
Ne
two
rk
s
,
v
o
l.
2
0
,
p
p
.
1
0
5
-
1
1
2
,
2
0
1
0
,
d
o
i:
1
0
.
1
1
1
5
/1
.
8
5
9
5
9
9
.
p
a
p
e
r1
4
.
[2
3
]
P
.
Ro
m
e
u
,
F
.
Zam
o
ra
-
M
a
rtí
n
e
z
,
P
.
Bo
tella
-
Ro
c
a
m
o
ra
,
a
n
d
J
.
P
a
rd
o
,
“
Ti
m
e
-
S
e
ries
F
o
re
c
a
stin
g
o
f
In
d
o
o
r
Tem
p
e
ra
tu
re
Us
in
g
P
re
-
trai
n
e
d
De
e
p
Ne
u
ra
l
Ne
two
r
k
s,"
Arti
fi
c
ia
l
Ne
u
ra
l
Ne
two
rk
s
a
n
d
M
a
c
h
i
n
e
L
e
a
r
n
in
g
–
ICANN
2
0
1
3
,
p
p
.
4
5
1
–
4
5
8
,
2
0
1
3
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
6
4
2
-
4
0
7
2
8
-
4
_
5
7
.
[2
4
]
F
.
Zam
o
ra
-
M
a
rtí
n
e
z
,
P
.
R
o
m
e
u
,
P
.
B
o
tella
-
Ro
c
a
m
o
ra
,
a
n
d
J.
P
a
rd
o
,
“
On
-
li
n
e
lea
rn
i
n
g
o
f
in
d
o
o
r
tem
p
e
ra
tu
re
fo
re
c
a
stin
g
m
o
d
e
ls
to
wa
rd
s
e
n
e
rg
y
e
fficie
n
c
y
,
”
En
e
rg
y
Bu
il
d
.
,
v
o
l
.
8
3
,
p
p
.
1
6
2
-
1
7
2
,
No
v
.
2
0
1
4
,
d
o
i:
1
0
.
1
0
1
6
/j
.
e
n
b
u
il
d
.
2
0
1
4
.
0
4
.
0
3
4
.
[2
5
]
M
.
Ho
ss
a
in
,
B.
Re
k
a
b
d
a
r,
S
.
J.
Lo
u
is,
a
n
d
S
.
Da
sc
a
lu
,
“
F
o
re
c
a
stin
g
t
h
e
we
a
th
e
r
o
f
Ne
v
a
d
a
:
A
d
e
e
p
lea
rn
i
n
g
a
p
p
ro
a
c
h
,
”
in
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
I
n
ter
n
a
ti
o
n
a
l
J
o
i
n
t
Co
n
fer
e
n
c
e
o
n
Ne
u
r
a
l
N
e
two
rk
s
,
2
0
1
5
,
d
o
i:
1
0
.
1
1
0
9
/IJCNN
.
2
0
1
5
.
7
2
8
0
8
1
2
.
[2
6
]
H.
Li
n
,
Y.
Hu
a
,
L.
M
a
,
a
n
d
L.
Ch
e
n
,
“
Ap
p
li
c
a
ti
o
n
o
f
Co
n
v
L
S
T
M
n
e
two
r
k
i
n
n
u
m
e
rica
l
tem
p
e
ra
tu
re
p
re
d
icti
o
n
in
terp
re
tatio
n
,
”
i
n
AC
M
I
n
ter
n
a
t
i
o
n
a
l
Co
n
fer
e
n
c
e
Pro
c
e
e
d
in
g
S
e
ri
e
s
,
v
o
l.
P
a
rt
F
1
4
8
1
5
0
,
2
0
1
9
,
p
p
.
1
0
9
-
1
1
3
.
[
2
7
]
M
.
H
o
s
s
a
i
n
,
B
.
Re
k
a
b
d
a
r
,
S
.
J
.
L
o
u
i
s
,
a
n
d
S
.
D
a
s
c
a
l
u
,
“
F
o
r
e
c
a
s
t
i
n
g
th
e
w
e
a
t
h
e
r
o
f
N
e
v
a
d
a
:
A
d
e
e
p
l
e
a
rn
i
n
g
a
p
p
r
o
a
c
h
,
”
P
r
o
c
.
I
n
t
.
J
t
.
C
o
n
f
.
N
e
u
r
a
l
N
e
t
w
o
rk
s
,
v
o
l
.
2
0
1
5
-
S
e
p
t
e
,
p
p
.
2
-
7
,
2
0
1
5
,
d
o
i
:
1
0
.
1
1
0
9
/
I
J
C
N
N
.
2
0
1
5
.
7
2
8
0
8
1
2
.
[2
8
]
A.
G
.
S
a
lm
a
n
,
B.
Ka
n
ig
o
r
o
,
a
n
d
Y.
He
ry
a
d
i,
“
Wea
th
e
r
fo
re
c
a
stin
g
u
sin
g
d
e
e
p
lea
rn
in
g
tec
h
n
i
q
u
e
s,”
ICACSIS
2
0
1
5
-
2
0
1
5
In
t.
Co
n
f.
A
d
v
.
C
o
mp
u
t.
S
c
i.
In
f
.
S
y
st.
Pro
c
.
,
p
p
.
2
8
1
-
2
8
5
,
2
0
1
6
,
d
o
i:
1
0
.
1
1
0
9
/ICAC
S
IS
.
2
0
1
5
.
7
4
1
5
1
5
4
.
[2
9
]
A.
G
o
a
p
,
D.
S
h
a
rm
a
,
A.
K.
S
h
u
k
la,
a
n
d
C.
Ra
m
a
Krish
n
a
,
“
An
Io
T
b
a
se
d
sm
a
rt
irri
g
a
ti
o
n
m
a
n
a
g
e
m
e
n
t
sy
ste
m
u
sin
g
M
a
c
h
in
e
lea
rn
in
g
a
n
d
o
p
e
n
so
u
rc
e
tec
h
n
o
l
o
g
ies
,
”
Co
mp
u
t.
El
e
c
tro
n
.
A
g
ric
.
,
v
o
l.
1
5
5
,
p
p
.
4
1
-
4
9
,
2
0
1
8
,
d
o
i:
1
0
.
1
0
1
6
/j
.
c
o
m
p
a
g
.
2
0
1
8
.
0
9
.
0
4
0
.
[3
0
]
I.
S
ri
Ra
h
a
y
u
,
E
.
C.
Dja
m
a
l,
R.
I
l
y
a
s,
a
n
d
A.
T.
B
o
n
,
“
Da
il
y
tem
p
e
ra
tu
re
p
re
d
icti
o
n
u
si
n
g
re
c
u
rre
n
t
n
e
u
ra
l
n
e
two
rk
s
a
n
d
l
o
n
g
-
sh
o
rt
term
m
e
m
o
ry
,
”
i
n
Pro
c
e
e
d
i
n
g
s
o
f
th
e
I
n
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
In
d
u
stri
a
l
E
n
g
i
n
e
e
rin
g
a
n
d
Op
e
ra
ti
o
n
s M
a
n
a
g
e
me
n
t
,
2
0
2
0
.
[3
1
]
K.
Zh
a
n
g
,
X.
G
e
n
g
,
a
n
d
X.
H.
Y
a
n
,
“
P
re
d
icti
o
n
o
f
3
-
D
Oc
e
a
n
Tem
p
e
ra
tu
re
b
y
M
u
lt
il
a
y
e
r
Co
n
v
o
l
u
ti
o
n
a
l
LS
TM
,
”
IEE
E
Ge
o
sc
i.
Rem
o
te
S
e
n
s.
L
e
tt
.,
v
o
l.
1
7
,
n
o
.
8
,
p
p
.
1
3
0
3
-
1
3
0
7
,
2
0
2
0
,
d
o
i:
1
0
.
1
1
0
9
/L
G
RS
.
2
0
1
9
.
2
9
4
7
1
7
0
.
Evaluation Warning : The document was created with Spire.PDF for Python.