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
9
,
No
.
2
,
A
u
g
u
s
t
2
0
2
5
,
p
p
.
1
072
~
1
0
8
0
I
SS
N:
2502
-
4
7
5
2
,
DOI
: 1
0
.
1
1
5
9
1
/ijeecs.v
3
9
.i
2
.
pp
1
0
7
2
-
1
0
8
0
1072
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs.ia
esco
r
e.
co
m
A multi
-
tie
r f
ra
mewo
rk of d
ecen
tr
a
lized com
puting
env
iro
nment
for
precisio
n ag
ricult
ure (
DCEP
A)
K
ira
n M
un
i
s
wa
m
y
P
a
nd
ura
ng
a
1
,
Ro
o
pa
s
hree
H
ej
j
a
j
i R
a
ng
a
na
t
ha
s
ha
rm
a
2
1
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
G
o
v
e
r
n
me
n
t
E
n
g
i
n
e
e
r
i
n
g
C
o
l
l
e
g
e
,
H
a
ss
a
n
,
A
f
f
i
l
i
a
t
e
d
t
o
V
i
s
v
e
s
v
a
r
a
y
a
T
e
c
h
n
o
l
o
g
i
c
a
l
U
n
i
v
e
r
si
t
y
,
B
e
l
a
g
a
v
i
,
I
n
d
i
a
2
D
e
p
a
r
t
me
n
t
o
f
A
r
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
D
a
t
a
S
c
i
e
n
c
e
,
G
S
S
S
I
n
st
i
t
u
t
e
o
f
E
n
g
i
n
e
e
r
i
n
g
a
n
d
Te
c
h
n
o
l
o
g
y
f
o
r
W
o
me
n
,
M
y
su
r
u
,
A
f
f
i
l
i
a
t
e
d
t
o
V
i
s
v
e
s
v
a
r
a
y
a
T
e
c
h
n
o
l
o
g
i
c
a
l
U
n
i
v
e
r
si
t
y
,
B
e
l
a
g
a
v
i
,
I
n
d
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
No
v
26
,
2
0
2
4
R
ev
is
ed
Mar
20
,
2
0
2
5
Acc
ep
ted
J
u
l
2
,
2
0
2
5
Alth
o
u
g
h
c
o
ll
e
c
ti
n
g
e
n
o
rm
o
u
s
v
o
lu
m
e
s
o
f
h
e
tero
g
e
n
e
o
u
s
d
a
ta
fr
o
m
m
a
n
y
se
n
so
rs
a
n
d
g
u
a
ra
n
tee
in
g
re
a
l
-
ti
m
e
d
e
c
isio
n
-
m
a
k
in
g
a
re
p
ro
b
lem
s,
p
re
c
isio
n
a
g
ricu
lt
u
re
(P
A)
h
a
s
e
m
e
rg
e
d
a
s
a
p
r
o
m
isin
g
a
p
p
ro
a
c
h
to
in
c
re
a
se
a
g
ricu
lt
u
ra
l
e
fficie
n
c
y
.
Th
e
e
ffi
c
a
c
y
o
f
c
u
rre
n
t
c
e
n
tralize
d
so
l
u
ti
o
n
s
is
li
m
it
e
d
in
larg
e
-
sc
a
le
a
g
ricu
lt
u
ra
l
se
tt
in
g
s
d
u
e
t
o
re
so
u
rc
e
li
m
it
a
ti
o
n
s
a
n
d
d
a
ta
sa
tu
ra
ti
o
n
.
I
n
o
rd
e
r
t
o
s
o
l
v
e
th
e
se
p
r
o
b
lem
s,
t
h
is
p
a
p
e
r
s
u
g
g
e
sts
a
d
e
c
e
n
tralize
d
c
o
m
p
u
t
in
g
e
n
v
iro
n
m
e
n
t
fo
r
p
re
c
isio
n
a
g
r
icu
lt
u
re
(
DECP
A),
wh
ich
d
i
v
i
d
e
s
re
so
u
rc
e
m
a
n
a
g
e
m
e
n
t
a
n
d
d
a
ta
p
ro
c
e
ss
in
g
a
m
o
n
g
se
v
e
ra
l
lay
e
rs
(e
n
d
,
e
d
g
e
,
a
n
d
c
lo
u
d
).
DE
CP
A
o
p
ti
m
ize
s
tas
k
e
x
e
c
u
ti
o
n
a
n
d
re
so
u
rc
e
a
ll
o
c
a
ti
o
n
i
n
th
e
field
b
y
u
t
il
izin
g
e
n
se
m
b
le
m
a
c
h
in
e
lea
rn
in
g
m
o
d
e
ls
(
d
e
e
p
n
e
u
ra
l
n
e
two
r
k
(
DNN
)
,
lo
n
g
sh
o
r
t
-
term
m
e
m
o
ry
(
LS
TM
)
,
a
u
t
o
e
n
c
o
d
e
r
(
AE
)
,
a
n
d
s
u
p
p
o
rt
v
e
c
to
r
m
a
c
h
i
n
e
(
S
VM
)
)
a
n
d
a
m
u
lt
i
-
t
ier
a
rc
h
it
e
c
tu
re
.
T
h
e
fin
d
i
n
g
s
d
e
m
o
n
stra
te
th
a
t
DECP
A
c
o
m
b
in
e
d
wit
h
DN
N
p
e
rfo
rm
s
b
e
tt
e
r
t
h
a
n
a
lt
e
rn
a
ti
v
e
m
o
d
e
ls,
a
c
h
ie
v
in
g
a
2
0
%
d
e
c
re
a
se
in
e
n
e
rg
y
u
sa
g
e
,
a
n
1
8
%
sp
e
e
d
u
p
i
n
re
sp
o
n
se
ti
m
e
,
a
5
%
imp
ro
v
e
m
e
n
t
in
a
c
c
u
ra
c
y
,
a
n
d
a
5
1
%
re
d
u
c
ti
o
n
i
n
late
n
c
y
.
Th
is
il
l
u
stra
tes
th
e
sy
ste
m
’
s
c
a
p
a
c
it
y
t
o
m
a
n
a
g
e
m
a
ss
iv
e
a
m
o
u
n
ts
o
f
d
a
ta
e
ffe
c
ti
v
e
ly
wh
il
e
p
re
se
rv
i
n
g
p
e
a
k
p
e
rfo
r
m
a
n
c
e
.
To
su
m
u
p
,
DECP
A
u
se
s
d
e
c
e
n
tral
ize
d
re
so
u
rc
e
s
a
n
d
c
u
tt
in
g
-
e
d
g
e
m
a
c
h
in
e
lea
rn
in
g
m
o
d
e
ls
to
p
ro
v
i
d
e
a
sc
a
lab
le
a
n
d
a
ff
o
rd
a
b
le
p
re
c
isio
n
a
g
ricu
lt
u
r
e
so
lu
ti
o
n
.
To
imp
r
o
v
e
t
h
e
sy
ste
m
’
s
flex
ib
il
it
y
a
n
d
re
a
l
-
ti
m
e
re
sp
o
n
siv
e
n
e
ss
,
fu
tu
re
re
se
a
rc
h
will
in
v
e
sti
g
a
te
a
d
d
it
i
o
n
a
l
o
p
ti
m
iza
ti
o
n
a
n
d
u
se
in
v
a
rio
u
s
a
g
ricu
lt
u
ra
l
c
o
n
te
x
ts.
K
ey
w
o
r
d
s
:
Dec
en
tr
alize
d
E
d
g
e
Fu
s
io
n
Ma
ch
in
e
lear
n
in
g
Pre
cisi
o
n
ag
r
icu
ltu
r
e
R
eso
u
r
ce
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
:
Kir
an
Mu
n
is
wam
y
Pan
d
u
r
an
g
a
Dep
ar
tm
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
an
d
E
n
g
in
ee
r
in
g
,
G
o
v
er
n
m
en
t E
n
g
in
ee
r
in
g
C
o
lleg
e
Hass
an
,
Af
f
iliated
to
Vis
v
esv
ar
ay
a
T
ec
h
n
o
lo
g
ical
Un
i
v
er
s
ity
B
elag
av
i
-
5
9
0
0
1
8
,
Kar
n
atak
a,
I
n
d
ia
E
m
ail: m
tech
.
k
ir
an
@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
a
r
e
a
o
f
p
r
e
ci
s
i
o
n
a
g
r
i
c
u
l
tu
r
e
(
P
A
)
ca
l
ls
f
o
r
a
d
o
p
t
i
n
g
v
ar
i
o
u
s
a
d
v
a
n
c
e
d
te
c
h
n
o
l
o
g
i
e
s
th
a
t
c
a
n
b
e
u
s
e
d
f
o
r
au
to
n
o
m
o
u
s
m
a
n
a
g
e
m
e
n
t
o
f
f
a
r
m
i
n
g
r
e
g
i
o
n
[
1
]
.
T
h
e
p
r
i
m
a
r
y
g
o
a
l o
f
PA
is
t
o
w
a
r
d
s
o
p
t
i
m
i
z
i
n
g
v
a
r
i
o
u
s
s
p
e
c
i
f
i
c
r
e
s
o
u
r
c
es
(
p
es
t
i
ci
d
e
s
,
s
e
e
d
s
,
f
e
r
ti
l
i
ze
r
s
,
a
n
d
w
a
t
e
r
)
a
d
o
p
t
e
d
i
n
a
n
y
s
t
a
n
d
a
r
d
a
g
r
i
c
u
lt
u
r
a
l
p
r
a
c
t
ic
e
s
w
it
h
a
n
i
n
t
e
n
t
i
o
n
t
o
wa
r
d
s
i
m
p
r
o
v
i
n
g
e
f
f
i
c
i
e
n
c
y
i
n
f
a
r
m
i
n
g
,
m
i
n
i
m
i
zin
g
e
n
v
i
r
o
n
m
e
n
t
a
l
i
m
p
a
c
t
,
a
n
d
e
n
h
a
n
c
i
n
g
y
i
e
l
d
o
f
c
r
o
p
s
[
2
]
.
V
a
r
i
o
u
s
k
e
y
c
o
m
p
o
n
e
n
t
s
i
n
P
A
a
r
e
s
e
n
s
o
r
s
an
d
i
n
t
e
r
n
e
t
-
of
-
t
h
i
n
g
s
(
I
o
T
)
,
u
s
a
g
e
o
f
g
e
o
s
p
at
i
al
t
e
c
h
n
o
l
o
g
y
,
d
r
o
n
e
s
a
n
d
a
e
r
i
al
im
a
g
i
n
g
,
d
a
t
a
a
n
a
l
y
ti
cs
,
a
u
t
o
m
at
e
d
e
q
u
i
p
m
e
n
t
s
(
e
.
g
.
m
a
c
h
i
n
a
r
ie
s
,
h
a
r
v
e
r
s
t
e
r
s
,
a
n
d
t
r
a
c
t
o
r
s
)
,
a
n
d
v
a
r
i
a
b
l
e
r
a
te
te
c
h
n
o
l
o
g
y
[
3
]
-
[
8
]
.
T
h
e
r
e
i
s
a
n
i
n
c
r
e
a
s
i
n
g
a
t
te
n
t
i
o
n
o
f
PA
a
m
o
n
g
s
c
i
e
n
t
i
f
ic
c
o
m
m
u
n
i
t
y
w
h
i
c
h
c
a
n
b
e
a
tt
r
i
b
u
t
e
d
b
y
p
o
s
i
t
i
v
e
r
at
i
o
n
a
l
e
e
.
g
.
s
u
s
t
a
i
n
a
b
il
i
t
y
,
r
es
o
u
r
c
e
e
f
f
i
ci
e
n
c
y
,
i
n
c
r
e
a
s
e
d
y
ie
l
d
,
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
A
mu
lti
-
tier
fr
a
mewo
r
k
o
f d
ec
en
tr
a
liz
ed
co
mp
u
tin
g
e
n
viro
n
men
t fo
r
…
(
K
ir
a
n
Mu
n
is
w
a
m
y
P
a
n
d
u
r
a
n
g
a
)
1073
a
n
d
d
a
t
a
-
d
r
i
v
e
n
d
e
c
i
s
i
o
n
.
H
o
we
v
e
r
,
P
A
i
s
a
ls
o
c
h
a
r
a
c
t
e
r
i
z
e
d
b
y
v
a
r
i
o
u
s
c
h
a
l
l
e
n
g
e
s
t
o
o
.
T
h
e
i
n
i
t
i
a
l
c
h
a
ll
e
n
g
e
is
t
h
a
t
P
A
i
n
v
o
l
v
es
h
i
g
h
e
r
i
n
i
t
i
a
l
c
o
s
t
w
h
i
c
h
is
m
a
i
n
l
y
d
u
e
t
o
i
n
c
l
u
s
i
o
n
o
f
v
a
r
i
o
u
s
d
e
v
i
c
e
s
a
n
d
t
e
c
h
n
o
l
o
g
y
t
h
a
t
a
l
s
o
d
e
m
a
n
d
s
s
p
ec
i
f
i
c
w
a
y
o
f
c
o
n
f
i
g
u
r
i
n
g
a
n
d
m
a
i
n
t
a
i
n
i
n
g
f
o
r
lo
n
g
-
t
e
r
m
o
p
e
r
a
t
i
o
n
.
PA
is
al
s
o
c
h
a
r
a
c
t
e
r
i
ze
d
b
y
v
o
l
u
m
i
n
o
u
s
y
i
e
l
d
o
f
a
g
r
i
c
u
lt
u
r
a
l
d
a
t
a
f
r
o
m
v
a
r
i
o
u
s
s
e
n
s
i
n
g
d
e
v
i
c
e
s
w
h
i
l
e
s
u
c
h
m
a
s
s
i
v
el
y
g
e
n
e
r
a
t
e
d
d
a
t
a
a
ls
o
d
e
m
a
n
d
s
a
p
r
o
p
e
r
w
a
y
t
o
i
n
t
e
g
r
a
t
e
t
h
e
m
.
O
w
i
n
g
t
o
i
n
c
l
u
s
i
o
n
o
f
h
e
t
e
r
o
g
e
n
e
o
u
s
f
o
r
m
s
o
f
d
e
v
i
c
e
s
,
t
h
e
c
o
m
p
l
e
x
i
t
y
o
f
i
n
t
e
g
r
a
t
i
n
g
s
u
c
h
d
a
t
a
a
r
i
s
es
e
x
p
o
n
e
n
t
i
a
l
l
y
.
F
r
o
m
t
h
e
v
i
ew
p
o
i
n
t
o
f
i
n
f
r
a
s
t
r
u
c
t
u
r
e
a
n
d
co
n
n
e
c
t
i
v
i
t
y
,
u
s
u
a
ll
y
f
a
r
m
i
n
g
a
r
e
a
a
r
e
l
o
c
at
e
d
r
e
m
o
t
e
l
y
w
h
e
r
e
b
e
tt
e
r
s
i
g
n
a
l
q
u
a
l
i
ty
c
a
n
n
o
t
b
e
a
n
t
i
c
i
p
at
e
d
m
u
c
h
.
T
h
i
s
a
c
ts
as
m
a
i
n
o
b
s
t
a
c
l
e
t
o
wa
r
d
s
i
m
p
l
e
m
e
n
ti
n
g
s
m
a
r
t f
a
r
m
i
n
g
o
p
e
r
at
i
o
n
s
.
T
h
e
o
t
h
e
r
c
h
al
l
e
n
g
e
s
a
r
e
d
a
t
a
p
r
i
v
ac
y
a
n
d
s
e
c
u
r
i
t
y
[
9
]
a
n
d
e
n
v
i
r
o
n
m
e
n
t
a
l
f
a
c
t
o
r
s
[
1
0
]
.
S
u
c
h
c
h
a
l
l
e
n
g
e
s
a
r
e
a
n
a
l
y
z
e
d
t
o
b
e
w
e
l
l
-
a
d
d
r
e
s
s
e
d
b
y
a
d
o
p
t
i
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
e
s
[
1
1
]
-
[
1
3
]
.
E
x
e
r
c
i
s
i
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
e
s
o
n
f
i
e
l
d
d
a
t
a
ca
n
o
f
f
e
r
p
r
e
d
i
c
t
i
v
e
a
n
a
l
y
s
is
o
f
y
i
e
l
d
,
w
e
a
t
h
e
r
,
d
i
s
ea
s
e
i
n
c
r
o
p
s
.
D
e
e
p
l
e
a
r
n
i
n
g
i
s
al
r
e
a
d
y
i
n
v
e
s
t
i
g
a
te
d
b
y
v
a
r
i
o
u
s
r
e
s
e
a
r
c
h
e
r
s
t
o
w
a
r
d
s
p
r
e
d
i
c
t
i
n
g
n
u
t
r
i
e
n
t
d
e
f
i
c
ie
n
c
y
,
p
e
s
t
i
n
f
e
s
ta
t
i
o
n
,
d
is
e
as
e
b
y
a
n
a
l
y
z
i
n
g
i
m
a
g
es
o
f
f
a
r
m
i
n
g
r
e
g
i
o
n
[
1
4
]
.
H
o
w
e
v
e
r
,
e
x
i
s
ti
n
g
r
e
s
e
a
r
c
h
w
o
r
k
u
s
i
n
g
d
e
e
p
l
e
a
r
n
i
n
g
i
s
o
f
t
e
n
f
o
u
n
d
t
o
b
e
m
o
r
e
i
n
c
l
i
n
e
d
t
o
w
a
r
d
s
ac
c
o
m
p
l
i
s
h
i
n
g
h
i
g
h
e
r
a
c
c
u
r
a
c
y
w
h
i
l
e
t
h
e
e
x
t
e
n
s
i
v
e
co
m
p
u
t
a
t
i
o
n
a
l
a
n
d
r
e
s
o
u
r
c
e
c
o
s
t
i
s
o
f
t
e
n
i
g
n
o
r
e
d
.
H
o
w
e
v
e
r
,
m
a
c
h
i
n
e
le
a
r
n
i
n
g
m
o
d
e
l
s
a
ls
o
e
n
c
o
u
n
t
e
r
s
v
a
r
i
o
u
s
r
o
u
n
d
s
o
f
o
n
-
g
o
i
n
g
p
r
a
c
t
i
c
a
l
is
s
u
es
.
T
h
e
f
i
r
s
t
is
s
u
e
is
r
e
l
at
e
d
t
o
p
o
o
r
d
a
ta
a
v
a
i
l
a
b
il
i
t
y
a
n
d
s
u
b
-
o
p
t
i
m
a
l
q
u
a
l
i
t
y
o
f
i
t
w
h
i
c
h
is
m
a
i
n
l
y
d
u
e
t
o
i
n
c
r
e
a
s
e
d
c
o
s
t
a
s
s
o
ci
a
t
e
d
w
it
h
d
a
t
a
c
o
l
l
e
c
ti
o
n
.
A
d
o
p
t
i
o
n
o
f
P
A
a
l
s
o
c
a
l
l
s
f
o
r
a
d
o
p
t
i
n
g
m
u
l
t
i
p
l
e
d
e
v
i
c
e
s
a
n
d
t
e
c
h
n
o
l
o
g
i
e
s
w
h
i
ch
f
u
r
t
h
e
r
g
i
v
e
r
is
e
t
o
d
i
v
e
r
s
i
f
i
ed
d
a
t
a
t
h
at
a
r
e
q
u
it
e
c
h
al
l
e
n
g
i
n
g
t
o
a
n
a
l
y
z
e
i
n
r
e
al
-
t
i
m
e
o
w
i
n
g
t
o
l
a
c
k
o
f
s
t
a
n
d
a
r
d
i
z
at
i
o
n
.
A
n
o
t
h
e
r
c
r
i
ti
ca
l
p
r
o
b
l
e
m
i
s
t
h
a
t
e
x
i
s
ti
n
g
s
t
u
d
i
e
s
u
s
i
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
m
o
d
e
l
s
h
a
v
e
m
a
i
n
l
y
f
o
c
u
s
e
d
o
n
u
s
e
-
c
a
s
e
o
f
c
r
o
p
s
o
r
s
p
e
c
i
f
i
c
f
a
r
m
i
n
g
as
p
e
c
t
wi
th
o
u
t
c
o
n
s
i
d
e
r
i
n
g
v
a
r
y
i
n
g
c
o
n
d
i
t
i
o
n
a
s
s
o
c
i
at
e
d
w
it
h
i
t
.
S
u
c
h
m
o
d
ellin
g
m
a
y
s
u
i
t
w
e
l
l
f
o
r
s
t
a
n
d
a
l
o
n
e
p
r
o
b
l
e
m
a
d
d
r
e
s
s
i
n
g
b
u
t
i
t
s
l
a
c
k
o
f
g
en
e
r
a
l
i
z
a
ti
o
n
l
e
a
d
s
t
o
n
a
r
r
o
w
e
d
s
c
o
p
e
o
f
a
p
p
l
i
c
a
b
il
i
ty
t
o
o
t
h
e
r
s
e
t
o
f
p
r
o
b
l
e
m
s
.
H
en
c
e
,
t
h
e
y
a
r
e
n
o
t
c
o
s
t
-
e
f
f
ec
t
i
v
e
w
h
e
n
i
t
c
o
m
es
t
o
p
r
a
c
t
i
c
a
l
w
o
r
l
d
d
e
p
l
o
y
m
e
n
t
.
Fu
r
t
h
e
r
,
m
a
c
h
i
n
e
l
ea
r
n
i
n
g
m
o
d
e
l
s
a
r
e
b
u
i
l
d
o
n
t
r
ai
n
e
d
d
a
t
a
w
it
h
s
p
e
c
i
f
i
c
r
a
n
g
e
o
f
f
e
a
t
u
r
e
s
w
h
i
c
h
w
il
l
w
o
r
k
w
el
l
w
h
e
n
t
h
e
y
a
r
e
v
a
l
i
d
a
te
d
w
i
t
h
s
i
m
i
l
a
r
s
e
t
o
f
u
n
t
r
a
i
n
e
d
d
a
ta
;
h
o
w
e
v
e
r
,
t
h
e
p
r
o
b
l
e
m
s
h
o
o
t
s
u
p
w
h
e
n
t
h
e
y
a
r
e
e
x
p
o
s
e
d
t
o
d
i
v
e
r
s
i
f
i
e
d
c
l
i
m
at
i
c
c
o
n
d
i
t
i
o
n
o
n
u
n
f
o
r
e
s
e
e
n
v
a
r
i
a
b
l
e
s
.
T
h
i
s
p
h
e
n
o
m
e
n
o
n
l
e
a
d
s
t
o
o
u
t
l
i
e
r
s
e
v
e
n
t
u
a
l
l
y
.
St
i
l
l
,
a
f
t
e
r
al
l
t
h
e
s
e
s
h
o
r
t
c
o
m
i
n
g
s
,
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
is
al
w
a
y
s
a
b
et
t
e
r
a
n
d
c
o
s
t
-
e
f
f
e
c
t
i
v
e
c
h
o
i
ce
t
o
i
m
p
l
e
m
e
n
t
a
p
r
o
a
c
t
i
v
e
s
o
l
u
t
i
o
n
f
o
r
i
m
p
r
o
v
i
n
g
t
h
e
o
v
e
r
a
l
l
p
e
r
f
o
r
m
a
n
c
e
o
f
P
A
.
I
t
i
s
b
e
c
a
u
s
e
o
f
t
h
e
r
e
a
s
o
n
t
h
a
t
d
i
f
f
e
r
e
n
t
v
a
r
ia
n
t
s
o
f
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
e
x
is
ts
w
h
i
l
e
t
h
e
y
a
r
e
s
t
i
ll
i
n
n
a
s
c
e
n
t
s
t
a
g
e
s
t
o
b
e
i
n
v
e
s
t
i
g
at
e
d
.
W
it
h
i
ts
p
o
w
e
r
to
r
e
a
l
i
z
e
t
h
e
c
o
m
p
l
e
x
p
a
tt
e
r
n
o
f
p
r
o
b
l
e
m
s
,
m
a
c
h
i
n
e
l
ea
r
n
i
n
g
s
t
il
l
o
f
f
e
r
a
b
et
t
er
c
h
o
i
c
e
t
o
u
n
d
e
r
s
t
a
n
d
t
h
e
p
r
o
b
l
em
.
Var
io
u
s
r
elate
d
wo
r
k
h
as
b
ee
n
s
tu
d
ied
in
p
er
s
p
ec
tiv
e
o
f
m
ac
h
in
e
le
ar
n
in
g
ad
o
p
tio
n
to
u
n
d
er
s
tan
d
th
eir
ef
f
ec
tiv
en
ess
.
T
h
e
a
d
o
p
t
io
n
o
f
l
o
n
g
s
h
o
r
t
-
ter
m
m
em
o
r
y
(
L
STM
)
h
as
b
ee
n
p
r
esen
te
d
b
y
Gaf
u
r
o
v
et
a
l.
[
1
5
]
i
n
o
r
d
er
t
o
p
er
f
o
r
m
p
r
ed
ictiv
e
an
aly
s
is
o
f
cr
o
p
r
ec
o
g
n
itio
n
i
n
PA.
B
h
im
av
ar
a
p
u
et
a
l.
[
1
6
]
h
a
v
e
p
r
esen
ted
a
p
r
ed
ictiv
e
m
o
d
el
wh
en
L
STM
is
u
s
ed
f
o
r
o
p
ti
m
izin
g
p
r
e
d
ictiv
e
p
er
f
o
r
m
a
n
c
e
to
war
d
s
cr
o
p
y
ield
r
ate.
Similar
d
ir
ec
tio
n
to
war
d
s
p
r
ed
ictiv
e
p
er
f
o
r
m
an
ce
o
p
ti
m
izatio
n
is
also
ca
r
r
ie
d
o
u
t
b
y
Sh
en
et
a
l.
[
1
7
]
wh
er
e
r
an
d
o
m
f
o
r
est
(
R
F)
is
jo
in
tly
u
s
ed
with
L
STM
to
war
d
s
an
aly
z
in
g
g
r
o
wth
r
ate
o
f
cr
o
p
s
.
An
o
th
e
r
v
er
s
io
n
o
f
d
ee
p
lear
n
in
g
m
o
d
el
k
n
o
wn
as
au
to
en
c
o
d
er
(
AE
)
is
im
p
lem
en
ted
b
y
Mu
jk
ic
et
a
l.
[
1
8
]
in
o
r
d
e
r
to
u
n
d
er
s
tan
d
th
e
d
eg
r
ee
o
f
a
n
o
m
alies
f
o
llo
wed
b
y
p
o
s
itiv
ely
co
n
f
ir
m
in
g
th
em
f
o
r
ag
r
icu
ltu
r
al
v
eh
icles.
I
atr
o
u
et
a
l.
[
1
9
]
h
av
e
d
ev
elo
p
ed
a
p
r
ed
ictiv
e
m
o
d
el
to
war
d
s
r
ea
lizin
g
n
itro
g
e
n
d
em
an
d
s
u
s
in
g
v
ar
iatio
n
al
AE
wh
er
e
tr
an
s
f
o
r
m
ed
d
ata
r
ep
r
es
en
tatio
n
is
lear
n
ed
t
o
ex
tr
ac
t
f
ea
tu
r
e
f
o
llo
wed
b
y
an
o
m
al
y
d
etec
tio
n
.
B
ai
et
al.
[
2
0
]
h
av
e
p
r
esen
ted
d
is
cu
s
s
io
n
o
f
t
h
e
AE
with
s
tack
ed
s
tr
u
ctu
r
e
in
clu
s
iv
e
o
f
en
c
o
d
er
a
n
d
d
ec
o
d
e
r
in
o
r
d
er
to
ca
teg
o
r
ize
th
e
im
ag
es
o
b
tain
e
d
f
r
o
m
r
em
o
te
s
en
s
in
g
d
ev
ice
s
.
Al
-
Nae
em
et
a
l.
[
2
1
]
h
a
v
e
u
s
ed
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
(
SVM)
in
o
r
d
e
r
to
p
er
f
o
r
m
m
o
n
ito
r
in
g
o
f
th
e
cr
o
p
s
b
y
co
n
tr
o
llin
g
th
e
m
o
v
em
en
t
an
d
lo
ca
tio
n
o
f
u
n
m
an
n
ed
ae
r
ial
v
e
h
icle
(
UAV)
.
Ad
o
p
tio
n
o
f
SVM
is
also
witn
ess
ed
to
ad
d
r
ess
th
e
class
i
f
icatio
n
p
r
o
b
lem
s
o
f
s
tr
ess
-
r
elate
d
tr
aits
am
o
n
g
p
lan
ts
as
n
o
ticed
in
wo
r
k
p
r
esen
t
ed
b
y
I
s
lam
et
a
l.
[
2
2
]
.
L
y
u
et
a
l.
[
2
3
]
h
av
e
u
s
ed
g
au
s
s
ian
Naïv
e
B
ay
es
(
GNB
)
class
if
icatio
n
ap
p
r
o
ac
h
f
o
r
esti
m
atin
g
th
e
ce
n
ter
lin
e
o
f
ag
r
icu
ltu
r
e
ar
ea
.
Ad
o
p
tio
n
o
f
d
ee
p
n
eu
r
al
n
etwo
r
k
(
DNN)
h
as
b
ee
n
also
witn
ess
ed
in
ex
is
tin
g
liter
atu
r
es
o
f
PA.
J
in
et
a
l.
[
2
4
]
h
av
e
co
n
s
tr
u
cted
a
p
r
e
d
icto
r
u
s
in
g
DNN
to
i
n
v
esti
g
ate
th
e
in
f
lu
en
ce
o
f
wea
th
er
o
n
cr
o
p
s
in
s
m
ar
t
f
ar
m
in
g
wh
er
e
tr
ain
in
g
is
ca
r
r
ie
d
o
u
t
u
s
in
g
g
ated
r
ec
u
r
r
en
t
u
n
its
.
R
eg
az
zo
et
a
l.
[
2
5
]
h
av
e
u
s
ed
co
n
v
o
l
u
tio
n
n
eu
r
al
n
etwo
r
k
to
war
d
s
s
o
lv
in
g
clas
s
if
icatio
n
p
r
o
b
lem
s
u
s
in
g
im
a
g
es
o
f
leaf
s
.
An
o
th
e
r
in
ter
est
in
g
wo
r
k
h
as
b
ee
n
d
em
o
n
s
tr
a
ted
b
y
C
am
a
-
Pin
to
et
a
l.
[
2
6
]
to
war
d
s
s
tu
d
y
in
g
p
r
o
p
ag
atio
n
o
f
r
ad
io
wav
es.
T
h
e
r
esear
ch
p
r
o
b
lem
s
ex
tr
ac
ted
f
r
o
m
ex
is
tin
g
s
tu
d
ies
ar
e
m
an
if
o
ld
th
at
d
em
an
d
s
to
b
e
ad
d
r
ess
ed
.
Fo
llo
win
g
ar
e
s
o
m
e
cr
itical
ar
ea
o
f
p
r
o
b
lem
s
v
iz.
i)
n
o
n
e
o
f
t
h
e
ex
is
tin
g
s
tu
d
ies
u
s
in
g
m
ac
h
in
e
lear
n
in
g
m
o
d
els
h
av
e
y
et
ad
d
r
ess
ed
th
e
p
r
o
b
lem
s
ass
o
ciate
d
with
d
ata
tr
an
s
m
is
s
io
n
co
n
s
id
er
in
g
r
eso
u
r
ce
co
n
s
tr
ain
ts
am
o
n
g
s
en
s
o
r
s
d
ep
lo
y
ed
o
n
f
ield
,
ii)
s
tu
d
ies
ar
e
ev
alu
ate
d
with
ac
cu
r
ac
y
i
g
n
o
r
i
n
g
p
o
s
s
ib
le
laten
cy
an
d
r
eso
u
r
ce
s
th
at
ar
e
eq
u
ally
af
f
ec
ted
wh
ile
p
er
f
o
r
m
in
g
o
n
-
f
i
eld
o
p
er
atio
n
s
in
PA,
iii)
ex
i
s
tin
g
s
tu
d
ies
h
av
e
co
n
s
id
er
ed
d
ata
g
ath
e
r
ed
f
r
o
m
o
n
e
f
ield
o
r
s
p
ec
if
ic
to
o
n
e
ty
p
e
o
f
cr
o
p
to
p
er
f
o
r
m
p
r
e
d
ictio
n
ig
n
o
r
in
g
th
e
r
o
le
o
f
ac
tu
ato
r
s
in
PA,
an
d
iv
)
d
e
cisi
o
n
m
ad
e
b
y
m
ac
h
in
e
lear
n
in
g
m
o
d
els
o
f
f
er
e
d
o
n
ly
o
n
e
p
r
ed
ictiv
e
o
u
tco
m
e
with
o
u
t c
o
n
s
id
er
in
g
th
e
c
h
allen
g
ed
in
v
o
lv
e
d
in
r
elay
i
n
g
th
e
i
n
f
o
r
m
atio
n
b
ac
k
to
th
e
f
ield
(
t
o
ac
tu
ato
r
s
)
.
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.
3
9
,
No
.
2
,
Au
g
u
s
t
20
25
:
1
0
7
2
-
1
080
1074
T
h
e
aim
o
f
th
e
p
r
o
p
o
s
ed
s
ch
em
e
is
to
ad
d
r
ess
th
e
ab
o
v
e
-
m
en
tio
n
ed
p
r
o
b
lem
b
y
p
r
e
s
en
tin
g
a
d
ec
en
tr
alize
d
ar
ch
itectu
r
e
u
s
in
g
m
ac
h
in
e
lear
n
i
n
g
.
T
h
e
v
alu
e
-
ad
d
e
d
co
n
tr
ib
u
tio
n
o
f
th
e
s
tu
d
y
ar
e
as
f
o
llo
ws:
i)
th
e
m
u
lti
-
tier
d
ec
e
n
tr
alize
d
ar
ch
itectu
r
e
is
p
r
esen
ted
t
o
s
h
ar
e
th
e
o
v
er
all
o
p
er
atio
n
r
elate
d
to
g
en
e
r
alize
d
ap
p
licatio
n
s
o
f
PA,
ii)
ed
g
e
co
m
p
u
tin
g
s
er
v
er
s
h
av
e
b
ee
n
co
n
s
id
er
ed
to
ad
d
r
ess
th
e
s
p
ee
d
ily
d
is
s
ip
ated
r
eso
u
r
ce
s
f
o
r
s
en
s
o
r
n
o
d
es,
i
ii)
a
clo
u
d
en
v
ir
o
n
m
en
t
h
as
b
ee
n
co
n
s
id
er
e
d
wh
er
e
m
ac
h
in
e
lear
n
in
g
b
ased
an
aly
tical
p
r
o
ce
s
s
in
g
is
ca
r
r
i
ed
o
u
t
to
co
n
t
r
o
l
o
p
er
atio
n
s
o
f
ac
tu
ato
r
s
as
well
as
d
at
a
an
aly
s
is
f
o
r
f
ield
in
f
o
r
m
atio
n
ca
p
tu
r
e
d
b
y
s
en
s
o
r
s
.
T
h
e
n
ex
t sectio
n
elab
o
r
ates
th
e
ad
o
p
ted
m
eth
o
d
o
lo
g
y
o
f
t
h
e
s
t
udy.
2.
M
E
T
H
O
D
T
h
e
p
r
im
ar
y
aim
o
f
th
e
p
r
o
p
o
s
ed
s
tu
d
y
is
to
d
ev
elo
p
a
d
ec
en
tr
alize
d
co
m
p
u
tin
g
en
v
ir
o
n
m
en
t
th
at
is
ca
p
ab
le
o
f
ad
d
r
ess
in
g
th
e
p
r
o
b
lem
ass
o
ciate
d
with
o
v
er
lo
ad
d
ata
m
an
ag
em
en
t
in
PA
an
d
h
en
ce
th
e
m
o
d
el
is
n
am
ed
as
d
ec
en
tr
alize
d
co
m
p
u
tin
g
e
n
v
ir
o
n
m
en
t
f
o
r
p
r
ec
is
i
o
n
a
g
r
icu
ltu
r
e
(
DC
E
PA)
.
T
h
e
im
p
lem
en
tatio
n
o
f
th
e
p
r
o
p
o
s
ed
s
tu
d
y
is
ca
r
r
ied
o
u
t
co
n
s
id
er
in
g
an
aly
tical
r
es
ea
r
ch
m
eth
o
d
o
l
o
g
y
wh
er
e
th
e
in
ten
tio
n
is
to
war
d
s
d
ev
elo
p
in
g
a
f
lex
ib
le
a
n
d
s
tr
ea
m
lin
ed
tr
an
s
m
is
s
io
n
o
f
ag
r
icu
ltu
r
al
f
ield
i
n
f
o
r
m
atio
n
c
o
n
s
id
er
in
g
clo
u
d
-
I
o
T
ar
ch
itectu
r
e
with
ed
g
e
co
m
p
u
tin
g
.
T
h
e
s
ec
o
n
d
ar
y
aim
o
f
th
e
s
tu
d
y
is
to
war
d
s
o
u
ts
o
u
r
cin
g
th
e
task
o
f
d
ata
an
aly
tics
to
ed
g
e
n
o
d
es
in
o
r
d
er
to
co
n
s
er
v
e
th
e
r
eso
u
r
c
es
d
em
an
d
ed
b
y
s
en
s
o
r
y
d
e
v
ices
o
n
th
e
f
ield
.
T
h
e
ar
ch
itectu
r
e
f
o
r
DC
E
PA
is
s
h
o
wn
in
Fig
u
r
e
1
.
Fig
u
r
e
1
.
Ar
c
h
itectu
r
e
o
f
DC
E
PA
Acc
o
r
d
in
g
to
Fig
u
r
e
1
,
it
ca
n
b
e
n
o
ted
th
at
p
r
o
p
o
s
ed
DC
E
PA
is
d
esig
n
ed
o
n
3
-
lay
er
ed
ar
ch
itectu
r
e
th
at
co
m
p
r
is
es
o
f
e
n
d
lay
er
,
ed
g
e
lay
er
,
an
d
cl
o
u
d
lay
er
.
T
h
e
ag
e
n
d
a
to
war
d
s
th
e
ad
o
p
ted
r
esear
ch
m
eth
o
d
o
l
o
g
y
is
m
ain
ly
to
wa
r
d
s
en
s
u
r
in
g
s
ea
m
less
an
d
h
ig
h
ly
s
tr
u
ctu
r
ed
ac
q
u
is
itio
n
o
f
f
ield
d
ata
f
r
o
m
m
u
ltip
le
o
r
ig
in
atio
n
p
o
in
t
b
e
ar
in
g
h
eter
o
g
en
o
u
s
f
ield
s
o
f
ag
r
icu
ltu
r
al
d
ata.
E
ac
h
lay
er
in
ter
ac
ts
with
ea
ch
o
th
er
to
en
s
u
r
e
th
at
th
e
f
in
al
o
u
tco
m
e
ass
is
t
i
n
b
o
th
en
r
ich
ed
ac
q
u
is
itio
n
o
f
f
ield
in
f
o
r
m
atio
n
f
o
llo
wed
b
y
r
elay
in
g
o
f
f
in
al
d
ec
is
io
n
-
m
ak
in
g
co
m
m
an
d
s
t
o
th
e
ac
tu
ato
r
s
o
n
th
e
f
ield
s
.
T
h
e
d
etailed
i
n
f
o
r
m
atio
n
o
f
ea
c
h
lay
er
o
p
e
r
atio
n
s
ar
e
as f
o
llo
ws
:
2
.
1
.
E
nd
la
y
er
o
pera
t
i
o
n
T
h
e
en
d
lay
er
is
th
e
b
o
tto
m
lay
er
in
DE
C
PA
ar
ch
itectu
r
e
wh
ich
m
ain
ly
co
m
p
r
is
es
o
f
t
wo
ty
p
es
o
f
d
ev
ices
v
iz.
i)
s
en
s
o
r
y
d
ev
ices
to
ca
p
tu
r
e
f
ield
in
f
o
r
m
atio
n
an
d
ii)
ac
tu
ato
r
s
to
ca
r
r
y
o
u
t
s
p
ec
if
ic
ag
r
icu
ltu
r
e
r
elate
d
task
.
Fig
u
r
e
2
,
s
h
o
ws m
ec
h
an
is
m
an
d
en
ti
ties
with
in
en
d
lay
er
o
p
e
r
atio
n
.
As
th
e
p
r
o
p
o
s
ed
a
r
ch
itectu
r
e
is
m
ea
n
t
f
o
r
g
en
er
aliza
tio
n
,
h
en
ce
,
n
o
s
p
ec
if
ic
u
s
e
-
ca
s
e
s
ce
n
ar
io
is
ap
p
licab
le;
h
o
wev
er
,
DE
C
PA
co
n
s
id
er
s
th
at
th
ese
s
en
s
o
r
y
d
e
v
ices
co
u
ld
b
e
s
o
il
s
en
s
o
r
,
clim
ate
an
d
wea
th
er
s
en
s
o
r
,
cr
o
p
h
ea
lth
s
en
s
o
r
,
air
q
u
ality
s
en
s
o
r
,
s
en
s
o
r
s
f
o
r
ir
r
ig
atio
n
an
d
wate
r
m
an
ag
em
e
n
t,
r
o
b
o
t
ic
an
d
au
to
m
atio
n
s
en
s
o
r
s
.
E
ac
h
s
en
s
o
r
s
co
llect
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
A
mu
lti
-
tier
fr
a
mewo
r
k
o
f d
ec
en
tr
a
liz
ed
co
mp
u
tin
g
e
n
viro
n
men
t fo
r
…
(
K
ir
a
n
Mu
n
is
w
a
m
y
P
a
n
d
u
r
a
n
g
a
)
1075
th
e
in
f
o
r
m
atio
n
f
r
o
m
ag
r
icu
ltu
r
al
f
ield
u
s
in
g
tim
e
d
iv
is
io
n
m
u
ltip
le
ac
ce
s
s
(
T
DM
A)
an
d
f
o
r
war
d
s
all
th
e
d
ata
to
a
lo
ca
l
g
atew
ay
n
o
d
e.
T
h
e
lo
ca
l
g
atew
ay
n
o
d
e
ca
r
r
y
o
u
t
d
ata
f
u
s
io
n
o
p
er
atio
n
wh
er
e
th
e
f
u
s
ed
d
ata
is
f
u
r
th
er
f
o
r
war
d
e
d
to
ed
g
e
n
o
d
es
in
its
u
p
p
er
lay
er
.
DE
C
P
A
also
co
n
s
id
er
s
in
clu
s
io
n
o
f
ac
tu
ato
r
s
wh
ich
is
m
ain
ly
m
ea
n
t
f
o
r
ex
ec
u
tin
g
c
er
tain
ag
r
icu
lt
u
r
e
r
elate
d
task
af
ter
r
ec
eiv
in
g
th
e
co
m
m
an
d
s
f
r
o
m
l
o
ca
l
g
atew
ay
n
o
d
e.
T
h
e
ac
t
u
ato
r
co
n
s
id
er
ed
in
d
esig
n
o
f
DE
C
PA
co
u
ld
b
e
r
elate
d
to
ce
r
tain
u
n
m
an
n
ed
tr
ac
to
r
s
o
r
au
to
m
atic
wate
r
/p
esti
cid
e
s
p
r
in
k
ler
s
,
o
r
it
wo
u
ld
b
e
s
o
m
e
d
ev
ice
th
at
co
u
ld
ca
p
t
u
r
e
s
elec
tiv
e
in
f
o
r
m
atio
n
b
ased
o
n
ev
e
n
t c
r
iticality
.
All th
e
s
en
s
o
r
s
ar
e
in
ter
co
n
n
ec
ted
to
ea
ch
o
th
er
an
d
p
er
f
o
r
m
ed
t
h
eir
p
r
o
ce
s
s
o
f
d
ata
ac
q
u
is
itio
n
an
d
p
r
o
ce
s
s
in
g
b
a
s
ed
o
n
f
o
r
m
atio
n
o
f
n
etwo
r
k
with
o
th
er
s
en
s
o
r
s
.
All
th
e
s
en
s
o
r
s
ar
e
co
n
s
id
er
e
d
to
b
e
d
ep
lo
y
e
d
with
a
d
ef
in
itiv
e
r
eso
u
r
ce
s
wh
i
ch
in
f
o
r
m
at
io
n
’
s
ar
e
r
etain
ed
with
in
th
e
lo
ca
l
g
atew
ay
.
As
p
r
o
p
o
s
ed
DE
C
PA ta
r
g
ets
a
lar
g
e
-
s
ca
le
d
ec
en
tr
alize
d
o
p
er
ati
o
n
,
it c
o
n
s
id
er
s
p
r
esen
ce
o
f
v
a
r
io
u
s
lo
ca
l g
atew
ay
ass
ig
n
ed
to
d
if
f
er
en
t
f
ar
m
i
n
g
ar
ea
s
in
d
if
f
er
en
t
g
eo
g
r
a
p
h
ical
r
eg
io
n
s
.
All
th
e
lo
ca
l
g
at
ewa
y
f
u
r
th
er
co
m
m
u
n
icate
s
with
ed
g
e
lay
e
r
in
o
r
d
er
t
o
ca
r
r
y
o
u
t
th
eir
r
esp
ec
tiv
e
task
i.e
.
,
d
ata
f
u
s
io
n
f
r
o
m
in
f
o
r
m
atio
n
ca
p
tu
r
ed
f
r
o
m
s
en
s
o
r
y
d
e
v
ices a
n
d
r
elay
i
n
g
co
m
m
an
d
s
to
ac
tu
ato
r
s
to
ca
r
r
y
o
u
t sp
ec
if
ic
task
.
Fig
u
r
e
2
.
Me
ch
a
n
is
m
with
in
e
n
d
lay
er
2
.
2
.
E
dg
e
la
y
er
o
pera
t
io
n
T
h
e
p
r
o
p
o
s
ed
s
y
s
tem
o
f
DE
C
PA
in
tr
o
d
u
ce
s
e
d
g
e
lay
e
r
in
o
r
d
er
to
o
f
f
er
c
o
m
p
u
tin
g
s
u
p
p
o
r
t
to
war
d
s
p
r
o
p
er
r
eso
u
r
ce
m
an
a
g
em
en
t a
s
s
h
o
wn
in
Fig
u
r
e
3
.
T
h
e
r
atio
n
ale
b
e
h
in
d
i
n
tr
o
d
u
cin
g
e
d
g
e
lay
er
ar
e
m
an
if
o
ld
.
C
o
n
v
en
tio
n
al
s
en
s
o
r
-
b
ased
ap
p
r
o
ac
h
es
in
PA
u
s
u
ally
r
el
y
o
n
d
ata
-
d
r
i
v
en
m
eth
o
d
o
l
o
g
ies
wh
en
ea
ch
s
en
s
o
r
is
b
u
r
d
e
n
ed
with
ac
q
u
is
itio
n
o
f
v
o
lu
m
in
o
u
s
in
f
o
r
m
atio
n
f
r
o
m
ag
r
icu
ltu
r
al
f
ar
m
f
o
llo
wed
b
y
p
r
o
ce
s
s
in
g
th
em
.
T
h
is
p
h
en
o
m
en
o
n
s
atu
r
ates
e
x
ce
s
s
iv
e
r
eso
u
r
ce
s
o
f
s
en
s
o
r
s
.
Fu
r
th
er
,
e
x
is
t
in
g
m
ec
h
a
n
is
m
o
f
s
en
s
o
r
n
etwo
r
k
in
d
u
lg
e
th
em
s
elv
es in
to
r
o
u
tin
g
o
p
er
atio
n
s
u
s
in
g
s
o
p
h
is
ticated
tr
an
s
m
is
s
io
n
p
r
o
to
co
l,
wh
i
ch
d
is
s
ip
ates e
n
er
g
y
ap
ar
t
f
r
o
m
t
h
e
en
er
g
y
d
r
ain
e
d
b
y
its
s
elf
-
h
ar
d
war
e
-
r
elate
d
o
p
er
atio
n
b
y
co
n
s
is
ten
t
m
o
n
ito
r
in
g
.
Fu
r
t
h
er
,
th
e
lo
ad
o
f
in
f
o
r
m
atio
n
p
r
o
ce
s
s
in
g
d
if
f
er
s
f
r
o
m
o
n
e
s
en
s
o
r
t
o
a
n
o
th
er
wh
ile
im
p
licatio
n
o
f
s
im
ilar
r
o
u
tin
g
s
ch
em
e
m
ay
r
esu
lt
in
h
ig
h
er
f
l
u
ctu
atio
n
an
d
in
c
o
n
s
is
ten
cies
o
f
p
er
f
o
r
m
an
ce
o
f
s
en
s
o
r
.
T
h
is
co
u
l
d
ev
en
tu
ally
lead
to
f
aster
r
eso
u
r
ce
d
r
ai
n
ag
e
al
o
n
g
with
s
u
b
-
o
p
t
im
al
q
u
ality
o
f
d
ata
ac
q
u
is
itio
n
p
r
o
ce
s
s
.
Hen
ce
,
DE
C
PA
in
tr
o
d
u
ce
s
f
o
g
n
o
d
es
wh
ich
c
an
ad
d
r
ess
th
is
ch
allen
g
es.
T
h
e
task
o
f
s
en
s
o
r
n
o
d
e
is
ju
s
t
to
ac
q
u
ir
e
d
ata
a
n
d
f
o
r
war
d
th
em
to
e
d
g
e
n
o
d
es
wh
er
e
d
ata
f
u
s
io
n
is
ca
r
r
ie
d
o
u
t
u
n
lik
e
ex
is
tin
g
ap
p
r
o
ac
h
es
wh
er
e
ag
g
r
e
g
atio
n
an
d
f
u
s
io
n
is
ca
r
r
ied
o
u
t
with
i
n
s
en
s
o
r
n
o
d
es.
T
h
is
lay
er
co
n
s
is
t
s
o
f
m
u
ltip
le
n
u
m
b
er
o
f
e
d
g
e
n
o
d
es
wh
ich
ar
e
co
n
n
ec
ted
in
d
ec
en
tr
alize
d
m
a
n
n
er
with
ea
ch
o
th
er
s
y
n
cin
g
i
n
f
o
r
m
atio
n
g
ath
e
r
ed
f
r
o
m
all
t
h
e
lo
ca
l
g
atew
ay
s
f
r
o
m
en
d
lay
er
.
T
h
e
e
d
g
e
n
o
d
es
p
er
f
o
r
m
s
m
u
ltip
le
task
as
f
o
llo
ws:
i)
it
f
u
s
es
th
e
d
ata
f
o
llo
wed
b
y
p
r
ep
r
o
ce
s
s
in
g
th
e
d
ata
an
d
f
o
r
war
d
th
e
p
r
ep
r
o
ce
s
s
ed
d
ata
to
n
ex
t u
p
p
er
lay
e
r
o
f
clo
u
d
,
ii)
it id
en
tifie
s
th
e
lo
ad
o
n
ea
ch
s
en
s
o
r
alo
n
g
with
m
o
n
ito
r
in
g
th
eir
r
esp
ec
tiv
e
r
eso
u
r
ce
s
to
ca
r
r
y
o
u
t
t
h
e
task
.
I
n
ca
s
e,
if
ed
g
e
n
o
d
e
f
in
d
s
o
n
e
o
f
its
s
en
s
o
r
s
to
h
av
e
r
ed
u
ce
d
r
eso
u
r
ce
s
,
it
id
en
tifie
s
a
n
eig
h
b
o
r
in
g
s
en
s
o
r
with
s
u
f
f
icien
t
r
eso
u
r
ce
s
an
d
o
u
ts
o
u
r
ce
/s
p
lit
th
e
task
o
f
ag
g
r
e
g
atin
g
t
h
e
s
en
s
o
r
y
d
at
a.
Acc
o
r
d
in
g
ly
,
it
alter
s
th
e
t
o
p
o
lo
g
y
to
en
s
u
r
e
r
eso
u
r
ce
s
o
f
ea
ch
s
en
s
o
r
s
ar
e
o
p
tim
ally
u
s
ed
.
iii)
Fin
ally
,
th
e
ed
g
e
n
o
d
e
f
o
r
war
d
s
h
ier
ar
ch
ies
o
f
co
m
m
an
d
s
to
lo
ca
l g
atew
ay
n
o
d
e
wh
ich
a
r
e
th
en
r
elay
ed
to
ac
tu
ato
r
s
.
Fig
u
r
e
3
.
Me
ch
a
n
is
m
with
in
e
d
g
e
lay
er
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.
3
9
,
No
.
2
,
Au
g
u
s
t
20
25
:
1
0
7
2
-
1
080
1076
2
.
3
.
Clo
ud
la
y
er
o
pera
t
io
n
T
h
is
is
th
e
to
p
m
o
s
t
lay
er
o
f
DE
C
PA
wh
ich
is
b
asical
ly
r
esp
o
n
s
ib
le
to
u
n
d
er
tak
e
s
o
m
e
cr
itical
d
ec
is
io
n
to
en
s
u
r
e
ef
f
icien
t o
p
er
atio
n
o
f
g
iv
e
n
s
m
ar
t f
ield
as sh
o
wn
in
Fig
u
r
e
4
.
T
h
e
p
r
im
ar
y
task
o
f
th
is
lay
er
is
to
ac
q
u
ir
e
th
e
p
r
ep
r
o
ce
s
s
ed
in
f
o
r
m
atio
n
f
r
o
m
ed
g
e
lay
er
.
T
h
e
p
r
ep
r
o
ce
s
s
ed
in
f
o
r
m
ati
o
n
f
r
o
m
its
b
o
tto
m
lay
er
(
ed
g
e
lay
er
)
c
o
n
s
is
ts
o
f
o
n
-
f
ield
d
ata
alo
n
g
with
s
tatu
s
o
f
s
en
s
o
r
n
o
d
es.
T
h
e
p
r
ep
r
o
ce
s
s
ed
d
ata
is
th
en
s
u
b
jecte
d
to
v
ar
io
u
s
m
ac
h
in
e
l
ea
r
n
in
g
m
o
d
els
wh
ich
u
n
d
er
ta
k
es
its
f
in
al
d
ec
is
io
n
th
at
is
r
e
lay
ed
b
ac
k
to
ed
g
e
n
o
d
es.
T
h
e
m
ac
h
in
e
lear
n
in
g
m
o
d
el
u
s
ed
b
y
DE
C
PA
p
er
f
o
r
m
s
f
o
llo
win
g
task
:
th
e
m
o
d
el
t
ak
es
m
u
ltip
le
in
p
u
t
o
f
p
r
ep
r
o
ce
s
s
ed
d
ata,
ex
tr
ac
ts
f
ea
tu
r
es,
an
d
ca
r
r
y
o
u
t
its
p
r
ed
ictiv
e
o
p
er
atio
n
.
T
h
e
o
b
jectiv
e
f
u
n
ctio
n
o
f
th
is
o
p
er
atio
n
is
to
f
in
d
o
u
t
o
p
tim
al
s
e
n
s
o
r
n
o
d
e
with
s
u
f
f
icien
t
r
eso
u
r
ce
s
as
well
as
m
ak
e
a
s
eq
u
en
tial
lis
tin
g
o
f
n
o
d
es
b
ased
o
n
o
r
d
er
o
f
th
ei
r
r
eso
u
r
ce
s
.
T
h
is
in
f
o
r
m
atio
n
o
u
tco
m
e
s
ig
n
if
ican
tl
y
ass
is
ts
th
e
e
d
g
e
n
o
d
e
to
in
s
tan
tly
s
elec
t
a
n
o
d
e
with
h
ig
h
er
r
eso
u
r
ce
s
in
ca
s
es
s
o
m
e
o
f
t
h
e
n
eig
h
b
o
r
in
g
n
o
d
e
s
ar
e
d
ep
letin
g
its
r
eso
u
r
ce
s
f
astl
y
.
An
o
th
er
o
b
j
ec
tiv
e
f
u
n
ctio
n
o
f
th
is
lay
e
r
i
s
r
elate
d
to
ac
tiv
atin
g
th
e
ac
t
u
ato
r
b
y
r
elay
in
g
a
s
p
ec
if
ic
co
m
m
an
d
.
T
h
e
m
ac
h
in
e
lear
n
in
g
m
o
d
el
p
er
f
o
r
m
it
s
p
r
ed
ictiv
e
an
aly
s
is
to
f
o
r
ec
ast
th
e
in
s
tan
ce
o
f
tim
e,
lo
ca
ti
o
n
,
an
d
s
elec
tiv
e
o
p
er
atio
n
to
b
e
e
x
ec
u
ted
b
y
an
ac
tu
ato
r
.
As
th
e
co
m
p
lete
o
p
er
atio
n
is
h
o
s
ted
u
n
d
er
clo
u
d
en
v
ir
o
n
m
e
n
t
m
an
ag
ed
b
y
s
er
v
ice
p
r
o
v
id
er
,
h
en
ce
n
o
s
p
ec
if
ic
c
o
n
ce
r
n
o
f
r
es
o
u
r
ce
u
tili
za
tio
n
in
th
is
lay
er
is
co
n
s
id
er
ed
o
win
g
to
ass
u
m
p
tio
n
o
f
h
ig
h
-
en
d
r
eso
u
r
ce
s
.
Fig
u
r
e
4
.
Me
ch
a
n
is
m
with
in
c
lo
u
d
lay
er
3.
RE
SU
L
T
S
Prio
r
to
im
p
lem
en
t
DE
C
PA,
it
is
n
o
ted
th
at
ex
is
tin
g
d
atas
et
f
o
r
PA
is
u
s
u
ally
im
ag
e
-
b
ased
wh
ile
s
tr
in
g
-
o
r
ien
ted
d
ataset
is
d
em
an
d
ed
in
p
r
o
p
o
s
ed
s
tu
d
y
(
o
w
in
g
to
ad
o
p
tio
n
o
f
s
en
s
o
r
s
)
.
Hen
ce
,
a
s
y
n
th
etic
d
ataset
h
as
b
ee
n
d
esig
n
ed
with
5
0
,
0
0
0
f
ield
s
ca
p
tu
r
i
n
g
in
f
o
r
m
atio
n
o
f
f
ield
h
y
p
o
th
etica
lly
d
esig
n
ed
.
T
h
e
s
tu
d
y
f
u
r
t
h
er
c
o
n
s
id
er
s
5
0
0
s
en
s
o
r
s
,
1
0
lo
ca
l
g
atew
a
y
n
o
d
es,
an
d
4
f
o
g
n
o
d
es
in
s
im
u
latio
n
ar
ea
o
f
1
,
1
0
0
x
1
,
500
m
2
with
7
d
is
cr
ete
g
eo
g
r
a
p
h
ical
f
ar
m
in
g
lo
c
atio
n
.
Pro
p
o
s
ed
DE
C
PA
h
as
b
ee
n
test
if
ied
with
m
u
lti
p
le
m
ac
h
in
e
lear
n
in
g
m
o
d
els
(
e.
g
.
,
L
STM
,
DNN,
AE
,
an
d
SVM)
wh
ich
ar
e
r
ep
o
r
t
ed
to
b
e
f
r
e
q
u
en
tly
ad
o
p
ted
i
n
ex
is
tin
g
liter
atu
r
es
in
PA.
T
h
e
p
e
r
f
o
r
m
an
ce
m
et
r
ic
co
n
s
id
er
ed
ar
e
en
e
r
g
y
co
n
s
u
m
p
tio
n
,
r
esp
o
n
s
e
tim
e,
ac
cu
r
ac
y
,
a
n
d
laten
cy
.
T
ab
le
1
s
h
o
wca
s
es
th
e
n
u
m
e
r
ical
o
u
tco
m
e
o
f
t
h
e
v
ar
ied
co
m
b
in
atio
n
o
f
DE
C
PA
wh
ich
s
tates
th
at
DE
C
PA
p
er
f
o
r
m
s
o
p
tim
ally
wh
en
c
o
m
b
in
ed
with
DNN.
T
h
e
ac
co
m
p
lis
h
ed
o
u
tco
m
e
s
h
o
ws
th
at
DE
C
PA
-
DNN
to
o
f
f
er
ap
p
r
o
x
im
ately
2
0
%
o
f
r
ed
u
ce
d
e
n
er
g
y
co
n
s
u
m
p
tio
n
,
1
8
%
o
f
f
a
s
ter
r
esp
o
n
s
e
tim
e,
5
%
o
f
i
n
cr
ea
s
ed
ac
cu
r
ac
y
,
an
d
5
1
%
o
f
m
in
im
ized
lat
en
cy
.
Fo
r
b
etter
u
n
d
er
s
tan
d
in
g
,
th
e
g
r
ap
h
ical
r
ep
r
esen
tatio
n
o
f
r
esp
ec
tiv
e
n
u
m
er
ical
s
co
r
es a
r
e
s
h
o
wn
in
Fig
u
r
e
5
.
T
ab
le
1
.
Nu
m
e
r
ical
a
cc
o
m
p
lis
h
m
en
t o
f
DE
C
PA
A
p
p
r
o
a
c
h
e
s
En
e
r
g
y
c
o
n
su
m
p
t
i
o
n
(
%)
R
e
s
p
o
n
se
t
i
me
(
s)
A
c
c
u
r
a
c
y
(
%)
La
t
e
n
c
y
(
s)
D
EC
P
A
-
LSTM
5
3
.
7
1
.
9
0
2
9
3
.
6
0
.
8
1
7
D
EC
P
A
-
DNN
2
7
.
8
0
.
5
7
8
9
8
.
7
0
.
1
8
1
D
EC
P
A
-
AE
3
8
.
2
2
.
6
7
1
9
5
.
6
0
.
6
2
2
D
EC
P
A
-
S
V
M
4
6
.
9
1
.
9
9
8
9
2
.
6
0
.
8
0
9
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
A
mu
lti
-
tier
fr
a
mewo
r
k
o
f d
ec
en
tr
a
liz
ed
co
mp
u
tin
g
e
n
viro
n
men
t fo
r
…
(
K
ir
a
n
Mu
n
is
w
a
m
y
P
a
n
d
u
r
a
n
g
a
)
1077
Acc
o
r
d
in
g
to
co
m
p
ar
ativ
e
an
aly
s
is
o
f
Fig
u
r
e
5
(
a)
,
it
ca
n
b
e
n
o
ted
th
at
L
STM
an
d
GNB
in
d
u
ce
s
m
o
r
e
en
e
r
g
y
co
n
s
u
m
p
tio
n
w
h
ich
is
m
ain
ly
d
u
e
t
o
co
m
p
lex
ities
ass
o
ciate
d
with
b
o
th
th
e
m
o
d
els
wh
en
ex
p
o
s
ed
to
lar
g
er
d
ataset.
Similar
ly
,
r
esp
o
n
s
e
tim
e
f
o
r
AE
an
d
GNB
i
s
n
o
ted
to
b
e
q
u
ite
h
ig
h
er
th
at
ca
n
b
e
ju
s
tifie
d
b
y
co
n
s
tr
ain
ts
o
f
th
is
m
o
d
els
to
war
d
s
wo
r
k
in
g
o
n
s
eq
u
en
tial
d
ata
alo
n
g
with
tr
a
in
in
g
co
m
p
le
x
ities
Fig
u
r
e
5
(
b
)
.
T
h
e
ac
c
u
r
ac
y
to
war
d
s
d
ec
is
io
n
m
ak
in
g
b
y
L
STM
,
SVM,
an
d
GNB
ar
e
q
u
ite
s
im
ilar
wh
er
e
s
ca
lab
ilit
y
is
s
u
es
s
u
r
f
ac
es
w
h
en
in
ter
ac
tio
n
is
p
er
f
o
r
m
ed
b
y
ed
g
e
lay
e
r
an
d
clo
u
d
la
y
er
with
s
ea
m
less
ly
g
r
o
win
g
d
ata
Fig
u
r
e
5
(
c
)
.
T
h
e
s
im
ilar
r
ea
s
o
n
ar
e
also
n
o
t
ed
to
war
d
s
h
i
g
h
er
laten
cy
Fi
g
u
r
e
5
(
d
)
.
DE
C
PA
wh
en
co
m
b
in
e
d
with
DNN
o
f
f
er
s
an
ex
ten
s
iv
e
ab
ilit
y
to
m
o
d
el
co
m
p
le
x
r
elatio
n
s
h
ip
b
etwe
en
all
th
e
in
p
u
t
v
ar
iab
les
o
f
f
e
r
in
g
b
alan
ce
b
et
wee
n
ac
cu
r
ac
y
an
d
o
th
e
r
p
e
r
f
o
r
m
an
ce
m
etr
ic.
Ap
a
r
t
f
r
o
m
t
h
is
,
DNN
is
n
o
ted
to
q
u
ite
ca
p
ab
le
o
f
m
a
n
ag
in
g
la
r
g
er
s
tr
ea
m
o
f
d
ataset
in
clu
s
iv
e
o
f
m
u
ltip
le
f
ea
tu
r
es.
Hen
c
e,
p
r
o
p
o
s
ed
s
y
s
tem
ex
ce
ls
b
etter
r
esu
lt
wh
e
n
co
m
b
in
ed
with
DNN
in
m
u
ltip
le
p
er
s
p
ec
tiv
e
in
PA
o
v
er
all
ex
h
ib
itin
g
a
c
o
s
t
-
ef
f
ec
tiv
e
d
ep
l
o
y
m
en
t.
(
a)
(
b
)
(
c)
(
d
)
Fig
u
r
e
5
.
E
v
alu
atio
n
o
u
tco
m
e
f
o
r
(
a)
en
er
g
y
co
n
s
u
m
p
tio
n
,
(
b
)
r
esp
o
n
s
e
tim
e,
(
c
)
ac
cu
r
ac
y
,
an
d
(
d
)
laten
cy
Acc
o
r
d
in
g
t
o
th
e
s
tu
d
y
’
s
f
in
d
i
n
g
s
,
th
e
DE
C
PA
is
s
u
cc
es
s
f
u
l,
esp
ec
ially
wh
en
co
m
b
in
ed
w
ith
DNN.
Sig
n
if
ican
t
p
er
f
o
r
m
an
ce
g
ain
s
wer
e
ac
h
iev
ed
b
y
co
m
b
i
n
in
g
DE
C
PA
an
d
DNN,
in
clu
d
in
g
a
2
0
%
d
ec
r
ea
s
e
in
en
er
g
y
u
s
ag
e,
an
1
8
%
s
p
ee
d
u
p
in
r
esp
o
n
s
e
tim
e,
a
5
%
i
m
p
r
o
v
e
m
en
t
in
ac
c
u
r
ac
y
,
a
n
d
a
5
1
%
d
ec
r
ea
s
e
in
laten
cy
.
T
h
ese
r
esu
lts
d
em
o
n
s
tr
ate
h
o
w
well
t
h
e
s
y
s
tem
ca
n
m
an
ag
e
r
eso
u
r
ce
s
an
d
ca
r
r
y
o
u
t
task
s
in
ex
ten
s
iv
e
ag
r
icu
ltu
r
al
s
e
ttin
g
s
.
On
e
o
f
th
e
m
ain
ar
g
u
m
en
ts
i
n
f
a
v
o
r
o
f
DNN
’
s
s
u
p
er
i
o
r
ity
o
v
er
o
th
er
m
ac
h
in
e
lear
n
in
g
m
o
d
els,
s
u
ch
as
L
S
T
M,
SVM,
an
d
AE
,
is
it
s
ca
p
ac
ity
to
m
an
ag
e
in
tr
icate
d
a
tasets
an
d
v
ar
iab
le
r
elatio
n
s
h
ip
s
,
wh
ich
m
ak
es it
m
o
r
e
f
lex
i
b
le
in
th
e
f
ac
e
o
f
c
h
an
g
in
g
f
ie
ld
co
n
d
itio
n
s
an
d
d
i
v
er
s
e
s
en
s
o
r
d
ata.
I
t
is
ev
id
en
t
f
r
o
m
co
m
p
ar
in
g
t
h
ese
f
in
d
in
g
s
to
ea
r
lier
PA
r
es
ea
r
ch
th
at
tr
a
d
itio
n
al
ap
p
r
o
ac
h
es,
wh
ich
f
r
eq
u
e
n
tly
r
ely
o
n
ce
n
tr
alize
d
s
y
s
tem
s
o
r
s
en
s
o
r
-
b
ased
ag
g
r
e
g
atio
n
,
h
a
v
e
tr
o
u
b
le
with
r
eso
u
r
ce
ef
f
icien
cy
an
d
s
ca
la
b
ilit
y
.
Prio
r
s
tu
d
ies
h
av
e
d
em
o
n
s
tr
ated
th
e
d
r
awb
ac
k
s
o
f
ce
n
tr
alize
d
d
ata
p
r
o
ce
s
s
in
g
,
wh
ich
f
r
eq
u
e
n
tly
lead
s
to
d
ata
c
o
n
g
esti
o
n
a
n
d
ex
ce
s
s
iv
e
e
n
er
g
y
u
s
ag
e
(
e.
g
.
,
L
STM
an
d
SVM
i
n
th
is
s
tu
d
y
)
.
T
h
e
im
p
lem
en
tatio
n
o
f
a
m
u
lti
-
tier
d
ec
en
t
r
alize
d
ar
c
h
itectu
r
e
w
it
h
ed
g
e
co
m
p
u
tin
g
in
th
is
wo
r
k
,
h
o
wev
e
r
,
is
a
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.
3
9
,
No
.
2
,
Au
g
u
s
t
20
25
:
1
0
7
2
-
1
080
1078
n
o
tab
le
ad
v
an
ce
m
e
n
t.
T
h
is
s
tr
ateg
y
’
s
p
r
im
a
r
y
ad
v
an
tag
e
is
its
d
is
tr
ib
u
ted
r
eso
u
r
ce
m
an
ag
em
en
t,
w
h
ich
less
en
s
th
e
b
o
ttlen
ec
k
s
th
at
tr
a
d
itio
n
al
s
y
s
tem
s
en
co
u
n
ter
.
Ho
wev
er
,
o
n
e
d
r
awb
ac
k
is
th
at
th
e
s
y
s
tem
r
eq
u
ir
es
a
s
ig
n
if
ican
t
n
u
m
b
er
o
f
s
en
s
o
r
s
an
d
co
m
p
u
tatio
n
al
p
o
wer
t
o
o
p
er
ate
c
o
m
p
letely
,
wh
ich
co
u
ld
b
e
d
if
f
icu
lt
i
n
s
ettin
g
s
with
f
ewe
r
r
eso
u
r
ce
s
.
T
h
e
s
eq
u
en
tial
n
atu
r
e
o
f
th
e
AE
m
o
d
el
’
s
d
ata
p
r
o
ce
s
s
in
g
,
wh
ich
h
as
tr
o
u
b
le
h
an
d
lin
g
b
ig
d
atasets
an
d
th
e
d
em
an
d
s
o
f
r
e
al
-
tim
e
d
ec
is
io
n
-
m
ak
i
n
g
in
PA,
is
p
r
o
b
ab
l
y
th
e
r
ea
s
o
n
wh
y
it
u
n
ex
p
ec
te
d
ly
f
ar
e
d
p
o
o
r
ly
i
n
t
er
m
s
o
f
r
esp
o
n
s
e
tim
e
an
d
late
n
cy
.
T
h
e
p
u
r
p
o
s
e
o
f
th
is
s
tu
d
y
was
to
p
r
esen
t
a
n
ew
d
ec
e
n
tr
alize
d
co
m
p
u
tatio
n
al
f
r
a
m
ewo
r
k
f
o
r
en
h
an
cin
g
p
r
ec
is
io
n
a
g
r
icu
ltu
r
e
d
ec
is
io
n
-
m
ak
in
g
an
d
r
eso
u
r
ce
ef
f
icien
cy
.
T
h
e
f
i
n
d
in
g
s
h
i
g
h
lig
h
t
th
e
v
alu
e
o
f
in
teg
r
atin
g
cu
ttin
g
-
ed
g
e
m
ac
h
in
e
lear
n
in
g
m
eth
o
d
s
with
e
d
g
e
co
m
p
u
tin
g
to
tack
le
is
s
u
es
in
co
n
tem
p
o
r
ar
y
ag
r
icu
ltu
r
e,
s
u
ch
h
an
d
lin
g
m
ass
iv
e
d
ata
s
ets
an
d
g
u
ar
an
te
ein
g
r
ea
l
-
tim
e
r
esp
o
n
s
iv
e
n
es
s
.
T
h
e
s
tu
d
y
o
f
f
er
s
in
s
ig
h
tf
u
l
in
f
o
r
m
atio
n
a
b
o
u
t
th
e
a
d
v
an
ta
g
es
o
f
a
m
u
lti
-
lay
er
ed
,
d
ec
en
t
r
alize
d
s
tr
ate
g
y
.
T
h
e
s
y
s
tem
’
s
s
ca
lab
ilit
y
in
ev
en
b
i
g
g
er
,
m
o
r
e
v
ar
ie
d
ag
r
ic
u
ltu
r
al
co
n
te
x
ts
is
s
till
u
p
f
o
r
d
eb
ate,
th
o
u
g
h
.
Fu
t
u
r
e
s
tu
d
ies
m
ig
h
t
co
n
ce
n
tr
ate
o
n
ex
am
i
n
in
g
o
th
er
m
ac
h
in
e
lear
n
in
g
m
o
d
els
f
o
r
p
ar
ticu
lar
ag
r
ic
u
ltu
r
al
ac
tiv
ities
o
r
r
ef
in
in
g
t
h
e
in
f
r
astru
ct
u
r
e
f
o
r
s
m
aller
-
s
ca
le
d
ep
lo
y
m
en
ts
.
Fu
r
th
er
m
o
r
e
,
in
v
esti
g
atin
g
h
o
w
clo
u
d
-
ed
g
e
s
y
n
er
g
y
an
d
I
o
T
in
teg
r
atio
n
m
ig
h
t
im
p
r
o
v
e
th
e
f
r
am
ewo
r
k
wo
u
l
d
o
f
f
er
ch
an
ce
s
to
in
cr
e
ase
th
e
s
y
s
tem
’
s
ef
f
ec
tiv
en
ess
an
d
af
f
o
r
d
a
b
ilit
y
.
4.
CO
NCLU
SI
O
N
T
h
e
ap
p
licatio
n
o
f
m
o
d
er
n
c
o
m
p
u
tin
g
tech
n
o
lo
g
y
in
ag
r
icu
ltu
r
e,
n
o
tab
l
y
PA,
h
as
th
e
p
o
ten
tial
to
tr
an
s
f
o
r
m
h
o
w
we
m
an
ag
e
r
e
s
o
u
r
ce
s
,
in
cr
ea
s
e
cr
o
p
y
ield
s
,
an
d
m
ak
e
m
o
r
e
in
f
o
r
m
ed
,
d
at
a
-
d
r
iv
e
n
d
ec
is
io
n
s
.
As
g
lo
b
al
ag
r
icu
ltu
r
al
d
em
an
d
g
r
o
ws,
tack
lin
g
th
e
d
if
f
icu
l
ties
o
f
d
ata
o
v
er
lo
ad
an
d
r
ea
l
-
tim
e
p
r
o
ce
s
s
in
g
is
cr
itical
to
en
s
u
r
e
s
u
s
tain
ab
le
an
d
ef
f
icien
t
m
et
h
o
d
s
.
T
h
is
p
ap
er
in
tr
o
d
u
ce
s
th
e
DE
C
PA,
a
r
ev
o
lu
tio
n
a
r
y
m
eth
o
d
t
o
r
eso
u
r
ce
m
an
a
g
e
m
en
t
an
d
d
ec
is
io
n
-
m
a
k
in
g
th
at
m
ak
es
u
s
e
o
f
d
ec
e
n
tr
ali
ze
d
co
m
p
u
tin
g
an
d
p
o
wer
f
u
l
m
a
ch
in
e
lear
n
in
g
m
o
d
els.
DE
C
PA,
p
ar
ticu
lar
ly
wh
en
p
ai
r
ed
with
DNN,
h
as
s
h
o
wn
h
ig
h
er
p
er
f
o
r
m
an
ce
in
en
er
g
y
u
s
ag
e,
r
esp
o
n
s
e
tim
e,
ac
cu
r
ac
y
,
a
n
d
laten
cy
,
m
a
k
in
g
it
a
p
r
o
m
is
in
g
alter
n
ativ
e
f
o
r
cu
r
r
en
t
ag
r
ic
u
ltu
r
al
o
p
er
atio
n
s
.
W
h
ile
s
o
m
e
m
ay
claim
t
h
at
ce
n
tr
alize
d
s
y
s
tem
s
o
r
s
im
p
ler
m
o
d
els
ar
e
s
u
f
f
icien
t,
DE
C
PA
’
s
s
ca
lab
ilit
y
an
d
ef
f
icien
cy
,
p
ar
ticu
lar
l
y
in
h
an
d
lin
g
m
ass
iv
e
d
atasets
an
d
ass
u
r
in
g
r
ea
l
-
tim
e
r
ep
lies
,
m
ak
e
it
th
e
o
b
v
i
o
u
s
ch
o
ice
f
o
r
ad
d
r
ess
in
g
PA
’
s
d
if
f
icu
lties
.
Un
lik
e
p
r
ev
io
u
s
s
y
s
tem
s
,
DE
C
P
A
s
p
r
ea
d
s
co
m
p
u
tatio
n
al
lo
ad
,
r
esu
ltin
g
in
b
etter
r
eso
u
r
ce
u
s
e
an
d
s
p
ee
d
ier
d
ec
is
io
n
-
m
a
k
in
g
.
Fu
tu
r
e
r
esear
ch
s
h
o
u
ld
f
o
cu
s
o
n
im
p
r
o
v
in
g
D
E
C
PA
f
o
r
s
m
aller
-
s
ca
le
ap
p
licatio
n
s
an
d
in
v
esti
g
atin
g
its
in
ter
ac
tio
n
with
I
o
T
an
d
clo
u
d
-
ed
g
e
tech
n
o
lo
g
ies.
T
h
e
p
o
te
n
tial
f
o
r
in
cr
ea
s
ed
a
d
o
p
tio
n
an
d
im
p
ac
t
is
e
n
o
r
m
o
u
s
,
an
d
im
p
r
o
v
in
g
th
ese
tech
n
o
lo
g
ies will p
av
e
t
h
e
p
ath
f
o
r
m
o
r
e
s
u
s
tain
ab
le,
e
f
f
icien
t,
an
d
in
tellig
en
t a
g
r
ic
u
ltu
r
al
m
eth
o
d
s
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
Au
th
o
r
s
s
tate
n
o
f
u
n
d
in
g
in
v
o
lv
ed
.
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
T
h
is
jo
u
r
n
al
u
s
es
th
e
C
o
n
tr
ib
u
to
r
R
o
les
T
ax
o
n
o
m
y
(
C
R
ed
iT)
to
r
ec
o
g
n
ize
in
d
iv
id
u
al
au
th
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
th
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
llab
o
r
atio
n
.
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
Kir
an
Mu
n
is
wam
y
Pan
d
u
r
an
g
a
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
R
o
o
p
ash
r
ee
Hejjaji
R
an
g
an
ath
ash
ar
m
a
✓
✓
✓
✓
✓
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
Au
th
o
r
s
s
tate
n
o
co
n
f
lict o
f
in
t
er
est.
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
A
mu
lti
-
tier
fr
a
mewo
r
k
o
f d
ec
en
tr
a
liz
ed
co
mp
u
tin
g
e
n
viro
n
men
t fo
r
…
(
K
ir
a
n
Mu
n
is
w
a
m
y
P
a
n
d
u
r
a
n
g
a
)
1079
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
ata
th
at
s
u
p
p
o
r
t
th
e
f
i
n
d
in
g
s
o
f
th
is
s
tu
d
y
ar
e
av
aila
b
le
o
n
r
eq
u
est
f
r
o
m
th
e
co
r
r
esp
o
n
d
in
g
au
th
o
r
.
RE
F
E
R
E
NC
E
S
[
1
]
M
.
S
a
n
Eme
t
e
r
i
o
d
e
l
a
P
a
r
t
e
,
J
.
F
.
M
a
r
t
í
n
e
z
-
O
r
t
e
g
a
,
V
.
H
e
r
n
á
n
d
e
z
D
í
a
z
,
a
n
d
N
.
L
.
M
a
r
t
í
n
e
z
,
“
B
i
g
d
a
t
a
a
n
d
p
r
e
c
i
si
o
n
a
g
r
i
c
u
l
t
u
r
e
:
a
n
o
v
e
l
sp
a
t
i
o
-
t
e
m
p
o
r
a
l
s
e
ma
n
t
i
c
I
o
T
d
a
t
a
m
a
n
a
g
e
m
e
n
t
f
r
a
mew
o
r
k
f
o
r
i
m
p
r
o
v
e
d
i
n
t
e
r
o
p
e
r
a
b
i
l
i
t
y
,
”
J
o
u
rn
a
l
o
f
Bi
g
D
a
t
a
,
v
o
l
.
1
0
,
n
o
.
1
,
A
p
r
.
2
0
2
3
,
d
o
i
:
1
0
.
1
1
8
6
/
s
4
0
5
3
7
-
0
2
3
-
0
0
7
2
9
-
0.
[
2
]
Q
.
H
e
,
H
.
Z
h
a
o
,
Y
.
F
e
n
g
,
Z
.
W
a
n
g
,
Z.
N
i
n
g
,
a
n
d
T
.
L
u
o
,
“
E
d
g
e
c
o
m
p
u
t
i
n
g
-
o
r
i
e
n
t
e
d
smar
t
a
g
r
i
c
u
l
t
u
r
a
l
s
u
p
p
l
y
c
h
a
i
n
mec
h
a
n
i
sm
w
i
t
h
a
u
c
t
i
o
n
a
n
d
f
u
z
z
y
n
e
u
r
a
l
n
e
t
w
o
r
k
s,”
J
o
u
rn
a
l
o
f
C
l
o
u
d
C
o
m
p
u
t
i
n
g
,
v
o
l
.
1
3
,
n
o
.
1
,
p
.
6
6
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
8
6
/
s1
3
6
7
7
-
024
-
0
0
6
2
6
-
8.
[
3
]
G
.
S
i
n
g
h
a
n
d
S
.
S
h
a
r
m
a
,
“
A
c
o
mp
r
e
h
e
n
s
i
v
e
r
e
v
i
e
w
o
n
t
h
e
i
n
t
e
r
n
e
t
o
f
t
h
i
n
g
s
i
n
p
r
e
c
i
si
o
n
a
g
r
i
c
u
l
t
u
r
e
,
”
M
u
l
t
i
m
e
d
i
a
T
o
o
l
s
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
8
4
,
n
o
.
1
7
,
p
p
.
1
8
1
2
3
–
1
8
1
9
8
,
J
u
l
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
0
4
2
-
024
-
1
9
6
5
6
-
0.
[
4
]
W
.
A
.
B
a
g
w
a
n
,
“
R
e
v
o
l
u
t
i
o
n
i
z
i
n
g
a
g
r
i
c
u
l
t
u
r
e
:
g
e
o
sp
a
t
i
a
l
t
e
c
h
n
o
l
o
g
i
e
s
a
n
d
p
r
e
c
i
si
o
n
f
a
r
mi
n
g
i
n
I
n
d
i
a
,
”
i
n
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
S
m
a
rt
Ag
r
i
c
u
l
t
u
re
,
S
p
r
i
n
g
e
r
N
a
t
u
r
e
S
i
n
g
a
p
o
r
e
,
2
0
2
4
,
p
p
.
4
3
–
5
9
.
[
5
]
S
.
M
a
k
a
m
,
B
.
K
.
K
o
m
a
t
i
n
e
n
i
,
S
.
S
.
M
e
e
n
a
,
a
n
d
U
.
M
e
e
n
a
,
“
U
n
m
a
n
n
e
d
a
e
r
i
a
l
v
e
h
i
c
l
e
s
(
U
A
V
s
)
:
a
n
a
d
o
p
t
a
b
l
e
t
e
c
h
n
o
l
o
g
y
f
o
r
p
r
e
c
i
s
e
a
n
d
s
m
a
r
t
f
a
r
m
i
n
g
,
”
D
i
s
c
o
v
e
r
I
n
t
e
r
n
e
t
o
f
T
h
i
n
g
s
,
v
o
l
.
4
,
n
o
.
1
,
p
.
1
2
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
0
7
/
s
4
3
9
2
6
-
024
-
00066
-
5.
[
6
]
N
.
C
h
e
r
g
u
i
a
n
d
M
.
T
.
K
e
c
h
a
d
i
,
“
D
a
t
a
a
n
a
l
y
t
i
c
s
f
o
r
c
r
o
p
ma
n
a
g
e
m
e
n
t
:
a
b
i
g
d
a
t
a
v
i
e
w
,
”
J
o
u
rn
a
l
o
f
Bi
g
D
a
t
a
,
v
o
l
.
9
,
n
o
.
1
,
p
.
1
2
3
,
D
e
c
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
8
6
/
s
4
0
5
3
7
-
0
2
2
-
0
0
6
6
8
-
2.
[
7
]
A
.
B
o
t
t
a
,
P
.
C
a
v
a
l
l
o
n
e
,
L
.
B
a
g
l
i
e
r
i
,
G
.
C
o
l
u
c
c
i
,
L.
T
a
g
l
i
a
v
i
n
i
,
a
n
d
G
.
Q
u
a
g
l
i
a
,
“
A
r
e
v
i
e
w
o
f
r
o
b
o
t
s,
p
e
r
c
e
p
t
i
o
n
,
a
n
d
t
a
s
k
s
i
n
p
r
e
c
i
si
o
n
a
g
r
i
c
u
l
t
u
r
e
,
”
Ap
p
l
i
e
d
Me
c
h
a
n
i
c
s
,
v
o
l
.
3
,
n
o
.
3
,
p
p
.
8
3
0
–
8
5
4
,
Ju
l
.
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
l
m
e
c
h
3
0
3
0
0
4
9
.
[
8
]
L.
H
e
,
“
V
a
r
i
a
b
l
e
r
a
t
e
t
e
c
h
n
o
l
o
g
i
e
s
f
o
r
p
r
e
c
i
s
i
o
n
a
g
r
i
c
u
l
t
u
r
e
,
”
i
n
E
n
c
y
c
l
o
p
e
d
i
a
o
f
S
m
a
r
t
A
g
r
i
c
u
l
t
u
r
e
T
e
c
h
n
o
l
o
g
i
e
s
,
S
p
r
i
n
g
e
r
I
n
t
e
r
n
a
t
i
o
n
a
l
P
u
b
l
i
s
h
i
n
g
,
2
0
2
3
,
p
p
.
1
–
9.
[
9
]
S
.
N
a
k
h
o
d
c
h
i
,
A
.
D
e
h
g
h
a
n
t
a
n
h
a
,
a
n
d
H
.
K
a
r
i
m
i
p
o
u
r
,
“
P
r
i
v
a
c
y
a
n
d
s
e
c
u
r
i
t
y
i
n
smar
t
a
n
d
p
r
e
c
i
si
o
n
f
a
r
m
i
n
g
:
a
b
i
b
l
i
o
me
t
r
i
c
a
n
a
l
y
si
s
,
”
i
n
H
a
n
d
b
o
o
k
o
f
B
i
g
D
a
t
a
P
ri
v
a
c
y
,
S
p
r
i
n
g
e
r
I
n
t
e
r
n
a
t
i
o
n
a
l
P
u
b
l
i
sh
i
n
g
,
2
0
2
0
,
p
p
.
3
0
5
–
3
1
8
.
[
1
0
]
S
.
Tr
o
i
a
n
o
,
M
.
C
a
r
z
e
d
d
a
,
a
n
d
F
.
M
a
r
a
n
g
o
n
,
“
B
e
t
t
e
r
r
i
c
h
e
r
t
h
a
n
e
n
v
i
r
o
n
m
e
n
t
a
l
l
y
f
r
i
e
n
d
l
y
?
D
e
scri
b
i
n
g
p
r
e
f
e
r
e
n
c
e
s
t
o
w
a
r
d
a
n
d
f
a
c
t
o
r
s
a
f
f
e
c
t
i
n
g
p
r
e
c
i
si
o
n
a
g
r
i
c
u
l
t
u
r
e
a
d
o
p
t
i
o
n
i
n
I
t
a
l
y
,
”
A
g
r
i
c
u
l
t
u
r
a
l
a
n
d
Fo
o
d
E
c
o
n
o
m
i
c
s
,
v
o
l
.
1
1
,
n
o
.
1
,
p
.
1
6
,
M
a
y
2
0
2
3
,
d
o
i
:
1
0
.
1
1
8
6
/
s
4
0
1
0
0
-
023
-
0
0
2
4
7
-
w.
[
1
1
]
K
.
M
.
P
a
n
d
u
r
a
n
g
a
a
n
d
R
.
H
.
R
a
n
g
a
n
a
t
h
a
s
h
a
r
ma
,
“
S
u
st
a
i
n
a
b
i
l
i
t
y
i
n
si
g
h
t
s
o
n
l
e
a
r
n
i
n
g
-
b
a
s
e
d
a
p
p
r
o
a
c
h
e
s
i
n
p
r
e
c
i
s
i
o
n
a
g
r
i
c
u
l
t
u
r
e
i
n
i
n
t
e
r
n
e
t
-
of
-
t
h
i
n
g
s
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
t
r
i
c
a
l
a
n
d
C
o
m
p
u
t
e
r
E
n
g
i
n
e
e
ri
n
g
(
I
J
EC
E)
,
v
o
l
.
1
4
,
n
o
.
3
,
p
p
.
3
4
9
5
–
3
5
1
1
,
J
u
n
.
20
2
4
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
c
e
.
v
1
4
i
3
.
p
p
3
4
9
5
-
3
5
1
1
.
[
1
2
]
J.
W
a
n
g
,
Y
.
W
a
n
g
,
G
.
Li
,
a
n
d
Z
.
Q
i
,
“
I
n
t
e
g
r
a
t
i
o
n
o
f
r
e
m
o
t
e
se
n
si
n
g
a
n
d
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
f
o
r
p
r
e
c
i
si
o
n
a
g
r
i
c
u
l
t
u
r
e
:
a
c
o
m
p
r
e
h
e
n
si
v
e
p
e
r
sp
e
c
t
i
v
e
o
n
a
p
p
l
i
c
a
t
i
o
n
s,
”
A
g
r
o
n
o
m
y
,
v
o
l
.
1
4
,
n
o
.
9
,
p
.
1
9
7
5
,
S
e
p
.
2
0
2
4
,
d
o
i
:
1
0
.
3
3
9
0
/
a
g
r
o
n
o
my
1
4
0
9
1
9
7
5
.
[
1
3
]
I
.
Zu
a
l
k
e
r
n
a
n
,
D
.
A
.
A
b
u
h
a
n
i
,
M
.
H
.
H
u
ssa
i
n
,
J.
K
h
a
n
,
a
n
d
M
.
El
M
o
h
a
n
d
e
s,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
f
o
r
p
r
e
c
i
si
o
n
a
g
r
i
c
u
l
t
u
r
e
u
s
i
n
g
i
ma
g
e
r
y
f
r
o
m
u
n
ma
n
n
e
d
a
e
r
i
a
l
v
e
h
i
c
l
e
s
(
U
A
V
s)
:
A
S
u
r
v
e
y
,
”
D
ro
n
e
s
,
v
o
l
.
7
,
n
o
.
6
,
p
.
3
8
2
,
Ju
n
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
d
r
o
n
e
s
7
0
6
0
3
8
2
.
[
1
4
]
H
.
W
a
h
e
e
d
,
N
.
Za
f
a
r
,
W
.
A
k
r
a
m,
A
.
M
a
n
z
o
o
r
,
A
.
G
a
n
i
,
a
n
d
S
.
U
.
I
sl
a
m,
“
D
e
e
p
l
e
a
r
n
i
n
g
b
a
se
d
d
i
se
a
se,
p
e
s
t
p
a
t
t
e
r
n
a
n
d
n
u
t
r
i
t
i
o
n
a
l
d
e
f
i
c
i
e
n
c
y
d
e
t
e
c
t
i
o
n
s
y
s
t
e
m
f
o
r
‘
Z
i
n
g
i
b
e
r
a
c
e
a
e
’
c
r
o
p
,
”
A
g
ri
c
u
l
t
u
r
e
,
v
o
l
.
1
2
,
n
o
.
6
,
p
.
7
4
2
,
M
a
y
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
a
g
r
i
c
u
l
t
u
r
e
1
2
0
6
0
7
4
2
.
[
1
5
]
A
.
G
a
f
u
r
o
v
,
S
.
M
u
k
h
a
r
a
m
o
v
a
,
A
.
S
a
v
e
l
i
e
v
,
a
n
d
O
.
Y
e
r
m
o
l
a
e
v
,
“
A
d
v
a
n
c
i
n
g
a
g
r
i
c
u
l
t
u
r
a
l
c
r
o
p
r
e
c
o
g
n
i
t
i
o
n
:
t
h
e
a
p
p
l
i
c
a
t
i
o
n
o
f
LSTM
n
e
t
w
o
r
k
s
a
n
d
s
p
a
t
i
a
l
g
e
n
e
r
a
l
i
z
a
t
i
o
n
i
n
s
a
t
e
l
l
i
t
e
d
a
t
a
a
n
a
l
y
si
s
,
”
Ag
r
i
c
u
l
t
u
r
e
,
v
o
l
.
1
3
,
n
o
.
9
,
p
.
1
6
7
2
,
A
u
g
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
a
g
r
i
c
u
l
t
u
r
e
1
3
0
9
1
6
7
2
.
[
1
6
]
U
.
B
h
i
ma
v
a
r
a
p
u
,
G
.
B
a
t
t
i
n
e
n
i
,
a
n
d
N
.
C
h
i
n
t
a
l
a
p
u
d
i
,
“
I
mp
r
o
v
e
d
o
p
t
i
m
i
z
a
t
i
o
n
a
l
g
o
r
i
t
h
m
i
n
LSTM
t
o
p
r
e
d
i
c
t
c
r
o
p
y
i
e
l
d
,
”
C
o
m
p
u
t
e
rs
,
v
o
l
.
1
2
,
n
o
.
1
,
p
.
1
0
,
J
a
n
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
c
o
m
p
u
t
e
r
s
1
2
0
1
0
0
1
0
.
[
1
7
]
Y
.
S
h
e
n
e
t
a
l
.
,
“
I
mp
r
o
v
i
n
g
w
h
e
a
t
y
i
e
l
d
p
r
e
d
i
c
t
i
o
n
a
c
c
u
r
a
c
y
u
si
n
g
LS
TM
-
R
F
f
r
a
mew
o
r
k
b
a
se
d
o
n
U
A
V
t
h
e
r
mal
i
n
f
r
a
r
e
d
a
n
d
mu
l
t
i
s
p
e
c
t
r
a
l
i
ma
g
e
r
y
,
”
A
g
ri
c
u
l
t
u
r
e
,
v
o
l
.
1
2
,
n
o
.
6
,
p
.
8
9
2
,
J
u
n
.
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
a
g
r
i
c
u
l
t
u
r
e
1
2
0
6
0
8
9
2
.
[
1
8
]
E.
M
u
j
k
i
c
,
M
.
P
.
P
h
i
l
i
p
se
n
,
T.
B
.
M
o
e
sl
u
n
d
,
M
.
P
.
C
h
r
i
s
t
i
a
n
s
e
n
,
a
n
d
O
.
R
a
v
n
,
“
A
n
o
ma
l
y
d
e
t
e
c
t
i
o
n
f
o
r
a
g
r
i
c
u
l
t
u
r
a
l
v
e
h
i
c
l
e
s
u
si
n
g
a
u
t
o
e
n
c
o
d
e
r
s
,
”
S
e
n
s
o
rs
,
v
o
l
.
2
2
,
n
o
.
1
0
,
p
.
3
6
0
8
,
M
a
y
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
s
2
2
1
0
3
6
0
8
.
[
1
9
]
M
.
I
a
t
r
o
u
,
C
.
K
a
r
y
d
a
s
,
X
.
Ts
e
n
i
,
a
n
d
S
.
M
o
u
r
e
l
a
t
o
s,
“
R
e
p
r
e
s
e
n
t
a
t
i
o
n
l
e
a
r
n
i
n
g
w
i
t
h
a
v
a
r
i
a
t
i
o
n
a
l
a
u
t
o
e
n
c
o
d
e
r
f
o
r
p
r
e
d
i
c
t
i
n
g
n
i
t
r
o
g
e
n
r
e
q
u
i
r
e
me
n
t
i
n
r
i
c
e
,
”
R
e
m
o
t
e
S
e
n
s
i
n
g
,
v
o
l
.
1
4
,
n
o
.
2
3
,
p
.
5
9
7
8
,
N
o
v
.
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
r
s
1
4
2
3
5
9
7
8
.
[
2
0
]
Y
.
B
a
i
,
X
.
S
u
n
,
Y
.
Ji
,
W
.
F
u
,
a
n
d
X
.
D
u
a
n
,
“
Li
g
h
t
w
e
i
g
h
t
3
D
d
e
n
se
a
u
t
o
e
n
c
o
d
e
r
n
e
t
w
o
r
k
f
o
r
h
y
p
e
r
s
p
e
c
t
r
a
l
r
e
m
o
t
e
s
e
n
s
i
n
g
i
m
a
g
e
c
l
a
ss
i
f
i
c
a
t
i
o
n
,
”
S
e
n
s
o
rs
,
v
o
l
.
2
3
,
n
o
.
2
0
,
p
.
8
6
3
5
,
O
c
t
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
s
2
3
2
0
8
6
3
5
.
[
2
1
]
M
.
A
l
-
N
a
e
e
m,
M
.
M
.
H
.
R
a
h
ma
n
,
A
.
B
a
n
e
r
j
e
e
,
a
n
d
A
.
S
u
f
i
a
n
,
“
S
u
p
p
o
r
t
v
e
c
t
o
r
m
a
c
h
i
n
e
-
b
a
se
d
e
n
e
r
g
y
e
f
f
i
c
i
e
n
t
m
a
n
a
g
e
me
n
t
o
f
U
A
V
l
o
c
a
t
i
o
n
s
f
o
r
a
e
r
i
a
l
mo
n
i
t
o
r
i
n
g
o
f
c
r
o
p
s
o
v
e
r
l
a
r
g
e
a
g
r
i
c
u
l
t
u
r
e
l
a
n
d
s,”
S
u
s
t
a
i
n
a
b
i
l
i
t
y
,
v
o
l
.
1
5
,
n
o
.
8
,
p
.
6
4
2
1
,
A
p
r
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
s
u
1
5
0
8
6
4
2
1
.
[
2
2
]
S
.
I
sl
a
m
e
t
a
l
.
,
“
I
mag
e
p
r
o
c
e
ss
i
n
g
a
n
d
s
u
p
p
o
r
t
v
e
c
t
o
r
m
a
c
h
i
n
e
(
S
V
M
)
f
o
r
c
l
a
ss
i
f
y
i
n
g
e
n
v
i
r
o
n
me
n
t
a
l
s
t
r
e
ss
sy
m
p
t
o
ms
o
f
p
e
p
p
e
r
see
d
l
i
n
g
s
g
r
o
w
n
i
n
a
p
l
a
n
t
f
a
c
t
o
r
y
,
”
A
g
ro
n
o
m
y
,
v
o
l
.
1
4
,
n
o
.
9
,
p
.
2
0
4
3
,
S
e
p
.
2
0
2
4
,
d
o
i
:
1
0
.
3
3
9
0
/
a
g
r
o
n
o
my
1
4
0
9
2
0
4
3
.
[
2
3
]
H.
-
K
.
L
y
u
,
C
.
-
H
.
P
a
r
k
,
D
.
-
H
.
H
a
n
,
S
.
W
.
K
w
a
k
,
a
n
d
B
.
C
h
o
i
,
“
O
r
c
h
a
r
d
f
r
e
e
s
p
a
c
e
a
n
d
c
e
n
t
e
r
l
i
n
e
e
st
i
ma
t
i
o
n
u
s
i
n
g
N
a
i
v
e
B
a
y
e
s
i
a
n
c
l
a
ssi
f
i
e
r
f
o
r
u
n
ma
n
n
e
d
g
r
o
u
n
d
se
l
f
-
d
r
i
v
i
n
g
v
e
h
i
c
l
e
,
”
S
y
m
m
e
t
ry
,
v
o
l
.
1
0
,
n
o
.
9
,
p
.
3
5
5
,
A
u
g
.
2
0
1
8
,
d
o
i
:
1
0
.
3
3
9
0
/
s
y
m1
0
0
9
0
3
5
5
.
[
2
4
]
X.
-
B
.
J
i
n
,
X
.
-
H
.
Y
u
,
X
.
-
Y
.
W
a
n
g
,
Y
.
-
T
.
B
a
i
,
T
.
-
L
.
S
u
,
a
n
d
J
.
-
L
.
K
o
n
g
,
“
D
e
e
p
l
e
a
r
n
i
n
g
p
r
e
d
i
c
t
o
r
f
o
r
s
u
s
t
a
i
n
a
b
l
e
p
r
e
c
i
s
i
o
n
a
g
r
i
c
u
l
t
u
r
e
b
a
s
e
d
o
n
i
n
t
e
r
n
e
t
o
f
t
h
i
n
g
s
s
y
s
t
e
m
,
”
S
u
s
t
a
i
n
a
b
i
l
i
t
y
,
v
o
l
.
1
2
,
n
o
.
4
,
p
.
1
4
3
3
,
F
e
b
.
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
s
u
1
2
0
4
1
4
3
3
.
[
2
5
]
J.
R
.
R
e
g
a
z
z
o
e
t
a
l
.
,
“
P
e
r
f
o
r
m
a
n
c
e
o
f
n
e
u
r
a
l
n
e
t
w
o
r
k
s
i
n
t
h
e
p
r
e
d
i
c
t
i
o
n
o
f
n
i
t
r
o
g
e
n
n
u
t
r
i
t
i
o
n
i
n
s
t
r
a
w
b
e
r
r
y
p
l
a
n
t
s,
”
Ag
ri
En
g
i
n
e
e
r
i
n
g
,
v
o
l
.
6
,
n
o
.
2
,
p
p
.
1
7
60
–
1
7
7
0
,
J
u
n
.
2
0
2
4
,
d
o
i
:
1
0
.
3
3
9
0
/
a
g
r
i
e
n
g
i
n
e
e
r
i
n
g
6
0
2
0
1
0
2
.
[
2
6
]
D
.
C
a
m
a
-
P
i
n
t
o
e
t
a
l
.
,
“
A
d
e
e
p
l
e
a
r
n
i
n
g
m
o
d
e
l
o
f
r
a
d
i
o
w
a
v
e
p
r
o
p
a
g
a
t
i
o
n
f
o
r
p
r
e
c
i
si
o
n
a
g
r
i
c
u
l
t
u
r
e
a
n
d
sen
s
o
r
sy
s
t
e
m
i
n
g
r
e
e
n
h
o
u
ses
,
”
Ag
ro
n
o
m
y
,
v
o
l
.
1
3
,
n
o
.
1
,
p
.
2
4
4
,
J
a
n
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
a
g
r
o
n
o
m
y
1
3
0
1
0
2
4
4
.
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.
3
9
,
No
.
2
,
Au
g
u
s
t
20
25
:
1
0
7
2
-
1
080
1080
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
K
ira
n
Mu
n
iswa
m
y
Pa
n
d
u
r
a
n
g
a
h
a
s
c
o
m
p
lete
d
B
.
E
.
(
I
n
fo
rm
a
ti
o
n
S
c
ien
c
e
a
n
d
En
g
i
n
e
e
rin
g
)
in
th
e
y
e
a
r
2
0
0
5
fr
o
m
S
ri
S
id
d
h
a
rt
h
a
In
stit
u
te
o
f
Tec
h
n
o
lo
g
y
T
u
m
k
u
r,
Affili
a
ted
to
Visv
e
sv
a
ra
y
a
Tec
h
n
o
lo
g
ica
l
Un
iv
e
rsit
y
,
Be
lag
a
v
i,
Ka
rn
a
t
a
k
a
,
In
d
ia
a
n
d
M
.
Tec
h
.
(
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
in
e
e
rin
g
)
in
th
e
y
e
a
r
2
0
0
7
fr
o
m
AMC
En
g
i
n
e
e
rin
g
Co
l
leg
e
Ba
n
g
a
lo
re
,
A
ffil
iate
d
t
o
Visv
e
sv
a
ra
y
a
Tec
h
n
o
lo
g
ica
l
Un
iv
e
rsit
y
,
Be
lag
a
v
i,
Ka
rn
a
tak
a
,
In
d
ia.
He
h
a
s
a
ro
u
n
d
1
4
y
e
a
rs
o
f
tea
c
h
in
g
e
x
p
e
rien
c
e
.
He
is p
re
se
n
tl
y
wo
rk
in
g
a
s
As
sista
n
t
P
r
o
fe
ss
o
r
in
th
e
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
i
n
e
e
rin
g
a
t
G
o
v
e
rn
m
e
n
t
En
g
in
e
e
rin
g
Co
ll
e
g
e
Ha
ss
a
n
–
5
7
3
2
0
1
,
Ka
rn
a
tak
a
,
I
n
d
ia.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
m
tec
h
.
k
iran
@g
m
a
il
.
c
o
m
.
Ro
o
p
a
shre
e
H
e
jja
ji
Ra
n
g
a
n
a
t
h
a
sha
r
m
a
h
a
s
c
o
m
p
lete
d
B
.
E
.
(
El
e
c
tro
n
ics
a
n
d
Co
m
m
u
n
ica
ti
o
n
En
g
i
n
e
e
rin
g
)
a
n
d
M
.
Tec
h
.
(
C
o
m
p
u
ter
S
c
ien
c
e
a
n
d
E
n
g
i
n
e
e
rin
g
)
fro
m
VTU,
Be
lag
a
v
i,
Ka
rn
a
tak
a
,
In
d
ia
a
n
d
P
h
.
D
.
fro
m
CHRI
S
T
(De
e
m
e
d
t
o
b
e
Un
i
v
e
rsity
)
Be
n
g
a
l
u
ru
,
Ka
rn
a
tak
a
,
In
d
ia.
S
h
e
h
a
s
a
ro
u
n
d
1
3
y
e
a
rs
o
f
in
d
u
s
tri
a
l
e
x
p
e
rien
c
e
a
n
d
6
y
e
a
rs
o
f
tea
c
h
in
g
e
x
p
e
rien
c
e
.
S
h
e
is
c
u
rre
n
tl
y
w
o
r
k
in
g
a
s
P
ro
fe
ss
o
r
a
n
d
He
a
d
in
t
h
e
De
p
a
rtme
n
t
o
f
Artifi
c
ial
In
telli
g
e
n
c
e
a
n
d
Da
ta
S
c
ien
c
e
a
t
G
S
S
S
In
stit
u
te
o
f
En
g
in
e
e
rin
g
a
n
d
Tec
h
n
o
l
o
g
y
fo
r
Wo
m
e
n
,
M
y
su
r
u
-
5
7
0
0
1
6
,
Ka
rn
a
tak
a
,
I
n
d
ia an
d
su
p
e
rv
isi
n
g
6
P
h
.
D
.
re
se
a
rc
h
sc
h
o
lars
i
n
Visv
e
sv
a
ra
y
a
Tec
h
n
o
l
o
g
ica
l
U
n
iv
e
rsit
y
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
r
o
o
p
a
sh
r
e
e
h
r@
g
ss
s.e
d
u
.
i
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.