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.
4
1
,
No
.
3
,
Ma
r
ch
20
2
6
,
p
p
.
1
0
7
0
~
1
0
8
1
I
SS
N:
2
502
-
4
7
52
,
DOI
: 1
0
.
1
1
5
9
1
/ijee
cs
.v
4
1
.
i
3
.
pp
1
0
7
0
-
1
0
8
1
1070
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs
.
ia
esco
r
e.
co
m
A
micro
serv
ice
-
o
riented
ma
chine
l
ea
rning
f
ra
mewo
rk f
o
r cold
cha
in ma
na
g
ement in
perisha
ble
fi
sh lo
g
istics
M
a
un
J
a
m
a
lud
in
1
,
Arie
f
G
in
a
nja
r
2
,
L
eni H
er
dia
ni
3
,
T
o
t
o
Ra
m
a
dh
a
n
4
M
uh
a
m
m
a
d Alif
Na
ufa
l
3
,
R.
I
s
m
et
Ro
him
a
t
3
1
D
e
p
a
r
t
me
n
t
o
f
B
u
si
n
e
ss
A
d
m
i
n
i
s
t
r
a
t
i
o
n
,
U
n
i
v
e
r
si
t
a
s
P
a
s
u
n
d
a
n
,
B
a
n
d
u
n
g
,
I
n
d
o
n
e
s
i
a
2
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
mat
i
c
,
F
a
c
u
l
t
y
o
f
En
g
i
n
e
e
r
i
n
g
,
U
n
i
v
e
r
s
i
t
a
s
L
a
n
g
l
a
n
g
b
u
a
n
a
,
B
a
n
d
u
n
g
,
I
n
d
o
n
e
si
a
3
D
e
p
a
r
t
me
n
t
o
f
I
n
d
u
s
t
r
i
a
l
En
g
i
n
e
e
r
i
n
g
,
F
a
c
u
l
t
y
o
f
E
n
g
i
n
e
e
r
i
n
g
,
U
n
i
v
e
r
si
t
a
s
La
n
g
l
a
n
g
b
u
a
n
a
,
B
a
n
d
u
n
g
,
I
n
d
o
n
e
si
a
4
D
e
p
a
r
t
me
n
t
o
f
I
n
d
u
s
t
r
i
a
l
En
g
i
n
e
e
r
i
n
g
,
F
a
c
u
l
t
y
o
f
E
n
g
i
n
e
e
r
i
n
g
,
U
n
i
v
e
r
si
t
a
s
P
a
su
n
d
a
n
,
B
a
n
d
u
n
g
,
I
n
d
o
n
e
si
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Oct
1
6
,
2
0
2
5
R
ev
is
ed
J
an
1
5
,
2
0
2
6
Acc
ep
ted
Ma
r
4
,
2
0
2
6
Th
is
stu
d
y
p
ro
p
o
se
s
a
m
icro
se
rv
i
c
e
-
o
rien
ted
m
a
c
h
in
e
lea
rn
i
n
g
fra
m
e
wo
rk
to
e
n
h
a
n
c
e
i
n
telli
g
e
n
c
e
a
n
d
sc
a
lab
il
it
y
in
p
e
rish
a
b
le
fish
c
o
l
d
c
h
a
in
lo
g
isti
c
s.
Un
li
k
e
c
o
n
v
e
n
ti
o
n
a
l
m
o
n
it
o
ri
n
g
-
c
e
n
tri
c
sy
ste
m
s,
t
h
e
fra
m
e
wo
rk
in
teg
ra
tes
e
d
g
e
–
c
lo
u
d
c
o
m
p
u
ti
n
g
wit
h
m
u
lt
i
m
o
d
a
l
m
a
c
h
in
e
lea
rn
i
n
g
m
o
d
e
ls,
in
c
lu
d
in
g
ra
n
d
o
m
fo
re
st
fo
r
a
n
o
m
a
ly
d
e
tec
ti
o
n
,
lo
n
g
sh
o
rt
-
term
m
e
m
o
ry
(L
S
TM
)
fo
r
sp
o
il
a
g
e
risk
p
re
d
ict
io
n
,
a
n
d
c
o
n
v
o
l
u
ti
o
n
a
l
n
e
u
ra
l
n
e
two
r
k
(CNN
)
fo
r
v
is
u
a
l
fish
q
u
a
li
ty
c
las
sifica
ti
o
n
.
Th
e
r
e
se
a
rc
h
a
d
o
p
ts
a
d
e
si
g
n
sc
ien
c
e
a
p
p
r
o
a
c
h
c
o
m
b
in
i
n
g
li
tera
tu
re
a
n
a
l
y
sis,
fie
ld
o
b
se
rv
a
ti
o
n
s
a
t
c
o
ld
st
o
ra
g
e
f
a
c
il
it
ies
in
In
d
ra
m
a
y
u
,
In
d
o
n
e
sia
,
a
n
d
sim
u
l
a
ti
o
n
-
b
a
se
d
v
a
li
d
a
ti
o
n
.
Ex
p
e
rime
n
tal
re
su
lt
s
d
e
m
o
n
stra
te
th
e
fe
a
sib
il
it
y
o
f
d
ist
rib
u
te
d
a
n
a
ly
t
ics
,
m
o
d
u
lar
d
e
p
lo
y
m
e
n
t,
a
n
d
re
a
l
-
ti
m
e
in
fe
r
e
n
c
e
with
in
h
e
t
e
ro
g
e
n
e
o
u
s
lo
g
isti
c
s
e
n
v
ir
o
n
m
e
n
ts.
Th
e
p
ro
p
o
se
d
fra
m
e
wo
rk
p
r
o
v
i
d
e
s
a
d
e
p
lo
y
a
b
le
a
rc
h
it
e
c
tu
ra
l
re
fe
re
n
c
e
fo
r
in
telli
g
e
n
t
fis
h
e
ries
c
o
ld
c
h
a
i
n
m
a
n
a
g
e
m
e
n
t
a
n
d
s
u
p
p
o
rts
f
u
tu
re
larg
e
-
sc
a
le,
m
u
lt
i
-
sta
k
e
h
o
ld
e
r
imp
lem
e
n
tatio
n
.
K
ey
w
o
r
d
s
:
C
o
ld
ch
ain
m
an
a
g
em
en
t
Desig
n
ar
ch
itectu
r
e
Fis
h
lo
g
is
tics
Ma
ch
in
e
lear
n
in
g
Mic
r
o
s
er
v
ice
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
:
Ar
ief
Gin
an
jar
Dep
ar
tm
en
t o
f
I
n
f
o
r
m
atics,
Facu
lty
o
f
E
n
g
in
ee
r
i
n
g
,
Un
i
v
er
s
itas
L
an
g
lan
g
b
u
an
a
B
an
d
u
n
g
,
I
n
d
o
n
esia
E
m
ail:
ar
ief
.
g
in
an
jar
@
u
n
la.
ac
.
id
1.
I
NT
RO
D
UCT
I
O
N
Fis
h
d
is
tr
ib
u
tio
n
in
I
n
d
o
n
esia
f
ac
es
s
ig
n
if
ican
t
ch
allen
g
es
i
n
m
ain
tain
in
g
p
r
o
d
u
ct
f
r
esh
n
ess
d
u
e
to
tem
p
er
atu
r
e
s
en
s
itiv
ity
an
d
lo
n
g
s
u
p
p
l
y
ch
ain
r
o
u
tes
[
1
]
,
[
2
]
.
C
o
n
v
en
tio
n
al
co
ld
ch
ain
s
y
s
tem
s
ar
e
lim
ited
in
th
eir
ab
ilit
y
t
o
m
o
n
ito
r
,
p
r
ed
ic
t,
an
d
r
esp
o
n
d
t
o
r
is
k
s
i
n
r
ea
l
t
im
e
[
3
]
,
[
4
]
.
T
h
e
in
teg
r
atio
n
o
f
in
ter
n
et
o
f
th
in
g
s
(
I
o
T
)
,
e
d
g
e
c
o
m
p
u
tin
g
,
b
i
g
d
ata,
an
d
a
r
tific
ial
in
tellig
en
ce
/m
ac
h
in
e
lear
n
in
g
(
AI
/ML
)
o
f
f
er
s
n
ew
o
p
p
o
r
tu
n
ities
to
im
p
r
o
v
e
ef
f
icien
cy
,
ac
cu
r
ac
y
,
an
d
s
u
s
tain
ab
i
lity
in
f
is
h
er
ies lo
g
is
tic
s
[
5
]
,
[
6
]
.
T
h
is
s
t
u
d
y
aim
s
to
d
esig
n
a
co
m
p
r
eh
en
s
iv
e
c
o
ld
ch
ain
ar
ch
itectu
r
e
p
o
wer
ed
b
y
AI
/ML
to
s
u
p
p
o
r
t
d
e
cisi
o
n
-
m
ak
in
g
an
d
en
h
an
ce
f
o
o
d
s
ec
u
r
ity
.
T
h
e
r
esear
ch
p
r
o
ce
s
s
was
ca
r
r
ied
o
u
t
in
s
ev
er
al
s
tag
es
to
en
s
u
r
e
b
o
t
h
th
e
o
r
etica
l
r
ig
o
r
an
d
p
r
ac
tical
r
elev
an
ce
.
First,
an
e
x
t
en
s
iv
e
liter
atu
r
e
r
ev
iew
was
co
n
d
u
cted
to
e
x
am
in
e
p
r
e
v
io
u
s
s
tu
d
ies
o
n
co
ld
ch
ain
m
an
ag
em
en
t,
th
e
ap
p
licatio
n
o
f
I
o
T
a
n
d
ed
g
e
co
m
p
u
tin
g
in
s
u
p
p
ly
ch
ain
s
,
an
d
th
e
r
o
le
o
f
m
ac
h
i
n
e
lear
n
in
g
an
d
b
ig
d
ata
in
p
r
ed
ictiv
e
a
n
aly
tics
an
d
an
o
m
aly
d
etec
ti
o
n
[
7
]
–
[
9
]
.
T
h
is
r
ev
iew
p
r
o
v
id
ed
th
e
th
eo
r
etica
l
f
o
u
n
d
atio
n
a
n
d
h
elp
ed
i
d
en
ti
f
y
tech
n
o
lo
g
ical
g
ap
s
in
e
x
is
tin
g
ap
p
r
o
ac
h
es.
Seco
n
d
,
a
d
esig
n
s
tu
d
y
was
un
d
er
tak
e
n
t
o
d
e
v
elo
p
a
c
o
n
ce
p
tu
al
co
ld
ch
ai
n
ar
c
h
itectu
r
e
tailo
r
ed
to
th
e
I
n
d
o
n
esian
f
is
h
er
ies
co
n
te
x
t.
Var
io
u
s
tech
n
o
lo
g
ical
co
m
p
o
n
en
ts
wer
e
ev
alu
ated
,
in
cl
u
d
in
g
m
u
ltimo
d
al
in
p
u
t
d
e
v
ices,
lo
w
-
co
s
t
ed
g
e
co
m
p
u
tin
g
p
latf
o
r
m
s
,
clo
u
d
-
b
ased
d
ata
s
to
r
ag
e,
an
d
ad
v
an
c
ed
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
s
s
u
ch
as
r
an
d
o
m
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
A
micro
s
ervice
-
o
r
ien
ted
ma
ch
in
e
lea
r
n
in
g
fr
a
mewo
r
k
fo
r
co
ld
ch
a
in
ma
n
a
g
eme
n
t in
…
(
M
a
u
n
Ja
m
a
lu
d
in
)
1071
f
o
r
e
s
t,
lo
n
g
s
h
o
r
t
-
ter
m
m
em
o
r
y
(
L
STM
)
,
an
d
co
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
(
C
NN)
[
1
0
]
–
[
1
2
]
.
T
h
e
s
elec
tio
n
o
f
th
ese
tec
h
n
o
lo
g
ies
was
b
ased
o
n
th
eir
s
u
itab
ilit
y
f
o
r
a
d
d
r
ess
in
g
is
s
u
es
o
f
s
ca
lab
ilit
y
,
i
n
ter
o
p
er
a
b
ilit
y
,
an
d
r
ea
l
-
tim
e
m
o
n
ito
r
in
g
.
T
h
ir
d
,
a
f
ield
s
u
r
v
ey
was
co
n
d
u
cte
d
at
th
e
co
ld
s
to
r
ag
e
f
ac
ilit
ies
in
I
n
d
r
am
ay
u
,
W
est
J
av
a,
to
v
alid
ate
th
e
f
in
d
in
g
s
f
r
o
m
th
e
liter
atu
r
e
an
d
d
esig
n
s
tag
es
[
1
3
]
,
[
1
4
]
.
Ob
s
er
v
atio
n
s
r
ev
ea
led
s
ig
n
if
ican
t
o
p
er
atio
n
al
lim
itatio
n
s
s
u
ch
as
r
elian
ce
o
n
m
an
u
al
tem
p
er
at
u
r
e
r
ea
d
i
n
g
s
,
lim
ited
C
C
T
V
f
u
n
ctio
n
ality
u
n
d
er
c
o
ld
co
n
d
itio
n
s
,
an
d
d
if
f
ic
u
lties
in
m
ain
tain
in
g
elec
tr
o
n
ic
d
e
v
ices
in
lo
w
-
tem
p
er
atu
r
e
en
v
ir
o
n
m
en
ts
[
1
5
]
.
Fin
ally
,
th
e
in
s
ig
h
ts
g
ain
ed
f
r
o
m
th
e
f
ield
s
u
r
v
ey
wer
e
co
m
p
ar
e
d
with
th
e
id
ea
l c
o
n
d
itio
n
s
en
v
is
io
n
ed
i
n
th
e
p
r
o
p
o
s
ed
a
r
ch
itectu
r
e.
T
h
is
c
o
m
p
ar
is
o
n
h
ig
h
lig
h
ted
t
h
e
g
a
p
b
etwe
en
cu
r
r
en
t
p
r
ac
tices
an
d
th
e
r
eq
u
ir
em
en
ts
o
f
a
n
in
telli
g
en
t,
m
icr
o
s
er
v
ice
-
o
r
ien
ted
c
o
ld
ch
ai
n
s
y
s
tem
[
1
6
]
,
[
1
7
]
.
B
y
b
r
id
g
i
n
g
t
h
ese
g
ap
s
,
th
e
p
r
o
p
o
s
ed
f
r
am
ewo
r
k
d
em
o
n
s
tr
ates
b
o
th
its
p
r
ac
tica
l
n
ec
ess
ity
an
d
its
p
o
ten
tial
to
s
er
v
e
as
a
s
ca
lab
le
m
o
d
el
f
o
r
f
is
h
er
ies lo
g
is
tics
.
An
o
th
er
c
r
itical
g
ap
i
d
en
tifie
d
d
u
r
in
g
th
e
f
ield
s
tu
d
y
r
elat
es
to
in
s
titu
tio
n
al
f
r
a
g
m
en
tatio
n
ac
r
o
s
s
th
e
co
ld
ch
ain
cy
cle.
I
d
ea
lly
,
th
e
en
tire
co
ld
ch
ain
lo
o
p
f
r
o
m
in
p
u
t
d
ev
ices,
ed
g
e
p
r
o
ce
s
s
in
g
,
d
ata
co
llectio
n
,
m
ac
h
in
e
lear
n
i
n
g
,
to
p
r
e
d
ictio
n
o
u
tp
u
t
s
h
o
u
ld
o
p
er
ate
u
n
d
er
a
s
in
g
le
o
r
g
an
izatio
n
al
f
r
am
ewo
r
k
to
en
s
u
r
e
s
ea
m
less
in
teg
r
atio
n
an
d
co
n
s
is
ten
t
s
tan
d
ar
d
s
.
Ho
wev
e
r
,
in
p
r
ac
tice,
ea
ch
s
eg
m
en
t
is
m
a
n
ag
ed
b
y
d
if
f
e
r
en
t
co
m
p
an
ies
with
d
is
tin
ct
b
u
s
in
ess
p
r
io
r
ities
,
r
esu
ltin
g
in
s
ilo
ed
o
p
er
atio
n
s
a
n
d
lim
ited
in
t
er
o
p
er
a
b
ilit
y
.
T
h
is
m
is
alig
n
m
en
t
r
ed
u
ce
s
th
e
ef
f
ec
tiv
en
ess
o
f
m
o
n
ito
r
i
n
g
,
p
r
e
d
ictio
n
,
a
n
d
d
ec
is
io
n
-
m
a
k
in
g
ac
r
o
s
s
th
e
s
u
p
p
ly
ch
ain
.
T
o
ad
d
r
ess
th
is
,
a
c
o
n
s
o
r
tiu
m
m
o
d
el
is
r
e
q
u
ir
e
d
,
in
it
iated
an
d
f
ac
ilit
ated
b
y
th
e
f
i
s
h
er
ies
an
d
m
a
r
in
e
af
f
air
s
o
f
f
ice
at
th
e
m
u
n
icip
a
l,
d
is
tr
ict,
an
d
p
r
o
v
in
cial
lev
els.
Su
ch
g
o
v
er
n
a
n
c
e
m
ec
h
a
n
is
m
s
wo
u
ld
en
ab
le
s
tak
eh
o
ld
er
s
with
d
if
f
er
e
n
t
in
ter
ests
to
alig
n
th
eir
s
tr
ateg
ie
s
,
s
h
ar
e
d
ata,
an
d
co
m
p
lem
en
t
ea
ch
o
th
er
’
s
r
o
les
with
in
a
u
n
if
ied
c
o
ld
c
h
ain
ec
o
s
y
s
tem
[
1
8
]
–
[
2
0
]
.
T
h
e
p
r
o
p
o
s
ed
m
icr
o
s
er
v
ice
-
o
r
ien
ted
an
d
m
ac
h
in
e
lear
n
in
g
-
b
ased
ar
ch
itectu
r
e
co
u
l
d
s
er
v
e
as
th
e
tech
n
o
lo
g
ical
f
o
u
n
d
ati
o
n
f
o
r
th
is
co
n
s
o
r
tiu
m
,
en
s
u
r
i
n
g
in
ter
o
p
e
r
ab
ilit
y
,
s
ca
lab
ilit
y
,
an
d
r
ea
l
-
tim
e
in
tell
ig
en
ce
ac
r
o
s
s
o
r
g
an
izatio
n
al
b
o
u
n
d
a
r
ies.
E
x
is
tin
g
s
tu
d
ies
o
n
AI
-
d
r
iv
en
co
ld
ch
ain
m
o
n
ito
r
in
g
p
r
im
a
r
ily
f
o
cu
s
o
n
s
en
s
o
r
tr
ac
k
in
g
,
te
m
p
er
atu
r
e
lo
g
g
in
g
,
o
r
clo
u
d
-
b
ased
d
as
h
b
o
ar
d
s
b
u
t
lack
r
ea
l
-
tim
e
p
r
ed
ictiv
e
ca
p
ab
ilit
ies
an
d
au
to
n
o
m
o
u
s
d
ec
is
io
n
s
u
p
p
o
r
t
m
ec
h
a
n
is
m
s
[
5
]
,
[
6
]
,
[
2
1
]
.
Mo
s
t
f
r
am
ewo
r
k
s
ar
e
d
esig
n
ed
u
s
in
g
m
o
n
o
lith
ic
o
r
ce
n
tr
alize
d
ar
ch
itectu
r
es
th
at
lim
it
s
ca
lab
ilit
y
,
in
ter
o
p
e
r
ab
ilit
y
,
a
n
d
s
y
s
tem
r
eliab
ilit
y
in
d
i
s
tr
ib
u
ted
f
is
h
er
ies
lo
g
is
tics
[
7
]
,
[
8
]
.
Fu
r
th
er
m
o
r
e
,
p
r
ev
io
u
s
m
o
d
els
d
o
n
o
t
c
o
m
b
in
e
an
o
m
aly
d
etec
tio
n
,
s
p
o
il
ag
e
p
r
ed
ictio
n
,
an
d
v
is
u
al
q
u
ality
ass
ess
m
en
t
u
s
in
g
m
u
ltimo
d
al
m
ac
h
in
e
l
ea
r
n
in
g
with
in
m
icr
o
s
er
v
ice
-
b
ased
d
ep
lo
y
m
en
t
en
v
ir
o
n
m
en
ts
[
9
]
,
[
2
2
]
.
W
h
ile
s
o
m
e
s
tu
d
ies
h
av
e
ex
p
l
o
r
ed
ML
f
o
r
tem
p
er
atu
r
e
a
n
o
m
al
y
d
etec
tio
n
[
1
0
]
,
o
r
f
is
h
q
u
ality
class
if
icatio
n
u
s
i
n
g
C
NN
[
1
2
]
,
th
ese
m
o
d
els
a
r
e
r
ar
ely
in
teg
r
ated
with
I
o
T
-
ed
g
e
p
r
o
ce
s
s
in
g
o
r
co
n
tain
er
ized
d
ep
lo
y
m
en
t,
an
d
h
av
e
n
o
t
b
ee
n
s
p
ec
if
ically
ap
p
lied
to
th
e
f
is
h
er
ies
co
ld
ch
ain
co
n
tex
t
i
n
I
n
d
o
n
esia
[
1
8
]
,
[
20]
.
T
h
ese
lim
itatio
n
s
in
d
icate
a
s
ig
n
if
i
ca
n
t
r
esear
ch
g
ap
in
d
ev
elo
p
in
g
a
n
in
tellig
en
t,
d
is
tr
ib
u
ted
,
an
d
m
o
d
u
lar
co
l
d
ch
ain
f
r
a
m
ewo
r
k
th
at
e
n
ab
les
r
ea
l
-
tim
e
in
f
er
en
ce
,
p
r
e
d
i
ctiv
e
an
aly
tics
,
an
d
cr
o
s
s
-
o
r
g
an
izatio
n
al
i
n
ter
o
p
e
r
ab
ilit
y
.
T
o
ad
d
r
ess
th
ese
g
a
p
s
,
th
is
s
tu
d
y
p
r
o
p
o
s
es
a
m
icr
o
s
er
v
ice
-
o
r
ien
ted
m
ac
h
i
n
e
lear
n
in
g
f
r
am
ewo
r
k
in
teg
r
atin
g
r
a
n
d
o
m
f
o
r
est
f
o
r
an
o
m
aly
d
etec
tio
n
,
L
STM
f
o
r
s
p
o
ilag
e
r
is
k
p
r
ed
ictio
n
,
an
d
C
NN
f
o
r
f
is
h
q
u
ality
class
if
icatio
n
,
d
esig
n
ed
to
o
p
er
ate
with
in
an
ed
g
e
–
clo
u
d
a
r
ch
itectu
r
e
[
2
2
]
,
[
2
3
]
.
T
h
e
f
r
am
ewo
r
k
lev
er
a
g
es
Do
ck
er
-
b
ased
m
o
d
u
lar
d
e
p
l
o
y
m
en
t,
MQ
T
T
f
o
r
s
en
s
o
r
s
tr
ea
m
in
g
,
an
d
API
Gate
way
f
o
r
r
ea
l
-
tim
e
o
r
ch
estra
tio
n
,
e
n
ab
lin
g
s
ca
la
b
le,
lo
w
-
laten
cy
,
a
n
d
in
te
r
o
p
er
ab
le
co
ld
c
h
ain
o
p
er
atio
n
s
[
2
4
]
,
[
2
5
]
.
Un
lik
e
p
r
ev
io
u
s
f
r
am
ewo
r
k
s
,
th
e
p
r
o
p
o
s
ed
s
y
s
tem
s
u
p
p
o
r
t
s
d
is
tr
ib
u
ted
an
aly
tics
,
h
e
ter
o
g
en
eo
u
s
d
ev
ice
co
m
p
atib
ilit
y
,
an
d
r
ea
l
-
tim
e
q
u
ality
m
o
n
ito
r
in
g
ac
r
o
s
s
m
u
ltip
le
lo
g
is
tics
en
v
ir
o
n
m
en
ts
,
s
p
ec
if
ically
tailo
r
ed
to
th
e
o
p
er
atio
n
al
ch
alle
n
g
es
o
f
p
er
is
h
ab
le
f
is
h
lo
g
is
tics
in
I
n
d
o
n
esia
[
1
6
]
,
[
2
6
]
.
T
a
b
le
1
p
r
esen
ts
a
co
m
p
ar
ativ
e
an
aly
s
is
h
ig
h
lig
h
tin
g
k
ey
p
ar
am
eter
s
,
lim
itatio
n
s
,
an
d
tech
n
o
lo
g
ical
g
ap
s
in
e
x
is
tin
g
s
tu
d
ies,
wh
ich
clea
r
l
y
p
o
s
itio
n
th
e
n
o
v
el
co
n
tr
ib
u
tio
n
an
d
s
ig
n
if
ica
n
ce
o
f
th
is
p
r
o
p
o
s
ed
f
r
am
ewo
r
k
.
2.
M
E
T
H
O
D
T
h
is
s
ec
tio
n
d
escr
ib
es
th
e
m
e
th
o
d
o
lo
g
y
a
d
o
p
te
d
to
d
ev
elo
p
an
d
v
alid
ate
th
e
p
r
o
p
o
s
ed
f
r
am
ewo
r
k
.
T
h
e
r
esear
ch
p
r
o
ce
s
s
was
s
tr
u
ctu
r
ed
to
en
s
u
r
e
s
cien
tific
r
i
g
o
r
an
d
p
r
ac
tical
r
elev
an
ce
,
c
o
m
b
in
in
g
liter
atu
r
e
r
ev
iew,
co
n
ce
p
tu
al
f
r
am
ew
o
r
k
d
esig
n
,
f
ield
s
u
r
v
ey
s
,
an
d
g
ap
an
aly
s
is
.
E
ac
h
s
tep
is
ex
p
lain
ed
ch
r
o
n
o
lo
g
ically
,
s
u
p
p
o
r
te
d
b
y
alg
o
r
ith
m
s
an
d
test
in
g
s
tr
ateg
ies to
en
s
u
r
e
m
eth
o
d
o
lo
g
ical
tr
an
s
p
ar
en
cy
.
2
.
1
.
Resea
rc
h
des
ig
n
T
h
e
r
esear
ch
em
p
lo
y
ed
a
d
esig
n
s
cien
ce
ap
p
r
o
ac
h
s
u
p
p
o
r
te
d
b
y
em
p
ir
ical
v
alid
atio
n
.
T
h
e
o
b
jectiv
e
was
to
p
r
o
p
o
s
e
a
m
icr
o
s
er
v
ice
-
o
r
ien
ted
,
m
ac
h
in
e
-
lear
n
in
g
f
r
am
ewo
r
k
f
o
r
co
ld
-
ch
ai
n
m
an
a
g
em
en
t
in
f
is
h
er
ies
lo
g
is
tics
.
T
h
e
d
esig
n
p
r
o
ce
s
s
f
o
llo
wed
a
s
eq
u
en
tial f
l
o
w:
−
L
iter
atu
r
e
r
ev
iew
–
to
id
e
n
t
if
y
ex
is
tin
g
co
l
d
ch
ain
m
an
ag
em
en
t
m
o
d
els,
I
o
T
ad
o
p
tio
n
,
ed
g
e/clo
u
d
co
m
p
u
tin
g
in
teg
r
atio
n
,
an
d
th
e
r
o
le
o
f
m
ac
h
in
e
lear
n
in
g
i
n
p
r
ed
ictiv
e
an
aly
tics
[
2
1
]
,
[
2
7
]
,
[
2
8
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
4
1
,
No
.
3
,
Ma
r
ch
20
2
6
:
1
0
7
0
-
1
0
8
1
1072
−
C
o
n
ce
p
tu
al
d
esig
n
s
tu
d
y
–
to
m
ap
o
u
t
th
e
ar
ch
itectu
r
al
f
r
am
ewo
r
k
,
d
ef
in
in
g
its
tech
n
o
lo
g
ical
co
m
p
o
n
en
ts
,
in
clu
d
i
n
g
s
en
s
o
r
s
,
ed
g
e
d
e
v
ices,
clo
u
d
s
to
r
ag
e
,
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
s
an
d
i
n
teg
r
atio
n
s
tr
ateg
y
.
−
Field
s
u
r
v
ey
–
to
co
llect
e
m
p
ir
ical
d
ata
f
r
o
m
co
ld
s
to
r
ag
e
f
ac
ilit
ies
in
I
n
d
r
am
ay
u
,
W
est
J
av
a.
T
h
is
in
clu
d
ed
d
ir
ec
t
o
b
s
er
v
atio
n
o
f
m
o
n
ito
r
in
g
p
r
ac
tices,
eq
u
ip
m
e
n
t
d
u
r
ab
ilit
y
,
an
d
o
r
g
an
izatio
n
al
f
r
ag
m
en
tatio
n
.
−
Gap
a
n
aly
s
is
–
to
co
m
p
ar
e
f
ield
co
n
d
itio
n
s
with
th
e
en
v
is
io
n
ed
id
ea
l
ar
c
h
itectu
r
e,
h
ig
h
lig
h
tin
g
d
ef
icien
cies in
tech
n
o
l
o
g
y
a
n
d
g
o
v
er
n
an
ce
[
2
9
]
–
[
3
1
]
.
−
Fra
m
ewo
r
k
d
e
v
elo
p
m
e
n
t
–
to
p
r
o
p
o
s
e
th
e
f
i
n
al
m
icr
o
s
er
v
i
ce
-
o
r
ien
ted
m
ac
h
in
e
lea
r
n
in
g
f
r
am
ewo
r
k
th
at
ad
d
r
ess
es o
b
s
er
v
ed
g
a
p
s
an
d
e
n
ab
les r
ea
l
-
tim
e
m
o
n
it
o
r
in
g
,
p
r
ed
ictio
n
,
an
d
d
ec
is
io
n
-
m
ak
in
g
.
T
ab
le
1
.
C
o
m
p
a
r
is
o
n
o
f
ex
is
tin
g
co
ld
ch
ain
AI
f
r
am
ewo
r
k
s
an
d
th
e
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
S
t
u
d
y
M
a
i
n
f
o
c
u
s
M
L
m
e
t
h
o
d
s
u
se
d
S
y
st
e
m
a
r
c
h
i
t
e
c
t
u
r
e
Li
mi
t
a
t
i
o
n
s i
d
e
n
t
i
f
i
e
d
N
o
v
e
l
c
o
n
t
r
i
b
u
t
i
o
n
o
f
t
h
i
s
st
u
d
y
Cil
e
t
a
l
.
[
5
]
I
o
T
-
b
a
se
d
r
e
a
l
-
tim
e
mo
n
i
t
o
r
i
n
g
f
o
r
c
o
l
d
c
h
a
i
n
B
a
si
c
a
n
o
ma
l
y
r
u
l
e
s
,
t
h
r
e
s
h
o
l
d
d
e
t
e
c
t
i
o
n
C
l
o
u
d
-
c
e
n
t
r
i
c
,
c
e
n
t
r
a
l
i
z
e
d
d
a
t
a
p
r
o
c
e
ss
i
n
g
N
o
p
r
e
d
i
c
t
i
v
e
a
n
a
l
y
t
i
c
s,
n
o
su
p
p
o
r
t
f
o
r
v
i
su
a
l
f
i
s
h
q
u
a
l
i
t
y
,
n
o
t
sca
l
a
b
l
e
I
n
t
r
o
d
u
c
e
s
M
L
-
b
a
se
d
p
r
e
d
i
c
t
i
v
e
a
n
a
l
y
t
i
c
s (RF
,
LSTM
)
a
n
d
i
ma
g
e
-
b
a
s
e
d
f
i
sh
q
u
a
l
i
t
y
mo
n
i
t
o
r
i
n
g
(
C
N
N
)
W
a
n
g
e
t
a
l
.
[
6
]
Ed
g
e
c
o
m
p
u
t
i
n
g
f
o
r
c
o
l
d
c
h
a
i
n
mo
n
i
t
o
r
i
n
g
A
n
o
m
a
l
y
d
e
t
e
c
t
i
o
n
(
st
a
t
i
st
i
c
a
l
)
Ed
g
e
-
c
l
o
u
d
h
y
b
r
i
d
,
si
n
g
l
e
serv
i
c
e
N
o
mi
c
r
o
s
e
r
v
i
c
e
mo
d
u
l
a
r
i
t
y
,
n
o
A
I
-
b
a
sed
f
r
e
sh
n
e
ss
c
l
a
ssi
f
i
c
a
t
i
o
n
A
d
d
s
mi
c
r
o
s
e
r
v
i
c
e
-
b
a
s
e
d
h
y
b
r
i
d
d
e
p
l
o
y
me
n
t
w
i
t
h
mu
l
t
i
m
o
d
a
l
M
L
c
a
p
a
b
i
l
i
t
i
e
s
H
a
n
i
f
a
e
t
a
l
.
[
1
2
]
C
N
N
f
o
r
f
i
s
h
q
u
a
l
i
t
y
c
l
a
ss
i
f
i
c
a
t
i
o
n
C
N
N
Lo
c
a
l
i
m
a
g
e
p
r
o
c
e
ss
i
n
g
,
n
o
i
n
t
e
g
r
a
t
i
o
n
w
i
t
h
c
o
l
d
c
h
a
i
n
sy
s
t
e
m
N
o
r
e
a
l
-
t
i
me
d
e
p
l
o
y
m
e
n
t
o
r
I
o
T
i
n
t
e
g
r
a
t
i
o
n
I
n
t
e
g
r
a
t
e
s
v
i
su
a
l
i
n
sp
e
c
t
i
o
n
(
C
N
N
)
i
n
t
o
r
e
a
l
-
t
i
me
c
o
l
d
c
h
a
i
n
f
r
a
m
e
w
o
r
k
B
a
i
e
t
a
l
.
[
7
]
A
I
o
T
-
e
n
a
b
l
e
d
smar
t
c
o
l
d
c
h
a
i
n
M
L
f
o
r
e
c
a
st
i
n
g
f
o
r
sp
o
i
l
a
g
e
C
l
o
u
d
+
I
o
T
-
b
a
s
e
d
mo
n
i
t
o
r
i
n
g
N
o
e
d
g
e
p
r
o
c
e
ss
i
n
g
,
l
a
c
k
s m
i
c
r
o
ser
v
i
c
e
sca
l
a
b
i
l
i
t
y
A
d
d
s
e
d
g
e
i
n
f
e
r
e
n
c
e
,
c
o
n
t
a
i
n
e
r
i
z
a
t
i
o
n
(
D
o
c
k
e
r
)
,
a
n
d
d
i
s
t
r
i
b
u
t
e
d
s
e
r
v
i
c
e
s
P
r
o
p
o
se
d
f
r
a
mew
o
r
k
(
Th
i
s
st
u
d
y
)
I
n
t
e
l
l
i
g
e
n
t
h
y
b
r
i
d
a
r
c
h
i
t
e
c
t
u
r
e
f
o
r
f
i
sh
l
o
g
i
st
i
c
s
R
F
,
LS
TM
,
C
N
N
M
i
c
r
o
s
e
r
v
i
c
e
-
b
a
s
e
d
Ed
g
e
–
C
l
o
u
d
w
i
t
h
D
o
c
k
e
r
,
M
Q
T
T,
A
P
I
G
a
t
e
w
a
y
A
d
d
r
e
ss
e
s m
o
d
u
l
a
r
d
e
p
l
o
y
me
n
t
,
p
r
e
d
i
c
t
i
v
e
a
n
a
l
y
t
i
c
s,
v
i
s
u
a
l
a
ssessm
e
n
t
,
a
n
d
i
n
t
e
r
o
p
e
r
a
b
i
l
i
t
y
.
A
u
n
i
f
i
e
d
,
sc
a
l
a
b
l
e
,
p
r
e
d
i
c
t
i
v
e
,
a
n
d
d
e
p
l
o
y
a
b
l
e
mi
c
r
o
serv
i
c
e
-
o
r
i
e
n
t
e
d
M
L
f
r
a
me
w
o
r
k
t
a
i
l
o
r
e
d
f
o
r
p
e
r
i
s
h
a
b
l
e
f
i
sh
l
o
g
i
st
i
c
s
2
.
2
.
Resea
rc
h
pro
ce
du
re
T
h
e
o
v
er
all
p
r
o
ce
d
u
r
e
o
f
th
is
r
esear
ch
was
ca
r
ef
u
lly
s
tr
u
ctu
r
ed
to
f
o
llo
w
a
c
h
r
o
n
o
lo
g
ical
s
eq
u
en
ce
.
E
ac
h
s
tag
e
was
lo
g
ically
co
n
n
ec
ted
to
th
e
p
r
ev
io
u
s
o
n
e
,
en
s
u
r
in
g
th
at
th
eo
r
etica
l
in
s
ig
h
ts
wer
e
v
alid
ated
th
r
o
u
g
h
p
r
ac
tical
o
b
s
er
v
atio
n
an
d
d
esig
n
ev
al
u
atio
n
.
T
h
e
f
o
llo
win
g
d
escr
ip
tio
n
elab
o
r
ates
th
e
m
aj
o
r
s
tep
s
in
d
etail,
h
ig
h
lig
h
tin
g
th
eir
o
r
d
e
r
an
d
co
n
tr
ib
u
tio
n
:
Step
1
:
L
iter
atu
r
e
r
ev
iew
–
s
y
s
tem
atica
lly
co
llected
ar
ticles
c
o
n
ce
r
n
in
g
I
o
T
-
b
ased
m
o
n
ito
r
in
g
,
ed
g
e
co
m
p
u
tin
g
in
lo
g
is
tics
,
ML
f
o
r
an
o
m
aly
d
etec
tio
n
,
an
d
s
u
p
p
ly
ch
ain
g
o
v
er
n
an
ce
[
2
1
]
,
[
2
7
]
,
[
2
8
]
.
Step
2
:
C
o
n
ce
p
tu
al
f
r
am
ewo
r
k
d
esig
n
–
d
ev
el
o
p
ed
a
n
ar
ch
itectu
r
e
m
o
d
el
co
n
s
is
tin
g
o
f
:
-
Mu
ltimo
d
al
in
p
u
t
lay
er
(
tem
p
er
atu
r
e
s
en
s
o
r
s
,
d
ig
ital
th
er
m
o
m
eter
s
,
im
ag
in
g
d
e
v
ices,
R
FID
,
an
d
GPS).
-
E
d
g
e
p
r
o
ce
s
s
in
g
lay
er
(
lo
w
-
co
s
t
ed
g
e
co
m
p
u
tin
g
p
latf
o
r
m
s
f
o
r
p
r
e
-
p
r
o
ce
s
s
in
g
an
d
an
o
m
aly
d
etec
tio
n
)
.
-
C
lo
u
d
s
to
r
ag
e
an
d
an
aly
tic
s
la
y
er
(
d
is
tr
ib
u
te
d
s
to
r
ag
e
s
u
ch
a
s
S3
/HDF
S,
b
ig
d
ata
p
ip
elin
es
)
.
-
Ma
ch
in
e
lear
n
in
g
la
y
er
(
r
a
n
d
o
m
f
o
r
est
f
o
r
a
n
o
m
aly
d
etec
tio
n
[
9
]
,
L
STM
f
o
r
t
im
e
-
s
er
ies
p
r
ed
ictio
n
[
1
0
]
,
C
NN
f
o
r
im
ag
e
-
b
ased
f
is
h
q
u
ality
ass
ess
m
en
t
[
1
1
]
).
-
Vis
u
aliza
tio
n
an
d
d
ec
is
io
n
lay
er
(
d
ash
b
o
ar
d
s
v
ia
Gr
af
an
a/
p
o
wer
B
I
,
g
eo
s
p
atial
in
ter
f
ac
es
lik
e
QGI
S/Lea
f
letJ
S).
T
h
e
d
esig
n
was
co
n
s
tr
u
cte
d
u
n
d
er
a
m
icr
o
s
er
v
ice
-
o
r
ien
ted
ar
c
h
itectu
r
e
e
n
s
u
r
in
g
s
ca
lab
ilit
y
,
in
ter
o
p
er
a
b
ilit
y
,
an
d
m
o
d
u
lar
ity
.
Step
3
:
Field
s
u
r
v
ey
an
d
d
ata
ac
q
u
is
itio
n
–
co
n
d
u
cte
d
in
Sep
tem
b
e
r
2
0
2
5
at
I
n
d
r
am
ay
u
co
ld
s
to
r
a
g
e
f
ac
ilit
y
(
ca
p
ac
ity
3
0
0
to
n
s
,
d
iv
id
ed
in
t
o
th
r
ee
ch
a
m
b
er
s
)
.
Ac
q
u
ir
ed
p
r
im
ar
y
d
ata
t
h
r
o
u
g
h
:
-
Dir
ec
t o
b
s
er
v
atio
n
o
f
m
o
n
ito
r
i
n
g
d
ev
ices a
n
d
p
r
o
ce
d
u
r
es.
-
Staf
f
in
ter
v
iews a
b
o
u
t c
h
allen
g
es in
eq
u
ip
m
e
n
t d
u
r
ab
ilit
y
an
d
m
o
n
ito
r
in
g
p
r
a
ctice
s
.
-
Do
cu
m
en
tatio
n
o
f
o
r
g
an
izatio
n
al
s
tr
u
ctu
r
e
(
n
o
tin
g
f
r
ag
m
e
n
t
atio
n
ac
r
o
s
s
m
u
ltip
le
co
m
p
an
i
es).
-
Key
f
in
d
in
g
s
:
m
an
u
al
th
er
m
o
m
eter
s
attac
h
ed
to
d
o
o
r
s
,
C
C
T
V
f
o
g
g
in
g
is
s
u
es
at
<1
4
°C
,
lack
o
f
ce
n
tr
alize
d
m
o
n
it
o
r
in
g
,
elec
tr
o
n
ic
d
ev
ice
d
eg
r
a
d
atio
n
in
co
l
d
r
o
o
m
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
A
micro
s
ervice
-
o
r
ien
ted
ma
ch
in
e
lea
r
n
in
g
fr
a
mewo
r
k
fo
r
co
ld
ch
a
in
ma
n
a
g
eme
n
t in
…
(
M
a
u
n
Ja
m
a
lu
d
in
)
1073
Step
4
:
Gap
an
aly
s
is
–
co
m
p
a
r
ed
cu
r
r
en
t p
r
ac
tices with
th
e
p
r
o
p
o
s
e
d
m
o
d
el.
I
d
en
tifie
d
g
ap
s
:
-
L
ac
k
o
f
r
ea
l
-
tim
e
an
o
m
aly
d
et
ec
tio
n
an
d
p
r
ed
ictiv
e
ca
p
ab
ilit
ies.
-
No
in
teg
r
atio
n
b
etwe
en
m
u
lti
m
o
d
al
s
en
s
o
r
d
ata
a
n
d
ce
n
tr
alize
d
d
ash
b
o
a
r
d
s
.
-
I
n
s
titu
tio
n
al
f
r
ag
m
e
n
tatio
n
r
e
q
u
ir
in
g
co
n
s
o
r
tiu
m
-
b
ased
g
o
v
er
n
an
ce
[
2
9
]
–
[
3
1
]
.
Step
5
:
Fra
m
ewo
r
k
s
y
n
th
esis
an
d
v
al
id
atio
n
s
tr
ateg
y
–
co
n
s
o
lid
ate
d
f
in
d
in
g
s
in
to
a
f
r
am
ewo
r
k
p
r
o
to
ty
p
e
d
esig
n
.
Valid
atio
n
p
lan
:
s
im
u
late
tem
p
er
atu
r
e/tim
e
-
s
er
ies
d
atasets
an
d
f
is
h
im
ag
e
class
if
icatio
n
to
test
ML
alg
o
r
ith
m
p
er
f
o
r
m
an
c
e.
Fu
tu
r
e
i
m
p
lem
en
tatio
n
:
d
ep
lo
y
ed
g
e
-
clo
u
d
in
te
g
r
ated
m
icr
o
s
er
v
ices
an
d
ev
alu
ate
a
g
ain
s
t K
P
I
s
s
u
ch
as a
cc
u
r
ac
y
,
laten
cy
,
s
ca
lab
i
lity
,
an
d
in
ter
o
p
er
a
b
ilit
y
[
2
3
]
,
[
2
4
]
,
[
3
2
]
.
T
h
e
f
r
am
ewo
r
k
u
tili
ze
s
a
h
y
b
r
id
e
d
g
e
–
cl
o
u
d
ar
ch
itectu
r
e,
lev
er
ag
i
n
g
co
n
tain
er
ize
d
s
er
v
ices
an
d
m
o
d
u
lar
d
ep
lo
y
m
en
t
f
o
r
s
ca
l
ab
ilit
y
,
in
ter
o
p
er
a
b
ilit
y
,
an
d
r
ea
l
-
tim
e
m
o
n
ito
r
in
g
.
T
ab
le
2
s
u
m
m
ar
izes
th
e
tech
n
ical
co
n
f
ig
u
r
ati
o
n
,
in
clu
d
in
g
t
h
e
in
te
g
r
atio
n
o
f
I
o
T
d
e
v
ices,
d
ata
o
r
ch
estra
tio
n
to
o
ls
,
m
ac
h
in
e
lear
n
i
n
g
en
g
in
es,
m
o
d
el
d
ep
lo
y
m
en
t e
n
v
ir
o
n
m
e
n
ts
,
an
d
s
y
s
tem
v
is
u
al
izatio
n
p
latf
o
r
m
s
.
T
ab
le
2
.
T
ec
h
n
ical
co
n
f
ig
u
r
ati
o
n
o
f
th
e
p
r
o
p
o
s
ed
co
ld
c
h
ain
f
r
am
ewo
r
k
La
y
e
r
/
c
o
m
p
o
n
e
n
t
To
o
l
s
/
t
e
c
h
n
o
l
o
g
i
e
s
F
u
n
c
t
i
o
n
a
l
i
t
y
M
L
a
l
g
o
r
i
t
h
m
u
s
e
d
D
e
p
l
o
y
me
n
t
t
y
p
e
I
n
p
u
t
a
n
d
se
n
si
n
g
l
a
y
e
r
Te
mp
e
r
a
t
u
r
e
a
n
d
h
u
m
i
d
i
t
y
sen
s
o
r
s (D
S
1
8
B
2
0
)
,
R
F
I
D
,
G
P
S
,
P
O
E
c
a
meras
En
v
i
r
o
n
m
e
n
t
m
o
n
i
t
o
r
i
n
g
,
b
a
t
c
h
t
r
a
c
k
i
n
g
,
i
ma
g
e
c
a
p
t
u
r
e
–
P
h
y
s
i
c
a
l
I
o
T
d
e
v
i
c
e
s,
M
Q
TT
I
o
T
d
a
t
a
b
r
o
k
e
r
M
Q
TT,
M
o
s
q
u
i
t
t
o
,
K
a
f
k
a
S
e
n
s
o
r
d
a
t
a
s
t
r
e
a
m
i
n
g
,
r
e
a
l
-
t
i
m
e
e
v
e
n
t
mess
a
g
i
n
g
–
Ed
g
e
a
n
d
C
l
o
u
d
Ed
g
e
p
r
o
c
e
ss
i
n
g
l
a
y
e
r
R
a
s
p
b
e
r
r
y
P
i
,
J
e
t
s
o
n
N
a
n
o
,
D
o
c
k
e
r
,
P
y
t
h
o
n
,
F
l
a
s
k
A
P
I
D
a
t
a
f
i
l
t
e
r
i
n
g
,
p
r
e
p
r
o
c
e
ss
i
n
g
,
l
i
g
h
t
i
n
f
e
r
e
n
c
e
R
F
(
a
n
o
m
a
l
y
d
e
t
e
c
t
i
o
n
)
,
C
N
N
(
b
a
si
c
c
l
a
s
si
f
i
c
a
t
i
o
n
)
Ed
g
e
c
o
n
t
a
i
n
e
r
M
i
c
r
o
s
e
r
v
i
c
e
O
r
c
h
e
s
t
r
a
t
i
o
n
D
o
c
k
e
r
,
K
u
b
e
r
n
e
t
e
s (
K
8
s)
,
g
R
P
C
,
R
EST
A
P
I
M
o
d
u
l
a
r
ser
v
i
c
e
d
e
p
l
o
y
me
n
t
,
f
a
u
l
t
i
so
l
a
t
i
o
n
,
c
o
n
t
a
i
n
e
r
s
c
a
l
i
n
g
–
C
l
o
u
d
a
n
d
Ed
g
e
A
P
I
g
a
t
e
w
a
y
a
n
d
l
o
a
d
b
a
l
a
n
c
e
r
K
o
n
g
,
N
g
i
n
x
,
H
A
P
r
o
x
y
R
o
u
t
i
n
g
,
l
o
a
d
m
a
n
a
g
e
m
e
n
t
,
a
u
t
h
e
n
t
i
c
a
t
i
o
n
–
C
l
o
u
d
D
a
t
a
st
o
r
a
g
e
a
n
d
man
a
g
e
me
n
t
S
3
O
b
j
e
c
t
S
t
o
r
a
g
e
,
H
D
F
S
,
S
Q
Li
t
e
,
P
o
st
g
r
e
S
Q
L
D
i
st
r
i
b
u
t
e
d
s
t
o
r
a
g
e
,
st
r
u
c
t
u
r
e
d
/
u
n
s
t
r
u
c
t
u
r
e
d
d
a
t
a
man
a
g
e
me
n
t
–
C
l
o
u
d
a
n
d
h
y
b
r
i
d
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
e
n
g
i
n
e
Te
n
s
o
r
F
l
o
w
,
S
c
i
k
i
t
-
l
e
a
r
n
,
P
y
T
o
r
c
h
M
L
m
o
d
e
l
t
r
a
i
n
i
n
g
a
n
d
i
n
f
e
r
e
n
c
e
R
F
,
LS
TM
,
C
N
N
C
l
o
u
d
-
b
a
se
d
i
n
f
e
r
e
n
c
e
/
b
a
t
c
h
p
r
o
c
e
ss
i
n
g
M
o
d
e
l
d
e
p
l
o
y
me
n
t
l
a
y
e
r
Te
n
s
o
r
F
l
o
w
s
e
r
v
i
n
g
,
M
Lf
l
o
w
,
F
a
st
A
P
I
R
e
a
l
-
t
i
me
i
n
f
e
r
e
n
c
e
,
m
o
d
e
l
v
e
r
si
o
n
i
n
g
,
R
EST
e
n
d
p
o
i
n
t
s
R
F
,
LS
TM
,
C
N
N
Ed
g
e
-
c
l
o
u
d
h
y
b
r
i
d
V
i
su
a
l
i
z
a
t
i
o
n
a
n
d
a
n
a
l
y
t
i
c
s
G
r
a
f
a
n
a
,
p
o
w
e
r
B
I
,
S
t
r
e
a
m
l
i
t
,
Le
a
f
l
e
t
JS
,
Q
G
I
S
D
a
sh
b
o
a
r
d
s
,
g
e
o
sp
a
t
i
a
l
r
o
u
t
e
t
r
a
c
k
i
n
g
,
p
r
e
d
i
c
t
i
v
e
a
n
a
l
y
t
i
c
s
–
C
l
o
u
d
-
b
a
se
d
U
I
P
e
r
f
o
r
ma
n
c
e
mo
n
i
t
o
r
i
n
g
P
r
o
met
h
e
u
s
,
G
r
a
f
a
n
a
,
EL
K
S
t
a
c
k
La
t
e
n
c
y
t
r
a
c
k
i
n
g
,
C
P
U
/
mem
o
r
y
m
o
n
i
t
o
r
i
n
g
,
a
n
o
ma
l
y
a
l
e
r
t
i
n
g
–
C
l
o
u
d
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
is
s
ec
tio
n
p
r
esen
ts
th
e
r
esear
ch
r
esu
lts
an
d
th
eir
im
p
licatio
n
s
f
o
r
f
is
h
er
ies co
ld
ch
ai
n
m
a
n
ag
em
en
t.
T
h
e
f
in
d
i
n
g
s
ar
e
s
tr
u
ctu
r
e
d
ac
co
r
d
in
g
to
th
e
ar
ch
itectu
r
al
la
y
er
s
an
d
an
al
y
tical
co
m
p
o
n
en
ts
o
f
th
e
p
r
o
p
o
s
ed
f
r
am
ewo
r
k
.
E
ac
h
lay
er
is
ex
a
m
in
ed
to
h
ig
h
lig
h
t
its
r
o
le
an
d
co
n
tr
ib
u
tio
n
to
en
ab
lin
g
an
in
tellig
en
t
co
ld
ch
ain
s
y
s
tem
th
at
s
u
p
p
o
r
ts
p
r
o
d
u
ct
f
r
esh
n
ess
,
o
p
er
atio
n
al
ef
f
icien
cy
,
an
d
s
u
s
tain
ab
le
d
is
tr
ib
u
tio
n
,
as
illu
s
tr
ated
in
Fig
u
r
e
1
.
3
.
1
.
Co
ncept
ua
l a
rc
hite
ct
ur
e
T
h
e
p
r
o
p
o
s
ed
f
r
am
ewo
r
k
ad
o
p
ts
a
m
icr
o
s
er
v
ice
-
o
r
ien
ted
ar
ch
itectu
r
e
to
s
u
p
p
o
r
t
s
ca
l
ab
ilit
y
an
d
m
o
d
u
lar
d
ep
lo
y
m
en
t
in
p
er
i
s
h
ab
le
f
is
h
co
ld
c
h
ain
lo
g
is
tics
.
C
o
r
e
f
u
n
ctio
n
alities
ar
e
d
ec
o
m
p
o
s
ed
in
to
in
d
ep
en
d
en
t
s
er
v
ices
an
d
d
is
tr
ib
u
ted
ac
r
o
s
s
ed
g
e
–
cl
o
u
d
e
n
v
ir
o
n
m
en
ts
.
Hete
r
o
g
en
eo
u
s
d
ata
f
r
o
m
s
en
s
o
r
s
,
GPS,
an
d
v
is
u
al
i
n
p
u
ts
a
r
e
p
r
o
ce
s
s
ed
th
r
o
u
g
h
a
u
n
i
f
ied
p
ip
elin
e,
e
n
ab
lin
g
r
ea
l
-
tim
e
an
aly
tics
,
m
ac
h
in
e
lear
n
in
g
in
f
er
en
ce
,
a
n
d
s
ea
m
le
s
s
s
y
s
tem
in
teg
r
atio
n
.
3
.
2
.
Co
ld cha
in cha
lleng
es in f
is
heries
dis
t
rib
utio
n
Fis
h
er
ies
co
ld
ch
ain
lo
g
is
tics
f
ac
e
ch
allen
g
es
r
elate
d
to
tem
p
er
atu
r
e
v
a
r
iab
ilit
y
,
f
r
ag
m
en
ted
d
is
tr
ib
u
tio
n
n
etwo
r
k
s
,
lim
ited
r
ea
l
-
tim
e
v
is
ib
ilit
y
,
an
d
d
elay
ed
d
ec
is
io
n
-
m
a
k
in
g
.
I
n
d
ev
el
o
p
in
g
c
o
n
tex
ts
s
u
ch
as
I
n
d
o
n
esia,
th
ese
is
s
u
es
ar
e
in
ten
s
if
ied
b
y
i
n
f
r
astru
ctu
r
e
co
n
s
tr
ain
ts
an
d
m
a
n
u
al
m
o
n
i
to
r
in
g
p
r
ac
tices.
C
o
n
v
en
tio
n
al
co
ld
ch
ai
n
s
y
s
tem
s
p
r
im
ar
ily
em
p
h
asize
m
o
n
ito
r
in
g
with
o
u
t
p
r
ed
ictiv
e
ca
p
ab
ilit
ies,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
4
1
,
No
.
3
,
Ma
r
ch
20
2
6
:
1
0
7
0
-
1
0
8
1
1074
u
n
d
er
s
co
r
i
n
g
th
e
n
ee
d
f
o
r
in
t
ellig
en
t
f
r
am
ewo
r
k
s
th
at
s
u
p
p
o
r
t
r
ea
l
-
tim
e
an
aly
tics
,
s
p
o
il
ag
e
r
is
k
p
r
ed
ictio
n
,
an
d
s
ca
lab
le
s
y
s
tem
in
teg
r
atio
n
.
Gap
b
etwe
en
id
ea
l
co
ld
c
h
ain
ar
ch
itectu
r
e
an
d
f
ield
co
n
d
itio
n
s
is
s
h
o
wn
in
T
ab
le
3
.
Fig
u
r
e
1
.
Pro
p
o
s
ed
m
icr
o
s
er
v
i
ce
-
o
r
ien
ted
AI
/ML
f
r
am
ewo
r
k
f
o
r
co
l
d
ch
ain
m
an
ag
e
m
en
t
T
ab
le
3
.
Gap
b
etwe
en
id
ea
l c
o
ld
ch
ain
ar
c
h
itectu
r
e
an
d
f
ield
co
n
d
itio
n
s
A
sp
e
c
t
I
d
e
a
l
c
o
n
d
i
t
i
o
n
(
p
l
a
n
n
e
d
a
r
c
h
i
t
e
c
t
u
r
e
)
F
i
e
l
d
o
b
ser
v
a
t
i
o
n
Te
mp
e
r
a
t
u
r
e
m
o
n
i
t
o
r
i
n
g
C
o
n
t
i
n
u
o
u
s
d
i
g
i
t
a
l
m
o
n
i
t
o
r
i
n
g
w
i
t
h
I
o
T
se
n
so
r
s
i
n
t
e
g
r
a
t
e
d
i
n
t
o
c
e
n
t
r
a
l
i
z
e
d
d
a
s
h
b
o
a
r
d
s
M
a
n
u
a
l
r
e
a
d
i
n
g
s
u
si
n
g
n
o
n
-
d
i
g
i
t
a
l
t
h
e
r
mo
me
t
e
r
s
a
t
t
a
c
h
e
d
a
t
c
o
l
d
r
o
o
m
d
o
o
r
s
V
i
su
a
l
m
o
n
i
t
o
r
i
n
g
H
i
g
h
-
r
e
so
l
u
t
i
o
n
c
a
mer
a
s
i
n
t
e
g
r
a
t
e
d
w
i
t
h
C
N
N
f
o
r
f
i
sh
q
u
a
l
i
t
y
a
sses
sme
n
t
C
C
TV
c
a
m
e
r
a
s f
o
g
g
e
d
a
t
<
1
4
°
C
,
u
n
a
b
l
e
t
o
c
l
e
a
r
l
y
c
a
p
t
u
r
e
f
i
s
h
c
o
n
d
i
t
i
o
n
D
a
t
a
a
c
c
e
ss
R
e
a
l
-
t
i
me,
c
e
n
t
r
a
l
i
z
e
d
m
o
n
i
t
o
r
i
n
g
a
c
c
e
ssi
b
l
e
a
t
c
o
n
t
r
o
l
d
e
sk
M
o
n
i
t
o
r
i
n
g
o
n
l
y
p
o
ssi
b
l
e
o
n
-
si
t
e
i
n
f
r
o
n
t
o
f
st
o
r
a
g
e
d
o
o
r
s
P
r
e
d
i
c
t
i
v
e
a
n
a
l
y
t
i
c
s
A
I
/
M
L
mo
d
e
l
s (
R
F
,
LS
TM
,
C
N
N
)
f
o
r
a
n
o
m
a
l
y
d
e
t
e
c
t
i
o
n
,
s
p
o
i
l
a
g
e
p
r
e
d
i
c
t
i
o
n
,
a
n
d
q
u
a
l
i
t
y
c
l
a
ss
i
f
i
c
a
t
i
o
n
N
o
p
r
e
d
i
c
t
i
v
e
sy
s
t
e
m
;
e
n
t
i
r
e
l
y
r
e
a
c
t
i
v
e
t
o
t
e
m
p
e
r
a
t
u
r
e
c
h
a
n
g
e
s
D
e
v
i
c
e
d
u
r
a
b
i
l
i
t
y
Ed
g
e
d
e
v
i
c
e
s
d
e
si
g
n
e
d
f
o
r
l
o
w
-
t
e
m
p
e
r
a
t
u
r
e
o
p
e
r
a
t
i
o
n
(
i
n
d
u
st
r
i
a
l
-
g
r
a
d
e
e
l
e
c
t
r
o
n
i
c
s
)
S
t
a
f
f
r
e
p
o
r
t
e
d
e
l
e
c
t
r
o
n
i
c
d
e
v
i
c
e
s
d
e
g
r
a
d
e
q
u
i
c
k
l
y
i
n
c
o
l
d
s
t
o
r
a
g
e
e
n
v
i
r
o
n
m
e
n
t
O
r
g
a
n
i
z
a
t
i
o
n
a
l
s
t
r
u
c
t
u
r
e
U
n
i
f
i
e
d
mi
c
r
o
s
e
r
v
i
c
e
-
b
a
s
e
d
a
r
c
h
i
t
e
c
t
u
r
e
u
n
d
e
r
a
si
n
g
l
e
g
o
v
e
r
n
a
n
c
e
m
o
d
e
l
Fr
a
g
me
n
t
e
d
o
p
e
r
a
t
i
o
n
s
a
c
r
o
ss m
u
l
t
i
p
l
e
c
o
m
p
a
n
i
e
s/
o
r
g
a
n
i
z
a
t
i
o
n
w
i
t
h
d
i
f
f
e
r
e
n
t
p
r
i
o
r
i
t
i
e
s
3.
3
.
I
np
ut
dev
ice
la
y
er
T
h
e
in
p
u
t
d
e
v
ice
lay
er
s
er
v
e
s
as
th
e
f
o
u
n
d
atio
n
o
f
th
e
p
r
o
p
o
s
ed
ar
ch
itectu
r
e,
f
u
n
ctio
n
i
n
g
as
th
e
p
r
im
ar
y
i
n
ter
f
ac
e
b
etwe
en
th
e
p
h
y
s
ical
co
ld
ch
ain
en
v
ir
o
n
m
en
t
an
d
t
h
e
d
ig
ital
m
o
n
ito
r
i
n
g
s
y
s
tem
.
T
h
is
lay
er
is
r
esp
o
n
s
ib
le
f
o
r
ca
p
tu
r
in
g
m
u
ltimo
d
al
d
ata
th
at
r
ef
lects
b
o
th
en
v
ir
o
n
m
en
tal
co
n
d
itio
n
s
an
d
p
r
o
d
u
ct
q
u
ality
in
r
ea
l
tim
e.
B
y
in
teg
r
atin
g
d
i
v
er
s
e
s
en
s
in
g
tech
n
o
lo
g
ies,
it
en
s
u
r
es
th
e
a
v
ailab
ilit
y
o
f
co
m
p
r
eh
en
s
iv
e
d
atasets
th
at
s
u
p
p
o
r
t
s
u
b
s
eq
u
en
t
p
r
o
ce
s
s
in
g
,
p
r
ed
ictio
n
,
a
n
d
d
ec
is
io
n
-
m
ak
in
g
.
T
h
e
i
n
p
u
t
d
ev
ice
l
ay
er
c
o
n
s
titu
tes
th
e
f
o
u
n
d
atio
n
f
o
r
d
ata
ac
q
u
is
itio
n
.
I
t in
teg
r
ates:
−
C
am
er
as c
ap
tu
r
in
g
r
ea
l
-
tim
e
f
i
s
h
im
ag
es f
o
r
co
m
p
u
ter
v
is
io
n
an
d
C
NN
-
b
ased
class
if
icatio
n
.
−
T
em
p
er
atu
r
e
a
n
d
h
u
m
id
ity
s
en
s
o
r
s
m
o
n
ito
r
s
tab
ilit
y
to
tr
ig
g
e
r
ea
r
ly
war
n
i
n
g
s
.
−
I
o
T
d
ev
ices
in
clu
d
e
in
R
FID
,
GPS,
an
d
s
m
ar
t
s
en
s
o
r
s
b
u
ild
with
in
ed
g
e
d
ev
ice
f
o
r
tr
ac
k
in
g
b
atch
es,
lo
ca
tio
n
,
an
d
s
h
o
ck
s
d
u
r
in
g
tr
an
s
p
o
r
tatio
n
.
T
h
e
m
in
im
u
m
c
o
n
f
ig
u
r
atio
n
p
er
d
is
tr
ib
u
tio
n
cy
cle
r
ef
er
s
to
th
e
ess
en
tial
s
et
o
f
in
p
u
t
d
ev
ices
r
eq
u
ir
ed
t
o
en
s
u
r
e
r
eliab
le
d
a
ta
ac
q
u
is
itio
n
an
d
m
o
n
ito
r
in
g
ac
r
o
s
s
d
if
f
er
en
t
s
tag
es
o
f
th
e
co
ld
ch
ain
.
T
h
is
co
n
f
ig
u
r
atio
n
o
u
tlin
es
t
h
e
n
u
m
b
er
o
f
ca
m
er
as,
s
en
s
o
r
s
,
an
d
I
o
T
g
atew
ay
s
n
ee
d
e
d
in
co
l
d
s
to
r
ag
e
f
ac
ilit
ies
an
d
tr
an
s
p
o
r
t
v
e
h
icles.
B
y
d
ef
in
in
g
th
ese
b
aselin
e
r
eq
u
ir
em
en
ts
,
th
e
f
r
am
ewo
r
k
estab
lis
h
es
a
p
r
ac
tical
g
u
id
elin
e
f
o
r
s
ca
lab
le
im
p
lem
e
n
tatio
n
in
f
is
h
er
ies lo
g
is
tics
in
T
ab
le
4
.
I
n
to
tal,
t
h
e
m
in
im
u
m
co
n
f
ig
u
r
atio
n
r
eq
u
ir
es
a
p
p
r
o
x
im
atel
y
n
in
e
ca
m
er
as,
twelv
e
s
en
s
o
r
s
,
an
d
s
ix
I
o
T
d
ev
ices to
s
u
p
p
o
r
t
o
n
e
c
o
m
p
lete
d
is
tr
ib
u
tio
n
c
y
cle.
T
h
e
esti
m
ated
co
s
t f
o
r
im
p
lem
en
ti
n
g
th
is
s
etu
p
r
an
g
es
f
r
o
m
USD
6
8
3
to
1
3
6
3
,
eq
u
i
v
alen
t
to
I
DR
1
0
.
6
to
2
1
.
2
m
ill
io
n
,
m
ak
in
g
it
a
f
ea
s
ib
le
y
et
s
ca
lab
le
in
v
estme
n
t
f
o
r
f
is
h
er
ies co
ld
ch
ain
o
p
er
ati
o
n
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
A
micro
s
ervice
-
o
r
ien
ted
ma
ch
in
e
lea
r
n
in
g
fr
a
mewo
r
k
fo
r
co
ld
ch
a
in
ma
n
a
g
eme
n
t in
…
(
M
a
u
n
Ja
m
a
lu
d
in
)
1075
3.
4.
E
dg
e
dev
ice
la
y
er
C
ap
tu
r
ed
d
ata
in
th
e
co
ld
ch
ai
n
s
y
s
tem
m
u
s
t
b
e
p
r
o
ce
s
s
ed
lo
ca
lly
b
ef
o
r
e
tr
an
s
m
is
s
io
n
to
th
e
clo
u
d
in
o
r
d
er
to
m
in
im
ize
d
elay
s
a
n
d
r
e
d
u
ce
r
elian
ce
o
n
ex
ter
n
al
n
etwo
r
k
s
.
E
d
g
e
c
o
m
p
u
tin
g
d
e
v
ices
p
er
f
o
r
m
lig
h
tweig
h
t
co
m
p
u
tatio
n
task
s
,
s
u
ch
as
p
r
ep
r
o
ce
s
s
in
g
telem
etr
y
d
ata
f
r
o
m
tem
p
er
atu
r
e
a
n
d
h
u
m
id
ity
s
en
s
o
r
s
,
wh
ich
en
s
u
r
es
th
at
o
n
ly
r
elev
a
n
t
in
f
o
r
m
atio
n
is
f
o
r
war
d
e
d
f
o
r
f
u
r
t
h
er
an
al
y
s
is
.
T
h
is
lo
ca
l
f
i
lter
in
g
m
ec
h
a
n
is
m
r
ed
u
ce
s
b
an
d
wid
th
co
n
s
u
m
p
ti
o
n
an
d
en
h
a
n
ce
s
th
e
r
esp
o
n
s
iv
en
ess
o
f
m
o
n
ito
r
in
g
s
y
s
tem
s
,
wh
ich
is
cr
u
cial
f
o
r
p
er
is
h
ab
le
p
r
o
d
u
cts th
at
r
e
q
u
ir
e
r
ap
id
in
ter
v
en
tio
n
[
2
5
]
.
Fo
r
m
o
r
e
ad
v
an
ce
d
task
s
,
s
u
c
h
as
co
m
p
u
ter
v
is
io
n
a
n
aly
s
is
o
f
f
is
h
q
u
ality
,
GPU
-
ac
ce
ler
ated
ed
g
e
p
latf
o
r
m
s
ar
e
r
eq
u
i
r
ed
to
h
an
d
le
th
e
co
m
p
u
tatio
n
al
co
m
p
le
x
ity
o
f
co
n
v
o
lu
tio
n
al
n
e
u
r
al
n
etwo
r
k
s
.
Dev
ices
in
th
is
ca
teg
o
r
y
ca
n
p
r
o
ce
s
s
h
ig
h
-
r
eso
lu
tio
n
im
ag
es
i
n
r
ea
l
ti
m
e,
en
a
b
lin
g
im
m
ed
iate
an
o
m
aly
d
etec
tio
n
a
n
d
r
ed
u
cin
g
t
h
e
r
is
k
s
o
f
s
p
o
ilag
e
d
u
r
in
g
s
to
r
a
g
e
an
d
tr
an
s
p
o
r
t
atio
n
.
T
h
e
ad
o
p
tio
n
o
f
s
u
ch
h
eter
o
g
en
eo
u
s
ed
g
e
in
f
r
astru
ctu
r
es
h
as
b
ee
n
s
h
o
wn
to
s
ig
n
if
ican
tly
i
m
p
r
o
v
e
b
o
th
laten
cy
an
d
s
ca
lab
ilit
y
in
s
u
p
p
ly
ch
ai
n
ap
p
licatio
n
s
[
2
2
]
,
[
3
3
]
.
T
ab
le
4
.
Min
im
u
m
co
n
f
ig
u
r
atio
n
p
er
d
is
tr
ib
u
tio
n
c
y
cle
Lo
c
a
t
i
o
n
C
o
m
p
o
n
e
n
t
u
n
i
t
s
C
o
s
t
e
st
i
mat
i
o
n
I
n
i
t
i
a
l
c
o
l
d
st
o
r
a
g
e
(
5
0
0
m
2
)
•
5
t
e
m
p
e
r
a
t
u
r
se
n
so
r
s
w
a
t
e
r
p
r
o
o
f
•
5
p
o
e
c
a
mer
a
s
1
0
8
0
p
•
2
I
o
T
g
a
t
e
w
a
y
U
S
D
6
,
9
0
(
~
I
D
R
1
0
7
r
b
)
U
S
D
4
0
–
8
0
(
~
I
D
R
6
2
0
r
b
–
1
,
2
4
j
t
)
U
S
D
3
5
–
8
0
(
~
I
D
R
5
5
0
r
b
–
1
,
2
4
j
t
)
Tr
a
n
s
p
o
r
t
t
r
u
c
k
(
5
–
1
0
t
o
n
s)
•
4
t
e
m
p
e
r
a
t
u
r
se
n
so
r
s
w
a
t
e
r
p
r
o
o
f
•
2
p
o
e
c
a
mer
a
s
1
0
8
0
p
•
1
G
P
S
Tr
a
c
k
e
r
•
2
I
o
T
g
a
t
e
w
a
y
U
S
D
6
,
9
0
(
~
I
D
R
1
0
7
r
b
)
U
S
D
4
0
–
8
0
(
~
I
D
R
6
2
0
r
b
–
1
,
2
4
j
t
)
U
S
D
3
0
–
8
0
(
~
I
D
R
4
6
5
r
b
–
1
,
2
4
j
t
)
U
S
D
3
5
–
8
0
(
~
I
D
R
5
5
0
r
b
–
1
,
2
4
j
t
)
D
e
st
i
n
a
t
i
o
n
c
o
l
d
st
o
r
a
g
e
(
3
0
0
m2
)
•
3
t
e
m
p
e
r
a
t
u
r
se
n
so
r
s
w
a
t
e
r
p
r
o
o
f
•
2
p
o
e
c
a
mer
a
s
1
0
8
0
p
•
2
I
o
T
g
a
t
e
w
a
y
U
S
D
6
,
9
0
(
~
I
D
R
1
0
7
r
b
)
U
S
D
4
0
–
8
0
(
~
I
D
R
6
2
0
r
b
–
1
,
2
4
j
t
)
U
S
D
3
5
–
8
0
(
~
I
D
R
5
5
0
r
b
–
1
,
2
4
j
t
)
3.
5.
Da
t
a
c
o
llect
io
n a
nd
big
da
t
a
infr
a
s
t
ruct
ure
Data
ag
g
r
eg
atio
n
in
th
e
p
r
o
p
o
s
ed
co
ld
ch
ain
f
r
am
ewo
r
k
in
v
o
lv
es
th
e
s
y
s
tem
atic
co
llectio
n
,
in
teg
r
atio
n
,
a
n
d
m
a
n
ag
em
en
t
o
f
d
ata
s
tr
ea
m
s
o
r
ig
i
n
atin
g
f
r
o
m
m
u
ltip
le
s
o
u
r
ce
s
ac
r
o
s
s
th
e
s
u
p
p
ly
ch
ain
.
T
h
is
p
r
o
ce
s
s
in
clu
d
es
r
o
u
tin
g
s
en
s
o
r
r
ea
d
in
g
s
,
im
ag
e
d
ata,
an
d
I
o
T
s
ig
n
als
th
r
o
u
g
h
s
ec
u
r
e
g
ate
way
s
an
d
b
alan
cin
g
th
eir
d
is
tr
ib
u
tio
n
ac
r
o
s
s
s
er
v
er
s
to
en
s
u
r
e
r
eliab
ilit
y
.
B
y
co
m
b
in
in
g
clo
u
d
-
b
ased
o
b
ject
s
to
r
ag
e
with
d
is
tr
ib
u
ted
f
ile
s
y
s
tem
s
,
th
e
ar
ch
itectu
r
e
g
u
ar
an
tees
b
o
t
h
s
ca
lab
ilit
y
an
d
r
esil
ien
ce
,
p
r
o
v
i
d
in
g
a
r
o
b
u
s
t
f
o
u
n
d
atio
n
f
o
r
r
ea
l
-
tim
e
m
o
n
it
o
r
in
g
a
n
d
ad
v
an
ce
d
an
aly
tics
.
−
API
Gate
way
as th
e
s
in
g
le
-
en
tr
y
p
o
i
n
t f
o
r
API
r
eq
u
ests
,
h
an
d
lin
g
au
th
e
n
ticatio
n
an
d
r
ate
li
m
itin
g
.
−
HT
T
P Ga
tewa
y
f
o
r
ef
f
icien
t
f
ile
tr
an
s
f
er
s
,
co
m
p
r
ess
io
n
,
an
d
s
ec
u
r
ity
.
−
L
o
ad
B
alan
ce
r
d
is
tr
ib
u
tin
g
r
eq
u
ests
ac
r
o
s
s
m
u
ltip
le
s
er
v
er
s
.
−
S3
Sto
r
ag
e
f
o
r
o
b
ject
-
b
ased
,
s
ca
lab
le
clo
u
d
s
to
r
a
g
e.
−
HDFS C
lu
s
ter
f
o
r
o
n
-
p
r
em
is
e,
d
is
tr
ib
u
ted
s
to
r
ag
e
o
f
v
e
r
y
lar
g
e
d
atasets
.
C
o
m
p
ar
ativ
e
an
aly
s
is
s
h
o
ws
S3
ex
ce
ls
f
o
r
s
m
all
-
to
-
m
ed
i
u
m
,
elastic
wo
r
k
lo
ad
s
,
wh
ile
HDFS
is
m
o
r
e
co
s
t
-
ef
f
ec
tiv
e
f
o
r
p
e
ta
b
y
te
-
s
ca
le,
lo
n
g
-
ter
m
s
to
r
ag
e
.
Fig
u
r
e
2
illu
s
tr
ates
th
e
d
ata
f
lo
w
ar
c
h
itectu
r
e
f
o
r
m
e
d
ia
an
d
telem
etr
y
s
tr
ea
m
s
with
in
th
e
co
ld
ch
ai
n
f
r
am
ew
o
r
k
.
I
t
h
ig
h
lig
h
ts
h
o
w
s
en
s
o
r
an
d
im
ag
e
d
ata
ar
e
r
o
u
ted
th
r
o
u
g
h
g
atew
ay
s
,
lo
a
d
b
alan
ce
r
s
,
an
d
d
is
tr
ib
u
te
d
s
to
r
ag
e
s
y
s
tem
s
(
S3
an
d
HDFS)
to
en
s
u
r
e
s
ca
lab
ilit
y
an
d
r
eliab
ilit
y
.
Fig
u
r
e
2
.
Data
f
l
o
w
ar
ch
itectu
r
e
f
o
r
m
ed
ia
an
d
telem
etr
y
in
th
e
co
ld
c
h
ain
f
r
a
m
ewo
r
k
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
4
1
,
No
.
3
,
Ma
r
ch
20
2
6
:
1
0
7
0
-
1
0
8
1
1076
3.
6.
Da
t
a
pro
ce
s
s
ing
wit
h ma
chine le
a
rning
T
h
r
ee
m
ain
alg
o
r
ith
m
s
wer
e
ev
alu
ated
to
a
d
d
r
ess
th
e
d
iv
er
s
e
an
aly
tical
n
ee
d
s
o
f
c
o
ld
ch
ain
m
o
n
ito
r
in
g
.
R
an
d
o
m
f
o
r
est
w
as
ap
p
lied
to
class
if
y
tab
u
lar
t
elem
etr
y
d
ata
an
d
d
etec
t
f
is
h
f
r
esh
n
ess
ca
teg
o
r
ies,
wh
ile
L
STM
wa
s
em
p
lo
y
ed
to
an
aly
ze
tem
p
o
r
al
v
ar
iatio
n
s
in
s
en
s
o
r
r
ea
d
in
g
s
an
d
f
o
r
ec
ast
s
p
o
ilag
e
r
is
k
s
.
I
n
p
ar
allel,
C
NN
was
u
tili
ze
d
f
o
r
v
is
u
al
in
s
p
ec
tio
n
o
f
f
is
h
i
m
ag
es,
en
ab
lin
g
au
to
m
ated
as
s
ess
m
en
t
o
f
q
u
ality
d
eg
r
ad
atio
n
.
Fig
u
r
e
3
p
r
esen
t
s
th
e
d
etailed
d
ata
p
r
o
ce
s
s
in
g
f
lo
w
th
at
u
n
d
er
p
in
s
th
e
co
ld
ch
ain
m
o
n
ito
r
in
g
f
r
am
ewo
r
k
.
I
t
s
h
o
ws
h
o
w
telem
etr
y
an
d
im
ag
e
d
ata
ar
e
in
g
ested
,
p
r
ep
r
o
ce
s
s
ed
,
an
d
tr
an
s
f
o
r
m
ed
th
r
o
u
g
h
v
ar
io
u
s
m
ac
h
in
e
lear
n
in
g
p
i
p
elin
es.
T
h
e
d
iag
r
am
also
h
ig
h
lig
h
ts
th
e
in
teg
r
atio
n
o
f
f
ea
tu
r
e
s
to
r
es,
m
o
d
el
r
eg
is
tr
ies,
an
d
in
f
er
e
n
ce
s
er
v
ices
th
at
co
llectiv
ely
g
en
e
r
ate
an
o
m
aly
d
etec
tio
n
,
s
p
o
il
ag
e
p
r
ed
ictio
n
,
an
d
q
u
ality
s
co
r
in
g
o
u
tp
u
ts
.
Fig
u
r
e
3
.
Data
p
r
o
ce
s
s
in
g
f
lo
w
f
o
r
m
ac
h
i
n
e
lear
n
in
g
-
b
ased
co
ld
ch
ain
m
o
n
ito
r
i
n
g
3
.
7
.
Va
lid
a
t
i
o
n
s
t
ra
t
eg
y
a
nd
pro
t
o
t
y
pe
t
esting
T
o
d
em
o
n
s
tr
ate
th
e
tech
n
ical
f
ea
s
ib
ilit
y
o
f
th
e
p
r
o
p
o
s
ed
m
icr
o
s
er
v
ice
-
o
r
ie
n
ted
m
ac
h
in
e
lear
n
in
g
f
r
am
ewo
r
k
,
a
s
et
of
s
im
u
latio
n
-
b
ased
v
alid
atio
n
s
ce
n
ar
io
s
was
d
esig
n
ed
,
ea
ch
r
ef
lecti
n
g
k
ey
o
p
er
atio
n
al
ch
allen
g
es
in
f
is
h
er
ies
co
ld
ch
ain
m
an
a
g
em
en
t
in
T
a
b
le
5
.
T
h
e
f
ir
s
t
s
ce
n
ar
i
o
f
o
cu
s
es
o
n
te
m
p
er
atu
r
e
an
o
m
aly
d
etec
tio
n
u
s
in
g
r
an
d
o
m
f
o
r
est
,
em
p
lo
y
in
g
m
u
lti
-
d
ay
s
im
u
la
ted
s
en
s
o
r
d
ata
to
d
if
f
er
en
tiat
e
n
o
r
m
al
o
p
e
r
atin
g
p
atter
n
s
f
r
o
m
d
ev
iatio
n
s
th
at
m
ay
in
d
icate
eq
u
ip
m
en
t
m
alf
u
n
ctio
n
o
r
in
cr
ea
s
ed
s
p
o
ilag
e
r
i
s
k
.
T
ab
le
5
.
Valid
atio
n
d
esig
n
f
o
r
th
e
p
r
o
p
o
s
ed
f
r
a
m
ewo
r
k
V
a
l
i
d
a
t
i
o
n
t
y
p
e
D
a
t
a
s
e
t
a
n
d
i
n
p
u
t
d
e
s
c
r
i
p
t
i
o
n
P
r
e
p
r
o
c
e
ss
i
n
g
M
o
d
e
l
c
o
n
f
i
g
u
r
a
t
i
o
n
Ev
a
l
u
a
t
i
o
n
met
r
i
c
s
P
u
r
p
o
se
Te
mp
e
r
a
t
u
r
e
a
n
o
ma
l
y
d
e
t
e
c
t
i
o
n
(
r
a
n
d
o
m
f
o
r
e
st
)
S
i
mu
l
a
t
e
d
t
e
m
p
e
r
a
t
u
r
e
d
a
t
a
se
t
(
1
0
–
1
4
d
a
y
s)
,
5
sen
s
o
r
s,
s
a
m
p
l
i
n
g
1
-
mi
n
u
t
e
i
n
t
e
r
v
a
l
(
≈
7
,
2
0
0
r
e
c
o
r
d
s
p
e
r
s
e
n
so
r
)
N
o
r
mal
i
z
a
t
i
o
n
,
mi
ssi
n
g
-
v
a
l
u
e
h
a
n
d
l
i
n
g
,
l
a
b
e
l
g
e
n
e
r
a
t
i
o
n
f
o
r
“
n
o
r
ma
l
/
a
n
o
ma
l
y
”
R
F
w
i
t
h
2
0
0
t
r
e
e
s,
max
d
e
p
t
h
=
1
0
,
b
o
o
t
st
r
a
p
e
n
a
b
l
e
d
A
c
c
u
r
a
c
y
,
P
r
e
c
i
s
i
o
n
,
R
e
c
a
l
l
,
F1
-
sc
o
r
e
V
a
l
i
d
a
t
e
e
a
r
l
y
a
n
o
m
a
l
y
d
e
t
e
c
t
i
o
n
c
a
p
a
b
i
l
i
t
y
f
o
r
c
o
l
d
st
o
r
a
g
e
S
p
o
i
l
a
g
e
r
i
s
k
p
r
e
d
i
c
t
i
o
n
(
LSTM
)
Ti
me
-
s
e
r
i
e
s
t
e
m
p
e
r
a
t
u
r
e
–
h
u
mi
d
i
t
y
d
a
t
a
,
1
se
q
u
e
n
c
e
p
e
r
h
o
u
r
,
3
0
–
5
0
t
i
m
e
st
e
p
s
M
i
n
–
ma
x
s
c
a
l
i
n
g
,
w
i
n
d
o
w
i
n
g
seq
u
e
n
c
e
(
l
o
o
k
-
b
a
c
k
=
2
4
)
,
t
r
a
i
n
-
t
e
st
sp
l
i
t
8
0
:
2
0
LSTM
w
i
t
h
6
4
u
n
i
t
s
,
d
r
o
p
o
u
t
0
.
2
,
A
d
a
m
o
p
t
i
mi
z
e
r
,
5
0
e
p
o
c
h
s
R
M
S
E
,
M
A
E,
R²
V
a
l
i
d
a
t
e
p
r
e
d
i
c
t
i
o
n
c
a
p
a
b
i
l
i
t
y
f
o
r
s
h
o
r
t
-
t
e
r
m
sp
o
i
l
a
g
e
r
i
s
k
F
i
sh
q
u
a
l
i
t
y
c
l
a
ss
i
f
i
c
a
t
i
o
n
(
C
N
N
)
S
mal
l
d
a
t
a
se
t
(
8
0
–
1
2
0
i
ma
g
e
s)
c
a
t
e
g
o
r
i
z
e
d
a
s
f
r
e
sh
/
s
l
i
g
h
t
l
y
sp
o
i
l
e
d
/
s
p
o
i
l
e
d
R
e
si
z
e
t
o
1
2
8
×
1
2
8
,
a
u
g
me
n
t
a
t
i
o
n
(
f
l
i
p
,
r
o
t
a
t
e
,
b
r
i
g
h
t
n
e
ss)
C
N
N
:
3
c
o
n
v
l
a
y
e
r
s,
R
e
LU
,
max
-
p
o
o
l
i
n
g
,
d
e
n
se
l
a
y
e
r
1
2
8
,
S
o
f
t
M
a
x
o
u
t
p
u
t
A
c
c
u
r
a
c
y
,
c
o
n
f
u
s
i
o
n
mat
r
i
x
,
La
t
e
n
c
y
p
e
r
i
n
f
e
r
e
n
c
e
V
a
l
i
d
a
t
e
f
e
a
s
i
b
i
l
i
t
y
o
f
v
i
s
u
a
l
a
ssessm
e
n
t
u
si
n
g
smal
l
-
sca
l
e
d
a
t
a
s
e
t
Ed
g
e
v
s
c
l
o
u
d
d
e
p
l
o
y
me
n
t
b
e
n
c
h
mar
k
S
a
mp
l
e
i
n
f
e
r
e
n
c
e
w
o
r
k
l
o
a
d
f
r
o
m
R
F
/
LST
M
/
C
N
N
–
Ed
g
e
(
J
e
t
s
o
n
/
R
a
s
p
b
e
r
r
y
)
,
C
l
o
u
d
(
V
M
i
n
st
a
n
c
e
)
La
t
e
n
c
y
,
C
P
U
u
sa
g
e
,
m
e
mo
r
y
u
sa
g
e
,
T
h
r
o
u
g
h
p
u
t
V
a
l
i
d
a
t
e
mi
c
r
o
ser
v
i
c
e
d
e
p
l
o
y
me
n
t
p
e
r
f
o
r
ma
n
c
e
u
n
d
e
r
h
y
b
r
i
d
a
r
c
h
i
t
e
c
t
u
r
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
A
micro
s
ervice
-
o
r
ien
ted
ma
ch
in
e
lea
r
n
in
g
fr
a
mewo
r
k
fo
r
co
ld
ch
a
in
ma
n
a
g
eme
n
t in
…
(
M
a
u
n
Ja
m
a
lu
d
in
)
1077
T
h
is
v
alid
atio
n
ev
alu
ates
t
h
e
m
o
d
el’
s
r
eliab
ilit
y
th
r
o
u
g
h
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
-
s
co
r
e
m
etr
ics.
T
h
e
s
ec
o
n
d
s
ce
n
ar
i
o
u
s
es
L
STM
n
etwo
r
k
s
to
m
o
d
e
l
tem
p
o
r
al
d
e
p
en
d
e
n
cies
in
tem
p
er
atu
r
e
–
h
u
m
i
d
ity
s
eq
u
en
ce
s
,
en
ab
lin
g
s
h
o
r
t
-
te
r
m
s
p
o
ilag
e
r
is
k
p
r
ed
ictio
n
.
Per
f
o
r
m
a
n
ce
is
ass
ess
ed
u
s
in
g
R
MSE
,
MA
E
,
an
d
R
²
to
g
au
g
e
f
o
r
ec
as
tin
g
q
u
ality
.
T
h
e
th
ir
d
s
ce
n
ar
io
a
p
p
lies
a
lig
h
tweig
h
t CNN m
o
d
el
to
class
if
y
f
is
h
q
u
ality
f
r
o
m
a
s
m
all
im
ag
e
d
ataset
r
ep
r
es
en
tin
g
f
r
esh
,
m
o
d
er
ately
s
p
o
iled
,
an
d
s
p
o
iled
ca
teg
o
r
ies,
v
alid
ated
th
r
o
u
g
h
ac
cu
r
ac
y
,
c
o
n
f
u
s
io
n
m
atr
ix
a
n
aly
s
is
,
an
d
in
f
er
en
ce
laten
c
y.
I
n
ad
d
itio
n
,
an
ed
g
e
–
clo
u
d
b
e
n
ch
m
ar
k
i
n
g
test
co
m
p
ar
es
ex
ec
u
tio
n
s
p
ee
d
,
C
PU
u
tili
za
tio
n
,
m
em
o
r
y
co
n
s
u
m
p
tio
n
,
an
d
th
r
o
u
g
h
p
u
t
b
etwe
en
d
is
tr
ib
u
ted
d
ep
lo
y
m
en
t
en
v
ir
o
n
m
en
ts
.
C
o
llectiv
ely
,
th
ese
v
alid
atio
n
s
tep
s
p
r
o
v
id
e
p
r
elim
in
a
r
y
e
m
p
ir
ical
ev
id
en
ce
th
at
th
e
f
r
a
m
e
wo
r
k
ca
n
s
u
p
p
o
r
t
r
ea
l
-
tim
e
m
o
n
ito
r
in
g
,
p
r
ed
ictiv
e
an
aly
tics
,
an
d
d
is
tr
ib
u
ted
in
tellig
en
ce
,
r
ein
f
o
r
ci
n
g
its
s
u
itab
ilit
y
f
o
r
s
ca
lab
le
an
d
m
o
d
u
lar
co
l
d
ch
ain
o
p
er
atio
n
s
.
T
h
ese
p
r
elim
in
ar
y
r
esu
lts
d
em
o
n
s
tr
ate
th
at
t
h
e
p
r
o
p
o
s
ed
f
r
am
ewo
r
k
is
tech
n
ically
f
ea
s
ib
le,
s
ca
lab
le,
an
d
ca
p
ab
le
o
f
p
r
o
v
id
in
g
ac
tio
n
ab
le
in
s
ig
h
ts
f
o
r
r
ea
l
-
tim
e
co
ld
c
h
ain
o
p
e
r
atio
n
s
,
m
ar
k
in
g
a
s
ig
n
if
ican
t a
d
v
an
ce
m
en
t o
v
er
ex
is
tin
g
m
o
n
ito
r
i
n
g
-
o
n
ly
ap
p
r
o
ac
h
es.
3.
8.
Vis
ua
liza
t
io
n a
nd
da
s
hb
o
a
rd
la
y
er
A
m
u
lti
-
to
o
l
v
is
u
aliza
tio
n
s
tr
ateg
y
is
p
r
o
p
o
s
ed
to
en
s
u
r
e
th
at
d
ata
f
r
o
m
v
ar
i
o
u
s
s
o
u
r
c
es
ca
n
b
e
ef
f
ec
tiv
ely
c
o
m
m
u
n
icate
d
to
d
if
f
er
en
t
s
tak
eh
o
ld
er
s
.
E
ac
h
t
o
o
l
p
lay
s
a
co
m
p
lem
e
n
tar
y
r
o
le,
r
an
g
in
g
f
r
o
m
r
ea
l
-
tim
e
m
o
n
ito
r
in
g
d
ash
b
o
ar
d
s
t
o
an
aly
tical
r
ep
o
r
tin
g
a
n
d
in
t
er
ac
tiv
e
g
eo
s
p
atial
m
ap
p
i
n
g
[3
4
]
.
B
y
co
m
b
in
in
g
th
ese
p
latf
o
r
m
s
,
th
e
f
r
am
ewo
r
k
d
eli
v
er
s
b
o
th
o
p
er
atio
n
al
a
war
en
ess
an
d
s
tr
ateg
ic
d
ec
is
io
n
-
m
ak
i
n
g
s
u
p
p
o
r
t
f
o
r
co
l
d
ch
ain
m
an
ag
em
e
n
t
[3
5
]
.
−
Stre
am
lit:
r
ap
id
p
r
o
to
t
y
p
in
g
a
n
d
ML
m
o
d
el
in
teg
r
atio
n
.
−
Gr
af
an
a:
r
ea
l
-
tim
e
m
o
n
ito
r
in
g
o
f
tim
e
-
s
er
ies s
en
s
o
r
d
ata
wit
h
aler
ts
.
−
Po
wer
B
I
: c
o
r
p
o
r
ate
-
le
v
el
r
ep
o
r
tin
g
an
d
KPI
d
ash
b
o
ar
d
s
.
−
R
ea
ct
Dash
b
o
ar
d
: f
u
lly
c
u
s
to
m
ized
o
p
er
atio
n
al
ap
p
s
in
teg
r
atin
g
m
ap
s
an
d
co
n
tr
o
ls
.
−
Me
tab
ase: lig
h
tweig
h
t self
-
s
er
v
ice
an
aly
tics
f
o
r
q
u
ick
in
s
ig
h
ts
.
−
T
h
ese
f
iv
e
to
o
ls
co
llectiv
ely
en
ab
le
m
o
n
ito
r
in
g
f
is
h
q
u
al
ity
,
an
o
m
aly
d
etec
tio
n
,
an
d
p
r
o
v
id
i
n
g
r
o
u
te
r
ec
o
m
m
en
d
atio
n
s
in
a
d
ec
is
io
n
-
s
u
p
p
o
r
t e
n
v
ir
o
n
m
e
n
t.
3.
9.
G
eo
s
pa
t
ia
l
a
na
ly
s
is
Geo
s
p
atial
an
aly
tics
en
r
ich
es
co
ld
ch
ain
m
o
n
ito
r
in
g
b
y
in
te
g
r
atin
g
GPS
d
ata
with
s
en
s
o
r
telem
etr
y
to
p
r
o
v
id
e
a
c
o
m
p
r
e
h
en
s
iv
e
s
p
atial
u
n
d
e
r
s
tan
d
in
g
o
f
d
is
tr
i
b
u
tio
n
d
y
n
am
ics.
T
h
e
p
r
o
ce
s
s
in
v
o
lv
es
m
u
ltip
le
s
tep
s
,
in
clu
d
in
g
d
ata
clea
n
in
g
,
r
o
u
te
s
eg
m
en
tatio
n
,
h
o
ts
p
o
t
d
etec
tio
n
,
an
d
r
is
k
s
u
r
f
ac
e
i
n
ter
p
o
latio
n
,
w
h
ich
to
g
eth
er
e
n
ab
le
p
r
o
ac
tiv
e
id
en
tific
atio
n
o
f
h
i
g
h
-
r
is
k
ar
ea
s
[3
6
]
.
R
ec
en
t
s
tu
d
ies
h
a
v
e
d
em
o
n
s
tr
ated
th
at
g
eo
s
p
atial
AI
tech
n
iq
u
es,
wh
en
ap
p
lied
to
f
o
o
d
an
d
lo
g
is
tics
ch
ain
s
,
s
ig
n
if
ican
tly
im
p
r
o
v
e
b
o
th
o
p
er
atio
n
al
ef
f
icien
cy
an
d
r
is
k
m
itig
atio
n
[3
7
]
,
[
3
8
]
.
T
h
e
o
u
tp
u
t in
clu
d
es
:
−
Hea
tm
ap
s
o
f
r
is
k
y
zo
n
es,
−
R
o
u
te
r
ec
o
m
m
en
d
atio
n
s
m
in
i
m
izin
g
ex
p
o
s
u
r
e,
−
R
ea
l
-
tim
e
aler
ts
v
ia
g
eo
f
en
cin
g
m
ec
h
an
is
m
s
.
−
QGI
S a
n
d
L
ea
f
letJ
S e
n
ab
le
b
o
th
in
-
d
ep
t
h
s
p
atial
an
aly
s
is
an
d
in
ter
ac
tiv
e
web
-
b
ased
m
ap
s
.
3.
10.
I
nte
g
ra
t
io
n
a
cr
o
s
s
blo
ck
s
All
f
u
n
ctio
n
al
b
lo
c
k
s
in
th
e
p
r
o
p
o
s
ed
ar
ch
itectu
r
e
ar
e
in
ter
co
n
n
ec
ted
in
a
s
ea
m
less
wo
r
k
f
lo
w
th
at
in
teg
r
ates
d
ata
ac
q
u
is
itio
n
,
ed
g
e
-
lev
el
p
r
o
ce
s
s
in
g
,
ce
n
tr
alize
d
b
ig
d
ata
in
f
r
astru
ctu
r
e,
m
ac
h
in
e
lear
n
in
g
an
aly
tics
,
v
is
u
aliza
tio
n
d
ash
b
o
ar
d
s
,
an
d
g
eo
s
p
at
ial
an
aly
s
is
.
T
o
g
eth
er
,
th
ese
co
m
p
o
n
e
n
ts
cr
ea
te
an
in
tellig
en
t
co
ld
ch
ain
s
y
s
tem
ca
p
ab
le
o
f
p
r
eser
v
in
g
f
is
h
q
u
ality
,
e
n
ab
lin
g
p
r
e
d
ictiv
e
d
ec
is
io
n
-
m
a
k
i
n
g
,
an
d
s
u
p
p
o
r
tin
g
s
u
s
tain
ab
le
lo
g
is
tics
o
p
er
atio
n
s
[
2
6
]
,
[
39
]
,
I
ts
in
teg
r
atio
n
cy
c
le
ac
r
o
s
s
s
y
s
tem
b
lo
ck
is
p
r
esen
ted
in
F
ig
u
r
e
4
.
Fig
u
r
e
4
.
I
n
teg
r
ated
wo
r
k
f
lo
w
cy
cle
o
f
th
e
p
r
o
p
o
s
ed
c
o
ld
ch
ain
ar
ch
itectu
r
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
4
1
,
No
.
3
,
Ma
r
ch
20
2
6
:
1
0
7
0
-
1
0
8
1
1078
4.
CO
NCLU
SI
O
N
T
h
is
s
tu
d
y
p
r
esen
ts
a
m
icr
o
s
er
v
ice
-
o
r
ien
ted
m
ac
h
in
e
lear
n
in
g
f
r
am
ewo
r
k
d
esig
n
ed
t
o
en
h
a
n
ce
in
tellig
en
ce
,
s
ca
lab
ilit
y
,
an
d
r
ea
l
-
tim
e
r
esp
o
n
s
iv
e
n
ess
in
f
i
s
h
er
ies
co
ld
ch
ain
m
an
a
g
em
e
n
t.
B
y
in
teg
r
atin
g
R
an
d
o
m
Fo
r
est
–
b
ased
an
o
m
a
ly
d
etec
tio
n
,
L
STM
-
b
ased
s
p
o
ilag
e
p
r
e
d
ictio
n
,
a
n
d
C
NN
-
b
ased
v
is
u
al
q
u
alit
y
class
if
icatio
n
in
to
a
h
y
b
r
id
ed
g
e
–
clo
u
d
ar
ch
itectu
r
e,
th
e
p
r
o
p
o
s
ed
f
r
am
ewo
r
k
a
d
d
r
ess
es
cr
i
tical
g
ap
s
id
en
tifie
d
in
p
r
ev
io
u
s
r
esear
ch
,
p
ar
ticu
lar
ly
th
e
ab
s
en
ce
o
f
p
r
ed
ictiv
e
an
aly
tics
,
m
u
ltimo
d
al
m
o
n
ito
r
in
g
,
an
d
m
o
d
u
lar
d
ep
l
o
y
m
en
t
m
ec
h
a
n
is
m
s
.
Simu
latio
n
-
b
ased
v
alid
a
tio
n
d
em
o
n
s
tr
ated
th
at
ea
ch
m
o
d
el
ca
n
o
p
er
ate
ef
f
ec
tiv
ely
with
in
a
d
is
tr
ib
u
te
d
m
icr
o
s
er
v
ice
en
v
i
r
o
n
m
e
n
t,
s
u
p
p
o
r
tin
g
r
ea
l
-
tim
e
in
f
e
r
en
ce
,
ad
ap
tiv
e
d
ec
is
io
n
-
m
ak
in
g
,
an
d
in
ter
o
p
er
ab
ilit
y
ac
r
o
s
s
h
eter
o
g
en
eo
u
s
co
ld
ch
ain
in
f
r
astru
ct
u
r
es.
Fu
r
th
e
r
m
o
r
e,
th
e
co
m
p
a
r
ativ
e
p
er
f
o
r
m
an
ce
an
al
y
s
is
b
etwe
en
ed
g
e
a
n
d
clo
u
d
e
x
ec
u
tio
n
c
o
n
f
ir
m
s
th
at
th
e
f
r
am
ewo
r
k
c
an
b
alan
ce
laten
c
y
,
r
eso
u
r
ce
u
s
ag
e,
an
d
c
o
m
p
u
tatio
n
al
d
em
a
n
d
s
b
ased
o
n
o
p
er
at
io
n
al
r
eq
u
i
r
em
en
ts
.
T
h
ese
f
in
d
in
g
s
co
llectiv
ely
in
d
icate
th
at
th
e
p
r
o
p
o
s
ed
f
r
am
ewo
r
k
o
f
f
e
r
s
a
tech
n
ically
f
ea
s
ib
le
an
d
o
p
er
atio
n
ally
s
ca
lab
le
s
o
lu
tio
n
,
s
tr
en
g
th
en
in
g
c
o
ld
ch
ain
r
eli
ab
ilit
y
,
r
ed
u
cin
g
s
p
o
ilag
e
r
is
k
,
an
d
en
ab
lin
g
d
ata
-
d
r
iv
en
lo
g
is
tics
g
o
v
er
n
a
n
ce
.
T
h
e
r
esear
ch
co
n
tr
ib
u
tes
a
d
ep
lo
y
ab
le
ar
ch
itectu
r
al
b
l
u
e
p
r
in
t
th
at
b
r
id
g
es
co
n
ce
p
tu
al
AI
-
e
n
ab
led
c
o
ld
ch
ain
m
o
d
els
with
p
r
ac
tical
im
p
lem
en
tatio
n
p
at
h
way
s
s
u
itab
le
f
o
r
f
is
h
er
ies
d
is
tr
ib
u
tio
n
in
I
n
d
o
n
esia.
5.
L
I
M
I
T
AT
I
O
NS A
N
D
F
UT
U
RE
WO
RK
Alth
o
u
g
h
th
e
p
r
o
p
o
s
ed
f
r
am
ewo
r
k
s
h
o
ws
s
tr
o
n
g
p
o
ten
tia
l,
th
is
s
tu
d
y
is
lim
ited
b
y
th
e
u
s
e
o
f
s
im
u
lated
d
atasets
an
d
s
m
all
-
s
ca
le
im
ag
e
s
am
p
les,
wh
ich
m
ay
n
o
t
f
u
lly
r
e
p
r
esen
t
r
ea
l
o
p
er
atio
n
al
v
ar
iab
ilit
y
in
f
is
h
er
ies
co
ld
ch
ain
s
.
Mo
d
el
p
er
f
o
r
m
a
n
ce
an
d
d
ep
lo
y
m
en
t
b
e
h
av
io
r
m
ay
d
if
f
e
r
u
n
d
er
f
l
u
ctu
atin
g
f
ield
co
n
d
itio
n
s
,
d
iv
e
r
s
e
s
p
ec
ies
ch
ar
ac
ter
is
tics
,
an
d
h
ar
d
war
e
co
n
s
tr
ain
ts
.
Fu
tu
r
e
wo
r
k
will
in
v
o
lv
e
lar
g
e
-
s
ca
le
f
ield
d
ep
lo
y
m
en
t,
c
o
n
tin
u
o
u
s
d
ata
ac
q
u
is
itio
n
,
an
d
m
o
d
el
r
ef
in
em
en
t
u
s
in
g
r
ea
l
-
wo
r
ld
s
en
s
o
r
an
d
v
is
u
al
d
atasets
.
Fu
r
th
er
r
esear
ch
will
ex
p
lo
r
e
lig
h
tweig
h
t
ar
ch
itectu
r
es
f
o
r
ed
g
e
in
f
er
e
n
c
e,
in
teg
r
atio
n
with
co
o
p
er
ativ
e
an
d
g
o
v
er
n
m
en
t
al
p
latf
o
r
m
s
th
r
o
u
g
h
s
tan
d
ar
d
ized
API
s
,
a
n
d
ev
alu
atio
n
u
n
d
er
m
u
lti
-
n
o
d
e,
n
etwo
r
k
-
v
a
r
iab
le
en
v
ir
o
n
m
en
t
s
to
ass
es
s
s
ca
lab
ilit
y
,
r
esil
ien
ce
,
an
d
lo
n
g
-
ter
m
o
p
e
r
atio
n
al
im
p
ac
t.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
T
h
is
r
es
ea
r
ch
was
s
u
p
p
o
r
ted
b
y
Un
iv
er
s
itas
Pas
u
n
d
an
an
d
th
e
Dir
ec
to
r
ate
o
f
R
esear
ch
,
T
ec
h
n
o
lo
g
y
,
an
d
C
o
m
m
u
n
ity
Ser
v
ice
(
D
R
T
PM)
,
Min
is
tr
y
o
f
E
d
u
ca
tio
n
,
C
u
ltu
r
e,
R
esear
ch
,
an
d
T
ec
h
n
o
lo
g
y
o
f
th
e
R
ep
u
b
lic
o
f
I
n
d
o
n
esia.
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
Auth
o
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
M
a
u
n
Ja
m
a
lu
d
i
n
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Arie
f
G
in
a
n
jar
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Len
i
He
rd
ian
i
✓
✓
✓
✓
✓
✓
✓
✓
✓
To
to
Ra
m
a
d
h
a
n
✓
✓
✓
M
u
h
a
m
m
a
d
Alif
Na
u
fa
l
✓
✓
✓
✓
✓
Ism
e
t
Ro
h
ima
t
✓
✓
✓
✓
✓
C
:
C
o
n
ce
p
tu
aliza
tio
n
M
:
Me
th
o
d
o
lo
g
y
So
:
So
f
twar
e
Va
:
Valid
atio
n
Fo
:
Fo
r
m
al
an
aly
s
is
I
:
I
n
v
esti
g
atio
n
R
:
R
eso
u
r
ce
s
D
:
Data
C
u
r
atio
n
O
:
W
r
itin
g
-
Or
ig
in
al
Dr
af
t
E
:
W
r
itin
g
-
R
ev
iew
&
E
d
itin
g
Vi
:
Vis
u
aliza
tio
n
Su
:
Su
p
er
v
is
io
n
P
:
Pro
ject
ad
m
in
is
tr
atio
n
Fu
:
Fu
n
d
in
g
ac
q
u
is
itio
n
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
T
h
e
au
th
o
r
s
d
ec
lar
e
n
o
co
n
f
lict o
f
in
ter
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:
2
5
0
2
-
4
7
52
A
micro
s
ervice
-
o
r
ien
ted
ma
ch
in
e
lea
r
n
in
g
fr
a
mewo
r
k
fo
r
co
ld
ch
a
in
ma
n
a
g
eme
n
t in
…
(
M
a
u
n
Ja
m
a
lu
d
in
)
1079
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
au
th
o
r
s
co
n
f
ir
m
th
at
th
e
d
ata
s
u
p
p
o
r
tin
g
th
e
f
in
d
in
g
s
o
f
th
is
s
tu
d
y
ar
e
a
v
ailab
le
with
in
th
e
ar
ticle
an
d
its
s
u
p
p
lem
e
n
tar
y
m
ater
ials
.
Ad
d
itio
n
al
d
atasets
g
en
e
r
ated
d
u
r
i
n
g
t
h
e
c
u
r
r
e
n
t
s
tu
d
y
will
b
e
m
a
d
e
av
ailab
le
u
p
o
n
r
ea
s
o
n
a
b
le
r
eq
u
est
.
RE
F
E
R
E
NC
E
S
[
1
]
L.
H
e
r
d
i
a
n
i
,
M
.
Jam
a
l
u
d
i
n
,
I
.
S
u
d
i
r
man
,
W
i
d
j
a
j
a
n
i
,
a
n
d
I
.
R
o
h
i
m
a
t
,
“
A
sy
st
e
m
d
y
n
a
m
i
c
s
mo
d
e
l
o
f
f
r
o
z
e
n
f
i
sh
s
u
p
p
l
y
c
h
a
i
n
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
A
d
v
a
n
c
e
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
6
,
n
o
.
1
,
p
p
.
8
6
2
–
8
7
3
,
2
0
2
5
,
d
o
i
:
1
0
.
1
4
5
6
9
/
I
JA
C
S
A
.
2
0
2
5
.
0
1
6
0
1
8
3
.
[
2
]
L.
H
e
r
d
i
a
n
i
,
M
.
Jam
a
l
u
d
i
n
,
I
.
R
o
h
i
ma
t
,
a
n
d
F
.
W
i
d
y
a
n
a
P
u
t
r
i
,
“
M
a
p
p
i
n
g
o
f
t
h
e
f
r
o
z
e
n
f
i
s
h
s
u
p
p
l
y
c
h
a
i
n
sy
st
e
m
a
t
TPI
K
a
r
a
n
g
s
o
n
g
,
I
n
d
r
a
m
a
y
u
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
T
re
n
d
i
n
Re
s
e
a
r
c
h
a
n
d
D
e
v
e
l
o
p
m
e
n
t
,
v
o
l
.
1
1
,
n
o
.
4
,
p
p
.
2
3
9
4
–
9
3
3
3
,
2
0
2
4
,
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
w
w
w
.
i
j
t
r
d
.
c
o
m
[
3
]
A
.
G
i
n
a
n
j
a
r
a
n
d
K
.
K
u
sm
a
y
a
,
“
R
e
l
i
a
b
i
l
i
t
y
c
o
m
p
a
r
i
so
n
o
f
h
i
g
h
p
e
r
f
o
r
ma
n
c
e
c
o
mp
u
t
i
n
g
b
e
t
w
e
e
n
si
n
g
l
e
t
h
r
e
a
d
l
o
o
p
a
n
d
mu
l
t
i
p
l
e
t
h
r
e
a
d
l
o
o
p
u
s
i
n
g
j
a
v
a
-
b
a
s
e
d
p
r
o
g
r
a
mm
i
n
g
a
t
f
i
n
g
e
r
p
r
i
n
t
d
a
t
a
p
r
o
c
e
ssi
n
g
,
”
J
u
r
n
a
l
S
i
s
f
o
t
e
k
G
l
o
b
a
l
,
v
o
l
.
1
2
,
n
o
.
1
,
p
.
1
1
,
M
a
r
.
2
0
2
2
,
d
o
i
:
1
0
.
3
8
1
0
1
/
s
i
sf
o
t
e
k
.
v
1
2
i
1
.
4
4
9
.
[
4
]
M
.
H
e
n
d
a
y
u
n
,
A
.
G
i
n
a
n
j
a
r
,
a
n
d
Y
.
I
h
san
,
“
A
n
a
l
y
s
i
s
o
f
a
p
p
l
i
c
a
t
i
o
n
p
e
r
f
o
r
ma
n
c
e
t
e
s
t
i
n
g
u
si
n
g
l
o
a
d
t
e
st
i
n
g
a
n
d
s
t
r
e
ss
t
e
s
t
i
n
g
met
h
o
d
s
i
n
a
p
i
ser
v
i
c
e
,
”
J
u
r
n
a
l
S
i
sf
o
t
e
k
G
l
o
b
a
l
,
v
o
l
.
1
3
,
n
o
.
1
,
p
.
2
8
,
M
a
r
.
2
0
2
3
,
d
o
i
:
1
0
.
3
8
1
0
1
/
s
i
sf
o
t
e
k
.
v
1
3
i
1
.
2
6
5
6
.
[
5
]
A
.
Y
.
C
i
l
,
D
.
A
b
d
u
r
a
h
ma
n
,
a
n
d
I
.
C
i
l
,
“
I
n
t
e
r
n
e
t
o
f
t
h
i
n
g
s
e
n
a
b
l
e
d
r
e
a
l
t
i
m
e
c
o
l
d
c
h
a
i
n
m
o
n
i
t
o
r
i
n
g
i
n
a
c
o
n
t
a
i
n
e
r
p
o
r
t
,
”
J
o
u
r
n
a
l
o
f
S
h
i
p
p
i
n
g
a
n
d
T
ra
d
e
,
v
o
l
.
7
,
n
o
.
1
,
p
.
9
,
D
e
c
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
8
6
/
s4
1
0
7
2
-
0
2
2
-
0
0
1
1
0
-
z.
[
6
]
T.
W
a
n
g
,
H
.
C
h
e
n
,
R
.
D
a
i
,
a
n
d
D
.
Z
h
u
,
“
I
n
t
e
l
l
i
g
e
n
t
l
o
g
i
st
i
c
s
s
y
st
e
m
d
e
si
g
n
a
n
d
su
p
p
l
y
c
h
a
i
n
m
a
n
a
g
e
me
n
t
u
n
d
e
r
e
d
g
e
c
o
m
p
u
t
i
n
g
a
n
d
i
n
t
e
r
n
e
t
o
f
t
h
i
n
g
s
,
”
C
o
m
p
u
t
a
t
i
o
n
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
N
e
u
r
o
s
c
i
e
n
c
e
,
v
o
l
.
2
0
2
2
,
p
p
.
1
–
1
2
,
S
e
p
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
2
/
1
8
2
3
7
6
2
.
[
7
]
L.
B
a
i
,
M
.
Li
u
,
a
n
d
Y
.
S
u
n
,
“
O
v
e
r
v
i
e
w
o
f
f
o
o
d
p
r
e
ser
v
a
t
i
o
n
a
n
d
t
r
a
c
e
a
b
i
l
i
t
y
t
e
c
h
n
o
l
o
g
y
i
n
t
h
e
smar
t
c
o
l
d
c
h
a
i
n
s
y
st
e
m,”
Fo
o
d
s
,
v
o
l
.
1
2
,
n
o
.
1
5
,
p
.
2
8
8
1
,
J
u
l
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
f
o
o
d
s
1
2
1
5
2
8
8
1
.
[
8
]
H
.
R
o
m
a
d
h
o
n
a
a
n
d
Zu
l
f
a
i
r
a
h
,
“
T
h
e
i
mp
a
c
t
o
f
t
h
e
i
n
t
e
r
n
e
t
o
f
t
h
i
n
g
s
(
I
o
T)
a
n
d
b
i
g
d
a
t
a
o
n
t
h
e
a
c
c
u
r
a
c
y
o
f
e
x
p
e
d
i
t
i
o
n
sh
i
p
me
n
t
t
r
a
c
k
i
n
g
(
i
n
I
n
d
o
n
e
s
i
a
n
)
,
”
J
u
r
n
a
l
G
re
e
n
a
t
i
o
n
I
l
m
u
T
e
k
n
i
k
,
v
o
l
.
2
,
n
o
.
2
,
p
p
.
7
5
–
8
4
,
J
u
l
.
2
0
2
4
,
d
o
i
:
1
0
.
3
8
0
3
5
/
j
g
i
t
.
v
2
i
2
.
2
6
4
.
[
9
]
G
.
B
a
r
y
a
n
n
i
s,
S
.
V
a
l
i
d
i
,
S
.
D
a
n
i
,
a
n
d
G
.
A
n
t
o
n
i
o
u
,
“
S
u
p
p
l
y
c
h
a
i
n
r
i
s
k
ma
n
a
g
e
me
n
t
a
n
d
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
:
st
a
t
e
o
f
t
h
e
a
r
t
a
n
d
f
u
t
u
r
e
r
e
s
e
a
r
c
h
d
i
r
e
c
t
i
o
n
s,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
Pro
d
u
c
t
i
o
n
Re
s
e
a
rc
h
,
v
o
l
.
5
7
,
n
o
.
7
,
p
p
.
2
1
7
9
–
2
2
0
2
,
A
p
r
.
2
0
1
9
,
d
o
i
:
1
0
.
1
0
8
0
/
0
0
2
0
7
5
4
3
.
2
0
1
8
.
1
5
3
0
4
7
6
.
[
1
0
]
P
.
M
a
n
i
r
i
h
o
,
E
.
N
i
y
i
g
a
b
a
,
Z
.
B
i
z
i
ma
n
a
,
V
.
Tw
i
r
i
n
g
i
y
i
m
a
n
a
,
L.
J
.
M
a
h
o
r
o
,
a
n
d
T.
A
h
m
a
d
,
“
A
n
o
ma
l
y
-
b
a
s
e
d
i
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
a
p
p
r
o
a
c
h
f
o
r
I
o
T
n
e
t
w
o
r
k
s
u
si
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
i
n
C
E
N
I
M
2
0
2
0
-
Pro
c
e
e
d
i
n
g
:
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
C
o
m
p
u
t
e
r
En
g
i
n
e
e
ri
n
g
,
N
e
t
w
o
rk,
a
n
d
I
n
t
e
l
l
i
g
e
n
t
Mu
l
t
i
m
e
d
i
a
2
0
2
0
,
I
EEE,
N
o
v
.
2
0
2
0
,
p
p
.
3
0
3
–
3
0
8
.
d
o
i
:
1
0
.
1
1
0
9
/
C
EN
I
M
5
1
1
3
0
.
2
0
2
0
.
9
2
9
7
9
5
8
.
[
1
1
]
S
.
H
o
c
h
r
e
i
t
e
r
a
n
d
J
.
S
c
h
m
i
d
h
u
b
e
r
,
“
Lo
n
g
sh
o
r
t
-
t
e
r
m
m
e
m
o
r
y
,
”
N
e
u
r
a
l
C
o
m
p
u
t
a
t
i
o
n
,
v
o
l
.
9
,
n
o
.
8
,
p
p
.
1
7
3
5
–
1
7
8
0
,
N
o
v
.
1
9
9
7
,
d
o
i
:
1
0
.
1
1
6
2
/
n
e
c
o
.
1
9
9
7
.
9
.
8
.
1
7
3
5
.
[
1
2
]
M
.
F
.
H
a
n
i
f
a
e
t
a
l
.
,
“
F
i
s
h
k
u
a
p
p
s:
f
i
sh
e
s
f
r
e
s
h
n
e
ss
d
e
t
e
c
t
i
o
n
u
si
n
g
C
N
N
w
i
t
h
M
o
b
i
l
e
n
e
t
V
2
,
”
I
J
C
C
S
(
I
n
d
o
n
e
s
i
a
n
J
o
u
r
n
a
l
o
f
C
o
m
p
u
t
i
n
g
a
n
d
C
y
b
e
r
n
e
t
i
c
s
S
y
s
t
e
m
s)
,
v
o
l
.
1
7
,
n
o
.
1
,
p
.
6
7
,
F
e
b
.
2
0
2
3
,
d
o
i
:
1
0
.
2
2
1
4
6
/
i
j
c
c
s.
8
0
0
4
9
.
[
1
3
]
L.
H
e
r
d
i
a
n
i
,
N
.
S
u
mar
n
i
,
E
.
S
u
h
e
r
ma
n
,
a
n
d
S
.
S
u
r
o
s
o
,
“
A
n
a
l
y
si
s
o
f
k
i
n
g
c
o
b
i
a
f
i
sh
c
o
mm
o
d
i
t
y
v
a
l
u
e
c
h
a
i
n
a
s
a
n
e
f
f
o
r
t
t
o
i
n
c
r
e
a
s
e
t
h
e
v
a
l
u
e
o
f
f
r
o
z
e
n
f
i
s
h
p
r
o
d
u
c
t
s
,
”
Al
m
a
n
a
:
J
u
r
n
a
l
M
a
n
a
j
e
m
e
n
d
a
n
Bi
sn
i
s
,
v
o
l
.
7
,
n
o
.
1
,
p
p
.
9
4
–
1
0
5
,
A
p
r
.
2
0
2
3
,
d
o
i
:
1
0
.
3
6
5
5
5
/
a
l
m
a
n
a
.
v
7
i
1
.
2
1
1
3
.
[
1
4
]
I
n
d
o
n
e
si
a
n
M
i
n
i
s
t
r
y
o
f
M
a
r
i
n
e
A
f
f
a
i
r
s a
n
d
F
i
s
h
e
r
i
e
s,
“
F
i
s
h
e
r
i
e
s S
t
a
t
i
s
t
i
c
s
o
f
I
n
d
o
n
e
s
i
a
,
”
M
MA
F
.
2
0
2
3
.
[
1
5
]
T.
N
.
Ts
i
r
o
n
i
,
N
.
G
.
S
t
o
f
o
r
o
s,
a
n
d
P
.
S
.
Ta
o
u
k
i
s,
“
Q
u
a
l
i
t
y
a
n
d
s
h
e
l
f
-
l
i
f
e
mo
d
e
l
i
n
g
o
f
f
r
o
z
e
n
f
i
s
h
a
t
c
o
n
s
t
a
n
t
a
n
d
v
a
r
i
a
b
l
e
t
e
m
p
e
r
a
t
u
r
e
c
o
n
d
i
t
i
o
n
s
,
”
Fo
o
d
s
,
v
o
l
.
9
,
n
o
.
1
2
,
p
.
1
8
9
3
,
D
e
c
.
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
f
o
o
d
s
9
1
2
1
8
9
3
.
[
1
6
]
T.
S
,
S
.
A
ma
l
a
n
a
t
h
a
n
,
V
.
S
,
a
n
d
B
.
V
e
n
k
a
t
e
s
u
,
“
E
n
g
i
n
e
e
r
i
n
g
su
st
a
i
n
a
b
l
e
su
p
p
l
y
c
h
a
i
n
o
p
t
i
m
i
z
a
t
i
o
n
i
n
r
e
s
o
u
r
c
e
-
c
o
n
st
r
a
i
n
e
d
e
n
v
i
r
o
n
m
e
n
t
s
:
a
g
e
o
-
sp
a
t
i
a
l
a
n
d
a
i
-
b
a
s
e
d
d
a
t
a
s
c
i
e
n
c
e
p
e
r
s
p
e
c
t
i
v
e
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
E
n
v
i
ro
n
m
e
n
t
a
l
S
c
i
e
n
c
e
s
,
p
p
.
6
9
2
–
7
0
1
,
J
u
l
.
2
0
2
5
,
d
o
i
:
1
0
.
6
4
2
5
2
/
r
v
k
5
y
x
1
2
.
[
1
7
]
B
.
S
.
T
h
o
m
p
so
n
a
n
d
S
.
R
u
st
,
“
S
u
s
t
a
i
n
a
b
l
e
d
e
v
e
l
o
p
m
e
n
t
o
f
s
e
a
f
o
o
d
s
u
p
p
l
y
c
h
a
i
n
s
v
i
a
b
l
o
c
k
c
h
a
i
n
t
e
c
h
n
o
l
o
g
y
:
i
n
n
o
v
a
t
i
o
n
a
d
o
p
t
i
o
n
a
n
d
i
m
p
l
e
me
n
t
a
t
i
o
n
b
y
b
u
si
n
e
ss
e
s
a
n
d
e
n
t
r
e
p
r
e
n
e
u
r
s,”
S
u
s
t
a
i
n
a
b
l
e
D
e
v
e
l
o
p
m
e
n
t
,
v
o
l
.
3
3
,
n
o
.
4
,
p
p
.
5
6
6
1
–
5
6
7
5
,
A
u
g
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
0
2
/
s
d
.
3
4
2
4
.
[
1
8
]
U
N
ESCA
P
,
“
S
t
r
e
n
g
t
h
e
n
i
n
g
r
e
g
i
o
n
a
l
c
o
l
d
c
h
a
i
n
a
n
d
l
o
g
i
s
t
i
c
s s
y
st
e
ms.
”
U
n
i
t
e
d
N
a
t
i
o
n
s,
2
0
2
1
.
[
1
9
]
F
A
O
a
n
d
O
E
C
D
,
“
F
i
s
h
e
r
i
e
s
a
n
d
A
q
u
a
c
u
l
t
u
r
e
G
o
v
e
r
n
a
n
c
e
a
n
d
P
o
l
i
c
y
R
e
v
i
e
w
.
”
F
A
O
,
2
0
2
2
.
[
2
0
]
L.
H
e
r
d
i
a
n
i
,
M
.
Ja
ma
l
u
d
i
n
,
M
.
A
.
R
i
z
k
i
n
i
t
a
,
I
.
S
u
d
i
r
ma
n
,
a
n
d
I
.
R
o
h
i
mat
,
“
Th
e
v
a
l
u
e
c
h
a
i
n
a
n
a
l
y
si
s o
f
c
o
f
f
e
e
p
r
o
d
u
c
t
s i
n
t
h
e
c
a
s
e
o
f
B
a
n
d
u
n
g
D
i
s
t
r
i
c
t
,
”
Al
m
a
n
a
:
J
u
r
n
a
l
M
a
n
a
j
e
m
e
n
d
a
n
Bi
s
n
i
s
,
v
o
l
.
8
,
n
o
.
2
,
p
p
.
3
0
6
–
3
1
7
,
A
u
g
.
2
0
2
4
,
d
o
i
:
1
0
.
3
6
5
5
5
/
a
l
m
a
n
a
.
v
8
i
2
.
2
5
6
6
.
[
2
1
]
J.
W
.
H
a
n
,
M
.
Z
u
o
,
W
.
Y
.
Z
h
u
,
J.
H
.
Zu
o
,
E.
L.
Lü
,
a
n
d
X
.
T.
Y
a
n
g
,
“
A
c
o
m
p
r
e
h
e
n
si
v
e
r
e
v
i
e
w
o
f
c
o
l
d
c
h
a
i
n
l
o
g
i
st
i
c
s
f
o
r
f
r
e
s
h
a
g
r
i
c
u
l
t
u
r
a
l
p
r
o
d
u
c
t
s
:
C
u
r
r
e
n
t
st
a
t
u
s,
c
h
a
l
l
e
n
g
e
s
,
a
n
d
f
u
t
u
r
e
t
r
e
n
d
s,
”
T
ren
d
s
i
n
Fo
o
d
S
c
i
e
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
1
0
9
,
p
p
.
5
3
6
–
5
5
1
,
M
a
r
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
t
i
f
s.
2
0
2
1
.
0
1
.
0
6
6
.
[
2
2
]
T.
Ta
l
e
b
,
K
.
S
a
m
d
a
n
i
s,
B
.
M
a
d
a
,
H
.
F
l
i
n
c
k
,
S
.
D
u
t
t
a
,
a
n
d
D
.
S
a
b
e
l
l
a
,
“
O
n
mu
l
t
i
-
a
c
c
e
ss
e
d
g
e
c
o
mp
u
t
i
n
g
:
a
s
u
r
v
e
y
o
f
t
h
e
e
mer
g
i
n
g
5
G
n
e
t
w
o
r
k
e
d
g
e
c
l
o
u
d
a
r
c
h
i
t
e
c
t
u
r
e
a
n
d
o
r
c
h
e
st
r
a
t
i
o
n
,
”
I
EEE
C
o
m
m
u
n
i
c
a
t
i
o
n
s
S
u
rv
e
y
s
a
n
d
T
u
t
o
r
i
a
l
s
,
v
o
l
.
1
9
,
n
o
.
3
,
p
p
.
1
6
5
7
–
1
6
8
1
,
2
0
1
7
,
d
o
i
:
1
0
.
1
1
0
9
/
C
O
M
S
T
.
2
0
1
7
.
2
7
0
5
7
2
0
.
[
2
3
]
J.
C
h
e
n
a
n
d
J
.
W
u
,
“
P
e
r
f
o
r
m
a
n
c
e
e
v
a
l
u
a
t
i
o
n
a
n
d
o
p
t
i
mi
z
a
t
i
o
n
f
o
r
m
i
c
r
o
s
e
r
v
i
c
e
a
r
c
h
i
t
e
c
t
u
r
e
:
m
e
t
r
i
c
s
a
n
d
m
e
t
h
o
d
s
,
”
J
o
u
rn
a
l
o
f
S
y
s
t
e
m
s
a
n
d
S
o
f
t
w
a
r
e
,
v
o
l
.
1
4
6
,
p
p
.
1
1
1
–
1
2
4
,
2
0
1
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
ss.
2
0
1
8
.
0
8
.
0
4
4
.
[
2
4
]
H
.
G
u
p
t
a
,
A
.
V
.
D
a
s
t
j
e
r
d
i
,
S
.
K
.
G
h
o
sh
,
a
n
d
R
.
B
u
y
y
a
,
“
i
F
o
g
S
i
m
:
a
t
o
o
l
k
i
t
f
o
r
mo
d
e
l
i
n
g
a
n
d
si
mu
l
a
t
i
o
n
o
f
r
e
s
o
u
r
c
e
ma
n
a
g
e
m
e
n
t
t
e
c
h
n
i
q
u
e
s
i
n
t
h
e
I
n
t
e
r
n
e
t
o
f
T
h
i
n
g
s
,
Ed
g
e
a
n
d
F
o
g
c
o
m
p
u
t
i
n
g
e
n
v
i
r
o
n
me
n
t
s,”
S
o
f
t
w
a
r
e
-
Pr
a
c
t
i
c
e
a
n
d
E
x
p
e
ri
e
n
c
e
,
v
o
l
.
4
7
,
n
o
.
9
,
p
p
.
1
2
7
5
–
1
2
9
6
,
S
e
p
.
2
0
1
7
,
d
o
i
:
1
0
.
1
0
0
2
/
s
p
e
.
2
5
0
9
.
[
2
5
]
W
.
S
h
i
,
J
.
C
a
o
,
Q
.
Zh
a
n
g
,
Y
.
L
i
,
a
n
d
L.
X
u
,
“
Ed
g
e
c
o
m
p
u
t
i
n
g
:
v
i
s
i
o
n
a
n
d
c
h
a
l
l
e
n
g
e
s
,
”
I
EE
E
I
n
t
e
rn
e
t
o
f
T
h
i
n
g
s
J
o
u
rn
a
l
,
v
o
l
.
3
,
n
o
.
5
,
p
p
.
6
3
7
–
6
4
6
,
O
c
t
.
2
0
1
6
,
d
o
i
:
1
0
.
1
1
0
9
/
JI
O
T.
2
0
1
6
.
2
5
7
9
1
9
8
.
[
2
6
]
J.
H
a
b
a
z
i
n
,
I
.
B
a
j
o
r
,
P
.
B
a
j
e
c
,
a
n
d
T
.
R
o
ž
i
ć
,
“
A
r
e
v
i
e
w
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
p
p
l
i
c
a
t
i
o
n
s
i
n
c
o
l
d
c
h
a
i
n
a
n
d
r
e
v
e
r
s
e
l
o
g
i
s
t
i
c
s,
”
Pro
m
e
t
-
T
r
a
f
f
i
c
a
n
d
T
r
a
n
sp
o
r
t
a
t
i
o
n
,
v
o
l
.
3
7
,
n
o
.
6
,
p
p
.
1
4
0
9
–
1
4
4
0
,
O
c
t
.
2
0
2
5
,
d
o
i
:
1
0
.
7
3
0
7
/
p
t
t
.
v
3
7
i
6
.
1
3
3
2
.
[
2
7
]
J.
R
u
i
z
-
G
a
r
c
i
a
a
n
d
L
.
L
u
n
a
d
e
i
,
“
M
o
n
i
t
o
r
i
n
g
c
o
l
d
c
h
a
i
n
l
o
g
i
s
t
i
c
s
b
y
m
e
a
n
s
o
f
R
F
I
D
a
n
d
w
i
r
e
l
e
ss
s
e
n
s
o
r
n
e
t
w
o
r
k
s,
”
T
r
e
n
d
s
i
n
Fo
o
d
S
c
i
e
n
c
e
& Te
c
h
n
o
l
o
g
y
,
v
o
l
.
2
1
,
n
o
.
9
,
p
p
.
4
2
5
–
4
3
3
,
2
0
1
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
t
i
f
s.
2
0
1
0
.
0
7
.
0
0
8
.
Evaluation Warning : The document was created with Spire.PDF for Python.