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.
37
,
No
.
2
,
Feb
r
u
ar
y
20
2
5
,
p
p
.
1
37
6
~1
38
6
I
SS
N:
2
502
-
4
7
52
,
DOI
:
1
0
.
1
1
5
9
1
/ijee
cs
.v
3
7
.
i
2
.
p
p
1
37
6
-
1
38
6
1376
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs
.
ia
esco
r
e.
co
m
M
a
chine
lea
rning
bas
ed predi
ction
o
f
pro
duction
usi
ng
real
time data
of
a po
i
nt
bo
t
tom
sea
ling
a
nd cut
t
ing
ma
ch
ine
F
a
t
him
a
Ra
ni I
ruda
y
a
M
a
ry
Dia
na
1
,
Subha
R
a
j
endra
n
2
,
Selv
a
da
s
s
M
uthus
a
m
y
3
1
S
c
h
o
o
l
o
f
C
o
m
me
r
ce
a
n
d
M
a
n
a
g
e
m
e
n
t
,
G
a
r
d
e
n
C
i
t
y
U
n
i
v
e
r
s
i
t
y
,
B
e
n
g
a
l
u
r
u
,
I
n
d
i
a
2
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
i
c
a
l
a
n
d
El
e
c
t
r
o
n
i
c
s E
n
g
i
n
e
e
r
i
n
g
,
M
S
R
a
m
a
i
a
h
I
n
st
i
t
u
t
e
o
f
Te
c
h
n
o
l
o
g
y
,
B
e
n
g
a
l
u
r
u
,
I
n
d
i
a
3
S
c
h
o
o
l
o
f
P
r
o
f
e
ssi
o
n
a
l
S
t
u
d
i
e
s
,
G
a
r
d
e
n
C
i
t
y
U
n
i
v
e
r
si
t
y
,
B
e
n
g
a
l
u
r
u
,
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
J
an
2
,
2
0
2
4
R
ev
is
ed
Sep
25
,
2
0
2
4
Acc
ep
ted
Sep
30
,
2
0
2
4
T
h
e
p
a
c
k
a
g
in
g
se
c
to
r
u
ti
li
z
e
s
p
o
ly
p
ro
p
y
le
n
e
b
a
se
d
fle
x
ib
le
m
a
teria
ls
fo
r
d
iv
e
rse
p
ro
d
u
c
t
p
a
c
k
a
g
i
n
g
wit
h
c
u
sto
m
iza
ti
o
n
o
p
ti
o
n
s
in
siz
e
a
n
d
d
e
sig
n
a
c
h
iev
e
d
th
r
o
u
g
h
a
d
v
a
n
c
e
d
flex
o
g
ra
p
h
ic
p
ri
n
ti
n
g
a
n
d
p
o
i
n
t
b
o
t
to
m
se
a
li
n
g
a
n
d
c
u
t
ti
n
g
m
a
c
h
in
e
s.
Ac
c
u
ra
tely
e
stim
a
ti
n
g
p
ro
d
u
c
ti
o
n
ti
m
e
a
n
d
q
u
a
n
t
it
y
is
v
it
a
l
fo
r
e
fficie
n
t
p
lan
n
in
g
a
n
d
c
o
st
e
stim
a
ti
o
n
,
wi
th
fa
c
to
rs
li
k
e
m
a
teria
l
d
ime
n
sio
n
s
,
th
ick
n
e
ss
,
a
n
d
c
u
t
ti
n
g
m
a
c
h
in
e
s
p
e
e
d
in
f
lu
e
n
c
i
n
g
p
ro
d
u
c
ti
o
n
o
u
t
p
u
t
.
Un
d
e
rsta
n
d
i
n
g
th
e
i
n
tri
c
a
te
re
latio
n
sh
i
p
b
e
twe
e
n
th
e
se
p
a
r
a
m
e
ters
is
e
ss
e
n
ti
a
l
fo
r
c
o
m
p
re
h
e
n
d
in
g
t
h
e
i
r
i
m
p
a
c
t
o
n
p
ro
d
u
c
ti
o
n
ti
m
e
a
n
d
q
u
a
n
ti
t
y
.
P
re
d
ictin
g
p
ro
d
u
c
ti
o
n
q
u
a
n
ti
t
y
b
e
f
o
re
p
r
o
d
u
c
ti
o
n
b
e
g
in
s
h
e
lp
s
i
n
d
e
term
in
in
g
m
a
c
h
in
e
ru
n
ti
m
e
a
n
d
a
ss
o
c
iate
d
c
o
sts.
In
larg
e
-
sc
a
le
p
ro
d
u
c
ti
o
n
sy
ste
m
s,
m
a
c
h
in
e
l
e
a
rn
in
g
(
M
L)
h
a
s
p
ro
v
e
n
t
o
b
e
a
u
se
fu
l
t
o
o
l
f
o
r
re
so
u
rc
e
a
ll
o
c
a
ti
o
n
a
n
d
p
re
d
ictiv
e
sc
h
e
d
u
li
n
g
.
An
a
tt
e
m
p
t
h
a
s b
e
e
n
m
a
d
e
i
n
th
is p
a
p
e
r
to
d
e
v
e
lo
p
a
n
in
tell
ig
e
n
t
m
o
d
e
l
f
o
r
p
re
d
icti
n
g
t
h
e
y
ield
o
f
a
c
u
tt
i
n
g
m
a
c
h
in
e
u
sin
g
a
rti
ficia
l
n
e
u
ra
l
n
e
two
r
k
(AN
N),
su
p
p
o
rt
v
e
c
to
r
re
g
re
ss
io
n
(
S
VR),
re
g
re
ss
io
n
tree
e
n
se
m
b
le
(RTE
)
a
n
d
g
a
u
ss
ian
p
ro
c
e
ss
re
g
re
ss
io
n
(
G
P
R).
Th
e
m
o
st
c
ru
c
ial
fe
a
tu
re
s
fo
r
p
re
d
icti
o
n
we
re
id
e
n
ti
fied
a
n
d
th
e
h
y
p
e
r
p
a
ra
m
e
ters
o
f
th
e
M
L
m
o
d
e
ls
we
re
o
p
ti
m
ize
d
to
c
re
a
te
e
fficie
n
t
m
o
d
e
ls
f
o
r
p
re
d
ictio
n
.
A
c
o
m
p
a
ra
ti
v
e
a
n
a
l
y
sis
o
f
t
h
e
fo
u
r
m
o
d
e
ls
re
v
e
a
led
th
a
t
th
e
G
P
R
m
o
d
e
l
wa
s
sim
p
le an
d
e
ffe
c
ti
v
e
wit
h
lea
st t
ra
in
in
g
ti
m
e
a
n
d
p
re
d
ictio
n
e
rro
r
.
K
ey
w
o
r
d
s
:
C
u
ttin
g
m
ac
h
in
e
Ma
ch
in
e
lear
n
in
g
Neu
r
al
n
etwo
r
k
Po
ly
m
er
f
ilm
R
eg
r
ess
io
n
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
:
Su
b
h
a
R
ajen
d
r
an
Dep
ar
tm
en
t o
f
E
lectr
ical
an
d
E
lectr
o
n
ics E
n
g
in
ee
r
i
n
g
,
M
S
R
am
aiah
I
n
s
titu
te
o
f
T
ec
h
n
o
lo
g
y
B
en
g
alu
r
u
,
Kar
n
atak
a,
I
n
d
ia
E
m
ail: d
r
.
r
s
u
b
h
a@
m
s
r
it.e
d
u
1.
I
NT
RO
D
UCT
I
O
N
Pack
ag
in
g
s
ec
to
r
is
am
o
n
g
t
h
e
f
ast
-
g
r
o
win
g
in
d
u
s
tr
ies
in
I
n
d
ia
a
n
d
wo
r
ld
wid
e.
An
in
teg
r
ate
d
p
ac
k
ag
in
g
m
ater
ial
is
a
ty
p
e
o
f
f
le
x
ib
le
p
ac
k
ag
in
g
m
ater
ia
l
th
at
ca
n
b
e
u
s
ed
to
p
ac
k
a
v
ar
iety
o
f
p
r
o
d
u
cts.
p
o
ly
p
r
o
p
y
le
n
e
(
PP
)
b
ased
f
le
x
ib
le
p
ac
k
a
g
in
g
m
ater
ials
ar
e
ex
ten
s
iv
ely
u
s
ed
f
o
r
p
a
ck
ag
i
n
g
v
ar
i
o
u
s
p
r
o
d
u
cts
b
y
th
e
u
n
o
r
g
an
ized
an
d
o
r
g
an
i
ze
d
m
an
u
f
ac
tu
r
i
n
g
s
ec
to
r
.
T
h
e
y
ar
e
lig
h
t
weig
h
t
a
n
d
c
o
m
e
with
th
e
a
d
v
an
ta
g
es
o
f
d
u
r
ab
ilit
y
,
r
eu
s
ab
ilit
y
an
d
co
s
t
ef
f
ec
tiv
en
ess
.
T
h
ey
ca
n
b
e
m
an
u
f
ac
t
u
r
ed
in
v
ar
iety
o
f
s
izes.
Ad
v
an
ce
d
f
lex
o
g
r
a
p
h
ic
p
r
in
tin
g
m
ac
h
in
es
ca
n
b
e
u
s
ed
to
p
r
in
t
o
n
th
ese
m
ater
ials
f
o
r
a
p
p
ea
l
an
d
b
r
an
d
in
g
.
T
h
e
co
n
tin
u
o
u
s
p
r
i
n
ted
f
ilm
is
th
en
s
ea
led
a
n
d
cu
t
u
s
in
g
a
p
o
in
t
b
o
tto
m
s
ea
lin
g
an
d
c
u
ttin
g
m
ac
h
in
e.
T
h
e
d
im
en
s
io
n
s
o
f
th
e
m
ater
ial
lik
e
s
ize
an
d
th
ick
n
ess
ar
e
s
et
a
s
p
er
th
e
n
ee
d
o
f
th
e
cu
s
to
m
er
.
T
h
e
s
p
ee
d
at
wh
ich
th
e
s
ea
lin
g
an
d
cu
ttin
g
o
p
er
atio
n
ca
n
b
e
p
e
r
f
o
r
m
ed
is
lim
ited
b
y
th
e
th
ick
n
ess
o
f
th
e
m
ater
ial
an
d
th
e
te
m
p
er
atu
r
e
r
is
e
in
t
h
e
m
ac
h
in
e.
Acc
u
r
ate
ass
ess
m
en
t
o
f
p
r
o
d
u
ctio
n
tim
e
a
n
d
q
u
an
tity
is
cr
u
cial
f
o
r
ef
f
ec
tiv
e
p
lan
n
in
g
an
d
co
s
t
esti
m
atio
n
.
T
h
e
p
r
o
d
u
ctio
n
q
u
an
tity
r
elies
o
n
f
ac
to
r
s
s
u
ch
as
th
e
m
ater
ial
d
im
en
s
io
n
s
,
th
ick
n
ess
,
a
n
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:
2
5
0
2
-
4
7
52
Ma
ch
in
e
lea
r
n
in
g
b
a
s
ed
p
r
ed
ictio
n
o
f p
r
o
d
u
ctio
n
u
s
in
g
r
ea
l
… (
F
a
th
ima
R
a
n
i I
r
u
d
a
ya
Ma
r
y
Dia
n
a
)
1377
o
p
er
atin
g
s
p
ee
d
o
f
th
e
c
u
ttin
g
m
ac
h
in
e.
T
h
e
r
elatio
n
s
h
ip
b
etwe
en
th
ese
p
ar
am
eter
s
is
f
air
ly
co
m
p
lex
,
as
s
p
ee
d
is
ag
ain
co
n
s
tr
ain
ed
b
y
f
ac
to
r
s
s
u
ch
as
th
ick
n
ess
an
d
m
ac
h
in
e’
s
tem
p
er
atu
r
e
r
is
e
an
d
th
e
tem
p
er
atu
r
e
s
ettin
g
o
f
th
e
m
ac
h
i
n
e
is
d
eter
m
in
ed
b
ased
o
n
th
e
m
at
er
ial’
s
th
ick
n
ess
.
T
h
er
e
f
o
r
e,
it
is
ess
en
tial
to
co
m
p
r
eh
e
n
d
th
e
co
r
r
elatio
n
b
etwe
en
v
ar
io
u
s
p
ar
am
eter
s
an
d
h
o
w
th
ey
im
p
ac
t
p
r
o
d
u
ctio
n
tim
e
an
d
q
u
an
tity
.
C
o
s
t
ef
f
ec
tiv
en
ess
an
d
r
u
n
ti
m
e
m
an
ag
em
en
t
ar
e
im
p
er
ati
v
e
f
ac
to
r
s
in
a
m
an
u
f
ac
tu
r
in
g
s
et
u
p
an
d
a
p
r
io
r
k
n
o
wled
g
e
o
f
p
r
o
d
u
ctiv
ity
ca
n
b
e
a
b
ig
lea
p
to
war
d
s
attain
in
g
it.
Hav
in
g
p
r
io
r
k
n
o
wled
g
e
o
f
th
e
p
r
o
d
u
ctio
n
q
u
an
tity
ca
n
ai
d
in
d
eter
m
in
in
g
b
o
th
t
h
e
m
ac
h
in
e
r
u
n
tim
e
a
n
d
th
e
ass
o
ciate
d
co
s
ts
.
Hen
ce
th
er
e
is
a
n
ee
d
t
o
p
r
ed
ict
th
e
p
r
o
d
u
ctio
n
q
u
a
n
tity
in
ter
m
s
o
f
n
u
m
b
er
o
f
p
iece
s
o
r
k
ilo
g
r
am
s
p
r
io
r
to
c
o
m
m
en
cin
g
p
r
o
d
u
ctio
n
.
T
h
is
m
o
tiv
ated
th
e
au
th
o
r
s
to
co
llect
r
ea
l
tim
e
d
ata
f
r
o
m
a
f
lex
o
p
r
in
tin
g
an
d
cu
ttin
g
u
n
i
t
to
u
n
d
er
s
tan
d
t
h
e
co
r
r
elatio
n
b
etwe
en
v
ar
io
u
s
p
ar
am
eter
s
an
d
to
d
e
v
elo
p
a
s
u
itab
le
m
o
d
el
f
o
r
p
r
ed
ictin
g
th
e
o
u
tp
u
t
o
f
a
p
o
i
n
t
b
o
tto
m
s
ea
lin
g
an
d
cu
ttin
g
m
a
ch
in
e.
Pro
p
er
m
an
a
g
em
en
t
o
f
d
ata
a
n
d
its
u
tili
za
tio
n
f
o
r
d
ata
d
r
iv
en
d
ec
is
io
n
m
ak
in
g
ca
n
g
iv
e
an
ed
g
e
to
an
in
d
u
s
tr
y
o
v
er
th
eir
co
m
p
e
tito
r
s
[
1
]
,
[
2
]
.
T
h
e
f
ield
o
f
a
r
tific
ial
in
tellig
en
ce
(
AI
)
h
as
b
ee
n
s
u
cc
ess
f
u
l
in
d
ea
lin
g
with
lar
g
e
am
o
u
n
ts
o
f
d
ata
to
d
r
aw
m
ea
n
in
g
f
u
l
co
n
clu
s
io
n
s
[
3
]
.
Ma
c
h
in
e
l
ea
r
n
in
g
(
ML
)
is
a
s
u
b
d
iv
is
io
n
o
f
AI
th
at
d
ea
ls
w
ith
alg
o
r
ith
m
s
th
at
ar
e
ca
p
ab
le
o
f
lear
n
in
g
f
r
o
m
th
e
g
iv
e
n
d
a
ta.
I
n
r
ec
en
t
y
ea
r
s
th
e
ap
p
licatio
n
s
o
f
ML
h
a
v
e
g
r
o
wn
tr
em
en
d
o
u
s
ly
in
all
f
ield
s
wh
ich
in
clu
d
e
m
ed
icin
e,
ag
r
icu
ltu
r
e
,
an
d
en
ter
tain
m
en
t
t
o
n
am
e
a
f
ew
[
4
]
-
[
7
]
.
ML
h
as
also
p
e
n
etr
ate
d
in
to
th
e
in
d
u
s
tr
ial
f
ield
,
an
d
m
an
y
wo
r
k
s
s
h
o
w
p
r
o
m
is
in
g
r
esu
lts
th
at
wo
u
ld
b
r
in
g
a
tr
a
n
s
f
o
r
m
atio
n
to
th
e
tr
ad
itio
n
al
m
an
u
f
ac
tu
r
in
g
s
y
s
tem
[
8
]
.
ML
h
as
estab
lis
h
ed
its
elf
to
b
e
a
v
alu
ab
le
to
o
l
in
p
r
ed
ictiv
e
s
ch
ed
u
lin
g
an
d
r
eso
u
r
ce
allo
ca
tio
n
in
lar
g
e
s
ca
le
m
an
u
f
ac
tu
r
in
g
s
y
s
tem
s
[
9
]
.
Mo
s
t
m
an
u
f
ac
t
u
r
in
g
s
y
s
tem
s
o
p
er
ate
i
n
d
y
n
am
ic
en
v
ir
o
n
m
en
ts
an
d
ML
ca
n
b
e
u
s
ed
f
o
r
ef
f
ec
tiv
e
s
ch
ed
u
lin
g
u
n
d
er
s
u
c
h
cir
cu
m
s
tan
ce
s
[
1
0
]
.
Hen
ce
an
attem
p
t
h
as
b
ee
n
m
ad
e
in
th
is
wo
r
k
to
d
ev
elo
p
f
o
u
r
d
if
f
er
en
t
ML
m
o
d
els
n
am
ely
ar
tific
ial
n
eu
r
al
n
etwo
r
k
(
ANN)
,
s
u
p
p
o
r
t
v
ec
t
o
r
r
eg
r
ess
io
n
(
SVR
)
,
r
eg
r
ess
io
n
tr
ee
e
n
s
em
b
le
(
R
T
E
)
an
d
g
a
u
s
s
ian
p
r
o
ce
s
s
r
e
g
r
ess
io
n
(
GPR
)
aim
ed
at
p
r
ed
ictin
g
p
r
o
d
u
ctio
n
q
u
an
tity
.
T
h
e
h
y
p
er
p
er
am
eter
s
o
f
th
ese
m
o
d
els
h
av
e
b
ee
n
o
p
tim
ized
with
f
i
v
e
-
f
o
l
d
cr
o
s
s
v
alid
atio
n
an
d
th
e
o
p
tim
ized
m
o
d
els
h
av
e
b
ee
n
a
s
s
es
s
ed
an
d
co
m
p
ar
ed
b
ased
o
n
th
eir
ac
cu
r
ac
y
in
p
r
ed
ictio
n
,
tr
ain
in
g
d
u
r
atio
n
,
an
d
p
r
e
d
ictio
n
s
p
ee
d
.
ML
ca
n
b
e
u
s
ed
f
o
r
class
if
icatio
n
an
d
r
eg
r
ess
io
n
task
s
.
T
h
e
r
elev
an
t
liter
atu
r
e
wo
r
k
s
ar
e
p
r
esen
ted
h
er
e
to
b
r
in
g
o
u
t
th
e
s
ig
n
if
ica
n
ce
o
f
th
e
p
r
o
p
o
s
ed
wo
r
k
.
Pre
d
ictiv
e
m
o
d
el
-
b
ased
q
u
ality
in
s
p
ec
tio
n
u
s
in
g
ML
an
d
E
d
g
e
C
lo
u
d
C
o
m
p
u
tin
g
h
as
b
ee
n
p
r
o
p
o
s
ed
with
a
ca
s
e
s
tu
d
y
in
elec
tr
o
n
ics
in
d
u
s
tr
y
[
1
1
]
.
Naïv
e
B
ay
es,
d
ec
is
io
n
tr
ee
(
DT
)
,
l
o
g
is
tic
r
e
g
r
ess
io
n
,
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
(
SVM)
an
d
g
r
ad
ien
t
b
o
o
s
ted
tr
ee
(
GB
T
)
h
av
e
b
ee
n
u
s
ed
f
o
r
th
e
class
if
icatio
n
task
.
A
m
o
d
if
ied
n
o
m
a
d
ic
b
ased
L
io
n
a
lg
o
r
ith
m
h
as
b
ee
n
u
s
ed
f
o
r
p
r
ed
ictin
g
th
e
o
p
tim
al
s
ch
ed
u
lin
g
in
f
l
ex
ib
le
m
an
u
f
a
ctu
r
in
g
s
y
s
tem
s
[
1
2
]
.
A
m
an
u
f
ac
tu
r
in
g
s
y
s
tem
wid
e
b
alan
ce
d
r
an
d
o
m
s
u
r
v
i
v
al
f
o
r
est
alg
o
r
ith
m
h
as
b
ee
n
u
s
ed
to
p
r
ed
ict
b
r
ea
k
d
o
wn
in
m
ac
h
in
es
3
0
m
in
u
tes
ah
ea
d
[
1
3
]
.
E
n
s
em
b
le
b
ased
m
eth
o
d
h
as
b
ee
n
u
s
ed
f
o
r
d
y
n
am
ic
s
ch
ed
u
lin
g
in
f
lex
ib
le
m
an
u
f
ac
t
u
r
in
g
s
y
s
tem
s
[
1
4
]
.
An
ANN
b
ased
m
o
d
el
h
as
b
ee
n
d
ev
elo
p
ed
f
o
r
p
r
ed
ictio
n
o
f
f
ailu
r
e
i
n
a
p
r
o
d
u
ctio
n
l
in
e
f
o
r
p
r
ed
ictiv
e
m
ain
ten
an
ce
o
f
i
n
d
u
s
tr
ial
p
ac
k
ag
in
g
r
o
b
o
ts
[
1
5
]
.
A
co
m
p
r
e
h
en
s
iv
e
r
ev
iew
o
f
v
a
r
io
u
s
ML
tech
n
iq
u
es
u
s
ed
f
o
r
in
d
u
s
tr
ial
ap
p
licatio
n
s
is
p
r
esen
ted
in
[
1
6
]
,
[
1
7
]
.
T
a
b
le
1
p
r
esen
ts
a
s
u
r
v
ey
o
f
liter
atu
r
es
u
s
in
g
r
eg
r
ess
io
n
m
o
d
els
f
o
r
p
r
e
d
ictio
n
i
n
v
a
r
io
u
s
ap
p
licatio
n
s
[
1
8
]
-
[
2
5
]
.
A
s
s
ee
n
f
r
o
m
th
e
tab
le,
th
e
M
L
m
o
d
els
u
s
ed
ar
e
lin
ea
r
r
eg
r
ess
io
n
(
L
R
)
,
ANN,
s
p
ac
e
v
ec
to
r
r
eg
r
ess
io
n
(
SV
R
)
u
s
in
g
PP
an
d
/o
r
r
ad
ial
b
i
as
f
u
n
ctio
n
(
R
B
F)
k
er
n
el,
K
n
ea
r
est
n
eig
h
b
o
r
(
K
NN)
,
DT
,
r
an
d
o
m
f
o
r
est
(
R
F),
g
r
ad
ien
t
b
o
o
s
tin
g
(
GB
)
,
en
s
em
b
le
lear
n
in
g
(
E
L
)
,
lig
h
t
g
r
a
d
ien
t
b
o
o
s
tin
g
m
ac
h
in
e
(
L
GB
M)
an
d
ex
tr
em
e
g
r
ad
ien
t
b
o
o
s
tin
g
(
XGB
o
o
s
t
)
.
L
R
is
th
e
s
im
p
lest
m
o
d
el
f
o
r
p
r
e
d
ictio
n
th
at
is
e
asy
to
d
ev
elo
p
.
SVR
with
R
B
F
k
er
n
el
is
th
e
m
o
s
t
f
r
eq
u
e
n
tly
u
s
ed
r
e
g
r
ess
io
n
m
o
d
el
f
o
r
p
r
ed
ictio
n
.
GB
an
d
o
th
er
en
s
em
b
le
-
b
ased
m
e
th
o
d
s
u
s
e
a
co
m
b
in
atio
n
o
f
wea
k
lear
n
er
s
f
o
r
p
r
ed
ictio
n
to
av
o
id
o
v
e
r
f
itti
n
g
.
T
h
e
p
e
r
f
o
r
m
an
ce
p
a
r
am
eter
s
co
n
s
id
er
ed
f
o
r
t
h
e
ev
alu
atio
n
o
f
m
o
d
els
in
clu
d
e
R
-
s
q
u
ar
ed
v
alu
e
,
m
ea
n
ab
s
o
l
u
te
er
r
o
r
(
MA
E
)
,
r
o
o
t
m
ea
n
s
q
u
ar
ed
er
r
o
r
(
R
MSE
)
,
p
er
c
en
tag
e
er
r
o
r
(
PE)
,
co
r
r
elatio
n
,
tr
ain
in
g
tim
e
an
d
co
m
p
u
tatio
n
tim
e.
B
ased
o
n
th
ese
p
ar
am
eter
s
,
t
h
e
b
est
m
o
d
els
id
en
tifie
d
f
o
r
ea
ch
ap
p
licatio
n
is
also
s
h
o
wn
in
T
ab
le
1
.
B
ased
o
n
th
e
s
u
r
v
ey
p
r
esen
ted
in
T
ab
le
1
,
th
e
r
eg
r
ess
io
n
m
o
d
els
g
iv
in
g
g
o
o
d
r
esu
lts
ar
e
id
en
tifi
ed
as SVR
,
ANN
an
d
E
n
s
em
b
le
b
ased
m
eth
o
d
s
u
s
in
g
tr
ee
s
.
GPR
is
y
et
an
o
th
er
r
eg
r
ess
io
n
m
o
d
el
with
p
r
o
m
is
in
g
r
esu
l
ts
f
o
r
s
m
all
d
atasets
,
wh
ich
is
r
elativ
ely
n
ew
an
d
h
as
n
o
t
b
ee
n
u
s
ed
f
o
r
m
an
y
ap
p
licatio
n
s
[
2
6
]
-
[
2
8
]
.
Hen
ce
an
attem
p
t
h
as
b
ee
n
m
ad
e
in
th
is
p
ap
er
to
d
ev
elo
p
a
n
in
tellig
en
t
m
o
d
el
f
o
r
p
r
e
d
ictin
g
th
e
y
ield
o
f
a
c
u
ttin
g
m
ac
h
in
e
u
s
in
g
ANN
,
SVR
,
R
T
E
an
d
GPR
.
T
h
e
aim
o
f
th
is
p
ap
er
is
to
d
et
er
m
in
e
th
e
m
o
s
t
im
p
o
r
tan
t
p
ar
am
eter
s
f
o
r
p
r
e
d
ictin
g
p
r
o
d
u
ct
io
n
,
d
ev
elo
p
h
ig
h
-
p
er
f
o
r
m
in
g
ML
m
o
d
els
with
o
p
tim
ized
h
y
p
er
p
a
r
am
eter
s
f
o
r
p
r
ed
ictio
n
u
tili
zin
g
th
e
s
e
s
elec
ted
in
p
u
t
p
ar
am
eter
s
,
an
d
p
er
f
o
r
m
a
co
m
p
ar
ativ
e
an
aly
s
is
o
f
t
h
e
r
esu
l
ts
to
f
in
d
th
e
o
p
tim
al
m
o
d
el.
T
h
is
p
ap
er
is
o
r
g
an
ized
as
f
o
llo
ws.
A
r
ev
iew
o
f
r
ec
en
t
l
iter
atu
r
es
with
s
im
ilar
wo
r
k
h
as
b
ee
n
p
r
esen
ted
in
th
e
n
e
x
t
s
ec
tio
n
.
T
h
e
m
eth
o
d
o
lo
g
y
,
co
m
p
r
is
in
g
o
f
a
d
etailed
ac
co
u
n
t
o
f
t
h
e
d
ataset
u
s
ed
f
o
r
tr
ain
in
g
th
e
ML
m
o
d
els
an
d
a
d
escr
ip
tio
n
o
f
th
e
f
o
u
r
r
eg
r
ess
io
n
m
o
d
els
is
p
r
esen
ted
in
th
e
s
ec
tio
n
3
.
I
t
is
f
o
llo
wed
b
y
th
e
r
esu
lts
an
d
d
is
cu
s
s
io
n
s
ec
tio
n
wh
er
e
t
h
e
v
is
u
aliza
tio
n
r
esu
lts
o
f
th
e
d
ataset
h
av
e
b
ee
n
p
r
esen
ted
to
u
n
d
er
s
tan
d
th
e
in
h
er
en
t
r
elatio
n
s
b
etwe
en
th
e
p
ar
am
eter
s
an
d
th
e
r
esu
lts
o
f
th
e
f
o
u
r
ML
m
o
d
els
d
ev
elo
p
e
d
.
R
esu
lts
h
av
e
also
b
ee
n
p
r
o
v
id
e
d
co
m
p
ar
in
g
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
f
o
u
r
r
eg
r
ess
io
n
m
o
d
els
an
d
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
7
,
No
.
2
,
Feb
r
u
a
r
y
20
25
:
1
37
6
-
1
38
6
1378
u
s
in
g
th
e
b
est
p
er
f
o
r
m
in
g
m
o
d
el
to
p
r
ed
ict
o
u
tp
u
t
f
o
r
u
n
s
ee
n
d
ata.
L
astl
y
,
th
e
c
o
n
clu
s
io
n
s
ec
tio
n
s
u
m
m
ar
izes
th
e
wo
r
k
a
n
d
co
n
clu
d
es with
t
h
e
f
in
al
co
n
tr
ib
u
tio
n
an
d
f
u
tu
r
e
s
co
p
e
o
f
t
h
e
wo
r
k
.
T
ab
le
1
.
Su
r
v
ey
o
f
r
e
g
r
ess
io
n
m
o
d
els d
ev
elo
p
ed
f
o
r
p
r
ed
icti
o
n
R
e
g
r
e
ssi
o
n
m
o
d
e
l
M
L
t
e
c
h
n
i
q
u
e
s
P
e
r
f
o
r
ma
n
c
e
p
a
r
a
m
e
t
e
r
B
e
st
m
o
d
e
l
i
d
e
n
t
i
f
i
e
d
P
r
e
d
i
c
t
i
o
n
o
f
p
h
o
t
o
v
o
l
t
a
i
c
e
n
e
r
g
y
p
r
o
d
u
c
t
i
o
n
[
1
8
]
S
V
R
(
R
B
F
)
M
A
E,
R
-
S
q
u
a
r
e
d
,
R
M
S
E
S
V
R
(
R
B
F
)
P
r
e
d
i
c
t
i
o
n
o
f
m
i
c
r
o
me
t
e
o
r
o
l
o
g
i
c
a
l
d
a
t
a
[
1
9
]
S
V
R
(
R
B
F
)
R
M
S
E
S
V
R
(
R
B
F
)
P
r
e
d
i
c
t
i
o
n
o
f
C
N
C
t
o
o
l
w
a
r
e
c
o
m
p
e
n
s
a
t
i
o
n
o
f
f
set
[
2
0
]
S
V
R
(
R
B
F
)
R
M
S
E
S
V
R
(
R
B
F
)
Est
i
m
a
t
i
o
n
o
f
m
a
n
u
f
a
c
t
u
r
i
n
g
c
o
st
o
f
j
e
t
e
n
g
i
n
e
c
o
mp
o
n
e
n
t
s
[
2
1
]
LR
,
A
N
N
,
S
V
R
,
G
B
R
-
s
q
u
a
r
e
d
,
M
A
E
,
R
M
S
E,
c
o
r
r
e
l
a
t
i
o
n
,
c
o
m
p
u
t
a
t
i
o
n
t
i
me
GB
Est
i
m
a
t
i
o
n
o
f
e
f
f
o
r
t
i
n
a
sp
r
i
n
t
[
2
2
]
LR
,
K
N
N
,
D
T,
R
F
,
S
V
R
C
o
r
r
e
l
a
t
i
o
n
,
M
A
E,
R
M
S
E
ANN
Est
i
m
a
t
i
o
n
o
f
c
r
o
p
p
r
o
d
u
c
t
i
o
n
[
2
3
]
G
B
,
R
F
,
D
T
,
S
V
R
Tr
a
i
n
a
c
c
u
r
a
c
y
,
t
e
st
a
c
c
u
r
a
c
y
DT
P
r
e
d
i
c
t
i
o
n
o
f
t
o
o
l
w
a
r
e
i
n
m
i
l
l
i
n
g
o
p
e
r
a
t
i
o
n
s
[
2
4
]
A
N
N
,
S
V
R
,
RF
M
S
E,
R
-
s
q
u
a
r
e
d
,
t
r
a
i
n
i
n
g
t
i
m
e
RF
Est
i
m
a
t
i
o
n
o
f
s
t
e
e
l
q
u
a
l
i
t
y
c
o
n
t
r
o
l
[
2
5
]
LR
,
S
V
M
,
K
N
N
,
EL
,
R
F
,
G
B
,
LG
B
M
,
X
G
B
O
O
S
T
R
-
s
q
u
a
r
e
d
,
R
M
S
E,
P
E
EL
2.
M
E
T
H
O
D
T
h
e
m
eth
o
d
o
lo
g
y
a
d
o
p
ted
in
th
e
d
ev
elo
p
m
en
t
o
f
p
r
ed
ictio
n
m
o
d
el
is
illu
s
tr
ated
in
Fig
u
r
e
1
.
Data
was
co
llected
f
r
o
m
t
h
e
p
r
o
d
u
ctio
n
r
ec
o
r
d
b
o
o
k
s
o
f
th
e
f
le
x
o
p
r
in
tin
g
u
n
it.
T
h
e
d
ata
was
f
u
r
th
e
r
clea
n
ed
b
y
r
em
o
v
in
g
d
ata
with
m
is
s
in
g
v
alu
es
to
g
en
er
ate
f
in
al
la
b
eled
d
ata.
T
h
e
d
ata
was
th
e
n
u
s
ed
to
co
m
p
u
te
th
e
o
p
tim
ized
h
y
p
er
p
a
r
am
eter
s
o
f
f
o
u
r
d
if
f
er
e
n
t
r
eg
r
ess
io
n
m
o
d
els
n
am
ely
ANN
,
SVR
,
R
T
E
an
d
GPR
with
f
iv
e
-
f
o
ld
cr
o
s
s
v
alid
atio
n
.
T
h
e
m
o
d
els
wer
e
th
en
tr
ain
ed
an
d
e
v
alu
ated
with
cr
o
s
s
v
alid
atio
n
to
p
r
ev
en
t
o
v
er
f
itti
n
g
o
f
d
ata.
T
h
e
m
o
d
el
was
f
u
r
th
e
r
u
s
ed
f
o
r
p
r
ed
ictio
n
o
f
p
r
o
d
u
ctio
n
o
u
tp
u
t
f
o
r
n
ew
u
n
s
ee
n
d
ata.
T
h
e
f
o
llo
win
g
s
u
b
s
ec
tio
n
s
in
clu
d
e
a
d
escr
ip
ti
o
n
o
f
th
e
f
lex
o
p
r
in
tin
g
,
cu
ttin
g
,
an
d
d
ataset
co
n
s
tr
u
ctio
n
p
r
o
ce
s
s
es.
T
h
e
d
ataset
its
elf
is
th
en
d
escr
ib
ed
.
T
h
e
f
o
u
r
r
eg
r
ess
io
n
m
o
d
els
tr
ain
e
d
an
d
u
s
ed
f
o
r
p
r
e
d
ictio
n
a
r
e
b
r
ief
ed
in
th
e
f
u
r
t
h
er
s
u
b
s
ec
tio
n
s
.
Fig
u
r
e
1
.
Gen
e
r
al
f
r
am
ew
o
r
k
o
f
th
e
p
r
o
p
o
s
ed
wo
r
k
2
.
1
.
P
r
o
ce
s
s
des
cr
iptio
n a
nd
co
ns
t
ruct
io
n o
f
da
t
a
s
et
T
h
e
p
u
r
p
o
s
e
o
f
a
p
ac
k
ag
e
is
to
s
af
eg
u
ar
d
,
co
n
tain
,
p
r
eser
v
e
a
n
d
co
n
v
ey
in
f
o
r
m
atio
n
ab
o
u
t a
p
r
o
d
u
ct.
Flex
ib
le
p
ac
k
ag
in
g
d
o
esn
’
t
h
av
e
a
s
et
s
h
ap
e
b
u
t
tak
es
th
e
s
h
ap
e
o
f
th
e
p
r
o
d
u
ct
it
p
r
o
tects
.
Ad
v
an
ce
d
f
lex
o
g
r
a
p
h
ic
p
r
in
tin
g
m
eth
o
d
s
f
ac
ilit
ate
b
r
an
d
o
wn
er
s
to
m
ar
k
et
th
eir
p
r
o
d
u
ct
an
d
co
n
v
e
y
in
f
o
r
m
atio
n
s
li
k
e
s
o
u
r
ce
o
f
th
e
p
r
o
d
u
ct,
n
u
tr
itio
n
al
d
etails,
v
ital
tr
ac
k
in
g
d
a
ta
f
o
r
p
r
o
d
u
ct
r
ec
all
etc
e
f
f
ec
tiv
ely
.
PP
an
d
lo
w
-
d
en
s
ity
(
L
D)
p
o
ly
eth
y
len
e
r
esin
b
ased
f
lex
ib
le
p
ac
k
ag
i
n
g
m
ater
ials
ar
e
ex
te
n
s
iv
ely
u
s
ed
f
o
r
p
ac
k
ag
i
n
g
v
ar
io
u
s
p
r
o
d
u
cts
b
y
th
e
u
n
o
r
g
an
ized
a
n
d
o
r
g
an
ized
m
an
u
f
ac
tu
r
in
g
s
ec
to
r
.
Of
te
n
,
th
ese
r
esin
s
ar
e
ex
tr
u
d
ed
in
to
a
f
ilm
f
o
r
m
u
s
in
g
PP
o
r
L
D
m
o
n
o
la
y
er
o
r
m
u
ltil
ay
er
b
lo
wn
f
ilm
m
ac
h
in
e.
T
h
e
ex
tr
u
d
ed
f
ilm
is
co
r
o
n
a
tr
ea
ted
an
d
t
h
e
tr
ea
ted
f
ilm
i
s
wo
u
n
d
in
th
e
f
o
r
m
o
f
a
r
o
ll.
C
o
r
o
n
a
tr
ea
tm
en
t
i
n
cr
ea
s
es
th
e
s
u
r
f
ac
e
en
e
r
g
y
o
f
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
Ma
ch
in
e
lea
r
n
in
g
b
a
s
ed
p
r
ed
ictio
n
o
f p
r
o
d
u
ctio
n
u
s
in
g
r
ea
l
… (
F
a
th
ima
R
a
n
i I
r
u
d
a
ya
Ma
r
y
Dia
n
a
)
1379
f
ilm
s
to
im
p
r
o
v
e
wettab
ilit
y
an
d
a
d
h
esio
n
o
f
in
k
s
.
T
h
e
ex
tr
u
d
ed
tr
ea
ted
f
ilm
ca
n
b
e
f
lex
o
p
r
in
te
d
,
b
o
tto
m
s
ea
led
an
d
cu
t
as
p
er
t
h
e
r
eq
u
ir
em
en
t
o
f
th
e
b
u
y
er
.
T
h
e
s
ea
lin
g
an
d
c
u
ttin
g
o
f
th
e
co
n
t
in
u
o
u
s
f
lex
o
p
r
in
te
d
f
ilm
ar
e
d
o
n
e
u
s
in
g
p
o
in
t
b
o
tto
m
s
ea
lin
g
an
d
cu
ttin
g
m
ac
h
in
e.
T
h
e
f
in
is
h
ed
p
r
o
d
u
ct
is
u
s
ed
as
in
teg
r
ated
p
ac
k
ag
in
g
m
ater
ial
to
p
ac
k
v
a
r
io
u
s
p
r
o
d
u
cts.
T
h
e
m
ac
h
in
e
c
o
n
s
is
ts
o
f
u
n
win
d
in
g
s
ec
tio
n
,
a
p
h
o
to
ce
ll
-
b
ased
s
en
s
o
r
to
d
etec
t
th
e
p
r
i
n
t
r
e
p
ea
t,
b
o
tto
m
s
ea
lin
g
an
d
a
cu
ttin
g
s
ec
tio
n
.
T
h
e
m
ac
h
i
n
e
is
eq
u
ip
p
ed
with
tem
p
er
atu
r
e
co
n
tr
o
ller
s
wh
ic
h
ca
n
p
r
o
v
id
e
th
e
m
o
s
t
a
cc
u
r
ate
an
d
f
astes
t
h
ea
tin
g
p
er
f
o
r
m
an
ce
f
o
r
s
ea
lin
g
p
r
o
ce
s
s
.
T
h
e
o
p
er
atio
n
o
f
th
e
m
ac
h
in
e
is
co
n
tr
o
lled
b
y
p
r
o
g
r
am
m
ab
le
lo
g
ic
c
o
n
tr
o
ller
(
PL
C
)
.
T
h
e
m
ac
h
in
e
is
eq
u
ip
p
e
d
with
s
er
v
o
m
o
to
r
f
o
r
i
n
d
ex
in
g
a
n
d
ac
cu
r
ac
y
a
n
d
is
id
ea
l
f
o
r
th
e
b
o
tto
m
s
ea
lin
g
an
d
c
u
ttin
g
o
p
er
atio
n
o
f
f
le
x
o
p
r
i
n
ted
PP
o
r
L
D
f
ilm
r
o
lls
.
T
h
e
m
ater
ial
is
p
r
in
ted
an
d
cu
t
in
d
i
f
f
er
en
t
d
im
en
s
io
n
s
as
p
er
th
e
cu
s
to
m
er
r
eq
u
ir
e
m
en
ts
.
T
h
e
p
r
o
d
u
ctio
n
d
e
p
en
d
s
o
n
th
e
len
g
th
,
wid
th
,
th
ic
k
n
ess
(
g
au
g
e)
o
f
th
e
m
ater
ial
an
d
th
e
cu
ttin
g
m
ac
h
in
e
s
p
e
ed
.
Fo
r
ec
asti
n
g
th
e
p
r
o
d
u
ctio
n
(
p
iece
s
/k
g
)
wo
u
ld
b
e
c
r
u
ci
al
f
o
r
in
f
er
r
in
g
th
e
m
ac
h
in
e
r
u
n
tim
e.
Hen
ce
t
o
d
ev
elo
p
a
p
r
ed
ictio
n
m
o
d
el,
a
to
tal
o
f
1
8
3
d
atasets
wer
e
co
llected
f
r
o
m
th
e
p
r
o
d
u
ctio
n
r
e
p
o
r
ts
.
2
.
2
.
Da
t
a
s
et
des
cr
iptio
n
A
p
r
ed
ictio
n
m
o
d
el
ca
n
b
e
d
e
v
elo
p
ed
to
p
r
ed
ict
th
e
p
r
o
d
u
ctio
n
b
ased
o
n
th
e
i
n
p
u
t
p
ar
am
e
ter
s
len
g
th
,
wid
th
,
g
au
g
e
m
ac
h
in
e
s
p
ee
d
an
d
tem
p
er
atu
r
e.
T
h
e
d
escr
ip
t
io
n
o
f
th
e
d
ataset
p
ar
am
eter
s
co
llected
f
r
o
m
th
e
p
r
o
d
u
ctio
n
r
e
p
o
r
ts
o
f
cu
ttin
g
m
ac
h
in
e
ar
e
p
r
esen
ted
in
T
a
b
le
2
.
T
h
e
wid
th
o
f
th
e
f
ilm
r
o
lls
an
d
len
g
t
h
o
f
cu
ttin
g
th
e
p
r
in
te
d
f
ilm
is
d
e
p
en
d
en
t
o
n
th
e
d
im
en
s
io
n
s
o
f
th
e
p
ac
k
ag
i
n
g
m
ater
ial.
T
h
ese
d
im
en
s
io
n
s
ar
e
p
r
o
v
id
e
d
b
y
th
e
b
u
y
e
r
.
T
h
e
f
i
lm
r
o
ll
f
o
r
p
r
i
n
tin
g
will
b
e
ex
tr
u
d
ed
as
p
er
th
e
wid
th
r
e
q
u
ir
ed
.
T
h
e
r
ep
ea
t
s
ize
f
o
r
th
e
p
r
i
n
tin
g
p
r
o
ce
s
s
will
b
e
d
ep
en
d
en
t
o
n
t
h
e
len
g
th
o
f
th
e
p
ac
k
a
g
in
g
p
r
in
ted
m
ater
ia
l.
T
h
e
s
am
e
le
n
g
th
will
b
e
s
et
in
th
e
cu
ttin
g
m
ac
h
in
e
f
o
r
s
ea
lin
g
an
d
c
u
ttin
g
p
r
o
ce
s
s
.
T
h
e
th
ick
n
ess
o
f
th
e
f
ilm
is
o
f
ten
ex
p
r
ess
ed
in
g
au
g
e
o
r
m
icr
o
n
.
A
f
ilm
t
h
at
h
as
1
0
0
g
a
u
g
e
o
r
2
5
.
4
0
m
icr
o
n
s
will
h
a
v
e
a
th
ick
n
ess
o
f
0
.
0
2
5
4
m
m
(
o
r
0
.
0
0
1
0
in
c
h
)
.
T
h
e
g
au
g
e
is
g
iv
en
to
th
e
e
x
tr
u
d
er
f
o
r
m
a
k
in
g
f
ilm
r
o
ll
a
n
d
th
e
ac
tu
al
g
au
g
e
o
f
th
e
f
ilm
r
ec
eiv
ed
f
o
r
p
r
in
tin
g
is
cr
o
s
s
-
ch
ec
k
ed
u
s
in
g
g
a
u
g
e
m
eter
.
T
h
e
s
p
ee
d
(
s
tr
o
k
es/min
u
te)
an
d
t
em
p
er
atu
r
e
(
C
)
o
f
th
e
cu
ttin
g
m
ac
h
i
n
e
is
s
et
b
y
th
e
cu
ttin
g
m
ac
h
i
n
e
o
p
er
ato
r
.
Op
tim
u
m
s
p
ee
d
an
d
tem
p
er
a
tu
r
e
is
s
et
with
th
e
cr
iter
ia
th
at
a
g
o
o
d
s
ea
lin
g
is
o
b
tain
ed
in
th
e
cu
t
m
ater
ial.
T
h
e
m
ater
ial
at
th
e
s
ea
l
in
g
m
u
s
t
n
o
t
o
p
en
.
T
h
e
p
r
o
d
u
ctio
n
(
p
iece
s
/k
ilo
g
r
am
)
i
s
o
b
tain
ed
b
y
weig
h
tin
g
2
0
0
p
iece
s
o
f
th
e
c
u
t
m
ater
ial
an
d
c
o
n
v
er
tin
g
to
p
iece
s
p
er
k
ilo
g
r
am
.
A
to
tal
o
f
1
8
3
d
atasets
wer
e
s
elec
ted
f
o
r
d
ev
elo
p
m
en
t
o
f
p
r
ed
ictio
n
m
o
d
el.
T
h
e
r
e
g
r
ess
io
n
m
o
d
els u
s
ed
in
th
is
wo
r
k
f
o
r
p
r
ed
ictio
n
ar
e
d
is
cu
s
s
ed
n
ex
t.
T
ab
le
2
.
Descr
ip
tio
n
o
f
d
ataset
p
ar
am
eter
s
S
l
.
N
o
.
P
a
r
a
me
t
e
r
n
a
m
e
D
e
scri
p
t
i
o
n
D
a
t
a
t
y
p
e
R
a
n
g
e
M
e
a
n
V
a
r
i
a
n
c
e
1
G
a
u
g
e
Th
i
c
k
n
e
ss
o
f
t
h
e
p
r
o
d
u
c
t
I
n
t
e
g
e
r
[
1
2
0
,
4
2
4
]
2
1
9
2
2
8
4
.
1
7
2
W
i
d
t
h
W
i
d
t
h
o
f
t
h
e
p
r
o
d
u
c
t
i
n
i
n
c
h
e
s
F
l
o
a
t
[
3
,
1
8
]
7
5
.
3
5
3
Le
n
g
t
h
Le
n
g
t
h
o
f
t
h
e
p
r
o
d
u
c
t
i
n
i
n
c
h
e
s
F
l
o
a
t
[
4
,
2
2
]
10
1
2
.
0
9
4
S
p
e
e
d
N
u
mb
e
r
o
f
st
r
o
k
e
s/
m
i
n
u
t
e
s
I
n
t
e
g
e
r
[
5
0
,
1
8
5
]
1
2
6
5
1
8
.
1
2
5
Te
mp
e
r
a
t
u
r
e
M
a
c
h
i
n
e
t
e
m
p
e
r
a
t
u
r
e
s
e
t
t
i
n
g
I
n
t
e
g
e
r
[
1
4
2
,
3
9
5
]
2
6
7
1
4
2
4
.
6
8
6
P
r
o
d
u
c
t
i
o
n
N
u
mb
e
r
o
f
p
i
e
c
e
s
/
k
g
I
n
t
e
g
e
r
[
3
7
,
1
5
3
8
]
3
1
0
7
1
3
9
2
.
1
5
2
.
3
.
Reg
re
s
s
io
n
mo
dels
R
eg
r
ess
io
n
m
o
d
els
u
s
e
in
p
u
t
-
o
u
tp
u
t
p
air
s
f
r
o
m
th
e
tr
ai
n
in
g
d
ataset
to
d
eter
m
i
n
e
th
e
co
n
n
ec
tio
n
b
etwe
en
a
d
ep
e
n
d
en
t
v
ar
iab
le
an
d
o
n
e
o
r
m
o
r
e
in
d
ep
e
n
d
en
t
v
ar
iab
les.
F
o
u
r
s
u
c
h
m
o
d
els
h
av
e
b
ee
n
t
r
ain
ed
to
lear
n
th
e
r
elatio
n
s
h
ip
b
etwe
en
p
r
o
d
u
ctio
n
an
d
len
g
th
,
wid
th
,
g
au
g
e,
an
d
s
p
ee
d
.
T
h
e
d
etails
o
f
th
e
f
o
u
r
m
o
d
els
ar
e
p
r
esen
ted
in
th
e
f
o
llo
win
g
s
u
b
s
ec
tio
n
s
.
2
.
3
.
1
.
Art
if
icia
l
neura
l net
wo
rk
An
ANN
is
a
p
o
wer
f
u
l m
o
d
el
th
at
lear
n
s
th
e
non
-
lin
ea
r
m
ap
p
in
g
in
p
u
t
-
o
u
t
p
u
t
.
T
h
e
in
p
u
t
,
h
id
d
en
an
d
o
u
tp
u
t
la
y
er
s
h
av
e
n
eu
r
o
n
s
w
ith
ac
tiv
atio
n
f
u
n
ctio
n
an
d
ar
e
in
ter
co
n
n
ec
ted
with
weig
h
te
d
co
n
n
ec
tio
n
s
.
T
h
e
ANN
is
tr
ain
ed
to
in
ter
p
o
late
d
ata
with
h
ig
h
ac
c
u
r
ac
y
t
h
ey
c
an
b
ased
o
n
in
p
u
t
-
o
u
t
p
u
t d
ata
p
air
s
.
2
.
3
.
2
.
Su
pp
o
rt
v
ec
t
o
r
re
g
re
s
s
io
n
SVM
is
a
s
u
p
er
v
is
ed
lear
n
in
g
m
o
d
el
th
at
an
aly
ze
s
d
ata
f
o
r
class
if
icatio
n
an
d
r
e
g
r
ess
io
n
.
T
h
e
SVM
m
o
d
el
u
s
ed
f
o
r
r
e
g
r
ess
io
n
is
ca
lled
SVR
.
I
t
p
r
o
v
id
es
a
n
ef
f
icien
t
p
r
ed
ictio
n
m
o
d
el
f
o
r
s
m
all
n
o
n
-
lin
ea
r
d
atasets
.
SVR
tr
ies
to
f
it
th
e
er
r
o
r
with
in
a
th
r
esh
o
ld
,
b
y
f
in
d
in
g
th
e
b
est
f
it
lin
e
ca
ll
ed
h
y
p
er
p
la
n
e
an
d
ap
p
r
o
x
im
atin
g
th
e
p
r
e
d
icted
v
alu
e
with
in
th
e
g
iv
en
m
ar
g
in
.
A
k
er
n
el
f
u
n
ctio
n
is
u
s
ed
to
m
ap
th
e
d
ata
p
o
in
ts
to
a
h
ig
h
er
d
im
e
n
s
io
n
.
T
h
e
S
VR
is
tr
ain
ed
u
s
in
g
in
p
u
t
-
o
u
t
p
u
t
d
atasets
to
f
in
d
th
e
b
est
f
it
h
y
p
er
p
la
n
e
th
at
f
its
as m
an
y
d
ata
p
o
in
ts
as p
o
s
s
ib
le
with
in
th
e
b
o
u
n
d
a
r
y
lin
es.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
7
,
No
.
2
,
Feb
r
u
a
r
y
20
25
:
1
37
6
-
1
38
6
1380
2
.
3
.
3
.
Reg
re
s
s
io
n
t
re
e
ens
em
ble
A
n
o
n
-
p
ar
am
etr
ic
m
o
d
el
ca
lle
d
a
DT
ca
n
b
e
tr
ain
ed
to
p
r
e
d
ict
an
o
u
tp
u
t
v
ar
iab
le
b
y
d
e
r
i
v
in
g
b
asic
d
ec
is
io
n
r
u
les
f
r
o
m
th
e
tr
ain
i
n
g
s
et
o
f
d
ata.
R
eg
r
ess
io
n
t
r
ee
s
ar
e
DT
s
th
at
a
r
e
u
tili
s
ed
f
o
r
r
eg
r
ess
io
n
;
th
ey
a
r
e
co
n
ce
p
tu
alis
ed
as
p
iece
wis
e
c
o
n
s
tan
t
ap
p
r
o
x
im
atio
n
s
.
R
eg
r
ess
io
n
tr
ee
s
ten
d
to
o
v
er
f
it
an
d
d
o
n
o
t
g
en
er
alize
well
o
n
u
n
s
ee
n
d
ata.
A
R
T
E
i
s
a
r
eg
r
ess
io
n
m
o
d
el
b
u
ilt
u
s
i
n
g
weig
h
ted
c
o
m
b
in
atio
n
o
f
m
u
ltip
le
r
eg
r
ess
io
n
tr
ee
s
.
C
o
m
b
in
in
g
m
u
ltip
le
r
e
g
r
ess
io
n
tr
ee
s
im
p
r
o
v
es
th
e
p
r
ed
ictiv
e
p
er
f
o
r
m
a
n
ce
o
f
t
h
e
m
o
d
el.
R
eg
r
ess
io
n
tr
ee
m
o
d
els
ar
e
tr
ain
e
d
in
a
p
r
o
ce
s
s
ca
lled
"b
o
o
s
tin
g
,
"
wh
er
e
ea
ch
m
o
d
el
aim
s
to
o
u
tp
e
r
f
o
r
m
th
e
o
n
e
b
ef
o
r
e
it
in
th
e
s
eq
u
en
ce
.
2
.
3
.
4
.
G
a
us
s
ia
n
pro
ce
s
s
re
g
re
s
s
io
n
A
p
r
o
b
ab
ilis
tic
s
u
p
er
v
is
ed
m
o
d
el
f
o
r
r
eg
r
ess
io
n
an
d
class
if
icatio
n
ap
p
licatio
n
s
is
t
h
e
ga
u
s
s
ian
p
r
o
ce
s
s
(
GP)
m
o
d
el
[
2
6
]
th
at
u
s
es
B
ay
es
ian
m
eth
o
d
f
o
r
f
itt
in
g
th
e
tr
ain
in
g
d
ata
o
v
e
r
p
o
s
s
ib
le
o
v
er
p
o
s
s
ib
le
f
u
n
ctio
n
s
.
GPR
m
o
d
el
is
a
n
o
n
-
p
ar
am
etr
ic
k
er
n
el
-
b
ased
m
o
d
el
th
at
u
s
es
th
e
tr
ain
in
g
d
ata
an
d
th
e
p
r
io
r
k
n
o
wled
g
e
f
o
r
p
r
ed
ictio
n
an
d
co
m
p
u
te
s
p
r
ed
ictiv
e
p
o
s
ter
io
r
d
is
tr
ib
u
tio
n
o
n
th
e
test
in
g
d
ata.
I
t
y
ield
s
g
o
o
d
r
esu
lts
o
n
d
atasets
wh
ich
ar
e
s
m
all
also
p
r
o
v
id
i
n
g
u
n
ce
r
tain
t
y
m
ea
s
u
r
es o
v
er
p
r
e
d
ictio
n
s
.
3
.
1
.
Da
t
a
v
is
ua
liza
t
io
n
T
h
e
h
is
to
g
r
am
o
f
th
e
in
p
u
t
an
d
th
e
r
esp
o
n
s
e
v
ar
iab
le
is
p
r
e
s
en
ted
in
Fig
u
r
e
2
.
Fro
m
th
e
h
is
to
g
r
am
,
we
o
b
s
er
v
e
th
at
m
ax
im
u
m
f
r
e
q
u
en
cy
o
f
g
a
u
g
e
d
u
r
in
g
p
r
o
d
u
ctio
n
is
b
etwe
en
1
8
0
t
o
2
7
5
,
wid
th
b
etwe
en
3
an
d
1
0
in
c
h
es,
len
g
th
b
etwe
en
4
an
d
1
2
i
n
ch
es,
s
p
ee
d
b
etwe
e
n
1
0
0
a
n
d
1
5
0
s
tr
o
k
es/min
,
t
em
p
er
atu
r
e
b
etwe
en
2
0
0
an
d
3
0
0
C
an
d
p
r
o
d
u
ctio
n
b
etwe
en
1
0
0
a
n
d
1
,
4
0
0
p
i
ec
es.
T
h
e
co
r
r
elatio
n
m
atr
ix
o
f
th
e
in
p
u
t
an
d
th
e
r
esp
o
n
s
e
v
ar
iab
le
is
p
r
esen
te
d
in
T
ab
le
3
.
I
t
s
h
o
ws
th
er
e
is
a
h
ig
h
to
m
o
d
er
ate
co
r
r
ela
tio
n
b
etwe
en
in
p
u
t
v
ar
iab
les
wid
th
,
len
g
th
,
g
au
g
e
an
d
s
p
ee
d
o
n
r
esp
o
n
s
e
v
ar
iab
le
p
r
o
d
u
ctio
n
.
As
th
e
v
ar
iab
le
tem
p
er
atu
r
e
h
as
a
wea
k
co
r
r
elatio
n
with
r
esp
o
n
s
e
v
ar
iab
le,
it
will
n
o
t
co
n
tr
ib
u
te
s
ig
n
if
ican
tly
in
p
r
ed
ictin
g
th
e
p
r
o
d
u
ctio
n
q
u
an
tity
an
d
h
e
n
ce
is
n
o
t u
s
ed
f
o
r
m
o
d
el
tr
ain
in
g
.
Fig
u
r
e
2
.
Vis
u
aliza
tio
n
o
f
in
p
u
t a
n
d
o
u
tp
u
t
f
ea
tu
r
es
T
ab
le
3
.
C
o
r
r
elatio
n
m
atr
ix
s
h
o
win
g
co
r
r
elatio
n
b
etwe
en
d
at
a
f
ea
tu
r
es
P
a
r
a
me
t
e
r
G
a
u
g
e
W
i
d
t
h
Le
n
g
t
h
S
p
e
e
d
Te
mp
e
r
a
t
u
r
e
P
r
o
d
u
c
t
i
o
n
G
a
u
g
e
1
W
i
d
t
h
0
.
0
1
3
0
1
Le
n
g
t
h
-
0
.
0
6
3
2
0
.
8
9
8
2
1
S
p
e
e
d
-
0
.
1
5
0
0
-
0
.
7
9
0
8
-
0
.
8
4
0
9
1
Te
mp
e
r
a
t
u
r
e
0
.
0
8
1
9
-
0
.
0
5
9
2
-
0
.
0
3
3
8
-
0
.
0
1
1
4
1
P
r
o
d
u
c
t
i
o
n
-
0
.
5
7
4
2
-
0
.
7
5
6
6
-
0
.
7
3
7
7
0
.
7
2
7
0
0
.
0
3
7
6
1
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
Ma
ch
in
e
lea
r
n
in
g
b
a
s
ed
p
r
ed
ictio
n
o
f p
r
o
d
u
ctio
n
u
s
in
g
r
ea
l
… (
F
a
th
ima
R
a
n
i I
r
u
d
a
ya
Ma
r
y
Dia
n
a
)
1381
3
.
2
.
Reg
re
s
s
io
n
mo
del t
ra
ini
ng
a
nd
perf
o
rm
a
nce
ev
a
lua
t
io
n
Fo
u
r
r
eg
r
ess
io
n
m
o
d
els
n
am
ely
ANN
m
o
d
el,
SVR
m
o
d
el,
R
T
E
m
o
d
el
an
d
GPR
m
o
d
el
wer
e
d
ev
elo
p
e
d
to
p
r
ed
ict
p
r
o
d
u
ct
io
n
b
ased
o
n
th
e
v
alu
es
o
f
wid
th
,
len
g
th
,
g
a
u
g
e
an
d
s
p
e
ed
.
T
h
e
p
ar
am
eter
tem
p
er
atu
r
e
was n
o
t u
s
ed
in
m
o
d
el
tr
ain
in
g
d
u
e
to
its
wea
k
co
r
r
elatio
n
with
o
u
tp
u
t v
ar
iab
le
.
T
h
e
m
o
d
els we
r
e
f
ir
s
t
o
p
tim
ized
u
s
in
g
B
ay
esia
n
o
p
tim
izatio
n
m
eth
o
d
with
f
iv
e
-
f
o
ld
cr
o
s
s
v
alid
atio
n
to
f
in
d
th
e
o
p
tim
ized
v
alu
es
o
f
h
y
p
er
p
a
r
am
eter
s
f
o
r
ea
ch
m
o
d
el
with
th
e
f
iv
e
-
f
o
l
d
cr
o
s
s
v
alid
atio
n
lo
s
s
as
th
e
o
b
jectiv
e
f
u
n
ctio
n
o
f
o
p
tim
izatio
n
.
T
h
e
v
ar
iatio
n
o
f
th
e
f
iv
e
-
f
o
ld
cr
o
s
s
v
alid
atio
n
lo
s
s
as
a
f
u
n
ctio
n
o
f
iter
atio
n
n
u
m
b
e
r
d
u
r
in
g
o
p
tim
izatio
n
is
s
h
o
wn
i
n
Fig
u
r
e
3
f
o
r
t
h
e
f
o
u
r
m
o
d
els.
Six
h
y
p
er
p
ar
am
eter
s
wer
e
o
p
tim
ized
f
o
r
ANN,
SVR
an
d
R
T
E
m
o
d
els
an
d
f
iv
e
h
y
p
er
p
ar
am
eter
s
f
o
r
GPR
m
o
d
el.
As
s
ee
n
f
r
o
m
Fig
u
r
e
s
3
(
a)
to
3
(
d
)
,
t
h
e
p
ar
a
m
eter
s
o
f
GPR
m
o
d
el
wer
e
o
p
tim
ize
d
with
m
in
im
u
m
cr
o
s
s
v
alid
atio
n
lo
s
s
v
al
u
e
in
m
in
im
u
m
n
u
m
b
er
o
f
iter
atio
n
s
.
T
h
e
h
y
p
er
p
ar
am
eter
s
th
at
we
r
e
o
p
tim
ize
d
in
ea
ch
m
o
d
el
a
n
d
th
eir
v
al
u
es
af
ter
o
p
tim
iza
tio
n
ar
e
s
h
o
wn
in
T
ab
le
4
.
Fu
r
th
er
t
h
e
m
o
d
els
wer
e
cr
o
s
s
v
alid
ate
d
t
o
a
v
o
id
o
v
e
r
f
itti
n
g
o
f
th
e
d
ata
a
n
d
t
h
e
K
f
o
ld
lo
s
s
was
o
b
tain
ed
.
(
a)
(
b
)
(
c)
(
d
)
Fig
u
r
e
3
.
Hy
p
er
p
a
r
am
eter
o
p
tim
izatio
n
u
s
in
g
f
i
v
ef
o
ld
c
r
o
s
s
v
alid
atio
n
lo
s
s
as th
e
o
b
jectiv
e
f
u
n
ctio
n
:
(
a)
ANN
m
o
d
el
,
(
b
)
SVR
m
o
d
el
,
(
c)
R
T
E
m
o
d
el
,
an
d
(
d
)
GP
R
m
o
d
el
T
ab
le
4
.
Op
tim
ized
h
y
p
e
r
p
ar
a
m
eter
s
ANN
S
V
R
R
TE
G
P
R
A
c
t
i
v
a
t
i
o
n
s:
R
e
LU
B
o
x
c
o
n
st
r
a
i
n
t
:
3
3
.
2
8
M
e
t
h
o
d
:
LSB
o
o
st
S
i
g
m
a
:
0
.
5
2
2
9
5
S
t
a
n
d
a
r
d
i
z
e
:
t
r
u
e
K
e
r
n
e
l
s
c
a
l
e
:
1
.
8
5
N
u
m
l
e
a
r
n
i
n
g
c
y
c
l
e
s
:
3
6
5
B
a
si
s
f
u
n
c
t
i
o
n
:
z
e
r
o
La
mb
d
a
:
3
.
7
e
-
0
6
Ep
si
l
o
n
:
3
1
.
5
7
5
Le
a
r
n
r
a
t
e
:
0
.
1
7
8
K
e
r
n
e
l
f
u
n
c
t
i
o
n
:
a
r
d
m
a
t
e
r
n
5
/
2
La
y
e
r
s we
i
g
h
t
s i
n
i
t
i
a
l
i
z
e
:
g
l
o
r
o
t
K
e
r
n
e
l
f
u
n
c
t
i
o
n
:
p
o
l
y
n
o
m
i
a
l
M
i
n
l
e
a
f
si
z
e
:
4
K
e
r
n
e
l
s
c
a
l
e
:
-
La
y
e
r
s
b
i
a
s i
n
i
t
i
a
l
i
z
e
:
z
e
r
o
s
P
o
l
y
n
o
m
i
a
l
o
r
d
e
r
:
4
M
a
x
n
u
m
s
p
l
i
t
s
:
4
S
t
a
n
d
a
r
d
i
z
e
:
f
a
l
se
La
y
e
r
si
z
e
s
:
2
4
-
17
-
11
S
t
a
n
d
a
r
d
i
z
e
:
t
r
u
e
N
u
m
v
a
r
i
a
b
l
e
s
t
o
s
a
mp
l
e
:
4
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
7
,
No
.
2
,
Feb
r
u
a
r
y
20
25
:
1
37
6
-
1
38
6
1382
T
h
e
ANN
m
o
d
el
th
at
was
d
e
v
elo
p
ed
h
ad
a
to
tal
o
f
f
iv
e
lay
er
s
,
o
n
e
in
p
u
t,
th
r
ee
h
id
d
e
n
an
d
o
n
e
o
u
tp
u
t
la
y
er
.
T
h
e
n
u
m
b
e
r
o
f
n
eu
r
o
n
s
in
ea
ch
la
y
er
was
4
-
24
-
17
-
11
-
1
.
T
h
e
n
u
m
b
er
o
f
n
eu
r
o
n
s
in
th
e
in
p
u
t
an
d
o
u
tp
u
t
la
y
er
ar
e
d
ec
id
e
d
b
y
th
e
n
u
m
b
e
r
o
f
in
p
u
ts
an
d
o
u
tp
u
ts
r
esp
ec
tiv
ely
.
T
h
e
n
u
m
b
er
o
f
h
id
d
en
lay
er
s
an
d
n
u
m
b
er
o
f
n
e
u
r
o
n
s
in
ea
ch
h
i
d
d
en
lay
er
d
ep
en
d
s
o
n
th
e
n
o
n
lin
ea
r
ity
in
th
e
in
p
u
t
o
u
t
p
u
t
r
elatio
n
s
h
ip
an
d
was
o
b
tain
ed
b
y
h
y
p
er
p
ar
am
eter
o
p
tim
izatio
n
.
R
ec
tifie
d
lin
ea
r
u
n
it
(
Re
L
U)
ac
tiv
atio
n
f
u
n
ct
io
n
was
u
s
ed
in
th
e
h
id
d
en
la
y
er
s
an
d
lim
ited
-
m
e
m
o
r
y
b
r
o
y
d
en
–
f
letch
er
–
g
o
ld
f
ar
b
–
s
h
an
n
o
(
L
B
FGS)
s
o
lv
er
i
n
th
e
o
u
tp
u
t
lay
e
r
.
T
h
e
r
esu
lts
o
f
ANN
m
o
d
el
is
s
h
o
wn
in
Fig
u
r
e
4
.
T
h
e
ac
t
u
al
an
d
p
r
e
d
icted
r
esp
o
n
s
e
o
f
th
e
m
o
d
el
is
s
h
o
wn
i
n
Fig
u
r
e
4
(
a)
an
d
th
e
er
r
o
r
h
is
to
g
r
am
in
Fig
u
r
e
4
(
b
)
.
T
h
e
K
f
o
ld
lo
s
s
in
th
e
ANN
m
o
d
el
was
1
4
.
7
3
.
A
SVR
m
o
d
el
with
a
Po
ly
n
o
m
ial
k
er
n
el
was
d
ev
elo
p
ed
f
o
r
p
r
e
d
ictio
n
.
T
h
e
k
er
n
el
f
u
n
ctio
n
ap
p
lies
n
o
n
lin
ea
r
tr
an
s
f
o
r
m
atio
n
to
th
e
d
ata
b
e
f
o
r
e
th
e
m
o
d
el
is
tr
ain
ed
.
T
h
e
o
p
tim
u
m
v
alu
e
o
f
b
o
x
c
o
n
s
tr
a
in
t
an
d
ep
s
ilo
n
wer
e
f
o
u
n
d
to
b
e
3
3
.
2
8
an
d
3
1
.
5
7
5
r
esp
ec
tiv
ely
.
Pre
d
ictio
n
er
r
o
r
s
s
m
aller
th
a
n
e
p
s
ilo
n
ar
e
co
n
s
id
er
ed
as
ze
r
o
.
A
k
er
n
el
s
ca
le
o
f
1
.
8
5
was
u
s
ed
in
th
e
m
o
d
el
to
co
n
tr
o
l
th
e
s
ca
le
o
f
th
e
p
r
ed
icto
r
s
o
n
wh
ich
th
e
k
er
n
el
f
lu
ctu
ates
co
n
s
id
er
ab
ly
.
T
h
e
s
eq
u
en
tial
m
in
im
al
o
p
tim
izatio
n
(
SMO)
alg
o
r
ith
m
was
u
s
ed
as
s
o
lv
er
d
u
r
in
g
th
e
tr
ain
in
g
.
T
h
e
r
esu
lts
o
f
SVR
m
o
d
el
is
s
h
o
wn
in
Fig
u
r
e
5
.
T
h
e
ac
tu
al
an
d
p
r
e
d
icted
r
esp
o
n
s
e
o
f
th
e
m
o
d
el
is
s
h
o
wn
in
Fig
u
r
e
5
(
a)
a
n
d
th
e
er
r
o
r
h
is
to
g
r
am
in
Fig
u
r
e
5
(
b
)
.
T
h
e
K
f
o
ld
lo
s
s
in
th
e
SVR
m
o
d
el
was
2
9
2
1
.
9
.
A
R
T
E
m
o
d
el
was
d
ev
elo
p
ed
b
y
tr
ain
in
g
e
n
s
em
b
les
o
f
r
eg
r
ess
io
n
tr
ee
s
an
d
co
m
b
in
in
g
t
h
eir
r
esu
lts
to
o
b
tain
a
en
s
em
b
le
m
o
d
el
with
h
ig
h
p
er
f
o
r
m
a
n
ce
.
T
h
e
en
s
em
b
le
m
eth
o
d
u
s
ed
f
o
r
r
e
g
r
ess
io
n
f
itti
n
g
was
L
ea
s
t
Sq
u
ar
es
B
o
o
s
tin
g
with
s
h
r
in
k
ag
e
with
a
lear
n
in
g
r
ate
o
f
0
.
1
7
8
.
Du
r
in
g
tr
ain
i
n
g
,
at
ev
e
r
y
s
tep
,
th
e
en
s
em
b
le
tr
ain
s
a
n
ew
lear
n
er
to
r
ed
u
ce
th
e
d
if
f
er
en
ce
b
etwe
en
th
e
o
b
s
er
v
ed
r
esp
o
n
s
e
an
d
th
e
cu
m
u
lativ
e
p
r
ed
ictio
n
o
f
all
lear
n
er
s
in
th
e
e
x
is
tin
g
m
o
d
el.
I
n
th
e
o
p
tim
ized
m
o
d
el,
t
h
e
m
in
im
u
m
leaf
s
ize,
m
ax
im
u
m
n
u
m
b
er
o
f
s
p
lits
an
d
n
u
m
b
er
o
f
v
ar
ia
b
les
to
s
am
p
le
wer
e
s
et
to
4
.
T
h
e
n
u
m
b
er
o
f
lear
n
i
n
g
cy
cles
was
s
et
to
3
6
5
.
I
t
lim
its
th
e
n
u
m
b
er
o
f
tr
ain
in
g
d
ata
s
am
p
l
es
u
s
ed
to
co
m
p
u
te
th
e
o
u
t
p
u
t
o
f
ea
ch
lea
f
n
o
d
e.
T
h
e
r
esu
lt
s
o
f
R
T
E
m
o
d
el
is
s
h
o
wn
in
Fig
u
r
e
6
.
T
h
e
ac
tu
al
an
d
p
r
e
d
icted
r
esp
o
n
s
e
o
f
th
e
m
o
d
el
is
s
h
o
w
n
in
Fig
u
r
e
6
(
a)
an
d
t
h
e
e
r
r
o
r
h
is
to
g
r
am
in
Fig
u
r
e
6
(
b
)
.
T
h
e
K
f
o
ld
lo
s
s
in
th
e
R
T
E
m
o
d
el
was
4
9
5
.
5
5
.
T
h
e
GPR
m
o
d
el
with
a
ze
r
o
-
b
asis
f
u
n
ctio
n
an
d
AR
D
Ma
ter
n
5
/2
k
er
n
el
with
a
s
ca
lin
g
f
ac
to
r
o
f
2
.
0
1
was
d
ev
el
o
p
ed
.
T
h
e
b
asi
s
f
u
n
ctio
n
in
d
icate
s
th
e
s
h
ap
e
o
f
th
e
p
r
io
r
m
e
an
f
u
n
ctio
n
o
f
th
e
m
o
d
el.
T
h
e
k
e
r
n
el
f
u
n
ctio
n
f
i
n
d
s
th
e
co
r
r
el
atio
n
in
th
e
o
u
tp
u
t
v
ar
iab
le
as
a
f
u
n
ctio
n
o
f
th
e
d
is
tan
ce
b
etwe
en
th
e
v
alu
es
o
f
in
p
u
t
v
ar
iab
les
k
ee
p
in
g
th
e
co
r
r
elatio
n
len
g
th
s
ca
les
s
am
e
f
o
r
all
th
e
v
ar
iab
les.
Sig
m
a
is
th
e
in
itial
v
alu
e
o
f
th
e
o
b
s
er
v
atio
n
n
o
is
e
s
tan
d
a
r
d
d
ev
iatio
n
a
n
d
its
v
alu
e
is
s
et
to
0
.
5
2
3
.
T
h
e
r
esu
lts
o
f
GPR
m
o
d
el
is
s
h
o
wn
in
Fig
u
r
e
7
.
T
h
e
ac
tu
al
an
d
p
r
e
d
icted
r
esp
o
n
s
e
f
o
r
th
e
m
o
d
el
is
s
h
o
w
n
in
Fig
u
r
e
7
(
a)
a
n
d
th
e
er
r
o
r
h
is
to
g
r
am
in
Fig
u
r
e
7
(
b
)
.
T
h
e
K
f
o
ld
lo
s
s
in
t
h
e
GPR
m
o
d
el
was 6
.
4
6
.
(
a)
(
b
)
Fig
u
r
e
4
.
ANN
m
o
d
el
(
a)
ac
t
u
al
an
d
p
r
e
d
icted
r
esp
o
n
s
e
an
d
(
b
)
er
r
o
r
h
is
to
g
r
am
with
2
0
b
i
n
s
3.
3
.
Co
m
pa
riso
n o
f
re
g
re
s
s
io
n m
o
dels
T
h
e
r
esu
lts
o
f
th
e
f
o
u
r
o
p
tim
i
ze
d
m
o
d
els
ar
e
co
m
p
a
r
ed
in
t
h
is
s
ec
tio
n
.
T
h
e
p
e
r
f
o
r
m
an
ce
p
ar
am
eter
s
co
n
s
id
er
ed
f
o
r
co
m
p
a
r
is
o
n
ar
e
th
e
tr
ain
in
g
K
Fo
ld
lo
s
s
,
Nu
m
b
er
o
f
iter
atio
n
s
o
f
o
p
tim
i
za
tio
n
,
t
h
e
f
u
n
ctio
n
ev
alu
atio
n
tim
e,
m
ea
n
s
q
u
ar
e
d
er
r
o
r
(
MSE
)
,
R
-
Sq
u
ar
e
d
,
an
d
MA
E
.
T
h
e
tr
ain
in
g
K
f
o
l
d
lo
s
s
is
th
e
m
in
im
u
m
v
alu
e
o
f
o
b
jectiv
e
f
u
n
ctio
n
o
b
tain
ed
at
th
e
en
d
o
f
m
ax
im
u
m
iter
atio
n
s
an
d
f
u
n
ctio
n
e
v
alu
atio
n
tim
e
is
th
e
tim
e
tak
en
f
o
r
ev
alu
atio
n
o
f
th
e
o
b
jectiv
e
f
u
n
ctio
n
d
u
r
i
n
g
h
y
p
e
r
p
ar
am
ete
r
o
p
tim
izat
io
n
.
MSE
was
th
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
Ma
ch
in
e
lea
r
n
in
g
b
a
s
ed
p
r
ed
ictio
n
o
f p
r
o
d
u
ctio
n
u
s
in
g
r
ea
l
… (
F
a
th
ima
R
a
n
i I
r
u
d
a
ya
Ma
r
y
Dia
n
a
)
1383
p
er
f
o
r
m
an
ce
p
ar
am
ete
r
u
s
ed
d
u
r
in
g
tr
ain
in
g
.
R
-
Sq
u
ar
ed
v
alu
e
g
iv
es
th
e
co
ef
f
icien
t
o
f
d
eter
m
in
atio
n
b
y
co
m
p
ar
in
g
th
e
tr
ain
ed
m
o
d
el
with
th
e
m
o
d
el
wh
e
r
e
th
e
r
esp
o
n
s
e
is
co
n
s
tan
t
an
d
eq
u
a
ls
th
e
m
ea
n
o
f
th
e
tr
ain
in
g
r
esp
o
n
s
e.
MA
E
is
an
o
th
er
p
er
f
o
r
m
an
ce
p
a
r
am
eter
th
at
is
s
im
ilar
to
MSE
b
u
t le
s
s
s
en
s
itiv
e
to
o
u
tlier
s
.
T
h
e
v
alu
es
o
f
th
ese
p
a
r
am
ete
r
s
ar
e
tab
u
lated
in
T
ab
le
5
f
o
r
ea
ch
m
o
d
el.
T
h
e
T
r
ai
n
in
g
tim
e
o
f
th
e
m
o
d
el
in
s
ec
o
n
d
s
an
d
th
e
Pre
d
ictio
n
s
p
ee
d
ex
p
r
ess
ed
as
n
u
m
b
er
o
f
o
b
s
er
v
atio
n
s
p
er
s
ec
o
n
d
ar
e
also
tab
u
lated
f
o
r
co
m
p
ar
is
o
n
.
As
s
ee
n
f
r
o
m
th
e
tab
le,
th
e
GPR
m
o
d
el
is
th
e
b
est
p
er
f
o
r
m
in
g
m
o
d
el
with
m
in
im
u
m
MSE
v
alu
e
o
f
6
.
4
6
3
3
,
an
d
MA
E
v
alu
e
o
f
1
.
3
2
1
.
I
t
is
f
o
llo
we
d
b
y
ANN
m
o
d
el,
R
T
E
m
o
d
el
an
d
SVR
m
o
d
el.
T
r
ain
in
g
tim
e
is
a
v
ital
p
ar
am
eter
d
u
r
i
n
g
m
o
d
el
d
ev
elo
p
m
en
t
an
d
it
is
s
ee
n
th
at
th
e
GP
R
m
o
d
el
also
tak
es
m
in
im
u
m
tim
e
f
o
r
tr
ain
in
g
.
(
a)
(
b
)
Fig
u
r
e
5
.
SVR
m
o
d
el
(
a
)
ac
tu
a
l a
n
d
p
r
e
d
icted
r
esp
o
n
s
e
an
d
(
b
)
er
r
o
r
h
is
to
g
r
a
m
with
2
0
b
in
s
(
a)
(
b
)
Fig
u
r
e
6
.
R
T
E
m
o
d
el
(
a)
ac
tu
a
l a
n
d
p
r
e
d
icted
r
esp
o
n
s
e
an
d
(
b
)
er
r
o
r
h
is
to
g
r
a
m
with
2
0
b
in
s
T
h
e
p
r
o
p
o
s
ed
m
o
d
el
wo
u
ld
p
r
o
v
e
to
b
e
v
er
y
u
s
ef
u
l
in
cr
ea
tin
g
r
ef
er
e
n
ce
ch
ar
ts
f
o
r
ass
es
s
in
g
p
r
o
d
u
ctio
n
f
o
r
d
if
f
er
en
t
in
p
u
t
p
ar
am
ete
r
s
.
A
m
ajo
r
p
ar
t
o
f
p
ac
k
ag
in
g
m
ater
ials
is
m
an
u
f
ac
tu
r
ed
i
n
s
tan
d
a
r
d
d
im
en
s
io
n
s
(
wid
th
an
d
le
n
g
th
)
.
Pre
d
ictin
g
th
e
p
r
o
d
u
ctio
n
f
o
r
th
e
s
tan
d
ar
d
d
im
e
n
s
io
n
s
f
o
r
v
ar
y
in
g
g
au
g
e
a
n
d
s
p
ee
d
wo
u
ld
p
r
o
v
id
e
a
r
ea
d
y
m
ad
e
r
ef
er
e
n
ce
to
o
l
f
o
r
th
e
i
n
d
u
s
tr
y
f
o
r
ef
f
icien
t
esti
m
atio
n
o
f
r
u
n
tim
e
an
d
c
o
s
t
b
ef
o
r
e
th
e
s
tar
t
o
f
b
u
l
k
p
r
o
d
u
ctio
n
.
Sam
p
le
p
r
e
d
ictio
n
r
esu
l
ts
u
s
in
g
GPR
m
o
d
el
f
o
r
a
s
tan
d
ar
d
d
im
en
s
io
n
o
f
3
x
4
is
p
r
esen
ted
in
T
ab
le
6
f
o
r
v
ar
y
in
g
g
au
g
e
an
d
s
p
ee
d
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
7
,
No
.
2
,
Feb
r
u
a
r
y
20
25
:
1
37
6
-
1
38
6
1384
(
a)
(
b
)
Fig
u
r
e
7
.
GPR
m
o
d
el
(a
)
ac
tu
a
l a
n
d
p
r
e
d
icted
r
esp
o
n
s
e
an
d
(
b
)
er
r
o
r
h
is
to
g
r
a
m
with
2
0
b
in
s
T
ab
le
5
.
C
o
m
p
a
r
is
o
n
o
f
p
er
f
o
r
m
an
ce
p
ar
am
ete
r
s
M
o
d
e
l
ANN
S
V
R
R
TE
G
P
R
Tr
a
i
n
i
n
g
K
f
o
l
d
l
o
ss
3
.
7
2
3
5
0
.
1
5
6
8
2
6
.
7
4
1
4
0
.
9
0
3
2
3
I
t
e
r
a
t
i
o
n
s
1
0
0
1
0
0
1
0
0
30
F
u
n
c
t
i
o
n
e
v
a
l
u
a
t
i
o
n
t
i
me
1
9
.
5
2
5
3
8
.
1
7
4
8
6
.
9
1
8
2
.
8
9
0
4
M
S
E
1
4
.
7
2
5
0
2
9
2
1
.
9
4
9
5
.
5
4
7
6
6
.
4
6
3
3
R
-
s
q
u
a
r
e
d
0
.
9
9
9
8
0
.
9
8
1
7
0
.
9
9
4
8
0
.
9
9
9
9
M
A
E
4
.
6
7
4
1
8
.
5
3
2
9
.
2
5
5
1
.
3
2
1
T
ab
le
6
.
Sam
p
le
p
r
ed
ictio
n
r
esu
lts
f
o
r
3
x
4
d
im
e
n
s
io
n
G
a
u
g
e
W
i
d
t
h
Le
n
g
t
h
S
p
e
e
d
P
r
o
d
u
c
t
i
o
n
1
8
0
3
4
1
7
2
1
5
0
1
2
0
0
3
4
1
7
2
1
3
5
5
2
2
0
3
4
1
7
2
1
2
3
9
2
4
0
3
4
1
7
2
1
1
4
1
2
6
0
3
4
1
7
2
1
0
4
5
1
8
0
3
4
1
6
5
1
2
1
2
2
0
0
3
4
1
6
5
1
0
8
5
2
2
0
3
4
1
6
5
9
8
7
2
4
0
3
4
1
6
5
9
0
4
2
6
0
3
4
1
6
5
8
3
2
1
8
0
3
4
1
5
8
1
1
7
2
2
0
0
3
4
1
5
8
1
0
4
0
2
2
0
3
4
1
5
8
9
3
1
2
4
0
3
4
1
5
8
8
4
0
2
6
0
3
4
1
5
8
7
7
7
3.
CO
NCLU
SI
O
N
T
h
e
o
b
jectiv
es
o
f
th
is
p
ap
e
r
wer
e
to
d
eter
m
in
e
th
e
in
p
u
t
p
ar
am
eter
s
m
o
s
t
s
u
itab
le
f
o
r
th
e
p
r
ed
ictio
n
o
f
p
r
o
d
u
ctio
n
,
d
ev
elo
p
b
est
p
er
f
o
r
m
in
g
ML
m
o
d
els
f
o
r
p
r
e
d
ictio
n
u
s
in
g
th
e
s
elec
ted
in
p
u
t
p
ar
am
eter
s
with
o
p
tim
ized
h
y
p
er
p
ar
am
eter
s
,
an
d
c
o
m
p
ar
e
th
e
r
esu
lts
o
b
tain
ed
to
id
en
tify
th
e
b
est
m
o
d
el.
Fiv
e
in
p
u
t
p
ar
am
eter
s
wer
e
co
n
s
id
er
e
d
n
am
ely
g
au
g
e
,
wid
th
,
len
g
t
h
,
s
p
ee
d
an
d
tem
p
er
atu
r
e
.
B
ased
o
n
th
e
co
r
r
elatio
n
co
ef
f
icien
ts
it
was
co
n
clu
d
ed
th
at
th
e
in
f
lu
en
ce
o
f
tem
p
er
at
u
r
e
in
th
e
p
r
o
d
u
ctio
n
q
u
a
n
tity
was
in
s
ig
n
if
ican
t
an
d
h
e
n
ce
it
was
elim
in
ated
i
n
th
e
m
o
d
el
d
ev
elo
p
m
en
t.
T
h
e
r
ea
l
-
tim
e
d
ata
co
llected
f
r
o
m
p
r
o
d
u
ctio
n
r
ep
o
r
ts
o
f
a
f
le
x
o
p
r
in
tin
g
u
n
it
was
u
s
ed
to
tr
ain
f
o
u
r
d
is
tin
ct
r
eg
r
e
s
s
io
n
m
o
d
els:
ANN
,
SVR
,
R
T
E
,
an
d
GPR
.
T
h
e
h
y
p
er
p
ar
am
eter
s
o
f
th
e
m
o
d
el
s
wer
e
o
p
tim
ized
b
y
B
ay
esian
o
p
tim
izatio
n
with
f
i
v
ef
o
ld
cr
o
s
s
v
alid
atio
n
.
T
h
e
p
er
f
o
r
m
an
ce
o
f
th
e
m
o
d
elswer
eth
en
e
v
alu
ated
with
cr
o
s
s
v
a
lid
atio
n
to
o
b
tain
th
e
p
er
f
o
r
m
an
ce
m
etr
ics
MSE
,
R
-
s
q
u
ar
ed
v
alu
e,
an
d
MA
E
.
B
ased
o
n
th
e
an
aly
s
is
o
f
r
esu
lts
it
was
o
b
s
er
v
ed
th
at
th
e
GP
R
m
o
d
el
s
to
o
d
o
u
t
i
n
s
ev
er
al
asp
ec
ts
.
Firstl
y
,
it
r
e
q
u
ir
ed
th
e
least
am
o
u
n
t
o
f
ti
m
e
f
o
r
tr
ain
in
g
,
in
d
icatin
g
e
f
f
icien
cy
i
n
m
o
d
el
d
ev
elo
p
m
e
n
t.
T
h
e
r
esu
lts
als
o
h
ig
h
lig
h
ted
th
e
s
u
p
e
r
io
r
ity
o
f
th
e
GPR
m
o
d
el,
s
h
o
wca
s
i
n
g
th
e
lo
west
MSE
,
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
Ma
ch
in
e
lea
r
n
in
g
b
a
s
ed
p
r
ed
ictio
n
o
f p
r
o
d
u
ctio
n
u
s
in
g
r
ea
l
… (
F
a
th
ima
R
a
n
i I
r
u
d
a
ya
Ma
r
y
Dia
n
a
)
1385
h
ig
h
est
R
-
s
q
u
ar
ed
v
alu
e
,
an
d
m
in
im
al
MA
E
v
alu
e.
Fo
llo
win
g
clo
s
ely
was
th
e
ANN
m
o
d
el,
in
d
icatin
g
its
ef
f
ec
tiv
en
ess
in
p
r
e
d
ictin
g
p
r
o
d
u
ctio
n
o
u
tp
u
t
as
well.
T
h
is
v
er
s
atility
d
em
o
n
s
tr
ated
th
e
m
o
d
el'
s
ca
p
ab
ilit
y
to
p
r
o
v
id
e
ac
cu
r
ate
esti
m
atio
n
s
o
f
r
u
n
tim
e
a
n
d
ass
o
ciate
d
co
s
ts
,
m
ak
es it a
v
alu
ab
le
to
o
l f
o
r
p
r
o
d
u
ctio
n
p
lan
n
in
g
an
d
o
p
tim
izatio
n
.
ACK
NO
WL
E
DG
E
M
E
NT
S
T
h
e
a
u
t
h
o
r
s
th
a
n
k
Hep
h
zi
Gr
ap
h
ics
So
lu
tio
n
s
,
B
an
g
alo
r
e,
Kar
n
ata
k
a,
I
n
d
ia
f
o
r
p
r
o
v
id
in
g
d
ata
s
u
p
p
o
r
t f
o
r
th
e
w
o
r
k
.
RE
F
E
R
E
NC
E
S
[
1
]
E.
B
r
y
n
j
o
l
f
sso
n
,
L
.
H
i
t
t
,
a
n
d
H
.
K
i
m
,
“
S
t
r
e
n
g
t
h
i
n
n
u
mb
e
r
s:
h
o
w
d
o
e
s
d
a
t
a
-
d
r
i
v
e
n
d
e
c
i
s
i
o
n
-
ma
k
i
n
g
a
f
f
e
c
t
f
i
r
m
p
e
r
f
o
r
ma
n
c
e
?
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
I
n
f
o
rm
a
t
i
o
n
S
y
s
t
e
m
s
2
0
1
1
,
I
C
I
S
2
0
1
1
,
v
o
l
.
1
,
p
p
.
5
4
1
–
5
5
8
,
2
0
1
1
,
d
o
i
:
1
0
.
2
1
3
9
/
ssr
n
.
1
8
1
9
4
8
6
.
[
2
]
J
.
P
a
s
c
h
e
n
,
J
.
K
i
e
t
z
m
a
n
n
,
a
n
d
T
.
C
.
K
i
e
t
z
m
a
n
n
,
“
A
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
(
A
I
)
a
n
d
i
t
s
i
m
p
l
i
c
a
t
i
o
n
s
f
o
r
m
a
r
k
e
t
k
n
o
w
l
e
d
g
e
i
n
B
2
B
m
a
r
k
e
t
i
n
g
,
”
J
o
u
r
n
a
l
o
f
B
u
s
i
n
e
s
s
a
n
d
I
n
d
u
s
t
r
i
a
l
M
a
r
k
e
t
i
n
g
,
v
o
l
.
3
4
,
n
o
.
7
,
p
p
.
1
4
1
0
–
1
4
1
9
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
8
/
J
B
I
M
-
10
-
2
0
1
8
-
0
2
9
5
.
[
3
]
F
.
T
a
o
,
Q
.
Q
i
,
A
.
L
i
u
,
a
n
d
A
.
K
u
si
a
k
,
“
D
a
t
a
-
d
r
i
v
e
n
smar
t
ma
n
u
f
a
c
t
u
r
i
n
g
,
”
J
o
u
r
n
a
l
o
f
M
a
n
u
f
a
c
t
u
ri
n
g
S
y
s
t
e
m
s
,
v
o
l
.
4
8
,
p
p
.
1
5
7
–
1
6
9
,
J
u
l
.
2
0
1
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
ms
y
.
2
0
1
8
.
0
1
.
0
0
6
.
[
4
]
A
.
M
.
U
.
D
.
K
h
a
n
d
a
y
,
S
.
T.
R
a
b
a
n
i
,
Q
.
R
.
K
h
a
n
,
N
.
R
o
u
f
,
a
n
d
M
.
M
o
h
i
U
d
D
i
n
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
b
a
se
d
a
p
p
r
o
a
c
h
e
s
f
o
r
d
e
t
e
c
t
i
n
g
C
O
V
I
D
-
1
9
u
si
n
g
c
l
i
n
i
c
a
l
t
e
x
t
d
a
t
a
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
(
S
i
n
g
a
p
o
r
e
)
,
v
o
l
.
1
2
,
n
o
.
3
,
p
p
.
7
3
1
–
7
3
9
,
J
u
n
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
0
7
/
s4
1
8
7
0
-
0
2
0
-
0
0
4
9
5
-
9.
[
5
]
S
.
S
h
i
d
n
a
l
,
M
.
V
.
La
t
t
e
,
a
n
d
A
.
K
a
p
o
o
r
,
“
C
r
o
p
y
i
e
l
d
p
r
e
d
i
c
t
i
o
n
:
t
w
o
-
t
i
e
r
e
d
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
m
o
d
e
l
a
p
p
r
o
a
c
h
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
(
S
i
n
g
a
p
o
re)
,
v
o
l
.
1
3
,
n
o
.
5
,
p
p
.
1
9
8
3
–
1
9
9
1
,
N
o
v
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
0
7
/
s4
1
8
7
0
-
0
1
9
-
0
0
3
7
5
-
x.
[
6
]
S
.
S
.
C
h
o
u
d
h
u
r
y
,
S
.
N
.
M
o
h
a
n
t
y
,
a
n
d
A
.
K
.
Ja
g
a
d
e
v
,
“
M
u
l
t
i
mo
d
a
l
t
r
u
s
t
b
a
s
e
d
r
e
c
o
mm
e
n
d
e
r
s
y
s
t
e
m
w
i
t
h
mac
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
e
s
f
o
r
mo
v
i
e
r
e
c
o
mm
e
n
d
a
t
i
o
n
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
(
S
i
n
g
a
p
o
re)
,
v
o
l
.
1
3
,
n
o
.
2
,
p
p
.
4
7
5
–
4
8
2
,
J
a
n
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
0
7
/
s4
1
8
7
0
-
0
2
0
-
0
0
5
5
3
-
2.
[
7
]
S
.
G
h
o
sh
,
“
I
d
e
n
t
i
f
y
i
n
g
c
l
i
c
k
b
a
i
t
s
u
si
n
g
v
a
r
i
o
u
s
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
(
S
i
n
g
a
p
o
r
e
)
,
v
o
l
.
1
3
,
n
o
.
3
,
p
p
.
1
2
3
5
–
1
2
4
2
,
M
a
y
2
0
2
1
,
d
o
i
:
1
0
.
1
0
0
7
/
s
4
1
8
7
0
-
0
2
0
-
0
0
4
7
3
-
1.
[
8
]
T
.
W
u
e
s
t
,
D
.
W
e
i
m
e
r
,
C
.
I
r
g
e
n
s
,
a
n
d
K
.
D
.
T
h
o
b
e
n
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
i
n
m
a
n
u
f
a
c
t
u
r
i
n
g
:
a
d
v
a
n
t
a
g
e
s
,
c
h
a
l
l
e
n
g
e
s
,
a
n
d
a
p
p
l
i
c
a
t
i
o
n
s
,
”
P
r
o
d
u
c
t
i
o
n
a
n
d
M
a
n
u
f
a
c
t
u
r
i
n
g
R
e
s
e
a
r
c
h
,
v
o
l
.
4
,
n
o
.
1
,
p
p
.
2
3
–
4
5
,
J
a
n
.
2
0
1
6
,
d
o
i
:
1
0
.
1
0
8
0
/
2
1
6
9
3
2
7
7
.
2
0
1
6
.
1
1
9
2
5
1
7
.
[
9
]
C
.
M
o
r
a
r
i
u
,
O
.
M
o
r
a
r
i
u
,
S
.
R
ă
i
l
e
a
n
u
,
a
n
d
T.
B
o
r
a
n
g
i
u
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
f
o
r
p
r
e
d
i
c
t
i
v
e
sc
h
e
d
u
l
i
n
g
a
n
d
r
e
so
u
r
c
e
a
l
l
o
c
a
t
i
o
n
i
n
l
a
r
g
e
s
c
a
l
e
m
a
n
u
f
a
c
t
u
r
i
n
g
sy
st
e
ms,”
C
o
m
p
u
t
e
rs
i
n
I
n
d
u
st
ry
,
v
o
l
.
1
2
0
,
p
.
1
0
3
2
4
4
,
S
e
p
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
mp
i
n
d
.
2
0
2
0
.
1
0
3
2
4
4
.
[
1
0
]
P
.
P
r
i
o
r
e
,
A
.
G
ó
me
z
,
R
.
P
i
n
o
,
a
n
d
R
.
R
o
s
i
l
l
o
,
“
D
y
n
a
mi
c
s
c
h
e
d
u
l
i
n
g
o
f
m
a
n
u
f
a
c
t
u
r
i
n
g
sy
st
e
ms u
s
i
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
:
a
n
u
p
d
a
t
e
d
r
e
v
i
e
w
,
”
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
f
o
r
E
n
g
i
n
e
e
r
i
n
g
D
e
s
i
g
n
,
An
a
l
y
s
i
s
a
n
d
M
a
n
u
f
a
c
t
u
r
i
n
g
:
AI
ED
A
M
,
v
o
l
.
2
8
,
n
o
.
1
,
p
p
.
8
3
–
9
7
,
Ja
n
.
2
0
1
4
,
d
o
i
:
1
0
.
1
0
1
7
/
S
0
8
9
0
0
6
0
4
1
3
0
0
0
5
1
6
.
[
1
1
]
J.
S
c
h
m
i
t
t
,
J.
B
ö
n
i
g
,
T.
B
o
r
g
g
r
ä
f
e
,
G
.
B
e
i
t
i
n
g
e
r
,
a
n
d
J.
D
e
u
s
e
,
“
P
r
e
d
i
c
t
i
v
e
mo
d
e
l
-
b
a
s
e
d
q
u
a
l
i
t
y
i
n
sp
e
c
t
i
o
n
u
si
n
g
mac
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
e
d
g
e
c
l
o
u
d
c
o
m
p
u
t
i
n
g
,
”
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
ri
n
g
I
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
4
5
,
p
.
1
0
1
1
0
1
,
A
u
g
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
e
i
.
2
0
2
0
.
1
0
1
1
0
1
.
[
1
2
]
M
.
H
.
A
b
i
d
i
,
H
.
A
l
k
h
a
l
e
f
a
h
,
M
.
K
.
M
o
h
a
mm
e
d
,
U
.
U
m
e
r
,
a
n
d
J.
E
.
A
.
Q
u
d
e
i
r
i
,
“
O
p
t
i
ma
l
sc
h
e
d
u
l
i
n
g
o
f
f
l
e
x
i
b
l
e
ma
n
u
f
a
c
t
u
r
i
n
g
sy
st
e
m
u
s
i
n
g
i
mp
r
o
v
e
d
l
i
o
n
-
b
a
s
e
d
h
y
b
r
i
d
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
,
”
I
EEE
Ac
c
e
ss
,
v
o
l
.
8
,
p
p
.
9
6
0
8
8
–
9
6
1
1
4
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
0
.
2
9
9
7
6
6
3
.
[
1
3
]
S
.
T.
S
.
B
u
k
k
a
p
a
t
n
a
m
,
K
.
A
f
r
i
n
,
D
.
D
a
v
e
,
a
n
d
S
.
R
.
T.
K
u
mar
a
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
A
I
f
o
r
l
o
n
g
-
t
e
r
m
f
a
u
l
t
p
r
o
g
n
o
s
i
s
i
n
c
o
m
p
l
e
x
ma
n
u
f
a
c
t
u
r
i
n
g
s
y
s
t
e
ms
,
”
C
I
RP
A
n
n
a
l
s
,
v
o
l
.
6
8
,
n
o
.
1
,
p
p
.
4
5
9
–
4
6
2
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
i
r
p
.
2
0
1
9
.
0
4
.
1
0
4
.
[
1
4
]
P
.
P
r
i
o
r
e
,
B
.
P
o
n
t
e
,
J.
P
u
e
n
t
e
,
a
n
d
A
.
G
ó
m
e
z
,
“
Le
a
r
n
i
n
g
-
b
a
se
d
sc
h
e
d
u
l
i
n
g
o
f
f
l
e
x
i
b
l
e
m
a
n
u
f
a
c
t
u
r
i
n
g
s
y
st
e
m
s
u
s
i
n
g
e
n
se
mb
l
e
met
h
o
d
s,
”
C
o
m
p
u
t
e
r
s
a
n
d
I
n
d
u
st
ri
a
l
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
1
2
6
,
p
p
.
2
8
2
–
2
9
1
,
D
e
c
.
2
0
1
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
i
e
.
2
0
1
8
.
0
9
.
0
3
4
.
[
1
5
]
O
.
K
o
c
a
,
O
.
T.
K
a
y
m
a
k
c
i
,
a
n
d
M
.
M
e
r
c
i
me
k
,
“
A
d
v
a
n
c
e
d
p
r
e
d
i
c
t
i
v
e
ma
i
n
t
e
n
a
n
c
e
w
i
t
h
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
f
a
i
l
u
r
e
e
s
t
i
m
a
t
i
o
n
i
n
i
n
d
u
st
r
i
a
l
p
a
c
k
a
g
i
n
g
r
o
b
o
t
s,
”
i
n
2
0
2
0
1
5
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
D
e
v
e
l
o
p
m
e
n
t
a
n
d
A
p
p
l
i
c
a
t
i
o
n
S
y
st
e
m
s,
D
AS
2
0
2
0
-
Pro
c
e
e
d
i
n
g
s
,
M
a
y
2
0
2
0
,
v
o
l
.
3
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
D
A
S
4
9
6
1
5
.
2
0
2
0
.
9
1
0
8
9
1
3
.
[
1
6
]
M
.
B
e
r
t
o
l
i
n
i
,
D
.
M
e
z
z
o
g
o
r
i
,
M
.
N
e
r
o
n
i
,
a
n
d
F
.
Za
mm
o
r
i
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
f
o
r
i
n
d
u
st
r
i
a
l
a
p
p
l
i
c
a
t
i
o
n
s
:
a
c
o
m
p
r
e
h
e
n
s
i
v
e
l
i
t
e
r
a
t
u
r
e
r
e
v
i
e
w
,
”
Ex
p
e
r
t
S
y
s
t
e
m
s
w
i
t
h
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
7
5
,
p
.
1
1
4
8
2
0
,
A
u
g
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
sw
a
.
2
0
2
1
.
1
1
4
8
2
0
.
[
1
7
]
M
.
S
h
a
r
p
,
R
.
A
k
,
a
n
d
T.
H
e
d
b
e
r
g
,
“
A
su
r
v
e
y
o
f
t
h
e
a
d
v
a
n
c
i
n
g
u
s
e
a
n
d
d
e
v
e
l
o
p
me
n
t
o
f
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
i
n
sm
a
r
t
man
u
f
a
c
t
u
r
i
n
g
,
”
J
o
u
rn
a
l
o
f
M
a
n
u
f
a
c
t
u
ri
n
g
S
y
st
e
m
s
,
v
o
l
.
4
8
,
p
p
.
1
7
0
–
1
7
9
,
J
u
l
.
2
0
1
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
msy
.
2
0
1
8
.
0
2
.
0
0
4
.
[
1
8
]
R
.
D
e
Le
o
n
e
,
M
.
P
i
e
t
r
i
n
i
,
a
n
d
A
.
G
i
o
v
a
n
n
e
l
l
i
,
“
P
h
o
t
o
v
o
l
t
a
i
c
e
n
e
r
g
y
p
r
o
d
u
c
t
i
o
n
f
o
r
e
c
a
s
t
u
si
n
g
s
u
p
p
o
r
t
v
e
c
t
o
r
r
e
g
r
e
ssi
o
n
,
”
N
e
u
r
a
l
C
o
m
p
u
t
i
n
g
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
2
6
,
n
o
.
8
,
p
p
.
1
9
5
5
–
1
9
6
2
,
M
a
r
.
2
0
1
5
,
d
o
i
:
1
0
.
1
0
0
7
/
s
0
0
5
2
1
-
0
1
5
-
1
8
4
2
-
y.
[
1
9
]
Y
.
S
u
z
u
k
i
,
Y
.
K
a
n
e
d
a
,
a
n
d
H
.
M
i
n
e
n
o
,
“
A
n
a
l
y
si
s
o
f
s
u
p
p
o
r
t
v
e
c
t
o
r
r
e
g
r
e
s
si
o
n
m
o
d
e
l
f
o
r
mi
c
r
o
m
e
t
e
o
r
o
l
o
g
i
c
a
l
d
a
t
a
p
r
e
d
i
c
t
i
o
n
,
”
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
3
,
n
o
.
2
,
p
p
.
3
7
–
4
8
,
M
a
r
.
2
0
1
5
,
d
o
i
:
1
0
.
1
3
1
8
9
/
c
s
i
t
.
2
0
1
5
.
0
3
0
2
0
2
.
[
2
0
]
J.
H
.
H
a
n
a
n
d
S
.
Y
.
C
h
i
,
“
C
o
n
si
d
e
r
a
t
i
o
n
o
f
m
a
n
u
f
a
c
t
u
r
i
n
g
d
a
t
a
t
o
a
p
p
l
y
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
me
t
h
o
d
s
f
o
r
p
r
e
d
i
c
t
i
v
e
ma
n
u
f
a
c
t
u
r
i
n
g
,
”
i
n
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
U
b
i
q
u
i
t
o
u
s
a
n
d
F
u
t
u
re
N
e
t
w
o
rks
,
I
C
U
FN
,
J
u
l
.
2
0
1
6
,
v
o
l
.
2
0
1
6
-
A
u
g
u
s
t
,
p
p
.
1
0
9
–
1
1
3
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
U
F
N
.
2
0
1
6
.
7
5
3
6
9
9
5
.
[
2
1
]
J.
L
.
Lo
y
e
r
,
E.
H
e
n
r
i
q
u
e
s,
M
.
F
o
n
t
u
l
,
a
n
d
S
.
W
i
se
a
l
l
,
“
C
o
m
p
a
r
i
so
n
o
f
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
m
e
t
h
o
d
s
a
p
p
l
i
e
d
t
o
t
h
e
e
s
t
i
m
a
t
i
o
n
o
f
man
u
f
a
c
t
u
r
i
n
g
c
o
st
o
f
j
e
t
e
n
g
i
n
e
c
o
mp
o
n
e
n
t
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
Ec
o
n
o
m
i
c
s
,
v
o
l
.
1
7
8
,
p
p
.
1
0
9
–
1
1
9
,
A
u
g
.
2
0
1
6
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
j
p
e
.
2
0
1
6
.
0
5
.
0
0
6
.
[
2
2
]
M
.
A
.
R
a
mess
u
r
a
n
d
S
.
D
.
N
a
g
o
w
a
h
,
“
A
p
r
e
d
i
c
t
i
v
e
mo
d
e
l
t
o
e
s
t
i
m
a
t
e
e
f
f
o
r
t
i
n
a
s
p
r
i
n
t
u
si
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s,”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
(
S
i
n
g
a
p
o
r
e
)
,
v
o
l
.
1
3
,
n
o
.
3
,
p
p
.
1
1
0
1
–
1
1
1
0
,
A
p
r
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
0
7
/
s
4
1
8
7
0
-
0
2
1
-
0
0
6
6
9
-
z.
[
2
3
]
J.
M
a
h
a
j
a
n
,
K
.
B
a
n
a
l
,
a
n
d
S
.
M
a
h
a
j
a
n
,
“
E
st
i
ma
t
i
o
n
o
f
c
r
o
p
p
r
o
d
u
c
t
i
o
n
u
s
i
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s
:
a
c
a
se
s
t
u
d
y
o
f
J&
K
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
(
S
i
n
g
a
p
o
re)
,
v
o
l
.
1
3
,
n
o
.
4
,
p
p
.
1
4
4
1
–
1
4
4
8
,
M
a
y
2
0
2
1
,
d
o
i
:
1
0
.
1
0
0
7
/
s
4
1
8
7
0
-
0
2
1
-
0
0
6
5
3
-
7.
[
2
4
]
D
.
W
u
,
C
.
J
e
n
n
i
n
g
s,
J.
Te
r
p
e
n
n
y
,
R
.
X
.
G
a
o
,
a
n
d
S
.
K
u
mar
a
,
“
A
c
o
m
p
a
r
a
t
i
v
e
st
u
d
y
o
n
mac
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms
f
o
r
smar
t
man
u
f
a
c
t
u
r
i
n
g
:
t
o
o
l
w
e
a
r
p
r
e
d
i
c
t
i
o
n
u
si
n
g
r
a
n
d
o
m
f
o
r
e
st
s
,
”
J
o
u
r
n
a
l
o
f
M
a
n
u
f
a
c
t
u
ri
n
g
S
c
i
e
n
c
e
a
n
d
En
g
i
n
e
e
ri
n
g
,
T
r
a
n
s
a
c
t
i
o
n
s
o
f
t
h
e
A
S
M
E
,
v
o
l
.
1
3
9
,
n
o
.
7
,
A
p
r
.
2
0
1
7
,
d
o
i
:
1
0
.
1
1
1
5
/
1
.
4
0
3
6
3
5
0
.
[
2
5
]
F
.
Li
e
t
a
l
.
,
“
E
n
se
mb
l
e
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
s
y
s
t
e
ms
f
o
r
t
h
e
e
s
t
i
m
a
t
i
o
n
o
f
st
e
e
l
q
u
a
l
i
t
y
c
o
n
t
r
o
l
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
-
2
0
1
8
I
EE
E
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
B
i
g
D
a
t
a
,
Bi
g
D
a
t
a
2
0
1
8
,
D
e
c
.
2
0
1
8
,
p
p
.
2
2
4
5
–
2
2
5
2
,
d
o
i
:
1
0
.
1
1
0
9
/
B
i
g
D
a
t
a
.
2
0
1
8
.
8
6
2
2
5
8
3
.
Evaluation Warning : The document was created with Spire.PDF for Python.