I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
pu
t
er
E
ng
ineering
(
I
J
E
CE
)
Vo
l.
15
,
No
.
2
,
A
p
r
il
20
25
,
p
p
.
2
0
5
5
~
2
0
6
9
I
SS
N:
2088
-
8
7
0
8
,
DOI
:
1
0
.
1
1
5
9
1
/ijece.
v
15
i
2
.
pp
2
0
5
5
-
2
0
6
9
2055
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
O
bje
ct
retr
i
ev
a
l ana
ly
sis
on pla
stic
bo
tt
le
wa
ste re
cy
cling
-
ba
sed
ima
g
e control us
i
ng
conv
ex
hull
al
g
o
rithm and a
uto
regres
siv
e
integra
ted
mo
v
in
g
av
erag
e predict
i
o
n method
M
a
risa
1,
2
,
Aziz
ul Az
ha
r
Ra
m
li
1
,
M
o
hd
F
a
rha
n M
d F
u
d
ze
e
1
,
Z
ub
a
ile
Ab
du
lla
h
1
1
F
a
c
u
l
t
y
o
f
C
o
mp
u
t
e
r
S
c
i
e
n
c
e
a
n
d
I
n
f
o
r
mat
i
o
n
Te
c
h
n
o
l
o
g
y
,
U
n
i
v
e
r
si
t
i
Tu
n
H
u
sei
n
O
n
n
M
a
l
a
y
si
a
,
B
a
t
u
P
a
h
a
t
,
M
a
l
a
y
si
a
2
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
mat
i
c
s
E
n
g
i
n
e
e
r
i
n
g
,
F
a
c
u
l
t
y
o
f
I
n
f
o
r
ma
t
i
o
n
T
e
c
h
n
o
l
o
g
y
a
n
d
D
i
g
i
t
a
l
,
B
a
n
i
S
a
l
e
h
U
n
i
v
e
r
s
i
t
y
,
B
e
k
a
s
i
,
I
n
d
o
n
e
s
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
l 3
,
2
0
2
4
R
ev
is
ed
Oct
2
4
,
2
0
2
4
Acc
ep
ted
Oct
3
1
,
2
0
2
4
In
In
d
o
n
e
sia
,
p
las
ti
c
g
a
r
b
a
g
e
b
o
tt
les
a
re
th
e
m
o
st
c
o
m
m
o
n
so
rt
o
f
wa
ste
.
G
iv
e
n
th
a
t
wa
ste
is
e
x
p
e
c
ted
t
o
g
ro
w
a
n
n
u
a
ll
y
,
m
a
n
a
g
i
n
g
p
las
ti
c
wa
ste
is
a
m
a
jo
r
c
h
a
ll
e
n
g
e
.
T
h
e
re
su
lt
s
o
f
t
h
e
stu
d
y
we
re
a
c
h
iev
e
d
b
y
c
o
m
p
a
rin
g
th
e
re
fe
re
n
c
e
,
wh
ich
wa
s
a
c
o
ll
e
c
ti
o
n
o
f
m
a
n
u
a
ll
y
c
re
a
ted
c
o
n
to
u
r
ima
g
e
s,
with
5
0
se
ts
o
f
v
o
rtex
ima
g
e
s
wit
h
d
iffere
n
t
f
o
rm
s
a
n
d
v
o
r
tex
a
re
a
s
a
s
e
x
p
e
rime
n
tal
o
b
jec
ts.
Th
e
re
su
l
ts
in
d
ica
te
th
a
t
t
h
e
su
g
g
e
ste
d
a
p
p
ro
a
c
h
re
p
o
rts
a
m
e
a
n
e
rro
r
o
f
2
.
8
4
%
,
a
c
o
rre
latio
n
c
o
e
fficie
n
t
o
f
0
.
9
9
6
5
,
a
n
d
a
ro
o
t
m
e
a
n
sq
u
a
re
e
rro
r
o
f
0
.
2
9
0
3
wh
e
n
c
o
m
p
a
re
d
t
o
t
h
e
m
a
n
u
a
l
e
x
trac
ti
o
n
m
e
th
o
d
.
Th
e
se
fi
n
d
i
n
g
s
imp
l
y
th
a
t
t
h
e
e
x
trac
t
a
re
a
d
e
term
in
e
d
b
y
th
e
p
ro
c
e
d
u
re
o
u
t
li
n
e
d
in
t
h
is
re
se
a
rc
h
is
m
o
re
a
c
c
u
ra
te
a
n
d
n
e
a
re
r
to
th
e
a
c
tu
a
l
v
a
lu
e
s.
Th
e
p
ro
p
o
se
d
m
e
th
o
d
c
a
n
th
e
re
fo
re
b
e
u
se
d
in
p
lac
e
o
f
th
e
t
ra
d
it
io
n
a
l
p
ro
c
e
ss
fo
r
in
v
e
stig
a
ti
n
g
c
o
o
li
n
g
p
a
ra
m
e
ters
th
ro
u
g
h
m
a
n
u
a
l
tes
t
in
g
.
Wi
t
h
m
e
a
su
re
m
e
n
t
v
a
l
u
e
s
m
e
a
n
a
b
s
o
lu
te
p
e
rc
e
n
tag
e
e
rr
o
r
(
M
APE
)
=
1
2
1
,
8
4
2
,
m
e
a
n
a
b
so
lu
te
d
e
v
iatio
n
(
M
A
D
)
=
2
0
,
1
4
0
,
a
n
d
m
e
a
n
sq
u
a
re
d
d
e
v
iati
o
n
(
MSD
)
=
7
7
6
,
7
1
2
,
t
h
e
tren
d
a
n
a
ly
sis
o
f
p
las
ti
c
b
o
tt
les
fo
r
au
to
r
eg
r
ess
iv
e
in
teg
r
ated
m
o
v
in
g
av
er
a
g
e
(
ARIMA
)
m
o
d
e
li
n
g
lea
d
s
to
t
h
e
c
o
n
c
lu
si
o
n
th
a
t
t
h
e
wa
ste
fro
m
p
las
ti
c
b
o
tt
l
e
s
will
c
o
n
ti
n
u
e
to
rise
a
n
n
u
a
ll
y
a
n
d
th
a
t
e
ffo
rts
m
u
st
b
e
m
a
d
e
t
o
a
d
d
re
ss
th
is
tren
d
wi
th
k
n
o
wle
d
g
e
a
n
d
wa
ste
re
c
y
c
li
n
g
tec
h
n
o
l
o
g
y
.
P
las
ti
c
th
a
t
is ad
v
a
n
tag
e
o
u
s t
o
i
n
d
u
stry
a
n
d
so
c
iety
.
K
ey
w
o
r
d
s
:
Au
to
r
eg
r
ess
iv
e
in
teg
r
ated
m
o
v
in
g
av
er
ag
e
C
o
n
v
ex
h
u
ll
I
m
ag
e
Plas
tic
b
o
ttle
Pre
d
ictio
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
:
Ma
r
is
a
Dep
ar
tm
en
t o
f
I
n
f
o
r
m
atics E
n
g
in
ee
r
in
g
,
Facu
lty
o
f
I
n
f
o
r
m
at
io
n
T
ec
h
n
o
lo
g
y
an
d
Dig
ital
,
B
an
i Sale
h
Un
iv
er
s
ity
Ma
jo
r
M.
Hasib
u
an
Stre
et
6
8
,
E
ast B
ek
asi 1
7
1
1
3
,
W
est J
av
a,
I
n
d
o
n
esia
E
m
ail:
m
ar
is
a@
u
b
s
.
ac
.
id
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
T
o
d
ay
'
s
g
lo
b
aliza
tio
n
an
d
r
ap
id
tech
n
o
lo
g
ical
d
e
v
e
lo
p
m
en
t
h
av
e
e
x
p
lain
ed
all
m
ea
n
s
o
f
m
ea
n
in
g
u
n
d
er
th
e
th
e
o
r
y
o
f
co
n
v
ex
h
u
ll
alg
o
r
ith
m
.
Acc
o
r
d
in
g
to
o
n
e
d
ef
in
itio
n
,
a
co
n
v
ex
h
u
ll
alg
o
r
ith
m
is
an
y
v
e
r
b
al
a
n
d
v
is
u
al
s
em
io
tic
to
o
l
th
at
m
ay
b
e
u
s
ed
to
id
en
tify
th
e
d
if
f
e
r
en
t
k
in
d
s
an
d
d
eg
r
ee
s
o
f
d
ialo
g
ic
in
v
o
lv
em
e
n
t
in
a
tex
t
[
1
]
.
C
o
n
v
ex
h
u
ll
alg
o
r
ith
m
s
ar
e
u
s
ef
u
l
f
o
r
lear
n
in
g
.
B
y
h
ig
h
lig
h
ti
n
g
th
e
v
ar
io
u
s
way
s
th
at
m
ea
n
in
g
is
cr
ea
ted
in
tex
ts
an
d
h
o
w
p
ar
ticu
lar
d
ec
is
i
o
n
s
h
elp
to
ac
co
m
p
lis
h
in
ten
d
ed
co
m
m
u
n
icativ
e
o
b
jectiv
es,
th
e
co
n
v
ex
h
u
ll
alg
o
r
ith
m
ap
p
r
o
ac
h
s
ee
k
s
to
cr
ea
te
a
p
r
o
d
u
ct
o
f
k
n
o
wled
g
ea
b
le
r
ea
d
er
s
an
d
p
r
o
d
u
ce
r
s
o
f
co
n
v
ex
h
u
ll
alg
o
r
ith
m
tex
ts
[
2
]
.
Ad
d
itio
n
al
ly
,
a
co
n
v
e
x
h
u
ll
alg
o
r
ith
m
tech
n
iq
u
e
en
s
u
r
es
in
clu
s
iv
ity
th
at
f
o
s
ter
s
in
tellectu
al
ex
ce
llen
ce
an
d
g
iv
es
u
s
er
s
a
wid
e
r
a
n
g
e
o
f
lear
n
in
g
o
p
p
o
r
t
u
n
ities
b
y
ac
co
m
m
o
d
atin
g
d
if
f
e
r
en
ce
.
B
ased
o
n
d
o
m
in
a
n
t
u
n
d
er
s
tan
d
i
n
g
s
,
en
ter
p
r
is
es
ca
n
u
s
e
a
co
n
v
ex
h
u
ll
alg
o
r
ith
m
tech
n
iq
u
e
to
s
elf
-
s
elec
t
lear
n
i
n
g
o
b
jects,
o
r
r
ep
r
esen
tatio
n
s
,
th
at
o
p
tim
ally
f
it
th
eir
m
o
d
al
p
r
ef
er
en
ce
s
[
3
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
2
,
Ap
r
il
20
25
:
2
0
5
5
-
2
0
6
9
2056
T
h
is
en
ab
les
th
e
in
d
u
s
tr
y
t
o
a
cc
o
m
m
o
d
ate
v
ar
i
o
u
s
em
p
lo
y
e
es'
n
ee
d
s
in
a
lear
n
in
g
en
v
ir
o
n
m
en
t
s
o
th
ey
ca
n
co
m
p
r
eh
e
n
d
t
h
e
g
o
o
d
s
th
at
will
b
e
ad
v
er
tis
ed
an
d
s
o
ld
[
4
]
.
Glo
b
al
ch
an
g
es
d
u
e
to
r
ap
id
tech
n
o
lo
g
ica
l
ad
v
an
ce
s
,
c
o
m
p
etitio
n
b
etwe
en
in
d
u
s
tr
ies
is
b
ec
o
m
in
g
in
cr
ea
s
in
g
ly
ag
g
r
ess
iv
e
to
s
u
r
v
iv
e.
T
ec
h
n
o
lo
g
ical
in
n
o
v
atio
n
to
b
u
s
in
ess
m
an
ag
em
en
t
is
to
r
ed
u
ce
p
r
o
d
u
ct
co
s
ts
,
im
p
r
o
v
e
f
u
n
ctio
n
ality
a
n
d
co
n
s
tan
tly
in
cr
ea
s
e
co
m
p
etitiv
e
s
tr
en
g
t
h
[
5
]
.
I
n
d
u
s
tr
ies
to
d
ay
d
esire
to
m
ain
tain
th
e
f
u
n
ctio
n
al
p
er
f
o
r
m
an
ce
o
f
p
r
o
d
u
cts
with
in
th
e
lim
its
o
f
ac
ce
p
te
d
s
tan
d
ar
d
s
an
d
r
e
d
u
ce
p
r
o
d
u
ctio
n
co
s
ts
.
I
n
d
u
s
tr
ies
n
ee
d
to
m
ee
t
c
u
s
to
m
er
d
em
a
n
d
s
to
b
e
m
o
r
e
ef
f
ec
tiv
e
an
d
co
n
s
is
ten
t
in
im
p
r
o
v
in
g
p
r
o
d
u
ct
p
er
f
o
r
m
an
ce
[
6
]
.
T
o
d
a
y
,
in
f
o
r
m
atio
n
an
d
co
m
m
u
n
icatio
n
tech
n
o
lo
g
ies
(
I
C
T
s
)
in
f
lu
e
n
ce
th
e
wa
y
p
eo
p
le
liv
e,
c
o
m
m
u
n
icate
,
wo
r
k
a
n
d
p
la
y
.
T
h
is
is
b
ec
au
s
e
tech
n
o
lo
g
ical
elem
en
ts
ar
e
f
o
u
n
d
in
alm
o
s
t
ev
er
y
th
in
g
[
7
]
.
B
u
s
in
ess
es
r
ely
s
ig
n
if
ican
tly
o
n
m
o
b
ile
d
e
v
ices
an
d
th
e
in
ter
n
et
to
o
b
tain
in
f
o
r
m
atio
n
a
n
d
ac
ce
s
s
a
v
ar
iety
o
f
k
n
o
wled
g
e
s
o
u
r
ce
s
at
th
e
t
o
u
ch
o
f
a
s
cr
ee
n
.
A
g
r
o
win
g
d
is
cu
s
s
io
n
th
at
r
ea
l
life
,
s
h
o
u
ld
b
e
th
e
s
tar
tin
g
p
o
in
t
r
ath
e
r
th
a
n
th
e
en
d
p
o
in
t
in
teac
h
in
g
ea
r
ly
liter
ac
y
an
d
th
at
s
k
ills
s
u
ch
as
p
h
o
n
etics
s
h
o
u
ld
b
e
u
s
ed
as
a
to
o
l
to
h
elp
m
a
k
e
s
en
s
e
o
f
th
e
p
r
in
ted
m
e
d
ia
s
ee
n
ar
o
u
n
d
[
8
]
.
T
h
e
d
y
n
am
i
c
n
atu
r
e
o
f
k
n
o
wled
g
e
d
o
es
n
o
t
en
d
at
k
n
o
wled
g
e
o
f
g
r
am
m
ar
,
p
h
o
n
etics
an
d
v
o
ca
b
u
lar
y
,
b
u
t a
ls
o
in
v
o
lv
es p
r
ac
tical
lear
n
in
g
t
o
in
ter
p
r
et
ev
er
y
th
in
g
[
9
]
.
T
ec
h
n
o
lo
g
y
h
as
p
e
n
etr
ated
in
to
th
e
i
n
d
u
s
tr
ial
in
th
e
wo
r
ld
,
th
is
d
o
es
n
o
t
ch
an
g
e
th
e
attitu
d
e
o
f
t
h
e
in
d
u
s
tr
y
in
d
ev
elo
p
i
n
g
in
n
o
v
atio
n
.
An
u
n
d
er
s
tan
d
in
g
o
f
tech
n
o
lo
g
y
m
u
s
t
b
e
b
alan
c
ed
with
in
d
u
s
tr
ial
m
aster
y
/s
k
ills
in
in
n
o
v
atio
n
m
an
ag
em
e
n
t.
T
h
e
asp
ec
t
o
f
r
ea
d
in
g
s
k
ills
,
f
o
r
ex
am
p
le,
is
im
p
o
r
tan
t
i
n
u
n
d
er
s
tan
d
i
n
g
th
e
s
ig
n
s
o
f
lan
g
u
ag
e
r
ec
o
r
d
ed
i
n
it.
As
is
we
ll
k
n
o
wn
,
th
e
r
ea
d
in
g
p
r
o
f
icie
n
cy
o
f
I
n
d
o
n
esian
s
r
em
ain
s
q
u
ite
lo
w.
I
n
d
o
n
esi
a'
s
liter
ac
y
cu
ltu
r
e
r
an
k
e
d
s
ec
o
n
d
o
u
t
o
f
6
5
n
atio
n
s
i
n
th
e
wo
r
ld
in
2
0
1
2
,
ac
co
r
d
in
g
to
th
e
p
r
o
g
r
am
f
o
r
i
n
ter
n
atio
n
al
s
tu
d
e
n
t
ass
ess
m
e
n
t
(
PISA)
r
esear
ch
.
I
n
d
o
n
esia is r
an
k
ed
6
4
th
o
u
t
o
f
6
5
n
atio
n
s
.
Vietn
am
is
in
th
e
to
p
2
0
at
th
e
s
am
e
tim
e.
T
h
e
r
ea
d
in
g
p
r
o
f
icien
cy
o
f
I
n
d
o
n
e
s
ia
was
r
an
k
ed
5
7
th
o
u
t
o
f
6
5
co
u
n
tr
ies
in
th
e
s
a
m
e
s
u
r
v
ey
b
y
PISA.
I
n
I
n
d
o
n
esia,
th
e
r
ea
d
in
g
in
te
r
est
in
d
e
x
h
as
o
n
ly
r
ea
ch
ed
0
.
0
0
1
,
wh
ich
m
ea
n
s
th
at
ju
s
t
o
n
e
p
er
s
o
n
o
u
t
o
f
ev
er
y
1
,
0
0
0
is
in
ter
ested
in
r
ea
d
in
g
,
ac
c
o
r
d
in
g
t
o
UNE
SC
O
2
0
1
2
s
tatis
tics
[
1
0
]
.
R
ec
y
clin
g
r
ec
y
cled
p
last
ic
b
o
t
tles
is
a
cr
u
cial
en
er
g
y
-
s
av
in
g
an
d
en
v
ir
o
n
m
e
n
tal
p
r
o
tectio
n
s
tr
ateg
y
.
v
ar
ied
c
o
lo
r
ed
b
o
ttles
h
av
e
v
ar
ied
r
ec
y
clin
g
v
alu
es.
C
lass
i
f
y
in
g
p
last
ic
b
o
ttles
b
ased
o
n
im
ag
e
r
ec
o
g
n
itio
n
d
u
r
in
g
r
ec
y
clin
g
is
an
ef
f
icie
n
t
m
eth
o
d
,
wh
er
e
p
o
s
itio
n
an
d
co
lo
r
i
d
en
tific
atio
n
a
r
e
th
e
m
ain
tech
n
o
l
o
g
ies.
T
h
e
in
itial
s
tep
in
clas
s
if
y
in
g
p
last
ic
b
o
ttles
i
s
to
id
en
tify
th
e
lo
ca
tio
n
in
to
th
r
ee
ca
teg
o
r
ies:
o
v
er
lap
p
in
g
,
ad
jace
n
t,
an
d
d
is
co
n
tin
u
o
u
s
.
B
ased
o
n
it
s
p
ictu
r
e,
d
is
co
n
tin
u
o
u
s
ca
n
b
e
ea
s
ily
d
etec
ted
b
y
th
e
r
atio
o
f
co
n
ca
v
e
to
co
n
v
ex
a
r
ea
s
.
A
co
m
b
in
atio
n
tech
n
iq
u
e
k
n
o
wn
as
d
is
tan
ce
tr
an
s
f
o
r
m
atio
n
an
d
th
r
esh
o
ld
s
eg
m
en
tatio
n
is
s
u
g
g
ested
f
o
r
b
o
ttles
th
at
ar
e
a
d
jace
n
t
an
d
o
v
er
lap
in
o
r
d
er
to
d
if
f
er
en
ti
ate
th
eir
p
o
s
itio
n
al
r
elatio
n
s
h
ip
.
On
ce
n
eig
h
b
o
r
in
g
b
o
ttles
h
av
e
b
ee
n
l
o
ca
ted
,
n
ea
r
b
y
r
ec
y
cled
b
o
ttles
will
b
e
f
u
r
th
er
s
ep
ar
ate
d
u
s
in
g
a
co
n
ca
v
e
p
o
in
t
s
ea
r
ch
t
ec
h
n
iq
u
e
b
ased
o
n
co
n
v
ex
h
u
l
l.
T
h
e
co
lo
r
o
f
th
e
s
ep
ar
ated
a
n
d
ad
jace
n
t
b
o
ttles
is
th
en
d
eter
m
in
ed
s
in
ce
it
is
to
o
co
m
p
le
x
an
d
ch
allen
g
in
g
to
d
is
tin
g
u
is
h
th
e
co
lo
r
an
d
s
ep
ar
ate
th
e
b
o
ttles
th
at
o
v
er
lap
.
Du
r
in
g
th
e
s
o
r
ti
n
g
p
r
o
ce
s
s
,
r
ec
y
cled
b
o
ttles
'
co
lo
r
s
ar
e
s
ep
ar
ated
i
n
to
s
ev
e
n
ca
teg
o
r
ies
in
th
e
co
lo
r
r
ec
o
g
n
itio
n
asp
ec
t.
I
n
o
r
d
er
to
av
o
id
s
h
a
p
e
in
ac
cu
r
ac
ie
s
ca
u
s
ed
b
y
b
o
ttle
ca
p
s
an
d
la
b
els
at
th
e
to
p
an
d
m
id
d
le
o
f
t
h
e
b
o
ttle,
r
esp
ec
tiv
ely
,
th
e
b
o
tto
m
co
lo
r
is
u
tili
ze
d
to
r
ep
r
esen
t o
n
e
o
f
th
e
r
ec
y
c
led
b
o
ttles
.
Pre
v
io
u
s
r
esear
ch
c
o
n
d
u
cted
b
y
W
ei
et
a
l.
[
1
1
]
,
a
f
ter
t
h
e
v
o
r
tex
p
ictu
r
e
h
as
b
ee
n
p
r
e
p
r
o
ce
s
s
ed
u
s
in
g
iter
ativ
e
ad
ap
tiv
e
b
in
ar
izatio
n
an
d
m
ea
n
f
ilter
in
g
,
th
e
co
n
v
e
x
h
u
ll
al
g
o
r
ith
m
an
d
ed
g
e
f
u
n
ctio
n
ar
e
a
p
p
lied
to
th
e
p
r
ep
r
o
ce
s
s
ed
im
ag
e
in
o
r
d
er
to
id
en
tify
t
h
e
v
o
r
te
x
im
ag
e'
s
p
r
ec
is
e
s
h
ap
e
an
d
d
eter
m
in
e
its
ar
ea
.
Un
d
er
v
ar
io
u
s
ex
p
er
im
en
tal
co
n
d
itio
n
s
,
th
e
v
o
r
tex
s
h
ap
e
a
n
d
ar
ea
ca
n
b
e
ex
t
r
ac
ted
u
s
in
g
th
is
m
eth
o
d
with
o
u
t
th
e
n
ee
d
f
o
r
u
s
er
i
n
ter
v
en
tio
n
,
a
cc
o
r
d
in
g
to
ex
p
e
r
im
en
tal
d
ata.
T
h
e
s
u
g
g
ested
ap
p
r
o
ac
h
is
m
o
r
e
s
u
itab
le
f
o
r
ex
p
o
s
in
g
th
e
ac
t
u
al
s
tate
o
f
th
e
v
o
r
tex
,
as
ev
i
d
en
ce
d
b
y
th
e
av
er
ag
e
ab
s
o
lu
te
e
r
r
o
r
r
ate
o
f
2
.
8
4
%,
r
o
o
t
m
ea
n
s
q
u
ar
e
er
r
o
r
(
R
MSE
)
o
f
0
.
2
9
0
3
,
an
d
c
o
r
r
elatio
n
c
o
ef
f
icien
t
o
f
0
.
9
9
6
5
r
ep
o
r
ted
b
y
th
is
m
eth
o
d
in
co
m
p
ar
is
o
n
to
th
e
v
o
r
tex
ar
ea
r
esu
lts
ac
q
u
ir
ed
u
s
in
g
th
e
m
an
u
al
ex
tr
ac
tio
n
m
eth
o
d
.
T
h
e
ex
tr
ac
tio
n
t
ec
h
n
iq
u
e
h
as
b
ee
n
s
tan
d
ar
d
ized
to
s
et
a
b
aselin
e
f
o
r
f
u
r
th
e
r
s
tu
d
ies o
n
v
o
r
tex
im
ag
es.
A
s
cien
tific
b
asi
s
f
o
r
th
e
r
ea
l
-
tim
e
tr
ac
k
in
g
s
tu
d
y
o
f
a
g
r
icu
ltu
r
al
cr
o
p
p
r
o
tectio
n
u
n
m
an
n
e
d
ae
r
ial
v
e
h
icles
(
UAV
s
)
an
d
v
o
r
tices
is
estab
lis
h
ed
b
y
th
e
m
eth
o
d
o
l
o
g
y
i
n
th
is
p
u
b
licatio
n
.
I
n
o
r
d
er
t
o
s
o
lv
e
a
n
u
m
b
er
o
f
im
p
o
r
ta
n
t
is
s
u
es,
in
clu
d
in
g
d
eter
m
i
n
in
g
t
h
e
p
o
s
itio
n
al
r
elatio
n
s
h
ip
s
b
etwe
en
n
ea
r
b
y
b
o
ttles
,
h
an
d
lin
g
n
e
ar
b
y
b
o
ttles
,
an
d
class
if
y
in
g
a
ll
b
o
ttles
b
y
co
lo
r
,
as
well
as
f
o
r
ec
asti
n
g
th
e
p
at
ter
n
o
f
waste
ac
cu
m
u
latio
n
in
I
n
d
o
n
esia
—
p
ar
ticu
lar
ly
p
last
ic
wa
s
te,
wh
ich
i
s
in
cr
ea
s
in
g
d
aily
—
an
d
f
in
d
in
g
alter
n
ate
r
ec
y
clin
g
u
s
es
f
o
r
s
u
ch
waste,
th
e
s
tu
d
y
aim
s
to
id
en
tify
a
s
y
s
tem
atic
m
eth
o
d
f
o
r
s
o
r
tin
g
p
last
ic
b
o
tt
les in
v
ar
io
u
s
co
lo
r
s
f
o
r
r
e
cy
cl
in
g
p
u
r
p
o
s
es.
2.
M
E
T
H
O
DO
L
O
G
Y
B
ased
o
n
th
e
th
eo
r
etica
l
b
asis
an
d
th
e
ex
p
lan
atio
n
ab
o
v
e
o
n
th
e
m
eth
o
d
o
lo
g
y
th
at
d
es
cr
ib
es
th
e
f
r
am
ewo
r
k
o
f
h
o
w
th
e
t
h
eo
r
ie
s
o
f
th
e
co
n
ce
p
tu
al
m
o
d
el
r
el
ated
to
th
e
v
a
r
io
u
s
f
ac
to
r
s
id
e
n
tifie
d
as
p
r
o
b
lem
s
to
ex
p
lain
t
h
eo
r
etica
lly
b
etwe
en
th
e
v
a
r
iab
les
to
b
e
s
tu
d
ie
d
.
B
ef
o
r
e
ca
r
r
y
in
g
o
u
t
th
e
p
r
o
ce
s
s
o
f
p
r
o
ce
s
s
in
g
p
last
ic
r
ec
y
clin
g
im
a
g
es,
a
r
e
s
ea
r
ch
m
eth
o
d
o
lo
g
y
is
f
ir
s
t
u
s
ed
wh
ich
s
tar
ts
f
r
o
m
d
e
f
in
in
g
th
e
p
r
o
b
lem
,
th
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
Ob
ject
r
etri
ev
a
l a
n
a
lysi
s
o
n
p
la
s
tic
b
o
ttle wa
s
te
r
ec
yc
lin
g
-
b
a
s
ed
ima
g
e
co
n
tr
o
l
…
(
Ma
r
is
a
)
2057
ap
p
r
o
ac
h
u
s
ed
,
d
ev
elo
p
m
en
t,
to
im
p
lem
en
tatio
n
to
th
e
p
u
b
l
ic,
m
ea
s
u
r
in
g
ac
c
u
r
ac
y
an
d
d
r
awin
g
co
n
clu
s
io
n
s
.
T
h
e
d
etailed
im
ag
e
p
r
o
ce
s
s
in
g
m
eth
o
d
o
lo
g
y
is
s
h
o
wn
in
Fig
u
r
e
1
.
Fig
u
r
e
1
.
R
esear
ch
f
r
am
ewo
r
k
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
I
n
th
e
r
esear
ch
,
an
ap
p
lied
r
es
ea
r
ch
ap
p
r
o
ac
h
will
b
e
ca
r
r
ied
o
u
t,
n
am
ely
as
en
g
in
ee
r
in
g
r
e
s
ea
r
ch
o
n
th
e
ap
p
licatio
n
o
f
s
cien
ce
t
o
an
a
n
aly
s
is
to
o
b
tain
p
er
f
o
r
m
an
ce
r
esu
lts
in
ac
co
r
d
an
ce
with
p
r
ed
eter
m
in
ed
r
eq
u
ir
em
e
n
ts
.
T
h
e
p
r
o
ce
s
s
o
f
r
esear
ch
r
esu
lts
u
s
ed
in
th
is
ap
p
r
o
ac
h
is
i
)
an
aly
s
i
s
to
d
eter
m
in
e
th
e
s
p
ec
if
icatio
n
s
o
f
o
b
ject
m
ea
s
u
r
em
en
t
ac
cu
r
ac
y
,
an
d
ii
)
r
es
u
lts
to
ch
o
o
s
e
o
n
e
o
f
th
e
b
est
m
o
d
els
an
d
ca
n
b
e
s
cien
tific
ally
ac
co
u
n
ted
f
o
r
i
n
ac
co
r
d
a
n
ce
with
r
esear
ch
r
u
l
es.
T
h
e
r
esear
ch
a
p
p
r
o
ac
h
p
r
o
ce
s
s
as
m
ater
ial
f
o
r
d
etailed
an
aly
s
is
is
as f
o
llo
ws:
3
.
1
.
Da
t
a
t
r
a
ini
ng
T
r
ain
in
g
d
ata
is
o
r
k
n
o
wn
as
tr
ain
in
g
d
atasets
,
lear
n
in
g
s
ets
an
d
tr
ain
in
g
s
ets,
is
p
ar
t
o
f
a
co
llectio
n
o
f
d
atasets
th
at
ar
e
p
r
o
v
id
ed
t
o
b
e
m
ater
ial
f
o
r
m
o
d
el
lear
n
i
n
g
s
o
th
at
th
e
m
o
d
el
ca
n
g
en
er
alize
(
f
in
d
p
atter
n
s
)
d
ata
s
o
th
at
it
ca
n
later
b
e
u
s
e
d
to
p
r
ed
ict
n
ew
d
ata
an
d
is
a
s
et
o
f
d
ata
u
s
ed
t
o
tr
ain
o
r
b
u
ild
m
o
d
els.
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
s
will
ch
an
g
e
th
e
p
ar
a
m
eter
s
o
n
th
em
s
el
v
es
to
ad
ju
s
t
to
th
e
d
ata
p
r
o
v
i
d
ed
d
u
r
in
g
tr
ai
n
in
g
[
1
2
]
.
T
h
e
s
tu
d
y
'
s
tr
ain
in
g
d
at
a
co
m
es
f
r
o
m
th
e
Min
is
tr
y
o
f
E
n
v
ir
o
n
m
e
n
t
an
d
Fo
r
estry
o
f
th
e
R
ep
u
b
lic
o
f
I
n
d
o
n
esia'
s
n
atio
n
al
waste
m
a
n
ag
em
en
t
in
f
o
r
m
atio
n
s
y
s
tem
(
h
ttp
s
:
//s
ip
s
n
.
men
lh
k.
g
o
.
id
/s
ip
s
n
)
.
Sp
ec
if
ically
,
it
p
r
o
v
id
es
in
f
o
r
m
atio
n
o
n
th
e
a
m
o
u
n
t
o
f
waste
ca
teg
o
r
ies
i
n
I
n
d
o
n
esia
b
y
p
r
o
v
in
ce
in
2
0
2
3
.
T
a
b
le
1
lis
ts
th
e
tr
ain
in
g
d
ata
in
to
n
s
f
o
r
g
lass
,
r
u
b
b
er
-
leath
er
,
f
ab
r
ic,
p
ap
er
-
c
ar
d
b
o
a
r
d
,
m
etal,
p
last
ic,
wo
o
d
-
twig
s
,
f
o
o
d
waste,
an
d
o
th
e
r
m
ater
ials
.
T
o
tal
waste
th
at
h
as
b
ee
n
co
llected
b
ased
o
n
3
8
p
r
o
v
in
ce
s
(
Nan
g
g
r
o
e
Ace
h
Dar
u
s
s
alam
,
No
r
th
Su
m
ater
a,
So
u
th
Su
m
ate
r
a,
W
est
Su
m
ater
a,
B
en
g
k
u
lu
,
R
iau
,
R
iau
I
s
lan
d
s
,
J
am
b
i,
L
am
p
u
n
g
,
B
an
g
k
a
B
elitu
n
g
,
W
est
Kalim
an
tan
,
E
ast
Kalim
an
tan
,
So
u
th
Kali
m
an
tan
,
C
en
tr
al
Kalim
an
tan
,
No
r
th
Kalim
an
tan
,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
2
,
Ap
r
il
20
25
:
2
0
5
5
-
2
0
6
9
2058
B
an
ten
,
DKI
J
ak
ar
ta,
W
est
J
av
a,
C
en
tr
al
J
av
a,
Sp
ec
ial
R
eg
io
n
o
f
Yo
g
y
a
k
ar
ta,
E
ast
J
av
a,
B
ali,
E
ast
Nu
s
a
T
en
g
g
ar
a
,
W
est
Su
lawe
s
i,
C
en
tr
al
Su
lawe
s
i,
No
r
th
Su
lawe
s
i,
So
u
th
ea
s
t
Su
lawe
s
i,
So
u
th
Su
lawe
s
i,
No
r
th
Ma
lu
k
u
,
Ma
lu
k
u
,
W
est
Pap
u
a,
C
en
tr
al
Pap
u
a,
Mo
u
n
tain
o
u
s
Pap
u
a,
So
u
th
Pap
u
a,
So
u
th
we
s
t
Pap
u
a)
ar
e
waste
th
at
h
as b
ee
n
s
ep
ar
ated
b
y
t
y
p
e
s
o
th
at
it is
ea
s
y
to
m
an
ag
e
n
atio
n
ally
,
as in
th
e
Fig
u
r
e
2
.
I
n
th
is
s
tu
d
y
,
th
e
d
ata
th
at
will
b
e
u
s
ed
as
a
s
am
p
le
is
d
ata
o
n
p
last
ic
wate
r
b
o
ttle
p
ac
k
ag
in
g
as
m
u
c
h
as
6
7
5
,
0
5
0
to
n
s
o
r
2
7
.
3
6
%
o
f
th
e
to
tal
n
atio
n
al
p
last
ic
wast
e
o
f
2
,
3
6
7
,
2
8
0
to
n
s
o
r
7
2
.
6
4
%,
as
in
T
ab
le
2
.
A
co
m
p
ar
is
o
n
o
f
th
e
q
u
an
tity
o
f
p
last
ic
wa
s
te
in
b
o
ttles
an
d
t
h
e
q
u
an
tity
o
f
p
last
ic
g
ar
b
a
g
e
in
g
en
er
al
is
s
h
o
wn
in
Fig
u
r
e
3
,
in
d
icatin
g
t
h
at
p
last
ic
waste
in
I
n
d
o
n
esia
is
ex
tr
em
ely
h
i
g
h
in
r
elatio
n
t
o
o
th
er
waste
an
d
d
is
p
er
s
ed
th
r
o
u
g
h
o
u
t 3
8
p
r
o
v
i
n
ce
s
.
T
ab
le
1
.
T
o
tal
v
o
lu
m
e
o
f
wast
e
ty
p
es in
I
n
d
o
n
esia b
y
p
r
o
v
in
ce
in
2
0
2
3
N
o
.
P
r
o
v
i
n
c
e
Ty
p
e
o
f
w
a
s
t
e
(
To
n
)
O
t
h
e
r
s
G
l
a
ss
R
u
b
b
e
r
-
l
e
a
t
h
e
r
P
l
a
st
i
c
W
o
o
d
-
t
w
i
g
s
F
o
o
d
s
c
r
a
p
s
1
N
a
n
g
g
r
o
e
A
c
e
h
D
a
r
u
ssa
l
a
m
7
9
.
8
5
4
1
.
2
5
4
7
.
5
0
2
5
2
.
7
0
1
7
1
.
4
0
3
9
5
.
7
0
2
N
o
r
t
h
S
u
mat
e
r
a
9
1
.
2
4
1
4
.
3
4
8
.
3
4
5
8
.
3
0
7
1
.
8
9
7
6
.
6
5
3
S
o
u
t
h
S
u
m
a
t
e
r
a
8
.
7
2
3
.
8
1
0
.
7
0
6
7
.
5
2
1
9
.
5
0
1
6
6
.
7
7
4
W
e
st
S
u
ma
t
e
r
a
8
6
.
8
7
2
2
.
3
7
1
2
.
6
7
2
4
1
.
0
8
1
3
8
.
0
5
6
0
6
.
5
5
5
B
e
n
g
k
u
l
u
0
.
5
0
0
.
4
0
0
.
3
0
5
.
6
0
5
.
4
0
7
6
.
5
0
…
…
…
…
…
…
…
…
…
…
…
…
…
…
…
…
37
S
o
u
t
h
P
a
p
u
a
0
0
0
0
0
0
38
S
o
u
t
h
w
e
st
P
a
p
u
a
9
.
1
0
7
.
7
0
1
8
.
5
0
8
9
.
6
0
3
4
.
5
0
7
5
.
2
0
To
t
a
l
8
4
9
.
8
1
2
9
3
.
2
1
2
4
1
.
5
8
2
.
3
6
7
.
2
8
1
.
3
5
8
.
2
2
5
.
3
5
5
.
0
8
Fig
u
r
e
2
.
T
o
tal
v
o
lu
m
e
o
f
was
te
ty
p
es in
I
n
d
o
n
esia b
y
p
r
o
v
i
n
ce
in
2
0
2
3
T
ab
le
2
.
T
o
tal
v
o
lu
m
e
waste
in
I
n
d
o
n
esia b
y
p
r
o
v
in
ce
an
d
p
last
ic
b
o
ttle w
aste ty
p
e,
2
0
2
3
No
P
r
o
v
i
n
c
e
To
n
A
l
l
p
l
a
st
i
c
w
a
st
e
P
l
a
st
i
c
b
o
t
t
l
e
w
a
s
t
e
1
N
a
n
g
g
r
o
e
A
c
e
h
D
a
r
u
ssa
l
a
m
2
5
2
.
7
0
6
9
.
1
4
2
N
o
r
t
h
S
u
mat
e
r
a
5
8
.
3
0
1
5
.
9
5
3
S
o
u
t
h
S
u
m
a
t
e
r
a
6
7
.
5
2
1
8
.
4
7
4
W
e
st
S
u
ma
t
e
r
a
2
4
1
.
0
8
6
5
.
9
6
5
B
e
n
g
k
u
l
u
5
.
6
0
1
.
5
3
…
…
…
…
…
…
…
…
37
S
o
u
t
h
P
a
p
u
a
0
0
38
S
o
u
t
h
w
e
st
P
a
p
u
a
8
9
.
6
0
2
4
5
1
To
t
a
l
2
.
3
6
7
.
2
8
6
7
5
.
0
5
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
Ob
ject
r
etri
ev
a
l a
n
a
lysi
s
o
n
p
la
s
tic
b
o
ttle wa
s
te
r
ec
yc
lin
g
-
b
a
s
ed
ima
g
e
co
n
tr
o
l
…
(
Ma
r
is
a
)
2059
Fig
u
r
e
3
.
T
o
tal
v
o
lu
m
e
o
f
b
o
tt
le
waste
ty
p
es in
I
n
d
o
n
esia b
y
p
r
o
v
in
ce
,
2
0
2
3
3
.
2
.
Co
nv
e
x
h
ull
C
o
n
v
ex
h
u
ll
(
C
H)
is
a
class
ic
p
r
o
b
lem
in
c
o
m
p
u
tatio
n
al
g
e
o
m
etr
y
,
th
e
p
r
o
b
lem
is
d
escr
i
b
ed
s
im
p
ly
in
two
-
d
im
en
s
io
n
al
s
p
ac
e
(
p
la
n
e)
as
f
in
d
in
g
a
s
u
b
s
et
o
f
th
e
s
et
o
f
p
o
in
ts
o
n
th
e
p
lan
e
s
u
ch
th
at
if
th
e
p
o
in
ts
ar
e
m
ad
e
in
to
p
o
ly
g
o
n
it will f
o
r
m
a
co
n
v
ex
p
o
ly
g
o
n
[
1
3
]
.
A
p
o
ly
g
o
n
is
s
aid
to
b
e
co
n
v
ex
i
f
a
lin
e
co
n
n
ec
tin
g
th
e
p
o
in
ts
is
d
r
awn
th
en
th
e
r
e
is
n
o
lin
e
th
at
in
ter
s
ec
ts
th
e
lin
e
wh
ich
is
th
e
o
u
ter
b
o
u
n
d
a
r
y
o
f
th
e
p
o
ly
g
o
n
.
An
o
th
er
d
ef
in
itio
n
o
f
co
n
v
ex
h
u
ll
is
a
p
o
ly
g
o
n
co
m
p
o
s
ed
o
f
a
s
u
b
s
et
o
f
p
o
in
ts
s
u
ch
th
at
n
o
p
o
in
t
f
r
o
m
th
e
in
itial
s
et
is
o
u
ts
id
e
th
e
p
o
l
y
g
o
n
all
p
o
in
ts
ar
e
o
n
th
e
o
u
t
er
b
o
u
n
d
a
r
y
o
r
in
s
id
e
t
h
e
ar
ea
en
clo
s
ed
b
y
th
e
p
o
ly
g
o
n
[
1
4
]
.
T
h
e
CH
o
f
a
s
et
o
f
p
o
in
ts
is
th
e
s
m
allest
co
n
v
ex
s
et
th
at
co
n
tain
s
th
o
s
e
p
o
in
ts
.
I
n
two
d
im
en
s
io
n
s
th
is
is
a
co
n
v
ex
p
o
ly
g
o
n
,
a
s
im
p
le
p
o
ly
g
o
n
is
a
two
-
d
im
en
s
io
n
al
s
h
a
p
e
th
a
t
h
as
m
an
y
an
g
les
wh
er
e
th
er
e
is
n
o
in
ter
s
ec
tio
n
b
etwe
en
th
e
an
g
les.
E
ac
h
s
im
p
le
p
o
ly
g
o
n
h
as
an
in
n
er
r
eg
io
n
an
d
a
n
o
u
ter
r
eg
io
n
[
1
5
]
.
A
s
im
p
le
p
o
ly
g
o
n
is
s
aid
to
b
e
co
n
v
ex
if
th
e
m
a
g
n
itu
d
e
o
f
th
e
in
n
e
r
d
eg
r
ee
f
o
r
m
ed
f
o
r
ea
c
h
an
g
le
is
s
m
aller
th
an
1
8
0
d
eg
r
ee
s
,
t
h
e
co
n
v
e
x
h
u
ll
o
f
a
p
o
ly
g
o
n
P
is
th
e
s
m
al
lest
r
eg
io
n
o
f
th
e
co
n
v
ex
p
o
ly
g
o
n
wh
ich
s
u
r
r
o
u
n
d
s
th
e
p
o
ly
g
o
n
P.
I
t
ca
n
also
b
e
s
aid
to
b
e
a
r
u
b
b
er
b
an
d
th
at
co
v
e
r
s
ar
o
u
n
d
P.
T
h
e
co
n
v
ex
h
u
ll
o
f
a
co
n
v
ex
p
o
ly
g
o
n
P is
P its
elf
[
1
6
]
.
3
.
2
.
1
.
I
dentif
ica
t
io
n a
nd
t
re
a
t
m
ent
o
f
t
he
po
s
it
io
na
l r
ela
t
i
o
ns
hip
s
bet
wee
n t
he
re
cy
cle
d pla
s
t
ic
bo
t
t
les
Ho
w
to
ar
r
an
g
e
r
ec
y
cled
b
o
tt
les
s
ev
er
al
p
n
eu
m
atic
n
o
zz
les
o
n
a
p
n
eu
m
atic
jet
s
ep
ar
ato
r
s
o
r
t
th
e
r
ec
y
cled
p
last
ic
b
o
ttles
.
T
h
e
r
e
f
o
r
e,
th
e
ce
n
tr
o
i
d
o
f
ea
ch
b
o
tt
le
m
u
s
t
b
e
o
b
tain
ed
th
r
o
u
g
h
i
m
ag
e
p
r
o
ce
s
s
in
g
in
o
r
d
er
to
id
e
n
tify
th
e
p
n
eu
m
at
ic
v
alv
e
id
en
tifie
r
s
th
at
s
h
o
u
l
d
b
e
ac
tiv
ated
an
d
wh
e
n
th
ese
p
n
eu
m
atic
v
alv
es
s
h
o
u
ld
b
e
tr
ig
g
er
ed
.
W
e
ca
r
r
ied
o
u
t
a
s
tr
aig
h
tf
o
r
war
d
ex
p
er
im
en
tal
in
v
esti
g
atio
n
p
r
io
r
to
u
n
d
er
ta
k
in
g
th
e
th
eo
r
etica
l
in
v
esti
g
atio
n
o
f
th
i
s
s
u
b
ject
[
1
7
]
.
Acc
o
r
d
in
g
to
e
x
p
er
im
en
ts
,
wh
en
a
p
last
ic
b
o
ttle
is
p
o
s
itio
n
ed
at
r
an
d
o
m
o
n
a
co
n
v
e
y
o
r
b
elt,
th
er
e
ar
e
th
r
ee
p
o
s
s
ib
le
o
u
tco
m
e
s
: d
is
ju
n
ct,
n
eig
h
b
o
r
in
g
,
an
d
o
v
er
lap
p
in
g
.
B
o
ttles
th
at
ar
e
n
o
t
in
co
n
tact
with
o
n
e
an
o
th
e
r
a
r
e
r
ef
er
r
e
d
to
as d
is
jo
in
t
b
o
ttles
.
A
d
jace
n
t b
o
ttles
ar
e
th
o
s
e
th
at
c
o
m
e
in
to
co
n
tact
with
o
n
e
a
n
o
th
er
with
o
u
t
b
ein
g
co
v
e
r
ed
.
Ad
d
i
tio
n
ally
,
if
th
e
b
o
ttles
o
v
er
la
p
,
it
in
d
icate
s
th
at,
ac
co
r
d
in
g
to
th
ese
r
ea
l c
ir
c
u
m
s
tan
ce
s
,
o
n
e
b
o
ttle is co
v
er
e
d
b
y
th
e
o
th
er
[
1
8
]
.
3
.
2
.
2
.
I
dentif
ica
t
io
n o
f
t
he
po
s
it
io
na
l r
ela
t
io
ns
hip
o
f
pla
s
t
i
c
bo
t
t
les
T
o
id
en
tify
th
e
p
o
s
itio
n
al
r
elatio
n
s
h
ip
s
o
f
p
last
ic
b
o
ttles
,
o
n
e
m
u
s
t f
ir
s
t d
is
tin
g
u
is
h
b
etwe
en
th
e
th
r
ee
s
ce
n
ar
io
s
.
T
o
id
en
tify
d
is
co
n
tin
u
o
u
s
p
last
ic
b
o
ttles
,
o
n
e
m
u
s
t
f
ir
s
t
g
et
th
eir
o
u
tlin
es
an
d
co
n
v
e
x
h
u
lls
o
f
tar
g
ets
o
n
th
e
co
n
v
e
y
er
b
elt.
T
h
e
co
n
v
e
x
h
u
ll
H
o
f
an
ar
b
itra
r
y
s
et
S
is
th
e
s
m
allest
co
n
v
ex
s
et
th
at
co
n
tain
s
S;
th
e
co
n
v
ex
d
ef
ec
t
is
th
e
d
if
f
er
en
ce
b
etwe
en
H
an
d
S.
I
n
th
is
p
ap
er
,
th
e
co
n
v
ex
h
u
ll
o
f
th
e
co
n
to
u
r
o
f
ea
ch
p
last
ic
b
o
ttle is o
b
tain
ed
u
s
in
g
th
e
J
ar
v
is
s
tep
p
in
g
co
n
v
ex
h
u
ll a
lg
o
r
ith
m
[
1
9
]
.
3
.
2
.
3
.
Sepa
ra
t
io
n o
f
a
dja
ce
nt
pla
s
t
ic
bo
t
t
les
W
h
ile
d
eter
m
in
in
g
th
e
ce
n
tr
o
id
o
f
ea
c
h
b
o
ttle
is
d
i
f
f
icu
lt f
o
r
o
v
e
r
lap
p
in
g
b
o
ttles
,
it
is
s
till
p
o
s
s
ib
le
to
d
eter
m
in
e
th
e
ce
n
tr
o
id
o
f
ea
c
h
b
o
ttle
b
y
im
a
g
e
p
r
o
ce
s
s
in
g
,
as
s
h
o
wn
b
y
th
e
b
in
a
r
y
im
ag
e
o
f
ad
jace
n
t
p
last
ic
b
o
ttles
.
W
h
en
th
e
two
r
ed
d
o
ts
ar
e
co
n
n
ec
ted
,
it
is
clea
r
th
at
th
e
n
ea
r
b
y
tar
g
et
ca
n
b
e
d
iv
id
ed
in
t
o
two
d
is
co
n
tin
u
o
u
s
tar
g
ets.
Af
ter
th
at,
th
eir
ce
n
tr
o
id
s
ca
n
b
e
ac
q
u
i
r
ed
in
d
ep
e
n
d
en
tly
.
T
h
e
two
co
n
ca
v
e
s
p
o
ts
in
th
is
wo
r
k
h
av
e
b
ee
n
f
o
u
n
d
u
s
in
g
th
e
co
n
v
ex
h
u
ll
an
d
th
e
co
n
v
ex
d
ef
ec
ts
o
f
th
e
co
n
to
u
r
.
T
h
e
p
ictu
r
e
o
f
n
ea
r
b
y
p
last
ic
b
o
ttles
[
2
0
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
2
,
Ap
r
il
20
25
:
2
0
5
5
-
2
0
6
9
2060
3
.
2
.
4
.
Ana
ly
s
is
r
esu
lt
o
f
c
o
nv
ex
h
ull
I
n
o
r
d
e
r
to
d
is
tin
g
u
is
h
th
e
co
lo
r
o
f
p
last
ic
b
o
ttles
an
d
u
s
e
it
as
a
f
ea
tu
r
e,
th
e
ag
g
r
eg
ate
ac
cu
r
ac
y
co
m
b
in
ed
with
th
e
co
lo
r
o
f
p
last
ic
b
o
ttles
is
s
im
p
ly
s
ep
ar
ated
in
to
t
h
r
ee
g
r
o
u
p
s
:
co
lo
r
less
,
b
lu
e,
an
d
g
r
ee
n
b
o
ttles
.
Sev
en
co
lo
r
-
b
ased
ca
t
eg
o
r
ies
ca
n
b
e
u
s
ed
to
class
if
y
p
last
ic
b
o
ttles
:
lig
h
t
b
lu
e,
li
g
h
t
p
u
r
p
le,
b
r
o
w
n
,
b
lu
e,
lig
h
t
g
r
ee
n
,
d
ar
k
g
r
ee
n
,
an
d
co
lo
r
less
.
Natu
r
ally
,
a
m
o
r
e
ac
cu
r
ate
co
lo
r
class
if
icatio
n
f
o
r
p
last
ic
b
o
ttles
will
m
ak
e
it
m
o
r
e
d
if
f
icu
lt
to
an
aly
ze
s
u
ch
im
ag
es,
Fig
u
r
e
4
,
s
h
o
ws
th
e
p
r
o
ce
s
s
o
f
id
en
tif
y
in
g
p
ile
o
f
p
last
ic
b
o
ttles
waste
.
Fig
u
r
e
4
(
a)
s
h
o
ws
waste
p
ile
u
s
ed
as
an
o
b
ject
f
o
r
an
aly
s
is
f
o
r
r
a
n
d
o
m
p
ile
o
f
p
last
ic
b
o
ttle
waste.
Fig
u
r
e
4
(
b
)
s
h
o
ws
an
aly
s
is
o
f
waste
p
ile
with
o
b
ject
m
ar
k
in
g
with
r
an
d
o
m
p
ile
o
f
p
last
ic
b
o
ttle
wast
e
b
ased
o
n
d
etec
ted
ar
ea
.
Fig
u
r
e
4
(
c)
s
h
o
ws an
aly
s
is
r
esu
lt b
as
ed
o
n
s
elec
ted
p
ile
o
f
p
last
ic
b
o
ttle w
aste.
(
a)
(
b
)
(
c)
Fig
u
r
e
4
.
Pil
e
o
f
p
last
ic
b
o
ttle w
aste: (
a)
waste
p
ile
u
s
ed
as a
n
o
b
ject
f
o
r
an
al
y
s
is
f
o
r
r
an
d
o
m
p
ile
o
f
p
last
ic
b
o
ttle w
aste,
(
b
)
an
aly
s
is
o
f
w
aste p
ile
with
o
b
ject
m
ar
k
in
g
with
r
an
d
o
m
p
ile
o
f
p
last
ic
b
o
ttle w
aste b
ased
o
n
d
etec
ted
ar
ea
,
a
n
d
(
c
)
an
aly
s
is
r
esu
lt b
ased
o
n
s
elec
ted
p
ile
o
f
p
last
ic
b
o
ttle w
aste
Fig
u
r
e
5
is
th
e
r
esu
lt
o
f
an
al
y
zin
g
th
e
g
r
a
p
h
o
f
th
e
im
ag
e
ca
p
tu
r
e
p
r
o
ce
s
s
o
f
th
e
r
a
n
d
o
m
waste
s
elec
tio
n
p
r
o
ce
s
s
with
th
e
p
r
o
ce
s
s
o
f
p
last
ic
b
o
ttle
waste
ty
p
es
in
p
ac
k
ag
in
g
th
at
ar
e
s
till
m
ix
ed
with
o
th
er
p
last
ic
b
o
ttles
.
Fu
r
th
er
m
o
r
e,
t
h
e
r
esu
lts
o
f
th
e
im
ag
e
an
aly
s
is
to
o
b
tain
th
e
p
last
ic
b
o
ttle g
a
r
b
ag
e
im
ag
e
r
esu
lts
ca
n
b
e
u
s
ed
as
p
o
ly
g
o
n
d
ata
f
o
r
im
ag
e
d
etec
tio
n
an
d
th
e
f
i
n
al
r
esu
lt
is
an
ac
cu
r
ate
ad
ap
t
iv
e
v
o
r
tex
e
d
g
eless
ar
ea
ex
tr
ac
tio
n
.
A
r
etr
iev
al
m
eth
o
d
th
at
p
ay
s
atten
tio
n
to
th
e
th
r
ee
ch
ar
ac
ter
is
tics
o
f
th
e
p
r
ep
r
o
ce
s
s
in
g
im
ag
e
an
d
to
clo
s
e
th
e
g
ap
,
th
e
f
ir
s
t
task
is
to
ac
cu
r
ately
r
etr
ie
v
e
th
e
v
o
r
tex
ed
g
e
ac
cu
r
ately
t
o
ac
cu
r
ate
a
d
ap
tiv
e
v
o
r
tex
e
d
g
e
-
less
ar
ea
ex
tr
ac
tio
n
f
o
r
t
h
e
r
etr
iev
al
m
eth
o
d
.
Fig
u
r
e
5
.
C
o
n
v
ex
h
u
ll im
ag
e
g
r
o
u
p
b
ased
o
n
d
etec
ted
im
a
g
e
Fro
m
th
e
co
n
v
ex
h
u
ll
im
a
g
e
p
o
in
t
s
et,
th
e
p
o
in
t
k
n
o
wn
as
th
e
p
o
le
is
ch
o
s
en
an
d
j
o
in
ed
to
cr
ea
te
a
co
n
v
ex
h
u
ll
d
iv
id
in
g
lin
e.
T
h
i
s
is
ac
h
iev
ed
b
y
s
o
r
tin
g
an
d
s
ca
n
n
in
g
th
e
p
o
in
ts
in
s
id
e
th
e
co
n
v
ex
h
u
ll
th
at
ar
e
th
e
f
ar
th
est
awa
y
in
r
esp
ec
t
to
th
e
v
o
r
tex
e
d
g
e
im
ag
e'
s
ed
g
e
n
o
is
e
p
o
in
ts
ch
a
r
ac
ter
i
s
tics
u
s
in
g
cy
clica
l
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
Ob
ject
r
etri
ev
a
l a
n
a
lysi
s
o
n
p
la
s
tic
b
o
ttle wa
s
te
r
ec
yc
lin
g
-
b
a
s
ed
ima
g
e
co
n
tr
o
l
…
(
Ma
r
is
a
)
2061
r
ec
u
r
s
io
n
.
Af
ter
th
en
,
a
n
ew
m
ast
is
a
ttach
ed
v
ia
s
ca
n
n
in
g
at
th
e
d
iv
id
in
g
lin
e'
s
f
u
r
th
est
p
o
in
t.
T
h
e
co
n
v
ex
h
u
ll
is
d
eter
m
in
e
d
r
ec
u
r
s
iv
ely
u
n
til
th
e
al
g
o
r
ith
m
is
u
n
a
b
le
to
g
en
er
ate
m
o
r
e
p
o
les.
T
h
e
c
o
n
v
ex
h
u
ll
m
eth
o
d
to
ex
tr
ac
t
is
o
lated
p
o
les
f
r
o
m
th
e
v
o
r
tex
im
ag
e
is
s
tr
aig
h
tf
o
r
war
d
[
2
1
]
.
A
co
o
r
d
in
ate
s
y
s
tem
is
estab
lis
h
ed
with
th
e
o
r
ig
in
in
th
e
lo
wer
le
f
t
co
r
n
er
.
Fo
llo
win
g
th
e
ass
ig
n
m
en
t
o
f
a
lin
k
in
g
lab
el
to
ea
ch
is
o
lated
p
o
in
t
o
n
th
e
p
o
s
itio
n
ed
im
ag
e,
th
e
p
r
o
ce
d
u
r
e
is
co
n
tin
u
e
d
u
n
til
th
e
c
o
n
v
ex
h
u
ll
co
r
r
esp
o
n
d
in
g
to
t
h
e
two
p
o
lar
p
o
in
ts
ca
n
n
o
t b
e
lo
ca
ted
an
d
th
e
c
o
n
v
ex
h
u
ll
p
o
in
t
o
r
co
n
v
ex
p
o
ly
g
o
n
[
2
2
]
is
th
e
f
ar
th
est p
o
i
n
t,
as seen
in
Fig
u
r
e
6
.
Fig
u
r
e
6
.
Gr
o
u
p
o
f
c
o
n
v
e
x
h
u
l
l im
ag
es b
ased
o
n
d
etec
ted
ar
e
a
ty
p
e
I
t
is
p
o
s
s
ib
le
to
d
eter
m
in
e
th
e
ce
n
tr
o
id
o
f
ea
ch
b
o
ttle
wh
ich
is
s
t
ill
o
v
er
lap
p
in
g
b
u
t
ad
jace
n
t
to
o
th
er
p
last
ic
b
o
ttles
b
y
u
s
in
g
im
a
g
e
p
r
o
ce
s
s
in
g
.
T
h
is
allo
ws
f
o
r
th
e
p
r
esen
tatio
n
o
f
a
b
in
ar
y
im
ag
e
o
f
ad
jace
n
t
p
last
ic
b
o
ttles
,
m
ak
in
g
it
clea
r
th
at,
o
n
ce
co
n
n
ec
ted
,
th
e
two
r
ed
d
o
ts
o
n
a
d
jace
n
t
tar
g
ets
c
an
b
e
d
is
tin
g
u
is
h
ed
as
two
d
is
tin
ct
tar
g
ets.
I
t
is
th
u
s
p
o
s
s
ib
le
to
d
eter
m
in
e
t
h
eir
ce
n
ter
p
o
in
ts
in
d
ep
e
n
d
e
n
tly
.
T
wo
co
n
ca
v
e
lo
ca
tio
n
s
h
av
e
b
ee
n
f
o
u
n
d
in
th
is
p
ap
er
u
s
in
g
th
e
co
n
t
o
u
r
'
s
co
n
v
ex
h
u
ll
an
d
co
n
v
ex
d
ef
ec
t.
Fig
u
r
e
7
,
an
aly
s
is
o
f
th
e
tr
an
s
f
o
r
m
atio
n
p
r
o
ce
s
s
u
s
in
g
th
e
co
n
v
e
x
h
u
ll
alg
o
r
i
th
m
f
o
r
p
last
ic
waste
b
o
ttles
.
Fig
u
r
e
7
(
a)
s
h
o
ws
co
n
v
ex
h
u
ll
an
aly
s
is
o
f
a
d
is
co
n
tin
u
o
u
s
tar
g
et
b
ased
o
n
co
lo
r
h
is
to
g
r
am
tr
an
s
f
o
r
m
atio
n
.
Fig
u
r
e
7
(
b
)
s
h
o
ws
co
n
v
ex
h
u
ll
an
aly
s
is
o
f
ad
jac
en
t
tar
g
ets
b
ased
o
n
co
lo
r
h
is
to
g
r
am
tr
a
n
s
f
o
r
m
atio
n
.
Fig
u
r
e
7
(
c)
s
h
o
ws
co
n
v
e
x
an
aly
s
is
o
f
o
v
er
la
p
p
in
g
tar
g
ets b
ased
o
n
c
o
lo
r
h
is
to
g
r
am
tr
a
n
s
f
o
r
m
atio
n
.
(
a)
(
b
)
(
c)
Fig
u
r
e
7
.
T
h
e
co
n
v
ex
h
u
ll tr
an
s
f
o
r
m
atio
n
: (
a)
co
n
v
ex
h
u
ll a
n
aly
s
is
o
f
a
d
is
co
n
tin
u
o
u
s
tar
g
e
t b
ased
o
n
c
o
lo
r
h
is
to
g
r
am
tr
an
s
f
o
r
m
atio
n
,
(
b
)
co
n
v
ex
h
u
ll a
n
al
y
s
is
o
f
ad
jace
n
t ta
r
g
ets b
ased
o
n
co
lo
r
h
is
to
g
r
am
tr
an
s
f
o
r
m
atio
n
,
an
d
(
c)
c
o
n
v
e
x
an
aly
s
is
o
f
o
v
er
lap
p
i
n
g
tar
g
ets b
ased
o
n
co
lo
r
h
is
to
g
r
am
tr
an
s
f
o
r
m
atio
n
T
h
e
co
n
to
u
r
ar
ea
an
d
th
e
c
o
n
v
ex
h
u
ll
ar
e
s
h
o
wn
as
th
e
ar
e
a
s
u
r
r
o
u
n
d
ed
b
y
th
e
b
lu
e
cu
r
v
e
an
d
th
e
ar
ea
s
u
r
r
o
u
n
d
ed
b
y
th
e
g
r
ee
n
cu
r
v
e
a
n
d
th
e
r
atio
o
f
th
e
two
o
n
th
e
g
r
ay
c
o
lo
r
cu
r
v
e.
So
th
at
th
e
ar
ea
d
if
f
er
en
ce
in
t
h
e
co
n
v
ex
d
e
f
e
ct
is
ju
d
g
ed
to
b
e
s
ig
n
i
f
ican
tly
d
if
f
e
r
en
t.
W
ith
a
n
u
m
b
er
o
f
im
ag
es
with
th
r
ee
k
in
d
s
o
f
p
o
s
itio
n
r
elatio
n
s
h
i
p
s
co
llected
as
th
e
d
escr
ip
tio
n
o
f
s
u
ch
c
u
r
v
es
as
th
e
co
n
v
ex
h
u
ll
o
f
t
h
e
d
is
jo
in
t
tar
g
et,
th
e
co
n
v
ex
h
u
ll
o
f
th
e
ad
jace
n
t
tar
g
et
an
d
th
e
co
n
v
ex
h
u
ll
o
f
th
e
o
v
e
r
lap
p
in
g
tar
g
et,
as
s
h
o
wn
in
Fig
u
r
e
8
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
2
,
Ap
r
il
20
25
:
2
0
5
5
-
2
0
6
9
2062
A
p
last
ic
b
o
ttle
s
o
r
tin
g
s
y
s
tem
b
ased
o
n
m
ac
h
in
e
v
is
io
n
ca
n
d
is
tin
g
u
is
h
b
etwe
en
s
ev
e
n
d
if
f
e
r
en
t
co
lo
r
s
o
f
p
last
ic
b
o
ttles
o
n
th
e
m
ar
k
et.
I
n
o
n
e
r
o
u
n
d
o
f
s
o
r
tin
g
,
t
h
e
s
y
s
tem
s
h
o
u
ld
b
e
a
b
le
to
r
ec
o
g
n
ize
p
last
ic
b
o
ttles
in
o
n
e
o
f
th
e
s
ev
e
n
co
l
o
r
s
,
as
s
h
o
wn
i
n
Fig
u
r
e
9
.
I
n
T
ab
le
3
,
th
e
r
elatio
n
s
h
ip
m
atr
i
x
o
b
tain
e
d
f
r
o
m
th
e
tr
ain
in
g
s
et
an
d
test
s
et
ar
e
t
h
e
co
lo
r
s
lig
h
t
b
lu
e
,
p
u
r
p
le,
b
r
o
wn
,
b
l
u
e,
lig
h
t
g
r
ee
n
,
d
ar
k
g
r
ee
n
,
a
n
d
c
o
lo
r
less
b
o
ttles
lab
eled
1
to
7
r
esp
ec
tiv
ely
b
y
g
iv
in
g
a
v
alu
e
to
th
e
m
atr
ix
,
th
e
im
ag
e
p
r
o
ce
s
s
u
s
ed
will b
e
v
is
ib
le.
Fig
u
r
e
8
.
R
elatio
n
s
h
ip
o
f
co
n
v
ex
h
u
ll c
u
r
v
e
o
f
o
b
ject
im
ag
e
p
r
o
ce
s
s
F
i
g
u
r
e
9
.
A
n
a
l
y
s
i
s
r
e
s
u
lt
s
w
i
t
h
b
o
t
t
l
e
s
o
r
ti
n
g
s
y
s
t
e
m
b
as
e
d
o
n
b
o
t
t
l
e
c
o
l
o
r
,
b
o
t
t
le
c
o
l
o
r
s
o
r
ti
n
g
r
e
s
u
l
ts
t
h
r
o
u
g
h
h
i
s
t
o
g
r
a
m
m
o
d
e
l
p
r
o
c
e
s
s
t
o
c
y
a
n
/
m
a
g
e
n
t
a
/
y
e
ll
o
w
/
k
e
y
(
C
M
YK
)
m
o
d
e
l
i
n
c
l
u
d
i
n
g
b
l
u
e
l
i
g
h
t
,
b
r
o
w
n
l
i
g
h
t
,
g
r
e
e
n
,
w
h
i
t
e
,
b
r
o
w
n
,
b
l
u
e
a
n
d
c
o
l
o
r
l
e
s
s
a
s
t
h
e
b
a
s
i
s
f
o
r
i
d
e
n
tif
i
c
a
t
i
o
n
b
a
s
e
d
o
n
C
h
e
n
a
n
d
H
an
(
CH
)
a
l
g
o
r
i
t
h
m
T
ab
le
3
.
C
o
n
f
u
s
io
n
m
atr
ic
o
f
t
r
ain
in
g
s
et
P
r
e
d
i
c
t
e
d
c
a
t
e
g
o
r
y
A
c
t
u
a
l
c
a
t
e
g
o
r
y
1
2
3
4
5
6
7
1
1
8
0
20
0
3
0
10
0
2
20
1
8
0
0
8
0
0
0
3
0
0
2
1
0
0
0
0
0
4
3
6
0
1
9
8
8
0
0
5
0
0
0
0
1
9
6
0
0
6
0
0
0
8
0
1
9
3
0
7
10
0
0
0
0
0
1
9
4
4
co
lo
r
less
p
last
ic
b
o
ttles
wer
e
m
is
id
en
tifie
d
as
lig
h
t
b
lu
e
b
o
ttles
,
7
lig
h
t
b
lu
e
b
o
ttles
as
p
u
r
p
l
e
b
o
ttles
,
an
d
7
p
u
r
p
le
b
o
ttles
as
lig
h
t
b
lu
e
b
o
ttles
.
T
h
e
p
h
en
o
m
en
a
o
f
m
u
tu
al
m
is
ju
d
g
m
en
t
ar
e
d
e
m
o
n
s
tr
ate
d
b
y
th
ese
th
r
ee
-
co
lo
r
ed
p
last
ic
b
o
ttles
.
On
ly
2
b
lu
e
b
o
ttles
ar
e
m
is
tak
en
f
o
r
p
u
r
p
le
b
o
ttles
,
an
d
2
d
ar
k
g
r
ee
n
b
o
ttles
ar
e
m
is
tak
en
f
o
r
lig
h
t
g
r
ee
n
b
o
ttles
.
T
h
is
in
d
icate
s
t
h
at
th
e
ac
cu
r
ac
y
o
f
id
e
n
tify
in
g
p
last
ic
b
o
ttles
o
f
d
if
f
er
en
t
co
lo
r
s
is
f
air
ly
h
ig
h
,
an
d
th
e
p
h
o
to
s
o
f
b
r
o
wn
a
n
d
lig
h
t
g
r
ee
n
p
last
ic
b
o
ttles
ar
e
all
ac
cu
r
ately
id
en
tifie
d
.
B
ased
o
n
T
ab
le
4
,
th
r
o
u
g
h
o
b
s
er
v
atio
n
,
th
e
c
o
lo
r
s
o
f
th
e
lig
h
t b
lu
e,
lig
h
t p
u
r
p
le,
a
n
d
co
l
o
r
l
ess
b
o
ttles
ar
e
r
elativ
ely
s
im
ilar
,
wh
ic
h
d
eter
m
in
es
th
at
it
m
ay
b
e
r
elati
v
ely
d
i
f
f
icu
lt
t
o
id
e
n
tify
th
em
ac
cu
r
ately
.
On
th
e
co
n
tr
ar
y
,
its
d
if
f
e
r
en
ce
f
r
o
m
t
h
e
o
th
e
r
f
o
u
r
co
lo
r
s
is
r
elativ
e
ly
clea
r
,
w
h
ich
d
eter
m
in
es
th
a
t
it
m
ay
b
e
ea
s
y
to
id
en
tify
it
ac
c
u
r
ately
,
s
o
,
th
e
t
est
r
esu
lts
h
av
e
co
m
e
in
ac
co
r
d
in
g
t
o
ex
p
ec
tatio
n
s
.
T
h
e
v
o
r
t
ex
h
u
ll
an
aly
s
is
is
to
id
en
tify
th
e
r
elatio
n
s
h
ip
b
etwe
en
th
e
p
o
s
itio
n
o
f
th
e
p
last
ic
b
o
ttle
an
d
t
h
e
co
l
o
r
r
e
co
g
n
itio
n
s
ch
em
e
d
escr
ib
ed
in
th
e
ex
p
e
r
im
en
t,
s
o
th
e
ex
p
er
im
en
tal
p
latf
o
r
m
n
ee
d
s
to
b
e
b
u
ilt
b
ef
o
r
e
th
e
illu
m
in
atio
n
co
n
d
itio
n
s
h
av
e
b
ee
n
s
im
u
lated
an
d
an
aly
ze
d
,
as in
T
ab
le
5
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
Ob
ject
r
etri
ev
a
l a
n
a
lysi
s
o
n
p
la
s
tic
b
o
ttle wa
s
te
r
ec
yc
lin
g
-
b
a
s
ed
ima
g
e
co
n
tr
o
l
…
(
Ma
r
is
a
)
2063
T
ab
le
4
.
C
o
n
f
u
s
io
n
m
atr
ic
o
f
t
h
e
test
s
et
P
r
e
d
i
c
t
e
d
c
a
t
e
g
o
r
y
A
c
t
u
a
l
C
a
t
e
g
o
r
y
1
2
3
4
5
6
7
1
85
13
0
4
0
0
8
2
15
20
0
0
0
0
0
3
0
1
0
0
1
1
0
0
0
0
0
4
0
4
0
98
0
0
0
5
0
0
0
0
1
1
0
0
0
6
0
0
0
0
0
1
0
0
0
7
6
0
0
0
0
0
98
T
ab
le
5
.
E
x
p
er
im
en
tal
r
esu
lts
o
f
th
e
d
is
cr
im
in
atio
n
o
f
th
e
p
o
s
itio
n
r
elatio
n
s
h
ip
s
b
etwe
en
p
l
asti
c
b
o
ttles
P
o
si
t
i
o
n
r
e
l
a
t
i
o
n
s
h
i
p
s
C
o
n
v
e
x
h
u
l
l
D
i
sj
o
i
n
t
t
a
r
g
e
t
s
A
d
j
a
c
e
n
t
t
a
r
g
e
t
s
O
v
e
r
l
a
p
p
i
n
g
t
a
r
g
e
t
s
Q
u
a
n
t
i
t
y
40
40
40
Q
u
a
n
t
i
t
y
w
i
t
h
c
o
r
r
e
c
t
j
u
d
g
me
n
t
40
30
40
A
c
c
u
r
a
c
y
1
0
0
%
9
0
,
2
0
%
1
0
0
%
To
t
a
l
a
c
c
u
r
a
c
y
9
8
.
6
0
%
B
ased
o
n
th
e
test
f
in
d
in
g
s
,
th
e
class
if
icat
io
n
ac
cu
r
ac
y
ten
d
s
to
s
ettle
wh
en
th
e
n
u
m
b
er
o
f
ch
ar
ac
ter
is
tics
r
ea
ch
es 8
.
T
h
is
d
em
o
n
s
tr
ates th
at
ce
r
tain
ca
n
d
id
ate
tr
aits
wi
th
lo
wer
weig
h
ts
ar
e
n
o
t im
p
o
r
tan
t,
allo
win
g
f
o
r
f
ea
tu
r
e
lim
itatio
n
.
W
h
en
it
co
m
es
to
p
last
ic
b
o
t
tle
co
lo
r
r
ec
o
g
n
itio
n
,
t
h
e
elem
en
ts
th
at
weig
h
th
e
m
o
s
t
ar
e
ch
o
s
en
as
co
lo
r
f
ea
tu
r
es.
C
lass
if
icat
io
n
m
o
d
els
wit
h
v
ar
y
in
g
t
r
ain
in
g
s
et
s
izes
ar
e
tr
ain
ed
a
n
d
test
ed
with
test
s
et
s
in
o
r
d
er
to
ex
am
in
e
th
e
im
p
ac
t
o
f
tr
ain
in
g
s
et
s
ize
o
n
co
lo
r
id
e
n
tific
atio
n
b
a
s
ed
o
n
th
e
s
y
s
tem
'
s
ac
tu
al
o
p
e
r
atin
g
en
v
ir
o
n
m
en
t
an
d
th
e
eig
h
t
co
l
o
r
f
ea
tu
r
es
t
h
at
wer
e
c
h
o
s
en
.
E
ac
h
co
lo
r
o
f
p
last
ic
b
o
ttle
h
as
th
e
s
am
e
q
u
an
tity
in
b
o
th
th
e
t
est an
d
tr
ain
in
g
s
ets.
Nu
m
er
o
u
s
f
ac
to
r
s
,
in
clu
d
in
g
lig
h
tin
g
co
n
d
itio
n
s
,
co
lo
r
f
ea
tu
r
es,
an
d
th
e
g
en
er
al
s
ch
em
e
o
f
r
ec
o
g
n
itio
n
alg
o
r
ith
m
s
f
o
r
c
o
l
o
r
r
ec
o
g
n
itio
n
p
r
o
b
lem
s
,
ca
n
i
n
f
lu
en
ce
th
e
s
ize
o
f
th
e
t
r
ain
in
g
s
et.
Fo
r
ex
am
p
le,
th
e
ac
cu
r
ac
y
o
f
th
e
test
s
et
'
s
r
esu
lts
in
cr
ea
s
e
s
s
ig
n
if
ican
tly
a
s
th
e
n
u
m
b
er
o
f
tr
ain
in
g
s
et
s
am
p
les
in
cr
ea
s
es
f
o
r
co
lo
r
r
ec
o
g
n
itio
n
o
f
p
last
ic
b
o
ttles
.
T
o
g
et
th
e
g
r
ea
test
r
esu
l
ts
,
th
ese
elem
en
ts
ca
n
o
n
ly
b
e
ch
an
g
ed
b
ased
o
n
th
e
ac
tu
al
ap
p
licatio
n
c
o
n
d
itio
n
s
,
as Fig
u
r
es 1
0
an
d
1
1
illu
s
tr
ate.
Fig
u
r
e
1
0
.
Acc
u
r
ac
y
r
ate
with
d
if
f
er
en
t
n
u
m
b
e
r
o
f
f
ea
tu
r
es
Fig
u
r
e
1
1
.
T
h
e
r
elatio
n
s
h
ip
b
e
twee
n
th
e
n
u
m
b
er
o
f
s
am
p
les
f
o
r
tr
ain
in
g
an
d
th
e
ac
cu
r
ac
y
o
f
th
e
test
s
et
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
2
,
Ap
r
il
20
25
:
2
0
5
5
-
2
0
6
9
2064
3
.
3
.
Aut
o
re
g
re
s
s
iv
e
inte
g
ra
t
ed
m
o
v
ing
a
v
er
a
g
e
T
h
e
au
to
r
eg
r
ess
iv
e
in
teg
r
ated
m
o
v
in
g
a
v
er
ag
e
(
AR
I
MA
)
m
eth
o
d
is
a
f
o
r
ec
asti
n
g
m
eth
o
d
th
at
d
o
es
n
o
t
u
s
e
th
eo
r
y
o
r
in
f
lu
en
ce
b
etwe
en
v
ar
iab
les
as
in
r
e
g
r
es
s
io
n
m
o
d
els,
th
u
s
th
e
AR
I
MA
m
eth
o
d
d
o
es
n
o
t
r
eq
u
ir
e
a
n
ex
p
lan
atio
n
o
f
wh
ich
v
ar
iab
les
ar
e
d
ep
e
n
d
en
t
an
d
in
d
ep
en
d
en
t.
T
h
is
m
eth
o
d
d
o
es
n
o
t
r
e
q
u
ir
e
b
r
ea
k
in
g
p
atter
n
s
in
to
tr
en
d
,
s
ea
s
o
n
al,
cy
clica
l
co
m
p
o
n
e
n
ts
as
in
tim
e
s
er
ies
d
ata
i
n
g
en
e
r
al
[
2
3
]
.
T
h
is
tech
n
iq
u
e,
wh
ich
is
co
m
m
o
n
l
y
r
ef
er
r
e
d
to
as th
e
B
o
x
-
J
en
k
in
s
ap
p
r
o
ac
h
b
ec
au
s
e
it wa
s
cr
ea
ted
in
1
9
7
0
b
y
two
Am
er
ican
s
tatis
tician
s
,
G
.
E
.
P
.
B
o
x
an
d
G.
M.
J
en
k
in
s
,
s
o
lely
u
s
es
p
ast
d
ata
to
p
r
o
d
u
ce
p
r
ed
ictio
n
s
.
Fin
d
in
g
a
s
tr
o
n
g
s
tatis
tical
co
r
r
elatio
n
b
etwe
en
th
e
v
ar
iab
le'
s
h
is
to
r
ical
v
alu
e
an
d
its
ex
p
ec
te
d
v
alu
e
is
th
e
aim
o
f
AR
I
MA
m
o
d
elin
g
,
wh
ich
e
n
ab
les
f
o
r
ec
asti
n
g
u
s
in
g
th
e
m
o
d
el.
W
h
en
ap
p
l
y
in
g
th
e
AR
I
MA
ap
p
r
o
ac
h
,
s
tatio
n
ar
y
d
ata
is
r
e
q
u
ir
ed
;
if
n
o
t,
a
d
ata
s
tatio
n
ar
y
test
m
u
s
t
b
e
p
er
f
o
r
m
ed
.
AR
I
MA
m
o
d
els
ar
e
ca
p
ab
le
o
f
m
ak
in
g
f
u
tu
r
e
p
r
ed
ictio
n
s
b
ased
s
o
lely
o
n
h
is
to
r
ical
d
ata
[
2
4
]
.
T
h
e
AR
I
MA
f
o
r
ec
asti
n
g
m
eth
o
d
'
s
b
en
ef
its
in
clu
d
e
its
f
lex
ib
ilit
y
(
f
o
llo
win
g
d
ata
p
atter
n
s
)
,
a
r
ea
s
o
n
ab
ly
h
ig
h
f
o
r
ec
asti
n
g
ac
cu
r
ac
y
,
an
d
th
e
ab
ilit
y
to
f
o
r
ec
ast
a
v
ar
iety
o
f
v
ar
iab
l
es
q
u
ick
ly
,
ea
s
ily
,
ac
cu
r
ately
,
an
d
af
f
o
r
d
ab
ly
b
ec
au
s
e
it
s
o
lely
n
ee
d
s
h
is
to
r
ical
d
ata.
T
h
e
AR
I
MA
f
o
r
ec
asti
n
g
m
eth
o
d
'
s
d
is
ad
v
an
tag
e
is
th
at
it
m
ak
es
t
h
e
ass
u
m
p
tio
n
th
at
th
e
m
o
d
el
is
lin
ea
r
.
As
a
r
esu
lt,
n
o
n
-
lin
ea
r
p
atter
n
s
th
at
ar
e
ty
p
ical
in
tim
e
s
er
ies
ar
e
n
o
t
ca
p
tu
r
ed
b
y
th
e
AR
I
MA
m
o
d
el.
C
o
n
s
eq
u
en
tly
,
a
m
o
d
el
th
a
t
ca
n
ca
p
tu
r
e
n
o
n
-
lin
ea
r
p
atter
n
s
is
n
ee
d
ed
[
2
5
]
.
On
th
e
p
er
tin
en
t
d
etails
r
eq
u
ir
ed
to
co
m
p
r
eh
en
d
a
n
d
a
p
p
l
y
AR
I
MA
m
o
d
els
f
o
r
u
n
iv
a
r
iate
tim
e
s
er
ies,
B
o
x
an
d
J
en
k
in
s
h
av
e
s
u
cc
ess
f
u
lly
co
m
e
to
a
co
n
s
en
s
u
s
.
T
h
er
e
ar
e
m
u
ltip
le
s
te
p
s
in
th
e
p
r
o
ce
s
s
o
f
cr
ea
tin
g
an
AR
I
MA
m
o
d
el
.
Mo
d
el
id
en
tific
atio
n
,
p
ar
am
et
er
esti
m
ates,
d
iag
n
o
s
tic
ch
ec
k
in
g
,
c
h
o
o
s
in
g
t
h
e
o
p
tim
al
m
o
d
el,
an
d
f
o
r
ec
asti
n
g
ar
e
th
e
s
tep
s
in
th
e
p
r
o
ce
s
s
.
B
o
th
s
ea
s
o
n
al
an
d
n
o
n
-
s
e
aso
n
al
m
o
d
els
ar
e
in
clu
d
ed
in
t
h
e
B
o
x
-
J
en
k
in
s
m
o
d
el.
W
h
ile
th
e
AR
I
MA
(
,
,
)
m
o
d
el
is
a
ty
p
e
o
f
n
o
n
-
s
tatio
n
ar
y
m
o
d
el,
th
e
n
o
n
-
s
e
aso
n
al
s
tat
io
n
ar
y
m
o
d
el
s
in
cl
u
d
e
a
u
t
o
r
e
g
r
ess
i
v
e
(
AR
)
(
)
,
m
o
v
i
n
g
a
v
er
ag
e
(
MA
)
(
)
,
a
n
d
a
u
t
o
r
e
g
r
ess
i
v
e
m
o
v
i
n
g
a
v
e
r
a
g
e
(
AR
MA
)
(
,
)
[
2
6
]
.
3
.
3
.
1
.
E
qu
a
t
io
n
f
o
rm
ula
s
AR
is
a
m
o
d
el
o
f
r
eg
r
ess
io
n
r
esu
lts
with
its
elf
at
th
e
p
r
ev
io
u
s
tim
e.
T
h
e
g
e
n
er
al
f
o
r
m
o
f
th
e
Au
to
r
eg
r
ess
iv
e
m
o
d
el
with
th
e
ℎ
o
r
d
e
r
,
n
am
el
y
(
)
o
r
AR
I
MA
(
,
0
,
0
)
m
o
d
el
is
wr
itten
as with
th
e
(
1
)
:
=
1
−
1
+
…
+
−
+
(
)
=
(
1
)
MA
m
o
d
el,
th
e
g
en
er
al
f
o
r
m
o
f
th
e
ℎ
-
o
r
d
er
,
(
)
o
r
AR
I
MA
(
0
,
0
,
)
is
wr
itten
as
(
2
)
:
=
–
1
−
1
−
…
−
−
=
(
)
(
2
)
AR
I
MA
,
th
e
g
en
er
al
f
o
r
m
o
f
b
o
th
(
)
an
d
(
)
m
o
d
els,
n
am
ely
AR
I
MA
(
,
0
,
)
with
th
e
(
3
)
:
(
)
=
(
)
(
3)
I
f
n
o
n
s
tatio
n
ar
ity
is
ad
d
e
d
to
th
e
AR
MA
p
r
o
ce
s
s
,
th
en
th
e
AR
I
MA
(
,
,
)
m
o
d
el
with
d
d
if
f
e
r
en
cin
g
is
wr
itten
with
th
e
(
4
)
;
(
)
(
1
−
)
=
(
)
(
4
)
3
.
3
.
2
.
Aut
o
co
rr
ela
t
i
o
n
f
un
ct
io
n a
nd
pa
rt
ia
l a
uto
co
rr
ela
t
i
o
n f
un
ct
io
n
I
n
a
tim
e
s
er
ies,
th
e
au
to
co
r
r
el
atio
n
f
u
n
ctio
n
(
AC
F)
is
th
e
lin
ea
r
r
elatio
n
s
h
ip
b
etwe
en
an
d
+
.
W
h
en
d
ata
is
s
tead
y
,
t
h
e
m
ea
n
μ
an
d
v
ar
ian
ce
σ
2
r
em
ain
c
o
n
s
tan
t.
AC
F
co
n
f
i
r
m
s
th
at
th
e
m
ea
n
is
s
tatio
n
ar
y
u
s
in
g
th
e
(
5
)
:
∑
(
−
)
(
+
−
+
)
−
=
1
∑
(
−
=
1
)
2
;
=
0
,
1
,
2
,
3
(
5
)
3
.
3
.
3
.
Ana
ly
s
is
r
esu
lt
o
f
ARI
M
A
T
h
e
s
tu
d
y
'
s
v
ar
iab
les
in
clu
d
e
th
e
to
tal
am
o
u
n
t
o
f
waste
g
en
er
ated
in
I
n
d
o
n
esia
b
y
p
r
o
v
in
ce
an
d
th
e
k
in
d
o
f
p
last
ic
b
o
ttle
waste
g
en
er
ated
in
2
0
2
3
.
T
h
e
d
ata
f
o
r
an
aly
s
is
is
s
ep
ar
ated
in
to
two
s
ec
tio
n
s
:
tr
ain
in
g
d
ata
an
d
test
in
g
d
ata.
As
s
h
o
wn
in
Fig
u
r
e
1
2
,
test
in
g
d
ata
i
s
u
s
ed
f
o
r
co
m
p
ar
is
o
n
with
f
o
r
ec
asti
n
g
o
u
tco
m
es,
wh
ile
tr
ain
in
g
d
ata
is
u
s
ed
f
o
r
m
o
d
elin
g
.
Fig
u
r
e
1
3
s
h
o
ws
th
e
s
tatio
n
ar
ity
test
,
wh
ich
elim
i
n
ates
th
e
n
ec
ess
ity
f
o
r
d
if
f
e
r
en
cin
g
b
y
allo
win
g
s
tatio
n
ar
y
d
ata
to
b
e
k
n
o
w
n
f
o
r
m
ally
o
r
v
is
u
ally
.
T
h
e
f
o
r
m
al
test
ca
n
b
e
p
er
f
o
r
m
ed
u
s
in
g
th
e
au
g
m
e
n
t
ed
Dick
ey
-
Fu
ller
(
ADF
)
test
,
wh
ile
th
e
v
is
u
al
test
is
p
er
f
o
r
m
ed
b
y
ex
am
i
n
in
g
Evaluation Warning : The document was created with Spire.PDF for Python.