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.
14
,
No
.
3
,
J
u
n
e
2
0
1
9
,
p
p
.
1235
~
1
2
4
3
I
SS
N:
2
5
0
2
-
4
7
5
2
,
DOI
: 1
0
.
1
1
5
9
1
/ijeecs.v
1
4
.i
3
.
p
p
1
2
3
5
-
1
2
4
3
1235
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
co
r
e.
co
m/jo
u
r
n
a
ls
/in
d
ex
.
p
h
p
/
ijeec
s
I
dentif
ica
tion
i
nf
o
rma
tion sens
o
rs o
f
ro
bo
t
sy
stems
I
g
o
r
P
a
rk
ho
m
ey
1
,
J
uli
y
B
o
iko
2
,
O
lek
s
a
nd
er
E
ro
m
enko
3
1
Tec
h
n
ica
l
Cy
b
e
rn
e
ti
c
s De
p
a
rtme
n
t,
Na
ti
o
n
a
l
Tec
h
n
ica
l
Un
i
v
e
rsity
o
f
Uk
ra
in
e
,
Ig
o
r
S
ik
o
rsk
y
Ky
i
v
P
o
ly
tec
h
n
ic I
n
stit
u
te,
Uk
ra
in
e
2
De
p
a
rtme
n
t
o
f
Tele
c
o
m
m
u
n
ica
ti
o
n
s a
n
d
Ra
d
i
o
E
n
g
i
n
e
e
rin
g
,
Kh
m
e
ln
y
tsk
y
Na
ti
o
n
a
l
Un
iv
e
rsity
,
Uk
r
a
in
e
3
De
p
a
rtme
n
t
o
f
P
h
y
sic
s a
n
d
El
e
c
t
rica
l
En
g
i
n
e
e
rin
g
,
Kh
m
e
ln
y
tsk
y
Na
ti
o
n
a
l
Un
i
v
e
rsity
,
Uk
ra
i
n
e
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Dec
2
2
,
2
0
1
8
R
ev
is
ed
J
an
2
1
,
2
0
1
9
Acc
ep
ted
Feb
2
8
,
2
0
1
9
At
th
e
p
re
se
n
t
ti
m
e
,
th
e
c
o
m
p
lex
it
y
o
f
id
e
n
ti
fica
ti
o
n
is
to
fi
n
d
su
c
h
a
d
e
sc
rip
ti
o
n
,
in
wh
ich
t
h
e
ima
g
e
(in
f
o
rm
a
ti
o
n
)
o
f
e
a
c
h
c
las
s
w
o
u
l
d
h
a
v
e
id
e
n
ti
fie
d
sim
il
a
r
p
ro
p
e
rti
e
s.
T
h
e
tas
k
is
to
m
a
k
e
th
e
tran
sfo
rm
e
d
d
e
sc
rip
ti
o
n
in
c
lu
d
e
s
th
e
wh
o
le
se
t
o
f
in
p
u
t
i
m
a
g
e
s,
u
n
it
e
d
b
y
t
h
e
sim
il
a
rit
y
c
las
s
b
y
t
h
e
g
iv
e
n
ra
ti
o
.
Us
in
g
th
e
o
rd
i
n
a
t
e
s
o
f
a
n
a
u
t
o
c
o
rre
latio
n
f
u
n
c
t
io
n
is
a
n
in
se
p
a
ra
b
le
sh
ift
i
n
th
e
c
e
n
ter
o
f
g
ra
v
it
y
o
f
a
n
ima
g
e
,
w
h
ich
lea
d
s
t
o
a
c
h
a
n
g
e
o
f
su
c
h
d
e
sc
rip
ti
o
n
.
Nic
e
st,
t
h
e
c
o
n
c
e
p
t
o
f
a
n
in
v
a
rian
t
d
e
sc
rip
ti
o
n
o
f
in
fo
rm
a
ti
o
n
a
rise
s,
th
is
is
a
n
a
u
t
o
c
o
rre
latio
n
fu
n
c
ti
o
n
,
w
h
ich
is
i
n
v
a
rian
t
to
th
e
d
e
sc
rip
ti
o
n
o
f
a
n
y
d
isp
lac
e
m
e
n
ts
o
f
t
h
e
ima
g
e
i
n
t
h
e
v
e
rti
c
a
l
a
n
d
h
o
rizo
n
tal
d
irec
ti
o
n
s.
T
h
e
p
ro
b
le
m
o
f
fin
d
i
n
g
a
n
o
p
ti
m
a
l
d
e
c
isio
n
ru
le
a
rise
s,
wh
ich
,
i
n
a
n
u
m
b
e
r
o
f
c
a
se
s,
c
a
n
b
e
c
o
n
str
u
c
ted
o
n
th
e
b
a
sis
o
f
a
m
e
th
o
d
,
b
a
se
d
o
n
th
e
d
e
f
in
it
i
o
n
o
f
th
e
m
a
x
imu
m
in
c
o
m
p
lete
c
o
e
fficie
n
t
o
f
sim
il
a
rit
y
.
Us
in
g
th
is
m
e
th
o
d
,
th
e
s
o
lu
ti
o
n
s,
th
a
t
a
re
a
lmo
st
u
n
in
telli
g
i
b
le
t
o
th
e
e
rro
rs
th
a
t
a
rise
d
u
e
to
t
h
e
e
ffe
c
ts
o
f
in
terfe
re
n
c
e
,
a
re
fo
u
n
d
.
Th
e
re
fo
re
,
in
i
n
c
re
m
e
n
ts
k
,
t
h
is r
u
le p
a
ss
e
s in
to
th
e
Ba
y
e
s’ r
u
le.
K
ey
w
o
r
d
s
:
Au
to
co
r
r
elatio
n
f
u
n
ctio
n
C
o
ef
f
icien
t o
f
s
im
ilar
ity
Descr
ip
tio
n
o
f
im
ag
es
I
m
ag
e
b
o
r
d
er
I
n
v
ar
ian
ce
Co
p
y
rig
h
t
©
2
0
1
9
In
stit
u
te o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
J
u
liy
B
o
ik
o
,
Dep
ar
tm
en
t o
f
T
elec
o
m
m
u
n
ic
atio
n
s
an
d
R
ad
io
E
n
g
in
ee
r
in
g
,
Kh
m
eln
y
ts
k
y
Natio
n
al
Un
i
v
er
s
ity
,
Uk
r
ain
e
.
E
m
ail:
b
o
ik
o
_
j
u
liu
s
@
u
k
r
.
n
et
1.
I
NT
RO
D
UCT
I
O
N
I
n
th
e
wo
r
k
s
o
f
au
th
o
r
s
s
u
c
h
as
[
1
]
-
[
9
]
a
n
d
o
th
er
.
I
t
is
n
o
ted
t
h
at
in
p
r
ac
tice
f
o
r
s
o
l
v
in
g
t
h
ese
p
r
o
b
lem
s
,
wh
e
n
th
e
class
if
icatio
n
p
r
o
ce
s
s
is
b
ased
o
n
in
co
m
p
lete
d
ata,
th
e
p
r
o
b
lem
o
f
f
in
d
in
g
a
n
o
p
tim
al
d
ec
id
in
g
r
u
le
ar
is
es,
th
e
m
et
h
o
d
s
o
f
d
eter
m
in
atio
n
o
f
wh
i
ch
ar
e
b
ased
o
n
th
e
d
ef
in
itio
n
o
f
th
e
m
ax
im
u
m
in
co
m
p
lete
co
ef
f
icien
t o
f
s
im
ilar
ity
.
Ho
wev
er
,
th
ese
m
et
h
o
d
s
d
o
n
o
t
tak
e
i
n
to
ac
co
u
n
t
th
e
ef
f
ec
t
o
f
in
ter
f
er
en
ce
o
n
th
e
r
e
co
g
n
itio
n
p
r
o
ce
s
s
.
B
ec
au
s
e
o
f
te
n
in
th
e
tr
ain
in
g
s
eq
u
e
n
ce
im
a
g
es
ar
e
p
r
esen
ted
th
at
ar
e
n
o
t
s
u
b
j
ec
t
to
in
te
r
f
er
en
ce
,
an
d
in
th
e
p
r
o
ce
s
s
o
f
r
ec
o
g
n
itio
n
,
an
al
y
ze
d
im
ag
es d
is
to
r
ted
b
y
n
o
is
e.
So
,
in
o
r
d
er
to
elim
in
ate
th
e
ef
f
ec
ts
o
f
in
te
r
f
er
en
ce
o
n
th
e
p
r
o
ce
s
s
o
f
r
ec
o
g
n
itio
n
,
it
is
p
r
o
p
o
s
ed
to
in
tr
o
d
u
ce
a
s
p
ec
ial
d
ec
r
ee
r
u
l
e
th
at
is
b
ased
o
n
th
e
f
ac
t
th
at
th
e
d
ec
is
io
n
o
n
t
h
e
a
f
f
iliatio
n
o
f
th
e
im
ag
e
t
o
th
e
im
ag
e
is
m
ad
e
o
n
th
e
b
asis
o
f
an
an
aly
s
is
o
f
im
ag
es
th
at
h
av
e
f
allen
in
to
a
ce
r
tain
clo
s
est
s
p
ac
e,
wh
ich
is
class
if
ied
.
2.
RE
S
E
ARCH
M
E
T
H
O
D
C
h
o
o
s
in
g
a
d
escr
ip
tio
n
o
f
im
ag
es
is
o
n
e
o
f
t
h
e
im
p
o
r
tan
t
t
ask
s
in
p
atter
n
r
ec
o
g
n
itio
n
.
I
t
is
k
n
o
wn
,
th
at
th
e
m
o
s
t
co
m
p
lete
d
escr
ip
tio
n
o
f
th
e
in
p
u
t
im
ag
es
ca
n
b
e
r
ep
r
esen
ted
as
a
co
n
tin
u
o
u
s
f
u
n
ctio
n
o
f
two
v
ar
iab
les,
wh
ich
d
escr
ib
es
t
h
e
d
is
tr
ib
u
tio
n
o
f
b
r
ig
h
tn
ess
ac
r
o
s
s
th
e
r
ec
e
p
to
r
f
ield
Z(x
,
y)
.
T
h
e
co
m
p
leten
ess
o
f
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
14
,
No
.
3
,
J
u
n
e
2
0
1
9
:
1
2
3
5
–
1
2
4
3
1236
th
ese
in
p
u
t
im
a
g
es
d
escr
ip
tio
n
h
as
a
n
u
m
b
er
o
f
s
ig
n
if
ica
n
t
d
is
ad
v
an
tag
es:
th
e
d
escr
ip
tio
n
i
s
to
o
cu
m
b
er
s
o
m
e
;
it is
n
o
t in
v
ar
ian
t w
ith
r
esp
ec
t
to
m
an
y
is
o
m
o
r
p
h
ic
tr
an
s
f
o
r
m
atio
n
s
o
f
th
e
im
a
g
es.
T
h
e
ab
ilit
y
o
f
g
en
e
r
aliza
tio
n
s
o
f
th
e
r
ec
o
g
n
itio
n
s
y
s
tem
’
s
r
esp
o
n
s
e
to
s
im
il
ar
in
p
u
t
im
ag
es
is
r
eq
u
ir
ed
,
r
eg
ar
d
less
o
f
th
eir
lo
ca
tio
n
in
th
e
r
etin
a
f
ield
,
o
n
th
e
in
ter
n
al
in
ter
ac
tio
n
s
an
d
in
ter
ac
tio
n
s
o
f
th
e
s
y
s
tem
.
T
o
en
s
u
r
e
th
e
a
b
ilit
y
o
f
g
e
n
er
aliza
tio
n
s
o
f
t
h
e
r
ea
ctio
n
,
th
er
e
a
r
e
u
s
u
ally
s
o
m
e
im
p
o
s
e
lim
itatio
n
s
,
wh
ich
d
ep
en
d
o
n
th
e
n
atu
r
e
o
f
th
e
s
im
ilar
ity
r
atio
.
T
h
e
r
estrictio
n
s
,
im
p
o
s
ed
o
n
th
e
lo
g
ical
n
atu
r
e
o
f
th
e
s
im
ilar
ity
r
atio
,
ar
e
th
ey
s
h
o
u
ld
h
av
e
th
e
p
r
o
p
er
ty
o
f
s
y
m
m
et
r
y
an
d
r
ef
lectiv
ity
,
th
at
is
,
if
A
is
lik
e
B
,
th
en
B
is
lik
e
A
,
an
d
A
is
alwa
y
s
lik
e
its
elf
.
T
h
er
e
ar
e
a
lar
g
e
n
u
m
b
er
o
f
s
im
ilar
ity
r
atio
s
in
n
atu
r
e,
wh
ich
th
ese
co
n
d
itio
n
s
ar
e
in
h
er
en
t
in
.
T
h
ese
in
clu
d
e:
th
e
s
o
lid
m
o
tio
n
o
f
th
e
im
a
g
e,
s
o
m
e
ty
p
es
o
f
co
n
tin
u
o
u
s
d
ef
o
r
m
atio
n
s
,
to
p
o
lo
g
ical
eq
u
iv
alen
ce
o
f
th
e
im
ag
es.
So
lid
m
o
tio
n
r
e
f
er
s
to
th
e
r
o
tati
o
n
a
n
d
m
o
v
e
m
en
t
o
f
th
e
im
a
g
e,
wh
ich
is
p
ar
allel
to
th
e
h
o
r
izo
n
tal
o
r
v
er
tical
ax
is
.
2.
1.
Rec
o
g
nitio
n
S
y
s
t
em
s
P
ro
blem
s
R
ec
o
g
n
itio
n
s
y
s
tem
s
,
p
o
s
s
ess
in
g
th
e
p
r
o
p
er
ty
o
f
g
en
er
aliz
atio
n
b
y
s
im
ilar
ity
,
a
r
e
c
h
ar
a
cter
ized
b
y
s
ig
n
if
ican
t
s
tr
u
ctu
r
al
co
m
p
lic
atio
n
s
(
f
o
r
ex
am
p
le,
an
in
c
r
ea
s
e
in
th
e
n
u
m
b
er
o
f
lay
er
s
o
f
A
-
elem
en
ts
in
p
er
ce
p
tr
o
n
)
c
o
m
p
ar
e
d
with
co
n
v
en
tio
n
al
s
y
s
tem
s
.
T
h
er
e
f
o
r
e,
it
is
d
esira
b
le
to
p
r
e
-
c
o
n
v
er
t
t
h
e
o
r
ig
in
al
d
escr
ip
tio
n
in
s
u
ch
a
way
as
t
o
g
en
er
alize
all
s
u
ch
o
b
jects
an
d
to
r
ea
ct,
in
a
d
if
f
er
en
tiated
wa
y
,
to
o
b
jects
th
at
ar
e
n
o
t similar
[
1
0
]
,
[
11]
.
T
h
e
class
o
f
s
im
ilar
ity
in
a
g
iv
en
r
atio
s
tan
d
s
f
o
r
th
e
s
et
o
f
in
p
u
t
im
ag
es,
s
im
ilar
in
th
is
r
atio
.
I
t
is
b
eliev
ed
,
th
at
th
e
s
im
ilar
ity
r
atio
is
th
e
im
p
o
s
itio
n
o
f
a
n
im
ag
e
s
o
th
at
A
∪B
/R
,
wh
ich
m
ea
n
s
A
is
s
im
ilar
to
B
in
r
elatio
n
(
wh
er
e
is
th
e
r
elativ
ity
o
f
th
e
m
o
tio
n
)
.
T
h
is
m
ea
n
s
th
at
A
is
a
m
ap
p
in
g
o
f
t
h
e
d
is
p
lace
m
en
t
B
,
an
d
B
is
a
r
ef
lectio
n
o
f
th
e
m
o
tio
n
o
f
A
.
T
h
e
p
r
o
b
lem
is
th
at
th
e
tr
an
s
f
o
r
m
ed
d
escr
ip
tio
n
in
clu
d
es
th
e
wh
o
le
s
et
o
f
in
p
u
t
im
ag
es,
u
n
ited
b
y
th
e
s
im
ilar
ity
class
b
y
th
e
g
iv
en
r
atio
n
.
T
h
e
au
to
co
r
r
elatio
n
f
u
n
ctio
n
ca
r
r
ies
s
u
f
f
icien
tly
co
m
p
lete
in
f
o
r
m
atio
n
ab
o
u
t
th
e
ch
ar
ac
ter
o
f
th
e
in
p
u
t
im
ag
e
[
12
]
-
[
1
5
]
in
ad
d
itio
n
,
it is
in
v
ar
i
a
n
t to
war
d
s
to
th
e
d
escr
ip
tio
n
o
f
m
o
v
in
g
im
ag
es in
th
e
v
er
tical
an
d
h
o
r
i
zo
n
tal
d
ir
ec
tio
n
s
.
T
o
en
s
u
r
e
th
e
in
v
ar
ian
ce
o
f
th
e
d
escr
ip
tio
n
to
th
e
m
o
v
em
e
n
t
o
f
th
e
im
ag
e,
it
is
en
o
u
g
h
to
u
s
e
th
e
o
r
d
in
ates
o
f
th
e
au
to
co
r
r
elatio
n
f
u
n
ctio
n
as
th
e
d
escr
ip
tio
n
elem
en
ts
.
Ho
wev
er
,
th
e
s
h
if
t
in
th
e
ce
n
ter
o
f
g
r
av
ity
o
f
th
e
im
ag
e
lea
d
s
to
a
ch
an
g
e
in
s
u
c
h
a
d
e
s
cr
ip
tio
n
.
T
o
r
ed
u
ce
th
e
ef
f
ec
t
o
f
th
e
s
h
if
t
o
f
th
e
ce
n
ter
o
f
g
r
av
ity
o
n
th
e
d
escr
ip
tio
n
o
f
t
h
e
in
p
u
t im
ag
e,
wh
ich
is
co
m
p
iled
f
r
o
m
th
e
o
r
d
in
ates o
f
s
u
c
h
an
au
to
co
r
r
elatio
n
f
u
n
ctio
n
,
o
n
e
s
h
o
u
ld
ex
clu
d
e
f
r
o
m
th
e
d
escr
ip
tio
n
o
r
d
in
at
es,
co
r
r
esp
o
n
d
in
g
to
a
r
o
t
atio
n
an
g
le
clo
s
e
to
0
º
an
d
1
8
0
º
.
I
t
is
d
esira
b
le
to
o
b
tain
s
u
ch
a
d
escr
ip
tio
n
th
at
wo
u
ld
co
v
er
th
e
wh
o
le
s
et
o
f
in
p
u
t
im
ag
es,
u
n
ited
b
y
th
e
s
im
ilar
ity
clas
s
o
f
all
d
is
p
l
ac
em
en
ts
o
f
im
ag
es r
elativ
e
to
th
e
r
ec
ep
to
r
f
ield
.
Su
ch
a
d
es
cr
ip
tio
n
is
in
v
ar
ian
t
wi
th
r
esp
ec
t
to
an
y
d
is
p
lace
m
en
t
o
f
a
n
im
ag
e.
I
n
o
r
d
e
r
to
o
b
tain
an
in
v
ar
ian
t
d
escr
ip
tio
n
,
with
r
esp
ec
t
to
all
th
e
r
ig
id
d
is
p
lace
m
en
ts
,
it
is
n
ec
ess
ar
y
to
cr
ea
te
a
f
u
n
d
am
e
n
tally
n
ew
ty
p
e
o
f
s
ca
n
.
I
f
tw
o
r
an
d
o
m
f
u
n
ctio
n
s
x=x
(
t)
an
d
y=y
(
t)
ar
e
p
u
t
o
n
th
e
ca
m
er
a’
s
d
ef
lectio
n
s
y
s
tem
,
th
en
th
e
b
ea
m
will
m
o
v
e
r
an
d
o
m
ly
o
n
th
e
s
cr
ee
n
,
an
d
th
e
s
ig
n
al
f
r
o
m
th
e
ca
m
er
a
will
b
e
a
r
an
d
o
m
f
u
n
ctio
n
o
f
t
h
e
tim
e,
th
e
s
tatis
tical
ch
ar
ac
ter
is
tics
o
f
wh
ich
d
ep
e
n
d
o
n
b
o
t
h
th
e
n
atu
r
e
o
f
t
h
e
in
p
u
t im
ag
e
a
n
d
o
n
th
e
p
r
o
p
er
ties
o
f
th
e
f
u
n
ctio
n
s
x=x
(
t)
an
d
y=y
(
t)
.
T
h
e
m
u
ltiv
ar
iate
d
is
tr
ib
u
tio
n
o
f
th
e
o
u
tp
u
t
s
ig
n
al
g
i
v
es
it
a
co
m
p
lete
p
r
o
b
ab
ilis
tic
ch
ar
ac
ter
is
tic
.
I
t
is
o
b
v
io
u
s
,
th
at
with
s
tab
l
e
p
r
o
b
a
b
ilis
tic
ch
ar
ac
ter
is
tics
o
f
f
u
n
ctio
n
s
x=x
(
t)
an
d
y=y
(
t)
th
e
p
r
o
b
ab
ilis
tic
ch
ar
ac
ter
is
tics
o
f
th
e
o
u
tp
u
t
s
ig
n
al
will
d
ep
en
d
o
n
ly
o
n
th
e
n
atu
r
e
o
f
th
e
in
p
u
t
im
ag
e.
T
h
is
s
tatem
en
t
i
s
p
r
o
v
e
d
in
[
16
]
-
[
1
9
]
.
I
f
th
e
f
u
n
cti
o
n
Z=Z
(
x,
y)
,
wh
er
e
x=x
(
t)
a
n
d
y=y
(
t
)
.
T
h
en
if
x=x
(
t)
an
d
y=y
(
t)
ar
e
s
tati
o
n
ar
y
an
d
s
tatio
n
ar
y
-
r
an
d
o
m
f
u
n
ctio
n
s
o
f
th
e
tim
e
wi
th
ev
en
d
is
tr
ib
u
tio
n
an
d
a
v
ec
to
r
,
wh
ich
co
n
s
i
s
ts
o
f
x
an
d
y
,
ch
ar
ac
ter
ized
b
y
a
u
n
i
f
o
r
m
ly
d
is
tr
ib
u
tio
n
o
f
p
r
o
b
ab
ilit
y
,
th
e
n
th
e
f
u
n
ctio
n
Z(t)
is
s
tatio
n
ar
y
in
th
e
b
r
o
ad
a
n
d
n
ar
r
o
w
s
en
s
e;
an
d
its
p
r
o
b
ab
il
is
tic
ch
ar
ac
ter
is
tics
d
o
n
o
t
d
e
p
en
d
o
n
th
e
in
v
er
s
es
tr
an
s
f
o
r
m
atio
n
s
an
d
p
a
r
allel
tr
an
s
f
er
o
f
t
h
e
f
u
n
ctio
n
Z(x
,
y
)
.
I
t
d
ir
ec
tly
f
o
llo
ws
f
r
o
m
th
is
,
t
h
at
th
e
o
r
d
in
ates
o
f
th
e
au
to
co
r
r
elatio
n
f
u
n
ctio
n
(
,
/
)
d
ep
en
d
o
n
ly
on
=
−
/
an
d
th
e
n
atu
r
e
o
f
th
e
d
ep
e
n
d
en
ce
Z(x
,
y)
an
d
d
o
n
o
t
d
ep
e
n
d
o
n
th
e
i
n
v
er
s
e
tr
a
n
s
f
o
r
m
ati
o
n
s
an
d
th
e
p
ar
allel
tr
an
s
f
er
o
f
th
e
f
u
n
ctio
n
.
T
h
u
s
,
th
e
d
escr
ip
tio
n
o
f
th
e
i
n
p
u
t
im
ag
e,
co
m
p
o
s
ed
o
f
th
e
o
r
d
in
ates
o
f
th
e
au
to
co
r
r
elatio
n
f
u
n
ctio
n
o
f
th
e
o
u
t
p
u
t
s
ig
n
al
o
f
th
e
te
lev
is
io
n
ca
m
er
a,
u
n
d
er
ce
r
tai
n
r
estrictio
n
s
im
p
o
s
ed
o
n
th
e
s
ig
n
al,
is
in
v
ar
ian
t
with
r
esp
ec
t
to
all
th
e
r
ig
id
m
o
v
em
en
ts
o
f
t
h
e
im
a
g
e
in
s
id
e
th
e
s
cr
ee
n
(
th
e
im
ag
e
is
ar
b
itr
ar
ily
m
o
v
ed
o
n
t
h
e
s
cr
ee
n
,
with
o
u
t le
av
in
g
an
y
o
f
its
elem
en
ts
b
ey
o
n
d
its
lim
its
)
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
I
d
en
tifi
ca
tio
n
in
f
o
r
ma
tio
n
s
en
s
o
r
s
o
f ro
b
o
t sys
tem
s
(
I
g
o
r
P
a
r
kh
o
mey
)
1237
2.
2.
T
he
P
o
s
s
ibl
e
M
et
ho
ds
f
o
r
D
escribin
g
t
he
I
m
a
g
e
I
t
wo
u
ld
s
ee
m
,
th
at
u
s
in
g
a
r
an
d
o
m
s
ca
n
a
n
d
d
escr
ip
tio
n
o
f
th
e
im
a
g
e
b
y
th
e
o
r
d
in
at
es
o
f
th
e
au
to
co
r
r
elatio
n
f
u
n
ctio
n
,
s
o
lv
es
a
v
er
y
co
m
p
licated
p
r
o
b
lem
o
f
r
ec
o
g
n
itio
n
.
Ho
wev
er
,
th
e
p
r
ac
tical
im
p
lem
en
tatio
n
o
f
s
u
ch
a
s
y
s
tem
h
as
s
ig
n
if
ica
n
t
tech
n
ical
d
if
f
ic
u
lties
.
First,
it
is
q
u
ite
d
if
f
icu
lt
to
f
u
lf
ill
all
th
e
co
n
s
tr
ain
ts
im
p
o
s
ed
o
n
t
h
e
s
ig
n
als
x(
t)
an
d
y(
t)
.
I
n
a
d
d
itio
n
,
th
e
p
r
o
v
ed
t
h
eo
r
em
r
elate
s
o
n
ly
to
th
e
q
u
alitativ
e
asp
ec
t
o
f
t
h
e
q
u
esti
o
n
an
d
d
o
es
n
o
t
r
elate
to
th
e
q
u
a
n
titativ
e
o
n
e
.
T
h
e
a
u
to
c
o
r
r
elatio
n
f
u
n
ctio
n
d
o
es
n
o
t
r
ea
lly
d
ep
en
d
o
n
th
e
m
o
v
em
en
t
o
f
th
e
im
ag
e
o
n
t
h
e
s
cr
ee
n
,
b
u
t,
at
th
e
s
am
e
ti
m
e,
its
d
if
f
er
en
ce
f
r
o
m
th
e
r
e
p
r
esen
tatio
n
o
f
th
e
im
ag
es
is
s
o
s
m
all,
th
at
it
is
p
r
ac
tically
im
p
o
s
s
ib
le
to
d
is
tin
g
u
is
h
au
to
co
r
r
elatio
n
f
u
n
ctio
n
s
,
ev
e
n
wh
en
th
e
im
ag
es,
co
r
r
esp
o
n
d
in
g
t
o
th
ese
f
u
n
ctio
n
s
,
a
r
e
q
u
ite
d
if
f
e
r
en
t
f
r
o
m
ea
ch
o
th
er
.
T
h
e
au
to
c
o
r
r
elatio
n
f
u
n
ctio
n
o
f
th
e
s
tatio
n
ar
y
s
ig
n
al
is
u
n
iq
u
ely
c
o
n
n
ec
ted
b
y
Fo
u
r
ier
tr
an
s
f
o
r
m
with
its
s
p
ec
tr
al
d
en
s
ity
:
(
,
/
)
=
(
)
=
∫
(
)
∞
0
ω
τ
d
ω
(
1
)
w
h
er
e
)
ω
(
Z
f
-
s
p
ec
tr
al
d
en
s
ity
o
f
t
h
e
s
ig
n
al
an
d
v
ice
v
er
s
a
(
)
=
2
∫
(
)
∞
0
ω
τ
d
τ
(
2
)
T
h
er
ef
o
r
e,
s
tatem
en
ts
,
co
n
ce
r
n
in
g
th
e
a
u
to
co
r
r
elatio
n
f
u
n
cti
o
n
,
ar
e
also
v
alid
f
o
r
s
p
ec
tr
al
d
en
s
ity
.
I
f
th
e
o
u
tp
u
t
s
ig
n
al
o
f
th
e
ca
m
er
a
Z(t)
g
o
es
to
th
e
an
aly
ze
r
,
wh
ich
co
n
s
is
ts
o
f
a
f
in
ite
n
u
m
b
er
o
f
f
ilter
s
with
u
n
if
o
r
m
f
r
eq
u
e
n
cy
ch
ar
ac
ter
is
tics
,
th
e
r
es
o
n
an
ce
f
r
eq
u
en
cies
o
f
wh
ich
ar
e
lo
c
ated
o
n
e
b
y
o
n
e
o
n
th
e
ax
is
ω
.
L
et’
s
s
u
p
p
o
s
e
th
a
t
th
e
o
u
tp
u
t
s
ig
n
als
o
f
t
h
e
f
il
ter
s
ar
e
r
ed
u
ce
d
t
o
a
s
q
u
ar
e,
an
d
th
en
t
h
ey
ar
e
in
teg
r
ated
.
Ou
tp
u
t
s
ig
n
als
o
f
s
u
ch
an
aly
ze
r
ar
e
d
eter
m
in
e
d
b
y
th
e
d
is
tr
ib
u
tio
n
o
f
th
e
en
er
g
y
W
Z
(ω)
o
f
th
e
s
ig
n
al
Z(t)
alo
n
g
th
e
f
r
eq
u
en
c
y
ax
is
.
I
t
is
k
n
o
wn
,
th
at
th
e
weig
h
ted
au
to
co
r
r
elatio
n
f
u
n
ctio
n
o
f
a
s
ig
n
al
A
Z
(
T)q
(
T)
is
r
elate
d
to
t
h
e
Fo
u
r
ier
tr
an
s
f
o
r
m
with
its
en
er
g
y
s
p
ec
tr
u
m
W
Z
(ω)
:
(
)
=
∫
2
(
)
∞
0
−
(
3
)
wh
er
e
K
(
ω
)
-
f
r
eq
u
e
n
cy
r
esp
o
n
s
e
o
f
th
e
f
ilter
.
T
h
er
ef
o
r
e,
th
e
d
escr
ip
tio
n
o
f
th
e
in
p
u
t
im
ag
e
ca
n
b
e
f
o
r
m
ed
u
s
in
g
t
h
e
o
r
d
in
a
te
o
f
t
h
e
en
er
g
y
s
p
ec
tr
u
m
.
T
h
u
s
,
ea
ch
o
f
th
e
f
u
n
ctio
n
s
A
Z
(
T)
,
f
Z
(ω)
o
r
W
Z
(ω)
m
a
y
b
e
co
n
v
en
ien
t
f
o
r
d
escr
ib
in
g
th
e
in
p
u
t
im
ag
es
wh
en
r
ec
o
g
n
izin
g
im
ag
es.
Ho
wev
er
,
it
is
m
u
ch
ea
s
ier
to
g
et
a
ch
ar
ac
ter
is
tic
o
f
th
e
s
p
ec
tr
al
d
en
s
ity
o
f
a
s
ig
n
al
th
an
its
au
to
co
r
r
elatio
n
f
u
n
ctio
n
.
I
n
[
20
-
23]
o
n
e
o
f
th
e
p
o
s
s
ib
le
m
eth
o
d
s
f
o
r
d
escr
ib
in
g
th
e
i
m
ag
e
is
co
n
s
id
er
ed
with
th
e
h
elp
o
f
th
e
s
p
ec
tr
al
ch
ar
ac
ter
is
tics
o
f
th
e
s
ig
n
al
o
b
tain
ed
in
th
e
f
r
am
e
s
ca
n
o
f
th
e
im
ag
e.
T
o
s
im
p
l
if
y
co
n
s
id
er
atio
n
s
,
im
ag
es
with
o
n
ly
two
d
eg
r
ee
s
o
f
in
ten
s
ity
o
f
in
f
o
r
m
atio
n
ar
e
co
n
s
id
er
ed
,
b
u
t
all
th
is
is
tr
u
e
f
o
r
im
a
g
es
with
a
co
n
tin
u
o
u
s
ch
an
g
e
in
in
ten
s
ity
.
I
n
th
e
g
en
er
al
ca
s
e,
th
e
s
ig
n
al,
r
ec
eiv
ed
at
th
e
o
u
tp
u
t o
f
t
h
e
t
elev
is
io
n
ca
m
er
a,
ca
r
r
ies
all
in
f
o
r
m
atio
n
ab
o
u
t
t
h
e
s
ca
n
n
e
d
b
lack
a
n
d
wh
ite
im
ag
e.
As
a
r
u
le,
th
is
s
ig
n
al
ca
n
alwa
y
s
b
e
r
ep
r
ese
n
ted
b
y
a
n
in
f
in
ite
Fo
u
r
ier
s
er
ies:
(
)
=
0
2
+
1
ω
+
1
ω
+
2
2
+
2
2
+
⋯
,
(
4
)
W
h
er
e
,
=
2
∫
(
)
0
,
=
2
∫
(
)
0
.
S
in
ce
a
telev
is
io
n
s
ig
n
al
h
as
a
f
in
ite
s
p
ec
tr
u
m
,
th
en
an
i
n
f
in
ite
Fo
u
r
ie
r
s
er
ies
ca
n
b
e
wr
itten
as
f
in
ite
s
u
m
:
(
)
=
0
2
+
∑
=
1
+
∑
=
1
(
5
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
14
,
No
.
3
,
J
u
n
e
2
0
1
9
:
1
2
3
5
–
1
2
4
3
1238
T
h
e
f
u
n
ctio
n
f
n
(
x
)
,
an
d
h
en
ce
th
e
im
ag
e
to
wh
ich
it
co
r
r
esp
o
n
d
s
,
ca
n
b
e
g
i
v
en
b
y
t
h
e
co
e
f
f
icien
ts
o
f
th
is
s
er
ies,
wh
ich
is
eq
u
al
to
th
e
r
ep
r
esen
tatio
n
o
f
th
e
im
ag
e
o
r
c
o
ef
f
icien
ts
o
f
t
h
e
Fo
u
r
ier
s
er
ies,
o
r
o
r
d
in
ates o
f
s
p
ec
tr
al
d
en
s
ity
.
T
h
e
telev
is
io
n
s
ig
n
al
t
h
at
co
r
r
esp
o
n
d
s
to
two
in
te
n
s
ity
g
r
ad
atio
n
s
is
a
s
eq
u
e
n
ce
o
f
r
ec
tan
g
u
lar
im
p
u
ls
es
o
f
th
e
s
am
e
am
p
litu
d
e,
all
o
f
wh
ich
is
co
n
tain
ed
in
th
e
d
u
r
atio
n
o
f
im
p
u
ls
es
an
d
p
au
s
es.
I
n
ad
d
itio
n
,
th
e
telev
is
io
n
s
ig
n
al
co
n
tain
s
m
o
r
e
s
tr
in
g
a
n
d
f
r
am
e
im
p
u
ls
es,
th
eir
am
p
litu
d
e
ar
e
2
5
%
h
ig
h
er
a
m
p
litu
d
e
o
f
u
s
ef
u
l im
p
u
ls
e
s.
T
h
e
r
ec
o
g
n
itio
n
p
r
o
ce
d
u
r
e
is
g
r
ea
tly
co
m
p
licated
with
lin
e
ar
an
d
f
r
a
m
e
im
p
u
ls
es,
f
ir
s
tly
,
b
ec
au
s
e
th
ey
clo
g
th
e
u
s
ef
u
l
s
ig
n
al,
an
d
s
ec
o
n
d
ly
,
b
ec
au
s
e
t
h
eir
p
r
esen
ce
lead
s
t
o
s
ig
n
if
ican
t
ch
a
n
g
es
in
th
e
s
p
ec
tr
al
d
en
s
ity
o
f
t
h
e
s
ig
n
al.
T
h
is
is
d
u
e
to
t
h
e
f
a
ct
th
at
th
e
o
f
f
s
ets
an
d
tu
r
n
s
o
f
th
e
im
ag
e
lea
d
to
a
ch
a
n
g
e
i
n
th
e
d
u
r
atio
n
a
n
d
r
ec
o
g
n
itio
n
o
f
th
e
u
s
ef
u
l im
p
u
ls
es r
elativ
e
to
th
e
s
tr
in
g
im
p
u
ls
es is
s
h
o
wn
in
Fig
u
r
e
1
.
I
n
o
r
d
e
r
to
elim
in
ate
th
e
ef
f
ec
t
o
f
th
e
im
ag
e
s
h
if
t,
wh
ich
is
p
ar
allel
to
th
e
ax
is
o
f
t
h
e
r
ec
ep
to
r
f
ield
,
it
is
n
ec
es
s
ar
y
to
r
em
o
v
e
lin
e
ar
an
d
f
r
am
e
im
p
u
ls
es
f
r
o
m
t
h
e
T
V
s
ig
n
al.
I
n
th
is
ca
s
e,
th
e
im
ag
e
s
h
if
t
af
f
ec
ts
o
n
ly
th
e
p
h
ase
o
f
th
e
s
ig
n
al
an
d
d
o
es n
o
t a
f
f
ec
t its
s
p
ec
tr
u
m
.
T
o
elim
in
ate
th
e
ef
f
ec
t
o
f
th
e
r
o
tatio
n
,
y
o
u
n
ee
d
to
r
o
tate
th
e
im
ag
e
o
n
th
e
r
ec
e
p
tiv
e
f
i
eld
o
f
th
e
v
id
ico
n
an
d
,
as
a
f
ea
tu
r
e,
ta
k
e
th
e
a
v
er
ag
e
o
r
d
in
ate
o
f
th
e
s
p
ec
tr
u
m
in
o
n
e
r
o
tatio
n
.
I
n
t
h
is
way
,
we
g
et
th
e
s
am
e
r
esu
lts
as wh
en
r
an
d
o
m
l
y
s
ca
n
n
ed
.
Ho
wev
er
,
it
m
ay
b
e
t
h
at
im
ag
es,
b
elo
n
g
in
g
to
d
i
f
f
er
en
t
class
es,
d
if
f
er
litt
le
f
r
o
m
th
e
s
p
ec
tr
al
co
m
p
o
n
en
t.
T
o
d
is
tin
g
u
is
h
s
u
ch
im
ag
es,
it
is
n
ec
ess
ar
y
t
o
ch
o
o
s
e
n
o
t
th
e
av
e
r
ag
e
v
alu
e
s
o
f
o
r
d
in
ates
p
er
r
o
tatio
n
,
b
u
t
th
e
f
u
n
ctio
n
s
o
f
th
eir
in
s
tan
tan
eo
u
s
v
alu
es
in
ti
m
e,
th
at
is
,
to
tak
e
in
to
ac
co
u
n
t
th
e
r
ed
is
tr
ib
u
tio
n
o
f
th
e
s
p
ec
tr
al
d
en
s
ity
o
f
th
e
s
ig
n
al
d
u
r
in
g
o
n
e
r
o
tatio
n
.
T
h
e
p
r
o
b
lem
o
f
r
ec
o
g
n
itio
n
,
in
t
h
is
ca
s
e,
is
g
r
ea
tly
co
m
p
licated
b
y
th
e
f
ac
t
th
at
t
h
e
d
escr
ip
tio
n
o
f
im
a
g
es
th
r
o
u
g
h
o
u
t
th
e
v
o
lu
m
e
i
n
cr
ea
s
es
s
h
ar
p
ly
.
At
t
h
e
s
am
e
tim
e,
it
ca
n
n
o
t
b
e
g
u
ar
a
n
teed
th
at
th
e
tr
an
s
f
o
r
m
e
d
d
escr
ip
t
io
n
will
b
e
less
th
an
th
e
o
r
ig
i
n
al,
b
u
t
it
ac
q
u
ir
es
u
s
ef
u
l p
r
o
p
er
ties
o
f
in
v
ar
ian
ce
with
r
esp
ec
t to
o
f
f
s
ets an
d
tu
r
n
s
.
А
t
А
t
Fig
u
r
e
1
.
Scan
n
in
g
a
n
im
ag
e
T
ak
in
g
in
to
ac
co
u
n
t th
e
p
er
io
d
ic
n
atu
r
e
o
f
th
e
telev
is
io
n
s
ig
n
al
in
f
r
am
e
s
ca
n
an
d
s
p
ec
if
ic
m
ax
im
a
in
th
e
f
r
e
q
u
en
c
y
a
r
ea
,
m
u
ltip
le
f
r
am
e
an
d
lin
ea
r
h
ar
m
o
n
ics,
c
o
n
tain
in
g
u
s
ef
u
l
in
f
o
r
m
atio
n
,
b
an
d
f
ilter
s
s
h
o
u
l
d
b
e
s
u
p
p
lem
e
n
ted
b
y
t
h
e
b
asi
c
f
r
eq
u
en
cies
o
f
th
ese
m
a
x
im
a.
T
h
e
h
ar
m
o
n
ics
o
f
th
e
f
r
am
e
f
r
eq
u
en
c
y
ca
r
r
y
in
f
o
r
m
atio
n
ab
o
u
t
th
e
lar
g
e
d
etails
o
f
th
e
im
ag
e
a
n
d
p
r
ac
tically
,
with
o
u
t
s
ig
n
if
ica
n
t
r
ed
u
ctio
n
in
th
e
r
ec
o
g
n
itio
n
q
u
ality
,
t
h
e
lo
w
-
f
r
eq
u
en
cy
p
ar
t o
f
th
e
s
p
ec
tr
u
m
ca
n
b
e
co
m
b
in
ed
.
E
x
p
er
im
en
tal
v
e
r
if
icatio
n
o
f
th
is
s
tatem
en
t
h
as
s
h
o
wn
th
at
wh
en
s
ep
a
r
atin
g
f
r
o
m
th
e
t
elev
is
io
n
s
ig
n
al
o
f
th
e
s
p
ec
tr
u
m
o
f
l
o
w
f
r
eq
u
e
n
cies
(
5
0
-
5
0
0
Hz)
an
d
at
co
n
s
tan
t
tim
e
with
in
0
.
5
s
ec
o
n
d
s
with
a
p
er
io
d
o
f
r
o
tatio
n
o
f
th
e
im
ag
e
2
-
3
s
ec
o
n
d
s
,
ac
cu
r
ately
,
s
im
p
le
g
eo
m
etr
ic
m
o
n
o
c
h
r
o
m
e
s
h
ap
es
s
u
ch
as
tr
ian
g
les,
s
q
u
ar
es,
r
ec
tan
g
l
es,
etc
ar
e
d
escr
ib
ed
.
Fu
n
ctio
n
s
,
r
ec
ei
v
ed
at
th
e
f
ilter
o
u
tp
u
t
,
ar
e
clo
s
e
to
co
n
to
u
r
s
.
T
o
d
is
tin
g
u
is
h
th
e
class
es
o
f
th
ese
f
ig
u
r
es,
th
er
e
ar
e
s
u
f
f
icien
t
s
im
p
le
f
ea
tu
r
es
s
u
ch
as
th
e
n
u
m
b
er
o
f
tr
an
s
itio
n
s
o
f
th
e
r
e
d
is
tr
ib
u
tio
n
f
u
n
ctio
n
th
r
o
u
g
h
ze
r
o
,
th
e
n
u
m
b
er
o
f
p
o
s
itiv
e
o
r
n
e
g
ativ
e
im
p
u
ls
es.
At
f
r
eq
u
en
cies,
co
r
r
esp
o
n
d
i
n
g
to
th
e
h
ar
m
o
n
ics
o
f
lin
ea
r
s
ca
n
,
d
escr
ib
in
g
im
ag
es
o
f
m
o
d
er
ate
co
m
p
lex
ity
it
is
n
ec
ess
ar
y
to
tak
e
in
to
ac
co
u
n
t
th
e
in
f
o
r
m
a
tio
n
o
f
a
lar
g
e
r
v
o
lu
m
e
-
p
r
a
ctica
lly
to
th
e
2
0
th
h
ar
m
o
n
ic.
Hig
h
e
r
f
r
eq
u
en
cies p
r
o
v
id
e
in
f
o
r
m
atio
n
a
b
o
u
t sm
all
d
etails o
f
co
m
p
lex
im
a
g
es.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
I
d
en
tifi
ca
tio
n
in
f
o
r
ma
tio
n
s
en
s
o
r
s
o
f ro
b
o
t sys
tem
s
(
I
g
o
r
P
a
r
kh
o
mey
)
1239
3.
RE
SU
L
T
S
A
ND
D
I
SCU
SS
I
O
N
So
lv
in
g
p
r
ac
tical
p
r
o
b
lem
s
,
th
er
e
ar
e
o
f
ten
ca
s
es
wh
er
e
th
e
d
ec
is
io
n
to
attac
h
a
n
im
ag
e
S
t
o
a
ce
r
tain
im
ag
e
is
b
ased
o
n
in
co
m
p
let
e
d
ata,
th
at
is
,
wh
e
n
n
o
t
all
n
elem
en
ts
o
f
th
e
d
escr
ip
tio
n
(
attr
ib
u
tes)
ca
n
b
e
m
ea
s
u
r
ed
.
T
h
e
p
r
o
b
lem
o
f
f
i
n
d
in
g
a
n
o
p
tim
al
d
ec
is
iv
e
r
u
le
ar
is
es,
wh
ich
,
in
a
n
u
m
b
er
o
f
ca
s
es,
ca
n
b
e
co
n
s
tr
u
cted
o
n
th
e
b
asis
o
f
a
m
et
h
o
d
b
ased
o
n
th
e
d
ef
in
it
io
n
o
f
t
h
e
m
a
x
im
u
m
in
co
m
p
lete
co
ef
f
icien
t
o
f
s
im
ilar
ity
.
I
n
[
12
]
,
[
15
]
,
[
24
]
f
o
u
r
s
u
ch
m
eth
o
d
s
ar
e
g
iv
e
n
.
1.
L
et
th
e
g
iv
e
n
im
ag
e
S
=S
(
x
1
,
…,
x
n
-
k
)
,
wh
er
e
k
-
th
e
n
u
m
b
er
o
f
m
is
s
in
g
s
ig
n
s
.
T
h
en
,
to
d
eter
m
in
e
t
h
e
b
elo
n
g
in
g
o
f
th
is
im
ag
e
to
o
n
e
o
f
two
im
ag
es,
u
s
e
th
e
f
o
llo
w
in
g
r
u
le:
∈
1
(
1
/
1
,
…
,
−
)
(
2
/
1
,
…
,
−
)
>
1
(
6
)
C
o
n
s
id
er
in
g
th
at
f
o
r
ea
ch
im
a
g
e
(
1
/
1
,
…
,
−
)
=
(
1
)
(
1
,
…
,
−
/
1
)
(
1
,
…
,
−
)
(
7
)
th
e
d
ec
is
io
n
r
u
le
ca
n
b
e
f
o
r
m
u
lated
as f
o
llo
ws:
∈
1
(
1
,
…
,
−
/
1
)
(
1
,
…
,
−
/
2
)
>
(
2
)
(
1
)
(
8
)
T
h
e
d
ec
is
io
n
s
,
m
ad
e
o
n
th
e
b
a
s
is
o
f
th
is
r
u
le,
m
ay
v
a
r
y
g
r
ea
t
ly
f
r
o
m
th
e
o
p
tim
al
o
n
es.
2.
L
et’
s
ass
u
m
e
th
at
it
is
p
o
s
s
ib
le
to
d
eter
m
i
n
e
th
e
m
o
s
t
p
r
o
b
a
b
le
v
alu
es
o
f
m
is
s
in
g
attr
ib
u
te
s
.
T
h
en
we
ca
n
m
ak
e
an
e
x
p
r
ess
io
n
f
o
r
co
n
d
it
io
n
al
d
en
s
ity
o
f
th
e
p
r
o
b
a
b
ilit
ies o
f
th
e
f
o
llo
win
g
f
o
r
m
:
P
(x
1
,…,
x
n
-
k
,
x
*
n
-
k
+1
,…,
x
*
n
/V
1
)
an
d
P
(x
1
,…,
x
n
-
k
,
x
*
n
-
k
+1
,…,
x
*
n
/V
2
)
,
wh
er
e
x
*
-
p
r
o
b
a
b
le
v
alu
es o
f
s
ig
n
s
.
T
h
e
d
ec
is
io
n
r
u
le
ca
n
b
e
f
o
r
m
u
lated
as f
o
llo
ws:
∈
1
(
1
,
…
,
−
,
−
+
1
*
,
*
/
1
)
(
1
,
…
,
−
,
−
+
1
*
,
*
/
2
)
>
(
2
)
(
1
)
=
(
9
)
3.
T
h
er
e
ar
e
co
n
d
itio
n
s
in
wh
ich
th
er
e
ar
e
n
o
n
-
k
m
ea
s
u
r
e
m
en
ts
,
an
d
th
e
s
im
ilar
ity
co
ef
f
icie
n
t
is
a
r
an
d
o
m
f
u
n
ctio
n
o
f
n
o
n
-
m
ea
s
u
r
ab
le
co
o
r
d
in
ates
x
n
-
k
+1
,…,
x
n
.
I
n
th
is
ca
s
e,
th
e
s
im
ilar
ity
co
ef
f
icien
t
ca
n
b
e
d
eter
m
in
ed
b
y
th
e
f
o
r
m
u
la:
(
)
=
1
(
−
+
1
,
…
,
/
1
,
2
,
…
,
−
)
2
(
−
+
1
,
…
,
/
1
,
2
,
…
,
−
)
(1
0
)
wh
er
e
p
r
o
b
ab
ilit
ies
P
V1
an
d
P
V
2
r
elate
to
im
ag
es
V
1
an
d
V
2
ac
co
r
d
in
g
l
y
.
W
ith
a
s
im
ilar
ity
co
ef
f
icien
t
L(x
)
th
e
p
r
o
b
ab
ilit
y
d
en
s
ity
P
[
L(x
)
]
is
b
o
u
n
d
ed
.
I
n
th
is
r
e
g
ar
d
,
th
er
e
is
s
u
ch
v
alu
e
o
f
L
*
(
x)
,
th
at
m
ax
i
m
izes
P
[
L(x
)
]
v
alu
e,
s
o
P
[
L
*
(
x)
]
=ma
x
P
[
L(x
)
]
.
T
h
en
th
e
d
ec
is
io
n
r
u
le
ca
n
b
e
wr
itten
as f
o
llo
ws:
∈
1
*
(
)
>
(1
1
)
4.
C
o
n
s
id
er
in
g
th
e
s
im
ilar
ity
c
o
ef
f
icien
t
as
a
r
an
d
o
m
f
u
n
ctio
n
o
f
t
h
e
m
is
s
in
g
m
ea
s
u
r
em
e
n
ts
,
th
e
av
er
ag
e
v
alu
e
o
f
t
h
e
d
ec
is
io
n
r
u
le
m
ay
b
e
u
s
ed
in
its
co
n
s
tr
u
ctio
n
:
(
)
=
∫
(
)
∞
−
∞
[
(
)
]
(1
2
)
I
n
th
is
ca
s
e
th
e
d
ec
is
io
n
r
u
le
c
an
b
e
f
o
r
m
u
lated
as f
o
llo
ws:
∈
1
(
)
>
(1
3
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
14
,
No
.
3
,
J
u
n
e
2
0
1
9
:
1
2
3
5
–
1
2
4
3
1240
C
o
m
p
ar
in
g
d
if
f
er
en
t
d
ec
is
io
n
r
u
les,
it
is
n
ec
ess
ar
y
to
d
eter
m
in
e
wh
ich
r
u
les
g
iv
e
th
e
lea
s
t
p
r
o
b
ab
ilit
y
o
f
er
r
o
r
.
Fo
r
th
is
p
u
r
p
o
s
e,
it
is
n
ec
ess
ar
y
t
o
ca
lcu
late
th
e
p
r
o
b
ab
ilit
y
o
f
er
r
o
r
s
o
f
th
e
f
ir
s
t
a
n
d
s
ec
o
n
d
s
er
ies
an
d
I
n
th
e
g
e
n
er
al
ca
s
e,
we
ca
n
wr
ite
it a
s
f
o
llo
w:
=
(
2
)
∫
∫
…
∫
(
1
,
…
,
−
/
2
)
Ω
1
1
,
…
,
−
,
=
(
1
)
∫
∫
…
∫
(
1
,
…
,
−
/
1
)
Ω
2
1
,
…
,
−
.
(1
4
)
T
h
e
d
if
f
e
r
en
ce
b
etwe
en
th
e
d
ec
is
io
n
r
u
les
is
d
eter
m
in
ed
o
n
ly
b
y
th
e
ch
o
ice
o
f
th
e
ar
ea
o
f
in
teg
r
atio
n
.
W
e
will
ass
u
m
e
th
at
in
th
e
ar
e
a
Ω
1
,
th
e
d
ec
is
io
n
r
u
le
c
will
ch
o
o
s
e
an
im
a
g
e
V
,
an
d
in
th
e
a
r
e
a
Ω
2
–
an
im
ag
e
2
.
C
o
n
s
id
er
in
g
th
e
co
s
t
o
f
t
h
e
er
r
o
r
o
f
th
e
f
ir
s
t
an
d
th
e
s
ec
o
n
d
k
in
d
,
an
d
,
th
en
,
two
d
if
f
er
en
t
d
ec
is
io
n
r
u
les
ca
n
b
e
co
m
p
ar
ed
,
tak
in
g
in
to
ac
co
u
n
t
th
e
v
alu
e
o
f
r
is
k
f
o
r
th
em
.
So
,
if
>
,
th
en
th
e
d
ec
is
iv
e
r
u
le
c
is
b
etter
th
an
d
.
T
h
e
r
is
k
o
r
t
h
e
av
er
a
g
e
p
e
n
alty
v
alu
e
f
o
r
th
is
d
ec
is
io
n
r
u
le
c
an
b
e
o
b
tain
ed
f
r
o
m
t
h
e
f
o
r
m
u
la:
=
(
1
)
∫
…
∫
[
(
2
)
(
1
,
…
,
−
/
2
)
−
−
(
2
)
(
1
,
…
,
−
/
1
)
]
Ω
1
,
…
,
−
(1
5
)
As
it
was
s
h
o
wn
ea
r
lier
,
th
e
m
in
im
u
m
v
alu
e
is
ac
h
iev
e
d
with
s
u
ch
a
ch
o
ice
o
f
th
e
ar
e
a
Ω
,
i
n
wh
ich
th
e
s
u
b
in
teg
r
al
ex
p
r
ess
io
n
wo
u
ld
alwa
y
s
b
e
n
e
g
ativ
e,
th
at
is
,
(
1
)
(
1
,
…
,
−
/
1
)
>
(
2
)
(
1
,
…
,
−
/
2
)
(1
6
)
I
f
th
e
co
s
t
o
f
th
e
er
r
o
r
o
f
th
e
f
ir
s
t
an
d
th
e
s
ec
o
n
d
k
in
d
a
r
e
th
e
s
am
e,
th
at
is
,
if
=
th
en
ar
ea
Ω
,
in
wh
ich
∈
1
s
h
o
u
ld
b
e
ch
o
s
en
s
o
th
at
(
1
,
…
,
−
/
1
)
(
1
,
…
,
−
/
2
)
>
(
2
)
(
1
)
(1
7
)
T
h
e
ex
p
r
ess
io
n
(
1
7
)
is
a
r
u
le
(
8
)
.
T
h
er
ef
o
r
e,
it
ca
n
b
e
ar
g
u
ed
th
at,
n
o
in
tr
o
d
u
ctio
n
o
f
ad
d
itio
n
al
p
r
o
b
a
b
ilis
tic
in
f
o
r
m
atio
n
ab
o
u
t
u
n
k
n
o
wn
s
ig
n
s
,
in
t
h
e
ca
s
e
o
f
eq
u
ality
o
f
co
s
t
o
f
e
r
r
o
r
s
,
c
an
g
iv
e
r
u
les
b
etter
th
an
r
u
le
(
6
)
.
B
ef
o
r
e
th
at
we
p
r
o
ce
e
d
ed
f
r
o
m
th
e
ass
u
m
p
tio
n
,
t
h
at
th
e
s
tatis
t
ical
p
r
o
p
er
ties
o
f
co
ll
ec
tio
n
s
o
f
ed
u
ca
tio
n
al
im
ag
es
an
d
im
a
g
e
s
,
wh
ich
a
r
e
e
n
co
u
n
ter
ed
in
r
e
co
g
n
itio
n
,
r
em
ai
n
c
o
n
s
tan
t.
O
f
ten
in
th
e
lear
n
in
g
s
eq
u
e
n
ce
im
ag
es
d
ep
ictin
g
v
ar
io
u
s
im
ag
es
th
at
ar
e
n
o
t
s
u
b
ject
to
in
ter
f
e
r
en
ce
ar
e
p
r
esen
ted
,
an
d
in
t
h
e
p
r
o
ce
s
s
o
f
r
ec
o
g
n
itio
n
,
im
ag
es
,
d
is
to
r
ted
b
y
n
o
is
e,
ar
e
an
aly
z
ed
.
I
n
ad
d
itio
n
,
if
th
e
tr
ain
in
g
o
f
th
e
in
f
o
r
m
atio
n
s
u
b
s
y
s
tem
is
co
n
d
u
cted
co
n
s
i
d
er
in
g
o
f
th
e
o
b
s
tacle
s
,
th
en
th
e
s
tatis
tica
l
p
r
o
p
er
ties
o
f
th
ese
o
b
s
tacle
s
m
ay
ev
en
tu
ally
b
e
u
n
s
tab
le.
T
h
e
l
ea
r
n
in
g
p
r
o
ce
s
s
its
elf
is
l
im
it
ed
in
tim
e.
T
h
er
ef
o
r
e,
r
ec
o
g
n
izab
le
im
ag
es
m
ay
d
if
f
er
s
ig
n
if
ica
n
tly
f
r
o
m
t
h
o
s
e
im
ag
es
th
at
wer
e
u
s
ed
in
th
e
lear
n
in
g
s
eq
u
e
n
ce
.
I
n
t
h
is
ca
s
e,
th
e
o
p
tim
al
s
o
lu
tio
n
,
o
b
tain
e
d
d
u
r
in
g
t
h
e
lear
n
in
g
p
r
o
ce
s
s
,
will
n
o
lo
n
g
er
b
e
o
p
tim
al
f
o
r
th
e
r
ec
o
g
n
itio
n
p
r
o
ce
s
s
,
an
d
h
e
n
ce
th
e
p
r
o
b
a
b
ilit
y
o
f
er
r
o
r
in
cr
ea
s
es.
Fig
u
r
e
2
s
h
o
ws th
e
q
u
alitativ
e
d
ep
en
d
en
ce
s
o
f
th
e
p
r
o
b
a
b
ilit
y
o
f
er
r
o
r
f
r
o
m
th
e
n
o
is
e
lev
el
[
25
]
-
[
29
]
.
I
n
th
e
ev
en
t
th
at
th
e
d
ec
is
io
n
r
u
le
will
b
e
o
p
tim
al
f
o
r
ea
ch
n
o
is
e
lev
el,
th
en
th
e
er
r
o
r
p
r
o
b
ab
ilit
y
in
cr
ea
s
es
with
in
cr
ea
s
in
g
n
o
is
e
an
d
r
ea
c
h
es th
e
lim
it a
t th
e
v
alu
e
o
f
0
.
5
(
d
o
tted
cu
r
v
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:
2502
-
4
7
5
2
I
d
en
tifi
ca
tio
n
in
f
o
r
ma
tio
n
s
en
s
o
r
s
o
f ro
b
o
t sys
tem
s
(
I
g
o
r
P
a
r
kh
o
mey
)
1241
1.0
1
.0
0
.5
0
P
2
2
0
Fig
u
r
e
2
.
T
h
e
er
r
o
r
d
e
p
en
d
e
n
c
e
o
n
n
o
is
e
I
f
th
e
o
p
tim
al
d
ec
is
io
n
r
u
le
is
f
o
u
n
d
o
n
ly
f
o
r
o
n
e
o
f
an
y
v
a
lu
e
o
f
t
h
e
n
o
is
e
lev
el,
an
d
in
t
h
e
f
u
r
th
er
p
r
o
ce
s
s
o
f
lear
n
in
g
is
n
o
t
r
ep
ea
ted
,
th
en
with
t
h
e
in
cr
ea
s
e
o
f
th
e
n
o
is
e
lev
el,
th
e
p
r
o
b
ab
i
lity
o
f
er
r
o
r
s
h
ar
p
ly
in
cr
ea
s
es
an
d
ca
n
r
ea
ch
v
alu
es
clo
s
e
to
o
n
e
(
s
o
lid
c
u
r
v
e)
.
At
th
e
p
o
in
t
co
r
r
esp
o
n
d
in
g
to
th
e
n
o
is
e
lev
el,
at
wh
ich
th
e
tr
ain
in
g
was
co
n
d
u
cted
,
th
e
two
cu
r
v
es
co
in
cid
e.
T
h
e
ass
ess
m
en
t
o
f
th
e
n
o
is
e
ef
f
ec
t
o
n
th
e
r
ec
o
g
n
itio
n
p
r
o
ce
s
s
is
a
v
er
y
d
if
f
icu
lt
task
,
wh
ich
,
in
t
h
e
g
en
er
al
ca
s
e,
h
as
n
o
an
aly
tical
s
o
lu
tio
n
.
T
h
e
latter
ca
n
o
n
ly
b
e
o
b
tain
ed
wh
en
t
h
e
ed
u
ca
tio
n
al
im
ag
es
an
d
au
d
ib
le
n
o
is
es
ar
e
d
is
tr
ib
u
ted
ac
co
r
d
in
g
to
n
o
r
m
al
law.
Alm
o
s
t
alwa
y
s
,
wh
en
s
o
lv
in
g
p
r
ac
tical
p
r
o
b
lem
s
,
it
is
ass
u
m
ed
th
at
at
s
m
all
d
ev
iatio
n
s
o
f
t
h
e
s
tatis
tical
p
r
o
p
er
ties
o
f
th
e
n
o
is
e,
th
e
d
ev
iatio
n
o
f
t
h
e
p
r
o
b
ab
ilit
y
o
f
er
r
o
r
f
r
o
m
its
m
in
im
u
m
v
al
u
e
is
in
s
ig
n
if
ican
t.
I
n
o
r
d
e
r
to
elim
in
ate
th
e
ef
f
ec
ts
o
f
in
ter
f
er
en
ce
o
n
th
e
p
r
o
ce
s
s
o
f
r
ec
o
g
n
itio
n
,
s
p
ec
ial
d
ec
id
in
g
r
u
les
ar
e
in
tr
o
d
u
ce
d
.
On
e
o
f
t
h
em
is
b
ased
o
n
th
e
f
ac
t
th
at
t
h
e
d
ec
is
io
n
o
n
th
e
a
f
f
iliatio
n
o
f
th
e
r
e
p
r
esen
tatio
n
to
t
h
e
im
ag
e
is
m
ad
e
o
n
th
e
b
asis
o
f
an
aly
s
is
o
f
r
ep
r
esen
tatio
n
s
th
at
h
av
e
f
allen
in
to
a
ce
r
tain
clo
s
est
s
p
ac
e,
wh
ich
is
class
if
ied
.
I
n
th
is
ca
s
e,
th
e
s
o
lu
tio
n
tak
es
in
to
ac
co
u
n
t
th
e
m
ajo
r
ity
,
wh
ich
is
in
k
ee
p
in
g
with
th
e
r
esu
lts
,
o
b
tain
ed
b
y
ca
lcu
latin
g
th
e
s
im
ilar
ity
f
ac
to
r
.
L
et'
s
f
o
r
m
u
lat
e
th
e
d
ec
is
io
n
r
u
le
as f
o
llo
ws:
∈
1
∑
[
1
/
1
+
(
(
1
)
)
]
1
=
1
>
∑
[
1
/
1
+
(
(
1
)
)
]
2
=
1
(1
8
)
I
n
th
is
e
x
p
r
ess
io
n
d
eter
m
in
es
a
p
lu
r
ality
o
f
im
ag
es,
wh
ich
q
u
ite
f
u
lly
c
h
ar
ac
ter
izes
th
e
wh
o
le
s
et
o
f
im
ag
es;
–
th
e
r
ad
i
u
s
o
f
th
e
ar
ea
,
wh
ich
s
ig
n
if
ican
tly
af
f
ec
ts
th
e
d
ec
is
io
n
.
T
h
e
s
p
h
er
e
wit
h
th
e
ce
n
ter
at
th
e
p
o
in
t,
co
r
r
esp
o
n
d
in
g
t
o
th
e
im
ag
e
,
f
o
r
m
ed
b
y
th
e
r
ad
iu
s
,
will
b
e
ca
lled
-
r
e
g
io
n
o
f
th
e
im
ag
e
is
s
h
o
wn
in
Fig
u
r
e
3
;
(
,
)
–
m
ea
s
u
r
e
o
f
t
h
e
s
im
ilar
ity
o
f
th
e
im
ag
e
with
im
ag
es
b
elo
n
g
in
g
to
th
e
im
ag
e
1
,
(
,
)
–
a
m
ea
s
u
r
e
o
f
s
im
ilar
ity
o
f
th
e
im
ag
e
with
im
ag
es b
elo
n
g
i
n
g
to
th
e
im
ag
e
2
.
Fo
r
d
is
cu
s
s
io
n
,
co
n
s
id
er
th
e
f
o
llo
win
g
.
T
h
u
s
,
f
o
r
a
r
ath
er
lar
g
e
m
ea
n
in
g
,
th
is
r
u
le
d
e
f
in
es
th
e
n
u
m
b
er
o
f
t
h
e
r
ep
r
esen
tatio
n
o
f
th
e
im
a
g
es
1
th
at
ar
e
c
o
n
tai
n
ed
with
in
a
s
p
h
er
e
with
a
r
a
d
iu
s
ce
n
ter
ed
at
th
e
p
o
in
t,
c
o
r
r
esp
o
n
d
in
g
to
th
e
im
ag
e
.
T
h
is
n
u
m
b
er
is
co
m
p
ar
ed
with
th
e
n
u
m
b
er
o
f
r
ep
r
esen
tatio
n
2
o
f
th
e
im
ag
es in
th
e
s
am
e
s
p
h
e
r
e.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
14
,
No
.
3
,
J
u
n
e
2
0
1
9
:
1
2
3
5
–
1
2
4
3
1242
2
x
1
x
S
r
Fig
u
r
e
3
.
T
h
e
in
f
o
r
m
atio
n
cir
c
le
o
f
th
e
im
ag
e
W
ith
th
is
m
eth
o
d
,
s
o
l
u
tio
n
s
ar
e
f
o
u
n
d
t
h
at
ar
e
alm
o
s
t
u
n
in
te
llig
ib
le
to
th
e
er
r
o
r
s
th
at
ar
is
e
d
u
e
to
th
e
ef
f
ec
ts
o
f
in
ter
f
e
r
en
ce
.
Ob
v
io
u
s
ly
,
with
in
cr
ea
s
in
g
k
th
is
r
u
le
g
o
es o
v
er
t
o
th
e
B
ay
es’
r
u
le
[
2
9
,
3
0
]
.
4.
CO
NCLU
SI
O
N
I
n
th
is
p
ap
er
,
th
e
p
r
o
ce
s
s
o
f
id
en
tific
atio
n
is
co
n
s
id
er
ed
in
th
e
ca
s
e
o
f
in
co
m
p
lete
in
p
u
t
in
f
o
r
m
atio
n
.
T
h
e
co
m
p
lex
ity
o
f
t
h
is
p
r
o
ce
s
s
is
to
f
in
d
s
u
ch
a
d
escr
ip
tio
n
in
wh
ich
th
e
im
ag
e
(
in
f
o
r
m
a
tio
n
)
o
f
ea
ch
class
wo
u
ld
h
a
v
e
d
e
f
in
ed
s
im
ilar
p
r
o
p
er
ties
.
T
h
e
p
r
o
b
lem
o
f
f
i
n
d
in
g
th
e
o
p
tim
al
d
ec
is
iv
e
r
u
l
e
ar
is
es,
wh
ich
in
s
o
m
e
ca
s
es
ca
n
b
e
co
n
s
tr
u
cte
d
o
n
th
e
b
asis
o
f
a
m
eth
o
d
b
a
s
ed
o
n
th
e
d
ef
in
itio
n
o
f
th
e
m
ax
im
u
m
in
c
o
m
p
lete
co
ef
f
icien
t
o
f
s
im
ilar
ity
.
T
o
elim
in
ate
th
e
in
f
lu
en
ce
o
f
in
ter
f
er
en
ce
o
n
th
e
r
ec
o
g
n
itio
n
p
r
o
ce
s
s
,
s
p
ec
ial
d
ec
is
io
n
r
u
les ar
e
in
tr
o
d
u
ce
d
.
On
e
o
f
th
em
is
b
ased
o
n
th
e
f
ac
t
th
at
t
h
e
d
ec
is
io
n
o
n
th
e
b
elo
n
g
in
g
o
f
t
h
e
im
a
g
e
to
th
e
im
ag
e
is
m
ad
e
o
n
th
e
b
asis
o
f
th
e
an
aly
s
is
o
f
th
e
im
ag
es
th
at
f
all
in
t
o
a
ce
r
tain
clo
s
e
s
p
ac
e,
is
clas
s
if
ied
.
I
n
th
is
ca
s
e,
th
e
d
ec
is
io
n
tak
es
in
to
ac
co
u
n
t
th
e
m
ajo
r
ity
,
wh
ich
ag
r
ee
s
well
with
th
e
r
esu
lts
o
b
tain
e
d
b
y
ca
lcu
latin
g
th
e
s
im
ilar
ity
co
ef
f
icien
t.
T
h
is
all
o
ws
y
o
u
to
f
in
d
s
o
lu
tio
n
s
th
at
ar
e
alm
o
s
t
n
o
t
s
en
s
itiv
e
to
er
r
o
r
s
th
at
o
cc
u
r
d
u
e
to
in
ter
f
er
en
ce
.
RE
F
E
R
E
NC
E
S
[1
]
Zh
a
n
g
K
,
Wan
g
X.
M
o
ti
o
n
fu
zz
y
ima
g
e
s
re
d
u
c
ti
o
n
o
f
h
ig
h
-
v
o
lt
a
g
e
li
n
e
in
s
p
e
c
ti
o
n
b
a
se
d
o
n
sp
e
c
tru
m
a
n
a
lys
is
a
n
d
ima
g
e
a
u
t
o
c
o
rr
e
la
ti
o
n
.
P
r
o
c
e
e
d
in
g
s
o
f
t
h
e
2
0
1
7
IEE
E
In
tern
a
ti
o
n
a
l
C
o
n
fe
re
n
c
e
o
n
R
o
b
o
ti
c
s
a
n
d
Bi
o
m
ime
ti
c
s
(ROBIO
)
,
Ch
in
a
,
2
0
1
7
;
1
1
6
0
–
1
1
6
4
.
[2
]
Attam
imi
M
,
M
a
rd
i
y
a
n
t
o
R,
Irfa
n
sy
a
h
AN
.
In
c
li
n
e
d
Im
a
g
e
Re
c
o
g
n
it
i
o
n
fo
r
Ae
rial
M
a
p
p
in
g
u
sin
g
De
e
p
Lea
rn
in
g
a
n
d
Tree
b
a
se
d
M
o
d
e
ls
.
T
EL
KO
M
NIKA
T
e
lec
o
mm
u
n
ica
ti
o
n
,
Co
mp
u
ti
n
g
,
El
e
c
tro
n
ics
a
n
d
C
o
n
tro
l
.
2
0
1
8
;
1
6
(6
):
3
0
3
4
-
3
0
4
4
.
[3
]
Ra
v
a
z
z
i
C,
C
o
lu
c
c
ia
G
,
M
a
g
li
E.
Cu
r
l
-
Co
n
stra
in
e
d
G
ra
d
ien
t
Esti
m
a
ti
o
n
fo
r
Im
a
g
e
Re
c
o
v
e
ry
F
r
o
m
Hig
h
l
y
In
c
o
m
p
lete
S
p
e
c
tral
Da
ta
.
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
Im
a
g
e
Pr
o
c
e
ss
in
g
.
2
0
1
7
;
2
6
(6
):
2
6
5
6
–
2
6
6
8
.
[4
]
S
h
e
u
g
h
L
,
Aliza
d
e
h
SH
.
A
n
o
te o
n
p
e
a
rs
o
n
c
o
rr
e
la
ti
o
n
c
o
e
ff
icie
n
t
a
s
a
me
tric
o
f
simila
rity
i
n
re
c
o
m
me
n
d
e
r
sy
ste
m
.
P
ro
c
e
e
d
in
g
s o
f
th
e
2
0
1
5
AI &
R
o
b
o
ti
c
s (IRANO
P
EN)
,
Ira
n
,
2
0
1
5
;
1
-
6.
[5
]
Zh
a
n
g
L
,
M
a
h
a
p
a
tra
D
,
T
ielb
e
e
k
Je
ro
e
n
AW
,
a
n
d
o
t
h
e
r.
Im
a
g
e
Re
g
istratio
n
Ba
se
d
o
n
Au
t
o
c
o
rre
latio
n
o
f
L
o
c
a
l
S
tru
c
tu
re
.
IEE
E
T
ra
n
s
a
c
ti
o
n
s o
n
M
e
d
ica
l
Ima
g
in
g
.
2
0
1
6
;
1
(3
5
):
6
3
-
75.
[6
]
Zh
u
C
,
Y
u
L
,
Ya
n
Z,
Xia
n
g
S.
F
r
e
q
u
e
n
c
y
Esti
m
a
ti
o
n
o
f
th
e
P
len
o
p
ti
c
F
u
n
c
ti
o
n
Us
in
g
t
h
e
Au
to
c
o
rre
l
a
ti
o
n
T
h
e
o
re
m
.
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
Co
mp
u
t
a
ti
o
n
a
l
Ima
g
in
g
.
2
0
1
7
;
3
(
4
):
9
6
6
-
9
8
1
.
[7
]
Hu
m
e
n
n
y
i
D,
P
a
rk
h
o
m
e
y
I
,
T
k
a
c
h
M
.
S
tru
c
t
u
ra
l
m
o
d
e
l
o
f
ro
b
o
t
-
m
a
n
ip
u
lat
o
r
f
o
r
th
e
c
a
p
tu
re
o
f
n
o
n
-
c
o
o
p
e
ra
ti
v
e
c
li
e
n
t
sp
a
c
e
c
ra
ft.
Ad
v
a
n
c
e
s in
In
t
e
ll
i
g
e
n
t
S
y
ste
ms
a
n
d
Co
m
p
u
ti
n
g
.
2
0
1
8
;
7
5
4
:
33
-
4
2
.
[8
]
Ha
z
ra
T,
CRS
K,
Ne
n
e
M
J.
S
trate
g
ies
fo
r
S
e
a
rc
h
in
g
Tar
g
e
ts
Us
in
g
M
o
b
il
e
S
e
n
s
o
rs
in
De
fe
n
se
S
c
e
n
a
rio
s
.
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
I
n
telli
g
e
n
t
S
y
ste
ms
a
n
d
Ap
p
li
c
a
ti
o
n
s
.
2
0
1
7
;
9
(
5
):
6
1
-
7
0
.
[9
]
Arifin
AS
,
Wah
y
u
n
i
DK
,
S
u
ry
a
n
e
g
a
ra
M
,
As
v
ial
M
.
S
h
i
p
S
p
e
e
d
Esti
m
a
ti
o
n
u
sin
g
Wi
re
les
s
S
e
n
so
r
Ne
two
r
k
s
:
Th
re
e
a
n
d
F
i
v
e
S
e
n
so
rs
F
o
rm
u
l
a
ti
o
n
.
T
EL
KOM
NIK
A
T
e
lec
o
mm
u
n
ica
ti
o
n
,
Co
m
p
u
t
in
g
,
El
e
c
tro
n
i
c
s
a
n
d
C
o
n
tr
o
l
.
2
0
1
8
;
1
6
(
4
):
1
5
2
7
-
1
5
3
4
.
[1
0
]
Lu
J.
Rec
u
rs
ive
fo
u
rie
r
-
b
a
se
d
h
i
g
h
-
fra
me
r
a
te
ima
g
i
n
g
.
P
ro
c
e
e
d
i
n
g
s
o
f
t
h
e
2
0
1
4
IEE
E
I
n
tern
a
ti
o
n
a
l
Ultras
o
n
ics
S
y
m
p
o
si
u
m
,
USA,
2
0
1
4
;
1
2
1
-
1
2
4
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
I
d
en
tifi
ca
tio
n
in
f
o
r
ma
tio
n
s
en
s
o
r
s
o
f ro
b
o
t sys
tem
s
(
I
g
o
r
P
a
r
kh
o
mey
)
1243
[1
1
]
Na
th
a
n
KS
,
Be
ig
i
HS
M
,
S
u
b
ra
h
m
o
n
ia
J,
Clary
G
J
,
M
a
ru
y
a
m
a
H.
Rea
l
-
t
ime
o
n
-
li
n
e
u
n
c
o
n
stra
i
n
e
d
h
a
n
d
writ
in
g
re
c
o
g
n
it
i
o
n
u
sin
g
st
a
ti
stica
l
me
th
o
d
s
.
P
ro
c
e
e
d
in
g
s
o
f
th
e
1
9
9
5
In
te
rn
a
ti
o
n
a
l
Co
n
fe
re
n
c
e
o
n
Ac
o
u
stic
s,
S
p
e
e
c
h
,
a
n
d
S
ig
n
a
l
P
ro
c
e
ss
in
g
,
De
tro
i
t
,
1
9
9
5
;
2
6
1
9
-
2
6
2
2
.
[1
2
]
Tan
g
D
,
Ya
n
g
Y
,
Fu
S.
S
e
mi
-
b
e
n
t
f
u
n
c
ti
o
n
s
wit
h
p
e
rfe
c
t
t
h
re
e
-
lev
e
l
a
d
d
it
ive
a
u
t
o
c
o
rr
e
la
ti
o
n
.
P
r
o
c
e
e
d
in
g
s
o
f
t
h
e
2
0
1
7
Ei
g
h
t
h
I
n
tern
a
ti
o
n
a
l
W
o
r
k
sh
o
p
o
n
S
ig
n
a
l
De
sig
n
a
n
d
I
ts
Ap
p
li
c
a
ti
o
n
s
i
n
C
o
m
m
u
n
ica
t
io
n
s
(IW
S
DA
)
,
S
a
p
p
o
ro
,
2
0
1
7
;
1
6
4
-
1
6
8
.
[1
3
]
Ja
a
fa
r
H,
I
sm
a
il
NS.
In
telli
g
e
n
t
P
e
rso
n
Re
c
o
g
n
i
ti
o
n
S
y
ste
m
Ba
se
d
o
n
ECG
S
ig
n
a
l
.
T
e
lec
o
mm
u
n
ica
ti
o
n
,
El
e
c
tro
n
ic
a
n
d
Co
m
p
u
ter
E
n
g
i
n
e
e
rin
g
.
2
0
1
8
:
1
0
(
1
-
1
3
):
8
3
-
8
8
.
[1
4
]
Ak
sh
a
y
a
R,
He
m
a
P
M
e
n
o
n
.
A
Re
v
iew
o
n
Re
g
istrati
o
n
o
f
M
e
d
i
c
a
l
Im
a
g
e
s
Us
in
g
G
r
a
p
h
Th
e
o
re
t
ic
Ap
p
ro
a
c
h
e
s
.
I
n
d
o
n
e
sia
n
J
o
u
rn
a
l
o
f
El
e
c
trica
l
En
g
i
n
e
e
rin
g
a
n
d
C
o
mp
u
ter
S
c
ien
c
e
.
2
0
1
8
;
1
2
(
3
):
9
7
4
-
9
8
3
.
[1
5
]
S
h
e
u
g
h
L
,
Aliza
d
e
h
S
H.
A
n
o
te o
n
p
e
a
rs
o
n
c
o
rr
e
la
ti
o
n
c
o
e
ff
icie
n
t
a
s
a
me
tric
o
f
simila
rity
i
n
re
c
o
m
me
n
d
e
r
sy
ste
m
.
P
ro
c
e
e
d
in
g
s o
f
th
e
2
0
1
5
AI &
R
o
b
o
ti
c
s (IRANO
P
EN)
,
Qa
z
v
i
n
,
2
0
1
5
;
1
-
6.
[1
6
]
S
u
n
J,
L
v
Q,
Tan
Z
,
Li
u
Y.
An
i
ma
g
e
sh
a
rp
e
n
i
n
g
stra
teg
y
b
a
se
d
o
n
m
u
lt
if
r
a
me
su
p
e
r
re
so
l
u
ti
o
n
f
o
r
mu
lt
is
p
e
c
tra
l
d
a
t
a
.
P
ro
c
e
e
d
i
n
g
s
o
f
th
e
20
1
6
8
t
h
W
o
rk
s
h
o
p
o
n
Hy
p
e
rs
p
e
c
tral
Im
a
g
e
a
n
d
S
i
g
n
a
l
P
ro
c
e
ss
in
g
:
E
v
o
lu
ti
o
n
i
n
Re
m
o
te
S
e
n
sin
g
(W
HISP
ERS
)
,
USA
,
2
0
1
6
;
1
-
5.
[1
7
]
Leo
w
CH
,
Bra
g
a
M
,
S
tan
z
io
la
A
,
a
n
d
o
t
h
e
r.
M
u
lt
i
-
fra
me
ra
te
p
la
n
e
wa
v
e
c
o
n
tra
st
-
e
n
h
a
n
c
e
u
lt
ra
so
u
n
d
ima
g
i
n
g
fo
r
tu
mo
u
r
v
a
sc
u
l
a
t
u
re
ima
g
i
n
g
a
n
d
p
e
rfu
sio
n
q
u
a
n
ti
fi
c
a
t
io
n
.
P
ro
c
e
e
d
in
g
s
o
f
t
h
e
2
0
1
7
IEE
E
In
tern
a
ti
o
n
a
l
Ultras
o
n
ics
S
y
m
p
o
si
u
m
(IUS)
,
U
S
A,
2
0
1
7
;
1
-
4.
[1
8
]
Erwin
E,
S
a
p
a
ru
d
in
S
,
S
a
p
u
tri
W.
H
y
b
ri
d
M
u
l
ti
lev
e
l
Th
re
sh
o
l
d
i
n
g
a
n
d
Im
p
r
o
v
e
d
Ha
rm
o
n
y
S
e
a
r
c
h
Alg
o
rit
h
m
f
o
r
S
e
g
m
e
n
tatio
n
.
I
n
ter
n
a
t
io
n
a
l
J
o
u
r
n
a
l
o
f
E
lec
trica
l
a
n
d
Co
mp
u
ter
E
n
g
i
n
e
e
rin
g
.
2
0
1
8
;
8
(
6
):
4
5
9
3
-
4
6
0
2
.
[1
9
]
Wen
X
,
Qia
o
L
,
M
a
S
,
a
n
d
o
th
e
r.
S
p
a
rs
e
S
u
b
s
p
a
c
e
Cl
u
ste
rin
g
fo
r
In
c
o
mp
lete
Im
a
g
e
s
.
P
ro
c
e
e
d
in
g
s
o
f
t
h
e
2
0
1
5
IEE
E
In
tern
a
ti
o
n
a
l
Co
n
fe
re
n
c
e
o
n
Co
m
p
u
ter Visio
n
Wo
r
k
sh
o
p
(IC
CVW)
,
Ch
il
e
,
2
0
1
5
;
8
5
9
-
8
6
7
.
[2
0
]
Aru
n
S
K,
Ra
v
i
K
.
An
Eff
icie
n
t
F
il
terin
g
Tec
h
n
iq
u
e
fo
r
De
n
o
i
sin
g
Co
lo
u
r
Im
a
g
e
s
.
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
El
e
c
trica
l
a
n
d
C
o
mp
u
ter
En
g
in
e
e
rin
g
.
2
0
1
8
;
8
(
5
):
3
6
0
4
-
3
6
0
8
.
[2
1
]
S
a
n
k
a
ra
n
S
,
S
e
th
u
m
a
d
h
a
v
a
n
G
.
En
tro
p
y
-
Ba
se
d
Co
lo
u
r
S
p
l
it
ti
n
g
in
De
rm
o
sc
o
p
y
Ima
g
e
s
to
Id
e
n
ti
fy
In
ter
n
a
l
Bo
rd
e
rs
.
P
ro
c
e
e
d
in
g
s
o
f
th
e
2
0
1
8
In
ter
n
a
ti
o
n
a
l
C
o
n
fe
re
n
c
e
o
n
In
v
e
n
t
iv
e
Re
se
a
rc
h
i
n
Co
m
p
u
ti
n
g
Ap
p
li
c
a
ti
o
n
s
(ICIRCA)
,
Co
imb
a
to
re
,
2
0
1
8
;
7
7
1
-
7
7
4
.
[2
2
]
Ch
iara
R,
S
o
p
h
ie
F
,
T
izia
n
o
B,
En
rico
M
.
S
p
a
rsit
y
e
stim
a
ti
o
n
f
r
o
m
c
o
m
p
re
ss
iv
e
p
ro
jec
ti
o
n
s
v
ia
sp
a
rse
ra
n
d
o
m
m
a
tri
c
e
s
.
EURA
S
IP
J
o
u
r
n
a
l
o
n
A
d
v
a
n
c
e
s in
S
i
g
n
a
l
Pr
o
c
e
ss
in
g
.
2
0
1
8
;
2
0
1
8
(
5
6
)
.
[2
3
]
Ok
ti
a
n
a
M
,
F
it
ri
A,
Aw
a
y
Y,
M
u
n
a
d
i
K
.
F
e
a
t
u
re
s
fo
r
Cr
o
ss
S
p
e
c
tral
Im
a
g
e
M
a
tch
in
g
:
A
S
u
rv
e
y
.
Bu
ll
e
ti
n
o
f
El
e
c
trica
l
En
g
in
e
e
rin
g
a
n
d
In
f
o
r
ma
ti
c
s
.
2
0
1
8
;
7
(4
):
5
5
2
-
5
6
0
.
[2
4
]
Re
d
d
y
A,
M
u
n
g
a
ra
J.
Wi
re
les
s
En
v
ir
o
n
m
e
n
t
Aw
a
re
Ad
a
p
ti
v
e
S
c
h
e
d
u
l
in
g
Tec
h
n
i
q
u
e
F
o
r
Ce
ll
u
lar
Ne
two
rk
s
.
I
n
d
o
n
e
sia
n
J
o
u
rn
a
l
o
f
El
e
c
trica
l
En
g
i
n
e
e
rin
g
a
n
d
C
o
mp
u
ter
S
c
ien
c
e
.
2
0
1
8
;
1
1
(
1
):
3
1
8
-
3
3
2
.
[2
5
]
Bo
ik
o
J,
Ero
m
e
n
k
o
O.
S
ig
n
a
l
P
r
o
c
e
ss
in
g
in
Tele
c
o
m
m
u
n
ica
ti
o
n
s
with
F
o
rwa
rd
Co
rre
c
ti
o
n
o
f
Err
o
rs
.
I
n
d
o
n
e
si
a
n
J
o
u
rn
a
l
o
f
El
e
c
trica
l
En
g
in
e
e
rin
g
a
n
d
Co
m
p
u
ter
S
c
ien
c
e
.
2
0
1
8
;
1
1
(3
):
8
6
8
-
8
7
7
.
[2
6
]
Hu
a
n
g
HC
,
Ch
e
n
P
L
,
Ch
a
n
g
FC
.
Erro
r
Res
il
ien
t
T
ra
n
sm
issio
n
fo
r
Co
mp
re
ss
e
d
S
e
n
sin
g
o
f
C
o
l
o
r
Ima
g
e
s
wit
h
M
u
lt
i
p
le
De
sc
rip
ti
o
n
Co
d
in
g
.
P
ro
c
e
e
d
in
g
s
o
f
t
h
e
2
0
1
5
Th
ird
I
n
tern
a
ti
o
n
a
l
Co
n
fe
re
n
c
e
o
n
R
o
b
o
t,
Vis
io
n
a
n
d
S
i
g
n
a
l
P
ro
c
e
ss
in
g
(RVS
P
)
,
Ka
o
h
siu
n
g
,
2
0
1
5
;
6
3
-
6
6
.
[2
7
]
P
a
rh
o
m
e
y
I
R
,
Bo
ik
o
JM,
Ero
m
e
n
k
o
OI
.
F
e
a
tu
re
s
o
f
d
ig
i
tal
sig
n
a
l
p
ro
c
e
ss
in
g
i
n
th
e
i
n
fo
rm
a
ti
o
n
c
o
n
tro
l
sy
ste
m
s
o
f
m
u
lt
ip
o
siti
o
n
a
l
ra
d
a
r
.
J
o
u
r
n
a
l
o
f
Ach
iev
e
me
n
ts i
n
M
a
ter
ia
ls
a
n
d
M
a
n
u
fa
c
t
u
rin
g
En
g
i
n
e
e
rin
g
.
2
0
1
6
;
2
(7
7
):
7
5
-
8
4
.
[2
8
]
S
h
y
n
k
a
r
u
k
O,
Bo
i
k
o
J,
Ero
m
e
n
k
o
O.
M
e
a
su
re
me
n
ts
o
f
th
e
e
n
e
rg
y
g
a
i
n
in
th
e
m
o
d
if
ied
c
irc
u
it
si
g
n
a
l
p
ro
c
e
ss
in
g
u
n
it
.
P
r
o
c
e
e
d
in
g
s
o
f
t
h
e
2
0
1
6
1
3
th
I
n
tern
a
ti
o
n
a
l
I
EE
E
C
o
n
fe
re
n
c
e
o
n
M
o
d
e
rn
P
ro
b
lem
s
o
f
Ra
d
i
o
En
g
i
n
e
e
rin
g
.
Tele
c
o
m
m
u
n
ica
ti
o
n
s a
n
d
C
o
m
p
u
t
e
r
S
c
ien
c
e
(TCS
ET
),
U
k
ra
in
e
,
2
0
1
6
;
5
8
2
-
5
8
4
.
[2
9
]
De
wi
YN
,
Rian
a
D,
M
a
n
t
o
ro
T.
Imp
ro
v
in
g
Na
ïve
Ba
y
e
s
p
e
rf
o
rm
a
n
c
e
i
n
sin
g
le
ima
g
e
p
a
p
sm
e
a
r
u
sin
g
we
ig
h
ted
p
rin
c
ip
a
l
c
o
mp
o
n
e
n
t
a
n
a
lys
is
(W
PCA
)
.
P
ro
c
e
e
d
in
g
s
o
f
th
e
2
0
1
7
I
n
tern
a
ti
o
n
a
l
Co
n
fe
re
n
c
e
o
n
Co
m
p
u
ti
n
g
,
En
g
i
n
e
e
rin
g
,
a
n
d
De
sig
n
(ICCED
)
,
M
a
lay
sia
,
2
0
1
7
;
1
-
5.
[3
0
]
Ja
h
ro
m
i
A
H,
Tah
e
ri
M
.
A
n
o
n
-
p
a
ra
me
tric
mix
tu
re
o
f
G
a
u
ss
ia
n
n
a
i
v
e
Ba
y
e
s
c
la
ss
if
ier
s
b
a
se
d
o
n
lo
c
a
l
i
n
d
e
p
e
n
d
e
n
t
fea
tu
re
s
.
P
ro
c
e
e
d
in
g
s
o
f
th
e
2
0
1
7
Artifi
c
ial
In
telli
g
e
n
c
e
a
n
d
S
ig
n
a
l
P
ro
c
e
ss
in
g
Co
n
fe
re
n
c
e
(AISP
)
,
S
h
iraz
,
2
0
1
7
;
209
-
2
1
2
.
Evaluation Warning : The document was created with Spire.PDF for Python.