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.
24
,
No
.
2
,
N
o
v
em
b
e
r
2
0
2
1
,
p
p
.
1
1
9
5
~
1
2
0
1
I
SS
N:
2
5
0
2
-
4
7
5
2
,
DOI
: 1
0
.
1
1
5
9
1
/ijeecs.v
24
.i
2
.
pp
1
1
9
5
-
1
2
0
1
1195
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs.ia
esco
r
e.
co
m
Im
plementa
tion
of
feat
ure
e
x
tractio
n
a
nd
dee
p
lea
rni
ng
-
ba
sed
ensem
ble
cla
ss
ifi
e
r
for
in
ter
fere
nc
e
mitig
a
tion
in
ra
d
a
r
sig
na
ls
N.
Durg
a
I
nd
ira
,
M.
Venu
G
o
pa
la
Ra
o
De
p
a
rtme
n
t
of
El
e
c
tro
n
ics
a
n
d
C
o
m
m
u
n
ica
ti
o
n
E
n
g
i
n
e
e
rin
g
,
Ko
n
e
ru
Lak
sh
m
a
iah
Ed
u
c
a
ti
o
n
F
o
u
n
d
ti
o
n
KLE
F
,
G
u
n
tu
r
,
I
n
d
ia
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
May
28
,
2
0
2
1
R
ev
is
ed
Au
g
31
,
2
0
2
1
Acc
ep
ted
Sep
13
,
2
0
2
1
In
a
u
to
m
o
t
iv
e
v
e
h
icle
s,
ra
d
a
r
is
th
e
one
of
th
e
c
o
m
p
o
n
e
n
t
f
o
r
a
u
to
n
o
m
o
u
s
d
riv
i
n
g
,
u
se
d
f
o
r
tar
g
e
t
d
e
te
c
ti
o
n
a
n
d
l
o
n
g
-
ra
n
g
e
se
n
si
n
g
.
Wh
e
re
a
s
in
terfe
re
n
c
e
e
x
ists
in
si
g
n
a
ls,
n
o
ise
in
c
re
a
se
s
a
n
d
it
e
ffe
c
ts
se
v
e
re
ly
wh
il
e
d
e
tec
ti
n
g
targ
e
t
o
b
jec
ts.
F
o
r
t
h
e
se
re
a
so
n
s,
v
a
rio
u
s
in
terfe
re
n
c
e
m
it
ig
a
ti
o
n
tec
h
n
iq
u
e
s
a
re
imp
lem
e
n
ted
in
th
is
p
a
p
e
r.
By
u
si
n
g
th
e
se
m
it
ig
a
ti
o
n
tec
h
n
iq
u
e
s
in
terfe
re
n
c
e
a
n
d
n
o
i
se
a
re
r
e
d
u
c
e
d
a
n
d
o
ri
g
in
a
l
si
g
n
a
ls
a
re
re
c
o
n
stru
c
ted
.
In
th
is
p
a
p
e
r,
we
p
ro
p
o
se
d
a
m
e
th
o
d
to
m
it
i
g
a
te
in
terfe
re
n
c
e
in
sig
n
a
l
u
si
n
g
d
e
e
p
lea
rn
i
n
g
.
T
h
e
p
ro
p
o
se
d
m
e
th
o
d
p
r
o
v
i
d
e
s
th
e
b
e
st
a
n
d
a
c
c
u
ra
te
p
e
rfo
rm
a
n
c
e
in
re
late
to
t
h
e
v
a
ri
o
u
s
in
terfe
re
n
c
e
c
o
n
d
i
ti
o
n
s
a
n
d
g
iv
e
s
b
e
tt
e
r
a
c
c
u
ra
c
y
c
o
m
p
a
re
d
w
it
h
o
th
e
r
e
x
isti
n
g
m
e
th
o
d
s.
K
ey
w
o
r
d
s
:
Deep
b
elief
n
etwo
r
k
Deep
lear
n
in
g
Dim
en
s
io
n
ality
r
ed
u
ctio
n
I
n
d
ep
e
n
d
en
t
c
o
m
p
o
n
en
t
an
aly
s
is
T
h
is
is
an
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r
th
e
CC
BY
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
N.
Du
r
g
a
I
n
d
ir
a
Dep
ar
tm
en
t
of
E
lectr
o
n
ics
an
d
C
o
m
m
u
n
icatio
n
E
n
g
in
ee
r
i
n
g
Ko
n
er
u
L
a
k
s
h
m
aiah
E
d
u
ca
tio
n
Fo
u
n
d
tio
n
(
KL
E
F)
Gr
ee
n
f
ield
s
,
Vad
d
eswar
am
,
Gu
n
tu
r
,
I
n
d
ia
E
m
ail:
d
u
r
g
ain
d
ir
a@
k
lu
n
iv
er
s
ity
.
in
1.
I
NT
RO
D
UCT
I
O
N
N
o
w
d
a
y
s
t
h
e
v
e
h
i
cl
es
a
r
e
e
q
u
i
p
p
e
d
w
i
t
h
s
p
e
ci
a
l
i
n
s
t
r
u
m
e
n
ts
s
u
c
h
a
r
e
c
a
l
le
d
as
a
u
t
o
n
o
m
o
u
s
v
e
h
i
c
l
es
w
h
e
r
e
r
a
d
a
r
s
a
r
e
m
o
u
n
t
e
d
,
it
r
e
q
u
i
r
e
s
v
a
r
i
o
u
s
f
u
n
c
ti
o
n
s
i
n
c
lu
d
i
n
g
t
a
r
g
e
t
d
e
t
e
c
ti
o
n
a
n
d
c
a
p
a
b
l
e
of
l
o
n
g
-
r
a
n
g
e
s
e
n
s
i
n
g
.
T
h
e
s
e
o
p
e
r
a
ti
o
n
s
can
be
p
e
r
f
o
r
m
e
d
a
u
t
o
m
a
t
i
c
a
ll
y
f
o
r
t
h
e
s
a
k
e
of
u
s
e
r
s
a
f
et
y
a
n
d
to
s
o
l
v
e
c
o
l
li
s
i
o
n
in
b
e
t
w
e
e
n
v
e
h
i
c
l
es
.
M
o
s
t
p
o
p
u
l
a
r
l
y
t
h
e
r
a
d
a
r
s
w
i
t
h
t
h
e
f
u
n
c
t
io
n
a
l
i
t
y
of
f
r
e
q
u
e
n
c
y
m
o
d
u
l
a
t
e
d
c
o
n
t
i
n
u
o
u
s
w
a
v
e
(
F
M
C
W
)
or
t
h
e
c
h
i
r
p
s
e
q
u
e
n
ce
(
CS
)
f
u
n
c
t
i
o
n
a
li
t
y
is
to
be
i
n
c
l
u
d
e
d
but
it
is
v
e
r
y
c
h
al
l
e
n
g
i
n
g
to
a
c
c
o
m
p
l
is
h
t
h
e
a
b
o
v
e
s
p
e
c
i
f
i
e
d
f
u
n
c
t
i
o
n
a
l
it
i
es
w
i
t
h
m
i
t
i
g
at
i
n
g
i
n
t
e
r
f
e
r
e
n
c
e
t
ec
h
n
i
q
u
e
[1
]
-
[
4
]
.
T
h
e
r
e
a
r
e
s
e
v
e
r
a
l
m
e
t
h
o
d
s
u
s
e
d
to
s
o
l
v
e
/
r
e
m
o
v
e
t
h
e
p
r
o
b
l
e
m
s
in
t
i
m
e
a
m
p
li
t
u
d
e
a
n
d
f
r
e
q
u
en
c
y
d
o
m
a
i
n
s
r
e
l
at
e
d
to
i
n
t
e
r
f
e
r
e
n
c
e
.
T
h
i
s
p
a
p
e
r
p
r
o
p
o
s
e
d
an
a
l
g
o
r
i
t
h
m
f
o
r
r
a
d
a
r
s
i
g
n
a
l
w
h
i
c
h
i
n
c
l
u
d
es
c
o
m
p
l
ex
i
t
y
w
i
t
h
a
s
m
al
l
c
o
m
p
u
t
a
ti
o
n
a
n
d
it
i
d
e
n
t
i
f
i
es
t
h
e
t
a
r
g
e
t
s
w
it
h
a
r
a
n
g
e
of
s
m
a
l
l
er
d
i
s
t
a
n
c
e
s
.
T
h
e
e
f
f
e
c
t
of
i
n
t
e
r
f
e
r
e
n
c
e
is
s
t
il
l
r
e
m
a
i
n
s
;
h
o
w
ev
e
r
t
h
e
t
a
r
g
e
t
is
not
d
e
t
e
c
t
e
d
w
h
e
n
t
h
e
i
n
t
e
r
f
e
r
e
n
ce
s
i
g
n
a
l
is
cl
o
s
e
r
to
t
h
e
r
a
d
a
r
t
h
a
n
t
h
e
t
a
r
g
e
t
[
5
]
,
[
6
]
.
In
our
wo
r
k
we
i
n
c
l
u
d
ed
t
h
e
d
e
e
p
l
e
a
r
n
i
n
g
te
c
h
n
i
q
u
e
s
in
r
a
d
a
r
s
to
m
i
ti
g
a
t
e
i
n
t
e
r
f
e
r
e
n
c
e
in
s
i
g
n
a
l
li
n
g
s
y
s
t
e
m
s
.
De
e
p
l
e
a
r
n
i
n
g
h
as
b
e
e
n
d
e
v
e
l
o
p
e
d
r
e
c
e
n
t
l
y
in
i
m
a
g
e
,
la
n
g
u
a
g
e
a
n
d
s
p
e
e
c
h
p
r
o
c
e
s
s
i
n
g
[7
]
-
[
1
0
]
.
In
t
h
i
s
p
a
p
e
r
r
e
c
u
r
r
e
n
t
n
e
u
r
a
l
n
e
tw
o
r
k
(
R
N
N
)
m
o
d
el
is
u
s
e
d
f
o
r
p
r
o
ce
s
s
i
n
g
d
a
t
a
(
n
o
i
s
e
r
e
d
u
c
t
i
o
n
)
,
e
l
i
m
i
n
a
ti
n
g
i
n
t
e
r
f
e
r
e
n
c
e
a
n
d
to
r
e
c
o
v
e
r
t
h
e
o
r
i
g
i
n
a
l
t
r
a
n
s
m
i
tt
e
d
s
i
g
n
a
l
e
v
e
n
in
t
h
e
ex
i
s
t
e
n
c
e
of
i
n
t
e
r
f
e
r
e
n
c
e
at
t
h
e
r
e
c
e
i
v
e
r
[
1
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.
24
,
No
.
2
,
No
v
em
b
er
2
0
2
1
:
1
1
9
5
-
1
2
0
1
1196
2.
AIM
AN
D
O
B
J
E
C
T
I
VE
T
h
e
aim
of
th
is
wo
r
k
is
to
d
e
s
ig
n
an
d
im
p
lem
e
n
tatio
n
of
f
e
atu
r
e
ex
tr
ac
tio
n
a
n
d
b
etter
cla
s
s
if
ier
f
o
r
I
n
ter
f
er
e
n
ce
Mitig
atio
n
in
r
ad
ar
s
ig
n
als.
To
o
b
tai
n
th
is
g
o
al,
th
e
p
r
im
ar
y
o
b
jectiv
e
is
,
−
To
ex
tr
ac
t
an
d
class
if
y
th
e
f
ea
tu
r
e
m
atr
ix
by
d
im
e
n
s
io
n
ality
r
ed
u
ctio
n
al
g
o
r
ith
m
.
T
h
is
will
en
h
an
ce
th
e
p
er
f
o
r
m
an
ce
f
o
r
lar
g
e
d
im
en
s
i
o
n
f
ea
tu
r
e
v
ec
to
r
.
−
To
in
v
esti
g
ate
th
e
tr
ai
n
in
g
an
d
test
in
g
d
ata
to
war
d
r
ec
o
g
n
izi
n
g
th
ei
r
o
v
er
lap
p
ed
f
o
r
m
s
in
b
o
th
f
r
eq
u
e
n
cy
an
d
tim
e
d
o
m
ain
h
e
n
ce
can
att
ain
b
etter
p
r
e
d
ictio
n
r
esu
lt.
−
To
an
aly
s
e
th
e
s
ig
n
al
r
ec
o
g
n
i
tio
n
p
er
f
o
r
m
an
ce
of
c
o
m
p
o
u
n
d
s
ig
n
als
by
ef
f
ec
tiv
e
lear
n
in
g
ar
ch
itectu
r
e
an
d
o
p
tim
izatio
n
m
eth
o
d
.
3.
M
E
T
H
O
DO
L
O
G
Y
T
h
e
p
r
esen
t
r
esear
ch
f
o
cu
s
es
on
th
e
d
esig
n
a
n
d
im
p
le
m
e
n
tatio
n
of
f
ea
t
u
r
e
ex
tr
ac
tio
n
an
d
d
ee
p
lear
n
in
g
-
b
ased
en
s
em
b
le
class
if
ier
f
o
r
in
ter
f
er
en
c
e
m
itig
atio
n
in
r
ad
ar
s
ig
n
als.
I
n
itially
,
th
e
in
p
u
t
s
ig
n
al
is
co
n
v
er
ted
in
to
b
in
a
r
y
f
o
r
m
t
h
en
e
x
tr
ac
ts
th
e
f
ea
tu
r
e
f
o
r
en
h
an
cin
g
th
e
r
ec
o
g
n
itio
n
p
er
f
o
r
m
a
n
ce
of
t
h
e
co
m
p
o
u
n
d
s
ig
n
al.
T
h
e
co
n
tr
ib
u
tio
n
of
th
is
r
esear
ch
h
as
f
o
u
r
-
f
o
ld
:
First,
will
p
r
e
-
p
r
o
ce
s
s
,
ex
tr
ac
t,
an
d
class
if
y
th
e
f
ea
tu
r
e
m
atr
ix
by
d
im
e
n
s
io
n
ality
r
ed
u
ctio
n
alg
o
r
ith
m
(
in
d
ep
en
d
en
t
co
m
p
o
n
e
n
t
an
aly
s
is
an
d
f
o
u
r
ier
tr
an
s
f
o
r
m
)
.
T
h
is
will
en
h
an
ce
th
e
p
er
f
o
r
m
a
n
ce
f
o
r
lar
g
e
d
i
m
en
s
io
n
f
ea
tu
r
e
v
ec
t
o
r
.
T
h
e
p
r
e
-
p
r
o
ce
s
s
in
g
s
tag
e
in
clu
d
es
tim
e
-
f
r
eq
u
e
n
cy
r
e
p
r
e
s
en
tatio
n
;
m
u
lti
-
lab
el
class
if
ic
atio
n
an
d
m
u
lti
-
d
ec
is
io
n
th
r
esh
o
ld
s
o
p
tim
izatio
n
ar
e
u
s
ed
f
o
r
o
u
tp
u
t
lab
el
d
e
cisi
o
n
.
Seco
n
d
,
will
m
eta
-
h
e
u
r
is
tic
b
ased
f
ir
ef
ly
alg
o
r
ith
m
is
u
s
ed
to
s
elec
t
o
p
tim
al
p
ar
am
eter
s
an
d
m
itig
ate
th
e
in
te
r
f
er
en
ce
in
b
o
t
h
tim
e
an
d
f
r
eq
u
en
cy
d
o
m
ain
[
1
4
]
-
[
1
9
]
.
T
h
i
r
d
,
will
u
s
e
ef
f
ec
tiv
e
d
ee
p
lear
n
in
g
ap
p
r
o
ac
h
(
d
ee
p
b
elief
n
etwo
r
k
)
with
v
ar
io
u
s
m
u
lti
-
lab
el
s
tr
ateg
ies
to
war
d
en
h
an
cin
g
th
e
r
ec
o
g
n
itio
n
p
er
f
o
r
m
an
ce
.
T
h
e
c
o
m
b
i
n
atio
n
of
o
p
tim
izatio
n
an
d
lear
n
in
g
tech
n
iq
u
e
will
be
u
s
ed
f
o
r
s
ig
n
al
an
aly
s
is
an
d
m
u
lti
-
d
ec
is
io
n
th
r
esh
o
ld
s
o
p
tim
izatio
n
ar
e
u
s
ed
f
o
r
o
u
t
p
u
t
f
o
r
o
u
t
p
u
t
lab
el
d
ec
is
io
n
.
Fin
ally
,
will
test
th
e
p
er
f
o
r
m
an
ce
u
s
in
g
MA
T
L
AB
s
im
u
latio
n
s
o
f
twar
e
an
d
c
o
m
p
ar
e
th
e
r
esu
lts
with
th
e
tr
ad
itio
n
al
m
eth
o
d
in
ter
m
s
of
ac
cu
r
ac
y
an
d
s
ig
n
al
to
n
o
is
e
r
atio
.
4.
M
UT
UAL
I
NT
E
RF
E
RE
NC
E
IN
AU
T
O
M
O
T
I
V
E
RAD
ARS
W
h
e
n
m
u
l
t
i
p
l
e
v
e
h
i
c
l
e
s
a
r
e
c
o
n
n
e
c
t
e
d
to
t
h
e
r
a
d
a
r
t
h
e
n
t
h
e
r
e
e
x
i
s
t
s
i
n
t
e
r
f
e
r
e
n
c
e
.
T
h
e
u
s
e
of
F
M
C
W
w
a
v
e
f
o
r
m
s
i
n
c
r
e
a
s
e
s
t
h
e
p
r
o
b
a
b
i
l
i
t
y
of
t
h
i
s
i
n
t
e
r
f
e
r
e
n
c
e
b
e
c
a
u
s
e
of
t
h
e
h
i
g
h
d
u
t
y
c
y
c
l
e
.
It
is
p
o
s
s
i
b
l
e
to
o
b
s
e
r
v
e
r
a
d
a
r
-
to
-
r
a
d
a
r
i
n
t
e
r
f
e
r
e
n
c
e
w
h
e
n
v
e
h
i
c
l
e
s
a
r
e
m
o
v
i
n
g
in
t
h
e
i
r
o
w
n
p
a
t
h
[
2
0
]
-
[
2
6
]
.
I
n
t
e
r
f
e
r
e
n
c
e
in
F
M
C
W
d
e
p
e
n
d
s
on
t
h
e
r
a
d
a
r
p
a
r
a
m
e
t
e
r
s
l
i
k
e
c
e
n
t
r
e
f
r
e
q
u
e
n
c
y
,
b
a
n
d
w
i
d
t
h
,
c
h
i
r
p
d
u
r
a
t
i
o
n
a
n
d
c
h
i
r
p
r
e
p
e
t
i
t
i
o
n
t
i
m
e
.
B
e
c
a
u
s
e
of
t
h
e
i
n
t
e
r
f
e
r
e
n
c
e
t
h
e
r
e
is
d
e
g
r
a
d
a
t
i
o
n
is
due
to
i
n
t
e
r
f
e
r
e
n
c
e
i
n
d
u
c
e
d
n
o
i
s
e
in
t
h
e
r
a
d
a
r
i
m
a
g
e
s
[
2
7
]
-
[
2
9
]
.
T
h
e
p
r
o
b
ab
ilit
y
of
en
co
u
n
ter
in
g
tim
e
-
lim
ited
i
n
ter
f
er
en
ce
th
at
lead
s
to
SIN
R
d
eg
r
ad
atio
n
is
m
u
ch
h
ig
h
er
th
an
th
e
g
h
o
s
t
tar
g
et
s
ce
n
ar
io
.
T
h
er
ef
o
r
e,
th
r
o
u
g
h
o
u
t
th
e
tr
an
s
m
is
s
io
n
an
d
r
ec
ep
tio
n
in
ter
f
er
in
g
r
a
d
ar
s
ig
n
als
h
av
e
non
-
id
en
tical
tr
an
s
m
it
p
ar
am
eter
s
.
5.
DIM
E
NS
I
O
NA
L
I
T
Y
RE
DU
CT
I
O
N
-
F
E
A
T
UR
E
E
XT
R
ACTI
O
N
A
ND
S
E
L
E
C
T
I
O
N
Dim
en
s
io
n
ality
r
ed
u
ctio
n
is
th
e
p
r
o
ce
s
s
o
f
r
ed
u
cin
g
th
e
n
u
m
b
er
o
f
v
ar
iab
les/
f
ea
tu
r
e
i
n
r
ev
iew.
D
im
en
s
io
n
ality
r
ed
u
ctio
n
is
ca
teg
o
r
ized
in
to
f
ea
t
u
r
e
s
elec
tio
n
an
d
f
ea
tu
r
e
e
x
tr
ac
tio
n
.
In
f
e
atu
r
e
ex
tr
ac
tio
n
,
th
e
p
r
in
cip
al
c
o
m
p
o
n
en
t
an
aly
s
is
(
PC
A
)
is
th
e
alg
o
r
ith
m
wh
ich
f
o
cu
s
es
on
r
e
d
u
cin
g
th
e
h
ig
h
d
im
en
s
io
n
al
s
p
ac
e
in
to
lo
wer
s
p
ac
e
an
d
in
d
e
p
en
d
en
t
co
m
p
o
n
e
n
t
an
aly
s
is
(
I
C
A
)
s
ep
er
ates
in
d
ep
en
d
e
n
t
s
p
a
ce
f
r
o
m
m
i
x
ed
s
et
of
s
ig
n
als
is
u
s
ed
.
In
th
is
p
ap
e
r
we
p
r
o
p
o
s
ed
I
C
A
m
eth
o
d
f
o
r
f
ea
t
u
r
e
ex
tr
a
ctio
n
[
3
0
]
-
[
3
4
]
.
Dim
en
s
io
n
alit
y
r
ed
u
ctio
n
b
en
ef
its
ar
e
:
b
y
r
e
d
u
cin
g
th
e
d
im
en
s
io
n
s
of
th
e
f
e
atu
r
es,
th
e
s
p
ac
e
r
eq
u
ir
ed
to
s
to
r
e
th
e
d
ataset
also
g
ets
r
ed
u
ce
d
,
less
co
m
p
u
tati
o
n
tr
ai
n
in
g
tim
e
is
r
eq
u
ir
e
d
f
o
r
r
e
d
u
ce
d
d
im
e
n
s
io
n
s
of
f
ea
tu
r
es,
r
ed
u
ce
d
d
im
en
s
io
n
s
of
f
ea
t
u
r
es
of
th
e
d
ataset
h
elp
in
v
is
u
alizin
g
th
e
d
ata
q
u
ick
ly
an
d
it
r
em
o
v
es
th
e
r
ed
u
n
d
a
n
t
f
ea
tu
r
es
if
p
r
esen
t
by
tak
in
g
c
ar
e
of
m
u
lti
-
co
llin
ea
r
ity
[
3
5
]
-
[
3
7
]
.
6.
I
NDEP
E
ND
E
N
T
CO
M
P
O
N
E
NT
A
NAL
YSI
S
(
I
CA)
I
C
A
is
a
m
ac
h
in
e
lear
n
in
g
tec
h
n
iq
u
e
u
s
ed
to
s
ep
ar
ate
in
d
ep
en
d
en
t
s
o
u
r
ce
s
f
o
r
m
a
m
ix
ed
s
ig
n
al.
I
C
A
f
o
cu
s
es
on
in
d
e
p
en
d
e
n
t
i.e
.
in
d
ep
en
d
e
n
t
co
m
p
o
n
en
ts
.
I
C
A
is
b
ased
on
in
f
o
r
m
atio
n
-
th
eo
r
y
an
d
is
also
o
n
e
of
th
e
m
o
s
t
wid
ely
u
s
ed
d
im
en
s
io
n
ality
r
ed
u
ctio
n
tech
n
iq
u
es.
T
h
e
m
ajo
r
d
if
f
er
en
ce
b
etwe
e
n
PC
A
an
d
I
C
A
is
th
a
t
PC
A
lo
o
k
s
f
o
r
u
n
co
r
r
elate
d
f
ac
to
r
s
wh
ile
I
C
A
lo
o
k
s
f
o
r
I
n
d
e
p
en
d
e
n
t
f
ac
to
r
s
[
3
8
]
-
[
4
0
]
.
If
two
v
a
r
iab
les
ar
e
u
n
co
r
r
elate
d
,
it
m
ea
n
s
th
er
e
is
no
lin
ea
r
r
elatio
n
b
etwe
en
th
em
.
If
th
ey
ar
e
i
n
d
ep
e
n
d
en
t
,
it
m
ea
n
s
th
ey
ar
e
not
d
ep
e
n
d
en
t
on
o
th
er
v
a
r
iab
l
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
mp
leme
n
ta
tio
n
o
f fe
a
tu
r
e
ex
tr
a
ctio
n
a
n
d
d
ee
p
lea
r
n
in
g
-
b
a
s
e
d
en
s
em
b
le
cla
s
s
ifier
fo
r
…
(
N
.
Du
r
g
a
I
n
d
ir
a
)
1197
7.
M
E
T
A
-
H
E
U
RIS
T
I
C
B
AS
E
D
F
I
RE
F
L
Y
AL
G
O
R
I
T
H
M
T
h
e
f
ir
ef
ly
alg
o
r
ith
m
(
FF
A)
is
a
m
etah
eu
r
is
tic
alg
o
r
ith
m
,
th
e
f
lash
in
g
b
eh
av
io
u
r
o
f
f
i
r
ef
lies
ar
e
im
p
lem
en
ted
.
T
h
e
f
ir
ef
l
y
'
s
f
la
s
h
is
ac
t
as
a
s
ig
n
al
s
y
s
tem
to
attr
ac
t
o
th
er
f
ir
e
f
lies
.
T
h
er
e
a
r
e
th
r
ee
r
u
les
u
s
ed
.
On
th
e
f
ir
s
t
r
u
le,
ea
ch
f
ir
ef
ly
a
ttra
cts
all
th
e
o
th
er
f
ir
e
f
lies
with
wea
k
er
f
lash
es.
All
f
ir
e
f
lies
ar
e
u
n
is
ex
s
o
th
at
o
n
e
f
ir
ef
l
y
will b
e
attr
ac
ted
to
o
th
er
f
ir
ef
lies
r
eg
a
r
d
less
o
f
th
e
ir
s
ex
.
Seco
n
d
ly
,
attr
ac
tiv
en
ess
is
p
r
o
p
o
r
tio
n
al
t
o
th
eir
b
r
i
g
h
tn
ess
wh
ich
is
r
ev
er
s
e
p
r
o
p
o
r
tio
n
al
to
t
h
eir
d
is
tan
ce
s
.
Fo
r
an
y
two
f
lash
in
g
f
ir
ef
lies
,
th
e
less
b
r
ig
h
t
o
n
e
will
m
o
v
e
to
war
d
s
th
e
b
r
ig
h
ter
o
n
e.
T
h
e
attr
ac
tiv
en
ess
is
p
r
o
p
o
r
tio
n
al
to
th
e
b
r
ig
h
tn
ess
an
d
th
ey
b
o
th
d
ec
r
ea
s
e
as th
eir
d
is
tan
ce
in
cr
ea
s
es.
I
f
th
er
e
is
n
o
b
r
ig
h
ter
o
n
e
th
an
a
p
ar
ticu
la
r
f
ir
ef
ly
,
it
will m
o
v
e
r
an
d
o
m
ly
.
Fi
n
ally
,
n
o
f
ir
ef
l
y
ca
n
attr
ac
t
th
e
b
r
ig
h
test
f
i
r
ef
ly
an
d
it
m
o
v
es
r
a
n
d
o
m
l
y
.
Fire
f
ly
alg
o
r
ith
m
u
s
ed
to
s
o
lv
e
d
if
f
er
en
t
o
p
tim
izatio
n
p
r
o
b
le
m
s
.
I
t is a
m
eta
-
h
eu
r
is
tic
alg
o
r
ith
m
in
s
p
ir
ed
b
y
f
lash
in
g
b
eh
a
v
io
u
r
o
f
f
iv
e
f
lies
.
Ass
u
m
p
tio
n
s
:
f
ir
ef
lies
ar
e
att
r
ac
te
d
to
each
o
t
h
er
.
L
ess
b
r
ig
h
t
f
ir
ef
ly
is
attr
ac
ted
to
th
e
b
r
ig
h
ter
f
ir
ef
ly
.
Attr
ac
tiv
en
ess
d
ec
r
ea
s
e
as
d
is
tan
ce
b
etwe
en
two
f
ir
ef
lies
in
cr
ea
s
es
[
4
1
]
.
If
b
r
i
g
h
tn
ess
f
o
r
b
o
th
is
s
am
e,
f
ir
ef
lies
move
r
a
n
d
o
m
ly
.
New
s
o
lu
tio
n
s
ar
e
g
e
n
er
ate
d
by
r
an
d
o
m
walk
an
d
attr
ac
t
io
n
of
f
ir
ef
lies
an
d
r
an
d
o
m
walk
is
eq
u
al
to
t
h
e
s
tep
s
ize.
a)
Fire
f
ly
o
p
tim
izatio
n
a
lg
o
r
ith
m
1)
I
n
itialize
p
ar
am
eter
s
lik
e
p
o
p
u
latio
n
s
ize,
m
ax
im
u
m
iter
atio
n
s
,
d
im
en
s
io
n
s
,
u
p
p
er
b
o
u
n
d
an
d
lo
wer
b
o
u
n
d
.
2)
Gen
er
ate
p
o
p
u
latio
n
of
n
f
ir
ef
l
ies.
3)
C
alcu
late
f
itn
ess
v
alu
e
f
o
r
ea
c
h
f
ir
ef
ly
.
4)
C
h
ec
k
if
(
t:=
1
to
Ma
x
t)
5)
Up
d
ate
p
o
s
itio
n
an
d
lig
h
t
in
te
n
s
ity
of
each
f
ir
ef
ly
.
6)
R
ep
o
r
t
th
e
b
est
s
o
lu
tio
n
.
b)
Ad
v
an
tag
es
o
f
f
ir
ef
ly
al
g
o
r
ith
m
1)
Fire
f
ly
can
co
m
p
ac
t
th
e
d
is
tin
ct
m
in
im
a
with
h
ig
h
ly
n
o
n
-
lin
ea
r
,
m
u
lti
-
m
o
d
al
o
p
tim
izatio
n
p
r
o
b
lem
s
v
er
y
ea
s
ily
an
d
ef
f
icien
tly
.
2)
T
h
e
s
p
ee
d
of
co
n
v
er
g
e
n
ce
of
f
ir
ef
ly
al
g
o
r
ith
m
is
v
er
y
h
ig
h
in
p
r
o
b
a
b
ilit
y
of
f
in
d
in
g
th
e
g
lo
b
al
m
in
im
a.
3)
It
h
as
th
e
f
lex
ib
ilit
y
of
in
teg
r
atio
n
with
o
th
er
o
p
tim
izatio
n
tech
n
iq
u
es
to
f
o
r
m
h
y
b
r
id
to
o
ls
.
4)
T
h
e
b
est,
a
v
er
ag
e
an
d
wo
r
s
t
ca
s
e
tim
e
co
m
p
lex
ities
d
o
esn
’
t
r
eq
u
i
r
e
a
g
o
o
d
in
itial
s
o
lu
ti
o
n
to
s
tar
t
d
u
r
in
g
its
iter
atio
n
p
r
o
ce
s
s
.
c)
Ap
p
licatio
n
a
r
ea
s
1)
Fo
r
s
o
lv
in
g
tr
a
v
ellin
g
s
alesm
an
p
r
o
b
lem
to
f
in
d
out
th
e
s
h
o
r
t
est
p
o
s
s
ib
le
r
o
u
tes
2)
Dig
ital
im
ag
e
co
m
p
r
ess
io
n
an
d
im
ag
e
p
r
o
ce
s
s
in
g
lead
s
to
th
e
en
h
an
ce
m
e
n
ts
of
id
en
tify
i
n
g
s
p
ec
if
ic
o
b
jects
3)
Featu
r
e
s
elec
tio
n
an
d
f
a
u
lt
d
et
ec
tio
n
u
s
ed
to
id
e
n
tify
th
e
p
att
er
n
s
in
an
in
p
u
t
s
ig
n
al,
im
a
g
e
or
v
id
e
o
4)
An
ten
n
a
d
esig
n
8.
DE
E
P
B
E
L
I
E
F
NE
T
WO
RK
(
DB
N)
On
e
p
r
o
b
lem
with
t
h
e
ar
tific
ial
n
eu
r
al
n
etwo
r
k
s
is
th
e
b
a
ck
p
r
o
p
ag
atio
n
can
o
f
te
n
lea
d
to
lo
ca
l
m
in
im
a.
T
h
is
o
cc
u
r
s
wh
en
‘
er
r
o
r
s
u
r
f
ac
e
’
co
n
tain
s
m
u
ltip
le
g
r
o
o
v
es.
Du
r
in
g
b
ac
k
p
r
o
p
a
g
a
tio
n
m
ay
f
all
in
to
a
g
r
o
o
v
e
th
at
is
th
e
lo
west
lo
ca
l
ly
but
not
o
v
er
all.
Deep
b
elief
n
etwo
r
k
s
ar
e
a
g
en
e
r
ativ
e
g
r
a
p
h
ical
m
o
d
el
an
d
it
is
r
ep
r
esen
ted
to
th
e
s
o
lu
tio
n
of
v
an
is
h
in
g
g
r
ad
ien
t
p
r
o
b
le
m
will
s
o
lv
e
th
is
p
r
o
b
lem
by
u
s
in
g
an
ex
tr
a
s
tep
ca
lled
p
r
e
-
tr
ain
in
g
.
Pre
-
tr
ain
in
g
is
p
er
f
o
r
m
ed
b
e
f
o
r
e
b
ac
k
p
r
o
p
ag
atio
n
can
lea
d
an
er
r
o
r
th
at’
s
in
th
e
v
icin
ity
of
th
e
f
in
al
s
o
lu
tio
n
[
4
2
]
,
[
4
3
]
.
We
can
u
s
e
b
ac
k
p
r
o
p
ag
ati
o
n
to
s
lo
wly
r
ed
u
ce
th
e
er
r
o
r
r
ate.
Deep
b
elief
n
etwo
r
k
s
can
be
d
iv
id
e
d
in
to
two
m
ajo
r
p
ar
ts
.
T
h
e
f
ir
s
t
p
ar
t
co
n
tain
s
m
u
ltip
le
lay
er
s
of
r
estricte
d
B
o
ltzm
an
n
m
ac
h
in
es
in
o
r
d
e
r
to
p
r
e
tr
a
in
th
e
n
etwo
r
k
[
4
4
]
.
T
h
e
s
ec
o
n
d
p
ar
t
is
t
h
e
f
ee
d
f
o
r
war
d
b
ac
k
p
r
o
p
ag
atio
n
n
etwo
r
k
,
wh
ic
h
will
f
u
r
th
e
r
r
e
f
in
e
th
e
r
esu
lts
f
r
o
m
r
estricte
d
B
o
ltzm
an
n
m
ac
h
in
es
(
RBM
)
s
tack
[
4
5
]
,
[
4
6
]
.
T
h
e
n
e
u
r
al
n
etwo
r
k
s
ar
e
of
d
if
f
er
en
t
ty
p
es
an
d
b
ased
on
t
h
e
ap
p
licatio
n
t
y
p
e,
th
e
n
eu
r
al
n
e
two
r
k
will
b
e
ch
o
s
en
.
By
ad
d
in
g
ex
tr
a
l
ay
er
s
will
g
et
ac
cu
r
ac
y
of
th
e
p
er
f
o
r
m
a
n
ce
of
th
e
m
o
d
el.
If
th
e
lay
er
s
ar
e
to
o
less
,
th
en
th
e
tr
ain
in
g
will
g
en
er
ate
th
e
u
n
d
er
f
it
m
o
d
el.
If
th
e
lay
er
s
ar
e
more
in
n
u
m
b
er
,
t
h
e
g
en
er
ated
m
o
d
el
will
go
o
v
er
f
it.
Fro
m
th
e
Fig
u
r
e
1
th
e
in
p
u
t
lay
er
d
ea
ls
with
th
e
in
p
u
t
an
d
co
n
v
er
ts
th
e
in
p
u
t
im
ag
e
in
ter
m
s
of
R
GB
,
th
e
s
et
of
p
ix
el
in
ten
s
ities
v
alu
es
ar
e
p
lace
d
in
an
ar
r
ay
th
u
s
ca
lled
co
n
v
o
l
u
tio
n
.
E
ac
h
co
n
v
o
lu
tio
n
h
as
a
s
et
of
in
p
u
t
v
alu
es
to
be
tak
e
n
a
n
d
id
en
tify
th
e
m
ax
im
u
m
v
alu
e
f
r
o
m
all
th
e
v
alu
es
ca
lled
MA
X
POOL
I
NG
lay
er
.
T
h
e
n
ew
v
alu
es
will
be
g
en
er
ate
d
an
d
t
h
en
ap
p
ly
a
f
ilter
wh
ich
is
ca
lled
a
k
er
n
el
an
d
d
ef
au
lt
weig
h
ts
ar
e
ap
p
lied
on
th
e
n
o
d
es
(
n
eu
r
o
n
s
)
to
g
et
th
e
h
id
d
en
lay
er
an
d
th
is
p
r
o
c
ess
wi
ll
co
n
tin
u
e
to
th
e
h
id
d
en
lay
er
s
in
th
e
n
etwo
r
k
.
T
h
e
o
u
tp
u
t
lay
er
is
u
s
ed
to
d
etec
t
or
id
en
tify
th
e
in
p
u
t
f
r
o
m
th
e
s
et
of
g
en
er
ated
p
atter
n
s
u
n
d
er
tr
ain
i
n
g
an
d
th
e
m
o
d
el
will
ea
s
ily
r
ec
o
g
n
is
e
th
e
p
atter
n
s
ef
f
ec
tiv
e
ly
.
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.
24
,
No
.
2
,
No
v
em
b
er
2
0
2
1
:
1
1
9
5
-
1
2
0
1
1198
Fig
u
r
e
1.
Deep
b
elief
n
etwo
r
k
ar
ch
itectu
r
e
9.
RE
SU
L
T
S
F
i
g
u
r
e
2
a
n
d
Fi
g
u
r
e
3
s
h
o
ws
s
i
g
n
a
l
i
n
t
e
r
f
e
r
e
n
c
e
m
i
t
i
g
at
i
o
n
a
f
t
e
r
a
n
d
b
e
f
o
r
e
.
F
r
o
m
F
i
g
u
r
e
2
we
can
a
n
a
l
y
s
e
t
h
a
t
b
e
f
o
r
e
t
r
a
n
s
m
i
s
s
i
o
n
t
h
e
s
i
g
n
a
l
a
d
d
e
d
w
i
t
h
i
n
t
e
r
f
e
r
e
n
c
e
(
n
o
i
s
e
)
.
F
r
o
m
F
i
g
u
r
e
3
it
is
c
l
e
a
r
l
y
o
b
s
e
r
v
e
d
t
h
a
t
i
n
t
e
r
f
e
r
e
n
c
e
is
e
l
i
m
i
n
a
t
e
d
f
r
o
m
t
h
e
s
i
g
n
a
l
.
F
i
g
u
r
e
4
s
h
o
w
s
r
a
d
a
r
s
i
g
n
a
l
b
e
f
o
r
e
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
a
n
d
F
i
g
u
r
e
5
r
e
p
r
e
s
e
n
t
s
r
a
d
a
r
s
i
g
n
al
a
f
t
e
r
f
e
at
u
r
e
e
x
t
r
a
c
t
i
o
n
.
In
t
h
is
p
a
p
e
r
we
p
r
o
p
o
s
e
d
I
C
A
f
o
r
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
.
Fig
u
r
e
2.
Sig
n
al
b
ef
o
r
e
in
ter
f
e
r
en
ce
m
itig
atio
n
Fig
u
r
e
3.
Sig
n
al
a
f
ter
in
ter
f
e
r
e
n
ce
m
itig
atio
n
Fig
u
r
e
4.
R
ad
ar
s
ig
n
al
b
ef
o
r
e
f
ea
tu
r
e
ex
tr
ac
tio
n
Fig
u
r
e
5.
R
ad
ar
s
ig
n
al
af
ter
f
e
atu
r
e
ex
tr
ac
tio
n
To
i
m
p
r
o
v
e
t
h
e
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
p
r
o
c
e
s
s
of
d
e
e
p
b
e
l
i
e
f
n
e
t
w
o
r
k
m
o
d
e
l
f
o
r
t
h
e
t
r
a
n
s
m
i
t
t
e
r
d
a
t
a
,
c
o
m
p
a
r
i
s
o
n
of
o
u
t
p
u
t
f
e
a
t
u
r
es
of
t
h
e
p
r
i
m
a
r
y
d
a
t
a
,
t
h
e
f
i
r
s
t
h
id
d
e
n
l
a
y
e
r
a
n
d
t
h
e
s
e
c
o
n
d
h
i
d
d
e
n
l
a
y
e
r
w
i
ll
t
a
k
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
mp
leme
n
ta
tio
n
o
f fe
a
tu
r
e
ex
tr
a
ctio
n
a
n
d
d
ee
p
lea
r
n
in
g
-
b
a
s
e
d
en
s
em
b
le
cla
s
s
ifier
fo
r
…
(
N
.
Du
r
g
a
I
n
d
ir
a
)
1199
p
l
a
c
e
.
T
h
e
f
e
a
t
u
r
e
s
f
r
o
m
d
i
f
f
e
r
e
n
t
l
a
y
e
r
s
can
be
c
o
m
p
a
r
e
d
t
h
r
o
u
g
h
each
a
n
d
e
v
e
r
y
node
of
t
h
e
d
a
t
a
w
h
i
c
h
a
r
e
p
r
o
c
e
s
s
e
d
by
f
e
a
t
u
r
e
v
i
s
u
al
i
z
ati
o
n
t
h
r
o
u
g
h
d
r
o
p
p
i
n
g
h
i
g
h
-
d
i
m
e
n
s
i
o
n
a
l
d
a
t
a
is
s
ca
l
e
d
i
n
t
o
3
-
d
i
m
e
n
s
i
o
n
a
l
i
m
a
g
e
s
by
u
s
i
n
g
I
C
A
a
l
g
o
r
i
t
h
m
.
Fi
g
u
r
e
6
d
e
p
i
c
t
s
t
h
e
p
l
o
t
a
x
is
f
o
r
t
im
e
s
a
m
p
l
e
,
f
r
e
q
u
e
n
c
y
s
a
m
p
l
e
a
n
d
t
h
e
a
m
p
l
i
t
u
d
e
of
d
i
m
e
n
s
i
o
n
a
li
t
y
r
e
d
u
c
t
i
o
n
of
t
h
e
i
n
i
t
i
a
l
t
i
m
e
-
d
o
m
a
i
n
s
a
m
p
l
e
d
d
a
t
a
of
3D
-
i
m
a
g
e
r
e
c
o
n
s
t
r
u
c
t
ed
s
i
g
n
a
l
u
s
i
n
g
d
e
e
p
b
e
l
i
e
f
n
e
tw
o
r
k
(
DB
N
)
.
F
i
g
u
r
e
7
i
n
d
i
c
a
t
es
t
h
a
t
t
h
e
m
o
d
e
l
ac
q
u
i
r
e
d
n
e
a
r
l
y
9
6
.
4
%
a
c
c
u
r
ac
y
w
h
e
n
t
h
e
s
i
g
n
a
l
-
to
-
n
o
i
s
e
r
a
t
i
o
(
S
NR
)
was
3dB
a
n
d
d
i
s
p
l
a
y
s
t
h
e
d
e
e
p
l
e
a
r
n
i
n
g
m
e
t
h
o
d
s
w
h
i
c
h
a
r
e
u
s
e
d
f
o
r
t
h
e
p
r
e
d
i
c
t
i
o
n
of
r
a
d
a
r
s
i
g
n
a
ls
e
f
f
i
c
ie
n
t
l
y
.
Fig
u
r
e
6.
3D
im
ag
e
-
r
ec
o
n
s
tr
u
cted
s
ig
n
al
u
s
in
g
d
ee
p
b
elief
n
etwo
r
k
(
DB
N)
Fig
u
r
e
7.
Sig
n
al
r
ec
o
g
n
itio
n
r
a
te
an
aly
s
is
10.
CO
NCLU
SI
O
N
T
h
e
d
esig
n
a
n
d
im
p
lem
en
ta
tio
n
can
be
d
o
n
e
f
o
r
f
ea
tu
r
e
ex
tr
ac
tio
n
a
n
d
d
ee
p
lear
n
in
g
-
b
ased
en
s
em
b
le
class
if
ier
f
o
r
in
ter
f
er
en
ce
m
itig
atio
n
in
r
ad
a
r
s
ig
n
als.
I
n
itially
,
th
e
in
p
u
t
s
ig
n
a
l
is
co
n
v
er
ted
in
to
b
in
ar
y
f
o
r
m
th
e
n
e
x
tr
ac
ts
th
e
f
ea
tu
r
e
f
o
r
en
h
a
n
cin
g
th
e
r
ec
o
g
n
itio
n
p
er
f
o
r
m
an
ce
of
th
e
co
m
p
o
u
n
d
s
ig
n
al.
In
th
is
wo
r
k
p
r
e
-
p
r
o
ce
s
s
,
ex
tr
a
ct,
an
d
class
if
y
th
e
f
ea
tu
r
e
m
atr
ix
by
d
im
en
s
io
n
ality
r
ed
u
ctio
n
alg
o
r
ith
m
(
in
d
ep
en
d
en
t
co
m
p
o
n
en
t
an
al
y
s
is
an
d
f
o
u
r
ier
tr
an
s
f
o
r
m
)
im
p
lem
en
ted
.
T
h
is
will
en
h
an
ce
th
e
p
er
f
o
r
m
an
ce
f
o
r
lar
g
e
d
im
en
s
io
n
f
ea
tu
r
e
v
ec
to
r
.
T
h
e
p
r
e
-
p
r
o
ce
s
s
in
g
s
tag
e
in
clu
d
es
tim
e
-
f
r
eq
u
en
c
y
r
ep
r
esen
tatio
n
,
tr
ain
in
g
th
e
m
o
d
el
with
m
u
lti
-
lab
el
class
if
icatio
n
an
d
th
e
d
ec
is
io
n
tr
ee
with
m
u
lti
-
d
ec
is
io
n
th
r
esh
o
l
d
s
o
p
tim
izatio
n
f
o
r
o
u
tp
u
t
lab
el
d
ec
is
io
n
.
In
th
is
wo
r
k
m
eta
-
h
e
u
r
is
tic
b
ased
f
ir
e
f
ly
alg
o
r
ith
m
is
u
s
ed
to
s
elec
t
o
p
tim
al
p
ar
am
eter
s
an
d
m
itig
ate
th
e
i
n
ter
f
er
e
n
ce
in
b
o
th
tim
e
an
d
f
r
eq
u
en
cy
d
o
m
ain
an
d
e
f
f
ec
tiv
e
d
ee
p
lear
n
in
g
ap
p
r
o
ac
h
(
d
ee
p
b
elief
n
etwo
r
k
)
with
v
ar
io
u
s
m
u
lti
-
lab
el
s
tr
ateg
ies
to
war
d
en
h
an
ci
n
g
th
e
r
ec
o
g
n
itio
n
p
er
f
o
r
m
an
ce
.
T
h
e
co
m
b
in
atio
n
of
o
p
tim
izatio
n
an
d
lea
r
n
in
g
tech
n
iq
u
e
will
be
u
s
ed
f
o
r
s
ig
n
al
an
aly
s
is
an
d
m
u
lti
-
d
ec
is
io
n
th
r
esh
o
ld
s
o
p
tim
izatio
n
f
o
r
o
u
tp
u
t
lab
el
d
ec
is
io
n
.
Fin
all
y
,
th
e
p
er
f
o
r
m
an
ce
u
s
in
g
MA
T
L
AB
s
im
u
latio
n
s
o
f
twar
e
an
d
co
m
p
ar
e
th
e
r
esu
lts
with
th
e
tr
ad
itio
n
al
m
eth
o
d
in
ter
m
s
of
ac
cu
r
ac
y
an
d
s
ig
n
al
to
n
o
is
e
r
atio
.
T
h
e
m
o
d
el
ac
q
u
ir
e
d
b
etter
ac
cu
r
ac
y
wh
en
th
e
s
ig
n
al
-
to
-
n
o
is
e
r
atio
is
ab
o
u
t
3dB
an
d
th
e
d
ee
p
lear
n
in
g
m
eth
o
d
s
can
be
u
s
ed
to
p
r
ed
ic
t
th
e
r
ad
ar
s
ig
n
als.
RE
F
E
R
E
NC
E
S
[1
]
M.
Ba
rjen
b
r
u
c
h
,
D.
Ke
ll
n
e
r,
K.
D
ietm
a
y
e
r,
J.
Kla
p
p
ste
in
,
a
n
d
J.
Di
c
k
m
a
n
n
,
“A
m
e
th
o
d
f
o
r
in
terfe
re
n
c
e
c
a
n
c
e
ll
a
ti
o
n
in
a
u
to
m
o
ti
v
e
ra
d
a
r
,
”
IEE
E
M
T
T
-
S
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
on
M
icr
o
wa
v
e
s
fo
r
In
telli
g
e
n
t
M
o
b
il
it
y
(ICM
I
M
)
.
IEE
E,
2
0
1
5
,
p
p
.
1
-
4,
d
o
i
:
1
0
.
1
1
0
9
/ICM
IM
.
2
0
1
5
.
7
1
1
7
9
2
5
.
[2
]
Z.
M
a
,
Z
Hu
a
n
g
,
A.
Li
n
,
a
n
d
G
.
Hu
a
n
g
,
“
L
P
I
Ra
d
a
r
Wav
e
fo
rm
Re
c
o
g
n
i
ti
o
n
Ba
se
d
on
F
e
a
tu
re
s
fro
m
M
u
lt
i
p
le
Im
a
g
e
s
,
”
S
e
n
so
rs
,
v
o
l
.
20
,
n
o
.
2
,
pp.
5
2
6
,
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/s2
0
0
2
0
5
2
6
.
[3
]
J.
Ro
c
k
,
M.
T
o
th
,
P.
M
e
issn
e
r
,
a
n
d
F.
P
e
rn
k
o
p
f
,
“
Cn
n
s
f
o
r
i
n
ter
fe
re
n
c
e
m
it
ig
a
to
n
a
n
d
d
e
n
o
isin
g
in
a
u
t
o
m
o
ti
v
e
ra
d
a
r
u
sin
g
re
a
l
wo
rld
d
a
ta
,
”
2
0
1
9
Ne
u
rIPS
W
o
rk
sh
o
p
on
M
a
c
h
in
e
L
e
a
rn
in
g
fo
r
Au
t
o
n
o
mo
u
s
Dr
ivin
g
,
Va
n
c
o
u
v
e
r,
d
o
i:
1
0
.
1
1
0
9
/RADA
R4
2
5
2
2
.
2
0
2
0
.
9
1
1
4
6
2
7
.
[4
]
C.
Wan
g
,
J.
Wan
g
,
a
n
d
X.
Z
h
a
n
g
,
"
A
u
to
m
a
ti
c
ra
d
a
r
wa
v
e
f
o
rm
re
c
o
g
n
i
ti
o
n
b
a
se
d
on
ti
m
e
-
fre
q
u
e
n
c
y
a
n
a
ly
sis
a
n
d
c
o
n
v
o
lu
ti
o
n
a
l
n
e
u
ra
l
n
e
two
rk
,
"
IEE
E
I
n
ter
n
a
t
io
n
a
l
Co
n
fer
e
n
c
e
on
Aco
u
stics
,
S
p
e
e
c
h
a
n
d
S
i
g
n
a
l
Pro
c
e
ss
in
g
(ICAS
S
P)
,
Ne
w
Orle
a
n
s,
LA,
2
0
1
7
,
p
p
.
2
4
3
7
2
4
4
1
,
d
o
i:
1
0
.
1
1
0
9
/IC
ASS
P
.
2
0
1
7
.
7
9
5
2
5
9
4
.
[5
]
D.
Op
risa
n
a
n
d
H.
R
o
h
l
in
g
,
“
A
n
a
ly
sis
of
m
u
t
u
a
l
i
n
terfe
re
n
c
e
b
e
twe
e
n
a
u
to
m
o
ti
v
e
ra
d
a
r
sy
ste
m
s,”
in
Pro
c
.
I
n
t.
Ra
d
a
r
S
y
mp
.
(IR
S
)
,
Be
rli
n
,
G
e
rm
a
n
y
,
pp.
83
-
90
,
2
0
0
5
.
[
6
]
X.
S
o
n
g
,
P.
W
i
l
l
e
t
t
,
a
n
d
S.
Z
h
o
u
,
“
J
a
m
m
e
r
d
e
t
e
c
t
i
o
n
a
n
d
e
s
t
i
m
a
t
io
n
w
i
t
h
M
I
M
O
r
a
d
a
r
,
”
in
P
r
o
c
.
C
o
n
f
.
R
e
c
.
4
6
t
h
A
s
i
l
o
m
a
r
C
o
n
f
.
S
i
g
n
a
l
s
,
S
y
s
t
.
C
o
m
p
u
t
.
(
A
S
I
L
O
M
A
R
)
,
p
p
.
1
3
1
2
-
1
3
1
6
,
N
o
v
.
2
0
1
2
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
S
S
C
.
2
0
1
2
.
6
4
8
9
2
3
7
.
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.
24
,
No
.
2
,
No
v
em
b
er
2
0
2
1
:
1
1
9
5
-
1
2
0
1
1200
[7
]
J.
Be
c
h
ter,
K.
Ei
d
,
F.
R
o
o
s
,
a
n
d
C.
Wald
sc
h
m
id
t
,
“
Dig
it
a
l
b
e
a
m
fo
rm
in
g
to
m
it
ig
a
te
a
u
t
o
m
o
ti
v
e
ra
d
a
r
in
terfe
re
n
c
e
,
”
in
I
EE
E
M
T
T
-
S
I
n
ter
n
a
t
io
n
a
l
Co
n
fer
e
n
c
e
on
M
icr
o
wa
v
e
s
fo
r
In
te
ll
ig
e
n
t
M
o
b
il
it
y
(ICM
I
M
)
,
M
a
y
.
2
0
1
6
,
p
p
.
1
-
4,
d
o
i:
1
0
.
1
1
0
9
/ICM
I
M
.
2
0
1
6
.
7
5
3
3
9
1
4
.
[8
]
G.
M.
Bro
o
k
e
r,
“
M
u
t
u
a
l
i
n
terfe
r
e
n
c
e
of
m
il
li
m
e
ter
-
wa
v
e
ra
d
a
r
sy
ste
m
s,”
IEE
E
T
ra
n
sa
c
ti
o
n
s
on
E
lec
tro
ma
g
n
e
ti
c
Co
mp
a
t
ib
il
it
y
,
v
o
l.
4
9
,
no.
1,
p
p
.
170
-
1
8
1
,
2
0
0
,
d
o
i:
1
0
.
1
1
0
9
/
TE
M
C.
2
0
0
6
.
8
9
0
2
2
3
.
[9
]
A.
S.
A.
M
e
n
d
o
z
a
a
n
d
B.
F
l
o
r
e
s,
“
Clas
sifica
ti
o
n
of
ra
d
a
r
jam
m
e
r
FM
sig
n
a
ls
u
sin
g
a
n
e
u
ra
l
n
e
two
rk
,
”
in
Pro
c
e
e
d
in
g
s
of
t
h
e
S
PIE
R
a
d
a
r
S
e
n
so
r
T
e
c
h
n
o
lo
g
y
XXI
,
v
o
l.
1
0
1
8
8
,
M
a
y
.
2
0
1
7
,
d
o
i
:
1
0
.
1
1
1
7
/
1
2
.
2
2
6
2
0
5
9
.
[1
0
]
E.
M
a
se
n
,
B.
Y
o
n
e
i
,
a
n
d
B.
Ya
z
ici,
“
De
e
p
lea
rn
in
g
f
o
r
ra
d
a
r,
”
in
Pro
c
e
e
d
in
g
s
of
th
e
2
0
1
7
IEE
E
R
a
d
a
r
C
o
n
fer
e
n
c
e
(Ra
d
a
rCo
n
f)
,
S
e
a
tt
le,
WA,
USA,
M
a
y
.
2
0
1
7
,
d
o
i:
1
0
.
1
1
0
9
/RADA
R.
2
0
1
7
.
7
9
4
4
4
8
1
.
[1
1
]
J.
Be
c
h
ter,
K.
Ei
d
,
F.
R
o
o
s,
a
n
d
C.
Wald
sc
h
m
id
t
,
“
Dig
it
a
l
b
e
a
m
fo
rm
in
g
to
m
it
ig
a
te
a
u
t
o
m
o
ti
v
e
ra
d
a
r
in
terfe
re
n
c
e
,
”
IEE
E
M
T
T
-
S
I
n
ter
n
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
on
M
icr
o
wa
v
e
s
fo
r
I
n
tell
ig
e
n
t
M
o
b
il
it
y
(IC
M
IM
)
,
I
EE
E,
2
0
1
6
,
p
p
.
1
-
4,
d
o
i:
1
0
.
1
1
0
9
/ICM
I
M
.
2
0
1
6
.
7
5
3
3
9
1
4
.
[1
2
]
J
.
Dic
k
m
a
n
n
,
J
.
Kla
p
p
ste
in
,
M
.
Ha
h
n
,
N
.
Ap
p
e
n
r
o
d
t
,
H
.
-
L
.
Bl
o
e
c
h
e
r
,
K
.
Werb
e
r,
a
n
d
A
.
S
a
il
e
r,
“
Au
to
m
o
ti
v
e
ra
d
a
r
th
e
k
e
y
tec
h
n
o
l
o
g
y
f
o
r
a
u
to
n
o
m
o
u
s
d
riv
in
g
:
F
ro
m
d
e
tec
ti
o
n
a
n
d
ra
n
g
in
g
to
e
n
v
ir
o
n
m
e
n
tal
u
n
d
e
rst
a
n
d
in
g
,
”
I
EE
E
Ra
d
a
r
Co
n
fer
e
n
c
e
(Ra
d
a
r
Co
n
f
.
)
,
M
a
y
.
2
0
1
6
,
p
p
.
1
-
6,
d
o
i:
1
0
.
1
1
0
9
/RADA
R.
2
0
1
6
.
7
4
8
5
2
1
4
.
[1
3
]
J.
J.
An
a
y
a
,
A.
P
o
n
z
,
F
.
G
a
rc
ía
,
a
n
d
E
.
Tala
v
e
ra
,
“
M
o
to
rc
y
c
le
d
e
tec
ti
o
n
f
o
r
ADAS
t
h
ro
u
g
h
c
a
m
e
ra
a
n
d
V2
V
Co
m
m
u
n
ica
ti
o
n
,
a
c
o
m
p
a
ra
ti
v
e
a
n
a
ly
sis
of
tw
o
m
o
d
e
rn
tec
h
n
o
l
o
g
ies
,
”
Exp
e
rt
S
y
ste
ms
wit
h
Ap
p
li
c
a
ti
o
n
s
,
v
o
l
.
77.
pp.
1
4
8
-
159
,
Ja
n
u
a
ry
2
0
1
7
,
d
o
i
:
1
0
.
1
0
1
6
/j
.
e
sw
a
.
2
0
1
7
.
0
1
.
0
3
2
.
[1
4
]
L.
Du
,
P
.
Wan
g
,
L.
Zh
a
n
g
,
H.
H
e
,
a
n
d
H.
L
iu
,
“
Ro
b
u
st
sta
ti
st
ica
l
re
c
o
g
n
it
i
o
n
a
n
d
re
c
o
n
stru
c
ti
o
n
sc
h
e
m
e
b
a
se
d
on
h
iera
rc
h
ica
l
Ba
y
e
sia
n
lea
rn
in
g
of
HRR
ra
d
a
r
targ
e
t
sig
n
a
l
,
”
Exp
e
rt
S
y
ste
ms
wit
h
Ap
p
li
c
a
t
io
n
s
,
v
o
l.
42
,
n
o
.
14
,
pp.
5
8
6
0
-
5
8
7
3
,
Au
g
u
st
,
2
0
1
5
,
doi
:
1
0
.
1
0
1
6
/j
.
e
sw
a
.
2
0
1
5
.
0
3
.
0
2
9
.
[1
5
]
W.
D.
v
a
n
Eed
e
n
a
,
J.
P
.
d
e
Vil
li
e
rs,
R.
J.
Be
rn
d
t
,
W.
A.
J.
Ne
l
,
a
n
d
E.
Blas
c
h
,
“
M
icr
o
-
Do
p
p
ler
ra
d
a
r
c
las
sifica
ti
o
n
of
h
u
m
a
n
s
a
n
d
a
n
ima
ls
in
an
o
p
e
ra
ti
o
n
a
l
e
n
v
iro
n
m
e
n
t
,
”
Exp
e
rt
S
y
ste
ms
wit
h
Ap
p
li
c
a
ti
o
n
s
,
v
o
l.
1
0
2
,
pp.
1
-
11
,
Ju
l
y
2
0
1
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j.
e
sw
a
.
2
0
1
8
.
0
2
.
0
1
9
.
[1
6
]
Z.
Hu
a
n
g
,
Y.
Yu
,
J.
G
u
,
a
n
d
H.
Li
u
,
"
An
Eff
icie
n
t
M
e
th
o
d
f
o
r
Traffic
S
ig
n
Re
c
o
g
n
it
i
o
n
Ba
se
d
on
Ex
trem
e
Lea
rn
in
g
M
a
c
h
i
n
e
,
”
IE
EE
T
r
a
n
sa
c
ti
o
n
s
on
Cy
b
e
rn
e
ti
c
s
,
v
o
l.
47
,
n
o
.
4
,
p
p
.
9
2
0
-
9
3
3
,
Ap
ril
2
0
1
7
,
d
o
i:
1
0
.
1
1
0
9
/T
CYB.
2
0
1
6
.
2
5
3
3
4
2
4
.
[1
7
]
J.
-
P.
Ka
u
p
p
i
,
K.
M
a
rti
k
a
in
e
n
,
a
n
d
U.
Ru
o
tsa
lain
e
n
,
“
Hie
ra
rc
h
ica
l
c
las
sifica
ti
o
n
of
d
y
n
a
m
ica
ll
y
v
a
r
y
in
g
ra
d
a
r
p
u
lse
re
p
e
ti
ti
o
n
in
ter
v
a
l
m
o
d
u
latio
n
p
a
tt
e
rn
s
,
”
Ne
u
ra
l
Ne
two
rk
s
,
v
o
l.
23
,
n
o
.
10
,
p
p
.
1
2
2
6
-
1
2
3
7
,
D
e
c
e
m
b
e
r
2010,
doi
:
1
0
.
1
0
1
6
/j
.
n
e
u
n
e
t.
2
0
1
0
.
0
6
.
0
0
8
.
[1
8
]
J.
H.
Kim
,
G.
Ba
tch
u
lu
u
n
,
a
n
d
K.
R.
P
a
rk
,
“
P
e
d
e
strian
d
e
tec
ti
o
n
b
a
se
d
on
fa
ste
r
R
-
CNN
in
n
ig
h
tt
ime
by
fu
si
n
g
d
e
e
p
c
o
n
v
o
lu
ti
o
n
a
l
fe
a
tu
re
s
of
su
c
c
e
ss
iv
e
ima
g
e
s
,
”
Exp
e
rt
S
y
ste
ms
wit
h
A
p
p
li
c
a
ti
o
n
s
,
v
o
l
.
114
,
pp.
15
-
33
,
De
c
e
m
b
e
r
2018
,
d
o
i
:
1
0
.
1
0
1
6
/j
.
e
sw
a
.
2
0
1
8
.
0
7
.
0
2
0
.
[1
9
]
D.
Li,
L.
G
u
,
a
n
d
L.
Zh
u
,
“
Id
e
n
ti
fica
ti
o
n
a
n
d
p
a
ra
m
e
ter
e
stim
a
ti
o
n
a
lg
o
rit
h
m
of
ra
d
a
r
sig
n
a
l
s
u
b
tl
e
fe
a
tu
re
s
,
”
Ph
y
sic
a
l
Co
mm
u
n
ica
ti
o
n
,
v
o
l
.
4
2
,
pp.
1
0
1
1
4
0
,
Oc
to
b
e
r
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/j
.
p
h
y
c
o
m
.
2
0
2
0
.
1
0
1
1
4
0
.
[2
0
]
J.
Li,
X.
M
e
i,
D.
P
r
o
k
h
o
r
o
v
,
a
n
d
D.
Tao
,
“
De
e
p
Ne
u
ra
l
Ne
two
r
k
fo
r
S
tr
u
c
tu
ra
l
P
re
d
ictio
n
a
n
d
Lan
e
De
tec
ti
o
n
in
Traffic
S
c
e
n
e
,
”
IEE
E
T
r
a
n
s
a
c
ti
o
n
s
on
Ne
u
ra
l
Ne
tw
o
rk
s
a
n
d
L
e
a
rn
in
g
S
y
ste
ms
,
v
o
l.
28
,
n
o
.
3
,
p
p
.
6
9
0
-
7
0
3
,
F
e
b
ru
a
ry
2
0
1
6
,
d
o
i:
1
0
.
1
1
0
9
/T
N
NLS
.
2
0
1
6
.
2
5
2
2
4
2
8
.
[2
1
]
Z.
M
a
,
Z.
Hu
a
n
g
,
A.
Li
n
,
a
n
d
G.
Hu
a
n
g
,
“
L
P
I
Ra
d
a
r
Wav
e
fo
r
m
Re
c
o
g
n
it
io
n
Ba
se
d
on
F
e
a
tu
re
s
fro
m
M
u
lt
i
p
le
Im
a
g
e
s
,
”
S
e
n
so
rs
,
v
o
l.
20
,
n
o
.
2
,
p.
5
2
6
,
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/s
2
0
0
2
0
5
2
6
.
[2
2
]
J.
M
u
n
,
H.
Kim
,
a
n
d
J.
Lee
,
“A
d
e
e
p
lea
rn
in
g
a
p
p
ro
a
c
h
f
o
r
a
u
to
m
o
ti
v
e
ra
d
a
r
in
terfe
re
n
c
e
m
it
ig
a
ti
o
n
,
”
IEE
E
8
8
t
h
Veh
icu
la
r
T
e
c
h
n
o
lo
g
y
Co
n
fer
e
n
c
e
(VT
C
-
Fa
ll
)
,
2
0
1
8
,
p
p
.
1
-
5,
d
o
i:
1
0
.
1
1
0
9
/VTC
F
a
ll
.
2
0
1
8
.
8
6
9
0
8
4
8
.
[2
3
]
N.
P
e
tro
v
,
I.
J
o
rd
a
n
o
v
,
a
n
d
J.
Ro
e
,
“
Ra
d
a
r
Emitt
e
r
S
ig
n
a
ls
Re
c
o
g
n
i
ti
o
n
a
n
d
Clas
sifica
ti
o
n
wit
h
F
e
e
d
fo
rwa
rd
Ne
two
rk
s
,
”
Pro
c
e
d
i
a
Co
m
p
u
ter
S
c
ien
c
e
,
v
o
l.
22
,
pp.
1
1
9
2
-
1
2
0
0
,
2
0
1
3
,
d
o
i
:
1
0
.
1
0
1
6
/j
.
p
ro
c
s.
2
0
1
3
.
0
9
.
2
0
6
.
[2
4
]
R.
Z
h
a
n
g
,
a
n
d
S.
Ca
o
,
“
S
u
p
p
o
rt
v
e
c
to
r
m
a
c
h
i
n
e
s
fo
r
c
las
sifica
ti
o
n
of
a
u
to
m
o
ti
v
e
ra
d
a
r
in
terfe
re
n
c
e
,
”
IEE
E
Ra
d
a
r
Co
n
fer
e
n
c
e
(Ra
d
a
r
C
o
n
f
.
1
8
)
2
0
1
8
,
IEE
E,
pp.
3
6
6
-
3
7
1
,
d
o
i:
1
0
.
1
1
0
9
/RADA
R.
2
0
1
8
.
8
3
7
8
5
8
6
.
[2
5
]
M.
Zh
u
,
Y.
Li,
Z.
P
a
n
,
J.
a
n
d
Ya
n
g
,
“
Au
t
o
m
a
ti
c
m
o
d
u
lati
o
n
re
c
o
g
n
it
io
n
of
c
o
m
p
o
u
n
d
si
g
n
a
ls
u
si
n
g
a
d
e
e
p
m
u
lt
i
-
lab
e
l
c
las
sifier:
A
c
a
se
stu
d
y
wit
h
ra
d
a
r
jam
m
in
g
si
g
n
a
ls
,
”
S
i
g
n
a
l
Pro
c
e
ss
in
g
,
v
o
l.
1
6
9
.
pp.
1
0
7
3
9
3
,
A
p
ril
2
0
2
0
,
d
o
i:
1
0
.
1
0
1
6
/j
.
si
g
p
r
o
.
2
0
1
9
.
1
0
7
3
9
3
.
[2
6
]
J
.
Be
c
h
ter,
M
.
Ra
m
e
e
z
,
a
n
d
C
.
Wald
sc
h
m
i
d
t
,
“
An
a
ly
ti
c
a
l
a
n
d
e
x
p
e
rime
n
tal
in
v
e
stig
a
ti
o
n
s
on
m
it
ig
a
ti
o
n
of
in
terfe
re
n
c
e
in
DBF
M
I
M
O
ra
d
a
r
,
”
IEE
E
T
ra
n
sa
c
ti
o
n
s
on
M
icr
o
wa
v
e
T
h
e
o
ry
a
n
d
T
e
c
h
n
i
q
u
e
s
,
v
o
l.
65
,
n
o
.
5
,
p
p
.
1
7
2
7
-
1
7
3
4
,
2
0
1
7
,
d
o
i
:
1
0
.
1
1
0
9
/T
M
T
T.
2
0
1
7
.
2
6
6
8
4
0
4
.
[2
7
]
M
.
Ra
m
e
e
z
,
M
.
Da
h
l
,
a
n
d
M.
I
.
P
e
tt
e
rss
o
n
,
“
Ad
a
p
ti
v
e
d
ig
it
a
l
b
e
a
m
fo
rm
in
g
f
o
r
i
n
terfe
re
n
c
e
su
p
p
re
ss
io
n
in
a
u
to
m
o
ti
v
e
fm
c
w
ra
d
a
rs
,
”
IE
EE
Ra
d
a
r
C
o
n
fer
e
n
c
e
(Ra
d
a
r
Co
n
f
.
1
8
)
,
p
p.
0
2
5
2
-
0
2
5
6
.
IEE
E,
2
0
1
8
,
doi
:
1
0
.
1
1
0
9
/RADA
R.
2
0
1
8
.
8
3
7
8
5
6
6
.
[2
8
]
M.
Ra
m
e
e
z
,
M.
Da
h
l
,
a
n
d
M.
I.
P
e
tt
e
rss
o
n
,
“
Ex
p
e
rime
n
tal
e
v
a
lu
a
ti
o
n
of
a
d
a
p
ti
v
e
b
e
a
m
fo
rm
in
g
f
o
r
a
u
to
m
o
ti
v
e
ra
d
a
r
in
terfe
re
n
c
e
su
p
p
re
ss
io
n
,
”
IEE
E
Ra
d
io
a
n
d
W
ire
les
s
S
y
mp
o
si
u
m
(RW
S
)
,
p
p.
183
-
1
8
6
,
2
0
2
0
,
d
o
i:
1
0
.
1
1
0
9
/RW
S
4
5
0
7
7
.
2
0
2
0
.
9
0
4
9
9
8
2
.
[
2
9
]
M
.
R
a
m
e
e
z
,
M
.
D
a
h
l
,
a
n
d
M
.
I
.
P
e
t
t
e
r
s
s
o
n
.
“
A
u
t
o
r
e
g
r
e
s
s
i
v
e
M
o
d
e
l
-
B
a
s
e
d
S
i
g
n
a
l
r
e
c
o
n
s
t
r
u
c
t
i
o
n
f
o
r
a
u
t
o
m
o
t
i
v
e
r
a
d
a
r
i
n
t
e
r
f
e
r
e
n
c
e
m
i
t
i
g
a
t
i
o
n
”
.
I
E
E
E
S
e
n
s
o
r
s
J
o
u
r
n
a
l
,
V
o
l
u
m
e
:
21,
I
s
s
u
e
:
5,
M
a
r
c
h
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
J
S
E
N
.
2
0
2
0
.
3
0
4
2
0
6
1
.
[
3
0
]
J
.
D
i
c
k
m
a
n
n
,
J
.
K
l
a
p
p
s
t
e
i
n
,
M
.
H
a
h
n
,
N
.
A
p
p
e
n
r
o
d
t
,
H
.
-
L
.
B
l
o
e
c
h
e
r
,
K
.
W
e
r
b
e
r
,
a
n
d
A
.
S
a
i
l
e
r
,
"
A
u
t
o
m
o
t
i
v
e
r
a
d
a
r
t
h
e
k
e
y
t
e
c
h
n
o
l
o
g
y
f
o
r
a
u
t
o
n
o
m
o
u
s
d
r
i
v
i
n
g
:
F
r
o
m
d
e
t
e
c
t
i
o
n
a
n
d
r
a
n
g
i
n
g
to
e
n
v
i
r
o
n
m
e
n
t
a
l
u
n
d
e
r
s
t
a
n
d
i
n
g
,
"
I
E
E
E
R
a
d
a
r
C
o
n
f
e
r
e
n
c
e
,
2016
,
p
p.
1
-
6,
d
o
i
:
1
0
.
1
1
0
9
/
R
A
D
A
R
.
2
0
1
6
.
7
4
8
5
2
1
4
.
[3
1
]
J.
Dic
k
m
a
n
n
,
J.
Kla
p
p
ste
in
,
H.
B
lo
e
c
h
e
r,
M.
M
u
n
tzin
g
e
r
,
a
n
d
H.
M
e
in
e
l
,
“
Au
to
m
o
ti
v
e
ra
d
a
r”
—
“
q
u
o
v
a
d
is?
,
”
9
th
Eu
ro
p
e
a
n
Ra
d
a
r
C
o
n
fer
e
n
c
e
,
Oc
t
.
2
0
1
2
,
p
p.
18
-
2
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:
2502
-
4
7
5
2
I
mp
leme
n
ta
tio
n
o
f fe
a
tu
r
e
ex
tr
a
ctio
n
a
n
d
d
ee
p
lea
r
n
in
g
-
b
a
s
e
d
en
s
em
b
le
cla
s
s
ifier
fo
r
…
(
N
.
Du
r
g
a
I
n
d
ir
a
)
1201
[3
2
]
K.
Ha
h
m
a
n
n
,
S.
S
c
h
n
e
id
e
r
,
a
n
d
T.
Zwick
,
“
Esti
m
a
ti
o
n
of
th
e
i
n
fl
u
e
n
c
e
of
in
c
o
h
e
re
n
t
in
terfe
re
n
c
e
on
th
e
d
e
tec
ti
o
n
of
sm
a
ll
o
b
sta
c
les
with
a
d
b
f
ra
d
a
r
,
”
IEE
E
M
T
T
-
S
I
n
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
on
M
icr
o
wa
v
e
s
fo
r
I
n
tel
li
g
e
n
t
M
o
b
il
it
y
(ICM
IM
)
,
Ap
ril
2
0
1
9
,
p
p.
1
-
4,
d
o
i
:
1
0
.
1
1
0
9
/ICM
IM
.
2
0
1
9
.
8
7
2
6
5
3
5
.
[3
3
]
A
.
G
.
S
to
v
e
,
“
Li
n
e
a
r
fm
c
w
ra
d
a
r
tec
h
n
i
q
u
e
s
,
”
In
IEE
Pro
c
e
e
d
in
g
s
F
(R
a
d
a
r
a
n
d
S
ig
n
a
l
Pro
c
e
ss
in
g
)
,
v
o
l
.
1
3
9
,
p
p.
3
4
3
-
3
5
0
.
IET
,
1
9
9
2
,
d
o
i:
1
0
.
1
0
4
9
/i
p
-
f
-
2
.
1
9
9
2
.
0
0
4
8
.
[3
4
]
Eu
ro
p
e
a
n
Tele
c
o
m
m
u
n
ica
ti
o
n
s
S
t
a
n
d
a
rd
s
I
n
stit
u
te
,
S
h
o
r
t
Ra
n
g
e
D
e
v
ice
s;
Tran
sp
o
r
t
a
n
d
Traffic
Tel
e
m
a
ti
c
s
(TT
T);
“
S
h
o
rt
Ra
n
g
e
Ra
d
a
r
e
q
u
i
p
m
e
n
t
o
p
e
ra
ti
n
g
in
t
h
e
77
G
Hz
to
81
G
H
z
b
a
n
d
;
Ha
rm
o
n
ise
d
S
ta
n
d
a
r
d
c
o
v
e
ri
n
g
t
h
e
e
ss
e
n
ti
a
l
re
q
u
irem
e
n
ts
of
a
rti
c
le
3
.
2
of
Dire
c
ti
v
e
2
0
1
4
/
5
3
/E
U
,
”
EN
302
2
6
4
V
2
.
1
.
1
,
ET
S
I
,
2
,
2
0
1
7
.
[
3
5
]
E
u
r
o
p
e
a
n
T
e
l
e
c
o
m
m
u
n
i
c
a
t
i
o
n
s
S
t
a
n
d
a
r
d
s
I
n
s
t
i
t
u
t
e
,
“
S
h
o
r
t
R
a
n
g
e
D
e
v
i
c
e
s
;
T
r
a
n
s
p
o
r
t
a
n
d
T
r
a
f
f
i
c
T
e
l
e
m
a
t
i
c
s
(
T
T
T
)
;
R
a
d
a
r
e
q
u
i
p
m
e
n
t
o
p
e
r
a
t
i
n
g
in
t
h
e
76
G
H
z
to
77
G
H
z
r
a
n
g
e
;
H
a
r
m
o
n
i
s
e
d
S
t
a
n
d
a
r
d
c
o
v
e
r
i
n
g
t
h
e
e
s
s
e
n
t
i
a
l
r
e
q
u
i
r
e
m
e
n
t
s
of
a
r
t
i
c
l
e
3
.
2
of
D
i
r
e
c
t
i
v
e
2
0
1
4
/
5
3
/
E
U
”
;
P
a
r
t
1:
G
r
o
u
n
d
b
a
s
e
d
v
e
h
i
c
u
l
a
r
r
a
d
a
r
.
EN
301
091
-
1
V
2
.
1
.
1
,
E
T
S
I
,
1
2017.
[
3
6
]
E
u
r
o
p
e
a
n
T
e
l
e
c
o
m
m
u
n
i
c
a
t
i
o
n
s
S
t
a
n
d
a
r
d
s
I
n
s
t
i
t
u
t
e
.
“
S
h
o
r
t
R
a
n
g
e
D
e
v
i
c
e
s
;
T
r
a
n
s
p
o
r
t
a
n
d
T
r
a
f
f
i
c
T
e
l
e
m
a
t
i
c
s
(
T
T
T
)
;
R
a
d
a
r
e
q
u
i
p
m
e
n
t
o
p
e
r
a
t
i
n
g
in
t
h
e
76
G
H
z
to
77
G
H
z
r
a
n
g
e
;
H
a
r
m
o
n
i
s
e
d
S
t
a
n
d
a
r
d
c
o
v
e
r
i
n
g
t
h
e
e
s
s
e
n
t
i
a
l
r
e
q
u
i
r
e
m
e
n
t
s
of
a
r
t
i
c
l
e
3
.
2
of
D
i
r
e
c
t
i
v
e
2
0
1
4
/
5
3
/
E
U
”
;
P
a
r
t
2:
F
i
x
e
d
i
n
f
r
a
s
t
r
u
c
t
u
r
e
r
a
d
a
r
e
q
u
i
p
m
e
n
t
.
EN
301
091
-
2
V
2
.
1
.
1
,
E
T
S
I
,
1
2017.
[3
7
]
H.
M.
G
o
p
p
e
lt
,
“
Blö
c
h
e
r
a
n
d
W.
M
e
n
z
e
l.
“
An
a
ly
t
ica
l
in
v
e
stig
a
ti
o
n
of
m
u
t
u
a
l
i
n
terfe
re
n
c
e
b
e
twe
e
n
a
u
t
o
m
o
ti
v
e
fm
c
w
ra
d
a
r
se
n
so
rs
,
”
Ge
rm
a
n
M
i
c
ro
wa
v
e
Co
n
fer
e
n
c
e
,
M
a
rc
h
2
0
1
1
,
p
p.
1
-
4,
d
o
i:
1
0
.
5
1
9
4
/ars
-
8
-
55
-
2
0
1
0
.
[3
8
]
T
.
S
c
h
i
p
p
e
r,
M
.
Ha
rter,
T
.
M
a
h
ler,
O
.
Ke
rn
a
n
d
T
.
Zwick
,
“
Di
sc
u
ss
io
n
of
t
h
e
o
p
e
ra
ti
n
g
ra
n
g
e
of
fre
q
u
e
n
c
y
m
o
d
u
late
d
ra
d
a
rs
in
t
h
e
p
re
se
n
c
e
of
in
terfe
re
n
c
e
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
of
M
icr
o
w
a
v
e
and
W
ire
les
s
T
e
c
h
n
o
l
o
g
ies
,
v
o
l.
6
,
n
o
.
3
-
4
,
p
p
.
3
7
1
-
3
7
8
,
2
0
1
4
,
d
o
i:
1
0
.
1
0
1
7
/
S
1
7
5
9
0
7
8
7
1
4
0
0
0
2
2
1
.
[3
9
]
M.
Ku
n
e
rt
,
Th
e
EU
p
r
o
jec
t
M
O
S
ARIM
,
“A
g
e
n
e
ra
l
o
v
e
r
v
iew
of
p
ro
jec
t
o
b
jec
ti
v
e
s
a
n
d
c
o
n
d
u
c
t
e
d
wo
rk
,
”
9
th
Eu
ro
p
e
a
n
Ra
d
a
r
C
o
n
fer
e
n
c
e
,
p
p.
1
-
5,
Oc
t.
2
0
1
2
.
[4
0
]
M.
I.
S
k
o
ln
i
k
,
“
I
n
tro
d
u
c
ti
o
n
to
Ra
d
a
r
S
y
ste
m
s
,
”
El
e
c
trica
l
e
n
g
in
e
e
r
in
g
se
rie
s
,
M
c
G
ra
w
-
Hill
,
2
0
0
1
.
[4
1
]
J
.
Ha
sc
h
,
E
.
To
p
a
k
,
R
.
S
c
h
n
a
b
e
l
,
T
.
Zwick
,
R
.
Wei
g
e
l
,
a
n
d
C
.
Wald
sc
h
m
id
t,
“
M
i
ll
ime
ter
-
wa
v
e
tec
h
n
o
l
o
g
y
fo
r
a
u
to
m
o
ti
v
e
ra
d
a
r
se
n
so
rs
in
t
h
e
77
G
Hz
fre
q
u
e
n
c
y
b
a
n
d
,
”
I
EE
E
T
r
a
n
s
a
c
ti
o
n
s
on
M
icr
o
w
a
v
e
T
h
e
o
ry
a
n
d
T
e
c
h
n
iq
u
e
s
,
v
o
l.
60
,
n
o
.
3
,
p
p
.
845
-
8
6
0
,
M
a
rc
h
2
0
1
2
,
d
o
i:
1
0
.
1
1
0
9
/
TM
TT
.
2
0
1
1
.
2
1
7
8
4
2
7
.
[4
2
]
V.
Wi
n
k
ler
,
“
Ra
n
g
e
Do
p
p
ler
d
e
t
e
c
ti
o
n
fo
r
a
u
to
m
o
t
iv
e
fm
c
w
ra
d
a
rs
,”
Eu
ro
p
e
a
n
R
a
d
a
r
Co
n
fer
e
n
c
e
,
p
p.
1
6
6
-
1
6
9
,
Oc
t
2
0
0
7
,
d
o
i:
1
0
.
1
1
0
9
/
EUM
C.
2
0
0
7
.
4
4
0
5
4
7
7
.
[4
3
]
H.
Krim
a
n
d
M.
Vi
b
e
rg
,
“
Tw
o
d
e
c
a
d
e
s
of
a
rra
y
sig
n
a
l
p
ro
c
e
ss
in
g
r
e
se
a
rc
h
:
th
e
p
a
ra
m
e
tri
c
a
p
p
ro
a
c
h
,
”
IEE
E
S
i
g
n
a
l
Pro
c
e
ss
in
g
M
a
g
a
zin
e
,
v
o
l.
13
,
n
o
.
4
,
p
p
.
67
-
9
4
,
J
u
ly
1
9
9
6
,
d
o
i
:
1
0
.
1
1
0
9
/
7
9
.
5
2
6
8
9
9
.
[4
4
]
J.
Din
g
,
V.
Tar
o
k
h
,
a
n
d
Y.
Ya
n
g
,
“
M
o
d
e
l
se
lec
ti
o
n
tec
h
n
iq
u
e
s:
An
o
v
e
r
v
iew
,
”
IEE
E
S
ig
n
a
l
Pro
c
e
ss
in
g
M
a
g
a
zi
n
e
,
v
o
l.
35
,
n
o
.
6
,
p
p
.
16
-
34,
No
v
2
0
1
8
,
d
o
i:
1
0
.
1
1
0
9
/M
S
P
.
2
0
1
8
.
2
8
6
7
6
3
8
.
[
4
5
]
D.
C
h
a
k
r
a
b
o
r
t
y
a
n
d
S.
K.
S
a
n
y
a
l
,
“
P
e
r
f
o
r
m
a
n
c
e
a
n
a
l
y
s
i
s
of
d
i
f
f
e
r
e
n
t
a
u
t
o
r
e
g
r
e
s
s
i
v
e
m
e
t
h
o
d
s
f
o
r
s
p
e
c
t
r
u
m
e
s
t
i
m
a
t
i
o
n
a
l
o
n
g
w
i
t
h
t
h
e
i
r
r
e
a
l
t
i
m
e
i
m
p
l
e
m
e
n
t
a
t
i
o
n
s
,
”
S
e
c
o
n
d
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
on
R
e
s
e
a
r
c
h
in
C
o
m
p
u
t
a
t
i
o
n
a
l
I
n
t
e
l
l
i
g
e
n
c
e
and
C
o
m
m
u
n
i
c
a
t
i
o
n
N
e
t
w
o
r
k
s
(
I
C
R
C
I
C
N
)
,
S
e
p
.
2
0
1
6
,
p
p.
141
-
146,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
R
C
I
C
N
.
2
0
1
6
.
7
8
1
3
6
4
6
.
[4
6
]
M.
Ba
rjen
b
ru
c
h
,
D.
Ke
ll
n
e
r,
K.
Die
tma
y
e
r,
J.
Kla
p
p
ste
in
,
a
n
d
J.
Dic
k
m
a
n
n
,
“A
m
e
th
o
d
f
o
r
i
n
terfe
re
n
c
e
c
a
n
c
e
ll
a
ti
o
n
in
a
u
to
m
o
ti
v
e
ra
d
a
r
,
”
IEE
E
M
T
T
-
S
I
n
ter
n
a
t
io
n
a
l
Co
n
fer
e
n
c
e
on
M
icr
o
w
a
v
e
s
fo
r
I
n
te
ll
ig
e
n
t
M
o
b
i
li
ty
(ICM
IM
)
,
Ap
ril
2
0
1
5
,
p
p.
1
-
4,
d
o
i
:
1
0
.
1
1
0
9
/ICM
IM
.
2
0
1
5
.
7
1
1
7
9
2
5
.
B
I
O
G
RAP
H
I
E
S
OF
AUTH
O
RS
N.
Durg
a
Ind
ira
,
is
p
u
rs
u
in
g
P
h
D
d
e
g
re
e
in
K
L
Un
i
v
e
rsity
,
Vijay
a
wa
d
a
in
t
h
e
fa
c
u
lt
y
of
El
e
c
tro
n
ics
a
n
d
Co
m
m
u
n
ica
ti
o
n
En
g
i
n
e
e
rin
g
,
sp
e
c
ialize
d
in
Co
m
m
u
n
ica
ti
o
n
s.
S
h
e
re
c
e
iv
e
d
h
e
r
M
a
ste
r
of
En
g
i
n
e
e
rin
g
De
g
re
e
in
Co
m
m
u
n
ica
ti
o
n
a
n
d
Ra
d
a
r
S
y
ste
m
s
fro
m
K
L
Un
iv
e
rsity
,
Va
d
d
e
sw
a
ra
m
.
He
r
p
re
se
n
t
a
ffil
iatio
n
is
with
K
L
U
n
iv
e
rsit
y
sin
c
e
2
0
1
2
,
Vijay
a
wa
d
a
d
e
sig
n
a
ted
as
As
sista
n
t
p
ro
fe
ss
o
r
in
ECE
.
S
h
e
is
a
fe
ll
o
w
of
IET
E
a
n
d
li
fe
m
e
m
b
e
r
in
IAENG
,
IS
TE
.
He
r
re
se
a
rc
h
in
tere
st
in
c
lu
d
e
s
sig
n
a
l
p
ro
c
e
ss
in
g
,
c
o
m
p
re
ss
iv
e
se
n
si
n
g
,
Co
m
m
u
n
ica
ti
o
n
s.
S
h
e
h
a
s
p
u
b
li
sh
e
d
p
a
p
e
rs
in
v
a
ri
o
u
s
in
tern
a
ti
o
n
a
l
a
n
d
n
a
ti
o
n
a
l
jo
u
rn
a
ls,
c
o
n
f
e
re
n
c
e
s
a
n
d
wo
rk
s
h
o
p
s.
M.
Ve
n
u
G
o
p
a
l
a
R
a
o
o
b
tain
e
d
h
is
A
M
IET
E
d
e
g
re
e
fr
o
m
In
stit
u
te
of
El
e
c
tro
n
ics
a
n
d
Tele
c
o
m
m
u
n
ica
ti
o
n
E
n
g
i
n
e
e
rs,
Ne
w
De
lh
i,
In
d
ia
d
u
r
in
g
1
9
9
6
.
He
o
b
tain
e
d
h
is
M.
Tec
h
.
fro
m
Re
g
io
n
a
l
En
g
in
e
e
rin
g
Co
ll
e
g
e
,
Wara
n
g
a
l,
a
n
d
Do
c
to
ra
te
fr
o
m
Os
m
a
n
ia
Un
iv
e
rsity
,
H
y
d
e
ra
b
a
d
.
He
p
o
ss
e
ss
e
s
17
y
e
a
rs
of
tea
c
h
in
g
e
x
p
e
rien
c
e
a
n
d
21
y
e
a
rs
of
i
n
d
u
strial
e
x
p
e
rien
c
e
.
P
re
se
n
t
ly
he
is
wo
rk
in
g
as
P
ro
fe
ss
o
r
in
th
e
d
e
p
a
rtme
n
t
of
ECE
a
n
d
As
so
c
iate
De
a
n
(Qu
a
li
ty
-
Au
d
i
ts),
K
L
Un
iv
e
rsity
,
Va
d
d
e
sw
a
ra
m
,
G
u
n
tu
r
Dt,
A.
P
.
,
I
n
d
ia.
He
re
c
e
iv
e
d
a
‘c
re
d
it
a
wa
rd
’
in
Ra
d
io
S
e
rv
icin
g
T
h
e
o
ry
fro
m
Cit
y
a
n
d
G
u
il
d
’s
L
o
n
d
o
n
I
n
stit
u
te,
L
o
n
d
o
n
in
1
9
7
8
.
He
is
a
fe
ll
o
w
of
IET
E
a
n
d
li
fe
m
e
m
b
e
r
in
IAE,
IS
TE
,
S
S
I,
a
n
d
IS
OI.
His
re
se
a
rc
h
i
n
tere
st
in
c
l
u
d
e
s
si
g
n
a
l,
ima
g
e
p
ro
c
e
ss
in
g
,
G
P
S
c
o
m
p
re
ss
iv
e
se
n
sin
g
,
S
p
a
rse
a
n
d
Dic
ti
o
n
a
r
y
lea
rn
in
g
.
He
h
a
s
p
u
b
li
s
h
e
d
m
o
re
th
a
n
50
p
a
p
e
rs
in
v
a
ri
o
u
s
i
n
tern
a
ti
o
n
a
l
a
n
d
n
a
ti
o
n
a
l
jo
u
rn
a
ls,
c
o
n
fe
r
e
n
c
e
s
a
n
d
wo
rk
s
h
o
p
s.
Evaluation Warning : The document was created with Spire.PDF for Python.