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.
12
,
No
.
1
,
Feb
r
u
ar
y
20
22
,
p
p
.
399
~
410
I
SS
N:
2088
-
8
7
0
8
,
DOI
: 1
0
.
1
1
5
9
1
/
ijece
.
v
1
2
i
1
.
pp
3
9
9
-
4
1
0
399
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
Ama
teur
ra
dio
se
nsing
t
echni
que u
sing
a co
mbina
tion o
f
ene
rg
y
detec
tion a
nd wa
v
eform cla
ss
ificat
io
n
Na
ra
t
hep P
hruk
s
a
hira
n
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
i
c
a
l
En
g
i
n
e
e
r
i
n
g
,
C
h
u
l
a
c
h
o
m
k
l
a
o
R
o
y
a
l
M
i
l
i
t
a
r
y
A
c
a
d
e
my
,
N
a
k
h
o
n
N
a
y
o
k
,
T
h
a
i
l
a
n
d
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Ma
r
2
9
,
2
0
2
1
R
ev
is
ed
Ma
y
3
1
,
2
0
2
1
Acc
ep
ted
J
u
l 1
,
2
0
2
1
A
c
rit
ica
l
p
ro
b
lem
in
sp
e
c
tru
m
se
n
sin
g
is
to
c
re
a
te
a
d
e
tec
ti
o
n
a
lg
o
rit
h
m
a
n
d
tes
t
sta
ti
stics
.
Th
e
e
x
isti
n
g
a
p
p
r
o
a
c
h
e
s
e
m
p
lo
y
th
e
e
n
e
r
g
y
le
v
e
l
o
f
e
a
c
h
c
h
a
n
n
e
l
o
f
in
tere
st.
Ho
we
v
e
r,
th
i
s
fe
a
tu
re
c
a
n
n
o
t
a
c
c
u
ra
tely
c
h
a
ra
c
teriz
e
th
e
a
c
tu
a
l
a
p
p
li
c
a
ti
o
n
o
f
p
u
b
li
c
a
m
a
teu
r
ra
d
io
.
T
h
e
tran
sm
it
ted
sig
n
a
l
is
n
o
t
c
o
n
ti
n
u
o
u
s
a
n
d
m
a
y
c
o
n
sist
o
n
l
y
o
f
a
c
a
rrier
fre
q
u
e
n
c
y
with
o
u
t
i
n
f
o
rm
a
ti
o
n
.
Th
is
p
a
p
e
r
p
ro
p
o
se
s
a
n
o
v
e
l
e
n
e
rg
y
d
e
tec
ti
o
n
a
n
d
wa
v
e
fo
r
m
fe
a
tu
re
c
las
sifica
ti
o
n
(EDW
C)
a
lg
o
rit
h
m
to
d
e
tec
t
sp
e
e
c
h
sig
n
a
ls
i
n
p
u
b
li
c
fre
q
u
e
n
c
y
b
a
n
d
s b
a
se
d
o
n
e
n
e
r
g
y
d
e
tec
ti
o
n
a
n
d
s
u
p
e
rv
ise
d
m
a
c
h
in
e
lea
rn
in
g
.
Th
e
e
n
e
rg
y
lev
e
l,
d
e
sc
rip
ti
v
e
sta
ti
stics
,
a
n
d
sp
e
c
tral
m
e
a
su
re
m
e
n
t
s
o
f
ra
d
io
c
h
a
n
n
e
ls
a
re
trea
ted
a
s
fe
a
tu
re
v
e
c
to
rs
a
n
d
c
las
sifiers
to
d
e
term
in
e
wh
e
th
e
r
th
e
sig
n
a
l
is
sp
e
e
c
h
o
r
n
o
ise
.
Th
e
a
lg
o
rit
h
m
is
v
a
li
d
a
ted
u
s
in
g
a
c
tu
a
l
fre
q
u
e
n
c
y
m
o
d
u
latio
n
(
F
M
)
b
r
o
a
d
c
a
stin
g
a
n
d
p
u
b
li
c
a
m
a
teu
r
si
g
n
a
ls.
Th
e
p
ro
p
o
se
d
EDW
C
a
lg
o
rit
h
m
'
s
p
e
rfo
rm
a
n
c
e
is
e
v
a
lu
a
ted
in
term
s
o
f
train
i
n
g
d
u
ra
ti
o
n
,
c
las
sifica
ti
o
n
ti
m
e
,
a
n
d
re
c
e
iv
e
r
o
p
e
ra
ti
n
g
c
h
a
ra
c
teristic.
T
h
e
sim
u
latio
n
a
n
d
e
x
p
e
rime
n
tal
o
u
tc
o
m
e
s
sh
o
w
th
a
t
th
e
EDW
C
c
a
n
d
isti
n
g
u
ish
a
n
d
c
las
sify
wa
v
e
fo
rm
c
h
a
ra
c
teristics
fo
r
s
p
e
c
tru
m
se
n
si
n
g
p
u
r
p
o
se
s,
p
a
rti
c
u
larly
fo
r
th
e
p
u
b
li
c
a
m
a
teu
r
u
se
c
a
se
.
Th
e
n
o
v
e
l
tec
h
n
ica
l
re
su
lt
s
c
a
n
d
e
tec
t
a
n
d
c
las
sify
p
u
b
li
c
ra
d
i
o
fr
e
q
u
e
n
c
y
sig
n
a
ls
a
s
v
o
ice
sig
n
a
ls
f
o
r
sp
e
e
c
h
c
o
m
m
u
n
ica
ti
o
n
o
r
ju
st
n
o
ise
,
wh
ich
is
e
ss
e
n
ti
a
l
a
n
d
c
a
n
b
e
a
p
p
li
e
d
in
se
c
u
rit
y
a
sp
e
c
ts.
K
ey
w
o
r
d
s
:
C
o
g
n
itiv
e
r
ad
io
E
n
er
g
y
d
etec
tio
n
Ma
ch
in
e
lear
n
in
g
Sp
ec
tr
u
m
s
en
s
in
g
W
av
ef
o
r
m
class
if
icatio
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
:
Nar
ath
ep
Ph
r
u
k
s
ah
ir
an
Dep
ar
tm
en
t o
f
E
lectr
ical
E
n
g
i
n
ee
r
in
g
,
C
h
u
lach
o
m
k
lao
R
o
y
a
l M
ilit
ar
y
Aca
d
em
y
Nak
h
o
n
Nay
o
k
,
2
6
0
0
1
,
T
h
aila
n
d
E
m
ail: n
ar
ath
ep
p
@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
r
a
d
io
s
p
ec
tr
u
m
r
em
ain
s
t
h
e
r
ad
i
o
f
r
eq
u
e
n
cy
(
R
F)
p
ar
t
o
f
th
e
elec
tr
o
m
a
g
n
etic
s
p
ec
tr
u
m
,
wh
ic
h
is
co
n
s
id
er
ed
a
lim
ited
s
o
u
r
ce
.
W
ith
th
e
ad
v
an
ce
m
en
t
o
f
c
o
m
m
u
n
icatio
n
tech
n
o
lo
g
y
,
g
o
v
er
n
m
en
t
ag
e
n
cies
m
u
s
t
s
u
p
er
v
is
e
th
e
m
an
a
g
e
m
en
t
o
f
th
e
f
r
eq
u
en
cy
b
a
n
d
f
o
llo
w
in
g
r
u
les
t
o
av
o
id
m
u
tu
al
in
ter
f
er
en
ce
.
T
h
er
ef
o
r
e,
m
o
n
ito
r
in
g
s
p
ec
tr
u
m
u
s
ag
e
an
d
r
ec
o
r
d
in
g
u
s
ag
e
s
tatis
tic
s
ar
e
ess
en
tial
f
o
r
th
e
d
ev
elo
p
m
en
t,
im
p
r
o
v
em
e
n
t
a
n
d
is
s
u
an
ce
o
f
r
eg
u
latio
n
s
u
n
d
er
ac
tu
al
u
s
e
co
n
d
itio
n
s
,
p
a
r
ticu
lar
ly
r
eg
a
r
d
in
g
th
e
a
v
ailab
le
f
r
eq
u
e
n
cies
o
f
p
u
b
lic
am
ateu
r
r
ad
io
.
T
h
e
tech
n
o
lo
g
y
th
at
ca
n
b
e
u
s
ed
to
s
u
p
p
o
r
t
th
is
ac
tiv
ity
is
co
g
n
itiv
e
r
ad
io
(
C
R
)
,
wh
ich
h
as
b
ee
n
u
s
ed
ex
ten
s
iv
ely
in
s
o
lv
in
g
th
e
p
r
o
b
lem
o
f
f
r
eq
u
en
cy
d
e
n
s
ity
,
as
d
em
o
n
s
tr
ated
in
[
1
]
,
[
2
]
.
Du
e
to
th
e
in
cr
ea
s
in
g
d
e
m
an
d
f
o
r
r
ad
io
f
r
eq
u
en
cy
co
m
m
u
n
i
ca
tio
n
,
it
is
v
er
y
ch
allen
g
i
n
g
t
o
ex
p
lo
it
th
ese
lim
ited
o
r
u
n
d
e
r
u
tili
ze
d
s
p
ec
tr
al
r
eso
u
r
ce
s
b
y
u
s
in
g
C
R
tech
n
o
lo
g
y
,
as
p
r
esen
ted
b
y
[
3
]
.
O
n
e
o
f
th
e
ess
en
tial
elem
en
ts
o
f
C
R
th
e
o
r
y
is
th
e
a
b
ilit
y
to
m
ea
s
u
r
e,
u
n
d
er
s
tan
d
,
d
eter
m
in
e
an
d
b
e
in
f
o
r
m
e
d
o
f
th
e
p
ar
am
eter
s
r
elate
d
to
r
ad
io
ch
an
n
el
p
r
o
p
e
r
ties
,
as
s
h
o
wn
b
y
[
4
]
,
[
5
]
.
T
h
e
m
ain
f
ea
tu
r
es
o
f
C
R
ar
e
s
p
ec
tr
u
m
s
en
s
in
g
,
s
p
ec
tr
u
m
d
ec
is
io
n
,
a
n
d
s
p
ec
tr
u
m
s
h
ar
i
n
g
an
d
s
p
e
ctr
u
m
m
o
b
ilit
y
,
as
s
h
o
wn
b
y
[
6
]
,
[
7
]
.
Sp
ec
tr
u
m
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.
12
,
No
.
1
,
Feb
r
u
ar
y
20
22
:
3
9
9
-
410
400
s
en
s
in
g
is
th
e
r
esp
o
n
s
ib
ilit
y
to
o
b
tain
k
n
o
wled
g
e
ab
o
u
t
t
h
e
s
p
ec
tr
u
m
u
s
ag
e
an
d
p
r
es
en
ce
o
f
u
s
er
s
in
a
g
eo
g
r
a
p
h
ical
ar
ea
.
As
d
em
o
n
s
tr
ated
b
y
[
8
]
,
[
9
]
,
t
h
e
b
asic
s
p
ec
tr
u
m
s
en
s
in
g
tech
n
i
q
u
es
a
r
e
en
er
g
y
d
etec
tio
n
(
E
D)
,
m
atch
ed
f
ilter
d
etec
tio
n
,
cy
clo
s
tatio
n
ar
y
d
etec
tio
n
,
an
d
ce
r
tain
o
th
er
d
e
tectio
n
t
ec
h
n
iq
u
es,
ea
ch
o
f
wh
ich
h
as
o
p
er
atio
n
al
s
p
ec
if
icatio
n
s
,
b
en
ef
its
an
d
lim
it
atio
n
s
.
E
D
is
a
s
u
cc
ess
f
u
l
an
d
u
n
c
o
m
p
licate
d
tech
n
iq
u
e
th
at
is
p
a
r
ticu
lar
ly
s
u
ited
to
a
r
a
n
d
o
m
s
ig
n
al,
an
d
i
t w
ill b
e
co
n
s
id
er
ed
in
th
is
p
ap
er
.
E
D
is
o
n
e
o
f
th
e
s
im
p
lest
m
e
th
o
d
s
o
f
d
e
t
e
c
t
i
o
n
t
e
c
h
n
o
l
o
g
y
b
e
c
a
u
s
e
t
h
e
C
R
r
e
c
e
i
v
e
r
d
o
e
s
n
o
t
r
e
q
u
i
r
e
a
n
y
i
n
f
o
r
m
a
t
i
o
n
a
b
o
u
t
t
h
e
s
a
m
p
l
e
s
r
e
c
e
i
v
e
d
p
r
e
v
i
o
u
s
l
y
.
N
o
t
a
b
l
y
,
i
t
s
p
u
r
p
o
s
e
i
s
t
o
p
r
o
c
e
s
s
t
h
e
r
e
c
e
i
v
e
d
s
a
m
p
l
e
s
t
o
e
s
t
i
m
a
t
e
t
h
e
e
n
e
r
g
y
l
e
v
e
l
i
n
t
h
e
c
h
a
n
n
e
l
.
A
s
d
e
m
o
n
s
t
r
a
t
e
d
b
y
[
1
0
]
,
t
h
e
au
t
h
o
r
s
p
r
o
p
o
s
ed
a
m
eth
o
d
to
u
s
e
E
D
af
ter
o
p
tim
ally
co
m
b
in
in
g
th
e
s
ig
n
al
s
am
p
les
r
ec
eiv
ed
in
s
p
a
c
e
a
n
d
t
i
m
e
b
as
e
d
o
n
t
h
e
p
r
i
n
ci
p
l
e
o
f
m
a
x
i
m
i
zi
n
g
t
h
e
s
i
g
n
a
l
-
to
-
n
o
i
s
e
r
a
ti
o
(
S
NR
)
.
T
h
e
d
e
t
e
r
m
i
n
a
t
i
o
n
o
f
t
h
e
th
r
e
s
h
o
l
d
i
s
t
h
e
c
r
i
t
i
ca
l
p
a
r
a
m
e
t
e
r
i
n
t
h
e
c
l
ass
i
c
a
l
e
n
e
r
g
y
d
e
t
e
c
t
o
r
.
I
t
m
u
s
t
b
e
o
p
ti
m
i
z
e
d
f
o
r
e
a
c
h
d
e
t
e
c
ti
o
n
t
e
c
h
n
i
q
u
e
t
o
i
m
p
r
o
v
e
i
t
s
p
e
r
f
o
r
m
a
n
c
e
,
a
s
d
e
m
o
n
s
t
r
a
t
e
d
b
y
[
1
1
]
-
[
1
3
]
.
I
n
a
w
i
d
e
-
b
a
n
d
s
p
e
c
t
r
u
m
s
e
n
s
i
n
g
s
c
e
n
a
r
i
o
,
a
s
u
b
b
a
n
d
E
D
m
e
t
h
o
d
c
a
n
p
e
r
f
o
r
m
e
f
f
e
c
t
i
v
e
l
y
u
n
d
e
r
n
o
i
s
e
u
n
c
e
r
t
a
i
n
t
y
a
n
d
f
r
e
q
u
e
n
c
y
-
s
e
l
e
c
t
i
v
e
c
h
a
n
n
e
l
s
a
n
d
t
h
e
i
m
p
l
e
m
e
n
t
a
t
i
o
n
o
f
f
i
l
t
e
r
b
a
n
k
s
p
e
c
t
r
u
m
s
e
n
s
i
n
g
,
a
s
s
h
o
w
n
b
y
[
1
4
]
,
[
1
5
]
,
r
e
s
p
e
c
t
i
v
e
l
y
.
H
o
w
e
v
e
r
,
t
h
e
f
u
n
d
a
m
e
n
t
a
l
p
r
i
n
c
i
p
l
e
o
f
E
D
i
s
t
o
c
o
m
p
a
r
e
t
h
e
s
i
g
n
a
l
e
n
e
r
g
y
t
o
a
s
e
n
s
i
n
g
t
h
r
e
s
h
o
l
d
i
n
a
g
i
v
e
n
b
a
n
d
w
i
d
t
h
w
i
t
h
i
n
a
s
p
e
c
i
f
i
c
s
e
n
s
i
n
g
p
e
r
i
o
d
,
a
s
d
e
m
o
n
s
t
r
a
t
e
d
b
y
[
1
6
]
.
Ma
n
y
r
esear
ch
er
s
h
av
e
f
o
cu
s
e
d
o
n
s
im
u
latin
g
an
d
m
ak
in
g
r
ea
l
-
tim
e
m
ea
s
u
r
em
en
ts
f
o
r
a
wid
e
r
an
g
e
o
f
en
v
ir
o
n
m
en
ts
an
d
co
n
d
itio
n
s
.
Ko
ley
et
a
l.
[
1
7
]
,
Var
m
a
a
n
d
Mitr
a
in
[
1
8
]
u
s
ed
NI
-
USR
P,
wh
ich
in
ter
f
ac
ed
with
a
s
y
s
tem
th
r
o
u
g
h
L
ab
V
I
E
W
s
o
f
twar
e
to
ac
t
as
an
R
F
tr
an
s
ce
iv
er
.
A
wir
eles
s
o
p
en
-
ac
ce
s
s
r
esear
ch
p
latf
o
r
m
(
W
AR
P)
b
o
ar
d
was
im
p
lem
en
ted
in
r
ea
l
-
tim
e
E
D,
as
d
em
o
n
s
tr
ated
b
y
[
1
9
]
,
[
2
0
]
.
Mo
r
e
o
v
er
,
th
e
R
Fey
e
s
en
s
in
g
n
o
d
e
was
u
s
e
d
to
r
ec
o
r
d
s
ig
n
als
f
o
r
r
ad
io
s
p
ec
tr
u
m
m
o
n
ito
r
in
g
p
u
r
p
o
s
es,
as
s
h
o
wn
b
y
[
2
1
]
.
An
o
th
er
in
ter
esti
n
g
is
s
u
e,
as
p
r
esen
ted
b
y
[
2
2
]
,
is
th
e
ca
s
e
in
wh
ich
th
e
t
r
an
s
m
itter
s
witch
es
f
r
o
m
ac
tiv
e
to
in
ter
ac
tiv
e
at
r
an
d
o
m
tim
e
in
ter
v
als.
T
h
is
p
ap
er
u
s
es
a
Z
e
d
B
o
ar
d
co
m
b
in
ed
with
th
e
a
n
alo
g
d
e
v
ices
AD
-
FMC
OM
M
S3
m
o
d
u
le
as
th
e
C
R
r
ec
eiv
er
in
th
e
ex
p
er
i
m
en
tal
s
etu
p
.
T
h
e
m
o
d
u
les
ar
e
co
n
tr
o
lled
an
d
p
r
o
ce
s
s
ed
with
a
p
r
o
g
r
am
d
ev
elo
p
ed
in
MA
T
L
AB
.
I
t
is
n
o
w
wid
el
y
ac
ce
p
ted
th
at
ar
tific
ial
in
tellig
en
ce
tech
n
o
lo
g
y
p
er
f
o
r
m
s
ess
en
tial
f
u
n
ctio
n
s
in
ev
er
y
f
ield
;
f
o
r
ex
am
p
le,
th
e
r
e
is
a
m
ac
h
in
e
lear
n
in
g
ap
p
r
o
a
ch
to
r
an
g
in
g
er
r
o
r
m
i
g
r
ati
o
n
f
o
r
lo
ca
lizatio
n
alg
o
r
ith
m
s
,
as
s
h
o
wn
b
y
[
2
3
]
.
Nu
m
e
r
o
u
s
m
ac
h
in
e
lea
r
n
in
g
tech
n
i
q
u
es,
in
clu
d
in
g
b
o
th
s
u
p
er
v
is
ed
an
d
u
n
s
u
p
er
v
is
ed
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
s
,
h
a
v
e
e
v
en
b
ee
n
u
s
ed
a
n
d
a
p
p
lied
i
n
s
p
ec
tr
u
m
s
en
s
in
g
ap
p
licatio
n
s
,
as
d
em
o
n
s
tr
ated
b
y
[
2
4
]
-
[
2
7
]
.
I
n
ad
d
itio
n
,
d
etec
tio
n
an
d
class
if
icatio
n
b
ased
o
n
wav
ef
o
r
m
ch
ar
ac
ter
is
tics
h
av
e
b
ee
n
in
v
e
s
tig
ated
in
n
u
m
e
r
o
u
s
ar
ea
s
,
s
u
ch
as
s
eismic
s
ig
n
als,
elec
tr
o
ca
r
d
io
g
r
am
s
ig
n
als
an
d
m
u
ltip
lex
in
g
s
ig
n
als,
as
s
h
o
wn
b
y
[
2
8
]
-
[3
0
]
.
T
h
e
c
o
m
b
in
atio
n
o
f
m
ac
h
in
e
lea
r
n
i
n
g
p
er
f
o
r
m
a
n
ce
an
d
wav
e
ch
ar
ac
ter
an
al
y
s
is
ca
n
b
e
u
s
ed
t
o
d
esig
n
n
o
v
el
m
o
d
el
s
th
at
ca
n
o
p
e
r
ate
m
o
r
e
e
f
f
ici
en
tly
f
o
r
s
p
ec
tr
u
m
s
en
s
in
g
p
u
r
p
o
s
es.
I
n
ac
tu
al
u
s
e,
a
p
ar
ticu
lar
f
r
eq
u
en
cy
s
p
ec
tr
u
m
h
as
d
iv
er
s
e
ch
ar
ac
ter
is
tics
a
n
d
ap
p
licatio
n
s
.
T
h
e
Of
f
ice
o
f
Natio
n
al
B
r
o
a
d
ca
s
tin
g
an
d
T
elec
o
m
m
u
n
icatio
n
s
C
o
m
m
is
s
io
n
,
T
h
ailan
d
,
h
as
d
e
ter
m
in
ed
th
e
c
o
n
tr
o
l
o
f
th
e
f
r
e
q
u
en
c
y
b
an
d
in
th
e
Natio
n
al
T
ab
le
o
f
Fre
q
u
e
n
cy
Allo
ca
tio
n
,
as
s
h
o
wn
b
y
[
3
1
]
,
b
y
s
p
ec
if
y
in
g
th
e
u
s
e
o
f
th
e
f
r
eq
u
e
n
cy
r
an
g
e
134
-
1
7
4
MH
z
f
o
r
am
ateu
r
p
u
b
li
c
r
ad
io
.
T
h
e
n
u
m
b
er
o
f
am
a
teu
r
r
ad
io
u
s
er
s
in
T
h
ailan
d
is
co
n
tin
u
o
u
s
ly
in
c
r
ea
s
in
g
.
Ho
wev
er
,
th
e
r
e
is
s
till
a
lack
o
f
s
tatis
tic
s
o
n
u
s
ag
e,
in
clu
d
in
g
th
e
d
is
tu
r
b
an
ce
o
f
th
e
f
r
eq
u
e
n
cy
s
p
ec
tr
u
m
in
th
e
a
m
ateu
r
r
a
d
i
o
b
an
d
,
wh
ich
is
v
er
y
im
p
o
r
t
an
t
f
o
r
th
e
ag
en
cies
r
esp
o
n
s
ib
le
f
o
r
g
o
v
er
n
in
g
th
e
allo
ca
tio
n
o
f
s
p
ec
tr
u
m
r
eso
u
r
c
es.
Mo
tiv
ated
b
y
th
e
ab
o
v
e
c
h
allen
g
es,
th
is
p
ap
er
p
r
o
p
o
s
es
an
en
er
g
y
d
etec
tio
n
an
d
wav
ef
o
r
m
f
ea
tu
r
e
class
if
icatio
n
(
E
DW
C
)
alg
o
r
ith
m
f
o
r
am
ateu
r
p
u
b
lic
r
a
d
io
b
ased
o
n
E
D
tec
h
n
iq
u
es
an
d
wav
e
f
o
r
m
ch
ar
ac
ter
is
tics
th
at
u
s
e
m
ac
h
i
n
e
lear
n
i
n
g
alg
o
r
ith
m
s
.
T
h
e
o
n
ly
p
r
io
r
in
f
o
r
m
atio
n
r
e
q
u
ir
ed
is
th
e
b
an
d
wid
th
o
f
ea
ch
ch
an
n
el
$
B
$
.
T
h
e
p
r
o
p
o
s
ed
E
DW
C
alg
o
r
ith
m
co
n
s
is
ts
o
f
two
p
r
o
ce
s
s
es:
E
D
an
d
wav
ef
o
r
m
class
if
icatio
n
.
T
h
e
wav
ef
o
r
m
class
if
icatio
n
p
r
o
ce
s
s
in
clu
d
es
two
s
tep
s
:
i)
th
e
tr
ain
i
n
g
p
h
ase
an
d
ii)
th
e
id
en
tific
atio
n
o
f
clu
s
ter
s
as
s
o
u
n
d
o
r
n
o
is
e
s
ig
n
als.
T
o
th
e
b
est
o
f
th
e
au
th
o
r
'
s
k
n
o
wled
g
e,
d
etec
tio
n
an
d
m
ac
h
in
e
lear
n
in
g
tech
n
iq
u
es
h
av
e
n
o
t
b
ee
n
a
d
o
p
te
d
f
o
r
s
p
ec
tr
u
m
s
en
s
in
g
in
th
e
am
ateu
r
f
r
eq
u
en
cy
b
an
d
in
th
e
ex
is
tin
g
liter
atu
r
e.
T
h
e
m
a
in
co
n
tr
ib
u
tio
n
s
o
f
t
h
is
p
ap
er
a
r
e
s
u
m
m
ar
ized
b
elo
w.
−
I
n
co
n
tr
ast
to
th
e
ex
is
tin
g
m
eth
o
d
s
,
th
is
p
ap
er
in
tr
o
d
u
c
es
a
d
ev
elo
p
ed
d
etec
tio
n
an
d
class
if
icatio
n
f
r
am
ewo
r
k
,
wh
ich
co
m
b
in
es
th
e
p
er
f
o
r
m
a
n
ce
o
f
E
D
an
d
d
em
o
d
u
lated
wav
ef
o
r
m
class
if
icatio
n
f
o
r
test
s
tatis
t
ic
d
esig
n
an
d
u
tili
ze
s
a
th
r
esh
o
ld
an
d
wav
ef
o
r
m
f
ea
tu
r
e
-
b
ased
m
ec
h
a
n
is
m
f
o
r
r
ea
l
-
tim
e
d
etec
tio
n
.
−
Un
d
er
th
e
E
DW
C
f
r
am
ewo
r
k
,
th
is
p
ap
er
p
r
o
p
o
s
es
s
u
p
er
v
is
ed
lear
n
in
g
ap
p
r
o
ac
h
e
s
s
u
ch
as
th
e
class
if
icatio
n
tr
ee
(
C
T
R
)
,
d
is
cr
im
in
an
t
an
aly
s
is
(
DC
A)
,
n
aiv
e
b
a
y
es
class
if
ier
(
NB
C
)
,
$
k
$
-
n
ea
r
est
n
eig
h
b
o
u
r
s
(
KNN)
,
an
d
s
u
p
p
o
r
t v
ec
to
r
m
ac
h
in
e
(
SVM)
alg
o
r
ith
m
s
.
−
T
h
is
p
ap
er
co
n
d
u
cts
ex
ten
s
iv
e
ex
p
er
im
en
ts
u
s
in
g
r
ea
l
ca
p
tu
r
ed
s
am
p
les.
T
h
e
r
esu
lts
v
er
if
y
th
e
ef
f
ici
en
cy
o
f
th
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
in
t
er
m
s
o
f
its
d
etec
tio
n
p
er
f
o
r
m
a
n
ce
an
d
s
ca
lab
ilit
y
.
T
h
e
p
er
f
o
r
m
an
ce
o
f
ea
ch
class
if
icatio
n
tech
n
iq
u
e
is
ev
a
lu
ated
in
ter
m
s
o
f
t
h
e
tr
ai
n
in
g
tim
e
an
d
t
h
e
r
ec
eiv
er
o
p
er
atin
g
c
h
ar
ac
ter
is
tic
(
R
OC
)
cu
r
v
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
A
ma
teu
r
r
a
d
io
s
en
s
in
g
tech
n
i
q
u
e
u
s
in
g
a
co
mb
i
n
a
tio
n
o
f e
n
erg
y
…
(
N
a
r
a
th
ep
P
h
r
u
ksa
h
ir
a
n
)
401
T
h
e
r
est
o
f
th
is
p
a
p
er
is
o
r
g
an
ized
as
f
o
llo
ws:
th
e
s
y
s
tem
m
o
d
el
is
p
r
esen
ted
in
s
ec
t
io
n
2
.
T
h
e
E
DW
C
alg
o
r
ith
m
f
r
am
ewo
r
k
is
p
r
o
p
o
s
ed
in
s
ec
tio
n
3
.
T
h
e
ex
p
er
im
en
tal
r
esu
lts
an
d
d
is
cu
s
s
io
n
ar
e
p
r
esen
ted
in
s
ec
tio
n
4
.
Fin
ally
,
c
o
n
clu
s
io
n
s
ar
e
d
r
awn
i
n
s
ec
tio
n
5
.
2.
SYST
E
M
M
O
D
E
L
T
h
e
p
r
o
b
lem
o
f
s
p
ec
tr
u
m
s
en
s
in
g
is
to
d
eter
m
in
e
wh
eth
er
a
p
ar
ticu
lar
p
ar
t
o
f
th
e
s
p
ec
tr
u
m
is
ac
ce
s
s
ib
le
o
r
n
o
t.
T
h
er
ef
o
r
e,
we
ca
n
ex
p
r
ess
th
e
s
p
ec
tr
u
m
s
en
s
in
g
p
r
o
b
lem
as
a
b
in
ar
y
h
y
p
o
th
esis
test
in
g
p
r
o
b
lem
at
t
h
e
d
is
cr
ete
-
tim
e
in
s
tan
t
:
0
∶
(
)
=
(
)
(
1
)
1
∶
(
)
=
(
)
+
(
)
,
(
2
)
wh
er
e
h
y
p
o
th
eses
0
an
d
1
in
d
icate
th
e
ab
s
en
ce
an
d
p
r
esen
c
e
o
f
th
e
p
r
im
ar
y
s
ig
n
al,
r
esp
ec
tiv
ely
,
(
)
r
ef
er
s
to
th
e
s
ig
n
al
r
ec
eiv
ed
at
th
e
lo
ca
tio
n
o
f
th
e
C
R
s
y
s
te
m
,
(
)
is
ad
d
itiv
e
co
m
p
lex
w
h
ite
Gau
s
s
ian
n
o
is
e
with
ze
r
o
m
ea
n
a
n
d
(
)
r
ep
r
esen
t
s
a
s
ig
n
al
tr
an
s
m
itted
b
y
th
e
p
r
im
ar
y
n
o
d
e.
2
.
1
.
E
nerg
y
det
ec
t
io
n
T
h
e
en
er
g
y
d
etec
to
r
co
n
tr
ib
u
t
es
to
en
er
g
y
e
v
alu
atio
n
s
co
r
r
e
s
p
o
n
d
in
g
t
o
th
e
ab
o
v
e
b
i
n
ar
y
h
y
p
o
th
esis
.
L
et
(
)
b
e
th
e
-
th
(
=
1
,
2
,
…
,
)
s
am
p
le
o
f
(
)
.
All
th
e
s
am
p
les
ar
e
p
l
a
c
e
d
i
n
t
o
t
h
e
v
e
c
t
o
r
=
[
(
1
)
,
(
2
)
,
…
,
(
)
]
.
T
y
p
i
c
a
l
l
y
,
t
h
e
d
e
c
i
s
i
o
n
s
t
a
ti
s
ti
c
(
y
)
b
a
s
e
d
o
n
r
e
c
e
i
v
e
d
s
a
m
p
l
es
ca
n
b
e
g
iv
en
by
(
3
)
:
(
)
=
∑
|
|
2
0
≷
1
=
1
,
(
3
)
wh
er
e
is
a
p
r
ed
ef
in
e
d
d
ec
is
i
o
n
th
r
esh
o
ld
.
T
h
e
r
eliab
ilit
y
co
r
r
elate
d
with
th
e
d
ec
is
io
n
r
u
le
in
(
3
)
ca
n
b
e
ch
ar
ac
ter
ized
b
y
th
e
p
r
o
b
ab
il
ity
o
f
d
etec
tio
n
an
d
th
e
p
r
o
b
ab
ilit
y
o
f
f
alse
alar
m
.
T
h
e
f
o
r
m
e
r
is
th
e
p
r
o
b
a
b
ilit
y
o
f
e
x
p
o
s
u
r
e
o
f
th
e
p
r
im
ar
y
s
ig
n
al
wh
en
it
is
p
r
e
s
en
t
in
th
e
f
r
eq
u
e
n
cy
b
a
n
d
a
n
d
ca
n
b
e
f
o
r
m
u
lated
m
ath
em
atica
lly
as
(
4
)
.
=
Pr
(
(
y
)
>
|
1
)
.
(
4
)
T
h
e
f
alse
-
alar
m
p
r
o
b
a
b
ilit
y
r
e
p
r
esen
ts
th
e
in
co
r
r
ec
t
d
ec
is
io
n
th
at
(
)
is
p
r
esen
t
in
th
e
f
r
eq
u
e
n
cy
b
an
d
wh
en
it is
ac
tu
ally
n
o
t,
an
d
it
m
ay
b
e
wr
itten
as
(
5
)
.
=
Pr
(
(
y
)
>
|
0
)
.
(
5
)
T
h
e
d
ec
is
io
n
t
h
r
esh
o
ld
is
th
e
cr
u
cial
p
a
r
am
eter
in
(
3
)
an
d
m
u
s
t
b
e
o
p
tim
ized
f
o
r
ea
c
h
d
etec
tio
n
tech
n
iq
u
e
to
en
h
a
n
ce
its
p
e
r
f
o
r
m
an
ce
.
I
n
g
en
e
r
al,
t
h
e
d
ec
is
io
n
th
r
esh
o
ld
is
ch
o
s
en
to
m
ak
e
as
lar
g
e
an
d
as sm
all
as p
o
s
s
ib
le.
T
h
e
th
r
esh
o
ld
is
co
m
m
o
n
ly
s
et
b
ased
o
n
a
co
n
s
tan
t f
alse
-
alar
m
p
r
o
b
a
b
ilit
y
as
(
6
)
:
=
Pr
(
(
y
)
>
|
0
)
.
(
6
)
wh
er
e
is
th
e
s
tan
d
ar
d
Gau
s
s
i
an
co
m
p
lem
en
ta
r
y
cu
m
u
lativ
e
d
is
tr
ib
u
tio
n
f
u
n
ctio
n
,
n
o
ti
n
g
th
at
th
e
d
ec
is
io
n
th
r
esh
o
ld
m
u
s
t b
e
ad
ju
s
ted
b
as
ed
o
n
t
h
e
v
ar
ian
ce
o
f
t
h
e
ad
d
it
iv
e
n
o
is
e.
2
.
2
.
M
a
chine le
a
rni
ng
Ma
ch
in
e
lear
n
in
g
alg
o
r
ith
m
s
lear
n
a
tar
g
et
f
u
n
ctio
n
f
th
at
b
est
m
ap
s
in
p
u
t
v
a
r
iab
les
X
to
a
n
o
u
tp
u
t
v
ar
iab
le
Y
.
T
h
is
o
b
jectiv
e
is
ex
p
r
ess
ed
f
o
r
a
m
ac
h
in
e
lear
n
i
n
g
alg
o
r
ith
m
as
(
7
)
.
Y
=
f
(
X
)
,
(
7
)
W
ith
X
=
[
11
12
21
22
⋯
1
⋯
2
⋮
⋮
1
2
⋮
⋮
⋯
]
(
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.
12
,
No
.
1
,
Feb
r
u
ar
y
20
22
:
3
9
9
-
410
402
Y
=
[
1
2
⋮
]
,
(
9
)
W
h
er
e
is
th
e
s
am
p
le
s
ize
an
d
is
th
e
n
u
m
b
er
o
f
f
ea
tu
r
es
f
o
r
ea
ch
o
b
s
er
v
atio
n
.
E
ac
h
p
air
o
f
m
atr
ix
(
X
,
Y
)
is
ca
lled
a
tr
ain
i
n
g
s
am
p
le
b
e
ca
u
s
e
it
is
u
s
ed
to
g
u
id
e
th
e
lear
n
in
g
alg
o
r
ith
m
h
o
w
to
o
b
t
ain
th
e
p
r
ed
icto
r
f
.
T
h
er
e
ar
e
two
class
ical
d
ata
m
o
d
els
th
at
d
ep
en
d
o
n
th
e
p
r
ed
ictio
n
ty
p
e.
I
f
th
e
o
u
t
c
o
m
e
v
ar
iab
le
Y
is
q
u
an
titativ
e,
t
h
e
lear
n
in
g
p
r
o
b
lem
s
ig
n
if
ies
a
r
eg
r
ess
io
n
p
r
o
b
lem
;
if
th
e
o
u
tp
u
t
v
a
r
iab
le
Y
is
a
d
ef
in
ite
v
alu
e,
it is
a
class
if
icatio
n
p
r
o
b
lem
.
A
class
if
icatio
n
p
r
o
b
lem
is
a
k
in
d
o
f
s
u
p
e
r
v
is
ed
m
ac
h
i
n
e
le
ar
n
in
g
task
in
wh
ich
an
alg
o
r
ith
m
lear
n
s
to
class
if
y
n
ew
o
b
s
er
v
atio
n
s
f
r
o
m
ex
a
m
p
les
o
f
an
o
u
tp
u
t
v
ar
iab
le.
T
h
e
class
if
icatio
n
ef
f
i
cien
cy
o
f
m
ac
h
in
e
lear
n
in
g
m
o
d
els
d
ep
en
d
s
g
r
ea
t
ly
o
n
th
e
s
elec
tio
n
o
f
th
e
d
ataset
r
ep
r
esen
tatio
n
o
r
f
ea
tu
r
es
u
s
ed
f
o
r
tr
a
in
in
g
.
I
n
th
is
p
ap
er
,
we
u
s
e
th
e
C
T
R
,
DC
A,
NB
C
,
KNN,
an
d
SVM
alg
o
r
ith
m
s
f
o
r
tr
ain
in
g
an
d
class
if
y
in
g
d
atasets
.
2
.
3
.
Dem
o
du
la
t
ed
wa
v
ef
o
r
m
cha
ra
ct
er
is
t
ics
I
n
th
is
p
ap
er
,
we
f
o
cu
s
o
n
th
e
s
ig
n
als
o
f
am
ateu
r
r
ad
io
co
m
m
u
n
icatio
n
,
wh
ich
ar
e
b
ased
o
n
f
r
eq
u
e
n
cy
m
o
d
u
latio
n
(
FM)
.
T
h
e
r
ec
eiv
er
'
s
d
em
o
d
u
lated
s
ig
n
al
is
a
s
ig
n
al
in
th
e
a
u
d
i
b
l
e
f
r
e
q
u
e
n
c
y
b
a
n
d
o
r
v
o
i
c
e
s
i
g
n
a
l
.
T
h
e
d
e
m
o
d
u
l
a
t
e
d
w
a
v
e
c
h
a
r
a
c
t
e
r
i
s
t
i
c
s
w
i
l
l
v
a
r
y
d
e
p
e
n
d
i
n
g
o
n
t
h
e
n
a
t
u
r
e
o
f
t
h
e
s
p
e
e
c
h
o
r
v
o
i
c
e
.
T
h
e
k
e
y
v
a
r
i
a
b
l
e
s
u
s
e
d
t
o
e
x
p
r
e
s
s
t
h
e
v
a
l
u
e
s
o
f
t
h
e
c
r
i
t
i
c
a
l
s
i
g
n
a
l
s
a
r
e
d
e
s
c
r
i
p
t
i
v
e
s
t
a
t
i
s
t
i
c
s
a
n
d
s
p
e
c
t
r
a
l
m
ea
s
u
r
em
en
ts
.
2
.
3
.
1.
Descript
iv
e
s
t
a
t
is
t
ics
Descr
ip
tiv
e
s
tatis
tic
s
ar
e
u
s
ed
to
r
e
p
r
esen
t
th
e
b
asic
f
ea
tu
r
es
o
f
a
s
ig
n
al.
T
h
e
y
p
r
o
v
id
e
s
u
m
m
ar
y
ch
ar
ac
ter
is
tics
f
o
r
th
e
s
ig
n
al
s
am
p
le
an
d
th
e
m
ea
s
u
r
es
,
e
.
g
.
,
th
e
m
ax
im
u
m
elem
en
ts
o
f
an
a
r
r
ay
(
m
ax
)
,
m
in
im
u
m
elem
en
ts
o
f
an
ar
r
a
y
(
m
in
)
,
av
e
r
ag
e
o
r
m
ea
n
v
al
u
e
o
f
an
ar
r
a
y
(
m
ea
n
)
,
m
ed
ia
n
v
alu
e
o
f
an
a
r
r
ay
(
m
ed
)
,
m
a
x
im
u
m
-
to
-
m
in
im
u
m
d
if
f
er
en
ce
(
p
2
p
)
,
r
o
o
t
-
m
ea
n
-
s
q
u
ar
e
(
R
MS)
lev
el
(
r
m
s
)
,
p
ea
k
-
m
ag
n
itu
d
e
-
to
-
R
MS
r
at
io
(
p
2
r
m
s
)
,
r
o
o
t
-
s
u
m
-
of
-
s
q
u
ar
es lev
el
(
r
s
s
q
)
,
s
tan
d
ar
d
d
ev
iatio
n
(
s
td
)
,
an
d
v
a
r
ian
ce
(
v
ar
)
.
2
.
3
.
2.
Sp
ec
t
ra
l m
ea
s
urem
ent
s
Sp
ec
tr
al
m
ea
s
u
r
em
en
ts
ca
n
r
ep
r
esen
t
an
elec
tr
ical
p
r
o
p
e
r
ties
ac
co
r
d
in
g
to
its
f
r
eq
u
e
n
cy
.
E
ac
h
f
r
eq
u
e
n
cy
elem
en
t
in
cl
u
d
ed
i
n
th
e
in
p
u
t
s
ig
n
al
is
d
is
p
lay
ed
as
a
s
ig
n
al
lev
el
co
r
r
esp
o
n
d
in
g
to
th
at
f
r
eq
u
e
n
c
y
b
an
d
o
f
in
ter
est,
e.
g
.
,
t
h
e
m
ea
n
f
r
eq
u
en
cy
(
m
ea
f
)
a
n
d
m
ed
ian
f
r
eq
u
en
cy
(
m
ed
f
)
.
T
h
i
s
p
ap
er
u
s
es
b
o
th
d
escr
ip
tiv
e
s
tatis
tics
an
d
s
p
ec
tr
al
m
ea
s
u
r
em
en
t
p
ar
am
eter
s
a
s
th
e
class
if
icatio
n
d
ata
f
ea
tu
r
es.
I
n
th
e
ad
d
itio
n
al
co
n
ten
t
co
n
ce
r
n
in
g
th
e
m
o
d
el
tr
ain
in
g
,
we
d
em
o
n
s
tr
ate
th
e
f
ea
s
ib
ilit
y
an
d
co
n
tr
ib
u
tio
n
o
f
th
e
class
if
icatio
n
d
ata
f
ea
tu
r
es to
th
e
wa
v
ef
o
r
m
ch
ar
ac
ter
is
tic
class
if
icatio
n
.
3.
P
RO
P
O
SE
D
E
D
WC
A
L
G
O
RIT
H
M
T
h
e
p
r
o
ce
s
s
in
g
p
ip
elin
e
o
f
th
e
p
r
o
p
o
s
ed
E
DW
C
alg
o
r
ith
m
f
r
am
ewo
r
k
is
s
h
o
wn
in
F
i
g
u
r
e
1
.
T
h
e
p
i
p
e
l
i
n
e
c
o
n
s
i
s
t
s
o
f
d
a
t
a
a
c
q
u
i
s
i
t
i
o
n
,
d
a
t
a
p
r
e
p
r
o
c
e
s
s
i
n
g
,
m
o
d
e
l
d
e
v
e
l
o
p
m
e
n
t
,
a
n
d
c
l
a
s
s
i
f
i
c
a
t
i
o
n
a
n
d
d
e
c
i
s
i
o
n
s
tep
s
.
Fig
u
r
e
1
.
Pro
ce
s
s
in
g
p
ip
elin
e
o
f
th
e
en
e
r
g
y
d
etec
tio
n
a
n
d
w
av
ef
o
r
m
f
ea
tu
r
e
class
if
icatio
n
(
E
DW
C
)
alg
o
r
ith
m
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
A
ma
teu
r
r
a
d
io
s
en
s
in
g
tech
n
i
q
u
e
u
s
in
g
a
co
mb
i
n
a
tio
n
o
f e
n
erg
y
…
(
N
a
r
a
th
ep
P
h
r
u
ksa
h
ir
a
n
)
403
3
.
1
.
Da
t
a
a
cquis
it
io
n
I
n
th
e
p
r
esen
t
wo
r
k
,
th
e
p
e
r
f
o
r
m
a
n
ce
o
f
t
h
e
p
r
o
p
o
s
ed
E
DW
C
alg
o
r
ith
m
is
v
alid
ated
u
s
in
g
a
co
m
b
in
atio
n
o
f
Av
n
et
Z
ed
B
o
ar
d
with
th
e
an
alo
g
d
ev
ices
AD
-
FMC
O
MM
S3
-
E
B
Z
FM
C
m
o
d
u
le.
T
ab
le
1
p
r
ese
n
ts
h
ar
d
wa
r
e
s
p
ec
if
icatio
n
s
in
a
d
e
f
in
ed
r
an
g
e
o
f
R
F
s
p
ec
tr
a.
T
h
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
s
ar
e
im
p
lem
e
n
ted
with
MA
T
L
AB
R
2
0
1
9
in
a
6
4
-
b
it c
o
m
p
u
ter
with
a
co
r
e
i5
p
r
o
ce
s
s
o
r
an
d
4
GB
R
AM
.
T
ab
le
1
.
Har
d
war
e
s
p
ec
if
icatio
n
s
P
a
r
a
me
t
e
r
V
a
l
u
e
R
F
t
r
a
n
s
c
e
i
v
e
r
2
×
T
x
a
n
d
2
×
R
x
F
r
e
q
u
e
n
c
y
r
a
n
g
e
7
0
M
H
z
t
o
6
.
0
G
H
z
C
h
a
n
n
e
l
b
a
n
d
w
i
d
t
h
<
2
0
0
k
H
z
t
o
5
6
M
H
z
R
F
i
n
p
u
t
s (
p
e
a
k
p
o
w
e
r
)
2
.
5
d
B
m
O
p
e
r
a
t
i
n
g
t
e
mp
e
r
a
t
u
r
e
r
a
n
g
e
-
4
0
º
C
t
o
+
8
5
º
C
Fig
u
r
e
2
s
h
o
ws
th
e
ex
p
er
im
en
tal
s
etu
p
,
wh
er
e
FMC
OM
MS3
an
d
Z
ed
B
o
ar
d
in
ter
f
ac
e
with
th
e
s
y
s
tem
th
r
o
u
g
h
MA
T
L
AB
s
o
f
twar
e.
T
h
e
an
ten
n
a
AOR
DAG7
3
5
G
is
co
n
n
ec
ted
to
th
e
R
x
p
o
r
t
o
f
th
e
FMC
OM
M
S3
b
o
ar
d
an
d
ca
n
co
v
er
a
f
r
eq
u
e
n
cy
r
an
g
e
o
f
7
5
MH
z
to
3
GHz
.
T
h
e
r
ec
eiv
in
g
an
ten
n
a
is
lo
ca
ted
at
1
3
.
7
6
7
7
5
6
º
N,
1
0
0
.
5
3
0
5
6
9
º
E
,
an
d
th
e
h
eig
h
t i
s
ap
p
r
o
x
im
a
tely
2
0
m
eter
s
ab
o
v
e
th
e
g
r
o
u
n
d
.
Fig
u
r
e
2
.
E
x
p
er
im
e
n
tal
s
etu
p
Fo
r
o
u
r
tr
ain
in
g
d
ataset,
th
e
ex
p
er
im
en
tal
s
etu
p
r
ec
o
r
d
s
3
0
0
0
0
R
F
s
ig
n
als
ev
er
y
ten
s
ec
o
n
d
s
with
a
s
p
ec
if
ic
ca
r
r
ier
f
r
eq
u
en
c
y
.
W
e
u
s
e
r
ea
l b
r
o
ad
ca
s
tin
g
FM
r
ad
io
s
ig
n
als to
tr
ai
n
th
e
d
ev
elo
p
ed
m
o
d
el
to
class
if
y
an
d
d
is
tin
g
u
is
h
wav
ef
o
r
m
ch
a
r
ac
ter
is
tics
.
W
e
u
s
e
an
o
th
er
3
0
0
0
0
R
F si
g
n
al
d
atasets
to
te
s
t
th
e
p
er
f
o
r
m
a
n
ce
o
f
o
u
r
d
e
v
elo
p
e
d
m
ac
h
in
e
lear
n
i
n
g
alg
o
r
ith
m
s
.
Fo
r
ap
p
licatio
n
p
u
r
p
o
s
es
an
d
f
o
r
p
lan
n
in
g
th
e
u
s
e
o
f
th
e
p
u
b
lic
s
p
ec
tr
u
m
,
we
im
p
lem
en
ted
th
e
d
ev
elo
p
ed
f
r
am
ewo
r
k
to
m
ain
tain
a
o
n
e
-
wee
k
cy
cle
u
s
ag
e
s
tatis
tic
f
o
r
FM
am
ateu
r
r
ad
io
.
T
h
e
av
ailab
le
f
r
eq
u
en
cy
b
an
d
s
f
o
r
FM
am
ateu
r
r
ad
io
ac
co
r
d
in
g
to
[
3
1
]
ar
e
d
iv
id
ed
in
to
f
o
u
r
s
ec
tio
n
s
as
f
o
llo
ws:
B
an
d
1
b
etwe
en
1
4
4
.
5
1
2
5
MH
z
an
d
1
4
4
.
9
8
7
5
MH
z,
B
an
d
2
b
etwe
en
1
4
5
.
1
3
7
5
MH
z
an
d
1
4
5
.
5
3
7
5
MH
z,
B
an
d
3
b
etwe
en
1
4
6
.
2
8
7
5
MH
z
an
d
1
4
6
.
6
0
0
0
MH
z,
an
d
B
an
d
4
b
etwe
en
1
4
6
.
8
1
2
5
MH
z
an
d
1
4
7
.
0
0
0
0
MH
z.
E
ac
h
ch
an
n
el
h
as a
b
an
d
wid
th
o
f
1
2
.
5
k
Hz.
Fig
u
r
e
3
(
a)
an
d
(
b
)
illu
s
tr
ate
ex
am
p
les o
f
th
e
in
s
tan
tan
eo
u
s
s
p
ec
tr
u
m
an
d
th
e
s
p
ec
tr
o
g
r
am
o
f
th
e
r
ea
l
FM
r
ad
io
s
ig
n
al,
r
esp
ec
tiv
ely
,
v
er
s
u
s
f
r
eq
u
en
cy
.
As
s
h
o
wn
in
Fig
u
r
e
3
(
a)
,
th
e
s
p
ec
tr
u
m
o
f
th
e
R
F
s
ig
n
al
v
ar
ies
d
ep
en
d
in
g
o
n
th
e
m
o
d
u
lated
v
o
ice
s
ig
n
al.
Fig
u
r
e
3
(
b
)
p
r
esen
ts
th
e
s
p
ec
tr
o
g
r
am
o
f
th
e
s
am
e
R
F
s
ig
n
al
wit
h
a
tim
e
h
is
to
r
y
o
f
1
0
0
m
s
.
3.
2
.
Da
t
a
prepro
ce
s
s
ing
T
h
e
an
alo
g
u
e
R
F
s
ig
n
als
at
th
e
s
p
ec
if
ied
f
r
eq
u
en
cy
r
an
g
e
ar
e
co
n
v
er
ted
to
th
e
in
ter
m
ed
iate
f
r
eq
u
en
cy
(
I
F)
an
d
s
to
r
ed
f
o
r
class
if
icatio
n
p
r
o
ce
s
s
in
g
.
T
h
e
p
o
ten
tial p
r
ed
icto
r
v
ar
iab
les u
s
ed
in
th
is
s
tu
d
y
ar
e
th
e
d
escr
ip
tiv
e
s
tatis
tics
an
d
s
p
ec
tr
al
m
ea
s
u
r
em
en
t
s
o
f
th
e
FM
d
em
o
d
u
lated
s
ig
n
al
o
f
ea
ch
ch
an
n
el,
as
d
escr
ib
ed
in
s
ec
tio
n
2
.
3
.
Fig
u
r
e
4
s
h
o
ws
a
co
m
p
ar
is
o
n
o
f
th
e
wav
ef
o
r
m
an
d
am
p
litu
d
e
o
b
tain
ed
f
r
o
m
th
e
d
em
o
d
u
latio
n
p
r
o
ce
s
s
in
g
o
f
o
n
e
d
ataset.
T
h
e
d
iag
r
am
clea
r
ly
s
h
o
ws
th
e
wav
ef
o
r
m
ch
ar
ac
ter
is
tics
o
f
ea
ch
s
ig
n
al
ty
p
e.
T
h
e
s
o
lid
lin
e
r
ep
r
esen
ts
th
e
wav
ef
o
r
m
o
f
th
e
v
o
ice
o
r
s
p
ee
ch
s
ig
n
al
o
f
FM
r
ad
io
b
r
o
ad
ca
s
tin
g
.
T
h
e
d
ash
ed
lin
e
d
ep
icts
th
e
wav
ef
o
r
m
o
f
th
e
n
o
is
e
s
ig
n
al.
T
h
e
wav
ef
o
r
m
ch
ar
ac
ter
is
tics
ar
e
d
if
f
er
en
t,
an
d
we
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.
12
,
No
.
1
,
Feb
r
u
ar
y
20
22
:
3
9
9
-
410
404
ca
n
u
s
e
th
e
wav
ef
o
r
m
p
r
o
p
er
ties
in
ea
ch
d
ataset
as
v
ar
iab
les
in
p
r
o
ce
s
s
in
g
th
e
wav
ef
o
r
m
r
elatio
n
s
h
ip
s
an
d
s
ig
n
al
ty
p
es.
(
a)
(
b
)
Fig
u
r
e
3
.
E
x
am
p
le
f
r
o
m
t
h
e
R
F si
g
n
al
d
at
aset; (
a)
s
p
ec
tr
u
m
o
f
R
F si
g
n
al,
(
b
)
s
p
ec
tr
o
g
r
am
o
f
R
F si
g
n
al
Fig
u
r
e
4
.
E
x
am
p
le
o
f
d
em
o
d
u
l
ated
wav
ef
o
r
m
3
.
3
.
M
o
del dev
elo
pm
ent
T
h
e
p
u
r
p
o
s
e
o
f
m
ac
h
in
e
lear
n
in
g
is
to
d
ev
elo
p
a
m
o
d
el
t
h
at
m
ak
es
class
if
icatio
n
s
b
ased
o
n
in
p
u
t
d
ata
o
r
f
ea
tu
r
es.
A
s
u
p
er
v
is
ed
lear
n
in
g
alg
o
r
ith
m
u
s
es
a
ce
r
tifie
d
s
et
o
f
in
p
u
t
d
ata
an
d
k
n
o
wn
co
r
r
esp
o
n
d
in
g
o
u
tp
u
ts
an
d
in
s
tr
u
cts
a
m
o
d
el
to
cr
ea
te
lo
g
ical
class
if
icatio
n
s
in
r
esp
o
n
s
e
to
n
ew
d
at
a,
as
d
escr
ib
ed
in
alg
o
r
ith
m
1
.
T
h
e
lear
n
in
g
p
r
o
ce
s
s
b
eg
in
s
with
an
in
p
u
t
d
ata
m
atr
ix
X
.
E
ac
h
r
o
w
o
f
X
r
e
p
r
esen
ts
o
n
e
o
b
s
er
v
atio
n
o
r
m
ea
s
u
r
em
en
t.
E
ac
h
co
lu
m
n
o
f
X
d
en
o
tes
o
n
e
f
ea
tu
r
e
o
r
p
r
e
d
icto
r
.
A
f
ter
m
o
d
el
f
itti
n
g
,
we
o
b
tain
s
ev
er
al
m
o
d
els
d
ep
e
n
d
i
n
g
o
n
th
e
alg
o
r
ith
m
s
.
T
h
ese
m
o
d
els
will
b
e
u
s
ed
to
class
if
y
th
e
o
u
tp
u
t.
I
n
th
is
ca
s
e,
we
h
av
e
two
ca
teg
o
r
ies:
v
o
ice
o
r
s
p
ee
c
h
wav
ef
o
r
m
s
an
d
n
o
is
e
wav
ef
o
r
m
s
.
3
.
4
.
Cla
s
s
if
ica
t
io
n a
nd
decisi
o
n
A
m
ea
s
u
r
e
o
f
en
e
r
g
y
le
v
el
will
in
d
icate
if
a
s
ig
n
al
is
tr
an
s
m
itted
in
th
at
f
r
eq
u
en
cy
b
an
d
o
r
n
o
t.
T
h
e
ap
p
licatio
n
o
f
class
ic
E
D
tec
h
n
iq
u
es
ca
n
p
r
o
v
id
e
o
n
ly
0
o
r
1
s
tatu
s
,
as
p
r
esen
ted
in
(
1
)
.
Ho
wev
er
,
in
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
A
ma
teu
r
r
a
d
io
s
en
s
in
g
tech
n
i
q
u
e
u
s
in
g
a
co
mb
i
n
a
tio
n
o
f e
n
erg
y
…
(
N
a
r
a
th
ep
P
h
r
u
ksa
h
ir
a
n
)
405
p
r
ac
tical
ap
p
licatio
n
s
with
r
a
d
io
am
ateu
r
s
,
th
er
e
is
also
a
f
o
r
m
o
f
n
o
is
e
tr
an
s
m
is
s
io
n
.
W
h
ich
th
e
n
o
is
e
is
s
en
t
o
u
t,
th
e
r
e
will
b
e
n
o
au
d
io
o
r
s
p
ee
ch
s
ig
n
al.
Fo
r
ex
am
p
le,
p
r
ess
an
d
h
o
ld
th
e
s
u
b
m
it
k
e
y
.
T
h
is
m
eth
o
d
o
f
an
aly
s
is
,
th
er
ef
o
r
e,
f
u
r
th
er
class
if
ies
th
e
f
o
r
m
an
d
n
at
u
r
e
o
f
th
e
m
ea
s
u
r
ed
s
ig
n
al.
T
h
e
d
ev
elo
p
e
d
E
DW
C
alg
o
r
ith
m
will b
e
b
e
n
ef
icial
in
f
u
r
th
er
ap
p
licatio
n
s
f
o
r
s
ec
u
r
i
ty
ag
en
cies.
T
h
e
p
r
o
ce
s
s
o
f
class
if
y
in
g
an
d
m
ak
in
g
d
ec
is
io
n
s
is
a
co
m
b
in
atio
n
o
f
t
h
e
ca
p
ab
ilit
ies
o
f
E
D
an
d
th
e
an
aly
s
is
o
f
v
o
ice
s
ig
n
als
u
s
in
g
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
s
,
as
d
escr
ib
ed
in
alg
o
r
ith
m
2
.
Acc
o
r
d
in
g
to
th
e
p
r
ep
r
o
g
r
am
m
e
d
p
r
o
ce
s
s
in
g
s
t
ep
s
,
th
e
d
e
v
elo
p
e
d
b
o
ar
d
ca
p
t
u
r
es
th
e
R
F
s
ig
n
al
in
r
ea
l
tim
e
.
T
h
en
,
it
f
ilter
s
th
e
wid
eb
an
d
s
ig
n
al
to
th
e
s
u
b
b
an
d
ac
co
r
d
in
g
to
th
e
r
esp
ec
tiv
e
ch
an
n
el
an
d
b
a
n
d
wid
th
s
ize.
Nex
t,
all
d
escr
ip
tiv
e
s
tatis
t
ics an
d
s
p
ec
tr
al
m
ea
s
u
r
em
en
ts
ar
e
ca
lcu
lated
to
p
r
ep
ar
e
th
e
in
p
u
t
r
o
w
o
f
X
.
Alg
o
r
ith
m
1
.
Mo
d
el
d
ev
elo
p
m
en
t
Input:
Wideband RF sample data
Output:
Classification models (CTR, DCA, NBC, KNN, SVM)
Initialization:
Training dataset acquisition
Loop
Process:
for
i = 1 to number of channels
do
Frequency band selection using bandpass filter
Calculate features of each frequency band
Preprocessing input data matrix
X
for
n=1 to number of machine learning models do
Train models
end for
Save model
end for
Test performance of each model
Alg
o
r
ith
m
2
.
C
lass
if
icatio
n
an
d
d
ec
is
io
n
Input:
Wideband RF sample data
Output:
Decision result
In
itialization:
Test data acquisition
y(t)
Threshold estimation λ
Load classification models (CTR, DCA, NBC, KNN, SVM)
Loop Process:
for
i = 1 to number of channels
do
Frequency band selection using bandpass filter
Calculate features of each frequency band
Preprocessing input data matrix
X
for
n=1 to number of machine learning models
do
Energy detection
T
(
y
)
Waveform classification (WC)
Decision based on EDWC algorithm
if
(
T
(
y
) < λ) and (WC == Noise)
then
Decision case
C
0
else
if
(
T
(
y
)
≷
λ) and (WC == Voice)
then
Decision case
C
1
else if
(
T
(
y
) > λ) and (WC == Noise)
then
Decision case
C
2
end if
end for
end for
Count
classification and decision results
As
m
en
tio
n
ed
ab
o
v
e,
th
e
p
o
wer
s
p
litt
in
g
m
eth
o
d
o
n
ly
p
r
o
v
id
es
in
f
o
r
m
atio
n
if
th
er
e
is
a
s
ig
n
al
in
th
e
o
b
s
er
v
ed
f
r
eq
u
en
cy
ch
an
n
el
o
r
n
o
t.
Fu
r
th
er
m
o
r
e,
o
n
ce
it
is
id
en
tifie
d
th
at
s
o
m
e
s
ig
n
al
p
o
wer
is
d
etec
tab
le,
it
is
th
e
p
r
o
ce
s
s
o
f
an
aly
s
is
to
class
if
y
it
as
a
s
p
ee
ch
s
ig
n
al
o
r
n
o
is
e.
T
h
e
alg
o
r
ith
m
is
class
if
ied
in
to
th
r
ee
s
u
b
g
r
o
u
p
s
,
C
0
,
C
1
,
an
d
C
2
.
T
h
e
class
if
icatio
n
m
o
d
els
p
r
o
ce
s
s
th
e
in
p
u
t
d
ata
an
d
class
if
y
th
e
wav
ef
o
r
m
f
ea
tu
r
es
in
to
two
g
r
o
u
p
s
:
(
W
C
=
Vo
ice)
an
d
(
W
C
=
N
o
is
e)
.
T
h
e
E
D
m
o
d
u
le
co
m
p
ar
es
th
e
en
er
g
y
lev
el
with
th
e
p
r
ed
ef
in
ed
th
r
esh
o
ld
an
d
g
iv
es
th
e
co
m
p
ar
is
o
n
r
esu
lts
:
0
o
r
1
.
I
n
th
e
d
ec
is
io
n
s
tep
,
we
d
ef
in
e
th
e
d
ec
is
io
n
o
u
tp
u
t
b
ased
o
n
wav
ef
o
r
m
class
if
icatio
n
an
d
E
D
as f
o
llo
ws:
−
C
0
wh
en
(
T
(
y
)
<
λ
,
0
)
an
d
(
W
C
=N
o
is
e)
:
I
n
th
is
ca
s
e,
th
e
s
ig
n
al
lev
el
is
wea
k
er
th
an
th
e
r
eg
u
lar
r
ef
er
en
ce
r
ate,
an
d
th
e
r
esu
ltin
g
wav
ef
o
r
m
ch
ar
ac
ter
is
tics
ar
e
g
en
er
ally
s
im
ilar
to
th
at
o
f
a
n
o
is
e
s
ig
n
al.
−
C
1
wh
en
(
T
(
y
)
≷
λ
,
0
o
r
1
)
an
d
(
W
C
=V
o
ice)
:
Su
p
p
o
s
e
th
e
m
ea
s
u
r
ed
en
er
g
y
lev
el
is
s
m
aller
th
an
th
e
s
p
ec
if
ied
th
r
esh
o
ld
lev
el,
b
u
t
th
e
wav
ef
o
r
m
ch
ar
ac
ter
is
tics
ar
e
s
im
ilar
to
v
o
ice
s
ig
n
als.
I
n
th
is
ca
s
e,
th
e
d
ec
is
io
n
alg
o
r
ith
m
will
class
if
y
th
e
d
etec
ted
s
ig
n
al
in
to
th
e
v
o
ice
g
r
o
u
p
.
T
h
er
e
is
a
p
o
s
s
ib
ilit
y
th
at
th
e
tr
an
s
m
itter
is
at
a
g
r
ea
t
d
is
tan
ce
,
ca
u
s
in
g
th
e
s
ig
n
al
in
ten
s
ity
to
d
ec
r
ea
s
e.
Ho
wev
er
,
th
e
wav
ef
o
r
m
ch
ar
ac
ter
is
tics
in
d
icate
th
at
it m
ay
b
e
a
v
o
ice
s
ig
n
al
em
p
lo
y
ed
f
o
r
r
ea
l c
o
m
m
u
n
icatio
n
.
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.
12
,
No
.
1
,
Feb
r
u
ar
y
20
22
:
3
9
9
-
410
406
−
C
2
wh
en
(
T
(
y
)
>
λ
,
1
)
an
d
(
W
C
=N
o
is
e)
:
I
n
p
u
b
lic
am
ateu
r
r
ad
io
u
s
e,
th
er
e
m
ay
b
e
ac
cid
en
tal
o
r
in
ten
tio
n
al
in
ter
f
er
en
ce
b
y
th
e
u
s
er
.
Alter
n
ativ
ely
,
th
e
u
s
er
m
ay
tr
an
s
m
it
a
ca
r
r
ier
wav
e
s
ig
n
al
with
o
u
t
m
o
d
u
latio
n
with
a
s
p
ee
ch
s
ig
n
al.
I
n
th
is
r
esear
ch
,
a
d
ec
is
io
n
m
ak
in
g
m
o
d
el
was
d
esig
n
ed
to
tak
e
th
e
ac
tu
al
s
itu
atio
n
in
to
ac
co
u
n
t.
I
n
o
th
er
wo
r
d
s
,
th
e
s
ig
n
al
lev
el
m
ay
b
e
g
r
ea
ter
th
an
th
e
th
r
esh
o
ld
d
u
e
to
th
e
tr
an
s
m
itted
ca
r
r
ier
f
r
eq
u
en
cy
.
Ho
wev
er
,
th
e
wav
ef
o
r
m
d
o
es
n
o
t
h
av
e
th
e
ch
ar
ac
ter
is
tics
o
f
a
v
o
ice
s
ig
n
al
as d
ef
in
ed
in
th
e
m
ac
h
in
e
lear
n
in
g
m
o
d
el.
4.
RE
SU
L
T
S
A
ND
D
I
SCU
SS
I
O
N
I
n
th
is
s
ec
tio
n
,
we
co
n
d
u
ct
ex
ten
s
iv
e
s
im
u
latio
n
s
to
v
er
if
y
t
h
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
p
r
o
p
o
s
ed
E
DW
C
alg
o
r
ith
m
.
I
n
p
ar
ticu
lar
,
we
e
v
alu
ate
th
e
tr
ain
in
g
p
e
r
f
o
r
m
a
n
ce
o
f
th
e
class
if
icatio
n
s
ch
em
e
in
s
ec
tio
n
4
.
1
.
T
h
en
,
we
d
em
o
n
s
tr
ate
th
e
test
in
g
p
er
f
o
r
m
an
ce
a
n
d
th
e
d
etec
tio
n
p
r
o
b
ab
ilit
y
o
f
t
h
e
d
if
f
er
en
t
alg
o
r
ith
m
s
i
n
s
ec
tio
n
4
.
2
.
Fin
ally
,
we
ass
e
s
s
th
e
p
er
f
o
r
m
an
ce
o
f
r
ea
l
-
ti
m
e
o
b
s
er
v
atio
n
ap
p
licatio
n
s
u
s
in
g
r
ea
l
am
ateu
r
p
u
b
lic
r
ad
i
o
in
s
ec
tio
n
4
.
3
.
4
.
1
.
T
ra
ini
ng
da
t
a
s
et
4
.
1
.
1.
Co
re
lla
t
io
n c
o
e
f
f
icient
o
f
f
ea
t
ures
B
ased
o
n
in
v
esti
g
atin
g
Fig
u
r
e
5
,
we
f
in
d
a
s
ig
n
if
ican
t
co
r
r
elatio
n
b
etwe
en
in
d
iv
id
u
al
wav
ef
o
r
m
ch
ar
ac
ter
is
tics
.
Mo
s
t
o
f
th
e
co
r
r
elatio
n
co
ef
f
icien
ts
o
f
th
e
s
elec
ted
f
ea
tu
r
es
ar
e
h
ig
h
er
th
an
0
.
3
;
i.e
.
,
th
er
e
is
a
r
o
b
u
s
t
co
r
r
elatio
n
.
T
h
er
ef
o
r
e,
u
s
in
g
th
e
wav
ef
o
r
m
p
r
o
p
er
ties
as
v
ar
iab
les
in
m
ac
h
in
e
lear
n
in
g
p
r
o
ce
s
s
in
g
ca
n
lead
to
r
eliab
le
an
d
p
r
ac
tical
r
esu
lts
.
4
.
1
.
2.
T
ra
ini
ng
du
ra
t
io
n o
f
diff
er
ent
a
lg
o
rit
h
m
s
T
h
e
av
er
ag
e
tr
ain
in
g
d
u
r
atio
n
s
f
o
r
th
e
d
if
f
er
en
t
class
if
ier
s
ac
co
r
d
in
g
to
th
e
s
ize
o
f
th
e
tr
ain
in
g
fe
atu
r
e
v
ec
to
r
s
ar
e
d
is
p
lay
ed
in
T
ab
le
2
.
T
h
e
n
ea
r
est
n
eig
h
b
o
r
alg
o
r
ith
m
d
is
p
lay
s
a
co
m
p
ar
ativ
ely
h
ig
h
tr
ain
in
g
d
u
r
atio
n
(
5
.
0
9
2
6
s
ec
o
n
d
s
f
o
r
3
0
0
0
0
s
am
p
les)
am
o
n
g
all
th
e
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
s
.
T
h
e
alg
o
r
ith
m
th
at
u
s
ed
th
e
least
tim
e
to
tr
ain
th
e
d
ataset
in
th
is
ex
p
er
im
en
t
was
d
is
cr
im
in
an
t
an
aly
s
is
,
with
0
.
3
0
2
6
s
ec
o
n
d
s
f
o
r
3
0
0
0
0
s
am
p
les.
Fig
u
r
e
5
.
Hea
t m
a
p
o
f
th
e
in
te
r
r
elate
d
f
ea
tu
r
es
T
ab
le
2
.
Av
e
r
ag
e
tr
ain
in
g
d
u
r
atio
n
f
o
r
d
if
f
er
e
n
t m
ac
h
in
e
lea
r
n
in
g
alg
o
r
ith
m
s
[
s
ec
o
n
d
s
]
A
l
g
o
r
i
t
h
ms
N
u
mb
e
r
o
f
Tr
a
i
n
i
n
g
S
a
m
p
l
e
s
6
0
0
0
1
0
8
0
0
1
5
2
0
0
2
0
4
0
0
2
5
2
0
0
3
0
0
0
0
C
TR
0
.
1
2
7
6
0
.
1
5
9
4
0
.
1
8
9
9
0
.
2
2
1
8
0
.
3
4
5
0
0
.
4
3
8
7
D
C
A
0
.
1
4
0
4
0
.
1
6
7
9
0
.
2
1
1
1
0
.
2
3
8
5
0
.
2
7
7
0
0
.
3
0
2
6
N
B
C
0
.
1
6
0
5
0
.
1
9
9
9
0
.
2
4
3
4
0
.
2
6
3
6
0
.
3
0
2
1
0
.
3
4
0
7
K
N
N
0
.
3
1
8
1
0
.
7
9
6
4
1
.
5
1
4
0
2
.
4
6
1
7
3
.
6
3
0
6
5
.
0
9
2
6
S
V
N
0
.
4
8
8
6
1
.
2
9
2
2
2
.
0
5
6
5
2
.
1
2
3
8
2
.
7
5
5
5
3
.
4
6
7
0
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
A
ma
teu
r
r
a
d
io
s
en
s
in
g
tech
n
i
q
u
e
u
s
in
g
a
co
mb
i
n
a
tio
n
o
f e
n
erg
y
…
(
N
a
r
a
th
ep
P
h
r
u
ksa
h
ir
a
n
)
407
4
.
2
.
T
est
da
t
a
s
et
4
.
2
.
1.
Cla
s
s
if
ica
t
io
n t
im
e
o
f
diff
er
ent
a
lg
o
rit
hm
s
T
ab
le
3
p
r
esen
ts
th
e
tim
e
n
ee
d
ed
f
o
r
class
if
icatio
n
o
f
th
e
wav
ef
o
r
m
ch
ar
ac
ter
s
f
o
r
d
if
f
er
en
t
class
if
ier
s
b
ased
o
n
3
0
0
0
0
test
s
am
p
les.
T
h
e
d
if
f
er
en
t
n
u
m
b
er
s
o
f
s
am
p
les
u
s
ed
in
th
e
esti
m
atio
n
p
r
o
ce
s
s
ar
e
p
r
esen
ted
in
th
e
“n
u
m
b
er
o
f
class
if
icatio
n
s
am
p
les”
co
lu
m
n
,
f
r
o
m
6
0
0
0
to
3
0
0
0
0
d
atasets
.
I
n
th
e
p
r
o
ce
s
s
in
g
u
s
ed
to
class
if
y
th
e
s
ig
n
al
wav
ef
o
r
m
,
th
e
p
r
o
p
o
s
ed
E
DW
C
alg
o
r
ith
m
with
d
ec
is
io
n
tr
ee
s
ca
n
o
b
tain
th
e
m
o
s
t
d
esira
b
le
class
if
icatio
n
tim
e
(
0
.
0
1
2
5
s
ec
o
n
d
s
f
o
r
3
0
0
0
0
s
am
p
les),
f
o
llo
wed
b
y
th
e
n
aiv
e
B
ay
es
alg
o
r
ith
m
(
0
.
0
1
6
8
s
ec
o
n
d
s
f
o
r
3
0
0
0
0
s
am
p
les)
an
d
d
is
cr
im
in
an
t
an
aly
s
is
(
0
.
0
1
9
6
s
ec
o
n
d
s
f
o
r
3
0
0
0
0
s
am
p
les).
T
h
ey
also
h
av
e
co
m
p
ar
ab
le
ac
cu
r
ac
y
r
ates.
T
ab
le
3
s
h
o
ws
th
at
th
e
p
r
o
p
o
s
ed
E
DW
C
alg
o
r
ith
m
u
s
in
g
an
SVM
o
b
tain
s
th
e
h
ig
h
est
ac
cu
r
ac
y
o
f
8
3
.
6
6
8
5
%;
th
e
o
th
er
alg
o
r
ith
m
s
also
s
h
o
w
a
r
elativ
ely
g
o
o
d
p
er
f
o
r
m
an
ce
o
f
ap
p
r
o
x
im
ately
8
3
.
6
%.
T
ab
le
3
.
Acc
u
r
ac
y
an
d
av
er
a
g
e
class
if
icatio
n
tim
e
f
o
r
d
if
f
e
r
en
t m
ac
h
in
e
lear
n
in
g
al
g
o
r
ith
m
s
[
s
ec
o
n
d
s
]
A
l
g
o
r
i
t
h
ms
A
c
c
u
r
a
c
y
%
N
u
mb
e
r
o
f
c
l
a
ss
i
f
i
c
a
t
i
o
n
s
a
mp
l
e
s
6
0
0
0
1
0
8
0
0
1
5
2
0
0
2
0
4
0
0
2
5
2
0
0
3
0
0
0
0
C
TR
8
3
.
6
8
4
5
0
.
0
0
6
0
0
.
0
0
7
6
0
.
0
0
9
3
0
.
0
1
0
3
0
.
0
1
1
6
0
.
0
1
2
5
D
C
A
8
3
.
6
0
7
9
0
.
0
0
6
7
0
.
0
1
0
2
0
.
0
1
2
6
0
.
0
1
5
5
0
.
0
1
7
2
0
.
0
1
9
6
N
B
C
8
3
.
6
6
5
3
0
.
0
0
7
2
0
.
0
1
0
6
0
.
0
1
2
6
0
.
0
1
3
8
0
.
0
1
5
6
0
.
0
1
6
8
K
N
N
8
3
.
6
2
3
8
0
.
6
3
7
7
1
.
1
4
3
4
1
.
6
4
4
7
2
.
1
4
7
2
2
.
6
5
1
6
3
.
1
5
3
6
S
V
N
8
3
.
6
6
8
5
0
.
0
0
9
1
0
.
0
1
2
9
0
.
0
1
6
1
0
.
0
1
9
6
0
.
0
2
3
0
0
.
0
2
6
0
4
.
2
.
2.
Det
ec
t
io
n pro
ba
bil
it
y
o
f
diff
er
ent
a
lg
o
rit
hm
s
T
h
e
R
OC
cu
r
v
e
is
a
m
etr
ic
ad
o
p
ted
to
ex
am
in
e
th
e
p
r
o
p
er
ties
o
f
class
if
ier
s
.
Fig
u
r
e
6
an
aly
ze
s
th
e
p
er
f
o
r
m
an
ce
o
f
in
d
iv
id
u
al
p
r
o
p
o
s
ed
E
DW
C
s
ch
em
es
in
ter
m
s
o
f
th
e
R
OC
cu
r
v
es.
T
h
e
tr
u
e
p
o
s
itiv
e
r
atio
(
T
PR
)
,
o
n
th
e
y
-
ax
is
,
in
d
icate
s
th
e
n
u
m
b
er
o
f
o
u
tp
u
ts
in
w
h
ich
th
e
ac
tu
al
an
d
p
r
ed
icted
class
es
ar
e
id
en
tical.
T
h
e
x
-
ax
is
r
ep
r
esen
ts
th
e
f
alse
p
o
s
itiv
e
r
atio
(
FP
R
)
,
wh
ich
is
th
e
r
atio
o
f
ca
s
es in
wh
ich
th
e
r
ea
l a
n
d
p
r
ed
icted
lab
els
ar
e
d
if
f
er
en
t.
Fro
m
th
e
co
m
p
ar
is
o
n
o
f
th
e
cu
r
v
es,
we
ca
n
s
ee
th
at
th
e
KNN
class
if
i
er
h
as
th
e
h
ig
h
est
p
r
ed
ictio
n
ef
f
icien
cy
,
f
o
llo
wed
b
y
th
e
C
T
R
an
d
NB
C
class
if
icatio
n
alg
o
r
ith
m
s
.
Ho
wev
er
,
th
e
d
if
f
er
en
ce
is
n
o
t
v
er
y
g
r
ea
t.
I
t
h
as
b
ee
n
s
h
o
wn
th
at
co
m
b
in
in
g
d
escr
ip
tiv
e
s
tatis
tics
an
d
s
p
ec
tr
al
m
ea
s
u
r
em
en
ts
in
m
o
d
el
d
ev
elo
p
m
en
t c
an
h
av
e
a
s
i
g
n
if
ican
t e
f
f
ec
t o
n
wav
ef
o
r
m
class
if
icatio
n
.
Fig
u
r
e
6
.
R
ec
eiv
er
o
p
er
atin
g
c
h
ar
ac
ter
is
tic
cu
r
v
e
o
f
th
e
p
r
o
p
o
s
ed
class
if
ier
s
4.
3
.
Rea
l
-
t
im
e
o
bs
er
v
a
t
io
n
I
n
th
e
r
ea
l
ap
p
licatio
n
ex
p
er
im
en
t,
th
e
ex
p
er
im
en
tal
s
etu
p
was
p
u
t
in
p
lace
an
d
ca
p
tu
r
ed
th
e
R
F
s
ig
n
als o
f
p
u
b
lic
am
ateu
r
r
ad
io
f
o
r
a
wee
k
(
1
1
-
1
7
Octo
b
er
2
0
2
0
)
in
a
p
ar
ticu
lar
b
an
d
.
4.
3
.
1
.
O
bs
er
v
ed
s
ig
na
l le
v
el
Fig
u
r
e
7
p
r
esen
ts
th
e
co
m
p
ar
is
o
n
p
lo
ts
o
f
th
e
en
er
g
y
lev
el
o
f
ea
ch
f
r
eq
u
en
cy
b
an
d
.
T
h
e
x
-
ax
is
in
d
icate
s
th
e
n
u
m
b
er
o
f
s
am
p
les,
an
d
th
e
y
-
ax
is
r
ep
r
esen
ts
th
e
s
ize
o
f
th
e
n
o
r
m
alize
d
u
p
p
er
en
v
elo
p
e
o
f
ea
ch
s
ig
n
al
s
am
p
le.
E
ac
h
f
r
eq
u
en
cy
b
an
d
h
as a
d
if
f
er
en
t e
n
er
g
y
lev
el
f
o
r
ea
ch
ca
p
tu
r
ed
R
F si
g
n
al
o
v
er
tim
e,
wh
ich
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.
12
,
No
.
1
,
Feb
r
u
ar
y
20
22
:
3
9
9
-
410
408
s
h
o
ws
h
o
w
th
e
u
s
ag
e
o
f
th
e
s
ig
n
als
v
ar
ies
in
th
e
o
b
s
er
v
atio
n
p
er
io
d
.
T
h
ese
b
an
d
s
ar
e
an
ess
en
tial
p
ar
t
o
f
d
eter
m
in
in
g
th
e
th
r
esh
o
ld
lev
el
an
d
th
e
lev
el
o
f
n
o
is
e
th
at
o
cc
u
r
s
in
ea
ch
f
r
eq
u
en
cy
r
an
g
e
as
well.
Fr
o
m
th
e
co
m
p
ar
is
o
n
o
f
th
e
g
r
ap
h
s
,
we
ca
n
s
ee
th
at
th
e
f
r
eq
u
en
cy
r
an
g
e
o
f
b
an
d
o
n
e
is
u
s
ed
th
e
m
o
s
t,
an
d
th
e
least
ac
tiv
e
f
r
eq
u
en
cy
r
an
g
e
is
b
an
d
f
o
u
r
.
Fig
u
r
e
7
.
No
r
m
alize
d
u
p
p
er
e
n
v
elo
p
e
o
f
ea
ch
s
ig
n
al
s
am
p
le
4.
3.
2
.
Co
un
t
ing
a
nd
decisi
o
n
m
a
k
ing
T
ab
le
4
s
h
o
ws
th
e
r
esu
lts
o
b
ta
in
ed
f
r
o
m
t
h
e
ex
p
er
im
en
ts
to
p
r
o
ce
s
s
th
e
ac
tu
al
p
u
b
lic
am
at
eu
r
s
ig
n
al
with
th
e
d
e
v
elo
p
ed
E
DW
C
alg
o
r
ith
m
.
T
h
e
r
esu
lts
ar
e
d
iv
id
ed
in
to
f
o
u
r
m
ain
g
r
o
u
p
s
ac
co
r
d
in
g
to
th
e
f
r
eq
u
e
n
cy
r
an
g
e
o
f
th
e
d
etec
ted
s
ig
n
al
an
d
th
e
m
ac
h
i
n
e
lear
n
in
g
u
s
ed
f
o
r
p
r
o
ce
s
s
in
g
to
class
if
y
th
e
wav
ef
o
r
m
ch
ar
ac
ter
is
tics
.
I
n
ad
d
itio
n
,
th
e
d
is
p
lay
is
d
iv
id
ed
i
n
to
f
iv
e
g
r
o
u
p
s
:
0
,
1
,
0
,
1
,
an
d
2
.
T
ab
le
4
.
C
o
u
n
tin
g
an
d
d
ec
is
io
n
m
ak
in
g
f
o
r
r
ea
l
-
tim
e
o
b
s
er
v
atio
n
s
B
a
n
d
A
l
g
o
r
i
t
h
ms
C
a
t
e
g
o
r
y
H
0
H
1
C
0
C
1
C
2
1
C
TR
3
1
0
5
7
2
2
6
3
8
8
3
1
0
5
7
2
2
5
3
0
3
1
0
8
5
D
C
A
3
8
6
8
2
2
5
2
0
N
B
C
4
1
7
1
2
2
2
1
7
K
N
N
2
8
2
1
2
3
5
6
7
S
V
N
1
0
2
2
6
2
8
6
2
C
TR
2
5
0
1
2
9
3
4
9
9
1
2
5
0
1
2
9
3
2
0
2
0
2
9
7
1
D
C
A
2
3
9
4
3
2
5
9
7
N
B
C
3
5
7
2
3
1
4
1
9
K
N
N
1
8
4
1
3
3
1
5
0
S
V
N
6
3
4
9
8
5
3
C
TR
1
9
3
0
2
6
3
1
6
1
4
1
9
3
0
2
6
3
1
2
5
8
3
5
6
D
C
A
8
7
2
0
2
2
8
9
4
N
B
C
8
4
8
4
2
3
1
3
0
K
N
N
8
3
8
2
2
3
2
3
2
S
V
N
8
3
1
6
0
6
4
C
TR
1
3
1
1
0
5
7
1
3
5
1
3
1
1
0
5
7
1
0
3
32
D
C
A
1
7
4
6
9
6
1
N
B
C
1
8
8
6
9
4
7
K
N
N
1
7
4
6
9
6
1
S
V
N
2
7
1
3
3
I
n
th
e
ca
s
e
o
f
0
an
d
1
,
we
f
o
cu
s
p
r
im
ar
ily
o
n
th
e
lev
el
o
f
en
er
g
y
,
an
d
we
ca
n
s
ee
th
at
th
e
s
ig
n
al
lev
els
wer
e
p
lace
d
in
g
r
o
u
p
s
o
f
2
6
3
8
8
,
3
4
9
9
1
,
3
1
6
1
4
,
an
d
7
1
3
5
r
ec
o
r
d
s
in
b
an
d
1
,
b
an
d
2
,
b
an
d
3
,
an
d
b
an
d
4
,
r
esp
ec
tiv
ely
.
I
n
f
r
eq
u
en
cy
b
an
d
1
,
f
o
r
ex
am
p
le,
th
e
s
ig
n
als,
wh
ich
ar
e
h
ig
h
er
th
an
th
e
th
r
esh
o
ld
lev
el
an
d
ar
e
class
if
ied
as
v
o
ice
wav
ef
o
r
m
s
,
ar
e
p
r
esen
ted
in
co
lu
m
n
1
.
W
ith
d
is
cr
im
in
an
t
an
aly
s
is
,
n
aiv
e
B
ay
es,
an
d
Evaluation Warning : The document was created with Spire.PDF for Python.