I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
p
u
t
er
Science
Vo
l.
21
,
No
.
2
,
Feb
r
u
ar
y
2
0
2
1
,
p
p
.
1
1
4
0
~1
1
50
I
SS
N:
2
5
02
-
4
7
5
2
,
DOI
: 1
0
.
1
1
5
9
1
/i
j
ee
cs.v
2
1
.i
2
.
p
p
1
1
4
0
-
11
50
1140
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs.ia
esco
r
e.
co
m
I
m
pro
v
ing
sig
na
l
detec
tion a
ccurac
y
at F
C
of a C
RN
using
m
a
chine
learning
a
nd f
u
zz
y
r
ules
M
d Abul K
a
la
m
Aza
d,
A
nu
p M
a
j
u
m
der,
J
ug
a
l K
rish
na
Da
s
,
M
d I
m
da
du
l Is
la
m
De
p
a
tme
n
t
o
f
Co
m
p
u
ter S
c
ien
c
e
a
n
d
E
n
g
in
e
e
rin
g
,
Ja
h
a
n
g
irn
a
g
a
r
Un
iv
e
rsit
y
,
Dh
a
k
a
,
Ba
n
g
lad
e
sh
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
n
1
9
,
2
0
2
0
R
ev
i
s
ed
A
u
g
1
1
,
2
0
2
0
A
cc
ep
ted
A
u
g
30
,
2
0
2
0
T
h
e
p
e
rf
o
r
m
a
n
c
e
o
f
a
c
o
g
n
it
iv
e
ra
d
io
n
e
tw
o
rk
(CRN)
m
a
in
l
y
d
e
p
e
n
d
s
o
n
th
e
f
a
it
h
f
u
l
si
g
n
a
l
d
e
tec
ti
o
n
a
t
f
u
sio
n
c
e
n
ter
(F
C).
In
th
is
p
a
p
e
r,
th
e
c
o
n
c
e
p
t
o
f
w
e
i
g
h
ted
f
u
z
z
y
ru
le
in
Ir
is
d
a
t
a
c
las
sif
i
c
a
ti
o
n
,
a
s
w
e
ll
a
s,
f
o
u
r
m
a
c
h
in
e
lea
rn
in
g
tec
h
n
i
q
u
e
s
n
a
m
e
d
f
u
z
z
y
in
f
e
re
n
c
e
s
y
ste
m
(F
IS
),
f
u
z
z
y
c
-
m
e
a
n
s
c
lu
st
e
rin
g
(F
CM
C),
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
(S
V
M
)
a
n
d
c
o
n
v
o
lu
ti
o
n
a
l
n
e
u
ra
l
n
e
tw
o
rk
(CNN
)
a
re
a
p
p
li
e
d
in
sig
n
a
l
d
e
tec
ti
o
n
a
t
F
C
tak
in
g
sig
n
a
l
-
to
-
in
terf
e
re
n
c
e
p
lu
s
n
o
ise
ra
ti
o
o
f
se
c
o
n
d
a
ry
u
se
rs
a
s
p
a
ra
m
e
ter.
T
h
e
we
ig
h
ted
f
u
z
z
y
ru
le
g
a
v
e
th
e
d
e
tec
ti
o
n
a
c
c
u
ra
c
y
o
f
8
6
.
6
%
,
w
h
ich
re
se
m
b
les
th
e
e
n
e
rg
y
d
e
tec
ti
o
n
m
o
d
e
l
o
f
m
a
jo
rit
y
ru
le
o
f
F
C;
h
o
w
e
v
e
r,
CNN
g
a
v
e
a
n
a
c
c
u
ra
c
y
o
f
9
1
.
3
%
a
t
t
h
e
e
x
p
e
n
se
o
f
m
o
re
d
e
c
isio
n
t
im
e
.
T
h
e
F
IS
,
F
CM
C
a
n
d
S
V
M
g
a
v
e
so
m
e
in
ter
m
e
d
iate
re
su
lt
s;
h
o
w
e
v
e
r,
th
e
c
o
m
b
in
e
d
m
e
th
o
d
g
a
v
e
th
e
b
e
st
re
su
lt
c
o
m
p
a
re
d
to
t
h
a
t
o
f
a
n
y
in
d
iv
id
u
a
l
tec
h
n
iq
u
e
.
K
ey
w
o
r
d
s
:
Co
-
o
p
er
ativ
e
C
R
N
Data
class
i
f
icat
io
n
E
n
tr
o
p
y
Fu
s
io
n
ce
n
ter
Fu
zz
y
s
y
s
te
m
T
h
is
is
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
:
An
u
p
Ma
j
u
m
d
er
Dep
at
m
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
an
d
E
n
g
i
n
ee
r
i
n
g
J
ah
an
g
ir
n
a
g
ar
Un
i
v
er
s
it
y
Dh
a
k
a
-
1
3
4
2
,
B
an
g
lad
esh
E
m
ail: a
n
u
p
m
aj
u
m
d
er
@
j
u
n
i
v
.
ed
u
1.
I
NT
RO
D
UCT
I
O
N
I
n
C
o
g
n
iti
v
e
R
ad
io
Net
w
o
r
k
(
C
R
N)
,
th
er
e
ex
is
t
s
t
w
o
t
y
p
es
o
f
u
s
er
s
s
u
ch
as
P
r
i
m
ar
y
User
(
P
U)
ca
lled
licen
s
ed
u
s
er
a
n
d
Seco
n
d
ar
y
U
s
er
(
SU)
ca
lled
u
n
lice
n
s
ed
u
s
er
.
A
P
U
ca
n
ac
ce
s
s
a
tr
af
f
i
c
ch
a
n
n
el
o
f
t
h
e
n
et
w
o
r
k
w
h
e
n
th
e
c
h
an
n
el
is
f
r
ee
;
h
o
w
ev
er
,
a
SU
is
an
o
p
p
o
r
tu
n
i
s
t
u
s
er
w
h
o
ca
n
ac
ce
s
s
a
ch
an
n
e
l
w
h
e
n
th
e
ch
an
n
el
i
s
n
o
t
o
cc
u
p
ied
b
y
an
y
P
U.
Mo
r
eo
v
er
,
a
SU
in
s
er
v
ice
h
as
to
r
elea
s
e
th
e
c
h
a
n
n
el
w
h
e
n
it
is
clai
m
ed
b
y
a
P
U.
T
h
er
ef
o
r
e
,
th
e
d
etec
tio
n
ac
cu
r
ac
y
o
f
th
e
p
r
ese
n
ce
o
f
a
P
U
is
a
k
e
y
f
ac
to
r
to
av
o
i
d
an
y
m
i
s
d
etec
tio
n
an
d
f
a
ls
e
a
lar
m
.
Hen
ce
,
th
e
c
o
n
ce
p
t
o
f
co
-
o
p
er
ativ
e
C
R
N
c
o
m
e
s
f
o
r
th
w
h
er
e
t
h
e
r
ec
e
i
v
e
d
s
ig
n
al
s
o
f
s
e
v
er
al
SUs
ar
e
co
m
b
in
ed
at
a
F
u
s
io
n
C
en
ter
(
F
C
)
t
o
ex
p
ed
ite
th
e
d
etec
tio
n
ac
cu
r
ac
y
,
I
n
co
n
te
m
p
o
r
ar
y
w
o
r
k
s
,
F
u
zz
y
lo
g
ic
a
n
d
v
ar
io
u
s
m
ac
h
in
e
lear
n
in
g
tec
h
n
iq
u
e
s
ar
e
u
s
ed
at
a
F
C
to
i
m
p
r
o
v
e
th
e
d
etec
tio
n
ac
cu
r
ac
y
.
T
h
e
w
ei
g
h
ted
Fu
zz
y
r
u
le
o
r
Fu
zz
y
s
y
s
te
m
is
w
i
d
ely
u
s
ed
i
n
d
ata
cla
s
s
i
f
icatio
n
p
r
o
b
lem
o
f
co
m
b
in
ed
M
e
m
b
er
s
h
ip
F
u
n
ct
io
n
s
(
MF)
o
f
in
p
u
t
v
ar
iab
les
.
I
t
is
u
s
ed
to
class
i
f
y
I
r
is
d
ata
w
h
er
e
t
h
e
w
ei
g
h
t
of
a
n
i
n
p
u
t
v
ar
iab
le
i
s
d
eter
m
in
ed
f
r
o
m
t
h
e
r
an
g
e
o
f
a
v
ar
iab
le
an
d
its
n
o
n
-
o
v
er
lap
p
in
g
p
ar
ts
[
1
]
.
Sin
ce
ac
cu
r
ac
y
d
ep
en
d
s
o
n
lab
els,
a
u
t
h
o
r
s
f
o
u
n
d
th
e
clas
s
i
f
icatio
n
ac
c
u
r
ac
y
o
f
9
6
.
7
%
u
n
d
er
1
1
lab
els.
T
h
e
F
u
zz
y
r
u
le
-
b
a
s
ed
class
i
f
icatio
n
o
f
co
r
o
n
ar
y
ar
ter
y
d
is
ea
s
e
d
ata
is
a
n
al
y
ze
d
in
[
2
]
;
w
h
er
e
tr
ap
ez
o
id
al
MFs
ar
e
u
s
ed
as
i
n
p
u
t
v
a
r
iab
les.
I
t
is
f
o
u
n
d
t
h
a
t
class
i
f
icatio
n
ac
cu
r
ac
y
is
v
a
r
ied
o
n
w
ei
g
h
ti
n
g
r
u
les
w
i
th
a
m
a
x
i
m
u
m
o
f
9
2
.
8
%
an
d
a
m
i
n
i
m
u
m
o
f
7
1
.
8
%.
A
s
i
m
u
lat
io
n
w
o
r
k
is
d
o
n
e
w
ith
r
ela
y
ed
l
in
k
co
m
m
u
n
icatio
n
to
g
e
n
er
ate
in
p
u
t
d
ata
i
n
s
tead
o
f
i
m
p
o
r
ti
n
g
th
e
m
f
r
o
m
a
d
atab
ase
.
S
ev
e
n
d
if
f
er
e
n
t
m
et
h
o
d
s
an
d
Fu
zz
y
c
-
M
ea
n
s
C
l
u
s
ter
i
n
g
[
FC
M
C
]
ar
e
ap
p
lied
in
m
a
g
n
etic
r
eso
n
a
n
ce
b
r
ain
i
m
a
g
e
cla
s
s
i
f
icatio
n
p
r
o
b
le
m
an
d
f
o
u
n
d
a
m
o
d
er
ate
p
er
f
o
r
m
an
ce
[
3
]
.
A
s
i
m
ilar
al
g
o
r
i
th
m
is
ap
p
lied
f
o
r
th
e
cla
s
s
if
icatio
n
o
f
fa
r
m
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
I
mp
r
o
vin
g
s
ig
n
a
l
d
etec
tio
n
a
c
cu
r
a
cy
a
t F
C
o
f a
C
R
N
u
s
in
g
ma
ch
in
e
lea
r
n
in
g
…
(
Md
A
b
u
l
K
a
la
m
A
z
a
d
)
1141
ac
co
r
d
in
g
to
t
h
eir
f
in
a
n
cial
h
ea
lt
h
[
4
]
.
An
i
m
a
g
e
s
e
g
m
e
n
tatio
n
m
eth
o
d
b
ased
o
n
F
u
zz
y
cl
u
s
ter
i
n
g
w
it
h
ce
llu
lar
a
u
to
m
a
ta
an
d
f
ea
t
u
r
e
w
e
ig
h
ti
n
g
is
p
r
o
p
o
s
ed
in
[
5
]
.
A
co
m
p
ar
i
s
o
n
i
s
m
ad
e
a
m
o
n
g
t
h
e
p
r
o
p
o
s
ed
m
et
h
o
d
,
FC
M
C
, K
-
m
ea
n
s
an
d
Ker
n
el
FC
M
C
.
A
p
p
licati
o
n
o
f
S
u
p
p
o
r
t V
ec
to
r
Ma
ch
i
n
e
(
SVM)
f
o
r
th
e
cla
s
s
i
f
icatio
n
o
f
h
a
n
d
m
o
v
e
m
e
n
t i
n
t
en
tio
n
s
i
s
ex
a
m
in
ed
in
[
6
]
;
w
h
er
e
au
th
o
r
s
class
if
ied
u
p
to
5
2
h
an
d
m
o
v
e
m
e
n
t
in
te
n
tio
n
s
b
ased
o
n
elec
tr
o
m
y
o
g
r
a
p
h
y
s
ig
n
al
s
.
I
t
is
s
h
o
w
n
t
h
at
SV
M
b
ased
s
y
s
te
m
g
i
v
es
a
b
etter
r
esu
lt
t
h
a
n
th
at
o
f
lea
s
t
s
q
u
ar
e
t
w
i
n
SVM
b
ased
s
y
s
te
m
[
7
]
.
F
o
u
r
k
er
n
els
n
a
m
ed
lin
ea
r
,
p
o
l
y
n
o
m
ial,
r
ad
ia
l
b
asis
a
n
d
s
i
g
m
o
id
b
asis
k
er
n
e
l
ar
e
u
s
ed
to
c
las
s
i
f
y
b
io
m
ed
ical
d
ata
a
m
o
n
g
v
ar
io
u
s
d
iease
s
g
r
o
u
p
s
[
8
]
.
A
u
t
h
o
r
f
o
u
n
d
t
h
e
m
ea
n
ac
c
u
r
ac
y
of
7
8
.
4
4
%,
6
2
.
8
%,
6
5
.
9
%
an
d
6
3
.
5
%
f
o
r
lin
ea
r
,
p
o
ly
n
o
m
ial,
r
ad
i
al
b
asi
s
a
n
d
s
i
g
m
o
id
b
as
is
k
er
n
el
,
r
esp
ec
tiv
e
l
y
.
St
ill,
a
r
esear
c
h
g
ap
o
f
SVM
r
eg
ar
d
i
n
g
it
s
ap
p
licatio
n
in
C
R
N
is
e
v
id
en
t.
T
h
e
ap
p
licatio
n
o
f
S
VM
i
n
s
p
ec
tr
u
m
s
e
n
s
i
n
g
o
f
C
R
N
i
s
f
o
u
n
d
in
[
9
]
.
T
h
e
r
e
ce
iv
ed
s
i
g
n
al
is
i
n
p
u
t
ted
to
a
tu
n
ab
le
b
a
n
d
p
ass
f
ilter
a
n
d
t
h
e
o
u
tp
u
t
b
ec
o
m
e
s
a
d
ig
i
t
al
s
i
g
n
al
,
w
h
ic
h
is
t
h
en
ap
p
lied
to
an
SVM.
T
h
e
pe
r
f
o
r
m
a
n
ce
o
f
e
n
er
g
y
d
etec
tio
n
is
co
m
p
ar
ed
w
ith
SVM
o
n
th
e
p
lan
e
o
f
p
r
o
b
ab
ilit
y
o
f
f
al
s
e
alar
m
a
n
d
d
etec
tio
n
.
A
s
i
m
il
ar
a
n
al
y
s
is
is
f
o
u
n
d
i
n
[
1
0
]
.
T
w
o
h
y
p
o
th
esis
m
o
d
el
o
f
C
R
N
is
u
s
ed
to
d
eter
m
i
n
e
t
h
e
co
-
v
ar
ian
ce
m
atr
i
x
o
f
r
ec
ei
v
ed
s
i
g
n
al
in
[
1
1
]
.
T
h
er
ef
o
r
e
,
N
E
ig
en
v
al
u
e
s
d
eter
m
i
n
ed
f
r
o
m
co
-
v
ar
ian
ce
m
atr
i
x
ar
e
ap
p
lied
to
k
er
n
el
b
ased
SVM.
T
h
e
p
r
o
f
ile
o
f
p
r
o
b
ab
ilit
y
o
f
f
alse
alar
m
an
d
m
is
d
etec
tio
n
ag
ain
s
t
Si
g
n
al
-
to
-
No
is
e
R
a
tio
(
SN
R
)
ar
e
s
h
o
w
n
tak
i
n
g
t
h
e
n
u
m
b
er
o
f
an
ten
n
a
ele
m
e
n
ts
an
d
in
p
u
t
d
ata
a
s
p
ar
a
m
eter
s
.
I
n
s
tead
o
f
N
-
d
i
m
e
n
s
io
n
al
en
er
g
y
v
ec
to
r
,
a
lo
w
-
d
i
m
e
n
s
io
n
al
p
r
o
b
ab
ilit
y
v
ec
to
r
is
d
er
iv
ed
f
r
o
m
m
u
l
tiv
ar
iate
Gau
s
s
ia
n
d
is
t
r
ib
u
tio
n
f
u
n
ctio
n
in
[
1
2
]
,
w
h
ich
is
ap
p
lied
to
SVM
b
ased
class
i
fi
ca
tio
n
.
T
h
e
au
t
h
o
r
s
clai
m
t
h
at
th
e
p
r
o
b
a
b
ilit
y
v
ec
to
r
o
f
li
n
ea
r
S
VM
h
as
a
b
etter
d
etec
tio
n
ac
cu
r
ac
y
t
h
an
t
h
e
e
n
er
g
y
v
ec
to
r
o
f
p
r
ev
io
u
s
w
o
r
k
;
h
o
w
ev
er
,
K
-
m
ea
n
s
c
lu
s
ter
in
g
p
er
f
o
r
m
s
s
lig
h
tl
y
w
o
r
s
e
.
A
s
i
m
ilar
a
n
al
y
s
i
s
an
d
g
r
ap
h
ical
r
esu
lt
ar
e
also
f
o
u
n
d
in
[
1
3
]
.
Sti
ll,
w
e
ca
n
u
s
e
th
r
e
e
lev
el
h
y
p
o
th
e
s
is
w
i
th
w
e
ig
h
ted
Fu
zz
y
r
u
le
o
r
d
ee
p
lear
n
in
g
to
o
b
s
er
v
e
t
h
e
d
etec
tio
n
ac
cu
r
ac
y
a
n
d
p
r
o
ce
s
s
in
g
ti
m
e.
I
n
[
1
4
]
,
a
3
-
Di
m
en
s
io
n
al
C
o
n
v
o
lu
tio
n
al
Ne
u
r
al
Net
w
o
r
k
(
3
-
D
C
NN)
is
ap
p
lied
to
ag
e
es
t
i
m
atio
n
in
m
ag
n
eti
c
r
eso
n
a
n
ce
i
m
a
g
i
n
g
o
f
h
u
m
a
n
b
r
ain
.
T
h
e
w
o
r
k
m
ak
e
s
a
co
m
p
ar
is
o
n
w
it
h
P
r
in
cip
al
C
o
m
p
o
n
e
n
t
An
al
y
s
i
s
,
lo
ca
l
f
ea
tu
r
e
s
an
d
2
-
DC
NN,
a
n
d
s
h
o
w
s
t
h
at
3
-
D
C
NN
g
i
v
es
th
e
b
est
ac
c
u
r
ac
y
.
T
h
e
co
n
ce
p
t
o
f
C
NN
is
also
ap
p
lied
to
s
o
u
n
d
c
lass
i
f
icatio
n
o
v
er
s
p
ec
tr
o
g
r
a
m
s
[
1
5
]
.
T
h
e
n
et
w
o
r
k
i
s
tr
ain
ed
w
i
t
h
a
d
ataset
co
n
s
i
s
t
s
o
f
6
,
7
7
6
s
p
ec
tr
o
g
r
am
s
o
f
d
if
f
er
en
t
s
o
u
n
d
s
,
a
n
d
th
e
e
x
p
er
i
m
en
t
g
iv
e
s
an
ac
c
u
r
ac
y
o
f
9
5
%
o
n
tr
ain
i
n
g
d
ata
s
et
an
d
an
ac
c
u
r
ac
y
o
f
8
5
% o
n
tes
t
d
ata
s
et
.
T
h
e
co
n
ce
p
t
o
f
Dee
p
Q
-
Net
w
o
r
k
(
DQN)
to
e
v
al
u
ate
t
h
e
ca
p
ac
it
y
o
f
a
n
et
w
o
r
k
is
f
o
u
n
d
i
n
[
1
6
]
;
w
h
er
e
SN
R
an
d
S
h
an
n
o
n
f
o
r
m
u
la
ar
e
tak
e
n
as
i
n
p
u
t
p
ar
am
eter
s
,
a
n
d
d
ata
p
ac
k
ets
ar
e
d
iv
id
ed
in
eq
u
al
ti
m
e
s
lo
t
k
ee
p
in
g
P
U
an
d
SU
s
y
n
c
h
r
o
n
ized
.
T
h
e
v
ar
iatio
n
o
f
s
y
s
te
m
ca
p
ac
it
y
a
g
ai
n
s
t
ti
m
e
s
lo
t
is
p
lo
tted
b
o
th
f
o
r
lear
n
in
g
ca
s
e
i.e
.
,
DQN
an
d
f
o
r
w
ith
o
u
t
lear
n
i
n
g
ca
s
e;
w
h
e
r
e
DQN
g
iv
e
s
a
b
etter
r
esu
lt.
Ho
w
e
v
er
,
th
e
w
o
r
k
ig
n
o
r
es
t
h
e
f
ad
i
n
g
m
o
d
el
,
as
w
ell
a
s
,
th
e
s
p
ec
tr
u
m
s
e
n
s
i
n
g
m
o
d
el
.
T
h
e
c
o
n
ce
p
t
o
f
FC
is
n
o
t
co
n
s
id
er
ed
eith
er
.
T
h
e
p
er
f
o
r
m
a
n
ce
o
f
C
R
N
is
d
eter
m
in
ed
at
F
C
u
s
in
g
t
h
e
i
d
ea
o
f
co
-
o
p
er
ativ
e
s
p
ec
tr
u
m
s
en
s
in
g
i
n
OFDM
s
y
s
te
m
[
1
7
]
.
T
h
e
p
r
o
b
a
b
ilit
y
o
f
f
al
s
e
alar
m
a
n
d
d
etec
tio
n
is
p
lo
tted
ag
ain
s
t
S
NR
f
o
r
1
6
-
QA
M
u
n
d
er
A
d
d
itiv
e
W
h
ite
Gau
s
s
io
an
No
i
s
e
(
A
W
GN)
.
T
h
e
C
NN
is
ap
p
lied
to
s
p
ec
tr
u
m
s
e
n
s
i
n
g
an
d
th
e
i
m
p
ac
t
o
f
s
ize
an
d
n
u
m
b
er
o
f
co
n
v
o
lu
tio
n
la
y
er
,
p
o
o
lin
g
la
y
er
a
n
d
f
u
ll
y
co
n
n
e
cted
la
y
er
o
n
ti
m
e
co
m
p
le
x
it
y
ar
e
also
an
al
y
ze
d
.
Sti
ll,
w
e
h
av
e
t
h
e
s
co
p
e
o
f
u
s
i
n
g
C
NN
u
n
d
er
d
if
f
er
en
t
f
ad
in
g
en
v
ir
o
n
m
en
t
to
g
et
a
m
o
r
e
r
ea
lis
tic
s
ce
n
ar
io
f
o
r
C
R
N.
I
n
th
is
p
ap
er
,
f
o
u
r
p
o
p
u
lar
m
ac
h
in
e
lear
n
i
n
g
m
et
h
o
d
s
i.e
.
,
FIS,
FC
MC
,
SVM
a
n
d
C
N
N
alo
n
g
w
it
h
Fu
zz
y
w
ei
g
h
ted
r
u
le
ar
e
ap
p
li
ed
in
d
etec
ti
n
g
th
e
p
r
esen
ce
o
f
P
Us
at
FC
;
w
h
er
e
th
e
F
C
ta
k
es
1
6
-
Q
A
M
s
ig
n
al
u
n
d
er
A
W
GN
an
d
R
a
y
le
ig
h
f
ad
in
g
ch
a
n
n
el.
T
w
o
co
n
v
e
n
t
io
n
al
h
y
p
o
th
es
is
m
o
d
el
s
f
o
r
s
ig
n
a
l
d
etec
tio
n
ar
e
u
s
ed
in
ea
c
h
m
eth
o
d
an
d
f
in
al
l
y
,
th
e
ac
c
u
r
ac
y
le
v
els o
f
f
i
v
e
m
et
h
o
d
s
ar
e
c
o
m
b
i
n
ed
u
s
in
g
E
n
tr
o
p
y
.
T
h
e
r
est
o
f
th
e
p
ap
er
is
o
r
g
a
n
i
ze
d
as
f
o
llo
w
s
:
Sectio
n
2
g
i
v
es
s
o
m
e
b
asic
t
h
eo
r
y
o
f
m
ac
h
in
e
lear
n
i
n
g
tech
n
iq
u
es
to
r
ec
o
g
n
ize
t
h
e
s
i
g
n
al
at
F
C
,
Sec
tio
n
3
d
ea
l
s
with
r
es
u
lt
s
b
ased
o
n
th
e
an
al
y
s
is
o
f
Sectio
n
2
an
d
f
i
n
all
y
,
Sectio
n
4
co
n
cl
u
d
es e
n
tire
an
al
y
s
is
.
2.
T
H
E
O
RY
O
F
DA
T
A
CL
AS
SI
F
I
CA
T
I
O
N
I
n
t
h
is
s
ec
tio
n
,
w
e
co
n
s
id
er
t
h
e
b
asic
t
h
eo
r
y
o
f
f
iv
e
d
ata
c
lass
i
f
icatio
n
tec
h
n
iq
u
es
:
F
u
zz
y
w
ei
g
h
ted
r
u
le,
FIS
,
F
C
M
C
,
SVM
a
n
d
C
NN.
2
.
1
.
F
uzzy
w
ei
g
hte
d r
ule
H
er
e,
Fu
zz
y
w
ei
g
h
ted
r
u
le
is
ex
p
lain
ed
w
i
th
t
h
e
h
elp
o
f
t
w
o
n
u
m
er
ical
e
x
a
m
p
le
s
.
Firs
t
o
f
all,
w
e
tak
e
s
i
m
u
latio
n
d
ata
u
n
d
er
tw
o
ca
teg
o
r
ies
ca
lled
H
0
an
d
H
1
as
s
h
o
w
n
i
n
T
ab
le
1
.
Fo
r
ea
ch
ca
teg
o
r
y
,
f
o
u
r
in
p
u
t
p
ar
a
m
eter
s
s
u
c
h
as
SU
1
,
SU
2
,
SU
3
an
d
SU
4
,
an
d
th
e
ir
co
r
r
esp
o
n
d
in
g
o
u
tp
u
t
ar
e
s
h
o
w
n
e
x
p
licitl
y
i
n
T
ab
le
2
.
I
n
th
is
p
ap
er
,
w
e
u
s
e
Fu
zz
y
r
u
le
s
w
it
h
f
i
v
e
M
e
m
b
er
s
h
ip
F
u
n
c
tio
n
s
(
MFs)
as s
h
o
wn
in
Fig
u
r
e
1.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
21
,
No
.
2
,
Feb
r
u
ar
y
2
0
2
1
:
1
1
40
-
11
50
1142
T
ab
le
1
.
I
n
p
u
t p
ar
am
eter
s
a
n
d
o
u
tp
u
t t
y
p
e
o
f
th
e
S
U
d
ata
f
r
o
m
s
i
m
u
latio
n
H
y
p
o
t
h
e
si
s
H
0
H
y
p
o
t
h
e
si
s
H
1
SU
1
SU
2
SU
3
SU
4
O
u
t
p
u
t
SU
1
SU
2
SU
3
SU
4
O
u
t
p
u
t
0
.
0
6
4
1
.
6
8
8
0
.
8
2
4
0
.
3
1
4
1
2
.
8
2
0
2
.
1
5
1
3
.
2
2
4
5
.
2
2
1
2
0
.
8
8
9
0
.
6
6
4
1
.
1
5
2
1
.
9
0
2
1
3
.
6
5
3
2
.
4
1
2
1
.
3
5
6
4
.
1
2
2
2
0
.
5
5
3
0
.
0
7
9
0
.
2
2
1
0
.
9
8
1
1
4
.
3
1
2
3
.
4
4
3
3
.
0
8
9
1
.
2
0
9
2
0
.
7
6
3
1
.
3
0
6
1
.
5
1
4
0
.
3
2
0
1
3
.
4
3
8
1
.
1
2
1
2
.
6
6
7
2
.
0
7
2
2
0
.
4
5
3
0
.
9
1
9
0
.
2
3
1
1
.
3
3
1
1
2
.
4
9
4
3
.
4
1
1
4
.
1
0
8
3
.
1
0
9
2
Fig
u
r
e
1
.
T
h
e
MFs o
f
th
e
f
y
zz
y
s
y
s
te
m
T
ab
le
2
.
I
n
p
u
t
p
ar
am
eter
s
a
n
d
o
u
tp
u
t t
y
p
e
s
i
m
u
la
tio
n
d
ata
H
y
p
o
t
h
e
si
s
H
0
H
y
p
o
t
h
e
si
s
H
1
SU
1
SU
2
SU
3
SU
4
O
u
t
p
u
t
SU
1
SU
2
SU
3
SU
4
O
u
t
p
u
t
A
B
B
A
1
C
C
C
E
2
B
A
B
B
1
D
C
B
D
2
A
A
A
B
1
D
C
C
B
2
B
B
B
A
1
C
B
C
C
2
A
B
A
B
1
C
C
D
C
2
No
w
,
t
h
e
r
u
le
f
o
r
H
0
is
R
0
=
(
(
{
A
,
B
}
,
{
A
,
B
}
,
{
A
,
B
}
,
{
A
,
B
})
,
H
0
)
an
d
t
h
e
r
u
le
f
o
r
H
1
is
R
1
=
(({
C
,
D
}
,
{
B
,
C
}
,
{
B
,
C
,
D
}
,
{
C
,
B
,
D,
E
})
,
H
1
)
.
W
e
w
ill
ex
p
lai
n
th
e
F
u
zz
y
w
ei
g
h
ted
r
u
le
t
h
r
o
u
g
h
d
ata
v
a
lid
atio
n
tech
n
iq
u
es i
n
a
d
if
f
er
en
t
w
a
y
,
s
p
ec
iall
y
u
s
i
n
g
lin
e
d
ia
g
r
a
m
s
an
d
n
u
m
er
ical
e
x
a
m
p
le
s
.
2
.
1
.
1.
Nu
m
er
ica
l
e
x
a
m
ple
-
1
Sh
o
w
t
h
at
(
SU
1
,
SU
2
,
SU
3
,
S
U
4
)
≡
(
0
.
7
2
,
0
.
8
3
,
1
.
7
1
,
0
.
1
3
4
)
b
elo
n
g
s
to
o
u
tp
u
t
H
0
.
Fro
m
t
h
e
m
e
m
b
er
s
h
ip
f
u
n
ctio
n
o
f
SU
s
i
g
n
al,
w
e
g
et
(
0
.
7
2
,
0
.
8
3
,
1
.
7
1
,
0
.
1
3
4
)
↔
(
{
A
}
,
{
B
}
,
{
B
}
,
{
A
})
.
C
o
n
s
id
er
in
g
t
h
e
s
ets
o
f
r
u
le
R
0
,
A
ɛ
{
A
,
B
}
,
B
∈
{
A
,
B
}
,
B
∈
{
A
,
B
}
,
an
d
A
∈
{
A
,
B
}
.
T
h
er
ef
o
r
e,
(
0
.
7
2
,
0
.
8
3
,
1
.
7
1
,
0
.
1
3
4
)
b
elo
n
g
s
to
th
e
class
H
0
.
Usi
n
g
t
h
e
th
eo
r
etica
l
an
al
y
s
i
s
o
f
[1
,
2
]
,
we
d
eter
m
in
e
t
h
e
Fu
zz
y
w
e
ig
h
t
f
ac
to
r
s
.
Fro
m
t
h
e
in
p
u
t
o
f
T
ab
le
1
,
th
e
r
an
g
e
o
f
S
U
1
f
o
r
o
u
tp
u
t
H
0
is
0
.
0
6
4
to
0
.
8
8
9
an
d
f
o
r
o
u
tp
u
t
H
1
is
2
.
4
9
4
to
4
.
3
1
2
as
s
h
o
w
n
i
n
Fig
u
r
e
2
(
a)
.
Fo
r
th
e
co
n
v
en
ie
n
ce
o
f
an
al
y
s
i
s
,
th
e
r
an
g
e
o
f
i
n
p
u
t
d
ata
ca
n
b
e
s
h
o
w
n
b
y
li
n
e
d
iag
r
a
m
a
s
f
o
llo
w
s
.
(
a)
R
an
g
e
o
f
SU
1
(
b
)
R
an
g
e
o
f
S
U2
(
c)
R
an
g
e
o
f
SU
3
(
d
)
R
an
g
e
o
f
S
U
4
Fig
u
r
e
2
.
R
an
g
e
o
f
i
n
p
u
t p
ar
am
eter
s
o
f
T
ab
le
1
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
I
mp
r
o
vin
g
s
ig
n
a
l
d
etec
tio
n
a
c
cu
r
a
cy
a
t F
C
o
f a
C
R
N
u
s
in
g
ma
ch
in
e
lea
r
n
in
g
…
(
Md
A
b
u
l
K
a
la
m
A
z
a
d
)
1143
Fo
r
in
p
u
t
p
ar
a
m
eter
o
f
SU
1
,
th
e
li
n
e
d
ia
g
r
a
m
b
ec
o
m
es
Fi
g
u
r
e
2
(
a)
.
T
h
er
e
is
n
o
o
v
er
la
p
p
in
g
p
ar
t;
th
er
ef
o
r
e
,
th
e
e
n
tire
r
an
g
e
S
an
d
n
o
n
-
o
v
er
lap
p
in
g
p
ar
t,
S
n
w
ill
b
e
th
e
s
a
m
e.
No
w
,
S
=
(
0
.
0
6
4
–
4
.
3
1
2
)
=
S
n
=
4
.
2
4
8
;
th
er
ef
o
r
e,
th
e
r
atio
b
ec
o
m
e
s
,
V
1
=
4
.
2
4
8
/4
.
2
4
8
=
1
.
Fo
r
SU
2
o
f
Fig
u
r
e
2
(
b
)
,
th
e
s
u
m
o
f
n
o
n
-
o
v
er
lap
p
in
g
p
ar
t,
S
n
=
(
1
.
1
2
1
-
0
.
0
7
9
)
+
(
3
.
4
4
3
-
1
.
6
8
8
)
=
2
.
7
9
7
.
T
h
e
en
tire
r
an
g
e
is
S
=
(
3
.
4
4
3
-
0
.
0
7
9
)
=
3
.
3
6
4
.
T
h
e
n
th
e
r
atio
b
ec
o
m
e
s
,
V
i
=
S
n
/S
=>
V
2
=
2
.
7
9
7
/
3
.
3
6
4
=
0
.
8
3
1
.
W
ith
s
i
m
ilar
ca
lcu
la
tio
n
s
o
f
Fig
u
r
e
2
(
c)
an
d
Fig
u
r
e
2
(
d
)
,
w
e
g
et
V
3
=
3
.
7
2
9
/3
.
8
8
7
=
0
.
9
6
f
o
r
S
U
3
,
an
d
V
4
=
4
.
2
0
8
/4
.
9
0
1
=
0
.
8
5
f
o
r
SU
4
,
r
esp
ec
tiv
el
y
.
No
w
,
V
Max
=
Ma
x
(
V
1
,
V
2
,
V
3
,
V
4
)
=
Ma
x
(
1
,
0
.
8
3
1
,
0
.
9
6
,
0
.
8
5
)
=
1
.
Fro
m
th
e
t
h
eo
r
y
,
w
e
k
n
o
w
t
h
at,
W
i
=
{
V
i
/Ma
x
(
V
1
,
V
2
,
V
3
,
V
4
)
}
2
.
T
h
er
ef
o
r
e,
W
1
=
(
1
/1
)
2
=
1
,
W
2
=
(
0
.
8
3
1
/1
)
2
=0
.
6
9
,
W
3
=
(
0
.
9
6
/1
)
2
=
0
.
9
2
,
an
d
W
4
=
(
0
.
8
5
/1
)
2
=
0
.
7
2
2
2
.
1
.
2.
Nu
m
er
ica
l
e
x
a
m
ple
-
2
W
e
tak
e
test
d
ata
as
(
SU
1
,
SU
2
,
SU
3
,
SU
4
)
≡
{(
0
.
9
2
,
0
.
5
1
,
1
.
6
1
,
1
.
7
2
)
,
1
}.
Fro
m
th
e
m
e
m
b
er
s
h
ip
f
u
n
ctio
n
o
f
S
L
,
Ψ
01
(
SU
1
=
0
.
9
2
)
=
0
.
6
2
↔
B
∈
{
A
,
B
}
i.e
.
,
B
b
elo
n
g
s
to
th
e
f
i
r
s
t set o
f
Ψ
02
(
SU
2
=
0
.
5
1
)
=
0
.
9
1
↔
A
∈
{
A
,
B
}
i.e
.,
A
b
elo
n
g
s
to
th
e
s
e
co
n
d
s
et
o
f
Ψ
03
(
SU
3
=1
.
6
1
)
=
0
.
7
4
↔
B
∈
{
A
,
B
}
i.e
.,
B
b
elo
n
g
to
th
e
th
ir
d
s
et
o
f
R
0
Ψ
04
(
SU
4
=
1
.
7
2
)
=
0
.
7
8
↔
B
∈
{
A
,
B
}
i.e
.
,
B
b
elo
n
g
to
th
e
f
o
u
r
th
s
et
o
f
R
0
T
h
e
w
eig
h
ted
co
-
v
ar
ian
ce
o
f
F
u
zz
y
r
u
le
R
0
,
4
1
0
)
(
i
i
i
i
W
X
R
=
1
*
0
.
6
2
+
0
.
6
9
*
0
.
9
1
+
0
.
9
2
*
0
.
7
4
+
0
.
7
2
2
*
0
.
7
8
=
2
.
4
9
Ψ
11
(
SU
1
=
0
.
9
2
)
=
0
.
6
2
↔
B
{
C
,
D
}
i.e
.
,
B
d
o
es n
o
t b
elo
n
g
to
th
e
f
ir
s
t
s
et
o
f
R
1
Ψ
12
(
SU
2
=
0
.
5
1
)
=
0
.
9
1
↔
A
{
B
,
C
}
i.e
.
,
A
d
o
es n
o
t b
elo
n
g
t
o
th
e
s
ec
o
n
d
s
et
o
f
R
1
Ψ
13
(
SU
3
=1
.
6
1
)
=
0
.
7
4
↔
B
∈
{B
,
C
,
D}
i.e
.
,
B
b
elo
n
g
to
th
e
th
ir
d
s
et
o
f
R
1
Ψ
14
(
SU
4
=
1
.
7
2
)
=
0
.
7
8
↔
B
∈
{
C
,
B
,
D
,
E
}
i.e
.
,
B
b
elo
n
g
to
th
e
f
o
u
r
th
s
et
o
f
R
1
T
h
e
w
eig
h
ted
co
-
v
ar
ian
ce
o
f
F
u
zz
y
r
u
le
R
1
,
4
1
1
)
(
i
i
i
i
W
X
R
=
0
+
0
+
0
.
9
2
*
0
.
7
4
+
0
.
7
2
2
*
0
.
7
8
=
1
.
2
4
T
h
e
m
a
x
i
m
u
m
v
al
u
e
o
f
R
is
f
o
u
n
d
f
o
r
r
u
le
R
0
;
t
h
er
ef
o
r
e,
(
0
.
9
2
,
0
.
5
1
,
1
.
6
1
,
1
.
7
2
)
s
u
p
p
o
r
ts
R
0
i.e
.
,
th
e
test
i
n
g
d
ata
is
u
n
d
er
h
y
p
o
th
e
s
i
s
H
0
,
w
h
ic
h
is
f
o
u
n
d
to
b
e
co
r
r
ec
t.
2
.2
.
F
uzzy
infe
re
nce
s
y
s
t
e
m
Fu
zz
y
I
n
f
er
en
ce
S
y
s
te
m
(
FI
S)
r
elate
s
in
p
u
t
v
ec
to
r
s
X
=
[
C
0
C
1
C
2
…
C
k
]
,
ea
ch
o
f
s
ize
k
,
to
o
u
tp
u
t
v
ar
iab
le
Y
u
s
i
n
g
Fu
zz
y
lo
g
ic.
A
FIS
co
n
s
is
t
s
o
f
t
h
r
ee
b
lo
ck
s
n
a
m
ed
F
u
zz
i
f
icat
io
n
b
lo
ck
,
I
n
f
er
e
n
ce
en
g
i
n
e
a
n
d
D
e
-
f
u
zz
i
f
ier
b
lo
ck
a
s
e
x
p
lain
e
d
in
[
1
8
-
2
1
]
f
o
r
d
if
f
er
e
n
t
ap
p
li
ca
tio
n
s
.
I
n
th
is
p
ap
er
,
w
e
u
s
e
t
h
e
f
o
llo
w
i
n
g
s
tep
s
to
r
elate
th
e
s
ig
n
al
s
o
f
SU
s
at
FC
w
it
h
t
h
e
d
ec
is
io
n
o
f
h
y
p
o
t
h
esi
s
H
0
o
r
H
1
.
a)
T
ak
e
M
s
a
m
p
les f
r
o
m
th
e
s
ig
n
al
s
(
t)
o
f
ea
ch
o
f
SU
s
at
F
C
.
b)
A
p
p
l
y
r
ec
u
r
r
en
t
d
is
cr
ete
w
a
v
e
let
tr
an
s
f
o
r
m
o
n
th
e
s
a
m
p
le
v
ec
to
r
u
n
til
r
ed
u
c
in
g
it
to
a
s
iz
e
o
f
4
as
V
=
[C
0
C
1
C
2
C
3
]
c)
A
p
p
l
y
v
ec
to
r
s
V
to
FIS
d)
Gen
er
ate
cr
is
p
o
u
tp
u
t Y
a
s
0
o
r
1
ag
ain
s
t t
h
e
h
y
p
o
th
e
s
is
H
0
o
r
H
1
T
h
e
r
esu
lt sectio
n
r
e
v
ea
ls
t
h
e
s
ig
n
al
v
ec
to
r
V
a
n
d
co
r
r
esp
o
n
d
in
g
o
u
tp
u
t
Y
i
n
a
tab
u
lar
f
o
r
m
.
2
.3
.
F
uzzy
c
-
m
ea
ns
cl
u
s
t
er
in
g
Her
e,
d
ata
is
s
ep
ar
ated
in
to
s
ev
er
al
cl
u
s
ter
s
,
w
h
ich
m
a
y
b
e
o
v
er
lap
p
in
g
o
r
n
o
n
-
o
v
er
lap
p
in
g
.
T
h
e
di
s
tan
ce
b
et
w
ee
n
t
h
e
ce
n
ter
o
f
a
clu
s
ter
an
d
th
e
p
o
in
t
u
n
d
e
r
co
n
s
id
er
atio
n
g
o
v
er
n
s
t
h
e
g
r
ad
e
o
f
a
MF
.
T
h
e
s
h
o
r
ter
t
h
e
d
is
tan
ce
,
th
e
h
ig
h
er
th
e
g
r
ad
e
o
f
a
M
F.
T
h
e
s
tep
s
o
f
F
u
zz
y
c
-
M
ea
n
s
C
lu
s
t
er
in
g
alg
o
r
it
h
m
i
s
av
ailab
le
in
[2
2
-
2
4
].
I
n
th
is
p
ap
er
,
w
e
tak
e
t
h
e
r
ec
eiv
e
d
s
ig
n
al
o
f
P
Us
at
FC
u
n
d
er
th
r
ee
ca
teg
o
r
ies:
H
y
p
o
th
es
is
H
0
(
ab
s
e
n
ce
o
f
P
U)
,
H
y
p
o
th
esi
s
H
1
(
p
r
ese
n
ce
o
f
P
U)
an
d
H
y
p
o
th
e
s
is
H
0
+
(
i
n
ter
m
ed
iate
r
e
s
u
l
t,
u
s
u
all
y
ap
p
licab
le
to
m
a
licio
u
s
at
tack
)
;
w
h
er
e
S
U
s
ar
e
u
s
ed
as
th
e
r
ela
y
s
tatio
n
s
.
Ne
x
t
,
w
e
ap
p
l
y
F
u
zz
y
c
-
M
ea
n
s
C
l
u
s
ter
i
n
g
al
g
o
r
ith
m
t
o
g
et
t
h
e
s
ca
tter
p
lo
t
o
f
d
ata
a
f
ter
co
n
v
er
g
e
n
ce
o
f
t
h
r
ee
d
eg
r
ee
o
f
b
elo
n
g
in
g
s
:
U
1
(
k
)
,
U
2
(
k
)
an
d
U
3
(
k
)
o
f
th
r
ee
h
y
p
o
th
e
s
es.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
21
,
No
.
2
,
Feb
r
u
ar
y
2
0
2
1
:
1
1
40
-
11
50
1144
2
.4
.
Su
pp
o
rt
v
ec
t
o
r
m
a
chine
A
S
u
p
p
o
r
t
Vec
to
r
Ma
ch
in
e
(
SVM)
is
a
m
ac
h
i
n
e
lear
n
i
n
g
m
o
d
el
f
o
r
th
e
class
i
f
icatio
n
o
f
r
esp
o
n
s
e
d
ata
o
f
a
s
y
s
te
m
.
T
h
e
b
asic
c
o
n
ce
p
t
o
f
S
VM
i
s
to
co
n
s
tr
u
c
t
a
li
n
ea
r
o
r
n
o
n
-
li
n
ea
r
h
y
p
er
p
lan
e
to
s
ep
ar
ate
th
e
d
ata
p
o
in
ts
u
n
d
er
d
if
f
er
en
t
co
n
d
itio
n
s
.
A
s
a
n
ex
a
m
p
le,
let
u
s
co
n
s
id
er
a
s
et
o
f
d
ata
{
x
i
},
i
=
0
,
1
,
2
,
…,
(
N
-
1
)
,
an
d
co
r
r
esp
o
n
d
in
g
d
es
ir
ed
r
esp
o
n
s
e
o
f
a
s
y
s
te
m
is
,
d
i
{+
1
,
-
1
},
w
h
ich
is
r
ep
r
esen
ted
a
s
t
h
e
s
et
o
f
o
r
d
er
ed
p
air
,
1
0
,
N
i
i
i
d
x
.
T
h
e
eq
u
atio
n
o
f
h
y
p
er
p
lan
e,
w
T
x
+b
=
0
(
w
h
er
e
x
i
s
i
n
p
u
t
v
ec
to
r
,
w
is
w
ei
g
h
t
v
ec
to
r
an
d
b
is
a
b
ias)
s
atis
f
ie
s
,
w
T
x
i
+b
≥
0
f
o
r
d
i
=
+1
an
d
w
T
x
i
+
b
<0
f
o
r
d
i
=
-
1
.
Hig
h
er
d
eg
r
ee
p
o
ly
n
o
m
i
al
o
r
ev
en
a
s
p
ec
ial
f
u
n
ctio
n
li
k
e
Gau
s
s
ia
n
R
ad
ial
B
asis
F
u
n
ctio
n
is
u
s
ed
as
a
h
y
p
er
p
lan
e
to
s
eg
r
eg
ate
co
m
p
le
x
d
ata
[
1
0
-
1
1
]
.
W
e
also
co
n
s
id
er
th
r
ee
t
y
p
e
s
o
f
d
ata
u
n
d
er
h
y
p
o
t
h
esi
s
H
0
,
h
y
p
o
th
esis
H
1
a
n
d
h
y
p
o
t
h
esi
s
H
0
+
.
Her
e,
th
e
i
n
p
u
t
v
ec
to
r
is
SIN
R
at
F
C
an
d
w
e
d
eter
m
in
e
SIN
R
at
r
ec
eiv
i
n
g
en
d
as
a
r
an
d
o
m
v
ar
iab
le
u
s
i
n
g
th
e
co
n
ce
p
t
o
f
[2
5
-
26
].
2
.
5
.
Co
nv
o
lutio
na
l
neura
l net
w
o
rk
A
C
o
n
v
o
l
u
tio
n
a
l
Neu
r
al
Nt
wo
r
k
(
C
NN)
is
o
n
e
k
in
d
o
f
De
ep
Neu
r
al
Net
w
o
r
k
(
DNN)
th
at
ac
q
u
ir
es
an
im
m
e
n
s
e
p
o
p
u
la
r
i
ty
in
o
b
ject
r
ec
o
g
n
it
io
n
.
T
h
e
m
ai
n
f
u
n
ctio
n
al
b
lo
ck
o
f
a
C
NN
is
co
n
v
o
l
u
tio
n
a
l
la
y
er
in
w
h
ic
h
a
L
i
n
ea
r
T
i
m
e
I
n
v
ar
ia
n
t
(
L
T
I
)
s
y
s
te
m
is
ac
t
iv
ated
a
s
y
(
t
)
=
x
(
t
)*
h
(
t
);
w
h
er
e
x
(
t
)
is
i
n
p
u
t
s
i
g
n
al,
h
(
t
)
is
i
m
p
u
l
s
e
r
esp
o
n
s
e
o
f
L
T
I
s
y
s
te
m
a
n
d
y
(
t
)
is
o
u
tp
u
t
o
f
t
h
e
s
y
s
te
m
.
I
f
L
T
I
s
y
s
te
m
is
a
f
ilter
,
th
en
t
h
e
co
n
v
o
lu
tio
n
al
o
p
er
atio
n
p
r
o
v
i
d
es
f
ilter
ed
s
i
g
n
al.
I
n
C
NN,
w
e
u
s
e
t
h
e
ter
m
“
co
n
v
o
lu
ti
o
n
al
f
il
te
r
”
or
“
k
e
r
n
el
”
ag
ain
s
t
th
e
im
p
u
ls
e
r
es
p
o
n
s
e
h
(
t
)
an
d
f
ea
tu
r
e
m
ap
f
o
r
o
u
tp
u
t
s
ig
n
al
y
(
t
)
.
E
ac
h
co
n
v
o
l
u
tio
n
a
l
la
y
er
is
f
o
llo
w
ed
b
y
a
p
o
o
lin
g
la
y
er
an
d
w
e
co
n
s
id
er
an
av
er
ag
e
p
o
o
lin
g
tech
n
iq
u
e.
Nex
t,
th
e
R
ec
ti
f
ie
d
L
in
ea
r
U
n
it
(
R
e
L
U
)
w
o
r
k
s
as
an
ac
ti
v
atio
n
f
u
n
ctio
n
li
k
e
th
e
th
r
e
s
h
o
ld
o
f
s
ig
n
al.
T
h
e
o
u
tp
u
t
o
f
t
h
e
R
e
L
U
i
s
co
n
n
ec
ted
to
a
f
u
ll
y
co
n
n
ec
ted
NN
to
p
r
o
d
u
ce
f
ea
t
u
r
e
co
r
r
esp
o
n
d
in
g
to
h
y
p
o
t
h
esi
s
H
0
an
d
H
1
as
s
h
o
w
n
in
Fi
g
u
r
e
3
.
T
h
e
r
ec
eiv
ed
s
ig
n
al
at
F
C
f
r
o
m
s
e
v
er
al
SUs
a
r
e
co
n
v
er
ted
in
to
an
i
m
a
g
e.
T
h
e
n
o
i
s
y
i
m
a
g
e
is
ap
p
lied
to
C
NN
to
tak
e
th
e
d
ec
is
io
n
ab
o
u
t
t
h
e
p
r
esen
ce
o
r
ab
s
en
ce
o
f
a
P
U
ta
k
in
g
th
e
ex
p
r
es
s
io
n
as
s
h
o
w
n
in
(
4
)
an
d
(
8
)
o
f
SIN
R
o
f
s
in
g
le
u
s
e
r
an
d
m
u
l
tiu
s
er
m
o
d
el
o
f
[
2
7
-
28
].
Fig
u
r
e
3.
B
asic b
u
ild
in
g
b
lo
ck
o
f
C
NN
to
r
ec
o
g
n
ize
s
i
g
n
al
at
FC
2
.
5
.
1.
Si
m
u
la
t
io
n a
lg
o
rit
h
m
a)
Set th
e
li
n
k
p
ar
a
m
eter
s
as
m
e
n
tio
n
in
r
es
u
lt
s
ec
tio
n
a
n
d
ε
=
2
b)
Ass
i
g
n
th
e
tr
a
n
s
m
itted
p
o
w
er
,
P
=r
an
d
(
)
; %
av
er
ag
e
p
o
w
er
o
f
0
.
5
u
n
d
er
H
0
c)
N=
4
9
; %
s
ize
o
f
i
m
a
g
e
is
4
9
×
4
9
f
o
r
i=1
:N
f
o
r
j
=1
:N
Sto
r
e
SIN
R
f
o
r
m
u
lti
u
s
er
as,
Ga
m
m
a_
m
(
i,
j
)
u
s
i
n
g
eq
.
(
8
)
o
f
[
2
7
]
Sto
r
e
SIN
R
f
o
r
s
i
n
g
le
u
s
er
as,
Ga
m
m
a_
s
(
i,
j
)
u
s
in
g
eq
.
(
4
)
,
o
f
[
2
7
]
as m
e
n
tio
n
ed
b
ef
o
r
e
en
d
en
d
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
I
mp
r
o
vin
g
s
ig
n
a
l
d
etec
tio
n
a
c
cu
r
a
cy
a
t F
C
o
f a
C
R
N
u
s
in
g
ma
ch
in
e
lea
r
n
in
g
…
(
Md
A
b
u
l
K
a
la
m
A
z
a
d
)
1145
d)
R
ep
ea
t step
c
tak
i
n
g
,
P
=
r
an
d
(
)
+5
; %
av
er
ag
e
P
o
w
er
o
f
5
u
n
d
er
H
1
e)
R
ep
ea
t step
a
to
d
f
o
r
ε
=
2
.
2
5
an
d
2
.
5
f)
C
r
ea
te
i
m
a
g
e
f
o
r
m
atr
ice
s
G
a
mm
a
_
s
an
d
G
a
mm
a
_
m
g)
Sto
r
e
1
0
im
a
g
es
f
o
r
ea
ch
ca
teg
o
r
y
in
a
f
o
ld
er
h)
A
p
p
l
y
t
h
e
i
m
ag
e
to
a
C
NN
tak
in
g
ap
p
r
o
p
r
iate
p
ar
am
eter
o
f
NN.
i)
A
cq
u
ir
e
th
e
f
ea
tu
r
e
s
o
f
t
h
e
i
m
ag
e
an
d
tak
e
d
ec
i
s
io
n
ab
o
u
t
h
y
p
o
t
h
esi
s
H
0
o
r
H
1
3.
RE
SU
L
T
S
A
ND
D
IS
CU
SS
I
O
N
First
,
w
e
co
n
ce
n
tr
ate
o
n
t
h
e
r
esu
lt
s
o
f
Fu
zz
y
w
ei
g
h
ted
r
u
l
e.
Ho
w
ev
er
,
o
u
r
p
r
i
m
e
f
o
cu
s
is
o
n
th
e
r
esu
lt
s
o
f
f
o
u
r
m
ac
h
i
n
e
lear
n
i
n
g
tech
n
iq
u
e
s
.
Her
e
,
w
e
co
n
s
i
d
er
f
o
u
r
SUs
as
r
ela
y
s
ta
tio
n
u
n
d
er
a
F
C
.
O
n
l
y
a
f
e
w
r
ec
ei
v
ed
d
ata
u
n
d
er
h
y
p
o
th
esi
s
H
1
a
n
d
H
0
ar
e
s
h
o
w
n
in
T
ab
le
1
.
A
b
o
u
t
100
d
ata
s
ets
r
ep
r
esen
ti
n
g
th
e
r
ec
eiv
ed
s
i
g
n
al
u
n
d
er
a
R
a
y
l
eig
h
f
ad
i
n
g
ch
a
n
n
el
alo
n
g
with
A
W
GN
li
k
e
[
29
]
ar
e
tak
en
f
o
r
s
i
m
u
la
tio
n
.
W
o
r
k
in
g
o
n
1
2
d
ata
s
et
(
ea
ch
d
ata
s
et
co
n
tai
n
s
1
0
0
r
ec
o
r
d
s
lik
e
T
ab
le
1
)
,
w
e
g
et
t
h
e
o
u
tco
m
e
o
f
F
u
zz
y
w
ei
g
h
ted
r
u
le
f
o
r
f
iv
e
d
i
f
f
er
e
n
t e
x
p
er
i
m
e
n
ts
o
n
s
i
m
u
lated
s
ig
n
al
as s
h
o
w
n
in
T
ab
le
3
.
T
h
e
n
ex
t
p
ar
t
o
f
th
e
ex
p
er
i
m
e
n
t
d
ea
ls
w
ith
FIS.
T
h
e
s
ig
n
al
v
ec
to
r
s
co
r
r
esp
o
d
in
g
to
s
ec
tio
n
2
.
2
ar
e
s
h
o
w
n
i
n
T
ab
le
4
f
o
r
b
o
th
H
0
an
d
H
1
u
s
i
n
g
1
6
-
Q
A
M
s
i
g
n
al
w
it
h
A
W
GN
a
n
d
R
a
y
leig
h
f
a
d
in
g
o
f
[
30
]
at
F
C
,
an
d
s
i
m
u
la
tio
n
is
d
o
n
e
5
0
0
ti
m
es
f
o
r
ea
ch
h
y
p
o
th
e
s
is
a
n
d
o
n
l
y
9
o
f
th
e
m
ar
e
s
h
o
w
n
.
T
h
e
v
er
if
icatio
n
o
f
Fu
zz
y
r
u
le
s
i
s
ca
r
r
ied
o
u
t
a
g
ain
s
t
H
0
a
n
d
H
1
w
it
h
t
h
r
ee
n
u
m
er
ica
l
v
a
lu
e
s
f
o
r
v
ec
to
r
V
as
V
1
=
[
1
0
.
0
1
9
8
0
.
0
5
8
8
0
.
1
8
0
6
]
an
d
Ou
t
p
u
t
≈
0
(
H
0
);
V
2
=
[
1
0
.
8
0
3
9
0
.
6
0
6
9
0
.
4
1
6
8
]
an
d
O
u
tp
u
t
≈
1
(
H
1
);
an
d
V
3
=
[
0
.
6
0
8
2
0
.
1
9
8
9
1
0
.
3
6
4
9
]
an
d
Ou
tp
u
t
≈
0
(
H
0
)
,
r
esp
ec
tiv
el
y
.
T
ab
le
3
.
Sig
n
al
d
etec
tio
n
w
it
h
Fu
zz
y
w
ei
g
h
ted
r
u
le
Ex
p
e
r
i
me
n
t
N
o
.
D
e
t
e
c
t
i
o
n
o
f
H
0
(
2
S
U
s a
t
F
C
)
D
e
t
e
c
t
i
o
n
o
f
H
1
(
2
S
U
s a
t
F
C
)
D
e
t
e
c
t
i
o
n
o
f
H
0
(
4
S
U
s a
t
F
C
)
D
e
t
e
c
t
i
o
n
o
f
H
1
(
4
S
U
s a
t
F
C
)
1
0
.
8
3
2
0
.
8
5
8
0
.
8
7
3
0
.
8
9
2
2
0
.
8
0
3
0
.
8
6
9
0
.
8
8
6
0
.
8
8
3
3
0
.
8
3
8
0
.
8
7
6
0
.
8
6
5
0
.
8
7
4
4
0
.
8
4
7
0
.
8
1
1
0
.
8
6
9
0
.
8
6
7
5
0
.
8
2
3
0
.
8
3
2
0
.
8
4
7
0
.
8
8
1
T
ab
le
4
.
Sig
n
al
v
ec
to
r
s
f
o
r
FIS
C
0
C
1
C
2
C
3
H
1
C
0
C
1
C
2
C
3
H
0
0
.
1
5
0
0
0
.
1
4
4
5
1
.
0
0
0
0
0
.
0
4
2
6
1
1
.
0
0
0
0
0
.
0
1
9
8
0
.
0
5
8
8
0
.
1
8
0
6
0
0
.
2
1
4
0
0
.
8
8
1
1
0
.
6
4
0
2
1
.
0
0
0
0
1
1
.
0
0
0
0
0
.
0
2
3
3
0
.
1
3
4
8
0
.
1
8
5
6
0
1
.
0
0
0
0
0
.
0
1
4
8
0
.
2
1
7
7
0
.
0
8
4
5
1
0
.
9
4
6
7
0
.
2
6
6
0
0
.
0
7
5
6
1
.
0
0
0
0
0
0
.
2
4
5
8
0
.
1
4
9
3
1
.
0
0
0
0
0
.
5
7
0
3
1
1
.
0
0
0
0
0
.
0
8
8
1
0
.
0
3
8
1
0
.
4
1
2
5
0
1
.
0
0
0
0
0
.
8
0
3
9
0
.
6
0
6
9
0
.
4
1
6
8
1
1
.
0
0
0
0
0
.
0
6
8
4
0
.
4
0
5
3
0
.
1
5
5
6
0
1
.
0
0
0
0
0
.
0
5
7
1
0
.
2
5
0
5
0
.
2
5
3
3
1
0
.
6
0
8
2
0
.
1
9
8
9
1
.
0
0
0
0
0
.
3
6
4
9
0
0
.
1
5
6
5
0
.
3
3
3
0
0
.
4
3
2
4
1
.
0
0
0
0
1
1
.
0
0
0
0
0
.
0
2
9
3
0
.
6
6
6
2
0
.
0
9
9
3
0
1
.
0
0
0
0
0
.
3
6
6
7
0
.
1
6
0
1
0
.
1
6
9
8
1
0
.
9
7
9
3
0
.
0
6
9
2
0
.
0
4
3
0
1
.
0
0
0
0
0
1
.
0
0
0
0
0
.
0
1
1
1
0
.
3
3
7
3
0
.
1
4
8
5
1
0
.
6
5
1
7
0
.
5
5
1
1
0
.
7
8
5
5
1
.
0
0
0
0
0
No
w
,
t
h
e
ex
p
er
i
m
e
n
t
d
ea
ls
with
F
u
zz
y
c
-
Me
a
n
s
C
l
u
s
ter
i
n
g
(
FC
MC)
.
T
h
e
s
ca
tter
p
lo
t
o
f
d
ata
s
et
o
f
H
0
,
H
1
an
d
H
0
+
u
n
d
er
FC
M
C
is
s
h
o
w
n
i
n
Fi
g
u
r
e
4
.
Af
t
er
6
1
iter
atio
n
s
,
w
e
g
et
t
h
r
ee
d
is
tin
ct
r
eg
io
n
s
o
n
s
ca
tter
p
lo
t;
w
h
er
e
th
e
f
u
n
ctio
n
U
(
k
)
tak
e
s
th
e
n
u
m
er
ical
v
alu
es
of
U
(
5
6
)
=5
9
4
.
7
3
0
2
0
9
,
U
(
5
7
)
=5
9
4
.
7
3
0
2
0
7
,
U
(
5
8
)
=
5
9
4
.
7
3
0
2
0
5
,
U
(
5
9
)
=5
9
4
.
7
3
0
2
0
4
,
U
(
6
0
)
=
5
9
4
.
7
3
0
2
0
3
,
U
(
6
1
)
=
5
9
4
.
7
3
0
2
0
2
,
w
h
ich
ar
e
v
er
y
clo
s
e.
W
e
r
u
n
s
i
m
u
latio
n
5
0
ti
m
e
s
i
n
M
atlab
v
.
1
8
an
d
g
et
t
h
e
d
ete
cti
o
n
ac
cu
r
ac
y
o
f
7
8
.
2
4
6
%
as
th
e
b
est
ca
s
e
a
n
d
o
f
7
3
.
2
1
5
%
as
t
h
e
w
o
r
s
t
ca
s
e.
I
f
w
e
u
s
e
t
w
o
h
y
p
o
th
e
s
is
m
o
d
e
l
i.e
.
,
ex
cl
u
d
i
n
g
th
e
d
ata
s
e
t
o
f
i
n
ter
m
ed
iate
le
v
el
H
0
+
,
th
e
n
w
e
g
e
t th
e
d
etec
tio
n
ac
cu
r
ac
y
o
f
9
4
.
1
1
3
% a
s
th
e
b
est ca
s
e
an
d
o
f
8
8
.
5
1
2
% a
s
th
e
w
o
r
s
t c
ase.
Nex
t,
w
e
ap
p
l
y
SVM
o
n
t
h
e
s
i
m
u
lated
r
a
n
d
o
m
d
ata
o
f
SI
NR
a
n
d
th
e
co
r
r
esp
o
n
d
i
n
g
s
c
atter
p
lo
t
is
s
h
o
w
n
in
F
ig
u
r
e
5
(
a)
an
d
th
e
r
eg
io
n
o
f
H
0
,
H
1
a
n
d
H
0
+
is
s
h
o
w
n
in
Fi
g
u
r
e
5
(
b
)
.
T
h
e
SVM
s
ee
m
s
to
b
e
m
o
r
e
s
u
cc
e
s
s
f
u
l
ap
p
r
o
ac
h
th
an
th
at
o
f
F
C
M
C
.
T
h
e
s
u
cc
ess
r
ate
f
o
r
2
0
0
r
an
d
o
m
d
ata
is
o
f
9
6
.
2
3
4
%
as
th
e
b
est
ca
s
e
an
d
o
f
9
2
.
6
7
8
% a
s
th
e
w
o
r
s
t c
ase.
Fin
all
y
,
w
e
ap
p
l
y
C
NN
on
r
e
ce
iv
ed
s
i
g
n
a
l
u
n
d
er
R
a
y
lei
g
h
f
ad
in
g
a
n
d
A
W
GN
ch
a
n
n
el
c
ap
tu
r
ed
at
FC
.
W
e
co
n
s
id
er
1
6
-
Q
AM
s
ig
n
al
a
n
d
t
h
e
d
u
r
atio
n
o
f
s
i
x
co
n
s
ec
u
ti
v
e
s
y
m
b
o
ls
a
s
t
i
m
e
s
lo
t.
T
h
e
f
ad
i
n
g
s
i
g
n
al
o
f
len
g
t
h
4
9
0
0
(
o
n
e
ti
m
e
s
lo
t)
is
co
n
v
er
ted
to
an
i
m
ag
e
o
f
4
9
×4
9
u
s
in
g
t
h
e
alg
o
r
it
h
m
o
f
s
ec
tio
n
2
.
5
.1
.
T
h
e
s
ig
n
al
o
f
a
t
i
m
e
s
lo
t
a
n
d
t
h
e
c
o
r
r
es
p
o
n
d
in
g
i
m
a
g
es a
r
e
s
h
o
wn
i
n
F
ig
u
r
e
6
(
a)
an
d
6
(
b
)
u
n
d
e
r
h
y
p
o
t
h
esi
s
H
1
a
n
d
H
0
,
r
esp
ec
tiv
el
y
.
W
e
m
a
k
e
1
0
0
i
m
a
g
es
f
o
r
ea
c
h
ca
te
g
o
r
y
,
a
n
d
t
h
en
ap
p
l
y
d
ee
p
lear
n
in
g
al
g
o
r
ith
m
e.
g
.
,
C
NN.
R
u
n
n
in
g
C
NN
s
e
v
er
al
ti
m
es,
w
e
m
ea
s
u
r
e
th
e
ac
c
u
r
ac
y
o
f
d
etec
tio
n
f
o
r
th
r
ee
ca
s
e
s
as s
h
o
w
n
i
n
Fi
g
u
r
e
7
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
21
,
No
.
2
,
Feb
r
u
ar
y
2
0
2
1
:
1
1
40
-
11
50
1146
Fig
u
r
e
4
.
Scatter
p
lo
t o
f
Fu
zz
y
c
-
m
ea
n
cl
u
s
ter
i
n
g
w
it
h
th
r
ee
d
is
tin
ct
r
e
g
io
n
(
a)
Scatter
p
lo
t o
f
d
ata
s
et
(
b
)
R
eg
io
n
u
s
i
n
g
S
VM
Fig
u
r
e
5
.
Scatter
p
lo
t o
f
t
w
o
h
y
p
o
th
esis
m
o
d
el
u
n
d
er
SVM
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
I
mp
r
o
vin
g
s
ig
n
a
l
d
etec
tio
n
a
c
cu
r
a
cy
a
t F
C
o
f a
C
R
N
u
s
in
g
ma
ch
in
e
lea
r
n
in
g
…
(
Md
A
b
u
l
K
a
la
m
A
z
a
d
)
1147
(
a)
No
is
y
s
i
g
n
al
a
n
d
i
m
a
g
e
u
n
d
er
H
1
(
b
)
No
is
y
s
ig
n
al
a
n
d
i
m
a
g
e
u
n
d
er
H
0
Fig
u
r
e
6
.
16
-
QA
M
s
ig
n
al
a
n
d
co
r
r
esp
o
n
d
in
g
i
m
ag
e
at
F
C
(
a)
W
o
r
s
t c
ase
(
b
)
I
n
ter
m
ed
iate
r
es
u
lt
(
c)
B
est ca
s
e
Fig
u
r
e
7
.
A
cc
u
r
ac
y
o
f
d
etec
tio
n
f
r
o
m
C
NN
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
21
,
No
.
2
,
Feb
r
u
ar
y
2
0
2
1
:
1
1
40
-
11
50
1148
Fin
all
y
,
t
h
e
o
u
tco
m
es
o
f
f
iv
e
d
if
f
er
e
n
t
m
et
h
o
d
s
ar
e
co
m
b
in
ed
to
g
eth
er
to
ac
h
iev
e
a
d
ec
i
s
io
n
ab
o
u
t
th
e
p
r
ese
n
ce
o
r
ab
s
en
ce
o
f
a
P
U
in
C
R
N.
T
o
co
m
b
i
n
e
f
iv
e
m
et
h
o
d
s
,
w
e
u
s
e
t
h
e
f
o
llo
w
i
n
g
al
g
o
r
ith
m
b
ased
o
n
th
e
id
ea
o
f
[
2
9
]:
a)
I
f
th
e
ac
c
u
r
ac
y
o
f
r
ec
o
g
n
itio
n
o
f
i
th
m
et
h
o
d
(
f
o
r
ex
a
m
p
le
S
VM
)
is
a
i
th
en
t
h
e
ac
cu
r
ac
y
v
e
cto
r
o
f
5
m
et
h
o
d
s
is
V
a
= [
a
1
,
a
2
,
a
3
,
a
4
,
a
5
].
b)
No
r
m
a
lize
th
e
ac
c
u
r
ac
y
v
ec
to
r
as,
V
n
= [
a
1
,
a
2
,
a
3
,
a
4
,
a
5
]/
5
1
i
i
a
=
[
b
1
,
b
2
,
b
3
,
b
4
,
b
5
]
c)
Dete
r
m
i
n
e
th
e
e
n
tr
o
p
y
o
f
ele
m
en
ts
o
f
V
n
,
5
1
2
1
l
o
g
i
i
i
b
b
E
,
w
h
ich
h
as t
h
e
m
a
x
i
m
u
m
v
alu
e
o
f
2
.
3
2
1
9
.
d)
I
f
E
>
2
.
2
an
d
m
aj
o
r
ity
o
f
th
e
m
et
h
o
d
s
(
3
o
u
t o
f
f
i
v
e)
h
as
a
i
>0
.
7
5
,
w
e
co
n
s
id
er
t
h
e
d
etec
tio
n
is
co
r
r
ec
t.
e)
R
ep
ea
t a
ll
s
tep
s
M
ti
m
e
an
d
d
eter
m
i
n
e
th
e
r
atio
o
f
co
r
r
ec
t d
ec
is
io
n
a
n
d
M
,
w
h
ic
h
th
e
ac
c
u
r
ac
y
o
f
co
m
b
i
n
ed
m
et
h
o
d
.
f)
T
h
e
co
r
r
ec
t
d
ec
is
io
n
ab
o
u
t
H
0
an
d
H
1
ar
e
av
er
ag
ed
.
T
h
e
co
m
b
i
n
ed
r
es
u
lt
o
f
ab
o
v
e
alg
o
r
it
h
m
is
s
h
o
w
n
in
T
ab
l
e
5
,
w
h
er
e
w
e
f
o
u
n
d
t
h
at
th
e
co
m
b
in
e
d
m
et
h
o
d
g
iv
e
s
a
b
etter
r
esu
lt t
h
an
th
at
o
f
an
y
i
n
d
iv
id
u
al
clas
s
i
f
icatio
n
tech
n
iq
u
e.
T
ab
le
5
.
C
o
m
p
ar
is
o
n
o
f
ex
p
er
i
m
en
tal
r
esu
lts
Ex
p
e
r
i
me
n
t
N
u
m
b
e
r
W
e
i
g
h
t
e
d
F
u
z
z
y
S
y
st
e
m
F
I
S
F
u
z
z
y
c
-
M
e
a
n
s
C
l
u
st
e
r
i
n
g
S
V
M
C
N
N
C
o
mb
i
n
e
d
1
0
.
8
3
6
0
.
8
7
3
0
.
7
8
2
0
.
7
6
3
0
.
8
9
4
0
.
9
6
2
2
0
.
8
1
1
0
.
8
4
9
0
.
7
6
5
0
.
7
2
4
0
.
8
7
3
0
.
9
5
8
3
0
.
8
2
9
0
.
8
8
1
0
.
7
9
1
0
.
7
8
3
0
.
9
0
1
0
.
9
6
7
4
0
.
8
0
2
0
.
8
4
7
0
.
7
5
2
0
.
7
7
2
0
.
8
4
3
0
.
9
2
5
5
0
.
8
6
6
0
.
8
9
1
0
.
7
8
7
0
.
7
8
2
0
.
9
1
3
0
.
9
7
1
4.
CO
NCLU
SI
O
N
I
n
th
is
p
ap
er
,
Fu
zz
y
s
y
s
te
m
a
n
d
f
o
u
r
d
if
f
er
en
t
m
ac
h
i
n
e
lear
n
in
g
tec
h
n
iq
u
es
ar
e
u
s
ed
at
FC
to
d
etec
t
th
e
p
r
esen
ce
o
r
ab
s
en
ce
o
f
a
P
U.
Her
e,
C
NN
s
h
o
w
s
t
h
e
b
est
r
esu
lt
a
m
o
n
g
all
cla
s
s
i
f
icatio
n
tech
n
iq
u
e
s
w
h
er
ea
s
SVM
s
h
o
w
s
t
h
e
w
o
r
s
t.
Ho
w
e
v
er
,
t
h
e
co
m
b
i
n
ed
m
et
h
o
d
g
i
v
es
th
e
b
est cla
s
s
i
f
icat
io
n
o
u
tco
m
e
w
i
th
a
n
ac
cu
r
ac
y
o
f
d
etec
tio
n
ab
o
u
t
9
6
.7
%.
Sti
ll,
w
e
h
av
e
t
h
e
s
co
p
e
to
o
b
s
er
v
e
th
e
p
er
f
o
r
m
an
ce
o
f
o
th
er
m
ac
h
i
n
e
lear
n
in
g
al
g
o
r
ith
m
s
s
u
ch
as
P
r
in
cip
al
C
o
m
p
o
n
e
n
t
An
al
y
s
is
,
L
i
n
ea
r
Dis
cr
i
m
i
n
an
t
An
al
y
s
i
s
,
Sp
ee
d
ed
-
Up
R
o
b
u
s
t
Fea
tu
r
es,
Sca
le
-
I
n
v
ar
i
an
t
Feat
u
r
e
T
r
an
s
f
o
r
m
,
etc.
I
n
f
u
t
u
r
e,
w
e
w
ill
i
n
cl
u
d
e
m
alic
i
o
u
s
u
s
er
attac
k
i
n
to
C
R
N
u
s
i
n
g
th
r
ee
h
y
p
o
t
h
esi
s
m
o
d
el
u
n
d
er
d
if
f
er
e
n
t
m
ac
h
i
n
e
l
ea
r
n
in
g
al
g
o
r
ith
m
s
.
RE
F
E
R
E
NC
E
S
[1
]
Y.
-
C.
Ch
e
n
,
e
t
a
l
.
,
“
G
e
n
e
ra
ti
n
g
w
e
i
g
h
ted
f
u
z
z
y
ru
les
f
ro
m
train
in
g
d
a
ta
f
o
r
d
e
a
li
n
g
w
it
h
th
e
ir
is
d
a
ta
c
las
si
f
ica
ti
o
n
p
ro
b
lem
,”
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
A
p
ll
ied
S
c
ien
c
e
a
n
d
En
g
in
e
e
ri
n
g
,
v
o
l.
4
,
p
p
.
41
-
5
2
,
2
0
0
6
.
[2
]
R.
A
.
M
o
h
a
m
m
a
d
p
o
u
r,
e
t
a
l
.
,
“
F
u
z
z
y
ru
le
-
b
a
se
d
c
las
si
f
ica
ti
o
n
s
y
ste
m
f
o
r
a
ss
e
s
sin
g
c
o
ro
n
a
ry
a
rter
y
d
ise
a
se
,
”
Co
mp
u
t
a
ti
o
n
a
l
a
n
d
M
a
t
h
e
ma
ti
c
a
l
M
e
th
o
d
s i
n
M
e
d
icin
e
,
v
o
l
.
2
0
1
5
,
p
p
.
1
-
8
,
2
0
1
5
.
[3
]
R.
M
.
P
ra
k
a
sh
a
n
d
R.
S
.
S
.
Ku
m
a
ri
,
“
F
u
z
z
y
C
m
e
a
n
s
in
teg
r
a
ted
w
i
th
sp
a
ti
a
l
in
f
o
rm
a
ti
o
n
a
n
d
c
o
n
tras
t
e
n
h
a
n
c
e
m
e
n
t
f
o
r
s
e
g
m
e
n
tatio
n
o
f
M
R
b
ra
in
ima
g
e
s,”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
I
ma
g
in
g
S
y
ste
ms
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l.
2
6
,
p
p
.
1
1
6
-
1
2
3
,
2
0
1
6
.
[4
]
P
.
O.
G
o
k
ten
,
e
t
a
l
.,
“
Us
in
g
f
u
z
z
y
c
-
m
e
a
n
s
c
lu
ste
rin
g
a
l
g
o
rit
h
m
i
n
f
in
a
n
c
ial
h
e
a
lt
h
sc
o
rin
g
,
”
T
h
e
Au
d
it
F
in
a
n
c
ia
r
J
o
u
rn
a
l
,
v
o
l
.
1
5
,
p
p
.
3
8
5
-
3
9
4
,
2
0
1
7
.
[5
]
C.
L
i,
e
t
a
l
.
,
“
Im
a
g
e
se
g
m
e
n
tatio
n
b
a
se
d
o
n
f
u
z
z
y
c
lu
ste
rin
g
with
c
e
ll
u
lar
a
u
to
m
a
ta
a
n
d
f
e
a
tu
re
s
we
ig
h
ti
n
g
,
”
EURA
S
IP
J
o
u
rn
a
l
o
n
Ima
g
e
a
n
d
Vi
d
e
o
Pr
o
c
e
ss
in
g
,
p
p
.
1
-
1
1
,
2
0
1
9
.
[6
]
D.
A
.
Re
y
e
s,
e
t
a
l.
,
“
Clas
si
fy
in
g
h
a
n
d
m
o
v
e
m
e
n
t
in
ten
ti
o
n
s
u
si
n
g
su
rf
a
c
e
EM
G
sig
n
a
ls
a
n
d
S
V
M
,
”
in
2
0
1
9
XX
II
S
y
mp
o
si
u
m o
n
Ima
g
e
,
S
ig
n
a
l
Pro
c
e
ss
in
g
a
n
d
Arti
fi
c
ia
l
Vi
si
o
n
(
S
T
S
IVA
)
,
p
p
.
24
-
26
,
2
0
1
9
.
[7
]
M.
S
.
Re
f
a
h
i,
e
t
a
l.
,
“
ECG
a
rrh
y
th
m
ia
c
las
si
f
ica
ti
o
n
u
sin
g
lea
st
sq
u
a
re
s
tw
in
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
s
,
”
in
2
6
t
h
Ira
n
ia
n
C
o
n
fer
e
n
c
e
o
n
El
e
c
trica
l
En
g
i
n
e
e
rin
g
(
ICEE
2
0
1
8
)
,
p
p
.
1
6
1
9
-
1
6
2
1
,
2
0
1
8
.
[8
]
I.
B.
A
y
d
il
e
k
,
“
Ex
a
m
in
in
g
e
ff
e
c
ts
o
f
th
e
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
s
k
e
rn
e
l
ty
p
e
s
o
n
b
i
o
m
e
d
ica
l
d
a
ta
c
las
sif
i
c
a
ti
o
n
,”
i
n
2
0
1
8
I
n
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Arti
fi
c
ia
l
In
tell
ig
e
n
c
e
a
n
d
Da
t
a
Pro
c
e
ss
in
g
(
IDAP)
,
p
p
.
1
-
4
,
2
0
1
8
.
[9
]
Z.
d
a
n
d
a
n
a
n
d
Z.
Xu
p
i
n
g
,
“
S
V
M
-
b
a
se
d
sp
e
c
tru
m
se
n
sin
g
in
c
o
g
n
it
iv
e
ra
d
io
,
”
in
2
0
1
1
7
th
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
W
ire
les
s Co
mm
u
n
ic
a
ti
o
n
s,
Ne
t
wo
rk
in
g
a
n
d
M
o
b
il
e
Co
m
p
u
t
in
g
,
p
p
.
1
-
4
,
2
0
1
1
.
[1
0
]
Y.
–
D.
H
u
a
n
g
,
e
t
a
l.
,
“
A
F
u
z
z
y
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
a
lg
o
rit
h
m
f
o
r
c
o
o
p
e
ra
ti
v
e
sp
e
c
tru
m
se
n
sin
g
w
it
h
n
o
ise
u
n
c
e
rtain
t
y
,
”
in
2
0
1
6
IEE
E
Glo
b
a
l
Co
mm
u
n
ica
ti
o
n
s C
o
n
fer
e
n
c
e
(
GLOBE
COM
)
,
p
p
.
1
-
6
,
2
0
1
6
.
[1
1
]
O.
P
.
A
w
e
,
e
t
a
l.
,
“
Ei
g
e
n
v
a
lu
e
a
n
d
su
p
p
o
r
t
v
e
c
to
r
m
a
c
h
in
e
tec
h
n
iq
u
e
s
f
o
r
sp
e
c
tru
m
se
n
si
n
g
in
c
o
g
n
it
iv
e
ra
d
io
n
e
tw
o
rk
s,” in
2
0
1
3
C
o
n
fer
e
n
c
e
o
n
T
e
c
h
n
o
l
o
g
ies
a
n
d
Ap
p
li
c
a
ti
o
n
s
o
f
Arti
f
icia
l
I
n
telli
g
e
n
c
e
,
p
p
.
2
2
3
-
227
,
2
0
1
3
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
I
mp
r
o
vin
g
s
ig
n
a
l
d
etec
tio
n
a
c
cu
r
a
cy
a
t F
C
o
f a
C
R
N
u
s
in
g
ma
ch
in
e
lea
r
n
in
g
…
(
Md
A
b
u
l
K
a
la
m
A
z
a
d
)
1149
[1
2
]
Y.
L
u
,
e
t
a
l.
,
“
M
a
c
h
in
e
lea
rn
i
n
g
tec
h
n
iq
u
e
s
w
it
h
p
ro
b
a
b
il
i
ty
v
e
c
to
r
f
o
r
c
o
o
p
e
ra
ti
v
e
sp
e
c
tru
m
se
n
si
n
g
in
c
o
g
n
it
iv
e
ra
d
io
n
e
tw
o
rk
s
,
”
in
IEE
E
W
ire
les
s Co
n
fer
e
n
c
e
a
n
d
Ne
tw
o
rk
in
g
Co
n
fer
e
n
c
e
(
W
CNC 2
0
1
6
)
,
p
p
.
1
-
6,
2
0
1
6
.
[1
3
]
K.
M
.
T
h
il
in
a
,
e
t
a
l.
,
“
M
a
c
h
in
e
lea
rn
in
g
tec
h
n
iq
u
e
s
f
o
r
c
o
o
p
e
ra
ti
v
e
sp
e
c
tru
m
se
n
si
n
g
in
c
o
g
n
it
iv
e
ra
d
io
n
e
tw
o
rk
s
,”
IEE
E
J
o
u
rn
a
l
o
n
S
e
lec
ted
Are
a
s i
n
Co
mm
u
n
ica
t
io
n
s
,
v
o
l.
3
1
,
n
o
.
1
1
,
p
p
.
2
2
0
9
-
2
2
2
1
,
2
0
1
3
.
[1
4
]
M.
Ue
d
a
,
e
t
a
l.
,
“
A
n
a
g
e
e
sti
m
a
ti
o
n
m
e
th
o
d
u
sin
g
3d
-
CNN
f
ro
m
b
ra
i
n
M
RI
im
a
g
e
s
,
”
in
2
0
1
9
IEE
E
1
6
t
h
In
ter
n
a
t
io
n
a
l
S
y
mp
o
si
u
m o
n
B
io
me
d
ica
l
Ima
g
in
g
(
IS
BI
2
0
1
9
)
,
p
p
.
3
8
0
-
3
8
3
,
2
0
1
9
.
[1
5
]
K.
Ja
is
w
a
l
a
n
d
D.
K.
P
a
tel,
“
S
o
u
n
d
c
las
si
f
ica
ti
o
n
u
sin
g
c
o
n
v
o
lu
ti
o
n
a
l
n
e
u
ra
l
n
e
tw
o
rk
s
,
”
in
2
0
1
8
IEE
E
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Clo
u
d
Co
mp
u
ti
n
g
in
Eme
rg
i
n
g
M
a
rk
e
ts
(
CCEM
)
,
pp.
81
-
84
,
2
0
1
8
.
[1
6
]
P.
Ya
n
g
,
e
t
a
l
.
,
“
Dy
n
a
m
ic
sp
e
c
t
ru
m
a
c
c
e
ss
in
c
o
g
n
it
iv
e
ra
d
io
n
e
tw
o
rk
s
u
sin
g
d
e
e
p
re
in
f
o
rc
e
m
e
n
t
lea
rn
i
n
g
a
n
d
e
v
o
lu
ti
o
n
a
ry
g
a
m
e
,
”
in
2
0
1
8
IEE
E/
CIC
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
C
o
mm
u
n
ica
ti
o
n
s
in
Ch
i
n
a
(
ICCC)
,
p
p
.
4
0
5
-
4
0
9
,
2
0
1
8
.
[1
7
]
H.
L
iu
,
e
t
a
l
.
,
“
En
se
m
b
le
d
e
e
p
lea
rn
in
g
b
a
se
d
c
o
o
p
e
ra
ti
v
e
sp
e
c
tru
m
se
n
sin
g
w
it
h
se
m
i
-
so
f
t
sta
c
k
in
g
f
u
sio
n
cen
ter,"
in
2
0
1
9
IEE
E
W
ire
les
s Co
mm
u
n
ic
a
ti
o
n
s a
n
d
Ne
two
rk
in
g
Co
n
fer
e
n
c
e
(
W
CNC)
, p
p
.
1
-
6
,
2
0
1
9
.
[1
8
]
S
.
M
.
T
a
h
e
ri,
e
t
a
l
.
,
“
A
p
p
li
c
a
ti
o
n
o
f
F
u
z
z
y
in
f
e
r
e
n
c
e
s
y
ste
m
s
in
a
rc
h
a
e
o
lo
g
y
,”
in
2
0
1
9
7
t
h
Ira
n
ia
n
J
o
in
t
C
o
n
g
re
ss
o
n
F
u
zz
y
a
n
d
I
n
telli
g
e
n
t
S
y
ste
ms
(
CFIS
)
,
p
p
.
1
-
4
,
2
0
1
9
.
[1
9
]
M
.
A
lras
h
o
u
d
,
“
Hie
ra
rc
h
ica
l
f
u
z
z
y
in
f
e
r
e
n
c
e
s
y
st
e
m
f
o
r
d
iag
n
o
si
n
g
d
e
n
g
u
e
d
ise
a
se
,”
in
2
0
1
9
IEE
E
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
M
u
lt
ime
d
i
a
&
Exp
o
W
o
rk
sh
o
p
s (
ICM
EW
)
,
p
p
.
3
1
-
36
,
2
0
1
9
.
[2
0
]
K.
Ku
sp
ij
a
n
i,
e
t
a
l
.
,
“
F
a
u
lt
c
las
sif
ica
ti
o
n
o
f
in
d
u
c
ti
o
n
m
o
to
r
u
sin
g
d
isc
re
te
wa
v
e
l
e
t
tran
s
f
o
rm
a
n
d
F
u
z
z
y
in
f
e
r
e
n
c
e
s
y
ste
m
,
”
in
2
0
2
0
I
n
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
S
m
a
rt T
e
c
h
n
o
l
o
g
y
a
n
d
A
p
p
li
c
a
ti
o
n
s (
ICo
S
T
A)
,
p
p
.
1
-
6
,
2
0
1
0
.
[2
1
]
M
.
M
a
z
a
n
d
a
ra
n
i
a
n
d
X
.
L
i,
“
F
ra
c
ti
o
n
a
l
F
u
z
z
y
in
f
e
re
n
c
e
s
y
st
e
m
:
T
h
e
n
e
w
g
e
n
e
ra
ti
o
n
o
f
F
u
z
z
y
in
f
e
re
n
c
e
s
y
ste
m
s,”
IEE
E
Acc
e
ss
,
v
o
l.
8
,
p
p
.
1
2
6
0
6
6
-
1
2
6
0
8
2
,
2
0
2
0
.
[2
2
]
M
.
B.
P
a
n
n
a
a
n
d
M
.
I.
Isla
m
,
“
h
u
m
a
n
f
a
c
e
d
e
tec
ti
o
n
b
a
se
d
o
n
c
o
m
b
in
a
ti
o
n
o
f
li
n
e
a
r
re
g
re
ss
io
n
,
P
C
A
a
n
d
F
u
z
z
y
c
-
m
e
a
n
s
c
lu
ste
rin
g
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
In
f
o
rm
a
ti
o
n
S
e
c
u
rity
,
v
o
l
.
1
7
,
n
o
.
7
,
p
p
.
5
7
-
6
2
,
2
0
1
9
.
[2
3
]
X
.
Z
h
a
n
g
,
e
t
a
l
.
,
“
Ro
b
u
st
im
a
g
e
se
g
m
e
n
tatio
n
u
sin
g
F
u
z
z
y
c
-
m
e
a
n
s
c
lu
ste
rin
g
w
it
h
sp
a
ti
a
l
i
n
f
o
rm
a
ti
o
n
b
a
se
d
o
n
t
o
tal
g
e
n
e
ra
li
z
e
d
v
a
riatio
n
,
”
IE
EE
Acc
e
ss
,
v
o
l
.
8
,
p
p
.
9
5
6
8
1
-
9
5
6
9
7
,
2
0
2
0
.
[2
4
]
P
.
Bo
,
e
t
a
l.
,
“
A
c
lo
u
d
a
n
d
c
lo
u
d
sh
a
d
o
w
d
e
tec
ti
o
n
m
e
th
o
d
b
a
se
d
o
n
F
u
z
z
y
c
-
m
e
a
n
s
a
lg
o
rit
h
m
,”
IE
EE
J
o
u
rn
a
l
o
f
S
e
lec
ted
T
o
p
ics
in
Ap
p
li
e
d
Ea
rt
h
Ob
se
rv
a
ti
o
n
s
a
n
d
Rem
o
te
S
e
n
sin
g
,
v
o
l.
1
3
,
p
p
.
1
7
1
4
-
1
7
2
7
,
2
0
2
0
.
[2
5
]
M
.
X
ia
a
n
d
S
.
A
ïssa
,
“
M
o
d
e
li
n
g
a
n
d
A
n
a
l
y
sis
o
f
Co
o
p
e
ra
ti
v
e
Re
la
y
in
g
in
S
p
e
c
tru
m
-
S
h
a
rin
g
Ce
ll
u
lar
S
y
ste
m
s,”
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
Veh
icu
l
a
r
T
e
c
h
n
o
l
o
g
y
,
v
o
l.
6
5
,
n
o
.
1
1
,
p
p
.
9
1
1
2
-
9
1
2
2
,
2
0
1
6
.
[2
6
]
S
.
Y.
Ch
a
g
a
n
ti
,
e
t
a
l.
,
“
Im
a
g
e
cl
a
ss
if
ic
a
ti
o
n
u
sin
g
S
VM
a
n
d
CNN
,
”
in
2
0
2
0
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
C
o
mp
u
ter
S
c
ien
c
e
,
En
g
in
e
e
rin
g
a
n
d
Ap
p
li
c
a
ti
o
n
s (
ICCS
EA
)
,
p
p
.
1
-
5
,
2
0
2
0
.
[2
7
]
M
.
A
.
K.
A
z
a
d
,
e
t
a
l
.,
“
Co
m
p
a
riso
n
o
f
p
e
rf
o
rm
a
n
c
e
o
f
c
o
g
n
it
iv
e
ra
d
io
n
e
tw
o
rk
u
n
d
e
r
sin
g
le
a
n
d
m
u
lt
i
-
u
se
r
sc
e
n
a
rio
,
”
in
2
0
1
9
1
st
I
n
ter
n
a
t
io
n
a
l
Co
n
fer
e
n
c
e
o
n
Ad
v
a
n
c
e
s
in
S
c
ien
c
e
,
En
g
i
n
e
e
rin
g
a
n
d
R
o
b
o
ti
c
s
T
e
c
h
n
o
lo
g
y
(
ICAS
ER
T
2
0
1
9
)
,
p
p
.
1
-
5
,
2
0
1
9
.
[2
8
]
B.
P
.
Am
iru
d
d
in
a
n
d
R.
E.
A
.
Ka
d
ir,
“
CNN
a
rc
h
it
e
c
tu
re
s
p
e
rfo
rm
a
n
c
e
e
v
a
lu
a
ti
o
n
f
o
r
i
m
a
g
e
c
las
sif
ic
a
ti
o
n
o
f
m
o
sq
u
it
o
i
n
i
n
d
o
n
e
sia
,
”
in
2
0
2
0
I
n
ter
n
a
ti
o
n
a
l
S
e
min
a
r
o
n
In
tel
li
g
e
n
t
T
e
c
h
n
o
l
o
g
y
a
n
d
Its
A
p
p
l
ica
ti
o
n
s
(
IS
IT
IA
)
,
p
p
.
223
-
2
2
7
,
2
0
2
0
.
[2
9
]
F.
T
a
b
a
ss
u
m
,
e
t
a
l
.,
“
Hu
m
a
n
f
a
c
e
re
c
o
g
n
it
io
n
w
it
h
c
o
m
b
in
a
ti
on
o
f
DWT
a
n
d
m
a
c
h
in
e
lea
rn
in
g
,
”
J
o
u
rn
a
l
o
f
Kin
g
S
a
u
d
U
n
ive
rs
it
y
-
Co
mp
u
ter
a
n
d
I
n
fo
rm
a
t
io
n
S
c
ien
c
e
s
(
El
se
v
ier
)
,
F
e
b
.
2
0
2
0
.
doi
:
1
0
.
1
0
1
6
/j
.
jk
su
c
i.
2
0
2
0
.
0
2
.
0
0
2
.
[3
0
]
A
.
K
.
A
z
a
d
,
e
t
a
l
.,
“
S
ig
n
a
l
d
e
tec
ti
o
n
o
f
Co
-
o
p
e
ra
ti
v
e
c
o
g
n
it
iv
e
ra
d
io
n
e
tw
o
rk
u
n
d
e
r
n
e
u
ra
l
n
e
tw
o
rk
,
”
J
o
u
rn
a
l
o
f
Co
mp
u
ter
a
n
d
Co
mm
u
n
ica
ti
o
n
s
,
v
o
l.
6
,
n
o
.
9
,
p
p
.
60
-
7
2
,
2
0
1
8
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
M
d
.
Ab
u
l
K
a
la
m
Az
a
d
h
a
s
c
o
m
p
lete
d
h
is
Ba
c
h
e
lo
r
o
f
S
c
ien
c
e
with
Ho
n
o
rs
in
El
e
c
tro
n
ics
a
n
d
Co
m
p
u
ter
S
c
ien
c
e
f
ro
m
J
a
h
a
n
g
ir
n
a
g
a
r
Un
iv
e
rsit
y
,
Dh
a
k
a
,
Ba
n
g
la
d
e
sh
a
n
d
M
a
ste
r
o
f
S
c
ien
c
e
in
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
l
o
g
y
f
ro
m
R
o
y
a
l
In
stit
u
te
o
f
T
e
c
h
n
o
lo
g
y
(K
T
H),
S
we
d
e
n
.
Cu
rre
n
t
ly
,
M
r.
A
z
a
d
is
w
o
rk
in
g
a
s
a
P
ro
f
e
ss
o
r
in
th
e
d
e
p
a
rtm
e
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
&
En
g
in
e
e
rin
g
,
Ja
h
a
n
g
irn
a
g
a
r
Un
iv
e
rsit
y
,
Dh
a
k
a
,
Ba
n
g
lad
e
sh
.
His
re
se
a
r
c
h
in
tere
st
in
c
lu
d
e
s
w
irel
e
ss
n
e
t
w
o
rk
s,
p
a
rti
c
u
larly
in
w
irele
ss
s
e
n
so
r
n
e
t
w
o
rk
s,
A
d
-
Ho
c
n
e
tw
o
rk
s,
a
n
d
m
o
b
il
e
c
o
g
n
it
iv
e
n
e
tw
o
rk
s.
Anu
p
M
a
ju
m
d
e
r
re
c
e
i
v
e
d
h
is
B
.
S
c
.
(Ho
n
o
rs)
a
n
d
M
.
S
c
.
i
n
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
in
e
e
rin
g
f
ro
m
Ja
h
a
n
g
irn
a
g
a
r
Un
iv
e
rsit
y
,
Dh
a
k
a
,
Ba
n
g
lad
e
sh
in
2
0
1
4
a
n
d
2
0
1
5
re
sp
e
c
ti
v
e
ly
.
P
re
v
io
u
sly
,
h
e
w
o
rk
e
d
a
s
a
lec
tu
re
r
in
th
e
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
i
n
e
e
rin
g
,
Da
ff
o
d
il
I
n
tern
a
ti
o
n
a
l
Un
iv
e
rsity
,
Dh
a
k
a
,
Ba
n
g
lad
e
sh
a
n
d
a
lso
w
o
rk
e
d
a
s
a
lec
tu
re
r
a
t
th
e
In
stit
u
te
o
f
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
l
o
g
y
,
No
a
k
h
a
li
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
Un
iv
e
rsit
y
,
No
a
k
h
a
li
,
Ba
n
g
lad
e
sh
.
Cu
rre
n
tl
y
,
h
e
is
w
o
rk
in
g
a
s
a
l
e
c
t
u
re
r
in
th
e
De
p
a
rtm
e
n
t
o
f
Co
m
p
u
ter
S
c
ie
n
c
e
a
n
d
En
g
in
e
e
rin
g
,
Ja
h
a
n
g
in
a
g
a
r
Un
iv
e
rsit
y
,
Dh
a
k
a
,
Ba
n
g
lad
e
sh
.
His
re
se
a
rc
h
in
tere
st
is
f
o
c
u
se
d
o
n
M
a
c
h
i
n
e
L
e
a
rn
in
g
a
n
d
Ex
p
e
rt
S
y
ste
m
,
Da
t
a
M
in
i
n
g
a
n
d
w
irele
ss
n
e
tw
o
rk
.
Evaluation Warning : The document was created with Spire.PDF for Python.