I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
p
ute
r
E
ng
in
ee
ring
(
I
J
E
CE
)
Vo
l.
9
,
No
.
6
,
Dec
em
b
er
201
9
,
p
p
.
5
1
5
9
~
5
1
6
4
I
SS
N:
2
0
8
8
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v9
i
6
.
pp
5
1
5
9
-
5164
5159
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
co
r
e
.
co
m/
jo
u
r
n
a
ls
/in
d
ex
.
p
h
p
/
I
JE
C
E
O
pti
m
e
tric
ana
ly
sis
of 1x
4
arra
y
of circ
ula
r
m
i
crow
a
v
e patch
a
ntennas
f
o
r
m
a
mm
o
g
ra
phic app
l
ica
tions
using
ada
ptive
g
ra
dient
desce
nt
a
lg
o
rith
m
Ojo
O
.
Adeda
y
o
,
M
o
s
es O
luw
a
f
em
i O
ni
bo
no
j
e
,
O
g
un
la
de
M
icha
el
Adeg
o
k
e
De
p
a
rtme
n
t
o
f
El
e
c
tri
c
a
l
El
e
c
tro
n
ic an
d
C
o
m
p
u
ter E
n
g
in
e
e
rin
g
,
C
o
ll
e
g
e
o
f
En
g
in
e
e
rin
g
,
Af
e
B
a
b
a
lo
la Un
iv
e
rsity
A
d
o
Ek
it
i
(A
BU
A
D),
Nig
e
ria
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Feb
2
5
,
2
0
1
9
R
ev
i
s
ed
A
p
r
4
,
2
0
1
9
A
cc
ep
ted
J
u
n
2
,
2
0
1
9
In
tere
st
in
th
e
u
se
o
f
m
icro
wa
v
e
e
q
u
ip
m
e
n
t
f
o
r
b
re
a
st
i
m
a
g
e
r
y
is
o
n
th
e
in
c
re
a
se
o
w
in
g
to
i
ts
sa
f
e
t
y
,
e
a
se
o
f
u
se
a
n
d
f
rien
d
li
e
r
c
o
st
.
Ho
w
e
v
e
r,
so
m
e
o
f
th
e
p
e
rti
n
e
n
t
b
li
g
h
ts
o
f
th
e
d
e
sig
n
a
n
d
o
p
ti
m
iza
ti
o
n
o
f
m
icro
w
a
v
e
a
n
ten
n
a
in
c
l
u
d
e
i
n
ten
siv
e
c
o
n
su
m
p
ti
o
n
o
f
c
o
m
p
u
ti
n
g
re
so
u
rc
e
s,
h
ig
h
p
rice
o
f
so
f
t
w
a
re
a
c
q
u
isit
io
n
a
n
d
v
e
r
y
lar
g
e
o
p
ti
m
iza
ti
o
n
ti
m
e
.
T
h
is
p
a
p
e
r
th
e
re
f
o
re
a
tt
e
m
p
ts
to
a
d
d
re
ss
th
e
se
c
o
n
c
e
r
n
s
b
y
d
e
v
isin
g
a
r
a
p
id
m
e
a
n
s
o
f
d
e
sig
n
in
g
a
n
d
o
p
ti
m
izin
g
th
e
p
e
rf
o
rm
a
n
c
e
o
f
a
1
×
4
a
rra
y
o
f
c
ircu
lar
m
icro
w
a
v
e
p
a
tch
a
n
ten
n
a
f
o
r
b
re
a
st
im
a
g
e
r
y
a
p
p
li
c
a
ti
o
n
s
b
y
d
e
p
l
o
y
in
g
th
e
a
d
a
p
ti
v
e
g
ra
d
ien
t
d
e
sc
e
n
t
a
lg
o
rit
h
m
(
AG
D
A
)
f
o
r
a
c
ircu
m
sp
e
c
tl
y
d
e
sig
n
e
d
a
rti
f
ic
ial
n
e
u
ra
l
n
e
tw
o
rk
.
In
o
r
d
e
r
to
c
ro
ss
v
a
li
d
a
te
th
e
f
in
d
i
n
g
s
o
f
th
is
w
o
rk
,
th
e
re
su
lt
s
o
b
ta
i
n
e
d
u
sin
g
t
h
e
a
d
a
p
t
iv
e
g
ra
d
ien
t
d
e
sc
e
n
t
a
lg
o
ri
th
m
w
a
s
c
o
m
p
a
re
d
w
it
h
th
o
se
o
b
tai
n
e
d
w
it
h
t
h
e
d
e
p
lo
y
m
e
n
t
o
f
th
e
m
u
c
h
re
p
o
rted
L
e
v
e
n
b
e
rg
-
M
a
rq
u
a
rd
t
a
lg
o
rit
h
m
f
o
r
th
e
sa
m
e
d
a
tas
e
t
o
v
e
r
sa
m
e
f
re
q
u
e
n
c
y
ra
n
g
e
a
n
d
train
i
n
g
c
o
n
stra
in
ts.
A
n
a
ly
sis
o
f
th
e
p
e
r
f
o
rm
a
n
c
e
o
f
t
h
e
AG
D
A
n
e
u
ra
l
n
e
tw
o
rk
sh
o
w
s
th
a
t
t
h
e
a
p
p
r
o
a
c
h
is
a
v
iab
le
a
n
d
a
c
c
u
ra
te
tec
h
n
i
q
u
e
f
o
r
ra
p
id
d
e
sig
n
a
n
d
a
n
a
ly
sis
o
f
a
rra
y
s
o
f
c
ircu
lar
m
icro
w
a
v
e
p
a
t
c
h
a
n
ten
n
a
f
o
r
b
re
a
st i
m
a
g
in
g
.
K
ey
w
o
r
d
s
:
B
r
ea
s
t i
m
ag
in
g
Gr
ad
ien
t d
escen
t a
l
g
o
r
ith
m
HFSS
Neu
r
al
n
et
w
o
r
k
P
atch
an
ten
n
a
Co
p
y
rig
h
t
©
2
0
1
9
In
stit
u
te o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts
re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Oj
o
O.
A
d
ed
ay
o
,
Dep
ar
te
m
en
t o
f
E
lectr
ical
E
le
ctr
o
n
ic
an
d
C
o
m
p
u
ter
E
n
g
i
n
ee
r
in
g
,
Af
e
B
ab
alo
la
Un
iv
er
s
it
y
A
d
o
-
E
k
iti
(
A
B
U
A
D)
,
P
MB
5
4
5
4
,
Km
8
.
5
,
Af
e
B
ab
alo
la
W
ay
,
A
d
o
E
k
iti,
E
k
iti Sta
te
Nig
er
ia
.
E
m
ail:
o
j
o
ao
@
ab
u
ad
.
ed
u
.
n
g
1.
I
NT
RO
D
UCT
I
O
N
Ma
x
w
ell
’
s
s
et
o
f
elec
tr
o
m
ag
n
etic
eq
u
atio
n
s
h
a
v
e
b
ee
n
t
h
e
m
ai
n
w
a
y
to
o
b
tain
ac
cu
r
ate
a
n
d
r
eliab
le
s
o
lu
tio
n
s
f
o
r
elec
tr
o
m
a
g
n
etic
r
ad
iatio
n
p
atter
n
p
r
o
b
lem
s
b
ef
o
r
e
th
e
ad
v
e
n
t
an
d
d
ev
elo
p
m
en
t
o
f
co
m
p
u
ter
-
b
ased
s
i
m
u
lat
io
n
s
o
f
t
w
ar
e.
T
h
is
s
o
f
t
w
ar
e
d
esi
g
n
ap
p
r
o
a
ch
h
elp
s
a
g
r
ea
t
d
ea
l
in
s
i
m
p
li
f
y
i
n
g
o
t
h
er
w
is
e
co
m
p
le
x
eq
u
atio
n
s
a
n
d
co
n
d
it
io
n
s
u
p
o
n
w
h
ich
s
o
l
u
tio
n
s
f
o
r
th
e
b
eh
a
v
io
u
r
o
f
r
ad
iatio
n
p
a
tter
n
s
o
f
co
m
p
le
x
s
tr
u
ct
u
r
es
ar
e
b
ased
.
Usi
n
g
s
u
itab
le
o
p
tim
izat
io
n
tech
n
iq
u
e
s
,
th
ese
co
m
p
u
ter
-
aid
ed
s
i
m
u
la
tio
n
s
h
a
v
e
o
p
en
ed
th
e
r
esear
c
h
w
o
r
ld
i
n
to
i
n
ter
es
tin
g
u
n
e
n
d
in
g
p
o
s
s
ib
ilit
ie
s
i
n
t
er
m
s
o
f
s
tr
u
ct
u
r
al
d
esi
g
n
s
lead
in
g
i
n
to
t
h
e
d
esi
g
n
o
f
s
tate
o
f
th
e
ar
t
m
icr
o
w
a
v
e
co
m
p
o
n
en
ts
a
n
d
d
ev
ices
t
h
a
t
in
cl
u
d
e
f
ilter
s
,
r
eso
n
ato
r
s
a
n
d
an
te
n
n
as
[1
,
2]
.
R
es
u
lts
f
r
o
m
t
h
i
s
d
ev
elo
p
m
en
t
h
a
v
e
b
ee
n
e
m
p
lo
y
ed
i
n
m
a
k
in
g
li
f
e
m
u
ch
ea
s
ier
as
t
h
e
y
h
av
e
b
ee
n
d
ep
lo
y
ed
f
o
r
m
ed
ical
ap
p
licatio
n
s
as
i
n
th
e
ca
s
e
o
f
m
ed
ical
i
m
ag
i
n
g
[
3
]
,
n
o
n
i
n
v
asi
v
e
to
m
o
g
r
a
p
h
y
[
4
]
an
d
ca
n
ce
r
d
etec
tio
n
[
3
-
8
]
.
T
h
e
m
aj
o
r
ch
allen
g
e
s
f
ac
i
n
g
t
h
e
co
m
p
u
ter
aid
ed
s
i
m
u
latio
n
s
o
f
h
ig
h
f
r
eq
u
en
c
y
s
tr
u
ct
u
r
es
h
o
w
e
v
er
in
cl
u
d
e
th
e
r
eq
u
ir
e
m
e
n
t
o
f
l
ar
g
e
a
m
o
u
n
t
o
f
co
m
p
u
ti
n
g
r
eso
u
r
ce
s
.
T
h
is
is
o
f
te
n
b
ec
au
s
e
m
u
lti
-
o
b
j
ec
tiv
e
opt
im
izatio
n
o
f
elec
tr
ic
an
d
m
ag
n
et
ic
f
ie
ld
p
atter
n
s
an
d
d
is
tr
ib
u
tio
n
s
ar
o
u
n
d
co
m
p
le
x
s
tr
u
c
tu
r
es
o
f
te
n
r
eq
u
ir
e
a
g
r
ea
t
d
ea
l
o
f
iter
atio
n
s
a
n
d
an
al
y
s
is
.
A
s
a
r
e
s
u
l
t,
t
h
e
q
u
es
t
f
o
r
t
h
e
d
ev
elo
p
m
e
n
t
o
f
ac
c
u
r
ate,
r
ap
id
an
d
les
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
6
,
Dec
em
b
er
2
0
1
9
:
5
1
5
9
-
5
1
6
4
5160
co
m
p
u
tatio
n
al
ly
i
n
te
n
s
i
v
e
ap
p
r
o
ac
h
es
f
o
r
t
h
e
d
esi
g
n
a
n
d
p
er
f
o
r
m
an
ce
an
a
l
y
s
is
o
f
m
i
cr
o
w
av
e
s
tr
u
ctu
r
e
s
r
e
m
ain
s
r
elata
b
le.
T
o
th
is
en
d
,
s
o
f
tco
m
p
u
ti
n
g
tec
h
n
iq
u
e
s
h
a
v
e
co
m
e
a
s
a
h
a
n
d
y
s
o
l
u
tio
n
.
A
r
ti
f
icial
Ne
u
r
al
Net
w
o
r
k
s
(
ANNs)
i
n
p
ar
tic
u
lar
h
av
e
b
ee
n
o
f
g
r
ea
t
u
s
e
i
n
th
is
r
e
g
ar
d
,
w
h
er
ein
t
h
ei
r
v
er
s
atili
t
y
,
co
m
p
u
tatio
n
a
l
ea
s
e,
s
p
ee
d
an
d
ex
ce
llen
t
ca
p
ac
it
y
i
n
s
o
lv
i
n
g
n
o
n
-
li
n
ea
r
p
r
o
b
lem
s
h
a
v
e
b
ee
n
ex
p
lo
ited
f
o
r
t
h
e
d
esi
g
n
o
f
m
i
cr
o
w
av
e
d
ev
ices.
E
f
f
o
r
ts
i
n
th
i
s
d
o
m
ai
n
i
n
cl
u
d
e
th
e
d
ev
elo
p
m
en
t o
f
A
NN
b
ased
tech
n
iq
u
es
f
o
r
t
h
e
c
h
ar
ac
ter
iz
atio
n
o
f
o
r
g
an
ic
tis
s
u
es
u
s
in
g
m
icr
o
w
a
v
e
an
ten
n
as
[
9
,
10
]
.
Si
m
ilar
s
u
cc
es
s
f
u
l
A
N
N
-
b
ased
w
o
r
k
s
th
a
t
ar
e
e
v
en
m
o
r
e
r
elata
b
le
to
t
h
e
d
o
m
a
in
o
f
th
is
p
ap
er
i
n
clu
d
e
[
1
1
,
1
2
]
w
h
er
e
i
n
th
e
p
er
f
o
r
m
a
n
ce
s
o
f
ca
n
ce
r
d
etec
tin
g
m
icr
o
w
a
v
e
a
n
ten
n
a
s
w
er
e
i
m
p
r
o
v
ed
u
s
in
g
t
h
e
co
m
p
u
ti
n
g
p
r
o
w
e
s
s
o
f
m
as
s
i
v
el
y
co
n
n
ec
ted
co
m
p
u
ti
n
g
ar
ti
f
icial
n
o
d
es.
T
h
e
p
er
f
o
r
m
a
n
ce
o
f
A
N
Ns
is
n
e
v
er
th
e
less
d
ep
en
d
en
t
o
n
t
h
e
n
et
w
o
r
k
ar
ch
itect
u
r
e
as
w
ell
as
th
e
e
f
f
icien
c
y
o
f
t
h
e
tr
ain
in
g
a
lg
o
r
ith
m
e
m
p
lo
y
ed
.
T
h
is
w
o
r
k
th
er
ef
o
r
e
e
x
p
lo
r
es
th
e
e
f
f
icie
n
c
y
o
f
t
h
e
ad
ap
tiv
e
g
r
ad
ien
t
d
esce
n
t
al
g
o
r
ith
m
f
o
r
th
e
o
p
ti
m
e
tr
ic
an
d
p
er
f
o
r
m
a
n
ce
an
al
y
s
i
s
o
f
a
1
×4
ar
r
a
y
o
f
cir
cu
lar
m
icr
o
w
a
v
e
an
ten
n
a
f
o
r
m
a
m
m
o
g
r
ap
h
ic
ap
p
licatio
n
s
.
2.
RE
S
E
ARCH
M
E
T
H
O
D
T
h
e
p
r
o
ce
d
u
r
e
in
v
o
l
v
ed
in
t
h
i
s
w
o
r
k
in
c
lu
d
es
t
h
e
d
esi
g
n
an
d
s
i
m
u
latio
n
o
f
t
h
e
an
te
n
n
a
ar
r
ay
a
s
w
el
l
as
t
h
e
b
r
ea
s
t
ti
s
s
u
e
p
r
o
to
t
y
p
e
.
An
ad
ap
ti
v
e
g
r
ad
ien
t
d
esce
n
t
al
g
o
r
ith
m
w
as
th
e
n
d
ep
lo
y
ed
o
n
an
A
r
ti
f
icial
Neu
r
al
Net
w
o
r
k
w
i
th
t
h
e
ai
m
o
f
ac
cu
r
atel
y
a
n
d
s
u
f
f
ic
ien
tl
y
m
o
d
eli
n
g
th
e
elec
tr
o
m
ag
n
etic
p
r
o
b
lem
.
2
.
1
.
T
he
a
nte
nn
a
a
rr
a
y
T
h
e
p
h
y
s
ical
co
n
f
ig
u
r
atio
n
o
f
th
e
a
n
ten
n
a
co
n
s
is
ts
o
f
a
1
×4
ar
r
ay
o
f
cir
cu
lar
p
atc
h
an
ten
n
a
as
s
h
o
w
n
in
Fi
g
u
r
e
1
w
h
ich
w
er
e
o
p
tim
ized
to
o
b
tain
th
e
g
ain
an
d
p
o
w
er
s
u
itab
le
f
o
r
b
r
ea
s
t
i
m
a
g
er
y
an
d
o
th
er
m
icr
o
w
av
e
m
a
m
m
o
g
r
ap
h
ic
a
p
p
licatio
n
s
.
A
t
a
s
w
ee
p
f
r
eq
u
en
c
y
r
an
g
e
o
f
to
,
th
e
an
ten
n
a
r
ad
iatio
n
p
atter
n
w
as
o
b
tain
ed
an
d
th
e
p
ar
am
eter
o
p
ti
m
izati
o
n
w
as
ca
r
r
ied
o
u
t
in
o
r
d
er
to
ac
q
u
ir
e
th
e
elec
tr
ic
f
ield
a
n
d
m
a
g
n
e
tic
f
ield
d
is
tr
i
b
u
tio
n
o
f
th
e
an
te
n
n
a
ar
r
a
y
.
T
h
is
in
f
o
r
m
at
io
n
,
to
g
et
h
er
w
it
h
th
e
c
u
r
r
en
t
d
en
s
it
y
d
is
tr
ib
u
tio
n
d
ata
ca
n
t
h
e
n
b
e
u
s
ed
f
o
r
an
te
n
n
a
ca
lib
r
atio
n
an
d
ch
ar
ac
ter
izatio
n
o
f
t
h
e
h
u
m
a
n
b
r
ea
s
t
ti
s
s
u
e
u
n
d
er
r
eg
u
lated
p
o
w
er
an
d
f
r
e
q
u
en
c
y
.
T
h
e
p
r
o
p
er
ties
an
d
d
i
m
en
s
io
n
s
o
f
v
ar
io
u
s
co
m
p
o
n
e
n
ts
a
n
d
s
u
b
s
ec
tio
n
s
o
f
th
e
a
n
ten
n
a
ar
e
lis
ted
i
n
T
a
b
le
1
.
Fig
u
r
e
1
.
Stru
ct
u
r
e
o
f
th
e
a
n
te
n
n
a
ar
r
a
y
T
ab
le
1
.
Dim
e
n
s
io
n
s
a
n
d
p
r
o
p
er
ties
o
f
v
ar
io
u
s
co
m
p
o
n
e
n
ts
o
f
th
e
d
esi
g
n
M
A
T
ER
I
A
L
P
R
O
P
ER
TI
ES
C
O
M
P
O
N
EN
T
D
I
M
EN
S
I
O
N
/
L
O
C
A
TI
O
N
(
mm
)
R
e
l
a
t
i
v
e
P
e
r
mi
t
t
i
v
i
t
y
R
e
l
a
t
i
v
e
P
e
r
me
a
b
i
l
i
t
y
B
u
l
k
C
o
n
d
u
c
t
i
v
i
t
y
M
a
ss
D
e
n
si
t
y
F
R
4
_
e
p
o
x
y
4
.
4
1
0
1
9
0
0
S
u
b
s
t
r
a
t
e
X
=
-
6
7
.
0
7
5
Y
=
-
2
4
0
.
7
Z
=
1
.
6
V
a
c
u
u
m
1
1
0
0
R
a
d
i
a
t
i
o
n
B
o
x
X
=
-
1
2
9
.
5
7
5
Y
=
-
3
0
3
.
2
Z
=
-
6
4
.
1
C
o
p
p
e
r
S
h
e
e
t
s
1
0
.
9
9
9
9
9
1
5
8
0
0
0
0
0
0
S
i
e
me
n
s/
m
8
9
3
3
S
o
u
r
c
e
X
-
A
x
i
s
Y
=
-
3
Z
=
-
1
.
6
1
0
.
9
9
9
9
9
1
5
8
0
0
0
0
0
0
S
i
e
me
n
s/
m
8
9
3
3
P
a
t
c
h
R
a
d
i
u
s
-
17
1
0
.
9
9
9
9
9
1
5
8
0
0
0
0
0
0
S
i
e
me
n
s/
m
8
9
3
3
G
r
o
u
n
d
Z
-
A
x
i
s
X
=
-
6
7
.
0
7
5
Y
=
-
2
4
0
.
7
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:
2
0
8
8
-
8708
Op
timetr
ic
a
n
a
lysi
s
o
f 1
x4
a
r
r
a
y
o
f c
ir
cu
la
r
micro
w
a
ve
p
a
tc
h
a
n
ten
n
a
s
…
(
Ojo
A
d
ed
a
y
o
)
5161
2
.
2
.
Ada
ptiv
e
g
ra
dient
des
ce
nt
a
lg
o
rit
h
m
(
A
G
DA)
T
h
e
o
v
er
all
ai
m
o
f
Gr
ad
ien
t
Descen
t
A
l
g
o
r
ith
m
is
to
r
ed
u
ce
th
e
er
r
o
r
f
u
n
ct
io
n
,
E
o
p
p
o
s
ite
to
th
e
d
ir
ec
tio
n
to
t
h
e
er
r
o
r
g
r
ad
ien
t
i
n
o
r
d
er
to
s
u
cc
e
s
s
i
v
el
y
ap
p
r
o
a
ch
th
e
m
in
i
m
u
m
ac
h
ie
v
ab
le
er
r
o
r
f
u
n
ctio
n
[
1
3
]
.
T
h
e
Gr
ad
ien
t
Descen
t
A
l
g
o
r
ith
m
s
h
o
w
i
n
g
t
h
e
d
ir
ec
tio
n
o
f
t
h
e
er
r
o
r
g
r
ad
i
en
t
a
n
d
t
h
e
m
in
i
m
a
w
it
h
r
esp
ec
t to
la
y
er
w
ei
g
h
ts
W
i a
n
d
W
j is illu
s
tr
ated
o
n
a
s
u
r
f
ac
e
p
lo
t a
n
d
s
h
o
w
n
i
n
Fi
g
u
r
e
2
.
G
l
o
b
a
l
m
i
n
i
m
a
L
o
c
a
l
m
i
n
i
m
a
Fig
u
r
e
2
.
I
llu
s
tr
atio
n
o
f
th
e
g
r
ad
ien
t d
escen
t e
r
r
o
r
s
u
r
f
ac
e
T
h
e
ch
an
g
e
i
n
t
h
e
er
r
o
r
f
u
n
c
ti
o
n
w
ith
r
esp
ec
t to
th
e
n
et
w
o
r
k
w
ei
g
h
ts
i
s
w
r
i
tten
a
s
:
(
1
)
W
h
er
e
is
th
e
co
n
n
ec
ti
n
g
w
e
ig
h
t f
r
o
m
th
e
h
id
d
en
la
y
er
to
th
e
o
u
tp
u
t la
y
er
.
T
h
is
ca
n
also
b
e
r
e
-
w
r
itte
n
as:
(
2
)
(
)
(
3
)
A
l
s
o
,
th
e
n
e
t
w
o
r
k
o
u
tp
u
t
is
ex
p
r
ess
ed
as:
∑
(
4
)
T
h
er
ef
o
r
e,
∑
(
5
)
(
)
(
6
)
T
o
ar
r
iv
e
at
a
g
lo
b
al
s
o
lu
tio
n
,
th
e
w
ei
g
h
t
co
r
r
ec
tio
n
m
u
s
t
o
p
p
o
s
e
th
e
d
ir
ec
tio
n
o
f
th
e
er
r
o
r
g
r
ad
ien
t;
th
e
ch
a
n
g
e
in
w
ei
g
h
t c
an
t
h
u
s
b
e
w
r
itte
n
as:
(
)
(
7
)
C
o
n
s
eq
u
en
tl
y
,
t
h
e
n
e
w
w
eig
h
t
is
ex
p
r
ess
ed
as:
(
)
(
8
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
6
,
Dec
em
b
er
2
0
1
9
:
5
1
5
9
-
5
1
6
4
5162
I
n
s
u
m
m
ar
y
,
A
G
D
A
is
a
n
ANN
tr
ain
i
n
g
al
g
o
r
ith
m
t
h
at
ad
ap
ts
th
e
v
a
lu
e
o
f
i
ts
lear
n
in
g
r
ate,
w
ei
g
h
t
an
d
b
ias
as
in
f
o
r
m
ed
b
y
g
r
ad
ien
t
d
escen
t.
T
h
e
in
itia
l
er
r
o
r
an
d
o
u
tp
u
t
o
f
t
h
e
n
et
w
o
r
k
ar
e
f
ir
s
t
co
m
p
u
ted
f
o
r
ea
ch
ep
o
ch
,
an
d
th
e
n
e
w
b
iases
,
o
u
tp
u
t
s
an
d
w
eig
h
t
s
ar
e
co
m
p
u
ted
w
it
h
th
e
cu
r
r
en
t
lear
n
i
n
g
r
ate.
T
h
e
alg
o
r
ith
m
r
eq
u
ir
es
th
a
t
i
f
th
e
n
e
w
l
y
co
m
p
u
ted
er
r
o
r
is
g
r
ea
ter
th
an
th
e
p
r
e
v
io
u
s
er
r
o
r
b
y
m
o
r
e
t
h
an
a
s
et
v
alu
e
,
th
e
n
e
w
b
ia
s
es
an
d
weig
h
ts
ar
e
d
is
ca
r
d
ed
an
d
th
e
lear
n
in
g
r
ate
is
r
ed
u
ce
d
b
y
a
f
ac
to
r
else,
th
e
n
e
w
p
ar
a
m
eter
s
ar
e
r
etai
n
ed
.
I
n
th
is
w
a
y
,
a
s
et
o
f
n
et
wo
r
k
w
eig
h
t
s
a
n
d
b
iases
ar
e
o
b
tain
ed
w
h
ic
h
y
ield
s
th
e
o
u
tp
u
t
w
it
h
th
e
clo
s
est
v
alu
es
to
th
e
tar
g
et
f
o
r
th
e
p
r
o
b
lem
ter
r
ain
.
Fo
r
th
is
w
o
r
k
th
e
v
al
u
es
o
f
an
d
ar
e
1
.
0
4
an
d
0
.
7
r
esp
ec
tiv
ely
.
T
h
ese
v
a
lu
e
s
w
er
e
s
elec
te
d
af
ter
r
ig
o
r
o
u
s
tr
ial
an
d
er
r
o
r
p
r
o
ce
s
s
f
o
r
o
p
tim
u
m
p
er
f
o
r
m
a
n
ce
o
f
t
h
e
a
lg
o
r
ith
m
.
2
.
3
.
T
he
neura
l net
w
o
rk
a
rc
hite
c
t
ure
T
h
e
ar
ch
itectu
r
e
o
f
th
e
ar
tif
ici
al
n
eu
r
al
n
et
w
o
r
k
co
n
s
i
s
ts
o
f
t
h
r
ee
in
p
u
t
la
y
er
n
eu
r
o
n
s
an
d
o
n
e
o
u
tp
u
t
la
y
er
n
e
u
r
o
n
.
T
h
e
to
tal
n
u
m
b
e
r
o
f
h
id
d
en
la
y
er
n
eu
r
o
n
s
w
er
e
v
ar
ied
in
s
tep
s
b
et
w
ee
n
1
0
an
d
4
0
n
eu
r
o
n
s
an
d
th
e
co
r
r
esp
o
n
d
in
g
p
er
f
o
r
m
a
n
c
es
o
f
th
e
n
e
t
w
o
r
k
s
w
er
e
ev
al
u
ated
w
it
h
b
o
th
ad
ap
tiv
e
g
r
ad
i
en
t
d
escen
t
(
A
GD)
an
d
L
e
v
en
b
er
g
-
Ma
r
q
u
ar
d
t
alg
o
r
ith
m
s
.
T
h
e
r
esu
lt
s
o
f
t
h
is
p
r
o
ce
d
u
r
e
ar
e
p
r
esen
ted
in
T
ab
le
4
.
I
n
ea
ch
ca
s
e,
th
e
i
n
p
u
ts
o
f
th
e
n
et
w
o
r
k
co
n
s
is
t o
f
t
h
e
r
ad
iu
s
(
R
)
,
i
n
m
illi
m
eter
,
o
f
th
e
cir
cu
lar
ele
m
e
n
ts
o
f
th
e
a
n
te
n
n
a
ar
r
a
y
,
th
e
ce
n
tr
e
-
to
-
ce
n
tr
e
(
C
T
C
)
s
p
ac
in
g
o
f
t
h
e
cir
cu
lar
ele
m
en
ts
o
f
t
h
e
a
n
ten
n
a
ar
r
a
y
in
m
illi
m
eter
,
an
d
th
e
f
r
eq
u
e
n
c
y
(
F)
in
Gig
a
h
e
r
tz.
T
h
e
tr
ain
in
g
d
ata
w
a
s
o
b
tain
ed
f
r
o
m
r
o
b
u
s
t
a
n
d
in
ten
s
i
v
e
o
p
ti
m
etr
ic
s
i
m
u
lat
io
n
a
n
d
p
er
f
o
r
m
a
n
ce
o
p
ti
m
izatio
n
o
n
H
ig
h
Fre
q
u
en
c
y
Str
u
ct
u
r
e
Si
m
u
latio
n
(
HFSS
)
s
o
f
t
w
ar
e.
T
h
e
tr
ain
in
g
d
ataset,
m
ad
e
u
p
o
f
8
0
0
d
atap
o
in
ts
w
as d
i
v
id
ed
r
an
d
o
m
l
y
in
to
th
r
ee
p
ar
ts
,
o
n
e
p
ar
t
w
h
ich
is
7
0
%
o
f
th
e
d
ata
w
a
s
u
s
ed
f
o
r
th
e
tr
ain
i
n
g
,
an
o
t
h
er
p
ar
t
w
h
ich
i
s
1
5
%
w
as
d
ep
lo
y
ed
f
o
r
th
e
v
al
id
atio
n
an
d
th
e
las
t
p
ar
t
f
o
r
th
e
test
i
n
g
.
T
h
e
u
s
e
o
f
th
is
p
ar
ticu
lar
r
atio
w
as
to
en
s
u
r
e
th
at
t
h
e
n
e
t
w
o
r
k
w
as
tr
a
in
ed
w
ith
s
u
f
f
icie
n
t
d
ata
in
o
r
d
er
to
ac
h
iev
e
g
o
o
d
g
en
er
aliza
tio
n
p
er
f
o
r
m
a
n
ce
as
w
ell
a
s
to
av
o
id
o
v
er
tr
ain
i
n
g
.
3.
RE
SU
L
T
S
A
ND
AN
AL
Y
SI
S
T
h
e
r
ad
iatio
n
p
atter
n
a
n
d
p
e
r
f
o
r
m
an
ce
o
f
th
e
1
×4
cir
cu
l
ar
an
te
n
n
a
ar
r
a
y
w
er
e
ev
al
u
ated
f
r
o
m
a
f
r
eq
u
en
c
y
r
an
g
e
b
et
w
ee
n
an
d
.
T
h
e
r
esu
lts
i
n
ter
m
s
o
f
ce
n
tr
e
f
r
eq
u
e
n
c
y
,
s
tr
u
ctu
r
a
l
co
n
f
i
g
u
r
atio
n
,
f
r
eq
u
e
n
c
y
r
a
n
g
e,
an
d
g
ain
ar
e
co
m
p
ar
ed
ag
ain
s
t
s
i
m
ilar
r
esu
lt
s
in
liter
at
u
r
e
in
s
a
m
e
d
o
m
ai
n
.
T
h
e
r
esu
lt
s
o
f
t
h
is
co
m
p
ar
is
o
n
ar
e
p
r
esen
ted
in
T
ab
le
2
.
Ou
r
o
p
ti
m
ized
a
n
te
n
n
a
ar
r
ay
p
er
f
o
r
m
ed
q
u
it
e
s
atis
f
ac
to
r
il
y
as
e
v
id
en
ce
d
b
y
its
g
ain
o
f
8
.
4
6
d
B
i
w
h
ic
h
is
2
4
.
4
1
%
h
ig
h
er
th
a
n
th
e
h
ig
h
est
g
ai
n
o
f
an
te
n
n
a
s
tr
u
ct
u
r
es
cr
o
s
s
-
co
m
p
ar
ed
.
T
h
is
i
m
p
r
o
v
ed
p
r
o
p
er
ty
is
a
g
o
o
d
q
u
alit
y
f
o
r
m
icr
o
w
a
v
e
a
n
ten
n
as
e
s
p
ec
iall
y
as
it
en
h
a
n
ce
s
t
h
e
r
eso
l
u
tio
n
a
n
d
p
r
ec
is
io
n
w
h
e
n
t
h
e
a
n
te
n
n
a
is
d
ep
lo
y
ed
f
o
r
b
r
ea
s
t
i
m
ag
er
y
a
n
d
o
th
er
m
a
m
m
o
g
r
ap
h
ic
ap
p
licatio
n
s
.
T
ab
le
2
.
C
o
m
p
ar
is
o
n
o
f
th
e
p
e
r
f
o
r
m
an
ce
s
o
f
b
r
ea
s
t i
m
ag
in
g
/
ca
n
ce
r
d
etec
tio
n
an
te
n
n
as
C
e
n
t
r
e
f
r
e
q
u
e
n
c
y
(
G
H
z
)
S
t
r
u
c
t
u
r
e
F
r
e
q
u
e
n
c
y
r
a
n
g
e
(
G
H
z
)
G
a
i
n
(
d
B
i
)
R
e
f
12
C
y
l
i
n
d
r
i
c
a
l
sl
o
t
t
e
d
p
a
t
c
h
a
n
t
e
n
n
a
0
-
20
6
.
4
0
[
1
4
]
2
.
4
5
R
e
c
t
a
n
g
u
l
a
r
p
a
t
c
h
a
n
t
e
n
n
a
w
i
t
h
i
n
se
r
t
g
a
p
_
_
_
_
_
_
[
3
]
1
4
.
2
6
S
q
u
a
r
e
p
a
t
c
h
a
n
t
e
n
n
a
w
i
t
h
T
-
sl
o
t
i
n
g
r
o
u
n
d
p
l
a
n
e
0
–
20
2
.
9
8
[
7
]
5
.
5
P
r
o
x
i
mi
t
y
f
e
d
V
-
sl
o
t
p
a
t
c
h
a
n
t
e
n
n
a
5
-
10
6
.
8
0
[
5
]
2
.
4
5
1
X
4
c
i
r
c
u
l
a
r
p
a
t
c
h
a
n
t
e
n
n
a
a
r
r
a
y
0
-
5
8
.
4
6
T
h
i
s w
o
r
k
Du
r
in
g
t
h
e
o
p
ti
m
izatio
n
p
r
o
ce
d
u
r
e
o
n
HFS
S,
t
h
e
ce
n
tr
e
-
to
-
ce
n
tr
e
(
C
T
C
)
d
is
ta
n
ce
o
f
th
e
f
o
u
r
ele
m
e
n
ts
o
f
th
e
a
n
te
n
n
a
ar
r
a
y
w
a
s
v
ar
ied
f
r
o
m
6
0
m
m
to
6
5
m
m
an
d
t
h
e
r
ad
iu
s
R
o
f
t
h
e
a
r
r
ay
ele
m
e
n
ts
w
a
s
v
ar
ied
f
r
o
m
1
0
m
m
to
2
0
m
m
.
T
h
e
S
-
p
ar
a
m
eter
a
n
d
th
e
v
o
l
tag
e
s
tan
d
i
n
g
w
av
e
r
atio
w
er
e
also
ev
al
u
ated
f
o
r
all
p
o
s
s
ib
le
co
m
b
in
at
io
n
s
o
f
th
e
t
w
o
v
ar
iab
les
w
it
h
in
th
e
in
d
iv
id
u
al
r
an
g
es.
A
f
e
w
o
f
th
e
s
e
r
esu
lts
ar
e
p
r
esen
ted
in
Fi
g
u
r
e
3
(
a
)
an
d
th
e
r
ad
iatio
n
p
atter
n
is
s
h
o
w
n
i
n
Fi
g
u
r
e
3
(
b
)
.
T
h
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
ar
ti
f
icial
n
e
u
r
al
n
e
t
w
o
r
k
p
r
ese
n
t
ed
in
t
h
is
w
o
r
k
(
alr
ea
d
y
d
e
s
cr
ib
ed
in
S
ec
tio
n
2
.
3
)
in
r
esp
o
n
s
e
to
t
h
e
test
in
g
d
ata
i
n
p
u
ts
w
as
e
v
al
u
ated
u
s
in
g
t
h
r
ee
m
aj
o
r
p
er
f
o
r
m
an
ce
e
v
al
u
atio
n
cr
iter
ia:
th
e
r
o
o
t
m
ea
n
s
q
u
ar
e
er
r
o
r
(
R
MSE
)
,
th
e
v
ar
ian
ce
a
cc
o
u
n
t
-
f
o
r
(
VA
F)
a
n
d
th
e
co
ef
f
icien
t
o
f
m
u
l
tip
le
d
eter
m
in
at
io
n
(
C
MD
)
.
T
h
es
e
p
r
o
ce
d
u
r
es
w
er
e
e
x
ec
u
te
d
f
o
r
th
e
n
et
w
o
r
k
f
o
r
b
o
t
h
th
e
A
G
D
an
d
th
e
L
ev
e
n
b
er
g
-
Ma
r
q
u
ar
d
t a
lg
o
r
ith
m
s
an
d
t
h
e
r
esu
lts
ar
e
p
r
esen
ted
in
T
ab
le
3
.
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:
2
0
8
8
-
8708
Op
timetr
ic
a
n
a
lysi
s
o
f 1
x4
a
r
r
a
y
o
f c
ir
cu
la
r
micro
w
a
ve
p
a
tc
h
a
n
ten
n
a
s
…
(
Ojo
A
d
ed
a
y
o
)
5163
(
a)
(
b
)
Fig
u
r
e
3
.
T
h
e
r
esu
lt o
f
th
e
H
F
SS
o
p
ti
m
izatio
n
p
r
o
ce
d
u
r
e
s
h
o
w
i
n
g
,
(
a)
th
e
S
-
p
ar
a
m
eter
,
an
d
(
b
)
th
e
r
ad
iatio
n
p
atter
n
o
f
th
e
an
te
n
n
a
T
ab
le
3
.
P
er
f
o
r
m
a
n
ce
in
d
ice
s
o
f
th
e
al
g
o
r
ith
m
s
f
o
r
th
e
tr
ai
n
i
n
g
,
v
alid
atio
n
a
n
d
test
i
n
g
d
ata
N
e
t
w
o
r
k
T
r
a
i
n
i
n
g
T
e
st
i
n
g
T
r
a
i
n
i
n
g
V
A
F
V
a
l
i
d
a
t
i
o
n
V
A
F
C
M
D
VAF
R
M
S
E
A
G
D
A
_
A
N
N
9
6
.
1
1
9
7
.
2
3
0
.
9
6
6
6
9
4
.
8
1
3
.
9
8
L
M
_
A
N
N
9
7
.
0
7
9
3
.
7
5
4
.
7
7
I
t
ca
n
b
e
o
b
s
er
v
ed
th
at,
in
co
m
p
ar
is
o
n
w
i
th
t
h
e
L
e
v
e
n
b
er
g
-
Ma
r
q
u
ar
d
t
alg
o
r
ith
m
(
L
M
-
A
NN)
,
th
e
A
G
D
al
g
o
r
ith
m
p
er
f
o
r
m
ed
s
atis
f
ac
to
r
il
y
f
o
r
b
o
th
th
e
tr
ain
i
n
g
,
v
al
id
atio
n
a
n
d
test
i
n
g
d
ata
w
h
er
ei
n
i
t
attain
ed
V
A
F
o
f
at
lea
s
t
9
4
.
8
1
an
d
a
m
ax
i
m
u
m
V
AF
o
f
9
7
.
2
3
f
o
r
th
e
v
alid
atio
n
d
ata.
E
v
en
th
o
u
g
h
t
h
e
L
M
-
A
N
N
p
er
f
o
r
m
ed
b
etter
t
h
an
t
h
e
A
GD
A
f
o
r
t
h
e
tr
ai
n
i
n
g
V
AF
f
o
r
e
x
a
m
p
le,
t
h
e
AGD
A
s
till
o
u
tp
er
f
o
r
m
ed
th
e
L
M_
A
NN
f
o
r
th
e
test
in
g
R
MSE
a
n
d
v
alid
atio
n
V
AF.
T
h
is
b
eh
a
v
io
u
r
is
an
i
n
d
icatio
n
th
at,
d
ep
en
d
in
g
o
n
th
e
d
ata
d
is
tr
i
b
u
t
io
n
a
n
d
d
ata
s
tr
u
ct
u
r
e,
A
NN
tr
ai
n
in
g
al
g
o
r
ith
m
s
ar
e
w
ell
s
u
i
ted
to
d
if
f
e
r
en
t
p
r
o
b
lem
s
t
h
an
th
e
o
th
er
,
an
d
t
h
at
th
e
AGD
A
is
w
ell
s
u
ited
to
th
e
m
icr
o
w
av
e
an
ten
n
a
ar
r
a
y
p
r
o
b
le
m
at
h
a
n
d
.
Var
y
in
g
t
h
e
n
u
m
b
er
o
f
h
id
d
e
n
la
y
er
n
eu
r
o
n
s
o
f
t
h
e
n
e
t
w
o
r
k
y
ield
ed
d
if
f
er
en
t
ANN
ar
ch
itect
u
r
e
s
w
it
h
v
ar
y
i
n
g
p
er
f
o
r
m
a
n
ce
s
.
T
h
e
t
w
o
b
est
p
er
f
o
r
m
i
n
g
n
et
w
o
r
k
s
f
r
o
m
t
h
i
s
m
o
d
i
f
ic
atio
n
ar
e
p
r
esen
ted
in
T
ab
le
4
.
Netw
o
r
k
A
h
as 3
2
h
id
d
en
n
e
u
r
o
n
s
w
h
i
le
Net
w
o
r
k
B
h
as 2
8
h
id
d
en
n
e
u
r
o
n
s
.
T
ab
le
4
.
P
er
f
o
r
m
a
n
ce
s
o
f
d
i
f
f
e
r
en
t
A
NN
ar
ch
i
tect
u
r
es
u
s
in
g
A
G
D
A
N
e
t
w
o
r
k
t
y
p
e
V
A
F
v
a
l
u
e
s f
o
r
t
r
a
i
n
i
n
g
d
a
t
a
(
%)
C
M
D
v
a
l
u
e
s fo
r
t
r
a
i
n
i
n
g
d
a
t
a
V
A
F
v
a
l
u
e
s f
o
r
t
e
st
i
n
g
d
a
t
a
(
%)
C
M
D
v
a
l
u
e
s fo
r
t
e
st
i
n
g
d
a
t
a
N
e
t
w
o
r
k
A
0
.
9
1
7
6
9
4
.
8
1
N
e
t
w
o
r
k
B
9
7
.
5
2
0
.
9
0
0
6
9
4
.
0
1
R
es
u
lts
f
r
o
m
th
i
s
p
ap
er
h
a
v
e
s
h
o
w
n
th
a
t
t
h
e
p
er
f
o
r
m
an
ce
o
f
n
e
u
r
al
n
et
w
o
r
k
b
ased
al
g
o
r
ith
m
i
s
lar
g
el
y
b
ased
o
n
a
n
u
m
b
er
o
f
o
th
er
f
ac
to
r
s
m
o
r
e
th
an
t
h
e
s
h
ee
r
ef
f
icie
n
c
y
o
f
t
h
e
f
lo
w
o
f
t
h
e
alg
o
r
ith
m
it
s
elf
.
T
h
ese
f
ac
to
r
s
i
n
cl
u
d
e
th
e
n
e
u
r
al
n
et
w
o
r
k
ar
c
h
itect
u
r
e,
th
e
d
is
tr
ib
u
tio
n
o
f
t
h
e
d
ata
t
h
at
d
ef
i
n
es
t
h
e
p
r
o
b
le
m
at
h
an
d
as
w
el
l a
s
th
e
w
e
ig
h
t i
n
itializa
tio
n
,
ch
o
ice
o
f
t
h
e
lear
n
in
g
r
ate
an
d
t
h
e
ad
ap
tatio
n
th
er
eo
f
.
4.
CO
NCLU
SI
O
N
I
n
th
is
w
o
r
k
,
th
e
c
h
alle
n
g
e
s
ass
o
ciate
d
w
i
th
t
h
e
d
ev
elo
p
m
e
n
t
o
f
r
ap
id
,
ch
ea
p
an
d
ef
f
icien
t
m
o
d
el
s
w
h
ic
h
ar
e
ap
p
licab
le
f
o
r
n
o
n
in
v
a
s
iv
e
m
icr
o
w
a
v
e
ch
ar
ac
t
er
izatio
n
,
m
o
d
elli
n
g
a
n
d
i
m
a
g
in
g
o
f
th
e
h
u
m
a
n
b
r
ea
s
t
w
a
s
ad
d
r
ess
ed
as
a
1
x
4
cir
cu
lar
an
te
n
n
a
ar
r
a
y
o
p
er
atin
g
at
a
n
o
p
ti
m
al
f
r
eq
u
e
n
c
y
o
f
2
.
4
5
GHz
w
a
s
d
esig
n
ed
an
d
an
al
y
s
ed
f
o
r
b
r
ea
s
t
i
m
a
g
i
n
g
ap
p
licatio
n
s
u
s
i
n
g
t
h
e
o
p
ti
m
izatio
n
ap
p
r
o
ac
h
o
f
f
er
ed
b
y
th
e
h
ig
h
f
r
eq
u
en
c
y
s
tr
u
ct
u
r
e
s
i
m
u
lato
r
(
HFSS
)
s
o
f
t
w
ar
e,
a
3
D
m
o
d
el
o
f
th
e
h
u
m
a
n
b
r
ea
s
t
an
d
ca
r
ef
u
ll
y
d
esi
g
n
ed
ar
tif
icial
n
e
u
r
al
n
et
w
o
r
k
.
T
h
e
ANN
r
es
u
lt
s
w
h
en
co
m
p
ar
e
d
w
it
h
th
e
s
i
m
u
lated
d
ata
u
s
in
g
t
h
r
ee
d
if
f
er
en
t
p
er
f
o
r
m
a
n
ce
in
d
ice
s
y
ield
ed
h
ig
h
ac
c
u
r
ac
y
an
d
i
m
p
r
es
s
iv
e
g
en
er
aliza
tio
n
ab
ilit
y
.
T
h
is
th
er
ef
o
r
e
in
d
icate
s
th
at
th
is
ap
p
r
o
ac
h
r
e
m
ain
s
a
p
r
o
m
is
i
n
g
o
n
e
in
th
e
d
o
m
ai
n
o
f
n
o
n
in
v
a
s
iv
e
b
r
ea
s
t
i
m
a
g
er
y
an
d
g
e
n
er
al
m
a
m
m
o
g
r
ap
h
ic
i
m
a
g
in
g
s
o
l
u
ti
o
n
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
6
,
Dec
em
b
er
2
0
1
9
:
5
1
5
9
-
5
1
6
4
5164
RE
F
E
R
E
NC
E
S
[1
]
S
.
J.
Ch
in
,
M
.
Z
.
A
.
A
.
A
z
iz,
a
n
d
M
.
R.
A
h
m
a
d
,
“
M
icro
strip
-
F
e
d
Circu
lar
Disc
M
o
n
o
p
o
le
A
n
ten
n
a
w
it
h
De
f
e
c
ted
W
a
v
e
g
u
id
e
S
tru
c
tu
re
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
trica
l
a
n
d
Co
mp
u
ter
En
g
in
e
e
rin
g
(
IJ
ECE
)
,
v
o
l.
8
,
n
o
.
1
,
p
p
.
1
8
9
–
1
9
7
,
2
0
1
8
.
[2
]
M
.
T
a
rb
o
u
c
h
,
A
.
El
Am
ri,
a
n
d
H.
T
e
r
c
h
o
u
n
e
,
“
De
sig
n
,
Re
a
li
z
a
t
io
n
a
n
d
M
e
a
su
re
m
e
n
ts
o
f
Co
m
p
a
c
t
Du
a
l
-
b
a
n
d
CP
W
-
f
e
d
P
a
tch
A
n
ten
n
a
f
o
r
2
.
4
5
/5
.
8
0
G
Hz
RF
ID
A
p
p
li
c
a
ti
o
n
s,”
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
El
e
c
trica
l
a
n
d
Co
mp
u
te
r
En
g
i
n
e
e
rin
g
(
IJ
ECE
)
,
v
o
l.
8
,
n
o
.
1
,
p
p
.
1
7
2
–
1
7
8
,
2
0
1
8
.
[3
]
R.
Ça
l,
S
.
S
.
G
ü
lt
e
k
in
,
D.
Uz
e
r,
a
n
d
Ö.
Dü
n
d
a
r,
“
A
M
icro
strip
P
a
t
c
h
A
n
ten
n
a
De
sig
n
f
o
r
Bre
a
st
Ca
n
c
e
r
De
tec
ti
o
n
,
”
Pro
c
e
d
ia
S
o
c
.
Beh
a
v
.
S
c
i
.
,
v
o
l.
1
9
5
,
p
p
.
2
9
0
5
–
2
9
1
1
,
2
0
1
5
.
[4
]
K.
Ou
e
rg
h
i,
N.
F
a
d
lallah
,
A
.
S
m
i
d
a
,
R.
G
h
a
y
o
u
la,
J.
F
a
tt
a
h
i,
a
n
d
N.
Bo
u
lejf
e
n
,
“
Circu
lar
A
n
ten
n
a
A
rra
y
De
si
g
n
f
o
r
Bre
a
st Can
c
e
r
De
tec
ti
o
n
,
”
S
e
n
so
r
s Ne
two
rk
s S
ma
rt E
me
rg
.
T
e
c
h
n
o
l
.
,
n
o
.
1
,
p
p
.
3
–
6
,
2
0
1
7
.
[5
]
M
.
Kh
a
n
,
a
t
a
l.
,
“
UW
B
L
-
P
ro
b
e
P
r
o
x
im
it
y
F
e
d
V
-
S
l
o
t
P
a
tch
A
n
ten
n
a
f
o
r
Early
De
tec
ti
o
n
o
f
Bre
a
st
Ca
n
c
e
r,
”
IEE
E
In
t.
S
y
mp
.
A
n
ten
n
a
s
Pr
o
p
a
g
.
Us
n
.
Na
tl
.
Ra
d
io
S
c
i.
M
e
e
t
.
,
p
p
.
1
8
8
2
–
1
8
8
3
,
2
0
1
5
.
[6
]
T
.
S
h
a
h
a
n
d
E.
S
io
re
s,
W
e
a
ra
b
le
mic
ro
wa
v
e
ra
d
io
me
try
d
e
v
ice
fo
r
e
a
rly
d
e
tec
ti
o
n
o
f
su
b
-
ti
ss
u
e
o
n
c
o
lo
g
ica
l
imp
e
rfe
c
ti
o
n
s
,
W
o
o
d
h
e
a
d
P
u
b
l.
L
td
.
,
p
p
.
4
3
7
–
4
4
8
,
2
0
1
0
.
[7
]
A
.
Afy
f
,
L
.
Be
ll
a
rb
i,
N.
Ya
a
k
o
u
b
i,
E.
G
a
v
io
t,
L
.
Ca
m
b
e
rlein
,
a
n
d
M
.
L
a
trac
h
,
“
No
v
e
l
A
n
ten
n
a
S
tru
c
tu
re
f
o
r
Early
Bre
a
st Can
c
e
r
De
tec
ti
o
n
,
”
Pro
c
e
d
ia
E
n
g
.
,
v
o
l.
1
6
8
,
p
p
.
1
3
3
4
–
1
3
3
7
,
2
0
1
6
.
[8
]
T
.
Hira
n
o
,
a
t
a
l.
,
“
4
x
4
P
e
n
tag
o
n
a
l
P
a
tch
A
rra
y
A
n
ten
n
a
f
o
r
Bre
a
st
Ca
n
c
e
r
De
t
e
c
ti
o
n
,
”
2
0
1
6
IEE
E
Co
n
fer
e
n
c
e
o
n
An
ten
n
a
M
e
a
su
re
me
n
ts
&
Ap
p
li
c
a
ti
o
n
s (
CAM
A)
,
Oc
t
2
0
1
6
.
[9
]
O.
O.
A
d
e
d
a
y
o
,
M
.
M
.
Isa
,
a
n
d
K.
Bu
d
a
y
a
w
a
n
,
“
A
rti
f
icia
l
Ne
u
ra
l
Ne
tw
o
rk
M
o
d
e
l
f
o
r
M
icro
w
a
v
e
P
r
o
p
a
g
a
ti
o
n
i
n
W
a
ter M
e
lo
n
,
”
2
0
1
2
IEE
E
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
C
irc
u
it
s
a
n
d
S
y
ste
ms
(
ICCAS
)
,
n
o
.
6
,
p
p
.
1
4
7
–
1
4
9
,
2
0
1
2
.
[1
0
]
O.
O.
A
d
e
d
a
y
o
,
M
.
M
.
Isa
,
A
.
C.
S
o
h
,
a
n
d
Z.
A
b
b
a
s,
“
Co
m
p
a
riso
n
o
f
F
e
e
d
F
o
rw
a
rd
Ne
u
ra
l
Ne
tw
o
rk
T
ra
in
in
g
A
l
g
o
rit
h
m
s
f
o
r
In
telli
g
e
n
t
M
o
d
e
li
n
g
o
f
Die
le
c
tri
c
P
ro
p
e
rti
e
s
o
f
Oil
P
a
lm
F
ru
it
lets,”
In
t.
J
.
En
g
.
Ad
v
.
T
e
c
h
n
o
l
.
,
v
o
l.
3
,
n
o
.
3
,
p
p
.
3
8
–
4
2
,
2
0
1
4
.
[1
1
]
D.
A
.
W
o
ten
a
n
d
M
.
El
-
S
h
e
n
a
w
e
e
,
“
I
m
p
ro
v
e
m
e
n
t
o
f
A
rti
f
icia
l
N
e
u
ra
l
Ne
tw
o
rk
De
tec
ti
o
n
o
f
Bre
a
st
Ca
n
c
e
r
u
sin
g
Bro
a
d
b
a
n
d
Du
a
l
P
o
lariz
e
d
A
n
ten
n
a
,
”
in
IEE
E
An
te
n
n
a
s
a
n
d
Pr
o
p
a
g
a
ti
o
n
S
o
c
iety
In
ter
n
a
ti
o
n
a
l
S
y
mp
o
siu
m
,
2
0
0
7
,
n
o
.
1
,
p
p
.
2
6
1
–
2
6
4
.
[1
2
]
S
.
A
.
A
lsh
e
h
ri
a
n
d
S
.
Kh
a
tu
n
,
“
UW
B
I
m
a
g
in
g
f
o
r
Bre
a
st
Ca
n
c
e
r
De
te
c
ti
o
n
Us
in
g
Ne
u
ra
l
Ne
t
w
o
rk
,
”
Pro
g
.
El
e
c
tro
ma
g
n
.
Res
.
C
,
v
o
l
.
7
,
p
p
.
7
9
–
9
3
,
2
0
0
9
.
[1
3
]
S
.
E.
P
a
rv
e
e
n
,
G
.
S
a
n
g
e
e
ta,
a
n
d
K.
Dh
a
r
m
in
d
e
r,
“
M
in
im
iza
ti
o
n
o
f
Err
o
r
in
T
ra
in
in
g
a
N
e
u
ra
l
Ne
tw
o
rk
Us
in
g
G
ra
d
ien
t
De
sc
e
n
t
M
e
t
h
o
d
,
”
I
n
t.
J
.
T
e
c
h
.
Res
.
,
v
o
l.
1
,
n
o
.
1
,
p
p
.
1
0
–
1
2
,
2
0
1
2
.
[1
4
]
A
.
I.
I
m
r
a
n
a
n
d
T
.
A
.
El
w
i,
“
En
g
i
n
e
e
rin
g
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
lo
g
y
,
a
n
In
tern
a
ti
o
n
a
l
Jo
u
r
n
a
l
A
c
y
li
n
d
rica
l
w
id
e
b
a
n
d
slo
tt
e
d
p
a
tch
a
n
ten
n
a
lo
a
d
e
d
w
it
h
F
re
q
u
e
n
c
y
S
e
lec
ti
v
e
S
u
rf
a
c
e
fo
r
M
RI
a
p
p
li
c
a
ti
o
n
s,”
In
t
.
J
.
En
g
.
S
c
i.
T
e
c
h
n
o
l
.
,
v
o
l.
2
0
,
p
p
.
9
9
0
–
9
9
6
,
2
0
1
7
.
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
O
jo
O
.
Adeda
y
o
g
ra
d
u
a
ted
f
ro
m
th
e
De
p
a
rt
m
e
n
t
o
f
El
e
c
tro
n
ic
a
n
d
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
in
L
a
d
o
k
e
Ak
in
to
la
Un
iv
e
rsit
y
o
f
Tec
h
n
o
l
o
g
y
(
LA
U
T
ECH)
Ni
g
e
ria
in
2
0
0
8
w
h
e
re
h
e
re
c
e
iv
e
d
h
is
B.
T
e
c
h
d
e
g
re
e
w
it
h
h
o
n
o
u
rs.
He
o
b
tain
e
d
h
is
M
sc
d
e
g
re
e
in
M
i
c
ro
e
lec
tro
n
ics
f
ro
m
Un
iv
e
r
siti
P
u
tra
M
a
lay
sia
(UP
M
)
in
2
0
1
4
.
He
is
c
u
rre
n
tl
y
a
lec
tu
re
r
a
t
t
h
e
d
e
p
a
rtm
e
n
t
o
f
El
e
c
tro
n
ic
El
e
c
tri
c
a
l
a
n
d
Co
m
p
u
ter E
n
g
in
e
e
rin
g
,
Af
e
Ba
b
a
lo
la Un
iv
e
rsit
y
A
d
o
Ek
it
i,
Ek
it
i
S
tate
Nig
e
ria.
He
is
c
u
rre
n
tl
y
p
u
rsu
i
n
g
a
P
h
D
d
e
g
r
e
e
a
t
th
e
De
p
a
rtme
n
t
o
f
El
e
c
tro
n
i
c
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
,
Ek
it
i
S
tate
Un
iv
e
rsity
,
Nig
e
ria.
His
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
c
o
m
m
u
n
ica
ti
o
n
sy
ste
m
s,
m
icro
e
le
c
tro
n
ics
,
so
f
t
c
o
m
p
u
ti
n
g
a
n
d
i
n
telli
g
e
n
t
sy
ste
m
s.
En
g
r
.
Dr
.
M
o
se
s
O
lu
w
a
fe
m
i
O
n
ib
o
n
o
je
is
a
S
e
n
io
r
L
e
c
tu
re
r
in
th
e
De
p
a
rtm
e
n
t
o
f
El
e
c
tri
c
a
l/
El
e
c
tro
n
ics
a
n
d
Co
m
p
u
ter
En
g
in
e
e
rin
g
a
t
A
f
e
Ba
b
a
lo
la
Un
iv
e
rsity
A
d
o
-
Ek
it
i
(A
BU
AD
),
Nig
e
ria.
H
e
sp
e
c
iali
z
e
s
in
Co
n
tro
l
a
n
d
In
str
u
m
e
n
tatio
n
E
n
g
in
e
e
rin
g
.
His
re
se
a
rc
h
a
re
a
s
in
c
lu
d
e
W
ir
e
les
s
S
e
n
so
r
Ne
t
w
o
rk
s,
Distrib
u
ted
S
y
ste
m
s,
W
irele
ss
In
stru
m
e
n
tatio
n
s
,
Op
ti
m
iza
ti
o
n
M
e
th
o
d
s,
a
n
d
A
g
r
o
-
El
e
c
tro
I
n
stru
m
e
n
tatio
n
s.
Dr.
O
n
ib
o
n
o
je
h
o
ld
s
a
P
h
.
D.
i
n
El
e
c
t
ro
n
ic
a
n
d
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
f
ro
m
Ob
a
f
e
m
i
Aw
o
lo
w
o
Un
i
v
e
rsit
y
,
Ile
-
Ife
,
Nig
e
ria.
He
is
COREN Re
g
istere
d
a
n
d
a
Co
rp
o
r
a
te M
e
m
b
e
r
o
f
th
e
Nig
e
rian
S
o
c
ie
ty
o
f
En
g
in
e
e
rs.
O
g
u
n
l
a
d
e
M
ich
a
e
l
A
d
e
g
o
k
e
re
c
e
iv
e
d
th
e
Ba
c
h
e
lo
r
o
f
En
g
in
e
e
rin
g
d
e
g
re
e
in
El
e
c
tri
c
a
l
a
n
d
El
e
c
tro
n
ic E
n
g
in
e
e
ri
n
g
f
ro
m
Un
i
v
e
rsit
y
o
f
A
d
o
Ek
it
i,
Nig
e
ria i
n
2
0
0
8
.
He
o
b
tain
e
d
th
e
M
a
ste
r
o
f
En
g
in
e
e
rin
g
d
e
g
re
e
in
S
ig
n
a
l
a
n
d
In
f
o
rm
a
ti
o
n
P
ro
c
e
ss
in
g
f
ro
m
T
i
a
n
ji
n
Un
iv
e
rsity
o
f
Tec
h
n
o
lo
g
y
a
n
d
Ed
u
c
a
ti
o
n
,
P
.
R.
C
h
in
a
.
He
i
s
a
lec
tu
re
r
a
n
d
a
re
se
a
rc
h
e
r
a
t
Af
e
Ba
b
a
lo
la
Un
iv
e
rsit
y
,
A
d
o
Ek
it
i,
Nig
e
ria.
He
is
c
u
rre
n
tl
y
p
u
rsu
in
g
P
h
D
in
El
e
c
tri
c
a
l
a
n
d
El
e
c
tro
n
ic
En
g
i
n
e
e
rin
g
f
ro
m
E
k
it
i
S
tate
Un
iv
e
rsit
y
,
Nig
e
ria.
H
e
is
a
m
e
m
b
e
r
o
f
th
e
Ce
n
tre
f
o
r
Re
se
a
rc
h
in
El
e
c
tri
c
a
l
Co
m
m
u
n
ica
ti
o
n
(CRECO),
Ek
it
i
S
tate
Un
iv
e
rsit
y
,
A
d
o
Ek
it
i,
Nig
e
ria.
His
re
se
a
rc
h
in
tere
sts
a
r
e
in
th
e
a
re
a
o
f
w
irele
s
s co
m
m
u
n
ic
a
ti
o
n
,
p
o
w
e
r
li
n
e
c
o
m
m
u
n
ica
ti
o
n
,
sig
n
a
l
p
ro
c
e
ss
in
g
,
El
e
c
tro
n
ics
a
n
d
sm
a
rt
A
n
ten
n
a
.
Evaluation Warning : The document was created with Spire.PDF for Python.