I
nte
rna
t
io
na
l J
o
urna
l
o
f
I
nfo
r
m
a
t
ics a
nd
Co
mm
u
n
ica
t
io
n T
ec
hn
o
lo
g
y
(
I
J
-
I
CT
)
Vo
l.
6
,
No
.
1
,
A
p
r
il
201
7
,
p
p
.
1
~9
I
SS
N:
2
2
5
2
-
8
7
7
6
,
DOI
: 1
0
.
1
1
5
9
1
/i
j
ict.
v
6
i1
.
p
p
1
-
9
1
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
jo
u
r
n
a
l.c
o
m/o
n
lin
e/in
d
ex
.
p
h
p
/I
J
I
C
T
Co
m
pa
riso
n of
t
h
e Reson
a
nt
Frequ
ency
Deter
m
ina
ti
o
n of a
M
icro
strip
Pat
ch
Antenna
using
A
NN and
Ana
ly
tical M
ethods
L
a
hcen
Ag
un
i
1
,
Sa
m
ira
Cha
ba
a
2
,
Sa
ida
I
bn
y
a
ich
1
,
Abdel
o
uh
a
b
Z
er
o
ua
l
2
1
De
p
a
rtme
n
t
o
f
P
h
y
sic
s,
Ca
d
i
Ay
y
a
d
Un
iv
e
rsit
y
F
a
c
u
lt
y
o
f
S
c
ien
c
e
s,
S
e
m
lalia M
a
rra
k
e
sh
,
M
o
ro
c
c
o
2
In
d
u
strial
En
g
i
n
e
e
rin
g
De
p
a
rtm
e
n
t,
Na
ti
o
n
a
l
S
c
h
o
o
l
o
f
A
p
p
li
e
d
S
c
ien
c
e
s,
Ib
n
Zo
h
r
Un
iv
e
rsity
,
A
g
a
d
ir,
M
o
r
o
c
c
o
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
an
1
3
,
2
0
1
7
R
ev
i
s
ed
Feb
2
4
,
2
0
1
7
A
cc
ep
ted
Mar
15
,
2
0
1
7
In
t
h
is
p
a
p
e
r
w
e
a
re
in
tere
ste
d
t
o
c
a
lcu
late
th
e
re
so
n
a
n
t
f
re
q
u
e
n
c
y
o
f
re
c
tan
g
u
lar
p
a
tch
a
n
ten
n
a
u
sin
g
a
rti
f
icia
l
n
e
u
ra
l
n
e
tw
o
rk
s
b
a
se
d
o
n
th
e
m
u
lt
il
a
y
e
r
e
d
p
e
rc
e
p
tro
n
s
.
T
h
e
a
rti
f
icia
l
n
e
u
ra
l
n
e
tw
o
rk
s
b
u
il
t,
tra
n
sf
o
r
m
s
th
e
in
p
u
ts
w
h
ich
a
re
,
th
e
w
id
th
o
f
th
e
p
a
tch
W
,
th
e
len
g
th
o
f
th
e
p
a
tch
L
,
th
e
th
ick
n
e
ss
o
f
th
e
su
b
stra
te
h
a
n
d
t
h
e
d
iele
c
tri
c
p
e
rm
it
ti
v
it
y
to
t
h
e
re
so
n
a
n
t
f
re
q
u
e
n
c
y
f
r
w
h
ich
is
a
n
im
p
o
rt
a
n
t
p
a
ra
m
e
ter
to
d
e
sig
n
a
m
i
c
r
o
strip
p
a
tch
a
n
ten
n
a
.
T
h
e
p
ro
p
o
se
d
m
e
th
o
d
b
a
se
d
o
n
a
rti
f
icia
l
n
e
u
ra
l
n
e
tw
o
rk
s
is
c
o
m
p
a
re
d
to
so
m
e
a
n
a
l
y
ti
c
a
l
m
e
th
o
d
s
u
sin
g
so
m
e
sta
ti
stica
l
c
rit
e
ria.
T
h
e
o
b
tai
n
e
d
re
su
lt
s
d
e
m
o
n
stra
te t
h
a
t
a
rti
f
icia
l
n
e
u
ra
l
n
e
tw
o
rk
s
a
r
e
m
o
re
a
d
e
q
u
a
te
to
a
c
h
iev
e
th
e
p
u
r
p
o
se
t
h
a
n
th
e
o
th
e
r
m
e
th
o
d
s
a
n
d
p
re
se
n
t
a
g
o
o
d
a
rg
u
m
e
n
t
w
it
h
th
e
e
x
p
e
ri
m
e
n
tal
re
su
lt
s
a
v
a
il
a
b
le
in
th
e
li
tera
tu
re
.
He
n
c
e
,
th
e
a
rti
f
icia
l
n
e
u
ra
l
n
e
tw
o
rk
s
c
a
n
b
e
u
se
d
b
y
r
e
se
a
rc
h
e
rs
to
p
re
d
ict
th
e
re
so
n
a
n
t
f
re
q
u
e
n
c
y
o
f
a
re
c
tan
g
u
lar
p
a
tch
a
n
ten
n
a
k
n
o
w
in
g
len
g
th
(L
),
w
id
th
(W
),
th
i
c
k
n
e
ss
(
h
)
a
n
d
d
iele
c
tri
c
p
e
rm
it
ti
v
it
y
w
it
h
a
g
o
o
d
a
c
c
u
ra
c
y
.
K
ey
w
o
r
d
s
:
A
r
ti
f
icial
Ne
u
r
al
N
et
w
o
r
k
s
(
A
NN)
Mu
lti
L
a
y
er
P
er
ce
p
tr
o
n
(
ML
P)
Mic
r
o
s
tr
ip
p
atch
an
ten
n
a
R
eso
n
a
n
t
f
r
eq
u
en
c
y
Co
p
y
rig
h
t
©
2
0
1
7
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
:
Dep
ar
te
m
en
t o
f
E
lectr
ical
an
d
C
o
m
p
u
ter
E
n
g
in
ee
r
i
n
g
,
Natio
n
al
C
h
u
n
g
C
h
e
n
g
Un
i
v
er
s
it
y
,
1
6
8
Un
iv
er
s
it
y
R
o
ad
,
Min
h
s
i
u
n
g
T
o
w
n
s
h
ip
,
C
h
ia
y
i
C
o
u
n
t
y
6
2
1
0
2
,
T
aiw
a
n
,
R
O
C
.
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
Mic
r
o
s
tr
ip
p
atch
an
te
n
n
as
b
ec
o
m
e
o
n
e
o
f
t
h
e
m
o
s
t
p
o
p
u
lar
an
ten
n
a
t
y
p
e
s
u
s
ed
in
m
an
y
ap
p
licatio
n
s
a
n
d
in
s
ev
er
al
f
i
eld
s
lik
e,
GP
S,
B
lu
eto
o
th
,
L
T
E
,
m
o
b
ile
p
h
o
n
e,
w
ir
ele
s
s
a
p
p
licatio
n
,
s
atellit
e
co
m
m
u
n
icatio
n
…
T
h
e
p
atch
an
te
n
n
as
ar
e
co
m
p
ati
b
le
w
it
h
p
la
n
ar
an
d
n
o
n
-
p
la
n
ar
s
u
r
f
ac
es
[
1
]
.
T
h
ese
an
ten
n
a
s
ar
e
ch
ar
ac
ter
ized
b
y
s
e
v
er
al
ad
v
a
n
ta
g
es.
I
n
o
n
e
h
an
d
,
t
h
e
lo
w
co
s
t
to
m
an
u
f
ac
t
u
r
e
it
f
r
o
m
co
m
p
atib
le
cir
c
u
it
w
i
th
h
y
b
r
i
d
cir
cu
its
a
n
d
MM
I
C
(
Mo
n
o
l
ith
ic
Mic
r
o
w
a
v
e
I
n
te
g
r
ated
C
ir
cu
it)
[
1
,
2
]
.
I
n
th
e
o
th
er
h
a
n
d
,
t
h
e
y
ca
n
b
e
m
o
u
n
t
ed
o
n
an
y
s
u
r
f
ac
e
d
u
e
to
t
h
eir
lo
w
w
ei
g
h
t
an
d
lo
w
v
o
l
u
m
e.
Fu
r
t
h
er
m
o
r
e,
t
h
ese
ad
v
an
ta
g
es
h
av
e
r
ec
e
n
tl
y
in
cr
ea
s
ed
th
eir
u
s
e
in
m
a
n
y
ar
ea
s
an
d
h
av
e
led
to
i
m
p
r
o
v
e
t
h
eir
p
er
f
o
r
m
a
n
ce
.
Ho
w
e
v
er
,
m
icr
o
s
tr
ip
a
n
ten
n
a
s
h
av
e
th
e
d
r
a
w
b
ac
k
o
f
n
ar
r
o
w
b
a
n
d
w
id
th
,
lo
w
g
ai
n
an
d
c
an
o
p
er
ate
ef
f
ec
tiv
e
l
y
o
n
l
y
in
th
e
v
ic
in
it
y
o
f
t
h
e
r
eso
n
an
t
f
r
eq
u
en
c
y
.
Fo
r
th
is
r
ea
s
o
n
a
n
d
in
o
r
d
er
to
d
esig
n
a
p
atc
h
an
ten
n
a
it
’
s
i
m
p
o
r
tan
t to
d
eter
m
i
n
e
th
e
r
eso
n
an
t
f
r
eq
u
e
n
c
y
a
cc
u
r
atel
y
[
3
]
.
I
n
t
h
e
li
ter
atu
r
e,
ar
ti
f
icial
n
e
u
r
al
n
et
w
o
r
k
s
(
ANN)
m
o
d
el
s
h
a
v
e
b
ee
n
b
u
il
t
u
s
u
all
y
f
o
r
t
h
e
a
n
al
y
s
i
s
o
f
m
icr
o
s
tr
ip
an
te
n
n
as.
T
h
e
y
ar
e
ca
lled
th
e
d
ata
-
p
r
o
ce
s
s
i
n
g
m
o
d
els
in
s
p
ir
ed
f
r
o
m
th
e
s
tr
u
ct
u
r
e
an
d
b
eh
a
v
io
r
o
f
th
e
b
io
lo
g
ical
n
e
u
r
o
n
s
[
4
]
.
T
h
e
co
m
p
u
tatio
n
a
l
ca
p
ab
ilit
y
o
f
A
N
N
is
g
iv
e
n
b
y
co
n
n
ec
tio
n
w
ei
g
h
ts
,
ar
ch
i
tectu
r
e
an
d
tr
ain
i
n
g
al
g
o
r
ith
m
[
5
]
.
ANNs
h
av
e
b
ee
n
u
s
ed
i
n
d
i
f
f
er
en
t
f
ield
s
o
f
s
cien
ce
,
tech
n
o
lo
g
y
an
d
i
n
t
h
e
d
e
s
ig
n
o
f
m
icr
o
s
tr
ip
p
atch
a
n
te
n
n
a
[
6
]
.
A
NN
s
h
a
v
e
b
ee
n
u
s
ed
to
ca
lcu
late
th
e
r
e
s
o
n
a
n
t
f
r
eq
u
e
n
c
y
o
f
a
r
ec
tan
g
u
lar
p
atch
an
ten
n
a
at
a
g
iv
e
n
le
n
g
t
h
,
w
id
t
h
,
h
ei
g
h
t
a
n
d
d
ielec
tr
ic
co
n
s
ta
n
t
[
7
]
.
I
n
[
8
]
ar
tif
icia
l
n
eu
r
al
m
o
d
el
s
b
ased
o
n
th
e
ML
P
s
a
n
d
t
h
e
R
B
F
N
s
ar
e
p
r
esen
ted
f
o
r
co
m
p
u
ti
n
g
t
h
e
r
eso
n
a
n
t
f
r
eq
u
e
n
c
y
o
f
cir
cu
lar
m
icr
o
s
tr
ip
an
ten
n
a
s
w
ith
t
h
i
n
an
d
th
ic
k
s
u
b
s
tr
ates.
W
ith
t
h
e
s
u
itab
le
lear
n
in
g
alg
o
r
ith
m
,
t
h
e
AN
N
ca
n
b
e
tr
ain
ed
t
o
ac
h
iev
e,
f
r
o
m
i
n
p
u
t
v
ar
iab
les,
a
m
in
i
m
u
m
er
r
o
r
b
et
w
ee
n
t
h
e
n
et
w
o
r
k
o
u
tp
u
t a
n
d
t
h
e
tar
g
et.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8776
IJ
-
I
C
T
Vo
l.
6
,
No
.
1
,
A
p
r
il
2
0
1
7
:
1
–
9
2
I
n
th
is
p
ap
er
,
w
e
ar
e
i
n
ter
este
d
to
ap
p
ly
t
h
e
ar
ti
f
icia
l n
e
u
r
al
n
et
w
o
r
k
m
et
h
o
d
b
ased
o
n
t
h
e
m
u
lti la
y
er
p
er
ce
p
t
r
o
n
(
ML
P
)
to
ca
lcu
late
th
e
r
eso
n
an
t
f
r
eq
u
e
n
c
y
o
f
th
e
r
ec
tan
g
u
lar
p
atch
a
n
te
n
n
a
f
o
r
a
n
u
m
b
er
o
f
s
a
m
p
les.
T
h
e
len
g
th
(
L
)
,
th
e
w
id
t
h
(
W
)
,
th
e
th
ick
n
e
s
s
(
h
)
o
f
th
e
s
u
b
s
tr
ate
an
d
th
e
d
ielec
tr
ic
p
er
m
itt
iv
it
y
ar
e
u
s
ed
a
s
in
p
u
ts
o
f
th
e
ar
ti
f
icial
n
e
u
r
al
n
et
w
o
r
k
m
o
d
el.
So
m
e
s
ta
tis
tica
l
cr
iter
ia
s
u
c
h
a
s
MSE
,
R
M
SE,
MA
P
E
an
d
R
ar
e
u
s
ed
to
co
m
p
ar
e
th
e
ap
p
r
o
x
i
m
atio
n
o
f
t
h
e
r
eso
n
a
n
t
f
r
eq
u
e
n
c
y
u
s
i
n
g
t
h
e
A
NN
an
d
t
h
o
s
e
g
iv
e
n
b
y
t
h
e
an
al
y
tical
m
et
h
o
d
s
av
ailab
le
i
n
t
h
e
li
ter
atu
r
e
i
n
p
ar
ticu
lar
t
h
o
s
e
p
r
o
p
o
s
ed
b
y
J
a
m
e
s
a
n
d
al
[
9
]
,
b
.
Sen
g
u
p
ta,
D.
L
[
1
0
]
an
d
Gü
n
e
y
,
K
[
1
1
]
.
2.
DE
SCR
I
P
T
I
O
N
O
F
RE
C
T
ANG
U
L
AR
P
A
T
CH
AN
T
E
NNA
Mic
r
o
s
tr
ip
an
ten
n
a
i
s
a
v
er
y
s
m
all
co
n
d
u
cti
n
g
p
atch
w
i
th
d
i
m
en
s
io
n
s
o
f
w
id
th
(
W
)
,
len
g
t
h
(
L
)
o
v
er
a
g
r
o
u
n
d
p
la
n
e
w
it
h
a
s
u
b
s
tr
at
e
th
ic
k
n
e
s
s
(
h
)
.
T
h
e
p
atch
is
g
en
er
all
y
m
ad
e
o
f
co
n
d
u
cti
n
g
m
ater
ial
s
u
ch
a
s
co
p
p
er
b
u
ilt
o
n
a
g
r
o
u
n
d
p
lan
e
s
ep
ar
ated
b
y
d
ielec
tr
ic
s
u
b
s
tr
ate
u
s
u
al
l
y
i
n
th
e
r
an
g
e
o
f
2
.
2
≤
≤
1
2
,
d
ep
en
d
in
g
o
n
t
h
e
u
s
ed
m
a
te
r
ial
[
1
]
.
T
h
e
r
ad
iatin
g
p
atc
h
m
a
y
b
e
s
q
u
ar
e,
r
ec
tan
g
u
lar
,
th
i
n
s
tr
ip
(
d
ip
o
le)
,
cir
cu
lar
,
ellip
tical,
tr
ian
g
u
lar
,
o
r
an
y
o
th
er
co
n
f
ig
u
r
atio
n
.
T
h
e
tr
an
s
m
is
s
io
n
-
li
n
e
m
o
d
el
r
ep
r
esen
ts
a
r
ec
tan
g
u
lar
m
icr
o
s
tr
ip
an
ten
n
a
a
s
a
n
ar
r
a
y
o
f
t
w
o
r
ad
iatin
g
n
ar
r
o
w
ap
er
tu
r
es (
s
lo
t
s
)
,
ea
ch
o
f
w
id
th
(
W
)
an
d
h
ei
g
h
t (
h
)
,
s
ep
ar
ated
b
y
a
d
is
tan
ce
(
L
)
[
1
]
.
Fig
u
r
e
1
.
R
ec
tan
g
u
lar
p
atch
a
n
ten
n
a
T
h
e
f
r
in
g
i
n
g
f
ield
s
m
a
k
es
t
h
e
m
icr
o
s
tr
ip
li
n
e
lo
o
k
w
id
e
r
elec
tr
icall
y
co
m
p
ar
ed
to
it
s
p
h
y
s
ica
l
d
i
m
en
s
io
n
s
,
th
e
len
g
t
h
o
f
t
h
e
p
atch
h
a
s
b
ee
n
e
x
ten
d
ed
b
y
o
n
ea
ch
s
id
e;
th
e
e
f
f
ec
ti
v
e
l
en
g
t
h
o
f
th
e
p
atch
i
s
n
o
w
[
1
]
.
Fig
u
r
e
2
.
R
ad
iatin
g
ele
m
en
t e
x
ten
d
ed
b
y
∆
L
3.
AP
P
RO
XIM
AT
I
O
N
O
F
T
H
E
RE
SO
NAN
T
F
RE
Q
U
E
N
CY
A
n
u
m
b
er
o
f
m
et
h
o
d
s
a
v
ailab
le
to
d
eter
m
i
n
e
t
h
e
r
eso
n
an
t
f
r
eq
u
en
c
y
o
f
r
ec
ta
n
g
u
lar
p
atch
an
te
n
n
a
s
.
I
n
th
i
s
p
ar
t,
w
e
ar
e
i
n
ter
ested
to
ca
lcu
late
t
h
e
r
eso
n
a
n
t
f
r
eq
u
en
c
y
w
i
th
th
r
ee
t
h
eo
r
etica
l
m
e
th
o
d
s
p
r
o
p
o
s
ed
b
y
J
am
e
s
an
d
al
[
9
]
,
Sen
g
u
p
ta,
D.
L
[
1
0
]
an
d
Gü
n
e
y
,
K
[
1
1
]
.
C
o
n
s
id
er
a
m
icr
o
s
tr
ip
an
te
n
n
a
w
it
h
a
r
ec
ta
n
g
u
lar
p
atc
h
o
f
w
i
d
th
W
an
d
len
g
t
h
L
o
v
er
a
g
r
o
u
n
d
p
la
n
e
w
it
h
a
s
u
b
s
tr
ate
o
f
th
ick
n
es
s
h
a
n
d
a
r
elativ
e
d
ielec
tr
ic
co
n
s
tan
t
,
as
s
h
o
w
n
i
n
Fi
g
u
r
e
1
.
T
h
e
ap
p
r
o
x
im
at
e
eq
u
atio
n
s
to
ca
lc
u
late
t
h
e
r
eso
n
an
t
f
r
eq
u
e
n
c
y
i
s
p
r
o
p
o
s
ed
in
th
is
s
ec
tio
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
I
C
T
I
SS
N:
2252
-
8776
C
o
mp
a
r
is
o
n
o
f th
e
R
eso
n
a
n
t F
r
eq
u
en
cy
Dete
r
min
a
tio
n
o
f
a
Micr
o
s
t
r
ip
…
(
La
h
ce
n
A
g
u
n
i
)
3
3
.
1
.
J
a
m
e
s
a
nd
a
l
m
et
ho
d
T
h
e
r
eso
n
an
t f
r
eq
u
e
n
c
y
s
u
g
g
e
s
ted
b
y
J
a
m
e
s
an
d
al
[
9
]
is
g
i
v
en
b
y
:
√
T
h
e
ef
f
ec
ti
v
e
p
er
m
itt
iv
i
t
y
i
n
f
u
n
ct
io
n
o
f
u
is
e
x
p
r
ess
ed
b
y
:
√
w
it
h
:
[
{
}
]
a
n
d
:
√
;
⁄
3
.
2
.
Seng
up
t
a
D.
L
m
et
ho
d
T
h
e
ex
p
r
ess
io
n
o
f
t
h
e
r
eso
n
a
n
t
f
r
eq
u
e
n
c
y
ap
p
r
o
x
i
m
ated
b
y
Sen
g
u
p
ta,
D,
L
[
1
0
]
tak
es
th
e
f
o
llo
w
in
g
ex
p
r
ess
io
n
:
[
√
]
T
h
e
ef
f
ec
ti
v
e
d
ielec
tr
ic
co
n
s
ta
n
t is
g
i
v
en
as
:
w
it
h
:
(
)
√
⁄
3.
3
.
Seng
up
t
a
D.
L
m
et
ho
d
T
o
ca
lcu
late
th
e
r
eso
n
a
n
t
f
r
eq
u
en
c
y
,
G
ü
n
e
y
,
K
[
1
1
]
p
r
o
p
o
s
e
s
th
e
f
o
llo
w
in
g
f
o
r
m
u
la:
√
T
h
e
ef
f
ec
ti
v
e
d
ielec
tr
ic
co
n
s
ta
n
t is d
ef
in
ed
as:
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8776
IJ
-
I
C
T
Vo
l.
6
,
No
.
1
,
A
p
r
il
2
0
1
7
:
1
–
9
4
w
h
er
e:
{
}
{
}
T
h
e
ef
f
ec
ti
v
e
len
g
t
h
o
f
t
h
e
p
at
ch
is
:
w
it
h
:
i
f
i
f
⁄
T
h
e
w
av
e
v
ec
to
r
an
d
th
e
w
a
v
e
len
g
t
h
ar
e
ex
p
r
ess
ed
b
y
:
√
4.
ARTI
F
I
CI
AL
N
E
URA
L
NE
T
WO
RK
M
E
T
H
O
D
A
r
ti
f
icial
n
e
u
r
al
n
et
w
o
r
k
s
ar
e
co
m
p
u
tatio
n
a
l
m
o
d
els
i
n
s
p
i
r
ed
f
r
o
m
t
h
e
s
tr
u
ct
u
r
e
an
d
b
eh
av
io
r
o
f
b
io
lo
g
ical
n
eu
r
o
n
s
an
d
r
ec
en
tl
y
b
ec
a
m
e
a
m
o
d
eli
n
g
a
n
d
d
esig
n
to
o
l
th
at
i
s
an
alter
n
ati
v
e
o
f
n
u
m
er
ical
m
o
d
el
s
an
d
an
al
y
tical
m
o
d
el
s
[
4
]
.
T
h
e
m
o
s
t
u
s
ed
m
o
d
el
o
f
ar
tif
icia
l
n
e
u
r
al
n
et
w
o
r
k
s
n
o
w
ad
ay
s
is
M
u
ltil
a
y
e
r
p
er
ce
p
tr
o
n
(
ML
P
)
[
1
5
]
.
Mu
ltil
a
y
er
p
er
ce
p
tr
o
n
s
as
a
f
e
ed
f
o
r
w
ar
d
n
e
u
r
al
n
et
w
o
r
k
tr
ai
n
ed
w
ith
th
e
s
tan
d
ar
d
b
ac
k
p
r
o
p
ag
atio
n
alg
o
r
ith
m
h
a
v
e
b
ee
n
ap
p
lied
s
u
cc
ess
f
u
ll
y
to
s
o
lv
e
m
a
n
y
p
r
o
b
lem
s
in
a
s
u
p
er
v
i
s
ed
m
an
n
er
[
1
2
]
.
T
h
e
ar
ch
itect
u
r
e
o
f
a
m
u
ltil
a
y
er
w
i
th
a
n
i
n
p
u
t
la
y
er
,
o
n
e
h
id
d
en
l
a
y
er
o
r
in
ter
m
ed
iate
la
y
er
a
n
d
an
o
u
tp
u
t
la
y
er
is
g
iv
e
n
i
n
Fi
g
u
r
e
3
.
Fig
u
r
e
3
.
Mu
ltil
a
y
er
p
er
ce
p
tr
o
n
s
s
tr
u
ct
u
r
e
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
I
C
T
I
SS
N:
2252
-
8776
C
o
mp
a
r
is
o
n
o
f th
e
R
eso
n
a
n
t F
r
eq
u
en
cy
Dete
r
min
a
tio
n
o
f
a
Micr
o
s
t
r
ip
…
(
La
h
ce
n
A
g
u
n
i
)
5
5.
M
L
P
ST
RUCTUR
E
An
ar
ti
f
icial
n
eu
r
al
n
et
w
o
r
k
i
s
a
m
at
h
e
m
at
ical
f
u
n
ctio
n
u
s
ed
to
p
r
ed
ict
d
ata;
th
e
s
tr
u
ct
u
r
e
u
s
ed
in
t
h
is
n
et
w
o
r
k
h
as
f
o
u
r
i
n
p
u
t
s
:
t
h
e
l
en
g
t
h
o
f
th
e
p
atch
(
L
)
,
th
e
w
i
d
th
(
W
)
,
th
e
th
ic
k
n
es
s
o
f
t
h
e
d
ielec
tr
ic
s
u
b
s
tr
ate
(
h
)
an
d
t
h
e
d
ielec
tr
ic
p
er
m
it
tiv
it
y
.
T
h
e
d
esire
d
o
u
tp
u
t
is
t
h
e
r
eso
n
a
n
t
f
r
eq
u
e
n
c
y
.
T
o
b
u
ild
A
N
N
s
tr
u
ct
u
r
e,
y
o
u
h
a
v
e
to
d
eter
m
i
n
e:
n
u
m
b
er
o
f
la
y
er
s
,
n
u
m
b
er
o
f
n
e
u
r
o
n
s
i
n
ea
c
h
la
y
er
,
n
e
u
r
o
n
s
ac
ti
v
atio
n
f
u
n
ctio
n
an
d
lear
n
i
n
g
alg
o
r
it
h
m
.
Fig
u
r
e
4
.
ML
P
s
tr
u
ct
u
r
e
T
h
e
d
atab
ase
u
s
ed
is
o
b
tain
ed
f
r
o
m
m
ea
s
u
r
e
m
e
n
ts
p
er
f
o
r
m
ed
b
y
Kar
a
M
[
1
3
]
an
d
[
1
4
]
;
th
e
id
en
ti
f
icatio
n
o
f
th
e
M
L
P
n
e
u
r
al
n
et
w
o
r
k
s
r
eq
u
ir
es
t
w
o
s
tep
s
.
T
h
e
f
ir
s
t
o
n
e
is
t
h
e
d
eter
m
i
n
atio
n
o
f
t
h
e
n
et
w
o
r
k
s
tr
u
ct
u
r
e
w
h
er
e
t
h
e
d
is
tr
ib
u
tio
n
o
f
d
ata
is
g
i
v
e
n
in
t
h
e
tab
le
b
elo
w
:
T
ab
le
1
.
D
atab
ase
d
is
tr
ib
u
tio
n
D
a
t
a
b
a
se
d
i
s
t
r
i
b
u
t
i
o
n
P
e
r
c
e
n
t
a
g
e
N
u
mb
e
r
o
f
samp
l
e
s
T
r
a
i
n
i
n
g
8
0
%
2
6
V
a
l
i
d
a
t
i
o
n
0
0
%
00
T
e
st
i
n
g
20
%
07
T
h
e
s
ec
o
n
d
o
n
e
is
th
e
id
en
t
if
i
ca
tio
n
o
f
p
ar
a
m
eter
s
(
lear
n
i
n
g
o
f
t
h
e
n
e
u
r
al
n
et
w
o
r
k
s
)
:
t
h
e
n
u
m
b
er
o
f
h
id
d
en
la
y
er
s
,
th
e
n
u
m
b
er
o
f
n
e
u
r
o
n
s
in
h
id
d
en
la
y
er
,
th
e
ap
p
r
o
p
r
iate
lear
n
in
g
al
g
o
r
ith
m
an
d
t
h
e
m
o
s
t
s
u
itab
le
tr
a
n
s
f
er
f
u
n
c
tio
n
f
o
r
th
e
n
et
w
o
r
k
.
Fig
u
r
e
5
.
V
ar
iatio
n
o
f
MSE
f
o
r
d
if
f
er
en
t
n
u
m
b
er
o
f
h
id
d
en
l
a
y
er
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8776
IJ
-
I
C
T
Vo
l.
6
,
No
.
1
,
A
p
r
il
2
0
1
7
:
1
–
9
6
Fig
u
r
e
6
.
V
ar
iatio
n
o
f
MSE
f
o
r
d
if
f
er
en
t
n
u
m
b
er
o
f
n
eu
r
o
n
s
in
h
id
d
en
la
y
er
GD
SCG
CGF
RP
LM
GDM
-0,1
0,0
0,1
0,2
0,3
0,4
0,5
0,6
0,7
0,8
Me
an
Squa
re
d Err
or
Tr
ainin
g a
lgor
ithm
Me
an
Squa
re
d Err
or
Fig
u
r
e
7
.
V
ar
iatio
n
o
f
MSE
f
o
r
d
if
f
er
en
t
tr
ai
n
i
n
g
alg
o
r
it
h
m
s
Fig
u
r
e
8
.
V
ar
iatio
n
o
f
MSE
f
o
r
d
if
f
er
en
t tr
a
n
s
f
er
f
u
n
ctio
n
s
T
h
e
o
p
tim
u
m
n
et
w
o
r
k
s
tr
u
ct
u
r
e
f
o
r
t
h
e
p
r
o
p
o
s
ed
p
r
o
b
lem
af
ter
m
u
ltip
le
tr
ai
n
i
n
g
co
n
s
is
t
s
o
f
th
r
ee
la
y
er
s
M
L
P
w
it
h
a
n
u
m
b
er
o
f
n
e
u
r
o
n
s
,
t
h
e
in
p
u
t
la
y
er
w
it
h
f
o
u
r
i
n
p
u
t
n
e
u
r
o
n
s
,
o
n
e
h
id
d
en
la
y
er
w
ith
1
0
h
id
d
en
n
e
u
r
o
n
s
a
n
d
o
n
e
o
u
tp
u
t
n
e
u
r
o
n
s
i
n
th
e
o
u
tp
u
t
la
y
e
r
.
W
h
ile
th
e
m
o
s
t
s
u
itab
le
le
ar
n
in
g
alg
o
r
it
h
m
is
L
e
v
en
b
er
g
Ma
r
q
u
ar
d
t
(
L
M)
.
T
h
e
ap
p
r
o
p
r
iate
tr
an
s
f
er
f
u
n
cti
o
n
i
n
t
h
e
h
id
d
en
la
y
er
is
s
i
g
m
o
id
f
u
n
ctio
n
,
w
h
ile
th
e
tr
an
s
f
er
f
u
n
ctio
n
u
s
ed
in
t
h
e
o
u
tp
u
t la
y
er
i
s
th
e
li
n
ea
r
f
u
n
ctio
n
.
6.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
I
n
t
h
is
s
t
u
d
y
o
u
r
g
o
al
i
s
f
ir
s
t
to
ca
lcu
late
th
e
r
eso
n
a
n
t
f
r
e
q
u
en
c
y
o
f
th
e
r
ec
tan
g
u
lar
p
atch
a
n
ten
n
a
w
h
ic
h
d
ep
en
d
s
o
n
t
h
e
d
i
m
en
s
i
o
n
s
o
f
t
h
e
a
n
te
n
n
a;
len
g
t
h
(
L
)
,
w
id
t
h
(
W
)
,
s
u
b
s
tr
ate
t
h
ic
k
n
es
s
(
h
)
an
d
d
ielec
tr
ic
p
er
m
i
tti
v
it
y
(
)
,
s
ec
o
n
d
l
y
w
e
p
er
f
o
r
m
a
co
m
p
ar
is
o
n
o
f
th
e
o
b
tain
ed
r
esu
lts
u
s
i
n
g
ar
tif
ic
i
al
n
eu
r
al
n
et
w
o
r
k
w
it
h
t
h
r
ee
an
al
y
tical
m
et
h
o
d
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
I
C
T
I
SS
N:
2252
-
8776
C
o
mp
a
r
is
o
n
o
f th
e
R
eso
n
a
n
t F
r
eq
u
en
cy
Dete
r
min
a
tio
n
o
f
a
Micr
o
s
t
r
ip
…
(
La
h
ce
n
A
g
u
n
i
)
7
T
h
e
p
er
f
o
r
m
an
ce
o
f
o
u
r
r
es
u
lts
i
s
ch
ec
k
ed
u
s
i
n
g
s
tat
is
t
ical
cr
iter
ia
g
iv
i
n
g
b
y
t
h
e
f
o
llo
w
in
g
eq
u
atio
n
s
:
Me
an
Sq
u
ar
e
E
r
r
o
r
:
∑
(
1
)
M
ea
n
A
b
s
o
lu
te
P
er
ce
n
tag
e
E
r
r
o
r
:
(
∑
|
|
)
(
2
)
A
b
s
o
l
u
te
Fra
ctio
n
o
f
Var
ian
ce
:
(
(
∑
|
|
∑
)
)
(
3
)
w
h
er
e:
n
i
s
th
e
to
tal
n
u
m
b
er
o
f
s
a
m
p
les,
an
d
r
ep
r
esen
t r
esp
ec
tiv
el
y
tar
g
et
a
n
d
o
u
tp
u
t d
ata
.
I
n
t
h
e
tab
le
b
elo
w
w
e
h
a
v
e
g
r
o
u
p
ed
th
e
v
al
u
es
o
f
s
o
m
e
s
tat
is
tical
cr
iter
ia
ex
p
lo
ited
i
n
t
h
i
s
s
t
u
d
y
f
o
r
th
e
an
al
y
tica
l
m
et
h
o
d
s
an
d
t
h
e
A
NN
m
et
h
o
d
:
T
ab
le
2
.
S
tatis
tical
cr
iter
ia
o
b
tain
ed
f
o
r
v
ar
io
u
s
m
et
h
o
d
s
V
a
r
i
a
b
l
e
M
S
E
M
A
P
E
R
Jame
s
a
n
d
a
l
1
.
1
2
8
8
1
9
.
4
3
2
7
9
.
2
2
S
e
n
g
u
p
t
a
,
D
.
L
0
.
1
0
3
1
5
.
1
5
3
8
9
8
.
1
0
G
u
n
e
y
,
K
1
.
1
6
6
1
1
9
.
3
9
5
7
8
.
5
4
A
N
N
0
.
0
0
2
0
0
.
2
8
8
6
9
9
.
9
6
As s
h
o
w
n
i
n
Fi
g
u
r
e
9
th
e
to
tal
n
u
m
b
er
o
f
5
5
ep
o
ch
s
is
r
eq
u
ir
ed
to
r
ed
u
ce
MSE
lev
el
to
a
lo
w
v
al
u
e.
Fig
u
r
e
9
.
Me
an
s
q
u
ar
ed
er
r
o
r
T
h
e
r
eg
r
ess
io
n
co
ef
f
icien
t
R
f
o
r
o
u
r
ML
P
n
et
w
o
r
k
w
h
ic
h
d
escr
ib
es
th
e
r
elatio
n
s
h
ip
b
et
w
ee
n
th
e
p
r
ed
icted
v
alu
es
(
o
u
tp
u
ts
)
a
n
d
th
e
o
b
s
er
v
ed
v
a
lu
e
s
(
t
ar
g
et
s
)
is
s
h
o
w
n
in
t
h
e
Fig
u
r
e
10
.
T
h
e
d
ata
s
h
o
u
ld
f
all
alo
n
g
a
4
5
d
eg
r
ee
lin
e,
f
o
r
a
p
er
f
ec
t
f
i
t,
w
h
er
e
t
h
e
n
et
w
o
r
k
o
u
tp
u
ts
ar
e
eq
u
al
to
t
h
e
tar
g
et
s
.
Fo
r
th
is
p
r
o
b
le
m
,
th
e
f
it
i
s
r
ea
s
o
n
ab
l
y
g
o
o
d
f
o
r
all
d
ata
s
ets,
w
it
h
R
v
al
u
es
in
ea
ch
ca
s
e
i
s
ap
p
r
o
x
i
m
a
tel
y
R
=1
,
th
e
v
al
u
e
o
f
t
h
i
s
co
ef
f
icie
n
t
s
h
o
w
s
t
h
at
t
h
e
n
e
t
w
o
r
k
b
u
ilt
w
it
h
s
tr
u
ct
u
r
e
(
4
-
10
-
1
)
is
p
er
f
o
r
m
in
g
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8776
IJ
-
I
C
T
Vo
l.
6
,
No
.
1
,
A
p
r
il
2
0
1
7
:
1
–
9
8
Fig
u
r
e
1
0
.
R
eg
r
ess
io
n
cu
r
v
es
o
f
tr
ain
ed
A
NN
T
o
p
r
o
v
id
e
ad
d
itio
n
al
v
er
if
i
ca
tio
n
o
f
n
e
t
w
o
r
k
p
er
f
o
r
m
a
n
ce
w
e
p
lo
t
in
F
ig
u
r
e
11
th
e
r
eso
n
an
t
f
r
eq
u
en
c
y
v
s
.
t
h
e
n
u
m
b
er
o
f
s
a
m
p
les
f
o
r
: e
x
p
er
i
m
e
n
tal
m
et
h
o
d
,
an
aly
tical
m
eth
o
d
s
a
n
d
ANN
m
et
h
o
d
.
Fig
u
r
e
1
1
.
R
eso
n
an
t
f
r
eq
u
e
n
c
y
v
s
.
s
a
m
p
le
s
W
e
ca
n
s
ee
f
r
o
m
t
h
e
co
m
p
ar
is
o
n
b
et
w
ee
n
th
e
ar
ti
f
icial
n
e
u
r
al
n
et
w
o
r
k
m
et
h
o
d
an
d
th
e
an
al
y
tical
m
et
h
o
d
s
in
Fig
u
r
e
11
an
d
in
T
ab
le
2
th
at;
th
e
o
b
tain
ed
r
es
u
lts
b
y
A
NN
m
et
h
o
d
u
s
i
n
g
t
h
e
lear
n
in
g
al
g
o
r
ith
m
L
e
v
en
b
er
g
-
Ma
r
q
u
ar
d
t
L
M
ar
e
in
p
er
f
ec
t
ad
ap
tatio
n
w
it
h
t
h
e
e
x
p
er
i
m
e
n
tal
r
es
u
lt
s
p
r
ese
n
ted
b
y
K
A
R
A
,
M
[
1
3
]
an
d
[
1
4
]
.
7.
CO
NCLU
SI
O
N
I
n
th
i
s
p
ap
er
,
w
e
ar
e
in
ter
e
s
ted
to
ap
p
ly
th
e
ar
ti
f
icial
n
eu
r
al
n
et
w
o
r
k
s
m
et
h
o
d
b
ased
o
n
th
e
m
u
lti
la
y
er
p
er
ce
p
tr
o
n
s
(
ML
P
)
to
ca
lcu
late
th
e
r
eso
n
an
t
f
r
eq
u
en
c
y
o
f
th
e
r
ec
tan
g
u
lar
p
atch
an
te
n
n
a.
T
h
e
p
r
o
p
o
s
ed
m
e
th
o
d
u
s
i
n
g
ANN
is
co
m
p
ar
ed
to
s
o
m
e
a
n
al
y
t
ical
m
et
h
o
d
s
i
n
ter
m
o
f
s
tati
s
tical
cr
iter
ia.
T
h
e
o
b
tain
ed
r
esu
lts
d
e
m
o
n
s
tr
ate
t
h
at
A
NN
i
s
m
o
r
e
ad
eq
u
ate
t
o
r
ich
th
e
p
u
r
p
o
s
e
th
a
n
th
e
o
t
h
e
r
m
eth
o
d
s
b
ec
au
s
e
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
I
C
T
I
SS
N:
2252
-
8776
C
o
mp
a
r
is
o
n
o
f th
e
R
eso
n
a
n
t F
r
eq
u
en
cy
Dete
r
min
a
tio
n
o
f
a
Micr
o
s
t
r
ip
…
(
La
h
ce
n
A
g
u
n
i
)
9
it
p
r
esen
ts
a
g
o
o
d
ar
g
u
m
e
n
t
w
it
h
t
h
e
ex
p
er
i
m
en
ta
l
r
esu
l
ts
.
C
o
n
s
eq
u
e
n
tl
y
,
ar
ti
f
icial
n
e
u
r
al
n
et
w
o
r
k
s
ca
n
b
e
u
s
ed
b
y
r
esear
ch
er
s
to
p
r
ed
ict
th
e
r
eso
n
an
t
f
r
eq
u
e
n
c
y
o
f
a
r
ec
tan
g
u
lar
p
atch
a
n
ten
n
a
u
s
i
n
g
len
g
t
h
(
L
)
,
w
id
th
(
W
)
,
th
ick
n
e
s
s
(
h
)
a
n
d
d
ielec
tr
ic
p
er
m
it
tiv
i
t
y
as
th
e
n
et
w
o
r
k
in
p
u
ts
.
T
h
e
co
r
r
elatio
n
v
al
u
e
R
is
9
9
.
9
6
%
w
h
ic
h
in
d
icate
s
t
h
e
g
o
o
d
ag
r
ee
m
en
t
b
et
w
ee
n
th
e
m
ea
s
u
r
ed
an
d
A
NN
p
r
ed
icted
v
alu
es.
T
h
er
ef
o
r
e,
th
e
ANN
ca
n
f
u
r
t
h
er
b
e
e
m
p
lo
y
ed
as
a
to
o
l
to
o
b
tain
th
e
g
eo
m
etr
ic
d
i
m
e
n
s
io
n
s
o
f
th
e
m
icr
o
s
tr
ip
p
atch
an
ten
n
a
w
it
h
a
h
ig
h
ac
c
u
r
ac
y
.
RE
F
E
R
E
NC
E
S
[1
]
Ca
n
sta
n
ti
n
e
.
A
.
Ba
lan
is
,
“
A
n
ten
n
a
T
h
e
o
r
y
,
A
n
a
l
y
sis
a
n
d
De
sig
n
se
c
o
n
d
e
d
it
i
o
n
”
,
Jo
h
n
W
il
e
y
&
S
o
n
s,
Ne
w
Yo
rk
,
2
0
0
9
.
[2
]
A
d
il
Bo
u
h
o
u
s
,
“
A
rti
f
i
c
ial
Ne
u
ra
l
Ne
t
w
o
rk
In
T
h
e
De
si
g
n
O
f
Re
c
tan
g
u
lar
M
icro
strip
A
n
ten
n
a
”
,
Ad
v
a
n
c
e
d
Co
mp
u
t
a
ti
o
n
a
l
I
n
telli
g
e
n
c
e
:
An
I
n
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
(
ACII)
,
v
o
l
.
2
,
n
o
.
2
,
A
p
ril
2
0
1
5
.
[3
]
D.
Ka
ra
b
o
g
a
;
K.
G
u
n
e
y
;
S
.
S
a
g
iro
g
lu
;
M
.
Er
ler
,
“
Ne
u
ra
l
c
o
m
p
u
tatio
n
o
f
re
so
n
a
n
t
f
r
e
q
u
e
n
c
y
o
f
e
lec
tri
c
a
ll
y
th
in
a
n
d
th
ick
re
c
tan
g
u
lar
m
i
c
ro
strip
a
n
ten
n
a
s”
,
M
icro
w
a
v
e
s,
A
n
ten
n
a
s
a
n
d
P
r
o
p
a
g
a
ti
o
n
,
IEE
Pro
c
e
e
d
in
g
s
,
v
o
l.
1
4
6
,
n
o
.
2
,
p
p
.
1
5
5
–
1
5
9
,
A
p
ril
1
9
9
9
.
[4
]
L
o
tf
i
M
e
r
a
d
;
F
e
th
i
T
a
ri
k
Be
d
i
m
e
ra
d
;
S
id
i
M
o
h
a
m
e
d
M
e
riah
;
S
id
i
A
h
m
e
d
Dje
n
n
a
s
,
“
Ne
u
r
a
l
Ne
t
w
o
rk
s
f
o
r
S
y
n
th
e
sis a
n
d
Op
ti
m
iza
ti
o
n
o
f
A
n
ten
n
a
A
rra
y
s
”
,
Ra
d
i
o
e
n
g
in
e
e
rin
g
,
v
o
l.
1
6
,
no
.
1
,
A
p
ril
2
0
0
7
.
[5
]
Am
it
Ku
m
a
r
Ya
d
a
v
;
Ha
s
m
a
t
M
a
li
k
;
A
.
P
.
M
it
tal
,
“
A
rti
f
icia
l
N
e
u
ra
l
Ne
tw
o
rk
F
it
ti
n
g
T
o
o
l
Ba
se
d
P
re
d
ictio
n
Of
S
o
lar Rad
iati
o
n
F
o
r
Id
e
n
t
ify
in
g
S
o
lar
P
o
w
e
r
P
o
ten
ti
a
l”,
J
o
u
r
n
a
l
o
f
El
e
c
trica
l
En
g
in
e
e
rin
g
.
[6
]
Ba
b
lu
Ku
m
a
r
S
in
g
h
,
“
De
si
g
n
o
f
Re
c
t
a
n
g
u
lar
M
icro
strip
P
a
tch
A
n
ten
n
a
b
a
se
d
o
n
A
rti
f
icia
l
N
e
u
ra
l
Ne
t
w
o
rk
A
l
g
o
rit
h
m
”
,
2
0
1
5
2
n
d
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
S
ig
n
a
l
Pro
c
e
ss
in
g
a
n
d
In
teg
ra
ted
Ne
two
rk
s
(
S
PIN).
9
7
8
-
1
-
47
99
-
5
9
9
1
-
4
/1
5
/$
3
1
.
0
0
©2
0
1
5
I
EE
E
.
[7
]
Bish
a
l
De
y
S
a
rk
a
r;
S
o
n
a
li
S
h
a
n
k
a
r;
A
n
it
a
T
h
a
k
u
r
a
n
d
Him
a
n
sh
u
Ch
a
u
ra
siy
a
,
“
Re
so
n
a
n
t
F
re
q
u
e
n
c
y
De
ter
m
in
a
ti
o
n
o
f
Re
c
tan
g
u
lar P
a
tch
A
n
ten
n
a
u
sin
g
Ne
u
ra
l
N
e
t
w
o
rk
”
,
2
0
1
5
1
st
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Ne
x
t
Ge
n
e
ra
ti
o
n
Co
mp
u
t
in
g
T
e
c
h
n
o
lo
g
ies
(
NGC
T
-
2
0
1
5
)
De
h
ra
d
u
n
,
In
d
ia,
4
-
5
S
e
p
tem
b
e
r
2
0
1
5
.
9
7
8
-
1
-
4
6
7
3
-
6
8
0
9
-
4
/1
5
/$
3
1
.
0
0
©2
0
1
5
IEE
E
[8
]
Ce
lal
Yild
iz;
S
in
a
n
G
u
lt
e
k
in
;
K
e
rim
G
u
n
e
y
;
S
e
r
e
f
S
a
g
iro
g
lu
,
“
Ne
u
ra
l
M
o
d
e
ls
f
o
r
th
e
Re
so
n
a
n
t
F
re
q
u
e
n
c
y
o
f
El
e
c
tri
c
a
ll
y
T
h
in
a
n
d
T
h
ick
Ci
rc
u
lar
M
icro
strip
A
n
ten
n
a
s
a
n
d
th
e
Ch
a
ra
c
teristic
P
a
ra
m
e
ter
s
o
f
A
s
y
m
m
e
tri
c
Co
p
lan
a
r
W
a
v
e
g
u
id
e
s Ba
c
k
e
d
w
it
h
a
Co
n
d
u
c
to
r”
,
I
n
t.
J
.
El
e
c
tro
n
.
Co
mm
u
n
.
(A
E¨
U) 5
6
(
2
0
0
2
)
N
o
.
6
,
3
9
6
−
4
0
6
.
[9
]
Ja
m
e
s,
J.R.
;
Ha
ll
,
P
.
S
.
(Ed
s.)
,
“
Ha
n
d
b
o
o
k
o
f
m
icro
strip
a
n
ten
n
a
s”
,
(
P
e
ter
P
e
re
g
rin
u
s L
td
.
,
1
9
8
9
),
v
o
ls
.
1
a
n
d
2
.
[1
0
]
S
e
n
g
u
p
ta,
D.L
,
“
A
p
p
ro
x
i
m
a
te
e
x
p
re
ss
io
n
f
o
r
th
e
re
so
n
a
n
t
f
re
q
u
e
n
c
y
o
f
a
re
c
t
a
n
g
u
lar
p
a
tch
a
n
ten
n
a
”
,
El
e
c
tro
n
.
L
e
tt
.
1
9
8
3
,
v
o
l
.
1
9
,
n
o
.
2
0
,
p
p
.
8
3
4
-
8
3
5
.
[1
1
]
G
u
n
e
y
,
K
,
“
A n
e
w
e
d
g
e
e
x
ten
sio
n
e
x
p
re
ss
io
n
f
o
r
th
e
re
so
n
a
n
t
f
re
q
u
e
n
c
y
o
f
e
le
c
tri
c
a
ll
y
th
ick
r
e
c
tan
g
u
lar m
icro
strip
a
n
ten
n
a
s”
,
In
t:
J
.
El
e
c
tro
n
.
,
1
9
9
3
,
v
o
l.
7
5
,
n
o.
4,
p
p
.
7
6
7
-
7
7
0
[1
2
]
S
im
o
n
Ha
y
k
in
,
“
Ne
u
ra
l
Ne
tw
o
rk
,
A
c
o
m
p
re
h
e
n
siv
e
f
o
u
n
d
a
ti
o
n
”
,
2
n
d
E
d
.
,
P
e
a
rso
n
,
IS
BN:
8
1
-
7
8
0
8
-
300
-
0
,
2
0
0
4
.
[1
3
]
Ka
ra
,
M
,
“
T
h
e
re
so
n
a
n
t
f
re
q
u
e
n
c
y
o
f
re
c
tan
g
u
la
r
m
icro
strip
a
n
ten
n
a
e
lem
e
n
ts
w
it
h
v
a
rio
u
s
su
b
stra
t
e
th
ick
n
e
ss
e
s”
,
M
icr
o
w.
Op
t.
T
e
c
k
n
o
l.
L
e
tt
,
1
9
9
6
,
v
o
l.
1
1
,
n
o
.
2
,
p
p
.
5
5
-
5
9
.
[1
4
]
Ka
ra
,
M
.
,
“
Clo
se
d
-
f
o
rm
e
x
p
re
ss
io
n
s
f
o
r
th
e
re
so
n
a
n
t
f
re
q
u
e
n
c
y
o
f
re
c
tan
g
u
lar
m
icro
strip
a
n
ten
n
a
e
le
m
e
n
ts
w
it
h
th
ick
su
b
stra
tes
”
,
M
icr
o
w.
Op
t
.
T
e
c
h
n
o
l.
L
e
tt
.
,
1
9
9
6
,
v
o
l
.
1
2
,
n
o
.
3
,
p
p
.
1
3
1
-
1
3
6
.
[1
5
]
Zein
a
li
z
a
d
e
h
,
N.
;
S
h
o
jaie
,
A
.
A
.
;
S
h
a
riatm
a
d
a
ri,
M
.
,
“
M
o
d
e
li
n
g
a
n
d
a
n
a
ly
sis
o
f
b
a
n
k
c
u
sto
m
e
r
sa
ti
sf
a
c
ti
o
n
u
sin
g
n
e
u
ra
l
n
e
tw
o
rk
s ap
p
ro
a
c
h
”
,
I
n
ter
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
B
a
n
k
M
a
rk
e
ti
n
g
,
v
o
l.
3
3
,
n
o
.
6
,
2
0
1
5
,
p
p
.
7
1
7
-
7
3
2
.
Evaluation Warning : The document was created with Spire.PDF for Python.