I
AE
S
I
nte
rna
t
io
na
l J
o
urna
l o
f
Art
if
icia
l In
t
ellig
ence
(
I
J
-
AI
)
Vo
l.
3
,
No
.
2
,
J
u
n
e
201
4
,
p
p
.
79
~
83
I
SS
N:
2252
-
8938
79
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
AI
H
a
ndo
v
er De
cisio
n Mecha
nis
m
in
Interw
o
rk
ing
Tec
hno
lo
g
ies
Using
Radia
l Ba
sis
F
unc
tions
P
a
y
a
l
M
a
ha
j
a
n
1
,
K
uld
ee
p Sin
g
h
2
,
H
a
rdee
p K
a
ur
3
1,
3
De
p
t.
o
f
El
e
c
tro
n
ics
T
e
c
h
n
o
l
o
g
y
,
G
u
ru
Na
n
a
k
De
v
Un
iv
e
r
sit
y
,
Am
rit
sa
r,
In
d
ia
2
De
p
t.
o
f
ECE
G
ND
U Reg
io
n
a
l
Ca
m
p
u
s S
u
lt
a
n
p
u
r
L
o
d
h
i,
G
u
ru
N
a
n
a
k
De
v
Un
iv
e
r
sit
y
,
Am
rit
sa
r,
In
d
ia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Dec
2
3
,
2
0
1
3
R
ev
i
s
ed
Ma
r
2
3
,
2
0
1
4
A
cc
ep
ted
A
p
r
29
,
2
0
1
4
A
s
a
m
o
b
il
e
u
se
r
trav
e
ls
b
e
tw
e
e
n
ra
d
i
o
n
e
tw
o
rk
s,
a
h
a
n
d
o
v
e
r
m
e
c
h
a
n
ism
is
re
q
u
ired
t
o
v
a
r
y
it
s
ra
d
io
c
o
n
n
e
c
ti
o
n
.
T
h
e
p
e
rsiste
n
c
e
o
f
a
c
a
ll
is
o
n
e
o
f
th
e
m
a
jo
r
q
u
a
li
ty
m
e
a
su
re
m
e
n
ts
in
w
irele
ss
c
e
ll
u
lar
n
e
tw
o
rk
s.
Ha
n
d
o
v
e
r
m
e
c
h
a
n
is
m
p
e
rm
it
s
a
c
e
ll
u
lar
n
e
tw
o
rk
to
o
f
fe
r
su
c
h
a
f
a
c
il
it
y
b
y
a
g
a
in
a
ll
o
c
a
ti
n
g
a
n
o
n
g
o
in
g
c
a
ll
f
ro
m
o
n
e
b
a
se
sta
ti
o
n
t
o
a
n
o
t
h
e
r
b
a
se
sta
ti
o
n
.
T
o
a
c
h
iev
e
h
a
n
d
o
v
e
r
n
e
u
ra
l
n
e
tw
o
rk
tec
h
n
iq
u
e
s
c
a
n
b
e
u
se
d
.
In
th
i
s
p
a
p
e
r,
a
h
a
n
d
o
v
e
r
d
e
c
isio
n
m
e
c
h
a
n
ism
is
p
ro
p
o
se
d
u
si
n
g
Ra
d
ial
Ba
sis
f
u
n
c
ti
o
n
(RBF
)
o
f
n
e
u
ra
l
n
e
tw
o
rk
s.
K
ey
w
o
r
d
:
B
ase
s
tatio
n
H
an
d
o
v
er
R
ad
ial
b
asis
f
u
n
ctio
n
R
ad
io
Co
p
y
rig
h
t
©
201
4
In
s
t
it
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
:
Har
d
ee
p
Kau
r
,
Dep
t.
o
f
E
C
E
GNDU
R
e
g
io
n
a
l Ca
m
p
u
s
S
u
lta
n
p
u
r
L
o
d
h
i
,
Gu
r
u
Na
n
a
k
Dev
U
n
i
v
er
s
it
y
Am
r
it
s
ar
,
I
n
d
ia
E
m
ail:
h
ar
d
ee
p
g
n
d
u
@
g
m
ail.
c
o
m
1.
I
NT
RO
D
UCT
I
O
N
Su
cc
es
s
o
f
w
ir
eles
s
co
m
m
u
n
ic
atio
n
s
h
a
s
ca
u
s
ed
th
e
cr
ea
tio
n
o
f
a
h
u
g
e
v
ar
iet
y
o
f
w
ir
eles
s
tech
n
o
lo
g
ie
s
lik
e
3
G
ce
ll
u
lar
,
s
atellite
s
,
B
lu
eto
o
th
an
d
W
i
-
Fi.
E
v
er
y
tec
h
n
o
lo
g
y
is
p
er
s
o
n
a
lized
to
g
r
asp
a
p
ar
ticu
lar
m
ar
k
et,
o
r
a
s
p
ec
if
ic
t
y
p
e
o
f
o
p
er
ato
r
w
it
h
a
p
r
ec
is
e
s
er
v
ice
n
ee
d
.
T
h
e
b
en
e
f
it
o
f
t
h
ese
d
iv
er
s
e
n
e
t
w
o
r
k
s
i
s
t
h
at
t
h
e
y
p
r
o
v
id
e
m
a
n
y
ch
o
ices
f
o
r
g
r
o
w
i
n
g
b
an
d
w
id
th
,
ac
ce
s
s
i
n
g
th
e
I
n
ter
n
et,
an
d
t
h
e
co
v
er
a
g
e
ar
ea
f
o
r
th
e
av
er
a
g
e
u
s
er
[
1
]
.
I
n
th
e
f
u
t
u
r
e,
th
e
h
o
m
e
an
d
o
f
f
ice
i
n
ter
ac
ti
n
g
a
t
m
o
s
p
h
er
es
ar
e
f
o
r
esee
n
to
b
e
co
n
tr
o
lled
b
y
a
d
i
v
er
s
it
y
o
f
in
ter
ac
ti
v
e
p
r
o
g
r
am
s
er
v
ice
s
lik
e
w
ir
eless
h
o
m
e
en
ter
tai
n
m
en
t,
w
ir
ele
s
s
HDT
V
an
d
v
ir
tu
al
w
ir
eles
s
o
f
f
ice
[
2
]
.
I
n
o
r
d
er
to
p
r
eser
v
e
th
es
e
ap
p
licatio
n
s
,
th
e
w
ir
eless
n
et
w
o
r
k
s
h
o
u
ld
d
eliv
er
th
e
u
s
e
r
w
it
h
tr
an
s
m
i
s
s
io
n
ca
p
ac
it
y
o
f
h
u
n
d
r
ed
s
o
f
Mb
p
s
u
s
i
n
g
s
h
o
r
t
-
r
an
g
e
Gb
p
s
tec
h
n
o
lo
g
y
a
n
d
u
s
i
n
g
tech
n
iq
u
e
s
lik
e
s
o
p
h
is
ticated
co
d
in
g
s
c
h
e
m
es,
an
te
n
n
a
d
iv
er
s
it
y
etc
[
2
]
.
I
t
is
a
s
ig
n
i
f
ica
n
t
an
d
ch
a
llen
g
i
n
g
m
at
ter
to
u
p
k
ee
p
co
n
ti
n
u
o
u
s
h
an
d
o
f
f
i
n
t
h
i
s
co
m
b
i
n
ed
ar
ch
i
tectu
r
e.
Han
d
o
f
f
r
e
f
er
s
to
t
h
e
p
r
o
ce
d
u
r
e
o
f
s
h
i
f
ti
n
g
a
cu
r
r
en
t
ca
ll
o
r
d
ata
s
ess
io
n
f
r
o
m
o
n
e
n
et
w
o
r
k
co
n
n
ec
ted
to
th
e
co
r
e
to
an
o
th
er
.
T
h
e
p
r
o
ce
d
u
r
e
o
f
h
an
d
o
v
er
n
ee
d
s
a
n
u
m
b
er
o
f
p
ar
a
m
eter
s
e.
g
.
h
o
w
m
a
n
y
ch
a
n
n
els
ar
e
f
r
ee
,
w
h
at
i
s
t
h
e
h
a
n
d
o
v
er
p
att
er
n
w
e
ar
e
u
s
i
n
g
.
T
h
e
h
a
n
d
o
v
er
p
r
o
ce
s
s
s
h
o
u
ld
m
ai
n
tai
n
t
h
e
q
u
a
lit
y
o
f
s
er
v
ic
e
u
p
to
t
h
e
s
tan
d
ar
d
.
Her
e,
t
h
e
m
atter
o
f
V
HO
i
n
d
i
v
er
s
e
w
ir
ele
s
s
n
et
w
o
r
k
s
i
s
in
v
e
s
ti
g
ated
[
3
]
.
T
h
is
p
ap
er
illu
s
tr
ates
th
e
u
s
e
o
f
m
u
lt
icast
in
g
tec
h
n
iq
u
es
aid
ed
b
y
m
o
b
ilit
y
ca
lc
u
latio
n
to
i
m
p
r
o
v
e
h
a
n
d
o
f
f
p
er
f
o
r
m
a
n
c
e
in
w
ir
eles
s
n
e
t
w
o
r
k
s
.
Ha
n
d
o
f
f
g
r
asp
s
t
h
e
k
e
y
to
d
ef
in
e
th
e
p
er
f
o
r
m
a
n
ce
o
f
w
ir
ele
s
s
n
et
w
o
r
k
s
.
T
h
e
Gr
e
y
m
o
d
el
h
a
s
b
ee
n
u
s
ed
as
t
h
e
e
s
ti
m
ate
m
e
th
o
d
as
it
h
as
b
ee
n
s
h
o
w
n
to
g
i
v
e
g
o
o
d
f
o
r
ec
ast
ac
cu
r
ac
y
[
4
]
.
W
o
r
ld
w
id
e
w
ir
eles
s
ac
ce
s
s
r
ef
er
s
to
th
e
ca
p
ac
it
y
o
f
a
u
s
er
to
li
n
k
a
n
y
p
lace
at
an
y
p
er
io
d
f
r
o
m
an
y
n
et
w
o
r
k
.
T
h
e
ch
an
g
e
in
j
o
in
in
g
m
a
y
b
e
in
tr
o
d
u
ce
d
b
y
th
e
u
s
er
o
r
m
a
y
h
e
in
tr
o
d
u
ce
d
b
y
th
e
n
et
w
o
r
k
,
clea
r
to
th
e
u
s
er
.
Fo
r
ex
a
m
p
le
,
a
u
s
er
m
a
y
elec
t
ac
ce
s
s
a
w
i
r
eless
L
AN
to
lead
lar
g
e
f
iles
,
b
u
t
m
a
y
elec
t
t
h
e
ce
llu
lar
n
et
w
o
r
k
to
tak
e
a
v
o
ic
e
ca
ll.
On
an
o
th
er
h
an
d
,
a
n
etw
o
r
k
m
a
y
ch
o
o
s
e
to
h
an
d
o
f
f
a
s
tatio
n
ar
y
d
ata
u
s
er
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
IJ
-
AI
Vo
l.
3
,
No
.
2
,
J
u
n
e
201
4
:
79
–
83
80
to
a
w
ir
eles
s
L
AN
in
o
r
d
er
t
o
r
aise
B
an
d
w
id
t
h
av
ailab
il
it
y
f
o
r
m
o
b
ile
u
s
er
s
in
a
3
G
n
etw
o
r
k
.
T
h
e
w
ir
eles
s
tech
n
o
lo
g
y
i
n
th
e
w
ir
eles
s
n
et
w
o
r
k
also
d
ec
id
es th
e
ce
ll to
p
o
lo
g
y
,
ce
ll si
ze
an
d
th
e
tr
af
f
ic
m
o
d
el.
No
w
a
d
a
y
’
s
n
et
w
o
r
k
m
a
y
h
ir
e
m
u
ltip
le
wir
eless
tec
h
n
o
lo
g
ies
at
th
e
s
a
m
e
ti
m
e
s
u
c
h
as:
GSM,
B
lu
e
to
o
th
,
W
L
A
N
a
n
d
UM
T
S.
T
h
is
lead
s
to
a
n
e
w
n
e
ed
o
f
h
an
d
o
f
f
m
et
h
o
d
s
b
et
w
ee
n
d
iv
er
s
e
w
ir
ele
s
s
tec
h
n
o
lo
g
ie
s
;
th
is
is
k
n
o
w
n
a
s
v
er
tical
h
a
n
d
o
f
f
.
B
ec
au
s
e
o
f
t
h
e
m
o
tio
n
o
f
u
s
er
s
a
n
d
th
e
r
a
n
g
e
o
f
3
G
an
d
4
g
u
s
e
s
,
it
is
s
ig
n
i
f
ica
n
t
t
h
at
t
h
e
d
ev
ices
m
a
k
i
n
g
u
s
e
o
f
UM
T
S
s
h
o
u
ld
h
an
d
o
f
f
to
s
ev
er
al
o
th
er
s
y
s
te
m
s
s
u
c
h
as
W
L
A
N,
G
SM,
W
iMA
X
an
d
B
lu
eto
o
th
.
I
n
o
r
d
er
to
k
ee
p
co
n
s
is
ten
t
co
m
m
u
n
icatio
n
i
n
a
m
icr
o
ce
llu
lar
a
n
d
in
ter
w
o
r
k
i
n
g
s
y
s
te
m
n
e
w
an
d
i
m
p
r
o
v
ed
h
an
d
o
f
f
alg
o
r
it
h
m
s
m
u
s
t
b
e
r
eq
u
ir
ed
t
o
k
ee
p
Q
o
S
as
h
ig
h
as
p
o
s
s
ib
le.
Qu
ali
t
y
o
f
s
er
v
ice
m
ea
n
s
p
r
o
v
id
in
g
r
eliab
le,
ex
p
ec
tab
le
d
ata
s
en
d
in
g
s
er
v
ice.
Qu
a
lit
y
o
f
s
er
v
ice
is
allo
ca
ted
b
y
p
r
o
v
id
in
g
r
ea
l
-
ti
m
e
an
d
n
o
n
-
r
ea
l
-
ti
m
e
s
er
v
ices.
R
ea
l
ti
m
e
s
er
v
ices
ar
e
n
ee
d
ed
to
b
e
lead
in
g
o
v
er
n
o
n
r
ea
l
t
i
m
e
f
o
r
Qu
alit
y
o
f
s
er
v
ice
p
r
o
s
p
ec
tiv
e
[
9
]
.
Han
d
o
f
f
alg
o
r
ith
m
s
b
u
il
t
o
n
s
o
f
t
co
m
p
u
tin
g
t
ec
h
n
iq
u
es
s
u
c
h
as
Fu
zz
y
L
o
g
i
c,
Neu
r
al
Net
w
o
r
k
s
etc.
ca
n
b
e
u
s
ed
f
o
r
th
e
s
i
m
ilar
p
u
r
p
o
s
e
[
8
]
.
A
s
i
m
p
le
h
an
d
o
v
er
tech
n
iq
u
e
b
et
w
ee
n
s
o
m
e
h
y
b
r
id
n
et
w
o
r
k
s
is
as
s
h
o
w
n
in
t
h
e
f
ig
u
r
e
b
elo
w
Fig
u
r
e
1
.
Sh
o
w
in
g
h
an
d
o
f
f
b
et
w
ee
n
d
if
f
er
en
t
w
ir
eless
tec
h
n
o
lo
g
ies
1
.
1
.
I
ntr
o
du
ct
io
n t
o
Ra
dia
l
B
a
s
is
F
un
ct
io
n
A
r
ti
f
icial
n
e
u
r
al
n
et
w
o
r
k
(
A
N
N)
is
a
m
ac
h
in
e
lear
n
i
n
g
m
et
h
o
d
o
lo
g
y
t
h
at
r
ep
licas
h
u
m
an
b
r
ain
an
d
co
n
tain
s
a
n
u
m
b
er
o
f
ar
ti
f
icial
n
eu
r
o
n
s
.
Neu
r
o
n
i
n
A
NN
s
h
a
s
a
ten
d
en
c
y
to
h
av
e
f
e
w
er
n
et
wo
r
k
s
th
a
n
b
io
lo
g
ical
n
eu
r
o
n
s
.
E
ac
h
n
e
u
r
o
n
in
A
NN
ac
ce
p
ts
a
n
u
m
b
er
o
f
i
n
p
u
ts
.
An
ac
tiv
at
io
n
f
u
n
ct
io
n
i
s
g
iv
e
n
to
th
ese
in
p
u
ts
w
h
ic
h
ef
f
ec
ts
t
h
e
ac
tiv
at
io
n
lev
e
l
o
f
n
eu
r
o
n
.
R
ad
ial
B
asis
F
u
n
ctio
n
s
ar
e
f
ir
s
t
p
r
esen
ted
in
t
h
e
ex
p
la
n
atio
n
o
f
t
h
e
ac
tu
a
l
m
u
lti
v
ar
iab
le
in
ter
p
o
latio
n
p
r
o
b
lem
s
.
B
r
o
o
m
h
ea
d
an
d
L
o
we
(
1
9
8
8
)
,
Mo
o
d
y
an
d
Dar
k
en
(
1
9
8
9
)
w
er
e
th
e
f
ir
s
t
to
ex
p
lo
it
th
e
u
s
ag
e
o
f
r
ad
ial
b
asis
f
u
n
ctio
n
s
i
n
th
e
s
ch
e
m
e
o
f
n
e
u
r
al
n
et
w
o
r
k
s
R
ad
ial
b
asis
f
u
n
ctio
n
n
et
w
o
r
k
s
ar
e
f
ee
d
-
f
o
r
w
ar
d
n
et
w
o
r
k
s
s
k
il
led
b
y
m
a
k
i
n
g
u
s
e
o
f
a
s
u
p
er
v
i
s
ed
tr
ain
i
n
g
al
g
o
r
ith
m
.
T
h
e
y
ar
e
u
s
u
all
y
o
r
g
a
n
ized
w
it
h
a
s
i
n
g
le
h
id
d
en
la
y
er
o
f
u
n
i
ts
w
h
o
s
e
ac
ti
v
atio
n
f
u
n
cti
o
n
is
ca
r
e
f
u
l
l
y
c
h
o
s
e
n
f
r
o
m
a
g
r
o
u
p
o
f
f
u
n
ctio
n
s
ca
lled
b
asis
f
u
n
ct
io
n
s
.
E
v
en
t
h
o
u
g
h
ali
k
e
b
ac
k
p
r
o
p
ag
atio
n
in
m
a
n
y
f
ea
t
u
r
es,
R
B
F
n
et
wo
r
k
s
h
a
v
e
v
ar
io
u
s
ad
v
an
ta
g
es.
T
h
e
y
u
s
u
a
ll
y
tr
ai
n
m
u
c
h
q
u
ic
k
er
th
a
n
b
ac
k
p
r
o
p
a
g
atio
n
.
T
h
e
y
ar
e
n
o
t
as
m
u
ch
o
f
p
r
o
n
e
to
p
r
o
b
lem
s
w
it
h
n
o
n
-
s
tatio
n
ar
y
i
n
p
u
ts
b
ec
au
s
e
o
f
t
h
e
ac
t
io
n
s
o
f
th
e
R
B
F
h
id
d
en
u
n
it
s
.
R
ad
ial
b
asi
s
f
u
n
ct
io
n
m
et
h
o
d
s
ar
e
m
o
d
er
n
w
a
y
s
to
ap
p
r
o
x
i
m
ate
m
u
lti
v
ar
iate
f
u
n
ctio
n
s
,
p
ar
ticu
lar
l
y
in
th
e
n
o
n
-
ap
p
ea
r
an
ce
o
f
g
r
id
d
ata.
T
h
ey
h
av
e
b
ee
n
r
ec
o
g
n
ized
,
test
ed
a
n
d
ex
a
m
in
ed
f
o
r
n
u
m
er
o
u
s
y
ea
r
s
n
o
w
a
n
d
m
an
y
o
p
ti
m
is
tic
p
r
o
p
er
ties
h
av
e
b
ee
n
r
ec
o
g
n
ized
.
I
n
th
i
s
p
ap
er
,
m
ain
l
y
th
e
n
e
w
r
e
s
u
l
ts
o
n
co
n
v
er
g
en
ce
r
ates
o
f
in
ter
p
o
lat
io
n
w
ith
R
B
F
ar
e
co
n
s
id
er
ed
,
alo
n
g
w
i
th
s
o
m
e
o
f
t
h
e
s
e
v
er
al
attai
n
m
en
t
s
a
n
d
t
h
e
ef
f
ec
t
iv
e
n
u
m
er
ical
ca
lcu
la
tio
n
o
f
i
n
ter
p
o
lates
f
o
r
v
er
y
h
u
g
e
s
et
s
o
f
d
ata
[
5
]
.
T
h
e
id
ea
o
f
R
B
F Ne
t
w
o
r
k
s
d
er
iv
es
f
r
o
m
th
e
t
h
eo
r
y
o
f
p
u
r
p
o
s
e
ap
p
r
o
x
i
m
atio
n
.
1
.
2
.
Str
uct
ure
o
f
t
he
RB
F
Ne
t
w
o
rk
s
R
ad
ial
B
asis
F
u
n
ctio
n
Net
w
o
r
k
s
co
n
s
is
t
s
o
f
3
la
y
er
s
n
a
m
ed
as:
a)
an
in
p
u
t la
y
er
b)
a
h
id
d
en
la
y
er
c)
an
o
u
tp
u
t la
y
er
T
h
e
s
tr
u
ctu
r
e
o
f
a
n
R
B
F
n
et
wo
r
k
s
in
v
o
lv
e
s
th
r
ee
e
n
tire
l
y
d
i
f
f
er
en
t la
y
er
s
as
s
h
o
w
i
n
f
ig
u
r
e
b
elo
w
:
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
AI
I
SS
N:
2252
-
8938
Ha
n
d
o
ve
r
Dec
is
io
n
Mech
a
n
is
m
in
I
n
terw
o
r
kin
g
Tech
n
o
lo
g
i
es
Usi
n
g
R
a
d
ia
l B
a
s
is
…
(
P
a
ya
l Ma
h
a
ja
n
)
81
Fig
u
r
e
2.
R
ad
ial
b
asis
f
u
n
ctio
n
s
T
h
e
h
id
d
en
u
n
it
s
g
i
v
e
a
s
et
o
f
f
u
n
ctio
n
s
t
h
at
s
et
u
p
an
ar
b
itra
r
y
b
asi
s
f
o
r
th
e
i
n
p
u
t
d
esi
g
n
s
[
6
]
.
Hid
d
en
u
n
i
ts
ar
e
ca
lled
r
ad
ial
ce
n
tr
es
co
n
v
er
s
io
n
f
r
o
m
i
n
p
u
t
s
p
ac
e
t
o
h
id
d
en
u
n
it
s
p
ac
e
is
n
o
n
li
n
e
ar
an
d
co
n
v
er
s
io
n
f
r
o
m
h
id
d
en
u
n
it
s
p
ac
e
to
o
u
tp
u
t
s
p
ac
e
is
lin
ea
r
T
h
e
R
B
F
in
th
e
h
id
d
en
la
y
er
p
r
o
d
u
ce
s
an
i
m
p
o
r
tan
t
n
o
n
-
ze
r
o
r
esp
o
n
s
e
o
n
l
y
w
h
e
n
t
h
e
in
p
u
t
d
r
o
p
s
w
i
th
i
n
a
m
in
o
r
r
estricte
d
r
eg
io
n
o
f
th
e
i
n
p
u
t
s
p
ac
e.
E
ac
h
h
id
d
en
u
n
it
h
a
s
its
in
d
i
v
id
u
a
l r
ec
ep
tiv
e
f
ie
ld
in
in
p
u
t sp
ac
e.
T
h
eir
m
ai
n
f
ea
t
u
r
es a
r
e
[
7
]
:
1
.
T
h
ey
ar
e
2
la
y
er
f
ee
d
-
f
o
r
w
ar
d
n
et
w
o
r
k
s
.
2
.
T
h
e
h
id
d
en
n
o
d
es g
i
v
e
a
s
et
o
f
R
B
F (
e.
g
.
Gau
s
s
ia
n
f
u
n
ctio
n
s
)
.
3
.
T
h
e
o
u
tp
u
t n
o
d
es g
i
v
e
li
n
ea
r
b
r
ief
f
u
n
c
tio
n
s
as i
n
an
M
L
P
.
4.
T
h
e
n
et
w
o
r
k
tr
ain
i
n
g
h
as
t
w
o
s
tag
e
s
:
f
ir
s
t
t
h
e
w
ei
g
h
ts
f
r
o
m
th
e
in
p
u
t
to
h
id
d
en
lay
er
ar
e
g
iv
en
,
an
d
th
e
n
th
e
w
ei
g
h
ts
f
r
o
m
t
h
e
h
id
d
en
to
o
u
tp
u
t la
y
er
.
5
.
T
h
e
tr
ain
in
g
is
v
er
y
f
ast.
6
.
T
h
e
n
et
w
o
r
k
s
ar
e
g
o
o
d
at
in
ter
p
o
latio
n
.
2
.
P
RO
P
O
SE
D
WO
RK
I
n
t
h
is
p
ap
er
,
a
h
an
d
o
v
er
m
ec
h
an
i
s
m
i
s
p
r
o
v
id
ed
b
ased
o
n
n
eu
r
al
n
et
w
o
r
k
s
.
Her
e
a
d
ata
s
et
o
f
2
5
0
0
v
alu
e
s
is
cr
ea
ted
o
u
t
o
f
w
h
ich
2
4
0
0
v
alu
es
ar
e
tak
en
as
in
p
u
t
v
alu
e
s
w
h
er
ea
s
1
0
0
ar
e
tak
e
n
f
o
r
test
p
u
r
p
o
s
es.
T
h
e
d
ata
s
et
is
cr
ea
ted
u
s
in
g
f
u
zz
y
i
n
f
er
e
n
ce
s
y
s
te
m
a
n
d
ea
ch
in
p
u
t
v
al
u
e
is
ev
al
u
ated
i
n
FIS
an
d
ac
cu
r
ate
r
esu
lt
s
ar
e
tak
en
to
cr
ea
te
th
e
d
ata
s
et.
T
h
e
MA
T
L
A
B
R
2
0
0
9
b
v
er
s
io
n
is
u
s
ed
.
I
n
th
is
p
ap
er
,
an
R
B
F
n
eu
r
al
n
et
w
o
r
k
to
o
l
o
f
M
A
T
L
A
B
is
u
s
ed
to
f
i
n
d
o
u
t
t
h
e
ac
c
u
r
ac
y
o
f
h
an
d
o
v
er
d
ec
i
s
io
n
s
a
n
d
ti
m
e
ta
k
en
b
y
t
h
e
n
et
w
o
r
k
to
tr
ain
th
e
i
n
p
u
t
v
al
u
es.
T
h
e
f
o
llo
w
i
n
g
tab
le
s
h
o
w
s
t
h
e
d
if
f
e
r
en
t p
ar
a
m
eter
s
ca
lc
u
lated
u
s
i
n
g
R
B
F n
et
w
o
r
k
s
.
T
ab
le
1.
Sh
o
w
i
n
g
d
i
f
f
er
e
n
t p
ar
a
m
eter
s
ca
lc
u
lated
u
s
in
g
R
B
F
S
e
r
i
a
l
n
o
.
n
u
m
b
e
r
o
f
n
e
u
r
o
n
s
a
c
c
u
r
a
c
y
%
me
a
n
s
q
.
e
r
r
o
r
T
i
me
i
n
m
i
n
u
t
e
s
1
50
58
0
.
1
4
0
:
6
0
2
1
0
0
64
0
.
1
1
0
:
6
4
3
1
5
0
68
0
.
0
8
8
0
:
7
0
4
2
0
0
71
0
.
0
7
0
:
8
0
5
2
5
0
78
0
.
0
5
1
:
2
5
6
3
0
0
81
0
.
0
4
7
1
:
5
5
7
3
5
0
85
0
.
0
4
1
:
5
7
8
4
0
0
86
0
.
0
3
5
2
:
0
0
9
4
5
0
88
0
.
0
3
2
2
:
0
5
10
5
0
0
91
0
.
0
3
2
:
5
0
3
.
RE
SUL
T
S AN
D
SI
M
UL
A
T
I
O
NS
T
h
e
Fig
u
r
e
3
an
d
4
s
h
o
w
th
e
d
ec
r
ea
s
e
in
t
h
e
m
ea
n
s
q
u
ar
e
e
r
r
o
r
as
th
e
n
u
m
b
er
o
f
n
e
u
r
o
n
s
in
cr
ea
s
e
s
w
h
ic
h
is
a
d
esira
b
le
f
ac
to
r
f
o
r
s
y
s
te
m
e
f
f
icie
n
c
y
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
IJ
-
AI
Vo
l.
3
,
No
.
2
,
J
u
n
e
201
4
:
79
–
83
82
Fig
u
r
e
3
.
W
h
en
n
u
m
b
er
o
f
n
e
u
r
o
n
s
ta
k
e
n
ar
e
5
0
Fig
u
r
e
4
.
W
h
en
n
u
m
b
er
o
f
n
e
u
r
o
n
s
ta
k
e
n
ar
e
5
0
0
Si
m
i
lar
l
y
o
th
er
g
r
ap
h
s
w
er
e
d
r
a
w
n
in
R
B
F
to
o
l
o
f
M
A
T
L
AB
.
A
s
th
e
n
u
m
b
er
o
f
n
e
u
r
o
n
s
in
cr
ea
s
es,
ti
m
e
ta
k
e
n
to
tr
ai
n
th
e
n
et
w
o
r
k
i
n
cr
ea
s
es
w
h
ic
h
r
ea
c
h
es
u
p
t
o
t
w
o
m
i
n
u
te
s
a
n
d
f
i
f
t
y
s
ec
o
n
d
s
w
h
e
n
t
h
e
n
u
m
b
er
o
f
n
e
u
r
o
n
s
r
ea
ch
e
s
to
f
i
v
e
h
u
n
d
r
ed
.
As
th
e
n
u
m
b
er
o
f
n
e
u
r
o
n
s
in
c
r
ea
s
es,
ac
cu
r
ac
y
i
n
h
a
n
d
o
v
er
d
ec
is
io
n
s
i
n
cr
ea
s
es
a
n
d
it
r
ea
ch
es
u
p
to
9
1
% f
o
r
5
0
0
n
eu
r
o
n
s
w
h
ich
is
ag
ain
a
d
e
s
ir
ab
le
f
ac
to
r
f
o
r
t
h
e
ef
f
icien
t p
er
f
o
r
m
a
n
ce
o
f
t
h
e
s
y
s
te
m
as s
h
o
w
n
in
th
e
f
o
llo
w
i
n
g
f
i
g
u
r
e
:
Fig
u
r
e
5
.
Gr
ap
h
b
et
w
ee
n
n
u
m
b
er
o
f
n
eu
r
o
n
s
a
n
d
ti
m
e
ta
k
en
Fig
u
r
e
6
.
Gr
ap
h
b
et
w
ee
n
n
u
m
b
er
o
f
n
eu
r
o
n
s
a
n
d
ac
cu
r
ac
y
W
ith
th
e
i
n
cr
ea
s
e
i
n
th
e
n
u
m
b
er
o
f
n
eu
r
o
n
s
,
m
ea
n
s
q
u
ar
e
er
r
o
r
d
ec
r
ea
s
es a
s
s
h
o
w
n
i
n
f
o
llo
w
i
n
g
f
i
g
u
r
e
:
Fig
u
r
e
7
.
Gr
ap
h
b
et
w
ee
n
n
u
m
b
er
o
f
n
eu
r
o
n
s
a
n
d
m
ea
n
s
q
u
a
r
e
er
r
o
r
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
AI
I
SS
N:
2252
-
8938
Ha
n
d
o
ve
r
Dec
is
io
n
Mech
a
n
is
m
in
I
n
terw
o
r
kin
g
Tech
n
o
lo
g
i
es
Usi
n
g
R
a
d
ia
l B
a
s
is
…
(
P
a
ya
l Ma
h
a
ja
n
)
83
4
.
CO
NCLUS
I
O
N
T
h
e
h
an
d
o
v
er
d
ec
is
io
n
ca
n
b
e
ca
r
r
ied
o
u
t
u
s
i
n
g
co
n
v
e
n
tio
n
al
s
o
u
r
ce
s
o
r
o
th
er
n
e
u
r
al
n
et
w
o
r
k
tech
n
iq
u
es
b
u
t
w
h
e
n
th
e
h
a
n
d
o
v
er
d
ec
is
io
n
p
ar
a
m
eter
s
ar
e
ca
lcu
lated
u
s
i
n
g
r
ad
ial
b
asi
s
f
u
n
ct
io
n
s
,
i
t
is
s
ee
n
th
at
t
h
e
ti
m
e
tak
e
n
f
o
r
m
ak
in
g
h
an
d
o
v
er
d
ec
is
io
n
s
is
w
ell
u
n
d
er
th
e
p
r
ac
tical
li
m
it
s
also
th
e
ac
cu
r
ac
y
d
r
a
w
n
i
s
m
o
r
e
t
h
a
n
o
th
er
co
n
v
e
n
tio
n
a
l
t
ec
h
n
iq
u
es.
So
,
i
n
t
h
is
p
ap
er
,
it is
p
r
o
p
o
s
ed
th
at
h
a
n
d
o
v
er
d
ec
is
io
n
s
ca
n
b
e
ta
k
en
u
s
i
n
g
R
B
F
to
o
l o
f
n
e
u
r
al
n
et
wo
r
k
in
M
A
T
L
A
B
f
o
r
p
r
ac
tical
u
s
e
s
.
RE
F
E
R
E
NC
E
S
[1
]
M
c
Na
ir,
Ja
n
ise
,
a
n
d
F
a
n
g
Z
h
u
.
"
V
e
rti
c
a
l
h
a
n
d
o
f
f
s
in
f
o
u
rth
-
g
e
n
e
ra
ti
o
n
m
u
lt
in
e
tw
o
rk
e
n
v
iro
n
m
e
n
ts."
W
ire
les
s
Co
mm
u
n
ica
ti
o
n
s,
IE
EE
.
1
1
.
3
(
2
0
0
4
):
8
-
1
5
.
[2
]
V
a
n
Qu
a
n
g
,
Bien
,
R
.
V
e
n
k
a
tes
h
a
P
ra
sa
d
,
a
n
d
Ig
n
a
s
Nie
m
e
g
e
e
rs.
"
A
su
rv
e
y
o
n
h
a
n
d
o
f
f
s
—
le
ss
o
n
s
fo
r
6
0
G
Hz
b
a
se
d
w
irele
ss
s
y
st
e
m
s."
Co
mm
u
n
ica
ti
o
n
s S
u
rv
e
y
s
&
T
u
to
ria
ls,
IEE
E
.
1
4
.
1
(2
0
1
2
):
6
4
-
86.
[3
]
S
a
m
b
a
re
,
S
.
S
.
,
a
n
d
M
a
d
h
u
ri
R.
P
a
w
a
r.
"
A
n
in
teg
ra
ted
W
LA
N
a
n
d
W
iM
A
X
a
rc
h
it
e
c
tu
re
w
it
h
q
o
s
-
b
a
se
d
v
e
rti
c
a
l
h
a
n
d
o
f
f
sc
h
e
m
e
.
"
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l.
2
0
1
3
.
[4
]
V
e
n
k
a
tac
h
a
laia
h
,
S
u
re
sh
,
R
ich
a
rd
J.
Ha
rris,
a
n
d
R
o
b
e
rt
S
u
ry
a
sa
p
u
tra.
"
Imp
ro
v
e
me
n
t
o
f
h
a
n
d
o
ff
i
n
wi
re
les
s
n
e
two
rk
s
u
sin
g
mo
b
il
it
y
p
re
d
icti
o
n
a
n
d
mu
lt
ica
stin
g
tec
h
n
iq
u
e
s
.
"
P
ro
c
e
e
d
i
n
g
s
o
f
th
e
4
t
h
W
S
EA
S
In
tern
a
ti
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
El
e
c
tro
n
ics
,
Ha
rd
w
a
re
,
W
irele
ss
a
n
d
Op
ti
c
a
l
C
o
m
m
u
n
ica
ti
o
n
s
.
W
o
rld
S
c
ien
t
if
ic
a
n
d
E
n
g
in
e
e
rin
g
Ac
a
d
e
m
y
a
n
d
S
o
c
iety
(
W
S
EA
S
),
2
0
0
5
.
[5
]
Bu
h
m
a
n
n
,
M
a
rti
n
D.
"
Ra
d
ial
b
a
sis f
u
n
c
ti
o
n
s."
Acta
Nu
me
ric
a
.
2
0
0
0
9
(2
0
0
0
):
1
-
3
8
.
[6
]
L
a
x
m
id
h
a
r
Be
h
e
ra
“
Ra
d
i
a
l
B
a
si
s
Fu
n
c
ti
o
n
Ne
two
rk
s
”
De
p
a
rtme
n
t
o
f
El
e
c
tri
c
a
l
En
g
in
e
e
ri
n
g
In
d
ian
In
stit
u
te
o
f
T
e
c
h
n
o
lo
g
y
,
Ka
n
p
u
r.
[7
]
Jo
h
n
A
.
Bu
ll
in
a
ria “Ra
d
ial
Ba
sis
F
u
n
c
ti
o
n
Ne
tw
o
rk
s: I
n
tro
d
u
c
ti
o
n
”
[8
]
S
a
ti
,
Da
y
a
l
C.
,
P
a
r
d
e
e
p
Ku
m
a
r,
a
n
d
Yo
g
e
sh
M
isra
.
"
F
P
G
A
i
m
p
lem
e
n
tatio
n
o
f
a
f
u
z
z
y
lo
g
ic
b
a
se
d
h
a
n
d
o
f
f
c
o
n
tro
ll
e
r
f
o
r
m
icro
c
e
ll
u
lar
m
o
b
il
e
n
e
tw
o
rk
s."
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
A
p
p
li
e
d
En
g
in
e
e
rin
g
Res
e
a
rc
h
.
(0
9
7
6
-
4
2
5
9
)
2
.
1
(
2
0
1
1
)
.
[9
]
Ku
m
a
r,
Ra
ji
v
,
a
n
d
Ra
jes
h
Kh
a
n
n
a
.
"
Qu
a
li
ty
o
f
S
e
rv
ice
Ap
p
r
o
a
c
h
i
n
UM
T
S
-
W
L
AN
H
a
n
d
o
v
e
r."
Gr
e
e
n
Co
m
p
u
t
in
g
a
n
d
Co
mm
u
n
ica
ti
o
n
s (
G
re
e
n
Co
m),
IEE
E
In
ter
n
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
o
n
.
I
EE
E,
2
0
1
2
.
Evaluation Warning : The document was created with Spire.PDF for Python.