T
E
L
K
O
M
NIKA
T
elec
o
mm
un
ica
t
io
n,
Co
m
pu
t
ing
,
E
lect
ro
nics
a
nd
Co
ntr
o
l
Vo
l.
18
,
No
.
5
,
Octo
b
er
2
0
2
0
,
p
p
.
2
4
0
1
~
2
4
1
1
I
SS
N:
1
6
9
3
-
6
9
3
0
,
ac
cr
ed
ited
First Gr
ad
e
b
y
Ke
m
e
n
r
is
te
k
d
i
k
ti,
Dec
r
ee
No
: 2
1
/E/KPT
/2
0
1
8
DOI
: 1
0
.
1
2
9
2
8
/
T
E
L
KOM
NI
KA
.
v
1
8
i5
.
1
4
8
5
9
2401
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//jo
u
r
n
a
l.u
a
d
.
a
c.
id
/in
d
ex
.
p
h
p
/TELK
OM
N
I
K
A
Secure and
reliab
le w
ireless
adv
ertising
sy
ste
m
using
intellec
tual cha
ra
cter
isti
c selec
tion
a
lg
o
rith
m
for s
ma
rt
cities
Yo
us
ra
Abdu
l A
ls
a
hi
b S.
Al
deen,
H
a
ider
M
o
ha
m
m
e
d A
bd
ul
ha
di
Co
ll
e
g
e
o
f
S
c
ien
c
e
f
o
r
W
o
m
e
n
,
D
e
p
a
rtme
n
t
o
f
Co
m
p
u
ter S
c
ien
c
e
,
Un
iv
e
rsit
y
o
f
B
a
g
h
d
a
d
,
Ira
q
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Dec
6
,
2
0
1
9
R
ev
i
s
ed
Ma
r
2
5
,
2
0
2
0
A
cc
ep
ted
A
p
r
1
1
,
2
0
2
0
S
m
a
rt
c
it
ies
w
ir
e
les
s
a
d
v
e
rti
si
n
g
(
sm
a
rt
m
o
b
il
e
-
A
D)
f
il
e
d
is
o
n
e
o
f
th
e
w
e
ll
-
k
n
o
w
n
a
re
a
o
f
re
se
a
rc
h
w
h
e
re
s
m
a
rt
d
e
v
i
c
e
s
u
sin
g
m
o
b
il
e
a
d
h
o
c
n
e
tw
o
rk
s
(M
A
NE
T
)
p
latf
o
r
m
fo
r
a
d
v
e
rti
se
m
e
n
t
a
n
d
m
a
rk
e
ti
n
g
p
u
rp
o
se
s.
W
irele
ss
a
d
v
e
rti
sin
g
th
ro
u
g
h
m
u
lt
ip
le
f
u
sio
n
i
n
tern
e
t
o
f
th
in
g
s
(Io
T
)
se
n
so
rs
is
o
n
e
o
f
th
e
im
p
o
rtan
t
f
ield
w
h
e
re
th
e
se
n
so
rs
c
o
m
b
in
e
s
m
u
lt
ip
le
se
n
so
rs
in
f
o
rm
a
ti
o
n
a
n
d
a
c
c
o
m
p
li
sh
th
e
c
o
n
tr
o
l
o
f
se
lf
-
g
o
v
e
rn
in
g
in
telli
g
e
n
t
m
a
c
h
in
e
s
f
o
r
sm
a
rt
c
it
ies
a
d
v
e
rti
sin
g
f
ra
m
e
w
o
rk
.
W
it
h
m
a
n
y
a
d
v
a
n
tag
e
s,
th
i
s
f
ield
h
a
s
su
ff
e
re
d
w
it
h
d
a
ta
se
c
u
rit
y
.
In
o
rd
e
r
to
tac
k
le
se
c
u
rit
y
th
re
a
ts,
in
tru
si
o
n
d
e
tec
ti
o
n
sy
ste
m
(I
DS)
is
a
d
o
p
te
d
.
Ho
w
e
v
e
r,
th
e
e
x
isti
n
g
IDS
s
y
st
e
m
a
re
n
o
t
a
b
le
to
f
u
lf
il
l
th
e
se
c
u
rit
y
re
q
u
ir
e
m
e
n
ts.
T
h
is
p
a
p
e
r
p
r
o
p
o
se
s
a
n
i
n
tellec
tu
a
l
c
h
a
ra
c
teristic
se
lec
ti
o
n
a
lg
o
rit
h
m
(ICS
A
)
in
teg
ra
t
e
d
w
it
h
n
o
rm
a
li
z
e
d
in
telli
g
e
n
t
g
e
n
e
ti
c
a
lg
o
ri
th
m
-
b
a
se
d
m
in
-
m
a
x
fe
a
tu
re
se
lec
ti
o
n
(NI
GA
-
M
F
S
).
T
h
e
p
ro
p
o
se
d
s
o
l
u
ti
o
n
d
e
sig
n
s
f
o
r
w
irele
ss
a
d
v
e
rti
sin
g
s
y
ste
m
f
o
r
b
u
sin
e
ss
/ad
v
e
rti
sin
g
d
a
ta
se
c
u
rit
y
a
n
d
o
th
e
r
tran
sa
c
ti
o
n
s
u
sin
g
in
d
e
p
e
n
d
e
n
t
re
c
o
n
f
ig
u
ra
b
le
a
rc
h
it
e
c
tu
re
.
T
h
is
a
p
p
ro
a
c
h
s
u
p
p
o
rts
t
h
e
w
irele
ss
a
d
v
e
rti
sin
g
p
o
rtals
t
o
m
a
n
a
g
e
th
e
d
a
ta
d
e
li
v
e
r
y
b
y
u
sin
g
4
G
sta
n
d
a
rd
.
T
h
e
p
ro
p
o
se
d
re
c
o
n
f
ig
u
ra
b
le
a
rc
h
it
e
c
tu
re
is
v
a
li
d
a
ted
b
y
u
sin
g
a
p
p
l
ica
ti
o
n
s
sp
e
c
if
ic
to
m
icro
c
o
n
tro
ll
e
rs w
it
h
m
u
lt
ip
le f
u
sio
n
I
o
T
se
n
so
rs.
K
ey
w
o
r
d
s
:
I
n
ter
n
et
o
f
t
h
i
n
g
s
I
n
tr
u
s
io
n
d
etec
tio
n
s
y
s
te
m
Mo
b
ile
ad
-
h
o
c
n
et
w
o
r
k
s
Mu
ltip
le
f
u
s
io
n
s
en
s
o
r
s
W
ir
ele
s
s
ad
v
er
tis
i
n
g
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r
th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Yo
u
s
r
a
A
b
d
u
l
A
ls
a
h
ib
S.
A
ld
e
en
,
C
o
lleg
e
o
f
Scien
ce
f
o
r
W
o
m
e
n
,
Dep
ar
t
m
en
t o
f
C
o
m
p
u
ter
Sc
ie
n
ce
,
Un
i
v
er
s
it
y
o
f
B
ag
h
d
ad
,
I
r
aq
.
E
m
ail:
y
o
u
s
r
aa
l
k
aa
le
s
i@
g
m
ail
.
co
m
1.
I
NT
RO
D
UCT
I
O
N
I
n
tr
u
s
io
n
d
etec
tio
n
s
y
s
te
m
(
I
DS)
is
p
la
y
i
n
g
a
s
i
g
n
i
f
ican
t r
o
le
f
o
r
d
ata
s
ec
u
r
it
y
o
f
w
ir
eles
s
a
d
v
er
tis
i
n
g
d
ata
in
m
o
b
ile
ad
-
h
o
c
n
et
w
o
r
k
s
(
M
A
NE
T
)
p
latf
o
r
m
.
I
DS
s
y
s
te
m
s
ar
e
u
s
ed
to
d
etec
t
th
e
k
n
o
w
n
a
n
d
u
n
k
n
o
wn
attac
k
s
[1
-
3]
.
T
h
e
attac
k
s
d
ete
ctio
n
o
n
w
ir
e
less
ad
v
er
tis
i
n
g
i
n
m
o
b
ile
ad
h
o
c
n
e
t
w
o
r
k
s
is
a
d
if
f
icu
l
t
tas
k
t
h
a
n
f
i
x
ed
w
ir
ed
n
et
w
o
r
k
s
,
b
ec
au
s
e
o
f
th
e
n
o
d
es
m
o
b
ilit
y
a
n
d
d
y
n
a
m
ic
to
p
o
lo
g
ies
[
4
,
5
]
.
I
n
th
ese
n
et
w
o
r
k
s
,
th
e
n
et
w
o
r
k
s
ar
e
m
o
r
e
co
m
p
l
ex
w
h
er
e
m
ai
n
te
n
a
n
ce
an
d
o
th
er
co
m
p
lex
itie
s
ex
i
s
t
[
6
,
7
]
.
Mo
r
eo
v
er
,
f
e
w
m
o
r
e
ad
d
iti
o
n
al
ch
alle
n
g
es
ar
e
also
p
r
esen
t
in
th
e
d
etec
tio
n
o
f
at
tack
s
i
n
cl
u
d
in
g
lac
k
o
f
m
o
n
it
o
r
in
g
f
ac
ilit
ie
s
f
o
r
th
e
m
o
b
ile
n
o
d
es
in
t
h
e
n
et
wo
r
k
.
T
h
er
ef
o
r
e,
th
er
e
is
n
ee
d
to
d
esig
n
m
o
r
e
s
u
i
tab
le
ap
p
r
o
ac
h
to
h
an
d
le
th
e
s
e
n
et
w
o
r
k
s
ch
ar
ac
ter
is
tic
s
an
d
n
ee
d
to
an
aly
z
e
t
h
e
s
ec
u
r
i
t
y
atta
ck
s
d
ataset
s
to
d
ev
elo
p
an
ef
f
ic
ien
t
I
DS.
R
ec
e
n
tl
y
,
th
e
attac
k
s
d
etec
tio
n
o
f
in
tr
u
d
er
s
ef
f
ec
tiv
e
l
y
o
n
w
ir
eless
ad
v
er
tis
i
n
g
in
M
ANE
T
is
p
r
o
ce
s
s
ed
u
s
in
g
f
ea
tu
r
i
n
g
ap
p
r
o
ac
h
es
[
8
]
.
C
lass
if
icatio
n
m
et
h
o
d
s
ar
e
u
s
ed
to
ca
teg
o
r
iz
ed
th
e
n
o
d
es
in
to
n
o
r
m
al
an
d
ab
n
o
r
m
al
w
h
ic
h
ar
e
b
ased
o
n
ce
r
tain
co
n
d
itio
n
s
.
Ma
n
y
s
o
f
t
co
m
p
u
ti
n
g
tec
h
n
iq
u
es
ar
e
i
n
tr
o
d
u
ce
d
i
n
t
h
e
p
ast
w
it
h
e
f
f
ec
t
iv
e
d
atasets
[
9
]
.
A
d
d
itio
n
all
y
,
t
h
e
ex
is
t
in
g
clas
s
i
f
icatio
n
tech
n
iq
u
es
ar
e
n
o
t
ab
le
to
clas
s
if
y
t
h
e
d
atasets
s
u
cc
es
s
f
u
ll
y
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
18
,
No
.
5
,
Octo
b
e
r
2
0
2
0
:
2
4
0
1
-
2411
2402
to
d
etec
t
th
e
i
n
tr
u
d
er
s
w
it
h
al
l
k
in
d
s
o
f
attac
k
s
.
I
n
[
1
0
]
,
a
f
ea
t
u
r
e
s
elec
t
io
n
tec
h
n
iq
u
e
i
s
i
n
tr
o
d
u
ce
d
f
o
r
i
m
p
r
o
v
in
g
th
e
clas
s
i
f
icati
o
n
ac
c
u
r
ac
y
[
1
1
]
.
I
n
th
is
co
n
te
x
t,
th
is
p
ap
er
p
r
o
p
o
s
es
a
tr
u
s
t
b
ased
r
o
u
tin
g
p
r
o
to
co
l
f
o
r
f
in
d
th
e
s
u
itab
le
an
d
s
ec
u
r
e
r
o
u
tes
in
t
h
e
n
et
w
o
r
k
.
Sp
ec
if
ical
l
y
,
an
I
n
tellect
u
al
c
h
ar
ac
ter
is
t
ic
s
elec
tio
n
al
g
o
r
ith
m
(
I
C
S
A
)
i
n
teg
r
ated
w
it
h
n
o
r
m
alize
d
in
tel
lig
e
n
t
g
e
n
etic
alg
o
r
ith
m
b
ased
m
i
n
-
m
a
x
f
ea
tu
r
e
s
elec
tio
n
(
NI
G
A
-
MFS)
d
esig
n
s
f
o
r
ef
f
ec
ti
v
e
p
r
e
-
p
r
o
ce
s
s
in
g
o
f
i
n
tr
u
s
io
n
d
etec
tio
n
d
ataset
i
n
w
ir
el
ess
ad
v
er
ti
s
in
g
f
r
a
m
e
w
o
r
k
o
f
s
m
ar
t
cit
ies.
T
h
e
r
est
o
f
th
e
p
ap
er
is
o
r
g
an
ized
as
f
o
llo
w
s
:
s
ec
t
io
n
2
p
r
esen
t
s
th
e
r
elate
d
w
o
r
k
i
n
t
h
e
d
o
m
ai
n
.
Sectio
n
3
illu
s
tr
ates
th
e
p
r
o
p
o
s
ed
ap
p
r
o
a
ch
,
its
p
r
o
ce
s
s
,
d
esig
n
an
d
alg
o
r
ith
m
.
Sectio
n
4
d
is
cu
s
s
es
th
e
s
i
m
u
latio
n
r
esu
lt
s
an
d
d
is
cu
s
s
io
n
.
P
ap
er
co
n
clu
d
es in
las
t
s
ec
tio
n
w
it
h
f
u
t
u
r
e
d
ir
ec
tio
n
.
2.
RE
L
AT
E
D
WO
RK
T
h
is
s
ec
tio
n
d
is
c
u
s
s
e
s
th
e
ex
is
ti
n
g
ap
p
r
o
ac
h
es
to
d
ea
l
th
e
s
ec
u
r
it
y
attac
k
s
i
n
w
ir
eles
s
ad
v
er
tis
i
n
g
M
ANE
T
.
2
.
1
.
F
e
a
t
ure
s
elec
t
io
n t
ec
hn
iqu
es
Featu
r
e
s
elec
tio
n
tech
n
iq
u
e
s
ar
e
in
tr
o
d
u
ce
d
b
y
m
a
n
y
r
esea
r
ch
er
s
w
h
o
ar
e
w
o
r
k
i
n
g
i
n
th
e
ar
ea
s
o
f
m
ed
ical
d
ata
m
i
n
i
n
g
,
i
m
ag
e
p
r
o
ce
s
s
in
g
an
d
in
tr
u
s
io
n
d
etec
tio
n
.
I
n
all
th
ese
ap
p
licatio
n
s
,
f
ea
t
u
r
e
s
elec
tio
n
is
u
s
ed
to
s
e
lect
t
h
e
o
p
ti
m
a
l
n
u
m
b
er
o
f
f
ea
tu
r
e
s
f
r
o
m
t
h
e
d
atasets
co
n
s
is
tin
g
o
f
m
o
r
e
n
u
m
b
er
o
f
f
ea
t
u
r
es.
I
n
th
e
p
ast,
s
e
v
er
al
r
esear
ch
w
o
r
k
s
h
av
e
ac
co
m
p
lis
h
ed
b
y
v
ar
io
u
s
r
e
s
ea
r
ch
er
s
.
Am
o
n
g
t
h
e
m
,
in
[
1
2
]
au
t
h
o
r
s
p
r
o
p
o
s
ed
th
e
f
ir
s
t
in
cr
e
m
e
n
tal
b
ased
alg
o
r
ith
m
f
o
r
f
ea
t
u
r
e
s
el
e
ctio
n
w
h
ic
h
is
u
s
ed
to
f
in
d
th
e
r
elev
an
t
f
ea
t
u
r
es
w
h
ic
h
ar
e
s
u
itab
le
to
s
o
l
v
e
t
h
e
p
r
o
b
lem
w
it
h
o
p
ti
m
al
n
u
m
b
er
o
f
f
ea
tu
r
es.
I
n
t
h
eir
w
o
r
k
,
t
h
e
n
u
m
b
er
o
f
f
ea
t
u
r
es
an
d
p
atter
n
s
ar
e
h
u
g
e
i
n
t
h
eir
d
ataset.
T
h
er
ef
o
r
e,
th
e
p
r
o
p
o
s
ed
an
d
ef
f
ec
ti
v
e
m
eth
o
d
f
o
r
f
ea
t
u
r
e
s
elec
tio
n
ca
n
h
e
lp
in
d
i
m
en
s
io
n
alit
y
r
ed
u
ctio
n
.
T
h
ey
also
d
esig
n
ed
an
in
cr
e
m
en
tal
p
r
o
b
ab
ili
s
tic
alg
o
r
ith
m
as
an
alter
n
ativ
e
ap
p
r
o
ac
h
to
th
e
ex
h
a
u
s
t
iv
e
a
n
d
h
e
u
r
is
tic
m
et
h
o
d
s
.
I
n
[
1
3
]
,
au
th
o
r
s
p
r
o
p
o
s
ed
an
in
cr
e
m
e
n
tal
f
ea
t
u
r
e
s
elec
tio
n
al
g
o
r
ith
m
(
I
FS
A
)
w
h
ich
i
s
d
y
n
a
m
ic
i
n
n
atu
r
e
f
o
r
tak
in
g
d
ec
is
io
n
s
o
v
er
th
e
d
if
f
er
e
n
t
f
u
n
ct
io
n
alit
ies
.
T
h
is
alg
o
r
ith
m
is
ca
p
ab
le
to
av
o
id
th
e
r
e
-
co
m
p
u
tatio
n
p
r
o
ce
s
s
i
n
s
tead
o
f
r
etr
ain
in
g
t
h
e
s
u
b
s
et
f
r
o
m
s
cr
at
ch
.
I
n
[
1
4
]
,
au
th
o
r
s
d
ev
elo
p
ed
a
n
e
w
ev
o
l
u
tio
n
ar
y
-
i
n
cr
e
m
e
n
tal
f
r
a
m
e
w
o
r
k
f
o
r
f
e
atu
r
e
s
elec
t
io
n
.
T
h
i
s
f
r
a
m
e
w
o
r
k
is
ap
p
lied
o
n
a
n
o
r
d
in
ar
y
e
v
o
lu
tio
n
ar
y
al
g
o
r
i
th
m
ca
lled
g
e
n
etic
al
g
o
r
ith
m
.
T
h
is
f
r
a
m
e
w
o
r
k
i
n
tr
o
d
u
ce
d
s
o
m
e
g
e
n
er
ic
m
o
d
i
f
icat
io
n
s
o
n
o
r
d
in
ar
y
ev
a
lu
atio
n
alg
o
r
it
h
m
s
w
h
ic
h
ar
e
co
m
p
atib
le
w
it
h
t
h
e
v
ar
iab
le
l
en
g
t
h
o
f
s
o
l
u
tio
n
s
.
Mo
r
eo
v
er
,
th
is
f
r
a
m
e
w
o
r
k
is
d
ep
lo
y
ed
f
o
r
p
er
f
o
r
m
i
n
g
cl
ass
i
f
icatio
n
o
p
er
atio
n
w
it
h
t
w
o
n
e
w
o
p
er
ato
r
s
n
a
m
e
l
y
ad
d
itio
n
a
n
d
d
eletio
n
o
p
er
ato
r
s
w
h
ic
h
ch
a
n
g
e
t
h
e
le
n
g
t
h
o
f
s
o
lu
tio
n
s
r
a
n
d
o
m
l
y
.
I
n
[
1
5
]
,
au
th
o
r
s
p
r
o
p
o
s
ed
a
n
e
w
u
n
s
u
p
er
v
is
ed
f
ea
tu
r
e
s
elec
ti
o
n
m
et
h
o
d
f
o
r
ef
f
ec
ti
v
e
d
ec
is
i
o
n
m
a
k
i
n
g
o
v
er
th
e
d
ata
s
et.
I
n
[
1
6
]
,
au
th
o
r
s
p
r
o
p
o
s
ed
a
n
e
w
m
o
d
el
f
o
r
f
ea
tu
r
e
s
elec
tio
n
b
ased
o
n
co
m
b
i
n
atio
n
o
f
in
cr
e
m
e
n
tal
m
i
x
ed
v
ar
iab
le
a
n
t
co
lo
n
y
o
p
ti
m
izatio
n
(
I
AC
OM
V)
an
d
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
i
n
e
(
SVM)
f
o
r
s
o
lv
in
g
th
e
m
o
d
el
s
elec
tio
n
p
r
o
b
le
m
s
ef
f
ec
tiv
e
l
y
.
I
n
[
1
7
]
,
au
th
o
r
s
p
r
o
p
o
s
ed
a
m
ac
h
in
e
lear
n
in
g
al
g
o
r
ith
m
v
er
s
io
n
o
f
th
e
b
in
ar
y
b
at
alg
o
r
ith
m
(
B
B
A)
f
o
r
p
er
f
o
r
m
i
n
g
ef
f
ec
tiv
e
clas
s
if
ica
tio
n
.
Ho
w
e
v
er
,
all
d
is
cu
s
s
ed
ap
p
r
o
ac
h
es a
r
e
n
o
t
s
u
itab
le
f
o
r
f
ea
t
u
r
e
s
elec
tio
n
i
n
i
n
tr
u
s
io
n
d
etec
tio
n
a
p
p
licatio
n
s
[
1
8
]
.
Mo
r
eo
v
er
,
t
h
e
ex
is
ti
n
g
f
ea
tu
r
e
s
elec
tio
n
alg
o
r
it
h
m
s
ar
e
m
o
r
e
co
m
p
le
x
a
n
d
h
en
ce
th
e
y
co
n
s
u
m
e
lo
t
o
f
t
i
m
e
f
o
r
co
n
v
er
g
en
c
e.
T
h
er
ef
o
r
e,
a
n
e
w
f
ea
t
u
r
e
s
elec
tio
n
al
g
o
r
ith
m
s
n
ee
d
ed
to
ad
d
r
ess
th
e
e
x
i
s
ti
n
g
ap
p
r
o
ac
h
es
li
m
itatio
n
s
a
n
d
b
est
s
o
lu
t
io
n
f
o
r
s
elec
ti
n
g
o
p
ti
m
al
n
u
m
b
er
o
f
f
e
atu
r
es.
3.
I
NT
E
L
L
E
CT
UAL CH
AR
A
CT
E
RIS
T
I
C
SE
L
E
CT
I
O
N
AL
G
O
RI
T
H
M
(
I
CSA
)
Du
e
to
r
an
d
o
m
d
ep
lo
y
m
e
n
t
o
f
s
tatic
s
en
s
o
r
n
o
d
es
an
d
en
v
ir
o
n
m
e
n
tal
f
ac
to
r
s
,
ex
is
te
n
ce
o
f
m
an
y
is
s
u
e
s
an
d
lo
o
p
h
o
les
i
n
w
ir
ele
s
s
s
e
n
s
o
r
n
e
t
w
o
r
k
s
(
W
SN)
is
in
e
v
itab
le
in
s
m
ar
t
citie
s
.
T
h
ese
l
i
m
itat
io
n
s
r
esu
lt
i
n
r
ed
u
cin
g
th
e
d
ata
tr
an
s
m
i
s
s
io
n
p
er
f
o
r
m
a
n
ce
in
ter
m
s
o
f
d
ata
r
eliab
ilit
y
,
d
ata
tr
an
s
f
er
in
w
ir
ele
s
s
ad
v
er
tis
i
n
g
an
d
in
en
er
g
y
co
n
s
u
m
p
tio
n
i
n
w
ir
eless
ad
v
er
ti
s
i
n
g
f
r
a
m
e
w
o
r
k
s
.
C
o
n
s
eq
u
e
n
tl
y
,
t
h
e
f
u
l
f
ill
t
h
e
all
n
et
w
o
r
k
r
eq
u
ir
e
m
en
ts
is
a
n
i
m
p
o
r
ta
n
t
f
ac
to
r
f
o
r
p
r
o
lo
n
g
in
g
t
h
e
n
et
w
o
r
k
li
f
eti
m
e
o
n
w
ir
ele
s
s
ad
v
er
tis
i
n
g
i
n
M
A
NE
T
p
latf
o
r
m
.
T
h
e
p
r
o
p
o
s
ed
f
r
a
m
e
w
o
r
k
s
h
o
w
s
i
n
F
ig
u
r
e
1
.
T
h
e
n
et
w
o
r
k
li
f
eti
m
e
o
f
th
e
i
n
ter
n
et
o
f
t
h
in
g
s
(
I
o
T
)
s
en
s
o
r
n
o
d
es
ca
n
b
e
im
p
r
o
v
ed
b
y
d
ep
lo
y
i
n
g
th
e
ad
d
itio
n
al
m
o
b
ile
s
en
s
o
r
s
an
d
s
tatic
s
e
n
s
o
r
d
ep
lo
y
m
e
n
t.
Fin
d
i
n
g
t
h
e
n
u
m
b
er
o
f
ad
d
iti
o
n
al
I
o
T
s
en
s
o
r
s
i
n
th
e
n
e
t
w
o
r
k
s
lead
s
to
o
p
ti
m
iz
atio
n
p
r
o
b
lem
.
I
n
tellect
u
al
c
h
ar
ac
ter
is
tic
s
elec
tio
n
al
g
o
r
ith
m
(
I
C
S
A
)
p
r
ese
n
ts
to
o
b
tain
th
e
b
est/
o
p
ti
m
a
l
co
v
er
ag
e
w
ith
h
i
g
h
r
eliab
ilit
y
o
f
d
ata
tr
an
s
f
er
o
f
n
et
w
o
r
k
ar
ea
b
y
I
o
T
s
en
s
o
r
n
o
d
es.
T
h
e
r
eq
u
ir
ed
n
u
m
b
er
s
o
f
s
tat
ic
s
en
s
o
r
s
ar
e
d
ep
lo
y
ed
r
an
d
o
m
l
y
i
n
th
e
m
o
n
ito
r
i
n
g
ar
ea
.
Af
ter
d
ep
lo
y
m
en
t
o
f
th
e
s
i
n
k
n
o
d
es,
n
o
d
es
s
e
n
d
a
h
ello
m
es
s
ag
e
to
all
o
th
er
s
en
s
o
r
n
o
d
es
in
t
h
e
n
et
w
o
r
k
,
a
s
a
r
ep
ly
t
h
e
n
o
d
es
s
en
d
t
h
eir
lo
ca
tio
n
an
d
n
o
d
e_
id
to
s
in
k
n
o
d
e.
B
y
u
s
i
n
g
t
h
ese
in
f
o
r
m
atio
n
,
s
i
n
k
n
o
d
es
ap
p
l
y
th
e
b
i
n
ar
y
d
etec
tio
n
m
o
d
el
to
d
etec
t
t
h
e
h
o
les
i
n
t
h
e
co
v
er
ag
e
o
f
m
o
n
ito
r
in
g
r
eg
io
n
d
u
r
i
n
g
in
f
o
r
m
at
io
n
tr
an
s
m
is
s
io
n
o
n
w
ir
eles
s
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
S
ec
u
r
e
a
n
d
r
elia
b
le
w
ir
eles
s
a
d
ve
r
tis
in
g
s
ystem
u
s
in
g
…
(
Yo
u
s
r
a
A
b
d
u
l A
ls
a
h
ib
S
.
A
ld
e
en
)
2403
ad
v
er
tis
i
n
g
p
lat
f
o
r
m
.
Af
ter
o
b
tain
i
n
g
t
h
e
co
v
er
ag
e
m
ap
,
th
e
s
in
k
ca
lcu
la
tes
th
e
o
p
ti
m
al
n
u
m
b
er
o
f
ad
d
it
io
n
al
s
en
s
o
r
r
eq
u
ir
ed
an
d
d
e
p
lo
y
s
t
h
o
s
e
m
o
b
ile
s
e
n
s
o
r
s
r
an
d
o
m
l
y
.
E
ac
h
m
o
b
ile
s
e
n
s
o
r
is
m
o
d
eled
as
a
ch
ar
g
ed
p
ar
ticle
in
elec
tr
o
m
a
g
n
et
is
m
a
lg
o
r
ith
m
a
n
d
th
e
I
C
S
A
alg
o
r
it
h
m
ca
lcu
late
s
t
h
e
to
tal
f
o
r
ce
a
p
p
lied
o
n
th
e
m
o
b
ile
s
en
s
o
r
b
y
n
eig
h
b
o
r
’
s
I
o
T
s
en
s
o
r
s
an
d
f
it
n
ess
(
A
i)
v
alu
e
s
.
=
[
1
∗
(
)
(
)
+
2
∗
(
(
)
)
+
3
∗
(
(
,
)
]
/
[
1
+
2
+
3
]
;
(
1
)
>
=
ℎ
>
=
ℎ
(
2
)
=
(
)
(
)
;
(
3
)
>
=
ℎ
<
ℎ
(
4
)
=
(
)
;
(
5
)
<
ℎ
>
=
ℎ
(
6
)
=
(
)
;
(
7
)
Fro
m
t
h
e
(1
-
4
)
d
en
o
te
t
h
e
f
it
n
ess
f
u
n
ct
io
n
to
c
h
ec
k
t
h
e
I
n
f
o
g
ain
r
atio
(
I
GR
)
a
n
d
f
ea
t
u
r
es
a
r
e
s
e
lecte
d
(
SS
)
b
ased
o
n
th
e
th
r
esh
o
ld
(
T
h
)
A
ND
f
it
n
es
s
(
A
j
)
f
u
n
ctio
n
as
p
r
esen
t
s
in
t
h
e
Alg
o
r
it
h
m
1
.
T
h
e
to
tal
f
o
r
ce
d
eter
m
in
e
s
th
e
d
ir
ec
tio
n
o
f
th
e
m
o
b
ile
n
o
d
e;
m
o
v
e
th
e
m
o
b
ile
n
o
d
e
ac
co
r
d
in
g
l
y
;
if
th
e
m
o
b
ile
n
o
d
e
is
n
o
t
in
o
p
tim
u
m
p
o
s
itio
n
,
t
h
en
ap
p
l
y
g
en
et
ic
o
p
er
ato
r
s
o
n
th
e
lo
c
atio
n
o
f
t
h
e
s
en
s
o
r
an
d
ap
p
ly
A
V
F
A
alg
o
r
it
h
m
.
T
h
is
w
il
l c
o
n
ti
n
u
e
t
ill all
t
h
e
m
o
b
ile
s
en
s
o
r
s
ar
e
m
o
v
ed
to
o
p
ti
m
al
lo
ca
tio
n
.
Fig
u
r
e
1
.
Ov
er
all
o
p
er
atio
n
o
f
th
e
p
r
o
p
o
s
ed
f
r
am
e
w
o
r
k
f
o
r
wir
eless
ad
v
er
ti
s
in
g
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
18
,
No
.
5
,
Octo
b
e
r
2
0
2
0
:
2
4
0
1
-
2411
2404
I
n
th
is
w
o
r
k
,
I
C
S
A
is
p
r
o
p
o
s
ed
w
it
h
th
e
co
m
b
in
a
tio
n
o
f
GA
a
n
d
I
AA
S
A
.
Her
e,
I
AAS
A
s
elec
ts
th
e
in
i
tial
s
u
b
s
ets
an
d
th
e
n
ap
p
lies
th
e
cr
o
s
s
o
v
er
f
it
n
es
s
s
el
ec
tio
n
(
C
FS
)
f
o
r
m
u
la
tio
n
f
o
r
f
i
n
alizi
n
g
t
h
e
ex
ac
t
f
ea
t
u
r
es
w
h
ic
h
ar
e
u
s
e
f
u
l
f
o
r
id
en
ti
f
y
i
n
g
th
e
f
o
u
r
t
y
p
es
o
f
attac
k
s
.
Fi
n
all
y
,
th
e
h
id
d
en
s
e
m
i
-
Ma
r
k
o
v
m
o
d
el
(
HSMM
)
[
1
9
]
an
d
SVM
[
2
0
]
ar
e
u
s
ed
f
o
r
clas
s
i
f
icatio
n
f
o
r
s
elec
ted
f
ea
tu
r
es.
T
h
ese
clas
s
if
ica
tio
n
tas
k
s
ar
e
ca
r
r
ied
o
u
t
u
s
i
n
g
t
h
e
ex
is
ti
n
g
class
i
f
ier
to
tes
t
t
h
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
p
r
o
p
o
s
ed
f
ea
t
u
r
e
s
elec
tio
n
al
g
o
r
ith
m
s
.
T
h
e
I
AA
S
A
u
s
es t
h
e
I
GR
w
h
i
ch
is
co
m
p
u
ted
u
s
in
g
t
h
e
(
8
-
10
)
.
(
)
=
−
∑
[
(
,
)
|
|
]
=
1
2
[
(
,
)
|
|
]
(
8
)
(
)
=
−
∑
[
|
|
|
|
]
=
1
×
(
)
(
9
)
(
)
=
[
(
)
−
(
)
(
)
+
(
)
]
×
(
)
(
10
)
Her
e,
D
is
t
h
e
d
ataset,
C
i
is
t
h
e
f
r
a
g
m
en
ts
m
ad
e
f
r
o
m
t
h
e
d
ataset,
F
is
t
h
e
f
ea
t
u
r
e
s
et
with
F
i
as
t
h
e
f
ea
t
u
r
e
an
d
I
GR
i
n
d
icate
s
t
h
e
i
n
f
o
r
m
a
tio
n
g
ai
n
r
atio
(
I
GR
)
.
T
h
e
w
o
r
d
in
f
o
i
n
d
icate
s
t
h
e
i
n
f
o
r
m
atio
n
g
ai
n
v
al
u
es.
No
w
,
th
e
s
tep
s
o
f
th
e
p
r
o
p
o
s
ed
A
lg
o
r
ith
m
1
ar
e
as f
o
llo
w
s
:
I
n
telli
g
en
t
ag
e
n
t b
ased
in
cr
e
m
en
tal
f
ea
tu
r
e
s
e
lectio
n
al
g
o
r
ith
m
Step 1:
The intelligent agents divide the dataset D into n subsets of equal size and
named as C1, C2,…Cn.
Step 2:
Agent computes the IGR value for every attribute (A
i
) of the dataset using
(
4
)
to obtain the value of IGR(A
i
) and is expressed
as:
(
)
=
[
(
)
−
(
)
(
)
+
(
)
]
×
(
)
Step 3:
The agent selects a feature from dataset which has maximum IGR.
Step 4:
Now the agent divides the sub datasets C
i
into two subsets based on their
distance between the neighbour nodes.
Step 5:
Make the first part of each subset as parents in the genetic algorithm.
Step 6:
Compute the fi
tness values using the formula
Fitness (A
i
) = [ W1 * IGR (A
i
) + W2 * IGR (Mutation (A
i
) ) + W3 * IGR (Crossove
r
(A
i
, A
j
) ] / [W1+W2+W3];
Fitness (A
j
) = [W1 * IGR (A
j
) + W2 * IGR (Mutation (A
j
)) + W3 * IGR (Crossover
(A
i
, A
j
)] / [W1+W2+W3];
Step 7:
If
Fitness (A
i
) >= Threshold AND Fitness (A
j
) >= Threshold then
Selected feature set SS = SS U (A
i
) U (A
j
);
S
tep 8:
If
Fitness (A
i
) >= Threshold AND Fitness (A
j
) < Threshold then
Selected feature set SS = SS U (A
i
);
Step 9:
If
Fitness (A
i
) < Threshold AND Fitness (A
j
) >= Threshold then
Selected feature set SS = SS U (A
j
);
Step 10:
If
A
i
is included
in SS then select the next attribute from the first subset
and call it as A
i
Step 11:
If
A
j
is included in SS then select the next attribute from the second subset
and call it as A
j
Step 12:
Repeat this process until all attributes are tested with the
rules used in this
procedure.
Step 13:
Return SS
Step 14:
If
No attributes are selected then change the Threshold with Threshold =
Threshold * 0.9 and go to step 6.
Fu
r
t
h
er
in
o
r
d
er
to
i
m
p
r
o
v
e
t
h
e
r
eliab
ilit
y
an
d
cla
s
s
i
f
icat
io
n
ac
cu
r
ac
y
NI
G
A
-
MFS
alg
o
r
i
t
h
m
i
s
u
s
ed
f
o
r
w
ir
eless
ad
v
er
tis
in
g
i
n
s
m
ar
t
cities.
I
n
th
is
w
o
r
k
,
a
ll
t
h
e
d
ataset
is
co
n
v
er
ted
i
n
to
a
s
ta
n
d
ar
d
f
o
r
m
at
w
h
ic
h
u
s
e
s
th
e
n
u
m
er
ical
v
al
u
e
s
b
etw
ee
n
0
an
d
1
s
o
t
h
at
it
i
s
ea
s
y
to
co
m
p
ar
e
d
u
r
i
n
g
th
e
c
la
s
s
i
f
icatio
n
p
r
o
ce
s
s
.
Fo
r
th
is
p
u
r
p
o
s
e,
th
e
m
i
n
i
m
u
m
a
n
d
m
a
x
i
m
u
m
v
al
u
es
ar
e
co
n
s
id
er
ed
as
th
e
b
o
u
n
d
ar
ies
f
o
r
ea
ch
attr
ib
u
te
an
d
th
e
a
ttrib
u
te
le
n
g
t
h
is
co
m
p
u
ted
u
s
i
n
g
t
h
e
d
if
f
er
e
n
ce
b
et
w
ee
n
t
h
e
m
ax
i
m
u
m
an
d
t
h
e
m
i
n
i
m
u
m
v
al
u
es.
T
h
e
n
o
r
m
al
ized
v
al
u
e
is
co
m
p
u
ted
u
s
in
g
t
h
e
f
o
r
m
u
la
g
i
v
en
i
n
(
1
1
)
.
(
)
=
(
)
(
–
)
(1
1
)
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
S
ec
u
r
e
a
n
d
r
elia
b
le
w
ir
eles
s
a
d
ve
r
tis
in
g
s
ystem
u
s
in
g
…
(
Yo
u
s
r
a
A
b
d
u
l A
ls
a
h
ib
S
.
A
ld
e
en
)
2405
w
h
er
e,
I
in
d
icate
th
e
I
t
h
d
ata
r
ec
o
r
d
,
g
iv
en
v
al
u
e
i
s
th
e
p
r
ese
n
t
v
al
u
e,
n
o
r
m
alize
d
v
al
u
e
is
t
h
e
co
m
p
u
ted
v
alu
e
w
h
ic
h
lies
b
et
w
ee
n
0
a
n
d
1
,
m
ax
v
a
lu
e
i
s
t
h
e
m
ax
i
m
u
m
v
a
lu
e
o
f
th
e
v
al
u
es f
o
r
th
e
p
ar
tic
u
l
ar
attr
ib
u
te
an
d
Mi
n
v
alu
e
is
t
h
e
Min
i
m
u
m
v
a
lu
e
o
f
th
e
v
al
u
es
f
o
r
th
e
p
ar
ticu
lar
attr
ib
u
te.
T
h
e
in
p
u
t
d
ata
ar
e
n
o
r
m
al
ized
o
n
ea
ch
r
ec
o
r
d
b
y
d
iv
id
in
g
t
h
e
m
a
x
-
m
i
n
v
al
u
e
b
y
th
e
m
a
x
i
m
u
m
v
al
u
e
an
d
h
en
ce
all
th
e
d
ata
ar
e
co
n
v
er
ted
in
to
u
n
if
o
r
m
f
o
r
m
at
w
i
th
a
r
an
g
e
o
f
v
al
u
es
f
r
o
m
0
to
1
.
T
h
is
p
r
e
-
p
r
o
ce
s
s
i
n
g
h
elp
s
th
e
d
ec
i
s
io
n
m
a
k
in
g
p
r
o
ce
s
s
to
ca
r
r
y
o
u
t
ea
s
ier
co
m
p
ar
is
o
n
s
.
Fo
r
th
is
p
u
r
p
o
s
e,
a
n
e
w
f
ea
t
u
r
e
s
elec
t
io
n
alg
o
r
it
h
m
ca
lled
G
A
b
ase
d
Min
-
Ma
x
f
ea
tu
r
e
s
elec
tio
n
al
g
o
r
ith
m
i
s
p
r
o
p
o
s
e
d
.
T
h
e
s
tep
s
o
f
th
e
NI
G
A
-
M
F
S Alg
o
r
it
h
m
2
ar
e
as f
o
llo
w
s
:
No
r
m
a
lized
in
t
ell
ig
e
n
t G
A
b
a
s
ed
m
i
n
-
m
a
x
f
ea
tu
r
e
s
elec
t
io
n
(
NI
GA
-
MF
S)
a
lg
o
r
ith
m
Input:
All features (F
i
, i=1 to n), Number of generations K, Population size PS,
Crossover proba
bility (CP
i
), Mutation probability (MP
i
).
Output:
Set of selected features SF
i
, i = 1 to m.
NIGA
-
MFS
(
)
Begin
Step 1:
Initialize the population from the dataset as F
i
, i=1 to n; n =41, Maximum
number of generations = 1000;
Step 2:
Convert the feature
s into feature numbers n binary form to represent them using
1s and 0s.
Step 3:
Form two parents by selecting two attributes at random
Step 4:
Remove them from F
i
and name them PA1 and PA2.
Step 5:
Initialize SF
i
= { } and Generation count = 1;
Step 6
:
Initialize the weights with W1=0.6, W2=0.4, CP
i
=0.5 and MP
i
=0.5.
Step 7:
For each chromosome F
i
present in the selected attributes population
{
i.
Ap
pl
y
un
if
or
m
cr
os
so
ve
r
wi
th
a
pr
ob
ab
il
it
y
C
P
i
an
d
mu
ta
ti
on
op
er
at
io
n
wi
th
probability MP
i
.
ii.
Find the norma
lized Min
-
Max value using the formula
Min
-
Max Value (I) = Given Value (I) / (Max Value
–
Min Value)
iii.
Evaluate Fitness (i)= [ W1 * RoundOf (Min
-
Max Value(i)) +
W2 * TruncateOf (Min
-
Max Value(i)+0.5)] / (W1 + W2)
iv.
If fitness value of F
i
> Threshold Then
FS
i
= FS
i
U F
i
Else
Read next attribute
Step 8:
If
Generation_Count < 1000 Then
Go to Step 7
Step 9:
Return FS
i
.
T
h
e
r
esu
lts
o
f
th
e
f
ea
t
u
r
e
s
e
le
ctio
n
al
g
o
r
ith
m
a
n
d
t
h
e
clas
s
i
f
icatio
n
al
g
o
r
ith
m
s
w
it
h
f
u
ll
f
e
atu
r
es
a
n
d
s
elec
ted
f
ea
tu
r
es
ar
e
s
e
lecte
d
u
s
i
n
g
th
e
p
r
o
p
o
s
ed
f
ea
tu
r
e
s
elec
tio
n
alg
o
r
ith
m
f
o
r
r
eliab
le
d
ata
tr
an
s
f
er
w
h
ic
h
is
d
is
cu
s
s
ed
in
t
h
e
r
esu
lts
a
n
d
d
is
cu
s
s
io
n
s
ec
tio
n
.
4.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
e
ef
f
icie
n
c
y
o
f
t
h
e
I
C
S
A
is
in
teg
r
ated
w
it
h
NI
GA
-
M
FS
f
o
r
o
p
tim
a
l
f
ea
t
u
r
e
s
elec
tio
n
f
o
r
r
el
iab
le
d
ata
tr
an
s
f
er
i
n
w
ir
eless
ad
v
er
tis
i
n
g
f
o
r
s
m
ar
t
citie
s
in
M
A
N
E
T
p
latf
o
r
m
w
ith
I
o
T
s
en
s
o
r
s
is
an
al
y
ze
d
in
t
h
i
s
s
ec
tio
n
.
T
h
e
p
r
o
p
o
s
ed
m
et
h
o
d
s
u
cc
es
s
f
u
ll
y
d
etec
ts
t
h
e
s
e
n
s
i
b
le
r
eg
io
n
w
h
ic
h
ex
a
m
i
n
e
s
th
e
o
p
tim
ized
cl
u
s
te
r
ce
n
ter
s
f
o
r
r
eliab
le
d
ata
tr
an
s
m
is
s
io
n
a
n
d
m
e
m
b
er
s
t
h
at
lead
s
to
cr
ea
te
th
e
ef
f
ec
t
iv
e
tr
an
s
m
i
s
s
io
n
p
ath
f
r
o
m
s
o
u
r
ce
to
d
esti
n
atio
n
i
n
s
m
ar
t
cit
y
en
v
ir
o
n
m
e
n
t.
T
h
en
th
e
p
e
r
f
o
r
m
an
ce
o
f
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
is
a
n
al
y
z
in
g
b
y
u
s
i
n
g
th
e
f
o
llo
w
in
g
m
etr
ics.
a)
C
o
v
er
ag
e
f
r
ac
tio
n
C
o
v
er
ag
e
f
r
ac
tio
n
is
m
e
tr
ic
to
an
al
y
ze
,
h
o
w
t
h
e
n
ei
g
h
b
o
r
n
o
d
es
ar
e
s
u
cc
ess
f
u
ll
y
e
x
a
m
i
n
i
n
g
w
h
ile
an
a
l
y
zi
n
g
th
e
s
e
n
s
ib
le
n
o
d
es in
w
ir
ele
s
s
s
en
s
o
r
n
et
w
o
r
k
s
o
f
s
m
ar
t c
itie
s
.
b)
E
n
er
g
y
c
o
n
s
u
m
p
tio
n
E
n
er
g
y
co
n
s
u
m
p
tio
n
is
o
n
e
t
h
e
i
m
p
o
r
tan
t
m
etr
ic
th
a
t
is
u
s
e
d
to
m
ea
s
u
r
e
h
o
w
m
u
c
h
p
o
wer
is
co
n
s
u
m
ed
w
h
ile
tr
a
n
s
m
itti
n
g
th
e
i
n
f
o
r
m
a
tio
n
f
r
o
m
s
o
u
r
ce
to
d
esti
n
a
tio
n
w
it
h
o
u
t
m
a
k
i
n
g
a
n
y
i
n
f
o
r
m
ati
o
n
lo
s
s
.
c)
A
cc
u
r
ac
y
T
h
e
last
m
etr
ics
is
ac
c
u
r
ac
y
i
n
w
h
ic
h
th
e
cl
u
s
ter
f
o
r
m
a
tio
n
e
f
f
icien
c
y
i
s
ex
a
m
i
n
ed
.
A
cc
u
r
a
c
y
is
a
n
al
y
ze
d
in
ter
m
s
o
f
u
s
i
n
g
n
u
m
b
er
o
f
n
o
d
e
s
alo
n
g
w
it
h
n
u
m
b
er
o
f
cl
u
s
ter
s
.
B
y
u
s
in
g
t
h
e
ab
o
v
e
e
f
f
icie
n
c
y
m
etr
ics,
e
x
ce
lle
n
ce
o
f
t
h
e
s
y
s
t
e
m
i
s
ev
a
lu
ated
w
i
th
th
e
h
elp
o
f
s
i
m
u
latio
n
s
et
u
p
,
w
h
ic
h
is
d
is
c
u
s
s
ed
as f
o
llo
w
s
.
T
h
e
ex
ce
llen
ce
o
f
p
r
o
p
o
s
ed
tech
n
iq
u
e
p
er
f
o
r
m
a
n
ce
is
an
al
y
ze
d
u
s
in
g
s
i
m
u
latio
n
s
et
u
p
th
at
is
co
m
p
ar
ed
w
it
h
tr
ad
itio
n
al
m
et
h
o
d
s
.
Du
r
i
n
g
t
h
e
i
m
p
le
m
en
tatio
n
p
r
o
ce
s
s
,
t
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
u
s
es
th
e
f
o
llo
w
i
n
g
s
i
m
u
latio
n
p
ar
a
m
eter
th
a
t is li
s
ted
in
t
h
e
T
ab
l
e
1
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
18
,
No
.
5
,
Octo
b
e
r
2
0
2
0
:
2
4
0
1
-
2411
2406
T
ab
le
1
.
Sim
u
latio
n
p
ar
a
m
eter
S
i
mu
l
a
t
i
o
n
P
a
r
a
me
t
e
r
P
a
r
a
me
t
e
r
V
a
l
u
e
S
i
mu
l
a
t
o
r
NS
2
(
v
.
2
.
2
9
)
T
r
a
n
smissi
o
n
R
a
n
g
e
5
0
0
*
5
0
0
s
q
u
a
r
e
me
t
e
r
s
B
a
n
d
w
i
d
t
h
4
M
b
p
s
I
n
t
e
r
f
a
c
e
Q
u
e
u
e
L
e
n
g
t
h
45
P
a
c
k
e
t
si
z
e
5
1
2
b
y
t
e
s
T
r
a
f
f
i
c
t
y
p
e
C
B
R
P
a
c
k
e
t
r
a
t
e
2
0
p
a
c
k
e
t
s/
se
c
T
o
p
o
l
o
g
y
si
z
e
7
0
0
*
7
0
0
m
2
N
u
mb
e
r
o
f
n
o
d
e
s
2
0
,
3
0
,
…5
0
N
u
mb
e
r
o
f
t
r
i
a
l
s
30
S
i
mu
l
a
t
i
o
n
T
i
me
8
0
0
se
c
M
a
x
i
m
u
m
S
p
e
e
d
4
0
m/
s
C
o
u
n
t
e
r
T
h
r
e
sh
o
l
d
(
C
)
6
R
A
D
T
max
0
.
0
2
se
c
o
n
d
s
A
f
t
e
r
s
i
m
u
l
a
t
i
o
n
n
e
tw
o
r
k
s
i
m
u
la
t
o
r
(
N
S
2
)
s
e
t
u
p
,
t
h
e
n
e
x
t
s
t
e
p
i
s
i
m
p
l
em
e
n
t
a
t
i
o
n
o
f
I
C
S
A
-
N
I
G
A
-
M
F
S
a
n
d
t
h
e
g
r
a
p
h
i
c
a
l
r
e
p
r
e
s
e
n
t
a
t
i
o
n
s
a
r
e
c
r
e
a
t
e
d
f
o
r
e
x
am
i
n
i
n
g
t
h
e
s
y
s
t
e
m
e
f
f
i
c
i
e
n
c
y
.
A
l
o
n
g
w
i
t
h
t
h
e
s
i
m
u
l
a
t
i
o
n
s
e
t
u
p
,
t
h
e
e
f
f
i
c
i
e
n
c
y
o
f
t
h
e
s
y
s
t
e
m
i
s
a
n
a
l
y
z
e
d
i
n
t
e
r
m
s
o
f
d
i
f
f
e
r
e
n
t
p
e
r
f
o
r
m
a
n
c
e
m
e
t
r
i
c
s
s
u
c
h
a
s
c
o
v
e
r
a
g
e
f
r
a
c
t
i
o
n
,
a
c
c
u
r
a
cy
o
f
c
l
u
s
t
e
r
a
n
d
e
n
e
r
g
y
c
o
n
s
u
m
p
t
i
o
n
m
e
t
r
i
c
s
.
D
e
p
e
n
d
i
n
g
o
n
t
h
e
v
a
r
i
o
u
s
d
i
s
c
u
s
s
i
o
n
s
c
l
u
s
t
e
r
h
e
a
d
a
n
d
c
e
n
t
r
o
i
d
n
o
d
e
i
s
s
e
l
e
c
t
e
d
u
s
i
n
g
t
h
e
I
C
S
A
i
n
t
e
g
r
a
t
e
d
N
I
G
A
-
M
F
S
w
i
t
h
e
f
f
e
c
t
i
v
e
m
a
n
n
e
r
.
T
h
e
n
t
h
e
e
f
f
i
c
i
e
n
c
y
o
f
c
l
u
s
t
e
r
i
s
e
x
a
m
i
n
e
d
i
n
t
e
r
m
s
o
f
p
r
e
c
i
s
i
o
n
,
r
e
c
a
l
l
a
n
d
a
c
c
u
r
a
c
y
m
e
t
r
i
c
s
,
w
h
i
c
h
i
s
e
x
p
l
a
i
n
e
d
a
s
f
o
l
l
o
w
s
.
a)
R
ec
all
R
ec
all
i
s
al
s
o
ca
lled
as
th
e
tr
u
e
p
o
s
itiv
e
r
ate
w
h
ich
h
elp
s
to
d
eter
m
in
e
h
o
w
e
x
ac
t
t
h
e
c
lu
s
t
er
h
ea
d
is
ch
o
s
en
f
r
o
m
t
h
e
co
llectio
n
o
f
n
o
d
es.
T
h
e
r
ec
all
v
alu
e
is
ca
lc
u
lated
as f
o
llo
w
s
,
R
e
c
a
l
l
=
Tr
ue
positive
Tr
ue
positive
+
F
a
l
s
e
N
e
ga
tive
(1
2
)
I
n
(
1
2
)
,
r
ec
all
v
alu
e
is
esti
m
a
ted
,
if
th
e
s
y
s
t
e
m
e
n
s
u
r
es
h
i
g
h
tr
u
e
p
o
s
itiv
e
r
ate
th
e
n
th
e
m
et
h
o
d
s
u
cc
ess
f
u
ll
y
s
elec
ts
t
h
e
ex
ac
t c
l
u
s
ter
w
ith
e
f
f
ec
tiv
e
m
a
n
n
er
.
b)
Fals
e
n
e
g
ati
v
e
r
ate
(
FNR
)
Fals
e
n
e
g
ati
v
e
r
ate
is
also
ca
lled
as
m
i
s
s
r
ate
th
at
m
ea
s
u
r
es
h
o
w
m
u
ch
f
r
ac
t
io
n
o
f
th
e
elem
e
n
t
s
class
i
f
ied
as n
e
g
ati
v
e
i
s
f
al
s
e.
T
h
e
FNR
v
al
u
e
is
e
s
ti
m
ated
as
f
o
llo
w
s
:
F
a
l
s
e
N
e
ga
tive
R
a
te
=
F
a
l
s
e
N
e
ga
tive
Tr
ue
Positive
+
F
a
l
s
e
N
e
ga
tive
(1
3
)
I
n
(
1
3
)
,
f
alse
n
eg
ati
v
e
r
ate
is
esti
m
ated
,
if
th
e
s
y
s
te
m
e
n
s
u
r
es
lo
w
n
eg
at
iv
e
r
ate
th
e
n
t
h
e
m
et
h
o
d
s
u
cc
es
s
f
u
ll
y
s
elec
ts
t
h
e
ex
ac
t
cl
u
s
ter
w
ith
e
f
f
ec
tiv
e
m
a
n
n
er
.
c)
P
r
ec
is
io
n
P
r
ec
is
io
n
is
also
ca
lled
as
P
o
s
itiv
e
P
r
ed
ictio
n
Valu
e
(
P
P
V)
,
it
s
h
o
w
s
h
o
w
m
u
c
h
f
r
ac
tio
n
o
f
th
e
ele
m
e
n
t
s
tr
u
l
y
p
o
s
itiv
e
i
s
cl
ass
i
f
ied
as
p
o
s
itiv
e.
Hi
g
h
er
P
PV
m
ea
n
s
b
etter
class
i
f
icatio
n
.
T
h
e
Pre
cisi
o
n
v
al
u
e
is
esti
m
ated
as
f
o
llo
w
s
,
Pr
e
c
ision
=
Tr
ue
Positive
Tr
ue
Postive
+
F
a
l
s
e
Positive
(1
4
)
B
ased
o
n
th
e
(
1
4
)
p
r
ec
is
io
n
,
r
ec
all
v
al
u
es,
ac
cu
r
ac
y
is
es
ti
m
a
ted
as f
o
llo
w
s
.
d)
A
cc
u
r
ac
y
(
AC
C
)
A
cc
u
r
ac
y
s
h
o
w
s
h
o
w
m
u
c
h
f
r
ac
tio
n
o
f
th
e
to
tal
ele
m
en
ts
class
i
f
ied
co
r
r
ec
tly
.
Hi
g
h
er
AC
C
m
ea
n
s
b
etter
class
if
icatio
n
.
I
t is ca
lc
u
lated
as f
o
llo
w
s
i
n
(
1
5
)
.
A
c
c
ura
c
y
=
Tr
ue
Positive
+
Tr
ue
N
e
ga
tive
(
Tr
ue
positive
+
Tr
ue
n
e
ga
tive
+
F
a
l
s
e
positive
+
F
a
l
s
e
N
e
ga
tive
)
(1
5
)
B
ased
o
n
th
e
ab
o
v
e
ac
cu
r
ac
y
m
etr
ic,
th
e
o
b
tain
ed
cl
u
s
ter
i
n
g
ac
cu
r
ac
y
v
a
lu
e
i
s
s
h
o
w
n
i
n
T
ab
le
2
.
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
S
ec
u
r
e
a
n
d
r
elia
b
le
w
ir
eles
s
a
d
ve
r
tis
in
g
s
ystem
u
s
in
g
…
(
Yo
u
s
r
a
A
b
d
u
l A
ls
a
h
ib
S
.
A
ld
e
en
)
2407
T
ab
le
2
.
P
er
f
o
r
m
a
n
ce
an
al
y
s
is
o
f
clu
s
ter
i
n
g
ac
cu
r
ac
y
I
A
C
O
M
V
S
V
M
BBA
I
C
S
A
-
N
I
G
A
-
M
F
S
A
c
c
u
r
a
c
y
0
.
7
5
0
.
8
4
0
.
8
3
0
.
9
7
p
r
e
c
i
si
o
n
0
.
7
4
0
.
8
5
0
.
7
6
0
.
9
8
R
e
c
a
l
l
0
.
8
3
0
.
5
4
0
.
6
6
0
.
8
9
F
a
l
s
e
N
e
g
a
t
i
v
e
R
a
t
e
0
.
9
1
0
.
6
0
.
7
1
0
.
5
5
B
a
s
e
d
o
n
T
a
b
l
e
2
,
I
C
SA
-
N
I
GA
-
M
FS
(
a
c
cu
r
a
cy
-
0
.
9
7
%
,
p
r
ec
i
s
i
o
n
-
0
.
9
8
%
an
d
r
e
c
al
l
-
0
.
5
5
%
)
i
s
m
o
r
e
r
e
l
i
a
b
l
e
in
d
a
t
a
t
r
an
s
f
e
r
w
h
en
co
m
p
a
r
e
d
t
o
o
t
h
e
r
m
e
th
o
d
s
s
u
ch
a
s
I
A
C
O
MV
(
a
c
c
u
r
ac
y
-
0
.
7
5
%
,
p
r
e
c
i
s
i
o
n
-
0
.
7
4
%
a
n
d
r
e
c
a
l
l
-
0
.
8
3
%
)
SV
M
(
a
cc
u
r
a
cy
-
0
.
8
4
%
,
p
r
e
c
is
i
o
n
-
0
.
8
5
%
a
n
d
r
e
c
a
ll
-
0
.
5
4
%
)
,
B
B
A
(
a
c
c
u
r
a
cy
-
0
.
8
3
%
,
p
r
e
c
i
s
i
o
n
-
0
.
7
6
%
an
d
r
e
c
a
l
l
-
0
.
6
6
%
)
a
n
d
I
C
SA
-
N
I
GA
-
MF
S
(
ac
c
u
r
a
cy
-
0
.
9
7
%
,
p
r
e
c
is
i
o
n
-
0
.
9
8
%
a
n
d
r
e
c
al
l
-
0
.
5
5
%
)
.
B
a
s
e
d
o
n
T
a
b
l
e
2
,
i
t
i
s
c
l
e
a
r
ly
s
h
o
w
in
g
th
a
t
th
e
I
C
SA
in
t
eg
r
a
t
e
d
N
I
GA
-
MF
S
en
s
u
r
es
th
e
h
i
g
h
a
c
cu
r
a
cy
w
h
i
le
d
e
t
e
c
t
in
g
ex
a
ct
c
lu
s
t
e
r
h
e
a
d
,
an
d
e
lim
in
a
t
in
g
th
e
f
a
ls
e
n
o
d
e
s
w
h
i
l
e
t
r
an
s
f
e
r
r
in
g
d
a
t
a
i
n
w
i
r
e
l
e
s
s
a
d
v
e
r
t
is
in
g
f
o
r
s
m
a
r
t
ci
t
i
es
w
h
e
n
c
o
m
p
a
r
e
d
t
o
t
h
e
o
th
e
r
m
e
th
o
d
s
.
E
v
en
th
o
u
g
h
in
t
r
o
d
u
c
e
m
eth
o
d
ef
f
e
c
ti
v
e
ly
f
o
r
m
th
e
r
eg
i
o
n
an
d
c
l
u
s
t
e
r
s
w
ith
h
i
g
h
a
cc
u
r
ac
y
,
t
h
e
n
e
t
w
o
r
k
m
u
s
t
c
o
n
s
u
m
e
m
in
im
u
m
en
e
r
g
y
t
h
a
t
l
e
a
d
s
t
o
im
p
r
o
v
e
o
v
e
r
a
l
l
n
e
t
w
o
r
k
l
if
e
t
im
e
w
h
il
e
t
r
an
s
m
it
ti
n
g
d
at
a
f
r
o
m
s
o
u
r
ce
t
o
d
e
s
t
in
a
ti
o
n
i
n
w
i
r
el
e
s
s
a
d
v
e
r
t
is
in
g
f
o
r
s
m
a
r
t
c
i
t
i
es
.
T
h
e
l
o
w
u
t
il
i
z
at
i
o
n
o
f
en
e
r
g
y
l
e
a
d
s
t
o
im
p
r
o
v
e
th
e
o
v
e
r
a
l
l
t
r
an
s
m
is
s
io
n
r
a
t
e
w
h
ic
h
al
s
o
el
im
in
at
e
s
s
ev
e
r
a
l
d
if
f
i
cu
l
t
i
es
.
S
o
,
I
C
SA
in
t
eg
r
at
e
d
N
I
GA
-
MF
S
a
lg
o
r
it
h
m
i
n
c
lu
s
t
e
r
h
e
a
d
t
o
c
o
l
l
e
c
t
th
e
d
at
a
f
r
o
m
b
as
e
s
t
a
tio
n
f
r
o
m
th
e
m
em
b
e
r
n
o
d
e
s
b
y
m
u
l
t
i
-
h
o
p
m
an
n
e
r
,
w
h
ic
h
s
a
v
e
s
th
e
en
e
r
g
y
c
o
n
s
u
m
p
t
i
o
n
o
f
c
lu
s
t
e
r
h
e
a
d
an
d
p
ar
t
i
c
i
p
an
ts
in
W
S
N
o
f
s
m
a
r
t
ci
t
i
es
.
I
n
I
A
C
OM
V
an
d
E
M
HR
p
r
o
t
o
c
o
l
s
,
e
n
e
r
g
y
b
u
r
d
e
n
is
d
u
e
t
o
th
e
l
o
n
g
-
h
au
l
c
o
m
m
u
n
i
c
at
i
o
n
l
in
k
s
b
e
tw
e
en
h
e
a
d
e
r
an
d
th
e
c
lu
s
t
e
r
m
em
b
e
r
s
.
H
o
w
ev
e
r
,
th
e
en
e
r
g
y
d
is
s
i
p
a
t
i
o
n
is
d
i
r
e
ct
ly
r
e
l
at
iv
e
t
o
th
e
ex
p
o
n
e
n
t
o
f
d
a
t
a
t
r
an
s
m
is
s
i
o
n
d
is
t
an
c
e
.
T
h
e
e
n
e
r
g
y
c
o
n
s
u
m
p
t
i
o
n
o
f
th
e
I
C
SA
in
t
eg
r
at
e
d
N
I
GA
-
M
FS
a
lg
o
r
i
th
m
is
l
e
s
s
th
a
n
t
h
at
o
f
I
A
C
OM
V
,
SV
M
an
d
B
B
A
[
2
1
]
.
L
es
s
en
e
r
g
y
c
o
n
s
u
m
p
t
i
o
n
m
e
an
s
l
o
n
g
e
r
lif
e
t
im
e
o
f
n
e
t
w
o
r
k
an
d
t
h
en
t
h
e
g
r
a
p
h
ic
a
l
r
e
p
r
es
en
t
at
i
o
n
o
f
r
e
s
i
d
u
a
l
e
n
e
r
g
y
i
s
s
h
o
w
n
in
Fig
u
r
e
2
.
T
a
b
l
e
2
s
h
o
w
s
th
e
e
n
e
r
g
y
c
o
n
s
u
m
p
ti
o
n
w
h
e
r
e
e
n
e
r
g
y
m
e
as
u
r
em
en
t
is
b
a
s
e
d
o
n
jo
u
l
es
.
Fig
u
r
e
2
.
P
er
f
o
r
m
a
n
ce
an
al
y
s
i
s
b
ased
o
n
en
er
g
y
As
s
h
o
w
s
in
F
ig
u
r
e
2
is
th
e
p
r
o
p
o
s
e
d
I
C
SA
i
n
te
g
r
ated
NI
GA
-
M
FS
o
b
tain
ed
a
h
i
g
h
e
n
e
r
g
y
s
a
v
i
n
g
w
h
ic
h
lead
s
to
i
m
p
r
o
v
e
o
v
er
a
ll
n
et
w
o
r
k
[
2
2
]
lif
eti
m
e.
Dep
en
d
in
g
o
n
th
e
ab
o
v
e
s
i
m
u
lati
o
n
r
esu
l
t,
th
e
I
C
S
A
in
te
g
r
ated
NI
GA
-
M
FS
alg
o
r
it
h
m
tr
a
n
s
m
it
s
th
e
d
ata
f
r
o
m
o
n
e
n
o
d
e
to
an
o
th
er
n
o
d
e
b
y
c
o
n
s
u
m
ed
m
in
i
m
u
m
p
o
w
er
th
at
u
s
ed
to
m
ai
n
tai
n
th
e
n
et
w
o
r
k
li
f
et
i
m
e
w
h
e
n
co
m
p
ar
ed
to
o
th
er
m
e
th
o
d
s
f
o
r
w
ir
eless
ad
v
er
ti
s
i
n
g
i
n
s
m
ar
t
ci
t
y
e
n
v
ir
o
n
m
en
t.
I
n
a
d
d
itio
n
to
th
is
,
e
f
f
ec
ti
v
e
u
tili
za
tio
n
o
f
n
o
d
es,
n
et
w
o
r
k
r
o
u
t
in
g
[
2
3
]
an
d
p
o
w
er
r
ed
u
ce
s
th
e
o
th
er
f
ail
u
r
es i
n
n
et
w
o
r
k
w
i
th
e
f
f
ec
ti
v
e
m
a
n
n
er
.
T
h
e
ab
o
v
e
Fig
u
r
e
3
s
h
o
w
s
th
at
th
e
co
m
p
ar
is
o
n
o
f
co
v
er
ag
e
f
r
ac
tio
n
f
o
r
th
e
v
ar
io
u
s
m
o
d
el
s
ar
e
r
ec
o
g
n
ized
s
e
n
s
iti
v
e
r
eg
io
n
f
r
o
m
th
e
d
ef
i
n
ed
co
v
er
a
g
e
ar
ea
w
ith
r
ea
s
o
n
ab
le
s
i
m
u
latio
n
r
u
n
s
i
n
d
ef
in
ed
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
18
,
No
.
5
,
Octo
b
e
r
2
0
2
0
:
2
4
0
1
-
2411
2408
ar
ea
[
2
4
]
.
T
h
e
o
b
tain
ed
co
v
er
ag
e
f
r
ac
tio
n
is
b
etter
f
o
r
I
C
S
A
i
n
te
g
r
ated
NI
GA
-
M
FS
w
h
e
n
co
m
p
ar
ed
to
th
e
ex
i
s
ti
n
g
s
e
n
s
in
g
I
AC
OM
V
,
SVM
an
d
B
B
A
.
T
h
is
s
u
cc
e
s
s
f
u
l
ex
a
m
in
a
tio
n
o
f
s
e
n
s
i
n
g
r
eg
io
n
h
elp
s
to
an
al
y
ze
th
e
n
u
m
b
er
o
f
n
o
d
es
in
r
e
g
io
n
w
it
h
e
f
f
ec
tiv
e
m
a
n
n
er
th
at
u
s
ed
to
f
o
r
m
t
h
e
clu
s
ter
w
it
h
d
if
f
er
e
n
t
n
u
m
b
er
o
f
r
o
u
n
d
s
an
d
n
o
d
es in
s
e
n
s
o
r
n
e
t
w
o
r
k
f
o
r
s
m
ar
t c
it
y
f
r
a
m
e
w
o
r
k
[
2
5
]
.
As
s
h
o
w
n
Fi
g
u
r
e
4
,
d
ep
en
d
in
g
o
n
th
e
n
u
m
b
er
o
f
cl
u
s
ter
n
o
d
es
ef
f
icie
n
c
y
,
th
e
s
u
cc
es
s
f
u
l
f
o
r
m
atio
n
s
o
f
clu
s
ter
en
h
an
ce
t
h
e
d
ata
tr
an
s
m
i
s
s
io
n
p
r
o
ce
s
s
b
y
m
a
x
i
m
i
zin
g
t
h
e
n
et
w
o
r
k
li
f
eti
m
e
i
n
w
ir
ele
s
s
ad
v
er
ti
s
i
n
g
f
r
a
m
e
w
o
r
k
f
o
r
s
m
ar
t
cit
y
p
lat
f
o
r
m
.
T
h
e
f
o
r
m
ed
cl
u
s
ter
lead
s
to
r
ed
u
ce
s
t
h
e
h
i
g
h
-
en
er
g
y
co
n
s
u
m
p
tio
n
w
h
ile
tr
an
s
m
itti
n
g
t
h
e
d
ata
f
r
o
m
s
o
u
r
ce
to
d
esti
n
at
io
n
n
o
d
e
in
s
m
ar
t
c
it
y
p
latf
o
r
m
w
h
ich
h
elp
s
to
i
m
p
r
o
v
e
th
e
ef
f
icie
n
c
y
o
f
t
h
e
n
et
w
o
r
k
.
Fig
u
r
e
3
.
P
er
f
o
r
m
a
n
ce
an
al
y
s
i
s
b
ased
o
n
co
v
er
ag
e
f
r
ac
tio
n
Fig
u
r
e
4
.
P
er
f
o
r
m
a
n
ce
an
al
y
s
i
s
b
ased
o
n
ef
f
icien
c
y
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
S
ec
u
r
e
a
n
d
r
elia
b
le
w
ir
eles
s
a
d
ve
r
tis
in
g
s
ystem
u
s
in
g
…
(
Yo
u
s
r
a
A
b
d
u
l A
ls
a
h
ib
S
.
A
ld
e
en
)
2409
Fig
u
r
e
5
d
ep
icts
th
e
co
m
p
ar
is
o
n
o
f
a
v
er
ag
e
t
i
m
e
ta
k
e
n
b
et
w
ee
n
I
C
S
A
in
te
g
r
ated
NI
GA
-
M
FS
co
m
p
ar
ed
to
th
e
e
x
is
ti
n
g
s
e
n
s
i
n
g
I
AC
OM
V,
SVM
an
d
B
B
A
m
o
d
els.
I
t
is
v
is
ib
le
t
h
at
I
C
S
A
i
n
teg
r
ated
NI
GA
-
M
FS
o
u
tp
er
f
o
r
m
s
in
co
m
p
ar
is
o
n
w
it
h
t
h
e
o
t
h
er
t
h
r
ee
alg
o
r
it
h
m
s
.
I
C
S
A
i
n
te
g
r
ated
NI
GA
-
MF
S
ah
ea
d
w
i
th
m
i
n
i
m
u
m
co
m
p
u
t
atio
n
al
ti
m
e
an
d
th
e
m
i
n
i
m
u
m
co
m
p
u
tatio
n
al
ti
m
e
i
s
d
u
e
to
th
e
m
e
m
b
er
s
h
ip
f
u
n
ctio
n
ev
al
u
atio
n
.
As
s
h
o
w
n
in
t
h
e
Fi
g
u
r
e
6
,
h
o
w
ev
er
,
I
C
S
A
in
te
g
r
ated
NI
G
A
-
MFS
h
a
s
less
er
ti
m
e
f
o
r
d
ata
tr
an
s
m
i
s
s
io
n
b
et
w
ee
n
th
e
I
o
T
s
en
s
o
r
n
o
d
es
in
s
m
ar
t
cit
y
p
lat
f
o
r
m
,
w
h
ich
g
r
o
w
s
e
x
p
o
n
en
tia
ll
y
as
t
h
e
s
i
ze
o
f
th
e
I
o
T
n
o
d
es
an
d
lin
k
s
i
n
cr
ea
s
e
s
in
s
m
ar
t
cit
y
p
lat
f
o
r
m
.
I
C
S
A
in
te
g
r
ate
d
NI
GA
-
MFS
ac
h
ie
v
es
t
h
e
o
p
ti
m
al
s
o
l
u
tio
n
i
n
a
m
a
x
i
m
ized
n
et
w
o
r
k
li
f
eti
m
e
f
o
r
th
e
n
o
d
e
g
en
er
atio
n
w
it
h
le
s
s
o
p
ti
m
u
m
ti
m
e
th
a
n
I
A
C
OM
V,
SVM
an
d
B
B
A
m
o
d
el
s
.
T
h
u
s
th
e
p
r
o
p
o
s
ed
s
o
lu
tio
n
s
h
o
w
s
th
e
o
p
ti
m
al
s
et
o
f
f
ea
tu
r
es
w
h
ic
h
ar
e
s
elec
ted
b
y
th
e
p
r
o
p
o
s
ed
in
telli
g
e
n
t i
n
cr
e
m
e
n
tal
f
ea
tu
r
e
s
elec
tio
n
al
g
o
r
ith
m
.
Fig
u
r
e
5
.
Av
er
ag
e
co
m
p
u
tatio
n
al
ti
m
e
an
al
y
s
is
Fi
g
u
r
e
6
.
Av
er
ag
e
co
m
p
u
tatio
n
al
ti
m
e
w
it
h
o
p
ti
m
u
m
s
o
lu
t
io
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
18
,
No
.
5
,
Octo
b
e
r
2
0
2
0
:
2
4
0
1
-
2411
2410
5.
CO
NCLU
SI
O
N
I
n
th
is
p
a
p
e
r
,
I
C
SA
in
t
eg
r
at
ed
N
I
GA
-
M
FS
a
lg
o
r
i
th
m
i
s
p
r
o
p
o
s
e
d
f
o
r
w
i
r
el
e
s
s
a
d
v
e
r
t
is
in
g
s
y
s
t
em
.
T
h
e
p
r
o
p
o
s
e
d
f
e
atu
r
e
s
e
l
e
ct
i
o
n
a
l
g
o
r
i
th
m
s
a
l
o
n
g
w
it
h
c
l
as
s
if
ie
r
s
is
u
s
e
d
an
d
i
t
is
o
b
s
e
r
v
e
d
t
h
a
t
b
o
th
th
e
f
e
at
u
r
e
s
e
l
e
ct
i
o
n
a
lg
o
r
i
th
m
s
in
c
r
e
as
e
d
t
h
e
c
l
as
s
i
f
i
c
a
ti
o
n
a
c
cu
r
a
cy
.
M
o
r
e
o
v
e
r
,
I
C
SA
in
t
eg
r
a
te
d
N
I
GA
-
M
FS
a
lg
o
r
i
th
m
p
r
o
v
i
d
e
d
b
e
t
t
e
r
r
e
s
u
l
ts
t
h
a
n
t
h
e
f
e
a
tu
r
e
s
e
l
ec
t
i
o
n
u
s
in
g
th
e
I
C
SA
d
u
e
t
o
th
e
u
s
e
o
f
n
o
r
m
a
li
z
a
t
i
o
n
w
ith
g
en
et
i
c
a
l
g
o
r
ith
m
s
.
B
o
th
th
e
a
lg
o
r
i
th
m
s
r
e
d
u
c
e
d
th
e
cl
a
s
s
if
ic
a
t
i
o
n
t
im
e
i
n
c
o
m
p
a
r
i
s
o
n
w
ith
I
A
C
OM
V
,
SV
M
an
d
B
B
A
m
o
d
e
ls
.
H
en
c
e
,
th
e
I
C
SA
-
N
I
GA
-
M
FS
a
ch
ie
v
e
s
b
et
t
e
r
p
e
r
f
o
r
m
an
c
e
in
t
e
r
m
s
o
f
cl
a
s
s
if
i
ca
t
i
o
n
a
c
cu
r
a
cy
an
d
c
l
a
s
s
if
ic
a
t
i
o
n
tim
e
b
y
th
e
u
s
e
o
f
th
e
p
r
o
p
o
s
e
d
p
r
e
-
p
r
o
c
e
s
s
in
g
t
ec
h
n
i
q
u
e
s
w
h
ich
i
s
m
o
s
t
s
u
i
ta
b
l
e
f
o
r
w
i
r
el
es
s
a
d
v
e
r
ti
s
in
g
in
s
m
a
r
t
ci
ty
en
v
i
r
o
n
m
en
t
f
o
r
r
e
l
ia
b
l
e
d
a
t
a
t
r
an
s
m
i
s
s
i
o
n
.
I
n
f
u
tu
r
e
,
th
e
p
r
o
p
o
s
e
d
al
g
o
r
it
h
m
w
i
ll
a
p
p
ly
o
n
o
th
e
r
d
o
m
a
in
l
ik
e
,
s
m
a
r
t
g
r
id
s
,
e
d
g
e
c
o
m
p
u
tin
g
,
in
d
u
s
t
r
ia
l
I
o
T
a
n
d
u
n
d
e
r
w
a
t
e
r
s
en
s
o
r
n
e
tw
o
r
k
s
.
AC
K
NO
WL
E
D
G
E
M
E
NT
S
T
h
is
w
o
r
k
w
a
s
s
u
p
p
o
r
ted
b
y
Un
i
v
er
s
it
y
o
f
B
ag
h
d
ad
.
REF
E
RENC
E
S
[1
]
A
.
G
u
p
t
a
,
R
.
K
.
J
h
a
,
P
.
G
a
n
d
o
t
r
a
,
a
n
d
S
.
J
a
i
n
,
"
B
a
n
d
w
i
d
t
h
s
p
o
o
f
i
n
g
a
n
d
i
n
t
r
u
s
i
o
n
d
e
t
e
c
t
i
o
n
sy
s
t
e
m
f
o
r
m
u
l
t
i
s
ta
g
e
5
G
w
i
re
l
e
s
s
c
o
m
m
u
n
i
c
a
t
i
o
n
n
e
tw
o
rk
,
"
I
E
E
E
T
r
a
n
s
a
c
t
i
o
n
s
o
n
V
e
h
i
c
u
l
a
r
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
6
7
,
n
o
.
1
,
p
p
.
6
1
8
-
6
3
2
,
2
0
1
7
.
[2
]
M
.
S
.
A
li
e
ro
,
I.
G
h
a
n
i,
K.
N.
Qu
r
e
sh
i,
a
n
d
M
.
F
.
A
.
Ro
h
a
n
i
,
"
A
n
a
lg
o
rit
h
m
f
o
r
d
e
tec
ti
n
g
S
QL
in
jec
ti
o
n
v
u
ln
e
ra
b
il
i
ty
u
sin
g
b
lac
k
-
b
o
x
tes
ti
n
g
,
"
J
o
u
rn
a
l
o
f
Amb
ie
n
t
In
telli
g
e
n
c
e
Hu
ma
n
ize
d
Co
mp
u
ti
n
g
,
v
o
l.
1
1
,
n
o
.
1
,
p
p
.
2
4
9
-
2
6
6
,
2
0
2
0
.
[3
]
K.
N.
Qu
re
sh
i,
F
.
Ba
sh
ir,
a
n
d
A
.
H.
A
b
d
u
ll
a
h
,
"
P
r
o
v
isio
n
o
f
S
e
c
u
rit
y
in
V
e
h
icu
lar
A
d
h
o
c
Ne
t
w
o
rk
s
th
ro
u
g
h
A
n
In
telli
g
e
n
t
S
e
c
u
re
Ro
u
ti
n
g
S
c
h
e
m
e
,
"
2
0
1
7
I
n
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
Fro
n
ti
e
rs
o
f
I
n
fo
rm
a
t
io
n
T
e
c
h
n
o
lo
g
y
(
FIT
)
,
p
p
.
2
0
0
-
205
,
2
0
1
7
.
[4
]
E.
Be
n
k
h
e
li
f
a
,
T
.
W
e
lsh
,
a
n
d
W
.
Ha
m
o
u
d
a
,
"
A
c
rit
ica
l
re
v
ie
w
o
f
p
ra
c
ti
c
e
s
a
n
d
c
h
a
ll
e
n
g
e
s
i
n
in
tr
u
sio
n
d
e
tec
ti
o
n
s
y
ste
m
s
f
o
r
Io
T
:
T
o
wa
rd
u
n
iv
e
rsa
l
a
n
d
re
sili
e
n
t
sy
ste
m
s,
"
IEE
E
Co
mm
u
n
ic
a
ti
o
n
s
S
u
rv
e
y
s
T
u
to
ria
ls,
v
o
l
.
2
0
,
n
o
.
4
,
p
p
.
3
4
9
6
-
3
5
0
9
,
2
0
1
8
.
[5
]
A
.
S
h
a
rif
,
J.
P
.
L
i,
a
n
d
M
.
A
.
S
a
lee
m
,
"
In
tern
e
t
o
f
th
in
g
s
e
n
a
b
led
v
e
h
icu
lar
a
n
d
a
d
h
o
c
n
e
tw
o
rk
s
f
o
r
s
m
a
rt
c
it
y
tra
ff
ic
m
o
n
it
o
rin
g
a
n
d
c
o
n
tr
o
ll
in
g
:
a
re
v
iew
,
"
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Ad
v
a
n
c
e
d
Ne
two
rk
in
g
Ap
p
li
c
a
ti
o
n
s,
v
o
l.
1
0
,
n
o
.
3
,
p
p
.
3
8
3
3
-
3
8
4
2
,
2
0
1
8
.
[6
]
A
.
M
e
h
m
o
o
d
,
A
.
Kh
a
n
a
n
,
M
.
M
.
Um
a
r,
S
.
A
b
d
u
ll
a
h
,
K.
A
.
Z.
A
riff
in
,
a
n
d
H.
S
o
n
g
,
"
S
e
c
u
re
k
n
o
w
led
g
e
a
n
d
c
l
u
ste
r
-
b
a
se
d
i
n
tr
u
sio
n
d
e
tec
ti
o
n
m
e
c
h
a
n
is
m
f
o
r
s
m
a
rt
w
ir
e
les
s
se
n
so
r
n
e
tw
o
rk
s,"
IEE
E
Acc
e
ss
,
v
o
l.
6
,
p
p
.
5
6
8
8
-
5
6
9
4
,
2
0
1
7
.
[7
]
K.
Qu
re
sh
i,
A
.
H.
A
b
d
u
ll
a
h
,
O.
Ka
iwa
rt
y
a
,
F
.
Ullah
,
a
n
d
S
.
I.
A
.
A
lt
a
m
e
e
m
,
"
W
e
ig
h
ted
li
n
k
q
u
a
li
ty
a
n
d
f
o
r
w
a
rd
p
ro
g
re
ss
c
o
u
p
led
w
it
h
m
o
d
if
ied
RT
S
/CT
S
f
o
r
b
e
a
c
o
n
les
s p
a
c
k
e
t
f
o
rw
a
rd
in
g
p
ro
to
c
o
l
(B
-
P
F
P
)
,
"
T
e
lec
o
mm
u
n
ic
a
ti
o
n
S
y
ste
ms
,
2
0
1
6
.
[8
]
K.
N.
Qu
re
sh
i,
M
.
M
.
I
d
re
e
s,
J.
L
lo
re
t,
a
n
d
I.
Bo
sc
h
,
"
S
e
lf
-
A
ss
e
s
s
m
e
n
t
Ba
se
d
Clu
ste
rin
g
Da
ta
Diss
e
m
in
a
ti
o
n
f
o
r
S
p
a
rse
a
n
d
De
n
se
T
ra
ff
ic Co
n
d
it
i
o
n
s f
o
r
In
tern
e
t
o
f
V
e
h
icle
s,"
IEE
E
Acc
e
ss
,
v
o
l.
8
,
p
p
.
1
0
3
6
3
-
1
0
3
7
2
,
2
0
2
0
.
[9
]
Q.
Ya
se
e
n
,
F
.
A
lb
a
las
,
Y.
Ja
ra
rwa
h
,
a
n
d
M
.
A
l
‐
Ay
y
o
u
b
,
"
L
e
v
e
r
a
g
in
g
f
o
g
c
o
m
p
u
ti
n
g
a
n
d
so
f
tw
a
r
e
d
e
f
in
e
d
sy
ste
m
s
f
o
r
se
lec
ti
v
e
f
o
rwa
rd
in
g
a
tt
a
c
k
s
d
e
tec
ti
o
n
i
n
m
o
b
il
e
w
irele
ss
se
n
so
r
n
e
tw
o
rk
s,"
T
ra
n
sa
c
ti
o
n
s
o
n
Eme
rg
i
n
g
T
e
lec
o
mm
u
n
ica
ti
o
n
s
T
e
c
h
n
o
lo
g
ie
s,
v
o
l.
2
9
,
n
o
.
4
,
2
0
1
8
.
[1
0
]
P
.
M
.
S
h
a
k
e
e
l,
S
.
B
a
sk
a
r,
V
.
S
.
Dh
u
li
p
a
la,
S
.
M
ish
ra
,
a
n
d
M
.
M
.
Ja
b
e
r,
"
M
a
in
tai
n
in
g
se
c
u
rit
y
a
n
d
p
ri
v
a
c
y
in
h
e
a
lt
h
c
a
re
s
y
st
e
m
u
sin
g
lea
rn
in
g
b
a
se
d
d
e
e
p
-
Q
-
n
e
tw
o
rk
s,"
J
o
u
rn
a
l
o
f
M
e
d
ica
l
S
y
ste
ms
,
v
o
l.
4
2
,
n
o
.
1
0
,
2
0
1
8
.
[1
1
]
H.
A
lan
a
z
i,
A
.
A
b
d
u
ll
a
h
,
K.
Q
u
re
sh
i,
a
n
d
A
.
Ism
a
il
,
"
Ac
c
u
ra
te
a
n
d
d
y
n
a
m
ic
p
re
d
ictiv
e
m
o
d
e
l
f
o
r
b
e
tt
e
r
p
re
d
icti
o
n
i
n
m
e
d
icin
e
a
n
d
h
e
a
lt
h
c
a
re
,
"
Irish
J
o
u
rn
a
l
o
f
M
e
d
ica
l
S
c
ien
c
e
,
v
o
l
.
1
8
7
,
n
o
.
2
,
p
p
.
5
0
1
-
5
1
3
,
2
0
1
8
.
[1
2
]
A
.
Bra
n
d
ã
o
,
H.
S
ã
o
M
a
m
e
d
e
,
a
n
d
R.
G
o
n
ç
a
lv
e
s,
"
A
s
m
a
rt
c
it
y
’s
m
o
d
e
l
se
c
u
re
d
b
y
b
lo
c
k
c
h
a
in
,
"
I
n
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
S
o
ft
w
a
re
Pro
c
e
ss
Imp
ro
v
e
me
n
t
,
S
p
rin
g
e
r,
p
p
.
2
4
9
-
2
6
0
,
2
0
1
8
.
[1
3
]
M
.
Do
rig
o
a
n
d
T
.
S
tü
tzle
,
"
A
n
t
c
o
lo
n
y
o
p
ti
m
iza
ti
o
n
:
o
v
e
rv
ie
w
a
n
d
re
c
e
n
t
a
d
v
a
n
c
e
s,"
Ha
n
d
b
o
o
k
o
f
M
e
tah
e
u
risti
c
s
:
S
p
rin
g
e
r,
p
p
.
3
1
1
-
3
5
1
,
2
0
1
9
.
[1
4
]
V
.
O.
C
o
sta
a
n
d
C
.
R
.
R
o
d
rig
u
e
s,
"
Hie
ra
rc
h
ica
l
a
n
t
c
o
lo
n
y
f
o
r
sim
u
lt
a
n
e
o
u
s
c
las
sif
ier
se
l
e
c
ti
o
n
a
n
d
h
y
p
e
rp
a
ra
m
e
t
e
r
o
p
ti
m
iza
ti
o
n
,
"
2
0
1
8
IEE
E
c
o
n
g
re
ss
o
n
e
v
o
l
u
ti
o
n
a
ry
c
o
m
p
u
t
a
ti
o
n
(
CEC)
,
p
p
.
1
-
8
,
2
0
1
8
.
[1
5
]
M
.
M
.
M
a
f
a
rja
a
n
d
S
.
M
ir
jalil
i,
"
H
y
b
rid
b
i
n
a
ry
a
n
t
li
o
n
o
p
ti
m
ize
r
w
it
h
r
o
u
g
h
se
t
a
n
d
a
p
p
ro
x
im
a
te
e
n
tro
p
y
re
d
u
c
ts
f
o
r
f
e
a
tu
re
se
lec
ti
o
n
,
"
S
o
ft
Co
m
p
u
ti
n
g
,
v
o
l.
2
3
,
n
o
.
1
5
,
p
p
.
6
2
4
9
-
6
2
6
5
,
2
0
1
9
.
[1
6
]
T
.
M
.
M
o
h
a
m
e
d
a
n
d
H.
M
.
M
o
f
t
a
h
,
"
S
im
u
lt
a
n
e
o
u
s
ra
n
k
in
g
a
n
d
s
e
lec
ti
o
n
o
f
k
e
y
stro
k
e
d
y
n
a
m
i
c
s
fe
a
tu
re
s
th
ro
u
g
h
a
n
o
v
e
l
m
u
lt
i
-
o
b
jec
ti
v
e
b
in
a
ry
b
a
t
a
lg
o
rit
h
m
,
"
Fu
tu
re
Co
mp
u
ti
n
g
I
n
fo
rm
a
ti
c
s
J
o
u
r
n
a
l,
v
o
l.
3
,
n
o
.
1
,
p
p
.
2
9
-
4
0
,
2
0
1
8
.
[1
7
]
D.
G
u
h
a
,
P
.
K.
Ro
y
,
a
n
d
S
.
Ba
n
e
r
jee
,
"
Bin
a
ry
Ba
t
A
lg
o
rit
h
m
A
p
p
li
e
d
to
S
o
lv
e
M
IS
O
-
T
y
p
e
P
ID
-
S
S
S
C
-
Ba
se
d
L
o
a
d
F
re
q
u
e
n
c
y
Co
n
tro
l
P
r
o
b
lem
,
"
I
r
a
n
i
a
n
J
o
u
rn
a
l
o
f
S
c
ien
c
e
T
e
c
h
n
o
lo
g
y
,
T
ra
n
sa
c
ti
o
n
s
o
f
El
e
c
trica
l
En
g
i
n
e
e
rin
g
,
v
o
l.
4
3
,
n
o
.
2
,
p
p
.
3
2
3
-
3
4
2
,
2
0
1
9
.
[1
8
]
A
.
T
h
a
r
w
a
t
a
n
d
A
.
E.
Ha
ss
a
n
i
e
n
,
"
Op
ti
m
izin
g
S
u
p
p
o
rt
V
e
c
to
r
M
a
c
h
in
e
P
a
ra
m
e
ter
s
Us
in
g
Ba
t
Op
ti
m
iza
ti
o
n
A
l
g
o
rit
h
m
,
"
M
a
c
h
in
e
L
e
a
rn
in
g
P
a
ra
d
ig
m
s: T
h
e
o
r
y
a
n
d
A
p
p
li
c
a
ti
o
n
:
S
p
rin
g
e
r,
p
p
.
3
5
1
-
3
7
4
,
2
0
1
9
.
Evaluation Warning : The document was created with Spire.PDF for Python.