I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
pu
t
er
Science
Vo
l.
24
,
No
.
1
,
Octo
b
er
20
21
,
p
p
.
39
4
~
40
2
I
SS
N:
2
5
0
2
-
4
7
5
2
,
DOI
: 1
0
.
1
1
5
9
1
/ijeecs.v
2
4
.i
1
.
pp
39
4
-
40
2
394
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs.ia
esco
r
e.
co
m
An int
eg
ra
ted
ma
chine learni
ng
mo
del f
o
r i
ndo
o
r net
wo
rk
o
ptimiza
tion to m
a
x
imize cov
erag
e
Ahm
ed
Wa
s
if
Rez
a
,
Abdu
lla
h Al
Rif
a
t
,
T
a
nv
ir
Ahm
ed
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
E
n
g
in
e
e
rin
g
,
Eas
t
Wes
t
U
n
iv
e
rsity
,
Dh
a
k
a
,
Ba
n
g
la
d
e
sh
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
un
22
,
2
0
2
1
R
ev
is
ed
Au
g
23
,
2
0
2
1
Acc
ep
ted
Au
g
30
,
2
0
2
1
In
d
o
o
r
n
e
two
r
k
o
p
ti
m
iza
ti
o
n
is
n
o
t
a
sim
p
le
tas
k
d
u
e
to
t
h
e
o
b
sta
c
les
,
in
terfe
re
n
c
e
,
a
n
d
a
tt
e
n
u
a
ti
o
n
o
f
t
h
e
sig
n
a
l
i
n
a
n
e
n
v
ir
o
n
m
e
n
t.
In
te
n
se
n
o
ise
s
c
a
n
a
ffe
c
t
th
e
in
telli
g
ib
i
li
ty
o
f
t
h
e
sig
n
a
l
a
n
d
re
d
u
c
e
th
e
c
o
v
e
ra
g
e
stre
n
g
t
h
sig
n
ifi
c
a
n
t
ly
wh
ich
re
su
lt
s
i
n
a
p
o
o
r
u
se
r
e
x
p
e
rie
n
c
e
.
M
o
st
o
f
t
h
e
e
x
isti
n
g
wo
rk
s
a
re
a
ss
o
c
iate
d
wit
h
fi
n
d
i
n
g
t
h
e
lo
c
a
ti
o
n
o
f
th
e
d
e
v
ice
s
v
i
a
d
iffere
n
t
m
a
th
e
m
a
ti
c
a
l
a
n
d
g
e
n
e
ric
a
lg
o
rit
h
m
ic
a
p
p
r
o
a
c
h
e
s,
b
u
t
v
e
ry
fe
w
a
re
fo
c
u
se
d
o
n
imp
ly
i
n
g
m
a
c
h
in
e
lea
rn
i
n
g
a
lg
o
rit
h
m
s.
Th
e
p
u
r
p
o
se
o
f
t
h
i
s
re
se
a
rc
h
is
to
in
tro
d
u
c
e
a
n
in
teg
ra
ted
m
a
c
h
in
e
lea
rn
in
g
m
o
d
e
l
t
o
fi
n
d
m
a
x
imu
m
in
d
o
o
r
c
o
v
e
ra
g
e
wit
h
a
m
in
im
u
m
n
u
m
b
e
r
o
f
tran
sm
it
ters
.
Th
e
u
se
rs
in
t
h
e
i
n
d
o
o
r
e
n
v
iro
n
m
e
n
t
a
lso
h
a
v
e
b
e
e
n
a
ll
o
c
a
ted
b
a
se
d
o
n
t
h
e
m
o
st
re
li
a
b
le
sig
n
a
l
stre
n
g
th
a
n
d
th
e
sy
ste
m
is
a
lso
c
a
p
a
b
le
o
f
a
ll
o
c
a
ti
n
g
n
e
w
u
se
rs.
K
-
m
e
a
n
s
c
lu
ste
rin
g
,
K
-
n
e
a
re
st
n
e
ig
h
b
o
r
(
KN
N),
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
(
S
VM),
a
n
d
G
a
u
ss
ian
Na
ïv
e
Ba
y
e
s
(
G
NB)
h
a
v
e
b
e
e
n
u
se
d
t
o
p
ro
v
id
e
a
n
o
p
ti
m
ize
d
so
lu
ti
o
n
.
It
is
fo
u
n
d
t
h
a
t
KN
N,
S
VM,
a
n
d
G
NB
o
b
tai
n
e
d
m
a
x
imu
m
a
c
c
u
ra
c
y
o
f
1
0
0
%
i
n
so
m
e
c
a
se
s.
Ho
we
v
e
r
,
a
m
o
n
g
a
ll
th
e
a
lg
o
rit
h
m
s,
KN
N
p
e
rfo
rm
e
d
th
e
b
e
st
a
n
d
p
r
o
v
i
d
e
d
a
n
a
v
e
ra
g
e
a
c
c
u
ra
c
y
o
f
9
3
.
3
3
%
.
K
-
f
o
ld
c
ro
ss
-
v
a
li
d
a
ti
o
n
(Kf
-
CV)
tec
h
n
iq
u
e
h
a
s
b
e
e
n
a
d
d
e
d
t
o
v
a
li
d
a
te
th
e
e
x
p
e
rime
n
tal
sim
u
latio
n
s a
n
d
re
-
e
v
a
l
u
a
te t
h
e
o
u
tco
m
e
s o
f
t
h
e
m
a
c
h
in
e
lea
rn
i
n
g
m
o
d
e
ls.
K
ey
w
o
r
d
s
:
C
o
v
er
ag
e
m
ax
im
izatio
n
Gau
s
s
ian
Naïv
e
B
ay
es
I
n
d
o
o
r
n
etwo
r
k
o
p
tim
izatio
n
K
-
m
ea
n
s
clu
s
ter
in
g
K
-
n
ea
r
est n
eig
h
b
o
r
s
Ma
ch
in
e
lear
n
in
g
Su
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
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
:
Ah
m
ed
W
asif
R
ez
a
Dep
ar
tm
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
an
d
E
n
g
in
ee
r
in
g
E
ast W
es
t U
n
iv
er
s
ity
Dh
ak
a,
B
an
g
lad
esh
E
m
ail:
wasif@ewu
b
d
.
ed
u
1.
I
NT
RO
D
UCT
I
O
N
I
n
th
e
er
a
o
f
m
o
d
er
n
-
d
a
y
co
m
m
u
n
icatio
n
,
th
e
n
ee
d
o
f
e
x
ch
a
n
g
in
g
d
ata
is
r
is
in
g
ex
p
o
n
en
ti
ally
.
T
h
is
en
o
r
m
o
u
s
v
o
l
u
m
e
o
f
d
ata
tr
af
f
ic
an
d
th
e
r
elev
an
t
p
r
o
to
co
ls
lik
e
E
th
e
r
n
et,
u
n
iv
er
s
al
asy
n
ch
r
o
n
o
u
s
r
ec
eiv
er
/tra
n
s
m
itter
(
UART
)
,
B
lu
eto
o
th
,
b
lu
et
o
o
th
l
o
w
e
n
er
g
y
(
B
L
E
)
,
n
ea
r
-
f
ield
c
o
m
m
u
n
icatio
n
(
NFC
)
,
wir
eless
f
id
elity
(
W
I
FI
)
,
Z
ig
B
ee
,
an
d
m
an
y
m
o
r
e
ar
e
b
ased
o
n
b
o
th
wir
ed
a
n
d
wir
eless
tech
n
o
lo
g
ies.
Fro
m
th
e
in
teg
r
atio
n
o
f
t
h
e
in
te
r
n
et
o
f
th
i
n
g
s
(
I
o
T
)
to
t
h
e
in
d
u
s
tr
ia
l
im
p
licatio
n
s
m
e
n
tio
n
ed
in
[
1
]
-
[
3
]
,
ea
ch
s
ec
to
r
is
g
ettin
g
m
o
r
e
a
n
d
m
o
r
e
r
elian
t
o
n
wir
eless
co
m
m
u
n
icatio
n
.
I
n
an
u
n
teth
er
ed
in
d
o
o
r
en
v
ir
o
n
m
en
t,
f
in
d
i
n
g
t
h
e
m
ax
im
u
m
co
v
er
a
g
e
with
a
m
in
im
u
m
n
u
m
b
e
r
o
f
tr
a
n
s
m
itter
s
is
n
o
t
o
v
er
ly
s
im
p
lis
tic
s
in
ce
th
er
e
a
r
e
m
a
n
y
o
b
s
tacle
s
lik
e
co
n
cr
ete
wall
s
,
win
d
o
ws,
d
o
o
r
s
,
b
r
ick
s
,
g
lass
es,
an
d
p
ar
titi
o
n
s
.
Sti
ll,
co
v
er
in
g
a
lar
g
e
en
v
ir
o
n
m
en
t
with
o
u
t
h
av
in
g
l
in
e
-
of
-
s
ig
h
t
(
L
o
S)
co
m
m
u
n
ic
atio
n
is
ch
allen
g
in
g
in
m
an
y
ca
s
es.
As
a
r
esu
lt,
th
er
e
is
n
o
o
b
v
io
u
s
s
o
lu
tio
n
t
h
at
is
in
tr
icate
ly
o
p
tim
ized
an
d
ca
n
p
er
f
o
r
m
r
o
b
u
s
tly
alo
n
g
with
p
r
o
v
id
in
g
th
e
b
est
wir
eles
s
co
n
n
ec
tiv
ity
.
I
n
th
is
r
esear
ch
,
we
h
av
e
u
tili
ze
d
f
o
u
r
m
ac
h
i
n
e
lear
n
in
g
a
lg
o
r
ith
m
s
,
s
u
ch
as
K
-
m
ea
n
s
clu
s
ter
in
g
,
K
-
n
ea
r
est
n
eig
h
b
o
r
(
KNN)
,
s
u
p
p
o
r
t
v
e
cto
r
m
ac
h
in
e
(
SVM)
,
an
d
Ga
u
s
s
ian
Naïv
e
B
ay
es
(
GNB),
to
ev
alu
ate
t
h
e
m
ax
i
m
u
m
co
v
er
ag
e
an
d
f
in
d
th
e
t
r
an
s
m
itter
’
s
ex
ac
t
lo
ca
tio
n
s
t
o
p
r
o
p
ag
ate
s
tr
o
n
g
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
A
n
in
teg
r
a
ted
ma
c
h
in
e
lea
r
n
in
g
mo
d
el
fo
r
in
d
o
o
r
n
etw
o
r
k
o
p
timiz
a
tio
n
to
… (
A
h
med
Wa
s
if R
eza
)
395
s
ig
n
als
th
r
o
u
g
h
o
u
t
th
e
en
v
ir
o
n
m
en
t.
Ou
r
m
o
d
el
is
also
ca
p
ab
le
o
f
ef
f
ec
tiv
ely
p
r
ed
ic
tin
g
th
e
n
ew
u
s
er
’
s
lo
ca
tio
n
b
ased
o
n
th
e
co
o
r
d
i
n
ated
ap
p
r
o
ac
h
an
d
b
est
s
ig
n
al
s
tr
en
g
th
.
Fro
m
th
e
KNN
a
lg
o
r
ith
m
,
we
h
av
e
ac
h
iev
ed
th
e
h
ig
h
est
ac
cu
r
ac
y
in
a
v
er
ag
e
f
o
r
all
th
e
e
x
p
e
r
im
en
tal
en
v
ir
o
n
m
e
n
ts
.
T
h
is
m
o
d
el
ca
n
p
er
f
o
r
m
ef
f
ec
tiv
ely
to
p
r
o
v
id
e
a
n
in
teg
r
ated
s
o
lu
tio
n
in
o
p
tim
izin
g
i
n
d
o
o
r
wir
eless
n
etwo
r
k
s
.
T
h
is
p
ap
er
is
o
r
g
a
n
ized
as
f
o
llo
ws:
r
elate
d
wo
r
k
s
a
n
d
m
et
h
o
d
o
lo
g
y
ar
e
p
r
esen
ted
in
s
ec
tio
n
s
2
an
d
3
,
r
e
s
p
ec
tiv
ely
.
I
n
th
e
m
eth
o
d
o
l
o
g
y
s
ec
tio
n
,
th
e
s
y
s
t
em
wo
r
k
f
l
o
w
is
g
iv
en
,
f
o
llo
w
ed
b
y
t
h
e
ex
p
er
im
en
tal
en
v
ir
o
n
m
en
ts
an
d
wir
eless
tech
n
o
lo
g
ies.
Af
ter
war
d
,
th
e
r
esu
lts
an
d
d
is
cu
s
s
io
n
s
ec
tio
n
h
a
v
e
b
ee
n
p
r
esen
ted
.
L
astl
y
,
th
e
co
n
cl
u
d
in
g
r
em
ar
k
s
h
av
e
b
ee
n
a
d
d
ed
.
2.
RE
L
AT
E
D
WO
RK
S
Op
tim
izin
g
in
d
o
o
r
n
etwo
r
k
co
v
er
ag
e
is
a
v
er
y
co
m
m
o
n
p
h
e
n
o
m
en
o
n
in
in
d
o
o
r
wir
eless
n
etwo
r
k
in
g
.
Du
e
to
h
av
in
g
v
a
r
io
u
s
o
b
s
ta
cles
an
d
atten
u
atio
n
o
f
th
e
s
ig
n
al
in
th
e
e
n
v
ir
o
n
m
en
t,
it
h
a
s
b
ec
o
m
e
a
v
er
y
ch
allen
g
in
g
task
to
d
o
.
As
a
r
esu
lt,
in
m
an
y
e
x
is
tin
g
ty
p
es
o
f
r
esear
ch
,
b
o
th
two
-
d
im
en
s
io
n
al
(
2
D)
an
d
th
r
ee
-
d
im
en
s
io
n
al
(
3
D
)
en
v
i
r
o
n
m
en
ts
a
r
e
c
o
n
s
id
er
ed
to
en
s
u
r
e
o
p
tim
u
m
in
d
o
o
r
n
e
two
r
k
co
v
er
ag
e
.
I
n
p
ap
er
[
4
]
,
a
3
D
en
v
ir
o
n
m
e
n
t
is
co
n
s
id
e
r
ed
to
b
u
ild
th
e
in
d
o
o
r
m
o
d
el
b
y
co
llectin
g
th
e
b
u
ild
in
g
in
f
o
r
m
atio
n
m
o
d
elin
g
(
B
I
M)
.
B
esid
es
r
ay
tr
ac
in
g
was
p
er
f
o
r
m
ed
to
f
i
n
d
in
d
o
o
r
r
a
d
io
co
v
er
ag
e.
Pa
p
er
[
5
]
s
h
o
ws
th
at
in
d
o
o
r
r
a
d
io
c
o
v
er
a
g
e
ca
n
b
e
en
s
u
r
ed
b
y
d
is
tr
ib
u
tin
g
a
p
a
r
ticu
lar
s
ce
n
ar
io
wh
er
e
acce
s
s
p
o
in
ts
(
APs
)
ar
e
in
s
talled
to
f
in
d
th
e
b
est
p
o
s
itio
n
f
o
r
th
e
r
ec
eiv
er
an
d
th
e
tr
a
n
s
m
itter
as
well.
T
h
e
r
e
ar
e
tw
o
co
r
e
p
a
r
ts
,
o
n
e
is
to
r
ed
u
ce
th
e
c
o
m
p
lex
it
y
o
f
t
h
e
d
ep
lo
y
ed
s
y
s
tem
an
d
th
e
o
th
er
o
n
e
is
to
f
in
d
th
e
m
in
im
u
m
n
u
m
b
er
o
f
APs
.
Als
o
,
p
ap
er
[
6
]
s
h
o
ws,
to
r
ed
u
ce
u
n
n
ec
ess
ar
y
p
o
wer
co
n
s
u
m
p
tio
n
,
tr
an
s
m
itter
s
m
u
s
t
b
e
p
lace
d
in
p
r
ec
is
e
lo
ca
tio
n
s
.
Af
ter
e
n
s
u
r
in
g
lo
w
p
o
wer
c
o
n
s
u
m
p
tio
n
,
r
em
o
v
i
n
g
co
v
e
r
ag
e
o
v
er
la
p
p
in
g
is
an
o
th
er
task
in
o
r
d
er
t
o
o
p
tim
ize
in
d
o
o
r
n
etwo
r
k
c
o
v
er
ag
e.
I
n
m
an
y
ca
s
es,
m
ac
h
i
n
e
lear
n
i
n
g
al
g
o
r
ith
m
s
ar
e
u
s
ed
to
f
i
n
d
in
d
o
o
r
p
r
o
p
a
g
atio
n
a
n
d
s
o
lv
e
lo
ca
li
za
tio
n
p
r
o
b
lem
s
with
s
o
m
e
p
o
p
u
lar
alg
o
r
ith
m
s
lik
e
K
-
m
ea
n
s
,
Naïv
e
B
ay
es,
KNN,
an
d
SVM.
T
h
ese
alg
o
r
ith
m
s
ar
e
also
u
tili
ze
d
in
v
ar
i
o
u
s
class
if
icatio
n
an
d
clu
s
ter
in
g
-
b
ased
p
r
o
b
lem
s
wh
ich
is
m
en
t
io
n
ed
in
[
7
]
.
Fro
m
p
ap
er
[
8
]
-
[
1
3
]
,
it
is
d
is
cu
s
s
ed
th
at
h
o
w
to
r
em
o
v
e
o
v
er
la
p
p
in
g
b
y
u
s
in
g
s
o
f
t
-
K
-
m
ea
n
s
clu
s
ter
in
g
.
Acc
o
r
d
in
g
to
th
em
,
r
o
u
tin
g
p
r
o
t
o
co
l
clu
s
ter
in
g
is
co
n
s
id
er
ed
th
e
m
o
s
t
d
esira
b
le
p
r
o
to
co
l
in
ter
m
s
o
f
in
d
o
o
r
n
etwo
r
k
co
v
er
ag
e.
Ap
ar
t
f
r
o
m
clu
s
ter
in
g
p
r
o
to
co
l,
d
ee
p
n
eu
r
al
n
etwo
r
k
(
DNN)
f
r
am
ewo
r
k
an
d
its
f
ield
p
r
o
g
r
am
m
a
b
le
g
ate
ar
r
ay
(
FP
GA)
im
p
lem
en
tatio
n
g
iv
e
ef
f
icien
t
r
esu
lts
f
o
r
in
d
o
o
r
lo
ca
lizatio
n
m
en
tio
n
ed
in
[
1
4
]
.
Du
et
a
l.
[
1
5
]
,
th
e
p
r
o
p
o
s
ed
f
in
g
er
p
r
in
t
lo
ca
lizatio
n
alg
o
r
ith
m
(
KF
-
KNN)
b
ased
o
n
FM
s
ig
n
als
is
co
m
p
ar
ed
w
ith
KNN
an
d
weig
h
ted
K
-
n
ea
r
est
n
eig
h
b
o
r
s
(
W
KNN)
.
KF
-
KN
N
o
u
tp
er
f
o
r
m
ed
th
e
KNN
an
d
W
KN
N
alg
o
r
ith
m
s
.
Als
o
,
f
o
r
r
ed
u
cin
g
lo
ca
lizatio
n
er
r
o
r
,
an
AP
d
ep
lo
y
m
en
t
s
tr
ateg
y
was
in
tr
o
d
u
ce
d
in
th
e
p
ap
er
[
1
6
]
,
wh
ich
o
u
tp
e
r
f
o
r
m
ed
th
e
p
r
ev
i
o
u
s
alg
o
r
ith
m
s
.
3.
M
E
T
H
O
DO
L
O
G
Y
T
h
e
o
v
er
all
s
y
s
tem
wo
r
k
f
lo
w
o
f
th
e
th
r
ee
alg
o
r
ith
m
s
,
n
am
ely
KNN,
SVM,
an
d
GNB
h
as
b
ee
n
s
h
o
wn
in
Fig
u
r
e
1
.
First
r
aw
d
ata
ar
e
in
itialized
to
th
e
alg
o
r
i
th
m
s
,
an
d
af
te
r
p
r
e
-
p
r
o
ce
s
s
in
g
,
th
e
d
ata
h
as
b
ee
n
s
p
lit
in
to
tr
ain
s
e
t
an
d
test
s
et
.
Af
ter
lo
ad
in
g
th
e
d
ataset,
th
e
th
r
ee
ab
o
v
e
alg
o
r
ith
m
s
h
av
e
b
ee
n
ap
p
lied
an
d
f
in
ally
ev
alu
ated
an
d
a
n
aly
s
ed
with
th
e
test
s
et.
Fig
u
r
e
1
.
Pro
p
o
s
ed
m
o
d
el
wo
r
k
f
lo
w
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
2
4
,
No
.
1
,
Octo
b
er
20
21
:
39
4
-
40
2
396
3
.
1
.
D
a
t
a
v
is
ua
liza
t
io
n
T
h
e
f
o
llo
win
g
two
3
D
m
o
d
els
in
Fig
u
r
es
2
(
a
)
an
d
2
(
b
)
s
h
o
w
th
e
s
am
p
lin
g
p
o
in
ts
an
d
r
ec
ei
v
ed
s
ig
n
al
s
tr
en
g
th
in
d
icato
r
(
R
SS
I
)
v
alu
es
f
o
r
b
etter
o
b
s
er
v
atio
n
.
W
e
h
av
e
u
s
ed
R
S
SI
v
alu
es
co
llected
b
y
th
r
e
e
d
if
f
er
en
t
wir
eless
tech
n
o
lo
g
ie
s
,
n
am
ely
Z
i
g
B
ee
,
b
lu
eto
o
th
l
o
w
en
er
g
y
(
B
L
E
)
,
an
d
W
I
FI.
W
e
h
av
e
to
tal
R
SS
I
v
alu
es
f
o
r
s
ce
n
ar
i
o
-
1
is
4
4
1
,
f
o
r
s
ce
n
ar
i
o
-
2
is
1
4
4
a
n
d
f
in
all
y
f
o
r
s
ce
n
a
r
io
-
3
is
3
6
0
.
T
h
er
e
f
o
r
e,
th
e
t
o
tal
s
u
m
o
f
th
e
R
SS
I
v
alu
es is
9
4
5
.
(
a)
(
b
)
Fig
u
r
e
2
.
(
a
)
U
s
er
’
s
co
o
r
d
in
at
es a
n
d
(
b
)
R
SS
I
v
alu
es
3
.
2
.
D
a
t
a
prepro
ce
s
s
ing
Fo
r
tr
ain
in
g
th
e
m
ac
h
in
e
lear
n
in
g
m
o
d
els,
class
if
icatio
n
o
f
t
h
e
d
ataset
was
r
eq
u
ir
ed
.
Featu
r
e
s
ca
lin
g
h
as
b
ee
n
in
tr
o
d
u
ce
d
h
er
e.
Fo
r
th
e
R
S
SI
s
co
r
es
o
n
a
p
o
s
itiv
e
s
ca
le
o
f
1
to
1
0
0
,
if
th
e
v
alu
e
is
clo
s
er
to
1
0
0
th
en
it
is
co
n
s
id
er
ed
as
b
est.
I
n
th
e
ca
s
e
o
f
n
e
g
ativ
e
s
ca
lin
g
,
i.e
.
,
-
1
0
0
to
-
1
,
if
th
e
v
al
u
e
ten
d
s
to
ze
r
o
th
en
R
SS
I
s
ig
n
al
s
tr
en
g
th
is
co
n
s
id
er
ed
as
a
g
o
o
d
s
ig
n
al
[
1
7
]
.
W
e
h
av
e
d
o
n
e
th
e
s
am
e
th
in
g
f
o
r
all
th
e
d
if
f
er
en
t
s
ce
n
ar
io
s
b
y
ev
alu
atin
g
th
e
p
o
s
itiv
e
R
SS
I
s
ca
le.
C
o
n
s
id
er
in
g
th
e
3
D
en
v
i
r
o
n
m
e
n
t,
we
h
av
e
in
tr
o
d
u
ce
d
z
-
ax
is
th
at
was
n
o
t
p
r
esen
ted
in
th
e
r
aw
d
ataset.
W
e
ass
u
m
ed
th
e
v
alu
e
‘
5
’
f
o
r
th
e
z
-
ax
is
f
o
r
ev
er
y
d
ata
p
o
in
t.
O
u
r
ass
u
m
p
tio
n
is
b
ased
o
n
th
e
p
h
y
s
ical
o
r
ien
tatio
n
o
f
th
e
en
v
ir
o
n
m
en
ts
.
Acc
o
r
d
in
g
to
I
n
te
r
n
atio
n
al
B
u
il
d
in
g
C
o
d
e
(
I
B
C
)
,
th
e
s
tan
d
ar
d
ce
ili
n
g
h
eig
h
t
is
9
f
ee
t.
Ho
we
v
er
,
we
h
av
e
ass
u
m
ed
th
e
d
ata
p
o
in
ts
wer
e
at
‘
5
’
f
ee
t
h
ig
h
wh
ich
is
co
n
s
id
er
ed
as
th
e
v
alu
e
o
f
th
e
z
-
a
x
is
[
1
8
]
(
r
ef
er
to
Fig
u
r
e
2
(
a)
)
.
I
n
th
e
d
a
taset,
R
SS
I
A,
B
,
C
r
ep
r
esen
t
th
e
wir
eless
tech
n
o
l
o
g
ies
Z
ig
B
ee
(
I
E
E
E
8
0
2
.
1
5
.
4
)
,
B
L
E
,
an
d
W
I
FI
(
I
E
E
E
8
0
2
.
1
1
n
2
.
4
GHz
b
an
d
)
.
B
y
u
tili
zin
g
th
e
ab
o
v
e
-
m
e
n
tio
n
ed
wir
eless
tech
n
o
lo
g
ies,
th
r
ee
d
if
f
er
en
t
R
SS
I
v
alu
es
wer
e
co
llected
.
T
o
p
r
e
-
p
r
o
ce
s
s
th
e
d
ataset,
we
to
o
k
th
e
av
er
a
g
e
o
f
R
SS
I
A,
B
,
C
,
s
o
th
at
we
ca
n
clas
s
if
y
th
e
d
ataset
b
ased
o
n
th
e
co
m
b
in
ed
R
SS
I
v
alu
es.
Fo
r
i
n
s
tan
ce
,
in
th
e
ca
s
e
o
f
th
e
s
c
en
ar
io
-
1
Z
ig
B
ee
d
ataset,
we
h
av
e
c
o
n
s
id
er
ed
th
e
av
er
ag
e
R
SS
I
v
alu
e
6
0
o
r
g
r
ea
ter
as
a
th
r
esh
o
ld
to
b
e
a
g
o
o
d
s
ig
n
al
s
tr
en
g
th
an
d
an
y
th
in
g
b
el
o
w
is
p
r
esu
m
ab
ly
in
f
er
i
o
r
.
As
‘
0
’
an
d
‘
1
’
ar
e
o
u
r
two
d
ec
id
in
g
f
ac
to
r
s
an
d
o
t
h
er
v
ar
iab
le
s
ar
e
in
d
ep
en
d
en
t,
th
er
ef
o
r
e,
ac
c
o
r
d
in
g
to
th
e
d
e
cid
in
g
f
ac
to
r
s
,
0
in
d
icate
s
a
b
ad
s
ig
n
al,
an
d
1
in
d
icate
s
a
g
o
o
d
s
ig
n
al.
W
e
s
p
lit
th
e
d
ataset
in
to
2
0
%
an
d
8
0
%
ac
co
r
d
in
g
ly
f
o
r
t
h
e
test
an
d
tr
ain
s
et.
Min
Ma
x
Scaler
is
u
s
e
d
to
tr
a
n
s
f
o
r
m
th
e
en
tire
d
ataset
in
to
th
e
r
a
n
g
e
b
e
twee
n
ze
r
o
an
d
o
n
e
.
3
.
3
.
K
-
m
e
a
ns
clus
t
er
ing
Fo
r
f
in
d
in
g
th
e
o
p
tim
u
m
n
u
m
b
er
o
f
clu
s
ter
s
,
we
h
av
e
u
s
ed
s
k
lear
n
.
clu
s
ter
.
K
m
ea
n
s
lib
r
ar
y
.
I
n
itially
,
we
allo
ca
te
=
5
,
wh
ich
is
th
e
n
u
m
b
er
o
f
p
o
s
s
ib
le
in
itial
clu
s
ter
s
.
T
h
en
th
e
s
u
m
o
f
th
e
s
q
u
a
r
ed
d
is
tan
ce
b
etwe
en
d
ata
p
o
in
ts
an
d
th
e
ce
n
tr
o
id
s
is
ca
lcu
late
d
.
Af
ter
th
at,
ea
ch
d
ata
p
o
in
t
to
th
ei
r
r
esp
ec
tiv
e
clo
s
est
clu
s
ter
is
as
s
ig
n
ed
.
T
h
en
th
e
iter
atio
n
co
n
tin
u
es
u
n
til
th
er
e
is
n
o
ch
an
g
e
in
th
e
p
o
s
itio
n
o
f
th
e
ce
n
tr
o
id
s
.
Fin
ally
,
af
ter
co
m
p
letin
g
t
h
e
it
er
atio
n
s
,
we
g
et
o
u
r
o
p
tim
ized
clu
s
ter
s
.
Als
o
,
s
im
ilar
ap
p
r
o
a
ch
es
f
o
r
f
in
d
in
g
an
o
p
tim
u
m
n
u
m
b
e
r
o
f
clu
s
ter
s
h
av
e
b
ee
n
u
tili
ze
d
in
[
1
9
]
-
[
2
1
]
.
I
n
Fig
u
r
e
3
(
a)
,
i
n
itial c
lu
s
ter
ce
n
ter
s
.
I
n
er
ti
a
r
ep
r
esen
ts
th
e
s
u
m
o
f
s
q
u
ar
ed
er
r
o
r
f
o
r
ea
ch
clu
s
ter
.
A
s
m
aller
in
er
tia
s
co
r
e
m
ea
n
s
th
e
clu
s
ter
is
d
en
s
er
an
d
t
h
e
p
o
in
ts
ar
e
cl
o
s
er
.
T
h
e
tar
g
et
o
f
th
e
K
-
m
ea
n
s
clu
s
ter
in
g
alg
o
r
ith
m
is
to
s
elec
t
ce
n
tr
o
id
s
t
h
at
m
in
im
ize
in
er
tia.
T
h
e
in
e
r
tia
s
co
r
e
ag
ain
s
t
th
e
n
u
m
b
er
o
f
clu
s
ter
s
h
as
b
ee
n
r
ep
r
esen
t
ed
in
Fig
u
r
e
3
(
b
)
.
Fig
u
r
e
4
(
a)
r
e
p
r
esen
ts
th
e
u
p
d
ated
f
o
u
r
d
if
f
e
r
en
t
clu
s
ter
s
an
d
th
eir
ce
n
ter
s
.
C
u
r
r
e
n
tly
,
4
9
u
s
er
s
ar
e
in
f
o
u
r
g
r
o
u
p
s
o
f
1
6
,
1
0
,
1
1
,
1
2
a
n
d
th
e
y
b
elo
n
g
to
th
eir
d
esig
n
ated
cl
u
s
ter
s
0
,
1
,
2
,
a
n
d
3
in
asce
n
d
in
g
o
r
d
e
r
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
A
n
in
teg
r
a
ted
ma
c
h
in
e
lea
r
n
in
g
mo
d
el
fo
r
in
d
o
o
r
n
etw
o
r
k
o
p
timiz
a
tio
n
to
… (
A
h
med
Wa
s
if R
eza
)
397
I
n
Fig
u
r
e
4
(
b
)
,
ce
n
t
r
o
id
s
ar
e
u
p
d
ated
f
r
o
m
f
i
v
e
to
f
o
u
r
af
t
er
ex
ec
u
tin
g
th
e
K
-
m
ea
n
s
clu
s
ter
in
g
.
I
n
ter
m
s
o
f
allo
ca
tin
g
u
s
er
s
,
h
er
e
we
ca
n
s
ee
th
e
to
tal
n
u
m
b
er
o
f
u
s
er
s
is
4
9
.
E
ac
h
u
s
er
b
elo
n
g
s
to
th
eir
clu
s
ter
s
.
W
h
en
ev
er
a
n
ew
u
s
er
en
ter
s
th
e
en
v
ir
o
n
m
en
t,
t
h
e
u
s
er
wil
l
f
in
d
th
e
b
est
lo
ca
tio
n
ac
co
r
d
in
g
to
th
e
u
s
er
’
s
p
o
s
itio
n
an
d
o
p
tim
al
s
ig
n
al
s
tr
en
g
th
.
T
h
e
E
u
clid
ian
d
is
tan
ce
f
o
r
m
u
la
is
u
s
ed
to
ca
lcu
l
ate
th
e
u
s
er
’
s
n
ew
co
o
r
d
in
ate
b
y
ca
lcu
latin
g
th
e
d
is
tan
ce
an
d
R
SS
I
v
alu
es.
I
n
th
e
in
d
o
o
r
e
n
v
ir
o
n
m
en
t,
w
h
e
n
ev
er
th
e
n
ew
u
s
er
en
ter
s
,
it
g
ets
allo
ca
ted
to
a
s
p
ec
if
ic
clu
s
ter
.
Her
e,
th
e
n
ew
u
s
er
b
elo
n
g
s
to
th
e
p
u
r
p
le
-
co
lo
r
ed
clu
s
ter
1
(
Fig
u
r
e
4
(
b
)
)
.
E
u
clid
ia
n
d
is
tan
ce
s
f
r
o
m
th
e
n
ew
u
s
er
’
s
lo
ca
tio
n
to
th
e
tr
an
s
m
itter
s
ar
e
ca
lcu
lated
.
Af
ter
th
at,
th
e
in
i
tial c
lu
s
ter
s
also
g
et
u
p
d
ated
.
(
a)
(
b
)
Fig
u
r
e
3
.
(
a
)
I
n
itial c
lu
s
ter
ce
n
ter
s
an
d
(
b
)
I
n
er
tia
s
co
r
es
(
a)
(
b
)
Fig
u
r
e
4
.
(
a
)
U
p
d
ate
d
clu
s
ter
s
f
o
r
s
ce
n
ar
io
1
an
d
(
b
)
A
llo
ca
tin
g
n
ew
u
s
er
s
3.
4
.
K
NN
Her
e,
we
h
av
e
u
tili
ze
d
t
h
e
s
k
lear
n
.
n
eig
h
b
o
r
s
.
KNe
ig
h
b
o
r
s
C
lass
if
ier
.
T
h
e
KNN
m
o
d
el
is
t
r
ain
ed
f
o
r
n
_
n
e
ighb
o
r
s
=
2
to
n
_
n
e
ighb
or
s
=
10
.
is
th
e
n
u
m
b
er
o
f
n
e
ar
est
n
_
n
eig
h
b
o
r
s
.
Fo
r
i
n
s
tan
ce
,
in
ex
p
er
im
en
tal
en
v
ir
o
n
m
en
t
1
,
f
o
r
th
e
v
alu
e
4
,
we
h
a
v
e
g
o
t
th
e
h
ig
h
est
ac
cu
r
ac
y
a
n
d
lo
west
m
ea
n
er
r
o
r
wh
ich
is
r
e
p
r
esen
ted
in
Fig
u
r
e
5
.
T
h
e
class
if
ier
u
s
es
a
weig
h
t
p
ar
am
eter
th
at
r
etu
r
n
s
th
e
weig
h
ts
u
n
if
o
r
m
ly
.
I
t
also
ca
lcu
lates
th
e
d
is
tan
ce
b
etwe
en
p
o
in
ts
b
y
u
s
in
g
th
e
E
u
clid
ian
d
is
tan
ce
f
o
r
m
u
la.
A
u
s
er
-
d
ef
in
e
d
ca
llab
le
f
u
n
ctio
n
is
u
s
ed
to
r
etu
r
n
t
h
e
weig
h
ted
v
alu
es
in
th
e
f
o
r
m
o
f
an
ar
r
a
y
.
Her
e,
th
e
p
o
wer
p
a
r
am
eter
p
r
ep
r
esen
ts
th
e
Min
k
o
wsk
i
m
etr
ic.
T
h
e
v
alu
e
o
f
=
2
r
ep
r
esen
ts
t
h
e
E
u
clid
ea
n
d
is
t
an
ce
.
Als
o
,
in
[
2
2
]
-
[
2
4
]
,
th
e
E
u
clid
ian
d
is
tan
ce
f
o
r
m
u
la
is
u
s
ed
to
ca
lcu
late
th
e
d
is
tan
ce
s
b
etwe
en
th
e
d
ata
p
o
in
ts
.
3
.
5
.
SVM
Fo
r
th
e
SVM
clas
s
if
icatio
n
m
o
d
el,
we
h
av
e
u
s
ed
th
e
s
k
lear
n
.
s
v
m
.
L
in
ea
r
SVC
lib
r
ar
y
.
T
h
e
lin
ea
r
k
er
n
el
is
ap
p
lied
b
ec
au
s
e
it
is
ca
p
ab
le
o
f
tr
ain
in
g
f
aster
th
an
an
y
o
th
er
k
er
n
el.
A
h
y
p
er
p
lan
e
is
co
m
m
o
n
ly
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
2
4
,
No
.
1
,
Octo
b
er
20
21
:
39
4
-
40
2
398
u
s
ed
to
class
if
y
th
e
d
ata
p
o
in
t
s
in
SVM.
Af
ter
in
itiatin
g
t
h
e
tr
ain
in
g
d
ataset,
it
class
if
ies
th
e
d
ata
in
to
m
u
ltip
le
class
es.
I
n
o
u
r
ca
s
e,
g
o
o
d
s
ig
n
al
an
d
b
ad
s
ig
n
al
s
tr
en
g
th
s
ar
e
class
if
ied
in
to
two
d
if
f
er
en
t
class
es.
I
n
[
2
5
]
-
[
2
7
]
,
th
e
d
atasets
wer
e
also
class
if
ied
in
th
e
s
am
e
m
an
n
er
.
I
n
Fig
u
r
e
6
(
a)
,
all
th
e
r
ed
lin
es
d
o
n
o
t
h
av
e
p
er
f
ec
t
m
a
r
g
in
s
p
ac
e
o
n
th
eir
lef
t
o
r
r
ig
h
t
s
id
e
ex
ce
p
t
th
e
b
lu
e
lin
e
ac
co
r
d
in
g
to
th
e
s
u
p
p
o
r
t
v
ec
to
r
s
.
I
n
Fig
u
r
e
6
(
b
)
,
two
d
ata
p
o
in
ts
t
h
at
ar
e
clo
s
est
to
t
h
e
b
lac
k
d
o
tted
lin
es
ar
e
th
e
s
u
p
p
o
r
t
v
ec
to
r
s
.
Or
an
g
e
lin
es
r
ep
r
esen
t
th
e
d
is
tan
ce
f
r
o
m
th
e
d
o
tted
lin
es
an
d
s
u
p
p
o
r
t
v
ec
to
r
s
.
Als
o
,
th
e
b
lu
e
lin
e
s
h
o
w
n
in
Fig
u
r
e
6
(
b
)
is
th
e
m
o
s
t
r
o
b
u
s
t
s
o
lu
tio
n
in
ter
m
s
o
f
class
if
y
in
g
ex
is
tin
g
o
r
n
ew
d
ata.
As a
r
esu
lt,
th
e
b
lu
e
lin
e
class
if
ies th
e
d
ata
p
o
in
ts
with
m
ax
im
u
m
m
a
r
g
in
a
n
d
p
r
o
d
u
c
es th
e
b
est r
esu
lt.
Fig
u
r
e
5
.
Me
an
er
r
o
r
(
a)
(
b
)
Fig
u
r
e
6
.
(
a
)
I
n
itial SVM
h
y
p
e
r
p
lan
e
an
d
(
b
)
U
p
d
ated
SVM
h
y
p
er
p
lan
e
3
.
6
.
G
NB
W
e
h
av
e
u
tili
ze
d
th
e
s
k
lear
n
.
n
aiv
e
_
b
a
y
es.
Gau
s
s
ian
NB
lib
r
ar
y
.
Firstl
y
,
GNB
in
itializes
t
h
e
d
ataset
f
o
r
th
r
ee
d
if
f
e
r
en
t
s
ce
n
ar
io
s
.
Af
ter
th
at,
it
ca
lcu
lates
th
e
p
r
o
b
ab
ilit
y
o
f
th
e
R
SS
I
v
alu
es
wh
ich
is
p
r
ev
io
u
s
ly
p
r
esen
ted
in
th
e
d
ataset
(
Fig
u
r
e
2
(
b
)
)
.
T
h
e
n
it
ca
lcu
lates
th
e
p
r
io
r
p
r
o
b
a
b
ilit
y
.
Af
ter
th
at
,
it
d
eter
m
in
e
s
th
e
m
ar
g
in
al
lik
elih
o
o
d
f
o
r
th
e
R
SS
I
at
th
e
u
n
k
n
o
wn
lo
ca
ti
o
n
an
d
ca
lcu
lates
th
e
lik
elih
o
o
d
f
u
n
ctio
n
.
T
h
e
p
o
s
ter
io
r
p
r
o
b
ab
ilit
y
is
ca
lcu
lated
f
o
r
a
s
in
g
le
t
r
an
s
m
itter
to
f
in
d
t
h
e
o
v
e
r
all
p
o
s
ter
io
r
p
r
o
b
a
b
ilit
y
f
o
r
all
tr
an
s
m
itter
s
wh
ich
co
m
p
u
tes
th
e
esti
m
a
ted
lo
ca
tio
n
.
Fo
r
o
u
t
lier
d
etec
tio
n
in
th
e
in
d
u
s
tr
ial
in
ter
n
et
o
f
th
in
g
s
(II
o
T
)
s
y
s
tem
,
GNB
is
u
s
ed
a
s
m
en
tio
n
ed
in
[
2
8
]
.
Als
o
,
in
[
2
9
]
,
[
3
0
]
,
GNB
is
im
p
lem
en
te
d
in
s
u
c
h
d
etec
tio
n
p
r
o
b
lem
s
.
4.
E
XP
E
R
I
M
E
N
T
A
L
E
NV
I
R
O
NM
E
N
T
S
W
e
h
av
e
co
n
s
id
er
ed
th
r
ee
d
if
f
er
en
t
s
ce
n
ar
io
s
s
h
o
wn
in
Fi
g
u
r
es
7
(
a)
-
7
(
c)
.
Few
o
f
th
o
s
e
s
ce
n
ar
io
s
wer
e
in
ter
f
er
en
ce
-
f
r
ee
an
d
s
o
m
e
o
f
th
em
h
ad
ex
is
tin
g
n
o
is
es.
T
h
r
ee
tr
an
s
m
itter
s
wer
e
s
et
an
d
r
ec
eiv
er
s
wer
e
p
lace
d
in
t
h
e
ce
n
ter
o
f
th
e
tr
a
n
s
m
itter
s
.
T
h
e
tr
an
s
m
itter
s
wer
e
p
lace
d
i
n
a
tr
ia
n
g
u
lar
s
h
a
p
e.
Scen
ar
io
1
was
in
ter
f
er
en
ce
-
f
r
ee
an
d
f
o
r
s
ce
n
a
r
io
s
2
an
d
3
,
th
e
en
v
ir
o
n
m
e
n
t w
as
n
o
is
y
.
All
e
x
p
er
im
e
n
tal
s
ettin
g
s
p
r
esen
ted
in
th
is
p
ap
er
ar
e
s
im
ilar
as in
[
3
1
]
.
Mo
r
eo
v
er
,
we
h
av
e
p
a
r
tially
u
s
ed
th
e
s
am
e
d
ataset,
as r
ef
e
r
r
ed
to
[
3
1
]
.
E
n
v
ir
o
n
m
en
t
1
wa
s
a
m
ee
tin
g
r
o
o
m
.
T
h
e
s
ize
o
f
th
e
r
o
o
m
was
6
.
0
×5
.
5
m
.
T
r
a
n
s
m
itter
s
wer
e
p
lace
d
4
m
d
is
tan
ce
f
r
o
m
ea
ch
o
th
er
i
n
tr
ian
g
u
lar
s
h
a
p
e
a
n
d
r
ec
eiv
e
r
s
wer
e
p
lace
d
0
.
5
m
ap
a
r
t
f
r
o
m
ea
ch
o
th
er
in
th
e
ce
n
ter
o
f
th
e
tr
an
s
m
itter
s
.
E
n
v
ir
o
n
m
e
n
t
2
was
in
ter
f
er
e
n
ce
-
f
r
ee
.
T
h
is
s
ce
n
ar
io
was
n
o
is
y
.
T
h
e
s
ize
o
f
th
e
r
o
o
m
was
5
.
8
×5
.
3
m
.
R
ec
eiv
er
s
wer
e
p
lace
d
f
ar
f
r
o
m
ea
c
h
o
th
er
.
So
m
e
ex
tr
a
tr
a
n
s
m
itter
s
wer
e
p
lace
d
to
in
ter
f
er
e.
E
n
v
ir
o
n
m
en
t
3
was
m
u
ch
n
o
is
y
.
T
h
e
s
ize
o
f
th
e
p
lace
was
1
0
.
8
×
7
.
3
m
.
L
o
S
c
o
m
m
u
n
icatio
n
was
av
ailab
le
b
etw
ee
n
th
e
tr
an
s
m
it
ter
s
an
d
th
e
r
ec
eiv
er
s
.
Data
w
er
e
co
llected
m
ai
n
tain
in
g
a
1
.
2
m
d
is
tan
ce
in
o
n
e
d
ir
ec
tio
n
an
d
0
.
6
m
in
t
h
e
o
t
h
er
.
Her
e
f
o
r
R
SS
I
m
ea
s
u
r
em
en
t,
Z
ig
B
ee
,
B
L
E
,
W
I
FI
wer
e
u
s
ed
.
Z
ig
B
ee
is
a
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
A
n
in
teg
r
a
ted
ma
c
h
in
e
lea
r
n
in
g
mo
d
el
fo
r
in
d
o
o
r
n
etw
o
r
k
o
p
timiz
a
tio
n
to
… (
A
h
med
Wa
s
if R
eza
)
399
n
etwo
r
k
in
g
p
r
o
to
c
o
l
f
o
r
cr
ea
t
in
g
p
er
s
o
n
al
ar
ea
n
etwo
r
k
s
.
I
t
r
eq
u
ir
es
lo
w
p
o
wer
an
d
b
a
n
d
wid
th
to
o
p
er
ate.
Ar
d
u
in
o
Un
o
m
icr
o
c
o
n
tr
o
ller
s
with
s
er
ies
2
XB
E
E
s
wer
e
u
s
ed
in
[
3
1
]
f
o
r
g
ettin
g
h
i
g
h
th
r
o
u
g
h
p
u
t.
Gim
b
al
s
er
ies
1
0
was
u
s
ed
in
[
3
1
]
as
t
r
an
s
m
itter
s
.
T
h
e
iB
ea
co
n
p
r
o
d
u
ce
d
u
n
iv
er
s
ally
u
n
iq
u
e
id
en
ti
f
ier
(
UUI
D)
,
m
ajo
r
v
alu
e,
an
d
m
in
o
r
v
alu
e.
Sad
o
wsk
i
et
a
l.
[
3
1
]
,
p
r
o
p
o
s
ed
R
a
s
p
b
er
r
y
PI
3
Mo
d
el
B
s
wer
e
u
s
e
d
to
co
llect
th
e
R
SS
I
v
alu
es.
Als
o
,
in
[
3
1
]
,
R
asp
b
er
r
y
PI
3
was
u
s
ed
as
r
ec
eiv
er
s
an
d
tr
an
s
m
itter
s
.
PI
3
s
alo
n
g
with
a
n
o
n
b
o
a
r
d
a
n
ten
n
a
wer
e
u
s
ed
to
cr
ea
te
a
W
L
AN
n
etwo
r
k
.
B
y
p
o
llin
g
th
e
R
asp
b
er
r
y
an
ten
n
a
,
R
SS
I
v
alu
es
wer
e
co
llected
.
(
a)
(
b
)
(
c)
Fig
u
r
e
7
.
(
a
)
S
ce
n
ar
io
1
,
(
b
)
S
ce
n
ar
io
2
,
an
d
(
c)
S
ce
n
ar
i
o
3
4
.
1
.
E
v
a
lua
t
io
n
m
et
rics
Fo
r
ev
alu
atin
g
o
u
r
m
o
d
el,
we
h
av
e
u
s
ed
th
e
co
n
f
u
s
io
n
m
etr
ics.
C
o
n
f
u
s
io
n
m
etr
ics
r
etu
r
n
tr
u
e
p
o
s
itiv
e
(
T
P),
f
alse
p
o
s
itiv
e
(
FP
)
,
tr
u
e
n
eg
ativ
e
(
T
N)
,
an
d
f
alse
n
eg
ativ
e
(
FN)
.
B
y
u
s
in
g
th
ese
f
o
u
r
p
ar
am
eter
s
,
we
h
a
v
e
ca
lcu
late
d
th
e
p
r
ec
is
io
n
,
r
e
ca
ll,
F1
_
s
co
r
e,
an
d
ac
cu
r
ac
y
.
Pre
cisi
o
n
r
et
u
r
n
s
th
e
p
er
ce
n
tag
e
o
f
th
e
m
o
d
el’
s
r
elev
an
t
r
esu
l
t
wh
ile
r
ec
all
r
etu
r
n
s
th
e
p
er
ce
n
tag
e
o
f
co
r
r
ec
tly
class
if
ied
r
esu
lts
.
Acc
u
r
ac
y
r
etu
r
n
s
th
e
r
atio
o
f
to
tal
T
P
a
n
d
T
N.
F1
_
s
co
r
e
r
ep
r
esen
ts
th
e
weig
h
ted
av
er
a
g
e
o
f
p
r
ec
is
io
n
an
d
r
ec
all
o
f
t
h
e
m
o
d
el.
Fo
r
s
im
ilar
ly
d
is
tr
ib
u
ti
v
e
class
es,
we
u
s
e
ac
cu
r
ac
y
,
wh
ich
g
iv
es
m
o
r
e
p
r
ec
is
e
r
esu
lts
,
an
d
o
n
th
e
o
th
er
h
an
d
,
f
o
r
im
b
alan
ce
d
d
atasets
,
F1
_
s
co
r
e
g
iv
es
a
b
etter
r
esu
lt.
Pre
cisi
o
n
,
r
ec
all,
F1
_
s
co
r
e,
an
d
ac
cu
r
ac
y
ar
e
m
ea
s
u
r
ed
u
s
in
g
t
h
e
(1
)
-
(
4
)
.
Pre
cisi
o
n
=
+
(
1
)
R
ec
all
=
+
(
2
)
F1
_
s
co
r
e
=
2
×
(
Pr
ecis
i
o
n
×
Recal
l
Pr
ecis
i
o
n
+
Recal
l
)
(
3
)
Acc
u
r
ac
y
=
+
+
+
+
(
4
)
5.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
e
r
esu
lt
s
h
o
ws
th
at
o
u
r
p
r
o
p
o
s
ed
m
o
d
el
g
i
v
es
s
atis
f
ac
to
r
y
an
d
ac
cu
r
ate
r
esu
lts
.
Fo
r
th
r
ee
d
if
f
er
en
t
s
ce
n
ar
io
s
,
we
o
b
tain
ed
th
e
d
esire
d
o
u
tco
m
es.
Ou
r
m
o
d
e
l
h
elp
s
to
s
et
u
p
in
d
o
o
r
wir
eless
n
etwo
r
k
s
b
y
o
p
tim
izin
g
clu
s
ter
s
.
Ou
r
m
o
d
el
also
p
r
ed
icts
th
e
co
o
r
d
i
n
at
es
o
f
th
e
tr
an
s
m
itter
s
.
As
we
ca
n
f
i
g
u
r
e
o
u
t
th
e
o
p
tim
u
m
n
u
m
b
er
o
f
clu
s
ter
s
an
d
t
h
eir
co
o
r
d
in
ates
,
s
o
t
r
an
s
m
itter
s
ca
n
ea
s
ily
b
e
p
l
ac
ed
in
a
n
in
d
o
o
r
en
v
ir
o
n
m
en
t.
As
a
r
esu
lt,
th
e
m
ax
im
u
m
s
ig
n
al
s
tr
en
g
th
ca
n
b
e
r
ec
eiv
ed
b
y
an
y
u
s
er
wh
o
h
as
b
ee
n
r
o
am
in
g
th
r
o
u
g
h
t
h
e
co
v
er
ag
e
.
T
a
b
le
1
illu
s
tr
ates
th
e
ev
alu
atio
n
o
f
th
e
alg
o
r
ith
m
s
ac
co
r
d
in
g
to
s
ce
n
ar
io
s
1
,
2
,
an
d
3
.
I
t
also
s
h
o
ws
th
e
p
r
ec
is
io
n
,
r
ec
a
ll,
F1
_
s
co
r
e,
ac
cu
r
ac
y
,
an
d
k
-
f
o
ld
c
r
o
s
s
-
v
alid
atio
n
(
Kf
-
C
V)
s
co
r
es.
Acc
o
r
d
in
g
to
th
e
s
ce
n
ar
io
s
an
d
r
elev
an
t
wir
eless
tech
n
o
lo
g
ies,
KNN,
SVM,
an
d
GNB
g
i
v
e
1
0
0
%
o
f
ac
cu
r
ac
y
i
n
s
o
m
e
ca
s
es.
I
n
T
ab
le
1
,
th
e
co
lu
m
n
n
am
e
d
Kf
-
C
V
r
ep
r
esen
ts
th
e
ac
cu
r
ac
y
s
co
r
es
af
te
r
th
e
im
p
lem
en
tatio
n
o
f
th
e
cr
o
s
s
-
v
alid
atio
n
tech
n
i
q
u
e.
T
h
is
r
esam
p
lin
g
tech
n
iq
u
e
is
u
s
ed
f
o
r
r
e
-
ev
al
u
atin
g
th
e
o
u
tco
m
es
o
f
th
e
m
ac
h
in
e
lear
n
in
g
m
o
d
els.
T
h
e
p
ar
am
et
er
K
r
ep
r
esen
ts
th
e
n
u
m
b
er
o
f
g
r
o
u
p
s
in
wh
ich
th
e
d
ataset
will
s
p
lit.
W
e
h
av
e
s
elec
ted
a
co
m
m
o
n
ly
u
s
ed
v
al
u
e
o
f
1
0
f
o
r
t
h
e
K
p
ar
am
eter
d
u
r
in
g
th
e
ev
alu
atio
n
p
r
o
ce
s
s
.
Fo
r
ea
c
h
f
o
ld
,
t
h
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
2
4
,
No
.
1
,
Octo
b
er
20
21
:
39
4
-
40
2
400
ac
cu
r
ac
y
s
co
r
es
ar
e
ca
lcu
lated
.
T
h
e
m
ea
n
ac
c
u
r
ac
y
s
co
r
e
f
r
o
m
th
e
ten
iter
atio
n
s
is
also
ca
l
cu
lated
.
I
n
ter
m
s
o
f
av
er
ag
e
ac
cu
r
ac
y
,
KNN,
SVM,
an
d
GNB
r
etu
r
n
9
3
.
3
3
%,
8
6
.
7
0
%,
an
d
9
2
.
2
2
%,
r
esp
ec
ti
v
ely
.
T
h
ese
av
er
ag
e
ac
cu
r
ac
ies
wer
e
ca
lcu
lated
f
r
o
m
th
r
ee
d
if
f
er
e
n
t
s
ce
n
ar
io
s
as
p
r
esen
ted
in
Fig
u
r
es
7
(
a)
,
(
b
)
,
an
d
(
c)
.
T
h
e
tim
e
an
d
s
p
ac
e
co
m
p
le
x
ities
o
f
t
h
e
alg
o
r
ith
m
s
ar
e
also
m
en
tio
n
e
d
.
T
im
e
co
m
p
lex
ities
o
f
K
-
m
ea
n
s
,
KNN,
SVM,
GNB
ar
e
O
(
n
2
)
,
O
(
n
×
m
)
,
O
(
n
2
)
,
O
(
n
×
m
×
n
)
an
d
s
p
ac
e
co
m
p
lex
ities
ar
e
O
(
n
+
m
)
,
O
(
n
×
m
)
,
O
(
n
×
m
)
,
O
(
m
×
c
)
.
Du
e
to
t
h
e
s
ca
r
city
o
f
d
ata
,
th
e
ac
cu
r
ac
y
o
f
SVM
is
lo
wer
co
m
p
ar
e
d
to
KNN
an
d
GNB.
On
th
e
o
th
er
h
an
d
,
K
NN
attai
n
ed
h
ig
h
er
ac
c
u
r
ac
y
.
Als
o
,
GNB
r
etu
r
n
s
a
g
o
o
d
a
cc
u
r
ac
y
ag
ai
n
s
t
th
e
d
ataset
as
u
s
ed
p
r
ev
io
u
s
ly
.
T
h
o
u
g
h
t
h
e
wir
eless
tech
n
o
lo
g
ie
s
wer
e
u
tili
ze
d
to
co
llect
th
e
d
ata,
d
u
e
to
h
av
in
g
a
lim
ited
d
ataset
in
f
ew
ca
s
es,
i.e
.
,
s
ce
n
ar
io
2
,
SVM
d
id
n
o
t
p
er
f
o
r
m
s
atis
f
ac
t
o
r
ily
.
Var
za
k
as
[
3
2
]
s
tu
d
ied
t
h
e
av
er
ag
e
ch
a
n
n
el
ca
p
ac
ity
o
f
a
h
y
b
r
i
d
ce
llu
lar
s
y
s
tem
is
th
eo
r
etica
lly
ac
h
iev
e
d
b
y
i
n
co
r
p
o
r
atin
g
d
ir
ec
t
s
eq
u
en
ce
(
DS)
,
f
ast
f
r
eq
u
en
cy
h
o
p
p
i
n
g
(
FF
H)
,
an
d
co
d
e
-
d
iv
is
io
n
m
u
ltip
le
-
ac
ce
s
s
(
C
DM
A)
.
Al
s
o
,
th
e
co
m
p
ar
ativ
e
a
n
aly
s
is
is
p
r
esen
ted
in
[
3
2
]
with
th
e
s
im
u
lat
ed
r
esu
lts
.
I
n
ter
m
s
o
f
c
o
m
p
ar
is
o
n
,
th
e
e
x
is
tin
g
r
esear
ch
es
in
th
is
f
ield
ar
e
m
ain
ly
f
o
cu
s
ed
o
n
in
d
o
o
r
lo
ca
l
izatio
n
s
y
s
tem
s
wh
ile
th
e
s
co
p
e
o
f
th
e
p
r
o
p
o
s
ed
r
esear
ch
is
to
f
in
d
th
e
o
p
tim
u
m
n
u
m
b
er
o
f
tr
an
s
m
itter
s
b
ased
o
n
t
h
e
clu
s
ter
in
g
a
p
p
r
o
ac
h
an
d
allo
ca
tin
g
n
ew
u
s
er
s
b
ased
o
n
t
h
e
s
ig
n
al
s
tr
en
g
th
b
y
en
s
u
r
i
n
g
m
ax
im
u
m
co
v
e
r
ag
e
o
f
th
e
n
etwo
r
k
wh
ich
ad
d
s
a
n
ew
d
im
en
s
io
n
in
in
d
o
o
r
wir
eless
co
m
m
u
n
icatio
n
.
C
o
m
p
a
r
ativ
e
an
aly
s
is
h
as
b
ee
n
p
r
esen
ted
in
T
a
b
le
1
b
y
in
co
r
p
o
r
atin
g
th
e
o
u
tco
m
es
f
r
o
m
KNN,
SVM,
an
d
GNB.
Al
s
o
,
th
e
Kf
-
C
V
s
co
r
es
ar
e
ad
d
ed
to
p
r
esen
t
a
m
o
r
e
p
r
ec
is
e
co
m
p
ar
is
o
n
an
d
en
s
u
r
e
th
e
ef
f
icac
y
o
f
th
e
o
u
tco
m
e
s
f
r
o
m
th
e
ab
o
v
e
-
m
en
tio
n
ed
a
lg
o
r
ith
m
s
.
As
th
er
e
ar
e
n
o
u
n
u
s
u
al
v
a
r
iatio
n
s
in
th
e
o
b
tain
e
d
r
esu
lts
b
e
f
o
r
e
an
d
a
f
ter
in
tr
o
d
u
cin
g
th
e
cr
o
s
s
-
v
ali
d
atio
n
tech
n
iq
u
e,
it
in
d
icate
s
th
at
th
e
ex
p
er
im
e
n
tal
f
in
d
in
g
s
ar
e
i
d
en
tical
to
th
e
o
b
jectiv
es o
f
th
e
p
r
o
p
o
s
ed
r
esear
ch
wo
r
k
an
d
h
av
e
s
ig
n
if
ican
t p
o
ten
tial in
th
e
ex
t
en
s
iv
e
s
ec
to
r
o
f
wir
eless
n
etwo
r
k
in
g
an
d
c
o
m
m
u
n
icatio
n
s
.
T
ab
le
1
.
Per
f
o
r
m
an
ce
o
f
th
e
m
ac
h
in
e
lear
n
in
g
m
o
d
els
S
c
e
n
a
r
i
o
A
l
g
o
r
i
t
h
m
Te
c
h
n
o
l
o
g
y
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
F
1
_
S
c
o
r
e
A
c
c
u
r
a
c
y
Kf
-
CV
S
c
e
n
a
r
i
o
1
K
-
n
e
a
r
e
st
n
e
i
g
h
b
o
r
s
(
K
N
N
)
Zi
g
B
e
e
1
0
0
1
0
0
1
0
0
1
0
0
94
B
LE
8
1
9
0
8
5
.
3
9
0
96
W
i
F
i
1
0
0
1
0
0
1
0
0
1
0
0
90
S
u
p
p
o
r
t
v
e
c
t
o
r
ma
c
h
i
n
e
(
S
V
M
)
Zi
g
B
e
e
9
3
9
0
9
0
.
3
90
9
1
.
5
B
LE
8
1
9
0
8
5
.
3
90
98
W
i
F
i
1
0
0
1
0
0
1
0
0
1
0
0
94
G
a
u
ss
i
a
n
N
a
i
v
e
B
a
y
e
s
(
G
N
B
)
Zi
g
B
e
e
9
3
9
0
9
0
.
3
9
0
9
1
.
5
B
LE
8
1
9
0
8
5
.
3
9
0
94
W
i
F
i
1
0
0
1
0
0
1
0
0
1
0
0
94
S
c
e
n
a
r
i
o
2
K
-
n
e
a
r
e
st
n
e
i
g
h
b
o
r
s
(
K
N
N
)
Zi
g
B
e
e
83
75
7
3
.
3
75
75
B
LE
1
0
0
1
0
0
1
0
0
1
0
0
85
W
i
F
i
1
0
0
1
0
0
1
0
0
1
0
0
95
S
u
p
p
o
r
t
v
e
c
t
o
r
ma
c
h
i
n
e
(
S
V
M
)
Zi
g
B
e
e
83
75
73
75
70
B
LE
1
0
0
50
67
50
90
W
i
F
i
1
0
0
1
0
0
1
0
0
1
0
0
95
G
a
u
ss
i
a
n
N
a
i
v
e
B
a
y
e
s
(
G
N
B
)
Zi
g
B
e
e
25
50
33
50
70
B
LE
1
0
0
1
0
0
1
0
0
1
0
0
85
W
i
F
i
1
0
0
1
0
0
1
0
0
1
0
0
1
0
0
S
c
e
n
a
r
i
o
3
K
-
n
e
a
r
e
st
n
e
i
g
h
b
o
r
s
(
K
N
N
)
Zi
g
B
e
e
1
0
0
1
0
0
1
0
0
1
0
0
8
7
.
5
B
LE
90
88
8
7
.
3
8
7
.
5
9
2
.
5
W
i
F
i
90
88
8
7
.
3
8
7
.
5
90
S
u
p
p
o
r
t
v
e
c
t
o
r
ma
c
h
i
n
e
(
S
V
M
)
Zi
g
B
e
e
1
0
0
1
0
0
1
0
0
1
0
0
1
0
0
B
LE
83
75
7
3
.
3
75
9
7
.
5
W
i
F
i
1
0
0
1
0
0
1
0
0
1
0
0
1
0
0
G
a
u
ss
i
a
n
N
a
i
v
e
B
a
y
e
s
(
G
N
B
)
Zi
g
B
e
e
1
0
0
1
0
0
1
0
0
1
0
0
8
7
.
5
B
LE
1
0
0
1
0
0
1
0
0
1
0
0
9
2
.
5
W
i
F
i
1
0
0
1
0
0
1
0
0
1
0
0
9
7
.
5
6.
CO
NCLU
SI
O
N
I
n
th
is
r
esear
ch
,
we
o
b
tain
ed
th
e
m
in
im
u
m
n
u
m
b
er
o
f
tr
a
n
s
m
itter
s
to
m
ax
im
ize
th
e
co
v
er
ag
e
f
o
r
th
r
ee
d
if
f
er
en
t
i
n
d
o
o
r
e
x
p
er
i
m
en
tal
en
v
ir
o
n
m
e
n
ts
.
W
e
h
a
v
e
in
co
r
p
o
r
ate
d
K
-
m
ea
n
s
,
K
NN,
SVM,
an
d
GNB
an
d
ac
h
iev
e
d
th
e
m
o
s
t
ac
cu
r
at
e
r
esu
lts
f
r
o
m
th
e
KNN
alg
o
r
i
th
m
.
Kf
-
C
V
tech
n
iq
u
e
h
as
b
e
en
im
p
lem
en
ted
t
o
v
alid
ate
th
e
ex
p
er
im
en
tal
s
im
u
latio
n
s
an
d
r
e
-
ev
alu
ate
th
e
o
u
tco
m
es o
f
th
e
m
ac
h
in
e
lear
n
i
n
g
m
o
d
els.
Als
o
,
th
e
co
m
p
ar
ativ
e
a
n
aly
s
is
h
as e
n
r
ich
ed
th
e
v
alid
ity
o
f
th
e
r
esu
lts
an
d
en
s
u
r
e
d
th
e
ef
f
icac
y
o
f
t
h
e
p
r
o
p
o
s
ed
r
esear
ch
wo
r
k
.
Ou
r
p
r
o
p
o
s
ed
m
o
d
el
is
ca
p
ab
le
o
f
d
etec
tin
g
th
e
m
in
im
u
m
n
u
m
b
er
o
f
tr
an
s
m
itter
s
b
ased
o
n
th
e
R
SS
I
v
alu
es
b
y
in
co
r
p
o
r
atin
g
m
ac
h
i
n
e
lear
n
in
g
al
g
o
r
ith
m
s
.
B
ased
o
n
th
e
o
b
tain
ed
r
esu
lts
,
we
ca
n
co
n
clu
d
e
th
at
th
e
p
r
o
p
o
s
ed
r
esear
c
h
wo
r
k
wo
u
ld
ad
d
a
s
ig
n
if
ican
t
co
n
tr
i
b
u
tio
n
to
t
h
e
f
ield
o
f
wir
el
ess
n
etwo
r
k
in
g
an
d
co
m
m
u
n
icatio
n
s
.
Ho
wev
er
,
t
h
e
m
o
d
el’
s
ac
cu
r
ac
y
ca
n
b
e
h
ig
h
er
with
f
u
r
th
er
r
esear
ch
an
d
m
o
r
e
in
tr
icate
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
A
n
in
teg
r
a
ted
ma
c
h
in
e
lea
r
n
in
g
mo
d
el
fo
r
in
d
o
o
r
n
etw
o
r
k
o
p
timiz
a
tio
n
to
… (
A
h
med
Wa
s
if R
eza
)
401
tu
n
in
g
a
n
d
also
b
y
tr
ain
in
g
t
h
e
m
o
d
el
with
a
la
r
g
er
d
ataset.
T
h
e
f
u
r
th
e
r
d
e
p
lo
y
m
e
n
t
o
f
th
is
wo
r
k
ca
n
b
e
b
en
ef
icial
to
o
p
tim
ize
an
y
in
d
o
o
r
n
etwo
r
k
b
y
d
o
i
n
g
clu
s
ter
an
aly
s
is
b
ased
o
n
th
e
R
SS
I
v
alu
es
an
d
co
o
r
d
in
ate
s
y
s
tem
.
I
n
ca
s
e
o
f
id
e
n
tify
in
g
p
r
o
p
ag
an
d
a
ca
m
p
aig
n
s
,
u
n
d
er
s
tan
d
in
g
c
u
s
to
m
er
’
s
p
u
r
ch
asin
g
in
ter
est
an
d
b
eh
av
io
r
al
an
al
y
s
is
,
r
ec
o
m
m
en
d
atio
n
s
r
elate
d
to
n
ew
lo
ca
tio
n
ex
p
an
s
io
n
f
o
r
a
b
u
s
i
n
ess
b
ased
o
n
th
e
g
en
er
ated
tr
a
f
f
ic,
th
is
m
eth
o
d
wo
u
ld
also
b
e
b
en
ef
icial.
RE
F
E
R
E
NC
E
S
[
1
]
C
.
H
u
a
n
g
,
H
.
L
i
u
,
W
.
W
a
n
g
a
n
d
J
.
L
i
,
"
A
C
o
m
p
a
c
t
a
n
d
C
o
s
t
-
E
f
f
e
c
t
iv
e
B
L
E
B
e
a
c
o
n
w
i
t
h
M
u
l
t
i
p
r
o
t
o
c
o
l
a
n
d
D
y
n
a
m
i
c
C
o
n
t
e
n
t
A
d
v
e
r
t
i
s
i
n
g
f
o
r
I
o
T
A
p
p
l
i
c
a
t
i
o
n
,
"
i
n
I
E
E
E
I
n
t
e
r
n
e
t
o
f
T
h
i
n
g
s
J
o
u
r
n
a
l
,
v
o
l
.
7
,
n
o
.
3
,
p
p
.
2
3
0
9
-
2
3
2
0
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
J
I
O
T
.
2
0
1
9
.
2
9
5
8
4
5
5
.
[2
]
H.
P
iray
e
sh
,
P
.
Kh
e
ir
k
h
a
h
S
a
n
g
d
e
h
a
n
d
H.
Zen
g
,
"
S
e
c
u
ri
n
g
Z
ig
Be
e
Co
m
m
u
n
ica
ti
o
n
s
Ag
a
in
st
C
o
n
sta
n
t
Ja
m
m
in
g
Attac
k
Us
in
g
Ne
u
ra
l
Ne
two
r
k
,
"
in
I
EE
E
I
n
ter
n
e
t
o
f
T
h
in
g
s
J
o
u
rn
a
l
,
v
o
l
.
8
,
n
o
.
6
,
p
p
.
4
9
5
7
-
4
9
6
8
,
2
0
2
1
,
d
o
i:
1
0
.
1
1
0
9
/JIOT.
2
0
2
0
.
3
0
3
4
1
2
8
.
[3
]
M
.
Ab
d
e
lHa
fe
e
z
,
A.
H.
A
h
m
e
d
a
n
d
M
.
Ab
d
e
l
Ra
h
e
e
m
,
"
De
sig
n
a
n
d
Op
e
ra
ti
o
n
o
f
a
Li
g
h
twe
ig
h
t
E
d
u
c
a
ti
o
n
a
l
Tes
tb
e
d
fo
r
In
tern
e
t
-
of
-
T
h
in
g
s
A
p
p
li
c
a
ti
o
n
s,"
in
IEE
E
I
n
ter
n
e
t
o
f
T
h
in
g
s
J
o
u
rn
a
l
,
v
o
l
.
7
,
n
o
.
1
2
,
p
p
.
1
1
4
4
6
-
1
1
4
5
9
,
De
c
.
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/JIOT.
2
0
2
0
.
3
0
1
2
0
2
2
.
[4
]
J.
S
.
Lo
u
ro
,
T.
R
u
i
F
e
rn
a
n
d
e
s,
H.
Ro
d
ri
g
u
e
s
a
n
d
R.
F
.
S
.
Ca
ld
e
iri
n
h
a
,
"
3
D
I
n
d
o
o
r
Ra
d
io
C
o
v
e
ra
g
e
f
o
r
5
G
P
lan
n
i
n
g
:
A
F
ra
m
e
wo
rk
o
f
Co
m
b
in
i
n
g
B
IM
with
Ra
y
-
trac
in
g
,
"
2
0
2
0
1
2
th
In
ter
n
a
ti
o
n
a
l
S
y
mp
o
si
u
m
o
n
Co
mm
u
n
ica
t
io
n
S
y
ste
ms
,
Ne
two
rk
s
a
n
d
Dig
it
a
l
S
ig
n
a
l
Pro
c
e
ss
in
g
(CS
NDS
P),
P
o
rto
,
P
o
rtu
g
a
l,
2
0
2
0
,
p
p
.
1
-
5
,
d
o
i:
1
0
.
1
1
0
9
/CS
ND
S
P
4
9
0
4
9
.
2
0
2
0
.
9
2
4
9
5
0
3
.
[5
]
Y.
Zi
a
d
e
,
"
Op
ti
m
iza
ti
o
n
o
f
in
d
o
o
r
ra
d
io
c
o
v
e
ra
g
e
,
"
2
0
1
8
IEE
E
M
id
d
le
Ea
st
a
n
d
No
rth
Af
ric
a
Co
mm
u
n
ica
ti
o
n
s
Co
n
fer
e
n
c
e
(M
ENA
CO
M
M
)
,
Jo
u
n
ieh
,
Leb
a
n
o
n
,
2
0
1
8
,
p
p
.
1
-
6
,
d
o
i:
1
0
.
1
1
0
9
/M
ENACO
M
M
.
2
0
1
8
.
8
3
7
1
0
2
3
.
[6
]
W.
F
a
k
h
e
t,
S
.
E.
Kh
e
d
iri
,
A.
Da
ll
a
li
a
n
d
A.
Ka
c
h
o
u
ri
,
"
Ne
w
K
-
m
e
a
n
s
a
lg
o
rit
h
m
f
o
r
c
lu
ste
rin
g
i
n
wire
les
s
se
n
so
r
n
e
two
rk
s,
"
2
0
1
7
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
I
n
ter
n
e
t
o
f
T
h
i
n
g
s,
Em
b
e
d
d
e
d
S
y
ste
ms
a
n
d
Co
mm
u
n
ica
ti
o
n
s
(IINT
EC),
G
a
fsa
,
2
0
1
7
,
p
p
.
6
7
-
7
1
,
d
o
i:
1
0
.
1
1
0
9
/IIN
TE
C.
2
0
1
7
.
8
3
2
5
9
1
5
.
[7
]
J.
Na
y
a
k
,
B
.
Na
ik
,
a
n
d
H.
Be
h
e
ra
,
“
A
c
o
m
p
re
h
e
n
siv
e
s
u
rv
e
y
o
n
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
i
n
e
in
d
a
t
a
m
in
in
g
tas
k
s:
a
p
p
li
c
a
ti
o
n
s
a
n
d
c
h
a
ll
e
n
g
e
s
,”
In
te
rn
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Da
t
a
b
a
se
T
h
e
o
ry
a
n
d
Ap
p
li
c
a
t
io
n
,
v
o
l.
8
,
n
o
.
1
,
p
p
.
1
6
9
-
1
8
6
,
2
0
1
5
,
d
o
i:
1
0
.
1
4
2
5
7
/i
j
d
ta.2
0
1
5
.
8
.
1
.
1
8
.
[8
]
B.
Zh
u
,
E
.
Be
d
e
e
r,
H.
H
.
Ng
u
y
e
n
,
R.
Ba
rt
o
n
a
n
d
J.
He
n
ry
,
"
I
m
p
ro
v
e
d
S
o
f
t
-
k
-
M
e
a
n
s
Clu
ste
rin
g
Alg
o
rit
h
m
fo
r
Ba
lan
c
in
g
E
n
e
rg
y
Co
n
su
m
p
t
io
n
in
Wi
re
les
s
S
e
n
s
o
r
Ne
two
rk
s
,
"
i
n
IEE
E
In
ter
n
e
t
o
f
T
h
i
n
g
s
J
o
u
r
n
a
l
,
v
o
l
.
8
,
n
o
.
6
,
p
p
.
4
8
6
8
-
4
8
8
1
,
1
5
M
a
rc
h
,
2
0
2
1
,
d
o
i:
1
0
.
1
1
0
9
/JIOT.
2
0
2
0
.
3
0
3
1
2
7
2
.
[9
]
A.
Ha
ss
a
n
,
W
.
M
.
S
h
a
h
,
A.
H
u
se
in
,
a
n
d
A.
A.
J.
M
o
h
a
m
m
e
d
,
M
.
F
.
I.
Oth
m
a
n
,
a
n
d
M
.
S
.
Ta
li
b
,
“
Clu
st
e
ri
n
g
a
p
p
ro
a
c
h
i
n
wire
les
s
se
n
so
r
n
e
two
rk
s
b
a
se
d
o
n
k
-
m
e
a
n
s:
Li
m
it
a
ti
o
n
s
a
n
d
re
c
o
m
m
e
n
d
a
ti
o
n
s
,”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Rec
e
n
t
T
e
c
h
n
o
l
o
g
y
a
n
d
E
n
g
in
e
e
rin
g
,
v
o
l
.
7
,
n
o
.
6
5
,
p
p
.
1
1
9
-
1
2
6
,
2
0
1
9
.
[1
0
]
Y.
Zh
a
o
,
W
.
Wo
n
g
,
T.
F
e
n
g
a
n
d
H.
K.
G
a
rg
,
"
Eff
icie
n
t
a
n
d
S
c
a
lab
le
Ca
li
b
ra
ti
o
n
-
F
re
e
In
d
o
o
r
P
o
siti
o
n
in
g
Us
in
g
Cro
wd
so
u
rc
e
d
Da
ta,"
i
n
IEE
E
In
ter
n
e
t
o
f
T
h
in
g
s
J
o
u
rn
a
l
,
v
o
l
.
7
,
n
o
.
1
,
p
p
.
1
6
0
-
1
7
5
,
Ja
n
.
2
0
2
0
,
d
o
i:
1
0
.
1
1
0
9
/JIOT.
2
0
1
9
.
2
9
4
4
9
2
9
.
[1
1
]
A.
Ne
ss
a
,
B.
Ad
h
ik
a
ri,
F
.
Hu
ss
a
i
n
a
n
d
X.
N.
F
e
rn
a
n
d
o
,
"
A
S
u
r
v
e
y
o
f
M
a
c
h
i
n
e
Le
a
rn
in
g
f
o
r
In
d
o
o
r
P
o
siti
o
n
i
n
g
,
"
in
IEE
E
Acc
e
ss
,
v
o
l
.
8
,
p
p
.
2
1
4
9
4
5
-
2
1
4
9
6
5
,
2
0
2
0
,
d
o
i:
1
0
.
1
1
0
9
/ACC
ES
S
.
2
0
2
0
.
3
0
3
9
2
7
1
.
[1
2
]
K.
Wan
g
,
"
Qu
a
si
-
P
a
ss
iv
e
In
d
o
o
r
Op
ti
c
a
l
Wi
re
les
s
Co
m
m
u
n
ic
a
ti
o
n
S
y
ste
m
s,"
in
IEE
E
Ph
o
to
n
ics
T
e
c
h
n
o
l
o
g
y
L
e
tt
e
rs
,
v
o
l
.
3
2
,
n
o
.
2
1
,
p
p
.
1
3
7
3
-
1
3
7
6
,
1
N
o
v
.
1
,
2
0
2
0
,
d
o
i:
1
0
.
1
1
0
9
/L
P
T
.
2
0
2
0
.
3
0
2
6
3
4
3
.
[1
3
]
W.
Ya
n
g
,
J.
Z
h
a
n
g
,
A.
A.
G
laz
u
n
o
v
a
n
d
J.
Z
h
a
n
g
,
"
Li
n
e
-
of
-
S
i
g
h
t
P
ro
b
a
b
il
it
y
f
o
r
C
h
a
n
n
e
l
M
o
d
e
li
n
g
in
3
-
D
I
n
d
o
o
r
En
v
ir
o
n
m
e
n
ts,
"
i
n
IE
EE
A
n
ten
n
a
s
a
n
d
W
ire
les
s
Pro
p
a
g
a
ti
o
n
L
e
tt
e
rs
,
v
o
l
.
1
9
,
n
o
.
7
,
p
p
.
1
1
8
2
-
1
1
8
6
,
Ju
ly
2
0
2
0
,
d
o
i:
1
0
.
1
1
0
9
/L
AWP
.
2
0
2
0
.
2
9
9
4
3
9
2
.
[1
4
]
C.
Li
u
,
C
.
Wan
g
a
n
d
J
.
Lu
o
,
"
Larg
e
-
S
c
a
le
De
e
p
Lea
rn
in
g
F
ra
m
e
wo
rk
o
n
F
P
G
A
fo
r
F
in
g
e
rp
ri
n
t
-
Ba
se
d
In
d
o
o
r
Lo
c
a
li
z
a
ti
o
n
,
"
i
n
IEE
E
Acc
e
ss
,
v
o
l.
8
,
p
p
.
6
5
6
0
9
-
6
5
6
1
7
,
2
0
2
0
,
d
o
i:
1
0
.
1
1
0
9
/AC
CE
S
S
.
2
0
2
0
.
2
9
8
5
1
6
2
.
[1
5
]
C.
Du
,
B.
P
e
n
g
,
Z.
Zh
a
n
g
,
W.
Xu
e
a
n
d
M
.
G
u
a
n
,
"
KF
-
KN
N:
Lo
w
-
Co
st
a
n
d
Hi
g
h
-
Ac
c
u
ra
te
F
M
-
Ba
se
d
In
d
o
o
r
Lo
c
a
li
z
a
ti
o
n
M
o
d
e
l
v
ia
F
in
g
e
rp
rin
t
Tec
h
n
o
l
o
g
y
,
"
in
IEE
E
Acc
e
ss
,
v
o
l.
8
,
p
p
.
1
9
7
5
2
3
-
1
9
7
5
3
1
,
2
0
2
0
,
d
o
i:
1
0
.
1
1
0
9
/ACCES
S
.
2
0
2
0
.
3
0
3
1
0
8
9
.
[1
6
]
M
.
Jia
,
S
.
B.
A.
K
h
a
tt
a
k
,
Q.
G
u
o
,
X.
G
u
a
n
d
Y.
Li
n
,
"
Ac
c
e
ss
P
o
i
n
t
Op
ti
m
iza
ti
o
n
fo
r
Re
li
a
b
le
I
n
d
o
o
r
Lo
c
a
li
z
a
ti
o
n
S
y
ste
m
s,"
in
IEE
E
T
ra
n
s
a
c
ti
o
n
s
o
n
Relia
b
il
it
y
,
v
o
l.
6
9
,
n
o
.
4
,
p
p
.
1
4
2
4
-
1
4
3
6
,
De
c
.
2
0
2
0
,
d
o
i:
1
0
.
1
1
0
9
/T
R.
2
0
1
9
.
2
9
5
5
7
4
8
.
[1
7
]
Já
n
Tó
th
,
Ľ
u
b
o
š
Ov
se
n
ík
,
Já
n
T
u
rá
n
,
Li
n
u
s
M
ich
a
e
li
,
M
ic
h
a
l
M
á
rto
n
,
"
C
las
sifica
ti
o
n
P
re
d
icti
o
n
A
n
a
ly
sis
o
f
RS
S
I
P
a
ra
m
e
ter
in
H
a
rd
S
witch
in
g
P
r
o
c
e
ss
fo
r
F
S
O/RF
S
y
ste
m
s,
"
i
n
M
e
a
su
re
me
n
t
,
v
o
l
.
1
1
6
,
p
p
.
6
0
2
-
6
1
0
,
F
e
b
.
2
0
1
8
,
doi
:
1
0
.
1
0
1
6
/
j.
m
e
a
su
re
m
e
n
t.
2
0
1
7
.
1
1
.
0
4
4
.
[1
8
]
F.
G
h
a
fa
ri,
S
.
M
irrah
imi,
a
n
d
S
.
He
id
a
ri
,
"
In
f
lu
e
n
c
e
o
f
C
e
il
i
n
g
H
e
ig
h
t
o
n
H
e
a
ti
n
g
E
n
e
rg
y
C
o
n
su
m
p
ti
o
n
i
n
E
d
u
c
a
ti
o
n
a
l
B
u
il
d
i
n
g
"
i
n
1
5
t
h
In
t
e
rn
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
C
ivil
a
n
d
Arc
h
it
e
c
tu
re
En
g
in
e
e
rin
g
,
M
a
y
2
0
1
8
.
[1
9
]
L.
Ch
e
tt
r
i
a
n
d
R.
Be
ra
,
"
A
Co
m
p
re
h
e
n
siv
e
S
u
r
v
e
y
o
n
I
n
tern
e
t
o
f
Th
i
n
g
s
(Io
T)
To
wa
r
d
5
G
Wi
re
l
e
ss
S
y
ste
m
s,"
in
IEE
E
In
ter
n
e
t
o
f
T
h
i
n
g
s
J
o
u
r
n
a
l
,
v
o
l.
7
,
n
o
.
1
,
p
p
.
1
6
-
3
2
,
Ja
n
.
2
0
2
0
,
d
o
i:
1
0
.
1
1
0
9
/JIOT
.
2
0
1
9
.
2
9
4
8
8
8
8
.
[2
0
]
A.
M
a
jd
a
ra
a
n
d
S
.
No
o
sh
a
b
a
d
i,
"
No
n
p
a
ra
m
e
tri
c
De
n
sity
Esti
m
a
ti
o
n
Us
in
g
Co
p
u
la
Tran
sfo
rm
,
Ba
y
e
sia
n
S
e
q
u
e
n
ti
a
l
P
a
rti
ti
o
n
in
g
,
a
n
d
Diffu
si
o
n
-
Ba
se
d
Ke
rn
e
l
Esti
m
a
to
r,
"
i
n
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
Kn
o
wled
g
e
a
n
d
D
a
ta
E
n
g
i
n
e
e
rin
g
,
v
o
l.
3
2
,
n
o
.
4
,
p
p
.
8
2
1
-
8
2
6
,
1
A
p
r
il
2
0
2
0
,
d
o
i:
1
0
.
1
1
0
9
/T
KD
E.
2
0
1
9
.
2
9
3
0
0
5
2
.
[
2
1
]
K
.
P
.
S
i
n
a
g
a
a
n
d
M
.
Y
a
n
g
,
"
U
n
s
u
p
e
r
v
i
s
e
d
K
-
M
e
a
n
s
C
l
u
s
te
r
i
n
g
A
l
g
o
r
i
t
h
m
,
"
i
n
I
E
E
E
A
c
c
e
s
s
,
v
o
l
.
8
,
p
p
.
8
0
7
1
6
-
8
0
7
2
7
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
E
S
S
.
2
0
2
0
.
2
9
8
8
7
9
6
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
2
4
,
No
.
1
,
Octo
b
er
20
21
:
39
4
-
40
2
402
[2
2
]
Y.
Zh
a
n
g
,
J.
Wu
,
J.
Wan
g
a
n
d
C.
Xin
g
,
"
A
Tran
sfo
rm
a
ti
o
n
-
Ba
se
d
F
ra
m
e
wo
rk
fo
r
KN
N
S
e
t
S
i
m
il
a
rit
y
S
e
a
rc
h
,
"
in
IEE
E
T
ra
n
s
a
c
ti
o
n
s
o
n
K
n
o
w
led
g
e
a
n
d
Da
t
a
En
g
in
e
e
rin
g
,
v
o
l.
3
2
,
n
o
.
3
,
p
p
.
4
0
9
-
4
2
3
,
1
M
a
rc
h
2
0
2
0
,
d
o
i:
1
0
.
1
1
0
9
/T
KD
E.
2
0
1
8
.
2
8
8
6
1
8
9
.
[2
3
]
N.
M
a
rc
h
a
n
g
a
n
d
R.
Tr
ip
a
th
i,
"
KN
N
-
S
T:
Ex
p
l
o
it
i
n
g
S
p
a
ti
o
-
Tem
p
o
ra
l
Co
rre
latio
n
fo
r
M
issi
n
g
Da
ta
In
fe
re
n
c
e
in
En
v
ir
o
n
m
e
n
tal
Cro
w
d
S
e
n
sin
g
,
"
i
n
I
EE
E
S
e
n
s
o
rs
J
o
u
rn
a
l
,
v
o
l.
2
1
,
n
o
.
3
,
p
p
.
3
4
2
9
-
3
4
3
6
,
1
F
e
b
.
1
,
2
0
2
1
,
d
o
i:
1
0
.
1
1
0
9
/JS
EN.
2
0
2
0
.
3
0
2
4
9
7
6
.
[2
4
]
W.
Xin
g
a
n
d
Y.
Be
i,
"
M
e
d
ica
l
He
a
lt
h
Big
Da
ta
Clas
sifica
ti
o
n
B
a
se
d
o
n
KN
N
Clas
sifica
ti
o
n
Al
g
o
rit
h
m
,
"
in
IEE
E
Acc
e
ss
,
v
o
l.
8
,
p
p
.
2
8
8
0
8
-
2
8
8
1
9
,
2
0
2
0
,
d
o
i:
1
0
.
1
1
0
9
/ACCE
S
S
.
2
0
1
9
.
2
9
5
5
7
5
4
.
[2
5
]
T.
Da
o
,
T
.
N
g
u
y
e
n
,
J.
P
a
n
,
Y.
Qi
a
o
a
n
d
Q.
Lai,
"
I
d
e
n
ti
fica
ti
o
n
F
a
i
lu
re
Da
ta
f
o
r
C
lu
ste
r
He
a
d
s
Ag
g
r
e
g
a
ti
o
n
i
n
W
S
N
Ba
se
d
o
n
Im
p
r
o
v
i
n
g
Clas
sifica
ti
o
n
o
f
S
VM,
"
i
n
I
EE
E
Acc
e
ss
,
v
o
l.
8
,
p
p
.
6
1
0
7
0
-
6
1
0
8
4
,
2
0
2
0
,
d
o
i:
1
0
.
1
1
0
9
/ACCES
S
.
2
0
2
0
.
2
9
8
3
2
1
9
.
[
2
6
]
G
.
W
a
n
g
,
J
.
L
u
,
K
.
C
h
o
i
a
n
d
G
.
Z
h
a
n
g
,
"
A
T
r
a
n
s
f
e
r
-
B
a
s
e
d
A
d
d
i
t
i
v
e
L
S
-
S
V
M
C
l
a
s
s
i
f
i
e
r
f
o
r
H
a
n
d
l
i
n
g
M
i
s
s
i
n
g
D
a
t
a
,
"
in
I
E
E
E
T
r
a
n
s
a
c
t
i
o
n
s
o
n
C
y
b
e
r
n
e
t
i
c
s
,
v
o
l
.
5
0
,
n
o
.
2
,
p
p
.
7
3
9
-
7
5
2
,
F
e
b
.
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
T
C
Y
B
.
2
0
1
8
.
2
8
7
2
8
0
0
.
[2
7
]
K.
Li
,
X.
Ch
e
n
,
R.
Z
h
a
n
g
a
n
d
E.
P
ick
we
ll
-
M
a
c
P
h
e
rso
n
,
"
Cl
a
ss
ifi
c
a
ti
o
n
fo
r
G
lu
c
o
se
a
n
d
L
a
c
to
se
Tera
h
e
rtz
S
p
e
c
tru
m
s
Ba
se
d
o
n
S
VM
a
n
d
DN
N
M
e
th
o
d
s,
"
i
n
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
T
e
ra
h
e
rtz
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l.
1
0
,
n
o
.
6
,
p
p
.
6
1
7
-
6
2
3
,
No
v
.
2
0
2
0
,
d
o
i:
1
0
.
1
1
0
9
/
TT
HZ.
2
0
2
0
.
3
0
1
3
8
1
9
.
[2
8
]
D
.
W
u
,
Z
.
J
i
a
n
g
,
X
.
X
i
e
,
X
.
W
e
i
,
W
.
Y
u
a
n
d
R
.
L
i
,
"
L
S
T
M
L
e
a
r
n
i
n
g
w
i
t
h
B
a
y
e
s
i
a
n
a
n
d
G
a
u
s
s
i
a
n
P
r
o
c
e
s
s
i
n
g
f
o
r
A
n
o
m
a
l
y
D
e
t
e
c
t
i
o
n
i
n
I
n
d
u
s
t
r
i
a
l
I
o
T
,
"
i
n
I
E
E
E
T
r
a
n
s
a
c
t
i
o
n
s
o
n
I
n
d
u
s
t
r
i
a
l
I
n
f
o
r
m
a
t
i
c
s
,
v
o
l
.
1
6
,
n
o
.
8
,
p
p
.
5
2
4
4
-
5
2
5
3
,
A
u
g
.
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
T
I
I
.
2
0
1
9
.
2
9
5
2
9
1
7
.
[2
9
]
N.
Ja
wa
d
,
M
.
S
a
li
h
a
n
d
J.
Co
sm
a
s,
"
M
e
d
ia
Ca
stin
g
a
s
a
S
e
rv
ice
:
In
d
u
str
ies
Co
n
v
e
r
g
e
n
c
e
Op
p
o
r
tu
n
i
ty
a
n
d
Ca
c
h
in
g
S
e
rv
ice
fo
r
5
G
In
d
o
o
r
g
NB,
"
i
n
IEE
E
T
r
a
n
sa
c
ti
o
n
s
o
n
Bro
a
d
c
a
stin
g
,
v
o
l.
6
6
,
n
o
.
2
,
p
p
.
5
7
9
-
5
8
8
,
Ju
n
e
2
0
2
0
,
d
o
i:
1
0
.
1
1
0
9
/T
BC.
2
0
2
0
.
2
9
7
7
5
5
2
.
[3
0
]
A.
K.
Ns
a
if
e
t
a
l
.
,
"
F
RCNN
-
G
N
B:
Ca
sc
a
d
e
F
a
ste
r
R
-
CNN
w
it
h
G
a
b
o
r
F
il
ters
a
n
d
Na
ïv
e
Ba
y
e
s
f
o
r
E
n
h
a
n
c
e
d
Ey
e
De
tec
ti
o
n
,
"
i
n
IE
EE
Ac
c
e
ss
,
v
o
l
.
9
,
p
p
.
1
5
7
0
8
-
1
5
7
1
9
,
2
0
2
1
,
d
o
i:
1
0
.
1
1
0
9
/ACCE
S
S
.
2
0
2
1
.
3
0
5
2
8
5
1
.
[3
1
]
S.
S
a
d
o
ws
k
i,
P
.
S
p
a
c
h
o
s,
a
n
d
K
.
N.
P
lata
n
i
o
ti
s,
“
M
e
m
o
ry
les
s
T
e
c
h
n
iq
u
e
s
a
n
d
W
irele
ss
Tec
h
n
o
l
o
g
ies
f
o
r
In
d
o
o
r
Lo
c
a
li
z
a
ti
o
n
with
th
e
I
n
tern
e
t
o
f
Th
in
g
s
,”
IEE
E
In
ter
n
e
t
o
f
T
h
in
g
s
J
o
u
rn
a
l
,
v
o
l.
7
,
n
o
.
1
1
,
p
p
.
1
0
9
9
6
-
1
1
0
0
5
,
2
0
2
0
,
d
o
i:
1
0
.
1
1
0
9
/JIOT.
2
0
2
0
.
2
9
9
2
6
5
1
.
[3
2
]
P
.
Va
rz
a
k
a
s,
"
Ch
a
n
n
e
l
Ca
p
a
c
it
y
p
e
r
u
se
r
in
a
P
o
we
r
a
n
d
Ra
te
Ad
a
p
ti
v
e
Hy
b
ri
d
DS/
F
F
H
-
CDMA
Ce
ll
u
lar
S
y
ste
m
o
v
e
r
Ra
y
lei
g
h
F
a
d
in
g
Ch
a
n
n
e
ls,
"
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
C
o
m
mu
n
ica
t
io
n
S
y
ste
ms
,
v
o
l.
2
5
,
n
o
.
7
,
p
p
.
9
4
3
-
9
5
2
,
2
0
1
2
,
d
o
i:
1
0
.
1
0
0
2
/
d
a
c
.
1
2
9
8
.
Evaluation Warning : The document was created with Spire.PDF for Python.