I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
p
u
t
er
Science
Vo
l.
21
,
No
.
1
,
J
an
u
ar
y
2
0
2
1
,
p
p
.
5
1
6
~5
2
3
I
SS
N:
2
5
02
-
4
7
5
2
,
DOI
:
1
0
.
1
1
5
9
1
/i
j
ee
cs.v
2
1
.i
1
.
pp
5
1
6
-
523
516
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs.ia
esco
r
e.
co
m
Da
ta
m
ining
appr
o
a
ch t
o
ana
ly
z
ing
int
rusio
n
dete
cti
o
n of
w
ireless
senso
r ne
tw
o
rk
M
d Ala
ud
din
Rez
v
i
,
Sid
ra
t
u
l M
o
o
nta
ha
,
K
ha
dija
Ak
t
er
T
ris
ha
,
Sh
a
m
s
e
T
a
s
ni
m
Cy
n
t
hia
,
Sh
a
m
i
m
R
ipo
n
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
W
e
st Un
iv
e
rsit
y
,
Dh
a
k
a
,
Ba
n
g
lad
e
sh
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Ma
y
5
,
2
0
20
R
ev
i
s
ed
J
u
l 4
,
2
0
20
A
cc
ep
ted
J
ul
1
8
,
2
0
20
W
irele
ss
se
n
so
r
n
e
tw
o
rk
(
W
S
N
)
is
a
c
o
ll
e
c
ti
o
n
o
f
w
irel
e
ss
s
e
n
so
r
n
o
d
e
s
w
h
ich
a
re
d
istri
b
u
ted
in
n
a
t
u
re
a
n
d
a
b
a
se
sta
ti
o
n
w
h
e
re
th
e
d
isp
e
rse
d
n
o
d
e
s
a
re
u
se
d
to
m
o
n
it
o
r
a
n
d
t
h
e
p
h
y
sic
a
l
c
o
n
d
it
i
o
n
s
o
f
th
e
e
n
v
iro
n
m
e
n
t
is
re
c
o
rd
e
d
a
n
d
th
e
n
t
h
e
se
d
a
ta
a
re
o
rg
a
n
ize
d
in
t
o
t
h
e
b
a
se
.
Its
a
p
p
li
c
a
ti
o
n
h
a
s
b
e
e
n
re
a
c
h
e
d
o
u
t
f
ro
m
c
rit
ica
l
m
il
it
a
r
y
a
p
p
li
c
a
ti
o
n
su
c
h
a
s
b
a
tt
lef
ield
su
rv
e
il
lan
c
e
to
tra
f
f
i
c
,
h
e
a
lt
h
,
in
d
u
strial
a
re
a
s,
in
tru
d
e
r
d
e
tec
ti
o
n
,
se
c
u
rit
y
a
n
d
su
rv
e
il
lan
c
e
.
Du
e
to
v
a
rio
u
s fea
tu
re
s in
W
S
N i
t
is
v
e
r
y
p
ro
n
e
to
v
a
r
io
u
s ty
p
e
s
e
x
tern
a
l
a
tt
a
c
k
s.
P
re
v
e
n
ti
n
g
su
c
h
a
tt
a
c
k
s,
in
tru
sio
n
d
e
tec
ti
o
n
sy
ste
m
(IDS)
is
v
e
r
y
i
m
p
o
rtan
t
so
th
a
t
a
tt
a
c
k
e
r
c
a
n
n
o
t
ste
a
l
o
r
m
a
n
ip
u
late
d
a
ta.
Da
ta
m
in
in
g
is
a
tec
h
n
iq
u
e
th
a
t
c
a
n
h
e
lp
t
o
d
i
sc
o
v
e
r
p
a
tt
e
rn
s
in
larg
e
d
a
tas
e
t.
T
h
is
p
a
p
e
r
pr
o
p
o
se
d
a
d
a
ta
m
in
in
g
tec
h
n
i
q
u
e
f
o
r
d
if
f
e
r
e
n
t
ty
p
e
s
o
f
c
la
ss
if
ic
a
ti
o
n
a
lg
o
rit
h
m
s
to
d
e
tec
t
d
e
n
ial
o
f
se
rv
ice
(Do
S
)
a
tt
a
c
k
s
w
h
ich
is
o
f
f
o
u
r
ty
p
e
s
.
T
h
e
y
a
re
G
ra
y
h
o
le,
Blac
k
h
o
le,
F
lo
o
d
i
n
g
a
n
d
T
DMA
.
A
n
u
m
b
e
r
o
f
d
a
ta
m
in
in
g
tec
h
n
iq
u
e
s,
su
c
h
a
s
KN
N,
Na
ïv
e
Ba
y
e
s,
L
o
g
isti
c
Re
g
r
e
ss
io
n
,
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
(S
V
M
)
a
n
d
A
NN
a
lg
o
rit
h
m
s
a
re
a
p
p
li
e
d
o
n
th
e
d
a
tas
e
t
a
n
d
a
n
a
ly
z
e
th
e
ir
p
e
r
f
o
rm
a
n
c
e
in
d
e
tec
ti
n
g
th
e
a
tt
a
c
k
s.
T
h
e
a
n
a
l
y
sis
r
e
v
e
a
ls
th
e
a
p
p
li
c
a
b
il
i
ty
o
f
th
e
se
a
lg
o
rit
h
m
s
fo
r
d
e
tec
ti
n
g
a
n
d
p
re
d
icti
n
g
su
c
h
a
tt
a
c
k
s an
d
c
a
n
b
e
re
c
o
m
m
e
n
d
e
d
f
o
r
n
e
tw
o
rk
sp
e
c
ialist
a
n
d
a
n
a
ly
sts
.
K
ey
w
o
r
d
s
:
C
las
s
i
m
b
ala
n
ce
Do
S a
ttack
I
n
tr
u
s
io
n
d
etec
tio
n
s
y
s
te
m
(
I
DS)
W
ir
eless
s
en
s
o
r
n
et
w
o
r
k
(
W
SN)
T
h
is
is
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
:
Sh
a
m
i
m
R
ip
o
n
Dep
ar
t
m
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
an
d
E
n
g
i
n
ee
r
in
g
E
ast W
est Un
i
v
er
s
i
t
y
A
/2
J
ah
u
r
u
l I
s
la
m
C
it
y
,
D
h
a
k
a
,
B
an
g
lad
esh
E
m
ail: d
s
h
r
@
e
w
u
b
d
.
ed
u
1.
I
NT
RO
D
UCT
I
O
N
No
w
ad
a
y
s
w
ir
eless
s
e
n
s
o
r
s
n
et
w
o
r
k
(
W
SN)
[
1
]
is
a
s
tan
d
o
u
t
a
m
o
n
g
s
t
th
e
m
o
s
t
r
is
in
g
an
d
q
u
ick
l
y
d
ev
elo
p
in
g
f
ield
s
i
n
th
e
w
o
r
ld
[
2
-
3
]
.
A
t
f
ir
s
t,
it
w
as
d
esi
g
n
e
d
to
ac
ce
ler
ate
an
d
f
ac
ilit
ate
m
ilit
ar
y
o
p
er
atio
n
s
b
u
t
later
its
ap
p
licatio
n
h
as
b
ee
n
e
x
te
n
d
ed
to
h
ea
l
th
,
tr
af
f
i
c,
in
d
u
s
tr
ial
ar
ea
s
a
n
d
t
h
r
ea
t
d
etec
tio
n
[
4
]
.
W
SN
co
n
s
is
ts
o
f
s
p
ec
ialized
tr
a
n
s
d
u
ce
r
s
w
i
th
a
co
m
m
u
n
icat
io
n
s
in
f
r
astr
u
ctu
r
e
w
h
ic
h
u
s
e
s
r
a
d
io
to
o
b
s
er
v
e
an
d
r
ec
o
r
d
p
h
y
s
ical
o
r
en
v
ir
o
n
m
e
n
tal
co
n
d
itio
n
s
[
5
]
.
I
t
is
b
u
ilt
o
f
lo
ca
l
s
ca
tt
er
ed
s
en
s
o
r
s
w
i
th
li
m
ited
s
en
s
in
g
ca
p
ab
ilit
y
an
d
tr
an
s
m
is
s
io
n
r
a
te
w
h
ic
h
is
d
ep
lo
y
ed
in
m
o
n
it
o
r
in
g
r
eg
io
n
t
h
r
o
u
g
h
w
ir
ele
s
s
co
m
m
u
n
icatio
n
[
6
]
.
T
h
e
s
en
s
o
r
s
ar
e
r
esp
o
n
s
ib
le
f
o
r
e
x
ch
a
n
g
in
g
th
e
en
v
ir
o
n
m
en
t
i
n
f
o
r
m
atio
n
to
co
n
s
tr
u
ct
a
m
o
d
el
o
f
t
h
e
m
o
n
ito
r
ed
r
eg
io
n
[
7
]
.
T
o
tr
an
s
f
er
d
ata
o
v
er
th
e
n
e
t
w
o
r
k
,
e
ac
h
s
e
n
s
o
r
n
o
d
e
co
n
s
u
m
es
s
o
m
e
e
n
er
g
y
.
So
,
t
h
e
lif
eti
m
e
o
f
t
h
e
n
et
w
o
r
k
d
ep
en
d
s
o
n
h
o
w
m
u
c
h
en
er
g
y
s
p
en
t
o
n
ea
ch
tr
an
s
m
is
s
io
n
.
I
n
o
r
d
er
to
ex
ten
d
th
e
li
f
e
ti
m
e
o
f
W
S
N,
r
o
u
ti
n
g
p
r
o
to
co
ls
ar
e
d
es
ig
n
ed
f
o
r
r
ed
u
ci
n
g
e
n
e
r
g
y
co
n
s
u
m
p
tio
n
o
f
s
en
s
o
r
s
.
So
m
e
o
f
th
e
w
ell
-
k
n
o
w
n
r
o
u
ti
n
g
p
r
o
to
co
ls
ar
e
L
E
AC
H,
P
E
GASI
S,
T
E
E
N,
A
PT
E
E
N
an
d
HE
E
D
[
8
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
Da
ta
min
in
g
a
p
p
r
o
a
c
h
to
a
n
a
l
yzin
g
in
tr
u
s
io
n
d
etec
tio
n
o
f wi
r
eless
s
en
s
o
r
n
etw
o
r
k
(
Md
A
la
u
d
d
in
R
ezvi
)
517
T
h
e
d
ataset
w
e
u
s
e
i
n
t
h
i
s
p
ap
er
w
as b
u
ilt
u
s
in
g
L
E
A
C
H
p
r
o
to
co
l [
9
]
.
L
E
A
C
H
is
a
p
r
o
to
co
l
w
h
ic
h
is
clu
s
ter
i
n
g
,
ad
ap
tiv
e,
a
n
d
s
el
f
-
o
r
g
an
izi
n
g
[
1
0
]
.
L
E
A
C
H
p
r
o
to
co
l
is
ai
m
ed
to
estab
li
s
h
clu
s
ter
s
o
f
n
o
d
es
f
o
r
d
is
tr
ib
u
ti
n
g
t
h
e
en
er
g
y
i
n
all
o
f
th
e
n
e
t
w
o
r
k
n
o
d
es
[
1
1
]
.
T
h
er
e
is
a
C
lu
s
ter
Hea
d
(
C
H)
n
o
d
e
in
ea
ch
p
r
o
to
co
l
w
h
ic
h
is
r
e
s
p
o
n
s
ib
le
f
o
r
g
at
h
e
r
in
g
d
ata
f
r
o
m
i
ts
cl
u
s
ter
m
e
m
b
er
n
o
d
es
a
n
d
f
o
r
w
ar
d
th
e
m
to
th
e
B
ase
Sta
tio
n
(
B
S)
o
r
Sin
k
.
T
h
e
lo
ca
tio
n
o
f
B
S
is
f
ar
a
w
a
y
f
r
o
m
t
h
e
s
e
n
s
o
r
n
o
d
es.
T
h
e
L
E
AC
H
p
r
o
to
co
l
ai
m
s
f
o
r
th
e
r
ed
u
ctio
n
o
f
t
h
e
co
n
s
u
m
p
tio
n
o
f
en
er
g
y
t
h
at
is
n
ec
es
s
ar
y
t
o
m
a
in
ta
in
cl
u
s
ter
s
to
p
r
o
lo
n
g
th
e
l
if
et
i
m
e
o
f
a
W
SN
[
8
]
.
T
h
e
lim
itatio
n
o
f
c
o
m
p
u
tatio
n
p
o
w
er
,
m
e
m
o
r
y
a
n
d
b
atter
y
li
f
eti
m
e
o
f
s
e
n
s
o
r
n
o
d
es
also
in
cr
ea
s
es
th
e
in
s
ec
u
r
it
y
o
f
W
SN.
T
h
e
ai
m
o
f
m
o
s
t
o
f
th
e
attac
k
s
in
W
SN
is
eith
er
li
m
iti
n
g
o
r
el
i
m
i
n
ati
n
g
n
et
w
o
r
k
ab
ilit
y
f
o
r
p
er
f
o
r
m
i
n
g
it
s
e
x
p
e
cted
w
o
r
k
p
r
o
ce
d
u
r
es
[
1
2
]
.
On
e
o
f
t
h
o
s
e
a
ttac
k
s
is
Do
S
a
tta
ck
[
1
3
]
.
T
h
is
attac
k
is
p
er
f
o
r
m
ed
b
y
h
ar
d
w
ar
e
f
a
i
lu
r
e,
b
u
g
,
r
eso
u
r
ce
e
x
h
a
u
s
tio
n
,
m
a
licio
u
s
b
r
o
ad
ca
s
tin
g
o
f
h
ig
h
e
n
er
g
y
s
ig
n
al
s
an
d
m
i
n
i
m
ize
t
h
e
p
er
f
o
r
m
an
ce
o
f
th
e
n
e
t
w
o
r
k
.
Ma
n
y
p
iece
s
o
f
r
esear
ch
[
1
4
]
s
h
o
w
t
h
at
m
a
n
y
ex
is
ti
n
g
p
r
ev
en
tio
n
m
e
c
h
a
n
is
m
s
ar
e
n
o
t
s
u
f
f
icien
t
to
s
ec
u
r
e
t
h
e
d
ata
p
ac
k
et
s
o
f
th
e
n
et
w
o
r
k
a
n
d
m
ai
n
tai
n
t
h
e
s
er
v
ice
o
f
W
SN
[
1
5
]
.
T
h
ey
al
s
o
ca
n
n
o
t
p
r
ev
e
n
t
th
e
n
et
w
o
r
k
f
r
o
m
all
t
h
e
attac
k
s
ex
p
er
ien
ce
d
b
y
t
h
e
m
.
Fo
r
th
i
s
r
ea
s
o
n
,
th
e
d
etec
tio
n
b
ased
t
ec
h
n
iq
u
e
co
m
b
in
ed
w
it
h
a
p
r
ev
en
t
io
n
b
ased
tec
h
n
iq
u
e
w
ill
b
e
m
o
r
e
e
f
f
icie
n
t
[
1
6
]
.
So
,
in
tr
u
s
io
n
d
etec
tio
n
s
y
s
te
m
is
v
ita
l
f
o
r
m
o
n
ito
r
i
n
g
s
u
s
p
icio
u
s
ac
ti
v
it
y
i
n
n
et
w
o
r
k
tr
a
f
f
ic
a
n
d
is
s
u
es
aler
t
if
s
u
ch
ac
ti
v
it
y
is
d
etec
ted
.
T
h
r
o
u
g
h
in
tr
u
s
io
n
d
etec
tio
n
s
y
s
te
m
w
e
ca
n
d
etec
t
an
attac
k
ea
r
l
y
an
d
s
av
e
t
h
e
n
et
w
o
r
k
f
r
o
m
v
ar
io
u
s
m
a
licio
u
s
attac
k
s
.
T
h
e
au
th
o
r
in
[
1
3
]
d
e
m
o
n
s
tr
ates a
p
r
o
ce
s
s
f
o
r
d
etec
tin
g
f
o
u
r
t
y
p
es o
f
Do
S a
ttac
k
s
i
n
W
SN.
T
h
ey
h
a
v
e
ap
p
lied
r
an
d
o
m
f
o
r
est
cla
s
s
i
f
ier
to
d
et
ec
t
attac
k
s
o
n
a
d
ataset
a
n
d
h
a
v
e
ac
h
ie
v
ed
t
h
e
b
est
p
er
f
o
r
m
a
n
ce
f
o
r
B
lack
h
o
le,
Flo
o
d
in
g
,
Gr
a
y
h
o
le,
Sch
ed
u
l
i
n
g
(
T
DM
A
)
attac
k
s
an
d
No
r
m
al
b
eh
a
v
io
r
.
M.
A
h
s
a
n
L
ati
f
an
d
M.
A
d
n
a
n
in
[
1
7
]
h
av
e
d
ev
elo
p
ed
th
r
ee
d
if
f
er
en
t
A
N
N
-
b
a
s
ed
m
o
d
el
s
o
th
at
t
h
e
b
eh
a
v
io
r
o
f
t
h
e
n
et
w
o
r
k
tr
a
f
f
ic
ca
n
b
e
d
is
co
v
er
ed
.
T
h
e
y
h
av
e
p
r
o
p
o
s
ed
a
m
o
d
el
t
h
at
en
j
o
y
i
n
g
an
i
n
telli
g
e
n
t
ag
e
n
t
f
o
r
m
o
n
ito
r
i
n
g
th
e
tr
af
f
ic
p
atter
n
at
th
e
lev
e
l o
f
t
h
e
b
ase
s
tatio
n
.
T
h
e
d
ataset
u
s
ed
i
n
t
h
is
p
ap
er
co
n
tain
s
f
o
u
r
t
y
p
e
s
o
f
Do
S
[
1
8
]
attac
k
: G
r
a
y
h
o
le,
B
lack
h
o
l
e,
Flo
o
d
in
g
an
d
T
DM
A
[
1
9
-
2
0
]
.
B
y
ap
p
ly
in
g
s
u
itab
le
d
ata
m
i
n
i
n
g
t
ec
h
n
iq
u
es,
it
is
p
o
s
s
ib
le
to
ac
tiv
el
y
d
etec
t
in
tr
u
s
io
n
i
n
n
et
w
o
r
k
b
ec
au
s
e
it
h
elp
s
to
d
i
s
co
v
er
p
atter
n
s
i
n
lar
g
e
d
atase
ts
[
2
1
]
.
T
h
en
d
i
f
f
er
e
n
t
al
g
o
r
it
h
m
s
h
e
lp
to
cla
s
s
i
f
y
an
d
p
r
ed
ict
in
tr
u
s
io
n
.
B
y
u
s
i
n
g
d
ata
m
i
n
i
n
g
,
w
e
h
a
v
e
d
is
co
v
er
ed
p
atter
n
s
o
f
attac
k
s
a
n
d
also
ca
n
p
r
ed
ict
w
h
et
h
er
it
is
an
attac
k
o
r
n
o
t
w
h
e
n
a
n
e
w
r
eq
u
es
t
ar
r
iv
e
s
.
A
f
ter
ap
p
l
y
i
n
g
v
ar
io
u
s
m
i
n
i
n
g
al
g
o
r
ith
m
s
,
it
i
s
p
o
s
s
ib
le
to
an
al
y
ze
t
h
e
p
er
f
o
r
m
an
ce
o
f
i
n
tr
u
s
io
n
d
etec
tio
n
as
w
ell
as
co
m
p
ar
e
v
ar
io
u
s
te
ch
n
iq
u
es
w
i
th
ea
c
h
o
th
er
to
id
en
tify
t
h
e
b
est alg
o
r
ith
m
f
o
r
in
tr
u
s
io
n
d
etec
tio
n
.
I
n
[
2
2
]
th
e
au
th
o
r
h
as
p
r
ese
n
t
ed
s
o
m
e
Do
S
attac
k
a
n
d
h
av
e
s
u
g
g
e
s
ted
s
o
m
e
s
o
l
u
tio
n
f
o
r
d
etec
tin
g
an
d
s
o
lv
i
n
g
ce
r
tain
a
ttack
.
T
h
e
y
h
a
v
e
ca
te
g
o
r
ized
s
o
m
e
Do
S
attac
k
s
ac
co
r
d
in
g
to
p
r
o
to
co
l
s
tack
la
y
er
s
a
n
d
h
av
e
d
escr
ib
ed
s
i
n
k
h
o
le,
He
llo
f
lo
o
d
in
g
,
w
o
r
m
h
o
le,
s
ele
ctiv
e
f
o
r
w
ar
d
i
n
g
a
ttack
f
o
r
n
et
w
o
r
k
la
y
er
an
d
f
lo
o
d
in
g
attac
k
f
o
r
th
e
tr
an
s
p
o
r
t
lay
er
.
L
u
i
g
i
C
o
p
p
o
lin
o
et
al.
[
2
1
]
h
as
p
r
o
p
o
s
ed
a
h
y
b
r
id
in
tr
u
s
io
n
d
etec
tio
n
s
y
s
te
m
f
o
r
W
SN
t
h
at
u
s
es
f
o
r
m
is
u
s
e
an
d
an
o
m
al
y
-
b
a
s
ed
d
ete
ctio
n
tec
h
n
iq
u
es.
T
h
e
y
h
av
e
u
s
ed
d
ec
is
io
n
tr
ee
as c
lass
i
f
icat
io
n
al
g
o
r
ith
m
f
o
r
th
e
d
etec
tio
n
p
r
o
ce
s
s
.
T
h
e
r
est
o
f
th
e
p
ap
er
is
o
r
g
an
ized
as
f
o
llo
w
s
.
Sectio
n
2
o
u
tlin
es
t
h
e
p
r
o
p
o
s
ed
m
et
h
o
d
ap
p
li
ed
in
th
is
.
Sectio
n
3
d
escr
ib
es a
n
o
v
er
v
ie
w
o
f
t
h
e
d
ataset
th
at
is
u
s
ed
i
n
th
e
e
x
p
er
i
m
e
n
t.
Sect
io
n
4
p
r
o
v
id
es i
m
p
le
m
en
ted
p
ar
t
o
f
o
u
r
w
o
r
k
.
Sec
tio
n
5
p
r
esen
ts
r
esu
lts
a
n
d
a
n
al
y
s
i
s
.
Sectio
n
6
d
e
m
o
n
s
tr
ates
h
o
w
cla
s
s
i
m
b
ala
n
ce
p
r
o
b
lem
ca
n
b
e
h
a
n
d
led
f
o
r
i
m
b
alan
ce
d
ataset.
Fi
n
all
y
,
Sectio
n
7
d
r
a
w
s
a
co
n
cl
u
s
io
n
o
f
th
e
p
ap
e
r
to
s
u
m
m
ar
ize
th
e
w
o
r
k
a
n
d
to
o
u
tlin
e
o
u
r
f
u
t
u
r
e
p
lan
.
2.
P
RO
P
O
SE
D
M
E
T
H
O
D
Af
ter
co
llectin
g
t
h
e
d
ataset,
we
p
er
f
o
r
m
ed
p
r
ep
r
o
ce
s
s
in
g
f
o
r
th
e
co
n
v
e
n
ie
n
ce
o
f
o
u
r
ex
p
er
i
m
e
n
t.
A
t
f
ir
s
t,
th
e
attac
k
n
a
m
es
ar
e
co
n
v
er
ted
in
to
n
u
m
er
ic
v
al
u
es.
T
h
e
v
alu
es
0
,
1
,
2
,
3
,
4
ar
e
u
s
ed
f
o
r
n
o
r
m
al(
n
o
n
-
attac
k
)
,
B
lack
h
o
le
attac
k
,
Gr
ay
h
o
le
at
tack
,
F
lo
o
d
in
g
a
n
d
T
DM
A
attac
k
r
esp
ec
tiv
e
l
y
.
A
b
in
ar
y
cla
s
s
i
f
icatio
n
h
as a
l
s
o
b
ee
n
p
er
f
o
r
m
ed
as a
tt
ac
k
s
a
n
d
n
o
n
-
attac
k
(
n
o
r
m
al)
t
y
p
e
a
n
d
ass
i
g
n
s
1
an
d
0
r
esp
ec
tiv
el
y
.
Af
ter
p
r
o
ce
s
s
i
n
g
th
e
d
ata
s
et,
it
h
as
b
ee
n
d
iv
id
ed
in
to
6
0
%
an
d
4
0
%
as
tr
ai
n
in
g
a
n
d
tes
tin
g
d
ata
ap
p
l
y
i
n
g
1
0
-
f
o
ld
cr
o
s
s
-
v
alid
a
tio
n
.
T
h
en
w
e
h
a
v
e
c
h
o
s
en
s
o
m
e
clas
s
i
f
icatio
n
alg
o
r
it
h
m
s
w
h
ic
h
ar
e
m
o
s
tl
y
u
s
ed
i
n
v
ar
io
u
s
l
iter
atu
r
e
a
n
d
ap
p
ly
t
h
e
m
o
n
th
e
d
ata
s
et
to
d
etec
t in
tr
u
s
io
n
b
o
th
f
o
r
t
y
p
e
o
f
ea
ch
attac
k
a
n
d
f
o
r
b
in
ar
y
clas
s
if
icatio
n
.
I
n
t
h
is
p
ap
er
,
w
e
h
a
v
e
ap
p
lied
KNN,
Naïv
e
B
ay
e
s
,
Su
p
p
o
r
t
Vec
to
r
Ma
ch
in
e
(
SVM)
,
an
d
L
o
g
is
t
ic
r
eg
r
es
s
io
n
al
g
o
r
it
h
m
to
s
ee
w
h
ic
h
al
g
o
r
ith
m
ca
n
d
etec
t
i
n
tr
u
s
io
n
m
o
r
e
ac
cu
r
a
tel
y
.
A
NN
h
a
s
also
b
ee
n
ap
p
lied
to
p
r
esen
t
a
co
m
p
ar
ativ
e
an
al
y
s
is
w
i
th
t
h
e
d
ata
s
o
u
r
ce
in
[
4
]
.
Var
io
u
s
s
tan
d
ar
d
m
etr
ic
s
ar
e
u
s
ed
to
m
ea
s
u
r
e
th
e
o
b
tain
ed
r
es
u
l
t.
T
h
e
ex
p
er
i
m
en
tal
r
e
s
u
l
t
an
a
l
y
s
i
s
ca
n
r
e
v
ea
l
i
m
p
o
r
tan
t
i
n
f
o
r
m
at
io
n
r
eg
ar
d
in
g
th
e
t
y
p
e
s
o
f
al
g
o
r
ith
m
s
a
n
d
th
eir
s
u
itab
ilit
y
f
o
r
d
etec
tin
g
v
ar
io
u
s
t
y
p
e
s
o
f
attac
k
s
.
T
h
e
p
r
o
p
o
s
ed
f
r
a
m
e
w
o
r
k
is
illu
s
tr
ated
in
Fi
g
u
r
e
1
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
21
,
No
.
1
,
J
an
u
ar
y
2
0
2
1
:
5
1
6
-
523
518
Fig
u
r
e
1
.
P
r
o
p
o
s
ed
m
et
h
o
d
3.
DATAS
E
T
O
VE
RV
I
E
W
T
h
e
d
ataset
th
at
h
as
b
ee
n
co
l
lecte
d
f
r
o
m
th
e
w
o
r
k
i
n
[
4
]
.
I
t
is
ca
lled
W
SN
-
DS
[
9
]
.
T
o
d
ev
elo
p
a
s
p
ec
ialized
d
ataset
f
o
r
t
h
e
W
SN
in
tr
u
s
io
n
d
etec
tio
n
s
y
s
te
m
th
e
a
u
th
o
r
h
as
u
s
ed
L
E
A
C
H
p
r
o
to
co
l.
T
h
is
I
DS
d
ataset
is
co
n
s
i
s
ten
t
w
ith
t
h
e
ch
ar
ac
ter
is
tic
s
o
f
W
SN
an
d
is
am
e
n
ab
le
f
o
r
d
etec
tio
n
an
d
class
i
f
icatio
n
o
f
f
o
u
r
t
y
p
es
o
f
Do
S
attac
k
s
.
T
h
e
d
ataset
co
n
tai
n
s
3
7
4
6
6
1
in
s
tan
ce
s
an
d
2
3
attr
ib
u
tes.
Am
o
n
g
t
h
ese
2
3
attr
ib
u
tes
R
SS
I
,
Ma
x
d
is
ta
n
ce
to
C
H,
Av
er
ag
e
d
is
ta
n
ce
to
C
H,
C
u
r
r
e
n
t
en
er
g
y
ar
e
n
o
t
u
s
ed
f
o
r
d
etec
tin
g
Do
S
attac
k
s
.
T
ab
le
1
s
h
o
w
s
t
h
e
attr
ib
u
tes a
n
d
th
eir
t
y
p
e
s
.
T
ab
le
1
.
Data
ty
p
e
o
f
d
at
aset a
ttrib
u
te
A
t
t
r
i
b
u
t
e
n
a
me
D
a
t
a
t
y
p
e
I
d
,
t
i
me
,
I
s_
C
H
,
w
h
o
_
C
H
,
A
D
V
_
S
,
A
D
V
_
R
,
JO
I
N
_
S
,
JO
I
N
_
R
,
S
C
H
_
S
,
S
C
H
_
R
,
R
a
n
k
,
D
A
TA
_
S
,
D
A
TA
_
R
,
D
a
t
a
_
S
e
n
t
_
T
o
_
B
S
,
S
e
n
d
_
c
o
d
e
I
n
t
e
g
e
r
D
i
st
_
T
o
_
C
H
,
D
i
st
_
C
H
_
T
o
_
B
S
,
C
o
n
s
u
me
d
e
n
e
r
g
y
F
l
o
a
t
A
t
t
a
c
k
t
y
p
e
P
o
l
y
n
o
mi
a
l
T
h
e
attac
k
s
t
h
at
t
h
i
s
d
atase
t
co
n
tai
n
s
ar
e,
Gr
a
y
h
o
le,
B
lack
h
o
le,
Flo
o
d
in
g
a
n
d
T
DM
A
.
T
h
e
d
is
tr
ib
u
tio
n
o
f
t
h
ese
attac
k
s
a
n
d
th
e
n
o
n
-
attac
k
s
(
n
o
r
m
al)
ar
e
s
h
o
w
n
in
Fi
g
u
r
e
2
.
W
e
h
av
e
co
m
p
ar
ed
ea
ch
attr
ib
u
te
o
f
t
h
e
d
ataset
w
it
h
at
tack
attr
ib
u
te
to
id
e
n
ti
f
y
w
h
ic
h
attr
ib
u
te
i
s
r
esp
o
n
s
ib
le
f
o
r
d
etec
tin
g
w
h
ich
t
y
p
e
o
f
attac
k
.
T
h
e
r
esu
lt i
s
ill
u
s
tr
at
ed
in
T
ab
le
2
.
Fig
u
r
e
2
.
A
ttac
k
s
tat
is
tic
s
in
d
ataset
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
Da
ta
min
in
g
a
p
p
r
o
a
c
h
to
a
n
a
l
yzin
g
in
tr
u
s
io
n
d
etec
tio
n
o
f wi
r
eless
s
en
s
o
r
n
etw
o
r
k
(
Md
A
la
u
d
d
in
R
ezvi
)
519
T
ab
le
2.
Su
m
m
ar
y
o
f
attr
ib
u
te
s
o
f
v
ar
io
u
s
attac
k
s
A
t
t
a
c
k
n
a
me
A
t
t
r
i
b
u
t
e
n
a
me
G
r
a
y
h
o
l
e
T
i
me
,
I
s_
C
H
,
w
h
o
_
C
H
,
a
d
v
_
r
,
j
o
i
n
_
r
,
D
a
t
a
_
R
d
a
t
a
_
se
n
t
_
t
o
_
b
s
B
l
a
c
k
h
o
l
e
T
i
me
,
I
s_
C
H
,
w
h
o
_
C
H
,
a
d
v
_
r
,
j
o
i
n
_
r
,
D
a
t
a
_
R
,
d
a
t
a
_
se
n
t
_
t
o
_
b
s
F
l
o
o
d
i
n
g
I
s_
C
H
,
w
h
o
_
C
H
,
c
o
n
s
u
me
d
_
e
n
e
r
g
y
,
a
d
v
_
s
,
a
d
v
_
r
,
d
a
t
a
_
se
n
t
_
t
o
_
b
s
,
D
i
st
_
C
H
_
t
o
_
B
S
T
D
M
A
T
i
me
,
I
s_
C
H
,
j
o
i
n
_
r
,
sc
h
_
s,
d
a
t
a
_
se
n
t
_
t
o
_
b
s
4.
I
M
P
L
E
M
E
NT
AT
I
O
N
T
h
e
m
ac
h
i
n
e
t
h
at
h
as
b
ee
n
u
s
ed
f
o
r
th
i
s
w
o
r
k
is
a
C
o
r
e
i3
C
P
U
w
i
th
s
p
ee
d
2
GHz
,
an
d
J
u
p
y
te
r
No
teb
o
o
k
is
u
s
ed
a
s
a
w
o
r
k
i
n
g
en
v
ir
o
n
m
e
n
t.
T
o
p
r
ed
ict
ea
ch
t
y
p
e
o
f
attac
k
,
t
h
e
s
tr
in
g
d
ata
o
f
attac
k
t
y
p
e
attr
ib
u
tes
ar
e
co
n
v
er
ted
in
to
n
u
m
er
ic
v
al
u
e
as
m
en
tio
n
e
d
in
th
e
p
r
o
p
o
s
ed
m
et
h
o
d
an
d
ap
p
ly
v
ar
io
u
s
alg
o
r
ith
m
s
o
n
th
e
d
ataset.
I
n
t
h
is
p
ap
er
,
f
ir
s
t,
w
e
h
a
v
e
tr
ai
n
e
d
th
e
m
o
d
el
t
h
en
f
i
t
t
h
e
m
o
d
el
b
y
a
f
it()
f
u
n
ctio
n
to
p
r
ed
ict
ac
cu
r
ac
y
,
an
d
d
er
iv
e
co
n
f
u
s
io
n
m
atr
i
x
f
r
o
m
te
s
ti
n
g
d
ata.
T
a
b
le
3
r
e
p
r
esen
ts
s
o
m
e
o
f
th
e
p
ar
a
m
eter
s
th
at
h
a
v
e
b
ee
n
u
s
ed
i
n
th
e
m
i
n
in
g
al
g
o
r
it
h
m
s
.
K
-
n
ea
r
est
n
eig
h
b
o
r
:
A
s
u
p
er
v
is
ed
m
ac
h
i
n
e
lear
n
i
n
g
al
g
o
r
it
h
m
w
h
ic
h
i
s
m
o
s
tl
y
u
s
ed
f
o
r
class
i
f
icatio
n
.
KN
N
class
i
f
ies
n
e
w
ca
s
e
s
b
ased
o
n
s
i
m
ilar
it
y
m
ea
s
u
r
es.
KN
N
is
e
f
f
ec
tiv
e
f
o
r
lar
g
e
tr
ai
n
in
g
d
ata.
N
a
ïve
B
a
ye
s
:
A
s
u
p
er
v
is
ed
cl
ass
i
f
icatio
n
al
g
o
r
ith
m
th
at
i
s
p
ar
ti
cu
lar
l
y
u
s
ed
f
o
r
lar
g
e
d
a
ta.
A
Nai
v
e
B
a
y
es
class
i
f
ier
is
a
m
ac
h
in
e
lear
n
in
g
m
o
d
el
an
d
it i
s
p
r
o
b
ab
ilis
tic.
S
u
p
p
o
r
t
ve
cto
r
ma
ch
in
e:
SV
M
is
a
s
u
p
er
v
i
s
ed
lear
n
i
n
g
m
o
d
el
w
h
ich
i
s
u
s
ed
f
o
r
class
i
f
ic
atio
n
an
d
r
eg
r
es
s
io
n
an
al
y
s
is
.
Lo
g
is
tic
r
eg
r
ess
io
n
:
I
t
is
a
class
i
f
icatio
n
alg
o
r
ith
m
u
s
ed
to
p
r
ed
ict
p
r
o
b
ab
ilit
y
o
f
b
in
ar
y
v
a
lu
e
b
ased
o
n
o
n
e
o
r
m
o
r
e
i
n
d
ep
en
d
en
t
v
ar
iab
les.
T
ab
le
3
.
P
ar
am
eter
u
s
ed
in
t
h
e
alg
o
r
ith
m
s
A
l
g
o
r
i
t
h
m
P
a
r
a
me
t
e
r
a
n
d
D
e
scri
p
t
i
o
n
V
a
l
u
e
K
N
N
n
-
n
e
i
g
h
b
o
r
s
-
N
u
mb
e
r
o
f
n
e
i
g
h
b
o
r
s t
o
u
se
b
y
d
e
f
a
u
l
t
3
N
a
ï
v
e
B
a
y
e
s
A
l
p
h
a
-
I
t
i
s a
d
d
i
t
i
v
e
smo
o
t
h
i
n
g
p
a
r
a
me
t
e
r
(
0
f
o
r
n
o
smo
o
t
h
i
n
g
)
1
.
5
S
V
M
C
–
I
t
me
a
n
s p
e
n
a
l
t
y
p
a
r
a
me
t
e
r
C
o
f
t
h
e
e
r
r
o
r
t
e
r
m
1
.
0
L
o
g
i
st
i
c
R
e
g
r
e
ssi
o
n
C
–
I
n
v
e
r
se
o
f
r
e
g
u
l
a
r
i
z
a
t
i
o
n
st
r
e
n
g
t
h
a
n
d
m
u
st
b
e
a
p
o
si
t
i
v
e
f
l
o
a
t
1
.
0
4
.
1
.
Appl
y
ing
m
a
chine le
a
rn
ing
a
lg
o
rit
h
m
s
Fo
u
r
w
id
el
y
u
s
ed
alg
o
r
it
h
m
s
ar
e
ap
p
lied
in
t
h
e
ex
p
er
i
m
e
n
t.
T
h
e
clas
s
i
f
icatio
n
p
er
f
o
r
m
an
ce
s
ar
e
m
ea
s
u
r
e
b
y
ap
p
l
y
i
n
g
w
id
el
y
u
s
ed
m
etr
ics,
s
u
c
h
as,
A
cc
u
r
ac
y
,
P
r
ec
is
io
n
,
R
ec
all,
F1
Sco
r
e,
a
n
d
E
r
r
o
r
(
1
)
-
(4
)
.
(
1
)
(
2
)
(
3
)
(
4
)
KNN
m
a
k
e
s
clu
s
ter
s
to
cla
s
s
i
f
y
ea
c
h
a
n
d
ev
er
y
attac
k
in
g
a
n
d
n
o
n
-
attac
k
i
n
g
clas
s
es.
I
n
t
h
e
test
in
g
p
ar
t
o
f
t
h
e
d
ataset,
th
er
e
ar
e
4
0
7
7
B
lack
h
o
le
attac
k
s
a
m
o
n
g
w
h
ic
h
KN
N
ca
n
d
etec
t
3
7
9
4
attac
k
s
,
f
r
o
m
5
9
3
8
Gr
a
y
h
o
le
attac
k
s
it
ca
n
d
etec
t
5
1
6
9
attac
k
s
,
1
0
0
6
Flo
o
d
in
g
a
ttack
ca
n
b
e
d
etec
ted
f
r
o
m
1
3
1
0
,
an
d
f
r
o
m
2
6
5
1
T
DM
A
attac
k
2
1
4
3
is
p
r
ed
icte
d
.
Am
o
n
g
t
h
e
1
3
5
8
8
9
n
o
r
m
al
d
ata,
th
e
d
etec
ted
n
u
m
b
er
i
s
1
3
5
3
2
3
.
Naïv
e
B
a
y
e
s
ca
n
d
etec
t
o
n
l
y
1
3
9
9
B
lack
h
o
le
attac
k
s
f
r
o
m
4
0
7
7
,
f
r
o
m
5
9
3
8
Gr
a
y
h
o
le
at
t
ac
k
s
i
t
ca
n
d
etec
t
2
7
6
0
attac
k
s
,
1
0
7
5
Flo
o
d
in
g
attac
k
s
ar
e
d
etec
ted
f
r
o
m
1
3
1
0
,
f
o
r
T
DM
A
,
2
1
4
8
att
ac
k
s
ar
e
p
r
ed
icted
f
r
o
m
2
6
5
1
an
d
f
o
r
n
o
r
m
a
l d
ata,
1
0
8
6
9
0
a
r
e
d
etec
ted
f
r
o
m
1
3
5
8
8
9
.
5.
RE
SU
L
T
AND
ANA
L
YS
I
S
T
h
is
s
ec
tio
n
d
e
s
cr
ib
es
th
e
ap
p
licatio
n
o
f
v
ar
io
u
s
m
ac
h
i
n
e
le
ar
n
in
g
tec
h
n
iq
u
e
s
o
n
t
h
e
tr
ain
i
n
g
a
n
d
test
i
n
g
s
et
o
f
d
ata.
L
ea
r
n
in
g
al
g
o
r
ith
m
s
ar
e
ap
p
lied
in
t
w
o
p
h
a
s
es.
T
h
e
f
ir
s
t
p
h
a
s
e
is
a
m
u
lti
-
clas
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
21
,
No
.
1
,
J
an
u
ar
y
2
0
2
1
:
5
1
6
-
523
520
class
i
f
icatio
n
p
h
ase,
w
h
er
e
al
l
th
e
al
g
o
r
ith
m
s
ar
e
ap
p
lied
to
class
i
f
y
al
l
th
e
attac
k
s
in
th
e
d
ataset.
I
n
t
h
e
s
ec
o
n
d
p
h
ase,
b
in
ar
y
clas
s
if
ic
atio
n
is
p
er
f
o
r
m
ed
w
h
er
e
all
th
e
attac
k
s
ar
e
co
n
s
id
er
ed
o
n
e
class
(
attac
k
clas
s
)
an
d
n
o
n
-
attac
k
s
ar
e
t
h
e
o
th
er
class
(
n
o
r
m
al)
.
Su
p
p
o
r
t
v
ec
to
r
m
ac
h
i
n
e
(
SV
M)
ca
n
d
etec
t
o
n
l
y
8
7
9
attac
k
s
f
r
o
m
4
0
7
7
B
lack
h
o
le
attac
k
S
VM
,
it
ca
n
n
o
t
p
r
ed
ict
an
y
Gr
a
y
h
o
le
an
d
Flo
o
d
in
g
attac
k
,
o
n
l
y
4
1
1
T
DM
A
attac
k
s
ar
e
p
r
ed
icted
f
r
o
m
2
6
5
1
an
d
n
o
r
m
al
d
ata
is
d
etec
ted
1
3
5
8
8
3
f
r
o
m
1
3
5
8
8
9
.
L
o
g
is
tic
R
eg
r
ess
io
n
p
r
ed
icts
4
0
5
5
attac
k
s
f
r
o
m
4
0
7
7
B
lack
h
o
le
attac
k
,
f
r
o
m
5
9
3
8
Gr
ay
h
o
le
at
tack
s
it c
a
n
d
etec
t
930
attac
k
s
,
905
Flo
o
d
in
g
attac
k
s
ca
n
b
e
d
etec
ted
f
r
o
m
1
3
1
0
,
2194
T
DM
A
attac
k
s
ar
e
p
r
ed
icted
f
r
o
m
2
6
5
1
an
d
n
o
r
m
a
l
d
ata
is
d
etec
ted
135435
f
r
o
m
1
3
5
8
8
9
.
T
a
b
le
4
illu
s
tr
ates
t
h
e
co
m
p
ar
i
s
o
n
o
f
a
ll
th
e
p
r
ed
icted
attac
k
s
b
y
ea
c
h
o
f
t
h
e
al
g
o
r
ith
m
s
.
I
t
ca
n
b
e
f
o
u
n
d
t
h
at
n
o
s
i
n
g
l
e
tech
n
iq
u
e
is
a
w
i
n
n
er
h
er
e.
Ho
w
e
v
er
,
L
R
p
er
f
o
r
m
s
b
etter
i
n
m
o
s
t o
f
t
h
e
ca
s
e
s
.
T
ab
le
4
.
C
o
m
p
ar
is
o
n
o
f
v
ar
io
u
s
attac
k
p
r
ed
ictio
n
A
t
t
a
c
k
Ty
p
e
T
o
t
a
l
P
r
e
d
i
c
t
i
o
n
K
N
N
NB
S
V
M
LR
B
l
a
c
k
h
o
l
e
4
0
7
7
3
7
9
4
(
9
3
.
0
6
%)
1
3
9
9
(
3
4
.
3
1
%)
8
7
9
(
2
1
.
5
6
%)
4
0
5
5
(
9
9
.
4
6
%)
G
r
a
y
h
o
l
e
5
9
3
8
5
1
6
9
(
8
7
.
0
5
%)
2
7
6
0
(
4
6
.
4
8
%)
0
(
0
.
0
%)
9
3
0
(
1
5
.
6
6
%)
F
l
o
o
d
i
n
g
1
3
1
0
1
0
0
6
(
7
6
.
8
4
%)
1
0
7
5
(
8
2
.
0
6
%)
0
(
0
.
0
%)
9
0
5
(
6
9
.
0
8
%)
T
D
M
A
2
6
5
1
2
1
4
3
(
8
0
.
8
4
%)
2
1
4
8
(
8
1
.
0
3
%)
4
1
1
(
1
5
.
5
0
%)
2
1
9
4
(
8
2
.
7
6
%)
N
o
r
mal
1
3
5
8
8
9
1
3
5
3
2
3
(
9
9
.
5
8
%)
1
0
8
6
9
0
(
7
9
.
9
8
%)
1
3
5
8
8
3
(
1
0
0
%)
1
3
5
4
3
5
(
9
9
.
6
7
%)
5
.
1
.
Art
if
ici
a
l
neura
l net
w
o
r
k
(
ANN)
A
N
N
is
ap
p
lied
w
ith
2
h
id
d
en
la
y
er
s
an
d
ca
lc
u
lates
t
h
e
p
r
ec
is
io
n
an
d
ac
cu
r
ac
y
to
co
m
p
ar
e
t
h
e
r
esu
lt
s
w
it
h
t
h
e
p
r
ev
io
u
s
l
y
p
u
b
lis
h
ed
r
es
u
lt
[
9
]
u
s
i
n
g
1
0
-
f
o
ld
cr
o
s
s
-
v
alid
atio
n
.
T
h
e
co
m
p
ar
ativ
e
an
a
l
y
s
is
o
f
th
e
o
b
tain
ed
r
esu
lts
i
s
ill
u
s
tr
ated
in
T
ab
le
5
.
Ou
r
ex
p
er
i
m
en
t
p
r
o
d
u
ce
s
al
m
o
s
t
th
e
s
a
m
e
r
es
u
lt
as
i
n
t
h
e
o
r
ig
in
al
w
o
r
k
.
Fo
r
A
NN
w
it
h
2
h
id
d
en
la
y
er
s
w
e
g
e
t
9
8
.
5
6
%
ac
cu
r
ac
y
f
o
r
d
etec
tin
g
atta
ck
an
d
in
p
r
ev
io
u
s
w
o
r
k
,
t
h
e
au
t
h
o
r
o
f
[
6
]
f
o
u
n
d
9
8
.
5
3
% a
cc
u
r
ac
y
f
o
r
d
etec
tin
g
attac
k
.
T
ab
le
5
.
C
o
m
p
ar
is
o
n
o
f
r
esu
l
t
s
b
et
w
ee
n
o
u
r
w
o
r
k
an
d
p
r
ev
i
o
u
s
w
o
r
k
[
9
]
T
P
R
F
P
R
F
N
R
T
N
R
P
r
e
c
i
si
o
n
P
r
e
se
n
t
W
o
r
k
R
e
f
.
P
r
e
se
n
t
W
o
r
k
R
e
f
.
P
r
e
se
n
t
W
o
r
k
R
e
f
P
r
e
se
n
t
W
o
r
k
R
e
f
.
P
r
e
se
n
t
W
o
r
k
R
e
f
.
N
o
r
mal
9
9
.
7
9
%
9
9
.
8
0
%
1
.
8
5
%
2
.
0
0
%
0
.
2
2
%
0
.
2
0
%
9
8
.
1
5
%
9
8
.
0
0
%
9
9
.
8
0
%
9
9
.
8
0
%
F
l
o
o
d
i
n
g
9
8
.
9
7
%
9
8
.
5
0
%
0
.
0
9
%
0
.
1
0
%
1
.
0
3
%
1
.
5
0
%
9
9
.
9
1
%
9
9
.
9
0
%
9
0
.
3
0
%
9
0
%
T
D
M
A
9
1
.
9
9
%
9
1
.
5
0
%
0
.
0
1
%
0
.
0
0
%
8
.
0
1
%
8
.
5
0
%
9
9
.
9
9
%
1
0
0
.
0
0
%
9
9
.
1
0
%
9
9
.
2
0
%
G
r
a
y
h
o
l
e
8
5
.
1
9
%
8
6
.
7
0
%
0
.
6
4
%
0
.
7
0
%
1
4
.
8
1
%
1
3
.
3
0
%
9
9
.
3
6
%
9
9
.
3
0
%
8
4
.
4
0
%
8
3
.
2
0
%
B
l
a
c
k
h
o
l
e
8
0
.
2
9
%
7
7
.
8
0
%
0
.
5
7
%
0
.
5
0
%
1
9
.
7
1
%
2
2
.
2
0
%
9
9
.
4
3
%
9
9
.
5
0
%
7
9
.
6
0
%
8
1
%
5
.
2
.
B
ina
ry
cla
s
s
if
ica
t
io
n
I
n
b
in
ar
y
cla
s
s
i
f
ica
tio
n
,
all
t
h
e
attac
k
clas
s
es
ar
e
co
n
s
id
er
ed
as
A
ttac
k
a
n
d
r
est
ar
e
co
n
s
id
er
ed
No
r
m
a
l.
T
ab
le
6
illu
s
tr
ates
t
h
e
n
u
m
b
er
o
f
p
r
ed
ictio
n
s
b
y
e
ac
h
o
f
t
h
e
ap
p
lied
alg
o
r
ith
m
s
.
I
t
ca
n
b
e
o
b
s
er
v
ed
th
at
Naï
v
e
B
a
y
es
s
h
o
w
s
t
h
e
b
est
p
er
f
o
r
m
an
ce
a
m
o
n
g
all
th
e
ap
p
lied
alg
o
r
ith
m
s
.
C
o
m
p
ar
i
s
o
n
o
f
class
i
f
icat
io
n
ac
cu
r
ac
ies ar
e
illu
s
t
r
ated
in
F
i
g
u
r
e
3
.
T
ab
le
6
.
C
o
m
p
ar
is
o
n
o
f
n
u
m
b
er
o
f
attac
k
p
r
ed
ictio
n
A
t
t
a
c
k
Ty
p
e
T
o
t
a
l
P
r
e
d
i
c
t
e
d
K
N
N
NB
S
V
M
LR
N
o
r
mal
1
3
5
8
8
9
1
3
5
2
3
2
1
1
6
2
6
8
1
3
5
8
8
9
1
3
4
9
0
7
A
t
t
a
c
k
1
3
9
7
6
1
2
6
5
7
1
3
8
1
9
1
0
3
1
0
0
0
8
Fig
u
r
e
3
.
B
in
ar
y
attac
k
p
r
ed
ict
io
n
co
m
p
ar
is
o
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
Da
ta
min
in
g
a
p
p
r
o
a
c
h
to
a
n
a
l
yzin
g
in
tr
u
s
io
n
d
etec
tio
n
o
f wi
r
eless
s
en
s
o
r
n
etw
o
r
k
(
Md
A
la
u
d
d
in
R
ezvi
)
521
5
.
3
.
P
er
f
o
rm
a
nce
f
o
r
s
pl
it
t
ing
da
t
a
A
p
ar
t
f
r
o
m
a
n
al
y
zi
n
g
t
h
e
p
er
f
o
r
m
an
ce
s
o
f
v
ar
io
u
s
lear
n
i
n
g
tec
h
n
iq
u
es,
w
e
h
av
e
al
s
o
ex
a
m
i
n
ed
w
h
et
h
er
t
h
e
d
ataset
s
ize
h
a
s
an
y
i
m
p
ac
t
o
n
t
h
e
cla
s
s
i
f
ic
atio
n
p
er
f
o
r
m
a
n
ce
o
f
t
h
e
al
g
o
r
ith
m
s
.
W
e
h
av
e
ex
p
er
i
m
e
n
ted
ac
cu
r
ac
y
b
y
s
p
l
itti
n
g
d
ata
s
et
s
in
to
t
h
e
s
ize
s
o
f
1
0
0
K,
2
0
0
K,
3
0
0
K+
in
s
tan
ce
s
an
d
ap
p
lied
all
f
o
u
r
al
g
o
r
ith
m
s
.
F
ig
u
r
e
4
s
h
o
w
s
th
e
co
m
p
ar
is
o
n
o
f
ac
cu
r
ac
ies
f
o
r
s
p
litt
in
g
d
ata.
I
t
is
o
b
s
er
v
ed
th
at
o
n
l
y
t
h
e
ac
cu
r
ac
y
o
f
KN
N
is
in
cr
ea
s
in
g
w
it
h
th
e
i
n
cr
ea
s
e
in
d
ata
s
iz
e.
Ho
w
ev
er
,
f
o
r
SMV
t
h
e
ac
cu
r
ac
y
is
d
ec
r
ea
s
e
d
f
o
r
2
0
0
k
d
ata
s
ize.
T
h
e
o
th
er
tw
o
al
g
o
r
ith
m
s
d
o
n
o
t h
a
v
e
an
y
co
n
s
id
er
ab
le
ef
f
ec
t o
v
er
t
h
e
d
ata
s
eize
.
Fig
u
r
e
4
.
A
cc
u
r
ac
y
co
m
p
ar
is
o
n
f
o
r
s
p
litt
i
n
g
d
ata
5
.
4
.
Co
m
pa
ra
t
iv
e
a
na
ly
s
is
Af
ter
ap
p
l
y
i
n
g
all
t
h
e
m
en
t
io
n
ed
alg
o
r
ith
m
s
f
o
r
ea
ch
a
ttack
t
y
p
e
th
e
o
v
er
all
p
er
f
o
r
m
an
ce
i
s
ev
alu
a
ted
b
y
ca
lc
u
lati
n
g
ac
c
u
r
ac
y
,
er
r
o
r
,
p
r
ec
is
io
n
,
r
ec
all
an
d
F1
-
Sco
r
e
f
o
r
t
h
e
d
ata
s
e
t
an
d
il
lu
s
tr
ated
in
T
ab
le
7
.
Fro
m
tab
le,
w
e
ca
n
s
ee
t
h
at
t
h
e
ac
c
u
r
ac
y
o
f
K
NN
is
9
8
.
4
%,
Naïv
e
B
a
y
e
s
i
s
8
6
.
8
8
%,
L
o
g
i
s
tic
R
eg
r
es
s
io
n
is
9
6
.
7
2
%,
SVM
i
s
9
1
.
2
2
% a
n
d
A
NN
h
as
9
8
.
5
6
%.
I
n
t
h
e
e
x
p
er
i
m
e
n
t,
ANN
a
n
d
KNN
s
h
o
w
b
etter
p
er
f
o
r
m
a
n
ce
t
h
an
t
h
e
o
th
er
s
.
F
ig
u
r
e
5
r
ep
r
esen
ts
t
h
e
co
m
p
ar
i
s
o
n
o
f
t
h
e
ac
cu
r
ac
y
o
f
ap
p
lied
alg
o
r
ith
m
s
.
A
p
ar
t
f
r
o
m
ca
lc
u
lat
in
g
cla
s
s
i
f
icatio
n
ac
c
u
r
ac
ies,
P
r
ec
is
io
n
an
d
R
ec
all
ar
e
also
ca
lc
u
late
d
.
Fo
r
th
i
s
ex
p
er
i
m
e
n
t,
R
ec
all
is
cr
u
cia
l
as
it
is
r
eq
u
ir
ed
to
k
n
o
w
h
o
w
g
o
o
d
an
alg
o
r
ith
m
ca
n
p
r
ed
ict
ea
ch
t
y
p
e
o
f
attac
k
a
m
o
n
g
th
e
to
tal
n
u
m
b
er
o
f
at
tack
s
i
n
th
e
d
ataset.
I
n
th
e
e
x
p
er
im
e
n
t,
th
e
p
er
f
o
r
m
a
n
c
e
o
f
SVM
is
v
er
y
p
o
o
r
w
h
ile
Naï
v
e
B
a
y
es p
er
f
o
r
m
s
v
er
y
w
e
ll.
T
ab
le
7
.
C
o
m
p
ar
ativ
e
a
n
al
y
s
i
s
o
f
all
alg
o
r
ith
m
s
A
l
g
o
r
i
t
h
m
A
c
c
u
r
a
c
y
(
%)
Er
r
o
r
(
%)
P
r
e
c
i
si
o
n
(
%)
R
e
c
a
l
l
(
%)
F
1
S
c
o
r
e
(
%)
K
N
N
9
8
.
4
1
.
6
9
5
.
6
9
9
1
.
5
0
9
3
.
5
5
N
a
ï
v
e
B
a
y
e
s
8
6
.
8
8
1
3
.
1
2
4
1
.
3
9
9
8
.
8
7
5
8
.
3
5
L
o
g
i
st
i
c
R
e
g
r
e
ssi
o
n
9
6
.
7
2
3
.
2
8
9
0
.
9
9
7
1
.
8
1
8
0
.
2
8
S
V
M
9
1
.
2
2
8
.
7
8
9
5
.
9
5
5
.
7
8
7
.
1
6
A
N
N
9
8
.
5
6
0
.
2
7
9
0
.
6
6
9
1
.
2
4
9
0
.
9
5
4
Fig
u
r
e
5
.
C
o
m
p
ar
is
o
n
o
f
ac
c
u
r
ac
y
o
f
d
if
f
er
en
t a
lg
o
r
it
h
m
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
21
,
No
.
1
,
J
an
u
ar
y
2
0
2
1
:
5
1
6
-
523
522
6.
M
ANAG
I
NG
CL
A
SS
I
M
B
AL
ANC
E
P
RO
B
L
E
M
C
las
s
i
m
b
ala
n
ce
p
r
o
b
le
m
[
2
3
]
in
a
d
ataset
r
ef
er
s
to
i
m
b
alan
ce
d
is
tr
ib
u
tio
n
o
f
cla
s
s
e
s
in
th
e
d
ataset.
T
h
e
W
SN
-
DS
d
ataset
t
h
at
h
a
s
b
ee
n
u
s
ed
in
t
h
e
ex
p
er
i
m
en
t
s
u
f
f
er
s
f
r
o
m
s
u
ch
p
r
o
b
le
m
.
I
t
ca
n
b
e
o
b
s
er
v
ed
f
r
o
m
Fig
u
r
e
2
.
th
a
t
t
h
e
to
tal
n
u
m
b
er
o
f
at
tack
s
i
n
t
h
e
d
at
aset
is
f
ar
le
s
s
t
h
a
n
t
h
at
o
f
n
o
n
-
at
tac
k
s
.
Hav
i
n
g
i
m
b
alan
ce
d
d
is
tr
ib
u
t
io
n
o
f
cla
s
s
es
i
n
a
d
ataset,
t
h
e
clas
s
if
ica
tio
n
ac
c
u
r
ac
y
o
f
an
alg
o
r
it
h
m
m
i
g
h
t
b
e
v
er
y
h
i
g
h
w
h
ile
th
e
cla
s
s
i
f
ier
m
a
y
co
m
p
letel
y
f
ai
l
to
p
r
ed
ict
t
h
e
m
in
o
r
it
y
c
lass
.
I
n
t
h
e
p
r
esen
t
w
o
r
k
,
in
tr
u
s
io
n
d
etec
tio
n
is
t
h
e
m
ai
n
f
o
cu
s
,
h
o
w
e
v
er
,
i
n
th
e
d
ataset,
i
t
is
t
h
e
m
i
n
o
r
it
y
class
.
He
n
ce
,
i
t
i
s
a
n
es
s
e
n
tial
tas
k
to
h
a
n
d
le
t
h
e
class
-
i
m
b
a
lan
ce
p
r
o
b
le
m
to
p
r
o
p
er
ly
p
r
ed
ict
th
e
attac
k
s
.
Am
o
n
g
v
ar
io
u
s
av
a
ilab
le
t
ec
h
n
iq
u
es,
SMOT
E
(
S
y
n
th
et
ic
Min
o
r
it
y
O
v
er
-
s
a
m
p
lin
g
T
ec
h
n
iq
u
e)
[
2
4
]
is
a
m
e
th
o
d
th
at
h
a
s
b
ee
n
ap
p
lied
v
er
y
w
id
el
y
.
W
e
ex
p
er
i
m
e
n
ted
to
o
b
s
er
v
e
th
e
ef
f
ec
t
o
f
SMOT
E
[
2
5
]
w
h
i
le
class
i
f
y
in
g
th
e
m
i
n
o
r
it
y
cla
s
s
es
(
all
t
y
p
es
o
f
attac
k
s
in
th
is
w
o
r
k
)
.
T
ab
le
8
.
illu
s
tr
ates
th
e
ex
p
er
i
m
en
tal
r
es
u
lt.
Fo
r
t
h
e
e
x
p
er
im
en
tal
p
u
r
p
o
s
e,
o
n
l
y
Naï
v
e
B
ay
e
s
a
n
d
L
o
g
i
s
tic
R
e
g
r
es
s
io
n
ar
e
ap
p
lied
h
er
e.
I
t
ca
n
b
e
o
b
s
er
v
ed
th
at
in
m
o
s
t
o
f
th
e
ca
s
e
s
,
af
ter
ap
p
l
y
i
n
g
S
MO
T
E
,
th
e
p
r
ed
ictio
n
r
ate
o
f
attac
k
s
is
i
n
cr
ea
s
ed
(
ex
ce
p
t
f
o
r
Gr
a
y
h
o
le)
.
Su
c
h
ex
p
er
i
m
en
t
r
e
v
ea
ls
t
h
at
ev
en
i
f
t
h
e
d
ataset
is
i
m
b
a
lan
ce
d
,
t
h
e
m
i
n
o
r
it
y
class
es
ca
n
n
o
w
b
e
cla
s
s
i
f
ie
d
p
r
o
p
e
r
ly
a
f
ter
ap
p
l
y
in
g
S
MO
T
E
.
A
s
i
n
ea
r
lier
ex
p
er
i
m
e
n
ts
,
L
o
g
i
s
tic
R
eg
r
es
s
io
n
also
p
er
f
o
r
m
s
b
etter
in
t
h
i
s
ex
p
er
i
m
e
n
t.
T
ab
le
8
.
E
f
f
ec
t o
f
SMOT
E
o
n
class
i
f
y
in
g
attac
k
t
y
p
e
s
A
t
t
a
c
k
T
y
p
e
T
o
t
a
l
P
r
e
d
i
c
t
i
o
n
s
N
a
ï
v
e
B
a
y
e
s
L
o
g
i
st
i
c
R
e
g
r
e
ssi
o
n
B
e
f
o
r
e
S
M
O
T
E
A
f
t
e
r
S
M
O
T
E
B
e
f
o
r
e
S
M
O
T
E
A
f
t
e
r
S
M
O
T
E
N
o
r
mal
1
3
5
8
8
9
1
1
8
1
6
7
(
8
6
.
9
6
%)
1
1
3
4
6
0
(
8
3
.
4
9
%)
1
3
4
9
5
8
(
9
9
.
3
1
%)
1
1
3
3
8
9
(
8
3
.
4
4
%)
F
l
o
o
d
i
n
g
1
3
1
0
1
1
4
3
(
8
7
.
2
5
%)
1
2
5
0
(
9
5
.
4
2
%)
1
0
5
3
(
8
0
.
3
8
%)
1
2
7
4
(
9
7
.
2
5
%)
T
D
M
A
2
6
5
1
9
5
8
(
3
6
.
1
4
%)
1
6
1
0
(
6
0
.
7
3
%)
1
9
3
0
(
7
2
.
8
0
%)
2
0
6
4
(
7
7
.
8
6
%)
G
r
a
y
h
o
l
e
5
9
3
8
3
0
8
2
(
5
1
.
9
0
%)
2
7
3
6
(
4
6
.
0
8
%)
3
0
0
3
(
5
0
.
5
7
%)
3
2
0
6
(
5
3
.
9
9
%)
B
l
a
c
k
h
o
l
e
4
0
7
7
3
8
0
8
(
9
3
.
4
0
%)
3
9
4
0
(
9
6
.
6
4
%)
2
8
1
6
(
6
9
.
0
7
%)
3
8
2
6
(
9
3
.
8
4
%)
7.
CO
NCLU
SI
O
N
Var
io
u
s
d
ata
m
i
n
i
n
g
tec
h
n
iq
u
es
f
o
r
d
etec
ti
n
g
Do
S
attac
k
s
f
r
o
m
W
SN
-
DS
d
ataset
h
av
e
b
ee
n
p
r
esen
ted
in
th
is
p
ap
er
.
Af
ter
u
s
i
n
g
KNN,
L
o
g
is
t
ic
r
eg
r
es
s
i
o
n
,
SVM,
Naï
v
e
B
a
y
e
s
a
n
d
ANN
w
e
h
av
e
f
o
u
n
d
o
u
t
th
at
A
N
N
(
9
8
.
5
6
%)
an
d
KNN
(
9
8
.
4
%)
p
er
f
o
r
m
ed
b
etter
f
o
r
in
tr
u
s
io
n
d
etec
tio
n
in
o
u
r
d
ataset.
A
co
m
p
ar
is
o
n
h
a
s
b
ee
n
m
ad
e
w
i
th
th
e
e
x
is
ti
n
g
w
o
r
k
f
r
o
m
w
h
e
r
e
th
e
d
ataset
h
as
b
ee
n
co
llect
ed
.
Ou
r
ex
p
er
im
e
n
t
s
h
o
w
s
s
i
m
ilar
r
esu
lt
to
t
h
at
w
o
r
k
an
d
it
co
n
f
ir
m
s
t
h
at
o
u
r
ex
p
er
i
m
en
t
h
as
b
ee
n
c
o
n
d
u
cted
u
s
i
n
g
an
ap
p
r
o
p
r
iate
an
d
s
ta
n
d
a
r
d
s
et
u
p
.
As
t
h
e
d
atase
t
i
s
o
b
tain
ed
b
y
u
s
i
n
g
L
E
A
C
H
p
r
o
to
co
l,
s
elec
ted
alg
o
r
it
h
m
i
s
p
r
o
p
er
f
o
r
th
is
t
y
p
e
o
f
d
atase
t.
Ho
w
e
v
er
,
th
e
s
e
d
ata
m
i
n
i
n
g
tech
n
iq
u
es
ca
n
also
b
e
ap
p
lied
to
th
e
d
ataset
o
b
tain
ed
b
y
o
th
er
r
o
u
ti
n
g
p
r
o
to
co
ls
.
W
e
ca
n
u
s
e
KNN
an
d
A
N
N
alg
o
r
i
t
h
m
i
n
I
DS
o
f
a
W
SN
w
h
ic
h
w
ill
h
elp
to
d
etec
t
attac
k
in
n
et
w
o
r
k
an
d
g
iv
e
alar
m
to
s
tar
t
t
h
e
p
r
ev
en
tio
n
m
ec
h
an
i
s
m
.
T
h
is
ca
n
b
e
u
s
ed
in
r
ea
l
ti
m
e
ap
p
licatio
n
.
A
s
t
h
e
d
ataset
is
i
m
b
a
lan
ce
,
w
e
also
s
h
o
w
h
o
w
to
m
a
n
a
g
e
th
e
i
m
b
a
lan
ce
t
h
e
d
ataset
an
d
p
er
f
o
r
m
class
i
f
icatio
n
s
.
T
h
e
ex
p
er
i
m
e
n
tal
r
es
u
lt
s
h
o
w
s
t
h
at
af
ter
ap
p
ly
in
g
SMOT
E
th
e
alg
o
r
it
h
m
s
ca
n
p
r
ed
ict
attac
k
s
th
an
t
h
at
w
i
th
o
u
t b
alan
ci
n
g
th
e
d
ataset.
I
n
f
u
t
u
r
e
w
e
w
o
u
ld
li
k
e
to
ap
p
ly
o
t
h
er
alg
o
r
it
h
m
s
to
f
in
d
o
u
t
w
h
ic
h
w
il
l
h
a
v
e
b
etter
p
er
f
o
r
m
an
ce
th
an
KNN
a
n
d
A
NN
alg
o
r
i
th
m
.
W
e
w
il
l
u
s
e
d
i
f
f
er
en
t
h
y
b
r
id
a
lg
o
r
it
h
m
s
a
n
d
al
s
o
w
ill
i
m
p
r
o
v
e
th
e
p
er
f
o
r
m
a
n
ce
o
f
Naï
v
e
B
a
y
e
s
,
SVM
an
d
L
o
g
is
tic
R
eg
r
e
s
s
io
n
.
I
t
is
also
b
en
e
f
icial
t
o
d
ev
elo
p
v
ar
io
u
s
ass
o
ciatio
n
r
u
les
a
m
o
n
g
th
e
a
ttrib
u
tes
t
h
at
ca
n
s
u
p
p
o
r
t
u
s
er
s
to
m
an
a
g
e
n
et
w
o
r
k
r
eq
u
est
s
to
p
r
ed
ict
v
ar
io
u
s
t
y
p
es o
f
attac
k
s
.
ACK
NO
WL
E
D
G
E
M
E
NT
S
W
e
ar
e
g
r
ate
f
u
l
to
Dr
.
I
m
a
n
A
l
m
o
m
a
n
i,
(
Ass
o
ciate
P
r
o
f
e
s
s
o
r
,
P
r
in
ce
S
u
lta
n
Un
i
v
er
s
i
t
y
,
W
o
m
e
n
C
a
m
p
u
s
,
R
i
y
ad
h
,
KS
A
)
f
o
r
p
r
o
v
in
g
u
s
th
e
d
atase
t th
at
h
as b
ee
n
u
s
ed
in
o
u
r
ex
p
er
i
m
en
t
RE
F
E
R
E
NC
E
S
[1
]
I.
F
.
A
k
y
il
d
iz an
d
M
.
C.
Vu
ra
n
,
"
W
irele
ss
s
e
n
so
r
n
e
tw
o
rk
s
,"
J
o
h
n
W
il
e
y
&
S
o
n
s,
v
o
l
.
4
,
2
0
1
0
.
[2
]
A
.
H.
F
a
ro
o
q
i
a
n
d
F
.
A
.
Kh
a
n
,
“
In
tru
si
o
n
De
tec
ti
o
n
S
y
ste
m
s
f
o
r
W
irel
e
ss
S
e
n
so
r
Ne
t
w
o
rk
s:
A
S
u
rv
e
y
,
”
In
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
F
u
tu
re
Ge
n
e
ra
ti
o
n
Co
mm
u
n
ica
t
io
n
a
n
d
Ne
two
rk
in
g
,
S
p
ri
n
g
e
r
,
Be
rli
n
,
He
i
d
e
lb
e
rg
,
p
p
.
2
3
4
–
2
4
1
,
2
0
0
9
.
[3
]
G
h
o
sa
l,
A
.
,
&
H
a
ld
e
r,
S
.
,
"
In
tru
sio
n
d
e
tec
ti
o
n
i
n
w
irele
ss
se
n
so
r
n
e
tw
o
rk
s:
Iss
u
e
s,
c
h
a
ll
e
n
g
e
s
a
n
d
a
p
p
r
o
a
c
h
e
s
,"
In
W
ire
les
s n
e
two
rk
s a
n
d
se
c
u
rity
.
S
p
ri
n
g
e
r,
p
p
.
3
2
9
-
3
6
7
.
2
0
1
3
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
Da
ta
min
in
g
a
p
p
r
o
a
c
h
to
a
n
a
l
yzin
g
in
tr
u
s
io
n
d
etec
tio
n
o
f wi
r
eless
s
en
s
o
r
n
etw
o
r
k
(
Md
A
la
u
d
d
in
R
ezvi
)
523
[4
]
A
.
H.
F
a
ro
o
q
i
a
n
d
F
.
A
.
Kh
a
n
,
“
A
su
rv
e
y
o
f
In
tru
sio
n
De
tec
ti
o
n
S
y
ste
m
s
f
o
r
W
irele
ss
S
e
n
so
r
Ne
t
wo
rk
s,”
In
t.
J
.
Ad
Ho
c
Ub
iq
u
it
o
u
s C
o
mp
u
t
.
,
v
o
l.
9
,
n
o
.
2
,
p
p
.
6
9
-
83
,
2
0
1
2
.
[5
]
A
rd
ian
s
y
a
h
,
A
.
Y.,
&
S
a
rn
o
,
R.
,
"
P
e
rf
o
rm
a
n
c
e
a
n
a
l
y
sis
o
f
w
irele
ss
se
n
so
r
n
e
tw
o
rk
w
it
h
lo
a
d
b
a
la
n
c
in
g
f
o
r
d
a
ta
tran
sm
issio
n
u
sin
g
x
b
e
e
z
b
m
o
d
u
le
,"
In
d
o
n
e
si
a
n
J
o
u
r
n
a
l
o
f
El
e
c
trica
l
En
g
i
n
e
e
rin
g
a
n
d
C
o
mp
u
ter
S
c
ie
n
c
e
(
IJ
EE
CS
),
v
o
l.
18
,
n
o
.
1
,
p
p
.
88
-
1
0
0
,
2
0
1
9
.
[6
]
Q.
L
iao
a
n
d
H.
Zh
u
,
“
A
n
En
e
rg
y
Ba
lan
c
e
d
Clu
ste
rin
g
A
lg
o
rit
h
m
B
a
se
d
o
n
L
E
A
CH
P
ro
t
o
c
o
l
,
”
Ap
p
l.
M
e
c
h
.
M
a
ter
.
,
v
o
l.
3
4
1
–
3
4
2
,
p
p
.
1
1
3
8
–
1
1
4
3
,
Ju
l
.
2
0
1
3
.
[7
]
S
.
Um
ra
o
,
A
.
Ku
m
a
r,
a
n
d
P
.
Um
r
a
o
,
“
S
e
c
u
rit
y
a
tt
a
c
k
s
a
n
d
th
e
ir
c
o
u
n
term
e
a
su
re
s
a
lo
n
g
w
it
h
n
o
d
e
re
p
li
c
a
ti
o
n
a
tt
a
c
k
f
o
r
ti
m
e
s
y
n
c
h
ro
n
iza
ti
o
n
in
w
irel
e
ss
se
n
so
r
n
e
t
w
o
rk
,
”
in
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
A
d
v
a
n
c
e
d
N
a
n
o
m
a
ter
ia
ls
&
Eme
rg
in
g
En
g
in
e
e
rin
g
T
e
c
h
n
o
l
o
g
ies
,
p
p
.
5
7
6
–
5
8
1
,
2
0
1
3
.
[8
]
Ja
li
l
Ja
b
a
ri
L
o
tf
,
M
.
Ho
ss
e
in
z
a
d
e
h
,
R.
M
.
A
lg
u
li
e
v
,
“
Hie
ra
rc
h
ica
l
r
o
u
ti
n
g
in
w
irele
ss
se
n
so
r
n
e
tw
o
rk
s:
a
su
rv
e
y
,
”
in
2
0
1
0
2
n
d
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
Co
m
p
u
ter
E
n
g
i
n
e
e
rin
g
a
n
d
T
e
c
h
n
o
l
o
g
y
,
p
p
.
V
3
-
6
5
0
-
V3
-
6
5
4
,
2
0
1
0
.
[9
]
A
l
m
o
m
a
n
i,
I.
,
A
l
-
Ka
sa
sb
e
h
,
B.
,
&
A
l
-
A
k
h
ra
s,
M
.
,
"
W
S
N
-
DS:
A
d
a
tas
e
t
f
o
r
in
tru
sio
n
d
e
tec
ti
o
n
sy
s
tem
s
in
w
irele
ss
se
n
so
r
n
e
tw
o
rk
s
,"
J
o
u
rn
a
l
o
f
S
e
n
s
o
rs
,
2
0
1
6
.
.
[1
0
]
W
.
R.
He
in
z
e
lm
a
n
,
A
.
Ch
a
n
d
ra
k
a
sa
n
,
a
n
d
H.
Ba
lak
rish
n
a
n
,
“
E
n
e
rg
y
-
e
ff
icie
n
t
c
o
m
m
u
n
ica
ti
o
n
p
ro
t
o
c
o
l
f
o
r
w
irele
ss
m
icro
se
n
so
r
n
e
t
w
o
rk
s,”
in
Pro
c
e
e
d
in
g
s
o
f
th
e
3
3
rd
A
n
n
u
a
l
H
a
wa
ii
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
S
y
ste
m
S
c
ien
c
e
s,
v
o
l.
2
,
p
.
1
0
,
2
0
0
0
.
[1
1
]
A
.
A
.
Hu
ss
ien
,
S
.
W
.
Al
-
S
h
a
m
m
a
ri,
M
.
J.
M
a
rie
.,
"
P
e
rf
o
rm
a
n
c
e
e
v
a
lu
a
ti
o
n
o
f
w
irele
ss
se
n
so
r
n
e
tw
o
rk
s
u
sin
g
L
E
A
CH
p
ro
to
c
o
l
,"
In
d
o
n
e
sia
n
J
o
u
rn
a
l
o
f
El
e
c
trica
l
E
n
g
in
e
e
rin
g
a
n
d
Co
m
p
u
ter
S
c
ien
c
e
,
v
o
l.
1
9
,
n
o
.
1
,
p
p
.
3
9
5
-
402
,
2
0
2
0
.
[1
2
]
C.
Io
a
n
n
o
u
,
V
.
V
a
ss
il
i
o
u
,
a
n
d
C
.
S
e
rg
io
u
,
“
A
n
In
tr
u
sio
n
De
tec
ti
o
n
S
y
st
e
m
f
o
r
W
irele
ss
S
e
n
so
r
Ne
t
wo
rk
s,”
in
2017
2
4
t
h
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
T
e
lec
o
mm
u
n
ica
ti
o
n
s (
ICT
)
,
p
p
.
1
–
5
,
2
0
1
7
.
[1
3
]
T.
-
T.
-
H.
L
e
,
T
.
P
a
rk
,
D.
Ch
o
,
H.
Kim
,
“
A
n
E
ff
e
c
ti
v
e
Clas
sif
i
c
a
ti
o
n
f
o
r
Do
S
A
tt
a
c
k
s
in
W
irele
s
s
S
e
n
so
r
Ne
tw
o
rk
s,”
in
2
0
1
8
T
e
n
th
In
ter
n
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
o
n
Ub
i
q
u
it
o
u
s
a
n
d
F
u
t
u
re
Ne
two
rk
s (
ICUFN)
,
p
p
.
6
8
9
–
6
9
2
,
2
0
1
8
.
[1
4
]
Zh
a
n
g
,
R.
,
&
X
iao
,
X
.
,
"
In
tr
u
sio
n
De
tec
ti
o
n
in
W
irele
ss
S
e
n
so
r
N
e
tw
o
rk
s
w
it
h
a
n
I
m
p
ro
v
e
d
NSA
Ba
se
d
o
n
S
p
a
c
e
Div
isio
n
,
"
J
o
u
r
n
a
l
o
f
S
e
n
so
rs
,
2
0
1
9
.
[1
5
]
H.
S
u
h
a
im
i,
S
.
I.
S
u
li
m
a
n
,
I.
M
u
sirin
,
A
.
F
.
Ha
ru
n
,
a
n
d
R.
M
o
h
a
m
a
d
,
"
Ne
t
w
o
rk
in
tru
sio
n
d
e
tec
ti
o
n
sy
ste
m
b
y
u
sin
g
g
e
n
e
ti
c
a
lg
o
rit
h
m
,
"
In
d
o
n
e
s.
J
.
E
l
e
c
tr.
En
g
.
Co
mp
u
t.
S
c
i
.
(
IJ
EE
CS
)
,
v
o
l.
1
6
,
n
o
.
3
,
p
p
.
1
5
9
3
–
1
5
9
9
,
2
0
1
9
.
[1
6
]
F
.
Jo
se
p
h
i
n
a
n
d
N.
Ra
m
a
ra
j,
“
P
re
v
e
n
ti
o
n
a
n
d
De
tec
ti
o
n
o
f
S
e
lec
ti
v
e
F
o
r
w
a
rd
in
g
A
tt
a
c
k
in
W
irele
ss
S
e
n
so
r
Ne
tw
o
rk
s
,
”
In
t.
J
.
S
c
i
.
Res
.
I
n
n
o
v
.
,
v
o
l.
1
,
p
p
.
1
2
–
1
7
,
2
0
1
6
.
[1
7
]
M
.
A
.
L
a
ti
f
,
M
.
A
d
n
a
n
,
"
A
N
N
-
Ba
se
d
Da
ta
M
in
in
g
f
o
r
Be
tt
e
r
Re
so
u
rc
e
M
a
n
a
g
e
m
e
n
t
in
th
e
N
e
x
t
G
e
n
e
ra
ti
o
n
W
irele
ss
N
e
t
w
o
rk
s,
"
in
2
0
1
6
I
n
te
rn
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Fro
n
ti
e
r
s o
f
In
fo
rm
a
t
io
n
T
e
c
h
n
o
l
o
g
y
,
p
p
.
3
5
–
39
,
2
0
1
6
.
[1
8
]
A
.
P
.
A
b
id
o
y
e
a
n
d
E.
O.
Oc
h
o
la,
"
De
n
ial
o
f
S
e
rv
ice
A
tt
a
c
k
s
in
W
irele
ss
S
e
n
so
r
Ne
tw
o
rk
s
w
it
h
P
r
o
p
o
se
d
Co
u
n
term
e
a
su
re
s,
"
in
In
fo
rm
a
ti
o
n
T
e
c
h
n
o
l
o
g
y
-
Ne
w
Ge
n
e
ra
t
io
n
s,
p
p
.
1
8
5
–
1
9
1
,
2
0
1
8
.
[1
9
]
H.
Ka
lk
h
a
,
H.
S
a
to
ri,
a
n
d
K
.
S
a
t
o
ri,
"
P
re
v
e
n
ti
n
g
Blac
k
Ho
le
A
tt
a
c
k
in
W
irele
ss
S
e
n
so
r
Ne
t
w
o
rk
Us
in
g
HMM
,
"
in
Pro
c
e
d
ia
C
o
mp
u
ter
S
c
ien
c
e
,
v
o
l.
1
4
8
,
p
p
.
5
5
2
–
5
6
1
,
2
0
1
9
.
[2
0
]
A
.
A
h
m
e
d
,
M
.
I.
Ch
a
n
n
a
,
a
n
d
U
.
A
.
Kh
a
n
,
"
P
e
rf
o
rm
a
n
c
e
Ev
a
lu
a
t
io
n
o
f
W
irele
ss
S
e
n
so
r
Ne
tw
o
rk
in
P
re
se
n
c
e
o
f
G
ra
y
h
o
le
A
tt
a
c
k
,
"
Qu
e
st
Res
.
J
.
,
v
o
l.
1
3
,
n
o
.
1
,
p
p
.
1
–
8
,
2
0
1
4
.
[2
1
]
L
.
Co
p
p
o
li
n
o
,
S
.
DA
n
to
n
i
o
,
A
.
Ga
ro
f
a
lo
,
a
n
d
L
.
Ro
m
a
n
o
,
"
Ap
p
ly
in
g
Da
ta
M
in
in
g
Tec
h
n
iq
u
e
s
to
In
tru
sio
n
De
tec
ti
o
n
in
W
irele
ss
S
e
n
so
r
Ne
tw
o
rk
s,
"
in
2
0
1
3
Ei
g
h
th
I
n
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
P
2
P,
P
a
ra
l
l
e
l,
Gr
id
,
Cl
o
u
d
a
n
d
In
ter
n
e
t
Co
mp
u
ti
n
g
,
p
p
.
2
4
7
–
254
,
2
0
1
3
.
[2
2
]
Ž.
G
a
v
rić
a
n
d
D.
S
im
ić,
"
Ov
e
r
v
ie
w
o
f
DO
S
a
tt
a
c
k
s
o
n
w
irele
s
s
se
n
so
r
n
e
tw
o
rk
s
a
n
d
e
x
p
e
rim
e
n
tal
re
su
lt
s
f
o
r
sim
u
latio
n
o
f
in
terf
e
re
n
c
e
a
tt
a
c
k
s
,"
In
g
e
n
ier
ía
e
I
n
v
e
stig
a
c
i
ó
n
,
v
o
l.
3
8
,
n
o
.
1
,
p
p
.
1
3
0
–
1
3
8
,
2
0
1
8
.
[2
3
]
N.
Ja
p
k
o
w
i
c
z
a
n
d
S
.
S
tep
h
e
n
,
"
Th
e
c
las
s
i
m
b
a
lan
c
e
p
ro
b
lem
:
A
s
y
ste
m
a
ti
c
stu
d
y
,
"
In
tell.
Da
ta
An
a
l
.
,
v
o
l.
6
,
n
o
.
5
,
p
p
.
4
2
9
–
4
4
9
,
N
o
v
.
2
0
0
2
.
[2
4
]
N.
V
.
Ch
a
w
la,
K.
W
.
Bo
wy
e
r,
L.
O.
Ha
ll
,
a
n
d
W
.
P
.
Ke
g
e
l
m
e
y
e
r,
"
S
M
OT
E:
S
y
n
th
e
ti
c
M
in
o
rit
y
Ov
e
r
-
sa
m
p
li
n
g
T
e
c
h
n
iq
u
e
,
"
J
.
Arti
f.
In
tell.
Res
.
,
v
o
l.
1
6
,
p
p
.
3
2
1
–
3
5
7
,
2
0
0
2
.
[2
5
]
N
.
S
a
n
t
o
so
,
W
.
W
ib
o
w
o
,
H
.
Hik
m
a
w
a
ti
“
In
teg
ra
ti
o
n
o
f
sy
n
th
e
ti
c
m
in
o
rit
y
o
v
e
r
sa
m
p
li
n
g
tec
h
n
iq
u
e
f
o
r
im
b
a
lan
c
e
d
c
las
s
,
"
In
d
o
n
e
sia
n
J
o
u
rn
a
l
o
f
E
lec
trica
l
En
g
i
n
e
e
rin
g
a
n
d
Co
mp
u
te
r
S
c
ien
c
(
IJ
EE
CS
)
,
v
o
l.
1
3
,
n
o
.
1
,
p
p
.
1
0
2
-
1
0
8
,
2
0
1
9
.
Evaluation Warning : The document was created with Spire.PDF for Python.