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.
23
,
No
.
2
,
A
u
g
u
s
t
20
21
,
p
p
.
9
5
3
~
9
6
1
I
SS
N:
2
5
0
2
-
4
7
5
2
,
DOI
: 1
0
.
1
1
5
9
1
/ijeecs.v
23
.i
2
.
pp
953
-
9
6
1
953
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs.ia
esco
r
e.
co
m
Intrusio
n
d
e
tect
io
n sy
stem ba
sed o
n ma
chine l
ea
r
n
i
ng
techniqu
es
M
us
a
a
b Riy
a
dh
,
Di
na
Ria
dh
Als
hib
a
n
i
Dep
ar
tem
en
t Co
m
p
u
ter
Scien
ce
,
C
o
lleg
e
o
f
Scien
ce
,
Mu
s
ta
n
s
ir
iy
ah
Un
iv
er
s
ity
,
I
r
aq
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Oct
8
,
2
0
2
0
R
ev
is
ed
J
u
n
29
,
2
0
2
1
Acc
ep
ted
J
u
l 7
,
2
0
2
1
Re
c
e
n
tl
y
,
t
h
e
d
a
ta
flo
w
o
v
e
r
t
h
e
in
tern
e
t
h
a
s
e
x
p
o
n
e
n
ti
a
ll
y
i
n
c
re
a
se
d
d
u
e
to
th
e
m
a
ss
iv
e
g
ro
wth
o
f
c
o
m
p
u
ter
n
e
two
rk
s c
o
n
n
e
c
ted
to
it
.
S
o
m
e
o
f
th
e
se
d
a
ta
c
a
n
b
e
c
las
sified
a
s
a
m
a
li
c
io
u
s
a
c
ti
v
it
y
wh
ich
c
a
n
n
o
t
b
e
c
a
p
tu
re
d
b
y
firew
a
ll
s
a
n
d
a
n
ti
-
m
a
lwa
re
s.
Du
e
to
th
is,
t
h
e
i
n
tru
si
o
n
d
e
tec
ti
o
n
s
y
ste
m
s
a
re
u
rg
e
n
t
n
e
e
d
in
o
rd
e
r
t
o
re
c
o
g
n
ize
m
a
li
c
io
u
s a
c
ti
v
it
y
to
k
e
e
p
d
a
ta i
n
t
e
g
rit
y
a
n
d
a
v
a
il
a
b
il
it
y
.
I
n
t
h
is
stu
d
y
,
a
n
in
tru
sio
n
d
e
tec
ti
o
n
s
y
ste
m
b
a
se
d
o
n
c
l
u
ste
r
fe
a
tu
re
c
o
n
c
e
p
ts an
d
KN
N cla
ss
if
ier h
a
s b
e
e
n
su
g
g
e
ste
d
to
h
a
n
d
le t
h
e
v
a
rio
u
s
c
h
a
ll
e
n
g
e
s
issu
e
s
in
d
a
ta
su
c
h
a
s
in
c
o
m
p
lete
d
a
ta,
m
ix
e
d
-
ty
p
e
,
a
n
d
n
o
ise
d
a
ta.
To
stre
n
g
t
h
e
n
t
h
e
p
ro
p
o
se
d
sy
ste
m
a
sp
e
c
ial
k
in
d
o
f
p
a
tt
e
rn
s
sim
il
a
rit
y
m
e
a
su
re
s
a
re
su
p
p
o
rted
t
o
d
e
a
l
with
th
e
se
ty
p
e
s
o
f
c
h
a
ll
e
n
g
e
s.
Th
e
e
x
p
e
rime
n
tal
re
s
u
lt
s
sh
o
w
t
h
a
t
t
h
e
c
las
sifica
ti
o
n
a
c
c
u
ra
c
y
o
f
th
e
su
g
g
e
ste
d
sy
ste
m
is
b
e
tt
e
r
th
a
n
K
-
n
e
a
re
st
n
e
ig
h
b
o
r
(KN
N)
a
n
d
su
p
p
o
r
t
v
e
c
t
o
r
m
a
c
h
in
e
c
las
sifiers
wh
e
n
p
r
o
c
e
ss
in
g
in
c
o
m
p
lete
d
a
ta
se
t,
in
s
p
it
e
o
f
d
ro
p
in
g
d
o
wn
t
h
e
o
v
e
ra
ll
d
e
tec
ti
o
n
a
c
c
u
ra
c
y
.
K
ey
w
o
r
d
s
:
C
lu
s
te
r
f
ea
tu
r
e
I
n
co
m
p
lete
d
ata
I
n
tr
u
s
io
n
d
etec
tio
n
s
y
s
tem
KNN
L
o
o
s
e
clu
s
ter
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
:
Mu
s
aa
b
R
iy
ad
h
Dep
ar
tm
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
Mu
s
tan
s
ir
iy
ah
Un
iv
er
s
ity
Palest
in
e
s
tr
ee
t,
B
ag
h
d
ad
,
I
r
aq
E
m
ail: m
.
s
h
aib
an
i@
u
o
m
u
s
tan
s
ir
iy
ah
.
ed
u
.
iq
1.
I
NT
RO
D
UCT
I
O
N
C
y
b
er
attac
k
s
h
av
e
ex
p
o
n
e
n
t
ially
in
cr
ea
s
ed
o
v
er
th
e
p
ast
d
ec
ad
e;
th
ese
attac
k
s
aim
t
o
s
teal
th
e
in
tellectu
al
p
r
o
p
er
ty
o
f
o
r
g
a
n
izatio
n
an
d
d
is
r
u
p
t
th
eir
r
eso
u
r
es
an
d
in
f
r
a
-
s
tr
u
ctu
r
e
[
1
]
-
[
3
]
.
So
m
e
o
f
th
ese
attac
k
s
ar
e
in
s
id
io
u
s
a
n
d
ca
n
n
o
t
b
e
d
etec
ted
b
y
f
ir
ewa
lls
an
d
an
t
im
alwa
r
es.
T
h
er
ef
o
r
e,
a
n
ad
d
itio
n
al
s
ec
u
r
ity
d
ef
en
s
iv
e
lin
e
s
u
ch
as
an
I
n
tr
u
s
io
n
d
etec
tio
n
s
y
s
tem
s
I
DS
a
r
e
r
eq
u
ir
ed
to
e
f
f
ec
tiv
ely
m
o
n
ito
r
th
e
a
ctiv
ities
o
f
th
e
n
etwo
r
k
i
n
o
r
d
er
to
ca
p
tu
r
e
in
s
id
io
u
s
attac
k
s
[
4
]
.
T
h
e
i
n
tr
u
s
io
n
d
etec
tio
n
s
y
s
tem
s
I
DS
ca
n
b
e
cl
ass
if
ied
in
to
two
m
ai
n
ap
p
r
o
ac
h
es:
s
ig
n
atu
r
e
-
b
ased
(
SID
S)
an
d
an
o
m
aly
-
b
ased
(
AI
DS)
ap
p
r
o
ac
h
s
.
T
h
e
m
ain
c
o
n
ce
p
t
o
f
SID
S
is
to
co
m
p
ar
e
th
e
s
ig
n
atu
r
e
o
f
c
u
r
r
en
t
ac
tiv
ity
ag
ai
n
s
t
a
lis
t
o
f
p
r
ev
io
u
s
ly
s
to
r
ed
in
tr
u
s
io
n
s
s
ig
n
atu
r
es
an
d
th
e
alar
m
is
tr
ig
g
e
r
ed
if
a
m
atch
is
f
o
u
n
d
.
Du
e
to
th
is
,
th
e
SID
S
ap
p
r
o
ac
h
is
h
ar
d
ly
d
et
ec
tin
g
a
n
ew
attac
k
wh
ich
h
as
n
o
p
r
ev
io
u
s
p
atter
n
in
th
e
d
atab
ase
th
at
r
ep
r
esen
t
s
th
e
m
ain
wea
k
p
o
in
t
o
f
th
is
ap
p
r
o
ac
h
[
5
]
.
I
n
t
h
e
AI
DS
wh
ich
is
th
e
f
o
cu
s
in
g
o
f
th
is
wo
r
k
,
a
m
o
d
el
f
o
r
th
e
n
o
r
m
al
b
eh
av
io
r
o
f
a
co
m
p
u
ter
s
y
s
tem
is
b
u
ild
b
ased
o
n
m
ac
h
in
e
lear
n
i
n
g
t
ec
h
n
iq
u
es,
a
n
y
r
em
ar
k
ab
le
d
ev
iatio
n
b
etwe
en
th
e
m
o
d
el
an
d
th
e
o
b
s
er
v
ed
b
eh
av
io
r
ca
n
b
e
co
n
s
id
er
e
d
a
s
an
in
tr
u
s
io
n
[
6
]
.
I
n
co
n
tr
a
r
y
with
SID
S
ap
p
r
o
ac
h
,
th
e
u
p
d
ate
o
n
d
ata
is
n
o
t
r
eq
u
ir
ed
to
d
etec
t n
ew
attac
k
s
.
Ma
n
y
r
esear
ch
er
s
s
u
g
g
ested
AI
DS b
ased
o
n
s
in
g
le
m
ac
h
in
e
lear
in
g
tech
n
iq
u
es
s
u
ch
as
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
i
n
e
(
SVM
)
[
7
]
,
[
8
]
,
th
e
KNN
alg
o
r
ith
m
[
9
]
,
[
1
0
]
,
an
d
d
ec
is
io
n
tr
ee
s
[
1
1
]
,
[
1
2
]
.
T
h
e
SVM
an
d
KNN
class
if
ier
s
ar
e
p
o
o
r
ly
p
er
f
o
r
m
ed
with
n
o
is
y
an
d
b
ig
d
ata,
wh
ile
d
ec
is
io
n
tr
ee
is
a
tim
e
-
co
n
s
u
m
in
g
class
if
ier
esp
ec
ially
in
tr
ain
in
g
p
h
ase.
T
h
e
B
ay
e
s
ian
Naïv
e
is
also
s
u
g
g
ested
in
[
1
3
]
,
h
o
wev
er
th
is
p
r
o
b
a
b
ilis
tic
clas
s
if
ier
is
n
o
t
co
n
v
en
ien
t
f
o
r
r
ea
l
tim
e
d
ata
th
at
ar
e
g
en
er
ated
with
h
ig
h
s
p
ee
d
.
Oth
er
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.
23
,
No
.
2
,
Au
g
u
s
t
20
21
:
953
-
9
6
1
954
r
esear
ch
er
s
p
r
o
p
o
s
ed
I
DS
b
a
s
ed
o
n
h
y
b
r
id
tech
n
iq
u
es
s
u
ch
as
Z
am
an
i
an
d
Mo
v
a
h
ed
i
[
1
4
]
s
u
g
g
ested
an
ac
cu
r
ate
h
y
b
r
id
tech
n
iq
u
e
b
ased
o
n
th
e
g
au
s
s
ian
m
ix
tu
r
e
m
o
d
el
(
GM
M
)
an
d
K
-
m
ea
n
s
cl
u
s
ter
in
g
alg
o
r
ith
m
an
d
r
an
d
o
m
f
o
r
est
class
if
icati
o
n
tech
n
iq
u
e
.
Saleh
et
a
l
.
[
1
5
]
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
tem
d
ep
en
d
e
d
o
n
p
r
io
r
itized
K
-
n
e
ar
est
n
eig
h
b
o
r
s
an
d
o
p
tim
ized
s
u
p
p
o
r
t
v
ec
t
o
r
m
ac
h
i
n
e
SVM
class
if
ier
s
b
u
t
th
is
s
y
s
tem
is
n
o
t c
o
n
v
en
ien
t f
o
r
m
as
s
iv
e
d
ata
with
h
ig
h
d
im
en
s
io
n
s
.
A
h
y
b
r
id
r
ea
l tim
e
I
DS
in
[
1
6
]
was p
r
o
p
o
s
ed
d
ep
en
d
i
n
g
o
n
two
n
eu
r
al
n
etw
o
r
k
s
lay
er
s
,
th
e
f
ir
s
t
n
e
u
r
al
n
etwo
r
k
p
er
f
o
r
m
s
as
a
n
o
u
tlier
s
-
b
ased
d
etec
tio
n
f
o
r
an
o
n
y
m
o
u
s
attac
k
s
an
d
th
e
o
th
er
s
p
er
f
o
r
m
s
as
a
m
is
u
s
e
-
b
ased
d
etec
tio
n
f
o
r
an
o
n
y
m
o
u
s
attac
k
s
.
A
m
o
r
e
co
m
p
lex
m
u
lti
-
lev
el
I
DS
was
p
r
o
p
o
s
ed
b
y
Al
-
Yaseen
et
a
l
.
[
1
7
]
b
ased
o
n
SVM
an
d
ex
tr
em
e
lear
n
i
n
g
m
ac
h
in
e.
T
h
is
s
y
s
tem
s
ig
n
if
ic
an
tly
en
h
an
ce
d
th
e
d
etec
tio
n
ac
cu
r
ac
y
f
o
r
d
if
f
er
en
t
k
i
n
d
o
f
attac
k
s
;
h
o
wev
er
,
th
e
s
y
s
tem
was
b
u
ilt
f
o
r
s
p
ec
i
f
ic
d
ata
s
et
(
KDD
-
C
u
p
9
9
)
an
d
it
is
d
if
f
icu
lt
to
ap
p
ly
it
to
a
n
o
th
er
d
ata
s
et.
I
t
is
o
b
v
io
u
s
th
at
th
e
h
y
b
r
id
tech
n
iq
u
es
ar
e
m
o
r
e
ac
cu
r
ate
th
an
th
e
s
in
g
le
o
n
e
b
u
t
th
e
y
a
r
e
tim
e
co
n
s
u
m
in
g
tech
n
iq
u
es.
T
h
e
a
f
o
r
em
e
n
tio
n
ed
s
tu
d
u
es
h
av
e
f
o
c
u
s
ed
o
n
ly
o
n
en
h
a
n
cin
g
th
e
class
if
icati
o
n
ac
c
u
r
ac
y
o
f
th
e
in
tr
u
s
io
n
d
etec
tio
n
s
y
s
tem
an
d
d
id
n
o
t
ta
k
e
in
to
co
n
s
id
er
atio
n
th
e
ch
allen
g
i
n
g
is
s
u
es
in
d
at
a
s
et
s
u
ch
as
n
o
is
y
an
d
in
c
o
m
p
lete
d
ata.
B
esid
es
th
at,
th
e
y
u
s
ed
iter
ativ
e
an
d
co
m
p
lecta
ted
tr
ain
in
g
tech
n
i
q
es
wh
ich
m
ad
e
it
u
n
s
u
itab
le
f
o
r
m
ass
iv
e
an
d
in
c
r
em
en
tal
d
ata.
O
n
t
h
e
o
t
h
e
r
h
a
n
d
,
I
D
S
d
a
t
a
s
e
ts
h
a
v
e
v
a
r
i
o
u
s
c
h
a
l
l
e
n
g
e
s
s
u
c
h
a
s
m
i
x
e
d
-
t
y
p
e
,
h
i
g
h
d
i
m
e
n
s
i
o
n
a
l
i
t
y
,
a
n
d
n
o
i
s
y
d
a
t
a
t
h
a
t s
i
g
n
i
f
i
c
a
n
t
l
y
a
f
f
e
c
t
t
h
e
c
la
s
s
i
f
i
ca
t
i
o
n
a
c
c
u
r
a
c
y
.
T
h
e
s
e
c
h
al
l
e
n
g
es
m
u
s
t
b
e
t
a
k
en
i
n
t
o
c
o
n
s
i
d
e
r
a
ti
o
n
w
h
e
n
d
e
s
i
g
n
i
n
g
e
f
f
i
c
i
e
n
t
I
DS
[
1
8
]
,
[
1
9
]
.
Var
io
u
s
s
tu
d
ies
h
av
e
b
ee
n
co
n
d
u
cted
to
tac
k
le
th
ese
ch
allen
g
es:
th
e
s
tu
d
ies
in
[
2
0
]
,
[
2
1
]
tr
a
n
s
f
o
r
m
ed
n
d
im
en
s
io
n
al
d
at
a
o
f
m
ix
ed
-
ty
p
e
to
o
n
e
d
im
en
s
io
n
al
d
ata
an
d
class
if
ied
th
ese
d
ata
b
ased
o
n
KNN
an
d
SVM
class
if
ier
s
in
o
r
d
er
t
o
m
ax
im
ize
th
e
e
f
f
icien
cy
o
f
I
DS.
Ma
n
ju
n
ath
a
an
d
Go
g
o
i
[
2
2
]
p
r
o
p
o
s
ed
an
ef
f
icien
t
alg
o
r
ith
m
b
ased
o
n
en
h
a
n
cin
g
t
h
e
C
an
b
er
r
a
m
eth
o
d
an
d
m
in
im
u
m
th
r
esh
o
l
d
s
u
p
p
o
r
t
co
u
n
t
to
d
etec
t
in
tr
u
s
io
n
s
in
h
ig
h
-
d
im
e
n
s
io
n
ality
d
ata
s
et
th
at
co
n
s
is
ts
o
f
n
u
m
er
ical
a
n
d
ca
te
g
o
r
ical
f
ea
tu
r
es
.
O
t
h
e
r
s
t
u
d
i
es
h
a
v
e
f
o
c
u
s
e
d
o
n
t
h
e
e
f
f
e
c
t
s
o
f
n
o
i
s
e
i
n
t
h
e
p
e
r
f
o
r
m
a
n
c
e
o
f
I
D
S
.
T
h
e
w
o
r
k
s
i
n
[
1
8
]
,
[
2
3
]
e
l
i
m
i
n
at
e
t
h
e
n
o
i
s
y
p
at
t
e
r
n
s
b
a
s
e
d
o
n
t
h
e
d
e
n
s
i
t
y
-
b
as
e
d
s
p
a
t
i
a
l
c
l
u
s
t
e
r
i
n
g
o
f
a
p
p
l
i
c
a
t
i
o
n
s
wi
t
h
n
o
is
e
(
D
B
SC
A
N
)
c
l
u
s
t
e
r
i
n
g
a
l
g
o
r
i
t
h
m
i
n
o
r
d
e
r
t
o
e
n
h
a
n
c
e
t
h
e
cl
a
s
s
i
f
i
c
a
t
i
o
n
a
c
c
u
r
a
c
y
o
f
I
DS
.
B
h
o
s
a
le
e
t
a
l
.
[
2
4
]
s
u
g
g
es
t
e
d
a
n
o
i
s
e
r
e
m
o
v
al
a
l
g
o
r
it
h
m
t
o
e
n
h
a
n
c
e
t
h
e
c
la
s
s
i
f
ic
a
t
i
o
n
ac
c
u
r
ac
y
o
f
N
a
i
v
e
B
a
y
es
c
l
a
s
s
i
f
ie
r
h
o
w
e
v
e
r
,
i
t
i
s
a
t
im
e
-
c
o
n
s
u
m
i
n
g
c
l
a
s
s
i
f
ie
r
.
H
u
s
s
ai
n
an
d
L
a
l
m
u
a
n
a
w
m
a
[
2
5
]
p
r
o
v
e
d
t
h
a
t
s
e
l
f
o
r
g
a
n
i
z
a
t
i
o
n
m
a
p
h
as
b
e
t
te
r
i
n
t
r
u
s
i
o
n
d
e
t
ec
t
i
o
n
a
cc
u
r
a
c
y
i
n
n
o
i
s
e
d
a
t
a
t
h
a
n
wi
d
e
s
p
r
e
a
d
c
la
s
s
i
f
i
e
r
s
(
J
R
i
p
,
J
4
8
,
R
F
,
NB
T
r
e
e
)
d
es
p
i
t
e
o
f
t
h
e
lo
w
p
e
r
f
o
r
m
a
n
c
e
i
n
n
o
r
m
a
l
d
a
t
a
.
T
h
es
e
s
t
u
d
i
es
f
o
c
u
s
e
d
o
n
t
h
e
i
m
p
o
r
t
a
n
c
e
o
f
e
l
i
m
i
n
a
ti
n
g
n
o
i
s
e
t
o
e
n
h
a
n
c
e
th
e
c
l
a
s
s
i
f
i
c
at
i
o
n
a
c
c
u
r
a
c
y
.
H
o
w
e
v
e
r
,
t
h
e
s
es
s
t
u
d
i
e
s
s
u
p
p
o
r
t
e
d
s
i
m
i
l
a
r
i
t
y
m
e
a
s
u
r
es
s
u
c
h
a
s
E
u
c
l
i
d
e
a
n
d
i
s
t
a
n
c
e
wh
i
c
h
a
r
e
s
i
g
n
i
f
i
c
a
n
t
l
y
a
f
f
e
ct
e
d
w
h
e
n
u
s
i
n
g
i
n
c
o
m
p
l
e
t
e
d
a
t
a
.
T
a
b
l
e
1
s
h
o
w
s
a
c
o
m
p
a
r
t
i
o
n
b
e
t
w
e
e
n
t
h
e
r
e
l
a
ted
w
o
r
k
s
.
U
lt
i
m
a
t
el
y
,
a
n
i
n
t
r
u
s
i
o
n
d
e
t
e
c
t
i
o
n
h
as
b
e
e
n
p
r
o
p
o
s
e
d
i
n
t
h
i
s
s
t
u
d
y
t
o
h
a
n
d
l
e
v
a
r
i
o
u
s
c
h
a
ll
e
n
g
i
n
g
i
s
s
u
e
s
i
n
m
a
s
s
i
v
e
d
at
a
s
e
ts
s
u
ch
a
s
m
i
x
e
d
-
t
y
p
e
,
h
i
g
h
d
i
m
e
n
s
i
o
n
a
l
i
t
y
,
n
o
is
y
,
a
n
d
i
n
c
o
m
p
l
e
t
e
d
a
ta
.
T
o
t
h
e
b
es
t
o
f
o
u
r
k
n
o
w
l
e
d
g
e
t
h
e
r
e
a
r
e
n
o
s
tu
d
i
e
s
t
h
at
f
o
c
u
s
o
n
t
h
e
t
h
e
p
r
o
b
l
e
m
o
f
i
n
c
o
m
p
l
e
t
e
d
a
t
a
s
et
d
u
e
t
o
i
n
t
e
n
ti
o
n
a
l
o
r
u
n
i
n
t
e
n
d
e
d
e
r
r
o
r
s
i
n
c
o
l
le
c
t
i
n
g
d
at
a
w
h
i
c
h
is
t
h
e
m
ai
n
o
b
j
e
c
t
i
v
e
o
f
t
h
i
s
s
t
u
d
y
.
T
ab
le
1
.
R
elate
d
wo
r
k
s
c
o
m
p
a
r
s
io
n
W
o
r
k
Te
c
h
n
i
q
u
e
s
D
a
t
a
S
e
t
M
i
x
e
d
t
y
p
e
d
a
t
a
N
o
i
s
y
d
a
t
a
I
n
c
o
mp
l
e
t
e
d
a
t
a
Ev
a
l
u
a
t
i
o
n
met
h
o
d
S
a
l
e
h
e
t
a
l
.
[
1
5
]
G
M
M
a
n
d
K
-
mea
n
s
K
D
D
-
C
u
p
9
9
Y
e
s
No
No
AC
1
,
F
A
R
2
,
D
R
3
Al
-
Y
a
see
n
e
t
a
l
.
[
1
7
]
S
V
M
a
n
d
e
x
t
r
e
me
l
e
a
r
n
i
n
g
ma
c
h
i
n
e
O
n
l
y
K
D
D
-
C
u
p
9
9
Y
e
s
N
o
N
o
D
R
,
A
C
,
F
A
R
D
o
n
g
e
t
a
l
.
[
1
8
]
K
-
me
a
n
s
+
D
B
S
C
A
N
N
S
L
-
K
D
D
Y
e
s
Y
e
s
No
A
C
,
P
r
e
c
i
s
i
o
n
C
h
e
n
e
t
a
l
.
[
1
9
]
D
B
S
C
A
N
D
A
R
P
A
Y
e
s
Y
e
s
No
TD
R
4
,
F
D
R
5
G
u
o
e
t
a
l
.
[
2
0
]
S
V
M
K
D
D
-
C
u
p
9
9
D
R
,
R
O
C
6
Li
n
e
t
a
l
.
[
2
1
]
K
-
me
a
n
s
+
K
N
N
K
D
D
-
C
u
p
9
9
Y
e
s
No
No
AC
M
a
n
j
u
n
a
t
h
a
e
t
a
l
.
[
2
2
]
C
a
n
b
e
r
r
a
m
e
t
h
o
d
a
n
d
M
TSC
7
K
D
D
-
C
u
p
9
9
Y
e
s
No
No
AC
S
h
a
k
y
a
e
t
a
l
.
[
2
3
]
K
-
me
a
n
s
+
D
B
S
C
A
N
+
S
M
O
8
K
D
D
-
C
u
p
9
9
Y
e
s
Y
e
s
No
AC
B
h
o
sa
l
e
e
t
a
l
.
[
2
4
]
N
a
i
v
e
B
a
y
e
s
K
D
D
-
C
u
p
9
9
Y
e
s
Y
e
s
No
A
C
,
P
r
e
c
i
s
i
o
n
H
u
ssa
i
n
e
t
a
l
.
[
2
5
]
N
N
(
S
O
M
9
)
K
D
D
-
C
u
p
9
9
&
N
S
L
-
K
D
D
3
Y
e
s
Y
e
s
No
A
C
,
TP
R
10
,
FPR
11
,
R
O
C
1
A
cc
u
ra
cy
2
F
al
s
e
A
l
ar
m
Rat
e
3
D
et
e
ct
i
o
n
Ra
t
e
4
T
r
u
e
D
e
t
ec
t
i
o
n
R
at
e
5
F
al
s
e
D
et
ect
i
o
n
Ra
t
e
6
Rec
ei
v
er
O
p
era
t
i
n
g
Ch
arac
t
er
i
s
t
i
c
7
M
i
n
i
mu
m
T
h
re
s
h
o
l
d
S
u
p
p
o
r
t
Co
u
n
t
8
S
eq
u
e
n
t
i
a
l
Mi
n
i
ma
l
O
p
t
i
mi
zat
i
o
n
9
Se
l
f
-
O
r
g
a
n
i
zi
n
g
Ma
p
10
T
r
u
e
P
o
s
i
t
i
v
e
Ra
t
e
11
Fal
s
e
Po
s
i
t
i
v
e
Ra
t
e
2.
DIS
S
I
M
I
L
ARI
T
Y
M
E
A
SU
RE
T
h
e
d
is
tan
ce
(
d
is
s
im
ilar
ity
)
b
etwe
en
a
p
air
of
p
atter
n
s
is
a
n
ess
en
tial
ta
s
k
to
ev
alu
ate
h
o
w
alik
e
o
r
u
n
alik
e
p
atter
n
s
ar
e
in
co
m
p
a
r
is
o
n
to
o
n
e
an
o
th
er
.
I
t
is
th
e
e
s
s
en
ce
o
f
d
if
f
er
en
t
m
ac
h
in
e
le
ar
n
in
g
ap
p
licaio
n
s
s
u
ch
as
clu
s
ter
in
g
an
d
class
if
icatio
n
wh
ich
r
em
a
r
k
ab
ly
af
f
e
cts
th
e
class
if
icatio
n
ac
cu
r
acy
[
2
6
]
,
[
2
7
].
Mo
s
t
o
f
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
I
n
tr
u
s
io
n
d
etec
tio
n
s
ystem
b
a
s
ed
o
n
ma
c
h
in
e
lea
r
n
in
g
tech
n
i
q
u
es
(
Mu
s
a
a
b
R
iy
a
d
h
)
955
th
e
ex
is
tin
g
s
tu
d
ies
s
u
p
p
o
r
t
e
u
cli
d
ea
n
d
is
tan
ce
(
ED
)
to
m
e
asu
r
e
th
e
d
is
s
im
ilar
ity
b
etwe
en
two
p
atter
n
s
o
f
m
ix
in
g
attr
ib
u
te
s
(
e.
g
.
b
in
ar
y
;
n
o
m
in
al;
o
r
d
in
al;
an
d
n
u
m
e
r
ic)
,
h
o
wev
er
E
D
is
s
en
s
itiv
e
t
o
in
co
m
p
lete
d
ata.
T
h
er
ef
o
r
e,
a
s
p
ec
ial
k
in
d
o
f
d
is
s
im
ilar
ty
m
ea
s
u
r
e
h
as
b
ee
n
em
p
lo
y
ed
in
th
is
s
tu
d
y
t
o
p
r
o
ce
s
s
th
e
m
ix
ed
-
ty
p
e
attr
ib
u
tes th
at
h
av
e
m
is
s
i
n
g
v
a
lu
es f
o
r
s
o
m
e
attr
ib
u
tes
[2
8
]
a
s
d
ef
in
ed
in
(
1
)
.
(
,
)
=
∑
µ
=
1
∑
µ
=
1
(
1
)
W
h
er
e
d
is
t
(p
i
,p
j
)
is
th
e
d
is
m
i
lar
ity
m
ea
s
u
r
e
b
etwe
en
p
atter
n
s
p
i
,
p
j
an
d
N
r
ep
r
esen
ts
th
e
n
u
m
b
er
o
f
attr
ib
u
tes in
ea
ch
p
atter
n
,
an
d
th
e
p
ar
am
eter
µ
=0
eith
er
:
-
I
f
th
er
e
is
n
o
m
ea
s
u
r
m
e
n
ts
o
f
attr
ib
u
te
A
o
f
p
atter
n
s
p
i
o
r
p
j
.
-
If
A
is
asy
m
m
etr
ic
b
in
ar
y
attr
i
b
u
te
an
d
p
i
A
=0
,
p
j
A
=0
.
-
Oth
er
wis
e,
µ
=
1
.
T
h
e
co
n
tr
i
b
u
tio
n
o
f
attr
i
b
u
te
A
to
th
e
d
is
tan
ce
(
d
is
s
im
ilar
it
y
)
b
etwe
en
p
i
an
d
p
j
is
ca
lcu
lated
b
ased
o
n
its
ty
p
e:
-
If
attr
ib
u
te
A
is
a
n
u
m
er
ic
ty
p
e:
d
is
t
A
p
i,
pj
=
|
x
p
i
A
–
x
pj
A
|
/(
M
ax
A
-
Min
A
),
wh
er
e
m
ax
A
a
n
d
m
in
A
a
r
e
th
e
m
ax
im
u
m
a
n
d
m
in
im
u
m
v
al
u
es o
f
th
e
attr
ib
u
te
A
o
v
er
all
th
e
n
o
n
e
m
is
s
in
g
v
alu
es
.
-
I
f
attr
ib
u
te
A
is
a
n
o
m
in
al
ty
p
e
o
r
b
in
a
r
y
:
d
is
t
A
p
i,
pj
=
0
if
p
i
A
=
p
j
A
; o
th
er
wis
e,
d
is
t
A
p
i,
pj
=
1
.
-
I
f
attr
ib
u
te
A
is
o
r
d
in
al
ty
p
e:
c
o
n
v
er
t th
e
r
an
k
o
f
attr
i
b
u
tes
r
pi
A
an
d
r
p
j
A
to
z
p
i
A
a
n
d
z
pj
A
as g
i
v
en
in
(
2
)
.
z
p
A
=
(
r
p
A
−1
)
/
(
M
A
−1
)
(
2
)
W
h
er
e
M
A
is
th
e
p
o
s
s
ib
le
s
tates
n
u
m
b
e
r
th
at
an
o
r
d
i
n
al
attr
i
b
u
te
ca
n
h
a
v
e.
T
h
en
co
m
p
u
te
th
e
d
is
s
im
ilar
ity
as
d
ef
in
ed
in
(
3
)
:
dist
A
pi, pj
=
|z
pi
A
–
z
pj
A
|
(
3
)
Fin
ally
,
th
e
s
u
p
p
o
r
ted
s
im
ilar
ity
m
ea
s
u
r
e
c
o
m
b
in
es
th
e
v
ar
i
o
u
s
attr
ib
u
tes
in
to
a
s
in
g
le
d
is
s
im
ilar
ity
m
ea
s
u
r
e
o
n
to
a
co
m
m
o
n
s
ca
le
o
f
th
e
in
te
r
v
al
[
0
.
0
,
1
.
0
]
.
3.
T
H
E
R
E
S
E
ARCH
M
E
T
H
O
D
T
h
e
m
ain
o
b
jectiv
e
o
f
th
is
s
tu
d
y
is
to
d
esig
n
an
i
n
tr
u
s
io
n
d
etec
tio
n
s
y
s
tem
f
o
r
th
e
in
c
o
m
p
lete
d
ata
(
I
DS
-
I
D)
class
if
ier
b
ased
o
n
h
y
b
r
id
m
ac
h
in
e
lear
n
in
g
tech
n
iq
u
es
th
at
ar
e
ca
p
ab
le
to
d
e
al
with
in
co
m
p
lete
d
ata
s
et
alo
n
g
with
th
e
o
th
er
ch
allen
g
es
s
u
ch
as
m
ix
ed
-
ty
p
e
an
d
n
o
is
e
d
ata
s
et.
T
h
e
p
r
o
p
o
s
ed
class
if
ier
I
DS
-
I
D
co
n
s
is
ts
o
f
two
p
h
ases
: th
e
tr
ain
in
g
p
h
ase
an
d
t
h
e
test
in
g
p
h
ase.
T
h
e
tr
ain
in
g
p
h
ase
aim
s
to
clu
s
ter
th
e
d
ata
b
as
ed
o
n
t
h
e
n
o
tio
n
o
f
clu
s
ter
f
ea
tu
r
es
C
Fs
,
wh
en
th
e
en
tir
e
s
ize
o
f
C
Fs
ex
ce
ed
s
a
g
iv
en
m
em
o
r
y
s
p
ac
e
th
e
m
o
s
t
s
im
ilar
C
Fs
is
m
er
g
ed
.
W
h
ile
,
th
e
KNN
cla
s
s
if
ier
h
as
b
ee
n
s
u
p
p
o
r
te
d
in
th
e
test
in
g
p
h
ase.
Fin
ally
,
5
0
%
o
f
th
e
d
ata
s
et
is
u
s
ed
f
o
r
tr
ain
in
g
p
h
ase
an
d
5
0
% f
o
r
test
in
g
p
h
ase
as illu
s
tr
ated
in
Fig
u
r
e
1
.
Fig
u
r
e
1
.
T
h
e
I
DS
-
I
D
p
h
ases
3
.1
.
T
he
t
ra
ini
ng
ph
a
s
e
T
h
e
tr
ain
in
g
p
h
ase
o
f
th
is
s
tu
d
y
is
m
ain
ly
b
ased
o
n
th
e
n
o
ti
o
n
o
f
clu
s
ter
f
ea
tu
r
es
C
F
d
u
e
to
its
g
o
o
d
s
p
ee
d
an
d
s
ca
lab
ilit
y
in
m
ass
iv
e
o
r
ev
en
s
tr
ea
m
in
g
d
atab
ases
.
I
t
co
n
s
is
ts
o
f
two
lev
els:
i)
th
e
co
n
s
tr
u
ctio
n
o
f
clu
s
ter
s
an
d
C
F
s
an
d
ii)
t
h
e
m
er
g
in
g
o
f
cl
u
s
ter
s
an
d
C
Fs
.
T
h
e
f
ir
s
t
lev
el
s
to
r
es
s
u
m
m
ar
izin
g
in
f
o
r
m
atio
n
ab
o
u
t
ea
ch
clu
s
ter
in
C
F
d
ata
s
tr
u
ctu
r
e
an
d
u
p
d
ate
th
is
in
f
o
r
m
atio
n
o
n
ce
a
n
ew
p
atter
n
is
ad
d
ed
to
th
e
clu
s
ter
e.
g
th
e
C
F
i
o
f
clu
s
ter
C
i
i
s
(
N,
L
s
1
,
Ss
1
,
L
s
2
,
Ss
2
,
….
,
L
s
m
,
S
s
m
)
wh
er
e
N
r
ep
r
esen
ts
th
e
n
u
m
b
er
o
f
p
atter
n
s
in
th
e
clu
s
ter
,
m
is
th
e
n
u
m
b
er
o
f
f
ea
tu
r
es
in
ea
ch
p
atter
n
an
d
L
s
m
,
Ss
m
r
ep
r
esen
t
th
e
lin
ea
r
s
u
m
an
d
s
q
u
ar
e
s
u
m
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.
23
,
No
.
2
,
Au
g
u
s
t
20
21
:
953
-
9
6
1
956
o
f
f
ea
tu
r
e
m
f
o
r
all
p
atter
n
s
in
C
i
.
At
th
e
en
d
o
f
th
e
co
n
s
tr
u
ctio
n
lev
el,
th
e
cl
u
s
ter
s
th
at
h
av
e
p
atter
n
s
l
ess
th
an
I
tem
min
th
r
esh
o
ld
will
b
e
d
is
ca
r
d
im
m
ed
iately
s
in
ce
th
ey
ar
e
n
o
is
e
d
ata.
I
n
th
e
m
er
g
in
g
lev
el,
th
e
m
o
s
t
s
im
ila
r
clu
s
t
er
s
ar
e
m
er
g
e
d
as
d
e
f
in
ed
in
(
4
)
.
T
h
e
m
e
r
g
in
g
task
is
b
a
s
ed
o
n
a
d
is
s
im
ilar
ity
m
ea
s
u
r
e
th
at
f
in
d
a
t
y
p
ical
tr
ad
e
-
o
f
f
b
etwe
en
cl
u
s
t
er
s
d
en
s
ity
an
d
th
e
d
is
tan
ce
b
etwe
en
th
eir
ce
n
te
r
s
as
d
ef
in
ed
in
(
5
)
.
N
o
te
th
at,
th
e
m
er
g
in
g
le
v
el
is
ac
tiv
ated
wh
e
n
th
e
last
p
atter
n
in
t
h
e
d
ata
s
e
t is p
r
o
ce
s
s
ed
.
Me
r
g
e
(
CF
i
,
C
F
j
)
=
(
N
i
+N
j
, LS
i
1
+L
S
j
1
,
SS
i
2
+S
S
j
2
….
,
LS
i
m
+L
S
j
m
,
SS
i
m
+S
S
j
m
)
(
4
)
Dis
tan
ce
(
C
i
, C
j
)
=
|
C
ceni
-
C
ce
nj
|
-
0
.
5
(
C
Di
+ C
Dj
)
(
5
)
W
h
er
e
C
ceni
,
C
cenj
ar
e
t
h
e
ce
n
ter
o
f
clu
s
ter
s
C
i
an
d
C
j
,
an
d
C
Di
,
C
Dj
r
ep
r
esen
t
th
e
clu
s
ter
s
d
en
s
ity
a
n
d
ca
n
co
m
p
u
te
f
r
o
m
CF
i
,
C
F
j
p
ar
am
eter
s
b
ased
o
n
(
6
)
an
d
(
7
)
.
C
cen
=
L
S/N
(
6
)
C
D
=
√
2
∗
∗
−
2
∗
(
−
1
)
(
7
)
I
t
is
o
b
v
io
u
s
th
at
(
5
)
g
iv
e
s
a
p
r
io
r
ity
to
m
er
g
i
n
g
two
lo
o
s
e
cl
u
s
ter
s
to
g
eth
er
r
ath
er
t
h
an
m
er
g
in
g
tig
h
t
clu
s
ter
s
if
th
e
d
is
tan
ce
b
etwe
en
th
eir
ce
n
ter
s
is
ap
p
r
o
x
im
ate
ly
eq
u
als.
T
h
is
is
b
ec
au
s
e,
th
e
m
er
g
in
g
two
tig
h
t
clu
s
ter
s
will
b
r
ea
k
th
eir
tig
h
t
n
ess
as
illu
s
tr
ated
in
Fig
u
r
e
s
2
(
a)
an
d
(
b
)
.
T
h
e
cl
u
s
ter
s
’
m
er
g
in
g
p
r
o
ce
s
s
is
co
n
tin
u
ed
till
th
e
n
u
m
b
er
o
f
clu
s
ter
s
in
th
e
tr
ain
in
g
p
h
ase
b
ec
o
m
es
eq
u
al
to
f
iv
e.
T
h
is
d
u
e
to
,
th
e
KDD
-
C
u
p
9
9
d
ata
ar
e
tag
g
e
d
with
5
d
if
f
er
en
t
lab
els
.
T
h
e
m
ain
s
t
ep
s
o
f
tr
ain
in
g
p
h
ase
ar
e
illu
s
tr
ated
in
Fig
u
r
e
3
.
Fin
ally
,
T
h
e
C
Fs
tech
n
iq
u
e
h
a
s
b
ee
n
c
h
o
s
en
f
o
r
th
is
lev
el
d
u
e
to
th
eir
ab
ilit
y
t
o
clu
s
ter
h
ig
h
d
im
en
s
io
n
al
d
ata
with
a
s
in
g
le
p
ass
o
v
er
th
e
d
at
a
wh
ich
lead
to
s
ig
n
i
f
ican
tly
m
in
im
ize
th
e
r
u
n
n
in
g
tim
e
o
f
t
h
e
tr
ain
in
g
p
h
ase.
(
a)
(
b
)
Fig
u
r
e
2
.
Me
r
g
in
g
cl
u
s
ter
s
;
(
a
)
m
er
g
in
g
tig
h
t c
lu
s
ter
an
d
(
b
)
m
er
g
in
g
l
o
o
s
e
clu
s
ter
Fig
u
r
e
3
.
T
h
e
tr
ain
in
g
p
h
ase
o
f
I
DS
-
I
D
class
if
ier
3
.
2
.
T
he
t
esting
ph
a
s
e
T
h
e
s
ec
o
n
d
p
h
ase
o
f
th
e
I
DS
-
I
D
s
y
s
tem
is
th
e
test
in
g
p
h
ase,
it
aim
s
to
class
if
y
th
e
test
in
g
d
ata
b
ased
o
n
th
e
k
-
n
ea
r
est
n
eig
h
b
o
r
s
(
K
NN)
alg
o
r
ith
m
.
T
h
e
KNN
cla
s
s
if
ier
h
as
b
ee
n
u
tili
ze
d
in
th
is
p
h
ase
d
u
e
to
its
lo
w
co
m
p
u
tatio
n
co
s
t,
f
ew
p
a
r
am
eter
s
,
an
d
class
if
y
th
e
d
at
a
b
ased
o
n
n
o
n
-
lin
ea
r
d
ec
is
io
n
b
o
u
n
d
a
r
ies.
T
h
e
k
ey
n
o
tio
n
b
eh
i
n
d
th
e
KNN
class
if
ier
is
th
at,
f
o
r
ev
er
y
p
a
tter
n
in
th
e
tr
ai
n
in
g
s
et,
if
m
o
s
t
o
f
its
n
ea
r
est
n
eig
h
b
o
r
p
atter
n
s
b
elo
n
g
to
a
clu
s
ter
C
i
,
th
en
th
e
p
atter
n
b
el
o
n
g
s
to
th
e
C
i
clu
s
ter
[
9
]
.
T
h
e
KNN
class
if
ier
in
th
is
p
h
ase
h
as u
s
ed
5
0
% o
f
t
h
e
KDD
-
C
u
p
9
9
to
test
th
e
class
if
icatio
n
ac
cu
r
ac
y
o
f
t
h
e
I
DS
-
I
D
class
if
ier
.
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
I
n
tr
u
s
io
n
d
etec
tio
n
s
ystem
b
a
s
ed
o
n
ma
c
h
in
e
lea
r
n
in
g
tech
n
i
q
u
es
(
Mu
s
a
a
b
R
iy
a
d
h
)
957
4.
RE
SU
L
T
S
A
ND
D
IS
CU
SS
I
O
N
T
h
e
KDD
-
C
u
p
9
9
d
ata
s
et
is
u
s
ed
in
th
is
wo
r
k
t
o
tr
ain
an
d
test
th
e
class
if
ier
s
I
DS
-
I
D,
KNN
,
an
d
SVM
in
o
r
d
er
t
o
ev
alu
ate
t
h
e
ir
p
er
f
o
r
m
an
ce
,
it
was
cr
ea
ted
an
d
m
an
ag
e
d
b
y
DARP
A
b
ased
o
n
th
e
o
r
g
i
n
al
d
ata
s
et
f
r
o
m
MI
T
L
in
co
l
n
L
a
b
o
r
ato
r
ies
to
e
v
alu
ate
th
e
r
esear
ch
s
o
n
a
n
in
tr
u
s
io
n
d
etec
tio
n
s
y
s
tem
s
.
T
h
e
d
ata
s
et
co
n
tain
s
4
9
4
,
0
2
0
r
ec
o
r
d
s
an
d
ea
c
h
r
ec
o
r
d
h
as
4
1
d
i
m
en
s
io
n
s
o
f
v
ar
io
u
s
ty
p
es
(
b
in
ar
y
,
n
o
m
in
al,
an
d
n
u
m
er
ic)
.
T
h
ese
d
im
en
s
io
n
s
r
ep
r
esen
t
th
e
n
etwo
r
k
c
o
n
ec
tio
n
s
an
d
ca
n
b
e
ca
teg
o
r
ized
in
to
th
r
ee
m
ain
class
es:
th
e
tr
af
f
ic
f
lo
w
(
1
9
d
im
en
s
io
n
s
)
,
th
e
in
tr
in
s
ic
ty
p
es
(
9
d
i
m
en
s
io
n
s
)
,
an
d
th
e
c
o
n
ten
t
ty
p
e
(
1
3
d
i
m
en
s
io
n
s
)
.
T
ab
le
2
illu
s
tr
ate
s
a
s
m
all
s
a
m
p
le
o
f
th
ese
d
im
e
n
s
io
n
s
.
T
h
e
I
DS
-
ID
class
if
er
h
as
b
ee
n
im
p
lem
en
te
d
u
s
in
g
Ma
tlab
(
2
0
1
2
a)
o
n
in
tel
co
r
e
i
3
h
p
la
p
to
p
with
win
d
o
ws 7
o
p
r
atin
g
s
y
s
tem
.
T
ab
le
2
.
T
C
P c
o
n
ec
tio
n
a
ttrib
u
tes in
KDD
-
c
up99
d
ata
s
et
C
a
t
e
g
o
r
y
N
a
m
e
F
e
a
t
u
r
e
s N
a
mes
D
a
t
a
t
y
p
e
D
e
scri
p
t
i
o
n
B
a
si
c
A
t
t
r
i
b
u
t
e
s
D
u
r
a
t
i
o
n
I
n
t
e
g
e
r
c
o
n
n
e
c
t
i
o
n
t
i
me
(
sec
o
n
d
s)
P
r
o
t
o
c
o
l
t
y
p
e
N
o
mi
n
a
l
P
r
o
t
o
c
o
l
k
i
n
d
(
T
C
P
a
n
d
U
D
P
)
C
o
n
t
e
n
t
A
t
t
r
i
b
u
t
e
s
Lo
g
g
e
d
i
n
B
i
n
a
r
y
1
i
f
su
c
c
e
ss t
o
l
o
g
i
n
o
t
h
e
r
w
i
z
e
b
0
.
N
u
mb
e
r
o
f
u
n
s
u
c
c
e
ssf
u
l
L
o
g
i
n
s
I
n
t
e
r
g
e
r
N
u
mb
e
r
o
f
u
n
s
u
c
c
e
ssf
u
l
l
o
g
i
n
s
i
n
t
o
a
c
o
n
n
e
c
t
i
o
n
Tr
a
f
f
i
c
A
t
t
r
i
b
u
t
e
s
(
2
s
t
i
me
w
i
n
d
o
w
f
r
o
m
d
e
s
t
.
t
o
h
o
s
t
)
d
e
s
t
i
n
a
t
i
o
n
h
o
s
t
c
o
u
n
t
I
n
t
e
g
e
r
c
o
n
n
e
c
t
i
o
n
s Su
m t
o
t
h
e
s
a
me
d
e
st
i
n
a
t
i
o
n
I
P
a
d
d
r
e
ss
d
e
s
t
i
n
a
t
i
o
n
h
o
s
t
sa
me
sr
v
r
a
t
e
R
e
a
l
P
e
r
c
e
n
t
a
g
e
o
f
c
o
n
n
e
c
t
i
o
n
s
t
h
a
t
w
e
r
e
t
o
t
h
e
same
s
e
r
v
i
c
e
,
a
mo
n
g
t
h
e
c
o
n
n
e
c
t
i
o
n
s
a
g
g
r
e
g
a
t
e
d
i
n
t
o
d
e
st
i
n
a
t
i
o
n
h
o
st
c
o
u
n
t
(
P
3
2
)
No
te
th
at,
th
e
KDD
-
C
u
p
9
9
p
atter
n
s
ar
e
tag
e
d
with
f
iv
e
d
if
f
er
en
t
lab
els:
th
e
f
ir
s
t
o
n
e
r
ep
r
esen
ts
th
e
au
th
o
r
ized
ac
tiv
ites
an
d
th
e
o
t
h
er
f
o
u
r
lab
els r
ep
r
esen
t
f
o
u
r
k
in
d
s
o
f
attac
k
ac
tiv
ities
as
lis
ted
b
elo
w:
-
Den
ial
-
of
-
s
er
v
ice
(
Do
s
)
:
s
o
m
e
co
m
p
u
ter
r
eso
u
r
ce
s
ar
e
u
n
a
v
ailab
le
o
r
to
o
b
u
s
y
t
o
r
esp
o
n
s
e
to
le
g
itima
te
u
s
er
'
s
r
eq
u
ests
.
-
R
em
o
te
-
to
-
lo
ca
l
(
R
2
l)
:
u
n
a
u
th
o
r
ized
ac
ce
s
s
is
d
o
n
e
b
y
a
r
e
m
o
te
d
e
v
ice
i
n
o
r
d
er
to
d
etec
t
th
e
v
u
ln
er
ab
ilit
ies o
f
th
e
m
ac
h
in
e.
-
User
-
to
-
r
o
o
t
U2
r
:
an
u
n
au
t
h
o
r
ized
attac
k
tr
y
s
to
ac
ce
s
s
th
e
p
r
iv
ileg
es
o
f
lo
ca
l
s
u
p
er
u
s
er
(
r
o
o
t)
th
r
o
u
g
h
th
e
s
y
s
tem
v
u
ln
er
ab
ilit
ies.
-
Pro
b
e
Prb
: a
n
u
n
au
t
h
o
r
ized
attac
k
attem
p
t to
g
et
i
n
f
o
r
m
atio
n
ab
o
u
t th
e
tar
g
et
h
o
s
t to
f
in
d
v
u
ln
er
ab
ilit
ies.
4
.1
.
D
a
t
a
pre
-
pro
ce
s
s
ing
Pre
-
p
r
o
ce
s
s
in
g
is
a
cr
u
cial
s
tep
in
v
o
lv
e
d
wh
ile
d
ea
lin
g
with
d
ata
s
ets b
ef
o
r
e
u
s
in
g
it f
o
r
d
a
ta
an
aly
s
is
an
d
co
n
s
tr
u
ctio
n
class
if
ier
m
o
d
els.
Var
io
u
s
p
r
e
-
p
r
o
ce
s
s
in
g
s
tep
s
h
av
e
b
ee
n
d
o
n
e
in
t
h
is
s
tu
d
y
s
u
c
h
as:
f
ir
s
tly
,
elim
in
atin
g
d
u
p
licates
f
r
o
m
t
h
e
d
ataset.
Seco
n
d
l
y
,
m
ap
p
i
n
g
s
o
m
e
n
o
m
in
al
attr
i
b
u
tes
to
n
u
m
e
r
ic
-
v
alu
e
d
.
T
h
ir
d
ly
,
m
a
p
p
in
g
s
o
m
e
n
o
m
in
al
attr
ib
u
tes
(
e.
g
.
"p
r
o
to
c
o
l
"
an
d
“T
C
P
s
tatu
s
flag
”)
to
b
in
ar
y
attr
ib
u
tes.
Fin
ally
,
n
o
r
m
alizi
n
g
s
o
m
e
attr
ib
u
tes
s
in
ce
th
ey
h
av
e
d
if
f
er
en
t
s
ca
les
s
u
ch
as
"d
esti
n
atio
n
h
o
s
t
c
o
u
n
t”
wh
ich
h
as a
r
an
g
e
o
f
(
0
-
2
5
5
)
,
w
h
er
ea
s
“so
u
r
ce
b
y
tes” r
an
g
es
(
f
r
o
m
0
to
6
9
3
3
7
5
6
3
0
)
.
4
.2
.
P
a
ra
m
et
er
s
s
ens
it
iv
it
y
T
h
e
p
ar
am
eter
s
D
threshold
an
d
K
r
elate
d
to
KNN
class
if
ier
in
th
e
test
in
g
p
h
ase
ar
e
s
i
g
n
if
ican
tly
af
f
ec
tin
g
t
h
e
class
if
icatio
n
ac
c
u
r
ac
y
o
f
th
e
I
DS
-
I
D
class
if
ier
.
T
h
er
ef
o
r
e,
th
e
class
if
icatio
n
a
cc
u
r
ac
y
o
f
I
DS
-
I
D
h
as
b
ee
n
test
ed
f
o
r
d
if
f
er
en
t
v
alu
es
o
f
D
threshold
(
f
r
o
m
2
to
8
)
an
d
K
(
3
,
5
,
7
,
9
,
an
d
1
1
)
t
o
d
eter
m
in
e
th
e
v
alu
es
wh
ich
g
iv
e
th
e
h
ig
h
er
class
if
icatio
n
ac
cu
r
ac
y
f
o
r
th
e
I
DS
-
I
D
clas
s
if
ier
.
T
h
e
ex
p
er
im
en
ts
illu
s
tr
ate
th
at
th
e
b
est v
alu
es th
at
p
er
f
o
r
m
th
e
b
est cla
s
s
if
icatio
n
ac
cu
r
ac
y
(
9
8
.
4
9
)
ar
e
wh
e
n
D
threshold
=4
an
d
k
=5
as illu
s
tr
ated
in
T
ab
le
3
.
T
ab
le
3
.
T
h
e
ac
cu
r
ac
y
d
etec
ti
o
n
f
o
r
d
if
f
e
r
en
t v
al
u
es o
f
D
thres
hold
an
d
k
b
ased
o
n
s
elec
ted
2
0
d
im
en
s
io
n
s
D
t
hre
s
h
ol
d
K
=
3
K
=
5
K
=
7
K
=
9
K
=
1
1
2
9
7
.
6
9
7
.
4
9
9
6
.
5
9
5
.
5
6
9
7
.
8
4
9
6
.
7
8
9
8
.
4
9
9
6
.
4
9
5
.
4
0
9
6
.
7
0
6
9
5
.
7
0
9
7
.
9
0
9
6
.
1
0
9
5
.
3
5
9
6
.
2
5
8
9
5
.
6
0
9
7
.
6
5
9
5
.
9
1
9
4
,
9
0
9
6
.
1
4
4
.3
.
E
f
f
iciency
e
v
a
lua
t
io
n
T
h
e
ef
f
icien
cy
(
r
u
n
n
in
g
tim
e)
o
f
I
DS
-
I
D
class
if
ier
h
as
b
ee
n
c
o
m
p
ar
e
d
with
KNN
an
d
SVM
class
if
ier
s
b
ased
o
n
2
0
s
elec
te
d
d
im
e
n
s
io
n
s
as
illu
s
tr
ated
in
T
ab
le
4
.
T
h
e
co
m
p
ar
is
o
n
s
h
o
ws
th
at
th
e
r
u
n
n
i
n
g
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.
23
,
No
.
2
,
Au
g
u
s
t
20
21
:
953
-
9
6
1
958
tim
e
o
f
d
ata
p
r
e
-
p
r
o
ce
s
s
in
g
p
h
ase
f
o
r
I
DS
-
I
D
to
o
k
lo
n
g
er
tim
e
th
an
KNN.
Ho
wev
er
,
th
e
o
v
er
all
r
u
n
n
in
g
tim
e
f
o
r
I
DS
-
I
D
(
1
5
0
4
m
in
s
)
is
less
th
an
KNN
(
2
1
7
3
m
in
s
)
a
n
d
SVM
(
4
1
5
5
m
in
s
)
class
if
ier
s
s
in
ce
th
e
I
DS_
I
D
class
if
ier
is
b
ased
o
n
C
F c
o
n
ce
p
ts
wh
ich
s
ig
n
if
ican
tly
m
in
i
m
ize
th
e
r
u
n
n
in
g
tim
e
.
T
ab
le
4
.
T
h
e
r
u
n
n
in
g
tim
e
o
f
t
h
e
I
DS
-
I
D,
SVM
,
an
d
KNN
b
ased
o
n
s
elec
ted
2
0
d
im
en
s
io
n
s
D
a
t
a
p
r
e
p
r
o
c
e
ss
i
n
g
Tr
a
i
n
i
n
g
a
n
d
t
e
st
i
n
g
o
v
e
r
a
l
l
K
D
D
-
C
u
p
9
9
d
a
t
a
s
e
t
K
N
N
2
0
mi
n
s
2
1
5
3
m
i
n
s
2
1
7
3
m
i
n
s
S
V
M
-
4
1
5
5
m
i
n
s
4
1
5
5
m
i
n
s
I
D
S
-
ID
3
0
mi
n
s
1
5
0
4
m
i
n
s
1
5
0
4
m
i
n
s
4
.4
.
T
he
c
la
s
s
if
ica
t
io
n per
f
o
rm
a
nce
I
n
th
is
s
ec
tio
n
,
th
e
class
if
icati
o
n
ac
c
u
r
ac
y
o
f
th
e
I
DS
-
I
D
cla
s
s
if
ier
is
co
m
p
ar
ed
with
th
e
p
er
f
o
r
m
a
n
ce
o
f
KNN,
a
n
d
SVM
class
if
ier
s
b
ased
o
n
th
e
d
etec
tio
n
r
ate
(
DR
)
,
f
alse
p
o
s
itiv
e
r
ate
(
FR
)
,
a
n
d
ac
cu
r
ac
y
(
A)
[
3
]
.
T
h
ese
m
etice
s
ar
e
u
s
ed
b
y
t
h
e
m
o
s
t e
x
is
tin
g
s
tu
d
ies
an
d
d
ef
i
n
ed
in
(
8)
-
(
10
)
.
=
/
(
+
)
(
8
)
=
/
(
+
)
(
9
)
=
(
+
)
/
(
+
+
+
)
(
10
)
W
h
er
e
:
Fals
e
p
o
s
itiv
e
(
FP
)
is
th
e
n
o
r
m
al
p
atter
n
s
n
u
m
b
er
,
wh
ic
h
is
class
if
ied
as a
n
attac
k
in
s
tan
ce
s
.
Fals
e
n
eg
ativ
e
(
FN)
is
th
e
attac
k
s
p
atter
n
s
n
u
m
b
er
,
wh
ic
h
ar
e
class
if
ied
as
a
n
o
r
m
al
in
s
tan
ce
s
.
T
r
u
e
p
o
s
itiv
e
(
T
P)
is
th
e
d
etec
ted
attac
k
s
n
u
m
b
e
r
an
d
in
f
ac
t
th
ey
ar
e
attac
k
s
.
T
r
u
e
n
e
g
ativ
e
(
T
N)
is
th
e
d
etec
ted
n
o
r
m
al
i
n
s
tan
ce
s
n
u
m
b
e
r
an
d
in
f
ac
t t
h
ey
ar
e
n
o
r
m
al.
T
h
e
f
ir
s
t
s
tep
to
ev
alu
ate
t
h
e
p
er
f
o
r
m
an
ce
o
f
th
e
I
DS
-
I
D
cl
ass
if
ier
is
to
f
in
d
t
h
e
co
n
f
u
s
io
n
m
atr
ix
b
ased
o
n
th
e
KDD
-
C
u
p
9
9
as
elab
o
r
ate
in
T
a
b
le
5
.
I
t
is
o
b
v
io
u
s
th
at
(
9
8
.
49
%)
o
f
th
e
n
o
r
m
al
p
atter
n
s
ca
n
b
e
clas
s
if
ied
co
r
r
ec
tly
,
wh
ile
th
e
p
er
f
o
r
m
an
ce
o
f
I
DS
-
I
D
s
h
o
ws
a
lo
w
class
if
icatio
n
r
ate
to
war
d
U2
r
(
5
.
4
%)
a
n
d
R
2
l
(
6
.
4
6
%)
attac
k
s
.
I
n
a
d
d
iti
o
n
,
f
o
u
r
ex
p
er
im
en
ts
h
a
v
e
b
ee
n
d
o
n
e
t
o
ass
ess
th
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
I
DS
-
I
D,
KNN,
an
d
SVM
class
if
ier
s
b
ased
o
n
KDD
-
C
u
p
9
9
d
ata
s
et:
th
e
f
ir
s
t
ex
p
er
im
en
ts
u
s
ed
th
e
ac
tu
al
d
ata
with
o
u
t
an
y
ch
an
g
e.
T
h
e
f
in
al
r
esu
lts
s
h
o
ws
th
at
th
e
o
v
er
all
ac
cu
r
ac
y
o
f
I
DS
-
I
D
(
9
2
.
8
5
)
is
b
etter
th
an
KNN
(
9
1
.
5
3
)
,
an
d
SVM
(
9
2
.
2
5
)
as
illu
s
tr
ated
in
T
ab
le
6
.
Ho
we
v
er
,
th
e
d
if
f
ir
en
ce
b
etwe
en
th
e
class
if
icatio
n
ac
cu
r
ac
y
o
f
th
e
th
r
ee
class
if
ier
s
is
s
m
all.
T
ab
le
5
.
C
o
n
f
u
s
io
n
m
atr
ix
o
b
t
ain
ed
with
I
DS
-
I
D
f
o
r
th
e
fiv
e
class
es o
f
th
e
KDD
-
c
up99
N
o
r
mal
Prb
R
2
l
D
o
s
U
2
r
A
c
t
u
a
l
C
o
r
r
e
c
t
N
o
r
mal
5
9
5
8
7
5
9
8
80
1
4
5
88
6
0
4
9
8
9
8
.
4
9
%
Prb
4
1
5
3
6
4
0
21
79
5
4
1
6
0
8
7
.
5
%
R
2
l
1
5
0
0
3
81
1
0
5
5
23
52
1
6
2
1
4
6
.
4
6
%
D
o
s
4
3
5
0
1
5
2
5
5
1
7
2
2
3
4
6
0
0
2
2
9
8
5
2
9
7
.
2
1
%
U
2
r
55
1
5
8
12
0
13
2
3
8
5
.
4
%
T
ab
le
6
.
C
lass
ificatio
n
ac
cu
r
ac
y
o
f
KNN
,
SVM,
an
d
I
DS
-
I
D
f
o
r
th
e
KDD
-
c
u
p
9
9
M
e
t
r
i
c
K
N
N
S
V
M
I
D
S
-
ID
N
o
r
mal
D
R
%
9
7
.
2
6
9
6
.
4
5
9
8
.
4
9
F
R
%
8
.
8
5
8
.
6
5
8
.
5
5
Prb
D
R
%
8
0
.
4
5
8
5
.
3
5
8
6
.
2
5
F
R
%
0
.
4
0
0
.
4
0
0
.
7
5
R
2
l
D
R
%
6
.
4
5
7
.
2
0
6
.
2
0
F
R
%
0
.
1
0
.
2
0
.
2
1
D
o
s
D
R
%
9
7
.
1
5
9
6
.
9
5
9
7
.
5
5
F
R
%
0
.
5
5
0
.
9
5
0
.
4
0
U
2
r
D
R
%
1
1
.
8
9
.
2
0
4
.
3
6
F
R
%
0
0
.
1
0
O
v
e
r
a
l
l
A
C
%
9
1
.
5
3
9
2
.
2
5
9
2
.
8
5
I
n
th
e
s
ec
o
n
d
ex
p
er
im
en
t,
th
e
o
v
er
all
class
if
icatio
n
ac
cu
r
ac
y
o
f
t
h
e
all
class
if
ier
s
h
av
e
b
e
en
s
lig
h
tly
d
ec
r
ea
s
ed
d
u
e
to
r
em
o
v
i
n
g
5
%
o
f
th
e
d
ata
b
u
t
s
till
th
e
th
e
I
DS
-
I
D
class
if
ier
(
92
.
2
4
)
h
as
th
e
h
ig
h
est
class
if
icatio
n
ac
cu
r
ac
y
.
B
esid
es
th
at,
th
e
class
if
icatio
n
ac
cu
r
ac
y
g
ap
b
etwe
en
th
e
I
DS
-
I
D
class
if
ier
an
d
,
KNN
an
d
SVM
clas
s
if
ier
s
h
as
b
e
en
in
cr
ea
s
ed
as
illu
s
tr
ated
i
n
T
ab
le
7
.
T
h
e
class
if
icatio
n
ac
cu
r
ac
y
is
s
till
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
I
n
tr
u
s
io
n
d
etec
tio
n
s
ystem
b
a
s
ed
o
n
ma
c
h
in
e
lea
r
n
in
g
tech
n
i
q
u
es
(
Mu
s
a
a
b
R
iy
a
d
h
)
959
d
ec
r
ea
s
in
g
in
th
e
t
h
ir
d
an
d
f
o
u
r
th
ex
p
er
im
e
n
ts
o
f
th
e
all
class
if
ier
s
d
u
e
to
in
cr
ea
s
in
g
th
e
p
er
ce
n
tag
e
r
ate
o
f
th
e
r
em
o
v
in
g
d
ata
1
0
an
d
1
5
%.
Ho
wev
er
,
th
e
class
if
icatio
n
p
er
f
o
r
m
a
n
ce
o
f
t
h
e
I
DS
-
I
D
cla
s
s
if
ier
(
9
1
.
0
)
is
s
till
t
h
e
h
ig
h
est
as
illu
s
tr
ated
in
T
ab
le
s
8
an
d
9
.
Ultim
ately
,
th
e
class
if
icat
io
n
ac
cu
r
ac
y
o
f
I
DS
-
I
D
class
if
ier
is
b
etter
th
an
KNN
an
d
SVM
wh
en
r
an
d
o
m
ly
r
em
o
v
i
n
g
5
,
1
0
,
an
d
1
5
%
o
f
t
h
e
d
ata
in
s
p
ite
o
f
d
r
o
p
i
n
g
d
o
wn
th
e
o
v
er
all
d
etec
tio
n
ac
cu
r
ac
y
o
f
a
ll c
lass
if
ier
s
a
s
s
h
o
wn
in
Fig
u
r
e
4
.
T
ab
le
7
.
C
lass
ificatio
n
ac
cu
r
ac
y
o
f
KNN
,
SVM,
an
d
I
DS
-
I
D
af
ter
r
an
d
o
m
ly
elim
in
ate
5
% o
f
th
e
KDD
-
c
u
p
9
9
d
ata
s
et
M
e
t
r
i
c
K
N
N
S
V
M
I
D
S
-
ID
N
o
r
mal
D
ER
%
9
6
.
1
9
5
.
9
9
7
.
9
F
P
R
%
8
.
5
8
.
2
4
8
.
1
5
Prb
D
ER
%
7
8
.
2
8
4
.
5
8
6
.
7
F
P
R
%
0
.
4
0
0
.
4
1
0
.
7
3
R
2
l
D
ER
%
5
.
7
3
6
.
2
1
5
.
9
F
P
R
%
0
.
0
8
0
.
1
7
0
.
1
8
D
o
s
D
ER
%
9
6
.
1
0
9
6
.
0
0
9
7
.
0
0
F
P
R
%
0
.
4
1
0
.
8
1
0
.
3
4
U
2
r
D
ER
%
1
1
.
3
8
.
9
5
4
.
5
2
F
P
R
%
0
0
.
0
9
0
O
v
e
r
a
l
l
A
C
%
8
8
.
9
4
8
9
.
3
4
9
2
.
2
4
T
ab
le
8
.
C
lass
ificatio
n
ac
cu
r
ac
y
o
f
KNN
,
SVM,
an
d
I
DS
-
I
D
af
ter
r
an
d
o
m
ly
elim
in
ate
1
0
%
o
f
th
e
KDD
-
c
up99
d
ata
s
et
M
e
t
r
i
c
K
N
N
S
V
M
I
D
S
-
ID
N
o
r
mal
D
ER
%
9
6
.
8
5
9
6
.
3
5
9
7
.
1
5
F
P
R
%
8
.
5
6
8
.
3
1
8
.
2
6
Prb
D
ER
%
7
8
.
2
8
4
.
5
5
8
6
.
6
F
P
R
%
0
.
4
0
0
.
4
2
0
.
7
0
R
2
l
D
ER
%
5
.
7
5
6
.
2
4
5
.
9
9
F
P
R
%
0
.
0
8
0
.
1
7
0
.
1
8
D
o
s
D
ER
%
9
6
.
2
9
6
.
0
5
9
7
.
0
1
F
P
R
%
0
.
3
9
0
.
7
9
0
.
3
2
U
2
r
D
ER
%
1
1
.
1
0
8
.
8
0
4
.
2
8
F
P
R
%
0
0
.
0
7
0
O
v
e
r
a
l
l
A
C
%
8
8
.
3
5
8
8
.
8
8
9
1
.
0
T
ab
le
9
.
C
lass
ificatio
n
ac
cu
r
ac
y
o
f
KNN
,
SVM,
an
d
I
DS
-
I
D
af
ter
r
an
d
o
m
ly
elim
in
ate
1
5
%
o
f
th
e
KDD
-
c
up99
d
ata
s
et
M
e
t
r
i
c
K
N
N
S
V
M
I
D
S
-
ID
N
o
r
mal
D
ER
%
9
6
.
5
5
9
6
.
0
5
9
7
.
0
1
F
P
R
%
8
.
5
0
8
.
2
4
8
.
2
0
Prb
D
ER
%
7
7
.
9
8
4
.
0
5
8
6
.
1
F
P
R
%
0
.
3
8
0
.
4
1
0
.
6
7
R
2
l
D
ER
%
5
.
6
5
6
.
1
1
5
.
7
8
F
P
R
%
0
.
0
7
0
.
1
6
0
.
1
7
D
o
s
D
ER
%
9
5
.
9
9
5
.
8
9
6
.
8
9
F
P
R
%
0
.
3
7
0
.
7
7
0
.
3
0
U
2
r
D
ER
%
1
0
.
9
1
8
.
6
2
4
.
0
7
F
P
R
%
0
0
.
0
5
0
O
v
e
r
a
l
l
A
C
%
8
7
.
6
8
8
.
3
3
8
9
.
7
Fig
u
r
e
4
.
T
h
e
d
r
o
p
p
i
n
g
in
d
ete
ctio
n
ac
cu
r
ac
y
af
ter
r
e
m
o
v
in
g
5
,
1
0
,
an
d
1
0
% o
f
th
e
d
ata
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.
23
,
No
.
2
,
Au
g
u
s
t
20
21
:
953
-
9
6
1
960
5.
CO
NCLU
SI
O
N
T
h
e
an
aly
s
is
o
f
t
h
e
in
tr
u
s
io
n
d
etec
tio
n
d
ata
s
et
b
ased
o
n
m
ac
h
i
n
e
lear
n
i
n
g
tech
n
i
q
u
es
is
a
ch
allen
g
in
g
task
d
u
e
to
its
m
a
s
s
iv
e
s
ize,
m
ix
ed
-
ty
p
e
attr
ib
u
t
es,
an
d
th
e
r
ed
u
n
d
a
n
cy
o
f
d
at
a
.
B
esid
es
th
at,
th
e
d
ata
m
ay
b
e
i
n
co
m
p
lete
a
n
d
n
o
is
ey
.
I
n
th
is
s
tu
d
y
,
a
n
in
tr
u
ti
o
n
d
etec
tio
n
s
y
s
tem
h
as
b
ee
n
p
r
o
p
o
s
ed
to
tack
le
th
ese
is
s
u
es,
i
t
co
n
n
s
is
ts
o
f
tw
o
p
h
ases
:
th
e
lear
in
g
p
h
ase
an
d
test
in
g
p
h
ase.
T
h
e
lear
n
in
g
p
h
ase
s
u
p
p
o
r
ts
th
e
clu
s
ter
f
ea
tu
r
e
co
n
ce
p
t
to
s
u
m
m
ar
ize
th
e
d
ata
s
et
a
n
d
s
p
ec
ia
l
k
in
d
o
f
s
im
ilar
ity
m
ea
s
u
r
es
t
o
d
ea
l
with
m
ix
e
d
-
ty
p
e
attr
ib
u
tes
an
d
in
co
m
p
l
ete
d
ata.
W
h
ile
th
e
test
in
g
p
h
ase
u
s
es
th
e
KNN
ca
ls
s
if
er
d
u
e
t
o
its
lo
w
co
m
p
u
tatio
n
al
co
s
t.
T
h
e
ex
p
e
r
im
en
tal
r
esu
lts
s
h
o
ws
th
at
th
e
p
r
o
p
o
s
ed
class
if
ier
h
as
a
h
ig
h
er
class
if
icatio
n
ac
cu
r
ac
y
an
d
lo
wer
r
u
n
n
in
g
ti
m
e
in
ac
tu
al
d
ata
an
d
in
co
m
p
l
ete
d
ata
wh
en
r
an
d
o
m
ly
r
em
o
v
e
5
,
1
0
,
a
n
d
1
5
%
p
er
s
an
teg
e
o
f
d
ata
in
s
p
ite
o
f
d
r
o
p
in
g
d
o
wn
t
h
e
o
v
e
r
all
d
etec
tio
n
ac
cu
r
ac
y
as
co
m
p
ar
e
d
with
S
VM
an
d
KNN
class
if
ier
.
ACK
NO
WL
E
DG
E
M
E
NT
S
T
h
e
au
th
o
r
wo
u
ld
lik
e
to
th
a
n
k
Mu
s
tan
s
ir
iy
ah
Un
i
v
er
s
ity
(
www.
u
o
m
u
s
tan
s
ir
iy
ah
.
ed
u
.
iq
B
ag
h
d
ad
-
I
r
aq
)
f
o
r
it
s
u
p
p
o
r
tin
g
th
e
p
r
esen
t w
o
r
k
.
RE
F
E
R
E
NC
E
S
[1
]
S.
K.
S
a
h
u
a
n
d
D.
P
.
M
o
h
a
p
a
tra
,
"
A
Re
v
iew
o
n
S
c
a
lab
le
Lea
rn
i
n
g
Ap
p
ro
a
c
h
e
s
o
n
In
tr
u
sio
n
De
t
e
c
ti
o
n
Da
tas
e
t,
"
Pro
c
e
e
d
in
g
s
o
f
ICRIC
S
p
rin
g
e
r
,
v
o
l.
5
9
7
,
p
p
.
6
9
9
-
7
1
4
,
2
0
2
0
,
d
o
i:
1
0
.
1
0
0
7
/9
7
8
-
3
-
0
3
0
-
2
9
4
0
7
-
6
_
5
0
.
[2
]
M
.
P
ra
d
h
a
n
,
C.
K.
Na
y
a
k
,
a
n
d
S
.
K.
P
ra
d
h
a
n
,
"
I
n
tru
si
o
n
De
tec
ti
o
n
S
y
ste
m
(IDS)
a
n
d
Th
e
ir
T
y
p
e
s,"
i
n
S
e
c
u
rin
g
t
h
e
In
ter
n
e
t
o
f
T
h
in
g
s:
C
o
n
c
e
p
ts,
M
e
th
o
d
o
lo
g
ies
,
T
o
o
ls,
a
n
d
A
p
p
li
c
a
ti
o
n
s
,
IG
I
G
lo
b
a
l,
p
p
.
4
8
1
-
4
9
7
,
2
0
2
0
,
d
o
i:
1
0
.
4
0
1
8
/9
7
8
-
1
-
5
2
2
5
-
9
8
6
6
-
4
.
c
h
0
2
6
.
[3
]
M.
C.
Be
lav
a
g
i
a
n
d
B.
M
u
n
iy
a
l,
"
P
e
rfo
rm
a
n
c
e
e
v
a
lu
a
ti
o
n
o
f
su
p
e
r
v
i
se
d
m
a
c
h
in
e
lea
rn
in
g
a
l
g
o
rit
h
m
s
fo
r
i
n
tr
u
sio
n
d
e
tec
ti
o
n
,
"
Pro
c
e
d
ia
C
o
mp
u
ter
S
c
ien
c
e
,
v
o
l.
8
9
,
p
p
.
1
1
7
-
1
2
3
,
2
0
1
6
,
d
o
i:
1
0
.
1
0
1
6
/j
.
p
ro
c
s.
2
0
1
6
.
0
6
.
0
1
6
.
[4
]
N.
S
u
lt
a
n
a
,
N.
Ch
i
lam
k
u
rti
,
W.
P
e
n
g
,
a
n
d
R.
Al
h
a
d
a
d
,
"
S
u
r
v
e
y
o
n
S
DN
b
a
se
d
n
e
two
rk
in
tr
u
sio
n
d
e
tec
ti
o
n
sy
ste
m
u
sin
g
m
a
c
h
i
n
e
lea
rn
in
g
a
p
p
r
o
a
c
h
e
s,"
Pee
r
-
to
-
Pee
r
Ne
two
rk
in
g
a
n
d
Ap
p
li
c
a
t
io
n
s
,
v
o
l.
1
2
,
n
o
.
2
,
p
p
.
4
9
3
-
5
0
1
,
2
0
1
9
,
d
o
i:
1
0
.
1
0
0
7
/s1
2
0
8
3
-
0
1
7
-
0
6
3
0
-
0.
[5
]
A.
Kh
ra
isa
t
,
I.
G
o
n
d
a
l,
P
.
Va
m
p
ley
,
a
n
d
J.
Ka
m
ru
z
z
a
m
a
n
,
"
S
u
r
v
e
y
o
f
in
tru
si
o
n
d
e
tec
ti
o
n
sy
ste
m
s:
tec
h
n
iq
u
e
s,
d
a
tas
e
ts an
d
c
h
a
ll
e
n
g
e
s,"
Cy
b
e
rs
e
c
u
rity
,
v
o
l.
2
,
n
o
.
1
,
p
p
.
1
-
2
0
,
2
0
1
9
,
d
o
i:
1
0
.
1
1
8
6
/s4
2
4
0
0
-
0
1
9
-
0
0
3
8
-
7.
[6
]
N.
Ug
tak
h
b
a
y
a
r
B.
Us
u
k
h
b
a
y
a
r,
a
n
d
S
.
Ba
ig
a
lt
u
g
s,
"
A
H
y
b
ri
d
M
o
d
e
l
fo
r
An
o
m
a
l
y
-
Ba
se
d
In
tr
u
sio
n
De
tec
ti
o
n
S
y
ste
m
,
"
Pr
o
c
e
e
d
in
g
s
o
f
Ad
v
a
n
c
e
s
in
In
telli
g
e
n
t
In
fo
rm
a
t
io
n
Hid
i
n
g
a
n
d
M
u
lt
ime
d
ia
S
i
g
n
a
l
Pr
o
c
e
ss
in
g
S
p
ri
n
g
e
r
,
p
p
.
4
1
9
-
4
3
1
,
2
0
2
0
,
d
o
i:
1
0
.
1
0
0
7
/
9
7
8
-
9
8
1
-
13
-
9
7
1
0
-
3
_
4
4
.
[7
]
S
.
Kris
h
n
a
v
e
n
i
,
e
t
a
l
.
,
"
A
n
o
m
a
ly
-
Ba
se
d
In
tr
u
sio
n
De
tec
ti
o
n
S
y
ste
m
Us
in
g
S
u
p
p
o
rt
Ve
c
to
r
M
a
c
h
in
e
,
"
Pro
c
e
e
d
i
n
g
s
of
Arti
f
icia
l
I
n
telli
g
e
n
c
e
a
n
d
Ev
o
l
u
ti
o
n
a
ry
C
o
mp
u
ta
ti
o
n
s
in
E
n
g
in
e
e
rin
g
S
y
ste
ms
sp
rin
g
e
r
,
2
0
2
0
,
p
p
.
7
2
3
-
7
3
1
.
[8
]
H.
Wan
g
,
J.
G
u
,
a
n
d
S
.
Wan
g
,
"
A
n
e
ffe
c
ti
v
e
i
n
tru
si
o
n
d
e
te
c
ti
o
n
fra
m
e
wo
rk
b
a
se
d
o
n
S
V
M
with
fe
a
t
u
re
a
u
g
m
e
n
tatio
n
,
"
Kn
o
wled
g
e
-
Ba
se
d
S
y
ste
ms
,
v
o
l
.
1
3
6
,
p
p
.
1
3
0
-
1
3
9
,
2
0
1
7
,
d
o
i:
1
0
.
1
0
1
6
/j
.
k
n
o
sy
s.
2
0
1
7
.
0
9
.
0
1
4
.
[9
]
Y.
Li
a
o
,
a
n
d
V.
Ve
m
u
ri,
"
Us
e
o
f
k
-
n
e
a
re
st
n
e
ig
h
b
o
r
c
las
sifier
fo
r
in
tr
u
sio
n
d
e
tec
ti
o
n
,
"
C
o
mp
u
t
e
rs
&
se
c
u
rity
,
v
o
l.
2
1
,
n
o
.
5
,
p
p
.
4
3
9
-
4
4
8
,
Oc
to
b
e
r
2
0
0
2
,
d
o
i:
1
0
.
1
0
1
6
/
S
0
1
6
7
-
4
0
4
8
(0
2
)0
0
5
1
4
-
X.
[1
0
]
W.
L
i
,
P
.
Yi,
Y.
Wu
,
L
.
P
a
n
,
a
n
d
J.
Li
,
"
A n
e
w
i
n
tru
si
o
n
d
e
tec
ti
o
n
sy
ste
m
b
a
se
d
o
n
KN
N
c
las
sifica
ti
o
n
a
lg
o
rit
h
m
in
wire
les
s
se
n
so
r
n
e
two
rk
,
"
J
o
u
rn
a
l
o
f
El
e
c
trica
l
a
n
d
Co
m
p
u
ter
En
g
i
n
e
e
rin
g
,
v
o
l.
2
0
1
4
,
n
o
.
5
,
p
p
.
1
-
8,
2
0
1
4
,
doi
:
1
0
.
1
1
5
5
/2
0
1
4
/
2
4
0
2
1
7
.
[1
1
]
Y.
J.
Ch
e
w,
S
.
Y.
Oo
i,
K
o
k
-
S
e
n
g
Wo
n
g
,
a
n
d
Y.
H.
P
a
n
g
,
"
De
c
isio
n
Tree
with
S
e
n
siti
v
e
P
ru
n
in
g
in
Ne
two
rk
-
b
a
se
d
In
tru
si
o
n
De
tec
ti
o
n
S
y
ste
m
,
"
Pr
o
c
e
e
d
in
g
s
o
f
C
o
mp
u
ta
ti
o
n
a
l
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
S
p
rin
g
e
r
,
v
o
l
.
6
0
3
,
p
p
.
1
-
1
0
,
2
0
2
0
,
d
o
i:
1
0
.
1
0
0
7
/
9
7
8
-
9
8
1
-
15
-
0
0
5
8
-
9
_
1
.
[1
2
]
S.
M
.
M
o
u
sa
v
i,
V.
M
a
ji
d
n
a
z
h
a
d
,
a
n
d
A.
Na
g
h
ip
o
u
r
,
"
A
n
e
w
in
te
ll
ig
e
n
t
i
n
tru
si
o
n
d
e
tec
to
r
b
a
se
d
o
n
e
n
se
m
b
le
o
f
d
e
c
isio
n
tree
s,"
J
o
u
rn
a
l
o
f
Am
b
ien
t
In
telli
g
e
n
c
e
a
n
d
Hu
m
a
n
ize
d
C
o
mp
u
t
in
g
,
2
0
1
9
,
p
p
.
1
-
1
3
,
d
o
i:
1
0
.
1
0
0
7
/s1
2
6
5
2
-
019
-
0
1
5
9
6
-
5
.
[1
3
]
M
.
G
.
S
c
h
u
lt
z
,
E
.
Esk
in
,
F
.
Za
d
o
k
,
a
n
d
S
.
J.
S
t
o
lfo
,
"
Da
ta
m
i
n
in
g
m
e
th
o
d
s
f
o
r
d
e
tec
ti
o
n
o
f
n
e
w
m
a
li
c
io
u
s
e
x
e
c
u
tab
les
,
"
Pr
o
c
e
e
d
in
g
s
2
0
0
1
IEE
E
S
y
mp
o
siu
m
o
n
S
e
c
u
rity
a
n
d
Priva
c
y
.
S
&
P
2
0
0
1
,
2
0
0
1
,
p
p
.
3
8
-
4
9
,
d
o
i:
1
0
.
1
1
0
9
/S
EC
P
RI.
2
0
0
1
.
9
2
4
2
8
6
.
[1
4
]
M
.
Zam
a
n
i
a
n
d
M
.
M
o
v
a
h
e
d
i
,
"
M
a
c
h
i
n
e
Lea
rn
i
n
g
Tec
h
n
i
q
u
e
s
fo
r
I
n
tru
si
o
n
De
tec
ti
o
n
,
"
a
rXiv
p
re
p
ri
n
t
a
rXiv:1
3
1
2
.
2
1
7
7
,
2
0
1
3
.
[1
5
]
A.
I.
S
a
leh
,
F
.
M
.
Tala
a
t,
a
n
d
L.
M
.
Lab
i
b
,
"
A
h
y
b
rid
i
n
tru
si
o
n
d
e
tec
ti
o
n
sy
ste
m
(HID
S
)
b
a
se
d
o
n
p
ri
o
rit
ize
d
k
-
n
e
a
re
st
n
e
ig
h
b
o
rs
a
n
d
o
p
ti
m
ize
d
S
VM
c
las
sifiers
,
"
Art
if
icia
l
In
telli
g
e
n
c
e
Rev
iew
,
v
o
l.
5
1
,
n
o
.
3
,
p
p
.
4
0
3
-
4
4
3
,
2
0
1
9
,
d
o
i:
1
0
.
1
0
0
7
/s1
0
4
6
2
-
0
1
7
-
9
5
6
7
-
1.
[1
6
]
G
.
M
y
lav
a
ra
p
u
,
J.
Th
o
m
a
s,
a
n
d
A.
K.
TK,
"
Re
a
l
-
Ti
m
e
Hy
b
rid
I
n
tru
sio
n
De
tec
ti
o
n
S
y
ste
m
Us
in
g
Ap
a
c
h
e
S
to
rm
,
"
2
0
1
5
IEE
E
1
2
t
h
I
n
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Em
b
e
d
d
e
d
S
o
ft
wa
re
a
n
d
S
y
ste
ms
,
2
0
1
5
,
p
p
.
1
4
3
6
-
1
4
4
1
,
d
o
i:
1
0
.
1
1
0
9
/HP
CC
-
CS
S
-
ICES
S
.
2
0
1
5
.
2
4
1
.
[1
7
]
W.
L.
Al
-
Ya
se
e
n
,
Z.
A.
Oth
m
a
n
,
a
n
d
M
.
Z.
A.
Na
z
ri,
"
M
u
lt
i
-
le
v
e
l
h
y
b
rid
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
i
n
e
a
n
d
e
x
trem
e
lea
rn
in
g
m
a
c
h
in
e
b
a
se
d
o
n
m
o
d
i
fied
K
-
m
e
a
n
s
fo
r
i
n
tr
u
si
o
n
d
e
tec
ti
o
n
sy
ste
m
,
"
Ex
p
e
rt
S
y
ste
ms
wit
h
A
p
p
li
c
a
ti
o
n
s
,
v
o
l.
6
7
,
p
p
.
2
9
6
-
3
0
3
,
Ja
n
.
2
0
1
7
,
d
o
i:
1
0
.
1
0
1
6
/
j.
e
sw
a
.
2
0
1
6
.
0
9
.
0
4
1
.
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
I
n
tr
u
s
io
n
d
etec
tio
n
s
ystem
b
a
s
ed
o
n
ma
c
h
in
e
lea
r
n
in
g
tech
n
i
q
u
es
(
Mu
s
a
a
b
R
iy
a
d
h
)
961
[1
8
]
G
.
Do
n
g
,
Y.
Ji
n
,
S
.
Wan
g
,
W.
L
i,
Z.
Ta
o
,
a
n
d
S
.
G
u
o
,
"
DB
-
Km
e
a
n
s:An
In
tr
u
sio
n
De
tec
ti
o
n
Alg
o
rit
h
m
Ba
se
d
o
n
DBSCAN
a
n
d
K
-
m
e
a
n
s,"
2
0
1
9
2
0
t
h
Asia
-
Pa
c
if
ic
Ne
two
rk
Op
e
r
a
ti
o
n
s
a
n
d
M
a
n
a
g
e
me
n
t
S
y
mp
o
si
u
m
(AP
NOM
S
)
,
2
0
1
9
,
p
p
.
1
-
4
,
d
o
i:
1
0
.
2
3
9
1
9
/AP
NO
M
S
.
2
0
1
9
.
8
8
9
2
9
1
0
.
[1
9
]
Z.
Ch
e
n
a
n
d
Y
.
Li
,
"
An
o
m
a
ly
d
e
tec
ti
o
n
b
a
se
d
o
n
e
n
h
a
n
c
e
d
DB
S
c
a
n
a
lg
o
ri
th
m
,
"
Pro
c
e
d
i
a
En
g
i
n
e
e
rin
g
,
v
o
l
.
1
5
,
p
p
.
1
7
8
-
1
8
2
,
2
0
1
1
,
d
o
i:
1
0
.
1
0
1
6
/
j
.
p
ro
e
n
g
.
2
0
1
1
.
0
8
.
0
3
6
.
[2
0
]
C.
G
u
o
,
Y.
Zh
o
u
,
Y.
P
i
n
g
,
Z.
Z
h
a
n
g
,
G
.
Li
u
,
a
n
d
Y.
Ya
n
g
,
"
A
d
istan
c
e
su
m
-
b
a
se
d
h
y
b
ri
d
m
e
th
o
d
f
o
r
in
tr
u
si
o
n
d
e
tec
ti
o
n
,
"
A
p
p
li
e
d
i
n
telli
g
e
n
c
e
,
v
o
l.
4
0
,
n
o
.
1
,
p
p
.
1
7
8
-
1
8
8
,
2
0
1
4
,
d
o
i:
1
0
.
1
0
0
7
/s
1
0
4
8
9
-
0
1
3
-
0
4
5
2
-
6.
[2
1
]
W
ei
-
C
h
a
o
Li
n
,
S
h
i
h
-
Wen
Ke
,
a
n
d
C
h
ih
-
F
o
n
g
Tsa
i,
"
CAN
N:
An
in
tru
si
o
n
d
e
tec
ti
o
n
sy
ste
m
b
a
se
d
o
n
c
o
m
b
i
n
in
g
c
lu
ste
r
c
e
n
ters
a
n
d
n
e
a
re
st
n
e
ig
h
b
o
rs,
"
K
n
o
wle
d
g
e
-
b
a
se
d
s
y
ste
ms
,
v
o
l.
7
8
,
p
p
.
1
3
-
2
1
,
Ap
ril
2
0
1
5
,
d
o
i:
1
0
.
1
0
1
6
/j
.
k
n
o
sy
s.
2
0
1
5
.
0
1
.
0
0
9
.
[2
2
]
B.
M
a
n
j
u
n
a
t
h
a
a
n
d
P
.
G
o
g
o
i.
"
An
o
m
a
ly
b
a
se
d
i
n
tr
u
sio
n
d
e
tec
ti
o
n
in
m
ix
e
d
a
tt
ri
b
u
te
d
a
tas
e
t
u
si
n
g
d
a
ta
m
in
in
g
m
e
th
o
d
s,"
J
o
u
r
n
a
l
o
f
Arti
fi
c
i
a
l
In
telli
g
e
n
c
e
,
v
o
l.
9
,
n
o
.
1
-
3
,
p
p
.
1
-
1
1
,
2
0
1
6
.
[2
3
]
V.
S
h
a
k
y
a
a
n
d
R.
R.
S
.
M
a
k
wa
n
a
,
"
F
e
a
tu
re
se
lec
ti
o
n
b
a
se
d
in
tr
u
sio
n
d
e
tec
ti
o
n
sy
ste
m
u
sin
g
th
e
c
o
m
b
in
a
ti
o
n
o
f
DBSCAN,
K
-
M
e
a
n
+
+
a
n
d
S
M
O
a
lg
o
rit
h
m
s,"
2
0
1
7
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
T
re
n
d
s
in
El
e
c
tro
n
ics
a
n
d
In
fo
rm
a
t
ics
(ICEI
)
,
2
0
1
7
,
p
p
.
9
2
8
-
9
3
2
,
d
o
i:
1
0
.
1
1
0
9
/ICOEI.
2
0
1
7
.
8
3
0
0
8
4
3
.
[2
4
]
K.
S
.
Bh
o
sa
le,
M
.
Ne
n
o
v
a
,
a
n
d
G
.
Ili
e
v
,
"
M
o
d
ifi
e
d
Na
iv
e
Ba
y
e
s
In
tru
si
o
n
De
tec
ti
o
n
S
y
ste
m
(M
NBID
S
),
"
2
0
1
8
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
C
o
mp
u
ta
ti
o
n
a
l
T
e
c
h
n
iq
u
e
s,
El
e
c
tro
n
ics
a
n
d
M
e
c
h
a
n
ica
l
S
y
ste
ms
(CT
EM
S
)
,
2
0
1
8
,
p
p
.
2
9
1
-
2
9
6
,
d
o
i:
1
0
.
1
1
0
9
/CT
E
M
S
.
2
0
1
8
.
8
7
6
9
2
4
8
.
[2
5
]
J
.
H
u
s
s
a
i
n
a
n
d
S
.
L
a
l
m
u
a
n
a
wm
a
,
"
F
e
a
t
u
r
e
a
n
a
l
y
s
is
,
e
v
a
l
u
a
t
i
o
n
a
n
d
c
o
m
p
a
r
i
s
o
n
s
o
f
c
l
a
s
s
i
f
ic
a
t
i
o
n
a
l
g
o
r
i
t
h
m
s
b
a
s
e
d
o
n
n
o
i
s
y
i
n
t
r
u
s
i
o
n
d
a
t
a
s
e
t
,
"
P
r
o
c
e
d
i
a
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
9
2
,
p
p
.
1
8
8
-
1
9
8
,
2
0
1
6
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
r
o
c
s
.
2
0
1
6
.
0
7
.
3
4
5
.
[2
6
]
X
.
Z
u
o
,
Z
.
C
h
e
n
,
L
.
D
o
n
g
,
J
.
C
h
a
n
g
,
a
n
d
B
.
H
o
u
,
"
P
o
w
e
r
i
n
f
o
r
m
a
t
i
o
n
n
e
t
w
o
r
k
i
n
t
r
u
s
i
o
n
d
e
t
e
c
t
i
o
n
b
a
s
e
d
o
n
d
a
t
a
m
i
n
i
n
g
a
l
g
o
r
i
t
h
m
,
"
T
h
e
J
o
u
r
n
a
l
o
f
S
u
p
e
r
c
o
m
p
u
t
i
n
g
,
v
o
l
.
7
6
,
n
o
.
7
,
p
p
.
1
-
1
9
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
2
2
7
-
019
-
0
2
8
9
9
-
2
.
[2
7
]
M
.
Riy
a
d
h
,
N.
M
u
sta
p
h
a
,
a
n
d
D
.
Riy
a
d
h
,
"
Re
v
iew
o
f
Traje
c
to
ri
e
s
S
imilarity
M
e
a
su
re
s
in
M
in
i
n
g
Alg
o
r
it
h
m
s,"
2
0
1
8
Al
-
M
a
n
s
o
u
r
I
n
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Ne
w
T
re
n
d
s
i
n
Co
mp
u
ti
n
g
,
Co
mm
u
n
ica
t
io
n
,
a
n
d
I
n
f
o
rm
a
ti
o
n
T
e
c
h
n
o
l
o
g
y
(N
T
CCIT
)
,
2
0
1
8
,
p
p
.
3
6
-
4
0
,
d
o
i:
1
0
.
1
1
0
9
/NTCCI
T.
2
0
1
8
.
8
6
8
1
1
8
6
.
[2
8
]
J.
Ha
n
,
J.
P
e
i
,
a
n
d
M
.
Ka
m
b
e
r,
Da
ta
mi
n
i
n
g
:
c
o
n
c
e
p
ts
a
n
d
tec
h
n
iq
u
e
s
,
USA:
M
o
rg
a
n
Ka
u
fm
a
n
n
,
2
0
1
1
.
Evaluation Warning : The document was created with Spire.PDF for Python.