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
.
2
,
N
o
v
em
b
e
r
2
0
2
1
,
p
p
.
1
1
0
0
~
1
1
0
6
I
SS
N:
2
5
0
2
-
4
7
5
2
,
DOI
: 1
0
.
1
1
5
9
1
/ijeecs.v
24
.i
2
.
p
p
1
1
0
0
-
1
1
0
6
1100
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs.ia
esco
r
e.
co
m
Intrusio
n
de
tect
io
n sy
stem ba
sed o
n bag
g
ing
with
su
ppo
rt
v
ector ma
chine
Ali K
ha
lid
H
ilo
o
l
,
So
uk
a
ena
H
.
H
a
s
hem
,
Sh
a
t
ha
H
.
J
a
f
er
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
,
Un
iv
e
rsit
y
o
f
Tec
h
n
o
l
o
g
y
,
Ba
g
h
d
a
d
,
Ira
q
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
n
6
,
2021
R
ev
is
ed
Au
g
27
,
2
0
2
1
Acc
ep
ted
Sep
2
,
2
0
2
1
D
u
e
t
o
t
h
e
i
r
r
a
p
i
d
s
p
r
e
a
d
,
c
o
m
p
u
t
e
r
w
o
r
m
s
p
e
rf
o
r
m
h
a
r
m
f
u
l
t
a
s
k
s
i
n
n
e
t
w
o
r
k
s
,
p
o
s
i
n
g
a
s
e
c
u
r
i
t
y
r
is
k
;
h
o
w
e
v
e
r
,
e
x
i
s
t
i
n
g
w
o
r
m
d
e
te
c
t
i
o
n
a
l
g
o
r
i
t
h
m
s
c
o
n
t
i
n
u
e
t
o
s
t
r
u
g
g
l
e
t
o
a
c
h
i
e
v
e
g
o
o
d
p
e
r
f
o
r
m
a
n
c
e
a
n
d
t
h
e
r
e
a
s
o
n
s
f
o
r
t
h
a
t
a
r
e
:
F
i
r
s
t
,
a
l
a
r
g
e
a
m
o
u
n
t
o
f
i
r
r
e
l
e
v
a
n
t
d
a
ta
a
f
f
e
c
t
s
c
l
a
ss
i
f
i
c
a
t
i
o
n
a
c
c
u
r
a
c
y
.
S
e
c
o
n
d
,
i
n
d
i
v
i
d
u
a
l
c
l
a
ss
i
f
i
e
rs
d
o
n
o
t
d
e
t
e
c
t
a
l
l
t
y
p
e
s
o
f
w
o
r
m
s
e
f
fe
c
t
i
v
e
l
y
.
T
h
i
r
d
,
m
a
n
y
sy
s
t
e
m
s
a
re
b
a
s
e
d
o
n
o
u
t
d
a
t
e
d
d
a
t
a
,
m
a
k
i
n
g
t
h
e
m
u
n
s
u
i
t
a
b
l
e
f
o
r
n
e
w
w
o
r
m
s
p
e
c
i
e
s
.
T
h
e
g
o
a
l
o
f
t
h
e
s
t
u
d
y
i
s
t
o
u
s
e
d
a
t
a
m
i
n
i
n
g
a
l
g
o
r
i
t
h
m
s
t
o
d
e
t
e
c
t
w
o
r
m
s
i
n
t
h
e
n
e
t
w
o
r
k
b
e
c
a
u
s
e
t
h
e
y
h
a
v
e
a
h
i
g
h
a
b
i
l
i
t
y
t
o
d
e
t
e
c
t
n
e
w
t
y
p
e
s
a
c
c
u
r
a
t
e
l
y
.
T
h
e
p
r
o
p
o
s
a
l
i
s
b
a
s
e
d
o
n
t
h
e
U
N
S
W
N
B
1
5
d
a
t
a
s
e
t
a
n
d
u
s
e
s
a
s
u
p
p
o
r
t
v
e
c
t
o
r
m
a
c
h
i
n
e
t
o
t
r
a
i
n
a
n
d
t
e
s
t
t
h
e
e
n
s
e
m
b
l
e
b
a
g
g
i
n
g
a
l
g
o
r
i
t
h
m
.
T
o
d
e
t
e
c
t
v
a
r
i
o
u
s
t
y
p
e
s
o
f
w
o
r
m
s
e
f
f
i
c
ie
n
t
l
y
,
t
h
e
c
o
n
t
r
i
b
u
t
i
o
n
s
u
g
g
e
s
t
s
c
o
m
b
i
n
i
n
g
c
o
r
r
e
l
a
t
i
o
n
a
n
d
C
h
i
2
f
e
a
t
u
r
e
se
l
e
c
t
i
o
n
m
e
t
h
o
d
c
a
ll
e
d
C
h
i
2
-
C
o
r
r
t
o
s
e
l
e
c
t
re
l
e
v
a
n
t
f
e
a
t
u
r
e
s
a
n
d
u
s
i
n
g
s
u
p
p
o
r
t
v
e
c
t
o
r
m
a
c
h
i
n
e
(
S
V
M
)
i
n
t
h
e
b
a
g
g
i
n
g
a
l
g
o
r
i
t
h
m
.
T
h
e
s
y
s
t
e
m
a
c
h
i
e
v
e
d
a
c
c
u
r
a
c
y
r
e
a
c
h
i
n
g
0
.
9
9
8
w
i
t
h
C
h
i
2
-
C
o
r
r
,
a
n
d
0
.
9
8
9
,
0
.
9
9
2
w
i
t
h
c
o
r
r
e
l
a
t
i
o
n
a
n
d
c
h
i
-
s
q
u
a
r
e
s
e
p
a
ra
t
e
l
y
.
K
ey
w
o
r
d
s
:
B
ag
g
in
g
C
o
m
p
u
ter
wo
r
m
s
E
n
s
em
b
le
lear
n
in
g
I
DS
SVM
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
:
Ali K
h
alid
Hilo
o
l
Dep
ar
tm
en
t Co
m
p
u
ter
Scien
ce
Un
iv
er
s
ity
Of
T
ec
h
n
o
lo
g
y
B
ag
h
d
ad
,
I
r
aq
E
m
ail:
cs.1
9
.
4
2
@
g
r
ad
.
u
o
tech
n
o
lo
g
y
.
ed
u
.
i
q
1.
I
NT
RO
D
UCT
I
O
N
W
o
r
m
s
a
r
e
a
h
a
z
a
r
d
b
e
c
a
u
s
e
t
h
e
y
a
r
e
s
e
l
f
-
c
o
n
t
ai
n
e
d
a
n
d
d
o
n
o
t
c
o
u
n
t
o
n
o
t
h
e
r
s
o
f
t
w
a
r
e
f
o
r
p
r
o
p
a
g
a
t
i
o
n
,
a
l
l
o
w
i
n
g
t
h
e
m
t
o
s
p
r
e
a
d
r
a
p
i
d
l
y
.
A
l
o
t
o
f
m
e
t
h
o
d
s
h
a
v
e
b
e
e
n
u
s
e
d
t
o
d
e
t
e
c
t
c
o
m
p
u
t
e
r
w
o
r
m
s
a
n
d
e
s
t
i
m
a
t
e
t
h
e
i
r
d
a
m
a
g
e
,
i
n
cl
u
d
in
g
t
h
e
u
s
e
o
f
e
n
c
r
y
p
t
i
o
n
,
f
i
r
e
wa
l
l
s
,
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
e
s
,
a
n
d
a
v
a
r
i
et
y
o
f
o
t
h
e
r
m
e
t
h
o
d
s
[
1
]
,
[
2
]
.
I
n
t
r
u
s
i
o
n
d
e
t
e
c
t
i
o
n
s
y
s
t
e
m
(
I
DS
)
i
s
o
n
e
o
f
t
h
e
m
o
s
t
r
el
i
a
b
l
e
s
y
s
t
e
m
s
f
o
r
d
e
t
ec
t
i
n
g
p
e
n
e
t
r
a
t
i
o
n
s
a
n
d
a
tt
a
c
k
s
i
n
n
e
t
w
o
r
k
i
n
f
r
a
s
t
r
u
c
t
u
r
e
[
3]
-
[
5
]
.
A
n
o
m
a
l
y
-
b
a
s
e
d
d
e
t
e
ct
i
o
n
s
a
n
d
m
is
u
s
e
-
b
as
e
d
d
e
t
e
c
t
i
o
n
s
a
r
e
t
w
o
t
y
p
e
s
o
f
i
n
tr
u
s
i
o
n
d
e
t
e
c
t
i
o
n
m
e
t
h
o
d
s
.
At
t
ac
k
s
a
r
e
i
d
e
n
t
i
f
ie
d
u
s
i
n
g
a
n
o
m
a
l
y
-
b
a
s
e
d
d
e
t
e
ct
i
o
n
a
p
p
r
o
a
c
h
e
s
b
as
e
d
o
n
t
h
ei
r
b
eh
a
v
i
o
r
.
W
h
e
n
a
d
e
p
a
r
t
u
r
e
f
r
o
m
u
s
u
a
l
b
e
h
a
v
i
o
r
is
n
o
ti
c
e
d
in
a
c
o
n
n
e
c
ti
o
n
,
i
t
is
c
l
a
s
s
e
d
as
a
n
a
s
s
a
u
lt
.
M
is
u
s
e
-
b
a
s
e
d
d
e
t
e
ct
i
o
n
,
o
n
t
h
e
o
t
h
e
r
h
a
n
d
,
i
d
e
n
t
i
f
i
e
s
a
n
i
n
c
u
r
s
i
o
n
b
y
c
o
m
p
a
r
i
n
g
i
t
t
o
p
r
e
s
e
t
s
i
g
n
a
t
u
r
es
.
As
a
r
es
u
l
t
,
u
n
d
e
r
s
t
a
n
d
i
n
g
t
h
e
c
h
a
r
a
ct
e
r
is
t
i
cs
o
f
as
s
a
u
l
t
s
i
s
r
e
q
u
i
r
e
d
in
o
r
d
e
r
t
o
c
r
e
a
t
e
a
m
i
s
u
s
e
-
b
as
e
d
d
e
te
c
t
i
o
n
s
y
s
te
m
[
6
]
,
[
7
]
.
I
D
S
g
e
n
e
r
a
t
es
a
l
a
r
g
e
n
u
m
b
e
r
o
f
f
a
l
s
e
a
l
a
r
m
s
,
w
h
ic
h
h
a
s
p
r
o
m
p
t
e
d
m
a
n
y
r
e
s
e
a
r
c
h
e
r
s
t
o
s
e
e
k
a
s
o
l
u
ti
o
n
t
o
d
i
s
ti
n
g
u
i
s
h
al
e
r
ts
t
o
l
e
s
s
s
e
r
i
o
u
s
i
n
c
i
d
e
n
t
s
a
n
d
r
e
d
u
c
e
f
a
ls
e
a
l
a
r
m
s
,
w
h
i
c
h
a
r
e
b
o
t
h
f
a
l
s
e
p
o
s
it
i
v
e
(
FP
)
a
n
d
f
a
l
s
e
n
e
g
a
ti
v
e
(
F
N
)
.
I
DS
b
a
s
e
d
o
n
d
a
t
a
m
i
n
i
n
g
t
e
c
h
n
i
q
u
e
s
c
a
n
b
e
u
s
e
d
t
o
i
m
p
r
o
v
e
I
D
S
i
n
a
c
t
u
a
l
t
i
m
e
,
e
li
m
i
n
a
t
e
n
o
r
m
a
l
a
c
ti
v
i
t
y
f
r
o
m
al
a
r
m
d
a
t
a
i
n
o
r
d
e
r
t
o
f
o
c
u
s
o
n
r
e
al
a
t
t
a
c
k
s
,
a
n
d
d
e
te
c
t
a
b
n
o
r
m
a
l
a
c
t
i
v
it
y
t
h
a
t
r
e
v
e
a
ls
a
r
e
a
l
at
t
a
c
k
[
8
]
,
[9
]
.
I
D
S
c
o
n
s
i
s
ts
o
f
tw
o
s
o
r
t
s
o
f
a
p
p
r
o
a
c
h
e
s
:
h
o
s
t
-
b
as
e
d
(
H
I
DS
)
a
n
d
n
e
t
w
o
r
k
-
b
a
s
e
d
(
N
I
D
S
)
[
1
0
]
.
H
I
D
S
i
s
t
h
e
m
o
s
t
c
o
m
m
o
n
t
y
p
e
o
f
I
D
S
;
i
t
s
p
r
i
m
a
r
y
f
u
n
c
t
i
o
n
i
s
i
n
t
e
r
n
a
l
m
o
n
i
t
o
r
i
n
g
(
o
f
a
c
o
m
p
u
t
e
r
o
r
m
a
c
h
i
n
e
)
;
h
o
w
e
v
e
r
,
s
e
v
e
r
a
l
v
er
s
i
o
n
s
o
f
H
I
DS
h
a
v
e
b
e
e
n
d
e
v
e
l
o
p
e
d
t
h
a
t
m
a
y
b
e
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
b
a
g
g
in
g
w
ith
s
u
p
p
o
r
t v
ec
to
r
ma
ch
in
e
(
A
li K
.
Hilo
o
l
)
1101
u
s
e
d
t
o
m
o
n
i
t
o
r
a
n
e
t
w
o
r
k
.
H
I
D
S
d
e
t
e
r
m
i
n
e
w
h
e
t
h
e
r
a
s
y
s
tem
h
a
s
b
e
e
n
h
a
c
k
e
d
a
n
d
i
s
s
u
e
ap
p
r
o
p
r
i
a
t
e
w
a
r
n
i
n
g
s
t
o
a
d
m
i
n
i
s
t
r
at
o
r
s
[
1
1
]
.
A
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
s
y
s
t
e
m
(
N
I
D
S
)
i
s
u
s
e
d
t
o
m
o
n
i
t
o
r
a
n
d
m
a
n
a
g
e
n
e
t
w
o
r
k
t
r
a
f
f
i
c
i
n
o
r
d
e
r
t
o
p
r
o
t
e
c
t
a
s
y
s
t
e
m
a
g
a
i
n
s
t
n
e
tw
o
r
k
-
b
a
s
e
d
a
tt
a
c
k
s
[
1
2
]
,
[
1
3
]
.
B
e
c
a
u
s
e
o
f
th
e
c
o
n
s
e
q
u
e
n
c
e
s
o
f
i
n
c
r
e
a
s
e
d
s
e
c
u
r
it
y
a
tt
a
c
k
s
t
o
d
ay
,
n
e
t
w
o
r
k
i
n
t
r
u
s
i
o
n
d
e
t
e
ct
i
o
n
s
y
s
te
m
s
(
N
I
D
S
)
h
a
v
e
b
e
c
o
m
e
th
e
m
o
s
t
c
r
i
t
i
ca
l
p
a
r
t
o
f
m
o
d
e
r
n
n
e
t
w
o
r
k
t
e
c
h
n
o
l
o
g
y
.
T
h
e
i
n
t
r
u
s
i
o
n
d
et
e
c
ti
o
n
s
y
s
t
e
m
(
I
DS
)
g
e
n
e
r
a
te
s
a
l
a
r
g
e
n
u
m
b
e
r
o
f
a
l
a
r
m
s
;
h
o
w
e
v
e
r
,
a
l
g
o
r
i
t
h
m
i
c
p
r
o
c
e
d
u
r
e
s
a
r
e
u
s
e
d
t
o
r
e
d
u
c
e
f
a
ls
e
p
o
s
it
i
v
e
s
[
14]
,
[
1
5
]
.
E
n
s
em
b
le
lear
n
in
g
is
a
m
ac
h
in
e
lear
n
in
g
tech
n
iq
u
e
th
at
en
tails
teac
h
in
g
a
g
r
o
u
p
o
f
b
a
d
lear
n
er
s
(
m
o
d
els)
to
s
o
lv
e
a
p
r
o
b
lem
a
n
d
th
en
co
m
b
in
in
g
th
eir
r
esu
l
ts
to
g
et
b
etter
r
esu
lts
.
T
h
e
b
a
s
ic
id
ea
is
th
at
we
ca
n
g
et
m
o
r
e
ac
cu
r
ate
an
d
/
o
r
r
o
b
u
s
t m
o
d
els b
y
co
m
b
i
n
in
g
w
ea
k
m
o
d
els in
th
e
r
ig
h
t w
ay
[
1
6
]
.
T
h
e
th
r
ee
ty
p
es
o
f
en
s
em
b
le
a
p
p
r
o
ac
h
es
ar
e
as
f
o
llo
ws.
B
ag
g
in
g
is
a
m
et
h
o
d
o
f
co
m
b
in
in
g
h
o
m
o
g
e
n
e
o
u
s
wea
k
lear
n
e
r
s
,
tr
ain
in
g
an
d
test
in
g
th
em
in
p
ar
allel,
an
d
th
en
co
m
b
i
n
in
g
t
h
em
u
s
in
g
av
er
ag
e
v
o
tin
g
[
1
7
]
.
B
o
o
s
tin
g
,
wh
ich
b
r
in
g
s
to
g
et
h
er
a
g
r
o
u
p
o
f
s
i
m
ilar
p
o
o
r
lear
n
e
r
s
an
d
t
r
ain
s
an
d
test
s
th
em
in
a
s
y
s
tem
atic
m
an
n
er
(
ea
ch
iter
atio
n
d
ep
en
d
s
o
n
p
r
ev
io
u
s
o
n
es)
[
1
8
]
.
Stack
in
g
is
an
en
s
em
b
le
m
eth
o
d
in
wh
ich
a
n
e
w
m
o
d
el
lear
n
s
th
e
m
o
s
t e
f
f
icien
t w
ay
to
c
o
m
b
in
e
th
e
p
r
ed
ictio
n
s
o
f
m
u
ltip
le
ex
is
tin
g
m
o
d
els
[1
9
].
T
h
e
co
m
p
u
ter
wo
r
m
wo
r
k
s
to
ca
u
s
e
g
r
ea
t
d
am
a
g
e
to
n
etwo
r
k
s
y
s
tem
s
,
an
d
s
y
s
tem
s
th
at
d
ep
en
d
o
n
class
if
icatio
n
an
d
th
at
ar
e
u
s
e
d
to
p
r
ev
en
t
it,
s
u
f
f
e
r
f
r
o
m
s
e
v
er
al
p
r
o
b
lem
s
,
as
s
o
m
e
o
f
th
em
u
s
e
in
d
i
v
id
u
al
class
if
ier
s
wh
er
e
n
ew
ty
p
es
ar
e
n
o
t
d
is
co
v
e
r
ed
with
h
ig
h
ac
cu
r
ac
y
d
u
e
t
o
th
e
lim
ita
tio
n
s
o
f
in
d
iv
i
d
u
al
class
if
ier
s
.
T
h
e
d
ata
u
s
ed
in
th
is
f
ield
is
o
f
ten
o
u
td
ated
an
d
o
b
s
o
lete
an
d
s
u
f
f
e
r
s
f
r
o
m
th
e
r
ep
etitio
n
o
f
d
ata
an
d
th
e
p
r
esen
ce
o
f
ir
r
elev
an
t
d
ata
an
d
wr
o
n
g
a
n
d
d
is
to
r
ted
d
ata.
T
h
er
ef
o
r
e,
all
o
f
th
is
will a
f
f
ec
t th
e
ac
cu
r
ac
y
o
f
th
e
class
if
icatio
n
an
d
will
l
ea
d
to
a
h
ig
h
f
alse
alar
m
r
ate.
I
n
o
r
d
e
r
to
o
v
er
c
o
m
e
t
h
ese
lim
itatio
n
s
,
we
will
f
ir
s
t
u
s
e
th
e
latest
in
tr
u
s
io
n
d
etec
tio
n
d
ataset
(
UNSW
-
NB
1
5
)
,
wh
ich
h
as
f
ewe
r
p
r
o
b
lem
s
t
h
an
its
p
r
ed
ec
ess
o
r
s
.
An
d
we
m
a
k
e
p
r
e
-
p
r
o
ce
s
s
in
g
it
to
g
et
r
id
o
f
th
e
d
is
to
r
ted
d
ata,
th
e
n
we
p
r
o
p
o
s
e
to
co
m
b
in
e
two
m
eth
o
d
s
o
f
id
en
tif
y
in
g
f
ea
tu
r
es
(
C
h
i2
-
C
o
r
r
)
to
d
eter
m
i
n
e
o
n
ly
th
e
f
ea
tu
r
es
r
elate
d
to
o
u
r
p
r
o
b
lem
,
th
e
n
w
e
will
u
s
e
th
e
en
s
em
b
le
m
eth
o
d
s
th
at
wo
r
k
o
n
th
e
p
r
in
cip
le
o
f
(
u
n
io
n
is
s
tr
en
g
th
)
to
o
v
er
co
m
e
th
e
p
r
o
b
le
m
s
o
f
in
d
iv
id
u
al
class
if
icatio
n
an
d
g
iv
e
th
e
h
ig
h
est ac
cu
r
ac
y
o
f
cla
s
s
if
icatio
n
W
ith
th
e
lo
west f
al
s
e
alar
m
r
ate.
T
h
e
r
est
o
f
th
e
p
ap
er
is
o
r
g
an
i
ze
d
as
f
o
llo
ws:
I
n
s
ec
tio
n
2
,
we
d
escr
ib
e
th
e
ar
ch
itectu
r
e
o
f
th
e
wo
r
m
d
etec
tio
n
s
y
s
tem
,
wh
ich
is
b
ased
o
n
en
s
e
m
b
le
b
ag
g
in
g
.
Sectio
n
2
.
1
d
is
cu
s
s
es
th
e
u
n
s
w
-
n
b
1
5
d
ataset,
in
s
ec
tio
n
s
2
.
2
an
d
2
.
3
we
d
is
cu
s
s
th
e
p
r
ep
r
o
ce
s
s
in
g
s
tep
s
an
d
f
ea
tu
r
e
s
elec
tio
n
m
eth
o
d
s
wh
ich
in
clu
d
e
u
s
in
g
ch
i2
an
d
c
o
r
r
elatio
n
.
I
n
s
ec
tio
n
2
.
4
,
we'
ll
g
o
o
v
e
r
h
o
w
to
c
o
n
s
tr
u
ct
a
b
ag
g
in
g
class
if
ie
r
an
d
h
o
w
to
tr
ain
a
n
d
test
a
m
o
d
el
u
s
in
g
an
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
i
n
e
(
SVM
)
class
i
f
ier
.
I
n
s
ec
tio
n
3
,
we
an
al
y
ze
o
u
r
e
x
ten
s
iv
e
test
s
f
o
r
ev
al
u
atin
g
th
e
p
r
o
p
o
s
ed
w
o
r
m
d
etec
tio
n
m
eth
o
d
.
Sectio
n
4
wr
ap
s
u
p
b
y
ela
b
o
r
atin
g
o
n
th
e
co
n
clu
s
io
n
.
2.
RE
S
E
ARCH
M
E
T
H
O
D
T
o
im
p
r
o
v
e
th
e
d
etec
tio
n
o
f
wo
r
m
s
in
n
etwo
r
k
s
,
we
p
r
o
p
o
s
e
an
ef
f
ec
tiv
e
d
ata
m
in
in
g
m
o
d
el
f
o
r
wo
r
m
d
etec
tio
n
th
at
u
s
es
b
o
t
h
an
o
m
aly
a
n
d
m
is
u
s
e
d
etec
t
io
n
tech
n
iq
u
es,
wh
e
r
e
ea
c
h
c
ase
in
a
d
ataset
is
lab
eled
as
"a
ttack
"
o
r
"
n
o
r
m
al
"
(
wo
r
m
s
ar
e
o
n
e
k
i
n
d
o
f
atta
c
k
)
,
a
n
d
a
lear
n
in
g
alg
o
r
ith
m
is
tr
ain
ed
o
v
er
th
e
class
d
ata.
T
h
e
s
tr
u
ct
u
r
e
o
f
th
e
p
r
o
p
o
s
ed
wo
r
m
d
etec
tio
n
m
o
d
el
is
s
h
o
wn
in
Fig
u
r
e
1
.
W
h
ich
is
b
r
o
k
en
d
o
wn
in
to
f
o
u
r
d
is
tin
ct
s
tag
es:
1)
Data
s
et
p
r
ep
r
o
ce
s
s
in
g
:
T
o
p
r
ep
ar
e
th
e
d
ata
f
o
r
th
e
class
if
icatio
n
alg
o
r
ith
m
,
we
f
ir
s
t
ad
d
p
r
ep
r
o
ce
s
s
in
g
s
tep
s
to
th
e
in
itial d
atasets
.
2)
2
-
D
i
m
e
n
s
i
o
n
a
l
i
t
y
r
e
d
u
ct
i
o
n
:
T
o
p
i
c
k
t
h
e
m
o
s
t
i
m
p
o
r
t
a
n
t
f
e
a
t
u
r
e
s
a
n
d
r
e
d
u
c
e
t
h
e
d
i
m
e
n
s
i
o
n
a
l
it
y
o
f
t
h
e
d
a
t
a
s
et
,
a
f
e
a
t
u
r
e
s
e
l
ec
t
i
o
n
s
tr
a
t
e
g
y
c
a
l
l
e
d
(
C
h
i
2
-
C
o
r
r
)
b
as
e
d
o
n
c
h
i
-
s
q
u
a
r
e
a
n
d
c
o
r
r
e
la
t
i
o
n
f
e
a
t
u
r
es
s
e
l
e
ct
i
o
n
is
u
s
e
d
.
3)
C
las
s
if
ier
tr
ain
in
g
:
T
o
im
p
r
o
v
e
th
e
ac
cu
r
ac
y
o
f
wo
r
m
d
e
tectio
n
,
we
u
s
e
th
e
b
ag
g
in
g
alg
o
r
ith
m
t
o
co
n
s
tr
u
ct
class
if
ier
s
.
4)
T
o
f
o
r
ec
ast th
e
o
u
tco
m
e
o
f
o
u
r
m
o
d
el,
we
u
s
ed
class
if
icatio
n
(
test
in
g
)
.
Fig
u
r
e
1
.
Flo
wch
ar
t
o
f
p
r
o
p
o
s
ed
wo
r
m
d
etec
tio
n
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.
24
,
No
.
2
,
No
v
em
b
er
2
0
2
1
:
1
1
0
0
-
1
1
0
6
1102
2
.
1
.
T
he
un
s
w
-
nb
1
5
da
t
a
s
et
T
h
e
p
r
o
p
o
s
ed
m
o
d
el
is
tr
ain
ed
u
s
in
g
th
e
UNSW
-
N
B
1
5
d
ataset.
T
h
er
e
ar
e
2
,
5
4
0
,
0
4
4
in
s
tan
ce
s
in
th
is
d
ataset
[
2
0
]
.
T
h
is
d
ata
is
s
p
lit
in
to
f
o
u
r
h
u
g
e
cr
ea
tin
g
s
h
ar
ed
v
alu
e
(
C
SV)
d
ir
ec
to
r
ies.
T
h
er
e
ar
e
d
etac
h
e
d
tr
ain
in
g
an
d
test
in
g
s
ets.
T
h
e
tr
ain
in
g
d
ataset
co
n
s
is
ts
o
f
1
7
5
,
3
4
1
r
ec
o
r
d
s
,
an
d
t
h
e
test
in
g
co
n
s
is
ts
o
f
8
2
,
3
3
2
r
ec
o
r
d
s
.
I
t h
as 4
5
co
lu
m
n
s
,
o
n
e
f
o
r
id
an
d
f
o
r
t
y
-
f
o
u
r
f
o
r
f
ea
tu
r
es.
T
h
e
p
r
o
p
o
s
ed
m
o
d
el
was tr
ain
ed
u
s
in
g
5
0
0
0
r
ec
o
r
d
s
f
r
o
m
th
e
af
o
r
em
en
tio
n
ed
tr
ain
in
g
an
d
test
in
g
r
ec
o
r
d
s
,
o
f
wh
ich
1
5
4
r
ec
o
r
d
s
co
n
t
ain
wo
r
m
s
an
d
th
e
r
est
co
n
tain
n
o
r
m
al
an
d
o
th
er
t
y
p
es
o
f
attac
k
s
.
UNSW
-
NB
1
5
d
ataset
is
co
n
s
is
ts
o
f
n
o
r
m
al
d
ata
an
d
n
i
n
e
ty
p
es
o
f
attac
k
s
(
B
ac
k
d
o
o
r
s
,
Do
s
attac
k
s
,
E
x
p
lo
its
attac
k
s
,
Fu
zz
er
s
attac
k
s
,
Gen
er
ic
attac
k
s
,
R
ec
o
n
n
aiss
an
ce
attac
k
s
,
Sh
ellco
d
e
attac
k
s
,
an
d
W
o
r
m
s
attac
k
s
)
ar
e
all
in
clu
d
ed
in
th
ese
tr
ain
in
g
an
d
test
in
g
d
atasets
[
2
1
]
.
2
.
2
.
P
re
pro
ce
s
s
ing
B
ec
au
s
e
th
e
UNS
W
-
NB
1
5
d
ataset
co
n
tain
s
b
o
th
co
n
tin
u
o
u
s
an
d
d
is
cr
ete
f
ea
tu
r
es,
it
is
n
e
ce
s
s
ar
y
to
co
n
v
er
t
t
h
e
co
n
tin
u
o
u
s
attr
ib
u
tes
to
d
is
cr
ete
to
e
n
s
u
r
e
th
e
s
y
s
tem
'
s
ef
f
icien
cy
an
d
to
d
e
al
with
th
e
is
s
u
e
o
f
n
ew
v
alu
es
ap
p
ea
r
in
g
in
th
e
t
est
d
ataset
th
at
ar
e
n
o
t
p
r
esen
t
in
th
e
tr
ain
in
g
d
ataset.
W
e
u
s
ed
th
e
Min
-
Ma
x
n
o
r
m
aliza
tio
n
p
r
o
ce
s
s
f
o
llo
win
g
d
is
cr
etiza
tio
n
to
im
p
r
o
v
e
t
h
e
m
o
d
el'
s
ef
f
icien
cy
an
d
ef
f
e
ctiv
en
ess
b
y
p
lacin
g
attr
ib
u
te
v
alu
es
b
etwe
en
(
0
-
1
)
[
2
2
]
.
W
e
will
u
s
e
co
r
r
elatio
n
f
ea
tu
r
e
s
elec
tio
n
an
d
ch
i
-
s
q
u
a
r
e
f
ea
tu
r
e
s
elec
tio
n
to
ex
clu
d
e
u
n
u
s
ed
an
d
r
ed
u
n
d
an
t
f
ea
tu
r
es
f
r
o
m
th
e
d
ata
s
et
af
ter
d
is
cr
etiza
tio
n
an
d
n
o
r
m
aliza
tio
n
(
See
Alg
o
r
ith
m
1
)
.
Algorithm (1) min
-
max normalization
input : subset unsw
-
nb15 Datasets
Output: data values ranging from zero to one
For each column in the Dataset
extract the largest number in column
extract the smallest number in column
For each (X) rate in Feature extract
_
(
)
=
(
)
−
−
End For
End For
2
.
3
.
F
ea
t
ure
s
elec
t
io
n
On
e
o
f
th
e
m
o
s
t
cr
itical
p
r
e
p
r
o
ce
s
s
in
g
s
tep
s
in
m
ac
h
in
e
lear
n
in
g
tech
n
iq
u
es
is
f
ea
tu
r
e
s
elec
tio
n
,
wh
ich
is
u
s
ed
to
r
em
o
v
e
u
n
n
e
ce
s
s
ar
y
an
d
r
ed
u
n
d
an
t
f
ea
tu
r
e
s
f
r
o
m
th
e
d
ataset,
en
h
an
ce
th
e
m
o
d
el'
s
ef
f
icien
cy
b
y
u
s
in
g
t
h
e
co
r
r
ec
t
f
ea
tu
r
es
an
d
r
ed
u
ce
th
e
am
o
u
n
t
o
f
tim
e
it
tak
es
to
p
r
o
ce
s
s
th
e
d
at
a
[
2
3
]
,
[
2
4
]
.
I
n
th
is
s
tu
d
y
,
we
u
s
ed
ch
i
2
f
ea
tu
r
es selectio
n
an
d
c
o
r
r
elatio
n
f
ea
tu
r
es selectio
n
.
See
alg
o
r
ith
m
(
2
)
.
-
C
o
r
r
elatio
n
f
ea
tu
r
e
s
elec
tio
n
C
o
r
r
elatio
n
-
b
ased
f
ea
tu
r
e
s
elec
tio
n
(
C
FS
)
r
an
k
s
attr
ib
u
tes
u
s
in
g
a
h
e
u
r
is
tic
ass
ess
m
en
t
f
u
n
ctio
n
b
ased
o
n
co
r
r
elatio
n
s
.
T
h
e
f
u
n
ctio
n
co
m
p
a
r
ed
attr
ib
u
te
v
ec
to
r
s
u
b
s
ets
th
at
ar
e
co
n
n
ec
ted
t
o
th
e
class
lab
el
b
u
t
n
o
t
to
o
n
e
a
n
o
th
er
.
T
h
e
C
FS
m
eth
o
d
ass
u
m
es
th
at
ir
r
elev
a
n
t
f
ea
tu
r
es
h
av
e
a
lo
w
co
r
r
el
atio
n
with
th
e
clas
s
an
d
,
as a
r
esu
lt,
s
h
o
u
ld
b
e
n
eg
lect.
E
x
ce
s
s
ch
ar
ac
ter
is
tic
s
,
o
n
th
e
o
th
er
h
an
d
,
s
h
o
u
ld
b
e
lo
o
k
ed
at
b
ec
au
s
e
th
ey
ar
e
f
r
eq
u
e
n
tly
co
r
r
elate
d
with
o
n
e
o
r
m
o
r
e
o
f
th
e
o
th
er
attr
ib
u
tes.
T
h
e
cr
iter
io
n
f
o
r
e
v
alu
atin
g
a
s
u
b
s
et
o
f
n
f
ea
tu
r
es is
as f
o
llo
ws:
=
̅
̅
̅
̅
̅
√
+
(
−
1
)
̅
̅
̅
̅
̅
(
1
)
MS
s
ig
n
if
ies
th
e
ev
alu
atio
n
o
f
a
s
u
b
s
et
o
f
S
th
at
h
as
N
ch
a
r
ac
ter
is
tics
.
̅
̅
̅
̅
.
is
th
e
av
er
ag
e
o
f
th
e
co
r
r
elatio
n
b
etwe
en
attr
ib
u
tes an
d
class
lab
els.
̅
̅
̅
̅
.
is
th
e
av
er
ag
e
c
o
r
r
elatio
n
b
etwe
en
two
c
h
ar
ac
ter
is
tics
[
2
5
]
,
[
2
6
]
.
-
C
h
i
-
s
q
u
ar
e
f
ea
tu
r
e
s
elec
tio
n
A
s
tati
s
tical
te
s
t i
s
a
C
h
i2
test
.
T
h
e
C
h
i2
test
ex
am
in
es th
e
r
e
latio
n
s
h
ip
b
etwe
en
a
class
an
d
a
f
ea
tu
r
e,
allo
win
g
it
to
s
elec
t
f
ea
tu
r
es
th
at
ar
e
m
o
r
e
r
elev
a
n
t
f
o
r
a
g
iv
en
d
ataset.
As
a
r
esu
lt,
f
ea
tu
r
es
th
at
ar
en
'
t
r
elev
an
t
f
o
r
ca
te
g
o
r
izatio
n
ca
n
b
e
r
em
o
v
ed
f
r
o
m
th
e
f
ea
tu
r
e
s
p
ac
e
[
2
7
]
.
Fro
m
th
e
d
ata
o
f
two
f
ea
tu
r
es,
we
will
g
et
th
e
o
b
s
er
v
ed
c
o
u
n
t
A
an
d
an
ticip
ated
c
o
u
n
t
E
.
T
h
e
C
h
i
-
Sq
u
ar
e
test
is
u
s
ed
to
m
ea
s
u
r
e
h
o
w
f
ar
an
ticip
ated
co
u
n
t E
an
d
o
b
s
er
v
ed
co
u
n
t A
d
if
f
er
.
2
=
(
−
)
2
(
2
)
W
h
er
e
C
i
s
th
e
d
eg
r
ee
o
f
f
r
ee
d
o
m
,
A
d
en
o
tes th
e
o
b
s
er
v
ed
v
alu
e(
s
)
,
an
d
E
d
e
n
o
tes th
e
ex
p
ec
ted
v
alu
e
(
s
)
.
W
e
co
m
p
ar
e
th
e
v
alu
e
o
f
2
to
th
e
v
alu
e
o
f
th
e
ch
i2
tab
le
v
alu
e
w
h
er
e
alp
h
a
=0
.
0
5
an
d
d
elete
t
h
e
f
ea
tu
r
e
i
f
it
is
less
th
an
th
e
ch
i2
tab
le
v
al
u
e
(
in
d
ep
en
d
en
t)
; e
ls
e,
th
e
f
ea
t
u
r
e
is
ac
ce
p
ted
.
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
b
a
g
g
in
g
w
ith
s
u
p
p
o
r
t v
ec
to
r
ma
ch
in
e
(
A
li K
.
Hilo
o
l
)
1103
Algorithm (2) Chi
-
Corr feature selection
input : subset unsw
-
nb15 Datasets
Output:
independent
features
with
a
strong
conn
ection
to
class,
and
fe
atures
that
are
class
-
dependent
Start
Step 1: correlation CFS
For each class column
Extract the correlation of class with all features
Choose features that have a strong relatio
nship with class.
Remove the remainder
End For
For each feature in the subset you've chosen,
Extract the correlation of feature with all features
Remove the remainder
End For
Step 2: Chi square feature selection
For each unsw
-
nb15Dataset feature
seek for
2
with class. See (1)
alpha=0.05
from chi2 table find X_c^2' where alpha=0.05 and matched it to X_c^2
If
2
<
2
′
the feature is independent (droped)
Else it is depend on class (not drop)
End For
End
2.
4
.
T
ra
ini
ng
a
nd
t
esting
Fo
llo
win
g
f
ea
tu
r
e
s
elec
tio
n
m
eth
o
d
s
,
we
will
d
iv
id
e
th
e
d
ataset
in
to
two
p
ar
ts
:
tr
ain
in
g
a
n
d
test
in
g
.
T
r
ain
in
g
co
n
tain
s
6
7
p
er
ce
n
t
o
f
th
e
to
tal
n
u
m
b
er
o
f
r
ec
o
r
d
s
in
th
e
d
ataset,
wh
ile
test
in
g
c
o
n
tain
s
3
3
p
er
ce
n
t.
T
h
e
p
r
o
p
o
s
ed
m
o
d
el
is
tr
ain
ed
an
d
test
ed
u
s
in
g
th
e
two
p
a
r
ts
.
T
h
en
we
will
d
is
tr
ib
u
te
th
e
tr
ain
in
g
p
a
r
t
o
n
th
r
ee
p
ar
allel
SVM
in
en
s
em
b
l
e
b
ag
g
in
g
alg
o
r
ith
m
to
m
a
k
e
c
lass
if
icatio
n
d
ec
is
io
n
s
.
See
alg
o
r
ith
m
(
3
)
.
Algorithm (3) Bagging SVM Ensemble Algorithm.
Input: A subset of UNSW
-
NB15 Dataset
Outp
ut: SVM Bagging Model
Begin
Steps:
Step 1: dividing dataset into three samples
Srep 2: Foreach Sample aply SVM algorithm
-
Initialize
(Xi,
Yj
)
fo
r
al
l
tr
ai
ni
ng
da
ta
se
t
po
in
ts
,
wh
er
e
X
is
a
da
t
a
vector (x1…. , xn) and Y is a
class vector.
-
Set the weight W vector.
-
Allotment points of (x, y) and elicitation the hyper plane separator.
-
He
ck
th
e
hy
pe
r
pl
an
e
if
it
is
pr
o
vi
de
s
th
e
be
st
se
pa
ra
ti
on
,
us
e
it
as
a
classifier system for the
classification
of
the
unsw
nb
-
15
te
st
in
g
da
ta
se
t
an
d
sw
it
ch
to
En
d;
otherwise, proceed to the next
step.
-
Make the hyperplan b
igger.
-
Set up the Lagrange multiplier. αi vector α1…αn.
-
Use the classification function.
-
Fi
nd
th
e
n
on
-
ze
ro
su
pp
or
t
ve
ct
or
s
x
i
(s
up
po
rt
ve
ct
or
s
ar
e
th
e
po
in
ts
th
at
determine the rea of hyper
plan).
-
Us
e
th
e
hy
pe
r
pl
an
th
at
em
er
ge
d
af
te
r
id
en
ti
fy
in
g
su
pp
or
t
ve
ct
or
s
as
th
e
classifier model to classify
the unsw nb
-
15 testing dataset.
End For
Make voting to return results
End
3.
RE
SU
L
T
S
A
ND
D
IS
CU
SS
I
O
N
T
h
e
aim
o
f
th
is
p
ap
e
r
,
as
m
en
tio
n
ed
p
r
ev
i
o
u
s
ly
,
is
to
d
e
v
elo
p
a
g
o
o
d
-
ac
c
u
r
ac
y
wo
r
m
d
etec
tio
n
s
y
s
tem
.
T
o
r
em
o
v
e
ir
r
elev
an
t
f
ea
tu
r
es
an
d
in
cr
ea
s
e
class
if
icatio
n
r
eliab
ilit
y
,
a
m
o
d
el
ca
l
led
C
h
i2
-
C
o
r
r
th
at
co
m
b
in
es
C
FS
an
d
ch
i2
is
u
s
e
d
to
ev
alu
ate
a
s
u
b
s
et
o
f
th
e
o
r
ig
in
al
f
ea
tu
r
es.
Usi
n
g
t
h
e
UN
SW
NB
1
5
d
ataset,
a
b
ag
g
in
g
en
s
em
b
le
class
if
ier
is
tr
ain
ed
an
d
test
ed
d
u
r
i
n
g
th
e
class
if
icatio
n
s
tag
e
u
s
i
n
g
SVM
as
b
ase
esti
m
ato
r
r
ath
er
th
an
d
ec
is
io
n
tr
ee
w
h
ich
is
th
e
d
ef
au
lt
esti
m
ato
r
.
T
h
e
test
s
ar
e
c
o
n
d
u
cted
o
n
a
d
esk
to
p
PC
with
a
1
.
8
0
GHz
I
n
tel
C
o
r
e
i3
-
3
2
1
7
U
p
r
o
ce
s
s
o
r
an
d
4
GB
o
f
r
an
d
o
m
ac
ce
s
s
m
e
m
o
r
y
(
R
AM
)
.
T
h
e
class
if
icatio
n
r
esu
lts
o
f
test
in
g
ar
e
eith
er
tr
u
e
p
o
s
itiv
es
(
T
P)
(
in
tr
u
s
io
n
)
,
tr
u
e
n
eg
ativ
es
(
T
N)
(
n
o
r
m
al)
,
FP
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.
24
,
No
.
2
,
No
v
em
b
er
2
0
2
1
:
1
1
0
0
-
1
1
0
6
1104
(
m
is
class
if
ied
as
in
tr
u
s
io
n
)
,
(
FN)
(
m
is
cla
s
s
if
ied
as
n
o
r
m
al)
,
Un
k
n
o
wn
(
n
ew
attac
k
s
)
.
T
ab
le
1
an
d
T
a
b
le
2
s
h
o
ws
th
e
r
esu
lts
o
f
a
p
p
ly
in
g
th
e
b
a
g
g
in
g
tech
n
iq
u
e
to
class
if
y
th
e
r
ec
o
r
d
s
in
th
e
test
in
g
d
ataset
u
s
in
g
SVM
an
d
d
if
f
u
s
io
n
ten
s
o
r
(
DT
)
c
lass
if
ier
s
.
I
n
T
ab
le
1
W
h
en
all
f
ea
tu
r
es
ar
e
s
elec
ted
an
d
f
ea
tu
r
e
s
elec
tio
n
p
r
o
ce
d
u
r
es
ar
e
u
s
ed
,
th
ese
f
in
d
in
g
s
r
e
v
ea
l
th
at
th
e
T
P
is
b
i
g
g
er
t
h
an
th
e
T
N,
FP
,
FN,
an
d
u
n
k
n
o
wn
.
W
h
en
em
p
lo
y
in
g
f
ea
tu
r
e
s
elec
tio
n
m
eth
o
d
s
in
th
e
SVM
class
if
ier
,
th
e
FP
r
ates
d
r
o
p
f
r
o
m
1
5
to
1
0
wh
en
u
s
in
g
C
FS
,
6
wh
en
u
s
in
g
C
h
i2
,
an
d
0
wh
e
n
u
s
in
g
C
h
i2
-
C
o
r
r
.
T
ab
le
1
.
C
lass
if
icatio
n
r
esu
lts
o
f
b
ag
g
in
g
with
SVM
class
if
ier
s
F
e
a
t
u
r
e
s
e
l
e
c
t
i
o
n
mea
s
u
r
e
TP
TN
FP
FN
U
n
k
n
o
w
C
h
i
2
-
C
o
r
r
.
9
3
8
7
1
0
0
2
0
C
F
S
9
1
7
7
1
5
10
8
0
C
h
i
2
9
1
3
7
2
5
6
6
0
A
LL
9
0
2
7
2
1
15
12
0
T
ab
le
2
.
C
lass
if
icatio
n
r
esu
lts
o
f
b
ag
g
in
g
with
DT
class
if
ier
s
F
e
a
t
u
r
e
s
e
l
e
c
t
i
o
n
mea
s
u
r
e
TP
TN
FP
FN
U
n
k
n
o
w
C
h
i
2
-
C
o
r
r
.
9
2
0
7
1
3
10
7
0
C
F
S
9
0
0
7
0
1
25
24
0
C
h
i
2
9
3
0
6
9
8
17
5
0
A
LL
8
9
9
6
8
3
40
28
0
T
h
e
d
e
t
e
c
t
i
o
n
r
a
t
e
(
D
R
)
i
s
t
h
e
r
a
t
i
o
b
e
t
w
e
e
n
t
h
e
n
u
m
b
e
r
o
f
T
P
a
n
d
t
h
e
t
o
t
a
l
n
u
m
b
e
r
o
f
i
n
t
r
u
s
i
o
n
r
e
c
o
r
d
s
p
r
e
s
e
n
t
e
d
i
n
t
h
e
t
e
s
t
i
n
g
d
a
t
a
s
e
t
.
I
t
h
a
s
b
e
e
n
c
o
m
p
u
t
e
d
u
s
i
n
g
t
h
e
f
o
l
l
o
w
i
n
g
e
q
u
a
t
i
o
n
:
D
R
=
T
P
/
(
T
P
+
F
N
+
U
n
k
n
o
w
n
)
,
a
n
d
t
h
e
f
a
l
s
e
a
l
a
r
m
r
a
t
e
(
F
A
R
)
i
s
t
h
e
r
a
t
i
o
b
e
t
w
e
e
n
s
e
v
e
r
a
l
"
n
o
r
m
a
l
"
r
e
c
o
r
d
s
c
l
a
s
s
i
f
i
e
d
a
s
a
t
t
a
c
k
s
(
F
P
)
a
n
d
t
h
e
t
o
t
a
l
n
u
m
b
e
r
o
f
"
n
o
r
m
a
l
"
r
e
c
o
r
d
s
p
r
e
s
e
n
t
e
d
i
n
t
h
e
t
e
s
t
i
n
g
d
a
t
a
s
e
t
.
I
t
h
a
s
b
e
e
n
c
o
m
p
u
t
e
d
u
s
i
n
g
t
h
e
f
o
l
l
o
w
i
n
g
e
q
u
a
t
i
o
n
:
F
A
R
=
F
P
/
(
T
N
+
F
P
+
U
n
k
n
o
w
n
)
,
S
e
l
e
c
t
i
o
n
o
f
t
h
e
b
e
s
t
c
l
a
s
s
i
f
i
c
a
t
i
o
n
m
o
d
e
l
c
a
n
b
e
d
o
n
e
a
c
c
o
r
d
i
n
g
t
o
i
t
s
c
l
a
s
s
i
f
i
c
a
t
i
o
n
a
c
c
u
r
a
c
y
,
w
h
i
c
h
i
s
t
h
e
r
a
t
i
o
b
e
t
w
e
e
n
t
h
e
n
u
m
b
e
r
o
f
c
o
r
r
e
c
t
l
y
c
l
a
s
s
i
f
i
e
d
p
a
t
t
e
r
n
s
(
T
P
,
T
N
)
a
n
d
t
h
e
t
o
t
a
l
n
u
m
b
e
r
o
f
p
a
t
t
e
r
n
s
o
f
t
h
e
t
e
s
t
i
n
g
d
a
t
a
s
e
t
.
T
h
e
a
c
c
u
r
a
c
y
(
A
c
c
)
o
f
e
a
c
h
c
l
a
s
s
i
f
i
e
r
h
a
s
b
e
e
n
c
o
m
p
u
t
e
d
u
s
i
n
g
A
c
c
=
(
T
P
+
T
N
)
/
(
T
P
+
F
P
+
T
N
+
F
N
+
u
n
k
n
o
w
n
)
,
f
a
l
s
e
d
i
s
c
o
v
e
r
y
r
a
t
e
(
F
D
R
=
F
P
/
F
P
+
T
P
)
,
P
r
e
c
i
s
i
o
n
=
T
P
/
(
T
P
+
F
P
)
,
S
p
e
c
i
f
i
c
i
t
y
=
T
N
/
(
T
N
+
F
P
)
,
F
-
m
e
a
s
u
r
e
=
(
2
*
R
e
c
a
l
l
*
P
r
e
c
i
s
i
o
n
)
/
(
R
e
c
a
l
l
+
P
r
e
c
i
s
i
o
n
)
.
V
a
l
u
e
s
f
o
r
a
l
l
m
e
n
t
i
o
n
e
d
m
e
t
r
i
c
s
h
a
v
e
b
e
e
n
i
l
l
u
s
t
r
a
t
e
d
i
n
T
a
b
l
e
3
a
n
d
T
a
b
l
e
4
.
T
ab
le
3
s
u
m
m
ar
izes
th
e
o
u
tco
m
es
f
r
o
m
th
e
UNSW
-
NB
1
5
d
ataset,
wh
i
ch
in
clu
d
es
th
e
r
esu
lts
o
f
th
e
en
s
em
b
le
B
ag
g
in
g
with
t
h
e
SVM
class
if
ier
.
I
t
is
p
r
o
p
o
s
ed
t
h
at
th
e
en
s
em
b
le
class
if
ier
is
n
o
t
o
p
tim
al
e
n
o
u
g
h
in
n
u
m
er
o
u
s
cr
iter
ia
with
o
u
t
f
ea
tu
r
e
s
elec
tio
n
.
Per
f
o
r
m
an
ce
,
o
n
th
e
o
t
h
er
h
a
n
d
,
im
p
r
o
v
es
to
th
e
b
est
f
ea
s
ib
le
ca
s
e
wh
en
f
ea
tu
r
e
s
elec
tio
n
m
eth
o
d
s
ar
e
ap
p
lied
.
W
ith
o
u
t
em
p
lo
y
i
n
g
f
ea
tu
r
e
s
elec
tio
n
m
eth
o
d
s
,
o
u
r
s
u
g
g
ested
s
y
s
tem
ac
h
iev
es
an
ac
cu
r
ac
y
o
f
0
.
9
8
3
,
FAR
o
f
0
.
0
2
0
,
DR
o
f
0
.
9
8
6
,
Pre
cisi
o
n
o
f
0
.
9
8
3
,
F
-
m
ea
s
u
r
e
o
f
0
.
9
8
4
,
Sp
ec
i
f
icity
o
f
0
.
9
7
9
,
an
d
f
alse
d
is
co
v
er
y
r
ate
(
FD
R
)
o
f
0
.
0
1
6
.
W
h
en
em
p
lo
y
i
n
g
f
ea
tu
r
e
s
elec
tio
n
m
eth
o
d
s
,
th
e
r
esu
lts
ar
e
o
p
ti
m
ized
,
an
d
wh
e
n
u
s
in
g
C
h
i2
-
C
o
r
r
.
th
e
b
est
ca
s
e
is
r
ea
ch
e
d
with
th
e
m
ax
im
u
m
ac
cu
r
ac
y
o
f
0
.
9
9
8
,
FAR
o
f
0
.
0
,
an
d
DR
o
f
0
.
9
9
8
,
Pre
cisi
o
n
o
f
1
.
0
,
F
-
m
ea
s
u
r
e
o
f
0
.
9
9
8
,
Sp
ec
if
icity
o
f
1
.
0
,
FDR
o
f
0
.
T
ab
le
3
.
Me
tr
ics to
ev
al
u
ate
e
n
s
em
b
le
b
ag
g
i
n
g
with
SVM
M
e
t
r
i
c
s
A
l
l
C
F
S
C
h
i
2
C
h
i
2
-
C
o
r
r
n
.
o
f
.
f
e
a
t
u
r
e
44
33
33
27
A
c
c
u
r
a
c
y
0
.
9
8
3
0
.
9
8
9
0
.
9
9
2
0
.
9
9
8
DR
0
.
9
8
6
0
.
9
9
1
0
.
9
9
3
0
.
9
9
8
F
A
R
0
.
0
2
0
0
.
0
1
3
0
.
0
0
8
0
.
0
P
r
e
c
i
s
i
o
n
0
.
9
8
3
0
.
9
8
9
0
.
9
9
3
1
.
0
0
F
-
mea
su
r
e
0
.
9
8
4
0
.
9
8
9
0
.
9
9
3
0
.
9
9
8
S
p
e
c
i
f
i
c
i
t
y
0
.
9
7
9
0
.
9
8
6
0
.
9
9
1
1
.
0
0
F
D
R
0
.
0
1
6
0
.
0
1
0
0
.
0
0
6
0
.
0
T
ab
le
4
.
m
etr
ics to
e
v
alu
ate
en
s
em
b
le
B
ag
g
in
g
with
DT
M
e
t
r
i
c
s
A
l
l
C
F
S
C
h
i
2
C
h
i
2
-
C
o
r
r
n
.
o
f
.
f
e
a
t
u
r
e
44
33
33
27
A
c
c
u
r
a
c
y
0
.
9
5
8
0
.
9
7
0
.
9
8
6
0
.
9
8
9
DR
0
.
9
6
9
0
.
9
7
4
0
.
9
9
4
0
.
9
9
2
F
A
R
0
.
0
5
5
0
.
0
3
4
0
.
0
2
3
0
.
1
3
P
r
e
c
i
s
i
o
n
0
.
9
5
7
0
.
9
7
2
0
.
9
8
2
0
.
9
8
9
F
-
mea
su
r
e
0
.
9
6
2
0
.
9
7
2
0
.
9
8
7
0
.
9
9
S
p
e
c
i
f
i
c
i
t
y
0
.
9
4
4
0
.
9
6
5
0
.
9
7
6
0
.
9
8
6
F
D
R
0
.
0
4
2
0
.
0
2
7
0
.
0
1
7
0
.
0
1
0
W
h
ile
u
s
in
g
th
e
DT
class
if
ier
in
co
n
ju
n
ctio
n
with
th
e
en
s
em
b
le
B
ag
g
in
g
alg
o
r
ith
m
Ou
r
p
r
o
p
o
s
ed
s
y
s
tem
h
as
an
ac
cu
r
ac
y
o
f
0
.
9
5
8
,
FAR
o
f
0
.
0
5
5
,
DR
o
f
0
.
9
6
9
,
Pre
cisi
o
n
o
f
0
.
9
5
7
,
F
-
m
ea
s
u
r
e
o
f
0
.
9
6
2
,
Sp
ec
if
icity
o
f
0
.
9
4
4
,
a
n
d
FDR
o
f
0
.
0
4
2
with
o
u
t
ap
p
ly
in
g
f
ea
tu
r
e
s
ele
ctio
n
m
eth
o
d
s
.
T
h
e
r
e
s
u
lts
ar
e
o
p
tim
ized
wh
en
em
p
lo
y
in
g
f
ea
tu
r
e
s
elec
tio
n
m
et
h
o
d
s
,
th
er
ef
o
r
e
wh
en
u
s
in
g
C
h
i2
-
C
o
r
r
,
th
e
b
est
ca
s
e
i
s
attain
ed
with
th
e
g
r
ea
test
ac
cu
r
ac
y
o
f
0
.
9
8
9
,
F
AR
o
f
0
.
0
1
3
,
DR
o
f
0
.
9
9
2
,
Pre
cisi
o
n
o
f
0
.
9
8
9
,
F
-
m
ea
s
u
r
e
o
f
0
.
9
9
,
Sp
ec
if
icity
o
f
0
.
9
8
6
,
a
n
d
FDR
o
f
0
.
0
1
0
.
W
e
co
m
p
ar
e
o
u
r
p
r
o
p
o
s
ed
s
y
s
tem
to
s
o
m
e
r
elate
d
wo
r
k
to
b
ette
r
g
r
asp
th
e
b
en
e
f
its
o
f
th
e
s
u
g
g
ested
m
eth
o
d
o
lo
g
y
.
T
ab
le
5
s
h
o
ws th
e
o
u
tco
m
es
o
f
th
e
co
m
p
ar
is
o
n
.
T
h
e
co
m
p
a
r
is
o
n
in
clu
d
es
th
e
class
if
icatio
n
m
eth
o
d
,
t
h
e
s
elec
ted
d
ataset,
f
ea
tu
r
e
s
elec
tio
n
ap
p
r
o
ac
h
es,
th
e
n
u
m
b
er
o
f
s
elec
ted
f
ea
tu
r
es,
ac
cu
r
ac
y
,
FAR
,
an
d
DR
f
o
r
in
tr
u
s
io
n
d
ete
ctio
n
,
as
s
h
o
wn
in
T
ab
le
5
.
W
h
en
co
m
p
ar
e
d
to
C
4
.
5
,
R
F,
o
u
r
s
y
s
tem
h
as
th
e
b
est
a
cc
u
r
ac
y
an
d
d
etec
tio
n
r
ate,
as
well
a
s
th
e
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
b
a
g
g
in
g
w
ith
s
u
p
p
o
r
t v
ec
to
r
ma
ch
in
e
(
A
li K
.
Hilo
o
l
)
1105
lo
west
f
alse
alar
m
r
ate.
W
h
en
we
co
m
p
ar
e
o
u
r
p
r
o
p
o
s
ed
s
y
s
tem
to
th
e
S
VM
,
we
ca
n
s
ee
th
at
th
e
en
s
em
b
le
m
eth
o
d
h
as
ad
v
an
tag
es
o
v
e
r
th
e
SVM,
wh
ich
is
a
s
in
g
l
e
class
if
ier
with
a
h
u
g
e
v
ar
ian
ce
.
As
a
r
esu
lt,
en
s
em
b
les
f
r
eq
u
en
tly
r
ed
u
ce
t
h
e
v
ar
ian
ce
co
m
p
o
n
en
t
o
f
c
o
n
tr
ib
u
tin
g
m
o
d
el
p
r
ed
ictio
n
e
r
r
o
r
s
,
r
esu
ltin
g
in
a
s
ig
n
if
ican
t
im
p
r
o
v
em
e
n
t
in
ac
cu
r
ac
y
(
f
r
o
m
0
.
8
5
to
0
.
9
9
8
)
as
well
as
a
r
ed
u
ctio
n
in
th
e
f
alse
alar
m
r
ate
(
FAR
)
(
f
r
o
m
1
5
.
2
6
to
0
.
0
)
.
W
h
en
SVM
was
u
s
ed
as
th
e
b
ase
esti
m
ato
r
,
o
u
r
p
r
o
p
o
s
ed
m
et
h
o
d
h
ad
th
e
h
ig
h
est
ac
cu
r
ac
y
an
d
d
etec
tio
n
r
ate
w
h
en
co
m
p
ar
ed
t
o
o
th
e
r
en
s
em
b
le
ap
p
r
o
ac
h
es lik
e
s
tack
in
g
,
an
d
b
o
o
s
tin
g
.
T
ab
le
5
.
C
o
m
p
r
ess
io
n
b
etwe
en
th
e
p
r
o
p
o
s
ed
s
y
s
tem
an
d
th
e
r
elate
d
wo
r
k
M
e
t
h
o
d
D
a
t
a
s
e
t
F
e
a
t
u
r
e
s
e
l
e
c
t
i
o
n
n
.
o
f
f
e
a
t
u
r
e
s
A
C
C
C
4
.
5
C
I
C
-
I
D
S
2
0
1
7
C
F
S
-
BA
10
0
.
9
8
RF
C
I
C
-
I
D
S
2
0
1
7
C
F
S
-
BA
10
0
.
9
9
3
S
V
M
Tr
a
i
n
a
n
d
T
e
st
U
N
S
W
-
N
B
1
5
N
/
A
44
0
.
8
5
S
TA
C
K
I
N
G
U
N
S
W
-
N
B
1
5
N
/
A
49
0
.
6
2
8
B
o
o
st
i
n
g
U
N
S
W
-
N
B
1
5
N
/
A
49
0
.
9
4
7
P
r
o
p
o
se
d
S
y
st
e
m
S
u
b
s
e
t
o
f
Tr
a
i
n
a
n
d
Te
s
t
U
N
S
W
-
N
B
1
5
C
F
S
-
C
h
i
2
s
27
0
.
9
9
8
4.
CO
NCLU
SI
O
N
T
h
e
s
u
g
g
ested
ap
p
r
o
ac
h
s
tr
e
s
s
es
th
e
n
ec
ess
ity
o
f
n
etwo
r
k
in
tr
u
s
io
n
d
etec
tio
n
s
y
s
tem
s
(
I
DS)
f
o
r
d
etec
tin
g
wo
r
m
ass
au
lts
,
wh
ic
h
ar
e
th
e
m
o
s
t
d
a
n
g
er
o
u
s
atta
ck
s
in
a
n
etwo
r
k
a
n
d
h
av
e
an
im
p
ac
t
o
n
r
eso
u
r
ce
av
ailab
ilit
y
.
B
ec
au
s
e
o
f
th
e
n
o
r
m
alizin
g
an
d
d
is
cr
etiza
tio
n
o
p
er
atio
n
s
,
th
e
s
u
g
g
ested
s
y
s
tem
is
m
o
r
e
ef
f
icien
t.
T
h
e
co
r
r
elatio
n
an
d
ch
i2
alg
o
r
ith
m
s
ar
e
o
f
f
er
e
d
as
f
ea
tu
r
e
s
elec
tio
n
ap
p
r
o
ac
h
es
to
im
p
r
o
v
e
th
e
ac
cu
r
ac
y
o
f
th
e
p
r
o
p
o
s
ed
s
y
s
tem
an
d
r
ed
u
ce
th
e
am
o
u
n
t
o
f
tim
e
r
e
q
u
ir
e
d
.
T
h
e
ac
cu
r
ac
y
o
f
t
h
e
B
ag
g
i
n
g
clas
s
if
ier
,
wh
ich
em
p
lo
y
s
SVM
an
d
is
as
s
is
ted
b
y
C
h
i2
-
C
o
r
r
,
is
b
etter
th
an
u
tili
zin
g
all
f
ea
tu
r
es
o
r
u
s
in
g
B
ag
g
in
g
C
lass
if
ier
with
C
o
r
r
o
r
ch
i2
with
3
3
f
ea
tu
r
es,
also
th
e
C
h
i2
-
C
o
r
r
h
as
a
lo
wer
f
alse
alar
m
r
ate
th
an
C
FS
o
r
C
h
i2
.
Usi
n
g
a
d
ec
is
io
n
tr
ee
class
if
ier
as
a
b
a
s
e
esti
m
ato
r
in
B
ag
g
in
g
(
with
o
u
t
o
u
r
co
n
tr
ib
u
tio
n
)
will
r
esu
lt
in
a
s
y
s
tem
th
at
is
less
ac
cu
r
ate,
h
as less
d
etec
tio
n
r
ate,
an
d
h
av
e
a
f
alse a
lar
m
r
ate.
RE
F
E
R
E
NC
E
S
[1
]
Y
.
Ya
o
,
Q
.
Fu
,
W
.
Ya
n
g
,
Y
.
Wa
n
g
,
a
n
d
C
.
S
h
e
n
g
,
“
An
E
p
id
e
m
ic M
o
d
e
l
o
f
Co
m
p
u
ter
Wo
rm
s
with
Ti
m
e
De
lay
a
n
d
Va
riab
le In
fe
c
ti
o
n
Ra
te,“
S
e
c
u
rity
a
n
d
Co
mm
u
n
ica
ti
o
n
Ne
two
rk
s
2
0
1
8
,
v
o
l
.
2
0
1
8
,
d
o
i:
1
0
.
1
1
5
5
/
2
0
1
8
/9
7
5
6
9
8
2
.
[2
]
S
.
H.
Ha
sh
e
m
a
n
d
I
.
A
.
Ab
d
u
lmu
n
e
m
,
"
A
p
r
o
p
o
sa
l
t
o
d
e
tec
t
c
o
m
p
u
ter
wo
rm
s
(m
a
li
c
io
u
s
c
o
d
e
s)
u
si
n
g
d
a
ta
m
in
i
n
g
c
las
sifica
ti
o
n
a
lg
o
r
it
h
m
s
,
"
En
g
in
e
e
rin
g
a
n
d
T
e
c
h
n
o
l
o
g
y
J
o
u
rn
a
l,
v
ol
.
3
1
,
n
o
.
2
,
2
0
1
3
.
[3
]
A.
D.
Ce
sa
re
e
t
a
l
.
,
"
Co
m
b
in
a
ti
o
n
o
f
flo
w
c
y
to
m
e
try
a
n
d
m
o
lec
u
lar
a
n
a
ly
sis
to
m
o
n
it
o
r
th
e
e
ffe
c
t
o
f
UV
C/H2
O2
v
s
UV
C/H2
O2
/Cu
-
IDS
p
ro
c
e
ss
e
s
o
n
p
a
th
o
g
e
n
s
a
n
d
a
n
ti
b
i
o
ti
c
re
sista
n
t
g
e
n
e
s
in
se
c
o
n
d
a
ry
wa
ste
wa
ter
e
fflu
e
n
ts,"
W
a
ter
Res
e
a
rc
h
,
v
ol
.
1
8
4
,
p
.
1
1
6
1
9
4
,
2
0
2
0
,
d
o
i:
1
0
.
1
0
1
6
/j
.
wa
tres
.
2
0
2
0
.
1
1
6
1
9
4
.
[4
]
S
.
H.
Ha
sh
e
m
,
"
En
h
a
n
c
e
n
e
two
rk
in
tr
u
sio
n
d
e
tec
ti
o
n
sy
ste
m
b
y
e
x
p
lo
it
in
g
b
r
a
lg
o
rit
h
m
a
s
a
n
o
p
ti
m
a
l
fe
a
tu
re
se
lec
ti
o
n
,
"
H
a
n
d
b
o
o
k
o
f
Res
e
a
rc
h
o
n
T
h
re
a
t
De
tec
ti
o
n
a
n
d
Co
u
n
ter
me
a
su
re
s
in
Ne
two
rk
S
e
c
u
ri
ty
,
IG
I
G
lo
b
a
l,
2
0
1
5
,
d
o
i:
1
0
.
4
0
1
8
/
9
7
8
-
1
-
4
6
6
6
-
6
5
8
3
-
5
.
c
h
0
0
2
.
[5
]
T
.
B
.
S
e
o
n
g
,
V
.
P
o
n
n
u
sa
m
y
,
N
.
Z
.
Jh
a
n
jh
i
,
R
.
An
n
u
r
,
a
n
d
M
.
N
.
Tali
b
,
"
A
c
o
m
p
a
ra
ti
v
e
a
n
a
ly
s
is
o
n
trad
it
i
o
n
a
l
wire
d
d
a
tas
e
ts
a
n
d
t
h
e
n
e
e
d
f
o
r
wire
les
s
d
a
tas
e
ts
fo
r
Io
T
wire
l
e
ss
in
tru
sio
n
d
e
tec
ti
o
n
,
"
I
n
d
o
n
e
s
ia
n
J
o
u
rn
a
l
o
f
El
e
c
trica
l
En
g
in
e
e
rin
g
a
n
d
Co
mp
u
ter
S
c
ien
c
e
,
v
o
l
.
2
2
,
n
o
.
2
,
M
a
y
2
0
2
1
,
p
p
.
1
1
6
5
-
1
1
7
6
,
d
o
i:
1
0
.
1
1
5
9
1
/
ij
e
e
c
s.v
2
2
.
i2
.
p
p
1
1
6
5
-
1
1
7
6
.
[6
]
B
.
N
.
K
u
m
a
r
,
M
.
S
.
V
.
S
iv
a
ra
m
a
Bh
a
d
ri
Ra
ju
,
a
n
d
B
Vis
h
n
u
V
a
rd
h
a
n
,
"
A
n
o
v
e
l
a
p
p
r
o
a
c
h
fo
r
s
e
lec
ti
v
e
fe
a
tu
re
m
e
c
h
a
n
ism
fo
r
tw
o
-
p
h
a
se
in
tru
si
o
n
d
e
tec
ti
o
n
s
y
ste
m
,
"
I
n
d
o
n
e
si
a
n
J
o
u
rn
a
l
o
f
El
e
c
trica
l
En
g
in
e
e
rin
g
a
n
d
Co
m
p
u
ter
S
c
ien
c
e
,
v
o
l.
1
4
,
n
o
.
1
,
p
p
.
1
0
1
-
1
1
2
,
A
p
ril
2
0
1
9
,
d
o
i
:
1
0
.
1
1
5
9
1
/
ij
e
e
c
s.v
1
4
.
i1
.
p
p
1
0
1
-
1
1
2
.
[7
]
H
.
S
u
h
a
im
e
t
a
l
.
,
"
G
e
n
e
ti
c
a
lg
o
rit
h
m
fo
r
in
tr
u
sio
n
d
e
tec
ti
o
n
sy
ste
m
in
c
o
m
p
u
ter
n
e
two
r
k
,
"
I
n
d
o
n
e
sia
n
J
o
u
r
n
a
l
o
f
El
e
c
trica
l
En
g
in
e
e
rin
g
a
n
d
Co
mp
u
ter
S
c
ien
c
e
,
v
o
l.
1
9
,
n
o
.
3
,
p
p
.
1
6
7
0
-
1
6
7
6
,
S
e
p
tem
b
e
r
2
0
2
0
,
d
o
i:
1
0
.
1
1
5
9
1
/
ij
e
e
c
s.v
1
9
.
i3
.
p
p
1
6
7
0
-
1
6
7
6
.
[8
]
S
.
H.
Ha
sh
im
a
n
d
S
.
S
h
a
re
f,
"
In
tru
sio
n
d
e
tec
ti
o
n
sy
ste
m
b
a
se
d
o
n
d
a
ta
m
in
i
n
g
tec
h
n
iq
u
e
s
to
re
d
u
c
e
fa
lse
a
larm
ra
te,
"
En
g
in
e
e
rin
g
a
n
d
T
e
c
h
n
o
l
o
g
y
J
o
u
rn
a
l,
v
o
l
.
3
6
,
n
o
.
2
,
2
0
1
8
,
d
o
i:
1
0
.
3
0
6
8
4
/etj
.
3
6
.
2
B
.
3
.
[9
]
S
.
H.
Ha
sh
im
a
n
d
S
.
S
h
a
re
f,
"
P
r
o
p
o
se
d
Hy
b
r
id
Clas
sifier
to
Im
p
ro
v
e
Ne
two
rk
I
n
tr
u
sio
n
De
tec
ti
o
n
S
y
ste
m
u
si
n
g
Da
ta
M
in
in
g
Tec
h
n
i
q
u
e
s,"
En
g
i
n
e
e
rin
g
a
n
d
T
e
c
h
n
o
lo
g
y
J
o
u
rn
a
l,
v
o
l.
3
8
,
n
o
.
1
B,
2
0
2
0
,
d
o
i:
1
0
.
3
0
6
8
4
/etj
.
v
3
8
i
1
B.
1
4
9
.
[1
0
]
N
.
N
.
Tran
,
R
.
S
a
rk
e
r
,
a
n
d
Jia
n
k
u
n
H
u
,
"
A
n
a
p
p
r
o
a
c
h
fo
r
h
o
st
-
b
a
se
d
in
tru
si
o
n
d
e
tec
ti
o
n
s
y
ste
m
d
e
sig
n
u
sin
g
c
o
n
v
o
lu
ti
o
n
a
l
n
e
u
ra
l
n
e
tw
o
rk
,
"
I
n
ter
n
a
ti
o
n
a
l
c
o
n
fer
e
n
c
e
o
n
mo
b
il
e
n
e
two
rk
s
a
n
d
ma
n
a
g
e
me
n
t
,
S
p
r
in
g
e
r,
v
o
l
.
2
3
5
,
2
0
1
7
,
d
o
i:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
3
1
9
-
9
0
7
7
5
-
8
_
1
0
.
[1
1
]
V
.
S
stla
,
V
.
K.
K.
K
o
ll
i
,
L
.
K.
Vo
g
g
u
,
R
.
Bh
a
v
a
n
a
m
,
a
n
d
S
.
Va
ll
a
b
h
a
so
y
u
la,
"
P
re
d
icti
v
e
M
o
d
e
l
fo
r
Ne
two
r
k
In
tru
s
i
o
n
De
tec
ti
o
n
S
y
ste
m
Us
in
g
De
e
p
Lea
rn
in
g
,
"
Rev
u
e
d
'I
n
telli
g
e
n
c
e
Arti
fi
c
ielle
J
o
u
rn
a
l
,
v
o
l.
3
4
,
n
o
.
3
,
p
p
.
3
2
3
-
330
,
Ju
n
e
2
0
2
0
,
d
o
i
:
1
0
.
1
8
2
8
0
/ri
a
.
3
4
0
3
1
0
.
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.
24
,
No
.
2
,
No
v
em
b
er
2
0
2
1
:
1
1
0
0
-
1
1
0
6
1106
[1
2
]
R.
S
a
m
rin
a
n
d
D.
Va
su
m
a
th
i,
"
R
e
v
iew
o
n
a
n
o
m
a
ly
b
a
se
d
n
e
two
r
k
in
tr
u
sio
n
d
e
tec
ti
o
n
sy
ste
m
,
"
2
0
1
7
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
El
e
c
trica
l,
El
e
c
tro
n
ics
,
C
o
mm
u
n
ic
a
ti
o
n
,
C
o
mp
u
te
r,
a
n
d
Op
t
imiza
ti
o
n
T
e
c
h
n
i
q
u
e
s
(ICEE
CCOT
)
,
2
0
1
7
,
p
p
.
1
4
1
-
1
4
7
,
d
o
i:
1
0
.
1
1
0
9
/I
CEE
CCOT.2
0
1
7
.
8
2
8
4
6
5
5
.
[1
3
]
S
.
H.
Ha
sh
e
m
M
a
h
m
o
o
d
a
n
d
A
.
Ha
fz
a
,
"
Ne
two
rk
in
tr
u
sio
n
d
e
tec
ti
o
n
s
y
ste
m
(NID
S
)
in
c
l
o
u
d
e
n
v
iro
n
m
e
n
t
b
a
se
d
o
n
h
id
d
e
n
Na
ïv
e
Ba
y
e
s
m
u
lt
icla
s
s
c
las
sifier,"
Al
-
M
u
st
a
n
siriy
a
h
J
o
u
rn
a
l
o
f
S
c
ien
c
e
,
v
o
l.
2
8
,
n
o
.
2
,
2
0
1
7
,
d
o
i:
1
0
.
2
3
8
5
1
/mjs
.
v
2
8
i2
.
5
0
8
.
[1
4
]
S
.
H.
Ha
sh
e
m
,
"
Eff
icie
n
c
y
o
f
S
v
m
a
n
d
P
c
a
t
o
e
n
h
a
n
c
e
in
tru
si
o
n
d
e
tec
ti
o
n
sy
ste
m
,
"
J
o
u
rn
a
l
o
f
Asia
n
S
c
ien
ti
fi
c
Res
e
a
rc
h
,
v
o
l.
3
,
n
o
.
4
p
.
3
8
1
,
2
0
1
3
,
d
o
i:
[1
5
]
S
.
K
M
a
jee
d
,
S
.
H.
Ha
sh
e
m
,
a
n
d
I
.
K.
G
b
a
sh
i,
"
P
r
o
p
o
se
h
m
n
id
s
h
y
b
rid
m
u
lt
il
e
v
e
l
n
e
two
r
k
i
n
tr
u
sio
n
d
e
tec
ti
o
n
sy
ste
m
,"
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Co
mp
u
ter
S
c
ien
c
e
Iss
u
e
s (IJCS
I),
v
ol
.
1
0
,
n
o
.
5
,
2
0
1
3
,
d
o
i:
[1
6
]
X
.
Do
n
g
,
Z
.
Yu
,
CAO
2
.
We
n
m
in
g
,
S
.
H
.
I
Yifa
n
,
a
n
d
M
.
A
.
Qia
n
l
i,
"
A
su
rv
e
y
o
n
e
n
se
m
b
le
lea
rn
in
g
,
"
Fro
n
ti
e
rs
o
f
Co
mp
u
ter
S
c
ien
c
e
,
v
o
l.
1
4
,
n
o
.
2
,
p
p
.
2
4
1
-
2
5
8
,
2
0
2
0
,
d
o
i:
1
0
.
1
0
0
7
/s
1
1
7
0
4
-
0
1
9
-
8
2
0
8
-
z
.
[1
7
]
T
.
G
o
k
su
,
a
n
d
D
.
Bira
n
t,
"
En
h
a
n
c
e
d
b
a
g
g
in
g
(e
Ba
g
g
i
n
g
)
:
A
n
o
v
e
l
a
p
p
ro
a
c
h
f
o
r
e
n
se
m
b
le
lea
rn
in
g
,
"
T
h
e
In
ter
n
a
t
io
n
a
l
Ara
b
J
o
u
r
n
a
l
o
f
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
lo
g
y
,
v
o
l.
1
7
,
n
o
.
4
,
J
u
ly
2
0
2
0
,
d
o
i:
1
0
.
3
4
0
2
8
/
iajit
/
1
7
/
4
/1
0
.
[1
8
]
L.
Yih
e
n
g
a
n
d
W
.
C
h
e
n
,
"
A
Co
m
p
a
ra
ti
v
e
P
e
rfo
rm
a
n
c
e
As
se
ss
m
e
n
t
o
f
En
se
m
b
le
Lea
rn
i
n
g
f
o
r
Cre
d
it
S
c
o
rin
g
,
"
M
a
th
e
ma
t
ics
,
v
o
l.
8
,
n
o
.
1
0
,
p
.
1
7
5
6
,
d
o
i:
1
0
.
3
3
9
0
/ma
th
8
1
0
1
7
5
6
.
[1
9
]
S
.
K.
S
in
g
h
,
K
.
K.
Be
jag
a
m
,
Y
.
An
,
a
n
d
S
.
A.
De
sh
m
u
k
h
,
“
M
a
c
h
in
e
-
lea
rn
i
n
g
b
a
se
d
sta
c
k
e
d
e
n
se
m
b
le
m
o
d
e
l
f
o
r
a
c
c
u
ra
te
a
n
a
ly
sis
o
f
m
o
lec
u
lar
d
y
n
a
m
ics
sim
u
latio
n
s,
"
T
h
e
J
o
u
r
n
a
l
o
f
P
h
y
sic
a
l
Ch
e
mistr
y
A
,
v
o
l.
1
2
3
,
n
o
.
2
4
,
p
p
.
5
1
9
0
-
5
1
9
8
,
2
0
1
9
,
d
o
i:
1
0
.
1
0
2
1
/ac
s.jp
c
a
.
9
b
0
3
4
2
0
.
[2
0
]
C
.
S
a
rik
a
,
a
n
d
N
.
Ke
ss
wa
n
i
,
"
An
a
ly
sis
o
f
KD
D
-
Cu
p
’9
9
,
NSL
-
KD
D
a
n
d
UN
S
W
-
NB1
5
d
a
tas
e
ts
u
sin
g
d
e
e
p
lea
rn
i
n
g
in
Io
T,
"
El
se
v
ier
J
o
u
rn
a
l
,
v
o
l
.
1
6
7
,
p
p
.
1
5
6
1
-
1
5
7
3
,
2
0
2
0
,
d
o
i:
1
0
.
1
0
1
6
/j
.
p
ro
c
s.2
0
2
0
.
0
3
.
3
6
7
.
[2
1
]
M
.
K.
S
y
d
n
e
y
a
n
d
Y.
S
u
n
,
"
P
e
rfo
rm
a
n
c
e
a
n
a
ly
sis
o
f
i
n
tr
u
sio
n
d
e
tec
ti
o
n
s
y
ste
m
s
u
sin
g
a
fe
a
t
u
re
se
lec
ti
o
n
m
e
th
o
d
o
n
t
h
e
UN
S
W
-
NB1
5
d
a
tas
e
t,
"
J
o
u
rn
a
l
o
f
Bi
g
Da
t
a
,
v
o
l
.
7
,
n
o
.
1
p
p
.
1
-
2
0
,
2
0
2
0
,
d
o
i:
1
0
.
1
1
8
6
/s4
0
5
3
7
-
0
2
0
-
0
0
3
7
9
-
6
.
[2
2
]
A.
Ba
to
o
l,
A.
G
h
a
m
d
i,
S
.
Ka
m
e
l
,
a
n
d
M
.
Kh
a
y
y
a
t,
"
E
v
a
lu
a
ti
o
n
o
f
Artifi
c
ial
Ne
u
ra
l
Ne
two
rk
s
P
e
rfo
rm
a
n
c
e
Us
in
g
Va
rio
u
s
No
rm
a
li
z
a
ti
o
n
M
e
th
o
d
s
fo
r
Wate
r
De
m
a
n
d
F
o
re
c
a
stin
g
,
"
2
0
2
1
Na
ti
o
n
a
l
Co
mp
u
ti
n
g
Co
l
leg
e
s
Co
n
fer
e
n
c
e
(NCCC)
,
IEE
E,
2
0
2
1
,
p
p
.
1
-
6
,
d
o
i
:
1
0
.
1
1
0
9
/NCCC4
9
3
3
0
.
2
0
2
1
.
9
4
2
8
8
5
6
.
[2
3
]
R
.
R.
Zeb
a
ri
,
A
.
M
.
Ab
d
u
laz
e
e
z
,
D
.
Q
.
Zee
b
a
re
e
,
D
.
A
.
Zeb
a
ri
,
a
n
d
J
.
N
.
S
a
e
e
d
"
A
c
o
m
p
re
h
e
n
siv
e
re
v
iew
o
f
d
ime
n
sio
n
a
l
it
y
re
d
u
c
ti
o
n
tec
h
n
i
q
u
e
s
fo
r
fe
a
tu
re
se
lec
ti
o
n
a
n
d
fe
a
tu
re
e
x
trac
ti
o
n
,
"
J
o
u
rn
a
l
o
f
A
p
p
li
e
d
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
T
re
n
d
s
,
v
o
l.
1
,
n
o
.
2
,
p
p
.
5
6
-
7
0
,
2
0
2
0
,
d
o
i:
1
0
.
3
8
0
9
4
/j
a
stt1
2
2
4
.
[2
4
]
N
.
M
.
N
.
M
a
th
i
v
a
n
a
n
,
N
.
A
.
M
d
.
G
h
a
n
i,
a
n
d
R
.
M
.
Ja
n
o
r,
"
A
c
o
m
p
a
ra
ti
v
e
stu
d
y
o
n
d
ime
n
si
o
n
a
li
ty
re
d
u
c
ti
o
n
b
e
twe
e
n
p
rin
c
ip
a
l
c
o
m
p
o
n
e
n
t
a
n
a
ly
sis
a
n
d
k
-
m
e
a
n
s
c
lu
ste
rin
g
G
e
n
e
ti
c
a
lg
o
rit
h
m
fo
r
in
tr
u
sio
n
d
e
te
c
ti
o
n
sy
ste
m
in
c
o
m
p
u
ter
n
e
tw
o
rk
,
"
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
6
,
n
o
.
2
,
p
p
.
7
5
2
-
758
,
No
v
e
m
b
e
r
2
0
1
9
,
d
o
i
:
1
0
.
1
1
5
9
1
/i
jee
c
s.v
1
6
.
i2
.
p
p
7
5
2
-
7
5
8
.
[2
5
]
Wo
sia
k
,
A
g
n
ies
z
k
a
,
a
n
d
D
.
Zak
rz
e
ws
k
a
,
"
In
te
g
ra
ti
n
g
c
o
rre
lati
o
n
-
b
a
se
d
fe
a
tu
re
se
lec
ti
o
n
a
n
d
c
lu
ste
rin
g
fo
r
imp
ro
v
e
d
c
a
rd
io
v
a
sc
u
lar d
ise
a
se
d
iag
n
o
sis,"
Co
mp
lex
it
y
,
2
0
1
8
,
d
o
i
:
h
tt
p
s:
1
0
.
1
1
5
5
/
2
0
1
8
/
2
5
2
0
7
0
6
.
[2
6
]
R
.
Bo
b
b
y
e
t
a
l
.
,
"
DU
BS
tep
R:
c
o
rre
latio
n
-
b
a
se
d
fe
a
tu
re
se
lec
ti
o
n
fo
r
c
lu
ste
rin
g
si
n
g
le
-
c
e
ll
R
NA
se
q
u
e
n
c
in
g
Da
ta,"
b
io
Rxiv
(2
0
2
1
)
,
2
0
2
0
-
1
0
,
d
o
i:
1
0
.
1
1
0
1
/
2
0
2
0
.
1
0
.
0
7
.
3
3
0
5
6
3
.
[2
7
]
L.
Ali,
C.
Zh
u
,
N.
A.
G
o
li
larz
,
A.
Ja
v
e
e
d
,
M
.
Zh
o
u
a
n
d
Y.
L
iu
,
"
Re
li
a
b
le
P
a
rk
i
n
so
n
’s
Dise
a
se
De
tec
ti
o
n
b
y
An
a
ly
z
in
g
Ha
n
d
writ
ten
Dra
win
g
s:
Co
n
str
u
c
ti
o
n
o
f
a
n
Un
b
ias
e
d
Ca
sc
a
d
e
d
Lea
rn
in
g
S
y
ste
m
Ba
se
d
o
n
F
e
a
tu
r
e
S
e
lec
ti
o
n
a
n
d
Ad
a
p
t
iv
e
Bo
o
stin
g
M
o
d
e
l
,
"
i
n
IEE
E
Acc
e
ss
,
v
o
l.
7
,
p
p
.
1
1
6
4
8
0
-
1
1
6
4
8
9
,
2
0
1
9
,
d
o
i:
1
0
.
1
1
0
9
/ACCES
S
.
2
0
1
9
.
2
9
3
2
0
3
7
.
Evaluation Warning : The document was created with Spire.PDF for Python.