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.
3
8
,
No
.
2
,
Ma
y
20
2
5
,
p
p
.
887
~
8
9
6
I
SS
N:
2
502
-
4
7
52
,
DOI
: 1
0
.
1
1
5
9
1
/ijee
cs
.v
3
8
.
i
2
.
pp
887
-
8
9
6
887
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 in c
lus
tering
wi
reless net
wo
rk by
apply
ing
ex
tr
eme learn
ing
ma
chine wi
th
de
e
p neural n
etwork
a
lg
o
rithm
P
a
la
nira
j
Ra
j
idu
ra
i P
a
rv
a
t
h
y
1
,
Sa
t
heesh
k
um
a
r
Seka
r
1
,
B
ha
ra
t
T
idk
e
2
,
Rudra
ra
j
u
L
ee
la
J
y
o
t
hi
3
,
Venug
o
pa
l
Su
j
a
t
ha
4
,
M
a
da
p
pa
Sh
a
nm
ug
a
t
ha
i
5
,
Su
bb
ia
h
M
urug
a
n
6
1
P
r
o
j
e
c
t
M
a
n
a
g
e
r
,
M
p
h
a
si
s
C
o
r
p
o
r
a
t
i
o
n
,
C
h
a
n
d
l
e
r
,
A
r
i
z
o
n
a
,
U
n
i
t
e
d
S
t
a
t
e
s
o
f
A
meri
c
a
2
S
y
m
b
i
o
si
s
I
n
st
i
t
u
t
e
o
f
Te
c
h
n
o
l
o
g
y
N
a
g
p
u
r
C
a
mp
u
s
,
S
y
m
b
i
o
s
i
s
i
n
t
e
r
n
a
t
i
o
n
a
l
(
D
e
e
me
d
)
U
n
i
v
e
r
si
t
y
,
P
u
n
e
,
I
n
d
i
a
3
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
S
a
g
i
R
a
ma
K
r
i
sh
n
a
m
R
a
j
u
En
g
i
n
e
e
r
i
n
g
C
o
l
l
e
g
e
(
A
)
,
B
h
i
ma
v
a
r
a
m
,
I
n
d
i
a
4
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
A
p
p
l
i
c
a
t
i
o
n
s,
S
.
A
.
En
g
i
n
e
e
r
i
n
g
C
o
l
l
e
g
e
,
C
h
e
n
n
a
i
,
I
n
d
i
a
5
De
p
a
r
t
me
n
t
o
f
E
n
g
l
i
s
h
,
S
r
i
S
a
i
r
a
m
E
n
g
i
n
e
e
r
i
n
g
C
o
l
l
e
g
e
,
C
h
e
n
n
a
i
,
I
n
d
i
a
6
D
e
p
a
r
t
me
n
t
o
f
B
i
o
m
e
d
i
c
a
l
E
n
g
i
n
e
e
r
i
n
g
,
S
a
v
e
e
t
h
a
S
c
h
o
o
l
o
f
E
n
g
i
n
e
e
r
i
n
g
,
S
a
v
e
e
t
h
a
I
n
st
i
t
u
t
e
o
f
M
e
d
i
c
a
l
a
n
d
Te
c
h
n
i
c
a
l
S
c
i
e
n
c
e
s
,
S
a
v
e
e
t
h
a
U
n
i
v
e
r
si
t
y
,
C
h
e
n
n
a
i
,
I
n
d
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Feb
24
,
2
0
2
4
R
ev
is
ed
Oct
26
,
202
4
Acc
ep
ted
No
v
11
,
2
0
2
4
No
wa
d
a
y
s,
in
tr
u
sio
n
d
e
tec
ti
o
n
s
y
ste
m
s
(IDSs)
h
a
v
e
g
ro
wi
n
g
l
y
c
o
m
e
to
b
e
c
o
n
sid
e
re
d
a
s
a
n
imp
o
rtan
t
m
e
th
o
d
o
wi
n
g
to
t
h
e
ir
p
o
ss
ib
le
to
e
x
p
a
n
d
in
to
a
k
e
y
fa
c
to
r,
w
h
ich
is
c
ru
c
ial
f
o
r
t
h
e
se
c
u
rit
y
o
f
wire
les
s
n
e
two
r
k
s.
I
n
wire
les
s
n
e
two
rk
,
w
h
e
n
th
e
re
is
a
th
o
u
s
a
n
d
ti
m
e
s
m
o
re
traffic,
th
e
e
ffe
c
ti
v
e
n
e
ss
o
f
n
o
rm
a
l
IDS
to
id
e
n
ti
f
y
h
o
stil
e
n
e
t
wo
rk
i
n
tr
u
sio
n
s
is
d
e
c
re
a
se
d
b
y
a
n
a
v
e
ra
g
e
fa
c
to
r.
Th
is
is
b
e
c
a
u
se
o
f
th
e
e
x
p
o
n
e
n
ti
a
l
g
ro
wt
h
i
n
n
e
tw
o
rk
traffic.
Th
is
is
d
u
e
t
o
t
h
e
d
e
c
re
a
se
d
n
u
m
b
e
r
o
f
p
o
ss
ib
i
li
ti
e
s
t
o
d
isc
o
v
e
r
t
h
e
in
t
ru
sio
n
s.
T
h
is
is
b
e
c
a
u
se
th
e
re
a
re
fe
we
r
o
p
p
o
rt
u
n
it
ies
t
o
se
e
p
o
ss
ib
le
risk
s.
We
in
ten
d
a
n
e
x
trem
e
lea
rn
in
g
m
a
c
h
in
e
with
d
e
e
p
n
e
u
ra
l
n
e
two
r
k
(DN
N)
a
lg
o
r
i
th
m
-
b
a
se
d
i
n
tru
si
o
n
d
e
tec
ti
o
n
in
c
lu
ste
ri
n
g
(EI
DC)
wire
les
s
n
e
two
r
k
.
Th
e
m
a
in
o
b
jec
ti
v
e
o
f
th
is
a
rti
c
le
is
t
o
d
e
tec
t
th
e
in
tr
u
sio
n
e
fficie
n
t
ly
a
n
d
m
in
imiz
e
th
e
fa
lse
a
larm
ra
te.
Th
is
m
e
c
h
a
n
ism
u
ti
li
z
e
s
th
e
e
x
t
re
m
e
lea
rn
in
g
m
a
c
h
in
e
(EL
M
)
with
a
d
e
e
p
n
e
u
ra
l
n
e
tw
o
rk
a
lg
o
r
it
h
m
fo
r
o
p
t
imiz
in
g
t
h
e
we
ig
h
ts
o
f
in
p
u
t
a
n
d
h
i
d
d
e
n
n
o
d
e
b
ias
e
s
to
d
e
d
u
c
e
th
e
n
e
tw
o
rk
o
u
t
p
u
t
we
ig
h
ts.
S
imu
latio
n
o
u
tco
m
e
s
il
l
u
stra
te
th
a
t
th
e
EIDC
m
e
c
h
a
n
ism
n
o
t
o
n
l
y
a
ss
u
re
s
a
b
e
tt
e
r
a
c
c
u
ra
c
y
fo
r
d
e
tec
ti
o
n
,
c
o
n
sid
e
ra
b
ly
m
i
n
imiz
e
s
a
n
in
tr
u
sio
n
d
e
tec
ti
o
n
ti
m
e
,
a
n
d
sh
o
rten
s
th
e
fa
lse
a
larm
ra
te.
K
ey
w
o
r
d
s
:
C
lu
s
ter
in
g
Dee
p
n
eu
r
al
n
etwo
r
k
E
x
tr
em
e
lear
n
in
g
m
ac
h
in
e
alg
o
r
ith
m
I
n
tr
u
s
io
n
d
etec
tio
n
W
ir
eles
s
n
etwo
r
k
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
:
B
h
ar
at
T
id
k
e
Sy
m
b
io
s
is
I
n
s
titu
te
o
f
T
ec
h
n
o
lo
g
y
Nag
p
u
r
C
am
p
u
s
,
Sy
m
b
io
s
is
in
ter
n
atio
n
al
(
Dee
m
ed
)
Un
iv
er
s
ity
Pu
n
e,
I
n
d
ia
E
m
ail:
b
atid
k
e@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
B
ec
au
s
e
o
f
th
e
en
h
an
ce
d
ass
o
ciatio
n
b
etwe
en
n
o
d
es,
th
e
r
e
ce
p
tiv
ity
o
f
wir
eless
n
etwo
r
k
o
p
er
atio
n
ar
ea
s
,
an
d
th
e
tr
a
n
s
itio
n
ca
p
ab
ilit
y
,
th
e
wir
eless
n
etwo
r
k
is
s
u
s
ce
p
tib
le
to
in
tr
u
s
io
n
s
.
T
h
is
r
esu
lts
in
a
s
ig
n
if
ican
t
in
cr
ea
s
e
in
th
e
d
is
clo
s
u
r
e
o
f
d
an
g
e
r
s
th
at
in
tim
i
d
ate
th
e
av
ailab
ilit
y
o
f
in
f
o
r
m
atio
n
s
y
s
tem
s
in
th
e
n
etwo
r
k
s
y
s
tem
in
f
r
astru
ctu
r
e
[
1
]
.
An
I
DS
to
o
b
s
er
v
e,
id
e
n
tify
,
an
d
n
o
tify
a
b
o
u
t
h
o
s
tile
a
ctiv
ity
[
2
]
.
Sev
er
al
s
tu
d
ies
an
aly
ze
th
e
d
etec
tio
n
an
d
p
r
e
v
en
tio
n
m
o
d
els;
m
o
r
e
o
v
er
,
th
er
e
n
ee
d
s
to
b
e
m
o
r
e
co
n
s
is
ten
cy
in
th
e
o
p
p
o
r
tu
n
is
tic
d
ev
elo
p
m
en
ts
in
th
e
m
o
d
els
[
3
]
.
I
n
ad
d
itio
n
,
t
h
e
cu
r
r
en
tly
u
s
ed
m
o
d
els
co
m
e
with
a
n
u
m
b
er
o
f
r
estrictio
n
s
th
at
n
ee
d
to
b
e
in
v
esti
g
ated
b
ef
o
r
e
an
y
n
ew
s
ec
u
r
ity
m
o
d
els
ca
n
b
e
d
ev
elo
p
ed
.
I
DS
s
tan
d
s
f
o
r
in
tellig
en
t
d
ata
s
ec
u
r
ity
an
d
is
a
s
y
s
tem
th
at
co
o
r
d
in
ates
th
e
o
p
er
atio
n
s
o
f
h
o
s
ts
an
d
n
etwo
r
k
s
.
T
h
is
p
er
f
o
r
m
s
an
an
aly
s
is
o
f
th
e
p
ac
k
ets
th
at
ar
e
b
ei
n
g
tr
a
n
s
p
o
r
ted
o
v
er
th
e
n
etwo
r
k
,
s
ea
r
ch
es
f
o
r
p
o
ten
tially
m
alicio
u
s
o
cc
u
r
r
e
n
ce
s
,
an
d
th
e
n
p
r
o
ce
s
s
es th
e
aler
t sig
n
al
[
4
]
.
I
DS h
a
v
e
g
ar
n
er
e
d
m
u
c
h
atten
tio
n
,
a
n
d
s
ev
er
al
p
r
o
m
in
en
t
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
8
,
No
.
2
,
May
20
2
5
:
8
8
7
-
8
9
6
888
m
o
d
els
h
av
e
b
ee
n
p
r
esen
ted
t
o
cr
ea
te
an
in
te
n
s
iv
e
s
ec
u
r
ity
f
r
am
ewo
r
k
.
W
ith
in
th
is
f
r
am
e
wo
r
k
,
th
e
f
u
n
ctio
n
o
f
I
DS
is
to
ex
am
in
e
th
e
f
r
e
s
h
d
if
f
icu
lties
to
d
is
co
v
er
v
ia
b
le
way
s
to
s
o
lv
e
th
e
co
n
ce
r
n
s
in
th
e
d
et
ec
tio
n
m
o
d
els.
T
h
e
v
ar
i
o
u
s
cu
r
r
e
n
t
d
etec
tio
n
m
eth
o
d
s
in
ter
m
s
o
f
p
er
f
o
r
m
an
ce
,
u
s
ag
e
o
f
a
v
ailab
le
b
an
d
wid
th
,
am
o
u
n
t
o
f
tim
e
r
e
q
u
ir
ed
f
o
r
d
etec
tio
n
,
an
d
o
v
er
lo
a
d
in
g
o
f
p
r
o
ce
s
s
o
r
s
[
5
]
.
I
t
is
a
m
ajo
r
is
s
u
e
th
at
m
a
y
l
ea
d
to
a
b
r
ea
ch
in
s
ec
u
r
ity
a
n
d
is
o
n
e
o
f
th
e
k
ey
ca
u
s
es
o
f
s
ec
u
r
ity
b
r
ea
ch
es
s
in
ce
a
s
in
g
le
in
s
tan
ce
o
f
in
tr
u
s
io
n
ca
n
r
em
o
v
e
d
a
ta
f
r
o
m
a
wir
eless
n
etwo
r
k
in
s
ec
o
n
d
s
o
r
d
elete
it
to
tally
.
Sin
ce
,
in
tr
u
s
io
n
is
o
n
e
o
f
th
e
p
r
im
a
r
y
ca
u
s
es
o
f
s
ec
u
r
ity
b
r
ea
ch
es
[
6
]
.
An
in
tr
u
s
io
n
m
ig
h
t
p
o
ten
tially
ca
u
s
e
p
h
y
s
ical
d
am
ag
e
to
a
n
etwo
r
k
.
I
n
ad
d
itio
n
,
an
i
n
tr
u
s
io
n
m
ay
r
esu
lt
in
m
ass
iv
e
f
in
a
n
cial
lo
s
s
es
an
d
p
u
t
th
e
cr
u
cial
in
f
r
astru
ctu
r
e
o
f
in
f
o
r
m
atio
n
tech
n
o
l
o
g
y
at
r
is
k
,
wh
ich
ca
n
e
v
en
tu
ally
c
o
n
tr
ib
u
te
to
an
in
f
o
r
m
atio
n
d
is
ad
v
an
tag
e
in
t
h
e
e
v
en
t
o
f
a
c
y
b
er
-
c
o
n
f
lic
t.
C
o
n
s
eq
u
en
tly
,
b
o
t
h
th
e
p
r
ev
en
tio
n
o
f
i
n
tr
u
s
io
n
s
an
d
th
e
id
en
tific
atio
n
o
f
th
o
s
e
th
at
h
a
v
e
alr
ea
d
y
o
cc
u
r
r
e
d
ar
e
o
b
lig
at
o
r
y
an
d
ess
en
tial ta
s
k
s
[
7
]
.
T
h
e
ac
cu
r
ac
y
o
f
th
ese
m
an
y
way
s
f
o
r
d
etec
tin
g
in
tr
u
s
io
n
s
is
s
till
an
is
s
u
e
s
in
ce
ac
cu
r
ac
y
is
b
ased
o
n
th
e
d
etec
tio
n
r
ate
as
well
as
th
e
r
ate
o
f
f
alse
alar
m
s
.
Alth
o
u
g
h
th
e
r
e
ar
e
a
r
an
g
e
o
f
m
e
th
o
d
s
f
o
r
d
etec
tin
g
in
tr
u
s
io
n
s
,
th
e
ac
cu
r
ac
y
o
f
th
ese
m
eth
o
d
s
s
till
n
ee
d
s
to
b
e
im
p
r
o
v
ed
.
Fin
d
in
g
a
s
o
lu
tio
n
to
th
e
p
r
o
b
lem
o
f
ac
cu
r
ac
y
is
im
p
o
r
tan
t
in
o
r
d
er
to
r
ed
u
ce
th
e
f
alse
ala
r
m
co
u
n
t
a
n
d
in
cr
ea
s
e
t
h
e
p
r
o
p
o
r
tio
n
o
f
s
u
cc
ess
f
u
l
d
etec
tio
n
s
[
8
]
.
T
h
e
in
v
esti
g
ati
o
n
th
at
was
ca
r
r
ied
o
u
t
was
p
r
o
m
p
ted
b
y
th
e
n
o
tio
n
th
at
w
as
p
r
esen
ted
h
er
e.
T
h
e
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
(
SVM)
,
r
an
d
o
m
f
o
r
est
(
R
F),
an
d
E
L
M
tech
n
iq
u
es
ar
e
all
m
et
h
o
d
s
th
at
h
av
e
b
ee
n
p
r
o
v
e
n
to
b
e
ef
f
ec
tiv
e
in
th
eir
ab
ilit
y
to
tack
le
th
e
class
if
ica
tio
n
task
.
C
o
m
p
ar
ed
to
th
e
SVM,
R
F,
an
d
E
L
M
m
ec
h
an
is
m
s
,
th
e
E
L
M
alg
o
r
ith
m
p
er
f
o
r
m
s
b
etter
t
h
an
o
t
h
er
alg
o
r
ith
m
s
[
9
]
.
I
n
o
r
d
er
to
id
en
tif
y
in
tr
u
s
io
n
s
,
an
I
DS
was
u
s
ed
,
an
d
f
o
r
th
i
s
p
u
r
p
o
s
e,
ML
alg
o
r
it
h
m
s
wer
e
u
tili
ze
d
.
T
r
ad
itio
n
al
ML
alg
o
r
ith
m
s
,
s
u
ch
as
th
e
SVM,
th
e
k
n
ee
-
h
ig
h
est
n
eig
h
b
o
r
(
KNN)
,
an
d
f
ilter
-
b
ased
f
ea
tu
r
e
s
elec
tio
n
,
o
f
ten
r
esu
lted
in
in
ac
cu
r
ate
class
if
icatio
n
s
an
d
lo
w
lev
els
o
f
p
r
ec
is
io
n
.
T
h
e
m
eth
o
d
is
th
e
B
o
r
u
ta
f
ea
tu
r
e
s
elec
tio
n
with
g
r
id
s
e
ar
ch
r
an
d
o
m
f
o
r
est
(
B
FS
F).
T
h
e
o
b
jectiv
e
o
f
th
is
alg
o
r
ith
m
is
to
en
h
an
ce
th
e
class
if
ier
'
s
p
er
f
o
r
m
an
ce
b
y
u
s
in
g
a
f
ea
tu
r
e
s
elec
tio
n
a
p
p
r
o
ac
h
.
B
FS
F
m
ec
h
an
is
m
th
at
f
o
r
m
u
lates
a
f
r
ee
-
f
r
o
m
-
n
o
is
e
as
well
as
f
alse
f
o
r
ec
ast
in
g
.
Ho
we
v
er
,
T
h
is
m
ec
h
a
n
is
m
in
cr
ea
s
es
th
e
tr
ain
in
g
tim
e
d
u
r
in
g
ar
r
i
v
in
g
n
ew
attac
k
s
[
1
0
]
.
I
t
is
an
I
DS'
s
r
o
le
to
n
o
tice
a
n
y
ac
ts
th
at
m
ig
h
t
p
o
s
s
ib
ly
b
e
d
etr
im
en
tal.
I
t
m
a
y
r
ef
e
r
to
a
b
r
o
ad
g
r
o
u
p
o
f
s
y
s
tem
s
,
th
e
in
p
u
t
o
f
wh
ic
h
is
a
tr
af
f
ic
s
o
u
r
ce
an
d
th
e
o
u
tp
u
t
o
f
wh
ich
is
a
class
if
ic
atio
n
ju
d
g
m
e
n
t
o
n
wh
eth
er
o
r
n
o
t
a
g
iv
en
in
s
tan
ce
is
m
alicio
u
s
.
Ho
s
t
-
b
ased
an
d
n
etwo
r
k
-
b
ased
I
DS
ar
e
two
p
r
im
a
r
y
class
if
icatio
n
s
.
I
DS
th
at
ar
e
h
o
s
t
-
b
ased
g
ath
er
d
ata
f
r
o
m
th
e
im
m
ed
iate
ar
ea
,
b
u
t
I
DS
th
a
t
ar
e
n
etwo
r
k
-
b
ase
d
h
av
e
ac
ce
s
s
to
in
f
o
r
m
atio
n
o
n
a
g
lo
b
al
s
ca
le.
E
ith
er
in
d
iv
id
u
al
n
etwo
r
k
p
ac
k
ets
o
r
th
e
wh
o
le
f
lo
w
o
f
p
ac
k
ets
m
ay
b
e
ex
am
in
ed
an
d
an
aly
ze
d
in
o
r
d
er
to
d
eter
m
in
e
wh
eth
er
o
r
n
o
t
a
ce
r
tain
ac
tio
n
o
n
th
e
n
etwo
r
k
is
h
ar
m
f
u
l.
Fro
m
t
h
e
m
o
m
en
t
th
ey
ar
e
c
o
n
ce
iv
e
d
u
n
til
th
e
m
o
m
en
t
th
ey
ar
e
p
u
t
in
to
o
p
e
r
atio
n
,
n
etwo
r
k
I
DS
ar
e
f
ac
ed
with
a
ch
allen
g
e
in
th
e
f
o
r
m
o
f
a
r
is
e
in
th
e
co
u
n
t
o
f
a
s
s
o
ciate
d
d
ev
ices
an
d
a
co
n
tin
u
al
d
ev
elo
p
m
e
n
t
in
th
e
m
eth
o
d
s
an
d
s
tr
ateg
ies
th
at
attac
k
er
s
u
s
e.
T
h
is
tech
n
iq
u
e
s
ep
ar
ates
th
e
r
is
k
o
f
m
alev
o
len
t
b
e
h
av
io
r
d
ep
en
d
i
n
g
o
n
ML
[
1
1
]
.
An
en
h
an
ce
d
d
ee
p
b
elief
n
et
wo
r
k
(
DB
N)
.
T
r
ad
itio
n
al
n
eu
r
al
n
etwo
r
k
tr
ain
in
g
tech
n
iq
u
es,
s
u
ch
as
B
ac
k
Pro
p
ag
atio
n
(
B
P),
b
eg
i
n
tr
ain
in
g
a
m
o
d
el
with
f
ix
e
d
p
a
r
am
eter
s
,
s
u
ch
as
th
e
r
a
n
d
o
m
ly
in
itialized
weig
h
ts
an
d
th
r
esh
o
l
d
s
.
T
h
is
m
ig
h
t
b
r
in
g
ab
o
u
t
ce
r
tain
d
r
a
wb
ac
k
s
,
s
u
ch
as
d
r
awin
g
th
e
m
o
d
el
to
th
e
lo
ca
l
o
p
tim
u
m
s
o
lu
tio
n
s
o
r
n
ee
d
in
g
a
len
g
th
y
tr
ain
in
g
tim
e,
b
u
t
it
i
s
s
till
th
e
m
o
s
t
co
m
m
o
n
ap
p
r
o
ac
h
.
Ker
n
el
-
b
ased
ex
tr
em
e
lear
n
in
g
m
ac
h
in
e
(
K
E
L
M)
th
at
h
as
th
e
ca
p
ab
ilit
y
o
f
s
u
p
er
v
is
ed
lear
n
in
g
an
d
will
r
esto
r
e
th
e
B
ac
k
Pro
p
ag
atio
n
m
et
h
o
d
.
I
n
lig
h
t o
f
th
e
is
s
u
e
o
f
in
ad
eq
u
ate
clas
s
if
icatio
n
o
p
er
atio
n
ex
p
licitly
o
f
ten
b
r
o
u
g
h
t
o
n
b
y
ar
b
itra
r
ily
lau
n
c
h
in
g
k
e
r
n
el
p
ar
am
eter
s
with
KE
L
M,
an
im
p
r
o
v
e
d
g
r
e
y
wo
lf
o
p
tim
izer
(
E
GW
O)
h
as
b
ee
n
d
ev
elo
p
e
d
to
o
p
tim
i
ze
th
e
n
et
wo
r
k
.
A
u
n
i
q
u
e
o
p
tim
izatio
n
ap
p
r
o
ac
h
th
at
co
m
b
in
es
in
n
er
an
d
o
u
ter
h
u
n
tin
g
h
as b
ee
n
cr
ea
ted
to
in
cr
ea
s
e
th
e
s
ea
r
ch
as we
ll a
s
o
p
tim
izatio
n
ab
ilit
y
[
1
2
]
.
A
tech
n
iq
u
e
f
o
r
d
etec
tin
g
n
e
two
r
k
in
tr
u
s
io
n
b
y
ap
p
ly
in
g
d
ec
is
io
n
tr
ee
(
DT
)
d
o
u
b
le
S
VM
with
hi
er
ar
ch
ical
clu
s
ter
in
g
.
T
h
is
ap
p
r
o
ac
h
is
ab
le
to
id
en
tify
a
v
ar
iety
o
f
v
ar
io
u
s
ty
p
es
o
f
I
DS
s
u
cc
ess
f
u
lly
.
T
o
b
eg
in
,
th
e
h
ier
ar
c
h
ical
clu
s
ter
in
g
alg
o
r
ith
m
is
u
s
ed
to
b
u
ild
th
e
DT
f
o
r
t
h
e
n
etwo
r
k
tr
af
f
ic
d
ata.
T
h
e
b
o
tto
m
-
u
p
m
er
g
i
n
g
m
eth
o
d
is
u
tili
ze
d
in
o
r
d
e
r
to
en
h
a
n
ce
th
e
d
is
co
n
n
ec
tio
n
o
f
th
e
u
p
p
er
n
o
d
es
th
at,
in
tu
r
n
,
m
in
im
izes th
e
er
r
o
r
co
llectio
n
th
at
o
cc
u
r
s
d
u
r
in
g
th
e
b
u
ild
i
n
g
o
f
th
e
DT
T
h
e
in
tr
u
s
io
n
d
ete
ctio
n
m
o
d
el
is
th
en
im
p
lem
en
ted
b
y
em
b
e
d
d
in
g
t
win
SVM
in
to
th
e
cr
ea
ted
DT
.
T
h
is
m
o
d
el
is
ab
le
to
id
en
tif
y
th
e
in
tr
u
s
io
n
t
y
p
e
[
1
3
]
s
u
cc
ess
f
u
lly
.
T
h
e
I
DS
ar
e
b
ased
o
n
d
ee
p
lear
n
in
g
(
D
L
)
an
d
p
r
esen
ts
an
in
-
d
ep
th
r
ev
iew
as
well
as
a
ca
teg
o
r
izatio
n
o
f
th
ese
s
ch
em
es.
I
t
d
o
es
th
is
b
y
d
iv
id
in
g
th
e
s
e
s
tr
ateg
ies
in
to
ca
teg
o
r
ies
b
y
th
e
m
an
y
k
i
n
d
s
o
f
DL
ap
p
r
o
ac
h
es
th
at
ar
e
u
s
ed
in
ea
ch
o
f
t
h
em
.
I
t
ex
p
lain
s
h
o
w
ac
cu
r
ate
r
ec
o
g
n
itio
n
o
f
in
tr
u
s
io
n
s
m
ay
b
e
ac
h
iev
ed
v
ia
DL
n
etwo
r
k
s
in
i
n
tr
u
s
io
n
d
etec
tio
n
[
1
4
]
.
ML
-
b
ased
Netwo
r
k
I
DS
f
u
n
ctio
n
s
o
n
f
lo
w
ch
ar
ac
ter
is
tics
g
ath
er
ed
v
ia
f
lo
w
ex
p
o
r
tatio
n
m
ec
h
an
is
m
s
.
T
h
ese
f
ea
tu
r
es
a
r
e
u
s
ed
to
d
etec
t
an
d
p
r
ev
e
n
t
n
etwo
r
k
in
tr
u
s
io
n
s
.
T
h
e
ML
a
n
d
DL
-
b
ased
NI
DS
s
o
lu
tio
n
s
p
r
esu
p
p
o
s
e
th
at
f
lo
w
in
f
o
r
m
atio
n
is
r
ec
eiv
ed
f
r
o
m
all
th
e
p
ac
k
ets
th
at
m
ak
e
u
p
th
e
f
lo
w.
E
v
e
n
if
s
am
p
lin
g
is
p
r
esen
t,
it
is
p
o
s
s
ib
le
to
co
n
d
u
ct
a
r
eliab
le
ass
ess
m
en
t
o
f
ML
-
b
ased
NI
DS
s
b
y
an
aly
zin
g
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:
2
5
0
2
-
4
7
52
I
n
tr
u
s
io
n
d
etec
tio
n
in
clu
s
teri
n
g
w
ir
eless
n
et
w
o
r
k
b
y
a
p
p
lyi
n
g
ex
tr
eme
… (
P
a
la
n
ir
a
j R
a
jid
u
r
a
i P
a
r
va
th
y
)
889
ef
f
ec
t
th
at
p
ac
k
et
s
am
p
lin
g
h
as
o
n
th
e
p
er
f
o
r
m
an
ce
an
d
ef
f
icien
cy
o
f
th
ese
s
y
s
tem
s
.
As
a
r
esu
lt
o
f
o
u
r
s
am
p
lin
g
s
tu
d
ies,
we
d
is
co
v
er
ed
th
at
m
alicio
u
s
f
lo
ws
o
f
a
s
m
aller
s
ize
(
in
ter
m
s
o
f
th
e
n
u
m
b
er
o
f
p
ac
k
ets),
h
av
e
a
h
ig
h
e
r
p
r
o
b
a
b
ilit
y
o
f
g
o
in
g
u
n
d
etec
ted
ev
en
with
lo
w
s
am
p
le
r
ates.
Fo
llo
wi
n
g
th
at,
u
s
in
g
th
e
ass
es
s
m
en
t
p
r
o
ce
s
s
th
at
h
ad
b
ee
n
s
u
g
g
ested
,
we
s
tu
d
ied
th
e
in
f
lu
en
ce
th
at
d
if
f
er
en
t
s
am
p
lin
g
s
tr
ateg
ies
h
ad
o
n
th
e
NI
DS d
etec
tio
n
r
ate
as
well
as th
e
f
alse a
lar
m
[
1
5
]
.
A
n
etwo
r
k
I
DS
o
p
er
ates
o
n
t
h
e
p
r
i
n
cip
le
o
f
s
elf
-
s
u
p
e
r
v
is
ed
lear
n
in
g
a
n
d
m
ak
es
it
p
o
s
s
ib
le
to
d
o
h
ier
ar
ch
ical
d
etec
tio
n
.
T
h
e
m
e
th
o
d
th
at
h
as b
ee
n
o
f
f
er
ed
co
n
s
is
t
s
o
f
v
ar
io
u
s
p
h
ases
o
f
d
etec
tio
n
,
o
n
e
o
f
wh
ic
h
is
th
e
ea
r
ly
id
e
n
tific
atio
n
o
f
ex
tr
em
e
o
u
tlier
s
,
wh
ich
,
i
f
le
f
t
u
n
ch
ec
k
ed
,
m
ig
h
t
d
o
s
ig
n
i
f
ican
t
h
ar
m
to
t
h
e
s
y
s
tem
.
I
n
ad
d
itio
n
,
it
d
o
es
i
n
-
d
ep
th
r
ee
x
am
in
atio
n
s
b
y
u
s
in
g
th
e
h
id
d
en
ar
ea
s
with
s
p
ec
ialized
an
o
m
aly
s
co
r
es,
wh
ich
u
ltima
tely
r
esu
lts
in
h
ig
h
d
etec
tio
n
ac
cu
r
ac
y
[
1
6
]
.
Un
s
u
p
er
v
is
ed
m
ac
h
in
e
le
ar
n
i
n
g
m
eth
o
d
s
ar
e
esp
ec
ially
attr
ac
tiv
e
to
I
DS
b
e
ca
u
s
e
o
f
th
eir
a
b
ilit
y
to
id
e
n
tify
k
n
o
wn
an
d
u
n
d
is
co
v
er
e
d
f
o
r
m
s
o
f
ass
au
lts
,
in
ad
d
itio
n
to
ze
r
o
-
d
ay
in
t
r
u
s
io
n
s
.
An
u
n
s
u
p
er
v
is
ed
an
o
m
aly
d
etec
tio
n
ap
p
r
o
ac
h
th
at
d
etec
ts
as
s
au
lts
wi
th
o
u
t
an
y
p
r
e
v
io
u
s
in
f
o
r
m
atio
n
b
y
c
o
m
b
in
in
g
s
u
b
-
s
p
ac
e
clu
s
ter
in
g
an
d
o
n
e
class
SVM
[
1
7
]
.
T
h
e
p
e
r
f
o
r
m
an
ce
an
d
p
r
e
d
ictio
n
ac
c
u
r
ac
y
o
f
an
o
m
aly
-
b
ased
ML
-
en
a
b
led
I
DS
(
AM
L
-
I
D
Ss
)
d
u
r
in
g
d
etec
tin
g
in
tr
u
s
io
n
s
is
m
u
c
h
l
o
wer
th
an
th
at
o
f
DL
I
DS.
Par
ticu
lar
ly
in
ef
f
ec
tiv
e
in
d
ete
ctin
g
in
tr
u
s
io
n
s
ar
e
AM
L
-
I
DS
s
y
s
tem
s
th
at
m
ak
e
u
s
e
o
f
l
o
w
-
co
m
p
lex
ity
m
o
d
els,
s
u
ch
as
th
e
p
r
in
cip
al
c
o
m
p
o
n
en
t
m
ac
h
in
e
ap
p
r
o
ac
h
an
d
th
e
o
n
e
-
class
S
VM
alg
o
r
ith
m
.
Ad
d
itio
n
ally
,
th
e
d
if
f
er
en
ce
s
b
etwe
en
th
e
d
ata
u
s
ed
f
o
r
test
in
g
an
d
th
e
d
ata
u
s
ed
f
o
r
tr
ain
in
g
lead
to
a
p
r
o
g
r
ess
iv
e
ly
g
r
ea
t
er
p
er
ce
n
tag
e
o
f
f
alse
p
o
s
itiv
es,
wh
ich
h
av
e
lo
w
r
ates
o
f
f
alse
alar
m
s
an
d
h
i
g
h
lev
els
o
f
p
r
ed
ictab
ilit
y
.
T
h
e
u
s
e
o
f
o
p
tim
izatio
n
s
tr
ateg
ies
to
im
p
r
o
v
e
t
h
e
p
er
f
o
r
m
an
ce
o
f
s
in
g
le
-
lear
n
e
r
[
1
8
]
.
I
DS
is
estab
li
s
h
ed
o
n
ML
to
e
n
s
u
r
e
s
ec
u
r
ity
.
T
h
e
b
ig
d
at
a
-
b
ased
h
ier
ar
ch
ical
DL
s
y
s
tem
m
ak
es
u
s
e
o
f
b
o
th
b
eh
av
io
r
al
an
d
co
n
ten
t
asp
ec
ts
in
o
r
d
er
t
o
g
et
an
u
n
d
e
r
s
tan
d
in
g
o
f
th
e
ch
a
r
ac
t
er
is
tics
o
f
n
etwo
r
k
tr
af
f
ic
as
well
as
d
ata
th
at
is
ca
r
r
ied
in
th
e
p
ay
lo
a
d
.
E
v
er
y
DL
m
o
d
el
p
ar
t
o
f
th
e
B
DHDL
S
f
o
cu
s
es
all
its
att
en
tio
n
an
d
en
e
r
g
y
o
n
m
aster
in
g
o
n
e
cl
u
s
ter
'
s
p
ar
ticu
lar
d
ata
d
is
tr
ib
u
tio
n
.
C
o
m
p
ar
ed
t
o
th
e
s
y
s
tem
s
th
a
t
r
elied
o
n
a
s
in
g
le
lear
n
in
g
m
o
d
el
in
th
e
p
ast,
th
is
m
eth
o
d
h
as
th
e
p
o
ten
tial
to
h
av
e
a
h
ig
h
er
r
ate
o
f
d
etec
tio
n
f
o
r
in
tr
u
s
iv
e
attac
k
s
[
1
9
]
.
I
DS
u
tili
ze
s
a
d
ee
p
lear
n
in
g
alg
o
r
ith
m
f
o
r
o
b
s
er
v
in
g
cr
i
tical
s
tr
u
ctu
r
es
an
d
d
etec
tin
g
th
e
in
tr
u
s
io
n
s
en
s
o
r
n
o
d
e
p
r
esen
t
in
th
e
n
etwo
r
k
.
Ho
wev
er
,
th
is
m
ec
h
a
n
is
m
r
a
is
es
th
e
f
alse
alar
m
r
ate
[
2
0
]
.
Sam
p
le
c
h
o
s
en
E
L
M
m
eth
o
d
ca
n
s
to
r
e
e
x
ce
p
tio
n
ally
h
u
g
e
v
o
lu
m
es
o
f
tr
ain
in
g
d
ata.
As
a
r
esu
lt,
th
ey
ar
e
s
av
ed
,
ca
lc
u
lated
,
an
d
s
am
p
led
b
y
th
e
s
er
v
er
s
h
o
u
s
ed
in
th
e
clo
u
d
.
Af
ter
th
at
,
th
e
ch
o
s
en
s
p
ec
im
en
is
s
en
t
as
tr
ain
in
g
m
ater
ial
t
o
t
h
e
h
o
s
ts
o
f
th
e
f
o
g
n
o
d
es.
A
lth
o
u
g
h
it
is
a
lig
h
tweig
h
t
m
eth
o
d
,
t
h
e
in
tr
u
s
io
n
d
etec
tio
n
p
r
o
ce
s
s
u
s
in
g
it
tak
e
s
a
m
u
ch
lo
n
g
er
p
er
io
d
o
f
tim
e
[
2
1
]
.
Dee
p
ex
tr
e
m
e
lear
n
in
g
m
ac
h
in
e
(
DE
L
M)
th
at
in
itially
b
u
ild
s
th
e
e
v
alu
a
tio
n
o
f
s
af
ety
ch
ar
ac
ter
is
tics
,
wh
ich
lead
s
to
th
eir
im
p
o
r
tan
ce
an
d
th
en
cr
ea
tes
an
ad
a
p
tiv
e
I
DS
f
o
cu
s
ed
o
n
t
h
e
r
elev
a
n
t
ch
a
r
ac
ter
is
tics
.
DE
L
M
s
tan
d
s
f
o
r
d
ee
p
lear
n
in
g
ex
tr
em
e
m
ac
h
i
n
e.
T
h
e
DE
L
M
-
b
ased
I
DS
ca
r
r
ies
o
u
t
d
ataset
ev
alu
atio
n
s
an
d
a
n
aly
ze
s
th
e
p
er
f
o
r
m
a
n
ce
asp
e
cts
to
ev
alu
ate
th
e
s
y
s
tem
'
s
d
ep
en
d
ab
ilit
y
[
2
2
]
.
I
DS,
wh
ich
is
b
ased
o
n
d
ee
p
lear
n
in
g
with
E
L
M,
is
m
ad
e
u
p
o
f
n
u
m
er
o
u
s
a
u
to
-
en
c
o
d
er
s
to
ex
tr
ac
t
in
-
d
ep
th
f
ea
t
u
r
es
f
r
o
m
th
e
in
it
ial
in
p
u
t.
Fo
llo
win
g
th
at,
th
e
e
x
tr
ac
ted
f
ea
tu
r
es
ar
e
in
s
er
ted
i
n
to
th
e
E
L
M
at
th
e
v
er
y
b
o
tto
m
o
f
th
e
h
id
d
e
n
lay
er
s
u
s
in
g
s
u
p
er
v
is
ed
lear
n
in
g
i
n
o
r
d
er
to
r
ec
o
g
n
ize
th
e
v
ar
i
o
u
s
f
o
r
m
s
o
f
attac
k
s
.
Ho
wev
er
,
i
t
r
e
q
u
ir
es
a
la
r
g
e
am
o
u
n
t
o
f
tim
e
to
d
etec
t
a
n
ab
n
o
r
m
al
n
o
d
e
[
2
3
]
.
T
h
e
n
etwo
r
k
s
ec
u
r
ity
in
cy
b
er
s
p
ac
e
m
ec
h
an
is
m
s
co
p
e
is
to
ex
am
in
e
ML
m
eth
o
d
s
f
o
r
cy
b
er
s
ec
u
r
ity
co
n
ce
n
tr
atin
g
o
n
r
eg
i
o
n
s
f
o
r
ex
am
p
le
in
tr
u
s
io
n
d
etec
tio
n
s
,
s
p
am
d
etec
tio
n
s
,
an
d
m
alw
ar
e
d
etec
t
io
n
s
o
n
n
etwo
r
k
[
2
4
]
,
[
2
5
]
.
T
h
e
ML
alg
o
r
ith
m
u
tili
ze
d
to
im
p
r
o
v
e
th
e
S
p
o
r
ts
an
d
f
itn
ess
[
2
6
]
.
I
t
ca
n
ex
am
i
n
e
a
h
u
g
e
v
o
lu
m
e
o
f
d
ata
,
f
in
d
p
atter
n
s
,
an
d
it
im
p
r
o
v
e
th
e
p
er
f
o
r
m
an
c
e
an
d
tr
ain
in
g
[
2
7
]
.
2.
P
RO
P
O
SE
D
M
E
T
H
O
D
2
.
1
.
Net
w
o
rk
c
re
a
t
io
n
T
h
e
n
u
m
b
er
o
f
wir
eless
n
o
d
es
in
s
talled
in
th
e
r
eg
io
n
b
ein
g
m
o
n
ito
r
ed
an
d
th
ese
n
o
d
es
s
elf
-
o
r
g
a
n
ize
in
to
a
n
etwo
r
k
.
T
h
e
n
etwo
r
k
co
n
tain
s
s
ev
er
al
wir
eless
n
o
d
es,
b
ase
s
tatio
n
(
B
S)
an
d
u
s
er
.
T
h
e
wir
eless
n
etwo
r
k
is
clu
s
ter
ed
to
m
a
k
e
ad
m
in
is
tr
atio
n
p
r
o
ce
s
s
es
a
s
s
im
p
le
as
p
o
s
s
ib
le
in
o
r
d
e
r
to
g
u
a
r
an
tee
t
h
e
n
etwo
r
k
'
s
co
n
s
is
ten
t
f
u
n
ctio
n
in
g
.
T
h
e
wir
eless
n
o
d
e
e
n
er
g
y
,
d
is
tan
ce
b
etwe
en
n
o
d
e
an
d
B
S,
an
d
co
m
m
u
n
icatio
n
r
atio
p
ar
am
et
er
s
d
ec
id
e
th
e
clu
s
ter
h
ea
d
(
C
H)
.
T
h
e
C
H
n
o
d
es
b
r
o
ad
ca
s
t
th
e
d
ata
th
at
th
ey
h
av
e
g
ath
er
e
d
to
th
e
B
S
n
o
d
e
v
ia
a
m
u
lti
-
h
o
p
r
elay
,
an
d
th
is
d
ata
ev
en
tu
ally
m
ak
es
its
wa
y
to
th
e
u
s
er
v
ia
th
e
I
n
ter
n
et.
T
h
r
o
u
g
h
th
e
u
s
er
h
a
s
th
e
ab
ilit
y
to
r
em
o
tely
s
et
u
p
o
r
ad
m
in
is
ter
th
e
n
etwo
r
k
,
as
well
a
s
p
er
f
o
r
m
m
o
n
ito
r
in
g
task
s
.
Fig
u
r
e
1
ex
p
lain
s
th
e
ar
ch
itect
u
r
e
o
f
th
e
E
I
DC
m
ec
h
an
is
m
.
Fro
m
Fig
u
r
e
1
,
th
r
ee
co
m
p
o
n
en
ts
m
ak
e
u
p
th
e
n
etwo
r
k
:
a
n
u
m
b
er
o
f
s
en
s
o
r
n
o
d
es
th
at
a
r
e
d
is
p
er
s
ed
o
v
er
th
e
o
b
s
er
v
i
n
g
r
eg
io
n
,
B
S
th
at
is
s
p
r
ea
d
,
an
d
a
u
s
er
.
T
h
e
f
o
llo
win
g
ar
e
th
e
r
o
les
th
at
ea
ch
co
m
p
o
n
en
t
p
lay
s
:
i
)
s
en
s
o
r
:
t
h
is
elem
en
t
o
f
th
e
W
SN
s
er
v
es
as
th
e
n
etwo
r
k
'
s
f
o
u
n
d
atio
n
an
d
its
p
r
i
m
ar
y
r
esp
o
n
s
ib
ilit
y
is
to
g
ath
er
th
e
d
ata
o
f
e
v
er
y
r
an
g
e,
p
r
o
ce
s
s
th
e
in
f
o
r
m
atio
n
th
at
h
as
b
ee
n
g
ath
er
e
d
,
an
d
th
en
s
en
d
th
e
p
r
o
ce
s
s
ed
d
ata
to
th
e
h
ig
h
er
n
o
d
e.
T
h
is
co
m
p
o
n
en
t
co
n
tain
s
b
o
th
u
s
u
al
s
en
s
o
r
n
o
d
es
an
d
C
H
n
o
d
es
,
ii
)
B
S:
c
o
m
b
in
es
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
8
,
No
.
2
,
May
20
2
5
:
8
8
7
-
8
9
6
890
th
e
d
ata
th
at
is
s
u
p
p
lied
b
y
th
e
C
H
s
en
s
o
r
,
an
d
n
ex
t
s
en
d
s
it
to
th
e
u
s
er
v
ia
in
ter
n
et
,
an
d
ii
i
)
u
s
er
:
t
h
is
n
o
d
e
is
g
ea
r
ed
to
war
d
th
e
e
n
d
u
s
er
.
Fig
u
r
e
1
.
Ar
c
h
itectu
r
e
o
f
E
I
D
C
m
ec
h
an
is
m
Utilized
to
m
o
n
ito
r
th
e
o
p
e
r
at
io
n
al
co
n
d
itio
n
,
ca
r
r
y
o
u
t
in
tr
u
s
io
n
d
etec
tio
n
an
d
an
aly
s
is
o
n
th
e
d
ata
th
at
is
f
o
r
war
d
e
d
b
y
th
e
B
S,
a
n
d
ca
r
r
y
o
u
t
f
u
n
ctio
n
s
th
at
ar
e
ap
p
r
o
p
r
iate
to
t
h
ese
task
s
.
I
n
ad
d
itio
n
,
th
e
u
s
er
h
as
th
e
ca
p
a
b
ilit
y
o
f
ac
tiv
ely
tr
an
s
m
itti
n
g
a
q
u
er
y
r
e
q
u
est
t
o
th
e
wir
eless
n
etwo
r
k
.
I
t
h
as
b
o
th
u
s
u
al
s
en
s
o
r
n
o
d
es
a
n
d
C
H
n
o
d
es
with
in
i
ts
s
tr
u
ctu
r
e.
I
n
o
r
d
e
r
t
o
s
en
s
e
an
d
g
ath
er
d
ata
in
th
e
m
o
n
ito
r
in
g
r
eg
i
o
n
,
u
s
u
al
s
en
s
o
r
n
o
d
es
ar
e
u
s
ed
,
a
n
d
C
H
n
o
d
es
ar
e
u
tili
ze
d
to
s
u
m
m
ar
ize
th
e
d
ata
s
u
p
p
lied
b
y
cu
r
r
en
t
ty
p
ical
n
o
d
es.
I
t
is
r
esp
o
n
s
ib
le
f
o
r
t
h
e
co
llectio
n
o
f
in
f
o
r
m
atio
n
.
First,
all
o
f
th
e
d
ata
th
at
h
as
b
ee
n
tr
an
s
m
it
ted
b
y
th
e
n
etwo
r
k
an
d
C
H
n
o
d
es is
g
ath
er
e
d
.
Af
t
er
th
at,
th
e
d
ata
ar
e
co
m
b
in
ed
,
an
d
th
e
c
h
ar
ac
ter
is
tics
o
f
th
e
I
DS is d
er
iv
ed
.
2
.
2
.
I
ntr
us
io
n
det
ec
t
io
n sy
s
t
em
T
h
e
in
tr
u
s
io
n
d
etec
tio
n
m
o
d
u
l
e
is
in
ch
ar
g
e
o
f
r
ec
eiv
in
g
d
ata
in
f
o
r
m
atio
n
f
r
o
m
th
e
B
S
an
d
ass
es
s
in
g
p
o
s
s
ib
le
in
tr
u
s
io
n
s
.
B
ec
au
s
e
i
t
is
th
e
m
o
s
t
im
p
o
r
tan
t
co
m
p
o
n
en
t
o
f
an
I
DS,
th
is
m
o
d
u
le'
s
s
u
cc
e
s
s
is
d
ir
ec
tly
tied
to
th
e
p
r
ec
is
io
n
an
d
ti
m
elin
ess
o
f
th
e
d
ata
an
d
in
f
o
r
m
atio
n
a
n
aly
s
is
it
d
o
es.
Fo
r
p
r
ed
ictio
n
a
n
d
class
if
icatio
n
o
f
th
e
test
in
g
d
a
taset,
th
is
m
o
d
u
le
u
s
es
th
e
E
L
M
d
etec
tio
n
m
eth
o
d
as
a
class
if
ier
.
T
h
e
o
u
tp
u
t
o
f
th
e
E
L
M
is
h
an
d
lin
g
a
n
o
m
al
y
th
at
is
r
esp
o
n
s
ib
le
f
o
r
an
al
y
zin
g
t
h
e
f
i
n
al
r
esu
lt
a
n
d
tak
in
g
th
e
ap
p
r
o
p
r
iate
ac
tio
n
s
in
r
esp
o
n
s
e
.
2
.
2
.
1
.
E
L
M
wit
h D
NN
-
ba
s
ed
I
DS
T
h
is
m
ec
h
an
is
m
u
tili
ze
s
an
E
L
M
m
ec
h
an
is
m
,
a
n
d
it
is
a
co
m
b
in
atio
n
o
f
DNN
with
a
h
id
d
en
lay
e
r
.
I
t
is
a
p
o
s
s
ib
ilit
y
b
ased
o
n
s
ev
e
r
al
wir
eless
n
o
d
e
attac
k
d
etec
tio
n
to
f
o
llo
w
in
cid
e
n
ts
in
a
wir
eless
n
etwo
r
k
.
I
t
h
as
b
ee
n
s
h
o
wn
th
at
E
L
M,
a
n
ex
am
p
le
o
f
a
s
in
g
le
-
h
id
d
e
n
-
la
y
er
f
ee
d
-
f
o
r
war
d
n
e
u
r
al
n
etwo
r
k
,
is
b
en
ef
icial
f
o
r
th
e
I
DS
.
T
h
e
E
L
M
is
a
b
asic
an
d
ef
f
ici
en
t
ap
p
r
o
ac
h
th
at
d
o
es
n
o
t
n
ee
d
an
y
tr
ain
in
g
d
ata
to
p
e
r
f
o
r
m
to
its
f
u
l
l
p
o
ten
tial.
I
n
s
tead
,
a
least
-
s
q
u
ar
es
s
o
lu
tio
n
is
u
s
ed
to
g
en
er
ate
th
e
o
u
tp
u
t
weig
h
ts
,
an
d
th
e
weig
h
ts
o
f
th
e
h
id
d
en
lay
er
ar
e
in
itialized
with
an
ar
b
itra
r
y
b
eg
i
n
n
in
g
p
o
in
t.
W
h
ile
th
e
weig
h
ts
o
f
th
e
h
id
d
en
lay
e
r
ar
e
in
itialized
,
th
ey
ar
e
also
g
iv
en
an
ar
b
itra
r
y
b
eg
i
n
n
in
g
p
o
in
t.
E
L
M
m
ay
b
e
tau
g
h
t
in
a
v
er
y
s
h
o
r
t
am
o
u
n
t
o
f
tim
e.
T
h
is
is
b
ec
au
s
e
th
e
we
ig
h
ts
o
f
th
e
h
id
d
e
n
lay
er
ar
e
lau
n
ch
ed
b
ased
o
n
an
ar
b
itr
ar
y
v
alu
e,
b
u
t
th
e
weig
h
ts
o
f
th
e
o
u
tp
u
t
lay
er
is
g
en
er
ate
d
with
a
s
o
lu
tio
n
t
h
at
is
estab
li
s
h
ed
o
n
th
e
least
s
q
u
ar
es.
T
h
is
lead
s
to
th
e
o
b
s
er
v
e
d
r
esu
lt.
E
L
M
is
q
u
alif
ied
b
y
a
g
r
ea
t
d
eg
r
ee
o
f
ac
cu
r
ac
y
.
T
h
is
is
s
in
ce
th
e
s
o
lu
tio
n
th
at
em
p
lo
y
s
least
s
q
u
ar
es
g
u
ar
an
tees
th
at
t
h
e
o
u
t
p
u
t
weig
h
ts
ar
e
o
p
tim
iz
ed
f
o
r
th
e
d
a
ta
th
at
was
tr
ain
e
d
o
n
.
T
h
e
lev
el
o
f
b
ac
k
g
r
o
u
n
d
n
o
is
e
th
at
E
L
M
c
an
to
ler
ate
is
r
ath
er
h
ig
h
.
T
h
is
is
b
ec
au
s
e
th
e
in
itializatio
n
o
f
th
e
h
id
d
en
lay
e
r
is
estab
lis
h
ed
o
n
ar
b
itra
r
y
in
teg
e
r
s
th
at
s
er
v
e
to
p
r
ev
e
n
t
th
e
wir
eless
n
etwo
r
k
f
r
o
m
o
v
er
f
itti
n
g
th
e
tr
ain
in
g
d
ata.
T
h
e
r
ea
s
o
n
f
o
r
th
is
ca
n
b
e
s
ee
n
in
th
e
p
r
ev
io
u
s
s
en
ten
ce
.
T
h
e
E
L
M
is
ef
f
ec
tiv
e
in
d
et
ec
tin
g
a
v
ar
iety
o
f
in
tr
u
s
io
n
s
an
d
it h
as a
g
r
ea
ter
co
m
p
u
tin
g
ca
p
ab
ilit
y
,
b
etter
lear
n
in
g
ab
ilit
y
,
an
d
q
u
ick
er
tr
ai
n
in
g
s
p
ee
d
.
T
h
is
is
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:
2
5
0
2
-
4
7
52
I
n
tr
u
s
io
n
d
etec
tio
n
in
clu
s
teri
n
g
w
ir
eless
n
et
w
o
r
k
b
y
a
p
p
lyi
n
g
ex
tr
eme
… (
P
a
la
n
ir
a
j R
a
jid
u
r
a
i P
a
r
va
th
y
)
891
b
ec
au
s
e
th
er
e
is
n
o
p
r
e
-
ex
is
t
in
g
f
ee
d
b
ac
k
er
r
o
r
iter
atio
n
co
m
p
u
tatio
n
.
Fig
u
r
e
2
ex
p
lain
s
th
e
s
tr
u
ctu
r
e
o
f
E
L
M
with
th
e
DNN
alg
o
r
ith
m
.
Fig
u
r
e
2
.
Stru
ctu
r
e
o
f
E
L
M
wi
th
DNN
alg
o
r
ith
m
Fro
m
Fi
g
u
r
e
2
,
d
r
e
p
r
esen
ts
th
e
co
u
n
t
o
f
in
p
u
t
lay
er
n
o
d
es
,
k
in
d
icate
s
th
e
co
u
n
t
o
f
h
i
d
d
en
lay
er
n
o
d
es,
an
d
n
d
e
n
o
tes
th
e
co
u
n
t
o
f
o
u
tp
u
t
lay
er
n
o
d
es.
T
h
e
tr
ain
in
g
s
am
p
les
ar
e
γ
1
;
γ
2
;
.
.
.
;
γ
d
,
an
d
th
e
eq
u
iv
alen
t
lab
els
ar
e
l
1
;
l
2
;
.
.
.
;
l
k
.
ω
j
d
ep
icts
th
e
weig
h
t
v
ec
to
r
am
o
n
g
th
e
h
id
d
en
as
well
as
th
e
in
p
u
t
lay
er
j
th
n
o
d
e,
λ
in
d
icate
s
th
e
m
atr
ix
o
f
weig
h
t,
λ
j
in
d
icate
s
th
e
we
ig
h
t
v
ec
to
r
b
etwe
en
th
e
j
-
th
n
o
d
e
f
o
r
th
e
h
id
d
en
lay
er
an
d
th
e
in
p
u
t
lay
e
r
,
b
j
r
ep
r
esen
ts
th
e
b
ias
v
alu
e
o
f
th
e
j
th
n
o
d
e
i
n
th
e
h
id
d
en
lay
er
.
T
h
e
E
L
M
m
et
h
o
d
o
u
tp
u
t a
n
d
K
h
id
d
en
n
eu
r
o
n
s
is
co
n
v
ey
ed
as
(
1
)
a
n
d
th
e
o
u
tp
u
t m
atr
ix
h
id
d
en
lay
e
r
is
d
en
o
t
ed
as
(
2
)
.
=
∑
=
1
(
+
)
(
1
)
=
[
(
+
)
.
.
.
(
+
)
.
.
.
.
.
.
.
.
.
(
+
)
.
.
.
(
+
)
]
(
2
)
Her
e,
(
)
j
h
(
x
)
T
j
j
j
gb
=+
d
en
o
tes
th
e
h
id
d
e
n
lay
er
f
u
n
ctio
n
th
at
is
lin
k
ed
to
γ
j
.
Af
ter
th
at,
th
e
p
u
r
p
o
s
e
o
f
o
p
tim
izatio
n
E
L
M
is
s
p
e
cif
ied
in
(
3
)
.
Her
e
,
R
in
d
i
ca
tes
th
e
r
eg
u
lar
izatio
n
f
ac
to
r
.
Fu
r
th
er
m
o
r
e
,
th
e
ca
teg
o
r
izatio
n
o
f
th
e
E
L
M
ca
n
b
e
co
n
v
ey
ed
as
(
4
)
.
|
|
−
|
|
2
+
2
|
|
|
|
2
(
3
)
(
)
=
(
ℎ
(
)
(
(
)
+
)
−
1
)
(
4
)
E
L
M
is
ad
ap
ted
b
y
u
p
d
atin
g
th
e
in
p
u
t
weig
h
ts
v
ar
iab
le
s
an
d
th
e
h
id
d
en
b
iases
to
r
ea
ch
m
o
r
e
ac
cu
r
ac
y
.
T
h
is
m
eth
o
d
r
aises
th
e
ac
cu
r
ac
y
.
T
h
is
is
u
s
ed
to
b
u
ild
th
e
n
etwo
r
k
weig
h
ts
o
f
o
u
tp
u
t.
Owin
g
t
o
,
it
is
f
ea
s
ib
le
to
o
p
tim
ize
th
e
wei
g
h
ts
o
f
in
p
u
t
as
well
as
th
e
b
iases
o
f
h
id
d
e
n
n
o
d
e
.
I
n
th
is
m
ec
h
an
is
m
,
th
e
d
ata
is
co
llected
m
ay
co
m
p
r
is
e
th
e
ac
tiv
ity
o
f
u
s
er
,
tr
af
f
ic
o
f
th
e
n
etwo
r
k
,
an
d
l
o
g
s
s
y
s
tem
.
Gath
er
ed
d
ata
f
r
o
m
tr
af
f
ic
ca
n
b
e
ex
am
in
e
d
to
s
p
o
t
ab
n
o
r
m
al
p
atter
n
s
in
th
at
tr
av
el,
f
o
r
ex
a
m
p
le,
a
r
aise
p
ac
k
et
co
u
n
t
ar
r
iv
in
g
f
r
o
m
a
s
en
d
er
.
T
h
e
s
y
s
tem
ac
tio
n
lo
g
s
m
ay
b
e
an
aly
ze
d
to
d
eter
m
in
e
ab
n
o
r
m
al
h
ap
p
en
in
g
s
,
f
o
r
ex
am
p
le,
a
q
u
ick
r
is
e
in
th
e
c
o
u
n
t
o
f
in
e
f
f
ec
tiv
e
ef
f
o
r
ts
to
lo
g
in
.
Dat
a
o
n
u
s
er
ac
tio
n
m
ay
b
e
ex
a
m
in
ed
to
d
ete
r
m
in
e
ab
n
o
r
m
al
u
s
er
p
atter
n
s
b
e
h
a
v
io
u
r
,
th
at
is
an
u
n
ex
p
ec
ted
in
cr
ea
s
e
in
th
e
am
o
u
n
t
o
f
it
em
s
th
at
ar
e
b
ein
g
tr
an
s
f
er
r
ed
.
T
h
e
f
ea
tu
r
es
th
at
ar
e
elicited
f
r
o
m
t
h
e
d
ata
m
ay
b
e
a
p
p
lied
to
d
e
p
ict
th
e
d
ata
in
a
m
eth
o
d
th
at
th
e
I
DS
m
o
r
e
p
r
o
m
p
tly
r
ea
lizes.
T
h
e
p
o
r
ts
em
p
lo
y
ed
b
y
th
e
s
e
n
d
er
I
P
ad
d
r
ess
an
d
th
e
r
e
ce
iv
er
I
P
a
d
d
r
ess
s
o
r
t
d
ata
p
ac
k
ets,
wh
ich
ar
e
f
o
r
w
ar
d
ed
an
d
r
em
o
v
e
d
ata
f
r
o
m
tr
af
f
ic.
T
h
e
h
o
s
ts
o
f
th
e
s
en
d
er
an
d
r
ec
ei
v
er
,
th
e
o
cc
u
r
r
e
n
ce
o
f
th
e
tim
e
an
d
d
a
te,
an
d
o
th
er
ap
p
licab
le
d
ata
m
ay
b
e
r
ec
o
v
er
ed
f
r
o
m
th
e
lo
g
s
s
y
s
tem
.
T
h
e
f
ile
n
am
e,
an
d
u
s
er
'
s
n
am
e
th
at
ar
e
ad
m
ittan
ce
,
an
d
ac
ce
s
s
tim
e
an
d
d
ate
m
a
y
b
e
am
o
n
g
th
e
ex
p
r
ess
io
n
s
g
ain
e
d
f
r
o
m
t
h
e
u
s
er
'
s
ac
tiv
ity
d
ata
.
Af
ter
th
e
m
o
d
el
h
as
b
ee
n
"tr
a
in
ed
"
o
n
th
e
ex
tr
ac
ted
f
ea
tu
r
e
s
,
it
m
ay
b
e
ap
p
lied
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
8
,
No
.
2
,
May
20
2
5
:
8
8
7
-
8
9
6
892
to
th
e
d
ata
in
o
r
d
er
to
class
if
y
it
as
n
o
r
m
al
o
r
ab
n
o
r
m
al.
T
o
d
o
th
is
,
a
co
m
p
ar
is
o
n
will
b
e
m
ad
e
b
etwe
en
th
e
m
o
d
el
th
at
h
as
b
ee
n
tr
ain
e
d
a
n
d
th
e
n
ew
d
ata.
W
h
en
th
e
m
o
d
el
d
is
co
v
er
s
an
an
o
m
aly
,
it
is
p
o
s
s
ib
le
to
u
s
e
i
t
to
d
eter
m
in
e
wh
eth
er
o
r
n
o
t
an
in
tr
u
s
io
n
h
as
o
cc
u
r
r
ed
,
d
ep
en
d
in
g
o
n
wh
eth
er
o
r
n
o
t
th
e
ab
n
o
r
m
ality
is
p
r
esen
t
.
2
.
2
.
2
.
I
ntr
us
io
n
det
ec
t
io
n
pr
o
ce
du
re
T
h
is
m
ec
h
an
is
m
u
tili
ze
s
th
e
E
I
DC
m
eth
o
d
to
ca
teg
o
r
ize
t
h
e
d
ata.
I
n
itially
,
th
e
r
aw
d
at
a
is
tr
ea
ted
u
tili
zin
g
d
ata
p
r
o
c
ess
in
g
to
c
r
ea
te
it
b
etter
ap
p
r
o
ac
h
ab
le.
I
n
th
e
f
o
llo
win
g
p
r
o
ce
d
u
r
e,
"tr
ain
in
g
",
i
n
wh
ic
h
E
I
DC
is
s
u
b
jecte
d
to
n
o
r
m
al
as
wel
l
as
attac
k
d
ata.
I
n
th
e
ca
teg
o
r
izatio
n
,
th
e
f
u
n
d
am
en
tal
f
ea
tu
r
e
s
co
m
m
u
n
icate
to
t
h
e
two
ca
teg
o
r
ies
o
f
n
o
r
m
al
as
well
a
s
in
tr
u
s
io
n
,
wh
ile
in
th
e
e
v
en
t
o
f
m
u
lti
-
class
ca
teg
o
r
izatio
n
,
th
e
c
h
ar
ac
ter
i
s
tics
cla
s
s
co
m
m
u
n
icate
to
n
o
r
m
al
as
well
as
s
ev
er
al
ty
p
es
o
f
attac
k
.
T
h
is
m
ec
h
an
is
m
p
r
o
ce
d
u
r
e
is
s
p
ec
if
ied
b
elo
w
:
Ass
u
m
e
M
ar
b
itra
r
y
n
o
d
es,
K
h
id
d
en
n
o
d
es
an
d
P
d
en
o
tes
th
e
ac
tio
n
f
u
n
ctio
n
.
L
au
n
c
h
ed
e
v
er
y
n
o
d
e
in
d
iv
id
u
al
f
ac
to
r
v
ec
to
r
th
at
c
o
m
p
r
is
e
p
a
r
am
eter
s
o
f
a
n
en
ti
r
e
h
id
d
en
n
o
d
es.
I
t
co
n
tain
s
th
r
ee
f
u
n
ctio
n
s
,
s
u
c
h
as
n
o
d
e
cr
ea
tio
n
,
in
ter
s
ec
ts
,
an
d
p
ick
ed
-
o
u
t
f
o
r
war
d
er
n
o
d
e
,
th
at
ar
e
ac
co
m
p
lis
h
ed
to
g
en
er
ate
th
e
v
ec
to
r
f
o
r
th
e
n
ew
n
o
d
e
.
T
h
is
p
r
o
ce
d
u
r
e
is
r
ep
ea
ted
till
th
e
d
is
co
n
tin
u
e
s
itu
atio
n
is
f
u
l
f
illed
.
B
u
ild
a
p
er
f
ec
t
esti
m
atin
g
m
o
d
el
with
b
etter
ac
c
u
r
ac
y
o
f
test
in
g
b
y
alter
in
g
th
e
ty
p
e
o
f
P
an
d
r
aisi
n
g
th
e
K
co
u
n
t
in
c
r
ea
s
in
g
ly
f
r
o
m
o
n
e
.
Dec
id
e
th
e
weig
h
ts
o
f
o
u
tp
u
t
λ
,
Y
alt
,
an
d
T.
T
h
e
n
,
co
m
p
a
r
e
ex
is
tin
g
an
d
p
r
o
p
o
s
ed
m
ec
h
an
is
m
f
o
r
ec
asti
n
g
an
d
r
elate
th
eir
ac
cu
r
aten
ess
.
3.
E
XP
E
R
I
M
E
N
T
A
L
RE
SUL
T
S
T
h
is
s
tu
d
y
u
s
es
th
e
NSL
k
n
o
wled
g
e
d
is
co
v
er
y
an
d
d
ata
m
in
in
g
(
KDD)
d
ataset
[
2
8
]
,
wh
ich
is
an
u
p
d
ated
v
e
r
s
io
n
o
f
th
e
o
r
ig
i
n
al
KDD
d
ataset
an
d
is
ac
k
n
o
wled
g
ed
as
a
s
tan
d
ar
d
in
th
e
ass
es
s
m
en
t
o
f
alg
o
r
ith
m
s
f
o
r
in
tr
u
s
io
n
d
etec
t
io
n
.
W
e
d
ea
lt
with
th
e
ex
p
er
i
m
en
ts
u
tili
zin
g
th
e
E
L
M
alg
o
r
ith
m
an
d
th
e
E
I
DC
m
ec
h
an
is
m
to
ev
alu
ate
th
e
ef
f
ec
t
th
at
f
ea
tu
r
es
o
n
th
e
f
u
n
ctio
n
o
f
th
e
m
o
d
el
[
2
9
]
.
T
h
e
E
L
M
alg
o
r
ith
m
o
p
tim
izes
th
e
n
etwo
r
k
weig
h
ts
o
f
o
u
tp
u
t
an
d
th
e
h
id
d
en
n
o
d
e
p
ar
a
m
eter
s
.
T
h
e
E
I
L
M
m
ec
h
an
is
m
h
as
th
e
p
o
ten
tial to
r
ea
c
h
a
b
etter
ac
c
u
r
ac
y
.
Fig
u
r
e
3
ex
p
lain
s
th
e
am
o
u
n
t
o
f
tim
e
ess
en
tial to
id
en
tify
an
in
tr
u
s
io
n
an
d
th
e
ac
cu
r
ac
y
lev
el
r
ea
ch
ed
b
y
th
e
B
FS
F
an
d
E
I
DC
m
ec
h
an
is
m
s
.
Fro
m
Fig
u
r
e
3
,
th
e
p
r
o
p
o
s
ed
m
ec
h
an
is
m
h
as
t
h
e
g
r
ea
test
ac
cu
r
ac
y
p
er
ce
n
tag
e
th
a
n
th
e
ex
is
tin
g
E
I
DC
m
ec
h
an
is
m
.
T
h
e
E
I
DC
m
ec
h
an
is
m
r
ea
ch
es
9
7
%,
b
u
t
th
e
ex
is
tin
g
m
ec
h
an
is
m
r
ea
c
h
es
o
n
l
y
8
0
%.
T
h
e
E
L
M
is
e
f
f
ec
tiv
e
in
d
et
ec
tin
g
a
v
ar
iety
o
f
in
tr
u
s
io
n
s
an
d
it
h
as
a
g
r
ea
ter
co
m
p
u
tin
g
ca
p
ab
ilit
y
,
b
etter
l
ea
r
n
in
g
ab
ilit
y
,
an
d
q
u
ick
e
r
tr
ain
in
g
s
p
ee
d
.
T
h
is
is
b
ec
au
s
e
th
er
e
is
n
o
p
r
e
-
ex
is
tin
g
f
ee
d
b
ac
k
er
r
o
r
iter
ati
o
n
c
o
m
p
u
tatio
n
.
Fig
u
r
e
4
ex
p
lain
s
th
e
d
etec
tio
n
ac
c
u
r
ac
y
c
o
m
p
ar
is
o
n
am
o
n
g
B
FS
F a
n
d
E
I
DC
m
ec
h
an
is
m
s
b
ased
o
n
wir
eless
n
o
d
es
.
Fig
u
r
e
3
.
Per
ce
n
ta
g
e
o
f
d
etec
tio
n
ac
cu
r
ac
y
f
o
r
B
FS
F a
n
d
E
I
DC
m
ec
h
an
is
m
s
b
ased
on
in
tr
u
s
io
n
d
etec
tio
n
tim
e
Fig
u
r
e
4
d
is
p
lay
s
th
at
wh
en
th
e
wir
eless
n
o
d
e
co
u
n
t
is
r
aised
f
r
o
m
4
0
to
2
0
0
,
th
e
p
e
r
ce
n
tag
e
o
f
d
etec
tio
n
ac
cu
r
ac
y
is
r
ed
u
ce
d
.
Pro
p
o
s
ed
E
I
DC
m
ec
h
an
is
m
,
co
m
p
ar
ed
to
th
e
b
aselin
e
B
FS
F
m
ec
h
an
is
m
,
th
e
E
I
DC
m
ec
h
an
is
m
p
r
o
v
i
d
es
t
h
e
h
ig
h
est
in
tr
u
s
io
n
d
etec
tio
n
ac
cu
r
ac
y
s
in
ce
it
u
tili
ze
s
t
h
e
E
L
M
with
DNN
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:
2
5
0
2
-
4
7
52
I
n
tr
u
s
io
n
d
etec
tio
n
in
clu
s
teri
n
g
w
ir
eless
n
et
w
o
r
k
b
y
a
p
p
lyi
n
g
ex
tr
eme
… (
P
a
la
n
ir
a
j R
a
jid
u
r
a
i P
a
r
va
th
y
)
893
alg
o
r
ith
m
to
d
etec
t
th
e
in
tr
u
s
io
n
well.
At
p
r
esen
t,
with
2
0
0
wir
eless
n
o
d
es,
th
e
p
er
c
en
tag
e
o
f
d
etec
tio
n
ac
cu
r
ac
y
is
9
7
%.
Ho
wev
er
,
th
e
ex
is
tin
g
B
FS
F
m
ec
h
an
is
m
d
etec
tio
n
r
atio
is
o
n
ly
6
5
.
8
2
%
.
Sin
ce
th
e
E
I
DC
m
ec
h
an
is
m
im
p
r
o
v
es
th
e
s
ca
l
ab
ilit
y
p
er
f
o
r
m
a
n
ce
.
Fig
u
r
e
5
ex
p
lain
s
th
e
Fals
e
alar
m
r
ate
f
o
r
B
FS
F
an
d
E
I
DC
m
ec
h
a
n
is
m
s
b
ased
o
n
W
ir
eless
No
d
es b
etwe
en
4
0
to
2
0
0
.
Fig
u
r
e
4
.
Per
ce
n
ta
g
e
o
f
ac
cu
r
a
cy
f
o
r
B
FS
F a
n
d
E
I
DC
m
ec
h
a
n
is
m
s
b
ased
o
n
wir
eless
n
o
d
es
Fig
u
r
e
5
.
Fals
e
alar
m
r
ate
f
o
r
B
FS
F a
n
d
E
I
DC
m
ec
h
an
is
m
s
b
ased
o
n
wir
eless
n
o
d
es
T
h
e
E
I
DC
m
ec
h
an
is
m
co
m
p
a
r
es
to
th
e
B
FS
F
m
ec
h
an
is
m
;
th
e
E
I
DC
m
ec
h
a
n
is
m
'
s
f
alse
al
ar
m
r
ate
is
b
elo
w
0
.
5
%
at
2
0
0
wir
eless
n
o
d
es.
I
t
d
etec
ts
th
e
in
tr
u
s
io
n
ef
f
icien
tly
b
y
ap
p
ly
in
g
E
L
M
with
th
e
DNN
alg
o
r
ith
m
.
H
o
wev
er
,
t
h
e
ex
is
t
in
g
B
FS
F
m
ec
h
an
is
m
h
as
a
h
i
g
h
er
f
alse
alar
m
r
ate;
th
at
is
,
t
h
e
f
alse
alar
m
r
ate
p
er
ce
n
tag
e
v
alu
e
is
1
.
6
3
%
at
2
0
0
wir
eless
n
o
d
es
.
T
h
e
E
L
M
is
a
b
asic
an
d
ef
f
icien
t
ap
p
r
o
ac
h
t
h
at
d
o
es
n
o
t
n
ee
d
a
n
y
tr
ai
n
in
g
d
ata
t
o
p
e
r
f
o
r
m
to
its
f
u
ll
p
o
ten
tial.
T
h
e
E
L
M
is
ef
f
ec
tiv
e
in
d
etec
tin
g
v
ar
io
u
s
in
tr
u
s
io
n
s
an
d
m
in
im
izes t
h
e
f
alse a
lar
m
r
ate
.
4.
CO
NCLU
SI
O
N
I
n
wir
eless
n
etwo
r
k
s
,
in
tr
u
s
io
n
d
etec
tio
n
is
a
n
ec
ess
ar
y
an
d
s
ig
n
if
ican
t
p
ar
a
m
eter
.
T
h
is
ar
ticle
p
r
esen
ts
an
e
x
tr
em
e
lear
n
in
g
m
ac
h
in
e
(
E
L
M
)
with
DNN
-
b
ased
I
n
tr
u
s
io
n
d
etec
tio
n
i
n
a
clu
s
ter
in
g
wir
eless
n
etwo
r
k
.
T
h
e
i
n
tr
o
d
u
ce
d
m
eth
o
d
ca
n
r
em
o
v
e
m
o
r
e
in
ter
p
r
eter
ch
ar
ac
ter
is
tics
an
d
en
h
an
ce
in
tr
u
s
io
n
d
etec
tio
n
ac
cu
r
ac
y
.
I
n
itially
,
th
e
wir
ele
s
s
n
etwo
r
k
is
clu
s
ter
ed
to
m
a
k
e
ad
m
in
is
tr
atio
n
p
r
o
ce
s
s
es
as
s
im
p
le
as
p
o
s
s
ib
le
in
o
r
d
er
to
g
u
a
r
an
tee
th
e
n
et
wo
r
k
'
s
co
n
s
is
ten
t
f
u
n
ctio
n
in
g
an
d
s
elec
t
th
e
C
H
b
ased
o
n
n
o
d
e
ab
ilit
y
.
T
h
is
0
20
40
60
80
1
0
0
1
2
0
40
80
1
2
0
1
6
0
2
0
0
B
F
S
F
EI
D
C
W
i
r
e
l
e
ss
Nodes
A
c
c
u
r
a
c
y
(
%)
0
0
.
2
0
.
4
0
.
6
0
.
8
1
1
.
2
1
.
4
1
.
6
1
.
8
40
80
1
2
0
1
6
0
2
0
0
B
F
S
F
EI
D
C
W
i
r
e
l
e
ss
N
o
d
e
s
Fa
l
s
e
A
l
a
r
m
Rate
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
8
,
No
.
2
,
May
20
2
5
:
8
8
7
-
8
9
6
894
m
ec
h
an
is
m
u
tili
ze
s
an
E
L
M
m
ec
h
an
is
m
,
a
co
m
b
i
n
atio
n
o
f
DNN
with
a
h
id
d
en
lay
er
,
w
h
ich
is
a
p
o
s
s
ib
ilit
y
b
ased
wir
eless
n
o
d
e
attac
k
d
e
tectio
n
.
T
h
e
n
,
we,
u
s
in
g
th
e
Simu
latio
n
o
u
tc
o
m
es,
d
e
m
o
n
s
tr
ate
th
at
th
e
E
I
DC
m
ec
h
a
n
is
m
en
h
a
n
ce
s
th
e
d
ete
ctio
n
ac
cu
r
ac
y
an
d
s
h
o
r
ten
s
t
h
e
tim
e
f
o
r
in
tr
u
s
io
n
d
etec
tio
n
co
m
p
a
r
ed
to
t
h
e
b
aselin
e
m
ec
h
an
is
m
.
Fu
r
th
er
m
o
r
e,
it
m
in
im
izes
th
e
f
alse
alar
m
r
ate.
Yet,
th
e
E
I
DC
m
ec
h
an
is
m
u
s
in
g
th
e
s
tatic
n
o
d
es,
in
th
e
f
u
tu
r
e,
g
i
v
es
th
e
m
o
b
ilit
y
p
ar
am
et
er
a
n
d
s
ep
ar
ates
wh
ich
ty
p
es
o
f
attac
k
s
in
wir
eles
s
n
etwo
r
k
s
.
RE
F
E
R
E
NC
E
S
[
1
]
S
.
M
a
e
sar
o
h
,
L.
K
u
s
u
m
a
n
i
n
g
r
u
m,
N
.
S
i
n
t
a
w
a
n
a
,
D
.
P
.
La
z
i
r
k
h
a
,
a
n
d
R
.
D
.
O
.
,
“
W
i
r
e
l
e
ss
n
e
t
w
o
r
k
se
c
u
r
i
t
y
d
e
si
g
n
a
n
d
a
n
a
l
y
si
s
u
si
n
g
w
i
r
e
l
e
ss
i
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
s
y
s
t
e
m,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
C
y
b
e
r
a
n
d
I
T
S
e
rvi
c
e
Ma
n
a
g
e
m
e
n
t
,
v
o
l
.
2
,
n
o
.
1
,
p
p
.
3
0
–
3
9
,
F
e
b
.
2
0
2
2
,
d
o
i
:
1
0
.
3
4
3
0
6
/
i
j
c
i
t
s
m.
v
2
i
1
.
7
4
.
[
2
]
R
.
K
u
mar,
A
.
M
a
l
i
k
,
a
n
d
V
.
R
a
n
g
a
,
“
A
n
i
n
t
e
l
l
e
c
t
u
a
l
i
n
t
r
u
s
i
o
n
d
e
t
e
c
t
i
o
n
s
y
st
e
m
u
si
n
g
h
y
b
r
i
d
h
u
n
g
e
r
g
a
mes
s
e
a
r
c
h
a
n
d
r
e
mo
r
a
o
p
t
i
m
i
z
a
t
i
o
n
a
l
g
o
r
i
t
h
m
f
o
r
I
o
T
w
i
r
e
l
e
ss
n
e
t
w
o
r
k
s
,
”
K
n
o
w
l
e
d
g
e
-
Ba
s
e
d
S
y
st
e
m
s
,
v
o
l
.
2
5
6
,
p
.
1
0
9
7
6
2
,
N
o
v
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
k
n
o
sy
s
.
2
0
2
2
.
1
0
9
7
6
2
.
[
3
]
M
.
J.
K
u
mar
,
S
.
M
i
s
h
r
a
,
E.
G
.
R
e
d
d
y
,
M
.
R
a
j
m
o
h
a
n
,
S
.
M
u
r
u
g
a
n
,
a
n
d
N
.
A
.
V
i
g
n
e
s
h
,
“
B
a
y
e
s
i
a
n
d
e
c
i
s
i
o
n
mo
d
e
l
b
a
s
e
d
r
e
l
i
a
b
l
e
r
o
u
t
e
f
o
r
ma
t
i
o
n
i
n
i
n
t
e
r
n
e
t
o
f
t
h
i
n
g
s
,
”
I
n
d
o
n
e
si
a
n
J
o
u
r
n
a
l
o
f
E
l
e
c
t
ri
c
a
l
E
n
g
i
n
e
e
r
i
n
g
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
3
4
,
n
o
.
3
,
p
p
.
1
6
6
5
–
1
6
7
3
,
Ju
n
.
2
0
2
4
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s
.
v
3
4
.
i
3
.
p
p
1
6
6
5
-
1
6
7
3
.
[
4
]
M
.
A
mr
u
e
t
a
l
.
,
“
N
e
t
w
o
r
k
i
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
sy
st
e
m
b
y
a
p
p
l
y
i
n
g
e
n
se
m
b
l
e
mo
d
e
l
f
o
r
smar
t
h
o
me
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
t
r
i
c
a
l
a
n
d
C
o
m
p
u
t
e
r
En
g
i
n
e
e
r
i
n
g
(
I
J
EC
E)
,
v
o
l
.
1
4
,
n
o
.
3
,
p
p
.
3
4
8
5
–
3
4
9
4
,
J
u
n
.
2
0
2
4
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
c
e
.
v
1
4
i
3
.
p
p
3
4
8
5
-
3
4
9
4
.
[
5
]
A
.
H
e
i
d
a
r
i
a
n
d
M
.
A
.
Ja
b
r
a
e
i
l
J
a
m
a
l
i
,
“
I
n
t
e
r
n
e
t
o
f
Th
i
n
g
s
i
n
t
r
u
s
i
o
n
d
e
t
e
c
t
i
o
n
sy
s
t
e
ms
:
a
c
o
mp
r
e
h
e
n
s
i
v
e
r
e
v
i
e
w
a
n
d
f
u
t
u
r
e
d
i
r
e
c
t
i
o
n
s,
”
C
l
u
st
e
r
C
o
m
p
u
t
i
n
g
,
v
o
l
.
2
6
,
n
o
.
6
,
p
p
.
3
7
5
3
–
3
7
8
0
,
D
e
c
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
0
5
8
6
-
0
2
2
-
0
3
7
7
6
-
z.
[
6
]
S
.
G
h
a
y
y
a
d
,
S
.
D
u
,
a
n
d
A
.
K
u
r
i
e
n
,
“
T
h
e
f
l
a
w
s
o
f
i
n
t
e
r
n
e
t
o
f
t
h
i
n
g
s
(
I
o
T)
i
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
a
n
d
p
r
e
v
e
n
t
i
o
n
s
c
h
e
mes
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
S
e
n
so
r
N
e
t
w
o
rks
,
v
o
l
.
3
8
,
n
o
.
1
,
p
p
.
2
5
–
3
6
,
2
0
2
2
,
d
o
i
:
1
0
.
1
5
0
4
/
I
JS
N
ET.
2
0
2
2
.
1
2
0
2
7
0
.
[
7
]
M
.
P
r
a
sa
d
,
S
.
Tr
i
p
a
t
h
i
,
a
n
d
K
.
D
a
h
a
l
,
“
A
n
i
n
t
e
l
l
i
g
e
n
t
i
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
a
n
d
p
e
r
f
o
r
ma
n
c
e
r
e
l
i
a
b
i
l
i
t
y
e
v
a
l
u
a
t
i
o
n
m
e
c
h
a
n
i
sm
i
n
mo
b
i
l
e
a
d
-
h
o
c
n
e
t
w
o
r
k
s
,
”
E
n
g
i
n
e
e
ri
n
g
A
p
p
l
i
c
a
t
i
o
n
s
o
f
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
1
1
9
,
p
.
1
0
5
7
6
0
,
M
a
r
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
n
g
a
p
p
a
i
.
2
0
2
2
.
1
0
5
7
6
0
.
[
8
]
C
.
Zh
a
n
g
,
D
.
J
i
a
,
L
.
W
a
n
g
,
W
.
W
a
n
g
,
F
.
Li
u
,
a
n
d
A
.
Y
a
n
g
,
“
C
o
mp
a
r
a
t
i
v
e
r
e
sea
r
c
h
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
m
e
t
h
o
d
s
b
a
s
e
d
o
n
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
C
o
m
p
u
t
e
rs
&
S
e
c
u
ri
t
y
,
v
o
l
.
1
2
1
,
p
.
1
0
2
8
6
1
,
O
c
t
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
se.
2
0
2
2
.
1
0
2
8
6
1
.
[
9
]
I
.
A
h
mad
,
M
.
B
a
s
h
e
r
i
,
M
.
J.
I
q
b
a
l
,
a
n
d
A
.
R
a
h
i
m
,
“
P
e
r
f
o
r
ma
n
c
e
c
o
mp
a
r
i
so
n
o
f
s
u
p
p
o
r
t
v
e
c
t
o
r
ma
c
h
i
n
e
,
r
a
n
d
o
m
f
o
r
e
st
,
a
n
d
e
x
t
r
e
me
l
e
a
r
n
i
n
g
m
a
c
h
i
n
e
f
o
r
i
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
,
”
I
E
EE
A
c
c
e
ss
,
v
o
l
.
6
,
p
p
.
3
3
7
8
9
–
3
3
7
9
5
,
2
0
1
8
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
1
8
.
2
8
4
1
9
8
7
.
[
1
0
]
S
.
S
u
b
b
i
a
h
,
K
.
S
.
M
.
A
n
b
a
n
a
n
t
h
e
n
,
S
.
Th
a
n
g
a
r
a
j
,
S
.
K
a
n
n
a
n
,
a
n
d
D
.
C
h
e
l
l
i
a
h
,
“
I
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
t
e
c
h
n
i
q
u
e
i
n
w
i
r
e
l
e
ss
se
n
s
o
r
n
e
t
w
o
r
k
u
si
n
g
g
r
i
d
s
e
a
r
c
h
r
a
n
d
o
m
f
o
r
e
st
w
i
t
h
B
o
r
u
t
a
f
e
a
t
u
r
e
s
e
l
e
c
t
i
o
n
a
l
g
o
r
i
t
h
m,”
J
o
u
rn
a
l
o
f
C
o
m
m
u
n
i
c
a
t
i
o
n
s
a
n
d
N
e
t
w
o
rks
,
v
o
l
.
2
4
,
n
o
.
2
,
p
p
.
2
6
4
–
2
7
3
,
A
p
r
.
2
0
2
2
,
d
o
i
:
1
0
.
2
3
9
1
9
/
J
C
N
.
2
0
2
2
.
0
0
0
0
0
2
.
[
1
1
]
G
.
D
e
C
a
r
v
a
l
h
o
B
e
r
t
o
l
i
e
t
a
l
.
,
“
A
n
e
n
d
-
to
-
e
n
d
f
r
a
mew
o
r
k
f
o
r
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
-
b
a
s
e
d
n
e
t
w
o
r
k
i
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
s
y
st
e
m,
”
I
EEE
Ac
c
e
ss
,
v
o
l
.
9
,
p
p
.
1
0
6
7
9
0
–
1
0
6
8
0
5
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
1
.
3
1
0
1
1
8
8
.
[
1
2
]
Z.
W
a
n
g
,
Y
.
Ze
n
g
,
Y
.
L
i
u
,
a
n
d
D
.
Li
,
“
D
e
e
p
b
e
l
i
e
f
n
e
t
w
o
r
k
i
n
t
e
g
r
a
t
i
n
g
i
m
p
r
o
v
e
d
k
e
r
n
e
l
-
b
a
se
d
e
x
t
r
e
m
e
l
e
a
r
n
i
n
g
ma
c
h
i
n
e
f
o
r
n
e
t
w
o
r
k
i
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
,
”
I
EEE
A
c
c
e
ss
,
v
o
l
.
9
,
p
p
.
1
6
0
6
2
–
1
6
0
9
1
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
1
.
3
0
5
1
0
7
4
.
[
1
3
]
L.
Z
o
u
,
X
.
L
u
o
,
Y
.
Z
h
a
n
g
,
X
.
Y
a
n
g
,
a
n
d
X
.
W
a
n
g
,
“
H
C
-
D
TTSV
M
:
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
me
t
h
o
d
b
a
s
e
d
o
n
d
e
c
i
si
o
n
t
r
e
e
t
w
i
n
s
u
p
p
o
r
t
v
e
c
t
o
r
m
a
c
h
i
n
e
a
n
d
h
i
e
r
a
r
c
h
i
c
a
l
c
l
u
st
e
r
i
n
g
,
”
I
E
EE
Ac
c
e
ss
,
v
o
l
.
1
1
,
p
p
.
2
1
4
0
4
–
2
1
4
1
6
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
3
.
3
2
5
1
3
5
4
.
[
1
4
]
J.
La
n
s
k
y
e
t
a
l
.
,
“
D
e
e
p
l
e
a
r
n
i
n
g
-
b
a
s
e
d
i
n
t
r
u
s
i
o
n
d
e
t
e
c
t
i
o
n
s
y
s
t
e
ms
:
a
sy
st
e
ma
t
i
c
r
e
v
i
e
w
,
”
I
EEE
Ac
c
e
ss
,
v
o
l
.
9
,
p
p
.
1
0
1
5
7
4
–
1
0
1
5
9
9
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
1
.
3
0
9
7
2
4
7
.
[
1
5
]
J.
A
l
i
k
h
a
n
o
v
,
R
.
Ja
n
g
,
M
.
A
b
u
h
a
m
a
d
,
D
.
M
o
h
a
i
s
e
n
,
D
.
N
y
a
n
g
,
a
n
d
Y
.
N
o
h
,
“
I
n
v
e
s
t
i
g
a
t
i
n
g
t
h
e
e
f
f
e
c
t
o
f
t
r
a
f
f
i
c
sa
mp
l
i
n
g
o
n
mac
h
i
n
e
l
e
a
r
n
i
n
g
-
b
a
se
d
n
e
t
w
o
r
k
i
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
a
p
p
r
o
a
c
h
e
s
,
”
I
E
EE
Ac
c
e
ss
,
v
o
l
.
1
0
,
p
p
.
5
8
0
1
–
5
8
2
3
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
1
.
3
1
3
7
3
1
8
.
[
1
6
]
H
.
K
y
e
,
M
.
K
i
m
,
a
n
d
M
.
K
w
o
n
,
“
H
i
e
r
a
r
c
h
i
c
a
l
d
e
t
e
c
t
i
o
n
o
f
n
e
t
w
o
r
k
a
n
o
mal
i
e
s
:
a
s
e
l
f
-
su
p
e
r
v
i
s
e
d
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
,”
I
EEE
S
i
g
n
a
l
Pro
c
e
ssi
n
g
L
e
t
t
e
rs
,
v
o
l
.
2
9
,
p
p
.
1
9
0
8
–
1
9
1
2
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
LSP
.
2
0
2
2
.
3
2
0
3
2
9
6
.
[
1
7
]
G
.
P
u
,
L.
W
a
n
g
,
J.
S
h
e
n
,
a
n
d
F
.
D
o
n
g
,
“
A
h
y
b
r
i
d
u
n
su
p
e
r
v
i
s
e
d
c
l
u
st
e
r
i
n
g
-
b
a
se
d
a
n
o
mal
y
d
e
t
e
c
t
i
o
n
m
e
t
h
o
d
,
”
T
si
n
g
h
u
a
S
c
i
e
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
2
6
,
n
o
.
2
,
p
p
.
1
4
6
–
1
5
3
,
A
p
r
.
2
0
2
1
,
d
o
i
:
1
0
.
2
6
5
9
9
/
TST
.
2
0
1
9
.
9
0
1
0
0
5
1
.
[
1
8
]
G
.
A
b
d
e
l
m
o
u
m
i
n
,
D
.
B
.
R
a
w
a
t
,
a
n
d
A
.
R
a
h
m
a
n
,
“
O
n
t
h
e
p
e
r
f
o
r
ma
n
c
e
o
f
mac
h
i
n
e
l
e
a
r
n
i
n
g
m
o
d
e
l
s
f
o
r
a
n
o
m
a
l
y
-
b
a
se
d
i
n
t
e
l
l
i
g
e
n
t
i
n
t
r
u
s
i
o
n
d
e
t
e
c
t
i
o
n
sy
st
e
ms
f
o
r
t
h
e
i
n
t
e
r
n
e
t
o
f
t
h
i
n
g
s
,
”
I
EEE
I
n
t
e
r
n
e
t
o
f
T
h
i
n
g
s
J
o
u
rn
a
l
,
v
o
l
.
9
,
n
o
.
6
,
p
p
.
4
2
8
0
–
4
2
9
0
,
M
a
r
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
JI
O
T.
2
0
2
1
.
3
1
0
3
8
2
9
.
[
1
9
]
W
.
Z
h
o
n
g
,
N
.
Y
u
,
a
n
d
C
.
A
i
,
“
A
p
p
l
y
i
n
g
b
i
g
d
a
t
a
b
a
se
d
d
e
e
p
l
e
a
r
n
i
n
g
s
y
st
e
m
t
o
i
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
,
”
Bi
g
D
a
t
a
Mi
n
i
n
g
a
n
d
An
a
l
y
t
i
c
s
,
v
o
l
.
3
,
n
o
.
3
,
p
p
.
1
8
1
–
1
9
5
,
S
e
p
.
2
0
2
0
,
d
o
i
:
1
0
.
2
6
5
9
9
/
B
D
M
A
.
2
0
2
0
.
9
0
2
0
0
0
3
.
[
2
0
]
S
.
O
t
o
u
m,
B
.
K
a
n
t
a
r
c
i
,
a
n
d
H
.
T.
M
o
u
f
t
a
h
,
“
O
n
t
h
e
f
e
a
si
b
i
l
i
t
y
o
f
d
e
e
p
l
e
a
r
n
i
n
g
i
n
s
e
n
s
o
r
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
,
”
I
EEE
N
e
t
w
o
rk
i
n
g
L
e
t
t
e
rs
,
v
o
l
.
1
,
n
o
.
2
,
p
p
.
6
8
–
7
1
,
S
e
p
.
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
l
n
e
t
.
2
0
1
9
.
2
9
0
1
7
9
2
.
[
2
1
]
X
.
A
n
,
X
.
Zh
o
u
,
X
.
L
ü
,
F
.
Li
n
,
a
n
d
L.
Y
a
n
g
,
“
sam
p
l
e
se
l
e
c
t
e
d
e
x
t
r
e
m
e
l
e
a
r
n
i
n
g
m
a
c
h
i
n
e
b
a
s
e
d
i
n
t
r
u
s
i
o
n
d
e
t
e
c
t
i
o
n
i
n
f
o
g
c
o
m
p
u
t
i
n
g
a
n
d
M
E
C
,
”
Wi
r
e
l
e
ss
C
o
m
m
u
n
i
c
a
t
i
o
n
s
a
n
d
M
o
b
i
l
e
C
o
m
p
u
t
i
n
g
,
v
o
l
.
2
0
1
8
,
n
o
.
1
,
Jan
.
2
0
1
8
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
1
8
/
7
4
7
2
0
9
5
.
[
2
2
]
M
.
A
.
K
h
a
n
,
A
.
R
e
h
ma
n
,
K
.
M
.
K
h
a
n
,
M
.
A
.
A
l
G
h
a
m
d
i
,
a
n
d
S
.
H
.
A
l
m
o
t
i
r
i
,
“
En
h
a
n
c
e
i
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
i
n
c
o
mp
u
t
e
r
n
e
t
w
o
r
k
s
b
a
s
e
d
o
n
d
e
e
p
e
x
t
r
e
me
l
e
a
r
n
i
n
g
m
a
c
h
i
n
e
,
”
C
o
m
p
u
t
e
rs
,
M
a
t
e
ri
a
l
s
&
C
o
n
t
i
n
u
a
,
v
o
l
.
6
6
,
n
o
.
1
,
p
p
.
4
6
7
–
4
8
0
,
2
0
2
0
,
d
o
i
:
1
0
.
3
2
6
0
4
/
c
mc
.
2
0
2
0
.
0
1
3
1
2
1
.
[
2
3
]
B
.
Li
u
,
“
R
ET
R
A
C
T
ED
A
R
TI
C
LE:
H
y
b
r
i
d
e
x
t
r
e
me
l
e
a
r
n
i
n
g
mac
h
i
n
e
-
b
a
se
d
a
p
p
r
o
a
c
h
f
o
r
I
D
S
i
n
smar
t
A
d
H
o
c
n
e
t
w
o
r
k
s,”
EU
RAS
I
P
J
o
u
rn
a
l
o
n
Wi
r
e
l
e
s
s
C
o
m
m
u
n
i
c
a
t
i
o
n
s
a
n
d
N
e
t
w
o
rk
i
n
g
,
v
o
l
.
2
0
2
3
,
n
o
.
1
,
p
.
8
4
,
A
u
g
.
2
0
2
3
,
d
o
i
:
1
0
.
1
1
8
6
/
s
1
3
6
3
8
-
0
2
3
-
0
2
2
9
7
-
6.
[
2
4
]
R
.
R
a
m
a
n
,
V
.
S
u
j
a
t
h
a
,
C
.
B
h
u
p
e
s
h
b
h
a
i
T
h
a
c
k
e
r
,
K
.
B
i
k
r
a
m,
M
.
B
S
a
h
a
a
i
,
a
n
d
S
.
M
u
r
u
g
a
n
,
“
I
n
t
e
l
l
i
g
e
n
t
p
a
r
k
i
n
g
ma
n
a
g
e
me
n
t
sy
st
e
ms
u
si
n
g
i
o
t
a
n
d
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s
f
o
r
r
e
a
l
-
t
i
me
s
p
a
c
e
a
v
a
i
l
a
b
i
l
i
t
y
e
s
t
i
m
a
t
i
o
n
,
”
i
n
2
0
2
3
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
S
u
s
t
a
i
n
a
b
l
e
C
o
m
m
u
n
i
c
a
t
i
o
n
N
e
t
w
o
rks
a
n
d
A
p
p
l
i
c
a
t
i
o
n
(
I
C
S
C
N
A)
,
N
o
v
.
2
0
2
3
,
p
p
.
2
8
6
–
2
9
1
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
S
C
N
A
5
8
4
8
9
.
2
0
2
3
.
1
0
3
7
0
6
3
6
.
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:
2
5
0
2
-
4
7
52
I
n
tr
u
s
io
n
d
etec
tio
n
in
clu
s
teri
n
g
w
ir
eless
n
et
w
o
r
k
b
y
a
p
p
lyi
n
g
ex
tr
eme
… (
P
a
la
n
ir
a
j R
a
jid
u
r
a
i P
a
r
va
th
y
)
895
[
2
5
]
T.
M
e
e
n
a
k
s
h
i
,
R
.
R
a
m
a
n
i
,
A
.
K
a
r
t
h
i
k
e
y
a
n
,
N
.
S
.
V
a
n
i
t
h
a
,
a
n
d
S
.
M
u
r
u
g
a
n
,
“
P
o
w
e
r
q
u
a
l
i
t
y
mo
n
i
t
o
r
i
n
g
o
f
a
p
h
o
t
o
v
o
l
t
a
i
c
s
y
s
t
e
m
t
h
r
o
u
g
h
I
o
T,
”
i
n
2
0
2
3
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
S
u
st
a
i
n
a
b
l
e
C
o
m
m
u
n
i
c
a
t
i
o
n
N
e
t
w
o
rks
a
n
d
A
p
p
l
i
c
a
t
i
o
n
(
I
C
S
C
N
A)
,
N
o
v
.
2
0
2
3
,
p
p
.
4
1
3
–
418
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
S
C
N
A
5
8
4
8
9
.
2
0
2
3
.
1
0
3
7
0
4
9
4
.
[
2
6
]
C
.
S
.
R
a
n
g
a
n
a
t
h
a
n
,
R
.
R
a
ma
n
,
K
.
K
.
S
u
t
a
r
i
a
,
R
.
A
V
a
r
ma
,
a
n
d
S
.
M
u
r
u
g
a
n
,
“
N
e
t
w
o
r
k
s
e
c
u
r
i
t
y
i
n
c
y
b
e
r
sp
a
c
e
u
s
i
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s,”
i
n
2
0
2
3
7
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
E
l
e
c
t
r
o
n
i
c
s
,
C
o
m
m
u
n
i
c
a
t
i
o
n
a
n
d
A
e
r
o
sp
a
c
e
T
e
c
h
n
o
l
o
g
y
(
I
C
E
C
A)
,
N
o
v
.
2
0
2
3
,
p
p
.
1
7
5
5
–
1
7
5
9
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
EC
A
5
8
5
2
9
.
2
0
2
3
.
1
0
3
9
4
9
6
2
.
[
2
7
]
R
.
R
a
m
a
n
,
M
.
K
a
u
l
,
R
.
M
e
e
n
a
k
s
h
i
,
S
.
Ja
y
a
p
r
a
k
a
s
h
,
D
.
R
u
k
ma
n
i
D
e
v
i
,
a
n
d
S
.
M
u
r
u
g
a
n
,
“
I
o
T
a
p
p
l
i
c
a
t
i
o
n
s
i
n
sp
o
r
t
s
a
n
d
f
i
t
n
e
ss:
e
n
h
a
n
c
i
n
g
p
e
r
f
o
r
m
a
n
c
e
m
o
n
i
t
o
r
i
n
g
a
n
d
t
r
a
i
n
i
n
g
,
”
i
n
2
0
2
3
S
e
c
o
n
d
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
O
n
S
m
a
r
t
T
e
c
h
n
o
l
o
g
i
e
s
Fo
r
S
m
a
rt
N
a
t
i
o
n
(
S
m
a
rt
T
e
c
h
C
o
n
)
,
A
u
g
.
2
0
2
3
,
p
p
.
1
3
7
–
141
,
d
o
i
:
1
0
.
1
1
0
9
/
S
mart
Te
c
h
C
o
n
5
7
5
2
6
.
2
0
2
3
.
1
0
3
9
1
3
0
1
.
[
2
8
]
M
.
R
S
u
d
h
a
,
G
.
B
.
H
.
M
a
l
i
n
i
,
R
.
S
a
n
k
a
r
,
M
.
M
y
t
h
i
l
y
,
P
.
S
.
K
u
mares
h
,
M
.
N
.
V
a
r
a
d
a
r
a
j
a
n
,
a
n
d
S
.
S
u
j
a
t
h
a
,
“
P
r
e
d
i
c
t
i
v
e
m
o
d
e
l
i
n
g
f
o
r
h
e
a
l
t
h
c
a
r
e
w
o
r
k
e
r
w
e
l
l
-
b
e
i
n
g
w
i
t
h
c
l
o
u
d
c
o
m
p
u
t
i
n
g
a
n
d
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
f
o
r
s
t
r
e
ss
m
a
n
a
g
e
me
n
t
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
El
e
c
t
r
i
c
a
l
a
n
d
C
o
m
p
u
t
e
r
En
g
i
n
e
e
r
i
n
g
(
I
J
EC
E)
,
v
o
l
.
1
5
,
n
o
.
1
,
2
0
2
5
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
c
e
.
v
1
5
i
1
.
p
p
1
2
1
8
-
1
2
2
8
.
[
2
9
]
D
.
Ja
v
a
h
e
r
i
,
S
.
G
o
r
g
i
n
,
J.
-
A
.
Le
e
,
a
n
d
M
.
M
a
s
d
a
r
i
,
“
F
u
z
z
y
l
o
g
i
c
-
b
a
se
d
D
D
o
S
a
t
t
a
c
k
s
a
n
d
n
e
t
w
o
r
k
t
r
a
f
f
i
c
a
n
o
m
a
l
y
d
e
t
e
c
t
i
o
n
met
h
o
d
s
:
C
l
a
ssi
f
i
c
a
t
i
o
n
,
o
v
e
r
v
i
e
w
,
a
n
d
f
u
t
u
r
e
p
e
r
s
p
e
c
t
i
v
e
s,”
I
n
f
o
rm
a
t
i
o
n
S
c
i
e
n
c
e
s
,
v
o
l
.
6
2
6
,
p
p
.
3
1
5
–
3
3
8
,
M
a
y
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
n
s.
2
0
2
3
.
0
1
.
0
6
7
.
BIO
G
RA
PH
IES
O
F
AU
TH
O
R
S
Pa
la
n
ira
j
Ra
jid
u
r
a
i
Pa
r
v
a
th
y
i
s
a
P
ro
jec
t
M
a
n
a
g
e
r
a
t
M
p
h
a
s
is
Co
rp
o
ra
ti
o
n
in
Ch
a
n
d
ler,
Ariz
o
n
a
,
USA
.
He
h
a
s
1
6
+
y
e
a
rs o
f
I
T
e
x
p
e
rien
c
e
in
t
h
e
BI
&
a
n
d
An
a
l
y
ti
c
s d
o
m
a
in
with
a
fo
c
u
s
o
n
d
a
ta
m
o
d
e
li
n
g
,
i
n
teg
ra
ti
o
n
a
n
d
v
isu
a
li
z
a
ti
o
n
(S
n
o
wfla
k
e
,
Az
u
re
,
AWS
,
G
CP
,
a
z
u
re
d
a
ta
fa
c
to
ry
,
d
a
ta
b
rick
s
,
tab
lea
u
,
p
o
we
r
BI,
py
t
h
o
n
,
R,
S
AP
BO,
al
trey
x
,
xc
e
p
to
r
(RP
A)).
Re
wa
rd
e
d
fr
o
m
c
u
st
o
m
e
r
f
o
r
p
ro
v
i
d
in
g
“
Cu
st
o
m
e
r
Va
lu
e
Ad
d
i
ti
o
n
”
fo
r
p
e
rf
o
rm
a
n
c
e
tu
n
i
n
g
o
n
sc
h
e
d
u
le
.
He
h
a
s
b
e
e
n
re
wa
rd
e
d
th
e
“
S
tar
P
e
rfo
rm
e
r”
a
wa
rd
o
f
t
h
e
q
u
a
rter
fo
r
a
su
p
p
o
rt
p
r
o
jec
t
b
y
h
e
x
a
wa
re
lea
d
e
rsh
i
p
.
Also
,
h
e
re
c
e
iv
e
d
th
e
“
S
t
a
t
P
e
rfo
rm
e
r”
a
wa
rd
o
f
th
e
q
u
a
rter
fo
r
m
ig
ra
ti
o
n
p
ro
jec
t
fr
o
m
h
e
x
a
wa
re
lea
d
e
r
sh
ip
.
M
o
re
o
v
e
r,
r
e
wa
rd
e
d
“
M
o
st
Va
l
u
a
b
le
P
lay
e
r”
su
p
p
o
rt
p
r
o
jec
t
fr
o
m
wi
p
ro
-
b
e
st
b
u
y
a
c
c
o
u
n
t
lea
d
e
rsh
ip
.
F
u
rt
h
e
rm
o
re
,
r
e
wa
rd
e
d
a
“
F
e
a
th
e
r
in
m
y
c
a
p
”
fo
r
o
u
tsta
n
d
i
n
g
c
o
n
tri
b
u
ti
o
n
to
t
h
e
p
r
o
jec
t
b
u
sin
e
ss
g
ro
u
p
h
iera
rc
h
y
it
e
ra
t
io
n
.
He
wa
s
re
wa
rd
e
d
with
a
“
F
e
a
th
e
r
in
m
y
c
a
p
”
a
wa
rd
fo
r
h
is
o
u
tstan
d
in
g
c
o
n
tri
b
u
ti
o
n
to
p
ro
jec
t
b
u
sin
e
ss
g
r
o
u
p
h
i
e
ra
rc
h
y
it
e
ra
ti
o
n
1
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
p
a
lan
irajrp
s@
g
m
a
il
.
c
o
m
.
S
a
th
e
e
shk
u
m
a
r
S
e
k
a
r
w
it
h
o
v
e
r
1
5
y
e
a
rs
o
f
se
a
so
n
e
d
e
x
p
e
rt
ise
in
In
f
o
rm
a
ti
o
n
Tec
h
n
o
l
o
g
y
,
he
b
rin
g
s
a
we
a
lt
h
o
f
e
x
p
e
rien
c
e
sp
a
n
n
in
g
P
ro
jec
t
a
n
d
P
o
rtf
o
li
o
M
a
n
a
g
e
m
e
n
t,
Tec
h
n
ica
l
De
li
v
e
ry
,
a
n
d
M
a
n
a
g
e
d
S
e
rv
ice
s.
M
y
e
x
ten
si
v
e
b
a
c
k
g
r
o
u
n
d
in
c
lu
d
e
s
a
stro
n
g
fo
c
u
s
on
d
a
ta
a
n
d
c
l
o
u
d
p
r
o
jec
t
s
,
wh
e
r
e
he
ha
s
e
x
c
e
ll
e
d
in
s
y
ste
m
a
n
a
ly
sis,
re
q
u
irem
e
n
t
g
a
th
e
ri
n
g
,
d
e
sig
n
,
d
e
v
e
lo
p
m
e
n
t
,
tes
ti
n
g
,
q
u
a
li
ty
a
ss
u
ra
n
c
e
,
imp
lem
e
n
tatio
n
,
a
n
d
s
u
p
p
o
rt
a
c
ro
ss
b
a
n
k
i
n
g
,
in
su
ra
n
c
e
,
h
e
a
lt
h
c
a
re
,
a
n
d
m
a
n
u
fa
c
tu
rin
g
d
o
m
a
in
s.
No
tab
le
sk
i
ll
s
in
c
lu
d
e
p
ro
ficie
n
c
y
i
n
S
n
o
wfla
k
e
,
a
z
u
re
d
a
ta
b
rick
s
,
a
n
d
Az
u
re
se
rv
ice
s,
with
a
sp
e
c
ial
e
m
p
h
a
sis
o
n
HV
R
Re
a
l
-
Ti
m
e
re
p
li
c
a
ti
o
n
.
He
h
a
s
su
c
c
e
ss
fu
ll
y
m
a
n
a
g
e
d
e
n
d
-
to
-
e
n
d
P
r
o
jec
t
P
lan
n
i
n
g
,
Ex
e
c
u
t
io
n
,
a
n
d
M
a
n
a
g
e
m
e
n
t,
a
li
g
n
in
g
a
c
ti
v
it
ies
with
c
o
re
b
u
si
n
e
ss
o
b
jec
ti
v
e
s.
M
y
c
o
m
p
e
ten
c
ies
e
x
ten
d
t
o
d
a
ta
a
n
a
ly
sis,
g
o
v
e
rn
a
n
c
e
,
i
n
te
g
ra
ti
o
n
,
q
u
a
li
ty
,
a
p
p
li
c
a
ti
o
n
tu
n
in
g
,
a
n
d
se
c
u
ri
ty
.
He
h
a
s
d
e
m
o
n
stra
ted
m
a
ste
ry
i
n
d
e
v
e
lo
p
in
g
c
u
sto
m
P
y
th
o
n
u
t
il
it
ies
fo
r
s
e
a
m
les
s
d
a
ta
m
ig
ra
ti
o
n
a
n
d
e
x
h
ib
it
h
a
n
d
s
-
o
n
e
x
p
e
rien
c
e
in
S
p
a
rk
,
S
c
a
la,
P
y
th
o
n
,
a
n
d
UN
IX
S
h
e
ll
sc
rip
ti
n
g
.
A
sta
n
d
o
u
t
a
c
h
iev
e
m
e
n
t
in
c
lu
d
e
s
d
e
sig
n
in
g
a
n
d
b
u
il
d
in
g
HV
R
EL
T
p
ip
e
li
n
e
s
fo
r
v
a
ri
o
u
s
p
latfo
rm
s,
h
ig
h
li
g
h
ti
n
g
m
y
e
x
p
e
rti
se
i
n
d
a
ta
m
o
v
e
m
e
n
t.
F
u
rth
e
rm
o
re
,
m
y
b
a
c
k
g
ro
u
n
d
e
n
c
o
m
p
a
ss
e
s
re
e
n
g
in
e
e
rin
g
leg
a
c
y
a
p
p
li
c
a
ti
o
n
s
in
t
o
m
icro
se
rv
ice
s
o
n
th
e
d
a
ta
b
r
ick
s
p
latf
o
rm
a
n
d
e
x
e
c
u
ti
n
g
su
c
c
e
ss
fu
l
Tera
d
a
ta
to
S
n
o
wfla
k
e
m
ig
ra
ti
o
n
s
a
n
d
Tera
d
a
ta
to
G
CP
Big
Qu
e
ry
.
Wel
l
-
ve
rse
d
in
Az
u
re
De
v
Op
s
a
n
d
d
a
ta
b
rick
s
M
LOp
s,
He
b
rin
g
a
c
o
m
p
re
h
e
n
siv
e
u
n
d
e
rsta
n
d
in
g
o
f
t
o
o
ls
a
n
d
tec
h
n
o
l
o
g
ies
in
IBM
M
a
i
n
fra
m
e
,
v
isi
o
n
p
lu
s,
a
n
d
IDM
S
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
sa
th
e
e
sh
k
u
m
a
r.
se
k
a
r2
4
@
g
m
a
il
.
c
o
m
.
Bh
a
r
a
t
Tid
k
e
o
b
tain
e
d
h
is
M
Tec
h
a
n
d
P
h
.
D
.
d
e
g
re
e
i
n
C
o
m
p
u
ter
E
n
g
in
e
e
rin
g
fro
m
S
a
rd
a
r
Va
ll
a
b
h
b
h
a
i
Na
ti
o
n
a
l
In
stit
u
te
o
f
Tec
h
n
o
l
o
g
y
,
S
u
ra
t,
In
d
ia.
He
is
c
u
rre
n
tl
y
wo
rk
i
n
g
wit
h
S
IT
Na
g
p
u
r.
He
p
u
b
li
s
h
e
d
m
a
n
y
p
a
p
e
rs
in
re
p
u
te
d
in
tern
a
ti
o
n
a
l
jo
u
rn
a
ls
a
n
d
c
o
n
fe
re
n
c
e
s
His
in
tere
sts
in
c
lu
d
e
so
ft
c
o
m
p
u
ti
n
g
,
b
ig
d
a
ta,
m
a
c
h
in
e
lea
rn
in
g
a
n
d
so
c
ial
n
e
two
rk
d
a
ta an
a
ly
ti
c
s.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
b
a
ti
d
k
e
@g
m
a
il
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
8
,
No
.
2
,
May
20
2
5
:
8
8
7
-
8
9
6
896
Rud
r
a
r
a
ju
Le
e
la
J
y
o
t
h
i
c
u
rre
n
tl
y
se
rv
e
a
s
a
n
As
sista
n
t
P
ro
fe
ss
o
r
i
n
t
h
e
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
i
n
e
e
rin
g
a
t
S
a
g
i
Ra
m
a
Krish
n
a
m
Ra
ju
En
g
in
e
e
rin
g
Co
ll
e
g
e
(A),
B
h
ima
v
a
ra
m
,
An
d
h
ra
P
ra
d
e
sh
,
In
d
ia.
S
h
e
h
a
s
8
Ye
a
rs
o
f
Tea
c
h
in
g
Ex
p
e
rien
c
e
.
Co
m
in
g
to
m
y
a
re
a
s
o
f
i
n
tere
sts
i
n
c
l
u
d
e
s
I
o
T,
a
n
d
r
o
id
d
e
v
e
lo
p
m
e
n
t
a
n
d
we
b
d
e
v
e
l
o
p
m
e
n
t.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
r
u
d
ra
ra
ju
.
lee
la9
2
@
g
m
a
il
.
c
o
m
.
Ve
n
u
g
o
p
a
l
S
u
j
a
th
a
re
c
e
iv
e
d
h
e
r
Ba
c
h
e
lo
r
o
f
S
c
ien
c
e
in
M
a
th
e
m
a
ti
c
s
fro
m
M
a
d
ra
s
Un
iv
e
rsit
y
i
n
1
9
9
4
,
M
.
C.
A
fro
m
M
a
d
ra
s
U
n
iv
e
rsit
y
.
S
h
e
c
o
m
p
lete
d
P
h
.
D
.
d
e
g
re
e
fro
m
AME
T
Un
iv
e
rsity
.
At
p
re
se
n
t;
sh
e
is
w
o
rk
i
n
g
a
s
a
n
As
so
c
iat
e
p
ro
fe
ss
o
r
&
HO
D
in
S
.
A.
En
g
i
n
e
e
rin
g
C
o
ll
e
g
e
Ch
e
n
n
a
i.
T
h
e
a
u
th
o
r
is
h
a
v
i
n
g
m
o
re
th
a
n
2
3
y
e
a
rs
o
f
e
x
p
e
rien
c
e
in
tea
c
h
in
g
field
.
He
r
fiel
d
s
o
f
re
se
a
rc
h
in
c
l
u
d
e
wire
les
s
se
n
so
r
n
e
tw
o
rk
s,
a
n
d
m
a
c
h
in
e
lea
rn
in
g
.
S
h
e
h
a
s
1
0
p
a
p
e
rs
in
Na
ti
o
n
a
l/
In
t
e
rn
a
ti
o
n
a
l
c
o
n
fe
re
n
c
e
a
n
d
1
1
P
a
p
e
rs
in
In
ter
n
a
ti
o
n
a
l
j
o
u
r
n
a
ls.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
su
j
a
th
a
@s
a
e
c
.
a
c
.
in
.
Ma
d
a
p
p
a
S
h
a
n
m
u
g
a
t
h
a
i
wo
rk
in
g
a
s
a
P
r
o
fe
ss
o
r
i
n
th
e
De
p
a
rtme
n
t
o
f
En
g
li
s
h
a
t
S
ri
S
a
iram
En
g
in
e
e
ri
n
g
C
o
ll
e
g
e
,
C
h
e
n
n
a
i
,
Tam
il
n
a
d
u
,
In
d
ia.
S
h
e
is
re
c
e
iv
e
d
h
is
M
a
ste
r’s
in
En
g
l
ish
with
M
.
P
h
il
a
n
d
Do
c
to
ra
l
De
g
re
e
h
a
v
i
n
g
d
o
n
e
re
se
a
rc
h
in
th
e
a
re
a
o
f
En
g
li
s
h
f
o
r
S
p
e
c
ifi
c
P
u
rp
o
se
s
(ES
P
)
i
.
S
h
e
is
c
o
m
p
letin
g
2
8
y
e
a
rs
o
f
Tea
c
h
in
g
f
o
r
UG
(En
g
i
n
e
e
rin
g
)
a
n
d
P
G
(Bu
si
n
e
ss
S
tu
d
ies
)
a
n
d
in
p
r
o
g
re
ss
.
S
h
e
h
a
s
a
He
a
d
in
g
t
h
e
De
p
a
rtme
n
t
o
f
En
g
li
s
h
,
S
r
i
S
a
iram
En
g
i
n
e
e
rin
g
C
o
ll
e
g
e
.
S
h
e
is
a
Lea
d
e
rsh
i
p
in
M
e
n
t
o
r
f
o
r
S
e
lf
He
l
p
G
ro
u
p
-
Wo
m
e
n
.
S
h
e
is
a
Co
o
rd
i
n
a
to
r
in
-
f
in
e
a
rts
a
n
d
p
re
v
e
n
t
io
n
o
f
se
x
u
a
l
h
a
ra
ss
m
e
n
t
(P
OSH)
a
t
th
e
in
sti
tu
ti
o
n
lev
e
l.
Als
o
,
s
h
e
is
a
TE
D
o
r
g
a
n
ize
r.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
S
h
a
n
m
u
g
a
th
a
i.
e
n
g
@s
a
iram
.
e
d
u
.
i
n
.
S
u
b
b
i
a
h
Mu
r
u
g
a
n
is
a
n
Ad
ju
n
c
t
P
ro
fe
ss
o
r,
S
a
v
e
e
th
a
S
c
h
o
o
l
o
f
E
n
g
in
e
e
rin
g
,
S
a
v
e
e
th
a
In
stit
u
te
o
f
M
e
d
ica
l
a
n
d
Tec
h
n
ica
l
S
c
ien
c
e
s,
Ch
e
n
n
a
i,
Tam
il
Na
d
u
,
In
d
ia.
He
p
u
b
li
sh
e
d
h
is
re
se
a
rc
h
a
rti
c
les
i
n
m
a
n
y
in
ter
n
a
ti
o
n
a
l
a
n
d
n
a
ti
o
n
a
l
c
o
n
fe
re
n
c
e
s
a
n
d
jo
u
rn
a
ls.
His
re
se
a
rc
h
a
re
a
s
in
c
lu
d
e
n
e
two
rk
se
c
u
rit
y
a
n
d
m
a
c
h
i
n
e
lea
rn
i
n
g
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
sm
u
re
sju
r@g
m
a
il
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.