I
nte
rna
t
io
na
l J
o
urna
l o
f
I
nfo
r
m
a
t
ics a
nd
Co
mm
u
n
ica
t
io
n T
ec
hn
o
lo
g
y
(
I
J
-
I
CT
)
Vo
l.
5
,
No
.
1
,
A
p
r
il 2
0
1
6
,
p
p
.
1
1
~
2
0
I
SS
N:
2252
-
8776
11
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
jo
u
r
n
a
l.c
o
m/o
n
lin
e/in
d
ex
.
p
h
p
/I
J
I
C
T
Att
a
c
k
De
t
ection
in a Rule
-
Ba
sed S
y
ste
m
u
sing
F
u
zz
y
Spi
k
ing
Neura
l P
Sys
te
m
F
Ruf
a
i K
a
ze
e
m
I
do
w
u*
,
Ra
v
ie
Cha
nd
re
n M
un
iy
a
nd
i*
,
Z
u
la
iha
Ali O
t
h
m
a
n*
*
*
S
OF
TA
M
Re
se
a
r
c
h
Ce
n
tret,
F
a
c
u
lt
y
o
f
In
f
o
r
m
a
ti
o
n
S
c
ien
c
e
&
T
e
c
h
n
o
l
o
g
y
,
Un
iv
e
rsiti
Ke
b
a
n
g
sa
a
n
M
a
lay
sia
*
*
C
A
I
T
Re
se
a
rc
h
Ce
n
tre,
F
a
c
u
lt
y
o
f
In
f
o
r
m
a
ti
o
n
S
c
ien
c
e
&
T
e
c
h
n
o
l
o
g
y
,
Un
iv
e
rsiti
Ke
b
a
n
g
sa
a
n
M
a
la
y
sia
.
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Dec
1
5
,
2
0
1
5
R
ev
i
s
ed
Mar
2
4
,
2
0
1
6
A
cc
ep
ted
Mar
26
,
2
0
1
6
T
h
e
v
irt
u
a
l
a
re
a
o
f
c
o
m
m
u
n
ica
ti
o
n
k
n
o
w
n
a
s
c
y
b
e
r
sp
a
c
e
b
ro
u
g
h
t
a
b
o
u
t
b
y
th
e
d
e
b
u
t
o
f
th
e
in
tern
e
t
h
a
s
e
n
a
b
led
so
m
e
c
y
b
e
r
c
ri
m
e
s
–
‗In
tru
si
o
n
‘
in
c
lu
siv
e
.
S
o
,
e
ff
o
rts
a
re
b
e
in
g
g
e
a
re
d
to
wa
rd
s
e
n
su
rin
g
th
a
t
re
li
a
b
le
a
n
d
e
ff
ici
e
n
t
In
tr
u
sio
n
De
tec
ti
o
n
S
y
ste
m
s
(IDSs)
a
re
d
e
v
e
lo
p
e
d
t
o
c
u
rtail
th
is
m
e
n
a
c
e
.
Ho
we
v
e
r,
S
p
ik
in
g
Ne
u
ra
l
P
(S
N
P
)
sy
ste
m
s h
a
v
e
b
e
e
n
e
sta
b
li
sh
e
d
a
s
a
c
las
s
o
f
d
istri
b
u
ted
p
a
ra
ll
e
l
c
o
m
p
u
ti
n
g
m
o
d
e
ls.
S
o
,
i
n
th
is
p
a
p
e
r,
a
n
o
v
e
l
n
e
tw
o
rk
in
tru
sio
n
p
re
d
icti
o
n
m
o
d
e
l
b
a
se
d
o
n
tra
p
e
z
o
id
a
l
F
u
z
z
y
Re
a
so
n
in
g
S
p
ik
in
g
Ne
u
ra
l
P
(tF
RS
N
P
)
sy
s
tem
,
is
i
m
p
le
m
e
n
ted
f
o
r
th
e
v
e
r
y
f
irst
ti
m
e
f
o
r
th
e
d
e
tec
ti
o
n
o
f
in
tru
si
o
n
.
t
F
RS
N
P
sy
ste
m
is
a
n
e
x
ten
sio
n
o
f
S
N
P
s
y
ste
m
.
It
h
a
s
a
g
ra
p
h
ica
l
m
o
d
e
li
n
g
a
d
v
a
n
tag
e
w
h
ich
m
a
k
e
s
it
w
e
l
l
su
it
e
d
f
o
r
f
u
z
z
y
re
a
so
n
in
g
a
s
we
ll
a
s
f
u
z
z
y
k
n
o
w
led
g
e
re
p
re
se
n
tatio
n
u
sin
g
I
f
-
T
h
e
n
ru
les
.
T
h
e
d
y
n
a
m
ic
f
iri
n
g
p
o
we
r
o
f
n
e
u
ro
n
s
is
h
a
r
n
e
ss
e
d
in
a
sim
p
le
p
a
ra
ll
e
l
m
a
tri
x
-
b
a
se
d
f
u
z
z
y
re
a
so
n
in
g
f
o
rm
a
t
to
g
e
n
e
ra
te
in
f
e
re
n
c
e
s.
T
o
e
s
tab
li
sh
t
h
e
e
ffe
c
ti
v
e
n
e
ss
o
f
th
is
a
p
p
ro
a
c
h
e
sp
e
c
iall
y
in
th
e
a
re
a
o
f
sp
e
e
d
o
f
p
a
ra
ll
e
l
re
a
so
n
in
g
a
n
d
th
e
h
a
n
d
li
n
g
o
f
u
n
c
e
rtain
ti
e
s,
d
e
tec
ti
o
n
o
f
Bru
te
F
o
rc
e
A
tt
a
c
k
(BF
A
)
is
u
se
d
f
o
r
d
e
m
o
n
stra
ti
o
n
.
F
ro
m
th
e
c
risp
re
su
lt
s
(
0
.
0
4
3
1
,
0
.
0
4
1
4
,
0
.
4
4
5
3
,
0
.
1
7
0
3
an
d
0
.
0
4
1
4
)
o
b
tain
e
d
,
it
sh
o
w
s
th
a
t
th
e
p
a
ra
ll
e
l
p
ro
c
e
ss
in
g
c
a
p
a
b
il
it
y
o
f
tF
RS
N P
sy
ste
m
c
o
u
ld
b
e
u
se
d
t
o
ra
p
i
d
ly
re
a
so
n
a
n
d
a
n
a
ly
z
e
th
e
se
v
e
rit
y
(p
o
ss
ib
il
it
y
o
f
a
n
a
tt
a
c
k
)
f
ro
m
a
n
y
n
e
tw
o
rk
d
a
ta.
K
ey
w
o
r
d
:
Fu
zz
y
s
p
ik
in
g
n
e
u
r
al
P
s
y
s
te
m
P
ar
allel
co
m
p
u
tat
io
n
Ma
tr
ix
-
b
ased
f
u
zz
y
r
ea
s
o
n
i
n
g
m
e
m
b
r
a
n
e
co
m
p
u
tin
g
R
u
le
-
b
ased
s
y
s
te
m
Co
p
y
rig
h
t
©
2
0
16
In
stit
u
te o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts
re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
R
u
f
ai
Kaz
ee
m
I
.
,
SOFT
A
M
R
esear
ch
C
en
tr
et,
Facu
lt
y
o
f
I
n
f
o
r
m
atio
n
Scie
n
ce
&
T
ec
h
n
o
lo
g
y
,
Natio
n
al
U
n
iv
er
s
it
y
o
f
Ma
la
y
s
ia,
4
3
6
0
0
UKM
B
an
g
i,
Selan
g
o
r
,
Ma
la
y
s
ia
.
E
m
ail:
r
u
f
f
y
k
2
0
0
1
@
y
a
h
o
o
.
co
m
1.
I
NT
RO
D
UCT
I
O
N
G
lo
b
a
ll
y
,
‗In
tru
sio
n
‘
issu
e
h
a
s b
e
c
o
m
e
a
m
a
jo
r
c
o
n
c
e
rn
n
o
t
o
n
ly
to
th
e
c
y
b
e
r
se
c
u
rit
y
e
x
p
e
rts
b
u
t
to
a
ll
th
e
u
se
rs
o
f
th
e
in
tern
e
t.
Mo
s
t
o
f
te
n
,
i
t
i
s
a
h
ac
u
lea
n
ta
s
k
to
f
lag
a
u
s
er
‘
s
b
eh
a
v
io
u
r
a
s
a
n
a
ttack
.
T
h
is
is
n
o
t
u
n
co
n
n
ec
ted
to
th
e
f
ac
t
t
h
at
s
o
m
e
d
eg
r
ee
s
o
f
u
n
ce
r
tain
t
ies
ar
e
in
v
o
lv
ed
.
Hen
ce
,
an
y
m
ec
h
a
n
is
m
w
h
ic
h
w
o
u
ld
v
en
t
u
r
e
in
to
h
an
d
li
n
g
t
h
is
t
y
p
e
o
f
s
ec
u
r
it
y
ch
alle
n
g
e
m
u
s
t b
e
ca
p
ab
le
o
f
r
ea
s
o
n
i
n
g
w
i
th
u
n
ce
r
tai
n
t
y
.
T
h
er
ef
o
r
e,
s
in
ce
f
u
zz
y
lo
g
ic
ca
n
r
ed
u
ce
th
e
f
al
s
e
s
i
g
n
al
i
n
d
eter
m
i
n
i
n
g
in
tr
u
s
i
v
e
a
ctiv
itie
s
b
y
p
r
o
v
id
i
n
g
p
o
s
s
ib
il
it
y
i
n
s
tead
o
f
cr
is
p
y
d
ec
is
io
n
,
its
u
s
ag
e
w
it
h
SN
P
w
h
ich
h
as
a
g
r
ap
h
ical
m
o
d
eli
n
g
ad
v
an
tag
e,
w
o
u
ld
en
g
e
n
d
er
q
u
ick
an
d
au
to
m
at
ic
attac
k
d
etec
tio
n
d
ec
is
io
n
.
T
h
er
e
is
n
o
d
is
p
u
ti
n
g
t
h
e
f
ac
t
th
at
S
p
i
k
i
n
g
Ne
u
r
al
P
(
SN
P
)
s
y
s
te
m
i
s
a
w
ell
e
s
tab
lis
h
ed
class
o
f
Me
m
b
r
an
e
C
o
m
p
u
ti
n
g
(
MC)
.
SN
P
s
y
s
te
m
w
h
ic
h
is
a
b
io
lo
g
icall
y
i
n
s
p
ir
ed
d
is
tr
i
b
u
ted
p
ar
allel
co
m
p
u
t
in
g
d
ev
ice
w
h
ich
f
u
n
ctio
n
s
b
y
t
h
e
w
a
y
n
e
u
r
o
n
s
co
m
m
u
n
ica
te.
A
p
ar
t
f
r
o
m
o
th
er
i
n
tr
i
n
s
ic
a
d
v
an
ta
g
es
o
f
SN
P
s
y
s
te
m
s
,
th
e
y
h
av
e
b
ee
n
p
r
o
v
e
d
to
b
e
c
o
m
p
u
tatio
n
al
l
y
co
m
p
l
ete
[
1
]
,
[
2
]
.
So
f
ar
,
s
o
m
e
o
f
t
h
e
ar
ea
s
i
n
w
h
ic
h
th
e
y
h
a
v
e
p
r
o
v
ed
to
b
e
i
m
m
en
s
el
y
b
e
n
ef
icial
i
n
clu
d
e
th
e
ef
f
o
r
ts
o
f
Díaz
-
P
er
n
i
l
et
al
[
3
]
in
2
0
1
2
.
I
n
th
eir
w
o
r
k
,
th
e
y
u
s
ed
s
p
i
k
in
g
n
eu
r
al
P
s
y
s
te
m
s
to
s
o
lv
e
th
e
s
k
eleto
n
izat
io
n
p
r
o
b
lem
.
B
ase
d
o
n
s
u
ch
d
ev
i
ce
s
,
th
e
y
b
u
i
lt
a
p
ar
allel
s
o
f
tw
ar
e
w
h
ich
w
as
i
m
p
le
m
en
ted
w
it
h
i
n
th
e
Gr
ap
h
ic
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8776
IJ
-
I
C
T
Vo
l.
5
,
No
.
1
,
A
p
r
il
2
0
1
6
:
1
1
–
2
0
12
P
r
o
ce
s
s
o
r
s
Un
its
(
GP
U)
ar
ch
itectu
r
e.
Fu
r
t
h
er
m
o
r
e,
T
s
er
en
-
O
n
o
lt
et
al
[
4
]
em
p
lo
y
ed
a
v
ar
ian
t
o
f
M
C
to
s
p
ec
if
icall
y
g
iv
e
a
d
eter
m
in
i
s
t
ic
s
o
lu
tio
n
to
ea
ch
o
f
t
h
e
t
w
o
w
ell
k
n
o
w
n
P
SP
AC
E
-
co
m
p
let
e
p
r
o
b
lem
s
:
Q
S
A
T
an
d
Q3
SA
T
.
I
n
th
e
ca
s
e
o
f
Q
S
A
T
,
th
ey
o
p
in
ed
t
h
at
th
e
a
n
s
w
er
to
an
y
i
n
s
tan
ce
o
f
t
h
e
p
r
o
b
le
m
is
co
m
p
u
tab
le
in
a
ti
m
e
w
h
ich
is
li
n
ea
r
w
i
th
r
esp
ec
t
to
b
o
th
th
e
n
u
m
b
er
n
o
f
B
o
o
lean
v
ar
iab
les
an
d
th
e
n
u
m
b
er
m
o
f
clau
s
es
th
at
co
m
p
o
s
e
t
h
e
i
n
s
tan
ce
.
As
r
eg
ar
d
s
Q3
S
A
T
,
th
e
y
p
o
s
t
u
lat
ed
th
at
th
e
an
s
w
er
i
s
co
m
p
u
ta
b
le
in
a
ti
m
e
w
h
ic
h
is
at
m
o
s
t c
u
b
ic
in
t
h
e
n
u
m
b
er
n
o
f
B
o
o
lean
v
ar
iab
les
.
Mo
s
t
r
ec
en
tl
y
,
p
r
ec
is
el
y
i
n
2
0
1
4
,
R
u
f
ai
et
al
[
5
]
ex
p
lo
r
ed
th
e
p
ar
allelis
m
a
d
v
a
n
tag
e
o
f
MC
f
o
r
th
e
f
ea
t
u
r
e
s
elec
tio
n
i
n
I
DS.
I
n
th
e
w
o
r
k
,
th
e
y
ap
p
lied
MC
to
th
e
B
ee
alg
o
r
ith
m
u
s
ed
f
o
r
an
an
o
m
al
y
-
b
a
s
ed
I
DS
w
it
h
a
v
ie
w
to
r
ed
u
ci
n
g
m
i
n
i
m
all
y
,
t
h
e
r
ed
u
n
d
an
t
f
ea
tu
r
es
w
h
ic
h
ad
v
er
s
e
l
y
af
f
ec
t
d
etec
tio
n
r
ate.
T
h
eir
ap
p
r
o
ac
h
co
n
s
q
en
tl
y
p
r
o
d
u
c
ed
h
ig
h
d
etec
tio
n
a
n
d
class
if
icatio
n
ac
cu
r
ac
y
r
ates
as
w
ell
a
s
r
ea
s
o
n
ab
l
y
d
ec
r
ea
s
ed
th
e
f
alse
alar
m
r
at
e.
I
n
a
s
i
m
ilar
p
er
s
p
ec
ti
v
e,
T
h
u
za
r
[
6
]
h
ad
ea
r
lier
o
n
in
2
0
1
2
p
r
o
p
o
s
ed
an
ap
p
r
o
ac
h
w
h
ich
u
s
ed
m
u
tu
al
c
o
r
r
elatio
n
f
o
r
f
ea
tu
r
e
e
lectio
n
b
y
r
ed
u
c
i
n
g
f
r
o
m
3
4
co
n
tin
u
o
u
s
attr
ib
u
tes
to
1
0
.
Sh
e
s
u
b
s
eq
u
en
tl
y
u
s
ed
Fu
zz
y
Dec
is
io
n
T
r
ee
class
if
ier
f
o
r
d
etec
tio
n
an
d
d
ia
g
n
o
s
i
s
o
f
att
ac
k
s
w
h
ic
h
y
ield
ed
g
o
o
ac
cu
r
ac
y
.
Ho
w
e
v
er
,
d
esp
ite
t
h
e
tr
e
m
en
d
o
u
s
ac
h
ie
v
e
m
e
n
t
s
b
ein
g
r
ec
o
r
d
ed
b
y
SN P
s
y
s
te
m
s
i
n
d
i
f
f
er
en
t a
r
ea
s
,
a
ch
all
e
n
g
e
o
f
u
s
i
n
g
it
to
h
an
d
le
u
n
ce
r
tai
n
t
y
p
r
o
b
le
m
s
h
as
ar
is
en
.
T
h
er
e
is
th
er
ef
o
r
e
th
e
co
n
s
tan
t
n
ee
d
to
ex
te
n
d
it so
as
to
h
a
n
d
le
e
m
er
g
i
n
g
ca
s
es
s
u
c
h
a
s
f
u
zz
y
p
r
o
b
le
m
s
.
H
en
ce
,
i
n
t
h
is
w
o
r
k
,
a
tr
ap
ez
o
id
al
Fu
zz
y
R
ea
s
o
n
in
g
Sp
ik
i
n
g
Neu
r
al
P
s
y
s
te
m
(
tF
R
SN
P
)
s
y
s
te
m
(
a
s
p
r
o
p
o
s
ed
b
y
W
an
g
et
al
2
0
1
3
)
[7
]
is
u
s
ed
to
r
ep
r
esen
t
t
h
e
f
u
zz
y
p
r
o
d
u
ctio
n
r
u
les
in
a
k
n
o
w
led
g
e
b
ase
o
f
a
r
u
le
-
b
ased
in
tr
u
s
io
n
d
etec
tio
n
s
y
s
te
m
.
W
ith
th
i
s
ap
p
licatio
n
,
th
e
ce
r
tain
t
y
f
ac
to
r
s
o
f
f
u
zz
y
p
r
o
d
u
ctio
n
r
u
les
a
n
d
th
e
tr
u
th
v
al
u
es
o
f
p
r
o
p
o
s
itio
n
s
ar
e
d
escr
ib
ed
b
y
tr
ap
ez
o
id
al
f
u
zz
y
n
u
m
b
er
s
.
I
n
th
is
w
o
r
k
h
o
w
ev
er
,
a
tr
ap
ez
o
i
d
al
Fu
zz
y
R
ea
s
o
n
i
n
g
Sp
i
k
i
n
g
Neu
r
al
P
-
Net
w
o
r
k
I
n
tr
u
s
io
n
S
y
s
te
m
(
tF
R
SN
P
-
NI
DS)
f
r
a
m
e
w
o
r
k
i
s
h
er
eb
y
p
r
o
p
o
s
ed
.
T
h
is
ap
p
lies
a
tr
ap
ez
o
id
al
Fu
zz
y
R
ea
s
o
n
i
n
g
Sp
i
k
in
g
Ne
u
r
al
P
s
y
s
te
m
to
d
etec
t
in
tr
u
s
iv
e
tr
af
f
ic
in
a
r
u
le
-
b
ased
e
n
v
ir
o
n
m
en
t
o
f
a
n
et
w
o
r
k
d
etec
tio
n
in
tr
u
s
io
n
s
y
s
te
m
.
T
h
is
is
ac
h
ie
v
ed
b
y
co
m
b
i
n
i
n
g
th
e
(
class
ical)
d
y
n
a
m
ic
f
ir
in
g
m
ec
h
a
n
is
m
s
o
f
n
e
u
r
o
n
s
w
it
h
f
u
zz
y
r
ea
s
o
n
in
g
i
n
a
m
atr
ix
-
b
ased
f
o
r
m
.
B
y
s
o
d
o
in
g
,
t
FR
SN
P
-
NI
DS
w
o
u
ld
b
r
in
g
ab
o
u
t
m
u
ch
m
o
r
e
e
n
h
a
n
ce
d
in
f
er
en
ce
ab
ili
t
y
in
attac
k
d
et
ec
tio
n
.
T
h
is
m
a
y
b
e
co
n
s
id
er
e
d
as
a
n
o
v
el
ap
p
r
o
ac
h
b
ec
au
s
e
g
o
i
n
g
th
r
o
u
g
h
t
h
e
liter
atu
r
e,
it
ap
p
ea
r
s
th
at
th
is
i
s
th
e
f
ir
s
t
ti
m
e
S
N
P
s
y
s
te
m
(
an
ele
m
e
n
t
o
f
MC)
is
b
ein
g
ap
p
lied
to
r
u
le
-
b
ased
I
DS.
T
h
e
f
r
a
m
e
w
o
r
k
r
elie
s
o
n
t
h
e
s
ig
n
i
f
ica
n
t
p
ar
a
m
eter
s
o
f
an
o
m
alo
u
s
n
e
t
w
o
r
k
p
ac
k
et
s
,
th
e
s
tatis
t
ics
o
f
s
y
s
te
m
b
eh
a
v
io
r
,
an
d
th
e
d
ec
is
io
n
w
i
th
t
h
r
es
h
o
ld
an
d
f
u
zz
y
r
u
le
-
b
a
s
ed
tech
n
iq
u
e.
W
it
h
a
s
et
o
f
f
u
zz
y
r
u
le
s
co
r
r
esp
o
n
d
in
g
w
i
th
t
h
e
ap
p
r
o
p
r
iate
m
e
m
b
er
s
h
ip
v
al
u
es,
t
h
e
e
x
a
m
p
le
o
f
B
r
u
te
Fo
r
ce
A
ttac
k
(
B
FA
)
w
a
s
i
m
p
le
m
en
ted
.
T
h
e
r
est
o
f
th
e
p
ap
er
is
tr
u
ctu
r
ed
u
n
d
er
th
e
f
o
llo
w
i
n
g
s
ec
tio
n
s
:
Sec
tio
n
2
b
r
ief
l
y
d
i
s
cu
s
s
e
s
I
DS
an
d
attac
k
clas
s
i
f
icatio
n
s
.
I
n
s
ec
ti
o
n
3
,
Fu
zz
y
R
u
le
-
b
ase
k
n
o
wled
g
e
b
ase
I
DS
is
p
r
esen
ted
w
it
h
e
m
p
h
as
is
o
n
tr
ap
ez
o
i
d
al
f
u
zz
y
n
u
m
b
er
ar
it
h
m
e
tics
a
n
d
g
e
n
er
atio
n
o
f
f
u
z
z
y
p
r
o
d
u
ctio
n
r
u
le
s
f
o
r
n
et
w
o
r
k
attac
k
.
W
h
ile
th
e
f
o
u
r
t
h
s
ec
tio
n
d
w
ells
o
n
SN
P
v
er
s
u
s
tFF
R
SNP
s
y
s
te
m
s
,
s
ec
tio
n
5
p
r
esen
ts
th
e
p
r
o
p
o
s
ed
tFR
SNP
-
NI
DS
f
r
a
m
e
w
o
r
k
.
Sectio
n
s
6
a
n
d
7
h
ig
h
l
ig
h
t
th
e
i
m
p
le
m
e
n
tatio
n
,
r
esu
lt
s
a
n
d
d
is
cu
s
s
io
n
.
T
h
e
f
i
n
a
l sectio
n
d
r
a
w
s
t
h
e
co
n
clu
s
io
n.
2.
I
DS A
ND
A
T
T
ACK
CL
ASS
I
F
I
CA
T
I
O
N
S
An
i
n
tr
u
s
io
n
is
a
s
ec
u
r
it
y
t
h
r
ea
t
w
h
ic
h
i
s
d
elib
er
atel
y
d
o
n
e
to
ac
ce
s
s
a
n
d
co
m
p
r
o
m
i
s
e
t
h
e
in
te
g
r
it
y
an
d
co
n
f
id
en
tial
it
y
o
f
a
r
eso
u
r
ce
an
d
also
t
o
r
en
d
er
an
in
f
o
r
m
atio
n
s
y
s
te
m
u
n
r
eliab
le
o
r
u
n
u
s
ab
le.
[
8
]
-
[
1
0
]
.
T
h
en
,
an
I
D
S
i
s
a
d
e
v
ice
w
h
i
ch
m
o
n
i
to
r
s
t
h
e
i
n
f
o
r
m
atio
n
s
y
ate
m
i
n
o
r
d
er
to
ch
ec
k
i
t
a
g
a
in
s
t
an
y
p
o
te
n
ti
all
y
m
alicio
u
s
ac
tiv
it
y
a
n
d
to
r
e
p
o
r
t
s
a
m
e
to
ad
m
i
n
i
s
tr
ato
r
s
f
o
r
f
u
r
th
er
in
v
est
ig
at
io
n
.
I
DSs
ar
e
a
cr
itica
l
co
m
p
o
n
e
n
t
o
f
an
y
s
ec
u
r
it
y
i
n
f
r
astr
u
ctu
r
e.
A
ls
o
,
an
I
n
tr
u
s
io
n
Dete
ctio
n
S
y
s
te
m
an
al
y
ze
s
in
f
o
r
m
atio
n
f
r
o
m
a
co
m
p
u
ter
o
r
a
n
et
w
o
r
k
to
d
etec
t
m
alicio
u
s
ac
tio
n
s
a
n
d
b
eh
av
io
r
s
t
h
at
ca
n
co
m
p
r
o
m
i
s
e
th
e
s
ec
u
r
it
y
o
f
a
co
m
p
u
ter
s
y
s
te
m
[
1
1
]
,
[
1
2
]
.
T
h
er
ef
o
r
e,
it
is
a
s
o
f
t
w
ar
e
p
r
o
d
u
ct
o
f
h
ar
d
w
ar
e
tech
n
o
lo
g
y
t
h
at
au
to
m
ate
a
m
o
n
ito
r
i
n
g
p
r
o
ce
s
s
o
f
e
v
en
t
s
w
h
ic
h
o
cc
u
r
in
a
co
m
p
u
ter
s
y
s
te
m
o
r
n
et
w
o
r
k
w
it
h
a
v
ie
w
to
an
al
y
s
i
n
g
t
h
e
m
f
o
r
s
ig
n
s
o
f
in
tr
u
s
io
n
.
I
n
s
i
m
ilar
p
er
s
p
ec
tiv
e
,
Deb
ar
et
al
[
1
3
]
w
er
e
o
f
th
e
v
ie
w
th
a
t
an
I
DS
is
a
s
y
s
te
m
w
h
ic
h
d
y
n
a
m
icall
y
m
o
n
ito
r
s
t
h
e
ac
tio
n
ta
k
e
n
in
a
g
iv
e
n
en
v
ir
o
n
m
e
n
t,
an
d
d
ec
id
es
w
h
et
h
er
o
r
n
o
t
th
ese
ac
tio
n
s
ar
e
s
y
m
p
to
m
atic
o
f
an
attac
k
o
r
co
n
s
tit
u
te
a
leg
iti
m
ate
u
s
e
o
f
th
e
e
n
v
ir
o
n
m
e
n
t
A
ttac
k
s
ar
e
u
s
ed
to
s
p
r
ea
d
m
is
in
f
o
r
m
a
t
io
n
,
cr
ip
p
le
tactica
l
s
er
v
ice
s
,
ac
ce
s
s
s
en
s
iti
v
e
i
n
f
o
r
m
at
io
n
,
esp
io
n
ag
e,
d
ata
t
h
e
f
t
an
d
ab
o
v
e
all,
f
in
a
n
cial
lo
s
s
e
s
[
1
4
]
.
Or
d
in
ar
il
y
,
s
et
s
o
f
n
et
w
o
r
k
tr
af
f
ic
s
h
o
u
ld
co
m
p
r
is
e
o
f
s
ets o
f
n
o
r
m
al
tr
a
f
f
ic
an
d
f
o
u
r
ca
teg
o
r
ies o
f
attac
k
.
T
h
ese
ca
teg
o
r
ies o
f
attac
k
ar
e:
1)
Den
ia
l
o
f
s
ervice
(
Do
S)
attac
k
s
i
s
an
a
ttack
s
it
u
atio
n
in
wh
ich
th
e
at
tack
er
m
a
k
es
s
o
m
e
co
m
p
u
ti
n
g
o
r
m
e
m
o
r
y
r
eso
u
r
ce
to
o
b
u
s
y
to
m
a
n
ag
e
au
th
e
n
tic
r
eq
u
est
s
.
I
n
o
th
er
w
o
r
d
s
,
it
i
s
a
s
ce
n
ar
i
o
w
h
er
eb
y
a
n
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
I
C
T
I
SS
N:
2252
-
8776
A
tta
ck
Dete
ctio
n
in
a
R
u
le
-
B
a
s
ed
S
ystem
u
s
i
n
g
…
(
R
u
fa
i,
K
.
I
et
a
l.
)
13
attac
k
er
o
v
er
w
h
e
l
m
s
a
tar
g
e
t
m
ac
h
in
e
w
i
th
to
o
m
u
c
h
d
ata
an
d
co
n
s
eq
u
e
n
tl
y
d
is
allo
w
i
n
g
it
f
r
o
m
ex
ec
u
t
in
g
it
s
le
g
iti
m
ate
d
u
ties
.
I
t
s
i
m
p
l
y
ex
h
a
u
s
t
s
t
h
e
n
e
t
w
o
r
k
.
E
x
a
m
p
les
h
er
e
in
cl
u
d
e;
S
m
u
r
f
,
T
ea
r
d
r
o
p
,
Nep
tu
n
e
a
n
d
T
C
P
SYN
f
lo
o
d
in
g
.
2)
User
to
r
o
o
t
(
U2
R
)
attac
k
s
:
An
attac
k
er
i
n
th
i
s
s
it
u
atio
n
b
eg
in
s
h
i
s
d
astar
d
l
y
ac
t
b
y
ac
c
ess
i
n
g
a
n
o
r
m
al
u
s
er
ac
co
u
n
t
an
d
tak
es
ad
v
a
n
t
ag
e
o
f
its
v
u
l
n
er
ab
ilit
ies
to
g
a
in
u
n
au
th
o
r
ized
ac
ce
s
s
to
th
e
r
o
o
t.
E
x
am
p
les
ar
e;
B
u
f
f
er
_
o
v
er
f
lo
w
,
lo
ad
m
o
d
u
le,
an
d
r
o
o
tk
it
3)
R
emo
te
to
u
s
er
(
R
2
L
)
attac
k
o
cc
u
r
s
w
h
en
an
attac
k
er
w
h
o
h
as
th
e
p
r
iv
ile
g
e
o
f
s
en
d
i
n
g
n
et
w
o
r
k
p
ac
k
et
s
to
a
m
ac
h
i
n
e,
t
h
er
ea
f
ter
e
x
p
lo
its
th
e
m
ac
h
i
n
e‘
s
v
u
l
n
er
ab
ilit
ies
to
g
ain
lo
ca
l
ac
ce
s
s
.
E
x
a
m
p
le
s
ar
e:
Ftp
_
w
r
ite,
i
m
ap
,
m
u
lti
h
o
p
,
p
h
f
,
s
p
y
,
w
ar
ez
clie
n
t,
B
r
u
te
Fo
r
ce
A
ttac
k
(
B
F
A
)
4)
P
r
o
b
in
g
(
P
R
OB
E
)
A
s
t
h
e
n
a
m
e
co
n
n
o
tes,
is
a
s
itu
a
tio
n
w
h
er
eb
y
a
n
a
ttack
er
ex
a
m
i
n
es
a
n
et
w
o
r
k
f
o
r
t
h
e
s
o
le
ai
m
o
f
g
ar
n
er
i
n
g
v
i
tal
in
f
o
r
m
at
io
n
w
h
ich
m
a
y
b
e
u
s
ed
t
o
cir
cu
m
v
en
t
its
s
ec
u
r
it
y
co
n
tr
o
ls
.
E
x
a
m
p
le
s
ar
e
Satan
,
ip
s
w
ee
p
,
n
m
ap
,
p
o
r
ts
w
ee
p
.
3.
F
U
Z
Z
Y
R
UL
E
-
B
ASE
K
NO
WL
E
D
G
E
B
AS
E
I
DS
Fu
zz
y
r
u
le
s
ar
e
n
o
r
m
a
ll
y
cr
ea
ted
b
y
n
et
w
o
r
k
s
ec
u
r
it
y
e
x
p
er
ts
b
ased
o
n
t
h
eir
d
o
m
ai
n
k
n
o
w
led
g
e.
I
n
g
en
er
al
th
er
e
f
o
r
e,
th
e
f
u
zz
y
r
u
les
g
i
v
e
n
to
th
e
f
u
zz
y
s
y
s
te
m
i
s
d
o
n
e
m
a
n
u
all
y
o
r
b
y
ex
p
er
ts
,
w
h
o
g
i
v
e
t
h
e
r
u
les
b
y
a
n
al
y
zi
n
g
in
tr
u
s
io
n
b
eh
av
io
u
r
[
1
5
]
.
Ho
w
e
v
er
,
t
h
e
n
u
m
b
er
o
f
f
u
zz
y
r
u
le
s
s
h
o
u
l
d
b
e
r
ed
u
ce
d
as
m
u
ch
as p
o
s
s
ib
le.
A
l
s
o
,
th
e
―
IF
‖
p
ar
t o
f
f
u
zz
y
r
u
les s
h
o
u
ld
co
n
s
id
e
r
ab
ly
b
e
s
h
o
r
t [
1
6
]
,
[
1
7
]
.
Fu
zz
y
r
u
les ar
e
d
esira
b
le
b
ec
a
u
s
e
o
f
t
h
eir
i
n
ter
p
r
etab
ilit
y
b
y
h
u
m
a
n
e
x
p
er
ts
.
B
ased
o
n
th
e
s
ev
er
it
y
o
f
an
attac
k
,
f
u
zz
y
r
u
le
s
co
u
ld
b
e
u
s
ed
to
g
e
n
er
ate
an
aler
t
w
h
ic
h
f
all
s
u
n
d
er
eith
er
o
f
a
b
s
o
lu
tely
-
fa
ls
e,
ve
r
y
-
lo
w
,
lo
w
,
med
iu
m
-
lo
w
,
med
iu
m,
me
d
iu
m
-
h
ig
h
,
h
ig
h
,
e
ve
r
y
-
h
ig
h
o
r
a
b
s
o
lu
tely
-
h
ig
h
.
3
.
1
.
T
ra
pezo
ida
l F
uzzy
Nu
m
ber
Arit
h
m
et
ic
T
r
a
p
ez
o
id
al
f
u
zz
y
s
et
h
as
b
ee
n
ac
k
n
o
w
led
g
ed
to
b
e
h
i
g
h
l
y
u
s
e
f
u
l
b
ec
au
s
e
i
t
allo
w
s
f
u
ll
m
e
m
b
er
s
h
ip
o
v
er
an
y
r
an
g
e
in
th
e
u
n
i
v
er
s
e
o
f
d
is
co
u
r
s
e
a
n
d
t
h
e
r
an
g
e
o
f
th
e
r
i
g
h
t
a
n
d
le
f
t
ta
ils
ca
n
b
e
ad
j
u
s
ted
,
th
u
s
,
p
r
o
v
id
in
g
g
r
ea
t f
le
x
ib
ilit
y
.
T
r
a
p
ez
o
id
Fu
zz
y
N
u
m
b
er
Ā
,
m
a
y
b
e
p
ar
a
m
eter
ized
as
a
4
-
tu
p
p
le
(
p
,
q
,
r
,
s
)
,
as
s
h
o
w
n
i
n
Fi
g
u
re
1
b
elo
w
,
w
h
er
e
it
s
m
e
m
b
er
s
h
ip
f
u
n
ctio
n
d
ef
i
n
ed
b
y
:
Fig
u
r
e
1
.
Gr
ap
h
o
f
T
r
a
p
ez
o
id
a
l n
u
m
b
er
s
[
1
8
]
Fro
m
tab
le
1
b
elo
w
,
f
o
r
th
e
n
u
m
_
f
ailed
_
lo
g
i
n
s
f
ea
t
u
r
e,
th
e
m
e
m
b
er
s
h
ip
ter
m
s
u
s
ed
ar
e;
A
b
s
o
l
u
tel
y
S
m
all
(
A
S),
Ver
y
S
m
all
(
VS)
,
S
m
al
l (
S),
Me
d
iu
m
S
m
a
ll (
M
S),
Me
d
iu
m
(
M)
,
Me
d
i
u
m
L
ar
g
e
(
ME
)
,
L
ar
g
e
(
E
)
,
Ver
y
L
ar
g
e
(
VE
)
,
A
b
s
o
lu
tel
y
L
ar
g
e
(
A
E
)
.
Ho
w
ev
er
,
t
h
e
ti
m
e
i
n
ter
v
al
b
et
w
ee
n
n
u
m
b
er
o
f
f
a
iled
lo
g
i
n
s
is
r
ep
r
esen
ted
w
it
h
t
h
e
ter
m
s
;
A
b
s
o
l
u
tel
y
S
h
o
r
t
(
A
T
)
,
Ver
y
S
h
o
r
t
(
VT
)
,
Sh
o
r
t
(
T
)
,
M
ed
iu
m
S
h
o
r
t
(
M
T
)
,
Me
d
iu
m
(
M)
,
Me
d
iu
m
L
o
n
g
(
MG
)
,
L
o
n
g
(
G)
,
Ver
y
L
o
n
g
(
VG)
an
d
A
b
s
o
lu
tel
y
L
o
n
g
(
A
G)
.
A
l
s
o
,
th
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8776
IJ
-
I
C
T
Vo
l.
5
,
No
.
1
,
A
p
r
il
2
0
1
6
:
1
1
–
2
0
14
m
e
m
b
er
s
h
ip
ter
m
s
u
s
ed
f
o
r
at
tack
p
o
s
s
ib
il
it
y
ar
e;
A
b
s
o
l
u
tel
y
Fal
s
e
(
AF)
,
Ver
y
L
o
w
(
V
L
)
,
L
o
w
(
L
)
,
Me
d
iu
m
L
o
w
(
ML
)
,
Me
d
iu
m
(
M)
,
Me
d
iu
m
Hig
h
(
MH
)
,
Hig
h
(
H)
,
Ve
r
y
H
ig
h
(
VH)
an
d
A
b
s
o
lu
tel
y
Hig
h
(
AH)
.
So
,
w
h
e
n
ap
p
l
y
i
n
g
tF
SN
P
to
attac
k
d
etec
tio
n
,
ea
ch
i
n
p
u
t
f
u
zz
y
ter
m
d
ef
i
n
ed
in
th
e
d
eter
m
i
n
is
t
ic
tr
ap
ez
o
id
al
f
u
zz
y
s
y
s
te
m
in
cl
u
d
es
t
h
e
f
o
ll
o
w
i
n
g
m
e
m
b
er
s
h
ip
f
u
n
ctio
n
s
(
A
F,
V
L
,
L
,
ML
,
M,
MH
,
H,
VH,
an
d
AH)
co
u
ld
be
ad
o
p
t
ed
.
T
ab
le
1
.
Nu
m
b
er
s
De
f
i
n
i
n
g
Me
m
b
er
s
h
ip
T
er
m
s
3
.
2
.
G
ener
a
t
ing
F
uzzy
P
ro
du
ct
io
n Rule
f
o
r
Net
w
o
rk
At
t
a
ck
A
lt
h
o
u
g
h
,
th
er
e
ar
e
f
i
v
e
b
asi
c
t
y
p
es
o
f
f
u
zz
y
p
r
o
d
u
ctio
n
r
u
les,
i
n
th
is
w
o
r
k
h
o
w
ev
er
,
we
ap
p
ly
t
h
e
t
y
p
e
ca
lled
co
m
p
o
s
ite
co
n
j
u
n
c
tiv
e
f
u
zz
y
p
r
o
d
u
ctio
n
r
u
le
o
f
t
h
e
f
o
r
m
[
7
]
,
[
1
9
]
:
Her
e,
R
i
an
d
c
i
r
esp
ec
tiv
el
y
r
ep
r
esen
t
th
e
i
th
f
u
zz
y
p
r
o
d
u
ctio
n
r
u
le
a
n
d
ce
r
tain
t
y
f
ac
to
r
.
W
h
er
ea
s
,
P
s
tan
d
s
f
o
r
th
e
p
r
o
p
o
s
itio
n
an
d
k
f
o
r
its
n
u
m
b
er
in
a
r
u
le
-
b
ased
en
v
ir
o
n
m
e
n
t,
θ
is
t
h
e
tr
u
th
v
al
u
e
f
o
r
th
e
i
th
pr
o
p
o
s
itio
n
.
Ho
w
e
v
er
,
th
e
s
y
m
b
o
l
―
‖
r
ep
r
esen
t
s
t
h
e
A
N
D
o
p
er
ato
r
o
f
tr
ap
ez
o
id
al
f
u
zz
y
n
u
m
b
er
i
n
w
h
ic
h
―
‖
p
er
f
o
r
m
s
m
i
n
i
m
izat
io
n
o
p
er
atio
n
.
A
f
u
zz
y
s
et
i
s
a
s
et
w
h
ich
i
s
d
ef
in
ed
b
y
a
m
e
m
b
er
s
h
ip
f
u
n
ctio
n
.
A
m
e
m
b
er
s
h
ip
f
u
n
ctio
n
ass
i
g
n
s
to
ea
ch
ele
m
e
n
t
i
n
t
h
e
s
et
u
n
d
er
co
n
s
id
er
atio
n
(
t
h
e
u
n
iv
er
s
a
l
s
p
ac
e)
a
m
e
m
b
er
s
h
ip
g
r
ad
e,
wh
ich
is
a
v
alu
e
i
n
t
h
e
in
ter
v
a
l
[
0
,
1
]
.
Fu
zz
y
"
if
-
th
en
"
r
u
les
ar
e
o
f
ten
e
m
p
lo
y
ed
to
ca
p
tu
r
e
t
h
e
i
m
p
r
ec
is
e
m
o
d
es
o
f
r
ea
s
o
n
in
g
w
h
i
c
h
p
lay
a
n
es
s
en
t
ial
r
o
le
in
t
h
e
h
u
m
an
ab
ili
t
y
to
m
ak
e
d
ec
is
io
n
s
in
u
n
ce
r
tai
n
an
d
i
m
p
r
ec
i
s
e
en
v
ir
o
n
m
e
n
ts
.
T
h
e
f
o
llo
w
i
n
g
r
u
les
w
h
ic
h
ar
e
f
o
r
m
u
lated
f
o
r
B
r
u
te
Fo
r
ce
Attack
(
B
F
A
)
w
er
e
d
o
n
e
b
y
ad
o
p
tin
g
t
h
e
s
i
m
p
le
f
u
zz
y
r
u
le
s
th
eo
r
y
.
B
FA
i
s
a
s
it
u
atio
n
w
h
er
e
a
n
i
n
tr
u
d
er
tr
ies
to
lo
g
i
n
w
i
th
s
e
v
er
al
u
s
er
s
‘
p
a
s
s
w
o
r
d
s
an
d
f
ai
ls
.
T
h
is
a
ttack
ca
n
b
e
id
en
ti
f
ied
b
y
o
b
s
er
v
in
g
t
h
e
n
u
m
b
er
o
f
lo
g
i
n
f
ail
u
r
es
a
n
d
th
e
t
i
m
e
i
n
ter
v
a
l
b
et
w
ee
n
ea
ch
f
ail
u
r
e.
[
2
0
]
Rule
1
:
(
C
F =
VH)
S
y
m
p
to
m
(
i)
Set o
f
n
u
m
_
f
ailed
_
lo
g
i
n
s
is
V
S
(
ii)
T
im
e
i
n
te
r
v
al
i
s
VG
P
r
o
b
ab
le
A
ttack
B
r
u
te
Fo
r
ce
attac
k
n
o
t s
u
s
p
ec
t
ed
Rule
2
:
(
C
F =
H)
S
y
m
p
to
m
(
i)
Set o
f
n
u
m
_
f
ailed
_
lo
g
i
n
s
is
V
S
(
ii)
T
im
e
i
n
ter
v
al
i
s
T
P
r
o
b
ab
le
A
ttack
Gen
er
al
f
ai
led
lo
g
in
at
te
m
p
t
s
Rule
3
:
(
C
F =
H)
S
y
m
p
to
m
(
i)
Set o
f
n
u
m
_
f
ailed
_
lo
g
i
n
s
is
M
(
ii)
T
im
e
i
n
ter
v
al
i
s
M
P
r
o
b
ab
le
A
ttack
Ma
y
an
d
m
a
y
n
o
t b
e
B
FA
Rule
4
:
(
C
F =
H)
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
I
C
T
I
SS
N:
2252
-
8776
A
tta
ck
Dete
ctio
n
in
a
R
u
le
-
B
a
s
ed
S
ystem
u
s
i
n
g
…
(
R
u
fa
i,
K
.
I
et
a
l.
)
15
S
y
m
p
to
m
(
i)
Set o
f
n
u
m
_
f
ailed
_
lo
g
i
n
s
is
V
E
(
ii)
T
im
e
i
n
ter
v
al
i
s
T
P
r
o
b
ab
le
A
ttack
Ser
io
u
s
B
r
u
te
Fo
r
ce
attac
k
Rule
5
:
(
C
F =
H)
S
y
m
p
to
m
(
i)
Set o
f
n
u
m
_
f
ailed
_
lo
g
i
n
s
is
V
E
(
ii)
T
im
e
i
n
ter
v
al
i
s
VT
P
r
o
b
ab
le
A
tta
ck
Ver
y
s
e
v
er
e
B
r
u
te
Fo
r
ce
attac
k
4.
SN P
SYS
T
E
M
VE
RSU
S t
F
RSN
P
E
f
f
o
r
ts
h
a
v
e
b
ee
n
p
u
t
u
p
to
ex
ten
d
th
e
b
asic Sp
i
k
i
n
g
Ne
u
r
al
P
s
y
s
te
m
li
k
e
th
at
o
f
W
an
g
H
et
al
[
7
]
w
h
er
e
tr
ap
ez
o
id
al
Fu
zz
y
R
ea
s
o
n
in
g
Sp
i
k
in
g
Ne
u
r
al
P
s
y
s
te
m
(
tF
R
SN P
)
s
y
s
te
m
w
a
s
p
r
o
m
u
lg
ated
.
4
.
1
.
B
a
s
ic
SN P
Sy
s
t
e
m
SN
P
s
y
s
te
m
is
cla
s
s
o
f
d
i
s
tr
ib
u
ted
an
d
p
ar
allel
co
m
p
u
ti
n
g
m
o
d
el
w
h
ic
h
is
i
n
s
p
ir
ed
b
y
th
e
n
eu
r
o
p
h
y
s
io
lo
g
ical
b
eh
a
v
io
u
r
o
f
n
e
u
r
o
n
s
s
e
n
d
i
n
g
elec
tr
ica
l
i
m
p
u
ls
es
(
s
p
i
k
es)
to
o
th
er
n
eu
r
o
n
s
.
T
h
e
s
et
o
f
n
eu
r
o
n
s
ar
e
p
lace
d
in
th
e
n
o
d
es
o
f
a
g
r
ap
h
w
h
ic
h
f
ac
ilit
ate
th
e
m
o
v
e
m
e
n
t
o
f
t
h
e
s
p
ik
e
s
alo
n
g
t
h
e
s
y
n
ap
s
es
(
ed
g
es
o
f
t
h
e
g
r
ap
h
)
,
u
n
d
er
th
e
co
n
tr
o
l
o
f
f
ir
i
n
g
r
u
les.
Fo
r
th
e
m
ai
n
p
u
r
p
o
s
e
o
f
co
m
m
u
n
ica
tio
n
,
th
e
s
e
n
eu
r
o
n
s
ar
e
co
n
n
ec
ted
to
ea
ch
o
t
h
er
in
a
n
in
tr
icate
p
atter
n
.
T
h
e
y
h
a
v
e
t
h
r
ee
f
u
n
ctio
n
a
ll
y
d
i
s
tin
c
t
p
ar
ts
ca
lled
d
end
r
ites
,
s
o
m
a
an
d
axon
.
H
en
ce
,
w
h
e
n
t
h
e
y
in
ter
ac
t,
t
h
er
e
is
an
e
x
c
h
an
g
e
o
f
s
p
ik
e
s
.
I
n
d
o
in
g
t
h
is
t
h
o
u
g
h
,
p
r
e
-
s
y
n
ap
tic
n
e
u
r
o
n
i
s
co
n
f
i
g
u
r
ed
to
h
a
v
e
a
k
in
d
o
f
‗
h
a
n
d
s
h
ak
e
‘
w
it
h
t
h
e
p
o
s
t
-
s
y
n
ap
tic
n
eu
r
o
n
at
a
j
u
n
ctio
n
k
n
o
w
n
as
s
y
na
p
s
e
b
y
m
ea
n
s
o
f
s
p
ec
i
f
ic
r
u
le
s
.
Fig
u
r
e
2
.
Sch
e
m
atic
r
ep
r
esen
t
atio
n
o
f
h
o
w
Ne
u
r
o
n
s
co
m
m
u
n
icate
[
2
1
]
Fig
u
r
e
2
ab
o
v
e
d
ep
icts
a
s
i
m
p
le
s
ch
e
m
atic
r
ep
r
ese
n
tatio
n
o
f
an
SN
P
s
y
s
te
m
w
it
h
th
r
ee
n
e
u
r
o
n
s
x
,
y
an
d
z
.
T
h
e
s
p
i
k
e,
d
en
o
ted
a
s
―
a”
w
h
ic
h
i
s
t
h
e
b
asic
u
n
it
o
f
i
n
f
o
r
m
atio
n
is
s
to
r
ed
in
th
e
n
e
u
r
o
n
.
W
h
i
le
n
e
u
r
o
n
x
h
as r
u
le
a
2
→
a
,
y
h
as r
u
le
a
→
a
an
d
z
h
as r
u
le
a
→
λ
.
T
h
e
s
y
n
ap
s
e
i
s
also
ca
p
tu
r
ed
.
Fu
r
t
h
er
m
o
r
e,
w
h
en
t
h
e
r
u
le
s
(
w
h
ich
m
a
y
b
e
u
s
ed
co
n
cu
r
r
en
tl
y
)
ar
e
ap
p
lied
,
th
e
s
y
s
te
m
is
tr
an
s
f
o
r
m
ed
.
B
y
a
s
s
u
m
i
n
g
t
h
e
p
r
esen
ce
o
f
a
g
lo
b
al
clo
c
k
,
t
h
e
s
y
s
te
m
is
s
y
n
c
h
r
o
n
ize
d
.
A
ti
m
es,
th
e
ce
ll
s
en
d
i
n
g
o
u
t
s
p
ik
e
s
is
―
clo
s
ed
‖
d
u
r
in
g
a
r
e
f
r
ac
to
r
y
p
er
io
d
o
f
a
n
eu
r
o
n
.
A
t
t
h
i
s
p
o
in
t,
th
e
n
e
u
r
o
n
d
o
es
n
o
t
o
n
l
y
clo
s
es
to
th
e
ac
ce
p
tan
ce
o
f
i
n
p
u
t,
it
also
ca
n
n
o
t
f
ir
e
s
p
ik
e
a
g
ain
.
Dep
e
n
d
in
g
o
n
th
e
e
x
ac
t
f
o
r
m
ali
s
atio
n
o
f
th
e
m
o
d
el,
t
h
e
n
o
tio
n
o
f
a
s
u
cc
ess
f
u
l c
o
m
p
u
ta
tio
n
is
d
e
f
i
n
ed
to
g
eth
er
w
it
h
its
o
u
tp
u
t [
2
2
].
Si
m
p
l
y
p
u
t,
Sp
ik
in
g
Neu
r
al
P
s
y
s
te
m
is
a
n
o
n
d
eter
m
i
n
is
t
ic
class
o
f
m
e
m
b
r
an
e
co
m
p
u
ti
n
g
s
y
s
te
m
s
w
h
ic
h
is
s
i
m
i
lar
to
o
th
er
P
s
y
s
te
m
v
ar
ia
n
t
s
s
u
ch
as
T
is
s
u
e
-
li
k
e
an
d
C
el
l
-
l
ik
e
.
I
n
g
e
n
er
al,
a
n
SN P
s
y
s
te
m
o
f
d
eg
r
ee
m
≥
1
is
a
co
n
s
tr
u
ct
o
f
th
e
f
o
r
m
:
∏
=
(
O
, σ
1
….
.
σ
m
s
y
n
,
o
u
t)
,
W
h
er
e:
1
)
O
=
{a
}
is
th
e
s
in
g
leto
n
alp
h
ab
et.
(
a
is
ca
lled
s
p
ik
e)
;
2
)
σ
1,
….
.
,
σ
m
ar
e
n
eu
r
o
n
s
,
o
f
th
e
f
o
r
m
σ
1
=
(
n
i
,
R
i
)
,
1
≤
i
≤
m
,
w
h
er
e:
*
n
i
≥
0
is
th
e
i
n
it
ial
n
u
m
b
er
o
f
s
p
i
k
es
co
n
tai
n
ed
b
y
th
e
n
e
u
r
o
n
;
*
R
i
i
s
a
f
i
n
ite
s
e
t o
f
r
u
le
s
o
f
t
h
e
f
o
llo
w
i
n
g
t
w
o
f
o
r
m
s
:
a)
E/
a
c
→
a
;
d
,
w
h
er
e
E
is
a
r
eg
u
lar
ex
p
r
ess
io
n
o
v
er
O,
c
≥
1
,
a
n
d
d
≥
0
;
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8776
IJ
-
I
C
T
Vo
l.
5
,
No
.
1
,
A
p
r
il
2
0
1
6
:
1
1
–
2
0
16
b)
a
s
→
λ
,
f
o
r
s
o
m
e
s
≥
1
,
w
it
h
th
e
r
estrictio
n
th
at
as
L
€
f
o
r
n
o
r
u
le
E
/
a
c
a;
d
o
f
t
y
p
e
(
1
)
f
r
o
m
R
i
;
3
)
s
y
n
⊆
{
1
,
2
,
.
.
.
.
,
m
}
x
{
1
,
2
,
.
.
.
.
,
m
}w
i
th
(
i
,
i
)
s
y
n
,
f
o
r
1
≤
i
≤
m
(
s
y
n
ap
s
es);
4)
o
u
t
{
1
,
2
,
.
.
.
.
,
m
}
in
d
ic
ates th
e
o
u
tp
u
t
n
eu
r
o
n
T
h
e
r
u
les
o
f
t
y
p
e
(
1
)
a
r
e
ca
ll
ed
s
p
ikin
g
r
u
les
,
w
h
ich
i
s
w
r
i
tten
in
a
s
h
o
r
th
a
n
d
n
o
tatio
n
a
s
a
c
→
a
b
.
T
h
e
r
u
les
o
f
t
y
p
e
(
2
)
ar
e
ca
l
le
d
fo
r
g
ettin
g
r
u
les
.
T
h
e
ap
p
lic
atio
n
o
f
t
h
e
r
u
les
d
ep
en
d
s
o
n
th
e
co
n
ten
ts
o
f
th
e
n
eu
r
o
n
.
T
h
is
i
m
p
l
ies
th
at
t
h
e
ap
p
li
ca
b
ilit
y
o
f
a
r
u
le
is
estab
lis
h
ed
b
ased
o
n
th
e
to
tal
n
u
m
b
er
o
f
s
p
i
k
es
co
n
tain
ed
i
n
t
h
e
n
e
u
r
o
n
.
I
f
n
o
f
ir
i
n
g
r
u
le
ca
n
b
e
ap
p
lied
in
a
n
eu
r
o
n
,
th
er
e
m
a
y
b
e
t
h
e
p
o
s
s
ib
ilit
y
to
ap
p
l
y
a
f
o
r
g
etti
n
g
r
u
le,
w
h
ich
r
e
m
o
v
e
s
f
r
o
m
t
h
e
n
e
u
r
o
n
a
p
r
ed
ef
in
e
d
n
u
m
b
er
o
f
s
p
ik
e
s.
4
.
2
.
T
ra
pezo
ida
l F
uzzy
Rea
s
o
nin
g
Sp
i
k
ing
Neura
l P
Sy
s
t
e
m
No
r
m
a
ll
y
,
w
h
e
n
th
e
a
n
tece
d
e
n
t
(
co
n
d
itio
n
)
p
ar
t
o
f
a
r
u
le
i
s
s
atis
f
ied
,
t
h
e
r
ig
h
t
h
a
n
d
s
id
e
w
h
ic
h
is
ca
lled
th
e
co
n
s
eq
u
e
n
t
is
tr
ig
g
e
r
ed
/activ
ated
.
Fu
zz
y
R
ea
s
o
n
i
n
g
th
er
e
f
o
r
e,
is
th
e
p
r
o
ce
s
s
o
f
f
ir
in
g
an
d
ex
ec
u
tio
n
o
f
th
e
f
u
zz
y
r
u
le.
A
t
F
R
S
N
P
s
y
s
te
m
o
f
d
e
g
r
ee
m
≥
1
[
2
3
]
,
is
a
co
n
s
tr
u
ct
o
f
t
h
e
f
o
r
m
∏
=
(
O
, σ
1
,
.
.
.
,
σ
m
, s
yn
,
in
o
u
t
)
w
h
er
e:
1)
O
= {
a
}is th
e
s
i
n
g
leto
n
alp
h
ab
et
(
a
is
ca
lled
s
p
ik
e)
;
2)
σ
1
,
.
.
.
,
σ
m
ar
e
n
eu
r
o
n
s
o
f
th
e
s
a
m
e
f
o
r
m
σ
i
=
(
θ
,
c
i
,
r
i
)
,
1
≤
i
≤
,
m,
w
h
er
e:
a)
θ
i
is
t
h
e
p
o
ten
tia
l
v
a
lu
e
o
f
s
p
ik
es
(
i.e
.
p
u
ls
e
v
al
u
e)
co
n
t
ain
ed
i
n
n
eu
r
o
n
σ
i
,
an
d
it
i
s
ex
p
r
ess
ed
b
y
a
tr
ap
ez
o
id
al
f
u
z
z
y
n
u
m
b
er
i
n
[
0
,
1
]
;
b)
c
i
ca
n
b
e
u
n
d
er
s
to
o
d
as e
i
th
er
th
e
f
u
zz
y
tr
u
t
h
v
alu
e
o
f
a
p
r
o
p
o
s
itio
n
(
w
h
en
σ
i
co
r
r
e
s
p
o
n
d
s
t
o
a
p
r
o
p
o
s
itio
n
n
e
u
r
o
n
)
o
r
th
e
c
er
tain
t
y
f
ac
to
r
o
f
a
p
r
o
d
u
ctio
n
r
u
le
(
w
h
e
n
σ
i
co
r
r
esp
o
n
d
s
to
a
r
u
le
n
e
u
r
o
n
)
,
an
d
it is
e
x
p
r
ess
e
d
b
y
a
tr
ap
ez
o
id
al
f
u
zz
y
n
u
m
b
er
in
[
0
,
1
]
;
c)
r
i
r
ep
r
esen
ts
a
f
ir
in
g
(
s
p
ik
in
g
)
r
u
le
co
n
tai
n
ed
in
n
eu
r
o
n
σ
i
w
it
h
th
e
f
o
r
m
E
/
a
θ
→
a
β
,
w
h
er
e
E
(
E
=
a
n
)
is
th
e
f
ir
in
g
co
n
d
it
io
n
,
an
d
n
is
th
e
n
u
m
b
er
o
f
p
r
es
y
n
ap
tic
n
e
u
r
o
n
s
co
n
n
ec
ted
to
n
eu
r
o
n
σ
i
w
h
ic
h
is
ex
p
r
es
s
ed
b
y
an
i
n
teg
er
,
θ
an
d
β
ar
e
ex
p
r
ess
ed
b
y
tr
ap
ez
o
id
al
f
u
zz
y
n
u
m
b
er
s
i
n
[
0
,
1
]
.
3)
s
y
n
⊆
{
1
,
2
,
.
.
.
,
m
}×
{1
,
2
,
.
.
.
,
m
}
,
w
it
h
i
≠
j
f
o
r
all
(
i
,
j
)
s
yn
,
1
≤
i
,
j
≤
m
,
is
a
d
ir
ec
te
d
g
r
ap
h
o
f
s
y
n
ap
s
es b
et
w
ee
n
th
e
l
in
k
ed
n
eu
r
o
n
s
;
4)
in
,
o
u
t
in
d
icate
th
e
in
p
u
t
n
e
u
r
o
n
s
et
a
n
d
th
e
o
u
tp
u
t n
e
u
r
o
n
s
et
o
f
∏
,
r
esp
ec
tiv
el
y
.
Su
f
f
ice
to
n
o
te
t
h
at
w
h
e
n
tF
R
SN
P
s
y
s
te
m
is
i
m
p
le
m
ete
n
d
in
a
m
atr
ix
r
ea
s
o
n
i
n
g
f
o
r
m
at
a
s
it
r
elate
s
to
th
e
co
m
p
o
s
ite
co
n
j
u
n
ct
iv
e
f
u
zz
y
p
r
o
d
u
ctio
n
r
u
le
b
ei
n
g
ap
p
lied
h
er
e,
ar
ith
m
etic
m
u
ltip
li
ca
tio
n
x
o
p
er
ato
r
,
m
atr
ices
θ
*
an
d
δ
*
n
ee
d
to
b
e
d
ef
in
ed
th
u
s
;
Def
i
n
itio
n
4
.
2
.
1
: G
iv
en
tr
ap
ez
o
id
al
n
u
m
b
er
s
P
=
(
p
1
, p
2
,
p
3
, p
4
)
an
d
Q
=
(
q
1
, q
2
, q
3
,
q
4
)
,
P
x
Q
=
(
p
1
, p
2
,
p
3
, p
4
)
x
(
q
1
, q
2
,
q
3
, q
4
)
=
(
p
1
x
q
1
,
p
2
x
q
2
, p
3
x
q
3
, p
4
x
q
4
)
Def
i
n
itio
n
4
.
2
.
2
:
θ
*
is
an
n
x1
m
atr
ix
co
n
tai
n
i
n
g
th
e
tr
u
t
h
v
al
u
es
o
f
t
h
e
p
r
o
p
o
s
itio
n
n
e
u
r
o
n
s
e
x
p
r
ess
ed
b
y
tr
ap
ez
o
id
al
f
u
zz
y
n
u
m
b
er
in
[
0
,
1
]
.
Def
i
n
itio
n
4
.
2
.
3
:
δ
*
is
a
mx1
m
atr
i
x
co
n
tai
n
i
n
g
t
h
e
tr
u
th
v
al
u
es
o
f
th
e
r
u
le
n
e
u
r
o
n
s
ex
p
r
e
s
s
ed
b
y
tr
ap
ez
o
id
al
f
u
zz
y
n
u
m
b
er
in
[
0
,
1
]
5
.
T
H
E
P
RO
P
O
SE
D
t
F
RSN
P
–
NIDS
F
RAM
E
WO
RK
T
h
is
s
ec
tio
n
d
is
c
u
s
s
es t
h
e
ar
ch
itectu
r
e
o
f
t
h
e
p
r
o
p
o
s
ed
f
r
am
e
w
o
r
k
f
o
r
tFR
SN P
-
NI
DS.
T
h
e
f
r
a
m
e
w
o
r
k
u
s
es
f
u
zz
y
r
u
le
-
b
ased
s
y
s
te
m
to
d
etec
t
in
tr
u
s
i
v
e
tr
a
f
f
ics
a
n
d
to
s
e
n
d
s
i
g
n
al
to
o
r
aler
t
t
h
e
S
y
s
te
m
A
d
m
i
n
is
tr
ato
r
(
SA
)
ab
o
u
t th
e
s
e
attac
k
s
.
I
n
th
e
f
r
a
m
e
w
o
r
k
(
f
i
g
.
3
)
b
elo
w
,
t
h
e
t
FR
SN
P
ac
ts
a
s
th
e
co
o
r
d
in
ati
n
g
p
o
in
t
o
f
t
h
e
f
u
zz
i
f
i
ed
n
et
w
o
r
k
tr
af
f
ic
an
d
t
h
e
w
ell
-
d
ef
i
n
ed
r
u
les
co
m
in
g
f
r
o
m
t
h
e
r
u
le
b
ase.
I
n
f
ac
t,
i
t
is
co
n
s
id
er
ed
as
th
e
e
n
g
in
e
r
o
o
m
b
ec
au
s
e
it
i
s
w
h
er
e
d
ec
is
io
n
s
ar
e
tak
en
.
Af
ter
p
er
f
o
r
m
i
n
g
f
u
zz
y
r
ea
s
o
n
in
g
o
n
it,
tF
R
SN
P
s
y
s
te
m
r
elea
s
e
s
d
ef
u
zz
i
f
ied
i
n
f
o
r
m
atio
n
(
th
at
is
,
th
e
d
etec
tio
n
r
e
s
u
l
ts
)
to
t
h
e
o
u
ts
id
e
w
o
r
ld
t
h
r
o
u
g
h
t
h
e
u
s
er
i
n
ter
f
ac
e.
T
h
e
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
I
C
T
I
SS
N:
2252
-
8776
A
tta
ck
Dete
ctio
n
in
a
R
u
le
-
B
a
s
ed
S
ystem
u
s
i
n
g
…
(
R
u
fa
i,
K
.
I
et
a
l.
)
17
m
e
m
b
er
s
h
ip
f
u
n
ctio
n
i
s
d
ef
i
n
ed
b
ased
o
n
f
u
zz
y
lo
g
ic
o
f
tr
ap
ez
o
id
al
lin
g
u
i
s
tic
ter
m
s
w
h
ich
f
al
ls
w
it
h
i
n
th
e
tr
ap
ez
o
id
al
n
u
m
b
er
[
0
,
1
]
.
Fig
u
r
e
3
.
tFR
SN P
-
I
DS
Fra
m
e
w
o
r
k
6.
I
M
P
L
E
M
E
NT
I
N
G
t
F
RSN
P
I
N
AT
T
ACK
DE
T
E
CT
I
O
N
T
h
e
k
n
o
w
led
g
e
b
ase
s
h
o
w
n
a
b
o
v
e
ca
n
b
e
m
o
d
eled
u
s
i
n
g
t
F
R
SN
P
s
y
s
te
m
a
s
ca
p
tu
r
ed
i
n
t
h
e
Fi
g
u
r
e
4
b
elo
w
.
T
h
e
m
o
d
el
co
n
tai
n
s
1
2
p
r
o
p
o
s
itio
n
n
e
u
r
o
n
s
a
n
d
5
r
u
le
n
e
u
r
o
n
s
.
I
n
t
h
e
m
o
d
el,
th
e
in
itia
l
tr
ap
ez
o
id
al
lin
g
u
i
s
tic
tr
u
t
h
v
al
u
es
o
f
i
n
p
u
t
s
n
e
u
r
o
n
s
σ
1
,
σ
2
,
σ
3
,
σ
4
,
σ
5
,
σ
6
an
d
σ
7
ar
e
―
VG
‖,
―
T
‖,
―
M
‖,
―
VT
‖
,
―
VS‖,
―
M‖
an
d
―
VE
‖
r
esp
ec
ti
v
el
y
.
I
n
s
u
m
m
ar
y
t
h
er
e
f
o
r
e,
th
e
f
u
z
z
y
p
r
o
d
u
ctio
n
r
u
les ar
e
d
ef
i
n
e
d
as a
co
n
s
tr
u
ct:
∏
=
(
O
, σ
1
,
.
.
.
,
σ
12
, σ
13
,
.
.
.
,
σ
17
, s
yn
,
in
,
o
u
t
)
W
h
er
e
(
1
)
O
=
{
a}
(
2
)
σ
1
, . . .,
σ
12
a
r
e
p
r
o
p
o
s
itio
n
n
eu
r
o
n
s
h
av
in
g
f
u
zz
y
tr
u
t
h
v
a
lu
es p
1
, . . .,
p
12
r
esp
ec
tiv
el
y
.
(
3
)
σ
13,
.
.
.
,
σ
17
ar
e
―
AND‖
–
ty
p
e
r
u
le
n
e
u
r
o
n
s
as
s
o
ciate
d
w
it
h
p
r
o
d
u
ctio
n
r
u
le
s
R
1
,
.
.
.
.
,
R
5
r
esp
ec
tiv
el
y
.
(
4
)
s
y
n
=
{(
1
,
1
3
)
,
(
2
,
1
4
)
,
(
2
,
1
6
)
,
(
3
,
1
5
)
,
(
4
,
1
7
)
,
(
5
,
1
3
)
,
(
5
,
1
4
)
,
(
6
,
1
5
)
,
(
7
,
1
6
)
,
(
7
,
1
7
)
,
(
1
3
,
8
)
,
(
1
4
,
9
)
,
(
1
5
,
1
0
)
,
(
1
6
,
1
1
)
,
(
1
7
,
1
2
)
}
(
5
)
in
=
{
σ
1
, σ
2
, σ
3
, σ
4
,
σ
5
, σ
6
, σ
7
}
o
u
t
=
{
σ
8
, σ
9
,
σ
10
, σ
11
σ
1
2
}
Fig
u
r
e
4
.
tFR
SN P
s
y
s
te
m
M
o
d
el
f
o
r
B
FA
A
t t
h
e
i
n
itial i
n
s
tan
ce
,
i.e
w
h
e
n
t
= 0
,
θ
0
an
d
δ
0
w
h
ic
h
r
ep
r
esen
t t
h
e
i
n
itial
v
alu
e
s
o
f
p
r
o
p
o
s
itio
n
n
eu
r
o
n
s
an
d
r
u
le
n
e
u
r
o
n
s
r
esp
ec
tiv
el
y
,
ar
e
g
i
v
en
i
n
th
e
f
o
llo
w
i
n
g
m
atr
ice
s
:
0
.
9
7
5
,
0
.
9
8
,
1
,
1
0
.
0
4
,
0
.
1
,
0
.
1
8
,
0
.
2
3
0
.
3
2
,
0
.
4
1
,
0
.
5
8
,
0
.
6
5
θ
0
=
0
,
0
,
0
.
0
2
,
0
.
0
7
δ
0
=
[
0
]
5x1
0
,
0
,
0
.
0
2
,
0
.
0
7
0
.
3
2
,
0
.
4
1
,
0
.
5
8
,
0
.
6
5
0
.
9
7
5
,
0
.
9
8
,
1
,
1
0
12x1
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8776
IJ
-
I
C
T
Vo
l.
5
,
No
.
1
,
A
p
r
il
2
0
1
6
:
1
1
–
2
0
18
A
t
s
tep
t =
1
,
af
ter
p
er
f
o
r
m
in
g
th
e
o
p
er
atio
n
˄
w
i
th
i
n
t
h
e
f
i
v
e
r
u
le
n
eu
r
o
n
s
an
d
s
u
b
s
eq
u
e
n
tl
y
m
u
l
tip
l
y
i
n
g
x
w
it
h
t
h
eir
co
r
r
esp
o
n
d
in
g
ce
r
ta
in
t
y
f
ac
to
r
s
(
C
F),
w
e
o
b
tain
t
h
e
r
esu
lts
:
0
,
0
,
0
.
0
2
,
0
.
0
7
0
,
0
,
0
.
0
2
,
0
.
0
7
δ
1
=
0
.
3
2
,
0
.
4
1
,
0
.
5
8
,
0
.
6
5
0
.
0
4
,
0
.
1
,
0
.
1
8
,
0
.
2
3
0
,
0
,
0
.
0
2
,
0
.
0
7
5x1
0
0
,
0
,
0
.
0
2
,
0
.
0
7
0
,
0
,
0
.
0
1
8
4
,
0
.
0
6
7
9
θ
1
=
0
.
2
3
0
4
,
0
.
3
1
9
8
,
0
.
5
3
3
6
,
0
.
6
3
0
5
0
.
0
2
8
8
,
0
.
0
7
8
,
0
.
1
6
5
6
,
0
.
2
2
3
1
0
,
0
,
0
.
0
1
8
4
,
0
.
0
6
7
9
12x1
A
t s
tep
t =
2
,
th
e
r
ea
s
o
n
in
g
p
r
o
ce
s
s
en
d
s
h
en
ce
w
e
o
b
tain
t
h
e
r
esu
lts
:
δ
2
=
[
0
]
5x1
7.
RE
SU
L
T
AND
DI
SCUS
SI
O
N
T
h
e
co
m
p
u
tatio
n
h
alt
s
s
in
ce
t
h
er
e
ar
e
f
iv
e
r
ea
s
o
n
in
g
r
es
u
lts
:
(
0
,
0
,
0
.
0
2
,
0
.
0
7
)
,
(
0
,
0
,
0
.
0
1
8
4
,
0
.
0
6
7
9
)
,
(
0
.
2
3
4
,
0
.
3
1
9
8
,
0
.
5
3
3
6
,
0
.
6
3
0
5
)
,
(
0
.
0
2
8
8
,
0
.
0
7
8
,
0
.
1
6
5
6
,
0
.
2
2
3
1
)
,
an
d
(
0
,
0
,
0
.
1
8
4
,
0
.
0
6
7
9
)
co
r
r
esp
o
n
d
in
g
to
th
e
f
i
v
e
o
u
t
p
u
t
n
eu
r
o
n
s
σ
8
,
σ
9
,
σ
10
,
σ
11
an
d
σ
12
.
A
ls
o
,
th
er
e
ar
e
n
o
f
u
r
t
h
er
r
u
les
to
b
e
ex
ec
u
ted
a
n
d
is
ca
lled
s
to
p
p
in
g
cr
iter
ia
(
i.e
δ
2
=
0
,
0
,
0
,
0
)
,
w
h
ic
h
i
s
an
ab
s
o
l
u
tel
y
f
a
ls
e
co
n
d
itio
n
[
2
4
]
.
T
h
ese
r
esu
lt
s
e
x
p
r
ess
t
h
e
c
o
n
f
id
e
n
ce
le
v
els
a
t
w
h
ich
B
r
u
te
Fo
r
ce
co
u
ld
o
cc
u
r
i
n
a
t
y
p
ical
n
et
w
o
r
k
en
v
ir
o
n
m
e
n
t.
T
h
er
ea
f
ter
,
th
e
ab
o
v
e
is
d
ef
u
zz
if
ied
.
Def
u
zz
i
f
icatio
n
is
a
p
r
o
ce
s
s
w
h
ich
co
n
v
er
ts
a
f
u
z
z
y
s
et
o
r
f
u
zz
y
n
u
m
b
er
i
n
to
a
cr
i
s
p
v
alu
e.
D
ef
u
zz
if
ica
tio
n
is
u
s
ed
in
f
u
zz
y
m
o
d
elin
g
s
i
m
p
l
y
f
o
r
t
h
e
p
u
r
p
o
s
e
o
f
co
n
v
e
r
tin
g
f
u
zz
y
o
u
tp
u
ts
f
r
o
m
t
h
e
s
y
s
te
m
s
t
o
cr
is
p
v
alu
e
s
(
w
h
ic
h
ar
e
q
u
an
ti
f
ied
b
y
r
ea
l
-
v
al
u
ed
f
u
n
ct
io
n
s
)
.
T
h
e
co
m
p
u
ted
d
ef
u
zz
i
f
ied
r
es
u
lts
t
h
e
n
h
elp
to
d
eter
m
i
n
e
th
e
s
ev
er
it
y
o
f
t
h
e
attac
k
.
(
3
)
As ad
ap
ted
f
r
o
m
[
2
4
]
,
e
an
d
f
ar
e
0
,
1
r
esp
ec
tiv
ely
b
ei
n
g
th
e
t
w
o
e
x
tr
e
m
e
v
al
u
es o
f
th
e
e
n
ti
r
e
f
u
z
z
y
s
et
r
a
n
g
e
.
A
l
s
o
,
(
as
s
h
o
w
n
in
f
i
g
.
1
ab
o
v
e)
w
h
ile
p
an
d
s
ar
e
th
e
le
f
t
an
d
r
ig
h
t
w
id
t
h
o
f
th
e
tr
ap
ez
o
id
al
r
an
g
e,
q
a
n
d
r
s
tan
d
f
o
r
th
e
in
ter
v
al
at
w
h
ic
h
th
e
m
e
m
b
er
s
h
ip
i
s
1
.
Hen
c
e,
w
e
o
b
tain
ed
0
.
0
4
3
1
(
4
.
3
1
%),
0
.
0
4
1
4
(
4
.
1
4
%),
0
.
4
4
5
3
(
4
4
.
5
3
%),
0
.
1
7
0
3
(
1
7
.
0
3
%)
an
d
0
.
0
4
1
4
(
4
.
1
4
%)
r
esp
ec
tiv
el.
T
h
er
ef
o
r
e,
s
in
ce
th
e
s
ev
er
it
y
o
f
n
o
n
e
o
f
t
h
ese
v
alu
e
s
is
u
p
to
0
.
5
(
5
0
%),
w
e
t
h
en
co
n
c
lu
d
e
th
at
B
F
A
d
o
es n
o
t p
o
r
ten
d
an
y
d
an
g
er
o
r
ap
p
ea
r
s
to
b
e
a
th
r
ea
t in
th
i
s
s
ce
n
ar
io
.
8.
CO
NCLU
SI
O
N
Fo
r
th
e
v
er
y
f
ir
s
t
ti
m
e,
Sp
ik
i
n
g
Neu
r
al
P
(
SN
P
)
s
y
s
te
m
i
n
co
n
j
u
n
ctio
n
w
it
h
tr
ap
ez
o
id
al
f
u
zz
y
lo
g
i
c
s
y
s
te
m
h
as
s
u
cc
e
s
s
f
u
ll
y
b
ee
n
ap
p
lied
to
a
r
u
le
-
b
ased
I
n
tr
u
s
i
o
n
Dete
ctio
n
s
y
s
te
m
.
I
t
w
a
s
ab
le
to
f
lag
t
h
e
lev
e
l
at
w
h
ic
h
th
e
s
ev
er
it
y
o
f
t
h
e
att
ac
k
co
u
ld
o
r
o
th
er
w
i
s
e
s
er
v
e
a
s
a
th
r
ea
t
to
th
e
i
n
f
o
r
m
atio
n
s
y
s
te
m
.
So
,
w
e
h
a
v
e
ap
p
lied
tFR
SN
P
s
y
s
te
m
to
attac
k
d
etec
tio
n
a
n
d
h
av
e
u
s
ed
it
to
m
o
d
el
th
e
k
n
o
w
led
g
e
b
ase
o
f
a
t
y
p
e
o
f
attac
k
ca
lle
d
B
FA
.
I
m
p
le
m
e
n
ti
n
g
t
h
i
s
d
etec
tio
n
i
n
a
m
atr
ix
f
o
r
m
at
b
y
in
co
r
p
o
r
atin
g
t
h
e
p
ar
allelis
m
ad
v
an
ta
g
e
o
f
SN
P
s
y
s
te
m
m
a
k
es
it
to
b
e
v
er
y
in
t
u
iti
v
e,
s
i
m
p
le
a
n
d
ab
o
v
e
al
l,
f
ast.
Fu
r
t
h
er
m
o
r
e,
s
in
ce
th
i
s
w
o
r
k
h
as
o
n
l
y
b
ee
n
i
m
p
le
m
en
ted
f
o
r
B
F
A
,
f
u
t
u
r
e
w
o
r
k
s
m
a
y
b
e
e
x
te
n
d
ed
to
in
c
l
u
d
e
th
e
ap
p
licatio
n
o
f
tFR
SN P
s
y
s
te
m
t
o
o
th
er
cl
ass
es o
f
attac
k
s
u
c
h
as De
n
ial
o
f
Ser
v
ice
(
Do
S)
.
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
I
C
T
I
SS
N:
2252
-
8776
A
tta
ck
Dete
ctio
n
in
a
R
u
le
-
B
a
s
ed
S
ystem
u
s
i
n
g
…
(
R
u
fa
i,
K
.
I
et
a
l.
)
19
RE
F
E
R
E
NC
E
S
[1
]
A
.
P
ӑ
u
n
,
G
h
.
P
ӑ
u
n
,
―
S
m
a
ll
Un
iv
e
rsa
l
S
p
ik
in
g
Ne
u
ra
l
P
S
y
ste
m
s‖
,
Jo
u
rn
a
l
o
f
Bio
sy
ste
m
s,
El
se
v
ier,
V
o
l
.
9
0
,
(
2
0
0
7
)
P
p
.
4
8
-
60.
[2
]
M
.
Io
n
e
sc
u
,
G
h
.
P
ă
u
n
,
T
.
Yo
k
o
m
o
ri
.
―
S
p
ik
in
g
Ne
u
ra
l
P
sy
ste
m
s‖
.
F
u
n
d
a
m
e
n
ta In
f
o
r
m
a
ti
c
a
e
7
1
(
2
–
3
):
p
p
.
2
7
9
–
3
0
8
,
2
0
0
6
.
[3
]
D.
Día
z
-
P
e
rn
il
,
P
.
F
r
a
n
c
isc
o
,
A
.
G
.
M
ig
u
e
.
―
A
P
a
ra
ll
e
l
a
lg
o
rit
h
m
f
o
r
sk
e
l
e
to
n
izin
g
im
a
g
e
s
b
y
u
sin
g
sp
ik
in
g
n
e
u
ra
l
P
sy
ste
m
s‖
.
Ne
u
ro
c
o
m
p
u
ti
n
g
Vo
l
.
1
1
5
(
2
0
1
3
)
P
p
.
8
1
–
91
[4
]
I.
T
se
re
n
-
On
o
lt
,
A
.
Lep
o
ra
ti
,
L
.
P
a
n
,
X
.
Zen
g
,
X.
Zh
a
n
g
.
De
term
in
isti
c
so
lu
ti
o
n
s
t
o
QSA
T
a
n
d
Q3
S
AT
b
y
S
p
ik
in
g
Ne
u
ra
l
P
sy
ste
m
s
w
it
h
P
re
-
c
o
m
p
u
ted
Re
so
u
rc
e
s.
T
h
e
o
re
ti
c
a
l
Co
m
p
u
ter S
c
ien
c
e
4
1
1
(
2
0
1
0
)
2
3
4
5
-
2
3
5
8
[5
]
K.
I.
Ru
f
a
i,
C.
M
.
Ra
v
ie
a
n
d
Z.
A
.
Oth
m
a
n
.
I
m
p
ro
v
in
g
Be
e
A
l
g
o
rit
h
m
Ba
s
e
d
F
e
a
tu
re
S
e
l
e
c
ti
o
n
in
In
tru
si
o
n
De
tec
ti
o
n
S
y
ste
m
Us
in
g
M
e
m
b
ra
n
e
Co
m
p
u
ti
n
g
J
o
u
r
n
a
l
o
f
N
e
tw
o
rk
s
,
V
o
l
9
,
No
3
(2
0
1
4
),
5
2
3
-
5
2
9
,
[6
]
H.
T
h
u
z
a
r:
―
F
e
a
tu
re
S
e
lec
ti
o
n
a
n
d
F
u
z
z
y
De
c
isio
n
T
re
e
f
o
r
Ne
tw
o
rk
In
tru
sio
n
De
tec
ti
o
n
‖
.
In
ter
n
a
ti
o
n
a
l
Jo
u
rn
a
l
o
f
In
f
o
rm
a
ti
c
s an
d
Co
m
m
u
n
ica
ti
o
n
T
e
c
h
n
o
lo
g
y
(IJ
-
IC
T
)
V
o
l.
1
,
No
.
2
,
De
c
e
m
b
e
r
2
0
1
2
,
p
p
.
1
0
9
~
1
1
8
[7
]
T
.
W
a
n
g
,
G
.
Zh
a
n
g
.
―
A
p
p
li
c
a
ti
o
n
o
f
F
u
z
z
y
Re
a
so
n
in
g
S
p
ik
in
g
Ne
u
ra
l
P
S
y
ste
m
to
F
a
u
lt
Dia
g
n
o
sis
‖
.
(2
0
1
3
).
A
sia
n
Co
n
f
e
re
n
c
e
o
n
M
e
m
b
ra
n
e
Co
m
p
u
ti
n
g
.
[8
]
M
.
S
.
A
b
a
d
e
h
,
H.
M
o
h
a
m
a
d
i
,
J
.
Ha
b
ib
i.
De
sig
n
a
n
d
A
n
a
l
y
sis
o
f
G
e
n
e
ti
c
F
u
z
z
y
S
y
ste
m
s
f
o
r
In
tru
sio
n
De
tec
ti
o
n
in
Co
m
p
u
ter Ne
tw
o
rk
s.
Ex
p
e
rt
S
y
ste
m
s
w
it
h
A
p
p
li
c
a
ti
o
n
s
3
8
(2
0
1
1
)
7
0
6
7
–
7
0
7
5
[9
]
H.
T
.
El
sh
o
u
sh
,
I.
M
.
Os
m
a
n
.
A
lert
Co
rre
latio
n
in
Co
l
lab
o
ra
ti
v
e
In
telli
g
e
n
t
In
tru
sio
n
De
tec
ti
o
n
S
y
st
e
m
s
—
A
S
u
rv
e
y
.
A
p
p
li
e
d
S
o
f
t
Co
m
p
u
ti
n
g
1
1
(
2
0
1
1
)
4
3
4
9
–
4
3
6
5
[1
0
]
A
.
N.
T
o
o
si,
M
.
Ka
h
a
n
i,
A
n
e
w
Ap
p
r
o
a
c
h
to
In
tru
si
o
n
De
tec
ti
o
n
B
a
se
d
o
n
a
n
Ev
o
lu
ti
o
n
a
ry
S
o
f
t
Co
m
p
u
ti
n
g
M
o
d
e
l
u
sin
g
Ne
u
ro
-
F
u
z
z
y
Clas
si
f
iers
,
C
o
m
p
u
ter Co
m
m
u
n
ica
ti
o
n
s
3
0
(
2
0
0
7
)
P
p
2
2
0
1
–
2
2
1
2
.
[1
1
]
R.
G
.
Ba
c
e
,
In
tru
sio
n
De
tec
ti
o
n
:
De
f
in
in
g
In
tru
sio
n
De
tec
ti
o
n
.
M
a
c
m
il
lan
T
e
c
h
n
ica
l
P
u
b
li
s
h
in
g
,
2
0
0
0
[1
2
]
A
.
Ei
n
ip
o
u
r.
In
telli
g
e
n
t
In
tr
u
sio
n
De
tec
ti
o
n
i
n
Co
m
p
u
ter
Ne
two
rk
s
Us
in
g
F
u
z
z
y
S
y
ste
m
s.
G
lo
b
a
l
Jo
u
r
n
a
l
o
f
Co
m
p
u
ter S
c
ien
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
N
e
u
ra
l
&
A
rti
f
icia
l
In
telli
g
e
n
c
e
V
o
l
u
m
e
1
2
Iss
u
e
1
1
V
e
rsio
n
1
.
0
(
2
0
1
2
)
[1
3
]
H.
De
b
a
r,
M
.
Da
c
ier
a
n
d
A
.
W
e
s
p
i,
―
T
o
w
a
rd
s
a
T
a
x
o
n
o
m
y
o
f
In
tru
sio
n
-
De
tec
ti
o
n
S
y
ste
m
s
‖
Co
m
p
u
ter
Ne
tw
o
rk
s,
3
1
(
8
),
p
p
.
8
0
5
–
8
2
2
,
1
9
9
9
.
[1
4
]
M
.
Um
a
,
G
.
P
a
d
m
a
v
a
th
i.
―
A
S
u
rv
e
y
o
n
V
a
rio
u
s
Cy
b
e
r
A
tt
a
c
k
s
a
n
d
th
e
ir
Clas
sif
ica
ti
o
n
‖
In
tern
a
ti
o
n
a
l
Jo
u
r
n
a
l
o
f
Ne
tw
o
rk
S
e
c
u
rit
y
,
V
o
l.
1
5
,
No
.
6
,
P
P
.
3
9
1
-
3
9
7
,
N
o
v
.
2
0
1
3
3
9
1
[1
5
]
B.
S
h
a
n
m
u
g
a
m
N.
B.
Id
ris.
Im
p
r
o
v
e
d
In
tr
u
sio
n
De
tec
ti
o
n
S
y
ste
m
Us
in
g
F
u
z
z
y
L
o
g
ic
f
o
r
De
tec
ti
n
g
A
n
a
m
o
l
y
a
n
d
M
isu
se
ty
p
e
o
f
A
tt
a
c
k
s.
In
tern
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
o
f
S
o
f
t
Co
m
p
u
ti
n
g
a
n
d
P
a
tt
e
rn
Re
c
o
g
n
it
io
n
(
2
0
0
9
)
[1
6
]
O.
Co
rd
o
n
,
F
.
G
o
m
id
e
,
F
.
He
rre
ra
,
F
.
Ho
ffm
a
n
n
,
L
.
M
a
g
d
a
len
a
.
―
Te
n
y
e
a
r
s
o
f
g
e
n
e
ti
c
f
u
z
z
y
s
y
ste
m
s:
Cu
rre
n
t
F
ra
m
e
w
o
rk
a
n
d
Ne
w
T
re
n
d
s‖
,
F
u
z
z
y
S
e
ts
a
n
d
S
y
ste
m
s,
v
o
l.
1
4
1
,
n
o
.
1
,
(
2
0
0
4
)
p
p
.
5
–
31.
[1
7
]
M
.
S
a
n
iee
A
b
a
d
e
h
,
J.
Ha
b
i
b
a
n
d
C.
L
u
c
a
s.
―
In
tru
sio
n
d
e
tec
ti
o
n
u
s
in
g
a
f
u
z
z
y
g
e
n
e
ti
c
s
-
b
a
se
d
lea
rn
i
n
g
a
lg
o
rit
h
m
‖
,
Jo
u
rn
a
l
o
f
Ne
tw
o
rk
a
n
d
Co
m
p
u
ter A
p
p
li
c
a
ti
o
n
s,
v
o
l.
3
0
,
n
o
.
1
,
,
(2
0
0
7
)
p
p
.
4
1
4
–
4
2
8
[1
8
]
W
.
H.
Ch
e
n
.
F
a
u
lt
S
e
c
ti
o
n
Esti
m
a
ti
o
n
Us
in
g
M
a
tri
x
-
b
a
se
d
Re
a
so
n
in
g
M
e
t
h
o
d
s.
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
P
o
w
e
r
De
li
v
e
r
y
,
2
6
(1
),
(
2
0
1
1
),
2
0
5
-
213
[1
9
]
H.
P
e
n
g
,
J.
W
a
n
g
,
M
.
J.
P
e
re
z
-
Jim
e
n
e
z
,
H.
Wan
g
,
J.
S
h
a
o
,
T
.
W
a
n
g
.
―
F
u
z
z
y
R
e
a
so
n
in
g
S
p
ik
in
g
Ne
u
ra
l
P
S
y
ste
m
f
o
r
F
a
u
lt
Dia
g
n
o
sis‖
.
I
n
f
o
rm
a
ti
o
n
S
c
ien
c
e
s,
2
3
5
(
2
0
1
3
)
1
0
6
[2
0
]
S
.
S
a
n
g
e
e
th
a
,
S
.
Ha
rip
riy
a
,
S
.
G
.
M
o
h
a
n
a
P
riy
a
,
V
.
V
a
i
d
e
h
i,
.
N.
S
rin
iv
a
sa
n
.
F
u
z
z
y
Ru
le
-
Ba
se
B
a
se
d
In
tru
si
o
n
De
tec
ti
o
n
S
y
ste
m
o
n
A
p
p
li
c
a
ti
o
n
L
a
y
e
r
C
NSA
2
0
1
0
,
CCIS
8
9
,
(2
0
1
0
)
p
p
.
2
7
–
3
6
.
[2
1
]
K.
I.
Ru
f
a
i,
C.
M
.
Ra
v
ie
a
n
d
Z
.
A
.
Oth
m
a
n
.
T
h
e
P
ro
sp
e
c
ts
o
f
Us
in
g
S
p
ik
in
g
Ne
u
ra
l
P
S
y
ste
m
f
o
r
In
tru
si
o
n
De
tec
ti
o
n
:
In
tern
a
ti
o
n
a
l
Jo
u
rn
a
l
o
f
In
f
o
r
m
a
ti
o
n
&
N
e
t
w
o
rk
S
e
c
u
r
it
y
(IJIN
S
)
V
o
l.
2
,
No
.
6
(2
0
1
3
),
p
p
.
4
9
2
~
4
9
8
,
IS
S
N:
2
0
8
9
-
3
2
9
9
[2
2
]
P
.
M
.
V
e
n
k
a
ta,
e
t
a
l.
,
―
P
ro
t
o
c
o
l
M
o
d
e
li
n
g
in
S
p
ik
i
n
g
Ne
u
ra
l
P
s
y
ste
m
s
a
n
d
P
e
tri
n
e
ts‖
In
tern
a
ti
o
n
a
l
Jo
u
r
n
a
l
o
f
Co
m
p
u
ter A
p
p
li
c
a
ti
o
n
s.
Vo
lu
m
e
1
–
N
o
.
2
4
,
2
0
1
0
[2
3
]
T
a
o
W
a
n
g
,
J.
W
a
n
g
,
H.
P
e
n
g
,
H.
W
a
n
g
.
Kn
o
w
led
g
e
Re
p
re
se
n
tatio
n
a
n
d
Re
a
so
n
i
n
g
Ba
s
e
d
o
n
F
RS
N
P
S
y
ste
m
(
P
r
o
c
e
e
d
in
g
s
o
f
th
e
8
th
W
o
rld
Co
n
g
re
ss
o
n
In
telli
g
e
n
t
Co
n
tr
o
l
a
n
d
A
u
to
m
a
ti
o
n
Ju
n
e
2
1
-
2
5
(
2
0
1
1
),
T
a
ip
e
i,
T
a
iwa
n
)
978
-
1
-
6
1
2
8
4
-
7
0
0
-
9
/1
1
/$
2
6
.
0
0
©
2
0
1
1
IE
EE
[2
4
]
G
.
X
io
n
g
,
D.
S
h
i,
L
.
Zh
u
,
X.
Du
a
n
.
A
Ne
w
A
p
p
ro
a
c
h
to
F
a
u
lt
Dia
g
n
o
sis o
f
P
o
w
e
r
S
y
ste
m
s Us
in
g
F
u
z
z
y
Re
a
so
n
in
g
S
p
ik
in
g
Ne
u
ra
l
P
S
y
ste
m
s.
M
a
th
e
m
a
ti
c
a
l
P
ro
b
lem
s in
E
n
g
in
e
e
rin
g
Vo
lu
m
e
2
0
1
3
(
2
0
1
3
)
,
h
tt
p
:
//
d
x
.
d
o
i.
o
rg
/1
0
.
1
1
5
5
/
2
0
1
3
/
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8776
IJ
-
I
C
T
Vo
l.
5
,
No
.
1
,
A
p
r
il
2
0
1
6
:
1
1
–
2
0
20
B
I
B
L
I
O
G
R
AP
H
Y
O
F
AUT
H
O
RS
Ru
fa
i
I.
K
a
z
e
e
m
is
a
Nig
e
rian
a
c
a
d
e
m
ics
w
h
o
is
c
u
rre
n
tl
y
p
u
rsu
in
g
a
P
h
D
d
e
g
re
e
a
t
th
e
Na
ti
o
n
a
l
Un
iv
e
rsity
o
f
M
a
la
y
sia
.
His
re
se
a
rc
h
in
tere
st
is
in
o
p
ti
m
izin
g
In
tru
sio
n
De
tec
ti
o
n
S
y
st
e
m
u
sin
g
M
e
m
b
ra
n
e
Co
m
p
u
ti
n
g
p
a
ra
d
ig
m
.
Ru
f
a
i
h
a
s b
e
e
n
in
v
o
lv
e
d
i
n
tea
c
h
i
n
g
a
n
d
re
se
a
rc
h
f
o
r
o
v
e
r
a
d
e
c
a
d
e
.
He
is
a
m
e
m
b
e
r
o
f
th
e
Co
m
p
u
ter
P
ro
f
e
ss
io
n
a
l
Re
g
istratio
n
C
o
u
n
c
il
o
f
Nig
e
ria(CP
RN)
w
h
ich
is
th
e
h
ig
h
e
st r
e
g
u
lato
ry
b
o
d
y
in
ICT
in
Nig
e
ria.
Ch
a
n
d
r
e
n
M
.
Ra
v
ie
(P
h
D)
is
a
se
n
io
r
re
se
a
r
c
h
f
e
ll
o
w
o
f
th
e
F
a
c
u
lt
y
o
f
Tec
h
n
o
lo
g
y
a
n
d
In
f
o
rm
a
ti
o
n
S
c
ien
c
e
.
He
is
p
re
se
n
tl
y
w
o
rk
in
g
o
n
In
f
o
r
m
a
ti
o
n
Re
tri
e
v
a
l,
P
ro
g
ra
m
m
in
g
a
n
d
M
e
m
b
ra
n
e
Co
m
p
u
ti
n
g
.
He
h
a
s p
u
b
li
sh
e
d
se
v
e
ra
l
a
rti
c
les
i
n
in
tern
a
ti
o
n
a
l
j
o
u
r
n
a
ls
a
n
d
p
re
se
n
ted
p
a
p
e
rs b
o
th
a
t
n
a
ti
o
n
a
l
a
n
d
i
n
tern
a
ti
o
n
a
l
c
o
n
f
e
re
n
c
e
s.
Zu
la
i
h
a
Ali
O
t
h
m
a
n
(P
h
D)
is
a
n
A
ss
o
c
iate
P
ro
f
e
ss
o
r.
S
h
e
b
a
g
g
e
d
h
e
r
M
a
ste
r
a
n
d
P
h
D
d
e
g
re
e
s
f
ro
m
th
e
p
re
stig
io
u
s Un
iv
e
rsit
y
o
f
S
h
e
f
f
ield
,
Un
it
e
d
Kin
g
d
o
m
.
S
h
e
sp
e
c
ialize
s in
Da
ta M
i
n
in
g
a
n
d
Op
ti
m
iza
ti
o
n
.
Zu
lai
h
a
is
a
p
r
o
li
f
ic
w
rit
e
r
o
f
re
p
u
te
Evaluation Warning : The document was created with Spire.PDF for Python.