Co
m
pu
t
er
Science
a
nd
I
nfo
r
m
a
t
io
n T
ec
hn
o
lo
g
ies
Vo
l.
6
,
No
.
1
,
Ma
r
c
h
2
0
2
5
,
p
p
.
80
~
90
I
SS
N:
2722
-
3
2
2
1
,
DOI
:
1
0
.
1
1
5
9
1
/csi
t
.
v6
i
1
.
pp
80
-
90
80
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
p
r
ime.
co
m/in
d
ex
.
p
h
p
/csi
t
M
a
chine
lea
rning
mo
del appro
a
ch
in cyber a
t
tack t
h
reat
detec
tion in se
cur
ity o
pera
tion cen
t
er
M
uh
a
m
m
a
d Aj
ra
n Sa
pu
t
ra
1
,
Der
is
Stia
wa
n
1
,
Ra
hm
a
t
B
ud
ia
rt
o
2
1
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
En
g
i
n
e
e
r
i
n
g
,
F
a
c
u
l
t
y
o
f
C
o
mp
u
t
e
r
S
c
i
e
n
c
e
,
U
n
i
v
e
r
si
t
y
o
f
S
r
i
w
i
j
a
y
a
,
I
n
d
r
a
l
a
y
a
,
I
n
d
o
n
e
s
i
a
2
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
,
C
o
l
l
e
g
e
o
f
C
o
mp
u
t
i
n
g
a
n
d
I
n
f
o
r
mat
i
o
n
,
A
l
-
B
a
h
a
U
n
i
v
e
r
si
t
y
,
A
l
a
q
i
q
,
S
a
u
d
i
A
r
a
b
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Oct
9
,
2
0
2
4
R
ev
is
ed
Feb
7
,
2
0
2
5
Acc
ep
ted
Feb
18
,
2
0
2
5
Th
e
e
v
o
lu
ti
o
n
o
f
tec
h
n
o
lo
g
y
r
o
l
e
s
a
tt
ra
c
ted
c
y
b
e
r
se
c
u
rit
y
t
h
re
a
ts
n
o
t
o
n
l
y
c
o
m
p
ro
m
ise
sta
b
le
tec
h
n
o
l
o
g
y
b
u
t
a
lso
c
a
u
se
sig
n
if
ica
n
t
fin
a
n
c
i
a
l
lo
ss
fo
r
o
rg
a
n
iza
ti
o
n
s
a
n
d
i
n
d
iv
i
d
u
a
ls.
As
a
re
su
lt
,
o
rg
a
n
iza
ti
o
n
s
m
u
st
c
re
a
te
a
n
d
imp
lem
e
n
t
a
c
o
m
p
re
h
e
n
siv
e
c
y
b
e
r
se
c
u
rit
y
stra
teg
y
t
o
m
in
imiz
e
fu
r
th
e
r
lo
ss
.
Th
e
fo
u
n
d
in
g
o
f
a
c
y
b
e
rse
c
u
rit
y
su
rv
e
il
lan
c
e
c
e
n
ter
is
o
n
e
o
f
th
e
o
p
ti
m
a
l
a
d
o
p
te
d
stra
teg
ies
,
k
n
o
w
n
a
s
se
c
u
rit
y
o
p
e
ra
ti
o
n
c
e
n
ter
(S
OC).
T
h
e
stra
teg
y
h
a
s
b
e
c
o
m
e
th
e
fo
re
fro
n
t
o
f
d
i
g
it
a
l
sy
ste
m
s
p
ro
tec
ti
o
n
.
We
p
ro
p
o
s
e
stra
teg
y
o
p
ti
m
iza
ti
o
n
to
p
re
v
e
n
t
o
r
m
it
i
g
a
te
c
y
b
e
ra
tt
a
c
k
s
b
y
a
n
a
ly
z
i
n
g
a
n
d
d
e
tec
ti
n
g
lo
g
a
n
o
m
a
li
e
s
u
sin
g
m
a
c
h
in
e
l
e
a
rn
in
g
m
o
d
e
ls.
Th
is
stu
d
y
e
m
p
lo
y
s
two
m
a
c
h
in
e
lea
rn
in
g
m
o
d
e
ls:
th
e
n
a
ï
v
e
Ba
y
e
s
m
o
d
e
l
wi
th
m
u
lt
in
o
m
ial
,
G
a
u
ss
ian
,
a
n
d
Be
rn
o
u
ll
i
v
a
rian
ts
,
a
n
d
th
e
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
(S
VM)
m
o
d
e
l
with
ra
d
ial
b
a
sis
f
u
n
c
ti
o
n
(RBF
),
l
in
e
a
r,
p
o
l
y
n
o
m
ial,
a
n
d
sig
m
o
i
d
k
e
rn
e
l
v
a
rian
ts.
T
h
e
h
y
p
e
rp
a
ra
m
e
ters
in
b
o
t
h
m
o
d
e
ls are
th
e
n
o
p
ti
m
ize
d
.
Th
e
m
o
d
e
ls
with
o
p
ti
m
ize
d
h
y
p
e
rp
a
ra
m
e
ters
a
re
su
b
se
q
u
e
n
tl
y
trai
n
e
d
a
n
d
tes
t
e
d
.
Th
e
e
x
p
e
rime
n
tal
re
su
lt
s
in
d
ica
te
th
a
t
th
e
b
e
st
p
e
rfo
rm
a
n
c
e
is
a
c
h
iev
e
d
b
y
th
e
RBF
k
e
r
n
e
l
S
VM
m
o
d
e
l,
with
a
n
a
c
c
u
ra
c
y
o
f
7
9
.
7
5
%
,
p
re
c
isio
n
o
f
8
0
.
8
%
,
re
c
a
ll
o
f
7
9
.
7
5
%
,
a
n
d
F
1
-
sc
o
re
o
f
8
0
.
0
1
%
;
a
n
d
t
h
e
G
a
u
ss
ian
n
a
ï
v
e
Ba
y
e
s
m
o
d
e
l,
with
a
n
a
c
c
u
ra
c
y
o
f
7
0
.
0
%
,
p
re
c
isio
n
o
f
8
0
.
2
7
%
,
re
c
a
ll
o
f
7
0
.
0
%
,
a
n
d
F
1
-
sc
o
re
o
f
7
0
.
6
6
%
.
Ov
e
ra
ll
,
b
o
th
m
o
d
e
ls
p
e
rfo
rm
re
lativ
e
ly
we
ll
a
n
d
a
re
c
las
sified
in
th
e
v
e
ry
g
o
o
d
c
a
teg
o
ry
(7
5
%
‒
8
9
%
)
.
K
ey
w
o
r
d
s
:
C
y
b
er
attac
k
Dete
ctio
n
Hy
p
er
p
ar
a
m
eter
Naïv
e
B
ay
es
Su
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
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
:
Der
is
Sti
awa
n
Dep
ar
tm
en
t o
f
C
o
m
p
u
ter
E
n
g
i
n
ee
r
in
g
,
Facu
lty
o
f
C
o
m
p
u
ter
Scien
ce
,
Un
iv
er
s
ity
o
f
Sriwija
y
a
Og
an
I
lir
-
3
0
6
6
2
,
I
n
d
r
alay
a
,
I
n
d
o
n
esia
E
m
ail: d
er
is
@
u
n
s
r
i.a
c.
id
1.
I
NT
RO
D
UCT
I
O
N
I
n
r
ec
en
t
d
ec
ad
es,
th
e
ev
o
lu
t
io
n
o
f
tech
n
o
l
o
g
y
r
o
les
h
as
i
m
p
ac
ted
in
f
o
r
m
atio
n
im
p
r
o
v
e
m
en
t
an
d
h
u
m
an
cr
ea
tiv
ity
.
T
h
is
e
v
o
lu
tio
n
attr
ac
ted
cy
b
e
r
s
ec
u
r
ity
th
r
ea
ts
s
u
ch
as
d
en
ial
o
f
s
er
v
ice
(
Do
S)
attac
k
,
z
er
o
-
d
a
y
attac
k
,
o
r
s
o
cial
en
g
in
ee
r
in
g
,
wh
ich
h
av
e
b
ec
o
m
e
s
o
u
b
i
q
u
ito
u
s
a
s
m
all
p
ar
t
o
f
in
f
o
r
m
atio
n
s
ec
u
r
ity
th
r
ea
ts
[
1
]
.
C
y
b
e
r
s
ec
u
r
ity
atta
ck
s
n
o
t
o
n
l
y
co
m
p
r
o
m
is
e
s
tab
le
tech
n
o
lo
g
y
b
u
t
also
ca
u
s
e
s
ig
n
if
ican
t
f
in
a
n
cial
lo
s
s
f
o
r
o
r
g
an
izatio
n
s
an
d
in
d
iv
id
u
als.
C
y
b
er
cr
im
e
h
as
a
n
i
m
m
en
s
e
ec
o
n
o
m
ic
im
p
ac
t,
wi
th
an
est
im
ated
lo
s
s
o
f
8
tr
illi
o
n
in
2
0
2
3
an
d
c
o
n
t
in
u
o
u
s
ly
in
c
r
ea
s
in
g
to
1
0
,
5
tr
illi
o
n
b
y
2
0
2
5
[
2
]
.
T
h
e
n
u
m
b
er
o
f
c
y
b
e
r
attac
k
s
ex
ce
ed
s
8
0
0
,
0
0
0
a
n
d
o
cc
u
r
s
alm
o
s
t e
v
er
y
3
9
s
ec
o
n
d
s
; th
is
th
r
ea
t h
as e
v
o
lv
ed
in
to
a
s
er
io
u
s
g
lo
b
al
r
is
k
[
3
]
.
As
a
r
esu
lt,
o
r
g
an
izati
o
n
s
m
u
s
t c
r
ea
te
an
d
im
p
lem
en
t a
co
m
p
r
eh
en
s
iv
e
cy
b
er
s
ec
u
r
ity
s
tr
ateg
y
t
o
m
in
im
ize
f
u
r
th
er
lo
s
s
.
I
t
is
n
ec
ess
ar
y
t
o
ass
ess
th
e
s
o
lu
tio
n
s
t
h
at
im
p
ac
t
co
m
p
r
eh
en
s
iv
e
ac
tiv
ities
b
ef
o
r
e
b
u
ild
in
g
t
h
e
s
ec
u
r
ity
s
tr
ateg
y
.
T
h
e
f
o
u
n
d
in
g
o
f
a
c
y
b
er
s
ec
u
r
ity
s
u
r
v
eillan
ce
ce
n
te
r
is
o
n
e
o
f
th
e
o
p
tim
al
ad
o
p
ted
s
tr
ateg
ies,
k
n
o
wn
as a
s
ec
u
r
ity
o
p
er
atio
n
ce
n
ter
(
SOC
)
.
T
h
e
s
tr
ateg
y
h
as b
ec
o
m
e
th
e
f
o
r
e
f
r
o
n
t o
f
d
ig
ital sy
s
tem
s
p
r
o
tectio
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
I
SS
N:
2722
-
3
2
2
1
Ma
ch
in
e
lea
r
n
in
g
mo
d
el
a
p
p
r
o
a
ch
in
cy
b
er a
tta
ck
th
r
ea
t
d
etec
tio
n
in
s
ec
u
r
ity
…
(
Mu
h
a
m
ma
d
A
jr
a
n
S
a
p
u
tr
a
)
81
Oth
er
r
esear
ch
er
s
an
n
o
u
n
ce
d
d
if
f
er
en
t w
ay
s
to
o
p
er
ate
an
d
d
esig
n
ed
a
SOC
.
Var
io
u
s
f
ac
t
o
r
s
,
s
u
ch
as
r
eg
u
latio
n
s
,
co
m
p
an
y
s
tr
ateg
y
,
an
d
ex
p
e
r
tis
e,
in
f
lu
en
ce
d
th
e
d
esig
n
[
4
]
.
SOC
was
d
iv
id
ed
in
to
s
ev
er
al
f
u
n
ctio
n
s
.
T
h
e
d
eta
ch
e
d
f
u
n
ctio
n
was
ev
alu
ated
t
o
d
eter
m
i
n
e
th
e
ac
tu
al
p
er
f
o
r
m
a
n
ce
.
T
h
ese
f
u
n
ctio
n
s
in
cl
u
d
e
m
o
n
ito
r
in
g
an
d
d
etec
tio
n
,
an
aly
s
is
,
r
esp
o
n
s
e
an
d
r
ep
o
r
tin
g
,
in
tellig
en
ce
,
b
aselin
e
an
d
v
u
ln
er
a
b
ilit
y
,
an
d
p
o
licy
an
d
s
ig
n
atu
r
e
m
an
ag
e
m
en
t
[
5
]
.
T
h
e
f
r
am
ewo
r
k
o
f
a
n
o
th
er
s
tu
d
y
p
r
o
p
o
s
ed
p
er
f
o
r
m
an
ce
m
o
n
ito
r
in
g
o
f
ea
ch
f
u
n
ctio
n
u
s
in
g
q
u
an
titati
v
e
an
d
q
u
alitativ
e
m
etr
ics.
Ho
wev
e
r
,
th
e
f
r
am
ewo
r
k
d
id
n
o
t
p
r
o
v
id
e
a
co
n
c
r
ete
ev
alu
atio
n
m
ec
h
an
is
m
th
at
o
r
g
an
izatio
n
s
ca
n
u
s
e
to
im
p
lem
en
t th
e
d
ef
in
e
d
m
etr
ics in
th
e
f
r
am
ewo
r
k
[
6
]
.
T
h
r
ea
ts
in
u
n
s
tab
le
n
etwo
r
k
tr
af
f
ic,
k
n
o
wn
as
tr
af
f
ic
an
o
m
aly
,
b
ec
o
m
e
s
ig
n
if
ica
n
t
ch
all
en
g
es
[
7
]
.
An
o
m
aly
n
o
t
o
n
ly
m
a
k
es
th
e
n
etwo
r
k
v
u
ln
er
a
b
le
to
atta
ck
b
u
t
also
h
as
th
e
p
o
ten
tial
to
b
r
an
ch
o
f
f
th
e
s
y
s
tem
tar
g
eted
b
y
th
e
in
tr
u
d
er
[
8
]
.
Acc
o
r
d
in
g
t
o
th
e
Natio
n
al
C
y
b
er
an
d
C
r
y
p
to
Ag
en
c
y
r
ep
o
r
t,
t
h
er
e
wer
e
27
,
4
7
6
,
7
8
8
tr
af
f
ic
an
o
m
aly
in
cid
en
ts
in
I
n
d
o
n
esia,
with
m
o
r
e
th
an
5
0
%
in
d
icate
d
as
m
alwa
r
e
an
d
tr
o
ja
n
attac
k
s
o
n
Ap
r
il 2
0
2
3
[
9
]
.
Sev
er
al
way
s
ar
e
u
s
ed
to
p
r
ev
en
t
n
etwo
r
k
t
r
af
f
ic
an
o
m
al
ies,
s
u
ch
as
lo
g
an
o
m
aly
an
a
ly
s
is
an
d
d
etec
tio
n
[
1
0
]
.
Netwo
r
k
tr
a
f
f
i
c
an
o
m
aly
d
etec
tio
n
id
en
tifie
s
u
n
u
s
u
al
p
atter
n
s
o
r
b
e
h
av
io
r
s
in
n
etwo
r
k
tr
a
f
f
ic.
T
h
e
d
etec
tio
n
h
elp
s
d
eter
m
i
n
e
p
o
ten
tial
s
ec
u
r
ity
th
r
ea
ts
an
d
allo
ws
f
o
r
tim
ely
co
u
n
ter
m
ea
s
u
r
es
[
1
1
]
,
[
1
2
]
.
Netwo
r
k
tr
af
f
ic
a
n
o
m
aly
d
ete
ctio
n
is
an
im
p
o
r
tan
t
ar
ea
o
f
n
etwo
r
k
s
ec
u
r
ity
d
esig
n
ed
t
o
im
p
r
o
v
e
n
etwo
r
k
s
ec
u
r
ity
[
1
3
]
.
An
o
m
aly
d
ete
ctio
n
ca
n
b
e
ex
ec
u
ted
m
a
n
u
ally
b
y
th
e
id
en
tifie
d
lo
g
,
b
u
t
th
is
ap
p
r
o
ac
h
is
im
p
r
ac
tical
b
ec
au
s
e
o
f
th
e
co
m
p
lex
ity
an
d
lar
g
e
am
o
u
n
t
o
f
d
ata
av
ailab
le
[
1
4
]
.
An
o
m
aly
d
etec
tio
n
is
cr
u
ci
al
b
ec
au
s
e
th
e
d
etec
ted
d
ata
ca
n
r
ep
r
esen
t
s
ig
n
if
ican
t,
cr
itical,
an
d
ac
tio
n
ab
le
in
f
o
r
m
atio
n
[
1
5
]
.
T
h
e
r
ef
o
r
e,
an
au
to
m
ated
p
r
o
ce
s
s
is
n
e
ed
ed
t
o
an
aly
ze
lo
g
class
if
icatio
n
r
elate
d
to
tr
af
f
ic
a
n
o
m
alies
[
1
6
]
.
Data
s
cien
ce
n
av
ig
ates
th
e
tr
an
s
f
o
r
m
atio
n
,
in
wh
ic
h
m
ac
h
in
e
lear
n
in
g
is
a
cr
itical
asp
ec
t
o
f
ar
tific
ial
in
telli
g
en
ce
(
AI
)
.
Data
s
cien
ce
co
u
ld
tak
e
an
im
p
o
r
tan
t
r
o
l
e
in
f
in
d
in
g
h
i
d
d
en
p
atter
n
s
in
d
ata.
T
h
e
m
eth
o
d
s
o
f
d
ata
s
cien
ce
g
en
er
ate
a
n
ew
s
cien
tific
p
ar
ad
ig
m
an
d
m
ac
h
in
e
lear
n
in
g
,
s
ig
n
if
ica
n
tly
im
p
ac
tin
g
th
e
cy
b
er
s
ec
u
r
ity
la
n
d
s
ca
p
e
[
1
1
]
.
I
n
th
e
liter
atu
r
e,
Veen
a
et
a
l
.
[
1
7
]
was
co
n
d
u
cted
f
o
r
atta
ck
d
etec
tio
n
with
a
co
m
p
ar
is
o
n
o
f
s
u
p
p
o
r
t
v
ec
t
o
r
m
ac
h
in
e
(
SVM)
an
d
k
-
n
ea
r
est
n
eig
h
b
o
r
s
(
KNN)
in
d
etec
tin
g
cy
b
er
cr
im
e.
T
h
e
r
esear
ch
was
co
n
d
u
cte
d
u
s
in
g
t
h
e
E
C
ML
-
PKDD
2
0
0
7
d
ata
s
et
th
at
co
n
tain
ed
cy
b
er
cr
im
e
d
ata
in
th
e
b
a
n
k
in
g
s
ec
to
r
.
As
a
r
esu
lt,
it
was
f
o
u
n
d
th
at
th
e
SVM
h
ad
th
e
h
ig
h
est
ac
cu
r
ac
y
th
an
KNN,
wh
ic
h
was
ab
o
u
t
9
8
.
8
%
an
d
9
6
.
4
7
%.
Similar
ly
,
Vis
h
wak
ar
m
a
an
d
Kess
wan
i
[
1
8
]
d
is
cu
s
s
ed
th
e
in
tr
u
s
io
n
d
etec
tio
n
s
y
s
tem
(
I
DS)
b
y
co
m
p
ar
in
g
th
e
n
aïv
e
B
ay
es
alg
o
r
ith
m
with
th
e
lo
g
is
tic
r
eg
r
ess
io
n
,
KNN,
d
ec
is
io
n
tr
ee
,
r
a
n
d
o
m
f
o
r
est
,
lin
ea
r
d
is
cr
im
in
an
t
an
aly
s
is
(
L
DA)
,
q
u
ad
r
atic
d
is
cr
im
in
a
n
t
an
al
y
s
is
(
QDA)
,
Ad
aBo
o
s
t,
Gr
ad
ien
t
B
o
o
s
tin
g
,
an
d
E
x
tr
a
T
r
ee
s
alg
o
r
ith
m
s
.
T
h
e
r
esear
ch
was
co
n
d
u
c
ted
u
s
in
g
two
ty
p
es
o
f
d
atasets
,
NSL
-
KDD
an
d
UNSW
_
N
B
1
5
.
T
h
e
r
esu
lts
s
h
o
wed
th
at
n
aïv
e
B
ay
es
p
er
f
o
r
m
ed
th
e
b
est,
with
th
e
9
7
.
1
%
h
ig
h
est
ac
cu
r
ac
y
u
s
in
g
th
e
NSL
-
KDD
d
ataset
an
d
8
6
.
9
% a
cc
u
r
ac
y
u
s
in
g
t
h
e
UNSW
_
N
B
1
5
d
ataset.
T
h
er
ef
o
r
e,
th
is
s
tu
d
y
co
n
d
u
ct
ed
an
a
n
a
ly
s
is
an
d
class
if
icatio
n
o
f
cy
b
er
attac
k
s
o
n
AI
-
b
as
ed
s
y
s
tem
lo
g
s
to
r
ed
u
ce
th
e
wo
r
k
lo
a
d
o
f
th
e
SOC
.
T
h
e
n
aïv
e
B
ay
es
an
d
SVM
alg
o
r
ith
m
s
ar
e
u
s
ed
as
class
if
ier
s
an
d
th
eir
p
er
f
o
r
m
an
ce
s
ar
e
co
m
p
ar
ed
.
T
h
is
s
tu
d
y
u
s
es
th
e
n
a
ïv
e
B
ay
es
alg
o
r
ith
m
b
ec
au
s
e
it
is
s
u
it
ab
le
f
o
r
class
if
icatio
n
task
s
with
th
e
ad
v
an
tag
e
o
f
h
av
in
g
h
ig
h
p
er
f
o
r
m
an
ce
o
n
lar
g
e
d
ata
s
ets
an
d
t
h
e
ab
ilit
y
to
h
a
n
d
le
m
an
y
f
ea
tu
r
es
an
d
ca
n
g
en
er
a
lize
in
f
o
r
m
atio
n
f
r
o
m
p
r
e
v
io
u
s
o
b
s
er
v
atio
n
[
1
9
]
.
T
h
e
u
s
e
o
f
SVM
in
th
is
s
tu
d
y
was
ch
o
s
en
b
ec
au
s
e
SVM
is
a
m
ac
h
in
e
lear
n
in
g
m
o
d
el
t
h
at
ca
n
b
e
u
s
ed
f
o
r
class
if
icatio
n
an
d
r
e
g
r
ess
io
n
p
r
o
b
lem
s
[
2
0
]
.
R
ec
en
t
r
esear
ch
p
r
esen
te
d
a
n
in
n
o
v
ativ
e
m
ac
h
in
e
lea
r
n
i
n
g
m
eth
o
d
to
d
etec
t
an
o
m
al
ies
in
I
o
T
d
ev
ices.
SVM
an
d
r
an
d
o
m
f
o
r
est
m
eth
o
d
s
g
en
e
r
ated
an
ac
cu
r
ac
y
o
f
9
9
.
9
%
an
d
9
7
.
9
%.
T
h
e
r
esear
ch
esti
m
ated
th
at
SVM
'
s
d
etec
ti
o
n
p
r
o
ce
s
s
was
an
ex
ce
llen
t
s
u
p
er
v
is
ed
lear
n
in
g
ap
p
r
o
ac
h
[
2
1
]
.
L
ast
b
u
t
n
o
t
least,
r
esear
ch
p
r
o
p
o
s
ed
u
s
in
g
n
aïv
e
B
ay
es
an
d
SVM
alg
o
r
ith
m
s
to
id
en
tify
an
o
m
alies.
T
h
e
s
tu
d
y
s
h
o
wed
th
at
th
e
n
aïv
e
B
ay
es
alg
o
r
ith
m
co
u
ld
id
en
tif
y
an
o
m
alies
well
[
2
2
]
.
B
ased
o
n
s
ev
er
al
r
ese
ar
ch
es
th
at
h
ad
b
ee
n
ca
r
r
ied
o
u
t
b
y
r
aisi
n
g
d
if
f
e
r
e
n
t
ca
s
e
s
tu
d
ies,
t
h
is
o
u
r
r
ese
ar
ch
also
co
n
tr
i
b
u
tes
to
th
e
wo
r
ld
o
f
SOC
.
I
n
s
u
m
m
ar
y
,
th
e
m
ain
co
n
tr
ib
u
ti
o
n
s
ar
e
s
u
m
m
ar
ize
d
as f
o
ll
o
w
s
:
‒
W
e
p
r
o
p
o
s
e
th
e
an
aly
s
is
an
d
class
if
icatio
n
o
f
cy
b
er
attac
k
s
o
n
lo
g
s
y
s
tem
s
b
ased
o
n
th
e
m
ac
h
in
e
lear
n
in
g
ap
p
r
o
ac
h
th
at
is
u
s
ef
u
l in
o
p
ti
m
izin
g
th
e
wo
r
k
lo
ad
i
n
th
e
S
OC
.
‒
W
e
co
m
p
ar
e
th
e
m
ac
h
in
e
lear
n
in
g
ap
p
r
o
ac
h
,
th
e
n
aïv
e
B
ay
es
alg
o
r
ith
m
,
with
th
e
m
u
ltin
o
m
ial
,
Gau
s
s
ian
,
an
d
b
er
n
o
u
lli
ty
p
es,
an
d
th
e
SVM
alg
o
r
ith
m
with
r
ad
ial
b
asis
f
u
n
ctio
n
(
RBF
)
,
l
in
ea
r
,
p
o
ly
n
o
m
ial,
an
d
s
ig
m
o
id
k
er
n
els in
d
etec
tin
g
t
h
e
th
r
ea
t o
f
cy
b
e
r
attac
k
s
.
2.
M
E
T
H
O
D
T
h
e
r
esear
ch
f
lo
w
illu
s
tr
ated
in
Fig
u
r
e
1
o
u
tlin
es
th
e
s
tag
e
s
in
v
o
lv
ed
in
a
d
d
r
ess
in
g
t
h
e
p
r
o
b
lem
o
f
d
etec
tin
g
cy
b
e
r
-
attac
k
th
r
ea
ts
in
th
e
SOC
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
7
2
2
-
3
2
2
1
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
,
Vo
l.
6
,
No
.
1
,
Ma
r
ch
2
0
2
5
:
80
-
90
82
Fig
u
r
e
1
.
Ov
e
r
all
r
esear
ch
f
l
o
w
2
.
1
.
Da
t
a
s
et
I
n
th
is
s
tu
d
y
,
th
e
d
ata
u
s
ed
c
am
e
f
r
o
m
L
o
g
h
u
b
,
wh
ich
m
ai
n
tain
s
a
co
llectio
n
o
f
s
y
s
tem
lo
g
s
u
s
in
g
th
e
Had
o
o
p
d
ataset.
T
h
e
d
ata
s
et
h
as
f
o
u
r
lab
els,
n
am
ely
m
ac
h
in
e_
d
o
wn
,
n
etwo
r
k
_
d
is
co
n
n
ec
tio
n
,
d
is
k
_
f
u
ll
,
an
d
n
o
r
m
al
[
2
3
]
.
I
n
f
o
r
m
atio
n
ab
o
u
t
t
h
e
d
ataset
ca
n
b
e
s
ee
n
in
T
ab
le
1
,
wh
ile
s
am
p
les
o
f
t
h
e
d
ataset
u
s
ed
ca
n
b
e
s
ee
n
in
T
ab
le
s
2
t
o
5
f
o
r
ea
ch
lab
el/class
.
T
ab
le
1
.
Data
s
et
in
f
o
r
m
atio
n
D
e
scri
p
t
i
o
n
La
b
e
l
e
d
Ti
me
sp
a
n
Li
n
e
s
R
a
w
s
i
z
e
H
a
d
o
o
p
m
a
p
r
e
d
u
c
e
j
o
b
l
o
g
Y
e
s
N
.
A
.
3
9
4
,
3
0
8
4
8
.
6
1
M
B
Evaluation Warning : The document was created with Spire.PDF for Python.
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
I
SS
N:
2722
-
3
2
2
1
Ma
ch
in
e
lea
r
n
in
g
mo
d
el
a
p
p
r
o
a
ch
in
cy
b
er a
tta
ck
th
r
ea
t
d
etec
tio
n
in
s
ec
u
r
ity
…
(
Mu
h
a
m
ma
d
A
jr
a
n
S
a
p
u
tr
a
)
83
T
ab
le
2
.
Ma
ch
i
n
e
d
o
w
n
class
d
ataset
s
am
p
le
D
a
t
e
Ti
me
Le
v
e
l
P
r
o
c
e
ss
C
o
m
p
o
n
e
n
t
C
o
n
t
e
n
t
T
e
mp
l
a
t
e
L
a
b
e
l
1
7
/
1
0
/
2
0
1
5
0
9
:
2
1
.
5
I
N
F
O
mai
n
o
r
g
.
a
p
a
c
h
e
.
h
a
d
o
o
p
.
map
r
e
d
u
c
e
.
v
2
.
a
p
p
.
M
R
A
p
p
M
a
st
e
r
:
C
r
e
a
t
e
d
M
R
A
p
p
M
a
st
e
r
f
o
r
a
p
p
l
i
c
a
t
i
o
n
a
p
p
a
t
t
e
mp
t
_
1
4
4
5
0
7
6
4
3
7
7
7
7
_
0
0
0
4
_
0
0
0
0
0
1
C
r
e
a
t
e
d
M
R
A
p
p
M
a
st
e
r
f
o
r
a
p
p
l
i
c
a
t
i
o
n
a
p
p
a
t
t
e
mp
t
_
<
*
>
mac
h
i
n
e
_
d
o
w
n
1
7
/
1
0
/
2
0
1
5
0
9
:
2
1
.
9
I
N
F
O
mai
n
o
r
g
.
a
p
a
c
h
e
.
h
a
d
o
o
p
.
map
r
e
d
u
c
e
.
v
2
.
a
p
p
.
M
R
A
p
p
M
a
st
e
r
:
Ex
e
c
u
t
i
n
g
w
i
t
h
t
o
k
e
n
s:
Ex
e
c
u
t
i
n
g
w
i
t
h
t
o
k
e
n
s:
mac
h
i
n
e
_
d
o
w
n
….
.
….
.
….
.
….
.
….
.
….
.
….
.
….
.
1
7
/
1
0
/
2
0
1
5
0
9
:
2
3
.
4
I
N
F
O
mai
n
o
r
g
.
a
p
a
c
h
e
.
h
a
d
o
o
p
.
map
r
e
d
u
c
e
.
v
2
.
a
p
p
.
M
R
A
p
p
M
a
st
e
r
:
O
u
t
p
u
t
C
o
mm
i
t
t
e
r
s
e
t
i
n
c
o
n
f
i
g
n
u
l
l
O
u
t
p
u
t
C
o
mm
i
t
t
e
r
set
i
n
c
o
n
f
i
g
n
u
l
l
mac
h
i
n
e
_
d
o
w
n
T
ab
le
3
.
Sam
p
le
n
etwo
r
k
d
is
co
n
n
ec
tio
n
class
d
ataset
D
a
t
e
Ti
me
Le
v
e
l
P
r
o
c
e
ss
C
o
m
p
o
n
e
n
t
C
o
n
t
e
n
t
T
e
mp
l
a
t
e
L
a
b
e
l
1
8
/
1
0
/
2
0
1
5
2
0
:
3
3
.
8
I
N
F
O
mai
n
o
r
g
.
a
p
a
c
h
e
.
h
a
d
o
o
p
.
map
r
e
d
u
c
e
.
v
2
.
a
p
p
.
M
R
A
p
p
M
a
st
e
r
:
C
r
e
a
t
e
d
M
R
A
p
p
M
a
st
e
r
f
o
r
a
p
p
l
i
c
a
t
i
o
n
a
p
p
a
t
t
e
mp
t
_
1
4
4
5
1
4
4
4
2
3
7
2
2
_
0
0
2
0
_
0
0
0
0
0
2
C
r
e
a
t
e
d
M
R
A
p
p
M
a
st
e
r
f
o
r
a
p
p
l
i
c
a
t
i
o
n
a
p
p
a
t
t
e
mp
t
_
<
*
>
n
e
t
w
o
r
k
_
d
i
s
c
o
n
n
e
c
t
i
o
n
1
8
/
1
0
/
2
0
1
5
2
0
:
3
4
.
2
I
N
F
O
mai
n
o
r
g
.
a
p
a
c
h
e
.
h
a
d
o
o
p
.
map
r
e
d
u
c
e
.
v
2
.
a
p
p
.
M
R
A
p
p
M
a
st
e
r
:
Ex
e
c
u
t
i
n
g
w
i
t
h
t
o
k
e
n
s:
Ex
e
c
u
t
i
n
g
w
i
t
h
t
o
k
e
n
s:
n
e
t
w
o
r
k
_
d
i
s
c
o
n
n
e
c
t
i
o
n
….
….
….
….
….
….
….
….
1
8
/
1
0
/
2
0
1
5
2
0
:
3
4
.
9
I
N
F
O
mai
n
o
r
g
.
a
p
a
c
h
e
.
h
a
d
o
o
p
.
map
r
e
d
u
c
e
.
v
2
.
a
p
p
.
M
R
A
p
p
M
a
st
e
r
:
O
u
t
p
u
t
C
o
mm
i
t
t
e
r
s
e
t
i
n
c
o
n
f
i
g
n
u
l
l
O
u
t
p
u
t
C
o
mm
i
t
t
e
r
set
i
n
c
o
n
f
i
g
n
u
l
l
n
e
t
w
o
r
k
_
d
i
s
c
o
n
n
e
c
t
i
o
n
T
ab
le
4
.
Fu
ll
d
is
k
class
d
ataset
s
am
p
le
D
a
t
e
Ti
me
Le
v
e
l
P
r
o
c
e
ss
C
o
m
p
o
n
e
n
t
C
o
n
t
e
n
t
Te
mp
l
a
t
e
La
b
e
l
1
9
/
1
0
/
2
0
1
5
2
1
:
3
2
.
9
I
N
F
O
mai
n
o
r
g
.
a
p
a
c
h
e
.
h
a
d
o
o
p
.
ma
p
r
e
d
u
c
e
.
v
2
.
a
p
p
.
M
R
A
p
p
M
a
st
e
r
:
C
r
e
a
t
e
d
M
R
A
p
p
M
a
st
e
r
f
o
r
a
p
p
l
i
c
a
t
i
o
n
a
p
p
a
t
t
e
mp
t
_
1
4
4
5
1
8
2
1
5
9
1
1
9
_
0
0
0
1
_
0
0
0
0
0
1
C
r
e
a
t
e
d
M
R
A
p
p
M
a
st
e
r
f
o
r
a
p
p
l
i
c
a
t
i
o
n
a
p
p
a
t
t
e
mp
t
_
<
*
>
d
i
s
k
_
f
u
l
l
1
9
/
1
0
/
2
0
1
5
2
1
:
3
3
.
7
I
N
F
O
mai
n
o
r
g
.
a
p
a
c
h
e
.
h
a
d
o
o
p
.
ma
p
r
e
d
u
c
e
.
v
2
.
a
p
p
.
M
R
A
p
p
M
a
st
e
r
:
Ex
e
c
u
t
i
n
g
w
i
t
h
t
o
k
e
n
s:
Ex
e
c
u
t
i
n
g
w
i
t
h
t
o
k
e
n
s:
d
i
s
k
_
f
u
l
l
….
.
….
.
….
.
….
.
….
.
….
.
….
.
….
.
1
9
/
1
0
/
2
0
1
5
2
1
:
3
4
.
9
I
N
F
O
mai
n
o
r
g
.
a
p
a
c
h
e
.
h
a
d
o
o
p
.
ma
p
r
e
d
u
c
e
.
v
2
.
a
p
p
.
M
R
A
p
p
M
a
st
e
r
:
O
u
t
p
u
t
C
o
mm
i
t
t
e
r
s
e
t
i
n
c
o
n
f
i
g
n
u
l
l
O
u
t
p
u
t
C
o
mm
i
t
t
e
r
set
i
n
c
o
n
f
i
g
n
u
l
l
d
i
s
k
_
f
u
l
l
T
ab
le
5
.
No
r
m
al
class
d
ataset
s
am
p
le
D
a
t
e
Ti
me
Le
v
e
l
P
r
o
c
e
ss
C
o
m
p
o
n
e
n
t
C
o
n
t
e
n
t
Te
mp
l
a
t
e
La
b
e
l
1
9
/
1
0
/
2
0
1
5
4
9
:
5
1
.
5
I
N
F
O
mai
n
o
r
g
.
a
p
a
c
h
e
.
h
a
d
o
o
p
.
map
r
e
d
u
c
e
.
v
2
.
a
p
p
.
M
R
A
p
p
M
a
st
e
r
:
C
r
e
a
t
e
d
M
R
A
p
p
M
a
st
e
r
f
o
r
a
p
p
l
i
c
a
t
i
o
n
a
p
p
a
t
t
e
mp
t
_
1
4
4
5
1
8
2
1
5
9
1
1
9
_
0
0
1
2
_
0
0
0
0
0
1
C
r
e
a
t
e
d
M
R
A
p
p
M
a
st
e
r
f
o
r
a
p
p
l
i
c
a
t
i
o
n
a
p
p
a
t
t
e
mp
t
_
<
*
>
N
o
r
mal
1
9
/
1
0
/
2
0
1
5
4
9
:
5
1
.
8
I
N
F
O
mai
n
o
r
g
.
a
p
a
c
h
e
.
h
a
d
o
o
p
.
map
r
e
d
u
c
e
.
v
2
.
a
p
p
.
M
R
A
p
p
M
a
st
e
r
:
Ex
e
c
u
t
i
n
g
w
i
t
h
t
o
k
e
n
s:
Ex
e
c
u
t
i
n
g
w
i
t
h
t
o
k
e
n
s:
N
o
r
mal
….
.
….
.
….
.
….
.
….
.
….
.
….
.
….
.
1
9
/
1
0
/
2
0
1
5
4
9
:
5
3
.
5
I
N
F
O
mai
n
o
r
g
.
a
p
a
c
h
e
.
h
a
d
o
o
p
.
map
r
e
d
u
c
e
.
v
2
.
a
p
p
.
M
R
A
p
p
M
a
st
e
r
:
O
u
t
p
u
t
C
o
mm
i
t
t
e
r
s
e
t
i
n
c
o
n
f
i
g
n
u
l
l
O
u
t
p
u
t
C
o
mm
i
t
t
e
r
s
e
t
i
n
c
o
n
f
i
g
n
u
l
l
N
o
r
mal
2
.
2
.
L
o
g
p
a
rsin
g
L
o
g
p
a
r
s
in
g
is
m
o
d
eled
as
a
clu
s
ter
in
g
p
r
o
b
lem
,
w
h
er
e
lo
g
m
ess
ag
es
d
escr
ib
in
g
t
h
e
s
am
e
s
y
s
tem
s
h
o
u
ld
b
e
g
r
o
u
p
ed
in
to
s
im
ilar
clu
s
ter
s
[
2
4
]
.
T
h
e
p
r
o
b
lem
o
f
lo
g
p
a
r
s
in
g
is
h
o
w
to
ac
cu
r
a
tely
an
d
ef
f
icien
tly
s
ep
ar
ate
u
n
s
tr
u
ctu
r
ed
lo
g
m
ess
ag
es in
to
d
if
f
er
en
t g
r
o
u
p
s
b
y
d
esig
n
in
g
s
im
il
ar
ity
m
etr
ics f
o
r
lo
g
m
ess
ag
es a
n
d
n
ew
clu
s
ter
in
g
ap
p
r
o
ac
h
es [
2
4
]
.
T
h
e
im
p
lem
en
tatio
n
a
r
ch
ite
ctu
r
e
o
f
l
o
g
p
a
r
s
in
g
ca
n
b
e
s
ee
n
in
Fig
u
r
e
2
[
2
5
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
7
2
2
-
3
2
2
1
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
,
Vo
l.
6
,
No
.
1
,
Ma
r
ch
2
0
2
5
:
80
-
90
84
Fig
u
r
e
1
.
L
o
g
p
a
r
s
in
g
ar
c
h
itectu
r
e
2
.
3
.
Wo
rd
weig
hting
us
ing
T
F
-
I
DF
m
et
ho
d
Nex
t,
th
e
ter
m
f
r
eq
u
e
n
cy
-
in
v
e
r
s
e
d
o
cu
m
e
n
t
f
r
eq
u
en
cy
(
T
F
-
I
DF)
s
tag
e
is
ca
r
r
ied
o
u
t
b
ec
a
u
s
e
th
e
lo
g
d
ata
is
in
t
h
e
f
o
r
m
o
f
s
en
te
n
ce
s
(
tex
t)
f
o
r
wo
r
d
weig
h
ti
n
g
[
2
6
]
.
T
h
e
f
ilter
ed
lo
g
d
at
aset
is
th
en
f
u
r
th
er
p
r
o
ce
s
s
ed
to
e
x
tr
ac
t
d
is
cr
im
in
ativ
e
an
d
n
u
m
er
ic
f
ea
tu
r
es
b
y
ad
ap
tin
g
th
e
TF
-
I
DF
alg
o
r
ith
m
[
2
5
]
.
TF
-
I
DF
was
ch
o
s
en
b
ec
au
s
e
th
e
m
eth
o
d
g
iv
es
g
r
ea
ter
weig
h
t
to
ter
m
s
th
at
ap
p
ea
r
less
f
r
eq
u
e
n
tly
in
a
d
o
cu
m
e
n
t
an
d
r
ed
u
ce
s
th
e
im
p
o
r
tan
ce
o
f
ter
m
s
th
at
ap
p
ea
r
m
o
r
e
f
r
eq
u
en
t
ly
,
r
esu
ltin
g
in
c
o
m
p
ac
t
n
u
m
er
ical
f
ea
tu
r
es
[
2
5
]
.
T
h
e
T
F
-
I
DF
al
g
o
r
ith
m
is
u
s
e
d
to
n
u
m
er
ically
ass
ess
th
e
r
elev
an
ce
o
f
w
o
r
d
s
in
d
o
cu
m
e
n
ts
.
T
h
e
f
r
eq
u
en
cy
s
co
r
e
ass
ig
n
ed
to
a
wo
r
d
with
T
F
-
I
DF
d
eter
m
in
es
th
e
im
p
o
r
tan
ce
o
f
th
e
wo
r
d
to
t
h
e
d
o
c
u
m
en
t
b
ased
o
n
t
h
e
f
r
eq
u
e
n
cy
o
f
th
e
wo
r
d
[
2
7
]
.
T
h
e
T
F
-
I
DF
m
eth
o
d
en
ab
les
th
e
id
en
t
if
icatio
n
o
f
k
ey
ter
m
s
th
at
ar
e
u
n
iq
u
e
to
a
p
ar
ticu
lar
d
o
cu
m
en
t,
wh
ich
c
o
n
tr
ib
u
tes
s
ig
n
if
ican
tly
t
o
task
s
s
u
ch
as
tex
t
an
aly
s
is
,
in
f
o
r
m
atio
n
r
etr
iev
al,
a
n
d
d
o
cu
m
e
n
t c
lass
if
icatio
n
[
2
8
]
.
First,
a
f
u
n
ctio
n
is
c
r
ea
ted
t
o
p
r
o
ce
s
s
th
e
te
x
t
g
i
v
en
as
in
p
u
t,
wh
ich
in
clu
d
es
r
ep
lacin
g
th
e
ch
ar
ac
te
r
"/"
with
a
s
p
ac
e.
Nex
t,
th
e
to
k
en
izatio
n
p
r
o
ce
s
s
is
ca
r
r
ied
o
u
t
o
n
th
e
X_
tr
ai
n
_
to
k
e
n
an
d
X_
test
_
to
k
en
d
ata.
T
h
en
,
a
T
f
id
f
Vec
to
r
izer
o
b
je
ct
is
cr
ea
ted
wh
ich
is
u
s
ed
to
tr
an
s
f
o
r
m
a
co
llectio
n
o
f
tex
t
d
o
cu
m
e
n
ts
in
to
a
TF
-
I
DF
m
atr
ix
.
T
F
-
I
DF
is
a
tech
n
iq
u
e
co
m
m
o
n
l
y
u
s
ed
i
n
n
atu
r
al
lan
g
u
ag
e
p
r
o
ce
s
s
in
g
to
m
ea
s
u
r
e
t
h
e
im
p
o
r
tan
ce
o
f
a
wo
r
d
in
a
d
o
c
u
m
en
t r
elativ
e
to
a
co
llectio
n
o
f
o
th
e
r
d
o
c
u
m
en
ts
.
Af
ter
th
at,
d
ata
tr
a
n
s
f
o
r
m
atio
n
is
p
er
f
o
r
m
ed
to
o
b
tain
f
ea
tu
r
e
n
am
es
f
r
o
m
T
F
-
I
DF
d
ata
an
d
ca
lcu
late
th
e
f
r
eq
u
en
cy
o
f
o
cc
u
r
r
en
ce
o
f
wo
r
d
s
in
tr
ain
in
g
an
d
test
in
g
d
ata.
T
h
u
s
,
b
o
th
r
ep
r
esen
t
atio
n
s
(
T
F
-
I
DF
an
d
f
r
eq
u
e
n
cy
)
ca
n
b
e
u
s
ed
f
o
r
f
u
r
th
er
an
aly
s
is
,
s
u
ch
as
class
if
icatio
n
.
T
h
e
r
esu
lts
o
f
th
e
T
F
-
I
DF
p
r
o
ce
s
s
ar
e
s
to
r
ed
in
C
SV f
ile
f
o
r
m
at,
a
n
d
th
e
r
esu
lts
o
f
th
e
T
F
-
I
DF p
r
o
c
ess
ar
e
s
n
ip
p
ed
an
d
d
is
p
lay
ed
in
Fig
u
r
e
3
.
Fig
u
r
e
2
.
R
esu
lt o
f
T
F
-
I
DF
p
r
o
ce
s
s
T
h
e
n
ex
t
s
tag
e
is
T
F
-
I
DF
weig
h
tin
g
,
s
h
o
win
g
r
elev
an
t
wo
r
d
s
(
with
weig
h
ts
g
r
ea
ter
th
an
0
)
f
o
r
th
e
f
ir
s
t
f
iv
e
ex
am
p
les
o
f
th
e
d
a
ta
u
s
ed
.
E
ac
h
wo
r
d
an
d
its
weig
h
t
ar
e
p
r
esen
ted
in
a
ta
b
le
u
s
in
g
a
Pan
d
as
Data
Fra
m
e,
th
at
is
u
s
ef
u
l
f
o
r
f
u
r
th
er
a
n
aly
s
is
o
f
th
e
f
e
atu
r
e
s
th
at
co
n
tr
ib
u
te
to
th
e
m
o
d
el
in
th
e
co
n
tex
t
o
f
class
if
icatio
n
o
r
clu
s
ter
in
g
.
An
ex
am
p
le
o
f
T
F
-
I
DF
weig
h
t
o
n
th
e
1
s
t
d
ata
f
r
o
m
th
e
test
d
ata
ca
n
b
e
s
ee
n
in
Fig
u
r
e
3
.
2
.
4
.
Sp
lit
d
a
t
a
At
th
is
s
tag
e,
th
e
d
ata
is
d
iv
id
ed
in
to
tr
ain
in
g
d
ata
an
d
test
in
g
d
ata.
T
h
e
p
r
o
p
o
r
tio
n
o
f
d
ata
d
iv
is
io
n
u
s
ed
in
t
h
is
s
tu
d
y
is
7
0
%
f
o
r
tr
ain
in
g
d
ata
an
d
3
0
%
f
o
r
test
in
g
d
ata.
T
h
is
d
iv
is
io
n
is
b
ased
o
n
p
r
ev
i
o
u
s
r
esear
c
h
[
2
5
]
,
wh
ich
s
h
o
ws th
at
u
s
in
g
th
e
p
r
o
p
o
r
tio
n
7
0
%:3
0
% p
r
o
d
u
ce
s
an
ac
cu
r
ac
y
o
f
1
0
0
%.
Evaluation Warning : The document was created with Spire.PDF for Python.
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
I
SS
N:
2722
-
3
2
2
1
Ma
ch
in
e
lea
r
n
in
g
mo
d
el
a
p
p
r
o
a
ch
in
cy
b
er a
tta
ck
th
r
ea
t
d
etec
tio
n
in
s
ec
u
r
ity
…
(
Mu
h
a
m
ma
d
A
jr
a
n
S
a
p
u
tr
a
)
85
Fig
u
r
e
3
.
E
x
am
p
le
o
f
weig
h
TF
-
I
DF
on
th
e
f
ir
s
t d
ata
2
.
5
.
Ano
m
a
ly
det
ec
t
io
n us
in
g
na
ïv
e
B
a
y
es a
nd
s
up
po
rt
v
ec
t
o
r
ma
chine
Nex
t,
th
e
m
o
d
el
b
u
ild
in
g
s
tag
e
is
ca
r
r
ied
o
u
t
t
o
d
etec
t
an
o
m
alies.
At
th
is
s
tag
e,
th
e
m
o
d
el
is
b
u
ilt
u
s
in
g
n
aïv
e
B
ay
es a
n
d
SVM
b
y
u
tili
zin
g
7
0
% o
f
t
h
e
tr
ain
in
g
d
ata.
C
lass
if
icat
io
n
is
ca
r
r
ied
o
u
t u
s
in
g
th
e
n
aï
v
e
B
ay
es
an
d
SVM
m
o
d
els.
T
h
e
n
aï
v
e
B
ay
es
m
et
h
o
d
s
u
s
ed
in
clu
d
e
n
aïv
e
B
ay
es
Gau
s
s
ian
,
n
aïv
e
B
ay
es
B
er
n
o
u
lli,
an
d
n
aïv
e
B
ay
es
m
u
ltin
o
m
ial
.
I
n
n
aïv
e
B
ay
es
Gau
s
s
ian
d
o
esn
’
t
r
eq
u
ir
e
c
o
m
p
lex
p
ar
am
eter
s
ea
r
ch
in
g
,
w
h
ich
r
ed
u
ce
s
th
e
v
ar
ian
ce
o
f
th
e
m
o
d
el
an
d
n
aï
v
e
B
ay
es
Gau
s
s
ian
s
u
p
p
o
r
ts
i
n
cr
em
en
tal
lea
r
n
in
g
[
2
9
]
.
W
h
ile
in
n
aïv
e
B
ay
es B
er
n
o
u
lli
,
m
o
d
el
p
r
im
a
r
ily
f
o
c
u
s
es o
n
s
ea
r
ch
in
g
f
o
r
v
ec
to
r
f
ea
t
u
r
es th
at
ar
e
b
in
a
r
y
[
3
0
]
.
Naïv
e
B
ay
es
Mu
ltin
o
m
ial
is
a
clas
s
if
icatio
n
m
eth
o
d
with
p
r
o
b
a
b
ilit
y
,
wh
ich
p
r
ed
icts
f
u
tu
r
e
opp
o
r
tu
n
ities
b
ased
o
n
p
r
e
v
io
u
s
ex
p
er
ien
ce
s
o
it is
k
n
o
wn
a
s
B
ay
es T
h
eo
r
em
[
3
1
]
.
W
h
ile
in
th
e
SVM
m
o
d
el,
v
ar
io
u
s
k
er
n
els
ar
e
u
s
ed
,
n
am
ely
lin
ea
r
k
er
n
els,
p
o
ly
n
o
m
ia
l
k
er
n
els,
s
ig
m
o
id
k
er
n
els,
an
d
R
B
F
k
er
n
els.
T
h
e
class
if
icatio
n
r
esu
lts
o
f
th
e
two
m
o
d
els
will
b
e
co
m
p
ar
e
d
.
L
in
ea
r
k
er
n
el
in
SVM
ca
n
g
u
a
r
an
tee
g
lo
b
al
o
p
tim
izatio
n
f
o
r
r
e
g
r
e
s
s
io
n
o
r
class
if
icatio
n
p
r
o
b
le
m
s
in
s
m
all
-
to
-
lar
g
e
d
atasets
[
3
2
]
.
Un
lik
e
th
e
lin
e
ar
k
er
n
el,
th
e
p
o
ly
n
o
m
ial
k
er
n
el
d
o
es
in
v
o
lv
e
ta
k
in
g
th
e
i
n
n
er
p
r
o
d
u
ct
f
r
o
m
a
h
ig
h
er
d
im
en
s
io
n
s
p
ac
e.
Un
li
k
e
th
e
p
o
ly
n
o
m
ial
k
e
r
n
el,
wh
ich
lo
o
k
s
at
ex
tr
a
d
im
en
s
io
n
s
,
R
B
F
ex
p
an
d
s
in
to
an
d
in
f
in
ite
n
u
m
b
e
r
o
f
d
im
en
s
io
n
s
[
3
3
]
.
Sig
m
o
id
k
e
r
n
e
l
f
u
n
ctio
n
s
ar
e
co
m
m
o
n
l
y
i
m
p
lem
en
ted
,
th
ese
f
u
n
ctio
n
s
a
r
e
n
o
t
p
o
s
itiv
e
s
em
i
-
d
ef
in
ite
f
o
r
ce
r
tain
v
alu
es
o
f
th
ese
k
e
r
n
el
p
ar
am
eter
s
.
C
o
n
s
eq
u
en
tly
,
t
h
e
p
ar
am
eter
s
γ
(
g
am
m
a)
a
n
d
c
m
u
s
t b
e
ch
o
s
en
ca
r
ef
u
lly
t
o
av
o
id
er
r
o
r
s
in
th
e
r
esu
lts
o
b
tain
ed
[
3
4
]
.
I
n
t
h
is
s
t
u
d
y
,
h
y
p
er
p
ar
am
ete
r
i
m
p
le
m
e
n
t
ati
o
n
was
c
ar
r
i
ed
o
u
t
u
s
in
g
G
r
i
d
Se
ar
ch
C
V
f
o
r
th
e
S
VM
m
o
d
el
wit
h
R
B
F
k
er
n
el.
W
i
th
C
a
n
d
g
am
m
a
p
a
r
a
m
e
te
r
s
,
t
h
e
m
o
d
el
wil
l
b
e
tes
te
d
t
o
f
i
n
d
t
h
e
b
es
t
c
o
m
b
i
n
ati
o
n
th
a
t
p
r
o
v
i
d
es
t
h
e
b
est
p
er
f
o
r
m
an
ce
o
n
th
e
t
r
a
in
in
g
d
ata
.
Af
te
r
f
i
n
d
in
g
t
h
e
o
p
ti
m
a
l
p
a
r
a
m
e
te
r
s
,
t
h
e
m
o
d
el
wil
l
b
e
u
s
e
d
to
p
r
e
d
i
ct
th
e
class
o
n
t
h
e
tes
t
d
at
a.
T
h
is
is
a
c
o
m
m
o
n
a
p
p
r
o
a
ch
t
o
i
m
p
r
o
v
i
n
g
t
h
e
ac
c
u
r
a
cy
o
f
m
ac
h
i
n
e
lea
r
n
i
n
g
m
o
d
e
ls
w
it
h
h
y
p
e
r
p
ar
am
e
te
r
o
p
ti
m
i
za
t
io
n
.
T
h
e
h
y
p
e
r
p
a
r
a
m
et
er
s
u
s
e
d
ca
n
b
e
s
ee
n
i
n
T
a
b
l
e
6
.
T
ab
le
6
.
Gr
id
SVM
p
ar
am
eter
s
P
a
r
a
me
t
e
r
S
V
M
S
i
g
m
o
i
d
k
e
r
n
e
l
R
B
F
k
e
r
n
e
l
Li
n
e
a
r
k
e
r
n
e
l
P
o
l
y
n
o
m
i
a
l
k
e
r
n
e
l
C
0
.
1
0
.
1
0
.
1
0
.
1
C
1
1
1
1
C
10
10
10
10
C
1
0
0
1
0
0
1
0
0
1
0
0
g
a
mm
a
0
.
0
0
1
0
.
0
0
1
sca
l
e
g
a
mm
a
0
.
0
1
0
.
0
1
a
u
t
o
g
a
mm
a
0
.
1
0
.
1
g
a
mm
a
1
1
d
e
g
r
e
e
2
d
e
g
r
e
e
3
d
e
g
r
e
e
4
Fro
m
th
e
p
ar
am
eter
s
u
s
ed
,
th
e
b
est p
ar
am
eter
s
f
o
r
th
e
R
B
F
k
er
n
el
ar
e
o
b
tain
ed
.
T
h
e
R
B
F
k
er
n
el
g
ets
th
e
b
est
p
ar
am
eter
s
,
n
am
ely
C
=1
0
0
,
class
_
weig
h
t
=
'
b
alan
ce
d
'
,
g
am
m
a
=0
.
1
.
T
h
e
v
alu
e
o
f
C
=1
0
0
in
d
icate
s
th
at
th
e
m
o
d
el
f
o
cu
s
es
m
o
r
e
o
n
r
ed
u
ci
n
g
class
if
icatio
n
er
r
o
r
s
s
o
th
at
it
is
m
o
r
e
s
en
s
itiv
e
to
o
u
tlier
s
.
class
_
weig
h
t
=
'
b
alan
ce
d
'
,
h
elp
s
h
an
d
le
class
i
m
b
alan
ce
p
r
o
b
lem
s
b
y
g
iv
in
g
m
o
r
e
weig
h
t
to
u
n
d
er
r
e
p
r
esen
te
d
class
es.
A
v
alu
e
o
f
0
.
1
in
d
icate
s
th
at
th
e
in
f
lu
en
ce
o
f
o
n
e
d
ata
is
b
r
o
ad
er
,
h
elp
in
g
t
h
e
m
o
d
el
r
ec
o
g
n
ize
m
o
r
e
co
m
p
lex
p
atter
n
s
.
Fro
m
th
e
p
ar
am
eter
s
u
s
ed
,
t
h
e
b
est
p
a
r
a
m
eter
s
f
o
r
t
h
e
lin
ea
r
k
er
n
el
a
r
e
o
b
tain
e
d
.
I
n
th
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
7
2
2
-
3
2
2
1
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
,
Vo
l.
6
,
No
.
1
,
Ma
r
ch
2
0
2
5
:
80
-
90
86
lin
ea
r
k
er
n
el,
th
e
b
est
p
ar
am
eter
s
ar
e
C
=1
0
0
,
class
_
weig
h
t
=
'
b
alan
ce
d
'
,
k
er
n
el
=
'
lin
ea
r
'
.
T
h
e
v
alu
e
o
f
C
=1
0
0
in
d
icate
s
th
at
th
e
m
o
d
el
f
o
cu
s
es
m
o
r
e
o
n
r
ed
u
cin
g
c
lass
if
icatio
n
er
r
o
r
s
s
o
th
at
it
is
m
o
r
e
s
en
s
itiv
e
to
o
u
tlier
s
.
class
_
w
eig
h
t
=
'
b
alan
ce
d
'
,
h
elp
s
h
an
d
le
class
im
b
alan
ce
p
r
o
b
lem
s
b
y
g
iv
i
n
g
m
o
r
e
weig
h
t
to
u
n
d
er
r
ep
r
esen
ted
class
es.
k
er
n
el
=
'
lin
ea
r
'
in
d
icate
s
th
at
th
e
m
o
d
el
u
s
es
a
lin
ea
r
s
ep
ar
ato
r
f
u
n
ctio
n
.
Fro
m
ea
ch
p
ar
am
eter
u
s
ed
,
th
e
b
est
p
ar
a
m
eter
f
o
r
th
e
p
o
ly
n
o
m
ial
k
er
n
el
is
o
b
tain
ed
.
I
n
th
e
p
o
ly
n
o
m
ial
k
er
n
el,
th
e
b
est
p
ar
am
eter
is
C
=1
0
,
class
_
weig
h
t
=
'
b
alan
ce
d
'
,
d
eg
r
ee
=2
,
k
er
n
el
=
'
p
o
ly
'
.
T
h
e
v
alu
e
o
f
C
=1
0
s
h
o
ws
a
litt
le
m
o
r
e
t
o
ler
an
ce
f
o
r
m
is
class
if
icatio
n
.
T
h
is
ca
n
h
elp
t
h
e
m
o
d
el
n
o
t
o
v
er
f
it.
class
_
weig
h
t
=
'
b
alan
ce
d
'
,
h
elp
s
d
ea
l
with
th
e
p
r
o
b
lem
o
f
cla
s
s
im
b
alan
ce
b
y
g
iv
in
g
m
o
r
e
weig
h
t
to
u
n
d
er
r
ep
r
esen
ted
class
es.
d
eg
r
ee
=2
in
d
icate
s
th
at
th
e
m
o
d
el
u
s
es
a
p
o
ly
n
o
m
ial
f
u
n
ctio
n
o
f
d
eg
r
ee
2
,
w
h
ich
allo
ws
th
e
m
o
d
el
to
ca
p
tu
r
e
n
o
n
lin
ea
r
in
ter
ac
tio
n
s
b
etwe
en
f
ea
tu
r
es.
k
er
n
el
=
'
p
o
ly
'
in
d
icate
s
th
e
u
s
e
o
f
a
p
o
ly
n
o
m
ial
k
er
n
el
th
at
i
s
s
u
itab
le
f
o
r
d
ata
with
n
o
n
-
lin
ea
r
r
elatio
n
s
h
ip
s
.
Fro
m
ea
ch
p
ar
am
eter
u
s
ed
,
th
e
b
est
p
ar
am
eter
f
o
r
th
e
p
o
ly
n
o
m
ial
k
er
n
el
is
o
b
tain
ed
.
I
n
th
e
p
o
ly
n
o
m
ial
k
er
n
el,
th
e
b
est p
a
r
am
eter
is
C
=1
0
,
class
_
w
eig
h
t =
'
b
alan
ce
d
'
,
g
am
m
a
=1
,
k
er
n
el
=
'si
g
m
o
id
'
.
T
h
e
v
alu
e
o
f
C
=1
0
s
h
o
ws
a
litt
le
m
o
r
e
t
o
ler
an
ce
f
o
r
m
is
class
if
icatio
n
.
T
h
is
ca
n
h
elp
th
e
m
o
d
el
n
o
t
o
v
er
f
it.
class
_
weig
h
t
=
'
b
alan
ce
d
'
,
h
elp
s
d
ea
l
with
th
e
p
r
o
b
lem
o
f
class
im
b
alan
ce
b
y
g
iv
in
g
m
o
r
e
weig
h
t
t
o
u
n
d
er
r
ep
r
esen
ted
class
es.
G
a
m
m
a
=1
m
ea
n
s
th
at
th
e
in
f
lu
e
n
ce
o
f
ea
ch
d
ata
p
o
i
n
t
is
q
u
ite
s
ig
n
if
ican
t,
an
d
ca
n
p
r
o
d
u
ce
n
o
n
-
lin
ea
r
p
atter
n
s
in
th
e
d
ata.
K
er
n
el
=
'
s
ig
m
o
id
'
in
d
icate
s
th
e
u
s
e
o
f
th
e
s
ig
m
o
id
ac
tiv
atio
n
f
u
n
cti
o
n
wh
ich
ca
n
p
r
o
v
id
e
n
o
n
-
lin
ea
r
ch
a
r
ac
ter
is
tics
f
o
r
class
s
ep
ar
atio
n
.
2
.
6
.
E
v
a
lua
t
i
o
n
I
n
th
e
m
o
d
el
ev
alu
atio
n
u
s
in
g
co
n
f
u
s
io
n
m
atr
ix
wh
ich
p
r
o
d
u
ce
s
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
F1
-
s
co
r
e
an
d
f
alse
p
o
s
itiv
e
r
ate
(
FP
R
)
v
alu
es.
Acc
u
r
ac
y
m
ea
s
u
r
e
is
ca
lcu
lated
b
y
tak
in
g
all
th
e
tr
u
e
p
r
ed
ictio
n
s
a
n
d
d
iv
id
in
g
t
h
em
am
o
n
g
all
th
e
p
r
ed
icted
v
alu
es,
i
n
clu
d
in
g
th
e
tr
u
e
p
r
e
d
ictio
n
s
[
3
5
]
.
Pre
cisi
o
n
is
m
ea
s
u
r
in
g
t
h
e
n
u
m
b
er
o
f
co
r
r
ec
tly
p
r
ed
icte
d
p
o
s
itiv
e
r
ate
d
iv
id
ed
b
y
t
h
e
to
tal
p
r
ed
icted
p
o
s
itiv
e
r
ates
[
3
6
]
.
R
ec
all
o
r
Sen
s
itiv
ity
is
th
e
p
r
o
p
o
r
tio
n
o
f
r
ea
l
p
o
s
itiv
e
c
ases
th
at
ar
e
co
r
r
ec
tly
p
r
ed
icted
p
o
s
itiv
e
[
3
7
]
.
F1
-
s
co
r
e
is
th
e
weig
h
ted
h
ar
m
o
n
ic
m
ea
n
o
f
th
e
r
ec
all
a
n
d
p
r
ec
is
io
n
v
al
u
es
[
3
8
]
.
FP
R
is
r
atio
b
etwe
en
th
e
in
c
o
r
r
ec
tl
y
class
if
ied
n
eg
ativ
e
s
am
p
les
to
th
e
to
tal
n
u
m
b
er
o
f
n
e
g
ativ
e
s
am
p
les
[
3
9
]
.
M
o
d
el
test
in
g
co
n
s
is
ts
o
f
SVM
m
o
d
els
with
R
B
F
k
er
n
el,
lin
e
ar
,
p
o
ly
n
o
m
ial
an
d
s
ig
m
o
id
as
well
as
m
u
ltin
o
m
ial
n
aïv
e
B
ay
es
,
g
au
s
s
ian
n
aïv
e
B
ay
es
,
b
er
n
o
u
lli
n
aïv
e
B
ay
es
m
o
d
els
.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
At
th
is
s
tag
e,
th
e
r
esu
lts
o
f
th
e
m
o
d
el
ev
alu
atio
n
u
s
in
g
th
e
co
n
f
u
s
io
n
m
at
r
ix
f
r
o
m
th
e
m
u
ltin
o
m
ial
n
aïv
e
B
ay
es,
g
au
s
s
ian
n
aïv
e
B
ay
es,
b
er
n
o
u
lli
n
aïv
e
B
ay
es
m
eth
o
d
s
ar
e
ex
p
lain
ed
.
Fro
m
s
ev
er
al
test
s
th
at
h
av
e
b
ee
n
c
o
n
d
u
cted
f
o
r
t
h
e
d
etec
tio
n
o
f
cy
b
e
r
attac
k
th
r
ea
ts
in
SOC
u
s
in
g
th
e
m
ac
h
in
e
lear
n
in
g
ap
p
r
o
ac
h
o
f
th
e
SVM
m
eth
o
d
with
R
B
F
k
er
n
el,
SVM
with
lin
ea
r
k
e
r
n
el,
SVM
with
p
o
ly
n
o
m
ial
k
er
n
el,
SVM
with
Sig
m
o
id
k
er
n
el
an
d
n
aïv
e
B
ay
es
f
r
o
m
m
u
ltin
o
m
ial
n
aï
v
e
B
ay
es
,
g
au
s
s
ian
n
aïv
e
B
ay
es
an
d
b
er
n
o
u
lli
n
aïv
e
B
ay
es
o
b
tain
ed
v
ar
y
in
g
m
o
d
el
p
er
f
o
r
m
a
n
ce
r
esu
lts
.
T
h
e
o
v
er
all
m
o
d
el
r
esu
lts
ca
n
b
e
s
ee
n
in
T
ab
le
7
.
T
ab
le
7
.
R
esu
lts
o
f
th
e
o
v
er
all
m
o
d
el
ev
al
u
atio
n
M
o
d
e
l
A
c
c
u
r
a
c
y
(
%)
P
r
e
c
i
s
i
o
n
(
%)
R
e
c
a
l
l
(
%)
F1
-
sc
o
r
e
(
%)
S
V
M
w
i
t
h
R
B
F
k
e
r
n
e
l
7
9
.
7
5
8
0
.
8
7
9
.
7
5
8
0
.
0
1
S
V
M
w
i
t
h
l
i
n
e
a
r
k
e
r
n
e
l
7
9
.
5
8
0
.
5
1
7
9
.
5
7
9
.
7
5
S
V
M
w
i
t
h
p
o
l
y
n
o
mi
a
l
k
e
r
n
e
l
7
5
.
7
5
7
7
.
1
1
7
5
.
7
5
7
6
.
0
4
S
V
M
w
i
t
h
si
g
m
o
i
d
k
e
r
n
e
l
7
8
.
7
5
8
0
.
1
2
7
8
.
7
5
7
9
.
0
5
M
u
l
t
i
n
o
m
i
a
l
n
a
ï
v
e
B
a
y
e
s
6
9
.
5
8
7
2
.
3
6
9
.
5
8
6
9
.
9
2
G
a
u
ss
i
a
n
n
a
ï
v
e
B
a
y
e
s
7
0
.
0
8
0
.
2
7
7
0
.
0
7
0
.
6
6
B
e
r
n
o
u
l
l
i
n
a
ï
v
e
B
a
y
e
s
6
3
.
7
5
6
8
.
6
6
3
.
7
5
6
4
.
2
B
ased
o
n
Fig
u
r
e
5
,
it
ca
n
b
e
ex
p
lain
ed
th
at
th
e
SVM
al
g
o
r
ith
m
with
th
e
R
B
F
k
er
n
el
o
b
tain
ed
p
r
ed
ictio
n
r
esu
lts
o
n
th
e
m
ac
h
in
e_
d
o
wn
lab
el
co
r
r
ec
tly
cla
s
s
if
ied
as
m
an
y
as
2
3
0
d
ata,
wh
ile
th
e
p
r
ed
ictio
n
er
r
o
r
with
4
2
d
ata
en
ter
ed
in
t
o
th
e
n
o
r
m
al
lab
el,
1
d
ata
en
t
er
ed
in
to
th
e
n
etwo
r
k
_
d
is
co
n
n
ec
tio
n
lab
el,
an
d
2
1
d
ata
en
ter
ed
in
to
th
e
d
is
k
_
f
u
ll lab
el.
I
n
th
e
n
o
r
m
al
lab
el
with
a
to
tal
o
f
2
5
5
d
ata
class
if
ied
c
o
r
r
ec
tly
,
wh
ile
t
h
e
p
r
ed
ictio
n
er
r
o
r
with
3
3
d
ata
en
ter
ed
in
to
th
e
m
a
ch
in
e_
d
o
wn
lab
el,
2
d
ata
en
ter
ed
in
to
th
e
n
etwo
r
k
_
d
is
co
n
n
ec
tio
n
lab
el,
an
d
2
5
d
ata
en
ter
ed
i
n
to
th
e
d
i
s
k
_
f
u
ll
lab
el.
I
n
th
e
n
etwo
r
k
_
d
is
co
n
n
ec
tio
n
lab
el
with
a
to
tal
o
f
2
3
0
d
ata
cla
s
s
if
ied
co
r
r
ec
tly
,
wh
ile
th
e
p
r
ed
ictio
n
er
r
o
r
with
1
7
d
at
a
en
ter
ed
in
to
t
h
e
m
ac
h
in
e_
d
o
wn
lab
el,
1
5
d
ata
en
ter
ed
in
to
th
e
n
o
r
m
al
lab
el,
an
d
2
2
d
ata
en
ter
e
d
in
to
th
e
d
is
k
_
f
u
ll lab
el.
I
n
th
e
d
is
k
_
f
u
ll
lab
el,
2
4
2
d
ata
wer
e
class
if
ied
co
r
r
ec
tly
,
wh
ile
p
r
e
d
ictio
n
er
r
o
r
s
in
clu
d
ed
3
7
d
ata
th
at
wer
e
in
clu
d
ed
Evaluation Warning : The document was created with Spire.PDF for Python.
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
I
SS
N:
2722
-
3
2
2
1
Ma
ch
in
e
lea
r
n
in
g
mo
d
el
a
p
p
r
o
a
ch
in
cy
b
er a
tta
ck
th
r
ea
t
d
etec
tio
n
in
s
ec
u
r
ity
…
(
Mu
h
a
m
ma
d
A
jr
a
n
S
a
p
u
tr
a
)
87
in
th
e
m
ac
h
in
e
_
d
o
wn
lab
el,
2
8
d
ata
th
at
wer
e
in
clu
d
ed
in
th
e
n
o
r
m
al
l
ab
el,
a
n
d
0
d
ata
t
h
at
wer
e
in
cl
u
d
ed
in
th
e
n
etwo
r
k
_
d
is
co
n
n
ec
tio
n
la
b
el.
T
h
e
r
esu
lts
o
f
th
e
co
n
f
u
s
io
n
m
atr
ix
p
lo
t
o
n
th
e
SVM
m
eth
o
d
with
th
e
R
B
F
k
er
n
el
ca
n
b
e
s
ee
n
in
Fig
u
r
e
4
.
Fig
u
r
e
4
.
C
o
n
f
u
s
io
n
m
atr
i
x
SVM
k
er
n
el
RBF
T
h
e
f
o
ll
o
wi
n
g
e
x
p
la
in
s
t
h
e
r
es
u
lts
o
f
t
h
e
FP
R
t
est o
f
t
h
e
m
et
h
o
d
u
s
ed
.
F
r
o
m
T
ab
le
8
t
h
e
r
e
s
u
lts
o
f
t
h
e
FP
R
test
o
n
t
h
e
SVM
wit
h
R
B
F
k
er
n
e
l
t
h
a
t
t
h
e
n
et
wo
r
k
_
d
is
co
n
n
e
cti
o
n
l
a
b
el
h
as
th
e
lo
west
FP
R
o
f
0
.
3
3
%
,
wh
i
ch
m
ea
n
s
t
h
a
t
t
h
e
m
o
d
el
i
s
th
e
b
est
b
ec
a
u
s
e
t
h
e
g
r
o
u
n
d
tr
u
t
h
v
a
lu
e
o
f
FP
R
is
0
[
4
0
]
.
Fr
o
m
T
a
b
l
e
8
,
t
h
e
SVM
m
et
h
o
d
w
it
h
t
h
e
R
B
F
k
er
n
e
l
d
em
o
n
s
t
r
at
es
t
h
e
b
es
t
p
e
r
f
o
r
m
a
n
ce
in
class
if
y
i
n
g
c
y
b
e
r
t
h
r
e
ats,
ac
h
i
ev
in
g
an
a
cc
u
r
ac
y
o
f
7
9
.
7
5
%
,
p
r
e
cisi
o
n
o
f
8
0
.
8
%,
r
e
ca
ll
o
f
7
9
.
7
5
%,
a
n
d
a
n
F
1
-
s
co
r
e
o
f
8
0
.
0
1
%.
O
th
e
r
SVM
k
e
r
n
els
,
s
u
c
h
as
li
n
e
a
r
(
7
9
.
5
%)
,
p
o
l
y
n
o
m
i
al
(
7
5
.
7
5
%
)
,
a
n
d
s
i
g
m
o
i
d
(
7
8
.
7
5
%)
,
als
o
y
iel
d
g
o
o
d
r
es
u
lts
.
Me
a
n
w
h
ile
,
Gau
s
s
ia
n
n
aï
v
e
B
a
y
es
ac
h
ie
v
es
7
0
.
0
%
ac
cu
r
ac
y
,
wh
ile
m
u
lt
in
o
m
ia
l
(
6
9
.
5
8
%
)
a
n
d
b
e
r
n
o
u
lli
n
a
ïv
e
B
a
y
es
(
6
3
.
7
5
%
)
s
h
o
w
l
o
w
er
p
e
r
f
o
r
m
an
ce
.
O
v
er
all
,
t
h
e
SVM
m
o
d
el
f
al
ls
wi
th
in
t
h
e
"v
e
r
y
g
o
o
d
"
ca
te
g
o
r
y
(
7
5
%
-
8
9
%
)
,
wh
e
r
ea
s
s
o
m
e
n
a
ïv
e
B
ay
es
v
ar
ia
n
ts
a
r
e
ca
te
g
o
r
ize
d
as
"
f
air
"
o
r
"
p
o
o
r
.
"
T
h
es
e
f
i
n
d
i
n
g
s
in
d
i
ca
te
th
a
t
th
e
S
VM
wit
h
t
h
e
R
B
F
k
e
r
n
el
is
th
e
m
o
s
t
e
f
f
ec
t
i
v
e
m
et
h
o
d
,
wh
ile
n
aï
v
e
B
a
y
es
r
e
q
u
i
r
es
f
u
r
t
h
e
r
d
e
v
e
lo
p
m
e
n
t
,
s
u
c
h
as
h
y
p
e
r
p
a
r
am
e
te
r
tu
n
i
n
g
,
t
o
e
n
h
a
n
c
e
i
ts
p
er
f
o
r
m
a
n
c
e
in
d
et
ec
ti
n
g
c
y
b
e
r
th
r
e
ats.
T
ab
le
8
.
FPR
m
o
d
el
La
b
e
l
S
V
M
M
u
l
t
i
n
o
m
i
a
l
n
a
ï
v
e
B
a
y
e
s
(
%)
G
a
u
ss
i
a
n
n
a
ï
v
e
B
a
y
e
s
(
%)
B
e
r
n
o
u
l
l
i
n
a
ï
v
e
B
a
y
e
s
(
%)
R
B
F
k
e
r
n
e
l
(
%)
Li
n
e
a
r
k
e
r
n
e
l
(
%)
P
o
l
y
n
o
m
i
a
l
k
e
r
n
e
l
(
%)
S
i
g
m
o
i
d
k
e
r
n
e
l
(
%)
M
a
c
h
i
n
e
_
d
o
w
n
9
.
6
9
.
0
5
1
0
.
7
1
8
.
8
3
8
.
2
8
0
.
4
4
1
4
.
9
N
o
r
mal
9
.
6
1
0
.
1
7
1
2
.
8
8
1
2
.
9
9
1
8
.
0
8
2
.
8
2
2
4
.
0
7
N
e
t
w
o
r
k
_
d
i
sc
o
n
n
e
c
t
i
o
n
0
.
3
3
0
.
4
4
0
.
9
8
0
.
5
5
1
.
0
9
3
1
.
7
7
0
.
5
5
D
i
sk
_
f
u
l
l
7
.
6
1
7
.
8
4
7
.
9
5
6
.
1
6
1
3
.
4
4
4
.
4
8
9
.
1
8
4.
CO
NCLU
SI
O
N
Fro
m
th
e
r
esear
ch
th
at
h
as
b
e
en
d
o
n
e
o
n
cy
b
e
r
-
attac
k
d
etec
tio
n
in
SOC
u
s
in
g
th
e
m
ac
h
i
n
e
lear
n
in
g
m
eth
o
d
ap
p
r
o
ac
h
,
th
e
f
o
llo
wi
n
g
co
n
clu
s
io
n
s
ca
n
b
e
d
r
awn
:
i)
d
etec
tio
n
o
f
cy
b
e
r
-
attac
k
t
h
r
ea
ts
in
th
e
SO
C
u
s
in
g
AI
-
b
ased
s
y
s
tem
lo
g
d
ata
was
s
u
cc
ess
f
u
lly
ca
r
r
ied
o
u
t
u
s
in
g
th
e
n
aïv
e
B
ay
es
a
n
d
SVM
m
ac
h
in
e
lear
n
in
g
m
o
d
el
a
p
p
r
o
ac
h
es
,
ii
)
t
h
e
m
ac
h
in
e
lear
n
i
n
g
m
o
d
el
ap
p
r
o
ac
h
in
d
etec
tin
g
cy
b
er
-
attac
k
th
r
ea
ts
at
th
e
SOC
u
s
in
g
AI
-
b
ased
s
y
s
tem
l
o
g
d
ata
is
ca
r
r
ied
o
u
t
with
th
e
n
aïv
e
B
ay
es
m
o
d
el
with
m
u
ltin
o
m
ial,
g
au
s
s
ian
,
b
er
n
o
u
lli
ty
p
es
an
d
S
VM
with
R
B
F,
lin
ea
r
,
p
o
ly
n
o
m
ial,
s
ig
m
o
id
k
e
r
n
els
,
an
d
iii)
t
h
e
r
esu
lts
o
f
th
e
e
v
alu
atio
n
u
s
in
g
co
n
f
u
s
io
n
m
atr
i
x
o
b
tain
ed
th
e
b
est
m
o
d
el
p
er
f
o
r
m
a
n
c
e
in
th
e
SVM
m
eth
o
d
with
R
B
F
k
er
n
el
with
an
ac
cu
r
ac
y
v
alu
e
o
f
7
9
.
7
5
%,
p
r
ec
is
io
n
o
f
8
0
.
8
%,
r
ec
all
o
f
7
9
.
7
5
%
,
an
d
F1
-
s
co
r
e
o
f
8
0
.
0
1
%
.
Me
an
wh
ile,
in
th
e
n
aïv
e
B
ay
es
ty
p
e
th
er
e
is
a
g
au
s
s
ian
n
aïv
e
B
ay
es
with
an
ac
cu
r
ac
y
o
f
7
0
.
0
%,
p
r
ec
is
io
n
o
f
8
0
.
2
7
%,
r
ec
all
o
f
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
7
2
2
-
3
2
2
1
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
,
Vo
l.
6
,
No
.
1
,
Ma
r
ch
2
0
2
5
:
80
-
90
88
7
0
.
0
%
,
a
n
d
F1
-
s
co
r
e
o
f
7
0
.
6
6
%.
T
h
er
ef
o
r
e,
o
v
er
all
,
th
e
m
o
d
el
s
u
cc
ee
d
s
in
class
if
y
in
g
well
an
d
f
alls
in
to
th
e
v
er
y
g
o
o
d
class
if
icatio
n
ca
teg
o
r
y
(
7
5
%
-
8
9
%),
b
u
t
th
e
m
u
lti
n
o
m
ial
n
aïv
e
B
ay
es
m
eth
o
d
g
ets
an
ac
cu
r
ac
y
o
f
6
9
.
5
8
%
in
t
h
e
f
air
ca
teg
o
r
y
(
6
5
%
-
7
4
%)
an
d
t
h
e
b
er
n
o
u
lli
n
a
ïv
e
B
ay
es
m
eth
o
d
g
ets
an
ac
c
u
r
ac
y
o
f
6
3
.
7
5
%
in
th
e
p
o
o
r
ca
te
g
o
r
y
(
5
0
%
-
6
4
%).
Su
g
g
esti
o
n
s
th
at
c
an
b
e
g
iv
en
f
r
o
m
th
is
r
esear
ch
,
f
o
r
f
u
r
th
er
d
ev
elo
p
m
e
n
t,
ar
e
co
m
p
ar
is
o
n
s
m
ad
e
o
n
v
ar
io
u
s
p
r
o
p
o
r
tio
n
s
o
f
d
atasets
u
s
ed
.
I
n
ad
d
itio
n
,
o
t
h
er
h
y
p
er
p
ar
a
m
eter
tu
n
in
g
ca
n
b
e
d
o
n
e
o
n
SVM
an
d
n
aïv
e
B
ay
es
m
o
d
els
s
o
th
at
th
e
b
est
p
ar
am
eter
co
m
b
i
n
atio
n
ca
n
b
e
s
ee
n
an
d
im
p
r
o
v
e
m
o
d
el
p
er
f
o
r
m
a
n
ce
.
ACK
NO
WL
E
DG
M
E
N
T
S
T
h
e
au
th
o
r
s
wo
u
ld
lik
e
to
t
h
an
k
th
e
C
o
m
p
u
ter
Netwo
r
k
,
E
n
ter
p
r
is
e
an
d
I
n
f
o
r
m
atio
n
Secu
r
ity
R
esear
ch
Gr
o
u
p
(
C
OM
NE
T
S
R
G)
,
Un
iv
er
s
itas
Sriwijay
a,
I
n
d
o
n
esia
f
o
r
p
r
o
v
id
in
g
f
u
ll
s
u
p
p
o
r
t
f
o
r
th
eir
r
esear
ch
n
ec
ess
ar
y
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
Au
th
o
r
s
s
tate
n
o
f
u
n
d
in
g
in
v
o
lv
ed
.
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
T
h
is
jo
u
r
n
al
u
s
es
th
e
C
o
n
tr
ib
u
to
r
R
o
les
T
ax
o
n
o
m
y
(
C
R
ed
iT)
to
r
ec
o
g
n
ize
in
d
iv
id
u
al
au
th
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
th
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
llab
o
r
atio
n
.
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
Mu
h
am
m
ad
Ajr
a
n
Sap
u
tr
a
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Der
is
Sti
awa
n
✓
✓
✓
✓
✓
R
ah
m
at
B
u
d
iar
to
✓
✓
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
Au
th
o
r
s
s
tate
n
o
co
n
f
lict o
f
in
t
er
est.
DATA
AV
AI
L
AB
I
L
I
T
Y
D
a
t
a
a
v
a
il
a
b
i
li
t
y
is
n
o
t
a
p
p
l
i
ca
b
l
e
t
o
t
h
is
p
a
p
e
r
a
s
n
o
n
e
w
d
at
a
w
e
r
e
c
r
e
a
t
e
d
o
r
a
n
al
y
z
e
d
i
n
t
h
is
s
t
u
d
y
.
RE
F
E
R
E
NC
E
S
[
1
]
M
.
A
h
sa
n
,
K
.
E.
N
y
g
a
r
d
,
R
.
G
o
mes
,
M
.
M
.
C
h
o
w
d
h
u
r
y
,
N
.
R
i
f
a
t
,
a
n
d
J.
F
.
C
o
n
n
o
l
l
y
,
“
C
y
b
e
r
se
c
u
r
i
t
y
t
h
r
e
a
t
s a
n
d
t
h
e
i
r
m
i
t
i
g
a
t
i
o
n
a
p
p
r
o
a
c
h
e
s
u
s
i
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
-
a
r
e
v
i
e
w
,
”
J
o
u
r
n
a
l
o
f
C
y
b
e
rsec
u
r
i
t
y
a
n
d
Pri
v
a
c
y
,
v
o
l
.
2
,
n
o
.
3
,
p
p
.
5
2
7
–
5
5
5
,
J
u
l
.
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
j
c
p
2
0
3
0
0
2
7
.
[
2
]
C
.
B
r
o
o
k
s,
“
C
y
b
e
r
se
c
u
r
i
t
y
t
r
e
n
d
s
&
st
a
t
i
s
t
i
c
s
f
o
r
2
0
2
3
;
w
h
a
t
y
o
u
n
e
e
d
t
o
k
n
o
w
,
”
Fo
r
b
e
s
,
2
0
2
3
.
A
c
c
e
sse
d
:
O
c
t
.
1
6
,
2
0
2
4
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s
:
/
/
w
w
w
.
f
o
r
b
e
s.c
o
m
/
si
t
e
s
/
c
h
u
c
k
b
r
o
o
k
s/
2
0
2
3
/
0
3
/
0
5
/
c
y
b
e
r
se
c
u
r
i
t
y
-
t
r
e
n
d
s
--
st
a
t
i
s
t
i
c
s
-
f
o
r
-
2
0
2
3
-
mo
r
e
-
t
r
e
a
c
h
e
r
y
-
a
n
d
-
r
i
sk
-
a
h
e
a
d
-
as
-
a
t
t
a
c
k
-
su
r
f
a
c
e
-
a
n
d
-
h
a
c
k
e
r
-
c
a
p
a
b
i
l
i
t
i
e
s
-
g
r
o
w
/
?
s
h
=
6
b
b
5
e
a
0
3
1
9
d
b
[
3
]
S
.
Ja
i
n
,
“
1
6
0
c
y
b
e
r
se
c
u
r
i
t
y
s
t
a
t
i
st
i
c
s
2
0
2
4
,
”
G
e
t
a
st
r
a
,
2
0
2
4
.
A
c
c
e
ss
e
d
:
D
e
c
.
1
2
,
2
0
2
4
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s
:
/
/
w
w
w
.
g
e
t
a
st
r
a
.
c
o
m/
b
l
o
g
/
s
e
c
u
r
i
t
y
-
a
u
d
i
t
/
c
y
b
e
r
-
sec
u
r
i
t
y
-
s
t
a
t
i
s
t
i
c
s
/
[
4
]
M
.
V
i
e
l
b
e
r
t
h
,
F
.
B
o
h
m,
I
.
F
i
c
h
t
i
n
g
e
r
,
a
n
d
G
.
P
e
r
n
u
l
,
“
S
e
c
u
r
i
t
y
o
p
e
r
a
t
i
o
n
s
c
e
n
t
e
r
:
a
s
y
st
e
mat
i
c
st
u
d
y
a
n
d
o
p
e
n
c
h
a
l
l
e
n
g
e
s,”
I
EE
E
Ac
c
e
ss
,
v
o
l
.
8
,
p
p
.
2
2
7
7
5
6
–
2
2
7
7
7
9
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
0
.
3
0
4
5
5
1
4
.
[
5
]
E.
A
g
y
e
p
o
n
g
,
Y
.
C
h
e
r
d
a
n
t
s
e
v
a
,
P
.
R
e
i
n
e
c
k
e
,
a
n
d
P
.
B
u
r
n
a
p
,
“
A
s
y
st
e
ma
t
i
c
me
t
h
o
d
f
o
r
m
e
a
s
u
r
i
n
g
t
h
e
p
e
r
f
o
r
ma
n
c
e
o
f
a
c
y
b
e
r
sec
u
r
i
t
y
o
p
e
r
a
t
i
o
n
s c
e
n
t
r
e
a
n
a
l
y
s
t
,
”
C
o
m
p
u
t
e
rs &
S
e
c
u
ri
t
y
,
v
o
l
.
1
2
4
,
Ja
n
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
se
.
2
0
2
2
.
1
0
2
9
5
9
.
[
6
]
E.
A
h
l
m
,
“
H
o
w
t
o
b
u
i
l
d
a
n
d
o
p
e
r
a
t
e
a
m
o
d
e
r
n
s
e
c
u
r
i
t
y
o
p
e
r
a
t
i
o
n
s
c
e
n
t
e
r
,
”
G
a
r
t
n
e
r
I
n
c
,
2
0
2
1
.
A
c
c
e
ss
e
d
:
D
e
c
.
1
2
,
2
0
2
4
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s:
/
/
w
w
w
.
g
a
r
t
n
e
r
.
c
o
m
/
e
n
/
d
o
c
u
me
n
t
s/
4
0
0
2
2
5
9
[
7
]
M
.
Z
o
l
a
n
v
a
r
i
,
M
.
A
.
T
e
i
x
e
i
r
a
,
L
.
G
u
p
t
a
,
K
.
M
.
K
h
a
n
,
a
n
d
R
.
J
a
i
n
,
“
M
a
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
v
u
l
n
e
r
a
b
i
l
i
t
y
a
n
a
l
y
s
i
s
o
f
i
n
d
u
s
t
r
i
a
l
i
n
t
e
r
n
e
t
o
f
t
h
i
n
g
s
,
”
I
E
E
E
I
n
t
e
r
n
e
t
o
f
T
h
i
n
g
s
J
o
u
r
n
a
l
,
v
o
l
.
6
,
n
o
.
4
,
p
p
.
6
8
2
2
–
6
8
3
4
,
A
u
g
.
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
J
I
O
T
.
2
0
1
9
.
2
9
1
2
0
2
2
.
Evaluation Warning : The document was created with Spire.PDF for Python.
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
I
SS
N:
2722
-
3
2
2
1
Ma
ch
in
e
lea
r
n
in
g
mo
d
el
a
p
p
r
o
a
ch
in
cy
b
er a
tta
ck
th
r
ea
t
d
etec
tio
n
in
s
ec
u
r
ity
…
(
Mu
h
a
m
ma
d
A
jr
a
n
S
a
p
u
tr
a
)
89
[
8
]
T
.
J
a
f
a
r
i
a
n
,
M
.
M
a
s
d
a
r
i
,
A
.
G
h
a
f
f
a
r
i
,
a
n
d
K
.
M
a
j
i
d
z
a
d
e
h
,
“
A
s
u
r
v
e
y
a
n
d
c
l
a
s
s
i
f
i
c
a
t
i
o
n
o
f
t
h
e
s
e
c
u
r
i
t
y
a
n
o
m
a
l
y
d
e
t
e
c
t
i
o
n
m
e
c
h
a
n
i
s
m
s
i
n
s
o
f
t
w
a
r
e
d
e
f
i
n
e
d
n
e
t
w
o
r
k
s
,
”
C
l
u
s
t
e
r
C
o
m
p
u
t
i
n
g
,
v
o
l
.
2
4
,
n
o
.
2
,
p
p
.
1
2
3
5
–
1
2
5
3
,
J
u
n
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
0
5
8
6
-
0
2
0
-
03184
-
1.
[
9
]
C
N
N
,
“
B
S
S
N
d
e
t
e
c
t
s
4
4
m
i
l
l
i
o
n
ma
l
w
a
r
e
a
c
t
i
v
i
t
i
e
s
u
n
t
i
l
M
a
y
2
0
2
4
(
i
n
I
n
d
o
n
e
s
i
a
n
:
BS
S
N
d
e
t
e
k
s
i
4
4
j
u
t
a
a
k
t
i
v
i
t
a
s
m
a
l
w
a
re
h
i
n
g
g
a
Me
i
2
0
2
4
)
,
”
C
N
N
I
n
d
o
n
e
si
a
,
2
0
2
4
.
A
c
c
e
sse
d
:
O
c
t
.
1
6
,
2
0
2
4
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s
:
/
/
w
w
w
.
c
n
n
i
n
d
o
n
e
si
a
.
c
o
m
/
t
e
k
n
o
l
o
g
i
/
2
0
2
4
0
5
1
6
1
8
4
3
5
4
-
1
8
5
-
1
0
9
8
6
2
6
/
b
ssn
-
d
e
t
e
k
s
i
-
44
-
j
u
t
a
-
a
k
t
i
v
i
t
a
s
-
mal
w
a
r
e
-
h
i
n
g
g
a
-
m
e
i
-
2
0
2
4
[
1
0
]
A
.
H
.
S
h
a
h
,
D
.
P
a
s
h
a
,
E.
H
.
Za
d
e
h
,
a
n
d
S
.
K
o
n
u
r
,
“
A
u
t
o
ma
t
e
d
l
o
g
a
n
a
l
y
si
s
a
n
d
a
n
o
m
a
l
y
d
e
t
e
c
t
i
o
n
u
s
i
n
g
mac
h
i
n
e
l
e
a
r
n
i
n
g
,
”
Fro
n
t
i
e
rs
i
n
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
,
p
p
.
1
3
7
-
1
4
7
,
2
0
2
2
,
d
o
i
:
1
0
.
3
2
3
3
/
F
A
I
A
2
2
0
3
7
8
.
[
1
1
]
H
.
H
a
n
,
Z.
Y
a
n
,
X
.
Ji
n
g
,
a
n
d
W
.
P
e
d
r
y
c
z
,
“
A
p
p
l
i
c
a
t
i
o
n
s
o
f
s
k
e
t
c
h
e
s
i
n
n
e
t
w
o
r
k
t
r
a
f
f
i
c
mea
s
u
r
e
m
e
n
t
:
a
s
u
r
v
e
y
,
”
I
n
f
o
rm
a
t
i
o
n
Fu
si
o
n
,
v
o
l
.
8
2
,
p
p
.
5
8
–
8
5
,
J
u
n
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
n
f
f
u
s.
2
0
2
1
.
1
2
.
0
0
7
.
[
1
2
]
A
.
D
i
r
o
,
S
.
K
a
i
sar,
A
.
V
.
V
a
si
l
a
k
o
s
,
A
.
A
n
w
a
r
,
A
.
N
a
s
i
r
i
a
n
,
a
n
d
G
.
O
l
a
n
i
,
“
A
n
o
ma
l
y
d
e
t
e
c
t
i
o
n
f
o
r
s
p
a
c
e
i
n
f
o
r
mat
i
o
n
n
e
t
w
o
r
k
s:
a
s
u
r
v
e
y
o
f
c
h
a
l
l
e
n
g
e
s,
t
e
c
h
n
i
q
u
e
s,
a
n
d
f
u
t
u
r
e
d
i
r
e
c
t
i
o
n
s,
”
C
o
m
p
u
t
e
rs
&
S
e
c
u
ri
t
y
,
v
o
l
.
1
3
9
,
A
p
r
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
s
e
.
2
0
2
4
.
1
0
3
7
0
5
.
[
1
3
]
Z.
Z
h
a
o
,
H
.
G
u
o
,
a
n
d
Y
.
W
a
n
g
,
“
A
mu
l
t
i
-
i
n
f
o
r
mat
i
o
n
f
u
s
i
o
n
a
n
o
m
a
l
y
d
e
t
e
c
t
i
o
n
mo
d
e
l
b
a
s
e
d
o
n
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s
a
n
d
A
u
t
o
E
n
c
o
d
e
r
,
”
S
c
i
e
n
t
i
f
i
c
R
e
p
o
rt
s
,
v
o
l
.
1
4
,
n
o
.
1
,
J
u
l
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
3
8
/
s4
1
5
9
8
-
024
-
6
6
7
6
0
-
0.
[
1
4
]
A
.
B
.
N
a
ssi
f
,
M
.
A
.
Ta
l
i
b
,
Q
.
N
a
si
r
,
a
n
d
F
.
M
.
D
a
k
a
l
b
a
b
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
f
o
r
a
n
o
ma
l
y
d
e
t
e
c
t
i
o
n
:
a
s
y
st
e
ma
t
i
c
r
e
v
i
e
w
,
”
I
EEE
Ac
c
e
ss
,
v
o
l
.
9
,
p
p
.
7
8
6
5
8
–
7
8
7
0
0
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
1
.
3
0
8
3
0
6
0
.
[
1
5
]
W
.
A
.
A
l
i
,
K
.
N
.
M
a
n
a
sa
,
M
.
B
e
n
d
e
c
h
a
c
h
e
,
M
.
F
.
A
l
j
u
n
i
d
,
a
n
d
P
.
S
a
n
d
h
y
a
,
“
A
r
e
v
i
e
w
o
f
c
u
r
r
e
n
t
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
e
s
f
o
r
a
n
o
m
a
l
y
d
e
t
e
c
t
i
o
n
i
n
n
e
t
w
o
r
k
t
r
a
f
f
i
c
,
”
J
o
u
r
n
a
l
o
f
T
e
l
e
c
o
m
m
u
n
i
c
a
t
i
o
n
s
a
n
d
t
h
e
D
i
g
i
t
a
l
E
c
o
n
o
m
y
,
v
o
l
.
8
,
n
o
.
4
,
p
p
.
6
4
–
9
5
,
D
e
c
.
2
0
2
0
,
d
o
i
:
1
0
.
1
8
0
8
0
/
j
t
d
e
.
v
8
n
4
.
3
0
7
.
[
1
6
]
N
.
A
.
A
z
e
e
z
,
T.
O
.
O
d
e
y
e
mi
,
C
.
C
.
I
si
e
k
w
e
n
e
,
a
n
d
A
.
P
.
A
b
i
d
o
y
e
,
“
C
y
b
e
r
a
t
t
a
c
k
d
e
t
e
c
t
i
o
n
i
n
a
g
l
o
b
a
l
n
e
t
w
o
r
k
u
si
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
,
”
FU
O
Y
E
J
o
u
r
n
a
l
o
f
En
g
i
n
e
e
ri
n
g
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
8
,
n
o
.
4
,
p
p
.
4
4
8
-
4
5
5
,
D
e
c
.
2
0
2
3
,
d
o
i
:
1
0
.
4
6
7
9
2
/
f
u
o
y
e
j
e
t
.
v
8
i
4
.
1
1
1
3
.
[
1
7
]
K
.
V
e
e
n
a
,
K
.
M
e
e
n
a
,
Y
.
Te
e
k
a
r
a
m
a
n
,
R
.
K
u
p
p
u
s
a
m
y
,
a
n
d
A
.
R
a
d
h
a
k
r
i
s
h
n
a
n
,
“
C
S
V
M
c
l
a
ssi
f
i
c
a
t
i
o
n
a
n
d
K
N
N
t
e
c
h
n
i
q
u
e
s
f
o
r
c
y
b
e
r
c
r
i
me
d
e
t
e
c
t
i
o
n
,
”
Wi
re
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
2
2
,
p
p
.
1
–
9
,
Ja
n
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
2
/
3
6
4
0
0
1
7
.
[
1
8
]
M
.
V
i
sh
w
a
k
a
r
ma
a
n
d
N
.
K
e
ssw
a
n
i
,
“
A
n
e
w
t
w
o
-
p
h
a
s
e
i
n
t
r
u
s
i
o
n
d
e
t
e
c
t
i
o
n
sy
st
e
m
w
i
t
h
N
a
ï
v
e
B
a
y
e
s
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
f
o
r
d
a
t
a
c
l
a
ss
i
f
i
c
a
t
i
o
n
a
n
d
e
l
l
i
p
t
i
c
e
n
v
e
l
o
p
me
t
h
o
d
f
o
r
a
n
o
ma
l
y
d
e
t
e
c
t
i
o
n
,
”
D
e
c
i
si
o
n
A
n
a
l
y
t
i
c
s
J
o
u
r
n
a
l
,
v
o
l
.
7
,
Ju
n
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
d
a
j
o
u
r
.
2
0
2
3
.
1
0
0
2
3
3
.
[
1
9
]
V
.
N
a
k
h
i
p
o
v
a
e
t
a
l
.
,
“
U
se
o
f
t
h
e
n
a
i
v
e
B
a
y
e
s
c
l
a
ss
i
f
i
e
r
a
l
g
o
r
i
t
h
m
i
n
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
f
o
r
s
t
u
d
e
n
t
p
e
r
f
o
r
ma
n
c
e
p
r
e
d
i
c
t
i
o
n
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
I
n
f
o
rm
a
t
i
o
n
a
n
d
Ed
u
c
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
1
4
,
n
o
.
1
,
2
0
2
4
,
d
o
i
:
1
0
.
1
8
1
7
8
/
i
j
i
e
t
.
2
0
2
4
.
1
4
.
1
.
2
0
2
8
.
[
2
0
]
B
.
M
a
h
e
s
h
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms
-
a
r
e
v
i
e
w
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
S
c
i
e
n
c
e
a
n
d
Re
s
e
a
r
c
h
(
I
J
S
R)
,
v
o
l
.
9
,
n
o
.
1
,
p
p
.
3
8
1
–
3
8
6
,
J
a
n
.
2
0
2
0
,
d
o
i
:
1
0
.
2
1
2
7
5
/
A
R
T2
0
2
0
3
9
9
5
.
[
2
1
]
M
.
D
.
N
a
t
h
a
n
d
T.
B
h
a
t
t
a
s
a
l
i
,
“
A
n
o
m
a
l
y
d
e
t
e
c
t
i
o
n
u
s
i
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
e
s,”
Aze
r
b
a
i
j
a
n
J
o
u
rn
a
l
o
f
H
i
g
h
Pe
rf
o
rm
a
n
c
e
C
o
m
p
u
t
i
n
g
,
v
o
l
.
3
,
n
o
.
2
,
p
p
.
196
–
2
0
6
,
D
e
c
.
2
0
2
0
,
d
o
i
:
1
0
.
3
2
0
1
0
/
2
6
1
6
6
1
2
7
.
2
0
2
0
.
3
.
2
.
1
9
6
.
2
0
6
.
[
2
2
]
A
.
A
l
O
b
a
i
d
l
i
,
D
.
M
a
n
s
o
u
r
,
S
.
M
.
A
b
d
u
l
h
a
mi
d
,
N
.
B
.
H
a
l
i
m
a
,
a
n
d
A
.
A
l
-
G
h
u
s
h
a
m
i
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
t
o
a
n
o
mal
y
d
e
t
e
c
t
i
o
n
a
t
t
a
c
k
s
c
l
a
ssi
f
i
c
a
t
i
o
n
i
n
I
o
T
d
e
v
i
c
e
s,”
i
n
2
0
2
3
1
s
t
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
A
d
v
a
n
c
e
d
I
n
n
o
v
a
t
i
o
n
s
i
n
S
m
a
r
t
C
i
t
i
e
s
(
I
C
AI
S
C
)
,
Ja
n
.
2
0
2
3
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
A
I
S
C
5
6
3
6
6
.
2
0
2
3
.
1
0
0
8
5
3
4
9
.
[
2
3
]
P
.
C
h
h
a
j
e
r
,
M
.
S
h
a
h
,
a
n
d
A
.
K
s
h
i
r
sa
g
a
r
,
“
T
h
e
a
p
p
l
i
c
a
t
i
o
n
s o
f
a
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s
,
s
u
p
p
o
r
t
v
e
c
t
o
r
m
a
c
h
i
n
e
s
,
a
n
d
l
o
n
g
-
sh
o
r
t
t
e
r
m m
e
m
o
r
y
f
o
r
st
o
c
k
mar
k
e
t
p
r
e
d
i
c
t
i
o
n
,
”
D
e
c
i
s
i
o
n
A
n
a
l
y
t
i
c
s
J
o
u
r
n
a
l
,
v
o
l
.
2
,
M
a
r
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
d
a
j
o
u
r
.
2
0
2
1
.
1
0
0
0
1
5
.
[
2
4
]
J.
Zh
u
,
S
.
H
e
,
P
.
H
e
,
J.
Li
u
,
a
n
d
M
.
R
.
L
y
u
,
“
L
o
g
h
u
b
:
a
l
a
r
g
e
c
o
l
l
e
c
t
i
o
n
o
f
sy
s
t
e
m
l
o
g
d
a
t
a
set
s
f
o
r
a
i
-
d
r
i
v
e
n
l
o
g
a
n
a
l
y
t
i
c
s
,
”
i
n
2
0
2
3
I
EE
E
3
4
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
S
y
m
p
o
s
i
u
m
o
n
S
o
f
t
w
a
re
Re
l
i
a
b
i
l
i
t
y
En
g
i
n
e
e
ri
n
g
(
I
S
S
RE)
,
O
c
t
.
2
0
2
3
,
p
p
.
3
5
5
–
3
6
6
.
d
o
i
:
1
0
.
1
1
0
9
/
I
S
S
R
E
5
9
8
4
8
.
2
0
2
3
.
0
0
0
7
1
.
[
2
5
]
M
.
A
k
a
n
l
e
e
t
a
l
.
,
“
E
x
p
e
r
i
m
e
n
t
a
t
i
o
n
s
w
i
t
h
o
p
e
n
s
t
a
c
k
s
y
st
e
m
l
o
g
s
a
n
d
s
u
p
p
o
r
t
v
e
c
t
o
r
mac
h
i
n
e
f
o
r
a
n
a
n
o
ma
l
y
d
e
t
e
c
t
i
o
n
m
o
d
e
l
i
n
a
p
r
i
v
a
t
e
c
l
o
u
d
i
n
f
r
a
st
r
u
c
t
u
r
e
,
”
i
n
2
0
2
0
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
B
i
g
D
a
t
a
,
C
o
m
p
u
t
i
n
g
a
n
d
D
a
t
a
C
o
m
m
u
n
i
c
a
t
i
o
n
S
y
st
e
m
s
(
i
c
ABC
D
)
,
A
u
g
.
2
0
2
0
,
p
p
.
1
–
7
,
d
o
i
:
1
0
.
1
1
0
9
/
i
c
A
B
C
D
4
9
1
6
0
.
2
0
2
0
.
9
1
8
3
8
7
8
.
[
2
6
]
L.
X
i
a
n
g
,
“
A
p
p
l
i
c
a
t
i
o
n
o
f
a
n
i
mp
r
o
v
e
d
TF
-
I
D
F
met
h
o
d
i
n
l
i
t
e
r
a
r
y
t
e
x
t
c
l
a
ss
i
f
i
c
a
t
i
o
n
,
”
A
d
v
a
n
c
e
s
i
n
M
u
l
t
i
m
e
d
i
a
,
v
o
l
.
2
0
2
2
,
p
p
.
1
–
1
0
,
M
a
y
2
0
2
2
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
2
/
9
2
8
5
3
2
4
.
[
2
7
]
A
.
A
d
d
i
g
a
a
n
d
S
.
B
a
g
u
i
,
“
S
e
n
t
i
m
e
n
t
a
n
a
l
y
si
s
o
n
t
w
i
t
t
e
r
d
a
t
a
u
si
n
g
t
e
r
m
f
r
e
q
u
e
n
c
y
-
i
n
v
e
r
s
e
d
o
c
u
m
e
n
t
f
r
e
q
u
e
n
c
y
,
”
J
o
u
rn
a
l
o
f
C
o
m
p
u
t
e
r
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
s
,
v
o
l
.
1
0
,
n
o
.
0
8
,
p
p
.
1
1
7
–
1
2
8
,
2
0
2
2
,
d
o
i
:
1
0
.
4
2
3
6
/
j
c
c
.
2
0
2
2
.
1
0
8
0
0
8
.
[
2
8
]
R
.
C
h
a
v
a
n
,
G
.
P
a
t
i
l
,
V
.
M
a
d
l
e
,
a
n
d
R
.
Jo
s
h
i
,
“
C
u
r
a
t
i
n
g
st
o
p
w
o
r
d
s
i
n
m
a
r
a
t
h
i
:
a
TF
-
I
D
F
a
p
p
r
o
a
c
h
f
o
r
i
m
p
r
o
v
e
d
t
e
x
t
a
n
a
l
y
s
i
s a
n
d
i
n
f
o
r
m
a
t
i
o
n
r
e
t
r
i
e
v
a
l
,
”
2
0
2
4
I
EEE
9
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
f
o
r
C
o
n
v
e
rg
e
n
c
e
i
n
T
e
c
h
n
o
l
o
g
y
(
I
2
C
T
)
,
P
u
n
e
,
I
n
d
i
a
,
2
0
2
4
,
p
p
.
1
-
6,
d
o
i
:
1
0
.
1
1
0
9
/
I
2
C
T
6
1
2
2
3
.
2
0
2
4
.
1
0
5
4
4
3
5
9
.
[
2
9
]
M
.
V
.
A
n
a
n
d
,
B
.
K
i
r
a
n
B
a
l
a
,
S
.
R
.
S
r
i
v
i
d
h
y
a
,
C
.
K
a
v
i
t
h
a
,
M
.
Y
o
u
n
u
s
,
a
n
d
M
.
H
.
R
a
h
m
a
n
,
“
G
a
u
ssi
a
n
n
a
ï
v
e
B
a
y
e
s
a
l
g
o
r
i
t
h
m:
a
r
e
l
i
a
b
l
e
t
e
c
h
n
i
q
u
e
i
n
v
o
l
v
e
d
i
n
t
h
e
a
s
so
r
t
m
e
n
t
o
f
t
h
e
se
g
r
e
g
a
t
i
o
n
i
n
c
a
n
c
e
r
,
”
M
o
b
i
l
e
I
n
f
o
rm
a
t
i
o
n
S
y
s
t
e
m
s
,
v
o
l
.
2
0
2
2
,
p
p
.
1
–
7
,
Ju
n
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
2
/
2
4
3
6
9
4
6
.
[
3
0
]
M
.
I
smai
l
,
N
.
H
a
ssa
n
,
a
n
d
S
.
S
.
B
a
f
j
a
i
s
h
,
“
C
o
m
p
a
r
a
t
i
v
e
a
n
a
l
y
si
s
o
f
N
a
i
v
e
B
a
y
e
si
a
n
t
e
c
h
n
i
q
u
e
s
i
n
h
e
a
l
t
h
-
r
e
l
a
t
e
d
f
o
r
c
l
a
ss
i
f
i
c
a
t
i
o
n
t
a
sk
,
”
J
o
u
rn
a
l
o
f
S
o
f
t
C
o
m
p
u
t
i
n
g
a
n
d
D
a
t
a
Mi
n
i
n
g
,
v
o
l
.
1
,
n
o
.
2
,
p
p
.
1
–
1
0
,
2
0
2
0
,
d
o
i
:
1
0
.
3
0
8
8
0
/
j
sc
d
m.
2
0
2
0
.
0
1
.
0
2
.
0
0
1
.
[
3
1
]
W
.
B
.
Z
u
l
f
i
k
a
r
,
A
.
R
.
A
t
ma
d
j
a
,
a
n
d
S
.
F
.
P
r
a
t
a
ma
,
“
S
e
n
t
i
me
n
t
a
n
a
l
y
si
s
o
n
so
c
i
a
l
me
d
i
a
a
g
a
i
n
st
p
u
b
l
i
c
p
o
l
i
c
y
u
s
i
n
g
mu
l
t
i
n
o
m
i
a
l
N
a
i
v
e
B
a
y
e
s
,
”
S
c
i
e
n
t
i
f
i
c
J
o
u
r
n
a
l
o
f
I
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
1
0
,
n
o
.
1
,
p
p
.
2
5
–
3
4
,
J
a
n
.
2
0
2
3
,
d
o
i
:
1
0
.
1
5
2
9
4
/
s
j
i
.
v
1
0
i
1
.
3
9
9
5
2
.
[
3
2
]
N
.
N
a
i
c
k
e
r
,
T
.
A
d
e
l
i
y
i
,
a
n
d
J.
W
i
n
g
,
“
L
i
n
e
a
r
s
u
p
p
o
r
t
v
e
c
t
o
r
ma
c
h
i
n
e
s
f
o
r
p
r
e
d
i
c
t
i
o
n
o
f
st
u
d
e
n
t
p
e
r
f
o
r
ma
n
c
e
i
n
s
c
h
o
o
l
-
b
a
s
e
d
e
d
u
c
a
t
i
o
n
,
”
M
a
t
h
e
m
a
t
i
c
a
l
Pr
o
b
l
e
m
s
i
n
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
2
0
2
0
,
p
p
.
1
–
7
,
O
c
t
.
2
0
2
0
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
0
/
4
7
6
1
4
6
8
.
[
3
3
]
M
.
A
l
i
d
a
a
n
d
M
.
M
u
st
i
k
a
sari
,
“
R
u
p
i
a
h
e
x
c
h
a
n
g
e
p
r
e
d
i
c
t
i
o
n
o
f
U
S
d
o
l
l
a
r
u
s
i
n
g
l
i
n
e
a
r
,
p
o
l
y
n
o
mi
a
l
,
a
n
d
r
a
d
i
a
l
b
a
si
s
f
u
n
c
t
i
o
n
k
e
r
n
e
l
i
n
s
u
p
p
o
r
t
v
e
c
t
o
r
r
e
g
r
e
ss
i
o
n
,
”
J
u
rn
a
l
O
n
l
i
n
e
I
n
f
o
rm
a
t
i
k
a
,
v
o
l
.
5
,
n
o
.
1
,
p
p
.
5
3
-
6
0
,
2
0
2
0
,
d
o
i
:
1
0
.
1
5
5
7
5
/
j
o
i
n
.
v
5
i
1
.
5
3
7
.
[
3
4
]
I
.
S
.
A
l
-
M
e
j
i
b
l
i
,
J
.
K
.
A
l
w
a
n
,
a
n
d
D
.
H
.
A
b
d
,
“
T
h
e
e
f
f
e
c
t
o
f
g
a
mm
a
v
a
l
u
e
o
n
s
u
p
p
o
r
t
v
e
c
t
o
r
ma
c
h
i
n
e
p
e
r
f
o
r
ma
n
c
e
w
i
t
h
d
i
f
f
e
r
e
n
t
k
e
r
n
e
l
s
,
”
I
n
t
e
r
n
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
E
n
g
i
n
e
e
ri
n
g
(
I
J
EC
E)
,
v
o
l
.
1
0
,
n
o
.
5
,
p
p
.
5
4
9
7
-
5
5
0
6
,
O
c
t
.
2
0
2
0
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
c
e
.
v
1
0
i
5
.
p
p
5
4
9
7
-
5
5
0
6
.
[
3
5
]
S
.
U
d
d
i
n
,
I
.
H
a
q
u
e
,
H
.
L
u
,
M
.
A
.
M
o
n
i
,
a
n
d
E
.
G
i
d
e
,
“
C
o
m
p
a
r
a
t
i
v
e
p
e
r
f
o
r
m
a
n
c
e
a
n
a
l
y
s
i
s
o
f
k
-
n
e
a
r
e
s
t
n
e
i
g
h
b
o
u
r
(
K
N
N
)
a
l
g
o
r
i
t
h
m
a
n
d
i
t
s
d
i
f
f
e
r
e
n
t
v
a
r
i
a
n
t
s
f
o
r
d
i
s
e
a
se
p
r
e
d
i
c
t
i
o
n
,
”
S
c
i
e
n
t
i
f
i
c
R
e
p
o
r
t
s
,
v
o
l
.
1
2
,
n
o
.
1
,
A
p
r
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
5
9
8
-
022
-
10358
-
x.
[
3
6
]
C
.
K
a
v
i
t
h
a
,
V
.
M
a
n
i
,
S
.
R
.
S
r
i
v
i
d
h
y
a
,
O
.
I
.
K
h
a
l
a
f
,
a
n
d
C
.
A
.
T
.
R
o
m
e
r
o
,
“
Ea
r
l
y
-
s
t
a
g
e
a
l
z
h
e
i
m
e
r
’
s
d
i
se
a
se
p
r
e
d
i
c
t
i
o
n
u
si
n
g
mac
h
i
n
e
l
e
a
r
n
i
n
g
mo
d
e
l
s,
”
Fr
o
n
t
i
e
rs
i
n
P
u
b
l
i
c
H
e
a
l
t
h
,
v
o
l
.
1
0
,
M
a
r
.
2
0
2
2
,
d
o
i
:
1
0
.
3
3
8
9
/
f
p
u
b
h
.
2
0
2
2
.
8
5
3
2
9
4
.
[
3
7
]
D
.
M
.
W
.
P
o
w
e
r
s,
“
Ev
a
l
u
a
t
i
o
n
:
f
r
o
m
p
r
e
c
i
si
o
n
,
r
e
c
a
l
l
a
n
d
F
-
me
a
su
r
e
t
o
R
O
C
,
i
n
f
o
r
me
d
n
e
ss
,
mark
e
d
n
e
ss
a
n
d
c
o
r
r
e
l
a
t
i
o
n
,
”
a
rXi
v
-
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
p
p
.
1
-
2
7
,
2
0
2
0
.
Evaluation Warning : The document was created with Spire.PDF for Python.