I
AE
S In
t
er
na
t
io
na
l J
o
urna
l o
f
Art
if
icia
l In
t
ellig
ence
(
I
J
-
AI
)
Vo
l.
14
,
No
.
3
,
J
u
n
e
2
0
2
5
,
p
p
.
2102
~
2
1
1
0
I
SS
N:
2
2
5
2
-
8938
,
DOI
: 1
0
.
1
1
5
9
1
/i
j
ai.
v
14
.i
3
.
p
p
2
1
0
2
-
2
1
1
0
2102
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
i
.
ia
esco
r
e.
co
m
A new
w
ra
pper f
ea
ture
selec
tion a
p
pro
a
ch f
o
r binary
ra
nso
m
w
a
re det
ection
O
m
a
r
Cha
ieb
1
,
Na
bil
K
a
nn
o
uf
2
,
M
o
ha
m
m
ed
B
e
na
b
della
h
1
1
A
r
i
t
h
me
t
i
c
,
S
c
i
e
n
t
i
f
i
c
C
o
m
p
u
t
a
t
i
o
n
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
L
a
b
o
r
a
t
o
r
y
,
F
a
c
u
l
t
y
o
f
S
c
i
e
n
c
e
s,
M
o
h
a
me
d
P
r
e
mi
e
r
U
n
i
v
e
r
si
t
y
,
O
u
j
d
a
,
M
o
r
o
c
c
o
2
A
p
p
l
i
e
d
S
c
i
e
n
c
e
s L
a
b
o
r
a
t
o
r
y
,
N
a
t
i
o
n
a
l
S
c
h
o
o
l
o
f
A
p
p
l
i
e
d
S
c
i
e
n
c
e
s,
A
b
d
e
l
mal
e
k
Essa
a
d
i
U
n
i
v
e
r
si
t
y
,
T
e
t
o
u
a
n
,
M
o
r
o
c
c
o
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Feb
1
8
,
2
0
2
4
R
ev
i
s
ed
Feb
1
1
,
2
0
2
5
A
cc
ep
ted
Ma
r
1
5
,
2
0
2
5
Co
n
c
e
rn
s
a
b
o
u
t
ra
n
s
o
m
w
a
r
e
a
tt
a
c
k
s
h
a
v
e
h
e
i
g
h
ten
e
d
in
re
c
e
n
t
y
e
a
r
s
f
o
r
b
o
th
in
d
iv
id
u
a
ls
a
n
d
o
rg
a
n
iza
ti
o
n
s.
De
tec
ti
n
g
th
e
se
m
a
li
c
io
u
s
a
tt
a
c
k
s
p
o
se
s
c
o
n
sid
e
ra
b
le
c
h
a
ll
e
n
g
e
s
f
o
r
c
y
b
e
rse
c
u
rit
y
p
ro
fe
ss
io
n
a
ls,
p
a
rti
c
u
lar
ly
d
u
e
to
th
e
ir
e
v
e
r
-
e
v
o
lv
in
g
n
a
tu
re
.
A
lt
h
o
u
g
h
b
e
h
a
v
io
r
-
b
a
se
d
d
e
tec
ti
o
n
m
e
th
o
d
s
sh
o
w
p
ro
m
ise
in
re
c
o
g
n
izin
g
n
e
w
ra
n
so
m
w
a
re
v
a
rian
ts,
th
e
y
fa
c
e
s
ig
n
if
ica
n
t
h
u
r
d
les
,
e
sp
e
c
iall
y
in
m
a
n
a
g
in
g
t
h
e
m
a
ss
iv
e
v
o
lu
m
e
s
o
f
d
a
ta
g
e
n
e
ra
ted
f
ro
m
re
a
l
-
ti
m
e
m
a
l
w
a
r
e
b
e
h
a
v
io
r
m
o
n
i
to
rin
g
,
lea
d
in
g
to
h
ig
h
d
im
e
n
sio
n
a
li
ty
.
T
h
is
p
a
p
e
r
in
tr
o
d
u
c
e
s
a
n
e
w
f
e
a
tu
re
se
lec
ti
o
n
a
p
p
r
o
a
c
h
sp
e
c
if
ica
ll
y
fo
r
b
i
n
a
ry
ra
n
so
m
w
a
r
e
d
e
tec
ti
o
n
.
Ou
r
m
e
t
h
o
d
e
m
p
h
a
siz
e
s
a
ss
e
ss
in
g
th
e
i
m
p
a
c
t
o
f
f
e
a
tu
re
c
a
te
g
o
ries
o
n
th
e
e
ff
e
c
ti
v
e
n
e
ss
a
n
d
sp
e
e
d
o
f
d
e
tec
ti
o
n
a
lg
o
rit
h
m
s.
It
in
v
o
lv
e
s
tw
o
sta
g
e
s:
th
e
f
irst
sta
g
e
se
lec
ts
th
e
m
o
st
re
lev
a
n
t
g
ro
u
p
s
(c
a
teg
o
ries
)
o
f
fe
a
tu
re
s,
w
h
il
e
th
e
se
c
o
n
d
ra
n
k
s
a
n
d
id
e
n
ti
f
ies
th
e
i
m
p
o
rtan
t
f
e
a
tu
re
s
w
it
h
in
th
o
se
c
a
teg
o
ries
.
Ex
p
e
rim
e
n
tal
re
su
lt
s
in
d
ica
te
th
a
t
o
u
r
a
p
p
ro
a
c
h
s
u
rp
a
ss
e
s
sim
il
a
r
stu
d
ies
re
g
a
rd
in
g
a
c
c
u
ra
c
y
a
n
d
a
b
il
it
y
to
m
in
i
m
ize
th
e
o
rig
in
a
l
f
e
a
tu
re
s
se
t.
M
o
re
o
v
e
r,
b
o
t
h
c
o
m
p
u
tatio
n
sp
e
e
d
a
n
d
a
c
c
u
ra
c
y
a
re
n
o
tab
ly
e
n
h
a
n
c
e
d
wh
e
n
u
si
n
g
th
e
se
lec
ted
su
b
se
t
c
o
m
p
a
re
d
to
th
e
o
rig
in
a
l
f
e
a
tu
re
s.
K
ey
w
o
r
d
s
:
An
o
m
al
y
d
etec
tio
n
B
eh
av
io
r
an
al
y
s
i
s
Featu
r
e
s
elec
t
io
n
Ma
ch
i
n
e
lear
n
i
n
g
R
an
s
o
m
w
ar
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
:
O
m
ar
C
h
aieb
A
r
it
h
m
etic,
Scie
n
ti
f
ic
C
o
m
p
u
t
atio
n
an
d
A
p
p
licatio
n
s
L
ab
o
r
ato
r
y
,
Fac
u
lt
y
o
f
Scie
n
ce
s
Mo
h
a
m
ed
P
r
e
m
ier
Un
i
v
er
s
i
t
y
Ou
j
d
a,
Mo
r
o
cc
o
E
m
ail:
o
m
ar
.
ch
aieb
.
m
e
n
@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
Un
i
v
er
s
al
c
y
b
er
attac
k
s
h
a
v
e
g
r
o
w
n
e
x
p
o
n
en
tia
ll
y
i
n
r
ec
en
t
y
ea
r
s
w
it
h
n
e
w
s
o
p
h
is
ti
ca
ted
an
d
h
ar
d
-
to
-
d
etec
t
c
y
b
er
attac
k
s
s
u
ch
as
m
al
w
ar
e
[
1
]
,
in
s
id
er
att
ac
k
s
[
2
]
,
ad
v
a
n
ce
d
p
er
s
is
te
n
t
th
r
ea
ts
(
A
P
T
s
)
[
3
]
,
an
d
d
is
tr
ib
u
ted
d
en
ial
o
f
s
er
v
ice
(
DDOS
)
attac
k
s
[
4
]
.
Am
o
n
g
all
t
h
ese
d
estr
u
cti
v
e
at
ta
ck
s
,
r
an
s
o
m
w
ar
e
is
co
n
s
id
er
ed
as
o
n
e
o
f
t
h
e
m
o
s
t
d
an
g
er
o
u
s
an
d
h
ar
m
f
u
l
c
y
b
e
r
attac
k
[
5
]
.
T
h
e
s
itu
a
tio
n
b
ec
o
m
e
s
m
o
r
e
s
er
io
u
s
w
h
e
n
attac
k
er
s
ad
o
p
t
th
e
r
an
s
o
m
w
ar
e
-
as
-
a
-
s
er
v
ice
(
R
AAS)
m
o
d
el,
u
s
i
n
g
id
en
titi
e
s
s
to
le
n
f
r
o
m
t
h
e
d
ar
k
w
eb
to
lau
n
c
h
t
h
eir
attac
k
s
[
6
]
,
[
7
]
.
I
n
ad
d
itio
n
,
th
e
n
u
m
b
er
o
f
r
an
s
o
m
w
ar
e
v
icti
m
s
r
ep
o
r
ted
i
n
Ma
r
ch
2
0
2
3
w
as
1
.
6
tim
e
s
h
i
g
h
er
t
h
a
n
t
h
at
i
n
t
h
e
p
ea
k
m
o
n
th
o
f
2
0
2
2
,
p
r
o
v
in
g
th
at
m
a
n
y
c
y
b
er
s
ec
u
r
it
y
p
l
a
y
er
s
w
h
o
b
eliev
ed
th
e
y
h
ad
s
u
cc
ee
d
ed
in
s
to
p
p
in
g
r
an
s
o
m
w
ar
e
attac
k
s
w
er
e
m
i
s
tak
e
n
[
8
]
.
W
e
ca
n
d
ef
in
e
r
an
s
o
m
w
ar
e
as
a
s
p
ec
ial
k
in
d
o
f
m
al
w
ar
e
t
h
a
t
s
ilen
tl
y
e
n
cr
y
p
t
s
a
v
icti
m
's
d
ata
o
r
lo
ck
d
o
w
n
th
e
s
y
s
te
m
i
n
o
r
d
er
to
s
t
o
p
th
e
v
ic
ti
m
f
r
o
m
u
s
i
n
g
it
[
9
]
.
Af
ter
w
ar
d
s
,
t
h
e
attac
k
er
s
r
eq
u
est
th
at
th
e
v
icti
m
p
ay
s
a
r
an
s
o
m
in
d
ig
ital
cu
r
r
en
c
y
s
o
th
at
h
e
ca
n
g
e
t
h
is
d
ata
b
ac
k
.
L
ik
e
m
o
s
t
m
a
licio
u
s
p
r
o
g
r
a
m
s
,
r
an
s
o
m
w
ar
e
ca
n
b
e
co
n
tain
ed
th
r
o
u
g
h
t
w
o
m
a
in
m
ea
s
u
r
e
s
:
d
etec
tio
n
a
n
d
p
r
ev
en
t
io
n
.
O
f
t
h
e
t
w
o
ap
p
r
o
ac
h
es,
d
etec
tio
n
is
m
o
r
e
e
f
f
ec
t
iv
e
[
1
0
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
A
r
ti
f
I
n
tell
I
SS
N:
2252
-
8938
A
n
ew w
r
a
p
p
er fea
tu
r
e
s
elec
ti
o
n
a
p
p
r
o
a
ch
fo
r
b
in
a
r
y
r
a
n
s
o
mw
a
r
e
d
etec
tio
n
(
Oma
r
C
h
a
ieb
)
2103
Fu
r
th
e
r
m
o
r
e
,
w
h
en
it
co
m
es
to
v
ar
ian
ts
an
d
s
teal
th
y
attac
k
s
lik
e
r
an
s
o
m
w
ar
e,
m
ac
h
in
e
lea
r
n
in
g
(
ML
)
tech
n
i
q
u
es
ca
n
s
u
r
p
ass
s
ev
e
r
a
l
lim
itatio
n
s
s
h
o
w
n
b
y
s
ig
n
atu
r
e
-
b
ase
d
d
et
ec
ti
o
n
m
eth
o
d
s
[
1
1
]
b
y
s
u
cc
ess
f
u
lly
ex
p
l
o
it
in
g
ad
v
an
c
ed
ca
p
a
b
il
iti
es
s
u
ch
as
b
y
teco
d
es
,
A
P
I
in
v
o
ca
ti
o
n
s
[
1
2
]
an
d
b
eh
av
i
o
r
al
r
ep
o
r
tin
g
ex
t
r
ac
te
d
th
r
o
u
g
h
s
ta
tic
o
r
d
y
n
a
m
ic
m
al
w
ar
e
an
aly
s
is
[
1
3
]
,
[
1
4
]
.
H
o
w
ev
er
,
d
u
e
t
o
th
e
la
r
g
e
am
o
u
n
t
o
f
d
ata
c
o
n
tain
e
d
i
n
b
eh
av
i
o
r
-
b
ase
d
r
an
s
o
m
w
ar
e
d
atas
ets,
ML
alg
o
r
ith
m
s
ar
e
n
o
t
g
o
o
d
at
p
r
e
d
i
ctin
g
w
h
eth
er
a
n
ev
en
t
is
a
n
o
r
m
al
o
r
m
alici
o
u
s
ac
tiv
ity
[
1
5
]
.
F
o
r
th
is
r
ea
s
o
n
,
f
ea
tu
r
e
s
el
ec
t
io
n
(
FS
)
m
eth
o
d
s
a
r
e
u
s
e
d
to
d
ec
r
ea
s
e
th
e
v
o
lu
m
e
o
f
d
at
a
b
y
r
em
o
v
in
g
ir
r
el
ev
an
t
f
e
atu
r
es t
o
en
h
an
c
e
th
e
ef
f
icien
c
y
o
f
ML
alg
o
r
ith
m
s
[
1
6
]
,
[
1
7
]
.
T
h
e
is
s
u
e
s
tate
m
e
n
t
i
n
th
i
s
r
esear
ch
s
tu
d
y
is
t
h
at
as
r
an
s
o
m
w
ar
e
attac
k
s
ar
e
d
estru
cti
v
e
an
d
ir
r
ev
er
s
ib
le,
th
e
y
n
ee
d
to
b
e
d
etec
ted
q
u
ick
l
y
an
d
e
f
f
ec
tiv
el
y
.
B
esid
es,
ta
k
in
g
i
n
to
co
n
s
id
er
atio
n
th
at
l
ar
g
e
d
atasets
li
m
i
t
t
h
e
p
er
f
o
r
m
a
n
c
e
o
f
M
L
-
b
ased
s
o
l
u
tio
n
s
,
es
p
ec
iall
y
w
h
e
n
d
ata
co
m
e
s
f
r
o
m
b
eh
a
v
io
r
-
b
ased
m
al
w
ar
e
an
al
y
s
is
.
B
y
e
m
p
lo
y
in
g
a
n
e
w
w
r
ap
p
er
-
b
ased
FS
tech
n
iq
u
e
to
d
ec
r
ea
s
e
th
e
v
o
l
u
m
e
o
f
th
e
o
r
ig
i
n
al
d
ataset,
th
e
m
ai
n
o
b
j
ec
tiv
e
o
f
th
is
w
o
r
k
is
e
nh
an
ci
n
g
r
esp
o
n
s
i
v
e
n
ess
,
ac
c
u
r
ac
y
,
a
n
d
s
p
ee
d
o
f
class
i
f
icatio
n
alg
o
r
ith
m
.
W
e
h
y
p
o
th
esized
th
a
t
ch
o
o
s
i
n
g
t
h
e
m
o
s
t
r
ele
v
an
t
f
ea
t
u
r
es
ca
teg
o
r
ies
w
h
ile
i
g
n
o
r
i
n
g
o
t
h
er
s
w
o
u
ld
ca
s
t
a
s
h
ad
o
w
o
v
er
t
h
e
p
er
f
o
r
m
an
ce
a
n
d
s
p
ee
d
o
f
th
e
ML
al
g
o
r
ith
m
s
.
T
o
v
alid
ate
th
is
h
y
p
o
th
esi
s
,
w
e
s
u
g
g
e
s
t
a
n
e
w
ap
p
r
o
ac
h
f
o
r
ev
al
u
ati
n
g
t
h
e
ef
f
icac
y
o
f
d
is
ti
n
ct
f
e
atu
r
e
g
r
o
u
p
s
(
ca
teg
o
r
ies),
an
d
th
en
w
e
b
u
ilt
a
n
o
p
tim
a
l
s
et
co
n
tai
n
i
n
g
t
h
e
m
o
s
t
r
elev
an
t
f
ea
t
u
r
es
f
r
o
m
s
ele
cted
g
r
o
u
p
s
.
T
h
e
p
r
o
p
o
s
ed
m
eth
o
d
in
clu
d
e
s
t
w
o
s
tag
e
s
:
t
h
e
f
ir
s
t
i
s
d
ev
o
te
d
to
s
elec
t
t
h
e
m
o
s
t
p
er
tin
e
n
t
g
r
o
u
p
o
f
f
ea
t
u
r
es,
an
d
t
h
e
s
ec
o
n
d
is
d
ed
icate
d
to
r
an
k
an
d
s
elec
t
t
h
e
r
elev
a
n
t
f
ea
tu
r
e
s
w
ith
in
t
h
e
ch
o
s
en
g
r
o
u
p
s
.
Ad
d
itio
n
all
y
,
w
h
en
d
o
in
g
tr
a
f
f
i
c
b
eh
av
io
r
an
al
y
s
i
s
an
d
s
u
b
s
eq
u
e
n
t
v
ar
iab
le
e
x
tr
a
ctio
n
,
t
h
is
n
e
w
g
r
o
u
p
-
b
ased
f
e
a
tu
r
e
r
ed
u
ctio
n
tec
h
n
iq
u
e
w
ill
en
ab
le
u
s
to
f
o
cu
s
o
n
l
y
o
n
t
h
e
m
o
s
t c
r
u
cial
f
ea
t
u
r
e
ca
teg
o
r
ies an
d
d
is
m
is
s
th
o
s
e
th
at
ar
e
less
i
m
p
o
r
tan
t.
T
h
is
ar
ticle
is
d
iv
id
ed
in
to
f
iv
e
s
ec
tio
n
s
:
s
ec
tio
n
2
g
i
v
es
b
ac
k
g
r
o
u
n
d
in
f
o
r
m
atio
n
a
n
d
ev
alu
ate
s
r
elate
d
liter
atu
r
e.
T
h
e
m
et
h
o
d
o
lo
g
y
is
h
i
g
h
l
ig
h
ted
in
s
ec
tio
n
3
.
R
esu
lt
s
an
d
d
is
c
u
s
s
io
n
ar
e
s
h
o
w
n
in
s
ec
tio
n
4
.
C
o
n
cl
u
s
io
n
s
a
n
d
u
p
co
m
i
n
g
p
r
o
j
ec
ts
ar
e
c
o
v
er
ed
in
th
e
f
in
al
p
ar
t.
2.
RE
L
AT
E
D
WO
RK
S
T
h
is
s
ec
tio
n
p
r
o
v
id
es
s
o
m
e
b
ac
k
g
r
o
u
n
d
in
f
o
r
m
at
io
n
an
d
r
elate
d
w
o
r
k
s
.
W
e
f
ir
s
t
h
ig
h
li
g
h
t
th
e
d
if
f
er
e
n
t
t
y
p
e
s
o
f
r
a
n
s
o
m
w
ar
e
attac
k
s
,
d
etec
tio
n
tec
h
n
iq
u
es,
ML
a
n
d
FS
ap
p
r
o
ac
h
u
s
ed
to
i
m
p
r
o
v
e
d
etec
tio
n
.
T
h
en
,
w
e
w
il
l g
i
v
e
a
s
tate
o
f
ar
t o
f
r
an
s
o
m
w
ar
e
d
etec
tio
n
an
d
FS
ap
p
r
o
ac
h
es f
o
r
d
ata
w
it
h
h
ig
h
d
i
m
en
s
io
n
s
.
2
.
1
.
T
y
pes
o
f
r
a
ns
o
m
w
a
re
s
W
e
ca
n
class
i
f
y
r
a
n
s
o
m
w
ar
e
b
ased
o
n
a
v
ar
iet
y
o
f
f
ac
to
r
s
,
s
u
c
h
as
th
eir
m
et
h
o
d
o
f
en
cr
y
p
t
io
n
an
d
h
o
w
t
h
e
y
ar
e
ca
r
r
ied
o
u
t.
R
an
s
o
m
w
ar
e
attac
k
s
ca
n
b
e
b
r
o
ad
ly
d
i
v
id
ed
in
to
th
r
ee
t
y
p
e
s
:
s
ca
r
e
w
ar
e,
lo
ck
er
r
an
s
o
m
w
ar
e
,
an
d
cr
y
p
to
-
r
an
s
o
m
w
ar
e.
Scar
e
w
ar
e
e
m
p
lo
y
es
t
ec
h
n
iq
u
es
s
u
ch
a
s
s
o
cial
en
g
i
n
ee
r
in
g
o
r
p
h
i
s
h
in
g
to
tr
ick
v
ic
ti
m
s
i
n
to
p
r
o
v
id
in
g
v
al
u
ab
le
i
n
f
o
r
m
atio
n
,
p
u
r
ch
asi
n
g
,
o
r
d
o
w
n
lo
ad
in
g
d
an
g
er
o
u
s
s
o
f
t
w
ar
e.
I
t
m
o
s
tl
y
s
er
v
e
s
f
o
r
co
llectin
g
d
ata
an
d
d
is
p
la
y
s
w
ar
n
in
g
m
e
s
s
ag
es
to
aler
t
y
o
u
th
at
y
o
u
r
d
ev
ice
is
th
e
s
u
b
j
ec
t o
f
an
attac
k
[
1
8
]
.
L
o
ck
er
-
r
an
s
o
m
w
ar
e,
w
h
ic
h
d
o
es
n
o
t
a
f
f
ec
t
d
ata
b
u
t
p
r
ev
e
n
ts
u
s
er
s
f
r
o
m
u
s
in
g
t
h
eir
s
y
s
te
m
b
y
d
is
p
la
y
i
n
g
p
o
p
-
u
p
w
i
n
d
o
w
s
t
h
at
n
e
v
er
clo
s
e
o
r
b
y
lo
c
k
in
g
th
eir
d
esk
to
p
[
1
0
]
,
[
1
9
]
.
C
r
y
p
to
-
r
an
s
o
m
w
ar
e
i
s
r
eg
ar
d
ed
as
o
n
e
o
f
th
e
m
o
s
t
d
an
g
er
o
u
s
r
an
s
o
m
w
ar
es,
it
e
n
cr
y
p
t
s
f
ile
s
o
n
t
h
e
v
icti
m
's
d
ev
ic
e
an
d
r
en
d
er
s
t
h
e
m
u
s
ele
s
s
b
y
e
m
p
lo
y
i
n
g
p
o
w
er
f
u
l e
n
cr
y
p
tio
n
al
g
o
r
ith
m
s
th
at
ar
e
d
if
f
ic
u
lt to
d
etec
t
[
2
0
]
,
[
2
1
]
.
2
.
2
.
Ra
ns
o
m
w
a
re
det
ec
t
io
n
a
pp
ro
a
ches
T
o
r
ed
u
ce
th
e
r
is
k
o
f
r
an
s
o
m
w
ar
e
attac
k
s
,
w
e
m
ig
h
t
u
s
e
eith
er
a
p
r
ev
en
tativ
e
o
r
a
d
etec
tio
n
ap
p
r
o
ac
h
[
2
2
]
.
T
h
e
f
ir
s
t
s
ee
k
s
to
p
r
ev
en
t
r
a
n
s
o
m
w
ar
e
d
am
ag
e
b
e
f
o
r
e
it
o
cc
u
r
s
b
y
i
m
p
o
s
in
g
s
tr
o
n
g
ac
ce
s
s
co
n
tr
o
ls
[2
3
]
,
[
2
4
]
,
s
ec
u
r
in
g
d
ata
an
d
p
ass
w
o
r
d
s
an
d
b
o
o
s
tin
g
u
s
er
a
w
ar
en
es
s
[
2
5
]
w
h
er
ea
s
th
e
s
ec
o
n
d
tr
ai
n
an
d
test
a
d
etec
tio
n
m
o
d
el
u
tili
zi
n
g
h
is
to
r
ical
d
ata
a
n
d
s
ig
n
at
u
r
es
f
r
o
m
p
r
ev
io
u
s
at
t
ac
k
s
.
Fu
r
t
h
er
m
o
r
e,
d
y
n
a
m
ic
a
n
al
y
s
i
s
ca
n
b
e
u
s
e
d
as
a
d
etec
tio
n
to
o
l
to
lo
ca
t
e
r
an
s
o
m
w
ar
e
b
y
e
x
a
m
in
in
g
th
e
b
eh
a
v
io
r
o
f
th
e
m
al
w
ar
e
w
h
ile
it
is
r
u
n
n
in
g
,
o
r
s
tatic
a
n
al
y
s
i
s
to
d
etec
t
r
a
n
s
o
m
w
ar
e
b
y
an
a
l
y
zi
n
g
t
h
e
c
o
n
ten
t
s
o
f
b
i
n
ar
ies
w
it
h
o
u
t
r
u
n
n
i
n
g
th
e
s
o
f
t
w
ar
e
[
2
6
]
.
Ho
w
e
v
er
,
b
ec
au
s
e
h
u
m
a
n
lo
g
m
o
n
i
to
r
in
g
ta
k
es
ti
m
e
an
d
s
p
ec
i
f
ic
k
n
o
w
led
g
e,
d
ata
g
at
h
er
ed
d
u
r
in
g
s
tat
ic
o
r
d
y
n
a
m
ic
a
n
al
y
s
i
s
s
u
c
h
as
n
et
w
o
r
k
tr
af
f
ic
a
n
d
A
P
I
in
v
o
ca
tio
n
s
ar
e
u
s
ed
to
f
ee
d
ML
alg
o
r
it
h
m
s
.
ML
tec
h
n
iq
u
e
s
m
a
y
o
v
er
co
m
e
s
e
v
er
al
l
i
m
its
o
f
s
ig
n
at
u
r
e
-
ba
s
ed
d
etec
tio
n
ap
p
r
o
ac
h
e
s
,
h
o
w
e
v
er
g
iv
e
n
t
h
at
ML
alg
o
r
it
h
m
s
ar
e
r
ec
o
g
n
ized
f
o
r
lear
n
in
g
f
r
o
m
p
r
ev
io
u
s
d
ata,
th
is
d
ata
n
e
ed
s
to
b
e
p
r
ep
ar
e
d
b
ef
o
r
e
u
s
i
n
g
it,
it
is
cr
u
cial
to
clea
n
,
n
o
r
m
alize
,
an
d
f
ilter
t
h
e
d
ata.
On
e
o
f
t
h
e
m
o
s
t
i
m
p
o
r
ta
n
t
m
eth
o
d
s
d
u
r
in
g
th
e
d
ata
p
r
ep
ar
atio
n
p
h
ase
is
th
e
FS
[
1
6
]
,
[
2
7
]
.
T
h
is
tech
n
iq
u
e
ca
n
b
e
d
iv
id
ed
in
to
f
ilter
an
d
w
r
ap
p
er
.
R
eg
ar
d
les
s
o
f
t
h
e
d
ata
m
o
d
el
in
g
al
g
o
r
ith
m
e
m
p
lo
y
ed
,
t
h
e
f
o
r
m
er
c
h
o
o
s
es
f
ea
t
u
r
es
b
ase
d
o
n
p
er
f
o
r
m
a
n
ce
m
ea
s
u
r
e
m
e
n
t,
w
h
er
ea
s
t
h
e
la
tter
s
elec
ts
t
h
e
r
ele
v
an
t
f
ea
t
u
r
es
b
y
ev
al
u
ati
n
g
t
h
eir
p
er
f
o
r
m
an
ce
t
h
r
o
u
g
h
a
lear
n
in
g
al
g
o
r
ith
m
[
2
8
]
.
I
n
th
is
s
t
u
d
y
,
to
s
o
lv
e
th
e
FS
p
r
o
b
le
m
f
o
r
h
i
g
h
-
d
i
m
e
n
s
io
n
al
d
ata,
w
e
co
m
b
in
e
t
h
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
I
n
t J
A
r
ti
f
I
n
tell
,
Vo
l.
14
,
No
.
3
,
J
u
n
e
2
0
2
5
:
2
1
0
2
-
2110
2104
b
est
p
r
o
p
e
r
ties
o
f
f
ilter
s
an
d
w
r
ap
p
er
s
b
y
u
s
i
n
g
f
ea
t
u
r
e
g
r
o
u
p
-
b
ased
h
y
b
r
id
tech
n
iq
u
es
to
ac
h
iev
e
h
ig
h
ac
cu
r
ac
y
a
n
d
h
i
g
h
s
p
ee
d
t
y
p
ic
al
o
f
w
r
ap
p
er
s
,
i.e
.
,
f
ilter
s
c
h
ar
ac
ter
is
tics
.
2
.
3
.
Rela
t
ed
wo
rk
s
Sg
a
n
d
u
r
r
a
et
a
l.
[
2
9
]
p
r
o
p
o
s
ed
a
n
o
v
el
m
et
h
o
d
n
a
m
ed
E
ld
eRan
to
id
en
tify
k
e
y
d
y
n
a
m
i
c
ch
ar
ac
ter
is
tic
s
o
f
r
an
s
o
m
w
ar
e,
w
h
ic
h
ar
e
th
en
u
s
ed
f
o
r
r
an
s
o
m
w
ar
e
d
etec
tio
n
.
T
h
e
m
eth
o
d
co
n
s
is
ted
o
f
t
w
o
co
m
p
o
n
e
n
t
s
:
m
o
n
ito
r
in
g
an
d
a
ML
p
r
o
ce
s
s
.
T
h
e
f
ir
s
t
co
m
p
o
n
en
t
d
y
n
a
m
icall
y
a
n
al
y
ze
d
tr
ac
es
o
f
s
a
m
p
les
f
r
o
m
t
w
o
d
ataset
s
in
a
s
a
n
d
b
o
x
en
v
ir
o
n
m
e
n
t:
r
a
n
s
o
m
w
ar
e
an
d
g
o
o
d
w
ar
e.
Fro
m
t
h
ese
r
ec
o
r
d
s
,
E
ld
eRan
r
etr
iev
ed
an
d
p
ar
s
ed
s
e
v
en
f
u
n
ctio
n
al
clas
s
es
(
W
in
d
o
w
s
AP
I
ca
lls
,
d
elete
d
f
iles
,
a
n
d
d
ir
ec
to
r
y
o
p
er
atio
n
s
)
.
T
h
e
ML
p
ar
t c
o
n
s
is
ted
o
f
t
w
o
s
tag
e
s
: F
S a
n
d
clas
s
i
f
icatio
n
.
Fo
r
FS
,
t
h
e
a
u
th
o
r
s
u
s
ed
m
u
t
u
al
in
f
o
r
m
at
io
n
(
MI
)
as
a
f
ilter
-
b
ased
FS
tec
h
n
iq
u
e
.
Fo
r
class
if
icatio
n
is
s
u
es,
E
l
d
eRan
u
s
ed
a
lo
g
is
tic
r
eg
r
es
s
io
n
(
L
R
)
clas
s
i
f
ier
.
Fu
r
t
h
er
m
o
r
e,
th
e
a
u
t
h
o
r
s
co
m
p
ar
ed
th
e
ac
cu
r
ac
y
o
f
L
R
al
g
o
r
ith
m
to
t
h
at
o
f
o
t
h
er
M
L
a
lg
o
r
ith
m
s
,
s
u
c
h
a
s
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
s
(
SV
M)
an
d
n
ai
v
e
B
a
y
es
(
NB
)
.
T
h
e
s
u
g
g
es
t
ed
m
et
h
o
d
p
er
f
o
r
m
s
w
ell
o
v
er
NB
an
d
r
iv
als
SV
M.
Mo
r
eo
v
er
,
as
th
e
au
th
o
r
s
m
en
t
io
n
ed
,
MI
alg
o
r
ith
m
h
as
p
r
o
v
en
to
b
e
a
p
o
w
er
f
u
l
m
et
h
o
d
f
o
r
au
to
m
at
ic
F
S
p
r
o
ce
s
s
.
Ho
w
ev
er
,
th
is
m
et
h
o
d
r
eq
u
ir
ed
a
p
r
es
et
n
u
m
b
er
o
f
f
ea
tu
r
e
s
to
b
e
s
el
ec
ted
as
i
n
p
u
t
,
a
n
d
u
s
e
s
th
e
en
tire
d
ataset
as
a
s
tar
tin
g
p
o
in
t
w
h
en
p
er
f
o
r
m
in
g
FS
in
s
tead
o
f
k
ee
p
in
g
o
n
l
y
th
e
m
o
s
t
r
elev
a
n
t
g
r
o
u
p
s
o
f
f
ea
t
u
r
es,
w
h
ic
h
w
e
ass
u
m
e
w
ill
in
cr
ea
s
e
th
e
p
er
f
o
r
m
a
n
ce
o
f
v
alid
atio
n
al
g
o
r
ith
m
s
.
F
u
r
t
h
er
m
o
r
e,
au
th
o
r
s
d
id
n
’
t
co
m
p
ar
e
th
e
r
esu
lt
s
o
b
tain
ed
u
s
i
n
g
s
elec
te
d
f
ea
tu
r
es
w
it
h
th
e
o
r
ig
i
n
al
f
ea
tu
r
es
in
ter
m
s
o
f
a
cc
u
r
ac
y
a
n
d
p
r
o
ce
s
s
in
g
t
i
m
e.
A
b
b
asi
et
a
l.
[
3
0
]
p
r
o
p
o
s
ed
an
au
to
m
atic
w
r
ap
p
er
-
b
ased
FS
ap
p
r
o
ac
h
f
o
r
b
eh
a
v
io
r
-
b
ased
r
an
s
o
m
w
ar
e
d
etec
tio
n
.
T
h
is
ap
p
r
o
ac
h
u
s
ed
a
n
e
w
g
r
o
u
p
-
b
a
s
ed
s
tr
ateg
y
to
ad
d
r
ess
th
e
i
s
s
u
e
o
f
d
ata
w
it
h
h
ig
h
d
i
m
en
s
io
n
.
T
h
e
s
tr
en
g
t
h
o
f
th
is
tech
n
iq
u
e
i
s
th
at,
u
n
l
ik
e
t
h
e
f
ilter
m
et
h
o
d
u
s
ed
in
[
2
9
]
,
it
d
id
n
’
t
u
s
e
a
p
r
eset
a
m
o
u
n
t
o
f
f
ea
tu
r
es
to
b
e
s
elec
ted
as
in
p
u
t.
F
u
r
th
er
m
o
r
e,
to
il
lu
s
tr
ate
th
e
in
f
l
u
en
ce
o
f
ea
c
h
f
ea
tu
r
e
ca
teg
o
r
y
o
n
class
i
f
icatio
n
ac
cu
r
ac
y
,
th
e
y
u
s
ed
a
g
r
o
u
p
-
o
r
ien
ted
s
tr
ateg
y
co
n
s
is
tin
g
o
f
t
w
o
s
tag
e
s
.
Usi
n
g
th
e
MI
alg
o
r
ith
m
as
a
f
ea
t
u
r
e
r
an
k
i
n
g
tech
n
iq
u
e,
a
s
i
m
ilar
a
m
o
u
n
t
o
f
th
e
b
e
s
t
-
r
a
n
k
ed
f
ea
t
u
r
es
is
c
h
o
s
e
n
f
r
o
m
ev
er
y
f
ea
t
u
r
e
ca
teg
o
r
y
i
n
th
e
f
ir
s
t
s
ta
g
e.
W
h
ile
i
n
th
e
s
ec
o
n
d
s
ta
g
e,
a
w
r
ap
p
er
-
b
ased
FS
m
et
h
o
d
is
u
ti
lized
to
ch
o
o
s
e
an
id
ea
l
n
u
m
b
er
o
f
r
elev
a
n
t
f
ea
t
u
r
es
f
r
o
m
ev
er
y
ca
te
g
o
r
y
u
s
i
n
g
b
o
th
L
R
an
d
p
ar
ticle
s
w
ar
m
o
p
tim
izatio
n
(
P
SO)
alg
o
r
ith
m
s
.
T
o
av
o
id
o
v
er
f
it
ti
n
g
,
th
is
m
et
h
o
d
u
s
ed
t
h
e
L
R
as
a
w
r
ap
p
ed
alg
o
r
ith
m
d
u
r
i
n
g
t
h
e
F
S
p
r
o
ce
s
s
,
w
h
ile
t
h
e
y
u
s
ed
o
th
er
al
g
o
r
ith
m
s
s
u
c
h
a
s
SVM,
K
-
n
ea
r
est
n
eig
h
b
o
r
(
KNN
)
,
r
an
d
o
m
f
o
r
est
(
RF
)
,
an
d
d
ec
is
i
o
n
tr
ee
(
DT
)
to
ev
alu
ate
t
h
e
g
en
er
aliza
b
ilit
y
o
f
t
h
e
s
e
lecte
d
f
ea
tu
r
es.
A
l
th
o
u
g
h
t
h
e
a
u
t
h
o
r
s
m
a
n
ag
ed
to
f
u
ll
y
au
to
m
ate
t
h
e
p
r
o
ce
s
s
o
f
v
a
r
iab
le
s
elec
tio
n
in
t
h
is
m
et
h
o
d
,
th
e
n
u
m
b
er
o
f
v
ar
iab
l
es
s
elec
ted
in
[
2
9
]
(
4
0
0
f
ea
tu
r
es)
w
a
s
less
t
h
an
i
n
th
is
m
et
h
o
d
(
8
2
3
s
elec
ted
f
ea
tu
r
es),
an
d
if
th
i
s
d
o
es
n
o
t
af
f
e
ct
th
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
alg
o
r
it
h
m
,
th
e
n
d
o
in
g
s
o
w
ill
d
ef
i
n
itel
y
a
f
f
ec
t
t
h
e
r
es
p
o
n
s
e
ti
m
e,
w
h
ich
is
in
to
ler
ab
le
w
h
e
n
it
co
m
es
to
r
an
s
o
m
w
ar
e
d
etec
tio
n
.
I
n
ad
d
i
tio
n
,
th
e
m
et
h
o
d
u
s
ed
th
e
e
n
tir
e
d
ataset
as
a
s
tar
tin
g
p
o
in
t
wh
en
p
er
f
o
r
m
in
g
FS
in
s
tead
o
f
k
ee
p
i
n
g
o
n
l
y
th
e
m
o
s
t
r
elev
a
n
t
g
r
o
u
p
s
o
f
f
ea
tu
r
e
s
,
w
h
ic
h
w
e
a
s
s
u
m
e
w
il
l
i
n
cr
ea
s
e
t
h
e
p
er
f
o
r
m
an
ce
o
f
d
etec
tio
n
alg
o
r
ith
m
.
Fu
r
t
h
e
r
m
o
r
e,
au
th
o
r
s
d
id
n
’
t
co
m
p
ar
e
th
e
r
esu
lt
s
o
b
tain
ed
u
s
i
n
g
s
el
ec
ted
f
ea
tu
r
es
w
it
h
th
e
o
r
ig
i
n
al
f
ea
tu
r
es i
n
ter
m
s
o
f
ac
cu
r
ac
y
a
n
d
p
r
o
ce
s
s
in
g
ti
m
e.
3.
M
E
T
H
O
D
Star
tin
g
w
it
h
t
h
e
g
r
o
u
p
-
b
ased
s
tr
ateg
y
f
o
r
FS
ad
o
p
ted
b
y
[
3
0
]
,
w
h
ic
h
s
h
o
w
ed
t
h
at
i
n
d
iv
id
u
al
f
ea
tu
r
e
g
r
o
u
p
s
h
av
e
a
s
ig
n
i
f
ica
n
t
i
n
f
l
u
en
ce
o
n
th
e
c
lass
if
ica
tio
n
p
e
r
f
o
r
m
an
ce
.
W
e
as
s
u
m
ed
t
h
at
ch
o
o
s
in
g
t
h
e
m
o
s
t
r
elev
an
t
f
ea
t
u
r
e
g
r
o
u
p
s
w
h
ile
i
g
n
o
r
i
n
g
o
t
h
er
s
w
o
u
ld
ca
s
t a
s
h
ad
o
w
o
v
er
th
e
p
er
f
o
r
m
a
n
ce
an
d
s
p
ee
d
o
f
th
e
M
L
alg
o
r
ith
m
.
T
o
v
alid
ate
th
is
h
y
p
o
t
h
esi
s
,
w
e
s
u
g
g
est
a
n
e
w
ap
p
r
o
ac
h
f
o
r
ev
alu
ati
n
g
th
e
ef
f
icac
y
o
f
d
is
tin
c
t
f
ea
t
u
r
e
g
r
o
u
p
s
,
an
d
th
e
n
w
e
b
u
ilt
a
n
o
p
ti
m
al
s
et
co
n
tai
n
in
g
t
h
e
m
o
s
t
r
elev
a
n
t
f
ea
t
u
r
e
s
f
r
o
m
ch
o
s
e
n
g
r
o
u
p
s
.
T
h
e
FS
ap
p
r
o
ac
h
ad
o
p
te
d
in
o
u
r
p
ap
er
is
d
iv
id
ed
in
to
t
w
o
d
if
f
er
e
n
t
s
ta
g
e
s
.
T
h
e
f
ir
s
t
s
tag
e
ai
m
s
to
r
an
k
a
n
d
s
elec
t
th
e
m
o
s
t
r
ele
v
an
t
f
ea
t
u
r
e
ca
teg
o
r
y
u
s
in
g
L
R
a
s
an
e
v
alu
atio
n
al
g
o
r
ith
m
w
h
ile
t
h
e
s
ec
o
n
d
o
n
e
co
n
s
is
t
s
o
f
r
an
k
in
g
an
d
t
h
e
n
s
elec
ti
n
g
an
eq
u
al
n
u
m
b
er
o
f
t
h
e
m
o
s
t s
ig
n
if
ican
t
f
ea
t
u
r
es
f
r
o
m
ea
ch
c
ateg
o
r
y
.
E
ac
h
s
tag
e
w
il
l
b
e
co
m
p
o
s
ed
o
f
t
w
o
d
i
f
f
e
r
en
t
p
h
ase
s
,
o
n
e
f
o
r
t
h
e
r
an
k
i
n
g
an
d
t
h
e
o
th
er
f
o
r
t
h
e
s
elec
t
io
n
.
T
h
e
p
r
o
ce
s
s
o
f
o
u
r
m
et
h
o
d
is
p
r
esen
ted
in
Fi
g
u
r
e
1.
3
.
1
.
St
a
g
e
1
:
c
a
t
e
g
o
ry
ra
nk
i
ng
a
nd
s
elec
t
io
n
T
h
is
s
tep
o
f
t
h
e
ap
p
r
o
ac
h
is
d
iv
id
ed
in
to
t
w
o
p
ar
ts
:
o
n
e
w
il
l
b
e
d
ed
icate
d
to
r
an
k
f
ea
t
u
r
e
g
r
o
u
p
s
,
an
d
th
e
o
th
er
to
th
e
s
elec
tio
n
o
f
f
e
atu
r
e
g
r
o
u
p
s
.
R
a
n
k
i
n
g
f
ea
t
u
r
e
g
r
o
u
p
s
in
v
o
l
v
es
ap
p
l
y
i
n
g
t
h
e
L
R
m
et
h
o
d
to
ea
ch
g
r
o
u
p
i
n
d
iv
id
u
all
y
to
clas
s
i
f
y
th
e
m
f
r
o
m
t
h
e
ca
te
g
o
r
y
w
it
h
t
h
e
h
ig
h
e
s
t p
er
f
o
r
m
a
n
ce
to
th
e
o
n
e
w
it
h
t
h
e
lo
w
e
s
t
s
co
r
e.
Af
ter
al
l
g
r
o
u
p
s
h
a
v
e
b
ee
n
r
ated
,
th
e
L
R
alg
o
r
it
h
m
w
ill
b
e
ap
p
lied
ag
ai
n
,
b
u
t
t
h
is
ti
m
e
o
n
g
r
o
u
p
s
u
b
s
et
s
,
s
tar
ti
n
g
w
it
h
t
h
e
s
u
b
s
et
co
m
p
r
is
i
n
g
t
h
e
t
w
o
b
es
t
-
r
an
k
ed
g
r
o
u
p
s
o
b
tain
ed
i
n
p
h
ase
1
.
Du
r
i
n
g
ea
c
h
iter
atio
n
,
a
n
e
w
g
r
o
u
p
is
ad
d
e
d
to
th
e
s
u
b
s
et
o
f
g
r
o
u
p
s
w
h
il
e
m
ai
n
tai
n
i
n
g
th
e
r
an
k
in
g
o
b
tain
ed
d
u
r
in
g
th
e
f
ir
s
t
p
h
ase,
th
e
n
th
e
n
e
w
g
e
n
er
at
ed
s
u
b
s
et
is
ev
al
u
ated
u
s
in
g
th
e
L
R
alg
o
r
it
h
m
.
I
n
ad
d
iti
o
n
,
to
m
ea
s
u
r
e
th
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
A
r
ti
f
I
n
tell
I
SS
N:
2252
-
8938
A
n
ew w
r
a
p
p
er fea
tu
r
e
s
elec
ti
o
n
a
p
p
r
o
a
ch
fo
r
b
in
a
r
y
r
a
n
s
o
mw
a
r
e
d
etec
tio
n
(
Oma
r
C
h
a
ieb
)
2105
ef
f
ec
tiv
e
n
e
s
s
o
f
ea
ch
s
u
b
-
s
et
o
f
g
r
o
u
p
s
,
th
e
L
R
alg
o
r
ith
m
w
il
l
b
e
u
s
ed
as
a
w
r
ap
p
er
alg
o
r
ith
m
to
s
elec
t
t
h
e
b
est
s
u
b
-
s
et.
Fo
r
t
h
e
r
e
m
ai
n
i
n
g
p
h
a
s
es
o
f
t
h
e
p
r
o
ce
s
s
,
o
n
l
y
g
r
o
u
p
s
b
elo
n
g
in
g
to
th
e
s
elec
ted
s
u
b
-
s
et
a
n
d
p
r
o
v
id
ed
th
e
b
est r
esu
lt
w
ill b
e
p
r
e
s
er
v
ed
.
Fig
u
r
e
1
.
An
o
v
er
v
ie
w
o
f
th
e
p
r
o
p
o
s
ed
m
et
h
o
d
3
.
2
.
St
a
g
e
2
:
ind
iv
idu
a
l f
ea
t
ure
ra
n
k
ing
a
nd
s
elec
t
io
n
T
h
e
in
d
iv
id
u
al
f
ea
tu
r
e
r
an
k
i
n
g
en
tail
s
in
d
i
v
id
u
a
ll
y
r
an
k
i
n
g
f
ea
tu
r
es
b
ased
o
n
th
e
ir
r
elev
an
ce
u
s
in
g
th
e
MI
alg
o
r
ith
m
a
s
a
f
ea
t
u
r
e
r
an
k
i
n
g
m
et
h
o
d
f
o
r
ea
c
h
p
r
ev
io
u
s
l
y
s
elec
ted
g
r
o
u
p
.
I
n
o
u
r
ca
s
e,
th
e
class
i
f
icatio
n
is
d
o
n
e
s
ep
ar
atel
y
f
o
r
th
e
f
o
u
r
g
r
o
u
p
s
s
elec
t
ed
d
u
r
in
g
s
ta
g
e
1
n
a
m
el
y
A
P
I
,
S
T
R
,
R
E
G,
an
d
FIL
E
S_
E
XT
.
Fo
r
ea
ch
g
r
o
u
p
,
w
e
w
i
ll
s
o
r
t
th
e
f
ea
t
u
r
es
in
d
escen
d
in
g
o
r
d
er
b
ased
o
n
th
eir
r
ele
v
an
ce
a
s
d
eter
m
in
ed
b
y
t
h
e
MI
f
ea
t
u
r
e
r
an
k
i
n
g
m
et
h
o
d
.
T
h
e
w
r
a
p
p
e
r
-
b
as
e
d
in
d
iv
i
d
u
a
l
FS
p
h
a
s
e
c
o
n
s
is
ts
o
f
s
e
l
ec
t
in
g
an
e
q
u
al
s
u
b
s
e
t
o
f
th
e
b
e
s
t
-
r
an
k
e
d
f
e
at
u
r
es
f
r
o
m
e
a
ch
g
r
o
u
p
o
f
th
e
c
a
t
eg
o
r
y
s
e
t
af
t
e
r
r
an
k
i
n
g
an
d
s
o
r
t
in
g
t
h
e
v
a
r
i
o
u
s
v
a
r
i
a
b
l
es
in
e
a
ch
c
a
t
eg
o
r
y
.
T
h
i
s
p
h
a
s
e
w
i
ll
b
e
c
a
r
r
i
e
d
o
u
t
in
f
o
u
r
a
c
t
i
o
n
s
:
g
en
e
r
a
ti
n
g
s
u
b
s
e
t
,
a
s
s
es
s
i
n
g
s
u
b
s
et
,
d
e
f
in
in
g
s
to
p
p
i
n
g
c
r
i
t
e
r
i
a
,
an
d
e
v
a
lu
at
in
g
r
es
u
l
ts
[
3
1
]
.
T
h
e
f
i
r
s
t
s
t
e
p
c
o
n
s
is
ts
o
f
g
en
e
r
a
t
in
g
a
s
u
b
s
e
t
o
f
f
e
a
tu
r
es
t
o
b
e
ev
alu
a
te
d
.
T
o
t
h
i
s
en
d
,
w
e
a
d
o
p
t
e
d
a
f
o
r
w
a
r
d
s
e
a
r
ch
t
e
ch
n
i
q
u
e
th
at
b
eg
in
s
w
i
th
a
n
em
p
ty
s
e
t
o
f
f
ea
tu
r
e
s
th
en
a
d
d
s
o
n
e
f
e
atu
r
e
f
r
o
m
e
a
ch
c
a
t
eg
o
r
y
at
e
a
ch
i
t
e
r
at
i
o
n
.
I
n
th
e
s
e
c
o
n
d
s
t
e
p
,
w
e
d
e
f
i
n
e
d
th
e
s
t
o
p
p
in
g
c
r
it
e
r
i
a
,
w
h
i
ch
is
1
0
0
i
t
e
r
a
t
i
o
n
s
.
I
n
th
e
t
h
i
r
d
s
t
e
p
,
w
e
ev
a
lu
a
te
d
t
h
e
s
el
e
c
t
e
d
s
u
b
s
e
t
o
f
f
e
at
u
r
es
u
s
in
g
L
R
al
g
o
r
i
th
m
,
w
h
i
ch
p
l
ay
s
th
e
r
o
l
e
o
f
a
w
r
a
p
p
e
d
a
l
g
o
r
ith
m
.
T
h
e
s
c
o
r
es
ac
h
i
ev
ed
b
y
e
a
ch
s
u
b
s
e
t
w
il
l
b
e
c
o
m
p
a
r
e
d
w
it
h
th
e
b
e
s
t
s
c
o
r
e
a
ch
ie
v
e
d
d
u
r
in
g
th
e
w
h
o
l
e
s
u
b
s
e
t
e
v
a
lu
a
t
i
o
n
p
r
o
c
es
s
u
n
ti
l
t
h
e
s
t
o
p
p
in
g
c
r
i
te
r
i
a
(
1
0
0
i
t
e
r
ati
o
n
s
)
i
s
r
e
a
ch
e
d
.
A
t
th
e
en
d
o
f
t
h
e
FS
p
r
o
c
es
s
,
w
e
f
o
u
n
d
th
a
t
s
el
e
c
t
in
g
9
8
v
a
r
i
a
b
l
e
s
in
e
a
ch
c
a
t
eg
o
r
y
w
o
u
l
d
g
iv
e
t
h
e
b
e
s
t
r
esu
l
t
b
y
a
p
p
ly
in
g
t
h
e
L
R
a
lg
o
r
ith
m
.
F
in
a
l
ly
,
t
o
te
s
t
th
e
g
en
e
r
a
l
i
za
b
i
l
i
ty
o
f
o
u
r
r
e
s
u
lt
s
,
w
e
v
al
i
d
a
te
d
t
h
e
s
u
b
s
e
t
o
f
s
el
e
c
te
d
f
e
a
tu
r
e
s
u
s
in
g
d
if
f
e
r
en
t
a
l
g
o
r
ith
m
s
s
u
ch
as
S
V
M
,
KNN
,
R
F
,
an
d
D
T
.
A
l
l
v
a
li
d
a
t
i
o
n
a
lg
o
r
i
th
m
s
s
h
o
w
e
d
b
e
t
t
e
r
r
es
u
l
ts
t
h
a
n
p
r
ev
i
o
u
s
s
im
il
a
r
m
et
h
o
d
s
in
th
e
l
i
te
r
a
tu
r
e
.
F
ig
u
r
e
2
i
l
lu
s
t
r
a
t
es
t
h
e
p
h
a
s
e
2
p
r
o
c
e
s
s
o
f
o
u
r
FS
t
ec
h
n
i
q
u
e
,
w
h
i
ch
b
eg
i
n
s
w
i
th
t
h
e
s
e
le
c
t
e
d
f
e
at
u
r
e
g
r
o
u
p
s
an
d
c
o
n
t
in
u
es
u
n
t
il
th
e
s
t
o
p
p
i
n
g
c
r
i
t
e
r
i
a
a
r
e
r
ea
ch
e
d
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
I
n
t J
A
r
ti
f
I
n
tell
,
Vo
l.
14
,
No
.
3
,
J
u
n
e
2
0
2
5
:
2
1
0
2
-
2110
2106
Fig
u
r
e
2
.
T
h
e
w
r
ap
p
er
-
b
ased
FS
p
r
o
ce
s
s
4.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
4
.
1
.
E
x
peri
m
ent
a
l e
nv
iro
n
ments
T
h
e
w
o
r
k
s
tatio
n
u
s
ed
f
o
r
all
ex
p
er
i
m
e
n
ts
h
a
s
th
e
f
o
llo
w
i
n
g
s
p
ec
if
icatio
n
s
:
I
n
te
l
C
o
r
e
i5
-
1
0
5
0
0
(
3
.
1
GHz
)
,
8
GB
o
f
R
AM
.
I
n
ad
d
itio
n
,
P
y
t
h
o
n
3
.
9
.
7
a
n
d
t
w
o
p
r
i
m
ar
y
lib
r
ar
ies
w
e
r
e
u
tili
ze
d
f
o
r
th
e
ex
p
er
i
m
e
n
ts
.
T
h
e
f
ir
s
t
o
n
e
is
th
e
1
.
3
.
4
v
er
s
io
n
o
f
P
an
d
as
w
h
ic
h
w
a
s
e
m
p
lo
y
ed
f
o
r
d
ata
m
a
n
ip
u
la
tio
n
a
n
d
an
al
y
s
is
,
w
h
ile
t
h
e
s
ec
o
n
d
is
th
e
0
.
2
4
.
2
v
er
s
io
n
o
f
SC
I
KI
T
-
L
E
A
R
N
w
h
ic
h
w
a
s
u
ti
lized
f
o
r
f
ea
t
u
r
e
r
an
k
i
n
g
an
d
s
elec
tio
n
,
cla
s
s
i
f
icatio
n
s
tr
ateg
ies,
a
n
d
alg
o
r
ith
m
e
v
al
u
ati
o
n
.
4
.
2
.
Da
t
a
s
et
des
cr
iptio
n
T
h
e
d
ataset
u
tili
ze
d
i
n
t
h
is
ar
ticle
is
R
e
s
ilie
n
t
I
n
f
o
r
m
a
tio
n
S
y
s
te
m
s
Secu
r
i
t
y
(
R
I
S
S)
[
2
9
]
,
a
d
y
n
a
m
icall
y
g
e
n
er
ated
d
atase
t.
I
t
w
as
r
etr
iev
ed
in
Feb
r
u
ar
y
2
0
1
6
an
d
a
n
al
y
ze
d
i
n
a
s
a
n
d
b
o
x
.
T
h
e
d
ataset
co
n
tain
s
a
to
tal
o
f
1
,
5
2
4
ex
a
m
p
le
s
,
i
n
cl
u
d
in
g
5
8
2
s
a
m
p
les
o
f
r
an
s
o
m
w
ar
e
f
r
o
m
1
1
ca
teg
o
r
ies
a
n
d
9
4
2
g
o
o
d
w
ar
e
s
a
m
p
le
s
.
T
h
is
d
ataset
also
co
n
tai
n
s
3
0
,
9
7
0
f
ea
t
u
r
es
g
r
o
u
p
ed
in
to
t
h
e
7
g
r
o
u
p
s
d
escr
ib
ed
in
T
ab
le
1
.
I
n
ad
d
itio
n
,
ea
ch
f
ea
tu
r
e
in
th
e
d
ataset
h
as
b
in
ar
y
-
q
u
an
tita
tiv
e
v
al
u
es,
th
er
e
f
o
r
e
w
e
d
id
n
o
t
h
av
e
to
p
er
f
o
r
m
t
h
e
e
n
co
d
in
g
o
r
n
o
r
m
aliza
tio
n
o
p
er
atio
n
s
.
T
ab
le
1
.
Descr
ip
tio
n
o
f
th
e
ca
t
eg
o
r
ies o
f
f
ea
tu
r
es
C
a
t
e
g
o
r
y
c
o
d
e
S
i
g
n
i
f
i
c
a
t
i
o
n
N
b
_
f
e
a
t
u
r
e
s
A
P
I
A
P
I
i
n
v
o
c
a
t
i
o
n
s
2
3
2
R
EG
R
e
g
i
st
r
y
k
e
y
o
p
e
r
a
t
i
o
n
s
6
,
6
2
2
S
T
R
Emb
e
d
d
e
d
s
t
r
i
n
g
s
16
,
267
D
R
O
P
Ex
t
e
n
si
o
n
s
o
f
t
h
e
d
r
o
p
p
e
d
f
i
l
e
s
3
4
6
D
I
R
F
i
l
e
d
i
r
e
c
t
o
r
y
o
p
e
r
a
t
i
o
n
s
2
,
4
2
4
F
I
L
E
F
i
l
e
o
p
e
r
a
t
i
o
n
s
4
,
1
4
1
F
I
L
ES_
EX
T
F
i
l
e
e
x
t
e
n
si
o
n
s i
n
v
o
l
v
e
d
i
n
f
i
l
e
o
p
e
r
a
t
i
o
n
s
9
3
5
4
.
3
.
H
y
per
pa
ra
m
et
er
s
s
et
t
i
ng
W
e
em
p
lo
y
ed
m
a
n
y
ML
alg
o
r
ith
m
s
t
h
r
o
u
g
h
o
u
t
o
u
r
p
r
o
ce
s
s
,
b
eg
in
n
in
g
w
it
h
th
e
L
R
al
g
o
r
ith
m
a
s
a
w
r
ap
p
ed
alg
o
r
ith
m
a
n
d
th
e
n
m
o
v
i
n
g
o
n
to
th
e
SVM,
KNN,
R
F,
an
d
DT
alg
o
r
ith
m
s
to
g
e
n
er
alize
th
e
f
i
n
d
in
g
s
o
b
tain
ed
u
s
in
g
th
e
w
r
ap
p
ed
a
lg
o
r
ith
m
.
I
n
o
r
d
er
to
m
ai
n
tai
n
th
e
s
a
m
e
co
n
d
itio
n
s
a
s
th
e
r
elate
d
w
o
r
k
s
w
h
e
n
p
er
f
o
r
m
in
g
o
u
r
ex
p
er
i
m
en
ts
,
all
alg
o
r
it
h
m
s
cited
p
r
ev
io
u
s
l
y
w
er
e
e
x
ec
u
ted
w
it
h
d
e
f
au
lt
v
alu
e
s
a
n
d
w
it
h
o
u
t
an
y
h
y
p
er
p
ar
a
m
eter
o
p
ti
m
iz
atio
n
.
A
d
d
itio
n
all
y
,
to
p
er
f
o
r
m
tr
ain
i
n
g
an
d
test
in
g
p
r
o
ce
s
s
es,
w
e
s
p
lit
t
h
e
d
ataset
u
s
i
n
g
a
s
tr
at
i
f
ied
4
-
f
o
ld
cr
o
s
s
v
alid
atio
n
to
b
e
s
u
r
e
th
at
ev
er
y
m
al
w
ar
e
f
a
m
il
y
i
s
r
ep
r
esen
ted
in
all
f
o
ld
s
,
as r
ec
o
m
m
en
d
ed
b
y
[
3
0
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
A
r
ti
f
I
n
tell
I
SS
N:
2252
-
8938
A
n
ew w
r
a
p
p
er fea
tu
r
e
s
elec
ti
o
n
a
p
p
r
o
a
ch
fo
r
b
in
a
r
y
r
a
n
s
o
mw
a
r
e
d
etec
tio
n
(
Oma
r
C
h
a
ieb
)
2107
4
.
4
.
E
x
peri
m
ent
a
l
r
esu
lt
s
T
h
is
s
ec
tio
n
d
is
p
la
y
s
t
h
e
e
x
p
er
i
m
en
tal
f
i
n
d
i
n
g
s
f
o
r
ea
ch
p
h
ase
o
f
o
u
r
ap
p
r
o
ac
h
,
w
h
ic
h
in
cl
u
d
es
r
an
k
i
n
g
a
n
d
s
elec
t
in
g
th
e
m
o
s
t
r
elev
a
n
t
ca
teg
o
r
y
g
r
o
u
p
s
,
r
an
k
in
g
an
d
s
elec
ti
n
g
t
h
e
m
o
s
t
r
e
lev
an
t
f
ea
t
u
r
es
a
n
d
v
alid
ati
n
g
t
h
e
s
elec
ted
s
u
b
s
et
o
f
f
ea
t
u
r
es
u
s
i
n
g
s
e
v
er
al
ML
alg
o
r
ith
m
s
.
Fu
r
t
h
er
m
o
r
e,
r
eg
a
r
d
in
g
ac
c
u
r
ac
y
a
n
d
p
r
o
ce
s
s
in
g
t
i
m
e,
w
e
co
m
p
ar
e
d
th
e
v
alid
atio
n
r
es
u
lt
s
o
f
t
h
e
s
elec
ted
f
ea
t
u
r
es
to
th
o
s
e
p
r
o
d
u
ce
d
b
y
t
h
e
en
t
ir
e
d
ataset,
an
d
t
h
e
n
w
e
co
m
p
ar
ed
th
e
e
x
p
er
i
m
e
n
tal
f
i
n
d
i
n
g
s
ac
q
u
ir
ed
b
y
o
u
r
m
et
h
o
d
to
t
h
o
s
e
o
b
tain
ed
b
y
r
elate
d
w
o
r
k
s
.
A
s
m
e
n
tio
n
ed
i
n
th
e
m
et
h
o
d
o
lo
g
y
s
ec
tio
n
,
th
e
f
i
r
s
t
s
tep
o
f
o
u
r
s
tr
ateg
y
w
as
to
r
an
k
g
r
o
u
p
s
b
y
ap
p
ly
i
n
g
th
e
L
R
alg
o
r
it
h
m
o
n
ea
ch
g
r
o
u
p
s
ep
ar
atel
y
.
T
ab
le
2
p
r
esen
ts
th
e
ac
c
u
r
ac
y
ev
alu
a
tio
n
m
etr
ic
o
b
tain
ed
f
o
r
ea
ch
g
r
o
u
p
w
h
e
n
u
s
i
n
g
L
R
al
g
o
r
ith
m
.
Af
ter
r
an
k
in
g
th
e
f
ea
t
u
r
e
g
r
o
u
p
s
b
ased
o
n
th
e
s
co
r
es
th
e
y
o
b
tain
ed
,
w
e
u
s
ed
th
e
LR
al
g
o
r
ith
m
to
s
elec
t
t
h
e
s
u
b
s
et
o
f
g
r
o
u
p
s
t
h
at
g
a
v
e
u
s
t
h
e
b
est
s
co
r
e.
T
h
e
s
co
r
e
r
ea
ch
ed
b
y
ea
ch
s
u
b
s
et
o
f
g
r
o
u
p
s
w
h
en
m
ea
s
u
r
in
g
th
e
ac
c
u
r
ac
y
ev
al
u
atio
n
m
etr
ic
i
s
p
r
esen
ted
i
n
T
ab
le
3
.
Am
o
n
g
all
s
u
b
s
ets
,
t
h
e
s
u
b
s
e
t
co
n
tai
n
i
n
g
A
P
I
,
ST
R
,
R
E
G
,
an
d
FIL
E
S_
E
XT
g
r
o
u
p
s
r
ea
ch
ed
th
e
b
est s
co
r
e.
T
ab
le
2
.
G
r
o
u
p
r
an
k
i
n
g
s
co
r
es
G
r
o
u
p
n
a
me
S
c
o
r
e
A
P
I
9
4
.
4
2
D
R
O
P
8
4
.
0
0
R
EG
8
8
.
5
1
F
I
L
ES
8
3
.
8
3
F
I
L
ES_
EX
T
8
5
.
0
6
D
I
R
8
3
.
5
9
S
T
R
9
0
.
5
6
T
ab
le
3
.
Gr
o
u
p
s
s
u
b
s
et
s
s
co
r
e
s
G
r
o
u
p
s s
u
b
se
t
S
c
o
r
e
E1
=
{A
P
I
,
S
T
R
}
9
7
.
1
2
E2
=
{A
P
I
,
S
T
R
,
R
EG
}
9
7
.
6
2
E3
=
{A
P
I
,
S
T
R
,
R
EG
,
F
I
L
E
S
_
EX
T
}
9
7
.
7
8
E4
=
{A
P
I
,
S
T
R
,
R
EG
,
F
I
L
E
S
_
EX
T
,
D
R
O
P
}
9
7
.
7
0
E5
=
{A
P
I
,
S
T
R
,
R
EG
,
F
I
L
E
S
_
EX
T
,
D
R
O
P
,
F
I
L
ES}
9
7
.
7
0
E6
=
{A
P
I
,
S
T
R
,
R
EG
,
F
I
L
E
S
_
EX
T
,
D
R
O
P
,
F
I
L
ES,
D
I
R
}
9
7
.
4
5
T
h
e
co
m
p
ar
is
o
n
b
et
w
ee
n
t
h
e
r
esu
lt
s
o
f
o
u
r
m
et
h
o
d
an
d
th
o
s
e
o
b
tain
ed
b
y
r
elate
d
w
o
r
k
s
[
2
9
]
,
[
3
0
]
,
is
p
r
esen
ted
in
T
ab
le
4
.
T
h
is
tab
le
h
ig
h
li
g
h
ts
th
e
ac
cu
r
a
c
y
m
etr
ic
u
s
ed
to
e
v
al
u
ate
t
h
e
p
er
f
o
r
m
a
n
ce
o
f
d
if
f
er
e
n
t
v
a
lid
atio
n
al
g
o
r
ith
m
s
in
cl
u
d
in
g
S
VM
,
DT
,
R
F
,
an
d
KNN.
B
esid
es,
w
e
co
m
p
ar
e
th
e
n
u
m
b
er
o
f
s
elec
ted
f
ea
t
u
r
es a
n
d
f
ea
tu
r
e
r
ed
u
ctio
n
r
ate
w
h
ich
s
h
o
w
an
o
u
tp
er
f
o
r
m
i
n
g
r
esu
lt f
o
r
th
e
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
.
Fu
r
t
h
er
m
o
r
e,
t
h
e
co
m
p
ar
i
s
o
n
b
et
w
ee
n
t
h
e
o
b
tai
n
ed
r
es
u
lts
a
n
d
t
h
o
s
e
r
ea
c
h
ed
b
y
th
e
en
t
ir
e
d
ataset
i
n
ter
m
s
o
f
ac
c
u
r
ac
y
an
d
s
p
ee
d
is
p
r
esen
ted
in
T
ab
le
5
.
A
s
s
h
o
w
n
i
n
th
i
s
tab
le,
th
e
s
elec
t
ed
f
ea
tu
r
es
b
y
o
u
r
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
o
b
tain
ed
o
u
tp
er
f
o
r
m
i
n
g
r
es
u
lts
ac
r
o
s
s
al
l
v
alid
atio
n
alg
o
r
it
h
m
s
w
h
e
n
u
s
i
n
g
th
e
ac
cu
r
ac
y
ev
alu
a
tio
n
m
etr
ic.
I
n
ad
d
itio
n
,
w
e
ca
lc
u
late
th
e
co
m
p
u
tat
io
n
ti
m
e
f
o
r
th
e
w
r
ap
p
er
an
d
v
a
lid
atio
n
alg
o
r
it
h
m
s
w
h
ic
h
in
d
icate
a
s
u
p
er
io
r
it
y
o
f
s
elec
ted
f
ea
t
u
r
es c
o
m
p
ar
ed
to
th
e
o
r
ig
i
n
al
f
ea
t
u
r
es.
T
ab
le
4
.
Selecte
d
f
ea
tu
r
es c
o
m
p
ar
ed
w
it
h
o
r
ig
i
n
al
f
ea
tu
r
e
s
M
L
a
l
g
o
r
i
t
h
m
LR
S
V
M
DT
RF
K
N
N
N
b
se
l
e
c
t
e
d
f
e
a
t
u
r
e
s
F
e
a
t
u
r
e
s re
d
u
c
t
i
o
n
r
a
t
e
(
%)
[
2
9
]
9
7
.
2
7
9
6
.
6
2
9
5
.
1
4
9
7
.
4
8
9
3
.
4
5
4
0
0
9
8
.
7
0
[
3
0
]
9
7
.
3
3
9
6
.
3
3
9
5
.
0
3
9
7
.
0
6
9
4
.
1
8
8
2
3
9
7
.
3
3
O
u
r
me
t
h
o
d
9
7
.
3
7
9
6
.
8
8
9
6
.
3
8
9
7
.
7
0
9
4
.
2
5
3
9
2
9
8
.
7
3
T
ab
le
5
.
T
h
e
p
r
o
p
o
s
ed
m
eth
o
d
co
m
p
ar
ed
w
ith
r
elate
d
w
o
r
k
s
M
L
a
l
g
o
r
i
t
h
m
LR
S
V
M
RF
DT
K
N
N
A
c
c
u
r
a
c
y
T
i
me
A
c
c
u
r
a
c
y
T
i
me
A
c
c
u
r
a
c
y
T
i
me
A
c
c
u
r
a
c
y
T
i
me
A
c
c
u
r
a
c
y
T
i
me
S
e
l
e
c
t
e
d
f
e
a
t
u
r
e
s
9
7
.
3
7
0
.
2
4
9
6
.
8
8
0
.
7
7
9
7
.
7
0
1
.
3
0
9
6
.
3
8
0
.
2
0
9
4
.
2
5
0
.
4
5
O
r
i
g
i
n
a
l
f
e
a
t
u
r
e
s
9
7
.
4
5
1
9
.
3
9
5
.
6
5
1
1
6
.
2
5
9
6
.
3
0
1
8
.
6
2
9
5
.
9
7
6
.
2
9
0
.
0
7
6
.
0
1
4
.
5
.
Dis
cus
s
io
n
W
e
ass
u
m
ed
at
t
h
e
b
e
g
in
n
i
n
g
o
f
th
i
s
p
ap
er
th
at
s
elec
ti
n
g
th
e
m
o
s
t
r
ele
v
a
n
t
f
ea
tu
r
e
g
r
o
u
p
s
an
d
ig
n
o
r
i
n
g
th
e
r
es
t
w
o
u
ld
co
n
s
i
d
er
ab
ly
a
f
f
ec
t
th
e
e
f
f
ec
ti
v
e
n
ess
a
n
d
s
p
ee
d
o
f
d
etec
tio
n
al
g
o
r
ith
m
s
.
T
o
v
alid
ate
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
I
n
t J
A
r
ti
f
I
n
tell
,
Vo
l.
14
,
No
.
3
,
J
u
n
e
2
0
2
5
:
2
1
0
2
-
2110
2108
th
is
h
y
p
o
th
es
is
,
w
e
p
r
o
p
o
s
ed
a
n
e
w
tec
h
n
iq
u
e
f
o
r
m
ea
s
u
r
in
g
t
h
e
e
f
f
ec
t
iv
e
n
es
s
o
f
in
d
i
v
id
u
al
f
ea
t
u
r
e
g
r
o
u
p
s
,
s
u
b
s
eq
u
en
t
l
y
co
n
s
tr
u
cti
n
g
an
o
p
ti
m
al
s
et
o
f
th
e
s
e
g
r
o
u
p
s
.
As
w
e
w
i
ll
s
h
o
w
in
th
i
s
s
ec
tio
n
,
t
h
e
r
es
u
lt
s
ac
h
iev
ed
b
y
o
u
r
m
et
h
o
d
s
h
o
w
ed
a
lar
g
e
s
u
p
er
io
r
it
y
co
m
p
ar
ed
to
th
o
s
e
o
b
tain
ed
b
y
th
e
e
n
tire
d
ataset
o
r
r
elate
d
w
o
r
k
s
.
T
h
e
s
co
r
es
o
b
tain
ed
f
o
r
ea
ch
g
r
o
u
p
i
n
p
h
a
s
e
1
.
1
o
f
o
u
r
m
et
h
o
d
s
h
o
w
t
h
at
th
e
"
A
P
I
in
v
o
ca
tio
n
"
ca
teg
o
r
y
r
ec
eiv
ed
th
e
h
i
g
h
est
s
co
r
e,
w
h
ich
m
ea
n
s
th
at
t
h
i
s
g
r
o
u
p
co
n
tain
s
th
e
lar
g
e
s
t
n
u
m
b
er
o
f
r
elev
an
t
f
ea
t
u
r
es.
T
h
is
r
es
u
lt
w
as c
o
n
cl
u
d
ed
b
y
[
3
0
]
,
s
in
ce
t
h
e
A
P
I
in
v
o
ca
tio
n
g
r
o
u
p
co
n
tr
ib
u
ted
t
h
e
m
o
s
t to
t
h
e
s
u
b
s
et
s
elec
ted
b
y
t
h
eir
ap
p
r
o
ac
h
.
A
cc
o
r
d
in
g
to
th
e
r
esu
lt
s
o
b
tain
ed
in
p
h
ase
1
.
2
o
f
o
u
r
a
p
p
r
o
ac
h
,
th
e
s
u
b
s
et
in
cl
u
d
in
g
t
h
e
f
o
llo
w
i
n
g
ca
teg
o
r
ies:
A
P
I
,
ST
R
,
R
E
G,
an
d
FIL
E
S_
E
XT
r
ea
ch
ed
th
e
h
i
g
h
est
s
co
r
e
th
u
s
w
a
s
e
m
p
lo
y
ed
in
th
e
n
ex
t
p
h
ase
o
f
o
u
r
ap
p
r
o
ac
h
,
w
h
ic
h
is
co
n
s
is
te
n
t
w
it
h
w
h
at
h
as
b
ee
n
d
is
co
v
er
ed
in
r
elate
d
w
o
r
k
s
[
2
9
]
,
[
3
0
]
,
s
in
ce
th
e
lar
g
est
g
r
o
u
p
s
i
n
t
h
eir
s
elec
ted
f
ea
tu
r
es
ar
e
t
h
e
s
a
m
e
as
t
h
o
s
e
ch
o
s
en
in
t
h
i
s
s
tep
.
Mo
r
eo
v
er
,
in
th
e
MI
f
ea
t
u
r
e
s
r
an
k
i
n
g
p
h
ase,
t
h
e
r
es
u
lts
co
llected
f
o
r
ea
ch
ca
teg
o
r
y
s
h
o
w
t
h
at
th
e
A
P
I
ca
teg
o
r
y
h
as t
h
e
m
o
s
t
h
i
g
h
l
y
r
ated
f
ea
tu
r
e
s
a
m
o
n
g
o
th
er
g
r
o
u
p
s
.
T
h
er
ef
o
r
e,
it c
an
b
e
n
o
ted
th
at
t
h
e
A
P
I
g
r
o
u
p
co
n
tain
s
th
e
f
ea
t
u
r
es
th
a
t,
in
a
cc
o
r
d
an
ce
w
it
h
o
th
er
e
ar
lier
r
esear
ch
[
3
2
]
,
m
a
y
h
a
v
e
th
e
m
o
s
t
in
f
lu
e
n
ce
o
n
t
h
e
d
ec
is
io
n
o
f
t
h
e
r
an
s
o
m
w
ar
e
d
etec
tio
n
alg
o
r
it
h
m
.
Fu
r
t
h
er
m
o
r
e,
as
s
h
o
w
n
i
n
T
ab
le
s
4
an
d
5
,
o
u
r
ch
o
s
en
s
et
o
f
f
ea
t
u
r
es
o
u
tp
er
f
o
r
m
ed
s
elec
te
d
f
ea
tu
r
es
o
f
r
elate
d
w
o
r
k
s
r
e
g
ar
d
in
g
ac
cu
r
ac
y
a
n
d
f
ea
tu
r
e
r
ed
u
ct
io
n
r
ate.
First,
o
u
r
ap
p
r
o
ac
h
r
ed
u
ce
d
9
8
.
7
3
%
o
f
th
e
o
v
er
all
d
ataset,
w
h
er
ea
s
o
th
er
FS
m
eth
o
d
s
r
ed
u
ce
d
it
to
9
7
.
3
3
%
[
3
0
]
an
d
9
8
.
7
0
%
[
2
9
]
,
i
m
p
ac
tin
g
d
etec
tio
n
alg
o
r
ith
m
ac
cu
r
ac
y
an
d
s
p
ee
d
.
Seco
n
d
,
o
u
r
FS
o
u
tp
er
f
o
r
m
ed
r
elate
d
w
o
r
k
s
an
d
o
r
ig
i
n
al
f
e
atu
r
es
i
n
ac
cu
r
ac
y
,
s
co
r
in
g
9
7
.
3
7
%
w
it
h
L
R
,
9
6
.
8
8
%
w
it
h
SV
M,
9
6
.
3
8
w
i
t
h
DT
,
9
7
.
7
0
w
i
th
R
F,
an
d
9
4
.
2
5
w
i
t
h
KNN.
5.
CO
NCLU
SI
O
N
A
cc
o
r
d
in
g
to
th
e
h
y
p
o
th
es
is
p
r
o
p
o
s
ed
ea
r
lier
in
th
i
s
ar
ti
cle,
ch
o
o
s
in
g
t
h
e
m
o
s
t
r
ele
v
an
t
f
ea
tu
r
e
g
r
o
u
p
s
w
h
ile
ig
n
o
r
in
g
o
th
er
s
w
o
u
ld
p
o
s
itiv
el
y
af
f
ec
t
t
h
e
p
er
f
o
r
m
an
ce
a
n
d
s
p
ee
d
o
f
th
e
d
etec
tio
n
m
et
h
o
d
.
W
e
s
u
g
g
e
s
ted
a
n
e
w
ap
p
r
o
ac
h
f
o
r
ev
al
u
ati
n
g
t
h
e
e
f
f
icac
y
o
f
d
is
ti
n
ct
f
ea
t
u
r
e
g
r
o
u
p
s
(
ca
te
g
o
r
ies)
to
v
er
if
y
t
h
i
s
h
y
p
o
t
h
esi
s
,
an
d
th
en
w
e
b
u
il
t
an
o
p
tim
al
s
e
t
o
f
th
ese
g
r
o
u
p
s
.
R
eg
ar
d
in
g
th
e
f
ea
tu
r
e
r
ed
u
ctio
n
r
ate
an
d
ac
cu
r
ac
y
,
o
u
r
ap
p
r
o
ac
h
o
u
tp
er
f
o
r
m
ed
r
elate
d
w
o
r
k
s
.
I
n
ad
d
itio
n
,
w
h
e
n
w
e
co
m
p
ar
e
t
h
e
o
u
tco
m
es
o
f
s
elec
te
d
f
ea
t
u
r
es
w
it
h
th
e
o
r
i
g
in
a
l
f
ea
t
u
r
es
i
n
ter
m
s
o
f
d
etec
tio
n
r
ate
an
d
co
m
p
u
tatio
n
s
p
ee
d
,
th
e
c
h
o
s
en
f
ea
tu
r
es
g
i
v
e
b
etter
r
esu
lts
.
I
n
co
n
clu
s
io
n
,
w
e
n
o
te
t
h
at
all
th
e
o
b
tain
ed
r
esu
lts
s
u
p
p
o
r
t
th
e
h
y
p
o
th
e
s
is
p
r
esen
ted
at
th
e
b
eg
in
n
i
n
g
o
f
t
h
i
s
p
ap
er
.
Ou
r
a
p
p
r
o
ac
h
b
ased
o
n
h
o
w
t
h
e
s
el
ec
ted
f
ea
tu
r
e
g
r
o
u
p
s
a
f
f
ec
t
th
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
d
etec
tio
n
alg
o
r
ith
m
w
ill
n
o
t
o
n
l
y
i
m
p
r
o
v
e
r
an
s
o
m
w
ar
e
d
etec
tio
n
b
u
t
also
tech
n
icall
y
a
llo
w
u
s
to
f
o
cu
s
o
n
t
h
e
m
o
s
t
i
m
p
o
r
t
an
t
f
ea
tu
r
e
s
ca
te
g
o
r
ies
an
d
d
is
ca
r
d
t
h
o
s
e
less
i
m
p
o
r
ta
n
t
w
h
e
n
co
llecti
n
g
d
at
a
u
s
in
g
b
e
h
av
io
r
al
an
al
y
s
is
.
F
u
r
th
er
m
o
r
e,
w
e
b
eli
ev
e
t
h
at
th
is
n
e
w
FS
m
et
h
o
d
w
il
l
al
s
o
h
elp
i
m
p
r
o
v
e
o
t
h
er
a
r
ea
s
w
h
er
e
d
ataset
s
ar
e
h
ig
h
-
d
i
m
e
n
s
io
n
al,
s
u
c
h
as
i
m
ag
e
p
r
o
ce
s
s
i
n
g
,
co
m
p
u
ter
v
is
io
n
,
an
d
n
at
u
r
al
lan
g
u
ag
e
p
r
o
ce
s
s
in
g
.
I
n
t
h
e
f
u
tu
r
e,
o
u
r
m
et
h
o
d
ca
n
b
e
u
s
ed
to
p
er
f
o
r
m
m
u
lt
i
-
cla
s
s
r
an
s
o
m
w
ar
e
d
etec
tio
n
an
d
ev
al
u
ated
o
n
o
th
er
r
ea
l
w
o
r
d
d
atasets
.
ACK
NO
WL
E
D
G
M
E
NT
S
T
h
er
e
ar
e
n
o
in
d
iv
id
u
als,
o
r
g
an
iza
tio
n
s
,
o
r
f
u
n
d
in
g
b
o
d
ies
to
ac
k
n
o
w
led
g
e
f
o
r
th
is
w
o
r
k
.
T
h
e
r
esear
ch
an
d
p
r
ep
ar
atio
n
o
f
th
e
m
a
n
u
s
cr
ip
t
w
er
e
co
n
d
u
ct
ed
in
d
ep
en
d
en
tl
y
b
y
t
h
e
lis
t
ed
au
th
o
r
s
w
i
th
o
u
t
ex
ter
n
al
p
er
s
o
n
a
l a
s
s
i
s
ta
n
ce
r
eq
u
ir
in
g
ac
k
n
o
w
led
g
m
e
n
t.
F
UNDIN
G
I
NF
O
RM
AT
I
O
N
Au
t
h
o
r
s
s
tate
t
h
er
e
is
n
o
f
u
n
d
i
n
g
i
n
v
o
lv
ed
.
AUTHO
R
CO
NT
RIB
UT
I
O
NS ST
A
T
E
M
E
NT
T
h
is
jo
u
r
n
al
u
s
e
s
th
e
C
o
n
tr
ib
u
to
r
R
o
les
T
ax
o
n
o
m
y
(
C
R
ed
iT
)
t
o
r
ec
o
g
n
ize
in
d
i
v
id
u
al
au
t
h
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
t
h
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
lla
b
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
O
m
ar
C
h
aieb
Nab
il
Kan
n
o
u
f
Mo
h
a
m
m
ed
B
en
ab
d
ellah
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
A
r
ti
f
I
n
tell
I
SS
N:
2252
-
8938
A
n
ew w
r
a
p
p
er fea
tu
r
e
s
elec
ti
o
n
a
p
p
r
o
a
ch
fo
r
b
in
a
r
y
r
a
n
s
o
mw
a
r
e
d
etec
tio
n
(
Oma
r
C
h
a
ieb
)
2109
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
si
s
I
:
I
n
v
e
st
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
si
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
t
h
o
r
s
s
tate
n
o
co
n
f
lic
t o
f
i
n
t
er
est.
I
NF
O
RM
E
D
CO
NSE
N
T
W
e
h
av
e
o
b
tain
ed
in
f
o
r
m
ed
c
o
n
s
en
t f
r
o
m
al
l in
d
i
v
id
u
al
s
in
c
lu
d
ed
in
th
is
s
t
u
d
y
.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
ata
th
at
s
u
p
p
o
r
t
th
e
f
i
n
d
in
g
s
o
f
t
h
is
s
t
u
d
y
ar
e
o
p
en
l
y
av
ai
lab
le
in
R
esi
lien
t
I
n
f
o
r
m
atio
n
S
y
s
te
m
s
Sec
u
r
it
y
at
h
ttp
s
:
//d
o
i.o
r
g
/1
0
.
4
8
5
5
0
/ar
Xiv
.
1
6
0
9
.
0
3
0
2
0
,
r
ef
er
e
n
ce
n
u
m
b
er
[
2
9
]
.
RE
F
E
R
E
NC
E
S
[
1
]
D
.
U
c
c
i
,
L
.
A
n
i
e
l
l
o
,
a
n
d
R
.
B
a
l
d
o
n
i
,
“
S
u
r
v
e
y
o
f
mac
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s
f
o
r
mal
w
a
r
e
a
n
a
l
y
si
s,”
C
o
m
p
u
t
e
rs a
n
d
S
e
c
u
ri
t
y
,
v
o
l
.
8
1
,
p
p
.
1
2
3
–
1
4
7
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
se
.
2
0
1
8
.
1
1
.
0
0
1
.
[
2
]
L
.
D
a
u
b
n
e
r
,
M
.
M
a
c
a
k
,
R
.
M
a
t
u
l
e
v
i
č
i
u
s
,
B
.
B
u
h
n
o
v
a
,
S
.
M
a
k
so
v
i
ć
,
a
n
d
T
.
P
i
t
n
e
r
,
“
A
d
d
r
e
ssi
n
g
i
n
s
i
d
e
r
a
t
t
a
c
k
s
v
i
a
f
o
r
e
n
si
c
-
r
e
a
d
y
r
i
sk
m
a
n
a
g
e
me
n
t
,
”
J
o
u
rn
a
l
o
f
I
n
f
o
rm
a
t
i
o
n
S
e
c
u
r
i
t
y
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
7
3
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
i
sa.
2
0
2
3
.
1
0
3
4
3
3
.
[
3
]
A
.
S
h
a
r
ma,
B
.
B
.
G
u
p
t
a
,
A
.
K
.
S
i
n
g
h
,
a
n
d
V
.
K
.
S
a
r
a
sw
a
t
,
“
A
d
v
a
n
c
e
d
p
e
r
si
st
e
n
t
t
h
r
e
a
t
s
(
A
P
T
)
:
e
v
o
l
u
t
i
o
n
,
a
n
a
t
o
my
,
a
t
t
r
i
b
u
t
i
o
n
a
n
d
c
o
u
n
t
e
r
me
a
su
r
e
s,”
J
o
u
r
n
a
l
o
f
A
m
b
i
e
n
t
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
H
u
m
a
n
i
z
e
d
C
o
m
p
u
t
i
n
g
,
v
o
l
.
1
4
,
n
o
.
7
,
p
p
.
9
3
5
5
–
9
3
8
1
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
2
6
5
2
-
0
2
3
-
0
4
6
0
3
-
y.
[
4
]
S
.
C
h
a
u
d
h
a
r
y
a
n
d
P
.
K
.
M
i
sh
r
a
,
“
D
D
o
S
a
t
t
a
c
k
s
i
n
i
n
d
u
s
t
r
i
a
l
I
o
T
:
a
su
r
v
e
y
,
”
C
o
m
p
u
t
e
r
N
e
t
w
o
rks
,
v
o
l
.
2
3
6
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
mn
e
t
.
2
0
2
3
.
1
1
0
0
1
5
.
[
5
]
T
.
R
.
R
e
sh
mi
,
“
I
n
f
o
r
mat
i
o
n
se
c
u
r
i
t
y
b
r
e
a
c
h
e
s
d
u
e
t
o
r
a
n
so
mw
a
r
e
a
t
t
a
c
k
s
-
a
sy
st
e
mat
i
c
l
i
t
e
r
a
t
u
r
e
r
e
v
i
e
w
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
I
n
f
o
rm
a
t
i
o
n
Ma
n
a
g
e
m
e
n
t
D
a
t
a
I
n
si
g
h
t
s
,
v
o
l
.
1
,
n
o
.
2
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
j
i
me
i
.
2
0
2
1
.
1
0
0
0
1
3
.
[
6
]
A
.
A
.
M
.
A
.
A
l
w
a
sh
a
l
i
,
N
.
A
.
A
.
R
a
h
man
,
a
n
d
N
.
I
smai
l
,
“
A
su
r
v
e
y
o
f
r
a
n
so
mw
a
r
e
a
s
a
se
r
v
i
c
e
(
R
a
a
S
)
a
n
d
me
t
h
o
d
s
t
o
m
i
t
i
g
a
t
e
t
h
e
a
t
t
a
c
k
,
”
i
n
2
0
2
1
1
4
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
o
n
D
e
v
e
l
o
p
m
e
n
t
s
i
n
e
S
y
s
t
e
m
s
E
n
g
i
n
e
e
ri
n
g
(
D
e
S
E)
,
2
0
2
1
,
p
p
.
9
2
–
96
,
d
o
i
:
1
0
.
1
1
0
9
/
D
e
S
E5
4
2
8
5
.
2
0
2
1
.
9
7
1
9
4
5
6
.
[
7
]
P
.
H
.
M
e
l
a
n
d
,
Y
.
F
.
F
.
B
a
y
o
u
my
,
a
n
d
G
.
S
i
n
d
r
e
,
“
T
h
e
r
a
n
so
mw
a
r
e
-
as
-
a
-
se
r
v
i
c
e
e
c
o
n
o
my
w
i
t
h
i
n
t
h
e
d
a
r
k
n
e
t
,
”
C
o
m
p
u
t
e
rs
a
n
d
S
e
c
u
r
i
t
y
,
v
o
l
.
9
2
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
se
.
2
0
2
0
.
1
0
1
7
6
2
.
[
8
]
V
e
e
a
m,
“
2
0
2
3
r
a
n
s
o
mw
a
r
e
t
r
e
n
d
s
r
e
p
o
r
t
,
”
V
e
e
a
m
S
o
f
t
w
a
re
.
2
0
2
3
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s:
/
/
g
o
.
v
e
e
a
m.c
o
m/
w
p
-
r
a
n
so
mw
a
r
e
-
t
r
e
n
d
s
-
r
e
p
o
r
t
-
2
0
2
3
.
[
9
]
M
.
M
.
G
h
o
n
g
e
,
S
.
P
r
a
m
a
n
i
k
,
R
.
M
a
n
g
r
u
l
k
a
r
,
a
n
d
D
.
-
N
.
L
e
,
C
y
b
e
r
se
c
u
r
i
t
y
a
n
d
d
i
g
i
t
a
l
f
o
r
e
n
s
i
c
s:
c
h
a
l
l
e
n
g
e
s
a
n
d
f
u
t
u
re
t
re
n
d
s
.
P
o
r
t
smo
u
t
h
,
U
n
i
t
e
d
S
t
a
t
e
s:
S
c
r
i
v
e
n
e
r
P
u
b
l
i
s
h
i
n
g
,
2
0
2
2
.
[
1
0
]
C
.
B
e
a
ma
n
,
A
.
B
a
r
k
w
o
r
t
h
,
T
.
D
.
A
k
a
n
d
e
,
S
.
H
a
k
a
k
,
a
n
d
M
.
K
.
K
h
a
n
,
“
R
a
n
so
mw
a
r
e
:
r
e
c
e
n
t
a
d
v
a
n
c
e
s,
a
n
a
l
y
si
s,
c
h
a
l
l
e
n
g
e
s
a
n
d
f
u
t
u
r
e
r
e
se
a
r
c
h
d
i
r
e
c
t
i
o
n
s,”
C
o
m
p
u
t
e
r
s a
n
d
S
e
c
u
ri
t
y
,
v
o
l
.
1
1
1
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
se
.
2
0
2
1
.
1
0
2
4
9
0
.
[
1
1
]
F
.
A
.
V
a
d
h
i
l
,
M
.
L
.
S
a
l
i
h
i
,
a
n
d
M
.
F
.
N
a
n
n
e
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
-
b
a
se
d
i
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
sy
st
e
m fo
r
d
e
t
e
c
t
i
n
g
w
e
b
a
t
t
a
c
k
s,
”
I
A
E
S
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
1
3
,
n
o
.
1
,
p
.
7
1
1
,
M
a
r
.
2
0
2
4
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
a
i
.
v
1
3
.
i
1
.
p
p
7
1
1
-
7
2
1
.
[
1
2
]
P
.
B
a
j
p
a
i
a
n
d
R
.
En
b
o
d
y
,
“
A
n
e
mp
i
r
i
c
a
l
st
u
d
y
o
f
A
P
I
c
a
l
l
s
i
n
r
a
n
so
mw
a
r
e
,
”
i
n
2
0
2
0
I
EEE
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
El
e
c
t
r
o
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
(
EI
T
)
,
2
0
2
0
,
p
p
.
4
4
3
–
448
,
d
o
i
:
1
0
.
1
1
0
9
/
EI
T
4
8
9
9
9
.
2
0
2
0
.
9
2
0
8
2
8
4
.
[
1
3
]
S
.
K
u
mar,
B
.
Jan
e
t
,
a
n
d
S
.
N
e
e
l
a
k
a
n
t
a
n
,
“
I
d
e
n
t
i
f
i
c
a
t
i
o
n
o
f
mal
w
a
r
e
f
a
m
i
l
i
e
s
u
si
n
g
st
a
c
k
i
n
g
o
f
t
e
x
t
u
r
a
l
f
e
a
t
u
r
e
s
a
n
d
mac
h
i
n
e
l
e
a
r
n
i
n
g
,
”
Ex
p
e
r
t
S
y
s
t
e
m
s
w
i
t
h
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
2
0
8
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
s
w
a
.
2
0
2
2
.
1
1
8
0
7
3
.
[
1
4
]
M
.
G
o
p
i
n
a
t
h
a
n
d
S
.
C
.
S
e
t
h
u
r
a
m
a
n
,
“
A
c
o
mp
r
e
h
e
n
si
v
e
s
u
r
v
e
y
o
n
d
e
e
p
l
e
a
r
n
i
n
g
b
a
se
d
mal
w
a
r
e
d
e
t
e
c
t
i
o
n
t
e
c
h
n
i
q
u
e
s,”
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
Re
v
i
e
w
,
v
o
l
.
4
7
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
sr
e
v
.
2
0
2
2
.
1
0
0
5
2
9
.
[
1
5
]
N
.
K
a
n
n
o
u
f
,
M
.
L
a
b
b
i
,
Y
.
C
h
a
h
i
d
,
M
.
B
e
n
a
b
d
e
l
l
a
h
,
a
n
d
A
.
A
z
i
z
i
,
“
A
k
e
y
e
st
a
b
l
i
sh
me
n
t
a
t
t
e
m
p
t
b
a
se
d
o
n
g
e
n
e
t
i
c
a
l
g
o
r
i
t
h
ms
a
p
p
l
i
e
d
t
o
r
f
i
d
t
e
c
h
n
o
l
o
g
i
e
s,”
I
n
t
e
rn
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
S
e
c
u
r
i
t
y
a
n
d
Pri
v
a
c
y
,
v
o
l
.
1
5
,
n
o
.
3
,
2
0
2
1
,
d
o
i
:
1
0
.
4
0
1
8
/
I
J
I
S
P
.
2
0
2
1
0
7
0
1
0
3
.
[
1
6
]
O
.
C
h
a
i
e
b
,
N
.
K
a
n
n
o
u
f
,
R
.
A
mj
o
u
n
,
a
n
d
M
.
B
e
n
a
b
d
e
l
l
a
h
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
-
b
a
se
d
i
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
sy
st
e
m
:
r
e
v
i
e
w
a
n
d
t
a
x
o
n
o
my
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
6
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
Bi
g
D
a
t
a
a
n
d
I
n
t
e
rn
e
t
o
f
T
h
i
n
g
s
,
2
0
2
3
,
p
p
.
1
0
–
21
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
0
3
1
-
2
8
3
8
7
-
1
_
2
.
[
1
7
]
M
.
B
e
r
h
i
l
i
,
O
.
C
h
a
i
e
b
,
a
n
d
M
.
B
e
n
a
b
d
e
l
l
a
h
,
“
I
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
sy
st
e
ms
i
n
I
o
T
b
a
se
d
o
n
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
:
a
st
a
t
e
o
f
t
h
e
a
r
t
,
”
Pro
c
e
d
i
a
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
2
5
1
,
p
p
.
9
9
–
1
0
7
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
r
o
c
s.2
0
2
4
.
1
1
.
0
8
9
.
[
1
8
]
S
.
B
a
g
u
i
a
n
d
H
.
B
r
o
c
k
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
f
o
r
a
n
d
r
o
i
d
sca
r
e
w
a
r
e
d
e
t
e
c
t
i
o
n
,
”
J
o
u
r
n
a
l
o
f
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
R
e
se
a
rc
h
,
v
o
l
.
1
5
,
n
o
.
1
,
p
p
.
1
–
1
5
,
2
0
2
2
,
d
o
i
:
1
0
.
4
0
1
8
/
j
i
t
r
.
2
9
8
3
2
6
.
[
1
9
]
M
.
H
u
may
u
n
,
N
.
Z
.
J
h
a
n
j
h
i
,
A
.
A
l
s
a
y
a
t
,
a
n
d
V
.
P
o
n
n
u
samy
,
“
I
n
t
e
r
n
e
t
o
f
t
h
i
n
g
s
a
n
d
r
a
n
so
mw
a
r
e
:
e
v
o
l
u
t
i
o
n
,
m
i
t
i
g
a
t
i
o
n
a
n
d
p
r
e
v
e
n
t
i
o
n
,
”
E
g
y
p
t
i
a
n
I
n
f
o
rm
a
t
i
c
s
J
o
u
rn
a
l
,
v
o
l
.
2
2
,
n
o
.
1
,
p
p
.
1
0
5
–
1
1
7
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
i
j
.
2
0
2
0
.
0
5
.
0
0
3
.
[
2
0
]
K
.
B
e
g
o
v
i
c
,
A
.
A
l
-
A
l
i
,
a
n
d
Q
.
M
a
l
l
u
h
i
,
“
C
r
y
p
t
o
g
r
a
p
h
i
c
r
a
n
so
mw
a
r
e
e
n
c
r
y
p
t
i
o
n
d
e
t
e
c
t
i
o
n
:
s
u
r
v
e
y
,
”
C
o
m
p
u
t
e
rs
a
n
d
S
e
c
u
ri
t
y
,
v
o
l
.
1
3
2
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
se
.
2
0
2
3
.
1
0
3
3
4
9
.
[
2
1
]
N
.
R
a
n
i
,
S
.
V
.
D
h
a
v
a
l
e
,
A
.
S
i
n
g
h
,
a
n
d
A
.
M
e
h
r
a
,
“
A
su
r
v
e
y
o
n
mac
h
i
n
e
l
e
a
r
n
i
n
g
-
b
a
se
d
r
a
n
so
mw
a
r
e
d
e
t
e
c
t
i
o
n
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s o
f
t
h
e
S
e
v
e
n
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
o
n
M
a
t
h
e
m
a
t
i
c
s
a
n
d
C
o
m
p
u
t
i
n
g
,
2
0
2
2
,
p
p
.
1
7
1
–
1
8
6
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
981
-
16
-
6
8
9
0
-
6
_
1
3
.
[
2
2
]
S
.
M
a
n
i
a
t
h
,
P
.
P
o
o
r
n
a
c
h
a
n
d
r
a
n
,
a
n
d
V
.
G
.
S
u
j
a
d
e
v
i
,
“
S
u
r
v
e
y
o
n
p
r
e
v
e
n
t
i
o
n
,
mi
t
i
g
a
t
i
o
n
a
n
d
c
o
n
t
a
i
n
me
n
t
o
f
r
a
n
s
o
mw
a
r
e
a
t
t
a
c
k
s,”
C
o
m
m
u
n
i
c
a
t
i
o
n
s
i
n
C
o
m
p
u
t
e
r
a
n
d
I
n
f
o
rm
a
t
i
o
n
S
c
i
e
n
c
e
,
v
o
l
.
9
6
9
,
p
p
.
3
9
–
5
2
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
9
8
1
-
13
-
5
8
2
6
-
5
_
3
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
I
n
t J
A
r
ti
f
I
n
tell
,
Vo
l.
14
,
No
.
3
,
J
u
n
e
2
0
2
5
:
2
1
0
2
-
2110
2110
[
2
3
]
T
.
M
c
I
n
t
o
sh
,
A
.
S
.
M
.
K
a
y
e
s,
Y
.
P
.
P
.
C
h
e
n
,
A
.
N
g
,
a
n
d
P
.
W
a
t
t
e
r
s,
“
D
y
n
a
mi
c
u
se
r
-
c
e
n
t
r
i
c
a
c
c
e
ss
c
o
n
t
r
o
l
f
o
r
d
e
t
e
c
t
i
o
n
o
f
r
a
n
so
mw
a
r
e
a
t
t
a
c
k
s
,
”
C
o
m
p
u
t
e
rs
a
n
d
S
e
c
u
r
i
t
y
,
v
o
l
.
1
1
1
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
se
.
2
0
2
1
.
1
0
2
4
6
1
.
[
2
4
]
T
.
M
c
I
n
t
o
sh
,
A
.
S
.
M
.
K
a
y
e
s,
Y
.
P
.
P
.
C
h
e
n
,
A
.
N
g
,
a
n
d
P
.
W
a
t
t
e
r
s,
“
A
p
p
l
y
i
n
g
st
a
g
e
d
e
v
e
n
t
-
d
r
i
v
e
n
a
c
c
e
ss
c
o
n
t
r
o
l
t
o
c
o
mb
a
t
r
a
n
so
mw
a
r
e
,
”
C
o
m
p
u
t
e
rs
a
n
d
S
e
c
u
r
i
t
y
,
v
o
l
.
1
2
8
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
se
.
2
0
2
3
.
1
0
3
1
6
0
.
[
2
5
]
X
.
L
u
o
a
n
d
Q
.
L
i
a
o
,
“
A
w
a
r
e
n
e
ss
e
d
u
c
a
t
i
o
n
a
s
t
h
e
k
e
y
t
o
r
a
n
so
mw
a
r
e
p
r
e
v
e
n
t
i
o
n
,
”
I
n
f
o
rm
a
t
i
o
n
S
y
st
e
m
s
S
e
c
u
ri
t
y
,
v
o
l
.
1
6
,
n
o
.
4
,
p
p
.
1
9
5
–
2
0
2
,
2
0
0
7
,
d
o
i
:
1
0
.
1
0
8
0
/
1
0
6
5
8
9
8
0
7
0
1
5
7
6
4
1
2
.
[
2
6
]
A
.
D
a
mo
d
a
r
a
n
,
F
.
D
i
T
r
o
i
a
,
C
.
A
.
V
i
sag
g
i
o
,
T
.
H
.
A
u
st
i
n
,
a
n
d
M
.
S
t
a
m
p
,
“
A
c
o
mp
a
r
i
so
n
o
f
st
a
t
i
c
,
d
y
n
a
m
i
c
,
a
n
d
h
y
b
r
i
d
a
n
a
l
y
si
s
f
o
r
mal
w
a
r
e
d
e
t
e
c
t
i
o
n
,
”
J
o
u
rn
a
l
o
f
C
o
m
p
u
t
e
r
V
i
ro
l
o
g
y
a
n
d
H
a
c
k
i
n
g
T
e
c
h
n
i
q
u
e
s
,
v
o
l
.
1
3
,
n
o
.
1
,
p
p
.
1
–
1
2
,
2
0
1
7
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
4
1
6
-
0
1
5
-
0
2
6
1
-
z.
[
2
7
]
D
.
M
a
n
i
k
a
n
d
a
n
a
n
d
J
.
D
h
i
l
i
p
a
n
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
f
o
r
i
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
sy
st
e
m
u
s
i
n
g
d
i
me
n
si
o
n
a
l
i
t
y
r
e
d
u
c
t
i
o
n
,
”
I
n
d
o
n
e
si
a
n
J
o
u
r
n
a
l
o
f
El
e
c
t
ri
c
a
l
En
g
i
n
e
e
r
i
n
g
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
3
4
,
n
o
.
1
,
p
p
.
4
3
0
–
4
4
0
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s.v
3
4
.
i
1
.
p
p
4
3
0
-
4
4
0
.
[
2
8
]
M
.
M
o
h
a
mm
a
d
i
e
t
a
l
.
,
“
A
c
o
mp
r
e
h
e
n
si
v
e
su
r
v
e
y
a
n
d
t
a
x
o
n
o
my
o
f
t
h
e
S
V
M
-
b
a
se
d
i
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
sy
st
e
ms,”
J
o
u
r
n
a
l
o
f
N
e
t
w
o
rk
a
n
d
C
o
m
p
u
t
e
r
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
7
8
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
n
c
a
.
2
0
2
1
.
1
0
2
9
8
3
.
[
2
9
]
D
.
S
g
a
n
d
u
r
r
a
,
L
.
M
u
ñ
o
z
-
G
o
n
z
á
l
e
z
,
R
.
M
o
h
se
n
,
a
n
d
E
.
C
.
L
u
p
u
,
“
A
u
t
o
mat
e
d
d
y
n
a
mi
c
a
n
a
l
y
si
s
o
f
r
a
n
so
mw
a
r
e
:
b
e
n
e
f
i
t
s,
l
i
mi
t
a
t
i
o
n
s
a
n
d
u
se
f
o
r
d
e
t
e
c
t
i
o
n
,
”
a
rX
i
v
-
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
p
p
.
1
–
1
2
,
2
0
1
6
.
[
3
0
]
M
.
S
.
A
b
b
a
si
,
H
.
A
l
-
S
a
h
a
f
,
M
.
M
a
n
so
o
r
i
,
a
n
d
I
.
W
e
l
c
h
,
“
B
e
h
a
v
i
o
r
-
b
a
se
d
r
a
n
so
mw
a
r
e
c
l
a
ssi
f
i
c
a
t
i
o
n
:
a
p
a
r
t
i
c
l
e
s
w
a
r
m
o
p
t
i
m
i
z
a
t
i
o
n
w
r
a
p
p
e
r
-
b
a
se
d
a
p
p
r
o
a
c
h
f
o
r
f
e
a
t
u
r
e
sel
e
c
t
i
o
n
,
”
A
p
p
l
i
e
d
S
o
f
t
C
o
m
p
u
t
i
n
g
,
v
o
l
.
1
2
1
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
so
c
.
2
0
2
2
.
1
0
8
7
4
4
.
[
3
1
]
A
.
T
h
a
k
k
a
r
a
n
d
R
.
L
o
h
i
y
a
,
“
A
su
r
v
e
y
o
n
i
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
sy
st
e
m:
f
e
a
t
u
r
e
sel
e
c
t
i
o
n
,
mo
d
e
l
,
p
e
r
f
o
r
man
c
e
me
a
su
r
e
s,
a
p
p
l
i
c
a
t
i
o
n
p
e
r
sp
e
c
t
i
v
e
,
c
h
a
l
l
e
n
g
e
s,
a
n
d
f
u
t
u
r
e
r
e
se
a
r
c
h
d
i
r
e
c
t
i
o
n
s,”
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
Re
v
i
e
w
,
v
o
l
.
5
5
,
n
o
.
1
,
p
p
.
4
5
3
–
5
6
3
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
0
4
6
2
-
0
2
1
-
1
0
0
3
7
-
9.
[
3
2
]
A
.
P
e
k
t
a
ş a
n
d
T
.
A
c
a
r
man
,
“
M
a
l
w
a
r
e
c
l
a
ssi
f
i
c
a
t
i
o
n
b
a
se
d
o
n
A
P
I
c
a
l
l
s a
n
d
b
e
h
a
v
i
o
u
r
a
n
a
l
y
si
s,”
I
ET I
n
f
o
rm
a
t
i
o
n
S
e
c
u
r
i
t
y
,
v
o
l
.
1
2
,
n
o
.
2
,
p
p
.
1
0
7
–
1
1
7
,
2
0
1
8
,
d
o
i
:
1
0
.
1
0
4
9
/
i
e
t
-
i
f
s.
2
0
1
7
.
0
4
3
0
.
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
O
m
a
r
Cha
ieb
is
a
P
h
.
D
.
st
u
d
e
n
t
in
th
e
L
a
b
o
ra
to
ry
o
f
A
rit
h
m
e
ti
c
,
S
c
ien
ti
f
i
c
Co
m
p
u
ti
n
g
,
a
n
d
th
e
ir
A
p
p
li
c
a
ti
o
n
s
(L
A
CS
A
)
a
t
th
e
F
a
c
u
lt
y
o
f
S
c
ien
c
e
,
M
o
h
a
m
e
d
F
irst
Un
iv
e
rsit
y
,
OU
JD
A
.
He
re
c
e
iv
e
d
h
is
m
a
ste
r’s
in
2
0
1
3
i
n
c
o
d
e
,
c
r
y
p
to
g
ra
p
h
y
,
a
n
d
se
c
u
rit
y
o
f
in
f
o
rm
a
ti
o
n
f
ro
m
th
e
F
a
c
u
lt
y
o
f
S
c
ien
c
e
s,
Un
iv
e
rsity
M
o
h
a
m
e
d
V
in
Ra
b
a
t,
M
o
ro
c
c
o
.
His
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
in
tr
u
sio
n
d
e
tec
ti
o
n
sy
ste
m
s,
a
rti
f
icia
l
in
telli
g
e
n
c
e
,
a
n
d
m
a
l
w
a
re
a
n
a
ly
sis.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
o
m
a
r.
c
h
a
ieb
.
m
e
n
@g
m
a
il
.
c
o
m
.
Na
b
il
K
a
n
n
o
u
f
is
a
p
ro
fe
ss
o
r
o
f
c
o
m
p
u
ter
sc
ien
c
e
a
t
A
b
d
e
lm
a
le
k
Ess
a
a
d
i
Un
iv
e
rsit
y
in
M
o
ro
c
c
o
,
a
p
o
siti
o
n
h
e
h
a
s
h
e
ld
sin
c
e
2
0
2
0
.
He
h
o
l
d
s
a
P
h
.
D.
i
n
c
o
m
p
u
ter
sc
ien
c
e
a
n
d
e
a
rn
e
d
h
is
m
a
ste
r’s
d
e
g
re
e
in
c
o
m
p
u
ter
e
n
g
in
e
e
rin
g
in
2
0
1
0
f
ro
m
F
a
c
u
lt
y
o
f
S
c
ien
c
e
s,
M
o
h
a
m
e
d
P
re
m
ier
Un
iv
e
rsit
y
’s
,
Ou
jd
a
,
M
o
ro
c
c
o
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
n
a
b
il
.
k
a
n
n
o
u
f
@g
m
a
il
.
c
o
m
.
M
o
h
a
m
m
e
d
B
e
n
a
b
d
e
ll
a
h
is
a
p
r
o
f
e
ss
o
r
o
f
c
o
m
p
u
ter
sc
ien
c
e
a
t
M
o
h
a
m
m
e
d
F
irst
Un
iv
e
rsit
y
in
Ou
jd
a
,
M
o
ro
c
c
o
.
H
e
e
a
rn
e
d
h
is
P
h
.
D.
in
e
n
g
in
e
e
rin
g
sc
ien
c
e
s
f
ro
m
M
o
h
a
m
m
e
d
V
U
n
iv
e
rsity
in
Ra
b
a
t,
M
o
r
o
c
c
o
,
in
J
u
n
e
2
0
0
7
.
Re
n
o
w
n
e
d
f
o
r
h
is
in
tern
a
ti
o
n
a
ll
y
re
c
o
g
n
ize
d
re
se
a
rc
h
in
c
y
b
e
rs
e
c
u
rit
y
,
a
rti
f
ici
a
l
in
telli
g
e
n
c
e
,
a
n
d
im
a
g
e
p
ro
c
e
s
sin
g
,
h
e
a
c
ti
v
e
l
y
c
o
n
tri
b
u
tes
to
a
d
v
a
n
c
in
g
t
h
e
se
f
ield
s.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
m
e
d
_
b
e
n
a
b
d
e
ll
a
h
@y
a
h
o
o
.
f
r.
Evaluation Warning : The document was created with Spire.PDF for Python.