Co
m
pu
t
er
Science
a
n
d In
f
o
r
m
a
t
io
n T
ec
hn
o
lo
g
ies
Vo
l.
2
,
No
.
3
,
No
v
em
b
er
2
0
2
1
,
p
p
.
1
03
~
1
12
I
SS
N:
2722
-
3221
,
DOI
: 1
0
.
1
1
5
9
1
/
csit
.
v
2
i
3
.p
1
03
-
1
12
ļ²
103
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
H
a
ncitor
m
a
lw
a
r
e re
co
g
nition us
i
n
g
s
w
a
rm
intellige
nt
techniqu
e
L
a
heeb
M
.
I
bra
hi
m
1
,
M
a
is
ir
re
e
m
At
heee
d K
a
m
a
l
2
,
A
bd
u
lSa
t
t
a
r
A.
Al
-
Alus
i
3
1,
2
De
p
a
rtm
e
n
t
o
f
S
o
f
t
w
a
re
En
g
in
e
e
rin
g
,
Co
ll
e
g
e
o
f
Co
m
p
u
ter S
c
ien
c
e
&
M
a
th
,
Un
iv
e
rsity
o
f
M
o
su
l,
M
o
su
l
,
Ira
q
3
Co
ll
e
g
e
o
f
S
e
c
u
rit
y
a
n
d
G
lo
b
a
l
S
tu
d
ies
,
A
m
e
ri
c
a
n
Un
iv
e
rsit
y
in
th
e
Em
irate
s,
Du
b
a
i,
Un
it
e
d
A
ra
b
E
m
irat
e
s
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
n
6
,
2
0
2
0
R
ev
i
s
ed
M
a
r
9
,
2
0
2
1
A
cc
ep
ted
A
pr
18
,
2
0
2
1
M
a
lw
a
r
e
is
a
g
lo
b
a
l
risk
rif
e
d
e
si
g
n
e
d
to
d
e
stro
y
c
o
m
p
u
ter
s
y
ste
m
s
w
it
h
o
u
t
t
h
e
o
w
n
e
r'
s
k
n
o
w
led
g
e
.
It
is
stil
l
re
g
a
rd
e
d
a
s
th
e
m
o
st
p
o
p
u
lar
t
h
re
a
t
th
a
t
a
tt
a
c
k
s
c
o
m
p
u
ter
sy
ste
m
s.
Earl
y
re
c
o
g
n
it
io
n
o
f
u
n
k
n
o
w
n
m
a
l
w
a
r
e
re
m
a
in
s
a
p
ro
b
lem
.
S
w
a
r
m
In
telli
g
e
n
c
e
(S
I),
u
su
a
ll
y
c
u
sto
m
e
r
so
c
ieties
,
c
o
m
m
u
n
ica
te
lo
c
a
ll
y
w
it
h
th
e
ir
d
o
m
a
in
a
n
d
w
it
h
e
a
c
h
o
th
e
r
.
Cli
e
n
ts
u
se
v
e
r
y
si
m
p
le
ru
les
o
f
b
e
h
a
v
io
r
a
n
d
t
h
e
in
tera
c
ti
o
n
s
b
e
tw
e
e
n
th
e
m
lea
d
to
sm
a
rt
a
p
p
e
a
ra
n
c
e
,
n
o
ti
c
e
a
b
le,
in
d
iv
id
u
a
l
b
e
h
a
v
io
r
a
n
d
o
p
t
im
iz
e
d
so
l
u
ti
o
n
o
f
p
ro
b
lem
a
n
d
S
I
h
a
s
b
e
e
n
su
c
c
e
ss
f
u
ll
y
a
p
p
li
e
d
in
m
a
n
y
f
ie
l
d
s,
e
sp
e
c
ially
f
o
r
m
a
l
w
a
re
io
n
tas
k
s.
S
I
a
lso
sa
v
e
s
a
c
o
n
sid
e
ra
b
le
a
m
o
u
n
t
o
f
ti
m
e
a
n
d
e
n
h
a
n
c
e
s
th
e
p
re
c
isio
n
o
f
th
e
m
a
l
w
a
r
e
re
c
o
g
n
it
io
n
sy
ste
m
.
T
h
is
p
a
p
e
r
i
n
tro
d
u
c
e
s
a
m
a
l
w
a
re
re
c
o
g
n
it
io
n
s
y
ste
m
f
o
r
Ha
n
c
it
o
r
m
a
lwa
re
u
sin
g
th
e
G
ra
y
W
o
lf
Op
ti
m
iza
ti
o
n
a
lg
o
ri
th
m
(
GW
O)
a
n
d
A
rti
f
icia
l
Be
e
Co
lo
n
y
a
l
g
o
rit
h
m
(A
BC),
w
h
ich
c
a
n
e
ffe
c
ti
v
e
l
y
re
c
o
g
n
ize
Ha
n
c
it
o
r
in
n
e
tw
o
rk
s.
K
ey
w
o
r
d
s
:
A
r
ti
f
icial
i
n
tel
lig
e
n
t te
c
h
n
iq
u
e
A
r
ti
f
icial
b
ee
co
lo
n
y
alg
o
r
it
h
m
(
A
B
C
)
Gr
a
y
w
o
l
v
e
s
o
p
ti
m
izatio
n
Han
cito
r
m
al
w
ar
e
Ma
l
w
ar
e
r
ec
o
g
n
itio
n
S
w
ar
m
i
n
telli
g
e
n
ce
(
SI)
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
:
L
a
h
ee
b
M.
I
b
r
ah
i
m
Dep
ar
t
m
en
t o
f
So
f
t
w
ar
e
E
n
g
i
n
ee
r
in
g
C
o
lleg
e
o
f
C
o
m
p
u
ter
Scie
n
ce
&
M
at
h
Un
i
v
er
s
it
y
o
f
Mo
s
u
l
A
lj
a
m
eia,
Mo
s
u
l,
I
r
aq
E
m
ail: la
h
ee
b
_
alzu
b
aid
y
3
2
1
9
6
6
@
u
o
m
o
s
u
l.e
d
u
.
iq
1.
I
NT
RO
D
UCT
I
O
N
Ma
l
w
ar
e
i
s
r
ec
o
g
n
ized
as
a
p
r
o
g
r
am
cr
ea
ted
to
d
is
ab
le
co
m
p
u
ter
o
p
er
atio
n
an
d
ac
ce
s
s
to
p
r
iv
ate
co
m
p
u
ter
s
y
s
te
m
s
.
W
h
en
t
h
e
m
al
w
ar
e
is
i
m
p
le
m
e
n
ted
,
th
e
m
alicio
u
s
p
r
o
g
r
a
m
d
esi
g
n
er
ta
k
es a
d
v
a
n
ta
g
e
o
f
t
h
e
b
en
ef
it
o
f
ac
ce
s
s
i
n
g
t
h
e
co
m
p
u
ter
s
y
s
te
m
s
o
f
th
e
i
n
f
ec
ted
d
ev
ice,
an
d
co
llects
p
er
s
o
n
al
in
f
o
r
m
atio
n
an
d
ev
er
y
t
h
i
n
g
t
h
at
t
h
e
d
ev
ice
co
n
tain
s
w
it
h
o
u
t
t
h
e
co
n
s
en
t
o
f
th
e
co
m
p
u
ter
o
w
n
er
.
C
u
r
r
en
t
l
y
,
m
al
w
ar
e
i
s
u
s
ed
t
o
s
teal
i
m
p
o
r
tan
t
co
m
m
er
cial
a
n
d
b
an
k
in
g
in
f
o
r
m
at
io
n
.
I
t
is
u
s
u
all
y
u
s
ed
w
id
el
y
a
g
ai
n
s
t
g
o
v
er
n
m
e
n
t
w
eb
s
ites
,
co
r
p
o
r
ate
s
ites
,
an
d
b
an
k
s
to
co
llect
p
r
o
tecte
d
in
f
o
r
m
at
io
n
o
r
d
is
r
u
p
t
it
s
o
p
er
atio
n
in
g
en
er
al.
Ma
l
w
ar
e
i
s
u
s
u
a
ll
y
u
s
ed
ag
a
in
s
t
i
n
d
iv
id
u
als
to
o
b
tain
p
er
s
o
n
al
i
n
f
o
r
m
atio
n
,
s
u
ch
a
s
b
an
k
ca
r
d
n
u
m
b
er
s
.
T
h
e
d
if
f
er
en
t
t
y
p
e
s
o
f
m
al
w
ar
e
cr
ea
te
d
a
m
ag
e
s
d
u
e
t
o
th
eir
r
e
m
o
v
al
d
i
f
f
icu
lt
y
u
p
o
n
i
n
s
ta
llatio
n
o
n
t
h
e
p
r
e
y
's
m
a
ch
in
e.
T
h
e
s
e
v
er
it
y
o
f
th
e
s
o
f
t
w
ar
e
r
an
g
e
s
f
r
o
m
m
in
o
r
in
co
n
v
en
ien
ce
to
ir
r
ep
ar
a
b
le
h
a
r
m
th
at
r
eq
u
ir
es
r
e
f
o
r
m
a
ttin
g
th
e
h
ar
d
d
r
iv
e.
Ma
l
w
ar
e
is
co
n
s
id
er
ed
a
g
r
ea
t
d
an
g
er
a
n
d
t
h
r
ea
ts
s
tan
d
u
p
t
o
th
e
w
o
r
ld
o
f
t
h
e
I
n
ter
n
e
t
an
d
co
m
p
u
te
r
n
et
w
o
r
k
s
to
d
a
y
a
n
d
th
e
s
e
m
al
w
ar
e
u
s
u
all
y
co
m
e
in
v
ar
io
u
s
f
o
r
m
s
s
u
ch
as T
r
o
j
an
h
o
r
s
e,
Vir
u
s
,
W
o
r
m
,
B
o
tn
et,
Sp
y
w
ar
e,
an
d
A
d
w
ar
e.
[
1
]
.
F
ir
e
E
y
e
r
ep
o
r
ted
th
at
4
7
%
o
f
o
r
g
an
izatio
n
s
h
ad
e
n
co
u
n
ter
ed
b
r
ea
ch
es
o
f
t
h
e
m
al
w
ar
e
ac
cid
en
t
s
a
f
et
y
.
Ma
l
w
ar
e
is
co
n
s
ta
n
tl
y
g
r
o
w
i
n
g
i
n
s
ize,
d
iv
er
s
it
y
,
a
n
d
s
p
ee
d
.
T
h
u
s
,
m
al
w
ar
e
h
a
s
b
ec
o
m
e
co
m
p
le
x
an
d
u
s
es
n
e
w
a
n
d
ad
v
an
ce
d
m
e
th
o
d
s
to
in
f
ec
t c
o
m
p
u
ter
s
an
d
s
m
ar
t p
h
o
n
es [
1
]
.
Ma
n
y
tec
h
n
iq
u
e
s
w
er
e
u
s
ed
i
n
m
al
w
ar
e
clas
s
i
f
icatio
n
a
n
d
r
ec
o
g
n
itio
n
[2
]
.
A
d
ee
p
n
eu
r
al
n
et
w
o
r
k
u
s
e
s
f
o
r
m
al
w
ar
e
d
y
n
a
m
ic
b
eh
a
v
i
o
r
r
ec
o
g
n
itio
n
,
in
w
h
ic
h
d
ee
p
n
eu
r
al
n
et
w
o
r
k
co
u
ld
r
ec
o
g
n
is
e
f
u
t
u
r
e
m
al
w
ar
e
Evaluation Warning : The document was created with Spire.PDF for Python.
ļ²
I
SS
N
:
2722
-
3221
C
o
m
p
u
t.
Sci.
I
n
f
.
T
ec
h
n
o
l.
,
Vo
l.
2
,
No
.
3
,
No
v
em
b
er
20
2
1
:
1
03
ā
1
12
104
th
r
o
u
g
h
th
e
g
e
n
er
ati
v
e
ad
v
e
r
s
ar
ial
n
et
w
o
r
k
i
m
p
le
m
e
n
tati
o
n
.
A
S
w
ar
m
i
n
telli
g
e
n
t
te
ch
n
iq
u
e
u
s
ed
f
o
r
r
ec
o
g
n
itio
n
o
f
m
al
w
ar
e
as
i
n
[
3
]
-
[
4
]
w
h
er
e
P
ar
ticle
S
w
ar
m
Op
ti
m
izatio
n
(
P
SO)
is
u
s
es
t
o
b
u
ild
a
s
y
s
te
m
to
r
ec
o
g
n
is
e
m
al
w
ar
e
,
in
t
h
ese
s
tu
d
ies
t
h
e
r
esear
c
h
er
's
r
ef
i
n
e
m
en
t
t
h
e
r
ate
o
f
r
ec
o
g
n
itio
n
w
it
h
P
SO
.
I
n
[
5
]
t
h
e
r
esear
ch
er
s
ā
u
s
i
n
g
P
SO
in
t
h
e
r
ec
o
g
n
itio
n
o
f
t
h
e
alg
o
r
it
h
m
an
d
to
i
m
p
r
o
v
e
th
e
r
ec
o
g
n
i
tio
n
r
ate.
I
n
[
5
]
,
th
e
r
esear
ch
er
s
r
ec
o
g
n
ize
m
al
w
ar
e
u
s
in
g
s
tati
s
tical
ap
p
r
o
ac
h
.
An
o
th
er
ap
p
r
o
ac
h
f
o
r
r
ec
o
g
n
is
i
n
g
m
al
w
ar
e
u
s
ed
as
i
n
[
6
]
,
w
h
er
e
t
h
e
r
esear
ch
er
u
s
ed
a
d
ata
m
i
n
i
n
g
m
et
h
o
d
.
[
7
]
-
[
1
1
]
u
s
ed
m
ac
h
i
n
e
lear
n
i
n
g
f
o
r
r
ec
o
g
n
i
s
in
g
m
al
w
ar
e.
An
o
th
er
s
t
u
d
y
u
s
ed
a
h
y
b
r
id
ap
p
r
o
ac
h
w
h
ic
h
en
h
a
n
ce
s
t
h
e
p
er
f
o
r
m
an
ce
to
r
ec
o
g
n
is
e
u
n
k
n
o
w
n
m
al
w
ar
e
,
r
ec
o
g
n
izer
p
r
o
p
o
s
ed
in
[
1
2
]
-
[
1
7
]
,
as
[
1
2
]
,
w
h
e
r
e
it
s
u
g
g
es
ts
a
m
al
w
ar
e
r
ec
o
g
n
itio
n
s
y
s
te
m
f
o
r
An
d
r
o
id
s
y
s
te
m
u
s
i
n
g
co
n
ce
p
t
o
f
h
y
b
r
id
in
telli
g
e
n
t
d
ep
en
d
ed
o
n
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
i
n
e
(
SVM)
w
i
th
e
v
o
lu
tio
n
ar
y
alg
o
r
ith
m
s
(
g
e
n
etic
al
g
o
r
ith
m
(
GA
)
a
n
d
P
SO)
to
en
h
a
n
ce
m
al
w
ar
e
r
ec
o
g
n
itio
n
,
w
h
ic
h
i
s
r
esp
ec
tiv
el
y
r
ef
er
r
ed
to
as
Dr
o
id
-
HE
SVMG
A
a
n
d
D
r
o
id
-
HE
SVMP
SO,
to
in
cr
ea
s
e
th
e
p
r
ec
is
io
n
r
ate
to
r
ec
o
g
n
ize
m
al
w
ar
e
.
[
1
3
]
T
h
e
m
et
h
o
d
s
b
ased
o
n
Naiv
e
-
B
a
y
es,
S
u
p
p
o
r
t
Vec
to
r
Ma
ch
in
e,
an
d
D
ec
is
io
n
T
r
ee
u
s
ed
as
r
ec
o
g
n
i
s
er
s
,
ar
e
ex
h
a
u
s
tib
les
t
h
at
b
o
o
s
t
d
ec
is
io
n
.
T
r
ee
is
a
to
p
m
et
h
o
d
u
s
e
d
as
a
r
ec
o
g
n
is
er
o
f
m
a
l
w
ar
e
.
[
1
4
]
A
m
al
w
ar
e
r
ec
o
g
n
itio
n
m
et
h
o
d
h
as
b
ee
n
p
r
o
p
o
s
ed
u
s
in
g
i
m
a
g
e
p
r
o
ce
s
s
in
g
m
et
h
o
d
s
,
w
h
ich
d
ep
icts
m
al
w
a
r
e
b
in
ar
y
as
g
r
a
y
s
ca
le
i
m
a
g
e
s
.
A
K
-
n
ea
r
est
n
ei
g
h
b
o
r
tech
n
iq
u
e
w
it
h
E
u
cl
id
ea
n
d
is
tan
ce
m
et
h
o
d
is
u
s
ed
f
o
r
m
al
w
ar
e
r
ec
o
g
n
itio
n
.
[
1
5
]
P
r
o
o
f
ed
a
co
n
ce
p
t
o
f
u
s
i
n
g
h
y
b
r
id
in
tell
ig
e
n
t
to
r
ec
o
g
n
i
s
e
m
al
w
ar
e
b
ased
o
n
5
r
ec
o
g
n
is
er
s
i.e
.
k
-
Nea
r
est
Neig
h
b
o
r
s
(
k
NN)
,
Naiv
e
B
a
y
es,
J
4
8
Dec
is
io
n
T
r
ee
,
Su
p
p
o
r
t
Vec
to
r
Ma
ch
in
e
(
SV
M)
,
an
d
Mu
ltil
a
y
er
P
er
ce
p
tr
o
n
Neu
r
al
Net
w
o
r
k
(
ML
P
)
.
[
1
6
]
B
u
ilt
OP
E
M
s
y
s
t
e
m
,
w
h
ich
u
s
ed
4
al
g
o
r
ith
m
s
as
r
ec
o
g
n
i
s
er
s
,
t
h
ese
m
et
h
o
d
s
ar
e
Dec
is
io
n
T
r
ee
,
K
-
n
ea
r
e
s
t
n
ei
g
h
b
o
r
,
B
ay
e
s
ia
n
n
et
w
o
r
k
,
a
n
d
Su
p
p
o
r
t
Vec
to
r
Ma
ch
i
n
e
to
r
ec
o
g
n
is
e
u
n
k
n
o
w
n
m
al
w
ar
e,
a
s
i
m
ilar
w
o
r
k
is
d
o
n
e
b
y
[
1
7
]
t
o
r
ec
o
g
n
is
e
th
e
m
al
w
ar
e
u
s
i
n
g
SV
M,
I
B
1
,
D
T
an
d
R
F.
[
1
8
]
p
r
o
p
o
s
ed
a
m
et
h
o
d
w
h
ic
h
u
s
e
d
s
u
p
p
o
r
t v
ec
to
r
m
ac
h
i
n
e
r
ec
o
g
n
izer
.
Ma
l
w
ar
e
cla
s
s
i
f
icatio
n
an
d
r
e
co
g
n
itio
n
u
s
i
n
g
s
w
ar
m
i
n
tel
lig
en
t
tec
h
n
iq
u
e
ar
e
s
ig
n
i
f
ica
n
t
a
r
ea
s
in
t
h
e
r
ec
o
g
n
itio
n
o
f
m
al
icio
u
s
ap
p
li
ca
tio
n
s
.
T
h
e
m
et
h
o
d
u
s
ed
b
y
m
al
w
ar
e
r
ec
o
g
n
ize
ex
p
er
ts
d
ep
en
d
s
o
n
th
e
p
r
o
b
le
m
an
d
d
ataset
r
eg
ar
d
less
o
f
th
e
ca
teg
o
r
ical
o
r
n
u
m
er
ical
o
u
tp
u
t
d
ata,
th
er
ef
o
r
e
s
w
ar
m
i
n
tell
ig
en
t
tech
n
iq
u
e
s
ca
n
b
e
u
s
ed
f
o
r
r
ec
o
g
n
itio
n
,
f
o
r
ec
asti
n
g
,
an
d
esti
m
atio
n
m
al
w
ar
es
[
3
]
.
I
n
th
is
p
ap
er
S
w
ar
m
I
n
telli
g
en
t
(
SI)
alg
o
r
ith
m
s
ar
e
u
s
ed
to
r
ec
o
g
n
is
e
Ha
n
cito
r
m
al
w
ar
e
b
ec
au
s
e
SI
ar
e
f
a
m
iliar
in
r
ec
o
g
n
it
io
n
an
d
clas
s
i
f
icatio
n
ap
p
licatio
n
s
d
u
e
to
t
h
e
y
d
ep
en
d
ed
o
n
s
i
m
p
le
id
ea
a
n
d
b
ein
g
ac
cu
r
ate
an
d
ea
s
y
co
n
ce
p
t
s
to
i
m
p
le
m
en
t,
d
o
n
o
t
r
eq
u
ir
e
p
r
o
g
r
ess
iv
e
in
f
o
r
m
at
i
o
n
an
d
I
t
i
s
o
f
te
n
u
s
ed
to
s
o
lv
e
a
w
id
e
r
a
n
g
e
o
f
p
r
o
b
le
m
s
th
a
t
co
v
er
m
an
y
ap
p
licatio
n
s
[
1
9
]
.
SI
alg
o
r
ith
m
s
ar
e
d
iv
id
ed
in
t
w
o
ca
teg
o
r
ies
d
ep
en
d
in
g
o
n
its
t
y
p
e;
th
e
f
ir
s
t
t
y
p
e
is
th
e
i
n
s
ec
t
-
b
ased
ca
teg
o
r
y
f
o
r
e
x
a
m
p
le,
An
t
C
o
lo
n
y
Op
ti
m
izatio
n
(
AC
O)
,
A
r
tific
ial
B
ee
C
o
lo
n
y
(
A
B
C
)
etc
.
T
h
e
s
ec
o
n
d
ca
teg
o
r
y
is
A
n
i
m
a
l
-
b
ased
alg
o
r
ith
m
s
w
h
ic
h
in
cl
u
d
e
P
r
ac
tical
S
w
ar
m
Op
ti
m
izatio
n
(
P
SO)
,
ar
tif
icial
Fis
h
,
an
d
Gr
e
y
W
o
lf
Op
ti
m
izatio
n
(
GW
O
)
etc
.
[
1
9
]
-
[
2
0
]
.
T
w
o
o
f
S
w
a
r
m
I
n
telli
g
e
n
t
alg
o
r
it
h
m
s
to
r
ec
o
g
n
i
s
in
g
Ha
n
cito
r
m
al
w
ar
e
u
s
e
s
in
th
i
s
p
ap
er
d
ep
en
d
o
n
its
ca
teg
o
r
ies,
f
ir
s
t
f
o
r
A
n
i
m
a
l
-
b
ased
alg
o
r
it
h
m
s
is
Gr
a
y
W
o
lf
Op
ti
m
izatio
n
al
g
o
r
ith
m
(
GW
O)
an
d
s
ec
o
n
d
f
o
r
i
n
s
ec
t
-
b
as
ed
ca
teg
o
r
y
i
s
A
r
ti
f
icia
l
B
ee
C
o
lo
n
y
al
g
o
r
ith
m
(
A
B
C
)
.
GW
O
is
u
s
ed
in
t
h
i
s
p
ap
er
to
r
ec
o
g
n
ize
Han
ict
o
r
m
al
w
ar
e
d
u
e
to
t
h
e
ad
v
a
n
tag
e
s
o
f
GW
O
b
y
m
ai
n
tai
n
in
g
i
n
f
o
r
m
atio
n
o
n
t
h
e
s
ea
r
ch
s
p
ac
e
o
v
er
co
m
e
t
h
e
co
u
r
s
e
o
f
iter
atio
n
s
.
[
1
9
]
-
[
2
1
]
,
u
s
es
m
e
m
o
r
y
to
s
to
r
e
th
e
b
est
s
o
lu
tio
n
o
b
tain
ed
,
co
n
tai
n
s
s
o
m
e
p
ar
a
m
eter
s
to
ad
ju
s
t
a
n
d
i
m
p
le
m
e
n
ted
i
n
ea
s
y
w
a
y
[
1
9
]
an
d
GW
O
h
av
e
ca
p
ab
ilit
ie
s
to
s
o
lv
e
o
p
ti
m
izatio
n
p
r
o
b
lem
s
[
2
0
]
-
[
2
4
]
t
h
r
o
u
g
h
t
h
e
s
o
cial
h
ier
ar
ch
y
o
f
GW
O.
T
h
e
s
ec
o
n
d
SI
alg
o
r
ith
m
u
s
e
d
to
id
en
tify
Ha
n
cito
r
Ma
l
war
e
is
th
e
A
B
C
alg
o
r
it
h
m
wh
er
e
A
B
C
alg
o
r
ith
m
r
eq
u
ir
es
a
m
in
i
m
u
m
le
v
el
o
f
u
n
d
er
s
ta
n
d
in
g
o
f
th
e
p
r
o
b
lem
ar
ea
as
it
d
o
es
n
o
t
r
eq
u
ir
e
c
o
m
p
le
x
tr
ain
i
n
g
d
ata
as
th
e
b
ee
r
ec
r
u
iter
b
etter
u
p
d
ates
h
i
m
s
el
f
w
it
h
th
e
attr
ib
u
te
co
r
r
elatio
n
an
d
u
p
d
ate
d
ir
ec
tly
o
n
th
e
p
er
f
o
r
m
a
n
ce
o
f
t
h
e
cla
s
s
i
f
icati
o
n
ca
teg
o
r
y
t
h
a
n
th
e
k
n
o
w
led
g
e
o
f
t
h
e
w
a
g
g
le
d
a
n
ce
[
2
5
]
-
[
2
6
]
.
T
h
er
ef
o
r
e,
th
ese
t
y
p
es
o
f
p
r
o
ce
d
u
r
es
ce
r
tain
l
y
h
av
e
a
g
r
ea
ter
p
o
ten
tial
i
n
i
m
p
r
o
v
in
g
cla
s
s
i
f
icatio
n
ac
cu
r
ac
y
.
I
n
an
A
B
C
d
ata
class
i
f
icatio
n
it
ca
n
b
e
a
m
i
m
ic
b
eh
av
io
r
o
f
i
n
s
ec
t
s
to
f
i
n
d
th
e
b
est
f
o
o
d
s
o
u
r
ce
,
an
d
b
u
ild
an
i
d
ea
l
n
est
s
tr
u
ct
u
r
e.
T
h
e
b
ee
s
d
is
tr
ib
u
te
th
e
w
o
r
k
l
o
ad
am
o
n
g
t
h
e
m
s
el
v
es,
w
h
ic
h
d
o
es
n
o
t
clas
s
i
f
y
t
h
e
d
ata
i
n
co
r
r
ec
tl
y
an
d
ar
e
h
o
m
o
g
en
eo
u
s
s
p
ec
tr
u
m
a
n
d
s
p
ec
tr
al
in
ter
f
er
e
n
ce
.
Dan
c
in
g
b
e
h
av
io
r
aid
s
i
n
o
p
ti
m
al
d
es
ig
n
.
T
h
e
W
ag
g
le
d
an
ce
is
o
n
e
o
f
th
e
m
ec
h
a
n
i
s
m
s
f
o
r
s
h
ar
in
g
th
e
ex
i
s
ti
n
g
f
o
o
d
s
o
u
r
ce
,
w
h
ic
h
in
d
icate
s
a
g
o
o
d
ca
n
d
id
ate
f
o
r
d
ev
elo
p
in
g
a
n
e
w
s
m
ar
t
s
ea
r
ch
f
o
r
th
e
o
p
ti
m
al
s
o
l
u
tio
n
[
2
5
]
-
[
2
6
]
.
T
h
e
r
est
o
f
t
h
e
p
ap
er
is
ar
r
an
g
ed
in
th
e
f
o
llo
w
i
n
g
s
t
y
le;
in
s
ec
tio
n
t
w
o
is
t
h
eo
r
etica
l
b
ac
k
g
r
o
u
n
d
ex
p
lo
r
es
m
al
w
ar
e
r
ec
o
g
n
itio
n
tec
h
n
iq
u
es
a
n
d
Han
cito
r
m
al
w
ar
e
a
n
d
its
d
an
g
er
,
w
h
ile
i
n
s
ec
t
io
n
th
r
ee
th
e
s
w
ar
m
in
te
lli
g
en
t
tec
h
n
i
q
u
es
u
s
ed
in
m
al
w
ar
e
r
ec
o
g
n
i
ti
o
n
,
GW
O
an
d
A
B
C
alg
o
r
ith
m
s
ar
e
ex
p
lai
n
ed
.
Sect
io
n
f
o
u
r
p
r
esen
t
s
t
h
e
p
r
o
p
o
s
ed
m
o
d
el,
f
o
llo
w
ed
b
y
t
h
e
r
es
u
lt
s
o
f
t
h
e
co
m
p
ar
is
o
n
in
s
ec
tio
n
f
i
v
e,
i
n
s
ec
tio
n
s
i
x
t
h
e
co
n
cl
u
s
io
n
an
d
f
u
t
u
r
e
w
o
r
k
.
2.
M
AL
WARE RE
CO
G
N
I
T
O
N
T
E
CH
N
I
Q
UE
S
Han
cito
r
s
o
m
eti
m
es
ca
lled
T
o
r
d
al
an
d
C
h
a
n
ito
r
.
T
h
e
m
a
l
w
ar
e
h
as
b
ee
n
ar
o
u
n
d
s
i
n
ce
2
0
1
4
.
Han
icto
r
attac
k
to
in
f
ec
t
u
s
er
s
'
d
e
v
ices
i
s
m
alic
io
u
s
s
p
a
m
ca
m
p
a
ig
n
s
;
Han
cito
r
m
o
s
tl
y
g
ets
i
n
to
d
ev
i
ce
s
w
ith
M
icr
o
s
o
f
t
Of
f
ice
f
iles
.
O
n
ce
t
h
e
u
s
er
d
o
w
n
lo
ad
s
an
d
o
p
en
s
t
h
e
m
a
licio
u
s
f
ile,
t
h
e
m
al
w
ar
e
eit
h
er
u
s
es
th
e
l
u
r
e
to
tr
ick
t
h
e
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.
ļ²
Ha
n
cito
r
ma
lw
a
r
e
r
ec
o
g
n
itio
n
u
s
in
g
s
w
a
r
m
in
tellig
en
t te
ch
n
iq
u
e
(
La
h
ee
b
M.
I
b
r
a
h
im
)
105
v
icti
m
i
n
to
en
ab
lin
g
m
ac
r
o
s
o
r
u
s
es
an
e
x
p
lo
it.
Af
ter
th
a
t
Han
cito
r
w
ill
b
e
eith
er
d
o
w
n
l
o
ad
ed
f
r
o
m
th
e
C
2
s
er
v
er
o
r
d
r
o
p
p
ed
f
r
o
m
a
n
O
f
f
ice
f
ile.
T
h
e
n
ex
t
s
te
p
is
its
e
x
ec
u
tio
n
d
u
r
i
n
g
w
h
ic
h
t
h
e
m
al
w
ar
e
d
o
w
n
lo
ad
s
th
e
m
ai
n
p
a
y
lo
ad
,
u
s
u
al
l
y
a
T
r
o
j
an
s
u
ch
as
P
o
n
y
,
Va
w
tr
a
k
,
o
r
DE
L
o
ad
er
.
Han
cito
r
m
e
th
o
d
o
f
in
f
ec
ti
n
g
t
h
e
v
ict
i
m
's
m
ac
h
in
e
u
s
in
g
m
a
n
y
w
a
y
s
,
o
n
e
o
f
th
e
s
e
w
a
y
s
is
u
s
in
g
.
D
OC
attac
h
m
en
ts
ta
k
i
n
g
ad
v
a
n
tag
e
o
f
Mic
r
o
s
o
f
t
ā
s
d
y
n
a
m
ic
d
ata
ex
ch
a
n
g
e
(
DDE
)
tech
n
iq
u
e.
[
2
7
]
,
th
e
u
s
er
m
u
s
t f
ir
s
t d
o
w
n
lo
ad
th
e
f
ile
an
d
th
en
ac
tiv
ate
m
ac
r
o
s
,
ig
n
o
r
i
n
g
m
u
l
tip
le
s
ec
u
r
it
y
w
ar
n
in
g
s
.
Ma
l
w
ar
e
au
t
h
o
r
s
u
s
e
lu
r
es
to
tr
ick
u
s
er
s
in
to
d
o
in
g
th
at.
So
m
e
p
h
i
s
h
i
n
g
e
m
ail
s
co
n
tai
n
an
in
v
o
ice
o
r
a
f
ak
e
p
a
y
m
e
n
t
r
elate
d
d
o
cu
m
e
n
t,
tr
y
i
n
g
to
m
ak
e
t
h
e
u
s
er
d
o
w
n
lo
ad
it.
I
n
ad
d
itio
n
,
attac
k
er
s
p
r
o
v
id
e
in
s
tr
u
ct
io
n
t
o
en
ab
le
m
ac
r
o
s
.
I
f
t
h
e
u
s
er
co
m
p
lies
,
m
alicio
u
s
m
ac
r
o
s
w
ill d
o
w
n
lo
ad
Han
c
ito
r
o
r
it w
ill
b
e
d
r
o
p
p
ed
f
r
o
m
th
e
d
o
cu
m
en
t.
I
n
s
o
m
e
m
a
ls
p
a
m
c
a
m
p
aig
n
s
,
Ha
n
cito
r
w
as
d
eli
v
er
ed
to
v
icti
m
s
w
it
h
.
R
T
F
d
o
cu
m
e
n
t
s
w
h
ich
u
s
ed
an
ex
p
lo
it
to
r
u
n
th
e
P
o
w
er
Sh
ell
co
m
m
a
n
d
w
h
ich
d
o
w
n
lo
ad
ed
th
e
lo
ad
er
to
th
e
co
m
p
u
ter
.
An
o
th
er
w
a
y
o
f
Ha
n
cito
r
to
in
f
ec
ti
n
g
t
h
e
v
icti
m
's
m
ac
h
i
n
e
is
b
y
u
s
i
n
g
E
x
ce
l
s
p
r
ea
d
s
h
ee
ts
as
a
tr
a
p
d
o
cu
m
en
ts
s
i
n
ce
Dec
e
m
b
er
1
7
,
2
0
1
8
,
th
e
ex
ec
u
tab
le
f
ile
(
Han
icto
r
)
w
as
in
s
til
led
in
E
x
ce
l
s
p
r
ea
d
s
h
ee
ts
,
th
e
n
Han
cito
r
d
ec
lin
in
g
to
a
v
u
l
n
er
ab
le
W
in
d
o
w
s
h
o
s
t
a
f
ter
o
p
en
in
g
t
h
e
s
p
r
ea
d
s
h
ee
t
i
n
E
x
ce
l
a
n
d
en
ab
li
n
g
m
ac
r
o
s
o
n
J
an
u
ar
y
2
8
,
2
0
1
9
.
H
o
w
ev
er
,
th
e
Han
c
i
to
r
ca
m
p
aig
n
ch
a
n
g
ed
its
d
ec
o
y
d
o
cu
m
en
t
o
n
Feb
r
u
ar
y
5
,
2
0
1
9
.
T
h
is
ca
m
p
aig
n
w
e
n
t
b
ac
k
to
u
s
i
n
g
W
o
r
d
d
o
cu
m
en
t
s
i
n
s
tead
o
f
E
x
ce
l
s
p
r
ea
d
s
h
ee
t
s
.
T
h
e
Han
c
ito
r
ex
ec
u
tab
le
w
a
s
r
etr
iev
ed
f
r
o
m
a
w
eb
s
er
v
er
h
o
s
ted
o
n
t
h
e
s
a
m
e
I
P
ad
d
r
ess
(
b
u
t
a
d
if
f
er
en
t
d
o
m
ain
)
a
s
t
h
e
i
n
it
ial
W
o
r
d
d
o
cu
m
e
n
t
af
ter
en
ab
li
n
g
m
ac
r
o
s
.
T
h
e
Han
cito
r
in
f
ec
tio
n
s
o
n
Feb
r
u
ar
y
5
,
2
0
1
9
,
s
ee
Fig
u
r
e
1
.
Fig
u
r
e
1
.
Han
cito
r
m
al
w
ar
e
i
n
f
ec
tio
n
o
n
Feb
r
u
ar
y
5
,
2
0
1
9
W
h
en
Ha
n
cito
r
in
itiall
y
i
n
f
ec
t
s
a
s
y
s
te
m
,
it
s
en
d
s
a
P
OST
r
eq
u
est
to
it
s
C
o
m
m
a
n
d
a
n
d
C
o
n
t
r
o
l
(
C
&
C
)
s
er
v
er
w
it
h
in
f
o
r
m
at
io
n
o
n
t
h
e
in
f
ec
ted
s
y
s
te
m
.
Fig
u
r
e
2
s
h
o
w
t
h
e
Ha
n
cito
r
m
al
w
ar
e
I
n
f
ec
t
ed
s
y
s
te
m
Fig
u
r
e
2
.
Han
cito
r
m
al
w
ar
e
3.
WH
Y
SWARM
I
NT
E
L
L
I
G
E
NC
E
(
SI
)
S
w
ar
m
i
n
telli
g
e
n
ce
(
SI)
is
a
b
r
an
ch
o
f
ar
ti
f
icial
i
n
telli
g
e
n
ce
(
A
I
)
b
r
an
ch
es
a
n
d
is
s
p
ec
if
ied
b
y
Ger
ar
d
o
B
en
i
an
d
J
in
g
W
a
n
g
i
n
1
9
8
9
.
T
h
er
e
ar
e
m
an
y
p
u
r
p
o
s
es
ac
co
u
n
tab
le
f
o
r
u
s
i
n
g
SI
alg
o
r
ith
m
s
b
ased
o
n
f
lex
ib
ilit
y
,
ea
s
e
o
f
u
s
e,
s
p
ee
d
in
i
m
p
le
m
en
tatio
n
,
v
er
s
atili
t
y
,
t
h
e
s
el
f
-
lear
n
i
n
g
ca
p
ab
ilit
y
a
n
d
ad
ap
tab
ilit
y
to
ex
ter
n
al
v
ar
iatio
n
s
.
A
ls
o
SI
u
s
ed
to
s
o
lv
e
n
o
n
li
n
ea
r
p
r
o
b
lem
s
in
r
ea
l
-
w
o
r
ld
ap
p
licatio
n
s
i
n
s
cie
n
c
es,
en
g
in
ee
r
i
n
g
,
in
b
io
in
f
o
r
m
at
ics ap
p
licatio
n
s
,
r
ec
o
g
n
itio
n
an
d
clas
s
i
f
icatio
n
te
ch
n
o
lo
g
ies,
an
d
n
et
w
o
r
k
s
ec
u
r
it
y
[
1
9
]
-
[
2
1
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
ļ²
I
SS
N
:
2722
-
3221
C
o
m
p
u
t.
Sci.
I
n
f
.
T
ec
h
n
o
l.
,
Vo
l.
2
,
No
.
3
,
No
v
em
b
er
20
2
1
:
1
03
ā
1
12
106
3
.
1
.
G
re
y
w
o
lf
o
ptim
iza
t
io
n (
G
W
O
)
GW
O
alg
o
r
ith
m
i
s
s
u
g
g
est
ed
b
y
[
2
0
]
,
[
22
]
-
[
2
3
]
r
ely
i
n
g
o
n
s
o
cial
h
ier
ar
ch
y
a
n
d
h
u
n
ti
n
g
h
ab
its
f
o
r
g
r
a
y
w
o
l
v
es
to
f
in
d
v
ict
i
m
s
.
T
h
er
e
ar
e
f
o
u
r
h
ier
ar
ch
y
t
y
p
es
o
f
in
d
iv
id
u
al
s
in
C
o
m
m
u
n
it
y
o
f
G
W
O
th
ese
t
y
p
es
ar
e
alp
h
a,
b
eta,
d
elta,
an
d
o
m
e
g
a
b
ased
o
n
th
eir
f
it
n
ess
.
W
h
er
e
t
h
e
r
esear
ch
p
r
o
ce
s
s
is
d
o
n
e
b
y
d
esig
n
i
n
g
a
m
o
d
el
to
m
i
m
ic
th
e
h
u
n
ti
n
g
b
eh
a
v
io
r
o
f
g
r
ay
w
o
lv
e
s
th
r
o
u
g
h
s
ea
r
ch
in
g
f
o
r
p
r
ey
,
attac
k
in
g
th
e
p
r
ey
an
d
co
v
er
in
g
ex
p
lo
itatio
n
.
I
n
GW
O
alg
o
r
ith
m
t
h
e
h
u
n
ti
n
g
m
eth
o
d
h
el
p
s
to
d
eter
m
in
e
t
h
e
lo
ca
tio
n
o
f
p
r
ey
[
2
0
]
.
T
h
e
m
at
h
e
m
a
tical
s
i
m
u
latio
n
o
f
th
e
Gr
ay
W
o
lv
e
s
o
p
ti
m
izatio
n
i
s
ex
p
lain
ed
i
n
[
2
8
]
,
an
d
th
e
GW
O
alg
o
r
ith
m
f
o
r
Han
cito
r
in
f
ec
tio
n
m
al
w
ar
e
r
ec
o
g
n
itio
n
is
p
r
ese
n
ted
f
o
llo
w
s
.
G
WO
a
lg
o
r
it
h
m
[
2
0
]
In
it
ialize
th
e
p
a
ra
m
e
t
e
rs a,
A
,
C
In
it
ialize
G
W
O p
o
p
u
latio
n
G
W
Oi
(i
=
1
,
2
.
.
.
m
)
F
o
r
Eac
h
se
a
rc
h
a
g
e
n
t
m
u
st ca
lcu
late
th
e
f
it
n
e
ss
f
o
r
it
GW
OĪ±
=
b
e
st se
a
rc
h
a
g
e
n
t
GW
OĪ²
=
se
c
o
n
d
b
e
st se
a
rc
h
a
g
e
n
t
GW
OĪ“
=
th
ird
b
e
st se
a
rc
h
a
g
e
n
t
Wh
il
e
(i
<
M
a
x
i
m
u
m
No
.
o
f
it
e
ra
ti
o
n
s)
Fo
r
e
a
c
h
se
a
r
c
h
a
g
e
n
t
Up
g
ra
d
e
th
e
p
o
siti
o
n
o
f
th
e
c
u
rre
n
t
se
a
rc
h
a
g
e
n
t
b
y
GW
O
(
i
+
1
)
=
(
GWO
1
+
GWO
2
+
ā
GWO
3
)
/
3
En
d
f
o
r
Up
g
ra
d
e
a
,
A
,
a
n
d
C
Co
m
p
u
te t
h
e
f
it
n
e
ss
o
f
a
ll
se
a
rc
h
a
g
e
n
ts
Up
g
ra
d
e
GWO
Ī±
,
GWO
Ī²,
a
n
d
G
WO
Ī“
i++
En
d
w
h
il
e
Re
tu
rn
GWO
Ī±
3
.
2
.
Art
if
icia
l bee
co
lo
ny
(
AB
C)
T
h
e
A
r
tific
ial
B
ee
C
o
lo
n
y
al
g
o
r
ith
m
(
A
B
C
)
is
an
o
p
ti
m
iz
atio
n
alg
o
r
it
h
m
b
ased
o
n
t
h
e
in
telli
g
e
n
t
f
o
r
ag
i
n
g
b
eh
a
v
io
r
o
f
h
o
n
e
y
b
ee
s
w
ar
m
,
p
r
o
p
o
s
ed
b
y
Der
v
iÅ
Kar
ab
o
Ä
a
in
2
0
0
5
,
th
e
co
l
o
n
y
in
to
th
e
A
B
C
alg
o
r
ith
m
co
n
tai
n
f
r
o
m
t
h
r
ee
ty
p
e
s
o
f
b
ee
s
:
e
m
p
lo
y
ed
b
ee
s
,
o
n
lo
o
k
er
s
an
d
s
co
u
t
s
.
I
n
A
B
C
th
e
y
ar
e
s
i
m
u
late
d
to
o
n
l
y
o
n
e
ar
tific
ial
b
ee
f
o
r
e
ac
h
f
o
o
d
s
o
u
r
ce
,
w
h
er
e
t
h
e
n
u
m
b
er
s
o
f
b
ee
s
u
s
ed
in
t
h
e
co
lo
n
y
ar
e
eq
u
al
to
t
h
e
n
u
m
b
er
o
f
f
o
o
d
s
o
u
r
ce
s
ar
o
u
n
d
th
e
h
i
v
e.
I
n
A
B
C
,
e
m
p
lo
y
ed
b
ee
s
g
o
to
th
eir
f
o
o
d
s
o
u
r
ce
,
r
etu
r
n
to
t
h
e
h
i
v
e
a
n
d
d
an
ce
in
th
is
r
eg
io
n
.
E
m
p
lo
y
e
d
b
ee
s
w
h
o
s
e
f
o
o
d
s
o
u
r
ce
h
as
b
ee
n
ab
an
d
o
n
ed
b
ec
o
m
e
s
co
u
t
s
an
d
b
eg
in
to
s
ea
r
ch
f
o
r
a
n
e
w
s
o
u
r
ce
o
f
f
o
o
d
.
On
lo
o
k
er
s
w
atch
th
e
d
a
n
ce
s
o
f
e
m
p
lo
y
ed
b
ee
s
a
n
d
ch
o
o
s
e
f
o
o
d
s
o
u
r
ce
s
ac
co
r
d
in
g
to
th
e
d
an
ce
s
.
A
B
C
d
i
f
f
er
f
r
o
m
a
n
o
th
er
S
war
m
in
tell
ig
e
n
ce
alg
o
r
it
h
m
s
b
ased
o
n
th
e
s
itu
a
tio
n
th
a
t
th
e
p
o
ten
tial
s
o
lu
tio
n
s
ar
e
ap
p
ea
r
b
y
th
e
f
o
o
d
s
o
u
r
ce
s
,
n
o
t
th
e
in
d
iv
id
u
al
s
in
th
e
p
o
p
u
latio
n
.
T
h
e
q
u
alit
y
o
f
th
e
p
o
ten
tial
s
o
lu
tio
n
is
p
r
esen
ted
as
a
f
itn
e
s
s
v
al
u
e
;
th
e
f
itn
e
s
s
v
a
lu
e
is
c
alcu
lated
b
y
th
e
v
al
u
e
o
f
th
e
o
b
j
ec
tiv
e
f
u
n
ct
io
n
o
f
th
e
p
r
o
b
lem
.
I
n
t
h
e
A
B
C
alg
o
r
ith
m
o
n
lo
o
k
er
s
an
d
e
m
p
lo
y
ed
b
ee
s
ca
r
r
y
o
u
t
th
e
ex
p
lo
ita
tio
n
p
r
o
ce
s
s
in
th
e
s
ea
r
ch
s
p
ac
e,
w
h
ile
th
e
s
co
u
ts
co
n
tr
o
l
th
e
e
x
p
lo
r
atio
n
p
r
o
ce
s
s
.
T
h
e
p
h
ases
o
f
A
B
C
alg
o
r
it
h
m
a
n
d
m
a
th
e
m
atica
l
eq
u
atio
n
s
ar
e
i
n
[
2
9
]
.
P
s
eu
d
o
-
co
d
e
o
f
th
e
A
B
C
al
g
o
r
ith
m
f
o
r
co
n
s
tr
ain
ed
o
p
ti
m
izatio
n
p
r
o
b
le
m
s
[
3
0
]
is
:
ļ
I
n
itialize
t
h
e
p
o
p
u
latio
n
o
f
s
o
lu
tio
n
s
an
d
ev
a
lu
ate
t
h
e
p
o
p
u
la
tio
n
,
w
h
er
e
x
i (
i =
1
,
2
,
SN)
is
a
D
-
d
i
m
en
s
io
n
al
v
ec
to
r
p
r
esen
t t
h
e
s
o
lu
tio
n
,
S
N
r
ep
r
esen
t t
h
e
s
iz
e
o
f
th
e
p
o
p
u
latio
n
.
ļ
I
n
itialize
v
alu
e
o
f
c
y
cle
b
y
1
ļ
Do
w
h
ile
c
y
cle
n
o
t e
q
u
al
M
C
N
ļ
C
alcu
late
n
e
w
s
o
lu
tio
n
s
f
o
r
t
h
e
e
m
p
lo
y
ed
b
ee
s
,
as in
(
1
)
v
īÆ
,
īÆ
=
{
x
īÆ
,
īÆ
+
ā
īÆ
,
īÆ
Ć
(
x
īÆ
,
īÆ
ā
x
īÆ
,
īÆ
)
,
R
īÆ
<
MR
x
īÆ
,
īÆ
īī
ā
īī
ī
ī
ī
ī
(
1
)
W
h
er
e
k
is
a
r
an
d
o
m
n
u
m
b
er
(
1
-
SN/2
)
an
d
d
if
f
er
en
t
f
r
o
m
i
.
ļ
C
alcu
late
s
elec
tio
n
o
p
er
atio
n
d
ep
en
d
s
o
n
Deb
ā
s
m
et
h
o
d
[
3
1
]
.
ļ
C
o
n
s
tr
ain
t
v
io
latio
n
s
(
C
V)
,
as
in
(
2
)
an
d
ca
lcu
late
t
h
e
p
r
o
b
ab
ilit
y
v
al
u
es (
p
i)
f
o
r
x
i
u
s
i
n
g
f
it
n
es
s
o
f
th
e
s
o
lu
tio
n
s
,
as
(
3
)
.
ī„īø
=
ā
ī
īÆ
īÆ
ī³
>
0
(
ī
)
+
ā
ā
īÆ
īÆ
īƤ
+
1
(
ī
)
(
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.
ļ²
Ha
n
cito
r
ma
lw
a
r
e
r
ec
o
g
n
itio
n
u
s
in
g
s
w
a
r
m
in
tellig
en
t te
ch
n
iq
u
e
(
La
h
ee
b
M.
I
b
r
a
h
im
)
107
ī²ī
=
{
0
.
5
+
(
īÆ
īÆ
īƧ
īÆ”
īÆ
īƦīƦ
ī³
ā
īÆ
īÆ
īƧ
īÆ”
īÆ
īƦīƦ
ī³
ī³ī²æ
ī³
=
1
)
Ć
0
.
5
ī ī
ī
īī
ī
īī ī
ī
ī ī
ī
īī½
ī
ī
ī¾
īī
(
1
ā
ī®¼īÆ
ā
ī®¼īÆ
ī³ī²æ
ī³
=
1
)
Ć
0
.
5
ī ī
ī
īī
ī
īī ī
ī
ī ī
ī
ī
ī
īī½
ī
ī
ī¾
īī
(
3
)
ļ
P
r
o
d
u
ct
a
n
e
w
s
o
l
u
tio
n
v
ij
,
as in
(
1
)
f
o
r
ea
ch
o
n
lo
o
k
er
b
ee
in
th
e
n
ei
g
h
b
o
u
r
h
o
o
d
o
f
th
e
s
o
l
u
tio
n
s
elec
ted
d
ep
en
d
in
g
o
n
p
i
an
d
e
v
alu
a
te
i
t
ļ
C
alcu
late
s
elec
tio
n
o
p
er
atio
n
th
e
v
al
u
e
b
et
w
ee
n
(
Ļ
i
-
x
i
)
d
ep
en
d
ed
o
n
Deb
ā
s
m
et
h
o
d
ļ
Use ā
li
m
itā
p
ar
a
m
eter
f
o
r
th
e
s
co
u
t to
d
ec
id
e
th
e
d
is
u
s
ed
s
o
lu
tio
n
s
.
if
t
h
e
y
e
x
i
s
t,
r
ep
lace
th
e
m
w
it
h
n
e
w
r
an
d
o
m
l
y
p
r
o
d
u
ce
d
s
o
lu
tio
n
s
,
as in
(
4
)
ļ
ī
īÆīÆ
=
ī
ī¾
īÆ
+
ī
ī½īī
(
0
,
1
)
Ć
(
īī¾
īÆ
ā
īī¾
īÆ
)
(
4
)
ļ
Sto
r
e
th
e
b
est s
o
lu
tio
n
co
m
p
le
ted
u
p
till
n
o
w
ļ
c
y
cle
=
c
y
cle+
1
ļ
E
n
d
d
o
4.
P
RO
P
O
SE
D
M
O
DE
L
I
n
th
i
s
p
ap
er
a
r
ec
o
g
n
is
er
s
y
s
te
m
is
d
e
s
ig
n
ed
to
r
ec
o
g
n
is
e
Ha
n
cito
r
tr
af
f
ic
f
r
o
m
n
o
r
m
al
tr
a
f
f
ic,
to
allo
w
th
e
n
e
t
w
o
r
k
ad
m
i
n
i
s
tr
ato
r
to
m
ak
e
th
e
ap
p
r
o
p
r
iate
d
ec
is
io
n
,
S
ee
Fig
u
r
e
3
.
I
n
p
r
o
p
o
s
ed
m
o
d
el
a
Han
cito
r
m
et
h
o
d
o
f
in
f
ec
ti
n
g
th
e
v
icti
m
's
m
ac
h
in
e
is
u
s
i
n
g
.
DO
C
attac
h
m
e
n
t
s
tak
i
n
g
ad
v
a
n
tag
e
o
f
Mic
r
o
s
o
f
tā
s
d
y
n
a
m
ic
d
ata
ex
ch
a
n
g
e
(
DDE
)
tech
n
iq
u
e
,
N
etFlo
w
T
r
af
f
ic
A
n
al
y
ze
r
(
NT
A
)
to
o
l
Ver
.
9
u
s
ed
to
co
llect
n
et
w
o
r
k
tr
a
f
f
ic
s
b
y
ca
p
tu
r
in
g
th
e
m
a
n
d
o
b
tain
in
g
th
e
d
ata
u
s
ed
in
th
e
p
r
o
p
o
s
ed
m
o
d
el.
T
h
e
ca
p
tu
r
ed
tr
af
f
ics
(
n
o
r
m
al
o
r
Han
cito
r
m
al
w
ar
e
tr
af
f
ic
s
)
ar
e
th
e
n
s
to
r
ed
in
th
e
Ha
n
cito
r
d
ata
f
ile.
T
h
e
co
llected
tr
af
f
ics
ar
e
u
s
ed
f
o
r
th
e
s
elec
tio
n
o
f
s
o
m
e
f
ea
t
u
r
es
r
elate
d
to
th
e
u
n
d
er
ly
i
n
g
n
et
w
o
r
k
tr
af
f
ic
to
s
ele
ct
th
e
f
o
llo
w
in
g
attr
ib
u
te
s
(
So
u
r
ce
I
P
,
Destin
atio
n
I
P
,
Pro
to
co
l,
T
im
eli
n
e,
an
d
L
en
g
t
h
)
,
s
ee
T
a
b
le
1
.
A
f
ter
th
e
s
elec
tio
n
o
f
attr
ib
u
tes,
th
e
m
o
n
ito
r
ed
tr
af
f
ics
ar
e
u
s
ed
as
in
p
u
t
to
th
e
r
ec
o
g
n
i
s
e
r
(
GW
O
an
d
A
B
C
alg
o
r
ith
m
s
)
to
r
ec
o
g
n
is
e
t
h
e
tr
af
f
ic
in
to
Han
cito
r
o
r
n
o
r
m
al
tr
af
f
ic.
GW
O
an
d
A
B
C
s
w
ar
m
i
n
telli
g
e
n
t
al
g
o
r
ith
m
s
ar
e
u
s
ed
to
r
ec
o
g
n
is
e
Han
ci
to
r
tr
af
f
ics
o
n
t
h
e
n
et
w
o
r
k
u
s
i
n
g
th
e
attr
ib
u
te
s
.
T
h
e
u
n
d
er
l
y
in
g
co
n
v
e
y
a
n
ce
s
a
n
d
th
e
p
a
r
am
eter
s
u
s
ed
in
t
h
e
test
s
ar
e
s
ig
n
i
f
ica
n
t.
T
h
e
p
ar
am
eter
s
o
f
th
e
g
r
a
y
-
w
o
lf
o
p
ti
m
izer
ar
e
c
h
o
s
en
a
f
ter
r
u
n
n
in
g
a
f
e
w
te
s
ts
to
o
b
tain
s
ati
s
f
ac
to
r
y
o
u
tco
m
es.
GW
O
w
as i
n
it
ialized
w
it
h
:
ļ
P
o
p
u
latio
n
o
f
GW
O:
Nu
m
b
er
o
f
g
r
a
y
w
o
l
v
es =
2
0
.
ļ
Ma
x
i
m
u
m
iter
atio
n
n
u
m
b
er
=
1
5
0
.
ļ
T
h
e
v
alu
es o
f
a
=
(
2
to
0
)
T
h
e
f
itn
e
s
s
f
u
n
ctio
n
as g
i
v
e
n
b
y
E
u
clid
ea
n
d
is
tan
ce
,
as i
n
(
5
)
is
ca
lcu
lated
to
h
a
v
e
b
est s
o
l
u
tio
n
a
f
ter
f
ir
s
t iter
atio
n
as
āĪ±
-
w
o
l
f
,
ā
,
an
d
ā
Ī²ā a
n
d
ā
Ī“ā
w
o
l
v
es,
an
d
t
h
e
s
ec
o
n
d
an
d
th
ir
d
b
est s
o
l
u
tio
n
ar
e
Ī² a
n
d
Ī“
ī¦
=
ā
ā
(
ī
īÆ
īÆ”
īÆ
=
1
ā
ī
īÆ
)
2
(
5
)
T
h
e
p
ar
am
eter
s
o
f
t
h
e
A
r
ti
f
ici
al
B
ee
C
o
lo
n
y
al
g
o
r
ith
m
(
A
B
C
)
ar
e
ch
o
s
en
a
f
ter
r
u
n
n
in
g
a
f
e
w
tes
ts
to
o
b
tain
s
atis
f
ac
to
r
y
o
u
tco
m
e
s
.
A
B
C
w
a
s
in
itialized
w
it
h
:
ļ
P
o
p
u
latio
n
s
ize
o
f
A
B
C
: E
m
p
l
o
y
ed
b
ee
s
=
3
0
.
ļ
Ma
x
i
m
u
m
iter
atio
n
n
u
m
b
er
=
1
0
0
.
ļ
L
i
m
ite
=
3
0
T
h
e
f
itn
e
s
s
f
u
n
ct
io
n
as
g
i
v
e
n
b
y
E
u
clid
ea
n
d
is
ta
n
ce
,
as
i
n
(
5
)
is
ca
lcu
lated
to
h
a
v
e
b
est
s
o
lu
tio
n
a
f
ter
f
ir
s
t iter
atio
n
.
T
o
m
ea
s
u
r
e
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
GW
O
an
d
A
B
C
al
g
o
r
ith
m
s
to
r
ec
o
g
n
ize
Ha
n
cito
r
m
al
w
ar
e
t
w
o
eq
u
atio
n
s
ar
e
u
s
ed
.
[
4
,
3
2
]
,
th
ese
eq
u
atio
n
s
ar
e
A
cc
u
r
ac
y
o
f
R
ec
o
g
n
itio
n
p
ac
k
et
s
u
s
ed
to
ca
lcu
late
th
e
p
er
ce
n
tag
e
o
f
co
r
r
ec
tl
y
cla
s
s
i
f
ied
p
ac
k
ets
(
n
o
r
m
al
o
r
Ha
n
cit
o
r
p
ac
k
et)
a
m
o
n
g
th
e
to
tal
n
u
m
b
er
o
f
p
ac
k
ets
i
s
co
m
p
u
ted
,
as
i
n
(
6
)
an
d
Fals
e
A
lar
m
R
ate
(
F
AR
)
w
h
er
e
F
A
R
is
r
e
f
er
r
ed
to
as
th
e
FP
R
(
f
a
ls
e
p
o
s
iti
v
e
r
ate)
o
r
s
en
s
iti
v
it
y
,
a
s
in
(
7
)
.
ī£ī„ī„
=
īÆīÆ
+
īÆīÆ
īÆīÆ
+
ī®æīÆ
+
ī®æīÆ
+
ī®æīÆ
(
6
)
īØ
ī£
ī“
=
ī®æīÆ
īÆīÆ
+
ī®æīÆ
(
7)
Evaluation Warning : The document was created with Spire.PDF for Python.
ļ²
I
SS
N
:
2722
-
3221
C
o
m
p
u
t.
Sci.
I
n
f
.
T
ec
h
n
o
l.
,
Vo
l.
2
,
No
.
3
,
No
v
em
b
er
20
2
1
:
1
03
ā
1
12
108
W
h
er
e
T
P
(
T
r
u
e
p
o
s
itiv
e)
:
co
r
r
ec
tly
id
e
n
ti
f
ied
Han
ci
to
r
m
a
l
w
ar
e
;
T
N
(
T
r
u
e
Neg
ati
v
e)
:
in
co
r
r
ec
tly
id
en
tifie
d
Han
cito
r
m
al
w
ar
e
;
FP
(
Fals
e
P
o
s
itiv
e
)
:
cor
r
e
ct
l
y
r
e
j
ec
t
ed
H
anc
i
t
or
m
al
w
ar
e
;
and
FN
(
Fal
se
N
eg
at
i
v
e)
:
i
nco
r
r
e
ct
l
y
r
e
j
ec
t
ed
H
an
ci
t
o
r
m
al
w
ar
e
.
Fig
u
r
e
3
.
P
r
o
p
o
s
ed
m
o
d
el
T
ab
le
1
.
Der
iv
ed
s
tatis
tic
attr
i
b
u
tes
f
r
o
m
th
e
ca
p
t
u
r
ed
f
ile
F
e
a
t
u
r
e
n
a
me
F
e
a
t
u
r
e
c
o
n
t
e
n
t
s
L
e
n
g
t
h
S
i
z
e
o
f
t
h
e
w
h
o
l
e
p
a
c
k
e
t
i
n
c
l
u
d
e
h
e
a
d
e
r
,
t
r
a
i
l
e
r
a
n
d
d
a
t
a
t
h
a
t
se
n
d
o
n
t
h
e
p
a
c
k
e
t
S
n
a
p
sh
o
t
(
l
e
n
g
t
h
)
T
h
e
a
mo
u
n
t
o
f
d
a
t
a
f
o
r
e
a
c
h
f
r
a
me
t
h
a
t
a
c
t
u
a
l
l
y
c
a
p
t
u
r
e
d
b
y
t
h
e
n
e
t
w
o
r
k
c
a
p
t
u
r
i
n
g
t
o
o
l
a
n
d
s
t
o
r
e
d
i
n
t
o
t
h
e
c
a
p
t
u
r
e
f
i
l
e
L
a
st
p
a
c
k
e
t
e
l
a
p
se
C
a
p
t
u
r
e
t
i
me
a
n
d
d
u
r
a
t
i
o
n
o
f
t
h
e
l
a
st
p
a
c
k
e
t
P
a
c
k
e
t
T
h
e
n
u
m
b
e
r
o
f
p
r
o
t
o
c
o
l
p
a
c
k
e
t
f
r
o
m t
h
e
t
o
t
a
l
c
a
p
t
u
r
e
p
a
c
k
e
t
T
i
me
sp
a
n
/
s
I
s t
h
e
t
i
me
b
e
t
w
e
e
n
t
h
e
f
i
r
s
t
a
n
d
l
a
st
p
a
c
k
e
t
A
v
e
r
a
g
e
A
p
p
A
v
e
r
a
g
e
a
p
p
:
i
n
f
o
r
ma
t
i
o
n
a
b
o
u
t
N
e
t
F
l
o
w
T
r
a
f
f
i
c
A
n
a
l
y
z
e
r
h
a
r
d
w
a
r
e
.
A
v
e
r
a
g
e
si
z
e
T
h
e
a
v
e
r
a
g
e
si
z
e
o
f
t
h
e
h
e
a
d
e
r
o
n
t
h
e
p
a
c
k
e
t
B
y
t
e
s
T
h
e
n
u
m
b
e
r
o
f
p
r
o
t
o
c
o
l
b
y
t
e
s fr
o
m t
h
e
t
o
t
a
l
c
a
p
t
u
r
e
p
a
c
k
e
t
s
A
v
e
r
a
g
e
B
y
t
e
/
s
T
h
e
a
v
e
r
a
g
e
n
u
m
b
e
r
o
f
p
r
o
t
o
c
o
l
b
y
t
e
s fr
o
m t
h
e
t
o
t
a
l
c
a
p
t
u
r
e
p
a
c
k
e
t
s
A
v
e
r
a
g
e
B
i
t
s
/
s
T
h
e
a
v
e
r
a
g
e
b
a
n
d
w
i
d
t
h
o
f
t
h
i
s
p
r
o
t
o
c
o
l
i
n
r
e
l
a
t
i
o
n
t
o
t
h
e
c
a
p
t
u
r
e
t
i
me
5.
E
XP
E
R
I
M
E
NT
A
L
RE
SUL
T
T
h
e
p
r
o
p
o
s
ed
r
ec
o
g
n
itio
n
m
o
d
el
f
o
r
Han
cito
r
m
a
l
w
ar
e
w
a
s
i
m
p
le
m
e
n
ted
i
n
M
A
T
L
A
B
v
er
s
io
n
R
2
0
1
5
a
.
T
h
e
p
r
o
p
o
s
ed
m
o
d
el
p
er
f
o
r
m
ed
GW
O
an
d
A
B
C
al
g
o
r
ith
m
s
o
n
th
e
s
et
o
f
p
ac
k
et
s
s
t
o
r
ed
in
th
e
Han
cito
r
d
ata
f
ile
to
r
ec
o
g
n
is
e
Han
ci
to
r
tr
af
f
ics.
T
w
o
ex
p
er
i
m
en
t
s
w
e
r
e
co
n
d
u
cted
in
th
e
p
r
o
p
o
s
ed
w
o
r
k
b
ased
o
n
t
w
o
t
y
p
es o
f
p
ac
k
et
s
:
ļ
P
ac
k
ets
b
ased
o
n
s
tati
s
tic
attr
i
b
u
tes
(L
e
n
g
t
h
,
P
ac
k
et
s
ize
li
m
it
,
E
lap
s
ed
,
P
ac
k
ets
,
T
im
e
s
p
a
n
(
s
)
,
A
v
er
a
g
e
pps
m
m
Av
er
ag
e
p
ac
k
et
s
ize
(
B
)
,
B
y
tes
,
A
v
er
a
g
e
b
y
tes/
s
,
Av
er
ag
e
b
its
/
s
)
,
s
ee
T
ab
le
2
,
th
e
s
ize
o
f
p
ac
k
ets
b
ased
o
n
s
tatis
tic
at
tr
ib
u
tes
ar
e
3
0
0
0
p
ac
k
ets.
ļ
P
ac
k
ets
b
ased
o
n
I
P
v
4
ch
ar
ac
t
er
is
tics
,
s
ee
T
ab
les
3
an
d
4
,
th
e
s
ize
o
f
p
ac
k
ets
b
ased
o
n
I
P
v
4
ch
ar
ac
ter
is
tic
s
ar
e
3
0
0
0
p
ac
k
ets
.
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.
ļ²
Ha
n
cito
r
ma
lw
a
r
e
r
ec
o
g
n
itio
n
u
s
in
g
s
w
a
r
m
in
tellig
en
t te
ch
n
iq
u
e
(
La
h
ee
b
M.
I
b
r
a
h
im
)
109
T
ab
le
2
.
P
ac
k
ets b
ased
o
n
s
tati
s
tic
attr
ib
u
te
s
f
r
o
m
th
e
ca
p
tu
r
e
d
tr
af
f
ic
(
n
o
r
m
al
an
d
Ha
n
ctio
r
p
ac
k
et)
I
t
e
ms
H
a
n
i
c
t
o
r
t
r
a
f
f
i
c
N
o
r
mal
t
r
a
f
f
i
c
L
e
n
g
t
h
1
2
7
2
k
b
1
0
7
3
M
B
P
a
c
k
e
t
si
z
e
l
i
mi
t
6
5
5
3
5
b
y
t
e
4
0
9
6
b
y
t
e
s
El
a
p
se
d
0
1
:
2
6
:
0
9
0
0
:
3
5
:
1
6
P
a
c
k
e
t
s
6
4
8
9
4
1
9
8
0
1
1
T
i
me
sp
a
n
,
s
5
1
6
9
.
7
8
5
2
1
1
6
.
1
4
0
A
v
e
r
a
g
e
p
p
s
1
.
3
1
9
8
3
.
8
A
v
e
r
a
g
e
p
a
c
k
e
t
si
z
e
,
B
1
8
0
2
4
0
B
y
t
e
s
1
1
6
8
2
3
6
1
0
0
6
5
7
3
1
1
9
A
v
e
r
a
g
e
b
y
t
e
s/
s
2
2
5
4
7
5
k
A
v
e
r
a
g
e
b
i
t
s
/
s
1
8
0
7
k
38
0
5
k
T
ab
le
3
.
Der
iv
ed
attr
ib
u
tes f
r
o
m
th
e
ca
p
t
u
r
ed
f
ile
u
s
i
n
g
I
P
v
4
ch
ar
ac
ter
is
tics
(
n
o
r
m
al
p
ac
k
et
)
T
o
p
i
c
/
I
t
e
m
C
o
u
n
t
R
a
t
e
(
ms)
P
e
r
c
e
n
t
B
u
r
s
t
r
a
t
e
B
u
r
s
t
st
a
r
t
A
l
l
A
d
d
r
e
sse
s
1
2
8
6
2
.
9
9
0
7
1
0
0
%
6
.
9
9
0
0
0
.
0
0
0
6
4
.
4
.
2
3
.
1
4
3
1
0
.
0
0
2
3
0
.
0
8
%
0
.
0
1
0
0
0
.
2
5
0
2
2
4
.
0
.
0
.
1
0
3
0
.
0
0
7
0
0
.
2
3
%
0
.
0
2
0
0
0
.
2
1
0
1
9
2
.
1
6
8
.
2
8
.
2
5
4
10
0
.
0
2
3
3
0
.
7
8
%
0
.
0
8
0
0
0
.
1
2
0
1
9
2
.
1
6
8
.
2
8
.
2
0
2
42
0
.
0
9
7
7
3
.
2
7
%
0
.
2
8
0
0
0
.
1
2
0
1
9
2
.
1
6
8
.
2
7
.
2
5
3
80
0
.
1
8
6
0
6
.
2
2
%
0
.
3
1
0
0
0
.
1
5
0
1
9
2
.
1
6
8
.
2
7
.
2
5
7
0
.
0
1
6
3
0
.
5
4
%
0
.
0
3
0
0
0
.
2
2
0
1
9
2
.
1
6
8
.
2
7
.
2
0
3
2
0
.
0
0
4
7
0
.
1
6
%
0
.
0
2
0
0
0
.
3
2
0
1
9
2
.
1
6
8
.
2
7
.
2
0
2
5
0
.
0
1
1
6
0
.
3
9
%
0
.
0
3
0
0
0
.
3
2
0
1
9
2
.
1
6
8
.
2
7
.
1
5
2
3
0
.
0
0
7
0
0
.
2
3
%
0
.
0
1
0
0
0
.
0
0
0
1
9
2
.
1
6
8
.
2
7
.
1
0
3
2
0
.
0
0
4
7
0
.
1
6
%
0
.
0
1
0
0
0
.
0
0
0
1
9
2
.
1
6
8
.
2
7
.
1
0
2
6
0
.
0
1
4
0
0
.
4
7
%
0
.
0
3
0
0
0
.
2
2
0
1
9
2
.
1
6
8
.
2
7
.
1
0
1
6
0
.
0
1
4
0
0
.
4
7
%
0
.
0
4
0
0
0
.
2
4
0
1
9
2
.
1
6
8
.
2
7
.
1
0
0
1
7
9
0
.
4
1
6
3
1
3
.
9
2
%
0
.
4
6
00
0
.
3
1
0
1
9
2
.
1
6
8
.
2
6
.
2
5
4
1
0
.
0
0
2
3
0
.
0
8
%
0
.
0
1
0
0
0
.
1
0
0
1
9
2
.
1
6
8
.
2
6
.
2
5
3
8
0
.
0
1
8
6
0
.
6
2
%
0
.
0
4
0
0
0
.
2
4
0
1
9
2
.
1
6
8
.
2
6
.
2
5
2
8
0
.
0
1
8
6
0
.
6
2
%
0
.
0
4
0
0
0
.
2
4
0
1
9
2
.
1
6
8
.
2
6
.
2
5
4
0
.
0
0
9
3
0
.
3
1
%
0
.
0
4
0
0
0
.
2
3
0
1
9
2
.
1
6
8
.
2
6
.
2
0
3
6
0
.
0
1
4
0
0
.
4
7
%
0
.
0
4
0
0
0
.
2
4
0
1
9
2
.
1
6
8
.
2
6
.
2
0
2
2
0
.
0
0
4
7
0
.
1
6%
0
.
0
2
0
0
0
.
3
1
0
T
ab
le
4
.
Der
iv
ed
attr
ib
u
tes f
r
o
m
th
e
ca
p
t
u
r
ed
f
ile
u
s
i
n
g
I
P
v
4
ch
ar
ac
ter
is
tics
(
Ha
n
cito
r
P
ac
k
et)
T
o
p
i
c
/
I
t
e
m
C
o
u
n
t
R
a
t
e
(
ms)
P
e
r
c
e
n
t
B
u
r
s
t
r
a
t
e
B
u
r
s
t
st
a
r
t
A
l
l
A
d
d
r
e
sse
s
6
4
8
9
0
.
0
0
1
3
1
0
0
%
0
.
3
8
0
0
2
6
6
.
0
5
5
8
2
.
1
9
6
.
9
.
4
5
2
8
3
0
.
0
0
0
1
4
.
3
6
%
0
.
0
2
0
0
6
0
7
.
3
0
6
8
.
8
.
8
.
8
2
8
0
0
.
0
0
0
1
4
.
3
1
%
0
.
0
3
0
0
3
1
4
8
.
7
4
1
5
4
.
2
4
3
.
1
2
3
.
3
9
11
0
.
0
0
0
0
0
.
1
7
%
0
.
0
4
0
0
2
5
1
.
2
82
5
1
.
2
5
5
.
4
8
.
7
8
4
2
3
0
.
0
0
0
1
6
.
5
2
%
0
.
0
2
0
0
4
9
9
.
7
0
4
4
7
.
5
2
.
4
5
.
1
7
8
3
7
8
0
.
0
0
0
1
5
.
8
3
%
0
.
0
8
0
0
8
5
8
.
0
0
4
4
7
.
2
5
4
.
1
9
9
.
1
9
2
3
4
7
0
.
0
0
0
1
5
.
3
5%
0
.
0
9
0
0
5
4
.
9
7
1
4
6
.
2
3
5
.
4
7
.
5
9
3
6
1
0
.
0
0
0
1
5
.
5
6
%
0
.
3
8
0
0
2
6
6
.
0
5
5
2
1
3
.
1
3
6
.
8
5
.
2
5
3
7
0
0
0
.
0
0
0
1
1
0
.
7
9
%
0
.
0
2
0
0
3
4
7
.
9
2
2
2
0
7
.
1
4
8
.
8
3
.
2
4
1
2
8
0
0.
0
0
0
1
4
.
3
1
%
0
.
0
2
0
0
5
7
9
.
3
0
7
1
9
3
.
1
8
3
.
9
8
.
6
6
2
8
3
0
.
0
0
0
1
4
.
3
6
%
0
.
0
2
0
0
5
7
8
.
9
4
4
1
9
2
.
7
1
.
2
4
5
.
2
0
8
2
8
3
0
.
0
0
0
1
4
.
3
6
%
0
.
0
2
0
0
7
7
8
.
8
2
6
1
9
1
.
1
0
1
.
2
0
.
1
6
4
6
0
0
.
0
0
0
1
7
.
0
9
%
0
.
0
6
0
0
2
6
2
.
6
5
7
1
7
8
.
1
7
.
1
7
0
.
1
7
9
3
3
8
0
.
0
0
0
1
5
.
2
1
%
0
.
0
4
0
0
1
1
5
5
.
8
9
6
1
5
9
.
8
9
.
2
4
9
.
2
4
9
2
8
3
0
.
0
0
0
1
4
.
3
6
%
0
.
0
2
0
0
6
0
6
.
8
0
0
1
4
2
.
4
.
2
0
5
.
4
7
7
0
0
0
.
0
0
0
1
1
0
.
7
9
%
0
.
0
2
0
0
3
3
5
.
8
6
9
1
1
1
.
6
7
.
2
0
.
8
2
8
3
0
.
0
0
0
1
4
.
3
6
%
0
.
0
2
0
0
5
8
0
.
0
0
4
1
0
3
.
2
3
6
.
1
6
2
.
1
1
9
3
5
6
0
.
0
0
0
1
5
.
4
9
%
0
.
0
6
0
0
5
8
2
.
6
9
2
1
0
.
1
2
.
6
.
1
0
1
6
4
8
9
0
.
0
0
1
3
1
0
0
.
0
0
%
0
.
3
8
0
0
2
6
6
.
0
5
5
1
0
.
1
2
.
6
.
1
4
4
0
0
.
0
0
0
1
6
.
7
8
%
0
.
0
6
0
0
7
4
7
.
3
4
3
T
ab
le
5
.
E
x
p
lain
s
th
e
ac
c
u
r
ac
y
o
f
t
h
e
GW
O
an
d
A
B
C
alg
o
r
i
th
m
s
co
n
s
i
d
er
in
g
r
ec
o
g
n
i
tio
n
p
ac
k
ets
(
n
o
r
m
a
l o
r
Han
cito
r
p
ac
k
et)
f
o
r
th
e
t
w
o
t
y
p
e
s
o
f
d
ata.
S
w
a
r
m
I
n
t
e
l
l
i
g
e
n
t
A
l
g
o
r
i
t
h
ms
P
a
c
k
e
t
s
T
o
t
a
l
p
a
c
k
e
t
s
F
a
l
s
e
A
l
a
r
m R
a
t
e
%
A
c
c
u
r
a
c
y
%
G
W
O
P
a
c
k
e
t
s
b
a
se
d
o
n
st
a
t
i
st
i
c
a
t
t
r
i
b
u
t
e
s
3
0
0
0
4
.
2
%
9
5
.
8
%
P
a
c
k
e
t
s
b
a
se
d
o
n
I
P
v
4
c
h
a
r
a
c
t
e
r
i
st
i
c
s
3
0
0
0
8%
9
2
%
A
B
C
P
a
c
k
e
t
s
b
a
se
d
o
n
st
a
t
i
st
i
c
a
t
t
r
i
b
u
t
e
s
3
0
0
0
2
.
8
%
9
7
.
2
%
P
a
c
k
e
t
s
b
a
se
d
o
n
I
P
v
4
c
h
a
r
a
c
t
e
r
i
st
i
c
s
3
0
0
0
5
.
7
%
9
4
,
3
%
Evaluation Warning : The document was created with Spire.PDF for Python.
ļ²
I
SS
N
:
2722
-
3221
C
o
m
p
u
t.
Sci.
I
n
f
.
T
ec
h
n
o
l.
,
Vo
l.
2
,
No
.
3
,
No
v
em
b
er
20
2
1
:
1
03
ā
1
12
110
T
ab
le
5
.
A
cc
u
r
ac
y
o
f
GW
O
an
d
A
B
C
Alg
o
r
it
h
m
s
f
o
r
r
ec
o
g
n
i
tio
n
Han
cito
r
m
al
w
ar
e
,
Af
ter
p
er
f
o
r
m
i
n
g
ex
p
er
i
m
e
n
ts
o
n
t
w
o
t
y
p
e
s
o
f
d
ata
p
ac
k
ets
u
s
i
n
g
th
e
GW
O
alg
o
r
ith
m
to
r
ec
o
g
n
i
s
e
Ha
n
cito
r
m
al
w
ar
e,
th
e
E
x
p
er
i
m
e
n
tal
r
es
u
lt
s
h
o
w
s
t
h
at
u
s
i
n
g
d
ata
b
ased
o
n
attr
ib
u
tes
is
b
etter
t
h
an
u
s
i
n
g
d
ata
b
ased
o
n
I
P
v
4
ch
ar
ac
ter
is
tic
s
to
r
ec
o
g
n
is
e
Ha
n
cito
r
m
al
w
ar
e
,
s
ee
Fig
u
r
e
4
,
a
n
d
also
af
ter
p
er
f
o
r
m
in
g
ex
p
er
i
m
e
n
ts
u
s
i
n
g
A
B
C
alg
o
r
ith
m
o
n
t
w
o
t
y
p
es
o
f
d
ata
p
ac
k
ets
to
r
ec
o
g
n
is
e
Ha
n
cito
r
m
al
w
ar
e,
th
e
E
x
p
er
i
m
e
n
tal
r
esu
lt
also
s
h
o
w
th
a
t
u
s
i
n
g
d
ata
b
ased
o
n
attr
ib
u
te
s
is
b
etter
t
h
a
n
u
s
i
n
g
d
ata
b
as
ed
o
n
I
P
v
4
ch
ar
ac
ter
is
tic
s
to
r
ec
o
g
n
is
e
Han
c
ito
r
m
al
w
ar
e
,
s
ee
Fi
g
u
r
e
5
.
Fig
u
r
e
4
.
R
ec
o
g
n
i
tio
n
ac
c
u
r
ac
y
r
esu
lt f
o
r
Han
ci
to
r
u
s
i
n
g
th
e
GW
O
al
g
o
r
ith
m
Fig
u
r
e
5
.
R
ec
o
g
n
i
tio
n
ac
c
u
r
ac
y
r
esu
lt f
o
r
Han
ci
to
r
u
s
i
n
g
th
e
A
B
C
al
g
o
r
ith
m
Fro
m
T
ab
le
5
an
d
F
ig
u
r
e
6
,
w
e
n
o
te
th
at
th
e
ac
cu
r
ac
y
r
ate
o
f
th
e
r
ec
o
g
n
itio
n
of
Han
c
ito
r
m
al
w
ar
e
u
s
in
g
A
B
C
alg
o
r
it
h
m
is
b
etter
t
h
a
n
GW
O
alg
o
r
ith
m
in
t
h
e
t
w
o
t
y
p
es
o
f
d
ata
P
ac
k
et
s
b
ased
o
n
s
ta
tis
tic
attr
ib
u
tes
a
n
d
P
ac
k
et
s
b
ased
o
n
I
P
v
4
ch
ar
ac
ter
is
tics
,
an
d
also
th
e
Fal
s
e
Alar
m
R
a
te
in
A
B
C
alg
o
r
it
h
m
i
s
lo
w
er
t
h
an
GW
O
f
o
r
t
w
o
t
y
p
e
s
o
f
d
ata.
A
B
C
alg
o
r
ith
m
is
b
etter
th
an
GW
O
alg
o
r
ith
m
to
r
ec
o
g
n
i
s
e
Han
ci
to
r
m
a
l
w
ar
e
in
s
p
i
te
o
f
o
u
r
u
s
e
o
f
an
eq
u
al
n
u
m
b
er
o
f
p
ac
k
ets
a
n
d
t
h
e
s
a
m
e
d
ata
b
ec
au
s
e
A
B
C
a
lg
o
r
it
h
m
d
o
es
n
o
t r
eq
u
ir
e
a
co
m
p
le
x
d
ata
tr
ain
i
n
g
,
w
h
et
h
er
it i
s
s
i
m
p
le
o
r
co
m
p
lex
tr
ain
in
g
d
ata,
b
u
t
r
ath
er
r
e
q
u
ir
es
an
u
n
d
e
r
s
tan
d
in
g
o
f
th
e
m
in
i
m
u
m
u
n
d
er
s
tan
d
in
g
o
f
th
e
p
r
o
b
lem
ar
ea
t
h
at
h
elp
ed
in
ac
c
u
r
ac
y
a
n
d
s
p
ee
d
o
f
d
is
cr
i
m
i
n
atio
n
.
Usi
n
g
S
w
ar
m
i
n
tell
ig
e
n
ce
(
SI)
in
r
ec
o
g
n
is
e
Han
cito
r
Ma
l
w
ar
e
h
a
v
e
b
ig
ad
v
an
ta
g
es,
b
ec
u
ase
SI
p
r
esen
ts
s
i
m
ila
r
in
tel
lig
e
n
t
co
l
lectiv
e
b
eh
a
v
io
r
,
w
h
er
e
SI
p
r
o
v
id
es
in
tel
lig
e
n
t
s
o
l
u
tio
n
s
to
p
r
o
b
lem
s
b
y
th
e
s
el
f
-
o
r
g
an
izatio
n
an
d
co
m
m
u
n
icat
io
n
b
et
w
ee
n
in
d
i
v
id
u
al
s
i
n
t
h
e
s
w
ar
m
,
a
n
d
th
e
s
ea
m
les
s
co
o
r
d
in
atio
n
o
f
all
in
d
iv
id
u
al
ac
ti
v
it
ies
d
o
es
n
o
t
r
eq
u
ir
e
s
u
p
er
v
is
o
r
.
GW
O
an
d
A
B
C
a
lg
o
r
it
h
m
s
u
s
ed
to
d
etec
t
co
r
r
ec
tly
a
Han
ci
to
r
m
al
w
ar
e
i
n
a
f
ast a
n
d
h
i
g
h
r
ec
o
g
n
itio
n
r
ate
b
ec
au
s
e
GW
O
a
n
d
A
B
C
s
w
ar
m
i
n
telli
g
e
n
ce
al
g
o
r
ith
m
s
h
a
v
e
a
b
ig
ad
v
an
ta
g
e,
w
h
er
e
A
B
C
alg
o
r
ith
m
is
a
s
i
m
p
lest
s
w
ar
m
i
n
t
ellig
e
n
ce
alg
o
r
it
h
m
a
n
d
d
eliv
er
s
h
ig
h
l
y
ac
cu
r
ate
r
esu
lt
s
f
o
r
o
p
ti
m
izatio
n
p
r
o
b
lem
s
w
it
h
le
v
els
r
an
g
i
n
g
f
r
o
m
s
i
m
p
licit
y
to
co
m
p
le
x
it
y
,
an
d
it
p
r
o
v
ed
th
at
th
e
A
B
C
alg
o
r
ith
m
is
t
h
e
b
est
ch
o
ice
f
o
r
s
o
lv
in
g
Ha
n
icto
r
m
al
w
ar
e
p
r
o
b
lem
s
an
d
ca
n
b
e
ap
p
lied
to
m
an
y
ap
p
licatio
n
s
,
also
GW
O
w
a
s
id
en
ti
f
ied
to
b
e
s
u
f
f
icie
n
t
co
m
p
etiti
v
e
w
it
h
o
th
er
s
tate
-
of
-
th
e
-
ar
t
m
et
h
eu
r
is
tic
m
eth
o
d
s
to
r
ec
o
g
n
is
ed
Ha
n
icto
r
m
al
w
ar
e,
it a
ch
ie
v
es b
etter
p
er
f
o
r
m
an
ce
.
Fig
u
r
e
6
.
R
ec
o
g
n
i
tio
n
ac
c
u
r
ac
y
r
esu
lt f
o
r
Han
ci
to
r
u
s
i
n
g
th
e
GW
O
an
d
A
B
C
al
g
o
r
ith
m
s
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.
ļ²
Ha
n
cito
r
ma
lw
a
r
e
r
ec
o
g
n
itio
n
u
s
in
g
s
w
a
r
m
in
tellig
en
t te
ch
n
iq
u
e
(
La
h
ee
b
M.
I
b
r
a
h
im
)
111
6.
CO
NCLU
SI
O
N
A
n
e
w
m
o
d
el
u
s
e
s
Gr
e
y
-
W
o
l
f
Op
ti
m
izer
an
d
(
GW
O)
a
n
d
Ar
tif
icial
B
ee
C
o
lo
n
y
Alg
o
r
it
h
m
(
A
B
C
)
to
r
ec
o
g
n
is
e
Han
ci
to
r
m
al
w
ar
e
b
eh
av
io
r
s
i
s
p
r
o
p
o
s
ed
.
I
t
ca
n
p
r
o
tect
u
s
er
s
f
r
o
m
Ha
n
cito
r
m
al
w
ar
e
attac
k
s
.
I
n
th
is
r
e
s
ea
r
ch
GW
O
a
n
d
A
B
C
h
av
e
ab
ili
t
y
to
r
ec
o
g
n
is
e
co
r
r
ec
tl
y
a
Ha
n
cito
r
m
al
w
ar
e
i
n
a
f
ast
a
n
d
p
r
ec
is
io
n
r
ec
o
g
n
itio
n
r
ate.
A
B
C
a
n
d
G
W
O
g
iv
e
s
g
o
o
d
r
esu
lt
s
f
o
r
r
ec
o
g
n
ize
t
h
e
ex
is
te
n
ce
o
f
Ha
n
cit
o
r
in
th
e
n
e
t
w
o
r
k
w
it
h
ac
cu
r
ac
y
o
f
7
9
.
2
%
b
y
u
s
in
g
A
B
C
a
n
d
9
5
.
8
%
u
s
i
n
g
GW
O
f
o
r
d
ata
d
ep
en
d
o
n
s
tatic
at
tr
ib
u
tes,
f
o
r
th
e
s
ec
o
n
d
t
y
p
e
o
f
d
ata
d
ep
en
d
o
n
I
P
v
4
ch
ar
ac
ter
is
tic
s
th
e
r
ec
o
g
n
itio
n
r
ate
is
9
4
.
3
%
b
y
u
s
i
n
g
A
B
C
an
d
9
2
%
b
y
u
s
i
n
g
GW
O.
T
h
e
p
r
ed
ictio
n
o
f
p
er
ce
n
tag
e
o
f
in
f
ec
tio
n
h
as
g
o
o
d
p
er
f
o
r
m
an
ce
u
s
i
n
g
A
B
C
b
etter
t
h
an
GW
O
w
it
h
d
at
a
d
ep
en
d
o
n
s
tatic
attr
ib
u
te
s
b
etter
th
an
d
ata
d
ep
en
d
o
n
I
P
v
4
c
h
ar
ac
ter
is
tic
s
.
RE
F
E
R
E
NC
E
S
[1
]
.
E.
G
a
n
d
o
tra,
e
t
a
l.
,
"
M
a
lw
a
re
A
n
a
l
y
sis
a
n
d
Clas
sif
ica
ti
o
n
:
A
S
u
rv
e
y
,
"
Jo
u
rn
a
l
o
f
I
n
f
o
rm
a
ti
o
n
S
e
c
u
rit
y
,
v
o
l.
5
,
p
p
.
5
6
-
6
4
,
2
0
1
4
.
[2
]
.
L
.
S
h
u
q
i
n
g
,
e
t
a
l.
,
"
Ne
w
Era
o
f
D
e
e
p
lea
rn
in
g
Ba
se
d
M
a
lw
a
r
e
In
tru
sio
n
:
T
h
e
M
a
lw
a
re
De
t
e
c
ti
o
n
a
n
d
P
re
d
ictio
n
Ba
se
d
o
n
De
e
p
L
e
a
rn
in
g
,
"
Co
mp
u
ter
S
c
i
e
n
c
e
Pu
b
li
s
h
e
d
i
n
ArXi
v
,
2
0
1
9
.
[3
]
.
O.S
.
A
d
e
b
a
y
o
a
n
d
N.
A
b
d
u
l
A
z
iz,
"
Im
p
ro
v
e
d
M
a
lw
a
re
De
te
c
ti
o
n
M
o
d
e
l
w
it
h
A
p
rio
ri
A
ss
o
c
iatio
n
Ru
le an
d
P
a
rti
c
le
S
w
a
r
m
Op
ti
m
iz
a
ti
o
n
,
"
Hin
d
a
wi
S
e
c
u
rity
a
n
d
Co
mm
u
n
ic
a
ti
o
n
Ne
two
rk
s
,
v
o
l.
2
0
1
9
,
p
p
.
1
-
1
3
,
2
0
1
9
.
A
rti
c
le
ID
2
8
5
0
9
3
2
.
h
tt
p
s:/
/d
o
i.
o
rg
/1
0
.
1
1
5
5
/
2
0
1
9
/
2
8
5
0
9
3
2
.
[4
]
.
T
.
S
.
S
o
b
h
,
"
H
y
b
rid
S
w
a
r
m
In
tel
li
g
e
n
c
e
a
n
d
A
rti
f
icia
l
N
e
u
ra
l
Ne
tw
o
rk
f
o
r
M
it
ig
a
ti
n
g
M
a
l
w
a
re
E
ff
e
c
ts,"
Rec
e
n
t
Pa
ten
ts
o
n
Co
mp
u
ter
S
c
ien
c
e
,
v
o
l
.
7
,
n
o
.
1
,
p
p
.
38
-
53
,
2
0
1
4
.
[5
]
.
P
.
V
i
n
o
d
a
n
d
K.
A
.
Dh
a
n
y
a
,
"
I
d
e
n
ti
f
ica
ti
o
n
o
f
M
a
li
c
i
o
u
s
A
n
d
ro
i
d
A
p
p
u
si
n
g
M
a
n
if
e
st
a
n
d
Op
-
c
o
d
e
F
e
a
tu
re
s,"
Jo
u
rn
a
l
o
f
Co
m
p
u
ter V
ir
o
lo
g
y
a
n
d
Ha
c
k
i
n
g
T
e
c
h
n
iq
u
e
s,
S
p
rin
g
e
r
-
V
e
rlag
F
ra
n
c
e
,
v
o
l.
1
3
,
n
o
.
2
,
p
p
.
1
2
5
ā
138
,
2
0
1
7
.
[6
]
.
W
.
Co
h
e
n
,
"
F
a
st
Ef
fe
c
ti
v
e
Ru
le
I
n
d
u
c
t
io
n
,
"
Pro
c
e
e
d
in
g
s
o
f
1
2
t
h
I
n
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
M
a
c
h
i
n
e
L
e
a
rn
in
g
,
S
a
n
Fra
n
c
isc
o
,
p
p
.
1
1
5
-
1
2
3
,
1
9
9
5
.
[7
]
.
M
.
Ha
ll
,
e
t
a
l.
,
"
T
h
e
W
EK
A
D
a
ta
M
in
i
n
g
S
o
f
tw
a
re
:
A
n
Up
d
a
te"
.
ACM
S
IGKD
D
Exp
lo
ra
t
io
n
s
Ne
wsle
tt
e
r
,
p
p
.
1
0
-
1
8
,
2
0
0
9
.
[8
]
.
I.
S
a
n
to
s,
e
t
a
l
.
,
"
S
e
m
i
-
S
u
p
e
rv
ise
d
L
e
a
rn
in
g
f
o
r
Un
k
n
o
w
n
M
a
lw
a
r
e
De
te
c
ti
o
n
,
"
In
ter
n
a
t
io
n
a
l
S
y
mp
o
siu
m
o
n
Distrib
u
ted
C
o
mp
u
ti
n
g
a
n
d
Arti
fi
c
ia
l
In
telli
g
e
n
c
e
Ad
v
a
n
c
e
s
in
I
n
telli
g
e
n
t
a
n
d
S
o
ft
C
o
mp
u
ti
n
g
,
v
o
l
.
9
1
,
p
p
.
4
1
5
-
4
2
2
,
2
0
1
1
.
[9
]
.
M
.
S
i
d
d
iq
u
i,
M
o
rg
a
n
C.
W
a
n
g
,
Jo
o
h
a
n
L
ee
,
"
De
te
c
ti
n
g
In
tern
e
t
W
o
rm
s Us
in
g
Da
ta M
in
in
g
T
e
c
h
n
iq
u
e
s,"
J
o
u
rn
a
l
o
f
S
y
ste
mic
,
Cy
b
e
rn
e
ti
c
s a
n
d
In
f
o
rm
a
ti
c
s
,
v
o
l.
6
,
n
o
.
6
,
p
p
.
4
8
-
5
3
,
2
0
0
9
.
[1
0
]
.
K.
Riec
k
,
e
t
a
l
,
"
A
u
to
m
a
ti
c
A
n
a
l
y
sis
o
f
M
a
lwa
re
Be
h
a
v
io
r
Us
in
g
M
a
c
h
in
e
L
e
a
rn
in
g
,
"
J
o
u
rn
a
l
o
f
C
o
mp
u
ter
S
e
c
u
rity
,
v
o
l.
1
9
,
n
o
.
4
,
p
p
.
6
3
9
-
6
6
8
,
2
0
1
1
.
[1
1
]
.
T
.
L
e
e
a
n
d
M
o
d
y
,
J.
J,
"
Be
h
a
v
io
ra
l
Clas
sif
ica
ti
o
n
,
"
Pro
c
e
e
d
in
g
s
o
f
t
h
e
E
u
ro
p
e
a
n
In
sti
tu
te
fo
r
C
o
mp
u
ter
A
n
ti
v
iru
s
Res
e
a
rc
h
Co
n
fer
e
n
c
e
(EI
CA
Rā0
6
),
2
0
0
6
.
[1
2
]
.
W
.
A
li
,
"
H
y
b
rid
In
telli
g
e
n
t
A
n
d
r
o
id
M
a
lw
a
re
D
e
tec
ti
o
n
Us
in
g
Ev
o
lv
in
g
S
u
p
p
o
rt
V
e
c
to
r
M
a
c
h
i
n
e
Ba
se
d
o
n
G
e
n
e
ti
c
A
l
g
o
rit
h
m
a
n
d
P
a
rti
c
le
S
w
a
rm
Op
ti
m
iza
ti
o
n
,
"
IJ
CS
NS
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
Ne
tw
o
rk
S
e
c
u
rity
,
v
o
l.
1
9
,
n
o
.
9
,
p
p
.
1
5
-
28
,
2
0
1
9
.
[1
3
]
.
J.
Ko
lt
e
r,
a
n
d
M
.
M
a
lo
o
f
,
"
L
e
a
rn
in
g
to
De
tec
t
M
a
li
c
io
u
s
Ex
e
c
u
tab
le
in
th
e
W
il
d
,
"
Pro
c
e
e
d
in
g
s
o
f
t
h
e
10
t
h
ACM
S
IGKD
D In
ter
n
a
ti
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
Kn
o
wled
g
e
Disc
o
v
e
ry
a
n
d
Da
t
a
M
in
i
n
g
,
p
p
.
4
7
0
-
4
7
8
,
2
0
0
4
.
[1
4
]
.
L
.
Na
tara
j,
e
t
a
l.
,
ā
M
a
lw
a
re
I
m
a
g
e
s:
V
isu
a
li
z
a
ti
o
n
a
n
d
A
u
to
m
a
ti
c
Clas
sif
ic
a
ti
o
n
,
"
Pro
c
e
e
d
in
g
s
o
f
t
h
e
8
th
I
n
ter
n
a
t
io
n
a
l
S
y
mp
o
si
u
m o
n
Vi
su
a
li
z
a
ti
o
n
f
o
r
Cy
b
e
r S
e
c
u
rity
,
A
rti
c
le No
.
4
,
2
0
1
1
.
[1
5
]
.
F
ird
a
u
si,
e
t
a
l.
,
"
A
n
a
ly
sis
o
f
M
a
c
h
in
e
L
e
a
rn
in
g
T
e
c
h
n
iq
u
e
s
Us
e
d
in
Be
h
a
v
io
r
Ba
se
d
M
a
lw
a
r
e
De
te
c
ti
o
n
,
"
Pro
c
e
e
d
in
g
s
o
f
2
n
d
I
n
ter
n
a
t
io
n
a
l
Co
n
fer
e
n
c
e
o
n
Ad
v
a
n
c
e
s
in
Co
mp
u
ti
n
g
,
Co
n
t
ro
l
a
n
d
T
e
lec
o
mm
u
n
ica
ti
o
n
T
e
c
h
n
o
l
o
g
ies
(
AC
T
),
J
a
k
a
rta
,
2
-
3
De
c
e
mb
e
r 2
0
1
0
,
p
p
.
2
0
1
-
2
0
3
,
2
0
1
0
.
[1
6
]
.
I.
S
a
n
t
o
s,
e
t
a
l
.
,
"
O
P
EM
:
A
S
tatic
-
D
y
n
a
m
ic
A
p
p
ro
a
c
h
f
o
r
M
a
c
h
in
e
L
e
a
rn
in
g
Ba
se
d
M
a
lw
a
r
e
De
tec
ti
o
n
,
"
Pro
c
e
e
d
in
g
s
o
f
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
CIS
IS
ā1
2
-
ICEUT
Eā
1
2
,
S
p
e
c
ia
l
S
e
ss
io
n
s
Ad
v
a
n
c
e
s
in
In
telli
g
e
n
t
S
y
ste
ms
a
n
d
Co
m
p
u
t
in
g
,
v
o
l.
1
8
9
,
p
p
.
2
7
1
-
2
8
0
,
2
0
1
3
.
[1
7
]
.
R.
Isla
m
,
e
t
a
l.
"
Clas
si
f
ica
ti
o
n
o
f
M
a
l
w
a
re
B
a
se
d
o
n
In
teg
ra
ted
S
tatic
a
n
d
Dy
n
a
m
ic
F
e
a
tu
re
s,"
J
o
u
rn
a
l
o
f
Ne
two
rk
a
n
d
Co
m
p
u
ter
A
p
p
li
c
a
ti
o
n
,
v
o
l.
3
6
,
n
o
.
2
,
p
p
.
6
4
6
-
5
5
6
,
2
0
1
3
.
[1
8
]
.
B.
A
n
d
e
rso
n
,
e
t
a
l.
,
"
Im
p
ro
v
in
g
M
a
lw
a
r
e
Clas
si
f
ic
a
ti
o
n
:
Bri
d
g
in
g
th
e
S
tatic/Dy
n
a
m
ic
G
a
p
,
"
Pro
c
e
e
d
in
g
s
o
f
5
th
ACM
W
o
rk
sh
o
p
o
n
S
e
c
u
rity a
n
d
Arti
fi
c
ia
l
I
n
telli
g
e
n
c
e
(
AIS
e
c
),
3
-
1
4
,
2
0
1
2
.
[1
9
]
.
H.
F
a
ris
,
e
t
a
l
.
"
G
re
y
w
o
l
f
o
p
ti
m
ize
r:
a
re
v
ie
w
o
f
re
c
e
n
t
v
a
rian
ts
a
n
d
a
p
p
li
c
a
ti
o
n
s,"
Ne
u
ra
l
C
o
mp
u
ti
n
g
&
Ap
p
li
c
a
ti
o
n
s
,
vo
l.
3
0
,
n
o
.
2
,
p
p
.
4
1
3
-
4
3
5
,
2
0
1
8
.
[2
0
]
.
S
.
M
irj
a
li
li
,
e
t
a
l.
,
"
A
.
G
re
y
W
o
lf
Op
ti
m
iz
e
r,
"
Ad
v
.
En
g
.
S
o
ft
w.
,
v
o
l.
6
9
,
p
p
.
4
6
ā
6
1
,
2
0
1
4
.
h
tt
p
s:/
/d
o
i.
o
rg
/1
0
.
1
0
1
6
/j
.
a
d
v
e
n
g
so
f
t.
2
0
1
3
.
1
2
.
0
0
7
[2
1
]
.
A
.
Ch
a
k
ra
b
o
rty
a
n
d
A
.
Ka
r
,
"
S
wa
r
m
In
telli
g
e
n
c
e
,
A
Re
v
ie
w
o
f
A
lg
o
rit
h
m
s,"
S
p
rin
g
e
r
In
ter
n
a
ti
o
n
a
l
Pu
b
l
ish
i
n
g
AG
,
v
o
l.
1
0
,
p
p
.
4
7
5
-
4
9
4
,
2
0
1
7
.
h
tt
p
s:/
/d
o
i
.
o
rg
/1
0
.
1
0
0
7
/
9
7
8
-
3
-
3
1
9
-
5
0
9
2
0
-
4
_
1
9
.
[2
2
]
.
P
.
Ra
d
u
Em
il
,
e
t
a
l.
,
"
A
n
Eas
il
y
U
n
d
e
rsta
n
d
a
b
le
G
re
y
W
o
lf
Op
ti
m
iz
e
r
a
n
d
Its
A
p
p
li
c
a
ti
o
n
t
o
F
u
z
z
y
Co
n
tro
ll
e
r
T
u
n
in
g
,
"
Al
g
o
rit
h
ms
,
v
o
l
.
1
0
,
n
o
.
2
,
p
p
.
1
-
15
,
2
0
1
7
.
[2
3
]
.
K.
M
u
ra
li
e
t
a
l.
,
"
A
u
to
m
a
ted
I
m
a
g
e
En
h
a
n
c
e
m
e
n
t
Us
in
g
G
re
y
-
W
o
lf
Op
ti
m
ize
r
A
lg
o
rit
h
m
,
"
IIOAB
J
,
v
o
l.
7
,
n
o
.
3
,
p
p
.
77
-
84
,
2
0
1
6
.
Evaluation Warning : The document was created with Spire.PDF for Python.
ļ²
I
SS
N
:
2722
-
3221
C
o
m
p
u
t.
Sci.
I
n
f
.
T
ec
h
n
o
l.
,
Vo
l.
2
,
No
.
3
,
No
v
em
b
er
20
2
1
:
1
03
ā
1
12
112
[2
4
]
.
T
.
Yin
g
,
e
t
a
l
.,
"
A
d
v
a
n
c
e
s
i
n
S
w
a
r
m
I
n
t
e
l
l
i
g
e
n
c
e
,
"
1
0
th
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
,
ICS
I
2
0
1
9
,
Ch
i
a
n
g
M
a
i,
T
h
a
il
a
n
d
,
J
u
ly 2
6
ā
3
0
,
2
0
1
9
,
Pro
c
e
e
d
i
n
g
s
,
s
p
rin
g
e
r
P
a
rt
I,
2
0
1
9
.
[2
5
]
.
C.
Zh
a
n
g
.
,
e
t
a
l
.,
"
A
n
a
rti
f
icia
l
b
e
e
c
o
lo
n
y
a
p
p
ro
a
c
h
f
o
r
c
lu
ste
ri
n
g
,
"
Exp
e
rt S
y
st.
A
p
p
l
.
v
o
l.
3
7
,
n
o
.
7
,
p
p
.
4
7
6
1
ā
4
7
6
7
,
2
0
1
0
.
[2
6
]
.
C.
Xu
,
e
t
a
l
.,
"
Ch
a
o
ti
c
a
rti
f
icia
l
b
e
e
c
o
lo
n
y
a
p
p
ro
a
c
h
to
u
n
in
h
a
b
it
e
d
c
o
m
b
a
t
a
ir
v
e
h
icle
(UCA
V
)
p
a
th
p
lan
n
in
g
.
A
e
ro
sp
,
"
S
c
i.
T
e
c
h
n
o
l
.
,
v
o
l
.
1
4
,
n
o
.
8
,
p
p
.
5
3
5
ā
5
4
1
,
2
0
1
0
.
[2
7
]
.
Ha
n
c
it
o
r
m
a
lsp
a
m
a
n
d
in
f
e
c
ti
o
n
traf
f
ic
,
2
0
1
9
-
02
-
05
.
[
On
li
n
e
]
.
A
v
a
il
a
b
le:
h
tt
p
s:/
/i
sc
.
sa
n
s.e
d
u
/f
o
r
u
m
s/d
iar
y
/
Ha
n
c
it
o
r+
m
a
lsp
a
m
+
a
n
d
+
in
f
e
c
ti
o
n
+
traff
ic+
f
ro
m
+
T
u
e
sd
a
y
+
2
0
1
9
0
2
0
5
/
2
4
6
1
6
/
[2
8
]
.
L
.
Qia
n
g
,
e
t
a
l.
,
"
A
n
En
h
a
n
c
e
d
G
re
y
W
o
lf
Op
ti
m
iza
ti
o
n
Ba
se
d
F
e
a
tu
re
S
e
lec
ti
o
n
W
ra
p
p
e
d
Ke
rn
e
l
E
x
tre
m
e
L
e
a
rn
in
g
M
a
c
h
in
e
f
o
r
M
e
d
ica
l
Dia
g
n
o
sis,
"
Co
mp
u
ta
t
io
n
a
l
a
n
d
M
a
th
e
ma
ti
c
a
l
M
e
th
o
d
s
i
n
M
e
d
ici
n
e
,
v
o
l.
2
0
1
7
,
A
rti
c
le
ID
9
5
1
2
7
4
,
p
p
.
1
-
1
5
,
2
0
1
7
.
h
tt
p
s://
d
o
i
.
o
rg
/1
0
.
1
1
5
5
/2
0
1
7
/
9
5
1
2
7
4
1
0
2
0
0
6
8
ww
w
.
m
d
p
i.
c
o
m
/j
o
u
rn
a
l/
a
lg
o
r
it
h
m
s
.
[2
9
]
.
S
.
S
h
a
rm
a
,
e
t
a
l.
,
"
A
rti
f
i
c
ial
Be
e
Co
lo
n
y
A
l
g
o
rit
h
m
:
A
S
u
rv
e
y
,
"
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Co
mp
u
ter
A
p
p
li
c
a
ti
o
n
s,
v
o
l.
1
4
9
ā
no
.
4
,
p
p
.
1
1
-
1
9
,
2
0
1
6
.
[3
0
]
.
D.
Ka
ra
b
o
g
a
,
e
t
a
l
.
,
"
A
rti
f
icia
l
Be
e
Co
lo
n
y
(
A
BC)
Op
ti
m
iza
ti
o
n
A
l
g
o
rit
h
m
f
o
r
S
o
lv
in
g
C
o
n
stra
i
n
e
d
Op
ti
m
iza
ti
o
n
P
r
o
b
lem
s,
ā
Pro
c
.
IFS
A
2
0
0
7
,
L
N
AI
4
5
2
9
,
2
0
0
7
,
p
p
.
7
8
9
-
7
9
8
.
[3
1
]
.
K.
De
b
,
"
A
n
Ef
f
i
c
ien
t
Co
n
stra
i
n
th
a
n
d
li
n
g
M
e
th
o
d
f
o
r
G
e
n
e
ti
c
A
lg
o
rit
h
m
s,"
Co
mp
u
ter
M
e
th
o
d
s
in
A
p
p
li
e
d
M
e
c
h
a
n
ics
a
n
d
En
g
i
n
e
e
rin
g
,
v
o
l.
1
8
6
,
n
o
.
2
-
4
,
p
p
.
3
1
1
-
3
3
8
,
2
0
0
0
.
[3
2
]
.
I.
S
a
n
t
o
s,
e
t
a
l
.
,
"
O
P
EM
:
A
S
tatic
-
D
y
n
a
m
ic
A
p
p
ro
a
c
h
f
o
r
M
a
c
h
in
e
L
e
a
rn
in
g
Ba
se
d
M
a
lw
a
r
e
De
tec
ti
o
n
,
"
Pro
c
e
e
d
in
g
s
o
f
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
CIS
IS
ā1
2
-
ICEUT
Eā
1
2
,
S
p
e
c
ia
l
S
e
ss
io
n
s
Ad
v
a
n
c
e
s
in
In
telli
g
e
n
t
S
y
ste
ms
a
n
d
Co
m
p
u
t
in
g
,
v
o
l.
1
8
9
,
p
p
.
2
7
1
-
2
8
0
,
2
0
1
3
.
Evaluation Warning : The document was created with Spire.PDF for Python.