I
nte
rna
t
io
na
l J
o
urna
l o
f
Appl
ied P
o
wer
E
ng
i
neer
ing
(
I
J
AP
E
)
Vo
l.
14
,
No
.
3
,
Sep
tem
b
er
20
25
,
p
p
.
7
2
2
~
73
2
I
SS
N:
2252
-
8
7
9
2
,
DOI
:
1
0
.
1
1
5
9
1
/ijap
e
.
v
14
.
i
3
.
pp
722
-
73
2
722
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//
ija
p
e.
ia
esco
r
e.
co
m/
G
a
ted
dila
ted
ca
u
sa
l conv
o
lution
-
ba
sed enco
der
-
dec
o
der
network
for Io
T i
ntrusio
n de
tec
tion
Aa
rt
hi G
o
pa
la
k
rish
na
n,
Sh
a
ro
n P
riy
a
Su
re
nd
ra
n,
Ais
ha
B
a
nu
Wa
ha
b
D
e
p
a
r
t
me
n
t
o
f
C
o
mp
u
t
e
r
S
c
i
e
n
c
e
a
n
d
En
g
i
n
e
e
r
i
n
g
,
B
.
S
.
A
b
d
u
r
R
a
h
m
a
n
C
r
e
sce
n
t
I
n
st
i
t
u
t
e
o
f
S
c
i
e
n
c
e
a
n
d
Te
c
h
n
o
l
o
g
y
,
C
h
e
n
n
a
i
,
I
n
d
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Ap
r
1
2
,
2
0
2
4
R
ev
is
ed
Ma
r
1
4
,
2
0
2
5
Acc
ep
ted
J
u
n
2
3
,
2
0
2
5
Th
e
in
ter
n
e
t
o
f
th
i
n
g
s
(Io
T)
is
p
e
rh
a
p
s
th
e
g
re
a
tes
t
m
o
d
e
rn
d
e
v
e
l
o
p
m
e
n
t,
a
s
it
a
ffe
c
ts
o
u
r
d
a
il
y
li
v
e
s
a
n
d
is
r
a
p
id
l
y
e
x
p
a
n
d
i
n
g
i
n
it
s
a
p
p
li
c
a
ti
o
n
z
o
n
e
s.
Th
e
Io
T
is
u
se
d
i
n
e
v
e
ry
d
a
y
a
c
ti
v
it
ies
,
so
se
c
u
rit
y
is
m
o
re
c
ru
c
ia
l
b
e
c
a
u
se
in
tru
si
o
n
d
e
tec
ti
o
n
will
i
n
tr
o
d
u
c
e
a
n
d
e
li
m
in
a
te
a
tt
a
c
k
s.
In
th
is
p
a
p
e
r,
a
n
o
v
e
l
d
e
e
p
lea
rn
i
n
g
b
a
se
d
in
tr
u
s
io
n
d
e
tec
ti
o
n
tec
h
n
i
q
u
e
(DEBIT
)
h
a
s
b
e
e
n
p
ro
p
o
se
d
th
a
t
d
e
tec
ts
th
e
in
t
ru
sio
n
u
si
n
g
d
e
e
p
lea
rn
i
n
g
t
e
c
h
n
iq
u
e
s
e
fficie
n
tl
y
.
In
it
ially
,
th
e
d
a
ta
fr
o
m
Io
T
u
se
r
is
p
re
p
r
o
c
e
ss
e
d
a
n
d
c
las
sified
u
sin
g
t
h
e
n
o
v
e
l
g
a
ted
d
il
a
ted
c
a
su
a
l
c
o
n
v
o
lu
ti
o
n
b
a
se
d
e
n
c
o
d
e
r
-
d
e
c
o
d
e
r
(G
DCC
-
ED)
m
e
th
o
d
,
wh
ich
c
las
sifies
th
e
d
a
ta
i
n
t
o
a
tt
a
c
k
a
n
d
n
o
n
-
a
tt
a
c
k
.
Th
e
p
r
o
p
o
se
d
DEBIT
fra
m
e
wo
rk
h
a
s
b
e
e
n
a
ss
e
ss
e
d
u
sin
g
a
M
ATLAB
sim
u
lato
r.
Th
e
p
e
rf
o
rm
a
n
c
e
o
f
th
e
p
ro
p
o
se
d
DEBIT
fra
m
e
wo
rk
h
a
s
b
e
e
n
a
ss
e
ss
e
d
b
a
se
d
o
n
sp
e
c
ifi
c
p
a
ra
m
e
ters
,
in
c
lu
d
in
g
re
c
a
ll
,
d
e
tec
ti
o
n
ra
te
,
a
c
c
u
ra
c
y
,
F
1
sc
o
re
,
a
n
d
p
re
c
is
io
n
.
Ba
se
d
o
n
e
x
p
e
rime
n
tal
re
su
lt
s,
t
h
e
su
g
g
e
ste
d
m
e
th
o
d
is
9
9
.
5
%
m
o
re
a
c
c
u
ra
te
th
a
n
p
ig
e
o
n
-
in
sp
ired
o
p
ti
m
iza
ti
o
n
(P
IO),
Re
s
-
Tran
BiL
S
TM
,
a
n
d
b
lo
c
k
c
h
a
in
-
b
a
se
d
Afric
a
n
b
u
ffa
lo
(Bb
AB),
wh
ich
a
re
8
5
.
4
%
,
9
2
.
5
%
,
a
n
d
8
5
%
,
re
sp
e
c
ti
v
e
l
y
.
K
ey
w
o
r
d
s
:
B
o
T
-
I
o
T
d
ataset
Dee
p
lear
n
in
g
GDC
C
-
ED
I
n
ter
n
et
o
f
th
in
g
s
I
n
tr
u
s
io
n
d
etec
tio
n
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
:
Sh
ar
o
n
Priy
a
S
u
r
en
d
r
a
n
Dep
ar
tm
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
an
d
E
n
g
in
ee
r
in
g
B
.
S.
Ab
d
u
r
R
ah
m
an
C
r
escen
t
I
n
s
titu
te
o
f
Scien
ce
an
d
T
ec
h
n
o
lo
g
y
C
h
en
n
ai,
I
n
d
i
a
E
m
ail:
s
h
ar
o
n
p
r
i
y
a@
cr
escen
t.e
d
u
ca
tio
n
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
in
ter
n
et
o
f
th
i
n
g
s
(
I
o
T
)
is
a
r
elativ
ely
r
ec
en
t
in
v
en
tio
n
t
r
an
s
f
o
r
m
th
e
way
p
e
o
p
le
liv
e,
wo
r
k
,
an
d
en
jo
y
life
[
1
]
.
I
n
in
d
u
s
tr
ies
lik
e
m
an
u
f
ac
tu
r
in
g
,
h
ea
lth
,
a
g
r
icu
ltu
r
e,
ed
u
ca
tio
n
,
an
d
to
u
r
is
m
,
th
is
tech
n
o
lo
g
y
g
iv
es
b
u
s
in
ess
es
an
d
o
r
g
an
izatio
n
s
en
o
r
m
o
u
s
b
u
s
in
ess
v
alu
e
[
2
]
,
[
3
]
.
I
o
T
is
a
n
ew
p
ar
ad
ig
m
f
o
r
co
m
m
u
n
icatio
n
lik
e
u
s
es
s
en
s
o
r
s
to
let
o
b
jects
d
etec
t
th
eir
s
u
r
r
o
u
n
d
in
g
s
,
talk
to
a
n
o
th
er
,
a
n
d
tr
an
s
f
er
d
ata
on
th
e
in
ter
n
et
[
4
]
,
[
5
]
.
I
n
th
e
y
ea
r
s
th
at
f
o
llo
w,
th
e
r
e
will
b
e
an
u
n
p
r
ec
ed
e
n
ted
a
m
o
u
n
t
o
f
I
o
T
d
e
v
ices
ass
o
cia
ted
to
th
e
in
ter
n
et
[
6
]
,
[
7
]
.
T
h
e
av
ailab
ilit
y
,
in
teg
r
ity
,
a
n
d
d
ata
p
r
iv
ac
y
ar
e
s
er
io
u
s
ly
e
n
d
an
g
er
ed
b
y
it
s
g
r
o
win
g
v
o
lu
m
e,
an
d
m
alicio
u
s
ac
to
r
s
m
ay
ex
p
l
o
it
all
o
f
th
ese
asp
ec
ts
[
8
]
.
I
o
T
s
ec
u
r
ity
h
as
g
ain
ed
m
o
r
e
att
en
tio
n
as
a
r
esu
lt
o
f
a
n
u
m
b
e
r
o
f
in
n
o
v
ativ
e
ap
p
s
th
at
m
ak
e
u
s
e
o
f
co
n
n
ec
ted
d
e
v
ices th
at
h
av
e
b
ee
n
d
ev
el
o
p
e
d
r
ec
en
tly
[
9
,
1
0
]
.
C
o
n
s
id
er
in
g
th
e
s
ec
u
r
ity
m
ea
s
u
r
es,
it
is
v
ital
to
b
u
ild
a
s
ec
u
r
ity
m
o
d
el
f
o
r
an
I
o
T
e
n
v
ir
o
n
m
en
t
[
1
1
]
.
T
o
p
r
ev
en
t
h
ar
m
f
u
l
u
s
er
s
f
r
o
m
g
ain
in
g
u
n
wan
ted
ac
ce
s
s
to
d
ata
s
o
u
r
ce
s
,
d
ata
-
o
r
ie
n
ted
s
ec
u
r
ity
m
ea
s
u
r
es
m
u
s
t
b
e
p
r
io
r
itized
.
Ma
n
y
a
r
tific
ial
in
tellig
en
ce
(
AI
)
ap
p
r
o
ac
h
es,
in
clu
d
in
g
co
n
v
o
lu
tio
n
a
l
n
eu
r
al
n
etwo
r
k
s
(
C
NN)
,
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
i
n
es
(
SVM)
,
B
ay
es
ian
n
etwo
r
k
s
,
an
d
d
ee
p
b
elief
n
etwo
r
k
s
(
DB
N)
,
ar
e
wid
ely
u
s
ed
to
id
e
n
tify
p
atter
n
s
o
f
u
n
u
s
u
al
b
eh
av
i
o
r
in
I
o
T
n
etwo
r
k
s
[
1
2
]
-
[
1
5
]
.
AI
is
a
u
s
ef
u
l
to
o
l
th
at
ca
n
b
e
u
s
ed
to
d
etec
t
h
ar
m
f
u
l
ass
au
lts
in
a
tim
ely
m
an
n
er
.
E
v
en
th
o
u
g
h
in
t
r
u
s
io
n
d
etec
tio
n
f
o
r
I
o
T
n
etw
o
r
k
s
u
tili
ze
s
a
lo
t
o
f
DL
tech
n
iq
u
es,
s
ec
u
r
ity
r
em
ai
n
s
an
is
s
u
e
[
1
6
]
,
[
1
7
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ap
p
l Po
wer
E
n
g
I
SS
N:
2252
-
8
7
9
2
Ga
ted
d
ila
ted
c
a
u
s
a
l c
o
n
v
o
lu
t
io
n
-
b
a
s
ed
e
n
co
d
er
-
d
ec
o
d
er n
e
tw
o
r
k
fo
r
I
o
T
…
(
A
a
r
th
i G
o
p
a
la
kris
h
n
a
n
)
723
T
h
ese
s
tu
d
ies
d
em
o
n
s
tr
ate
s
ev
er
al
s
tr
ateg
ies
f
o
r
en
h
a
n
cin
g
I
o
T
s
ec
u
r
ity
u
s
in
g
ef
f
icien
t
in
tr
u
s
io
n
d
etec
tio
n
s
y
s
tem
s
(
I
DS)
s
o
lu
ti
o
n
s
th
at
m
ak
e
u
tili
ze
o
f
DL
,
c
lo
u
d
co
m
p
u
tin
g
,
a
n
d
s
p
ec
ializ
ed
alg
o
r
ith
m
s
[
1
8
]
.
I
o
T
p
latf
o
r
m
s
p
o
s
e
a
n
u
m
b
er
o
f
ch
allen
g
es,
in
cl
u
d
in
g
c
o
m
p
u
tatio
n
al
o
v
er
h
ea
d
,
th
e
co
m
p
l
ex
ity
o
f
in
teg
r
atin
g
with
d
iv
er
s
e
p
latf
o
r
m
s
,
m
an
a
g
in
g
f
alse
p
o
s
itiv
es
an
d
f
alse
n
eg
ativ
es,
th
e
in
h
er
e
n
t
c
y
b
e
r
s
ec
u
r
ity
r
is
k
s
,
t
h
e
o
p
tim
izatio
n
o
f
I
DS
f
o
r
r
es
o
u
r
ce
-
c
o
n
s
tr
ain
ed
en
v
ir
o
n
m
e
n
ts
,
th
e
v
ar
iab
ilit
y
o
f
d
ataset
q
u
ality
,
an
d
t
h
e
em
er
g
en
ce
o
f
c
y
b
er
th
r
ea
ts
w
ith
in
I
o
T
ec
o
s
y
s
tem
s
[
1
9
]
.
T
o
o
v
e
r
co
m
e
t
h
ese
ch
allen
g
es
s
ev
er
al
s
tu
d
ies
lik
e
en
co
d
er
-
d
ec
o
d
er
[
2
0
]
tech
n
iq
u
es h
as b
ee
n
u
s
ed
,
y
et
h
av
e
p
o
s
e
d
s
o
m
e
ch
allen
g
es [
2
1
]
.
I
n
2
0
2
0
,
R
an
i
an
d
Kau
s
h
al
[
22
]
s
u
g
g
ested
a
s
u
p
er
v
is
ed
ML
tech
n
iq
u
e
-
b
ased
,
u
n
if
o
r
m
I
DS
th
at
i
s
b
o
th
e
f
f
icien
t
a
n
d
u
s
es
a
R
an
d
o
m
Fo
r
est
class
if
ier
.
T
h
e
lim
ited
s
to
r
ag
e
ca
p
ac
ity
a
n
d
c
o
m
p
u
tatio
n
al
lim
its
o
f
I
o
T
h
a
v
e
led
to
en
h
a
n
ce
in
th
e
p
o
p
u
lar
ity
o
f
clo
u
d
-
b
ased
I
o
T
.
I
n
2
0
2
0
,
Sicato
et
a
l
.
[
23
]
p
r
o
p
o
s
ed
d
is
tr
ib
u
ted
clo
u
d
f
r
am
ew
o
r
k
with
s
o
f
twa
r
e
-
d
ef
in
e
d
I
DS,
wh
ich
p
r
o
v
id
es
a
s
af
e
I
o
T
en
v
ir
o
n
m
e
n
t.
An
ef
f
icien
t
I
DS
is
ess
en
tial,
as
ev
id
en
ce
d
b
y
th
e
r
is
e
in
b
o
th
th
e
q
u
a
n
tity
an
d
r
an
g
e
o
f
s
ec
u
r
ity
th
r
ea
ts
to
th
es
e
s
y
s
tem
s
.
I
n
2
0
2
1
,
Ullah
an
d
Ma
h
m
o
u
d
[
24
]
s
u
g
g
ested
C
NN
m
o
d
el
is
test
ed
u
s
in
g
th
e
I
D
d
atasets
f
r
o
m
I
o
T
-
2
3
,
B
o
T
-
I
o
T
,
an
d
I
o
T
n
etwo
r
k
in
tr
u
s
io
n
.
T
h
e
class
es
s
p
ar
ta,
n
o
r
m
al
,
a
n
d
s
ca
n
ar
e
c
o
r
r
ec
tly
id
e
n
tifie
d
.
T
h
e
s
in
g
le
m
is
class
if
icatio
n
r
esu
lted
in
an
FNR
o
f
1
.
4
8
% f
o
r
th
e
MQ
T
T
b
r
u
te
f
o
r
ce
ass
au
lt c
lass
.
I
n
2
0
2
1
,
Kaln
o
o
r
a
n
d
Go
wr
is
h
an
k
ar
[2
5
]
p
r
o
v
id
e
d
a
h
ig
h
lev
el
o
f
s
ec
u
r
ity
f
o
r
I
o
T
s
m
ar
t
en
v
ir
o
n
m
en
ts
b
y
u
tili
zin
g
th
e
in
n
o
v
ativ
e
in
tellig
en
t I
DS te
ch
n
iq
u
e.
W
h
en
co
m
p
ar
ed
to
alt
er
n
ativ
e
alg
o
r
ith
m
s
,
th
e
s
u
g
g
ested
m
o
d
el'
s
ac
cu
r
ac
y
h
as
b
ee
n
1
0
0
%.
I
n
2
0
2
3
,
Su
b
r
am
an
i
an
d
Selv
i
[
2
6
]
p
r
o
p
o
s
ed
a
n
i
n
tellig
en
t
I
DS
to
f
in
d
in
tr
u
s
io
n
s
in
I
o
T
b
ased
W
SN.
B
y
m
in
im
izi
n
g
f
alse
p
o
s
itiv
e
r
ates
an
d
im
p
r
o
v
i
n
g
d
etec
tio
n
ac
cu
r
ac
y
,
th
e
s
tu
d
ies
co
n
d
u
ct
ed
with
C
I
DD
an
d
KDD
'
9
9
C
u
p
d
atasets
f
o
r
ev
alu
atio
n
s
h
o
w
th
at
th
e
I
DS
can
ca
tch
th
e
in
t
r
u
d
er
s
m
o
r
e
p
r
e
cisely
.
I
n
2
0
2
3
,
Alg
h
a
n
am
e
t
a
l
.
[2
7
]
p
r
o
p
o
s
ed
to
en
h
an
ce
p
ig
eo
n
-
in
s
p
ir
ed
o
p
tim
izatio
n
(
PIO
)
b
y
in
c
o
r
p
o
r
atin
g
a
lo
ca
l
s
ea
r
ch
(LS
-
PIO
)
t
ec
h
n
iq
u
e.
T
h
e
r
ec
o
m
m
en
d
ed
ap
p
r
o
ac
h
o
u
tp
er
f
o
r
m
s
alter
n
ativ
e
NI
D
S
m
eth
o
d
s
s
elec
ted
f
r
o
m
th
e
liter
atu
r
e
b
ased
o
n
t
h
e
m
o
s
t
r
ec
en
t
r
elev
an
t
r
esear
ch
,
as p
er
th
e
r
esu
lts
.
I
n
2
0
2
3
,
C
ao
et
a
l
.
[2
8
]
s
u
g
g
ested
an
en
s
em
b
le
lear
n
in
g
p
r
o
ce
s
s
o
n
s
tack
in
g
to
cr
ea
te
a
s
u
cc
ess
f
u
l
I
DS.
T
h
e
ex
p
er
im
e
n
t'
s
r
esu
lt
s
s
u
g
g
est
th
at
p
r
o
p
o
s
ed
I
DS
m
ay
im
p
r
o
v
e
I
o
T
d
ev
ice
s
ec
u
r
it
y
an
d
r
ea
c
h
a
h
u
g
e
ac
cu
r
ac
y
r
ate
o
f
9
9
.
6
8
%,
wh
ich
wo
u
ld
ev
e
n
tu
ally
b
e
n
ef
it
th
e
u
s
er
s
wh
o
r
ely
o
n
th
ese
d
ev
ices.
I
n
2
0
2
3
,
W
an
g
et
a
l.
[2
9
]
p
r
o
p
o
s
ed
R
es
-
T
r
an
B
iLST
M,
an
I
D
m
o
d
el
th
at
c
o
n
s
id
er
s
tem
p
o
r
al
an
d
g
eo
g
r
ap
h
ical
ch
ar
ac
ter
is
tics
o
f
n
etwo
r
k
tr
a
f
f
ic.
T
h
e
r
esu
lts
d
e
m
o
n
s
tr
ate
th
at
r
ec
o
m
m
en
d
ed
s
y
s
tem
p
er
f
o
r
m
s
b
etter
th
a
n
o
th
er
s
y
s
tem
s
.
I
n
2
0
2
3
,
Sar
av
an
an
et
a
l.
[
30
]
p
r
o
p
o
s
ed
to
id
en
tify
in
tr
u
s
io
n
s
an
d
en
h
a
n
ce
s
ec
u
r
ity
b
y
u
tili
zin
g
th
e
Af
r
ican
b
u
f
f
alo
(
B
b
AB
)
s
y
s
tem
.
B
etter
h
ig
h
r
ec
all
o
f
9
9
.
9
2
%
an
d
ac
cu
r
ac
y
o
f
9
9
.
8
7
%
ar
e
ac
h
iev
ed
b
y
th
e
d
ev
elo
p
e
d
m
eth
o
d
’
s
p
er
f
o
r
m
a
n
ce
.
T
o
o
v
er
co
m
e
th
ese
is
s
u
e,
o
f
f
er
s
a
DE
B
I
T
f
r
am
ewo
r
k
f
o
r
p
r
ev
en
tin
g
n
etwo
r
k
attac
k
s
o
n
th
e
I
o
T
to
d
etec
t in
tr
u
s
io
n
s
.
T
h
e
f
o
llo
win
g
ar
e
th
e
c
o
n
tr
ib
u
tio
n
s
o
f
t
h
e
s
u
g
g
ested
DE
B
I
T
f
r
am
ew
o
r
k
:
-
I
n
itially
,
th
e
d
ata
is
co
llected
f
r
o
m
th
e
I
o
T
u
s
er
tr
af
f
ic
an
d
t
h
is
d
ata
is
f
ed
in
to
p
r
ep
r
o
ce
s
s
ed
tech
n
iq
u
es
s
u
ch
as
d
ata
clea
n
in
g
,
to
k
en
iz
atio
n
,
lem
m
atiza
tio
n
,
a
n
d
s
te
m
m
in
g
.
-
T
h
e
GDCC
B
-
E
D
ap
p
r
o
ac
h
is
u
s
ed
to
p
r
o
ce
s
s
th
e
d
ata
an
d
f
o
r
ec
ast
wh
eth
er
an
attac
k
o
r
n
o
n
-
attac
k
h
as
o
cc
u
r
r
e
d
.
-
T
h
e
m
ain
ad
v
an
tag
e
o
f
th
e
p
r
o
p
o
s
ed
m
eth
o
d
s
ig
n
if
ican
tl
y
en
h
an
ce
s
ac
cu
r
ac
y
in
f
au
lt
p
r
ed
ictio
n
b
y
ef
f
icien
tly
ca
p
tu
r
in
g
lo
n
g
-
r
an
g
e
d
ep
en
d
en
cies a
n
d
p
r
o
ce
s
s
in
g
tem
p
o
r
al
d
ata
in
r
ea
l tim
e.
-
E
v
alu
atio
n
s
o
f
th
e
s
u
g
g
ested
DE
B
I
T
f
r
am
ewo
r
k
'
s
p
er
f
o
r
m
an
ce
h
av
e
b
ee
n
co
n
d
u
cte
d
u
s
in
g
p
ar
ticu
lar
m
etr
ics,
in
clu
d
in
g
F1
s
co
r
e,
d
etec
tio
n
r
ate,
p
r
ec
is
io
n
,
ac
cu
r
a
cy
,
an
d
r
ec
all.
T
h
e
r
est
o
f
th
e
a
n
aly
s
is
is
ar
r
an
g
ed
as
f
o
llo
ws:
I
n
s
ec
tio
n
2
,
f
in
d
in
g
th
e
liter
atu
r
e
r
ev
i
ew
o
n
DL
tech
n
iq
u
es
f
o
r
I
DS
ar
e
d
is
p
la
y
ed
.
S
ec
tio
n
3
p
r
esen
ts
an
ex
p
lan
atio
n
o
f
th
e
s
u
g
g
ested
DE
B
I
T
m
eth
o
d
o
lo
g
y
.
T
h
e
ex
p
e
r
im
en
tal
r
esu
lts
ar
e
g
iv
en
in
s
ec
tio
n
4
,
an
d
a
s
tu
d
y
s
u
m
m
ar
y
is
p
r
o
v
id
e
d
in
s
ec
tio
n
5
.
2.
P
RO
P
O
SE
D
M
E
T
H
O
DO
L
O
G
Y
T
o
o
v
er
co
m
e
th
e
n
o
v
el
p
r
o
p
o
s
ed
in
th
is
s
ec
tio
n
,
Fig
u
r
e
1
r
ep
r
esen
ts
th
e
I
o
T
u
tili
zin
g
t
h
e
DL
b
ased
in
tr
u
s
io
n
d
etec
tio
n
(
DE
B
I
T
)
f
r
am
ewo
r
k
.
T
h
e
p
r
e
p
r
o
ce
s
s
in
g
o
f
th
e
p
r
o
p
o
s
ed
f
r
am
e
wo
r
k
in
cl
u
d
es
d
ata
clea
n
in
g
,
to
k
e
n
izatio
n
,
lem
m
a
tizatio
n
,
an
d
s
tem
m
in
g
.
T
h
e
G
DC
C
B
-
E
D
m
o
d
el
is
u
s
ed
to
p
r
o
ce
s
s
th
e
d
ata
an
d
f
o
r
ec
ast
wh
eth
er
an
attac
k
o
r
n
o
n
-
attac
k
h
as
o
cc
u
r
r
ed
.
T
h
i
s
will
b
e
o
b
v
io
u
s
in
th
e
f
in
al
p
r
o
d
u
ct'
s
q
u
ality
,
wh
ich
will
u
s
e
an
id
ea
l
s
u
b
s
et
o
f
f
ea
tu
r
es
an
d
in
c
r
ea
s
e
th
e
p
o
s
s
ib
ilit
y
o
f
I
D
in
an
I
o
T
en
v
i
r
o
n
m
e
n
t.
A
th
o
r
o
u
g
h
e
x
p
lan
atio
n
o
f
t
h
e
f
r
am
ewo
r
k
will b
e
p
r
o
v
id
e
d
i
n
th
e
p
ar
ts
th
at
f
o
llo
w
.
2
.
1
.
Da
t
a
c
o
llect
io
n
Sev
er
al
d
atasets
h
av
e
b
ee
n
u
s
ed
b
y
r
esear
c
h
er
s
to
ass
ess
s
y
s
tem
s
.
T
h
e
UNSW
in
C
an
b
er
r
a
p
r
o
d
u
ce
d
th
e
B
o
T
-
I
o
T
d
ataset
was
cr
e
ated
f
o
r
th
is
p
u
r
p
o
s
e
th
e
UNSW
L
ab
o
r
ato
r
y
.
C
o
m
b
in
in
g
r
eg
u
lar
tr
af
f
ic
with
b
o
tn
ets,
th
e
en
v
ir
o
n
m
en
t
was
f
o
r
m
e
d
.
C
o
m
m
a
s
ep
ar
ated
v
alu
es
(
C
SV)
f
iles
an
d
th
e
o
r
i
g
in
al
f
ile
with
a
ca
p
ex
ten
s
io
n
wer
e
two
o
f
th
e
f
o
r
m
s
in
wh
ich
th
e
d
ata
s
o
u
r
ce
s
wer
e
s
u
p
p
lied
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
9
2
I
n
t J Ap
p
l Po
wer
E
n
g
,
Vo
l.
14
,
No
.
3
,
Sep
tem
b
er
20
25
:
7
2
2
-
73
2
724
Fig
u
r
e
1
.
T
h
e
o
v
er
all
b
lo
ck
d
i
ag
r
am
f
o
r
th
e
p
r
o
p
o
s
ed
DE
B
I
T
f
r
am
ewo
r
k
wh
ich
c
o
n
tain
s
p
r
e
-
p
r
o
ce
s
s
in
g
a
n
d
GDC
C
B
-
E
D
m
o
d
el
f
o
r
in
tr
u
s
io
n
d
etec
tio
n
2
.
2
.
P
re
-
pro
ce
s
s
ing
Data
p
r
o
ce
s
s
in
g
is
d
o
n
e
in
ad
v
an
ce
to
g
et
it
r
ea
d
y
f
o
r
m
ai
n
p
r
o
ce
s
s
in
g
o
r
ad
d
itio
n
al
an
aly
s
is
.
T
h
e
p
r
ep
r
o
ce
s
s
in
g
d
ata
h
as
s
p
lit
i
n
to
d
ata
clea
n
in
g
,
to
k
en
izatio
n
,
lem
m
atiza
tio
n
,
an
d
s
tem
m
i
n
g
.
T
h
e
d
ataset
is
in
itially
clea
n
ed
in
th
is
s
tep
-
i
n
o
r
d
er
to
g
et
r
id
o
f
d
u
p
licate
r
ec
o
r
d
s
.
Nev
er
th
eless
,
we
m
ak
e
u
s
e
o
f
th
e
p
r
e
-
clea
n
ed
B
o
t
-
I
o
T
d
ataset.
T
h
u
s
,
th
is
clea
n
in
g
s
tep
is
n
o
t
im
p
o
r
tan
t
in
o
u
r
ex
p
e
r
im
en
t;
n
ev
er
th
eless
,
it
is
n
ec
ess
ar
y
if
th
e
o
r
ig
in
al
d
atas
et,
s
u
ch
as
KDD'
9
9
,
is
em
p
lo
y
ed
.
Af
ter
d
ata
clea
n
in
g
,
t
h
e
s
en
ten
ce
'
s
"to
k
en
s
,
"
o
r
wo
r
d
s
an
d
p
u
n
ctu
atio
n
,
a
p
p
ea
r
f
ir
s
t.
I
n
th
e
tex
tb
o
x
b
el
o
w,
th
e
o
u
tp
u
t
in
s
er
ts
p
ip
e
c
h
ar
ac
ter
s
in
b
etwe
en
th
e
to
k
en
s
.
E
v
er
y
in
f
lectio
n
is
m
a
p
p
ed
b
y
a
lem
m
atize
r
to
a
ca
n
o
n
ical
f
o
r
m
ca
lled
th
e
lem
m
a,
wh
ich
is
u
s
u
ally
th
e
f
o
r
m
f
o
u
n
d
in
d
ictio
n
ar
ie
s
wr
itten
in
th
e
la
n
g
u
a
g
e
o
f
th
e
in
ten
d
e
d
au
d
ien
ce
.
W
e
u
s
e
th
e
T
r
ee
T
a
g
g
er
lem
m
atize
r
in
th
is
s
tu
d
y
.
T
ex
t
s
tem
m
in
g
alter
s
wo
r
d
s
to
p
r
o
d
u
ce
alter
n
ativ
e
wo
r
d
f
o
r
m
s
u
s
in
g
a
v
ar
iety
o
f
lin
g
u
is
tic
o
p
er
atio
n
s
,
in
clu
d
in
g
af
f
ix
atio
n
.
Fo
r
e
x
am
p
le,
"stu
d
y
"
is
th
e
r
o
o
t o
f
t
h
e
wo
r
d
"stu
d
y
in
g
”.
2
.
3
.
At
t
a
c
k
det
ec
t
io
n us
ing
G
DCC
-
ED
E
n
co
d
er
-
d
ec
o
d
er
a
r
ch
itectu
r
e
is
u
s
ed
in
o
u
r
s
u
g
g
ested
GDCC
-
E
D
m
o
d
el,
as
s
ee
n
in
Fig
u
r
e
2
.
T
w
o
p
r
im
ar
y
c
o
m
p
o
n
en
ts
m
ak
e
u
p
GDCC
-
ED
:
i
)
a
n
en
co
d
er
t
h
at
u
s
es
a
GDCC
d
esig
n
ed
to
m
o
d
el
l
o
n
g
-
r
an
g
e
tem
p
o
r
al
d
e
p
en
d
e
n
cies
an
d
ii
)
a
d
ec
o
d
er
f
o
r
m
u
lti
-
p
h
ase
n
et
wo
r
k
tr
af
f
ic
p
r
e
d
ictio
n
.
T
h
e
p
r
o
p
o
s
ed
f
r
am
ewo
r
k
co
m
b
in
es c
h
ar
ac
ter
is
tics
s
u
ch
as we
b
-
b
ased
attac
k
s
an
d
n
etwo
r
k
h
a
r
m
in
a
d
d
itio
n
t
o
th
e
en
co
d
er
'
s
o
u
tp
u
t.
2
.
3
.
1
.
E
nco
der
f
o
r
mo
dellin
g
a
t
t
a
c
k
s
T
h
r
ee
ch
ar
ac
ter
is
tics
d
is
tin
g
u
is
h
th
e
s
u
g
g
ested
en
co
d
er
f
r
o
m
th
e
s
tan
d
ar
d
C
NN
o
r
R
NN
.
I
t
m
ak
es
u
s
e
o
f
th
r
ee
d
if
f
er
en
t
tech
n
iq
u
es,
wh
ich
ar
e
ex
p
lain
ed
in
th
e
s
ec
tio
n
s
th
at
f
o
llo
w:
i
)
d
ilated
ca
u
s
al
co
n
v
o
l
u
tio
n
s
,
ii
)
g
ated
ac
tiv
a
tio
n
s
,
an
d
iii
)
r
esid
u
al
c
o
n
n
e
ctio
n
s
.
T
h
ese
tech
n
i
q
u
es
h
elp
im
p
r
o
v
e
lear
n
i
n
g
,
ca
p
tu
r
e
lo
n
g
-
ter
m
p
atter
n
s
,
an
d
m
ain
tain
tr
ain
i
n
g
s
tab
ilit
y
.
-
C
au
s
al
co
n
v
o
lu
tio
n
R
aw
au
d
io
wav
es
ar
e
g
en
e
r
ated
b
y
th
e
d
ee
p
g
en
er
ativ
e
m
o
d
el
W
av
eNe
t.
I
t
is
wh
e
r
e
ca
u
s
al
co
n
v
o
l
u
tio
n
f
ir
s
t
ap
p
ea
r
ed
.
H
o
wev
er
,
w
eb
-
b
ased
attac
k
s
r
e
p
r
esen
t
s
er
io
u
s
r
is
k
s
to
I
n
d
u
s
t
r
y
5
.
0
in
f
r
astru
ctu
r
e
wh
en
we
u
s
e
th
em
,
p
o
s
s
ib
ly
r
esu
ltin
g
in
th
e
lo
s
s
o
f
co
n
f
i
d
en
tial
d
ata.
I
n
o
r
d
er
t
o
r
elia
b
ly
d
etec
t
n
etwo
r
k
h
ar
m
s
as
s
o
o
n
as
th
e
y
ar
e
p
o
s
s
ib
le,
it
is
n
ec
ess
ar
y
to
au
to
m
atica
lly
ex
tr
ac
t
f
ea
tu
r
es
u
s
in
g
co
n
v
en
tio
n
al
ap
p
r
o
ac
h
es.
-
Dilated
c
o
n
v
o
lu
tio
n
s
T
h
e
attac
k
s
u
r
f
a
ce
is
in
cr
ea
s
ed
wh
en
I
o
T
d
ev
ices,
b
ig
d
a
ta,
an
d
clo
u
d
c
o
m
p
u
tin
g
a
r
e
co
m
b
in
ed
,
m
ak
in
g
th
ese
s
y
s
tem
s
m
o
r
e
at
r
is
k
f
o
r
cy
b
er
attac
k
s
.
A
n
etwo
r
k
f
lo
w
h
ap
p
e
n
s
wh
en
two
en
d
p
o
in
ts
,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ap
p
l Po
wer
E
n
g
I
SS
N:
2252
-
8
7
9
2
Ga
ted
d
ila
ted
c
a
u
s
a
l c
o
n
v
o
lu
t
io
n
-
b
a
s
ed
e
n
co
d
er
-
d
ec
o
d
er n
e
tw
o
r
k
fo
r
I
o
T
…
(
A
a
r
th
i G
o
p
a
la
kris
h
n
a
n
)
725
s
u
ch
as
a
clien
t
an
d
a
web
s
er
v
er
,
ex
ch
a
n
g
e
p
ac
k
ets
b
ac
k
a
n
d
f
o
r
th
o
v
er
a
s
et
p
er
io
d
o
f
t
im
e.
I
n
o
u
r
wo
r
k
,
a
s
y
s
tem
f
lo
w
is
d
e
f
in
ed
as
a
s
er
ies
o
f
L
o
r
d
er
e
d
c
o
llectio
n
s
,
wh
er
e
L
is
th
e
t
o
tal
len
g
t
h
o
f
a
f
lo
w.
A
f
lo
w
is
d
en
o
ted
as
(
1
)
.
=
{
1
,
2
,
……
}
∀
∈
ℝ
∧
1
≤
≤
L
(
1
)
W
h
er
e
w
is
th
e
len
g
th
o
f
a
p
a
c
k
et.
Descr
ib
es
th
e
d
is
tan
ce
b
etwe
en
v
ar
iab
les
in
a
ce
r
ea
l,
t
h
e
ab
s
o
r
p
tio
n
v
alu
e
is
th
e
m
o
s
t
r
ec
e
n
t
p
a
r
am
eter
t
o
b
e
p
r
o
d
u
ce
d
b
y
e
x
ten
d
ed
tr
a
n
s
f
o
r
m
atio
n
s
.
T
h
e
d
ilated
ca
u
s
al
co
n
v
o
lu
tio
n
[
2
0
]
is
d
ep
icted
in
Fig
u
r
e
3
.
Fig
u
r
e
2
.
T
h
e
ar
ch
itectu
r
e
d
ia
g
r
am
o
f
th
e
g
ate
d
d
ilated
ca
s
u
al
co
n
v
o
l
u
tio
n
b
ased
e
n
co
d
e
r
-
d
ec
o
d
er
m
o
d
el’
s
wh
ich
class
if
ies th
e
d
ata
in
to
attac
k
o
r
n
o
n
-
attac
k
Fig
u
r
e
3
.
T
h
e
b
lo
c
k
d
iag
r
am
o
f
th
e
d
ilated
ca
u
s
al
co
n
v
o
l
u
tio
n
with
th
r
ee
h
i
d
d
en
la
y
er
s
s
h
o
win
g
th
e
f
lo
w
o
f
in
f
o
r
m
atio
n
f
r
o
m
in
p
u
t to
o
u
tp
u
t
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
9
2
I
n
t J Ap
p
l Po
wer
E
n
g
,
Vo
l.
14
,
No
.
3
,
Sep
tem
b
er
20
25
:
7
2
2
-
73
2
726
T
h
e
f
o
llo
win
g
is
th
e
f
o
r
m
al
d
ef
in
itio
n
o
f
th
e
e
x
ten
d
e
d
t
r
an
s
f
o
r
m
atio
n
b
etwe
en
th
e
f
o
r
etell
an
d
ce
r
ea
l
.
T
h
is
r
elatio
n
s
h
ip
is
m
a
th
em
atica
lly
ex
p
r
ess
ed
in
(
2
)
.
(
)
=
(
∗
)
=
∑
−
1
=
0
∙
−
(
2
)
W
h
er
e
is
th
e
a
b
s
o
r
p
tio
n
v
al
u
e
an
d
s
is
th
e
f
ilter
s
ize.
Mo
r
e
p
ar
ticu
lar
ly
,
at
=
1
,
e
x
ten
d
ed
tr
an
s
f
o
r
m
atio
n
s
im
p
lifie
s
to
a
ty
p
ical
co
n
v
o
lu
tio
n
.
-
Gate
d
ac
tiv
atio
n
Sig
m
o
id
f
u
n
ctio
n
s
ar
e
f
r
eq
u
e
n
tly
em
p
lo
y
ed
as
in
itiatio
n
f
u
n
ctio
n
s
,
b
u
t
in
th
is
ca
s
e,
it
ac
ts
as
th
e
g
atin
g
f
u
n
ctio
n
r
ath
er
th
an
th
e
in
itiatio
n
f
u
n
ctio
n
.
W
e
h
av
e
s
elec
ted
th
e
s
ig
m
o
id
f
u
n
ctio
n
as
an
atten
u
atio
n
f
ac
to
r
f
o
r
th
e
in
itiatio
n
o
f
t
h
e
ex
ten
d
ed
tr
an
s
f
o
r
m
atio
n
s
in
ce
its
v
alu
e
r
an
g
e
is
b
etwe
en
0
an
d
1
.
T
h
e
ad
v
an
tag
e
is
b
ein
g
ab
le
to
m
o
r
e
p
r
ec
is
ely
r
eg
u
late
th
e
f
lo
w
o
f
k
n
o
wled
g
e
v
ia
ea
ch
b
u
r
ied
lay
er
.
W
h
en
tak
e
n
as a
wh
o
le,
th
ese
r
o
les ar
e
ca
lled
g
ated
ac
tiv
atio
n
.
Hen
ce
,
two
co
m
p
o
n
en
ts
m
ak
e
u
p
th
e
lea
r
n
ab
le
co
n
v
o
lu
tio
n
f
ilter
:
ar
e
d
iv
id
e
d
in
to
f
o
r
g
at
e
an
d
ℎ
f
o
r
f
ilt
er
.
-
R
esid
u
al
co
n
n
ec
tio
n
T
h
e
in
p
u
t
a
n
d
o
u
tp
u
t
o
f
two
l
ay
er
s
ar
e
co
n
n
ec
ted
v
ia
r
esid
u
al
co
n
n
ec
tio
n
s
.
Gate
d
a
ctiv
at
io
n
[
2
0
]
is
s
h
o
wn
in
Fig
u
r
e
4
.
T
h
e
r
esid
u
al
f
u
n
ctio
n
m
ak
es
u
s
e
of
th
e
d
is
tin
ctio
n
b
etwe
en
a
v
is
u
aliza
t
io
n
th
at
is
ap
p
lied
to
(
3
)
.
(
)
=
(
)
−
(
3
)
T
h
e
o
r
i
g
in
al
v
is
u
alizin
g
F(c
)
i
s
m
o
r
e
d
if
f
icu
lt
to
i
m
p
r
o
v
e
th
an
th
e
r
esid
u
al
f
u
n
ctio
n
H(
c
)
.
As
a
co
n
s
eq
u
en
ce
,
th
e
o
r
ig
in
al
p
u
r
p
o
s
e
b
ec
o
m
es
(
4
)
.
=
(
+
(
)
)
(
4
)
W
h
er
e
th
e
ac
tiv
atio
n
f
u
n
ctio
n
is
r
ep
r
esen
ted
b
y
σ
.
T
h
e
ad
d
itio
n
o
f
r
em
ain
in
g
co
n
n
e
ctio
n
s
f
o
llo
ws
ea
ch
GDC
C
-
E
D
f
r
o
m
in
p
u
t to
co
n
v
o
lu
tio
n
to
o
u
tp
u
t
.
-
Dec
o
d
er
f
o
r
m
u
lti
-
s
tep
tr
af
f
ic
f
o
r
ec
ast
T
h
e
d
ec
o
d
e
r
g
en
e
r
ates
th
e
n
ex
t
s
tate
b
y
f
o
llo
win
g
a
s
er
i
es
o
f
s
eq
u
en
tial
s
tep
s
.
I
t
p
r
o
ce
s
s
es
th
e
cu
r
r
en
t
in
p
u
t
alo
n
g
with
th
e
p
r
ev
io
u
s
s
tate
to
p
r
e
d
ict
th
e
n
e
x
t
o
u
t
p
u
t.
T
h
is
o
u
t
p
u
t
is
t
h
en
u
s
ed
to
u
p
d
ate
th
e
s
tate
f
o
r
th
e
f
o
llo
win
g
tim
e
s
tep
.
Γ
<
>
=
(
[
<
−
1
>
,
<
>
]
+
)
(
5
)
Γ
<
>
=
(
[
<
−
1
>
,
<
>
]
+
)
(
6
)
~
<
>
=
ta
n
h
(
[
<
−
1
>
,
<
>
]
+
)
(
7
)
W
h
er
e
Γ
<
>
,
Γ
<
>
,
an
d
~
<
>
in
d
icate
th
e
o
u
tp
u
t
g
ate,
h
id
d
en
s
tate,
an
d
ca
n
d
id
ate
f
o
r
ce
ll
s
tate,
in
th
at
o
r
d
er
.
T
h
e
s
ig
m
o
id
f
u
n
ctio
n
i
s
r
ep
r
esen
ted
b
y
σ
,
th
e
h
y
p
er
b
o
lic
tan
g
en
t
f
u
n
ctio
n
b
y
tan
h
,
an
d
d
iv
is
io
n
-
s
ag
e
co
m
b
in
in
g
b
y
.
T
h
e
(
5
)
d
ef
in
e
s
th
e
s
ize
th
at
co
n
tr
o
l th
e
n
eg
l
ec
t g
ate'
s
b
eh
av
io
r
.
Fig
u
r
e
4
.
T
h
e
g
ated
ac
tiv
atio
n
m
ec
h
an
is
m
with
d
ilated
ca
u
s
a
l c
o
n
v
o
l
u
tio
n
,
c
o
m
b
in
in
g
tan
h
an
d
s
ig
m
o
id
ac
tiv
atio
n
s
f
o
r
g
atin
g
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ap
p
l Po
wer
E
n
g
I
SS
N:
2252
-
8
7
9
2
Ga
ted
d
ila
ted
c
a
u
s
a
l c
o
n
v
o
lu
t
io
n
-
b
a
s
ed
e
n
co
d
er
-
d
ec
o
d
er n
e
tw
o
r
k
fo
r
I
o
T
…
(
A
a
r
th
i G
o
p
a
la
kris
h
n
a
n
)
727
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
e
p
r
o
p
o
s
ed
DE
B
I
T
m
eth
o
d
an
d
e
x
p
er
im
e
n
tal
r
esu
lts
ar
e
an
aly
ze
d
,
a
n
d
a
d
is
cu
s
s
io
n
o
f
ef
f
icien
cy
is
p
r
esen
ted
.
Usi
n
g
MA
T
L
AB
s
tim
u
latio
n
an
d
a
W
in
d
o
ws
OS
with
an
I
n
tel
C
o
r
e
i7
C
P
U
an
d
1
6
GB
R
AM
,
th
e
DE
B
I
T
f
r
a
m
ewo
r
k
is
co
n
s
tr
u
cted
an
d
ev
alu
ate
d
.
T
h
e
B
o
t
-
I
o
T
d
ataset
is
u
tili
ze
d
t
o
e
x
am
in
e
th
e
ef
f
icac
y
o
f
th
e
s
u
g
g
est
ed
s
y
s
tem
.
T
h
e
B
o
t
-
I
o
T
d
ataset
ca
n
b
e
au
g
m
e
n
ted
wh
ich
im
p
r
o
v
es
th
e
d
iv
e
r
s
ity
an
d
r
o
b
u
s
tn
ess
o
f
th
e
d
ataset,
th
er
eb
y
e
n
h
an
cin
g
th
e
e
f
f
ec
tiv
en
ess
o
f
th
e
s
u
g
g
ested
DE
B
I
T
f
r
am
ewo
r
k
f
o
r
I
o
T
in
tr
u
s
io
n
d
etec
tio
n
.
T
h
e
e
f
f
icac
y
o
f
th
e
s
u
g
g
ested
f
r
am
ewo
r
k
is
ev
alu
ated
to
th
e
f
o
llo
win
g
p
a
r
am
et
er
s
:
F1
-
s
co
r
e,
R
OC
cu
r
v
e,
ac
c
u
r
ac
y
,
r
ec
all,
an
d
p
r
ec
is
io
n
.
3
.
1
.
P
er
f
o
r
m
a
nce
ev
a
lua
t
io
n
I
n
Fig
u
r
e
5
,
test
in
g
an
d
tr
ain
in
g
ar
e
c
o
n
d
u
cted
.
T
h
is
is
to
av
o
id
m
ak
i
n
g
m
a
n
y
attr
i
b
u
te
ca
l
ls
b
ec
au
s
e
th
ese
p
r
o
ce
s
s
es
ar
e
alr
ea
d
y
in
ter
d
ep
en
d
e
n
t.
T
h
e
f
ac
t
th
at
th
e
tr
ain
in
g
an
d
test
in
g
ac
cu
r
ac
y
r
o
s
e
s
u
g
g
ests
th
at
th
e
co
n
v
o
l
u
tio
n
al
n
eu
r
al
n
etw
o
r
k
'
s
p
ar
am
eter
s
wer
e
tr
u
ly
b
ein
g
ap
p
r
o
p
r
iately
tu
n
e
d
.
T
h
e
t
esti
n
g
ac
cu
r
ac
y
was
ap
p
r
o
x
im
ately
0
at
th
e
b
eg
in
n
in
g
an
d
in
cr
ea
s
ed
to
1
b
y
th
e
th
ir
teen
th
ep
o
c
h
.
T
e
s
t
i
n
g
l
o
s
s
p
e
r
b
at
c
h
is
s
t
i
ll
d
e
c
l
i
n
i
n
g
a
t
t
h
e
c
o
n
c
l
u
s
i
o
n
o
f
th
e
e
l
e
v
e
n
t
h
e
p
o
c
h
,
w
h
i
c
h
is
c
o
n
s
i
s
t
e
n
t
wi
t
h
t
h
e
c
o
n
d
i
ti
o
n
s
h
o
w
n
b
y
t
h
e
l
o
s
s
p
l
o
t
s
.
Fo
r
attac
k
an
d
n
o
n
-
attac
k
s
ce
n
ar
io
s
,
Fig
u
r
e
6
d
is
p
lay
s
th
e
F1
s
co
r
es,
r
ec
all,
ac
cu
r
ac
y
,
an
d
p
r
ec
is
io
n
.
Her
e
we
f
in
d
th
e
p
er
f
o
r
m
a
n
ce
r
atio
,
an
d
th
e
n
o
n
-
attac
k
9
5
.
8
%
an
d
attac
k
9
7
.
8
%
will
o
cc
u
r
.
T
h
e
attac
k
is
in
th
e
h
ig
h
er
ac
c
u
r
ac
y
o
f
th
e
g
r
a
p
h
.
T
h
e
p
er
f
o
r
m
an
ce
r
atio
f
o
r
ac
cu
r
ac
y
is
9
8
%.
Pack
et
r
ates
f
o
r
v
ar
i
o
u
s
attac
k
s
o
v
er
s
p
ec
if
ic
tim
e
in
ter
v
als.
Fig
u
r
e
7
illu
s
tr
ates
h
o
w
t
o
u
s
e
th
e
b
lack
cu
r
v
es
to
clea
r
l
y
v
is
u
alize
th
e
n
etwo
r
k
tr
af
f
ic
p
atter
n
s
,
wh
ich
v
ar
y
d
ep
en
d
i
n
g
o
n
t
h
e
p
ac
k
et
ty
p
e.
Netwo
r
k
-
an
d
web
-
b
ased
attac
k
s
s
tan
d
o
u
t
in
p
ar
ticu
lar
d
u
e
to
th
e
v
o
lu
m
e
o
f
p
ac
k
ets
th
e
y
s
en
d
an
d
ca
u
s
e.
Fig
u
r
e
8
d
is
p
lay
s
th
e
R
OC
cu
r
v
e
o
b
tain
ed
f
r
o
m
th
e
s
u
g
g
ested
I
DS
ass
e
s
s
ed
wi
th
th
e
B
o
T
-
I
o
T
d
ataset.
I
n
th
is
ca
s
e,
th
e
y
-
ax
is
r
ep
r
esen
ts
th
e
tr
u
e
p
o
s
itiv
e
r
ate,
an
d
th
e
x
-
ax
is
illu
s
tr
ates th
e
f
alse p
o
s
itiv
e
r
ate.
T
wo
class
es
ar
e
r
ep
r
esen
ted
b
y
t
h
e
R
OC
cu
r
v
e.
(
a)
(
b
)
Fig
u
r
e
5
.
T
h
e
test
in
g
an
d
tr
ain
in
g
u
s
in
g
th
e
B
o
t
-
I
o
T
d
ataset
:
(
a)
th
e
ac
cu
r
ac
y
an
d
(
b
)
th
e
lo
s
s
g
r
ap
h
Fig
u
r
e
6
.
T
h
e
ef
f
icien
c
y
r
atio
o
f
th
e
s
u
g
g
ested
DE
B
I
T
ap
p
r
o
ac
h
f
o
r
attac
k
an
d
n
o
n
-
attac
k
s
ce
n
ar
io
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
9
2
I
n
t J Ap
p
l Po
wer
E
n
g
,
Vo
l.
14
,
No
.
3
,
Sep
tem
b
er
20
25
:
7
2
2
-
73
2
728
Fig
u
r
e
7
.
T
h
e
q
u
an
titativ
e
p
att
er
n
o
f
n
etwo
r
k
p
ac
k
et
attac
k
s
f
o
r
v
a
r
io
u
s
attac
k
s
o
v
e
r
s
p
ec
if
ic
tim
e
in
ter
v
als
Fig
u
r
e
8
.
T
h
e
R
OC
cu
r
v
e
o
b
ta
in
ed
f
r
o
m
th
e
s
u
g
g
ested
I
DS a
s
s
es
s
ed
with
th
e
B
o
T
-
I
o
T
d
ata
s
et
3
.
2
.
Co
m
pa
riso
n a
na
ly
s
is
T
h
e
tr
ad
e
-
o
f
f
b
etwe
en
ADR a
n
d
FAR
i
s
r
ep
r
esen
ted
b
y
a
d
e
tectio
n
r
ate
g
r
ap
h
,
d
is
p
lay
e
d
in
Fig
u
r
e
9
.
W
ith
th
e
s
am
e
d
ataset,
th
e
d
et
ec
tio
n
r
ate
m
ay
also
b
e
u
s
ed
t
o
co
m
p
ar
e
m
u
ltip
le
I
DSs
.
I
DS
p
er
f
o
r
m
a
n
ce
o
v
er
tim
e
ca
n
also
b
e
ev
alu
ate
d
.
T
h
e
tim
e
p
er
f
o
r
m
an
c
e
is
th
e
o
v
er
all
tim
e
r
eq
u
ir
ed
b
y
th
e
I
DS
to
id
en
tify
a
n
in
tr
u
s
io
n
.
T
h
e
p
r
o
p
ag
atio
n
tim
e
an
d
th
e
p
r
o
ce
s
s
in
g
tim
e
c
o
m
p
o
s
e
th
is
am
o
u
n
t
o
f
tim
e.
I
n
o
r
d
er
to
p
r
o
ce
s
s
in
tr
u
s
io
n
s
in
r
ea
l tim
e,
th
e
in
tr
u
s
io
n
d
etec
tio
n
s
y
s
tem
'
s
p
r
o
ce
s
s
in
g
s
p
ee
d
n
ee
d
s
to
b
e
as f
ast
as p
o
s
s
ib
le.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ap
p
l Po
wer
E
n
g
I
SS
N:
2252
-
8
7
9
2
Ga
ted
d
ila
ted
c
a
u
s
a
l c
o
n
v
o
lu
t
io
n
-
b
a
s
ed
e
n
co
d
er
-
d
ec
o
d
er n
e
tw
o
r
k
fo
r
I
o
T
…
(
A
a
r
th
i G
o
p
a
la
kris
h
n
a
n
)
729
I
n
Fig
u
r
e
1
0
,
PC
g
r
a
p
h
'
s
x
-
a
x
is
s
h
o
ws
r
ec
all,
F1
s
co
r
es,
a
cc
u
r
ac
y
,
an
d
p
r
ec
is
io
n
,
wh
ile
th
e
y
-
ax
is
r
ef
lects
PIO
,
R
e
s
-
T
r
an
B
iLST
M,
B
b
AB
,
an
d
DE
B
I
T
.
T
h
e
r
esu
lts
s
h
o
w
th
at
f
o
r
F1
-
s
co
r
e
m
ea
s
u
r
em
en
t,
th
e
PIO
r
ea
ch
ed
8
2
.
6
%,
th
e
R
es
-
T
r
an
B
iLST
M
r
ea
ch
ed
8
0
.
4
%,
th
e
B
b
AB
r
ea
ch
ed
7
1
.
6
%,
an
d
th
e
DE
B
I
T
r
ea
ch
ed
8
8
.
4
%.
Fo
r
ac
cu
r
ac
y
,
th
e
p
er
f
o
r
m
an
ce
with
a
s
co
r
e
o
f
PIO
r
ea
ch
ed
8
5
.
4
%,
th
e
R
es
-
T
r
an
B
iLST
M
r
ea
ch
ed
9
2
.
5
%,
th
e
B
b
AB
r
e
ac
h
ed
8
5
%,
an
d
th
e
DE
B
I
T
r
ea
ch
ed
9
9
.
5
%.
B
ased
o
n
th
es
e
r
esu
lts
,
th
e
d
ee
p
lear
n
in
g
tec
h
n
iq
u
es
a
r
e
all
ca
lcu
lated
b
ased
o
n
p
er
f
o
r
m
an
c
e
co
m
p
ar
is
o
n
s
.
T
ab
le
1
d
e
p
ic
ts
th
e
tr
en
d
s
o
f
th
e
r
u
n
tim
e
o
f
th
e
s
u
g
g
ested
with
ex
is
tin
g
ar
ch
itectu
r
es
in
d
if
f
er
en
t
ep
o
ch
s
.
Acc
o
r
d
in
g
to
th
is
tab
le,
th
e
p
r
o
p
o
s
ed
ar
ch
itectu
r
e
h
as a
ch
ie
v
ed
th
e
s
h
o
r
test
r
u
n
tim
e.
Fig
u
r
e
1
1
s
h
o
ws
th
e
s
ca
lab
ilit
y
ef
f
icac
y
is
co
m
p
ar
ed
wi
th
th
e
o
th
er
ex
is
tin
g
ap
p
r
o
a
ch
es.
T
h
is
s
u
g
g
ests
th
at
th
e
DE
B
I
T
ap
p
r
o
ac
h
ef
f
icien
tly
h
an
d
les
in
cr
e
asin
g
am
o
u
n
ts
o
f
d
ata
with
o
u
t
a
s
ig
n
if
ican
t
d
r
o
p
in
p
er
f
o
r
m
an
ce
,
wh
ich
is
a
k
ey
ad
v
an
tag
e
wh
e
n
d
ea
lin
g
with
lar
g
er
d
atasets
.
T
h
e
co
n
s
is
ten
t
p
er
f
o
r
m
an
ce
ac
r
o
s
s
all
tr
an
s
ac
tio
n
s
izes
s
h
o
ws
th
at
th
e
DE
B
I
T
m
o
d
el
is
r
eliab
le
an
d
r
o
b
u
s
t
f
o
r
h
a
n
d
lin
g
v
ar
y
i
n
g
d
ata
lo
ad
s
,
u
n
lik
e
th
e
o
th
er
m
o
d
els,
wh
ich
s
h
o
w
f
lu
ctu
ati
o
n
s
an
d
i
n
s
tab
ilit
y
in
s
ca
lab
ilit
y
.
T
h
e
p
r
o
p
o
s
ed
m
et
h
o
d
is
d
esi
g
n
ed
f
o
r
p
r
ac
tical
im
p
lem
en
t
atio
n
in
clin
ical
s
ettin
g
s
to
e
n
h
an
ce
th
e
ac
cu
r
ac
y
o
f
m
ed
ical
d
iag
n
o
s
es
th
r
o
u
g
h
a
u
to
m
ated
im
a
g
e
a
n
d
d
ata
class
if
icatio
n
.
B
y
in
teg
r
atin
g
th
is
s
y
s
tem
in
to
h
ea
lth
ca
r
e
f
ac
ilit
ies,
m
ed
ical
p
r
o
f
ess
io
n
als
ca
n
le
v
er
ag
e
ad
v
an
ce
d
m
ac
h
in
e
lear
n
in
g
m
o
d
els
to
q
u
ick
l
y
an
d
ef
f
ec
tiv
ely
an
aly
ze
p
atien
t
d
ata,
lead
in
g
to
ea
r
ly
d
etec
tio
n
o
f
d
is
ea
s
es
s
u
ch
as
ca
n
ce
r
o
r
ca
r
d
io
v
ascu
lar
d
is
o
r
d
er
s
.
T
h
e
r
ea
l
-
tim
e
ca
p
a
b
ilit
ies
o
f
th
e
m
o
d
el
allo
w
f
o
r
m
o
r
e
im
m
ed
iate
d
ia
g
n
o
s
ti
c
in
s
ig
h
ts
,
r
ed
u
cin
g
p
atien
t
waitin
g
tim
es
an
d
im
p
r
o
v
in
g
th
e
q
u
ality
o
f
ca
r
e.
Ad
d
itio
n
ally
,
th
is
m
eth
o
d
co
u
ld
b
e
ap
p
lied
in
r
em
o
te
an
d
u
n
d
er
-
r
eso
u
r
ce
d
ar
ea
s
,
p
r
o
v
id
in
g
ac
ce
s
s
to
h
ig
h
-
lev
el
d
iag
n
o
s
tic
to
o
ls
in
r
eg
io
n
s
wh
er
e
s
p
ec
ialized
ex
p
er
tis
e
is
s
ca
r
ce
.
U
l
ti
m
a
t
e
ly
,
t
h
e
p
r
o
p
o
s
e
d
s
y
s
t
e
m
n
o
t
o
n
l
y
a
u
g
m
e
n
t
s
t
h
e
d
e
ci
s
i
o
n
-
m
a
k
i
n
g
p
r
o
c
e
s
s
f
o
r
c
l
i
n
i
c
ia
n
s
b
u
t
a
ls
o
c
o
n
t
r
i
b
u
t
es
to
b
e
t
t
e
r
p
a
t
i
e
n
t
o
u
tc
o
m
e
s
t
h
r
o
u
g
h
m
o
r
e
p
e
r
s
o
n
a
l
i
z
e
d
a
n
d
p
r
e
c
is
e
t
r
e
at
m
e
n
t
p
l
a
n
s
.
Fig
u
r
e
9
.
T
h
e
attac
k
d
etec
tio
n
r
ate
co
m
p
ar
is
o
n
o
f
s
u
g
g
ested
m
eth
o
d
with
e
x
is
tin
g
ap
p
r
o
ac
h
es
Fig
u
r
e
1
0
.
T
h
e
ef
f
icien
cy
c
o
m
p
ar
is
o
n
o
f
p
r
o
p
o
s
ed
f
r
am
ewo
r
k
with
ex
is
tin
g
f
r
am
ew
o
r
k
s
th
at
co
m
p
r
is
es
f1
-
s
co
r
e,
r
ec
all,
p
r
ec
is
io
n
,
a
n
d
ac
cu
r
ac
y
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
9
2
I
n
t J Ap
p
l Po
wer
E
n
g
,
Vo
l.
14
,
No
.
3
,
Sep
tem
b
er
20
25
:
7
2
2
-
73
2
730
T
ab
le
1
.
T
h
e
r
u
n
tim
e
with
d
if
f
er
en
t e
p
o
c
h
s
co
m
p
ar
is
o
n
o
f
s
u
g
g
ested
m
o
d
el
with
o
th
er
e
x
is
tin
g
m
o
d
els
Te
c
h
n
i
q
u
e
s
Ep
o
c
h
30
60
90
1
2
0
1
5
0
P
I
O
[
1
5
]
1
1
0
1
8
5
2
3
9
3
1
0
3
8
9
Res
-
Tr
a
n
B
i
LST
M
[
1
7
]
1
0
1
1
7
5
2
4
6
3
6
1
4
2
9
B
b
A
B
[
1
8
]
91
1
6
9
2
2
4
2
9
6
3
5
1
D
EB
I
T
[
p
r
o
p
o
s
e
d
]
74
1
4
5
1
9
6
2
7
5
3
2
1
Fig
u
r
e
1
1
.
T
h
e
s
ca
lab
ilit
y
co
m
p
ar
is
o
n
o
f
s
u
g
g
ested
m
eth
o
d
with
o
th
er
ex
is
tin
g
m
et
h
o
d
s
4.
CO
NCLU
SI
O
N
I
n
th
is
p
a
p
er
,
a
DE
B
I
T
h
a
s
b
ee
n
p
r
o
p
o
s
ed
wh
ich
d
et
ec
ts
th
e
in
tr
u
s
io
n
u
s
in
g
d
ee
p
lear
n
in
g
tech
n
iq
u
es
ef
f
icien
tly
.
T
h
e
s
u
g
g
ested
m
eth
o
d
'
s
ef
f
icien
cy
h
as
b
ee
n
ev
alu
ated
b
y
a
co
m
m
o
n
B
o
t
-
I
o
T
in
tr
u
s
io
n
d
etec
tio
n
d
ataset.
T
h
e
s
u
g
g
ested
DE
B
I
T
f
r
am
ewo
r
k
h
as
b
e
en
ass
es
s
ed
u
s
in
g
MA
T
L
AB
s
im
u
lato
r
.
Me
tr
ics
s
u
ch
as
r
ec
all,
p
r
ec
is
io
n
,
F
m
ea
s
u
r
e,
ac
cu
r
ac
y
,
a
n
d
d
etec
tio
n
r
ate
h
av
e
b
ee
n
u
tili
ze
d
to
ev
alu
ate
th
e
ef
f
icac
y
o
f
th
e
s
u
g
g
ested
DE
B
I
T
ap
p
r
o
ac
h
.
Acc
o
r
d
in
g
to
e
x
p
er
im
en
tal
d
ata,
th
e
p
r
o
p
o
s
ed
m
et
h
o
d
h
as
a
g
r
ea
ter
ac
cu
r
ac
y
o
f
9
9
.
5
%
co
m
p
ar
e
d
to
th
e
8
5
.
4
%,
9
2
.
5
%,
an
d
8
5
%
ac
cu
r
ac
y
o
f
ex
is
tin
g
tech
n
i
q
u
es
lik
e
PIO
,
R
es
-
T
r
an
B
iLST
M,
an
d
B
b
AB
.
T
o
p
r
ed
ict
th
e
p
ac
k
et
i
n
to
attac
k
an
d
n
o
n
-
attac
k
.
Fu
tu
r
e
p
lan
s
ca
ll
f
o
r
ex
a
m
in
in
g
v
ar
io
u
s
I
o
T
d
ev
ices,
in
v
esti
g
atin
g
n
ew
tech
n
o
lo
g
ies,
an
d
co
n
d
u
ctin
g
test
s
u
s
in
g
v
ar
io
u
s
I
o
T
d
ev
ice
d
ata
th
at
h
as b
ee
n
co
m
p
r
o
m
is
ed
b
y
th
e
h
ac
k
.
ACK
NO
WL
E
DG
M
E
N
T
S
T
h
e
au
th
o
r
w
o
u
ld
lik
e
to
ex
p
r
ess
h
is
h
ea
r
tf
elt
g
r
atitu
d
e
to
th
e
s
u
p
er
v
is
o
r
f
o
r
h
is
g
u
i
d
an
ce
an
d
u
n
wav
er
in
g
s
u
p
p
o
r
t d
u
r
in
g
t
h
is
r
esear
ch
f
o
r
h
is
g
u
id
an
ce
an
d
s
u
p
p
o
r
t.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
Au
th
o
r
s
s
tate
n
o
f
u
n
d
in
g
in
v
o
lv
ed
.
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
T
h
is
jo
u
r
n
al
u
s
es
th
e
C
o
n
t
r
ib
u
to
r
R
o
les
T
a
x
o
n
o
m
y
(
C
R
ed
iT)
to
r
ec
o
g
n
ize
in
d
iv
i
d
u
al
au
th
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
th
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
llab
o
r
atio
n
.
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
Aar
th
i G
o
p
alak
r
is
h
n
a
n
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Sh
ar
o
n
Priy
a
Su
r
en
d
r
a
n
✓
✓
✓
✓
✓
✓
✓
✓
✓
Ais
h
a
B
an
u
W
ah
ab
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ap
p
l Po
wer
E
n
g
I
SS
N:
2252
-
8
7
9
2
Ga
ted
d
ila
ted
c
a
u
s
a
l c
o
n
v
o
lu
t
io
n
-
b
a
s
ed
e
n
co
d
er
-
d
ec
o
d
er n
e
tw
o
r
k
fo
r
I
o
T
…
(
A
a
r
th
i G
o
p
a
la
kris
h
n
a
n
)
731
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
T
h
e
au
th
o
r
s
d
ec
lar
e
th
at
th
ey
h
av
e
n
o
k
n
o
w
n
co
m
p
etin
g
f
in
an
cial
in
ter
ests
o
r
p
er
s
o
n
al
r
el
atio
n
s
h
ip
s
th
at
co
u
ld
h
av
e
ap
p
ea
r
ed
t
o
in
f
lu
en
ce
th
e
wo
r
k
r
e
p
o
r
te
d
in
t
h
is
p
ap
er
.
I
NF
O
RM
E
D
CO
NS
E
N
T
W
e
ce
r
tify
th
at
we
h
av
e
ex
p
lain
ed
th
e
n
atu
r
e
an
d
p
u
r
p
o
s
e
o
f
th
is
s
tu
d
y
to
th
e
ab
o
v
e
-
n
am
e
d
in
d
iv
id
u
al,
an
d
we
h
av
e
d
is
cu
s
s
ed
th
e
p
o
ten
tial
b
en
ef
its
o
f
th
is
s
tu
d
y
p
a
r
ticip
atio
n
.
T
h
e
q
u
esti
o
n
s
th
e
in
d
iv
id
u
al
h
ad
a
b
o
u
t
th
is
s
tu
d
y
h
av
e
b
ee
n
an
s
wer
ed
,
an
d
we
will
a
lway
s
b
e
av
ailab
l
e
to
ad
d
r
ess
f
u
tu
r
e
q
u
esti
o
n
s
.
E
T
H
I
CAL AP
P
RO
V
AL
T
h
e
r
e
s
e
a
r
c
h
g
u
i
d
e
h
as
r
e
v
i
e
we
d
a
n
d
e
t
h
i
c
a
l
l
y
a
p
p
r
o
v
e
d
t
h
is
m
a
n
u
s
c
r
i
p
t
f
o
r
p
u
b
l
i
c
a
ti
o
n
i
n
th
i
s
j
o
u
r
n
a
l
.
DATA AV
AI
L
AB
I
L
I
T
Y
Data
s
h
ar
in
g
is
n
o
t
ap
p
licab
l
e
to
th
is
ar
ticle
as
n
o
d
ataset
s
we
r
eg
en
er
ate
d
o
r
an
aly
ze
d
d
u
r
in
g
th
e
cu
r
r
en
t stu
d
y
.
RE
F
E
R
E
NC
E
S
[
1
]
M
.
R
o
o
p
a
k
,
G
.
Y
u
n
Ti
a
n
,
a
n
d
J.
C
h
a
mb
e
r
s,
“
D
e
e
p
l
e
a
r
n
i
n
g
m
o
d
e
l
s
f
o
r
c
y
b
e
r
se
c
u
r
i
t
y
i
n
I
o
T
N
e
t
w
o
r
k
s,
”
i
n
2
0
1
9
I
EEE
9
t
h
A
n
n
u
a
l
C
o
m
p
u
t
i
n
g
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
Wo
rks
h
o
p
a
n
d
C
o
n
f
e
r
e
n
c
e
(
C
C
WC
)
,
Ja
n
.
2
0
1
9
,
p
p
.
0
4
5
2
–
0
4
5
7
,
d
o
i
:
1
0
.
1
1
0
9
/
C
C
W
C
.
2
0
1
9
.
8
6
6
6
5
8
8
.
[
2
]
N
.
A
n
g
e
l
o
v
a
,
G
.
K
i
r
y
a
k
o
v
a
,
a
n
d
L.
Y
o
r
d
a
n
o
v
a
,
“
T
h
e
g
r
e
a
t
i
m
p
a
c
t
o
f
i
n
t
e
r
n
e
t
o
f
t
h
i
n
g
s
o
n
b
u
si
n
e
s
s,”
T
ra
k
i
a
J
o
u
r
n
a
l
o
f
S
c
i
e
n
c
e
,
v
o
l
.
1
5
,
n
o
.
S
u
p
p
l
.
1
,
p
p
.
4
0
6
–
4
1
2
,
2
0
1
7
,
d
o
i
:
1
0
.
1
5
5
4
7
/
t
j
s.
2
0
1
7
.
s
.
0
1
.
0
6
8
.
[
3
]
V
.
H
a
ssi
j
a
,
V
.
C
h
a
m
o
l
a
,
V
.
S
a
x
e
n
a
,
D
.
J
a
i
n
,
P
.
G
o
y
a
l
,
a
n
d
B
.
S
i
k
d
a
r
,
“
A
s
u
r
v
e
y
o
n
I
o
T
s
e
c
u
r
i
t
y
:
a
p
p
l
i
c
a
t
i
o
n
a
r
e
a
s
,
se
c
u
r
i
t
y
t
h
r
e
a
t
s
,
a
n
d
s
o
l
u
t
i
o
n
a
r
c
h
i
t
e
c
t
u
r
e
s
,
”
I
E
EE
A
c
c
e
ss
,
v
o
l
.
7
,
p
p
.
8
2
7
2
1
–
8
2
7
4
3
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
1
9
.
2
9
2
4
0
4
5
.
[
4
]
M
.
F
.
El
r
a
w
y
,
A
.
I
.
A
w
a
d
,
a
n
d
H
.
F
.
A
.
H
a
me
d
,
“
I
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
s
y
st
e
ms
f
o
r
I
o
T
-
b
a
se
d
smar
t
e
n
v
i
r
o
n
men
t
s:
a
s
u
r
v
e
y
,
”
J
o
u
rn
a
l
o
f
C
l
o
u
d
C
o
m
p
u
t
i
n
g
,
v
o
l
.
7
,
n
o
.
1
,
p
.
2
1
,
D
e
c
.
2
0
1
8
,
d
o
i
:
1
0
.
1
1
8
6
/
s
1
3
6
7
7
-
0
1
8
-
0
1
2
3
-
6.
[
5
]
L.
G
o
a
sd
u
f
f
,
“
G
a
r
t
n
e
r
sa
y
s
5
.
8
b
i
l
l
i
o
n
e
n
t
e
r
p
r
i
s
e
a
n
d
a
u
t
o
mo
t
i
v
e
I
o
T
e
n
d
p
o
i
n
t
s
w
i
l
l
b
e
i
n
u
se
i
n
2
0
2
0
,
”
G
a
r
t
n
e
r
R
e
p
o
r
t
2
0
1
9
,
2
0
2
0
.
[
6
]
M
.
A
l
m
i
a
n
i
,
A
.
A
b
u
G
h
a
z
l
e
h
,
A
.
A
l
-
R
a
h
a
y
f
e
h
,
S
.
A
t
i
e
w
i
,
a
n
d
A
.
R
a
z
a
q
u
e
,
“
D
e
e
p
r
e
c
u
r
r
e
n
t
n
e
u
r
a
l
n
e
t
w
o
r
k
f
o
r
I
o
T
i
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
sy
s
t
e
m
,
”
S
i
m
u
l
a
t
i
o
n
Mo
d
e
l
l
i
n
g
Pr
a
c
t
i
c
e
a
n
d
T
h
e
o
r
y
,
v
o
l
.
1
0
1
,
p
.
1
0
2
0
3
1
,
M
a
y
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
si
m
p
a
t
.
2
0
1
9
.
1
0
2
0
3
1
.
[
7
]
S
.
J.
M
o
o
r
e
,
C
.
D
.
N
u
g
e
n
t
,
S
.
Z
h
a
n
g
,
a
n
d
I
.
C
l
e
l
a
n
d
,
“
I
o
T
r
e
l
i
a
b
i
l
i
t
y
:
a
r
e
v
i
e
w
l
e
a
d
i
n
g
t
o
5
k
e
y
r
e
s
e
a
r
c
h
d
i
r
e
c
t
i
o
n
s
,
”
C
C
F
T
ra
n
s
a
c
t
i
o
n
s
o
n
Pe
r
v
a
si
v
e
C
o
m
p
u
t
i
n
g
a
n
d
I
n
t
e
ra
c
t
i
o
n
,
v
o
l
.
2
,
n
o
.
3
,
p
p
.
1
4
7
–
1
6
3
,
O
c
t
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
0
7
/
s
4
2
4
8
6
-
0
2
0
-
0
0
0
3
7
-
z.
[
8
]
S
.
C
.
M
u
k
h
o
p
a
d
h
y
a
y
a
n
d
N
.
K
.
S
u
r
y
a
d
e
v
a
r
a
,
“
I
n
t
e
r
n
e
t
o
f
t
h
i
n
g
s
:
c
h
a
l
l
e
n
g
e
s
a
n
d
o
p
p
o
r
t
u
n
i
t
i
e
s
,
”
i
n
S
m
a
rt
S
e
n
s
o
rs,
M
e
a
su
r
e
m
e
n
t
a
n
d
I
n
st
r
u
m
e
n
t
a
t
i
o
n
,
2
0
1
4
,
p
p
.
1
–
17
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
319
-
0
4
2
2
3
-
7
_
1
.
[
9
]
A
.
T
h
a
k
k
a
r
a
n
d
R
.
L
o
h
i
y
a
,
“
A
r
e
v
i
e
w
o
n
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
p
e
r
sp
e
c
t
i
v
e
s
o
f
I
D
S
f
o
r
I
o
T:
r
e
c
e
n
t
u
p
d
a
t
e
s
,
s
e
c
u
r
i
t
y
i
ssu
e
s,
a
n
d
c
h
a
l
l
e
n
g
e
s
,
”
Arc
h
i
v
e
s
o
f
C
o
m
p
u
t
a
t
i
o
n
a
l
Me
t
h
o
d
s
i
n
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
2
8
,
n
o
.
4
,
p
p
.
3
2
1
1
–
3
2
4
3
,
Ju
n
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
8
3
1
-
0
2
0
-
0
9
4
9
6
-
0.
[
1
0
]
Y
.
Li
,
Y
.
Z
u
o
,
H
.
S
o
n
g
,
a
n
d
Z
.
L
v
,
“
D
e
e
p
l
e
a
r
n
i
n
g
i
n
sec
u
r
i
t
y
o
f
i
n
t
e
r
n
e
t
o
f
t
h
i
n
g
s
,
”
I
E
EE
I
n
t
e
rn
e
t
o
f
T
h
i
n
g
s
J
o
u
r
n
a
l
,
v
o
l
.
9
,
n
o
.
2
2
,
p
p
.
2
2
1
3
3
–
2
2
1
4
6
,
N
o
v
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
JI
O
T.
2
0
2
1
.
3
1
0
6
8
9
8
.
[
1
1
]
S
.
K
r
i
s
h
n
a
v
e
n
i
,
P
.
V
i
g
n
e
s
h
w
a
r
,
S
.
K
i
s
h
o
r
e
,
B
.
J
o
t
h
i
,
a
n
d
S
.
S
i
v
a
m
o
h
a
n
,
“
A
n
o
m
a
l
y
-
b
a
se
d
i
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
sy
s
t
e
m u
si
n
g
s
u
p
p
o
r
t
v
e
c
t
o
r
mac
h
i
n
e
,”
i
n
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
and
Ev
o
l
u
t
i
o
n
a
ry
C
o
m
p
u
t
a
t
i
o
n
s
i
n
E
n
g
i
n
e
e
r
i
n
g
S
y
s
t
e
m
s
,
2
0
2
0
,
p
p
.
7
2
3
–
731
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
981
-
15
-
0
1
9
9
-
9
_
6
2
.
[
1
2
]
R
.
U
i
k
e
y
a
n
d
M
.
G
y
a
n
c
h
a
n
d
a
n
i
,
“
S
u
r
v
e
y
o
n
c
l
a
ss
i
f
i
c
a
t
i
o
n
t
e
c
h
n
i
q
u
e
s
a
p
p
l
i
e
d
t
o
i
n
t
r
u
s
i
o
n
d
e
t
e
c
t
i
o
n
sy
s
t
e
m
a
n
d
i
t
s
c
o
mp
a
r
a
t
i
v
e
a
n
a
l
y
si
s
,
”
i
n
2
0
1
9
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
C
o
m
m
u
n
i
c
a
t
i
o
n
a
n
d
E
l
e
c
t
r
o
n
i
c
s
S
y
st
e
m
s
(
I
C
C
E
S
)
,
Ju
l
.
2
0
1
9
,
p
p
.
1
4
5
1
–
1
4
5
6
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
C
ES
4
5
8
9
8
.
2
0
1
9
.
9
0
0
2
1
2
9
.
[
1
3
]
M
.
A
l
-
H
a
w
a
w
r
e
h
,
E.
S
i
t
n
i
k
o
v
a
,
a
n
d
F
.
d
e
n
H
a
r
t
o
g
,
“
A
n
e
f
f
i
c
i
e
n
t
i
n
t
r
u
s
i
o
n
d
e
t
e
c
t
i
o
n
m
o
d
e
l
f
o
r
e
d
g
e
sy
s
t
e
m
i
n
b
r
o
w
n
f
i
e
l
d
i
n
d
u
st
r
i
a
l
i
n
t
e
r
n
e
t
o
f
t
h
i
n
g
s
,
”
i
n
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
3
r
d
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
B
i
g
D
a
t
a
a
n
d
I
n
t
e
rn
e
t
o
f
T
h
i
n
g
s
,
A
u
g
.
2
0
1
9
,
p
p
.
8
3
–
87
,
d
o
i
:
1
0
.
1
1
4
5
/
3
3
6
1
7
5
8
.
3
3
6
1
7
6
2
.
[
1
4
]
M
.
Es
k
a
n
d
a
r
i
,
Z.
H
.
J
a
n
j
u
a
,
M
.
V
e
c
c
h
i
o
,
a
n
d
F
.
A
n
t
o
n
e
l
l
i
,
“
P
a
ss
b
a
n
I
D
S
:
A
n
i
n
t
e
l
l
i
g
e
n
t
a
n
o
ma
l
y
-
b
a
se
d
i
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
sy
s
t
e
m
f
o
r
I
o
T
e
d
g
e
d
e
v
i
c
e
s
,
”
I
EEE
I
n
t
e
rn
e
t
o
f
T
h
i
n
g
s
J
o
u
r
n
a
l
,
v
o
l
.
7
,
n
o
.
8
,
p
p
.
6
8
8
2
–
6
8
9
7
,
A
u
g
.
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
JI
O
T.
2
0
2
0
.
2
9
7
0
5
0
1
.
[
1
5
]
A
.
S
h
u
k
l
a
,
H
.
S
h
a
r
ma
,
A
.
S
i
n
g
h
,
a
n
d
A
.
A
h
m
a
d
,
“
F
u
t
u
r
e
o
f
i
n
t
e
r
n
e
t
o
f
t
h
i
n
g
s
:
t
r
e
n
d
s
,
c
h
a
l
l
e
n
g
e
s
&
i
n
si
g
h
t
t
o
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
A
d
v
a
n
c
e
d
Re
s
e
a
rc
h
i
n
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
9
,
n
o
.
S
p
e
c
i
a
l
I
ssu
e
2
,
p
p
.
1
6
2
–
1
6
7
,
2
0
1
8
,
d
o
i
:
1
0
.
2
6
4
8
3
/
i
j
a
r
c
s.
v
9
i
0
.
6
1
5
8
.
[
1
6
]
K
.
A
l
b
u
l
a
y
h
i
,
A
.
A
.
S
ma
d
i
,
F
.
T.
S
h
e
l
d
o
n
,
a
n
d
R
.
K
.
A
b
e
r
c
r
o
m
b
i
e
,
“
I
o
T
i
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
t
a
x
o
n
o
m
y
,
r
e
f
e
r
e
n
c
e
a
r
c
h
i
t
e
c
t
u
r
e
,
a
n
d
a
n
a
l
y
ses
,
”
S
e
n
s
o
rs
,
v
o
l
.
2
1
,
n
o
.
1
9
,
p
.
6
4
3
2
,
S
e
p
.
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
s2
1
1
9
6
4
3
2
.
[
1
7
]
B
.
S
h
a
r
ma
,
L
.
S
h
a
r
ma,
C
.
La
l
,
a
n
d
S
.
R
o
y
,
“
Ex
p
l
a
i
n
a
b
l
e
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
f
o
r
i
n
t
r
u
s
i
o
n
d
e
t
e
c
t
i
o
n
i
n
I
o
T
n
e
t
w
o
r
k
s:
A
d
e
e
p
l
e
a
r
n
i
n
g
b
a
se
d
a
p
p
r
o
a
c
h
,
”
E
x
p
e
rt
S
y
st
e
m
s w
i
t
h
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
2
3
8
,
p
.
1
2
1
7
5
1
,
M
a
r
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
sw
a
.
2
0
2
3
.
1
2
1
7
5
1
.
[
1
8
]
M
.
S
h
a
h
i
n
,
M
.
M
a
g
h
a
n
a
k
i
,
A
.
H
o
sse
i
n
z
a
d
e
h
,
a
n
d
F
.
F
.
C
h
e
n
,
“
A
d
v
a
n
c
i
n
g
n
e
t
w
o
r
k
s
e
c
u
r
i
t
y
i
n
i
n
d
u
s
t
r
i
a
l
I
o
T:
A
d
e
e
p
d
i
v
e
i
n
t
o
AI
-
e
n
a
b
l
e
d
i
n
t
r
u
s
i
o
n
d
e
t
e
c
t
i
o
n
s
y
st
e
ms
,”
A
d
v
a
n
c
e
d
En
g
i
n
e
e
r
i
n
g
I
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
6
2
,
p
.
1
0
2
6
8
5
,
O
c
t
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
e
i
.
2
0
2
4
.
1
0
2
6
8
5
.
[
1
9
]
M
.
N
a
n
j
a
p
p
a
n
,
K
.
P
r
a
d
e
e
p
,
G
.
N
a
t
e
s
a
n
,
A
.
S
a
m
y
d
u
r
a
i
,
a
n
d
G
.
P
r
e
m
a
l
a
t
h
a
,
“
D
e
e
p
LG
s
e
c
N
e
t
:
u
t
i
l
i
z
i
n
g
d
e
e
p
LST
M
a
n
d
G
R
U
w
i
t
h
sec
u
r
e
n
e
t
w
o
r
k
f
o
r
e
n
h
a
n
c
e
d
i
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
i
n
I
o
T
e
n
v
i
r
o
n
m
e
n
t
s,
”
C
l
u
st
e
r
C
o
m
p
u
t
i
n
g
,
v
o
l
.
2
7
,
n
o
.
4
,
p
p
.
5
4
5
9
–
5
4
7
1
,
Ju
l
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
0
5
8
6
-
0
2
3
-
0
4
2
2
3
-
3.
Evaluation Warning : The document was created with Spire.PDF for Python.