I
AE
S In
t
er
na
t
io
na
l J
o
urna
l o
f
Art
if
icia
l In
t
ellig
ence
(
I
J
-
AI
)
Vo
l.
1
5
,
No
.
2
,
A
p
r
il 2
0
2
6
,
p
p
.
1
5
0
5
~
1
5
1
2
I
SS
N:
2
2
5
2
-
8
9
3
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijai
.
v
1
5
.
i
2.
pp
1
5
0
5
-
1
5
1
2
1505
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
i
.
ia
esco
r
e
.
co
m
Zo
neo
ut
regu
la
ri
za
tion
-
g
a
ted
re
cu
rrent u
nit
alg
o
rithm on
NIDS
with
cla
ss
im
ba
la
nce handli
ng
M
a
la
K
a
riy
a
pp
a
1
,
M
a
njuna
t
h H
a
nu
m
a
ntha
pp
a
Ra
ng
a
pp
a
2
,
Venug
o
pa
l D
a
s
a
pp
a
3
,
G
urura
j
a
H
ebbu
r
Sa
t
y
a
na
ra
y
a
na
4
,
G
iris
h K
esh
a
v
a
Ra
o
5
,
G
o
us
ia
T
ha
hn
iy
a
t
h
6
1
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
mat
i
o
n
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
C
h
a
n
n
a
b
a
se
v
e
s
h
w
a
r
a
I
n
st
i
t
u
t
e
o
f
T
e
c
h
n
o
l
o
g
y
,
T
u
m
k
u
r
,
I
n
d
i
a
2
D
e
p
a
r
t
me
n
t
o
f
A
r
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
,
J
y
o
t
h
y
I
n
st
i
t
u
t
e
o
f
Te
c
h
n
o
l
o
g
y
,
B
e
n
g
a
l
u
r
u
,
I
n
d
i
a
3
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
H
a
r
s
h
a
I
n
st
i
t
u
t
e
o
f
T
e
c
h
n
o
l
o
g
y
,
B
e
n
g
a
l
u
r
u
,
I
n
d
i
a
4
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
B
u
s
i
n
e
ss S
y
st
e
ms,
B
.
M
.
S
.
C
o
l
l
e
g
e
o
f
E
n
g
i
n
e
e
r
i
n
g
,
B
e
n
g
a
l
u
r
u
,
I
n
d
i
a
5
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
A
p
p
l
i
c
a
t
i
o
n
s,
B
.
M
.
S
.
C
o
l
l
e
g
e
o
f
E
n
g
i
n
e
e
r
i
n
g
,
B
e
n
g
a
l
u
r
u
,
I
n
d
i
a
6
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
D
a
y
a
n
a
n
d
a
S
a
g
a
r
U
n
i
v
e
r
si
t
y
,
B
e
n
g
a
l
u
r
u
,
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
Ma
y
1
2
,
2
0
2
5
R
ev
is
ed
J
an
1
6
,
2
0
2
6
Acc
ep
ted
J
an
2
5
,
2
0
2
6
Ne
two
rk
in
t
ru
sio
n
d
e
tec
ti
o
n
s
y
ste
m
(NID
S
)
is
p
rima
ril
y
u
ti
li
z
e
d
to
o
l
t
o
id
e
n
ti
f
y
m
a
li
c
io
u
s
t
h
re
a
ts
o
n
th
e
n
e
two
rk
.
It
p
lay
s
a
n
e
ss
e
n
ti
a
l
ro
le
i
n
sa
fe
g
u
a
rd
in
g
a
g
a
in
st
a
n
in
c
re
a
sin
g
v
a
riety
o
f
a
tt
a
c
k
s
a
n
d
e
n
su
re
s
e
n
h
a
n
c
e
d
se
c
u
rit
y
f
o
r
t
h
e
n
e
two
rk
.
T
h
e
e
x
isti
n
g
m
o
d
e
l
stru
g
g
led
t
o
h
a
n
d
le
th
e
imb
a
lan
c
e
o
f
c
las
s
issu
e
s
d
u
rin
g
th
e
p
ro
c
e
ss
o
f
c
las
sifica
ti
o
n
d
u
e
to
th
e
ir
b
ias
e
d
n
a
tu
re
,
wh
ich
re
d
u
c
e
d
th
e
p
e
rfo
rm
a
n
c
e
o
f
t
h
e
a
lg
o
r
it
h
m
.
I
n
t
h
is p
a
p
e
r,
th
e
z
o
n
e
o
u
t
re
g
u
lariz
a
ti
o
n
–
g
a
te
d
re
c
u
rre
n
t
u
n
it
(ZR
-
G
RU)
a
lg
o
rit
h
m
is
d
e
v
e
lo
p
e
d
to
d
e
tec
t
a
n
d
c
las
sify
i
n
tru
si
o
n
s
in
t
h
e
n
e
two
rk
.
I
n
c
o
rp
o
ra
ti
n
g
th
e
ZR
in
to
G
RU
re
d
u
c
e
s
o
v
e
rfit
ti
n
g
b
y
p
re
v
e
n
ti
n
g
th
e
m
o
d
e
l
fro
m
b
e
c
o
m
in
g
o
v
e
rly
d
e
p
e
n
d
e
n
t
o
n
sp
e
c
ifi
c
fe
a
tu
re
s
.
It
p
ro
v
id
e
s
g
o
o
d
g
e
n
e
ra
l
iza
ti
o
n
b
y
m
a
in
tain
in
g
d
i
v
e
rsity
in
lea
r
n
e
d
re
p
re
se
n
tatio
n
.
S
y
n
th
e
ti
c
m
in
o
rit
y
o
v
e
rsa
m
p
li
n
g
tec
h
n
iq
u
e
(S
M
OT
E)
a
n
d
Ne
a
r
M
iss
m
e
th
o
d
s
a
re
u
ti
li
z
e
d
to
b
a
lan
c
e
th
e
sa
m
p
les
in
th
e
d
a
tas
e
t,
wh
ich
h
e
l
p
s
to
in
c
re
a
se
th
e
p
e
r
fo
rm
a
n
c
e
o
f
a
c
las
sifier
i
n
NID
S
.
Th
e
ZR
-
G
RU
tec
h
n
iq
u
e
a
tt
a
in
e
d
9
9
.
9
1
%
a
c
c
u
ra
c
y
o
n
UN
S
W
-
NB1
5
,
9
9
.
9
2
%
a
c
c
u
ra
c
y
o
n
CIC
-
IDS
2
0
1
8
,
a
n
d
9
9
.
1
4
%
a
c
c
u
ra
c
y
o
n
CIC
-
DD
o
S
2
0
1
9
wh
e
n
c
o
m
p
a
rin
g
wit
h
a
c
o
n
v
o
lu
ti
o
n
a
l
n
e
u
ra
l
n
e
two
rk
-
b
id
irec
ti
o
n
a
l
l
o
n
g
sh
o
rt
-
term
m
e
m
o
ry
(CNN
-
BiL
S
T
M
)
.
K
ey
w
o
r
d
s
:
Gate
d
r
ec
u
r
r
e
n
t u
n
it
Nea
r
Miss
N
e
t
w
o
r
k
i
n
t
r
u
s
i
o
n
d
e
t
e
c
t
i
o
n
s
y
s
t
e
m
SMOT
E
Z
o
n
eo
u
t
r
eg
u
lar
izatio
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
:
Ma
la
Kar
iy
ap
p
a
Dep
ar
tm
en
t o
f
I
n
f
o
r
m
atio
n
Scien
ce
an
d
E
n
g
in
ee
r
i
n
g
,
C
h
an
n
ab
asev
esh
war
a
I
n
s
titu
te
o
f
T
e
ch
n
o
lo
g
y
T
u
m
k
u
r
,
I
n
d
ia
E
m
ail: m
ala
.
k
@
cittu
m
k
u
r
.
o
r
g
1.
I
NT
RO
D
UCT
I
O
N
As
am
o
u
n
t
o
f
u
s
er
s
an
d
d
ep
e
n
d
en
cy
o
n
th
e
in
ter
n
et
c
o
n
tin
u
e
to
g
r
o
w,
n
etwo
r
k
attac
k
s
h
a
v
e
b
ec
o
m
e
m
u
ch
m
o
r
e
f
r
eq
u
en
t,
d
is
r
u
p
ti
n
g
s
tan
d
ar
d
p
r
o
ce
s
s
es
[
1
]
.
T
h
e
r
is
e
in
v
ar
io
u
s
ty
p
es
an
d
s
ca
les
o
f
attac
k
s
h
as
ex
p
o
s
ed
th
e
d
r
awb
ac
k
s
o
f
tr
ad
itio
n
al
s
ec
u
r
ity
m
ea
s
u
r
es
l
ik
e
an
tiv
ir
u
s
s
o
f
twar
e,
p
o
lic
y
o
f
s
ec
u
r
ity
,
an
d
f
ir
ewa
lls
,
wh
ich
ar
e
in
s
u
f
f
icien
t
to
f
u
lly
p
r
o
tect
th
e
n
etwo
r
k
s
[
2
]
,
[
3
]
.
T
h
e
n
etwo
r
k
in
t
r
u
s
io
n
d
etec
tio
n
s
y
s
te
m
(
NI
DS)
is
d
ev
elo
p
ed
to
p
r
ev
e
n
t
tar
g
eted
attac
k
s
th
r
o
u
g
h
c
o
n
tin
u
o
u
s
ly
m
o
n
ito
r
in
g
tr
af
f
ic
in
th
e
n
etwo
r
k
[
4
]
.
T
h
at
s
y
s
tem
an
aly
ze
s
d
ata
an
d
tr
ies
to
r
ec
o
g
n
ize
an
o
m
alies
in
a
n
etwo
r
k
,
lik
e
u
n
a
u
th
o
r
iz
ed
ac
ce
s
s
,
d
am
ag
e,
o
r
in
tr
u
s
io
n
s
[
5
]
.
I
n
tr
u
s
io
n
d
etec
tio
n
s
y
s
tem
(
I
DS)
is
g
en
er
ally
ass
ig
n
ed
as
a
s
o
f
tw
ar
e
ap
p
licatio
n
f
o
r
m
o
n
ito
r
in
g
a
n
etwo
r
k
a
n
d
ac
ti
v
ities
o
f
a
s
y
s
tem
f
o
r
m
alicio
u
s
b
eh
a
v
io
r
s
[
6
]
.
I
t
id
en
tifie
s
u
n
au
th
o
r
ized
ac
ce
s
s
to
a
s
y
s
tem
an
d
th
en
r
ep
o
r
ts
th
at
to
n
etwo
r
k
a
d
m
in
is
tr
ato
r
s
[
7
]
.
Dif
f
e
r
en
t
m
ac
h
i
n
e
le
ar
n
in
g
(
ML
)
-
b
ased
alg
o
r
ith
m
s
h
a
v
e
b
ee
n
d
e
v
elo
p
ed
f
o
r
I
DS
f
o
r
id
e
n
tify
in
g
an
d
class
if
y
in
g
s
ec
u
r
ity
attac
k
s
[
8
]
.
T
h
e
ML
-
b
ased
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2252
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
2
,
Ap
r
il 2
0
2
6
:
1
5
0
5
-
1
5
1
2
1506
ap
p
r
o
ac
h
es
in
n
etwo
r
k
tr
af
f
ic
an
d
ass
o
ciate
d
th
em
with
d
i
f
f
er
en
t
p
r
e
-
d
ef
in
e
d
n
etwo
r
k
t
r
af
f
ic
p
r
o
f
iles
an
d
s
u
p
p
o
r
t
i
n
d
etec
tin
g
if
th
e
s
p
e
cif
ic
n
etwo
r
k
tr
af
f
ic
in
s
tan
ce
s
ar
e
in
t
r
u
s
io
n
s
o
r
n
o
t
[
9
]
,
[
1
0
]
.
T
h
ese
alg
o
r
ith
m
s
u
s
e
ML
f
o
r
d
ev
el
o
p
in
g
an
I
DS,
em
p
lo
y
in
g
eith
e
r
o
n
e
class
if
ier
o
r
a
h
y
b
r
i
d
cla
s
s
if
ier
[
1
1
]
.
Sin
g
le
class
if
ier
-
b
ased
s
y
s
tem
s
u
tili
z
e
o
n
e
ML
-
b
ased
ap
p
r
o
ac
h
es
f
o
r
id
en
tify
in
g
th
e
attac
k
s
,
wh
ile
h
y
b
r
id
s
y
s
tem
s
in
teg
r
ate
m
u
ltip
le
ML
-
b
ased
alg
o
r
ith
m
s
,
with
o
n
e
class
if
ier
h
an
d
lin
g
th
e
p
r
e
-
p
r
o
ce
s
s
in
g
in
f
o
r
m
atio
n
an
d
th
e
o
th
er
f
o
r
tr
ain
in
g
th
e
p
r
e
-
p
r
o
c
ess
ed
in
f
o
r
m
atio
n
[
1
2
]
,
[
1
3
]
.
T
o
m
ee
t
th
e
d
em
an
d
s
o
f
lar
g
e
-
s
ca
le
n
etwo
r
k
s
,
th
e
d
ee
p
lear
n
in
g
(
DL
)
-
b
ased
alg
o
r
ith
m
,
wh
ich
is
a
b
r
an
ch
o
f
ML
is
em
p
lo
y
ed
i
n
NI
DS
[
1
4
]
.
An
ley
et
a
l
.
[
1
5
]
im
p
lem
en
ted
an
in
n
o
v
ativ
e
te
ch
n
iq
u
e
t
o
d
is
tr
ib
u
ted
d
en
ial
o
f
s
er
v
ice
(
DDo
S
)
d
etec
tio
n
u
s
in
g
a
co
n
v
o
l
u
tio
n
al
n
eu
r
al
n
etwo
r
k
(
C
NN)
an
d
ad
ap
tiv
e
s
tr
u
ctu
r
es o
f
t
r
an
s
f
er
le
ar
n
in
g
m
et
h
o
d
s
.
Z
h
ao
et
a
l
.
[
1
6
]
in
tr
o
d
u
ce
d
a
DDo
S
attac
k
d
etec
tio
n
tech
n
i
q
u
e,
wh
ich
in
te
g
r
ated
th
e
s
elf
-
atten
tio
n
m
ec
h
an
is
m
with
C
NN
-
b
id
ir
e
ctio
n
al
lo
n
g
s
h
o
r
t
-
te
r
m
m
e
m
o
r
y
(
B
iLST
M)
to
ad
d
r
ess
p
r
o
b
lem
s
o
n
h
ig
h
d
im
en
s
io
n
ality
,
m
u
lti
-
f
ea
tu
r
e
d
im
en
s
io
n
s
,
lo
w
class
if
icatio
n
ac
cu
r
ac
y
,
an
d
h
ig
h
f
alse
p
o
s
i
tiv
e
r
ate
in
o
r
ig
in
al
tr
af
f
ic
in
f
o
r
m
atio
n
.
Z
h
ao
et
a
l
.
[
1
7
]
p
r
esen
ted
a
h
y
b
r
id
I
DS
th
at
d
e
p
en
d
e
d
o
n
t
h
e
c
o
r
r
el
atio
n
-
b
ased
f
ea
tu
r
e
s
elec
tio
n
with
d
if
f
e
r
en
tial
e
v
o
lu
tio
n
(
C
FS
-
DE
)
f
ea
tu
r
e
s
elec
tio
n
tech
n
iq
u
e
an
d
th
e
weig
h
ted
s
tack
in
g
class
if
icatio
n
tech
n
iq
u
e
.
T
h
e
p
r
esen
ted
m
eth
o
d
m
i
n
im
ized
h
ig
h
-
d
im
en
s
io
n
al
f
ea
tu
r
e
s
an
d
m
ax
im
i
z
e
d
class
if
icatio
n
p
er
f
o
r
m
a
n
ce
.
Yin
et
a
l
.
[
1
8
]
s
u
g
g
ested
a
h
y
b
r
id
f
ea
tu
r
e
s
elec
tio
n
tech
n
i
q
u
e
o
n
m
u
lti
-
class
n
etwo
r
k
an
o
m
alies
b
y
u
tili
zin
g
a
m
u
lti
-
lay
er
p
er
ce
p
t
r
o
n
(
ML
P)
n
etwo
r
k
.
Ay
a
n
tay
o
et
a
l
.
[
1
9
]
d
ev
elo
p
ed
th
r
ee
v
ar
io
u
s
DL
-
b
ased
alg
o
r
ith
m
s
k
n
o
wn
as
ea
r
ly
-
f
u
s
io
n
,
l
ate
-
f
u
s
io
n
,
an
d
late
-
en
s
em
b
le
lear
n
in
g
tech
n
iq
u
es
u
tili
zin
g
f
ea
tu
r
e
f
u
s
io
n
with
co
m
p
letely
in
teg
r
ated
d
ee
p
n
etwo
r
k
s
.
E
x
is
tin
g
alg
o
r
ith
m
s
f
o
r
I
DS
s
u
f
f
er
ed
f
r
o
m
v
an
is
h
in
g
g
r
ad
ien
ts
,
o
v
er
f
itti
n
g
,
a
n
d
p
o
o
r
h
an
d
lin
g
o
f
im
b
alan
ce
d
d
atasets
.
R
ec
u
r
r
en
t
n
e
u
r
al
n
etwo
r
k
(
R
NN
)
-
b
ased
alg
o
r
ith
m
s
f
ailed
to
ca
p
tu
r
e
lo
n
g
-
ter
m
d
ep
en
d
en
cies
b
ec
a
u
s
e
o
f
g
r
a
d
ien
t
p
r
o
b
lem
s
,
wh
il
e
o
v
er
f
itti
n
g
lim
its
th
eir
g
en
er
al
izatio
n
o
n
u
n
s
ee
n
attac
k
s
.
Fo
r
m
itig
atin
g
th
ese
is
s
u
es,
th
is
r
e
s
ea
r
ch
ex
p
lo
r
es th
e
ef
f
ec
tiv
en
ess
o
f
zo
n
eo
u
t
r
eg
u
lar
izatio
n
–
g
ate
d
r
ec
u
r
r
en
t
u
n
it
(ZR
-
GR
U)
m
eth
o
d
is
d
e
v
elo
p
ed
t
o
en
h
a
n
ce
n
etwo
r
k
in
tr
u
s
io
n
d
etec
tio
n
ef
f
icien
tly
.
Z
o
n
e
o
u
t
is
p
ar
ticu
lar
ly
s
elec
ted
o
v
er
o
th
er
r
eg
u
lar
izatio
n
s
lik
e
d
r
o
p
o
u
t
a
n
d
b
atch
n
o
r
m
aliza
tio
n
b
ec
au
s
e
o
f
its
tem
p
o
r
al
c
o
n
s
is
ten
cy
-
p
r
eser
v
in
g
n
atu
r
e,
wh
ich
is
s
u
itab
l
e
f
o
r
GR
U
u
s
ed
in
NI
DS
.
Ad
d
itio
n
ally
,
lik
e
th
e
s
y
n
th
etic
m
i
n
o
r
ity
o
v
e
r
s
am
p
lin
g
tec
h
n
iq
u
e
(
SMOT
E
)
an
d
Nea
r
Miss
b
ased
class
im
b
alan
ce
h
an
d
lin
g
tech
n
iq
u
es
ar
e
i
n
teg
r
a
ted
with
th
e
p
r
o
p
o
s
ed
in
tr
u
s
io
n
d
etec
tio
n
m
o
d
el
th
e
s
ig
n
if
ican
t
c
o
n
tr
ib
u
tio
n
s
o
f
th
e
ar
ticle
a
r
e
d
escr
ib
e
d
as
f
o
llo
ws:
SMOT
E
an
d
Nea
r
Mi
s
s
m
eth
o
d
s
ar
e
u
s
ed
in
a
p
r
e
-
p
r
o
ce
s
s
in
g
p
h
ase
to
b
alan
ce
s
am
p
les
in
th
e
d
ataset,
wh
ich
h
elp
s
to
im
p
r
o
v
e
th
e
class
if
icatio
n
p
er
f
o
r
m
an
ce
.
T
h
e
Z
R
-
GR
U
alg
o
r
ith
m
is
d
ev
elo
p
ed
f
o
r
t
h
e
d
etec
tio
n
an
d
class
if
icatio
n
o
f
in
tr
u
s
io
n
s
in
a
n
etwo
r
k
,
wh
ic
h
ef
f
ec
tiv
ely
class
if
ies th
e
in
tr
u
s
io
n
s
in
th
e
n
etwo
r
k
with
class
if
icatio
n
ac
cu
r
ac
y
.
T
h
is
r
esear
ch
p
a
p
er
is
s
y
s
tem
atize
d
as
f
o
llo
ws
.
Sectio
n
2
p
r
o
v
id
es
d
etails
o
f
a
p
r
o
p
o
s
ed
alg
o
r
ith
m
.
Sectio
n
3
g
iv
es
th
e
r
esu
lts
an
d
d
is
cu
s
s
io
n
o
f
th
e
p
r
o
p
o
s
ed
al
g
o
r
ith
m
.
T
h
e
co
n
clu
s
io
n
is
g
iv
en
in
s
ec
tio
n
4
.
2.
P
RO
P
O
SE
D
M
E
T
H
O
D
T
h
is
r
esear
ch
p
r
o
p
o
s
ed
a
DL
-
b
ased
alg
o
r
ith
m
with
class
b
alan
cin
g
alg
o
r
ith
m
s
to
d
etec
t
an
d
class
if
y
in
tr
u
s
io
n
s
in
th
e
n
etwo
r
k
.
Fig
u
r
e
1
r
e
p
r
esen
ts
th
e
p
r
o
ce
s
s
o
f
NI
DS
.
T
h
e
th
r
ee
b
e
n
ch
m
ar
k
d
atasets
ar
e
u
s
ed
in
th
is
ar
ticle
,
wh
ich
ar
e
th
en
p
r
e
-
p
r
o
ce
s
s
ed
b
y
u
s
in
g
SMOT
E
,
Nea
r
Miss
,
an
d
s
tan
d
ar
d
izatio
n
tech
n
iq
u
es
to
en
h
an
ce
t
h
e
q
u
ality
o
f
d
ata
.
T
h
en
,
th
e
f
ea
t
u
r
es
ar
e
clas
s
if
ied
b
y
u
s
in
g
th
e
d
ev
elo
p
e
d
Z
R
-
GR
U,
wh
ich
class
if
ied
th
e
in
tr
u
s
io
n
s
ef
f
ec
tiv
ely
.
Fig
u
r
e
1
.
Pro
ce
s
s
o
f
NI
DS
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
Zo
n
eo
u
t reg
u
la
r
iz
a
tio
n
-
g
a
ted
r
ec
u
r
r
en
t u
n
it a
lg
o
r
ith
m
o
n
N
I
DS
w
ith
cla
s
s
imb
a
la
n
ce
…
(
Ma
la
K
a
r
iya
p
p
a
)
1507
2
.
1
.
Da
t
a
s
et
T
h
e
d
a
t
a
s
e
t
s
u
s
e
d
i
n
t
h
i
s
r
e
s
e
a
r
c
h
a
r
e
U
N
S
W
-
N
B
1
5
[
2
0
]
,
C
S
E
-
C
I
C
-
I
D
S
2
0
1
8
[
2
1
]
,
a
n
d
C
I
C
-
D
D
o
S
2
0
1
9
[
2
2
]
.
UNSW
-
NB
1
5
d
ataset
in
clu
d
es
n
in
e
s
p
ec
if
ic
attac
k
ty
p
es
an
d
4
9
f
ea
tu
r
es.
T
h
ese
atta
ck
ty
p
es
co
v
er
wid
e
r
an
g
e
o
f
cy
b
e
r
th
r
ea
ts
an
d
en
ab
le
th
e
co
m
p
lete
ev
alu
atio
n
o
f
I
DS.
T
h
e
UNSW
-
NB
1
5
co
n
s
is
ts
o
f
1
0
tr
af
f
ic
ty
p
es
s
u
ch
as
wo
r
m
s
,
s
h
ellc
o
d
e,
b
ac
k
d
o
o
r
,
an
aly
s
is
,
f
u
zz
er
s
,
r
ec
o
n
n
aiss
an
ce
,
Do
S,
ex
p
lo
its
,
g
en
er
ic
,
an
d
b
en
ig
n
.
Nex
t,
th
e
C
I
C
-
I
DS2
0
1
8
d
ataset
in
clu
d
es
8
ty
p
es
o
f
tr
af
f
ic
d
ata,
s
u
ch
as
DDo
S
attac
k
s
-
s
lo
w
HT
T
P
test
,
DDo
S
a
ttack
s
-
L
OI
C
-
UD
P,
DDo
S
attac
k
s
Slo
wlo
r
is
,
DDo
S
attac
k
s
Go
ld
en
E
y
e,
DDo
S
attac
k
s
-
HUL
K
,
DDo
S
attac
k
s
-
HOI
C
,
DDo
S
attac
k
s
–
lo
ic
–
HHT
P,
an
d
B
e
n
ig
n
.
T
h
e
C
I
C
-
DDo
S2
0
1
9
d
ataset
in
v
o
lv
es
13
v
ar
io
u
s
ty
p
es
o
f
tr
af
f
ic
d
ata
lik
e
W
eb
DDo
S,
Po
r
tm
ap
,
NetBIOS,
L
DAP,
B
en
ig
n
,
DNS,
SNMP,
MSSQL
,
SYN,
SS
D
P,
NT
P,
UDP,
an
d
T
FTP r
esp
ec
tiv
ely
.
2
.
2
.
P
re
-
pro
ce
s
s
ing
T
h
e
d
a
t
a
s
et
is
p
r
e
-
p
r
o
c
e
s
s
e
d
b
y
u
s
i
n
g
t
h
r
e
e
d
i
f
f
e
r
e
n
t
p
r
e
-
p
r
o
c
e
s
s
i
n
g
a
l
g
o
r
i
t
h
m
s
l
i
k
e
S
MO
T
E
,
N
e
ar
M
i
s
s
m
et
h
o
d
,
a
n
d
s
t
a
n
d
a
r
d
i
z
at
io
n
.
S
M
O
T
E
a
n
d
N
e
a
r
Mi
s
s
t
e
ch
n
i
q
u
e
s
a
r
e
u
s
e
d
f
o
r
e
f
f
e
c
ti
v
e
ly
h
a
n
d
l
i
n
g
m
i
n
o
r
i
t
y
a
n
d
m
a
j
o
r
i
t
y
c
l
as
s
e
s
i
n
N
I
D
S
.
A
d
e
t
a
i
le
d
d
e
s
c
r
i
p
t
i
o
n
o
f
t
h
e
s
e
p
r
e
-
p
r
o
c
e
s
s
i
n
g
t
ec
h
n
i
q
u
e
s
is
g
iv
e
n
a
s
f
o
l
l
o
ws
.
2
.
2
.
1
.
Sy
nthet
ic
m
ino
rit
y
o
v
e
rsa
m
pli
ng
t
ec
hn
iqu
e
SMOT
E
[
2
3
]
is
a
r
esam
p
lin
g
alg
o
r
ith
m
th
at
m
ax
im
izes
th
e
q
u
an
tity
o
f
m
in
o
r
ity
class
s
am
p
les
b
y
d
ev
elo
p
in
g
s
y
n
th
etic
s
am
p
les
in
th
e
m
in
o
r
ity
class
an
d
is
e
m
p
lo
y
ed
t
o
b
alan
ce
d
ata
with
a
h
ig
h
u
n
b
alan
ce
d
r
atio
.
T
h
e
p
r
im
a
r
y
aim
o
f
SM
OT
E
is
to
p
r
o
d
u
ce
n
ew
s
am
p
l
es
in
th
e
m
in
o
r
ity
class
d
ata
t
h
r
o
u
g
h
i
n
ter
p
o
latio
n
am
o
n
g
s
am
p
les
o
f
class
es
th
at
ar
e
n
ea
r
er
to
ea
c
h
o
th
e
r
.
I
n
itially
,
th
e
th
at
is
th
e
ch
o
s
en
q
u
an
tity
o
f
o
v
er
s
am
p
lin
g
is
s
et
to
an
i
n
teg
er
n
u
m
b
er
.
T
h
is
n
u
m
b
er
is
s
elec
ted
to
b
ala
n
ce
th
e
d
ataset,
a
ch
iev
in
g
a
1
:1
r
atio
ac
r
o
s
s
v
ar
io
u
s
class
es
.
Nex
t,
t
h
r
ee
m
ajo
r
p
h
ases
ar
e
co
n
s
id
er
ed
iter
ativ
ely
.
T
h
ese
p
h
ases
ar
e
r
an
d
o
m
s
elec
tio
n
o
f
s
am
p
les
th
at
b
elo
n
g
to
t
h
e
m
in
o
r
ity
class
.
T
h
e
k
-
n
ea
r
est
n
eig
h
b
o
r
s
o
f
th
e
s
am
p
le
ar
e
c
h
o
s
en
,
an
d
t
h
e
o
f
th
ese
n
eig
h
b
o
r
s
ar
e
ch
o
s
en
r
a
n
d
o
m
ly
f
o
r
i
n
ter
p
o
latio
n
an
d
p
r
o
d
u
cin
g
n
ew
s
am
p
les
.
2
.
2
.
2
.
Nea
r
M
is
s
t
ec
hn
iq
ue
T
h
is
tech
n
iq
u
e
b
alan
ce
s
class
d
is
tr
ib
u
tio
n
to
class
if
icatio
n
d
atasets
wi
th
s
k
ewe
d
clas
s
d
i
s
tr
ib
u
tio
n
ca
lled
as
u
n
d
e
r
-
s
am
p
lin
g
.
Fo
r
b
alan
ci
n
g
class
d
is
tr
ib
u
ti
o
n
,
u
n
d
er
-
s
am
p
lin
g
elim
in
at
es
tr
ain
in
g
d
ataset
s
am
p
les
th
at
p
er
tain
to
th
e
m
ajo
r
ity
class
lik
e
m
in
im
izin
g
s
k
ew
f
r
o
m
a
1
:
1
0
0
t
o
a
1
:
1
0
,
1
:
2
o
r
1
:1
class
d
is
tr
ib
u
tio
n
.
Fo
r
ev
al
u
atin
g
th
e
in
f
lu
en
ce
o
f
th
e
d
ata
-
p
o
in
t
t
ec
h
n
iq
u
e,
th
is
ar
ticle
u
tili
ze
s
an
u
n
d
er
-
s
am
p
lin
g
s
tr
ateg
y
d
ep
e
n
d
ed
o
n
a
Nea
r
Miss
tec
h
n
iq
u
e
.
Nea
r
Miss
is
s
elec
ted
d
ep
en
d
in
g
o
n
th
e
b
en
ef
its
o
f
p
r
o
v
id
in
g
a
m
u
ch
m
o
r
e
r
o
b
u
s
t
an
d
f
air
cla
s
s
d
is
tr
ib
u
tio
n
b
o
u
n
d
a
r
y
th
at
i
s
id
en
tifie
d
to
en
h
an
ce
class
if
ier
p
er
f
o
r
m
an
ce
to
d
etec
t la
r
g
e
-
s
ca
le
im
b
alan
ce
d
d
ata
.
2
.
2
.
3
.
Sta
nd
a
rdiza
t
io
n
T
h
e
s
tan
d
ar
d
izatio
n
[
2
4
]
o
f
d
a
ta
r
em
o
v
es
th
e
in
f
lu
e
n
ce
o
f
v
a
r
y
in
g
s
ca
les
o
f
v
ar
io
u
s
elem
en
ts
o
n
s
tep
s
izes
an
d
av
o
id
s
u
n
wan
ted
o
v
er
h
ea
d
.
Stan
d
ar
d
izatio
n
en
s
u
r
es
0
m
ea
n
an
d
1
s
tan
d
ar
d
d
e
v
iatio
n
,
p
r
o
v
i
d
in
g
an
ad
v
an
tag
e
f
o
r
s
tatis
tical
an
aly
s
is
.
T
h
e
m
ath
em
atica
l
eq
u
atio
n
f
o
r
s
tan
d
ar
d
izatio
n
is
g
iv
en
in
(
1
)
.
I
n
(
1
)
,
is
th
e
ac
tu
al
d
ata,
is
th
e
m
ea
n
,
is
th
e
s
tan
d
ar
d
d
e
v
iatio
n
,
an
d
is
s
tan
d
ar
d
ized
d
ata
.
=
−
(
1
)
2
.
3
.
Cla
s
s
if
ica
t
io
n
G
R
U
i
s
a
d
v
a
n
c
e
d
v
e
r
s
i
o
n
o
f
R
N
N
w
it
h
a
g
a
t
i
n
g
m
e
c
h
a
n
i
s
m
an
d
c
l
o
s
e
r
t
o
t
h
e
s
ta
n
d
a
r
d
L
S
T
M
n
e
t
w
o
r
k
,
b
u
t
w
i
t
h
f
e
w
e
r
t
r
a
i
n
i
n
g
p
a
r
a
m
e
t
e
r
s
.
GR
U
is
a
v
e
r
y
s
u
i
ta
b
l
e
R
N
N
v
e
r
s
i
o
n
f
o
r
s
h
o
r
t
s
e
q
u
e
n
c
es
o
f
i
n
p
u
t
d
a
t
a
[2
5
]
.
G
R
U
i
n
v
o
l
v
es
t
w
o
g
a
t
es
s
u
c
h
a
s
u
p
d
a
t
e
g
a
t
e
w
h
i
c
h
s
u
p
p
o
r
t
s
t
o
d
e
t
e
r
m
i
n
e
h
o
w
m
u
c
h
i
n
f
o
r
m
a
t
i
o
n
i
s
f
o
r
w
a
r
d
e
d
b
a
s
e
d
o
n
p
a
s
t
ti
m
e
s
t
e
p
s
.
T
h
e
r
e
s
e
t
g
at
e
a
i
m
s
t
o
i
d
e
n
ti
f
y
t
h
e
am
o
u
n
t
o
f
d
a
t
a
t
h
a
t
is
r
e
m
o
v
e
d
f
r
o
m
t
h
e
p
a
s
t
.
Ad
d
itio
n
ally
,
t
h
e
GR
U
d
etac
h
es
th
e
ce
ll
s
tate,
a
n
d
d
ata
is
tr
an
s
f
er
r
e
d
th
r
o
u
g
h
a
h
id
d
en
s
tate
.
T
h
e
p
ar
am
eter
s
co
n
s
id
er
ed
in
th
i
s
m
an
u
s
cr
ip
t
f
o
r
GR
U
ar
e
2
0
E
p
o
ch
s
,
s
p
ar
s
e
ca
teg
o
r
ical
cr
o
s
s
en
tr
o
p
y
l
o
s
s
f
u
n
ctio
n
,
3
2
b
atch
s
ize,
Ad
a
m
o
p
tim
izer
,
a
n
d
So
f
tMa
x
ac
tiv
atio
n
f
u
n
ctio
n
.
T
h
is
r
esear
ch
ex
p
l
o
r
es
th
e
ef
f
ec
tiv
en
ess
o
f
ZR
in
th
e
G
R
U
m
eth
o
d
in
teg
r
ated
with
c
lass
im
b
alan
ce
h
an
d
lin
g
tech
n
iq
u
es
lik
e
SMOT
E
an
d
Nea
r
Miss
o
v
er
m
u
ltip
le
d
atasets
.
Z
o
n
eo
u
t
is
p
ar
ticu
lar
ly
s
elec
ted
o
v
er
o
th
er
r
eg
u
lar
i
za
tio
n
s
lik
e
d
r
o
p
o
u
t
an
d
b
atch
n
o
r
m
aliza
tio
n
b
ec
a
u
s
e
o
f
its
tem
p
o
r
al
co
n
s
is
ten
cy
-
p
r
eser
v
i
n
g
n
atu
r
e,
wh
ich
is
s
u
itab
le
f
o
r
GR
U
u
s
ed
in
NI
DS
.
T
h
e
elem
en
ts
p
r
esen
ted
in
th
e
GR
U
ar
ch
itectu
r
e
ar
e
d
escr
ib
ed
as
f
o
llo
ws
.
T
h
e
ex
ter
n
al
in
p
u
t
d
ata
r
ep
r
esen
te
d
as
at
tim
e
s
t
ep
.
T
h
e
h
id
d
en
s
tate
is
r
ep
r
es
en
ted
as
ℎ
−
1
at
th
e
p
ast
tim
e
s
tep
−
1
.
T
h
e
r
eset
g
ate
m
an
ag
es
th
e
am
o
u
n
t
o
f
p
r
ev
io
u
s
d
ata,
wh
ich
is
f
o
r
g
o
tten
af
ter
th
e
p
o
in
t
-
by
-
p
o
in
t
m
u
ltip
licatio
n
th
r
o
u
g
h
ℎ
−
1
.
T
h
e
r
esu
lt
o
f
th
e
u
p
d
ate
g
ate
with
th
e
s
ig
m
o
id
f
u
n
ctio
n
id
en
tifie
s
th
e
am
o
u
n
t
o
f
d
ata
o
f
t
h
e
p
r
ev
io
u
s
h
id
d
e
n
lay
e
r
,
wh
ic
h
is
p
r
o
ce
s
s
ed
i
n
th
e
co
n
s
ec
u
ti
v
e
h
id
d
en
s
tate
.
T
h
e
ca
n
d
id
at
e
ac
tiv
atio
n
v
ec
to
r
,
wh
ich
u
tili
ze
s
th
e
r
eset
g
ate
v
ec
to
r
f
o
r
co
n
s
er
v
in
g
p
r
e
v
io
u
s
s
ig
n
if
ican
t
d
ata
.
T
h
e
co
n
s
ec
u
tiv
e
h
id
d
en
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2252
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
2
,
Ap
r
il 2
0
2
6
:
1
5
0
5
-
1
5
1
2
1508
s
tate
v
alu
e
ℎ
is
s
im
ilar
to
th
e
o
u
tco
m
e
.
E
v
er
y
ca
n
d
id
ate
ac
tiv
atio
n
v
ec
to
r
a
n
d
in
ter
n
al
g
at
e
in
th
e
GR
U
ce
ll f
o
r
ev
er
y
n
ew
in
p
u
t d
ata
a
t tim
e
co
m
p
u
tes ce
r
tain
s
ig
n
if
ican
t u
p
d
ates,
g
iv
e
n
in
(
2
)
to
(
4
)
.
=
(
+
ℎ
−
1
+
)
(
2
)
=
(
+
ℎ
−
1
+
)
(
3
)
=
ℎ
(
+
(
⊗
ℎ
−
1
)
+
)
(
4
)
W
h
er
e
r
ep
r
esen
ts
th
e
p
r
esen
t
in
p
u
t
u
tili
zin
g
weig
h
t
m
atr
i
x
,
ℎ
−
1
r
ep
r
esen
ts
p
ast
h
id
d
en
s
tate
wit
h
weig
h
t
m
atr
ix
,
r
ep
r
esen
ts
th
e
b
ias
ter
m
f
o
r
r
esu
lt
ac
tiv
ati
o
n
,
an
d
r
ep
r
esen
ts
th
e
s
ig
m
o
id
ac
tiv
atio
n
f
u
n
ctio
n
,
wh
ich
e
n
s
u
r
es
v
alu
e
b
etwe
en
0
an
d
1
.
r
ep
r
esen
ts
th
e
p
r
esen
t
in
p
u
t
to
th
e
r
eset
g
ate,
ℎ
−
1
r
ep
r
esen
ts
p
r
ev
io
u
s
h
id
d
e
n
s
tate
to
a
r
eset
g
ate,
an
d
is
b
ias
ter
m
o
f
a
r
eset
g
ate
.
r
ep
r
esen
ts
th
e
p
r
esen
t
in
p
u
t
o
f
th
e
ca
n
d
id
ate
s
tate,
(
⊗
ℎ
−
1
)
r
ep
r
esen
ts
th
e
p
r
ev
io
u
s
h
id
d
en
s
tate
o
f
t
h
e
ca
n
d
id
at
e
s
tate,
r
ep
r
esen
ts
r
eset
g
ate
th
at
h
an
d
les
h
o
w
m
u
c
h
o
f
p
ast
h
id
d
en
s
tate
is
u
tili
ze
d
,
⊗
r
ep
r
esen
ts
elem
en
t
-
wis
e
m
u
ltip
licatio
n
,
r
ep
r
esen
ts
b
ias
ter
m
o
f
a
c
an
d
id
ate
h
id
d
en
s
tate,
an
d
ℎ
is
ac
tiv
atio
n
f
u
n
ctio
n
.
T
h
r
o
u
g
h
m
an
ip
u
latin
g
a
v
ec
t
o
r
o
f
th
e
u
p
d
ate
g
ate
,
th
e
f
u
r
th
er
h
i
d
d
en
la
y
er
an
d
th
e
last
o
u
tco
m
e
o
f
th
e
GR
U
ce
ll
u
n
it
ar
e
attain
ed
,
an
d
its
m
ath
em
atica
l
f
o
r
m
u
la
is
g
iv
en
as
(
5
)
.
I
n
(
5
)
,
ℎ
r
ep
r
esen
ts
th
e
h
id
d
en
s
tate
at
tim
e
,
r
ep
r
esen
ts
o
u
tp
u
t
g
ate
at
tim
e
,
r
ep
r
esen
t
s
th
e
ca
n
d
id
ate
h
id
d
en
s
tate,
(
1
−
)
r
ep
r
esen
ts
th
e
co
m
p
lem
en
t o
f
th
e
o
u
tp
u
t g
ate,
an
d
⨂
r
ep
r
esen
t
s
elem
en
t
-
wis
e
m
u
ltip
licatio
n
.
ℎ
=
⊗
+
(
1
−
)
⨂
ℎ
−
1
(
5
)
2
.
3
.
1
.
Z
o
neo
ut
re
g
ula
riza
t
io
n
Z
o
n
eo
u
t
is
p
ar
ticu
lar
ly
s
elec
ted
o
v
e
r
o
t
h
er
r
e
g
u
lar
izatio
n
s
lik
e
d
r
o
p
o
u
t
an
d
b
atc
h
n
o
r
m
aliza
tio
n
b
ec
au
s
e
o
f
its
tem
p
o
r
al
co
n
s
is
ten
cy
-
p
r
eser
v
in
g
n
atu
r
e,
wh
ich
is
s
u
itab
le
f
o
r
GR
U
u
s
ed
in
NI
DS
.
Un
lik
e
d
r
o
p
o
u
t
t
h
at
r
a
n
d
o
m
l
y
d
ea
cti
v
ates
n
eu
r
o
n
s
an
d
d
is
r
u
p
ts
s
e
q
u
en
ce
co
n
tin
u
ity
.
ZR
r
an
d
o
m
ly
p
r
eser
v
es
p
ast
h
id
d
en
s
tates a
n
d
h
an
d
les s
eq
u
en
tial in
teg
r
ity
,
wh
ich
is
ess
en
tial in
n
etwo
r
k
tr
af
f
ic
d
ata
.
B
atch
n
o
r
m
aliza
tio
n
is
ef
f
ici
en
t
in
f
ee
d
f
o
r
war
d
n
etwo
r
k
s
b
u
t
u
n
d
er
p
e
r
f
o
r
m
s
in
R
NNs
d
u
e
to
d
if
f
icu
lties
in
em
p
lo
y
in
g
co
n
s
is
ten
t
n
o
r
m
aliza
tio
n
o
v
er
tim
e
s
tep
s
.
Z
R
o
u
tp
er
f
o
r
m
s
d
r
o
p
o
u
t
-
GR
U
an
d
co
n
v
en
tio
n
al
GR
U
m
eth
o
d
s
.
I
n
ev
er
y
tim
estep
,
z
o
n
eo
u
t
s
to
ch
asti
ca
lly
f
o
r
ce
s
ce
r
tain
h
id
d
en
u
n
its
to
h
an
d
le
th
eir
p
ast
s
co
r
es
.
Un
lik
e
d
r
o
p
o
u
t,
zo
n
e
o
u
t
u
tili
ze
s
r
an
d
o
m
n
o
is
e
f
o
r
tr
ain
i
n
g
a
p
s
eu
d
o
-
en
s
e
m
b
le
an
d
im
p
r
o
v
es
g
en
er
aliza
tio
n
ab
ilit
y
.
T
h
r
o
u
g
h
p
r
o
tectin
g
r
ath
er
th
an
d
r
o
p
p
in
g
h
id
d
en
u
n
its
,
g
r
ad
ien
ts
,
an
d
s
tate
d
ata
ar
e
q
u
ick
ly
p
r
o
p
a
g
ated
o
v
er
tim
e
in
f
ee
d
f
o
r
war
d
s
to
ch
asti
c
d
e
p
th
n
etwo
r
k
s
.
B
y
in
c
o
r
p
o
r
atin
g
Z
R
in
to
GR
U,
m
in
im
izes
o
v
er
f
itti
n
g
o
f
th
e
m
o
d
el
b
y
r
ely
in
g
o
n
s
o
m
e
f
ea
tu
r
es
an
d
p
r
o
v
id
es
g
o
o
d
g
en
er
aliza
tio
n
b
y
m
ain
tain
in
g
d
i
v
er
s
ity
in
r
e
p
r
esen
tatio
n
.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
Z
R
-
G
R
U
alg
o
r
ith
m
is
s
im
u
lated
in
a
Py
th
o
n
e
n
v
ir
o
n
m
en
t,
an
d
t
h
e
r
eq
u
ir
e
d
s
y
s
tem
co
n
f
ig
u
r
atio
n
s
ar
e
a
n
i
5
p
r
o
ce
s
s
o
r
,
8
GB
R
AM
,
an
d
W
in
d
o
ws
1
0
(
6
4
-
b
it)
.
Data
s
et
s
am
p
les
ar
e
s
p
lit
in
an
8
0
:2
0
f
o
r
tr
ain
in
g
an
d
test
in
g
s
ets
.
E
v
alu
atio
n
m
etr
ics
l
ik
e
ac
cu
r
ac
y
,
r
ec
all,
F1
-
s
co
r
e
,
an
d
p
r
ec
is
io
n
ar
e
tak
en
to
an
al
y
ze
th
e
p
e
r
f
o
r
m
a
n
ce
o
f
th
e
Z
R
-
GR
U
alg
o
r
ith
m
.
I
n
T
ab
le
1
,
t
h
e
p
er
f
o
r
m
an
ce
o
f
SMOT
E
+
Nea
r
Miss
b
alan
cin
g
tech
n
i
q
u
e
is
ev
al
u
ated
u
s
in
g
th
r
ee
b
en
ch
m
ar
k
d
atasets
.
R
an
d
o
m
u
n
d
er
s
am
p
lin
g
,
Ad
aSy
n
,
tr
ad
itio
n
al
Nea
r
Miss
,
an
d
SMOT
E
ar
e
tak
en
to
ev
alu
ate
a
p
e
r
f
o
r
m
an
ce
o
f
S
MO
T
E
+
Nea
r
Miss
b
alan
cin
g
tech
n
iq
u
e.
SMOT
E
+
Nea
r
Miss
tech
n
iq
u
e
attain
ed
h
ig
h
ac
cu
r
ac
y
o
n
UNSW
-
NB
1
5
,
C
I
C
-
I
DS2
0
1
8
,
a
n
d
C
I
C
-
DDo
S2
0
1
9
d
atasets
r
esp
ec
tiv
ely
.
I
n
T
ab
le
2
,
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
GR
U
with
zo
n
eo
u
t
tec
h
n
iq
u
e
is
ev
alu
ated
u
s
in
g
UNSW
-
N
B
1
5
,
C
I
C
-
I
DS2
0
1
8
,
an
d
C
I
C
-
DDo
S2
0
1
9
with
d
if
f
er
e
n
t
m
etr
ics.
T
h
e
tr
ad
itio
n
al
GR
U,
GR
U+
d
r
o
p
o
u
t,
GR
U+
L
2
,
an
d
GR
U+
L
1
ar
e
tak
en
to
ev
alu
ate
th
e
p
e
r
f
o
r
m
an
ce
o
f
GR
U
with
zo
n
eo
u
t
tech
n
i
q
u
e.
I
n
T
ab
le
3
,
th
e
p
er
f
o
r
m
an
ce
o
f
Z
R
-
GR
U
tec
h
n
iq
u
e
is
ev
alu
ated
u
s
in
g
th
r
ee
v
ar
io
u
s
in
tr
u
s
io
n
d
atasets
.
T
h
e
R
NN,
L
STM
,
Bi
-
L
STM
,
an
d
tr
ad
itio
n
al
GR
U
ar
e
tak
en
to
e
v
alu
ate
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
Z
R
-
GR
U
tech
n
iq
u
e.
3
.
1
.
Co
m
pa
ra
t
iv
e
a
na
ly
s
is
Per
f
o
r
m
an
ce
o
f
Z
R
-
GR
U
tech
n
iq
u
e
is
co
m
p
ar
ed
to
ex
i
s
tin
g
tech
n
iq
u
es
lik
e
ad
ap
ti
v
e
tr
an
s
f
er
lear
n
in
g
[
1
6
]
,
C
NN
-
B
iLST
M
[
1
7
]
,
h
y
b
r
i
d
f
r
am
ewo
r
k
with
C
FS
-
DE
[
1
8
]
,
I
GR
F
-
R
FE+
ML
P
[
1
9
]
,
an
d
d
ee
p
f
u
s
io
n
m
ec
h
a
n
is
m
[
2
0
]
.
T
h
e
Z
R
-
GR
U
tech
n
iq
u
e
attain
ed
h
ig
h
d
etec
tio
n
ac
cu
r
ac
y
o
n
UNSW
-
NB
1
5
,
C
I
C
-
I
DS2
0
1
8
,
an
d
C
I
C
-
DDo
S2
0
1
9
d
atasets
wh
en
c
o
m
p
a
r
e
d
to
ex
is
tin
g
tr
a
d
itio
n
al
d
etec
t
io
n
m
o
d
els.
T
a
b
le
4
r
ep
r
esen
ts
th
e
co
m
p
ar
ativ
e
an
aly
s
is
o
f
th
e
p
r
o
p
o
s
ed
Z
R
-
GR
U
alg
o
r
ith
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
Zo
n
eo
u
t reg
u
la
r
iz
a
tio
n
-
g
a
ted
r
ec
u
r
r
en
t u
n
it a
lg
o
r
ith
m
o
n
N
I
DS
w
ith
cla
s
s
imb
a
la
n
ce
…
(
Ma
la
K
a
r
iya
p
p
a
)
1509
3
.
2
.
Dis
cus
s
io
n
T
h
e
p
er
f
o
r
m
an
ce
an
d
r
esu
lts
o
f
a
p
r
o
p
o
s
ed
alg
o
r
ith
m
ar
e
ev
alu
ated
with
th
r
ee
d
atasets
u
s
in
g
d
if
f
er
en
t
class
b
alan
cin
g
tech
n
iq
u
es
an
d
class
if
ier
s
.
Mo
r
eo
v
er
,
th
e
p
e
r
f
o
r
m
an
ce
o
f
a
d
e
v
elo
p
ed
tec
h
n
iq
u
e
is
co
m
p
ar
ed
with
o
th
er
ex
is
tin
g
tech
n
iq
u
es,
lik
e
ad
ap
tiv
e
tr
a
n
s
f
er
lear
n
in
g
[
1
6
]
,
C
NN
-
B
i
L
STM
[
1
7
]
,
h
y
b
r
id
f
r
am
ewo
r
k
with
C
FS
-
DE
[
1
8
]
,
I
GR
F
-
R
FE+
ML
P
[
1
9
]
,
an
d
d
ee
p
f
u
s
io
n
m
ec
h
an
is
m
[
2
0
]
.
T
h
e
ex
is
tin
g
m
o
d
el
s
tr
u
g
g
led
to
h
an
d
le
th
e
class
i
m
b
alan
ce
is
s
u
e
d
u
r
in
g
th
e
p
r
o
ce
s
s
o
f
class
if
icatio
n
d
u
e
to
th
eir
b
iased
n
atu
r
e,
wh
ich
r
ed
u
ce
d
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
m
o
d
els.
I
n
th
is
p
ap
e
r
,
th
e
Z
R
-
GR
U
alg
o
r
ith
m
is
d
ev
elo
p
ed
t
o
d
etec
t
an
d
class
if
y
in
tr
u
s
io
n
s
in
th
e
n
etwo
r
k
.
I
n
c
o
r
p
o
r
atin
g
Z
R
in
GR
U
m
in
im
izes
o
v
er
f
itti
n
g
b
y
p
r
ev
e
n
tin
g
t
h
e
m
o
d
el
f
r
o
m
o
v
er
-
r
ely
in
g
o
n
s
p
ec
if
ic
f
ea
tu
r
es
wh
ile
p
r
o
v
id
i
n
g
g
o
o
d
g
en
e
r
aliza
tio
n
b
y
p
r
e
s
er
v
in
g
d
iv
e
r
s
ity
in
th
e
lear
n
ed
r
ep
r
esen
tatio
n
.
S
MO
T
E
an
d
Nea
r
Miss
m
eth
o
d
s
ar
e
u
tili
ze
d
to
b
alan
ce
th
e
s
am
p
les
in
th
e
d
ataset,
wh
ich
h
elp
s
im
p
r
o
v
e
class
if
ier
p
er
f
o
r
m
an
ce
in
NI
DS.
T
ab
le
1
.
Per
f
o
r
m
an
ce
o
f
SMO
T
E
+
Nea
r
Miss
b
alan
cin
g
tech
n
iq
u
e
D
a
t
a
s
e
t
s
M
e
t
h
o
d
s
A
c
c
u
r
a
c
y
(
%)
P
r
e
c
i
s
i
o
n
(
%)
R
e
c
a
l
l
(
%)
F1
-
sc
o
r
e
(
%)
U
N
S
W
-
N
B
1
5
N
e
a
r
M
i
ss
9
3
.
8
1
8
9
.
5
5
8
9
.
9
4
8
9
.
7
R
a
n
d
o
m
u
n
d
e
r
sa
mp
l
i
n
g
9
5
.
2
1
9
1
.
3
5
9
1
.
8
4
9
1
.
7
A
d
a
S
y
n
9
7
.
2
1
9
2
.
6
5
9
3
.
2
4
9
2
.
8
S
M
O
TE
9
8
.
6
1
9
3
.
6
5
9
4
.
8
4
9
3
.
9
S
M
O
TE+
N
e
a
r
M
i
s
s
9
9
.
9
1
9
5
.
4
5
9
6
.
2
4
9
5
.
8
C
I
C
-
I
D
S
2
0
1
8
N
e
a
r
M
i
ss
9
2
.
3
2
9
4
.
2
3
9
3
.
6
2
9
4
.
7
2
R
a
n
d
o
m
u
n
d
e
r
sa
mp
l
i
n
g
9
4
.
0
2
9
5
.
3
3
9
5
.
4
2
9
6
.
0
2
A
d
a
S
y
n
9
6
.
0
2
9
7
.
3
3
9
6
.
9
2
9
7
.
1
2
S
M
O
TE
9
8
.
0
2
9
8
.
4
3
9
8
.
8
2
9
8
.
4
2
S
M
O
TE+
N
e
a
r
M
i
s
s
9
9
.
9
2
9
9
.
9
3
9
9
.
9
2
9
9
.
9
2
C
I
C
-
D
D
o
S
2
0
1
9
N
e
a
r
M
i
ss
9
2
.
7
4
9
3
.
6
2
9
4
.
5
8
9
3
.
4
R
a
n
d
o
m
u
n
d
e
r
sa
mp
l
i
n
g
9
4
.
5
4
9
5
.
5
2
9
5
.
6
8
9
5
.
1
A
d
a
S
y
n
9
6
.
1
4
9
6
.
5
2
9
7
.
4
8
9
6
.
8
S
M
O
TE
9
7
.
2
4
9
8
.
0
2
9
8
.
6
8
9
7
.
8
S
M
O
TE+
N
e
a
r
M
i
s
s
9
9
.
1
4
9
9
.
7
2
9
9
.
6
8
9
9
.
7
T
ab
le
2
.
Per
f
o
r
m
an
ce
o
f
d
if
f
er
en
t r
eg
u
lar
izatio
n
alg
o
r
ith
m
s
D
a
t
a
s
e
t
s
M
e
t
h
o
d
s
A
c
c
u
r
a
c
y
(
%)
P
r
e
c
i
s
i
o
n
(
%)
R
e
c
a
l
l
(
%)
F1
-
sc
o
r
e
(
%)
U
N
S
W
-
N
B
1
5
G
R
U
9
2
.
3
1
9
0
.
6
5
9
1
.
0
2
9
0
.
8
1
G
R
U
+
d
r
o
p
o
u
t
9
4
.
0
2
9
1
.
3
4
9
1
.
9
2
9
1
.
6
2
G
R
U
+
L
2
9
5
.
2
7
9
2
.
1
2
9
2
.
6
5
9
2
.
3
7
G
R
U
+
L
1
9
4
.
7
5
9
1
.
5
4
9
1
.
9
2
9
1
.
6
4
G
R
U
w
i
t
h
z
o
n
e
o
u
t
9
9
.
9
1
9
5
.
4
5
9
6
.
2
4
9
5
.
8
0
C
I
C
-
I
D
S
2
0
1
8
G
R
U
9
5
.
7
4
9
5
.
6
8
9
5
.
9
2
9
5
.
5
9
G
R
U
+
d
r
o
p
o
u
t
9
6
.
8
3
9
6
.
3
4
9
6
.
9
1
9
6
.
5
1
G
R
U
+
L
2
9
7
.
6
5
9
7
.
4
3
9
7
.
8
8
9
7
.
5
4
G
R
U
+
L
1
9
7
.
2
1
9
7
.
0
2
9
7
.
5
6
9
7
.
0
8
G
R
U
w
i
t
h
z
o
n
e
o
u
t
9
9
.
9
2
9
9
.
9
3
9
9
.
9
2
9
9
.
9
2
C
I
C
-
D
D
o
S
2
0
1
9
G
R
U
9
4
.
8
3
9
4
.
2
1
9
4
.
5
6
9
4
.
3
6
G
R
U
+
D
r
o
p
o
u
t
9
6
.
1
8
9
6
.
1
2
9
6
.
4
5
9
6
.
1
9
G
R
U
+
L
2
9
6
.
9
2
9
6
.
7
1
9
6
.
8
5
9
6
.
7
4
G
R
U
+
L
1
9
6
.
5
4
9
6
.
0
2
9
6
.
4
4
9
6
.
1
0
G
R
U
w
i
t
h
z
o
n
e
o
u
t
9
9
.
1
4
9
9
.
7
2
9
9
.
6
8
9
9
.
7
0
T
ab
le
3
.
Per
f
o
r
m
an
ce
o
f
Z
R
-
GR
U
clas
s
if
ier
D
a
t
a
s
e
t
s
M
e
t
h
o
d
s
A
c
c
u
r
a
c
y
(
%)
P
r
e
c
i
s
i
o
n
(
%)
R
e
c
a
l
l
(
%)
F1
-
sc
o
r
e
(
%)
U
N
S
W
-
N
B
1
5
R
N
N
9
7
.
3
1
9
2
.
0
5
9
2
.
6
4
9
3
.
0
0
LSTM
9
7
.
8
1
9
2
.
9
5
9
3
.
6
4
9
3
.
5
0
B
i
LST
M
9
8
.
3
1
9
3
.
8
5
9
4
.
6
4
9
4
.
0
0
G
R
U
9
8
.
9
1
9
4
.
7
5
9
5
.
2
4
9
4
.
9
0
ZR
-
G
R
U
9
9
.
9
1
9
5
.
4
5
9
6
.
2
4
9
5
.
8
0
C
I
C
I
D
S
2
0
1
8
R
N
N
9
7
.
2
2
9
6
.
4
3
9
7
.
3
2
9
6
.
4
2
LSTM
9
7
.
7
2
9
7
.
2
3
9
7
.
9
2
9
7
.
3
2
B
i
LST
M
9
8
.
6
2
9
8
.
1
3
9
8
.
7
2
9
8
.
3
2
G
R
U
9
9
.
3
2
9
8
.
9
3
9
9
.
2
2
9
9
.
2
2
ZR
-
G
R
U
9
9
.
9
2
9
9
.
9
3
9
9
.
9
2
9
9
.
9
2
C
I
C
-
D
D
o
S
2
0
1
9
R
N
N
9
8
.
9
1
9
4
.
7
5
9
5
.
2
4
9
4
.
9
0
LSTM
9
7
.
2
4
9
7
.
7
2
9
7
.
3
8
9
7
.
5
0
B
i
LST
M
9
7
.
9
4
9
8
.
2
2
9
8
.
3
8
9
8
.
2
0
G
R
U
9
8
.
5
4
9
9
.
1
2
9
9
.
1
8
9
8
.
7
0
ZR
-
G
R
U
9
9
.
1
4
9
9
.
7
2
9
9
.
6
8
9
9
.
7
0
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2252
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
2
,
Ap
r
il 2
0
2
6
:
1
5
0
5
-
1
5
1
2
1510
T
ab
le
4
.
C
o
m
p
a
r
ativ
e
an
aly
s
is
o
f
Z
R
-
GR
U
alg
o
r
ith
m
D
a
t
a
s
e
t
s
M
e
t
h
o
d
s
A
c
c
u
r
a
c
y
(
%)
P
r
e
c
i
s
i
o
n
(
%)
R
e
c
a
l
l
(
%)
F1
-
sc
o
r
e
(
%)
U
N
S
W
-
N
B
1
5
A
d
a
p
t
i
v
e
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
[
1
6
]
99
.
84
NA
NA
NA
I
G
R
F
-
R
F
E+
M
LP
[
1
9
]
84
.
24
NA
NA
82
.
85
D
e
e
p
f
u
s
i
o
n
m
e
c
h
a
n
i
sm
[
2
0
]
77
.
84
86
.
04
69
.
50
NA
P
r
o
p
o
se
d
Z
R
-
G
R
U
a
l
g
o
r
i
t
h
m
99
.
91
95
.
45
96
.
24
95
.
8
C
I
C
-
D
D
O
S
2
0
1
9
A
d
a
p
t
i
v
e
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
[
1
6
]
93
.
62
NA
NA
NA
C
N
N
-
B
i
LS
TM
[
1
7
]
95
.
67
95
.
82
95
.
90
95
.
86
P
r
o
p
o
se
d
Z
R
-
G
R
U
a
l
g
o
r
i
t
h
m
99
.
14
99
.
72
99
.
68
99
.
70
C
I
C
I
D
S
2
0
1
8
A
d
a
p
t
i
v
e
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
[
1
6
]
99
.
92
NA
NA
NA
H
y
b
r
i
d
f
r
a
mew
o
r
k
w
i
t
h
C
F
S
-
D
E
[
1
8
]
99
.
87
99
.
88
99
.
87
99
.
88
P
r
o
p
o
se
d
Z
R
-
G
R
U
a
l
g
o
r
i
t
h
m
99
.
92
99
.
93
99
.
92
99
.
92
4.
CO
NCLU
SI
O
N
T
h
i
s
r
e
s
e
ar
ch
i
n
tr
o
d
u
ce
d
c
la
s
s
b
a
l
a
n
c
in
g
t
e
ch
n
iq
u
e
s
an
d
a
D
L
-
b
a
s
e
d
a
lg
o
r
i
t
h
m
f
o
r
d
e
t
e
c
t
in
g
n
e
t
w
o
r
k
in
t
r
u
s
i
o
n
s
an
d
o
b
ta
in
i
n
g
h
ig
h
ac
c
u
r
a
c
y
.
I
n
i
t
i
a
l
l
y
,
t
h
e
c
l
a
s
s
e
s
w
e
r
e
b
a
l
an
c
ed
u
s
i
n
g
S
M
O
T
E
an
d
N
e
a
r
M
i
s
s
t
e
ch
n
iq
u
e
s
,
w
h
ic
h
b
a
l
a
n
c
e
d
t
h
e
s
a
m
p
le
s
i
n
t
h
e
d
a
t
a
s
e
t
.
T
h
e
n
,
t
h
e
b
a
la
n
c
ed
c
l
a
s
s
e
s
ar
e
s
t
a
n
d
ar
d
i
z
ed
u
s
i
n
g
t
h
e
s
t
a
n
d
ar
d
i
z
a
t
io
n
t
e
c
h
n
i
q
u
e
.
N
e
x
t,
t
h
e
s
t
a
n
d
ar
d
i
ze
d
f
e
a
tu
r
e
s
w
er
e
cl
a
s
s
i
f
i
e
d
u
s
i
n
g
t
h
e
ZR
-
G
R
U
t
e
c
h
n
i
q
u
e
w
i
th
h
i
g
h
c
l
a
s
s
i
f
i
ca
t
i
o
n
a
cc
u
r
a
c
y
.
I
n
co
r
p
o
r
at
i
n
g
Z
R
i
n
G
R
U
m
i
n
im
i
z
e
s
o
v
e
r
f
i
t
t
i
n
g
b
y
r
e
l
y
in
g
o
n
s
o
m
e
f
e
a
t
u
r
e
s
an
d
p
r
o
v
i
d
e
s
g
o
o
d
g
e
n
er
a
l
i
z
a
t
io
n
b
y
m
a
i
n
ta
i
n
in
g
d
iv
e
r
s
i
t
y
i
n
r
ep
r
e
s
e
n
t
a
t
i
o
n
.
T
h
e
ZR
-
G
R
U
a
l
g
o
r
i
th
m
m
in
i
m
i
ze
s
o
v
e
r
f
i
t
t
i
n
g
a
n
d
t
h
e
g
r
ad
i
e
n
t
v
a
n
i
s
h
in
g
i
s
s
u
e
d
u
r
i
n
g
t
h
e
tr
ai
n
i
n
g
p
r
o
c
e
s
s
t
h
a
t
h
e
l
p
s
t
o
e
n
h
a
n
c
e
t
h
e
c
l
a
s
s
i
f
i
c
a
t
i
o
n
p
e
r
f
o
r
m
a
n
ce
o
f
N
I
D
S
.
T
h
e
Z
R
-
G
R
U
t
e
ch
n
iq
u
e
a
t
t
a
i
n
ed
9
9
.
9
1
%
,
99
.
92%
,
an
d
9
9
.
1
4
%
a
c
c
u
r
ac
y
o
n
U
N
S
W
-
N
B
1
5
,
C
I
C
-
I
D
S
2
0
1
8
,
an
d
C
I
C
-
D
D
o
S2
0
1
9
d
a
t
a
s
e
t
s
.
I
n
t
h
e
f
u
t
u
r
e
,
a
f
e
a
tu
r
e
s
e
l
ec
t
i
o
n
p
h
a
s
e
w
i
l
l
b
e
u
s
ed
t
o
r
e
d
u
c
e
ir
r
e
l
e
v
an
t
a
n
d
i
n
ap
p
r
o
p
r
i
a
te
f
e
at
u
r
e
s
f
o
r
en
h
an
c
in
g
c
l
a
s
s
i
f
i
c
a
t
i
o
n
p
e
r
f
o
r
m
a
n
c
e
.
ACK
NO
WL
E
DG
M
E
N
T
S
T
h
e
au
th
o
r
s
wo
u
ld
lik
e
to
ex
p
r
ess
th
eir
s
in
ce
r
e
th
an
k
s
to
th
e
Dep
ar
tm
en
t
o
f
I
n
f
o
r
m
atio
n
S
cien
ce
an
d
E
n
g
in
ee
r
in
g
,
C
h
an
n
ab
asev
esh
war
a
I
n
s
titu
te
o
f
T
ec
h
n
o
lo
g
y
,
T
u
m
k
u
r
,
an
d
th
e
Dep
ar
tm
e
n
t
o
f
I
n
f
o
r
m
atio
n
Scien
ce
an
d
E
n
g
in
ee
r
in
g
,
Sr
i
Sid
d
h
ar
th
a
I
n
s
titu
te
o
f
T
ec
h
n
o
lo
g
y
,
T
u
m
k
u
r
,
f
o
r
p
r
o
v
id
in
g
th
e
n
ec
ess
ar
y
s
u
p
p
o
r
t a
n
d
f
ac
ilit
ies to
ca
r
r
y
o
u
t th
is
r
esear
ch
wo
r
k
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
Au
th
o
r
s
s
tate
n
o
f
u
n
d
in
g
in
v
o
lv
ed
.
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
T
h
is
jo
u
r
n
al
u
s
es
th
e
C
o
n
tr
ib
u
to
r
R
o
les
T
ax
o
n
o
m
y
(
C
R
ed
iT)
to
r
ec
o
g
n
ize
in
d
iv
id
u
al
au
th
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
th
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
llab
o
r
atio
n
.
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
Ma
la
Kar
iy
ap
p
a
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Ma
n
ju
n
ath
Han
u
m
an
th
a
p
p
a
R
an
g
ap
p
a
✓
✓
✓
✓
✓
✓
✓
✓
Ven
u
g
o
p
al
Dasap
p
a
✓
✓
✓
✓
✓
✓
✓
Gu
r
u
r
aja
Heb
b
u
r
Saty
an
ar
ay
an
a
✓
✓
✓
✓
✓
✓
✓
✓
Gir
is
h
Kesh
av
a
R
ao
✓
✓
✓
✓
✓
✓
✓
✓
Go
u
s
ia
T
h
ah
n
iy
at
h
✓
✓
✓
✓
✓
✓
✓
✓
✓
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 Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
Zo
n
eo
u
t reg
u
la
r
iz
a
tio
n
-
g
a
ted
r
ec
u
r
r
en
t u
n
it a
lg
o
r
ith
m
o
n
N
I
DS
w
ith
cla
s
s
imb
a
la
n
ce
…
(
Ma
la
K
a
r
iya
p
p
a
)
1511
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
Au
th
o
r
s
s
tate
n
o
co
n
f
lict o
f
in
t
er
est
.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
atasets
g
en
er
ated
d
u
r
in
g
th
e
c
u
r
r
en
t
s
tu
d
y
ar
e
av
ailab
le
in
UNSW
S
y
d
n
ey
at
h
ttp
s
://re
s
ea
r
ch
.
u
n
s
w.
ed
u
.
au
/
p
r
o
jects/u
n
s
w
-
nb15
-
d
ataset,
r
e
f
er
en
ce
[
2
0
]
;
Un
iv
e
r
s
ity
o
f
New
B
r
u
n
s
wick
at
h
ttp
s
://www.
u
n
b
.
ca
/cic/d
atasets
/id
s
-
2
0
1
8
.
h
tm
l
,
r
ef
er
en
ce
[
2
1
]
a
n
d
h
ttp
s
://www.
u
n
b
.
ca
/cic/d
atasets
/d
d
o
s
-
2
0
1
9
.
h
tm
l,
r
e
f
er
en
ce
[
2
2
]
.
RE
F
E
R
E
NC
E
S
[
1
]
N
.
Th
o
c
k
c
h
o
m,
M
.
M
.
S
i
n
g
h
,
a
n
d
U
.
N
a
n
d
i
,
“
A
n
o
v
e
l
e
n
sem
b
l
e
l
e
a
r
n
i
n
g
-
b
a
se
d
mo
d
e
l
f
o
r
n
e
t
w
o
r
k
i
n
t
r
u
s
i
o
n
d
e
t
e
c
t
i
o
n
,
”
C
o
m
p
l
e
x
a
n
d
I
n
t
e
l
l
i
g
e
n
t
S
y
st
e
m
s
,
v
o
l
.
9
,
n
o
.
5
,
p
p
.
5
6
9
3
–
5
7
1
4
,
A
p
r
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s
4
0
7
4
7
-
0
2
3
-
0
1
0
1
3
-
7
.
[
2
]
A
.
A
b
d
e
l
k
h
a
l
e
k
a
n
d
M
.
M
a
s
h
a
l
y
,
“
A
d
d
r
e
ss
i
n
g
t
h
e
c
l
a
ss
i
mb
a
l
a
n
c
e
p
r
o
b
l
e
m
i
n
n
e
t
w
o
r
k
i
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
s
y
st
e
ms
u
s
i
n
g
d
a
t
a
r
e
samp
l
i
n
g
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
,
”
J
o
u
r
n
a
l
o
f
S
u
p
e
rc
o
m
p
u
t
i
n
g
,
v
o
l
.
7
9
,
n
o
.
1
0
,
p
p
.
1
0
6
1
1
–
1
0
6
4
4
,
F
e
b
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
2
2
7
-
0
2
3
-
0
5
0
7
3
-
x
.
[
3
]
A
.
K
.
M
a
n
a
n
a
y
a
k
a
a
n
d
S
.
S
.
C
h
u
n
g
,
“
N
e
t
w
o
r
k
i
n
t
r
u
s
i
o
n
d
e
t
e
c
t
i
o
n
w
i
t
h
t
w
o
-
p
h
a
se
d
h
y
b
r
i
d
e
n
s
e
m
b
l
e
l
e
a
r
n
i
n
g
a
n
d
a
u
t
o
m
a
t
i
c
f
e
a
t
u
r
e
s
e
l
e
c
t
i
o
n
,
”
I
E
EE
Ac
c
e
ss
,
v
o
l
.
1
1
,
p
p
.
4
5
1
5
4
–
4
5
1
6
7
,
M
a
y
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
3
.
3
2
7
4
4
7
4
.
[
4
]
Y
.
X
i
e
a
n
d
H
.
C
h
e
n
,
“
A
n
o
v
e
l
me
t
h
o
d
f
o
r
e
f
f
e
c
t
i
v
e
i
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
b
a
s
e
d
o
n
c
o
n
v
o
l
u
t
i
o
n
a
l
sp
e
a
k
i
n
g
n
e
u
r
a
l
n
e
t
w
o
r
k
s
,
”
J
o
u
rn
a
l
o
f
K
i
n
g
S
a
u
d
U
n
i
v
e
r
si
t
y
-
C
o
m
p
u
t
e
r
a
n
d
I
n
f
o
rm
a
t
i
o
n
S
c
i
e
n
c
e
s
,
v
o
l
.
3
6
,
n
o
.
2
,
F
e
b
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
k
s
u
c
i
.
2
0
2
4
.
1
0
1
9
7
5
.
[
5
]
M
.
I
.
T
.
H
u
ssa
n
,
G
.
V
.
R
e
d
d
y
,
P
.
T
.
A
n
i
t
h
a
,
A
.
K
a
n
a
g
a
r
a
j
,
a
n
d
P
.
N
a
r
e
s
h
,
“
D
D
o
S
a
t
t
a
c
k
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
u
s
i
n
g
o
p
t
i
m
i
z
e
d
E
l
ma
n
r
e
c
u
r
r
e
n
t
n
e
u
r
a
l
n
e
t
w
o
r
k
s
b
a
se
d
o
n
c
h
a
o
t
i
c
b
a
c
t
e
r
i
a
l
c
o
l
o
n
y
o
p
t
i
mi
z
a
t
i
o
n
,
”
C
l
u
st
e
r
C
o
m
p
u
t
i
n
g
,
v
o
l
.
2
7
,
n
o
.
4
,
pp
.
4
4
6
9
–
4
4
9
0
,
N
o
v
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
0
5
8
6
-
0
2
3
-
0
4
1
8
7
-
4
.
[
6
]
S
.
S
i
v
a
m
o
h
a
n
a
n
d
S
.
S
.
S
r
i
d
h
a
r
,
“
A
n
o
p
t
i
mi
z
e
d
m
o
d
e
l
f
o
r
n
e
t
w
o
r
k
i
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
sy
st
e
ms
i
n
i
n
d
u
st
r
y
4
.
0
u
si
n
g
X
A
I
b
a
se
d
Bi
-
LST
M
f
r
a
m
e
w
o
r
k
,
”
N
e
u
r
a
l
C
o
m
p
u
t
i
n
g
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
3
5
,
n
o
.
1
5
,
p
p
.
1
1
4
5
9
–
1
1
4
7
5
,
M
a
r
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s
0
0
5
2
1
-
0
2
3
-
0
8
3
1
9
-
0
.
[
7
]
I
.
O
.
-
F
e
r
n
a
n
d
e
z
,
M
.
S
e
s
t
e
l
o
,
J
.
C
.
B
u
r
g
u
i
l
l
o
,
a
n
d
C
.
P
.
-
B
l
a
n
c
o
,
“
N
e
t
w
o
r
k
i
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
s
y
s
t
e
m
f
o
r
D
D
o
S
a
t
t
a
c
k
s
i
n
I
C
S
u
si
n
g
d
e
e
p
a
u
t
o
e
n
c
o
d
e
r
s,”
W
i
re
l
e
ss
N
e
t
w
o
r
k
s
,
v
o
l
.
3
0
,
n
o
.
6
,
p
p
.
5
0
5
9
–
5
0
7
5
,
J
a
n
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
2
7
6
-
0
2
2
-
0
3
2
1
4
-
3
.
[
8
]
A
.
V
.
T
u
r
u
k
m
a
n
e
a
n
d
R
.
D
e
v
e
n
d
i
r
a
n
,
“
M
-
M
u
l
t
i
S
V
M
:
a
n
e
f
f
i
c
i
e
n
t
f
e
a
t
u
r
e
sel
e
c
t
i
o
n
a
ssi
s
t
e
d
n
e
t
w
o
r
k
i
n
t
r
u
s
i
o
n
d
e
t
e
c
t
i
o
n
s
y
st
e
m
u
si
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
C
o
m
p
u
t
e
rs
a
n
d
S
e
c
u
ri
t
y
,
v
o
l
.
1
3
7
,
F
e
b
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
se
.
2
0
2
3
.
1
0
3
5
8
7
.
[
9
]
B
.
B
r
e
n
n
e
r
e
t
a
l
.
,
“
B
e
t
t
e
r
s
a
f
e
t
h
a
n
s
o
r
r
y
:
r
i
sk
m
a
n
a
g
e
me
n
t
b
a
s
e
d
o
n
a
sa
f
e
t
y
-
a
u
g
me
n
t
e
d
n
e
t
w
o
r
k
i
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
s
y
s
t
e
m
,
”
I
EEE
O
p
e
n
J
o
u
rn
a
l
o
f
t
h
e
I
n
d
u
st
ri
a
l
El
e
c
t
r
o
n
i
c
s
S
o
c
i
e
t
y
,
v
o
l
.
4
,
p
p
.
287
–
3
0
3
,
J
u
l
.
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
O
JI
ES
.
2
0
2
3
.
3
2
9
7
0
5
7
.
[
1
0
]
S
.
La
y
e
g
h
y
,
M
.
B
a
k
t
a
sh
mo
t
l
a
g
h
,
a
n
d
M
.
P
o
r
t
m
a
n
n
,
“
D
I
-
N
I
D
S
:
d
o
mai
n
i
n
v
a
r
i
a
n
t
n
e
t
w
o
r
k
i
n
t
r
u
s
i
o
n
d
e
t
e
c
t
i
o
n
s
y
st
e
m,”
K
n
o
w
l
e
d
g
e
-
B
a
se
d
S
y
s
t
e
m
s
,
v
o
l
.
2
7
3
,
A
u
g
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
k
n
o
s
y
s
.
2
0
2
3
.
1
1
0
6
2
6
.
[
1
1
]
R
.
D
e
v
e
n
d
i
r
a
n
a
n
d
A
.
V
.
T
u
r
u
k
ma
n
e
,
“
D
u
g
a
t
-
LS
TM
:
d
e
e
p
l
e
a
r
n
i
n
g
b
a
s
e
d
n
e
t
w
o
r
k
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
c
h
a
o
t
i
c
o
p
t
i
m
i
z
a
t
i
o
n
s
t
r
a
t
e
g
y
,
”
Ex
p
e
r
t
S
y
s
t
e
m
s w
i
t
h
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
2
4
5
,
Ju
l
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
sw
a
.
2
0
2
3
.
1
2
3
0
2
7
.
[
1
2
]
A
.
M
u
h
a
mm
a
d
,
I
.
M
u
r
t
z
a
,
A
.
S
a
a
d
i
a
,
a
n
d
K
.
K
i
f
a
y
a
t
,
“
C
o
r
t
e
x
-
i
n
s
p
i
r
e
d
e
n
s
e
mb
l
e
-
b
a
s
e
d
n
e
t
w
o
r
k
i
n
t
r
u
s
i
o
n
d
e
t
e
c
t
i
o
n
s
y
st
e
m,
”
N
e
u
ra
l
C
o
m
p
u
t
i
n
g
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
3
5
,
n
o
.
2
1
,
p
p
.
1
5
4
1
5
–
1
5
4
2
8
,
A
p
r
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s
0
0
5
2
1
-
023
-
0
8
5
6
1
-
6
.
[
1
3
]
Y
.
G
.
D
a
mt
e
w
,
H
.
C
h
e
n
,
a
n
d
Z
.
Y
u
a
n
,
“
H
e
t
e
r
o
g
e
n
e
o
u
s
e
n
sem
b
l
e
f
e
a
t
u
r
e
sel
e
c
t
i
o
n
f
o
r
n
e
t
w
o
r
k
i
n
t
r
u
s
i
o
n
d
e
t
e
c
t
i
o
n
s
y
st
e
m,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
C
o
m
p
u
t
a
t
i
o
n
a
l
I
n
t
e
l
l
i
g
e
n
c
e
S
y
s
t
e
m
s
,
v
o
l
.
1
6
,
n
o
.
1
,
F
e
b
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s4
4
1
9
6
-
0
2
2
-
0
0
1
7
4
-
6
.
[
1
4
]
A
.
S
h
i
r
a
v
a
n
i
,
M
.
H
.
S
a
d
r
e
d
d
i
n
i
,
a
n
d
H
.
N
.
N
a
h
o
o
k
,
“
N
e
t
w
o
r
k
i
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
u
s
i
n
g
d
a
t
a
d
i
m
e
n
s
i
o
n
s
r
e
d
u
c
t
i
o
n
t
e
c
h
n
i
q
u
e
s,”
J
o
u
rn
a
l
o
f
Bi
g
D
a
t
a
,
v
o
l
.
1
0
,
n
o
.
1
,
M
a
r
.
2
0
2
3
,
d
o
i
:
1
0
.
1
1
8
6
/
s4
0
5
3
7
-
023
-
0
0
6
9
7
-
5
.
[
1
5
]
M
.
B
.
A
n
l
e
y
,
A
.
G
e
n
o
v
e
s
e
,
D
.
A
g
o
st
i
n
e
l
l
o
,
a
n
d
V
.
P
i
u
r
i
,
“
R
o
b
u
s
t
D
D
o
S
a
t
t
a
c
k
d
e
t
e
c
t
i
o
n
w
i
t
h
a
d
a
p
t
i
v
e
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
,
”
C
o
m
p
u
t
e
rs
a
n
d
S
e
c
u
r
i
t
y
,
v
o
l
.
1
4
4
,
S
e
p
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
se
.
2
0
2
4
.
1
0
3
9
6
2
.
[
1
6
]
J
.
Z
h
a
o
,
Y
.
Li
u
,
Q
.
Z
h
a
n
g
,
a
n
d
X
.
Z
h
e
n
g
,
“
C
N
N
-
A
t
t
B
i
LST
M
m
e
c
h
a
n
i
sm
:
a
D
D
o
S
a
t
t
a
c
k
d
e
t
e
c
t
i
o
n
met
h
o
d
b
a
sed
o
n
a
t
t
e
n
t
i
o
n
mec
h
a
n
i
s
m
a
n
d
C
N
N
-
B
i
LST
M
,
”
I
EE
E
Ac
c
e
ss
,
v
o
l
.
1
1
,
p
p
.
1
3
6
3
0
8
–
1
3
6
3
1
7
,
N
o
v
.
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
3
.
3
3
3
4
9
1
6
.
[
1
7
]
R
.
Zh
a
o
,
Y
.
M
u
,
L
.
Zo
u
,
a
n
d
X
.
W
e
n
,
“
A
h
y
b
r
i
d
i
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
sy
s
t
e
m
b
a
s
e
d
o
n
f
e
a
t
u
r
e
s
e
l
e
c
t
i
o
n
a
n
d
w
e
i
g
h
t
e
d
s
t
a
c
k
i
n
g
c
l
a
ss
i
f
i
e
r
,
”
I
EEE
Ac
c
e
ss
,
v
o
l
.
1
0
,
p
p
.
7
1
4
1
4
–
7
1
4
2
6
,
J
u
n
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
2
.
3
1
8
6
9
7
5
.
[
1
8
]
Y
.
Y
i
n
e
t
a
l
.
,
“
I
G
R
F
-
R
F
E:
a
h
y
b
r
i
d
f
e
a
t
u
r
e
s
e
l
e
c
t
i
o
n
m
e
t
h
o
d
f
o
r
M
LP
-
b
a
se
d
n
e
t
w
o
r
k
i
n
t
r
u
s
i
o
n
d
e
t
e
c
t
i
o
n
o
n
U
N
S
W
-
N
B
1
5
d
a
t
a
se
t
,
”
J
o
u
rn
a
l
o
f
Bi
g
D
a
t
a
,
v
o
l
.
1
0
,
n
o
.
1
,
F
e
b
.
2
0
2
3
,
d
o
i
:
1
0
.
1
1
8
6
/
s
4
0
5
3
7
-
0
2
3
-
0
0
6
9
4
-
8
.
[
1
9
]
A
.
A
y
a
n
t
a
y
o
e
t
a
l
.
,
“
N
e
t
w
o
r
k
i
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
u
si
n
g
f
e
a
t
u
r
e
f
u
si
o
n
w
i
t
h
d
e
e
p
l
e
a
r
n
i
n
g
,
”
J
o
u
r
n
a
l
o
f
Bi
g
D
a
t
a
,
v
o
l
.
1
0
,
n
o
.
1
,
N
o
v
.
2
0
2
3
,
d
o
i
:
1
0
.
1
1
8
6
/
s4
0
5
3
7
-
023
-
0
0
8
3
4
-
0
.
[
2
0
]
N
.
M
o
u
s
t
a
f
a
,
“
Th
e
U
N
S
W
-
N
B
1
5
d
a
t
a
set
,
”
U
N
S
W
S
y
d
n
e
y
.
A
c
c
e
ss
e
d
:
D
e
c
.
1
5
,
2
0
2
5
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s
:
/
/
r
e
se
a
r
c
h
.
u
n
sw
.
e
d
u
.
a
u
/
p
r
o
j
e
c
t
s
/
u
n
sw
-
n
b
1
5
-
d
a
t
a
s
e
t
[
2
1
]
I
.
S
h
a
r
a
f
a
l
d
i
n
,
A
.
H
.
La
s
h
k
a
r
i
,
a
n
d
A
.
A
.
G
h
o
r
b
a
n
i
,
“
C
S
E
-
C
I
C
-
I
D
S
2
0
1
8
o
n
A
W
S
,
”
U
n
i
v
e
rs
i
t
y
o
f
N
e
w
Br
u
n
sw
i
c
k
.
A
c
c
e
sse
d
:
D
e
c
.
1
5
,
2
0
2
5
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s
:
/
/
w
w
w
.
u
n
b
.
c
a
/
c
i
c
/
d
a
t
a
s
e
t
s
/
i
d
s
-
2
0
1
8
.
h
t
ml
[
2
2
]
M
.
R
a
b
b
a
n
i
,
“
D
D
o
S
e
v
a
l
u
a
t
i
o
n
d
a
t
a
set
(
C
I
C
-
D
D
o
S
2
0
1
9
)
,
”
U
n
i
v
e
rsi
t
y
o
f
N
e
w
Br
u
n
s
w
i
c
k
.
A
c
c
e
ss
e
d
:
D
e
c
.
1
5
,
2
0
2
5
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s:
/
/
w
w
w
.
u
n
b
.
c
a
/
c
i
c
/
d
a
t
a
set
s
/
d
d
o
s
-
2
0
1
9
.
h
t
ml
[
2
3
]
Z.
A
l
l
a
l
,
H
.
N
.
N
o
u
r
a
,
O
.
S
a
l
m
a
n
,
a
n
d
K
.
C
h
a
h
i
n
e
,
“
Le
v
e
r
a
g
i
n
g
t
h
e
p
o
w
e
r
o
f
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
d
a
t
a
b
a
l
a
n
c
i
n
g
t
e
c
h
n
i
q
u
e
s
t
o
e
v
a
l
u
a
t
e
st
a
b
i
l
i
t
y
i
n
sm
a
r
t
g
r
i
d
s,”
E
n
g
i
n
e
e
ri
n
g
A
p
p
l
i
c
a
t
i
o
n
s
o
f
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
1
3
3
,
J
u
l
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
n
g
a
p
p
a
i
.
2
0
2
4
.
1
0
8
3
0
4
.
[
2
4
]
A
.
P
e
t
e
r
se
n
,
M
.
B
r
a
b
r
a
n
d
,
a
n
d
S
.
K
u
c
h
e
r
y
a
v
s
k
i
y
,
“
U
si
n
g
a
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s
f
o
r
a
n
o
ma
l
y
d
e
t
e
c
t
i
o
n
i
n
i
n
f
r
a
r
e
d
t
h
e
r
mo
g
r
a
p
h
y
i
ma
g
e
s f
o
r
r
a
p
i
d
d
i
a
g
n
o
si
s
i
n
a
n
e
mer
g
e
n
c
y
c
a
r
e
u
n
i
t
,
”
S
e
c
u
ri
t
y
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
N
e
t
w
o
r
k
s
,
v
o
l
.
1
1
2
,
F
e
b
.
2
0
2
6
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
b
s
p
c
.
2
0
2
5
.
1
0
8
7
3
4
.
[2
5
]
H
.
M
a
,
J
.
C
a
o
,
B
.
M
i
,
D
.
H
u
a
n
g
,
Y
.
Li
u
,
a
n
d
S
.
L
i
,
“
A
G
R
U
-
b
a
se
d
l
i
g
h
t
w
e
i
g
h
t
s
y
st
e
m
f
o
r
C
A
N
i
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
i
n
r
e
a
l
t
i
m
e
,
”
S
e
c
u
r
i
t
y
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
N
e
t
w
o
r
k
s
,
v
o
l
.
2
0
2
2
,
p
p
.
1
–
1
1
,
J
u
n
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
2
/
5
8
2
7
0
5
6
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2252
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
2
,
Ap
r
il 2
0
2
6
:
1
5
0
5
-
1
5
1
2
1512
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Ma
la
K
a
r
i
y
a
p
p
a
re
c
e
iv
e
d
h
e
r
B.
E.
d
e
g
re
e
in
Co
m
p
u
ter
S
c
ie
n
c
e
a
n
d
En
g
in
e
e
rin
g
fro
m
S
JB
In
stit
u
te
o
f
Tec
h
n
o
lo
g
y
,
Be
n
g
a
lu
r
u
,
In
d
ia,
in
2
0
1
4
,
a
n
d
c
o
m
p
lete
d
h
e
r
M
.
Tec
h
.
in
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
E
n
g
i
n
e
e
ri
n
g
fro
m
S
ri
S
id
d
h
a
rt
h
a
In
sti
tu
te
o
f
Tec
h
n
o
l
o
g
y
,
Tu
m
k
u
r,
In
d
ia,
in
2
0
1
8
.
S
h
e
h
a
s
b
e
e
n
se
rv
in
g
a
s
a
n
a
ss
istan
t
p
ro
fe
ss
o
r
in
t
h
e
De
p
a
rtme
n
t
o
f
In
f
o
rm
a
ti
o
n
S
c
ie
n
c
e
a
n
d
E
n
g
i
n
e
e
rin
g
sin
c
e
2
0
1
9
.
S
h
e
re
c
e
iv
e
d
h
e
r
P
h
.
D
.
fr
o
m
S
ri
S
i
d
d
h
a
rth
a
In
st
it
u
te
o
f
Tec
h
n
o
lo
g
y
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
m
a
la
.
k
@c
it
tu
m
k
u
r
.
o
rg
.
Ma
n
ju
n
a
th
H
a
n
u
m
a
n
th
a
p
p
a
Ra
n
g
a
p
p
a
re
c
e
iv
e
d
h
is
B
.
E
.
d
e
g
re
e
in
C
o
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
i
n
e
e
rin
g
fr
o
m
S
.
J.M
.
I
n
stit
u
te
o
f
Tec
h
n
o
l
o
g
y
,
Ch
i
trad
u
r
g
a
,
a
ffil
iate
d
wit
h
Ku
v
e
m
p
u
Un
iv
e
rsity
,
In
d
ia,
a
n
d
h
is
M
.
Tec
h
.
d
e
g
re
e
in
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
in
e
e
rin
g
fro
m
Ba
sa
v
e
sh
wa
ra
En
g
in
e
e
rin
g
Co
l
leg
e
,
Ba
g
a
lk
o
t,
a
ffil
iate
d
wit
h
Visv
e
sv
a
ra
y
a
Tec
h
n
o
lo
g
ica
l
Un
iv
e
rsity
.
He
o
b
tain
e
d
h
is
P
h
.
D
.
d
e
g
re
e
fro
m
S
ri
S
id
d
h
a
rt
h
a
Ac
a
d
e
m
y
o
f
Hig
h
e
r
Ed
u
c
a
ti
o
n
(S
r
i
S
id
d
h
a
rth
a
Un
iv
e
rsity
)
,
Tu
m
k
u
r,
In
d
ia,
i
n
2
0
2
2
.
He
is
c
u
rre
n
t
ly
se
rv
in
g
a
s
a
n
a
ss
o
c
iate
p
ro
fe
ss
o
r
in
t
h
e
De
p
a
rtme
n
t
o
f
Artifi
c
ial
In
telli
g
e
n
c
e
a
n
d
M
a
c
h
in
e
Lea
rn
in
g
.
He
is
a
li
fe
m
e
m
b
e
r
o
f
IS
TE
a
n
d
IET
E
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
m
a
n
ju
n
a
th
.
h
r@j
y
o
t
h
y
it
.
ac
.
in
.
Ve
n
u
g
o
p
a
l
D
a
sa
p
p
a
re
c
e
iv
e
d
h
is
B
.
E
.
d
e
g
re
e
in
C
o
m
p
u
ter
S
c
ie
n
c
e
a
n
d
En
g
in
e
e
rin
g
in
2
0
1
0
a
n
d
h
is
M
.
Tec
h
.
d
e
g
re
e
in
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
i
n
e
e
rin
g
i
n
2
0
1
2
fro
m
Ch
a
n
n
a
b
a
sa
v
e
sh
wa
ra
In
stit
u
te
o
f
Tec
h
n
o
l
o
g
y
,
G
u
b
b
i
,
a
ffil
iate
d
wit
h
Visv
e
sv
a
ra
y
a
Tec
h
n
o
l
o
g
ica
l
Un
iv
e
rsity
,
Be
lag
a
v
i
,
In
d
ia
.
He
i
s
p
re
se
n
tl
y
w
o
rk
i
n
g
a
s
a
n
a
ss
istan
t
p
r
o
fe
ss
o
r
a
t
Ha
rsh
a
I
n
stit
u
te
o
f
Tec
h
n
o
lo
g
y
,
Ne
lam
a
n
g
a
la,
Be
n
g
a
lu
r
u
.
P
re
v
i
o
u
sl
y
,
h
e
se
rv
e
d
a
s
a
n
a
s
sista
n
t
p
ro
fe
ss
o
r
a
t
S
id
d
a
g
a
n
g
a
I
n
stit
u
te
o
f
Tec
h
n
o
lo
g
y
,
T
u
m
a
k
u
r
u
,
a
n
d
a
t
Ak
sh
a
y
a
In
stit
u
te
o
f
Tec
h
n
o
lo
g
y
,
Tu
m
a
k
u
r
u
.
He
a
lso
h
a
s
in
d
u
str
y
e
x
p
e
rien
c
e
a
s
a
so
ftwa
re
d
e
v
e
lo
p
e
r
a
t
On
e
6
7
Dig
i
tal
S
o
l
u
ti
o
n
s
P
v
t
.
Ltd
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
v
e
n
u
g
d
8
9
@
g
m
a
il
.
c
o
m
.
G
u
r
u
r
a
ja
H
e
b
b
u
r
S
a
ty
a
n
a
r
a
y
a
n
a
re
c
e
iv
e
d
h
is
d
o
c
to
ra
l
d
e
g
re
e
in
C
o
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
i
n
e
e
rin
g
a
n
d
is
c
u
rre
n
tl
y
se
rv
i
n
g
a
s
a
n
a
ss
istan
t
p
r
o
fe
ss
o
r
(se
lec
ti
o
n
g
ra
d
e
)
i
n
t
h
e
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
Bu
sin
e
ss
S
y
ste
m
s
a
t
B
.
M
.
S
.
Co
l
leg
e
o
f
En
g
in
e
e
ri
n
g
,
Be
n
g
a
lu
r
u
,
I
n
d
ia
.
His
re
se
a
rc
h
in
tere
sts
in
c
l
u
d
e
c
o
m
p
u
ter
sc
i
e
n
c
e
a
p
p
li
c
a
ti
o
n
s,
i
n
fo
rm
a
ti
o
n
sy
ste
m
s,
a
n
d
e
m
e
rg
in
g
c
o
m
p
u
ti
n
g
tec
h
n
o
lo
g
ies
.
He
h
a
s
p
u
b
li
s
h
e
d
re
se
a
rc
h
a
rti
c
les
in
in
tern
a
ti
o
n
a
l
jo
u
rn
a
ls
a
n
d
c
o
n
f
e
re
n
c
e
s
in
d
e
x
e
d
in
S
c
o
p
u
s
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
g
u
r
u
ra
jh
s
.
ise
@b
m
sc
e
.
ac
.
in
.
G
irish
K
e
sha
v
a
Ra
o
is
c
u
rre
n
tl
y
se
rv
in
g
a
s
a
n
a
ss
istan
t
p
ro
fe
ss
o
r
in
t
h
e
De
p
a
rtme
n
t
o
f
C
o
m
p
u
ter
Ap
p
li
c
a
ti
o
n
s
a
t
B
.
M
.
S
.
C
o
ll
e
g
e
o
f
En
g
i
n
e
e
rin
g
,
B
e
n
g
a
lu
r
u
,
I
n
d
ia
.
His
a
c
a
d
e
m
ic
a
n
d
re
se
a
rc
h
in
tere
sts
in
c
l
u
d
e
c
o
m
p
u
ter
a
p
p
li
c
a
ti
o
n
s,
d
a
ta
a
n
a
ly
ti
c
s,
a
n
d
e
m
e
rg
i
n
g
c
o
m
p
u
t
in
g
tec
h
n
o
l
o
g
ies
.
He
h
a
s
p
u
b
l
ish
e
d
re
se
a
rc
h
a
rti
c
les
in
in
ter
n
a
ti
o
n
a
l
j
o
u
rn
a
ls
a
n
d
c
o
n
fe
re
n
c
e
s
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
g
k
.
m
c
a
@b
m
sc
e
.
ac
.
in
.
G
o
u
sia
Th
a
h
n
iy
a
th
re
c
e
iv
e
d
h
e
r
B
.
E
.
d
e
g
re
e
in
C
o
m
p
u
ter
S
c
ien
c
e
a
n
d
E
n
g
i
n
e
e
rin
g
fro
m
G
u
lb
a
rg
a
Un
i
v
e
rsity
a
n
d
h
e
r
M
.
E
.
d
e
g
re
e
fro
m
Ba
n
g
a
l
o
re
Un
iv
e
rsit
y
.
S
h
e
o
b
tai
n
e
d
h
e
r
Ph
.
D
.
d
e
g
re
e
in
Co
m
p
u
ter S
c
ien
c
e
a
n
d
En
g
i
n
e
e
rin
g
fr
o
m
Visv
e
sv
a
ra
y
a
Tec
h
n
o
l
o
g
ica
l
Un
i
v
e
rsity
,
with
d
o
c
to
ra
l
re
se
a
rc
h
fo
c
u
se
d
o
n
in
tru
si
o
n
d
e
tec
ti
o
n
sy
ste
m
s fo
r
w
irele
ss
se
n
so
r
n
e
two
rk
s
.
S
h
e
is
c
u
rre
n
tl
y
se
rv
in
g
a
s
a
n
a
ss
o
c
i
a
te
p
ro
fe
ss
o
r
i
n
t
h
e
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
i
n
e
e
rin
g
a
t
Da
y
a
n
a
n
d
a
S
a
g
a
r
Un
iv
e
rsit
y
,
Be
n
g
a
lu
r
u
,
In
d
ia
.
S
h
e
h
a
s
p
u
b
li
s
h
e
d
e
x
ten
siv
e
l
y
i
n
S
CI
-
a
n
d
S
c
o
p
u
s
-
i
n
d
e
x
e
d
jo
u
rn
a
ls,
c
o
n
fe
re
n
c
e
s,
a
n
d
b
o
o
k
c
h
a
p
ters
a
n
d
h
a
s
re
c
e
iv
e
d
fu
n
d
e
d
re
se
a
rc
h
p
ro
jec
ts
fro
m
re
c
o
g
n
ize
d
a
g
e
n
c
ies
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
g
o
u
sia
-
c
se
@d
su
.
e
d
u
.
in
.
Evaluation Warning : The document was created with Spire.PDF for Python.