I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
pu
t
er
Science
Vo
l.
3
9
,
No
.
3
,
Sep
tem
b
er
2
0
2
5
,
p
p
.
1
7
5
5
~
1
7
64
I
SS
N:
2
5
0
2
-
4
7
5
2
,
DOI
: 1
0
.
1
1
5
9
1
/ijeecs.v
3
9
.i
3
.
pp
1
7
55
-
1
7
64
1755
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs.ia
esco
r
e.
co
m
M
echa
nized ne
tw
o
rk bas
ed
cy
ber
-
a
tt
a
ck
d
etec
tion a
n
d
cla
ss
ificatio
n usin
g
DNN
-
g
en
erativ
e adv
ersa
ria
l mo
del
K
a
t
ika
m
M
a
hes
h,
K
un
j
a
m
Na
g
eswa
ra
Ra
o
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
S
y
st
e
ms
En
g
i
n
e
e
r
i
n
g
,
A
U
C
E
(
A
)
,
A
n
d
h
r
a
U
n
i
v
e
r
si
t
y
,
V
i
s
a
k
h
a
p
a
t
n
a
m
,
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
Dec
4
,
2
0
2
4
R
ev
is
ed
Ap
r
4
,
2
0
2
5
Acc
ep
ted
J
ul
2
,
2
0
2
5
Th
e
se
d
a
y
s
a
lmo
st
e
v
e
ry
t
h
in
g
is
in
tern
e
t.
Cy
b
e
ra
tt
a
c
k
s
a
re
t
h
e
w
o
rld
'
s
m
o
st
p
re
ss
in
g
issu
e
s.
D
u
e
to
t
h
e
se
a
tt
a
c
k
s,
Co
m
p
u
ter
s
y
ste
m
s
c
a
n
b
e
re
n
d
e
re
d
in
o
p
e
ra
b
le,
d
isru
p
ted
,
d
e
stro
y
e
d
o
r
c
o
n
tro
ll
e
d
v
ia
c
y
b
e
ra
tt
a
c
k
s.
Ad
d
it
io
n
a
ll
y
,
th
e
y
c
a
n
b
e
u
se
d
to
ste
a
l,
m
o
d
if
y
,
e
ra
se
,
b
l
o
c
k
,
o
r
a
lt
e
r
d
a
ta.
M
o
st
o
rg
a
n
iza
ti
o
n
s
a
re
fa
c
in
g
t
h
is
Iss
u
e
a
n
d
l
o
se
fin
a
n
c
ially
a
s
we
ll
a
s
in
d
a
ta
se
c
u
rit
y
,
th
e
re
a
re
n
u
m
e
ro
u
s
c
o
n
v
e
n
ti
o
n
a
l
in
tru
sio
n
d
e
tec
ti
o
n
sy
st
e
m
s
(IDS)
a
n
d
firew
a
ll
s a
re
il
lu
stra
ti
o
n
s f
o
r
n
e
two
rk
se
c
u
rit
y
to
o
ls wh
ich
a
re
n
o
t
a
b
le t
o
c
las
sify
a
n
d
d
e
tec
t
d
iffere
n
t
t
y
p
e
s
o
f
a
tt
a
c
k
s
in
n
e
two
r
k
.
Wi
t
h
m
a
c
h
in
e
lea
rn
in
g
a
p
p
r
o
a
c
h
u
si
n
g
th
e
Da
t
a
se
t
KD
D_
CUP
9
9
a
s
in
p
u
t,
t
h
e
sy
n
t
h
e
ti
c
m
in
o
rit
y
o
v
e
rsa
m
p
li
n
g
tec
h
n
i
q
u
e
(S
M
OTE)
is
o
n
e
o
f
t
h
e
m
o
st
o
ften
u
se
d
o
v
e
rsa
m
p
li
n
g
m
e
th
o
d
s fo
r
a
d
d
re
ss
in
g
imb
a
lan
c
e
issu
e
s.
Th
e
p
ro
p
o
se
d
h
y
b
ri
d
d
e
e
p
n
e
u
ra
l
n
e
two
rk
(DN
N),
g
e
n
e
ra
ti
v
e
a
d
v
e
rsa
rial
n
e
two
r
k
(G
AN
)
,
a
n
d
e
x
h
a
u
sti
v
e
fe
a
tu
re
se
lec
ti
o
n
(EF
S
)
c
a
n
d
e
tec
t
a
n
d
c
las
sify
se
v
e
ra
l
a
tt
a
c
k
ty
p
e
s
i
n
c
lu
d
in
g
R2
L
,
U2
R
,
P
r
o
b
e
,
d
e
n
ial
o
f
se
rv
ice
(
Do
S
)
,
a
n
d
n
o
r
m
a
l
a
tt
a
c
k
s
ty
p
e
s
a
n
d
in
f
o
rm
to
a
d
m
i
n
istrato
r
to
rin
g
a
larm
so
u
n
d
t
o
c
o
n
tr
o
l
a
n
d
m
o
n
it
o
r
n
e
two
r
k
traffic i
n
d
y
n
a
m
ica
ll
y
ty
p
e
d
n
e
two
rk
s
.
K
ey
w
o
r
d
s
:
C
las
s
if
icatio
n
attac
k
s
C
y
b
er
th
r
ea
t d
etec
tio
n
Dee
p
n
eu
r
al
n
etwo
r
k
al
g
o
r
ith
m
Featu
r
e
ex
tr
ac
tio
n
I
n
tr
u
s
io
n
d
ete
ctio
n
s
y
s
tem
Netwo
r
k
s
ec
u
r
ity
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
:
Katik
am
Ma
h
esh
Dep
ar
tm
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
an
d
Sy
s
tem
s
E
n
g
i
n
ee
r
in
g
,
AUCE
(
A)
,
An
d
h
r
a
Un
i
v
er
s
ity
Vis
ak
h
ap
atn
am
-
5
3
0
0
0
3
,
I
n
d
ia
E
m
ail:
k
atik
am
m
ah
esh
@
g
m
ai
l.c
o
m
1.
I
NT
RO
D
UCT
I
O
N
A
cy
b
er
attac
k
is
an
in
ten
tio
n
al
attem
p
t to
h
ac
k
in
to
an
o
th
e
r
p
er
s
o
n
'
s
o
r
th
e
in
f
o
r
m
atio
n
s
y
s
tem
o
f
th
e
o
r
g
an
izatio
n
[
1
]
.
T
y
p
ically
,
th
e
attac
k
er
g
ain
s
an
ad
v
an
ta
g
e
b
y
tam
p
e
r
in
g
in
th
e
v
icti
m
'
s
n
etwo
r
k
[
2
]
.
An
ar
tific
ial
n
eu
r
al
n
etwo
r
k
(
ANN
)
with
m
an
y
g
en
er
ativ
e
ad
v
e
r
s
ar
ial
n
etwo
r
k
(
GAN
)
an
d
d
ee
p
n
eu
r
al
n
etwo
r
k
s
(
DNNs
)
h
av
e
th
e
ab
ilit
y
to
m
o
d
el
n
o
n
-
lin
ea
r
r
elatio
n
s
h
ip
s
ju
s
t a
s
s
h
allo
w
ANN
s
as sh
o
wn
in
Fig
u
r
e
1
.
Fig
u
r
e
1
.
DNN
f
o
r
attac
k
class
if
icatio
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
9
,
No
.
3
,
Sep
tem
b
er
20
25
:
1
7
5
5
-
1
7
64
1756
Fu
r
th
er
m
o
r
e
,
cu
r
r
e
n
t
in
tr
u
s
io
n
d
etec
tio
n
s
y
s
tem
(
I
DS)
tech
n
o
lo
g
ies
ar
e
n
o
t
ab
le
to
m
an
ag
e
n
etwo
r
k
f
lo
w
o
r
d
etec
t,
class
if
y
,
an
d
id
en
tify
v
ar
io
u
s
ty
p
es
o
f
cy
b
er
at
tack
s
o
n
co
m
p
u
ter
n
etwo
r
k
s
[
3
]
.
Dif
f
er
en
t
attac
k
ty
p
es,
in
clu
d
in
g
d
e
n
ial
o
f
s
er
v
ice
(
Do
S
)
,
Pro
b
e,
R
2
L
,
an
d
U2
R
,
ca
n
b
e
id
en
tifie
d
an
d
ca
teg
o
r
ized
b
y
th
e
p
r
o
p
o
s
ed
m
ac
h
in
e
lea
r
n
in
g
a
n
d
d
ee
p
lear
n
in
g
tech
n
iq
u
e
w
ith
th
e
KDD_
C
UP
9
9
d
ataset
as
in
p
u
t
in
a
DNN
[
4
]
.
A
lay
e
r
o
f
in
p
u
t,
an
o
u
tp
u
t
lay
er
,
a
n
d
at
least
a
lay
er
in
th
e
ce
n
tr
e
m
ak
es
u
p
a
DN
N
.
T
h
e
n
etwo
r
k
is
d
ee
p
er
th
e
f
ewe
r
lay
er
s
y
o
u
a
r
e.
E
ac
h
o
f
th
es
e
lev
els
u
s
es
a
p
r
o
ce
s
s
ca
lled
“
f
ea
tu
r
e
s
ele
ctio
n
”
to
ca
r
r
y
o
u
t
d
is
tin
ct
class
if
icatio
n
an
d
s
o
r
tin
g
task
s
[
5
]
.
All
we
h
av
e
to
d
o
is
lo
o
k
at
h
o
w
th
e
h
u
m
an
b
r
ain
f
u
n
ctio
n
s
to
g
e
t
a
g
r
ea
ter
awa
r
en
ess
o
f
h
o
w
a
DNN
wo
r
k
s
[
6
]
.
2.
L
I
T
E
R
AT
U
RE
WO
RK
Sev
er
al
p
r
io
r
s
t
u
d
ies
h
av
e
h
i
g
h
lig
h
ted
u
s
in
g
d
ee
p
lea
r
n
in
g
an
d
m
ac
h
in
e
lear
n
i
n
g
ap
p
r
o
ac
h
es
to
im
p
r
o
v
e
th
e
s
af
ety
o
f
s
y
s
tem
s
f
o
r
cy
b
er
s
ec
u
r
ity
[
7
]
.
T
h
e
b
ac
k
g
r
o
u
n
d
o
f
s
ec
u
r
ity
v
u
ln
er
ab
ilit
ies
s
y
s
tem
s
:
th
r
ea
t
s
tack
(
I
DS
(
ac
ce
s
s
ed
o
n
1
9
Ma
y
2
0
2
2
)
.
B
u
t
h
ig
h
ly
f
ew
f
r
eq
u
e
n
tly
a
ttack
s
ar
e
r
ep
o
r
ted
[
8
]
.
T
h
is
wo
r
k
o
n
ly
class
if
ies
th
e
n
o
r
m
al
atta
ck
s
b
u
t
n
o
n
ew
ty
p
es
o
f
attac
k
s
[
9
]
.
T
h
is
wo
r
k
class
if
ies
th
e
d
ata
b
u
t
n
o
clea
r
ab
o
u
t
d
if
f
e
r
en
t
attac
k
d
etec
tio
n
.
T
o
elim
in
ate
all
th
ese
d
r
awb
ac
k
s
as
well
th
e
p
r
o
p
o
s
ed
wo
r
k
ca
n
av
o
id
p
itfa
ll
s
in
p
ast
s
tu
d
ies
[
1
0
]
.
Fu
r
th
er
m
o
r
e,
th
e
m
an
y
f
o
r
m
s
o
f
cy
b
er
attac
k
s
o
n
co
m
p
u
ter
n
etwo
r
k
s
ca
n
n
o
t
b
e
d
etec
ted
,
class
if
ied
,
o
r
id
en
t
if
ied
b
y
th
e
I
DS
tech
n
o
lo
g
i
es
cu
r
r
en
tly
in
u
s
e
[
1
1
]
.
W
ith
in
p
u
t
f
r
o
m
th
e
KDD_
C
UP 9
9
d
ataset,
th
e
p
r
o
p
o
s
ed
DNN
[
1
2
]
.
3.
P
RO
P
O
SE
D
M
E
T
H
O
D
T
h
e
attac
k
d
etec
tio
n
m
eth
o
d
'
s
ar
ch
itectu
r
e
is
b
ased
o
n
th
e
s
ec
u
r
ity
s
y
s
tem
'
s
co
n
tin
u
o
u
s
d
ata
tr
af
f
ic
m
o
n
ito
r
in
g
o
f
n
etwo
r
k
s
y
s
tem
s
to
d
etec
t
an
d
ca
teg
o
r
ize
v
ar
io
u
s
s
ec
u
r
ity
attac
k
ty
p
es.
T
h
e
attac
k
d
etec
tio
n
s
tr
ateg
y
is
cr
ea
ted
with
th
e
p
r
o
p
o
s
ed
DNN
with
GAN
.
GAN
s
is
a
ty
p
e
o
f
d
ee
p
lear
n
i
n
g
ar
ch
itectu
r
e
[
1
3
]
.
I
t
tr
ain
s
two
n
eu
r
al
n
etwo
r
k
s
t
o
co
m
p
ete
with
o
n
e
an
o
th
er
to
g
en
er
ate
m
o
r
e
r
ea
l
n
ew
d
ata
f
r
o
m
a
g
i
v
en
tr
ai
n
in
g
d
ataset
[
1
4
]
.
I
n
th
is
ca
s
e,
y
o
u
m
ay
cr
ea
te
n
ew
p
h
o
to
s
f
r
o
m
a
n
ex
is
tin
g
im
ag
e
d
atab
a
s
e
o
r
o
r
ig
in
al
m
u
s
ic
f
r
o
m
a
s
o
n
g
lib
r
a
r
y
.
W
ith
KDD_
C
UP9
9
as
in
p
u
t
f
o
r
id
e
n
tify
in
g
cy
b
er
-
attac
k
s
th
at
a
r
e
in
tr
o
d
u
c
ed
in
to
th
e
s
y
s
tem
b
y
attac
k
er
s
an
d
d
etec
ted
in
s
y
s
tem
o
r
g
an
izatio
n
s
wh
ich
ca
n
id
en
tify
an
d
ca
te
g
o
r
ize
d
if
f
er
en
t
attac
k
ty
p
es
s
u
ch
as
n
o
r
m
al,
D
o
S,
Pro
b
e,
R
2
L
,
an
d
U2
R
[
1
5
]
.
3
.
1
.
Da
t
a
c
o
llect
io
n
KDD
C
U
P
9
9
is
an
ex
tr
em
ely
d
em
an
d
i
n
g
d
ataset
as
s
h
o
wn
in
Fig
u
r
e
2
with
v
ast
s
ize,
r
ed
u
n
d
an
c
y
,
an
ex
ten
s
iv
e
n
u
m
b
e
r
o
f
v
a
r
iab
les
(
co
n
tain
in
g
b
o
th
n
u
m
er
i
c
an
d
ca
te
g
o
r
ical)
,
an
d
a
s
k
e
wed
tar
g
et
v
a
r
iab
le
[
1
6
]
.
I
t
is
a
p
r
o
m
in
en
t
d
ata
s
et
u
s
ed
f
o
r
in
tr
u
s
io
n
d
etec
t
io
n
in
ac
ad
em
ic
liter
atu
r
e.
Du
r
in
g
a
DARP
A
-
s
p
o
n
s
o
r
ed
e
v
en
t
in
1
9
9
9
at
M
I
T
'
s
L
in
co
ln
L
ab
o
r
ato
r
y
s
ev
er
al
attac
k
s
s
ce
n
ar
io
s
wer
e
s
im
u
lated
an
d
f
ea
tu
r
es
wer
e
co
llected
,
r
esu
ltin
g
in
th
e
cr
ea
tio
n
o
f
th
e
d
ataset
[
1
7
]
.
T
h
is
d
ataset
was
a
p
ar
t
o
f
th
e
1
9
9
9
KDD
co
n
t
est
in
in
tr
u
s
io
n
d
etec
tio
n
.
I
n
th
e
KDD
tr
ain
in
g
d
ataset,
ea
ch
o
f
th
e
n
ea
r
ly
4
,
9
0
0
,
0
0
0
u
n
i
q
u
e
co
n
n
e
ctio
n
v
ec
to
r
s
h
av
e
r
esu
lted
in
4
1
attr
ib
u
tes an
d
a
lab
el
d
en
o
tin
g
as to
is
th
is
a
n
ew
o
r
n
o
r
m
al
ty
p
e
o
f
attac
k
s
[
1
8
]
.
F
ig
u
r
e
2
.
Featu
r
es o
f
KDD_
C
UP9
9
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
Mech
a
n
iz
ed
n
etw
o
r
k
b
a
s
ed
cy
b
er
-
a
tta
ck
d
etec
tio
n
a
n
d
cla
s
s
ifica
tio
n
u
s
in
g
…
(
K
a
tika
m
M
a
h
esh
)
1757
3
.
2
.
Da
t
a
prepro
ce
s
s
ing
Pre
p
ar
in
g
in
f
o
r
m
atio
n
r
ef
e
r
s
to
th
e
p
r
o
ce
s
s
u
s
ed
to
co
llect
d
ata
th
at
was
n
o
t
p
r
o
ce
s
s
ed
t
h
at
will
b
e
u
tili
ze
d
b
y
a
m
ac
h
in
e
lear
n
in
g
m
o
d
el
as sh
o
wn
in
Fig
u
r
e
3
.
C
o
n
s
id
er
in
g
o
n
ly
5
0
K
d
ata
co
m
b
in
ed
f
r
o
m
all
th
e
ty
p
es
o
f
p
r
o
to
co
ls
,
v
er
if
y
in
g
s
h
ap
e
(
n
u
m
b
e
r
o
f
r
o
ws
an
d
co
lu
m
n
s
)
,
lo
o
k
i
n
g
u
p
co
lu
m
n
n
am
es
t
o
id
e
n
tify
f
ea
tu
r
es,
v
e
r
if
y
in
g
d
ata
in
teg
r
ity
b
y
ch
ec
k
i
n
g
f
o
r
n
u
ll
v
alu
es,
an
d
ex
am
in
in
g
th
e
d
is
tr
ib
u
tio
n
o
f
t
h
e
tar
g
et
co
lu
m
n
(
'
L
ab
el'
)
to
u
n
d
er
s
tan
d
class
d
is
tr
ib
u
tio
n
ar
e
all
ca
r
r
ied
o
u
t
as
p
ar
t
o
f
an
ex
h
a
u
s
tiv
e
f
ea
tu
r
e
s
elec
tio
n
(
E
FS
)
[
1
9
]
.
An
ef
f
o
r
t
to
en
h
a
n
ce
p
r
ed
ictiv
e
m
o
d
el
b
y
tr
y
i
n
g
to
o
p
tim
ize
f
ea
tu
r
es
with
in
a
d
ataset
m
ad
e
u
s
e
o
f
ex
h
au
s
tiv
e
f
ea
tu
r
e
s
elec
tio
n
[
2
0
]
.
T
h
is
test
s
ea
ch
p
o
ten
tial
f
ea
tu
r
e
co
m
b
in
atio
n
will
d
o
1
0
-
f
o
ld
cr
o
s
s
v
alid
atio
n
th
at
u
tili
ze
d
to
lim
i
t
th
e
m
ax
im
u
m
n
u
m
b
er
o
f
f
ea
tu
r
es
th
at
m
ay
b
e
s
elec
ted
f
r
o
m
a
d
ataset
wh
ich
co
m
p
r
is
ed
m
o
r
e
th
an
8
0
f
ea
tu
r
es [
2
1
]
.
Fig
u
r
e
3
.
Fra
m
ewo
r
k
f
o
r
attac
k
class
if
icatio
n
3
.
3
.
F
e
a
t
ure
s
elec
t
io
n
T
h
e
p
ar
ts
d
ee
m
ed
m
o
s
t
s
ig
n
if
ican
t
an
d
r
elev
an
t
ar
e
s
elec
ted
u
s
in
g
a
b
r
u
te
-
f
o
r
c
e
f
ea
tu
r
e
s
u
b
s
et
ev
alu
atio
n
o
cc
u
r
s
in
a
f
ea
tu
r
e
s
elec
tio
n
p
r
o
ce
s
s
m
eth
o
d
[
2
2
]
.
Giv
en
a
n
y
r
a
n
d
o
m
r
eg
r
ess
o
r
o
r
class
if
ier
,
th
e
b
est
s
u
b
s
et
is
ch
o
s
en
b
y
o
p
tim
izin
g
a
g
iv
e
n
p
e
r
f
o
r
m
an
ce
p
ar
am
eter
.
I
f
th
e
d
ataset
h
as
f
o
u
r
f
ea
tu
r
es
a
n
d
th
e
class
if
ier
is
a
r
an
d
o
m
f
o
r
est
r
eg
r
ess
o
r
,
th
e
alg
o
r
ith
m
will
ex
am
in
e
all
f
if
teen
f
ea
tu
r
e
c
o
m
b
in
atio
n
s
(
ass
u
m
in
g
m
in
_
f
ea
tu
r
es=3
a
n
d
m
a
x
_
f
e
atu
r
es=2
0
)
.
f
s
=
E
FS
(
R
an
d
o
m
Fo
r
est
R
eg
r
ess
o
r
(
)
)
,
m
in
_
f
ea
tu
r
es=3
,
m
ax
_
f
ea
tu
r
es=2
0
,
s
co
r
in
g
='
n
eg
_
m
ea
n
_
s
q
u
ar
ed
_
er
r
o
r
=1
0
)
E
f
s
.
f
it (
Y,
X)
.
3
.
4
.
DNN
-
G
AN
m
o
del f
o
r
a
t
t
a
ck
det
ec
t
io
n
T
h
e
n
etwo
r
k
la
y
er
s
o
f
th
e
D
NN
an
d
GAN
m
o
d
els
ar
e
co
m
b
in
ed
in
th
e
h
y
b
r
id
DNN
-
G
AN
m
o
d
el.
W
h
en
v
iewe
d
in
Fig
u
r
e
4
,
th
e
h
y
b
r
id
a
r
ch
itectu
r
e
co
m
b
in
e
s
th
e
lay
er
s
o
f
th
e
C
NN
with
th
e
GAN
m
o
d
el,
i.e
.
,
co
m
b
in
in
g
th
e
o
u
tp
u
t
DNN
w
ith
GAN
to
ac
c
u
r
ately
id
en
tif
y
th
e
cy
b
e
r
attac
k
[
2
3
]
.
First,
t
h
e
g
e
n
er
ato
r
m
ak
es
an
im
ag
e
b
y
p
r
o
v
id
i
n
g
a
n
y
r
a
n
d
o
m
i
n
teg
er
.
T
h
e
d
is
cr
im
in
at
o
r
ac
ce
p
ts
th
e
im
a
g
e
th
at
was
g
en
er
ated
as
in
p
u
t,
an
d
th
e
r
ea
l
d
ataset
is
u
s
ed
to
ex
tr
ac
t
th
e
ac
tu
al
im
ag
es
[
2
4
]
.
B
o
th
ac
tu
al
an
d
p
h
o
n
y
p
h
o
to
s
ar
e
p
r
esen
t
in
th
e
d
is
cr
im
in
ato
r
,
wh
ic
h
n
o
w
s
ee
k
s
to
id
en
tif
y
th
e
r
ea
l
a
n
d
f
ak
e
im
ag
es
an
d
p
r
ed
ict
th
e
lab
e
ls
.
I
ts
o
u
tp
u
t
is
th
e
p
r
o
b
a
b
ilit
y
o
f
a
n
u
m
b
er
b
et
wee
n
0
an
d
1
,
wh
er
e
1
d
e
n
o
tes
au
th
en
ticity
an
d
0
d
en
o
tes
a
b
o
g
u
s
f
o
r
ec
ast.
T
h
e
g
r
ap
h
ic
b
elo
w
d
escr
ib
es
h
o
w
a
GAN
o
p
er
ates.
A
DNN
is
m
ad
e
u
p
o
f
an
in
p
u
t
lay
er
,
an
o
u
tp
u
t
lay
er
,
an
d
at
least
o
n
e
in
ter
v
en
in
g
la
y
er
[
2
5
]
.
T
h
e
d
ee
p
er
th
e
n
etwo
r
k
,
t
h
e
m
o
r
e
lay
e
r
s
th
er
e
ar
e.
I
n
a
m
eth
o
d
k
n
o
wn
as
“
f
ea
tu
r
e
h
ier
a
r
ch
y
,
”
ea
ch
o
f
th
ese
tier
s
wo
r
k
s
o
u
t d
if
f
er
e
n
t k
i
n
d
s
o
f
s
p
ec
if
ic
s
o
r
tin
g
an
d
cla
s
s
if
y
in
g
[
2
6
]
,
[
2
7
]
.
3
.
4
.
1
.
I
ntr
o
du
ct
io
n t
o
g
ener
a
t
iv
e
a
dv
er
s
a
ria
l
net
wo
r
k
(
G
AN)
A
m
ac
h
in
e
lear
n
in
g
m
o
d
el
c
alled
a
g
en
er
ativ
e
ad
v
er
s
ar
ia
l
n
etwo
r
k
(
GAN)
is
m
ad
e
t
o
p
r
o
d
u
ce
r
ea
lis
tic
d
ata
b
y
i
d
en
tify
in
g
p
atter
n
s
in
p
r
e
-
ex
is
tin
g
tr
ain
i
n
g
d
atasets
.
T
h
r
o
u
g
h
th
e
u
s
e
o
f
d
ee
p
lear
n
in
g
tech
n
iq
u
es a
n
d
an
u
n
s
u
p
er
v
is
e
d
lear
n
in
g
f
r
am
e
wo
r
k
,
it f
u
n
ct
io
n
s
in
o
p
p
o
s
itio
n
to
two
n
eu
r
al
n
etwo
r
k
s
,
o
n
e
o
f
wh
ich
g
en
e
r
ates
d
ata
an
d
th
e
o
th
er
d
eter
m
in
es
wh
eth
e
r
th
e
d
ata
is
g
en
e
r
ated
o
r
r
ea
l
.
T
h
e
in
tr
icac
y
o
f
ca
lcu
latio
n
s
in
g
en
er
ativ
e
m
o
d
els
h
as
m
ad
e
it
m
o
r
e
d
if
f
icu
l
t
to
g
en
er
ate
f
r
esh
d
ata,
in
cl
u
d
in
g
r
ea
lis
tic
im
ag
es
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
9
,
No
.
3
,
Sep
tem
b
er
20
25
:
1
7
5
5
-
1
7
64
1758
o
r
tex
t,
e
v
en
i
f
d
ee
p
lear
n
i
n
g
h
as
p
er
f
o
r
m
ed
ex
ce
p
tio
n
ally
well
in
task
s
lik
e
im
ag
e
class
if
icatio
n
an
d
s
p
ee
ch
r
ec
o
g
n
itio
n
.
W
h
en
it p
er
tain
s
t
o
m
an
ag
i
n
g
co
m
p
lex
n
etwo
r
k
tr
af
f
ic,
GANs a
r
e
th
e
m
ain
p
lay
er
s
.
Fig
u
r
e
4
.
DNN
-
GAN
m
o
d
el
f
o
r
attac
k
d
etec
tio
n
3.
4
.
2
.
G
ener
a
t
iv
e
a
dv
er
s
a
ria
l net
wo
rk
a
lg
o
rit
hm
f
o
r
d
et
e
ct
cy
ber
-
t
hrea
t
s
a
nd
cla
s
s
if
y
diff
er
ent
a
t
t
a
c
k
s
C
y
b
er
s
ec
u
r
ity
ex
p
e
r
ts
ca
n
i
m
p
r
o
v
e
th
eir
in
tr
u
s
io
n
d
etec
tio
n
s
y
s
tem
s
(
I
DS)
b
y
s
im
u
latin
g
th
e
co
m
p
lex
m
o
v
em
e
n
ts
o
f
p
o
s
s
ib
le
attac
k
er
s
b
y
cr
ea
tin
g
h
o
s
t
ile
n
etwo
r
k
tr
a
f
f
ic.
Kn
o
win
g
th
e
en
em
y
'
s
tactics
b
ef
o
r
e
t
h
e
co
m
b
at
s
tar
ts
is
a
p
r
o
ac
tiv
e
d
ef
i
n
es
tech
n
iq
u
e
th
a
t
th
is
s
u
p
p
o
r
ts
.
B
y
k
ee
p
i
n
g
o
n
e
s
tep
ah
ea
d
o
f
an
y
attac
k
s
,
it
s
er
v
es
as
a
d
ig
ital
s
p
ar
r
in
g
p
ar
tn
er
in
th
is
co
n
tex
t,
ass
is
tin
g
f
ir
m
s
in
s
tr
en
g
t
h
en
in
g
t
h
eir
cy
b
er
d
ef
en
ce
s
.
Alg
o
r
it
h
m
f
o
r
d
etec
t
cy
b
er
-
t
h
r
ea
ts
an
d
class
if
y
d
if
f
er
en
t a
ttack
s
s
h
o
wn
in
Alg
o
r
it
h
m
1
.
Alg
o
r
ith
m
1
:
D
etec
t c
y
b
er
-
th
r
ea
ts
I
n
p
u
t: Da
taset KD
D_
C
UP9
9
Step
1
: T
h
e
g
e
n
er
ato
r
g
en
er
ate
s
an
im
ag
e
f
o
llo
win
g
r
ec
eiv
in
g
a
r
an
d
o
m
in
te
g
er
f
ee
d
.
Step
2
: A
s
tr
ea
m
o
f
im
ag
es f
r
o
m
th
e
r
ea
l,
g
r
o
u
n
d
-
tr
u
th
d
atas
et
will b
e
in
p
u
t in
to
t
h
e
d
is
cr
i
m
in
ato
r
co
m
b
in
ed
with
th
e
n
ewly
cr
ea
ted
im
ag
e.
Step
3
: A
s
tr
ea
m
o
f
im
ag
es f
r
o
m
th
e
r
ea
l,
g
r
o
u
n
d
-
tr
u
th
d
atas
et
is
d
eliv
er
ed
in
to
a
d
is
cr
im
in
ato
r
alo
n
g
with
th
e
n
ewly
g
en
er
ate
d
im
ag
e.
Step
4
:
T
h
e
d
is
cr
im
in
ato
r
r
ea
ll
y
tak
es a
n
d
p
ictu
r
es a
n
d
r
etu
r
n
s
lik
elih
o
o
d
th
at
co
m
p
r
is
e
o
f
n
u
m
b
er
s
b
etwe
en
0
an
d
1
,
w
h
en
0
in
d
icate
s
an
im
ag
e
an
d
1
d
e
n
o
tes an
au
th
e
n
tic
im
ag
e.
Ou
tp
u
t: T
o
d
etec
t c
y
b
er
t
h
r
ea
t
s
an
d
class
if
y
d
if
f
er
en
t a
ttack
s
.
Sto
p
4.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
4
.
1
.
Check
ing
f
o
r
nu
ll v
a
lue
s
T
h
e
r
esu
lts
h
a
v
in
g
n
o
n
u
ll
d
at
aset
ar
e
r
ec
o
g
n
ized
as
m
is
s
in
g
v
alu
es.
Va
r
io
u
s
s
y
m
b
o
ls
in
cl
u
d
e
b
lan
k
ce
lls
,
n
u
ll
v
alu
es,
o
r
s
p
ec
ial
c
h
ar
ac
ter
s
lik
e
“
NA
”
o
r
“
u
n
k
n
o
wn
,
”
a
r
e
r
ea
d
ily
a
v
ailab
le
to
r
ep
r
esen
t
it.
T
h
ese
m
is
s
in
g
d
ata
p
o
in
ts
s
av
e
d
ata
an
aly
s
is
ex
tr
em
ely
h
ar
d
an
d
m
ay
r
esu
lt
in
b
iased
o
r
in
ac
cu
r
ate
f
in
d
in
g
s
.
T
o
o
b
tain
in
g
th
e
q
u
ality
o
f
d
ataset
n
ee
d
to
p
er
f
o
r
m
i
n
g
v
ar
io
u
s
d
ata
p
r
ep
r
o
ce
s
s
in
g
tech
n
iq
u
es
o
n
e
o
f
th
em
ar
e
h
an
d
lin
g
m
is
s
in
g
v
alu
e
an
d
c
h
ec
k
in
g
th
e
n
u
ll
v
al
u
es.
Af
te
r
ch
ec
k
i
n
g
n
u
ll
v
alu
es,
th
e
m
o
d
el
p
e
r
f
o
r
m
s
an
d
tak
es
co
r
r
ec
t
d
ec
is
i
o
n
s
b
y
r
e
p
l
ac
e
with
"NA
"
o
r
Nan
.
I
n
a
d
eq
u
ate
m
ain
ten
an
ce
m
ay
ca
u
s
e
p
ast
d
ata
to
b
ec
o
m
e
co
r
r
u
p
te
d
.
Fo
r
a
v
ar
iety
o
f
r
e
aso
n
s
,
s
o
m
e
f
ield
s
d
o
n
o
t
r
ec
o
r
d
o
b
s
er
v
atio
n
s
.
Hu
m
a
n
er
r
o
r
m
ig
h
t
en
d
u
p
i
n
a
f
ailu
r
e
to
r
ec
o
r
d
th
e
v
alu
es.
T
h
e
v
al
u
es
wer
e
n
o
t
p
u
r
p
o
s
ef
u
lly
s
er
v
e
d
as
b
y
th
e
u
s
er
.
T
h
is
s
h
o
ws
th
at
th
e
p
ar
ticip
an
t n
eg
lecte
d
to
r
esp
o
n
d
.
T
h
e
r
esu
lts
as sh
o
wn
in
Fig
u
r
e
5
,
th
er
e
is
n
o
an
y
n
u
ll v
al
u
es f
o
u
n
d
.
4
.
2
.
Vis
ua
liza
t
io
n
Vis
u
aliza
tio
n
o
f
n
u
ll
v
alu
es
u
s
in
g
v
alu
es
f
o
r
th
e
m
ain
v
ar
iab
le
o
f
in
ter
est
ac
r
o
s
s
two
ax
i
s
v
ar
iab
les
ar
e
r
ep
r
esen
ted
as
a
g
r
id
o
f
co
lo
r
ed
s
q
u
ar
es
in
a
h
ea
t
m
ap
as
s
h
o
wn
in
Fig
u
r
e
6
.
A
p
o
wer
f
u
l
to
o
l
f
o
r
co
n
v
ey
i
n
g
n
u
m
er
ical
d
ata
is
h
ea
tm
ap
d
ata
v
is
u
aliza
tio
n
,
w
h
ich
u
s
es
co
lo
u
r
s
to
r
ep
r
es
en
t
n
u
m
b
er
s
.
I
t
wo
r
k
s
p
ar
ticu
lar
ly
n
icely
f
o
r
f
in
d
i
n
g
tr
en
d
s
,
p
atter
n
s
,
an
d
ab
n
o
r
m
alities
in
b
ig
d
atasets
.
T
h
e
d
ef
in
itio
n
,
ty
p
es,
b
en
ef
its
an
d
b
est
p
r
ac
tices
f
o
r
h
ea
tm
ap
d
ata
v
is
u
aliza
tio
n
will
all
b
e
co
v
er
ed
in
th
is
ar
ticl
e.
A
h
ea
t
m
ap
is
a
two
-
d
im
en
s
io
n
a
l
v
is
u
aliza
tio
n
o
f
d
ata
wh
er
e
d
if
f
er
e
n
t
v
alu
es
ar
e
p
r
esen
ted
as
d
if
f
er
e
n
t
co
lo
u
r
s
.
User
s
ca
n
r
ap
id
ly
u
n
d
er
s
tan
d
th
e
m
o
s
t
i
m
p
o
r
tan
t
o
r
im
p
o
r
tan
t
d
ata
p
o
in
ts
with
th
e
h
elp
o
f
a
b
asi
c
h
ea
t
m
ap
,
wh
ic
h
in
s
tan
tly
o
f
f
er
s
a
v
is
u
al
s
u
m
m
ar
y
o
f
d
ata
alo
n
g
two
a
x
es.
T
h
e
u
s
er
ca
n
co
m
p
r
e
h
en
d
co
m
p
lex
d
ata
s
ets
with
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
Mech
a
n
iz
ed
n
etw
o
r
k
b
a
s
ed
cy
b
er
-
a
tta
ck
d
etec
tio
n
a
n
d
cla
s
s
ifica
tio
n
u
s
in
g
…
(
K
a
tika
m
M
a
h
esh
)
1759
th
e
h
elp
o
f
m
o
r
e
in
t
r
icate
h
ea
t
m
ap
s
.
Data
p
o
in
ts
in
a
d
ata
s
et
ca
n
b
e
v
iewe
d
u
s
in
g
a
h
ea
t
m
ap
.
A
co
m
m
o
n
tr
ait
u
n
ites
all
h
ea
t
m
ap
s
:
th
ey
co
n
v
ey
th
e
p
o
ten
tial
co
r
r
elati
o
n
s
b
etwe
en
th
e
v
ar
iab
les
d
ep
icted
o
n
th
e
x
-
a
x
is
an
d
y
-
a
x
is
b
y
u
s
in
g
v
ar
io
u
s
co
lo
r
s
o
r
s
h
ad
es o
f
th
e
s
am
e
co
l
o
r
to
in
d
icate
v
ar
io
u
s
v
alu
es.
Fig
u
r
e
5
.
C
h
ec
k
i
n
g
n
u
ll v
alu
e
s
f
o
r
KDD_
C
UP9
9
d
ataset
4
.
3
.
O
v
er
a
ll f
e
a
t
ures g
et
t
ing
o
nly
t
he
ca
t
eg
o
rica
l f
e
a
t
ures
T
h
er
e
is
a
lim
ited
r
an
g
e
o
f
p
o
s
s
ib
le
v
alu
es
f
o
r
ca
teg
o
r
ical
d
ata
as
s
h
o
wn
in
Fig
u
r
e
7
.
Fo
r
ex
am
p
le,
th
e
v
ar
io
u
s
an
im
al
s
p
ec
ies
f
o
u
n
d
in
a
n
atio
n
al
p
a
r
k
.
T
h
e
s
tr
ee
t
n
am
es
in
a
ce
r
tain
city
wh
eth
er
an
em
ail
is
s
p
am
o
r
n
o
t
th
e
ex
ter
io
r
p
ai
n
t
co
lo
u
r
s
o
f
h
o
u
s
es
.
T
h
e
wo
r
k
in
g
with
n
u
m
er
ical
d
ata
s
ec
tio
n
d
is
cu
s
s
es
b
in
n
ed
n
u
m
b
er
s
.
C
ateg
o
r
ical
d
ata
ar
e
th
o
s
e
th
at
ca
n
b
e
g
r
o
u
p
e
d
o
r
d
ef
in
ed
.
I
n
s
tatis
tics
,
th
is
f
o
r
m
o
f
d
ata
is
m
ad
e
u
p
o
f
v
a
r
iab
le
ca
teg
o
r
ies
o
r
d
at
a
th
at
is
g
r
o
u
p
ed
.
I
t
ca
n
b
e
o
b
tain
ed
f
r
o
m
o
b
s
er
v
atio
n
s
o
f
q
u
a
n
titativ
e
d
ata
g
r
o
u
p
ed
with
in
s
p
ec
if
ied
i
n
ter
v
als
o
r
f
r
o
m
o
b
s
er
v
atio
n
s
o
f
q
u
alitativ
e
d
ata
th
at
a
r
e
d
i
s
till
ed
in
to
co
u
n
ts
.
Qu
alitativ
e
d
ata
is
an
o
th
er
n
am
e
f
o
r
d
ata
th
at
ca
n
b
e
ca
t
eg
o
r
ized
.
T
h
e
s
im
p
lest
an
d
p
r
im
ar
y
ca
teg
o
r
ical
-
co
lu
m
n
en
co
d
in
g
ap
p
r
o
ac
h
is
o
n
e
-
h
o
t
en
co
d
in
g
.
E
ac
h
ca
t
eg
o
r
y
o
u
g
h
t
to
h
a
v
e
its
o
wn
m
u
lti
-
d
ig
it
b
in
ar
y
n
u
m
b
er
.
T
h
e
r
ef
o
r
e,
th
e
n
u
m
b
er
o
f
ca
teg
o
r
ies
f
o
r
th
e
ca
teg
o
r
ical
ch
ar
ac
ter
is
tic
to
b
e
e
n
c
o
d
ed
is
e
q
u
al
to
th
e
n
u
m
b
er
o
f
d
ig
its
.
T
h
e
ter
m
“
o
n
e
-
hot
”
co
m
es
f
r
o
m
th
e
b
in
ar
y
n
u
m
b
e
r
'
s
o
n
e
d
ig
it
b
ein
g
1
an
d
ev
er
y
o
t
h
er
d
ig
it
b
e
ze
r
o
s
.
Fig
u
r
e
6
.
Vis
u
aliza
tio
n
o
f
n
u
ll
v
alu
es u
s
in
g
h
ea
t
m
ap
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
9
,
No
.
3
,
Sep
tem
b
er
20
25
:
1
7
5
5
-
1
7
64
1760
4
.
4
.
T
a
rg
e
t
a
t
t
a
c
k
s
t
y
pes
T
ar
g
eted
h
a
r
m
ty
p
ically
em
p
l
o
y
s
s
tr
ateg
ies
th
at
ar
e
co
m
p
a
r
ab
le
with
th
o
s
e
o
f
r
eg
u
lar
o
n
li
n
e
th
r
ea
ts
,
lik
e
m
alwa
r
e,
ex
p
l
o
its
,
co
r
r
u
p
ted
o
r
f
a
k
e
web
s
ites
,
an
d
m
ali
cio
u
s
em
ails
.
T
h
er
e
ar
e
n
u
m
er
o
u
s
way
s
in
wh
ich
tar
g
eted
attac
k
s
a
r
e
d
if
f
er
en
t
f
r
o
m
tr
ad
itio
n
al
in
ter
n
et
th
r
ea
ts
.
Usu
ally
,
tar
g
eted
attac
k
s
ar
e
ca
r
r
ie
d
o
u
t
as
ca
m
p
aig
n
s
.
Ad
v
an
ce
d
p
er
s
is
ten
t
th
r
ea
ts
(
APTs)
ar
e
n
o
t
is
o
l
ated
in
cid
en
ts
b
ec
a
u
s
e
th
ey
a
r
e
o
f
ten
ca
r
r
ied
o
u
t
as
p
ar
t
o
f
ca
m
p
aig
n
s
,
w
h
ich
ar
e
a
s
er
ies
o
f
f
r
u
itles
s
an
d
s
u
cc
ess
f
u
l
attem
p
ts
o
v
er
tim
e
to
ac
ce
s
s
a
tar
g
et'
s
n
etwo
r
k
in
g
r
ea
ter
a
n
d
g
r
ea
ter
d
etail.
T
h
e
wo
r
k
tar
g
ete
d
f
o
r
d
etec
tin
g
an
d
class
if
y
in
g
u
n
iq
u
e
a
ttack
s
ty
p
es
s
u
ch
as
n
o
r
m
al,
d
o
s
,
p
r
o
b
e,
r
2
l,
u
2
r
with
a
s
er
ies
th
at
h
as
t
h
e
co
u
n
ts
o
f
ea
ch
v
alu
e
is
r
et
u
r
n
ed
b
y
th
e
v
alu
e.
co
u
n
ts
(
)
m
eth
o
d
as
s
h
o
wn
in
Fig
u
r
e
8
.
I
n
o
th
er
wo
r
d
s
,
th
is
m
eth
o
d
r
etu
r
n
s
a
n
u
m
b
er
o
f
u
n
iq
u
e
item
s
in
an
y
p
ar
ticu
lar
co
lu
m
n
f
r
o
m
a
d
ata
f
r
am
e.
Fig
u
r
e
7
.
C
ateg
o
r
ical
f
ea
tu
r
es
Fig
u
r
e
8
.
T
a
r
g
et
attac
k
s
ty
p
es
4
.
5
.
Dis
t
ributio
n
o
f
a
t
t
a
c
k
s
t
y
pes
B
y
g
iv
in
g
th
e
v
ar
ia
b
les,
a
r
an
g
e
th
at
in
clu
d
es
p
o
s
s
ib
le
v
alu
es,
s
tatis
tica
l
d
is
tr
ib
u
ti
o
n
s
aid
in
r
ec
o
g
n
izin
g
is
s
u
es
an
d
ar
e
h
i
g
h
ly
u
s
ef
u
l
in
d
ata
s
cien
ce
a
n
d
m
ac
h
in
e
lea
r
n
in
g
.
T
h
e
att
ac
k
d
is
tr
ib
u
tio
n
is
s
h
o
wn
in
p
ie
ch
ar
t
in
Fig
u
r
e
9
with
d
if
f
er
en
t
attac
k
s
d
etec
tio
n
an
d
class
if
icatio
n
.
T
h
e
d
etec
tio
n
an
d
class
if
icatio
n
o
f
attac
k
s
s
u
c
h
as
n
o
r
m
al
,
Do
S,
p
r
o
b
e,
R
2
L
,
U2
R
ca
n
b
e
s
h
o
wn
in
p
ie
ch
a
r
t.
T
h
e
v
ar
ia
b
le
f
o
r
wh
ich
f
o
r
ec
ast
o
r
ex
p
la
n
atio
n
s
ar
e
s
o
u
g
h
t
is
k
n
o
wn
as
th
e
d
ep
en
d
e
n
t
v
a
r
iab
le.
Pre
d
ictin
g
a
ta
r
g
et
v
a
r
iab
le
b
ased
o
n
th
e
v
alu
es
o
f
a
g
r
o
u
p
o
f
in
p
u
t
v
a
r
iab
les
is
k
n
o
wn
a
s
s
u
p
er
v
is
ed
lea
r
n
in
g
.
T
h
e
p
r
i
ce
o
f
a
h
o
u
s
e
co
u
l
d
b
e
th
e
d
e
p
en
d
e
n
t
v
ar
iab
le
i
n
a
r
eg
r
ess
io
n
p
r
o
b
lem
,
w
h
er
ea
s
th
e
n
eig
h
b
o
r
h
o
o
d
,
lo
t
s
ize,
n
u
m
b
er
o
f
b
ed
r
o
o
m
s
,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
Mech
a
n
iz
ed
n
etw
o
r
k
b
a
s
ed
cy
b
er
-
a
tta
ck
d
etec
tio
n
a
n
d
cla
s
s
ifica
tio
n
u
s
in
g
…
(
K
a
tika
m
M
a
h
esh
)
1761
an
d
o
th
er
f
ac
to
r
s
co
u
ld
b
e
th
e
i
n
d
ep
en
d
e
n
t
v
ar
iab
les.
On
th
e
o
th
er
h
an
d
,
in
d
e
p
en
d
e
n
t
v
ar
iab
les
also
ca
lled
to
as
p
r
ed
icto
r
v
a
r
iab
les
ar
e
em
p
lo
y
ed
to
ex
p
lain
o
r
p
r
o
d
u
ce
p
r
ed
ictio
n
s
f
o
r
th
e
v
ar
iatio
n
in
th
e
d
ep
e
n
d
en
t
v
ar
iab
le
(
th
e
o
b
jectiv
e)
.
Var
iab
les
m
ig
h
t
h
av
e
a
co
n
tin
u
o
u
s
o
r
ca
teg
o
r
ica
l
s
tr
u
ctu
r
e
an
d
ca
n
b
e
eith
er
q
u
an
titativ
e
o
r
q
u
alitativ
e.
T
o
im
p
r
o
v
e
its
p
r
ed
ictiv
e
v
al
u
e,
d
ata
ca
n
b
e
s
ca
led
o
r
tr
a
n
s
f
o
r
m
ed
.
T
h
e
r
esu
lt
in
Fig
u
r
e
9
s
h
o
ws
th
e
d
is
tr
ib
u
tio
n
o
f
v
a
r
io
u
s
attac
k
s
'
d
u
r
atio
n
'
co
lu
m
n
d
is
tr
ib
u
tio
n
s
p
litt
in
g
th
e
d
ataset
in
t
o
d
ep
en
d
e
n
t
an
d
in
d
ep
e
n
d
en
t
f
e
atu
r
es.
Fig
u
r
e
9
.
Dis
tr
ib
u
tio
n
o
f
attac
k
s
ty
p
es
4
.
6
.
No
r
m
a
liza
t
io
n
T
wo
im
p
o
r
tan
t
m
eth
o
d
s
in
d
ata
p
r
ep
r
o
ce
s
s
in
g
ar
e
n
o
r
m
ali
za
tio
n
an
d
s
tan
d
ar
d
izatio
n
.
A
d
ju
s
ted
b
y
n
o
r
m
aliza
tio
n
,
th
e
d
ata
t
h
at
f
a
lls
b
etwe
en
0
an
d
1
,
b
u
t
s
tan
d
ar
d
izatio
n
in
v
o
lv
es
r
escalin
g
t
h
e
d
ata
to
h
av
e
t
h
e
s
am
e
s
tan
d
ar
d
d
e
v
iatio
n
an
d
m
ea
n
.
On
e
o
f
t
h
e
m
o
s
t
wi
d
ely
u
s
ed
n
o
r
m
alizin
g
tech
n
i
q
u
es,
th
e
m
in
-
m
ax
m
eth
o
d
,
was
u
s
ed
in
th
e
cu
r
r
en
t
s
tu
d
y
.
Min
-
m
a
x
s
ca
lin
g
is
co
m
m
o
n
ly
r
ef
er
r
ed
to
as
“
n
o
r
m
aliza
tio
n
.
”
Featu
r
es a
r
e
ch
an
g
e
d
to
a
d
ef
i
n
ed
r
an
g
e,
u
s
u
ally
0
–
1
.
T
h
e
m
in
-
m
ax
s
ca
lin
g
is
s
h
o
wn
in
(
1
)
.
−
−
=
(
1
)
T
h
e
r
an
d
o
m
f
ea
tu
r
e
v
alu
e
‘
X
’
is
th
e
o
n
e
th
at
n
ee
d
s
to
b
e
n
o
r
m
alize
d
.
T
h
e
d
ataset'
s
m
i
n
im
al
an
d
m
ax
im
u
m
f
ea
tu
r
e
v
alu
es
ar
e
d
en
o
ted
b
y
Xm
in
an
d
Xm
ax
,
r
esp
ec
tiv
ely
.
T
h
e
n
o
r
m
alize
d
v
alu
e
is
0
wh
e
n
‘
X’
is
th
e
m
in
im
al
v
al
u
e
s
in
ce
th
e
n
u
m
er
at
o
r
is
ze
r
o
(
Xm
in
-
Xm
in
)
.
T
h
e
n
o
r
m
alize
d
v
alu
e
is
1
wh
e
n
‘
X’
is
th
e
m
ax
im
u
m
v
alu
e
s
in
ce
th
e
n
u
m
er
ato
r
eq
u
als
th
e
d
en
o
m
in
at
o
r
(
Xm
ax
-
Xm
in
)
.
T
h
e
n
o
r
m
alize
d
v
alu
e
is
in
th
e
r
an
g
e
o
f
0
an
d
1
wh
en
X
is
n
eith
er
m
in
im
u
m
n
o
r
m
a
x
im
u
m
.
T
h
is
m
eth
o
d
is
k
n
o
wn
as
th
e
m
in
-
m
ax
s
ca
lin
g
s
tr
ate
g
y
.
Z
-
s
co
r
e
n
o
r
m
aliza
tio
n
(
s
tan
d
ar
d
izatio
n
)
ad
j
u
s
ts
f
ea
tu
r
es
to
h
av
e
a
m
ea
n
(
μ
)
o
f
0
an
d
a
s
tan
d
a
r
d
d
ev
iatio
n
(
σ
)
o
f
1
,
u
s
in
g
a
Ga
u
s
s
ian
(
b
ell
cu
r
v
e)
d
is
tr
ib
u
tio
n
o
f
th
e
d
ata.
T
h
e
s
tan
d
a
r
d
izati
o
n
is
s
h
o
wn
in
(
2
)
.
‘
’
=
−
(2
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
9
,
No
.
3
,
Sep
tem
b
er
20
25
:
1
7
5
5
-
1
7
64
1762
4
.
7
.
H
a
nd
lin
g
t
he
cla
s
s
im
ba
la
nce
us
ing
S
M
O
T
E
T
ec
hn
i
qu
e
On
e
o
f
th
e
m
o
s
t
co
m
m
o
n
o
v
er
s
am
p
lin
g
tech
n
iq
u
es
f
o
r
r
eso
lv
in
g
d
if
f
icu
lties
with
im
b
al
an
ce
is
th
e
s
y
n
th
etic
m
in
o
r
ity
o
v
e
r
s
am
p
lin
g
tech
n
i
q
u
e,
o
r
SMOT
E
tech
n
iq
u
e
.
B
y
r
ep
licatin
g
m
i
n
o
r
ity
class
s
itu
ati
o
n
s
at
r
an
d
o
m
,
it
aim
s
to
r
ea
c
h
class
d
is
tr
ib
u
tio
n
b
alan
ce
b
y
u
tili
zin
g
o
ld
m
in
o
r
ity
in
s
tan
ce
s
.
SMOT
E
b
u
ild
s
n
ew
m
in
o
r
ity
in
s
tan
ce
s
th
at
it
g
en
er
ates
f
r
o
m
im
b
lear
n
.
Ov
er
s
a
m
p
lin
g
im
p
o
r
t
SMOT
E
f
r
o
m
co
llectio
n
s
im
p
o
r
t
co
u
n
ter
.
B
ef
o
r
e
SMOT
E
,
ch
ec
k
th
e
class
d
i
s
tr
ib
u
tio
n
p
r
in
t (
"Cl
ass
d
is
tr
ib
u
tio
n
b
ef
o
r
e
SMOT
E
:",
C
o
u
n
ter
(
Y)
)
Setu
p
to
th
e
SMOT
E
o
b
ject:
m
o
tes =
SMOT
E
(
r
an
d
o
m
s
tate
=
4
2
,
s
am
p
lin
g
s
tr
ateg
y
=
"a
u
to
")
Ap
p
ly
SMOT
E
to
b
alan
ce
th
e
d
ataset: sm
o
te.
f
it_
r
esam
p
le
(
X,
Y)
=
r
esam
p
led
,
y
_
r
esam
p
led
Ver
if
y
th
e
d
is
tr
ib
u
tio
n
o
f
ea
ch
class
o
n
SMOT
E
p
r
in
t (
"Cl
ass
d
is
tr
ib
u
tio
n
o
n
SMOT
E
:",
C
o
u
n
ter
(
r
esam
p
led
)
.
I
n
f
er
r
e
d
f
r
o
m
t
h
e
ex
p
er
im
en
t
al
r
esu
lts
,
th
e
GAN
m
o
d
el
a
ch
iev
es
ex
tr
ao
r
d
in
ar
y
ac
cu
r
a
cy
,
attac
k
d
etec
tin
g
an
d
class
if
icatio
n
.
R
esu
lts
v
alid
ate
th
e
ef
f
ec
tiv
en
ess
o
f
th
e
o
p
tim
ized
DNN
-
GAN
m
o
d
el.
W
ith
th
e
o
ld
tech
n
iq
u
e,
u
s
in
g
I
DS
ju
s
t
d
etec
tin
g
an
d
class
if
y
in
g
o
n
ly
n
o
r
m
al
attac
k
s
b
u
t
th
e
s
e
ar
e
n
o
t
a
b
le
to
m
o
n
ito
r
in
g
th
e
n
etwo
r
k
tr
af
f
i
c.
So
,
with
th
e
ac
h
iev
ed
r
esu
l
ts
o
f
d
if
f
er
en
t
at
tack
ty
p
es
s
u
ch
as
n
o
r
m
al,
D
o
S,
Pro
b
e,
R
2
L
,
U2
R
u
s
in
g
p
r
o
p
o
s
ed
m
o
d
el:
h
y
b
r
id
DNN
-
GA
N
wh
ich
ca
n
m
o
n
ito
r
n
etwo
r
k
s
tr
af
f
ic
ef
f
icien
tly
.
T
h
e
co
m
p
a
r
ativ
e
an
aly
s
is
is
s
h
o
wn
in
T
ab
le
1
.
T
ab
le
1
.
C
o
m
p
a
r
ativ
e
an
aly
s
is
A
i
m
A
t
t
a
c
k
t
y
p
e
C
y
b
e
r
a
t
t
a
c
k
d
e
t
e
c
t
i
n
g
a
n
d
c
l
a
ss
i
f
i
c
a
t
i
o
n
U
si
n
g
I
D
S
U
si
n
g
p
r
o
p
o
se
d
m
o
d
e
l
:
h
y
b
r
i
d
D
N
N
-
GAN
N
o
r
mal
a
t
t
a
c
k
s
N
o
r
mal
,
D
o
S
,
P
r
o
b
e
,
R
2
L,
U
2
R
.
5.
CO
NCLU
SI
O
N
On
e
o
f
th
e
b
ig
g
est
is
s
u
es
af
f
ec
tin
g
th
e
g
l
o
b
e
n
o
w
is
cy
b
er
attac
k
s
.
C
y
b
er
attac
k
s
ar
e
u
n
wan
ted
attem
p
ts
to
en
ter
co
m
p
u
ter
s
y
s
tem
s
u
n
au
th
o
r
ized
au
th
o
r
iz
atio
n
h
av
in
g
th
e
in
ten
t
to
s
teal,
s
h
o
w,
ch
an
g
e,
d
is
ab
le,
o
r
d
estro
y
in
f
o
r
m
atio
n
.
Du
e
to
t
h
e
f
ac
t
th
at
m
illi
o
n
s
o
f
co
m
p
u
ter
s
f
all
p
r
ey
to
t
h
is
k
in
d
o
f
ac
tiv
ity
ev
er
y
d
ay
,
wh
ich
c
o
s
ts
o
r
g
a
n
izatio
n
s
m
o
n
e
y
b
y
d
is
clo
s
in
g
s
en
s
itiv
e
in
f
o
r
m
atio
n
t
o
r
iv
al
co
m
p
an
ies,
d
ata
s
ec
u
r
ity
h
as
g
ain
e
d
p
r
o
m
in
e
n
ce
an
d
r
eq
u
ir
es
im
m
ed
iate
atten
tio
n
.
Fo
r
th
e
p
u
r
p
o
s
e
o
f
d
etec
tin
g
n
etwo
r
k
in
tr
u
s
io
n
,
th
e
r
e
ar
e
n
u
m
e
r
o
u
s
co
n
v
en
tio
n
al
n
etwo
r
k
s
ec
u
r
ity
to
o
ls
an
d
ap
p
r
o
ac
h
es
av
ailab
l
e
s
u
ch
as
th
e
o
n
es
lis
ted
b
elo
w:
an
tiv
ir
u
s
s
o
f
t
war
e
in
clu
d
es
an
ti
-
m
alwa
r
e,
en
cr
y
p
tio
n
an
d
d
ec
r
y
p
tio
n
,
an
d
ac
ce
s
s
co
n
tr
o
l
p
r
o
tectiv
e
f
ir
ewa
lls
.
Fu
r
th
e
r
m
o
r
e,
cu
r
r
en
t
I
DS
m
eth
o
d
o
lo
g
i
es
ar
e
u
n
ab
le
to
id
e
n
tify
a
n
d
class
if
y
m
an
y
ty
p
es
o
f
in
tr
u
s
io
n
s
o
n
co
m
p
u
ter
n
etwo
r
k
s
.
T
h
is
wo
r
k
class
if
ies
th
e
d
ata
b
u
t
n
o
clar
ity
ab
o
u
t
d
if
f
er
e
n
t
attac
k
s
d
etec
tio
n
.
T
o
elim
in
ate
all
th
ese
d
r
awb
ac
k
s
,
th
e
p
r
o
p
o
s
ed
wo
r
k
ca
n
av
o
id
p
itfa
ll
s
in
p
a
s
t
s
tu
d
ies.
Fu
r
th
er
m
o
r
e
,
m
a
n
y
f
o
r
m
s
o
f
cy
b
er
attac
k
s
o
n
co
m
p
u
ter
n
et
wo
r
k
s
ca
n
n
o
t
b
e
d
etec
ted
,
cla
s
s
if
ied
,
o
r
id
e
n
tifie
d
b
y
th
e
I
DS
tech
n
o
l
o
g
ies
cu
r
r
en
tly
in
u
s
e.
L
ev
e
r
ag
in
g
th
e
KDD_
C
UP
9
9
d
ataset,
th
e
p
r
o
p
o
s
ed
k
in
d
s
o
f
ass
au
lts
,
am
o
n
g
t
h
em
D
o
S,
P
r
o
b
e,
R
2
L
,
a
n
d
U2
R
ca
n
all
b
e
n
o
ticed
a
n
d
s
o
r
ted
v
ia
m
a
ch
in
e
lear
n
in
g
an
d
m
eth
o
d
s
o
f
d
ee
p
lear
n
in
g
s
u
c
h
as
n
eu
r
al
n
etwo
r
k
alg
o
r
ith
m
s
(
DNN
s
)
.
3
tier
s
:
o
n
e
f
o
r
i
n
p
u
t,
o
n
e
as
o
u
tp
u
t,
an
d
a
c
o
u
p
le
o
f
in
ter
m
ed
iar
y
elem
en
ts
m
ak
e
u
p
a
DNN
.
I
n
f
u
tu
r
e
s
co
p
e,
d
etec
tin
g
an
d
c
la
s
s
if
y
in
g
a
g
r
ea
ter
n
u
m
b
er
o
f
d
if
f
er
e
n
t ty
p
es o
f
attac
k
s
will b
e
m
ad
e
to
r
ea
c
h
ac
cu
r
ac
y
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
Au
th
o
r
s
s
tate
n
o
f
u
n
d
in
g
in
v
o
lv
ed
.
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
T
h
is
jo
u
r
n
al
u
s
es
th
e
C
o
n
tr
ib
u
to
r
R
o
les
T
ax
o
n
o
m
y
(
C
R
ed
iT
)
to
r
ec
o
g
n
ize
in
d
iv
id
u
al
au
th
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
th
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
llab
o
r
atio
n
.
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
Katik
am
Ma
h
esh
✓
✓
✓
✓
✓
✓
✓
✓
✓
Ku
n
jam
Nag
eswar
a
R
ao
✓
✓
✓
✓
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
Mech
a
n
iz
ed
n
etw
o
r
k
b
a
s
ed
cy
b
er
-
a
tta
ck
d
etec
tio
n
a
n
d
cla
s
s
ifica
tio
n
u
s
in
g
…
(
K
a
tika
m
M
a
h
esh
)
1763
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
Au
th
o
r
s
s
tate
n
o
co
n
f
lict o
f
in
t
er
est.
DATA AV
AI
L
AB
I
L
I
T
Y
Data
av
ailab
ilit
y
d
o
es n
o
t a
p
p
l
y
to
th
is
p
ap
e
r
as n
o
n
ew
d
ata
wer
e
cr
ea
ted
o
r
an
aly
ze
d
in
th
is
s
tu
d
y
.
R
E
F
E
R
E
NC
E
S
[
1
]
Q
.
A
b
u
A
l
-
H
a
i
j
a
a
n
d
S
.
Z
e
i
n
-
S
a
b
a
t
t
o
,
“
A
n
e
f
f
i
c
i
e
n
t
d
e
e
p
-
l
e
a
r
n
i
n
g
-
b
a
se
d
d
e
t
e
c
t
i
o
n
a
n
d
c
l
a
ssi
f
i
c
a
t
i
o
n
s
y
st
e
m
f
o
r
c
y
b
e
r
-
a
t
t
a
c
k
s
i
n
I
o
T
c
o
mm
u
n
i
c
a
t
i
o
n
n
e
t
w
o
r
k
s
,
”
El
e
c
t
r
o
n
i
c
s
,
v
o
l
.
9
,
n
o
.
1
2
,
p
.
2
1
5
2
,
D
e
c
.
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
e
l
e
c
t
r
o
n
i
c
s9
1
2
2
1
5
2
.
[
2
]
Y
.
Z
h
o
u
,
G
.
C
h
e
n
g
,
S
.
J
i
a
n
g
,
a
n
d
M
.
D
a
i
,
“
B
u
i
l
d
i
n
g
a
n
e
f
f
i
c
i
e
n
t
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
sel
e
c
t
i
o
n
a
n
d
e
n
s
e
mb
l
e
c
l
a
ssi
f
i
e
r
,
”
C
o
m
p
u
t
e
r
N
e
t
w
o
rks
,
v
o
l
.
1
7
4
,
p
.
1
0
7
2
4
7
,
J
u
n
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
m
n
e
t
.
2
0
2
0
.
1
0
7
2
4
7
.
[
3
]
R
.
V
i
n
a
y
a
k
u
m
a
r
,
M
.
A
l
a
z
a
b
,
K
.
P
.
S
o
ma
n
,
P
.
P
o
o
r
n
a
c
h
a
n
d
r
a
n
,
A
.
A
l
-
N
e
mr
a
t
,
a
n
d
S
.
V
e
n
k
a
t
r
a
m
a
n
,
“
D
e
e
p
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
f
o
r
i
n
t
e
l
l
i
g
e
n
t
i
n
t
r
u
s
i
o
n
d
e
t
e
c
t
i
o
n
s
y
st
e
m,
”
I
EEE
Ac
c
e
ss
,
v
o
l
.
7
,
p
p
.
4
1
5
2
5
–
4
1
5
5
0
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
a
c
c
e
ss
.
2
0
1
9
.
2
8
9
5
3
3
4
.
[
4
]
N
.
S
h
o
n
e
,
T
.
N
.
N
g
o
c
,
V
.
D
.
P
h
a
i
,
a
n
d
Q
.
S
h
i
,
“
A
d
e
e
p
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
t
o
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
,
”
I
EEE
T
ra
n
s
a
c
t
i
o
n
s
o
n
Em
e
rg
i
n
g
T
o
p
i
c
s i
n
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
,
v
o
l
.
2
,
n
o
.
1
,
p
p
.
4
1
–
5
0
,
F
e
b
.
2
0
1
8
,
d
o
i
:
1
0
.
1
1
0
9
/
t
e
t
c
i
.
2
0
1
7
.
2
7
7
2
7
9
2
.
[
5
]
M
.
A
l
me
h
d
h
a
r
e
t
a
l
.
,
“
D
e
e
p
l
e
a
r
n
i
n
g
i
n
t
h
e
f
a
st
l
a
n
e
:
a
s
u
r
v
e
y
o
n
a
d
v
a
n
c
e
d
i
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
sy
s
t
e
m
s
f
o
r
i
n
t
e
l
l
i
g
e
n
t
v
e
h
i
c
l
e
n
e
t
w
o
r
k
s,”
I
EEE
O
p
e
n
J
o
u
r
n
a
l
o
f
V
e
h
i
c
u
l
a
r
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
5
,
p
p
.
8
6
9
–
9
0
6
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
o
j
v
t
.
2
0
2
4
.
3
4
2
2
2
5
3
.
[
6
]
W
.
L.
A
l
-
Y
a
s
e
e
n
,
Z
.
A
.
O
t
h
ma
n
,
a
n
d
M
.
Z.
A
.
N
a
z
r
i
,
“
M
u
l
t
i
-
l
e
v
e
l
h
y
b
r
i
d
su
p
p
o
r
t
v
e
c
t
o
r
mac
h
i
n
e
a
n
d
e
x
t
r
e
me
l
e
a
r
n
i
n
g
m
a
c
h
i
n
e
b
a
s
e
d
o
n
m
o
d
i
f
i
e
d
K
-
mea
n
s
f
o
r
i
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
s
y
st
e
m,”
E
x
p
e
rt
S
y
s
t
e
m
s
w
i
t
h
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
6
7
,
p
p
.
2
9
6
–
3
0
3
,
J
a
n
.
2
0
1
7
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
sw
a
.
2
0
1
6
.
0
9
.
0
4
1
.
[
7
]
M
.
B
e
l
o
u
c
h
,
S
.
E
l
,
a
n
d
M
.
I
d
h
a
mm
a
d
,
“
A
t
w
o
-
st
a
g
e
c
l
a
ss
i
f
i
e
r
a
p
p
r
o
a
c
h
u
si
n
g
r
e
p
t
r
e
e
a
l
g
o
r
i
t
h
m
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
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
A
d
v
a
n
c
e
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
8
,
n
o
.
6
,
2
0
1
7
,
d
o
i
:
1
0
.
1
4
5
6
9
/
i
j
a
c
s
a
.
2
0
1
7
.
0
8
0
6
5
1
.
[
8
]
I
.
A
.
M
a
h
a
r
,
W
.
L
i
b
i
n
g
,
G
.
A
.
R
a
h
u
,
Z
.
A
.
M
a
h
e
r
,
a
n
d
M
.
Y
.
K
o
o
n
d
h
a
r
,
“
F
e
a
t
u
r
e
b
a
se
d
c
o
m
p
a
r
a
t
i
v
e
a
n
a
l
y
si
s
o
f
t
r
a
d
i
t
i
o
n
a
l
i
n
t
r
u
s
i
o
n
d
e
t
e
c
t
i
o
n
sy
st
e
m
a
n
d
s
o
f
t
w
a
r
e
-
d
e
f
i
n
e
d
n
e
t
w
o
r
k
i
n
g
b
a
s
e
d
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
2
0
2
3
I
EEE
8
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
En
g
i
n
e
e
ri
n
g
T
e
c
h
n
o
l
o
g
i
e
s
a
n
d
A
p
p
l
i
e
d
S
c
i
e
n
c
e
s
(
I
C
ETA
S
)
,
O
c
t
.
2
0
2
3
,
p
p
.
1
–
5
,
d
o
i
:
1
0
.
1
1
0
9
/
i
c
e
t
a
s
5
9
1
4
8
.
2
0
2
3
.
1
0
3
4
6
4
9
7
.
[
9
]
D
.
R
.
D
i
p
t
a
,
J.
T
a
n
,
a
n
d
B
.
G
u
l
mez
o
g
l
u
,
“
S
y
st
e
ma
t
i
c
a
l
e
v
a
si
o
n
f
r
o
m
l
e
a
r
n
i
n
g
-
b
a
s
e
d
m
i
c
r
o
a
r
c
h
i
t
e
c
t
u
r
a
l
a
t
t
a
c
k
d
e
t
e
c
t
i
o
n
t
o
o
l
s,”
I
EEE
J
o
u
rn
a
l
o
n
Em
e
r
g
i
n
g
a
n
d
S
e
l
e
c
t
e
d
T
o
p
i
c
s
i
n
C
i
r
c
u
i
t
s
a
n
d
S
y
st
e
m
s
,
v
o
l
.
1
4
,
n
o
.
4
,
p
p
.
8
2
3
–
8
3
3
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
j
e
t
c
a
s.
2
0
2
4
.
3
4
9
1
4
9
7
.
[
1
0
]
M
.
A
h
m
e
d
,
A
.
N
a
ser
M
a
h
mo
o
d
,
a
n
d
J
.
H
u
,
“
A
s
u
r
v
e
y
o
f
n
e
t
w
o
r
k
a
n
o
mal
y
d
e
t
e
c
t
i
o
n
t
e
c
h
n
i
q
u
e
s,”
J
o
u
r
n
a
l
o
f
N
e
t
w
o
r
k
a
n
d
C
o
m
p
u
t
e
r
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
6
0
,
p
p
.
1
9
–
3
1
,
J
a
n
.
2
0
1
6
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
n
c
a
.
2
0
1
5
.
1
1
.
0
1
6
.
[
1
1
]
J.
C
h
e
n
,
Y
.
G
u
o
,
K
.
S
h
i
,
a
n
d
M
.
Y
a
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
m
e
t
h
o
d
o
f
p
o
w
e
r
mo
n
i
t
o
r
i
n
g
sy
s
t
e
m
b
a
se
d
o
n
d
a
t
a
mi
n
i
n
g
,
”
i
n
2
0
2
2
2
n
d
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
Al
g
o
ri
t
h
m
s
,
H
i
g
h
P
e
rf
o
rm
a
n
c
e
C
o
m
p
u
t
i
n
g
a
n
d
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
(
AH
PC
AI
)
,
O
c
t
.
2
0
2
2
,
p
p
.
2
5
5
–
2
5
9
,
d
o
i
:
1
0
.
1
1
0
9
/
a
h
p
c
a
i
5
7
4
5
5
.
2
0
2
2
.
1
0
0
8
7
4
0
5
.
[
1
2
]
I
.
G
h
a
f
i
r
a
n
d
V
.
P
r
e
n
o
s
i
l
,
“
A
d
v
a
n
c
e
d
p
e
r
si
s
t
e
n
t
t
h
r
e
a
t
a
t
t
a
c
k
d
e
t
e
c
t
i
o
n
:
a
n
o
v
e
r
v
i
e
w
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
Ad
v
a
n
c
e
m
e
n
t
s
i
n
C
o
m
p
u
t
e
r
N
e
t
w
o
r
k
s
a
n
d
I
t
s
S
e
c
u
r
i
t
y
–
I
J
C
N
S
,
v
o
l
.
4
,
n
o
.
4
,
p
p
.
5
0
–
5
4
,
A
u
g
.
2
0
1
4
.
[
1
3
]
A
.
S
.
A
sh
o
o
r
a
n
d
S
.
G
o
r
e
,
“
D
i
f
f
e
r
e
n
c
e
b
e
t
w
e
e
n
i
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
s
y
st
e
m
(
I
D
S
)
a
n
d
i
n
t
r
u
s
i
o
n
p
r
e
v
e
n
t
i
o
n
s
y
st
e
m
(
I
P
S
)
,
”
i
n
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
N
e
t
w
o
rk
S
e
c
u
r
i
t
y
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
,
2
0
1
1
,
p
p
.
4
9
7
–
5
0
1
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
6
4
2
-
2
2
5
4
0
-
6
_
4
8
.
[
1
4
]
T.
V
o
l
l
m
e
r
,
J
.
A
l
v
e
s
-
F
o
ss,
a
n
d
M
.
M
a
n
i
c
,
“
A
u
t
o
n
o
mo
u
s
r
u
l
e
c
r
e
a
t
i
o
n
f
o
r
i
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
,
”
i
n
2
0
1
1
I
EE
E
S
y
m
p
o
si
u
m
o
n
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
i
n
C
y
b
e
r
S
e
c
u
r
i
t
y
(
C
I
C
S
)
,
A
p
r
.
2
0
1
1
,
p
p
.
1
–
8
,
d
o
i
:
1
0
.
1
1
0
9
/
c
i
c
y
b
s.
2
0
1
1
.
5
9
4
9
3
9
4
.
[
1
5
]
M
.
T
a
v
a
l
l
a
e
e
,
E
.
B
a
g
h
e
r
i
,
W
.
L
u
,
a
n
d
A
.
A
.
G
h
o
r
b
a
n
i
,
“
A
d
e
t
a
i
l
e
d
a
n
a
l
y
s
i
s
o
f
t
h
e
K
D
D
C
U
P
9
9
d
a
t
a
s
e
t
,
”
i
n
2
0
0
9
I
EEE
S
y
m
p
o
s
i
u
m
o
n
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
f
o
r
S
e
c
u
ri
t
y
a
n
d
D
e
f
e
n
se
Ap
p
l
i
c
a
t
i
o
n
s
,
J
u
l
.
2
0
0
9
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
c
i
sd
a
.
2
0
0
9
.
5
3
5
6
5
2
8
.
[
1
6
]
S
.
M
.
G
a
f
f
e
r
,
M
.
E.
Y
a
h
i
a
,
a
n
d
K
.
R
a
g
a
b
,
“
G
e
n
e
t
i
c
f
u
z
z
y
sy
s
t
e
m
f
o
r
i
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
:
a
n
a
l
y
si
s
o
f
i
m
p
r
o
v
i
n
g
o
f
m
u
l
t
i
c
l
a
ss
c
l
a
ss
i
f
i
c
a
t
i
o
n
a
c
c
u
r
a
c
y
u
s
i
n
g
K
D
D
C
u
p
-
9
9
i
mb
a
l
a
n
c
e
d
a
t
a
set
,
”
i
n
2
0
1
2
1
2
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
H
y
b
r
i
d
I
n
t
e
l
l
i
g
e
n
t
S
y
s
t
e
m
s (H
I
S
)
,
D
e
c
.
2
0
1
2
,
p
p
.
3
1
8
–
3
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
h
i
s.
2
0
1
2
.
6
4
2
1
3
5
4
.
[
1
7
]
Y
.
C
h
e
n
a
n
d
F
.
Y
u
a
n
,
“
D
y
n
a
m
i
c
d
e
t
e
c
t
i
o
n
o
f
ma
l
i
c
i
o
u
s
i
n
t
r
u
si
o
n
i
n
w
i
r
e
l
e
s
s
n
e
t
w
o
r
k
b
a
se
d
o
n
i
m
p
r
o
v
e
d
r
a
n
d
o
m
f
o
r
e
st
a
l
g
o
r
i
t
h
m,
”
i
n
2
0
2
2
I
E
EE
As
i
a
-
P
a
c
i
f
i
c
C
o
n
f
e
re
n
c
e
o
n
I
m
a
g
e
Pr
o
c
e
ss
i
n
g
,
El
e
c
t
ro
n
i
c
s
a
n
d
C
o
m
p
u
t
e
rs
(
I
P
EC
)
,
A
p
r
.
2
0
2
2
,
pp
.
2
7
–
3
2
,
d
o
i
:
1
0
.
1
1
0
9
/
i
p
e
c
5
4
4
5
4
.
2
0
2
2
.
9
7
7
7
5
5
7
.
[
1
8
]
L.
C
h
e
n
,
X
.
K
u
a
n
g
,
A
.
X
u
,
S
.
S
u
o
,
a
n
d
Y
.
Y
a
n
g
,
“
A
n
o
v
e
l
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
sy
s
t
e
m
b
a
se
d
o
n
C
N
N
,
”
i
n
2
0
2
0
E
i
g
h
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
A
d
v
a
n
c
e
d
C
l
o
u
d
a
n
d
Bi
g
D
a
t
a
(
C
BD
)
,
D
e
c
.
2
0
2
0
,
p
p
.
2
4
3
–
24
7
,
d
o
i
:
1
0
.
1
1
0
9
/
c
b
d
5
1
9
0
0
.
2
0
2
0
.
0
0
0
5
1
.
[
1
9
]
I
.
S
h
a
r
a
f
a
l
d
i
n
,
A
.
G
h
a
r
i
b
,
A
.
H
.
La
sh
k
a
r
i
,
a
n
d
A
.
A
.
G
h
o
r
b
a
n
i
,
“
To
w
a
r
d
s
a
r
e
l
i
a
b
l
e
i
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
b
e
n
c
h
m
a
r
k
d
a
t
a
se
t
,
”
S
o
f
t
w
a
re
N
e
t
w
o
rk
i
n
g
,
v
o
l
.
2
0
1
7
,
n
o
.
1
,
p
p
.
1
7
7
–
2
0
0
,
2
0
1
7
,
d
o
i
:
1
0
.
1
3
0
5
2
/
j
s
n
2
4
4
5
-
9
7
3
9
.
2
0
1
7
.
0
0
9
.
[
2
0
]
M
.
B
i
j
o
n
e
a
n
d
J
.
D
a
n
g
r
a
,
“
A
s
u
r
v
e
y
o
f
s
i
g
n
a
t
u
r
e
b
a
se
d
&
s
t
a
t
i
s
t
i
c
a
l
b
a
s
e
d
i
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
t
e
c
h
n
i
q
u
e
s,”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
f
o
r
S
c
i
e
n
t
i
f
i
c
Re
se
a
rc
h
&
D
e
v
e
l
o
p
m
e
n
t
,
v
o
l
.
4
,
n
o
.
8
,
p
p
.
5
8
3
–
5
8
5
,
2
0
1
6
.
[
2
1
]
L.
M
o
h
a
n
,
S
.
Ja
i
n
,
P
.
S
u
y
a
l
,
a
n
d
A
.
K
u
ma
r
,
“
D
a
t
a
mi
n
i
n
g
c
l
a
ssi
f
i
c
a
t
i
o
n
t
e
c
h
n
i
q
u
e
s
f
o
r
i
n
t
r
u
s
i
o
n
d
e
t
e
c
t
i
o
n
sy
s
t
e
m,”
i
n
2
0
2
0
1
2
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
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
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
N
e
t
w
o
r
k
s
(
C
I
C
N
)
,
S
e
p
.
2
0
2
0
,
p
p
.
3
5
1
–
3
5
5
,
d
o
i
:
1
0
.
1
1
0
9
/
c
i
c
n
4
9
2
5
3
.
2
0
2
0
.
9
2
4
2
6
4
2
.
[
2
2
]
E.
P
.
N
u
g
r
o
h
o
,
T.
D
j
a
t
n
a
,
I
.
S
.
S
i
t
a
n
g
g
a
n
g
,
A
.
B
u
o
n
o
,
a
n
d
I
.
H
e
r
mad
i
,
“
A
r
e
v
i
e
w
o
f
i
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
s
y
s
t
e
m
i
n
I
o
T
w
i
t
h
smac
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
:
c
u
r
r
e
n
t
a
n
d
f
u
t
u
r
e
r
e
e
a
r
c
h
,
”
i
n
2
0
2
0
6
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
S
c
i
e
n
c
e
i
n
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
(
I
C
S
I
T
e
c
h
)
,
O
c
t
.
2
0
2
0
,
p
p
.
1
3
8
–
1
4
3
,
d
o
i
:
1
0
.
1
1
0
9
/
i
c
s
i
t
e
c
h
4
9
8
0
0
.
2
0
2
0
.
9
3
9
2
0
7
5
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
9
,
No
.
3
,
Sep
tem
b
er
20
25
:
1
7
5
5
-
1
7
64
1764
[
2
3
]
F
.
K
u
a
n
g
,
W
.
X
u
,
a
n
d
S
.
Z
h
a
n
g
,
“
A
n
o
v
e
l
h
y
b
r
i
d
K
P
C
A
a
n
d
S
V
M
w
i
t
h
G
A
m
o
d
e
l
f
o
r
i
n
t
r
u
s
i
o
n
d
e
t
e
c
t
i
o
n
,
”
A
p
p
l
i
e
d
S
o
f
t
C
o
m
p
u
t
i
n
g
,
v
o
l
.
1
8
,
p
p
.
1
7
8
–
1
8
4
,
M
a
y
2
0
1
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
s
o
c
.
2
0
1
4
.
0
1
.
0
2
8
.
[
2
4
]
I
.
A
h
mad
,
M
.
H
u
ssa
i
n
,
A
.
A
l
g
h
a
md
i
,
a
n
d
A
.
A
l
e
l
a
i
w
i
,
“
E
n
h
a
n
c
i
n
g
S
V
M
p
e
r
f
o
r
man
c
e
i
n
i
n
t
r
u
s
i
o
n
d
e
t
e
c
t
i
o
n
u
s
i
n
g
o
p
t
i
ma
l
f
e
a
t
u
r
e
su
b
s
e
t
se
l
e
c
t
i
o
n
b
a
s
e
d
o
n
g
e
n
e
t
i
c
p
r
i
n
c
i
p
a
l
c
o
mp
o
n
e
n
t
s
,
”
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
.
2
4
,
n
o
.
7
–
8
,
p
p
.
1
6
7
1
–
1
6
8
2
,
Ap
r
.
2
0
1
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s0
0
5
2
1
-
0
1
3
-
1
3
7
0
-
6.
[
2
5
]
F
.
N
.
M
.
S
a
b
r
i
,
N
.
M
d
.
N
o
r
w
a
w
i
,
a
n
d
K
.
S
e
ma
n
,
“
I
d
e
n
t
i
f
y
i
n
g
f
a
l
se
a
l
a
r
m
r
a
t
e
s
f
o
r
i
n
t
r
u
s
i
o
n
d
e
t
e
c
t
i
o
n
s
y
st
e
m
w
i
t
h
d
a
t
a
mi
n
i
n
g
,
”
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
e
r
S
c
i
e
n
c
e
a
n
d
N
e
t
w
o
rk
S
e
c
u
ri
t
y
,
v
o
l
.
1
1
,
n
o
.
4
,
p
p
.
95
–
9
9
,
2
0
1
1
.
[
2
6
]
L.
Z
h
a
n
g
,
J.
Z
h
a
n
g
,
Y
.
C
h
e
n
,
a
n
d
S
.
La
o
,
“
H
y
b
r
i
d
i
n
t
r
u
s
i
o
n
d
e
t
e
c
t
i
o
n
b
a
se
d
o
n
d
a
t
a
mi
n
i
n
g
,
”
i
n
2
0
1
8
1
1
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
I
n
t
e
l
l
i
g
e
n
t
C
o
m
p
u
t
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
a
n
d
Au
t
o
m
a
t
i
o
n
(
I
C
I
C
T
A)
,
S
e
p
.
2
0
1
8
,
p
p
.
2
9
9
–
3
0
1
,
d
o
i
:
1
0
.
1
1
0
9
/
i
c
i
c
t
a
.
2
0
1
8
.
0
0
0
7
4
.
[
2
7
]
T.
S
o
e
w
u
,
H
e
ma
n
t
,
M
.
R
a
k
h
r
a
,
a
n
d
D
.
S
i
n
g
h
,
“
A
n
a
l
y
s
i
s
o
f
d
a
t
a
mi
n
i
n
g
-
b
a
se
d
a
p
p
r
o
a
c
h
f
o
r
i
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
sy
s
t
e
m
,
”
i
n
2
0
2
2
5
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
C
o
n
t
e
m
p
o
r
a
ry
C
o
m
p
u
t
i
n
g
a
n
d
I
n
f
o
rm
a
t
i
c
s
(
I
C
3
I
)
,
D
e
c
.
2
0
2
2
,
p
p
.
9
0
8
–
9
1
2
,
d
o
i
:
1
0
.
1
1
0
9
/
i
c
3
i
5
6
2
4
1
.
2
0
2
2
.
1
0
0
7
2
8
2
8
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
K
a
tik
a
m
Ma
h
e
sh
c
u
rre
n
tl
y
a
s
a
re
se
a
rc
h
sc
h
o
lar
a
t
A
n
d
h
ra
U
n
iv
e
rsit
y
C
o
ll
e
g
e
o
f
En
g
in
e
e
rin
g
i
n
Visa
k
h
a
p
a
t
n
a
m
In
d
ia
i
n
th
e
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
S
y
ste
m
s
En
g
i
n
e
e
rin
g
.
He
p
u
rsu
e
d
h
is
M
a
ste
r’s
in
c
o
m
p
u
ter
sc
ien
c
e
a
n
d
e
n
g
i
n
e
e
rin
g
fro
m
S
IS
TAM
Co
ll
e
g
e
i
n
S
ri
k
a
k
u
lam
.
His
a
re
a
o
f
in
tere
st
in
c
lu
d
e
s
n
e
two
r
k
s
se
c
u
rit
y
a
n
d
m
a
c
h
in
e
lea
rn
i
n
g
.
He
h
a
s
a
ro
u
n
d
0
2
p
u
b
li
c
a
ti
o
n
s
in
th
e
a
re
a
o
f
n
e
two
r
k
s
se
c
u
rit
y
a
n
d
m
a
c
h
in
e
lea
rn
in
g
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
k
a
ti
k
a
m
m
a
h
e
sh
@g
m
a
il
.
c
o
m
.
Dr
.
K
u
n
ja
m
Na
g
e
sw
a
r
a
Ra
o
wo
rk
in
g
a
s
P
ro
fe
ss
o
r
a
n
d
He
a
d
i
n
th
e
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
S
y
ste
m
s
En
g
in
e
e
rin
g
,
U
n
iv
e
rsit
y
Co
ll
e
g
e
o
f
En
g
in
e
e
rin
g
,
An
d
h
ra
Un
iv
e
rsity
,
Visa
k
h
a
p
a
t
n
a
m
,
An
d
h
ra
P
ra
d
e
sh
,
In
d
ia.
He
c
o
m
p
lete
d
h
is
B.
Tec
h
.
i
n
c
o
m
p
u
ter
sc
ien
c
e
a
n
d
sy
ste
m
s
e
n
g
in
e
e
rin
g
fro
m
G
ITAM
En
g
i
n
e
e
rin
g
Co
ll
e
g
e
,
M
.
T
ech
.
i
n
c
o
m
p
u
ter
sc
ien
c
e
a
n
d
tec
h
n
o
l
o
g
y
fro
m
An
d
h
ra
Un
i
v
e
rsity
a
n
d
P
h
.
D
.
i
n
c
o
m
p
u
ter
sc
ien
c
e
e
n
g
in
e
e
rin
g
fro
m
An
d
h
ra
Un
i
v
e
rsity
.
His
c
u
rre
n
t
re
se
a
rc
h
in
c
lu
d
e
s
b
i
o
-
i
n
f
o
rm
a
ti
c
s,
c
o
m
p
u
ter
sc
ien
c
e
in
fo
rm
a
ti
o
n
s
y
ste
m
s,
h
e
a
lt
h
in
f
o
r
m
a
ti
c
s,
b
ig
d
a
ta
a
n
a
l
y
ti
c
s,
a
r
ti
fici
a
l
in
telli
g
e
n
c
e
a
n
d
m
a
c
h
in
e
lea
rn
in
g
,
a
lg
o
r
it
h
m
a
n
d
d
e
sig
n
a
n
a
l
y
sis
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
k
u
n
jam
n
a
g
@g
m
a
il
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.