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
4
9
7
~
1
5
0
4
I
SS
N:
2
2
5
2
-
8
9
3
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijai.v
15
.i
2
.
p
p
1
4
9
7
-
1
5
0
4
1497
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
i
.
ia
esco
r
e.
co
m
A rein
forcemen
t
-
g
uided multi
-
pha
se hy
brid archi
tec
ture
for
threat
pro
filing a
nd def
ense
towa
rds Io
T ha
ndheld
dev
ice
P
us
hp
a
Ra
j
pu
t
Na
ra
y
a
na
Sin
g
h
1
,2
,
Nee
la
m
bik
e
Sid
da
lin
g
a
ia
h
1,
3
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
,
G
M
I
n
st
i
t
u
t
e
o
f
T
e
c
h
n
o
l
o
g
y
,
D
a
v
a
n
a
g
e
r
e
,
I
n
d
i
a
2
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
,
Jaw
a
h
a
r
l
a
l
N
e
h
r
u
N
e
w
C
o
l
l
e
g
e
o
f
E
n
g
i
n
e
e
r
i
n
g
,
S
h
i
v
a
m
o
g
g
a
,
I
n
d
i
a
3
D
a
t
a
E
n
g
i
n
e
e
r
i
n
g
,
G
M
S
c
h
o
o
l
o
f
A
d
v
a
n
c
e
d
S
t
u
d
i
e
s
,
G
M
U
n
i
v
e
r
si
t
y
,
D
a
v
a
n
g
e
r
e
,
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
Sep
2
5
,
2
0
2
5
R
ev
is
ed
J
an
1
5
,
2
0
2
6
Acc
ep
ted
J
an
2
5
,
2
0
2
6
Th
e
c
o
n
tr
ib
u
ti
o
n
o
f
a
rti
ficia
l
in
t
e
ll
ig
e
n
c
e
(AI)
to
wa
rd
s
o
ffe
rin
g
p
ro
a
c
ti
v
e
se
c
u
rit
y
i
n
h
a
n
d
h
e
ld
d
e
v
ice
s
o
f
i
n
tern
e
t
of
th
i
n
g
s
(Io
T)
is
in
e
v
o
l
v
in
g
sta
g
e
.
Re
v
iew
o
f
li
tera
tu
re
sh
o
wc
a
se
s
n
o
tew
o
rt
h
y
a
t
tem
p
ts
o
f
m
a
c
h
in
e
lea
rn
in
g
(M
L)
a
n
d
d
e
e
p
lea
rn
in
g
(DL)
m
o
d
e
ls;
h
o
we
v
e
r,
th
e
y
a
re
a
larg
e
sc
o
p
e
o
f
imp
ro
v
e
m
e
n
t
t
o
wa
rd
s
b
r
id
g
in
g
th
e
tra
d
e
-
o
ff
b
e
twe
e
n
se
c
u
rit
y
a
n
d
c
o
m
p
u
tati
o
n
a
l
-
c
o
m
m
u
n
ica
ti
o
n
e
f
ficie
n
c
y
.
T
h
is
p
r
o
b
lem
is
a
d
d
re
ss
e
d
in
t
h
is
m
a
n
u
sc
rip
t
b
y
p
re
se
n
ti
n
g
a
u
n
i
q
u
e
a
n
d
in
n
o
v
a
ti
v
e
s
o
lu
ti
o
n
w
h
e
re
re
in
fo
rc
e
m
e
n
t
lea
rn
i
n
g
(R
L)
h
a
s
b
e
e
n
h
y
b
rid
ize
d
with
sta
n
d
a
l
o
n
e
M
L
a
n
d
DL
m
o
d
e
ls.
T
h
e
m
o
d
e
l
re
a
d
s
t
h
e
p
e
rm
issio
n
-
b
a
se
d
d
a
ta
i
n
c
l
o
u
d
,
fo
ll
o
we
d
b
y
v
u
l
n
e
ra
b
il
i
ty
p
re
d
icti
o
n
c
a
rrie
d
o
u
t
b
y
h
y
b
ri
d
iza
ti
o
n
o
f
RL
a
n
d
lo
g
isti
c
re
g
re
ss
io
n
(LR)
.
F
u
rth
e
r,
R
L
is
i
n
teg
ra
ted
wit
h
d
e
e
p
n
e
u
ra
l
n
e
two
rk
(DN
N)
fo
r
e
x
p
l
o
rin
g
a
se
c
u
re
p
a
th
to
f
a
c
il
it
a
te
d
a
ta
tran
sm
issio
n
.
Th
e
p
ro
p
o
se
d
m
o
d
e
l
witn
e
ss
e
d
9
7
.
9
%
a
c
c
u
ra
c
y
,
6
7
.
3
5
%
o
f
h
i
g
h
e
r
a
c
c
u
ra
c
y
,
5
5
.
1
4
%
o
f
re
d
u
c
e
d
late
n
c
y
,
a
n
d
5
2
.
5
4
%
o
f
f
a
ste
r
re
sp
o
n
se
ti
m
e
in
c
o
n
tras
t
t
o
b
a
se
li
n
e
s.
K
ey
w
o
r
d
s
:
Ar
tific
ial
in
tellig
en
ce
Dee
p
lear
n
in
g
Han
d
h
eld
d
ev
ice
I
n
ter
n
et
o
f
th
in
g
s
Ma
ch
in
e
lear
n
in
g
R
ein
f
o
r
ce
m
en
t le
ar
n
i
n
g
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
:
Pu
s
h
p
a
R
ajp
u
t N
ar
ay
an
a
Sin
g
h
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
,
GM
I
n
s
titu
te
o
f
T
ec
h
n
o
lo
g
y
P B
R
o
ad
,
Dav
an
g
er
e
5
7
7
0
0
6
,
I
n
d
ia
E
m
ail:
p
u
s
h
p
a@
jn
n
ce
.
ac
.
in
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
m
ajo
r
ity
o
f
th
e
ap
p
licati
o
n
s
h
o
s
ted
in
in
te
r
n
et
of
th
i
n
g
s
(
I
o
T
)
a
r
e
m
a
n
ag
ed
b
y
a
d
ed
icate
d
h
an
d
h
el
d
d
ev
ice
wh
ic
h
co
n
s
i
s
ten
tly
k
ee
p
s
o
n
ac
q
u
ir
in
g
d
ef
in
itiv
e
d
ata,
s
u
b
ject
th
em
to
p
r
o
ce
s
s
in
g
,
a
n
d
ex
ch
an
g
e
th
em
ac
co
r
d
in
g
l
y
[
1
]
.
Su
c
h
f
o
r
m
o
f
d
ata
b
ea
r
v
a
r
io
u
s
h
ig
h
er
-
v
alu
ed
co
n
f
id
en
t
ial
in
f
o
r
m
atio
n
a
n
d
th
is
lead
th
em
to
attr
ac
t
atten
tio
n
o
f
d
if
f
er
en
t
s
ca
les
o
f
an
attac
k
er
.
C
o
n
v
en
tio
n
al
en
cr
y
p
tio
n
-
b
ased
s
o
lu
tio
n
will
b
e
h
ea
v
y
-
weig
h
te
d
a
p
p
li
ca
tio
n
o
f
r
eso
u
r
ce
-
lim
ited
I
o
T
h
an
d
h
eld
d
ev
ice
an
d
h
e
n
ce
li
g
h
tweig
h
t
-
s
o
lu
tio
n
is
s
ee
k
ed
f
o
r
o
p
tim
al
p
er
f
o
r
m
an
ce
.
I
n
th
is
p
er
s
p
ec
tiv
e,
ar
tifi
cial
in
tellig
en
ce
(
AI
)
h
as
b
ee
n
n
o
ted
t
o
co
n
tr
ib
u
te
to
o
f
f
er
a
p
r
o
ac
tiv
e
s
ec
u
r
ity
s
o
lu
tio
n
with
an
aid
o
f
v
ar
io
u
s
alg
o
r
ith
m
s
m
ec
h
an
ized
b
y
m
ac
h
in
e
lear
n
in
g
(
ML
)
an
d
d
ee
p
lear
n
in
g
(
DL
)
.
T
h
e
AI
-
ce
n
tr
ic
s
ec
u
r
ity
s
o
lu
tio
n
m
o
d
ellin
g
o
f
f
e
r
s
s
ig
n
if
ican
t
s
u
p
p
o
r
ta
b
ilit
y
o
f
r
ea
l
-
tim
e
th
r
ea
t m
o
n
ito
r
in
g
,
h
i
g
h
er
ad
a
p
tiv
en
ess
,
an
d
i
n
cr
ea
s
ed
in
co
r
p
o
r
atio
n
o
f
i
n
tellig
en
c
e
[
2
]
.
Var
io
u
s
r
elate
d
wo
r
k
h
as
b
e
en
s
tu
d
ied
to
war
d
s
r
ea
lizin
g
th
e
ef
f
ec
tiv
e
n
ess
o
f
ex
is
tin
g
s
y
s
tem
.
E
x
is
tin
g
ap
p
r
o
ac
h
es
h
as
b
ee
n
n
o
ted
to
u
s
e
r
ein
f
o
r
ce
m
en
t
lea
r
n
in
g
(
R
L
)
m
o
d
els
to
war
d
s
ad
ap
tin
g
th
e
s
ec
u
r
it
y
p
o
licies
in
a
d
y
n
a
m
ic
m
an
n
e
r
f
r
o
m
leth
al
th
r
ea
ts
in
I
o
T
[
3
]
–
[
6
]
.
E
x
is
tin
g
s
tu
d
ies
h
av
e
a
ls
o
n
o
ted
u
s
ag
e
o
f
lo
g
is
tic
r
eg
r
ess
io
n
(
L
R
)
to
w
ar
d
s
class
if
icatio
n
o
f
eith
er
ac
tio
n
s
o
r
in
co
m
i
n
g
d
ata
as
r
eg
u
lar
o
r
attac
k
e
r
u
tili
zin
g
f
aster
an
d
s
im
p
ler
b
o
u
n
d
ar
ies
o
f
lin
ea
r
d
ec
is
io
n
[
7
]
–
[
1
1
]
.
R
an
d
o
m
f
o
r
es
t
(
R
F)
is
n
o
ted
to
b
e
im
p
lem
en
ted
in
s
tan
d
alo
n
e
a
s
well
as
in
en
s
em
b
led
ap
p
r
o
ac
h
f
o
r
i
d
en
tify
in
g
in
tr
u
s
io
n
u
s
in
g
v
o
tin
g
o
f
d
ec
is
io
n
tr
ee
f
o
r
en
ca
p
s
u
latin
g
d
iv
e
r
s
if
ied
p
atter
n
s
ass
o
ciate
d
with
d
e
v
ice
ac
tiv
ity
[
1
2
]
–
[
1
9
]
.
Dee
p
n
e
u
r
al
n
etwo
r
k
(
DNN)
b
ased
s
tr
ate
g
ic
s
ec
u
r
ity
s
o
lu
tio
n
h
as
also
b
ee
n
n
o
ted
to
war
d
s
lear
n
i
n
g
h
ig
h
-
d
im
e
n
s
io
n
al
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
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
4
9
7
-
1
5
0
4
1498
r
ep
r
esen
tatio
n
o
f
n
etwo
r
k
b
eh
av
io
r
f
o
r
d
ete
r
m
in
in
g
s
u
b
tle
f
o
r
m
s
o
f
v
u
ln
e
r
ab
ilit
ies
[
2
0
]
–
[
2
2
]
.
E
x
is
tin
g
s
tu
d
ies
h
av
e
also
im
p
lem
en
te
d
lo
n
g
s
h
o
r
t
-
ter
m
m
em
o
r
y
(
L
STM
)
f
o
r
id
e
n
tify
in
g
v
ar
io
u
s
f
o
r
m
s
o
f
an
o
m
alies
o
r
in
tr
u
d
er
s
em
er
g
in
g
i
n
I
o
T
[
2
3
]
–
[
2
5
]
.
T
h
e
r
esear
ch
p
r
o
b
lem
s
ass
o
ci
ated
with
ex
is
tin
g
liter
atu
r
es
ar
e
as
f
o
llo
ws
.
Firs
t,
alm
o
s
t
m
ajo
r
ity
o
f
ex
is
tin
g
s
o
lu
tio
n
s
h
a
v
e
b
ee
n
d
esig
n
b
ased
o
n
k
n
o
wn
b
eh
a
v
io
r
o
f
a
n
in
tr
u
d
er
wh
ich
is
n
o
t
ap
p
licab
le
wh
en
ex
p
o
s
ed
to
u
n
s
ee
n
a
d
v
er
s
ar
ial
en
v
ir
o
n
m
e
n
t
.
Seco
n
d
,
a
n
I
o
T
h
an
d
h
eld
d
ev
ice
h
as
less
er
m
em
o
r
y
an
d
less
er
p
r
o
ce
s
s
in
g
ca
p
a
b
ilit
ies
wh
ich
d
o
esn
’
t
ju
s
tifie
s
its
s
u
p
p
o
r
tab
ilit
y
to
war
d
s
h
o
s
tin
g
a
n
y
o
f
h
ig
h
l
y
-
claim
ed
ML
/DL
m
o
d
els
f
r
o
m
liter
atu
r
es
.
T
h
ir
d
,
th
er
e
ar
e
less
er
d
eg
r
ee
o
f
in
n
o
v
ativ
en
ess
ass
o
ciate
d
with
way
th
e
ML
/DL
m
o
d
els
ar
e
im
p
lem
e
n
ted
in
eith
e
r
s
tan
d
alo
n
e
o
r
in
en
s
em
b
led
m
eth
o
d
th
at
d
o
esn
’
t
o
f
f
er
m
o
r
e
co
m
p
etitiv
e
ed
g
e
to
wa
r
d
s
lev
er
ag
in
g
s
ec
u
r
ity
.
Fo
u
r
th
,
alm
o
s
t
n
o
n
e
o
f
ex
is
tin
g
s
o
lu
tio
n
is
claim
ed
to
p
r
esen
t
an
y
ac
tio
n
a
b
le
s
o
lu
tio
n
af
te
r
t
h
r
ea
t d
etec
tio
n
wh
ic
h
co
m
p
letely
ig
n
o
r
es
d
em
an
d
o
f
d
ata
tr
a
n
s
m
is
s
io
n
f
o
r
I
o
T
.
T
h
e
aim
o
f
t
h
e
p
r
o
p
o
s
ed
s
tu
d
y
is
to
in
t
r
o
d
u
ce
a
r
o
b
u
s
t
s
ec
u
r
ity
f
r
am
ewo
r
k
f
o
r
m
u
lated
b
y
a
d
is
tin
ct
h
y
b
r
id
izatio
n
o
f
R
L
m
o
d
el
m
ea
n
t
ex
p
licitly
f
o
r
d
eter
m
in
e
t
h
e
em
er
g
i
n
g
th
r
ea
ts
in
I
o
T
h
a
n
d
h
eld
d
ev
ices.
T
h
e
v
alu
e
-
ad
d
e
d
co
n
tr
i
b
u
tio
n
o
f
s
tu
d
y
is
as
f
o
llo
ws
.
First,
th
e
s
tu
d
y
p
r
esen
ts
a
th
r
ee
-
lay
er
ed
ar
ch
itectu
r
e
th
at
is
ca
p
ab
le
o
f
s
tr
u
ctu
r
in
g
p
er
m
is
s
io
n
-
in
f
o
r
m
atio
n
f
o
llo
wed
b
y
p
r
ed
ictio
n
o
f
t
h
r
ea
ts
an
d
e
x
p
lo
r
atio
n
o
f
s
ec
u
r
ed
r
o
u
tes
.
Seco
n
d
,
th
e
m
o
d
el
in
t
r
o
d
u
ce
s
a
n
o
v
el
m
ec
h
an
is
m
to
war
d
s
r
a
n
k
in
g
v
u
ln
er
ab
ilit
y
f
o
r
o
p
tim
izin
g
th
e
co
n
tain
m
en
t
m
et
h
o
d
f
o
r
p
r
o
a
ctiv
e
th
r
ea
ts
.
T
h
ir
d
,
R
L
is
h
y
b
r
id
ized
b
y
L
R
f
o
r
ex
p
l
o
r
in
g
ad
v
er
s
ar
ies
with
o
u
t
s
ac
r
if
icin
g
co
m
m
u
n
icatio
n
p
e
r
f
o
r
m
a
n
ce
,
wh
ile
R
L
is
also
h
y
b
r
i
d
ized
with
DL
ar
ch
ite
ctu
r
e
f
o
r
e
x
p
lo
r
in
g
co
m
m
u
n
icatio
n
r
o
u
tes with
m
in
im
al
v
u
ln
er
a
b
ilit
ies.
2.
M
E
T
H
O
D
T
h
e
p
r
o
p
o
s
ed
s
y
s
tem
i
n
tr
o
d
u
ce
s
an
in
n
o
v
ativ
e
h
y
b
r
id
ize
d
an
aly
tical
f
r
am
ew
o
r
k
h
ar
n
ess
in
g
th
e
p
o
ten
tial
o
f
R
L
to
war
d
s
s
ec
u
r
in
g
th
e
I
o
T
d
e
v
ices
f
r
o
m
all
t
h
e
v
u
ln
er
ab
le
f
o
r
m
s
o
f
tr
af
f
ic
s
y
s
tem
s
.
Fig
u
r
e
1
h
ig
h
lig
h
ts
th
e
ar
c
h
itectu
r
e
e
x
h
ib
itin
g
m
u
lti
-
s
tag
e
lear
n
in
g
,
wh
ich
in
v
o
lv
es
th
e
ac
q
u
is
itio
n
o
f
k
n
o
wled
g
e
b
ased
o
n
s
p
an
n
i
n
g
p
er
m
is
s
io
n
,
v
u
ln
er
a
b
ilit
y
p
r
ed
ictio
n
b
ased
o
n
R
L
,
an
d
o
p
tim
izatio
n
o
f
a
s
af
er
r
o
u
te.
T
h
e
id
ea
tio
n
o
f
p
r
o
p
o
s
ed
a
r
ch
itec
tu
r
e
is
to
war
d
s
id
en
tify
i
n
g
th
e
m
o
s
t
v
u
ln
er
ab
le
an
d
d
y
n
a
m
ic
f
o
r
m
o
f
th
r
ea
t
f
o
llo
win
g
b
y
p
r
o
v
id
in
g
th
em
an
alter
n
ativ
e
tr
a
n
s
m
is
s
io
n
r
o
u
te.
T
h
e
k
ey
b
en
ef
it
lies
in
p
a
r
allel
co
m
p
lian
ce
o
f
s
ec
u
r
ity
o
p
er
atio
n
s
as
well
as
d
ata
tr
an
s
m
is
s
io
n
b
y
h
an
d
h
e
ld
d
ev
ices
in
an
I
o
T
.
T
h
e
co
m
p
lete
o
p
er
atio
n
is
ca
r
r
ied
o
u
t b
y
p
er
f
o
r
m
in
g
s
eq
u
en
tial a
n
d
m
u
ltip
le
o
p
e
r
atio
n
al
m
o
d
u
les
,
wh
ich
a
r
e
d
is
cu
s
s
ed
as f
o
llo
ws
.
S
u
p
e
r
m
a
t
r
i
x
(
C
l
o
u
d
L
a
y
e
r
)
P
e
r
m
i
s
s
i
o
n
v
e
c
t
o
r
s
D
u
a
l
C
u
r
a
t
e
d
L
i
s
t
T
r
a
f
f
i
c
-
D
e
r
i
v
e
d
F
e
a
t
u
r
e
S
t
o
r
e
P
e
r
m
i
s
s
i
o
n
-
s
t
a
t
e
A
n
a
l
y
t
i
c
a
l
M
o
d
e
l
V
u
l
n
e
r
a
b
l
e
R
o
u
t
e
P
r
e
d
i
c
t
i
o
n
O
p
t
i
m
i
z
a
t
i
o
n
o
f
S
e
c
u
r
e
R
o
u
t
e
D
e
c
i
s
i
o
n
P
e
r
m
i
s
s
i
o
n
v
e
c
t
o
r
s
T
h
r
e
a
t
D
i
s
c
r
e
t
i
o
n
F
u
n
c
t
i
o
n
C
o
m
p
u
t
e
S
i
m
i
l
a
r
i
t
y
s
c
o
r
e
s
R
e
f
e
r
e
n
c
e
M
o
d
e
l
(
B
/
W
)
G
e
n
e
r
a
t
e
s
t
a
t
e
D
e
f
i
n
e
s
t
a
t
e
s
p
a
c
e
D
e
f
i
n
e
A
c
t
i
o
n
s
p
a
c
e
D
e
f
i
n
e
R
e
w
a
r
d
s
p
a
c
e
R
L
P
r
e
d
i
c
t
e
d
v
u
l
n
e
r
a
b
i
l
i
t
y
p
r
o
b
a
b
i
l
i
t
y
L
R
I
d
e
n
t
i
f
i
c
a
t
i
o
n
o
f
v
u
l
n
e
r
a
b
l
e
r
o
u
t
e
s
R
a
n
k
i
n
g
R
L
M
o
b
i
l
e
N
e
t
U
p
d
a
t
e
s
p
a
c
e
G
e
n
e
r
a
t
e
S
e
c
u
r
e
P
a
t
h
Fig
u
r
e
1
.
Ar
c
h
itectu
r
e
o
f
th
e
p
r
o
p
o
s
ed
s
y
s
tem
2
.
1
.
P
er
m
is
s
io
n
-
s
t
a
t
e
a
na
ly
t
i
ca
l m
o
del
T
h
is
is
th
e
f
ir
s
t
co
r
e
im
p
l
em
en
tatio
n
m
o
d
u
le
r
esp
o
n
s
i
b
le
f
o
r
ag
g
r
eg
atin
g
,
s
tr
u
ctu
r
in
g
,
a
n
d
tr
an
s
f
o
r
m
in
g
all
p
er
m
is
s
io
n
-
b
ased
b
eh
a
v
io
r
al
an
d
tr
af
f
ic
in
f
o
r
m
atio
n
in
to
a
u
s
ab
le
f
o
r
m
f
o
r
an
aly
tical
p
r
o
ce
s
s
in
g
.
All
th
e
p
er
m
is
s
io
n
-
o
r
ien
ted
i
n
f
o
r
m
atio
n
is
ag
g
r
e
g
ated
f
r
o
m
I
o
T
h
a
n
d
h
eld
d
ev
i
ce
wh
er
e
th
e
t
y
p
es
o
f
in
f
o
r
m
atio
n
co
llected
ar
e
tr
af
f
ic
ch
ar
ac
ter
is
tics
,
in
ter
ac
tio
n
p
atter
n
s
,
an
d
ac
ce
s
s
ca
p
ab
ilit
ies.
All
th
i
s
in
f
o
r
m
atio
n
is
s
to
r
ed
in
a
s
u
p
er
m
atr
ix
,
wh
ich
is
a
f
o
r
m
o
f
s
tr
u
ctu
r
ed
s
to
r
ag
e
u
n
it
h
o
s
ted
with
in
clo
u
d
ec
o
s
y
s
tem
.
C
o
n
s
id
er
1
,
2
,
…
,
r
ep
r
e
s
en
t
th
e
f
ea
s
ib
le
s
et
o
f
p
er
m
is
s
io
n
s
i.e
.
,
=
{
1
,
2
,
…
,
}
ass
o
ciate
d
with
an
I
o
T
h
an
d
h
eld
d
e
v
ice.
Ass
u
m
e
b
e
s
p
ec
if
ic
ap
p
licatio
n
th
at
is
ch
ar
ac
ter
ized
b
y
p
er
m
is
s
io
n
v
ec
to
r
v
em
p
ir
icall
y
r
ep
r
esen
ted
as
in
(
1
)
.
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
A
r
ein
fo
r
ce
men
t
-
g
u
id
ed
m
u
lti
-
p
h
a
s
e
h
yb
r
id
a
r
ch
itectu
r
e
fo
r
th
r
ea
t
…
(
P
u
s
h
p
a
R
a
jp
u
t Na
r
a
ya
n
a
S
i
n
g
h
)
1499
=
[
1
,
2
,
…
,
]
W
h
er
e,
=
{
1
0
ℎ
(
1
)
T
h
e
s
tu
d
y
c
o
n
s
id
er
s
th
e
p
r
esen
ce
o
f
wh
itelis
t
(
W
)
an
d
b
lack
lis
t
(
B
)
as
two
r
ef
er
en
ce
m
o
d
e
ls
p
r
esen
t
with
in
th
e
s
u
p
er
m
atr
ix
.
T
h
is
c
u
r
ated
in
f
o
r
m
atio
n
o
f
B
an
d
W
ar
e
s
to
r
ed
an
d
m
ain
tain
ed
i
n
a
s
u
p
er
m
atr
ix
th
at
is
b
ased
o
n
th
e
p
atter
n
s
o
f
h
is
to
r
ical
b
eh
av
i
o
r
.
Similar
ity
s
co
r
es a
r
e
d
ef
in
e
d
f
o
r
th
em
em
p
ir
ically
in
(
2
)
.
(
)
=
|
1
|
|
|
,
(
)
=
|
2
|
|
|
(
2
)
W
h
er
e
th
e
v
ar
iab
le
1
an
d
2
is
m
ath
em
atica
lly
r
ep
r
esen
ted
as
(
∩
)
an
d
(
∩
)
r
esp
ec
tiv
ely
.
Af
ter
th
e
in
f
o
r
m
atio
n
is
ag
g
r
eg
ated
f
r
o
m
th
e
d
u
al
cu
r
ated
lis
t,
th
i
s
m
o
d
u
le
s
tr
u
ct
u
r
ize
th
e
m
i
n
to
a
m
atr
ix
-
b
ased
r
ep
r
esen
tatio
n
f
o
r
s
eg
r
eg
atin
g
n
o
r
m
al
b
eh
av
i
o
r
f
r
o
m
p
at
ter
n
s
in
v
o
lv
in
g
tr
ac
es
o
f
att
ac
k
s
.
An
em
p
ir
ical
d
ef
in
itio
n
o
f
th
r
ea
t
d
is
cr
etio
n
f
u
n
ctio
n
is
as
in
(
3
)
.
(
)
=
{
0
(
)
≥
1
(
)
≥
2
ℎ
(
3
)
W
h
er
e
th
e
s
co
r
e
o
f
0
,
1
,
an
d
2
will
r
ep
r
esen
ts
b
en
ig
n
,
m
alicio
u
s
,
an
d
s
u
s
p
icio
u
s
(
b
u
t
n
o
t
c
o
n
f
ir
m
e
d
)
.
Fu
r
th
er
,
an
d
r
ep
r
esen
t
th
e
ac
ce
p
ted
c
u
t
-
o
f
f
f
o
r
class
if
y
in
g
wh
itelis
t
(
W
)
an
d
cu
t
-
o
f
f
f
o
r
lab
ellin
g
b
lack
lis
t
n
o
d
e
(
B
)
,
r
esp
ec
tiv
ely
.
T
h
is
m
o
d
u
l
e
is
al
s
o
r
esp
o
n
s
ib
le
f
o
r
y
ield
i
n
g
th
e
s
tate
o
f
R
L
in
f
o
r
m
o
f
=
{
,
(
)
,
}
,
wh
er
e
th
e
en
tity
f
i
r
ep
r
esen
ts
th
e
f
ea
tu
r
e
r
elate
d
to
tr
a
f
f
ic
(
v
i
z.
d
ev
ice
in
ter
ac
tio
n
,
en
tr
o
p
y
,
an
d
p
ac
k
et
r
ate)
.
2
.
2
.
Vuln
er
a
ble
ro
ute
predict
io
n
T
h
e
o
u
tco
m
e
o
f
t
h
e
p
r
io
r
o
p
e
r
atio
n
m
o
d
u
le
g
en
er
ates
tr
a
f
f
ic
f
ea
tu
r
es
wh
ich
ac
ts
lik
e
an
in
p
u
t
f
o
r
th
is
m
o
d
u
le
,
wh
ic
h
is
m
ea
n
t
f
o
r
d
e
ter
m
in
in
g
th
e
s
p
ec
if
ics
o
f
co
m
m
u
n
icatio
n
r
o
u
tes
with
p
ea
k
s
ec
u
r
ity
th
r
ea
t
to
o
r
f
r
o
m
th
e
p
ar
ticu
lar
I
o
T
d
ev
ic
e.
T
h
is
m
o
d
u
le
p
er
f
o
r
m
s
th
e
u
n
if
icatio
n
o
f
R
L
an
d
L
R
to
war
d
s
p
r
ed
ictio
n
o
f
v
u
ln
er
ab
ilit
y
ass
o
ciate
d
with
th
e
ML
m
o
d
el.
T
h
e
s
y
s
tem
ch
o
o
s
es
L
R
f
o
r
its
h
i
g
h
er
in
ter
p
r
etab
ilit
y
a
n
d
co
n
s
u
m
p
tio
n
o
f
lo
w
r
eso
u
r
ce
s
.
T
h
e
s
tate
s
p
ac
e
is
d
ef
in
ed
as
2
=
{
1
,
}
wh
er
e
th
e
b
eh
av
io
r
al
an
d
tr
af
f
ic
f
ea
tu
r
e
v
ec
to
r
is
r
ep
r
esen
te
d
b
y
v
ar
ia
b
le
X
.
T
h
e
ac
tio
n
s
p
ac
e
is
r
ep
r
esen
te
d
as
A
2
={
in
s
p
ec
t
,
m
ar
k
v
u
ln
er
a
b
le,
an
d
ig
n
o
r
e}
,
wh
ile
r
ewa
r
d
f
u
n
ctio
n
is
r
ep
r
esen
ted
as
in
(
4
)
.
2
(
,
)
=
{
+
1
−
1
0
(
4
)
T
h
e
tr
an
s
itio
n
m
o
d
el
2
(
`
|
,
)
is
d
ef
i
n
ed
b
y
alter
atio
n
s
ass
o
ciate
d
with
th
e
lik
elih
o
o
d
o
f
th
r
ea
t
af
ter
ea
ch
ac
tio
n
.
I
t
is
to
b
e
n
o
ted
t
h
at
p
r
o
b
a
b
ilis
tic
f
ee
d
b
ac
k
is
y
ield
e
d
b
y
th
is
m
o
d
el
,
ass
o
ciate
d
with
th
e
p
o
s
s
ib
ilit
y
th
at
an
I
o
T
h
an
d
h
e
ld
d
ev
ice
is
v
u
l
n
er
ab
le
to
p
o
t
en
tial
cy
b
er
th
r
ea
ts
.
T
h
is
f
ee
d
b
ac
k
is
u
s
ed
b
y
R
L
f
o
r
r
ef
in
i
n
g
its
p
r
o
ce
s
s
o
f
d
ec
i
s
io
n
-
m
ak
in
g
t
h
at
f
ac
ilit
ates
th
e
m
o
d
el
to
lear
n
p
o
ten
tial
f
ea
t
u
r
es
an
d
its
r
o
le
in
ex
h
ib
itin
g
r
is
k
y
b
eh
a
v
io
r
.
T
h
e
m
o
d
el
th
e
n
im
p
lem
en
ts
L
R
,
wh
ich
is
r
ep
r
esen
ted
as
in
(
5
)
.
̂
=
(
+
)
(
5
)
I
n
(
5
)
co
n
s
is
ts
o
f
co
m
p
u
tatio
n
o
f
th
e
p
r
o
b
ab
ilit
y
o
f
a
n
I
o
T
h
an
d
h
eld
d
ev
ice
b
ein
g
v
u
ln
e
r
ab
le
̂
b
ased
o
n
in
p
u
t
ar
g
u
m
e
n
ts
o
f
th
e
s
ig
m
o
id
f
u
n
cti
o
n
σ
(
.
)
,
f
ea
tu
r
e
v
e
cto
r
X
.
I
t
also
in
v
o
lv
es
m
o
d
el
p
ar
am
eter
s
(
w
,
b
)
r
ep
r
esen
tin
g
weig
h
ts
an
d
b
ia
s
es
,
r
esp
ec
tiv
ely
.
T
h
e
m
o
d
el
im
p
lem
en
ts
a
v
u
ln
er
ab
ilit
y
r
an
k
in
g
m
ec
h
an
is
m
wh
er
e
th
e
v
u
ln
er
ab
ilit
y
s
co
r
e
is
em
p
ir
ically
d
ef
in
ed
in
(
6
)
.
=
.
̂
+
ℎ
1
+
ℎ
2
(
6
)
I
n
(
6
)
,
th
e
c
o
m
p
u
tatio
n
o
f
th
e
v
u
ln
er
ab
ilit
y
s
co
r
e
is
ca
r
r
ied
o
u
t
b
y
a
d
d
itio
n
o
f
th
r
ee
co
m
p
o
n
en
ts
.
T
h
e
f
ir
s
t
co
m
p
o
n
e
n
t
r
ep
r
esen
ts
th
e
p
r
o
d
u
ct
o
f
weig
h
in
g
p
ar
am
et
er
an
d
p
r
o
b
ab
ilit
y
o
f
p
r
ed
icte
d
v
u
ln
er
a
b
ilit
y
̂
.
T
h
e
s
ec
o
n
d
co
m
p
o
n
en
t
ℎ
1
r
ep
r
e
s
en
ts
th
e
p
r
o
d
u
ct
o
f
weig
h
in
g
p
ar
am
eter
1
an
d
(
1
−
(
)
)
wh
ile
th
e
th
ir
d
co
m
p
o
n
en
t
ℎ
2
r
ep
r
esen
ts
p
r
o
d
u
ct
o
f
weig
h
in
g
p
ar
a
m
eter
2
an
d
(
)
.
T
h
e
r
an
k
i
n
g
o
f
th
e
I
o
T
h
an
d
h
eld
d
ev
ice
is
ca
r
r
ied
o
u
t
as
=
(
)
.
T
h
e
o
u
tco
m
e
o
f
th
is
m
o
d
u
le
is
m
ain
ly
two
-
f
o
l
d
d
eter
m
in
atio
n
o
f
v
u
ln
er
ab
le
I
o
T
h
an
d
h
eld
d
e
v
ice
(
)
an
d
r
an
k
lis
t o
f
p
o
t
e
n
tially
th
r
ea
t
-
p
r
o
n
e
co
m
m
u
n
icatio
n
ch
an
n
els (
).
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
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
4
9
7
-
1
5
0
4
1500
2
.
3
.
O
pti
m
iza
t
io
n
o
f
s
ec
ure
ro
ute
decisi
o
n
T
h
is
m
o
d
u
le
ex
ten
d
s
th
e
p
r
io
r
o
p
er
atio
n
b
y
f
ac
ilit
atin
g
an
alter
n
ativ
e
s
ec
u
r
e
r
o
u
te
f
o
r
d
ata
tr
an
s
m
is
s
io
n
,
ch
o
o
s
in
g
co
m
m
u
n
icatio
n
ch
an
n
els
th
at
ar
e
e
m
p
ir
ically
co
n
f
ir
m
e
d
to
h
av
e
th
e
lo
west
th
r
ea
ts
.
T
h
is
m
o
d
u
le
u
n
if
ies a
h
ig
h
l
y
co
m
p
ac
t a
r
ch
itectu
r
e
o
f
a
DL
k
n
o
wn
as M
o
b
ileNet
with
R
L
f
o
r
ca
r
r
y
in
g
o
u
t th
is
o
p
er
atio
n
.
T
h
e
s
tate
v
ar
iab
le
i
s
d
ef
in
ed
as
3
=
{
2
,
}
wh
er
e
th
e
n
etw
o
r
k
g
r
ap
h
is
r
e
p
r
esen
ted
as
G
,
wh
ile
ac
tio
n
is
r
ep
r
esen
ted
as
A
3
={
s
elec
t
n
ex
t
h
o
p
(
n
i
)|
n
i
∈
n
eig
h
b
o
r
s
}.
T
h
e
r
ewa
r
d
R
3
(
s
,
a
)
is
in
d
ex
ed
as
+5
,
-
5
,
+1
0
,
an
d
-
10
,
r
ep
r
esen
tin
g
a
s
ec
u
r
e
h
o
p
lead
i
n
g
to
a
d
esti
n
atio
n
n
o
d
e
,
a
h
o
p
lead
in
g
to
a
v
u
ln
er
ab
le
n
o
d
e
,
a
co
m
p
leted
s
ec
u
r
e
d
r
o
u
te
s
u
cc
ess
f
u
lly
,
an
d
a
d
etec
ted
attac
k
o
r
b
lo
ck
ed
r
o
u
te
o
f
tr
a
n
s
m
is
s
io
n
.
T
h
e
s
ec
u
r
ity
p
r
ed
ictio
n
f
o
r
I
o
T
h
an
d
h
eld
d
ev
ice
̂
=
(
)
,
wh
er
e
th
e
v
alu
atio
n
o
f
̂
r
an
g
es
to
[
0
,
1
]
.
T
h
er
ef
o
r
e,
it
ca
n
b
e
s
ee
n
th
at
Mo
b
ileNet
is
u
s
ed
f
o
r
ass
ess
in
g
wh
ich
I
o
T
h
an
d
h
eld
d
e
v
ice
is
f
o
u
n
d
s
ec
u
r
e
f
o
r
r
o
u
tin
g
.
T
h
is
DL
-
b
ased
p
r
ed
ictio
n
is
u
tili
ze
d
b
y
R
L
f
o
r
s
elec
tin
g
th
e
co
n
s
ec
u
tiv
e
o
p
tim
al
h
o
p
s
at
ev
e
r
y
p
o
in
t
o
f
d
ec
is
io
n
.
An
em
p
ir
ical
f
o
r
m
u
latio
n
o
f
t
h
e
s
ec
u
r
e
r
o
u
te
s
co
r
e
is
s
h
o
wn
in
(
7
)
.
(
ℎ
)
=
∑
̂
=
1
−
wh
er
e
=
∑
=
1
(
7
)
Af
ter
th
e
ex
p
r
ess
io
n
(
7
)
is
co
m
p
u
ted
,
th
e
ac
co
m
p
lis
h
ed
SR
(
p
ath
)
is
u
s
ed
f
o
r
f
in
d
in
g
th
e
o
p
tim
al
s
ec
u
r
e
r
o
u
te
as
=
[
(
ℎ
)
]
.
Hen
ce
,
th
e
m
o
d
u
le
is
p
r
o
g
r
ess
iv
e
to
b
e
h
ig
h
ly
in
tellig
en
t
in
r
esis
tin
g
all
v
u
ln
e
r
ab
le
a
r
ea
s
wh
ich
it
ca
n
e
f
f
ec
tiv
ely
d
eter
m
in
e
th
e
b
est
s
ec
u
r
e
d
d
ata
tr
a
n
s
m
is
s
io
n
ch
an
n
els.
T
h
e
n
o
v
elty
o
f
th
is
m
o
d
u
le
is
th
e
p
r
o
ac
tiv
e
s
elec
tio
n
o
f
s
ec
u
r
e
r
o
u
tes
d
ep
en
d
in
g
u
p
o
n
r
ea
l
-
tim
e
p
r
ed
ictio
n
o
f
DL
an
d
p
atter
n
s
o
f
lear
n
ed
b
eh
av
io
r
.
T
h
is
s
tr
ateg
y
co
m
p
l
etely
d
if
f
er
s
f
r
o
m
ex
is
tin
g
s
o
lu
tio
n
wh
er
e
s
tatic
r
o
u
tin
g
ta
b
les o
r
b
lo
c
k
in
g
m
ec
h
an
is
m
b
ased
o
n
th
r
ea
ts
h
av
e
b
ee
n
u
tili
ze
d
.
3.
RE
SU
L
T
S
AND
D
I
SCU
SS
I
O
N
A
s
p
ec
if
ic
an
d
h
ig
h
ly
c
o
n
tr
o
l
led
r
esear
ch
en
v
ir
o
n
m
e
n
t
h
as
b
ee
n
ch
o
s
en
in
o
r
d
e
r
to
ca
r
r
y
o
u
t
th
e
im
p
lem
en
tatio
n
o
f
t
h
e
p
r
o
p
o
s
ed
s
tu
d
y
m
o
d
el.
T
h
is
s
ec
tio
n
d
is
cu
s
s
es
th
e
r
atio
n
ale
o
f
t
h
e
d
ataset
ad
o
p
ted
f
o
llo
wed
b
y
th
e
ad
o
p
tio
n
o
f
an
en
v
ir
o
n
m
e
n
t
to
ca
r
r
y
o
u
t
an
ass
ess
m
en
t.
T
h
e
ass
ess
m
en
t
claim
s
th
e
ef
f
ec
tiv
en
ess
o
f
th
e
p
r
o
p
o
s
ed
m
o
d
el
b
ased
o
n
th
e
ac
co
m
p
lis
h
ed
r
esu
lt
th
at
is
also
d
is
cu
s
s
ed
in
th
is
s
ec
tio
n
f
o
r
b
etter
in
s
ig
h
t.
3
.
1
.
Da
t
a
s
et
a
do
ptio
n
T
h
e
im
p
lem
e
n
tatio
n
o
f
th
e
p
r
o
p
o
s
ed
s
y
s
tem
is
ca
r
r
ied
o
u
t
co
n
s
id
er
in
g
E
d
g
e
-
I
I
o
T
s
et
d
at
aset
[
2
6
]
.
T
h
e
d
ataset
co
n
s
is
t
s
o
f
r
aw
p
ac
k
et
tr
ac
es
o
f
tr
af
f
ic
ac
q
u
ir
ed
f
r
o
m
s
m
ar
t
-
h
o
m
e
h
a
n
d
h
eld
co
n
tr
o
ller
s
,
s
u
r
v
eillan
ce
ca
m
er
as,
s
m
ar
tp
h
o
n
e
,
an
d
R
asp
b
er
r
y
Pi d
e
v
ices.
T
h
e
p
r
im
e
r
ea
s
o
n
f
o
r
ad
o
p
tin
g
th
is
d
ataset
is
th
e
in
clu
s
io
n
o
f
m
ax
im
u
m
n
u
m
b
e
r
s
o
f
tr
af
f
ic
f
ea
tu
r
es
in
c
o
n
tr
a
s
t
to
o
th
er
ex
is
tin
g
d
atasets
f
o
r
s
im
ilar
p
u
r
p
o
s
es.
T
h
er
e
ar
e
6
1
tr
af
f
ic
f
ea
tu
r
es
ex
tr
ac
ted
v
iz.
en
tr
o
p
y
v
alu
es
,
f
lag
d
is
tr
ib
u
tio
n
,
in
te
r
-
ar
r
iv
a
l
tim
e,
p
ac
k
et
s
ize,
f
lo
w
d
u
r
atio
n
,
an
d
m
etad
ata
o
n
s
ig
n
atu
r
es a
s
s
o
ciate
d
with
co
m
m
u
n
icatio
n
o
f
h
an
d
h
eld
I
o
T
d
ev
ices.
3
.
2
.
E
nv
iro
nm
ent
a
do
pte
d in sim
ula
t
io
n
Fro
m
th
e
p
er
s
p
ec
tiv
e
o
f
h
ar
d
war
e
ad
o
p
tio
n
,
th
e
im
p
lem
e
n
tatio
n
ch
o
o
s
es
to
u
s
e
I
n
tel
i5
u
n
it
as
C
PU
with
3
2
GB
DD4
R
AM
an
d
1
T
B
o
f
s
to
r
ag
e
i
n
6
4
-
b
i
t
win
d
o
ws
m
ac
h
in
e.
Fu
r
th
e
r
,
f
r
o
m
a
s
o
f
twar
e
in
v
o
lv
em
e
n
t
p
er
s
p
ec
tiv
e,
t
h
e
s
cr
ip
tin
g
is
ca
r
r
ied
o
u
t
u
s
in
g
Py
th
o
n
lib
r
ar
ies
s
u
ch
as
T
en
s
o
r
Flo
w,
Pan
d
as,
Nu
m
Py
,
an
d
s
cik
it
-
lear
n
,
wh
il
e
th
e
v
er
if
icatio
n
o
f
f
ea
tu
r
e
e
x
tr
ac
tio
n
is
co
n
d
u
cted
u
s
in
g
C
I
C
Flo
wM
e
ter
.
T
h
e
an
aly
s
is
o
f
th
e
p
ac
k
et
is
ca
r
r
i
ed
o
u
t
u
s
in
g
W
ir
esh
ar
k
.
T
h
e
h
y
p
er
p
ar
am
eter
s
an
d
t
h
eir
v
al
u
es
ar
e
as
f
o
llo
ws:
t
h
e
s
cr
ip
t
in
v
o
lv
es
ch
o
o
s
in
g
0
.
0
0
0
4
as
th
e
lear
n
in
g
r
ate,
1
2
8
b
atch
s
ize,
an
d
1
0
0
e
p
o
ch
.
T
h
e
ex
p
lo
r
atio
n
r
ate
d
ec
ay
is
0
.
9
9
2
wh
ile
0
.
9
1
is
co
n
s
id
er
ed
as
t
h
e
d
is
co
u
n
t
f
a
cto
r
co
n
s
id
er
in
g
4
h
id
d
en
lay
er
s
.
R
ec
tifie
d
lin
ea
r
u
n
it
(
R
eL
U)
a
n
d
So
f
tMa
x
is
c
h
o
s
en
as
ac
tiv
atio
n
f
u
n
ctio
n
s
,
wh
ile
Ad
am
o
p
tim
izer
is
u
s
ed
with
1
5
,
0
0
0
r
ep
lay
b
u
f
f
er
s
ize.
3
.
3
.
Achiev
ed
re
s
ult
T
h
e
ac
co
m
p
lis
h
ed
o
u
tco
m
e
o
f
th
e
s
tu
d
y
is
co
m
p
a
r
ed
with
m
u
ltip
le
b
aselin
e
m
o
d
els
v
iz.
co
n
v
en
tio
n
al
L
R
m
o
d
el,
c
o
n
v
en
tio
n
al
R
L
m
o
d
el,
R
F
m
o
d
e
l,
an
d
DNN.
T
h
e
a
n
aly
s
is
is
ca
r
r
ied
o
u
t
in
d
u
al
p
er
s
p
ec
tiv
e
v
iz.
,
esti
m
atio
n
b
ased
o
n
ac
c
u
r
ac
y
p
er
f
o
r
m
an
ce
(
T
ab
le
1
)
a
n
d
esti
m
atio
n
b
ased
o
n
co
m
m
u
n
icatio
n
p
er
f
o
r
m
a
n
ce
(
T
ab
le
2
)
.
T
h
e
o
u
tco
m
e
o
f
T
ab
le
1
s
h
o
wca
s
es
th
at
p
r
o
p
o
s
ed
s
tu
d
y
m
o
d
el
o
f
f
er
s
m
ax
im
u
m
s
tr
en
g
t
h
o
f
a
d
v
er
s
ar
y
d
etec
tio
n
wh
ile
it
is
s
h
o
wn
m
ax
im
u
m
r
esil
ien
t
ag
ain
s
t
th
e
f
o
llo
win
g
ad
v
er
s
ar
ies
v
iz.
b
o
tn
et
-
r
elate
d
tr
af
f
ic,
r
ec
o
n
n
aiss
an
ce
,
p
ac
k
et
in
jectio
n
,
s
p
o
o
f
in
g
,
m
an
-
in
-
th
e
-
m
id
d
le
attac
k
,
an
d
d
is
tr
ib
u
ted
d
en
ial
-
of
-
s
er
v
i
ce
(
DDo
S).
Similar
ly
,
th
e
n
u
m
er
ical
o
u
tco
m
e
ex
h
i
b
ited
in
T
ab
le
2
r
ep
r
esen
ts
a
h
ig
h
er
th
r
o
u
g
h
p
u
t c
ap
ab
ilit
y
o
f
th
e
p
r
o
p
o
s
ed
m
o
d
el
alo
n
g
wi
th
m
in
im
al
laten
cy
a
n
d
r
e
d
u
ce
d
r
esp
o
n
s
e
tim
e.
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
A
r
ein
fo
r
ce
men
t
-
g
u
id
ed
m
u
lti
-
p
h
a
s
e
h
yb
r
id
a
r
ch
itectu
r
e
fo
r
th
r
ea
t
…
(
P
u
s
h
p
a
R
a
jp
u
t Na
r
a
ya
n
a
S
i
n
g
h
)
1501
T
ab
le
1
.
E
s
tim
ated
ac
cu
r
ac
y
p
er
f
o
r
m
a
n
ce
in
b
e
n
ch
m
a
r
k
an
al
y
s
is
M
o
d
e
l
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
(
%)
Ex
i
s
t
i
n
g
b
a
s
e
l
i
n
e
m
o
d
e
l
s
LR
8
2
.
7
8
1
.
2
8
0
.
9
8
1
.
0
RF
8
9
.
4
8
8
.
1
8
7
.
6
8
7
.
9
RL
9
0
.
6
8
9
.
4
8
8
.
9
8
9
.
1
DNN
9
2
.
3
9
1
.
5
9
0
.
7
9
1
.
1
P
r
o
p
o
se
d
m
o
d
e
l
9
7
.
9
9
7
.
3
9
6
.
8
9
7
.
0
T
ab
le
2
.
E
s
tim
ated
co
m
m
u
n
ic
atio
n
p
er
f
o
r
m
an
ce
in
b
e
n
ch
m
a
r
k
an
aly
s
is
M
o
d
e
l
Th
r
o
u
g
h
p
u
t
(
sam
p
l
e
s/
se
c
)
La
t
e
n
c
y
(
ms)
R
e
s
p
o
n
se
t
i
me
(
ms)
Ex
i
s
t
i
n
g
b
a
s
e
l
i
n
e
m
o
d
e
l
s
LR
3
8
0
36
54
RF
4
6
0
29
48
RL
5
3
0
23
41
DNN
5
9
0
19
34
P
r
o
p
o
se
d
m
o
d
el
8
2
0
12
21
3
.
4
.
Dis
cus
s
io
n
T
h
e
s
tu
d
y
o
u
tco
m
e
s
h
o
ws
s
o
m
e
in
ter
esti
n
g
p
atter
n
s
as
e
x
h
ib
ited
in
Fig
u
r
e
2
.
Fig
u
r
e
s
2
(
a
)
an
d
2
(
b
)
r
ep
r
esen
ts
o
u
tc
o
m
e
r
elate
d
to
ac
cu
r
ac
y
an
d
th
r
o
u
g
h
p
u
t
,
r
es
p
ec
tiv
ely
.
T
h
e
e
x
h
ib
its
o
f
Fig
u
r
e
s
2
(
c)
an
d
2
(
d
)
r
ep
r
esen
t la
ten
cy
a
n
d
r
esp
o
n
s
e
tim
e
,
r
esp
ec
tiv
ely
.
(
a)
(
b
)
(
c)
(
d
)
Fig
u
r
e
2
.
Gr
a
p
h
ical
o
u
tco
m
e
o
f
b
en
ch
m
ar
k
a
n
aly
s
is
of
(
a)
ac
cu
r
ac
y
s
co
r
es
,
(
b
)
th
r
o
u
g
h
p
u
t
,
(
c)
,
laten
cy
,
an
d
(
d
)
r
esp
o
n
s
e
tim
e
Fro
m
th
e
e
x
h
ib
its
o
f
Fig
u
r
e
2
(
a)
,
it
ca
n
b
e
s
ee
n
th
at
th
e
p
r
o
p
o
s
ed
s
y
s
tem
h
as
ac
co
m
p
lis
h
ed
9
7
.
9
%
o
f
d
etec
tio
n
ac
cu
r
ac
y
wh
ich
is
m
ain
ly
attr
ib
u
ted
f
o
r
in
clu
s
i
o
n
o
f
d
y
n
am
ic
m
u
lti
-
m
o
d
u
le
ad
ap
tatio
n
an
d
it
d
o
esn
’
t
co
n
s
id
er
a
n
y
s
tatic
s
ig
n
atu
r
es
,
wh
ich
is
s
ee
n
u
s
u
ally
in
ex
is
tin
g
ap
p
r
o
a
ch
es.
I
t
s
h
o
ws
an
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
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
4
9
7
-
1
5
0
4
1502
ac
co
m
p
lis
h
m
en
t
o
f
9
7
.
3
%
p
r
ec
is
io
n
wh
ich
m
ea
n
s
th
er
e
is
ex
tr
em
ely
f
ew
o
cc
u
r
r
e
n
ce
s
o
f
o
u
tlier
s
.
T
h
is
o
u
tco
m
e
tr
e
n
d
ca
n
b
e
attr
ib
u
ted
b
y
is
o
latio
n
ca
p
ab
ilit
y
o
f
th
e
m
o
d
el
to
war
d
s
p
atter
n
s
o
f
n
o
is
e
u
s
u
all
y
g
en
er
ated
b
y
I
o
T
h
an
d
h
eld
d
ev
ices.
T
h
e
o
u
tco
m
e
s
h
o
ws
th
e
p
r
o
p
o
s
ed
s
y
s
tem
to
ac
h
ie
v
e
9
6
.
8
%
o
f
r
ec
all
,
ex
h
ib
itin
g
p
o
ten
tial
d
etec
tio
n
ca
p
ab
ilit
y
ag
ai
n
s
t
tr
u
e
attac
k
s
wh
ich
is
r
ein
f
o
r
ce
d
b
y
in
v
o
lv
em
en
t
o
f
p
atter
n
lear
n
in
g
o
f
tem
p
o
r
al
f
lo
w.
I
t
s
h
o
ws
9
7
%
o
f
F1
-
s
co
r
e
ac
c
o
m
p
lis
h
ed
f
o
r
p
r
o
p
o
s
ed
m
o
d
el
ex
h
ib
itin
g
h
ig
h
ly
b
alan
ce
d
p
e
r
f
o
r
m
an
ce
wh
ich
is
d
u
e
to
p
ar
allel
u
n
if
icatio
n
o
f
r
ea
ctiv
e
an
d
p
r
ed
ictiv
e
a
n
aly
s
is
.
Fig
u
r
e
2
(
b
)
s
h
o
wca
s
es
th
e
p
r
o
p
o
s
ed
m
o
d
el
to
ac
co
m
p
lis
h
8
2
0
s
am
p
les
p
e
r
s
ec
o
n
d
wh
ich
is
n
o
ted
to
b
e
th
e
m
ax
im
ized
th
r
o
u
g
h
p
u
t
am
o
n
g
all
th
e
b
aselin
e
m
o
d
els.
T
h
e
o
u
tco
m
e
o
f
th
is
tr
e
n
d
ca
n
b
e
r
ea
s
o
n
ed
with
m
u
lti
-
th
r
ea
d
ed
o
p
tim
ized
in
f
e
r
en
ce
an
d
ex
ec
u
tio
n
in
th
e
p
r
o
p
o
s
ed
m
o
d
el.
T
h
e
p
r
o
p
o
s
ed
s
y
s
tem
is
n
o
ted
to
o
f
f
er
o
n
l
y
1
2
m
s
o
f
laten
cy
as
s
ee
n
in
Fig
u
r
e
2
(
c)
wh
ich
is
d
r
asti
ca
lly
b
etter
in
co
n
t
r
ast
to
an
y
ex
is
tin
g
b
aselin
e
m
o
d
els
.
T
h
e
p
r
im
e
r
ea
s
o
n
f
o
r
t
h
is
is
a
s
tr
ateg
ic
ac
ce
s
s
p
atter
n
with
m
em
o
r
y
e
f
f
icien
cy
a
n
d
lig
h
tweig
h
t
p
r
e
d
ictio
n
o
f
atta
ck
.
Fin
ally
,
Fig
u
r
e
2
(
d
)
s
h
o
ws
o
n
ly
2
1
m
s
o
f
r
esp
o
n
s
e
tim
e
wh
ich
is
h
ig
h
ly
r
ed
u
ce
d
in
co
n
tr
ast
to
o
th
er
m
o
d
els.
T
h
e
o
u
tco
m
e
s
h
o
ws
it
s
h
ig
h
in
clin
atio
n
to
war
d
s
p
o
ten
tial
th
r
ea
t
m
itig
atio
n
.
T
h
e
p
r
im
e
r
ea
s
o
n
f
o
r
th
is
is
f
aster
ev
alu
atio
n
o
f
s
tate
an
d
s
ig
n
if
ican
tly
r
ed
u
ce
d
b
u
f
f
er
i
n
g
.
3
.
5
.
No
v
elt
y
o
f
s
t
ud
y
W
h
ile
ad
o
p
tio
n
o
f
b
aselin
e
m
o
d
els
is
witn
es
s
ed
to
b
e
u
s
ed
f
o
r
r
esis
tin
g
a
p
r
io
r
i
ad
v
e
r
s
ar
ies
o
r
a
s
et
o
f
k
n
o
w
n
ad
v
er
s
ar
ies,
th
e
p
r
o
p
o
s
ed
m
o
d
el
is
d
esig
n
ed
co
n
s
id
er
in
g
lack
o
f
a
n
y
a
p
r
io
r
i
in
f
o
r
m
atio
n
o
f
th
e
th
r
ea
ts
.
T
ab
le
3
s
h
o
wca
s
es
th
e
p
o
ten
tial
ca
p
a
b
ilit
y
o
f
p
r
o
p
o
s
ed
s
y
s
tem
,
wh
er
e
it’s
ex
h
ib
ited
to
s
h
o
w
its
r
esil
ien
ce
f
r
o
m
ze
r
o
-
d
ay
attac
k
s
ap
ar
t
f
r
o
m
o
t
h
er
s
tan
d
ar
d
f
o
r
m
o
f
s
tan
d
ar
d
attac
k
s
f
r
e
q
u
e
n
tly
r
e
p
o
r
ted
.
Ap
ar
t
f
r
o
m
th
is
,
it
is
also
ca
p
ab
le
o
f
r
esis
tin
g
p
er
m
is
s
io
n
-
m
is
u
s
e
at
tack
s
,
p
o
ly
m
o
r
p
h
ic
a
n
d
a
d
ap
ti
v
e
f
o
r
m
o
f
th
r
ea
ts
,
an
d
later
al
m
o
v
em
en
t a
ttack
s
.
T
ab
le
3
.
E
s
tim
ated
co
m
m
u
n
ic
atio
n
p
er
f
o
r
m
an
ce
in
b
e
n
ch
m
a
r
k
an
aly
s
is
A
t
t
r
i
b
u
t
e
Ex
i
s
t
i
n
g
b
a
s
e
l
i
n
e
s
P
r
o
p
o
se
d
m
o
d
e
l
RL
LR
RF
LSTM
A
b
i
l
i
t
y
f
o
r
t
h
r
e
a
t
c
a
t
e
g
o
r
i
z
a
t
i
o
n
No
No
No
G
o
o
d
P
o
t
e
n
t
i
a
l
p
r
o
f
i
l
i
n
g
c
a
p
a
b
i
l
i
t
y
f
o
r
mu
l
t
i
-
d
i
me
n
s
i
o
n
a
l
a
t
t
a
c
k
e
r
s
Ze
r
o
-
d
a
y
a
t
t
a
c
k
s
P
o
o
r
e
x
p
l
o
r
a
t
i
o
n
N
o
t
c
a
p
a
b
l
e
Li
mi
t
e
d
g
e
n
e
r
a
l
i
z
a
t
i
o
n
M
o
d
e
r
a
t
e
S
u
p
e
r
i
o
r
a
d
a
p
t
i
v
e
e
x
p
l
o
r
a
t
i
o
n
,
su
p
p
o
r
t
i
v
e
o
f
a
d
v
e
r
sar
i
a
l
si
mu
l
a
t
i
o
n
st
u
d
y
R
e
s
p
o
n
s
i
v
e
n
e
ss
H
i
g
h
Lo
w
M
o
d
e
r
a
t
e
V
e
r
y
h
i
g
h
V
e
r
y
l
o
w
(
d
u
e
t
o
t
r
a
n
si
t
i
o
n
l
o
g
i
c
o
f
o
p
t
i
m
i
z
e
d
st
a
t
e
)
S
u
i
t
a
b
i
l
i
t
y
t
o
I
o
T
e
d
g
e
n
o
d
e
s
Lo
w
-
mo
d
e
r
a
t
e
H
i
g
h
M
o
d
e
r
a
t
e
M
o
d
e
r
a
t
e
V
e
r
y
h
i
g
h
(
d
u
e
t
o
l
i
g
h
t
w
e
i
g
h
t
o
p
t
i
m
i
z
a
t
i
o
n
)
4.
CO
NCLU
SI
O
N
T
h
e
p
r
o
p
o
s
e
d
s
tu
d
y
i
n
tr
o
d
u
c
e
s
a
n
in
n
o
v
a
t
i
v
e
s
e
c
u
r
i
t
y
f
r
a
m
e
wo
r
k
f
o
r
s
ec
u
r
in
g
I
o
T
h
a
n
d
h
e
l
d
d
e
v
i
ce
s
a
d
o
p
t
i
n
g
t
w
o
d
i
f
f
e
r
en
t
h
y
b
r
id
v
ar
i
an
t
s
o
f
R
L
m
o
d
e
l
i
t
s
e
l
f
.
T
h
e
m
o
d
e
l
i
s
c
a
p
ab
l
e
o
f
r
e
s
i
s
t
i
n
g
b
o
th
k
n
o
wn
a
n
d
u
n
k
n
o
wn
f
o
r
m
o
f
t
h
r
e
a
t
s
in
n
e
t
wo
r
k
la
y
er
s
.
I
t
d
o
e
s
s
o
b
y
co
m
b
i
n
in
g
s
u
p
e
r
m
a
t
r
i
x
w
i
th
p
e
r
m
i
s
s
i
o
n
i
n
f
o
r
m
a
t
io
n
i
n
to
a
d
a
p
t
iv
e
d
ec
i
s
i
o
n
-
m
ak
i
n
g
s
t
r
a
t
e
g
y
b
y
R
L
,
f
i
l
t
er
i
n
g
b
y
l
ig
h
t
w
e
i
g
h
t
M
L
a
n
d
r
o
u
te
r
ef
i
n
em
e
n
t
u
s
i
n
g
D
L
.
A
s
e
l
f
-
o
p
t
i
m
i
z
ed
an
d
h
o
l
i
s
t
i
c
s
t
r
u
c
t
u
r
e
h
a
s
b
e
en
p
r
e
s
e
n
t
ed
i
n
p
r
o
p
o
s
e
d
s
tu
d
y
t
h
a
t
ca
n
o
p
e
r
a
t
e
o
v
er
d
i
f
f
e
r
en
t
s
t
a
t
e
s
o
f
co
m
m
u
n
ic
a
t
i
o
n
d
y
n
a
m
i
c
s
f
a
c
i
l
i
ta
t
i
n
g
th
e
a
g
en
t
s
t
o
co
n
s
i
s
t
e
n
t
ly
r
e
a
l
i
z
e
th
e
u
p
d
at
e
d
tr
a
f
f
i
c
s
t
at
e
f
o
l
lo
w
e
d
b
y
id
e
n
t
if
i
c
a
t
io
n
o
f
v
u
l
n
e
r
ab
l
e
r
o
u
t
e
s
an
d
e
x
p
lo
r
i
n
g
s
a
f
er
r
o
u
t
e
s
.
T
h
e
s
tu
d
y
o
u
t
co
m
e
s
h
o
w
s
o
p
t
i
m
a
l
p
e
r
f
o
r
m
a
n
c
e
f
o
r
p
r
o
p
o
s
e
d
s
t
u
d
y
m
o
d
e
l
i
n
c
o
n
t
r
a
s
t
t
o
e
x
i
s
t
i
n
g
b
a
s
e
l
i
n
e
m
o
d
e
l
s
.
T
h
e
f
u
t
u
r
e
wo
r
k
c
a
n
b
e
i
n
i
t
i
at
e
d
t
o
w
ar
d
s
im
p
r
o
v
in
g
t
h
e
p
r
iv
a
c
y
p
r
e
s
e
r
v
a
t
io
n
b
y
f
u
r
t
h
e
r
i
n
c
o
r
p
o
r
a
t
in
g
f
ed
er
a
t
e
d
l
e
ar
n
in
g
i
n
t
h
e
cu
r
r
e
n
t
s
t
a
t
e
o
f
m
o
d
e
l
.
F
u
r
t
h
e
r
,
an
en
er
g
y
o
p
t
im
iz
e
d
m
o
d
e
l
l
in
g
c
an
b
e
c
ar
r
i
ed
o
u
t
t
o
wa
r
d
s
en
s
u
r
in
g
en
h
an
c
em
e
n
t
o
f
l
if
e
s
p
an
o
f
b
a
t
t
e
r
y
-
o
p
er
a
t
ed
h
an
d
h
e
ld
I
o
T
d
e
v
ic
e
.
Fu
t
u
r
e
w
o
r
k
c
an
b
e
a
l
s
o
c
ar
r
i
ed
o
u
t
t
o
w
a
r
d
s
in
v
o
l
v
em
e
n
t
b
lo
c
k
c
h
a
i
n
t
e
ch
n
o
l
o
g
y
f
o
r
ev
o
lv
in
g
tr
u
s
t
s
co
r
e
s
in
m
o
d
e
l
t
o
o
f
f
er
an
o
p
t
i
m
a
l
s
e
cu
r
i
t
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
.
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
A
r
ein
fo
r
ce
men
t
-
g
u
id
ed
m
u
lti
-
p
h
a
s
e
h
yb
r
id
a
r
ch
itectu
r
e
fo
r
th
r
ea
t
…
(
P
u
s
h
p
a
R
a
jp
u
t Na
r
a
ya
n
a
S
i
n
g
h
)
1503
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
P
u
s
h
p
a
R
a
j
p
u
t
N
a
r
a
y
a
n
a
S
i
n
g
h
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
N
e
e
l
a
m
b
i
k
e
S
i
d
d
a
l
i
n
g
a
ia
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
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.
I
NF
O
RM
E
D
CO
NS
E
N
T
T
h
is
s
ec
tio
n
n
o
t
ap
p
licab
le
.
T
h
is
s
tu
d
y
d
id
n
o
t
in
v
o
lv
e
a
n
y
h
u
m
an
s
u
b
jects,
p
e
r
s
o
n
al
id
en
tifia
b
le
in
f
o
r
m
atio
n
,
o
r
s
ce
n
ar
i
o
s
r
eq
u
ir
in
g
in
d
iv
id
u
al
in
f
o
r
m
ed
co
n
s
en
t,
as
it
ex
clu
s
iv
ely
u
tili
ze
d
p
u
b
licly
av
ailab
le
d
atasets
,
co
m
p
u
tatio
n
al
s
im
u
l
atio
n
s
,
an
d
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
s
with
o
u
t
b
r
ea
c
h
in
g
p
r
iv
ac
y
r
ig
h
ts
o
r
n
ec
ess
itatin
g
wr
itten
p
er
m
is
s
i
o
n
s
f
r
o
m
p
ar
ticip
an
ts
.
E
T
H
I
CAL AP
P
RO
V
AL
T
h
is
s
ec
tio
n
n
o
t
ap
p
licab
le.
T
h
e
r
esear
ch
c
o
m
p
lied
with
all
r
elev
an
t
in
s
titu
tio
n
al
p
o
licies
b
u
t
d
id
n
o
t
in
v
o
lv
e
h
u
m
a
n
s
u
b
jects
o
r
a
n
im
al
u
s
e,
r
ely
i
n
g
s
o
lely
o
n
n
o
n
-
b
io
lo
g
ical
co
m
p
u
tatio
n
a
l
m
eth
o
d
s
s
u
ch
as
o
p
tim
izatio
n
alg
o
r
ith
m
s
a
n
d
d
ata
an
aly
s
is
,
th
u
s
ex
e
m
p
t
f
r
o
m
r
ev
iew
b
y
an
i
n
s
titu
tio
n
al
r
ev
iew
b
o
ar
d
,
et
h
ics
co
m
m
ittee,
o
r
a
d
h
er
e
n
ce
to
th
e
Helsin
k
i D
ec
lar
atio
n
.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
ata
th
at
s
u
p
p
o
r
t
th
e
f
in
d
i
n
g
s
o
f
th
is
s
tu
d
y
ar
e
av
ailab
le
f
r
o
m
th
e
co
r
r
esp
o
n
d
in
g
au
th
o
r
[
PR
NS]
,
u
p
o
n
r
ea
s
o
n
ab
le
r
eq
u
est.
RE
F
E
R
E
NC
E
S
[
1
]
A
.
S
h
a
r
m
a
a
n
d
K
.
B
h
u
s
h
a
n
,
“
A
c
o
mp
r
e
h
e
n
si
v
e
su
r
v
e
y
o
n
I
o
T
s
e
c
u
r
i
t
y
:
c
h
a
l
l
e
n
g
e
s
,
se
c
u
r
i
t
y
i
ss
u
e
s,
a
n
d
c
o
u
n
t
e
r
m
e
a
s
u
r
e
s,
”
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
Re
v
i
e
w
,
v
o
l
.
5
9
,
2
0
2
6
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
sr
e
v
.
2
0
2
5
.
1
0
0
8
3
9
.
[
2
]
K
.
D
u
b
e
y
,
R
.
D
u
b
e
y
,
S
.
P
a
n
e
d
y
,
a
n
d
S
.
K
u
m
a
r
,
“
A
r
e
v
i
e
w
o
f
I
o
T
se
c
u
r
i
t
y
:
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
p
e
r
sp
e
c
t
i
v
e
,
”
Pro
c
e
d
i
a
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
2
3
5
,
p
p
.
3
3
5
–
3
4
6
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
r
o
c
s.
2
0
2
4
.
0
4
.
0
3
4
.
[
3
]
M
.
M
o
u
y
a
r
t
,
G
.
M
.
M
a
c
h
a
d
o
,
a
n
d
J.
Y
.
Ju
n
,
“
A
m
u
l
t
i
-
a
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
o
p
t
i
m
i
z
e
d
b
y
a
d
e
e
p
r
e
i
n
f
o
r
c
e
m
e
n
t
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
w
i
t
h
a
d
a
t
a
s
e
t
e
n
l
a
r
g
e
d
u
si
n
g
a
g
e
n
e
r
a
t
i
v
e
mo
d
e
l
t
o
r
e
d
u
c
e
t
h
e
b
i
a
s
e
f
f
e
c
t
,
”
J
o
u
r
n
a
l
o
f
S
e
n
so
r
a
n
d
Ac
t
u
a
t
o
r
N
e
t
w
o
rks
,
v
o
l
.
1
2
,
n
o
.
5
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
j
sa
n
1
2
0
5
0
0
6
8
.
[
4
]
J.
A
.
S
h
a
i
k
h
e
t
a
l
.
,
“
A
d
e
e
p
r
e
i
n
f
o
r
c
e
me
n
t
l
e
a
r
n
i
n
g
-
b
a
s
e
d
r
o
b
u
s
t
i
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
s
y
st
e
m
f
o
r
se
c
u
r
i
n
g
I
o
M
T
h
e
a
l
t
h
c
a
r
e
n
e
t
w
o
r
k
s,”
Fr
o
n
t
i
e
rs
i
n
Me
d
i
c
i
n
e
,
v
o
l
.
1
2
,
2
0
2
5
,
d
o
i
:
1
0
.
3
3
8
9
/
f
m
e
d
.
2
0
2
5
.
1
5
2
4
2
8
6
.
[
5
]
K
.
R
e
n
,
Y
.
Ze
n
g
,
Y
.
Z
h
o
n
g
,
B
.
S
h
e
n
g
,
a
n
d
Y
.
Zh
a
n
g
,
“
M
A
F
S
I
D
S
:
a
r
e
i
n
f
o
r
c
e
m
e
n
t
l
e
a
r
n
i
n
g
-
b
a
se
d
i
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
mo
d
e
l
f
o
r
mu
l
t
i
-
a
g
e
n
t
f
e
a
t
u
r
e
s
e
l
e
c
t
i
o
n
n
e
t
w
o
r
k
s,”
J
o
u
r
n
a
l
o
f
Bi
g
D
a
t
a
,
v
o
l
.
1
0
,
n
o
.
1
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
8
6
/
s
4
0
5
3
7
-
023
-
0
0
8
1
4
-
4.
[
6
]
C
.
M
a
h
j
o
u
b
,
M
.
H
a
md
i
,
R
.
I
.
A
l
k
a
n
h
e
l
,
S
.
M
o
h
a
me
d
,
a
n
d
R
.
Ej
b
a
l
i
,
“
A
n
a
d
v
e
r
sar
i
a
l
e
n
v
i
r
o
n
m
e
n
t
r
e
i
n
f
o
r
c
e
me
n
t
l
e
a
r
n
i
n
g
-
d
r
i
v
e
n
i
n
t
r
u
s
i
o
n
d
e
t
e
c
t
i
o
n
a
l
g
o
r
i
t
h
m
f
o
r
i
n
t
e
r
n
e
t
o
f
t
h
i
n
g
s,
”
Eu
r
a
si
p
J
o
u
rn
a
l
o
n
Wi
re
l
e
ss
C
o
m
m
u
n
i
c
a
t
i
o
n
s
a
n
d
N
e
t
w
o
rki
n
g
,
v
o
l
.
2
0
2
4
,
n
o
.
1
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
8
6
/
s
1
3
6
3
8
-
0
2
4
-
0
2
3
4
8
-
6.
[
7
]
V
.
S
,
“
L
o
g
i
st
i
c
r
e
g
r
e
ss
i
o
n
w
i
t
h
e
l
l
i
p
t
i
c
a
l
c
u
r
v
e
c
r
y
p
t
o
g
r
a
p
h
y
t
o
e
st
a
b
l
i
s
h
sec
u
r
e
I
o
T,
”
S
S
R
N
El
e
c
t
ro
n
i
c
J
o
u
rn
a
l
,
2
0
2
5
,
d
o
i
:
1
0
.
2
1
3
9
/
s
sr
n
.
5
2
1
9
8
5
9
.
[
8
]
S
.
C
h
a
l
i
c
h
a
l
a
m
a
l
a
,
N
.
G
o
v
i
n
d
a
n
,
a
n
d
R
.
K
a
sar
a
p
u
,
“
L
o
g
i
st
i
c
r
e
g
r
e
ssi
o
n
e
n
s
e
mb
l
e
c
l
a
ssi
f
i
e
r
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
i
n
t
e
r
n
e
t
o
f
t
h
i
n
g
s
,
”
S
e
n
s
o
rs
,
v
o
l
.
2
3
,
n
o
.
2
3
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
s
2
3
2
3
9
5
8
3
.
[
9
]
D
.
G
l
a
d
i
ć
,
J.
P
e
t
r
o
v
a
č
k
i
,
S
.
S
l
a
d
o
j
e
v
i
ć
,
M
.
A
r
se
n
o
v
i
ć
,
a
n
d
S
.
R
i
s
t
i
ć
,
“
A
n
a
l
y
s
i
s
o
f
d
i
f
f
e
r
e
n
t
I
D
S
-
b
a
sed
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
mo
d
e
l
s
f
o
r
sec
u
r
e
d
a
t
a
t
r
a
n
sm
i
ss
i
o
n
i
n
I
o
T
n
e
t
w
o
r
k
s,”
O
p
e
n
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
1
5
,
n
o
.
1
,
2
0
2
5
,
d
o
i
:
1
0
.
1
5
1
5
/
c
o
m
p
-
2
0
2
5
-
0
0
3
2
.
[
1
0
]
A
.
H
a
f
i
d
,
M
.
R
a
h
o
u
t
i
,
a
n
d
M
.
A
l
e
d
h
a
r
i
,
“
O
p
t
i
m
i
z
i
n
g
i
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
i
n
I
o
M
T
n
e
t
w
o
r
k
s
t
h
r
o
u
g
h
i
n
t
e
r
p
r
e
t
a
b
l
e
a
n
d
c
o
st
-
a
w
a
r
e
mac
h
i
n
e
l
e
a
r
n
i
n
g
,
”
Ma
t
h
e
m
a
t
i
c
s
,
v
o
l
.
1
3
,
n
o
.
1
0
,
2
0
2
5
,
d
o
i
:
1
0
.
3
3
9
0
/
ma
t
h
1
3
1
0
1
5
7
4
.
[
1
1
]
K
.
R
a
h
ma
n
e
t
a
l
.
,
“
C
o
g
n
i
t
i
v
e
l
i
g
h
t
w
e
i
g
h
t
l
o
g
i
s
t
i
c
r
e
g
r
e
ssi
o
n
-
b
a
s
e
d
I
D
S
f
o
r
I
o
T
-
e
n
a
b
l
e
d
F
A
N
ET
t
o
d
e
t
e
c
t
c
y
b
e
r
a
t
t
a
c
k
s,
”
M
o
b
i
l
e
I
n
f
o
rm
a
t
i
o
n
S
y
st
e
m
s
,
v
o
l
.
2
0
2
3
,
p
p
.
1
–
1
1
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
3
/
7
6
9
0
3
2
2
.
[
1
2
]
O
.
Z.
A
k
i
f
,
S
.
M
.
A
l
i
,
A
.
F
.
S
a
b
i
h
,
A
.
T.
S
a
d
i
q
,
a
n
d
S
.
K
.
S
u
b
r
a
m
a
n
i
a
m
,
“
I
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
s
y
st
e
m
f
o
r
I
o
T
b
a
sed
o
n
m
o
d
i
f
i
e
d
r
a
n
d
o
m
f
o
r
e
st
a
l
g
o
r
i
t
h
m
,
”
I
ra
q
i
J
o
u
r
n
a
l
f
o
r
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
Ma
t
h
e
m
a
t
i
c
s
,
v
o
l
.
6
,
n
o
.
2
,
p
p
.
2
2
1
–
2
2
9
,
2
0
2
5
,
d
o
i
:
1
0
.
5
2
8
6
6
/
2
7
8
8
-
7
4
2
1
.
1
2
5
8
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
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
4
9
7
-
1
5
0
4
1504
[
1
3
]
V
.
P
a
i
,
K
.
P
a
i
,
S
.
M
a
n
j
u
n
a
t
h
a
,
S
.
H
i
r
met
i
,
a
n
d
V
.
V
.
B
h
a
t
,
“
A
d
a
p
t
i
v
e
n
e
t
w
o
r
k
a
n
o
m
a
l
y
d
e
t
e
c
t
i
o
n
u
si
n
g
mac
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
e
s,
”
E
u
r
a
si
p
J
o
u
r
n
a
l
o
n
I
n
f
o
rm
a
t
i
o
n
S
e
c
u
r
i
t
y
,
v
o
l
.
2
0
2
5
,
n
o
.
1
,
2
0
2
5
,
d
o
i
:
1
0
.
1
1
8
6
/
s
1
3
6
3
5
-
025
-
0
0
2
1
6
-
4.
[
1
4
]
C
.
L
u
,
Y
.
C
a
o
,
a
n
d
Z.
W
a
n
g
,
“
R
e
s
e
a
r
c
h
o
n
i
n
t
r
u
s
i
o
n
d
e
t
e
c
t
i
o
n
b
a
se
d
o
n
a
n
e
n
h
a
n
c
e
d
r
a
n
d
o
m
f
o
r
e
s
t
a
l
g
o
r
i
t
h
m
,
”
Ap
p
l
i
e
d
S
c
i
e
n
c
e
s
,
v
o
l
.
1
4
,
n
o
.
2
,
2
0
2
4
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
4
0
2
0
7
1
4
.
[
1
5
]
K
.
S
.
A
d
e
w
o
l
e
,
A
.
J
a
c
o
b
sso
n
,
a
n
d
P
.
D
a
v
i
d
s
so
n
,
“
I
n
t
r
u
s
i
o
n
d
e
t
e
c
t
i
o
n
f
r
a
mew
o
r
k
f
o
r
i
n
t
e
r
n
e
t
o
f
t
h
i
n
g
s
w
i
t
h
r
u
l
e
i
n
d
u
c
t
i
o
n
f
o
r
mo
d
e
l
e
x
p
l
a
n
a
t
i
o
n
,
”
S
e
n
so
rs
,
v
o
l
.
2
5
,
n
o
.
6
,
2
0
2
5
,
d
o
i
:
1
0
.
3
3
9
0
/
s
2
5
0
6
1
8
4
5
.
[
1
6
]
M
.
S
a
si
,
O
.
R
.
A
d
e
g
b
o
y
e
,
a
n
d
A
.
A
l
z
u
b
i
,
“
E
x
p
l
a
i
n
a
b
l
e
a
n
d
o
p
t
i
m
i
z
e
d
r
a
n
d
o
m
f
o
r
e
s
t
f
o
r
a
n
o
ma
l
y
d
e
t
e
c
t
i
o
n
i
n
I
o
T
n
e
t
w
o
r
k
s
u
si
n
g
t
h
e
R
I
M
E
me
t
a
h
e
u
r
i
s
t
i
c
,”
El
e
c
t
ro
n
i
c
s
,
v
o
l
.
1
4
,
n
o
.
2
2
,
2
0
2
5
,
d
o
i
:
1
0
.
3
3
9
0
/
e
l
e
c
t
r
o
n
i
c
s
1
4
2
2
4
4
6
5
.
[
1
7
]
H
.
A
l
r
a
k
a
h
,
Y
.
A
.
A
d
a
m,
M
.
A
b
d
a
l
r
a
h
e
e
m,
P
.
M
a
n
s
u
r
,
S
.
R
i
z
w
a
n
,
a
n
d
I
.
Al
-
S
h
o
u
r
b
a
j
i
,
“
Le
v
e
r
a
g
i
n
g
r
a
n
d
o
m
f
o
r
e
s
t
t
o
d
e
t
e
c
t
b
o
t
n
e
t
a
t
t
a
c
k
s i
n
I
o
T
e
n
v
i
r
o
n
me
n
t
s
,
”
I
n
t
e
rn
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
a
n
d
E
x
p
e
ri
m
e
n
t
a
l
S
c
i
e
n
c
e
a
n
d
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
1
1
,
n
o
.
3
,
2
0
2
5
,
d
o
i
:
1
0
.
2
2
3
9
9
/
i
j
c
e
se
n
.
3
7
1
7
.
[
1
8
]
M
.
A
l
y
a
n
d
M
.
H
.
B
e
h
i
r
y
,
“
En
h
a
n
c
i
n
g
a
n
o
m
a
l
y
d
e
t
e
c
t
i
o
n
i
n
I
o
T
-
d
r
i
v
e
n
f
a
c
t
o
r
i
e
s
u
s
i
n
g
l
o
g
i
s
t
i
c
b
o
o
st
i
n
g
,
r
a
n
d
o
m
f
o
r
e
s
t
,
a
n
d
S
V
M
:
A
c
o
mp
a
r
a
t
i
v
e
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
,
”
S
c
i
e
n
t
i
f
i
c
R
e
p
o
r
t
s
,
v
o
l
.
1
5
,
n
o
.
1
,
2
0
2
5
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
5
9
8
-
0
2
5
-
0
8
4
3
6
-
x.
[
1
9
]
J.
B
.
A
w
o
t
u
n
d
e
,
F
.
E
.
A
y
o
,
R
.
P
a
n
i
g
r
a
h
i
,
A
.
G
a
r
g
,
A
.
K
.
B
h
o
i
,
a
n
d
P
.
B
a
r
so
c
c
h
i
,
“
A
m
u
l
t
i
-
l
e
v
e
l
r
a
n
d
o
m
f
o
r
e
st
m
o
d
e
l
-
b
a
se
d
i
n
t
r
u
s
i
o
n
d
e
t
e
c
t
i
o
n
u
s
i
n
g
f
u
z
z
y
i
n
f
e
r
e
n
c
e
sy
s
t
e
m
f
o
r
i
n
t
e
r
n
e
t
o
f
t
h
i
n
g
s
n
e
t
w
o
r
k
s,”
I
n
t
e
rn
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
st
e
m
s
,
v
o
l
.
1
6
,
n
o
.
1
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s
4
4
1
9
6
-
0
2
3
-
0
0
2
0
5
-
w.
[
2
0
]
S
.
A
.
B
a
k
h
s
h
,
M
.
A
.
K
h
a
n
,
F
.
A
h
m
e
d
,
M
.
S
.
A
l
s
h
e
h
r
i
,
H
.
A
l
i
,
a
n
d
J.
A
h
ma
d
,
“
E
n
h
a
n
c
i
n
g
I
o
T
n
e
t
w
o
r
k
s
e
c
u
r
i
t
y
t
h
r
o
u
g
h
d
e
e
p
l
e
a
r
n
i
n
g
-
p
o
w
e
r
e
d
i
n
t
r
u
s
i
o
n
d
e
t
e
c
t
i
o
n
sy
st
e
m
,
”
I
n
t
e
r
n
e
t
o
f
T
h
i
n
g
s
,
v
o
l
.
2
4
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
o
t
.
2
0
2
3
.
1
0
0
9
3
6
.
[
2
1
]
M
.
A
.
H
o
ss
a
i
n
,
“
D
e
e
p
l
e
a
r
n
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
f
o
r
I
o
T
n
e
t
w
o
r
k
s
:
a
s
c
a
l
a
b
l
e
a
n
d
e
f
f
i
c
i
e
n
t
a
p
p
r
o
a
c
h
,
”
E
u
ra
si
p
J
o
u
r
n
a
l
o
n
I
n
f
o
rm
a
t
i
o
n
S
e
c
u
ri
t
y
,
v
o
l
.
2
0
2
5
,
n
o
.
1
,
2
0
2
5
,
d
o
i
:
1
0
.
1
1
8
6
/
s
1
3
6
3
5
-
0
2
5
-
0
0
2
0
2
-
w.
[
2
2
]
M
.
V
i
s
h
w
a
k
a
r
m
a
a
n
d
N
.
K
e
ssw
a
n
i
,
“
D
I
D
S
:
a
d
e
e
p
n
e
u
r
a
l
n
e
t
w
o
r
k
b
a
s
e
d
r
e
a
l
-
t
i
m
e
i
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
s
y
st
e
m
f
o
r
I
o
T,
”
D
e
c
i
s
i
o
n
An
a
l
y
t
i
c
s
J
o
u
r
n
a
l
,
v
o
l
.
5
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
d
a
j
o
u
r
.
2
0
2
2
.
1
0
0
1
4
2
.
[
2
3
]
T.
B
.
O
g
u
n
se
y
i
a
n
d
G
.
T
h
i
y
a
g
a
r
a
j
a
n
,
“
A
n
e
x
p
l
a
i
n
a
b
l
e
LSTM
-
b
a
s
e
d
i
n
t
r
u
s
i
o
n
d
e
t
e
c
t
i
o
n
sy
s
t
e
m
o
p
t
i
mi
z
e
d
b
y
f
i
r
e
f
l
y
a
l
g
o
r
i
t
h
m
f
o
r
I
o
T
n
e
t
w
o
r
k
s,”
S
e
n
so
rs
,
v
o
l
.
2
5
,
n
o
.
7
,
2
0
2
5
,
d
o
i
:
1
0
.
3
3
9
0
/
s
2
5
0
7
2
2
8
8
.
[
2
4
]
P
.
S
i
n
h
a
,
D
.
S
a
h
u
,
S
.
P
r
a
k
a
s
h
,
T
.
Y
a
n
g
,
R
.
S
.
R
a
t
h
o
r
e
,
a
n
d
V
.
K
.
P
a
n
d
e
y
,
“
A
h
i
g
h
p
e
r
f
o
r
m
a
n
c
e
h
y
b
r
i
d
L
S
T
M
C
N
N
s
e
c
u
r
e
a
r
c
h
i
t
e
c
t
u
r
e
f
o
r
I
o
T
e
n
v
i
r
o
n
m
e
n
t
s
u
s
i
n
g
d
e
e
p
l
e
a
r
n
i
n
g
,
”
S
c
i
e
n
t
i
f
i
c
R
e
p
o
r
t
s
,
v
o
l
.
1
5
,
n
o
.
1
,
2
0
2
5
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
5
9
8
-
0
2
5
-
9
4
5
0
0
-
5.
[
2
5
]
A
.
N
a
z
i
r
e
t
a
l
.
,
“
A
d
e
e
p
l
e
a
r
n
i
n
g
-
b
a
se
d
n
o
v
e
l
h
y
b
r
i
d
C
N
N
-
LST
M
a
r
c
h
i
t
e
c
t
u
r
e
f
o
r
e
f
f
i
c
i
e
n
t
d
e
t
e
c
t
i
o
n
o
f
t
h
r
e
a
t
s
i
n
t
h
e
I
o
T
e
c
o
sy
s
t
e
m
,
”
Ai
n
S
h
a
m
s
En
g
i
n
e
e
ri
n
g
J
o
u
r
n
a
l
,
v
o
l
.
1
5
,
n
o
.
7
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
se
j
.
2
0
2
4
.
1
0
2
7
7
7
.
[
2
6
]
O
.
B
.
S
a
m
i
n
,
N
.
A
.
A
.
A
l
g
e
e
l
a
n
i
,
A
.
B
a
t
h
i
c
h
,
M
.
O
mar,
M
.
M
a
n
s
o
o
r
,
a
n
d
A
.
K
h
a
n
,
“
O
p
t
i
m
i
z
i
n
g
a
g
r
i
c
u
l
t
u
r
a
l
d
a
t
a
se
c
u
r
i
t
y
:
h
a
r
n
e
ss
i
n
g
I
o
T
a
n
d
A
I
w
i
t
h
l
a
t
e
n
c
y
a
w
a
r
e
a
c
c
u
r
a
c
y
i
n
d
e
x
(
LA
A
I
)
,
”
Pe
e
r
J
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
1
0
,
p
p
.
1
–
2
2
,
2
0
2
4
,
d
o
i
:
1
0
.
7
7
1
7
/
P
EER
J
-
C
S
.
2
2
7
6
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Pu
shp
a
Ra
jp
u
t
Na
r
a
y
a
n
a
S
in
g
h
is
a
n
a
c
c
o
m
p
li
sh
e
d
a
c
a
d
e
m
ic
a
n
d
p
r
o
fe
ss
io
n
a
l
with
a
M
.
Tec
h
.
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
Ja
wa
h
a
rlal
Ne
h
ru
Ne
w
Co
ll
e
g
e
o
f
En
g
i
n
e
e
rin
g
,
S
h
imo
g
a
,
u
n
d
e
r
Vis
v
e
sv
a
ra
y
a
Tec
h
n
o
l
o
g
ica
l
U
n
iv
e
rs
it
y
,
Be
lag
a
v
i
a
n
d
a
B
.
E.
in
th
e
sa
m
e
field
fr
o
m
Ja
wa
h
a
rlal
N
e
h
ru
Ne
w
C
o
ll
e
g
e
o
f
En
g
in
e
e
rin
g
,
S
h
imo
g
a
.
S
h
e
h
a
s 1
3
y
e
a
rs
o
f
tea
c
h
in
g
e
x
p
e
rien
c
e
,
sh
e
is
c
u
r
re
n
tl
y
wo
r
k
in
g
a
s
a
n
a
ss
istan
t
p
ro
fe
ss
o
r
,
in
th
e
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
in
e
e
rin
g
a
t
Ja
wa
h
a
rlal
Ne
h
ru
Ne
w
Co
ll
e
g
e
o
f
E
n
g
i
n
e
e
rin
g
,
S
h
imo
g
a
.
He
r
e
x
p
e
rti
se
sp
a
n
s
n
e
two
rk
s,
i
n
tern
e
t
o
f
t
h
in
g
s
,
a
n
d
m
a
c
h
in
e
lea
rn
in
g
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
p
u
sh
p
a
@jn
n
c
e
.
a
c
.
in
.
Dr
.
Ne
e
la
m
b
ik
e
S
id
d
a
li
n
g
a
i
a
h
is
a
n
a
c
c
o
m
p
li
sh
e
d
a
c
a
d
e
m
ic
a
n
d
p
ro
fe
ss
io
n
a
l
with
a
P
h
.
D.
i
n
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
in
e
e
rin
g
fro
m
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.
S
h
e
h
o
ld
s
a
n
M
.
Tec
h
.
in
th
e
sa
m
e
field
fro
m
Ba
p
u
ji
In
st
it
u
te
o
f
En
g
i
n
e
e
rin
g
a
n
d
Tec
h
n
o
lo
g
y
a
n
d
a
B.
E.
in
In
f
o
rm
a
ti
o
n
S
c
ien
c
e
fr
o
m
Ja
wa
h
a
rlal
Ne
h
ru
Ne
w
Co
ll
e
g
e
o
f
En
g
i
n
e
e
rin
g
,
S
h
imo
g
a
with
o
v
e
r
1
8
y
e
a
rs
o
f
e
x
p
e
rien
c
e
,
sh
e
is
c
u
rre
n
tl
y
w
o
rk
i
n
g
a
s
a
p
ro
fe
ss
o
r
a
n
d
h
e
a
d
o
f
t
h
e
D
e
p
a
rtme
n
t
o
f
I
n
fo
rm
a
ti
o
n
S
c
ien
c
e
a
n
d
E
n
g
i
n
e
e
rin
g
a
t
G
M
In
stit
u
te
o
f
Tec
h
n
o
l
o
g
y
,
Da
v
a
n
g
e
re
.
In
a
d
d
it
i
o
n
,
sh
e
is
a
lso
p
ro
g
ra
m
d
irec
to
r
fo
r
Da
ta
En
g
i
n
e
e
rin
g
a
t
G
M
S
c
h
o
o
l
o
f
Ad
v
a
n
c
e
d
S
t
u
d
ies
,
G
M
Un
iv
e
rsity
.
He
r
e
x
p
e
rti
se
sp
a
n
s
n
e
two
rk
s,
d
a
ta
a
n
a
ly
ti
c
s,
c
lo
u
d
c
o
m
p
u
ti
n
g
,
a
rti
ficia
l
i
n
telli
g
e
n
c
e
,
a
n
d
v
e
h
ic
u
lar
a
d
h
o
c
n
e
two
rk
s.
S
h
e
h
a
s
a
lso
p
u
b
li
s
h
e
d
se
v
e
ra
l
p
a
p
e
rs
a
n
d
h
o
l
d
s
se
v
e
ra
l
p
a
ten
ts,
re
c
o
g
n
ize
d
f
o
r
h
e
r
c
o
n
tr
i
b
u
ti
o
n
s,
sh
e
re
c
e
iv
e
d
t
h
e
"
Ex
c
e
ll
e
n
t
a
n
d
in
n
o
v
a
ti
o
n
a
c
a
d
e
m
icia
n
"
a
wa
rd
a
t
in
ter
n
a
ti
o
n
a
l
c
o
n
v
e
n
ti
o
n
2
0
2
1
a
n
d
e
x
c
e
ll
e
n
t
fa
c
u
lt
y
a
wa
rd
a
t
G
M
Un
iv
e
rsit
y
2
0
2
3
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
n
e
e
lam
b
ik
e
s@
g
m
it
.
a
c
.
in
.
Evaluation Warning : The document was created with Spire.PDF for Python.